5114 files changed, 131662 insertions, 79248 deletions

diff --git a/.editorconfig b/.editorconfig
new file mode 100644
index 000000000000..854773350cc5
--- /dev/null
+++ b/.editorconfig
@@ -0,0 +1,32 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+root = true
+
+[{*.{awk,c,dts,dtsi,dtso,h,mk,s,S},Kconfig,Makefile,Makefile.*}]
+charset = utf-8
+end_of_line = lf
+trim_trailing_whitespace = true
+insert_final_newline = true
+indent_style = tab
+indent_size = 8
+
+[*.{json,py,rs}]
+charset = utf-8
+end_of_line = lf
+trim_trailing_whitespace = true
+insert_final_newline = true
+indent_style = space
+indent_size = 4
+
+# this must be below the general *.py to overwrite it
+[tools/{perf,power,rcu,testing/kunit}/**.py,]
+indent_style = tab
+indent_size = 8
+
+[*.yaml]
+charset = utf-8
+end_of_line = lf
+trim_trailing_whitespace = unset
+insert_final_newline = true
+indent_style = space
+indent_size = 2
diff --git a/.gitignore b/.gitignore
index 98274e1160d7..689a4fa3f547 100644
--- a/.gitignore
+++ b/.gitignore
@@ -96,6 +96,7 @@ modules.order
 #
 !.clang-format
 !.cocciconfig
+!.editorconfig
 !.get_maintainer.ignore
 !.gitattributes
 !.gitignore
diff --git a/.mailmap b/.mailmap
index 1f6ad79b45e4..bd9f1025ac44 100644
--- a/.mailmap
+++ b/.mailmap
@@ -191,10 +191,11 @@ Gao Xiang <xiang@kernel.org> <gaoxiang25@huawei.com>
 Gao Xiang <xiang@kernel.org> <hsiangkao@aol.com>
 Gao Xiang <xiang@kernel.org> <hsiangkao@linux.alibaba.com>
 Gao Xiang <xiang@kernel.org> <hsiangkao@redhat.com>
-Geliang Tang <geliang.tang@linux.dev> <geliang.tang@suse.com>
-Geliang Tang <geliang.tang@linux.dev> <geliangtang@xiaomi.com>
-Geliang Tang <geliang.tang@linux.dev> <geliangtang@gmail.com>
-Geliang Tang <geliang.tang@linux.dev> <geliangtang@163.com>
+Geliang Tang <geliang@kernel.org> <geliang.tang@linux.dev>
+Geliang Tang <geliang@kernel.org> <geliang.tang@suse.com>
+Geliang Tang <geliang@kernel.org> <geliangtang@xiaomi.com>
+Geliang Tang <geliang@kernel.org> <geliangtang@gmail.com>
+Geliang Tang <geliang@kernel.org> <geliangtang@163.com>
 Georgi Djakov <djakov@kernel.org> <georgi.djakov@linaro.org>
 Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@de.ibm.com>
 Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com>
@@ -289,6 +290,7 @@ Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com>
 John Crispin <john@phrozen.org> <blogic@openwrt.org>
 John Fastabend <john.fastabend@gmail.com> <john.r.fastabend@intel.com>
 John Keeping <john@keeping.me.uk> <john@metanate.com>
+John Moon <john@jmoon.dev> <quic_johmoo@quicinc.com>
 John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
 John Stultz <johnstul@us.ibm.com>
 <jon.toppins+linux@gmail.com> <jtoppins@cumulusnetworks.com>
@@ -323,6 +325,7 @@ Kenneth W Chen <kenneth.w.chen@intel.com>
 Kenneth Westfield <quic_kwestfie@quicinc.com> <kwestfie@codeaurora.org>
 Kiran Gunda <quic_kgunda@quicinc.com> <kgunda@codeaurora.org>
 Kirill Tkhai <tkhai@ya.ru> <ktkhai@virtuozzo.com>
+Kishon Vijay Abraham I <kishon@kernel.org> <kishon@ti.com>
 Konstantin Khlebnikov <koct9i@gmail.com> <khlebnikov@yandex-team.ru>
 Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com>
 Koushik <raghavendra.koushik@neterion.com>
@@ -344,6 +347,7 @@ Leonid I Ananiev <leonid.i.ananiev@intel.com>
 Leon Romanovsky <leon@kernel.org> <leon@leon.nu>
 Leon Romanovsky <leon@kernel.org> <leonro@mellanox.com>
 Leon Romanovsky <leon@kernel.org> <leonro@nvidia.com>
+Leo Yan <leo.yan@linux.dev> <leo.yan@linaro.org>
 Liam Mark <quic_lmark@quicinc.com> <lmark@codeaurora.org>
 Linas Vepstas <linas@austin.ibm.com>
 Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch>
@@ -363,7 +367,6 @@ Maheshwar Ajja <quic_majja@quicinc.com> <majja@codeaurora.org>
 Malathi Gottam <quic_mgottam@quicinc.com> <mgottam@codeaurora.org>
 Manikanta Pubbisetty <quic_mpubbise@quicinc.com> <mpubbise@codeaurora.org>
 Manivannan Sadhasivam <mani@kernel.org> <manivannanece23@gmail.com>
-Manivannan Sadhasivam <mani@kernel.org> <manivannan.sadhasivam@linaro.org>
 Manoj Basapathi <quic_manojbm@quicinc.com> <manojbm@codeaurora.org>
 Marcin Nowakowski <marcin.nowakowski@mips.com> <marcin.nowakowski@imgtec.com>
 Marc Zyngier <maz@kernel.org> <marc.zyngier@arm.com>
@@ -391,9 +394,10 @@ Matthias Fuchs <socketcan@esd.eu> <matthias.fuchs@esd.eu>
 Matthieu Baerts <matttbe@kernel.org> <matthieu.baerts@tessares.net>
 Matthieu CASTET <castet.matthieu@free.fr>
 Matti Vaittinen <mazziesaccount@gmail.com> <matti.vaittinen@fi.rohmeurope.com>
-Matt Ranostay <matt.ranostay@konsulko.com> <matt@ranostay.consulting>
-Matt Ranostay <mranostay@gmail.com> Matthew Ranostay <mranostay@embeddedalley.com>
-Matt Ranostay <mranostay@gmail.com> <matt.ranostay@intel.com>
+Matt Ranostay <matt@ranostay.sg> <matt.ranostay@konsulko.com>
+Matt Ranostay <matt@ranostay.sg> <matt@ranostay.consulting>
+Matt Ranostay <matt@ranostay.sg> Matthew Ranostay <mranostay@embeddedalley.com>
+Matt Ranostay <matt@ranostay.sg> <matt.ranostay@intel.com>
 Matt Redfearn <matt.redfearn@mips.com> <matt.redfearn@imgtec.com>
 Maulik Shah <quic_mkshah@quicinc.com> <mkshah@codeaurora.org>
 Mauro Carvalho Chehab <mchehab@kernel.org> <maurochehab@gmail.com>
@@ -504,6 +508,9 @@ Ralf Baechle <ralf@linux-mips.org>
 Ralf Wildenhues <Ralf.Wildenhues@gmx.de>
 Ram Chandra Jangir <quic_rjangir@quicinc.com> <rjangir@codeaurora.org>
 Randy Dunlap <rdunlap@infradead.org> <rdunlap@xenotime.net>
+Randy Dunlap <rdunlap@infradead.org> <randy.dunlap@oracle.com>
+Randy Dunlap <rdunlap@infradead.org> <rddunlap@osdl.org>
+Randy Dunlap <rdunlap@infradead.org> <randy.dunlap@intel.com>
 Ravi Kumar Bokka <quic_rbokka@quicinc.com> <rbokka@codeaurora.org>
 Ravi Kumar Siddojigari <quic_rsiddoji@quicinc.com> <rsiddoji@codeaurora.org>
 Rémi Denis-Courmont <rdenis@simphalempin.com>
@@ -547,6 +554,7 @@ Senthilkumar N L <quic_snlakshm@quicinc.com> <snlakshm@codeaurora.org>
 Serge Hallyn <sergeh@kernel.org> <serge.hallyn@canonical.com>
 Serge Hallyn <sergeh@kernel.org> <serue@us.ibm.com>
 Seth Forshee <sforshee@kernel.org> <seth.forshee@canonical.com>
+Shakeel Butt <shakeel.butt@linux.dev> <shakeelb@google.com>
 Shannon Nelson <shannon.nelson@amd.com> <snelson@pensando.io>
 Shannon Nelson <shannon.nelson@amd.com> <shannon.nelson@intel.com>
 Shannon Nelson <shannon.nelson@amd.com> <shannon.nelson@oracle.com>
@@ -582,6 +590,7 @@ Surabhi Vishnoi <quic_svishnoi@quicinc.com> <svishnoi@codeaurora.org>
 Takashi YOSHII <takashi.yoshii.zj@renesas.com>
 Tamizh Chelvam Raja <quic_tamizhr@quicinc.com> <tamizhr@codeaurora.org>
 Taniya Das <quic_tdas@quicinc.com> <tdas@codeaurora.org>
+Tanzir Hasan <tanzhasanwork@gmail.com> <tanzirh@google.com>
 Tejun Heo <htejun@gmail.com>
 Tomeu Vizoso <tomeu@tomeuvizoso.net> <tomeu.vizoso@collabora.com>
 Thomas Graf <tgraf@suug.ch>
@@ -601,6 +610,11 @@ TripleX Chung <xxx.phy@gmail.com> <triplex@zh-kernel.org>
 TripleX Chung <xxx.phy@gmail.com> <zhongyu@18mail.cn>
 Tsuneo Yoshioka <Tsuneo.Yoshioka@f-secure.com>
 Tudor Ambarus <tudor.ambarus@linaro.org> <tudor.ambarus@microchip.com>
+Tvrtko Ursulin <tursulin@ursulin.net> <tvrtko.ursulin@intel.com>
+Tvrtko Ursulin <tursulin@ursulin.net> <tvrtko.ursulin@linux.intel.com>
+Tvrtko Ursulin <tursulin@ursulin.net> <tvrtko.ursulin@sophos.com>
+Tvrtko Ursulin <tursulin@ursulin.net> <tvrtko.ursulin@onelan.co.uk>
+Tvrtko Ursulin <tursulin@ursulin.net> <tvrtko@ursulin.net>
 Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws>
 Tzung-Bi Shih <tzungbi@kernel.org> <tzungbi@google.com>
 Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
diff --git a/CREDITS b/CREDITS
index 06b177c6af6a..3c2bb55847c6 100644
--- a/CREDITS
+++ b/CREDITS
@@ -63,6 +63,11 @@ D: dosfs, LILO, some fd features, ATM, various other hacks here and there
 S: Buenos Aires
 S: Argentina
 
+NTFS FILESYSTEM
+N: Anton Altaparmakov
+E: anton@tuxera.com
+D: NTFS filesystem
+
 N: Tim Alpaerts
 E: tim_alpaerts@toyota-motor-europe.com
 D: 802.2 class II logical link control layer,
@@ -179,6 +184,7 @@ E: ralf@gnu.org
 P: 1024/AF7B30C1 CF 97 C2 CC 6D AE A7 FE  C8 BA 9C FC 88 DE 32 C3
 D: Linux/MIPS port
 D: Linux/68k hacker
+D: AX25 maintainer
 S: Hauptstrasse 19
 S: 79837 St. Blasien
 S: Germany
@@ -677,6 +683,10 @@ D: Media subsystem (V4L/DVB) drivers and core
 D: EDAC drivers and EDAC 3.0 core rework
 S: Brazil
 
+N: Landen Chao
+E: Landen.Chao@mediatek.com
+D: MT7531 Ethernet switch support
+
 N: Raymond Chen
 E: raymondc@microsoft.com
 D: Author of Configure script
@@ -814,6 +824,10 @@ D: Support for Xircom PGSDB9 (firmware and host driver)
 S: Bucharest
 S: Romania
 
+N: John Crispin
+E: john@phrozen.org
+D: MediaTek MT7623 Gigabit ethernet support
+
 N: Laurence Culhane
 E: loz@holmes.demon.co.uk
 D: Wrote the initial alpha SLIP code
@@ -1538,6 +1552,10 @@ N: Andrew Haylett
 E: ajh@primag.co.uk
 D: Selection mechanism
 
+N: Johan Hedberg
+E: johan.hedberg@gmail.com
+D: Bluetooth subsystem maintainer
+
 N: Andre Hedrick
 E: andre@linux-ide.org
 E: andre@linuxdiskcert.org
@@ -2148,6 +2166,19 @@ N: Mike Kravetz
 E: mike.kravetz@oracle.com
 D: Maintenance and development of the hugetlb subsystem
 
+N: Seth Jennings
+E: sjenning@redhat.com
+D: Creation and maintenance of zswap
+
+N: Dan Streetman
+E: ddstreet@ieee.org
+D: Maintenance and development of zswap
+D: Creation and maintenance of the zpool API
+
+N: Vitaly Wool
+E: vitaly.wool@konsulko.com
+D: Maintenance and development of zswap
+
 N: Andreas S. Krebs
 E: akrebs@altavista.net
 D: CYPRESS CY82C693 chipset IDE, Digital's PC-Alpha 164SX boards
@@ -3052,6 +3083,10 @@ S: Demonstratsii 8-382
 S: Tula 300000
 S: Russia
 
+N: Thomas Petazzoni
+E: thomas.petazzoni@bootlin.com
+D: Driver for the Marvell Armada 370/XP network unit.
+
 N: Gordon Peters
 E: GordPeters@smarttech.com
 D: Isochronous receive for IEEE 1394 driver (OHCI module).
@@ -3950,6 +3985,10 @@ S: 21513 Conradia Ct
 S: Cupertino, CA 95014
 S: USA
 
+N: Manohar Vanga
+E: manohar.vanga@gmail.com
+D: VME subsystem maintainer
+
 N: Thibaut Varène
 E: hacks+kernel@slashdirt.org
 W: http://hacks.slashdirt.org/
@@ -4050,6 +4089,10 @@ D: Fixes for the NE/2-driver
 D: Miscellaneous MCA-support
 D: Cleanup of the Config-files
 
+N: Martyn Welch
+E: martyn@welchs.me.uk
+D: VME subsystem maintainer
+
 N: Matt Welsh
 E: mdw@metalab.unc.edu
 W: http://www.cs.berkeley.edu/~mdw
diff --git a/Documentation/ABI/testing/debugfs-vfio b/Documentation/ABI/testing/debugfs-vfio
new file mode 100644
index 000000000000..90f7c262f591
--- /dev/null
+++ b/Documentation/ABI/testing/debugfs-vfio
@@ -0,0 +1,25 @@
+What:		/sys/kernel/debug/vfio
+Date:		December 2023
+KernelVersion:	6.8
+Contact:	Longfang Liu <liulongfang@huawei.com>
+Description:	This debugfs file directory is used for debugging
+		of vfio devices, it's a common directory for all vfio devices.
+		Vfio core will create a device subdirectory under this
+		directory.
+
+What:		/sys/kernel/debug/vfio/<device>/migration
+Date:		December 2023
+KernelVersion:	6.8
+Contact:	Longfang Liu <liulongfang@huawei.com>
+Description:	This debugfs file directory is used for debugging
+		of vfio devices that support live migration.
+		The debugfs of each vfio device that supports live migration
+		could be created under this directory.
+
+What:		/sys/kernel/debug/vfio/<device>/migration/state
+Date:		December 2023
+KernelVersion:	6.8
+Contact:	Longfang Liu <liulongfang@huawei.com>
+Description:	Read the live migration status of the vfio device.
+		The contents of the state file reflects the migration state
+		relative to those defined in the vfio_device_mig_state enum
diff --git a/Documentation/ABI/testing/sysfs-bus-cdx b/Documentation/ABI/testing/sysfs-bus-cdx
index 8c067ff99e54..e84277531414 100644
--- a/Documentation/ABI/testing/sysfs-bus-cdx
+++ b/Documentation/ABI/testing/sysfs-bus-cdx
@@ -98,6 +98,13 @@ Description:
 
 		  # echo 1 > /sys/bus/cdx/devices/.../remove
 
+What:		/sys/bus/cdx/devices/.../resource<N>
+Date:		July 2023
+Contact:	puneet.gupta@amd.com
+Description:
+		The resource binary file contains the content of the memory
+		regions. These files can be m'maped from userspace.
+
 What:		/sys/bus/cdx/devices/.../modalias
 Date:		July 2023
 Contact:	nipun.gupta@amd.com
diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tmc b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tmc
index 6aa527296c71..96aafa66b4a5 100644
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tmc
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tmc
@@ -91,3 +91,19 @@ Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
 Description:	(RW) Size of the trace buffer for TMC-ETR when used in SYSFS
 		mode. Writable only for TMC-ETR configurations. The value
 		should be aligned to the kernel pagesize.
+
+What:		/sys/bus/coresight/devices/<memory_map>.tmc/buf_modes_available
+Date:		August 2023
+KernelVersion:	6.7
+Contact:	Anshuman Khandual <anshuman.khandual@arm.com>
+Description:	(Read) Shows all supported Coresight TMC-ETR buffer modes available
+		for the users to configure explicitly. This file is avaialble only
+		for TMC ETR devices.
+
+What:		/sys/bus/coresight/devices/<memory_map>.tmc/buf_mode_preferred
+Date:		August 2023
+KernelVersion:	6.7
+Contact:	Anshuman Khandual <anshuman.khandual@arm.com>
+Description:	(RW) Current Coresight TMC-ETR buffer mode selected. But user could
+		only provide a mode which is supported for a given ETR device. This
+		file is available only for TMC ETR devices.
diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
index 4a58e649550d..4dd49b159543 100644
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
@@ -11,3 +11,162 @@ Description:
 		Accepts only one of the 2 values -  1 or 2.
 		1 : Generate 64 bits data
 		2 : Generate 32 bits data
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/reset_dataset
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(Write) Reset the dataset of the tpdm.
+
+		Accepts only one value -  1.
+		1 : Reset the dataset of the tpdm
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_trig_type
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(RW) Set/Get the trigger type of the DSB for tpdm.
+
+		Accepts only one of the 2 values -  0 or 1.
+		0 : Set the DSB trigger type to false
+		1 : Set the DSB trigger type to true
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_trig_ts
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(RW) Set/Get the trigger timestamp of the DSB for tpdm.
+
+		Accepts only one of the 2 values -  0 or 1.
+		0 : Set the DSB trigger type to false
+		1 : Set the DSB trigger type to true
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_mode
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(RW) Set/Get the programming mode of the DSB for tpdm.
+
+		Accepts the value needs to be greater than 0. What data
+		bits do is listed below.
+		Bit[0:1] : Test mode control bit for choosing the inputs.
+		Bit[3] : Set to 0 for low performance mode. Set to 1 for high
+		performance mode.
+		Bit[4:8] : Select byte lane for high performance mode.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_edge/ctrl_idx
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(RW) Set/Get the index number of the edge detection for the DSB
+		subunit TPDM. Since there are at most 256 edge detections, this
+		value ranges from 0 to 255.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_edge/ctrl_val
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		Write a data to control the edge detection corresponding to
+		the index number. Before writing data to this sysfs file,
+		"ctrl_idx" should be written first to configure the index
+		number of the edge detection which needs to be controlled.
+
+		Accepts only one of the following values.
+		0 - Rising edge detection
+		1 - Falling edge detection
+		2 - Rising and falling edge detection (toggle detection)
+
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_edge/ctrl_mask
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		Write a data to mask the edge detection corresponding to the index
+		number. Before writing data to this sysfs file, "ctrl_idx" should
+		be written first to configure the index number of the edge detection
+		which needs to be masked.
+
+		Accepts only one of the 2 values -  0 or 1.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_edge/edcr[0:15]
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		Read a set of the edge control value of the DSB in TPDM.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_edge/edcmr[0:7]
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		Read a set of the edge control mask of the DSB in TPDM.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_trig_patt/xpr[0:7]
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(RW) Set/Get the value of the trigger pattern for the DSB
+		subunit TPDM.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_trig_patt/xpmr[0:7]
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(RW) Set/Get the mask of the trigger pattern for the DSB
+		subunit TPDM.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_patt/tpr[0:7]
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(RW) Set/Get the value of the pattern for the DSB subunit TPDM.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_patt/tpmr[0:7]
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(RW) Set/Get the mask of the pattern for the DSB subunit TPDM.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_patt/enable_ts
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(Write) Set the pattern timestamp of DSB tpdm. Read
+		the pattern timestamp of DSB tpdm.
+
+		Accepts only one of the 2 values -  0 or 1.
+		0 : Disable DSB pattern timestamp.
+		1 : Enable DSB pattern timestamp.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_patt/set_type
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(Write) Set the pattern type of DSB tpdm. Read
+		the pattern type of DSB tpdm.
+
+		Accepts only one of the 2 values -  0 or 1.
+		0 : Set the DSB pattern type to value.
+		1 : Set the DSB pattern type to toggle.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_msr/msr[0:31]
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(RW) Set/Get the MSR(mux select register) for the DSB subunit
+		TPDM.
diff --git a/Documentation/ABI/testing/sysfs-bus-cxl b/Documentation/ABI/testing/sysfs-bus-cxl
index e76c3600607f..fff2581b8033 100644
--- a/Documentation/ABI/testing/sysfs-bus-cxl
+++ b/Documentation/ABI/testing/sysfs-bus-cxl
@@ -28,6 +28,23 @@ Description:
 		Payload in the CXL-2.0 specification.
 
 
+What:		/sys/bus/cxl/devices/memX/ram/qos_class
+Date:		May, 2023
+KernelVersion:	v6.8
+Contact:	linux-cxl@vger.kernel.org
+Description:
+		(RO) For CXL host platforms that support "QoS Telemmetry"
+		this attribute conveys a comma delimited list of platform
+		specific cookies that identifies a QoS performance class
+		for the volatile partition of the CXL mem device. These
+		class-ids can be compared against a similar "qos_class"
+		published for a root decoder. While it is not required
+		that the endpoints map their local memory-class to a
+		matching platform class, mismatches are not recommended
+		and there are platform specific performance related
+		side-effects that may result. First class-id is displayed.
+
+
 What:		/sys/bus/cxl/devices/memX/pmem/size
 Date:		December, 2020
 KernelVersion:	v5.12
@@ -38,6 +55,23 @@ Description:
 		Payload in the CXL-2.0 specification.
 
 
+What:		/sys/bus/cxl/devices/memX/pmem/qos_class
+Date:		May, 2023
+KernelVersion:	v6.8
+Contact:	linux-cxl@vger.kernel.org
+Description:
+		(RO) For CXL host platforms that support "QoS Telemmetry"
+		this attribute conveys a comma delimited list of platform
+		specific cookies that identifies a QoS performance class
+		for the persistent partition of the CXL mem device. These
+		class-ids can be compared against a similar "qos_class"
+		published for a root decoder. While it is not required
+		that the endpoints map their local memory-class to a
+		matching platform class, mismatches are not recommended
+		and there are platform specific performance related
+		side-effects that may result. First class-id is displayed.
+
+
 What:		/sys/bus/cxl/devices/memX/serial
 Date:		January, 2022
 KernelVersion:	v5.18
diff --git a/Documentation/ABI/testing/sysfs-bus-i3c b/Documentation/ABI/testing/sysfs-bus-i3c
index e5248fd67a56..c812ab180ff4 100644
--- a/Documentation/ABI/testing/sysfs-bus-i3c
+++ b/Documentation/ABI/testing/sysfs-bus-i3c
@@ -88,6 +88,21 @@ Description:
 		This entry describes the HDRCAP of the master controller
 		driving the bus.
 
+What:		/sys/bus/i3c/devices/i3c-<bus-id>/hotjoin
+KernelVersion:  6.8
+Contact:	linux-i3c@vger.kernel.org
+Description:
+		I3C’s Hot-Join mechanism allows an I3C Device to inform the
+		Active Controller that a newly-joined Target is present on the
+		I3C Bus and is ready to receive a Dynamic Address, in order to
+		become fully functional on the Bus. Hot-Join is used when the
+		Target is mounted on the same I3C bus and remains depowered
+		until needed or until the Target is physically inserted into the
+		I3C bus
+
+		This entry allows to enable or disable Hot-join of the Current
+		Controller driving the bus.
+
 What:		/sys/bus/i3c/devices/i3c-<bus-id>/<bus-id>-<device-pid>
 KernelVersion:  5.0
 Contact:	linux-i3c@vger.kernel.org
diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index 19cde14f3869..2e6d5ebfd3c7 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -362,10 +362,21 @@ Description:
 What:		/sys/bus/iio/devices/iio:deviceX/in_accel_x_peak_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_accel_y_peak_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_accel_z_peak_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_humidityrelative_peak_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_temp_peak_raw
 KernelVersion:	2.6.36
 Contact:	linux-iio@vger.kernel.org
 Description:
-		Highest value since some reset condition.  These
+		Highest value since some reset condition. These
+		attributes allow access to this and are otherwise
+		the direct equivalent of the <type>Y[_name]_raw attributes.
+
+What:		/sys/bus/iio/devices/iio:deviceX/in_humidityrelative_trough_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_temp_trough_raw
+KernelVersion:	6.7
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Lowest value since some reset condition. These
 		attributes allow access to this and are otherwise
 		the direct equivalent of the <type>Y[_name]_raw attributes.
 
@@ -618,7 +629,9 @@ KernelVersion:	2.6.35
 Contact:	linux-iio@vger.kernel.org
 Description:
 		If a discrete set of scale values is available, they
-		are listed in this attribute.
+		are listed in this attribute. Unlike illumination,
+		multiplying intensity by intensity_scale does not
+		yield value with any standardized unit.
 
 What:		/sys/bus/iio/devices/iio:deviceX/out_voltageY_hardwaregain
 What:		/sys/bus/iio/devices/iio:deviceX/in_intensity_hardwaregain
@@ -1574,6 +1587,8 @@ What:		/sys/.../iio:deviceX/in_intensityY_raw
 What:		/sys/.../iio:deviceX/in_intensityY_ir_raw
 What:		/sys/.../iio:deviceX/in_intensityY_both_raw
 What:		/sys/.../iio:deviceX/in_intensityY_uv_raw
+What:		/sys/.../iio:deviceX/in_intensityY_uva_raw
+What:		/sys/.../iio:deviceX/in_intensityY_uvb_raw
 What:		/sys/.../iio:deviceX/in_intensityY_duv_raw
 KernelVersion:	3.4
 Contact:	linux-iio@vger.kernel.org
@@ -1582,8 +1597,9 @@ Description:
 		that measurements contain visible and infrared light
 		components or just infrared light, respectively. Modifier
 		uv indicates that measurements contain ultraviolet light
-		components. Modifier duv indicates that measurements
-		contain deep ultraviolet light components.
+		components. Modifiers uva, uvb and duv indicate that
+		measurements contain A, B or deep (C) ultraviolet light
+		components respectively.
 
 What:		/sys/.../iio:deviceX/in_uvindex_input
 KernelVersion:	4.6
@@ -2254,3 +2270,21 @@ Description:
 		If a label is defined for this event add that to the event
 		specific attributes. This is useful for userspace to be able to
 		better identify an individual event.
+
+What:		/sys/.../events/in_accel_gesture_tap_wait_timeout
+KernelVersion:	6.7
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Enable tap gesture confirmation with timeout.
+
+What:		/sys/.../events/in_accel_gesture_tap_wait_dur
+KernelVersion:	6.7
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Timeout value in seconds for tap gesture confirmation.
+
+What:		/sys/.../events/in_accel_gesture_tap_wait_dur_available
+KernelVersion:	6.7
+Contact:	linux-iio@vger.kernel.org
+Description:
+		List of available timeout value for tap gesture confirmation.
diff --git a/Documentation/ABI/testing/sysfs-class-led-trigger-netdev b/Documentation/ABI/testing/sysfs-class-led-trigger-netdev
index f6d9d72ce77b..a6c307c4befa 100644
--- a/Documentation/ABI/testing/sysfs-class-led-trigger-netdev
+++ b/Documentation/ABI/testing/sysfs-class-led-trigger-netdev
@@ -114,6 +114,45 @@ Description:
 		speed of 1000Mbps of the named network device.
 		Setting this value also immediately changes the LED state.
 
+What:		/sys/class/leds/<led>/link_2500
+Date:		Nov 2023
+KernelVersion:	6.8
+Contact:	linux-leds@vger.kernel.org
+Description:
+		Signal the link speed state of 2500Mbps of the named network device.
+
+		If set to 0 (default), the LED's normal state is off.
+
+		If set to 1, the LED's normal state reflects the link state
+		speed of 2500Mbps of the named network device.
+		Setting this value also immediately changes the LED state.
+
+What:		/sys/class/leds/<led>/link_5000
+Date:		Nov 2023
+KernelVersion:	6.8
+Contact:	linux-leds@vger.kernel.org
+Description:
+		Signal the link speed state of 5000Mbps of the named network device.
+
+		If set to 0 (default), the LED's normal state is off.
+
+		If set to 1, the LED's normal state reflects the link state
+		speed of 5000Mbps of the named network device.
+		Setting this value also immediately changes the LED state.
+
+What:		/sys/class/leds/<led>/link_10000
+Date:		Nov 2023
+KernelVersion:	6.8
+Contact:	linux-leds@vger.kernel.org
+Description:
+		Signal the link speed state of 10000Mbps of the named network device.
+
+		If set to 0 (default), the LED's normal state is off.
+
+		If set to 1, the LED's normal state reflects the link state
+		speed of 10000Mbps of the named network device.
+		Setting this value also immediately changes the LED state.
+
 What:		/sys/class/leds/<led>/half_duplex
 Date:		Jun 2023
 KernelVersion:	6.5
diff --git a/Documentation/ABI/testing/sysfs-class-led-trigger-tty b/Documentation/ABI/testing/sysfs-class-led-trigger-tty
index 2bf6b24e781b..30cef9ac0f49 100644
--- a/Documentation/ABI/testing/sysfs-class-led-trigger-tty
+++ b/Documentation/ABI/testing/sysfs-class-led-trigger-tty
@@ -4,3 +4,59 @@ KernelVersion:	5.10
 Contact:	linux-leds@vger.kernel.org
 Description:
 		Specifies the tty device name of the triggering tty
+
+What:		/sys/class/leds/<led>/rx
+Date:		February 2024
+KernelVersion:	6.8
+Description:
+		Signal reception (rx) of data on the named tty device.
+		If set to 0, the LED will not blink on reception.
+		If set to 1 (default), the LED will blink on reception.
+
+What:		/sys/class/leds/<led>/tx
+Date:		February 2024
+KernelVersion:	6.8
+Description:
+		Signal transmission (tx) of data on the named tty device.
+		If set to 0, the LED will not blink on transmission.
+		If set to 1 (default), the LED will blink on transmission.
+
+What:		/sys/class/leds/<led>/cts
+Date:		February 2024
+KernelVersion:	6.8
+Description:
+		CTS = Clear To Send
+		DCE is ready to accept data from the DTE.
+		If the line state is detected, the LED is switched on.
+		If set to 0 (default), the LED will not evaluate CTS.
+		If set to 1, the LED will evaluate CTS.
+
+What:		/sys/class/leds/<led>/dsr
+Date:		February 2024
+KernelVersion:	6.8
+Description:
+		DSR = Data Set Ready
+		DCE is ready to receive and send data.
+		If the line state is detected, the LED is switched on.
+		If set to 0 (default), the LED will not evaluate DSR.
+		If set to 1, the LED will evaluate DSR.
+
+What:		/sys/class/leds/<led>/dcd
+Date:		February 2024
+KernelVersion:	6.8
+Description:
+		DCD = Data Carrier Detect
+		DTE is receiving a carrier from the DCE.
+		If the line state is detected, the LED is switched on.
+		If set to 0 (default), the LED will not evaluate CAR (DCD).
+		If set to 1, the LED will evaluate CAR (DCD).
+
+What:		/sys/class/leds/<led>/rng
+Date:		February 2024
+KernelVersion:	6.8
+Description:
+		RNG = Ring Indicator
+		DCE has detected an incoming ring signal on the telephone
+		line. If the line state is detected, the LED is switched on.
+		If set to 0 (default), the LED will not evaluate RNG.
+		If set to 1, the LED will evaluate RNG.
diff --git a/Documentation/ABI/testing/sysfs-class-net-queues b/Documentation/ABI/testing/sysfs-class-net-queues
index 906ff3ca928a..5bff64d256c2 100644
--- a/Documentation/ABI/testing/sysfs-class-net-queues
+++ b/Documentation/ABI/testing/sysfs-class-net-queues
@@ -1,4 +1,4 @@
-What:		/sys/class/<iface>/queues/rx-<queue>/rps_cpus
+What:		/sys/class/net/<iface>/queues/rx-<queue>/rps_cpus
 Date:		March 2010
 KernelVersion:	2.6.35
 Contact:	netdev@vger.kernel.org
@@ -8,7 +8,7 @@ Description:
 		network device queue. Possible values depend on the number
 		of available CPU(s) in the system.
 
-What:		/sys/class/<iface>/queues/rx-<queue>/rps_flow_cnt
+What:		/sys/class/net/<iface>/queues/rx-<queue>/rps_flow_cnt
 Date:		April 2010
 KernelVersion:	2.6.35
 Contact:	netdev@vger.kernel.org
@@ -16,7 +16,7 @@ Description:
 		Number of Receive Packet Steering flows being currently
 		processed by this particular network device receive queue.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/tx_timeout
+What:		/sys/class/net/<iface>/queues/tx-<queue>/tx_timeout
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
@@ -24,7 +24,7 @@ Description:
 		Indicates the number of transmit timeout events seen by this
 		network interface transmit queue.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/tx_maxrate
+What:		/sys/class/net/<iface>/queues/tx-<queue>/tx_maxrate
 Date:		March 2015
 KernelVersion:	4.1
 Contact:	netdev@vger.kernel.org
@@ -32,7 +32,7 @@ Description:
 		A Mbps max-rate set for the queue, a value of zero means disabled,
 		default is disabled.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/xps_cpus
+What:		/sys/class/net/<iface>/queues/tx-<queue>/xps_cpus
 Date:		November 2010
 KernelVersion:	2.6.38
 Contact:	netdev@vger.kernel.org
@@ -42,7 +42,7 @@ Description:
 		network device transmit queue. Possible values depend on the
 		number of available CPU(s) in the system.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/xps_rxqs
+What:		/sys/class/net/<iface>/queues/tx-<queue>/xps_rxqs
 Date:		June 2018
 KernelVersion:	4.18.0
 Contact:	netdev@vger.kernel.org
@@ -53,7 +53,7 @@ Description:
 		number of available receive queue(s) in the network device.
 		Default is disabled.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/hold_time
+What:		/sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/hold_time
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
@@ -62,7 +62,7 @@ Description:
 		of this particular network device transmit queue.
 		Default value is 1000.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/inflight
+What:		/sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/inflight
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
@@ -70,7 +70,7 @@ Description:
 		Indicates the number of bytes (objects) in flight on this
 		network device transmit queue.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit
+What:		/sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
@@ -79,7 +79,7 @@ Description:
 		on this network device transmit queue. This value is clamped
 		to be within the bounds defined by limit_max and limit_min.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit_max
+What:		/sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit_max
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
@@ -88,7 +88,7 @@ Description:
 		queued on this network device transmit queue. See
 		include/linux/dynamic_queue_limits.h for the default value.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit_min
+What:		/sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit_min
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
diff --git a/Documentation/ABI/testing/sysfs-class-net-statistics b/Documentation/ABI/testing/sysfs-class-net-statistics
index 55db27815361..53e508c6936a 100644
--- a/Documentation/ABI/testing/sysfs-class-net-statistics
+++ b/Documentation/ABI/testing/sysfs-class-net-statistics
@@ -1,4 +1,4 @@
-What:		/sys/class/<iface>/statistics/collisions
+What:		/sys/class/net/<iface>/statistics/collisions
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -6,7 +6,7 @@ Description:
 		Indicates the number of collisions seen by this network device.
 		This value might not be relevant with all MAC layers.
 
-What:		/sys/class/<iface>/statistics/multicast
+What:		/sys/class/net/<iface>/statistics/multicast
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -14,7 +14,7 @@ Description:
 		Indicates the number of multicast packets received by this
 		network device.
 
-What:		/sys/class/<iface>/statistics/rx_bytes
+What:		/sys/class/net/<iface>/statistics/rx_bytes
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -23,7 +23,7 @@ Description:
 		See the network driver for the exact meaning of when this
 		value is incremented.
 
-What:		/sys/class/<iface>/statistics/rx_compressed
+What:		/sys/class/net/<iface>/statistics/rx_compressed
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -32,7 +32,7 @@ Description:
 		network device. This value might only be relevant for interfaces
 		that support packet compression (e.g: PPP).
 
-What:		/sys/class/<iface>/statistics/rx_crc_errors
+What:		/sys/class/net/<iface>/statistics/rx_crc_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -41,7 +41,7 @@ Description:
 		by this network device. Note that the specific meaning might
 		depend on the MAC layer used by the interface.
 
-What:		/sys/class/<iface>/statistics/rx_dropped
+What:		/sys/class/net/<iface>/statistics/rx_dropped
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -51,7 +51,7 @@ Description:
 		packet processing. See the network driver for the exact
 		meaning of this value.
 
-What:		/sys/class/<iface>/statistics/rx_errors
+What:		/sys/class/net/<iface>/statistics/rx_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -59,7 +59,7 @@ Description:
 		Indicates the number of receive errors on this network device.
 		See the network driver for the exact meaning of this value.
 
-What:		/sys/class/<iface>/statistics/rx_fifo_errors
+What:		/sys/class/net/<iface>/statistics/rx_fifo_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -68,7 +68,7 @@ Description:
 		network device. See the network driver for the exact
 		meaning of this value.
 
-What:		/sys/class/<iface>/statistics/rx_frame_errors
+What:		/sys/class/net/<iface>/statistics/rx_frame_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -78,7 +78,7 @@ Description:
 		on the MAC layer protocol used. See the network driver for
 		the exact meaning of this value.
 
-What:		/sys/class/<iface>/statistics/rx_length_errors
+What:		/sys/class/net/<iface>/statistics/rx_length_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -87,7 +87,7 @@ Description:
 		error, oversized or undersized. See the network driver for the
 		exact meaning of this value.
 
-What:		/sys/class/<iface>/statistics/rx_missed_errors
+What:		/sys/class/net/<iface>/statistics/rx_missed_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -96,7 +96,7 @@ Description:
 		due to lack of capacity in the receive side. See the network
 		driver for the exact meaning of this value.
 
-What:		/sys/class/<iface>/statistics/rx_nohandler
+What:		/sys/class/net/<iface>/statistics/rx_nohandler
 Date:		February 2016
 KernelVersion:	4.6
 Contact:	netdev@vger.kernel.org
@@ -104,7 +104,7 @@ Description:
 		Indicates the number of received packets that were dropped on
 		an inactive device by the network core.
 
-What:		/sys/class/<iface>/statistics/rx_over_errors
+What:		/sys/class/net/<iface>/statistics/rx_over_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -114,7 +114,7 @@ Description:
 		(e.g: larger than MTU). See the network driver for the exact
 		meaning of this value.
 
-What:		/sys/class/<iface>/statistics/rx_packets
+What:		/sys/class/net/<iface>/statistics/rx_packets
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -122,7 +122,7 @@ Description:
 		Indicates the total number of good packets received by this
 		network device.
 
-What:		/sys/class/<iface>/statistics/tx_aborted_errors
+What:		/sys/class/net/<iface>/statistics/tx_aborted_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -132,7 +132,7 @@ Description:
 		a medium collision). See the network driver for the exact
 		meaning of this value.
 
-What:		/sys/class/<iface>/statistics/tx_bytes
+What:		/sys/class/net/<iface>/statistics/tx_bytes
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -143,7 +143,7 @@ Description:
 		transmitted packets or all packets that have been queued for
 		transmission.
 
-What:		/sys/class/<iface>/statistics/tx_carrier_errors
+What:		/sys/class/net/<iface>/statistics/tx_carrier_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -152,7 +152,7 @@ Description:
 		because of carrier errors (e.g: physical link down). See the
 		network driver for the exact meaning of this value.
 
-What:		/sys/class/<iface>/statistics/tx_compressed
+What:		/sys/class/net/<iface>/statistics/tx_compressed
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -161,7 +161,7 @@ Description:
 		this might only be relevant for devices that support
 		compression (e.g: PPP).
 
-What:		/sys/class/<iface>/statistics/tx_dropped
+What:		/sys/class/net/<iface>/statistics/tx_dropped
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -170,7 +170,7 @@ Description:
 		See the driver for the exact reasons as to why the packets were
 		dropped.
 
-What:		/sys/class/<iface>/statistics/tx_errors
+What:		/sys/class/net/<iface>/statistics/tx_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -179,7 +179,7 @@ Description:
 		a network device. See the driver for the exact reasons as to
 		why the packets were dropped.
 
-What:		/sys/class/<iface>/statistics/tx_fifo_errors
+What:		/sys/class/net/<iface>/statistics/tx_fifo_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -188,7 +188,7 @@ Description:
 		FIFO error. See the driver for the exact reasons as to why the
 		packets were dropped.
 
-What:		/sys/class/<iface>/statistics/tx_heartbeat_errors
+What:		/sys/class/net/<iface>/statistics/tx_heartbeat_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -197,7 +197,7 @@ Description:
 		reported as heartbeat errors. See the driver for the exact
 		reasons as to why the packets were dropped.
 
-What:		/sys/class/<iface>/statistics/tx_packets
+What:		/sys/class/net/<iface>/statistics/tx_packets
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -206,7 +206,7 @@ Description:
 		device. See the driver for whether this reports the number of all
 		attempted or successful transmissions.
 
-What:		/sys/class/<iface>/statistics/tx_window_errors
+What:		/sys/class/net/<iface>/statistics/tx_window_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
diff --git a/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon b/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
index 8d7d8f05f6cd..92fe7c5c5ac1 100644
--- a/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
+++ b/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
@@ -1,4 +1,4 @@
-What:		/sys/devices/.../hwmon/hwmon<i>/in0_input
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/in0_input
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
@@ -6,7 +6,7 @@ Description:	RO. Current Voltage in millivolt.
 
 		Only supported for particular Intel i915 graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_max
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/power1_max
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
@@ -20,7 +20,7 @@ Description:	RW. Card reactive sustained  (PL1/Tau) power limit in microwatts.
 
 		Only supported for particular Intel i915 graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_rated_max
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/power1_rated_max
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
@@ -28,7 +28,7 @@ Description:	RO. Card default power limit (default TDP setting).
 
 		Only supported for particular Intel i915 graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_max_interval
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/power1_max_interval
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
@@ -37,7 +37,7 @@ Description:	RW. Sustained power limit interval (Tau in PL1/Tau) in
 
 		Only supported for particular Intel i915 graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_crit
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/power1_crit
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
@@ -50,7 +50,7 @@ Description:	RW. Card reactive critical (I1) power limit in microwatts.
 
 		Only supported for particular Intel i915 graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/curr1_crit
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/curr1_crit
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
@@ -63,7 +63,7 @@ Description:	RW. Card reactive critical (I1) power limit in milliamperes.
 
 		Only supported for particular Intel i915 graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/energy1_input
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/energy1_input
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
diff --git a/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon b/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon
index 8c321bc9dc04..023fd82de3f7 100644
--- a/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon
+++ b/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon
@@ -1,4 +1,4 @@
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_max
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/power1_max
 Date:		September 2023
 KernelVersion:	6.5
 Contact:	intel-xe@lists.freedesktop.org
@@ -12,7 +12,7 @@ Description:	RW. Card reactive sustained  (PL1) power limit in microwatts.
 
 		Only supported for particular Intel xe graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_rated_max
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/power1_rated_max
 Date:		September 2023
 KernelVersion:	6.5
 Contact:	intel-xe@lists.freedesktop.org
@@ -20,7 +20,7 @@ Description:	RO. Card default power limit (default TDP setting).
 
 		Only supported for particular Intel xe graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_crit
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/power1_crit
 Date:		September 2023
 KernelVersion:	6.5
 Contact:	intel-xe@lists.freedesktop.org
@@ -33,7 +33,7 @@ Description:	RW. Card reactive critical (I1) power limit in microwatts.
 
 		Only supported for particular Intel xe graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/curr1_crit
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/curr1_crit
 Date:		September 2023
 KernelVersion:	6.5
 Contact:	intel-xe@lists.freedesktop.org
@@ -44,7 +44,7 @@ Description:	RW. Card reactive critical (I1) power limit in milliamperes.
 		the operating frequency if the power averaged over a window
 		exceeds this limit.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/in0_input
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/in0_input
 Date:		September 2023
 KernelVersion:	6.5
 Contact:	intel-xe@lists.freedesktop.org
@@ -52,7 +52,7 @@ Description:	RO. Current Voltage in millivolt.
 
 		Only supported for particular Intel xe graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/energy1_input
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/energy1_input
 Date:		September 2023
 KernelVersion:	6.5
 Contact:	intel-xe@lists.freedesktop.org
@@ -60,7 +60,7 @@ Description:	RO. Energy input of device in microjoules.
 
 		Only supported for particular Intel xe graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_max_interval
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/power1_max_interval
 Date:		October 2023
 KernelVersion:	6.6
 Contact:	intel-xe@lists.freedesktop.org
diff --git a/Documentation/ABI/testing/sysfs-firmware-initrd b/Documentation/ABI/testing/sysfs-firmware-initrd
new file mode 100644
index 000000000000..20bf7cf77a19
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-firmware-initrd
@@ -0,0 +1,8 @@
+What:		/sys/firmware/initrd
+Date:		December 2023
+Contact:	Alexander Graf <graf@amazon.com>
+Description:
+		When the kernel was booted with an initrd and the
+		"retain_initrd" option is set on the kernel command
+		line, /sys/firmware/initrd contains the contents of the
+		initrd that the kernel was booted with.
diff --git a/Documentation/ABI/testing/sysfs-nvmem-cells b/Documentation/ABI/testing/sysfs-nvmem-cells
new file mode 100644
index 000000000000..c7c9444f92a8
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-nvmem-cells
@@ -0,0 +1,21 @@
+What:		/sys/bus/nvmem/devices/.../cells/<cell-name>
+Date:		May 2023
+KernelVersion:	6.5
+Contact:	Miquel Raynal <miquel.raynal@bootlin.com>
+Description:
+		The "cells" folder contains one file per cell exposed by the
+		NVMEM device. The name of the file is: "<name>@<byte>,<bit>",
+		with <name> being the cell name and <where> its location in
+		the NVMEM device, in hexadecimal bytes and bits (without the
+		'0x' prefix, to mimic device tree node names). The length of
+		the file is the size of the cell (when known). The content of
+		the file is the binary content of the cell (may sometimes be
+		ASCII, likely without trailing character).
+		Note: This file is only present if CONFIG_NVMEM_SYSFS
+		is enabled.
+
+		Example::
+
+		  hexdump -C /sys/bus/nvmem/devices/1-00563/cells/product-name@d,0
+		  00000000  54 4e 34 38 4d 2d 50 2d  44 4e         |TN48M-P-DN|
+		  0000000a
diff --git a/Documentation/ABI/testing/sysfs-platform-silicom b/Documentation/ABI/testing/sysfs-platform-silicom
index 2288b3665d16..4d1cc5bdbcc5 100644
--- a/Documentation/ABI/testing/sysfs-platform-silicom
+++ b/Documentation/ABI/testing/sysfs-platform-silicom
@@ -10,6 +10,7 @@ What:		/sys/devices/platform/silicom-platform/power_cycle
 Date:		November 2023
 KernelVersion:	6.7
 Contact:	Henry Shi <henrys@silicom-usa.com>
+Description:
 		This file allow user to power cycle the platform.
 		Default value is 0; when set to 1, it powers down
 		the platform, waits 5 seconds, then powers on the
diff --git a/Documentation/PCI/boot-interrupts.rst b/Documentation/PCI/boot-interrupts.rst
index 2ec70121bfca..931077bb0953 100644
--- a/Documentation/PCI/boot-interrupts.rst
+++ b/Documentation/PCI/boot-interrupts.rst
@@ -61,7 +61,7 @@ Conditions
 ==========
 
 The use of threaded interrupts is the most likely condition to trigger
-this problem today. Threaded interrupts may not be reenabled after the IRQ
+this problem today. Threaded interrupts may not be re-enabled after the IRQ
 handler wakes. These "one shot" conditions mean that the threaded interrupt
 needs to keep the interrupt line masked until the threaded handler has run.
 Especially when dealing with high data rate interrupts, the thread needs to
diff --git a/Documentation/PCI/msi-howto.rst b/Documentation/PCI/msi-howto.rst
index c9400f02333b..783d30b7bb42 100644
--- a/Documentation/PCI/msi-howto.rst
+++ b/Documentation/PCI/msi-howto.rst
@@ -236,7 +236,7 @@ including a full 'lspci -v' so we can add the quirks to the kernel.
 Disabling MSIs below a bridge
 -----------------------------
 
-Some PCI bridges are not able to route MSIs between busses properly.
+Some PCI bridges are not able to route MSIs between buses properly.
 In this case, MSIs must be disabled on all devices behind the bridge.
 
 Some bridges allow you to enable MSIs by changing some bits in their
diff --git a/Documentation/RCU/checklist.rst b/Documentation/RCU/checklist.rst
index 2d42998a89a6..3e6407de231c 100644
--- a/Documentation/RCU/checklist.rst
+++ b/Documentation/RCU/checklist.rst
@@ -68,7 +68,8 @@ over a rather long period of time, but improvements are always welcome!
 	rcu_read_lock_sched(), or by the appropriate update-side lock.
 	Explicit disabling of preemption (preempt_disable(), for example)
 	can serve as rcu_read_lock_sched(), but is less readable and
-	prevents lockdep from detecting locking issues.
+	prevents lockdep from detecting locking issues.  Acquiring a
+	spinlock also enters an RCU read-side critical section.
 
 	Please note that you *cannot* rely on code known to be built
 	only in non-preemptible kernels.  Such code can and will break,
@@ -382,16 +383,17 @@ over a rather long period of time, but improvements are always welcome!
 	must use whatever locking or other synchronization is required
 	to safely access and/or modify that data structure.
 
-	Do not assume that RCU callbacks will be executed on the same
-	CPU that executed the corresponding call_rcu() or call_srcu().
-	For example, if a given CPU goes offline while having an RCU
-	callback pending, then that RCU callback will execute on some
-	surviving CPU.	(If this was not the case, a self-spawning RCU
-	callback would prevent the victim CPU from ever going offline.)
-	Furthermore, CPUs designated by rcu_nocbs= might well *always*
-	have their RCU callbacks executed on some other CPUs, in fact,
-	for some  real-time workloads, this is the whole point of using
-	the rcu_nocbs= kernel boot parameter.
+	Do not assume that RCU callbacks will be executed on
+	the same CPU that executed the corresponding call_rcu(),
+	call_srcu(), call_rcu_tasks(), call_rcu_tasks_rude(), or
+	call_rcu_tasks_trace().  For example, if a given CPU goes offline
+	while having an RCU callback pending, then that RCU callback
+	will execute on some surviving CPU.  (If this was not the case,
+	a self-spawning RCU callback would prevent the victim CPU from
+	ever going offline.)  Furthermore, CPUs designated by rcu_nocbs=
+	might well *always* have their RCU callbacks executed on some
+	other CPUs, in fact, for some  real-time workloads, this is the
+	whole point of using the rcu_nocbs= kernel boot parameter.
 
 	In addition, do not assume that callbacks queued in a given order
 	will be invoked in that order, even if they all are queued on the
@@ -444,7 +446,7 @@ over a rather long period of time, but improvements are always welcome!
 	real-time workloads than is synchronize_rcu_expedited().
 
 	It is also permissible to sleep in RCU Tasks Trace read-side
-	critical, which are delimited by rcu_read_lock_trace() and
+	critical section, which are delimited by rcu_read_lock_trace() and
 	rcu_read_unlock_trace().  However, this is a specialized flavor
 	of RCU, and you should not use it without first checking with
 	its current users.  In most cases, you should instead use SRCU.
@@ -490,6 +492,12 @@ over a rather long period of time, but improvements are always welcome!
 		since the last time that you passed that same object to
 		call_rcu() (or friends).
 
+	CONFIG_RCU_STRICT_GRACE_PERIOD:
+		combine with KASAN to check for pointers leaked out
+		of RCU read-side critical sections.  This Kconfig
+		option is tough on both performance and scalability,
+		and so is limited to four-CPU systems.
+
 	__rcu sparse checks:
 		tag the pointer to the RCU-protected data structure
 		with __rcu, and sparse will warn you if you access that
diff --git a/Documentation/RCU/rcu_dereference.rst b/Documentation/RCU/rcu_dereference.rst
index 659d5913784d..2524dcdadde2 100644
--- a/Documentation/RCU/rcu_dereference.rst
+++ b/Documentation/RCU/rcu_dereference.rst
@@ -408,7 +408,10 @@ member of the rcu_dereference() to use in various situations:
 	RCU flavors, an RCU read-side critical section is entered
 	using rcu_read_lock(), anything that disables bottom halves,
 	anything that disables interrupts, or anything that disables
-	preemption.
+	preemption.  Please note that spinlock critical sections
+	are also implied RCU read-side critical sections, even when
+	they are preemptible, as they are in kernels built with
+	CONFIG_PREEMPT_RT=y.
 
 2.	If the access might be within an RCU read-side critical section
 	on the one hand, or protected by (say) my_lock on the other,
diff --git a/Documentation/RCU/whatisRCU.rst b/Documentation/RCU/whatisRCU.rst
index 60ce02475142..872ac665223f 100644
--- a/Documentation/RCU/whatisRCU.rst
+++ b/Documentation/RCU/whatisRCU.rst
@@ -172,14 +172,25 @@ rcu_read_lock()
 	critical section.  Reference counts may be used in conjunction
 	with RCU to maintain longer-term references to data structures.
 
+	Note that anything that disables bottom halves, preemption,
+	or interrupts also enters an RCU read-side critical section.
+	Acquiring a spinlock also enters an RCU read-side critical
+	sections, even for spinlocks that do not disable preemption,
+	as is the case in kernels built with CONFIG_PREEMPT_RT=y.
+	Sleeplocks do *not* enter RCU read-side critical sections.
+
 rcu_read_unlock()
 ^^^^^^^^^^^^^^^^^
 	void rcu_read_unlock(void);
 
 	This temporal primitives is used by a reader to inform the
 	reclaimer that the reader is exiting an RCU read-side critical
-	section.  Note that RCU read-side critical sections may be nested
-	and/or overlapping.
+	section.  Anything that enables bottom halves, preemption,
+	or interrupts also exits an RCU read-side critical section.
+	Releasing a spinlock also exits an RCU read-side critical section.
+
+	Note that RCU read-side critical sections may be nested and/or
+	overlapping.
 
 synchronize_rcu()
 ^^^^^^^^^^^^^^^^^
@@ -952,8 +963,8 @@ unfortunately any spinlock in a ``SLAB_TYPESAFE_BY_RCU`` object must be
 initialized after each and every call to kmem_cache_alloc(), which renders
 reference-free spinlock acquisition completely unsafe.  Therefore, when
 using ``SLAB_TYPESAFE_BY_RCU``, make proper use of a reference counter.
-(Those willing to use a kmem_cache constructor may also use locking,
-including cache-friendly sequence locking.)
+(Those willing to initialize their locks in a kmem_cache constructor
+may also use locking, including cache-friendly sequence locking.)
 
 With traditional reference counting -- such as that implemented by the
 kref library in Linux -- there is typically code that runs when the last
diff --git a/Documentation/accel/introduction.rst b/Documentation/accel/introduction.rst
index 89984dfececf..ae3030136637 100644
--- a/Documentation/accel/introduction.rst
+++ b/Documentation/accel/introduction.rst
@@ -101,8 +101,8 @@ External References
 email threads
 -------------
 
-* `Initial discussion on the New subsystem for acceleration devices <https://lkml.org/lkml/2022/7/31/83>`_ - Oded Gabbay (2022)
-* `patch-set to add the new subsystem <https://lkml.org/lkml/2022/10/22/544>`_ - Oded Gabbay (2022)
+* `Initial discussion on the New subsystem for acceleration devices <https://lore.kernel.org/lkml/CAFCwf11=9qpNAepL7NL+YAV_QO=Wv6pnWPhKHKAepK3fNn+2Dg@mail.gmail.com/>`_ - Oded Gabbay (2022)
+* `patch-set to add the new subsystem <https://lore.kernel.org/lkml/20221022214622.18042-1-ogabbay@kernel.org/>`_ - Oded Gabbay (2022)
 
 Conference talks
 ----------------
diff --git a/Documentation/admin-guide/acpi/cppc_sysfs.rst b/Documentation/admin-guide/acpi/cppc_sysfs.rst
index e53d76365aa7..36981c667823 100644
--- a/Documentation/admin-guide/acpi/cppc_sysfs.rst
+++ b/Documentation/admin-guide/acpi/cppc_sysfs.rst
@@ -75,4 +75,4 @@ taking two different snapshots of feedback counters at time T1 and T2.
   delivered_counter_delta = fbc_t2[del] - fbc_t1[del]
   reference_counter_delta = fbc_t2[ref] - fbc_t1[ref]
 
-  delivered_perf = (refernce_perf x delivered_counter_delta) / reference_counter_delta
+  delivered_perf = (reference_perf x delivered_counter_delta) / reference_counter_delta
diff --git a/Documentation/admin-guide/cifs/todo.rst b/Documentation/admin-guide/cifs/todo.rst
index 2646ed2e2d3e..9a65c670774e 100644
--- a/Documentation/admin-guide/cifs/todo.rst
+++ b/Documentation/admin-guide/cifs/todo.rst
@@ -2,7 +2,8 @@
 TODO
 ====
 
-Version 2.14 December 21, 2018
+As of 6.7 kernel. See https://wiki.samba.org/index.php/LinuxCIFSKernel
+for list of features added by release
 
 A Partial List of Missing Features
 ==================================
@@ -12,22 +13,22 @@ for visible, important contributions to this module.  Here
 is a partial list of the known problems and missing features:
 
 a) SMB3 (and SMB3.1.1) missing optional features:
+   multichannel performance optimizations, algorithmic channel selection,
+   directory leases optimizations,
+   support for faster packet signing (GMAC),
+   support for compression over the network,
+   T10 copy offload ie "ODX" (copy chunk, and "Duplicate Extents" ioctl
+   are currently the only two server side copy mechanisms supported)
 
-   - multichannel (partially integrated), integration of multichannel with RDMA
-   - directory leases (improved metadata caching). Currently only implemented for root dir
-   - T10 copy offload ie "ODX" (copy chunk, and "Duplicate Extents" ioctl
-     currently the only two server side copy mechanisms supported)
+b) Better optimized compounding and error handling for sparse file support,
+   perhaps addition of new optional SMB3.1.1 fsctls to make collapse range
+   and insert range more atomic
 
-b) improved sparse file support (fiemap and SEEK_HOLE are implemented
-   but additional features would be supportable by the protocol such
-   as FALLOC_FL_COLLAPSE_RANGE and FALLOC_FL_INSERT_RANGE)
-
-c) Directory entry caching relies on a 1 second timer, rather than
-   using Directory Leases, currently only the root file handle is cached longer
-   by leveraging Directory Leases
+c) Support for SMB3.1.1 over QUIC (and perhaps other socket based protocols
+   like SCTP)
 
 d) quota support (needs minor kernel change since quota calls otherwise
-    won't make it to network filesystems or deviceless filesystems).
+   won't make it to network filesystems or deviceless filesystems).
 
 e) Additional use cases can be optimized to use "compounding" (e.g.
    open/query/close and open/setinfo/close) to reduce the number of
@@ -92,23 +93,20 @@ t) split cifs and smb3 support into separate modules so legacy (and less
 
 v) Additional testing of POSIX Extensions for SMB3.1.1
 
-w) Add support for additional strong encryption types, and additional spnego
-   authentication mechanisms (see MS-SMB2).  GCM-256 is now partially implemented.
+w) Support for the Mac SMB3.1.1 extensions to improve interop with Apple servers
+
+x) Support for additional authentication options (e.g. IAKERB, peer-to-peer
+   Kerberos, SCRAM and others supported by existing servers)
 
-x) Finish support for SMB3.1.1 compression
+y) Improved tracing, more eBPF trace points, better scripts for performance
+   analysis
 
 Known Bugs
 ==========
 
 See https://bugzilla.samba.org - search on product "CifsVFS" for
 current bug list.  Also check http://bugzilla.kernel.org (Product = File System, Component = CIFS)
-
-1) existing symbolic links (Windows reparse points) are recognized but
-   can not be created remotely. They are implemented for Samba and those that
-   support the CIFS Unix extensions, although earlier versions of Samba
-   overly restrict the pathnames.
-2) follow_link and readdir code does not follow dfs junctions
-   but recognizes them
+and xfstest results e.g. https://wiki.samba.org/index.php/Xfstest-results-smb3
 
 Misc testing to do
 ==================
diff --git a/Documentation/admin-guide/cifs/usage.rst b/Documentation/admin-guide/cifs/usage.rst
index 5f936b4b6018..aa8290a29dc8 100644
--- a/Documentation/admin-guide/cifs/usage.rst
+++ b/Documentation/admin-guide/cifs/usage.rst
@@ -81,7 +81,7 @@ much older and less secure than the default dialect SMB3 which includes
 many advanced security features such as downgrade attack detection
 and encrypted shares and stronger signing and authentication algorithms.
 There are additional mount options that may be helpful for SMB3 to get
-improved POSIX behavior (NB: can use vers=3.0 to force only SMB3, never 2.1):
+improved POSIX behavior (NB: can use vers=3 to force SMB3 or later, never 2.1):
 
    ``mfsymlinks`` and either ``cifsacl`` or ``modefromsid`` (usually with ``idsfromsid``)
 
@@ -715,6 +715,7 @@ DebugData		Displays information about active CIFS sessions and
 Stats			Lists summary resource usage information as well as per
 			share statistics.
 open_files		List all the open file handles on all active SMB sessions.
+mount_params            List of all mount parameters available for the module
 ======================= =======================================================
 
 Configuration pseudo-files:
@@ -864,6 +865,11 @@ i.e.::
 
     echo "value" > /sys/module/cifs/parameters/<param>
 
+More detailed descriptions of the available module parameters and their values
+can be seen by doing:
+
+    modinfo cifs (or modinfo smb3)
+
 ================= ==========================================================
 1. enable_oplocks Enable or disable oplocks. Oplocks are enabled by default.
 		  [Y/y/1]. To disable use any of [N/n/0].
diff --git a/Documentation/admin-guide/devices.txt b/Documentation/admin-guide/devices.txt
index 839054923530..94c98be1329a 100644
--- a/Documentation/admin-guide/devices.txt
+++ b/Documentation/admin-guide/devices.txt
@@ -2704,6 +2704,9 @@
 		    ...
 		 185 = /dev/ttyNX15		Hilscher netX serial port 15
 		 186 = /dev/ttyJ0		JTAG1 DCC protocol based serial port emulation
+
+		 If maximum number of uartlite serial ports is more than 4, then the driver
+		 uses dynamic allocation instead of static allocation for major number.
 		 187 = /dev/ttyUL0		Xilinx uartlite - port 0
 		    ...
 		 190 = /dev/ttyUL3		Xilinx uartlite - port 3
diff --git a/Documentation/admin-guide/features.rst b/Documentation/admin-guide/features.rst
index 8c167082a84f..7651eca38227 100644
--- a/Documentation/admin-guide/features.rst
+++ b/Documentation/admin-guide/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features
+.. kernel-feat:: features
diff --git a/Documentation/admin-guide/hw_random.rst b/Documentation/admin-guide/hw_random.rst
index d494601717f1..bfc39f1cf470 100644
--- a/Documentation/admin-guide/hw_random.rst
+++ b/Documentation/admin-guide/hw_random.rst
@@ -14,10 +14,9 @@ into that core.
 
 To make the most effective use of these mechanisms, you
 should download the support software as well.  Download the
-latest version of the "rng-tools" package from the
-hw_random driver's official Web site:
+latest version of the "rng-tools" package from:
 
-	http://sourceforge.net/projects/gkernel/
+	https://github.com/nhorman/rng-tools
 
 Those tools use /dev/hwrng to fill the kernel entropy pool,
 which is used internally and exported by the /dev/urandom and
diff --git a/Documentation/admin-guide/kernel-parameters.rst b/Documentation/admin-guide/kernel-parameters.rst
index 102937bc8443..e8bdf5e86a9b 100644
--- a/Documentation/admin-guide/kernel-parameters.rst
+++ b/Documentation/admin-guide/kernel-parameters.rst
@@ -108,6 +108,7 @@ is applicable::
 	CMA	Contiguous Memory Area support is enabled.
 	DRM	Direct Rendering Management support is enabled.
 	DYNAMIC_DEBUG Build in debug messages and enable them at runtime
+	EARLY	Parameter processed too early to be embedded in initrd.
 	EDD	BIOS Enhanced Disk Drive Services (EDD) is enabled
 	EFI	EFI Partitioning (GPT) is enabled
 	EVM	Extended Verification Module
@@ -218,8 +219,3 @@ bytes respectively. Such letter suffixes can also be entirely omitted:
 
 .. include:: kernel-parameters.txt
    :literal:
-
-Todo
-----
-
-	Add more DRM drivers.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 6ee0f9a5da70..e8f675cc22fd 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -9,7 +9,7 @@
 			accept_memory=eager can be used to accept all memory
 			at once during boot.
 
-	acpi=		[HW,ACPI,X86,ARM64,RISCV64]
+	acpi=		[HW,ACPI,X86,ARM64,RISCV64,EARLY]
 			Advanced Configuration and Power Interface
 			Format: { force | on | off | strict | noirq | rsdt |
 				  copy_dsdt }
@@ -26,7 +26,7 @@
 
 			See also Documentation/power/runtime_pm.rst, pci=noacpi
 
-	acpi_apic_instance=	[ACPI, IOAPIC]
+	acpi_apic_instance=	[ACPI,IOAPIC,EARLY]
 			Format: <int>
 			2: use 2nd APIC table, if available
 			1,0: use 1st APIC table
@@ -41,7 +41,7 @@
 			If set to native, use the device's native backlight mode.
 			If set to none, disable the ACPI backlight interface.
 
-	acpi_force_32bit_fadt_addr
+	acpi_force_32bit_fadt_addr [ACPI,EARLY]
 			force FADT to use 32 bit addresses rather than the
 			64 bit X_* addresses. Some firmware have broken 64
 			bit addresses for force ACPI ignore these and use
@@ -97,7 +97,7 @@
 			no: ACPI OperationRegions are not marked as reserved,
 			no further checks are performed.
 
-	acpi_force_table_verification	[HW,ACPI]
+	acpi_force_table_verification	[HW,ACPI,EARLY]
 			Enable table checksum verification during early stage.
 			By default, this is disabled due to x86 early mapping
 			size limitation.
@@ -137,7 +137,7 @@
 	acpi_no_memhotplug [ACPI] Disable memory hotplug.  Useful for kdump
 			   kernels.
 
-	acpi_no_static_ssdt	[HW,ACPI]
+	acpi_no_static_ssdt	[HW,ACPI,EARLY]
 			Disable installation of static SSDTs at early boot time
 			By default, SSDTs contained in the RSDT/XSDT will be
 			installed automatically and they will appear under
@@ -151,7 +151,7 @@
 			Ignore the ACPI-based watchdog interface (WDAT) and let
 			a native driver control the watchdog device instead.
 
-	acpi_rsdp=	[ACPI,EFI,KEXEC]
+	acpi_rsdp=	[ACPI,EFI,KEXEC,EARLY]
 			Pass the RSDP address to the kernel, mostly used
 			on machines running EFI runtime service to boot the
 			second kernel for kdump.
@@ -228,10 +228,10 @@
 			to assume that this machine's pmtimer latches its value
 			and always returns good values.
 
-	acpi_sci=	[HW,ACPI] ACPI System Control Interrupt trigger mode
+	acpi_sci=	[HW,ACPI,EARLY] ACPI System Control Interrupt trigger mode
 			Format: { level | edge | high | low }
 
-	acpi_skip_timer_override [HW,ACPI]
+	acpi_skip_timer_override [HW,ACPI,EARLY]
 			Recognize and ignore IRQ0/pin2 Interrupt Override.
 			For broken nForce2 BIOS resulting in XT-PIC timer.
 
@@ -266,11 +266,11 @@
 			behave incorrectly in some ways with respect to system
 			suspend and resume to be ignored (use wisely).
 
-	acpi_use_timer_override [HW,ACPI]
+	acpi_use_timer_override [HW,ACPI,EARLY]
 			Use timer override. For some broken Nvidia NF5 boards
 			that require a timer override, but don't have HPET
 
-	add_efi_memmap	[EFI; X86] Include EFI memory map in
+	add_efi_memmap	[EFI,X86,EARLY] Include EFI memory map in
 			kernel's map of available physical RAM.
 
 	agp=		[AGP]
@@ -307,7 +307,7 @@
 			do not want to use tracing_snapshot_alloc() as it needs
 			to be done where GFP_KERNEL allocations are allowed.
 
-	allow_mismatched_32bit_el0 [ARM64]
+	allow_mismatched_32bit_el0 [ARM64,EARLY]
 			Allow execve() of 32-bit applications and setting of the
 			PER_LINUX32 personality on systems where only a strict
 			subset of the CPUs support 32-bit EL0. When this
@@ -351,7 +351,7 @@
 			             This mode requires kvm-amd.avic=1.
 			             (Default when IOMMU HW support is present.)
 
-	amd_pstate=	[X86]
+	amd_pstate=	[X86,EARLY]
 			disable
 			  Do not enable amd_pstate as the default
 			  scaling driver for the supported processors
@@ -391,7 +391,7 @@
 			not play well with APC CPU idle - disable it if you have
 			APC and your system crashes randomly.
 
-	apic=		[APIC,X86] Advanced Programmable Interrupt Controller
+	apic=		[APIC,X86,EARLY] Advanced Programmable Interrupt Controller
 			Change the output verbosity while booting
 			Format: { quiet (default) | verbose | debug }
 			Change the amount of debugging information output
@@ -401,7 +401,7 @@
 			Format: apic=driver_name
 			Examples: apic=bigsmp
 
-	apic_extnmi=	[APIC,X86] External NMI delivery setting
+	apic_extnmi=	[APIC,X86,EARLY] External NMI delivery setting
 			Format: { bsp (default) | all | none }
 			bsp:  External NMI is delivered only to CPU 0
 			all:  External NMIs are broadcast to all CPUs as a
@@ -508,21 +508,22 @@
 	bert_disable	[ACPI]
 			Disable BERT OS support on buggy BIOSes.
 
-	bgrt_disable	[ACPI][X86]
+	bgrt_disable	[ACPI,X86,EARLY]
 			Disable BGRT to avoid flickering OEM logo.
 
 	blkdevparts=	Manual partition parsing of block device(s) for
 			embedded devices based on command line input.
 			See Documentation/block/cmdline-partition.rst
 
-	boot_delay=	Milliseconds to delay each printk during boot.
+	boot_delay=	[KNL,EARLY]
+			Milliseconds to delay each printk during boot.
 			Only works if CONFIG_BOOT_PRINTK_DELAY is enabled,
 			and you may also have to specify "lpj=".  Boot_delay
 			values larger than 10 seconds (10000) are assumed
 			erroneous and ignored.
 			Format: integer
 
-	bootconfig	[KNL]
+	bootconfig	[KNL,EARLY]
 			Extended command line options can be added to an initrd
 			and this will cause the kernel to look for it.
 
@@ -557,7 +558,7 @@
 			trust validation.
 			format: { id:<keyid> | builtin }
 
-	cca=		[MIPS] Override the kernel pages' cache coherency
+	cca=		[MIPS,EARLY] Override the kernel pages' cache coherency
 			algorithm.  Accepted values range from 0 to 7
 			inclusive. See arch/mips/include/asm/pgtable-bits.h
 			for platform specific values (SB1, Loongson3 and
@@ -672,7 +673,7 @@
 			[X86-64] hpet,tsc
 
 	clocksource.arm_arch_timer.evtstrm=
-			[ARM,ARM64]
+			[ARM,ARM64,EARLY]
 			Format: <bool>
 			Enable/disable the eventstream feature of the ARM
 			architected timer so that code using WFE-based polling
@@ -702,7 +703,7 @@
 			10 seconds when built into the kernel.
 
 	cma=nn[MG]@[start[MG][-end[MG]]]
-			[KNL,CMA]
+			[KNL,CMA,EARLY]
 			Sets the size of kernel global memory area for
 			contiguous memory allocations and optionally the
 			placement constraint by the physical address range of
@@ -711,7 +712,7 @@
 			kernel/dma/contiguous.c
 
 	cma_pernuma=nn[MG]
-			[KNL,CMA]
+			[KNL,CMA,EARLY]
 			Sets the size of kernel per-numa memory area for
 			contiguous memory allocations. A value of 0 disables
 			per-numa CMA altogether. And If this option is not
@@ -722,7 +723,7 @@
 			they will fallback to the global default memory area.
 
 	numa_cma=<node>:nn[MG][,<node>:nn[MG]]
-			[KNL,CMA]
+			[KNL,CMA,EARLY]
 			Sets the size of kernel numa memory area for
 			contiguous memory allocations. It will reserve CMA
 			area for the specified node.
@@ -739,7 +740,7 @@
 			a hypervisor.
 			Default: yes
 
-	coherent_pool=nn[KMG]	[ARM,KNL]
+	coherent_pool=nn[KMG]	[ARM,KNL,EARLY]
 			Sets the size of memory pool for coherent, atomic dma
 			allocations, by default set to 256K.
 
@@ -757,7 +758,7 @@
 	condev=		[HW,S390] console device
 	conmode=
 
-	con3215_drop=	[S390] 3215 console drop mode.
+	con3215_drop=	[S390,EARLY] 3215 console drop mode.
 			Format: y|n|Y|N|1|0
 			When set to true, drop data on the 3215 console when
 			the console buffer is full. In this case the
@@ -863,7 +864,7 @@
 			kernel before the cpufreq driver probes.
 
 	cpu_init_udelay=N
-			[X86] Delay for N microsec between assert and de-assert
+			[X86,EARLY] Delay for N microsec between assert and de-assert
 			of APIC INIT to start processors.  This delay occurs
 			on every CPU online, such as boot, and resume from suspend.
 			Default: 10000
@@ -883,14 +884,14 @@
 			kernel more unstable.
 
 	crashkernel=size[KMG][@offset[KMG]]
-			[KNL] Using kexec, Linux can switch to a 'crash kernel'
+			[KNL,EARLY] Using kexec, Linux can switch to a 'crash kernel'
 			upon panic. This parameter reserves the physical
 			memory region [offset, offset + size] for that kernel
 			image. If '@offset' is omitted, then a suitable offset
 			is selected automatically.
-			[KNL, X86-64, ARM64, RISCV] Select a region under 4G first, and
-			fall back to reserve region above 4G when '@offset'
-			hasn't been specified.
+			[KNL, X86-64, ARM64, RISCV, LoongArch] Select a region
+			under 4G first, and fall back to reserve region above
+			4G when '@offset' hasn't been specified.
 			See Documentation/admin-guide/kdump/kdump.rst for further details.
 
 	crashkernel=range1:size1[,range2:size2,...][@offset]
@@ -901,25 +902,27 @@
 			Documentation/admin-guide/kdump/kdump.rst for an example.
 
 	crashkernel=size[KMG],high
-			[KNL, X86-64, ARM64, RISCV] range could be above 4G.
+			[KNL, X86-64, ARM64, RISCV, LoongArch] range could be
+			above 4G.
 			Allow kernel to allocate physical memory region from top,
 			so could be above 4G if system have more than 4G ram
 			installed. Otherwise memory region will be allocated
 			below 4G, if available.
 			It will be ignored if crashkernel=X is specified.
 	crashkernel=size[KMG],low
-			[KNL, X86-64, ARM64, RISCV] range under 4G. When crashkernel=X,high
-			is passed, kernel could allocate physical memory region
-			above 4G, that cause second kernel crash on system
-			that require some amount of low memory, e.g. swiotlb
-			requires at least 64M+32K low memory, also enough extra
-			low memory is needed to make sure DMA buffers for 32-bit
-			devices won't run out. Kernel would try to allocate
+			[KNL, X86-64, ARM64, RISCV, LoongArch] range under 4G.
+			When crashkernel=X,high is passed, kernel could allocate
+			physical memory region above 4G, that cause second kernel
+			crash on system that require some amount of low memory,
+			e.g. swiotlb requires at least 64M+32K low memory, also
+			enough extra low memory is needed to make sure DMA buffers
+			for 32-bit devices won't run out. Kernel would try to allocate
 			default	size of memory below 4G automatically. The default
 			size is	platform dependent.
 			  --> x86: max(swiotlb_size_or_default() + 8MiB, 256MiB)
 			  --> arm64: 128MiB
 			  --> riscv: 128MiB
+			  --> loongarch: 128MiB
 			This one lets the user specify own low range under 4G
 			for second kernel instead.
 			0: to disable low allocation.
@@ -952,10 +955,10 @@
 			Format: <port#>,<type>
 			See also Documentation/input/devices/joystick-parport.rst
 
-	debug		[KNL] Enable kernel debugging (events log level).
+	debug		[KNL,EARLY] Enable kernel debugging (events log level).
 
 	debug_boot_weak_hash
-			[KNL] Enable printing [hashed] pointers early in the
+			[KNL,EARLY] Enable printing [hashed] pointers early in the
 			boot sequence.  If enabled, we use a weak hash instead
 			of siphash to hash pointers.  Use this option if you are
 			seeing instances of '(___ptrval___)') and need to see a
@@ -972,10 +975,10 @@
 			will print _a_lot_ more information - normally only
 			useful to lockdep developers.
 
-	debug_objects	[KNL] Enable object debugging
+	debug_objects	[KNL,EARLY] Enable object debugging
 
 	debug_guardpage_minorder=
-			[KNL] When CONFIG_DEBUG_PAGEALLOC is set, this
+			[KNL,EARLY] When CONFIG_DEBUG_PAGEALLOC is set, this
 			parameter allows control of the order of pages that will
 			be intentionally kept free (and hence protected) by the
 			buddy allocator. Bigger value increase the probability
@@ -994,7 +997,7 @@
 			help tracking down these problems.
 
 	debug_pagealloc=
-			[KNL] When CONFIG_DEBUG_PAGEALLOC is set, this parameter
+			[KNL,EARLY] When CONFIG_DEBUG_PAGEALLOC is set, this parameter
 			enables the feature at boot time. By default, it is
 			disabled and the system will work mostly the same as a
 			kernel built without CONFIG_DEBUG_PAGEALLOC.
@@ -1002,8 +1005,8 @@
 			useful to also enable the page_owner functionality.
 			on: enable the feature
 
-	debugfs=    	[KNL] This parameter enables what is exposed to userspace
-			and debugfs internal clients.
+	debugfs=    	[KNL,EARLY] This parameter enables what is exposed to
+			userspace and debugfs internal clients.
 			Format: { on, no-mount, off }
 			on: 	All functions are enabled.
 			no-mount:
@@ -1082,7 +1085,7 @@
 	dhash_entries=	[KNL]
 			Set number of hash buckets for dentry cache.
 
-	disable_1tb_segments [PPC]
+	disable_1tb_segments [PPC,EARLY]
 			Disables the use of 1TB hash page table segments. This
 			causes the kernel to fall back to 256MB segments which
 			can be useful when debugging issues that require an SLB
@@ -1091,7 +1094,7 @@
 	disable=	[IPV6]
 			See Documentation/networking/ipv6.rst.
 
-	disable_radix	[PPC]
+	disable_radix	[PPC,EARLY]
 			Disable RADIX MMU mode on POWER9
 
 	disable_tlbie	[PPC]
@@ -1107,25 +1110,25 @@
 			causing system reset or hang due to sending
 			INIT from AP to BSP.
 
-	disable_ddw	[PPC/PSERIES]
+	disable_ddw	[PPC/PSERIES,EARLY]
 			Disable Dynamic DMA Window support. Use this
 			to workaround buggy firmware.
 
 	disable_ipv6=	[IPV6]
 			See Documentation/networking/ipv6.rst.
 
-	disable_mtrr_cleanup [X86]
+	disable_mtrr_cleanup [X86,EARLY]
 			The kernel tries to adjust MTRR layout from continuous
 			to discrete, to make X server driver able to add WB
 			entry later. This parameter disables that.
 
-	disable_mtrr_trim [X86, Intel and AMD only]
+	disable_mtrr_trim [X86, Intel and AMD only,EARLY]
 			By default the kernel will trim any uncacheable
 			memory out of your available memory pool based on
 			MTRR settings.  This parameter disables that behavior,
 			possibly causing your machine to run very slowly.
 
-	disable_timer_pin_1 [X86]
+	disable_timer_pin_1 [X86,EARLY]
 			Disable PIN 1 of APIC timer
 			Can be useful to work around chipset bugs.
 
@@ -1175,7 +1178,7 @@
 
 	dscc4.setup=	[NET]
 
-	dt_cpu_ftrs=	[PPC]
+	dt_cpu_ftrs=	[PPC,EARLY]
 			Format: {"off" | "known"}
 			Control how the dt_cpu_ftrs device-tree binding is
 			used for CPU feature discovery and setup (if it
@@ -1195,12 +1198,12 @@
 			Documentation/admin-guide/dynamic-debug-howto.rst
 			for details.
 
-	early_ioremap_debug [KNL]
+	early_ioremap_debug [KNL,EARLY]
 			Enable debug messages in early_ioremap support. This
 			is useful for tracking down temporary early mappings
 			which are not unmapped.
 
-	earlycon=	[KNL] Output early console device and options.
+	earlycon=	[KNL,EARLY] Output early console device and options.
 
 			When used with no options, the early console is
 			determined by stdout-path property in device tree's
@@ -1336,7 +1339,7 @@
 			address must be provided, and the serial port must
 			already be setup and configured.
 
-	earlyprintk=	[X86,SH,ARM,M68k,S390]
+	earlyprintk=	[X86,SH,ARM,M68k,S390,UM,EARLY]
 			earlyprintk=vga
 			earlyprintk=sclp
 			earlyprintk=xen
@@ -1394,7 +1397,7 @@
 	edd=		[EDD]
 			Format: {"off" | "on" | "skip[mbr]"}
 
-	efi=		[EFI]
+	efi=		[EFI,EARLY]
 			Format: { "debug", "disable_early_pci_dma",
 				  "nochunk", "noruntime", "nosoftreserve",
 				  "novamap", "no_disable_early_pci_dma" }
@@ -1415,13 +1418,13 @@
 			no_disable_early_pci_dma: Leave the busmaster bit set
 			on all PCI bridges while in the EFI boot stub
 
-	efi_no_storage_paranoia [EFI; X86]
+	efi_no_storage_paranoia [EFI,X86,EARLY]
 			Using this parameter you can use more than 50% of
 			your efi variable storage. Use this parameter only if
 			you are really sure that your UEFI does sane gc and
 			fulfills the spec otherwise your board may brick.
 
-	efi_fake_mem=	nn[KMG]@ss[KMG]:aa[,nn[KMG]@ss[KMG]:aa,..] [EFI; X86]
+	efi_fake_mem=	nn[KMG]@ss[KMG]:aa[,nn[KMG]@ss[KMG]:aa,..] [EFI,X86,EARLY]
 			Add arbitrary attribute to specific memory range by
 			updating original EFI memory map.
 			Region of memory which aa attribute is added to is
@@ -1452,7 +1455,7 @@
 	eisa_irq_edge=	[PARISC,HW]
 			See header of drivers/parisc/eisa.c.
 
-	ekgdboc=	[X86,KGDB] Allow early kernel console debugging
+	ekgdboc=	[X86,KGDB,EARLY] Allow early kernel console debugging
 			Format: ekgdboc=kbd
 
 			This is designed to be used in conjunction with
@@ -1467,13 +1470,13 @@
 			See comment before function elanfreq_setup() in
 			arch/x86/kernel/cpu/cpufreq/elanfreq.c.
 
-	elfcorehdr=[size[KMG]@]offset[KMG] [PPC,SH,X86,S390]
+	elfcorehdr=[size[KMG]@]offset[KMG] [PPC,SH,X86,S390,EARLY]
 			Specifies physical address of start of kernel core
 			image elf header and optionally the size. Generally
 			kexec loader will pass this option to capture kernel.
 			See Documentation/admin-guide/kdump/kdump.rst for details.
 
-	enable_mtrr_cleanup [X86]
+	enable_mtrr_cleanup [X86,EARLY]
 			The kernel tries to adjust MTRR layout from continuous
 			to discrete, to make X server driver able to add WB
 			entry later. This parameter enables that.
@@ -1506,7 +1509,7 @@
 			Permit 'security.evm' to be updated regardless of
 			current integrity status.
 
-	early_page_ext [KNL] Enforces page_ext initialization to earlier
+	early_page_ext [KNL,EARLY] Enforces page_ext initialization to earlier
 			stages so cover more early boot allocations.
 			Please note that as side effect some optimizations
 			might be disabled to achieve that (e.g. parallelized
@@ -1598,7 +1601,7 @@
 			can be changed at run time by the max_graph_depth file
 			in the tracefs tracing directory. default: 0 (no limit)
 
-	fw_devlink=	[KNL] Create device links between consumer and supplier
+	fw_devlink=	[KNL,EARLY] Create device links between consumer and supplier
 			devices by scanning the firmware to infer the
 			consumer/supplier relationships. This feature is
 			especially useful when drivers are loaded as modules as
@@ -1617,12 +1620,12 @@
 			rpm --	Like "on", but also use to order runtime PM.
 
 	fw_devlink.strict=<bool>
-			[KNL] Treat all inferred dependencies as mandatory
+			[KNL,EARLY] Treat all inferred dependencies as mandatory
 			dependencies. This only applies for fw_devlink=on|rpm.
 			Format: <bool>
 
 	fw_devlink.sync_state =
-			[KNL] When all devices that could probe have finished
+			[KNL,EARLY] When all devices that could probe have finished
 			probing, this parameter controls what to do with
 			devices that haven't yet received their sync_state()
 			calls.
@@ -1643,12 +1646,12 @@
 
 	gamma=		[HW,DRM]
 
-	gart_fix_e820=	[X86-64] disable the fix e820 for K8 GART
+	gart_fix_e820=	[X86-64,EARLY] disable the fix e820 for K8 GART
 			Format: off | on
 			default: on
 
 	gather_data_sampling=
-			[X86,INTEL] Control the Gather Data Sampling (GDS)
+			[X86,INTEL,EARLY] Control the Gather Data Sampling (GDS)
 			mitigation.
 
 			Gather Data Sampling is a hardware vulnerability which
@@ -1746,7 +1749,7 @@
 				(that will set all pages holding image data
 				during restoration read-only).
 
-	highmem=nn[KMG]	[KNL,BOOT] forces the highmem zone to have an exact
+	highmem=nn[KMG]	[KNL,BOOT,EARLY] forces the highmem zone to have an exact
 			size of <nn>. This works even on boxes that have no
 			highmem otherwise. This also works to reduce highmem
 			size on bigger boxes.
@@ -1757,7 +1760,7 @@
 
 	hlt		[BUGS=ARM,SH]
 
-	hostname=	[KNL] Set the hostname (aka UTS nodename).
+	hostname=	[KNL,EARLY] Set the hostname (aka UTS nodename).
 			Format: <string>
 			This allows setting the system's hostname during early
 			startup. This sets the name returned by gethostname.
@@ -1802,7 +1805,7 @@
 			Documentation/admin-guide/mm/hugetlbpage.rst.
 			Format: size[KMG]
 
-	hugetlb_cma=	[HW,CMA] The size of a CMA area used for allocation
+	hugetlb_cma=	[HW,CMA,EARLY] The size of a CMA area used for allocation
 			of gigantic hugepages. Or using node format, the size
 			of a CMA area per node can be specified.
 			Format: nn[KMGTPE] or (node format)
@@ -1848,9 +1851,10 @@
 				If specified, z/VM IUCV HVC accepts connections
 				from listed z/VM user IDs only.
 
-	hv_nopvspin	[X86,HYPER_V] Disables the paravirt spinlock optimizations
-				      which allow the hypervisor to 'idle' the
-				      guest on lock contention.
+	hv_nopvspin	[X86,HYPER_V,EARLY]
+			Disables the paravirt spinlock optimizations
+			which allow the hypervisor to 'idle' the guest
+			on lock contention.
 
 	i2c_bus=	[HW]	Override the default board specific I2C bus speed
 				or register an additional I2C bus that is not
@@ -1915,7 +1919,7 @@
 			Format: <io>[,<membase>[,<icn_id>[,<icn_id2>]]]
 
 
-	idle=		[X86]
+	idle=		[X86,EARLY]
 			Format: idle=poll, idle=halt, idle=nomwait
 			Poll forces a polling idle loop that can slightly
 			improve the performance of waking up a idle CPU, but
@@ -1971,7 +1975,7 @@
 			mode generally follows that for the NaN encoding,
 			except where unsupported by hardware.
 
-	ignore_loglevel	[KNL]
+	ignore_loglevel	[KNL,EARLY]
 			Ignore loglevel setting - this will print /all/
 			kernel messages to the console. Useful for debugging.
 			We also add it as printk module parameter, so users
@@ -2089,21 +2093,21 @@
 			unpacking being completed before device_ and
 			late_ initcalls.
 
-	initrd=		[BOOT] Specify the location of the initial ramdisk
+	initrd=		[BOOT,EARLY] Specify the location of the initial ramdisk
 
-	initrdmem=	[KNL] Specify a physical address and size from which to
+	initrdmem=	[KNL,EARLY] Specify a physical address and size from which to
 			load the initrd. If an initrd is compiled in or
 			specified in the bootparams, it takes priority over this
 			setting.
 			Format: ss[KMG],nn[KMG]
 			Default is 0, 0
 
-	init_on_alloc=	[MM] Fill newly allocated pages and heap objects with
+	init_on_alloc=	[MM,EARLY] Fill newly allocated pages and heap objects with
 			zeroes.
 			Format: 0 | 1
 			Default set by CONFIG_INIT_ON_ALLOC_DEFAULT_ON.
 
-	init_on_free=	[MM] Fill freed pages and heap objects with zeroes.
+	init_on_free=	[MM,EARLY] Fill freed pages and heap objects with zeroes.
 			Format: 0 | 1
 			Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON.
 
@@ -2159,7 +2163,7 @@
 			0	disables intel_idle and fall back on acpi_idle.
 			1 to 9	specify maximum depth of C-state.
 
-	intel_pstate=	[X86]
+	intel_pstate=	[X86,EARLY]
 			disable
 			  Do not enable intel_pstate as the default
 			  scaling driver for the supported processors
@@ -2203,7 +2207,7 @@
 			  Allow per-logical-CPU P-State performance control limits using
 			  cpufreq sysfs interface
 
-	intremap=	[X86-64, Intel-IOMMU]
+	intremap=	[X86-64,Intel-IOMMU,EARLY]
 			on	enable Interrupt Remapping (default)
 			off	disable Interrupt Remapping
 			nosid	disable Source ID checking
@@ -2215,7 +2219,7 @@
 		strict	regions from userspace.
 		relaxed
 
-	iommu=		[X86]
+	iommu=		[X86,EARLY]
 		off
 		force
 		noforce
@@ -2230,7 +2234,7 @@
 		nobypass	[PPC/POWERNV]
 			Disable IOMMU bypass, using IOMMU for PCI devices.
 
-	iommu.forcedac=	[ARM64, X86] Control IOVA allocation for PCI devices.
+	iommu.forcedac=	[ARM64,X86,EARLY] Control IOVA allocation for PCI devices.
 			Format: { "0" | "1" }
 			0 - Try to allocate a 32-bit DMA address first, before
 			  falling back to the full range if needed.
@@ -2238,7 +2242,7 @@
 			  forcing Dual Address Cycle for PCI cards supporting
 			  greater than 32-bit addressing.
 
-	iommu.strict=	[ARM64, X86, S390] Configure TLB invalidation behaviour
+	iommu.strict=	[ARM64,X86,S390,EARLY] Configure TLB invalidation behaviour
 			Format: { "0" | "1" }
 			0 - Lazy mode.
 			  Request that DMA unmap operations use deferred
@@ -2254,7 +2258,7 @@
 			legacy driver-specific options takes precedence.
 
 	iommu.passthrough=
-			[ARM64, X86] Configure DMA to bypass the IOMMU by default.
+			[ARM64,X86,EARLY] Configure DMA to bypass the IOMMU by default.
 			Format: { "0" | "1" }
 			0 - Use IOMMU translation for DMA.
 			1 - Bypass the IOMMU for DMA.
@@ -2264,7 +2268,7 @@
 			See comment before marvel_specify_io7 in
 			arch/alpha/kernel/core_marvel.c.
 
-	io_delay=	[X86] I/O delay method
+	io_delay=	[X86,EARLY] I/O delay method
 		0x80
 			Standard port 0x80 based delay
 		0xed
@@ -2277,28 +2281,28 @@
 	ip=		[IP_PNP]
 			See Documentation/admin-guide/nfs/nfsroot.rst.
 
-	ipcmni_extend	[KNL] Extend the maximum number of unique System V
+	ipcmni_extend	[KNL,EARLY] Extend the maximum number of unique System V
 			IPC identifiers from 32,768 to 16,777,216.
 
 	irqaffinity=	[SMP] Set the default irq affinity mask
 			The argument is a cpu list, as described above.
 
 	irqchip.gicv2_force_probe=
-			[ARM, ARM64]
+			[ARM,ARM64,EARLY]
 			Format: <bool>
 			Force the kernel to look for the second 4kB page
 			of a GICv2 controller even if the memory range
 			exposed by the device tree is too small.
 
 	irqchip.gicv3_nolpi=
-			[ARM, ARM64]
+			[ARM,ARM64,EARLY]
 			Force the kernel to ignore the availability of
 			LPIs (and by consequence ITSs). Intended for system
 			that use the kernel as a bootloader, and thus want
 			to let secondary kernels in charge of setting up
 			LPIs.
 
-	irqchip.gicv3_pseudo_nmi= [ARM64]
+	irqchip.gicv3_pseudo_nmi= [ARM64,EARLY]
 			Enables support for pseudo-NMIs in the kernel. This
 			requires the kernel to be built with
 			CONFIG_ARM64_PSEUDO_NMI.
@@ -2443,15 +2447,15 @@
 			parameter KASAN will print report only for the first
 			invalid access.
 
-	keep_bootcon	[KNL]
+	keep_bootcon	[KNL,EARLY]
 			Do not unregister boot console at start. This is only
 			useful for debugging when something happens in the window
 			between unregistering the boot console and initializing
 			the real console.
 
-	keepinitrd	[HW,ARM]
+	keepinitrd	[HW,ARM] See retain_initrd.
 
-	kernelcore=	[KNL,X86,IA-64,PPC]
+	kernelcore=	[KNL,X86,IA-64,PPC,EARLY]
 			Format: nn[KMGTPE] | nn% | "mirror"
 			This parameter specifies the amount of memory usable by
 			the kernel for non-movable allocations.  The requested
@@ -2476,7 +2480,7 @@
 			for Movable pages.  "nn[KMGTPE]", "nn%", and "mirror"
 			are exclusive, so you cannot specify multiple forms.
 
-	kgdbdbgp=	[KGDB,HW] kgdb over EHCI usb debug port.
+	kgdbdbgp=	[KGDB,HW,EARLY] kgdb over EHCI usb debug port.
 			Format: <Controller#>[,poll interval]
 			The controller # is the number of the ehci usb debug
 			port as it is probed via PCI.  The poll interval is
@@ -2497,7 +2501,7 @@
 			 kms, kbd format: kms,kbd
 			 kms, kbd and serial format: kms,kbd,<ser_dev>[,baud]
 
-	kgdboc_earlycon=	[KGDB,HW]
+	kgdboc_earlycon=	[KGDB,HW,EARLY]
 			If the boot console provides the ability to read
 			characters and can work in polling mode, you can use
 			this parameter to tell kgdb to use it as a backend
@@ -2512,14 +2516,14 @@
 			blank and the first boot console that implements
 			read() will be picked.
 
-	kgdbwait	[KGDB] Stop kernel execution and enter the
+	kgdbwait	[KGDB,EARLY] Stop kernel execution and enter the
 			kernel debugger at the earliest opportunity.
 
 	kmac=		[MIPS] Korina ethernet MAC address.
 			Configure the RouterBoard 532 series on-chip
 			Ethernet adapter MAC address.
 
-	kmemleak=	[KNL] Boot-time kmemleak enable/disable
+	kmemleak=	[KNL,EARLY] Boot-time kmemleak enable/disable
 			Valid arguments: on, off
 			Default: on
 			Built with CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y,
@@ -2538,8 +2542,8 @@
 			See also Documentation/trace/kprobetrace.rst "Kernel
 			Boot Parameter" section.
 
-	kpti=		[ARM64] Control page table isolation of user
-			and kernel address spaces.
+	kpti=		[ARM64,EARLY] Control page table isolation of
+			user and kernel address spaces.
 			Default: enabled on cores which need mitigation.
 			0: force disabled
 			1: force enabled
@@ -2616,7 +2620,8 @@
 			for NPT.
 
 	kvm-arm.mode=
-			[KVM,ARM] Select one of KVM/arm64's modes of operation.
+			[KVM,ARM,EARLY] Select one of KVM/arm64's modes of
+			operation.
 
 			none: Forcefully disable KVM.
 
@@ -2636,22 +2641,22 @@
 			used with extreme caution.
 
 	kvm-arm.vgic_v3_group0_trap=
-			[KVM,ARM] Trap guest accesses to GICv3 group-0
+			[KVM,ARM,EARLY] Trap guest accesses to GICv3 group-0
 			system registers
 
 	kvm-arm.vgic_v3_group1_trap=
-			[KVM,ARM] Trap guest accesses to GICv3 group-1
+			[KVM,ARM,EARLY] Trap guest accesses to GICv3 group-1
 			system registers
 
 	kvm-arm.vgic_v3_common_trap=
-			[KVM,ARM] Trap guest accesses to GICv3 common
+			[KVM,ARM,EARLY] Trap guest accesses to GICv3 common
 			system registers
 
 	kvm-arm.vgic_v4_enable=
-			[KVM,ARM] Allow use of GICv4 for direct injection of
-			LPIs.
+			[KVM,ARM,EARLY] Allow use of GICv4 for direct
+			injection of LPIs.
 
-	kvm_cma_resv_ratio=n [PPC]
+	kvm_cma_resv_ratio=n [PPC,EARLY]
 			Reserves given percentage from system memory area for
 			contiguous memory allocation for KVM hash pagetable
 			allocation.
@@ -2704,7 +2709,7 @@
 			(enabled). Disable by KVM if hardware lacks support
 			for it.
 
-	l1d_flush=	[X86,INTEL]
+	l1d_flush=	[X86,INTEL,EARLY]
 			Control mitigation for L1D based snooping vulnerability.
 
 			Certain CPUs are vulnerable to an exploit against CPU
@@ -2721,7 +2726,7 @@
 
 			on         - enable the interface for the mitigation
 
-	l1tf=           [X86] Control mitigation of the L1TF vulnerability on
+	l1tf=           [X86,EARLY] Control mitigation of the L1TF vulnerability on
 			      affected CPUs
 
 			The kernel PTE inversion protection is unconditionally
@@ -2790,7 +2795,7 @@
 
 	l3cr=		[PPC]
 
-	lapic		[X86-32,APIC] Enable the local APIC even if BIOS
+	lapic		[X86-32,APIC,EARLY] Enable the local APIC even if BIOS
 			disabled it.
 
 	lapic=		[X86,APIC] Do not use TSC deadline
@@ -2798,7 +2803,7 @@
 			back to the programmable timer unit in the LAPIC.
 			Format: notscdeadline
 
-	lapic_timer_c2_ok	[X86,APIC] trust the local apic timer
+	lapic_timer_c2_ok	[X86,APIC,EARLY] trust the local apic timer
 			in C2 power state.
 
 	libata.dma=	[LIBATA] DMA control
@@ -2922,7 +2927,7 @@
 	lockd.nlm_udpport=M	[NFS] Assign UDP port.
 			Format: <integer>
 
-	lockdown=	[SECURITY]
+	lockdown=	[SECURITY,EARLY]
 			{ integrity | confidentiality }
 			Enable the kernel lockdown feature. If set to
 			integrity, kernel features that allow userland to
@@ -3029,7 +3034,8 @@
 	logibm.irq=	[HW,MOUSE] Logitech Bus Mouse Driver
 			Format: <irq>
 
-	loglevel=	All Kernel Messages with a loglevel smaller than the
+	loglevel=	[KNL,EARLY]
+			All Kernel Messages with a loglevel smaller than the
 			console loglevel will be printed to the console. It can
 			also be changed with klogd or other programs. The
 			loglevels are defined as follows:
@@ -3043,13 +3049,15 @@
 			6 (KERN_INFO)		informational
 			7 (KERN_DEBUG)		debug-level messages
 
-	log_buf_len=n[KMG]	Sets the size of the printk ring buffer,
-			in bytes.  n must be a power of two and greater
-			than the minimal size. The minimal size is defined
-			by LOG_BUF_SHIFT kernel config parameter. There is
-			also CONFIG_LOG_CPU_MAX_BUF_SHIFT config parameter
-			that allows to increase the default size depending on
-			the number of CPUs. See init/Kconfig for more details.
+	log_buf_len=n[KMG] [KNL,EARLY]
+			Sets the size of the printk ring buffer, in bytes.
+			n must be a power of two and greater than the
+			minimal size. The minimal size is defined by
+			LOG_BUF_SHIFT kernel config parameter. There
+			is also CONFIG_LOG_CPU_MAX_BUF_SHIFT config
+			parameter that allows to increase the default size
+			depending on the number of CPUs. See init/Kconfig
+			for more details.
 
 	logo.nologo	[FB] Disables display of the built-in Linux logo.
 			This may be used to provide more screen space for
@@ -3107,7 +3115,7 @@
 	max_addr=nn[KMG]	[KNL,BOOT,IA-64] All physical memory greater
 			than or equal to this physical address is ignored.
 
-	maxcpus=	[SMP] Maximum number of processors that	an SMP kernel
+	maxcpus=	[SMP,EARLY] Maximum number of processors that an SMP kernel
 			will bring up during bootup.  maxcpus=n : n >= 0 limits
 			the kernel to bring up 'n' processors. Surely after
 			bootup you can bring up the other plugged cpu by executing
@@ -3134,7 +3142,7 @@
 			Format: <first>,<last>
 			Specifies range of consoles to be captured by the MDA.
 
-	mds=		[X86,INTEL]
+	mds=		[X86,INTEL,EARLY]
 			Control mitigation for the Micro-architectural Data
 			Sampling (MDS) vulnerability.
 
@@ -3166,11 +3174,12 @@
 
 			For details see: Documentation/admin-guide/hw-vuln/mds.rst
 
-	mem=nn[KMG]	[HEXAGON] Set the memory size.
+	mem=nn[KMG]	[HEXAGON,EARLY] Set the memory size.
 			Must be specified, otherwise memory size will be 0.
 
-	mem=nn[KMG]	[KNL,BOOT] Force usage of a specific amount of memory
-			Amount of memory to be used in cases as follows:
+	mem=nn[KMG]	[KNL,BOOT,EARLY] Force usage of a specific amount
+			of memory Amount of memory to be used in cases
+			as follows:
 
 			1 for test;
 			2 when the kernel is not able to see the whole system memory;
@@ -3194,8 +3203,8 @@
 			if system memory of hypervisor is not sufficient.
 
 	mem=nn[KMG]@ss[KMG]
-			[ARM,MIPS] - override the memory layout reported by
-			firmware.
+			[ARM,MIPS,EARLY] - override the memory layout
+			reported by firmware.
 			Define a memory region of size nn[KMG] starting at
 			ss[KMG].
 			Multiple different regions can be specified with
@@ -3204,7 +3213,7 @@
 	mem=nopentium	[BUGS=X86-32] Disable usage of 4MB pages for kernel
 			memory.
 
-	memblock=debug	[KNL] Enable memblock debug messages.
+	memblock=debug	[KNL,EARLY] Enable memblock debug messages.
 
 	memchunk=nn[KMG]
 			[KNL,SH] Allow user to override the default size for
@@ -3218,14 +3227,14 @@
 			option.
 			See Documentation/admin-guide/mm/memory-hotplug.rst.
 
-	memmap=exactmap	[KNL,X86] Enable setting of an exact
+	memmap=exactmap	[KNL,X86,EARLY] Enable setting of an exact
 			E820 memory map, as specified by the user.
 			Such memmap=exactmap lines can be constructed based on
 			BIOS output or other requirements. See the memmap=nn@ss
 			option description.
 
 	memmap=nn[KMG]@ss[KMG]
-			[KNL, X86, MIPS, XTENSA] Force usage of a specific region of memory.
+			[KNL, X86,MIPS,XTENSA,EARLY] Force usage of a specific region of memory.
 			Region of memory to be used is from ss to ss+nn.
 			If @ss[KMG] is omitted, it is equivalent to mem=nn[KMG],
 			which limits max address to nn[KMG].
@@ -3235,11 +3244,11 @@
 				memmap=100M@2G,100M#3G,1G!1024G
 
 	memmap=nn[KMG]#ss[KMG]
-			[KNL,ACPI] Mark specific memory as ACPI data.
+			[KNL,ACPI,EARLY] Mark specific memory as ACPI data.
 			Region of memory to be marked is from ss to ss+nn.
 
 	memmap=nn[KMG]$ss[KMG]
-			[KNL,ACPI] Mark specific memory as reserved.
+			[KNL,ACPI,EARLY] Mark specific memory as reserved.
 			Region of memory to be reserved is from ss to ss+nn.
 			Example: Exclude memory from 0x18690000-0x1869ffff
 			         memmap=64K$0x18690000
@@ -3249,14 +3258,14 @@
 			like Grub2, otherwise '$' and the following number
 			will be eaten.
 
-	memmap=nn[KMG]!ss[KMG]
+	memmap=nn[KMG]!ss[KMG,EARLY]
 			[KNL,X86] Mark specific memory as protected.
 			Region of memory to be used, from ss to ss+nn.
 			The memory region may be marked as e820 type 12 (0xc)
 			and is NVDIMM or ADR memory.
 
 	memmap=<size>%<offset>-<oldtype>+<newtype>
-			[KNL,ACPI] Convert memory within the specified region
+			[KNL,ACPI,EARLY] Convert memory within the specified region
 			from <oldtype> to <newtype>. If "-<oldtype>" is left
 			out, the whole region will be marked as <newtype>,
 			even if previously unavailable. If "+<newtype>" is left
@@ -3264,7 +3273,7 @@
 			specified as e820 types, e.g., 1 = RAM, 2 = reserved,
 			3 = ACPI, 12 = PRAM.
 
-	memory_corruption_check=0/1 [X86]
+	memory_corruption_check=0/1 [X86,EARLY]
 			Some BIOSes seem to corrupt the first 64k of
 			memory when doing things like suspend/resume.
 			Setting this option will scan the memory
@@ -3276,13 +3285,13 @@
 			affects the same memory, you can use memmap=
 			to prevent the kernel from using that memory.
 
-	memory_corruption_check_size=size [X86]
+	memory_corruption_check_size=size [X86,EARLY]
 			By default it checks for corruption in the low
 			64k, making this memory unavailable for normal
 			use.  Use this parameter to scan for
 			corruption in more or less memory.
 
-	memory_corruption_check_period=seconds [X86]
+	memory_corruption_check_period=seconds [X86,EARLY]
 			By default it checks for corruption every 60
 			seconds.  Use this parameter to check at some
 			other rate.  0 disables periodic checking.
@@ -3306,7 +3315,7 @@
 			Note that even when enabled, there are a few cases where
 			the feature is not effective.
 
-	memtest=	[KNL,X86,ARM,M68K,PPC,RISCV] Enable memtest
+	memtest=	[KNL,X86,ARM,M68K,PPC,RISCV,EARLY] Enable memtest
 			Format: <integer>
 			default : 0 <disable>
 			Specifies the number of memtest passes to be
@@ -3374,7 +3383,7 @@
 			https://repo.or.cz/w/linux-2.6/mini2440.git
 
 	mitigations=
-			[X86,PPC,S390,ARM64] Control optional mitigations for
+			[X86,PPC,S390,ARM64,EARLY] Control optional mitigations for
 			CPU vulnerabilities.  This is a set of curated,
 			arch-independent options, each of which is an
 			aggregation of existing arch-specific options.
@@ -3427,7 +3436,7 @@
 					       retbleed=auto,nosmt [X86]
 
 	mminit_loglevel=
-			[KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
+			[KNL,EARLY] When CONFIG_DEBUG_MEMORY_INIT is set, this
 			parameter allows control of the logging verbosity for
 			the additional memory initialisation checks. A value
 			of 0 disables mminit logging and a level of 4 will
@@ -3435,7 +3444,7 @@
 			so loglevel=8 may also need to be specified.
 
 	mmio_stale_data=
-			[X86,INTEL] Control mitigation for the Processor
+			[X86,INTEL,EARLY] Control mitigation for the Processor
 			MMIO Stale Data vulnerabilities.
 
 			Processor MMIO Stale Data is a class of
@@ -3510,7 +3519,7 @@
 	mousedev.yres=	[MOUSE] Vertical screen resolution, used for devices
 			reporting absolute coordinates, such as tablets
 
-	movablecore=	[KNL,X86,IA-64,PPC]
+	movablecore=	[KNL,X86,IA-64,PPC,EARLY]
 			Format: nn[KMGTPE] | nn%
 			This parameter is the complement to kernelcore=, it
 			specifies the amount of memory used for migratable
@@ -3521,7 +3530,7 @@
 			that the amount of memory usable for all allocations
 			is not too small.
 
-	movable_node	[KNL] Boot-time switch to make hotplugable memory
+	movable_node	[KNL,EARLY] Boot-time switch to make hotplugable memory
 			NUMA nodes to be movable. This means that the memory
 			of such nodes will be usable only for movable
 			allocations which rules out almost all kernel
@@ -3545,21 +3554,21 @@
 			[HW] Make the MicroTouch USB driver use raw coordinates
 			('y', default) or cooked coordinates ('n')
 
-	mtrr=debug	[X86]
+	mtrr=debug	[X86,EARLY]
 			Enable printing debug information related to MTRR
 			registers at boot time.
 
-	mtrr_chunk_size=nn[KMG] [X86]
+	mtrr_chunk_size=nn[KMG,X86,EARLY]
 			used for mtrr cleanup. It is largest continuous chunk
 			that could hold holes aka. UC entries.
 
-	mtrr_gran_size=nn[KMG] [X86]
+	mtrr_gran_size=nn[KMG,X86,EARLY]
 			Used for mtrr cleanup. It is granularity of mtrr block.
 			Default is 1.
 			Large value could prevent small alignment from
 			using up MTRRs.
 
-	mtrr_spare_reg_nr=n [X86]
+	mtrr_spare_reg_nr=n [X86,EARLY]
 			Format: <integer>
 			Range: 0,7 : spare reg number
 			Default : 1
@@ -3745,10 +3754,10 @@
 			emulation library even if a 387 maths coprocessor
 			is present.
 
-	no4lvl		[RISCV] Disable 4-level and 5-level paging modes. Forces
-			kernel to use 3-level paging instead.
+	no4lvl		[RISCV,EARLY] Disable 4-level and 5-level paging modes.
+			Forces kernel to use 3-level paging instead.
 
-	no5lvl		[X86-64,RISCV] Disable 5-level paging mode. Forces
+	no5lvl		[X86-64,RISCV,EARLY] Disable 5-level paging mode. Forces
 			kernel to use 4-level paging instead.
 
 	noaliencache	[MM, NUMA, SLAB] Disables the allocation of alien
@@ -3757,15 +3766,15 @@
 
 	noalign		[KNL,ARM]
 
-	noaltinstr	[S390] Disables alternative instructions patching
-			(CPU alternatives feature).
+	noaltinstr	[S390,EARLY] Disables alternative instructions
+			patching (CPU alternatives feature).
 
-	noapic		[SMP,APIC] Tells the kernel to not make use of any
+	noapic		[SMP,APIC,EARLY] Tells the kernel to not make use of any
 			IOAPICs that may be present in the system.
 
 	noautogroup	Disable scheduler automatic task group creation.
 
-	nocache		[ARM]
+	nocache		[ARM,EARLY]
 
 	no_console_suspend
 			[HW] Never suspend the console
@@ -3783,13 +3792,13 @@
 			turn on/off it dynamically.
 
 	no_debug_objects
-			[KNL] Disable object debugging
+			[KNL,EARLY] Disable object debugging
 
 	nodsp		[SH] Disable hardware DSP at boot time.
 
-	noefi		Disable EFI runtime services support.
+	noefi		[EFI,EARLY] Disable EFI runtime services support.
 
-	no_entry_flush  [PPC] Don't flush the L1-D cache when entering the kernel.
+	no_entry_flush  [PPC,EARLY] Don't flush the L1-D cache when entering the kernel.
 
 	noexec		[IA-64]
 
@@ -3820,6 +3829,7 @@
 			real-time systems.
 
 	no_hash_pointers
+			[KNL,EARLY]
 			Force pointers printed to the console or buffers to be
 			unhashed.  By default, when a pointer is printed via %p
 			format string, that pointer is "hashed", i.e. obscured
@@ -3844,9 +3854,9 @@
 			the impact of the sleep instructions. This is also
 			useful when using JTAG debugger.
 
-	nohugeiomap	[KNL,X86,PPC,ARM64] Disable kernel huge I/O mappings.
+	nohugeiomap	[KNL,X86,PPC,ARM64,EARLY] Disable kernel huge I/O mappings.
 
-	nohugevmalloc	[KNL,X86,PPC,ARM64] Disable kernel huge vmalloc mappings.
+	nohugevmalloc	[KNL,X86,PPC,ARM64,EARLY] Disable kernel huge vmalloc mappings.
 
 	nohz=		[KNL] Boottime enable/disable dynamic ticks
 			Valid arguments: on, off
@@ -3868,13 +3878,13 @@
 	noinitrd	[RAM] Tells the kernel not to load any configured
 			initial RAM disk.
 
-	nointremap	[X86-64, Intel-IOMMU] Do not enable interrupt
+	nointremap	[X86-64,Intel-IOMMU,EARLY] Do not enable interrupt
 			remapping.
 			[Deprecated - use intremap=off]
 
 	nointroute	[IA-64]
 
-	noinvpcid	[X86] Disable the INVPCID cpu feature.
+	noinvpcid	[X86,EARLY] Disable the INVPCID cpu feature.
 
 	noiotrap	[SH] Disables trapped I/O port accesses.
 
@@ -3885,19 +3895,19 @@
 
 	nojitter	[IA-64] Disables jitter checking for ITC timers.
 
-	nokaslr		[KNL]
+	nokaslr		[KNL,EARLY]
 			When CONFIG_RANDOMIZE_BASE is set, this disables
 			kernel and module base offset ASLR (Address Space
 			Layout Randomization).
 
-	no-kvmapf	[X86,KVM] Disable paravirtualized asynchronous page
+	no-kvmapf	[X86,KVM,EARLY] Disable paravirtualized asynchronous page
 			fault handling.
 
-	no-kvmclock	[X86,KVM] Disable paravirtualized KVM clock driver
+	no-kvmclock	[X86,KVM,EARLY] Disable paravirtualized KVM clock driver
 
-	nolapic		[X86-32,APIC] Do not enable or use the local APIC.
+	nolapic		[X86-32,APIC,EARLY] Do not enable or use the local APIC.
 
-	nolapic_timer	[X86-32,APIC] Do not use the local APIC timer.
+	nolapic_timer	[X86-32,APIC,EARLY] Do not use the local APIC timer.
 
 	nomca		[IA-64] Disable machine check abort handling
 
@@ -3922,23 +3932,23 @@
 			shutdown the other cpus.  Instead use the REBOOT_VECTOR
 			irq.
 
-	nopat		[X86] Disable PAT (page attribute table extension of
+	nopat		[X86,EARLY] Disable PAT (page attribute table extension of
 			pagetables) support.
 
-	nopcid		[X86-64] Disable the PCID cpu feature.
+	nopcid		[X86-64,EARLY] Disable the PCID cpu feature.
 
 	nopku		[X86] Disable Memory Protection Keys CPU feature found
 			in some Intel CPUs.
 
-	nopti		[X86-64]
+	nopti		[X86-64,EARLY]
 			Equivalent to pti=off
 
-	nopv=		[X86,XEN,KVM,HYPER_V,VMWARE]
+	nopv=		[X86,XEN,KVM,HYPER_V,VMWARE,EARLY]
 			Disables the PV optimizations forcing the guest to run
 			as generic guest with no PV drivers. Currently support
 			XEN HVM, KVM, HYPER_V and VMWARE guest.
 
-	nopvspin	[X86,XEN,KVM]
+	nopvspin	[X86,XEN,KVM,EARLY]
 			Disables the qspinlock slow path using PV optimizations
 			which allow the hypervisor to 'idle' the guest on lock
 			contention.
@@ -3958,20 +3968,20 @@
 			This is required for the Braillex ib80-piezo Braille
 			reader made by F.H. Papenmeier (Germany).
 
-	nosgx		[X86-64,SGX] Disables Intel SGX kernel support.
+	nosgx		[X86-64,SGX,EARLY] Disables Intel SGX kernel support.
 
-	nosmap		[PPC]
+	nosmap		[PPC,EARLY]
 			Disable SMAP (Supervisor Mode Access Prevention)
 			even if it is supported by processor.
 
-	nosmep		[PPC64s]
+	nosmep		[PPC64s,EARLY]
 			Disable SMEP (Supervisor Mode Execution Prevention)
 			even if it is supported by processor.
 
-	nosmp		[SMP] Tells an SMP kernel to act as a UP kernel,
+	nosmp		[SMP,EARLY] Tells an SMP kernel to act as a UP kernel,
 			and disable the IO APIC.  legacy for "maxcpus=0".
 
-	nosmt		[KNL,MIPS,PPC,S390] Disable symmetric multithreading (SMT).
+	nosmt		[KNL,MIPS,PPC,S390,EARLY] Disable symmetric multithreading (SMT).
 			Equivalent to smt=1.
 
 			[KNL,X86,PPC] Disable symmetric multithreading (SMT).
@@ -3981,24 +3991,25 @@
 	nosoftlockup	[KNL] Disable the soft-lockup detector.
 
 	nospec_store_bypass_disable
-			[HW] Disable all mitigations for the Speculative Store Bypass vulnerability
+			[HW,EARLY] Disable all mitigations for the Speculative
+			Store Bypass vulnerability
 
-	nospectre_bhb	[ARM64] Disable all mitigations for Spectre-BHB (branch
+	nospectre_bhb	[ARM64,EARLY] Disable all mitigations for Spectre-BHB (branch
 			history injection) vulnerability. System may allow data leaks
 			with this option.
 
-	nospectre_v1	[X86,PPC] Disable mitigations for Spectre Variant 1
+	nospectre_v1	[X86,PPC,EARLY] Disable mitigations for Spectre Variant 1
 			(bounds check bypass). With this option data leaks are
 			possible in the system.
 
-	nospectre_v2	[X86,PPC_E500,ARM64] Disable all mitigations for
-			the Spectre variant 2 (indirect branch prediction)
-			vulnerability. System may allow data leaks with this
-			option.
+	nospectre_v2	[X86,PPC_E500,ARM64,EARLY] Disable all mitigations
+			for the Spectre variant 2 (indirect branch
+			prediction) vulnerability. System may allow data
+			leaks with this option.
 
-	no-steal-acc	[X86,PV_OPS,ARM64,PPC/PSERIES] Disable paravirtualized
-			steal time accounting. steal time is computed, but
-			won't influence scheduler behaviour
+	no-steal-acc	[X86,PV_OPS,ARM64,PPC/PSERIES,RISCV,EARLY] Disable
+			paravirtualized steal time accounting. steal time is
+			computed, but won't influence scheduler behaviour
 
 	nosync		[HW,M68K] Disables sync negotiation for all devices.
 
@@ -4006,7 +4017,7 @@
 			broken timer IRQ sources.
 
 	no_uaccess_flush
-	                [PPC] Don't flush the L1-D cache after accessing user data.
+	                [PPC,EARLY] Don't flush the L1-D cache after accessing user data.
 
 	novmcoredd	[KNL,KDUMP]
 			Disable device dump. Device dump allows drivers to
@@ -4020,15 +4031,15 @@
 			is set.
 
 	no-vmw-sched-clock
-			[X86,PV_OPS] Disable paravirtualized VMware scheduler
-			clock and use the default one.
+			[X86,PV_OPS,EARLY] Disable paravirtualized VMware
+			scheduler clock and use the default one.
 
 	nowatchdog	[KNL] Disable both lockup detectors, i.e.
 			soft-lockup and NMI watchdog (hard-lockup).
 
-	nowb		[ARM]
+	nowb		[ARM,EARLY]
 
-	nox2apic	[X86-64,APIC] Do not enable x2APIC mode.
+	nox2apic	[X86-64,APIC,EARLY] Do not enable x2APIC mode.
 
 			NOTE: this parameter will be ignored on systems with the
 			LEGACY_XAPIC_DISABLED bit set in the
@@ -4066,7 +4077,7 @@
 			purges which is reported from either PAL_VM_SUMMARY or
 			SAL PALO.
 
-	nr_cpus=	[SMP] Maximum number of processors that	an SMP kernel
+	nr_cpus=	[SMP,EARLY] Maximum number of processors that an SMP kernel
 			could support.  nr_cpus=n : n >= 1 limits the kernel to
 			support 'n' processors. It could be larger than the
 			number of already plugged CPU during bootup, later in
@@ -4077,8 +4088,9 @@
 
 	nr_uarts=	[SERIAL] maximum number of UARTs to be registered.
 
-	numa=off 	[KNL, ARM64, PPC, RISCV, SPARC, X86] Disable NUMA, Only
-			set up a single NUMA node spanning all memory.
+	numa=off 	[KNL, ARM64, PPC, RISCV, SPARC, X86, EARLY]
+			Disable NUMA, Only set up a single NUMA node
+			spanning all memory.
 
 	numa_balancing=	[KNL,ARM64,PPC,RISCV,S390,X86] Enable or disable automatic
 			NUMA balancing.
@@ -4089,7 +4101,7 @@
 			This can be set from sysctl after boot.
 			See Documentation/admin-guide/sysctl/vm.rst for details.
 
-	ohci1394_dma=early	[HW] enable debugging via the ohci1394 driver.
+	ohci1394_dma=early	[HW,EARLY] enable debugging via the ohci1394 driver.
 			See Documentation/core-api/debugging-via-ohci1394.rst for more
 			info.
 
@@ -4115,7 +4127,8 @@
 				   Once locked, the boundary cannot be changed.
 				   1 indicates lock status, 0 indicates unlock status.
 
-	oops=panic	Always panic on oopses. Default is to just kill the
+	oops=panic	[KNL,EARLY]
+			Always panic on oopses. Default is to just kill the
 			process, but there is a small probability of
 			deadlocking the machine.
 			This will also cause panics on machine check exceptions.
@@ -4131,13 +4144,13 @@
 			can be read from sysfs at:
 			/sys/module/page_alloc/parameters/shuffle.
 
-	page_owner=	[KNL] Boot-time page_owner enabling option.
+	page_owner=	[KNL,EARLY] Boot-time page_owner enabling option.
 			Storage of the information about who allocated
 			each page is disabled in default. With this switch,
 			we can turn it on.
 			on: enable the feature
 
-	page_poison=	[KNL] Boot-time parameter changing the state of
+	page_poison=	[KNL,EARLY] Boot-time parameter changing the state of
 			poisoning on the buddy allocator, available with
 			CONFIG_PAGE_POISONING=y.
 			off: turn off poisoning (default)
@@ -4155,7 +4168,8 @@
 			timeout < 0: reboot immediately
 			Format: <timeout>
 
-	panic_on_taint=	Bitmask for conditionally calling panic() in add_taint()
+	panic_on_taint=	[KNL,EARLY]
+			Bitmask for conditionally calling panic() in add_taint()
 			Format: <hex>[,nousertaint]
 			Hexadecimal bitmask representing the set of TAINT flags
 			that will cause the kernel to panic when add_taint() is
@@ -4311,7 +4325,7 @@
 
 	pcbit=		[HW,ISDN]
 
-	pci=option[,option...]	[PCI] various PCI subsystem options.
+	pci=option[,option...]	[PCI,EARLY] various PCI subsystem options.
 
 				Some options herein operate on a specific device
 				or a set of devices (<pci_dev>). These are
@@ -4580,7 +4594,8 @@
 			Format: { 0 | 1 }
 			See arch/parisc/kernel/pdc_chassis.c
 
-	percpu_alloc=	Select which percpu first chunk allocator to use.
+	percpu_alloc=	[MM,EARLY]
+			Select which percpu first chunk allocator to use.
 			Currently supported values are "embed" and "page".
 			Archs may support subset or none of the	selections.
 			See comments in mm/percpu.c for details on each
@@ -4649,12 +4664,12 @@
 			execution priority.
 
 	ppc_strict_facility_enable
-			[PPC] This option catches any kernel floating point,
+			[PPC,ENABLE] This option catches any kernel floating point,
 			Altivec, VSX and SPE outside of regions specifically
 			allowed (eg kernel_enable_fpu()/kernel_disable_fpu()).
 			There is some performance impact when enabling this.
 
-	ppc_tm=		[PPC]
+	ppc_tm=		[PPC,EARLY]
 			Format: {"off"}
 			Disable Hardware Transactional Memory
 
@@ -4764,7 +4779,7 @@
 			[KNL] Number of legacy pty's. Overwrites compiled-in
 			default number.
 
-	quiet		[KNL] Disable most log messages
+	quiet		[KNL,EARLY] Disable most log messages
 
 	r128=		[HW,DRM]
 
@@ -4781,17 +4796,17 @@
 	ramdisk_start=	[RAM] RAM disk image start address
 
 	random.trust_cpu=off
-			[KNL] Disable trusting the use of the CPU's
+			[KNL,EARLY] Disable trusting the use of the CPU's
 			random number generator (if available) to
 			initialize the kernel's RNG.
 
 	random.trust_bootloader=off
-			[KNL] Disable trusting the use of the a seed
+			[KNL,EARLY] Disable trusting the use of the a seed
 			passed by the bootloader (if available) to
 			initialize the kernel's RNG.
 
 	randomize_kstack_offset=
-			[KNL] Enable or disable kernel stack offset
+			[KNL,EARLY] Enable or disable kernel stack offset
 			randomization, which provides roughly 5 bits of
 			entropy, frustrating memory corruption attacks
 			that depend on stack address determinism or
@@ -5032,6 +5047,11 @@
 			this kernel boot parameter, forcibly setting it
 			to zero.
 
+	rcutree.enable_rcu_lazy= [KNL]
+			To save power, batch RCU callbacks and flush after
+			delay, memory pressure or callback list growing too
+			big.
+
 	rcuscale.gp_async= [KNL]
 			Measure performance of asynchronous
 			grace-period primitives such as call_rcu().
@@ -5482,7 +5502,7 @@
 			Run specified binary instead of /init from the ramdisk,
 			used for early userspace startup. See initrd.
 
-	rdrand=		[X86]
+	rdrand=		[X86,EARLY]
 			force - Override the decision by the kernel to hide the
 				advertisement of RDRAND support (this affects
 				certain AMD processors because of buggy BIOS
@@ -5578,7 +5598,7 @@
 			them.  If <base> is less than 0x10000, the region
 			is assumed to be I/O ports; otherwise it is memory.
 
-	reservetop=	[X86-32]
+	reservetop=	[X86-32,EARLY]
 			Format: nn[KMG]
 			Reserves a hole at the top of the kernel virtual
 			address space.
@@ -5604,7 +5624,8 @@
 			Useful for devices that are detected asynchronously
 			(e.g. USB and MMC devices).
 
-	retain_initrd	[RAM] Keep initrd memory after extraction
+	retain_initrd	[RAM] Keep initrd memory after extraction. After boot, it will
+			be accessible via /sys/firmware/initrd.
 
 	retbleed=	[X86] Control mitigation of RETBleed (Arbitrary
 			Speculative Code Execution with Return Instructions)
@@ -5662,7 +5683,7 @@
 			[KNL] Disable ring 3 MONITOR/MWAIT feature on supported
 			CPUs.
 
-	riscv_isa_fallback [RISCV]
+	riscv_isa_fallback [RISCV,EARLY]
 			When CONFIG_RISCV_ISA_FALLBACK is not enabled, permit
 			falling back to detecting extension support by parsing
 			"riscv,isa" property on devicetree systems when the
@@ -5671,13 +5692,14 @@
 
 	ro		[KNL] Mount root device read-only on boot
 
-	rodata=		[KNL]
+	rodata=		[KNL,EARLY]
 		on	Mark read-only kernel memory as read-only (default).
 		off	Leave read-only kernel memory writable for debugging.
 		full	Mark read-only kernel memory and aliases as read-only
 		        [arm64]
 
 	rockchip.usb_uart
+			[EARLY]
 			Enable the uart passthrough on the designated usb port
 			on Rockchip SoCs. When active, the signals of the
 			debug-uart get routed to the D+ and D- pins of the usb
@@ -5738,7 +5760,7 @@
 	sa1100ir	[NET]
 			See drivers/net/irda/sa1100_ir.c.
 
-	sched_verbose	[KNL] Enables verbose scheduler debug messages.
+	sched_verbose	[KNL,EARLY] Enables verbose scheduler debug messages.
 
 	schedstats=	[KNL,X86] Enable or disable scheduled statistics.
 			Allowed values are enable and disable. This feature
@@ -5853,7 +5875,7 @@
 			non-zero "wait" parameter.  See weight_single
 			and weight_many.
 
-	skew_tick=	[KNL] Offset the periodic timer tick per cpu to mitigate
+	skew_tick=	[KNL,EARLY] Offset the periodic timer tick per cpu to mitigate
 			xtime_lock contention on larger systems, and/or RCU lock
 			contention on all systems with CONFIG_MAXSMP set.
 			Format: { "0" | "1" }
@@ -5984,10 +6006,10 @@
 				1: Fast pin select (default)
 				2: ATC IRMode
 
-	smt=		[KNL,MIPS,S390] Set the maximum number of threads (logical
-			CPUs) to use per physical CPU on systems capable of
-			symmetric multithreading (SMT). Will be capped to the
-			actual hardware limit.
+	smt=		[KNL,MIPS,S390,EARLY] Set the maximum number of threads
+			(logical CPUs) to use per physical CPU on systems
+			capable of symmetric multithreading (SMT). Will
+			be capped to the actual hardware limit.
 			Format: <integer>
 			Default: -1 (no limit)
 
@@ -6009,7 +6031,7 @@
 	sonypi.*=	[HW] Sony Programmable I/O Control Device driver
 			See Documentation/admin-guide/laptops/sonypi.rst
 
-	spectre_v2=	[X86] Control mitigation of Spectre variant 2
+	spectre_v2=	[X86,EARLY] Control mitigation of Spectre variant 2
 			(indirect branch speculation) vulnerability.
 			The default operation protects the kernel from
 			user space attacks.
@@ -6089,7 +6111,7 @@
 			spectre_v2_user=auto.
 
 	spec_rstack_overflow=
-			[X86] Control RAS overflow mitigation on AMD Zen CPUs
+			[X86,EARLY] Control RAS overflow mitigation on AMD Zen CPUs
 
 			off		- Disable mitigation
 			microcode	- Enable microcode mitigation only
@@ -6100,7 +6122,7 @@
 					  (cloud-specific mitigation)
 
 	spec_store_bypass_disable=
-			[HW] Control Speculative Store Bypass (SSB) Disable mitigation
+			[HW,EARLY] Control Speculative Store Bypass (SSB) Disable mitigation
 			(Speculative Store Bypass vulnerability)
 
 			Certain CPUs are vulnerable to an exploit against a
@@ -6196,7 +6218,7 @@
 			#DB exception for bus lock is triggered only when
 			CPL > 0.
 
-	srbds=		[X86,INTEL]
+	srbds=		[X86,INTEL,EARLY]
 			Control the Special Register Buffer Data Sampling
 			(SRBDS) mitigation.
 
@@ -6283,7 +6305,7 @@
 			srcutree.convert_to_big must have the 0x10 bit
 			set for contention-based conversions to occur.
 
-	ssbd=		[ARM64,HW]
+	ssbd=		[ARM64,HW,EARLY]
 			Speculative Store Bypass Disable control
 
 			On CPUs that are vulnerable to the Speculative
@@ -6307,7 +6329,7 @@
 			growing up) the main stack are reserved for no other
 			mapping. Default value is 256 pages.
 
-	stack_depot_disable= [KNL]
+	stack_depot_disable= [KNL,EARLY]
 			Setting this to true through kernel command line will
 			disable the stack depot thereby saving the static memory
 			consumed by the stack hash table. By default this is set
@@ -6346,12 +6368,12 @@
 			be used to filter out binaries which have
 			not yet been made aware of AT_MINSIGSTKSZ.
 
-	stress_hpt	[PPC]
+	stress_hpt	[PPC,EARLY]
 			Limits the number of kernel HPT entries in the hash
 			page table to increase the rate of hash page table
 			faults on kernel addresses.
 
-	stress_slb	[PPC]
+	stress_slb	[PPC,EARLY]
 			Limits the number of kernel SLB entries, and flushes
 			them frequently to increase the rate of SLB faults
 			on kernel addresses.
@@ -6411,7 +6433,7 @@
 			This parameter controls use of the Protected
 			Execution Facility on pSeries.
 
-	swiotlb=	[ARM,IA-64,PPC,MIPS,X86]
+	swiotlb=	[ARM,IA-64,PPC,MIPS,X86,EARLY]
 			Format: { <int> [,<int>] | force | noforce }
 			<int> -- Number of I/O TLB slabs
 			<int> -- Second integer after comma. Number of swiotlb
@@ -6421,7 +6443,7 @@
 			         wouldn't be automatically used by the kernel
 			noforce -- Never use bounce buffers (for debugging)
 
-	switches=	[HW,M68k]
+	switches=	[HW,M68k,EARLY]
 
 	sysctl.*=	[KNL]
 			Set a sysctl parameter, right before loading the init
@@ -6480,11 +6502,11 @@
 			<deci-seconds>: poll all this frequency
 			0: no polling (default)
 
-	threadirqs	[KNL]
+	threadirqs	[KNL,EARLY]
 			Force threading of all interrupt handlers except those
 			marked explicitly IRQF_NO_THREAD.
 
-	topology=	[S390]
+	topology=	[S390,EARLY]
 			Format: {off | on}
 			Specify if the kernel should make use of the cpu
 			topology information if the hardware supports this.
@@ -6725,7 +6747,7 @@
 			can be overridden by a later tsc=nowatchdog.  A console
 			message will flag any such suppression or overriding.
 
-	tsc_early_khz=  [X86] Skip early TSC calibration and use the given
+	tsc_early_khz=  [X86,EARLY] Skip early TSC calibration and use the given
 			value instead. Useful when the early TSC frequency discovery
 			procedure is not reliable, such as on overclocked systems
 			with CPUID.16h support and partial CPUID.15h support.
@@ -6760,7 +6782,7 @@
 			See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
 			for more details.
 
-	tsx_async_abort= [X86,INTEL] Control mitigation for the TSX Async
+	tsx_async_abort= [X86,INTEL,EARLY] Control mitigation for the TSX Async
 			Abort (TAA) vulnerability.
 
 			Similar to Micro-architectural Data Sampling (MDS)
@@ -6826,7 +6848,7 @@
 	unknown_nmi_panic
 			[X86] Cause panic on unknown NMI.
 
-	unwind_debug	[X86-64]
+	unwind_debug	[X86-64,EARLY]
 			Enable unwinder debug output.  This can be
 			useful for debugging certain unwinder error
 			conditions, including corrupt stacks and
@@ -6932,6 +6954,9 @@
 					pause after every control message);
 				o = USB_QUIRK_HUB_SLOW_RESET (Hub needs extra
 					delay after resetting its port);
+				p = USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT
+					(Reduce timeout of the SET_ADDRESS
+					request from 5000 ms to 500 ms);
 			Example: quirks=0781:5580:bk,0a5c:5834:gij
 
 	usbhid.mousepoll=
@@ -7013,7 +7038,7 @@
 			Example: user_debug=31
 
 	userpte=
-			[X86] Flags controlling user PTE allocations.
+			[X86,EARLY] Flags controlling user PTE allocations.
 
 				nohigh = do not allocate PTE pages in
 					HIGHMEM regardless of setting
@@ -7042,7 +7067,7 @@
 	vector=		[IA-64,SMP]
 			vector=percpu: enable percpu vector domain
 
-	video=		[FB] Frame buffer configuration
+	video=		[FB,EARLY] Frame buffer configuration
 			See Documentation/fb/modedb.rst.
 
 	video.brightness_switch_enabled= [ACPI]
@@ -7090,13 +7115,13 @@
 			  P	Enable page structure init time poisoning
 			  -	Disable all of the above options
 
-	vmalloc=nn[KMG]	[KNL,BOOT] Forces the vmalloc area to have an exact
-			size of <nn>. This can be used to increase the
-			minimum size (128MB on x86). It can also be used to
-			decrease the size and leave more room for directly
-			mapped kernel RAM.
+	vmalloc=nn[KMG]	[KNL,BOOT,EARLY] Forces the vmalloc area to have an
+			exact size of <nn>. This can be used to increase
+			the minimum size (128MB on x86). It can also be
+			used to decrease the size and leave more room
+			for directly mapped kernel RAM.
 
-	vmcp_cma=nn[MG]	[KNL,S390]
+	vmcp_cma=nn[MG]	[KNL,S390,EARLY]
 			Sets the memory size reserved for contiguous memory
 			allocations for the vmcp device driver.
 
@@ -7109,7 +7134,7 @@
 	vmpoff=		[KNL,S390] Perform z/VM CP command after power off.
 			Format: <command>
 
-	vsyscall=	[X86-64]
+	vsyscall=	[X86-64,EARLY]
 			Controls the behavior of vsyscalls (i.e. calls to
 			fixed addresses of 0xffffffffff600x00 from legacy
 			code).  Most statically-linked binaries and older
@@ -7219,6 +7244,15 @@
 			threshold repeatedly. They are likely good
 			candidates for using WQ_UNBOUND workqueues instead.
 
+	workqueue.cpu_intensive_warning_thresh=<uint>
+			If CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel
+			will report the work functions which violate the
+			intensive_threshold_us repeatedly. In order to prevent
+			spurious warnings, start printing only after a work
+			function has violated this threshold number of times.
+
+			The default is 4 times. 0 disables the warning.
+
 	workqueue.power_efficient
 			Per-cpu workqueues are generally preferred because
 			they show better performance thanks to cache
@@ -7257,13 +7291,13 @@
 			When enabled, memory and cache locality will be
 			impacted.
 
-	writecombine=	[LOONGARCH] Control the MAT (Memory Access Type) of
-			ioremap_wc().
+	writecombine=	[LOONGARCH,EARLY] Control the MAT (Memory Access
+			Type) of ioremap_wc().
 
 			on   - Enable writecombine, use WUC for ioremap_wc()
 			off  - Disable writecombine, use SUC for ioremap_wc()
 
-	x2apic_phys	[X86-64,APIC] Use x2apic physical mode instead of
+	x2apic_phys	[X86-64,APIC,EARLY] Use x2apic physical mode instead of
 			default x2apic cluster mode on platforms
 			supporting x2apic.
 
@@ -7274,7 +7308,7 @@
 			save/restore/migration must be enabled to handle larger
 			domains.
 
-	xen_emul_unplug=		[HW,X86,XEN]
+	xen_emul_unplug=		[HW,X86,XEN,EARLY]
 			Unplug Xen emulated devices
 			Format: [unplug0,][unplug1]
 			ide-disks -- unplug primary master IDE devices
@@ -7286,17 +7320,17 @@
 				the unplug protocol
 			never -- do not unplug even if version check succeeds
 
-	xen_legacy_crash	[X86,XEN]
+	xen_legacy_crash	[X86,XEN,EARLY]
 			Crash from Xen panic notifier, without executing late
 			panic() code such as dumping handler.
 
-	xen_msr_safe=	[X86,XEN]
+	xen_msr_safe=	[X86,XEN,EARLY]
 			Format: <bool>
 			Select whether to always use non-faulting (safe) MSR
 			access functions when running as Xen PV guest. The
 			default value is controlled by CONFIG_XEN_PV_MSR_SAFE.
 
-	xen_nopvspin	[X86,XEN]
+	xen_nopvspin	[X86,XEN,EARLY]
 			Disables the qspinlock slowpath using Xen PV optimizations.
 			This parameter is obsoleted by "nopvspin" parameter, which
 			has equivalent effect for XEN platform.
@@ -7308,7 +7342,7 @@
 			has equivalent effect for XEN platform.
 
 	xen_no_vector_callback
-			[KNL,X86,XEN] Disable the vector callback for Xen
+			[KNL,X86,XEN,EARLY] Disable the vector callback for Xen
 			event channel interrupts.
 
 	xen_scrub_pages=	[XEN]
@@ -7317,7 +7351,7 @@
 			with /sys/devices/system/xen_memory/xen_memory0/scrub_pages.
 			Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT.
 
-	xen_timer_slop=	[X86-64,XEN]
+	xen_timer_slop=	[X86-64,XEN,EARLY]
 			Set the timer slop (in nanoseconds) for the virtual Xen
 			timers (default is 100000). This adjusts the minimum
 			delta of virtualized Xen timers, where lower values
@@ -7370,7 +7404,7 @@
 			host controller quirks. Meaning of each bit can be
 			consulted in header drivers/usb/host/xhci.h.
 
-	xmon		[PPC]
+	xmon		[PPC,EARLY]
 			Format: { early | on | rw | ro | off }
 			Controls if xmon debugger is enabled. Default is off.
 			Passing only "xmon" is equivalent to "xmon=early".
diff --git a/Documentation/admin-guide/kernel-per-CPU-kthreads.rst b/Documentation/admin-guide/kernel-per-CPU-kthreads.rst
index 993c2a05f5ee..b6aeae3327ce 100644
--- a/Documentation/admin-guide/kernel-per-CPU-kthreads.rst
+++ b/Documentation/admin-guide/kernel-per-CPU-kthreads.rst
@@ -243,13 +243,9 @@ To reduce its OS jitter, do any of the following:
 3.	Do any of the following needed to avoid jitter that your
 	application cannot tolerate:
 
-	a.	Build your kernel with CONFIG_SLUB=y rather than
-		CONFIG_SLAB=y, thus avoiding the slab allocator's periodic
-		use of each CPU's workqueues to run its cache_reap()
-		function.
-	b.	Avoid using oprofile, thus avoiding OS jitter from
+	a.	Avoid using oprofile, thus avoiding OS jitter from
 		wq_sync_buffer().
-	c.	Limit your CPU frequency so that a CPU-frequency
+	b.	Limit your CPU frequency so that a CPU-frequency
 		governor is not required, possibly enlisting the aid of
 		special heatsinks or other cooling technologies.  If done
 		correctly, and if you CPU architecture permits, you should
@@ -259,7 +255,7 @@ To reduce its OS jitter, do any of the following:
 
 		WARNING:  Please check your CPU specifications to
 		make sure that this is safe on your particular system.
-	d.	As of v3.18, Christoph Lameter's on-demand vmstat workers
+	c.	As of v3.18, Christoph Lameter's on-demand vmstat workers
 		commit prevents OS jitter due to vmstat_update() on
 		CONFIG_SMP=y systems.  Before v3.18, is not possible
 		to entirely get rid of the OS jitter, but you can
@@ -274,7 +270,7 @@ To reduce its OS jitter, do any of the following:
 		(based on an earlier one from Gilad Ben-Yossef) that
 		reduces or even eliminates vmstat overhead for some
 		workloads at https://lore.kernel.org/r/00000140e9dfd6bd-40db3d4f-c1be-434f-8132-7820f81bb586-000000@email.amazonses.com.
-	e.	If running on high-end powerpc servers, build with
+	d.	If running on high-end powerpc servers, build with
 		CONFIG_PPC_RTAS_DAEMON=n.  This prevents the RTAS
 		daemon from running on each CPU every second or so.
 		(This will require editing Kconfig files and will defeat
@@ -282,12 +278,12 @@ To reduce its OS jitter, do any of the following:
 		due to the rtas_event_scan() function.
 		WARNING:  Please check your CPU specifications to
 		make sure that this is safe on your particular system.
-	f.	If running on Cell Processor, build your kernel with
+	e.	If running on Cell Processor, build your kernel with
 		CBE_CPUFREQ_SPU_GOVERNOR=n to avoid OS jitter from
 		spu_gov_work().
 		WARNING:  Please check your CPU specifications to
 		make sure that this is safe on your particular system.
-	g.	If running on PowerMAC, build your kernel with
+	f.	If running on PowerMAC, build your kernel with
 		CONFIG_PMAC_RACKMETER=n to disable the CPU-meter,
 		avoiding OS jitter from rackmeter_do_timer().
 
diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst
index 1cf40f69278c..9eb26014d34b 100644
--- a/Documentation/admin-guide/pm/amd-pstate.rst
+++ b/Documentation/admin-guide/pm/amd-pstate.rst
@@ -361,7 +361,7 @@ Global Attributes
 
 ``amd-pstate`` exposes several global attributes (files) in ``sysfs`` to
 control its functionality at the system level.  They are located in the
-``/sys/devices/system/cpu/amd-pstate/`` directory and affect all CPUs.
+``/sys/devices/system/cpu/amd_pstate/`` directory and affect all CPUs.
 
 ``status``
 	Operation mode of the driver: "active", "passive" or "disable".
diff --git a/Documentation/admin-guide/sysrq.rst b/Documentation/admin-guide/sysrq.rst
index 51906e47327b..2f2e5bd440f9 100644
--- a/Documentation/admin-guide/sysrq.rst
+++ b/Documentation/admin-guide/sysrq.rst
@@ -75,10 +75,19 @@ On other
 	submit a patch to be included in this section.
 
 On all
-	Write a character to /proc/sysrq-trigger.  e.g.::
+	Write a single character to /proc/sysrq-trigger.
+	Only the first character is processed, the rest of the string is
+	ignored. However, it is not recommended to write any extra characters
+	as the behavior is undefined and might change in the future versions.
+	E.g.::
 
 		echo t > /proc/sysrq-trigger
 
+	Alternatively, write multiple characters prepended by underscore.
+	This way, all characters will be processed. E.g.::
+
+		echo _reisub > /proc/sysrq-trigger
+
 The :kbd:`<command key>` is case sensitive.
 
 What are the 'command' keys?
diff --git a/Documentation/arch/arc/features.rst b/Documentation/arch/arc/features.rst
index b793583d688a..49ff446ff744 100644
--- a/Documentation/arch/arc/features.rst
+++ b/Documentation/arch/arc/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features arc
+.. kernel-feat:: features arc
diff --git a/Documentation/arch/arm/features.rst b/Documentation/arch/arm/features.rst
index 7414ec03dd15..0e76aaf68eca 100644
--- a/Documentation/arch/arm/features.rst
+++ b/Documentation/arch/arm/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features arm
+.. kernel-feat:: features arm
diff --git a/Documentation/arch/arm64/features.rst b/Documentation/arch/arm64/features.rst
index dfa4cb3cd3ef..03321f4309d0 100644
--- a/Documentation/arch/arm64/features.rst
+++ b/Documentation/arch/arm64/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features arm64
+.. kernel-feat:: features arm64
diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst
index f47f63bcf67c..45a7f4932fe0 100644
--- a/Documentation/arch/arm64/silicon-errata.rst
+++ b/Documentation/arch/arm64/silicon-errata.rst
@@ -71,6 +71,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A510     | #2658417        | ARM64_ERRATUM_2658417       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A510     | #3117295        | ARM64_ERRATUM_3117295       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A520     | #2966298        | ARM64_ERRATUM_2966298       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A53      | #826319         | ARM64_ERRATUM_826319        |
@@ -117,6 +119,10 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A76      | #1463225        | ARM64_ERRATUM_1463225       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A76      | #1490853        | N/A                         |
++----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A77      | #1491015        | N/A                         |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A77      | #1508412        | ARM64_ERRATUM_1508412       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A710     | #2119858        | ARM64_ERRATUM_2119858       |
@@ -127,6 +133,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A715     | #2645198        | ARM64_ERRATUM_2645198       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-X1       | #1502854        | N/A                         |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-X2       | #2119858        | ARM64_ERRATUM_2119858       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-X2       | #2224489        | ARM64_ERRATUM_2224489       |
@@ -135,6 +143,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1349291        | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Neoverse-N1     | #1490853        | N/A                         |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1542419        | ARM64_ERRATUM_1542419       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N2     | #2139208        | ARM64_ERRATUM_2139208       |
@@ -143,6 +153,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N2     | #2253138        | ARM64_ERRATUM_2253138       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Neoverse-V1     | #1619801        | N/A                         |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | MMU-500         | #841119,826419  | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | MMU-600         | #1076982,1209401| N/A                         |
@@ -225,11 +237,16 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | Rockchip       | RK3588          | #3588001        | ROCKCHIP_ERRATUM_3588001    |
 +----------------+-----------------+-----------------+-----------------------------+
-
 +----------------+-----------------+-----------------+-----------------------------+
 | Fujitsu        | A64FX           | E#010001        | FUJITSU_ERRATUM_010001      |
 +----------------+-----------------+-----------------+-----------------------------+
-
 +----------------+-----------------+-----------------+-----------------------------+
 | ASR            | ASR8601         | #8601001        | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
++----------------+-----------------+-----------------+-----------------------------+
+| Microsoft      | Azure Cobalt 100| #2139208        | ARM64_ERRATUM_2139208       |
++----------------+-----------------+-----------------+-----------------------------+
+| Microsoft      | Azure Cobalt 100| #2067961        | ARM64_ERRATUM_2067961       |
++----------------+-----------------+-----------------+-----------------------------+
+| Microsoft      | Azure Cobalt 100| #2253138        | ARM64_ERRATUM_2253138       |
++----------------+-----------------+-----------------+-----------------------------+
diff --git a/Documentation/arch/loongarch/features.rst b/Documentation/arch/loongarch/features.rst
index ebacade3ea45..009f44c7951f 100644
--- a/Documentation/arch/loongarch/features.rst
+++ b/Documentation/arch/loongarch/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features loongarch
+.. kernel-feat:: features loongarch
diff --git a/Documentation/arch/m68k/features.rst b/Documentation/arch/m68k/features.rst
index 5107a2119472..de7f0ccf7fc8 100644
--- a/Documentation/arch/m68k/features.rst
+++ b/Documentation/arch/m68k/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features m68k
+.. kernel-feat:: features m68k
diff --git a/Documentation/arch/mips/features.rst b/Documentation/arch/mips/features.rst
index 1973d729b29a..6e0ffe3e7354 100644
--- a/Documentation/arch/mips/features.rst
+++ b/Documentation/arch/mips/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features mips
+.. kernel-feat:: features mips
diff --git a/Documentation/arch/nios2/features.rst b/Documentation/arch/nios2/features.rst
index 8449e63f69b2..89913810ccb5 100644
--- a/Documentation/arch/nios2/features.rst
+++ b/Documentation/arch/nios2/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features nios2
+.. kernel-feat:: features nios2
diff --git a/Documentation/arch/openrisc/features.rst b/Documentation/arch/openrisc/features.rst
index 3f7c40d219f2..bae2e25adfd6 100644
--- a/Documentation/arch/openrisc/features.rst
+++ b/Documentation/arch/openrisc/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features openrisc
+.. kernel-feat:: features openrisc
diff --git a/Documentation/arch/parisc/features.rst b/Documentation/arch/parisc/features.rst
index 501d7c450037..b3aa4d243b93 100644
--- a/Documentation/arch/parisc/features.rst
+++ b/Documentation/arch/parisc/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features parisc
+.. kernel-feat:: features parisc
diff --git a/Documentation/arch/powerpc/features.rst b/Documentation/arch/powerpc/features.rst
index aeae73df86b0..ee4b95e04202 100644
--- a/Documentation/arch/powerpc/features.rst
+++ b/Documentation/arch/powerpc/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features powerpc
+.. kernel-feat:: features powerpc
diff --git a/Documentation/arch/riscv/features.rst b/Documentation/arch/riscv/features.rst
index c70ef6ac2368..36e90144adab 100644
--- a/Documentation/arch/riscv/features.rst
+++ b/Documentation/arch/riscv/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features riscv
+.. kernel-feat:: features riscv
diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index 7b2384de471f..b2bcc9eed9aa 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -12,7 +12,7 @@ is defined in <asm/hwprobe.h>::
     };
 
     long sys_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-                           size_t cpu_count, cpu_set_t *cpus,
+                           size_t cpusetsize, cpu_set_t *cpus,
                            unsigned int flags);
 
 The arguments are split into three groups: an array of key-value pairs, a CPU
@@ -20,12 +20,26 @@ set, and some flags. The key-value pairs are supplied with a count. Userspace
 must prepopulate the key field for each element, and the kernel will fill in the
 value if the key is recognized. If a key is unknown to the kernel, its key field
 will be cleared to -1, and its value set to 0. The CPU set is defined by
-CPU_SET(3). For value-like keys (eg. vendor/arch/impl), the returned value will
-be only be valid if all CPUs in the given set have the same value. Otherwise -1
-will be returned. For boolean-like keys, the value returned will be a logical
-AND of the values for the specified CPUs. Usermode can supply NULL for cpus and
-0 for cpu_count as a shortcut for all online CPUs. There are currently no flags,
-this value must be zero for future compatibility.
+CPU_SET(3) with size ``cpusetsize`` bytes. For value-like keys (eg. vendor,
+arch, impl), the returned value will only be valid if all CPUs in the given set
+have the same value. Otherwise -1 will be returned. For boolean-like keys, the
+value returned will be a logical AND of the values for the specified CPUs.
+Usermode can supply NULL for ``cpus`` and 0 for ``cpusetsize`` as a shortcut for
+all online CPUs. The currently supported flags are:
+
+* :c:macro:`RISCV_HWPROBE_WHICH_CPUS`: This flag basically reverses the behavior
+  of sys_riscv_hwprobe().  Instead of populating the values of keys for a given
+  set of CPUs, the values of each key are given and the set of CPUs is reduced
+  by sys_riscv_hwprobe() to only those which match each of the key-value pairs.
+  How matching is done depends on the key type.  For value-like keys, matching
+  means to be the exact same as the value.  For boolean-like keys, matching
+  means the result of a logical AND of the pair's value with the CPU's value is
+  exactly the same as the pair's value.  Additionally, when ``cpus`` is an empty
+  set, then it is initialized to all online CPUs which fit within it, i.e. the
+  CPU set returned is the reduction of all the online CPUs which can be
+  represented with a CPU set of size ``cpusetsize``.
+
+All other flags are reserved for future compatibility and must be zero.
 
 On success 0 is returned, on failure a negative error code is returned.
 
@@ -80,6 +94,100 @@ The following keys are defined:
   * :c:macro:`RISCV_HWPROBE_EXT_ZICBOZ`: The Zicboz extension is supported, as
        ratified in commit 3dd606f ("Create cmobase-v1.0.pdf") of riscv-CMOs.
 
+  * :c:macro:`RISCV_HWPROBE_EXT_ZBC` The Zbc extension is supported, as defined
+       in version 1.0 of the Bit-Manipulation ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZBKB` The Zbkb extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZBKC` The Zbkc extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZBKX` The Zbkx extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZKND` The Zknd extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZKNE` The Zkne extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZKNH` The Zknh extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZKSED` The Zksed extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZKSH` The Zksh extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZKT` The Zkt extension is supported, as defined
+       in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVBB`: The Zvbb extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVBC`: The Zvbc extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKB`: The Zvkb extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKG`: The Zvkg extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKNED`: The Zvkned extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKNHA`: The Zvknha extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKNHB`: The Zvknhb extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKSED`: The Zvksed extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKSH`: The Zvksh extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKT`: The Zvkt extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZFH`: The Zfh extension version 1.0 is supported
+       as defined in the RISC-V ISA manual.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZFHMIN`: The Zfhmin extension version 1.0 is
+       supported as defined in the RISC-V ISA manual.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZIHINTNTL`: The Zihintntl extension version 1.0
+       is supported as defined in the RISC-V ISA manual.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVFH`: The Zvfh extension is supported as
+       defined in the RISC-V Vector manual starting from commit e2ccd0548d6c
+       ("Remove draft warnings from Zvfh[min]").
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVFHMIN`: The Zvfhmin extension is supported as
+       defined in the RISC-V Vector manual starting from commit e2ccd0548d6c
+       ("Remove draft warnings from Zvfh[min]").
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZFA`: The Zfa extension is supported as
+       defined in the RISC-V ISA manual starting from commit 056b6ff467c7
+       ("Zfa is ratified").
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZTSO`: The Ztso extension is supported as
+       defined in the RISC-V ISA manual starting from commit 5618fb5a216b
+       ("Ztso is now ratified.")
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZACAS`: The Zacas extension is supported as
+       defined in the Atomic Compare-and-Swap (CAS) instructions manual starting
+       from commit 5059e0ca641c ("update to ratified").
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZICOND`: The Zicond extension is supported as
+       defined in the RISC-V Integer Conditional (Zicond) operations extension
+       manual starting from commit 95cf1f9 ("Add changes requested by Ved
+       during signoff")
+
 * :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: A bitmask that contains performance
   information about the selected set of processors.
 
diff --git a/Documentation/arch/s390/features.rst b/Documentation/arch/s390/features.rst
index 57c296a9d8f3..2883dc950681 100644
--- a/Documentation/arch/s390/features.rst
+++ b/Documentation/arch/s390/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features s390
+.. kernel-feat:: features s390
diff --git a/Documentation/arch/sh/features.rst b/Documentation/arch/sh/features.rst
index f722af3b6c99..fae48fe81e9b 100644
--- a/Documentation/arch/sh/features.rst
+++ b/Documentation/arch/sh/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features sh
+.. kernel-feat:: features sh
diff --git a/Documentation/arch/sparc/features.rst b/Documentation/arch/sparc/features.rst
index c0c92468b0fe..96835b6d598a 100644
--- a/Documentation/arch/sparc/features.rst
+++ b/Documentation/arch/sparc/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features sparc
+.. kernel-feat:: features sparc
diff --git a/Documentation/arch/x86/features.rst b/Documentation/arch/x86/features.rst
index b663f15053ce..a33616346a38 100644
--- a/Documentation/arch/x86/features.rst
+++ b/Documentation/arch/x86/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features x86
+.. kernel-feat:: features x86
diff --git a/Documentation/arch/x86/mds.rst b/Documentation/arch/x86/mds.rst
index e73fdff62c0a..c58c72362911 100644
--- a/Documentation/arch/x86/mds.rst
+++ b/Documentation/arch/x86/mds.rst
@@ -95,6 +95,9 @@ The kernel provides a function to invoke the buffer clearing:
 
     mds_clear_cpu_buffers()
 
+Also macro CLEAR_CPU_BUFFERS can be used in ASM late in exit-to-user path.
+Other than CFLAGS.ZF, this macro doesn't clobber any registers.
+
 The mitigation is invoked on kernel/userspace, hypervisor/guest and C-state
 (idle) transitions.
 
@@ -138,17 +141,30 @@ Mitigation points
 
    When transitioning from kernel to user space the CPU buffers are flushed
    on affected CPUs when the mitigation is not disabled on the kernel
-   command line. The migitation is enabled through the static key
-   mds_user_clear.
-
-   The mitigation is invoked in prepare_exit_to_usermode() which covers
-   all but one of the kernel to user space transitions.  The exception
-   is when we return from a Non Maskable Interrupt (NMI), which is
-   handled directly in do_nmi().
-
-   (The reason that NMI is special is that prepare_exit_to_usermode() can
-    enable IRQs.  In NMI context, NMIs are blocked, and we don't want to
-    enable IRQs with NMIs blocked.)
+   command line. The mitigation is enabled through the feature flag
+   X86_FEATURE_CLEAR_CPU_BUF.
+
+   The mitigation is invoked just before transitioning to userspace after
+   user registers are restored. This is done to minimize the window in
+   which kernel data could be accessed after VERW e.g. via an NMI after
+   VERW.
+
+   **Corner case not handled**
+   Interrupts returning to kernel don't clear CPUs buffers since the
+   exit-to-user path is expected to do that anyways. But, there could be
+   a case when an NMI is generated in kernel after the exit-to-user path
+   has cleared the buffers. This case is not handled and NMI returning to
+   kernel don't clear CPU buffers because:
+
+   1. It is rare to get an NMI after VERW, but before returning to userspace.
+   2. For an unprivileged user, there is no known way to make that NMI
+      less rare or target it.
+   3. It would take a large number of these precisely-timed NMIs to mount
+      an actual attack.  There's presumably not enough bandwidth.
+   4. The NMI in question occurs after a VERW, i.e. when user state is
+      restored and most interesting data is already scrubbed. Whats left
+      is only the data that NMI touches, and that may or may not be of
+      any interest.
 
 
 2. C-State transition
diff --git a/Documentation/arch/x86/tdx.rst b/Documentation/arch/x86/tdx.rst
index dc8d9fd2c3f7..719043cd8b46 100644
--- a/Documentation/arch/x86/tdx.rst
+++ b/Documentation/arch/x86/tdx.rst
@@ -10,6 +10,191 @@ encrypting the guest memory. In TDX, a special module running in a special
 mode sits between the host and the guest and manages the guest/host
 separation.
 
+TDX Host Kernel Support
+=======================
+
+TDX introduces a new CPU mode called Secure Arbitration Mode (SEAM) and
+a new isolated range pointed by the SEAM Ranger Register (SEAMRR).  A
+CPU-attested software module called 'the TDX module' runs inside the new
+isolated range to provide the functionalities to manage and run protected
+VMs.
+
+TDX also leverages Intel Multi-Key Total Memory Encryption (MKTME) to
+provide crypto-protection to the VMs.  TDX reserves part of MKTME KeyIDs
+as TDX private KeyIDs, which are only accessible within the SEAM mode.
+BIOS is responsible for partitioning legacy MKTME KeyIDs and TDX KeyIDs.
+
+Before the TDX module can be used to create and run protected VMs, it
+must be loaded into the isolated range and properly initialized.  The TDX
+architecture doesn't require the BIOS to load the TDX module, but the
+kernel assumes it is loaded by the BIOS.
+
+TDX boot-time detection
+-----------------------
+
+The kernel detects TDX by detecting TDX private KeyIDs during kernel
+boot.  Below dmesg shows when TDX is enabled by BIOS::
+
+  [..] virt/tdx: BIOS enabled: private KeyID range: [16, 64)
+
+TDX module initialization
+---------------------------------------
+
+The kernel talks to the TDX module via the new SEAMCALL instruction.  The
+TDX module implements SEAMCALL leaf functions to allow the kernel to
+initialize it.
+
+If the TDX module isn't loaded, the SEAMCALL instruction fails with a
+special error.  In this case the kernel fails the module initialization
+and reports the module isn't loaded::
+
+  [..] virt/tdx: module not loaded
+
+Initializing the TDX module consumes roughly ~1/256th system RAM size to
+use it as 'metadata' for the TDX memory.  It also takes additional CPU
+time to initialize those metadata along with the TDX module itself.  Both
+are not trivial.  The kernel initializes the TDX module at runtime on
+demand.
+
+Besides initializing the TDX module, a per-cpu initialization SEAMCALL
+must be done on one cpu before any other SEAMCALLs can be made on that
+cpu.
+
+The kernel provides two functions, tdx_enable() and tdx_cpu_enable() to
+allow the user of TDX to enable the TDX module and enable TDX on local
+cpu respectively.
+
+Making SEAMCALL requires VMXON has been done on that CPU.  Currently only
+KVM implements VMXON.  For now both tdx_enable() and tdx_cpu_enable()
+don't do VMXON internally (not trivial), but depends on the caller to
+guarantee that.
+
+To enable TDX, the caller of TDX should: 1) temporarily disable CPU
+hotplug; 2) do VMXON and tdx_enable_cpu() on all online cpus; 3) call
+tdx_enable().  For example::
+
+        cpus_read_lock();
+        on_each_cpu(vmxon_and_tdx_cpu_enable());
+        ret = tdx_enable();
+        cpus_read_unlock();
+        if (ret)
+                goto no_tdx;
+        // TDX is ready to use
+
+And the caller of TDX must guarantee the tdx_cpu_enable() has been
+successfully done on any cpu before it wants to run any other SEAMCALL.
+A typical usage is do both VMXON and tdx_cpu_enable() in CPU hotplug
+online callback, and refuse to online if tdx_cpu_enable() fails.
+
+User can consult dmesg to see whether the TDX module has been initialized.
+
+If the TDX module is initialized successfully, dmesg shows something
+like below::
+
+  [..] virt/tdx: 262668 KBs allocated for PAMT
+  [..] virt/tdx: module initialized
+
+If the TDX module failed to initialize, dmesg also shows it failed to
+initialize::
+
+  [..] virt/tdx: module initialization failed ...
+
+TDX Interaction to Other Kernel Components
+------------------------------------------
+
+TDX Memory Policy
+~~~~~~~~~~~~~~~~~
+
+TDX reports a list of "Convertible Memory Region" (CMR) to tell the
+kernel which memory is TDX compatible.  The kernel needs to build a list
+of memory regions (out of CMRs) as "TDX-usable" memory and pass those
+regions to the TDX module.  Once this is done, those "TDX-usable" memory
+regions are fixed during module's lifetime.
+
+To keep things simple, currently the kernel simply guarantees all pages
+in the page allocator are TDX memory.  Specifically, the kernel uses all
+system memory in the core-mm "at the time of TDX module initialization"
+as TDX memory, and in the meantime, refuses to online any non-TDX-memory
+in the memory hotplug.
+
+Physical Memory Hotplug
+~~~~~~~~~~~~~~~~~~~~~~~
+
+Note TDX assumes convertible memory is always physically present during
+machine's runtime.  A non-buggy BIOS should never support hot-removal of
+any convertible memory.  This implementation doesn't handle ACPI memory
+removal but depends on the BIOS to behave correctly.
+
+CPU Hotplug
+~~~~~~~~~~~
+
+TDX module requires the per-cpu initialization SEAMCALL must be done on
+one cpu before any other SEAMCALLs can be made on that cpu.  The kernel
+provides tdx_cpu_enable() to let the user of TDX to do it when the user
+wants to use a new cpu for TDX task.
+
+TDX doesn't support physical (ACPI) CPU hotplug.  During machine boot,
+TDX verifies all boot-time present logical CPUs are TDX compatible before
+enabling TDX.  A non-buggy BIOS should never support hot-add/removal of
+physical CPU.  Currently the kernel doesn't handle physical CPU hotplug,
+but depends on the BIOS to behave correctly.
+
+Note TDX works with CPU logical online/offline, thus the kernel still
+allows to offline logical CPU and online it again.
+
+Kexec()
+~~~~~~~
+
+TDX host support currently lacks the ability to handle kexec.  For
+simplicity only one of them can be enabled in the Kconfig.  This will be
+fixed in the future.
+
+Erratum
+~~~~~~~
+
+The first few generations of TDX hardware have an erratum.  A partial
+write to a TDX private memory cacheline will silently "poison" the
+line.  Subsequent reads will consume the poison and generate a machine
+check.
+
+A partial write is a memory write where a write transaction of less than
+cacheline lands at the memory controller.  The CPU does these via
+non-temporal write instructions (like MOVNTI), or through UC/WC memory
+mappings.  Devices can also do partial writes via DMA.
+
+Theoretically, a kernel bug could do partial write to TDX private memory
+and trigger unexpected machine check.  What's more, the machine check
+code will present these as "Hardware error" when they were, in fact, a
+software-triggered issue.  But in the end, this issue is hard to trigger.
+
+If the platform has such erratum, the kernel prints additional message in
+machine check handler to tell user the machine check may be caused by
+kernel bug on TDX private memory.
+
+Interaction vs S3 and deeper states
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+TDX cannot survive from S3 and deeper states.  The hardware resets and
+disables TDX completely when platform goes to S3 and deeper.  Both TDX
+guests and the TDX module get destroyed permanently.
+
+The kernel uses S3 for suspend-to-ram, and use S4 and deeper states for
+hibernation.  Currently, for simplicity, the kernel chooses to make TDX
+mutually exclusive with S3 and hibernation.
+
+The kernel disables TDX during early boot when hibernation support is
+available::
+
+  [..] virt/tdx: initialization failed: Hibernation support is enabled
+
+Add 'nohibernate' kernel command line to disable hibernation in order to
+use TDX.
+
+ACPI S3 is disabled during kernel early boot if TDX is enabled.  The user
+needs to turn off TDX in the BIOS in order to use S3.
+
+TDX Guest Support
+=================
 Since the host cannot directly access guest registers or memory, much
 normal functionality of a hypervisor must be moved into the guest. This is
 implemented using a Virtualization Exception (#VE) that is handled by the
@@ -20,7 +205,7 @@ TDX includes new hypercall-like mechanisms for communicating from the
 guest to the hypervisor or the TDX module.
 
 New TDX Exceptions
-==================
+------------------
 
 TDX guests behave differently from bare-metal and traditional VMX guests.
 In TDX guests, otherwise normal instructions or memory accesses can cause
@@ -30,7 +215,7 @@ Instructions marked with an '*' conditionally cause exceptions.  The
 details for these instructions are discussed below.
 
 Instruction-based #VE
----------------------
+~~~~~~~~~~~~~~~~~~~~~
 
 - Port I/O (INS, OUTS, IN, OUT)
 - HLT
@@ -41,7 +226,7 @@ Instruction-based #VE
 - CPUID*
 
 Instruction-based #GP
----------------------
+~~~~~~~~~~~~~~~~~~~~~
 
 - All VMX instructions: INVEPT, INVVPID, VMCLEAR, VMFUNC, VMLAUNCH,
   VMPTRLD, VMPTRST, VMREAD, VMRESUME, VMWRITE, VMXOFF, VMXON
@@ -52,7 +237,7 @@ Instruction-based #GP
 - RDMSR*,WRMSR*
 
 RDMSR/WRMSR Behavior
---------------------
+~~~~~~~~~~~~~~~~~~~~
 
 MSR access behavior falls into three categories:
 
@@ -73,7 +258,7 @@ trapping and handling in the TDX module.  Other than possibly being slow,
 these MSRs appear to function just as they would on bare metal.
 
 CPUID Behavior
---------------
+~~~~~~~~~~~~~~
 
 For some CPUID leaves and sub-leaves, the virtualized bit fields of CPUID
 return values (in guest EAX/EBX/ECX/EDX) are configurable by the
@@ -93,7 +278,7 @@ not know how to handle. The guest kernel may ask the hypervisor for the
 value with a hypercall.
 
 #VE on Memory Accesses
-======================
+----------------------
 
 There are essentially two classes of TDX memory: private and shared.
 Private memory receives full TDX protections.  Its content is protected
@@ -107,7 +292,7 @@ entries.  This helps ensure that a guest does not place sensitive
 information in shared memory, exposing it to the untrusted hypervisor.
 
 #VE on Shared Memory
---------------------
+~~~~~~~~~~~~~~~~~~~~
 
 Access to shared mappings can cause a #VE.  The hypervisor ultimately
 controls whether a shared memory access causes a #VE, so the guest must be
@@ -127,7 +312,7 @@ be careful not to access device MMIO regions unless it is also prepared to
 handle a #VE.
 
 #VE on Private Pages
---------------------
+~~~~~~~~~~~~~~~~~~~~
 
 An access to private mappings can also cause a #VE.  Since all kernel
 memory is also private memory, the kernel might theoretically need to
@@ -145,7 +330,7 @@ The hypervisor is permitted to unilaterally move accepted pages to a
 to handle the exception.
 
 Linux #VE handler
-=================
+-----------------
 
 Just like page faults or #GP's, #VE exceptions can be either handled or be
 fatal.  Typically, an unhandled userspace #VE results in a SIGSEGV.
@@ -167,7 +352,7 @@ While the block is in place, any #VE is elevated to a double fault (#DF)
 which is not recoverable.
 
 MMIO handling
-=============
+-------------
 
 In non-TDX VMs, MMIO is usually implemented by giving a guest access to a
 mapping which will cause a VMEXIT on access, and then the hypervisor
@@ -189,7 +374,7 @@ MMIO access via other means (like structure overlays) may result in an
 oops.
 
 Shared Memory Conversions
-=========================
+-------------------------
 
 All TDX guest memory starts out as private at boot.  This memory can not
 be accessed by the hypervisor.  However, some kernel users like device
diff --git a/Documentation/arch/xtensa/features.rst b/Documentation/arch/xtensa/features.rst
index 6b92c7bfa19d..28dcce1759be 100644
--- a/Documentation/arch/xtensa/features.rst
+++ b/Documentation/arch/xtensa/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features xtensa
+.. kernel-feat:: features xtensa
diff --git a/Documentation/block/ioprio.rst b/Documentation/block/ioprio.rst
index a25c6d5df87b..4662e1ff3d81 100644
--- a/Documentation/block/ioprio.rst
+++ b/Documentation/block/ioprio.rst
@@ -6,17 +6,16 @@ Block io priorities
 Intro
 -----
 
-With the introduction of cfq v3 (aka cfq-ts or time sliced cfq), basic io
-priorities are supported for reads on files.  This enables users to io nice
-processes or process groups, similar to what has been possible with cpu
-scheduling for ages.  This document mainly details the current possibilities
-with cfq; other io schedulers do not support io priorities thus far.
+The io priority feature enables users to io nice processes or process groups,
+similar to what has been possible with cpu scheduling for ages. Support for io
+priorities is io scheduler dependent and currently supported by bfq and
+mq-deadline.
 
 Scheduling classes
 ------------------
 
-CFQ implements three generic scheduling classes that determine how io is
-served for a process.
+Three generic scheduling classes are implemented for io priorities that
+determine how io is served for a process.
 
 IOPRIO_CLASS_RT: This is the realtime io class. This scheduling class is given
 higher priority than any other in the system, processes from this class are
diff --git a/Documentation/conf.py b/Documentation/conf.py
index 5830b01c5642..da64c9fb7e07 100644
--- a/Documentation/conf.py
+++ b/Documentation/conf.py
@@ -388,6 +388,12 @@ latex_elements = {
         verbatimhintsturnover=false,
     ''',
 
+    #
+    # Some of our authors are fond of deep nesting; tell latex to
+    # cope.
+    #
+    'maxlistdepth': '10',
+
     # For CJK One-half spacing, need to be in front of hyperref
     'extrapackages': r'\usepackage{setspace}',
 
diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst
index 2d6af6c4665c..ed73c612174d 100644
--- a/Documentation/core-api/workqueue.rst
+++ b/Documentation/core-api/workqueue.rst
@@ -256,15 +256,11 @@ may queue at the same time.  Unless there is a specific need for
 throttling the number of active work items, specifying '0' is
 recommended.
 
-Some users depend on the strict execution ordering of ST wq.  The
-combination of ``@max_active`` of 1 and ``WQ_UNBOUND`` used to
-achieve this behavior.  Work items on such wq were always queued to the
-unbound worker-pools and only one work item could be active at any given
-time thus achieving the same ordering property as ST wq.
-
-In the current implementation the above configuration only guarantees
-ST behavior within a given NUMA node. Instead ``alloc_ordered_workqueue()`` should
-be used to achieve system-wide ST behavior.
+Some users depend on strict execution ordering where only one work item
+is in flight at any given time and the work items are processed in
+queueing order. While the combination of ``@max_active`` of 1 and
+``WQ_UNBOUND`` used to achieve this behavior, this is no longer the
+case. Use ``alloc_ordered_queue()`` instead.
 
 
 Example Execution Scenarios
@@ -465,7 +461,7 @@ The command used: ::
 
 There are 24 issuers, each issuing 64 IOs concurrently. ``--verify=sha512``
 makes ``fio`` generate and read back the content each time which makes
-execution locality matter between the issuer and ``kcryptd``. The followings
+execution locality matter between the issuer and ``kcryptd``. The following
 are the read bandwidths and CPU utilizations depending on different affinity
 scope settings on ``kcryptd`` measured over five runs. Bandwidths are in
 MiBps, and CPU util in percents.
diff --git a/Documentation/dev-tools/checkuapi.rst b/Documentation/dev-tools/checkuapi.rst
new file mode 100644
index 000000000000..9072f21b50b0
--- /dev/null
+++ b/Documentation/dev-tools/checkuapi.rst
@@ -0,0 +1,477 @@
+.. SPDX-License-Identifier: GPL-2.0-only
+
+============
+UAPI Checker
+============
+
+The UAPI checker (``scripts/check-uapi.sh``) is a shell script which
+checks UAPI header files for userspace backwards-compatibility across
+the git tree.
+
+Options
+=======
+
+This section will describe the options with which ``check-uapi.sh``
+can be run.
+
+Usage::
+
+    check-uapi.sh [-b BASE_REF] [-p PAST_REF] [-j N] [-l ERROR_LOG] [-i] [-q] [-v]
+
+Available options::
+
+    -b BASE_REF    Base git reference to use for comparison. If unspecified or empty,
+                   will use any dirty changes in tree to UAPI files. If there are no
+                   dirty changes, HEAD will be used.
+    -p PAST_REF    Compare BASE_REF to PAST_REF (e.g. -p v6.1). If unspecified or empty,
+                   will use BASE_REF^1. Must be an ancestor of BASE_REF. Only headers
+                   that exist on PAST_REF will be checked for compatibility.
+    -j JOBS        Number of checks to run in parallel (default: number of CPU cores).
+    -l ERROR_LOG   Write error log to file (default: no error log is generated).
+    -i             Ignore ambiguous changes that may or may not break UAPI compatibility.
+    -q             Quiet operation.
+    -v             Verbose operation (print more information about each header being checked).
+
+Environmental args::
+
+    ABIDIFF  Custom path to abidiff binary
+    CC       C compiler (default is "gcc")
+    ARCH     Target architecture of C compiler (default is host arch)
+
+Exit codes::
+
+    0) Success
+    1) ABI difference detected
+    2) Prerequisite not met
+
+Examples
+========
+
+Basic Usage
+-----------
+
+First, let's try making a change to a UAPI header file that obviously
+won't break userspace::
+
+    cat << 'EOF' | patch -l -p1
+    --- a/include/uapi/linux/acct.h
+    +++ b/include/uapi/linux/acct.h
+    @@ -21,7 +21,9 @@
+     #include <asm/param.h>
+     #include <asm/byteorder.h>
+
+    -/*
+    +#define FOO
+    +
+    +/*
+      *  comp_t is a 16-bit "floating" point number with a 3-bit base 8
+      *  exponent and a 13-bit fraction.
+      *  comp2_t is 24-bit with 5-bit base 2 exponent and 20 bit fraction
+    diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
+    EOF
+
+Now, let's use the script to validate::
+
+    % ./scripts/check-uapi.sh
+    Installing user-facing UAPI headers from dirty tree... OK
+    Installing user-facing UAPI headers from HEAD... OK
+    Checking changes to UAPI headers between HEAD and dirty tree...
+    All 912 UAPI headers compatible with x86 appear to be backwards compatible
+
+Let's add another change that *might* break userspace::
+
+    cat << 'EOF' | patch -l -p1
+    --- a/include/uapi/linux/bpf.h
+    +++ b/include/uapi/linux/bpf.h
+    @@ -74,7 +74,7 @@ struct bpf_insn {
+            __u8    dst_reg:4;      /* dest register */
+            __u8    src_reg:4;      /* source register */
+            __s16   off;            /* signed offset */
+    -       __s32   imm;            /* signed immediate constant */
+    +       __u32   imm;            /* unsigned immediate constant */
+     };
+
+     /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */
+    EOF
+
+The script will catch this::
+
+    % ./scripts/check-uapi.sh
+    Installing user-facing UAPI headers from dirty tree... OK
+    Installing user-facing UAPI headers from HEAD... OK
+    Checking changes to UAPI headers between HEAD and dirty tree...
+    ==== ABI differences detected in include/linux/bpf.h from HEAD -> dirty tree ====
+        [C] 'struct bpf_insn' changed:
+          type size hasn't changed
+          1 data member change:
+            type of '__s32 imm' changed:
+              typedef name changed from __s32 to __u32 at int-ll64.h:27:1
+              underlying type 'int' changed:
+                type name changed from 'int' to 'unsigned int'
+                type size hasn't changed
+    ==================================================================================
+
+    error - 1/912 UAPI headers compatible with x86 appear _not_ to be backwards compatible
+
+In this case, the script is reporting the type change because it could
+break a userspace program that passes in a negative number. Now, let's
+say you know that no userspace program could possibly be using a negative
+value in ``imm``, so changing to an unsigned type there shouldn't hurt
+anything. You can pass the ``-i`` flag to the script to ignore changes
+in which the userspace backwards compatibility is ambiguous::
+
+    % ./scripts/check-uapi.sh -i
+    Installing user-facing UAPI headers from dirty tree... OK
+    Installing user-facing UAPI headers from HEAD... OK
+    Checking changes to UAPI headers between HEAD and dirty tree...
+    All 912 UAPI headers compatible with x86 appear to be backwards compatible
+
+Now, let's make a similar change that *will* break userspace::
+
+    cat << 'EOF' | patch -l -p1
+    --- a/include/uapi/linux/bpf.h
+    +++ b/include/uapi/linux/bpf.h
+    @@ -71,8 +71,8 @@ enum {
+
+     struct bpf_insn {
+            __u8    code;           /* opcode */
+    -       __u8    dst_reg:4;      /* dest register */
+            __u8    src_reg:4;      /* source register */
+    +       __u8    dst_reg:4;      /* dest register */
+            __s16   off;            /* signed offset */
+            __s32   imm;            /* signed immediate constant */
+     };
+    EOF
+
+Since we're re-ordering an existing struct member, there's no ambiguity,
+and the script will report the breakage even if you pass ``-i``::
+
+    % ./scripts/check-uapi.sh -i
+    Installing user-facing UAPI headers from dirty tree... OK
+    Installing user-facing UAPI headers from HEAD... OK
+    Checking changes to UAPI headers between HEAD and dirty tree...
+    ==== ABI differences detected in include/linux/bpf.h from HEAD -> dirty tree ====
+        [C] 'struct bpf_insn' changed:
+          type size hasn't changed
+          2 data member changes:
+            '__u8 dst_reg' offset changed from 8 to 12 (in bits) (by +4 bits)
+            '__u8 src_reg' offset changed from 12 to 8 (in bits) (by -4 bits)
+    ==================================================================================
+
+    error - 1/912 UAPI headers compatible with x86 appear _not_ to be backwards compatible
+
+Let's commit the breaking change, then commit the innocuous change::
+
+    % git commit -m 'Breaking UAPI change' include/uapi/linux/bpf.h
+    [detached HEAD f758e574663a] Breaking UAPI change
+     1 file changed, 1 insertion(+), 1 deletion(-)
+    % git commit -m 'Innocuous UAPI change' include/uapi/linux/acct.h
+    [detached HEAD 2e87df769081] Innocuous UAPI change
+     1 file changed, 3 insertions(+), 1 deletion(-)
+
+Now, let's run the script again with no arguments::
+
+    % ./scripts/check-uapi.sh
+    Installing user-facing UAPI headers from HEAD... OK
+    Installing user-facing UAPI headers from HEAD^1... OK
+    Checking changes to UAPI headers between HEAD^1 and HEAD...
+    All 912 UAPI headers compatible with x86 appear to be backwards compatible
+
+It doesn't catch any breaking change because, by default, it only
+compares ``HEAD`` to ``HEAD^1``. The breaking change was committed on
+``HEAD~2``. If we wanted the search scope to go back further, we'd have to
+use the ``-p`` option to pass a different past reference. In this case,
+let's pass ``-p HEAD~2`` to the script so it checks UAPI changes between
+``HEAD~2`` and ``HEAD``::
+
+    % ./scripts/check-uapi.sh -p HEAD~2
+    Installing user-facing UAPI headers from HEAD... OK
+    Installing user-facing UAPI headers from HEAD~2... OK
+    Checking changes to UAPI headers between HEAD~2 and HEAD...
+    ==== ABI differences detected in include/linux/bpf.h from HEAD~2 -> HEAD ====
+        [C] 'struct bpf_insn' changed:
+          type size hasn't changed
+          2 data member changes:
+            '__u8 dst_reg' offset changed from 8 to 12 (in bits) (by +4 bits)
+            '__u8 src_reg' offset changed from 12 to 8 (in bits) (by -4 bits)
+    ==============================================================================
+
+    error - 1/912 UAPI headers compatible with x86 appear _not_ to be backwards compatible
+
+Alternatively, we could have also run with ``-b HEAD~``. This would set the
+base reference to ``HEAD~`` so then the script would compare it to ``HEAD~^1``.
+
+Architecture-specific Headers
+-----------------------------
+
+Consider this change::
+
+    cat << 'EOF' | patch -l -p1
+    --- a/arch/arm64/include/uapi/asm/sigcontext.h
+    +++ b/arch/arm64/include/uapi/asm/sigcontext.h
+    @@ -70,6 +70,7 @@ struct sigcontext {
+     struct _aarch64_ctx {
+            __u32 magic;
+            __u32 size;
+    +       __u32 new_var;
+     };
+
+     #define FPSIMD_MAGIC   0x46508001
+    EOF
+
+This is a change to an arm64-specific UAPI header file. In this example, I'm
+running the script from an x86 machine with an x86 compiler, so, by default,
+the script only checks x86-compatible UAPI header files::
+
+    % ./scripts/check-uapi.sh
+    Installing user-facing UAPI headers from dirty tree... OK
+    Installing user-facing UAPI headers from HEAD... OK
+    No changes to UAPI headers were applied between HEAD and dirty tree
+
+With an x86 compiler, we can't check header files in ``arch/arm64``, so the
+script doesn't even try.
+
+If we want to check the header file, we'll have to use an arm64 compiler and
+set ``ARCH`` accordingly::
+
+    % CC=aarch64-linux-gnu-gcc ARCH=arm64 ./scripts/check-uapi.sh
+    Installing user-facing UAPI headers from dirty tree... OK
+    Installing user-facing UAPI headers from HEAD... OK
+    Checking changes to UAPI headers between HEAD and dirty tree...
+    ==== ABI differences detected in include/asm/sigcontext.h from HEAD -> dirty tree ====
+        [C] 'struct _aarch64_ctx' changed:
+          type size changed from 64 to 96 (in bits)
+          1 data member insertion:
+            '__u32 new_var', at offset 64 (in bits) at sigcontext.h:73:1
+        -- snip --
+        [C] 'struct zt_context' changed:
+          type size changed from 128 to 160 (in bits)
+          2 data member changes (1 filtered):
+            '__u16 nregs' offset changed from 64 to 96 (in bits) (by +32 bits)
+            '__u16 __reserved[3]' offset changed from 80 to 112 (in bits) (by +32 bits)
+    =======================================================================================
+
+    error - 1/884 UAPI headers compatible with arm64 appear _not_ to be backwards compatible
+
+We can see with ``ARCH`` and ``CC`` set properly for the file, the ABI
+change is reported properly. Also notice that the total number of UAPI
+header files checked by the script changes. This is because the number
+of headers installed for arm64 platforms is different than x86.
+
+Cross-Dependency Breakages
+--------------------------
+
+Consider this change::
+
+    cat << 'EOF' | patch -l -p1
+    --- a/include/uapi/linux/types.h
+    +++ b/include/uapi/linux/types.h
+    @@ -52,7 +52,7 @@ typedef __u32 __bitwise __wsum;
+     #define __aligned_be64 __be64 __attribute__((aligned(8)))
+     #define __aligned_le64 __le64 __attribute__((aligned(8)))
+
+    -typedef unsigned __bitwise __poll_t;
+    +typedef unsigned short __bitwise __poll_t;
+
+     #endif /*  __ASSEMBLY__ */
+     #endif /* _UAPI_LINUX_TYPES_H */
+    EOF
+
+Here, we're changing a ``typedef`` in ``types.h``. This doesn't break
+a UAPI in ``types.h``, but other UAPIs in the tree may break due to
+this change::
+
+    % ./scripts/check-uapi.sh
+    Installing user-facing UAPI headers from dirty tree... OK
+    Installing user-facing UAPI headers from HEAD... OK
+    Checking changes to UAPI headers between HEAD and dirty tree...
+    ==== ABI differences detected in include/linux/eventpoll.h from HEAD -> dirty tree ====
+        [C] 'struct epoll_event' changed:
+          type size changed from 96 to 80 (in bits)
+          2 data member changes:
+            type of '__poll_t events' changed:
+              underlying type 'unsigned int' changed:
+                type name changed from 'unsigned int' to 'unsigned short int'
+                type size changed from 32 to 16 (in bits)
+            '__u64 data' offset changed from 32 to 16 (in bits) (by -16 bits)
+    ========================================================================================
+    include/linux/eventpoll.h did not change between HEAD and dirty tree...
+    It's possible a change to one of the headers it includes caused this error:
+    #include <linux/fcntl.h>
+    #include <linux/types.h>
+
+Note that the script noticed the failing header file did not change,
+so it assumes one of its includes must have caused the breakage. Indeed,
+we can see ``linux/types.h`` is used from ``eventpoll.h``.
+
+UAPI Header Removals
+--------------------
+
+Consider this change::
+
+    cat << 'EOF' | patch -l -p1
+    diff --git a/include/uapi/asm-generic/Kbuild b/include/uapi/asm-generic/Kbuild
+    index ebb180aac74e..a9c88b0a8b3b 100644
+    --- a/include/uapi/asm-generic/Kbuild
+    +++ b/include/uapi/asm-generic/Kbuild
+    @@ -31,6 +31,6 @@ mandatory-y += stat.h
+     mandatory-y += statfs.h
+     mandatory-y += swab.h
+     mandatory-y += termbits.h
+    -mandatory-y += termios.h
+    +#mandatory-y += termios.h
+     mandatory-y += types.h
+     mandatory-y += unistd.h
+    EOF
+
+This script removes a UAPI header file from the install list. Let's run
+the script::
+
+    % ./scripts/check-uapi.sh
+    Installing user-facing UAPI headers from dirty tree... OK
+    Installing user-facing UAPI headers from HEAD... OK
+    Checking changes to UAPI headers between HEAD and dirty tree...
+    ==== UAPI header include/asm/termios.h was removed between HEAD and dirty tree ====
+
+    error - 1/912 UAPI headers compatible with x86 appear _not_ to be backwards compatible
+
+Removing a UAPI header is considered a breaking change, and the script
+will flag it as such.
+
+Checking Historic UAPI Compatibility
+------------------------------------
+
+You can use the ``-b`` and ``-p`` options to examine different chunks of your
+git tree. For example, to check all changed UAPI header files between tags
+v6.0 and v6.1, you'd run::
+
+    % ./scripts/check-uapi.sh -b v6.1 -p v6.0
+    Installing user-facing UAPI headers from v6.1... OK
+    Installing user-facing UAPI headers from v6.0... OK
+    Checking changes to UAPI headers between v6.0 and v6.1...
+
+    --- snip ---
+    error - 37/907 UAPI headers compatible with x86 appear _not_ to be backwards compatible
+
+Note: Before v5.3, a header file needed by the script is not present,
+so the script is unable to check changes before then.
+
+You'll notice that the script detected many UAPI changes that are not
+backwards compatible. Knowing that kernel UAPIs are supposed to be stable
+forever, this is an alarming result. This brings us to the next section:
+caveats.
+
+Caveats
+=======
+
+The UAPI checker makes no assumptions about the author's intention, so some
+types of changes may be flagged even though they intentionally break UAPI.
+
+Removals For Refactoring or Deprecation
+---------------------------------------
+
+Sometimes drivers for very old hardware are removed, such as in this example::
+
+    % ./scripts/check-uapi.sh -b ba47652ba655
+    Installing user-facing UAPI headers from ba47652ba655... OK
+    Installing user-facing UAPI headers from ba47652ba655^1... OK
+    Checking changes to UAPI headers between ba47652ba655^1 and ba47652ba655...
+    ==== UAPI header include/linux/meye.h was removed between ba47652ba655^1 and ba47652ba655 ====
+
+    error - 1/910 UAPI headers compatible with x86 appear _not_ to be backwards compatible
+
+The script will always flag removals (even if they're intentional).
+
+Struct Expansions
+-----------------
+
+Depending on how a structure is handled in kernelspace, a change which
+expands a struct could be non-breaking.
+
+If a struct is used as the argument to an ioctl, then the kernel driver
+must be able to handle ioctl commands of any size. Beyond that, you need
+to be careful when copying data from the user. Say, for example, that
+``struct foo`` is changed like this::
+
+    struct foo {
+        __u64 a; /* added in version 1 */
+    +   __u32 b; /* added in version 2 */
+    +   __u32 c; /* added in version 2 */
+    }
+
+By default, the script will flag this kind of change for further review::
+
+    [C] 'struct foo' changed:
+      type size changed from 64 to 128 (in bits)
+      2 data member insertions:
+        '__u32 b', at offset 64 (in bits)
+        '__u32 c', at offset 96 (in bits)
+
+However, it is possible that this change was made safely.
+
+If a userspace program was built with version 1, it will think
+``sizeof(struct foo)`` is 8. That size will be encoded in the
+ioctl value that gets sent to the kernel. If the kernel is built
+with version 2, it will think the ``sizeof(struct foo)`` is 16.
+
+The kernel can use the ``_IOC_SIZE`` macro to get the size encoded
+in the ioctl code that the user passed in and then use
+``copy_struct_from_user()`` to safely copy the value::
+
+    int handle_ioctl(unsigned long cmd, unsigned long arg)
+    {
+        switch _IOC_NR(cmd) {
+        0x01: {
+            struct foo my_cmd;  /* size 16 in the kernel */
+
+            ret = copy_struct_from_user(&my_cmd, arg, sizeof(struct foo), _IOC_SIZE(cmd));
+            ...
+
+``copy_struct_from_user`` will zero the struct in the kernel and then copy
+only the bytes passed in from the user (leaving new members zeroized).
+If the user passed in a larger struct, the extra members are ignored.
+
+If you know this situation is accounted for in the kernel code, you can
+pass ``-i`` to the script, and struct expansions like this will be ignored.
+
+Flex Array Migration
+--------------------
+
+While the script handles expansion into an existing flex array, it does
+still flag initial migration to flex arrays from 1-element fake flex
+arrays. For example::
+
+    struct foo {
+          __u32 x;
+    -     __u32 flex[1]; /* fake flex */
+    +     __u32 flex[];  /* real flex */
+    };
+
+This change would be flagged by the script::
+
+    [C] 'struct foo' changed:
+      type size changed from 64 to 32 (in bits)
+      1 data member change:
+        type of '__u32 flex[1]' changed:
+          type name changed from '__u32[1]' to '__u32[]'
+          array type size changed from 32 to 'unknown'
+          array type subrange 1 changed length from 1 to 'unknown'
+
+At this time, there's no way to filter these types of changes, so be
+aware of this possible false positive.
+
+Summary
+-------
+
+While many types of false positives are filtered out by the script,
+it's possible there are some cases where the script flags a change
+which does not break UAPI. It's also possible a change which *does*
+break userspace would not be flagged by this script. While the script
+has been run on much of the kernel history, there could still be corner
+cases that are not accounted for.
+
+The intention is for this script to be used as a quick check for
+maintainers or automated tooling, not as the end-all authority on
+patch compatibility. It's best to remember: use your best judgment
+(and ideally a unit test in userspace) to make sure your UAPI changes
+are backwards-compatible!
diff --git a/Documentation/dev-tools/index.rst b/Documentation/dev-tools/index.rst
index 3d2286c683bc..efa49cdc8e2e 100644
--- a/Documentation/dev-tools/index.rst
+++ b/Documentation/dev-tools/index.rst
@@ -31,6 +31,7 @@ Documentation/dev-tools/testing-overview.rst
    kselftest
    kunit/index
    ktap
+   checkuapi
 
 
 .. only::  subproject and html
diff --git a/Documentation/dev-tools/kselftest.rst b/Documentation/dev-tools/kselftest.rst
index ab376b316c36..7f3582a67318 100644
--- a/Documentation/dev-tools/kselftest.rst
+++ b/Documentation/dev-tools/kselftest.rst
@@ -245,6 +245,10 @@ Contributing new tests (details)
    TEST_PROGS, TEST_GEN_PROGS mean it is the executable tested by
    default.
 
+   TEST_GEN_MODS_DIR should be used by tests that require modules to be built
+   before the test starts. The variable will contain the name of the directory
+   containing the modules.
+
    TEST_CUSTOM_PROGS should be used by tests that require custom build
    rules and prevent common build rule use.
 
diff --git a/Documentation/dev-tools/kunit/running_tips.rst b/Documentation/dev-tools/kunit/running_tips.rst
index 024e9ad1d1e9..bd689db6fdd2 100644
--- a/Documentation/dev-tools/kunit/running_tips.rst
+++ b/Documentation/dev-tools/kunit/running_tips.rst
@@ -139,6 +139,17 @@ If your installed version of gcc doesn't work, you can tweak the steps:
 	$ ./tools/testing/kunit/kunit.py run --make_options=CC=/usr/bin/gcc-6
 	$ lcov -t "my_kunit_tests" -o coverage.info -c -d .kunit/ --gcov-tool=/usr/bin/gcov-6
 
+Alternatively, LLVM-based toolchains can also be used:
+
+.. code-block:: bash
+
+	# Build with LLVM and append coverage options to the current config
+	$ ./tools/testing/kunit/kunit.py run --make_options LLVM=1 --kunitconfig=.kunit/ --kunitconfig=tools/testing/kunit/configs/coverage_uml.config
+	$ llvm-profdata merge -sparse default.profraw -o default.profdata
+	$ llvm-cov export --format=lcov .kunit/vmlinux -instr-profile default.profdata > coverage.info
+	# The coverage.info file is in lcov-compatible format and it can be used to e.g. generate HTML report
+	$ genhtml -o /tmp/coverage_html coverage.info
+
 
 Running tests manually
 ======================
diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst
index a9efab50eed8..22955d56b379 100644
--- a/Documentation/dev-tools/kunit/usage.rst
+++ b/Documentation/dev-tools/kunit/usage.rst
@@ -671,8 +671,23 @@ Testing Static Functions
 ------------------------
 
 If we do not want to expose functions or variables for testing, one option is to
-conditionally ``#include`` the test file at the end of your .c file. For
-example:
+conditionally export the used symbol. For example:
+
+.. code-block:: c
+
+	/* In my_file.c */
+
+	VISIBLE_IF_KUNIT int do_interesting_thing();
+	EXPORT_SYMBOL_IF_KUNIT(do_interesting_thing);
+
+	/* In my_file.h */
+
+	#if IS_ENABLED(CONFIG_KUNIT)
+		int do_interesting_thing(void);
+	#endif
+
+Alternatively, you could conditionally ``#include`` the test file at the end of
+your .c file. For example:
 
 .. code-block:: c
 
diff --git a/Documentation/devicetree/bindings/Makefile b/Documentation/devicetree/bindings/Makefile
index 2323fd5b7cda..129cf698fa8a 100644
--- a/Documentation/devicetree/bindings/Makefile
+++ b/Documentation/devicetree/bindings/Makefile
@@ -28,7 +28,10 @@ $(obj)/%.example.dts: $(src)/%.yaml check_dtschema_version FORCE
 find_all_cmd = find $(srctree)/$(src) \( -name '*.yaml' ! \
 		-name 'processed-schema*' \)
 
-find_cmd = $(find_all_cmd) | sed 's|^$(srctree)/$(src)/||' | grep -F -e "$(subst :," -e ",$(DT_SCHEMA_FILES))" | sed 's|^|$(srctree)/$(src)/|'
+find_cmd = $(find_all_cmd) | \
+		sed 's|^$(srctree)/||' | \
+		grep -F -e "$(subst :," -e ",$(DT_SCHEMA_FILES))" | \
+		sed 's|^|$(srctree)/|'
 CHK_DT_DOCS := $(shell $(find_cmd))
 
 quiet_cmd_yamllint = LINT    $(src)
diff --git a/Documentation/devicetree/bindings/arm/qcom,coresight-tpdm.yaml b/Documentation/devicetree/bindings/arm/qcom,coresight-tpdm.yaml
index 3bad47b7b02b..61ddc3b5b247 100644
--- a/Documentation/devicetree/bindings/arm/qcom,coresight-tpdm.yaml
+++ b/Documentation/devicetree/bindings/arm/qcom,coresight-tpdm.yaml
@@ -44,6 +44,23 @@ properties:
     minItems: 1
     maxItems: 2
 
+  qcom,dsb-element-size:
+    description:
+      Specifies the DSB(Discrete Single Bit) element size supported by
+      the monitor. The associated aggregator will read this size before it
+      is enabled. DSB element size currently only supports 32-bit and 64-bit.
+    $ref: /schemas/types.yaml#/definitions/uint8
+    enum: [32, 64]
+
+  qcom,dsb-msrs-num:
+    description:
+      Specifies the number of DSB(Discrete Single Bit) MSR(mux select register)
+      registers supported by the monitor. If this property is not configured
+      or set to 0, it means this DSB TPDM doesn't support MSR.
+    $ref: /schemas/types.yaml#/definitions/uint32
+    minimum: 0
+    maximum: 32
+
   clocks:
     maxItems: 1
 
@@ -77,6 +94,9 @@ examples:
       compatible = "qcom,coresight-tpdm", "arm,primecell";
       reg = <0x0684c000 0x1000>;
 
+      qcom,dsb-element-size = /bits/ 8 <32>;
+      qcom,dsb-msrs-num = <16>;
+
       clocks = <&aoss_qmp>;
       clock-names = "apb_pclk";
 
diff --git a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml
index b29ce598f9aa..9952e0ef7767 100644
--- a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml
+++ b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml
@@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Ceva AHCI SATA Controller
 
 maintainers:
-  - Piyush Mehta <piyush.mehta@amd.com>
+  - Mubin Sayyed <mubin.sayyed@amd.com>
+  - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
 
 description: |
   The Ceva SATA controller mostly conforms to the AHCI interface with some
diff --git a/Documentation/devicetree/bindings/clock/google,gs101-clock.yaml b/Documentation/devicetree/bindings/clock/google,gs101-clock.yaml
index 3eebc03a309b..ca7fdada3ff2 100644
--- a/Documentation/devicetree/bindings/clock/google,gs101-clock.yaml
+++ b/Documentation/devicetree/bindings/clock/google,gs101-clock.yaml
@@ -85,8 +85,8 @@ allOf:
 
         clock-names:
           items:
-            - const: dout_cmu_misc_bus
-            - const: dout_cmu_misc_sss
+            - const: bus
+            - const: sss
 
 additionalProperties: false
 
diff --git a/Documentation/devicetree/bindings/connector/usb-connector.yaml b/Documentation/devicetree/bindings/connector/usb-connector.yaml
index 7c8a3e8430d3..fb216ce68bb3 100644
--- a/Documentation/devicetree/bindings/connector/usb-connector.yaml
+++ b/Documentation/devicetree/bindings/connector/usb-connector.yaml
@@ -66,7 +66,6 @@ properties:
       Particularly, if use an output GPIO to control a VBUS regulator, should
       model it as a regulator. See bindings/regulator/fixed-regulator.yaml
 
-  # The following are optional properties for "usb-c-connector".
   power-role:
     description: Determines the power role that the Type C connector will
       support. "dual" refers to Dual Role Port (DRP).
@@ -119,30 +118,6 @@ properties:
 
   # The following are optional properties for "usb-c-connector" with power
   # delivery support.
-  source-pdos:
-    description: An array of u32 with each entry providing supported power
-      source data object(PDO), the detailed bit definitions of PDO can be found
-      in "Universal Serial Bus Power Delivery Specification" chapter 6.4.1.2
-      Source_Capabilities Message, the order of each entry(PDO) should follow
-      the PD spec chapter 6.4.1. Required for power source and power dual role.
-      User can specify the source PDO array via PDO_FIXED/BATT/VAR/PPS_APDO()
-      defined in dt-bindings/usb/pd.h.
-    minItems: 1
-    maxItems: 7
-    $ref: /schemas/types.yaml#/definitions/uint32-array
-
-  sink-pdos:
-    description: An array of u32 with each entry providing supported power sink
-      data object(PDO), the detailed bit definitions of PDO can be found in
-      "Universal Serial Bus Power Delivery Specification" chapter 6.4.1.3
-      Sink Capabilities Message, the order of each entry(PDO) should follow the
-      PD spec chapter 6.4.1. Required for power sink and power dual role. User
-      can specify the sink PDO array via PDO_FIXED/BATT/VAR/PPS_APDO() defined
-      in dt-bindings/usb/pd.h.
-    minItems: 1
-    maxItems: 7
-    $ref: /schemas/types.yaml#/definitions/uint32-array
-
   sink-vdos:
     description: An array of u32 with each entry, a Vendor Defined Message Object (VDO),
       providing additional information corresponding to the product, the detailed bit
@@ -166,10 +141,43 @@ properties:
     maxItems: 6
     $ref: /schemas/types.yaml#/definitions/uint32-array
 
-  op-sink-microwatt:
-    description: Sink required operating power in microwatt, if source can't
-      offer the power, Capability Mismatch is set. Required for power sink and
-      power dual role.
+  accessory-mode-audio:
+    type: boolean
+    description: Whether the device supports Audio Adapter Accessory Mode. This
+      is only necessary if there are no other means to discover supported
+      alternative modes (e.g. through the UCSI firmware interface).
+
+  accessory-mode-debug:
+    type: boolean
+    description: Whether the device supports Debug Accessory Mode. This
+      is only necessary if there are no other means to discover supported
+      alternative modes (e.g. through the UCSI firmware interface).
+
+  altmodes:
+    type: object
+    description: List of Alternative Modes supported by the schematics on the
+      particular device. This is only necessary if there are no other means to
+      discover supported alternative modes (e.g. through the UCSI firmware
+      interface).
+
+    additionalProperties: false
+
+    patternProperties:
+      "^(displayport)$":
+        type: object
+        description:
+          A single USB-C Alternative Mode as supported by the USB-C connector logic.
+
+        additionalProperties: false
+
+        properties:
+          svid:
+            $ref: /schemas/types.yaml#/definitions/uint16
+            description: Unique value assigned by USB-IF to the Vendor / AltMode.
+            enum: [ 0xff01 ]
+          vdo:
+            $ref: /schemas/types.yaml#/definitions/uint32
+            description: VDO returned by Discover Modes USB PD command.
 
   port:
     $ref: /schemas/graph.yaml#/properties/port
@@ -231,6 +239,20 @@ properties:
       SNK_READY for non-pd link.
     type: boolean
 
+  capabilities:
+    description: A child node to contain all the selectable USB Power Delivery capabilities.
+    type: object
+
+    patternProperties:
+      "^caps-[0-9]+$":
+        description: Child nodes under "capabilities" node. Each node contains a selectable USB
+          Power Delivery capability.
+        type: object
+        $ref: "#/$defs/capabilities"
+        unevaluatedProperties: false
+
+    additionalProperties: false
+
 dependencies:
   sink-vdos-v1: [ sink-vdos ]
   sink-vdos: [ sink-vdos-v1 ]
@@ -238,7 +260,42 @@ dependencies:
 required:
   - compatible
 
+$defs:
+  capabilities:
+    type: object
+
+    properties:
+      source-pdos:
+        description: An array of u32 with each entry providing supported power
+          source data object(PDO), the detailed bit definitions of PDO can be found
+          in "Universal Serial Bus Power Delivery Specification" chapter 6.4.1.2
+          Source_Capabilities Message, the order of each entry(PDO) should follow
+          the PD spec chapter 6.4.1. Required for power source and power dual role.
+          User can specify the source PDO array via PDO_FIXED/BATT/VAR/PPS_APDO()
+          defined in dt-bindings/usb/pd.h.
+        minItems: 1
+        maxItems: 7
+        $ref: /schemas/types.yaml#/definitions/uint32-array
+
+      sink-pdos:
+        description: An array of u32 with each entry providing supported power sink
+          data object(PDO), the detailed bit definitions of PDO can be found in
+          "Universal Serial Bus Power Delivery Specification" chapter 6.4.1.3
+          Sink Capabilities Message, the order of each entry(PDO) should follow the
+          PD spec chapter 6.4.1. Required for power sink and power dual role. User
+          can specify the sink PDO array via PDO_FIXED/BATT/VAR/PPS_APDO() defined
+          in dt-bindings/usb/pd.h.
+        minItems: 1
+        maxItems: 7
+        $ref: /schemas/types.yaml#/definitions/uint32-array
+
+      op-sink-microwatt:
+        description: Sink required operating power in microwatt, if source can't
+          offer the power, Capability Mismatch is set. Required for power sink and
+          power dual role.
+
 allOf:
+  - $ref: "#/$defs/capabilities"
   - if:
       properties:
         compatible:
@@ -267,7 +324,7 @@ anyOf:
         - typec-power-opmode
         - new-source-frs-typec-current
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   # Micro-USB connector with HS lines routed via controller (MUIC).
@@ -289,6 +346,13 @@ examples:
             compatible = "usb-c-connector";
             label = "USB-C";
 
+            altmodes {
+                displayport {
+                    svid = /bits/ 16 <0xff01>;
+                    vdo = <0x00001c46>;
+                };
+            };
+
             ports {
                 #address-cells = <1>;
                 #size-cells = <0>;
diff --git a/Documentation/devicetree/bindings/display/bridge/nxp,tda998x.yaml b/Documentation/devicetree/bindings/display/bridge/nxp,tda998x.yaml
index 21d995f29a1e..b8e9cf6ce4e6 100644
--- a/Documentation/devicetree/bindings/display/bridge/nxp,tda998x.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/nxp,tda998x.yaml
@@ -29,19 +29,22 @@ properties:
 
   audio-ports:
     description:
-      Array of 8-bit values, 2 values per DAI (Documentation/sound/soc/dai.rst).
+      Array of 2 values per DAI (Documentation/sound/soc/dai.rst).
       The implementation allows one or two DAIs.
       If two DAIs are defined, they must be of different type.
     $ref: /schemas/types.yaml#/definitions/uint32-matrix
+    minItems: 1
+    maxItems: 2
     items:
-      minItems: 1
       items:
         - description: |
             The first value defines the DAI type: TDA998x_SPDIF or TDA998x_I2S
             (see include/dt-bindings/display/tda998x.h).
+          enum: [ 1, 2 ]
         - description:
             The second value defines the tda998x AP_ENA reg content when the
             DAI in question is used.
+          maximum: 0xff
 
   '#sound-dai-cells':
     enum: [ 0, 1 ]
diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml
index 25d53fde92e1..597c9cc6a312 100644
--- a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml
+++ b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml
@@ -85,7 +85,7 @@ allOf:
         clocks:
           minItems: 6
           maxItems: 6
-        regs:
+        reg:
           minItems: 2
           maxItems: 2
 
@@ -99,7 +99,7 @@ allOf:
         clocks:
           minItems: 4
           maxItems: 4
-        regs:
+        reg:
           minItems: 2
           maxItems: 2
 
@@ -116,7 +116,7 @@ allOf:
         clocks:
           minItems: 3
           maxItems: 3
-        regs:
+        reg:
           minItems: 1
           maxItems: 1
 
diff --git a/Documentation/devicetree/bindings/dma/dma-controller.yaml b/Documentation/devicetree/bindings/dma/dma-controller.yaml
index 04d150d4d15d..e6afca558c2d 100644
--- a/Documentation/devicetree/bindings/dma/dma-controller.yaml
+++ b/Documentation/devicetree/bindings/dma/dma-controller.yaml
@@ -19,19 +19,4 @@ properties:
 
 additionalProperties: true
 
-examples:
-  - |
-    dma: dma-controller@48000000 {
-        compatible = "ti,omap-sdma";
-        reg = <0x48000000 0x1000>;
-        interrupts = <0 12 0x4>,
-                     <0 13 0x4>,
-                     <0 14 0x4>,
-                     <0 15 0x4>;
-        #dma-cells = <1>;
-        dma-channels = <32>;
-        dma-requests = <127>;
-        dma-channel-mask = <0xfffe>;
-    };
-
 ...
diff --git a/Documentation/devicetree/bindings/dma/dma-router.yaml b/Documentation/devicetree/bindings/dma/dma-router.yaml
index 346fe0fa4460..5ad2febc581e 100644
--- a/Documentation/devicetree/bindings/dma/dma-router.yaml
+++ b/Documentation/devicetree/bindings/dma/dma-router.yaml
@@ -40,15 +40,4 @@ required:
 
 additionalProperties: true
 
-examples:
-  - |
-    sdma_xbar: dma-router@4a002b78 {
-        compatible = "ti,dra7-dma-crossbar";
-        reg = <0x4a002b78 0xfc>;
-        #dma-cells = <1>;
-        dma-requests = <205>;
-        ti,dma-safe-map = <0>;
-        dma-masters = <&sdma>;
-    };
-
 ...
diff --git a/Documentation/devicetree/bindings/dma/loongson,ls2x-apbdma.yaml b/Documentation/devicetree/bindings/dma/loongson,ls2x-apbdma.yaml
new file mode 100644
index 000000000000..6a1b49a49a64
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/loongson,ls2x-apbdma.yaml
@@ -0,0 +1,62 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/loongson,ls2x-apbdma.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Loongson LS2X APB DMA controller
+
+description:
+  The Loongson LS2X APB DMA controller is used for transferring data
+  between system memory and the peripherals on the APB bus.
+
+maintainers:
+  - Binbin Zhou <zhoubinbin@loongson.cn>
+
+allOf:
+  - $ref: dma-controller.yaml#
+
+properties:
+  compatible:
+    oneOf:
+      - const: loongson,ls2k1000-apbdma
+      - items:
+          - const: loongson,ls2k0500-apbdma
+          - const: loongson,ls2k1000-apbdma
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  '#dma-cells':
+    const: 1
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - '#dma-cells'
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/clock/loongson,ls2k-clk.h>
+
+    dma-controller@1fe00c00 {
+        compatible = "loongson,ls2k1000-apbdma";
+        reg = <0x1fe00c00 0x8>;
+        interrupt-parent = <&liointc1>;
+        interrupts = <12 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&clk LOONGSON2_APB_CLK>;
+        #dma-cells = <1>;
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml b/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml
index 4003dbe94940..877147e95ecc 100644
--- a/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml
+++ b/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml
@@ -53,6 +53,9 @@ properties:
       ADMA_CHn_CTRL register.
     const: 1
 
+  dma-channel-mask:
+    maxItems: 1
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
index 88d0de3d1b46..deb64cb9ca3e 100644
--- a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
+++ b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
@@ -32,6 +32,8 @@ properties:
               - qcom,sm8350-gpi-dma
               - qcom,sm8450-gpi-dma
               - qcom,sm8550-gpi-dma
+              - qcom,sm8650-gpi-dma
+              - qcom,x1e80100-gpi-dma
           - const: qcom,sm6350-gpi-dma
       - items:
           - enum:
diff --git a/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml b/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml
index c284abc6784a..a42b6a26a6d3 100644
--- a/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml
+++ b/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml
@@ -16,7 +16,7 @@ properties:
   compatible:
     items:
       - enum:
-          - renesas,r9a07g043-dmac # RZ/G2UL
+          - renesas,r9a07g043-dmac # RZ/G2UL and RZ/Five
           - renesas,r9a07g044-dmac # RZ/G2{L,LC}
           - renesas,r9a07g054-dmac # RZ/V2L
       - const: renesas,rz-dmac
diff --git a/Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml b/Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml
index a1af0b906365..3b22183a1a37 100644
--- a/Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml
+++ b/Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml
@@ -29,6 +29,7 @@ properties:
   compatible:
     items:
       - enum:
+          - microchip,mpfs-pdma
           - sifive,fu540-c000-pdma
       - const: sifive,pdma0
     description:
diff --git a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
index 4ca300a42a99..27b8e1636560 100644
--- a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
+++ b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
@@ -37,11 +37,11 @@ properties:
 
   reg:
     minItems: 3
-    maxItems: 5
+    maxItems: 9
 
   reg-names:
     minItems: 3
-    maxItems: 5
+    maxItems: 9
 
   "#dma-cells":
     const: 3
@@ -141,7 +141,10 @@ allOf:
         ti,sci-rm-range-tchan: false
 
         reg:
-          maxItems: 3
+          items:
+            - description: BCDMA Control /Status Registers region
+            - description: RX Channel Realtime Registers region
+            - description: Ring Realtime Registers region
 
         reg-names:
           items:
@@ -161,14 +164,29 @@ allOf:
       properties:
         reg:
           minItems: 5
+          items:
+            - description: BCDMA Control /Status Registers region
+            - description: Block Copy Channel Realtime Registers region
+            - description: RX Channel Realtime Registers region
+            - description: TX Channel Realtime Registers region
+            - description: Ring Realtime Registers region
+            - description: Ring Configuration Registers region
+            - description: TX Channel Configuration Registers region
+            - description: RX Channel Configuration Registers region
+            - description: Block Copy Channel Configuration Registers region
 
         reg-names:
+          minItems: 5
           items:
             - const: gcfg
             - const: bchanrt
             - const: rchanrt
             - const: tchanrt
             - const: ringrt
+            - const: ring
+            - const: tchan
+            - const: rchan
+            - const: bchan
 
       required:
         - ti,sci-rm-range-bchan
@@ -184,7 +202,11 @@ allOf:
         ti,sci-rm-range-bchan: false
 
         reg:
-          maxItems: 4
+          items:
+            - description: BCDMA Control /Status Registers region
+            - description: RX Channel Realtime Registers region
+            - description: TX Channel Realtime Registers region
+            - description: Ring Realtime Registers region
 
         reg-names:
           items:
@@ -220,8 +242,13 @@ examples:
                       <0x0 0x4c000000 0x0 0x20000>,
                       <0x0 0x4a820000 0x0 0x20000>,
                       <0x0 0x4aa40000 0x0 0x20000>,
-                      <0x0 0x4bc00000 0x0 0x100000>;
-                reg-names = "gcfg", "bchanrt", "rchanrt", "tchanrt", "ringrt";
+                      <0x0 0x4bc00000 0x0 0x100000>,
+                      <0x0 0x48600000 0x0 0x8000>,
+                      <0x0 0x484a4000 0x0 0x2000>,
+                      <0x0 0x484c2000 0x0 0x2000>,
+                      <0x0 0x48420000 0x0 0x2000>;
+                reg-names = "gcfg", "bchanrt", "rchanrt", "tchanrt", "ringrt",
+                            "ring", "tchan", "rchan", "bchan";
                 msi-parent = <&inta_main_dmss>;
                 #dma-cells = <3>;
 
diff --git a/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml
index a69f62f854d8..11e064c02994 100644
--- a/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml
+++ b/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml
@@ -45,14 +45,28 @@ properties:
       The second cell is the ASEL value for the channel
 
   reg:
-    maxItems: 4
+    minItems: 4
+    items:
+      - description: Packet DMA Control /Status Registers region
+      - description: RX Channel Realtime Registers region
+      - description: TX Channel Realtime Registers region
+      - description: Ring Realtime Registers region
+      - description: Ring Configuration Registers region
+      - description: TX Configuration Registers region
+      - description: RX Configuration Registers region
+      - description: RX Flow Configuration Registers region
 
   reg-names:
+    minItems: 4
     items:
       - const: gcfg
       - const: rchanrt
       - const: tchanrt
       - const: ringrt
+      - const: ring
+      - const: tchan
+      - const: rchan
+      - const: rflow
 
   msi-parent: true
 
@@ -136,8 +150,14 @@ examples:
                 reg = <0x0 0x485c0000 0x0 0x100>,
                       <0x0 0x4a800000 0x0 0x20000>,
                       <0x0 0x4aa00000 0x0 0x40000>,
-                      <0x0 0x4b800000 0x0 0x400000>;
-                reg-names = "gcfg", "rchanrt", "tchanrt", "ringrt";
+                      <0x0 0x4b800000 0x0 0x400000>,
+                      <0x0 0x485e0000 0x0 0x20000>,
+                      <0x0 0x484a0000 0x0 0x4000>,
+                      <0x0 0x484c0000 0x0 0x2000>,
+                      <0x0 0x48430000 0x0 0x4000>;
+                reg-names = "gcfg", "rchanrt", "tchanrt", "ringrt",
+                            "ring", "tchan", "rchan", "rflow";
+
                 msi-parent = <&inta_main_dmss>;
                 #dma-cells = <2>;
 
diff --git a/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml
index 22f6c5e2f7f4..b18cf2bfdb5b 100644
--- a/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml
+++ b/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml
@@ -69,13 +69,24 @@ properties:
       - ti,j721e-navss-mcu-udmap
 
   reg:
-    maxItems: 3
+    minItems: 3
+    items:
+      - description: UDMA-P Control /Status Registers region
+      - description: RX Channel Realtime Registers region
+      - description: TX Channel Realtime Registers region
+      - description: TX Configuration Registers region
+      - description: RX Configuration Registers region
+      - description: RX Flow Configuration Registers region
 
   reg-names:
+    minItems: 3
     items:
       - const: gcfg
       - const: rchanrt
       - const: tchanrt
+      - const: tchan
+      - const: rchan
+      - const: rflow
 
   msi-parent: true
 
@@ -158,8 +169,11 @@ examples:
                 compatible = "ti,am654-navss-main-udmap";
                 reg = <0x0 0x31150000 0x0 0x100>,
                       <0x0 0x34000000 0x0 0x100000>,
-                      <0x0 0x35000000 0x0 0x100000>;
-                reg-names = "gcfg", "rchanrt", "tchanrt";
+                      <0x0 0x35000000 0x0 0x100000>,
+                      <0x0 0x30b00000 0x0 0x20000>,
+                      <0x0 0x30c00000 0x0 0x8000>,
+                      <0x0 0x30d00000 0x0 0x4000>;
+                reg-names = "gcfg", "rchanrt", "tchanrt", "tchan", "rchan", "rflow";
                 #dma-cells = <1>;
 
                 ti,ringacc = <&ringacc>;
diff --git a/Documentation/devicetree/bindings/eeprom/at24.yaml b/Documentation/devicetree/bindings/eeprom/at24.yaml
index b6864d0ee81e..1812ef31d5f1 100644
--- a/Documentation/devicetree/bindings/eeprom/at24.yaml
+++ b/Documentation/devicetree/bindings/eeprom/at24.yaml
@@ -123,6 +123,7 @@ properties:
           - enum:
               - onnn,cat24c04
               - onnn,cat24c05
+              - rohm,br24g04
           - const: atmel,24c04
       - items:
           - const: renesas,r1ex24016
diff --git a/Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml b/Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml
index c1060e5fcef3..d3d8a2e143ed 100644
--- a/Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml
+++ b/Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml
@@ -126,7 +126,7 @@ examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
 
-        gpio@e000a000 {
+        gpio@a0020000 {
             compatible = "xlnx,xps-gpio-1.00.a";
             reg = <0xa0020000 0x10000>;
             #gpio-cells = <2>;
diff --git a/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml b/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml
index b1fd632718d4..bb93baa88879 100644
--- a/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml
+++ b/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml
@@ -12,7 +12,8 @@ description:
   PS_MODE). Every pin can be configured as input/output.
 
 maintainers:
-  - Piyush Mehta <piyush.mehta@amd.com>
+  - Mubin Sayyed <mubin.sayyed@amd.com>
+  - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/i2c/st,stm32-i2c.yaml b/Documentation/devicetree/bindings/i2c/st,stm32-i2c.yaml
index 94b75d9f66cd..1b31b87c1800 100644
--- a/Documentation/devicetree/bindings/i2c/st,stm32-i2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/st,stm32-i2c.yaml
@@ -19,6 +19,7 @@ allOf:
               - st,stm32f7-i2c
               - st,stm32mp13-i2c
               - st,stm32mp15-i2c
+              - st,stm32mp25-i2c
     then:
       properties:
         i2c-scl-rising-time-ns:
@@ -41,6 +42,30 @@ allOf:
         clock-frequency:
           enum: [100000, 400000]
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - st,stm32f4-i2c
+              - st,stm32f7-i2c
+              - st,stm32mp13-i2c
+              - st,stm32mp15-i2c
+    then:
+      properties:
+        interrupts:
+          minItems: 2
+
+        interrupt-names:
+          minItems: 2
+    else:
+      properties:
+        interrupts:
+          maxItems: 1
+
+        interrupt-names:
+          maxItems: 1
+
 properties:
   compatible:
     enum:
@@ -48,6 +73,7 @@ properties:
       - st,stm32f7-i2c
       - st,stm32mp13-i2c
       - st,stm32mp15-i2c
+      - st,stm32mp25-i2c
 
   reg:
     maxItems: 1
@@ -56,11 +82,13 @@ properties:
     items:
       - description: interrupt ID for I2C event
       - description: interrupt ID for I2C error
+    minItems: 1
 
   interrupt-names:
     items:
       - const: event
       - const: error
+    minItems: 1
 
   resets:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7091r5.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7091r5.yaml
index ce7ba634643c..ddec9747436c 100644
--- a/Documentation/devicetree/bindings/iio/adc/adi,ad7091r5.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7091r5.yaml
@@ -4,36 +4,92 @@
 $id: http://devicetree.org/schemas/iio/adc/adi,ad7091r5.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: Analog Devices AD7091R5 4-Channel 12-Bit ADC
+title: Analog Devices AD7091R-2/-4/-5/-8 Multi-Channel 12-Bit ADCs
 
 maintainers:
   - Michael Hennerich <michael.hennerich@analog.com>
+  - Marcelo Schmitt <marcelo.schmitt@analog.com>
 
 description: |
-  Analog Devices AD7091R5 4-Channel 12-Bit ADC
+  Analog Devices AD7091R5 4-Channel 12-Bit ADC supporting I2C interface
   https://www.analog.com/media/en/technical-documentation/data-sheets/ad7091r-5.pdf
+  Analog Devices AD7091R-2/AD7091R-4/AD7091R-8 2-/4-/8-Channel 12-Bit ADCs
+  supporting SPI interface
+  https://www.analog.com/media/en/technical-documentation/data-sheets/AD7091R-2_7091R-4_7091R-8.pdf
 
 properties:
   compatible:
     enum:
+      - adi,ad7091r2
+      - adi,ad7091r4
       - adi,ad7091r5
+      - adi,ad7091r8
 
   reg:
     maxItems: 1
 
+  vdd-supply:
+    description:
+      Provide VDD power to the sensor (VDD range is from 2.7V to 5.25V).
+
+  vdrive-supply:
+    description:
+      Determines the voltage level at which the interface logic will operate.
+      The V_drive voltage range is from 1.8V to 5.25V and must not exceed VDD by
+      more than 0.3V.
+
   vref-supply:
     description:
       Phandle to the vref power supply
 
-  interrupts:
+  convst-gpios:
+    description:
+      GPIO connected to the CONVST pin.
+      This logic input is used to initiate conversions on the analog
+      input channels.
     maxItems: 1
 
+  reset-gpios:
+    maxItems: 1
+
+  interrupts:
+    description:
+      Interrupt for signaling when conversion results exceed the high limit for
+      ADC readings or fall below the low limit for them. Interrupt source must
+      be attached to ALERT/BUSY/GPO0 pin.
+    maxItems: 1
 
 required:
   - compatible
   - reg
 
-additionalProperties: false
+allOf:
+  - $ref: /schemas/spi/spi-peripheral-props.yaml#
+
+  # AD7091R-2 does not have ALERT/BUSY/GPO pin
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - adi,ad7091r2
+    then:
+      properties:
+        interrupts: false
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - adi,ad7091r2
+              - adi,ad7091r4
+              - adi,ad7091r8
+    then:
+      required:
+        - convst-gpios
+
+unevaluatedProperties: false
 
 examples:
   - |
@@ -51,4 +107,22 @@ examples:
             interrupt-parent = <&gpio>;
         };
     };
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+    spi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        adc@0 {
+            compatible = "adi,ad7091r8";
+            reg = <0x0>;
+            spi-max-frequency = <1000000>;
+            vref-supply = <&adc_vref>;
+            convst-gpios = <&gpio 25 GPIO_ACTIVE_LOW>;
+            reset-gpios = <&gpio 27 GPIO_ACTIVE_LOW>;
+            interrupts = <22 IRQ_TYPE_EDGE_FALLING>;
+            interrupt-parent = <&gpio>;
+        };
+    };
 ...
diff --git a/Documentation/devicetree/bindings/iio/adc/maxim,max34408.yaml b/Documentation/devicetree/bindings/iio/adc/maxim,max34408.yaml
new file mode 100644
index 000000000000..4cba856e8d47
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/adc/maxim,max34408.yaml
@@ -0,0 +1,139 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/adc/maxim,max34408.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Maxim MAX34408/MAX34409 current monitors with overcurrent control
+
+maintainers:
+  - Ivan Mikhaylov <fr0st61te@gmail.com>
+
+description: |
+  The MAX34408/MAX34409 are two- and four-channel current monitors that are
+  configured and monitored with a standard I2C/SMBus serial interface. Each
+  unidirectional current sensor offers precision high-side operation with a
+  low full-scale sense voltage. The devices automatically sequence through
+  two or four channels and collect the current-sense samples and average them
+  to reduce the effect of impulse noise. The raw ADC samples are compared to
+  user-programmable digital thresholds to indicate overcurrent conditions.
+  Overcurrent conditions trigger a hardware output to provide an immediate
+  indication to shut down any necessary external circuitry.
+
+  Specifications about the devices can be found at:
+  https://www.analog.com/media/en/technical-documentation/data-sheets/MAX34408-MAX34409.pdf
+
+properties:
+  compatible:
+    enum:
+      - maxim,max34408
+      - maxim,max34409
+
+  "#address-cells":
+    const: 1
+
+  "#size-cells":
+    const: 0
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  powerdown-gpios:
+    description:
+      Shutdown Output. Open-drain output. This output transitions to high impedance
+      when any of the digital comparator thresholds are exceeded as long as the ENA
+      pin is high.
+    maxItems: 1
+
+  powerdown-status-gpios:
+    description:
+      SHTDN Enable Input. CMOS digital input. Connect to GND to clear the latch and
+      unconditionally deassert (force low) the SHTDN output and reset the shutdown
+      delay. Connect to VDD to enable normal latch operation of the SHTDN output.
+    maxItems: 1
+
+  vdd-supply: true
+
+patternProperties:
+  "^channel@[0-3]$":
+    $ref: adc.yaml
+    type: object
+    description:
+      Represents the internal channels of the ADC.
+
+    properties:
+      reg:
+        items:
+          - minimum: 0
+            maximum: 3
+
+      maxim,rsense-val-micro-ohms:
+        description:
+          Adjust the Rsense value to monitor higher or lower current levels for
+          input.
+        enum: [250, 500, 1000, 5000, 10000, 50000, 100000, 200000, 500000]
+        default: 1000
+
+    required:
+      - reg
+      - maxim,rsense-val-micro-ohms
+
+    unevaluatedProperties: false
+
+required:
+  - compatible
+  - reg
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: maxim,max34408
+    then:
+      patternProperties:
+        "^channel@[2-3]$": false
+        "^channel@[0-1]$":
+          properties:
+            reg:
+              maximum: 1
+    else:
+      patternProperties:
+        "^channel@[0-3]$":
+          properties:
+            reg:
+              maximum: 3
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        adc@1e {
+              compatible = "maxim,max34409";
+              reg = <0x1e>;
+              powerdown-gpios = <&gpio0 1 GPIO_ACTIVE_LOW>;
+              powerdown-status-gpios = <&gpio0 2 GPIO_ACTIVE_HIGH>;
+
+              #address-cells = <1>;
+              #size-cells = <0>;
+
+              channel@0 {
+                  reg = <0x0>;
+                  maxim,rsense-val-micro-ohms = <5000>;
+              };
+
+              channel@1 {
+                  reg = <0x1>;
+                  maxim,rsense-val-micro-ohms = <10000>;
+             };
+        };
+    };
diff --git a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml
index b6a233cd5f6b..5ed893ef5c18 100644
--- a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml
@@ -25,7 +25,7 @@ properties:
       - const: qcom,spmi-iadc
 
   reg:
-    description: IADC base address and length in the SPMI PMIC register map
+    description: IADC base address in the SPMI PMIC register map
     maxItems: 1
 
   qcom,external-resistor-micro-ohms:
@@ -50,10 +50,12 @@ additionalProperties: false
 examples:
   - |
     #include <dt-bindings/interrupt-controller/irq.h>
-    spmi {
+
+    pmic {
         #address-cells = <1>;
         #size-cells = <0>;
-        pmic_iadc: adc@3600 {
+
+        adc@3600 {
             compatible = "qcom,pm8941-iadc", "qcom,spmi-iadc";
             reg = <0x3600>;
             interrupts = <0x0 0x36 0x0 IRQ_TYPE_EDGE_RISING>;
diff --git a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-rradc.yaml b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-rradc.yaml
index 64abe9a4cd9e..f39bc92c2b99 100644
--- a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-rradc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-rradc.yaml
@@ -43,7 +43,7 @@ examples:
         #address-cells = <1>;
         #size-cells = <0>;
 
-        pmic_rradc: adc@4500 {
+        adc@4500 {
             compatible = "qcom,pmi8998-rradc";
             reg = <0x4500>;
             #io-channel-cells = <1>;
diff --git a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-vadc.yaml b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-vadc.yaml
index ad7d6fc49de5..40fa0710f1f0 100644
--- a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-vadc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-vadc.yaml
@@ -236,11 +236,11 @@ additionalProperties: false
 
 examples:
   - |
-    spmi {
+    pmic {
         #address-cells = <1>;
         #size-cells = <0>;
-        /* VADC node */
-        pmic_vadc: adc@3100 {
+
+        adc@3100 {
             compatible = "qcom,spmi-vadc";
             reg = <0x3100>;
             interrupts = <0x0 0x31 0x0 0x1>;
@@ -281,9 +281,10 @@ examples:
     #include <dt-bindings/iio/qcom,spmi-adc7-pm8350.h>
     #include <dt-bindings/interrupt-controller/irq.h>
 
-    spmi {
+    pmic {
         #address-cells = <1>;
         #size-cells = <0>;
+
         adc@3100 {
             reg = <0x3100>;
             compatible = "qcom,spmi-adc7";
diff --git a/Documentation/devicetree/bindings/iio/adc/ti,palmas-gpadc.yaml b/Documentation/devicetree/bindings/iio/adc/ti,palmas-gpadc.yaml
index 720c16a108d4..f94057d8f605 100644
--- a/Documentation/devicetree/bindings/iio/adc/ti,palmas-gpadc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/ti,palmas-gpadc.yaml
@@ -67,19 +67,4 @@ required:
   - compatible
   - "#io-channel-cells"
 
-examples:
-  - |
-    #include <dt-bindings/clock/mt8183-clk.h>
-    pmic {
-        compatible = "ti,twl6035-pmic", "ti,palmas-pmic";
-        adc {
-            compatible = "ti,palmas-gpadc";
-            interrupts = <18 0>,
-                         <16 0>,
-                         <17 0>;
-            #io-channel-cells = <1>;
-            ti,channel0-current-microamp = <5>;
-            ti,channel3-current-microamp = <10>;
-        };
-    };
 ...
diff --git a/Documentation/devicetree/bindings/iio/amplifiers/adi,hmc425a.yaml b/Documentation/devicetree/bindings/iio/amplifiers/adi,hmc425a.yaml
index 2ee6080deac7..67de9d4e3a1d 100644
--- a/Documentation/devicetree/bindings/iio/amplifiers/adi,hmc425a.yaml
+++ b/Documentation/devicetree/bindings/iio/amplifiers/adi,hmc425a.yaml
@@ -12,6 +12,9 @@ maintainers:
 description: |
   Digital Step Attenuator IIO devices with gpio interface.
   Offer various frequency and attenuation ranges.
+  ADRF5750 2 dB LSB, 4-Bit, Silicon Digital Attenuator, 10 MHz to 60 GHz
+    https://www.analog.com/media/en/technical-documentation/data-sheets/adrf5740.pdf
+
   HMC425A 0.5 dB LSB GaAs MMIC 6-BIT DIGITAL POSITIVE CONTROL ATTENUATOR, 2.2 - 8.0 GHz
     https://www.analog.com/media/en/technical-documentation/data-sheets/hmc425A.pdf
 
@@ -22,6 +25,7 @@ description: |
 properties:
   compatible:
     enum:
+      - adi,adrf5740
       - adi,hmc425a
       - adi,hmc540s
 
diff --git a/Documentation/devicetree/bindings/iio/chemical/aosong,ags02ma.yaml b/Documentation/devicetree/bindings/iio/chemical/aosong,ags02ma.yaml
new file mode 100644
index 000000000000..35e7b094e878
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/chemical/aosong,ags02ma.yaml
@@ -0,0 +1,47 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/chemical/aosong,ags02ma.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Aosong AGS02MA VOC Sensor
+
+description: |
+  AGS02MA is an TVOC (Total Volatile Organic Compounds) i2c sensor with default
+  address of 0x1a.
+
+  Datasheet:
+    https://asairsensors.com/wp-content/uploads/2021/09/AGS02MA.pdf
+
+maintainers:
+  - Anshul Dalal <anshulusr@gmail.com>
+
+properties:
+  compatible:
+    enum:
+      - aosong,ags02ma
+
+  reg:
+    maxItems: 1
+
+  vdd-supply: true
+
+required:
+  - compatible
+  - reg
+  - vdd-supply
+
+additionalProperties: false
+
+examples:
+  - |
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        voc-sensor@1a {
+            compatible = "aosong,ags02ma";
+            reg = <0x1a>;
+            vdd-supply = <&vdd_regulator>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad5791.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad5791.yaml
index 3a84739736f6..c81285d84db7 100644
--- a/Documentation/devicetree/bindings/iio/dac/adi,ad5791.yaml
+++ b/Documentation/devicetree/bindings/iio/dac/adi,ad5791.yaml
@@ -26,6 +26,11 @@ properties:
   vdd-supply: true
   vss-supply: true
 
+  adi,rbuf-gain2-en:
+    description: Specify to allow an external amplifier to be connected in a
+      gain of two configuration.
+    type: boolean
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/iio/dac/microchip,mcp4821.yaml b/Documentation/devicetree/bindings/iio/dac/microchip,mcp4821.yaml
new file mode 100644
index 000000000000..0dc577c33918
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/dac/microchip,mcp4821.yaml
@@ -0,0 +1,86 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/dac/microchip,mcp4821.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Microchip MCP4821 and similar DACs
+
+description: |
+  Supports MCP48x1 (single channel) and MCP48x2 (dual channel) series of DACs.
+  Device supports simplex communication over SPI in Mode 0 and Mode 3.
+
+  +---------+--------------+-------------+
+  | Device  |  Resolution  |   Channels  |
+  |---------|--------------|-------------|
+  | MCP4801 |     8-bit    |      1      |
+  | MCP4802 |     8-bit    |      2      |
+  | MCP4811 |    10-bit    |      1      |
+  | MCP4812 |    10-bit    |      2      |
+  | MCP4821 |    12-bit    |      1      |
+  | MCP4822 |    12-bit    |      2      |
+  +---------+--------------+-------------+
+
+  Datasheet:
+    MCP48x1: https://ww1.microchip.com/downloads/en/DeviceDoc/22244B.pdf
+    MCP48x2: https://ww1.microchip.com/downloads/en/DeviceDoc/20002249B.pdf
+
+maintainers:
+  - Anshul Dalal <anshulusr@gmail.com>
+
+allOf:
+  - $ref: /schemas/spi/spi-peripheral-props.yaml#
+
+properties:
+  compatible:
+    enum:
+      - microchip,mcp4801
+      - microchip,mcp4802
+      - microchip,mcp4811
+      - microchip,mcp4812
+      - microchip,mcp4821
+      - microchip,mcp4822
+
+  reg:
+    maxItems: 1
+
+  vdd-supply: true
+
+  ldac-gpios:
+    description: |
+      Active Low LDAC (Latch DAC Input) pin used to update the DAC output.
+    maxItems: 1
+
+  powerdown-gpios:
+    description: |
+      Active Low SHDN pin used to enter the shutdown mode.
+    maxItems: 1
+
+  spi-cpha: true
+  spi-cpol: true
+
+required:
+  - compatible
+  - reg
+  - vdd-supply
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+
+    spi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        dac@0 {
+            compatible = "microchip,mcp4821";
+            reg = <0>;
+            vdd-supply = <&vdd_regulator>;
+            ldac-gpios = <&gpio0 1 GPIO_ACTIVE_HIGH>;
+            powerdown-gpios = <&gpio0 2 GPIO_ACTIVE_HIGH>;
+            spi-cpha;
+            spi-cpol;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/iio/humidity/ti,hdc3020.yaml b/Documentation/devicetree/bindings/iio/humidity/ti,hdc3020.yaml
new file mode 100644
index 000000000000..7f6d0f9edc75
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/humidity/ti,hdc3020.yaml
@@ -0,0 +1,55 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/humidity/ti,hdc3020.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: HDC3020/HDC3021/HDC3022 humidity and temperature iio sensors
+
+maintainers:
+  - Li peiyu <579lpy@gmail.com>
+  - Javier Carrasco <javier.carrasco.cruz@gmail.com>
+
+description:
+  https://www.ti.com/lit/ds/symlink/hdc3020.pdf
+
+  The HDC302x is an integrated capacitive based relative humidity (RH)
+  and temperature sensor.
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+          - enum:
+              - ti,hdc3021
+              - ti,hdc3022
+          - const: ti,hdc3020
+      - const: ti,hdc3020
+
+  interrupts:
+    maxItems: 1
+
+  vdd-supply: true
+
+  reg:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - vdd-supply
+
+additionalProperties: false
+
+examples:
+  - |
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        humidity-sensor@47 {
+            compatible = "ti,hdc3021", "ti,hdc3020";
+            reg = <0x47>;
+            vdd-supply = <&vcc_3v3>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/iio/imu/adi,adis16460.yaml b/Documentation/devicetree/bindings/iio/imu/adi,adis16460.yaml
index 4e43c80e5119..4cacc9948726 100644
--- a/Documentation/devicetree/bindings/iio/imu/adi,adis16460.yaml
+++ b/Documentation/devicetree/bindings/iio/imu/adi,adis16460.yaml
@@ -25,6 +25,10 @@ properties:
 
   spi-cpol: true
 
+  spi-cs-inactive-delay-ns:
+    minimum: 16000
+    default: 16000
+
   interrupts:
     maxItems: 1
 
diff --git a/Documentation/devicetree/bindings/iio/imu/adi,adis16475.yaml b/Documentation/devicetree/bindings/iio/imu/adi,adis16475.yaml
index c73533c54588..9b7ad609f7db 100644
--- a/Documentation/devicetree/bindings/iio/imu/adi,adis16475.yaml
+++ b/Documentation/devicetree/bindings/iio/imu/adi,adis16475.yaml
@@ -47,6 +47,10 @@ properties:
   spi-max-frequency:
     maximum: 2000000
 
+  spi-cs-inactive-delay-ns:
+    minimum: 16000
+    default: 16000
+
   interrupts:
     maxItems: 1
 
diff --git a/Documentation/devicetree/bindings/iio/imu/bosch,bmi323.yaml b/Documentation/devicetree/bindings/iio/imu/bosch,bmi323.yaml
new file mode 100644
index 000000000000..64ef26e19669
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/imu/bosch,bmi323.yaml
@@ -0,0 +1,77 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/imu/bosch,bmi323.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Bosch BMI323 6-Axis IMU
+
+maintainers:
+  - Jagath Jog J <jagathjog1996@gmail.com>
+
+description:
+  BMI323 is a 6-axis inertial measurement unit that supports acceleration and
+  gyroscopic measurements with hardware fifo buffering. Sensor also provides
+  events information such as motion, steps, orientation, single and double
+  tap detection.
+
+properties:
+  compatible:
+    const: bosch,bmi323
+
+  reg:
+    maxItems: 1
+
+  vdd-supply: true
+  vddio-supply: true
+
+  interrupts:
+    minItems: 1
+    maxItems: 2
+
+  interrupt-names:
+    minItems: 1
+    maxItems: 2
+    items:
+      enum:
+        - INT1
+        - INT2
+
+  drive-open-drain:
+    description:
+      set if the specified interrupt pin should be configured as
+      open drain. If not set, defaults to push-pull.
+
+  mount-matrix:
+    description:
+      an optional 3x3 mounting rotation matrix.
+
+required:
+  - compatible
+  - reg
+  - vdd-supply
+  - vddio-supply
+
+allOf:
+  - $ref: /schemas/spi/spi-peripheral-props.yaml#
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    // Example for I2C
+    #include <dt-bindings/interrupt-controller/irq.h>
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        imu@68 {
+            compatible = "bosch,bmi323";
+            reg = <0x68>;
+            vddio-supply = <&vddio>;
+            vdd-supply = <&vdd>;
+            interrupt-parent = <&gpio1>;
+            interrupts = <29 IRQ_TYPE_EDGE_RISING>;
+            interrupt-names = "INT1";
+        };
+    };
diff --git a/Documentation/devicetree/bindings/iio/light/liteon,ltr390.yaml b/Documentation/devicetree/bindings/iio/light/liteon,ltr390.yaml
new file mode 100644
index 000000000000..5d98ef2af74d
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/light/liteon,ltr390.yaml
@@ -0,0 +1,56 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/light/liteon,ltr390.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Lite-On LTR390 ALS and UV Sensor
+
+description: |
+  The Lite-On LTR390 is an ALS (Ambient Light Sensor) and a UV sensor in a
+  single package with i2c address of 0x53.
+
+  Datasheet:
+    https://optoelectronics.liteon.com/upload/download/DS86-2015-0004/LTR-390UV_Final_%20DS_V1%201.pdf
+
+maintainers:
+  - Anshul Dalal <anshulusr@gmail.com>
+
+properties:
+  compatible:
+    enum:
+      - liteon,ltr390
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+    description: |
+      Level interrupt pin with open drain output.
+      The sensor pulls this pin low when the measured reading is greater than
+      some configured threshold.
+
+  vdd-supply: true
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        light-sensor@53 {
+            compatible = "liteon,ltr390";
+            reg = <0x53>;
+            interrupts = <18 IRQ_TYPE_EDGE_FALLING>;
+            vdd-supply = <&vdd_regulator>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/iio/light/vishay,veml6075.yaml b/Documentation/devicetree/bindings/iio/light/vishay,veml6075.yaml
new file mode 100644
index 000000000000..abee04cd126e
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/light/vishay,veml6075.yaml
@@ -0,0 +1,39 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/light/vishay,veml6075.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Vishay VEML6075 UVA and UVB sensor
+
+maintainers:
+  - Javier Carrasco <javier.carrasco.cruz@gmail.com>
+
+properties:
+  compatible:
+    const: vishay,veml6075
+
+  reg:
+    maxItems: 1
+
+  vdd-supply: true
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        uv-sensor@10 {
+            compatible = "vishay,veml6075";
+            reg = <0x10>;
+            vdd-supply = <&vdd_reg>;
+        };
+    };
+...
diff --git a/Documentation/devicetree/bindings/iio/pressure/honeywell,hsc030pa.yaml b/Documentation/devicetree/bindings/iio/pressure/honeywell,hsc030pa.yaml
new file mode 100644
index 000000000000..65a24ed67b3c
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/pressure/honeywell,hsc030pa.yaml
@@ -0,0 +1,142 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/pressure/honeywell,hsc030pa.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Honeywell TruStability HSC and SSC pressure sensor series
+
+description: |
+  support for Honeywell TruStability HSC and SSC digital pressure sensor
+  series.
+
+  These sensors have either an I2C, an SPI or an analog interface. Only the
+  digital versions are supported by this driver.
+
+  There are 118 models with different pressure ranges available in each family.
+  The vendor calls them "HSC series" and "SSC series". All of them have an
+  identical programming model but differ in pressure range, unit and transfer
+  function.
+
+  To support different models one needs to specify the pressure range as well
+  as the transfer function. Pressure range can either be provided via
+  pressure-triplet (directly extracted from the part number) or in case it's
+  a custom chip via numerical range limits converted to pascals.
+
+  The transfer function defines the ranges of raw conversion values delivered
+  by the sensor. pmin-pascal and pmax-pascal corespond to the minimum and
+  maximum pressure that can be measured.
+
+  Please note that in case of an SPI-based sensor, the clock signal should not
+  exceed 800kHz and the MOSI signal is not required.
+
+  Specifications about the devices can be found at:
+  https://prod-edam.honeywell.com/content/dam/honeywell-edam/sps/siot/en-us/products/sensors/pressure-sensors/board-mount-pressure-sensors/trustability-hsc-series/documents/sps-siot-trustability-hsc-series-high-accuracy-board-mount-pressure-sensors-50099148-a-en-ciid-151133.pdf
+  https://prod-edam.honeywell.com/content/dam/honeywell-edam/sps/siot/en-us/products/sensors/pressure-sensors/board-mount-pressure-sensors/trustability-ssc-series/documents/sps-siot-trustability-ssc-series-standard-accuracy-board-mount-pressure-sensors-50099533-a-en-ciid-151134.pdf
+
+maintainers:
+  - Petre Rodan <petre.rodan@subdimension.ro>
+
+properties:
+  compatible:
+    const: honeywell,hsc030pa
+
+  reg:
+    maxItems: 1
+
+  honeywell,transfer-function:
+    description: |
+      Transfer function which defines the range of valid values delivered by
+      the sensor.
+      0 - A, 10% to 90% of 2^14
+      1 - B, 5% to 95% of 2^14
+      2 - C, 5% to 85% of 2^14
+      3 - F, 4% to 94% of 2^14
+    enum: [0, 1, 2, 3]
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+  honeywell,pressure-triplet:
+    description: |
+      Case-sensitive five character string that defines pressure range, unit
+      and type as part of the device nomenclature. In the unlikely case of a
+      custom chip, set to "NA" and provide pmin-pascal and pmax-pascal.
+    enum: [001BA, 1.6BA, 2.5BA, 004BA, 006BA, 010BA, 1.6MD, 2.5MD, 004MD,
+           006MD, 010MD, 016MD, 025MD, 040MD, 060MD, 100MD, 160MD, 250MD,
+           400MD, 600MD, 001BD, 1.6BD, 2.5BD, 004BD, 2.5MG, 004MG, 006MG,
+           010MG, 016MG, 025MG, 040MG, 060MG, 100MG, 160MG, 250MG, 400MG,
+           600MG, 001BG, 1.6BG, 2.5BG, 004BG, 006BG, 010BG, 100KA, 160KA,
+           250KA, 400KA, 600KA, 001GA, 160LD, 250LD, 400LD, 600LD, 001KD,
+           1.6KD, 2.5KD, 004KD, 006KD, 010KD, 016KD, 025KD, 040KD, 060KD,
+           100KD, 160KD, 250KD, 400KD, 250LG, 400LG, 600LG, 001KG, 1.6KG,
+           2.5KG, 004KG, 006KG, 010KG, 016KG, 025KG, 040KG, 060KG, 100KG,
+           160KG, 250KG, 400KG, 600KG, 001GG, 015PA, 030PA, 060PA, 100PA,
+           150PA, 0.5ND, 001ND, 002ND, 004ND, 005ND, 010ND, 020ND, 030ND,
+           001PD, 005PD, 015PD, 030PD, 060PD, 001NG, 002NG, 004NG, 005NG,
+           010NG, 020NG, 030NG, 001PG, 005PG, 015PG, 030PG, 060PG, 100PG,
+           150PG, NA]
+    $ref: /schemas/types.yaml#/definitions/string
+
+  honeywell,pmin-pascal:
+    description: |
+      Minimum pressure value the sensor can measure in pascal.
+      To be specified only if honeywell,pressure-triplet is set to "NA".
+
+  honeywell,pmax-pascal:
+    description: |
+      Maximum pressure value the sensor can measure in pascal.
+      To be specified only if honeywell,pressure-triplet is set to "NA".
+
+  vdd-supply:
+    description:
+      Provide VDD power to the sensor (either 3.3V or 5V depending on the chip)
+
+  spi-max-frequency:
+    maximum: 800000
+
+required:
+  - compatible
+  - reg
+  - honeywell,transfer-function
+  - honeywell,pressure-triplet
+
+additionalProperties: false
+
+dependentSchemas:
+  honeywell,pmin-pascal:
+    properties:
+      honeywell,pressure-triplet:
+        const: NA
+  honeywell,pmax-pascal:
+    properties:
+      honeywell,pressure-triplet:
+        const: NA
+
+examples:
+  - |
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        pressure@28 {
+            compatible = "honeywell,hsc030pa";
+            reg = <0x28>;
+            honeywell,transfer-function = <0>;
+            honeywell,pressure-triplet = "030PA";
+        };
+    };
+  - |
+    spi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        pressure@0 {
+            compatible = "honeywell,hsc030pa";
+            reg = <0>;
+            spi-max-frequency = <800000>;
+            honeywell,transfer-function = <0>;
+            honeywell,pressure-triplet = "NA";
+            honeywell,pmin-pascal = <0>;
+            honeywell,pmax-pascal = <200000>;
+        };
+    };
+...
diff --git a/Documentation/devicetree/bindings/iio/pressure/honeywell,mprls0025pa.yaml b/Documentation/devicetree/bindings/iio/pressure/honeywell,mprls0025pa.yaml
index b31f8120f14e..d9e903fbfd99 100644
--- a/Documentation/devicetree/bindings/iio/pressure/honeywell,mprls0025pa.yaml
+++ b/Documentation/devicetree/bindings/iio/pressure/honeywell,mprls0025pa.yaml
@@ -53,12 +53,10 @@ properties:
   honeywell,pmin-pascal:
     description:
       Minimum pressure value the sensor can measure in pascal.
-    $ref: /schemas/types.yaml#/definitions/uint32
 
   honeywell,pmax-pascal:
     description:
       Maximum pressure value the sensor can measure in pascal.
-    $ref: /schemas/types.yaml#/definitions/uint32
 
   honeywell,transfer-function:
     description: |
diff --git a/Documentation/devicetree/bindings/iio/temperature/melexis,mlx90632.yaml b/Documentation/devicetree/bindings/iio/temperature/melexis,mlx90632.yaml
index 4a55e7f25ae7..03bb5d4fa8b5 100644
--- a/Documentation/devicetree/bindings/iio/temperature/melexis,mlx90632.yaml
+++ b/Documentation/devicetree/bindings/iio/temperature/melexis,mlx90632.yaml
@@ -4,7 +4,7 @@
 $id: http://devicetree.org/schemas/iio/temperature/melexis,mlx90632.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: Melexis MLX90632 contactless Infra Red temperature sensor
+title: Melexis MLX90632 and MLX90635 contactless Infra Red temperature sensor
 
 maintainers:
   - Crt Mori <cmo@melexis.com>
@@ -27,9 +27,24 @@ description: |
   Since measured object emissivity effects Infra Red energy emitted,
   emissivity should be set before requesting the object temperature.
 
+  https://www.melexis.com/en/documents/documentation/datasheets/datasheet-mlx90635
+
+  MLX90635 is most suitable for consumer applications where
+  measured object temperature is in range between -20 to 100 degrees
+  Celsius with relative error of measurement 2 degree Celsius in
+  object temperature range for industrial applications, while just 0.2
+  degree Celsius for human body measurement applications. Since it can
+  operate and measure ambient temperature in range of -20 to 85 degrees
+  Celsius it is suitable also for outdoor use.
+
+  Since measured object emissivity effects Infra Red energy emitted,
+  emissivity should be set before requesting the object temperature.
+
 properties:
   compatible:
-    const: melexis,mlx90632
+    enum:
+      - melexis,mlx90632
+      - melexis,mlx90635
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/iio/temperature/microchip,mcp9600.yaml b/Documentation/devicetree/bindings/iio/temperature/microchip,mcp9600.yaml
new file mode 100644
index 000000000000..d2cafa38a544
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/temperature/microchip,mcp9600.yaml
@@ -0,0 +1,70 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/temperature/microchip,mcp9600.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Microchip MCP9600 thermocouple EMF converter
+
+maintainers:
+  - Andrew Hepp <andrew.hepp@ahepp.dev>
+
+description:
+  https://ww1.microchip.com/downloads/en/DeviceDoc/MCP960X-Data-Sheet-20005426.pdf
+
+properties:
+  compatible:
+    const: microchip,mcp9600
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    minItems: 1
+    maxItems: 6
+
+  interrupt-names:
+    minItems: 1
+    maxItems: 6
+    items:
+      enum:
+        - open-circuit
+        - short-circuit
+        - alert1
+        - alert2
+        - alert3
+        - alert4
+
+  thermocouple-type:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      Type of thermocouple (THERMOCOUPLE_TYPE_K if omitted).
+      Use defines in dt-bindings/iio/temperature/thermocouple.h.
+      Supported types are B, E, J, K, N, R, S, T.
+
+  vdd-supply: true
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/iio/temperature/thermocouple.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        temperature-sensor@60 {
+            compatible = "microchip,mcp9600";
+            reg = <0x60>;
+            interrupt-parent = <&gpio>;
+            interrupts = <25 IRQ_TYPE_EDGE_RISING>;
+            interrupt-names = "open-circuit";
+            thermocouple-type = <THERMOCOUPLE_TYPE_K>;
+            vdd-supply = <&vdd>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/input/adafruit,seesaw-gamepad.yaml b/Documentation/devicetree/bindings/input/adafruit,seesaw-gamepad.yaml
new file mode 100644
index 000000000000..5e86f6de6978
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/adafruit,seesaw-gamepad.yaml
@@ -0,0 +1,63 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/input/adafruit,seesaw-gamepad.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Adafruit Mini I2C Gamepad with seesaw
+
+maintainers:
+  - Anshul Dalal <anshulusr@gmail.com>
+
+description: |
+  Adafruit Mini I2C Gamepad
+
+    +-----------------------------+
+    |   ___                       |
+    |  /   \               (X)    |
+    | |  S  |  __   __  (Y)   (A) |
+    |  \___/  |ST| |SE|    (B)    |
+    |                             |
+    +-----------------------------+
+
+  S -> 10-bit precision bidirectional analog joystick
+  ST -> Start
+  SE -> Select
+  X, A, B, Y -> Digital action buttons
+
+  Datasheet: https://cdn-learn.adafruit.com/downloads/pdf/gamepad-qt.pdf
+  Product page: https://www.adafruit.com/product/5743
+  Arduino Driver: https://github.com/adafruit/Adafruit_Seesaw
+
+properties:
+  compatible:
+    const: adafruit,seesaw-gamepad
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+    description:
+      The gamepad's IRQ pin triggers a rising edge if interrupts are enabled.
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        joystick@50 {
+            compatible = "adafruit,seesaw-gamepad";
+            interrupts = <18 IRQ_TYPE_EDGE_RISING>;
+            reg = <0x50>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/input/gpio-keys.yaml b/Documentation/devicetree/bindings/input/gpio-keys.yaml
index 159cd9d9fe57..cc78c2152921 100644
--- a/Documentation/devicetree/bindings/input/gpio-keys.yaml
+++ b/Documentation/devicetree/bindings/input/gpio-keys.yaml
@@ -31,7 +31,23 @@ patternProperties:
         maxItems: 1
 
       interrupts:
-        maxItems: 1
+        oneOf:
+          - items:
+              - description: Optional key interrupt or wakeup interrupt
+          - items:
+              - description: Key interrupt
+              - description: Wakeup interrupt
+
+      interrupt-names:
+        description:
+          Optional interrupt names, can be used to specify a separate dedicated
+          wake-up interrupt in addition to the gpio irq
+        oneOf:
+          - items:
+              - enum: [ irq, wakeup ]
+          - items:
+              - const: irq
+              - const: wakeup
 
       label:
         description: Descriptive name of the key.
@@ -97,6 +113,20 @@ patternProperties:
       - required:
           - gpios
 
+    allOf:
+      - if:
+          properties:
+            interrupts:
+              minItems: 2
+          required:
+            - interrupts
+        then:
+          properties:
+            interrupt-names:
+              minItems: 2
+          required:
+            - interrupt-names
+
     dependencies:
       wakeup-event-action: [ wakeup-source ]
       linux,input-value: [ gpios ]
@@ -137,6 +167,15 @@ examples:
             linux,code = <108>;
             interrupts = <1 IRQ_TYPE_EDGE_FALLING>;
         };
+
+        key-wakeup {
+            label = "GPIO Key WAKEUP";
+            linux,code = <143>;
+            interrupts-extended = <&intc 2 IRQ_TYPE_EDGE_FALLING>,
+                                  <&intc_wakeup 0 IRQ_TYPE_LEVEL_HIGH>;
+            interrupt-names = "irq", "wakeup";
+            wakeup-source;
+        };
     };
 
 ...
diff --git a/Documentation/devicetree/bindings/input/gpio-mouse.txt b/Documentation/devicetree/bindings/input/gpio-mouse.txt
deleted file mode 100644
index 519510a11af9..000000000000
--- a/Documentation/devicetree/bindings/input/gpio-mouse.txt
+++ /dev/null
@@ -1,32 +0,0 @@
-Device-Tree bindings for GPIO attached mice
-
-This simply uses standard GPIO handles to define a simple mouse connected
-to 5-7 GPIO lines.
-
-Required properties:
-	- compatible: must be "gpio-mouse"
-	- scan-interval-ms: The scanning interval in milliseconds
-	- up-gpios: GPIO line phandle to the line indicating "up"
-	- down-gpios: GPIO line phandle to the line indicating "down"
-	- left-gpios: GPIO line phandle to the line indicating "left"
-	- right-gpios: GPIO line phandle to the line indicating "right"
-
-Optional properties:
-	- button-left-gpios: GPIO line handle to the left mouse button
-	- button-middle-gpios: GPIO line handle to the middle mouse button
-	- button-right-gpios: GPIO line handle to the right mouse button
-Example:
-
-#include <dt-bindings/gpio/gpio.h>
-
-gpio-mouse {
-	compatible = "gpio-mouse";
-	scan-interval-ms = <50>;
-	up-gpios = <&gpio0 0 GPIO_ACTIVE_LOW>;
-	down-gpios = <&gpio0 1 GPIO_ACTIVE_LOW>;
-	left-gpios = <&gpio0 2 GPIO_ACTIVE_LOW>;
-	right-gpios = <&gpio0 3 GPIO_ACTIVE_LOW>;
-	button-left-gpios = <&gpio0 4 GPIO_ACTIVE_LOW>;
-	button-middle-gpios = <&gpio0 5 GPIO_ACTIVE_LOW>;
-	button-right-gpios = <&gpio0 6 GPIO_ACTIVE_LOW>;
-};
diff --git a/Documentation/devicetree/bindings/input/gpio-mouse.yaml b/Documentation/devicetree/bindings/input/gpio-mouse.yaml
new file mode 100644
index 000000000000..3928ec6aff1d
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/gpio-mouse.yaml
@@ -0,0 +1,68 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/input/gpio-mouse.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: GPIO attached mouse
+
+description: |
+  This simply uses standard GPIO handles to define a simple mouse connected
+  to 5-7 GPIO lines.
+
+maintainers:
+  - Anshul Dalal <anshulusr@gmail.com>
+
+properties:
+  compatible:
+    const: gpio-mouse
+
+  scan-interval-ms:
+    maxItems: 1
+
+  up-gpios:
+    maxItems: 1
+
+  down-gpios:
+    maxItems: 1
+
+  left-gpios:
+    maxItems: 1
+
+  right-gpios:
+    maxItems: 1
+
+  button-left-gpios:
+    maxItems: 1
+
+  button-middle-gpios:
+    maxItems: 1
+
+  button-right-gpios:
+    maxItems: 1
+
+required:
+  - compatible
+  - scan-interval-ms
+  - up-gpios
+  - down-gpios
+  - left-gpios
+  - right-gpios
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+
+    gpio-mouse {
+        compatible = "gpio-mouse";
+        scan-interval-ms = <50>;
+        up-gpios = <&gpio0 0 GPIO_ACTIVE_LOW>;
+        down-gpios = <&gpio0 1 GPIO_ACTIVE_LOW>;
+        left-gpios = <&gpio0 2 GPIO_ACTIVE_LOW>;
+        right-gpios = <&gpio0 3 GPIO_ACTIVE_LOW>;
+        button-left-gpios = <&gpio0 4 GPIO_ACTIVE_LOW>;
+        button-middle-gpios = <&gpio0 5 GPIO_ACTIVE_LOW>;
+        button-right-gpios = <&gpio0 6 GPIO_ACTIVE_LOW>;
+    };
diff --git a/Documentation/devicetree/bindings/input/iqs269a.yaml b/Documentation/devicetree/bindings/input/iqs269a.yaml
index 3c430d38594f..2c3f693b8982 100644
--- a/Documentation/devicetree/bindings/input/iqs269a.yaml
+++ b/Documentation/devicetree/bindings/input/iqs269a.yaml
@@ -9,6 +9,9 @@ title: Azoteq IQS269A Capacitive Touch Controller
 maintainers:
   - Jeff LaBundy <jeff@labundy.com>
 
+allOf:
+  - $ref: input.yaml#
+
 description: |
   The Azoteq IQS269A is an 8-channel capacitive touch controller that features
   additional Hall-effect and inductive sensing capabilities.
@@ -17,7 +20,10 @@ description: |
 
 properties:
   compatible:
-    const: azoteq,iqs269a
+    enum:
+      - azoteq,iqs269a
+      - azoteq,iqs269a-00
+      - azoteq,iqs269a-d0
 
   reg:
     maxItems: 1
@@ -204,6 +210,73 @@ properties:
     default: 1
     description: Specifies the slider coordinate filter strength.
 
+  azoteq,touch-hold-ms:
+    multipleOf: 256
+    minimum: 256
+    maximum: 65280
+    default: 5120
+    description:
+      Specifies the length of time (in ms) for which the channel selected by
+      'azoteq,gpio3-select' must be held in a state of touch in order for an
+      approximately 60-ms pulse to be asserted on the GPIO4 pin.
+
+  linux,keycodes:
+    minItems: 1
+    maxItems: 8
+    description: |
+      Specifies the numeric keycodes associated with each available gesture in
+      the following order (enter 0 for unused gestures):
+      0: Slider 0 tap
+      1: Slider 0 hold
+      2: Slider 0 positive flick or swipe
+      3: Slider 0 negative flick or swipe
+      4: Slider 1 tap
+      5: Slider 1 hold
+      6: Slider 1 positive flick or swipe
+      7: Slider 1 negative flick or swipe
+
+  azoteq,gesture-swipe:
+    type: boolean
+    description:
+      Directs the device to interpret axial gestures as a swipe (finger remains
+      on slider) instead of a flick (finger leaves slider).
+
+  azoteq,timeout-tap-ms:
+    multipleOf: 16
+    minimum: 0
+    maximum: 4080
+    default: 400
+    description:
+      Specifies the length of time (in ms) within which a slider touch must be
+      released in order to be interpreted as a tap. Default and maximum values
+      as well as step size are reduced by a factor of 4 with device version 2.
+
+  azoteq,timeout-swipe-ms:
+    multipleOf: 16
+    minimum: 0
+    maximum: 4080
+    default: 2000
+    description:
+      Specifies the length of time (in ms) within which an axial gesture must be
+      completed in order to be interpreted as a flick or swipe. Default and max-
+      imum values as well as step size are reduced by a factor of 4 with device
+      version 2.
+
+  azoteq,thresh-swipe:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    minimum: 0
+    maximum: 255
+    default: 128
+    description:
+      Specifies the number of points across which an axial gesture must travel
+      in order to be interpreted as a flick or swipe.
+
+dependencies:
+  azoteq,gesture-swipe: ["linux,keycodes"]
+  azoteq,timeout-tap-ms: ["linux,keycodes"]
+  azoteq,timeout-swipe-ms: ["linux,keycodes"]
+  azoteq,thresh-swipe: ["linux,keycodes"]
+
 patternProperties:
   "^channel@[0-7]$":
     type: object
@@ -454,6 +527,21 @@ patternProperties:
 
     additionalProperties: false
 
+if:
+  properties:
+    compatible:
+      contains:
+        enum:
+          - azoteq,iqs269a-d0
+then:
+  patternProperties:
+    "^channel@[0-7]$":
+      properties:
+        azoteq,slider1-select: false
+else:
+  properties:
+    azoteq,touch-hold-ms: false
+
 required:
   - compatible
   - reg
@@ -484,6 +572,14 @@ examples:
                     azoteq,hall-enable;
                     azoteq,suspend-mode = <2>;
 
+                    linux,keycodes = <KEY_PLAYPAUSE>,
+                                     <KEY_STOPCD>,
+                                     <KEY_NEXTSONG>,
+                                     <KEY_PREVIOUSSONG>;
+
+                    azoteq,timeout-tap-ms = <400>;
+                    azoteq,timeout-swipe-ms = <800>;
+
                     channel@0 {
                             reg = <0x0>;
 
diff --git a/Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml b/Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml
index e34c9e78d38d..70567d92c746 100644
--- a/Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml
+++ b/Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml
@@ -90,26 +90,4 @@ required:
 
 unevaluatedProperties: false
 
-examples:
-  - |
-    #include <dt-bindings/input/input.h>
-    #include <dt-bindings/interrupt-controller/arm-gic.h>
-
-    pmic {
-        compatible = "mediatek,mt6397";
-
-        keys {
-          compatible = "mediatek,mt6397-keys";
-          mediatek,long-press-mode = <1>;
-          power-off-time-sec = <0>;
-
-          key-power {
-            linux,keycodes = <KEY_POWER>;
-            wakeup-source;
-          };
-
-          key-home {
-            linux,keycodes = <KEY_VOLUMEDOWN>;
-          };
-        };
-    };
+...
diff --git a/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml b/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml
index 5b5d4f7d3482..7ade03f1b32b 100644
--- a/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml
+++ b/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml
@@ -45,13 +45,13 @@ properties:
       Enables the Linux input system's autorepeat feature on the input device.
 
   linux,keycodes:
-    minItems: 6
-    maxItems: 6
+    minItems: 3
+    maxItems: 8
     description: |
       Specifies an array of numeric keycode values to
       be used for the channels. If this property is
       omitted, KEY_A, KEY_B, etc are used as defaults.
-      The array must have exactly six entries.
+      The number of entries must correspond to the number of channels.
 
   microchip,sensor-gain:
     $ref: /schemas/types.yaml#/definitions/uint32
@@ -70,6 +70,59 @@ properties:
       open drain. This property allows using the active
       high push-pull output.
 
+  microchip,sensitivity-delta-sense:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    default: 32
+    enum: [1, 2, 4, 8, 16, 32, 64, 128]
+    description:
+      Controls the sensitivity multiplier of a touch detection.
+      Higher value means more sensitive settings.
+      At the more sensitive settings, touches are detected for a smaller delta
+      capacitance corresponding to a "lighter" touch.
+
+  microchip,signal-guard:
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+    minItems: 3
+    maxItems: 8
+    items:
+      enum: [0, 1]
+    description: |
+      0 - off
+      1 - on
+      The signal guard isolates the signal from virtual grounds.
+      If enabled then the behavior of the channel is changed to signal guard.
+      The number of entries must correspond to the number of channels.
+
+  microchip,input-threshold:
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+    minItems: 3
+    maxItems: 8
+    items:
+      minimum: 0
+      maximum: 127
+    description:
+      Specifies the delta threshold that is used to determine if a touch has
+      been detected. A higher value means a larger difference in capacitance
+      is required for a touch to be registered, making the touch sensor less
+      sensitive.
+      The number of entries must correspond to the number of channels.
+
+  microchip,calib-sensitivity:
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+    minItems: 3
+    maxItems: 8
+    items:
+      enum: [1, 2, 4]
+    description: |
+      Specifies an array of numeric values that controls the gain
+      used by the calibration routine to enable sensor inputs
+      to be more sensitive for proximity detection.
+      Gain is based on touch pad capacitance range
+      1 - 5-50pF
+      2 - 0-25pF
+      4 - 0-12.5pF
+      The number of entries must correspond to the number of channels.
+
 patternProperties:
   "^led@[0-7]$":
     type: object
@@ -99,10 +152,29 @@ allOf:
           contains:
             enum:
               - microchip,cap1106
+              - microchip,cap1203
+              - microchip,cap1206
+              - microchip,cap1293
+              - microchip,cap1298
     then:
       patternProperties:
         "^led@[0-7]$": false
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - microchip,cap1106
+              - microchip,cap1126
+              - microchip,cap1188
+              - microchip,cap1203
+              - microchip,cap1206
+    then:
+      properties:
+        microchip,signal-guard: false
+        microchip,calib-sensitivity: false
+
 required:
   - compatible
   - interrupts
@@ -122,6 +194,8 @@ examples:
         reg = <0x28>;
         autorepeat;
         microchip,sensor-gain = <2>;
+        microchip,sensitivity-delta-sense = <16>;
+        microchip,input-threshold = <21>, <18>, <46>, <46>, <46>, <21>;
 
         linux,keycodes = <103>,	/* KEY_UP */
                          <106>,	/* KEY_RIGHT */
diff --git a/Documentation/devicetree/bindings/input/sprd,sc27xx-vibrator.yaml b/Documentation/devicetree/bindings/input/sprd,sc27xx-vibrator.yaml
index a401a0bfcbec..4c8d303ff93c 100644
--- a/Documentation/devicetree/bindings/input/sprd,sc27xx-vibrator.yaml
+++ b/Documentation/devicetree/bindings/input/sprd,sc27xx-vibrator.yaml
@@ -28,21 +28,4 @@ required:
 
 additionalProperties: false
 
-examples:
-  - |
-    #include <dt-bindings/interrupt-controller/arm-gic.h>
-    sc2731_pmic: pmic@0 {
-      compatible = "sprd,sc2731";
-      reg = <0 0>;
-      spi-max-frequency = <26000000>;
-      interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
-      interrupt-controller;
-      #interrupt-cells = <2>;
-      #address-cells = <1>;
-      #size-cells = <0>;
-
-      vibrator@eb4 {
-        compatible = "sprd,sc2731-vibrator";
-        reg = <0xeb4>;
-      };
-    };
+...
diff --git a/Documentation/devicetree/bindings/input/ti,drv2665.txt b/Documentation/devicetree/bindings/input/ti,drv2665.txt
deleted file mode 100644
index 1ba97ac04305..000000000000
--- a/Documentation/devicetree/bindings/input/ti,drv2665.txt
+++ /dev/null
@@ -1,17 +0,0 @@
-* Texas Instruments - drv2665 Haptics driver
-
-Required properties:
-	- compatible - "ti,drv2665" - DRV2665
-	- reg -  I2C slave address
-	- vbat-supply - Required supply regulator
-
-Example:
-
-haptics: haptics@59 {
-	compatible = "ti,drv2665";
-	reg = <0x59>;
-	vbat-supply = <&vbat>;
-};
-
-For more product information please see the link below:
-http://www.ti.com/product/drv2665
diff --git a/Documentation/devicetree/bindings/input/ti,drv2667.txt b/Documentation/devicetree/bindings/input/ti,drv2667.txt
deleted file mode 100644
index 996382cf994a..000000000000
--- a/Documentation/devicetree/bindings/input/ti,drv2667.txt
+++ /dev/null
@@ -1,17 +0,0 @@
-* Texas Instruments - drv2667 Haptics driver
-
-Required properties:
-	- compatible - "ti,drv2667" - DRV2667
-	- reg -  I2C slave address
-	- vbat-supply - Required supply regulator
-
-Example:
-
-haptics: haptics@59 {
-	compatible = "ti,drv2667";
-	reg = <0x59>;
-	vbat-supply = <&vbat>;
-};
-
-For more product information please see the link below:
-http://www.ti.com/product/drv2667
diff --git a/Documentation/devicetree/bindings/input/ti,drv266x.yaml b/Documentation/devicetree/bindings/input/ti,drv266x.yaml
new file mode 100644
index 000000000000..da1818824373
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/ti,drv266x.yaml
@@ -0,0 +1,50 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/input/ti,drv266x.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Texas Instruments - drv266x Haptics driver
+
+description: |
+  Product Page:
+    http://www.ti.com/product/drv2665
+    http://www.ti.com/product/drv2667
+
+maintainers:
+  - Anshul Dalal <anshulusr@gmail.com>
+
+properties:
+  compatible:
+    enum:
+      - ti,drv2665
+      - ti,drv2667
+
+  reg:
+    maxItems: 1
+
+  vbat-supply:
+    description: Required supply regulator
+
+required:
+  - compatible
+  - reg
+  - vbat-supply
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        haptics@59 {
+            compatible = "ti,drv2667";
+            reg = <0x59>;
+            vbat-supply = <&vbat>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/input/touchscreen/neonode,zforce.yaml b/Documentation/devicetree/bindings/input/touchscreen/neonode,zforce.yaml
new file mode 100644
index 000000000000..c2ee89b76ea1
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/touchscreen/neonode,zforce.yaml
@@ -0,0 +1,72 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/input/touchscreen/neonode,zforce.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Neonode infrared touchscreen controller
+
+maintainers:
+  - Heiko Stuebner <heiko@sntech.de>
+
+allOf:
+  - $ref: touchscreen.yaml#
+
+properties:
+  compatible:
+    const: neonode,zforce
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  reset-gpios:
+    maxItems: 1
+
+  irq-gpios:
+    maxItems: 1
+
+  x-size:
+    deprecated: true
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+  y-size:
+    deprecated: true
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+  vdd-supply: true
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - reset-gpios
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        touchscreen@50 {
+            compatible = "neonode,zforce";
+            reg = <0x50>;
+            interrupts = <2 0>;
+            vdd-supply = <&reg_zforce_vdd>;
+
+            reset-gpios = <&gpio5 9 0>; /* RST */
+            irq-gpios = <&gpio5 6 0>; /* IRQ, optional */
+
+            touchscreen-min-x = <0>;
+            touchscreen-size-x = <800>;
+            touchscreen-min-y = <0>;
+            touchscreen-size-y = <600>;
+        };
+    };
+...
diff --git a/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.txt b/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.txt
deleted file mode 100644
index 6805d10d226d..000000000000
--- a/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.txt
+++ /dev/null
@@ -1,32 +0,0 @@
-* Samsung S6SY761 touchscreen controller
-
-Required properties:
-- compatible		: must be "samsung,s6sy761"
-- reg			: I2C slave address, (e.g. 0x48)
-- interrupts		: interrupt specification
-- avdd-supply		: analogic power supply
-- vdd-supply		: power supply
-
-Optional properties:
-- touchscreen-size-x	: see touchscreen.txt. This property is embedded in the
-			  device. If defined it forces a different x resolution.
-- touchscreen-size-y	: see touchscreen.txt. This property is embedded in the
-			  device. If defined it forces a different y resolution.
-
-Example:
-
-i2c@00000000 {
-
-	/* ... */
-
-	touchscreen@48 {
-		compatible = "samsung,s6sy761";
-		reg = <0x48>;
-		interrupt-parent = <&gpa1>;
-		interrupts = <1 IRQ_TYPE_NONE>;
-		avdd-supply = <&ldo30_reg>;
-		vdd-supply = <&ldo31_reg>;
-		touchscreen-size-x = <4096>;
-		touchscreen-size-y = <4096>;
-	};
-};
diff --git a/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.yaml b/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.yaml
new file mode 100644
index 000000000000..1ffd17af3c53
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.yaml
@@ -0,0 +1,54 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/input/touchscreen/samsung,s6sy761.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Samsung S6SY761 touchscreen controller
+
+maintainers:
+  - Andi Shyti <andi.shyti@kernel.org>
+
+allOf:
+  - $ref: touchscreen.yaml#
+
+properties:
+  compatible:
+    const: samsung,s6sy761
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  avdd-supply: true
+  vdd-supply: true
+
+unevaluatedProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - avdd-supply
+  - vdd-supply
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        touchscreen@48 {
+            compatible = "samsung,s6sy761";
+            reg = <0x48>;
+            interrupt-parent = <&gpa1>;
+            interrupts = <1 IRQ_TYPE_LEVEL_HIGH>;
+            avdd-supply = <&ldo30_reg>;
+            vdd-supply = <&ldo31_reg>;
+            touchscreen-size-x = <4096>;
+            touchscreen-size-y = <4096>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/input/touchscreen/zforce_ts.txt b/Documentation/devicetree/bindings/input/touchscreen/zforce_ts.txt
deleted file mode 100644
index e3c27c4fd9c8..000000000000
--- a/Documentation/devicetree/bindings/input/touchscreen/zforce_ts.txt
+++ /dev/null
@@ -1,34 +0,0 @@
-* Neonode infrared touchscreen controller
-
-Required properties:
-- compatible: must be "neonode,zforce"
-- reg: I2C address of the chip
-- interrupts: interrupt to which the chip is connected
-- reset-gpios: reset gpio the chip is connected to
-- x-size: horizontal resolution of touchscreen
-- y-size: vertical resolution of touchscreen
-
-Optional properties:
-- irq-gpios : interrupt gpio the chip is connected to
-- vdd-supply: Regulator controlling the controller supply
-
-Example:
-
-	i2c@00000000 {
-		/* ... */
-
-		zforce_ts@50 {
-			compatible = "neonode,zforce";
-			reg = <0x50>;
-			interrupts = <2 0>;
-			vdd-supply = <&reg_zforce_vdd>;
-
-			reset-gpios = <&gpio5 9 0>; /* RST */
-			irq-gpios = <&gpio5 6 0>; /* IRQ, optional */
-
-			x-size = <800>;
-			y-size = <600>;
-		};
-
-		/* ... */
-	};
diff --git a/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml b/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml
index 73f809cdb783..05067e197abe 100644
--- a/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml
+++ b/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml
@@ -25,13 +25,16 @@ properties:
       - const: qcom,msm8998-bwmon       # BWMON v4
       - items:
           - enum:
+              - qcom,qcm2290-cpu-bwmon
               - qcom,sc7180-cpu-bwmon
               - qcom,sc7280-cpu-bwmon
               - qcom,sc8280xp-cpu-bwmon
               - qcom,sdm845-cpu-bwmon
+              - qcom,sm6115-cpu-bwmon
               - qcom,sm6350-llcc-bwmon
               - qcom,sm8250-cpu-bwmon
               - qcom,sm8550-cpu-bwmon
+              - qcom,sm8650-cpu-bwmon
           - const: qcom,sdm845-bwmon    # BWMON v4, unified register space
       - items:
           - enum:
@@ -40,6 +43,7 @@ properties:
               - qcom,sm6350-cpu-bwmon
               - qcom,sm8250-llcc-bwmon
               - qcom,sm8550-llcc-bwmon
+              - qcom,sm8650-llcc-bwmon
           - const: qcom,sc7280-llcc-bwmon
       - const: qcom,sc7280-llcc-bwmon   # BWMON v5
       - const: qcom,sdm845-llcc-bwmon   # BWMON v5
diff --git a/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml b/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
index 00b570c82903..60441f0c5d72 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
@@ -11,8 +11,13 @@ maintainers:
 
 description: |
   This interrupt controller is found in the Loongson-3 family of chips and
-  Loongson-2K1000 chip, as the primary package interrupt controller which
+  Loongson-2K series chips, as the primary package interrupt controller which
   can route local I/O interrupt to interrupt lines of cores.
+  Be aware of the following points.
+  1.The Loongson-2K0500 is a single core CPU;
+  2.The Loongson-2K0500/2K1000 has 64 device interrupt sources as inputs, so we
+    need to define two nodes in dts{i} to describe the "0-31" and "32-61" interrupt
+    sources respectively.
 
 allOf:
   - $ref: /schemas/interrupt-controller.yaml#
@@ -33,6 +38,7 @@ properties:
       - const: main
       - const: isr0
       - const: isr1
+    minItems: 2
 
   interrupt-controller: true
 
@@ -45,11 +51,9 @@ properties:
   interrupt-names:
     description: List of names for the parent interrupts.
     items:
-      - const: int0
-      - const: int1
-      - const: int2
-      - const: int3
+      pattern: int[0-3]
     minItems: 1
+    maxItems: 4
 
   '#interrupt-cells':
     const: 2
@@ -69,6 +73,7 @@ required:
   - compatible
   - reg
   - interrupts
+  - interrupt-names
   - interrupt-controller
   - '#interrupt-cells'
   - loongson,parent_int_map
@@ -86,7 +91,8 @@ if:
 then:
   properties:
     reg:
-      minItems: 3
+      minItems: 2
+      maxItems: 3
 
   required:
     - reg-names
diff --git a/Documentation/devicetree/bindings/iommu/apple,dart.yaml b/Documentation/devicetree/bindings/iommu/apple,dart.yaml
index 903edf85d72e..7adb1de455a5 100644
--- a/Documentation/devicetree/bindings/iommu/apple,dart.yaml
+++ b/Documentation/devicetree/bindings/iommu/apple,dart.yaml
@@ -24,6 +24,7 @@ properties:
   compatible:
     enum:
       - apple,t8103-dart
+      - apple,t8103-usb4-dart
       - apple,t8110-dart
       - apple,t6000-dart
 
diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
index aa9e1c0895a5..a4042ae24770 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
@@ -56,6 +56,8 @@ properties:
               - qcom,sm8350-smmu-500
               - qcom,sm8450-smmu-500
               - qcom,sm8550-smmu-500
+              - qcom,sm8650-smmu-500
+              - qcom,x1e80100-smmu-500
           - const: qcom,smmu-500
           - const: arm,mmu-500
 
@@ -89,6 +91,8 @@ properties:
               - qcom,sm8150-smmu-500
               - qcom,sm8250-smmu-500
               - qcom,sm8350-smmu-500
+              - qcom,sm8450-smmu-500
+              - qcom,sm8550-smmu-500
           - const: qcom,adreno-smmu
           - const: qcom,smmu-500
           - const: arm,mmu-500
@@ -434,6 +438,30 @@ allOf:
         compatible:
           items:
             - enum:
+                - qcom,sm8350-smmu-500
+            - const: qcom,adreno-smmu
+            - const: qcom,smmu-500
+            - const: arm,mmu-500
+    then:
+      properties:
+        clock-names:
+          items:
+            - const: bus
+            - const: iface
+            - const: ahb
+            - const: hlos1_vote_gpu_smmu
+            - const: cx_gmu
+            - const: hub_cx_int
+            - const: hub_aon
+        clocks:
+          minItems: 7
+          maxItems: 7
+
+  - if:
+      properties:
+        compatible:
+          items:
+            - enum:
                 - qcom,sm6115-smmu-500
                 - qcom,sm6125-smmu-500
             - const: qcom,adreno-smmu
@@ -453,6 +481,50 @@ allOf:
             - description: Voter clock required for HLOS SMMU access
             - description: Interface clock required for register access
 
+  - if:
+      properties:
+        compatible:
+          const: qcom,sm8450-smmu-500
+    then:
+      properties:
+        clock-names:
+          items:
+            - const: gmu
+            - const: hub
+            - const: hlos
+            - const: bus
+            - const: iface
+            - const: ahb
+
+        clocks:
+          items:
+            - description: GMU clock
+            - description: GPU HUB clock
+            - description: HLOS vote clock
+            - description: GPU memory bus clock
+            - description: GPU SNoC bus clock
+            - description: GPU AHB clock
+
+  - if:
+      properties:
+        compatible:
+          const: qcom,sm8550-smmu-500
+    then:
+      properties:
+        clock-names:
+          items:
+            - const: hlos
+            - const: bus
+            - const: iface
+            - const: ahb
+
+        clocks:
+          items:
+            - description: HLOS vote clock
+            - description: GPU memory bus clock
+            - description: GPU SNoC bus clock
+            - description: GPU AHB clock
+
   # Disallow clocks for all other platforms with specific compatibles
   - if:
       properties:
@@ -472,9 +544,8 @@ allOf:
               - qcom,sdx65-smmu-500
               - qcom,sm6350-smmu-500
               - qcom,sm6375-smmu-500
-              - qcom,sm8350-smmu-500
-              - qcom,sm8450-smmu-500
-              - qcom,sm8550-smmu-500
+              - qcom,sm8650-smmu-500
+              - qcom,x1e80100-smmu-500
     then:
       properties:
         clock-names: false
diff --git a/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml b/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml
index ba9124f721f1..621dde0e45d8 100644
--- a/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml
+++ b/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml
@@ -19,9 +19,14 @@ description: |+
 
 properties:
   compatible:
-    enum:
-      - rockchip,iommu
-      - rockchip,rk3568-iommu
+    oneOf:
+      - enum:
+          - rockchip,iommu
+          - rockchip,rk3568-iommu
+      - items:
+          - enum:
+              - rockchip,rk3588-iommu
+          - const: rockchip,rk3568-iommu
 
   reg:
     items:
diff --git a/Documentation/devicetree/bindings/leds/allwinner,sun50i-a100-ledc.yaml b/Documentation/devicetree/bindings/leds/allwinner,sun50i-a100-ledc.yaml
new file mode 100644
index 000000000000..760cb336dccb
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/allwinner,sun50i-a100-ledc.yaml
@@ -0,0 +1,137 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/leds/allwinner,sun50i-a100-ledc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A100 LED Controller
+
+maintainers:
+  - Samuel Holland <samuel@sholland.org>
+
+description:
+  The LED controller found in Allwinner sunxi SoCs uses a one-wire serial
+  interface to drive up to 1024 RGB LEDs.
+
+properties:
+  compatible:
+    oneOf:
+      - const: allwinner,sun50i-a100-ledc
+      - items:
+          - enum:
+              - allwinner,sun20i-d1-ledc
+              - allwinner,sun50i-r329-ledc
+          - const: allwinner,sun50i-a100-ledc
+
+  reg:
+    maxItems: 1
+
+  "#address-cells":
+    const: 1
+
+  "#size-cells":
+    const: 0
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: Bus clock
+      - description: Module clock
+
+  clock-names:
+    items:
+      - const: bus
+      - const: mod
+
+  resets:
+    maxItems: 1
+
+  dmas:
+    maxItems: 1
+    description: TX DMA channel
+
+  dma-names:
+    const: tx
+
+  allwinner,pixel-format:
+    description: Pixel format (subpixel transmission order), default is "grb"
+    enum:
+      - bgr
+      - brg
+      - gbr
+      - grb
+      - rbg
+      - rgb
+
+  allwinner,t0h-ns:
+    default: 336
+    description: Length of high pulse when transmitting a "0" bit
+
+  allwinner,t0l-ns:
+    default: 840
+    description: Length of low pulse when transmitting a "0" bit
+
+  allwinner,t1h-ns:
+    default: 882
+    description: Length of high pulse when transmitting a "1" bit
+
+  allwinner,t1l-ns:
+    default: 294
+    description: Length of low pulse when transmitting a "1" bit
+
+  allwinner,treset-ns:
+    default: 300000
+    description: Minimum delay between transmission frames
+
+patternProperties:
+  "^multi-led@[0-9a-f]+$":
+    type: object
+    $ref: leds-class-multicolor.yaml#
+    unevaluatedProperties: false
+    properties:
+      reg:
+        minimum: 0
+        maximum: 1023
+        description: Index of the LED in the series (must be contiguous)
+
+    required:
+      - reg
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - resets
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/leds/common.h>
+
+    ledc: led-controller@2008000 {
+      compatible = "allwinner,sun20i-d1-ledc",
+                   "allwinner,sun50i-a100-ledc";
+      reg = <0x2008000 0x400>;
+      interrupts = <36 IRQ_TYPE_LEVEL_HIGH>;
+      clocks = <&ccu 12>, <&ccu 34>;
+      clock-names = "bus", "mod";
+      resets = <&ccu 12>;
+      dmas = <&dma 42>;
+      dma-names = "tx";
+      #address-cells = <1>;
+      #size-cells = <0>;
+
+      multi-led@0 {
+        reg = <0x0>;
+        color = <LED_COLOR_ID_RGB>;
+        function = LED_FUNCTION_INDICATOR;
+      };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml b/Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml
index feb5febaf361..54d6d1f08e24 100644
--- a/Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml
+++ b/Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml
@@ -10,15 +10,19 @@ maintainers:
   - Martin Kurbanov <mmkurbanov@sberdevices.ru>
 
 description: |
-  This controller is present on AW20036/AW20054/AW20072.
-  It is a 3x12/6x9/6x12 matrix LED programmed via
-  an I2C interface, up to 36/54/72 LEDs or 12/18/24 RGBs,
-  3 pattern controllers for auto breathing or group dimming control.
+  It is a matrix LED driver programmed via an I2C interface. Devices have
+  a set of individually controlled leds and support 3 pattern controllers
+  for auto breathing or group dimming control. Supported devices:
+    - AW20036 (3x12) 36 LEDs
+    - AW20054 (6x9)  54 LEDs
+    - AW20072 (6x12) 72 LEDs
+    - AW20108 (9x12) 108 LEDs
 
   For more product information please see the link below:
   aw20036 - https://www.awinic.com/en/productDetail/AW20036QNR#tech-docs
   aw20054 - https://www.awinic.com/en/productDetail/AW20054QNR#tech-docs
   aw20072 - https://www.awinic.com/en/productDetail/AW20072QNR#tech-docs
+  aw20108 - https://www.awinic.com/en/productDetail/AW20108QNR#tech-docs
 
 properties:
   compatible:
@@ -26,6 +30,7 @@ properties:
       - awinic,aw20036
       - awinic,aw20054
       - awinic,aw20072
+      - awinic,aw20108
 
   reg:
     maxItems: 1
@@ -36,13 +41,11 @@ properties:
   "#size-cells":
     const: 0
 
-  awinic,display-rows:
-    $ref: /schemas/types.yaml#/definitions/uint32
-    description:
-      Leds matrix size
+  enable-gpios:
+    maxItems: 1
 
 patternProperties:
-  "^led@[0-9a-f]$":
+  "^led@[0-9a-f]+$":
     type: object
     $ref: common.yaml#
     unevaluatedProperties: false
@@ -60,16 +63,11 @@ patternProperties:
           since the chip has a single global setting.
           The maximum output current of each LED is calculated by the
           following formula:
-            IMAXled = 160000 * (592 / 600.5) * (1 / display-rows)
+            IMAXled = 160000 * (592 / 600.5) * (1 / max-current-switch-number)
           And the minimum output current formula:
-            IMINled = 3300 * (592 / 600.5) * (1 / display-rows)
-
-required:
-  - compatible
-  - reg
-  - "#address-cells"
-  - "#size-cells"
-  - awinic,display-rows
+            IMINled = 3300 * (592 / 600.5) * (1 / max-current-switch-number)
+          where max-current-switch-number is determinated by led configuration
+          and depends on how leds are physically connected to the led driver.
 
 allOf:
   - if:
@@ -78,18 +76,67 @@ allOf:
           contains:
             const: awinic,aw20036
     then:
+      patternProperties:
+        "^led@[0-9a-f]+$":
+          properties:
+            reg:
+              items:
+                minimum: 0
+                maximum: 36
+
+  - if:
       properties:
-        awinic,display-rows:
-          enum: [1, 2, 3]
-    else:
+        compatible:
+          contains:
+            const: awinic,aw20054
+    then:
+      patternProperties:
+        "^led@[0-9a-f]+$":
+          properties:
+            reg:
+              items:
+                minimum: 0
+                maximum: 54
+
+  - if:
       properties:
-        awinic,display-rows:
-          enum: [1, 2, 3, 4, 5, 6, 7]
+        compatible:
+          contains:
+            const: awinic,aw20072
+    then:
+      patternProperties:
+        "^led@[0-9a-f]+$":
+          properties:
+            reg:
+              items:
+                minimum: 0
+                maximum: 72
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: awinic,aw20108
+    then:
+      patternProperties:
+        "^led@[0-9a-f]+$":
+          properties:
+            reg:
+              items:
+                minimum: 0
+                maximum: 108
+
+required:
+  - compatible
+  - reg
+  - "#address-cells"
+  - "#size-cells"
 
 additionalProperties: false
 
 examples:
   - |
+    #include <dt-bindings/gpio/gpio.h>
     #include <dt-bindings/leds/common.h>
 
     i2c {
@@ -101,7 +148,7 @@ examples:
             reg = <0x3a>;
             #address-cells = <1>;
             #size-cells = <0>;
-            awinic,display-rows = <3>;
+            enable-gpios = <&gpio 3 GPIO_ACTIVE_HIGH>;
 
             led@0 {
                 reg = <0x0>;
diff --git a/Documentation/devicetree/bindings/leds/backlight/mps,mp3309c.yaml b/Documentation/devicetree/bindings/leds/backlight/mps,mp3309c.yaml
index 4191e33626f5..527a37368ed7 100644
--- a/Documentation/devicetree/bindings/leds/backlight/mps,mp3309c.yaml
+++ b/Documentation/devicetree/bindings/leds/backlight/mps,mp3309c.yaml
@@ -14,8 +14,8 @@ description: |
   programmable switching frequency to optimize efficiency.
   It supports two different dimming modes:
 
-  - analog mode, via I2C commands (default)
-  - PWM controlled mode.
+  - analog mode, via I2C commands, as default mode (32 dimming levels)
+  - PWM controlled mode (optional)
 
   The datasheet is available at:
   https://www.monolithicpower.com/en/mp3309c.html
@@ -50,8 +50,6 @@ properties:
 required:
   - compatible
   - reg
-  - max-brightness
-  - default-brightness
 
 unevaluatedProperties: false
 
@@ -66,8 +64,8 @@ examples:
             compatible = "mps,mp3309c";
             reg = <0x17>;
             pwms = <&pwm1 0 3333333 0>; /* 300 Hz --> (1/f) * 1*10^9 */
-            max-brightness = <100>;
-            default-brightness = <80>;
+            brightness-levels = <0 4 8 16 32 64 128 255>;
+            default-brightness = <6>;
             mps,overvoltage-protection-microvolt = <24000000>;
         };
     };
diff --git a/Documentation/devicetree/bindings/leds/common.yaml b/Documentation/devicetree/bindings/leds/common.yaml
index c8d0ba5f2327..55a8d1385e21 100644
--- a/Documentation/devicetree/bindings/leds/common.yaml
+++ b/Documentation/devicetree/bindings/leds/common.yaml
@@ -167,7 +167,7 @@ properties:
       Note that this flag is mainly used for PWM-LEDs, where it is not possible
       to map brightness to current. Drivers for other controllers should use
       led-max-microamp.
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
 
   panic-indicator:
     description:
diff --git a/Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml b/Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml
index a8736fd5a539..1ba607685f5f 100644
--- a/Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml
+++ b/Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml
@@ -89,9 +89,11 @@ additionalProperties: false
 examples:
   - |
     #include <dt-bindings/leds/common.h>
-    spmi {
+
+    pmic {
         #address-cells = <1>;
         #size-cells = <0>;
+
         led-controller@ee00 {
             compatible = "qcom,pm8350c-flash-led", "qcom,spmi-flash-led";
             reg = <0xee00>;
diff --git a/Documentation/devicetree/bindings/loongarch/cpus.yaml b/Documentation/devicetree/bindings/loongarch/cpus.yaml
new file mode 100644
index 000000000000..f175872995e1
--- /dev/null
+++ b/Documentation/devicetree/bindings/loongarch/cpus.yaml
@@ -0,0 +1,61 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/loongarch/cpus.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: LoongArch CPUs
+
+maintainers:
+  - Binbin Zhou <zhoubinbin@loongson.cn>
+
+description:
+  This document describes the list of LoongArch CPU cores that support FDT,
+  it describe the layout of CPUs in a system through the "cpus" node.
+
+allOf:
+  - $ref: /schemas/cpu.yaml#
+
+properties:
+  compatible:
+    enum:
+      - loongson,la264
+      - loongson,la364
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/loongson,ls2k-clk.h>
+
+    cpus {
+        #size-cells = <0>;
+        #address-cells = <1>;
+
+        cpu@0 {
+            compatible = "loongson,la264";
+            device_type = "cpu";
+            reg = <0>;
+            clocks = <&clk LOONGSON2_NODE_CLK>;
+        };
+
+        cpu@1 {
+            compatible = "loongson,la264";
+            device_type = "cpu";
+            reg = <1>;
+            clocks = <&clk LOONGSON2_NODE_CLK>;
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/loongarch/loongson.yaml b/Documentation/devicetree/bindings/loongarch/loongson.yaml
new file mode 100644
index 000000000000..e1a4a97b7576
--- /dev/null
+++ b/Documentation/devicetree/bindings/loongarch/loongson.yaml
@@ -0,0 +1,34 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/loongarch/loongson.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Loongson SoC-based boards
+
+maintainers:
+  - Binbin Zhou <zhoubinbin@loongson.cn>
+
+properties:
+  $nodename:
+    const: '/'
+  compatible:
+    oneOf:
+      - description: Loongson-2K0500 processor based boards
+        items:
+          - const: loongson,ls2k0500-ref
+          - const: loongson,ls2k0500
+
+      - description: Loongson-2K1000 processor based boards
+        items:
+          - const: loongson,ls2k1000-ref
+          - const: loongson,ls2k1000
+
+      - description: Loongson-2K2000 processor based boards
+        items:
+          - const: loongson,ls2k2000-ref
+          - const: loongson,ls2k2000
+
+additionalProperties: true
+
+...
diff --git a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml
index a38413f8d132..79eb523b8436 100644
--- a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml
+++ b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml
@@ -25,6 +25,24 @@ properties:
           - const: qcom,ipq6018-apcs-apps-global
       - items:
           - enum:
+              - qcom,qcs404-apcs-apps-global
+          - const: qcom,msm8916-apcs-kpss-global
+          - const: syscon
+      - items:
+          - enum:
+              - qcom,msm8976-apcs-kpss-global
+          - const: qcom,msm8994-apcs-kpss-global
+          - const: syscon
+      - items:
+          - enum:
+              - qcom,msm8998-apcs-hmss-global
+              - qcom,sdm660-apcs-hmss-global
+              - qcom,sm4250-apcs-hmss-global
+              - qcom,sm6115-apcs-hmss-global
+              - qcom,sm6125-apcs-hmss-global
+          - const: qcom,msm8994-apcs-kpss-global
+      - items:
+          - enum:
               - qcom,sc7180-apss-shared
               - qcom,sc8180x-apss-shared
               - qcom,sm8150-apss-shared
@@ -34,22 +52,14 @@ properties:
               - qcom,msm8916-apcs-kpss-global
               - qcom,msm8939-apcs-kpss-global
               - qcom,msm8953-apcs-kpss-global
-              - qcom,msm8976-apcs-kpss-global
               - qcom,msm8994-apcs-kpss-global
-              - qcom,qcs404-apcs-apps-global
               - qcom,sdx55-apcs-gcc
           - const: syscon
       - enum:
           - qcom,ipq6018-apcs-apps-global
-          - qcom,ipq8074-apcs-apps-global
           - qcom,msm8996-apcs-hmss-global
-          - qcom,msm8998-apcs-hmss-global
           - qcom,qcm2290-apcs-hmss-global
-          - qcom,sdm660-apcs-hmss-global
           - qcom,sdm845-apss-shared
-          - qcom,sm4250-apcs-hmss-global
-          - qcom,sm6115-apcs-hmss-global
-          - qcom,sm6125-apcs-hmss-global
 
   reg:
     maxItems: 1
@@ -80,20 +90,38 @@ allOf:
   - if:
       properties:
         compatible:
-          enum:
-            - qcom,msm8916-apcs-kpss-global
-            - qcom,msm8939-apcs-kpss-global
-            - qcom,qcs404-apcs-apps-global
+          contains:
+            enum:
+              - qcom,msm8916-apcs-kpss-global
+    then:
+      properties:
+        clocks:
+          items:
+            - description: primary pll parent of the clock driver
+            - description: auxiliary parent
+        clock-names:
+          items:
+            - const: pll
+            - const: aux
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,msm8939-apcs-kpss-global
     then:
       properties:
         clocks:
           items:
             - description: primary pll parent of the clock driver
             - description: auxiliary parent
+            - description: reference clock
         clock-names:
           items:
             - const: pll
             - const: aux
+            - const: ref
 
   - if:
       properties:
@@ -113,6 +141,7 @@ allOf:
             - const: ref
             - const: pll
             - const: aux
+
   - if:
       properties:
         compatible:
@@ -137,16 +166,10 @@ allOf:
         compatible:
           enum:
             - qcom,msm8953-apcs-kpss-global
-            - qcom,msm8976-apcs-kpss-global
             - qcom,msm8994-apcs-kpss-global
             - qcom,msm8996-apcs-hmss-global
-            - qcom,msm8998-apcs-hmss-global
             - qcom,qcm2290-apcs-hmss-global
-            - qcom,sdm660-apcs-hmss-global
             - qcom,sdm845-apss-shared
-            - qcom,sm4250-apcs-hmss-global
-            - qcom,sm6115-apcs-hmss-global
-            - qcom,sm6125-apcs-hmss-global
     then:
       properties:
         clocks: false
@@ -192,7 +215,8 @@ examples:
     #define GCC_APSS_AHB_CLK_SRC  1
     #define GCC_GPLL0_AO_OUT_MAIN 123
     apcs: mailbox@b011000 {
-        compatible = "qcom,qcs404-apcs-apps-global", "syscon";
+        compatible = "qcom,qcs404-apcs-apps-global",
+                     "qcom,msm8916-apcs-kpss-global", "syscon";
         reg = <0x0b011000 0x1000>;
         #mbox-cells = <1>;
         clocks = <&apcs_hfpll>, <&gcc GCC_GPLL0_AO_OUT_MAIN>;
diff --git a/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml b/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml
index a35f9483dc71..8f004868aad9 100644
--- a/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml
+++ b/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml
@@ -35,6 +35,7 @@ properties:
           - qcom,sm8450-ipcc
           - qcom,sm8550-ipcc
           - qcom,sm8650-ipcc
+          - qcom,x1e80100-ipcc
       - const: qcom,ipcc
 
   reg:
diff --git a/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.yaml b/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.yaml
index 8b15a0532120..fe83b5cb1278 100644
--- a/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.yaml
+++ b/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.yaml
@@ -37,7 +37,9 @@ maintainers:
 
 properties:
   compatible:
-    const: xlnx,zynqmp-ipi-mailbox
+    enum:
+      - xlnx,zynqmp-ipi-mailbox
+      - xlnx,versal-ipi-mailbox
 
   method:
     description: |
@@ -58,6 +60,12 @@ properties:
   '#size-cells':
     const: 2
 
+  reg:
+    maxItems: 2
+
+  reg-names:
+    maxItems: 2
+
   xlnx,ipi-id:
     description: |
       Remote Xilinx IPI agent ID of which the mailbox is connected to.
@@ -76,7 +84,17 @@ patternProperties:
     properties:
 
       compatible:
-        const: xlnx,zynqmp-ipi-dest-mailbox
+        enum:
+          - xlnx,zynqmp-ipi-dest-mailbox
+          - xlnx,versal-ipi-dest-mailbox
+
+      reg:
+        minItems: 1
+        maxItems: 4
+
+      reg-names:
+        minItems: 1
+        maxItems: 4
 
       xlnx,ipi-id:
         description:
@@ -88,23 +106,44 @@ patternProperties:
         description:
           It contains tx(0) or rx(1) channel IPI id number.
 
-      reg:
-        maxItems: 4
-
-      reg-names:
-        items:
-          - const: local_request_region
-          - const: local_response_region
-          - const: remote_request_region
-          - const: remote_response_region
+    allOf:
+      - if:
+          properties:
+            compatible:
+              contains:
+                enum:
+                  - xlnx,zynqmp-ipi-dest-mailbox
+        then:
+          properties:
+            reg:
+              maxItems: 4
+
+            reg-names:
+              items:
+                - const: local_request_region
+                - const: local_response_region
+                - const: remote_request_region
+                - const: remote_response_region
+        else:
+          properties:
+            reg:
+              minItems: 1
+              items:
+                - description: Remote IPI agent control register region
+                - description: Remote IPI agent optional message buffers
+
+            reg-names:
+              minItems: 1
+              items:
+                - const: ctrl
+                - const: msg
 
     required:
       - compatible
       - reg
       - reg-names
       - "#mbox-cells"
-
-additionalProperties: false
+      - xlnx,ipi-id
 
 required:
   - compatible
@@ -113,6 +152,36 @@ required:
   - '#size-cells'
   - xlnx,ipi-id
 
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - xlnx,zynqmp-ipi-mailbox
+    then:
+      properties:
+        reg: false
+        reg-names: false
+
+    else:
+      properties:
+        reg:
+          items:
+            - description: Host IPI agent control register region
+            - description: Host IPI agent optional message buffers
+
+        reg-names:
+          items:
+            - const: ctrl
+            - const: msg
+
+      required:
+        - reg
+        - reg-names
+
+additionalProperties: false
+
 examples:
   - |
     #include<dt-bindings/interrupt-controller/arm-gic.h>
@@ -144,4 +213,41 @@ examples:
       };
     };
 
+  - |
+    #include<dt-bindings/interrupt-controller/arm-gic.h>
+
+    bus {
+      #address-cells = <2>;
+      #size-cells = <2>;
+      mailbox@ff300000 {
+        compatible = "xlnx,versal-ipi-mailbox";
+        interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
+        #address-cells = <2>;
+        #size-cells = <2>;
+        reg = <0x0 0xff300000 0x0 0x1000>,
+              <0x0 0xff990000 0x0 0x1ff>;
+        reg-names = "ctrl", "msg";
+        xlnx,ipi-id = <0>;
+        ranges;
+
+        /* buffered IPI */
+        mailbox@ff340000 {
+          compatible = "xlnx,versal-ipi-dest-mailbox";
+          reg = <0x0 0xff340000 0x0 0x1000>,
+                <0x0 0xff990400 0x0 0x1ff>;
+          reg-names = "ctrl", "msg";
+          #mbox-cells = <1>;
+          xlnx,ipi-id = <4>;
+        };
+
+        /* bufferless IPI */
+        mailbox@ff370000 {
+          compatible = "xlnx,versal-ipi-dest-mailbox";
+          reg = <0x0 0xff370000 0x0 0x1000>;
+          reg-names = "ctrl";
+          #mbox-cells = <1>;
+          xlnx,ipi-id = <7>;
+        };
+      };
+    };
 ...
diff --git a/Documentation/devicetree/bindings/media/cnm,wave521c.yaml b/Documentation/devicetree/bindings/media/cnm,wave521c.yaml
index 6d5569e77b7a..6a11c1d11fb5 100644
--- a/Documentation/devicetree/bindings/media/cnm,wave521c.yaml
+++ b/Documentation/devicetree/bindings/media/cnm,wave521c.yaml
@@ -17,7 +17,7 @@ properties:
   compatible:
     items:
       - enum:
-          - ti,k3-j721s2-wave521c
+          - ti,j721s2-wave521c
       - const: cnm,wave521c
 
   reg:
@@ -53,7 +53,7 @@ additionalProperties: false
 examples:
   - |
     vpu: video-codec@12345678 {
-        compatible = "ti,k3-j721s2-wave521c", "cnm,wave521c";
+        compatible = "ti,j721s2-wave521c", "cnm,wave521c";
         reg = <0x12345678 0x1000>;
         clocks = <&clks 42>;
         interrupts = <42>;
diff --git a/Documentation/devicetree/bindings/mfd/ams,as3711.yaml b/Documentation/devicetree/bindings/mfd/ams,as3711.yaml
new file mode 100644
index 000000000000..ad8649cbb2cc
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/ams,as3711.yaml
@@ -0,0 +1,223 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/mfd/ams,as3711.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Austria MicroSystems AS3711 Quad Buck High Current PMIC with Charger
+
+maintainers:
+  - Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
+
+description:
+  AS3711 is an I2C PMIC from Austria MicroSystems with multiple DC/DC and LDO
+  power supplies, a battery charger and an RTC.  So far only bindings for the
+  two step-up DC/DC converters are defined.
+
+properties:
+  compatible:
+    const: ams,as3711
+
+  reg:
+    maxItems: 1
+
+  backlight:
+    description:
+      Step-up converter configuration, to be used as a backlight source
+    type: object
+    additionalProperties: false
+    properties:
+      compatible:
+        const: ams,as3711-bl
+
+      su1-dev:
+        description: Framebuffer phandle for the first step-up converter
+        $ref: /schemas/types.yaml#/definitions/phandle
+
+      su1-max-uA:
+        description: Maximum current for the first step-up converter
+        $ref: /schemas/types.yaml#/definitions/uint32
+
+      su2-dev:
+        description: Framebuffer phandle for the second step-up converter
+        $ref: /schemas/types.yaml#/definitions/phandle
+
+      su2-max-uA:
+        description: Maximum current for the second step-up converter
+        $ref: /schemas/types.yaml#/definitions/uint32
+
+      su2-feedback-voltage:
+        description: Second step-up converter uses voltage feedback
+        type: boolean
+
+      su2-feedback-curr1:
+        description:
+          Second step-up converter uses CURR1 input for current feedback
+        type: boolean
+
+      su2-feedback-curr2:
+        description:
+          Second step-up converter uses CURR2 input for current feedback
+        type: boolean
+
+      su2-feedback-curr3:
+        description:
+          Second step-up converter uses CURR3 input for current feedback
+        type: boolean
+
+      su2-feedback-curr-auto:
+        description:
+          Second step-up converter uses automatic current feedback selection
+        type: boolean
+
+      su2-fbprot-lx-sd4:
+        description:
+          Second step-up converter uses LX_SD4 for over-voltage protection
+        type: boolean
+
+      su2-fbprot-gpio2:
+        description:
+          Second step-up converter uses GPIO2 for over-voltage protection
+        type: boolean
+
+      su2-fbprot-gpio3:
+        description:
+          Second step-up converter uses GPIO3 for over-voltage protection
+        type: boolean
+
+      su2-fbprot-gpio4:
+        description:
+          Second step-up converter uses GPIO4 for over-voltage protection
+        type: boolean
+
+      su2-auto-curr1:
+        description:
+          Second step-up converter uses CURR1 input for automatic current
+          feedback
+        type: boolean
+
+      su2-auto-curr2:
+        description:
+          Second step-up converter uses CURR2 input for automatic current
+          feedback
+        type: boolean
+
+      su2-auto-curr3:
+        description:
+          Second step-up converter uses CURR3 input for automatic current
+          feedback
+        type: boolean
+
+    required:
+      - compatible
+
+    dependentRequired:
+      # To use the SU1 converter as a backlight source the following two
+      # properties must be provided:
+      su1-dev: [ su1-max-uA ]
+      su1-max-uA: [ su1-dev ]
+
+      # To use the SU2 converter as a backlight source the following two
+      # properties must be provided:
+      su2-dev: [ su2-max-uA ]
+      su2-max-uA: [ su2-dev ]
+
+      su2-feedback-voltage: [ su2-dev ]
+      su2-feedback-curr1: [ su2-dev ]
+      su2-feedback-curr2: [ su2-dev ]
+      su2-feedback-curr3: [ su2-dev ]
+      su2-feedback-curr-auto: [ su2-dev ]
+      su2-fbprot-lx-sd4: [ su2-dev ]
+      su2-fbprot-gpio2: [ su2-dev ]
+      su2-fbprot-gpio3: [ su2-dev ]
+      su2-fbprot-gpio4: [ su2-dev ]
+      su2-auto-curr1: [ su2-feedback-curr-auto ]
+      su2-auto-curr2: [ su2-feedback-curr-auto ]
+      su2-auto-curr3: [ su2-feedback-curr-auto ]
+
+    dependentSchemas:
+      su2-dev:
+        allOf:
+          - oneOf:
+              - required:
+                  - su2-feedback-voltage
+              - required:
+                  - su2-feedback-curr1
+              - required:
+                  - su2-feedback-curr2
+              - required:
+                  - su2-feedback-curr3
+              - required:
+                  - su2-feedback-curr-auto
+          - oneOf:
+              - required:
+                  - su2-fbprot-lx-sd4
+              - required:
+                  - su2-fbprot-gpio2
+              - required:
+                  - su2-fbprot-gpio3
+              - required:
+                  - su2-fbprot-gpio4
+
+      su2-feedback-curr-auto:
+        anyOf:
+          - required:
+              - su2-auto-curr1
+          - required:
+              - su2-auto-curr2
+          - required:
+              - su2-auto-curr3
+
+  regulators:
+    description: Other DC/DC and LDO supplies
+    type: object
+    unevaluatedProperties: false
+    patternProperties:
+      "^(sd[1-4]|ldo[1-8])$":
+        type: object
+        $ref: /schemas/regulator/regulator.yaml#
+        unevaluatedProperties: false
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        pmic@40 {
+            compatible = "ams,as3711";
+            reg = <0x40>;
+
+            regulators {
+                sd4 {
+                    regulator-name = "1.215V";
+                    regulator-min-microvolt = <1215000>;
+                    regulator-max-microvolt = <1235000>;
+                };
+                ldo2 {
+                    regulator-name = "2.8V CPU";
+                    regulator-min-microvolt = <2800000>;
+                    regulator-max-microvolt = <2800000>;
+                    regulator-always-on;
+                    regulator-boot-on;
+                };
+            };
+
+            backlight {
+                compatible = "ams,as3711-bl";
+                su2-dev = <&lcdc>;
+                su2-max-uA = <36000>;
+                su2-feedback-curr-auto;
+                su2-fbprot-gpio4;
+                su2-auto-curr1;
+                su2-auto-curr2;
+                su2-auto-curr3;
+            };
+        };
+    };
diff --git a/Documentation/devicetree/bindings/mfd/as3711.txt b/Documentation/devicetree/bindings/mfd/as3711.txt
deleted file mode 100644
index d98cf18c721c..000000000000
--- a/Documentation/devicetree/bindings/mfd/as3711.txt
+++ /dev/null
@@ -1,73 +0,0 @@
-AS3711 is an I2C PMIC from Austria MicroSystems with multiple DCDC and LDO power
-supplies, a battery charger and an RTC. So far only bindings for the two stepup
-DCDC converters are defined. Other DCDC and LDO supplies are configured, using
-standard regulator properties, they must belong to a sub-node, called
-"regulators" and be called "sd1" to "sd4" and "ldo1" to "ldo8." Stepup converter
-configuration should be placed in a subnode, called "backlight."
-
-Compulsory properties:
-- compatible		: must be "ams,as3711"
-- reg			: specifies the I2C address
-
-To use the SU1 converter as a backlight source the following two properties must
-be provided:
-- su1-dev		: framebuffer phandle
-- su1-max-uA		: maximum current
-
-To use the SU2 converter as a backlight source the following two properties must
-be provided:
-- su2-dev		: framebuffer phandle
-- su1-max-uA		: maximum current
-
-Additionally one of these properties must be provided to select the type of
-feedback used:
-- su2-feedback-voltage	: voltage feedback is used
-- su2-feedback-curr1	: CURR1 input used for current feedback
-- su2-feedback-curr2	: CURR2 input used for current feedback
-- su2-feedback-curr3	: CURR3 input used for current feedback
-- su2-feedback-curr-auto: automatic current feedback selection
-
-and one of these to select the over-voltage protection pin
-- su2-fbprot-lx-sd4	: LX_SD4 is used for over-voltage protection
-- su2-fbprot-gpio2	: GPIO2 is used for over-voltage protection
-- su2-fbprot-gpio3	: GPIO3 is used for over-voltage protection
-- su2-fbprot-gpio4	: GPIO4 is used for over-voltage protection
-
-If "su2-feedback-curr-auto" is selected, one or more of the following properties
-have to be specified:
-- su2-auto-curr1	: use CURR1 input for current feedback
-- su2-auto-curr2	: use CURR2 input for current feedback
-- su2-auto-curr3	: use CURR3 input for current feedback
-
-Example:
-
-as3711@40 {
-	compatible = "ams,as3711";
-	reg = <0x40>;
-
-	regulators {
-		sd4 {
-			regulator-name = "1.215V";
-			regulator-min-microvolt = <1215000>;
-			regulator-max-microvolt = <1235000>;
-		};
-		ldo2 {
-			regulator-name = "2.8V CPU";
-			regulator-min-microvolt = <2800000>;
-			regulator-max-microvolt = <2800000>;
-			regulator-always-on;
-			regulator-boot-on;
-		};
-	};
-
-	backlight {
-		compatible = "ams,as3711-bl";
-		su2-dev = <&lcdc>;
-		su2-max-uA = <36000>;
-		su2-feedback-curr-auto;
-		su2-fbprot-gpio4;
-		su2-auto-curr1;
-		su2-auto-curr2;
-		su2-auto-curr3;
-	};
-};
diff --git a/Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml b/Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml
index bdff5b653453..6a824351834e 100644
--- a/Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml
+++ b/Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml
@@ -17,7 +17,7 @@ description: |
   node.
 
   The SPMI controller part is provided by
-  Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml
+  Documentation/devicetree/bindings/spmi/hisilicon,hisi-spmi-controller.yaml
 
 properties:
   $nodename:
@@ -42,13 +42,6 @@ properties:
 
     additionalProperties: false
 
-    properties:
-      '#address-cells':
-        const: 1
-
-      '#size-cells':
-        const: 0
-
     patternProperties:
       '^ldo[0-9]+$':
         type: object
@@ -66,72 +59,75 @@ additionalProperties: false
 
 examples:
   - |
+    #include <dt-bindings/spmi/spmi.h>
 
-    pmic: pmic@0 {
-      compatible = "hisilicon,hi6421v600-spmi";
-      reg = <0 0>;
-
-      #interrupt-cells = <2>;
-      interrupt-controller;
-      interrupt-parent = <&gpio28>;
-      interrupts = <0 0>;
-
-      regulators {
-        #address-cells = <1>;
+    spmi {
+        #address-cells = <2>;
         #size-cells = <0>;
 
-        ldo3: ldo3 {
-          regulator-name = "ldo3";
-          regulator-min-microvolt = <1500000>;
-          regulator-max-microvolt = <2000000>;
-          regulator-boot-on;
-        };
-
-        ldo4: ldo4 {
-          regulator-name = "ldo4";
-          regulator-min-microvolt = <1725000>;
-          regulator-max-microvolt = <1900000>;
-          regulator-boot-on;
-        };
-
-        ldo9: ldo9 {
-          regulator-name = "ldo9";
-          regulator-min-microvolt = <1750000>;
-          regulator-max-microvolt = <3300000>;
-          regulator-boot-on;
-        };
-
-        ldo15: ldo15 {
-          regulator-name = "ldo15";
-          regulator-min-microvolt = <1800000>;
-          regulator-max-microvolt = <3000000>;
-          regulator-always-on;
-        };
-
-        ldo16: ldo16 {
-          regulator-name = "ldo16";
-          regulator-min-microvolt = <1800000>;
-          regulator-max-microvolt = <3000000>;
-          regulator-boot-on;
-        };
-
-        ldo17: ldo17 {
-          regulator-name = "ldo17";
-          regulator-min-microvolt = <2500000>;
-          regulator-max-microvolt = <3300000>;
-        };
-
-        ldo33: ldo33 {
-          regulator-name = "ldo33";
-          regulator-min-microvolt = <2500000>;
-          regulator-max-microvolt = <3300000>;
-          regulator-boot-on;
-        };
-
-        ldo34: ldo34 {
-          regulator-name = "ldo34";
-          regulator-min-microvolt = <2600000>;
-          regulator-max-microvolt = <3300000>;
+        pmic@0 {
+            compatible = "hisilicon,hi6421v600-spmi";
+            reg = <0 SPMI_USID>;
+
+            #interrupt-cells = <2>;
+            interrupt-controller;
+            interrupt-parent = <&gpio28>;
+            interrupts = <0 0>;
+
+            regulators {
+                ldo3 {
+                    regulator-name = "ldo3";
+                    regulator-min-microvolt = <1500000>;
+                    regulator-max-microvolt = <2000000>;
+                    regulator-boot-on;
+                };
+
+                ldo4 {
+                    regulator-name = "ldo4";
+                    regulator-min-microvolt = <1725000>;
+                    regulator-max-microvolt = <1900000>;
+                    regulator-boot-on;
+                };
+
+                ldo9 {
+                    regulator-name = "ldo9";
+                    regulator-min-microvolt = <1750000>;
+                    regulator-max-microvolt = <3300000>;
+                    regulator-boot-on;
+                };
+
+                ldo15 {
+                    regulator-name = "ldo15";
+                    regulator-min-microvolt = <1800000>;
+                    regulator-max-microvolt = <3000000>;
+                    regulator-always-on;
+                };
+
+                ldo16 {
+                    regulator-name = "ldo16";
+                    regulator-min-microvolt = <1800000>;
+                    regulator-max-microvolt = <3000000>;
+                    regulator-boot-on;
+                };
+
+                ldo17 {
+                    regulator-name = "ldo17";
+                    regulator-min-microvolt = <2500000>;
+                    regulator-max-microvolt = <3300000>;
+                };
+
+                ldo33 {
+                    regulator-name = "ldo33";
+                    regulator-min-microvolt = <2500000>;
+                    regulator-max-microvolt = <3300000>;
+                    regulator-boot-on;
+                };
+
+                ldo34 {
+                    regulator-name = "ldo34";
+                    regulator-min-microvolt = <2600000>;
+                    regulator-max-microvolt = <3300000>;
+                };
+            };
         };
-      };
     };
diff --git a/Documentation/devicetree/bindings/mfd/qcom,pm8008.yaml b/Documentation/devicetree/bindings/mfd/qcom,pm8008.yaml
index 9e4eed34dae8..0c75d8bde568 100644
--- a/Documentation/devicetree/bindings/mfd/qcom,pm8008.yaml
+++ b/Documentation/devicetree/bindings/mfd/qcom,pm8008.yaml
@@ -99,10 +99,12 @@ examples:
   - |
     #include <dt-bindings/mfd/qcom-pm8008.h>
     #include <dt-bindings/interrupt-controller/irq.h>
-    qupv3_se13_i2c {
+
+    i2c {
       #address-cells = <1>;
       #size-cells = <0>;
-      pm8008i@8 {
+
+      pmic@8 {
         compatible = "qcom,pm8008";
         reg = <0x8>;
         #address-cells = <1>;
diff --git a/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml b/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml
index 9fa568603930..8103fb61a16c 100644
--- a/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml
+++ b/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml
@@ -66,6 +66,7 @@ properties:
           - qcom,pm8841
           - qcom,pm8909
           - qcom,pm8916
+          - qcom,pm8937
           - qcom,pm8941
           - qcom,pm8950
           - qcom,pm8953
@@ -134,9 +135,15 @@ patternProperties:
     type: object
     $ref: /schemas/sound/qcom,pm8916-wcd-analog-codec.yaml#
 
+  "^battery@[0-9a-f]+$":
+    type: object
+    oneOf:
+      - $ref: /schemas/power/supply/qcom,pm8916-bms-vm.yaml#
+
   "^charger@[0-9a-f]+$":
     type: object
     oneOf:
+      - $ref: /schemas/power/supply/qcom,pm8916-lbc.yaml#
       - $ref: /schemas/power/supply/qcom,pm8941-charger.yaml#
       - $ref: /schemas/power/supply/qcom,pm8941-coincell.yaml#
       - $ref: /schemas/power/supply/qcom,pmi8998-charger.yaml#
diff --git a/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml b/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml
index 33c3d023a106..798705ab6a46 100644
--- a/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml
+++ b/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml
@@ -29,6 +29,8 @@ properties:
           - qcom,sdx65-tcsr
           - qcom,sm4450-tcsr
           - qcom,sm8150-tcsr
+          - qcom,sm8250-tcsr
+          - qcom,sm8350-tcsr
           - qcom,sm8450-tcsr
           - qcom,tcsr-apq8064
           - qcom,tcsr-apq8084
diff --git a/Documentation/devicetree/bindings/mfd/sprd,ums512-glbreg.yaml b/Documentation/devicetree/bindings/mfd/sprd,ums512-glbreg.yaml
index 996bd4a17ca3..a750fa23d7e7 100644
--- a/Documentation/devicetree/bindings/mfd/sprd,ums512-glbreg.yaml
+++ b/Documentation/devicetree/bindings/mfd/sprd,ums512-glbreg.yaml
@@ -19,7 +19,9 @@ description:
 properties:
   compatible:
     items:
-      - const: sprd,ums512-glbregs
+      - enum:
+          - sprd,ums512-glbregs
+          - sprd,ums9620-glbregs
       - const: syscon
       - const: simple-mfd
 
diff --git a/Documentation/devicetree/bindings/mfd/ti,am3359-tscadc.yaml b/Documentation/devicetree/bindings/mfd/ti,am3359-tscadc.yaml
index 23a63265be3c..70b5dfce07d2 100644
--- a/Documentation/devicetree/bindings/mfd/ti,am3359-tscadc.yaml
+++ b/Documentation/devicetree/bindings/mfd/ti,am3359-tscadc.yaml
@@ -61,8 +61,6 @@ required:
   - interrupts
   - clocks
   - clock-names
-  - dmas
-  - dma-names
 
 additionalProperties: false
 
diff --git a/Documentation/devicetree/bindings/net/marvell,prestera.yaml b/Documentation/devicetree/bindings/net/marvell,prestera.yaml
index 5ea8b73663a5..16ff892f7bbd 100644
--- a/Documentation/devicetree/bindings/net/marvell,prestera.yaml
+++ b/Documentation/devicetree/bindings/net/marvell,prestera.yaml
@@ -78,8 +78,8 @@ examples:
     pcie@0 {
         #address-cells = <3>;
         #size-cells = <2>;
-        ranges = <0x0 0x0 0x0 0x0 0x0 0x0>;
-        reg = <0x0 0x0 0x0 0x0 0x0 0x0>;
+        ranges = <0x02000000 0x0 0x100000 0x10000000 0x0 0x0>;
+        reg = <0x0 0x1000>;
         device_type = "pci";
 
         switch@0,0 {
diff --git a/Documentation/devicetree/bindings/net/renesas,ethertsn.yaml b/Documentation/devicetree/bindings/net/renesas,ethertsn.yaml
index 475aff7714d6..ea35d19be829 100644
--- a/Documentation/devicetree/bindings/net/renesas,ethertsn.yaml
+++ b/Documentation/devicetree/bindings/net/renesas,ethertsn.yaml
@@ -65,9 +65,11 @@ properties:
 
   rx-internal-delay-ps:
     enum: [0, 1800]
+    default: 0
 
   tx-internal-delay-ps:
     enum: [0, 2000]
+    default: 0
 
   '#address-cells':
     const: 1
diff --git a/Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml b/Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml
index a69de3e92282..92bfe25f0571 100644
--- a/Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml
+++ b/Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml
@@ -24,6 +24,7 @@ properties:
       - st,stm32f4-otp
       - st,stm32mp13-bsec
       - st,stm32mp15-bsec
+      - st,stm32mp25-bsec
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml b/Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml
index 7e15aae7d69e..22491f7f8852 100644
--- a/Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml
@@ -64,6 +64,24 @@ properties:
 
   aspm-no-l0s: true
 
+  brcm,clkreq-mode:
+    description: A string that determines the operating
+      clkreq mode of the PCIe RC HW with respect to controlling the refclk
+      signal.  There are three different modes -- "safe", which drives the
+      refclk signal unconditionally and will work for all devices but does
+      not provide any power savings; "no-l1ss" -- which provides Clock
+      Power Management, L0s, and L1, but cannot provide L1 substate (L1SS)
+      power savings. If the downstream device connected to the RC is L1SS
+      capable AND the OS enables L1SS, all PCIe traffic may abruptly halt,
+      potentially hanging the system; "default" -- which provides L0s, L1,
+      and L1SS, but not compliant to provide Clock Power Management;
+      specifically, may not be able to meet the T_CLRon max timing of 400ns
+      as specified in "Dynamic Clock Control", section 3.2.5.2.2 PCI
+      Express Mini CEM 2.1 specification.  This situation is atypical and
+      should happen only with older devices.
+    $ref: /schemas/types.yaml#/definitions/string
+    enum: [ safe, no-l1ss, default ]
+
   brcm,scb-sizes:
     description: u64 giving the 64bit PCIe memory
       viewport size of a memory controller.  There may be up to
diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
index eadba38171e1..a93ab3b54066 100644
--- a/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
@@ -42,6 +42,10 @@ properties:
           - qcom,pcie-sm8450-pcie1
           - qcom,pcie-sm8550
       - items:
+          - enum:
+              - qcom,pcie-sm8650
+          - const: qcom,pcie-sm8550
+      - items:
           - const: qcom,pcie-msm8998
           - const: qcom,pcie-msm8996
 
@@ -62,7 +66,8 @@ properties:
     maxItems: 8
 
   iommu-map:
-    maxItems: 2
+    minItems: 1
+    maxItems: 16
 
   # Common definitions for clocks, clock-names and reset.
   # Platform constraints are described later.
@@ -88,7 +93,7 @@ properties:
     minItems: 1
     maxItems: 12
 
-  resets-names:
+  reset-names:
     minItems: 1
     maxItems: 12
 
@@ -483,6 +488,33 @@ allOf:
         compatible:
           contains:
             enum:
+              - qcom,pcie-sc8180x
+    then:
+      properties:
+        clocks:
+          minItems: 8
+          maxItems: 8
+        clock-names:
+          items:
+            - const: pipe # PIPE clock
+            - const: aux # Auxiliary clock
+            - const: cfg # Configuration clock
+            - const: bus_master # Master AXI clock
+            - const: bus_slave # Slave AXI clock
+            - const: slave_q2a # Slave Q2A clock
+            - const: ref # REFERENCE clock
+            - const: tbu # PCIe TBU clock
+        resets:
+          maxItems: 1
+        reset-names:
+          items:
+            - const: pci # PCIe core reset
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
               - qcom,pcie-sdm845
     then:
       oneOf:
@@ -526,8 +558,33 @@ allOf:
         compatible:
           contains:
             enum:
-              - qcom,pcie-sc8180x
               - qcom,pcie-sm8150
+    then:
+      properties:
+        clocks:
+          minItems: 8
+          maxItems: 8
+        clock-names:
+          items:
+            - const: pipe # PIPE clock
+            - const: aux # Auxiliary clock
+            - const: cfg # Configuration clock
+            - const: bus_master # Master AXI clock
+            - const: bus_slave # Slave AXI clock
+            - const: slave_q2a # Slave Q2A clock
+            - const: tbu # PCIe TBU clock
+            - const: ref # REFERENCE clock
+        resets:
+          maxItems: 1
+        reset-names:
+          items:
+            - const: pci # PCIe core reset
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
               - qcom,pcie-sm8250
     then:
       oneOf:
diff --git a/Documentation/devicetree/bindings/pci/rcar-pci-host.yaml b/Documentation/devicetree/bindings/pci/rcar-pci-host.yaml
index 8fdfbc763d70..b6a7cb32f61e 100644
--- a/Documentation/devicetree/bindings/pci/rcar-pci-host.yaml
+++ b/Documentation/devicetree/bindings/pci/rcar-pci-host.yaml
@@ -68,6 +68,15 @@ properties:
   phy-names:
     const: pcie
 
+  vpcie1v5-supply:
+    description: The 1.5v regulator to use for PCIe.
+
+  vpcie3v3-supply:
+    description: The 3.3v regulator to use for PCIe.
+
+  vpcie12v-supply:
+    description: The 12v regulator to use for PCIe.
+
 required:
   - compatible
   - reg
@@ -121,5 +130,7 @@ examples:
              clock-names = "pcie", "pcie_bus";
              power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
              resets = <&cpg 319>;
+             vpcie3v3-supply = <&pcie_3v3>;
+             vpcie12v-supply = <&pcie_12v>;
          };
     };
diff --git a/Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml b/Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml
index 1ae8dcfa072c..5f719218c472 100644
--- a/Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml
@@ -49,6 +49,7 @@ properties:
       - description: APB clock for PCIe
       - description: Auxiliary clock for PCIe
       - description: PIPE clock
+      - description: Reference clock for PCIe
 
   clock-names:
     minItems: 5
@@ -59,6 +60,7 @@ properties:
       - const: pclk
       - const: aux
       - const: pipe
+      - const: ref
 
   interrupts:
     items:
diff --git a/Documentation/devicetree/bindings/pci/ti,j721e-pci-ep.yaml b/Documentation/devicetree/bindings/pci/ti,j721e-pci-ep.yaml
index 62292185fe2e..97f2579ea908 100644
--- a/Documentation/devicetree/bindings/pci/ti,j721e-pci-ep.yaml
+++ b/Documentation/devicetree/bindings/pci/ti,j721e-pci-ep.yaml
@@ -10,13 +10,11 @@ title: TI J721E PCI EP (PCIe Wrapper)
 maintainers:
   - Kishon Vijay Abraham I <kishon@ti.com>
 
-allOf:
-  - $ref: cdns-pcie-ep.yaml#
-
 properties:
   compatible:
     oneOf:
       - const: ti,j721e-pcie-ep
+      - const: ti,j784s4-pcie-ep
       - description: PCIe EP controller in AM64
         items:
           - const: ti,am64-pcie-ep
@@ -65,6 +63,41 @@ properties:
     items:
       - const: link_state
 
+allOf:
+  - $ref: cdns-pcie-ep.yaml#
+  - if:
+      properties:
+        compatible:
+          enum:
+            - ti,am64-pcie-ep
+    then:
+      properties:
+        num-lanes:
+          const: 1
+
+  - if:
+      properties:
+        compatible:
+          enum:
+            - ti,j7200-pcie-ep
+            - ti,j721e-pcie-ep
+    then:
+      properties:
+        num-lanes:
+          minimum: 1
+          maximum: 2
+
+  - if:
+      properties:
+        compatible:
+          enum:
+            - ti,j784s4-pcie-ep
+    then:
+      properties:
+        num-lanes:
+          minimum: 1
+          maximum: 4
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/pci/ti,j721e-pci-host.yaml b/Documentation/devicetree/bindings/pci/ti,j721e-pci-host.yaml
index a2c5eaea57f5..b7a534cef24d 100644
--- a/Documentation/devicetree/bindings/pci/ti,j721e-pci-host.yaml
+++ b/Documentation/devicetree/bindings/pci/ti,j721e-pci-host.yaml
@@ -10,13 +10,11 @@ title: TI J721E PCI Host (PCIe Wrapper)
 maintainers:
   - Kishon Vijay Abraham I <kishon@ti.com>
 
-allOf:
-  - $ref: cdns-pcie-host.yaml#
-
 properties:
   compatible:
     oneOf:
       - const: ti,j721e-pcie-host
+      - const: ti,j784s4-pcie-host
       - description: PCIe controller in AM64
         items:
           - const: ti,am64-pcie-host
@@ -94,6 +92,41 @@ properties:
       interrupts:
         maxItems: 1
 
+allOf:
+  - $ref: cdns-pcie-host.yaml#
+  - if:
+      properties:
+        compatible:
+          enum:
+            - ti,am64-pcie-host
+    then:
+      properties:
+        num-lanes:
+          const: 1
+
+  - if:
+      properties:
+        compatible:
+          enum:
+            - ti,j7200-pcie-host
+            - ti,j721e-pcie-host
+    then:
+      properties:
+        num-lanes:
+          minimum: 1
+          maximum: 2
+
+  - if:
+      properties:
+        compatible:
+          enum:
+            - ti,j784s4-pcie-host
+    then:
+      properties:
+        num-lanes:
+          minimum: 1
+          maximum: 4
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/phy/amlogic,g12a-mipi-dphy-analog.yaml b/Documentation/devicetree/bindings/phy/amlogic,g12a-mipi-dphy-analog.yaml
index c8c83acfb871..81c2654b7e57 100644
--- a/Documentation/devicetree/bindings/phy/amlogic,g12a-mipi-dphy-analog.yaml
+++ b/Documentation/devicetree/bindings/phy/amlogic,g12a-mipi-dphy-analog.yaml
@@ -16,20 +16,8 @@ properties:
   "#phy-cells":
     const: 0
 
-  reg:
-    maxItems: 1
-
 required:
   - compatible
-  - reg
   - "#phy-cells"
 
 additionalProperties: false
-
-examples:
-  - |
-    phy@0 {
-          compatible = "amlogic,g12a-mipi-dphy-analog";
-          reg = <0x0 0xc>;
-          #phy-cells = <0>;
-    };
diff --git a/Documentation/devicetree/bindings/phy/amlogic,meson-axg-mipi-pcie-analog.yaml b/Documentation/devicetree/bindings/phy/amlogic,meson-axg-mipi-pcie-analog.yaml
index 009a39808318..70def36e5688 100644
--- a/Documentation/devicetree/bindings/phy/amlogic,meson-axg-mipi-pcie-analog.yaml
+++ b/Documentation/devicetree/bindings/phy/amlogic,meson-axg-mipi-pcie-analog.yaml
@@ -9,16 +9,6 @@ title: Amlogic AXG shared MIPI/PCIE analog PHY
 maintainers:
   - Remi Pommarel <repk@triplefau.lt>
 
-description: |+
-  The Everything-Else Power Domains node should be the child of a syscon
-  node with the required property:
-
-  - compatible: Should be the following:
-                "amlogic,meson-gx-hhi-sysctrl", "simple-mfd", "syscon"
-
-  Refer to the bindings described in
-  Documentation/devicetree/bindings/mfd/syscon.yaml
-
 properties:
   compatible:
     const: amlogic,axg-mipi-pcie-analog-phy
@@ -31,10 +21,3 @@ required:
   - "#phy-cells"
 
 additionalProperties: false
-
-examples:
-  - |
-    mpphy: phy {
-          compatible = "amlogic,axg-mipi-pcie-analog-phy";
-          #phy-cells = <0>;
-    };
diff --git a/Documentation/devicetree/bindings/phy/mediatek,dsi-phy.yaml b/Documentation/devicetree/bindings/phy/mediatek,dsi-phy.yaml
index 6703689fcdbe..f6e494d0d89b 100644
--- a/Documentation/devicetree/bindings/phy/mediatek,dsi-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/mediatek,dsi-phy.yaml
@@ -31,6 +31,7 @@ properties:
       - items:
           - enum:
               - mediatek,mt8188-mipi-tx
+              - mediatek,mt8195-mipi-tx
               - mediatek,mt8365-mipi-tx
           - const: mediatek,mt8183-mipi-tx
       - const: mediatek,mt2701-mipi-tx
diff --git a/Documentation/devicetree/bindings/phy/mediatek,tphy.yaml b/Documentation/devicetree/bindings/phy/mediatek,tphy.yaml
index 2bb91542e984..acba0720125d 100644
--- a/Documentation/devicetree/bindings/phy/mediatek,tphy.yaml
+++ b/Documentation/devicetree/bindings/phy/mediatek,tphy.yaml
@@ -235,6 +235,15 @@ patternProperties:
           Specify the flag to enable BC1.2 if support it
         type: boolean
 
+      mediatek,force-mode:
+        description:
+          The force mode is used to manually switch the shared phy mode between
+          USB3 and PCIe, when USB3 phy type is selected by the consumer, and
+          force-mode is set, will cause phy's power and pipe toggled and force
+          phy as USB3 mode which switched from default PCIe mode. But perfer to
+          use the property "mediatek,syscon-type" for newer SoCs that support it.
+        type: boolean
+
       mediatek,syscon-type:
         $ref: /schemas/types.yaml#/definitions/phandle-array
         maxItems: 1
diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
index 2c3d6553a7ba..6c03f2d5fca3 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
@@ -36,6 +36,8 @@ properties:
       - qcom,sm8450-qmp-gen4x2-pcie-phy
       - qcom,sm8550-qmp-gen3x2-pcie-phy
       - qcom,sm8550-qmp-gen4x2-pcie-phy
+      - qcom,sm8650-qmp-gen3x2-pcie-phy
+      - qcom,sm8650-qmp-gen4x2-pcie-phy
 
   reg:
     minItems: 1
@@ -147,6 +149,8 @@ allOf:
               - qcom,sm8450-qmp-gen3x2-pcie-phy
               - qcom,sm8550-qmp-gen3x2-pcie-phy
               - qcom,sm8550-qmp-gen4x2-pcie-phy
+              - qcom,sm8650-qmp-gen3x2-pcie-phy
+              - qcom,sm8650-qmp-gen4x2-pcie-phy
     then:
       properties:
         clocks:
@@ -189,6 +193,7 @@ allOf:
           contains:
             enum:
               - qcom,sm8550-qmp-gen4x2-pcie-phy
+              - qcom,sm8650-qmp-gen4x2-pcie-phy
     then:
       properties:
         resets:
diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml
index f3a3296c811c..8474eef8d0ff 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml
@@ -32,6 +32,7 @@ properties:
       - qcom,sm8350-qmp-ufs-phy
       - qcom,sm8450-qmp-ufs-phy
       - qcom,sm8550-qmp-ufs-phy
+      - qcom,sm8650-qmp-ufs-phy
 
   reg:
     maxItems: 1
@@ -112,6 +113,7 @@ allOf:
               - qcom,sm8250-qmp-ufs-phy
               - qcom,sm8350-qmp-ufs-phy
               - qcom,sm8550-qmp-ufs-phy
+              - qcom,sm8650-qmp-ufs-phy
     then:
       properties:
         clocks:
diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml
index 57702f7f2a46..15d82c67f157 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml
@@ -32,6 +32,7 @@ properties:
       - qcom,sm8150-qmp-usb3-uni-phy
       - qcom,sm8250-qmp-usb3-uni-phy
       - qcom,sm8350-qmp-usb3-uni-phy
+      - qcom,x1e80100-qmp-usb3-uni-phy
 
 
   reg:
@@ -135,6 +136,7 @@ allOf:
               - qcom,sm8150-qmp-usb3-uni-phy
               - qcom,sm8250-qmp-usb3-uni-phy
               - qcom,sm8350-qmp-usb3-uni-phy
+              - qcom,x1e80100-qmp-usb3-uni-phy
     then:
       properties:
         clocks:
@@ -171,6 +173,7 @@ allOf:
             enum:
               - qcom,sa8775p-qmp-usb3-uni-phy
               - qcom,sc8280xp-qmp-usb3-uni-phy
+              - qcom,x1e80100-qmp-usb3-uni-phy
     then:
       required:
         - power-domains
diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml
index 9af203dc8793..2d0d7e9e6431 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml
@@ -27,6 +27,8 @@ properties:
       - qcom,sm8350-qmp-usb3-dp-phy
       - qcom,sm8450-qmp-usb3-dp-phy
       - qcom,sm8550-qmp-usb3-dp-phy
+      - qcom,sm8650-qmp-usb3-dp-phy
+      - qcom,x1e80100-qmp-usb3-dp-phy
 
   reg:
     maxItems: 1
@@ -62,12 +64,12 @@ properties:
   "#clock-cells":
     const: 1
     description:
-      See include/dt-bindings/dt-bindings/phy/phy-qcom-qmp.h
+      See include/dt-bindings/phy/phy-qcom-qmp.h
 
   "#phy-cells":
     const: 1
     description:
-      See include/dt-bindings/dt-bindings/phy/phy-qcom-qmp.h
+      See include/dt-bindings/phy/phy-qcom-qmp.h
 
   orientation-switch:
     description:
@@ -128,6 +130,8 @@ allOf:
             - qcom,sc8280xp-qmp-usb43dp-phy
             - qcom,sm6350-qmp-usb3-dp-phy
             - qcom,sm8550-qmp-usb3-dp-phy
+            - qcom,sm8650-qmp-usb3-dp-phy
+            - qcom,x1e80100-qmp-usb3-dp-phy
     then:
       required:
         - power-domains
diff --git a/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml
index c95828607ab6..b82f7f5731ed 100644
--- a/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml
@@ -18,6 +18,8 @@ properties:
       - items:
           - enum:
               - qcom,sdx75-snps-eusb2-phy
+              - qcom,sm8650-snps-eusb2-phy
+              - qcom,x1e80100-snps-eusb2-phy
           - const: qcom,sm8550-snps-eusb2-phy
       - const: qcom,sm8550-snps-eusb2-phy
 
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-single.yaml b/Documentation/devicetree/bindings/pinctrl/pinctrl-single.yaml
index 45a307d3ce16..c11495524dd2 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-single.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-single.yaml
@@ -31,6 +31,7 @@ properties:
               - ti,omap3-padconf
               - ti,omap4-padconf
               - ti,omap5-padconf
+              - ti,j7200-padconf
           - const: pinctrl-single
 
   reg:
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq5018-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,ipq5018-tlmm.yaml
index fad0118fd521..23300606547c 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq5018-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq5018-tlmm.yaml
@@ -23,13 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 24
@@ -95,7 +88,10 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+allOf:
+  - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml#
+
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq5332-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,ipq5332-tlmm.yaml
index 3d3086ae1ba6..e571cd64418f 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq5332-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq5332-tlmm.yaml
@@ -26,13 +26,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 27
@@ -100,7 +93,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq6018-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,ipq6018-pinctrl.yaml
index 7c3e5e043f07..ed00fbaec11b 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq6018-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq6018-pinctrl.yaml
@@ -22,12 +22,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-
 patternProperties:
   "-state$":
     oneOf:
@@ -100,7 +94,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.yaml
index e053fbd588b5..6f90dbbdbdcc 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.yaml
@@ -23,13 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 35
@@ -103,7 +96,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq9574-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,ipq9574-tlmm.yaml
index e5e9962b2174..bca903b5da6d 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq9574-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq9574-tlmm.yaml
@@ -23,13 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 33
@@ -97,7 +90,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,lpass-lpi-common.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,lpass-lpi-common.yaml
new file mode 100644
index 000000000000..3b5045730471
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,lpass-lpi-common.yaml
@@ -0,0 +1,75 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/qcom,lpass-lpi-common.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm SoC LPASS LPI TLMM Common Properties
+
+maintainers:
+  - Bjorn Andersson <andersson@kernel.org>
+  - Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+  - Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+
+description:
+  Common properties for the Top Level Mode Multiplexer pin controllers in the
+  Low Power Audio SubSystem (LPASS) Low Power Island (LPI) of Qualcomm SoCs.
+
+properties:
+  gpio-controller: true
+
+  "#gpio-cells":
+    description:
+      Specifying the pin number and flags, as defined in
+      include/dt-bindings/gpio/gpio.h
+    const: 2
+
+  gpio-ranges:
+    maxItems: 1
+
+required:
+  - gpio-controller
+  - "#gpio-cells"
+  - gpio-ranges
+
+allOf:
+  - $ref: pinctrl.yaml#
+
+additionalProperties: true
+
+$defs:
+  qcom-tlmm-state:
+    properties:
+      drive-strength:
+        enum: [2, 4, 6, 8, 10, 12, 14, 16]
+        default: 2
+        description:
+          Selects the drive strength for the specified pins, in mA.
+
+      slew-rate:
+        enum: [0, 1, 2, 3]
+        default: 0
+        description: |
+          0: No adjustments
+          1: Higher Slew rate (faster edges)
+          2: Lower Slew rate (slower edges)
+          3: Reserved (No adjustments)
+
+      bias-bus-hold: true
+      bias-pull-down: true
+      bias-pull-up: true
+      bias-disable: true
+      input-enable: true
+      output-high: true
+      output-low: true
+
+    required:
+      - pins
+      - function
+
+    allOf:
+      - $ref: pincfg-node.yaml#
+      - $ref: pinmux-node.yaml#
+
+    additionalProperties: true
+
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml
index 5ece3b9d676b..bd3cbb44c99a 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml
@@ -25,19 +25,7 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
   gpio-reserved-ranges: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
 
 patternProperties:
   "-state$":
@@ -110,6 +98,12 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.yaml
index 5885aee95c98..299e0b4b0ab4 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.yaml
@@ -23,18 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  '#interrupt-cells': true
-  gpio-controller: true
-  '#gpio-cells': true
-  gpio-ranges: true
-
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
-
 patternProperties:
   "-state$":
     oneOf:
@@ -74,6 +62,12 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8226-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8226-pinctrl.yaml
index a602bf0d27fb..68d3fa2105b8 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8226-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8226-pinctrl.yaml
@@ -23,12 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-
   gpio-reserved-ranges:
     maxItems: 1
 
@@ -82,7 +76,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.yaml
index a05971611780..61f5be21f30c 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.yaml
@@ -23,13 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 86
@@ -92,7 +85,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8909-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8909-tlmm.yaml
index 5095e86fe9a2..295dd5fcf4c3 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8909-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8909-tlmm.yaml
@@ -25,19 +25,7 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
   gpio-reserved-ranges: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
 
 patternProperties:
   "-state$":
@@ -108,6 +96,12 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.yaml
index 063d004967bb..904af87f9eaf 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.yaml
@@ -23,13 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 61
@@ -114,7 +107,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8953-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8953-pinctrl.yaml
index 798aac9e6e31..8a3a962f6c00 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8953-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8953-pinctrl.yaml
@@ -22,12 +22,7 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
   gpio-reserved-ranges: true
-  "#gpio-cells": true
-  gpio-ranges: true
 
 patternProperties:
   "-state$":
@@ -117,7 +112,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.yaml
index 9172b50f7a98..46618740bd31 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.yaml
@@ -23,13 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 76
@@ -108,7 +101,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.yaml
index 8a3be65c51ed..840fdaabde12 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.yaml
@@ -23,13 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 73
@@ -124,7 +117,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8976-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8976-pinctrl.yaml
index ca95de0b87a6..d4391c194ff7 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8976-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8976-pinctrl.yaml
@@ -23,13 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 73
@@ -104,7 +97,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.yaml
index 41525ecfa8e3..fa90981db40b 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.yaml
@@ -25,13 +25,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 73
@@ -114,7 +107,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.yaml
index 59d406b60957..c5010c175b23 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.yaml
@@ -23,13 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 75
@@ -133,7 +126,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8998-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8998-pinctrl.yaml
index bd6d7caf499a..bcaa231adaf7 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8998-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8998-pinctrl.yaml
@@ -23,13 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 75
@@ -118,7 +111,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml
index 80f960671857..fe717d8d4798 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml
@@ -158,34 +158,40 @@ examples:
   - |
     #include <dt-bindings/pinctrl/qcom,pmic-mpp.h>
 
-    pm8841_mpp: mpps@a000 {
-      compatible = "qcom,pm8841-mpp", "qcom,spmi-mpp";
-      reg = <0xa000 0>;
-      gpio-controller;
-      #gpio-cells = <2>;
-      gpio-ranges = <&pm8841_mpp 0 0 4>;
-      gpio-line-names = "VDD_PX_BIAS", "WLAN_LED_CTRL",
-              "BT_LED_CTRL", "GPIO-F";
-      interrupt-controller;
-      #interrupt-cells = <2>;
-
-      pinctrl-names = "default";
-      pinctrl-0 = <&pm8841_default>;
-
-      mpp1-state {
-        pins = "mpp1";
-        function = "digital";
-        input-enable;
-        power-source = <PM8841_MPP_S3>;
-      };
-
-      default-state {
-        gpio-pins {
-          pins = "mpp1", "mpp2", "mpp3", "mpp4";
-          function = "digital";
-          input-enable;
-          power-source = <PM8841_MPP_S3>;
+    pmic {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        pm8841_mpp: mpps@a000 {
+            compatible = "qcom,pm8841-mpp", "qcom,spmi-mpp";
+            reg = <0xa000>;
+
+            gpio-controller;
+            #gpio-cells = <2>;
+            gpio-ranges = <&pm8841_mpp 0 0 4>;
+            gpio-line-names = "VDD_PX_BIAS", "WLAN_LED_CTRL",
+                              "BT_LED_CTRL", "GPIO-F";
+            interrupt-controller;
+            #interrupt-cells = <2>;
+
+            pinctrl-names = "default";
+            pinctrl-0 = <&pm8841_default>;
+
+            mpp1-state {
+                pins = "mpp1";
+                function = "digital";
+                input-enable;
+                power-source = <PM8841_MPP_S3>;
+            };
+
+            default-state {
+                gpio-pins {
+                    pins = "mpp1", "mpp2", "mpp3", "mpp4";
+                    function = "digital";
+                    input-enable;
+                    power-source = <PM8841_MPP_S3>;
+                };
+            };
         };
-      };
     };
 ...
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,qcm2290-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,qcm2290-tlmm.yaml
index c323f6d495a4..e123beb33aef 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,qcm2290-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,qcm2290-tlmm.yaml
@@ -22,13 +22,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
 patternProperties:
   "-state$":
     oneOf:
@@ -92,7 +85,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,qcs404-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,qcs404-pinctrl.yaml
index b1b9cd319e50..4009501b3414 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,qcs404-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,qcs404-pinctrl.yaml
@@ -29,13 +29,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 60
@@ -130,7 +123,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,qdu1000-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,qdu1000-tlmm.yaml
index 237cac4f6ce1..88afeae530c6 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,qdu1000-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,qdu1000-tlmm.yaml
@@ -23,10 +23,8 @@ properties:
   reg:
     maxItems: 1
 
-  interrupts: true
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
+  interrupts:
+    maxItems: 1
 
   gpio-reserved-ranges:
     minItems: 1
@@ -35,10 +33,6 @@ properties:
   gpio-line-names:
     maxItems: 151
 
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
 patternProperties:
   "-state$":
     oneOf:
@@ -101,7 +95,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml
index 2173c5255638..e9abbf2c0689 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml
@@ -22,13 +22,8 @@ properties:
   reg:
     maxItems: 1
 
-  interrupts: true
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
+  interrupts:
+    maxItems: 1
 
   gpio-reserved-ranges:
     minItems: 1
@@ -37,12 +32,6 @@ properties:
   gpio-line-names:
     maxItems: 148
 
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
-
 patternProperties:
   "-state$":
     oneOf:
@@ -108,6 +97,12 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sc7180-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sc7180-pinctrl.yaml
index 573e459b1c44..5606f2136ad1 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sc7180-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sc7180-pinctrl.yaml
@@ -29,13 +29,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 60
@@ -112,7 +105,7 @@ required:
   - reg
   - reg-names
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-lpass-lpi-pinctrl.yaml
index 00c5a00e35fc..08801cc4e476 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-lpass-lpi-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-lpass-lpi-pinctrl.yaml
@@ -20,16 +20,6 @@ properties:
   reg:
     maxItems: 2
 
-  gpio-controller: true
-
-  "#gpio-cells":
-    description: Specifying the pin number and flags, as defined in
-      include/dt-bindings/gpio/gpio.h
-    const: 2
-
-  gpio-ranges:
-    maxItems: 1
-
 patternProperties:
   "-state$":
     oneOf:
@@ -45,7 +35,8 @@ $defs:
     description:
       Pinctrl node's client devices use subnodes for desired pin configuration.
       Client device subnodes use below standard properties.
-    $ref: /schemas/pinctrl/pincfg-node.yaml
+    $ref: qcom,lpass-lpi-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
 
     properties:
       pins:
@@ -68,42 +59,14 @@ $defs:
           Specify the alternative function to be configured for the specified
           pins.
 
-      drive-strength:
-        enum: [2, 4, 6, 8, 10, 12, 14, 16]
-        default: 2
-        description:
-          Selects the drive strength for the specified pins, in mA.
-
-      slew-rate:
-        enum: [0, 1, 2, 3]
-        default: 0
-        description: |
-            0: No adjustments
-            1: Higher Slew rate (faster edges)
-            2: Lower Slew rate (slower edges)
-            3: Reserved (No adjustments)
-
-      bias-pull-down: true
-      bias-pull-up: true
-      bias-bus-hold: true
-      bias-disable: true
-      output-high: true
-      output-low: true
-
-    required:
-      - pins
-      - function
-
-    additionalProperties: false
-
 required:
   - compatible
   - reg
-  - gpio-controller
-  - "#gpio-cells"
-  - gpio-ranges
 
-additionalProperties: false
+allOf:
+  - $ref: qcom,lpass-lpi-common.yaml#
+
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-pinctrl.yaml
index c8735ab97e40..5329fe2a4397 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-pinctrl.yaml
@@ -23,24 +23,6 @@ properties:
     description: Specifies the TLMM summary IRQ
     maxItems: 1
 
-  interrupt-controller: true
-
-  '#interrupt-cells':
-    description:
-      Specifies the PIN numbers and Flags, as defined in defined in
-      include/dt-bindings/interrupt-controller/irq.h
-    const: 2
-
-  gpio-controller: true
-
-  '#gpio-cells':
-    description: Specifying the pin number and flags, as defined in
-      include/dt-bindings/gpio/gpio.h
-    const: 2
-
-  gpio-ranges:
-    maxItems: 1
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 88
@@ -48,8 +30,6 @@ properties:
   gpio-line-names:
     maxItems: 175
 
-  wakeup-parent: true
-
 patternProperties:
   "-state$":
     oneOf:
@@ -124,14 +104,8 @@ allOf:
 required:
   - compatible
   - reg
-  - interrupts
-  - interrupt-controller
-  - '#interrupt-cells'
-  - gpio-controller
-  - '#gpio-cells'
-  - gpio-ranges
-
-additionalProperties: false
+
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sc8180x-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sc8180x-tlmm.yaml
index b086a5184235..c122bb849f0f 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sc8180x-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sc8180x-tlmm.yaml
@@ -31,20 +31,7 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  '#interrupt-cells': true
-  gpio-controller: true
   gpio-reserved-ranges: true
-  '#gpio-cells': true
-  gpio-ranges: true
-  wakeup-parent: true
-
-required:
-  - compatible
-  - reg
-  - reg-names
-
-additionalProperties: false
 
 patternProperties:
   "-state$":
@@ -106,6 +93,13 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+  - reg-names
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-lpass-lpi-pinctrl.yaml
index a9167dac9ab5..240e6d45cc95 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-lpass-lpi-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-lpass-lpi-pinctrl.yaml
@@ -32,16 +32,6 @@ properties:
       - const: core
       - const: audio
 
-  gpio-controller: true
-
-  "#gpio-cells":
-    description: Specifying the pin number and flags, as defined in
-      include/dt-bindings/gpio/gpio.h
-    const: 2
-
-  gpio-ranges:
-    maxItems: 1
-
 patternProperties:
   "-state$":
     oneOf:
@@ -57,7 +47,8 @@ $defs:
     description:
       Pinctrl node's client devices use subnodes for desired pin configuration.
       Client device subnodes use below standard properties.
-    $ref: /schemas/pinctrl/pincfg-node.yaml
+    $ref: qcom,lpass-lpi-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
 
     properties:
       pins:
@@ -79,48 +70,16 @@ $defs:
           Specify the alternative function to be configured for the specified
           pins.
 
-      drive-strength:
-        enum: [2, 4, 6, 8, 10, 12, 14, 16]
-        default: 2
-        description:
-          Selects the drive strength for the specified pins, in mA.
-
-      slew-rate:
-        enum: [0, 1, 2, 3]
-        default: 0
-        description: |
-          0: No adjustments
-          1: Higher Slew rate (faster edges)
-          2: Lower Slew rate (slower edges)
-          3: Reserved (No adjustments)
-
-      bias-bus-hold: true
-      bias-pull-down: true
-      bias-pull-up: true
-      bias-disable: true
-      input-enable: true
-      output-high: true
-      output-low: true
-
-    required:
-      - pins
-      - function
-
-    additionalProperties: false
-
 allOf:
-  - $ref: pinctrl.yaml#
+  - $ref: qcom,lpass-lpi-common.yaml#
 
 required:
   - compatible
   - reg
   - clocks
   - clock-names
-  - gpio-controller
-  - "#gpio-cells"
-  - gpio-ranges
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-tlmm.yaml
index 4bd6d7977d3e..ed344deaf8b9 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-tlmm.yaml
@@ -25,19 +25,7 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
   gpio-reserved-ranges: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
 
 patternProperties:
   "-state$":
@@ -108,6 +96,12 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sdm630-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sdm630-pinctrl.yaml
index 508e0633b253..a00cb43df144 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sdm630-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sdm630-pinctrl.yaml
@@ -34,10 +34,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 57
@@ -45,10 +41,6 @@ properties:
   gpio-line-names:
     maxItems: 114
 
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
 patternProperties:
   "-state$":
     oneOf:
@@ -130,7 +122,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sdm670-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sdm670-tlmm.yaml
index 84a15f77e710..b56e717aa28e 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sdm670-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sdm670-tlmm.yaml
@@ -25,23 +25,10 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 75
 
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
-
 patternProperties:
   "-state$":
     oneOf:
@@ -98,6 +85,12 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sdm845-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sdm845-pinctrl.yaml
index d301881ddfa8..dfe5616b9b85 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sdm845-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sdm845-pinctrl.yaml
@@ -26,10 +26,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 75
@@ -37,10 +33,6 @@ properties:
   gpio-line-names:
     maxItems: 150
 
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
 patternProperties:
   "-state$":
     oneOf:
@@ -110,7 +102,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sdx55-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sdx55-pinctrl.yaml
index 67af99dd8f14..edbcff92bbf9 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sdx55-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sdx55-pinctrl.yaml
@@ -23,12 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-
   gpio-reserved-ranges:
     maxItems: 1
 
@@ -102,7 +96,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sdx65-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sdx65-tlmm.yaml
index 27319782d94b..a31b638c456d 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sdx65-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sdx65-tlmm.yaml
@@ -22,12 +22,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-
   gpio-reserved-ranges:
     maxItems: 1
 
@@ -122,7 +116,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sdx75-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sdx75-tlmm.yaml
index 7cb96aa75b08..cb1d978d02c9 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sdx75-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sdx75-tlmm.yaml
@@ -22,10 +22,8 @@ properties:
   reg:
     maxItems: 1
 
-  interrupts: true
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
+  interrupts:
+    maxItems: 1
 
   gpio-reserved-ranges:
     minItems: 1
@@ -34,10 +32,6 @@ properties:
   gpio-line-names:
     maxItems: 133
 
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
 patternProperties:
   "-state$":
     oneOf:
@@ -100,7 +94,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm4450-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm4450-tlmm.yaml
new file mode 100644
index 000000000000..bb08ca5a1509
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm4450-tlmm.yaml
@@ -0,0 +1,151 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/qcom,sm4450-tlmm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Technologies, Inc. SM4450 TLMM block
+
+maintainers:
+  - Tengfei Fan <quic_tengfan@quicinc.com>
+
+description:
+  Top Level Mode Multiplexer pin controller in Qualcomm SM4450 SoC.
+
+allOf:
+  - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml#
+
+properties:
+  compatible:
+    const: qcom,sm4450-pinctrl
+
+  reg:
+    maxItems: 1
+
+  interrupts: true
+  interrupt-controller: true
+  "#interrupt-cells": true
+  gpio-controller: true
+
+  gpio-reserved-ranges:
+    minItems: 1
+    maxItems: 68
+
+  gpio-line-names:
+    maxItems: 136
+
+  "#gpio-cells": true
+  gpio-ranges: true
+  wakeup-parent: true
+
+patternProperties:
+  "-state$":
+    oneOf:
+      - $ref: "#/$defs/qcom-sm4450-tlmm-state"
+      - patternProperties:
+          "-pins$":
+            $ref: "#/$defs/qcom-sm4450-tlmm-state"
+        additionalProperties: false
+
+$defs:
+  qcom-sm4450-tlmm-state:
+    type: object
+    description:
+      Pinctrl node's client devices use subnodes for desired pin configuration.
+      Client device subnodes use below standard properties.
+    $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
+
+    properties:
+      pins:
+        description:
+          List of gpio pins affected by the properties specified in this
+          subnode.
+        items:
+          oneOf:
+            - pattern: "^gpio([0-9]|[1-9][0-9]|1[0-2][0-9]|13[0-5])$"
+            - enum: [ sdc2_clk, sdc2_cmd, sdc2_data, ufs_reset ]
+          minItems: 1
+          maxItems: 36
+
+      function:
+        description:
+          Specify the alternative function to be configured for the specified
+          pins.
+        enum: [ gpio, atest_char, atest_char0, atest_char1, atest_char2,
+                atest_char3, atest_usb0, atest_usb00, atest_usb01, atest_usb02,
+                atest_usb03, audio_ref, cam_mclk, cci_async, cci_i2c,
+                cci_timer0, cci_timer1, cci_timer2, cci_timer3, cci_timer4,
+                cmu_rng0, cmu_rng1, cmu_rng2, cmu_rng3, coex_uart1, cri_trng,
+                cri_trng0, cri_trng1, dbg_out, ddr_bist, ddr_pxi0, ddr_pxi1,
+                dp0_hot, gcc_gp1, gcc_gp2, gcc_gp3, host2wlan_sol, ibi_i3c,
+                jitter_bist, mdp_vsync, mdp_vsync0, mdp_vsync1, mdp_vsync2,
+                mdp_vsync3, mi2s0_data0, mi2s0_data1, mi2s0_sck, mi2s0_ws,
+                mi2s2_data0, mi2s2_data1, mi2s2_sck, mi2s2_ws, mi2s_mclk0,
+                mi2s_mclk1, nav_gpio0, nav_gpio1, nav_gpio2, pcie0_clk,
+                phase_flag0, phase_flag1, phase_flag10, phase_flag11,
+                phase_flag12, phase_flag13, phase_flag14, phase_flag15,
+                phase_flag16, phase_flag17, phase_flag18, phase_flag19,
+                phase_flag2, phase_flag20, phase_flag21, phase_flag22,
+                phase_flag23, phase_flag24, phase_flag25, phase_flag26,
+                phase_flag27, phase_flag28, phase_flag29, phase_flag3,
+                phase_flag30, phase_flag31, phase_flag4, phase_flag5,
+                phase_flag6, phase_flag7, phase_flag8, phase_flag9,
+                pll_bist, pll_clk, prng_rosc0, prng_rosc1, prng_rosc2,
+                prng_rosc3, qdss_cti, qdss_gpio, qdss_gpio0, qdss_gpio1,
+                qdss_gpio10, qdss_gpio11, qdss_gpio12, qdss_gpio13, qdss_gpio14,
+                qdss_gpio15, qdss_gpio2, qdss_gpio3, qdss_gpio4, qdss_gpio5,
+                qdss_gpio6, qdss_gpio7, qdss_gpio8, qdss_gpio9, qlink0_enable,
+                qlink0_request, qlink0_wmss, qlink1_enable, qlink1_request,
+                qlink1_wmss, qlink2_enable, qlink2_request, qlink2_wmss,
+                qup0_se0, qup0_se1, qup0_se2, qup0_se3, qup0_se4, qup0_se5,
+                qup0_se6, qup0_se7, qup1_se0, qup1_se1, qup1_se2, qup1_se3,
+                qup1_se4, qup1_se5, qup1_se6, sd_write, tb_trig, tgu_ch0,
+                tgu_ch1, tgu_ch2, tgu_ch3, tmess_prng0, tmess_prng1,
+                tmess_prng2, tmess_prng3, tsense_pwm1, tsense_pwm2, uim0_clk,
+                uim0_data, uim0_present, uim0_reset, uim1_clk, uim1_data,
+                uim1_present, uim1_reset, usb0_hs, usb0_phy, vfr_0, vfr_1,
+                vsense_trigger ]
+
+        required:
+          - pins
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    tlmm: pinctrl@f100000 {
+        compatible = "qcom,sm4450-tlmm";
+        reg = <0x0f100000 0x300000>;
+        gpio-controller;
+        #gpio-cells = <2>;
+        gpio-ranges = <&tlmm 0 0 137>;
+        interrupt-controller;
+        #interrupt-cells = <2>;
+        interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
+
+        gpio-wo-state {
+            pins = "gpio1";
+            function = "gpio";
+        };
+
+        uart-w-state {
+            rx-pins {
+                pins = "gpio23";
+                function = "qup1_se2";
+                bias-pull-up;
+            };
+
+            tx-pins {
+                pins = "gpio22";
+                function = "qup1_se2";
+                bias-disable;
+            };
+        };
+    };
+...
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm6115-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm6115-lpass-lpi-pinctrl.yaml
index abac3311fc55..f4cf2ce86fcd 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm6115-lpass-lpi-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm6115-lpass-lpi-pinctrl.yaml
@@ -31,16 +31,6 @@ properties:
     items:
       - const: audio
 
-  gpio-controller: true
-
-  "#gpio-cells":
-    description: Specifying the pin number and flags, as defined in
-      include/dt-bindings/gpio/gpio.h
-    const: 2
-
-  gpio-ranges:
-    maxItems: 1
-
 patternProperties:
   "-state$":
     oneOf:
@@ -56,7 +46,8 @@ $defs:
     description:
       Pinctrl node's client devices use subnodes for desired pin configuration.
       Client device subnodes use below standard properties.
-    $ref: /schemas/pinctrl/pincfg-node.yaml
+    $ref: qcom,lpass-lpi-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
 
     properties:
       pins:
@@ -75,48 +66,17 @@ $defs:
           Specify the alternative function to be configured for the specified
           pins.
 
-      drive-strength:
-        enum: [2, 4, 6, 8, 10, 12, 14, 16]
-        default: 2
-        description:
-          Selects the drive strength for the specified pins, in mA.
-
-      slew-rate:
-        enum: [0, 1, 2, 3]
-        default: 0
-        description: |
-          0: No adjustments
-          1: Higher Slew rate (faster edges)
-          2: Lower Slew rate (slower edges)
-          3: Reserved (No adjustments)
-
-      bias-bus-hold: true
-      bias-pull-down: true
-      bias-pull-up: true
-      bias-disable: true
-      input-enable: true
-      output-high: true
-      output-low: true
-
-    required:
-      - pins
-      - function
-
-    additionalProperties: false
 
 allOf:
-  - $ref: pinctrl.yaml#
+  - $ref: qcom,lpass-lpi-common.yaml#
 
 required:
   - compatible
   - reg
   - clocks
   - clock-names
-  - gpio-controller
-  - "#gpio-cells"
-  - gpio-ranges
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm6115-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm6115-tlmm.yaml
index 871df54f69a2..7f36f9b93333 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm6115-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm6115-tlmm.yaml
@@ -29,13 +29,7 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
   gpio-reserved-ranges: true
-  wakeup-parent: true
 
 patternProperties:
   "-state$":
@@ -97,7 +91,7 @@ required:
   - reg
   - reg-names
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm6125-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm6125-tlmm.yaml
index 8d77707b02b9..ddeaeaa9a450 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm6125-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm6125-tlmm.yaml
@@ -30,20 +30,7 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
   gpio-reserved-ranges: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
-required:
-  - compatible
-  - reg
-  - reg-names
-
-additionalProperties: false
 
 patternProperties:
   "-state$":
@@ -105,6 +92,13 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+  - reg-names
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml
index 27af379cf791..a4771f87d936 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml
@@ -26,10 +26,6 @@ properties:
     minItems: 9
     maxItems: 9
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 78
@@ -37,16 +33,6 @@ properties:
   gpio-line-names:
     maxItems: 156
 
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
-
 patternProperties:
   "-state$":
     oneOf:
@@ -112,6 +98,12 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml
index 6e02ba24825f..047f82863f9b 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml
@@ -25,19 +25,7 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
   gpio-reserved-ranges: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
 
 patternProperties:
   "-state$":
@@ -113,6 +101,12 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm7150-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm7150-tlmm.yaml
index ede0f3acad9c..7f23f939ad32 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm7150-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm7150-tlmm.yaml
@@ -32,13 +32,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 60
@@ -111,7 +104,7 @@ required:
   - reg
   - reg-names
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8150-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8150-pinctrl.yaml
index c6439626464e..bdb7ed4be026 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8150-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8150-pinctrl.yaml
@@ -30,13 +30,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 88
@@ -113,7 +106,7 @@ required:
   - reg
   - reg-names
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-lpass-lpi-pinctrl.yaml
index 4b4be7efc150..750c996c10a7 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-lpass-lpi-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-lpass-lpi-pinctrl.yaml
@@ -30,16 +30,6 @@ properties:
       - const: core
       - const: audio
 
-  gpio-controller: true
-
-  "#gpio-cells":
-    description: Specifying the pin number and flags, as defined in
-      include/dt-bindings/gpio/gpio.h
-    const: 2
-
-  gpio-ranges:
-    maxItems: 1
-
 patternProperties:
   "-state$":
     oneOf:
@@ -55,7 +45,8 @@ $defs:
     description:
       Pinctrl node's client devices use subnodes for desired pin configuration.
       Client device subnodes use below standard properties.
-    $ref: /schemas/pinctrl/pincfg-node.yaml
+    $ref: qcom,lpass-lpi-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
 
     properties:
       pins:
@@ -78,48 +69,16 @@ $defs:
           Specify the alternative function to be configured for the specified
           pins.
 
-      drive-strength:
-        enum: [2, 4, 6, 8, 10, 12, 14, 16]
-        default: 2
-        description:
-          Selects the drive strength for the specified pins, in mA.
-
-      slew-rate:
-        enum: [0, 1, 2, 3]
-        default: 0
-        description: |
-            0: No adjustments
-            1: Higher Slew rate (faster edges)
-            2: Lower Slew rate (slower edges)
-            3: Reserved (No adjustments)
-
-      bias-pull-down: true
-      bias-pull-up: true
-      bias-bus-hold: true
-      bias-disable: true
-      input-enable: true
-      output-high: true
-      output-low: true
-
-    required:
-      - pins
-      - function
-
-    additionalProperties: false
-
 allOf:
-  - $ref: pinctrl.yaml#
+  - $ref: qcom,lpass-lpi-common.yaml#
 
 required:
   - compatible
   - reg
   - clocks
   - clock-names
-  - gpio-controller
-  - "#gpio-cells"
-  - gpio-ranges
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-pinctrl.yaml
index 021c54708524..b5d04347c064 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-pinctrl.yaml
@@ -28,13 +28,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 90
@@ -106,7 +99,7 @@ required:
   - reg
   - reg-names
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8350-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8350-lpass-lpi-pinctrl.yaml
index 2e65ae08dd21..9d782f910b31 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8350-lpass-lpi-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8350-lpass-lpi-pinctrl.yaml
@@ -33,16 +33,6 @@ properties:
       - const: core
       - const: audio
 
-  gpio-controller: true
-
-  "#gpio-cells":
-    description: Specifying the pin number and flags, as defined in
-      include/dt-bindings/gpio/gpio.h
-    const: 2
-
-  gpio-ranges:
-    maxItems: 1
-
 patternProperties:
   "-state$":
     oneOf:
@@ -58,7 +48,8 @@ $defs:
     description:
       Pinctrl node's client devices use subnodes for desired pin configuration.
       Client device subnodes use below standard properties.
-    $ref: /schemas/pinctrl/pincfg-node.yaml
+    $ref: qcom,lpass-lpi-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
 
     properties:
       pins:
@@ -81,48 +72,16 @@ $defs:
           Specify the alternative function to be configured for the specified
           pins.
 
-      drive-strength:
-        enum: [2, 4, 6, 8, 10, 12, 14, 16]
-        default: 2
-        description:
-          Selects the drive strength for the specified pins, in mA.
-
-      slew-rate:
-        enum: [0, 1, 2, 3]
-        default: 0
-        description: |
-          0: No adjustments
-          1: Higher Slew rate (faster edges)
-          2: Lower Slew rate (slower edges)
-          3: Reserved (No adjustments)
-
-      bias-bus-hold: true
-      bias-pull-down: true
-      bias-pull-up: true
-      bias-disable: true
-      input-enable: true
-      output-high: true
-      output-low: true
-
-    required:
-      - pins
-      - function
-
-    additionalProperties: false
-
 allOf:
-  - $ref: pinctrl.yaml#
+  - $ref: qcom,lpass-lpi-common.yaml#
 
 required:
   - compatible
   - reg
   - clocks
   - clock-names
-  - gpio-controller
-  - "#gpio-cells"
-  - gpio-ranges
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8350-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8350-tlmm.yaml
index 6e8f41ff0a76..ec5e09611d81 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8350-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8350-tlmm.yaml
@@ -25,10 +25,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 102
@@ -36,16 +32,6 @@ properties:
   gpio-line-names:
     maxItems: 203
 
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
-
 patternProperties:
   "-state$":
     oneOf:
@@ -108,6 +94,12 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-lpass-lpi-pinctrl.yaml
index 1eefa9aa6a86..e7565592da86 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-lpass-lpi-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-lpass-lpi-pinctrl.yaml
@@ -32,16 +32,6 @@ properties:
       - const: core
       - const: audio
 
-  gpio-controller: true
-
-  "#gpio-cells":
-    description: Specifying the pin number and flags, as defined in
-      include/dt-bindings/gpio/gpio.h
-    const: 2
-
-  gpio-ranges:
-    maxItems: 1
-
 patternProperties:
   "-state$":
     oneOf:
@@ -57,7 +47,8 @@ $defs:
     description:
       Pinctrl node's client devices use subnodes for desired pin configuration.
       Client device subnodes use below standard properties.
-    $ref: /schemas/pinctrl/pincfg-node.yaml
+    $ref: qcom,lpass-lpi-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
 
     properties:
       pins:
@@ -81,48 +72,16 @@ $defs:
           Specify the alternative function to be configured for the specified
           pins.
 
-      drive-strength:
-        enum: [2, 4, 6, 8, 10, 12, 14, 16]
-        default: 2
-        description:
-          Selects the drive strength for the specified pins, in mA.
-
-      slew-rate:
-        enum: [0, 1, 2, 3]
-        default: 0
-        description: |
-          0: No adjustments
-          1: Higher Slew rate (faster edges)
-          2: Lower Slew rate (slower edges)
-          3: Reserved (No adjustments)
-
-      bias-bus-hold: true
-      bias-pull-down: true
-      bias-pull-up: true
-      bias-disable: true
-      input-enable: true
-      output-high: true
-      output-low: true
-
-    required:
-      - pins
-      - function
-
-    additionalProperties: false
-
 allOf:
-  - $ref: pinctrl.yaml#
+  - $ref: qcom,lpass-lpi-common.yaml#
 
 required:
   - compatible
   - reg
   - clocks
   - clock-names
-  - gpio-controller
-  - "#gpio-cells"
-  - gpio-ranges
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-tlmm.yaml
index 5163fe3f5365..16fd2c5e2339 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-tlmm.yaml
@@ -25,10 +25,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 105
@@ -36,16 +32,6 @@ properties:
   gpio-line-names:
     maxItems: 210
 
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
-
 patternProperties:
   "-state$":
     oneOf:
@@ -107,6 +93,12 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-lpass-lpi-pinctrl.yaml
index ef9743246849..bf4a72facae1 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-lpass-lpi-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-lpass-lpi-pinctrl.yaml
@@ -16,7 +16,11 @@ description:
 
 properties:
   compatible:
-    const: qcom,sm8550-lpass-lpi-pinctrl
+    oneOf:
+      - const: qcom,sm8550-lpass-lpi-pinctrl
+      - items:
+          - const: qcom,x1e80100-lpass-lpi-pinctrl
+          - const: qcom,sm8550-lpass-lpi-pinctrl
 
   reg:
     items:
@@ -33,16 +37,6 @@ properties:
       - const: core
       - const: audio
 
-  gpio-controller: true
-
-  "#gpio-cells":
-    description: Specifying the pin number and flags, as defined in
-      include/dt-bindings/gpio/gpio.h
-    const: 2
-
-  gpio-ranges:
-    maxItems: 1
-
 patternProperties:
   "-state$":
     oneOf:
@@ -58,7 +52,8 @@ $defs:
     description:
       Pinctrl node's client devices use subnodes for desired pin configuration.
       Client device subnodes use below standard properties.
-    $ref: /schemas/pinctrl/pincfg-node.yaml
+    $ref: qcom,lpass-lpi-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
 
     properties:
       pins:
@@ -81,48 +76,16 @@ $defs:
           Specify the alternative function to be configured for the specified
           pins.
 
-      drive-strength:
-        enum: [2, 4, 6, 8, 10, 12, 14, 16]
-        default: 2
-        description:
-          Selects the drive strength for the specified pins, in mA.
-
-      slew-rate:
-        enum: [0, 1, 2, 3]
-        default: 0
-        description: |
-          0: No adjustments
-          1: Higher Slew rate (faster edges)
-          2: Lower Slew rate (slower edges)
-          3: Reserved (No adjustments)
-
-      bias-bus-hold: true
-      bias-pull-down: true
-      bias-pull-up: true
-      bias-disable: true
-      input-enable: true
-      output-high: true
-      output-low: true
-
-    required:
-      - pins
-      - function
-
-    additionalProperties: false
-
 allOf:
-  - $ref: pinctrl.yaml#
+  - $ref: qcom,lpass-lpi-common.yaml#
 
 required:
   - compatible
   - reg
   - clocks
   - clock-names
-  - gpio-controller
-  - "#gpio-cells"
-  - gpio-ranges
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-tlmm.yaml
index f789c7753a92..c2ae79df424f 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-tlmm.yaml
@@ -22,10 +22,8 @@ properties:
   reg:
     maxItems: 1
 
-  interrupts: true
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
+  interrupts:
+    maxItems: 1
 
   gpio-reserved-ranges:
     minItems: 1
@@ -34,10 +32,6 @@ properties:
   gpio-line-names:
     maxItems: 210
 
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
 patternProperties:
   "-state$":
     oneOf:
@@ -117,7 +111,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-lpass-lpi-pinctrl.yaml
new file mode 100644
index 000000000000..db7214362301
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-lpass-lpi-pinctrl.yaml
@@ -0,0 +1,107 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/qcom,sm8650-lpass-lpi-pinctrl.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm SM8650 SoC LPASS LPI TLMM
+
+maintainers:
+  - Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+  - Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+
+description:
+  Top Level Mode Multiplexer pin controller in the Low Power Audio SubSystem
+  (LPASS) Low Power Island (LPI) of Qualcomm SM8650 SoC.
+
+properties:
+  compatible:
+    const: qcom,sm8650-lpass-lpi-pinctrl
+
+  reg:
+    items:
+      - description: LPASS LPI TLMM Control and Status registers
+
+  clocks:
+    items:
+      - description: LPASS Core voting clock
+      - description: LPASS Audio voting clock
+
+  clock-names:
+    items:
+      - const: core
+      - const: audio
+
+patternProperties:
+  "-state$":
+    oneOf:
+      - $ref: "#/$defs/qcom-sm8650-lpass-state"
+      - patternProperties:
+          "-pins$":
+            $ref: "#/$defs/qcom-sm8650-lpass-state"
+        additionalProperties: false
+
+$defs:
+  qcom-sm8650-lpass-state:
+    type: object
+    description:
+      Pinctrl node's client devices use subnodes for desired pin configuration.
+      Client device subnodes use below standard properties.
+    $ref: qcom,lpass-lpi-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
+
+    properties:
+      pins:
+        description:
+          List of gpio pins affected by the properties specified in this
+          subnode.
+        items:
+          pattern: "^gpio([0-9]|1[0-9]|2[0-2])$"
+
+      function:
+        enum: [ dmic1_clk, dmic1_data, dmic2_clk, dmic2_data, dmic3_clk,
+                dmic3_data, dmic4_clk, dmic4_data, ext_mclk1_a, ext_mclk1_b,
+                ext_mclk1_c, ext_mclk1_d, ext_mclk1_e, gpio, i2s0_clk,
+                i2s0_data, i2s0_ws, i2s1_clk, i2s1_data, i2s1_ws, i2s2_clk,
+                i2s2_data, i2s2_ws, i2s3_clk, i2s3_data, i2s3_ws, i2s4_clk,
+                i2s4_data, i2s4_ws, qca_swr_clk, qca_swr_data, slimbus_clk,
+                slimbus_data, swr_rx_clk, swr_rx_data, swr_tx_clk, swr_tx_data,
+                wsa_swr_clk, wsa_swr_data, wsa2_swr_clk, wsa2_swr_data ]
+        description:
+          Specify the alternative function to be configured for the specified
+          pins.
+
+allOf:
+  - $ref: qcom,lpass-lpi-common.yaml#
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/sound/qcom,q6dsp-lpass-ports.h>
+
+    lpass_tlmm: pinctrl@6e80000 {
+        compatible = "qcom,sm8650-lpass-lpi-pinctrl";
+        reg = <0x06e80000 0x20000>;
+
+        clocks = <&q6prmcc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+                 <&q6prmcc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>;
+        clock-names = "core", "audio";
+
+        gpio-controller;
+        #gpio-cells = <2>;
+        gpio-ranges = <&lpass_tlmm 0 0 23>;
+
+        tx-swr-sleep-clk-state {
+            pins = "gpio0";
+            function = "swr_tx_clk";
+            drive-strength = <2>;
+            bias-pull-down;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-tlmm.yaml
new file mode 100644
index 000000000000..c0a06abf851d
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-tlmm.yaml
@@ -0,0 +1,141 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/qcom,sm8650-tlmm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Technologies, Inc. SM8650 TLMM block
+
+maintainers:
+  - Bjorn Andersson <andersson@kernel.org>
+
+description:
+  Top Level Mode Multiplexer pin controller in Qualcomm SM8650 SoC.
+
+allOf:
+  - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml#
+
+properties:
+  compatible:
+    const: qcom,sm8650-tlmm
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  gpio-reserved-ranges:
+    minItems: 1
+    maxItems: 105
+
+  gpio-line-names:
+    maxItems: 210
+
+patternProperties:
+  "-state$":
+    oneOf:
+      - $ref: "#/$defs/qcom-sm8650-tlmm-state"
+      - patternProperties:
+          "-pins$":
+            $ref: "#/$defs/qcom-sm8650-tlmm-state"
+        additionalProperties: false
+
+$defs:
+  qcom-sm8650-tlmm-state:
+    type: object
+    description:
+      Pinctrl node's client devices use subnodes for desired pin configuration.
+      Client device subnodes use below standard properties.
+    $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
+
+    properties:
+      pins:
+        description:
+          List of gpio pins affected by the properties specified in this
+          subnode.
+        items:
+          oneOf:
+            - pattern: "^gpio([0-9]|[1-9][0-9]|1[0-9][0-9]|20[0-9])$"
+            - enum: [ ufs_reset, sdc2_clk, sdc2_cmd, sdc2_data ]
+        minItems: 1
+        maxItems: 36
+
+      function:
+        description:
+          Specify the alternative function to be configured for the specified
+          pins.
+        enum: [ gpio, aoss_cti, atest_char, atest_usb, audio_ext_mclk0,
+                audio_ext_mclk1, audio_ref_clk, cam_aon_mclk2, cam_aon_mclk4,
+                cam_mclk, cci_async_in, cci_i2c_scl, cci_i2c_sda, cci_timer,
+                cmu_rng, coex_uart1_rx, coex_uart1_tx, coex_uart2_rx,
+                coex_uart2_tx, cri_trng, dbg_out_clk, ddr_bist_complete,
+                ddr_bist_fail, ddr_bist_start, ddr_bist_stop, ddr_pxi0,
+                ddr_pxi1, ddr_pxi2, ddr_pxi3, do_not, dp_hot, gcc_gp1,
+                gcc_gp2, gcc_gp3, gnss_adc0, gnss_adc1, i2chub0_se0,
+                i2chub0_se1, i2chub0_se2, i2chub0_se3, i2chub0_se4,
+                i2chub0_se5, i2chub0_se6, i2chub0_se7, i2chub0_se8,
+                i2chub0_se9, i2s0_data0, i2s0_data1, i2s0_sck, i2s0_ws,
+                i2s1_data0, i2s1_data1, i2s1_sck, i2s1_ws, ibi_i3c,
+                jitter_bist, mdp_vsync, mdp_vsync0_out, mdp_vsync1_out,
+                mdp_vsync2_out, mdp_vsync3_out, mdp_vsync_e, nav_gpio0,
+                nav_gpio1, nav_gpio2, nav_gpio3, pcie0_clk_req_n,
+                pcie1_clk_req_n, phase_flag, pll_bist_sync, pll_clk_aux,
+                prng_rosc0, prng_rosc1, prng_rosc2, prng_rosc3, qdss_cti,
+                qdss_gpio, qlink_big_enable, qlink_big_request,
+                qlink_little_enable, qlink_little_request, qlink_wmss,
+                qspi0, qspi1, qspi2, qspi3, qspi_clk, qspi_cs, qup1_se0,
+                qup1_se1, qup1_se2, qup1_se3, qup1_se4, qup1_se5, qup1_se6,
+                qup1_se7, qup2_se0, qup2_se1, qup2_se2, qup2_se3, qup2_se4,
+                qup2_se5, qup2_se6, qup2_se7, sd_write_protect, sdc40, sdc41,
+                sdc42, sdc43, sdc4_clk, sdc4_cmd, tb_trig_sdc2, tb_trig_sdc4,
+                tgu_ch0_trigout, tgu_ch1_trigout, tgu_ch2_trigout,
+                tgu_ch3_trigout, tmess_prng0, tmess_prng1, tmess_prng2,
+                tmess_prng3, tsense_pwm1, tsense_pwm2, tsense_pwm3, uim0_clk,
+                uim0_data, uim0_present, uim0_reset, uim1_clk, uim1_data,
+                uim1_present, uim1_reset, usb1_hs, usb_phy, vfr_0, vfr_1,
+                vsense_trigger_mirnat ]
+
+    required:
+      - pins
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    tlmm: pinctrl@f100000 {
+        compatible = "qcom,sm8650-tlmm";
+        reg = <0x0f100000 0x300000>;
+        gpio-controller;
+        #gpio-cells = <2>;
+        gpio-ranges = <&tlmm 0 0 211>;
+        interrupt-controller;
+        #interrupt-cells = <2>;
+        interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
+
+        gpio-wo-state {
+            pins = "gpio1";
+            function = "gpio";
+        };
+
+        uart-w-state {
+            rx-pins {
+                pins = "gpio60";
+                function = "qup1_se7";
+                bias-pull-up;
+            };
+
+            tx-pins {
+                pins = "gpio61";
+                function = "qup1_se7";
+                bias-disable;
+            };
+        };
+    };
+...
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,x1e80100-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,x1e80100-tlmm.yaml
new file mode 100644
index 000000000000..a1333e0743a9
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,x1e80100-tlmm.yaml
@@ -0,0 +1,137 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/qcom,x1e80100-tlmm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Technologies, Inc. X1E80100 TLMM block
+
+maintainers:
+  - Rajendra Nayak <quic_rjendra@quicinc.com>
+
+description:
+  Top Level Mode Multiplexer pin controller in Qualcomm X1E80100 SoC.
+
+allOf:
+  - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml#
+
+properties:
+  compatible:
+    const: qcom,x1e80100-tlmm
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  gpio-reserved-ranges:
+    minItems: 1
+    maxItems: 119
+
+  gpio-line-names:
+    maxItems: 238
+
+patternProperties:
+  "-state$":
+    oneOf:
+      - $ref: "#/$defs/qcom-x1e80100-tlmm-state"
+      - patternProperties:
+          "-pins$":
+            $ref: "#/$defs/qcom-x1e80100-tlmm-state"
+        additionalProperties: false
+
+$defs:
+  qcom-x1e80100-tlmm-state:
+    type: object
+    description:
+      Pinctrl node's client devices use subnodes for desired pin configuration.
+      Client device subnodes use below standard properties.
+    $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
+
+    properties:
+      pins:
+        description:
+          List of gpio pins affected by the properties specified in this
+          subnode.
+        items:
+          oneOf:
+            - pattern: "^gpio([0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-2][0-9]|23[0-7])$"
+            - enum: [ ufs_reset, sdc2_clk, sdc2_cmd, sdc2_data ]
+        minItems: 1
+        maxItems: 36
+
+      function:
+        description:
+          Specify the alternative function to be configured for the specified
+          pins.
+        enum: [ aon_cci, aoss_cti, atest_char, atest_char0,
+                atest_char1, atest_char2, atest_char3, atest_usb,
+                audio_ext, audio_ref, cam_aon, cam_mclk, cci_async,
+                cci_i2c, cci_timer0, cci_timer1, cci_timer2, cci_timer3,
+                cci_timer4, cmu_rng0, cmu_rng1, cmu_rng2, cmu_rng3,
+                cri_trng, dbg_out, ddr_bist, ddr_pxi0, ddr_pxi1,
+                ddr_pxi2, ddr_pxi3, ddr_pxi4, ddr_pxi5, ddr_pxi6, ddr_pxi7,
+                edp0_hot, edp0_lcd, edp1_hot, edp1_lcd, eusb0_ac, eusb1_ac,
+                eusb2_ac, eusb3_ac, eusb5_ac, eusb6_ac, gcc_gp1, gcc_gp2,
+                gcc_gp3, gpio, i2s0_data0, i2s0_data1, i2s0_sck, i2s0_ws, i2s1_data0,
+                i2s1_data1, i2s1_sck, i2s1_ws, ibi_i3c, jitter_bist, mdp_vsync0,
+                mdp_vsync1, mdp_vsync2, mdp_vsync3, mdp_vsync4, mdp_vsync5,
+                mdp_vsync6, mdp_vsync7, mdp_vsync8, pcie3_clk, pcie4_clk,
+                pcie5_clk, pcie6a_clk, pcie6b_clk, phase_flag, pll_bist, pll_clk,
+                prng_rosc0, prng_rosc1, prng_rosc2, prng_rosc3, qdss_cti,
+                qdss_gpio, qspi00, qspi01, qspi02, qspi03, qspi0_clk, qspi0_cs0,
+                qspi0_cs1, qup0_se0, qup0_se1, qup0_se2, qup0_se3, qup0_se4,
+                qup0_se5, qup0_se6, qup0_se7, qup1_se0, qup1_se1, qup1_se2, qup1_se3,
+                qup1_se4, qup1_se5, qup1_se6, qup1_se7, qup2_se0, qup2_se1, qup2_se2,
+                qup2_se3, qup2_se4, qup2_se5, qup2_se6, qup2_se7, sd_write, sdc4_clk,
+                sdc4_cmd, sdc4_data0, sdc4_data1, sdc4_data2, sdc4_data3, sys_throttle,
+                tb_trig, tgu_ch0, tgu_ch1, tgu_ch2, tgu_ch3, tgu_ch4, tgu_ch5,
+                tgu_ch6, tgu_ch7, tmess_prng0, tmess_prng1, tmess_prng2, tmess_prng3,
+                tsense_pwm1, tsense_pwm2, sense_pwm3, tsense_pwm4, usb0_dp, usb0_phy,
+                usb0_sbrx, usb0_sbtx, usb1_dp, usb1_phy, usb1_sbrx, usb1_sbtx,
+                usb2_dp, usb2_phy, usb2_sbrx, usb2_sbtx, vsense_trigger ]
+
+    required:
+      - pins
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    tlmm: pinctrl@f100000 {
+        compatible = "qcom,x1e80100-tlmm";
+        reg = <0x0f100000 0xf00000>;
+        gpio-controller;
+        #gpio-cells = <2>;
+        gpio-ranges = <&tlmm 0 0 239>;
+        interrupt-controller;
+        #interrupt-cells = <2>;
+        interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
+
+        gpio-wo-state {
+            pins = "gpio1";
+            function = "gpio";
+        };
+
+        uart-w-state {
+            rx-pins {
+                pins = "gpio26";
+                function = "qup2_se7";
+                bias-pull-up;
+            };
+
+            tx-pins {
+                pins = "gpio27";
+                function = "qup2_se7";
+                bias-disable;
+            };
+        };
+    };
+...
diff --git a/Documentation/devicetree/bindings/pinctrl/renesas,rza2-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/renesas,rza2-pinctrl.yaml
index 8271e7b2c162..8b8e4e1a000f 100644
--- a/Documentation/devicetree/bindings/pinctrl/renesas,rza2-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/renesas,rza2-pinctrl.yaml
@@ -20,7 +20,7 @@ description:
 
 properties:
   compatible:
-    const: "renesas,r7s9210-pinctrl" # RZ/A2M
+    const: renesas,r7s9210-pinctrl # RZ/A2M
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
index 1de91a51234d..4dfb49b0e07f 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
@@ -28,15 +28,27 @@ description: |
 
 properties:
   compatible:
-    enum:
-      - samsung,s3c2410-wakeup-eint
-      - samsung,s3c2412-wakeup-eint
-      - samsung,s3c64xx-wakeup-eint
-      - samsung,s5pv210-wakeup-eint
-      - samsung,exynos4210-wakeup-eint
-      - samsung,exynos7-wakeup-eint
-      - samsung,exynos850-wakeup-eint
-      - samsung,exynosautov9-wakeup-eint
+    oneOf:
+      - enum:
+          - samsung,s3c2410-wakeup-eint
+          - samsung,s3c2412-wakeup-eint
+          - samsung,s3c64xx-wakeup-eint
+          - samsung,s5pv210-wakeup-eint
+          - samsung,exynos4210-wakeup-eint
+          - samsung,exynos7-wakeup-eint
+          - samsung,exynosautov920-wakeup-eint
+      - items:
+          - enum:
+              - samsung,exynos5433-wakeup-eint
+              - samsung,exynos7885-wakeup-eint
+              - samsung,exynos850-wakeup-eint
+          - const: samsung,exynos7-wakeup-eint
+      - items:
+          - enum:
+              - google,gs101-wakeup-eint
+              - samsung,exynosautov9-wakeup-eint
+          - const: samsung,exynos850-wakeup-eint
+          - const: samsung,exynos7-wakeup-eint
 
   interrupts:
     description:
@@ -79,11 +91,14 @@ allOf:
   - if:
       properties:
         compatible:
-          contains:
-            enum:
-              - samsung,s5pv210-wakeup-eint
-              - samsung,exynos4210-wakeup-eint
-              - samsung,exynos7-wakeup-eint
+          # Match without "contains", to skip newer variants which are still
+          # compatible with samsung,exynos7-wakeup-eint
+          enum:
+            - samsung,s5pv210-wakeup-eint
+            - samsung,exynos4210-wakeup-eint
+            - samsung,exynos5433-wakeup-eint
+            - samsung,exynos7-wakeup-eint
+            - samsung,exynos7885-wakeup-eint
     then:
       properties:
         interrupts:
@@ -98,7 +113,7 @@ allOf:
           contains:
             enum:
               - samsung,exynos850-wakeup-eint
-              - samsung,exynosautov9-wakeup-eint
+              - samsung,exynosautov920-wakeup-eint
     then:
       properties:
         interrupts: false
diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
index 26614621774a..118549c25976 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
@@ -35,6 +35,7 @@ properties:
 
   compatible:
     enum:
+      - google,gs101-pinctrl
       - samsung,s3c2412-pinctrl
       - samsung,s3c2416-pinctrl
       - samsung,s3c2440-pinctrl
@@ -53,6 +54,7 @@ properties:
       - samsung,exynos7885-pinctrl
       - samsung,exynos850-pinctrl
       - samsung,exynosautov9-pinctrl
+      - samsung,exynosautov920-pinctrl
       - tesla,fsd-pinctrl
 
   interrupts:
@@ -313,7 +315,8 @@ examples:
         pinctrl-0 = <&initial_alive>;
 
         wakeup-interrupt-controller {
-            compatible = "samsung,exynos7-wakeup-eint";
+            compatible = "samsung,exynos5433-wakeup-eint",
+                         "samsung,exynos7-wakeup-eint";
             interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
         };
 
diff --git a/Documentation/devicetree/bindings/pinctrl/xlnx,zynq-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/xlnx,zynq-pinctrl.yaml
index b85f9e36ce4b..d2676f92ef5b 100644
--- a/Documentation/devicetree/bindings/pinctrl/xlnx,zynq-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/xlnx,zynq-pinctrl.yaml
@@ -39,7 +39,7 @@ properties:
       phandle to the SLCR.
 
 patternProperties:
-  '^(.*-)?(default|gpio)$':
+  '^(.*-)?(default|gpio-grp)$':
     type: object
     patternProperties:
       '^mux':
diff --git a/Documentation/devicetree/bindings/pinctrl/xlnx,zynqmp-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/xlnx,zynqmp-pinctrl.yaml
index 01b6f2b57843..f13d315b5d5e 100644
--- a/Documentation/devicetree/bindings/pinctrl/xlnx,zynqmp-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/xlnx,zynqmp-pinctrl.yaml
@@ -31,7 +31,7 @@ properties:
     const: xlnx,zynqmp-pinctrl
 
 patternProperties:
-  '^(.*-)?(default|gpio)$':
+  '^(.*-)?(default|gpio-grp)$':
     type: object
     patternProperties:
       '^mux':
diff --git a/Documentation/devicetree/bindings/power/reset/nvmem-reboot-mode.yaml b/Documentation/devicetree/bindings/power/reset/nvmem-reboot-mode.yaml
index 14a262bcbf7c..627f8a6078c2 100644
--- a/Documentation/devicetree/bindings/power/reset/nvmem-reboot-mode.yaml
+++ b/Documentation/devicetree/bindings/power/reset/nvmem-reboot-mode.yaml
@@ -28,17 +28,15 @@ properties:
     items:
       - const: reboot-mode
 
-patternProperties:
-  "^mode-.+":
-    $ref: /schemas/types.yaml#/definitions/uint32
-    description: Vendor-specific mode value written to the mode register
+allOf:
+  - $ref: reboot-mode.yaml#
 
 required:
   - compatible
   - nvmem-cells
   - nvmem-cell-names
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml b/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml
index 5e460128b0d1..fc8105a7b9b2 100644
--- a/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml
+++ b/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml
@@ -111,21 +111,24 @@ examples:
    #include <dt-bindings/interrupt-controller/irq.h>
    #include <dt-bindings/input/linux-event-codes.h>
    #include <dt-bindings/spmi/spmi.h>
-   spmi_bus: spmi@c440000 {
+
+   spmi@c440000 {
      reg = <0x0c440000 0x1100>;
      #address-cells = <2>;
      #size-cells = <0>;
-     pmk8350: pmic@0 {
+
+     pmic@0 {
        reg = <0x0 SPMI_USID>;
        #address-cells = <1>;
        #size-cells = <0>;
-       pmk8350_pon: pon_hlos@1300 {
-         reg = <0x1300>;
+
+       pon@800 {
          compatible = "qcom,pm8998-pon";
+         reg = <0x800>;
 
          pwrkey {
             compatible = "qcom,pm8941-pwrkey";
-            interrupts = < 0x0 0x8 0 IRQ_TYPE_EDGE_BOTH >;
+            interrupts = <0x0 0x8 0 IRQ_TYPE_EDGE_BOTH>;
             debounce = <15625>;
             bias-pull-up;
             linux,code = <KEY_POWER>;
diff --git a/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.yaml b/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.yaml
index 9b1ffceefe3d..b6acff199cde 100644
--- a/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.yaml
+++ b/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.yaml
@@ -29,12 +29,10 @@ properties:
     $ref: /schemas/types.yaml#/definitions/uint32
     description: Offset in the register map for the mode register (in bytes)
 
-patternProperties:
-  "^mode-.+":
-    $ref: /schemas/types.yaml#/definitions/uint32
-    description: Vendor-specific mode value written to the mode register
+allOf:
+  - $ref: reboot-mode.yaml#
 
-additionalProperties: false
+unevaluatedProperties: false
 
 required:
   - compatible
diff --git a/Documentation/devicetree/bindings/power/reset/xlnx,zynqmp-power.yaml b/Documentation/devicetree/bindings/power/reset/xlnx,zynqmp-power.yaml
index 45792e216981..799831636194 100644
--- a/Documentation/devicetree/bindings/power/reset/xlnx,zynqmp-power.yaml
+++ b/Documentation/devicetree/bindings/power/reset/xlnx,zynqmp-power.yaml
@@ -57,7 +57,7 @@ examples:
 
     firmware {
       zynqmp-firmware {
-        zynqmp-power {
+        power-management {
           compatible = "xlnx,zynqmp-power";
           interrupts = <0 35 4>;
         };
@@ -70,7 +70,7 @@ examples:
 
     firmware {
       zynqmp-firmware {
-        zynqmp-power {
+        power-management {
           compatible = "xlnx,zynqmp-power";
           interrupt-parent = <&gic>;
           interrupts = <0 35 4>;
diff --git a/Documentation/devicetree/bindings/power/supply/bq24190.yaml b/Documentation/devicetree/bindings/power/supply/bq24190.yaml
index d3ebc9de8c0b..131b7e57d22f 100644
--- a/Documentation/devicetree/bindings/power/supply/bq24190.yaml
+++ b/Documentation/devicetree/bindings/power/supply/bq24190.yaml
@@ -20,6 +20,7 @@ properties:
       - ti,bq24192
       - ti,bq24192i
       - ti,bq24196
+      - ti,bq24296
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/remoteproc/qcom,sc7180-pas.yaml b/Documentation/devicetree/bindings/remoteproc/qcom,sc7180-pas.yaml
index f10f329677d8..c054b84fdcd5 100644
--- a/Documentation/devicetree/bindings/remoteproc/qcom,sc7180-pas.yaml
+++ b/Documentation/devicetree/bindings/remoteproc/qcom,sc7180-pas.yaml
@@ -18,7 +18,10 @@ properties:
     enum:
       - qcom,sc7180-adsp-pas
       - qcom,sc7180-mpss-pas
+      - qcom,sc7280-adsp-pas
+      - qcom,sc7280-cdsp-pas
       - qcom,sc7280-mpss-pas
+      - qcom,sc7280-wpss-pas
 
   reg:
     maxItems: 1
@@ -75,6 +78,7 @@ allOf:
         compatible:
           enum:
             - qcom,sc7180-adsp-pas
+            - qcom,sc7280-adsp-pas
     then:
       properties:
         power-domains:
@@ -114,6 +118,23 @@ allOf:
         power-domains:
           items:
             - description: CX power domain
+            - description: MSS power domain
+        power-domain-names:
+          items:
+            - const: cx
+            - const: mss
+
+  - if:
+      properties:
+        compatible:
+          enum:
+            - qcom,sc7280-cdsp-pas
+            - qcom,sc7280-wpss-pas
+    then:
+      properties:
+        power-domains:
+          items:
+            - description: CX power domain
             - description: MX power domain
         power-domain-names:
           items:
diff --git a/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml b/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml
index 49db66801429..1f1b42dde94d 100644
--- a/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml
+++ b/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml
@@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Zynq UltraScale+ MPSoC and Versal reset
 
 maintainers:
-  - Piyush Mehta <piyush.mehta@amd.com>
+  - Mubin Sayyed <mubin.sayyed@amd.com>
+  - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
 
 description: |
   The Zynq UltraScale+ MPSoC and Versal has several different resets.
diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml
index f392e367d673..9d8670c00e3b 100644
--- a/Documentation/devicetree/bindings/riscv/cpus.yaml
+++ b/Documentation/devicetree/bindings/riscv/cpus.yaml
@@ -32,6 +32,7 @@ properties:
     oneOf:
       - items:
           - enum:
+              - amd,mbv32
               - andestech,ax45mp
               - canaan,k210
               - sifive,bullet0
@@ -62,8 +63,8 @@ properties:
 
   mmu-type:
     description:
-      Identifies the MMU address translation mode used on this
-      hart.  These values originate from the RISC-V Privileged
+      Identifies the largest MMU address translation mode supported by
+      this hart.  These values originate from the RISC-V Privileged
       Specification document, available from
       https://riscv.org/specifications/
     $ref: /schemas/types.yaml#/definitions/string
@@ -79,6 +80,11 @@ properties:
     description:
       The blocksize in bytes for the Zicbom cache operations.
 
+  riscv,cbop-block-size:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      The blocksize in bytes for the Zicbop cache operations.
+
   riscv,cboz-block-size:
     $ref: /schemas/types.yaml#/definitions/uint32
     description:
diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml
index c91ab0e46648..63d81dc895e5 100644
--- a/Documentation/devicetree/bindings/riscv/extensions.yaml
+++ b/Documentation/devicetree/bindings/riscv/extensions.yaml
@@ -48,7 +48,7 @@ properties:
       insensitive, letters in the riscv,isa string must be all
       lowercase.
     $ref: /schemas/types.yaml#/definitions/string
-    pattern: ^rv(?:64|32)imaf?d?q?c?b?k?j?p?v?h?(?:[hsxz](?:[a-z])+)?(?:_[hsxz](?:[a-z])+)*$
+    pattern: ^rv(?:64|32)imaf?d?q?c?b?k?j?p?v?h?(?:[hsxz](?:[0-9a-z])+)?(?:_[hsxz](?:[0-9a-z])+)*$
     deprecated: true
 
   riscv,isa-base:
@@ -171,6 +171,12 @@ properties:
             memory types as ratified in the 20191213 version of the privileged
             ISA specification.
 
+        - const: zacas
+          description: |
+            The Zacas extension for Atomic Compare-and-Swap (CAS) instructions
+            is supported as ratified at commit 5059e0ca641c ("update to
+            ratified") of the riscv-zacas.
+
         - const: zba
           description: |
             The standard Zba bit-manipulation extension for address generation
@@ -190,12 +196,111 @@ properties:
             multiplication as ratified at commit 6d33919 ("Merge pull request
             #158 from hirooih/clmul-fix-loop-end-condition") of riscv-bitmanip.
 
+        - const: zbkb
+          description:
+            The standard Zbkb bitmanip instructions for cryptography as ratified
+            in version 1.0 of RISC-V Cryptography Extensions Volume I
+            specification.
+
+        - const: zbkc
+          description:
+            The standard Zbkc carry-less multiply instructions as ratified
+            in version 1.0 of RISC-V Cryptography Extensions Volume I
+            specification.
+
+        - const: zbkx
+          description:
+            The standard Zbkx crossbar permutation instructions as ratified
+            in version 1.0 of RISC-V Cryptography Extensions Volume I
+            specification.
+
         - const: zbs
           description: |
             The standard Zbs bit-manipulation extension for single-bit
             instructions as ratified at commit 6d33919 ("Merge pull request #158
             from hirooih/clmul-fix-loop-end-condition") of riscv-bitmanip.
 
+        - const: zfa
+          description:
+            The standard Zfa extension for additional floating point
+            instructions, as ratified in commit 056b6ff ("Zfa is ratified") of
+            riscv-isa-manual.
+
+        - const: zfh
+          description:
+            The standard Zfh extension for 16-bit half-precision binary
+            floating-point instructions, as ratified in commit 64074bc ("Update
+            version numbers for Zfh/Zfinx") of riscv-isa-manual.
+
+        - const: zfhmin
+          description:
+            The standard Zfhmin extension which provides minimal support for
+            16-bit half-precision binary floating-point instructions, as ratified
+            in commit 64074bc ("Update version numbers for Zfh/Zfinx") of
+            riscv-isa-manual.
+
+        - const: zk
+          description:
+            The standard Zk Standard Scalar cryptography extension as ratified
+            in version 1.0 of RISC-V Cryptography Extensions Volume I
+            specification.
+
+        - const: zkn
+          description:
+            The standard Zkn NIST algorithm suite extensions as ratified in
+            version 1.0 of RISC-V Cryptography Extensions Volume I
+            specification.
+
+        - const: zknd
+          description: |
+            The standard Zknd for NIST suite: AES decryption instructions as
+            ratified in version 1.0 of RISC-V Cryptography Extensions Volume I
+            specification.
+
+        - const: zkne
+          description: |
+            The standard Zkne for NIST suite: AES encryption instructions as
+            ratified in version 1.0 of RISC-V Cryptography Extensions Volume I
+            specification.
+
+        - const: zknh
+          description: |
+            The standard Zknh for NIST suite: hash function instructions as
+            ratified in version 1.0 of RISC-V Cryptography Extensions Volume I
+            specification.
+
+        - const: zkr
+          description:
+            The standard Zkr entropy source extension as ratified in version
+            1.0 of RISC-V Cryptography Extensions Volume I specification.
+            This string being present means that the CSR associated to this
+            extension is accessible at the privilege level to which that
+            device-tree has been provided.
+
+        - const: zks
+          description:
+            The standard Zks ShangMi algorithm suite extensions as ratified in
+            version 1.0 of RISC-V Cryptography Extensions Volume I
+            specification.
+
+        - const: zksed
+          description: |
+            The standard Zksed for ShangMi suite: SM4 block cipher instructions
+            as ratified in version 1.0 of RISC-V Cryptography Extensions
+            Volume I specification.
+
+        - const: zksh
+          description: |
+            The standard Zksh for ShangMi suite: SM3 hash function instructions
+            as ratified in version 1.0 of RISC-V Cryptography Extensions
+            Volume I specification.
+
+        - const: zkt
+          description:
+            The standard Zkt for data independent execution latency as ratified
+            in version 1.0 of RISC-V Cryptography Extensions Volume I
+            specification.
+
         - const: zicbom
           description:
             The standard Zicbom extension for base cache management operations as
@@ -246,6 +351,12 @@ properties:
             The standard Zihintpause extension for pause hints, as ratified in
             commit d8ab5c7 ("Zihintpause is ratified") of the riscv-isa-manual.
 
+        - const: zihintntl
+          description:
+            The standard Zihintntl extension for non-temporal locality hints, as
+            ratified in commit 0dc91f5 ("Zihintntl is ratified") of the
+            riscv-isa-manual.
+
         - const: zihpm
           description:
             The standard Zihpm extension for hardware performance counters, as
@@ -258,5 +369,113 @@ properties:
             in commit 2e5236 ("Ztso is now ratified.") of the
             riscv-isa-manual.
 
+        - const: zvbb
+          description:
+            The standard Zvbb extension for vectored basic bit-manipulation
+            instructions, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvbc
+          description:
+            The standard Zvbc extension for vectored carryless multiplication
+            instructions, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvfh
+          description:
+            The standard Zvfh extension for vectored half-precision
+            floating-point instructions, as ratified in commit e2ccd05
+            ("Remove draft warnings from Zvfh[min]") of riscv-v-spec.
+
+        - const: zvfhmin
+          description:
+            The standard Zvfhmin extension for vectored minimal half-precision
+            floating-point instructions, as ratified in commit e2ccd05
+            ("Remove draft warnings from Zvfh[min]") of riscv-v-spec.
+
+        - const: zvkb
+          description:
+            The standard Zvkb extension for vector cryptography bit-manipulation
+            instructions, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvkg
+          description:
+            The standard Zvkg extension for vector GCM/GMAC instructions, as
+            ratified in commit 56ed795 ("Update riscv-crypto-spec-vector.adoc")
+            of riscv-crypto.
+
+        - const: zvkn
+          description:
+            The standard Zvkn extension for NIST algorithm suite instructions, as
+            ratified in commit 56ed795 ("Update riscv-crypto-spec-vector.adoc")
+            of riscv-crypto.
+
+        - const: zvknc
+          description:
+            The standard Zvknc extension for NIST algorithm suite with carryless
+            multiply instructions, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvkned
+          description:
+            The standard Zvkned extension for Vector AES block cipher
+            instructions, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvkng
+          description:
+            The standard Zvkng extension for NIST algorithm suite with GCM
+            instructions, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvknha
+          description: |
+            The standard Zvknha extension for NIST suite: vector SHA-2 secure,
+            hash (SHA-256 only) instructions, as ratified in commit
+            56ed795 ("Update riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvknhb
+          description: |
+            The standard Zvknhb extension for NIST suite: vector SHA-2 secure,
+            hash (SHA-256 and SHA-512) instructions, as ratified in commit
+            56ed795 ("Update riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvks
+          description:
+            The standard Zvks extension for ShangMi algorithm suite
+            instructions, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvksc
+          description:
+            The standard Zvksc extension for ShangMi algorithm suite with
+            carryless multiplication instructions, as ratified in commit 56ed795
+            ("Update riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvksed
+          description: |
+            The standard Zvksed extension for ShangMi suite: SM4 block cipher
+            instructions, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvksh
+          description: |
+            The standard Zvksh extension for ShangMi suite: SM3 secure hash
+            instructions, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvksg
+          description:
+            The standard Zvksg extension for ShangMi algorithm suite with GCM
+            instructions, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvkt
+          description:
+            The standard Zvkt extension for vector data-independent execution
+            latency, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
 additionalProperties: true
 ...
diff --git a/Documentation/devicetree/bindings/rtc/adi,max31335.yaml b/Documentation/devicetree/bindings/rtc/adi,max31335.yaml
new file mode 100644
index 000000000000..0125cf6727cc
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/adi,max31335.yaml
@@ -0,0 +1,70 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/rtc/adi,max31335.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Analog Devices MAX31335 RTC
+
+maintainers:
+  - Antoniu Miclaus <antoniu.miclaus@analog.com>
+
+description:
+  Analog Devices MAX31335 I2C RTC ±2ppm Automotive Real-Time Clock with
+  Integrated MEMS Resonator.
+
+allOf:
+  - $ref: rtc.yaml#
+
+properties:
+  compatible:
+    const: adi,max31335
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  "#clock-cells":
+    description:
+      RTC can be used as a clock source through its clock output pin.
+    const: 0
+
+  adi,tc-diode:
+    description:
+      Select the diode configuration for the trickle charger.
+      schottky - Schottky diode in series.
+      standard+schottky - standard diode + Schottky diode in series.
+    enum: [schottky, standard+schottky]
+
+  trickle-resistor-ohms:
+    description:
+      Selected resistor for trickle charger. Should be specified if trickle
+      charger should be enabled.
+    enum: [3000, 6000, 11000]
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        rtc@68 {
+            compatible = "adi,max31335";
+            reg = <0x68>;
+            pinctrl-0 = <&rtc_nint_pins>;
+            interrupts-extended = <&gpio1 16 IRQ_TYPE_LEVEL_HIGH>;
+            aux-voltage-chargeable = <1>;
+            trickle-resistor-ohms = <6000>;
+            adi,tc-diode = "schottky";
+        };
+    };
+...
diff --git a/Documentation/devicetree/bindings/rtc/epson,rx8900.yaml b/Documentation/devicetree/bindings/rtc/epson,rx8900.yaml
index 1df7c45d95c1..b770149c5fd6 100644
--- a/Documentation/devicetree/bindings/rtc/epson,rx8900.yaml
+++ b/Documentation/devicetree/bindings/rtc/epson,rx8900.yaml
@@ -29,6 +29,8 @@ properties:
 
   trickle-diode-disable: true
 
+  wakeup-source: true
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/rtc/nuvoton,ma35d1-rtc.yaml b/Documentation/devicetree/bindings/rtc/nuvoton,ma35d1-rtc.yaml
new file mode 100644
index 000000000000..5e4ade803eed
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/nuvoton,ma35d1-rtc.yaml
@@ -0,0 +1,48 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/rtc/nuvoton,ma35d1-rtc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Nuvoton MA35D1 Real Time Clock
+
+maintainers:
+  - Min-Jen Chen <mjchen@nuvoton.com>
+
+allOf:
+  - $ref: rtc.yaml#
+
+properties:
+  compatible:
+    enum:
+      - nuvoton,ma35d1-rtc
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/nuvoton,ma35d1-clk.h>
+    rtc@40410000 {
+        compatible = "nuvoton,ma35d1-rtc";
+        reg = <0x40410000 0x200>;
+        interrupts = <GIC_SPI 5 IRQ_TYPE_EDGE_RISING>;
+        clocks = <&clk RTC_GATE>;
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml b/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml
index b95a69cc9ae0..d274bb7a534b 100644
--- a/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml
+++ b/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml
@@ -61,27 +61,27 @@ additionalProperties: false
 
 examples:
   - |
+    #include <dt-bindings/interrupt-controller/irq.h>
     #include <dt-bindings/spmi/spmi.h>
-    spmi_bus: spmi@c440000 {
-      reg = <0x0c440000 0x1100>;
-      #address-cells = <2>;
-      #size-cells = <0>;
-      pmicintc: pmic@0 {
-        reg = <0x0 SPMI_USID>;
-        compatible = "qcom,pm8921";
-        interrupts = <104 8>;
-        #interrupt-cells = <2>;
-        interrupt-controller;
-        #address-cells = <1>;
+
+    spmi {
+        #address-cells = <2>;
         #size-cells = <0>;
 
-        pm8921_rtc: rtc@11d {
-          compatible = "qcom,pm8921-rtc";
-          reg = <0x11d>;
-          interrupts = <0x27 0>;
-          nvmem-cells = <&rtc_offset>;
-          nvmem-cell-names = "offset";
+        pmic@0 {
+            compatible = "qcom,pm8941", "qcom,spmi-pmic";
+            reg = <0x0 SPMI_USID>;
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            rtc@6000 {
+                compatible = "qcom,pm8941-rtc";
+                reg = <0x6000>, <0x6100>;
+                reg-names = "rtc", "alarm";
+                interrupts = <0x0 0x61 0x1 IRQ_TYPE_EDGE_RISING>;
+                nvmem-cells = <&rtc_offset>;
+                nvmem-cell-names = "offset";
+            };
         };
-      };
     };
 ...
diff --git a/Documentation/devicetree/bindings/serial/arm,dcc.yaml b/Documentation/devicetree/bindings/serial/arm,dcc.yaml
new file mode 100644
index 000000000000..fd0589356617
--- /dev/null
+++ b/Documentation/devicetree/bindings/serial/arm,dcc.yaml
@@ -0,0 +1,30 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/serial/arm,dcc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: ARM DCC (Data communication channel) serial emulation
+
+maintainers:
+  - Michal Simek <michal.simek@amd.com>
+
+description: |
+  ARM DCC (Data communication channel) serial emulation interface available
+  via JTAG can be also used as one of serial line tightly coupled with every
+  ARM CPU available in the system.
+
+properties:
+  compatible:
+    const: arm,dcc
+
+required:
+  - compatible
+
+additionalProperties: false
+
+examples:
+  - |
+    serial {
+      compatible = "arm,dcc";
+    };
diff --git a/Documentation/devicetree/bindings/serial/fsl,s32-linflexuart.yaml b/Documentation/devicetree/bindings/serial/fsl,s32-linflexuart.yaml
index 920539926d7e..7a105551fa6a 100644
--- a/Documentation/devicetree/bindings/serial/fsl,s32-linflexuart.yaml
+++ b/Documentation/devicetree/bindings/serial/fsl,s32-linflexuart.yaml
@@ -13,7 +13,7 @@ description: |
   https://www.nxp.com/webapp/Download?colCode=S32V234RM.
 
 maintainers:
-  - Chester Lin <clin@suse.com>
+  - Chester Lin <chester62515@gmail.com>
 
 allOf:
   - $ref: serial.yaml#
diff --git a/Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml b/Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml
index 83035553044a..9c6dc16f88a6 100644
--- a/Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml
+++ b/Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml
@@ -9,10 +9,6 @@ title: Freescale i.MX Universal Asynchronous Receiver/Transmitter (UART)
 maintainers:
   - Fabio Estevam <festevam@gmail.com>
 
-allOf:
-  - $ref: serial.yaml#
-  - $ref: rs485.yaml#
-
 properties:
   compatible:
     oneOf:
@@ -68,7 +64,11 @@ properties:
       - const: tx
 
   interrupts:
-    maxItems: 1
+    items:
+      - description: UART RX Interrupt
+      - description: UART TX Interrupt
+      - description: UART RTS Interrupt
+    minItems: 1
 
   wakeup-source: true
 
@@ -110,6 +110,25 @@ required:
   - clock-names
   - interrupts
 
+allOf:
+  - $ref: serial.yaml#
+  - $ref: rs485.yaml#
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: fsl,imx1-uart
+    then:
+      properties:
+        interrupts:
+          minItems: 3
+          maxItems: 3
+    else:
+      properties:
+        interrupts:
+          maxItems: 1
+
 unevaluatedProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/serial/qcom,msm-uartdm.yaml b/Documentation/devicetree/bindings/serial/qcom,msm-uartdm.yaml
index ee52bf8e8917..e0fa363ad7e2 100644
--- a/Documentation/devicetree/bindings/serial/qcom,msm-uartdm.yaml
+++ b/Documentation/devicetree/bindings/serial/qcom,msm-uartdm.yaml
@@ -48,9 +48,17 @@ properties:
       - const: tx
       - const: rx
 
+  interconnects:
+    maxItems: 1
+
   interrupts:
     maxItems: 1
 
+  operating-points-v2: true
+
+  power-domains:
+    maxItems: 1
+
   qcom,rx-crci:
     $ref: /schemas/types.yaml#/definitions/uint32
     description:
@@ -99,7 +107,9 @@ unevaluatedProperties: false
 
 examples:
   - |
+    #include <dt-bindings/interconnect/qcom,msm8996.h>
     #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/power/qcom-rpmpd.h>
 
     serial@f991e000 {
         compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm";
@@ -109,4 +119,7 @@ examples:
         clock-names = "core", "iface";
         dmas = <&dma0 0>, <&dma0 1>;
         dma-names = "tx", "rx";
+        power-domains = <&rpmpd MSM8996_VDDCX>;
+        operating-points-v2 = <&uart_opp_table>;
+        interconnects = <&pnoc MASTER_BLSP_1 &bimc SLAVE_EBI_CH0>;
     };
diff --git a/Documentation/devicetree/bindings/serial/renesas,sci.yaml b/Documentation/devicetree/bindings/serial/renesas,sci.yaml
index 9f7305200c47..64d3db6e54e5 100644
--- a/Documentation/devicetree/bindings/serial/renesas,sci.yaml
+++ b/Documentation/devicetree/bindings/serial/renesas,sci.yaml
@@ -17,7 +17,7 @@ properties:
     oneOf:
       - items:
           - enum:
-              - renesas,r9a07g043-sci     # RZ/G2UL
+              - renesas,r9a07g043-sci     # RZ/G2UL and RZ/Five
               - renesas,r9a07g044-sci     # RZ/G2{L,LC}
               - renesas,r9a07g054-sci     # RZ/V2L
           - const: renesas,sci            # generic SCI compatible UART
diff --git a/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.yaml b/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.yaml
index 17c553123f96..1001d2a6ace8 100644
--- a/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.yaml
+++ b/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.yaml
@@ -11,6 +11,7 @@ maintainers:
 
 allOf:
   - $ref: serial.yaml#
+  - $ref: rs485.yaml#
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/serial/sprd-uart.yaml b/Documentation/devicetree/bindings/serial/sprd-uart.yaml
index 28ff77aa86c8..f4dbb6dc2b6e 100644
--- a/Documentation/devicetree/bindings/serial/sprd-uart.yaml
+++ b/Documentation/devicetree/bindings/serial/sprd-uart.yaml
@@ -20,6 +20,7 @@ properties:
               - sprd,sc9860-uart
               - sprd,sc9863a-uart
               - sprd,ums512-uart
+              - sprd,ums9620-uart
           - const: sprd,sc9836-uart
       - const: sprd,sc9836-uart
 
diff --git a/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-spdif.yaml b/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-spdif.yaml
index 8108c564dd78..aa32dc950e72 100644
--- a/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-spdif.yaml
+++ b/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-spdif.yaml
@@ -22,6 +22,7 @@ properties:
       - const: allwinner,sun6i-a31-spdif
       - const: allwinner,sun8i-h3-spdif
       - const: allwinner,sun50i-h6-spdif
+      - const: allwinner,sun50i-h616-spdif
       - items:
           - const: allwinner,sun8i-a83t-spdif
           - const: allwinner,sun8i-h3-spdif
@@ -62,6 +63,8 @@ allOf:
             enum:
               - allwinner,sun6i-a31-spdif
               - allwinner,sun8i-h3-spdif
+              - allwinner,sun50i-h6-spdif
+              - allwinner,sun50i-h616-spdif
 
     then:
       required:
@@ -73,7 +76,7 @@ allOf:
           contains:
             enum:
               - allwinner,sun8i-h3-spdif
-              - allwinner,sun50i-h6-spdif
+              - allwinner,sun50i-h616-spdif
 
     then:
       properties:
diff --git a/Documentation/devicetree/bindings/sound/google,sc7280-herobrine.yaml b/Documentation/devicetree/bindings/sound/google,sc7280-herobrine.yaml
index ec4b6e547ca6..cdcd7c6f21eb 100644
--- a/Documentation/devicetree/bindings/sound/google,sc7280-herobrine.yaml
+++ b/Documentation/devicetree/bindings/sound/google,sc7280-herobrine.yaml
@@ -7,7 +7,6 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Google SC7280-Herobrine ASoC sound card driver
 
 maintainers:
-  - Srinivasa Rao Mandadapu <srivasam@codeaurora.org>
   - Judy Hsiao <judyhsiao@chromium.org>
 
 description:
diff --git a/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-max9808x.yaml b/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-max9808x.yaml
index c29d7942915c..241d20f3aad0 100644
--- a/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-max9808x.yaml
+++ b/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-max9808x.yaml
@@ -64,7 +64,7 @@ examples:
     #include <dt-bindings/clock/tegra30-car.h>
     #include <dt-bindings/soc/tegra-pmc.h>
     sound {
-        compatible = "lge,tegra-audio-max98089-p895",
+        compatible = "lg,tegra-audio-max98089-p895",
                      "nvidia,tegra-audio-max98089";
         nvidia,model = "LG Optimus Vu MAX98089";
 
diff --git a/Documentation/devicetree/bindings/sound/tas2562.yaml b/Documentation/devicetree/bindings/sound/tas2562.yaml
index f01c0dde0cf7..d28c102c0ce7 100644
--- a/Documentation/devicetree/bindings/sound/tas2562.yaml
+++ b/Documentation/devicetree/bindings/sound/tas2562.yaml
@@ -18,7 +18,6 @@ description: |
 
   Specifications about the audio amplifier can be found at:
     https://www.ti.com/lit/gpn/tas2562
-    https://www.ti.com/lit/gpn/tas2563
     https://www.ti.com/lit/gpn/tas2564
     https://www.ti.com/lit/gpn/tas2110
 
@@ -29,7 +28,6 @@ properties:
   compatible:
     enum:
       - ti,tas2562
-      - ti,tas2563
       - ti,tas2564
       - ti,tas2110
 
diff --git a/Documentation/devicetree/bindings/sound/ti,tas2781.yaml b/Documentation/devicetree/bindings/sound/ti,tas2781.yaml
index a69e6c223308..976238689249 100644
--- a/Documentation/devicetree/bindings/sound/ti,tas2781.yaml
+++ b/Documentation/devicetree/bindings/sound/ti,tas2781.yaml
@@ -5,36 +5,46 @@
 $id: http://devicetree.org/schemas/sound/ti,tas2781.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: Texas Instruments TAS2781 SmartAMP
+title: Texas Instruments TAS2563/TAS2781 SmartAMP
 
 maintainers:
   - Shenghao Ding <shenghao-ding@ti.com>
 
-description:
-  The TAS2781 is a mono, digital input Class-D audio amplifier
-  optimized for efficiently driving high peak power into small
-  loudspeakers. An integrated on-chip DSP supports Texas Instruments
-  Smart Amp speaker protection algorithm. The integrated speaker
-  voltage and current sense provides for real time
+description: |
+  The TAS2563/TAS2781 is a mono, digital input Class-D audio
+  amplifier optimized for efficiently driving high peak power into
+  small loudspeakers. An integrated on-chip DSP supports Texas
+  Instruments Smart Amp speaker protection algorithm. The
+  integrated speaker voltage and current sense provides for real time
   monitoring of loudspeaker behavior.
 
-allOf:
-  - $ref: dai-common.yaml#
+  Specifications about the audio amplifier can be found at:
+    https://www.ti.com/lit/gpn/tas2563
+    https://www.ti.com/lit/gpn/tas2781
 
 properties:
   compatible:
-    enum:
-      - ti,tas2781
+    description: |
+      ti,tas2563: 6.1-W Boosted Class-D Audio Amplifier With Integrated
+      DSP and IV Sense, 16/20/24/32bit stereo I2S or multichannel TDM.
+
+      ti,tas2781: 24-V Class-D Amplifier with Real Time Integrated Speaker
+      Protection and Audio Processing, 16/20/24/32bit stereo I2S or
+      multichannel TDM.
+    oneOf:
+      - items:
+          - enum:
+              - ti,tas2563
+          - const: ti,tas2781
+      - enum:
+          - ti,tas2781
 
   reg:
     description:
-      I2C address, in multiple tas2781s case, all the i2c address
+      I2C address, in multiple-AMP case, all the i2c address
       aggregate as one Audio Device to support multiple audio slots.
     maxItems: 8
     minItems: 1
-    items:
-      minimum: 0x38
-      maximum: 0x3f
 
   reset-gpios:
     maxItems: 1
@@ -49,6 +59,44 @@ required:
   - compatible
   - reg
 
+allOf:
+  - $ref: dai-common.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - ti,tas2563
+    then:
+      properties:
+        reg:
+          description:
+            I2C address, in multiple-AMP case, all the i2c address
+            aggregate as one Audio Device to support multiple audio slots.
+          maxItems: 4
+          minItems: 1
+          items:
+            minimum: 0x4c
+            maximum: 0x4f
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - ti,tas2781
+    then:
+      properties:
+        reg:
+          description:
+            I2C address, in multiple-AMP case, all the i2c address
+            aggregate as one Audio Device to support multiple audio slots.
+          maxItems: 8
+          minItems: 1
+          items:
+            minimum: 0x38
+            maximum: 0x3f
+
 additionalProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/timer/sifive,clint.yaml b/Documentation/devicetree/bindings/timer/sifive,clint.yaml
index 4b6c20fc8194..fced6f2d8ecb 100644
--- a/Documentation/devicetree/bindings/timer/sifive,clint.yaml
+++ b/Documentation/devicetree/bindings/timer/sifive,clint.yaml
@@ -33,6 +33,7 @@ properties:
               - sifive,fu540-c000-clint # SiFive FU540
               - starfive,jh7100-clint   # StarFive JH7100
               - starfive,jh7110-clint   # StarFive JH7110
+              - starfive,jh8100-clint   # StarFive JH8100
           - const: sifive,clint0        # SiFive CLINT v0 IP block
       - items:
           - enum:
diff --git a/Documentation/devicetree/bindings/timer/thead,c900-aclint-mtimer.yaml b/Documentation/devicetree/bindings/timer/thead,c900-aclint-mtimer.yaml
index fbd235650e52..2e92bcdeb423 100644
--- a/Documentation/devicetree/bindings/timer/thead,c900-aclint-mtimer.yaml
+++ b/Documentation/devicetree/bindings/timer/thead,c900-aclint-mtimer.yaml
@@ -17,7 +17,12 @@ properties:
       - const: thead,c900-aclint-mtimer
 
   reg:
-    maxItems: 1
+    items:
+      - description: MTIMECMP Registers
+
+  reg-names:
+    items:
+      - const: mtimecmp
 
   interrupts-extended:
     minItems: 1
@@ -28,6 +33,7 @@ additionalProperties: false
 required:
   - compatible
   - reg
+  - reg-names
   - interrupts-extended
 
 examples:
@@ -39,5 +45,6 @@ examples:
                             <&cpu3intc 7>,
                             <&cpu4intc 7>;
       reg = <0xac000000 0x00010000>;
+      reg-names = "mtimecmp";
     };
 ...
diff --git a/Documentation/devicetree/bindings/tpm/tpm-common.yaml b/Documentation/devicetree/bindings/tpm/tpm-common.yaml
index 90390624a8be..3c1241b2a43f 100644
--- a/Documentation/devicetree/bindings/tpm/tpm-common.yaml
+++ b/Documentation/devicetree/bindings/tpm/tpm-common.yaml
@@ -42,7 +42,7 @@ properties:
 
   resets:
     description: Reset controller to reset the TPM
-    $ref: /schemas/types.yaml#/definitions/phandle
+    maxItems: 1
 
   reset-gpios:
     description: Output GPIO pin to reset the TPM
diff --git a/Documentation/devicetree/bindings/trivial-devices.yaml b/Documentation/devicetree/bindings/trivial-devices.yaml
index 21d1f066f875..79dcd92c4a43 100644
--- a/Documentation/devicetree/bindings/trivial-devices.yaml
+++ b/Documentation/devicetree/bindings/trivial-devices.yaml
@@ -177,6 +177,8 @@ properties:
           - isil,isl29030
             # Intersil ISL68137 Digital Output Configurable PWM Controller
           - isil,isl68137
+            # Intersil ISL76682 Ambient Light Sensor
+          - isil,isl76682
             # Linear Technology LTC2488
           - lineartechnology,ltc2488
             # 5 Bit Programmable, Pulse-Width Modulator
diff --git a/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml b/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml
index 88cc1e3a0c88..b2b509b3944d 100644
--- a/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml
+++ b/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml
@@ -55,9 +55,12 @@ properties:
 
   samsung,sysreg:
     $ref: /schemas/types.yaml#/definitions/phandle-array
-    description: Should be phandle/offset pair. The phandle to the syscon node
-                 which indicates the FSYSx sysreg interface and the offset of
-                 the control register for UFS io coherency setting.
+    items:
+      - items:
+          - description: phandle to FSYSx sysreg node
+          - description: offset of the control register for UFS io coherency setting
+    description:
+      Phandle and offset to the FSYSx sysreg for UFS io coherency setting.
 
   dma-coherent: true
 
diff --git a/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml b/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml
index bb373eb025a5..00f87a558c7d 100644
--- a/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml
+++ b/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml
@@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Xilinx SuperSpeed DWC3 USB SoC controller
 
 maintainers:
-  - Piyush Mehta <piyush.mehta@amd.com>
+  - Mubin Sayyed <mubin.sayyed@amd.com>
+  - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/usb/generic-xhci.yaml b/Documentation/devicetree/bindings/usb/generic-xhci.yaml
index 594ebb3ee432..6ceafa4af292 100644
--- a/Documentation/devicetree/bindings/usb/generic-xhci.yaml
+++ b/Documentation/devicetree/bindings/usb/generic-xhci.yaml
@@ -9,9 +9,6 @@ title: USB xHCI Controller
 maintainers:
   - Mathias Nyman <mathias.nyman@intel.com>
 
-allOf:
-  - $ref: usb-xhci.yaml#
-
 properties:
   compatible:
     oneOf:
@@ -25,6 +22,11 @@ properties:
               - marvell,armada-380-xhci
               - marvell,armada-8k-xhci
           - const: generic-xhci
+      - description: Broadcom SoCs with power domains
+        items:
+          - enum:
+              - brcm,bcm2711-xhci
+          - const: brcm,xhci-brcm-v2
       - description: Broadcom STB SoCs with xHCI
         enum:
           - brcm,xhci-brcm-v2
@@ -49,6 +51,9 @@ properties:
       - const: core
       - const: reg
 
+  power-domains:
+    maxItems: 1
+
 unevaluatedProperties: false
 
 required:
@@ -56,6 +61,20 @@ required:
   - reg
   - interrupts
 
+allOf:
+  - $ref: usb-xhci.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: brcm,bcm2711-xhci
+    then:
+      required:
+        - power-domains
+    else:
+      properties:
+        power-domains: false
+
 examples:
   - |
     usb@f0931000 {
diff --git a/Documentation/devicetree/bindings/usb/genesys,gl850g.yaml b/Documentation/devicetree/bindings/usb/genesys,gl850g.yaml
index ee08b9c3721f..37cf5249e526 100644
--- a/Documentation/devicetree/bindings/usb/genesys,gl850g.yaml
+++ b/Documentation/devicetree/bindings/usb/genesys,gl850g.yaml
@@ -29,6 +29,11 @@ properties:
     description:
       the regulator that provides 3.3V core power to the hub.
 
+  peer-hub:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description:
+      phandle to the peer hub on the controller.
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml b/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml
index e9644e333d78..924fd3d748a8 100644
--- a/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml
+++ b/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml
@@ -124,6 +124,17 @@ properties:
       defined in the xHCI spec on MTK's controller.
     default: 5000
 
+  rx-fifo-depth:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      It is a quirk used to work around Gen1 isoc-in endpoint transfer issue
+      that still send out unexpected ACK after device finishes the burst
+      transfer with a short packet and cause an exception, specially on a 4K
+      camera device, it happens on controller before about IPM v1.6.0;
+      the side-effect is that it may cause performance drop about 10%,
+      including bulk transfer, prefer to use 3k here. The size is in bytes.
+    enum: [1024, 2048, 3072, 4096]
+
   # the following properties are only used for case 1
   wakeup-source:
     description: enable USB remote wakeup, see power/wakeup-source.txt
diff --git a/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml b/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
index 6d4cfd943f58..445183d9d6db 100644
--- a/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
+++ b/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
@@ -16,8 +16,9 @@ description:
   USB 2.0 traffic.
 
 maintainers:
-  - Piyush Mehta <piyush.mehta@amd.com>
   - Michal Simek <michal.simek@amd.com>
+  - Mubin Sayyed <mubin.sayyed@amd.com>
+  - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/usb/nxp,ptn5110.yaml b/Documentation/devicetree/bindings/usb/nxp,ptn5110.yaml
index 28eb25ecba74..eaedb4cc6b6c 100644
--- a/Documentation/devicetree/bindings/usb/nxp,ptn5110.yaml
+++ b/Documentation/devicetree/bindings/usb/nxp,ptn5110.yaml
@@ -4,7 +4,7 @@
 $id: http://devicetree.org/schemas/usb/nxp,ptn5110.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: NXP PTN5110 Typec Port Cotroller
+title: NXP PTN5110 Type-C Port Controller
 
 maintainers:
   - Li Jun <jun.li@nxp.com>
diff --git a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
index 915c8205623b..63d150b216c5 100644
--- a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
+++ b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
@@ -46,6 +46,8 @@ properties:
           - qcom,sm8350-dwc3
           - qcom,sm8450-dwc3
           - qcom,sm8550-dwc3
+          - qcom,sm8650-dwc3
+          - qcom,x1e80100-dwc3
       - const: qcom,dwc3
 
   reg:
@@ -97,12 +99,29 @@ properties:
       - const: apps-usb
 
   interrupts:
-    minItems: 1
-    maxItems: 4
+    description: |
+      Different types of interrupts are used based on HS PHY used on target:
+        - pwr_event: Used for wakeup based on other power events.
+        - hs_phY_irq: Apart from DP/DM/QUSB2 PHY interrupts, there is
+                       hs_phy_irq which is not triggered by default and its
+                       functionality is mutually exclusive to that of
+                       {dp/dm}_hs_phy_irq and qusb2_phy_irq.
+        - qusb2_phy: SoCs with QUSB2 PHY do not have separate DP/DM IRQs and
+                      expose only a single IRQ whose behavior can be modified
+                      by the QUSB2PHY_INTR_CTRL register. The required DPSE/
+                      DMSE configuration is done in QUSB2PHY_INTR_CTRL register
+                      of PHY address space.
+        - {dp/dm}_hs_phy_irq: These IRQ's directly reflect changes on the DP/
+                               DM pads of the SoC. These are used for wakeup
+                               only on SoCs with non-QUSB2 targets with
+                               exception of SDM670/SDM845/SM6350.
+        - ss_phy_irq: Used for remote wakeup in Super Speed mode of operation.
+    minItems: 2
+    maxItems: 5
 
   interrupt-names:
-    minItems: 1
-    maxItems: 4
+    minItems: 2
+    maxItems: 5
 
   qcom,select-utmi-as-pipe-clk:
     description:
@@ -263,6 +282,7 @@ allOf:
           contains:
             enum:
               - qcom,sc8280xp-dwc3
+              - qcom,x1e80100-dwc3
     then:
       properties:
         clocks:
@@ -288,8 +308,8 @@ allOf:
     then:
       properties:
         clocks:
-          minItems: 5
-          maxItems: 6
+          minItems: 4
+          maxItems: 5
         clock-names:
           oneOf:
             - items:
@@ -298,13 +318,11 @@ allOf:
                 - const: iface
                 - const: sleep
                 - const: mock_utmi
-                - const: bus
             - items:
                 - const: cfg_noc
                 - const: core
                 - const: sleep
                 - const: mock_utmi
-                - const: bus
 
   - if:
       properties:
@@ -318,6 +336,7 @@ allOf:
               - qcom,sm8250-dwc3
               - qcom,sm8450-dwc3
               - qcom,sm8550-dwc3
+              - qcom,sm8650-dwc3
     then:
       properties:
         clocks:
@@ -357,59 +376,20 @@ allOf:
         compatible:
           contains:
             enum:
-              - qcom,ipq4019-dwc3
+              - qcom,ipq5018-dwc3
               - qcom,ipq6018-dwc3
-              - qcom,ipq8064-dwc3
               - qcom,ipq8074-dwc3
-              - qcom,msm8994-dwc3
-              - qcom,qcs404-dwc3
-              - qcom,sc7180-dwc3
-              - qcom,sdm670-dwc3
-              - qcom,sdm845-dwc3
-              - qcom,sdx55-dwc3
-              - qcom,sdx65-dwc3
-              - qcom,sdx75-dwc3
-              - qcom,sm4250-dwc3
-              - qcom,sm6125-dwc3
-              - qcom,sm6350-dwc3
-              - qcom,sm8150-dwc3
-              - qcom,sm8250-dwc3
-              - qcom,sm8350-dwc3
-              - qcom,sm8450-dwc3
-              - qcom,sm8550-dwc3
-    then:
-      properties:
-        interrupts:
-          items:
-            - description: The interrupt that is asserted
-                when a wakeup event is received on USB2 bus.
-            - description: The interrupt that is asserted
-                when a wakeup event is received on USB3 bus.
-            - description: Wakeup event on DM line.
-            - description: Wakeup event on DP line.
-        interrupt-names:
-          items:
-            - const: hs_phy_irq
-            - const: ss_phy_irq
-            - const: dm_hs_phy_irq
-            - const: dp_hs_phy_irq
-
-  - if:
-      properties:
-        compatible:
-          contains:
-            enum:
               - qcom,msm8953-dwc3
-              - qcom,msm8996-dwc3
               - qcom,msm8998-dwc3
-              - qcom,sm6115-dwc3
     then:
       properties:
         interrupts:
-          maxItems: 2
+          minItems: 2
+          maxItems: 3
         interrupt-names:
           items:
-            - const: hs_phy_irq
+            - const: pwr_event
+            - const: qusb2_phy
             - const: ss_phy_irq
 
   - if:
@@ -417,37 +397,21 @@ allOf:
         compatible:
           contains:
             enum:
-              - qcom,ipq5018-dwc3
-              - qcom,ipq5332-dwc3
+              - qcom,msm8996-dwc3
+              - qcom,qcs404-dwc3
               - qcom,sdm660-dwc3
-    then:
-      properties:
-        interrupts:
-          minItems: 1
-          maxItems: 2
-        interrupt-names:
-          minItems: 1
-          items:
-            - const: hs_phy_irq
-            - const: ss_phy_irq
-
-  - if:
-      properties:
-        compatible:
-          contains:
-            enum:
-              - qcom,sc7280-dwc3
+              - qcom,sm6115-dwc3
+              - qcom,sm6125-dwc3
     then:
       properties:
         interrupts:
           minItems: 3
           maxItems: 4
         interrupt-names:
-          minItems: 3
           items:
+            - const: pwr_event
+            - const: qusb2_phy
             - const: hs_phy_irq
-            - const: dp_hs_phy_irq
-            - const: dm_hs_phy_irq
             - const: ss_phy_irq
 
   - if:
@@ -455,7 +419,8 @@ allOf:
         compatible:
           contains:
             enum:
-              - qcom,sc8280xp-dwc3
+              - qcom,ipq5332-dwc3
+              - qcom,x1e80100-dwc3
     then:
       properties:
         interrupts:
@@ -472,16 +437,35 @@ allOf:
         compatible:
           contains:
             enum:
+              - qcom,ipq4019-dwc3
+              - qcom,ipq8064-dwc3
+              - qcom,msm8994-dwc3
               - qcom,sa8775p-dwc3
+              - qcom,sc7180-dwc3
+              - qcom,sc7280-dwc3
+              - qcom,sc8280xp-dwc3
+              - qcom,sdm670-dwc3
+              - qcom,sdm845-dwc3
+              - qcom,sdx55-dwc3
+              - qcom,sdx65-dwc3
+              - qcom,sdx75-dwc3
+              - qcom,sm4250-dwc3
+              - qcom,sm6350-dwc3
+              - qcom,sm8150-dwc3
+              - qcom,sm8250-dwc3
+              - qcom,sm8350-dwc3
+              - qcom,sm8450-dwc3
+              - qcom,sm8550-dwc3
+              - qcom,sm8650-dwc3
     then:
       properties:
         interrupts:
-          minItems: 3
-          maxItems: 4
+          minItems: 4
+          maxItems: 5
         interrupt-names:
-          minItems: 3
           items:
             - const: pwr_event
+            - const: hs_phy_irq
             - const: dp_hs_phy_irq
             - const: dm_hs_phy_irq
             - const: ss_phy_irq
@@ -519,12 +503,13 @@ examples:
                           <&gcc GCC_USB30_PRIM_MASTER_CLK>;
             assigned-clock-rates = <19200000>, <150000000>;
 
-            interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
-                         <GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>,
+            interrupts = <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 489 IRQ_TYPE_EDGE_BOTH>,
                          <GIC_SPI 488 IRQ_TYPE_EDGE_BOTH>,
-                         <GIC_SPI 489 IRQ_TYPE_EDGE_BOTH>;
-            interrupt-names = "hs_phy_irq", "ss_phy_irq",
-                          "dm_hs_phy_irq", "dp_hs_phy_irq";
+                         <GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>;
+            interrupt-names = "pwr_event", "hs_phy_irq",
+                          "dp_hs_phy_irq", "dm_hs_phy_irq", "ss_phy_irq";
 
             power-domains = <&gcc USB30_PRIM_GDSC>;
 
diff --git a/Documentation/devicetree/bindings/usb/qcom,wcd939x-usbss.yaml b/Documentation/devicetree/bindings/usb/qcom,wcd939x-usbss.yaml
new file mode 100644
index 000000000000..7ddfd3313a18
--- /dev/null
+++ b/Documentation/devicetree/bindings/usb/qcom,wcd939x-usbss.yaml
@@ -0,0 +1,102 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/usb/qcom,wcd939x-usbss.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm WCD9380/WCD9385 USB SubSystem Altmode/Analog Audio Switch
+
+maintainers:
+  - Neil Armstrong <neil.armstrong@linaro.org>
+
+description:
+  Qualcomm WCD9390/WCD9395 is a standalone Hi-Fi audio codec IC with a
+  functionally separate USB SubSystem for Altmode/Analog Audio Switch
+  accessible over an I2C interface.
+  The Audio Headphone and Microphone data path between the Codec and the
+  USB-C Mux subsystems are external to the IC, thus requiring DT port-endpoint
+  graph description to handle USB-C altmode & orientation switching for Audio
+  Accessory Mode.
+
+properties:
+  compatible:
+    oneOf:
+      - const: qcom,wcd9390-usbss
+      - items:
+          - const: qcom,wcd9395-usbss
+          - const: qcom,wcd9390-usbss
+
+  reg:
+    maxItems: 1
+
+  reset-gpios:
+    maxItems: 1
+
+  vdd-supply:
+    description: USBSS VDD power supply
+
+  mode-switch:
+    description: Flag the port as possible handle of altmode switching
+    type: boolean
+
+  orientation-switch:
+    description: Flag the port as possible handler of orientation switching
+    type: boolean
+
+  ports:
+    $ref: /schemas/graph.yaml#/properties/ports
+    properties:
+      port@0:
+        $ref: /schemas/graph.yaml#/properties/port
+        description:
+          A port node to link the WCD939x USB SubSystem to a TypeC controller for the
+          purpose of handling altmode muxing and orientation switching.
+
+      port@1:
+        $ref: /schemas/graph.yaml#/properties/port
+        description:
+          A port node to link the WCD939x USB SubSystem to the Codec SubSystem for the
+          purpose of handling USB-C Audio Accessory Mode muxing and orientation switching.
+
+required:
+  - compatible
+  - reg
+  - ports
+
+additionalProperties: false
+
+examples:
+  - |
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        typec-mux@42 {
+            compatible = "qcom,wcd9390-usbss";
+            reg = <0x42>;
+
+            vdd-supply = <&vreg_bob>;
+
+            mode-switch;
+            orientation-switch;
+
+            ports {
+                #address-cells = <1>;
+                #size-cells = <0>;
+
+                port@0 {
+                    reg = <0>;
+                    wcd9390_usbss_sbu: endpoint {
+                        remote-endpoint = <&typec_sbu>;
+                    };
+                };
+                port@1 {
+                    reg = <1>;
+                    wcd9390_usbss_codec: endpoint {
+                        remote-endpoint = <&wcd9390_codec_usbss>;
+                    };
+                };
+            };
+        };
+    };
+...
diff --git a/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml b/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml
index bad55dfb2fa0..40ada78f2328 100644
--- a/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml
+++ b/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml
@@ -19,7 +19,7 @@ properties:
       - items:
           - enum:
               - renesas,usbhs-r7s9210   # RZ/A2
-              - renesas,usbhs-r9a07g043 # RZ/G2UL
+              - renesas,usbhs-r9a07g043 # RZ/G2UL and RZ/Five
               - renesas,usbhs-r9a07g044 # RZ/G2{L,LC}
               - renesas,usbhs-r9a07g054 # RZ/V2L
           - const: renesas,rza2-usbhs
diff --git a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml
index ee5af4b381b1..203a1eb66691 100644
--- a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml
+++ b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml
@@ -432,6 +432,10 @@ properties:
     items:
       enum: [1, 4, 8, 16, 32, 64, 128, 256]
 
+  num-hc-interrupters:
+    maximum: 8
+    default: 1
+
   port:
     $ref: /schemas/graph.yaml#/properties/port
     description:
diff --git a/Documentation/devicetree/bindings/usb/ti,tps6598x.yaml b/Documentation/devicetree/bindings/usb/ti,tps6598x.yaml
index 323d664ae06a..1745e28b3110 100644
--- a/Documentation/devicetree/bindings/usb/ti,tps6598x.yaml
+++ b/Documentation/devicetree/bindings/usb/ti,tps6598x.yaml
@@ -38,6 +38,10 @@ properties:
       - const: main
       - const: patch-address
 
+  reset-gpios:
+    description: GPIO used for the HRESET pin.
+    maxItems: 1
+
   wakeup-source: true
 
   interrupts:
@@ -90,6 +94,7 @@ additionalProperties: false
 
 examples:
   - |
+    #include <dt-bindings/gpio/gpio.h>
     #include <dt-bindings/interrupt-controller/irq.h>
     i2c {
         #address-cells = <1>;
@@ -106,6 +111,7 @@ examples:
 
             pinctrl-names = "default";
             pinctrl-0 = <&typec_pins>;
+            reset-gpios = <&gpio1 6 GPIO_ACTIVE_HIGH>;
 
             typec_con: connector {
                 compatible = "usb-c-connector";
diff --git a/Documentation/devicetree/bindings/usb/usb-xhci.yaml b/Documentation/devicetree/bindings/usb/usb-xhci.yaml
index 180a261c3e8f..4238ae896ef6 100644
--- a/Documentation/devicetree/bindings/usb/usb-xhci.yaml
+++ b/Documentation/devicetree/bindings/usb/usb-xhci.yaml
@@ -29,6 +29,12 @@ properties:
     description: Interrupt moderation interval
     default: 5000
 
+  num-hc-interrupters:
+    description: Maximum number of interrupters to allocate
+    $ref: /schemas/types.yaml#/definitions/uint16
+    minimum: 1
+    maximum: 1024
+
 additionalProperties: true
 
 examples:
diff --git a/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml b/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml
index 868dffe314bc..a7f75fe36665 100644
--- a/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml
+++ b/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml
@@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Xilinx udc controller
 
 maintainers:
-  - Piyush Mehta <piyush.mehta@amd.com>
+  - Mubin Sayyed <mubin.sayyed@amd.com>
+  - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml
index 02aaa1f538b2..1a0dc04f1db4 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.yaml
+++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml
@@ -121,6 +121,8 @@ patternProperties:
     description: Andes Technology Corporation
   "^anvo,.*":
     description: Anvo-Systems Dresden GmbH
+  "^aosong,.*":
+    description: Guangzhou Aosong Electronic Co., Ltd.
   "^apm,.*":
     description: Applied Micro Circuits Corporation (APM)
   "^apple,.*":
diff --git a/Documentation/devicetree/bindings/w1/amd,axi-1wire-host.yaml b/Documentation/devicetree/bindings/w1/amd,axi-1wire-host.yaml
new file mode 100644
index 000000000000..ef70fa2c0c5d
--- /dev/null
+++ b/Documentation/devicetree/bindings/w1/amd,axi-1wire-host.yaml
@@ -0,0 +1,44 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/w1/amd,axi-1wire-host.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: AMD AXI 1-wire bus host for programmable logic
+
+maintainers:
+  - Kris Chaplin <kris.chaplin@amd.com>
+
+properties:
+  compatible:
+    const: amd,axi-1wire-host
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - interrupts
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    onewire@a0000000 {
+        compatible = "amd,axi-1wire-host";
+        reg = <0xa0000000 0x10000>;
+        clocks = <&zynqmp_clk 0x47>;
+        interrupts = <GIC_SPI 0x59 IRQ_TYPE_LEVEL_HIGH>;
+    };
+
+...
diff --git a/Documentation/driver-api/dpll.rst b/Documentation/driver-api/dpll.rst
index e3d593841aa7..ea8d16600e16 100644
--- a/Documentation/driver-api/dpll.rst
+++ b/Documentation/driver-api/dpll.rst
@@ -545,7 +545,7 @@ In such scenario, dpll device input signal shall be also configurable
 to drive dpll with signal recovered from the PHY netdevice.
 This is done by exposing a pin to the netdevice - attaching pin to the
 netdevice itself with
-``netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin)``.
+``dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin)``.
 Exposed pin id handle ``DPLL_A_PIN_ID`` is then identifiable by the user
 as it is attached to rtnetlink respond to get ``RTM_NEWLINK`` command in
 nested attribute ``IFLA_DPLL_PIN``.
diff --git a/Documentation/driver-api/pci/p2pdma.rst b/Documentation/driver-api/pci/p2pdma.rst
index 44deb52beeb4..d0b241628cf1 100644
--- a/Documentation/driver-api/pci/p2pdma.rst
+++ b/Documentation/driver-api/pci/p2pdma.rst
@@ -83,19 +83,9 @@ this to include other types of resources like doorbells.
 Client Drivers
 --------------
 
-A client driver typically only has to conditionally change its DMA map
-routine to use the mapping function :c:func:`pci_p2pdma_map_sg()` instead
-of the usual :c:func:`dma_map_sg()` function. Memory mapped in this
-way does not need to be unmapped.
-
-The client may also, optionally, make use of
-:c:func:`is_pci_p2pdma_page()` to determine when to use the P2P mapping
-functions and when to use the regular mapping functions. In some
-situations, it may be more appropriate to use a flag to indicate a
-given request is P2P memory and map appropriately. It is important to
-ensure that struct pages that back P2P memory stay out of code that
-does not have support for them as other code may treat the pages as
-regular memory which may not be appropriate.
+A client driver only has to use the mapping API :c:func:`dma_map_sg()`
+and :c:func:`dma_unmap_sg()` functions as usual, and the implementation
+will do the right thing for the P2P capable memory.
 
 
 Orchestrator Drivers
diff --git a/Documentation/features/vm/TLB/arch-support.txt b/Documentation/features/vm/TLB/arch-support.txt
index 8fd22073a847..d222bd3ee749 100644
--- a/Documentation/features/vm/TLB/arch-support.txt
+++ b/Documentation/features/vm/TLB/arch-support.txt
@@ -20,7 +20,7 @@
     |    openrisc: |  ..  |
     |      parisc: | TODO |
     |     powerpc: | TODO |
-    |       riscv: | TODO |
+    |       riscv: |  ok  |
     |        s390: | TODO |
     |          sh: | TODO |
     |       sparc: | TODO |
diff --git a/Documentation/filesystems/files.rst b/Documentation/filesystems/files.rst
index 9e38e4c221ca..eb770f891b27 100644
--- a/Documentation/filesystems/files.rst
+++ b/Documentation/filesystems/files.rst
@@ -116,7 +116,7 @@ before and after the reference count increment. This pattern can be seen
 in get_file_rcu() and __files_get_rcu().
 
 In addition, it isn't possible to access or check fields in struct file
-without first aqcuiring a reference on it under rcu lookup. Not doing
+without first acquiring a reference on it under rcu lookup. Not doing
 that was always very dodgy and it was only usable for non-pointer data
 in struct file. With SLAB_TYPESAFE_BY_RCU it is necessary that callers
 either first acquire a reference or they must hold the files_lock of the
diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst
index e18bc5ae3b35..0ea1e44fa028 100644
--- a/Documentation/filesystems/index.rst
+++ b/Documentation/filesystems/index.rst
@@ -98,7 +98,6 @@ Documentation for filesystem implementations.
    isofs
    nilfs2
    nfs/index
-   ntfs
    ntfs3
    ocfs2
    ocfs2-online-filecheck
diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index d5bf4b6b7509..e664061ed55d 100644
--- a/Documentation/filesystems/locking.rst
+++ b/Documentation/filesystems/locking.rst
@@ -29,7 +29,7 @@ prototypes::
 	char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen);
 	struct vfsmount *(*d_automount)(struct path *path);
 	int (*d_manage)(const struct path *, bool);
-	struct dentry *(*d_real)(struct dentry *, const struct inode *);
+	struct dentry *(*d_real)(struct dentry *, enum d_real_type type);
 
 locking rules:
 
diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst
index 48b95d04f72d..4cc657d743f7 100644
--- a/Documentation/filesystems/netfs_library.rst
+++ b/Documentation/filesystems/netfs_library.rst
@@ -295,7 +295,6 @@ through which it can issue requests and negotiate::
 	struct netfs_request_ops {
 		void (*init_request)(struct netfs_io_request *rreq, struct file *file);
 		void (*free_request)(struct netfs_io_request *rreq);
-		int (*begin_cache_operation)(struct netfs_io_request *rreq);
 		void (*expand_readahead)(struct netfs_io_request *rreq);
 		bool (*clamp_length)(struct netfs_io_subrequest *subreq);
 		void (*issue_read)(struct netfs_io_subrequest *subreq);
@@ -317,20 +316,6 @@ The operations are as follows:
    [Optional] This is called as the request is being deallocated so that the
    filesystem can clean up any state it has attached there.
 
- * ``begin_cache_operation()``
-
-   [Optional] This is called to ask the network filesystem to call into the
-   cache (if present) to initialise the caching state for this read.  The netfs
-   library module cannot access the cache directly, so the cache should call
-   something like fscache_begin_read_operation() to do this.
-
-   The cache gets to store its state in ->cache_resources and must set a table
-   of operations of its own there (though of a different type).
-
-   This should return 0 on success and an error code otherwise.  If an error is
-   reported, the operation may proceed anyway, just without local caching (only
-   out of memory and interruption errors cause failure here).
-
  * ``expand_readahead()``
 
    [Optional] This is called to allow the filesystem to expand the size of a
@@ -460,14 +445,14 @@ When implementing a local cache to be used by the read helpers, two things are
 required: some way for the network filesystem to initialise the caching for a
 read request and a table of operations for the helpers to call.
 
-The network filesystem's ->begin_cache_operation() method is called to set up a
-cache and this must call into the cache to do the work.  If using fscache, for
-example, the cache would call::
+To begin a cache operation on an fscache object, the following function is
+called::
 
 	int fscache_begin_read_operation(struct netfs_io_request *rreq,
 					 struct fscache_cookie *cookie);
 
-passing in the request pointer and the cookie corresponding to the file.
+passing in the request pointer and the cookie corresponding to the file.  This
+fills in the cache resources mentioned below.
 
 The netfs_io_request object contains a place for the cache to hang its
 state::
diff --git a/Documentation/filesystems/ntfs.rst b/Documentation/filesystems/ntfs.rst
deleted file mode 100644
index 5bb093a26485..000000000000
--- a/Documentation/filesystems/ntfs.rst
+++ /dev/null
@@ -1,466 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0
-
-================================
-The Linux NTFS filesystem driver
-================================
-
-
-.. Table of contents
-
-   - Overview
-   - Web site
-   - Features
-   - Supported mount options
-   - Known bugs and (mis-)features
-   - Using NTFS volume and stripe sets
-     - The Device-Mapper driver
-     - The Software RAID / MD driver
-     - Limitations when using the MD driver
-
-
-Overview
-========
-
-Linux-NTFS comes with a number of user-space programs known as ntfsprogs.
-These include mkntfs, a full-featured ntfs filesystem format utility,
-ntfsundelete used for recovering files that were unintentionally deleted
-from an NTFS volume and ntfsresize which is used to resize an NTFS partition.
-See the web site for more information.
-
-To mount an NTFS 1.2/3.x (Windows NT4/2000/XP/2003) volume, use the file
-system type 'ntfs'.  The driver currently supports read-only mode (with no
-fault-tolerance, encryption or journalling) and very limited, but safe, write
-support.
-
-For fault tolerance and raid support (i.e. volume and stripe sets), you can
-use the kernel's Software RAID / MD driver.  See section "Using Software RAID
-with NTFS" for details.
-
-
-Web site
-========
-
-There is plenty of additional information on the linux-ntfs web site
-at http://www.linux-ntfs.org/
-
-The web site has a lot of additional information, such as a comprehensive
-FAQ, documentation on the NTFS on-disk format, information on the Linux-NTFS
-userspace utilities, etc.
-
-
-Features
-========
-
-- This is a complete rewrite of the NTFS driver that used to be in the 2.4 and
-  earlier kernels.  This new driver implements NTFS read support and is
-  functionally equivalent to the old ntfs driver and it also implements limited
-  write support.  The biggest limitation at present is that files/directories
-  cannot be created or deleted.  See below for the list of write features that
-  are so far supported.  Another limitation is that writing to compressed files
-  is not implemented at all.  Also, neither read nor write access to encrypted
-  files is so far implemented.
-- The new driver has full support for sparse files on NTFS 3.x volumes which
-  the old driver isn't happy with.
-- The new driver supports execution of binaries due to mmap() now being
-  supported.
-- The new driver supports loopback mounting of files on NTFS which is used by
-  some Linux distributions to enable the user to run Linux from an NTFS
-  partition by creating a large file while in Windows and then loopback
-  mounting the file while in Linux and creating a Linux filesystem on it that
-  is used to install Linux on it.
-- A comparison of the two drivers using::
-
-	time find . -type f -exec md5sum "{}" \;
-
-  run three times in sequence with each driver (after a reboot) on a 1.4GiB
-  NTFS partition, showed the new driver to be 20% faster in total time elapsed
-  (from 9:43 minutes on average down to 7:53).  The time spent in user space
-  was unchanged but the time spent in the kernel was decreased by a factor of
-  2.5 (from 85 CPU seconds down to 33).
-- The driver does not support short file names in general.  For backwards
-  compatibility, we implement access to files using their short file names if
-  they exist.  The driver will not create short file names however, and a
-  rename will discard any existing short file name.
-- The new driver supports exporting of mounted NTFS volumes via NFS.
-- The new driver supports async io (aio).
-- The new driver supports fsync(2), fdatasync(2), and msync(2).
-- The new driver supports readv(2) and writev(2).
-- The new driver supports access time updates (including mtime and ctime).
-- The new driver supports truncate(2) and open(2) with O_TRUNC.  But at present
-  only very limited support for highly fragmented files, i.e. ones which have
-  their data attribute split across multiple extents, is included.  Another
-  limitation is that at present truncate(2) will never create sparse files,
-  since to mark a file sparse we need to modify the directory entry for the
-  file and we do not implement directory modifications yet.
-- The new driver supports write(2) which can both overwrite existing data and
-  extend the file size so that you can write beyond the existing data.  Also,
-  writing into sparse regions is supported and the holes are filled in with
-  clusters.  But at present only limited support for highly fragmented files,
-  i.e. ones which have their data attribute split across multiple extents, is
-  included.  Another limitation is that write(2) will never create sparse
-  files, since to mark a file sparse we need to modify the directory entry for
-  the file and we do not implement directory modifications yet.
-
-Supported mount options
-=======================
-
-In addition to the generic mount options described by the manual page for the
-mount command (man 8 mount, also see man 5 fstab), the NTFS driver supports the
-following mount options:
-
-======================= =======================================================
-iocharset=name		Deprecated option.  Still supported but please use
-			nls=name in the future.  See description for nls=name.
-
-nls=name		Character set to use when returning file names.
-			Unlike VFAT, NTFS suppresses names that contain
-			unconvertible characters.  Note that most character
-			sets contain insufficient characters to represent all
-			possible Unicode characters that can exist on NTFS.
-			To be sure you are not missing any files, you are
-			advised to use nls=utf8 which is capable of
-			representing all Unicode characters.
-
-utf8=<bool>		Option no longer supported.  Currently mapped to
-			nls=utf8 but please use nls=utf8 in the future and
-			make sure utf8 is compiled either as module or into
-			the kernel.  See description for nls=name.
-
-uid=
-gid=
-umask=			Provide default owner, group, and access mode mask.
-			These options work as documented in mount(8).  By
-			default, the files/directories are owned by root and
-			he/she has read and write permissions, as well as
-			browse permission for directories.  No one else has any
-			access permissions.  I.e. the mode on all files is by
-			default rw------- and for directories rwx------, a
-			consequence of the default fmask=0177 and dmask=0077.
-			Using a umask of zero will grant all permissions to
-			everyone, i.e. all files and directories will have mode
-			rwxrwxrwx.
-
-fmask=
-dmask=			Instead of specifying umask which applies both to
-			files and directories, fmask applies only to files and
-			dmask only to directories.
-
-sloppy=<BOOL>		If sloppy is specified, ignore unknown mount options.
-			Otherwise the default behaviour is to abort mount if
-			any unknown options are found.
-
-show_sys_files=<BOOL>	If show_sys_files is specified, show the system files
-			in directory listings.  Otherwise the default behaviour
-			is to hide the system files.
-			Note that even when show_sys_files is specified, "$MFT"
-			will not be visible due to bugs/mis-features in glibc.
-			Further, note that irrespective of show_sys_files, all
-			files are accessible by name, i.e. you can always do
-			"ls -l \$UpCase" for example to specifically show the
-			system file containing the Unicode upcase table.
-
-case_sensitive=<BOOL>	If case_sensitive is specified, treat all file names as
-			case sensitive and create file names in the POSIX
-			namespace.  Otherwise the default behaviour is to treat
-			file names as case insensitive and to create file names
-			in the WIN32/LONG name space.  Note, the Linux NTFS
-			driver will never create short file names and will
-			remove them on rename/delete of the corresponding long
-			file name.
-			Note that files remain accessible via their short file
-			name, if it exists.  If case_sensitive, you will need
-			to provide the correct case of the short file name.
-
-disable_sparse=<BOOL>	If disable_sparse is specified, creation of sparse
-			regions, i.e. holes, inside files is disabled for the
-			volume (for the duration of this mount only).  By
-			default, creation of sparse regions is enabled, which
-			is consistent with the behaviour of traditional Unix
-			filesystems.
-
-errors=opt		What to do when critical filesystem errors are found.
-			Following values can be used for "opt":
-
-			  ========  =========================================
-			  continue  DEFAULT, try to clean-up as much as
-				    possible, e.g. marking a corrupt inode as
-				    bad so it is no longer accessed, and then
-				    continue.
-			  recover   At present only supported is recovery of
-				    the boot sector from the backup copy.
-				    If read-only mount, the recovery is done
-				    in memory only and not written to disk.
-			  ========  =========================================
-
-			Note that the options are additive, i.e. specifying::
-
-			   errors=continue,errors=recover
-
-			means the driver will attempt to recover and if that
-			fails it will clean-up as much as possible and
-			continue.
-
-mft_zone_multiplier=	Set the MFT zone multiplier for the volume (this
-			setting is not persistent across mounts and can be
-			changed from mount to mount but cannot be changed on
-			remount).  Values of 1 to 4 are allowed, 1 being the
-			default.  The MFT zone multiplier determines how much
-			space is reserved for the MFT on the volume.  If all
-			other space is used up, then the MFT zone will be
-			shrunk dynamically, so this has no impact on the
-			amount of free space.  However, it can have an impact
-			on performance by affecting fragmentation of the MFT.
-			In general use the default.  If you have a lot of small
-			files then use a higher value.  The values have the
-			following meaning:
-
-			      =====	    =================================
-			      Value	     MFT zone size (% of volume size)
-			      =====	    =================================
-				1		12.5%
-				2		25%
-				3		37.5%
-				4		50%
-			      =====	    =================================
-
-			Note this option is irrelevant for read-only mounts.
-======================= =======================================================
-
-
-Known bugs and (mis-)features
-=============================
-
-- The link count on each directory inode entry is set to 1, due to Linux not
-  supporting directory hard links.  This may well confuse some user space
-  applications, since the directory names will have the same inode numbers.
-  This also speeds up ntfs_read_inode() immensely.  And we haven't found any
-  problems with this approach so far.  If you find a problem with this, please
-  let us know.
-
-
-Please send bug reports/comments/feedback/abuse to the Linux-NTFS development
-list at sourceforge: linux-ntfs-dev@lists.sourceforge.net
-
-
-Using NTFS volume and stripe sets
-=================================
-
-For support of volume and stripe sets, you can either use the kernel's
-Device-Mapper driver or the kernel's Software RAID / MD driver.  The former is
-the recommended one to use for linear raid.  But the latter is required for
-raid level 5.  For striping and mirroring, either driver should work fine.
-
-
-The Device-Mapper driver
-------------------------
-
-You will need to create a table of the components of the volume/stripe set and
-how they fit together and load this into the kernel using the dmsetup utility
-(see man 8 dmsetup).
-
-Linear volume sets, i.e. linear raid, has been tested and works fine.  Even
-though untested, there is no reason why stripe sets, i.e. raid level 0, and
-mirrors, i.e. raid level 1 should not work, too.  Stripes with parity, i.e.
-raid level 5, unfortunately cannot work yet because the current version of the
-Device-Mapper driver does not support raid level 5.  You may be able to use the
-Software RAID / MD driver for raid level 5, see the next section for details.
-
-To create the table describing your volume you will need to know each of its
-components and their sizes in sectors, i.e. multiples of 512-byte blocks.
-
-For NT4 fault tolerant volumes you can obtain the sizes using fdisk.  So for
-example if one of your partitions is /dev/hda2 you would do::
-
-    $ fdisk -ul /dev/hda
-
-    Disk /dev/hda: 81.9 GB, 81964302336 bytes
-    255 heads, 63 sectors/track, 9964 cylinders, total 160086528 sectors
-    Units = sectors of 1 * 512 = 512 bytes
-
-	Device Boot      Start         End      Blocks   Id  System
-	/dev/hda1   *          63     4209029     2104483+  83  Linux
-	/dev/hda2         4209030    37768814    16779892+  86  NTFS
-	/dev/hda3        37768815    46170809     4200997+  83  Linux
-
-And you would know that /dev/hda2 has a size of 37768814 - 4209030 + 1 =
-33559785 sectors.
-
-For Win2k and later dynamic disks, you can for example use the ldminfo utility
-which is part of the Linux LDM tools (the latest version at the time of
-writing is linux-ldm-0.0.8.tar.bz2).  You can download it from:
-
-	http://www.linux-ntfs.org/
-
-Simply extract the downloaded archive (tar xvjf linux-ldm-0.0.8.tar.bz2), go
-into it (cd linux-ldm-0.0.8) and change to the test directory (cd test).  You
-will find the precompiled (i386) ldminfo utility there.  NOTE: You will not be
-able to compile this yourself easily so use the binary version!
-
-Then you would use ldminfo in dump mode to obtain the necessary information::
-
-    $ ./ldminfo --dump /dev/hda
-
-This would dump the LDM database found on /dev/hda which describes all of your
-dynamic disks and all the volumes on them.  At the bottom you will see the
-VOLUME DEFINITIONS section which is all you really need.  You may need to look
-further above to determine which of the disks in the volume definitions is
-which device in Linux.  Hint: Run ldminfo on each of your dynamic disks and
-look at the Disk Id close to the top of the output for each (the PRIVATE HEADER
-section).  You can then find these Disk Ids in the VBLK DATABASE section in the
-<Disk> components where you will get the LDM Name for the disk that is found in
-the VOLUME DEFINITIONS section.
-
-Note you will also need to enable the LDM driver in the Linux kernel.  If your
-distribution did not enable it, you will need to recompile the kernel with it
-enabled.  This will create the LDM partitions on each device at boot time.  You
-would then use those devices (for /dev/hda they would be /dev/hda1, 2, 3, etc)
-in the Device-Mapper table.
-
-You can also bypass using the LDM driver by using the main device (e.g.
-/dev/hda) and then using the offsets of the LDM partitions into this device as
-the "Start sector of device" when creating the table.  Once again ldminfo would
-give you the correct information to do this.
-
-Assuming you know all your devices and their sizes things are easy.
-
-For a linear raid the table would look like this (note all values are in
-512-byte sectors)::
-
-    # Offset into	Size of this	Raid type	Device		Start sector
-    # volume	device						of device
-    0		1028161		linear		/dev/hda1	0
-    1028161		3903762		linear		/dev/hdb2	0
-    4931923		2103211		linear		/dev/hdc1	0
-
-For a striped volume, i.e. raid level 0, you will need to know the chunk size
-you used when creating the volume.  Windows uses 64kiB as the default, so it
-will probably be this unless you changes the defaults when creating the array.
-
-For a raid level 0 the table would look like this (note all values are in
-512-byte sectors)::
-
-    # Offset   Size	    Raid     Number   Chunk  1st        Start	2nd	  Start
-    # into     of the   type     of	      size   Device	in	Device	  in
-    # volume   volume	     stripes			device		  device
-    0	   2056320  striped  2	      128    /dev/hda1	0	/dev/hdb1 0
-
-If there are more than two devices, just add each of them to the end of the
-line.
-
-Finally, for a mirrored volume, i.e. raid level 1, the table would look like
-this (note all values are in 512-byte sectors)::
-
-    # Ofs Size   Raid   Log  Number Region Should Number Source  Start Target Start
-    # in  of the type   type of log size   sync?  of     Device  in    Device in
-    # vol volume		 params		     mirrors	     Device	  Device
-    0    2056320 mirror core 2	16     nosync 2	   /dev/hda1 0   /dev/hdb1 0
-
-If you are mirroring to multiple devices you can specify further targets at the
-end of the line.
-
-Note the "Should sync?" parameter "nosync" means that the two mirrors are
-already in sync which will be the case on a clean shutdown of Windows.  If the
-mirrors are not clean, you can specify the "sync" option instead of "nosync"
-and the Device-Mapper driver will then copy the entirety of the "Source Device"
-to the "Target Device" or if you specified multiple target devices to all of
-them.
-
-Once you have your table, save it in a file somewhere (e.g. /etc/ntfsvolume1),
-and hand it over to dmsetup to work with, like so::
-
-    $ dmsetup create myvolume1 /etc/ntfsvolume1
-
-You can obviously replace "myvolume1" with whatever name you like.
-
-If it all worked, you will now have the device /dev/device-mapper/myvolume1
-which you can then just use as an argument to the mount command as usual to
-mount the ntfs volume.  For example::
-
-    $ mount -t ntfs -o ro /dev/device-mapper/myvolume1 /mnt/myvol1
-
-(You need to create the directory /mnt/myvol1 first and of course you can use
-anything you like instead of /mnt/myvol1 as long as it is an existing
-directory.)
-
-It is advisable to do the mount read-only to see if the volume has been setup
-correctly to avoid the possibility of causing damage to the data on the ntfs
-volume.
-
-
-The Software RAID / MD driver
------------------------------
-
-An alternative to using the Device-Mapper driver is to use the kernel's
-Software RAID / MD driver.  For which you need to set up your /etc/raidtab
-appropriately (see man 5 raidtab).
-
-Linear volume sets, i.e. linear raid, as well as stripe sets, i.e. raid level
-0, have been tested and work fine (though see section "Limitations when using
-the MD driver with NTFS volumes" especially if you want to use linear raid).
-Even though untested, there is no reason why mirrors, i.e. raid level 1, and
-stripes with parity, i.e. raid level 5, should not work, too.
-
-You have to use the "persistent-superblock 0" option for each raid-disk in the
-NTFS volume/stripe you are configuring in /etc/raidtab as the persistent
-superblock used by the MD driver would damage the NTFS volume.
-
-Windows by default uses a stripe chunk size of 64k, so you probably want the
-"chunk-size 64k" option for each raid-disk, too.
-
-For example, if you have a stripe set consisting of two partitions /dev/hda5
-and /dev/hdb1 your /etc/raidtab would look like this::
-
-    raiddev /dev/md0
-	    raid-level	0
-	    nr-raid-disks	2
-	    nr-spare-disks	0
-	    persistent-superblock	0
-	    chunk-size	64k
-	    device		/dev/hda5
-	    raid-disk	0
-	    device		/dev/hdb1
-	    raid-disk	1
-
-For linear raid, just change the raid-level above to "raid-level linear", for
-mirrors, change it to "raid-level 1", and for stripe sets with parity, change
-it to "raid-level 5".
-
-Note for stripe sets with parity you will also need to tell the MD driver
-which parity algorithm to use by specifying the option "parity-algorithm
-which", where you need to replace "which" with the name of the algorithm to
-use (see man 5 raidtab for available algorithms) and you will have to try the
-different available algorithms until you find one that works.  Make sure you
-are working read-only when playing with this as you may damage your data
-otherwise.  If you find which algorithm works please let us know (email the
-linux-ntfs developers list linux-ntfs-dev@lists.sourceforge.net or drop in on
-IRC in channel #ntfs on the irc.freenode.net network) so we can update this
-documentation.
-
-Once the raidtab is setup, run for example raid0run -a to start all devices or
-raid0run /dev/md0 to start a particular md device, in this case /dev/md0.
-
-Then just use the mount command as usual to mount the ntfs volume using for
-example::
-
-    mount -t ntfs -o ro /dev/md0 /mnt/myntfsvolume
-
-It is advisable to do the mount read-only to see if the md volume has been
-setup correctly to avoid the possibility of causing damage to the data on the
-ntfs volume.
-
-
-Limitations when using the Software RAID / MD driver
------------------------------------------------------
-
-Using the md driver will not work properly if any of your NTFS partitions have
-an odd number of sectors.  This is especially important for linear raid as all
-data after the first partition with an odd number of sectors will be offset by
-one or more sectors so if you mount such a partition with write support you
-will cause massive damage to the data on the volume which will only become
-apparent when you try to use the volume again under Windows.
-
-So when using linear raid, make sure that all your partitions have an even
-number of sectors BEFORE attempting to use it.  You have been warned!
-
-Even better is to simply use the Device-Mapper for linear raid and then you do
-not have this problem with odd numbers of sectors.
diff --git a/Documentation/filesystems/overlayfs.rst b/Documentation/filesystems/overlayfs.rst
index 1c244866041a..165514401441 100644
--- a/Documentation/filesystems/overlayfs.rst
+++ b/Documentation/filesystems/overlayfs.rst
@@ -145,7 +145,9 @@ filesystem, an overlay filesystem needs to record in the upper filesystem
 that files have been removed.  This is done using whiteouts and opaque
 directories (non-directories are always opaque).
 
-A whiteout is created as a character device with 0/0 device number.
+A whiteout is created as a character device with 0/0 device number or
+as a zero-size regular file with the xattr "trusted.overlay.whiteout".
+
 When a whiteout is found in the upper level of a merged directory, any
 matching name in the lower level is ignored, and the whiteout itself
 is also hidden.
@@ -154,6 +156,13 @@ A directory is made opaque by setting the xattr "trusted.overlay.opaque"
 to "y".  Where the upper filesystem contains an opaque directory, any
 directory in the lower filesystem with the same name is ignored.
 
+An opaque directory should not conntain any whiteouts, because they do not
+serve any purpose.  A merge directory containing regular files with the xattr
+"trusted.overlay.whiteout", should be additionally marked by setting the xattr
+"trusted.overlay.opaque" to "x" on the merge directory itself.
+This is needed to avoid the overhead of checking the "trusted.overlay.whiteout"
+on all entries during readdir in the common case.
+
 readdir
 -------
 
@@ -534,8 +543,9 @@ A lower dir with a regular whiteout will always be handled by the overlayfs
 mount, so to support storing an effective whiteout file in an overlayfs mount an
 alternative form of whiteout is supported. This form is a regular, zero-size
 file with the "overlay.whiteout" xattr set, inside a directory with the
-"overlay.whiteouts" xattr set. Such whiteouts are never created by overlayfs,
-but can be used by userspace tools (like containers) that generate lower layers.
+"overlay.opaque" xattr set to "x" (see `whiteouts and opaque directories`_).
+These alternative whiteouts are never created by overlayfs, but can be used by
+userspace tools (like containers) that generate lower layers.
 These alternative whiteouts can be escaped using the standard xattr escape
 mechanism in order to properly nest to any depth.
 
diff --git a/Documentation/filesystems/smb/ksmbd.rst b/Documentation/filesystems/smb/ksmbd.rst
index 7bed96d794fc..6b30e43a0d11 100644
--- a/Documentation/filesystems/smb/ksmbd.rst
+++ b/Documentation/filesystems/smb/ksmbd.rst
@@ -73,15 +73,14 @@ Auto Negotiation               Supported.
 Compound Request               Supported.
 Oplock Cache Mechanism         Supported.
 SMB2 leases(v1 lease)          Supported.
-Directory leases(v2 lease)     Planned for future.
+Directory leases(v2 lease)     Supported.
 Multi-credits                  Supported.
 NTLM/NTLMv2                    Supported.
 HMAC-SHA256 Signing            Supported.
 Secure negotiate               Supported.
 Signing Update                 Supported.
 Pre-authentication integrity   Supported.
-SMB3 encryption(CCM, GCM)      Supported. (CCM and GCM128 supported, GCM256 in
-                               progress)
+SMB3 encryption(CCM, GCM)      Supported. (CCM/GCM128 and CCM/GCM256 supported)
 SMB direct(RDMA)               Supported.
 SMB3 Multi-channel             Partially Supported. Planned to implement
                                replay/retry mechanisms for future.
@@ -112,6 +111,10 @@ DCE/RPC support                Partially Supported. a few calls(NetShareEnumAll,
                                for Witness protocol e.g.)
 ksmbd/nfsd interoperability    Planned for future. The features that ksmbd
                                support are Leases, Notify, ACLs and Share modes.
+SMB3.1.1 Compression           Planned for future.
+SMB3.1.1 over QUIC             Planned for future.
+Signing/Encryption over RDMA   Planned for future.
+SMB3.1.1 GMAC signing support  Planned for future.
 ============================== =================================================
 
 
diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
index eebcc0f9e2bc..6e903a903f8f 100644
--- a/Documentation/filesystems/vfs.rst
+++ b/Documentation/filesystems/vfs.rst
@@ -1264,7 +1264,7 @@ defined:
 		char *(*d_dname)(struct dentry *, char *, int);
 		struct vfsmount *(*d_automount)(struct path *);
 		int (*d_manage)(const struct path *, bool);
-		struct dentry *(*d_real)(struct dentry *, const struct inode *);
+		struct dentry *(*d_real)(struct dentry *, enum d_real_type type);
 	};
 
 ``d_revalidate``
@@ -1419,16 +1419,14 @@ defined:
 	the dentry being transited from.
 
 ``d_real``
-	overlay/union type filesystems implement this method to return
-	one of the underlying dentries hidden by the overlay.  It is
-	used in two different modes:
+	overlay/union type filesystems implement this method to return one
+	of the underlying dentries of a regular file hidden by the overlay.
 
-	Called from file_dentry() it returns the real dentry matching
-	the inode argument.  The real dentry may be from a lower layer
-	already copied up, but still referenced from the file.  This
-	mode is selected with a non-NULL inode argument.
+	The 'type' argument takes the values D_REAL_DATA or D_REAL_METADATA
+	for returning the real underlying dentry that refers to the inode
+	hosting the file's data or metadata respectively.
 
-	With NULL inode the topmost real underlying dentry is returned.
+	For non-regular files, the 'dentry' argument is returned.
 
 Each dentry has a pointer to its parent dentry, as well as a hash list
 of child dentries.  Child dentries are basically like files in a
diff --git a/Documentation/kbuild/Kconfig.recursion-issue-01 b/Documentation/kbuild/Kconfig.recursion-issue-01
index e8877db0461f..ac49836d8ecf 100644
--- a/Documentation/kbuild/Kconfig.recursion-issue-01
+++ b/Documentation/kbuild/Kconfig.recursion-issue-01
@@ -16,13 +16,13 @@
 # that are possible for CORE. So for example if CORE_BELL_A_ADVANCED is 'y',
 # CORE must be 'y' too.
 #
-#  * What influences CORE_BELL_A_ADVANCED ?
+#  * What influences CORE_BELL_A_ADVANCED?
 #
 # As the name implies CORE_BELL_A_ADVANCED is an advanced feature of
 # CORE_BELL_A so naturally it depends on CORE_BELL_A. So if CORE_BELL_A is 'y'
 # we know CORE_BELL_A_ADVANCED can be 'y' too.
 #
-#   * What influences CORE_BELL_A ?
+#   * What influences CORE_BELL_A?
 #
 # CORE_BELL_A depends on CORE, so CORE influences CORE_BELL_A.
 #
@@ -34,7 +34,7 @@
 # the "recursive dependency detected" error.
 #
 # Reading the Documentation/kbuild/Kconfig.recursion-issue-01 file it may be
-# obvious that an easy to solution to this problem should just be the removal
+# obvious that an easy solution to this problem should just be the removal
 # of the "select CORE" from CORE_BELL_A_ADVANCED as that is implicit already
 # since CORE_BELL_A depends on CORE. Recursive dependency issues are not always
 # so trivial to resolve, we provide another example below of practical
diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml
index b14aed18065f..3dcc9ece272a 100644
--- a/Documentation/netlink/specs/dpll.yaml
+++ b/Documentation/netlink/specs/dpll.yaml
@@ -384,8 +384,6 @@ operations:
             - type
 
       dump:
-        pre: dpll-lock-dumpit
-        post: dpll-unlock-dumpit
         reply: *dev-attrs
 
     -
@@ -473,8 +471,6 @@ operations:
             - fractional-frequency-offset
 
       dump:
-        pre: dpll-lock-dumpit
-        post: dpll-unlock-dumpit
         request:
           attributes:
             - id
diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml
index 1ad01d52a863..8e4d19adee8c 100644
--- a/Documentation/netlink/specs/rt_link.yaml
+++ b/Documentation/netlink/specs/rt_link.yaml
@@ -942,6 +942,10 @@ attribute-sets:
       -
         name: gro-ipv4-max-size
         type: u32
+      -
+        name: dpll-pin
+        type: nest
+        nested-attributes: link-dpll-pin-attrs
   -
     name: af-spec-attrs
     attributes:
@@ -1627,6 +1631,12 @@ attribute-sets:
       -
         name: used
         type: u8
+  -
+    name: link-dpll-pin-attrs
+    attributes:
+      -
+        name: id
+        type: u32
 
 sub-messages:
   -
diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst
index e33ad2401ad7..562f46b41274 100644
--- a/Documentation/networking/devlink/devlink-port.rst
+++ b/Documentation/networking/devlink/devlink-port.rst
@@ -126,7 +126,7 @@ Users may also set the RoCE capability of the function using
 `devlink port function set roce` command.
 
 Users may also set the function as migratable using
-'devlink port function set migratable' command.
+`devlink port function set migratable` command.
 
 Users may also set the IPsec crypto capability of the function using
 `devlink port function set ipsec_crypto` command.
diff --git a/Documentation/networking/net_cachelines/inet_sock.rst b/Documentation/networking/net_cachelines/inet_sock.rst
index a2babd0d7954..595d7ef5fc8b 100644
--- a/Documentation/networking/net_cachelines/inet_sock.rst
+++ b/Documentation/networking/net_cachelines/inet_sock.rst
@@ -1,9 +1,9 @@
 .. SPDX-License-Identifier: GPL-2.0
 .. Copyright (C) 2023 Google LLC
 
-=====================================================
-inet_connection_sock struct fast path usage breakdown
-=====================================================
+==========================================
+inet_sock struct fast path usage breakdown
+==========================================
 
 Type                    Name                  fastpath_tx_access  fastpath_rx_access  comment
 ..struct                ..inet_sock                                                     
diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index e75a53593bb9..dceb49d56a91 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -136,8 +136,8 @@ struct_netpoll_info*                npinfo                  -
 possible_net_t                      nd_net                  -                   read_mostly         (dev_net)napi_busy_loop,tcp_v(4/6)_rcv,ip(v6)_rcv,ip(6)_input,ip(6)_input_finish
 void*                               ml_priv                                                         
 enum_netdev_ml_priv_type            ml_priv_type                                                    
-struct_pcpu_lstats__percpu*         lstats                                                          
-struct_pcpu_sw_netstats__percpu*    tstats                                                          
+struct_pcpu_lstats__percpu*         lstats                  read_mostly                             dev_lstats_add()
+struct_pcpu_sw_netstats__percpu*    tstats                  read_mostly                             dev_sw_netstats_tx_add()
 struct_pcpu_dstats__percpu*         dstats                                                          
 struct_garp_port*                   garp_port                                                       
 struct_mrp_port*                    mrp_port                                                        
diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst
index 97d7a5c8e01c..1c154cbd1848 100644
--- a/Documentation/networking/net_cachelines/tcp_sock.rst
+++ b/Documentation/networking/net_cachelines/tcp_sock.rst
@@ -38,13 +38,13 @@ u32                           max_window              read_mostly         -
 u32                           mss_cache               read_mostly         read_mostly         tcp_rate_check_app_limited,tcp_current_mss,tcp_sync_mss,tcp_sndbuf_expand,tcp_tso_should_defer(tx);tcp_update_pacing_rate,tcp_clean_rtx_queue(rx)
 u32                           window_clamp            read_mostly         read_write          tcp_rcv_space_adjust,__tcp_select_window
 u32                           rcv_ssthresh            read_mostly         -                   __tcp_select_window
-u82                           scaling_ratio                                                   
+u8                            scaling_ratio           read_mostly         read_mostly         tcp_win_from_space
 struct                        tcp_rack                                                        
 u16                           advmss                  -                   read_mostly         tcp_rcv_space_adjust
 u8                            compressed_ack                                                  
 u8:2                          dup_ack_counter                                                 
 u8:1                          tlp_retrans                                                     
-u8:1                          tcp_usec_ts                                                     
+u8:1                          tcp_usec_ts             read_mostly         read_mostly
 u32                           chrono_start            read_write          -                   tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data)
 u32[3]                        chrono_stat             read_write          -                   tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data)
 u8:2                          chrono_type             read_write          -                   tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data)
diff --git a/Documentation/process/4.Coding.rst b/Documentation/process/4.Coding.rst
index 1f0d81f44e14..c2046dec0c2f 100644
--- a/Documentation/process/4.Coding.rst
+++ b/Documentation/process/4.Coding.rst
@@ -66,6 +66,10 @@ for aligning variables/macros, for reflowing text and other similar tasks.
 See the file :ref:`Documentation/process/clang-format.rst <clangformat>`
 for more details.
 
+Some basic editor settings, such as indentation and line endings, will be
+set automatically if you are using an editor that is compatible with
+EditorConfig. See the official EditorConfig website for more information:
+https://editorconfig.org/
 
 Abstraction layers
 ******************
diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
index 50b3d1cb1115..c78ecc1e176f 100644
--- a/Documentation/process/changes.rst
+++ b/Documentation/process/changes.rst
@@ -31,7 +31,7 @@ you probably needn't concern yourself with pcmciautils.
 ====================== ===============  ========================================
 GNU C                  5.1              gcc --version
 Clang/LLVM (optional)  11.0.0           clang --version
-Rust (optional)        1.74.1           rustc --version
+Rust (optional)        1.76.0           rustc --version
 bindgen (optional)     0.65.1           bindgen --version
 GNU make               3.82             make --version
 bash                   4.2              bash --version
diff --git a/Documentation/process/coding-style.rst b/Documentation/process/coding-style.rst
index 6db37a46d305..c48382c6b477 100644
--- a/Documentation/process/coding-style.rst
+++ b/Documentation/process/coding-style.rst
@@ -735,6 +735,10 @@ for aligning variables/macros, for reflowing text and other similar tasks.
 See the file :ref:`Documentation/process/clang-format.rst <clangformat>`
 for more details.
 
+Some basic editor settings, such as indentation and line endings, will be
+set automatically if you are using an editor that is compatible with
+EditorConfig. See the official EditorConfig website for more information:
+https://editorconfig.org/
 
 10) Kconfig configuration files
 -------------------------------
diff --git a/Documentation/process/cve.rst b/Documentation/process/cve.rst
new file mode 100644
index 000000000000..5e2753eff729
--- /dev/null
+++ b/Documentation/process/cve.rst
@@ -0,0 +1,121 @@
+====
+CVEs
+====
+
+Common Vulnerabilities and Exposure (CVE®) numbers were developed as an
+unambiguous way to identify, define, and catalog publicly disclosed
+security vulnerabilities.  Over time, their usefulness has declined with
+regards to the kernel project, and CVE numbers were very often assigned
+in inappropriate ways and for inappropriate reasons.  Because of this,
+the kernel development community has tended to avoid them.  However, the
+combination of continuing pressure to assign CVEs and other forms of
+security identifiers, and ongoing abuses by individuals and companies
+outside of the kernel community has made it clear that the kernel
+community should have control over those assignments.
+
+The Linux kernel developer team does have the ability to assign CVEs for
+potential Linux kernel security issues.  This assignment is independent
+of the :doc:`normal Linux kernel security bug reporting
+process<../process/security-bugs>`.
+
+A list of all assigned CVEs for the Linux kernel can be found in the
+archives of the linux-cve mailing list, as seen on
+https://lore.kernel.org/linux-cve-announce/.  To get notice of the
+assigned CVEs, please `subscribe
+<https://subspace.kernel.org/subscribing.html>`_ to that mailing list.
+
+Process
+=======
+
+As part of the normal stable release process, kernel changes that are
+potentially security issues are identified by the developers responsible
+for CVE number assignments and have CVE numbers automatically assigned
+to them.  These assignments are published on the linux-cve-announce
+mailing list as announcements on a frequent basis.
+
+Note, due to the layer at which the Linux kernel is in a system, almost
+any bug might be exploitable to compromise the security of the kernel,
+but the possibility of exploitation is often not evident when the bug is
+fixed.  Because of this, the CVE assignment team is overly cautious and
+assign CVE numbers to any bugfix that they identify.  This
+explains the seemingly large number of CVEs that are issued by the Linux
+kernel team.
+
+If the CVE assignment team misses a specific fix that any user feels
+should have a CVE assigned to it, please email them at <cve@kernel.org>
+and the team there will work with you on it.  Note that no potential
+security issues should be sent to this alias, it is ONLY for assignment
+of CVEs for fixes that are already in released kernel trees.  If you
+feel you have found an unfixed security issue, please follow the
+:doc:`normal Linux kernel security bug reporting
+process<../process/security-bugs>`.
+
+No CVEs will be automatically assigned for unfixed security issues in
+the Linux kernel; assignment will only automatically happen after a fix
+is available and applied to a stable kernel tree, and it will be tracked
+that way by the git commit id of the original fix.  If anyone wishes to
+have a CVE assigned before an issue is resolved with a commit, please
+contact the kernel CVE assignment team at <cve@kernel.org> to get an
+identifier assigned from their batch of reserved identifiers.
+
+No CVEs will be assigned for any issue found in a version of the kernel
+that is not currently being actively supported by the Stable/LTS kernel
+team.  A list of the currently supported kernel branches can be found at
+https://kernel.org/releases.html
+
+Disputes of assigned CVEs
+=========================
+
+The authority to dispute or modify an assigned CVE for a specific kernel
+change lies solely with the maintainers of the relevant subsystem
+affected.  This principle ensures a high degree of accuracy and
+accountability in vulnerability reporting.  Only those individuals with
+deep expertise and intimate knowledge of the subsystem can effectively
+assess the validity and scope of a reported vulnerability and determine
+its appropriate CVE designation.  Any attempt to modify or dispute a CVE
+outside of this designated authority could lead to confusion, inaccurate
+reporting, and ultimately, compromised systems.
+
+Invalid CVEs
+============
+
+If a security issue is found in a Linux kernel that is only supported by
+a Linux distribution due to the changes that have been made by that
+distribution, or due to the distribution supporting a kernel version
+that is no longer one of the kernel.org supported releases, then a CVE
+can not be assigned by the Linux kernel CVE team, and must be asked for
+from that Linux distribution itself.
+
+Any CVE that is assigned against the Linux kernel for an actively
+supported kernel version, by any group other than the kernel assignment
+CVE team should not be treated as a valid CVE.  Please notify the
+kernel CVE assignment team at <cve@kernel.org> so that they can work to
+invalidate such entries through the CNA remediation process.
+
+Applicability of specific CVEs
+==============================
+
+As the Linux kernel can be used in many different ways, with many
+different ways of accessing it by external users, or no access at all,
+the applicability of any specific CVE is up to the user of Linux to
+determine, it is not up to the CVE assignment team.  Please do not
+contact us to attempt to determine the applicability of any specific
+CVE.
+
+Also, as the source tree is so large, and any one system only uses a
+small subset of the source tree, any users of Linux should be aware that
+large numbers of assigned CVEs are not relevant for their systems.
+
+In short, we do not know your use case, and we do not know what portions
+of the kernel that you use, so there is no way for us to determine if a
+specific CVE is relevant for your system.
+
+As always, it is best to take all released kernel changes, as they are
+tested together in a unified whole by many community members, and not as
+individual cherry-picked changes.  Also note that for many bugs, the
+solution to the overall problem is not found in a single change, but by
+the sum of many fixes on top of each other.  Ideally CVEs will be
+assigned to all fixes for all issues, but sometimes we will fail to
+notice fixes, therefore assume that some changes without a CVE assigned
+might be relevant to take.
+
diff --git a/Documentation/process/index.rst b/Documentation/process/index.rst
index 6cb732dfcc72..de9cbb7bd7eb 100644
--- a/Documentation/process/index.rst
+++ b/Documentation/process/index.rst
@@ -81,6 +81,7 @@ of special classes of bugs: regressions and security problems.
 
    handling-regressions
    security-bugs
+   cve
    embargoed-hardware-issues
 
 Maintainer information
diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst
index 84ee60fceef2..fd96e4a3cef9 100644
--- a/Documentation/process/maintainer-netdev.rst
+++ b/Documentation/process/maintainer-netdev.rst
@@ -431,7 +431,7 @@ patchwork checks
 Checks in patchwork are mostly simple wrappers around existing kernel
 scripts, the sources are available at:
 
-https://github.com/kuba-moo/nipa/tree/master/tests
+https://github.com/linux-netdev/nipa/tree/master/tests
 
 **Do not** post your patches just to run them through the checks.
 You must ensure that your patches are ready by testing them locally
diff --git a/Documentation/process/security-bugs.rst b/Documentation/process/security-bugs.rst
index 692a3ba56cca..56c560a00b37 100644
--- a/Documentation/process/security-bugs.rst
+++ b/Documentation/process/security-bugs.rst
@@ -99,9 +99,8 @@ CVE assignment
 The security team does not assign CVEs, nor do we require them for
 reports or fixes, as this can needlessly complicate the process and may
 delay the bug handling.  If a reporter wishes to have a CVE identifier
-assigned, they should find one by themselves, for example by contacting
-MITRE directly.  However under no circumstances will a patch inclusion
-be delayed to wait for a CVE identifier to arrive.
+assigned for a confirmed issue, they can contact the :doc:`kernel CVE
+assignment team<../process/cve>` to obtain one.
 
 Non-disclosure agreements
 -------------------------
diff --git a/Documentation/rust/arch-support.rst b/Documentation/rust/arch-support.rst
index b91e9ef4d0c2..73203ba1e901 100644
--- a/Documentation/rust/arch-support.rst
+++ b/Documentation/rust/arch-support.rst
@@ -12,10 +12,11 @@ which uses ``libclang``.
 Below is a general summary of architectures that currently work. Level of
 support corresponds to ``S`` values in the ``MAINTAINERS`` file.
 
-============  ================  ==============================================
-Architecture  Level of support  Constraints
-============  ================  ==============================================
-``um``        Maintained        ``x86_64`` only.
-``x86``       Maintained        ``x86_64`` only.
-============  ================  ==============================================
+=============  ================  ==============================================
+Architecture   Level of support  Constraints
+=============  ================  ==============================================
+``loongarch``  Maintained        -
+``um``         Maintained        ``x86_64`` only.
+``x86``        Maintained        ``x86_64`` only.
+=============  ================  ==============================================
 
diff --git a/Documentation/rust/general-information.rst b/Documentation/rust/general-information.rst
index 236c6dd3c647..081397827a7e 100644
--- a/Documentation/rust/general-information.rst
+++ b/Documentation/rust/general-information.rst
@@ -77,27 +77,3 @@ configuration:
 	#[cfg(CONFIG_X="y")]   // Enabled as a built-in (`y`)
 	#[cfg(CONFIG_X="m")]   // Enabled as a module   (`m`)
 	#[cfg(not(CONFIG_X))]  // Disabled
-
-
-Testing
--------
-
-There are the tests that come from the examples in the Rust documentation
-and get transformed into KUnit tests. These can be run via KUnit. For example
-via ``kunit_tool`` (``kunit.py``) on the command line::
-
-	./tools/testing/kunit/kunit.py run --make_options LLVM=1 --arch x86_64 --kconfig_add CONFIG_RUST=y
-
-Alternatively, KUnit can run them as kernel built-in at boot. Refer to
-Documentation/dev-tools/kunit/index.rst for the general KUnit documentation
-and Documentation/dev-tools/kunit/architecture.rst for the details of kernel
-built-in vs. command line testing.
-
-Additionally, there are the ``#[test]`` tests. These can be run using
-the ``rusttest`` Make target::
-
-	make LLVM=1 rusttest
-
-This requires the kernel ``.config`` and downloads external repositories.
-It runs the ``#[test]`` tests on the host (currently) and thus is fairly
-limited in what these tests can test.
diff --git a/Documentation/rust/index.rst b/Documentation/rust/index.rst
index 965f2db529e0..46d35bd395cf 100644
--- a/Documentation/rust/index.rst
+++ b/Documentation/rust/index.rst
@@ -40,6 +40,7 @@ configurations.
     general-information
     coding-guidelines
     arch-support
+    testing
 
 .. only::  subproject and html
 
diff --git a/Documentation/rust/testing.rst b/Documentation/rust/testing.rst
new file mode 100644
index 000000000000..6658998d1b6c
--- /dev/null
+++ b/Documentation/rust/testing.rst
@@ -0,0 +1,135 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Testing
+=======
+
+This document contains useful information how to test the Rust code in the
+kernel.
+
+There are two sorts of tests:
+
+- The KUnit tests.
+- The ``#[test]`` tests.
+
+The KUnit tests
+---------------
+
+These are the tests that come from the examples in the Rust documentation. They
+get transformed into KUnit tests.
+
+Usage
+*****
+
+These tests can be run via KUnit. For example via ``kunit_tool`` (``kunit.py``)
+on the command line::
+
+	./tools/testing/kunit/kunit.py run --make_options LLVM=1 --arch x86_64 --kconfig_add CONFIG_RUST=y
+
+Alternatively, KUnit can run them as kernel built-in at boot. Refer to
+Documentation/dev-tools/kunit/index.rst for the general KUnit documentation
+and Documentation/dev-tools/kunit/architecture.rst for the details of kernel
+built-in vs. command line testing.
+
+To use these KUnit doctests, the following must be enabled::
+
+	CONFIG_KUNIT
+	   Kernel hacking -> Kernel Testing and Coverage -> KUnit - Enable support for unit tests
+	CONFIG_RUST_KERNEL_DOCTESTS
+	   Kernel hacking -> Rust hacking -> Doctests for the `kernel` crate
+
+in the kernel config system.
+
+KUnit tests are documentation tests
+***********************************
+
+These documentation tests are typically examples of usage of any item (e.g.
+function, struct, module...).
+
+They are very convenient because they are just written alongside the
+documentation. For instance:
+
+.. code-block:: rust
+
+	/// Sums two numbers.
+	///
+	/// ```
+	/// assert_eq!(mymod::f(10, 20), 30);
+	/// ```
+	pub fn f(a: i32, b: i32) -> i32 {
+	    a + b
+	}
+
+In userspace, the tests are collected and run via ``rustdoc``. Using the tool
+as-is would be useful already, since it allows verifying that examples compile
+(thus enforcing they are kept in sync with the code they document) and as well
+as running those that do not depend on in-kernel APIs.
+
+For the kernel, however, these tests get transformed into KUnit test suites.
+This means that doctests get compiled as Rust kernel objects, allowing them to
+run against a built kernel.
+
+A benefit of this KUnit integration is that Rust doctests get to reuse existing
+testing facilities. For instance, the kernel log would look like::
+
+	KTAP version 1
+	1..1
+	    KTAP version 1
+	    # Subtest: rust_doctests_kernel
+	    1..59
+	    # rust_doctest_kernel_build_assert_rs_0.location: rust/kernel/build_assert.rs:13
+	    ok 1 rust_doctest_kernel_build_assert_rs_0
+	    # rust_doctest_kernel_build_assert_rs_1.location: rust/kernel/build_assert.rs:56
+	    ok 2 rust_doctest_kernel_build_assert_rs_1
+	    # rust_doctest_kernel_init_rs_0.location: rust/kernel/init.rs:122
+	    ok 3 rust_doctest_kernel_init_rs_0
+	    ...
+	    # rust_doctest_kernel_types_rs_2.location: rust/kernel/types.rs:150
+	    ok 59 rust_doctest_kernel_types_rs_2
+	# rust_doctests_kernel: pass:59 fail:0 skip:0 total:59
+	# Totals: pass:59 fail:0 skip:0 total:59
+	ok 1 rust_doctests_kernel
+
+Tests using the `? <https://doc.rust-lang.org/reference/expressions/operator-expr.html#the-question-mark-operator>`_
+operator are also supported as usual, e.g.:
+
+.. code-block:: rust
+
+	/// ```
+	/// # use kernel::{spawn_work_item, workqueue};
+	/// spawn_work_item!(workqueue::system(), || pr_info!("x"))?;
+	/// # Ok::<(), Error>(())
+	/// ```
+
+The tests are also compiled with Clippy under ``CLIPPY=1``, just like normal
+code, thus also benefitting from extra linting.
+
+In order for developers to easily see which line of doctest code caused a
+failure, a KTAP diagnostic line is printed to the log. This contains the
+location (file and line) of the original test (i.e. instead of the location in
+the generated Rust file)::
+
+	# rust_doctest_kernel_types_rs_2.location: rust/kernel/types.rs:150
+
+Rust tests appear to assert using the usual ``assert!`` and ``assert_eq!``
+macros from the Rust standard library (``core``). We provide a custom version
+that forwards the call to KUnit instead. Importantly, these macros do not
+require passing context, unlike those for KUnit testing (i.e.
+``struct kunit *``). This makes them easier to use, and readers of the
+documentation do not need to care about which testing framework is used. In
+addition, it may allow us to test third-party code more easily in the future.
+
+A current limitation is that KUnit does not support assertions in other tasks.
+Thus, we presently simply print an error to the kernel log if an assertion
+actually failed. Additionally, doctests are not run for nonpublic functions.
+
+The ``#[test]`` tests
+---------------------
+
+Additionally, there are the ``#[test]`` tests. These can be run using the
+``rusttest`` Make target::
+
+	make LLVM=1 rusttest
+
+This requires the kernel ``.config`` and downloads external repositories. It
+runs the ``#[test]`` tests on the host (currently) and thus is fairly limited in
+what these tests can test.
diff --git a/Documentation/sphinx/kernel_feat.py b/Documentation/sphinx/kernel_feat.py
index b5fa2f0542a5..03ace5f01b5c 100644
--- a/Documentation/sphinx/kernel_feat.py
+++ b/Documentation/sphinx/kernel_feat.py
@@ -37,8 +37,6 @@ import re
 import subprocess
 import sys
 
-from os import path
-
 from docutils import nodes, statemachine
 from docutils.statemachine import ViewList
 from docutils.parsers.rst import directives, Directive
@@ -76,33 +74,26 @@ class KernelFeat(Directive):
         self.state.document.settings.env.app.warn(message, prefix="")
 
     def run(self):
-
         doc = self.state.document
         if not doc.settings.file_insertion_enabled:
             raise self.warning("docutils: file insertion disabled")
 
         env = doc.settings.env
-        cwd = path.dirname(doc.current_source)
-        cmd = "get_feat.pl rest --enable-fname --dir "
-        cmd += self.arguments[0]
-
-        if len(self.arguments) > 1:
-            cmd += " --arch " + self.arguments[1]
 
-        srctree = path.abspath(os.environ["srctree"])
+        srctree = os.path.abspath(os.environ["srctree"])
 
-        fname = cmd
+        args = [
+            os.path.join(srctree, 'scripts/get_feat.pl'),
+            'rest',
+            '--enable-fname',
+            '--dir',
+            os.path.join(srctree, 'Documentation', self.arguments[0]),
+        ]
 
-        # extend PATH with $(srctree)/scripts
-        path_env = os.pathsep.join([
-            srctree + os.sep + "scripts",
-            os.environ["PATH"]
-        ])
-        shell_env = os.environ.copy()
-        shell_env["PATH"]    = path_env
-        shell_env["srctree"] = srctree
+        if len(self.arguments) > 1:
+            args.extend(['--arch', self.arguments[1]])
 
-        lines = self.runCmd(cmd, shell=True, cwd=cwd, env=shell_env)
+        lines = subprocess.check_output(args, cwd=os.path.dirname(doc.current_source)).decode('utf-8')
 
         line_regex = re.compile(r"^\.\. FILE (\S+)$")
 
@@ -118,33 +109,9 @@ class KernelFeat(Directive):
             else:
                 out_lines += line + "\n"
 
-        nodeList = self.nestedParse(out_lines, fname)
+        nodeList = self.nestedParse(out_lines, self.arguments[0])
         return nodeList
 
-    def runCmd(self, cmd, **kwargs):
-        u"""Run command ``cmd`` and return its stdout as unicode."""
-
-        try:
-            proc = subprocess.Popen(
-                cmd
-                , stdout = subprocess.PIPE
-                , stderr = subprocess.PIPE
-                , **kwargs
-            )
-            out, err = proc.communicate()
-
-            out, err = codecs.decode(out, 'utf-8'), codecs.decode(err, 'utf-8')
-
-            if proc.returncode != 0:
-                raise self.severe(
-                    u"command '%s' failed with return code %d"
-                    % (cmd, proc.returncode)
-                )
-        except OSError as exc:
-            raise self.severe(u"problems with '%s' directive: %s."
-                              % (self.name, ErrorString(exc)))
-        return out
-
     def nestedParse(self, lines, fname):
         content = ViewList()
         node    = nodes.section()
diff --git a/Documentation/sphinx/requirements.txt b/Documentation/sphinx/requirements.txt
index a8a1aff6445e..5d47ed443949 100644
--- a/Documentation/sphinx/requirements.txt
+++ b/Documentation/sphinx/requirements.txt
@@ -1,4 +1,6 @@
 # jinja2>=3.1 is not compatible with Sphinx<4.0
 jinja2<3.1
+# alabaster>=0.7.14 is not compatible with Sphinx<=3.3
+alabaster<0.7.14
 Sphinx==2.4.4
 pyyaml
diff --git a/Documentation/sphinx/templates/kernel-toc.html b/Documentation/sphinx/templates/kernel-toc.html
index b58efa99df52..41f1efbe64bb 100644
--- a/Documentation/sphinx/templates/kernel-toc.html
+++ b/Documentation/sphinx/templates/kernel-toc.html
@@ -12,5 +12,7 @@
 <script type="text/javascript"> <!--
   var sbar = document.getElementsByClassName("sphinxsidebar")[0];
   let currents = document.getElementsByClassName("current")
-  sbar.scrollTop = currents[currents.length - 1].offsetTop;
+  if (currents.length) {
+    sbar.scrollTop = currents[currents.length - 1].offsetTop;
+  }
   --> </script>
diff --git a/Documentation/sphinx/translations.py b/Documentation/sphinx/translations.py
index 47161e6eba99..32c2b32b2b5e 100644
--- a/Documentation/sphinx/translations.py
+++ b/Documentation/sphinx/translations.py
@@ -29,10 +29,7 @@ all_languages = {
 }
 
 class LanguagesNode(nodes.Element):
-    def __init__(self, current_language, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-
-        self.current_language = current_language
+    pass
 
 class TranslationsTransform(Transform):
     default_priority = 900
@@ -49,7 +46,8 @@ class TranslationsTransform(Transform):
             # normalize docname to be the untranslated one
             docname = os.path.join(*components[2:])
 
-        new_nodes = LanguagesNode(all_languages[this_lang_code])
+        new_nodes = LanguagesNode()
+        new_nodes['current_language'] = all_languages[this_lang_code]
 
         for lang_code, lang_name in all_languages.items():
             if lang_code == this_lang_code:
@@ -84,7 +82,7 @@ def process_languages(app, doctree, docname):
 
         html_content = app.builder.templates.render('translations.html',
             context={
-                'current_language': node.current_language,
+                'current_language': node['current_language'],
                 'languages': languages,
             })
 
diff --git a/Documentation/staging/rpmsg.rst b/Documentation/staging/rpmsg.rst
index 1ce353cb232a..dba3e5f65612 100644
--- a/Documentation/staging/rpmsg.rst
+++ b/Documentation/staging/rpmsg.rst
@@ -68,13 +68,14 @@ User API
 
 ::
 
-  int rpmsg_send(struct rpmsg_channel *rpdev, void *data, int len);
+  int rpmsg_send(struct rpmsg_endpoint *ept, void *data, int len);
 
-sends a message across to the remote processor on a given channel.
-The caller should specify the channel, the data it wants to send,
+sends a message across to the remote processor from the given endpoint.
+The caller should specify the endpoint, the data it wants to send,
 and its length (in bytes). The message will be sent on the specified
-channel, i.e. its source and destination address fields will be
-set to the channel's src and dst addresses.
+endpoint's channel, i.e. its source and destination address fields will be
+respectively set to the endpoint's src address and its parent channel
+dst addresses.
 
 In case there are no TX buffers available, the function will block until
 one becomes available (i.e. until the remote processor consumes
@@ -87,17 +88,18 @@ Returns 0 on success and an appropriate error value on failure.
 
 ::
 
-  int rpmsg_sendto(struct rpmsg_channel *rpdev, void *data, int len, u32 dst);
+  int rpmsg_sendto(struct rpmsg_endpoint *ept, void *data, int len, u32 dst);
 
-sends a message across to the remote processor on a given channel,
+sends a message across to the remote processor from a given endpoint,
 to a destination address provided by the caller.
 
-The caller should specify the channel, the data it wants to send,
+The caller should specify the endpoint, the data it wants to send,
 its length (in bytes), and an explicit destination address.
 
 The message will then be sent to the remote processor to which the
-channel belongs, using the channel's src address, and the user-provided
-dst address (thus the channel's dst address will be ignored).
+endpoints's channel belongs, using the endpoints's src address,
+and the user-provided dst address (thus the channel's dst address
+will be ignored).
 
 In case there are no TX buffers available, the function will block until
 one becomes available (i.e. until the remote processor consumes
@@ -110,18 +112,19 @@ Returns 0 on success and an appropriate error value on failure.
 
 ::
 
-  int rpmsg_send_offchannel(struct rpmsg_channel *rpdev, u32 src, u32 dst,
+  int rpmsg_send_offchannel(struct rpmsg_endpoint *ept, u32 src, u32 dst,
 							void *data, int len);
 
 
 sends a message across to the remote processor, using the src and dst
 addresses provided by the user.
 
-The caller should specify the channel, the data it wants to send,
+The caller should specify the endpoint, the data it wants to send,
 its length (in bytes), and explicit source and destination addresses.
 The message will then be sent to the remote processor to which the
-channel belongs, but the channel's src and dst addresses will be
-ignored (and the user-provided addresses will be used instead).
+endpoint's channel belongs, but the endpoint's src and channel dst
+addresses will be ignored (and the user-provided addresses will
+be used instead).
 
 In case there are no TX buffers available, the function will block until
 one becomes available (i.e. until the remote processor consumes
@@ -134,13 +137,14 @@ Returns 0 on success and an appropriate error value on failure.
 
 ::
 
-  int rpmsg_trysend(struct rpmsg_channel *rpdev, void *data, int len);
+  int rpmsg_trysend(struct rpmsg_endpoint *ept, void *data, int len);
 
-sends a message across to the remote processor on a given channel.
-The caller should specify the channel, the data it wants to send,
+sends a message across to the remote processor from a given endpoint.
+The caller should specify the endpoint, the data it wants to send,
 and its length (in bytes). The message will be sent on the specified
-channel, i.e. its source and destination address fields will be
-set to the channel's src and dst addresses.
+endpoint's channel, i.e. its source and destination address fields will be
+respectively set to the endpoint's src address and its parent channel
+dst addresses.
 
 In case there are no TX buffers available, the function will immediately
 return -ENOMEM without waiting until one becomes available.
@@ -150,10 +154,10 @@ Returns 0 on success and an appropriate error value on failure.
 
 ::
 
-  int rpmsg_trysendto(struct rpmsg_channel *rpdev, void *data, int len, u32 dst)
+  int rpmsg_trysendto(struct rpmsg_endpoint *ept, void *data, int len, u32 dst)
 
 
-sends a message across to the remote processor on a given channel,
+sends a message across to the remote processor from a given endoint,
 to a destination address provided by the user.
 
 The user should specify the channel, the data it wants to send,
@@ -171,7 +175,7 @@ Returns 0 on success and an appropriate error value on failure.
 
 ::
 
-  int rpmsg_trysend_offchannel(struct rpmsg_channel *rpdev, u32 src, u32 dst,
+  int rpmsg_trysend_offchannel(struct rpmsg_endpoint *ept, u32 src, u32 dst,
 							void *data, int len);
 
 
@@ -284,7 +288,7 @@ content to the console.
 	dev_info(&rpdev->dev, "chnl: 0x%x -> 0x%x\n", rpdev->src, rpdev->dst);
 
 	/* send a message on our channel */
-	err = rpmsg_send(rpdev, "hello!", 6);
+	err = rpmsg_send(rpdev->ept, "hello!", 6);
 	if (err) {
 		pr_err("rpmsg_send failed: %d\n", err);
 		return err;
diff --git a/Documentation/trace/coresight/coresight.rst b/Documentation/trace/coresight/coresight.rst
index 826e59a698da..d4f93d6a2d63 100644
--- a/Documentation/trace/coresight/coresight.rst
+++ b/Documentation/trace/coresight/coresight.rst
@@ -624,6 +624,10 @@ They are also listed in the folder /sys/bus/event_source/devices/cs_etm/format/
    * - timestamp
      - Session local version of the system wide setting: :ref:`ETMv4_MODE_TIMESTAMP
        <coresight-timestamp>`
+   * - cc_threshold
+     - Cycle count threshold value. If nothing is provided here or the provided value is 0, then the
+       default value i.e 0x100 will be used. If provided value is less than minimum cycles threshold
+       value, as indicated via TRCIDR3.CCITMIN, then the minimum value will be used instead.
 
 How to use the STM module
 -------------------------
diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst
index 16122a8895ba..7e7b8ec17934 100644
--- a/Documentation/trace/ftrace.rst
+++ b/Documentation/trace/ftrace.rst
@@ -218,6 +218,27 @@ of ftrace. Here is a list of some of the key files:
 
 	This displays the total combined size of all the trace buffers.
 
+  buffer_subbuf_size_kb:
+
+	This sets or displays the sub buffer size. The ring buffer is broken up
+	into several same size "sub buffers". An event can not be bigger than
+	the size of the sub buffer. Normally, the sub buffer is the size of the
+	architecture's page (4K on x86). The sub buffer also contains meta data
+	at the start which also limits the size of an event.  That means when
+	the sub buffer is a page size, no event can be larger than the page
+	size minus the sub buffer meta data.
+
+	Note, the buffer_subbuf_size_kb is a way for the user to specify the
+	minimum size of the subbuffer. The kernel may make it bigger due to the
+	implementation details, or simply fail the operation if the kernel can
+	not handle the request.
+
+	Changing the sub buffer size allows for events to be larger than the
+	page size.
+
+	Note: When changing the sub-buffer size, tracing is stopped and any
+	data in the ring buffer and the snapshot buffer will be discarded.
+
   free_buffer:
 
 	If a process is performing tracing, and the ring buffer	should be
diff --git a/Documentation/trace/kprobes.rst b/Documentation/trace/kprobes.rst
index f825970a1495..e1636e579c9c 100644
--- a/Documentation/trace/kprobes.rst
+++ b/Documentation/trace/kprobes.rst
@@ -4,7 +4,7 @@ Kernel Probes (Kprobes)
 
 :Author: Jim Keniston <jkenisto@us.ibm.com>
 :Author: Prasanna S Panchamukhi <prasanna.panchamukhi@gmail.com>
-:Author: Masami Hiramatsu <mhiramat@redhat.com>
+:Author: Masami Hiramatsu <mhiramat@kernel.org>
 
 .. CONTENTS
 
@@ -321,6 +321,7 @@ architectures:
 - mips
 - s390
 - parisc
+- loongarch
 
 Configuring Kprobes
 ===================
diff --git a/Documentation/translations/zh_CN/arch/loongarch/features.rst b/Documentation/translations/zh_CN/arch/loongarch/features.rst
index 82bfac180bdc..cec38dda8298 100644
--- a/Documentation/translations/zh_CN/arch/loongarch/features.rst
+++ b/Documentation/translations/zh_CN/arch/loongarch/features.rst
@@ -5,4 +5,4 @@
 :Original: Documentation/arch/loongarch/features.rst
 :Translator: Huacai Chen <chenhuacai@loongson.cn>
 
-.. kernel-feat:: $srctree/Documentation/features loongarch
+.. kernel-feat:: features loongarch
diff --git a/Documentation/translations/zh_CN/arch/mips/features.rst b/Documentation/translations/zh_CN/arch/mips/features.rst
index da1b956e4a40..0d6df97db069 100644
--- a/Documentation/translations/zh_CN/arch/mips/features.rst
+++ b/Documentation/translations/zh_CN/arch/mips/features.rst
@@ -10,4 +10,4 @@
 
 .. _cn_features:
 
-.. kernel-feat:: $srctree/Documentation/features mips
+.. kernel-feat:: features mips
diff --git a/Documentation/translations/zh_TW/arch/loongarch/features.rst b/Documentation/translations/zh_TW/arch/loongarch/features.rst
index b64e430f55ae..c2175fd32b54 100644
--- a/Documentation/translations/zh_TW/arch/loongarch/features.rst
+++ b/Documentation/translations/zh_TW/arch/loongarch/features.rst
@@ -5,5 +5,5 @@
 :Original: Documentation/arch/loongarch/features.rst
 :Translator: Huacai Chen <chenhuacai@loongson.cn>
 
-.. kernel-feat:: $srctree/Documentation/features loongarch
+.. kernel-feat:: features loongarch
 
diff --git a/Documentation/translations/zh_TW/arch/mips/features.rst b/Documentation/translations/zh_TW/arch/mips/features.rst
index f69410420035..3d3906c4d08e 100644
--- a/Documentation/translations/zh_TW/arch/mips/features.rst
+++ b/Documentation/translations/zh_TW/arch/mips/features.rst
@@ -10,5 +10,5 @@
 
 .. _tw_features:
 
-.. kernel-feat:: $srctree/Documentation/features mips
+.. kernel-feat:: features mips
 
diff --git a/Documentation/usb/gadget-testing.rst b/Documentation/usb/gadget-testing.rst
index 29072c166d23..077dfac7ed98 100644
--- a/Documentation/usb/gadget-testing.rst
+++ b/Documentation/usb/gadget-testing.rst
@@ -448,15 +448,17 @@ Function-specific configfs interface
 The function name to use when creating the function directory is "ncm".
 The NCM function provides these attributes in its function directory:
 
-	=============== ==================================================
-	ifname		network device interface name associated with this
-			function instance
-	qmult		queue length multiplier for high and super speed
-	host_addr	MAC address of host's end of this
-			Ethernet over USB link
-	dev_addr	MAC address of device's end of this
-			Ethernet over USB link
-	=============== ==================================================
+	======================= ==================================================
+	ifname			network device interface name associated with this
+				function instance
+	qmult			queue length multiplier for high and super speed
+	host_addr		MAC address of host's end of this
+				Ethernet over USB link
+	dev_addr		MAC address of device's end of this
+				Ethernet over USB link
+	max_segment_size	Segment size required for P2P connections. This
+				will set MTU to 14 bytes
+	======================= ==================================================
 
 and after creating the functions/ncm.<instance name> they contain default
 values: qmult is 5, dev_addr and host_addr are randomly selected.
diff --git a/Documentation/usb/raw-gadget.rst b/Documentation/usb/raw-gadget.rst
index 818a1648b387..59b2132b584d 100644
--- a/Documentation/usb/raw-gadget.rst
+++ b/Documentation/usb/raw-gadget.rst
@@ -81,9 +81,6 @@ feature must be kept in the implementation.
 Potential future improvements
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-- Report more events (suspend, resume, etc.) through
-  ``USB_RAW_IOCTL_EVENT_FETCH``.
-
 - Support ``O_NONBLOCK`` I/O. This would be another mode of operation, where
   Raw Gadget would not wait until the completion of each USB request.
 
diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
index 457e16f06e04..3731ecf1e437 100644
--- a/Documentation/userspace-api/ioctl/ioctl-number.rst
+++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
@@ -82,8 +82,9 @@ Code  Seq#    Include File                                           Comments
 0x10  00-0F  drivers/char/s390/vmcp.h
 0x10  10-1F  arch/s390/include/uapi/sclp_ctl.h
 0x10  20-2F  arch/s390/include/uapi/asm/hypfs.h
-0x12  all    linux/fs.h
+0x12  all    linux/fs.h                                              BLK* ioctls
              linux/blkpg.h
+0x15  all    linux/fs.h                                              FS_IOC_* ioctls
 0x1b  all                                                            InfiniBand Subsystem
                                                                      <http://infiniband.sourceforge.net/>
 0x20  all    drivers/cdrom/cm206.h
diff --git a/Documentation/virt/hyperv/index.rst b/Documentation/virt/hyperv/index.rst
index 4a7a1b738bbe..de447e11b4a5 100644
--- a/Documentation/virt/hyperv/index.rst
+++ b/Documentation/virt/hyperv/index.rst
@@ -10,3 +10,4 @@ Hyper-V Enlightenments
    overview
    vmbus
    clocks
+   vpci
diff --git a/Documentation/virt/hyperv/vpci.rst b/Documentation/virt/hyperv/vpci.rst
new file mode 100644
index 000000000000..b65b2126ede3
--- /dev/null
+++ b/Documentation/virt/hyperv/vpci.rst
@@ -0,0 +1,316 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+PCI pass-thru devices
+=========================
+In a Hyper-V guest VM, PCI pass-thru devices (also called
+virtual PCI devices, or vPCI devices) are physical PCI devices
+that are mapped directly into the VM's physical address space.
+Guest device drivers can interact directly with the hardware
+without intermediation by the host hypervisor.  This approach
+provides higher bandwidth access to the device with lower
+latency, compared with devices that are virtualized by the
+hypervisor.  The device should appear to the guest just as it
+would when running on bare metal, so no changes are required
+to the Linux device drivers for the device.
+
+Hyper-V terminology for vPCI devices is "Discrete Device
+Assignment" (DDA).  Public documentation for Hyper-V DDA is
+available here: `DDA`_
+
+.. _DDA: https://learn.microsoft.com/en-us/windows-server/virtualization/hyper-v/plan/plan-for-deploying-devices-using-discrete-device-assignment
+
+DDA is typically used for storage controllers, such as NVMe,
+and for GPUs.  A similar mechanism for NICs is called SR-IOV
+and produces the same benefits by allowing a guest device
+driver to interact directly with the hardware.  See Hyper-V
+public documentation here: `SR-IOV`_
+
+.. _SR-IOV: https://learn.microsoft.com/en-us/windows-hardware/drivers/network/overview-of-single-root-i-o-virtualization--sr-iov-
+
+This discussion of vPCI devices includes DDA and SR-IOV
+devices.
+
+Device Presentation
+-------------------
+Hyper-V provides full PCI functionality for a vPCI device when
+it is operating, so the Linux device driver for the device can
+be used unchanged, provided it uses the correct Linux kernel
+APIs for accessing PCI config space and for other integration
+with Linux.  But the initial detection of the PCI device and
+its integration with the Linux PCI subsystem must use Hyper-V
+specific mechanisms.  Consequently, vPCI devices on Hyper-V
+have a dual identity.  They are initially presented to Linux
+guests as VMBus devices via the standard VMBus "offer"
+mechanism, so they have a VMBus identity and appear under
+/sys/bus/vmbus/devices.  The VMBus vPCI driver in Linux at
+drivers/pci/controller/pci-hyperv.c handles a newly introduced
+vPCI device by fabricating a PCI bus topology and creating all
+the normal PCI device data structures in Linux that would
+exist if the PCI device were discovered via ACPI on a bare-
+metal system.  Once those data structures are set up, the
+device also has a normal PCI identity in Linux, and the normal
+Linux device driver for the vPCI device can function as if it
+were running in Linux on bare-metal.  Because vPCI devices are
+presented dynamically through the VMBus offer mechanism, they
+do not appear in the Linux guest's ACPI tables.  vPCI devices
+may be added to a VM or removed from a VM at any time during
+the life of the VM, and not just during initial boot.
+
+With this approach, the vPCI device is a VMBus device and a
+PCI device at the same time.  In response to the VMBus offer
+message, the hv_pci_probe() function runs and establishes a
+VMBus connection to the vPCI VSP on the Hyper-V host.  That
+connection has a single VMBus channel.  The channel is used to
+exchange messages with the vPCI VSP for the purpose of setting
+up and configuring the vPCI device in Linux.  Once the device
+is fully configured in Linux as a PCI device, the VMBus
+channel is used only if Linux changes the vCPU to be interrupted
+in the guest, or if the vPCI device is removed from
+the VM while the VM is running.  The ongoing operation of the
+device happens directly between the Linux device driver for
+the device and the hardware, with VMBus and the VMBus channel
+playing no role.
+
+PCI Device Setup
+----------------
+PCI device setup follows a sequence that Hyper-V originally
+created for Windows guests, and that can be ill-suited for
+Linux guests due to differences in the overall structure of
+the Linux PCI subsystem compared with Windows.  Nonetheless,
+with a bit of hackery in the Hyper-V virtual PCI driver for
+Linux, the virtual PCI device is setup in Linux so that
+generic Linux PCI subsystem code and the Linux driver for the
+device "just work".
+
+Each vPCI device is set up in Linux to be in its own PCI
+domain with a host bridge.  The PCI domainID is derived from
+bytes 4 and 5 of the instance GUID assigned to the VMBus vPCI
+device.  The Hyper-V host does not guarantee that these bytes
+are unique, so hv_pci_probe() has an algorithm to resolve
+collisions.  The collision resolution is intended to be stable
+across reboots of the same VM so that the PCI domainIDs don't
+change, as the domainID appears in the user space
+configuration of some devices.
+
+hv_pci_probe() allocates a guest MMIO range to be used as PCI
+config space for the device.  This MMIO range is communicated
+to the Hyper-V host over the VMBus channel as part of telling
+the host that the device is ready to enter d0.  See
+hv_pci_enter_d0().  When the guest subsequently accesses this
+MMIO range, the Hyper-V host intercepts the accesses and maps
+them to the physical device PCI config space.
+
+hv_pci_probe() also gets BAR information for the device from
+the Hyper-V host, and uses this information to allocate MMIO
+space for the BARs.  That MMIO space is then setup to be
+associated with the host bridge so that it works when generic
+PCI subsystem code in Linux processes the BARs.
+
+Finally, hv_pci_probe() creates the root PCI bus.  At this
+point the Hyper-V virtual PCI driver hackery is done, and the
+normal Linux PCI machinery for scanning the root bus works to
+detect the device, to perform driver matching, and to
+initialize the driver and device.
+
+PCI Device Removal
+------------------
+A Hyper-V host may initiate removal of a vPCI device from a
+guest VM at any time during the life of the VM.  The removal
+is instigated by an admin action taken on the Hyper-V host and
+is not under the control of the guest OS.
+
+A guest VM is notified of the removal by an unsolicited
+"Eject" message sent from the host to the guest over the VMBus
+channel associated with the vPCI device.  Upon receipt of such
+a message, the Hyper-V virtual PCI driver in Linux
+asynchronously invokes Linux kernel PCI subsystem calls to
+shutdown and remove the device.  When those calls are
+complete, an "Ejection Complete" message is sent back to
+Hyper-V over the VMBus channel indicating that the device has
+been removed.  At this point, Hyper-V sends a VMBus rescind
+message to the Linux guest, which the VMBus driver in Linux
+processes by removing the VMBus identity for the device.  Once
+that processing is complete, all vestiges of the device having
+been present are gone from the Linux kernel.  The rescind
+message also indicates to the guest that Hyper-V has stopped
+providing support for the vPCI device in the guest.  If the
+guest were to attempt to access that device's MMIO space, it
+would be an invalid reference. Hypercalls affecting the device
+return errors, and any further messages sent in the VMBus
+channel are ignored.
+
+After sending the Eject message, Hyper-V allows the guest VM
+60 seconds to cleanly shutdown the device and respond with
+Ejection Complete before sending the VMBus rescind
+message.  If for any reason the Eject steps don't complete
+within the allowed 60 seconds, the Hyper-V host forcibly
+performs the rescind steps, which will likely result in
+cascading errors in the guest because the device is now no
+longer present from the guest standpoint and accessing the
+device MMIO space will fail.
+
+Because ejection is asynchronous and can happen at any point
+during the guest VM lifecycle, proper synchronization in the
+Hyper-V virtual PCI driver is very tricky.  Ejection has been
+observed even before a newly offered vPCI device has been
+fully setup.  The Hyper-V virtual PCI driver has been updated
+several times over the years to fix race conditions when
+ejections happen at inopportune times. Care must be taken when
+modifying this code to prevent re-introducing such problems.
+See comments in the code.
+
+Interrupt Assignment
+--------------------
+The Hyper-V virtual PCI driver supports vPCI devices using
+MSI, multi-MSI, or MSI-X.  Assigning the guest vCPU that will
+receive the interrupt for a particular MSI or MSI-X message is
+complex because of the way the Linux setup of IRQs maps onto
+the Hyper-V interfaces.  For the single-MSI and MSI-X cases,
+Linux calls hv_compse_msi_msg() twice, with the first call
+containing a dummy vCPU and the second call containing the
+real vCPU.  Furthermore, hv_irq_unmask() is finally called
+(on x86) or the GICD registers are set (on arm64) to specify
+the real vCPU again.  Each of these three calls interact
+with Hyper-V, which must decide which physical CPU should
+receive the interrupt before it is forwarded to the guest VM.
+Unfortunately, the Hyper-V decision-making process is a bit
+limited, and can result in concentrating the physical
+interrupts on a single CPU, causing a performance bottleneck.
+See details about how this is resolved in the extensive
+comment above the function hv_compose_msi_req_get_cpu().
+
+The Hyper-V virtual PCI driver implements the
+irq_chip.irq_compose_msi_msg function as hv_compose_msi_msg().
+Unfortunately, on Hyper-V the implementation requires sending
+a VMBus message to the Hyper-V host and awaiting an interrupt
+indicating receipt of a reply message.  Since
+irq_chip.irq_compose_msi_msg can be called with IRQ locks
+held, it doesn't work to do the normal sleep until awakened by
+the interrupt. Instead hv_compose_msi_msg() must send the
+VMBus message, and then poll for the completion message. As
+further complexity, the vPCI device could be ejected/rescinded
+while the polling is in progress, so this scenario must be
+detected as well.  See comments in the code regarding this
+very tricky area.
+
+Most of the code in the Hyper-V virtual PCI driver (pci-
+hyperv.c) applies to Hyper-V and Linux guests running on x86
+and on arm64 architectures.  But there are differences in how
+interrupt assignments are managed.  On x86, the Hyper-V
+virtual PCI driver in the guest must make a hypercall to tell
+Hyper-V which guest vCPU should be interrupted by each
+MSI/MSI-X interrupt, and the x86 interrupt vector number that
+the x86_vector IRQ domain has picked for the interrupt.  This
+hypercall is made by hv_arch_irq_unmask().  On arm64, the
+Hyper-V virtual PCI driver manages the allocation of an SPI
+for each MSI/MSI-X interrupt.  The Hyper-V virtual PCI driver
+stores the allocated SPI in the architectural GICD registers,
+which Hyper-V emulates, so no hypercall is necessary as with
+x86.  Hyper-V does not support using LPIs for vPCI devices in
+arm64 guest VMs because it does not emulate a GICv3 ITS.
+
+The Hyper-V virtual PCI driver in Linux supports vPCI devices
+whose drivers create managed or unmanaged Linux IRQs.  If the
+smp_affinity for an unmanaged IRQ is updated via the /proc/irq
+interface, the Hyper-V virtual PCI driver is called to tell
+the Hyper-V host to change the interrupt targeting and
+everything works properly.  However, on x86 if the x86_vector
+IRQ domain needs to reassign an interrupt vector due to
+running out of vectors on a CPU, there's no path to inform the
+Hyper-V host of the change, and things break.  Fortunately,
+guest VMs operate in a constrained device environment where
+using all the vectors on a CPU doesn't happen. Since such a
+problem is only a theoretical concern rather than a practical
+concern, it has been left unaddressed.
+
+DMA
+---
+By default, Hyper-V pins all guest VM memory in the host
+when the VM is created, and programs the physical IOMMU to
+allow the VM to have DMA access to all its memory.  Hence
+it is safe to assign PCI devices to the VM, and allow the
+guest operating system to program the DMA transfers.  The
+physical IOMMU prevents a malicious guest from initiating
+DMA to memory belonging to the host or to other VMs on the
+host. From the Linux guest standpoint, such DMA transfers
+are in "direct" mode since Hyper-V does not provide a virtual
+IOMMU in the guest.
+
+Hyper-V assumes that physical PCI devices always perform
+cache-coherent DMA.  When running on x86, this behavior is
+required by the architecture.  When running on arm64, the
+architecture allows for both cache-coherent and
+non-cache-coherent devices, with the behavior of each device
+specified in the ACPI DSDT.  But when a PCI device is assigned
+to a guest VM, that device does not appear in the DSDT, so the
+Hyper-V VMBus driver propagates cache-coherency information
+from the VMBus node in the ACPI DSDT to all VMBus devices,
+including vPCI devices (since they have a dual identity as a VMBus
+device and as a PCI device).  See vmbus_dma_configure().
+Current Hyper-V versions always indicate that the VMBus is
+cache coherent, so vPCI devices on arm64 always get marked as
+cache coherent and the CPU does not perform any sync
+operations as part of dma_map/unmap_*() calls.
+
+vPCI protocol versions
+----------------------
+As previously described, during vPCI device setup and teardown
+messages are passed over a VMBus channel between the Hyper-V
+host and the Hyper-v vPCI driver in the Linux guest.  Some
+messages have been revised in newer versions of Hyper-V, so
+the guest and host must agree on the vPCI protocol version to
+be used.  The version is negotiated when communication over
+the VMBus channel is first established.  See
+hv_pci_protocol_negotiation(). Newer versions of the protocol
+extend support to VMs with more than 64 vCPUs, and provide
+additional information about the vPCI device, such as the
+guest virtual NUMA node to which it is most closely affined in
+the underlying hardware.
+
+Guest NUMA node affinity
+------------------------
+When the vPCI protocol version provides it, the guest NUMA
+node affinity of the vPCI device is stored as part of the Linux
+device information for subsequent use by the Linux driver. See
+hv_pci_assign_numa_node().  If the negotiated protocol version
+does not support the host providing NUMA affinity information,
+the Linux guest defaults the device NUMA node to 0.  But even
+when the negotiated protocol version includes NUMA affinity
+information, the ability of the host to provide such
+information depends on certain host configuration options.  If
+the guest receives NUMA node value "0", it could mean NUMA
+node 0, or it could mean "no information is available".
+Unfortunately it is not possible to distinguish the two cases
+from the guest side.
+
+PCI config space access in a CoCo VM
+------------------------------------
+Linux PCI device drivers access PCI config space using a
+standard set of functions provided by the Linux PCI subsystem.
+In Hyper-V guests these standard functions map to functions
+hv_pcifront_read_config() and hv_pcifront_write_config()
+in the Hyper-V virtual PCI driver.  In normal VMs,
+these hv_pcifront_*() functions directly access the PCI config
+space, and the accesses trap to Hyper-V to be handled.
+But in CoCo VMs, memory encryption prevents Hyper-V
+from reading the guest instruction stream to emulate the
+access, so the hv_pcifront_*() functions must invoke
+hypercalls with explicit arguments describing the access to be
+made.
+
+Config Block back-channel
+-------------------------
+The Hyper-V host and Hyper-V virtual PCI driver in Linux
+together implement a non-standard back-channel communication
+path between the host and guest.  The back-channel path uses
+messages sent over the VMBus channel associated with the vPCI
+device.  The functions hyperv_read_cfg_blk() and
+hyperv_write_cfg_blk() are the primary interfaces provided to
+other parts of the Linux kernel.  As of this writing, these
+interfaces are used only by the Mellanox mlx5 driver to pass
+diagnostic data to a Hyper-V host running in the Azure public
+cloud.  The functions hyperv_read_cfg_blk() and
+hyperv_write_cfg_blk() are implemented in a separate module
+(pci-hyperv-intf.c, under CONFIG_PCI_HYPERV_INTERFACE) that
+effectively stubs them out when running in non-Hyper-V
+environments.
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 7025b3751027..09c7e585ff58 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -147,10 +147,29 @@ described as 'basic' will be available.
 The new VM has no virtual cpus and no memory.
 You probably want to use 0 as machine type.
 
+X86:
+^^^^
+
+Supported X86 VM types can be queried via KVM_CAP_VM_TYPES.
+
+S390:
+^^^^^
+
 In order to create user controlled virtual machines on S390, check
 KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL as
 privileged user (CAP_SYS_ADMIN).
 
+MIPS:
+^^^^^
+
+To use hardware assisted virtualization on MIPS (VZ ASE) rather than
+the default trap & emulate implementation (which changes the virtual
+memory layout to fit in user mode), check KVM_CAP_MIPS_VZ and use the
+flag KVM_VM_MIPS_VZ.
+
+ARM64:
+^^^^^^
+
 On arm64, the physical address size for a VM (IPA Size limit) is limited
 to 40bits by default. The limit can be configured if the host supports the
 extension KVM_CAP_ARM_VM_IPA_SIZE. When supported, use
@@ -608,18 +627,6 @@ interrupt number dequeues the interrupt.
 This is an asynchronous vcpu ioctl and can be invoked from any thread.
 
 
-4.17 KVM_DEBUG_GUEST
---------------------
-
-:Capability: basic
-:Architectures: none
-:Type: vcpu ioctl
-:Parameters: none)
-:Returns: -1 on error
-
-Support for this has been removed.  Use KVM_SET_GUEST_DEBUG instead.
-
-
 4.18 KVM_GET_MSRS
 -----------------
 
@@ -6192,6 +6199,130 @@ to know what fields can be changed for the system register described by
 ``op0, op1, crn, crm, op2``. KVM rejects ID register values that describe a
 superset of the features supported by the system.
 
+4.140 KVM_SET_USER_MEMORY_REGION2
+---------------------------------
+
+:Capability: KVM_CAP_USER_MEMORY2
+:Architectures: all
+:Type: vm ioctl
+:Parameters: struct kvm_userspace_memory_region2 (in)
+:Returns: 0 on success, -1 on error
+
+KVM_SET_USER_MEMORY_REGION2 is an extension to KVM_SET_USER_MEMORY_REGION that
+allows mapping guest_memfd memory into a guest.  All fields shared with
+KVM_SET_USER_MEMORY_REGION identically.  Userspace can set KVM_MEM_GUEST_MEMFD
+in flags to have KVM bind the memory region to a given guest_memfd range of
+[guest_memfd_offset, guest_memfd_offset + memory_size].  The target guest_memfd
+must point at a file created via KVM_CREATE_GUEST_MEMFD on the current VM, and
+the target range must not be bound to any other memory region.  All standard
+bounds checks apply (use common sense).
+
+::
+
+  struct kvm_userspace_memory_region2 {
+	__u32 slot;
+	__u32 flags;
+	__u64 guest_phys_addr;
+	__u64 memory_size; /* bytes */
+	__u64 userspace_addr; /* start of the userspace allocated memory */
+	__u64 guest_memfd_offset;
+	__u32 guest_memfd;
+	__u32 pad1;
+	__u64 pad2[14];
+  };
+
+A KVM_MEM_GUEST_MEMFD region _must_ have a valid guest_memfd (private memory) and
+userspace_addr (shared memory).  However, "valid" for userspace_addr simply
+means that the address itself must be a legal userspace address.  The backing
+mapping for userspace_addr is not required to be valid/populated at the time of
+KVM_SET_USER_MEMORY_REGION2, e.g. shared memory can be lazily mapped/allocated
+on-demand.
+
+When mapping a gfn into the guest, KVM selects shared vs. private, i.e consumes
+userspace_addr vs. guest_memfd, based on the gfn's KVM_MEMORY_ATTRIBUTE_PRIVATE
+state.  At VM creation time, all memory is shared, i.e. the PRIVATE attribute
+is '0' for all gfns.  Userspace can control whether memory is shared/private by
+toggling KVM_MEMORY_ATTRIBUTE_PRIVATE via KVM_SET_MEMORY_ATTRIBUTES as needed.
+
+4.141 KVM_SET_MEMORY_ATTRIBUTES
+-------------------------------
+
+:Capability: KVM_CAP_MEMORY_ATTRIBUTES
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_memory_attributes (in)
+:Returns: 0 on success, <0 on error
+
+KVM_SET_MEMORY_ATTRIBUTES allows userspace to set memory attributes for a range
+of guest physical memory.
+
+::
+
+  struct kvm_memory_attributes {
+	__u64 address;
+	__u64 size;
+	__u64 attributes;
+	__u64 flags;
+  };
+
+  #define KVM_MEMORY_ATTRIBUTE_PRIVATE           (1ULL << 3)
+
+The address and size must be page aligned.  The supported attributes can be
+retrieved via ioctl(KVM_CHECK_EXTENSION) on KVM_CAP_MEMORY_ATTRIBUTES.  If
+executed on a VM, KVM_CAP_MEMORY_ATTRIBUTES precisely returns the attributes
+supported by that VM.  If executed at system scope, KVM_CAP_MEMORY_ATTRIBUTES
+returns all attributes supported by KVM.  The only attribute defined at this
+time is KVM_MEMORY_ATTRIBUTE_PRIVATE, which marks the associated gfn as being
+guest private memory.
+
+Note, there is no "get" API.  Userspace is responsible for explicitly tracking
+the state of a gfn/page as needed.
+
+The "flags" field is reserved for future extensions and must be '0'.
+
+4.142 KVM_CREATE_GUEST_MEMFD
+----------------------------
+
+:Capability: KVM_CAP_GUEST_MEMFD
+:Architectures: none
+:Type: vm ioctl
+:Parameters: struct kvm_create_guest_memfd(in)
+:Returns: 0 on success, <0 on error
+
+KVM_CREATE_GUEST_MEMFD creates an anonymous file and returns a file descriptor
+that refers to it.  guest_memfd files are roughly analogous to files created
+via memfd_create(), e.g. guest_memfd files live in RAM, have volatile storage,
+and are automatically released when the last reference is dropped.  Unlike
+"regular" memfd_create() files, guest_memfd files are bound to their owning
+virtual machine (see below), cannot be mapped, read, or written by userspace,
+and cannot be resized  (guest_memfd files do however support PUNCH_HOLE).
+
+::
+
+  struct kvm_create_guest_memfd {
+	__u64 size;
+	__u64 flags;
+	__u64 reserved[6];
+  };
+
+Conceptually, the inode backing a guest_memfd file represents physical memory,
+i.e. is coupled to the virtual machine as a thing, not to a "struct kvm".  The
+file itself, which is bound to a "struct kvm", is that instance's view of the
+underlying memory, e.g. effectively provides the translation of guest addresses
+to host memory.  This allows for use cases where multiple KVM structures are
+used to manage a single virtual machine, e.g. when performing intrahost
+migration of a virtual machine.
+
+KVM currently only supports mapping guest_memfd via KVM_SET_USER_MEMORY_REGION2,
+and more specifically via the guest_memfd and guest_memfd_offset fields in
+"struct kvm_userspace_memory_region2", where guest_memfd_offset is the offset
+into the guest_memfd instance.  For a given guest_memfd file, there can be at
+most one mapping per page, i.e. binding multiple memory regions to a single
+guest_memfd range is not allowed (any number of memory regions can be bound to
+a single guest_memfd file, but the bound ranges must not overlap).
+
+See KVM_SET_USER_MEMORY_REGION2 for additional details.
+
 5. The kvm_run structure
 ========================
 
@@ -6826,6 +6957,30 @@ spec refer, https://github.com/riscv/riscv-sbi-doc.
 
 ::
 
+		/* KVM_EXIT_MEMORY_FAULT */
+		struct {
+  #define KVM_MEMORY_EXIT_FLAG_PRIVATE	(1ULL << 3)
+			__u64 flags;
+			__u64 gpa;
+			__u64 size;
+		} memory_fault;
+
+KVM_EXIT_MEMORY_FAULT indicates the vCPU has encountered a memory fault that
+could not be resolved by KVM.  The 'gpa' and 'size' (in bytes) describe the
+guest physical address range [gpa, gpa + size) of the fault.  The 'flags' field
+describes properties of the faulting access that are likely pertinent:
+
+ - KVM_MEMORY_EXIT_FLAG_PRIVATE - When set, indicates the memory fault occurred
+   on a private memory access.  When clear, indicates the fault occurred on a
+   shared access.
+
+Note!  KVM_EXIT_MEMORY_FAULT is unique among all KVM exit reasons in that it
+accompanies a return code of '-1', not '0'!  errno will always be set to EFAULT
+or EHWPOISON when KVM exits with KVM_EXIT_MEMORY_FAULT, userspace should assume
+kvm_run.exit_reason is stale/undefined for all other error numbers.
+
+::
+
     /* KVM_EXIT_NOTIFY */
     struct {
   #define KVM_NOTIFY_CONTEXT_INVALID	(1 << 0)
@@ -7858,6 +8013,27 @@ This capability is aimed to mitigate the threat that malicious VMs can
 cause CPU stuck (due to event windows don't open up) and make the CPU
 unavailable to host or other VMs.
 
+7.34 KVM_CAP_MEMORY_FAULT_INFO
+------------------------------
+
+:Architectures: x86
+:Returns: Informational only, -EINVAL on direct KVM_ENABLE_CAP.
+
+The presence of this capability indicates that KVM_RUN will fill
+kvm_run.memory_fault if KVM cannot resolve a guest page fault VM-Exit, e.g. if
+there is a valid memslot but no backing VMA for the corresponding host virtual
+address.
+
+The information in kvm_run.memory_fault is valid if and only if KVM_RUN returns
+an error with errno=EFAULT or errno=EHWPOISON *and* kvm_run.exit_reason is set
+to KVM_EXIT_MEMORY_FAULT.
+
+Note: Userspaces which attempt to resolve memory faults so that they can retry
+KVM_RUN are encouraged to guard against repeatedly receiving the same
+error/annotated fault.
+
+See KVM_EXIT_MEMORY_FAULT for more information.
+
 8. Other capabilities.
 ======================
 
@@ -8374,6 +8550,7 @@ PVHVM guests. Valid flags are::
   #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL		(1 << 4)
   #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND		(1 << 5)
   #define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG	(1 << 6)
+  #define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE	(1 << 7)
 
 The KVM_XEN_HVM_CONFIG_HYPERCALL_MSR flag indicates that the KVM_XEN_HVM_CONFIG
 ioctl is available, for the guest to set its hypercall page.
@@ -8417,6 +8594,11 @@ behave more correctly, not using the XEN_RUNSTATE_UPDATE flag until/unless
 specifically enabled (by the guest making the hypercall, causing the VMM
 to enable the KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG attribute).
 
+The KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE flag indicates that KVM supports
+clearing the PVCLOCK_TSC_STABLE_BIT flag in Xen pvclock sources. This will be
+done when the KVM_CAP_XEN_HVM ioctl sets the
+KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE flag.
+
 8.31 KVM_CAP_PPC_MULTITCE
 -------------------------
 
@@ -8596,6 +8778,24 @@ block sizes is exposed in KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES as a
 64-bit bitmap (each bit describing a block size). The default value is
 0, to disable the eager page splitting.
 
+8.41 KVM_CAP_VM_TYPES
+---------------------
+
+:Capability: KVM_CAP_MEMORY_ATTRIBUTES
+:Architectures: x86
+:Type: system ioctl
+
+This capability returns a bitmap of support VM types.  The 1-setting of bit @n
+means the VM type with value @n is supported.  Possible values of @n are::
+
+  #define KVM_X86_DEFAULT_VM	0
+  #define KVM_X86_SW_PROTECTED_VM	1
+
+Note, KVM_X86_SW_PROTECTED_VM is currently only for development and testing.
+Do not use KVM_X86_SW_PROTECTED_VM for "real" VMs, and especially not in
+production.  The behavior and effective ABI for software-protected VMs is
+unstable.
+
 9. Known KVM API problems
 =========================
 
diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst
index 3a034db5e55f..02880d5552d5 100644
--- a/Documentation/virt/kvm/locking.rst
+++ b/Documentation/virt/kvm/locking.rst
@@ -43,10 +43,9 @@ On x86:
 
 - vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock and kvm->arch.xen.xen_lock
 
-- kvm->arch.mmu_lock is an rwlock.  kvm->arch.tdp_mmu_pages_lock and
-  kvm->arch.mmu_unsync_pages_lock are taken inside kvm->arch.mmu_lock, and
-  cannot be taken without already holding kvm->arch.mmu_lock (typically with
-  ``read_lock`` for the TDP MMU, thus the need for additional spinlocks).
+- kvm->arch.mmu_lock is an rwlock; critical sections for
+  kvm->arch.tdp_mmu_pages_lock and kvm->arch.mmu_unsync_pages_lock must
+  also take kvm->arch.mmu_lock
 
 Everything else is a leaf: no other lock is taken inside the critical
 sections.
diff --git a/MAINTAINERS b/MAINTAINERS
index 391bbb855cbe..7f0b462d85a4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -441,6 +441,13 @@ W:	http://wiki.analog.com/AD7879
 W:	https://ez.analog.com/linux-software-drivers
 F:	drivers/input/touchscreen/ad7879.c
 
+ADAFRUIT MINI I2C GAMEPAD
+M:	Anshul Dalal <anshulusr@gmail.com>
+L:	linux-input@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/input/adafruit,seesaw-gamepad.yaml
+F:	drivers/input/joystick/adafruit-seesaw.c
+
 ADDRESS SPACE LAYOUT RANDOMIZATION (ASLR)
 M:	Jiri Kosina <jikos@kernel.org>
 S:	Maintained
@@ -890,6 +897,14 @@ Q:	https://patchwork.kernel.org/project/linux-rdma/list/
 F:	drivers/infiniband/hw/efa/
 F:	include/uapi/rdma/efa-abi.h
 
+AMD AXI W1 DRIVER
+M:	Kris Chaplin <kris.chaplin@amd.com>
+R:	Thomas Delev <thomas.delev@amd.com>
+R:	Michal Simek <michal.simek@amd.com>
+S:	Maintained
+F:	Documentation/devicetree/bindings/w1/amd,axi-1wire-host.yaml
+F:	drivers/w1/masters/amd_axi_w1.c
+
 AMD CDX BUS DRIVER
 M:	Nipun Gupta <nipun.gupta@amd.com>
 M:	Nikhil Agarwal <nikhil.agarwal@amd.com>
@@ -1123,6 +1138,14 @@ F:	Documentation/ABI/testing/sysfs-bus-iio-adc-ad4130
 F:	Documentation/devicetree/bindings/iio/adc/adi,ad4130.yaml
 F:	drivers/iio/adc/ad4130.c
 
+ANALOG DEVICES INC AD7091R DRIVER
+M:	Marcelo Schmitt <marcelo.schmitt@analog.com>
+L:	linux-iio@vger.kernel.org
+S:	Supported
+W:	http://ez.analog.com/community/linux-device-drivers
+F:	Documentation/devicetree/bindings/iio/adc/adi,ad7091r*
+F:	drivers/iio/adc/drivers/iio/adc/ad7091r*
+
 ANALOG DEVICES INC AD7192 DRIVER
 M:	Alexandru Tachici <alexandru.tachici@analog.com>
 L:	linux-iio@vger.kernel.org
@@ -1372,6 +1395,7 @@ F:	drivers/hwmon/max31760.c
 
 ANALOGBITS PLL LIBRARIES
 M:	Paul Walmsley <paul.walmsley@sifive.com>
+M:	Samuel Holland <samuel.holland@sifive.com>
 S:	Supported
 F:	drivers/clk/analogbits/*
 F:	include/linux/clk/analogbits*
@@ -2048,7 +2072,6 @@ ARM/CORESIGHT FRAMEWORK AND DRIVERS
 M:	Suzuki K Poulose <suzuki.poulose@arm.com>
 R:	Mike Leach <mike.leach@linaro.org>
 R:	James Clark <james.clark@arm.com>
-R:	Leo Yan <leo.yan@linaro.org>
 L:	coresight@lists.linaro.org (moderated for non-subscribers)
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -2134,7 +2157,7 @@ M:	Shawn Guo <shawnguo@kernel.org>
 M:	Sascha Hauer <s.hauer@pengutronix.de>
 R:	Pengutronix Kernel Team <kernel@pengutronix.de>
 R:	Fabio Estevam <festevam@gmail.com>
-R:	NXP Linux Team <linux-imx@nxp.com>
+L:	imx@lists.linux.dev
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git
@@ -3044,6 +3067,13 @@ S:	Supported
 W:	http://www.akm.com/
 F:	drivers/iio/magnetometer/ak8974.c
 
+AOSONG AGS02MA TVOC SENSOR DRIVER
+M:	Anshul Dalal <anshulusr@gmail.com>
+L:	linux-iio@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/iio/chemical/aosong,ags02ma.yaml
+F:	drivers/iio/chemical/ags02ma.c
+
 ASC7621 HARDWARE MONITOR DRIVER
 M:	George Joseph <george.joseph@fairview5.com>
 L:	linux-hwmon@vger.kernel.org
@@ -3139,10 +3169,10 @@ F:	drivers/hwmon/asus-ec-sensors.c
 
 ASUS NOTEBOOKS AND EEEPC ACPI/WMI EXTRAS DRIVERS
 M:	Corentin Chary <corentin.chary@gmail.com>
-L:	acpi4asus-user@lists.sourceforge.net
+M:	Luke D. Jones <luke@ljones.dev>
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
-W:	http://acpi4asus.sf.net
+W:	https://asus-linux.org/
 F:	drivers/platform/x86/asus*.c
 F:	drivers/platform/x86/eeepc*.c
 
@@ -3361,9 +3391,8 @@ F:	Documentation/devicetree/bindings/iio/adc/avia-hx711.yaml
 F:	drivers/iio/adc/hx711.c
 
 AX.25 NETWORK LAYER
-M:	Ralf Baechle <ralf@linux-mips.org>
 L:	linux-hams@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linux-ax25.in-berlin.de
 F:	include/net/ax25.h
 F:	include/uapi/linux/ax25.h
@@ -3602,7 +3631,6 @@ F:	drivers/mtd/devices/block2mtd.c
 
 BLUETOOTH DRIVERS
 M:	Marcel Holtmann <marcel@holtmann.org>
-M:	Johan Hedberg <johan.hedberg@gmail.com>
 M:	Luiz Augusto von Dentz <luiz.dentz@gmail.com>
 L:	linux-bluetooth@vger.kernel.org
 S:	Supported
@@ -3643,6 +3671,13 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/iio/accel/bosch,bma400.yaml
 F:	drivers/iio/accel/bma400*
 
+BOSCH SENSORTEC BMI323 IMU IIO DRIVER
+M:	Jagath Jog J <jagathjog1996@gmail.com>
+L:	linux-iio@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/iio/imu/bosch,bmi323.yaml
+F:	drivers/iio/imu/bmi323/
+
 BPF JIT for ARM
 M:	Russell King <linux@armlinux.org.uk>
 M:	Puranjay Mohan <puranjay12@gmail.com>
@@ -3658,6 +3693,13 @@ L:	bpf@vger.kernel.org
 S:	Supported
 F:	arch/arm64/net/
 
+BPF JIT for LOONGARCH
+M:	Tiezhu Yang <yangtiezhu@loongson.cn>
+R:	Hengqi Chen <hengqi.chen@gmail.com>
+L:	bpf@vger.kernel.org
+S:	Maintained
+F:	arch/loongarch/net/
+
 BPF JIT for MIPS (32-BIT AND 64-BIT)
 M:	Johan Almbladh <johan.almbladh@anyfinetworks.com>
 M:	Paul Burton <paulburton@kernel.org>
@@ -4128,14 +4170,14 @@ F:	drivers/firmware/broadcom/tee_bnxt_fw.c
 F:	drivers/net/ethernet/broadcom/bnxt/
 F:	include/linux/firmware/broadcom/tee_bnxt_fw.h
 
-BROADCOM BRCM80211 IEEE802.11n WIRELESS DRIVER
-M:	Arend van Spriel <aspriel@gmail.com>
-M:	Franky Lin <franky.lin@broadcom.com>
-M:	Hante Meuleman <hante.meuleman@broadcom.com>
+BROADCOM BRCM80211 IEEE802.11 WIRELESS DRIVERS
+M:	Arend van Spriel <arend.vanspriel@broadcom.com>
 L:	linux-wireless@vger.kernel.org
+L:	brcm80211@lists.linux.dev
 L:	brcm80211-dev-list.pdl@broadcom.com
 S:	Supported
 F:	drivers/net/wireless/broadcom/brcm80211/
+F:	include/linux/platform_data/brcmfmac.h
 
 BROADCOM BRCMSTB GPIO DRIVER
 M:	Doug Berger <opendmb@gmail.com>
@@ -4506,7 +4548,7 @@ F:	drivers/net/ieee802154/ca8210.c
 
 CACHEFILES: FS-CACHE BACKEND FOR CACHING ON MOUNTED FILESYSTEMS
 M:	David Howells <dhowells@redhat.com>
-L:	linux-cachefs@redhat.com (moderated for non-subscribers)
+L:	netfs@lists.linux.dev
 S:	Supported
 F:	Documentation/filesystems/caching/cachefiles.rst
 F:	fs/cachefiles/
@@ -4690,11 +4732,8 @@ F:	drivers/i2c/busses/i2c-octeon*
 F:	drivers/i2c/busses/i2c-thunderx*
 
 CAVIUM LIQUIDIO NETWORK DRIVER
-M:	Derek Chickles <dchickles@marvell.com>
-M:	Satanand Burla <sburla@marvell.com>
-M:	Felix Manlunas <fmanlunas@marvell.com>
 L:	netdev@vger.kernel.org
-S:	Supported
+S:	Orphan
 W:	http://www.marvell.com
 F:	drivers/net/ethernet/cavium/liquidio/
 
@@ -5198,7 +5237,7 @@ X:	drivers/clk/clkdev.c
 COMMON INTERNET FILE SYSTEM CLIENT (CIFS and SMB3)
 M:	Steve French <sfrench@samba.org>
 R:	Paulo Alcantara <pc@manguebit.com> (DFS, global name space)
-R:	Ronnie Sahlberg <lsahlber@redhat.com> (directory leases, sparse files)
+R:	Ronnie Sahlberg <ronniesahlberg@gmail.com> (directory leases, sparse files)
 R:	Shyam Prasad N <sprasad@microsoft.com> (multichannel)
 R:	Tom Talpey <tom@talpey.com> (RDMA, smbdirect)
 L:	linux-cifs@vger.kernel.org
@@ -5251,6 +5290,7 @@ M:	Dan Williams <dan.j.williams@intel.com>
 L:	linux-cxl@vger.kernel.org
 S:	Maintained
 F:	drivers/cxl/
+F:	include/linux/cxl-event.h
 F:	include/uapi/linux/cxl_mem.h
 F:	tools/testing/cxl/
 
@@ -5339,7 +5379,7 @@ CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)
 M:	Johannes Weiner <hannes@cmpxchg.org>
 M:	Michal Hocko <mhocko@kernel.org>
 M:	Roman Gushchin <roman.gushchin@linux.dev>
-M:	Shakeel Butt <shakeelb@google.com>
+M:	Shakeel Butt <shakeel.butt@linux.dev>
 R:	Muchun Song <muchun.song@linux.dev>
 L:	cgroups@vger.kernel.org
 L:	linux-mm@kvack.org
@@ -5384,6 +5424,12 @@ F:	include/linux/counter.h
 F:	include/uapi/linux/counter.h
 F:	tools/counter/
 
+COUNTER WATCH EVENTS TOOL
+M:	Fabrice Gasnier <fabrice.gasnier@foss.st.com>
+L:	linux-iio@vger.kernel.org
+S:	Maintained
+F:	tools/counter/counter_watch_events.c
+
 CP2615 I2C DRIVER
 M:	Bence Csókás <bence98@sch.bme.hu>
 S:	Maintained
@@ -5565,6 +5611,11 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/net/can/ctu,ctucanfd.yaml
 F:	drivers/net/can/ctucanfd/
 
+CVE ASSIGNMENT CONTACT
+M:	CVE Assignment Team <cve@kernel.org>
+S:	Maintained
+F:	Documentation/process/cve.rst
+
 CW1200 WLAN driver
 S:	Orphan
 F:	drivers/net/wireless/st/cw1200/
@@ -5913,7 +5964,6 @@ S:	Maintained
 F:	drivers/platform/x86/dell/dell-wmi-descriptor.c
 
 DELL WMI HARDWARE PRIVACY SUPPORT
-M:	Perry Yuan <Perry.Yuan@dell.com>
 L:	Dell.Client.Kernel@dell.com
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
@@ -7910,12 +7960,13 @@ L:	rust-for-linux@vger.kernel.org
 S:	Maintained
 F:	rust/kernel/net/phy.rs
 
-EXEC & BINFMT API
+EXEC & BINFMT API, ELF
 R:	Eric Biederman <ebiederm@xmission.com>
 R:	Kees Cook <keescook@chromium.org>
 L:	linux-mm@kvack.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/execve
+F:	Documentation/userspace-api/ELF.rst
 F:	fs/*binfmt_*.c
 F:	fs/exec.c
 F:	include/linux/binfmts.h
@@ -8176,6 +8227,20 @@ S:	Supported
 F:	fs/iomap/
 F:	include/linux/iomap.h
 
+FILESYSTEMS [NETFS LIBRARY]
+M:	David Howells <dhowells@redhat.com>
+R:	Jeff Layton <jlayton@kernel.org>
+L:	netfs@lists.linux.dev
+L:	linux-fsdevel@vger.kernel.org
+S:	Supported
+F:	Documentation/filesystems/caching/
+F:	Documentation/filesystems/netfs_library.rst
+F:	fs/netfs/
+F:	include/linux/fscache*.h
+F:	include/linux/netfs.h
+F:	include/trace/events/fscache.h
+F:	include/trace/events/netfs.h
+
 FILESYSTEMS [STACKABLE]
 M:	Miklos Szeredi <miklos@szeredi.hu>
 M:	Amir Goldstein <amir73il@gmail.com>
@@ -8431,7 +8496,7 @@ FREESCALE IMX / MXC FEC DRIVER
 M:	Wei Fang <wei.fang@nxp.com>
 R:	Shenwei Wang <shenwei.wang@nxp.com>
 R:	Clark Wang <xiaoning.wang@nxp.com>
-R:	NXP Linux Team <linux-imx@nxp.com>
+L:	imx@lists.linux.dev
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/fsl,fec.yaml
@@ -8466,7 +8531,7 @@ F:	drivers/i2c/busses/i2c-imx.c
 FREESCALE IMX LPI2C DRIVER
 M:	Dong Aisheng <aisheng.dong@nxp.com>
 L:	linux-i2c@vger.kernel.org
-L:	linux-imx@nxp.com
+L:	imx@lists.linux.dev
 S:	Maintained
 F:	Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.yaml
 F:	drivers/i2c/busses/i2c-imx-lpi2c.c
@@ -8621,14 +8686,6 @@ F:	Documentation/power/freezing-of-tasks.rst
 F:	include/linux/freezer.h
 F:	kernel/freezer.c
 
-FS-CACHE: LOCAL CACHING FOR NETWORK FILESYSTEMS
-M:	David Howells <dhowells@redhat.com>
-L:	linux-cachefs@redhat.com (moderated for non-subscribers)
-S:	Supported
-F:	Documentation/filesystems/caching/
-F:	fs/fscache/
-F:	include/linux/fscache*.h
-
 FSCRYPT: FILE SYSTEM LEVEL ENCRYPTION SUPPORT
 M:	Eric Biggers <ebiggers@kernel.org>
 M:	Theodore Y. Ts'o <tytso@mit.edu>
@@ -9731,6 +9788,13 @@ F:	lib/test_hmm*
 F:	mm/hmm*
 F:	tools/testing/selftests/mm/*hmm*
 
+HONEYWELL HSC030PA PRESSURE SENSOR SERIES IIO DRIVER
+M:	Petre Rodan <petre.rodan@subdimension.ro>
+L:	linux-iio@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/iio/pressure/honeywell,hsc030pa.yaml
+F:	drivers/iio/pressure/hsc030pa*
+
 HONEYWELL MPRLS0025PA PRESSURE SENSOR SERIES IIO DRIVER
 M:	Andreas Klinger <ak@it-klinger.de>
 L:	linux-iio@vger.kernel.org
@@ -10011,7 +10075,7 @@ F:	Documentation/i2c/busses/i2c-parport.rst
 F:	drivers/i2c/busses/i2c-parport.c
 
 I2C SUBSYSTEM
-M:	Wolfram Sang <wsa@kernel.org>
+M:	Wolfram Sang <wsa+renesas@sang-engineering.com>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 W:	https://i2c.wiki.kernel.org/
@@ -10033,7 +10097,7 @@ L:	linux-i2c@vger.kernel.org
 S:	Maintained
 W:	https://i2c.wiki.kernel.org/
 Q:	https://patchwork.ozlabs.org/project/linux-i2c/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/andi.shyti/linux.git
 F:	Documentation/devicetree/bindings/i2c/
 F:	drivers/i2c/algos/
 F:	drivers/i2c/busses/
@@ -10189,7 +10253,6 @@ IBM Power SRIOV Virtual NIC Device Driver
 M:	Haren Myneni <haren@linux.ibm.com>
 M:	Rick Lindsley <ricklind@linux.ibm.com>
 R:	Nick Child <nnac123@linux.ibm.com>
-R:	Dany Madden <danymadden@us.ibm.com>
 R:	Thomas Falcon <tlfalcon@linux.ibm.com>
 L:	netdev@vger.kernel.org
 S:	Supported
@@ -10226,7 +10289,7 @@ F:	drivers/scsi/ibmvscsi/ibmvscsi*
 F:	include/scsi/viosrp.h
 
 IBM Power Virtual SCSI Device Target Driver
-M:	Michael Cyr <mikecyr@linux.ibm.com>
+M:	Tyrel Datwyler <tyreld@linux.ibm.com>
 L:	linux-scsi@vger.kernel.org
 L:	target-devel@vger.kernel.org
 S:	Supported
@@ -10346,8 +10409,8 @@ IIO LIGHT SENSOR GAIN-TIME-SCALE HELPERS
 M:	Matti Vaittinen <mazziesaccount@gmail.com>
 L:	linux-iio@vger.kernel.org
 S:	Maintained
-F:	drivers/iio/light/gain-time-scale-helper.c
-F:	drivers/iio/light/gain-time-scale-helper.h
+F:	drivers/iio/industrialio-gts-helper.c
+F:	include/linux/iio/iio-gts-helper.h
 
 IIO MULTIPLEXER
 M:	Peter Rosin <peda@axentia.se>
@@ -10672,7 +10735,7 @@ INTEL DRM I915 DRIVER (Meteor Lake, DG2 and older excluding Poulsbo, Moorestown
 M:	Jani Nikula <jani.nikula@linux.intel.com>
 M:	Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
 M:	Rodrigo Vivi <rodrigo.vivi@intel.com>
-M:	Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
+M:	Tvrtko Ursulin <tursulin@ursulin.net>
 L:	intel-gfx@lists.freedesktop.org
 S:	Supported
 W:	https://drm.pages.freedesktop.org/intel-docs/
@@ -10744,11 +10807,11 @@ F:	drivers/gpio/gpio-tangier.h
 
 INTEL GVT-g DRIVERS (Intel GPU Virtualization)
 M:	Zhenyu Wang <zhenyuw@linux.intel.com>
-M:	Zhi Wang <zhi.a.wang@intel.com>
+M:	Zhi Wang <zhi.wang.linux@gmail.com>
 L:	intel-gvt-dev@lists.freedesktop.org
 L:	intel-gfx@lists.freedesktop.org
 S:	Supported
-W:	https://01.org/igvt-g
+W:	https://github.com/intel/gvt-linux/wiki
 T:	git https://github.com/intel/gvt-linux.git
 F:	drivers/gpu/drm/i915/gvt/
 
@@ -11070,7 +11133,6 @@ S:	Supported
 F:	drivers/net/wireless/intel/iwlegacy/
 
 INTEL WIRELESS WIFI LINK (iwlwifi)
-M:	Gregory Greenman <gregory.greenman@intel.com>
 M:	Miri Korenblit <miriam.rachel.korenblit@intel.com>
 L:	linux-wireless@vger.kernel.org
 S:	Supported
@@ -11668,6 +11730,7 @@ F:	fs/smb/server/
 KERNEL UNIT TESTING FRAMEWORK (KUnit)
 M:	Brendan Higgins <brendanhiggins@google.com>
 M:	David Gow <davidgow@google.com>
+R:	Rae Moar <rmoar@google.com>
 L:	linux-kselftest@vger.kernel.org
 L:	kunit-dev@googlegroups.com
 S:	Maintained
@@ -12454,7 +12517,6 @@ F:	arch/powerpc/include/asm/livepatch.h
 F:	include/linux/livepatch.h
 F:	kernel/livepatch/
 F:	kernel/module/livepatch.c
-F:	lib/livepatch/
 F:	samples/livepatch/
 F:	tools/testing/selftests/livepatch/
 
@@ -12583,6 +12645,13 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/gpio/loongson,ls-gpio.yaml
 F:	drivers/gpio/gpio-loongson-64bit.c
 
+LOONGSON LS2X APB DMA DRIVER
+M:	Binbin Zhou <zhoubinbin@loongson.cn>
+L:	dmaengine@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/dma/loongson,ls2x-apbdma.yaml
+F:	drivers/dma/ls2x-apb-dma.c
+
 LOONGSON LS2X I2C DRIVER
 M:	Binbin Zhou <zhoubinbin@loongson.cn>
 L:	linux-i2c@vger.kernel.org
@@ -12724,17 +12793,23 @@ F:	Documentation/devicetree/bindings/i2c/i2c-mux-ltc4306.txt
 F:	drivers/i2c/muxes/i2c-mux-ltc4306.c
 
 LTP (Linux Test Project)
-M:	Mike Frysinger <vapier@gentoo.org>
 M:	Cyril Hrubis <chrubis@suse.cz>
-M:	Wanlong Gao <wanlong.gao@gmail.com>
 M:	Jan Stancek <jstancek@redhat.com>
-M:	Stanislav Kholmanskikh <stanislav.kholmanskikh@oracle.com>
-M:	Alexey Kodanev <alexey.kodanev@oracle.com>
+M:	Petr Vorel <pvorel@suse.cz>
+M:	Li Wang <liwang@redhat.com>
+M:	Yang Xu <xuyang2018.jy@fujitsu.com>
 L:	ltp@lists.linux.it (subscribers-only)
 S:	Maintained
 W:	http://linux-test-project.github.io/
 T:	git https://github.com/linux-test-project/ltp.git
 
+LTR390 AMBIENT/UV LIGHT SENSOR DRIVER
+M:	Anshul Dalal <anshulusr@gmail.com>
+L:	linux-iio@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/iio/light/liteon,ltr390.yaml
+F:	drivers/iio/light/ltr390.c
+
 LYNX 28G SERDES PHY DRIVER
 M:	Ioana Ciornei <ioana.ciornei@nxp.com>
 L:	netdev@vger.kernel.org
@@ -12833,6 +12908,8 @@ M:	Alejandro Colomar <alx@kernel.org>
 L:	linux-man@vger.kernel.org
 S:	Maintained
 W:	http://www.kernel.org/doc/man-pages
+T:	git git://git.kernel.org/pub/scm/docs/man-pages/man-pages.git
+T:	git git://www.alejandro-colomar.es/src/alx/linux/man-pages/man-pages.git
 
 MANAGEMENT COMPONENT TRANSPORT PROTOCOL (MCTP)
 M:	Jeremy Kerr <jk@codeconstruct.com.au>
@@ -12947,10 +13024,10 @@ S:	Maintained
 F:	drivers/thermal/armada_thermal.c
 
 MARVELL MVNETA ETHERNET DRIVER
-M:	Thomas Petazzoni <thomas.petazzoni@bootlin.com>
+M:	Marcin Wojtas <marcin.s.wojtas@gmail.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
-F:	drivers/net/ethernet/marvell/mvneta.*
+F:	drivers/net/ethernet/marvell/mvneta*
 
 MARVELL MVPP2 ETHERNET DRIVER
 M:	Marcin Wojtas <marcin.s.wojtas@gmail.com>
@@ -13070,6 +13147,14 @@ F:	Documentation/devicetree/bindings/hwmon/adi,max31827.yaml
 F:	Documentation/hwmon/max31827.rst
 F:	drivers/hwmon/max31827.c
 
+MAX31335 RTC DRIVER
+M:	Antoniu Miclaus <antoniu.miclaus@analog.com>
+L:	linux-rtc@vger.kernel.org
+S:	Supported
+W:	https://ez.analog.com/linux-software-drivers
+F:	Documentation/devicetree/bindings/rtc/adi,max31335.yaml
+F:	drivers/rtc/rtc-max31335.c
+
 MAX6650 HARDWARE MONITOR AND FAN CONTROLLER DRIVER
 L:	linux-hwmon@vger.kernel.org
 S:	Orphan
@@ -13279,6 +13364,13 @@ F:	Documentation/ABI/testing/sysfs-bus-iio-potentiometer-mcp4531
 F:	drivers/iio/potentiometer/mcp4018.c
 F:	drivers/iio/potentiometer/mcp4531.c
 
+MCP4821 DAC DRIVER
+M:	Anshul Dalal <anshulusr@gmail.com>
+L:	linux-iio@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/iio/dac/microchip,mcp4821.yaml
+F:	drivers/iio/dac/mcp4821.c
+
 MCR20A IEEE-802.15.4 RADIO DRIVER
 M:	Stefan Schmidt <stefan@datenfreihafen.org>
 L:	linux-wpan@vger.kernel.org
@@ -13585,7 +13677,6 @@ F:	drivers/dma/mediatek/
 
 MEDIATEK ETHERNET DRIVER
 M:	Felix Fietkau <nbd@nbd.name>
-M:	John Crispin <john@phrozen.org>
 M:	Sean Wang <sean.wang@mediatek.com>
 M:	Mark Lee <Mark-MC.Lee@mediatek.com>
 M:	Lorenzo Bianconi <lorenzo@kernel.org>
@@ -13741,7 +13832,6 @@ F:	include/soc/mediatek/smi.h
 MEDIATEK SWITCH DRIVER
 M:	Arınç ÜNAL <arinc.unal@arinc9.com>
 M:	Daniel Golle <daniel@makrotopia.org>
-M:	Landen Chao <Landen.Chao@mediatek.com>
 M:	DENG Qingfang <dqfext@gmail.com>
 M:	Sean Wang <sean.wang@mediatek.com>
 L:	netdev@vger.kernel.org
@@ -13806,6 +13896,13 @@ S:	Supported
 W:	http://www.melexis.com
 F:	drivers/iio/temperature/mlx90632.c
 
+MELEXIS MLX90635 DRIVER
+M:	Crt Mori <cmo@melexis.com>
+L:	linux-iio@vger.kernel.org
+S:	Supported
+W:	http://www.melexis.com
+F:	drivers/iio/temperature/mlx90635.c
+
 MELFAS MIP4 TOUCHSCREEN DRIVER
 M:	Sangwon Jee <jeesw@melfas.com>
 S:	Supported
@@ -14014,6 +14111,17 @@ F:	mm/
 F:	tools/mm/
 F:	tools/testing/selftests/mm/
 
+MEMORY MAPPING
+M:	Andrew Morton <akpm@linux-foundation.org>
+R:	Liam R. Howlett <Liam.Howlett@oracle.com>
+R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Lorenzo Stoakes <lstoakes@gmail.com>
+L:	linux-mm@kvack.org
+S:	Maintained
+W:	http://www.linux-mm.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F:	mm/mmap.c
+
 MEMORY TECHNOLOGY DEVICES (MTD)
 M:	Miquel Raynal <miquel.raynal@bootlin.com>
 M:	Richard Weinberger <richard@nod.at>
@@ -14272,15 +14380,16 @@ MICROCHIP MCP16502 PMIC DRIVER
 M:	Claudiu Beznea <claudiu.beznea@tuxon.dev>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
-F:	Documentation/devicetree/bindings/regulator/mcp16502-regulator.txt
+F:	Documentation/devicetree/bindings/regulator/microchip,mcp16502.yaml
 F:	drivers/regulator/mcp16502.c
 
 MICROCHIP MCP3564 ADC DRIVER
-M:      Marius Cristea <marius.cristea@microchip.com>
-L:      linux-iio@vger.kernel.org
-S:      Supported
-F:      Documentation/devicetree/bindings/iio/adc/microchip,mcp3564.yaml
-F:      drivers/iio/adc/mcp3564.c
+M:	Marius Cristea <marius.cristea@microchip.com>
+L:	linux-iio@vger.kernel.org
+S:	Supported
+F:	Documentation/ABI/testing/sysfs-bus-iio-adc-mcp3564
+F:	Documentation/devicetree/bindings/iio/adc/microchip,mcp3564.yaml
+F:	drivers/iio/adc/mcp3564.c
 
 MICROCHIP MCP3911 ADC DRIVER
 M:	Marcus Folkesson <marcus.folkesson@gmail.com>
@@ -14740,6 +14849,13 @@ S:	Maintained
 F:	Documentation/driver-api/tty/moxa-smartio.rst
 F:	drivers/tty/mxser.*
 
+MP3309C BACKLIGHT DRIVER
+M:	Flavio Suligoi <f.suligoi@asem.it>
+L:	dri-devel@lists.freedesktop.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/leds/backlight/mps,mp3309c.yaml
+F:	drivers/video/backlight/mp3309c.c
+
 MR800 AVERMEDIA USB FM RADIO DRIVER
 M:	Alexey Klimov <klimov.linux@gmail.com>
 L:	linux-media@vger.kernel.org
@@ -15080,6 +15196,7 @@ F:	Documentation/networking/net_cachelines/net_device.rst
 F:	drivers/connector/
 F:	drivers/net/
 F:	include/dt-bindings/net/
+F:	include/linux/cn_proc.h
 F:	include/linux/etherdevice.h
 F:	include/linux/fcdevice.h
 F:	include/linux/fddidevice.h
@@ -15087,6 +15204,7 @@ F:	include/linux/hippidevice.h
 F:	include/linux/if_*
 F:	include/linux/inetdevice.h
 F:	include/linux/netdevice.h
+F:	include/uapi/linux/cn_proc.h
 F:	include/uapi/linux/if_*
 F:	include/uapi/linux/netdevice.h
 X:	drivers/net/wireless/
@@ -15135,6 +15253,8 @@ F:	Documentation/networking/
 F:	Documentation/networking/net_cachelines/
 F:	Documentation/process/maintainer-netdev.rst
 F:	Documentation/userspace-api/netlink/
+F:	include/linux/framer/framer-provider.h
+F:	include/linux/framer/framer.h
 F:	include/linux/in.h
 F:	include/linux/indirect_call_wrapper.h
 F:	include/linux/net.h
@@ -15222,7 +15342,7 @@ K:	\bmdo_
 NETWORKING [MPTCP]
 M:	Matthieu Baerts <matttbe@kernel.org>
 M:	Mat Martineau <martineau@kernel.org>
-R:	Geliang Tang <geliang.tang@linux.dev>
+R:	Geliang Tang <geliang@kernel.org>
 L:	netdev@vger.kernel.org
 L:	mptcp@lists.linux.dev
 S:	Maintained
@@ -15375,6 +15495,15 @@ F:	include/linux/nitro_enclaves.h
 F:	include/uapi/linux/nitro_enclaves.h
 F:	samples/nitro_enclaves/
 
+NITRO SECURE MODULE (NSM)
+M:	Alexander Graf <graf@amazon.com>
+L:	linux-kernel@vger.kernel.org
+L:	The AWS Nitro Enclaves Team <aws-nitro-enclaves-devel@amazon.com>
+S:	Supported
+W:	https://aws.amazon.com/ec2/nitro/nitro-enclaves/
+F:	drivers/misc/nsm.c
+F:	include/uapi/linux/nsm.h
+
 NOHZ, DYNTICKS SUPPORT
 M:	Frederic Weisbecker <frederic@kernel.org>
 M:	Thomas Gleixner <tglx@linutronix.de>
@@ -15460,16 +15589,6 @@ W:	https://github.com/davejiang/linux/wiki
 T:	git https://github.com/davejiang/linux.git
 F:	drivers/ntb/hw/intel/
 
-NTFS FILESYSTEM
-M:	Anton Altaparmakov <anton@tuxera.com>
-R:	Namjae Jeon <linkinjeon@kernel.org>
-L:	linux-ntfs-dev@lists.sourceforge.net
-S:	Supported
-W:	http://www.tuxera.com/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/aia21/ntfs.git
-F:	Documentation/filesystems/ntfs.rst
-F:	fs/ntfs/
-
 NTFS3 FILESYSTEM
 M:	Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
 L:	ntfs3@lists.linux.dev
@@ -15598,7 +15717,7 @@ F:	drivers/iio/gyro/fxas21002c_spi.c
 NXP i.MX 7D/6SX/6UL/93 AND VF610 ADC DRIVER
 M:	Haibo Chen <haibo.chen@nxp.com>
 L:	linux-iio@vger.kernel.org
-L:	linux-imx@nxp.com
+L:	imx@lists.linux.dev
 S:	Maintained
 F:	Documentation/devicetree/bindings/iio/adc/fsl,imx7d-adc.yaml
 F:	Documentation/devicetree/bindings/iio/adc/fsl,vf610-adc.yaml
@@ -15635,7 +15754,7 @@ F:	drivers/gpu/drm/imx/dcss/
 NXP i.MX 8QXP ADC DRIVER
 M:	Cai Huoqing <cai.huoqing@linux.dev>
 M:	Haibo Chen <haibo.chen@nxp.com>
-L:	linux-imx@nxp.com
+L:	imx@lists.linux.dev
 L:	linux-iio@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/iio/adc/nxp,imx8qxp-adc.yaml
@@ -15643,7 +15762,7 @@ F:	drivers/iio/adc/imx8qxp-adc.c
 
 NXP i.MX 8QXP/8QM JPEG V4L2 DRIVER
 M:	Mirela Rabulea <mirela.rabulea@nxp.com>
-R:	NXP Linux Team <linux-imx@nxp.com>
+L:	imx@lists.linux.dev
 L:	linux-media@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/media/nxp,imx8-jpeg.yaml
@@ -15653,7 +15772,7 @@ NXP i.MX CLOCK DRIVERS
 M:	Abel Vesa <abelvesa@kernel.org>
 R:	Peng Fan <peng.fan@nxp.com>
 L:	linux-clk@vger.kernel.org
-L:	linux-imx@nxp.com
+L:	imx@lists.linux.dev
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/abelvesa/linux.git clk/imx
 F:	Documentation/devicetree/bindings/clock/imx*
@@ -16614,6 +16733,7 @@ F:	drivers/pci/controller/dwc/*layerscape*
 PCI DRIVER FOR FU740
 M:	Paul Walmsley <paul.walmsley@sifive.com>
 M:	Greentime Hu <greentime.hu@sifive.com>
+M:	Samuel Holland <samuel.holland@sifive.com>
 L:	linux-pci@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/pci/sifive,fu740-pcie.yaml
@@ -16726,6 +16846,7 @@ F:	drivers/pci/controller/dwc/*designware*
 
 PCI DRIVER FOR TI DRA7XX/J721E
 M:	Vignesh Raghavendra <vigneshr@ti.com>
+R:	Siddharth Vadapalli <s-vadapalli@ti.com>
 L:	linux-omap@vger.kernel.org
 L:	linux-pci@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -16750,9 +16871,8 @@ F:	Documentation/devicetree/bindings/pci/xilinx-versal-cpm.yaml
 F:	drivers/pci/controller/pcie-xilinx-cpm.c
 
 PCI ENDPOINT SUBSYSTEM
-M:	Lorenzo Pieralisi <lpieralisi@kernel.org>
+M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
 M:	Krzysztof Wilczyński <kw@linux.com>
-R:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
 R:	Kishon Vijay Abraham I <kishon@kernel.org>
 L:	linux-pci@vger.kernel.org
 S:	Supported
@@ -17041,10 +17161,10 @@ PERFORMANCE EVENTS SUBSYSTEM
 M:	Peter Zijlstra <peterz@infradead.org>
 M:	Ingo Molnar <mingo@redhat.com>
 M:	Arnaldo Carvalho de Melo <acme@kernel.org>
+M:	Namhyung Kim <namhyung@kernel.org>
 R:	Mark Rutland <mark.rutland@arm.com>
 R:	Alexander Shishkin <alexander.shishkin@linux.intel.com>
 R:	Jiri Olsa <jolsa@kernel.org>
-R:	Namhyung Kim <namhyung@kernel.org>
 R:	Ian Rogers <irogers@google.com>
 R:	Adrian Hunter <adrian.hunter@intel.com>
 L:	linux-perf-users@vger.kernel.org
@@ -17072,7 +17192,7 @@ R:	John Garry <john.g.garry@oracle.com>
 R:	Will Deacon <will@kernel.org>
 R:	James Clark <james.clark@arm.com>
 R:	Mike Leach <mike.leach@linaro.org>
-R:	Leo Yan <leo.yan@linaro.org>
+R:	Leo Yan <leo.yan@linux.dev>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
 F:	tools/build/feature/test-libopencsd.c
@@ -17419,6 +17539,7 @@ F:	Documentation/devicetree/bindings/power/supply/
 F:	drivers/power/supply/
 F:	include/linux/power/
 F:	include/linux/power_supply.h
+F:	tools/testing/selftests/power_supply/
 
 POWERNV OPERATOR PANEL LCD DISPLAY DRIVER
 M:	Suraj Jitindar Singh <sjitindarsingh@gmail.com>
@@ -17866,33 +17987,34 @@ F:	drivers/media/tuners/qt1010*
 
 QUALCOMM ATH12K WIRELESS DRIVER
 M:	Kalle Valo <kvalo@kernel.org>
-M:	Jeff Johnson <quic_jjohnson@quicinc.com>
+M:	Jeff Johnson <jjohnson@kernel.org>
 L:	ath12k@lists.infradead.org
 S:	Supported
 W:	https://wireless.wiki.kernel.org/en/users/Drivers/ath12k
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git
 F:	drivers/net/wireless/ath/ath12k/
+N:	ath12k
 
 QUALCOMM ATHEROS ATH10K WIRELESS DRIVER
 M:	Kalle Valo <kvalo@kernel.org>
-M:	Jeff Johnson <quic_jjohnson@quicinc.com>
+M:	Jeff Johnson <jjohnson@kernel.org>
 L:	ath10k@lists.infradead.org
 S:	Supported
 W:	https://wireless.wiki.kernel.org/en/users/Drivers/ath10k
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git
-F:	Documentation/devicetree/bindings/net/wireless/qcom,ath10k.yaml
 F:	drivers/net/wireless/ath/ath10k/
+N:	ath10k
 
 QUALCOMM ATHEROS ATH11K WIRELESS DRIVER
 M:	Kalle Valo <kvalo@kernel.org>
-M:	Jeff Johnson <quic_jjohnson@quicinc.com>
+M:	Jeff Johnson <jjohnson@kernel.org>
 L:	ath11k@lists.infradead.org
 S:	Supported
 W:	https://wireless.wiki.kernel.org/en/users/Drivers/ath11k
 B:	https://wireless.wiki.kernel.org/en/users/Drivers/ath11k/bugreport
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git
-F:	Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml
 F:	drivers/net/wireless/ath/ath11k/
+N:	ath11k
 
 QUALCOMM ATHEROS ATH9K WIRELESS DRIVER
 M:	Toke Høiland-Jørgensen <toke@toke.dk>
@@ -17975,7 +18097,6 @@ F:	drivers/net/ethernet/qualcomm/emac/
 
 QUALCOMM ETHQOS ETHERNET DRIVER
 M:	Vinod Koul <vkoul@kernel.org>
-R:	Bhupesh Sharma <bhupesh.sharma@linaro.org>
 L:	netdev@vger.kernel.org
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained
@@ -18197,6 +18318,7 @@ F:	drivers/media/cec/usb/rainshadow/
 
 RALINK MIPS ARCHITECTURE
 M:	John Crispin <john@phrozen.org>
+M:	Sergio Paracuellos <sergio.paracuellos@gmail.com>
 L:	linux-mips@vger.kernel.org
 S:	Maintained
 F:	arch/mips/ralink
@@ -18321,7 +18443,7 @@ S:	Supported
 F:	drivers/infiniband/sw/rdmavt
 
 RDS - RELIABLE DATAGRAM SOCKETS
-M:	Santosh Shilimkar <santosh.shilimkar@oracle.com>
+M:	Allison Henderson <allison.henderson@oracle.com>
 L:	netdev@vger.kernel.org
 L:	linux-rdma@vger.kernel.org
 L:	rds-devel@oss.oracle.com (moderated for non-subscribers)
@@ -18363,7 +18485,6 @@ X:	include/linux/srcu*.h
 X:	kernel/rcu/srcu*.c
 
 REAL TIME CLOCK (RTC) SUBSYSTEM
-M:	Alessandro Zummo <a.zummo@towertech.it>
 M:	Alexandre Belloni <alexandre.belloni@bootlin.com>
 L:	linux-rtc@vger.kernel.org
 S:	Maintained
@@ -18989,6 +19110,7 @@ F:	Documentation/rust/
 F:	rust/
 F:	samples/rust/
 F:	scripts/*rust*
+F:	tools/testing/selftests/rust/
 K:	\b(?i:rust)\b
 
 RXRPC SOCKETS (AF_RXRPC)
@@ -19051,7 +19173,7 @@ F:	drivers/iommu/s390-iommu.c
 
 S390 IUCV NETWORK LAYER
 M:	Alexandra Winter <wintera@linux.ibm.com>
-M:	Wenjia Zhang <wenjia@linux.ibm.com>
+M:	Thorsten Winkler <twinkler@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Supported
@@ -19070,7 +19192,7 @@ F:	arch/s390/mm
 
 S390 NETWORK DRIVERS
 M:	Alexandra Winter <wintera@linux.ibm.com>
-M:	Wenjia Zhang <wenjia@linux.ibm.com>
+M:	Thorsten Winkler <twinkler@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Supported
@@ -19288,7 +19410,6 @@ R:	Alim Akhtar <alim.akhtar@samsung.com>
 L:	linux-samsung-soc@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/krzk/linux.git
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/snawrocki/clk.git
 F:	Documentation/devicetree/bindings/clock/samsung,*.yaml
 F:	Documentation/devicetree/bindings/clock/samsung,s3c*
 F:	drivers/clk/samsung/
@@ -19525,7 +19646,7 @@ F:	drivers/mmc/host/sdhci-of-at91.c
 
 SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) NXP i.MX DRIVER
 M:	Haibo Chen <haibo.chen@nxp.com>
-L:	linux-imx@nxp.com
+L:	imx@lists.linux.dev
 L:	linux-mmc@vger.kernel.org
 S:	Maintained
 F:	drivers/mmc/host/sdhci-esdhc-imx.c
@@ -19738,6 +19859,19 @@ T:	git git://linuxtv.org/media_tree.git
 F:	drivers/media/i2c/rj54n1cb0c.c
 F:	include/media/i2c/rj54n1cb0c.h
 
+SHRINKER
+M:	Andrew Morton <akpm@linux-foundation.org>
+M:	Dave Chinner <david@fromorbit.com>
+R:	Qi Zheng <zhengqi.arch@bytedance.com>
+R:	Roman Gushchin <roman.gushchin@linux.dev>
+R:	Muchun Song <muchun.song@linux.dev>
+L:	linux-mm@kvack.org
+S:	Maintained
+F:	Documentation/admin-guide/mm/shrinker_debugfs.rst
+F:	include/linux/shrinker.h
+F:	mm/shrinker.c
+F:	mm/shrinker_debug.c
+
 SH_VOU V4L2 OUTPUT DRIVER
 L:	linux-media@vger.kernel.org
 S:	Orphan
@@ -19847,36 +19981,15 @@ S:	Maintained
 F:	drivers/watchdog/simatic-ipc-wdt.c
 
 SIFIVE DRIVERS
-M:	Palmer Dabbelt <palmer@dabbelt.com>
 M:	Paul Walmsley <paul.walmsley@sifive.com>
+M:	Samuel Holland <samuel.holland@sifive.com>
 L:	linux-riscv@lists.infradead.org
 S:	Supported
+F:	drivers/dma/sf-pdma/
 N:	sifive
+K:	fu[57]40
 K:	[^@]sifive
 
-SIFIVE CACHE DRIVER
-M:	Conor Dooley <conor@kernel.org>
-L:	linux-riscv@lists.infradead.org
-S:	Maintained
-F:	Documentation/devicetree/bindings/cache/sifive,ccache0.yaml
-F:	drivers/cache/sifive_ccache.c
-
-SIFIVE FU540 SYSTEM-ON-CHIP
-M:	Paul Walmsley <paul.walmsley@sifive.com>
-M:	Palmer Dabbelt <palmer@dabbelt.com>
-L:	linux-riscv@lists.infradead.org
-S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pjw/sifive.git
-N:	fu540
-K:	fu540
-
-SIFIVE PDMA DRIVER
-M:	Green Wan <green.wan@sifive.com>
-S:	Maintained
-F:	Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml
-F:	drivers/dma/sf-pdma/
-
-
 SILEAD TOUCHSCREEN DRIVER
 M:	Hans de Goede <hdegoede@redhat.com>
 L:	linux-input@vger.kernel.org
@@ -20085,8 +20198,8 @@ F:	Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml
 F:	drivers/net/ethernet/socionext/sni_ave.c
 
 SOCIONEXT (SNI) NETSEC NETWORK DRIVER
-M:	Jassi Brar <jaswinder.singh@linaro.org>
 M:	Ilias Apalodimas <ilias.apalodimas@linaro.org>
+M:	Masahisa Kojima <kojima.masahisa@socionext.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/socionext,synquacer-netsec.yaml
@@ -20431,6 +20544,7 @@ F:	Documentation/translations/sp_SP/
 
 SPARC + UltraSPARC (sparc/sparc64)
 M:	"David S. Miller" <davem@davemloft.net>
+M:	Andreas Larsson <andreas@gaisler.com>
 L:	sparclinux@vger.kernel.org
 S:	Maintained
 Q:	http://patchwork.ozlabs.org/project/sparclinux/list/
@@ -21887,6 +22001,14 @@ F:	Documentation/devicetree/bindings/media/i2c/ti,ds90*
 F:	drivers/media/i2c/ds90*
 F:	include/media/i2c/ds90*
 
+TI HDC302X HUMIDITY DRIVER
+M:	Javier Carrasco <javier.carrasco.cruz@gmail.com>
+M:	Li peiyu <579lpy@gmail.com>
+L:	linux-iio@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/iio/humidity/ti,hdc3020.yaml
+F:	drivers/iio/humidity/hdc3020.c
+
 TI ICSSG ETHERNET DRIVER (ICSSG)
 R:	MD Danish Anwar <danishanwar@ti.com>
 R:	Roger Quadros <rogerq@kernel.org>
@@ -22742,9 +22864,8 @@ S:	Maintained
 F:	drivers/usb/typec/mux/pi3usb30532.c
 
 USB TYPEC PORT CONTROLLER DRIVERS
-M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-usb@vger.kernel.org
-S:	Maintained
+S:	Orphan
 F:	drivers/usb/typec/tcpm/
 
 USB UHCI DRIVER
@@ -22917,6 +23038,7 @@ M:	Alex Williamson <alex.williamson@redhat.com>
 L:	kvm@vger.kernel.org
 S:	Maintained
 T:	git https://github.com/awilliam/linux-vfio.git
+F:	Documentation/ABI/testing/debugfs-vfio
 F:	Documentation/ABI/testing/sysfs-devices-vfio-dev
 F:	Documentation/driver-api/vfio.rst
 F:	drivers/vfio/
@@ -22952,6 +23074,13 @@ L:	kvm@vger.kernel.org
 S:	Maintained
 F:	drivers/vfio/pci/mlx5/
 
+VFIO VIRTIO PCI DRIVER
+M:	Yishai Hadas <yishaih@nvidia.com>
+L:	kvm@vger.kernel.org
+L:	virtualization@lists.linux-foundation.org
+S:	Maintained
+F:	drivers/vfio/pci/virtio
+
 VFIO PCI DEVICE SPECIFIC DRIVERS
 R:	Jason Gunthorpe <jgg@nvidia.com>
 R:	Yishai Hadas <yishaih@nvidia.com>
@@ -23100,7 +23229,6 @@ M:	Amit Shah <amit@kernel.org>
 L:	virtualization@lists.linux.dev
 S:	Maintained
 F:	drivers/char/virtio_console.c
-F:	include/linux/virtio_console.h
 F:	include/uapi/linux/virtio_console.h
 
 VIRTIO CORE AND NET DRIVERS
@@ -23276,6 +23404,12 @@ S:	Maintained
 F:	drivers/input/serio/userio.c
 F:	include/uapi/linux/userio.h
 
+VISHAY VEML6075 UVA AND UVB LIGHT SENSOR DRIVER
+M:	Javier Carrasco <javier.carrasco.cruz@gmail.com>
+S:	Maintained
+F:	Documentation/devicetree/bindings/iio/light/vishay,veml6075.yaml
+F:	drivers/iio/light/veml6075.c
+
 VISL VIRTUAL STATELESS DECODER DRIVER
 M:	Daniel Almeida <daniel.almeida@collabora.com>
 L:	linux-media@vger.kernel.org
@@ -23316,11 +23450,8 @@ F:	include/linux/vmalloc.h
 F:	mm/vmalloc.c
 
 VME SUBSYSTEM
-M:	Martyn Welch <martyn@welchs.me.uk>
-M:	Manohar Vanga <manohar.vanga@gmail.com>
-M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 L:	linux-kernel@vger.kernel.org
-S:	Odd fixes
+S:	Orphan
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git
 F:	Documentation/driver-api/vme.rst
 F:	drivers/staging/vme_user/
@@ -24211,13 +24342,6 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/zonefs.git
 F:	Documentation/filesystems/zonefs.rst
 F:	fs/zonefs/
 
-ZPOOL COMPRESSED PAGE STORAGE API
-M:	Dan Streetman <ddstreet@ieee.org>
-L:	linux-mm@kvack.org
-S:	Maintained
-F:	include/linux/zpool.h
-F:	mm/zpool.c
-
 ZR36067 VIDEO FOR LINUX DRIVER
 M:	Corentin Labbe <clabbe@baylibre.com>
 L:	mjpeg-users@lists.sourceforge.net
@@ -24263,11 +24387,15 @@ N:	zstd
 K:	zstd
 
 ZSWAP COMPRESSED SWAP CACHING
-M:	Seth Jennings <sjenning@redhat.com>
-M:	Dan Streetman <ddstreet@ieee.org>
-M:	Vitaly Wool <vitaly.wool@konsulko.com>
+M:	Johannes Weiner <hannes@cmpxchg.org>
+M:	Yosry Ahmed <yosryahmed@google.com>
+M:	Nhat Pham <nphamcs@gmail.com>
 L:	linux-mm@kvack.org
 S:	Maintained
+F:	Documentation/admin-guide/mm/zswap.rst
+F:	include/linux/zpool.h
+F:	include/linux/zswap.h
+F:	mm/zpool.c
 F:	mm/zswap.c
 
 THE REST
diff --git a/Makefile b/Makefile
index f1b2fd977275..d18fa2a6240d 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
-PATCHLEVEL = 7
+PATCHLEVEL = 8
 SUBLEVEL = 0
 EXTRAVERSION =
 NAME = Hurr durr I'ma ninja sloth
@@ -155,6 +155,15 @@ endif
 
 export KBUILD_EXTMOD
 
+# backward compatibility
+KBUILD_EXTRA_WARN ?= $(KBUILD_ENABLE_EXTRA_GCC_CHECKS)
+
+ifeq ("$(origin W)", "command line")
+  KBUILD_EXTRA_WARN := $(W)
+endif
+
+export KBUILD_EXTRA_WARN
+
 # Kbuild will save output files in the current working directory.
 # This does not need to match to the root of the kernel source tree.
 #
@@ -181,14 +190,11 @@ ifeq ("$(origin O)", "command line")
 endif
 
 ifneq ($(KBUILD_OUTPUT),)
-# Make's built-in functions such as $(abspath ...), $(realpath ...) cannot
-# expand a shell special character '~'. We use a somewhat tedious way here.
-abs_objtree := $(shell mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) && pwd)
-$(if $(abs_objtree),, \
-     $(error failed to create output directory "$(KBUILD_OUTPUT)"))
-
+# $(realpath ...) gets empty if the path does not exist. Run 'mkdir -p' first.
+$(shell mkdir -p "$(KBUILD_OUTPUT)")
 # $(realpath ...) resolves symlinks
-abs_objtree := $(realpath $(abs_objtree))
+abs_objtree := $(realpath $(KBUILD_OUTPUT))
+$(if $(abs_objtree),,$(error failed to create output directory "$(KBUILD_OUTPUT)"))
 endif # ifneq ($(KBUILD_OUTPUT),)
 
 ifneq ($(words $(subst :, ,$(abs_srctree))), 1)
@@ -288,15 +294,15 @@ may-sync-config	:= 1
 single-build	:=
 
 ifneq ($(filter $(no-dot-config-targets), $(MAKECMDGOALS)),)
-	ifeq ($(filter-out $(no-dot-config-targets), $(MAKECMDGOALS)),)
+    ifeq ($(filter-out $(no-dot-config-targets), $(MAKECMDGOALS)),)
 		need-config :=
-	endif
+    endif
 endif
 
 ifneq ($(filter $(no-sync-config-targets), $(MAKECMDGOALS)),)
-	ifeq ($(filter-out $(no-sync-config-targets), $(MAKECMDGOALS)),)
+    ifeq ($(filter-out $(no-sync-config-targets), $(MAKECMDGOALS)),)
 		may-sync-config :=
-	endif
+    endif
 endif
 
 need-compiler := $(may-sync-config)
@@ -317,9 +323,9 @@ endif
 # We cannot build single targets and the others at the same time
 ifneq ($(filter $(single-targets), $(MAKECMDGOALS)),)
 	single-build := 1
-	ifneq ($(filter-out $(single-targets), $(MAKECMDGOALS)),)
+    ifneq ($(filter-out $(single-targets), $(MAKECMDGOALS)),)
 		mixed-build := 1
-	endif
+    endif
 endif
 
 # For "make -j clean all", "make -j mrproper defconfig all", etc.
@@ -609,8 +615,6 @@ export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL KBUILD_RUSTFLAGS_KERNEL
 export RCS_FIND_IGNORE := \( -name SCCS -o -name BitKeeper -o -name .svn -o    \
 			  -name CVS -o -name .pc -o -name .hg -o -name .git \) \
 			  -prune -o
-export RCS_TAR_IGNORE := --exclude SCCS --exclude BitKeeper --exclude .svn \
-			 --exclude CVS --exclude .pc --exclude .hg --exclude .git
 
 # ===========================================================================
 # Rules shared between *config targets and build targets
@@ -982,6 +986,10 @@ NOSTDINC_FLAGS += -nostdinc
 # perform bounds checking.
 KBUILD_CFLAGS += $(call cc-option, -fstrict-flex-arrays=3)
 
+#Currently, disable -Wstringop-overflow for GCC 11, globally.
+KBUILD_CFLAGS-$(CONFIG_CC_NO_STRINGOP_OVERFLOW) += $(call cc-option, -Wno-stringop-overflow)
+KBUILD_CFLAGS-$(CONFIG_CC_STRINGOP_OVERFLOW) += $(call cc-option, -Wstringop-overflow)
+
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= -fno-strict-overflow
 
@@ -1193,7 +1201,7 @@ prepare0: archprepare
 # All the preparing..
 prepare: prepare0
 ifdef CONFIG_RUST
-	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh
+	+$(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh
 	$(Q)$(MAKE) $(build)=rust
 endif
 
@@ -1658,10 +1666,11 @@ help:
 	@echo  '                       (sparse by default)'
 	@echo  '  make C=2   [targets] Force check of all c source with $$CHECK'
 	@echo  '  make RECORDMCOUNT_WARN=1 [targets] Warn about ignored mcount sections'
-	@echo  '  make W=n   [targets] Enable extra build checks, n=1,2,3 where'
+	@echo  '  make W=n   [targets] Enable extra build checks, n=1,2,3,c,e where'
 	@echo  '		1: warnings which may be relevant and do not occur too often'
 	@echo  '		2: warnings which occur quite often but may still be relevant'
 	@echo  '		3: more obscure warnings, can most likely be ignored'
+	@echo  '		c: extra checks in the configuration stage (Kconfig)'
 	@echo  '		e: warnings are being treated as errors'
 	@echo  '		Multiple levels can be combined with W=12 or W=123'
 	@$(if $(dtstree), \
@@ -1702,7 +1711,7 @@ $(DOC_TARGETS):
 # "Is Rust available?" target
 PHONY += rustavailable
 rustavailable:
-	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh && echo "Rust is available!"
+	+$(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh && echo "Rust is available!"
 
 # Documentation target
 #
diff --git a/arch/Kconfig b/arch/Kconfig
index 5ca66aad0d08..a5af0edd3eb8 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -301,6 +301,11 @@ config ARCH_HAS_DMA_CLEAR_UNCACHED
 config ARCH_HAS_CPU_FINALIZE_INIT
 	bool
 
+# The architecture has a per-task state that includes the mm's PASID
+config ARCH_HAS_CPU_PASID
+	bool
+	select IOMMU_MM_DATA
+
 config HAVE_ARCH_THREAD_STRUCT_WHITELIST
 	bool
 	help
@@ -668,6 +673,7 @@ config SHADOW_CALL_STACK
 	bool "Shadow Call Stack"
 	depends on ARCH_SUPPORTS_SHADOW_CALL_STACK
 	depends on DYNAMIC_FTRACE_WITH_ARGS || DYNAMIC_FTRACE_WITH_REGS || !FUNCTION_GRAPH_TRACER
+	depends on MMU
 	help
 	  This option enables the compiler's Shadow Call Stack, which
 	  uses a shadow stack to protect function return addresses from
diff --git a/arch/alpha/kernel/rtc.c b/arch/alpha/kernel/rtc.c
index fb3025396ac9..cfdf90bc8b3f 100644
--- a/arch/alpha/kernel/rtc.c
+++ b/arch/alpha/kernel/rtc.c
@@ -80,7 +80,7 @@ init_rtc_epoch(void)
 static int
 alpha_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
-	int ret = mc146818_get_time(tm);
+	int ret = mc146818_get_time(tm, 10);
 
 	if (ret < 0) {
 		dev_err_ratelimited(dev, "unable to read current time\n");
diff --git a/arch/alpha/kernel/srmcons.c b/arch/alpha/kernel/srmcons.c
index d6139dbae4ac..feaf89f6936b 100644
--- a/arch/alpha/kernel/srmcons.c
+++ b/arch/alpha/kernel/srmcons.c
@@ -53,7 +53,7 @@ srmcons_do_receive_chars(struct tty_port *port)
 	do {
 		result.as_long = callback_getc(0);
 		if (result.bits.status < 2) {
-			tty_insert_flip_char(port, (char)result.bits.c, 0);
+			tty_insert_flip_char(port, (u8)result.bits.c, 0);
 			count++;
 		}
 	} while((result.bits.status & 1) && (++loops < 10));
@@ -88,30 +88,27 @@ srmcons_receive_chars(struct timer_list *t)
 }
 
 /* called with callback_lock held */
-static int
-srmcons_do_write(struct tty_port *port, const char *buf, int count)
+static void
+srmcons_do_write(struct tty_port *port, const u8 *buf, size_t count)
 {
-	static char str_cr[1] = "\r";
-	long c, remaining = count;
+	size_t c;
 	srmcons_result result;
-	char *cur;
-	int need_cr;
 
-	for (cur = (char *)buf; remaining > 0; ) {
-		need_cr = 0;
+	while (count > 0) {
+		bool need_cr = false;
 		/* 
 		 * Break it up into reasonable size chunks to allow a chance
 		 * for input to get in
 		 */
-		for (c = 0; c < min_t(long, 128L, remaining) && !need_cr; c++)
-			if (cur[c] == '\n')
-				need_cr = 1;
+		for (c = 0; c < min_t(size_t, 128U, count) && !need_cr; c++)
+			if (buf[c] == '\n')
+				need_cr = true;
 		
 		while (c > 0) {
-			result.as_long = callback_puts(0, cur, c);
+			result.as_long = callback_puts(0, buf, c);
 			c -= result.bits.c;
-			remaining -= result.bits.c;
-			cur += result.bits.c;
+			count -= result.bits.c;
+			buf += result.bits.c;
 
 			/*
 			 * Check for pending input iff a tty port was provided
@@ -121,12 +118,11 @@ srmcons_do_write(struct tty_port *port, const char *buf, int count)
 		}
 
 		while (need_cr) {
-			result.as_long = callback_puts(0, str_cr, 1);
+			result.as_long = callback_puts(0, "\r", 1);
 			if (result.bits.c > 0)
-				need_cr = 0;
+				need_cr = false;
 		}
 	}
-	return count;
 }
 
 static ssize_t
@@ -135,7 +131,7 @@ srmcons_write(struct tty_struct *tty, const u8 *buf, size_t count)
 	unsigned long flags;
 
 	spin_lock_irqsave(&srmcons_callback_lock, flags);
-	srmcons_do_write(tty->port, (const char *) buf, count);
+	srmcons_do_write(tty->port, buf, count);
 	spin_unlock_irqrestore(&srmcons_callback_lock, flags);
 
 	return count;
diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h
index 563af3e75f01..329c94cd45d8 100644
--- a/arch/arc/include/asm/cacheflush.h
+++ b/arch/arc/include/asm/cacheflush.h
@@ -40,6 +40,7 @@ void dma_cache_wback(phys_addr_t start, unsigned long sz);
 
 /* TBD: optimize this */
 #define flush_cache_vmap(start, end)		flush_cache_all()
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		flush_cache_all()
 
 #define flush_cache_dup_mm(mm)			/* called on fork (VIVT only) */
diff --git a/arch/arc/include/asm/jump_label.h b/arch/arc/include/asm/jump_label.h
index 9d9618079739..a339223d9e05 100644
--- a/arch/arc/include/asm/jump_label.h
+++ b/arch/arc/include/asm/jump_label.h
@@ -31,7 +31,7 @@
 static __always_inline bool arch_static_branch(struct static_key *key,
 					       bool branch)
 {
-	asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)"	\n"
+	asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)"		\n"
 		 "1:							\n"
 		 "nop							\n"
 		 ".pushsection __jump_table, \"aw\"			\n"
@@ -47,7 +47,7 @@ l_yes:
 static __always_inline bool arch_static_branch_jump(struct static_key *key,
 						    bool branch)
 {
-	asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)"	\n"
+	asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)"		\n"
 		 "1:							\n"
 		 "b %l[l_yes]						\n"
 		 ".pushsection __jump_table, \"aw\"			\n"
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 2a7fbbb83b70..197707bc7658 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -91,7 +91,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
  * Plug in direct dma map ops.
  */
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	/*
 	 * IOC hardware snoops all DMA traffic keeping the caches consistent
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index b67d05468251..0af6709570d1 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -35,6 +35,7 @@ config ARM
 	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT if CPU_V7
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_HUGETLBFS if ARM_LPAE
+	select ARCH_SUPPORTS_PER_VMA_LOCK
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_MEMTEST
diff --git a/arch/arm/boot/dts/amazon/alpine.dtsi b/arch/arm/boot/dts/amazon/alpine.dtsi
index ff68dfb4eb78..90bd12feac01 100644
--- a/arch/arm/boot/dts/amazon/alpine.dtsi
+++ b/arch/arm/boot/dts/amazon/alpine.dtsi
@@ -167,7 +167,6 @@
 		msix: msix@fbe00000 {
 			compatible = "al,alpine-msix";
 			reg = <0x0 0xfbe00000 0x0 0x100000>;
-			interrupt-controller;
 			msi-controller;
 			al,msi-base-spi = <96>;
 			al,msi-num-spis = <64>;
diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-bletchley.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-bletchley.dts
index e899de681f47..5be0e8fd2633 100644
--- a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-bletchley.dts
+++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-bletchley.dts
@@ -45,8 +45,8 @@
 		num-chipselects = <1>;
 		cs-gpios = <&gpio0 ASPEED_GPIO(Z, 0) GPIO_ACTIVE_LOW>;
 
-		tpmdev@0 {
-			compatible = "tcg,tpm_tis-spi";
+		tpm@0 {
+			compatible = "infineon,slb9670", "tcg,tpm_tis-spi";
 			spi-max-frequency = <33000000>;
 			reg = <0>;
 		};
diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-wedge400.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-wedge400.dts
index a677c827e758..5a8169bbda87 100644
--- a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-wedge400.dts
+++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-wedge400.dts
@@ -80,8 +80,8 @@
 		gpio-miso = <&gpio ASPEED_GPIO(R, 5) GPIO_ACTIVE_HIGH>;
 		num-chipselects = <1>;
 
-		tpmdev@0 {
-			compatible = "tcg,tpm_tis-spi";
+		tpm@0 {
+			compatible = "infineon,slb9670", "tcg,tpm_tis-spi";
 			spi-max-frequency = <33000000>;
 			reg = <0>;
 		};
diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-opp-tacoma.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-opp-tacoma.dts
index 3f6010ef2b86..213023bc5aec 100644
--- a/arch/arm/boot/dts/aspeed/aspeed-bmc-opp-tacoma.dts
+++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-opp-tacoma.dts
@@ -456,7 +456,7 @@
 	status = "okay";
 
 	tpm: tpm@2e {
-		compatible = "tcg,tpm-tis-i2c";
+		compatible = "nuvoton,npct75x", "tcg,tpm-tis-i2c";
 		reg = <0x2e>;
 	};
 };
diff --git a/arch/arm/boot/dts/aspeed/aspeed-g4.dtsi b/arch/arm/boot/dts/aspeed/aspeed-g4.dtsi
index 530491ae5eb2..857cb26ed6d7 100644
--- a/arch/arm/boot/dts/aspeed/aspeed-g4.dtsi
+++ b/arch/arm/boot/dts/aspeed/aspeed-g4.dtsi
@@ -466,7 +466,6 @@
 	i2c0: i2c-bus@40 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x40 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -482,7 +481,6 @@
 	i2c1: i2c-bus@80 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x80 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -498,7 +496,6 @@
 	i2c2: i2c-bus@c0 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0xc0 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -515,7 +512,6 @@
 	i2c3: i2c-bus@100 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x100 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -532,7 +528,6 @@
 	i2c4: i2c-bus@140 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x140 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -549,7 +544,6 @@
 	i2c5: i2c-bus@180 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x180 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -566,7 +560,6 @@
 	i2c6: i2c-bus@1c0 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x1c0 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -583,7 +576,6 @@
 	i2c7: i2c-bus@300 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x300 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -600,7 +592,6 @@
 	i2c8: i2c-bus@340 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x340 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -617,7 +608,6 @@
 	i2c9: i2c-bus@380 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x380 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -634,7 +624,6 @@
 	i2c10: i2c-bus@3c0 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x3c0 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -651,7 +640,6 @@
 	i2c11: i2c-bus@400 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x400 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -668,7 +656,6 @@
 	i2c12: i2c-bus@440 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x440 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -685,7 +672,6 @@
 	i2c13: i2c-bus@480 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x480 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
diff --git a/arch/arm/boot/dts/aspeed/aspeed-g5.dtsi b/arch/arm/boot/dts/aspeed/aspeed-g5.dtsi
index 04f98d1dbb97..e6f3cf3c721e 100644
--- a/arch/arm/boot/dts/aspeed/aspeed-g5.dtsi
+++ b/arch/arm/boot/dts/aspeed/aspeed-g5.dtsi
@@ -363,6 +363,7 @@
 				interrupts = <40>;
 				reg = <0x1e780200 0x0100>;
 				clocks = <&syscon ASPEED_CLK_APB>;
+				#interrupt-cells = <2>;
 				interrupt-controller;
 				bus-frequency = <12000000>;
 				pinctrl-names = "default";
@@ -594,7 +595,6 @@
 	i2c0: i2c-bus@40 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x40 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -610,7 +610,6 @@
 	i2c1: i2c-bus@80 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x80 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -626,7 +625,6 @@
 	i2c2: i2c-bus@c0 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0xc0 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -643,7 +641,6 @@
 	i2c3: i2c-bus@100 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x100 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -660,7 +657,6 @@
 	i2c4: i2c-bus@140 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x140 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -677,7 +673,6 @@
 	i2c5: i2c-bus@180 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x180 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -694,7 +689,6 @@
 	i2c6: i2c-bus@1c0 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x1c0 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -711,7 +705,6 @@
 	i2c7: i2c-bus@300 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x300 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -728,7 +721,6 @@
 	i2c8: i2c-bus@340 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x340 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -745,7 +737,6 @@
 	i2c9: i2c-bus@380 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x380 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -762,7 +753,6 @@
 	i2c10: i2c-bus@3c0 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x3c0 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -779,7 +769,6 @@
 	i2c11: i2c-bus@400 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x400 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -796,7 +785,6 @@
 	i2c12: i2c-bus@440 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x440 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -813,7 +801,6 @@
 	i2c13: i2c-bus@480 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x480 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
diff --git a/arch/arm/boot/dts/aspeed/aspeed-g6.dtsi b/arch/arm/boot/dts/aspeed/aspeed-g6.dtsi
index c4d1faade8be..29f94696d8b1 100644
--- a/arch/arm/boot/dts/aspeed/aspeed-g6.dtsi
+++ b/arch/arm/boot/dts/aspeed/aspeed-g6.dtsi
@@ -474,6 +474,7 @@
 				reg = <0x1e780500 0x100>;
 				interrupts = <GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&syscon ASPEED_CLK_APB2>;
+				#interrupt-cells = <2>;
 				interrupt-controller;
 				bus-frequency = <12000000>;
 				pinctrl-names = "default";
@@ -488,6 +489,7 @@
 				reg = <0x1e780600 0x100>;
 				interrupts = <GIC_SPI 70 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&syscon ASPEED_CLK_APB2>;
+				#interrupt-cells = <2>;
 				interrupt-controller;
 				bus-frequency = <12000000>;
 				pinctrl-names = "default";
@@ -902,7 +904,6 @@
 	i2c0: i2c-bus@80 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x80 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -917,7 +918,6 @@
 	i2c1: i2c-bus@100 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x100 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -932,7 +932,6 @@
 	i2c2: i2c-bus@180 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x180 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -947,7 +946,6 @@
 	i2c3: i2c-bus@200 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x200 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -962,7 +960,6 @@
 	i2c4: i2c-bus@280 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x280 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -977,7 +974,6 @@
 	i2c5: i2c-bus@300 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x300 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -992,7 +988,6 @@
 	i2c6: i2c-bus@380 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x380 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -1007,7 +1002,6 @@
 	i2c7: i2c-bus@400 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x400 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -1022,7 +1016,6 @@
 	i2c8: i2c-bus@480 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x480 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -1037,7 +1030,6 @@
 	i2c9: i2c-bus@500 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x500 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -1052,7 +1044,6 @@
 	i2c10: i2c-bus@580 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x580 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -1067,7 +1058,6 @@
 	i2c11: i2c-bus@600 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x600 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -1082,7 +1072,6 @@
 	i2c12: i2c-bus@680 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x680 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -1097,7 +1086,6 @@
 	i2c13: i2c-bus@700 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x700 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -1112,7 +1100,6 @@
 	i2c14: i2c-bus@780 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x780 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -1127,7 +1114,6 @@
 	i2c15: i2c-bus@800 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x800 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
diff --git a/arch/arm/boot/dts/aspeed/ast2600-facebook-netbmc-common.dtsi b/arch/arm/boot/dts/aspeed/ast2600-facebook-netbmc-common.dtsi
index 31590d3186a2..00e5887c926f 100644
--- a/arch/arm/boot/dts/aspeed/ast2600-facebook-netbmc-common.dtsi
+++ b/arch/arm/boot/dts/aspeed/ast2600-facebook-netbmc-common.dtsi
@@ -35,8 +35,8 @@
 		gpio-mosi = <&gpio0 ASPEED_GPIO(X, 4) GPIO_ACTIVE_HIGH>;
 		gpio-miso = <&gpio0 ASPEED_GPIO(X, 5) GPIO_ACTIVE_HIGH>;
 
-		tpmdev@0 {
-			compatible = "tcg,tpm_tis-spi";
+		tpm@0 {
+			compatible = "infineon,slb9670", "tcg,tpm_tis-spi";
 			spi-max-frequency = <33000000>;
 			reg = <0>;
 		};
diff --git a/arch/arm/boot/dts/broadcom/bcm-cygnus.dtsi b/arch/arm/boot/dts/broadcom/bcm-cygnus.dtsi
index f9f79ed82518..07ca0d993c9f 100644
--- a/arch/arm/boot/dts/broadcom/bcm-cygnus.dtsi
+++ b/arch/arm/boot/dts/broadcom/bcm-cygnus.dtsi
@@ -167,6 +167,7 @@
 			#gpio-cells = <2>;
 			gpio-controller;
 			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupt-parent = <&mailbox>;
 			interrupts = <0>;
 		};
@@ -247,6 +248,7 @@
 			gpio-controller;
 			interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-controller;
+			#interrupt-cells = <2>;
 		};
 
 		i2c1: i2c@1800b000 {
@@ -518,6 +520,7 @@
 			gpio-controller;
 
 			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupts = <GIC_SPI 174 IRQ_TYPE_LEVEL_HIGH>;
 			gpio-ranges = <&pinctrl 0 42 1>,
 					<&pinctrl 1 44 3>,
diff --git a/arch/arm/boot/dts/broadcom/bcm-hr2.dtsi b/arch/arm/boot/dts/broadcom/bcm-hr2.dtsi
index 788a6806191a..75545b10ef2f 100644
--- a/arch/arm/boot/dts/broadcom/bcm-hr2.dtsi
+++ b/arch/arm/boot/dts/broadcom/bcm-hr2.dtsi
@@ -200,6 +200,7 @@
 			gpio-controller;
 			ngpios = <4>;
 			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupts = <GIC_SPI 93 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
diff --git a/arch/arm/boot/dts/broadcom/bcm-nsp.dtsi b/arch/arm/boot/dts/broadcom/bcm-nsp.dtsi
index 9d20ba3b1ffb..6a4482c93167 100644
--- a/arch/arm/boot/dts/broadcom/bcm-nsp.dtsi
+++ b/arch/arm/boot/dts/broadcom/bcm-nsp.dtsi
@@ -180,6 +180,7 @@
 			gpio-controller;
 			ngpios = <32>;
 			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupts = <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>;
 			gpio-ranges = <&pinctrl 0 0 32>;
 		};
@@ -352,6 +353,7 @@
 			gpio-controller;
 			ngpios = <4>;
 			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupts = <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
diff --git a/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi b/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi
index 98817a6675b9..d233a191c139 100644
--- a/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi
+++ b/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "bcm2835-rpi.dtsi"
 
+#include <dt-bindings/power/raspberrypi-power.h>
 #include <dt-bindings/reset/raspberrypi,firmware-reset.h>
 
 / {
@@ -76,3 +77,7 @@
 &vchiq {
 	interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
 };
+
+&xhci {
+	power-domains = <&power RPI_POWER_DOMAIN_USB>;
+};
diff --git a/arch/arm/boot/dts/broadcom/bcm2711.dtsi b/arch/arm/boot/dts/broadcom/bcm2711.dtsi
index 4a379a14966d..22c7f1561344 100644
--- a/arch/arm/boot/dts/broadcom/bcm2711.dtsi
+++ b/arch/arm/boot/dts/broadcom/bcm2711.dtsi
@@ -604,6 +604,20 @@
 			};
 		};
 
+		xhci: usb@7e9c0000 {
+			compatible = "brcm,bcm2711-xhci", "brcm,xhci-brcm-v2";
+			reg = <0x0 0x7e9c0000 0x100000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <GIC_SPI 176 IRQ_TYPE_LEVEL_HIGH>;
+			/* DWC2 and this IP block share the same USB PHY,
+			 * enabling both at the same time results in lockups.
+			 * So keep this node disabled and let the bootloader
+			 * decide which interface should be enabled.
+			 */
+			status = "disabled";
+		};
+
 		v3d: gpu@7ec00000 {
 			compatible = "brcm,2711-v3d";
 			reg = <0x0 0x7ec00000 0x4000>,
diff --git a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-gateway-7001.dts b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-gateway-7001.dts
index 4d70f6afd13a..6d5e69035f94 100644
--- a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-gateway-7001.dts
+++ b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-gateway-7001.dts
@@ -60,6 +60,8 @@
 			 * We have slots (IDSEL) 1 and 2 with one assigned IRQ
 			 * each handling all IRQs.
 			 */
+			#interrupt-cells = <1>;
+			interrupt-map-mask = <0xf800 0 0 7>;
 			interrupt-map =
 			/* IDSEL 1 */
 			<0x0800 0 0 1 &gpio0 11 IRQ_TYPE_LEVEL_LOW>, /* INT A on slot 1 is irq 11 */
diff --git a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-goramo-multilink.dts b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-goramo-multilink.dts
index 9ec0169bacf8..5f4c849915db 100644
--- a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-goramo-multilink.dts
+++ b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-goramo-multilink.dts
@@ -89,6 +89,8 @@
 			 * The slots have Ethernet, Ethernet, NEC and MPCI.
 			 * The IDSELs are 11, 12, 13, 14.
 			 */
+			#interrupt-cells = <1>;
+			interrupt-map-mask = <0xf800 0 0 7>;
 			interrupt-map =
 			/* IDSEL 11 - Ethernet A */
 			<0x5800 0 0 1 &gpio0 4 IRQ_TYPE_LEVEL_LOW>, /* INT A on slot 11 is irq 4 */
diff --git a/arch/arm/boot/dts/marvell/kirkwood-l-50.dts b/arch/arm/boot/dts/marvell/kirkwood-l-50.dts
index dffb9f84e67c..c841eb8e7fb1 100644
--- a/arch/arm/boot/dts/marvell/kirkwood-l-50.dts
+++ b/arch/arm/boot/dts/marvell/kirkwood-l-50.dts
@@ -65,6 +65,7 @@
 			gpio2: gpio-expander@20 {
 				#gpio-cells = <2>;
 				#interrupt-cells = <2>;
+				interrupt-controller;
 				compatible = "semtech,sx1505q";
 				reg = <0x20>;
 
@@ -79,6 +80,7 @@
 			gpio3: gpio-expander@21 {
 				#gpio-cells = <2>;
 				#interrupt-cells = <2>;
+				interrupt-controller;
 				compatible = "semtech,sx1505q";
 				reg = <0x21>;
 
diff --git a/arch/arm/boot/dts/nuvoton/nuvoton-wpcm450.dtsi b/arch/arm/boot/dts/nuvoton/nuvoton-wpcm450.dtsi
index fd671c7a1e5d..6e1f0f164cb4 100644
--- a/arch/arm/boot/dts/nuvoton/nuvoton-wpcm450.dtsi
+++ b/arch/arm/boot/dts/nuvoton/nuvoton-wpcm450.dtsi
@@ -120,6 +120,7 @@
 				interrupts = <2 IRQ_TYPE_LEVEL_HIGH>,
 					     <3 IRQ_TYPE_LEVEL_HIGH>,
 					     <4 IRQ_TYPE_LEVEL_HIGH>;
+				#interrupt-cells = <2>;
 				interrupt-controller;
 			};
 
@@ -128,6 +129,7 @@
 				gpio-controller;
 				#gpio-cells = <2>;
 				interrupts = <5 IRQ_TYPE_LEVEL_HIGH>;
+				#interrupt-cells = <2>;
 				interrupt-controller;
 			};
 
diff --git a/arch/arm/boot/dts/nvidia/tegra30-apalis-v1.1.dtsi b/arch/arm/boot/dts/nvidia/tegra30-apalis-v1.1.dtsi
index 1640763fd4af..ff0d684622f7 100644
--- a/arch/arm/boot/dts/nvidia/tegra30-apalis-v1.1.dtsi
+++ b/arch/arm/boot/dts/nvidia/tegra30-apalis-v1.1.dtsi
@@ -997,7 +997,6 @@
 			compatible = "st,stmpe811";
 			reg = <0x41>;
 			irq-gpio = <&gpio TEGRA_GPIO(V, 0) GPIO_ACTIVE_LOW>;
-			interrupt-controller;
 			id = <0>;
 			blocks = <0x5>;
 			irq-trigger = <0x1>;
diff --git a/arch/arm/boot/dts/nvidia/tegra30-apalis.dtsi b/arch/arm/boot/dts/nvidia/tegra30-apalis.dtsi
index 3b6fad273cab..d38f1dd38a90 100644
--- a/arch/arm/boot/dts/nvidia/tegra30-apalis.dtsi
+++ b/arch/arm/boot/dts/nvidia/tegra30-apalis.dtsi
@@ -980,7 +980,6 @@
 			compatible = "st,stmpe811";
 			reg = <0x41>;
 			irq-gpio = <&gpio TEGRA_GPIO(V, 0) GPIO_ACTIVE_LOW>;
-			interrupt-controller;
 			id = <0>;
 			blocks = <0x5>;
 			irq-trigger = <0x1>;
diff --git a/arch/arm/boot/dts/nvidia/tegra30-colibri.dtsi b/arch/arm/boot/dts/nvidia/tegra30-colibri.dtsi
index 4eb526fe9c55..81c8a5fd92cc 100644
--- a/arch/arm/boot/dts/nvidia/tegra30-colibri.dtsi
+++ b/arch/arm/boot/dts/nvidia/tegra30-colibri.dtsi
@@ -861,7 +861,6 @@
 			compatible = "st,stmpe811";
 			reg = <0x41>;
 			irq-gpio = <&gpio TEGRA_GPIO(V, 0) GPIO_ACTIVE_LOW>;
-			interrupt-controller;
 			id = <0>;
 			blocks = <0x5>;
 			irq-trigger = <0x1>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-b850v3.dts b/arch/arm/boot/dts/nxp/imx/imx6q-b850v3.dts
index db8c332df6a1..cad112e05475 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6q-b850v3.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx6q-b850v3.dts
@@ -227,7 +227,6 @@
 
 		#address-cells = <3>;
 		#size-cells = <2>;
-		#interrupt-cells = <1>;
 
 		bridge@2,1 {
 			compatible = "pci10b5,8605";
@@ -235,7 +234,6 @@
 
 			#address-cells = <3>;
 			#size-cells = <2>;
-			#interrupt-cells = <1>;
 
 			/* Intel Corporation I210 Gigabit Network Connection */
 			ethernet@3,0 {
@@ -250,7 +248,6 @@
 
 			#address-cells = <3>;
 			#size-cells = <2>;
-			#interrupt-cells = <1>;
 
 			/* Intel Corporation I210 Gigabit Network Connection */
 			switch_nic: ethernet@4,0 {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-bx50v3.dtsi b/arch/arm/boot/dts/nxp/imx/imx6q-bx50v3.dtsi
index 99f4f6ac71d4..c1ae7c47b442 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6q-bx50v3.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6q-bx50v3.dtsi
@@ -245,6 +245,7 @@
 				reg = <0x74>;
 				gpio-controller;
 				#gpio-cells = <2>;
+				#interrupt-cells = <2>;
 				interrupt-controller;
 				interrupt-parent = <&gpio2>;
 				interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
@@ -390,7 +391,6 @@
 
 		#address-cells = <3>;
 		#size-cells = <2>;
-		#interrupt-cells = <1>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi
index 2ae93f57fe5a..ea40623d12e5 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi
@@ -626,7 +626,6 @@
 		blocks = <0x5>;
 		id = <0>;
 		interrupts = <10 IRQ_TYPE_LEVEL_LOW>;
-		interrupt-controller;
 		interrupt-parent = <&gpio4>;
 		irq-trigger = <0x1>;
 		pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi
index 55c90f6393ad..d3a7a6eeb8e0 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi
@@ -550,7 +550,6 @@
 		blocks = <0x5>;
 		interrupts = <20 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-parent = <&gpio6>;
-		interrupt-controller;
 		id = <0>;
 		irq-trigger = <0x1>;
 		pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-emcon.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-emcon.dtsi
index a63e73adc1fc..42b2ba23aefc 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-emcon.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-emcon.dtsi
@@ -225,7 +225,6 @@
 		pinctrl-0 = <&pinctrl_pmic>;
 		interrupt-parent = <&gpio2>;
 		interrupts = <8 IRQ_TYPE_LEVEL_LOW>;
-		interrupt-controller;
 
 		onkey {
 			compatible = "dlg,da9063-onkey";
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi
index 113974520d54..c0c47adc5866 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi
@@ -124,6 +124,7 @@
 		reg = <0x58>;
 		interrupt-parent = <&gpio2>;
 		interrupts = <9 IRQ_TYPE_LEVEL_LOW>; /* active-low GPIO2_9 */
+		#interrupt-cells = <2>;
 		interrupt-controller;
 
 		regulators {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi
index 86b4269e0e01..85e278eb2016 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi
@@ -100,6 +100,7 @@
 		interrupt-parent = <&gpio1>;
 		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 		gpio-controller;
 		#gpio-cells = <2>;
 
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ull-phytec-tauri.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ull-phytec-tauri.dtsi
index 44cc4ff1d0df..d12fb44aeb14 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ull-phytec-tauri.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ull-phytec-tauri.dtsi
@@ -116,7 +116,7 @@
 	tpm_tis: tpm@1 {
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_tpm>;
-		compatible = "tcg,tpm_tis-spi";
+		compatible = "infineon,slb9670", "tcg,tpm_tis-spi";
 		reg = <1>;
 		spi-max-frequency = <20000000>;
 		interrupt-parent = <&gpio5>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx7d-flex-concentrator.dts b/arch/arm/boot/dts/nxp/imx/imx7d-flex-concentrator.dts
index 3a723843d562..9984b343cdf0 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7d-flex-concentrator.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx7d-flex-concentrator.dts
@@ -130,7 +130,7 @@
 	 * TCG specification - Section 6.4.1 Clocking:
 	 * TPM shall support a SPI clock frequency range of 10-24 MHz.
 	 */
-	st33htph: tpm-tis@0 {
+	st33htph: tpm@0 {
 		compatible = "st,st33htpm-spi", "tcg,tpm_tis-spi";
 		reg = <0>;
 		spi-max-frequency = <24000000>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx7d-pico-dwarf.dts b/arch/arm/boot/dts/nxp/imx/imx7d-pico-dwarf.dts
index 12361fcbe24a..1b965652291b 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7d-pico-dwarf.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx7d-pico-dwarf.dts
@@ -63,6 +63,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		#interrupt-cells = <2>;
+		interrupt-controller;
 		reg = <0x25>;
 	};
 
diff --git a/arch/arm/boot/dts/nxp/imx/imx7s.dtsi b/arch/arm/boot/dts/nxp/imx/imx7s.dtsi
index ebf7befcc11e..9c81c6baa2d3 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7s.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx7s.dtsi
@@ -834,16 +834,6 @@
 					<&clks IMX7D_LCDIF_PIXEL_ROOT_CLK>;
 				clock-names = "pix", "axi";
 				status = "disabled";
-
-				port {
-					#address-cells = <1>;
-					#size-cells = <0>;
-
-					lcdif_out_mipi_dsi: endpoint@0 {
-						reg = <0>;
-						remote-endpoint = <&mipi_dsi_in_lcdif>;
-					};
-				};
 			};
 
 			mipi_csi: mipi-csi@30750000 {
@@ -895,22 +885,6 @@
 				samsung,esc-clock-frequency = <20000000>;
 				samsung,pll-clock-frequency = <24000000>;
 				status = "disabled";
-
-				ports {
-					#address-cells = <1>;
-					#size-cells = <0>;
-
-					port@0 {
-						reg = <0>;
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						mipi_dsi_in_lcdif: endpoint@0 {
-							reg = <0>;
-							remote-endpoint = <&lcdif_out_mipi_dsi>;
-						};
-					};
-				};
 			};
 		};
 
diff --git a/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-b.dts b/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-b.dts
index b0ed68af0546..029f49be40e3 100644
--- a/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-b.dts
+++ b/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-b.dts
@@ -338,6 +338,7 @@
 		reg = <0x22>;
 		gpio-controller;
 		#gpio-cells = <2>;
+		#interrupt-cells = <2>;
 		interrupt-controller;
 		interrupt-parent = <&gpio3>;
 		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
diff --git a/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi b/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi
index 2045fc779f88..27429d0fedfb 100644
--- a/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi
@@ -340,10 +340,10 @@
 					  "msi8";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
-			interrupt-map = <0 0 0 1 &intc 0 0 0 141 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
-					<0 0 0 2 &intc 0 0 0 142 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
-					<0 0 0 3 &intc 0 0 0 143 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
-					<0 0 0 4 &intc 0 0 0 144 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
+			interrupt-map = <0 0 0 1 &intc 0 141 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
+					<0 0 0 2 &intc 0 142 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
+					<0 0 0 3 &intc 0 143 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
+					<0 0 0 4 &intc 0 144 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
 
 			clocks = <&gcc GCC_PCIE_PIPE_CLK>,
 				 <&gcc GCC_PCIE_AUX_CLK>,
diff --git a/arch/arm/boot/dts/renesas/r8a7790-lager.dts b/arch/arm/boot/dts/renesas/r8a7790-lager.dts
index 2fba4d084001..8590981245a6 100644
--- a/arch/arm/boot/dts/renesas/r8a7790-lager.dts
+++ b/arch/arm/boot/dts/renesas/r8a7790-lager.dts
@@ -447,6 +447,7 @@
 			interrupt-parent = <&irqc0>;
 			interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-controller;
+			#interrupt-cells = <2>;
 
 			rtc {
 				compatible = "dlg,da9063-rtc";
diff --git a/arch/arm/boot/dts/renesas/r8a7790-stout.dts b/arch/arm/boot/dts/renesas/r8a7790-stout.dts
index f9bc5b4f019d..683f7395fab0 100644
--- a/arch/arm/boot/dts/renesas/r8a7790-stout.dts
+++ b/arch/arm/boot/dts/renesas/r8a7790-stout.dts
@@ -347,6 +347,7 @@
 		interrupt-parent = <&irqc0>;
 		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 
 		onkey {
 			compatible = "dlg,da9063-onkey";
diff --git a/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts b/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts
index e9c13bb03772..0efd9f98c75a 100644
--- a/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts
+++ b/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts
@@ -819,6 +819,7 @@
 		interrupt-parent = <&irqc0>;
 		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 
 		rtc {
 			compatible = "dlg,da9063-rtc";
diff --git a/arch/arm/boot/dts/renesas/r8a7791-porter.dts b/arch/arm/boot/dts/renesas/r8a7791-porter.dts
index 7e8bc06715f6..93c86e921645 100644
--- a/arch/arm/boot/dts/renesas/r8a7791-porter.dts
+++ b/arch/arm/boot/dts/renesas/r8a7791-porter.dts
@@ -413,6 +413,7 @@
 		interrupt-parent = <&irqc0>;
 		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 
 		watchdog {
 			compatible = "dlg,da9063-watchdog";
diff --git a/arch/arm/boot/dts/renesas/r8a7792-blanche.dts b/arch/arm/boot/dts/renesas/r8a7792-blanche.dts
index 4f9838cf97ee..540a9ad28f28 100644
--- a/arch/arm/boot/dts/renesas/r8a7792-blanche.dts
+++ b/arch/arm/boot/dts/renesas/r8a7792-blanche.dts
@@ -381,6 +381,7 @@
 		interrupt-parent = <&irqc>;
 		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 
 		rtc {
 			compatible = "dlg,da9063-rtc";
diff --git a/arch/arm/boot/dts/renesas/r8a7793-gose.dts b/arch/arm/boot/dts/renesas/r8a7793-gose.dts
index 1744fdbf9e0c..1ea6c757893b 100644
--- a/arch/arm/boot/dts/renesas/r8a7793-gose.dts
+++ b/arch/arm/boot/dts/renesas/r8a7793-gose.dts
@@ -759,6 +759,7 @@
 		interrupt-parent = <&irqc0>;
 		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 
 		rtc {
 			compatible = "dlg,da9063-rtc";
diff --git a/arch/arm/boot/dts/renesas/r8a7794-alt.dts b/arch/arm/boot/dts/renesas/r8a7794-alt.dts
index c0d067df22a0..b5ecafbb2e4d 100644
--- a/arch/arm/boot/dts/renesas/r8a7794-alt.dts
+++ b/arch/arm/boot/dts/renesas/r8a7794-alt.dts
@@ -453,6 +453,7 @@
 		interrupt-parent = <&gpio3>;
 		interrupts = <31 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 
 		rtc {
 			compatible = "dlg,da9063-rtc";
diff --git a/arch/arm/boot/dts/renesas/r8a7794-silk.dts b/arch/arm/boot/dts/renesas/r8a7794-silk.dts
index 43d480a7f3ea..595e074085eb 100644
--- a/arch/arm/boot/dts/renesas/r8a7794-silk.dts
+++ b/arch/arm/boot/dts/renesas/r8a7794-silk.dts
@@ -439,6 +439,7 @@
 		interrupt-parent = <&gpio3>;
 		interrupts = <31 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 
 		onkey {
 			compatible = "dlg,da9063-onkey";
diff --git a/arch/arm/boot/dts/rockchip/rv1108.dtsi b/arch/arm/boot/dts/rockchip/rv1108.dtsi
index abf3006f0a84..f3291f3bbc6f 100644
--- a/arch/arm/boot/dts/rockchip/rv1108.dtsi
+++ b/arch/arm/boot/dts/rockchip/rv1108.dtsi
@@ -196,7 +196,6 @@
 	pwm4: pwm@10280000 {
 		compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm";
 		reg = <0x10280000 0x10>;
-		interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru SCLK_PWM>, <&cru PCLK_PWM>;
 		clock-names = "pwm", "pclk";
 		pinctrl-names = "default";
@@ -208,7 +207,6 @@
 	pwm5: pwm@10280010 {
 		compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm";
 		reg = <0x10280010 0x10>;
-		interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru SCLK_PWM>, <&cru PCLK_PWM>;
 		clock-names = "pwm", "pclk";
 		pinctrl-names = "default";
@@ -220,7 +218,6 @@
 	pwm6: pwm@10280020 {
 		compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm";
 		reg = <0x10280020 0x10>;
-		interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru SCLK_PWM>, <&cru PCLK_PWM>;
 		clock-names = "pwm", "pclk";
 		pinctrl-names = "default";
@@ -232,7 +229,6 @@
 	pwm7: pwm@10280030 {
 		compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm";
 		reg = <0x10280030 0x10>;
-		interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru SCLK_PWM>, <&cru PCLK_PWM>;
 		clock-names = "pwm", "pclk";
 		pinctrl-names = "default";
@@ -386,7 +382,6 @@
 	pwm0: pwm@20040000 {
 		compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm";
 		reg = <0x20040000 0x10>;
-		interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru SCLK_PWM0_PMU>, <&cru PCLK_PWM0_PMU>;
 		clock-names = "pwm", "pclk";
 		pinctrl-names = "default";
@@ -398,7 +393,6 @@
 	pwm1: pwm@20040010 {
 		compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm";
 		reg = <0x20040010 0x10>;
-		interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru SCLK_PWM0_PMU>, <&cru PCLK_PWM0_PMU>;
 		clock-names = "pwm", "pclk";
 		pinctrl-names = "default";
@@ -410,7 +404,6 @@
 	pwm2: pwm@20040020 {
 		compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm";
 		reg = <0x20040020 0x10>;
-		interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru SCLK_PWM0_PMU>, <&cru PCLK_PWM0_PMU>;
 		clock-names = "pwm", "pclk";
 		pinctrl-names = "default";
@@ -422,7 +415,6 @@
 	pwm3: pwm@20040030 {
 		compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm";
 		reg = <0x20040030 0x10>;
-		interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru SCLK_PWM0_PMU>, <&cru PCLK_PWM0_PMU>;
 		clock-names = "pwm", "pclk";
 		pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/samsung/exynos4212-tab3.dtsi b/arch/arm/boot/dts/samsung/exynos4212-tab3.dtsi
index d7954ff466b4..e5254e32aa8f 100644
--- a/arch/arm/boot/dts/samsung/exynos4212-tab3.dtsi
+++ b/arch/arm/boot/dts/samsung/exynos4212-tab3.dtsi
@@ -434,6 +434,7 @@
 };
 
 &fimd {
+	samsung,invert-vclk;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/st/stm32429i-eval.dts b/arch/arm/boot/dts/st/stm32429i-eval.dts
index 576235ec3c51..afa417b34b25 100644
--- a/arch/arm/boot/dts/st/stm32429i-eval.dts
+++ b/arch/arm/boot/dts/st/stm32429i-eval.dts
@@ -222,7 +222,6 @@
 		reg = <0x42>;
 		interrupts = <8 3>;
 		interrupt-parent = <&gpioi>;
-		interrupt-controller;
 		wakeup-source;
 
 		stmpegpio: stmpe_gpio {
diff --git a/arch/arm/boot/dts/st/stm32mp157c-dk2.dts b/arch/arm/boot/dts/st/stm32mp157c-dk2.dts
index 510cca5acb79..7a701f7ef0c7 100644
--- a/arch/arm/boot/dts/st/stm32mp157c-dk2.dts
+++ b/arch/arm/boot/dts/st/stm32mp157c-dk2.dts
@@ -64,7 +64,6 @@
 		reg = <0x38>;
 		interrupts = <2 2>;
 		interrupt-parent = <&gpiof>;
-		interrupt-controller;
 		touchscreen-size-x = <480>;
 		touchscreen-size-y = <800>;
 		status = "okay";
diff --git a/arch/arm/boot/dts/ti/omap/am335x-moxa-uc-2100-common.dtsi b/arch/arm/boot/dts/ti/omap/am335x-moxa-uc-2100-common.dtsi
index b8730aa52ce6..a59331aa58e5 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-moxa-uc-2100-common.dtsi
+++ b/arch/arm/boot/dts/ti/omap/am335x-moxa-uc-2100-common.dtsi
@@ -217,7 +217,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&spi1_pins>;
 
-	tpm_spi_tis@0 {
+	tpm@0 {
 		compatible = "tcg,tpm_tis-spi";
 		reg = <0>;
 		spi-max-frequency = <500000>;
diff --git a/arch/arm/boot/dts/ti/omap/am5729-beagleboneai.dts b/arch/arm/boot/dts/ti/omap/am5729-beagleboneai.dts
index c8e55642f9c6..3e834fc7e370 100644
--- a/arch/arm/boot/dts/ti/omap/am5729-beagleboneai.dts
+++ b/arch/arm/boot/dts/ti/omap/am5729-beagleboneai.dts
@@ -415,7 +415,6 @@
 		reg = <0x41>;
 		interrupts = <30 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-parent = <&gpio2>;
-		interrupt-controller;
 		id = <0>;
 		blocks = <0x5>;
 		irq-trigger = <0x1>;
diff --git a/arch/arm/common/locomo.c b/arch/arm/common/locomo.c
index 70480dd9e96d..6d0c9f7268ba 100644
--- a/arch/arm/common/locomo.c
+++ b/arch/arm/common/locomo.c
@@ -68,6 +68,8 @@ struct locomo {
 #endif
 };
 
+static const struct bus_type locomo_bus_type;
+
 struct locomo_dev_info {
 	unsigned long	offset;
 	unsigned long	length;
@@ -842,7 +844,7 @@ static void locomo_bus_remove(struct device *dev)
 		drv->remove(ldev);
 }
 
-struct bus_type locomo_bus_type = {
+static const struct bus_type locomo_bus_type = {
 	.name		= "locomo-bus",
 	.match		= locomo_match,
 	.probe		= locomo_bus_probe,
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index 0a90583f9f01..8f9dbe8d9029 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -297,6 +297,7 @@ CONFIG_FB_MODE_HELPERS=y
 CONFIG_LCD_CLASS_DEVICE=y
 CONFIG_LCD_L4F00242T03=y
 CONFIG_LCD_PLATFORM=y
+CONFIG_BACKLIGHT_CLASS_DEVICE=y
 CONFIG_BACKLIGHT_PWM=y
 CONFIG_BACKLIGHT_GPIO=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig
index feb38a94c1a7..43bc1255a5db 100644
--- a/arch/arm/configs/mxs_defconfig
+++ b/arch/arm/configs/mxs_defconfig
@@ -138,7 +138,8 @@ CONFIG_PWM_MXS=y
 CONFIG_NVMEM_MXS_OCOTP=y
 CONFIG_EXT4_FS=y
 # CONFIG_DNOTIFY is not set
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
 CONFIG_FSCACHE_STATS=y
 CONFIG_CACHEFILES=m
 CONFIG_VFAT_FS=y
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index f6181f69577f..1075534b0a2e 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -340,6 +340,8 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 		dsb(ishst);
 }
 
+#define flush_cache_vmap_early(start, end)	do { } while (0)
+
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
 {
 	if (!cache_is_vipt_nonaliasing())
diff --git a/arch/arm/include/asm/hardware/locomo.h b/arch/arm/include/asm/hardware/locomo.h
index aaaedafef7cc..9fd9ad5d9202 100644
--- a/arch/arm/include/asm/hardware/locomo.h
+++ b/arch/arm/include/asm/hardware/locomo.h
@@ -158,8 +158,6 @@
 #define LOCOMO_LPT_TOH(TOH)	((TOH & 0x7) << 4)
 #define LOCOMO_LPT_TOL(TOL)	((TOL & 0x7))
 
-extern struct bus_type locomo_bus_type;
-
 #define LOCOMO_DEVID_KEYBOARD	0
 #define LOCOMO_DEVID_FRONTLIGHT	1
 #define LOCOMO_DEVID_BACKLIGHT	2
diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h
index e12d7d096fc0..e4eb54f6cd9f 100644
--- a/arch/arm/include/asm/jump_label.h
+++ b/arch/arm/include/asm/jump_label.h
@@ -11,7 +11,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 WASM(nop) "\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".word 1b, %l[l_yes], %c0\n\t"
@@ -25,7 +25,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 WASM(b) " %l[l_yes]\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".word 1b, %l[l_yes], %c0\n\t"
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 16b02f44c7d3..d657b84b6bf7 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -151,6 +151,8 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 
+#define pgdp_get(pgpd)		READ_ONCE(*pgdp)
+
 #define pud_page(pud)		pmd_page(__pmd(pud_val(pud)))
 #define pud_write(pud)		pmd_write(__pmd(pud_val(pud)))
 
diff --git a/arch/arm/mach-davinci/Kconfig b/arch/arm/mach-davinci/Kconfig
index 59de137c6f53..2a8a9fe46586 100644
--- a/arch/arm/mach-davinci/Kconfig
+++ b/arch/arm/mach-davinci/Kconfig
@@ -11,6 +11,7 @@ menuconfig ARCH_DAVINCI
 	select PM_GENERIC_DOMAINS_OF if PM && OF
 	select REGMAP_MMIO
 	select RESET_CONTROLLER
+	select PINCTRL
 	select PINCTRL_SINGLE
 
 if ARCH_DAVINCI
diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c
index 71b113976420..8b1ec60a9a46 100644
--- a/arch/arm/mach-ep93xx/core.c
+++ b/arch/arm/mach-ep93xx/core.c
@@ -339,6 +339,7 @@ static struct gpiod_lookup_table ep93xx_i2c_gpiod_table = {
 				GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
 		GPIO_LOOKUP_IDX("G", 0, NULL, 1,
 				GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
+		{ }
 	},
 };
 
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index cfd9c933d2f0..b94850b57995 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -34,7 +34,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 }
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	if (IS_ENABLED(CONFIG_CPU_V7M)) {
 		/*
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 5409225b4abc..f68db05eba29 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -859,10 +859,7 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
 	int i = 0;
 	int order_idx = 0;
 
-	if (array_size <= PAGE_SIZE)
-		pages = kzalloc(array_size, GFP_KERNEL);
-	else
-		pages = vzalloc(array_size);
+	pages = kvzalloc(array_size, GFP_KERNEL);
 	if (!pages)
 		return NULL;
 
@@ -1713,7 +1710,7 @@ void arm_iommu_detach_device(struct device *dev)
 EXPORT_SYMBOL_GPL(arm_iommu_detach_device);
 
 static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				    const struct iommu_ops *iommu, bool coherent)
+				    bool coherent)
 {
 	struct dma_iommu_mapping *mapping;
 
@@ -1748,7 +1745,7 @@ static void arm_teardown_iommu_dma_ops(struct device *dev)
 #else
 
 static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				    const struct iommu_ops *iommu, bool coherent)
+				    bool coherent)
 {
 }
 
@@ -1757,7 +1754,7 @@ static void arm_teardown_iommu_dma_ops(struct device *dev) { }
 #endif	/* CONFIG_ARM_DMA_USE_IOMMU */
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	/*
 	 * Due to legacy code that sets the ->dma_coherent flag from a bus
@@ -1776,8 +1773,8 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 	if (dev->dma_ops)
 		return;
 
-	if (iommu)
-		arm_setup_iommu_dma_ops(dev, dma_base, size, iommu, coherent);
+	if (device_iommu_mapped(dev))
+		arm_setup_iommu_dma_ops(dev, dma_base, size, coherent);
 
 	xen_setup_dma_ops(dev);
 	dev->archdata.dma_ops_setup = true;
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index fef62e4a9edd..07565b593ed6 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -278,6 +278,37 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
 
+	if (!(flags & FAULT_FLAG_USER))
+		goto lock_mmap;
+
+	vma = lock_vma_under_rcu(mm, addr);
+	if (!vma)
+		goto lock_mmap;
+
+	if (!(vma->vm_flags & vm_flags)) {
+		vma_end_read(vma);
+		goto lock_mmap;
+	}
+	fault = handle_mm_fault(vma, addr, flags | FAULT_FLAG_VMA_LOCK, regs);
+	if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
+		vma_end_read(vma);
+
+	if (!(fault & VM_FAULT_RETRY)) {
+		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+		goto done;
+	}
+	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+	if (fault & VM_FAULT_MAJOR)
+		flags |= FAULT_FLAG_TRIED;
+
+	/* Quick path to respond to signals */
+	if (fault_signal_pending(fault, regs)) {
+		if (!user_mode(regs))
+			goto no_context;
+		return 0;
+	}
+lock_mmap:
+
 retry:
 	vma = lock_mm_and_find_vma(mm, addr, regs);
 	if (unlikely(!vma)) {
@@ -316,6 +347,7 @@ retry:
 	}
 
 	mmap_read_unlock(mm);
+done:
 
 	/*
 	 * Handle the "normal" case first - VM_FAULT_MAJOR
diff --git a/arch/arm/mm/kasan_init.c b/arch/arm/mm/kasan_init.c
index 24d71b5db62d..111d4f703136 100644
--- a/arch/arm/mm/kasan_init.c
+++ b/arch/arm/mm/kasan_init.c
@@ -28,6 +28,12 @@ static pgd_t tmp_pgd_table[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE);
 
 pmd_t tmp_pmd_table[PTRS_PER_PMD] __page_aligned_bss;
 
+static __init void *kasan_alloc_block_raw(size_t size)
+{
+	return memblock_alloc_try_nid_raw(size, size, __pa(MAX_DMA_ADDRESS),
+				      MEMBLOCK_ALLOC_NOLEAKTRACE, NUMA_NO_NODE);
+}
+
 static __init void *kasan_alloc_block(size_t size)
 {
 	return memblock_alloc_try_nid(size, size, __pa(MAX_DMA_ADDRESS),
@@ -50,7 +56,7 @@ static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr,
 			if (!pte_none(READ_ONCE(*ptep)))
 				continue;
 
-			p = kasan_alloc_block(PAGE_SIZE);
+			p = kasan_alloc_block_raw(PAGE_SIZE);
 			if (!p) {
 				panic("%s failed to allocate shadow page for address 0x%lx\n",
 				      __func__, addr);
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 7e8773a2d99d..b68efe643a12 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -800,6 +800,24 @@ static struct undef_hook neon_support_hook[] = {{
 	.cpsr_mask	= PSR_T_BIT,
 	.cpsr_val	= PSR_T_BIT,
 	.fn		= vfp_support_entry,
+}, {
+	.instr_mask	= 0xff000800,
+	.instr_val	= 0xfc000800,
+	.cpsr_mask	= 0,
+	.cpsr_val	= 0,
+	.fn		= vfp_support_entry,
+}, {
+	.instr_mask	= 0xff000800,
+	.instr_val	= 0xfd000800,
+	.cpsr_mask	= 0,
+	.cpsr_val	= 0,
+	.fn		= vfp_support_entry,
+}, {
+	.instr_mask	= 0xff000800,
+	.instr_val	= 0xfe000800,
+	.cpsr_mask	= 0,
+	.cpsr_val	= 0,
+	.fn		= vfp_support_entry,
 }};
 
 static struct undef_hook vfp_support_hook = {
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 8f6cf1221b6a..aa7c1d435139 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -133,6 +133,7 @@ config ARM64
 	select GENERIC_ARCH_TOPOLOGY
 	select GENERIC_CLOCKEVENTS_BROADCAST
 	select GENERIC_CPU_AUTOPROBE
+	select GENERIC_CPU_DEVICES
 	select GENERIC_CPU_VULNERABILITIES
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IDLE_POLL_SETUP
@@ -1038,8 +1039,12 @@ config ARM64_ERRATUM_2645198
 
 	  If unsure, say Y.
 
+config ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
+	bool
+
 config ARM64_ERRATUM_2966298
 	bool "Cortex-A520: 2966298: workaround for speculatively executed unprivileged load"
+	select ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
 	default y
 	help
 	  This option adds the workaround for ARM Cortex-A520 erratum 2966298.
@@ -1051,6 +1056,20 @@ config ARM64_ERRATUM_2966298
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_3117295
+	bool "Cortex-A510: 3117295: workaround for speculatively executed unprivileged load"
+	select ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
+	default y
+	help
+	  This option adds the workaround for ARM Cortex-A510 erratum 3117295.
+
+	  On an affected Cortex-A510 core, a speculatively executed unprivileged
+	  load might leak data from a privileged level via a cache side channel.
+
+	  Work around this problem by executing a TLBI before returning to EL0.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 47ecc4cff9d2..a88cdf910687 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -195,7 +195,7 @@ vdso_prepare: prepare0
 	include/generated/vdso-offsets.h arch/arm64/kernel/vdso/vdso.so
 ifdef CONFIG_COMPAT_VDSO
 	$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 \
-	include/generated/vdso32-offsets.h arch/arm64/kernel/vdso32/vdso.so
+	arch/arm64/kernel/vdso32/vdso.so
 endif
 endif
 
diff --git a/arch/arm64/boot/dts/allwinner/Makefile b/arch/arm64/boot/dts/allwinner/Makefile
index 91d505b385de..1f1f8d865d0e 100644
--- a/arch/arm64/boot/dts/allwinner/Makefile
+++ b/arch/arm64/boot/dts/allwinner/Makefile
@@ -42,5 +42,6 @@ dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-bigtreetech-cb1-manta.dtb
 dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-bigtreetech-pi.dtb
 dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-orangepi-zero2.dtb
 dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-x96-mate.dtb
+dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h618-orangepi-zero2w.dtb
 dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h618-orangepi-zero3.dtb
 dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h618-transpeed-8k618-t.dtb
diff --git a/arch/arm64/boot/dts/amazon/alpine-v2.dtsi b/arch/arm64/boot/dts/amazon/alpine-v2.dtsi
index dccbba6e7f98..dbf2dce8d1d6 100644
--- a/arch/arm64/boot/dts/amazon/alpine-v2.dtsi
+++ b/arch/arm64/boot/dts/amazon/alpine-v2.dtsi
@@ -145,7 +145,6 @@
 		msix: msix@fbe00000 {
 			compatible = "al,alpine-msix";
 			reg = <0x0 0xfbe00000 0x0 0x100000>;
-			interrupt-controller;
 			msi-controller;
 			al,msi-base-spi = <160>;
 			al,msi-num-spis = <160>;
diff --git a/arch/arm64/boot/dts/amazon/alpine-v3.dtsi b/arch/arm64/boot/dts/amazon/alpine-v3.dtsi
index 39481d7fd7d4..3ea178acdddf 100644
--- a/arch/arm64/boot/dts/amazon/alpine-v3.dtsi
+++ b/arch/arm64/boot/dts/amazon/alpine-v3.dtsi
@@ -355,7 +355,6 @@
 		msix: msix@fbe00000 {
 			compatible = "al,alpine-msix";
 			reg = <0x0 0xfbe00000 0x0 0x100000>;
-			interrupt-controller;
 			msi-controller;
 			al,msi-base-spi = <336>;
 			al,msi-num-spis = <959>;
diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
index 9dcd25ec2c04..896d1f33b5b6 100644
--- a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
@@ -586,6 +586,7 @@
 			#gpio-cells = <2>;
 			gpio-controller;
 			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupts = <GIC_SPI 400 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
index f049687d6b96..d8516ec0dae7 100644
--- a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
+++ b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
@@ -450,6 +450,7 @@
 			#gpio-cells = <2>;
 			gpio-controller;
 			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupts = <GIC_SPI 183 IRQ_TYPE_LEVEL_HIGH>;
 			gpio-ranges = <&pinmux 0 0 16>,
 					<&pinmux 16 71 2>,
diff --git a/arch/arm64/boot/dts/exynos/google/gs101.dtsi b/arch/arm64/boot/dts/exynos/google/gs101.dtsi
index 9747cb3fa03a..d838e3a7af6e 100644
--- a/arch/arm64/boot/dts/exynos/google/gs101.dtsi
+++ b/arch/arm64/boot/dts/exynos/google/gs101.dtsi
@@ -289,7 +289,7 @@
 			#clock-cells = <1>;
 			clocks = <&cmu_top CLK_DOUT_CMU_MISC_BUS>,
 				 <&cmu_top CLK_DOUT_CMU_MISC_SSS>;
-			clock-names = "dout_cmu_misc_bus", "dout_cmu_misc_sss";
+			clock-names = "bus", "sss";
 		};
 
 		watchdog_cl0: watchdog@10060000 {
diff --git a/arch/arm64/boot/dts/freescale/Makefile b/arch/arm64/boot/dts/freescale/Makefile
index 2e027675d7bb..2cb0212b63c6 100644
--- a/arch/arm64/boot/dts/freescale/Makefile
+++ b/arch/arm64/boot/dts/freescale/Makefile
@@ -20,23 +20,41 @@ dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1046a-frwy.dtb
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1046a-qds.dtb
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1046a-rdb.dtb
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1046a-tqmls1046a-mbls10xxa.dtb
+DTC_FLAGS_fsl-ls1088a-qds := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1088a-qds.dtb
+DTC_FLAGS_fsl-ls1088a-rdb := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1088a-rdb.dtb
+DTC_FLAGS_fsl-ls1088a-ten64 := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1088a-ten64.dtb
+DTC_FLAGS_fsl-ls1088a-tqmls1088a-mbls10xxa := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1088a-tqmls1088a-mbls10xxa.dtb
+DTC_FLAGS_fsl-ls2080a-qds := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2080a-qds.dtb
+DTC_FLAGS_fsl-ls2080a-rdb := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2080a-rdb.dtb
+DTC_FLAGS_fsl-ls2081a-rdb := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2081a-rdb.dtb
+DTC_FLAGS_fsl-ls2080a-simu := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2080a-simu.dtb
+DTC_FLAGS_fsl-ls2088a-qds := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2088a-qds.dtb
+DTC_FLAGS_fsl-ls2088a-rdb := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2088a-rdb.dtb
+DTC_FLAGS_fsl-lx2160a-bluebox3 := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-bluebox3.dtb
+DTC_FLAGS_fsl-lx2160a-bluebox3-rev-a := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-bluebox3-rev-a.dtb
+DTC_FLAGS_fsl-lx2160a-clearfog-cx := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-clearfog-cx.dtb
+DTC_FLAGS_fsl-lx2160a-honeycomb := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-honeycomb.dtb
+DTC_FLAGS_fsl-lx2160a-qds := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-qds.dtb
+DTC_FLAGS_fsl-lx2160a-rdb := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-rdb.dtb
+DTC_FLAGS_fsl-lx2162a-clearfog := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2162a-clearfog.dtb
+DTC_FLAGS_fsl-lx2162a-qds := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2162a-qds.dtb
 
 fsl-ls1028a-qds-13bb-dtbs := fsl-ls1028a-qds.dtb fsl-ls1028a-qds-13bb.dtbo
@@ -53,6 +71,7 @@ dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1028a-qds-85bb.dtb
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1028a-qds-899b.dtb
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1028a-qds-9999.dtb
 
+DTC_FLAGS_fsl-lx2160a-tqmlx2160a-mblx2160a := -Wno-interrupt_map
 fsl-lx2160a-tqmlx2160a-mblx2160a-12-11-x-dtbs := fsl-lx2160a-tqmlx2160a-mblx2160a.dtb \
 	fsl-lx2160a-tqmlx2160a-mblx2160a_12_x_x.dtbo \
 	fsl-lx2160a-tqmlx2160a-mblx2160a_x_11_x.dtbo
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l.dts b/arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l.dts
index 968f475b9a96..27a902569e2a 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l.dts
@@ -120,7 +120,7 @@
 	};
 
 	tpm: tpm@1 {
-		compatible = "tcg,tpm_tis-spi";
+		compatible = "infineon,slb9670", "tcg,tpm_tis-spi";
 		interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-parent = <&gpio2>;
 		pinctrl-names = "default";
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi
index 3f3f2a2c89cd..752caa38eb03 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi
@@ -89,7 +89,7 @@
 	status = "okay";
 
 	tpm@1 {
-		compatible = "tcg,tpm_tis-spi";
+		compatible = "atmel,attpm20p", "tcg,tpm_tis-spi";
 		reg = <0x1>;
 		spi-max-frequency = <36000000>;
 	};
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi
index 06fed9376996..2aa6c1090fc7 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi
@@ -109,7 +109,7 @@
 	status = "okay";
 
 	tpm@1 {
-		compatible = "tcg,tpm_tis-spi";
+		compatible = "atmel,attpm20p", "tcg,tpm_tis-spi";
 		reg = <0x1>;
 		spi-max-frequency = <36000000>;
 	};
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som-symphony.dts b/arch/arm64/boot/dts/freescale/imx8mn-var-som-symphony.dts
index f38ee2266b25..a6b94d1957c9 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-var-som-symphony.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som-symphony.dts
@@ -128,14 +128,9 @@
 		pinctrl-0 = <&pinctrl_ptn5150>;
 		status = "okay";
 
-		connector {
-			compatible = "usb-c-connector";
-			label = "USB-C";
-
-			port {
-				typec1_dr_sw: endpoint {
-					remote-endpoint = <&usb1_drd_sw>;
-				};
+		port {
+			typec1_dr_sw: endpoint {
+				remote-endpoint = <&usb1_drd_sw>;
 			};
 		};
 	};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts b/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
index feae77e03835..a08057410bde 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
@@ -234,7 +234,7 @@
 	status = "okay";
 
 	tpm: tpm@0 {
-		compatible = "infineon,slb9670";
+		compatible = "infineon,slb9670", "tcg,tpm_tis-spi";
 		reg = <0>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_tpm>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts b/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts
index d98a040860a4..5828c9d7821d 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts
@@ -486,7 +486,7 @@
 &uart4 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart4>;
-	status = "okay";
+	status = "disabled";
 };
 
 &usb3_phy0 {
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-pdk3.dts b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-pdk3.dts
index fea67a9282f0..b749e28e5ede 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-pdk3.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-pdk3.dts
@@ -175,14 +175,10 @@
 				pinctrl-names = "default";
 				pinctrl-0 = <&pinctrl_ptn5150>;
 
-				connector {
-					compatible = "usb-c-connector";
-					label = "USB-C";
-
-					port {
-						ptn5150_out_ep: endpoint {
-							remote-endpoint = <&dwc3_0_ep>;
-						};
+				port {
+
+					ptn5150_out_ep: endpoint {
+						remote-endpoint = <&dwc3_0_ep>;
 					};
 				};
 			};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi
index 4ae4fdab461e..43f1d45ccc96 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi
@@ -255,7 +255,7 @@
 				  <&clk IMX8MP_AUDIO_PLL2_OUT>;
 		assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL2_OUT>;
 		assigned-clock-rates = <13000000>, <13000000>, <156000000>;
-		reset-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&gpio4 1 GPIO_ACTIVE_HIGH>;
 		status = "disabled";
 
 		ports {
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts
index cc9d468b43ab..f87fa5a948cc 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts
@@ -137,6 +137,28 @@
 		};
 
 	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		dsp_vdev0vring0: vdev0vring0@942f0000 {
+			reg = <0 0x942f0000 0 0x8000>;
+			no-map;
+		};
+
+		dsp_vdev0vring1: vdev0vring1@942f8000 {
+			reg = <0 0x942f8000 0 0x8000>;
+			no-map;
+		};
+
+		dsp_vdev0buffer: vdev0buffer@94300000 {
+			compatible = "shared-dma-pool";
+			reg = <0 0x94300000 0 0x100000>;
+			no-map;
+		};
+	};
 };
 
 &flexspi {
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts
index a2d5d19b2de0..86d3da36e4f3 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts
@@ -184,6 +184,13 @@
 		enable-active-high;
 	};
 
+	reg_vcc_1v8: regulator-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "VCC_1V8";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+	};
+
 	reg_vcc_3v3: regulator-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
@@ -480,7 +487,7 @@
 		clock-names = "mclk";
 		clocks = <&audio_blk_ctrl IMX8MP_CLK_AUDIOMIX_SAI3_MCLK1>;
 		reset-gpios = <&gpio4 29 GPIO_ACTIVE_LOW>;
-		iov-supply = <&reg_vcc_3v3>;
+		iov-supply = <&reg_vcc_1v8>;
 		ldoin-supply = <&reg_vcc_3v3>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi
index c24587c895e1..41c79d2ebdd6 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi
@@ -103,7 +103,7 @@
 	status = "okay";
 
 	tpm@1 {
-		compatible = "tcg,tpm_tis-spi";
+		compatible = "atmel,attpm20p", "tcg,tpm_tis-spi";
 		reg = <0x1>;
 		spi-max-frequency = <36000000>;
 	};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi
index 628ffba69862..d5c400b355af 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi
@@ -115,7 +115,7 @@
 	status = "okay";
 
 	tpm@1 {
-		compatible = "tcg,tpm_tis-spi";
+		compatible = "atmel,attpm20p", "tcg,tpm_tis-spi";
 		reg = <0x1>;
 		spi-max-frequency = <36000000>;
 	};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts
index 9caf7ca25444..cae586cd45bd 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts
@@ -196,7 +196,7 @@
 	status = "okay";
 
 	tpm@0 {
-		compatible = "tcg,tpm_tis-spi";
+		compatible = "atmel,attpm20p", "tcg,tpm_tis-spi";
 		reg = <0x0>;
 		spi-max-frequency = <36000000>;
 	};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index 76c73daf546b..39a550c1cd26 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -1820,7 +1820,7 @@
 					compatible = "fsl,imx8mp-ldb";
 					reg = <0x5c 0x4>, <0x128 0x4>;
 					reg-names = "ldb", "lvds";
-					clocks = <&clk IMX8MP_CLK_MEDIA_LDB>;
+					clocks = <&clk IMX8MP_CLK_MEDIA_LDB_ROOT>;
 					clock-names = "ldb";
 					assigned-clocks = <&clk IMX8MP_CLK_MEDIA_LDB>;
 					assigned-clock-parents = <&clk IMX8MP_VIDEO_PLL1_OUT>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mq-kontron-pitx-imx8m.dts b/arch/arm64/boot/dts/freescale/imx8mq-kontron-pitx-imx8m.dts
index 6376417e918c..d8cf1f27c3ec 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq-kontron-pitx-imx8m.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mq-kontron-pitx-imx8m.dts
@@ -65,7 +65,7 @@
 	status = "okay";
 
 	tpm@0 {
-		compatible = "infineon,slb9670";
+		compatible = "infineon,slb9670", "tcg,tpm_tis-spi";
 		reg = <0>;
 		spi-max-frequency = <43000000>;
 	};
diff --git a/arch/arm64/boot/dts/lg/lg1312.dtsi b/arch/arm64/boot/dts/lg/lg1312.dtsi
index 48ec4ebec0a8..b864ffa74ea8 100644
--- a/arch/arm64/boot/dts/lg/lg1312.dtsi
+++ b/arch/arm64/boot/dts/lg/lg1312.dtsi
@@ -126,7 +126,6 @@
 	amba {
 		#address-cells = <2>;
 		#size-cells = <1>;
-		#interrupt-cells = <3>;
 
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
diff --git a/arch/arm64/boot/dts/lg/lg1313.dtsi b/arch/arm64/boot/dts/lg/lg1313.dtsi
index 3869460aa5dc..996fb39bb50c 100644
--- a/arch/arm64/boot/dts/lg/lg1313.dtsi
+++ b/arch/arm64/boot/dts/lg/lg1313.dtsi
@@ -126,7 +126,6 @@
 	amba {
 		#address-cells = <2>;
 		#size-cells = <1>;
-		#interrupt-cells = <3>;
 
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
diff --git a/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi b/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi
index 2c920e22cec2..7ec7c789d87e 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi
@@ -138,7 +138,6 @@
 
 			odmi: odmi@300000 {
 				compatible = "marvell,odmi-controller";
-				interrupt-controller;
 				msi-controller;
 				marvell,odmi-frames = <4>;
 				reg = <0x300000 0x4000>,
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
index 5506de83f61d..1b3396b1cee3 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
@@ -888,7 +888,7 @@
 	status = "okay";
 	cs-gpios = <&pio 86 GPIO_ACTIVE_LOW>;
 
-	cr50@0 {
+	tpm@0 {
 		compatible = "google,cr50";
 		reg = <0>;
 		spi-max-frequency = <1000000>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi
index f2281250ac35..d87aab8d7a79 100644
--- a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi
@@ -1402,7 +1402,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&spi5_pins>;
 
-	cr50@0 {
+	tpm@0 {
 		compatible = "google,cr50";
 		reg = <0>;
 		interrupts-extended = <&pio 171 IRQ_TYPE_EDGE_RISING>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
index bbdcd441c049..3c6079edda19 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
@@ -1294,6 +1294,7 @@
 &xhci0 {
 	status = "okay";
 
+	rx-fifo-depth = <3072>;
 	vusb33-supply = <&mt6359_vusb_ldo_reg>;
 	vbus-supply = <&usb_vbus>;
 };
@@ -1301,6 +1302,7 @@
 &xhci1 {
 	status = "okay";
 
+	rx-fifo-depth = <3072>;
 	vusb33-supply = <&mt6359_vusb_ldo_reg>;
 	vbus-supply = <&usb_vbus>;
 };
diff --git a/arch/arm64/boot/dts/mediatek/mt8195-demo.dts b/arch/arm64/boot/dts/mediatek/mt8195-demo.dts
index 69c7f3954ae5..4127cb84eba4 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195-demo.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8195-demo.dts
@@ -128,6 +128,7 @@
 		compatible = "mediatek,mt6360";
 		reg = <0x34>;
 		interrupt-controller;
+		#interrupt-cells = <1>;
 		interrupts-extended = <&pio 101 IRQ_TYPE_EDGE_FALLING>;
 		interrupt-names = "IRQB";
 
diff --git a/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts b/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts
index ea13c4a7027c..81a82933e350 100644
--- a/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts
+++ b/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts
@@ -175,7 +175,7 @@
 			status = "okay";
 
 			phy-handle = <&mgbe0_phy>;
-			phy-mode = "usxgmii";
+			phy-mode = "10gbase-r";
 
 			mdio {
 				#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/nvidia/tegra234.dtsi b/arch/arm64/boot/dts/nvidia/tegra234.dtsi
index 3f16595d099c..d1bd328892af 100644
--- a/arch/arm64/boot/dts/nvidia/tegra234.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra234.dtsi
@@ -1459,7 +1459,7 @@
 					<&mc TEGRA234_MEMORY_CLIENT_MGBEAWR &emc>;
 			interconnect-names = "dma-mem", "write";
 			iommus = <&smmu_niso0 TEGRA234_SID_MGBE>;
-			power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEA>;
+			power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEB>;
 			status = "disabled";
 		};
 
@@ -1493,7 +1493,7 @@
 					<&mc TEGRA234_MEMORY_CLIENT_MGBEBWR &emc>;
 			interconnect-names = "dma-mem", "write";
 			iommus = <&smmu_niso0 TEGRA234_SID_MGBE_VF1>;
-			power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEB>;
+			power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEC>;
 			status = "disabled";
 		};
 
@@ -1527,7 +1527,7 @@
 					<&mc TEGRA234_MEMORY_CLIENT_MGBECWR &emc>;
 			interconnect-names = "dma-mem", "write";
 			iommus = <&smmu_niso0 TEGRA234_SID_MGBE_VF2>;
-			power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEC>;
+			power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBED>;
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/qcom/ipq6018.dtsi b/arch/arm64/boot/dts/qcom/ipq6018.dtsi
index 5e1277fea725..61c8fd49c966 100644
--- a/arch/arm64/boot/dts/qcom/ipq6018.dtsi
+++ b/arch/arm64/boot/dts/qcom/ipq6018.dtsi
@@ -830,10 +830,10 @@
 
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
-			interrupt-map = <0 0 0 1 &intc 0 75 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
-					<0 0 0 2 &intc 0 78 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
-					<0 0 0 3 &intc 0 79 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
-					<0 0 0 4 &intc 0 83 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
+			interrupt-map = <0 0 0 1 &intc 0 0 0 75 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
+					<0 0 0 2 &intc 0 0 0 78 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
+					<0 0 0 3 &intc 0 0 0 79 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
+					<0 0 0 4 &intc 0 0 0 83 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
 
 			clocks = <&gcc GCC_SYS_NOC_PCIE0_AXI_CLK>,
 				 <&gcc GCC_PCIE0_AXI_M_CLK>,
diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi
index cf295bed3299..26441447c866 100644
--- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi
+++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi
@@ -814,13 +814,13 @@
 			interrupt-names = "msi";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
-			interrupt-map = <0 0 0 1 &intc 0 142
+			interrupt-map = <0 0 0 1 &intc 0 0 142
 					 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
-					<0 0 0 2 &intc 0 143
+					<0 0 0 2 &intc 0 0 143
 					 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
-					<0 0 0 3 &intc 0 144
+					<0 0 0 3 &intc 0 0 144
 					 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
-					<0 0 0 4 &intc 0 145
+					<0 0 0 4 &intc 0 0 145
 					 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
 
 			clocks = <&gcc GCC_SYS_NOC_PCIE1_AXI_CLK>,
@@ -876,13 +876,13 @@
 			interrupt-names = "msi";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
-			interrupt-map = <0 0 0 1 &intc 0 75
+			interrupt-map = <0 0 0 1 &intc 0 0 75
 					 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
-					<0 0 0 2 &intc 0 78
+					<0 0 0 2 &intc 0 0 78
 					 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
-					<0 0 0 3 &intc 0 79
+					<0 0 0 3 &intc 0 0 79
 					 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
-					<0 0 0 4 &intc 0 83
+					<0 0 0 4 &intc 0 0 83
 					 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
 
 			clocks = <&gcc GCC_SYS_NOC_PCIE0_AXI_CLK>,
diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi
index 7f8327b0dbdb..e423c57ddd41 100644
--- a/arch/arm64/boot/dts/qcom/msm8916.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi
@@ -540,9 +540,6 @@
 			compatible = "qcom,msm8916-bimc";
 			reg = <0x00400000 0x62000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_BIMC_CLK>,
-				 <&rpmcc RPM_SMD_BIMC_A_CLK>;
 		};
 
 		tsens: thermal-sensor@4a9000 {
@@ -575,18 +572,12 @@
 			compatible = "qcom,msm8916-pcnoc";
 			reg = <0x00500000 0x11000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_PCNOC_CLK>,
-				 <&rpmcc RPM_SMD_PCNOC_A_CLK>;
 		};
 
 		snoc: interconnect@580000 {
 			compatible = "qcom,msm8916-snoc";
 			reg = <0x00580000 0x14000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_SNOC_CLK>,
-				 <&rpmcc RPM_SMD_SNOC_A_CLK>;
 		};
 
 		stm: stm@802000 {
diff --git a/arch/arm64/boot/dts/qcom/msm8939.dtsi b/arch/arm64/boot/dts/qcom/msm8939.dtsi
index 29f6bd9df2eb..82d85ff61045 100644
--- a/arch/arm64/boot/dts/qcom/msm8939.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8939.dtsi
@@ -602,9 +602,6 @@
 		bimc: interconnect@400000 {
 			compatible = "qcom,msm8939-bimc";
 			reg = <0x00400000 0x62000>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_BIMC_CLK>,
-				 <&rpmcc RPM_SMD_BIMC_A_CLK>;
 			#interconnect-cells = <1>;
 		};
 
@@ -648,25 +645,16 @@
 		pcnoc: interconnect@500000 {
 			compatible = "qcom,msm8939-pcnoc";
 			reg = <0x00500000 0x11000>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_PCNOC_CLK>,
-				 <&rpmcc RPM_SMD_PCNOC_A_CLK>;
 			#interconnect-cells = <1>;
 		};
 
 		snoc: interconnect@580000 {
 			compatible = "qcom,msm8939-snoc";
 			reg = <0x00580000 0x14080>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_SNOC_CLK>,
-				 <&rpmcc RPM_SMD_SNOC_A_CLK>;
 			#interconnect-cells = <1>;
 
 			snoc_mm: interconnect-snoc {
 				compatible = "qcom,msm8939-snoc-mm";
-				clock-names = "bus", "bus_a";
-				clocks = <&rpmcc RPM_SMD_SYSMMNOC_CLK>,
-					 <&rpmcc RPM_SMD_SYSMMNOC_A_CLK>;
 				#interconnect-cells = <1>;
 			};
 		};
diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi
index 8c6a7efa90c4..ee6f87c828ae 100644
--- a/arch/arm64/boot/dts/qcom/msm8996.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi
@@ -457,25 +457,6 @@
 		};
 	};
 
-	mpm: interrupt-controller {
-		compatible = "qcom,mpm";
-		qcom,rpm-msg-ram = <&apss_mpm>;
-		interrupts = <GIC_SPI 171 IRQ_TYPE_EDGE_RISING>;
-		mboxes = <&apcs_glb 1>;
-		interrupt-controller;
-		#interrupt-cells = <2>;
-		#power-domain-cells = <0>;
-		interrupt-parent = <&intc>;
-		qcom,mpm-pin-count = <96>;
-		qcom,mpm-pin-map = <2 184>,  /* TSENS1 upper_lower_int */
-				   <52 243>, /* DWC3_PRI ss_phy_irq */
-				   <79 347>, /* DWC3_PRI hs_phy_irq */
-				   <80 352>, /* DWC3_SEC hs_phy_irq */
-				   <81 347>, /* QUSB2_PHY_PRI DP+DM */
-				   <82 352>, /* QUSB2_PHY_SEC DP+DM */
-				   <87 326>; /* SPMI */
-	};
-
 	psci {
 		compatible = "arm,psci-1.0";
 		method = "smc";
@@ -765,15 +746,8 @@
 		};
 
 		rpm_msg_ram: sram@68000 {
-			compatible = "qcom,rpm-msg-ram", "mmio-sram";
+			compatible = "qcom,rpm-msg-ram";
 			reg = <0x00068000 0x6000>;
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges = <0 0x00068000 0x7000>;
-
-			apss_mpm: sram@1b8 {
-				reg = <0x1b8 0x48>;
-			};
 		};
 
 		qfprom@74000 {
@@ -838,9 +812,6 @@
 			compatible = "qcom,msm8996-bimc";
 			reg = <0x00408000 0x5a000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_BIMC_CLK>,
-				 <&rpmcc RPM_SMD_BIMC_A_CLK>;
 		};
 
 		tsens0: thermal-sensor@4a9000 {
@@ -859,8 +830,8 @@
 			reg = <0x004ad000 0x1000>, /* TM */
 			      <0x004ac000 0x1000>; /* SROT */
 			#qcom,sensors = <8>;
-			interrupts-extended = <&mpm 2 IRQ_TYPE_LEVEL_HIGH>,
-					      <&intc GIC_SPI 430 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 184 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 430 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "uplow", "critical";
 			#thermal-sensor-cells = <1>;
 		};
@@ -891,18 +862,12 @@
 			compatible = "qcom,msm8996-cnoc";
 			reg = <0x00500000 0x1000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_CNOC_CLK>,
-				 <&rpmcc RPM_SMD_CNOC_A_CLK>;
 		};
 
 		snoc: interconnect@524000 {
 			compatible = "qcom,msm8996-snoc";
 			reg = <0x00524000 0x1c000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_SNOC_CLK>,
-				 <&rpmcc RPM_SMD_SNOC_A_CLK>;
 		};
 
 		a0noc: interconnect@543000 {
@@ -922,19 +887,14 @@
 			compatible = "qcom,msm8996-a1noc";
 			reg = <0x00562000 0x5000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_AGGR1_NOC_CLK>,
-				 <&rpmcc RPM_SMD_AGGR1_NOC_A_CLK>;
 		};
 
 		a2noc: interconnect@583000 {
 			compatible = "qcom,msm8996-a2noc";
 			reg = <0x00583000 0x7000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a", "aggre2_ufs_axi", "ufs_axi";
-			clocks = <&rpmcc RPM_SMD_AGGR2_NOC_CLK>,
-				 <&rpmcc RPM_SMD_AGGR2_NOC_A_CLK>,
-				 <&gcc GCC_AGGRE2_UFS_AXI_CLK>,
+			clock-names = "aggre2_ufs_axi", "ufs_axi";
+			clocks = <&gcc GCC_AGGRE2_UFS_AXI_CLK>,
 				 <&gcc GCC_UFS_AXI_CLK>;
 		};
 
@@ -942,19 +902,14 @@
 			compatible = "qcom,msm8996-mnoc";
 			reg = <0x005a4000 0x1c000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a", "iface";
-			clocks = <&rpmcc RPM_SMD_MMAXI_CLK>,
-				 <&rpmcc RPM_SMD_MMAXI_A_CLK>,
-				 <&mmcc AHB_CLK_SRC>;
+			clock-names = "iface";
+			clocks = <&mmcc AHB_CLK_SRC>;
 		};
 
 		pnoc: interconnect@5c0000 {
 			compatible = "qcom,msm8996-pnoc";
 			reg = <0x005c0000 0x3000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_PCNOC_CLK>,
-				 <&rpmcc RPM_SMD_PCNOC_A_CLK>;
 		};
 
 		tcsr_mutex: hwlock@740000 {
@@ -1382,7 +1337,6 @@
 			interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
 			gpio-controller;
 			gpio-ranges = <&tlmm 0 0 150>;
-			wakeup-parent = <&mpm>;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -1910,7 +1864,7 @@
 			      <0x0400a000 0x002100>;
 			reg-names = "core", "chnls", "obsrvr", "intr", "cnfg";
 			interrupt-names = "periph_irq";
-			interrupts-extended = <&mpm 87 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 326 IRQ_TYPE_LEVEL_HIGH>;
 			qcom,ee = <0>;
 			qcom,channel = <0>;
 			#address-cells = <2>;
@@ -2486,9 +2440,8 @@
 					  "handover",
 					  "stop-ack";
 
-			clocks = <&xo_board>,
-				 <&rpmcc RPM_SMD_AGGR2_NOC_CLK>;
-			clock-names = "xo", "aggre2";
+			clocks = <&xo_board>;
+			clock-names = "xo";
 
 			memory-region = <&slpi_mem>;
 
@@ -2533,10 +2486,15 @@
 				 <&gcc GCC_MSS_GPLL0_DIV_CLK>,
 				 <&gcc GCC_MSS_SNOC_AXI_CLK>,
 				 <&gcc GCC_MSS_MNOC_BIMC_AXI_CLK>,
-				 <&rpmcc RPM_SMD_PCNOC_CLK>,
 				 <&rpmcc RPM_SMD_QDSS_CLK>;
-			clock-names = "iface", "bus", "mem", "xo", "gpll0_mss",
-				      "snoc_axi", "mnoc_axi", "pnoc", "qdss";
+			clock-names = "iface",
+				      "bus",
+				      "mem",
+				      "xo",
+				      "gpll0_mss",
+				      "snoc_axi",
+				      "mnoc_axi",
+				      "qdss";
 
 			resets = <&gcc GCC_MSS_RESTART>;
 			reset-names = "mss_restart";
@@ -3067,8 +3025,8 @@
 			#size-cells = <1>;
 			ranges;
 
-			interrupts-extended = <&mpm 79 IRQ_TYPE_LEVEL_HIGH>,
-					      <&mpm 52 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 347 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 243 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "hs_phy_irq", "ss_phy_irq";
 
 			clocks = <&gcc GCC_SYS_NOC_USB3_AXI_CLK>,
diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi
index bb591c6bf573..2793cc22d381 100644
--- a/arch/arm64/boot/dts/qcom/msm8998.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi
@@ -1605,9 +1605,8 @@
 
 			px-supply = <&vreg_lvs2a_1p8>;
 
-			clocks = <&rpmcc RPM_SMD_XO_CLK_SRC>,
-				 <&rpmcc RPM_SMD_AGGR2_NOC_CLK>;
-			clock-names = "xo", "aggre2";
+			clocks = <&rpmcc RPM_SMD_XO_CLK_SRC>;
+			clock-names = "xo";
 
 			memory-region = <&slpi_mem>;
 
diff --git a/arch/arm64/boot/dts/qcom/qcs404.dtsi b/arch/arm64/boot/dts/qcom/qcs404.dtsi
index 6ac64ce9bb68..2f2eeaf2e945 100644
--- a/arch/arm64/boot/dts/qcom/qcs404.dtsi
+++ b/arch/arm64/boot/dts/qcom/qcs404.dtsi
@@ -558,9 +558,6 @@
 			reg = <0x00400000 0x80000>;
 			compatible = "qcom,qcs404-bimc";
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_BIMC_CLK>,
-				<&rpmcc RPM_SMD_BIMC_A_CLK>;
 		};
 
 		tsens: thermal-sensor@4a9000 {
@@ -601,18 +598,12 @@
 			reg = <0x00500000 0x15080>;
 			compatible = "qcom,qcs404-pcnoc";
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_PNOC_CLK>,
-				<&rpmcc RPM_SMD_PNOC_A_CLK>;
 		};
 
 		snoc: interconnect@580000 {
 			reg = <0x00580000 0x23080>;
 			compatible = "qcom,qcs404-snoc";
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_SNOC_CLK>,
-				<&rpmcc RPM_SMD_SNOC_A_CLK>;
 		};
 
 		remoteproc_cdsp: remoteproc@b00000 {
diff --git a/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts b/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts
index 043184557873..cd0db4f31d4a 100644
--- a/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts
+++ b/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts
@@ -1454,7 +1454,7 @@
 
 		altmodes {
 			displayport {
-				svid = <0xff01>;
+				svid = /bits/ 16 <0xff01>;
 				vdo = <0x00001c46>;
 			};
 		};
diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts b/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts
index ffc4406422ae..41215567b3ae 100644
--- a/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts
+++ b/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts
@@ -563,6 +563,8 @@
 };
 
 &pcie4 {
+	max-link-speed = <2>;
+
 	perst-gpios = <&tlmm 141 GPIO_ACTIVE_LOW>;
 	wake-gpios = <&tlmm 139 GPIO_ACTIVE_LOW>;
 
diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts
index def3976bd5bb..eb657e544961 100644
--- a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts
+++ b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts
@@ -722,6 +722,8 @@
 };
 
 &pcie4 {
+	max-link-speed = <2>;
+
 	perst-gpios = <&tlmm 141 GPIO_ACTIVE_LOW>;
 	wake-gpios = <&tlmm 139 GPIO_ACTIVE_LOW>;
 
diff --git a/arch/arm64/boot/dts/qcom/sdm630.dtsi b/arch/arm64/boot/dts/qcom/sdm630.dtsi
index 775700f78e0f..513fe5e76b68 100644
--- a/arch/arm64/boot/dts/qcom/sdm630.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm630.dtsi
@@ -606,9 +606,6 @@
 			compatible = "qcom,sdm660-bimc";
 			reg = <0x01008000 0x78000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_BIMC_CLK>,
-				 <&rpmcc RPM_SMD_BIMC_A_CLK>;
 		};
 
 		restart@10ac000 {
@@ -620,28 +617,17 @@
 			compatible = "qcom,sdm660-cnoc";
 			reg = <0x01500000 0x10000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_CNOC_CLK>,
-				 <&rpmcc RPM_SMD_CNOC_A_CLK>;
 		};
 
 		snoc: interconnect@1626000 {
 			compatible = "qcom,sdm660-snoc";
 			reg = <0x01626000 0x7090>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_SNOC_CLK>,
-				 <&rpmcc RPM_SMD_SNOC_A_CLK>;
 		};
 
 		anoc2_smmu: iommu@16c0000 {
 			compatible = "qcom,sdm630-smmu-v2", "qcom,smmu-v2";
 			reg = <0x016c0000 0x40000>;
-
-			assigned-clocks = <&rpmcc RPM_SMD_AGGR2_NOC_CLK>;
-			assigned-clock-rates = <1000>;
-			clocks = <&rpmcc RPM_SMD_AGGR2_NOC_CLK>;
-			clock-names = "bus";
 			#global-interrupts = <2>;
 			#iommu-cells = <1>;
 
@@ -686,16 +672,12 @@
 			compatible = "qcom,sdm660-a2noc";
 			reg = <0x01704000 0xc100>;
 			#interconnect-cells = <1>;
-			clock-names = "bus",
-				      "bus_a",
-				      "ipa",
+			clock-names = "ipa",
 				      "ufs_axi",
 				      "aggre2_ufs_axi",
 				      "aggre2_usb3_axi",
 				      "cfg_noc_usb2_axi";
-			clocks = <&rpmcc RPM_SMD_AGGR2_NOC_CLK>,
-				 <&rpmcc RPM_SMD_AGGR2_NOC_A_CLK>,
-				 <&rpmcc RPM_SMD_IPA_CLK>,
+			clocks = <&rpmcc RPM_SMD_IPA_CLK>,
 				 <&gcc GCC_UFS_AXI_CLK>,
 				 <&gcc GCC_AGGRE2_UFS_AXI_CLK>,
 				 <&gcc GCC_AGGRE2_USB3_AXI_CLK>,
@@ -706,10 +688,8 @@
 			compatible = "qcom,sdm660-mnoc";
 			reg = <0x01745000 0xa010>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a", "iface";
-			clocks = <&rpmcc RPM_SMD_MMSSNOC_AXI_CLK>,
-				 <&rpmcc RPM_SMD_MMSSNOC_AXI_CLK_A>,
-				 <&mmcc AHB_CLK_SRC>;
+			clock-names = "iface";
+			clocks = <&mmcc AHB_CLK_SRC>;
 		};
 
 		tsens: thermal-sensor@10ae000 {
@@ -1186,7 +1166,9 @@
 			clocks = <&gcc GCC_GPU_CFG_AHB_CLK>,
 				 <&gcc GCC_BIMC_GFX_CLK>,
 				 <&gcc GCC_GPU_BIMC_GFX_CLK>;
-			clock-names = "iface", "mem", "mem_iface";
+			clock-names = "iface",
+			              "mem",
+				      "mem_iface";
 			#global-interrupts = <2>;
 			#iommu-cells = <1>;
 
@@ -1288,20 +1270,16 @@
 				 <&gcc GCC_USB30_MASTER_CLK>,
 				 <&gcc GCC_AGGRE2_USB3_AXI_CLK>,
 				 <&gcc GCC_USB30_SLEEP_CLK>,
-				 <&gcc GCC_USB30_MOCK_UTMI_CLK>,
-				 <&rpmcc RPM_SMD_AGGR2_NOC_CLK>;
+				 <&gcc GCC_USB30_MOCK_UTMI_CLK>;
 			clock-names = "cfg_noc",
 				      "core",
 				      "iface",
 				      "sleep",
-				      "mock_utmi",
-				      "bus";
+				      "mock_utmi";
 
 			assigned-clocks = <&gcc GCC_USB30_MOCK_UTMI_CLK>,
-					  <&gcc GCC_USB30_MASTER_CLK>,
-					  <&rpmcc RPM_SMD_AGGR2_NOC_CLK>;
-			assigned-clock-rates = <19200000>, <120000000>,
-					       <19200000>;
+					  <&gcc GCC_USB30_MASTER_CLK>;
+			assigned-clock-rates = <19200000>, <120000000>;
 
 			interrupts = <GIC_SPI 347 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 243 IRQ_TYPE_LEVEL_HIGH>;
@@ -2204,10 +2182,9 @@
 
 			clocks = <&mmcc MNOC_AHB_CLK>,
 				 <&mmcc BIMC_SMMU_AHB_CLK>,
-				 <&rpmcc RPM_SMD_MMSSNOC_AXI_CLK>,
 				 <&mmcc BIMC_SMMU_AXI_CLK>;
 			clock-names = "iface-mm", "iface-smmu",
-				      "bus-mm", "bus-smmu";
+				      "bus-smmu";
 			#global-interrupts = <2>;
 			#iommu-cells = <1>;
 
@@ -2324,12 +2301,6 @@
 			compatible = "qcom,sdm660-gnoc";
 			reg = <0x17900000 0xe000>;
 			#interconnect-cells = <1>;
-			/*
-			 * This one apparently features no clocks,
-			 * so let's not mess with the driver needlessly
-			 */
-			clock-names = "bus", "bus_a";
-			clocks = <&xo_board>, <&xo_board>;
 		};
 
 		apcs_glb: mailbox@17911000 {
diff --git a/arch/arm64/boot/dts/qcom/sm6115.dtsi b/arch/arm64/boot/dts/qcom/sm6115.dtsi
index 160e098f1075..f9849b8befbf 100644
--- a/arch/arm64/boot/dts/qcom/sm6115.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm6115.dtsi
@@ -1304,6 +1304,9 @@
 						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>,
 						<&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG
 						 &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
diff --git a/arch/arm64/boot/dts/qcom/sm8650-mtp.dts b/arch/arm64/boot/dts/qcom/sm8650-mtp.dts
index 9d916edb1c73..be133a3d5cbe 100644
--- a/arch/arm64/boot/dts/qcom/sm8650-mtp.dts
+++ b/arch/arm64/boot/dts/qcom/sm8650-mtp.dts
@@ -622,7 +622,7 @@
 
 &tlmm {
 	/* Reserved I/Os for NFC */
-	gpio-reserved-ranges = <32 8>;
+	gpio-reserved-ranges = <32 8>, <74 1>;
 
 	disp0_reset_n_active: disp0-reset-n-active-state {
 		pins = "gpio133";
diff --git a/arch/arm64/boot/dts/qcom/sm8650-qrd.dts b/arch/arm64/boot/dts/qcom/sm8650-qrd.dts
index 592a67a47c78..b9151c2ddf2e 100644
--- a/arch/arm64/boot/dts/qcom/sm8650-qrd.dts
+++ b/arch/arm64/boot/dts/qcom/sm8650-qrd.dts
@@ -659,7 +659,7 @@
 
 &tlmm {
 	/* Reserved I/Os for NFC */
-	gpio-reserved-ranges = <32 8>;
+	gpio-reserved-ranges = <32 8>, <74 1>;
 
 	bt_default: bt-default-state {
 		bt-en-pins {
diff --git a/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi b/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi
index 3885ef3454ff..50de17e4fb3f 100644
--- a/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi
+++ b/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi
@@ -234,6 +234,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 		interrupt-parent = <&gpio6>;
 		interrupts = <8 IRQ_TYPE_EDGE_FALLING>;
 
@@ -294,6 +295,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 		interrupt-parent = <&gpio6>;
 		interrupts = <4 IRQ_TYPE_EDGE_FALLING>;
 	};
@@ -314,6 +316,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 		interrupt-parent = <&gpio7>;
 		interrupts = <3 IRQ_TYPE_EDGE_FALLING>;
 	};
@@ -324,6 +327,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 		interrupt-parent = <&gpio5>;
 		interrupts = <9 IRQ_TYPE_EDGE_FALLING>;
 	};
diff --git a/arch/arm64/boot/dts/rockchip/px30.dtsi b/arch/arm64/boot/dts/rockchip/px30.dtsi
index d0905515399b..9137dd76e72c 100644
--- a/arch/arm64/boot/dts/rockchip/px30.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30.dtsi
@@ -631,6 +631,7 @@
 		clock-names = "spiclk", "apb_pclk";
 		dmas = <&dmac 12>, <&dmac 13>;
 		dma-names = "tx", "rx";
+		num-cs = <2>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&spi0_clk &spi0_csn &spi0_miso &spi0_mosi>;
 		#address-cells = <1>;
@@ -646,6 +647,7 @@
 		clock-names = "spiclk", "apb_pclk";
 		dmas = <&dmac 14>, <&dmac 15>;
 		dma-names = "tx", "rx";
+		num-cs = <2>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&spi1_clk &spi1_csn0 &spi1_csn1 &spi1_miso &spi1_mosi>;
 		#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
index fb5dcf6e9327..7b4c15c4a9c3 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
@@ -488,7 +488,6 @@
 	pwm3: pwm@ff1b0030 {
 		compatible = "rockchip,rk3328-pwm";
 		reg = <0x0 0xff1b0030 0x0 0x10>;
-		interrupts = <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru SCLK_PWM>, <&cru PCLK_PWM>;
 		clock-names = "pwm", "pclk";
 		pinctrl-names = "default";
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts b/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts
index 0f9cc042d9bf..1cba1d857c96 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts
@@ -70,7 +70,7 @@
 &spi0 {
 	status = "okay";
 
-	cr50@0 {
+	tpm@0 {
 		compatible = "google,cr50";
 		reg = <0>;
 		interrupt-parent = <&gpio0>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi
index c5e7de60c121..5846a11f0e84 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi
@@ -706,7 +706,7 @@ camera: &i2c7 {
 &spi2 {
 	status = "okay";
 
-	cr50@0 {
+	tpm@0 {
 		compatible = "google,cr50";
 		reg = <0>;
 		interrupt-parent = <&gpio1>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-evb.dts b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-evb.dts
index d4c70835e0fe..a4946cdc3bb3 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-evb.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-evb.dts
@@ -72,7 +72,7 @@
 		vin-supply = <&vcc3v3_sys>;
 	};
 
-	vcc5v0_usb30_host: vcc5v0-usb30-host-regulator {
+	vcc5v0_usb_host1: vcc5v0_usb_host2: vcc5v0-usb-host-regulator {
 		compatible = "regulator-fixed";
 		regulator-name = "vcc5v0_host";
 		regulator-boot-on;
@@ -114,6 +114,7 @@
 	status = "okay";
 };
 
+/* Standard pcie */
 &pcie3x2 {
 	reset-gpios = <&gpio3 RK_PB0 GPIO_ACTIVE_HIGH>;
 	vpcie3v3-supply = <&vcc3v3_sys>;
@@ -122,6 +123,7 @@
 
 /* M.2 M-Key ssd */
 &pcie3x4 {
+	num-lanes = <2>;
 	reset-gpios = <&gpio4 RK_PB6 GPIO_ACTIVE_HIGH>;
 	vpcie3v3-supply = <&vcc3v3_sys>;
 	status = "okay";
@@ -188,12 +190,12 @@
 };
 
 &u2phy2_host {
-	phy-supply = <&vcc5v0_usb30_host>;
+	phy-supply = <&vcc5v0_usb_host1>;
 	status = "okay";
 };
 
 &u2phy3_host {
-	phy-supply = <&vcc5v0_usb30_host>;
+	phy-supply = <&vcc5v0_usb_host2>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi
index 0b02f4d6e003..cce1c8e83587 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi
@@ -16,8 +16,8 @@
 
 	aliases {
 		mmc0 = &sdhci;
-		mmc1 = &sdio;
-		mmc2 = &sdmmc;
+		mmc1 = &sdmmc;
+		mmc2 = &sdio;
 		serial2 = &uart2;
 	};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts b/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts
index ac7c677b0fb9..de30c2632b8e 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts
@@ -448,6 +448,7 @@
 			    <&rk806_dvs2_null>, <&rk806_dvs3_null>;
 		pinctrl-names = "default";
 		spi-max-frequency = <1000000>;
+		system-power-controller;
 
 		vcc1-supply = <&vcc5v0_sys>;
 		vcc2-supply = <&vcc5v0_sys>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts b/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts
index 4ce70fb75a30..39d65002add1 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts
@@ -62,7 +62,6 @@
 		compatible = "gpio-leds";
 		pinctrl-names = "default";
 		pinctrl-0 = <&led1_pin>;
-		status = "okay";
 
 		/* LED1 on PCB */
 		led-1 {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts b/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts
index d7722772ecd8..997b516c2533 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts
@@ -189,19 +189,19 @@
 	cpu-supply = <&vdd_cpu_lit_s0>;
 };
 
-&cpu_b0{
+&cpu_b0 {
 	cpu-supply = <&vdd_cpu_big0_s0>;
 };
 
-&cpu_b1{
+&cpu_b1 {
 	cpu-supply = <&vdd_cpu_big0_s0>;
 };
 
-&cpu_b2{
+&cpu_b2 {
 	cpu-supply = <&vdd_cpu_big1_s0>;
 };
 
-&cpu_b3{
+&cpu_b3 {
 	cpu-supply = <&vdd_cpu_big1_s0>;
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts b/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts
index ef4f058c20ff..e037bf9db75a 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts
@@ -19,8 +19,8 @@
 
 	aliases {
 		mmc0 = &sdhci;
-		mmc1 = &sdio;
-		mmc2 = &sdmmc;
+		mmc1 = &sdmmc;
+		mmc2 = &sdio;
 	};
 
 	analog-sound {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts b/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts
index dc677f29a9c7..3c2278886851 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts
@@ -195,13 +195,13 @@
 
 &gpio1 {
 	gpio-line-names = /* GPIO1 A0-A7 */
-			  "HEADER_27_3v3", "HEADER_28_3v3", "", "",
+			  "HEADER_27_3v3", "", "", "",
 			  "HEADER_29_1v8", "", "HEADER_7_1v8", "",
 			  /* GPIO1 B0-B7 */
 			  "", "HEADER_31_1v8", "HEADER_33_1v8", "",
 			  "HEADER_11_1v8", "HEADER_13_1v8", "", "",
 			  /* GPIO1 C0-C7 */
-			  "", "", "", "",
+			  "", "HEADER_28_3v3", "", "",
 			  "", "", "", "",
 			  /* GPIO1 D0-D7 */
 			  "", "", "", "",
@@ -225,11 +225,11 @@
 
 &gpio4 {
 	gpio-line-names = /* GPIO4 A0-A7 */
-			  "", "", "HEADER_37_3v3", "HEADER_32_3v3",
-			  "HEADER_36_3v3", "", "HEADER_35_3v3", "HEADER_38_3v3",
+			  "", "", "HEADER_37_3v3", "HEADER_8_3v3",
+			  "HEADER_10_3v3", "", "HEADER_32_3v3", "HEADER_35_3v3",
 			  /* GPIO4 B0-B7 */
 			  "", "", "", "HEADER_40_3v3",
-			  "HEADER_8_3v3", "HEADER_10_3v3", "", "",
+			  "HEADER_38_3v3", "HEADER_36_3v3", "", "",
 			  /* GPIO4 C0-C7 */
 			  "", "", "", "",
 			  "", "", "", "",
diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c
index bac4cabef607..467ac2f768ac 100644
--- a/arch/arm64/crypto/aes-neonbs-glue.c
+++ b/arch/arm64/crypto/aes-neonbs-glue.c
@@ -227,8 +227,19 @@ static int ctr_encrypt(struct skcipher_request *req)
 			src += blocks * AES_BLOCK_SIZE;
 		}
 		if (nbytes && walk.nbytes == walk.total) {
+			u8 buf[AES_BLOCK_SIZE];
+			u8 *d = dst;
+
+			if (unlikely(nbytes < AES_BLOCK_SIZE))
+				src = dst = memcpy(buf + sizeof(buf) - nbytes,
+						   src, nbytes);
+
 			neon_aes_ctr_encrypt(dst, src, ctx->enc, ctx->key.rounds,
 					     nbytes, walk.iv);
+
+			if (unlikely(nbytes < AES_BLOCK_SIZE))
+				memcpy(d, dst, nbytes);
+
 			nbytes = 0;
 		}
 		kernel_neon_end();
diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h
index 210bb43cff2c..d328f549b1a6 100644
--- a/arch/arm64/include/asm/alternative-macros.h
+++ b/arch/arm64/include/asm/alternative-macros.h
@@ -229,7 +229,7 @@ alternative_has_cap_likely(const unsigned long cpucap)
 	if (!cpucap_is_possible(cpucap))
 		return false;
 
-	asm_volatile_goto(
+	asm goto(
 	ALTERNATIVE_CB("b	%l[l_no]", %[cpucap], alt_cb_patch_nops)
 	:
 	: [cpucap] "i" (cpucap)
@@ -247,7 +247,7 @@ alternative_has_cap_unlikely(const unsigned long cpucap)
 	if (!cpucap_is_possible(cpucap))
 		return false;
 
-	asm_volatile_goto(
+	asm goto(
 	ALTERNATIVE("nop", "b	%l[l_yes]", %[cpucap])
 	:
 	: [cpucap] "i" (cpucap)
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 7b1975bf4b90..513787e43329 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -760,32 +760,25 @@ alternative_endif
 .endm
 
 	/*
-	 * Check whether preempt/bh-disabled asm code should yield as soon as
-	 * it is able. This is the case if we are currently running in task
-	 * context, and either a softirq is pending, or the TIF_NEED_RESCHED
-	 * flag is set and re-enabling preemption a single time would result in
-	 * a preempt count of zero. (Note that the TIF_NEED_RESCHED flag is
-	 * stored negated in the top word of the thread_info::preempt_count
+	 * Check whether asm code should yield as soon as it is able. This is
+	 * the case if we are currently running in task context, and the
+	 * TIF_NEED_RESCHED flag is set. (Note that the TIF_NEED_RESCHED flag
+	 * is stored negated in the top word of the thread_info::preempt_count
 	 * field)
 	 */
-	.macro		cond_yield, lbl:req, tmp:req, tmp2:req
+	.macro		cond_yield, lbl:req, tmp:req, tmp2
+#ifdef CONFIG_PREEMPT_VOLUNTARY
 	get_current_task \tmp
 	ldr		\tmp, [\tmp, #TSK_TI_PREEMPT]
 	/*
 	 * If we are serving a softirq, there is no point in yielding: the
 	 * softirq will not be preempted no matter what we do, so we should
-	 * run to completion as quickly as we can.
+	 * run to completion as quickly as we can. The preempt_count field will
+	 * have BIT(SOFTIRQ_SHIFT) set in this case, so the zero check will
+	 * catch this case too.
 	 */
-	tbnz		\tmp, #SOFTIRQ_SHIFT, .Lnoyield_\@
-#ifdef CONFIG_PREEMPTION
-	sub		\tmp, \tmp, #PREEMPT_DISABLE_OFFSET
 	cbz		\tmp, \lbl
 #endif
-	adr_l		\tmp, irq_stat + IRQ_CPUSTAT_SOFTIRQ_PENDING
-	get_this_cpu_offset	\tmp2
-	ldr		w\tmp, [\tmp, \tmp2]
-	cbnz		w\tmp, \lbl	// yield on pending softirq in task context
-.Lnoyield_\@:
 	.endm
 
 /*
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index f3034099fd95..b1e43f56ee46 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -38,7 +38,6 @@ struct cpuinfo_32bit {
 };
 
 struct cpuinfo_arm64 {
-	struct cpu	cpu;
 	struct kobject	kobj;
 	u64		reg_ctr;
 	u64		reg_cntfrq;
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 21c824edf8ce..bd8d4ca81a48 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -83,7 +83,7 @@ struct arm64_ftr_bits {
  * to full-0 denotes that this field has no override
  *
  * A @mask field set to full-0 with the corresponding @val field set
- * to full-1 denotes thath this field has an invalid override.
+ * to full-1 denotes that this field has an invalid override.
  */
 struct arm64_ftr_override {
 	u64		val;
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 7c7493cb571f..52f076afeb96 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -61,6 +61,7 @@
 #define ARM_CPU_IMP_HISI		0x48
 #define ARM_CPU_IMP_APPLE		0x61
 #define ARM_CPU_IMP_AMPERE		0xC0
+#define ARM_CPU_IMP_MICROSOFT		0x6D
 
 #define ARM_CPU_PART_AEM_V8		0xD0F
 #define ARM_CPU_PART_FOUNDATION		0xD00
@@ -135,6 +136,8 @@
 
 #define AMPERE_CPU_PART_AMPERE1		0xAC3
 
+#define MICROSOFT_CPU_PART_AZURE_COBALT_100	0xD49 /* Based on r0p0 of ARM Neoverse N2 */
+
 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
 #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
@@ -193,6 +196,7 @@
 #define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX)
 #define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX)
 #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
+#define MIDR_MICROSOFT_AZURE_COBALT_100 MIDR_CPU_MODEL(ARM_CPU_IMP_MICROSOFT, MICROSOFT_CPU_PART_AZURE_COBALT_100)
 
 /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
 #define MIDR_FUJITSU_ERRATUM_010001		MIDR_FUJITSU_A64FX
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index ae35939f395b..353fe08546cf 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -392,6 +392,21 @@ static inline bool esr_is_data_abort(unsigned long esr)
 	return ec == ESR_ELx_EC_DABT_LOW || ec == ESR_ELx_EC_DABT_CUR;
 }
 
+static inline bool esr_fsc_is_translation_fault(unsigned long esr)
+{
+	return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_FAULT;
+}
+
+static inline bool esr_fsc_is_permission_fault(unsigned long esr)
+{
+	return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_PERM;
+}
+
+static inline bool esr_fsc_is_access_flag_fault(unsigned long esr)
+{
+	return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_ACCESS;
+}
+
 const char *esr_get_class_string(unsigned long esr);
 #endif /* __ASSEMBLY */
 
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 50e5f25d3024..b67b89c54e1c 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -62,13 +62,13 @@ static inline void cpacr_restore(unsigned long cpacr)
  * When we defined the maximum SVE vector length we defined the ABI so
  * that the maximum vector length included all the reserved for future
  * expansion bits in ZCR rather than those just currently defined by
- * the architecture. While SME follows a similar pattern the fact that
- * it includes a square matrix means that any allocations that attempt
- * to cover the maximum potential vector length (such as happen with
- * the regset used for ptrace) end up being extremely large. Define
- * the much lower actual limit for use in such situations.
+ * the architecture.  Using this length to allocate worst size buffers
+ * results in excessively large allocations, and this effect is even
+ * more pronounced for SME due to ZA.  Define more suitable VLs for
+ * these situations.
  */
-#define SME_VQ_MAX	16
+#define ARCH_SVE_VQ_MAX ((ZCR_ELx_LEN_MASK >> ZCR_ELx_LEN_SHIFT) + 1)
+#define SME_VQ_MAX	((SMCR_ELx_LEN_MASK >> SMCR_ELx_LEN_SHIFT) + 1)
 
 struct task_struct;
 
@@ -386,6 +386,7 @@ extern void sme_alloc(struct task_struct *task, bool flush);
 extern unsigned int sme_get_vl(void);
 extern int sme_set_current_vl(unsigned long arg);
 extern int sme_get_current_vl(void);
+extern void sme_suspend_exit(void);
 
 /*
  * Return how many bytes of memory are required to store the full SME
@@ -421,6 +422,7 @@ static inline int sme_max_vl(void) { return 0; }
 static inline int sme_max_virtualisable_vl(void) { return 0; }
 static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; }
 static inline int sme_get_current_vl(void) { return -EINVAL; }
+static inline void sme_suspend_exit(void) { }
 
 static inline size_t sme_state_size(struct task_struct const *task)
 {
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index 50ce8b697ff3..e93548914c36 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -4,6 +4,8 @@
 
 #ifndef __ASSEMBLER__
 
+#include <linux/cpumask.h>
+
 #include <asm-generic/irq.h>
 
 void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu);
diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h
index 48ddc0f45d22..6aafbb789991 100644
--- a/arch/arm64/include/asm/jump_label.h
+++ b/arch/arm64/include/asm/jump_label.h
@@ -18,7 +18,7 @@
 static __always_inline bool arch_static_branch(struct static_key * const key,
 					       const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	nop					\n\t"
 		 "	.pushsection	__jump_table, \"aw\"	\n\t"
 		 "	.align		3			\n\t"
@@ -35,7 +35,7 @@ l_yes:
 static __always_inline bool arch_static_branch_jump(struct static_key * const key,
 						    const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	b		%l[l_yes]		\n\t"
 		 "	.pushsection	__jump_table, \"aw\"	\n\t"
 		 "	.align		3			\n\t"
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index b85f46a73e21..3c6f8ba1e479 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -108,6 +108,7 @@
 #define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En)
 
 /* TCR_EL2 Registers bits */
+#define TCR_EL2_DS		(1UL << 32)
 #define TCR_EL2_RES1		((1U << 31) | (1 << 23))
 #define TCR_EL2_TBI		(1 << 20)
 #define TCR_EL2_PS_SHIFT	16
@@ -122,6 +123,7 @@
 			 TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK | TCR_EL2_T0SZ_MASK)
 
 /* VTCR_EL2 Registers bits */
+#define VTCR_EL2_DS		TCR_EL2_DS
 #define VTCR_EL2_RES1		(1U << 31)
 #define VTCR_EL2_HD		(1 << 22)
 #define VTCR_EL2_HA		(1 << 21)
@@ -344,36 +346,47 @@
  * Once we get to a point where the two describe the same thing, we'll
  * merge the definitions. One day.
  */
-#define __HFGRTR_EL2_RES0	(GENMASK(63, 56) | GENMASK(53, 51))
+#define __HFGRTR_EL2_RES0	HFGxTR_EL2_RES0
 #define __HFGRTR_EL2_MASK	GENMASK(49, 0)
-#define __HFGRTR_EL2_nMASK	(GENMASK(58, 57) | GENMASK(55, 54) | BIT(50))
+#define __HFGRTR_EL2_nMASK	~(__HFGRTR_EL2_RES0 | __HFGRTR_EL2_MASK)
 
-#define __HFGWTR_EL2_RES0	(GENMASK(63, 56) | GENMASK(53, 51) |	\
-				 BIT(46) | BIT(42) | BIT(40) | BIT(28) | \
-				 GENMASK(26, 25) | BIT(21) | BIT(18) |	\
+/*
+ * The HFGWTR bits are a subset of HFGRTR bits. To ensure we don't miss any
+ * future additions, define __HFGWTR* macros relative to __HFGRTR* ones.
+ */
+#define __HFGRTR_ONLY_MASK	(BIT(46) | BIT(42) | BIT(40) | BIT(28) | \
+				 GENMASK(26, 25) | BIT(21) | BIT(18) | \
 				 GENMASK(15, 14) | GENMASK(10, 9) | BIT(2))
-#define __HFGWTR_EL2_MASK	GENMASK(49, 0)
-#define __HFGWTR_EL2_nMASK	(GENMASK(58, 57) | GENMASK(55, 54) | BIT(50))
-
-#define __HFGITR_EL2_RES0	GENMASK(63, 57)
-#define __HFGITR_EL2_MASK	GENMASK(54, 0)
-#define __HFGITR_EL2_nMASK	GENMASK(56, 55)
-
-#define __HDFGRTR_EL2_RES0	(BIT(49) | BIT(42) | GENMASK(39, 38) |	\
-				 GENMASK(21, 20) | BIT(8))
-#define __HDFGRTR_EL2_MASK	~__HDFGRTR_EL2_nMASK
-#define __HDFGRTR_EL2_nMASK	GENMASK(62, 59)
-
-#define __HDFGWTR_EL2_RES0	(BIT(63) | GENMASK(59, 58) | BIT(51) | BIT(47) | \
-				 BIT(43) | GENMASK(40, 38) | BIT(34) | BIT(30) | \
-				 BIT(22) | BIT(9) | BIT(6))
-#define __HDFGWTR_EL2_MASK	~__HDFGWTR_EL2_nMASK
-#define __HDFGWTR_EL2_nMASK	GENMASK(62, 60)
+#define __HFGWTR_EL2_RES0	(__HFGRTR_EL2_RES0 | __HFGRTR_ONLY_MASK)
+#define __HFGWTR_EL2_MASK	(__HFGRTR_EL2_MASK & ~__HFGRTR_ONLY_MASK)
+#define __HFGWTR_EL2_nMASK	~(__HFGWTR_EL2_RES0 | __HFGWTR_EL2_MASK)
+
+#define __HFGITR_EL2_RES0	HFGITR_EL2_RES0
+#define __HFGITR_EL2_MASK	(BIT(62) | BIT(60) | GENMASK(54, 0))
+#define __HFGITR_EL2_nMASK	~(__HFGITR_EL2_RES0 | __HFGITR_EL2_MASK)
+
+#define __HDFGRTR_EL2_RES0	HDFGRTR_EL2_RES0
+#define __HDFGRTR_EL2_MASK	(BIT(63) | GENMASK(58, 50) | GENMASK(48, 43) | \
+				 GENMASK(41, 40) | GENMASK(37, 22) | \
+				 GENMASK(19, 9) | GENMASK(7, 0))
+#define __HDFGRTR_EL2_nMASK	~(__HDFGRTR_EL2_RES0 | __HDFGRTR_EL2_MASK)
+
+#define __HDFGWTR_EL2_RES0	HDFGWTR_EL2_RES0
+#define __HDFGWTR_EL2_MASK	(GENMASK(57, 52) | GENMASK(50, 48) | \
+				 GENMASK(46, 44) | GENMASK(42, 41) | \
+				 GENMASK(37, 35) | GENMASK(33, 31) | \
+				 GENMASK(29, 23) | GENMASK(21, 10) | \
+				 GENMASK(8, 7) | GENMASK(5, 0))
+#define __HDFGWTR_EL2_nMASK	~(__HDFGWTR_EL2_RES0 | __HDFGWTR_EL2_MASK)
+
+#define __HAFGRTR_EL2_RES0	HAFGRTR_EL2_RES0
+#define __HAFGRTR_EL2_MASK	(GENMASK(49, 17) | GENMASK(4, 0))
+#define __HAFGRTR_EL2_nMASK	~(__HAFGRTR_EL2_RES0 | __HAFGRTR_EL2_MASK)
 
 /* Similar definitions for HCRX_EL2 */
-#define __HCRX_EL2_RES0		(GENMASK(63, 16) | GENMASK(13, 12))
-#define __HCRX_EL2_MASK		(0)
-#define __HCRX_EL2_nMASK	(GENMASK(15, 14) | GENMASK(4, 0))
+#define __HCRX_EL2_RES0         HCRX_EL2_RES0
+#define __HCRX_EL2_MASK		(BIT(6))
+#define __HCRX_EL2_nMASK	~(__HCRX_EL2_RES0 | __HCRX_EL2_MASK)
 
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
 #define HPFAR_MASK	(~UL(0xf))
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 78a550537b67..b804fe832184 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -17,6 +17,7 @@
 #include <asm/esr.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_hyp.h>
+#include <asm/kvm_nested.h>
 #include <asm/ptrace.h>
 #include <asm/cputype.h>
 #include <asm/virt.h>
@@ -54,11 +55,6 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu);
 int kvm_inject_nested_sync(struct kvm_vcpu *vcpu, u64 esr_el2);
 int kvm_inject_nested_irq(struct kvm_vcpu *vcpu);
 
-static inline bool vcpu_has_feature(const struct kvm_vcpu *vcpu, int feature)
-{
-	return test_bit(feature, vcpu->kvm->arch.vcpu_features);
-}
-
 #if defined(__KVM_VHE_HYPERVISOR__) || defined(__KVM_NVHE_HYPERVISOR__)
 static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
 {
@@ -248,7 +244,7 @@ static inline bool __is_hyp_ctxt(const struct kvm_cpu_context *ctxt)
 
 static inline bool is_hyp_ctxt(const struct kvm_vcpu *vcpu)
 {
-	return __is_hyp_ctxt(&vcpu->arch.ctxt);
+	return vcpu_has_nv(vcpu) && __is_hyp_ctxt(&vcpu->arch.ctxt);
 }
 
 /*
@@ -404,14 +400,25 @@ static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
 	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC;
 }
 
-static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu)
+static inline
+bool kvm_vcpu_trap_is_permission_fault(const struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_TYPE;
+	return esr_fsc_is_permission_fault(kvm_vcpu_get_esr(vcpu));
 }
 
-static __always_inline u8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *vcpu)
+static inline
+bool kvm_vcpu_trap_is_translation_fault(const struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_LEVEL;
+	return esr_fsc_is_translation_fault(kvm_vcpu_get_esr(vcpu));
+}
+
+static inline
+u64 kvm_vcpu_trap_get_perm_fault_granule(const struct kvm_vcpu *vcpu)
+{
+	unsigned long esr = kvm_vcpu_get_esr(vcpu);
+
+	BUG_ON(!esr_fsc_is_permission_fault(esr));
+	return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(esr & ESR_ELx_FSC_LEVEL));
 }
 
 static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
@@ -454,12 +461,7 @@ static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
 		 * first), then a permission fault to allow the flags
 		 * to be set.
 		 */
-		switch (kvm_vcpu_trap_get_fault_type(vcpu)) {
-		case ESR_ELx_FSC_PERM:
-			return true;
-		default:
-			return false;
-		}
+		return kvm_vcpu_trap_is_permission_fault(vcpu);
 	}
 
 	if (kvm_vcpu_trap_is_iabt(vcpu))
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 824f29f04916..21c57b812569 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -27,6 +27,7 @@
 #include <asm/fpsimd.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
+#include <asm/vncr_mapping.h>
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
@@ -306,6 +307,7 @@ struct kvm_arch {
 	 * Atomic access to multiple idregs are guarded by kvm_arch.config_lock.
 	 */
 #define IDREG_IDX(id)		(((sys_reg_CRm(id) - 1) << 3) | sys_reg_Op2(id))
+#define IDX_IDREG(idx)		sys_reg(3, 0, 0, ((idx) >> 3) + 1, (idx) & Op2_mask)
 #define IDREG(kvm, id)		((kvm)->arch.id_regs[IDREG_IDX(id)])
 #define KVM_ARM_ID_REG_NUM	(IDREG_IDX(sys_reg(3, 0, 0, 7, 7)) + 1)
 	u64 id_regs[KVM_ARM_ID_REG_NUM];
@@ -324,33 +326,33 @@ struct kvm_vcpu_fault_info {
 	u64 disr_el1;		/* Deferred [SError] Status Register */
 };
 
+/*
+ * VNCR() just places the VNCR_capable registers in the enum after
+ * __VNCR_START__, and the value (after correction) to be an 8-byte offset
+ * from the VNCR base. As we don't require the enum to be otherwise ordered,
+ * we need the terrible hack below to ensure that we correctly size the
+ * sys_regs array, no matter what.
+ *
+ * The __MAX__ macro has been lifted from Sean Eron Anderson's wonderful
+ * treasure trove of bit hacks:
+ * https://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
+ */
+#define __MAX__(x,y)	((x) ^ (((x) ^ (y)) & -((x) < (y))))
+#define VNCR(r)						\
+	__before_##r,					\
+	r = __VNCR_START__ + ((VNCR_ ## r) / 8),	\
+	__after_##r = __MAX__(__before_##r - 1, r)
+
 enum vcpu_sysreg {
 	__INVALID_SYSREG__,   /* 0 is reserved as an invalid value */
 	MPIDR_EL1,	/* MultiProcessor Affinity Register */
 	CLIDR_EL1,	/* Cache Level ID Register */
 	CSSELR_EL1,	/* Cache Size Selection Register */
-	SCTLR_EL1,	/* System Control Register */
-	ACTLR_EL1,	/* Auxiliary Control Register */
-	CPACR_EL1,	/* Coprocessor Access Control */
-	ZCR_EL1,	/* SVE Control */
-	TTBR0_EL1,	/* Translation Table Base Register 0 */
-	TTBR1_EL1,	/* Translation Table Base Register 1 */
-	TCR_EL1,	/* Translation Control Register */
-	TCR2_EL1,	/* Extended Translation Control Register */
-	ESR_EL1,	/* Exception Syndrome Register */
-	AFSR0_EL1,	/* Auxiliary Fault Status Register 0 */
-	AFSR1_EL1,	/* Auxiliary Fault Status Register 1 */
-	FAR_EL1,	/* Fault Address Register */
-	MAIR_EL1,	/* Memory Attribute Indirection Register */
-	VBAR_EL1,	/* Vector Base Address Register */
-	CONTEXTIDR_EL1,	/* Context ID Register */
 	TPIDR_EL0,	/* Thread ID, User R/W */
 	TPIDRRO_EL0,	/* Thread ID, User R/O */
 	TPIDR_EL1,	/* Thread ID, Privileged */
-	AMAIR_EL1,	/* Aux Memory Attribute Indirection Register */
 	CNTKCTL_EL1,	/* Timer Control Register (EL1) */
 	PAR_EL1,	/* Physical Address Register */
-	MDSCR_EL1,	/* Monitor Debug System Control Register */
 	MDCCINT_EL1,	/* Monitor Debug Comms Channel Interrupt Enable Reg */
 	OSLSR_EL1,	/* OS Lock Status Register */
 	DISR_EL1,	/* Deferred Interrupt Status Register */
@@ -381,26 +383,11 @@ enum vcpu_sysreg {
 	APGAKEYLO_EL1,
 	APGAKEYHI_EL1,
 
-	ELR_EL1,
-	SP_EL1,
-	SPSR_EL1,
-
-	CNTVOFF_EL2,
-	CNTV_CVAL_EL0,
-	CNTV_CTL_EL0,
-	CNTP_CVAL_EL0,
-	CNTP_CTL_EL0,
-
 	/* Memory Tagging Extension registers */
 	RGSR_EL1,	/* Random Allocation Tag Seed Register */
 	GCR_EL1,	/* Tag Control Register */
-	TFSR_EL1,	/* Tag Fault Status Register (EL1) */
 	TFSRE0_EL1,	/* Tag Fault Status Register (EL0) */
 
-	/* Permission Indirection Extension registers */
-	PIR_EL1,       /* Permission Indirection Register 1 (EL1) */
-	PIRE0_EL1,     /*  Permission Indirection Register 0 (EL1) */
-
 	/* 32bit specific registers. */
 	DACR32_EL2,	/* Domain Access Control Register */
 	IFSR32_EL2,	/* Instruction Fault Status Register */
@@ -408,21 +395,14 @@ enum vcpu_sysreg {
 	DBGVCR32_EL2,	/* Debug Vector Catch Register */
 
 	/* EL2 registers */
-	VPIDR_EL2,	/* Virtualization Processor ID Register */
-	VMPIDR_EL2,	/* Virtualization Multiprocessor ID Register */
 	SCTLR_EL2,	/* System Control Register (EL2) */
 	ACTLR_EL2,	/* Auxiliary Control Register (EL2) */
-	HCR_EL2,	/* Hypervisor Configuration Register */
 	MDCR_EL2,	/* Monitor Debug Configuration Register (EL2) */
 	CPTR_EL2,	/* Architectural Feature Trap Register (EL2) */
-	HSTR_EL2,	/* Hypervisor System Trap Register */
 	HACR_EL2,	/* Hypervisor Auxiliary Control Register */
-	HCRX_EL2,	/* Extended Hypervisor Configuration Register */
 	TTBR0_EL2,	/* Translation Table Base Register 0 (EL2) */
 	TTBR1_EL2,	/* Translation Table Base Register 1 (EL2) */
 	TCR_EL2,	/* Translation Control Register (EL2) */
-	VTTBR_EL2,	/* Virtualization Translation Table Base Register */
-	VTCR_EL2,	/* Virtualization Translation Control Register */
 	SPSR_EL2,	/* EL2 saved program status register */
 	ELR_EL2,	/* EL2 exception link register */
 	AFSR0_EL2,	/* Auxiliary Fault Status Register 0 (EL2) */
@@ -435,19 +415,62 @@ enum vcpu_sysreg {
 	VBAR_EL2,	/* Vector Base Address Register (EL2) */
 	RVBAR_EL2,	/* Reset Vector Base Address Register */
 	CONTEXTIDR_EL2,	/* Context ID Register (EL2) */
-	TPIDR_EL2,	/* EL2 Software Thread ID Register */
 	CNTHCTL_EL2,	/* Counter-timer Hypervisor Control register */
 	SP_EL2,		/* EL2 Stack Pointer */
-	HFGRTR_EL2,
-	HFGWTR_EL2,
-	HFGITR_EL2,
-	HDFGRTR_EL2,
-	HDFGWTR_EL2,
 	CNTHP_CTL_EL2,
 	CNTHP_CVAL_EL2,
 	CNTHV_CTL_EL2,
 	CNTHV_CVAL_EL2,
 
+	__VNCR_START__,	/* Any VNCR-capable reg goes after this point */
+
+	VNCR(SCTLR_EL1),/* System Control Register */
+	VNCR(ACTLR_EL1),/* Auxiliary Control Register */
+	VNCR(CPACR_EL1),/* Coprocessor Access Control */
+	VNCR(ZCR_EL1),	/* SVE Control */
+	VNCR(TTBR0_EL1),/* Translation Table Base Register 0 */
+	VNCR(TTBR1_EL1),/* Translation Table Base Register 1 */
+	VNCR(TCR_EL1),	/* Translation Control Register */
+	VNCR(TCR2_EL1),	/* Extended Translation Control Register */
+	VNCR(ESR_EL1),	/* Exception Syndrome Register */
+	VNCR(AFSR0_EL1),/* Auxiliary Fault Status Register 0 */
+	VNCR(AFSR1_EL1),/* Auxiliary Fault Status Register 1 */
+	VNCR(FAR_EL1),	/* Fault Address Register */
+	VNCR(MAIR_EL1),	/* Memory Attribute Indirection Register */
+	VNCR(VBAR_EL1),	/* Vector Base Address Register */
+	VNCR(CONTEXTIDR_EL1),	/* Context ID Register */
+	VNCR(AMAIR_EL1),/* Aux Memory Attribute Indirection Register */
+	VNCR(MDSCR_EL1),/* Monitor Debug System Control Register */
+	VNCR(ELR_EL1),
+	VNCR(SP_EL1),
+	VNCR(SPSR_EL1),
+	VNCR(TFSR_EL1),	/* Tag Fault Status Register (EL1) */
+	VNCR(VPIDR_EL2),/* Virtualization Processor ID Register */
+	VNCR(VMPIDR_EL2),/* Virtualization Multiprocessor ID Register */
+	VNCR(HCR_EL2),	/* Hypervisor Configuration Register */
+	VNCR(HSTR_EL2),	/* Hypervisor System Trap Register */
+	VNCR(VTTBR_EL2),/* Virtualization Translation Table Base Register */
+	VNCR(VTCR_EL2),	/* Virtualization Translation Control Register */
+	VNCR(TPIDR_EL2),/* EL2 Software Thread ID Register */
+	VNCR(HCRX_EL2),	/* Extended Hypervisor Configuration Register */
+
+	/* Permission Indirection Extension registers */
+	VNCR(PIR_EL1),	 /* Permission Indirection Register 1 (EL1) */
+	VNCR(PIRE0_EL1), /*  Permission Indirection Register 0 (EL1) */
+
+	VNCR(HFGRTR_EL2),
+	VNCR(HFGWTR_EL2),
+	VNCR(HFGITR_EL2),
+	VNCR(HDFGRTR_EL2),
+	VNCR(HDFGWTR_EL2),
+	VNCR(HAFGRTR_EL2),
+
+	VNCR(CNTVOFF_EL2),
+	VNCR(CNTV_CVAL_EL0),
+	VNCR(CNTV_CTL_EL0),
+	VNCR(CNTP_CVAL_EL0),
+	VNCR(CNTP_CTL_EL0),
+
 	NR_SYS_REGS	/* Nothing after this line! */
 };
 
@@ -464,6 +487,9 @@ struct kvm_cpu_context {
 	u64 sys_regs[NR_SYS_REGS];
 
 	struct kvm_vcpu *__hyp_running_vcpu;
+
+	/* This pointer has to be 4kB aligned. */
+	u64 *vncr_array;
 };
 
 struct kvm_host_data {
@@ -826,8 +852,19 @@ struct kvm_vcpu_arch {
  * accessed by a running VCPU.  For example, for userspace access or
  * for system registers that are never context switched, but only
  * emulated.
+ *
+ * Don't bother with VNCR-based accesses in the nVHE code, it has no
+ * business dealing with NV.
  */
-#define __ctxt_sys_reg(c,r)	(&(c)->sys_regs[(r)])
+static inline u64 *__ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r)
+{
+#if !defined (__KVM_NVHE_HYPERVISOR__)
+	if (unlikely(cpus_have_final_cap(ARM64_HAS_NESTED_VIRT) &&
+		     r >= __VNCR_START__ && ctxt->vncr_array))
+		return &ctxt->vncr_array[r - __VNCR_START__];
+#endif
+	return (u64 *)&ctxt->sys_regs[r];
+}
 
 #define ctxt_sys_reg(c,r)	(*__ctxt_sys_reg(c,r))
 
@@ -871,6 +908,7 @@ static inline bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val)
 	case AMAIR_EL1:		*val = read_sysreg_s(SYS_AMAIR_EL12);	break;
 	case CNTKCTL_EL1:	*val = read_sysreg_s(SYS_CNTKCTL_EL12);	break;
 	case ELR_EL1:		*val = read_sysreg_s(SYS_ELR_EL12);	break;
+	case SPSR_EL1:		*val = read_sysreg_s(SYS_SPSR_EL12);	break;
 	case PAR_EL1:		*val = read_sysreg_par();		break;
 	case DACR32_EL2:	*val = read_sysreg_s(SYS_DACR32_EL2);	break;
 	case IFSR32_EL2:	*val = read_sysreg_s(SYS_IFSR32_EL2);	break;
@@ -915,6 +953,7 @@ static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg)
 	case AMAIR_EL1:		write_sysreg_s(val, SYS_AMAIR_EL12);	break;
 	case CNTKCTL_EL1:	write_sysreg_s(val, SYS_CNTKCTL_EL12);	break;
 	case ELR_EL1:		write_sysreg_s(val, SYS_ELR_EL12);	break;
+	case SPSR_EL1:		write_sysreg_s(val, SYS_SPSR_EL12);	break;
 	case PAR_EL1:		write_sysreg_s(val, SYS_PAR_EL1);	break;
 	case DACR32_EL2:	write_sysreg_s(val, SYS_DACR32_EL2);	break;
 	case IFSR32_EL2:	write_sysreg_s(val, SYS_IFSR32_EL2);	break;
@@ -954,8 +993,6 @@ int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu,
 int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
 			      struct kvm_vcpu_events *events);
 
-#define KVM_ARCH_WANT_MMU_NOTIFIER
-
 void kvm_arm_halt_guest(struct kvm *kvm);
 void kvm_arm_resume_guest(struct kvm *kvm);
 
@@ -1177,6 +1214,13 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
 #define kvm_vm_has_ran_once(kvm)					\
 	(test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &(kvm)->arch.flags))
 
+static inline bool __vcpu_has_feature(const struct kvm_arch *ka, int feature)
+{
+	return test_bit(feature, ka->vcpu_features);
+}
+
+#define vcpu_has_feature(v, f)	__vcpu_has_feature(&(v)->kvm->arch, (f))
+
 int kvm_trng_call(struct kvm_vcpu *vcpu);
 #ifdef CONFIG_KVM
 extern phys_addr_t hyp_mem_base;
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 6cec8e9c6c91..4882905357f4 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -2,8 +2,9 @@
 #ifndef __ARM64_KVM_NESTED_H
 #define __ARM64_KVM_NESTED_H
 
-#include <asm/kvm_emulate.h>
+#include <linux/bitfield.h>
 #include <linux/kvm_host.h>
+#include <asm/kvm_emulate.h>
 
 static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu)
 {
@@ -12,12 +13,55 @@ static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu)
 		vcpu_has_feature(vcpu, KVM_ARM_VCPU_HAS_EL2));
 }
 
-extern bool __check_nv_sr_forward(struct kvm_vcpu *vcpu);
+/* Translation helpers from non-VHE EL2 to EL1 */
+static inline u64 tcr_el2_ps_to_tcr_el1_ips(u64 tcr_el2)
+{
+	return (u64)FIELD_GET(TCR_EL2_PS_MASK, tcr_el2) << TCR_IPS_SHIFT;
+}
+
+static inline u64 translate_tcr_el2_to_tcr_el1(u64 tcr)
+{
+	return TCR_EPD1_MASK |				/* disable TTBR1_EL1 */
+	       ((tcr & TCR_EL2_TBI) ? TCR_TBI0 : 0) |
+	       tcr_el2_ps_to_tcr_el1_ips(tcr) |
+	       (tcr & TCR_EL2_TG0_MASK) |
+	       (tcr & TCR_EL2_ORGN0_MASK) |
+	       (tcr & TCR_EL2_IRGN0_MASK) |
+	       (tcr & TCR_EL2_T0SZ_MASK);
+}
+
+static inline u64 translate_cptr_el2_to_cpacr_el1(u64 cptr_el2)
+{
+	u64 cpacr_el1 = 0;
+
+	if (cptr_el2 & CPTR_EL2_TTA)
+		cpacr_el1 |= CPACR_ELx_TTA;
+	if (!(cptr_el2 & CPTR_EL2_TFP))
+		cpacr_el1 |= CPACR_ELx_FPEN;
+	if (!(cptr_el2 & CPTR_EL2_TZ))
+		cpacr_el1 |= CPACR_ELx_ZEN;
 
-struct sys_reg_params;
-struct sys_reg_desc;
+	return cpacr_el1;
+}
+
+static inline u64 translate_sctlr_el2_to_sctlr_el1(u64 val)
+{
+	/* Only preserve the minimal set of bits we support */
+	val &= (SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | SCTLR_ELx_SA |
+		SCTLR_ELx_I | SCTLR_ELx_IESB | SCTLR_ELx_WXN | SCTLR_ELx_EE);
+	val |= SCTLR_EL1_RES1;
+
+	return val;
+}
+
+static inline u64 translate_ttbr0_el2_to_ttbr0_el1(u64 ttbr0)
+{
+	/* Clear the ASID field */
+	return ttbr0 & ~GENMASK_ULL(63, 48);
+}
+
+extern bool __check_nv_sr_forward(struct kvm_vcpu *vcpu);
 
-void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p,
-			  const struct sys_reg_desc *r);
+int kvm_init_nv_sysregs(struct kvm *kvm);
 
 #endif /* __ARM64_KVM_NESTED_H */
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 10068500d601..cfdf40f734b1 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -11,7 +11,8 @@
 #include <linux/kvm_host.h>
 #include <linux/types.h>
 
-#define KVM_PGTABLE_MAX_LEVELS		4U
+#define KVM_PGTABLE_FIRST_LEVEL		-1
+#define KVM_PGTABLE_LAST_LEVEL		3
 
 /*
  * The largest supported block sizes for KVM (no 52-bit PA support):
@@ -20,19 +21,29 @@
  *  - 64K (level 2):	512MB
  */
 #ifdef CONFIG_ARM64_4K_PAGES
-#define KVM_PGTABLE_MIN_BLOCK_LEVEL	1U
+#define KVM_PGTABLE_MIN_BLOCK_LEVEL	1
 #else
-#define KVM_PGTABLE_MIN_BLOCK_LEVEL	2U
+#define KVM_PGTABLE_MIN_BLOCK_LEVEL	2
 #endif
 
-#define kvm_lpa2_is_enabled()		false
+#define kvm_lpa2_is_enabled()		system_supports_lpa2()
+
+static inline u64 kvm_get_parange_max(void)
+{
+	if (kvm_lpa2_is_enabled() ||
+	   (IS_ENABLED(CONFIG_ARM64_PA_BITS_52) && PAGE_SHIFT == 16))
+		return ID_AA64MMFR0_EL1_PARANGE_52;
+	else
+		return ID_AA64MMFR0_EL1_PARANGE_48;
+}
 
 static inline u64 kvm_get_parange(u64 mmfr0)
 {
+	u64 parange_max = kvm_get_parange_max();
 	u64 parange = cpuid_feature_extract_unsigned_field(mmfr0,
 				ID_AA64MMFR0_EL1_PARANGE_SHIFT);
-	if (parange > ID_AA64MMFR0_EL1_PARANGE_MAX)
-		parange = ID_AA64MMFR0_EL1_PARANGE_MAX;
+	if (parange > parange_max)
+		parange = parange_max;
 
 	return parange;
 }
@@ -43,6 +54,8 @@ typedef u64 kvm_pte_t;
 
 #define KVM_PTE_ADDR_MASK		GENMASK(47, PAGE_SHIFT)
 #define KVM_PTE_ADDR_51_48		GENMASK(15, 12)
+#define KVM_PTE_ADDR_MASK_LPA2		GENMASK(49, PAGE_SHIFT)
+#define KVM_PTE_ADDR_51_50_LPA2		GENMASK(9, 8)
 
 #define KVM_PHYS_INVALID		(-1ULL)
 
@@ -53,21 +66,34 @@ static inline bool kvm_pte_valid(kvm_pte_t pte)
 
 static inline u64 kvm_pte_to_phys(kvm_pte_t pte)
 {
-	u64 pa = pte & KVM_PTE_ADDR_MASK;
-
-	if (PAGE_SHIFT == 16)
-		pa |= FIELD_GET(KVM_PTE_ADDR_51_48, pte) << 48;
+	u64 pa;
+
+	if (kvm_lpa2_is_enabled()) {
+		pa = pte & KVM_PTE_ADDR_MASK_LPA2;
+		pa |= FIELD_GET(KVM_PTE_ADDR_51_50_LPA2, pte) << 50;
+	} else {
+		pa = pte & KVM_PTE_ADDR_MASK;
+		if (PAGE_SHIFT == 16)
+			pa |= FIELD_GET(KVM_PTE_ADDR_51_48, pte) << 48;
+	}
 
 	return pa;
 }
 
 static inline kvm_pte_t kvm_phys_to_pte(u64 pa)
 {
-	kvm_pte_t pte = pa & KVM_PTE_ADDR_MASK;
-
-	if (PAGE_SHIFT == 16) {
-		pa &= GENMASK(51, 48);
-		pte |= FIELD_PREP(KVM_PTE_ADDR_51_48, pa >> 48);
+	kvm_pte_t pte;
+
+	if (kvm_lpa2_is_enabled()) {
+		pte = pa & KVM_PTE_ADDR_MASK_LPA2;
+		pa &= GENMASK(51, 50);
+		pte |= FIELD_PREP(KVM_PTE_ADDR_51_50_LPA2, pa >> 50);
+	} else {
+		pte = pa & KVM_PTE_ADDR_MASK;
+		if (PAGE_SHIFT == 16) {
+			pa &= GENMASK(51, 48);
+			pte |= FIELD_PREP(KVM_PTE_ADDR_51_48, pa >> 48);
+		}
 	}
 
 	return pte;
@@ -78,28 +104,28 @@ static inline kvm_pfn_t kvm_pte_to_pfn(kvm_pte_t pte)
 	return __phys_to_pfn(kvm_pte_to_phys(pte));
 }
 
-static inline u64 kvm_granule_shift(u32 level)
+static inline u64 kvm_granule_shift(s8 level)
 {
-	/* Assumes KVM_PGTABLE_MAX_LEVELS is 4 */
+	/* Assumes KVM_PGTABLE_LAST_LEVEL is 3 */
 	return ARM64_HW_PGTABLE_LEVEL_SHIFT(level);
 }
 
-static inline u64 kvm_granule_size(u32 level)
+static inline u64 kvm_granule_size(s8 level)
 {
 	return BIT(kvm_granule_shift(level));
 }
 
-static inline bool kvm_level_supports_block_mapping(u32 level)
+static inline bool kvm_level_supports_block_mapping(s8 level)
 {
 	return level >= KVM_PGTABLE_MIN_BLOCK_LEVEL;
 }
 
 static inline u32 kvm_supported_block_sizes(void)
 {
-	u32 level = KVM_PGTABLE_MIN_BLOCK_LEVEL;
+	s8 level = KVM_PGTABLE_MIN_BLOCK_LEVEL;
 	u32 r = 0;
 
-	for (; level < KVM_PGTABLE_MAX_LEVELS; level++)
+	for (; level <= KVM_PGTABLE_LAST_LEVEL; level++)
 		r |= BIT(kvm_granule_shift(level));
 
 	return r;
@@ -144,7 +170,7 @@ struct kvm_pgtable_mm_ops {
 	void*		(*zalloc_page)(void *arg);
 	void*		(*zalloc_pages_exact)(size_t size);
 	void		(*free_pages_exact)(void *addr, size_t size);
-	void		(*free_unlinked_table)(void *addr, u32 level);
+	void		(*free_unlinked_table)(void *addr, s8 level);
 	void		(*get_page)(void *addr);
 	void		(*put_page)(void *addr);
 	int		(*page_count)(void *addr);
@@ -240,7 +266,7 @@ struct kvm_pgtable_visit_ctx {
 	u64					start;
 	u64					addr;
 	u64					end;
-	u32					level;
+	s8					level;
 	enum kvm_pgtable_walk_flags		flags;
 };
 
@@ -343,7 +369,7 @@ static inline bool kvm_pgtable_walk_lock_held(void)
  */
 struct kvm_pgtable {
 	u32					ia_bits;
-	u32					start_level;
+	s8					start_level;
 	kvm_pteref_t				pgd;
 	struct kvm_pgtable_mm_ops		*mm_ops;
 
@@ -477,7 +503,7 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
  * The page-table is assumed to be unreachable by any hardware walkers prior to
  * freeing and therefore no TLB invalidation is performed.
  */
-void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level);
+void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level);
 
 /**
  * kvm_pgtable_stage2_create_unlinked() - Create an unlinked stage-2 paging structure.
@@ -501,7 +527,7 @@ void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *p
  * an ERR_PTR(error) on failure.
  */
 kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
-					      u64 phys, u32 level,
+					      u64 phys, s8 level,
 					      enum kvm_pgtable_prot prot,
 					      void *mc, bool force_pte);
 
@@ -727,7 +753,7 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
  * Return: 0 on success, negative error code on failure.
  */
 int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
-			 kvm_pte_t *ptep, u32 *level);
+			 kvm_pte_t *ptep, s8 *level);
 
 /**
  * kvm_pgtable_stage2_pte_prot() - Retrieve the protection attributes of a
diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
index e46250a02017..ad9cfb5c1ff4 100644
--- a/arch/arm64/include/asm/kvm_pkvm.h
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -56,10 +56,11 @@ static inline unsigned long hyp_vm_table_pages(void)
 
 static inline unsigned long __hyp_pgtable_max_pages(unsigned long nr_pages)
 {
-	unsigned long total = 0, i;
+	unsigned long total = 0;
+	int i;
 
 	/* Provision the worst case scenario */
-	for (i = 0; i < KVM_PGTABLE_MAX_LEVELS; i++) {
+	for (i = KVM_PGTABLE_FIRST_LEVEL; i <= KVM_PGTABLE_LAST_LEVEL; i++) {
 		nr_pages = DIV_ROUND_UP(nr_pages, PTRS_PER_PTE);
 		total += nr_pages;
 	}
diff --git a/arch/arm64/include/asm/vdso.h b/arch/arm64/include/asm/vdso.h
index b4ae32109932..4305995c8f82 100644
--- a/arch/arm64/include/asm/vdso.h
+++ b/arch/arm64/include/asm/vdso.h
@@ -17,9 +17,6 @@
 #ifndef __ASSEMBLY__
 
 #include <generated/vdso-offsets.h>
-#ifdef CONFIG_COMPAT_VDSO
-#include <generated/vdso32-offsets.h>
-#endif
 
 #define VDSO_SYMBOL(base, name)						   \
 ({									   \
diff --git a/arch/arm64/include/asm/vncr_mapping.h b/arch/arm64/include/asm/vncr_mapping.h
new file mode 100644
index 000000000000..df2c47c55972
--- /dev/null
+++ b/arch/arm64/include/asm/vncr_mapping.h
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * System register offsets in the VNCR page
+ * All offsets are *byte* displacements!
+ */
+
+#ifndef __ARM64_VNCR_MAPPING_H__
+#define __ARM64_VNCR_MAPPING_H__
+
+#define VNCR_VTTBR_EL2          0x020
+#define VNCR_VTCR_EL2           0x040
+#define VNCR_VMPIDR_EL2         0x050
+#define VNCR_CNTVOFF_EL2        0x060
+#define VNCR_HCR_EL2            0x078
+#define VNCR_HSTR_EL2           0x080
+#define VNCR_VPIDR_EL2          0x088
+#define VNCR_TPIDR_EL2          0x090
+#define VNCR_HCRX_EL2           0x0A0
+#define VNCR_VNCR_EL2           0x0B0
+#define VNCR_CPACR_EL1          0x100
+#define VNCR_CONTEXTIDR_EL1     0x108
+#define VNCR_SCTLR_EL1          0x110
+#define VNCR_ACTLR_EL1          0x118
+#define VNCR_TCR_EL1            0x120
+#define VNCR_AFSR0_EL1          0x128
+#define VNCR_AFSR1_EL1          0x130
+#define VNCR_ESR_EL1            0x138
+#define VNCR_MAIR_EL1           0x140
+#define VNCR_AMAIR_EL1          0x148
+#define VNCR_MDSCR_EL1          0x158
+#define VNCR_SPSR_EL1           0x160
+#define VNCR_CNTV_CVAL_EL0      0x168
+#define VNCR_CNTV_CTL_EL0       0x170
+#define VNCR_CNTP_CVAL_EL0      0x178
+#define VNCR_CNTP_CTL_EL0       0x180
+#define VNCR_SCXTNUM_EL1        0x188
+#define VNCR_TFSR_EL1		0x190
+#define VNCR_HFGRTR_EL2		0x1B8
+#define VNCR_HFGWTR_EL2		0x1C0
+#define VNCR_HFGITR_EL2		0x1C8
+#define VNCR_HDFGRTR_EL2	0x1D0
+#define VNCR_HDFGWTR_EL2	0x1D8
+#define VNCR_ZCR_EL1            0x1E0
+#define VNCR_HAFGRTR_EL2	0x1E8
+#define VNCR_TTBR0_EL1          0x200
+#define VNCR_TTBR1_EL1          0x210
+#define VNCR_FAR_EL1            0x220
+#define VNCR_ELR_EL1            0x230
+#define VNCR_SP_EL1             0x240
+#define VNCR_VBAR_EL1           0x250
+#define VNCR_TCR2_EL1		0x270
+#define VNCR_PIRE0_EL1		0x290
+#define VNCR_PIRE0_EL2		0x298
+#define VNCR_PIR_EL1		0x2A0
+#define VNCR_ICH_LR0_EL2        0x400
+#define VNCR_ICH_LR1_EL2        0x408
+#define VNCR_ICH_LR2_EL2        0x410
+#define VNCR_ICH_LR3_EL2        0x418
+#define VNCR_ICH_LR4_EL2        0x420
+#define VNCR_ICH_LR5_EL2        0x428
+#define VNCR_ICH_LR6_EL2        0x430
+#define VNCR_ICH_LR7_EL2        0x438
+#define VNCR_ICH_LR8_EL2        0x440
+#define VNCR_ICH_LR9_EL2        0x448
+#define VNCR_ICH_LR10_EL2       0x450
+#define VNCR_ICH_LR11_EL2       0x458
+#define VNCR_ICH_LR12_EL2       0x460
+#define VNCR_ICH_LR13_EL2       0x468
+#define VNCR_ICH_LR14_EL2       0x470
+#define VNCR_ICH_LR15_EL2       0x478
+#define VNCR_ICH_AP0R0_EL2      0x480
+#define VNCR_ICH_AP0R1_EL2      0x488
+#define VNCR_ICH_AP0R2_EL2      0x490
+#define VNCR_ICH_AP0R3_EL2      0x498
+#define VNCR_ICH_AP1R0_EL2      0x4A0
+#define VNCR_ICH_AP1R1_EL2      0x4A8
+#define VNCR_ICH_AP1R2_EL2      0x4B0
+#define VNCR_ICH_AP1R3_EL2      0x4B8
+#define VNCR_ICH_HCR_EL2        0x4C0
+#define VNCR_ICH_VMCR_EL2       0x4C8
+#define VNCR_VDISR_EL2          0x500
+#define VNCR_PMBLIMITR_EL1      0x800
+#define VNCR_PMBPTR_EL1         0x810
+#define VNCR_PMBSR_EL1          0x820
+#define VNCR_PMSCR_EL1          0x828
+#define VNCR_PMSEVFR_EL1        0x830
+#define VNCR_PMSICR_EL1         0x838
+#define VNCR_PMSIRR_EL1         0x840
+#define VNCR_PMSLATFR_EL1       0x848
+#define VNCR_TRFCR_EL1          0x880
+#define VNCR_MPAM1_EL1          0x900
+#define VNCR_MPAMHCR_EL2        0x930
+#define VNCR_MPAMVPMV_EL2       0x938
+#define VNCR_MPAMVPM0_EL2       0x940
+#define VNCR_MPAMVPM1_EL2       0x948
+#define VNCR_MPAMVPM2_EL2       0x950
+#define VNCR_MPAMVPM3_EL2       0x958
+#define VNCR_MPAMVPM4_EL2       0x960
+#define VNCR_MPAMVPM5_EL2       0x968
+#define VNCR_MPAMVPM6_EL2       0x970
+#define VNCR_MPAMVPM7_EL2       0x978
+
+#endif /* __ARM64_VNCR_MAPPING_H__ */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index d95b3d6b471a..467cb7117273 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -73,7 +73,13 @@ obj-$(CONFIG_ARM64_MTE)			+= mte.o
 obj-y					+= vdso-wrap.o
 obj-$(CONFIG_COMPAT_VDSO)		+= vdso32-wrap.o
 obj-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS)	+= patch-scs.o
+
+# We need to prevent the SCS patching code from patching itself. Using
+# -mbranch-protection=none here to avoid the patchable PAC opcodes from being
+# generated triggers an issue with full LTO on Clang, which stops emitting PAC
+# instructions altogether. So disable LTO as well for the compilation unit.
 CFLAGS_patch-scs.o			+= -mbranch-protection=none
+CFLAGS_REMOVE_patch-scs.o		+= $(CC_FLAGS_LTO)
 
 # Force dependency (vdso*-wrap.S includes vdso.so through incbin)
 $(obj)/vdso-wrap.o: $(obj)/vdso/vdso.so
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 5ff1942b04fc..5a7dbbe0ce63 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -117,8 +117,6 @@ int main(void)
   DEFINE(DMA_FROM_DEVICE,	DMA_FROM_DEVICE);
   BLANK();
   DEFINE(PREEMPT_DISABLE_OFFSET, PREEMPT_DISABLE_OFFSET);
-  DEFINE(SOFTIRQ_SHIFT, SOFTIRQ_SHIFT);
-  DEFINE(IRQ_CPUSTAT_SOFTIRQ_PENDING, offsetof(irq_cpustat_t, __softirq_pending));
   BLANK();
   DEFINE(CPU_BOOT_TASK,		offsetof(struct secondary_data, task));
   BLANK();
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index e29e0fea63fb..76b8dd37092a 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -374,6 +374,7 @@ static const struct midr_range erratum_1463225[] = {
 static const struct midr_range trbe_overwrite_fill_mode_cpus[] = {
 #ifdef CONFIG_ARM64_ERRATUM_2139208
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+	MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100),
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_2119858
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
@@ -387,6 +388,7 @@ static const struct midr_range trbe_overwrite_fill_mode_cpus[] = {
 static const struct midr_range tsb_flush_fail_cpus[] = {
 #ifdef CONFIG_ARM64_ERRATUM_2067961
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+	MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100),
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_2054223
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
@@ -399,6 +401,7 @@ static const struct midr_range tsb_flush_fail_cpus[] = {
 static struct midr_range trbe_write_out_of_range_cpus[] = {
 #ifdef CONFIG_ARM64_ERRATUM_2253138
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+	MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100),
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_2224489
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
@@ -416,6 +419,19 @@ static struct midr_range broken_aarch32_aes[] = {
 };
 #endif /* CONFIG_ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE */
 
+#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
+static const struct midr_range erratum_spec_unpriv_load_list[] = {
+#ifdef CONFIG_ARM64_ERRATUM_3117295
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A510),
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_2966298
+	/* Cortex-A520 r0p0 to r0p1 */
+	MIDR_REV_RANGE(MIDR_CORTEX_A520, 0, 0, 1),
+#endif
+	{},
+};
+#endif
+
 const struct arm64_cpu_capabilities arm64_errata[] = {
 #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
 	{
@@ -713,12 +729,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		MIDR_FIXED(MIDR_CPU_VAR_REV(1,1), BIT(25)),
 	},
 #endif
-#ifdef CONFIG_ARM64_ERRATUM_2966298
+#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
 	{
-		.desc = "ARM erratum 2966298",
-		.capability = ARM64_WORKAROUND_2966298,
+		.desc = "ARM errata 2966298, 3117295",
+		.capability = ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD,
 		/* Cortex-A520 r0p0 - r0p1 */
-		ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A520, 0, 0, 1),
+		ERRATA_MIDR_RANGE_LIST(erratum_spec_unpriv_load_list),
 	},
 #endif
 #ifdef CONFIG_AMPERE_ERRATUM_AC03_CPU_38
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 01a4c1d7fc09..8d1a634a403e 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -2341,7 +2341,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.capability = ARM64_HAS_NESTED_VIRT,
 		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
 		.matches = has_nested_virt_support,
-		ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, NV, IMP)
+		ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, NV, NV2)
 	},
 	{
 		.capability = ARM64_HAS_32BIT_EL0_DO_NOT_USE,
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index a6030913cd58..7ef0e127b149 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -428,16 +428,9 @@ alternative_else_nop_endif
 	ldp	x28, x29, [sp, #16 * 14]
 
 	.if	\el == 0
-alternative_if ARM64_WORKAROUND_2966298
-	tlbi	vale1, xzr
-	dsb	nsh
-alternative_else_nop_endif
-alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0
-	ldr	lr, [sp, #S_LR]
-	add	sp, sp, #PT_REGS_SIZE		// restore sp
-	eret
-alternative_else_nop_endif
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+	alternative_insn "b .L_skip_tramp_exit_\@", nop, ARM64_UNMAP_KERNEL_AT_EL0
+
 	msr	far_el1, x29
 
 	ldr_this_cpu	x30, this_cpu_vector, x29
@@ -446,16 +439,26 @@ alternative_else_nop_endif
 	ldr		lr, [sp, #S_LR]		// restore x30
 	add		sp, sp, #PT_REGS_SIZE	// restore sp
 	br		x29
+
+.L_skip_tramp_exit_\@:
 #endif
-	.else
+	.endif
+
 	ldr	lr, [sp, #S_LR]
 	add	sp, sp, #PT_REGS_SIZE		// restore sp
 
+	.if \el == 0
+	/* This must be after the last explicit memory access */
+alternative_if ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
+	tlbi	vale1, xzr
+	dsb	nsh
+alternative_else_nop_endif
+	.else
 	/* Ensure any device/NC reads complete */
 	alternative_insn nop, "dmb sy", ARM64_WORKAROUND_1508412
+	.endif
 
 	eret
-	.endif
 	sb
 	.endm
 
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 505f389be3e0..f27acca550d5 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -898,10 +898,8 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 	 * allocate SVE now in case it is needed for use in streaming
 	 * mode.
 	 */
-	if (system_supports_sve()) {
-		sve_free(task);
-		sve_alloc(task, true);
-	}
+	sve_free(task);
+	sve_alloc(task, true);
 
 	if (free_sme)
 		sme_free(task);
@@ -1219,8 +1217,10 @@ void fpsimd_release_task(struct task_struct *dead_task)
  */
 void sme_alloc(struct task_struct *task, bool flush)
 {
-	if (task->thread.sme_state && flush) {
-		memset(task->thread.sme_state, 0, sme_state_size(task));
+	if (task->thread.sme_state) {
+		if (flush)
+			memset(task->thread.sme_state, 0,
+			       sme_state_size(task));
 		return;
 	}
 
@@ -1311,6 +1311,22 @@ void __init sme_setup(void)
 		get_sme_default_vl());
 }
 
+void sme_suspend_exit(void)
+{
+	u64 smcr = 0;
+
+	if (!system_supports_sme())
+		return;
+
+	if (system_supports_fa64())
+		smcr |= SMCR_ELx_FA64;
+	if (system_supports_sme2())
+		smcr |= SMCR_ELx_EZT0;
+
+	write_sysreg_s(smcr, SYS_SMCR_EL1);
+	write_sysreg_s(0, SYS_SMPRI_EL1);
+}
+
 #endif /* CONFIG_ARM64_SME */
 
 static void sve_init_regs(void)
@@ -1635,7 +1651,7 @@ void fpsimd_preserve_current_state(void)
 void fpsimd_signal_preserve_current_state(void)
 {
 	fpsimd_preserve_current_state();
-	if (test_thread_flag(TIF_SVE))
+	if (current->thread.fp_type == FP_STATE_SVE)
 		sve_to_fpsimd(current);
 }
 
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 09bb7fc7d3c2..e3bef38fc2e2 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1108,12 +1108,13 @@ static int za_set(struct task_struct *target,
 		}
 	}
 
-	/* Allocate/reinit ZA storage */
-	sme_alloc(target, true);
-	if (!target->thread.sme_state) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	/*
+	 * Only flush the storage if PSTATE.ZA was not already set,
+	 * otherwise preserve any existing data.
+	 */
+	sme_alloc(target, !thread_za_enabled(&target->thread));
+	if (!target->thread.sme_state)
+		return -ENOMEM;
 
 	/* If there is no data then disable ZA */
 	if (!count) {
@@ -1499,7 +1500,8 @@ static const struct user_regset aarch64_regsets[] = {
 #ifdef CONFIG_ARM64_SVE
 	[REGSET_SVE] = { /* Scalable Vector Extension */
 		.core_note_type = NT_ARM_SVE,
-		.n = DIV_ROUND_UP(SVE_PT_SIZE(SVE_VQ_MAX, SVE_PT_REGS_SVE),
+		.n = DIV_ROUND_UP(SVE_PT_SIZE(ARCH_SVE_VQ_MAX,
+					      SVE_PT_REGS_SVE),
 				  SVE_VQ_BYTES),
 		.size = SVE_VQ_BYTES,
 		.align = SVE_VQ_BYTES,
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 417a8a86b2db..42c690bb2d60 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -402,19 +402,10 @@ static inline bool cpu_can_disable(unsigned int cpu)
 	return false;
 }
 
-static int __init topology_init(void)
+bool arch_cpu_is_hotpluggable(int num)
 {
-	int i;
-
-	for_each_possible_cpu(i) {
-		struct cpu *cpu = &per_cpu(cpu_data.cpu, i);
-		cpu->hotpluggable = cpu_can_disable(i);
-		register_cpu(cpu, i);
-	}
-
-	return 0;
+	return cpu_can_disable(num);
 }
-subsys_initcall(topology_init);
 
 static void dump_kernel_offset(void)
 {
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 0e8beb3349ea..425b1bc17a3f 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -242,7 +242,7 @@ static int preserve_sve_context(struct sve_context __user *ctx)
 		vl = task_get_sme_vl(current);
 		vq = sve_vq_from_vl(vl);
 		flags |= SVE_SIG_FLAG_SM;
-	} else if (test_thread_flag(TIF_SVE)) {
+	} else if (current->thread.fp_type == FP_STATE_SVE) {
 		vq = sve_vq_from_vl(vl);
 	}
 
@@ -878,7 +878,7 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
 	if (system_supports_sve() || system_supports_sme()) {
 		unsigned int vq = 0;
 
-		if (add_all || test_thread_flag(TIF_SVE) ||
+		if (add_all || current->thread.fp_type == FP_STATE_SVE ||
 		    thread_sm_enabled(&current->thread)) {
 			int vl = max(sve_max_vl(), sme_max_vl());
 
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 7f88028a00c0..b2a60e0bcfd2 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -247,7 +247,7 @@ struct kunwind_consume_entry_data {
 	void *cookie;
 };
 
-static bool
+static __always_inline bool
 arch_kunwind_consume_entry(const struct kunwind_state *state, void *cookie)
 {
 	struct kunwind_consume_entry_data *data = cookie;
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index eca4d0435211..eaaff94329cd 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -12,6 +12,7 @@
 #include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
 #include <asm/exec.h>
+#include <asm/fpsimd.h>
 #include <asm/mte.h>
 #include <asm/memory.h>
 #include <asm/mmu_context.h>
@@ -80,6 +81,8 @@ void notrace __cpu_suspend_exit(void)
 	 */
 	spectre_v4_enable_mitigation(NULL);
 
+	sme_suspend_exit();
+
 	/* Restore additional feature-specific configuration */
 	ptrauth_suspend_exit();
 }
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 2266fcdff78a..f5f80fdce0fe 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -127,9 +127,6 @@ obj-vdso := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso)
 targets += vdso.lds
 CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
 
-include/generated/vdso32-offsets.h: $(obj)/vdso32.so.dbg FORCE
-	$(call if_changed,vdsosym)
-
 # Strip rule for vdso.so
 $(obj)/vdso.so: OBJCOPYFLAGS := -S
 $(obj)/vdso.so: $(obj)/vdso32.so.dbg FORCE
@@ -166,9 +163,3 @@ quiet_cmd_vdsoas = AS32    $@
 
 quiet_cmd_vdsomunge = MUNGE   $@
       cmd_vdsomunge = $(obj)/$(munge) $< $@
-
-# Generate vDSO offsets using helper script (borrowed from the 64-bit vDSO)
-gen-vdsosym := $(srctree)/$(src)/../vdso/gen_vdso_offsets.sh
-quiet_cmd_vdsosym = VDSOSYM $@
-# The AArch64 nm should be able to read an AArch32 binary
-      cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 83c1e09be42e..27ca89b628a0 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -3,7 +3,6 @@
 # KVM configuration
 #
 
-source "virt/lib/Kconfig"
 source "virt/kvm/Kconfig"
 
 menuconfig VIRTUALIZATION
@@ -21,16 +20,14 @@ if VIRTUALIZATION
 menuconfig KVM
 	bool "Kernel-based Virtual Machine (KVM) support"
 	depends on HAVE_KVM
+	select KVM_COMMON
 	select KVM_GENERIC_HARDWARE_ENABLING
-	select MMU_NOTIFIER
-	select PREEMPT_NOTIFIERS
+	select KVM_GENERIC_MMU_NOTIFIER
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select KVM_MMIO
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_XFER_TO_GUEST_WORK
 	select KVM_VFIO
-	select HAVE_KVM_EVENTFD
-	select HAVE_KVM_IRQFD
 	select HAVE_KVM_DIRTY_RING_ACQ_REL
 	select NEED_KVM_DIRTY_RING_WITH_BITMAP
 	select HAVE_KVM_MSI
@@ -41,7 +38,6 @@ menuconfig KVM
 	select HAVE_KVM_VCPU_RUN_PID_CHANGE
 	select SCHED_INFO
 	select GUEST_PERF_EVENTS if PERF_EVENTS
-	select INTERVAL_TREE
 	select XARRAY_MULTI
 	help
 	  Support hosting virtualized guest machines.
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 13ba691b848f..9dec8c419bf4 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -295,8 +295,7 @@ static u64 wfit_delay_ns(struct kvm_vcpu *vcpu)
 	u64 val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu));
 	struct arch_timer_context *ctx;
 
-	ctx = (vcpu_has_nv(vcpu) && is_hyp_ctxt(vcpu)) ? vcpu_hvtimer(vcpu)
-						       : vcpu_vtimer(vcpu);
+	ctx = is_hyp_ctxt(vcpu) ? vcpu_hvtimer(vcpu) : vcpu_vtimer(vcpu);
 
 	return kvm_counter_compute_delta(ctx, val);
 }
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 4796104c4471..a25265aca432 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -221,7 +221,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = vgic_present;
 		break;
 	case KVM_CAP_IOEVENTFD:
-	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_USER_MEMORY:
 	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
@@ -669,6 +668,12 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 			return ret;
 	}
 
+	if (vcpu_has_nv(vcpu)) {
+		ret = kvm_init_nv_sysregs(vcpu->kvm);
+		if (ret)
+			return ret;
+	}
+
 	ret = kvm_timer_enable(vcpu);
 	if (ret)
 		return ret;
@@ -1837,6 +1842,7 @@ static int kvm_init_vector_slots(void)
 static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 {
 	struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
+	u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
 	unsigned long tcr;
 
 	/*
@@ -1859,6 +1865,10 @@ static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 	}
 	tcr &= ~TCR_T0SZ_MASK;
 	tcr |= TCR_T0SZ(hyp_va_bits);
+	tcr &= ~TCR_EL2_PS_MASK;
+	tcr |= FIELD_PREP(TCR_EL2_PS_MASK, kvm_get_parange(mmfr0));
+	if (kvm_lpa2_is_enabled())
+		tcr |= TCR_EL2_DS;
 	params->tcr_el2 = tcr;
 
 	params->pgd_pa = kvm_mmu_get_httbr();
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 06185216a297..431fd429932d 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -1012,6 +1012,7 @@ enum fgt_group_id {
 	HDFGRTR_GROUP,
 	HDFGWTR_GROUP,
 	HFGITR_GROUP,
+	HAFGRTR_GROUP,
 
 	/* Must be last */
 	__NR_FGT_GROUP_IDS__
@@ -1042,10 +1043,20 @@ enum fg_filter_id {
 
 static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
 	/* HFGRTR_EL2, HFGWTR_EL2 */
+	SR_FGT(SYS_AMAIR2_EL1,		HFGxTR, nAMAIR2_EL1, 0),
+	SR_FGT(SYS_MAIR2_EL1,		HFGxTR, nMAIR2_EL1, 0),
+	SR_FGT(SYS_S2POR_EL1,		HFGxTR, nS2POR_EL1, 0),
+	SR_FGT(SYS_POR_EL1,		HFGxTR, nPOR_EL1, 0),
+	SR_FGT(SYS_POR_EL0,		HFGxTR, nPOR_EL0, 0),
 	SR_FGT(SYS_PIR_EL1,		HFGxTR, nPIR_EL1, 0),
 	SR_FGT(SYS_PIRE0_EL1,		HFGxTR, nPIRE0_EL1, 0),
+	SR_FGT(SYS_RCWMASK_EL1,		HFGxTR, nRCWMASK_EL1, 0),
 	SR_FGT(SYS_TPIDR2_EL0,		HFGxTR, nTPIDR2_EL0, 0),
 	SR_FGT(SYS_SMPRI_EL1,		HFGxTR, nSMPRI_EL1, 0),
+	SR_FGT(SYS_GCSCR_EL1,		HFGxTR, nGCS_EL1, 0),
+	SR_FGT(SYS_GCSPR_EL1,		HFGxTR, nGCS_EL1, 0),
+	SR_FGT(SYS_GCSCRE0_EL1,		HFGxTR, nGCS_EL0, 0),
+	SR_FGT(SYS_GCSPR_EL0,		HFGxTR, nGCS_EL0, 0),
 	SR_FGT(SYS_ACCDATA_EL1,		HFGxTR, nACCDATA_EL1, 0),
 	SR_FGT(SYS_ERXADDR_EL1,		HFGxTR, ERXADDR_EL1, 1),
 	SR_FGT(SYS_ERXPFGCDN_EL1,	HFGxTR, ERXPFGCDN_EL1, 1),
@@ -1107,6 +1118,11 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
 	SR_FGT(SYS_AFSR1_EL1, 		HFGxTR, AFSR1_EL1, 1),
 	SR_FGT(SYS_AFSR0_EL1, 		HFGxTR, AFSR0_EL1, 1),
 	/* HFGITR_EL2 */
+	SR_FGT(OP_AT_S1E1A, 		HFGITR, ATS1E1A, 1),
+	SR_FGT(OP_COSP_RCTX, 		HFGITR, COSPRCTX, 1),
+	SR_FGT(OP_GCSPUSHX, 		HFGITR, nGCSEPP, 0),
+	SR_FGT(OP_GCSPOPX, 		HFGITR, nGCSEPP, 0),
+	SR_FGT(OP_GCSPUSHM, 		HFGITR, nGCSPUSHM_EL1, 0),
 	SR_FGT(OP_BRB_IALL, 		HFGITR, nBRBIALL, 0),
 	SR_FGT(OP_BRB_INJ, 		HFGITR, nBRBINJ, 0),
 	SR_FGT(SYS_DC_CVAC, 		HFGITR, DCCVAC, 1),
@@ -1674,6 +1690,49 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
 	SR_FGT(SYS_PMCR_EL0,		HDFGWTR, PMCR_EL0, 1),
 	SR_FGT(SYS_PMSWINC_EL0,		HDFGWTR, PMSWINC_EL0, 1),
 	SR_FGT(SYS_OSLAR_EL1,		HDFGWTR, OSLAR_EL1, 1),
+	/*
+	 * HAFGRTR_EL2
+	 */
+	SR_FGT(SYS_AMEVTYPER1_EL0(15),	HAFGRTR, AMEVTYPER115_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(14),	HAFGRTR, AMEVTYPER114_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(13),	HAFGRTR, AMEVTYPER113_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(12),	HAFGRTR, AMEVTYPER112_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(11),	HAFGRTR, AMEVTYPER111_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(10),	HAFGRTR, AMEVTYPER110_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(9),	HAFGRTR, AMEVTYPER19_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(8),	HAFGRTR, AMEVTYPER18_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(7),	HAFGRTR, AMEVTYPER17_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(6),	HAFGRTR, AMEVTYPER16_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(5),	HAFGRTR, AMEVTYPER15_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(4),	HAFGRTR, AMEVTYPER14_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(3),	HAFGRTR, AMEVTYPER13_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(2),	HAFGRTR, AMEVTYPER12_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(1),	HAFGRTR, AMEVTYPER11_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(0),	HAFGRTR, AMEVTYPER10_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(15),	HAFGRTR, AMEVCNTR115_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(14),	HAFGRTR, AMEVCNTR114_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(13),	HAFGRTR, AMEVCNTR113_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(12),	HAFGRTR, AMEVCNTR112_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(11),	HAFGRTR, AMEVCNTR111_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(10),	HAFGRTR, AMEVCNTR110_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(9),	HAFGRTR, AMEVCNTR19_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(8),	HAFGRTR, AMEVCNTR18_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(7),	HAFGRTR, AMEVCNTR17_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(6),	HAFGRTR, AMEVCNTR16_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(5),	HAFGRTR, AMEVCNTR15_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(4),	HAFGRTR, AMEVCNTR14_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(3),	HAFGRTR, AMEVCNTR13_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(2),	HAFGRTR, AMEVCNTR12_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(1),	HAFGRTR, AMEVCNTR11_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(0),	HAFGRTR, AMEVCNTR10_EL0, 1),
+	SR_FGT(SYS_AMCNTENCLR1_EL0,	HAFGRTR, AMCNTEN1, 1),
+	SR_FGT(SYS_AMCNTENSET1_EL0,	HAFGRTR, AMCNTEN1, 1),
+	SR_FGT(SYS_AMCNTENCLR0_EL0,	HAFGRTR, AMCNTEN0, 1),
+	SR_FGT(SYS_AMCNTENSET0_EL0,	HAFGRTR, AMCNTEN0, 1),
+	SR_FGT(SYS_AMEVCNTR0_EL0(3),	HAFGRTR, AMEVCNTR03_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR0_EL0(2),	HAFGRTR, AMEVCNTR02_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR0_EL0(1),	HAFGRTR, AMEVCNTR01_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR0_EL0(0),	HAFGRTR, AMEVCNTR00_EL0, 1),
 };
 
 static union trap_config get_trap_config(u32 sysreg)
@@ -1894,6 +1953,10 @@ bool __check_nv_sr_forward(struct kvm_vcpu *vcpu)
 			val = sanitised_sys_reg(vcpu, HDFGWTR_EL2);
 		break;
 
+	case HAFGRTR_GROUP:
+		val = sanitised_sys_reg(vcpu, HAFGRTR_EL2);
+		break;
+
 	case HFGITR_GROUP:
 		val = sanitised_sys_reg(vcpu, HFGITR_EL2);
 		switch (tc.fgf) {
diff --git a/arch/arm64/kvm/hyp/include/hyp/fault.h b/arch/arm64/kvm/hyp/include/hyp/fault.h
index 9ddcfe2c3e57..9e13c1bc2ad5 100644
--- a/arch/arm64/kvm/hyp/include/hyp/fault.h
+++ b/arch/arm64/kvm/hyp/include/hyp/fault.h
@@ -60,7 +60,7 @@ static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault)
 	 */
 	if (!(esr & ESR_ELx_S1PTW) &&
 	    (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
-	     (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_PERM)) {
+	     esr_fsc_is_permission_fault(esr))) {
 		if (!__translate_far_to_hpfar(far, &hpfar))
 			return false;
 	} else {
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index f99d8af0b9af..a038320cdb08 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -79,6 +79,45 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
 		clr |= ~hfg & __ ## reg ## _nMASK; 			\
 	} while(0)
 
+#define update_fgt_traps_cs(vcpu, reg, clr, set)			\
+	do {								\
+		struct kvm_cpu_context *hctxt =				\
+			&this_cpu_ptr(&kvm_host_data)->host_ctxt;	\
+		u64 c = 0, s = 0;					\
+									\
+		ctxt_sys_reg(hctxt, reg) = read_sysreg_s(SYS_ ## reg);	\
+		compute_clr_set(vcpu, reg, c, s);			\
+		s |= set;						\
+		c |= clr;						\
+		if (c || s) {						\
+			u64 val = __ ## reg ## _nMASK;			\
+			val |= s;					\
+			val &= ~c;					\
+			write_sysreg_s(val, SYS_ ## reg);		\
+		}							\
+	} while(0)
+
+#define update_fgt_traps(vcpu, reg)		\
+	update_fgt_traps_cs(vcpu, reg, 0, 0)
+
+/*
+ * Validate the fine grain trap masks.
+ * Check that the masks do not overlap and that all bits are accounted for.
+ */
+#define CHECK_FGT_MASKS(reg)							\
+	do {									\
+		BUILD_BUG_ON((__ ## reg ## _MASK) & (__ ## reg ## _nMASK));	\
+		BUILD_BUG_ON(~((__ ## reg ## _RES0) ^ (__ ## reg ## _MASK) ^	\
+			       (__ ## reg ## _nMASK)));				\
+	} while(0)
+
+static inline bool cpu_has_amu(void)
+{
+       u64 pfr0 = read_sysreg_s(SYS_ID_AA64PFR0_EL1);
+
+       return cpuid_feature_extract_unsigned_field(pfr0,
+               ID_AA64PFR0_EL1_AMU_SHIFT);
+}
 
 static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 {
@@ -86,6 +125,14 @@ static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 	u64 r_clr = 0, w_clr = 0, r_set = 0, w_set = 0, tmp;
 	u64 r_val, w_val;
 
+	CHECK_FGT_MASKS(HFGRTR_EL2);
+	CHECK_FGT_MASKS(HFGWTR_EL2);
+	CHECK_FGT_MASKS(HFGITR_EL2);
+	CHECK_FGT_MASKS(HDFGRTR_EL2);
+	CHECK_FGT_MASKS(HDFGWTR_EL2);
+	CHECK_FGT_MASKS(HAFGRTR_EL2);
+	CHECK_FGT_MASKS(HCRX_EL2);
+
 	if (!cpus_have_final_cap(ARM64_HAS_FGT))
 		return;
 
@@ -110,12 +157,15 @@ static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 		compute_clr_set(vcpu, HFGWTR_EL2, w_clr, w_set);
 	}
 
-	/* The default is not to trap anything but ACCDATA_EL1 */
-	r_val = __HFGRTR_EL2_nMASK & ~HFGxTR_EL2_nACCDATA_EL1;
+	/* The default to trap everything not handled or supported in KVM. */
+	tmp = HFGxTR_EL2_nAMAIR2_EL1 | HFGxTR_EL2_nMAIR2_EL1 | HFGxTR_EL2_nS2POR_EL1 |
+	      HFGxTR_EL2_nPOR_EL1 | HFGxTR_EL2_nPOR_EL0 | HFGxTR_EL2_nACCDATA_EL1;
+
+	r_val = __HFGRTR_EL2_nMASK & ~tmp;
 	r_val |= r_set;
 	r_val &= ~r_clr;
 
-	w_val = __HFGWTR_EL2_nMASK & ~HFGxTR_EL2_nACCDATA_EL1;
+	w_val = __HFGWTR_EL2_nMASK & ~tmp;
 	w_val |= w_set;
 	w_val &= ~w_clr;
 
@@ -125,34 +175,12 @@ static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 	if (!vcpu_has_nv(vcpu) || is_hyp_ctxt(vcpu))
 		return;
 
-	ctxt_sys_reg(hctxt, HFGITR_EL2) = read_sysreg_s(SYS_HFGITR_EL2);
+	update_fgt_traps(vcpu, HFGITR_EL2);
+	update_fgt_traps(vcpu, HDFGRTR_EL2);
+	update_fgt_traps(vcpu, HDFGWTR_EL2);
 
-	r_set = r_clr = 0;
-	compute_clr_set(vcpu, HFGITR_EL2, r_clr, r_set);
-	r_val = __HFGITR_EL2_nMASK;
-	r_val |= r_set;
-	r_val &= ~r_clr;
-
-	write_sysreg_s(r_val, SYS_HFGITR_EL2);
-
-	ctxt_sys_reg(hctxt, HDFGRTR_EL2) = read_sysreg_s(SYS_HDFGRTR_EL2);
-	ctxt_sys_reg(hctxt, HDFGWTR_EL2) = read_sysreg_s(SYS_HDFGWTR_EL2);
-
-	r_clr = r_set = w_clr = w_set = 0;
-
-	compute_clr_set(vcpu, HDFGRTR_EL2, r_clr, r_set);
-	compute_clr_set(vcpu, HDFGWTR_EL2, w_clr, w_set);
-
-	r_val = __HDFGRTR_EL2_nMASK;
-	r_val |= r_set;
-	r_val &= ~r_clr;
-
-	w_val = __HDFGWTR_EL2_nMASK;
-	w_val |= w_set;
-	w_val &= ~w_clr;
-
-	write_sysreg_s(r_val, SYS_HDFGRTR_EL2);
-	write_sysreg_s(w_val, SYS_HDFGWTR_EL2);
+	if (cpu_has_amu())
+		update_fgt_traps(vcpu, HAFGRTR_EL2);
 }
 
 static inline void __deactivate_traps_hfgxtr(struct kvm_vcpu *vcpu)
@@ -171,6 +199,9 @@ static inline void __deactivate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 	write_sysreg_s(ctxt_sys_reg(hctxt, HFGITR_EL2), SYS_HFGITR_EL2);
 	write_sysreg_s(ctxt_sys_reg(hctxt, HDFGRTR_EL2), SYS_HDFGRTR_EL2);
 	write_sysreg_s(ctxt_sys_reg(hctxt, HDFGWTR_EL2), SYS_HDFGWTR_EL2);
+
+	if (cpu_has_amu())
+		write_sysreg_s(ctxt_sys_reg(hctxt, HAFGRTR_EL2), SYS_HAFGRTR_EL2);
 }
 
 static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
@@ -591,7 +622,7 @@ static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
 	if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
 		bool valid;
 
-		valid = kvm_vcpu_trap_get_fault_type(vcpu) == ESR_ELx_FSC_FAULT &&
+		valid = kvm_vcpu_trap_is_translation_fault(vcpu) &&
 			kvm_vcpu_dabt_isvalid(vcpu) &&
 			!kvm_vcpu_abt_issea(vcpu) &&
 			!kvm_vcpu_abt_iss1tw(vcpu);
diff --git a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
index e91922daa8ca..51f043649146 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
@@ -69,6 +69,8 @@
 	ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_SSBS) \
 	)
 
+#define PVM_ID_AA64PFR2_ALLOW 0ULL
+
 /*
  * Allow for protected VMs:
  * - Mixed-endian
@@ -101,6 +103,7 @@
  * - Privileged Access Never
  * - SError interrupt exceptions from speculative reads
  * - Enhanced Translation Synchronization
+ * - Control for cache maintenance permission
  */
 #define PVM_ID_AA64MMFR1_ALLOW (\
 	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_HAFDBS) | \
@@ -108,7 +111,8 @@
 	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_HPDS) | \
 	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_PAN) | \
 	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_SpecSEI) | \
-	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_ETS) \
+	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_ETS) | \
+	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_CMOW) \
 	)
 
 /*
@@ -133,6 +137,8 @@
 	ARM64_FEATURE_MASK(ID_AA64MMFR2_EL1_E0PD) \
 	)
 
+#define PVM_ID_AA64MMFR3_ALLOW (0ULL)
+
 /*
  * No support for Scalable Vectors for protected VMs:
  *	Requires additional support from KVM, e.g., context-switching and
@@ -178,10 +184,18 @@
 	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_RNDR) \
 	)
 
+/* Restrict pointer authentication to the basic version. */
+#define PVM_ID_AA64ISAR1_RESTRICT_UNSIGNED (\
+	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_APA), ID_AA64ISAR1_EL1_APA_PAuth) | \
+	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_API), ID_AA64ISAR1_EL1_API_PAuth) \
+	)
+
+#define PVM_ID_AA64ISAR2_RESTRICT_UNSIGNED (\
+	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_APA3), ID_AA64ISAR2_EL1_APA3_PAuth) \
+	)
+
 #define PVM_ID_AA64ISAR1_ALLOW (\
 	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_DPB) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_APA) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_API) | \
 	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_JSCVT) | \
 	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_FCMA) | \
 	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_LRCPC) | \
@@ -196,8 +210,8 @@
 	)
 
 #define PVM_ID_AA64ISAR2_ALLOW (\
+	ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_ATS1A)| \
 	ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_GPA3) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_APA3) | \
 	ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_MOPS) \
 	)
 
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index 1cc06e6797bd..2994878d68ea 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -122,11 +122,7 @@ alternative_if ARM64_HAS_CNP
 alternative_else_nop_endif
 	msr	ttbr0_el2, x2
 
-	/*
-	 * Set the PS bits in TCR_EL2.
-	 */
 	ldr	x0, [x0, #NVHE_INIT_TCR_EL2]
-	tcr_compute_pa_size x0, #TCR_EL2_PS_SHIFT, x1, x2
 	msr	tcr_el2, x0
 
 	isb
@@ -292,6 +288,8 @@ alternative_else_nop_endif
 	mov	sp, x0
 
 	/* And turn the MMU back on! */
+	dsb	nsh
+	isb
 	set_sctlr_el2	x2
 	ret	x1
 SYM_FUNC_END(__pkvm_init_switch_pgd)
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 8d0a5834e883..861c76021a25 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -91,7 +91,7 @@ static void host_s2_put_page(void *addr)
 	hyp_put_page(&host_s2_pool, addr);
 }
 
-static void host_s2_free_unlinked_table(void *addr, u32 level)
+static void host_s2_free_unlinked_table(void *addr, s8 level)
 {
 	kvm_pgtable_stage2_free_unlinked(&host_mmu.mm_ops, addr, level);
 }
@@ -443,7 +443,7 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
 {
 	struct kvm_mem_range cur;
 	kvm_pte_t pte;
-	u32 level;
+	s8 level;
 	int ret;
 
 	hyp_assert_lock_held(&host_mmu.lock);
@@ -462,7 +462,7 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
 		cur.start = ALIGN_DOWN(addr, granule);
 		cur.end = cur.start + granule;
 		level++;
-	} while ((level < KVM_PGTABLE_MAX_LEVELS) &&
+	} while ((level <= KVM_PGTABLE_LAST_LEVEL) &&
 			!(kvm_level_supports_block_mapping(level) &&
 			  range_included(&cur, range)));
 
diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c
index 65a7a186d7b2..b01a3d1078a8 100644
--- a/arch/arm64/kvm/hyp/nvhe/mm.c
+++ b/arch/arm64/kvm/hyp/nvhe/mm.c
@@ -260,7 +260,7 @@ static void fixmap_clear_slot(struct hyp_fixmap_slot *slot)
 	 * https://lore.kernel.org/kvm/20221017115209.2099-1-will@kernel.org/T/#mf10dfbaf1eaef9274c581b81c53758918c1d0f03
 	 */
 	dsb(ishst);
-	__tlbi_level(vale2is, __TLBI_VADDR(addr, 0), (KVM_PGTABLE_MAX_LEVELS - 1));
+	__tlbi_level(vale2is, __TLBI_VADDR(addr, 0), KVM_PGTABLE_LAST_LEVEL);
 	dsb(ish);
 	isb();
 }
@@ -275,7 +275,7 @@ static int __create_fixmap_slot_cb(const struct kvm_pgtable_visit_ctx *ctx,
 {
 	struct hyp_fixmap_slot *slot = per_cpu_ptr(&fixmap_slots, (u64)ctx->arg);
 
-	if (!kvm_pte_valid(ctx->old) || ctx->level != KVM_PGTABLE_MAX_LEVELS - 1)
+	if (!kvm_pte_valid(ctx->old) || ctx->level != KVM_PGTABLE_LAST_LEVEL)
 		return -EINVAL;
 
 	slot->addr = ctx->addr;
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index b29f15418c0a..26dd9a20ad6e 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -136,6 +136,10 @@ static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu)
 			cptr_set |= CPTR_EL2_TTA;
 	}
 
+	/* Trap External Trace */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_ExtTrcBuff), feature_ids))
+		mdcr_clear |= MDCR_EL2_E2TB_MASK << MDCR_EL2_E2TB_SHIFT;
+
 	vcpu->arch.mdcr_el2 |= mdcr_set;
 	vcpu->arch.mdcr_el2 &= ~mdcr_clear;
 	vcpu->arch.cptr_el2 |= cptr_set;
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index 0d5e0a89ddce..bc58d1b515af 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -181,7 +181,7 @@ static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	if (!kvm_pte_valid(ctx->old))
 		return 0;
 
-	if (ctx->level != (KVM_PGTABLE_MAX_LEVELS - 1))
+	if (ctx->level != KVM_PGTABLE_LAST_LEVEL)
 		return -EINVAL;
 
 	phys = kvm_pte_to_phys(ctx->old);
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 1966fdee740e..ab9d05fcf98b 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -79,7 +79,10 @@ static bool kvm_pgtable_walk_skip_cmo(const struct kvm_pgtable_visit_ctx *ctx)
 
 static bool kvm_phys_is_valid(u64 phys)
 {
-	return phys < BIT(id_aa64mmfr0_parange_to_phys_shift(ID_AA64MMFR0_EL1_PARANGE_MAX));
+	u64 parange_max = kvm_get_parange_max();
+	u8 shift = id_aa64mmfr0_parange_to_phys_shift(parange_max);
+
+	return phys < BIT(shift);
 }
 
 static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx, u64 phys)
@@ -98,7 +101,7 @@ static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx,
 	return IS_ALIGNED(ctx->addr, granule);
 }
 
-static u32 kvm_pgtable_idx(struct kvm_pgtable_walk_data *data, u32 level)
+static u32 kvm_pgtable_idx(struct kvm_pgtable_walk_data *data, s8 level)
 {
 	u64 shift = kvm_granule_shift(level);
 	u64 mask = BIT(PAGE_SHIFT - 3) - 1;
@@ -114,7 +117,7 @@ static u32 kvm_pgd_page_idx(struct kvm_pgtable *pgt, u64 addr)
 	return (addr & mask) >> shift;
 }
 
-static u32 kvm_pgd_pages(u32 ia_bits, u32 start_level)
+static u32 kvm_pgd_pages(u32 ia_bits, s8 start_level)
 {
 	struct kvm_pgtable pgt = {
 		.ia_bits	= ia_bits,
@@ -124,9 +127,9 @@ static u32 kvm_pgd_pages(u32 ia_bits, u32 start_level)
 	return kvm_pgd_page_idx(&pgt, -1ULL) + 1;
 }
 
-static bool kvm_pte_table(kvm_pte_t pte, u32 level)
+static bool kvm_pte_table(kvm_pte_t pte, s8 level)
 {
-	if (level == KVM_PGTABLE_MAX_LEVELS - 1)
+	if (level == KVM_PGTABLE_LAST_LEVEL)
 		return false;
 
 	if (!kvm_pte_valid(pte))
@@ -154,11 +157,11 @@ static kvm_pte_t kvm_init_table_pte(kvm_pte_t *childp, struct kvm_pgtable_mm_ops
 	return pte;
 }
 
-static kvm_pte_t kvm_init_valid_leaf_pte(u64 pa, kvm_pte_t attr, u32 level)
+static kvm_pte_t kvm_init_valid_leaf_pte(u64 pa, kvm_pte_t attr, s8 level)
 {
 	kvm_pte_t pte = kvm_phys_to_pte(pa);
-	u64 type = (level == KVM_PGTABLE_MAX_LEVELS - 1) ? KVM_PTE_TYPE_PAGE :
-							   KVM_PTE_TYPE_BLOCK;
+	u64 type = (level == KVM_PGTABLE_LAST_LEVEL) ? KVM_PTE_TYPE_PAGE :
+						       KVM_PTE_TYPE_BLOCK;
 
 	pte |= attr & (KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI);
 	pte |= FIELD_PREP(KVM_PTE_TYPE, type);
@@ -203,11 +206,11 @@ static bool kvm_pgtable_walk_continue(const struct kvm_pgtable_walker *walker,
 }
 
 static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data,
-			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, u32 level);
+			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, s8 level);
 
 static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data,
 				      struct kvm_pgtable_mm_ops *mm_ops,
-				      kvm_pteref_t pteref, u32 level)
+				      kvm_pteref_t pteref, s8 level)
 {
 	enum kvm_pgtable_walk_flags flags = data->walker->flags;
 	kvm_pte_t *ptep = kvm_dereference_pteref(data->walker, pteref);
@@ -272,12 +275,13 @@ out:
 }
 
 static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data,
-			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, u32 level)
+			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, s8 level)
 {
 	u32 idx;
 	int ret = 0;
 
-	if (WARN_ON_ONCE(level >= KVM_PGTABLE_MAX_LEVELS))
+	if (WARN_ON_ONCE(level < KVM_PGTABLE_FIRST_LEVEL ||
+			 level > KVM_PGTABLE_LAST_LEVEL))
 		return -EINVAL;
 
 	for (idx = kvm_pgtable_idx(data, level); idx < PTRS_PER_PTE; ++idx) {
@@ -340,7 +344,7 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
 
 struct leaf_walk_data {
 	kvm_pte_t	pte;
-	u32		level;
+	s8		level;
 };
 
 static int leaf_walker(const struct kvm_pgtable_visit_ctx *ctx,
@@ -355,7 +359,7 @@ static int leaf_walker(const struct kvm_pgtable_visit_ctx *ctx,
 }
 
 int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
-			 kvm_pte_t *ptep, u32 *level)
+			 kvm_pte_t *ptep, s8 *level)
 {
 	struct leaf_walk_data data;
 	struct kvm_pgtable_walker walker = {
@@ -408,7 +412,8 @@ static int hyp_set_prot_attr(enum kvm_pgtable_prot prot, kvm_pte_t *ptep)
 	}
 
 	attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_AP, ap);
-	attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_SH, sh);
+	if (!kvm_lpa2_is_enabled())
+		attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_SH, sh);
 	attr |= KVM_PTE_LEAF_ATTR_LO_S1_AF;
 	attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW;
 	*ptep = attr;
@@ -467,7 +472,7 @@ static int hyp_map_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	if (hyp_map_walker_try_leaf(ctx, data))
 		return 0;
 
-	if (WARN_ON(ctx->level == KVM_PGTABLE_MAX_LEVELS - 1))
+	if (WARN_ON(ctx->level == KVM_PGTABLE_LAST_LEVEL))
 		return -EINVAL;
 
 	childp = (kvm_pte_t *)mm_ops->zalloc_page(NULL);
@@ -563,14 +568,19 @@ u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
 int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits,
 			 struct kvm_pgtable_mm_ops *mm_ops)
 {
-	u64 levels = ARM64_HW_PGTABLE_LEVELS(va_bits);
+	s8 start_level = KVM_PGTABLE_LAST_LEVEL + 1 -
+			 ARM64_HW_PGTABLE_LEVELS(va_bits);
+
+	if (start_level < KVM_PGTABLE_FIRST_LEVEL ||
+	    start_level > KVM_PGTABLE_LAST_LEVEL)
+		return -EINVAL;
 
 	pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_page(NULL);
 	if (!pgt->pgd)
 		return -ENOMEM;
 
 	pgt->ia_bits		= va_bits;
-	pgt->start_level	= KVM_PGTABLE_MAX_LEVELS - levels;
+	pgt->start_level	= start_level;
 	pgt->mm_ops		= mm_ops;
 	pgt->mmu		= NULL;
 	pgt->force_pte_cb	= NULL;
@@ -624,7 +634,7 @@ struct stage2_map_data {
 u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift)
 {
 	u64 vtcr = VTCR_EL2_FLAGS;
-	u8 lvls;
+	s8 lvls;
 
 	vtcr |= kvm_get_parange(mmfr0) << VTCR_EL2_PS_SHIFT;
 	vtcr |= VTCR_EL2_T0SZ(phys_shift);
@@ -635,6 +645,15 @@ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift)
 	lvls = stage2_pgtable_levels(phys_shift);
 	if (lvls < 2)
 		lvls = 2;
+
+	/*
+	 * When LPA2 is enabled, the HW supports an extra level of translation
+	 * (for 5 in total) when using 4K pages. It also introduces VTCR_EL2.SL2
+	 * to as an addition to SL0 to enable encoding this extra start level.
+	 * However, since we always use concatenated pages for the first level
+	 * lookup, we will never need this extra level and therefore do not need
+	 * to touch SL2.
+	 */
 	vtcr |= VTCR_EL2_LVLS_TO_SL0(lvls);
 
 #ifdef CONFIG_ARM64_HW_AFDBM
@@ -654,6 +673,9 @@ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift)
 		vtcr |= VTCR_EL2_HA;
 #endif /* CONFIG_ARM64_HW_AFDBM */
 
+	if (kvm_lpa2_is_enabled())
+		vtcr |= VTCR_EL2_DS;
+
 	/* Set the vmid bits */
 	vtcr |= (get_vmid_bits(mmfr1) == 16) ?
 		VTCR_EL2_VS_16BIT :
@@ -711,7 +733,9 @@ static int stage2_set_prot_attr(struct kvm_pgtable *pgt, enum kvm_pgtable_prot p
 	if (prot & KVM_PGTABLE_PROT_W)
 		attr |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W;
 
-	attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S2_SH, sh);
+	if (!kvm_lpa2_is_enabled())
+		attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S2_SH, sh);
+
 	attr |= KVM_PTE_LEAF_ATTR_LO_S2_AF;
 	attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW;
 	*ptep = attr;
@@ -902,7 +926,7 @@ static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx,
 {
 	u64 phys = stage2_map_walker_phys_addr(ctx, data);
 
-	if (data->force_pte && (ctx->level < (KVM_PGTABLE_MAX_LEVELS - 1)))
+	if (data->force_pte && ctx->level < KVM_PGTABLE_LAST_LEVEL)
 		return false;
 
 	return kvm_block_mapping_supported(ctx, phys);
@@ -981,7 +1005,7 @@ static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx,
 	if (ret != -E2BIG)
 		return ret;
 
-	if (WARN_ON(ctx->level == KVM_PGTABLE_MAX_LEVELS - 1))
+	if (WARN_ON(ctx->level == KVM_PGTABLE_LAST_LEVEL))
 		return -EINVAL;
 
 	if (!data->memcache)
@@ -1151,7 +1175,7 @@ struct stage2_attr_data {
 	kvm_pte_t			attr_set;
 	kvm_pte_t			attr_clr;
 	kvm_pte_t			pte;
-	u32				level;
+	s8				level;
 };
 
 static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx,
@@ -1194,7 +1218,7 @@ static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx,
 static int stage2_update_leaf_attrs(struct kvm_pgtable *pgt, u64 addr,
 				    u64 size, kvm_pte_t attr_set,
 				    kvm_pte_t attr_clr, kvm_pte_t *orig_pte,
-				    u32 *level, enum kvm_pgtable_walk_flags flags)
+				    s8 *level, enum kvm_pgtable_walk_flags flags)
 {
 	int ret;
 	kvm_pte_t attr_mask = KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI;
@@ -1296,7 +1320,7 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
 				   enum kvm_pgtable_prot prot)
 {
 	int ret;
-	u32 level;
+	s8 level;
 	kvm_pte_t set = 0, clr = 0;
 
 	if (prot & KVM_PTE_LEAF_ATTR_HI_SW)
@@ -1349,7 +1373,7 @@ int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
 }
 
 kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
-					      u64 phys, u32 level,
+					      u64 phys, s8 level,
 					      enum kvm_pgtable_prot prot,
 					      void *mc, bool force_pte)
 {
@@ -1395,7 +1419,6 @@ kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
 				 level + 1);
 	if (ret) {
 		kvm_pgtable_stage2_free_unlinked(mm_ops, pgtable, level);
-		mm_ops->put_page(pgtable);
 		return ERR_PTR(ret);
 	}
 
@@ -1407,7 +1430,7 @@ kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
  * fully populated tree up to the PTE entries. Note that @level is
  * interpreted as in "level @level entry".
  */
-static int stage2_block_get_nr_page_tables(u32 level)
+static int stage2_block_get_nr_page_tables(s8 level)
 {
 	switch (level) {
 	case 1:
@@ -1418,7 +1441,7 @@ static int stage2_block_get_nr_page_tables(u32 level)
 		return 0;
 	default:
 		WARN_ON_ONCE(level < KVM_PGTABLE_MIN_BLOCK_LEVEL ||
-			     level >= KVM_PGTABLE_MAX_LEVELS);
+			     level > KVM_PGTABLE_LAST_LEVEL);
 		return -EINVAL;
 	};
 }
@@ -1431,13 +1454,13 @@ static int stage2_split_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	struct kvm_s2_mmu *mmu;
 	kvm_pte_t pte = ctx->old, new, *childp;
 	enum kvm_pgtable_prot prot;
-	u32 level = ctx->level;
+	s8 level = ctx->level;
 	bool force_pte;
 	int nr_pages;
 	u64 phys;
 
 	/* No huge-pages exist at the last level */
-	if (level == KVM_PGTABLE_MAX_LEVELS - 1)
+	if (level == KVM_PGTABLE_LAST_LEVEL)
 		return 0;
 
 	/* We only split valid block mappings */
@@ -1478,7 +1501,6 @@ static int stage2_split_walker(const struct kvm_pgtable_visit_ctx *ctx,
 
 	if (!stage2_try_break_pte(ctx, mmu)) {
 		kvm_pgtable_stage2_free_unlinked(mm_ops, childp, level);
-		mm_ops->put_page(childp);
 		return -EAGAIN;
 	}
 
@@ -1514,7 +1536,7 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
 	u64 vtcr = mmu->vtcr;
 	u32 ia_bits = VTCR_EL2_IPA(vtcr);
 	u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr);
-	u32 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
+	s8 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
 
 	pgd_sz = kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE;
 	pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_pages_exact(pgd_sz);
@@ -1537,7 +1559,7 @@ size_t kvm_pgtable_stage2_pgd_size(u64 vtcr)
 {
 	u32 ia_bits = VTCR_EL2_IPA(vtcr);
 	u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr);
-	u32 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
+	s8 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
 
 	return kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE;
 }
@@ -1573,7 +1595,7 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
 	pgt->pgd = NULL;
 }
 
-void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level)
+void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level)
 {
 	kvm_pteref_t ptep = (kvm_pteref_t)pgtable;
 	struct kvm_pgtable_walker walker = {
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index d87c8fcc4c24..d14504821b79 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -223,12 +223,12 @@ static void stage2_free_unlinked_table_rcu_cb(struct rcu_head *head)
 {
 	struct page *page = container_of(head, struct page, rcu_head);
 	void *pgtable = page_to_virt(page);
-	u32 level = page_private(page);
+	s8 level = page_private(page);
 
 	kvm_pgtable_stage2_free_unlinked(&kvm_s2_mm_ops, pgtable, level);
 }
 
-static void stage2_free_unlinked_table(void *addr, u32 level)
+static void stage2_free_unlinked_table(void *addr, s8 level)
 {
 	struct page *page = virt_to_page(addr);
 
@@ -804,13 +804,13 @@ static int get_user_mapping_size(struct kvm *kvm, u64 addr)
 	struct kvm_pgtable pgt = {
 		.pgd		= (kvm_pteref_t)kvm->mm->pgd,
 		.ia_bits	= vabits_actual,
-		.start_level	= (KVM_PGTABLE_MAX_LEVELS -
-				   CONFIG_PGTABLE_LEVELS),
+		.start_level	= (KVM_PGTABLE_LAST_LEVEL -
+				   CONFIG_PGTABLE_LEVELS + 1),
 		.mm_ops		= &kvm_user_mm_ops,
 	};
 	unsigned long flags;
 	kvm_pte_t pte = 0;	/* Keep GCC quiet... */
-	u32 level = ~0;
+	s8 level = S8_MAX;
 	int ret;
 
 	/*
@@ -829,7 +829,9 @@ static int get_user_mapping_size(struct kvm *kvm, u64 addr)
 	 * Not seeing an error, but not updating level? Something went
 	 * deeply wrong...
 	 */
-	if (WARN_ON(level >= KVM_PGTABLE_MAX_LEVELS))
+	if (WARN_ON(level > KVM_PGTABLE_LAST_LEVEL))
+		return -EFAULT;
+	if (WARN_ON(level < KVM_PGTABLE_FIRST_LEVEL))
 		return -EFAULT;
 
 	/* Oops, the userspace PTs are gone... Replay the fault */
@@ -1374,7 +1376,7 @@ static bool kvm_vma_mte_allowed(struct vm_area_struct *vma)
 
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			  struct kvm_memory_slot *memslot, unsigned long hva,
-			  unsigned long fault_status)
+			  bool fault_is_perm)
 {
 	int ret = 0;
 	bool write_fault, writable, force_pte = false;
@@ -1388,17 +1390,17 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	gfn_t gfn;
 	kvm_pfn_t pfn;
 	bool logging_active = memslot_is_logging(memslot);
-	unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu);
 	long vma_pagesize, fault_granule;
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
 	struct kvm_pgtable *pgt;
 
-	fault_granule = 1UL << ARM64_HW_PGTABLE_LEVEL_SHIFT(fault_level);
+	if (fault_is_perm)
+		fault_granule = kvm_vcpu_trap_get_perm_fault_granule(vcpu);
 	write_fault = kvm_is_write_fault(vcpu);
 	exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
 	VM_BUG_ON(write_fault && exec_fault);
 
-	if (fault_status == ESR_ELx_FSC_PERM && !write_fault && !exec_fault) {
+	if (fault_is_perm && !write_fault && !exec_fault) {
 		kvm_err("Unexpected L2 read permission error\n");
 		return -EFAULT;
 	}
@@ -1409,8 +1411,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * only exception to this is when dirty logging is enabled at runtime
 	 * and a write fault needs to collapse a block entry into a table.
 	 */
-	if (fault_status != ESR_ELx_FSC_PERM ||
-	    (logging_active && write_fault)) {
+	if (!fault_is_perm || (logging_active && write_fault)) {
 		ret = kvm_mmu_topup_memory_cache(memcache,
 						 kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu));
 		if (ret)
@@ -1527,8 +1528,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * backed by a THP and thus use block mapping if possible.
 	 */
 	if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) {
-		if (fault_status ==  ESR_ELx_FSC_PERM &&
-		    fault_granule > PAGE_SIZE)
+		if (fault_is_perm && fault_granule > PAGE_SIZE)
 			vma_pagesize = fault_granule;
 		else
 			vma_pagesize = transparent_hugepage_adjust(kvm, memslot,
@@ -1541,7 +1541,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		}
 	}
 
-	if (fault_status != ESR_ELx_FSC_PERM && !device && kvm_has_mte(kvm)) {
+	if (!fault_is_perm && !device && kvm_has_mte(kvm)) {
 		/* Check the VMM hasn't introduced a new disallowed VMA */
 		if (mte_allowed) {
 			sanitise_mte_tags(kvm, pfn, vma_pagesize);
@@ -1567,7 +1567,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * permissions only if vma_pagesize equals fault_granule. Otherwise,
 	 * kvm_pgtable_stage2_map() should be called to change block size.
 	 */
-	if (fault_status == ESR_ELx_FSC_PERM && vma_pagesize == fault_granule)
+	if (fault_is_perm && vma_pagesize == fault_granule)
 		ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
 	else
 		ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
@@ -1618,7 +1618,7 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
  */
 int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 {
-	unsigned long fault_status;
+	unsigned long esr;
 	phys_addr_t fault_ipa;
 	struct kvm_memory_slot *memslot;
 	unsigned long hva;
@@ -1626,12 +1626,12 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	gfn_t gfn;
 	int ret, idx;
 
-	fault_status = kvm_vcpu_trap_get_fault_type(vcpu);
+	esr = kvm_vcpu_get_esr(vcpu);
 
 	fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
 	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
 
-	if (fault_status == ESR_ELx_FSC_FAULT) {
+	if (esr_fsc_is_permission_fault(esr)) {
 		/* Beyond sanitised PARange (which is the IPA limit) */
 		if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) {
 			kvm_inject_size_fault(vcpu);
@@ -1666,9 +1666,9 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 			      kvm_vcpu_get_hfar(vcpu), fault_ipa);
 
 	/* Check the stage-2 fault is trans. fault or write fault */
-	if (fault_status != ESR_ELx_FSC_FAULT &&
-	    fault_status != ESR_ELx_FSC_PERM &&
-	    fault_status != ESR_ELx_FSC_ACCESS) {
+	if (!esr_fsc_is_translation_fault(esr) &&
+	    !esr_fsc_is_permission_fault(esr) &&
+	    !esr_fsc_is_access_flag_fault(esr)) {
 		kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
 			kvm_vcpu_trap_get_class(vcpu),
 			(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
@@ -1730,13 +1730,14 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	/* Userspace should not be able to register out-of-bounds IPAs */
 	VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->arch.hw_mmu));
 
-	if (fault_status == ESR_ELx_FSC_ACCESS) {
+	if (esr_fsc_is_access_flag_fault(esr)) {
 		handle_access_fault(vcpu, fault_ipa);
 		ret = 1;
 		goto out_unlock;
 	}
 
-	ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status);
+	ret = user_mem_abort(vcpu, fault_ipa, memslot, hva,
+			     esr_fsc_is_permission_fault(esr));
 	if (ret == 0)
 		ret = 1;
 out:
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 042695a210ce..ba95d044bc98 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -23,13 +23,9 @@
  * This list should get updated as new features get added to the NV
  * support, and new extension to the architecture.
  */
-void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p,
-			  const struct sys_reg_desc *r)
+static u64 limit_nv_id_reg(u32 id, u64 val)
 {
-	u32 id = reg_to_encoding(r);
-	u64 val, tmp;
-
-	val = p->regval;
+	u64 tmp;
 
 	switch (id) {
 	case SYS_ID_AA64ISAR0_EL1:
@@ -158,5 +154,17 @@ void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p,
 		break;
 	}
 
-	p->regval = val;
+	return val;
+}
+int kvm_init_nv_sysregs(struct kvm *kvm)
+{
+	mutex_lock(&kvm->arch.config_lock);
+
+	for (int i = 0; i < KVM_ARM_ID_REG_NUM; i++)
+		kvm->arch.id_regs[i] = limit_nv_id_reg(IDX_IDREG(i),
+						       kvm->arch.id_regs[i]);
+
+	mutex_unlock(&kvm->arch.config_lock);
+
+	return 0;
 }
diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index 8350fb8fee0b..b7be96a53597 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -101,6 +101,17 @@ void __init kvm_hyp_reserve(void)
 		 hyp_mem_base);
 }
 
+static void __pkvm_destroy_hyp_vm(struct kvm *host_kvm)
+{
+	if (host_kvm->arch.pkvm.handle) {
+		WARN_ON(kvm_call_hyp_nvhe(__pkvm_teardown_vm,
+					  host_kvm->arch.pkvm.handle));
+	}
+
+	host_kvm->arch.pkvm.handle = 0;
+	free_hyp_memcache(&host_kvm->arch.pkvm.teardown_mc);
+}
+
 /*
  * Allocates and donates memory for hypervisor VM structs at EL2.
  *
@@ -181,7 +192,7 @@ static int __pkvm_create_hyp_vm(struct kvm *host_kvm)
 	return 0;
 
 destroy_vm:
-	pkvm_destroy_hyp_vm(host_kvm);
+	__pkvm_destroy_hyp_vm(host_kvm);
 	return ret;
 free_vm:
 	free_pages_exact(hyp_vm, hyp_vm_sz);
@@ -194,23 +205,19 @@ int pkvm_create_hyp_vm(struct kvm *host_kvm)
 {
 	int ret = 0;
 
-	mutex_lock(&host_kvm->lock);
+	mutex_lock(&host_kvm->arch.config_lock);
 	if (!host_kvm->arch.pkvm.handle)
 		ret = __pkvm_create_hyp_vm(host_kvm);
-	mutex_unlock(&host_kvm->lock);
+	mutex_unlock(&host_kvm->arch.config_lock);
 
 	return ret;
 }
 
 void pkvm_destroy_hyp_vm(struct kvm *host_kvm)
 {
-	if (host_kvm->arch.pkvm.handle) {
-		WARN_ON(kvm_call_hyp_nvhe(__pkvm_teardown_vm,
-					  host_kvm->arch.pkvm.handle));
-	}
-
-	host_kvm->arch.pkvm.handle = 0;
-	free_hyp_memcache(&host_kvm->arch.pkvm.teardown_mc);
+	mutex_lock(&host_kvm->arch.config_lock);
+	__pkvm_destroy_hyp_vm(host_kvm);
+	mutex_unlock(&host_kvm->arch.config_lock);
 }
 
 int pkvm_init_host_vm(struct kvm *host_kvm)
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 5bb4de162cab..68d1d05672bd 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -280,12 +280,11 @@ int __init kvm_set_ipa_limit(void)
 	parange = cpuid_feature_extract_unsigned_field(mmfr0,
 				ID_AA64MMFR0_EL1_PARANGE_SHIFT);
 	/*
-	 * IPA size beyond 48 bits could not be supported
-	 * on either 4K or 16K page size. Hence let's cap
-	 * it to 48 bits, in case it's reported as larger
-	 * on the system.
+	 * IPA size beyond 48 bits for 4K and 16K page size is only supported
+	 * when LPA2 is available. So if we have LPA2, enable it, else cap to 48
+	 * bits, in case it's reported as larger on the system.
 	 */
-	if (PAGE_SIZE != SZ_64K)
+	if (!kvm_lpa2_is_enabled() && PAGE_SIZE != SZ_64K)
 		parange = min(parange, (unsigned int)ID_AA64MMFR0_EL1_PARANGE_48);
 
 	/*
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index ff45d688bd7d..30253bd19917 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -45,44 +45,170 @@ static u64 sys_reg_to_index(const struct sys_reg_desc *reg);
 static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 		      u64 val);
 
-static bool read_from_write_only(struct kvm_vcpu *vcpu,
-				 struct sys_reg_params *params,
-				 const struct sys_reg_desc *r)
+static bool bad_trap(struct kvm_vcpu *vcpu,
+		     struct sys_reg_params *params,
+		     const struct sys_reg_desc *r,
+		     const char *msg)
 {
-	WARN_ONCE(1, "Unexpected sys_reg read to write-only register\n");
+	WARN_ONCE(1, "Unexpected %s\n", msg);
 	print_sys_reg_instr(params);
 	kvm_inject_undefined(vcpu);
 	return false;
 }
 
+static bool read_from_write_only(struct kvm_vcpu *vcpu,
+				 struct sys_reg_params *params,
+				 const struct sys_reg_desc *r)
+{
+	return bad_trap(vcpu, params, r,
+			"sys_reg read to write-only register");
+}
+
 static bool write_to_read_only(struct kvm_vcpu *vcpu,
 			       struct sys_reg_params *params,
 			       const struct sys_reg_desc *r)
 {
-	WARN_ONCE(1, "Unexpected sys_reg write to read-only register\n");
-	print_sys_reg_instr(params);
-	kvm_inject_undefined(vcpu);
-	return false;
+	return bad_trap(vcpu, params, r,
+			"sys_reg write to read-only register");
+}
+
+#define PURE_EL2_SYSREG(el2)						\
+	case el2: {							\
+		*el1r = el2;						\
+		return true;						\
+	}
+
+#define MAPPED_EL2_SYSREG(el2, el1, fn)					\
+	case el2: {							\
+		*xlate = fn;						\
+		*el1r = el1;						\
+		return true;						\
+	}
+
+static bool get_el2_to_el1_mapping(unsigned int reg,
+				   unsigned int *el1r, u64 (**xlate)(u64))
+{
+	switch (reg) {
+		PURE_EL2_SYSREG(  VPIDR_EL2	);
+		PURE_EL2_SYSREG(  VMPIDR_EL2	);
+		PURE_EL2_SYSREG(  ACTLR_EL2	);
+		PURE_EL2_SYSREG(  HCR_EL2	);
+		PURE_EL2_SYSREG(  MDCR_EL2	);
+		PURE_EL2_SYSREG(  HSTR_EL2	);
+		PURE_EL2_SYSREG(  HACR_EL2	);
+		PURE_EL2_SYSREG(  VTTBR_EL2	);
+		PURE_EL2_SYSREG(  VTCR_EL2	);
+		PURE_EL2_SYSREG(  RVBAR_EL2	);
+		PURE_EL2_SYSREG(  TPIDR_EL2	);
+		PURE_EL2_SYSREG(  HPFAR_EL2	);
+		PURE_EL2_SYSREG(  CNTHCTL_EL2	);
+		MAPPED_EL2_SYSREG(SCTLR_EL2,   SCTLR_EL1,
+				  translate_sctlr_el2_to_sctlr_el1	     );
+		MAPPED_EL2_SYSREG(CPTR_EL2,    CPACR_EL1,
+				  translate_cptr_el2_to_cpacr_el1	     );
+		MAPPED_EL2_SYSREG(TTBR0_EL2,   TTBR0_EL1,
+				  translate_ttbr0_el2_to_ttbr0_el1	     );
+		MAPPED_EL2_SYSREG(TTBR1_EL2,   TTBR1_EL1,   NULL	     );
+		MAPPED_EL2_SYSREG(TCR_EL2,     TCR_EL1,
+				  translate_tcr_el2_to_tcr_el1		     );
+		MAPPED_EL2_SYSREG(VBAR_EL2,    VBAR_EL1,    NULL	     );
+		MAPPED_EL2_SYSREG(AFSR0_EL2,   AFSR0_EL1,   NULL	     );
+		MAPPED_EL2_SYSREG(AFSR1_EL2,   AFSR1_EL1,   NULL	     );
+		MAPPED_EL2_SYSREG(ESR_EL2,     ESR_EL1,     NULL	     );
+		MAPPED_EL2_SYSREG(FAR_EL2,     FAR_EL1,     NULL	     );
+		MAPPED_EL2_SYSREG(MAIR_EL2,    MAIR_EL1,    NULL	     );
+		MAPPED_EL2_SYSREG(AMAIR_EL2,   AMAIR_EL1,   NULL	     );
+		MAPPED_EL2_SYSREG(ELR_EL2,     ELR_EL1,	    NULL	     );
+		MAPPED_EL2_SYSREG(SPSR_EL2,    SPSR_EL1,    NULL	     );
+	default:
+		return false;
+	}
 }
 
 u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
 {
 	u64 val = 0x8badf00d8badf00d;
+	u64 (*xlate)(u64) = NULL;
+	unsigned int el1r;
+
+	if (!vcpu_get_flag(vcpu, SYSREGS_ON_CPU))
+		goto memory_read;
 
-	if (vcpu_get_flag(vcpu, SYSREGS_ON_CPU) &&
-	    __vcpu_read_sys_reg_from_cpu(reg, &val))
+	if (unlikely(get_el2_to_el1_mapping(reg, &el1r, &xlate))) {
+		if (!is_hyp_ctxt(vcpu))
+			goto memory_read;
+
+		/*
+		 * If this register does not have an EL1 counterpart,
+		 * then read the stored EL2 version.
+		 */
+		if (reg == el1r)
+			goto memory_read;
+
+		/*
+		 * If we have a non-VHE guest and that the sysreg
+		 * requires translation to be used at EL1, use the
+		 * in-memory copy instead.
+		 */
+		if (!vcpu_el2_e2h_is_set(vcpu) && xlate)
+			goto memory_read;
+
+		/* Get the current version of the EL1 counterpart. */
+		WARN_ON(!__vcpu_read_sys_reg_from_cpu(el1r, &val));
 		return val;
+	}
 
+	/* EL1 register can't be on the CPU if the guest is in vEL2. */
+	if (unlikely(is_hyp_ctxt(vcpu)))
+		goto memory_read;
+
+	if (__vcpu_read_sys_reg_from_cpu(reg, &val))
+		return val;
+
+memory_read:
 	return __vcpu_sys_reg(vcpu, reg);
 }
 
 void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
 {
-	if (vcpu_get_flag(vcpu, SYSREGS_ON_CPU) &&
-	    __vcpu_write_sys_reg_to_cpu(val, reg))
+	u64 (*xlate)(u64) = NULL;
+	unsigned int el1r;
+
+	if (!vcpu_get_flag(vcpu, SYSREGS_ON_CPU))
+		goto memory_write;
+
+	if (unlikely(get_el2_to_el1_mapping(reg, &el1r, &xlate))) {
+		if (!is_hyp_ctxt(vcpu))
+			goto memory_write;
+
+		/*
+		 * Always store a copy of the write to memory to avoid having
+		 * to reverse-translate virtual EL2 system registers for a
+		 * non-VHE guest hypervisor.
+		 */
+		__vcpu_sys_reg(vcpu, reg) = val;
+
+		/* No EL1 counterpart? We're done here.? */
+		if (reg == el1r)
+			return;
+
+		if (!vcpu_el2_e2h_is_set(vcpu) && xlate)
+			val = xlate(val);
+
+		/* Redirect this to the EL1 version of the register. */
+		WARN_ON(!__vcpu_write_sys_reg_to_cpu(val, el1r));
+		return;
+	}
+
+	/* EL1 register can't be on the CPU if the guest is in vEL2. */
+	if (unlikely(is_hyp_ctxt(vcpu)))
+		goto memory_write;
+
+	if (__vcpu_write_sys_reg_to_cpu(val, reg))
 		return;
 
-	__vcpu_sys_reg(vcpu, reg) = val;
+memory_write:
+	 __vcpu_sys_reg(vcpu, reg) = val;
 }
 
 /* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */
@@ -1505,8 +1631,6 @@ static bool access_id_reg(struct kvm_vcpu *vcpu,
 		return write_to_read_only(vcpu, p, r);
 
 	p->regval = read_id_reg(vcpu, r);
-	if (vcpu_has_nv(vcpu))
-		access_nested_id_reg(vcpu, p, r);
 
 	return true;
 }
@@ -1885,6 +2009,32 @@ static unsigned int el2_visibility(const struct kvm_vcpu *vcpu,
 	return REG_HIDDEN;
 }
 
+static bool bad_vncr_trap(struct kvm_vcpu *vcpu,
+			  struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	/*
+	 * We really shouldn't be here, and this is likely the result
+	 * of a misconfigured trap, as this register should target the
+	 * VNCR page, and nothing else.
+	 */
+	return bad_trap(vcpu, p, r,
+			"trap of VNCR-backed register");
+}
+
+static bool bad_redir_trap(struct kvm_vcpu *vcpu,
+			   struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	/*
+	 * We really shouldn't be here, and this is likely the result
+	 * of a misconfigured trap, as this register should target the
+	 * corresponding EL1, and nothing else.
+	 */
+	return bad_trap(vcpu, p, r,
+			"trap of EL2 register redirected to EL1");
+}
+
 #define EL2_REG(name, acc, rst, v) {		\
 	SYS_DESC(SYS_##name),			\
 	.access = acc,				\
@@ -1894,6 +2044,9 @@ static unsigned int el2_visibility(const struct kvm_vcpu *vcpu,
 	.val = v,				\
 }
 
+#define EL2_REG_VNCR(name, rst, v)	EL2_REG(name, bad_vncr_trap, rst, v)
+#define EL2_REG_REDIR(name, rst, v)	EL2_REG(name, bad_redir_trap, rst, v)
+
 /*
  * EL{0,1}2 registers are the EL2 view on an EL0 or EL1 register when
  * HCR_EL2.E2H==1, and only in the sysreg table for convenience of
@@ -2508,32 +2661,33 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ PMU_SYS_REG(PMCCFILTR_EL0), .access = access_pmu_evtyper,
 	  .reset = reset_val, .reg = PMCCFILTR_EL0, .val = 0 },
 
-	EL2_REG(VPIDR_EL2, access_rw, reset_unknown, 0),
-	EL2_REG(VMPIDR_EL2, access_rw, reset_unknown, 0),
+	EL2_REG_VNCR(VPIDR_EL2, reset_unknown, 0),
+	EL2_REG_VNCR(VMPIDR_EL2, reset_unknown, 0),
 	EL2_REG(SCTLR_EL2, access_rw, reset_val, SCTLR_EL2_RES1),
 	EL2_REG(ACTLR_EL2, access_rw, reset_val, 0),
-	EL2_REG(HCR_EL2, access_rw, reset_val, 0),
+	EL2_REG_VNCR(HCR_EL2, reset_val, 0),
 	EL2_REG(MDCR_EL2, access_rw, reset_val, 0),
 	EL2_REG(CPTR_EL2, access_rw, reset_val, CPTR_NVHE_EL2_RES1),
-	EL2_REG(HSTR_EL2, access_rw, reset_val, 0),
-	EL2_REG(HFGRTR_EL2, access_rw, reset_val, 0),
-	EL2_REG(HFGWTR_EL2, access_rw, reset_val, 0),
-	EL2_REG(HFGITR_EL2, access_rw, reset_val, 0),
-	EL2_REG(HACR_EL2, access_rw, reset_val, 0),
+	EL2_REG_VNCR(HSTR_EL2, reset_val, 0),
+	EL2_REG_VNCR(HFGRTR_EL2, reset_val, 0),
+	EL2_REG_VNCR(HFGWTR_EL2, reset_val, 0),
+	EL2_REG_VNCR(HFGITR_EL2, reset_val, 0),
+	EL2_REG_VNCR(HACR_EL2, reset_val, 0),
 
-	EL2_REG(HCRX_EL2, access_rw, reset_val, 0),
+	EL2_REG_VNCR(HCRX_EL2, reset_val, 0),
 
 	EL2_REG(TTBR0_EL2, access_rw, reset_val, 0),
 	EL2_REG(TTBR1_EL2, access_rw, reset_val, 0),
 	EL2_REG(TCR_EL2, access_rw, reset_val, TCR_EL2_RES1),
-	EL2_REG(VTTBR_EL2, access_rw, reset_val, 0),
-	EL2_REG(VTCR_EL2, access_rw, reset_val, 0),
+	EL2_REG_VNCR(VTTBR_EL2, reset_val, 0),
+	EL2_REG_VNCR(VTCR_EL2, reset_val, 0),
 
 	{ SYS_DESC(SYS_DACR32_EL2), trap_undef, reset_unknown, DACR32_EL2 },
-	EL2_REG(HDFGRTR_EL2, access_rw, reset_val, 0),
-	EL2_REG(HDFGWTR_EL2, access_rw, reset_val, 0),
-	EL2_REG(SPSR_EL2, access_rw, reset_val, 0),
-	EL2_REG(ELR_EL2, access_rw, reset_val, 0),
+	EL2_REG_VNCR(HDFGRTR_EL2, reset_val, 0),
+	EL2_REG_VNCR(HDFGWTR_EL2, reset_val, 0),
+	EL2_REG_VNCR(HAFGRTR_EL2, reset_val, 0),
+	EL2_REG_REDIR(SPSR_EL2, reset_val, 0),
+	EL2_REG_REDIR(ELR_EL2, reset_val, 0),
 	{ SYS_DESC(SYS_SP_EL1), access_sp_el1},
 
 	/* AArch32 SPSR_* are RES0 if trapped from a NV guest */
@@ -2549,10 +2703,10 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_IFSR32_EL2), trap_undef, reset_unknown, IFSR32_EL2 },
 	EL2_REG(AFSR0_EL2, access_rw, reset_val, 0),
 	EL2_REG(AFSR1_EL2, access_rw, reset_val, 0),
-	EL2_REG(ESR_EL2, access_rw, reset_val, 0),
+	EL2_REG_REDIR(ESR_EL2, reset_val, 0),
 	{ SYS_DESC(SYS_FPEXC32_EL2), trap_undef, reset_val, FPEXC32_EL2, 0x700 },
 
-	EL2_REG(FAR_EL2, access_rw, reset_val, 0),
+	EL2_REG_REDIR(FAR_EL2, reset_val, 0),
 	EL2_REG(HPFAR_EL2, access_rw, reset_val, 0),
 
 	EL2_REG(MAIR_EL2, access_rw, reset_val, 0),
@@ -2565,24 +2719,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	EL2_REG(CONTEXTIDR_EL2, access_rw, reset_val, 0),
 	EL2_REG(TPIDR_EL2, access_rw, reset_val, 0),
 
-	EL2_REG(CNTVOFF_EL2, access_rw, reset_val, 0),
+	EL2_REG_VNCR(CNTVOFF_EL2, reset_val, 0),
 	EL2_REG(CNTHCTL_EL2, access_rw, reset_val, 0),
 
-	EL12_REG(SCTLR, access_vm_reg, reset_val, 0x00C50078),
-	EL12_REG(CPACR, access_rw, reset_val, 0),
-	EL12_REG(TTBR0, access_vm_reg, reset_unknown, 0),
-	EL12_REG(TTBR1, access_vm_reg, reset_unknown, 0),
-	EL12_REG(TCR, access_vm_reg, reset_val, 0),
-	{ SYS_DESC(SYS_SPSR_EL12), access_spsr},
-	{ SYS_DESC(SYS_ELR_EL12), access_elr},
-	EL12_REG(AFSR0, access_vm_reg, reset_unknown, 0),
-	EL12_REG(AFSR1, access_vm_reg, reset_unknown, 0),
-	EL12_REG(ESR, access_vm_reg, reset_unknown, 0),
-	EL12_REG(FAR, access_vm_reg, reset_unknown, 0),
-	EL12_REG(MAIR, access_vm_reg, reset_unknown, 0),
-	EL12_REG(AMAIR, access_vm_reg, reset_amair_el1, 0),
-	EL12_REG(VBAR, access_rw, reset_val, 0),
-	EL12_REG(CONTEXTIDR, access_vm_reg, reset_val, 0),
 	EL12_REG(CNTKCTL, access_rw, reset_val, 0),
 
 	EL2_REG(SP_EL2, NULL, reset_unknown, 0),
diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index 2dad2d095160..28a93074eca1 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -468,6 +468,9 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
 		}
 
 		irq = vgic_get_irq(vcpu->kvm, NULL, intids[i]);
+		if (!irq)
+			continue;
+
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 		irq->pending_latch = pendmask & (1U << bit_nr);
 		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
@@ -590,7 +593,11 @@ static struct vgic_irq *vgic_its_check_cache(struct kvm *kvm, phys_addr_t db,
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&dist->lpi_list_lock, flags);
+
 	irq = __vgic_its_check_cache(dist, db, devid, eventid);
+	if (irq)
+		vgic_get_irq_kref(irq);
+
 	raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
 
 	return irq;
@@ -769,6 +776,7 @@ int vgic_its_inject_cached_translation(struct kvm *kvm, struct kvm_msi *msi)
 	raw_spin_lock_irqsave(&irq->irq_lock, flags);
 	irq->pending_latch = true;
 	vgic_queue_irq_unlock(kvm, irq, flags);
+	vgic_put_irq(kvm, irq);
 
 	return 0;
 }
@@ -1427,6 +1435,8 @@ static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its,
 
 	for (i = 0; i < irq_count; i++) {
 		irq = vgic_get_irq(kvm, NULL, intids[i]);
+		if (!irq)
+			continue;
 
 		update_affinity(irq, vcpu2);
 
diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
index a764b0ab8bf9..c15ee1df036a 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
@@ -357,31 +357,13 @@ static int vgic_v3_uaccess_write_pending(struct kvm_vcpu *vcpu,
 					 gpa_t addr, unsigned int len,
 					 unsigned long val)
 {
-	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
-	int i;
-	unsigned long flags;
-
-	for (i = 0; i < len * 8; i++) {
-		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
-
-		raw_spin_lock_irqsave(&irq->irq_lock, flags);
-		if (test_bit(i, &val)) {
-			/*
-			 * pending_latch is set irrespective of irq type
-			 * (level or edge) to avoid dependency that VM should
-			 * restore irq config before pending info.
-			 */
-			irq->pending_latch = true;
-			vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
-		} else {
-			irq->pending_latch = false;
-			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
-		}
+	int ret;
 
-		vgic_put_irq(vcpu->kvm, irq);
-	}
+	ret = vgic_uaccess_write_spending(vcpu, addr, len, val);
+	if (ret)
+		return ret;
 
-	return 0;
+	return vgic_uaccess_write_cpending(vcpu, addr, len, ~val);
 }
 
 /* We want to avoid outer shareable. */
diff --git a/arch/arm64/kvm/vgic/vgic-mmio.c b/arch/arm64/kvm/vgic/vgic-mmio.c
index ff558c05e990..cf76523a2194 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio.c
@@ -301,9 +301,8 @@ static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq)
 		vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2);
 }
 
-void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
-			      gpa_t addr, unsigned int len,
-			      unsigned long val)
+static void __set_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len,
+			  unsigned long val, bool is_user)
 {
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 	int i;
@@ -312,14 +311,22 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 	for_each_set_bit(i, &val, len * 8) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
-		/* GICD_ISPENDR0 SGI bits are WI */
-		if (is_vgic_v2_sgi(vcpu, irq)) {
+		/* GICD_ISPENDR0 SGI bits are WI when written from the guest. */
+		if (is_vgic_v2_sgi(vcpu, irq) && !is_user) {
 			vgic_put_irq(vcpu->kvm, irq);
 			continue;
 		}
 
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
+		/*
+		 * GICv2 SGIs are terribly broken. We can't restore
+		 * the source of the interrupt, so just pick the vcpu
+		 * itself as the source...
+		 */
+		if (is_vgic_v2_sgi(vcpu, irq))
+			irq->source |= BIT(vcpu->vcpu_id);
+
 		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
 			/* HW SGI? Ask the GIC to inject it */
 			int err;
@@ -335,7 +342,7 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 		}
 
 		irq->pending_latch = true;
-		if (irq->hw)
+		if (irq->hw && !is_user)
 			vgic_irq_set_phys_active(irq, true);
 
 		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
@@ -343,33 +350,18 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 	}
 }
 
+void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
+			      gpa_t addr, unsigned int len,
+			      unsigned long val)
+{
+	__set_pending(vcpu, addr, len, val, false);
+}
+
 int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu,
 				gpa_t addr, unsigned int len,
 				unsigned long val)
 {
-	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
-	int i;
-	unsigned long flags;
-
-	for_each_set_bit(i, &val, len * 8) {
-		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
-
-		raw_spin_lock_irqsave(&irq->irq_lock, flags);
-		irq->pending_latch = true;
-
-		/*
-		 * GICv2 SGIs are terribly broken. We can't restore
-		 * the source of the interrupt, so just pick the vcpu
-		 * itself as the source...
-		 */
-		if (is_vgic_v2_sgi(vcpu, irq))
-			irq->source |= BIT(vcpu->vcpu_id);
-
-		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
-
-		vgic_put_irq(vcpu->kvm, irq);
-	}
-
+	__set_pending(vcpu, addr, len, val, true);
 	return 0;
 }
 
@@ -394,9 +386,9 @@ static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq)
 		vgic_irq_set_phys_active(irq, false);
 }
 
-void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
-			      gpa_t addr, unsigned int len,
-			      unsigned long val)
+static void __clear_pending(struct kvm_vcpu *vcpu,
+			    gpa_t addr, unsigned int len,
+			    unsigned long val, bool is_user)
 {
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 	int i;
@@ -405,14 +397,22 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 	for_each_set_bit(i, &val, len * 8) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
-		/* GICD_ICPENDR0 SGI bits are WI */
-		if (is_vgic_v2_sgi(vcpu, irq)) {
+		/* GICD_ICPENDR0 SGI bits are WI when written from the guest. */
+		if (is_vgic_v2_sgi(vcpu, irq) && !is_user) {
 			vgic_put_irq(vcpu->kvm, irq);
 			continue;
 		}
 
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
+		/*
+		 * More fun with GICv2 SGIs! If we're clearing one of them
+		 * from userspace, which source vcpu to clear? Let's not
+		 * even think of it, and blow the whole set.
+		 */
+		if (is_vgic_v2_sgi(vcpu, irq))
+			irq->source = 0;
+
 		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
 			/* HW SGI? Ask the GIC to clear its pending bit */
 			int err;
@@ -427,7 +427,7 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 			continue;
 		}
 
-		if (irq->hw)
+		if (irq->hw && !is_user)
 			vgic_hw_irq_cpending(vcpu, irq);
 		else
 			irq->pending_latch = false;
@@ -437,33 +437,18 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 	}
 }
 
+void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
+			      gpa_t addr, unsigned int len,
+			      unsigned long val)
+{
+	__clear_pending(vcpu, addr, len, val, false);
+}
+
 int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu,
 				gpa_t addr, unsigned int len,
 				unsigned long val)
 {
-	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
-	int i;
-	unsigned long flags;
-
-	for_each_set_bit(i, &val, len * 8) {
-		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
-
-		raw_spin_lock_irqsave(&irq->irq_lock, flags);
-		/*
-		 * More fun with GICv2 SGIs! If we're clearing one of them
-		 * from userspace, which source vcpu to clear? Let's not
-		 * even think of it, and blow the whole set.
-		 */
-		if (is_vgic_v2_sgi(vcpu, irq))
-			irq->source = 0;
-
-		irq->pending_latch = false;
-
-		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
-
-		vgic_put_irq(vcpu->kvm, irq);
-	}
-
+	__clear_pending(vcpu, addr, len, val, true);
 	return 0;
 }
 
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 3cb101e8cb29..61886e43e3a1 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -47,7 +47,7 @@ void arch_teardown_dma_ops(struct device *dev)
 #endif
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	int cls = cache_line_size_of_cpu();
 
@@ -58,7 +58,7 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		   ARCH_DMA_MINALIGN, cls);
 
 	dev->dma_coherent = coherent;
-	if (iommu)
+	if (device_iommu_mapped(dev))
 		iommu_setup_dma_ops(dev, dma_base, dma_base + size - 1);
 
 	xen_setup_dma_ops(dev);
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index 1e07d74d7a6c..b912b1409fc0 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -84,7 +84,6 @@ WORKAROUND_2077057
 WORKAROUND_2457168
 WORKAROUND_2645198
 WORKAROUND_2658417
-WORKAROUND_2966298
 WORKAROUND_AMPERE_AC03_CPU_38
 WORKAROUND_TRBE_OVERWRITE_FILL_MODE
 WORKAROUND_TSB_FLUSH_FAILURE
@@ -100,3 +99,4 @@ WORKAROUND_NVIDIA_CARMEL_CNP
 WORKAROUND_QCOM_FALKOR_E1003
 WORKAROUND_REPEAT_TLBI
 WORKAROUND_SPECULATIVE_AT
+WORKAROUND_SPECULATIVE_UNPRIV_LOAD
diff --git a/arch/csky/abiv1/inc/abi/cacheflush.h b/arch/csky/abiv1/inc/abi/cacheflush.h
index 908d8b0bc4fd..d011a81575d2 100644
--- a/arch/csky/abiv1/inc/abi/cacheflush.h
+++ b/arch/csky/abiv1/inc/abi/cacheflush.h
@@ -43,6 +43,7 @@ static inline void flush_anon_page(struct vm_area_struct *vma,
  */
 extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
 #define flush_cache_vmap(start, end)		cache_wbinv_all()
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		cache_wbinv_all()
 
 #define flush_icache_range(start, end)		cache_wbinv_range(start, end)
diff --git a/arch/csky/abiv2/inc/abi/cacheflush.h b/arch/csky/abiv2/inc/abi/cacheflush.h
index 40be16907267..6513ac5d2578 100644
--- a/arch/csky/abiv2/inc/abi/cacheflush.h
+++ b/arch/csky/abiv2/inc/abi/cacheflush.h
@@ -41,6 +41,7 @@ void flush_icache_mm_range(struct mm_struct *mm,
 void flush_icache_deferred(struct mm_struct *mm);
 
 #define flush_cache_vmap(start, end)		do { } while (0)
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		do { } while (0)
 
 #define copy_to_user_page(vma, page, vaddr, dst, src, len) \
diff --git a/arch/csky/configs/defconfig b/arch/csky/configs/defconfig
index af722e4dfb47..ff559e5162aa 100644
--- a/arch/csky/configs/defconfig
+++ b/arch/csky/configs/defconfig
@@ -34,7 +34,8 @@ CONFIG_GENERIC_PHY=y
 CONFIG_EXT4_FS=y
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA=y
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
 CONFIG_FSCACHE_STATS=y
 CONFIG_CACHEFILES=m
 CONFIG_MSDOS_FS=y
diff --git a/arch/csky/include/asm/jump_label.h b/arch/csky/include/asm/jump_label.h
index 98a3f4b168bd..ef2e37a10a0f 100644
--- a/arch/csky/include/asm/jump_label.h
+++ b/arch/csky/include/asm/jump_label.h
@@ -12,7 +12,7 @@
 static __always_inline bool arch_static_branch(struct static_key *key,
 					       bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	nop32					\n"
 		"	.pushsection	__jump_table, \"aw\"	\n"
 		"	.align		2			\n"
@@ -29,7 +29,7 @@ label:
 static __always_inline bool arch_static_branch_jump(struct static_key *key,
 						    bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	bsr32		%l[label]		\n"
 		"	.pushsection	__jump_table, \"aw\"	\n"
 		"	.align		2			\n"
diff --git a/arch/loongarch/Kbuild b/arch/loongarch/Kbuild
index beb8499dd8ed..bfa21465d83a 100644
--- a/arch/loongarch/Kbuild
+++ b/arch/loongarch/Kbuild
@@ -4,6 +4,7 @@ obj-y += net/
 obj-y += vdso/
 
 obj-$(CONFIG_KVM) += kvm/
+obj-$(CONFIG_BUILTIN_DTB) += boot/dts/
 
 # for cleaning
 subdir- += boot
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index ee123820a476..929f68926b34 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -5,12 +5,14 @@ config LOONGARCH
 	select ACPI
 	select ACPI_GENERIC_GSI if ACPI
 	select ACPI_MCFG if ACPI
+	select ACPI_HOTPLUG_CPU if ACPI_PROCESSOR && HOTPLUG_CPU
 	select ACPI_PPTT if ACPI
 	select ACPI_SYSTEM_POWER_STATES_SUPPORT	if ACPI
 	select ARCH_BINFMT_ELF_STATE
 	select ARCH_DISABLE_KASAN_INLINE
 	select ARCH_ENABLE_MEMORY_HOTPLUG
 	select ARCH_ENABLE_MEMORY_HOTREMOVE
+	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
 	select ARCH_HAS_ACPI_TABLE_UPGRADE	if ACPI
 	select ARCH_HAS_CPU_FINALIZE_INIT
 	select ARCH_HAS_FORTIFY_SOURCE
@@ -71,6 +73,7 @@ config LOONGARCH
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_CPU_AUTOPROBE
+	select GENERIC_CPU_DEVICES
 	select GENERIC_ENTRY
 	select GENERIC_GETTIMEOFDAY
 	select GENERIC_IOREMAP if !ARCH_IOREMAP
@@ -97,6 +100,7 @@ config LOONGARCH
 	select HAVE_ARCH_KFENCE
 	select HAVE_ARCH_KGDB if PERF_EVENTS
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
+	select HAVE_ARCH_SECCOMP
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
@@ -140,6 +144,7 @@ config LOONGARCH
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RETHOOK
 	select HAVE_RSEQ
+	select HAVE_RUST
 	select HAVE_SAMPLE_FTRACE_DIRECT
 	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
 	select HAVE_SETUP_PER_CPU_AREA if NUMA
@@ -374,6 +379,24 @@ config CMDLINE_FORCE
 
 endchoice
 
+config BUILTIN_DTB
+	bool "Enable built-in dtb in kernel"
+	depends on OF
+	help
+	  Some existing systems do not provide a canonical device tree to
+	  the kernel at boot time. Let's provide a device tree table in the
+	  kernel, keyed by the dts filename, containing the relevant DTBs.
+
+	  Built-in DTBs are generic enough and can be used as references.
+
+config BUILTIN_DTB_NAME
+	string "Source file for built-in dtb"
+	depends on BUILTIN_DTB
+	help
+	  Base name (without suffix, relative to arch/loongarch/boot/dts/)
+	  for the DTS file that will be used to produce the DTB linked into
+	  the kernel.
+
 config DMI
 	bool "Enable DMI scanning"
 	select DMI_SCAN_MACHINE_NON_EFI_FALLBACK
@@ -575,6 +598,9 @@ config ARCH_SELECTS_CRASH_DUMP
 	depends on CRASH_DUMP
 	select RELOCATABLE
 
+config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
+	def_bool CRASH_CORE
+
 config RELOCATABLE
 	bool "Relocatable kernel"
 	help
@@ -608,23 +634,6 @@ config RANDOMIZE_BASE_MAX_OFFSET
 
 	  This is limited by the size of the lower address memory, 256MB.
 
-config SECCOMP
-	bool "Enable seccomp to safely compute untrusted bytecode"
-	depends on PROC_FS
-	default y
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via /proc/<pid>/seccomp, it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
-	  If unsure, say Y. Only embedded should say N here.
-
 endmenu
 
 config ARCH_SELECT_MEMORY_MODEL
@@ -643,10 +652,6 @@ config ARCH_SPARSEMEM_ENABLE
 	  or have huge holes in the physical address space for other reasons.
 	  See <file:Documentation/mm/numa.rst> for more.
 
-config ARCH_ENABLE_THP_MIGRATION
-	def_bool y
-	depends on TRANSPARENT_HUGEPAGE
-
 config ARCH_MEMORY_PROBE
 	def_bool y
 	depends on MEMORY_HOTPLUG
diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile
index 4ba8d67ddb09..983aa2b1629a 100644
--- a/arch/loongarch/Makefile
+++ b/arch/loongarch/Makefile
@@ -6,6 +6,7 @@
 boot	:= arch/loongarch/boot
 
 KBUILD_DEFCONFIG := loongson3_defconfig
+KBUILD_DTBS      := dtbs
 
 image-name-y			:= vmlinux
 image-name-$(CONFIG_EFI_ZBOOT)	:= vmlinuz
@@ -81,8 +82,11 @@ KBUILD_AFLAGS_MODULE		+= -Wa,-mla-global-with-abs
 KBUILD_CFLAGS_MODULE		+= -fplt -Wa,-mla-global-with-abs,-mla-local-with-abs
 endif
 
+KBUILD_RUSTFLAGS_MODULE		+= -Crelocation-model=pic
+
 ifeq ($(CONFIG_RELOCATABLE),y)
 KBUILD_CFLAGS_KERNEL		+= -fPIE
+KBUILD_RUSTFLAGS_KERNEL		+= -Crelocation-model=pie
 LDFLAGS_vmlinux			+= -static -pie --no-dynamic-linker -z notext $(call ld-option, --apply-dynamic-relocs)
 endif
 
@@ -141,7 +145,7 @@ endif
 
 vdso-install-y += arch/loongarch/vdso/vdso.so.dbg
 
-all:	$(notdir $(KBUILD_IMAGE))
+all:	$(notdir $(KBUILD_IMAGE)) $(KBUILD_DTBS)
 
 vmlinuz.efi: vmlinux.efi
 
diff --git a/arch/loongarch/boot/dts/Makefile b/arch/loongarch/boot/dts/Makefile
index 5f1f55e911ad..747d0c3f6389 100644
--- a/arch/loongarch/boot/dts/Makefile
+++ b/arch/loongarch/boot/dts/Makefile
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
-dtstree	:= $(srctree)/$(src)
 
-dtb-y := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts))
+dtb-y = loongson-2k0500-ref.dtb loongson-2k1000-ref.dtb loongson-2k2000-ref.dtb
+
+obj-$(CONFIG_BUILTIN_DTB)	+= $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_NAME))
diff --git a/arch/loongarch/boot/dts/loongson-2k0500-ref.dts b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts
new file mode 100644
index 000000000000..8aefb0c12672
--- /dev/null
+++ b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+/dts-v1/;
+
+#include "loongson-2k0500.dtsi"
+
+/ {
+	compatible = "loongson,ls2k0500-ref", "loongson,ls2k0500";
+	model = "Loongson-2K0500 Reference Board";
+
+	aliases {
+		ethernet0 = &gmac0;
+		ethernet1 = &gmac1;
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory@200000 {
+		device_type = "memory";
+		reg = <0x0 0x00200000 0x0 0x0ee00000>,
+		      <0x0 0x90000000 0x0 0x60000000>;
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		linux,cma {
+			compatible = "shared-dma-pool";
+			reusable;
+			size = <0x0 0x2000000>;
+			linux,cma-default;
+		};
+	};
+};
+
+&gmac0 {
+	status = "okay";
+
+	phy-mode = "rgmii";
+	bus_id = <0x0>;
+};
+
+&gmac1 {
+	status = "okay";
+
+	phy-mode = "rgmii";
+	bus_id = <0x1>;
+};
+
+&i2c0 {
+	status = "okay";
+
+	#address-cells = <1>;
+	#size-cells = <0>;
+	eeprom@57 {
+		compatible = "atmel,24c16";
+		reg = <0x57>;
+		pagesize = <16>;
+	};
+};
+
+&ehci0 {
+	status = "okay";
+};
+
+&ohci0 {
+	status = "okay";
+};
+
+&sata {
+	status = "okay";
+};
+
+&uart0 {
+	status = "okay";
+};
+
+&rtc0 {
+	status = "okay";
+};
diff --git a/arch/loongarch/boot/dts/loongson-2k0500.dtsi b/arch/loongarch/boot/dts/loongson-2k0500.dtsi
new file mode 100644
index 000000000000..444779c21034
--- /dev/null
+++ b/arch/loongarch/boot/dts/loongson-2k0500.dtsi
@@ -0,0 +1,266 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/interrupt-controller/irq.h>
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			compatible = "loongson,la264";
+			device_type = "cpu";
+			reg = <0x0>;
+			clocks = <&cpu_clk>;
+		};
+	};
+
+	cpu_clk: cpu-clk {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <500000000>;
+	};
+
+	cpuintc: interrupt-controller {
+		compatible = "loongson,cpu-interrupt-controller";
+		#interrupt-cells = <1>;
+		interrupt-controller;
+	};
+
+	bus@10000000 {
+		compatible = "simple-bus";
+		ranges = <0x0 0x10000000 0x0 0x10000000 0x0 0x10000000>,
+			 <0x0 0x02000000 0x0 0x02000000 0x0 0x02000000>,
+			 <0x0 0x20000000 0x0 0x20000000 0x0 0x10000000>,
+			 <0x0 0x40000000 0x0 0x40000000 0x0 0x40000000>,
+			 <0xfe 0x0 0xfe 0x0 0x0 0x40000000>;
+		#address-cells = <2>;
+		#size-cells = <2>;
+
+		isa@16400000 {
+			compatible = "isa";
+			#size-cells = <1>;
+			#address-cells = <2>;
+			ranges = <1 0x0 0x0 0x16400000 0x4000>;
+		};
+
+		liointc0: interrupt-controller@1fe11400 {
+			compatible = "loongson,liointc-2.0";
+			reg = <0x0 0x1fe11400 0x0 0x40>,
+			      <0x0 0x1fe11040 0x0 0x8>;
+			reg-names = "main", "isr0";
+
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupt-parent = <&cpuintc>;
+			interrupts = <2>;
+			interrupt-names = "int0";
+
+			loongson,parent_int_map = <0xffffffff>, /* int0 */
+						  <0x00000000>, /* int1 */
+						  <0x00000000>, /* int2 */
+						  <0x00000000>; /* int3 */
+		};
+
+		liointc1: interrupt-controller@1fe11440 {
+			compatible = "loongson,liointc-2.0";
+			reg = <0x0 0x1fe11440 0x0 0x40>,
+			      <0x0 0x1fe11048 0x0 0x8>;
+			reg-names = "main", "isr0";
+
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupt-parent = <&cpuintc>;
+			interrupts = <4>;
+			interrupt-names = "int2";
+
+			loongson,parent_int_map = <0x00000000>, /* int0 */
+						  <0x00000000>, /* int1 */
+						  <0xffffffff>, /* int2 */
+						  <0x00000000>; /* int3 */
+		};
+
+		eiointc: interrupt-controller@1fe11600 {
+			compatible = "loongson,ls2k0500-eiointc";
+			reg = <0x0 0x1fe11600 0x0 0xea00>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&cpuintc>;
+			interrupts = <3>;
+		};
+
+		gmac0: ethernet@1f020000 {
+			compatible = "snps,dwmac-3.70a";
+			reg = <0x0 0x1f020000 0x0 0x10000>;
+			interrupt-parent = <&liointc0>;
+			interrupts = <12 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "macirq";
+			status = "disabled";
+		};
+
+		gmac1: ethernet@1f030000 {
+			compatible = "snps,dwmac-3.70a";
+			reg = <0x0 0x1f030000 0x0 0x10000>;
+			interrupt-parent = <&liointc0>;
+			interrupts = <14 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "macirq";
+			status = "disabled";
+		};
+
+		sata: sata@1f040000 {
+			compatible = "snps,spear-ahci";
+			reg = <0x0 0x1f040000 0x0 0x10000>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <75>;
+			status = "disabled";
+		};
+
+		ehci0: usb@1f050000 {
+			compatible = "generic-ehci";
+			reg = <0x0 0x1f050000 0x0 0x8000>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <71>;
+			status = "disabled";
+		};
+
+		ohci0: usb@1f058000 {
+			compatible = "generic-ohci";
+			reg = <0x0 0x1f058000 0x0 0x8000>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <72>;
+			status = "disabled";
+		};
+
+		uart0: serial@1ff40800 {
+			compatible = "ns16550a";
+			reg = <0x0 0x1ff40800 0x0 0x10>;
+			clock-frequency = <100000000>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <2>;
+			no-loopback-test;
+			status = "disabled";
+		};
+
+		i2c0: i2c@1ff48000 {
+			compatible = "loongson,ls2k-i2c";
+			reg = <0x0 0x1ff48000 0x0 0x0800>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <14>;
+			status = "disabled";
+		};
+
+		i2c@1ff48800 {
+			compatible = "loongson,ls2k-i2c";
+			reg = <0x0 0x1ff48800 0x0 0x0800>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <15>;
+			status = "disabled";
+		};
+
+		i2c@1ff49000 {
+			compatible = "loongson,ls2k-i2c";
+			reg = <0x0 0x1ff49000 0x0 0x0800>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <16>;
+			status = "disabled";
+		};
+
+		i2c@1ff49800 {
+			compatible = "loongson,ls2k-i2c";
+			reg = <0x0 0x1ff49800 0x0 0x0800>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <17>;
+			status = "disabled";
+		};
+
+		i2c@1ff4a000 {
+			compatible = "loongson,ls2k-i2c";
+			reg = <0x0 0x1ff4a000 0x0 0x0800>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <18>;
+			status = "disabled";
+		};
+
+		i2c@1ff4a800 {
+			compatible = "loongson,ls2k-i2c";
+			reg = <0x0 0x1ff4a800 0x0 0x0800>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <19>;
+			status = "disabled";
+		};
+
+		pmc: power-management@1ff6c000 {
+			compatible = "loongson,ls2k0500-pmc", "syscon";
+			reg = <0x0 0x1ff6c000 0x0 0x58>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <56>;
+			loongson,suspend-address = <0x0 0x1c000500>;
+
+			syscon-reboot {
+				compatible = "syscon-reboot";
+				offset = <0x30>;
+				mask = <0x1>;
+			};
+
+			syscon-poweroff {
+				compatible = "syscon-poweroff";
+				regmap = <&pmc>;
+				offset = <0x14>;
+				mask = <0x3c00>;
+				value = <0x3c00>;
+			};
+		};
+
+		rtc0: rtc@1ff6c100 {
+			compatible = "loongson,ls2k0500-rtc", "loongson,ls7a-rtc";
+			reg = <0x0 0x1ff6c100 0x0 0x100>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <35>;
+			status = "disabled";
+		};
+
+		pcie@1a000000 {
+			compatible = "loongson,ls2k-pci";
+			reg = <0x0 0x1a000000 0x0 0x02000000>,
+			      <0xfe 0x0 0x0 0x20000000>;
+			#address-cells = <3>;
+			#size-cells = <2>;
+			device_type = "pci";
+			bus-range = <0x0 0x5>;
+			ranges = <0x01000000 0x0 0x00004000 0x0 0x16404000 0x0 0x00004000>,
+				 <0x02000000 0x0 0x40000000 0x0 0x40000000 0x0 0x40000000>;
+
+			pcie@0,0 {
+				reg = <0x0000 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&eiointc>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &eiointc 81>;
+				ranges;
+			};
+
+			pcie@1,0 {
+				reg = <0x0800 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&eiointc>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &eiointc 82>;
+				ranges;
+			};
+		};
+	};
+};
diff --git a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts
new file mode 100644
index 000000000000..ed4d32434041
--- /dev/null
+++ b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts
@@ -0,0 +1,183 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+/dts-v1/;
+
+#include "loongson-2k1000.dtsi"
+
+/ {
+	compatible = "loongson,ls2k1000-ref", "loongson,ls2k1000";
+	model = "Loongson-2K1000 Reference Board";
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory@200000 {
+		device_type = "memory";
+		reg = <0x0 0x00200000 0x0 0x06e00000>,
+		      <0x0 0x08000000 0x0 0x07000000>,
+		      <0x0 0x90000000 0x1 0xe0000000>;
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		linux,cma {
+			compatible = "shared-dma-pool";
+			reusable;
+			size = <0x0 0x2000000>;
+			linux,cma-default;
+		};
+	};
+};
+
+&gmac0 {
+	status = "okay";
+
+	phy-mode = "rgmii";
+	phy-handle = <&phy0>;
+	mdio {
+		compatible = "snps,dwmac-mdio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		phy0: ethernet-phy@0 {
+			reg = <0>;
+		};
+	};
+};
+
+&gmac1 {
+	status = "okay";
+
+	phy-mode = "rgmii";
+	phy-handle = <&phy1>;
+	mdio {
+		compatible = "snps,dwmac-mdio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		phy1: ethernet-phy@1 {
+			reg = <16>;
+		};
+	};
+};
+
+&i2c2 {
+	status = "okay";
+
+	pinctrl-0 = <&i2c0_pins_default>;
+	pinctrl-names = "default";
+
+	#address-cells = <1>;
+	#size-cells = <0>;
+	eeprom@57 {
+		compatible = "atmel,24c16";
+		reg = <0x57>;
+		pagesize = <16>;
+	};
+};
+
+&spi0 {
+	status = "okay";
+
+	#address-cells = <1>;
+	#size-cells = <0>;
+	spidev@0 {
+		compatible = "rohm,dh2228fv";
+		spi-max-frequency = <100000000>;
+		reg = <0>;
+	};
+};
+
+&ehci0 {
+	status = "okay";
+};
+
+&ohci0 {
+	status = "okay";
+};
+
+&sata {
+	status = "okay";
+};
+
+&uart0 {
+	status = "okay";
+};
+
+&clk {
+	status = "okay";
+};
+
+&rtc0 {
+	status = "okay";
+};
+
+&pctrl {
+	status = "okay";
+
+	sdio_pins_default: sdio-pins {
+		sdio-pinmux {
+			groups = "sdio";
+			function = "sdio";
+		};
+		sdio-det-pinmux {
+			groups = "pwm2";
+			function = "gpio";
+		};
+	};
+
+	pwm1_pins_default: pwm1-pins {
+		pinmux {
+			groups = "pwm1";
+			function = "pwm1";
+		};
+	};
+
+	pwm0_pins_default: pwm0-pins {
+		pinmux {
+			groups = "pwm0";
+			function = "pwm0";
+		};
+	};
+
+	i2c1_pins_default: i2c1-pins {
+		pinmux {
+			groups = "i2c1";
+			function = "i2c1";
+		};
+	};
+
+	i2c0_pins_default: i2c0-pins {
+		pinmux {
+			groups = "i2c0";
+			function = "i2c0";
+		};
+	};
+
+	nand_pins_default: nand-pins {
+		pinmux {
+			groups = "nand";
+			function = "nand";
+		};
+	};
+
+	hda_pins_default: hda-pins {
+		grp0-pinmux {
+			groups = "hda";
+			function = "hda";
+		};
+		grp1-pinmux {
+			groups = "i2s";
+			function = "gpio";
+		};
+	};
+};
diff --git a/arch/loongarch/boot/dts/loongson-2k1000.dtsi b/arch/loongarch/boot/dts/loongson-2k1000.dtsi
new file mode 100644
index 000000000000..49a70f8c3cab
--- /dev/null
+++ b/arch/loongarch/boot/dts/loongson-2k1000.dtsi
@@ -0,0 +1,492 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/clock/loongson,ls2k-clk.h>
+#include <dt-bindings/gpio/gpio.h>
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			compatible = "loongson,la264";
+			device_type = "cpu";
+			reg= <0x0>;
+			clocks = <&clk LOONGSON2_NODE_CLK>;
+		};
+
+		cpu1: cpu@1 {
+			compatible = "loongson,la264";
+			device_type = "cpu";
+			reg = <0x1>;
+			clocks = <&clk LOONGSON2_NODE_CLK>;
+		};
+	};
+
+	ref_100m: clock-ref-100m {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <100000000>;
+		clock-output-names = "ref_100m";
+	};
+
+	cpuintc: interrupt-controller {
+		compatible = "loongson,cpu-interrupt-controller";
+		#interrupt-cells = <1>;
+		interrupt-controller;
+	};
+
+	/* i2c of the dvi eeprom edid */
+	i2c-gpio-0 {
+		compatible = "i2c-gpio";
+		scl-gpios = <&gpio0 0 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+		sda-gpios = <&gpio0 1 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+		i2c-gpio,delay-us = <5>;        /* ~100 kHz */
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
+	/* i2c of the eeprom edid */
+	i2c-gpio-1 {
+		compatible = "i2c-gpio";
+		scl-gpios = <&gpio0 33 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+		sda-gpios = <&gpio0 32 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+		i2c-gpio,delay-us = <5>;        /* ~100 kHz */
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
+	thermal-zones {
+		cpu-thermal {
+			polling-delay-passive = <1000>;
+			polling-delay = <5000>;
+			thermal-sensors = <&tsensor 0>;
+
+			trips {
+				cpu_alert: cpu-alert {
+					temperature = <33000>;
+					hysteresis = <2000>;
+					type = "active";
+				};
+
+				cpu_crit: cpu-crit {
+					temperature = <85000>;
+					hysteresis = <5000>;
+					type = "critical";
+				};
+			};
+		};
+	};
+
+	bus@10000000 {
+		compatible = "simple-bus";
+		ranges = <0x0 0x10000000 0x0 0x10000000 0x0 0x10000000>,
+			 <0x0 0x02000000 0x0 0x02000000 0x0 0x02000000>,
+			 <0x0 0x20000000 0x0 0x20000000 0x0 0x10000000>,
+			 <0x0 0x40000000 0x0 0x40000000 0x0 0x40000000>,
+			 <0xfe 0x0 0xfe 0x0 0x0 0x40000000>;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		dma-coherent;
+
+		liointc0: interrupt-controller@1fe01400 {
+			compatible = "loongson,liointc-2.0";
+			reg = <0x0 0x1fe01400 0x0 0x40>,
+			      <0x0 0x1fe01040 0x0 0x8>,
+			      <0x0 0x1fe01140 0x0 0x8>;
+			reg-names = "main", "isr0", "isr1";
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupt-parent = <&cpuintc>;
+			interrupts = <2>;
+			interrupt-names = "int0";
+			loongson,parent_int_map = <0xffffffff>, /* int0 */
+						  <0x00000000>, /* int1 */
+						  <0x00000000>, /* int2 */
+						  <0x00000000>; /* int3 */
+		};
+
+		liointc1: interrupt-controller@1fe01440 {
+			compatible = "loongson,liointc-2.0";
+			reg = <0x0 0x1fe01440 0x0 0x40>,
+			      <0x0 0x1fe01048 0x0 0x8>,
+			      <0x0 0x1fe01148 0x0 0x8>;
+			reg-names = "main", "isr0", "isr1";
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupt-parent = <&cpuintc>;
+			interrupts = <3>;
+			interrupt-names = "int1";
+			loongson,parent_int_map = <0x00000000>, /* int0 */
+						  <0xffffffff>, /* int1 */
+						  <0x00000000>, /* int2 */
+						  <0x00000000>; /* int3 */
+		};
+
+		chipid@1fe00000 {
+			compatible = "loongson,ls2k-chipid";
+			reg = <0x0 0x1fe00000 0x0 0x30>;
+			little-endian;
+		};
+
+		pctrl: pinctrl@1fe00420 {
+			compatible = "loongson,ls2k-pinctrl";
+			reg = <0x0 0x1fe00420 0x0 0x18>;
+			status = "disabled";
+		};
+
+		clk: clock-controller@1fe00480 {
+			compatible = "loongson,ls2k-clk";
+			reg = <0x0 0x1fe00480 0x0 0x58>;
+			#clock-cells = <1>;
+			clocks = <&ref_100m>;
+			clock-names = "ref_100m";
+			status = "disabled";
+		};
+
+		gpio0: gpio@1fe00500 {
+			compatible = "loongson,ls2k-gpio";
+			reg = <0x0 0x1fe00500 0x0 0x38>;
+			ngpios = <64>;
+			#gpio-cells = <2>;
+			gpio-controller;
+			gpio-ranges = <&pctrl 0x0 0x0 15>,
+				      <&pctrl 16 16 15>,
+				      <&pctrl 32 32 10>,
+				      <&pctrl 44 44 20>;
+			interrupt-parent = <&liointc1>;
+			interrupts = <28 IRQ_TYPE_LEVEL_HIGH>,
+				     <29 IRQ_TYPE_LEVEL_HIGH>,
+				     <30 IRQ_TYPE_LEVEL_HIGH>,
+				     <30 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <>,
+				     <>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		tsensor: thermal-sensor@1fe01500 {
+			compatible = "loongson,ls2k1000-thermal";
+			reg = <0x0 0x1fe01500 0x0 0x30>;
+			interrupt-parent = <&liointc0>;
+			interrupts = <7 IRQ_TYPE_LEVEL_HIGH>;
+			#thermal-sensor-cells = <1>;
+		};
+
+		dma-controller@1fe00c00 {
+			compatible = "loongson,ls2k1000-apbdma";
+			reg = <0x0 0x1fe00c00 0x0 0x8>;
+			interrupt-parent = <&liointc1>;
+			interrupts = <12 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk LOONGSON2_APB_CLK>;
+			#dma-cells = <1>;
+			status = "disabled";
+		};
+
+		dma-controller@1fe00c10 {
+			compatible = "loongson,ls2k1000-apbdma";
+			reg = <0x0 0x1fe00c10 0x0 0x8>;
+			interrupt-parent = <&liointc1>;
+			interrupts = <13 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk LOONGSON2_APB_CLK>;
+			#dma-cells = <1>;
+			status = "disabled";
+		};
+
+		dma-controller@1fe00c20 {
+			compatible = "loongson,ls2k1000-apbdma";
+			reg = <0x0 0x1fe00c20 0x0 0x8>;
+			interrupt-parent = <&liointc1>;
+			interrupts = <14 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk LOONGSON2_APB_CLK>;
+			#dma-cells = <1>;
+			status = "disabled";
+		};
+
+		dma-controller@1fe00c30 {
+			compatible = "loongson,ls2k1000-apbdma";
+			reg = <0x0 0x1fe00c30 0x0 0x8>;
+			interrupt-parent = <&liointc1>;
+			interrupts = <15 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk LOONGSON2_APB_CLK>;
+			#dma-cells = <1>;
+			status = "disabled";
+		};
+
+		dma-controller@1fe00c40 {
+			compatible = "loongson,ls2k1000-apbdma";
+			reg = <0x0 0x1fe00c40 0x0 0x8>;
+			interrupt-parent = <&liointc1>;
+			interrupts = <16 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk LOONGSON2_APB_CLK>;
+			#dma-cells = <1>;
+			status = "disabled";
+		};
+
+		uart0: serial@1fe20000 {
+			compatible = "ns16550a";
+			reg = <0x0 0x1fe20000 0x0 0x10>;
+			clock-frequency = <125000000>;
+			interrupt-parent = <&liointc0>;
+			interrupts = <0x0 IRQ_TYPE_LEVEL_HIGH>;
+			no-loopback-test;
+			status = "disabled";
+		};
+
+		i2c2: i2c@1fe21000 {
+			compatible = "loongson,ls2k-i2c";
+			reg = <0x0 0x1fe21000 0x0 0x8>;
+			interrupt-parent = <&liointc0>;
+			interrupts = <22 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
+		i2c3: i2c@1fe21800 {
+			compatible = "loongson,ls2k-i2c";
+			reg = <0x0 0x1fe21800 0x0 0x8>;
+			interrupt-parent = <&liointc0>;
+			interrupts = <23 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
+		pmc: power-management@1fe27000 {
+			compatible = "loongson,ls2k1000-pmc", "loongson,ls2k0500-pmc", "syscon";
+			reg = <0x0 0x1fe27000 0x0 0x58>;
+			interrupt-parent = <&liointc1>;
+			interrupts = <11 IRQ_TYPE_LEVEL_HIGH>;
+			loongson,suspend-address = <0x0 0x1c000500>;
+
+			syscon-reboot {
+				compatible = "syscon-reboot";
+				offset = <0x30>;
+				mask = <0x1>;
+			};
+
+			syscon-poweroff {
+				compatible = "syscon-poweroff";
+				regmap = <&pmc>;
+				offset = <0x14>;
+				mask = <0x3c00>;
+				value = <0x3c00>;
+			};
+		};
+
+		rtc0: rtc@1fe27800 {
+			compatible = "loongson,ls2k1000-rtc";
+			reg = <0x0 0x1fe27800 0x0 0x100>;
+			interrupt-parent = <&liointc1>;
+			interrupts = <8 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
+		spi0: spi@1fff0220 {
+			compatible = "loongson,ls2k1000-spi";
+			reg = <0x0 0x1fff0220 0x0 0x10>;
+			clocks = <&clk LOONGSON2_BOOT_CLK>;
+			status = "disabled";
+		};
+
+		pcie@1a000000 {
+			compatible = "loongson,ls2k-pci";
+			reg = <0x0 0x1a000000 0x0 0x02000000>,
+			      <0xfe 0x0 0x0 0x20000000>;
+			#address-cells = <3>;
+			#size-cells = <2>;
+			device_type = "pci";
+			bus-range = <0x0 0xff>;
+			ranges = <0x01000000 0x0 0x00008000 0x0 0x18008000 0x0 0x00008000>,
+				 <0x02000000 0x0 0x60000000 0x0 0x60000000 0x0 0x20000000>;
+
+			gmac0: ethernet@3,0 {
+				reg = <0x1800 0x0 0x0 0x0 0x0>;
+				interrupt-parent = <&liointc0>;
+				interrupts = <12 IRQ_TYPE_LEVEL_HIGH>,
+					     <13 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names = "macirq", "eth_lpi";
+				status = "disabled";
+			};
+
+			gmac1: ethernet@3,1 {
+				reg = <0x1900 0x0 0x0 0x0 0x0>;
+				interrupt-parent = <&liointc0>;
+				interrupts = <14 IRQ_TYPE_LEVEL_HIGH>,
+					     <15 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names = "macirq", "eth_lpi";
+				status = "disabled";
+			};
+
+			ehci0: usb@4,1 {
+				reg = <0x2100 0x0 0x0 0x0 0x0>;
+				interrupt-parent = <&liointc1>;
+				interrupts = <18 IRQ_TYPE_LEVEL_HIGH>;
+				status = "disabled";
+			};
+
+			ohci0: usb@4,2 {
+				reg = <0x2200 0x0 0x0 0x0 0x0>;
+				interrupt-parent = <&liointc1>;
+				interrupts = <19 IRQ_TYPE_LEVEL_HIGH>;
+				status = "disabled";
+			};
+
+			display@6,0 {
+				reg = <0x3000 0x0 0x0 0x0 0x0>;
+				interrupt-parent = <&liointc0>;
+				interrupts = <28 IRQ_TYPE_LEVEL_HIGH>;
+				status = "disabled";
+			};
+
+			hda@7,0 {
+				reg = <0x3800 0x0 0x0 0x0 0x0>;
+				interrupt-parent = <&liointc0>;
+				interrupts = <4 IRQ_TYPE_LEVEL_HIGH>;
+				status = "disabled";
+			};
+
+			sata: sata@8,0 {
+				reg = <0x4000 0x0 0x0 0x0 0x0>;
+				interrupt-parent = <&liointc0>;
+				interrupts = <19 IRQ_TYPE_LEVEL_HIGH>;
+				status = "disabled";
+			};
+
+			pcie@9,0 {
+				reg = <0x4800 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 0x0 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@a,0 {
+				reg = <0x5000 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&liointc1>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 1 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@b,0 {
+				reg = <0x5800 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&liointc1>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 2 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@c,0 {
+				reg = <0x6000 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&liointc1>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 3 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@d,0 {
+				reg = <0x6800 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&liointc1>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 4 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@e,0 {
+				reg = <0x7000 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&liointc1>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 5 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+		};
+	};
+};
diff --git a/arch/loongarch/boot/dts/loongson-2k2000-ref.dts b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts
new file mode 100644
index 000000000000..dca91caf895e
--- /dev/null
+++ b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+/dts-v1/;
+
+#include "loongson-2k2000.dtsi"
+
+/ {
+	compatible = "loongson,ls2k2000-ref", "loongson,ls2k2000";
+	model = "Loongson-2K2000 Reference Board";
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory@200000 {
+		device_type = "memory";
+		reg = <0x0 0x00200000 0x0 0x0ee00000>,
+		      <0x0 0x90000000 0x0 0x70000000>;
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		linux,cma {
+			compatible = "shared-dma-pool";
+			reusable;
+			size = <0x0 0x2000000>;
+			linux,cma-default;
+		};
+	};
+};
+
+&sata {
+	status = "okay";
+};
+
+&uart0 {
+	status = "okay";
+};
+
+&rtc0 {
+	status = "okay";
+};
+
+&xhci0 {
+	status = "okay";
+};
+
+&xhci1 {
+	status = "okay";
+};
+
+&gmac0 {
+	status = "okay";
+};
+
+&gmac1 {
+	status = "okay";
+};
+
+&gmac2 {
+	status = "okay";
+};
diff --git a/arch/loongarch/boot/dts/loongson-2k2000.dtsi b/arch/loongarch/boot/dts/loongson-2k2000.dtsi
new file mode 100644
index 000000000000..a231949b5f55
--- /dev/null
+++ b/arch/loongarch/boot/dts/loongson-2k2000.dtsi
@@ -0,0 +1,300 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/interrupt-controller/irq.h>
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@1 {
+			compatible = "loongson,la364";
+			device_type = "cpu";
+			reg = <0x0>;
+			clocks = <&cpu_clk>;
+		};
+
+		cpu1: cpu@2 {
+			compatible = "loongson,la364";
+			device_type = "cpu";
+			reg = <0x1>;
+			clocks = <&cpu_clk>;
+		};
+	};
+
+	cpu_clk: cpu-clk {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <1400000000>;
+	};
+
+	cpuintc: interrupt-controller {
+		compatible = "loongson,cpu-interrupt-controller";
+		#interrupt-cells = <1>;
+		interrupt-controller;
+	};
+
+	bus@10000000 {
+		compatible = "simple-bus";
+		ranges = <0x0 0x10000000 0x0 0x10000000 0x0 0x10000000>,
+			 <0x0 0x02000000 0x0 0x02000000 0x0 0x02000000>,
+			 <0x0 0x40000000 0x0 0x40000000 0x0 0x40000000>,
+			 <0xfe 0x0 0xfe 0x0 0x0 0x40000000>;
+		#address-cells = <2>;
+		#size-cells = <2>;
+
+		pmc: power-management@100d0000 {
+			compatible = "loongson,ls2k2000-pmc", "loongson,ls2k0500-pmc", "syscon";
+			reg = <0x0 0x100d0000 0x0 0x58>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <47>;
+			loongson,suspend-address = <0x0 0x1c000500>;
+
+			syscon-reboot {
+				compatible = "syscon-reboot";
+				offset = <0x30>;
+				mask = <0x1>;
+			};
+
+			syscon-poweroff {
+				compatible = "syscon-poweroff";
+				regmap = <&pmc>;
+				offset = <0x14>;
+				mask = <0x3c00>;
+				value = <0x3c00>;
+			};
+		};
+
+		liointc: interrupt-controller@1fe01400 {
+			compatible = "loongson,liointc-1.0";
+			reg = <0x0 0x1fe01400 0x0 0x64>;
+
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupt-parent = <&cpuintc>;
+			interrupts = <2>;
+			interrupt-names = "int0";
+			loongson,parent_int_map = <0xffffffff>, /* int0 */
+						  <0x00000000>, /* int1 */
+						  <0x00000000>, /* int2 */
+						  <0x00000000>; /* int3 */
+		};
+
+		eiointc: interrupt-controller@1fe01600 {
+			compatible = "loongson,ls2k2000-eiointc";
+			reg = <0x0 0x1fe01600 0x0 0xea00>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&cpuintc>;
+			interrupts = <3>;
+		};
+
+		pic: interrupt-controller@10000000 {
+			compatible = "loongson,pch-pic-1.0";
+			reg = <0x0 0x10000000 0x0 0x400>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			loongson,pic-base-vec = <0>;
+			interrupt-parent = <&eiointc>;
+		};
+
+		msi: msi-controller@1fe01140 {
+			compatible = "loongson,pch-msi-1.0";
+			reg = <0x0 0x1fe01140 0x0 0x8>;
+			msi-controller;
+			loongson,msi-base-vec = <64>;
+			loongson,msi-num-vecs = <192>;
+			interrupt-parent = <&eiointc>;
+		};
+
+		rtc0: rtc@100d0100 {
+			compatible = "loongson,ls2k2000-rtc", "loongson,ls7a-rtc";
+			reg = <0x0 0x100d0100 0x0 0x100>;
+			interrupt-parent = <&pic>;
+			interrupts = <52 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
+		uart0: serial@1fe001e0 {
+			compatible = "ns16550a";
+			reg = <0x0 0x1fe001e0 0x0 0x10>;
+			clock-frequency = <100000000>;
+			interrupt-parent = <&liointc>;
+			interrupts = <10 IRQ_TYPE_LEVEL_HIGH>;
+			no-loopback-test;
+			status = "disabled";
+		};
+
+		pcie@1a000000 {
+			compatible = "loongson,ls2k-pci";
+			reg = <0x0 0x1a000000 0x0 0x02000000>,
+			      <0xfe 0x0 0x0 0x20000000>;
+			#address-cells = <3>;
+			#size-cells = <2>;
+			device_type = "pci";
+			bus-range = <0x0 0xff>;
+			ranges = <0x01000000 0x0 0x00008000 0x0 0x18400000 0x0 0x00008000>,
+				 <0x02000000 0x0 0x60000000 0x0 0x60000000 0x0 0x20000000>;
+
+			gmac0: ethernet@3,0 {
+				reg = <0x1800 0x0 0x0 0x0 0x0>;
+				interrupts = <12 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-parent = <&pic>;
+				status = "disabled";
+			};
+
+			gmac1: ethernet@3,1 {
+				reg = <0x1900 0x0 0x0 0x0 0x0>;
+				interrupts = <14 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-parent = <&pic>;
+				status = "disabled";
+			};
+
+			gmac2: ethernet@3,2 {
+				reg = <0x1a00 0x0 0x0 0x0 0x0>;
+				interrupts = <17 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-parent = <&pic>;
+				status = "disabled";
+			};
+
+			xhci0: usb@4,0 {
+				reg = <0x2000 0x0 0x0 0x0 0x0>;
+				interrupts = <48 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-parent = <&pic>;
+				status = "disabled";
+			};
+
+			xhci1: usb@19,0 {
+				reg = <0xc800 0x0 0x0 0x0 0x0>;
+				interrupts = <22 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-parent = <&pic>;
+				status = "disabled";
+			};
+
+			display@6,1 {
+				reg = <0x3100 0x0 0x0 0x0 0x0>;
+				interrupts = <28 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-parent = <&pic>;
+				status = "disabled";
+			};
+
+			hda@7,0 {
+				reg = <0x3800 0x0 0x0 0x0 0x0>;
+				interrupts = <58 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-parent = <&pic>;
+				status = "disabled";
+			};
+
+			sata: sata@8,0 {
+				reg = <0x4000 0x0 0x0 0x0 0x0>;
+				interrupts = <16 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-parent = <&pic>;
+				status = "disabled";
+			};
+
+			pcie@9,0 {
+				reg = <0x4800 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&pic>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &pic 32 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@a,0 {
+				reg = <0x5000 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&pic>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &pic 33 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@b,0 {
+				reg = <0x5800 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&pic>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &pic 34 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@c,0 {
+				reg = <0x6000 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&pic>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &pic 35 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@d,0 {
+				reg = <0x6800 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&pic>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &pic 36 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@e,0 {
+				reg = <0x7000 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&pic>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &pic 37 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@f,0 {
+				reg = <0x7800 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&pic>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &pic 40 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@10,0 {
+				reg = <0x8000 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&pic>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &pic 30 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+		};
+	};
+};
diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig
index 60e331af9839..f18c2ba871ef 100644
--- a/arch/loongarch/configs/loongson3_defconfig
+++ b/arch/loongarch/configs/loongson3_defconfig
@@ -6,6 +6,8 @@ CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BPF_SYSCALL=y
 CONFIG_BPF_JIT=y
 CONFIG_PREEMPT=y
+CONFIG_PREEMPT_DYNAMIC=y
+CONFIG_SCHED_CORE=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_BSD_PROCESS_ACCT_V3=y
 CONFIG_TASKSTATS=y
@@ -19,6 +21,7 @@ CONFIG_BLK_CGROUP=y
 CONFIG_CFS_BANDWIDTH=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_CGROUP_PIDS=y
+CONFIG_CGROUP_RDMA=y
 CONFIG_CGROUP_FREEZER=y
 CONFIG_CGROUP_HUGETLB=y
 CONFIG_CPUSETS=y
@@ -26,6 +29,7 @@ CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_PERF=y
 CONFIG_CGROUP_BPF=y
+CONFIG_CGROUP_MISC=y
 CONFIG_NAMESPACES=y
 CONFIG_USER_NS=y
 CONFIG_CHECKPOINT_RESTORE=y
@@ -35,6 +39,8 @@ CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 CONFIG_KALLSYMS_ALL=y
 CONFIG_PERF_EVENTS=y
+CONFIG_KEXEC=y
+CONFIG_CRASH_DUMP=y
 CONFIG_LOONGARCH=y
 CONFIG_64BIT=y
 CONFIG_MACH_LOONGSON64=y
@@ -44,13 +50,11 @@ CONFIG_DMI=y
 CONFIG_EFI=y
 CONFIG_SMP=y
 CONFIG_HOTPLUG_CPU=y
-CONFIG_NR_CPUS=64
+CONFIG_NR_CPUS=256
 CONFIG_NUMA=y
 CONFIG_CPU_HAS_FPU=y
 CONFIG_CPU_HAS_LSX=y
 CONFIG_CPU_HAS_LASX=y
-CONFIG_KEXEC=y
-CONFIG_CRASH_DUMP=y
 CONFIG_RANDOMIZE_BASE=y
 CONFIG_SUSPEND=y
 CONFIG_HIBERNATION=y
@@ -62,10 +66,6 @@ CONFIG_ACPI_IPMI=m
 CONFIG_ACPI_HOTPLUG_CPU=y
 CONFIG_ACPI_PCI_SLOT=y
 CONFIG_ACPI_HOTPLUG_MEMORY=y
-CONFIG_EFI_ZBOOT=y
-CONFIG_EFI_GENERIC_STUB_INITRD_CMDLINE_LOADER=y
-CONFIG_EFI_CAPSULE_LOADER=m
-CONFIG_EFI_TEST=m
 CONFIG_VIRTUALIZATION=y
 CONFIG_KVM=m
 CONFIG_JUMP_LABEL=y
@@ -74,10 +74,18 @@ CONFIG_MODULE_FORCE_LOAD=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
+CONFIG_BLK_DEV_ZONED=y
 CONFIG_BLK_DEV_THROTTLING=y
+CONFIG_BLK_DEV_THROTTLING_LOW=y
+CONFIG_BLK_WBT=y
+CONFIG_BLK_CGROUP_IOLATENCY=y
+CONFIG_BLK_CGROUP_FC_APPID=y
+CONFIG_BLK_CGROUP_IOCOST=y
+CONFIG_BLK_CGROUP_IOPRIO=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_BSD_DISKLABEL=y
 CONFIG_UNIXWARE_DISKLABEL=y
+CONFIG_CMDLINE_PARTITION=y
 CONFIG_IOSCHED_BFQ=y
 CONFIG_BFQ_GROUP_IOSCHED=y
 CONFIG_BINFMT_MISC=m
@@ -93,6 +101,8 @@ CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
+CONFIG_CMA=y
+CONFIG_CMA_SYSFS=y
 CONFIG_USERFAULTFD=y
 CONFIG_NET=y
 CONFIG_PACKET=y
@@ -128,6 +138,7 @@ CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_IPV6_ROUTE_INFO=y
 CONFIG_INET6_ESP=m
 CONFIG_IPV6_MROUTE=y
+CONFIG_MPTCP=y
 CONFIG_NETWORK_PHY_TIMESTAMPING=y
 CONFIG_NETFILTER=y
 CONFIG_BRIDGE_NETFILTER=m
@@ -352,6 +363,7 @@ CONFIG_PCIEAER=y
 CONFIG_PCI_IOV=y
 CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_SHPC=y
+CONFIG_PCI_HOST_GENERIC=y
 CONFIG_PCCARD=m
 CONFIG_YENTA=m
 CONFIG_RAPIDIO=y
@@ -365,6 +377,10 @@ CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_FW_LOADER_COMPRESS=y
 CONFIG_FW_LOADER_COMPRESS_ZSTD=y
+CONFIG_EFI_ZBOOT=y
+CONFIG_EFI_BOOTLOADER_CONTROL=m
+CONFIG_EFI_CAPSULE_LOADER=m
+CONFIG_EFI_TEST=m
 CONFIG_MTD=m
 CONFIG_MTD_BLOCK=m
 CONFIG_MTD_CFI=m
@@ -586,6 +602,7 @@ CONFIG_RTW89_8852AE=m
 CONFIG_RTW89_8852CE=m
 CONFIG_ZD1211RW=m
 CONFIG_USB_NET_RNDIS_WLAN=m
+CONFIG_USB4_NET=m
 CONFIG_INPUT_MOUSEDEV=y
 CONFIG_INPUT_MOUSEDEV_PSAUX=y
 CONFIG_INPUT_EVDEV=y
@@ -691,6 +708,9 @@ CONFIG_SND_HDA_CODEC_SIGMATEL=y
 CONFIG_SND_HDA_CODEC_HDMI=y
 CONFIG_SND_HDA_CODEC_CONEXANT=y
 CONFIG_SND_USB_AUDIO=m
+CONFIG_SND_SOC=m
+CONFIG_SND_SOC_LOONGSON_CARD=m
+CONFIG_SND_VIRTIO=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 CONFIG_HID_A4TECH=m
@@ -738,6 +758,11 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_EFI=y
 CONFIG_RTC_DRV_LOONGSON=y
 CONFIG_DMADEVICES=y
+CONFIG_LS2X_APB_DMA=y
+CONFIG_UDMABUF=y
+CONFIG_DMABUF_HEAPS=y
+CONFIG_DMABUF_HEAPS_SYSTEM=y
+CONFIG_DMABUF_HEAPS_CMA=y
 CONFIG_UIO=m
 CONFIG_UIO_PDRV_GENIRQ=m
 CONFIG_UIO_DMEM_GENIRQ=m
@@ -778,7 +803,15 @@ CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND=y
 CONFIG_DEVFREQ_GOV_PERFORMANCE=y
 CONFIG_DEVFREQ_GOV_POWERSAVE=y
 CONFIG_DEVFREQ_GOV_USERSPACE=y
+CONFIG_NTB=m
+CONFIG_NTB_MSI=y
+CONFIG_NTB_IDT=m
+CONFIG_NTB_EPF=m
+CONFIG_NTB_SWITCHTEC=m
+CONFIG_NTB_PERF=m
+CONFIG_NTB_TRANSPORT=m
 CONFIG_PWM=y
+CONFIG_USB4=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
@@ -797,6 +830,10 @@ CONFIG_GFS2_FS_LOCKING_DLM=y
 CONFIG_OCFS2_FS=m
 CONFIG_BTRFS_FS=y
 CONFIG_BTRFS_FS_POSIX_ACL=y
+CONFIG_F2FS_FS=m
+CONFIG_F2FS_FS_SECURITY=y
+CONFIG_F2FS_CHECK_FS=y
+CONFIG_F2FS_FS_COMPRESSION=y
 CONFIG_FANOTIFY=y
 CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
 CONFIG_QUOTA=y
@@ -883,7 +920,6 @@ CONFIG_KEY_DH_OPERATIONS=y
 CONFIG_SECURITY=y
 CONFIG_SECURITY_SELINUX=y
 CONFIG_SECURITY_SELINUX_BOOTPARAM=y
-CONFIG_SECURITY_SELINUX_DISABLE=y
 CONFIG_SECURITY_APPARMOR=y
 CONFIG_SECURITY_YAMA=y
 CONFIG_DEFAULT_SECURITY_DAC=y
@@ -914,6 +950,9 @@ CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 CONFIG_CRYPTO_CRC32_LOONGARCH=m
 CONFIG_CRYPTO_DEV_VIRTIO=m
+CONFIG_DMA_CMA=y
+CONFIG_DMA_NUMA_CMA=y
+CONFIG_CMA_SIZE_MBYTES=0
 CONFIG_PRINTK_TIME=y
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/loongarch/include/asm/acpi.h b/arch/loongarch/include/asm/acpi.h
index 8de6c4b83a61..49e29b29996f 100644
--- a/arch/loongarch/include/asm/acpi.h
+++ b/arch/loongarch/include/asm/acpi.h
@@ -32,8 +32,10 @@ static inline bool acpi_has_cpu_in_madt(void)
 	return true;
 }
 
+#define MAX_CORE_PIC 256
+
 extern struct list_head acpi_wakeup_device_list;
-extern struct acpi_madt_core_pic acpi_core_pic[NR_CPUS];
+extern struct acpi_madt_core_pic acpi_core_pic[MAX_CORE_PIC];
 
 extern int __init parse_acpi_topology(void);
 
diff --git a/arch/loongarch/include/asm/bootinfo.h b/arch/loongarch/include/asm/bootinfo.h
index c60796869b2b..6d5846dd075c 100644
--- a/arch/loongarch/include/asm/bootinfo.h
+++ b/arch/loongarch/include/asm/bootinfo.h
@@ -24,13 +24,15 @@ struct loongson_board_info {
 	const char *board_vendor;
 };
 
+#define NR_WORDS DIV_ROUND_UP(NR_CPUS, BITS_PER_LONG)
+
 struct loongson_system_configuration {
 	int nr_cpus;
 	int nr_nodes;
 	int boot_cpu_id;
 	int cores_per_node;
 	int cores_per_package;
-	unsigned long cores_io_master;
+	unsigned long cores_io_master[NR_WORDS];
 	unsigned long suspend_addr;
 	const char *cpuname;
 };
@@ -42,7 +44,7 @@ extern struct loongson_system_configuration loongson_sysconf;
 
 static inline bool io_master(int cpu)
 {
-	return test_bit(cpu, &loongson_sysconf.cores_io_master);
+	return test_bit(cpu, loongson_sysconf.cores_io_master);
 }
 
 #endif /* _ASM_BOOTINFO_H */
diff --git a/arch/loongarch/include/asm/crash_core.h b/arch/loongarch/include/asm/crash_core.h
new file mode 100644
index 000000000000..218bdbfa527b
--- /dev/null
+++ b/arch/loongarch/include/asm/crash_core.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _LOONGARCH_CRASH_CORE_H
+#define _LOONGARCH_CRASH_CORE_H
+
+#define CRASH_ALIGN			SZ_2M
+
+#define CRASH_ADDR_LOW_MAX		SZ_4G
+#define CRASH_ADDR_HIGH_MAX		memblock_end_of_DRAM()
+
+extern phys_addr_t memblock_end_of_DRAM(void);
+
+#endif
diff --git a/arch/loongarch/include/asm/elf.h b/arch/loongarch/include/asm/elf.h
index 9b16a3b8e706..f16bd42456e4 100644
--- a/arch/loongarch/include/asm/elf.h
+++ b/arch/loongarch/include/asm/elf.h
@@ -241,8 +241,6 @@ void loongarch_dump_regs64(u64 *uregs, const struct pt_regs *regs);
 do {									\
 	current->thread.vdso = &vdso_info;				\
 									\
-	loongarch_set_personality_fcsr(state);				\
-									\
 	if (personality(current->personality) != PER_LINUX)		\
 		set_personality(PER_LINUX);				\
 } while (0)
@@ -259,7 +257,6 @@ do {									\
 	clear_thread_flag(TIF_32BIT_ADDR);				\
 									\
 	current->thread.vdso = &vdso_info;				\
-	loongarch_set_personality_fcsr(state);				\
 									\
 	p = personality(current->personality);				\
 	if (p != PER_LINUX32 && p != PER_LINUX)				\
@@ -340,6 +337,4 @@ extern int arch_elf_pt_proc(void *ehdr, void *phdr, struct file *elf,
 extern int arch_check_elf(void *ehdr, bool has_interpreter, void *interp_ehdr,
 			  struct arch_elf_state *state);
 
-extern void loongarch_set_personality_fcsr(struct arch_elf_state *state);
-
 #endif /* _ASM_ELF_H */
diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h
index a11996eb5892..de891c2c83d4 100644
--- a/arch/loongarch/include/asm/ftrace.h
+++ b/arch/loongarch/include/asm/ftrace.h
@@ -63,7 +63,7 @@ ftrace_regs_get_instruction_pointer(struct ftrace_regs *fregs)
 static __always_inline void
 ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip)
 {
-	regs_set_return_value(&fregs->regs, ip);
+	instruction_pointer_set(&fregs->regs, ip);
 }
 
 #define ftrace_regs_get_argument(fregs, n) \
diff --git a/arch/loongarch/include/asm/jump_label.h b/arch/loongarch/include/asm/jump_label.h
index 3cea299a5ef5..29acfe3de3fa 100644
--- a/arch/loongarch/include/asm/jump_label.h
+++ b/arch/loongarch/include/asm/jump_label.h
@@ -22,7 +22,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	nop			\n\t"
 		JUMP_TABLE_ENTRY
 		:  :  "i"(&((char *)key)[branch]) :  : l_yes);
@@ -35,7 +35,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	b	%l[l_yes]	\n\t"
 		JUMP_TABLE_ENTRY
 		:  :  "i"(&((char *)key)[branch]) :  : l_yes);
diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h
index 11328700d4fa..2d62f7b0d377 100644
--- a/arch/loongarch/include/asm/kvm_host.h
+++ b/arch/loongarch/include/asm/kvm_host.h
@@ -45,7 +45,10 @@ struct kvm_vcpu_stat {
 	u64 signal_exits;
 };
 
+#define KVM_MEM_HUGEPAGE_CAPABLE	(1UL << 0)
+#define KVM_MEM_HUGEPAGE_INCAPABLE	(1UL << 1)
 struct kvm_arch_memory_slot {
+	unsigned long flags;
 };
 
 struct kvm_context {
@@ -92,8 +95,10 @@ enum emulation_result {
 };
 
 #define KVM_LARCH_FPU		(0x1 << 0)
-#define KVM_LARCH_SWCSR_LATEST	(0x1 << 1)
-#define KVM_LARCH_HWCSR_USABLE	(0x1 << 2)
+#define KVM_LARCH_LSX		(0x1 << 1)
+#define KVM_LARCH_LASX		(0x1 << 2)
+#define KVM_LARCH_SWCSR_LATEST	(0x1 << 3)
+#define KVM_LARCH_HWCSR_USABLE	(0x1 << 4)
 
 struct kvm_vcpu_arch {
 	/*
@@ -175,6 +180,21 @@ static inline void writel_sw_gcsr(struct loongarch_csrs *csr, int reg, unsigned
 	csr->csrs[reg] = val;
 }
 
+static inline bool kvm_guest_has_fpu(struct kvm_vcpu_arch *arch)
+{
+	return arch->cpucfg[2] & CPUCFG2_FP;
+}
+
+static inline bool kvm_guest_has_lsx(struct kvm_vcpu_arch *arch)
+{
+	return arch->cpucfg[2] & CPUCFG2_LSX;
+}
+
+static inline bool kvm_guest_has_lasx(struct kvm_vcpu_arch *arch)
+{
+	return arch->cpucfg[2] & CPUCFG2_LASX;
+}
+
 /* Debug: dump vcpu state */
 int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu);
 
@@ -183,7 +203,6 @@ void kvm_flush_tlb_all(void);
 void kvm_flush_tlb_gpa(struct kvm_vcpu *vcpu, unsigned long gpa);
 int kvm_handle_mm_fault(struct kvm_vcpu *vcpu, unsigned long badv, bool write);
 
-#define KVM_ARCH_WANT_MMU_NOTIFIER
 void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, bool blockable);
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
diff --git a/arch/loongarch/include/asm/kvm_vcpu.h b/arch/loongarch/include/asm/kvm_vcpu.h
index 553cfa2b2b1c..0cb4fdb8a9b5 100644
--- a/arch/loongarch/include/asm/kvm_vcpu.h
+++ b/arch/loongarch/include/asm/kvm_vcpu.h
@@ -55,7 +55,26 @@ void kvm_save_fpu(struct loongarch_fpu *fpu);
 void kvm_restore_fpu(struct loongarch_fpu *fpu);
 void kvm_restore_fcsr(struct loongarch_fpu *fpu);
 
-void kvm_acquire_timer(struct kvm_vcpu *vcpu);
+#ifdef CONFIG_CPU_HAS_LSX
+int kvm_own_lsx(struct kvm_vcpu *vcpu);
+void kvm_save_lsx(struct loongarch_fpu *fpu);
+void kvm_restore_lsx(struct loongarch_fpu *fpu);
+#else
+static inline int kvm_own_lsx(struct kvm_vcpu *vcpu) { return -EINVAL; }
+static inline void kvm_save_lsx(struct loongarch_fpu *fpu) { }
+static inline void kvm_restore_lsx(struct loongarch_fpu *fpu) { }
+#endif
+
+#ifdef CONFIG_CPU_HAS_LASX
+int kvm_own_lasx(struct kvm_vcpu *vcpu);
+void kvm_save_lasx(struct loongarch_fpu *fpu);
+void kvm_restore_lasx(struct loongarch_fpu *fpu);
+#else
+static inline int kvm_own_lasx(struct kvm_vcpu *vcpu) { return -EINVAL; }
+static inline void kvm_save_lasx(struct loongarch_fpu *fpu) { }
+static inline void kvm_restore_lasx(struct loongarch_fpu *fpu) { }
+#endif
+
 void kvm_init_timer(struct kvm_vcpu *vcpu, unsigned long hz);
 void kvm_reset_timer(struct kvm_vcpu *vcpu);
 void kvm_save_timer(struct kvm_vcpu *vcpu);
diff --git a/arch/loongarch/include/asm/shmparam.h b/arch/loongarch/include/asm/shmparam.h
deleted file mode 100644
index c9554f48d2df..000000000000
--- a/arch/loongarch/include/asm/shmparam.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
- */
-#ifndef _ASM_SHMPARAM_H
-#define _ASM_SHMPARAM_H
-
-#define __ARCH_FORCE_SHMLBA	1
-
-#define	SHMLBA	SZ_64K		 /* attach addr a multiple of this */
-
-#endif /* _ASM_SHMPARAM_H */
diff --git a/arch/loongarch/include/uapi/asm/kvm.h b/arch/loongarch/include/uapi/asm/kvm.h
index c6ad2ee6106c..923d0bd38294 100644
--- a/arch/loongarch/include/uapi/asm/kvm.h
+++ b/arch/loongarch/include/uapi/asm/kvm.h
@@ -79,6 +79,7 @@ struct kvm_fpu {
 #define LOONGARCH_REG_64(TYPE, REG)	(TYPE | KVM_REG_SIZE_U64 | (REG << LOONGARCH_REG_SHIFT))
 #define KVM_IOC_CSRID(REG)		LOONGARCH_REG_64(KVM_REG_LOONGARCH_CSR, REG)
 #define KVM_IOC_CPUCFG(REG)		LOONGARCH_REG_64(KVM_REG_LOONGARCH_CPUCFG, REG)
+#define KVM_LOONGARCH_VCPU_CPUCFG	0
 
 struct kvm_debug_exit_arch {
 };
diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
index 8e00a754e548..5cf59c617126 100644
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@@ -29,11 +29,9 @@ int disabled_cpus;
 
 u64 acpi_saved_sp;
 
-#define MAX_CORE_PIC 256
-
 #define PREFIX			"ACPI: "
 
-struct acpi_madt_core_pic acpi_core_pic[NR_CPUS];
+struct acpi_madt_core_pic acpi_core_pic[MAX_CORE_PIC];
 
 void __init __iomem * __acpi_map_table(unsigned long phys, unsigned long size)
 {
@@ -119,7 +117,7 @@ acpi_parse_eio_master(union acpi_subtable_headers *header, const unsigned long e
 		return -EINVAL;
 
 	core = eiointc->node * CORES_PER_EIO_NODE;
-	set_bit(core, &(loongson_sysconf.cores_io_master));
+	set_bit(core, loongson_sysconf.cores_io_master);
 
 	return 0;
 }
diff --git a/arch/loongarch/kernel/efi.c b/arch/loongarch/kernel/efi.c
index acb5d3385675..000825406c1f 100644
--- a/arch/loongarch/kernel/efi.c
+++ b/arch/loongarch/kernel/efi.c
@@ -140,4 +140,6 @@ void __init efi_init(void)
 
 		early_memunmap(tbl, sizeof(*tbl));
 	}
+
+	efi_esrt_init();
 }
diff --git a/arch/loongarch/kernel/elf.c b/arch/loongarch/kernel/elf.c
index 183e94fc9c69..0fa81ced28dc 100644
--- a/arch/loongarch/kernel/elf.c
+++ b/arch/loongarch/kernel/elf.c
@@ -23,8 +23,3 @@ int arch_check_elf(void *_ehdr, bool has_interpreter, void *_interp_ehdr,
 {
 	return 0;
 }
-
-void loongarch_set_personality_fcsr(struct arch_elf_state *state)
-{
-	current->thread.fpu.fcsr = boot_cpu_data.fpu_csr0;
-}
diff --git a/arch/loongarch/kernel/env.c b/arch/loongarch/kernel/env.c
index 6b3bfb0092e6..2f1f5b08638f 100644
--- a/arch/loongarch/kernel/env.c
+++ b/arch/loongarch/kernel/env.c
@@ -5,13 +5,16 @@
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
 #include <linux/acpi.h>
+#include <linux/clk.h>
 #include <linux/efi.h>
 #include <linux/export.h>
 #include <linux/memblock.h>
+#include <linux/of_clk.h>
 #include <asm/early_ioremap.h>
 #include <asm/bootinfo.h>
 #include <asm/loongson.h>
 #include <asm/setup.h>
+#include <asm/time.h>
 
 u64 efi_system_table;
 struct loongson_system_configuration loongson_sysconf;
@@ -36,7 +39,16 @@ void __init init_environ(void)
 
 static int __init init_cpu_fullname(void)
 {
-	int cpu;
+	struct device_node *root;
+	int cpu, ret;
+	char *model;
+
+	/* Parsing cpuname from DTS model property */
+	root = of_find_node_by_path("/");
+	ret = of_property_read_string(root, "model", (const char **)&model);
+	of_node_put(root);
+	if (ret == 0)
+		loongson_sysconf.cpuname = strsep(&model, " ");
 
 	if (loongson_sysconf.cpuname && !strncmp(loongson_sysconf.cpuname, "Loongson", 8)) {
 		for (cpu = 0; cpu < NR_CPUS; cpu++)
@@ -46,6 +58,26 @@ static int __init init_cpu_fullname(void)
 }
 arch_initcall(init_cpu_fullname);
 
+static int __init fdt_cpu_clk_init(void)
+{
+	struct clk *clk;
+	struct device_node *np;
+
+	np = of_get_cpu_node(0, NULL);
+	if (!np)
+		return -ENODEV;
+
+	clk = of_clk_get(np, 0);
+	if (IS_ERR(clk))
+		return -ENODEV;
+
+	cpu_clock_freq = clk_get_rate(clk);
+	clk_put(clk);
+
+	return 0;
+}
+late_initcall(fdt_cpu_clk_init);
+
 static ssize_t boardinfo_show(struct kobject *kobj,
 			      struct kobj_attribute *attr, char *buf)
 {
diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S
index d53ab10f4644..4382e36ae3d4 100644
--- a/arch/loongarch/kernel/fpu.S
+++ b/arch/loongarch/kernel/fpu.S
@@ -349,6 +349,7 @@ SYM_FUNC_START(_restore_lsx_upper)
 	lsx_restore_all_upper a0 t0 t1
 	jr	ra
 SYM_FUNC_END(_restore_lsx_upper)
+EXPORT_SYMBOL(_restore_lsx_upper)
 
 SYM_FUNC_START(_init_lsx_upper)
 	lsx_init_all_upper t1
@@ -384,6 +385,7 @@ SYM_FUNC_START(_restore_lasx_upper)
 	lasx_restore_all_upper a0 t0 t1
 	jr	ra
 SYM_FUNC_END(_restore_lasx_upper)
+EXPORT_SYMBOL(_restore_lasx_upper)
 
 SYM_FUNC_START(_init_lasx_upper)
 	lasx_init_all_upper t1
diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S
index 0ecab4216392..c4f7de2e2805 100644
--- a/arch/loongarch/kernel/head.S
+++ b/arch/loongarch/kernel/head.S
@@ -74,6 +74,11 @@ SYM_CODE_START(kernel_entry)			# kernel entry point
 	la.pcrel	t0, fw_arg2
 	st.d		a2, t0, 0
 
+#ifdef CONFIG_PAGE_SIZE_4KB
+	li.d		t0, 0
+	li.d		t1, CSR_STFILL
+	csrxchg		t0, t1, LOONGARCH_CSR_IMPCTL1
+#endif
 	/* KSave3 used for percpu base, initialized as 0 */
 	csrwr		zero, PERCPU_BASE_KS
 	/* GPR21 used for percpu base (runtime), initialized as 0 */
@@ -126,6 +131,11 @@ SYM_CODE_START(smpboot_entry)
 
 	JUMP_VIRT_ADDR	t0, t1
 
+#ifdef CONFIG_PAGE_SIZE_4KB
+	li.d		t0, 0
+	li.d		t1, CSR_STFILL
+	csrxchg		t0, t1, LOONGARCH_CSR_IMPCTL1
+#endif
 	/* Enable PG */
 	li.w		t0, 0xb0		# PLV=0, IE=0, PG=1
 	csrwr		t0, LOONGARCH_CSR_CRMD
diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c
index 767d94cce0de..f2ff8b5d591e 100644
--- a/arch/loongarch/kernel/process.c
+++ b/arch/loongarch/kernel/process.c
@@ -85,6 +85,7 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp)
 	regs->csr_euen = euen;
 	lose_fpu(0);
 	lose_lbt(0);
+	current->thread.fpu.fcsr = boot_cpu_data.fpu_csr0;
 
 	clear_thread_flag(TIF_LSX_CTX_LIVE);
 	clear_thread_flag(TIF_LASX_CTX_LIVE);
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index d183a745fb85..634ef17fd38b 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -252,38 +252,23 @@ static void __init arch_reserve_vmcore(void)
 #endif
 }
 
-/* 2MB alignment for crash kernel regions */
-#define CRASH_ALIGN	SZ_2M
-#define CRASH_ADDR_MAX	SZ_4G
-
-static void __init arch_parse_crashkernel(void)
+static void __init arch_reserve_crashkernel(void)
 {
-#ifdef CONFIG_KEXEC
 	int ret;
-	unsigned long long total_mem;
+	unsigned long long low_size = 0;
 	unsigned long long crash_base, crash_size;
+	char *cmdline = boot_command_line;
+	bool high = false;
 
-	total_mem = memblock_phys_mem_size();
-	ret = parse_crashkernel(boot_command_line, total_mem,
-				&crash_size, &crash_base,
-				NULL, NULL);
-	if (ret < 0 || crash_size <= 0)
+	if (!IS_ENABLED(CONFIG_KEXEC_CORE))
 		return;
 
-	if (crash_base <= 0) {
-		crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, CRASH_ALIGN, CRASH_ADDR_MAX);
-		if (!crash_base) {
-			pr_warn("crashkernel reservation failed - No suitable area found.\n");
-			return;
-		}
-	} else if (!memblock_phys_alloc_range(crash_size, CRASH_ALIGN, crash_base, crash_base + crash_size)) {
-		pr_warn("Invalid memory region reserved for crash kernel\n");
+	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
+				&crash_size, &crash_base, &low_size, &high);
+	if (ret)
 		return;
-	}
 
-	crashk_res.start = crash_base;
-	crashk_res.end	 = crash_base + crash_size - 1;
-#endif
+	reserve_crashkernel_generic(cmdline, crash_size, crash_base, low_size, high);
 }
 
 static void __init fdt_setup(void)
@@ -295,8 +280,12 @@ static void __init fdt_setup(void)
 	if (acpi_os_get_root_pointer())
 		return;
 
-	/* Look for a device tree configuration table entry */
-	fdt_pointer = efi_fdt_pointer();
+	/* Prefer to use built-in dtb, checking its legality first. */
+	if (!fdt_check_header(__dtb_start))
+		fdt_pointer = __dtb_start;
+	else
+		fdt_pointer = efi_fdt_pointer(); /* Fallback to firmware dtb */
+
 	if (!fdt_pointer || fdt_check_header(fdt_pointer))
 		return;
 
@@ -330,7 +319,9 @@ static void __init bootcmdline_init(char **cmdline_p)
 		if (boot_command_line[0])
 			strlcat(boot_command_line, " ", COMMAND_LINE_SIZE);
 
-		strlcat(boot_command_line, init_command_line, COMMAND_LINE_SIZE);
+		if (!strstr(boot_command_line, init_command_line))
+			strlcat(boot_command_line, init_command_line, COMMAND_LINE_SIZE);
+
 		goto out;
 	}
 #endif
@@ -357,7 +348,7 @@ out:
 void __init platform_init(void)
 {
 	arch_reserve_vmcore();
-	arch_parse_crashkernel();
+	arch_reserve_crashkernel();
 
 #ifdef CONFIG_ACPI_TABLE_UPGRADE
 	acpi_table_upgrade();
@@ -366,6 +357,8 @@ void __init platform_init(void)
 	acpi_gbl_use_default_register_widths = false;
 	acpi_boot_table_init();
 #endif
+
+	early_init_fdt_scan_reserved_mem();
 	unflatten_and_copy_device_tree();
 
 #ifdef CONFIG_NUMA
@@ -399,8 +392,6 @@ static void __init arch_mem_init(char **cmdline_p)
 
 	check_kernel_sections_mem();
 
-	early_init_fdt_scan_reserved_mem();
-
 	/*
 	 * In order to reduce the possibility of kernel panic when failed to
 	 * get IO TLB memory under CONFIG_SWIOTLB, it is better to allocate
@@ -467,15 +458,6 @@ static void __init resource_init(void)
 		request_resource(res, &data_resource);
 		request_resource(res, &bss_resource);
 	}
-
-#ifdef CONFIG_KEXEC
-	if (crashk_res.start < crashk_res.end) {
-		insert_resource(&iomem_resource, &crashk_res);
-		pr_info("Reserving %ldMB of memory at %ldMB for crashkernel\n",
-			(unsigned long)((crashk_res.end - crashk_res.start + 1) >> 20),
-			(unsigned long)(crashk_res.start  >> 20));
-	}
-#endif
 }
 
 static int __init add_legacy_isa_io(struct fwnode_handle *fwnode,
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index 5bca12d16e06..aabee0b280fe 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -88,6 +88,73 @@ void show_ipi_list(struct seq_file *p, int prec)
 	}
 }
 
+static inline void set_cpu_core_map(int cpu)
+{
+	int i;
+
+	cpumask_set_cpu(cpu, &cpu_core_setup_map);
+
+	for_each_cpu(i, &cpu_core_setup_map) {
+		if (cpu_data[cpu].package == cpu_data[i].package) {
+			cpumask_set_cpu(i, &cpu_core_map[cpu]);
+			cpumask_set_cpu(cpu, &cpu_core_map[i]);
+		}
+	}
+}
+
+static inline void set_cpu_sibling_map(int cpu)
+{
+	int i;
+
+	cpumask_set_cpu(cpu, &cpu_sibling_setup_map);
+
+	for_each_cpu(i, &cpu_sibling_setup_map) {
+		if (cpus_are_siblings(cpu, i)) {
+			cpumask_set_cpu(i, &cpu_sibling_map[cpu]);
+			cpumask_set_cpu(cpu, &cpu_sibling_map[i]);
+		}
+	}
+}
+
+static inline void clear_cpu_sibling_map(int cpu)
+{
+	int i;
+
+	for_each_cpu(i, &cpu_sibling_setup_map) {
+		if (cpus_are_siblings(cpu, i)) {
+			cpumask_clear_cpu(i, &cpu_sibling_map[cpu]);
+			cpumask_clear_cpu(cpu, &cpu_sibling_map[i]);
+		}
+	}
+
+	cpumask_clear_cpu(cpu, &cpu_sibling_setup_map);
+}
+
+/*
+ * Calculate a new cpu_foreign_map mask whenever a
+ * new cpu appears or disappears.
+ */
+void calculate_cpu_foreign_map(void)
+{
+	int i, k, core_present;
+	cpumask_t temp_foreign_map;
+
+	/* Re-calculate the mask */
+	cpumask_clear(&temp_foreign_map);
+	for_each_online_cpu(i) {
+		core_present = 0;
+		for_each_cpu(k, &temp_foreign_map)
+			if (cpus_are_siblings(i, k))
+				core_present = 1;
+		if (!core_present)
+			cpumask_set_cpu(i, &temp_foreign_map);
+	}
+
+	for_each_online_cpu(i)
+		cpumask_andnot(&cpu_foreign_map[i],
+			       &temp_foreign_map, &cpu_sibling_map[i]);
+}
+
 /* Send mailbox buffer via Mail_Send */
 static void csr_mail_send(uint64_t data, int cpu, int mailbox)
 {
@@ -208,7 +275,7 @@ static void __init fdt_smp_setup(void)
 	}
 
 	loongson_sysconf.nr_cpus = num_processors;
-	set_bit(0, &(loongson_sysconf.cores_io_master));
+	set_bit(0, loongson_sysconf.cores_io_master);
 #endif
 }
 
@@ -216,6 +283,9 @@ void __init loongson_smp_setup(void)
 {
 	fdt_smp_setup();
 
+	if (loongson_sysconf.cores_per_package == 0)
+		loongson_sysconf.cores_per_package = num_processors;
+
 	cpu_data[0].core = cpu_logical_map(0) % loongson_sysconf.cores_per_package;
 	cpu_data[0].package = cpu_logical_map(0) / loongson_sysconf.cores_per_package;
 
@@ -300,6 +370,7 @@ int loongson_cpu_disable(void)
 	numa_remove_cpu(cpu);
 #endif
 	set_cpu_online(cpu, false);
+	clear_cpu_sibling_map(cpu);
 	calculate_cpu_foreign_map();
 	local_irq_save(flags);
 	irq_migrate_all_off_this_cpu();
@@ -334,6 +405,7 @@ void __noreturn arch_cpu_idle_dead(void)
 		addr = iocsr_read64(LOONGARCH_IOCSR_MBUF0);
 	} while (addr == 0);
 
+	local_irq_disable();
 	init_fn = (void *)TO_CACHE(addr);
 	iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_CLEAR);
 
@@ -376,59 +448,6 @@ static int __init ipi_pm_init(void)
 core_initcall(ipi_pm_init);
 #endif
 
-static inline void set_cpu_sibling_map(int cpu)
-{
-	int i;
-
-	cpumask_set_cpu(cpu, &cpu_sibling_setup_map);
-
-	for_each_cpu(i, &cpu_sibling_setup_map) {
-		if (cpus_are_siblings(cpu, i)) {
-			cpumask_set_cpu(i, &cpu_sibling_map[cpu]);
-			cpumask_set_cpu(cpu, &cpu_sibling_map[i]);
-		}
-	}
-}
-
-static inline void set_cpu_core_map(int cpu)
-{
-	int i;
-
-	cpumask_set_cpu(cpu, &cpu_core_setup_map);
-
-	for_each_cpu(i, &cpu_core_setup_map) {
-		if (cpu_data[cpu].package == cpu_data[i].package) {
-			cpumask_set_cpu(i, &cpu_core_map[cpu]);
-			cpumask_set_cpu(cpu, &cpu_core_map[i]);
-		}
-	}
-}
-
-/*
- * Calculate a new cpu_foreign_map mask whenever a
- * new cpu appears or disappears.
- */
-void calculate_cpu_foreign_map(void)
-{
-	int i, k, core_present;
-	cpumask_t temp_foreign_map;
-
-	/* Re-calculate the mask */
-	cpumask_clear(&temp_foreign_map);
-	for_each_online_cpu(i) {
-		core_present = 0;
-		for_each_cpu(k, &temp_foreign_map)
-			if (cpus_are_siblings(i, k))
-				core_present = 1;
-		if (!core_present)
-			cpumask_set_cpu(i, &temp_foreign_map);
-	}
-
-	for_each_online_cpu(i)
-		cpumask_andnot(&cpu_foreign_map[i],
-			       &temp_foreign_map, &cpu_sibling_map[i]);
-}
-
 /* Preload SMP state for boot cpu */
 void smp_prepare_boot_cpu(void)
 {
@@ -506,7 +525,6 @@ asmlinkage void start_secondary(void)
 	sync_counter();
 	cpu = raw_smp_processor_id();
 	set_my_cpu_offset(per_cpu_offset(cpu));
-	rcutree_report_cpu_starting(cpu);
 
 	cpu_probe();
 	constant_clockevent_init();
diff --git a/arch/loongarch/kernel/topology.c b/arch/loongarch/kernel/topology.c
index 3fd166006698..75d5c51a7cd3 100644
--- a/arch/loongarch/kernel/topology.c
+++ b/arch/loongarch/kernel/topology.c
@@ -10,47 +10,9 @@
 
 #include <acpi/processor.h>
 
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
-
 #ifdef CONFIG_HOTPLUG_CPU
-int arch_register_cpu(int cpu)
+bool arch_cpu_is_hotpluggable(int cpu)
 {
-	int ret;
-	struct cpu *c = &per_cpu(cpu_devices, cpu);
-
-	c->hotpluggable = 1;
-	ret = register_cpu(c, cpu);
-	if (ret < 0)
-		pr_warn("register_cpu %d failed (%d)\n", cpu, ret);
-
-	return ret;
-}
-EXPORT_SYMBOL(arch_register_cpu);
-
-void arch_unregister_cpu(int cpu)
-{
-	struct cpu *c = &per_cpu(cpu_devices, cpu);
-
-	c->hotpluggable = 0;
-	unregister_cpu(c);
+	return !io_master(cpu);
 }
-EXPORT_SYMBOL(arch_unregister_cpu);
 #endif
-
-static int __init topology_init(void)
-{
-	int i, ret;
-
-	for_each_present_cpu(i) {
-		struct cpu *c = &per_cpu(cpu_devices, i);
-
-		c->hotpluggable = !io_master(i);
-		ret = register_cpu(c, i);
-		if (ret < 0)
-			pr_warn("topology_init: register_cpu %d failed (%d)\n", i, ret);
-	}
-
-	return 0;
-}
-
-subsys_initcall(topology_init);
diff --git a/arch/loongarch/kvm/Kconfig b/arch/loongarch/kvm/Kconfig
index fda425babfb2..61f7e33b1f95 100644
--- a/arch/loongarch/kvm/Kconfig
+++ b/arch/loongarch/kvm/Kconfig
@@ -22,14 +22,13 @@ config KVM
 	depends on AS_HAS_LVZ_EXTENSION
 	depends on HAVE_KVM
 	select HAVE_KVM_DIRTY_RING_ACQ_REL
-	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
+	select KVM_COMMON
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_GENERIC_HARDWARE_ENABLING
+	select KVM_GENERIC_MMU_NOTIFIER
 	select KVM_MMIO
 	select KVM_XFER_TO_GUEST_WORK
-	select MMU_NOTIFIER
-	select PREEMPT_NOTIFIERS
 	help
 	  Support hosting virtualized guest machines using
 	  hardware virtualization extensions. You will need
diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c
index ce8de3fa472c..ed1d89d53e2e 100644
--- a/arch/loongarch/kvm/exit.c
+++ b/arch/loongarch/kvm/exit.c
@@ -200,17 +200,8 @@ int kvm_emu_idle(struct kvm_vcpu *vcpu)
 	++vcpu->stat.idle_exits;
 	trace_kvm_exit_idle(vcpu, KVM_TRACE_EXIT_IDLE);
 
-	if (!kvm_arch_vcpu_runnable(vcpu)) {
-		/*
-		 * Switch to the software timer before halt-polling/blocking as
-		 * the guest's timer may be a break event for the vCPU, and the
-		 * hypervisor timer runs only when the CPU is in guest mode.
-		 * Switch before halt-polling so that KVM recognizes an expired
-		 * timer before blocking.
-		 */
-		kvm_save_timer(vcpu);
-		kvm_vcpu_block(vcpu);
-	}
+	if (!kvm_arch_vcpu_runnable(vcpu))
+		kvm_vcpu_halt(vcpu);
 
 	return EMULATE_DONE;
 }
@@ -643,6 +634,11 @@ static int kvm_handle_fpu_disabled(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
 
+	if (!kvm_guest_has_fpu(&vcpu->arch)) {
+		kvm_queue_exception(vcpu, EXCCODE_INE, 0);
+		return RESUME_GUEST;
+	}
+
 	/*
 	 * If guest FPU not present, the FPU operation should have been
 	 * treated as a reserved instruction!
@@ -660,6 +656,36 @@ static int kvm_handle_fpu_disabled(struct kvm_vcpu *vcpu)
 }
 
 /*
+ * kvm_handle_lsx_disabled() - Guest used LSX while disabled in root.
+ * @vcpu:      Virtual CPU context.
+ *
+ * Handle when the guest attempts to use LSX when it is disabled in the root
+ * context.
+ */
+static int kvm_handle_lsx_disabled(struct kvm_vcpu *vcpu)
+{
+	if (kvm_own_lsx(vcpu))
+		kvm_queue_exception(vcpu, EXCCODE_INE, 0);
+
+	return RESUME_GUEST;
+}
+
+/*
+ * kvm_handle_lasx_disabled() - Guest used LASX while disabled in root.
+ * @vcpu:	Virtual CPU context.
+ *
+ * Handle when the guest attempts to use LASX when it is disabled in the root
+ * context.
+ */
+static int kvm_handle_lasx_disabled(struct kvm_vcpu *vcpu)
+{
+	if (kvm_own_lasx(vcpu))
+		kvm_queue_exception(vcpu, EXCCODE_INE, 0);
+
+	return RESUME_GUEST;
+}
+
+/*
  * LoongArch KVM callback handling for unimplemented guest exiting
  */
 static int kvm_fault_ni(struct kvm_vcpu *vcpu)
@@ -687,6 +713,8 @@ static exit_handle_fn kvm_fault_tables[EXCCODE_INT_START] = {
 	[EXCCODE_TLBS]			= kvm_handle_write_fault,
 	[EXCCODE_TLBM]			= kvm_handle_write_fault,
 	[EXCCODE_FPDIS]			= kvm_handle_fpu_disabled,
+	[EXCCODE_LSXDIS]		= kvm_handle_lsx_disabled,
+	[EXCCODE_LASXDIS]		= kvm_handle_lasx_disabled,
 	[EXCCODE_GSPR]			= kvm_handle_gspr,
 };
 
diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c
index 1c1d5199500e..86a2f2d0cb27 100644
--- a/arch/loongarch/kvm/main.c
+++ b/arch/loongarch/kvm/main.c
@@ -287,7 +287,6 @@ int kvm_arch_hardware_enable(void)
 	if (env & CSR_GCFG_MATC_ROOT)
 		gcfg |= CSR_GCFG_MATC_ROOT;
 
-	gcfg |= CSR_GCFG_TIT;
 	write_csr_gcfg(gcfg);
 
 	kvm_flush_tlb_all();
diff --git a/arch/loongarch/kvm/mmu.c b/arch/loongarch/kvm/mmu.c
index 80480df5f550..50a6acd7ffe4 100644
--- a/arch/loongarch/kvm/mmu.c
+++ b/arch/loongarch/kvm/mmu.c
@@ -13,6 +13,16 @@
 #include <asm/tlb.h>
 #include <asm/kvm_mmu.h>
 
+static inline bool kvm_hugepage_capable(struct kvm_memory_slot *slot)
+{
+	return slot->arch.flags & KVM_MEM_HUGEPAGE_CAPABLE;
+}
+
+static inline bool kvm_hugepage_incapable(struct kvm_memory_slot *slot)
+{
+	return slot->arch.flags & KVM_MEM_HUGEPAGE_INCAPABLE;
+}
+
 static inline void kvm_ptw_prepare(struct kvm *kvm, kvm_ptw_ctx *ctx)
 {
 	ctx->level = kvm->arch.root_level;
@@ -365,6 +375,69 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 	kvm_ptw_top(kvm->arch.pgd, start << PAGE_SHIFT, end << PAGE_SHIFT, &ctx);
 }
 
+int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old,
+				   struct kvm_memory_slot *new, enum kvm_mr_change change)
+{
+	gpa_t gpa_start;
+	hva_t hva_start;
+	size_t size, gpa_offset, hva_offset;
+
+	if ((change != KVM_MR_MOVE) && (change != KVM_MR_CREATE))
+		return 0;
+	/*
+	 * Prevent userspace from creating a memory region outside of the
+	 * VM GPA address space
+	 */
+	if ((new->base_gfn + new->npages) > (kvm->arch.gpa_size >> PAGE_SHIFT))
+		return -ENOMEM;
+
+	new->arch.flags = 0;
+	size = new->npages * PAGE_SIZE;
+	gpa_start = new->base_gfn << PAGE_SHIFT;
+	hva_start = new->userspace_addr;
+	if (IS_ALIGNED(size, PMD_SIZE) && IS_ALIGNED(gpa_start, PMD_SIZE)
+			&& IS_ALIGNED(hva_start, PMD_SIZE))
+		new->arch.flags |= KVM_MEM_HUGEPAGE_CAPABLE;
+	else {
+		/*
+		 * Pages belonging to memslots that don't have the same
+		 * alignment within a PMD for userspace and GPA cannot be
+		 * mapped with PMD entries, because we'll end up mapping
+		 * the wrong pages.
+		 *
+		 * Consider a layout like the following:
+		 *
+		 *    memslot->userspace_addr:
+		 *    +-----+--------------------+--------------------+---+
+		 *    |abcde|fgh  Stage-1 block  |    Stage-1 block tv|xyz|
+		 *    +-----+--------------------+--------------------+---+
+		 *
+		 *    memslot->base_gfn << PAGE_SIZE:
+		 *      +---+--------------------+--------------------+-----+
+		 *      |abc|def  Stage-2 block  |    Stage-2 block   |tvxyz|
+		 *      +---+--------------------+--------------------+-----+
+		 *
+		 * If we create those stage-2 blocks, we'll end up with this
+		 * incorrect mapping:
+		 *   d -> f
+		 *   e -> g
+		 *   f -> h
+		 */
+		gpa_offset = gpa_start & (PMD_SIZE - 1);
+		hva_offset = hva_start & (PMD_SIZE - 1);
+		if (gpa_offset != hva_offset) {
+			new->arch.flags |= KVM_MEM_HUGEPAGE_INCAPABLE;
+		} else {
+			if (gpa_offset == 0)
+				gpa_offset = PMD_SIZE;
+			if ((size + gpa_offset) < (PMD_SIZE * 2))
+				new->arch.flags |= KVM_MEM_HUGEPAGE_INCAPABLE;
+		}
+	}
+
+	return 0;
+}
+
 void kvm_arch_commit_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *old,
 				   const struct kvm_memory_slot *new,
@@ -562,47 +635,23 @@ out:
 }
 
 static bool fault_supports_huge_mapping(struct kvm_memory_slot *memslot,
-				unsigned long hva, unsigned long map_size, bool write)
+				unsigned long hva, bool write)
 {
-	size_t size;
-	gpa_t gpa_start;
-	hva_t uaddr_start, uaddr_end;
+	hva_t start, end;
 
 	/* Disable dirty logging on HugePages */
 	if (kvm_slot_dirty_track_enabled(memslot) && write)
 		return false;
 
-	size = memslot->npages * PAGE_SIZE;
-	gpa_start = memslot->base_gfn << PAGE_SHIFT;
-	uaddr_start = memslot->userspace_addr;
-	uaddr_end = uaddr_start + size;
+	if (kvm_hugepage_capable(memslot))
+		return true;
 
-	/*
-	 * Pages belonging to memslots that don't have the same alignment
-	 * within a PMD for userspace and GPA cannot be mapped with stage-2
-	 * PMD entries, because we'll end up mapping the wrong pages.
-	 *
-	 * Consider a layout like the following:
-	 *
-	 *    memslot->userspace_addr:
-	 *    +-----+--------------------+--------------------+---+
-	 *    |abcde|fgh  Stage-1 block  |    Stage-1 block tv|xyz|
-	 *    +-----+--------------------+--------------------+---+
-	 *
-	 *    memslot->base_gfn << PAGE_SIZE:
-	 *      +---+--------------------+--------------------+-----+
-	 *      |abc|def  Stage-2 block  |    Stage-2 block   |tvxyz|
-	 *      +---+--------------------+--------------------+-----+
-	 *
-	 * If we create those stage-2 blocks, we'll end up with this incorrect
-	 * mapping:
-	 *   d -> f
-	 *   e -> g
-	 *   f -> h
-	 */
-	if ((gpa_start & (map_size - 1)) != (uaddr_start & (map_size - 1)))
+	if (kvm_hugepage_incapable(memslot))
 		return false;
 
+	start = memslot->userspace_addr;
+	end = start + memslot->npages * PAGE_SIZE;
+
 	/*
 	 * Next, let's make sure we're not trying to map anything not covered
 	 * by the memslot. This means we have to prohibit block size mappings
@@ -615,8 +664,7 @@ static bool fault_supports_huge_mapping(struct kvm_memory_slot *memslot,
 	 * userspace_addr or the base_gfn, as both are equally aligned (per
 	 * the check above) and equally sized.
 	 */
-	return (hva & ~(map_size - 1)) >= uaddr_start &&
-		(hva & ~(map_size - 1)) + map_size <= uaddr_end;
+	return (hva >= ALIGN(start, PMD_SIZE)) && (hva < ALIGN_DOWN(end, PMD_SIZE));
 }
 
 /*
@@ -627,7 +675,7 @@ static bool fault_supports_huge_mapping(struct kvm_memory_slot *memslot,
  *
  * There are several ways to safely use this helper:
  *
- * - Check mmu_invalidate_retry_hva() after grabbing the mapping level, before
+ * - Check mmu_invalidate_retry_gfn() after grabbing the mapping level, before
  *   consuming it.  In this case, mmu_lock doesn't need to be held during the
  *   lookup, but it does need to be held while checking the MMU notifier.
  *
@@ -807,7 +855,7 @@ retry:
 
 	/* Check if an invalidation has taken place since we got pfn */
 	spin_lock(&kvm->mmu_lock);
-	if (mmu_invalidate_retry_hva(kvm, mmu_seq, hva)) {
+	if (mmu_invalidate_retry_gfn(kvm, mmu_seq, gfn)) {
 		/*
 		 * This can happen when mappings are changed asynchronously, but
 		 * also synchronously if a COW is triggered by
@@ -842,7 +890,7 @@ retry:
 
 	/* Disable dirty logging on HugePages */
 	level = 0;
-	if (!fault_supports_huge_mapping(memslot, hva, PMD_SIZE, write)) {
+	if (!fault_supports_huge_mapping(memslot, hva, write)) {
 		level = 0;
 	} else {
 		level = host_pfn_mapping_level(kvm, gfn, memslot);
@@ -901,12 +949,6 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
 {
 }
 
-int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old,
-				   struct kvm_memory_slot *new, enum kvm_mr_change change)
-{
-	return 0;
-}
-
 void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
 					const struct kvm_memory_slot *memslot)
 {
diff --git a/arch/loongarch/kvm/switch.S b/arch/loongarch/kvm/switch.S
index 0ed9040307b7..ba976509bfe8 100644
--- a/arch/loongarch/kvm/switch.S
+++ b/arch/loongarch/kvm/switch.S
@@ -245,6 +245,37 @@ SYM_FUNC_START(kvm_restore_fpu)
 	jr                 ra
 SYM_FUNC_END(kvm_restore_fpu)
 
+#ifdef CONFIG_CPU_HAS_LSX
+SYM_FUNC_START(kvm_save_lsx)
+	fpu_save_csr    a0 t1
+	fpu_save_cc     a0 t1 t2
+	lsx_save_data   a0 t1
+	jr              ra
+SYM_FUNC_END(kvm_save_lsx)
+
+SYM_FUNC_START(kvm_restore_lsx)
+	lsx_restore_data a0 t1
+	fpu_restore_cc   a0 t1 t2
+	fpu_restore_csr  a0 t1 t2
+	jr               ra
+SYM_FUNC_END(kvm_restore_lsx)
+#endif
+
+#ifdef CONFIG_CPU_HAS_LASX
+SYM_FUNC_START(kvm_save_lasx)
+	fpu_save_csr    a0 t1
+	fpu_save_cc     a0 t1 t2
+	lasx_save_data  a0 t1
+	jr              ra
+SYM_FUNC_END(kvm_save_lasx)
+
+SYM_FUNC_START(kvm_restore_lasx)
+	lasx_restore_data a0 t1
+	fpu_restore_cc    a0 t1 t2
+	fpu_restore_csr   a0 t1 t2
+	jr                ra
+SYM_FUNC_END(kvm_restore_lasx)
+#endif
 	.section ".rodata"
 SYM_DATA(kvm_exception_size, .quad kvm_exc_entry_end - kvm_exc_entry)
 SYM_DATA(kvm_enter_guest_size, .quad kvm_enter_guest_end - kvm_enter_guest)
diff --git a/arch/loongarch/kvm/timer.c b/arch/loongarch/kvm/timer.c
index 284bf553fefe..111328f60872 100644
--- a/arch/loongarch/kvm/timer.c
+++ b/arch/loongarch/kvm/timer.c
@@ -65,40 +65,23 @@ void kvm_init_timer(struct kvm_vcpu *vcpu, unsigned long timer_hz)
 }
 
 /*
- * Restore hard timer state and enable guest to access timer registers
- * without trap, should be called with irq disabled
- */
-void kvm_acquire_timer(struct kvm_vcpu *vcpu)
-{
-	unsigned long cfg;
-
-	cfg = read_csr_gcfg();
-	if (!(cfg & CSR_GCFG_TIT))
-		return;
-
-	/* Enable guest access to hard timer */
-	write_csr_gcfg(cfg & ~CSR_GCFG_TIT);
-
-	/*
-	 * Freeze the soft-timer and sync the guest stable timer with it. We do
-	 * this with interrupts disabled to avoid latency.
-	 */
-	hrtimer_cancel(&vcpu->arch.swtimer);
-}
-
-/*
  * Restore soft timer state from saved context.
  */
 void kvm_restore_timer(struct kvm_vcpu *vcpu)
 {
-	unsigned long cfg, delta, period;
+	unsigned long cfg, estat;
+	unsigned long ticks, delta, period;
 	ktime_t expire, now;
 	struct loongarch_csrs *csr = vcpu->arch.csr;
 
 	/*
 	 * Set guest stable timer cfg csr
+	 * Disable timer before restore estat CSR register, avoid to
+	 * get invalid timer interrupt for old timer cfg
 	 */
 	cfg = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_TCFG);
+
+	write_gcsr_timercfg(0);
 	kvm_restore_hw_gcsr(csr, LOONGARCH_CSR_ESTAT);
 	kvm_restore_hw_gcsr(csr, LOONGARCH_CSR_TCFG);
 	if (!(cfg & CSR_TCFG_EN)) {
@@ -108,23 +91,55 @@ void kvm_restore_timer(struct kvm_vcpu *vcpu)
 	}
 
 	/*
+	 * Freeze the soft-timer and sync the guest stable timer with it.
+	 */
+	hrtimer_cancel(&vcpu->arch.swtimer);
+
+	/*
+	 * From LoongArch Reference Manual Volume 1 Chapter 7.6.2
+	 * If oneshot timer is fired, CSR TVAL will be -1, there are two
+	 * conditions:
+	 *  1) timer is fired during exiting to host
+	 *  2) timer is fired and vm is doing timer irq, and then exiting to
+	 *     host. Host should not inject timer irq to avoid spurious
+	 *     timer interrupt again
+	 */
+	ticks = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_TVAL);
+	estat = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_ESTAT);
+	if (!(cfg & CSR_TCFG_PERIOD) && (ticks > cfg)) {
+		/*
+		 * Writing 0 to LOONGARCH_CSR_TVAL will inject timer irq
+		 * and set CSR TVAL with -1
+		 */
+		write_gcsr_timertick(0);
+
+		/*
+		 * Writing CSR_TINTCLR_TI to LOONGARCH_CSR_TINTCLR will clear
+		 * timer interrupt, and CSR TVAL keeps unchanged with -1, it
+		 * avoids spurious timer interrupt
+		 */
+		if (!(estat & CPU_TIMER))
+			gcsr_write(CSR_TINTCLR_TI, LOONGARCH_CSR_TINTCLR);
+		return;
+	}
+
+	/*
 	 * Set remainder tick value if not expired
 	 */
+	delta = 0;
 	now = ktime_get();
 	expire = vcpu->arch.expire;
 	if (ktime_before(now, expire))
 		delta = ktime_to_tick(vcpu, ktime_sub(expire, now));
-	else {
-		if (cfg & CSR_TCFG_PERIOD) {
-			period = cfg & CSR_TCFG_VAL;
-			delta = ktime_to_tick(vcpu, ktime_sub(now, expire));
-			delta = period - (delta % period);
-		} else
-			delta = 0;
+	else if (cfg & CSR_TCFG_PERIOD) {
+		period = cfg & CSR_TCFG_VAL;
+		delta = ktime_to_tick(vcpu, ktime_sub(now, expire));
+		delta = period - (delta % period);
+
 		/*
 		 * Inject timer here though sw timer should inject timer
 		 * interrupt async already, since sw timer may be cancelled
-		 * during injecting intr async in function kvm_acquire_timer
+		 * during injecting intr async
 		 */
 		kvm_queue_irq(vcpu, INT_TI);
 	}
@@ -139,27 +154,41 @@ void kvm_restore_timer(struct kvm_vcpu *vcpu)
  */
 static void _kvm_save_timer(struct kvm_vcpu *vcpu)
 {
-	unsigned long ticks, delta;
+	unsigned long ticks, delta, cfg;
 	ktime_t expire;
 	struct loongarch_csrs *csr = vcpu->arch.csr;
 
+	cfg = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_TCFG);
 	ticks = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_TVAL);
-	delta = tick_to_ns(vcpu, ticks);
-	expire = ktime_add_ns(ktime_get(), delta);
-	vcpu->arch.expire = expire;
-	if (ticks) {
+
+	/*
+	 * From LoongArch Reference Manual Volume 1 Chapter 7.6.2
+	 * If period timer is fired, CSR TVAL will be reloaded from CSR TCFG
+	 * If oneshot timer is fired, CSR TVAL will be -1
+	 * Here judge one-shot timer fired by checking whether TVAL is larger
+	 * than TCFG
+	 */
+	if (ticks < cfg) {
+		delta = tick_to_ns(vcpu, ticks);
+		expire = ktime_add_ns(ktime_get(), delta);
+		vcpu->arch.expire = expire;
+
 		/*
-		 * Update hrtimer to use new timeout
 		 * HRTIMER_MODE_PINNED is suggested since vcpu may run in
 		 * the same physical cpu in next time
 		 */
-		hrtimer_cancel(&vcpu->arch.swtimer);
 		hrtimer_start(&vcpu->arch.swtimer, expire, HRTIMER_MODE_ABS_PINNED);
-	} else
+	} else if (vcpu->stat.generic.blocking) {
 		/*
-		 * Inject timer interrupt so that hall polling can dectect and exit
+		 * Inject timer interrupt so that halt polling can dectect and exit.
+		 * VCPU is scheduled out already and sleeps in rcuwait queue and
+		 * will not poll pending events again. kvm_queue_irq() is not enough,
+		 * hrtimer swtimer should be used here.
 		 */
-		kvm_queue_irq(vcpu, INT_TI);
+		expire = ktime_add_ns(ktime_get(), 10);
+		vcpu->arch.expire = expire;
+		hrtimer_start(&vcpu->arch.swtimer, expire, HRTIMER_MODE_ABS_PINNED);
+	}
 }
 
 /*
@@ -168,21 +197,15 @@ static void _kvm_save_timer(struct kvm_vcpu *vcpu)
  */
 void kvm_save_timer(struct kvm_vcpu *vcpu)
 {
-	unsigned long cfg;
 	struct loongarch_csrs *csr = vcpu->arch.csr;
 
 	preempt_disable();
-	cfg = read_csr_gcfg();
-	if (!(cfg & CSR_GCFG_TIT)) {
-		/* Disable guest use of hard timer */
-		write_csr_gcfg(cfg | CSR_GCFG_TIT);
-
-		/* Save hard timer state */
-		kvm_save_hw_gcsr(csr, LOONGARCH_CSR_TCFG);
-		kvm_save_hw_gcsr(csr, LOONGARCH_CSR_TVAL);
-		if (kvm_read_sw_gcsr(csr, LOONGARCH_CSR_TCFG) & CSR_TCFG_EN)
-			_kvm_save_timer(vcpu);
-	}
+
+	/* Save hard timer state */
+	kvm_save_hw_gcsr(csr, LOONGARCH_CSR_TCFG);
+	kvm_save_hw_gcsr(csr, LOONGARCH_CSR_TVAL);
+	if (kvm_read_sw_gcsr(csr, LOONGARCH_CSR_TCFG) & CSR_TCFG_EN)
+		_kvm_save_timer(vcpu);
 
 	/* Save timer-related state to vCPU context */
 	kvm_save_hw_gcsr(csr, LOONGARCH_CSR_ESTAT);
diff --git a/arch/loongarch/kvm/trace.h b/arch/loongarch/kvm/trace.h
index a1e35d655418..c2484ad4cffa 100644
--- a/arch/loongarch/kvm/trace.h
+++ b/arch/loongarch/kvm/trace.h
@@ -102,6 +102,8 @@ TRACE_EVENT(kvm_exit_gspr,
 #define KVM_TRACE_AUX_DISCARD		4
 
 #define KVM_TRACE_AUX_FPU		1
+#define KVM_TRACE_AUX_LSX		2
+#define KVM_TRACE_AUX_LASX		3
 
 #define kvm_trace_symbol_aux_op				\
 	{ KVM_TRACE_AUX_SAVE,		"save" },	\
@@ -111,7 +113,9 @@ TRACE_EVENT(kvm_exit_gspr,
 	{ KVM_TRACE_AUX_DISCARD,	"discard" }
 
 #define kvm_trace_symbol_aux_state			\
-	{ KVM_TRACE_AUX_FPU,     "FPU" }
+	{ KVM_TRACE_AUX_FPU,     "FPU" },		\
+	{ KVM_TRACE_AUX_LSX,     "LSX" },		\
+	{ KVM_TRACE_AUX_LASX,    "LASX" }
 
 TRACE_EVENT(kvm_aux,
 	    TP_PROTO(struct kvm_vcpu *vcpu, unsigned int op,
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 73d0c2b9c1a5..36106922b5d7 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -95,7 +95,6 @@ static int kvm_pre_enter_guest(struct kvm_vcpu *vcpu)
 		 * check vmid before vcpu enter guest
 		 */
 		local_irq_disable();
-		kvm_acquire_timer(vcpu);
 		kvm_deliver_intr(vcpu);
 		kvm_deliver_exception(vcpu);
 		/* Make sure the vcpu mode has been written */
@@ -187,8 +186,15 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 {
-	return kvm_pending_timer(vcpu) ||
+	int ret;
+
+	/* Protect from TOD sync and vcpu_load/put() */
+	preempt_disable();
+	ret = kvm_pending_timer(vcpu) ||
 		kvm_read_hw_gcsr(LOONGARCH_CSR_ESTAT) & (1 << INT_TI);
+	preempt_enable();
+
+	return ret;
 }
 
 int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu)
@@ -244,23 +250,6 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	return -EINVAL;
 }
 
-/**
- * kvm_migrate_count() - Migrate timer.
- * @vcpu:       Virtual CPU.
- *
- * Migrate hrtimer to the current CPU by cancelling and restarting it
- * if the hrtimer is active.
- *
- * Must be called when the vCPU is migrated to a different CPU, so that
- * the timer can interrupt the guest at the new CPU, and the timer irq can
- * be delivered to the vCPU.
- */
-static void kvm_migrate_count(struct kvm_vcpu *vcpu)
-{
-	if (hrtimer_cancel(&vcpu->arch.swtimer))
-		hrtimer_restart(&vcpu->arch.swtimer);
-}
-
 static int _kvm_getcsr(struct kvm_vcpu *vcpu, unsigned int id, u64 *val)
 {
 	unsigned long gintc;
@@ -309,6 +298,75 @@ static int _kvm_setcsr(struct kvm_vcpu *vcpu, unsigned int id, u64 val)
 	return ret;
 }
 
+static int _kvm_get_cpucfg_mask(int id, u64 *v)
+{
+	if (id < 0 || id >= KVM_MAX_CPUCFG_REGS)
+		return -EINVAL;
+
+	switch (id) {
+	case 2:
+		/* CPUCFG2 features unconditionally supported by KVM */
+		*v = CPUCFG2_FP     | CPUCFG2_FPSP  | CPUCFG2_FPDP     |
+		     CPUCFG2_FPVERS | CPUCFG2_LLFTP | CPUCFG2_LLFTPREV |
+		     CPUCFG2_LAM;
+		/*
+		 * For the ISA extensions listed below, if one is supported
+		 * by the host, then it is also supported by KVM.
+		 */
+		if (cpu_has_lsx)
+			*v |= CPUCFG2_LSX;
+		if (cpu_has_lasx)
+			*v |= CPUCFG2_LASX;
+
+		return 0;
+	default:
+		/*
+		 * No restrictions on other valid CPUCFG IDs' values, but
+		 * CPUCFG data is limited to 32 bits as the LoongArch ISA
+		 * manual says (Volume 1, Section 2.2.10.5 "CPUCFG").
+		 */
+		*v = U32_MAX;
+		return 0;
+	}
+}
+
+static int kvm_check_cpucfg(int id, u64 val)
+{
+	int ret;
+	u64 mask = 0;
+
+	ret = _kvm_get_cpucfg_mask(id, &mask);
+	if (ret)
+		return ret;
+
+	if (val & ~mask)
+		/* Unsupported features and/or the higher 32 bits should not be set */
+		return -EINVAL;
+
+	switch (id) {
+	case 2:
+		if (!(val & CPUCFG2_LLFTP))
+			/* Guests must have a constant timer */
+			return -EINVAL;
+		if ((val & CPUCFG2_FP) && (!(val & CPUCFG2_FPSP) || !(val & CPUCFG2_FPDP)))
+			/* Single and double float point must both be set when FP is enabled */
+			return -EINVAL;
+		if ((val & CPUCFG2_LSX) && !(val & CPUCFG2_FP))
+			/* LSX architecturally implies FP but val does not satisfy that */
+			return -EINVAL;
+		if ((val & CPUCFG2_LASX) && !(val & CPUCFG2_LSX))
+			/* LASX architecturally implies LSX and FP but val does not satisfy that */
+			return -EINVAL;
+		return 0;
+	default:
+		/*
+		 * Values for the other CPUCFG IDs are not being further validated
+		 * besides the mask check above.
+		 */
+		return 0;
+	}
+}
+
 static int kvm_get_one_reg(struct kvm_vcpu *vcpu,
 		const struct kvm_one_reg *reg, u64 *v)
 {
@@ -378,10 +436,10 @@ static int kvm_set_one_reg(struct kvm_vcpu *vcpu,
 		break;
 	case KVM_REG_LOONGARCH_CPUCFG:
 		id = KVM_GET_IOC_CPUCFG_IDX(reg->id);
-		if (id >= 0 && id < KVM_MAX_CPUCFG_REGS)
-			vcpu->arch.cpucfg[id] = (u32)v;
-		else
-			ret = -EINVAL;
+		ret = kvm_check_cpucfg(id, v);
+		if (ret)
+			break;
+		vcpu->arch.cpucfg[id] = (u32)v;
 		break;
 	case KVM_REG_LOONGARCH_KVM:
 		switch (reg->id) {
@@ -471,10 +529,94 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 	return -EINVAL;
 }
 
+static int kvm_loongarch_cpucfg_has_attr(struct kvm_vcpu *vcpu,
+					 struct kvm_device_attr *attr)
+{
+	switch (attr->attr) {
+	case 2:
+		return 0;
+	default:
+		return -ENXIO;
+	}
+
+	return -ENXIO;
+}
+
+static int kvm_loongarch_vcpu_has_attr(struct kvm_vcpu *vcpu,
+				       struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	case KVM_LOONGARCH_VCPU_CPUCFG:
+		ret = kvm_loongarch_cpucfg_has_attr(vcpu, attr);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static int kvm_loongarch_get_cpucfg_attr(struct kvm_vcpu *vcpu,
+					 struct kvm_device_attr *attr)
+{
+	int ret = 0;
+	uint64_t val;
+	uint64_t __user *uaddr = (uint64_t __user *)attr->addr;
+
+	ret = _kvm_get_cpucfg_mask(attr->attr, &val);
+	if (ret)
+		return ret;
+
+	put_user(val, uaddr);
+
+	return ret;
+}
+
+static int kvm_loongarch_vcpu_get_attr(struct kvm_vcpu *vcpu,
+				       struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	case KVM_LOONGARCH_VCPU_CPUCFG:
+		ret = kvm_loongarch_get_cpucfg_attr(vcpu, attr);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static int kvm_loongarch_cpucfg_set_attr(struct kvm_vcpu *vcpu,
+					 struct kvm_device_attr *attr)
+{
+	return -ENXIO;
+}
+
+static int kvm_loongarch_vcpu_set_attr(struct kvm_vcpu *vcpu,
+				       struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	case KVM_LOONGARCH_VCPU_CPUCFG:
+		ret = kvm_loongarch_cpucfg_set_attr(vcpu, attr);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
 	long r;
+	struct kvm_device_attr attr;
 	void __user *argp = (void __user *)arg;
 	struct kvm_vcpu *vcpu = filp->private_data;
 
@@ -514,6 +656,27 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
 		break;
 	}
+	case KVM_HAS_DEVICE_ATTR: {
+		r = -EFAULT;
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			break;
+		r = kvm_loongarch_vcpu_has_attr(vcpu, &attr);
+		break;
+	}
+	case KVM_GET_DEVICE_ATTR: {
+		r = -EFAULT;
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			break;
+		r = kvm_loongarch_vcpu_get_attr(vcpu, &attr);
+		break;
+	}
+	case KVM_SET_DEVICE_ATTR: {
+		r = -EFAULT;
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			break;
+		r = kvm_loongarch_vcpu_set_attr(vcpu, &attr);
+		break;
+	}
 	default:
 		r = -ENOIOCTLCMD;
 		break;
@@ -561,12 +724,96 @@ void kvm_own_fpu(struct kvm_vcpu *vcpu)
 	preempt_enable();
 }
 
+#ifdef CONFIG_CPU_HAS_LSX
+/* Enable LSX and restore context */
+int kvm_own_lsx(struct kvm_vcpu *vcpu)
+{
+	if (!kvm_guest_has_fpu(&vcpu->arch) || !kvm_guest_has_lsx(&vcpu->arch))
+		return -EINVAL;
+
+	preempt_disable();
+
+	/* Enable LSX for guest */
+	set_csr_euen(CSR_EUEN_LSXEN | CSR_EUEN_FPEN);
+	switch (vcpu->arch.aux_inuse & KVM_LARCH_FPU) {
+	case KVM_LARCH_FPU:
+		/*
+		 * Guest FPU state already loaded,
+		 * only restore upper LSX state
+		 */
+		_restore_lsx_upper(&vcpu->arch.fpu);
+		break;
+	default:
+		/* Neither FP or LSX already active,
+		 * restore full LSX state
+		 */
+		kvm_restore_lsx(&vcpu->arch.fpu);
+		break;
+	}
+
+	trace_kvm_aux(vcpu, KVM_TRACE_AUX_RESTORE, KVM_TRACE_AUX_LSX);
+	vcpu->arch.aux_inuse |= KVM_LARCH_LSX | KVM_LARCH_FPU;
+	preempt_enable();
+
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_CPU_HAS_LASX
+/* Enable LASX and restore context */
+int kvm_own_lasx(struct kvm_vcpu *vcpu)
+{
+	if (!kvm_guest_has_fpu(&vcpu->arch) || !kvm_guest_has_lsx(&vcpu->arch) || !kvm_guest_has_lasx(&vcpu->arch))
+		return -EINVAL;
+
+	preempt_disable();
+
+	set_csr_euen(CSR_EUEN_FPEN | CSR_EUEN_LSXEN | CSR_EUEN_LASXEN);
+	switch (vcpu->arch.aux_inuse & (KVM_LARCH_FPU | KVM_LARCH_LSX)) {
+	case KVM_LARCH_LSX:
+	case KVM_LARCH_LSX | KVM_LARCH_FPU:
+		/* Guest LSX state already loaded, only restore upper LASX state */
+		_restore_lasx_upper(&vcpu->arch.fpu);
+		break;
+	case KVM_LARCH_FPU:
+		/* Guest FP state already loaded, only restore upper LSX & LASX state */
+		_restore_lsx_upper(&vcpu->arch.fpu);
+		_restore_lasx_upper(&vcpu->arch.fpu);
+		break;
+	default:
+		/* Neither FP or LSX already active, restore full LASX state */
+		kvm_restore_lasx(&vcpu->arch.fpu);
+		break;
+	}
+
+	trace_kvm_aux(vcpu, KVM_TRACE_AUX_RESTORE, KVM_TRACE_AUX_LASX);
+	vcpu->arch.aux_inuse |= KVM_LARCH_LASX | KVM_LARCH_LSX | KVM_LARCH_FPU;
+	preempt_enable();
+
+	return 0;
+}
+#endif
+
 /* Save context and disable FPU */
 void kvm_lose_fpu(struct kvm_vcpu *vcpu)
 {
 	preempt_disable();
 
-	if (vcpu->arch.aux_inuse & KVM_LARCH_FPU) {
+	if (vcpu->arch.aux_inuse & KVM_LARCH_LASX) {
+		kvm_save_lasx(&vcpu->arch.fpu);
+		vcpu->arch.aux_inuse &= ~(KVM_LARCH_LSX | KVM_LARCH_FPU | KVM_LARCH_LASX);
+		trace_kvm_aux(vcpu, KVM_TRACE_AUX_SAVE, KVM_TRACE_AUX_LASX);
+
+		/* Disable LASX & LSX & FPU */
+		clear_csr_euen(CSR_EUEN_FPEN | CSR_EUEN_LSXEN | CSR_EUEN_LASXEN);
+	} else if (vcpu->arch.aux_inuse & KVM_LARCH_LSX) {
+		kvm_save_lsx(&vcpu->arch.fpu);
+		vcpu->arch.aux_inuse &= ~(KVM_LARCH_LSX | KVM_LARCH_FPU);
+		trace_kvm_aux(vcpu, KVM_TRACE_AUX_SAVE, KVM_TRACE_AUX_LSX);
+
+		/* Disable LSX & FPU */
+		clear_csr_euen(CSR_EUEN_FPEN | CSR_EUEN_LSXEN);
+	} else if (vcpu->arch.aux_inuse & KVM_LARCH_FPU) {
 		kvm_save_fpu(&vcpu->arch.fpu);
 		vcpu->arch.aux_inuse &= ~KVM_LARCH_FPU;
 		trace_kvm_aux(vcpu, KVM_TRACE_AUX_SAVE, KVM_TRACE_AUX_FPU);
@@ -789,17 +1036,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	if (vcpu->arch.last_sched_cpu != cpu) {
-		kvm_debug("[%d->%d]KVM vCPU[%d] switch\n",
-				vcpu->arch.last_sched_cpu, cpu, vcpu->vcpu_id);
-		/*
-		 * Migrate the timer interrupt to the current CPU so that it
-		 * always interrupts the guest and synchronously triggers a
-		 * guest timer interrupt.
-		 */
-		kvm_migrate_count(vcpu);
-	}
-
 	/* Restore guest state to registers */
 	_kvm_vcpu_load(vcpu, cpu);
 	local_irq_restore(flags);
diff --git a/arch/loongarch/mm/kasan_init.c b/arch/loongarch/mm/kasan_init.c
index cc3e81fe0186..c608adc99845 100644
--- a/arch/loongarch/mm/kasan_init.c
+++ b/arch/loongarch/mm/kasan_init.c
@@ -44,6 +44,9 @@ void *kasan_mem_to_shadow(const void *addr)
 		unsigned long xrange = (maddr >> XRANGE_SHIFT) & 0xffff;
 		unsigned long offset = 0;
 
+		if (maddr >= FIXADDR_START)
+			return (void *)(kasan_early_shadow_page);
+
 		maddr &= XRANGE_SHADOW_MASK;
 		switch (xrange) {
 		case XKPRANGE_CC_SEG:
diff --git a/arch/loongarch/mm/tlb.c b/arch/loongarch/mm/tlb.c
index 2c0a411f23aa..0b95d32b30c9 100644
--- a/arch/loongarch/mm/tlb.c
+++ b/arch/loongarch/mm/tlb.c
@@ -284,12 +284,16 @@ static void setup_tlb_handler(int cpu)
 		set_handler(EXCCODE_TLBNR * VECSIZE, handle_tlb_protect, VECSIZE);
 		set_handler(EXCCODE_TLBNX * VECSIZE, handle_tlb_protect, VECSIZE);
 		set_handler(EXCCODE_TLBPE * VECSIZE, handle_tlb_protect, VECSIZE);
-	}
+	} else {
+		int vec_sz __maybe_unused;
+		void *addr __maybe_unused;
+		struct page *page __maybe_unused;
+
+		/* Avoid lockdep warning */
+		rcutree_report_cpu_starting(cpu);
+
 #ifdef CONFIG_NUMA
-	else {
-		void *addr;
-		struct page *page;
-		const int vec_sz = sizeof(exception_handlers);
+		vec_sz = sizeof(exception_handlers);
 
 		if (pcpu_handlers[cpu])
 			return;
@@ -305,8 +309,8 @@ static void setup_tlb_handler(int cpu)
 		csr_write64(pcpu_handlers[cpu], LOONGARCH_CSR_EENTRY);
 		csr_write64(pcpu_handlers[cpu], LOONGARCH_CSR_MERRENTRY);
 		csr_write64(pcpu_handlers[cpu] + 80*VECSIZE, LOONGARCH_CSR_TLBRENTRY);
-	}
 #endif
+	}
 }
 
 void tlb_init(int cpu)
diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c
index 4fcd6cd6da23..e73323d759d0 100644
--- a/arch/loongarch/net/bpf_jit.c
+++ b/arch/loongarch/net/bpf_jit.c
@@ -201,6 +201,11 @@ bool bpf_jit_supports_kfunc_call(void)
 	return true;
 }
 
+bool bpf_jit_supports_far_kfunc_call(void)
+{
+	return true;
+}
+
 /* initialized on the first pass of build_body() */
 static int out_offset = -1;
 static int emit_bpf_tail_call(struct jit_ctx *ctx)
@@ -465,7 +470,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 	const u8 dst = regmap[insn->dst_reg];
 	const s16 off = insn->off;
 	const s32 imm = insn->imm;
-	const u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm;
 	const bool is32 = BPF_CLASS(insn->code) == BPF_ALU || BPF_CLASS(insn->code) == BPF_JMP32;
 
 	switch (code) {
@@ -923,8 +927,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 
 	/* dst = imm64 */
 	case BPF_LD | BPF_IMM | BPF_DW:
+	{
+		const u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm;
+
 		move_imm(ctx, dst, imm64, is32);
 		return 1;
+	}
 
 	/* dst = *(size *)(src + off) */
 	case BPF_LDX | BPF_MEM | BPF_B:
diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile
index c74c9921304f..f597cd08a96b 100644
--- a/arch/loongarch/vdso/Makefile
+++ b/arch/loongarch/vdso/Makefile
@@ -2,6 +2,7 @@
 # Objects to go into the VDSO.
 
 KASAN_SANITIZE := n
+UBSAN_SANITIZE := n
 KCOV_INSTRUMENT := n
 
 # Include the generic Makefile to check the built vdso.
diff --git a/arch/m68k/Makefile b/arch/m68k/Makefile
index 43e39040d3ac..0abcf994ce55 100644
--- a/arch/m68k/Makefile
+++ b/arch/m68k/Makefile
@@ -15,10 +15,10 @@
 KBUILD_DEFCONFIG := multi_defconfig
 
 ifdef cross_compiling
-	ifeq ($(CROSS_COMPILE),)
+    ifeq ($(CROSS_COMPILE),)
 		CROSS_COMPILE := $(call cc-cross-prefix, \
 			m68k-linux-gnu- m68k-linux- m68k-unknown-linux-gnu-)
-	endif
+    endif
 endif
 
 #
diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c
index a708fbd5a844..642fb80c5c4e 100644
--- a/arch/m68k/emu/nfblock.c
+++ b/arch/m68k/emu/nfblock.c
@@ -96,6 +96,9 @@ static const struct block_device_operations nfhd_ops = {
 
 static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
 {
+	struct queue_limits lim = {
+		.logical_block_size	= bsize,
+	};
 	struct nfhd_device *dev;
 	int dev_id = id - NFHD_DEV_OFFSET;
 	int err = -ENOMEM;
@@ -117,9 +120,11 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
 	dev->bsize = bsize;
 	dev->bshift = ffs(bsize) - 10;
 
-	dev->disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!dev->disk)
+	dev->disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(dev->disk)) {
+		err = PTR_ERR(dev->disk);
 		goto free_dev;
+	}
 
 	dev->disk->major = major_num;
 	dev->disk->first_minor = dev_id * 16;
@@ -128,7 +133,6 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
 	dev->disk->private_data = dev;
 	sprintf(dev->disk->disk_name, "nfhd%u", dev_id);
 	set_capacity(dev->disk, (sector_t)blocks * (bsize / 512));
-	blk_queue_logical_block_size(dev->disk->queue, bsize);
 	err = add_disk(dev->disk);
 	if (err)
 		goto out_cleanup_disk;
diff --git a/arch/m68k/emu/nfcon.c b/arch/m68k/emu/nfcon.c
index 3a74d493eb3e..17b2987c2bf5 100644
--- a/arch/m68k/emu/nfcon.c
+++ b/arch/m68k/emu/nfcon.c
@@ -23,9 +23,9 @@ static int stderr_id;
 static struct tty_port nfcon_tty_port;
 static struct tty_driver *nfcon_tty_driver;
 
-static void nfputs(const char *str, unsigned int count)
+static void nfputs(const u8 *str, size_t count)
 {
-	char buf[68];
+	u8 buf[68];
 	unsigned long phys = virt_to_phys(buf);
 
 	buf[64] = 0;
diff --git a/arch/m68k/include/asm/cacheflush_mm.h b/arch/m68k/include/asm/cacheflush_mm.h
index ed12358c4783..9a71b0148461 100644
--- a/arch/m68k/include/asm/cacheflush_mm.h
+++ b/arch/m68k/include/asm/cacheflush_mm.h
@@ -191,6 +191,7 @@ extern void cache_push_v(unsigned long vaddr, int len);
 #define flush_cache_all() __flush_cache_all()
 
 #define flush_cache_vmap(start, end)		flush_cache_all()
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		flush_cache_all()
 
 static inline void flush_cache_mm(struct mm_struct *mm)
diff --git a/arch/microblaze/configs/mmu_defconfig b/arch/microblaze/configs/mmu_defconfig
index 7b2d7f6f23c0..4da7bc4ac4a3 100644
--- a/arch/microblaze/configs/mmu_defconfig
+++ b/arch/microblaze/configs/mmu_defconfig
@@ -3,11 +3,9 @@ CONFIG_POSIX_MQUEUE=y
 CONFIG_AUDIT=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
-CONFIG_SYSFS_DEPRECATED=y
-CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_EXPERT=y
 # CONFIG_BASE_FULL is not set
 CONFIG_KALLSYMS_ALL=y
-CONFIG_EXPERT=y
 CONFIG_XILINX_MICROBLAZE0_USE_MSR_INSTR=1
 CONFIG_XILINX_MICROBLAZE0_USE_PCMP_INSTR=1
 CONFIG_XILINX_MICROBLAZE0_USE_BARREL=1
@@ -20,7 +18,6 @@ CONFIG_CMDLINE_FORCE=y
 CONFIG_HIGHMEM=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
 CONFIG_PARTITION_ADVANCED=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_CMA=y
@@ -28,6 +25,10 @@ CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
 CONFIG_INET=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
 # CONFIG_IPV6 is not set
 CONFIG_BRIDGE=m
 CONFIG_PCI=y
@@ -43,6 +44,7 @@ CONFIG_NETDEVICES=y
 CONFIG_XILINX_EMACLITE=y
 CONFIG_XILINX_AXI_EMAC=y
 CONFIG_XILINX_LL_TEMAC=y
+CONFIG_MARVELL_PHY=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
@@ -77,14 +79,13 @@ CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
 CONFIG_ROMFS_FS=y
 CONFIG_NFS_FS=y
+CONFIG_ROOT_NFS=y
 CONFIG_CIFS=y
-CONFIG_CIFS_STATS2=y
 CONFIG_ENCRYPTED_KEYS=y
 CONFIG_DMA_CMA=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_KGDB=y
 CONFIG_KGDB_TESTS=y
 CONFIG_KGDB_KDB=y
-CONFIG_DEBUG_SLAB=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEBUG_SPINLOCK=y
diff --git a/arch/mips/alchemy/common/prom.c b/arch/mips/alchemy/common/prom.c
index b13d8adf3be4..20d30f6265cd 100644
--- a/arch/mips/alchemy/common/prom.c
+++ b/arch/mips/alchemy/common/prom.c
@@ -40,6 +40,7 @@
 #include <linux/string.h>
 
 #include <asm/bootinfo.h>
+#include <prom.h>
 
 int prom_argc;
 char **prom_argv;
diff --git a/arch/mips/alchemy/common/setup.c b/arch/mips/alchemy/common/setup.c
index 2388d68786f4..a7a6d31a7a41 100644
--- a/arch/mips/alchemy/common/setup.c
+++ b/arch/mips/alchemy/common/setup.c
@@ -30,13 +30,11 @@
 #include <linux/mm.h>
 #include <linux/dma-map-ops.h> /* for dma_default_coherent */
 
+#include <asm/bootinfo.h>
 #include <asm/mipsregs.h>
 
 #include <au1000.h>
 
-extern void __init board_setup(void);
-extern void __init alchemy_set_lpj(void);
-
 static bool alchemy_dma_coherent(void)
 {
 	switch (alchemy_get_cputype()) {
diff --git a/arch/mips/alchemy/devboards/db1200.c b/arch/mips/alchemy/devboards/db1200.c
index f521874ebb07..67f067706af2 100644
--- a/arch/mips/alchemy/devboards/db1200.c
+++ b/arch/mips/alchemy/devboards/db1200.c
@@ -847,7 +847,7 @@ int __init db1200_dev_setup(void)
 	i2c_register_board_info(0, db1200_i2c_devs,
 				ARRAY_SIZE(db1200_i2c_devs));
 	spi_register_board_info(db1200_spi_devs,
-				ARRAY_SIZE(db1200_i2c_devs));
+				ARRAY_SIZE(db1200_spi_devs));
 
 	/* SWITCHES:	S6.8 I2C/SPI selector  (OFF=I2C	 ON=SPI)
 	 *		S6.7 AC97/I2S selector (OFF=AC97 ON=I2S)
diff --git a/arch/mips/alchemy/devboards/db1550.c b/arch/mips/alchemy/devboards/db1550.c
index fd91d9c9a252..6c6837181f55 100644
--- a/arch/mips/alchemy/devboards/db1550.c
+++ b/arch/mips/alchemy/devboards/db1550.c
@@ -589,7 +589,7 @@ int __init db1550_dev_setup(void)
 	i2c_register_board_info(0, db1550_i2c_devs,
 				ARRAY_SIZE(db1550_i2c_devs));
 	spi_register_board_info(db1550_spi_devs,
-				ARRAY_SIZE(db1550_i2c_devs));
+				ARRAY_SIZE(db1550_spi_devs));
 
 	c = clk_get(NULL, "psc0_intclk");
 	if (!IS_ERR(c)) {
diff --git a/arch/mips/bcm47xx/buttons.c b/arch/mips/bcm47xx/buttons.c
index 437a737c01dd..46994f9bb821 100644
--- a/arch/mips/bcm47xx/buttons.c
+++ b/arch/mips/bcm47xx/buttons.c
@@ -147,21 +147,21 @@ static const struct gpio_keys_button
 bcm47xx_buttons_buffalo_whr_g125[] __initconst = {
 	BCM47XX_GPIO_KEY(0, KEY_WPS_BUTTON),
 	BCM47XX_GPIO_KEY(4, KEY_RESTART),
-	BCM47XX_GPIO_KEY(5, BTN_0), /* Router / AP mode swtich */
+	BCM47XX_GPIO_KEY(5, BTN_0), /* Router / AP mode switch */
 };
 
 static const struct gpio_keys_button
 bcm47xx_buttons_buffalo_whr_g54s[] __initconst = {
 	BCM47XX_GPIO_KEY(0, KEY_WPS_BUTTON),
 	BCM47XX_GPIO_KEY_H(4, KEY_RESTART),
-	BCM47XX_GPIO_KEY(5, BTN_0), /* Router / AP mode swtich */
+	BCM47XX_GPIO_KEY(5, BTN_0), /* Router / AP mode switch */
 };
 
 static const struct gpio_keys_button
 bcm47xx_buttons_buffalo_whr_hp_g54[] __initconst = {
 	BCM47XX_GPIO_KEY(0, KEY_WPS_BUTTON),
 	BCM47XX_GPIO_KEY(4, KEY_RESTART),
-	BCM47XX_GPIO_KEY(5, BTN_0), /* Router / AP mode swtich */
+	BCM47XX_GPIO_KEY(5, BTN_0), /* Router / AP mode switch */
 };
 
 static const struct gpio_keys_button
diff --git a/arch/mips/bcm63xx/boards/board_bcm963xx.c b/arch/mips/bcm63xx/boards/board_bcm963xx.c
index 01aff80a5967..99f321b6e417 100644
--- a/arch/mips/bcm63xx/boards/board_bcm963xx.c
+++ b/arch/mips/bcm63xx/boards/board_bcm963xx.c
@@ -702,7 +702,7 @@ static struct ssb_sprom bcm63xx_sprom = {
 	.boardflags_hi		= 0x0000,
 };
 
-int bcm63xx_get_fallback_sprom(struct ssb_bus *bus, struct ssb_sprom *out)
+static int bcm63xx_get_fallback_sprom(struct ssb_bus *bus, struct ssb_sprom *out)
 {
 	if (bus->bustype == SSB_BUSTYPE_PCI) {
 		memcpy(out, &bcm63xx_sprom, sizeof(struct ssb_sprom));
diff --git a/arch/mips/bcm63xx/clk.c b/arch/mips/bcm63xx/clk.c
index 86a6e2590866..3144965fb7dc 100644
--- a/arch/mips/bcm63xx/clk.c
+++ b/arch/mips/bcm63xx/clk.c
@@ -174,7 +174,7 @@ static void enetsw_set(struct clk *clk, int enable)
 	}
 
 	if (enable) {
-		/* reset switch core afer clock change */
+		/* reset switch core after clock change */
 		bcm63xx_core_set_reset(BCM63XX_RESET_ENETSW, 1);
 		msleep(10);
 		bcm63xx_core_set_reset(BCM63XX_RESET_ENETSW, 0);
@@ -304,7 +304,7 @@ static void xtm_set(struct clk *clk, int enable)
 	bcm_hwclock_set(CKCTL_6368_SAR_EN, enable);
 
 	if (enable) {
-		/* reset sar core afer clock change */
+		/* reset sar core after clock change */
 		bcm63xx_core_set_reset(BCM63XX_RESET_SAR, 1);
 		mdelay(1);
 		bcm63xx_core_set_reset(BCM63XX_RESET_SAR, 0);
diff --git a/arch/mips/bcm63xx/dev-rng.c b/arch/mips/bcm63xx/dev-rng.c
index d277b4dc6c68..f94151f7c96f 100644
--- a/arch/mips/bcm63xx/dev-rng.c
+++ b/arch/mips/bcm63xx/dev-rng.c
@@ -26,7 +26,7 @@ static struct platform_device bcm63xx_rng_device = {
 	.resource	= rng_resources,
 };
 
-int __init bcm63xx_rng_register(void)
+static int __init bcm63xx_rng_register(void)
 {
 	if (!BCMCPU_IS_6368())
 		return -ENODEV;
diff --git a/arch/mips/bcm63xx/dev-uart.c b/arch/mips/bcm63xx/dev-uart.c
index 3bc7f3bfc9ad..5d6bf0445b29 100644
--- a/arch/mips/bcm63xx/dev-uart.c
+++ b/arch/mips/bcm63xx/dev-uart.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <bcm63xx_cpu.h>
+#include <bcm63xx_dev_uart.h>
 
 static struct resource uart0_resources[] = {
 	{
diff --git a/arch/mips/bcm63xx/dev-wdt.c b/arch/mips/bcm63xx/dev-wdt.c
index 42130914a3c2..302bf7ed5ad5 100644
--- a/arch/mips/bcm63xx/dev-wdt.c
+++ b/arch/mips/bcm63xx/dev-wdt.c
@@ -34,7 +34,7 @@ static struct platform_device bcm63xx_wdt_device = {
 	},
 };
 
-int __init bcm63xx_wdt_register(void)
+static int __init bcm63xx_wdt_register(void)
 {
 	wdt_resources[0].start = bcm63xx_regset_address(RSET_WDT);
 	wdt_resources[0].end = wdt_resources[0].start;
diff --git a/arch/mips/bcm63xx/irq.c b/arch/mips/bcm63xx/irq.c
index 2548013442f6..6240a8f88ea3 100644
--- a/arch/mips/bcm63xx/irq.c
+++ b/arch/mips/bcm63xx/irq.c
@@ -72,7 +72,7 @@ static inline int enable_irq_for_cpu(int cpu, struct irq_data *d,
  */
 
 #define BUILD_IPIC_INTERNAL(width)					\
-void __dispatch_internal_##width(int cpu)				\
+static void __dispatch_internal_##width(int cpu)			\
 {									\
 	u32 pending[width / 32];					\
 	unsigned int src, tgt;						\
diff --git a/arch/mips/bcm63xx/setup.c b/arch/mips/bcm63xx/setup.c
index d811e3e03f81..c13ddb544a23 100644
--- a/arch/mips/bcm63xx/setup.c
+++ b/arch/mips/bcm63xx/setup.c
@@ -159,7 +159,7 @@ void __init plat_mem_setup(void)
 	board_setup();
 }
 
-int __init bcm63xx_register_devices(void)
+static int __init bcm63xx_register_devices(void)
 {
 	/* register gpiochip */
 	bcm63xx_gpio_init();
diff --git a/arch/mips/bcm63xx/timer.c b/arch/mips/bcm63xx/timer.c
index a86065854c0c..74b83807df30 100644
--- a/arch/mips/bcm63xx/timer.c
+++ b/arch/mips/bcm63xx/timer.c
@@ -178,7 +178,7 @@ int bcm63xx_timer_set(int id, int monotonic, unsigned int countdown_us)
 
 EXPORT_SYMBOL(bcm63xx_timer_set);
 
-int bcm63xx_timer_init(void)
+static int bcm63xx_timer_init(void)
 {
 	int ret, irq;
 	u32 reg;
diff --git a/arch/mips/boot/compressed/dbg.c b/arch/mips/boot/compressed/dbg.c
index 2f1ac38fe1cc..95405292accd 100644
--- a/arch/mips/boot/compressed/dbg.c
+++ b/arch/mips/boot/compressed/dbg.c
@@ -3,7 +3,7 @@
  * MIPS-specific debug support for pre-boot environment
  *
  * NOTE: putc() is board specific, if your board have a 16550 compatible uart,
- * please select SYS_SUPPORTS_ZBOOT_UART16550 for your machine. othewise, you
+ * please select SYS_SUPPORTS_ZBOOT_UART16550 for your machine. otherwise, you
  * need to implement your own putc().
  */
 #include <linux/compiler.h>
diff --git a/arch/mips/boot/compressed/head.S b/arch/mips/boot/compressed/head.S
index 5795d0af1e1b..d237a834b85e 100644
--- a/arch/mips/boot/compressed/head.S
+++ b/arch/mips/boot/compressed/head.S
@@ -25,8 +25,8 @@
 	/* Clear BSS */
 	PTR_LA	a0, _edata
 	PTR_LA	a2, _end
-1:	sw	zero, 0(a0)
-	addiu	a0, a0, 4
+1:	PTR_S	zero, 0(a0)
+	PTR_ADDIU a0, a0, PTRSIZE
 	bne	a2, a0, 1b
 
 	PTR_LA	a0, (.heap)	     /* heap address */
diff --git a/arch/mips/boot/elf2ecoff.c b/arch/mips/boot/elf2ecoff.c
index 6972b97235da..549c5d6ef6d7 100644
--- a/arch/mips/boot/elf2ecoff.c
+++ b/arch/mips/boot/elf2ecoff.c
@@ -443,7 +443,7 @@ int main(int argc, char *argv[])
 	efh.f_symptr = 0;
 	efh.f_nsyms = 0;
 	efh.f_opthdr = sizeof eah;
-	efh.f_flags = 0x100f;	/* Stripped, not sharable. */
+	efh.f_flags = 0x100f;	/* Stripped, not shareable. */
 
 	memset(esecs, 0, sizeof esecs);
 	strcpy(esecs[0].s_name, ".text");
diff --git a/arch/mips/cavium-octeon/csrc-octeon.c b/arch/mips/cavium-octeon/csrc-octeon.c
index 124817609ce0..af62a210a40b 100644
--- a/arch/mips/cavium-octeon/csrc-octeon.c
+++ b/arch/mips/cavium-octeon/csrc-octeon.c
@@ -113,7 +113,7 @@ static struct clocksource clocksource_mips = {
 
 unsigned long long notrace sched_clock(void)
 {
-	/* 64-bit arithmatic can overflow, so use 128-bit.  */
+	/* 64-bit arithmetic can overflow, so use 128-bit.  */
 	u64 t1, t2, t3;
 	unsigned long long rv;
 	u64 mult = clocksource_mips.mult;
diff --git a/arch/mips/cavium-octeon/executive/cvmx-boot-vector.c b/arch/mips/cavium-octeon/executive/cvmx-boot-vector.c
index b7019d21808e..76446db66def 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-boot-vector.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-boot-vector.c
@@ -143,7 +143,7 @@ static void cvmx_boot_vector_init(void *mem)
 		uint64_t v = _cvmx_bootvector_data[i];
 
 		if (OCTEON_IS_OCTEON1PLUS() && (i == 0 || i == 7))
-			v &= 0xffffffff00000000ull; /* KScratch not availble. */
+			v &= 0xffffffff00000000ull; /* KScratch not available */
 		cvmx_write_csr(CVMX_MIO_BOOT_LOC_ADR, i * 8);
 		cvmx_write_csr(CVMX_MIO_BOOT_LOC_DAT, v);
 	}
diff --git a/arch/mips/cavium-octeon/executive/cvmx-bootmem.c b/arch/mips/cavium-octeon/executive/cvmx-bootmem.c
index 334bf8e577e5..628ebdf4b9c5 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-bootmem.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-bootmem.c
@@ -264,7 +264,7 @@ int64_t cvmx_bootmem_phy_alloc(uint64_t req_size, uint64_t address_min,
 	 * Convert !0 address_min and 0 address_max to special case of
 	 * range that specifies an exact memory block to allocate.  Do
 	 * this before other checks and adjustments so that this
-	 * tranformation will be validated.
+	 * transformation will be validated.
 	 */
 	if (address_min && !address_max)
 		address_max = address_min + req_size;
diff --git a/arch/mips/cavium-octeon/executive/cvmx-cmd-queue.c b/arch/mips/cavium-octeon/executive/cvmx-cmd-queue.c
index aa7bbf8d0df5..042a6bc44b5c 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-cmd-queue.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-cmd-queue.c
@@ -192,7 +192,7 @@ cvmx_cmd_queue_result_t cvmx_cmd_queue_initialize(cvmx_cmd_queue_id_t queue_id,
 }
 
 /*
- * Shutdown a queue a free it's command buffers to the FPA. The
+ * Shutdown a queue and free its command buffers to the FPA. The
  * hardware connected to the queue must be stopped before this
  * function is called.
  *
@@ -285,7 +285,7 @@ int cvmx_cmd_queue_length(cvmx_cmd_queue_id_t queue_id)
 
 /*
  * Return the command buffer to be written to. The purpose of this
- * function is to allow CVMX routine access t othe low level buffer
+ * function is to allow CVMX routine access to the low level buffer
  * for initial hardware setup. User applications should not call this
  * function directly.
  *
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-jtag.c b/arch/mips/cavium-octeon/executive/cvmx-helper-jtag.c
index 607b4e659579..1fceb7fd2c94 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-jtag.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-jtag.c
@@ -103,7 +103,7 @@ uint32_t cvmx_helper_qlm_jtag_shift(int qlm, int bits, uint32_t data)
 /**
  * Shift long sequences of zeros into the QLM JTAG chain. It is
  * common to need to shift more than 32 bits of zeros into the
- * chain. This function is a convience wrapper around
+ * chain. This function is a convenience wrapper around
  * cvmx_helper_qlm_jtag_shift() to shift more than 32 bits of
  * zeros at a time.
  *
diff --git a/arch/mips/cavium-octeon/executive/cvmx-pko.c b/arch/mips/cavium-octeon/executive/cvmx-pko.c
index 15faca494c80..6e70b859a0ac 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-pko.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-pko.c
@@ -615,7 +615,7 @@ int cvmx_pko_rate_limit_bits(int port, uint64_t bits_s, int burst)
 	/*
 	 * Each packet has a 12 bytes of interframe gap, an 8 byte
 	 * preamble, and a 4 byte CRC. These are not included in the
-	 * per word count. Multiply by 8 to covert to bits and divide
+	 * per word count. Multiply by 8 to convert to bits and divide
 	 * by 256 for limit granularity.
 	 */
 	pko_mem_port_rate0.s.rate_pkt = (12 + 8 + 4) * 8 * tokens_per_bit / 256;
diff --git a/arch/mips/cavium-octeon/octeon-platform.c b/arch/mips/cavium-octeon/octeon-platform.c
index f76783c24338..5e1dd4e6e82f 100644
--- a/arch/mips/cavium-octeon/octeon-platform.c
+++ b/arch/mips/cavium-octeon/octeon-platform.c
@@ -973,7 +973,7 @@ int __init octeon_prune_device_tree(void)
 			 * zero.
 			 */
 
-			/* Asume that CS1 immediately follows. */
+			/* Assume that CS1 immediately follows. */
 			mio_boot_reg_cfg.u64 =
 				cvmx_read_csr(CVMX_MIO_BOOT_REG_CFGX(cs + 1));
 			region1_base = mio_boot_reg_cfg.s.base << 16;
diff --git a/arch/mips/cobalt/setup.c b/arch/mips/cobalt/setup.c
index 2e099d55a564..9a266bf78339 100644
--- a/arch/mips/cobalt/setup.c
+++ b/arch/mips/cobalt/setup.c
@@ -23,9 +23,6 @@
 
 #include <cobalt.h>
 
-extern void cobalt_machine_restart(char *command);
-extern void cobalt_machine_halt(void);
-
 const char *get_system_type(void)
 {
 	switch (cobalt_board_id) {
diff --git a/arch/mips/configs/ip27_defconfig b/arch/mips/configs/ip27_defconfig
index b51f738a39a0..4714074c8bd7 100644
--- a/arch/mips/configs/ip27_defconfig
+++ b/arch/mips/configs/ip27_defconfig
@@ -287,7 +287,8 @@ CONFIG_BTRFS_FS_POSIX_ACL=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
 CONFIG_FSCACHE_STATS=y
 CONFIG_CACHEFILES=m
 CONFIG_PROC_KCORE=y
diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig
index 38f17b658421..3389e6e885d9 100644
--- a/arch/mips/configs/lemote2f_defconfig
+++ b/arch/mips/configs/lemote2f_defconfig
@@ -238,7 +238,8 @@ CONFIG_BTRFS_FS=m
 CONFIG_QUOTA=y
 CONFIG_QFMT_V2=m
 CONFIG_AUTOFS_FS=m
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
 CONFIG_CACHEFILES=m
 CONFIG_ISO9660_FS=m
 CONFIG_JOLIET=y
diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig
index 07839a4b397e..78f498752066 100644
--- a/arch/mips/configs/loongson3_defconfig
+++ b/arch/mips/configs/loongson3_defconfig
@@ -356,7 +356,8 @@ CONFIG_QFMT_V2=m
 CONFIG_AUTOFS_FS=y
 CONFIG_FUSE_FS=m
 CONFIG_VIRTIO_FS=m
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
 CONFIG_ISO9660_FS=m
 CONFIG_JOLIET=y
 CONFIG_MSDOS_FS=m
diff --git a/arch/mips/configs/pic32mzda_defconfig b/arch/mips/configs/pic32mzda_defconfig
index 166d2ad372d1..54774f90c23e 100644
--- a/arch/mips/configs/pic32mzda_defconfig
+++ b/arch/mips/configs/pic32mzda_defconfig
@@ -68,7 +68,8 @@ CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
 CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
 CONFIG_ISO9660_FS=m
 CONFIG_JOLIET=y
 CONFIG_ZISOFS=y
diff --git a/arch/mips/fw/arc/memory.c b/arch/mips/fw/arc/memory.c
index 66188739f54d..fb78e6fd5de4 100644
--- a/arch/mips/fw/arc/memory.c
+++ b/arch/mips/fw/arc/memory.c
@@ -37,7 +37,7 @@ static unsigned int nr_prom_mem __initdata;
  */
 #define ARC_PAGE_SHIFT	12
 
-struct linux_mdesc * __init ArcGetMemoryDescriptor(struct linux_mdesc *Current)
+static struct linux_mdesc * __init ArcGetMemoryDescriptor(struct linux_mdesc *Current)
 {
 	return (struct linux_mdesc *) ARC_CALL1(get_mdesc, Current);
 }
diff --git a/arch/mips/fw/arc/promlib.c b/arch/mips/fw/arc/promlib.c
index 5e9e840a9314..93e1e70393ee 100644
--- a/arch/mips/fw/arc/promlib.c
+++ b/arch/mips/fw/arc/promlib.c
@@ -15,11 +15,11 @@
 /*
  * For 64bit kernels working with a 32bit ARC PROM pointer arguments
  * for ARC calls need to reside in CKEG0/1. But as soon as the kernel
- * switches to it's first kernel thread stack is set to an address in
+ * switches to its first kernel thread stack is set to an address in
  * XKPHYS, so anything on stack can't be used anymore. This is solved
- * by using a * static declartion variables are put into BSS, which is
+ * by using a * static declaration variables are put into BSS, which is
  * linked to a CKSEG0 address. Since this is only used on UP platforms
- * there is not spinlock needed
+ * there is no spinlock needed
  */
 #define O32_STATIC	static
 #else
diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h
index f36c2519ed97..1f14132b3fc9 100644
--- a/arch/mips/include/asm/cacheflush.h
+++ b/arch/mips/include/asm/cacheflush.h
@@ -97,6 +97,8 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 		__flush_cache_vmap();
 }
 
+#define flush_cache_vmap_early(start, end)     do { } while (0)
+
 extern void (*__flush_cache_vunmap)(void);
 
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h
index 4044eaf989ac..0921ddda11a4 100644
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h
@@ -241,7 +241,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 	"	.set	pop"
 	: "=&r" (sum), "=&r" (tmp)
 	: "r" (saddr), "r" (daddr),
-	  "0" (htonl(len)), "r" (htonl(proto)), "r" (sum));
+	  "0" (htonl(len)), "r" (htonl(proto)), "r" (sum)
+	: "memory");
 
 	return csum_fold(sum);
 }
diff --git a/arch/mips/include/asm/debug.h b/arch/mips/include/asm/debug.h
index c7013e1cb53f..e70392429246 100644
--- a/arch/mips/include/asm/debug.h
+++ b/arch/mips/include/asm/debug.h
@@ -10,7 +10,7 @@
 
 /*
  * mips_debugfs_dir corresponds to the "mips" directory at the top level
- * of the DebugFS hierarchy. MIPS-specific DebugFS entires should be
+ * of the DebugFS hierarchy. MIPS-specific DebugFS entries should be
  * placed beneath this directory.
  */
 extern struct dentry *mips_debugfs_dir;
diff --git a/arch/mips/include/asm/dmi.h b/arch/mips/include/asm/dmi.h
index 27415a288adf..dc397f630c66 100644
--- a/arch/mips/include/asm/dmi.h
+++ b/arch/mips/include/asm/dmi.h
@@ -5,7 +5,7 @@
 #include <linux/io.h>
 #include <linux/memblock.h>
 
-#define dmi_early_remap(x, l)		ioremap_cache(x, l)
+#define dmi_early_remap(x, l)		ioremap(x, l)
 #define dmi_early_unmap(x, l)		iounmap(x)
 #define dmi_remap(x, l)			ioremap_cache(x, l)
 #define dmi_unmap(x)			iounmap(x)
diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index 85bbd967e05f..af58d6ae06b8 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -159,7 +159,7 @@ void iounmap(const volatile void __iomem *addr);
  * address is not guaranteed to be usable directly as a virtual
  * address.
  *
- * This version of ioremap ensures that the memory is marked cachable by
+ * This version of ioremap ensures that the memory is marked cacheable by
  * the CPU.  Also enables full write-combining.	 Useful for some
  * memory-like regions on I/O busses.
  */
@@ -177,7 +177,7 @@ void iounmap(const volatile void __iomem *addr);
  * address is not guaranteed to be usable directly as a virtual
  * address.
  *
- * This version of ioremap ensures that the memory is marked uncachable
+ * This version of ioremap ensures that the memory is marked uncacheable
  * but accelerated by means of write-combining feature. It is specifically
  * useful for PCIe prefetchable windows, which may vastly improve a
  * communications performance. If it was determined on boot stage, what
diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h
index 081be98c71ef..ff5d388502d4 100644
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@@ -39,7 +39,7 @@ extern void jump_label_apply_nops(struct module *mod);
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\t" B_INSN " 2f\n\t"
+	asm goto("1:\t" B_INSN " 2f\n\t"
 		"2:\t.insn\n\t"
 		".pushsection __jump_table,  \"aw\"\n\t"
 		WORD_INSN " 1b, %l[l_yes], %0\n\t"
@@ -53,7 +53,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\t" J_INSN " %l[l_yes]\n\t"
+	asm goto("1:\t" J_INSN " %l[l_yes]\n\t"
 		".pushsection __jump_table,  \"aw\"\n\t"
 		WORD_INSN " 1b, %l[l_yes], %0\n\t"
 		".popsection\n\t"
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 54a85f1d4f2c..179f320cc231 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -810,8 +810,6 @@ int kvm_mips_mkclean_gpa_pt(struct kvm *kvm, gfn_t start_gfn, gfn_t end_gfn);
 pgd_t *kvm_pgd_alloc(void);
 void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
 
-#define KVM_ARCH_WANT_MMU_NOTIFIER
-
 /* Emulation */
 enum emulation_result update_pc(struct kvm_vcpu *vcpu, u32 cause);
 int kvm_get_badinstr(u32 *opc, struct kvm_vcpu *vcpu, u32 *out);
diff --git a/arch/mips/include/asm/mach-au1x00/au1000.h b/arch/mips/include/asm/mach-au1x00/au1000.h
index a7eec3364a64..41546777902b 100644
--- a/arch/mips/include/asm/mach-au1x00/au1000.h
+++ b/arch/mips/include/asm/mach-au1x00/au1000.h
@@ -597,6 +597,9 @@
 
 #include <asm/cpu.h>
 
+void alchemy_set_lpj(void);
+void board_setup(void);
+
 /* helpers to access the SYS_* registers */
 static inline unsigned long alchemy_rdsys(int regofs)
 {
diff --git a/arch/mips/include/asm/mach-au1x00/au1000_dma.h b/arch/mips/include/asm/mach-au1x00/au1000_dma.h
index 0a0cd4270c6f..b82e513c8523 100644
--- a/arch/mips/include/asm/mach-au1x00/au1000_dma.h
+++ b/arch/mips/include/asm/mach-au1x00/au1000_dma.h
@@ -259,7 +259,7 @@ static inline void set_dma_mode(unsigned int dmanr, unsigned int mode)
 	if (!chan)
 		return;
 	/*
-	 * set_dma_mode is only allowed to change endianess, direction,
+	 * set_dma_mode is only allowed to change endianness, direction,
 	 * transfer size, device FIFO width, and coherency settings.
 	 * Make sure anything else is masked off.
 	 */
diff --git a/arch/mips/include/asm/mach-au1x00/gpio-au1000.h b/arch/mips/include/asm/mach-au1x00/gpio-au1000.h
index 82bc2766e2ec..d820b481ac56 100644
--- a/arch/mips/include/asm/mach-au1x00/gpio-au1000.h
+++ b/arch/mips/include/asm/mach-au1x00/gpio-au1000.h
@@ -435,7 +435,7 @@ static inline void alchemy_gpio2_disable_int(int gpio2)
 /**
  * alchemy_gpio2_enable -  Activate GPIO2 block.
  *
- * The GPIO2 block must be enabled excplicitly to work.	 On systems
+ * The GPIO2 block must be enabled explicitly to work.	 On systems
  * where this isn't done by the bootloader, this macro can be used.
  */
 static inline void alchemy_gpio2_enable(void)
diff --git a/arch/mips/include/asm/mach-cobalt/cobalt.h b/arch/mips/include/asm/mach-cobalt/cobalt.h
index 5b9fce73f11d..97f9d5e9446d 100644
--- a/arch/mips/include/asm/mach-cobalt/cobalt.h
+++ b/arch/mips/include/asm/mach-cobalt/cobalt.h
@@ -19,4 +19,7 @@ extern int cobalt_board_id;
 #define COBALT_BRD_ID_QUBE2    0x5
 #define COBALT_BRD_ID_RAQ2     0x6
 
+void cobalt_machine_halt(void);
+void cobalt_machine_restart(char *command);
+
 #endif /* __ASM_COBALT_H */
diff --git a/arch/mips/include/asm/mach-lantiq/falcon/lantiq_soc.h b/arch/mips/include/asm/mach-lantiq/falcon/lantiq_soc.h
index 5855ba1bd1ec..40eaa72e54d0 100644
--- a/arch/mips/include/asm/mach-lantiq/falcon/lantiq_soc.h
+++ b/arch/mips/include/asm/mach-lantiq/falcon/lantiq_soc.h
@@ -55,7 +55,7 @@ extern __iomem void *ltq_sys1_membase;
 #define ltq_sys1_w32_mask(clear, set, reg)   \
 	ltq_sys1_w32((ltq_sys1_r32(reg) & ~(clear)) | (set), reg)
 
-/* allow the gpio and pinctrl drivers to talk to eachother */
+/* allow the gpio and pinctrl drivers to talk to each other */
 extern int pinctrl_falcon_get_range_size(int id);
 extern void pinctrl_falcon_add_gpio_range(struct pinctrl_gpio_range *range);
 
diff --git a/arch/mips/include/asm/mach-loongson64/loongson_hwmon.h b/arch/mips/include/asm/mach-loongson64/loongson_hwmon.h
index 545f91f2ae16..721eafc4644e 100644
--- a/arch/mips/include/asm/mach-loongson64/loongson_hwmon.h
+++ b/arch/mips/include/asm/mach-loongson64/loongson_hwmon.h
@@ -42,7 +42,7 @@ struct loongson_fan_policy {
 	/* period between two check. (Unit: S) */
 	u8	adjust_period;
 
-	/* fan adjust usually depend on a temprature input */
+	/* fan adjust usually depend on a temperature input */
 	get_temp_fun	depend_temp;
 
 	/* up_step/down_step used when type is STEP_SPEED_POLICY */
diff --git a/arch/mips/include/asm/mach-loongson64/loongson_regs.h b/arch/mips/include/asm/mach-loongson64/loongson_regs.h
index b5be7511f6cd..fec767507604 100644
--- a/arch/mips/include/asm/mach-loongson64/loongson_regs.h
+++ b/arch/mips/include/asm/mach-loongson64/loongson_regs.h
@@ -227,7 +227,7 @@ static inline void csr_writeq(u64 val, u32 reg)
 #define LOONGSON_CSR_NODECNT	0x408
 #define LOONGSON_CSR_CPUTEMP	0x428
 
-/* PerCore CSR, only accessable by local cores */
+/* PerCore CSR, only accessible by local cores */
 #define LOONGSON_CSR_IPI_STATUS	0x1000
 #define LOONGSON_CSR_IPI_EN	0x1004
 #define LOONGSON_CSR_IPI_SET	0x1008
diff --git a/arch/mips/include/asm/mach-malta/spaces.h b/arch/mips/include/asm/mach-malta/spaces.h
index d7e54971ec66..1ce4ba97852f 100644
--- a/arch/mips/include/asm/mach-malta/spaces.h
+++ b/arch/mips/include/asm/mach-malta/spaces.h
@@ -23,13 +23,13 @@
  * The kernel is still located in 0x80000000(kseg0). However,
  * the physical mask has been shifted to 0x80000000 which exploits the alias
  * on the Malta board. As a result of which, we override the __pa_symbol
- * to peform direct mapping from virtual to physical addresses. In other
+ * to perform direct mapping from virtual to physical addresses. In other
  * words, the 0x80000000 virtual address maps to 0x80000000 physical address
  * which in turn aliases to 0x0. We do this in order to be able to use a flat
  * 2GB of memory (0x80000000 - 0xffffffff) so we can avoid the I/O hole in
  * 0x10000000 - 0x1fffffff.
  * The last 64KB of physical memory are reserved for correct HIGHMEM
- * macros arithmetics.
+ * macros arithmetic.
  *
  */
 
diff --git a/arch/mips/include/asm/mips-boards/bonito64.h b/arch/mips/include/asm/mips-boards/bonito64.h
index 5368891d424b..31a31fe78d77 100644
--- a/arch/mips/include/asm/mips-boards/bonito64.h
+++ b/arch/mips/include/asm/mips-boards/bonito64.h
@@ -16,7 +16,7 @@
  */
 
 /* Revision 1.48 autogenerated on 08/17/99 15:20:01 */
-/* This bonito64 version editted from bonito.h Revision 1.48 on 11/09/00 */
+/* This bonito64 version edited from bonito.h Revision 1.48 on 11/09/00 */
 
 #ifndef _ASM_MIPS_BOARDS_BONITO64_H
 #define _ASM_MIPS_BOARDS_BONITO64_H
diff --git a/arch/mips/include/asm/mips-cpc.h b/arch/mips/include/asm/mips-cpc.h
index b54453f1648c..5f3a7a9f42bf 100644
--- a/arch/mips/include/asm/mips-cpc.h
+++ b/arch/mips/include/asm/mips-cpc.h
@@ -22,7 +22,7 @@ extern void __iomem *mips_cpc_base;
  *                              the CPC
  *
  * Returns the default physical base address of the Cluster Power Controller
- * memory mapped registers. This is platform dependant & must therefore be
+ * memory mapped registers. This is platform dependent & must therefore be
  * implemented per-platform.
  */
 extern phys_addr_t mips_cpc_default_phys_base(void);
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 2d53704d9f24..ec58cb76d076 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -98,7 +98,7 @@
 
 /*
  * R4640/R4650 cp0 register names.  These registers are listed
- * here only for completeness; without MMU these CPUs are not useable
+ * here only for completeness; without MMU these CPUs are not usable
  * by Linux.  A future ELKS port might take make Linux run on them
  * though ...
  */
@@ -461,7 +461,7 @@
 #define EXCCODE_THREAD		25	/* Thread exceptions (MT) */
 #define EXCCODE_DSPDIS		26	/* DSP disabled exception */
 #define EXCCODE_GE		27	/* Virtualized guest exception (VZ) */
-#define EXCCODE_CACHEERR	30	/* Parity/ECC occured on a core */
+#define EXCCODE_CACHEERR	30	/* Parity/ECC occurred on a core */
 
 /* Implementation specific trap codes used by MIPS cores */
 #define MIPS_EXCCODE_TLBPAR	16	/* TLB parity error exception */
diff --git a/arch/mips/include/asm/octeon/cvmx-bootinfo.h b/arch/mips/include/asm/octeon/cvmx-bootinfo.h
index c1c0b3230e0a..028bf1d6daee 100644
--- a/arch/mips/include/asm/octeon/cvmx-bootinfo.h
+++ b/arch/mips/include/asm/octeon/cvmx-bootinfo.h
@@ -114,7 +114,7 @@ struct cvmx_bootinfo {
 
 	/*
 	 * flags indicating various configuration options.  These
-	 * flags supercede the 'flags' variable and should be used
+	 * flags supersede the 'flags' variable and should be used
 	 * instead if available.
 	 */
 	uint32_t config_flags;
diff --git a/arch/mips/include/asm/octeon/cvmx-cmd-queue.h b/arch/mips/include/asm/octeon/cvmx-cmd-queue.h
index a07a36f7d814..67e1b2162b19 100644
--- a/arch/mips/include/asm/octeon/cvmx-cmd-queue.h
+++ b/arch/mips/include/asm/octeon/cvmx-cmd-queue.h
@@ -145,7 +145,7 @@ typedef struct {
 /**
  * This structure contains the global state of all command queues.
  * It is stored in a bootmem named block and shared by all
- * applications running on Octeon. Tickets are stored in a differnet
+ * applications running on Octeon. Tickets are stored in a different
  * cache line that queue information to reduce the contention on the
  * ll/sc used to get a ticket. If this is not the case, the update
  * of queue state causes the ll/sc to fail quite often.
@@ -172,7 +172,7 @@ cvmx_cmd_queue_result_t cvmx_cmd_queue_initialize(cvmx_cmd_queue_id_t queue_id,
 						  int pool_size);
 
 /**
- * Shutdown a queue a free it's command buffers to the FPA. The
+ * Shutdown a queue and free its command buffers to the FPA. The
  * hardware connected to the queue must be stopped before this
  * function is called.
  *
@@ -194,7 +194,7 @@ int cvmx_cmd_queue_length(cvmx_cmd_queue_id_t queue_id);
 
 /**
  * Return the command buffer to be written to. The purpose of this
- * function is to allow CVMX routine access t othe low level buffer
+ * function is to allow CVMX routine access to the low level buffer
  * for initial hardware setup. User applications should not call this
  * function directly.
  *
diff --git a/arch/mips/include/asm/octeon/cvmx-pko.h b/arch/mips/include/asm/octeon/cvmx-pko.h
index 5fec8476e421..f18a7f24daf8 100644
--- a/arch/mips/include/asm/octeon/cvmx-pko.h
+++ b/arch/mips/include/asm/octeon/cvmx-pko.h
@@ -91,7 +91,7 @@ typedef enum {
 } cvmx_pko_status_t;
 
 /**
- * This enumeration represents the differnet locking modes supported by PKO.
+ * This enumeration represents the different locking modes supported by PKO.
  */
 typedef enum {
 	/*
diff --git a/arch/mips/include/asm/octeon/cvmx-pow.h b/arch/mips/include/asm/octeon/cvmx-pow.h
index a3b23811e0c3..21b4378244fa 100644
--- a/arch/mips/include/asm/octeon/cvmx-pow.h
+++ b/arch/mips/include/asm/octeon/cvmx-pow.h
@@ -1342,7 +1342,7 @@ static inline void cvmx_pow_tag_sw_wait(void)
  * This function does NOT wait for previous tag switches to complete,
  * so the caller must ensure that there is not a pending tag switch.
  *
- * @wait:   When set, call stalls until work becomes avaiable, or times out.
+ * @wait:   When set, call stalls until work becomes available, or times out.
  *		 If not set, returns immediately.
  *
  * Returns: the WQE pointer from POW. Returns NULL if no work
@@ -1376,7 +1376,7 @@ static inline struct cvmx_wqe *cvmx_pow_work_request_sync_nocheck(cvmx_pow_wait_
  * This function waits for any previous tag switch to complete before
  * requesting the new work.
  *
- * @wait:   When set, call stalls until work becomes avaiable, or times out.
+ * @wait:   When set, call stalls until work becomes available, or times out.
  *		 If not set, returns immediately.
  *
  * Returns: the WQE pointer from POW. Returns NULL if no work
diff --git a/arch/mips/include/asm/octeon/octeon-model.h b/arch/mips/include/asm/octeon/octeon-model.h
index 6c68517c2770..e53b61a8e32f 100644
--- a/arch/mips/include/asm/octeon/octeon-model.h
+++ b/arch/mips/include/asm/octeon/octeon-model.h
@@ -54,7 +54,7 @@
 #define OM_CHECK_SUBMODEL	  0x02000000
 /* Match all models previous than the one specified */
 #define OM_MATCH_PREVIOUS_MODELS  0x04000000
-/* Ignores the minor revison on newer parts */
+/* Ignores the minor revision on newer parts */
 #define OM_IGNORE_MINOR_REVISION  0x08000000
 #define OM_FLAG_MASK		  0xff000000
 
@@ -226,7 +226,7 @@
 #define OCTEON_CN52XX_PASS2	OCTEON_CN52XX_PASS2_X
 
 /*
- * CN3XXX models with old revision enconding
+ * CN3XXX models with old revision encoding
  */
 #define OCTEON_CN38XX_PASS1	0x000d0000
 #define OCTEON_CN38XX_PASS2	0x000d0001
diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h
index 5978a8dfb917..ef9585d96f6b 100644
--- a/arch/mips/include/asm/page.h
+++ b/arch/mips/include/asm/page.h
@@ -173,7 +173,7 @@ static inline unsigned long ___pa(unsigned long x)
 	if (IS_ENABLED(CONFIG_64BIT)) {
 		/*
 		 * For MIPS64 the virtual address may either be in one of
-		 * the compatibility segements ckseg0 or ckseg1, or it may
+		 * the compatibility segments ckseg0 or ckseg1, or it may
 		 * be in xkphys.
 		 */
 		return x < CKSEG0 ? XPHYSADDR(x) : CPHYSADDR(x);
diff --git a/arch/mips/include/asm/pci.h b/arch/mips/include/asm/pci.h
index 3fd6e22c108b..d993df6302dc 100644
--- a/arch/mips/include/asm/pci.h
+++ b/arch/mips/include/asm/pci.h
@@ -23,7 +23,7 @@
 #ifdef CONFIG_PCI_DRIVERS_LEGACY
 
 /*
- * Each pci channel is a top-level PCI bus seem by CPU.	 A machine  with
+ * Each PCI channel is a top-level PCI bus seem by CPU.	 A machine with
  * multiple PCI channels may have multiple PCI host controllers or a
  * single controller supporting multiple channels.
  */
diff --git a/arch/mips/include/asm/pgtable-bits.h b/arch/mips/include/asm/pgtable-bits.h
index 421e78c30253..088623ba7b8b 100644
--- a/arch/mips/include/asm/pgtable-bits.h
+++ b/arch/mips/include/asm/pgtable-bits.h
@@ -201,7 +201,7 @@ enum pgtable_bits {
  * The final layouts of the PTE bits are:
  *
  *   64-bit, R1 or earlier:     CCC D V G [S H] M A W R P
- *   32-bit, R1 or earler:      CCC D V G M A W R P
+ *   32-bit, R1 or earlier:     CCC D V G M A W R P
  *   64-bit, R2 or later:       CCC D V G RI/R XI [S H] M A W P
  *   32-bit, R2 or later:       CCC D V G RI/R XI M A W P
  */
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index daf3cf244ea9..d14d0e37ad02 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -60,6 +60,7 @@ static inline void instruction_pointer_set(struct pt_regs *regs,
                                            unsigned long val)
 {
 	regs->cp0_epc = val;
+	regs->cp0_cause &= ~CAUSEF_BD;
 }
 
 /* Query offset/name of register from its name/offset */
@@ -154,6 +155,8 @@ static inline long regs_return_value(struct pt_regs *regs)
 }
 
 #define instruction_pointer(regs) ((regs)->cp0_epc)
+extern unsigned long exception_ip(struct pt_regs *regs);
+#define exception_ip(regs) exception_ip(regs)
 #define profile_pc(regs) instruction_pointer(regs)
 
 extern asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall);
diff --git a/arch/mips/include/asm/sgi/mc.h b/arch/mips/include/asm/sgi/mc.h
index 3a070cec97e7..5e96f9d32624 100644
--- a/arch/mips/include/asm/sgi/mc.h
+++ b/arch/mips/include/asm/sgi/mc.h
@@ -96,7 +96,7 @@ struct sgimc_regs {
 	volatile u32 lbursttp;	/* Time period for long bursts */
 
 	/* MC chip can drive up to 4 bank 4 SIMMs each. All SIMMs in bank must
-	 * be the same size. The size encoding for supported SIMMs is bellow */
+	 * be the same size. The size encoding for supported SIMMs is below */
 	u32 _unused11[9];
 	volatile u32 mconfig0;	/* Memory config register zero */
 	u32 _unused12;
diff --git a/arch/mips/include/asm/sn/klconfig.h b/arch/mips/include/asm/sn/klconfig.h
index 117f85e4bef5..3d1670b3e052 100644
--- a/arch/mips/include/asm/sn/klconfig.h
+++ b/arch/mips/include/asm/sn/klconfig.h
@@ -851,7 +851,7 @@ typedef union kldev_s {	     /* for device structure allocation */
 /*
  * TBD - Allocation issues.
  *
- * Do we need to Mark off sepatate heaps for lboard_t, rboard_t, component,
+ * Do we need to Mark off separate heaps for lboard_t, rboard_t, component,
  * errinfo and allocate from them, or have a single heap and allocate all
  * structures from it. Debug is easier in the former method since we can
  * dump all similar structs in one command, but there will be lots of holes,
diff --git a/arch/mips/include/asm/sync.h b/arch/mips/include/asm/sync.h
index aabd097933fe..44c04a82d0b7 100644
--- a/arch/mips/include/asm/sync.h
+++ b/arch/mips/include/asm/sync.h
@@ -19,7 +19,7 @@
  *
  * Ordering barriers can be more efficient than completion barriers, since:
  *
- *   a) Ordering barriers only require memory access instructions which preceed
+ *   a) Ordering barriers only require memory access instructions which precede
  *      them in program order (older instructions) to reach a point in the
  *      load/store datapath beyond which reordering is not possible before
  *      allowing memory access instructions which follow them (younger
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index ecae7470faa4..b9d76e8ac5a2 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -27,7 +27,7 @@ struct thread_info {
 	unsigned long		flags;		/* low level flags */
 	unsigned long		tp_value;	/* thread pointer */
 	__u32			cpu;		/* current CPU */
-	int			preempt_count;	/* 0 => preemptable, <0 => BUG */
+	int			preempt_count;	/* 0 => preemptible, <0 => BUG */
 	struct pt_regs		*regs;
 	long			syscall;	/* syscall number */
 };
diff --git a/arch/mips/include/asm/timex.h b/arch/mips/include/asm/timex.h
index 2e107886f97a..7ef06dcdc46e 100644
--- a/arch/mips/include/asm/timex.h
+++ b/arch/mips/include/asm/timex.h
@@ -46,7 +46,7 @@ typedef unsigned int cycles_t;
  *
  * There is a suggested workaround and also the erratum can't strike if
  * the compare interrupt isn't being used as the clock source device.
- * However for now the implementaton of this function doesn't get these
+ * However for now the implementation of this function doesn't get these
  * fine details right.
  */
 static inline int can_use_mips_counter(unsigned int prid)
diff --git a/arch/mips/include/asm/vdso/vdso.h b/arch/mips/include/asm/vdso/vdso.h
index a327ca21270e..6cd88191fefa 100644
--- a/arch/mips/include/asm/vdso/vdso.h
+++ b/arch/mips/include/asm/vdso/vdso.h
@@ -32,7 +32,7 @@ static inline unsigned long get_vdso_base(void)
 #else
 	/*
 	 * Get the base load address of the VDSO. We have to avoid generating
-	 * relocations and references to the GOT because ld.so does not peform
+	 * relocations and references to the GOT because ld.so does not perform
 	 * relocations on the VDSO. We use the current offset from the VDSO base
 	 * and perform a PC-relative branch which gives the absolute address in
 	 * ra, and take the difference. The assembler chokes on
diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h
index c6e1fc77c996..9c48d9a21aa0 100644
--- a/arch/mips/include/uapi/asm/mman.h
+++ b/arch/mips/include/uapi/asm/mman.h
@@ -88,7 +88,7 @@
 #define MADV_HUGEPAGE	14		/* Worth backing with hugepages */
 #define MADV_NOHUGEPAGE 15		/* Not worth backing with hugepages */
 
-#define MADV_DONTDUMP	16		/* Explicity exclude from the core dump,
+#define MADV_DONTDUMP	16		/* Explicitly exclude from core dump,
 					   overrides the coredump filter bits */
 #define MADV_DODUMP	17		/* Clear the MADV_NODUMP flag */
 
diff --git a/arch/mips/include/uapi/asm/msgbuf.h b/arch/mips/include/uapi/asm/msgbuf.h
index 128af72f2dfe..d546642fc67e 100644
--- a/arch/mips/include/uapi/asm/msgbuf.h
+++ b/arch/mips/include/uapi/asm/msgbuf.h
@@ -62,7 +62,7 @@ struct msqid64_ds {
 	unsigned long  __unused5;
 };
 #else
-#warning no endianess set
+#warning no endianness set
 #endif
 
 #endif /* _ASM_MSGBUF_H */
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index de7460c3a72e..bda7f193baab 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -1138,7 +1138,7 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 		 * This processor doesn't have an MMU, so it's not
 		 * "real easy" to run Linux on it. It is left purely
 		 * for documentation.  Commented out because it shares
-		 * it's c0_prid id number with the TX3900.
+		 * its c0_prid id number with the TX3900.
 		 */
 		c->cputype = CPU_R4650;
 		__cpu_name[cpu] = "R4650";
diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c
index 5582a4ca1e9e..7aa2c2360ff6 100644
--- a/arch/mips/kernel/elf.c
+++ b/arch/mips/kernel/elf.c
@@ -11,6 +11,7 @@
 
 #include <asm/cpu-features.h>
 #include <asm/cpu-info.h>
+#include <asm/fpu.h>
 
 #ifdef CONFIG_MIPS_FP_SUPPORT
 
@@ -309,6 +310,11 @@ void mips_set_personality_nan(struct arch_elf_state *state)
 	struct cpuinfo_mips *c = &boot_cpu_data;
 	struct task_struct *t = current;
 
+	/* Do this early so t->thread.fpu.fcr31 won't be clobbered in case
+	 * we are preempted before the lose_fpu(0) in start_thread.
+	 */
+	lose_fpu(0);
+
 	t->thread.fpu.fcr31 = c->fpu_csr31;
 	switch (state->nan_2008) {
 	case 0:
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index b6de8e88c1bd..a572ce36a24f 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -272,18 +272,17 @@ NESTED(except_vec_vi, 0, sp)
 	.set	push
 	.set	noreorder
 	PTR_LA	v1, except_vec_vi_handler
-FEXPORT(except_vec_vi_lui)
-	lui	v0, 0		/* Patched */
 	jr	v1
 FEXPORT(except_vec_vi_ori)
-	 ori	v0, 0		/* Patched */
+	 ori	v0, zero, 0		/* Offset in vi_handlers[] */
 	.set	pop
 	END(except_vec_vi)
 EXPORT(except_vec_vi_end)
 
 /*
  * Common Vectored Interrupt code
- * Complete the register saves and invoke the handler which is passed in $v0
+ * Complete the register saves and invoke the handler, $v0 holds
+ * offset into vi_handlers[]
  */
 NESTED(except_vec_vi_handler, 0, sp)
 	SAVE_TEMP
@@ -331,6 +330,7 @@ NESTED(except_vec_vi_handler, 0, sp)
 	/* Save task's sp on IRQ stack so that unwinding can follow it */
 	LONG_S	s1, 0(sp)
 2:
+	PTR_L	v0, vi_handlers(v0)
 	jalr	v0
 
 	/* Restore sp */
diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c
index 316b27d0d2fb..dc39f5b3fb83 100644
--- a/arch/mips/kernel/kprobes.c
+++ b/arch/mips/kernel/kprobes.c
@@ -55,7 +55,7 @@ NOKPROBE_SYMBOL(insn_has_delayslot);
  * one; putting breakpoint on top of atomic ll/sc pair is bad idea;
  * so we need to prevent it and refuse kprobes insertion for such
  * instructions; cannot do much about breakpoint in the middle of
- * ll/sc pair; it is upto user to avoid those places
+ * ll/sc pair; it is up to user to avoid those places
  */
 static int insn_has_ll_or_sc(union mips_instruction insn)
 {
diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c
index f88ce78e13e3..6062e6fa589a 100644
--- a/arch/mips/kernel/prom.c
+++ b/arch/mips/kernel/prom.c
@@ -28,6 +28,8 @@ __init void mips_set_machine_name(const char *name)
 
 	strscpy(mips_machine_name, name, sizeof(mips_machine_name));
 	pr_info("MIPS: machine is %s\n", mips_get_machine_name());
+
+	dump_stack_set_arch_desc(name);
 }
 
 char *mips_get_machine_name(void)
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index d9df543f7e2c..59288c13b581 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -31,6 +31,7 @@
 #include <linux/seccomp.h>
 #include <linux/ftrace.h>
 
+#include <asm/branch.h>
 #include <asm/byteorder.h>
 #include <asm/cpu.h>
 #include <asm/cpu-info.h>
@@ -48,6 +49,12 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
+unsigned long exception_ip(struct pt_regs *regs)
+{
+	return exception_epc(regs);
+}
+EXPORT_SYMBOL(exception_ip);
+
 /*
  * Called by kernel/ptrace.c when detaching..
  *
diff --git a/arch/mips/kernel/relocate.c b/arch/mips/kernel/relocate.c
index 58fc8d089402..7eeeaf1ff95d 100644
--- a/arch/mips/kernel/relocate.c
+++ b/arch/mips/kernel/relocate.c
@@ -380,7 +380,7 @@ void *__init relocate_kernel(void)
 		}
 #endif /* CONFIG_USE_OF */
 
-		/* Copy the kernel to it's new location */
+		/* Copy the kernel to its new location */
 		memcpy(loc_new, &_text, kernel_length);
 
 		/* Perform relocations on the new kernel */
diff --git a/arch/mips/kernel/relocate_kernel.S b/arch/mips/kernel/relocate_kernel.S
index 8f0a7263a9d6..de894a0211d7 100644
--- a/arch/mips/kernel/relocate_kernel.S
+++ b/arch/mips/kernel/relocate_kernel.S
@@ -70,7 +70,7 @@ copy_word:
 done:
 #ifdef CONFIG_SMP
 	/* kexec_flag reset is signal to other CPUs what kernel
-	   was moved to it's location. Note - we need relocated address
+	   was moved to its location. Note - we need relocated address
 	   of kexec_flag.  */
 
 	bal		1f
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 328426c3ed6f..9c30de151597 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -147,7 +147,7 @@ static unsigned long __init init_initrd(void)
 	/*
 	 * Board specific code or command line parser should have
 	 * already set up initrd_start and initrd_end. In these cases
-	 * perfom sanity checks and use them if all looks good.
+	 * perform sanity checks and use them if all looks good.
 	 */
 	if (!initrd_start || initrd_end <= initrd_start)
 		goto disable;
@@ -322,11 +322,11 @@ static void __init bootmem_init(void)
 		panic("Incorrect memory mapping !!!");
 
 	if (max_pfn > PFN_DOWN(HIGHMEM_START)) {
+		max_low_pfn = PFN_DOWN(HIGHMEM_START);
 #ifdef CONFIG_HIGHMEM
-		highstart_pfn = PFN_DOWN(HIGHMEM_START);
+		highstart_pfn = max_low_pfn;
 		highend_pfn = max_pfn;
 #else
-		max_low_pfn = PFN_DOWN(HIGHMEM_START);
 		max_pfn = max_low_pfn;
 #endif
 	}
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index ccbf580827f6..4a10f18a8806 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -570,7 +570,7 @@ void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
 		return (void __user __force *)(-1UL);
 
 	/*
-	 * FPU emulator may have it's own trampoline active just
+	 * FPU emulator may have its own trampoline active just
 	 * above the user stack, 16-bytes before the next lowest
 	 * 16 byte boundary.  Try to avoid trashing it.
 	 */
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index c58c0c3c5b40..a1c1cb5de913 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -2007,7 +2007,13 @@ unsigned long vi_handlers[64];
 
 void reserve_exception_space(phys_addr_t addr, unsigned long size)
 {
-	memblock_reserve(addr, size);
+	/*
+	 * reserve exception space on CPUs other than CPU0
+	 * is too late, since memblock is unavailable when APs
+	 * up
+	 */
+	if (smp_processor_id() == 0)
+		memblock_reserve(addr, size);
 }
 
 void __init *set_except_vector(int n, void *addr)
@@ -2055,108 +2061,71 @@ static void do_default_vi(void)
 	panic("Caught unexpected vectored interrupt.");
 }
 
-static void *set_vi_srs_handler(int n, vi_handler_t addr, int srs)
+void *set_vi_handler(int n, vi_handler_t addr)
 {
+	extern const u8 except_vec_vi[];
+	extern const u8 except_vec_vi_ori[], except_vec_vi_end[];
+	extern const u8 rollback_except_vec_vi[];
 	unsigned long handler;
 	unsigned long old_handler = vi_handlers[n];
 	int srssets = current_cpu_data.srsets;
 	u16 *h;
 	unsigned char *b;
+	const u8 *vec_start;
+	int ori_offset;
+	int handler_len;
 
 	BUG_ON(!cpu_has_veic && !cpu_has_vint);
 
 	if (addr == NULL) {
 		handler = (unsigned long) do_default_vi;
-		srs = 0;
 	} else
 		handler = (unsigned long) addr;
 	vi_handlers[n] = handler;
 
 	b = (unsigned char *)(ebase + 0x200 + n*VECTORSPACING);
 
-	if (srs >= srssets)
-		panic("Shadow register set %d not supported", srs);
-
 	if (cpu_has_veic) {
 		if (board_bind_eic_interrupt)
-			board_bind_eic_interrupt(n, srs);
+			board_bind_eic_interrupt(n, 0);
 	} else if (cpu_has_vint) {
 		/* SRSMap is only defined if shadow sets are implemented */
 		if (srssets > 1)
-			change_c0_srsmap(0xf << n*4, srs << n*4);
+			change_c0_srsmap(0xf << n*4, 0 << n*4);
 	}
 
-	if (srs == 0) {
-		/*
-		 * If no shadow set is selected then use the default handler
-		 * that does normal register saving and standard interrupt exit
-		 */
-		extern const u8 except_vec_vi[], except_vec_vi_lui[];
-		extern const u8 except_vec_vi_ori[], except_vec_vi_end[];
-		extern const u8 rollback_except_vec_vi[];
-		const u8 *vec_start = using_rollback_handler() ?
-				      rollback_except_vec_vi : except_vec_vi;
+	vec_start = using_rollback_handler() ? rollback_except_vec_vi :
+					       except_vec_vi;
 #if defined(CONFIG_CPU_MICROMIPS) || defined(CONFIG_CPU_BIG_ENDIAN)
-		const int lui_offset = except_vec_vi_lui - vec_start + 2;
-		const int ori_offset = except_vec_vi_ori - vec_start + 2;
+	ori_offset = except_vec_vi_ori - vec_start + 2;
 #else
-		const int lui_offset = except_vec_vi_lui - vec_start;
-		const int ori_offset = except_vec_vi_ori - vec_start;
+	ori_offset = except_vec_vi_ori - vec_start;
 #endif
-		const int handler_len = except_vec_vi_end - vec_start;
+	handler_len = except_vec_vi_end - vec_start;
 
-		if (handler_len > VECTORSPACING) {
-			/*
-			 * Sigh... panicing won't help as the console
-			 * is probably not configured :(
-			 */
-			panic("VECTORSPACING too small");
-		}
-
-		set_handler(((unsigned long)b - ebase), vec_start,
-#ifdef CONFIG_CPU_MICROMIPS
-				(handler_len - 1));
-#else
-				handler_len);
-#endif
-		h = (u16 *)(b + lui_offset);
-		*h = (handler >> 16) & 0xffff;
-		h = (u16 *)(b + ori_offset);
-		*h = (handler & 0xffff);
-		local_flush_icache_range((unsigned long)b,
-					 (unsigned long)(b+handler_len));
-	}
-	else {
+	if (handler_len > VECTORSPACING) {
 		/*
-		 * In other cases jump directly to the interrupt handler. It
-		 * is the handler's responsibility to save registers if required
-		 * (eg hi/lo) and return from the exception using "eret".
+		 * Sigh... panicing won't help as the console
+		 * is probably not configured :(
 		 */
-		u32 insn;
+		panic("VECTORSPACING too small");
+	}
 
-		h = (u16 *)b;
-		/* j handler */
+	set_handler(((unsigned long)b - ebase), vec_start,
 #ifdef CONFIG_CPU_MICROMIPS
-		insn = 0xd4000000 | (((u32)handler & 0x07ffffff) >> 1);
+			(handler_len - 1));
 #else
-		insn = 0x08000000 | (((u32)handler & 0x0fffffff) >> 2);
+			handler_len);
 #endif
-		h[0] = (insn >> 16) & 0xffff;
-		h[1] = insn & 0xffff;
-		h[2] = 0;
-		h[3] = 0;
-		local_flush_icache_range((unsigned long)b,
-					 (unsigned long)(b+8));
-	}
+	/* insert offset into vi_handlers[] */
+	h = (u16 *)(b + ori_offset);
+	*h = n * sizeof(handler);
+	local_flush_icache_range((unsigned long)b,
+				 (unsigned long)(b+handler_len));
 
 	return (void *)old_handler;
 }
 
-void *set_vi_handler(int n, vi_handler_t addr)
-{
-	return set_vi_srs_handler(n, addr, 0);
-}
-
 /*
  * Timer interrupt
  */
@@ -2416,7 +2385,7 @@ void __init trap_init(void)
 		set_except_vector(i, handle_reserved);
 
 	/*
-	 * Copy the EJTAG debug exception vector handler code to it's final
+	 * Copy the EJTAG debug exception vector handler code to its final
 	 * destination.
 	 */
 	if (cpu_has_ejtag && board_ejtag_handler_setup)
diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c
index e9a0cfd02ae2..737d0d4fdcd3 100644
--- a/arch/mips/kernel/vpe.c
+++ b/arch/mips/kernel/vpe.c
@@ -6,9 +6,9 @@
  * Copyright (C) 2004, 2005 MIPS Technologies, Inc.  All rights reserved.
  * Copyright (C) 2013 Imagination Technologies Ltd.
  *
- * VPE spport module for loading a MIPS SP program into VPE1. The SP
+ * VPE support module for loading a MIPS SP program into VPE1. The SP
  * environment is rather simple since there are no TLBs. It needs
- * to be relocatable (or partiall linked). Initialize your stack in
+ * to be relocatable (or partially linked). Initialize your stack in
  * the startup-code. The loader looks for the symbol __start and sets
  * up the execution to resume from there. To load and run, simply do
  * a cat SP 'binary' to the /dev/vpe1 device.
diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig
index a8cdba75f98d..18e7a17d5115 100644
--- a/arch/mips/kvm/Kconfig
+++ b/arch/mips/kvm/Kconfig
@@ -20,13 +20,11 @@ config KVM
 	depends on HAVE_KVM
 	depends on MIPS_FP_SUPPORT
 	select EXPORT_UASM
-	select PREEMPT_NOTIFIERS
+	select KVM_COMMON
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
-	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
 	select KVM_MMIO
-	select MMU_NOTIFIER
-	select INTERVAL_TREE
+	select KVM_GENERIC_MMU_NOTIFIER
 	select KVM_GENERIC_HARDWARE_ENABLING
 	help
 	  Support for hosting Guest kernels.
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index e64372b8f66a..0feec52222fb 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -531,7 +531,7 @@ static void kvm_mips_resume_hrtimer(struct kvm_vcpu *vcpu,
  * to be used for a period of time, but the exact ktime corresponding to the
  * final Count that must be restored is not known.
  *
- * It is gauranteed that a timer interrupt immediately after restore will be
+ * It is guaranteed that a timer interrupt immediately after restore will be
  * handled, but not if CP0_Compare is exactly at @count. That case should
  * already be handled when the hardware timer state is saved.
  *
diff --git a/arch/mips/lantiq/prom.c b/arch/mips/lantiq/prom.c
index a3cf29365858..0c45767eacf6 100644
--- a/arch/mips/lantiq/prom.c
+++ b/arch/mips/lantiq/prom.c
@@ -108,10 +108,9 @@ void __init prom_init(void)
 	prom_init_cmdline();
 
 #if defined(CONFIG_MIPS_MT_SMP)
-	if (cpu_has_mipsmt) {
-		lantiq_smp_ops = vsmp_smp_ops;
+	lantiq_smp_ops = vsmp_smp_ops;
+	if (cpu_has_mipsmt)
 		lantiq_smp_ops.init_secondary = lantiq_init_secondary;
-		register_smp_ops(&lantiq_smp_ops);
-	}
+	register_smp_ops(&lantiq_smp_ops);
 #endif
 }
diff --git a/arch/mips/loongson2ef/common/platform.c b/arch/mips/loongson2ef/common/platform.c
index 0084820cffaa..b10300a527af 100644
--- a/arch/mips/loongson2ef/common/platform.c
+++ b/arch/mips/loongson2ef/common/platform.c
@@ -17,7 +17,7 @@ static int __init loongson2_cpufreq_init(void)
 {
 	struct cpuinfo_mips *c = &current_cpu_data;
 
-	/* Only 2F revision and it's successors support CPUFreq */
+	/* Only 2F revision and its successors support CPUFreq */
 	if ((c->processor_id & PRID_REV_MASK) >= PRID_REV_LOONGSON2F)
 		return platform_device_register(&loongson2_cpufreq_device);
 
diff --git a/arch/mips/loongson64/init.c b/arch/mips/loongson64/init.c
index f25caa6aa9d3..553142c1f14f 100644
--- a/arch/mips/loongson64/init.c
+++ b/arch/mips/loongson64/init.c
@@ -103,6 +103,9 @@ void __init szmem(unsigned int node)
 	if (loongson_sysconf.vgabios_addr)
 		memblock_reserve(virt_to_phys((void *)loongson_sysconf.vgabios_addr),
 				SZ_256K);
+	/* set nid for reserved memory */
+	memblock_set_node((u64)node << 44, (u64)(node + 1) << 44,
+			&memblock.reserved, node);
 }
 
 #ifndef CONFIG_NUMA
diff --git a/arch/mips/loongson64/numa.c b/arch/mips/loongson64/numa.c
index 8f61e93c0c5b..68dafd6d3e25 100644
--- a/arch/mips/loongson64/numa.c
+++ b/arch/mips/loongson64/numa.c
@@ -132,6 +132,8 @@ static void __init node_mem_init(unsigned int node)
 
 		/* Reserve pfn range 0~node[0]->node_start_pfn */
 		memblock_reserve(0, PAGE_SIZE * start_pfn);
+		/* set nid for reserved memory on node 0 */
+		memblock_set_node(0, 1ULL << 44, &memblock.reserved, 0);
 	}
 }
 
diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c
index 498bdc1bb0ed..5a990cdef91a 100644
--- a/arch/mips/loongson64/smp.c
+++ b/arch/mips/loongson64/smp.c
@@ -516,7 +516,7 @@ static void __init loongson3_prepare_cpus(unsigned int max_cpus)
 }
 
 /*
- * Setup the PC, SP, and GP of a secondary processor and start it runing!
+ * Setup the PC, SP, and GP of a secondary processor and start it running!
  */
 static int loongson3_boot_secondary(int cpu, struct task_struct *idle)
 {
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index b45bf026ee55..10413b6f6662 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -1650,7 +1650,7 @@ static void coherency_setup(void)
 
 	/*
 	 * c0_status.cu=0 specifies that updates by the sc instruction use
-	 * the coherency mode specified by the TLB; 1 means cachable
+	 * the coherency mode specified by the TLB; 1 means cacheable
 	 * coherent update on write will be used.  Not all processors have
 	 * this bit and; some wire it to zero, others like Toshiba had the
 	 * silly idea of putting something else there ...
diff --git a/arch/mips/mm/cex-gen.S b/arch/mips/mm/cex-gen.S
index 45dff5cd4b8e..e528583d1331 100644
--- a/arch/mips/mm/cex-gen.S
+++ b/arch/mips/mm/cex-gen.S
@@ -25,7 +25,7 @@
 	 * This is a very bad place to be.  Our cache error
 	 * detection has triggered.  If we have write-back data
 	 * in the cache, we may not be able to recover.	 As a
-	 * first-order desperate measure, turn off KSEG0 cacheing.
+	 * first-order desperate measure, turn off KSEG0 caching.
 	 */
 	mfc0	k0,CP0_CONFIG
 	li	k1,~CONF_CM_CMASK
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
index 3c4fc97b9f39..0f3cec663a12 100644
--- a/arch/mips/mm/dma-noncoherent.c
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -138,7 +138,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 
 #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-		const struct iommu_ops *iommu, bool coherent)
+		bool coherent)
 {
 	dev->dma_coherent = coherent;
 }
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index c2e0e5aebe90..39f129205b0c 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -422,8 +422,17 @@ void __init paging_init(void)
 		       " %ldk highmem ignored\n",
 		       (highend_pfn - max_low_pfn) << (PAGE_SHIFT - 10));
 		max_zone_pfns[ZONE_HIGHMEM] = max_low_pfn;
+
+		max_mapnr = max_low_pfn;
+	} else if (highend_pfn) {
+		max_mapnr = highend_pfn;
+	} else {
+		max_mapnr = max_low_pfn;
 	}
+#else
+	max_mapnr = max_low_pfn;
 #endif
+	high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
 
 	free_area_init(max_zone_pfns);
 }
@@ -459,13 +468,6 @@ void __init mem_init(void)
 	 */
 	BUILD_BUG_ON(IS_ENABLED(CONFIG_32BIT) && (PFN_PTE_SHIFT > PAGE_SHIFT));
 
-#ifdef CONFIG_HIGHMEM
-	max_mapnr = highend_pfn ? highend_pfn : max_low_pfn;
-#else
-	max_mapnr = max_low_pfn;
-#endif
-	high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
-
 	maar_init();
 	memblock_free_all();
 	setup_zero_pages();	/* Setup zeroed pages.  */
diff --git a/arch/mips/mm/ioremap.c b/arch/mips/mm/ioremap.c
index b6dad2fd5575..d8243d61ef32 100644
--- a/arch/mips/mm/ioremap.c
+++ b/arch/mips/mm/ioremap.c
@@ -72,6 +72,10 @@ void __iomem *ioremap_prot(phys_addr_t phys_addr, unsigned long size,
 	    flags == _CACHE_UNCACHED)
 		return (void __iomem *) CKSEG1ADDR(phys_addr);
 
+	/* Early remaps should use the unmapped regions til' VM is available */
+	if (WARN_ON_ONCE(!slab_is_available()))
+		return NULL;
+
 	/*
 	 * Don't allow anybody to remap RAM that may be allocated by the page
 	 * allocator, since that could lead to races & data clobbering.
diff --git a/arch/mips/mm/tlb-r3k.c b/arch/mips/mm/tlb-r3k.c
index f6db65410c65..173f7b36033b 100644
--- a/arch/mips/mm/tlb-r3k.c
+++ b/arch/mips/mm/tlb-r3k.c
@@ -183,7 +183,7 @@ void __update_tlb(struct vm_area_struct *vma, unsigned long address, pte_t pte)
 	int idx, pid;
 
 	/*
-	 * Handle debugger faulting in for debugee.
+	 * Handle debugger faulting in for debuggee.
 	 */
 	if (current->active_mm != vma->vm_mm)
 		return;
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index 7e2a0011a6fb..4106084e57d7 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -301,7 +301,7 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte)
 	int idx, pid;
 
 	/*
-	 * Handle debugger faulting in for debugee.
+	 * Handle debugger faulting in for debuggee.
 	 */
 	if (current->active_mm != vma->vm_mm)
 		return;
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index b4e1c783e617..4017fa0e2f68 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -789,7 +789,7 @@ void build_get_pmde64(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
 
 	if (check_for_high_segbits) {
 		/*
-		 * The kernel currently implicitely assumes that the
+		 * The kernel currently implicitly assumes that the
 		 * MIPS SEGBITS parameter for the processor is
 		 * (PGDIR_SHIFT+PGDIR_BITS) or less, and will never
 		 * allocate virtual addresses outside the maximum
@@ -1715,7 +1715,7 @@ iPTE_SW(u32 **p, struct uasm_reloc **r, unsigned int pte, unsigned int ptr,
 /*
  * Check if PTE is present, if not then jump to LABEL. PTR points to
  * the page table where this PTE is located, PTE will be re-loaded
- * with it's original value.
+ * with its original value.
  */
 static void
 build_pte_present(u32 **p, struct uasm_reloc **r,
diff --git a/arch/mips/net/bpf_jit_comp32.c b/arch/mips/net/bpf_jit_comp32.c
index ace5db3fbd17..40a878b672f5 100644
--- a/arch/mips/net/bpf_jit_comp32.c
+++ b/arch/mips/net/bpf_jit_comp32.c
@@ -95,7 +95,7 @@
 /*
  * Mapping of 64-bit eBPF registers to 32-bit native MIPS registers.
  *
- * 1) Native register pairs are ordered according to CPU endiannes, following
+ * 1) Native register pairs are ordered according to CPU endianness, following
  *    the MIPS convention for passing 64-bit arguments and return values.
  * 2) The eBPF return value, arguments and callee-saved registers are mapped
  *    to their native MIPS equivalents.
diff --git a/arch/mips/pci/ops-loongson2.c b/arch/mips/pci/ops-loongson2.c
index 0d1b36ba1c21..068113f5c49d 100644
--- a/arch/mips/pci/ops-loongson2.c
+++ b/arch/mips/pci/ops-loongson2.c
@@ -49,7 +49,7 @@ static int loongson_pcibios_config_access(unsigned char access_type,
 		 */
 #ifdef CONFIG_CS5536
 		/* cs5536_pci_conf_read4/write4() will call _rdmsr/_wrmsr() to
-		 * access the regsters PCI_MSR_ADDR, PCI_MSR_DATA_LO,
+		 * access the registers PCI_MSR_ADDR, PCI_MSR_DATA_LO,
 		 * PCI_MSR_DATA_HI, which is bigger than PCI_MSR_CTRL, so, it
 		 * will not go this branch, but the others. so, no calling dead
 		 * loop here.
diff --git a/arch/mips/pci/pci-alchemy.c b/arch/mips/pci/pci-alchemy.c
index 1c722dd0c130..58625d1b6465 100644
--- a/arch/mips/pci/pci-alchemy.c
+++ b/arch/mips/pci/pci-alchemy.c
@@ -453,7 +453,7 @@ static int alchemy_pci_probe(struct platform_device *pdev)
 
 	/* we can't ioremap the entire pci config space because it's too large,
 	 * nor can we dynamically ioremap it because some drivers use the
-	 * PCI config routines from within atomic contex and that becomes a
+	 * PCI config routines from within atomic context and that becomes a
 	 * problem in get_vm_area().  Instead we use one wired TLB entry to
 	 * handle all config accesses for all busses.
 	 */
diff --git a/arch/mips/pci/pci-ar2315.c b/arch/mips/pci/pci-ar2315.c
index e17d862cfa4c..a925842ee125 100644
--- a/arch/mips/pci/pci-ar2315.c
+++ b/arch/mips/pci/pci-ar2315.c
@@ -16,7 +16,7 @@
  * the CFG_SEL bit in the PCI_MISC_CONFIG register.
  *
  * Devices on the bus can perform DMA requests via chip BAR1. PCI host
- * controller BARs are programmend as if an external device is programmed.
+ * controller BARs are programmed as if an external device is programmed.
  * Which means that during configuration, IDSEL pin of the chip should be
  * asserted.
  *
diff --git a/arch/mips/pci/pci-lantiq.c b/arch/mips/pci/pci-lantiq.c
index 80f7293166bb..68a8cefed420 100644
--- a/arch/mips/pci/pci-lantiq.c
+++ b/arch/mips/pci/pci-lantiq.c
@@ -152,7 +152,7 @@ static int ltq_pci_startup(struct platform_device *pdev)
 		temp_buffer &= ~0xf0000;
 	/* enable internal arbiter */
 	temp_buffer |= (1 << INTERNAL_ARB_ENABLE_BIT);
-	/* enable internal PCI master reqest */
+	/* enable internal PCI master request */
 	temp_buffer &= (~(3 << PCI_MASTER0_REQ_MASK_2BITS));
 
 	/* enable EBU request */
diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c
index d19d9d456309..36d12cea3512 100644
--- a/arch/mips/pci/pci-octeon.c
+++ b/arch/mips/pci/pci-octeon.c
@@ -376,7 +376,7 @@ static void octeon_pci_initialize(void)
 	ctl_status.s.timer = 1;
 	cvmx_write_csr(CVMX_NPI_CTL_STATUS, ctl_status.u64);
 
-	/* Deassert PCI reset and advertize PCX Host Mode Device Capability
+	/* Deassert PCI reset and advertise PCX Host Mode Device Capability
 	   (64b) */
 	cvmx_write_csr(CVMX_CIU_SOFT_PRST, 0x4);
 	cvmx_read_csr(CVMX_CIU_SOFT_PRST);
diff --git a/arch/mips/pci/pci-xtalk-bridge.c b/arch/mips/pci/pci-xtalk-bridge.c
index 68d5211afea8..45ddbaa6c123 100644
--- a/arch/mips/pci/pci-xtalk-bridge.c
+++ b/arch/mips/pci/pci-xtalk-bridge.c
@@ -114,7 +114,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SGI, PCI_DEVICE_ID_SGI_IOC3,
  *
  * The function is complicated by the ultimate brokenness of the IOC3 chip
  * which is used in SGI systems.  The IOC3 can only handle 32-bit PCI
- * accesses and does only decode parts of it's address space.
+ * accesses and does only decode parts of its address space.
  */
 static int pci_conf0_read_config(struct pci_bus *bus, unsigned int devfn,
 				 int where, int size, u32 *value)
diff --git a/arch/mips/pci/pcie-octeon.c b/arch/mips/pci/pcie-octeon.c
index c9edd3fb380d..2583e318e8c6 100644
--- a/arch/mips/pci/pcie-octeon.c
+++ b/arch/mips/pci/pcie-octeon.c
@@ -1037,7 +1037,7 @@ retry:
 			in_fif_p_count = dbg_data.s.data & 0xff;
 		} while (in_fif_p_count != ((old_in_fif_p_count+1) & 0xff));
 
-		/* Update in_fif_p_count for it's offset with respect to out_p_count */
+		/* Update in_fif_p_count for its offset with respect to out_p_count */
 		in_fif_p_count = (in_fif_p_count + in_p_offset) & 0xff;
 
 		/* Read the OUT_P_COUNT from the debug select */
diff --git a/arch/mips/ralink/mt7621.c b/arch/mips/ralink/mt7621.c
index 137781d0bd0a..5a9fd3fe41d7 100644
--- a/arch/mips/ralink/mt7621.c
+++ b/arch/mips/ralink/mt7621.c
@@ -175,7 +175,7 @@ void __init prom_soc_init(struct ralink_soc_info *soc_info)
 		 * mips_cm_probe() wipes out bootloader
 		 * config for CM regions and we have to configure them
 		 * again. This SoC cannot talk to pamlbus devices
-		 * witout proper iocu region set up.
+		 * without proper iocu region set up.
 		 *
 		 * FIXME: it would be better to do this with values
 		 * from DT, but we need this very early because
diff --git a/arch/mips/sgi-ip27/Makefile b/arch/mips/sgi-ip27/Makefile
index 27c14ede191e..9877fcc512b1 100644
--- a/arch/mips/sgi-ip27/Makefile
+++ b/arch/mips/sgi-ip27/Makefile
@@ -5,7 +5,7 @@
 
 obj-y	:= ip27-berr.o ip27-irq.o ip27-init.o ip27-klconfig.o \
 	   ip27-klnuma.o ip27-memory.o ip27-nmi.o ip27-reset.o ip27-timer.o \
-	   ip27-hubio.o ip27-xtalk.o
+	   ip27-xtalk.o
 
 obj-$(CONFIG_EARLY_PRINTK)	+= ip27-console.o
 obj-$(CONFIG_SMP)		+= ip27-smp.o
diff --git a/arch/mips/sgi-ip27/ip27-berr.c b/arch/mips/sgi-ip27/ip27-berr.c
index 923a63a51cda..9eb497cb5d52 100644
--- a/arch/mips/sgi-ip27/ip27-berr.c
+++ b/arch/mips/sgi-ip27/ip27-berr.c
@@ -22,6 +22,8 @@
 #include <asm/traps.h>
 #include <linux/uaccess.h>
 
+#include "ip27-common.h"
+
 static void dump_hub_information(unsigned long errst0, unsigned long errst1)
 {
 	static char *err_type[2][8] = {
@@ -57,7 +59,7 @@ static void dump_hub_information(unsigned long errst0, unsigned long errst1)
 	       [st0.pi_stat0_fmt.s0_err_type] ? : "invalid");
 }
 
-int ip27_be_handler(struct pt_regs *regs, int is_fixup)
+static int ip27_be_handler(struct pt_regs *regs, int is_fixup)
 {
 	unsigned long errst0, errst1;
 	int data = regs->cp0_cause & 4;
diff --git a/arch/mips/sgi-ip27/ip27-common.h b/arch/mips/sgi-ip27/ip27-common.h
index ed008a08464c..a0059fa13934 100644
--- a/arch/mips/sgi-ip27/ip27-common.h
+++ b/arch/mips/sgi-ip27/ip27-common.h
@@ -10,6 +10,7 @@ extern void hub_rt_clock_event_init(void);
 extern void hub_rtc_init(nasid_t nasid);
 extern void install_cpu_nmi_handler(int slice);
 extern void install_ipi(void);
+extern void ip27_be_init(void);
 extern void ip27_reboot_setup(void);
 extern const struct plat_smp_ops ip27_smp_ops;
 extern unsigned long node_getfirstfree(nasid_t nasid);
@@ -17,4 +18,5 @@ extern void per_cpu_init(void);
 extern void replicate_kernel_text(void);
 extern void setup_replication_mask(void);
 
+
 #endif /* __IP27_COMMON_H */
diff --git a/arch/mips/sgi-ip27/ip27-hubio.c b/arch/mips/sgi-ip27/ip27-hubio.c
deleted file mode 100644
index 8352eb6403b4..000000000000
--- a/arch/mips/sgi-ip27/ip27-hubio.c
+++ /dev/null
@@ -1,185 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 1992-1997, 2000-2003 Silicon Graphics, Inc.
- * Copyright (C) 2004 Christoph Hellwig.
- *
- * Support functions for the HUB ASIC - mostly PIO mapping related.
- */
-
-#include <linux/bitops.h>
-#include <linux/string.h>
-#include <linux/mmzone.h>
-#include <asm/sn/addrs.h>
-#include <asm/sn/arch.h>
-#include <asm/sn/agent.h>
-#include <asm/sn/io.h>
-#include <asm/xtalk/xtalk.h>
-
-
-static int force_fire_and_forget = 1;
-
-/**
- * hub_pio_map	-  establish a HUB PIO mapping
- *
- * @hub:	hub to perform PIO mapping on
- * @widget:	widget ID to perform PIO mapping for
- * @xtalk_addr: xtalk_address that needs to be mapped
- * @size:	size of the PIO mapping
- *
- **/
-unsigned long hub_pio_map(nasid_t nasid, xwidgetnum_t widget,
-			  unsigned long xtalk_addr, size_t size)
-{
-	unsigned i;
-
-	/* use small-window mapping if possible */
-	if ((xtalk_addr % SWIN_SIZE) + size <= SWIN_SIZE)
-		return NODE_SWIN_BASE(nasid, widget) + (xtalk_addr % SWIN_SIZE);
-
-	if ((xtalk_addr % BWIN_SIZE) + size > BWIN_SIZE) {
-		printk(KERN_WARNING "PIO mapping at hub %d widget %d addr 0x%lx"
-				" too big (%ld)\n",
-				nasid, widget, xtalk_addr, size);
-		return 0;
-	}
-
-	xtalk_addr &= ~(BWIN_SIZE-1);
-	for (i = 0; i < HUB_NUM_BIG_WINDOW; i++) {
-		if (test_and_set_bit(i, hub_data(nasid)->h_bigwin_used))
-			continue;
-
-		/*
-		 * The code below does a PIO write to setup an ITTE entry.
-		 *
-		 * We need to prevent other CPUs from seeing our updated
-		 * memory shadow of the ITTE (in the piomap) until the ITTE
-		 * entry is actually set up; otherwise, another CPU might
-		 * attempt a PIO prematurely.
-		 *
-		 * Also, the only way we can know that an entry has been
-		 * received  by the hub and can be used by future PIO reads/
-		 * writes is by reading back the ITTE entry after writing it.
-		 *
-		 * For these two reasons, we PIO read back the ITTE entry
-		 * after we write it.
-		 */
-		IIO_ITTE_PUT(nasid, i, HUB_PIO_MAP_TO_MEM, widget, xtalk_addr);
-		__raw_readq(IIO_ITTE_GET(nasid, i));
-
-		return NODE_BWIN_BASE(nasid, widget) + (xtalk_addr % BWIN_SIZE);
-	}
-
-	printk(KERN_WARNING "unable to establish PIO mapping for at"
-			" hub %d widget %d addr 0x%lx\n",
-			nasid, widget, xtalk_addr);
-	return 0;
-}
-
-
-/*
- * hub_setup_prb(nasid, prbnum, credits, conveyor)
- *
- *	Put a PRB into fire-and-forget mode if conveyor isn't set.  Otherwise,
- *	put it into conveyor belt mode with the specified number of credits.
- */
-static void hub_setup_prb(nasid_t nasid, int prbnum, int credits)
-{
-	union iprb_u prb;
-	int prb_offset;
-
-	/*
-	 * Get the current register value.
-	 */
-	prb_offset = IIO_IOPRB(prbnum);
-	prb.iprb_regval = REMOTE_HUB_L(nasid, prb_offset);
-
-	/*
-	 * Clear out some fields.
-	 */
-	prb.iprb_ovflow = 1;
-	prb.iprb_bnakctr = 0;
-	prb.iprb_anakctr = 0;
-
-	/*
-	 * Enable or disable fire-and-forget mode.
-	 */
-	prb.iprb_ff = force_fire_and_forget ? 1 : 0;
-
-	/*
-	 * Set the appropriate number of PIO credits for the widget.
-	 */
-	prb.iprb_xtalkctr = credits;
-
-	/*
-	 * Store the new value to the register.
-	 */
-	REMOTE_HUB_S(nasid, prb_offset, prb.iprb_regval);
-}
-
-/**
- * hub_set_piomode  -  set pio mode for a given hub
- *
- * @nasid:	physical node ID for the hub in question
- *
- * Put the hub into either "PIO conveyor belt" mode or "fire-and-forget" mode.
- * To do this, we have to make absolutely sure that no PIOs are in progress
- * so we turn off access to all widgets for the duration of the function.
- *
- * XXX - This code should really check what kind of widget we're talking
- * to.	Bridges can only handle three requests, but XG will do more.
- * How many can crossbow handle to widget 0?  We're assuming 1.
- *
- * XXX - There is a bug in the crossbow that link reset PIOs do not
- * return write responses.  The easiest solution to this problem is to
- * leave widget 0 (xbow) in fire-and-forget mode at all times.	This
- * only affects pio's to xbow registers, which should be rare.
- **/
-static void hub_set_piomode(nasid_t nasid)
-{
-	u64 ii_iowa;
-	union hubii_wcr_u ii_wcr;
-	unsigned i;
-
-	ii_iowa = REMOTE_HUB_L(nasid, IIO_OUTWIDGET_ACCESS);
-	REMOTE_HUB_S(nasid, IIO_OUTWIDGET_ACCESS, 0);
-
-	ii_wcr.wcr_reg_value = REMOTE_HUB_L(nasid, IIO_WCR);
-
-	if (ii_wcr.iwcr_dir_con) {
-		/*
-		 * Assume a bridge here.
-		 */
-		hub_setup_prb(nasid, 0, 3);
-	} else {
-		/*
-		 * Assume a crossbow here.
-		 */
-		hub_setup_prb(nasid, 0, 1);
-	}
-
-	/*
-	 * XXX - Here's where we should take the widget type into
-	 * when account assigning credits.
-	 */
-	for (i = HUB_WIDGET_ID_MIN; i <= HUB_WIDGET_ID_MAX; i++)
-		hub_setup_prb(nasid, i, 3);
-
-	REMOTE_HUB_S(nasid, IIO_OUTWIDGET_ACCESS, ii_iowa);
-}
-
-/*
- * hub_pio_init	 -  PIO-related hub initialization
- *
- * @hub:	hubinfo structure for our hub
- */
-void hub_pio_init(nasid_t nasid)
-{
-	unsigned i;
-
-	/* initialize big window piomaps for this hub */
-	bitmap_zero(hub_data(nasid)->h_bigwin_used, HUB_NUM_BIG_WINDOW);
-	for (i = 0; i < HUB_NUM_BIG_WINDOW; i++)
-		IIO_ITTE_DISABLE(nasid, i);
-
-	hub_set_piomode(nasid);
-}
diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c
index a0dd3bd2b81b..8f5299b269e7 100644
--- a/arch/mips/sgi-ip27/ip27-irq.c
+++ b/arch/mips/sgi-ip27/ip27-irq.c
@@ -23,6 +23,8 @@
 #include <asm/sn/intr.h>
 #include <asm/sn/irq_alloc.h>
 
+#include "ip27-common.h"
+
 struct hub_irq_data {
 	u64	*irq_mask[2];
 	cpuid_t	cpu;
diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c
index f79c48393716..b8ca94cfb4fe 100644
--- a/arch/mips/sgi-ip27/ip27-memory.c
+++ b/arch/mips/sgi-ip27/ip27-memory.c
@@ -23,6 +23,7 @@
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <asm/sections.h>
+#include <asm/sgialib.h>
 
 #include <asm/sn/arch.h>
 #include <asm/sn/agent.h>
diff --git a/arch/mips/sgi-ip27/ip27-nmi.c b/arch/mips/sgi-ip27/ip27-nmi.c
index 84889b57d5ff..fc2816398d0c 100644
--- a/arch/mips/sgi-ip27/ip27-nmi.c
+++ b/arch/mips/sgi-ip27/ip27-nmi.c
@@ -11,6 +11,8 @@
 #include <asm/sn/arch.h>
 #include <asm/sn/agent.h>
 
+#include "ip27-common.h"
+
 #if 0
 #define NODE_NUM_CPUS(n)	CNODE_NUM_CPUS(n)
 #else
@@ -23,16 +25,7 @@
 typedef unsigned long machreg_t;
 
 static arch_spinlock_t nmi_lock = __ARCH_SPIN_LOCK_UNLOCKED;
-
-/*
- * Let's see what else we need to do here. Set up sp, gp?
- */
-void nmi_dump(void)
-{
-	void cont_nmi_dump(void);
-
-	cont_nmi_dump();
-}
+static void nmi_dump(void);
 
 void install_cpu_nmi_handler(int slice)
 {
@@ -53,7 +46,7 @@ void install_cpu_nmi_handler(int slice)
  * into the eframe format for the node under consideration.
  */
 
-void nmi_cpu_eframe_save(nasid_t nasid, int slice)
+static void nmi_cpu_eframe_save(nasid_t nasid, int slice)
 {
 	struct reg_struct *nr;
 	int		i;
@@ -129,7 +122,7 @@ void nmi_cpu_eframe_save(nasid_t nasid, int slice)
 	pr_emerg("\n");
 }
 
-void nmi_dump_hub_irq(nasid_t nasid, int slice)
+static void nmi_dump_hub_irq(nasid_t nasid, int slice)
 {
 	u64 mask0, mask1, pend0, pend1;
 
@@ -153,7 +146,7 @@ void nmi_dump_hub_irq(nasid_t nasid, int slice)
  * Copy the cpu registers which have been saved in the IP27prom format
  * into the eframe format for the node under consideration.
  */
-void nmi_node_eframe_save(nasid_t nasid)
+static void nmi_node_eframe_save(nasid_t nasid)
 {
 	int slice;
 
@@ -170,8 +163,7 @@ void nmi_node_eframe_save(nasid_t nasid)
 /*
  * Save the nmi cpu registers for all cpus in the system.
  */
-void
-nmi_eframes_save(void)
+static void nmi_eframes_save(void)
 {
 	nasid_t nasid;
 
@@ -179,8 +171,7 @@ nmi_eframes_save(void)
 		nmi_node_eframe_save(nasid);
 }
 
-void
-cont_nmi_dump(void)
+static void nmi_dump(void)
 {
 #ifndef REAL_NMI_SIGNAL
 	static atomic_t nmied_cpus = ATOMIC_INIT(0);
diff --git a/arch/mips/sgi-ip30/ip30-console.c b/arch/mips/sgi-ip30/ip30-console.c
index b91f8c4fdc78..7c6dcf6e73f7 100644
--- a/arch/mips/sgi-ip30/ip30-console.c
+++ b/arch/mips/sgi-ip30/ip30-console.c
@@ -3,6 +3,7 @@
 #include <linux/io.h>
 
 #include <asm/sn/ioc3.h>
+#include <asm/setup.h>
 
 static inline struct ioc3_uartregs *console_uart(void)
 {
diff --git a/arch/mips/sgi-ip30/ip30-setup.c b/arch/mips/sgi-ip30/ip30-setup.c
index 75a34684e704..e8547636a748 100644
--- a/arch/mips/sgi-ip30/ip30-setup.c
+++ b/arch/mips/sgi-ip30/ip30-setup.c
@@ -14,6 +14,7 @@
 #include <linux/percpu.h>
 #include <linux/memblock.h>
 
+#include <asm/bootinfo.h>
 #include <asm/smp-ops.h>
 #include <asm/sgialib.h>
 #include <asm/time.h>
diff --git a/arch/mips/sgi-ip32/crime.c b/arch/mips/sgi-ip32/crime.c
index a8e0c776ca6c..b8a0e4cfa9ce 100644
--- a/arch/mips/sgi-ip32/crime.c
+++ b/arch/mips/sgi-ip32/crime.c
@@ -18,6 +18,8 @@
 #include <asm/ip32/crime.h>
 #include <asm/ip32/mace.h>
 
+#include "ip32-common.h"
+
 struct sgi_crime __iomem *crime;
 struct sgi_mace __iomem *mace;
 
@@ -39,7 +41,7 @@ void __init crime_init(void)
 	       id, rev, field, (unsigned long) CRIME_BASE);
 }
 
-irqreturn_t crime_memerr_intr(unsigned int irq, void *dev_id)
+irqreturn_t crime_memerr_intr(int irq, void *dev_id)
 {
 	unsigned long stat, addr;
 	int fatal = 0;
@@ -90,7 +92,7 @@ irqreturn_t crime_memerr_intr(unsigned int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-irqreturn_t crime_cpuerr_intr(unsigned int irq, void *dev_id)
+irqreturn_t crime_cpuerr_intr(int irq, void *dev_id)
 {
 	unsigned long stat = crime->cpu_error_stat & CRIME_CPU_ERROR_MASK;
 	unsigned long addr = crime->cpu_error_addr & CRIME_CPU_ERROR_ADDR_MASK;
diff --git a/arch/mips/sgi-ip32/ip32-berr.c b/arch/mips/sgi-ip32/ip32-berr.c
index 478b63b4c808..7cbc27941f92 100644
--- a/arch/mips/sgi-ip32/ip32-berr.c
+++ b/arch/mips/sgi-ip32/ip32-berr.c
@@ -18,6 +18,8 @@
 #include <asm/ptrace.h>
 #include <asm/tlbdebug.h>
 
+#include "ip32-common.h"
+
 static int ip32_be_handler(struct pt_regs *regs, int is_fixup)
 {
 	int data = regs->cp0_cause & 4;
diff --git a/arch/mips/sgi-ip32/ip32-common.h b/arch/mips/sgi-ip32/ip32-common.h
new file mode 100644
index 000000000000..cfc0225b1419
--- /dev/null
+++ b/arch/mips/sgi-ip32/ip32-common.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __IP32_COMMON_H
+#define __IP32_COMMON_H
+
+#include <linux/init.h>
+#include <linux/interrupt.h>
+
+void __init crime_init(void);
+irqreturn_t crime_memerr_intr(int irq, void *dev_id);
+irqreturn_t crime_cpuerr_intr(int irq, void *dev_id);
+void __init ip32_be_init(void);
+void ip32_prepare_poweroff(void);
+
+#endif /* __IP32_COMMON_H */
diff --git a/arch/mips/sgi-ip32/ip32-irq.c b/arch/mips/sgi-ip32/ip32-irq.c
index e21ea1de05e3..29d04468a06b 100644
--- a/arch/mips/sgi-ip32/ip32-irq.c
+++ b/arch/mips/sgi-ip32/ip32-irq.c
@@ -28,6 +28,8 @@
 #include <asm/ip32/mace.h>
 #include <asm/ip32/ip32_ints.h>
 
+#include "ip32-common.h"
+
 /* issue a PIO read to make sure no PIO writes are pending */
 static inline void flush_crime_bus(void)
 {
@@ -107,10 +109,6 @@ static inline void flush_mace_bus(void)
  * is quite different anyway.
  */
 
-/* Some initial interrupts to set up */
-extern irqreturn_t crime_memerr_intr(int irq, void *dev_id);
-extern irqreturn_t crime_cpuerr_intr(int irq, void *dev_id);
-
 /*
  * This is for pure CRIME interrupts - ie not MACE.  The advantage?
  * We get to split the register in half and do faster lookups.
diff --git a/arch/mips/sgi-ip32/ip32-memory.c b/arch/mips/sgi-ip32/ip32-memory.c
index 3fc8d0a0bdfa..5fee33744f67 100644
--- a/arch/mips/sgi-ip32/ip32-memory.c
+++ b/arch/mips/sgi-ip32/ip32-memory.c
@@ -15,6 +15,7 @@
 #include <asm/ip32/crime.h>
 #include <asm/bootinfo.h>
 #include <asm/page.h>
+#include <asm/sgialib.h>
 
 extern void crime_init(void);
 
diff --git a/arch/mips/sgi-ip32/ip32-reset.c b/arch/mips/sgi-ip32/ip32-reset.c
index 18d1c115cd53..6bdc1421cda4 100644
--- a/arch/mips/sgi-ip32/ip32-reset.c
+++ b/arch/mips/sgi-ip32/ip32-reset.c
@@ -29,6 +29,8 @@
 #include <asm/ip32/crime.h>
 #include <asm/ip32/ip32_ints.h>
 
+#include "ip32-common.h"
+
 #define POWERDOWN_TIMEOUT	120
 /*
  * Blink frequency during reboot grace period and when panicked.
diff --git a/arch/mips/sgi-ip32/ip32-setup.c b/arch/mips/sgi-ip32/ip32-setup.c
index 8019dae1721a..aeb0805aae57 100644
--- a/arch/mips/sgi-ip32/ip32-setup.c
+++ b/arch/mips/sgi-ip32/ip32-setup.c
@@ -26,8 +26,7 @@
 #include <asm/ip32/mace.h>
 #include <asm/ip32/ip32_ints.h>
 
-extern void ip32_be_init(void);
-extern void crime_init(void);
+#include "ip32-common.h"
 
 #ifdef CONFIG_SGI_O2MACE_ETH
 /*
diff --git a/arch/mips/txx9/generic/pci.c b/arch/mips/txx9/generic/pci.c
index 5ae30b78d38d..d9249f5a632e 100644
--- a/arch/mips/txx9/generic/pci.c
+++ b/arch/mips/txx9/generic/pci.c
@@ -348,7 +348,7 @@ static void final_fixup(struct pci_dev *dev)
 	unsigned char bist;
 	int ret;
 
-	/* Do build-in self test */
+	/* Do built-in self test */
 	ret = pci_read_config_byte(dev, PCI_BIST, &bist);
 	if ((ret != PCIBIOS_SUCCESSFUL) || !(bist & PCI_BIST_CAPABLE))
 		return;
diff --git a/arch/nios2/include/asm/cacheflush.h b/arch/nios2/include/asm/cacheflush.h
index 348cea097792..81484a776b33 100644
--- a/arch/nios2/include/asm/cacheflush.h
+++ b/arch/nios2/include/asm/cacheflush.h
@@ -38,6 +38,7 @@ void flush_icache_pages(struct vm_area_struct *vma, struct page *page,
 #define flush_icache_pages flush_icache_pages
 
 #define flush_cache_vmap(start, end)		flush_dcache_range(start, end)
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		flush_dcache_range(start, end)
 
 extern void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index d14ccc948a29..5c845e8d59d9 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -25,7 +25,6 @@ config PARISC
 	select RTC_DRV_GENERIC
 	select INIT_ALL_POSSIBLE
 	select BUG
-	select BUILDTIME_TABLE_SORT
 	select HAVE_KERNEL_UNCOMPRESSED
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 920db57b6b4c..316f84f1d15c 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -50,12 +50,12 @@ export CROSS32CC
 
 # Set default cross compiler for kernel build
 ifdef cross_compiling
-	ifeq ($(CROSS_COMPILE),)
+    ifeq ($(CROSS_COMPILE),)
 		CC_SUFFIXES = linux linux-gnu unknown-linux-gnu suse-linux
 		CROSS_COMPILE := $(call cc-cross-prefix, \
 			$(foreach a,$(CC_ARCHES), \
 			$(foreach s,$(CC_SUFFIXES),$(a)-$(s)-)))
-	endif
+    endif
 endif
 
 ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h
index 74d17d7e759d..5937d5edaba1 100644
--- a/arch/parisc/include/asm/assembly.h
+++ b/arch/parisc/include/asm/assembly.h
@@ -576,6 +576,7 @@
 	.section __ex_table,"aw"			!	\
 	.align 4					!	\
 	.word (fault_addr - .), (except_addr - .)	!	\
+	or %r0,%r0,%r0					!	\
 	.previous
 
 
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index b4006f2a9705..ba4c05bc24d6 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -41,6 +41,7 @@ void flush_kernel_vmap_range(void *vaddr, int size);
 void invalidate_kernel_vmap_range(void *vaddr, int size);
 
 #define flush_cache_vmap(start, end)		flush_cache_all()
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		flush_cache_all()
 
 void flush_dcache_folio(struct folio *folio);
diff --git a/arch/parisc/include/asm/extable.h b/arch/parisc/include/asm/extable.h
new file mode 100644
index 000000000000..4ea23e3d79dc
--- /dev/null
+++ b/arch/parisc/include/asm/extable.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PARISC_EXTABLE_H
+#define __PARISC_EXTABLE_H
+
+#include <asm/ptrace.h>
+#include <linux/compiler.h>
+
+/*
+ * The exception table consists of three addresses:
+ *
+ * - A relative address to the instruction that is allowed to fault.
+ * - A relative address at which the program should continue (fixup routine)
+ * - An asm statement which specifies which CPU register will
+ *   receive -EFAULT when an exception happens if the lowest bit in
+ *   the fixup address is set.
+ *
+ * Note: The register specified in the err_opcode instruction will be
+ * modified at runtime if a fault happens. Register %r0 will be ignored.
+ *
+ * Since relative addresses are used, 32bit values are sufficient even on
+ * 64bit kernel.
+ */
+
+struct pt_regs;
+int fixup_exception(struct pt_regs *regs);
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+struct exception_table_entry {
+	int insn;	/* relative address of insn that is allowed to fault. */
+	int fixup;	/* relative address of fixup routine */
+	int err_opcode; /* sample opcode with register which holds error code */
+};
+
+#define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr, opcode )\
+	".section __ex_table,\"aw\"\n"			   \
+	".align 4\n"					   \
+	".word (" #fault_addr " - .), (" #except_addr " - .)\n" \
+	opcode "\n"					   \
+	".previous\n"
+
+/*
+ * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() creates a special exception table entry
+ * (with lowest bit set) for which the fault handler in fixup_exception() will
+ * load -EFAULT on fault into the register specified by the err_opcode instruction,
+ * and zeroes the target register in case of a read fault in get_user().
+ */
+#define ASM_EXCEPTIONTABLE_VAR(__err_var)		\
+	int __err_var = 0
+#define ASM_EXCEPTIONTABLE_ENTRY_EFAULT( fault_addr, except_addr, register )\
+	ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1, "or %%r0,%%r0," register)
+
+static inline void swap_ex_entry_fixup(struct exception_table_entry *a,
+				       struct exception_table_entry *b,
+				       struct exception_table_entry tmp,
+				       int delta)
+{
+	a->fixup = b->fixup + delta;
+	b->fixup = tmp.fixup - delta;
+	a->err_opcode = b->err_opcode;
+	b->err_opcode = tmp.err_opcode;
+}
+#define swap_ex_entry_fixup swap_ex_entry_fixup
+
+#endif
diff --git a/arch/parisc/include/asm/jump_label.h b/arch/parisc/include/asm/jump_label.h
index 94428798b6aa..317ebc5edc9f 100644
--- a/arch/parisc/include/asm/jump_label.h
+++ b/arch/parisc/include/asm/jump_label.h
@@ -12,7 +12,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".align %1\n\t"
@@ -29,7 +29,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "b,n %l[l_yes]\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".align %1\n\t"
diff --git a/arch/parisc/include/asm/kprobes.h b/arch/parisc/include/asm/kprobes.h
index 0a175ac87698..0f42f5c8e3b6 100644
--- a/arch/parisc/include/asm/kprobes.h
+++ b/arch/parisc/include/asm/kprobes.h
@@ -10,9 +10,10 @@
 #ifndef _PARISC_KPROBES_H
 #define _PARISC_KPROBES_H
 
+#include <asm-generic/kprobes.h>
+
 #ifdef CONFIG_KPROBES
 
-#include <asm-generic/kprobes.h>
 #include <linux/types.h>
 #include <linux/ptrace.h>
 #include <linux/notifier.h>
diff --git a/arch/parisc/include/asm/special_insns.h b/arch/parisc/include/asm/special_insns.h
index c822bd0c0e3c..51f40eaf7780 100644
--- a/arch/parisc/include/asm/special_insns.h
+++ b/arch/parisc/include/asm/special_insns.h
@@ -8,7 +8,8 @@
 		"copy %%r0,%0\n"			\
 		"8:\tlpa %%r0(%1),%0\n"			\
 		"9:\n"					\
-		ASM_EXCEPTIONTABLE_ENTRY(8b, 9b)	\
+		ASM_EXCEPTIONTABLE_ENTRY(8b, 9b,	\
+				"or %%r0,%%r0,%%r0")	\
 		: "=&r" (pa)				\
 		: "r" (va)				\
 		: "memory"				\
@@ -22,7 +23,8 @@
 		"copy %%r0,%0\n"			\
 		"8:\tlpa %%r0(%%sr3,%1),%0\n"		\
 		"9:\n"					\
-		ASM_EXCEPTIONTABLE_ENTRY(8b, 9b)	\
+		ASM_EXCEPTIONTABLE_ENTRY(8b, 9b,	\
+				"or %%r0,%%r0,%%r0")	\
 		: "=&r" (pa)				\
 		: "r" (va)				\
 		: "memory"				\
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index 4165079898d9..88d0ae5769dd 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -7,6 +7,7 @@
  */
 #include <asm/page.h>
 #include <asm/cache.h>
+#include <asm/extable.h>
 
 #include <linux/bug.h>
 #include <linux/string.h>
@@ -26,37 +27,6 @@
 #define STD_USER(sr, x, ptr)	__put_user_asm(sr, "std", x, ptr)
 #endif
 
-/*
- * The exception table contains two values: the first is the relative offset to
- * the address of the instruction that is allowed to fault, and the second is
- * the relative offset to the address of the fixup routine. Since relative
- * addresses are used, 32bit values are sufficient even on 64bit kernel.
- */
-
-#define ARCH_HAS_RELATIVE_EXTABLE
-struct exception_table_entry {
-	int insn;	/* relative address of insn that is allowed to fault. */
-	int fixup;	/* relative address of fixup routine */
-};
-
-#define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr )\
-	".section __ex_table,\"aw\"\n"			   \
-	".align 4\n"					   \
-	".word (" #fault_addr " - .), (" #except_addr " - .)\n\t" \
-	".previous\n"
-
-/*
- * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() creates a special exception table entry
- * (with lowest bit set) for which the fault handler in fixup_exception() will
- * load -EFAULT into %r29 for a read or write fault, and zeroes the target
- * register in case of a read fault in get_user().
- */
-#define ASM_EXCEPTIONTABLE_REG	29
-#define ASM_EXCEPTIONTABLE_VAR(__variable)		\
-	register long __variable __asm__ ("r29") = 0
-#define ASM_EXCEPTIONTABLE_ENTRY_EFAULT( fault_addr, except_addr )\
-	ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1)
-
 #define __get_user_internal(sr, val, ptr)		\
 ({							\
 	ASM_EXCEPTIONTABLE_VAR(__gu_err);		\
@@ -83,7 +53,7 @@ struct exception_table_entry {
 							\
 	__asm__("1: " ldx " 0(%%sr%2,%3),%0\n"		\
 		"9:\n"					\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)	\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%1")	\
 		: "=r"(__gu_val), "+r"(__gu_err)        \
 		: "i"(sr), "r"(ptr));			\
 							\
@@ -115,8 +85,8 @@ struct exception_table_entry {
 		"1: ldw 0(%%sr%2,%3),%0\n"		\
 		"2: ldw 4(%%sr%2,%3),%R0\n"		\
 		"9:\n"					\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)	\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b)	\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%1")	\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b, "%1")	\
 		: "=&r"(__gu_tmp.l), "+r"(__gu_err)	\
 		: "i"(sr), "r"(ptr));			\
 							\
@@ -174,7 +144,7 @@ struct exception_table_entry {
 	__asm__ __volatile__ (					\
 		"1: " stx " %1,0(%%sr%2,%3)\n"			\
 		"9:\n"						\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)		\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%0")	\
 		: "+r"(__pu_err)				\
 		: "r"(x), "i"(sr), "r"(ptr))
 
@@ -186,15 +156,14 @@ struct exception_table_entry {
 		"1: stw %1,0(%%sr%2,%3)\n"			\
 		"2: stw %R1,4(%%sr%2,%3)\n"			\
 		"9:\n"						\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)		\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b)		\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%0")	\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b, "%0")	\
 		: "+r"(__pu_err)				\
 		: "r"(__val), "i"(sr), "r"(ptr));		\
 } while (0)
 
 #endif /* !defined(CONFIG_64BIT) */
 
-
 /*
  * Complex access routines -- external declarations
  */
@@ -216,7 +185,4 @@ unsigned long __must_check raw_copy_from_user(void *dst, const void __user *src,
 #define INLINE_COPY_TO_USER
 #define INLINE_COPY_FROM_USER
 
-struct pt_regs;
-int fixup_exception(struct pt_regs *regs);
-
 #endif /* __PARISC_UACCESS_H */
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 268d90a9325b..422f3e1e6d9c 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -58,7 +58,7 @@ int pa_serialize_tlb_flushes __ro_after_init;
 
 struct pdc_cache_info cache_info __ro_after_init;
 #ifndef CONFIG_PA20
-struct pdc_btlb_info btlb_info __ro_after_init;
+struct pdc_btlb_info btlb_info;
 #endif
 
 DEFINE_STATIC_KEY_TRUE(parisc_has_cache);
@@ -264,6 +264,10 @@ parisc_cache_init(void)
 	icache_stride = CAFL_STRIDE(cache_info.ic_conf);
 #undef CAFL_STRIDE
 
+	/* stride needs to be non-zero, otherwise cache flushes will not work */
+	WARN_ON(cache_info.dc_size && dcache_stride == 0);
+	WARN_ON(cache_info.ic_size && icache_stride == 0);
+
 	if ((boot_cpu_data.pdc.capabilities & PDC_MODEL_NVA_MASK) ==
 						PDC_MODEL_NVA_UNSUPPORTED) {
 		printk(KERN_WARNING "parisc_cache_init: Only equivalent aliasing supported!\n");
@@ -850,7 +854,7 @@ SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes,
 #endif
 			"   fic,m	%3(%4,%0)\n"
 			"2: sync\n"
-			ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b)
+			ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b, "%1")
 			: "+r" (start), "+r" (error)
 			: "r" (end), "r" (dcache_stride), "i" (SR_USER));
 	}
@@ -865,7 +869,7 @@ SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes,
 #endif
 			"   fdc,m	%3(%4,%0)\n"
 			"2: sync\n"
-			ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b)
+			ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b, "%1")
 			: "+r" (start), "+r" (error)
 			: "r" (end), "r" (icache_stride), "i" (SR_USER));
 	}
diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index 25f9b9e9d6df..c7ff339732ba 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -742,7 +742,7 @@ parse_tree_node(struct device *parent, int index, struct hardware_path *modpath)
 	};
 
 	if (device_for_each_child(parent, &recurse_data, descend_children))
-		{ /* nothing */ };
+		{ /* nothing */ }
 
 	return d.dev;
 }
@@ -1004,6 +1004,9 @@ static __init int qemu_print_iodc_data(struct device *lin_dev, void *data)
 
 	pr_info("\n");
 
+	/* Prevent hung task messages when printing on serial console */
+	cond_resched();
+
 	pr_info("#define HPA_%08lx_DESCRIPTION \"%s\"\n",
 		hpa, parisc_hardware_description(&dev->id));
 
diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c
index 904ca3b9e7a7..c69f6d5946e9 100644
--- a/arch/parisc/kernel/firmware.c
+++ b/arch/parisc/kernel/firmware.c
@@ -123,10 +123,10 @@ static unsigned long f_extend(unsigned long address)
 #ifdef CONFIG_64BIT
 	if(unlikely(parisc_narrow_firmware)) {
 		if((address & 0xff000000) == 0xf0000000)
-			return 0xf0f0f0f000000000UL | (u32)address;
+			return (0xfffffff0UL << 32) | (u32)address;
 
 		if((address & 0xf0000000) == 0xf0000000)
-			return 0xffffffff00000000UL | (u32)address;
+			return (0xffffffffUL << 32) | (u32)address;
 	}
 #endif
 	return address;
diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c
index d1defb9ede70..621a4b386ae4 100644
--- a/arch/parisc/kernel/ftrace.c
+++ b/arch/parisc/kernel/ftrace.c
@@ -78,7 +78,7 @@ asmlinkage void notrace __hot ftrace_function_trampoline(unsigned long parent,
 #endif
 }
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_FUNCTION_GRAPH_TRACER)
 int ftrace_enable_ftrace_graph_caller(void)
 {
 	static_key_enable(&ftrace_graph_enable.key);
diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c
index e95a977ba5f3..bf73562706b2 100644
--- a/arch/parisc/kernel/processor.c
+++ b/arch/parisc/kernel/processor.c
@@ -172,7 +172,6 @@ static int __init processor_probe(struct parisc_device *dev)
 	p->cpu_num = cpu_info.cpu_num;
 	p->cpu_loc = cpu_info.cpu_loc;
 
-	set_cpu_possible(cpuid, true);
 	store_cpu_topology(cpuid);
 
 #ifdef CONFIG_SMP
@@ -474,13 +473,6 @@ static struct parisc_driver cpu_driver __refdata = {
  */
 void __init processor_init(void)
 {
-	unsigned int cpu;
-
 	reset_cpu_topology();
-
-	/* reset possible mask. We will mark those which are possible. */
-	for_each_possible_cpu(cpu)
-		set_cpu_possible(cpu, false);
-
 	register_parisc_driver(&cpu_driver);
 }
diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c
index ce25acfe4889..c520e551a165 100644
--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@@ -120,8 +120,8 @@ static int emulate_ldh(struct pt_regs *regs, int toreg)
 "2:	ldbs	1(%%sr1,%3), %0\n"
 "	depw	%2, 23, 24, %0\n"
 "3:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1")
 	: "+r" (val), "+r" (ret), "=&r" (temp1)
 	: "r" (saddr), "r" (regs->isr) );
 
@@ -152,8 +152,8 @@ static int emulate_ldw(struct pt_regs *regs, int toreg, int flop)
 "	mtctl	%2,11\n"
 "	vshd	%0,%3,%0\n"
 "3:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1")
 	: "+r" (val), "+r" (ret), "=&r" (temp1), "=&r" (temp2)
 	: "r" (saddr), "r" (regs->isr) );
 
@@ -189,8 +189,8 @@ static int emulate_ldd(struct pt_regs *regs, int toreg, int flop)
 "	mtsar	%%r19\n"
 "	shrpd	%0,%%r20,%%sar,%0\n"
 "3:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1")
 	: "=r" (val), "+r" (ret)
 	: "0" (val), "r" (saddr), "r" (regs->isr)
 	: "r19", "r20" );
@@ -209,9 +209,9 @@ static int emulate_ldd(struct pt_regs *regs, int toreg, int flop)
 "	vshd	%0,%R0,%0\n"
 "	vshd	%R0,%4,%R0\n"
 "4:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 4b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 4b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 4b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 4b, "%1")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 4b, "%1")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 4b, "%1")
 	: "+r" (val), "+r" (ret), "+r" (saddr), "=&r" (shift), "=&r" (temp1)
 	: "r" (regs->isr) );
     }
@@ -244,8 +244,8 @@ static int emulate_sth(struct pt_regs *regs, int frreg)
 "1:	stb %1, 0(%%sr1, %3)\n"
 "2:	stb %2, 1(%%sr1, %3)\n"
 "3:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%0")
 	: "+r" (ret), "=&r" (temp1)
 	: "r" (val), "r" (regs->ior), "r" (regs->isr) );
 
@@ -285,8 +285,8 @@ static int emulate_stw(struct pt_regs *regs, int frreg, int flop)
 "	stw	%%r20,0(%%sr1,%2)\n"
 "	stw	%%r21,4(%%sr1,%2)\n"
 "3:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%0")
 	: "+r" (ret)
 	: "r" (val), "r" (regs->ior), "r" (regs->isr)
 	: "r19", "r20", "r21", "r22", "r1" );
@@ -329,10 +329,10 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop)
 "3:	std	%%r20,0(%%sr1,%2)\n"
 "4:	std	%%r21,8(%%sr1,%2)\n"
 "5:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 5b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 5b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 5b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 5b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 5b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 5b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 5b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 5b, "%0")
 	: "+r" (ret)
 	: "r" (val), "r" (regs->ior), "r" (regs->isr)
 	: "r19", "r20", "r21", "r22", "r1" );
@@ -357,11 +357,11 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop)
 "4:	stw	%%r1,4(%%sr1,%2)\n"
 "5:	stw	%R1,8(%%sr1,%2)\n"
 "6:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 6b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 6b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 6b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 6b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(5b, 6b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 6b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 6b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 6b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 6b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(5b, 6b, "%0")
 	: "+r" (ret)
 	: "r" (val), "r" (regs->ior), "r" (regs->isr)
 	: "r19", "r20", "r21", "r1" );
diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c
index 27ae40a443b8..f7e0fee5ee55 100644
--- a/arch/parisc/kernel/unwind.c
+++ b/arch/parisc/kernel/unwind.c
@@ -228,10 +228,8 @@ static int unwind_special(struct unwind_frame_info *info, unsigned long pc, int
 #ifdef CONFIG_IRQSTACKS
 	extern void * const _call_on_stack;
 #endif /* CONFIG_IRQSTACKS */
-	void *ptr;
 
-	ptr = dereference_kernel_function_descriptor(&handle_interruption);
-	if (pc_is_kernel_fn(pc, ptr)) {
+	if (pc_is_kernel_fn(pc, handle_interruption)) {
 		struct pt_regs *regs = (struct pt_regs *)(info->sp - frame_size - PT_SZ_ALGN);
 		dbg("Unwinding through handle_interruption()\n");
 		info->prev_sp = regs->gr[30];
@@ -239,13 +237,13 @@ static int unwind_special(struct unwind_frame_info *info, unsigned long pc, int
 		return 1;
 	}
 
-	if (pc_is_kernel_fn(pc, ret_from_kernel_thread) ||
-	    pc_is_kernel_fn(pc, syscall_exit)) {
+	if (pc == (unsigned long)&ret_from_kernel_thread ||
+	    pc == (unsigned long)&syscall_exit) {
 		info->prev_sp = info->prev_ip = 0;
 		return 1;
 	}
 
-	if (pc_is_kernel_fn(pc, intr_return)) {
+	if (pc == (unsigned long)&intr_return) {
 		struct pt_regs *regs;
 
 		dbg("Found intr_return()\n");
@@ -257,14 +255,14 @@ static int unwind_special(struct unwind_frame_info *info, unsigned long pc, int
 	}
 
 	if (pc_is_kernel_fn(pc, _switch_to) ||
-	    pc_is_kernel_fn(pc, _switch_to_ret)) {
+	    pc == (unsigned long)&_switch_to_ret) {
 		info->prev_sp = info->sp - CALLEE_SAVE_FRAME_SIZE;
 		info->prev_ip = *(unsigned long *)(info->prev_sp - RP_OFFSET);
 		return 1;
 	}
 
 #ifdef CONFIG_IRQSTACKS
-	if (pc_is_kernel_fn(pc, _call_on_stack)) {
+	if (pc == (unsigned long)&_call_on_stack) {
 		info->prev_sp = *(unsigned long *)(info->sp - FRAME_SIZE - REG_SZ);
 		info->prev_ip = *(unsigned long *)(info->sp - FRAME_SIZE - RP_OFFSET);
 		return 1;
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index 548051b0b4af..b445e47903cf 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -127,7 +127,7 @@ SECTIONS
 	}
 #endif
 
-	RO_DATA(8)
+	RO_DATA(PAGE_SIZE)
 
 	/* unwind info */
 	. = ALIGN(4);
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 2fe5b44986e0..c39de84e98b0 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -150,11 +150,16 @@ int fixup_exception(struct pt_regs *regs)
 		 * Fix up get_user() and put_user().
 		 * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() sets the least-significant
 		 * bit in the relative address of the fixup routine to indicate
-		 * that gr[ASM_EXCEPTIONTABLE_REG] should be loaded with
-		 * -EFAULT to report a userspace access error.
+		 * that the register encoded in the "or %r0,%r0,register"
+		 * opcode should be loaded with -EFAULT to report a userspace
+		 * access error.
 		 */
 		if (fix->fixup & 1) {
-			regs->gr[ASM_EXCEPTIONTABLE_REG] = -EFAULT;
+			int fault_error_reg = fix->err_opcode & 0x1f;
+			if (!WARN_ON(!fault_error_reg))
+				regs->gr[fault_error_reg] = -EFAULT;
+			pr_debug("Unalignment fixup of register %d at %pS\n",
+				fault_error_reg, (void*)regs->iaoq[0]);
 
 			/* zero target register for get_user() */
 			if (parisc_acctyp(0, regs->iir) == VM_READ) {
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 414b978b8010..b9fc064d38d2 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -859,6 +859,7 @@ config THREAD_SHIFT
 	int "Thread shift" if EXPERT
 	range 13 15
 	default "15" if PPC_256K_PAGES
+	default "15" if PPC_PSERIES || PPC_POWERNV
 	default "14" if PPC64
 	default "13"
 	help
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index 1ebd2ca97f12..107fc5a48456 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -20,14 +20,6 @@
 #ifndef __ASSEMBLY__
 extern void _mcount(void);
 
-static inline unsigned long ftrace_call_adjust(unsigned long addr)
-{
-	if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY))
-		addr += MCOUNT_INSN_SIZE;
-
-	return addr;
-}
-
 unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
 				    unsigned long sp);
 
@@ -142,8 +134,10 @@ static inline u8 this_cpu_get_ftrace_enabled(void) { return 1; }
 #ifdef CONFIG_FUNCTION_TRACER
 extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[];
 void ftrace_free_init_tramp(void);
+unsigned long ftrace_call_adjust(unsigned long addr);
 #else
 static inline void ftrace_free_init_tramp(void) { }
+static inline unsigned long ftrace_call_adjust(unsigned long addr) { return addr; }
 #endif
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/powerpc/include/asm/hvconsole.h b/arch/powerpc/include/asm/hvconsole.h
index ccb2034506f0..d841a97010a0 100644
--- a/arch/powerpc/include/asm/hvconsole.h
+++ b/arch/powerpc/include/asm/hvconsole.h
@@ -21,8 +21,8 @@
  * Vio firmware always attempts to fetch MAX_VIO_GET_CHARS chars.  The 'count'
  * parm is included to conform to put_chars() function pointer template
  */
-extern int hvc_get_chars(uint32_t vtermno, char *buf, int count);
-extern int hvc_put_chars(uint32_t vtermno, const char *buf, int count);
+extern ssize_t hvc_get_chars(uint32_t vtermno, u8 *buf, size_t count);
+extern ssize_t hvc_put_chars(uint32_t vtermno, const u8 *buf, size_t count);
 
 /* Provided by HVC VIO */
 void hvc_vio_init_early(void);
diff --git a/arch/powerpc/include/asm/hvsi.h b/arch/powerpc/include/asm/hvsi.h
index 464a7519ed64..9058edcb632b 100644
--- a/arch/powerpc/include/asm/hvsi.h
+++ b/arch/powerpc/include/asm/hvsi.h
@@ -64,7 +64,7 @@ struct hvsi_priv {
 	unsigned int	inbuf_len;	/* data in input buffer */
 	unsigned char	inbuf[HVSI_INBUF_SIZE];
 	unsigned int	inbuf_cur;	/* Cursor in input buffer */
-	unsigned int	inbuf_pktlen;	/* packet length from cursor */
+	size_t		inbuf_pktlen;	/* packet length from cursor */
 	atomic_t	seqno;		/* packet sequence number */
 	unsigned int	opened:1;	/* driver opened */
 	unsigned int	established:1;	/* protocol established */
@@ -72,24 +72,26 @@ struct hvsi_priv {
 	unsigned int	mctrl_update:1;	/* modem control updated */
 	unsigned short	mctrl;		/* modem control */
 	struct tty_struct *tty;		/* tty structure */
-	int (*get_chars)(uint32_t termno, char *buf, int count);
-	int (*put_chars)(uint32_t termno, const char *buf, int count);
+	ssize_t (*get_chars)(uint32_t termno, u8 *buf, size_t count);
+	ssize_t (*put_chars)(uint32_t termno, const u8 *buf, size_t count);
 	uint32_t	termno;
 };
 
 /* hvsi lib functions */
 struct hvc_struct;
 extern void hvsilib_init(struct hvsi_priv *pv,
-			 int (*get_chars)(uint32_t termno, char *buf, int count),
-			 int (*put_chars)(uint32_t termno, const char *buf,
-					  int count),
+			 ssize_t (*get_chars)(uint32_t termno, u8 *buf,
+					      size_t count),
+			 ssize_t (*put_chars)(uint32_t termno, const u8 *buf,
+					      size_t count),
 			 int termno, int is_console);
 extern int hvsilib_open(struct hvsi_priv *pv, struct hvc_struct *hp);
 extern void hvsilib_close(struct hvsi_priv *pv, struct hvc_struct *hp);
 extern int hvsilib_read_mctrl(struct hvsi_priv *pv);
 extern int hvsilib_write_mctrl(struct hvsi_priv *pv, int dtr);
 extern void hvsilib_establish(struct hvsi_priv *pv);
-extern int hvsilib_get_chars(struct hvsi_priv *pv, char *buf, int count);
-extern int hvsilib_put_chars(struct hvsi_priv *pv, const char *buf, int count);
+extern ssize_t hvsilib_get_chars(struct hvsi_priv *pv, u8 *buf, size_t count);
+extern ssize_t hvsilib_put_chars(struct hvsi_priv *pv, const u8 *buf,
+				 size_t count);
 
 #endif /* _HVSI_H */
diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h
index 93ce3ec25387..2f2a86ed2280 100644
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -17,7 +17,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "nop # arch_static_branch\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".long 1b - ., %l[l_yes] - .\n\t"
@@ -32,7 +32,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "b %l[l_yes] # arch_static_branch_jump\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".long 1b - ., %l[l_yes] - .\n\t"
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 8799b37be295..8abac532146e 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -63,8 +63,6 @@
 
 #include <linux/mmu_notifier.h>
 
-#define KVM_ARCH_WANT_MMU_NOTIFIER
-
 #define HPTEG_CACHE_NUM			(1 << 15)
 #define HPTEG_HASH_BITS_PTE		13
 #define HPTEG_HASH_BITS_PTE_LONG	12
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index b66b0c615f4f..af304e6cb486 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -313,9 +313,11 @@ extern int early_init_dt_scan_recoverable_ranges(unsigned long node,
 				 const char *uname, int depth, void *data);
 void __init opal_configure_cores(void);
 
-extern int opal_get_chars(uint32_t vtermno, char *buf, int count);
-extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len);
-extern int opal_put_chars_atomic(uint32_t vtermno, const char *buf, int total_len);
+extern ssize_t opal_get_chars(uint32_t vtermno, u8 *buf, size_t count);
+extern ssize_t opal_put_chars(uint32_t vtermno, const u8 *buf,
+			      size_t total_len);
+extern ssize_t opal_put_chars_atomic(uint32_t vtermno, const u8 *buf,
+				     size_t total_len);
 extern int opal_flush_chars(uint32_t vtermno, bool wait);
 extern int opal_flush_console(uint32_t vtermno);
 
diff --git a/arch/powerpc/include/asm/papr-sysparm.h b/arch/powerpc/include/asm/papr-sysparm.h
index 0dbbff59101d..c3cd5b131033 100644
--- a/arch/powerpc/include/asm/papr-sysparm.h
+++ b/arch/powerpc/include/asm/papr-sysparm.h
@@ -32,7 +32,7 @@ typedef struct {
  */
 struct papr_sysparm_buf {
 	__be16 len;
-	char val[PAPR_SYSPARM_MAX_OUTPUT];
+	u8 val[PAPR_SYSPARM_MAX_OUTPUT];
 };
 
 struct papr_sysparm_buf *papr_sysparm_buf_alloc(void);
diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h
index ce2b1b5eebdd..a8b7e8682f5b 100644
--- a/arch/powerpc/include/asm/ppc-pci.h
+++ b/arch/powerpc/include/asm/ppc-pci.h
@@ -30,6 +30,16 @@ void *pci_traverse_device_nodes(struct device_node *start,
 				void *data);
 extern void pci_devs_phb_init_dynamic(struct pci_controller *phb);
 
+#if defined(CONFIG_IOMMU_API) && (defined(CONFIG_PPC_PSERIES) || \
+				  defined(CONFIG_PPC_POWERNV))
+extern void ppc_iommu_register_device(struct pci_controller *phb);
+extern void ppc_iommu_unregister_device(struct pci_controller *phb);
+#else
+static inline void ppc_iommu_register_device(struct pci_controller *phb) { }
+static inline void ppc_iommu_unregister_device(struct pci_controller *phb) { }
+#endif
+
+
 /* From rtas_pci.h */
 extern void init_pci_config_tokens (void);
 extern unsigned long get_phb_buid (struct device_node *);
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 7fd09f25452d..bb47af9054a9 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -617,6 +617,8 @@
 #endif
 #define SPRN_HID2	0x3F8		/* Hardware Implementation Register 2 */
 #define SPRN_HID2_GEKKO	0x398		/* Gekko HID2 Register */
+#define SPRN_HID2_G2_LE	0x3F3		/* G2_LE HID2 Register */
+#define  HID2_G2_LE_HBE	(1<<18)		/* High BAT Enable (G2_LE) */
 #define SPRN_IABR	0x3F2	/* Instruction Address Breakpoint Register */
 #define SPRN_IABR2	0x3FA		/* 83xx */
 #define SPRN_IBCR	0x135		/* 83xx Insn Breakpoint Control Reg */
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 9bb2210c8d44..065ffd1b2f8a 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -69,7 +69,7 @@ enum rtas_function_index {
 	RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE,
 	RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2,
 	RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW,
-	RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS,
+	RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW,
 	RTAS_FNIDX__IBM_SCAN_LOG_DUMP,
 	RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR,
 	RTAS_FNIDX__IBM_SET_EEH_OPTION,
@@ -164,7 +164,7 @@ typedef struct {
 #define RTAS_FN_IBM_READ_SLOT_RESET_STATE         rtas_fn_handle(RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE)
 #define RTAS_FN_IBM_READ_SLOT_RESET_STATE2        rtas_fn_handle(RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2)
 #define RTAS_FN_IBM_REMOVE_PE_DMA_WINDOW          rtas_fn_handle(RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW)
-#define RTAS_FN_IBM_RESET_PE_DMA_WINDOWS          rtas_fn_handle(RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS)
+#define RTAS_FN_IBM_RESET_PE_DMA_WINDOW           rtas_fn_handle(RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW)
 #define RTAS_FN_IBM_SCAN_LOG_DUMP                 rtas_fn_handle(RTAS_FNIDX__IBM_SCAN_LOG_DUMP)
 #define RTAS_FN_IBM_SET_DYNAMIC_INDICATOR         rtas_fn_handle(RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR)
 #define RTAS_FN_IBM_SET_EEH_OPTION                rtas_fn_handle(RTAS_FNIDX__IBM_SET_EEH_OPTION)
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index ea26665f82cf..f43f3a6b0051 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -14,6 +14,7 @@ typedef struct func_desc func_desc_t;
 
 extern char __head_end[];
 extern char __srwx_boundary[];
+extern char __exittext_begin[], __exittext_end[];
 
 /* Patch sites */
 extern s32 patch__call_flush_branch_caches1;
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index bf5dde1a4114..15c5691dd218 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -14,7 +14,7 @@
 
 #ifdef __KERNEL__
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN) && CONFIG_THREAD_SHIFT < 15
 #define MIN_THREAD_SHIFT	(CONFIG_THREAD_SHIFT + 1)
 #else
 #define MIN_THREAD_SHIFT	CONFIG_THREAD_SHIFT
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index f1f9890f50d3..de10437fd206 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -74,7 +74,7 @@ __pu_failed:							\
 /* -mprefixed can generate offsets beyond range, fall back hack */
 #ifdef CONFIG_PPC_KERNEL_PREFIXED
 #define __put_user_asm_goto(x, addr, label, op)			\
-	asm_volatile_goto(					\
+	asm goto(					\
 		"1:	" op " %0,0(%1)	# put_user\n"		\
 		EX_TABLE(1b, %l2)				\
 		:						\
@@ -83,7 +83,7 @@ __pu_failed:							\
 		: label)
 #else
 #define __put_user_asm_goto(x, addr, label, op)			\
-	asm_volatile_goto(					\
+	asm goto(					\
 		"1:	" op "%U1%X1 %0,%1	# put_user\n"	\
 		EX_TABLE(1b, %l2)				\
 		:						\
@@ -97,7 +97,7 @@ __pu_failed:							\
 	__put_user_asm_goto(x, ptr, label, "std")
 #else /* __powerpc64__ */
 #define __put_user_asm2_goto(x, addr, label)			\
-	asm_volatile_goto(					\
+	asm goto(					\
 		"1:	stw%X1 %0, %1\n"			\
 		"2:	stw%X1 %L0, %L1\n"			\
 		EX_TABLE(1b, %l2)				\
@@ -146,7 +146,7 @@ do {								\
 /* -mprefixed can generate offsets beyond range, fall back hack */
 #ifdef CONFIG_PPC_KERNEL_PREFIXED
 #define __get_user_asm_goto(x, addr, label, op)			\
-	asm_volatile_goto(					\
+	asm_goto_output(					\
 		"1:	"op" %0,0(%1)	# get_user\n"		\
 		EX_TABLE(1b, %l2)				\
 		: "=r" (x)					\
@@ -155,7 +155,7 @@ do {								\
 		: label)
 #else
 #define __get_user_asm_goto(x, addr, label, op)			\
-	asm_volatile_goto(					\
+	asm_goto_output(					\
 		"1:	"op"%U1%X1 %0, %1	# get_user\n"	\
 		EX_TABLE(1b, %l2)				\
 		: "=r" (x)					\
@@ -169,7 +169,7 @@ do {								\
 	__get_user_asm_goto(x, addr, label, "ld")
 #else /* __powerpc64__ */
 #define __get_user_asm2_goto(x, addr, label)			\
-	asm_volatile_goto(					\
+	asm_goto_output(					\
 		"1:	lwz%X1 %0, %1\n"			\
 		"2:	lwz%X1 %L0, %L1\n"			\
 		EX_TABLE(1b, %l2)				\
diff --git a/arch/powerpc/include/uapi/asm/papr-sysparm.h b/arch/powerpc/include/uapi/asm/papr-sysparm.h
index 9f9a0f267ea5..f733467b1534 100644
--- a/arch/powerpc/include/uapi/asm/papr-sysparm.h
+++ b/arch/powerpc/include/uapi/asm/papr-sysparm.h
@@ -14,7 +14,7 @@ enum {
 struct papr_sysparm_io_block {
 	__u32 parameter;
 	__u16 length;
-	char data[PAPR_SYSPARM_MAX_OUTPUT];
+	__u8 data[PAPR_SYSPARM_MAX_OUTPUT];
 };
 
 /**
diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S
index f29ce3dd6140..bfd3f442e5eb 100644
--- a/arch/powerpc/kernel/cpu_setup_6xx.S
+++ b/arch/powerpc/kernel/cpu_setup_6xx.S
@@ -26,6 +26,15 @@ BEGIN_FTR_SECTION
 	bl	__init_fpu_registers
 END_FTR_SECTION_IFCLR(CPU_FTR_FPU_UNAVAILABLE)
 	bl	setup_common_caches
+
+	/*
+	 * This assumes that all cores using __setup_cpu_603 with
+	 * MMU_FTR_USE_HIGH_BATS are G2_LE compatible
+	 */
+BEGIN_MMU_FTR_SECTION
+	bl      setup_g2_le_hid2
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
+
 	mtlr	r5
 	blr
 _GLOBAL(__setup_cpu_604)
@@ -115,6 +124,16 @@ SYM_FUNC_START_LOCAL(setup_604_hid0)
 	blr
 SYM_FUNC_END(setup_604_hid0)
 
+/* Enable high BATs for G2_LE and derivatives like e300cX */
+SYM_FUNC_START_LOCAL(setup_g2_le_hid2)
+	mfspr	r11,SPRN_HID2_G2_LE
+	oris	r11,r11,HID2_G2_LE_HBE@h
+	mtspr	SPRN_HID2_G2_LE,r11
+	sync
+	isync
+	blr
+SYM_FUNC_END(setup_g2_le_hid2)
+
 /* 7400 <= rev 2.7 and 7410 rev = 1.0 suffer from some
  * erratas we work around here.
  * Moto MPC710CE.pdf describes them, those are errata
@@ -495,4 +514,3 @@ _GLOBAL(__restore_cpu_setup)
 	mtcr	r7
 	blr
 _ASM_NOKPROBE_SYMBOL(__restore_cpu_setup)
-
diff --git a/arch/powerpc/kernel/cpu_specs_e500mc.h b/arch/powerpc/kernel/cpu_specs_e500mc.h
index ceb06b109f83..2ae8e9a7b461 100644
--- a/arch/powerpc/kernel/cpu_specs_e500mc.h
+++ b/arch/powerpc/kernel/cpu_specs_e500mc.h
@@ -8,7 +8,8 @@
 
 #ifdef CONFIG_PPC64
 #define COMMON_USER_BOOKE	(PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
-				 PPC_FEATURE_HAS_FPU | PPC_FEATURE_64)
+				 PPC_FEATURE_HAS_FPU | PPC_FEATURE_64 | \
+				 PPC_FEATURE_BOOKE)
 #else
 #define COMMON_USER_BOOKE	(PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
 				 PPC_FEATURE_BOOKE)
diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S
index bd863702d812..1ad059a9e2fe 100644
--- a/arch/powerpc/kernel/interrupt_64.S
+++ b/arch/powerpc/kernel/interrupt_64.S
@@ -52,7 +52,8 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
 	mr	r10,r1
 	ld	r1,PACAKSAVE(r13)
 	std	r10,0(r1)
-	std	r11,_NIP(r1)
+	std	r11,_LINK(r1)
+	std	r11,_NIP(r1)	/* Saved LR is also the next instruction */
 	std	r12,_MSR(r1)
 	std	r0,GPR0(r1)
 	std	r10,GPR1(r1)
@@ -70,7 +71,6 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
 	std	r9,GPR13(r1)
 	SAVE_NVGPRS(r1)
 	std	r11,_XER(r1)
-	std	r11,_LINK(r1)
 	std	r11,_CTR(r1)
 
 	li	r11,\trapnr
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index ebe259bdd462..1185efebf032 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1287,20 +1287,22 @@ spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain,
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 	struct iommu_group *grp = iommu_group_get(dev);
 	struct iommu_table_group *table_group;
-	int ret = -EINVAL;
 
 	/* At first attach the ownership is already set */
-	if (!domain)
+	if (!domain) {
+		iommu_group_put(grp);
 		return 0;
-
-	if (!grp)
-		return -ENODEV;
+	}
 
 	table_group = iommu_group_get_iommudata(grp);
-	ret = table_group->ops->take_ownership(table_group);
+	/*
+	 * The domain being set to PLATFORM from earlier
+	 * BLOCKED. The table_group ownership has to be released.
+	 */
+	table_group->ops->release_ownership(table_group);
 	iommu_group_put(grp);
 
-	return ret;
+	return 0;
 }
 
 static const struct iommu_domain_ops spapr_tce_platform_domain_ops = {
@@ -1312,13 +1314,32 @@ static struct iommu_domain spapr_tce_platform_domain = {
 	.ops = &spapr_tce_platform_domain_ops,
 };
 
-static struct iommu_domain spapr_tce_blocked_domain = {
-	.type = IOMMU_DOMAIN_BLOCKED,
+static int
+spapr_tce_blocked_iommu_attach_dev(struct iommu_domain *platform_domain,
+				     struct device *dev)
+{
+	struct iommu_group *grp = iommu_group_get(dev);
+	struct iommu_table_group *table_group;
+	int ret = -EINVAL;
+
 	/*
 	 * FIXME: SPAPR mixes blocked and platform behaviors, the blocked domain
 	 * also sets the dma_api ops
 	 */
-	.ops = &spapr_tce_platform_domain_ops,
+	table_group = iommu_group_get_iommudata(grp);
+	ret = table_group->ops->take_ownership(table_group);
+	iommu_group_put(grp);
+
+	return ret;
+}
+
+static const struct iommu_domain_ops spapr_tce_blocked_domain_ops = {
+	.attach_dev = spapr_tce_blocked_iommu_attach_dev,
+};
+
+static struct iommu_domain spapr_tce_blocked_domain = {
+	.type = IOMMU_DOMAIN_BLOCKED,
+	.ops = &spapr_tce_blocked_domain_ops,
 };
 
 static bool spapr_tce_iommu_capable(struct device *dev, enum iommu_cap cap)
@@ -1339,7 +1360,7 @@ static struct iommu_device *spapr_tce_iommu_probe_device(struct device *dev)
 	struct pci_controller *hose;
 
 	if (!dev_is_pci(dev))
-		return ERR_PTR(-EPERM);
+		return ERR_PTR(-ENODEV);
 
 	pdev = to_pci_dev(dev);
 	hose = pdev->bus->sysdata;
@@ -1388,6 +1409,21 @@ static const struct attribute_group *spapr_tce_iommu_groups[] = {
 	NULL,
 };
 
+void ppc_iommu_register_device(struct pci_controller *phb)
+{
+	iommu_device_sysfs_add(&phb->iommu, phb->parent,
+				spapr_tce_iommu_groups, "iommu-phb%04x",
+				phb->global_number);
+	iommu_device_register(&phb->iommu, &spapr_tce_iommu_ops,
+				phb->parent);
+}
+
+void ppc_iommu_unregister_device(struct pci_controller *phb)
+{
+	iommu_device_unregister(&phb->iommu);
+	iommu_device_sysfs_remove(&phb->iommu);
+}
+
 /*
  * This registers IOMMU devices of PHBs. This needs to happen
  * after core_initcall(iommu_init) + postcore_initcall(pci_driver_init) and
@@ -1398,11 +1434,7 @@ static int __init spapr_tce_setup_phb_iommus_initcall(void)
 	struct pci_controller *hose;
 
 	list_for_each_entry(hose, &hose_list, list_node) {
-		iommu_device_sysfs_add(&hose->iommu, hose->parent,
-				       spapr_tce_iommu_groups, "iommu-phb%04x",
-				       hose->global_number);
-		iommu_device_register(&hose->iommu, &spapr_tce_iommu_ops,
-				      hose->parent);
+		ppc_iommu_register_device(hose);
 	}
 	return 0;
 }
diff --git a/arch/powerpc/kernel/irq_64.c b/arch/powerpc/kernel/irq_64.c
index 938e66829eae..d5c48d1b0a31 100644
--- a/arch/powerpc/kernel/irq_64.c
+++ b/arch/powerpc/kernel/irq_64.c
@@ -230,7 +230,7 @@ again:
 	 * This allows interrupts to be unmasked without hard disabling, and
 	 * also without new hard interrupts coming in ahead of pending ones.
 	 */
-	asm_volatile_goto(
+	asm goto(
 "1:					\n"
 "		lbz	9,%0(13)	\n"
 "		cmpwi	9,0		\n"
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 7e793b503e29..8064d9c3de86 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -375,8 +375,13 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 	[RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW] = {
 		.name = "ibm,remove-pe-dma-window",
 	},
-	[RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS] = {
-		.name = "ibm,reset-pe-dma-windows",
+	[RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW] = {
+		/*
+		 * Note: PAPR+ v2.13 7.3.31.4.1 spells this as
+		 * "ibm,reset-pe-dma-windows" (plural), but RTAS
+		 * implementations use the singular form in practice.
+		 */
+		.name = "ibm,reset-pe-dma-window",
 	},
 	[RTAS_FNIDX__IBM_SCAN_LOG_DUMP] = {
 		.name = "ibm,scan-log-dump",
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 82010629cf88..d8d6b4fd9a14 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -27,10 +27,22 @@
 #include <asm/ftrace.h>
 #include <asm/syscall.h>
 #include <asm/inst.h>
+#include <asm/sections.h>
 
 #define	NUM_FTRACE_TRAMPS	2
 static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
 
+unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	if (addr >= (unsigned long)__exittext_begin && addr < (unsigned long)__exittext_end)
+		return 0;
+
+	if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY))
+		addr += MCOUNT_INSN_SIZE;
+
+	return addr;
+}
+
 static ppc_inst_t ftrace_create_branch_inst(unsigned long ip, unsigned long addr, int link)
 {
 	ppc_inst_t op;
diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c
index 7b85c3b460a3..12fab1803bcf 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_pg.c
+++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c
@@ -37,6 +37,11 @@
 #define	NUM_FTRACE_TRAMPS	8
 static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
 
+unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	return addr;
+}
+
 static ppc_inst_t
 ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
 {
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 1c5970df3233..f420df7888a7 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -281,7 +281,9 @@ SECTIONS
 	 * to deal with references from __bug_table
 	 */
 	.exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
+		__exittext_begin = .;
 		EXIT_TEXT
+		__exittext_end = .;
 	}
 
 	. = ALIGN(PAGE_SIZE);
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 902611954200..074263429faf 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -19,13 +19,11 @@ if VIRTUALIZATION
 
 config KVM
 	bool
-	select PREEMPT_NOTIFIERS
-	select HAVE_KVM_EVENTFD
+	select KVM_COMMON
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
 	select KVM_VFIO
 	select IRQ_BYPASS_MANAGER
 	select HAVE_KVM_IRQ_BYPASS
-	select INTERVAL_TREE
 
 config KVM_BOOK3S_HANDLER
 	bool
@@ -42,7 +40,7 @@ config KVM_BOOK3S_64_HANDLER
 config KVM_BOOK3S_PR_POSSIBLE
 	bool
 	select KVM_MMIO
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 
 config KVM_BOOK3S_HV_POSSIBLE
 	bool
@@ -85,7 +83,7 @@ config KVM_BOOK3S_64_HV
 	tristate "KVM for POWER7 and later using hypervisor mode in host"
 	depends on KVM_BOOK3S_64 && PPC_POWERNV
 	select KVM_BOOK3S_HV_POSSIBLE
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	select CMA
 	help
 	  Support running unmodified book3s_64 guest kernels in
@@ -194,7 +192,7 @@ config KVM_E500V2
 	depends on !CONTEXT_TRACKING_USER
 	select KVM
 	select KVM_MMIO
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	help
 	  Support running unmodified E500 guest kernels in virtual machines on
 	  E500v2 host processors.
@@ -211,7 +209,7 @@ config KVM_E500MC
 	select KVM
 	select KVM_MMIO
 	select KVM_BOOKE_HV
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	help
 	  Support running unmodified E500MC/E5500/E6500 guest kernels in
 	  virtual machines on E500MC/E5500/E6500 host processors.
@@ -225,7 +223,6 @@ config KVM_MPIC
 	bool "KVM in-kernel MPIC emulation"
 	depends on KVM && PPC_E500
 	select HAVE_KVM_IRQCHIP
-	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_MSI
 	help
@@ -238,7 +235,6 @@ config KVM_XICS
 	bool "KVM in-kernel XICS emulation"
 	depends on KVM_BOOK3S_64 && !KVM_MPIC
 	select HAVE_KVM_IRQCHIP
-	select HAVE_KVM_IRQFD
 	default y
 	help
 	  Include support for the XICS (eXternal Interrupt Controller
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index e48126a59ba7..0b921704da45 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -391,6 +391,24 @@ static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr)
 /* Dummy value used in computing PCR value below */
 #define PCR_ARCH_31    (PCR_ARCH_300 << 1)
 
+static inline unsigned long map_pcr_to_cap(unsigned long pcr)
+{
+	unsigned long cap = 0;
+
+	switch (pcr) {
+	case PCR_ARCH_300:
+		cap = H_GUEST_CAP_POWER9;
+		break;
+	case PCR_ARCH_31:
+		cap = H_GUEST_CAP_POWER10;
+		break;
+	default:
+		break;
+	}
+
+	return cap;
+}
+
 static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
 {
 	unsigned long host_pcr_bit = 0, guest_pcr_bit = 0, cap = 0;
@@ -424,11 +442,9 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
 			break;
 		case PVR_ARCH_300:
 			guest_pcr_bit = PCR_ARCH_300;
-			cap = H_GUEST_CAP_POWER9;
 			break;
 		case PVR_ARCH_31:
 			guest_pcr_bit = PCR_ARCH_31;
-			cap = H_GUEST_CAP_POWER10;
 			break;
 		default:
 			return -EINVAL;
@@ -440,6 +456,12 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
 		return -EINVAL;
 
 	if (kvmhv_on_pseries() && kvmhv_is_nestedv2()) {
+		/*
+		 * 'arch_compat == 0' would mean the guest should default to
+		 * L1's compatibility. In this case, the guest would pick
+		 * host's PCR and evaluate the corresponding capabilities.
+		 */
+		cap = map_pcr_to_cap(guest_pcr_bit);
 		if (!(cap & nested_capabilities))
 			return -EINVAL;
 	}
@@ -6240,7 +6262,7 @@ static int kvmhv_svm_off(struct kvm *kvm)
 	}
 
 	srcu_idx = srcu_read_lock(&kvm->srcu);
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		struct kvm_memory_slot *memslot;
 		struct kvm_memslots *slots = __kvm_memslots(kvm, i);
 		int bkt;
diff --git a/arch/powerpc/kvm/book3s_hv_nestedv2.c b/arch/powerpc/kvm/book3s_hv_nestedv2.c
index 5378eb40b162..8e6f5355f08b 100644
--- a/arch/powerpc/kvm/book3s_hv_nestedv2.c
+++ b/arch/powerpc/kvm/book3s_hv_nestedv2.c
@@ -138,6 +138,7 @@ static int gs_msg_ops_vcpu_fill_info(struct kvmppc_gs_buff *gsb,
 	vector128 v;
 	int rc, i;
 	u16 iden;
+	u32 arch_compat = 0;
 
 	vcpu = gsm->data;
 
@@ -347,8 +348,23 @@ static int gs_msg_ops_vcpu_fill_info(struct kvmppc_gs_buff *gsb,
 			break;
 		}
 		case KVMPPC_GSID_LOGICAL_PVR:
-			rc = kvmppc_gse_put_u32(gsb, iden,
-						vcpu->arch.vcore->arch_compat);
+			/*
+			 * Though 'arch_compat == 0' would mean the default
+			 * compatibility, arch_compat, being a Guest Wide
+			 * Element, cannot be filled with a value of 0 in GSB
+			 * as this would result into a kernel trap.
+			 * Hence, when `arch_compat == 0`, arch_compat should
+			 * default to L1's PVR.
+			 */
+			if (!vcpu->arch.vcore->arch_compat) {
+				if (cpu_has_feature(CPU_FTR_ARCH_31))
+					arch_compat = PVR_ARCH_31;
+				else if (cpu_has_feature(CPU_FTR_ARCH_300))
+					arch_compat = PVR_ARCH_300;
+			} else {
+				arch_compat = vcpu->arch.vcore->arch_compat;
+			}
+			rc = kvmppc_gse_put_u32(gsb, iden, arch_compat);
 			break;
 		}
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index f6af752698d0..23407fbd73c9 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -528,7 +528,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_IOEVENTFD:
-	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_IMMEDIATE_EXIT:
 	case KVM_CAP_SET_GUEST_DEBUG:
 		r = 1;
@@ -578,7 +577,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 #endif
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 	case KVM_CAP_IRQFD_RESAMPLE:
 		r = !xive_enabled();
 		break;
@@ -632,13 +631,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 #endif
 	case KVM_CAP_SYNC_MMU:
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-		r = hv_enabled;
-#elif defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+		BUILD_BUG_ON(!IS_ENABLED(CONFIG_KVM_GENERIC_MMU_NOTIFIER));
 		r = 1;
-#else
-		r = 0;
-#endif
 		break;
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	case KVM_CAP_PPC_HTAB_FD:
diff --git a/arch/powerpc/mm/kasan/init_32.c b/arch/powerpc/mm/kasan/init_32.c
index a70828a6d935..aa9aa11927b2 100644
--- a/arch/powerpc/mm/kasan/init_32.c
+++ b/arch/powerpc/mm/kasan/init_32.c
@@ -64,6 +64,7 @@ int __init __weak kasan_init_region(void *start, size_t size)
 	if (ret)
 		return ret;
 
+	k_start = k_start & PAGE_MASK;
 	block = memblock_alloc(k_end - k_start, PAGE_SIZE);
 	if (!block)
 		return -ENOMEM;
diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c
index e966b2ad8ecd..b3327a358eb4 100644
--- a/arch/powerpc/platforms/85xx/mpc8536_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c
@@ -27,7 +27,7 @@
 
 #include "mpc85xx.h"
 
-void __init mpc8536_ds_pic_init(void)
+static void __init mpc8536_ds_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
 			0, 256, " OpenPIC  ");
diff --git a/arch/powerpc/platforms/85xx/mvme2500.c b/arch/powerpc/platforms/85xx/mvme2500.c
index 1b59e45a0c64..19122daadb55 100644
--- a/arch/powerpc/platforms/85xx/mvme2500.c
+++ b/arch/powerpc/platforms/85xx/mvme2500.c
@@ -21,7 +21,7 @@
 
 #include "mpc85xx.h"
 
-void __init mvme2500_pic_init(void)
+static void __init mvme2500_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0,
 		  MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/p1010rdb.c b/arch/powerpc/platforms/85xx/p1010rdb.c
index 10d6f1fa3327..491895ac8bcf 100644
--- a/arch/powerpc/platforms/85xx/p1010rdb.c
+++ b/arch/powerpc/platforms/85xx/p1010rdb.c
@@ -24,7 +24,7 @@
 
 #include "mpc85xx.h"
 
-void __init p1010_rdb_pic_init(void)
+static void __init p1010_rdb_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
 	  MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c
index 0dd786a061a6..adc3a2ee1415 100644
--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@@ -370,7 +370,7 @@ exit:
  *
  * @pixclock: the wavelength, in picoseconds, of the clock
  */
-void p1022ds_set_pixel_clock(unsigned int pixclock)
+static void p1022ds_set_pixel_clock(unsigned int pixclock)
 {
 	struct device_node *guts_np = NULL;
 	struct ccsr_guts __iomem *guts;
@@ -418,7 +418,7 @@ void p1022ds_set_pixel_clock(unsigned int pixclock)
 /**
  * p1022ds_valid_monitor_port: set the monitor port for sysfs
  */
-enum fsl_diu_monitor_port
+static enum fsl_diu_monitor_port
 p1022ds_valid_monitor_port(enum fsl_diu_monitor_port port)
 {
 	switch (port) {
@@ -432,7 +432,7 @@ p1022ds_valid_monitor_port(enum fsl_diu_monitor_port port)
 
 #endif
 
-void __init p1022_ds_pic_init(void)
+static void __init p1022_ds_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
 		MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/p1022_rdk.c b/arch/powerpc/platforms/85xx/p1022_rdk.c
index 25ab6e9c1470..6198299d95b1 100644
--- a/arch/powerpc/platforms/85xx/p1022_rdk.c
+++ b/arch/powerpc/platforms/85xx/p1022_rdk.c
@@ -40,7 +40,7 @@
  *
  * @pixclock: the wavelength, in picoseconds, of the clock
  */
-void p1022rdk_set_pixel_clock(unsigned int pixclock)
+static void p1022rdk_set_pixel_clock(unsigned int pixclock)
 {
 	struct device_node *guts_np = NULL;
 	struct ccsr_guts __iomem *guts;
@@ -88,7 +88,7 @@ void p1022rdk_set_pixel_clock(unsigned int pixclock)
 /**
  * p1022rdk_valid_monitor_port: set the monitor port for sysfs
  */
-enum fsl_diu_monitor_port
+static enum fsl_diu_monitor_port
 p1022rdk_valid_monitor_port(enum fsl_diu_monitor_port port)
 {
 	return FSL_DIU_PORT_DVI;
@@ -96,7 +96,7 @@ p1022rdk_valid_monitor_port(enum fsl_diu_monitor_port port)
 
 #endif
 
-void __init p1022_rdk_pic_init(void)
+static void __init p1022_rdk_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
 		MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
index baa12eff6d5d..60e0b8947ce6 100644
--- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
+++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
@@ -8,6 +8,8 @@
 #include <linux/of_irq.h>
 #include <linux/io.h>
 
+#include "socrates_fpga_pic.h"
+
 /*
  * The FPGA supports 9 interrupt sources, which can be routed to 3
  * interrupt request lines of the MPIC. The line to be used can be
diff --git a/arch/powerpc/platforms/85xx/xes_mpc85xx.c b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
index 45f257fc1ade..2582427d8d01 100644
--- a/arch/powerpc/platforms/85xx/xes_mpc85xx.c
+++ b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
@@ -37,7 +37,7 @@
 #define MPC85xx_L2CTL_L2I		0x40000000 /* L2 flash invalidate */
 #define MPC85xx_L2CTL_L2SIZ_MASK	0x30000000 /* L2 SRAM size (R/O) */
 
-void __init xes_mpc85xx_pic_init(void)
+static void __init xes_mpc85xx_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
 			0, 256, " OpenPIC  ");
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index cdf3838f08d3..45dd77e3ccf6 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -424,7 +424,7 @@ static int __init opal_message_init(struct device_node *opal_node)
 	return 0;
 }
 
-int opal_get_chars(uint32_t vtermno, char *buf, int count)
+ssize_t opal_get_chars(uint32_t vtermno, u8 *buf, size_t count)
 {
 	s64 rc;
 	__be64 evt, len;
@@ -441,10 +441,11 @@ int opal_get_chars(uint32_t vtermno, char *buf, int count)
 	return 0;
 }
 
-static int __opal_put_chars(uint32_t vtermno, const char *data, int total_len, bool atomic)
+static ssize_t __opal_put_chars(uint32_t vtermno, const u8 *data,
+				size_t total_len, bool atomic)
 {
 	unsigned long flags = 0 /* shut up gcc */;
-	int written;
+	ssize_t written;
 	__be64 olen;
 	s64 rc;
 
@@ -484,7 +485,7 @@ static int __opal_put_chars(uint32_t vtermno, const char *data, int total_len, b
 		if (atomic) {
 			/* Should not happen */
 			pr_warn("atomic console write returned partial "
-				"len=%d written=%d\n", total_len, written);
+				"len=%zu written=%zd\n", total_len, written);
 		}
 		if (!written)
 			written = -EAGAIN;
@@ -497,7 +498,7 @@ out:
 	return written;
 }
 
-int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
+ssize_t opal_put_chars(uint32_t vtermno, const u8 *data, size_t total_len)
 {
 	return __opal_put_chars(vtermno, data, total_len, false);
 }
@@ -508,7 +509,8 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
  * true at the moment because console space can race with OPAL's console
  * writes.
  */
-int opal_put_chars_atomic(uint32_t vtermno, const char *data, int total_len)
+ssize_t opal_put_chars_atomic(uint32_t vtermno, const u8 *data,
+			      size_t total_len)
 {
 	return __opal_put_chars(vtermno, data, total_len, true);
 }
diff --git a/arch/powerpc/platforms/pseries/hvconsole.c b/arch/powerpc/platforms/pseries/hvconsole.c
index 1ac52963e08b..8803c947998e 100644
--- a/arch/powerpc/platforms/pseries/hvconsole.c
+++ b/arch/powerpc/platforms/pseries/hvconsole.c
@@ -25,7 +25,7 @@
  *	firmware.
  * @count: not used?
  */
-int hvc_get_chars(uint32_t vtermno, char *buf, int count)
+ssize_t hvc_get_chars(uint32_t vtermno, u8 *buf, size_t count)
 {
 	long ret;
 	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
@@ -52,7 +52,7 @@ EXPORT_SYMBOL(hvc_get_chars);
  *	firmware. Must be at least 16 bytes, even if count is less than 16.
  * @count: Send this number of characters.
  */
-int hvc_put_chars(uint32_t vtermno, const char *buf, int count)
+ssize_t hvc_put_chars(uint32_t vtermno, const u8 *buf, size_t count)
 {
 	unsigned long *lbuf = (unsigned long *) buf;
 	long ret;
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 496e16c588aa..e8c4129697b1 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -574,29 +574,6 @@ static void iommu_table_setparms(struct pci_controller *phb,
 
 struct iommu_table_ops iommu_table_lpar_multi_ops;
 
-/*
- * iommu_table_setparms_lpar
- *
- * Function: On pSeries LPAR systems, return TCE table info, given a pci bus.
- */
-static void iommu_table_setparms_lpar(struct pci_controller *phb,
-				      struct device_node *dn,
-				      struct iommu_table *tbl,
-				      struct iommu_table_group *table_group,
-				      const __be32 *dma_window)
-{
-	unsigned long offset, size, liobn;
-
-	of_parse_dma_window(dn, dma_window, &liobn, &offset, &size);
-
-	iommu_table_setparms_common(tbl, phb->bus->number, liobn, offset, size, IOMMU_PAGE_SHIFT_4K, NULL,
-				    &iommu_table_lpar_multi_ops);
-
-
-	table_group->tce32_start = offset;
-	table_group->tce32_size = size;
-}
-
 struct iommu_table_ops iommu_table_pseries_ops = {
 	.set = tce_build_pSeries,
 	.clear = tce_free_pSeries,
@@ -724,26 +701,71 @@ struct iommu_table_ops iommu_table_lpar_multi_ops = {
  * dynamic 64bit DMA window, walking up the device tree.
  */
 static struct device_node *pci_dma_find(struct device_node *dn,
-					const __be32 **dma_window)
+					struct dynamic_dma_window_prop *prop)
 {
-	const __be32 *dw = NULL;
+	const __be32 *default_prop = NULL;
+	const __be32 *ddw_prop = NULL;
+	struct device_node *rdn = NULL;
+	bool default_win = false, ddw_win = false;
 
 	for ( ; dn && PCI_DN(dn); dn = dn->parent) {
-		dw = of_get_property(dn, "ibm,dma-window", NULL);
-		if (dw) {
-			if (dma_window)
-				*dma_window = dw;
-			return dn;
+		default_prop = of_get_property(dn, "ibm,dma-window", NULL);
+		if (default_prop) {
+			rdn = dn;
+			default_win = true;
+		}
+		ddw_prop = of_get_property(dn, DIRECT64_PROPNAME, NULL);
+		if (ddw_prop) {
+			rdn = dn;
+			ddw_win = true;
+			break;
+		}
+		ddw_prop = of_get_property(dn, DMA64_PROPNAME, NULL);
+		if (ddw_prop) {
+			rdn = dn;
+			ddw_win = true;
+			break;
 		}
-		dw = of_get_property(dn, DIRECT64_PROPNAME, NULL);
-		if (dw)
-			return dn;
-		dw = of_get_property(dn, DMA64_PROPNAME, NULL);
-		if (dw)
-			return dn;
+
+		/* At least found default window, which is the case for normal boot */
+		if (default_win)
+			break;
 	}
 
-	return NULL;
+	/* For PCI devices there will always be a DMA window, either on the device
+	 * or parent bus
+	 */
+	WARN_ON(!(default_win | ddw_win));
+
+	/* caller doesn't want to get DMA window property */
+	if (!prop)
+		return rdn;
+
+	/* parse DMA window property. During normal system boot, only default
+	 * DMA window is passed in OF. But, for kdump, a dedicated adapter might
+	 * have both default and DDW in FDT. In this scenario, DDW takes precedence
+	 * over default window.
+	 */
+	if (ddw_win) {
+		struct dynamic_dma_window_prop *p;
+
+		p = (struct dynamic_dma_window_prop *)ddw_prop;
+		prop->liobn = p->liobn;
+		prop->dma_base = p->dma_base;
+		prop->tce_shift = p->tce_shift;
+		prop->window_shift = p->window_shift;
+	} else if (default_win) {
+		unsigned long offset, size, liobn;
+
+		of_parse_dma_window(rdn, default_prop, &liobn, &offset, &size);
+
+		prop->liobn = cpu_to_be32((u32)liobn);
+		prop->dma_base = cpu_to_be64(offset);
+		prop->tce_shift = cpu_to_be32(IOMMU_PAGE_SHIFT_4K);
+		prop->window_shift = cpu_to_be32(order_base_2(size));
+	}
+
+	return rdn;
 }
 
 static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
@@ -751,17 +773,20 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 	struct iommu_table *tbl;
 	struct device_node *dn, *pdn;
 	struct pci_dn *ppci;
-	const __be32 *dma_window = NULL;
+	struct dynamic_dma_window_prop prop;
 
 	dn = pci_bus_to_OF_node(bus);
 
 	pr_debug("pci_dma_bus_setup_pSeriesLP: setting up bus %pOF\n",
 		 dn);
 
-	pdn = pci_dma_find(dn, &dma_window);
+	pdn = pci_dma_find(dn, &prop);
 
-	if (dma_window == NULL)
-		pr_debug("  no ibm,dma-window property !\n");
+	/* In PPC architecture, there will always be DMA window on bus or one of the
+	 * parent bus. During reboot, there will be ibm,dma-window property to
+	 * define DMA window. For kdump, there will at least be default window or DDW
+	 * or both.
+	 */
 
 	ppci = PCI_DN(pdn);
 
@@ -771,13 +796,24 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 	if (!ppci->table_group) {
 		ppci->table_group = iommu_pseries_alloc_group(ppci->phb->node);
 		tbl = ppci->table_group->tables[0];
-		if (dma_window) {
-			iommu_table_setparms_lpar(ppci->phb, pdn, tbl,
-						  ppci->table_group, dma_window);
 
-			if (!iommu_init_table(tbl, ppci->phb->node, 0, 0))
-				panic("Failed to initialize iommu table");
-		}
+		iommu_table_setparms_common(tbl, ppci->phb->bus->number,
+				be32_to_cpu(prop.liobn),
+				be64_to_cpu(prop.dma_base),
+				1ULL << be32_to_cpu(prop.window_shift),
+				be32_to_cpu(prop.tce_shift), NULL,
+				&iommu_table_lpar_multi_ops);
+
+		/* Only for normal boot with default window. Doesn't matter even
+		 * if we set these with DDW which is 64bit during kdump, since
+		 * these will not be used during kdump.
+		 */
+		ppci->table_group->tce32_start = be64_to_cpu(prop.dma_base);
+		ppci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift);
+
+		if (!iommu_init_table(tbl, ppci->phb->node, 0, 0))
+			panic("Failed to initialize iommu table");
+
 		iommu_register_group(ppci->table_group,
 				pci_domain_nr(bus), 0);
 		pr_debug("  created table: %p\n", ppci->table_group);
@@ -968,6 +1004,12 @@ static void find_existing_ddw_windows_named(const char *name)
 			continue;
 		}
 
+		/* If at the time of system initialization, there are DDWs in OF,
+		 * it means this is during kexec. DDW could be direct or dynamic.
+		 * We will just mark DDWs as "dynamic" since this is kdump path,
+		 * no need to worry about perforance. ddw_list_new_entry() will
+		 * set window->direct = false.
+		 */
 		window = ddw_list_new_entry(pdn, dma64);
 		if (!window) {
 			of_node_put(pdn);
@@ -1524,8 +1566,8 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 {
 	struct device_node *pdn, *dn;
 	struct iommu_table *tbl;
-	const __be32 *dma_window = NULL;
 	struct pci_dn *pci;
+	struct dynamic_dma_window_prop prop;
 
 	pr_debug("pci_dma_dev_setup_pSeriesLP: %s\n", pci_name(dev));
 
@@ -1538,7 +1580,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 	dn = pci_device_to_OF_node(dev);
 	pr_debug("  node is %pOF\n", dn);
 
-	pdn = pci_dma_find(dn, &dma_window);
+	pdn = pci_dma_find(dn, &prop);
 	if (!pdn || !PCI_DN(pdn)) {
 		printk(KERN_WARNING "pci_dma_dev_setup_pSeriesLP: "
 		       "no DMA window found for pci dev=%s dn=%pOF\n",
@@ -1551,8 +1593,20 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 	if (!pci->table_group) {
 		pci->table_group = iommu_pseries_alloc_group(pci->phb->node);
 		tbl = pci->table_group->tables[0];
-		iommu_table_setparms_lpar(pci->phb, pdn, tbl,
-				pci->table_group, dma_window);
+
+		iommu_table_setparms_common(tbl, pci->phb->bus->number,
+				be32_to_cpu(prop.liobn),
+				be64_to_cpu(prop.dma_base),
+				1ULL << be32_to_cpu(prop.window_shift),
+				be32_to_cpu(prop.tce_shift), NULL,
+				&iommu_table_lpar_multi_ops);
+
+		/* Only for normal boot with default window. Doesn't matter even
+		 * if we set these with DDW which is 64bit during kdump, since
+		 * these will not be used during kdump.
+		 */
+		pci->table_group->tce32_start = be64_to_cpu(prop.dma_base);
+		pci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift);
 
 		iommu_init_table(tbl, pci->phb->node, 0, 0);
 		iommu_register_group(pci->table_group,
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 4561667832ed..4e9916bb03d7 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -662,8 +662,12 @@ u64 pseries_paravirt_steal_clock(int cpu)
 {
 	struct lppaca *lppaca = &lppaca_of(cpu);
 
-	return be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) +
-		be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb));
+	/*
+	 * VPA steal time counters are reported at TB frequency. Hence do a
+	 * conversion to ns before returning
+	 */
+	return tb_to_ns(be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) +
+			be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb)));
 }
 #endif
 
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 4ba824568119..4448386268d9 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -35,6 +35,8 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn)
 
 	pseries_msi_allocate_domains(phb);
 
+	ppc_iommu_register_device(phb);
+
 	/* Create EEH devices for the PHB */
 	eeh_phb_pe_create(phb);
 
@@ -76,6 +78,8 @@ int remove_phb_dynamic(struct pci_controller *phb)
 		}
 	}
 
+	ppc_iommu_unregister_device(phb);
+
 	pseries_msi_free_domains(phb);
 
 	/* Keep a reference so phb isn't freed yet */
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 3868483fbe29..ef7707ea0db7 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -54,7 +54,7 @@ static void quirk_fsl_pcie_early(struct pci_dev *dev)
 
 	/* if we aren't in host mode don't bother */
 	pci_read_config_byte(dev, PCI_HEADER_TYPE, &hdr_type);
-	if ((hdr_type & 0x7f) != PCI_HEADER_TYPE_BRIDGE)
+	if ((hdr_type & PCI_HEADER_TYPE_MASK) != PCI_HEADER_TYPE_BRIDGE)
 		return;
 
 	dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL;
@@ -581,7 +581,7 @@ static int fsl_add_bridge(struct platform_device *pdev, int is_primary)
 		hose->ops = &fsl_indirect_pcie_ops;
 		/* For PCIE read HEADER_TYPE to identify controller mode */
 		early_read_config_byte(hose, 0, 0, PCI_HEADER_TYPE, &hdr_type);
-		if ((hdr_type & 0x7f) != PCI_HEADER_TYPE_BRIDGE)
+		if ((hdr_type & PCI_HEADER_TYPE_MASK) != PCI_HEADER_TYPE_BRIDGE)
 			goto no_bridge;
 
 	} else {
diff --git a/arch/powerpc/sysdev/udbg_memcons.c b/arch/powerpc/sysdev/udbg_memcons.c
index 5020044400dc..4de57ba52236 100644
--- a/arch/powerpc/sysdev/udbg_memcons.c
+++ b/arch/powerpc/sysdev/udbg_memcons.c
@@ -41,7 +41,7 @@ struct memcons memcons = {
 	.input_end = &memcons_input[CONFIG_PPC_MEMCONS_INPUT_SIZE],
 };
 
-void memcons_putc(char c)
+static void memcons_putc(char c)
 {
 	char *new_output_pos;
 
@@ -54,7 +54,7 @@ void memcons_putc(char c)
 	memcons.output_pos = new_output_pos;
 }
 
-int memcons_getc_poll(void)
+static int memcons_getc_poll(void)
 {
 	char c;
 	char *new_input_pos;
@@ -77,7 +77,7 @@ int memcons_getc_poll(void)
 	return -1;
 }
 
-int memcons_getc(void)
+static int memcons_getc(void)
 {
 	int c;
 
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index cd4c9a204d08..e3142ce531a0 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -53,24 +53,28 @@ config RISCV
 	select ARCH_USE_MEMTEST
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USES_CFI_TRAPS if CFI_CLANG
+	select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH if SMP && MMU
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_GENERAL_HUGETLB if !RISCV_ISA_SVNAPOT
 	select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
 	select ARCH_WANT_LD_ORPHAN_WARN if !XIP_KERNEL
 	select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP
+	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU
 	select BUILDTIME_TABLE_SORT if MMU
 	select CLINT_TIMER if !MMU
 	select CLONE_BACKWARDS
 	select COMMON_CLK
-	select CPU_PM if CPU_IDLE || HIBERNATION
+	select CPU_PM if CPU_IDLE || HIBERNATION || SUSPEND
 	select EDAC_SUPPORT
 	select FRAME_POINTER if PERF_EVENTS || (FUNCTION_TRACER && !DYNAMIC_FTRACE)
+	select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if DYNAMIC_FTRACE
 	select GENERIC_ARCH_TOPOLOGY
 	select GENERIC_ATOMIC64 if !64BIT
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+	select GENERIC_CPU_DEVICES
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_ENTRY
 	select GENERIC_GETTIMEOFDAY if HAVE_GENERIC_VDSO
@@ -113,6 +117,7 @@ config RISCV
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS if MMU
 	select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && (CLANG_SUPPORTS_DYNAMIC_FTRACE || GCC_SUPPORTS_DYNAMIC_FTRACE)
+	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
 	select HAVE_FUNCTION_GRAPH_TRACER
@@ -140,6 +145,8 @@ config RISCV
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RETHOOK if !XIP_KERNEL
 	select HAVE_RSEQ
+	select HAVE_SAMPLE_FTRACE_DIRECT
+	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU
@@ -181,6 +188,20 @@ config HAVE_SHADOW_CALL_STACK
 	# https://github.com/riscv-non-isa/riscv-elf-psabi-doc/commit/a484e843e6eeb51f0cb7b8819e50da6d2444d769
 	depends on $(ld-option,--no-relax-gp)
 
+config RISCV_USE_LINKER_RELAXATION
+	def_bool y
+	# https://github.com/llvm/llvm-project/commit/6611d58f5bbcbec77262d392e2923e1d680f6985
+	depends on !LD_IS_LLD || LLD_VERSION >= 150000
+
+# https://github.com/llvm/llvm-project/commit/bbc0f99f3bc96f1db16f649fc21dd18e5b0918f6
+config ARCH_HAS_BROKEN_DWARF5
+	def_bool y
+	depends on RISCV_USE_LINKER_RELAXATION
+	# https://github.com/llvm/llvm-project/commit/1df5ea29b43690b6622db2cad7b745607ca4de6a
+	depends on AS_IS_LLVM && AS_VERSION < 180000
+	# https://github.com/llvm/llvm-project/commit/7ffabb61a5569444b5ac9322e22e5471cc5e4a77
+	depends on LD_IS_LLD && LLD_VERSION < 180000
+
 config ARCH_MMAP_RND_BITS_MIN
 	default 18 if 64BIT
 	default 8
@@ -294,7 +315,6 @@ config AS_HAS_OPTION_ARCH
 	# https://reviews.llvm.org/D123515
 	def_bool y
 	depends on $(as-instr, .option arch$(comma) +m)
-	depends on !$(as-instr, .option arch$(comma) -i)
 
 source "arch/riscv/Kconfig.socs"
 source "arch/riscv/Kconfig.errata"
@@ -414,7 +434,9 @@ config NUMA
 	depends on SMP && MMU
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select GENERIC_ARCH_NUMA
+	select HAVE_SETUP_PER_CPU_AREA
 	select NEED_PER_CPU_EMBED_FIRST_CHUNK
+	select NEED_PER_CPU_PAGE_FIRST_CHUNK
 	select OF_NUMA
 	select USE_PERCPU_NUMA_NODE_ID
 	help
@@ -525,6 +547,28 @@ config RISCV_ISA_V_DEFAULT_ENABLE
 
 	  If you don't know what to do here, say Y.
 
+config RISCV_ISA_V_UCOPY_THRESHOLD
+	int "Threshold size for vectorized user copies"
+	depends on RISCV_ISA_V
+	default 768
+	help
+	  Prefer using vectorized copy_to_user()/copy_from_user() when the
+	  workload size exceeds this value.
+
+config RISCV_ISA_V_PREEMPTIVE
+	bool "Run kernel-mode Vector with kernel preemption"
+	depends on PREEMPTION
+	depends on RISCV_ISA_V
+	default y
+	help
+	  Usually, in-kernel SIMD routines are run with preemption disabled.
+	  Functions which envoke long running SIMD thus must yield core's
+	  vector unit to prevent blocking other tasks for too long.
+
+	  This config allows kernel to run SIMD without explicitly disable
+	  preemption. Enabling this config will result in higher memory
+	  consumption due to the allocation of per-task's kernel Vector context.
+
 config TOOLCHAIN_HAS_ZBB
 	bool
 	default y
@@ -651,6 +695,20 @@ config RISCV_MISALIGNED
 	  load/store for both kernel and userspace. When disable, misaligned
 	  accesses will generate SIGBUS in userspace and panic in kernel.
 
+config RISCV_EFFICIENT_UNALIGNED_ACCESS
+	bool "Assume the CPU supports fast unaligned memory accesses"
+	depends on NONPORTABLE
+	select DCACHE_WORD_ACCESS if MMU
+	select HAVE_EFFICIENT_UNALIGNED_ACCESS
+	help
+	  Say Y here if you want the kernel to assume that the CPU supports
+	  efficient unaligned memory accesses.  When enabled, this option
+	  improves the performance of the kernel on such CPUs.  However, the
+	  kernel will run much more slowly, or will not be able to run at all,
+	  on CPUs that do not support efficient unaligned memory accesses.
+
+	  If unsure what to do here, say N.
+
 endmenu # "Platform type"
 
 menu "Kernel features"
@@ -722,6 +780,25 @@ config COMPAT
 
 	  If you want to execute 32-bit userspace applications, say Y.
 
+config PARAVIRT
+	bool "Enable paravirtualization code"
+	depends on RISCV_SBI
+	help
+	  This changes the kernel so it can modify itself when it is run
+	  under a hypervisor, potentially improving performance significantly
+	  over full virtualization.
+
+config PARAVIRT_TIME_ACCOUNTING
+	bool "Paravirtual steal time accounting"
+	depends on PARAVIRT
+	help
+	  Select this option to enable fine granularity task steal time
+	  accounting. Time spent executing other tasks in parallel with
+	  the current vCPU is discounted from the vCPU power. To account for
+	  that, there can be a small performance impact.
+
+	  If in doubt, say N here.
+
 config RELOCATABLE
 	bool "Build a relocatable kernel"
 	depends on MMU && 64BIT && !XIP_KERNEL
@@ -902,13 +979,13 @@ config RISCV_ISA_FALLBACK
 	  on the replacement properties, "riscv,isa-base" and
 	  "riscv,isa-extensions".
 
-endmenu # "Boot options"
-
 config BUILTIN_DTB
-	bool
+	bool "Built-in device tree"
 	depends on OF && NONPORTABLE
 	default y if XIP_KERNEL
 
+endmenu # "Boot options"
+
 config PORTABLE
 	bool
 	default !NONPORTABLE
diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata
index f5c432b005e7..910ba8837add 100644
--- a/arch/riscv/Kconfig.errata
+++ b/arch/riscv/Kconfig.errata
@@ -98,6 +98,7 @@ config ERRATA_THEAD_CMO
 	depends on ERRATA_THEAD && MMU
 	select DMA_DIRECT_REMAP
 	select RISCV_DMA_NONCOHERENT
+	select RISCV_NONSTANDARD_CACHE_OPS
 	default y
 	help
 	  This will apply the cache management errata to handle the
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index a74be78678eb..0b7d109258e7 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -43,8 +43,7 @@ else
 	KBUILD_LDFLAGS += -melf32lriscv
 endif
 
-ifeq ($(CONFIG_LD_IS_LLD),y)
-ifeq ($(call test-lt, $(CONFIG_LLD_VERSION), 150000),y)
+ifndef CONFIG_RISCV_USE_LINKER_RELAXATION
 	KBUILD_CFLAGS += -mno-relax
 	KBUILD_AFLAGS += -mno-relax
 ifndef CONFIG_AS_IS_LLVM
@@ -52,7 +51,6 @@ ifndef CONFIG_AS_IS_LLVM
 	KBUILD_AFLAGS += -Wa,-mno-relax
 endif
 endif
-endif
 
 ifeq ($(CONFIG_SHADOW_CALL_STACK),y)
 	KBUILD_LDFLAGS += --no-relax-gp
@@ -108,7 +106,9 @@ KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax)
 # unaligned accesses.  While unaligned accesses are explicitly allowed in the
 # RISC-V ISA, they're emulated by machine mode traps on all extant
 # architectures.  It's faster to have GCC emit only aligned accesses.
+ifneq ($(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS),y)
 KBUILD_CFLAGS += $(call cc-option,-mstrict-align)
+endif
 
 ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y)
 prepare: stack_protector_prepare
@@ -163,6 +163,8 @@ BOOT_TARGETS := Image Image.gz loader loader.bin xipImage vmlinuz.efi
 
 all:	$(notdir $(KBUILD_IMAGE))
 
+loader.bin: loader
+Image.gz loader vmlinuz.efi: Image
 $(BOOT_TARGETS): vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 	@$(kecho) '  Kernel: $(boot)/$@ is ready'
diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts
index 07387f9c135c..72b87b08ab44 100644
--- a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts
+++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts
@@ -123,6 +123,7 @@
 		interrupt-parent = <&gpio>;
 		interrupts = <1 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 
 		onkey {
 			compatible = "dlg,da9063-onkey";
diff --git a/arch/riscv/boot/dts/sophgo/sg2042.dtsi b/arch/riscv/boot/dts/sophgo/sg2042.dtsi
index 93256540d078..ead1cc35d88b 100644
--- a/arch/riscv/boot/dts/sophgo/sg2042.dtsi
+++ b/arch/riscv/boot/dts/sophgo/sg2042.dtsi
@@ -93,144 +93,160 @@
 					      <&cpu63_intc 3>;
 		};
 
-		clint_mtimer0: timer@70ac000000 {
+		clint_mtimer0: timer@70ac004000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac000000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac004000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu0_intc 7>,
 					      <&cpu1_intc 7>,
 					      <&cpu2_intc 7>,
 					      <&cpu3_intc 7>;
 		};
 
-		clint_mtimer1: timer@70ac010000 {
+		clint_mtimer1: timer@70ac014000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac010000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac014000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu4_intc 7>,
 					      <&cpu5_intc 7>,
 					      <&cpu6_intc 7>,
 					      <&cpu7_intc 7>;
 		};
 
-		clint_mtimer2: timer@70ac020000 {
+		clint_mtimer2: timer@70ac024000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac020000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac024000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu8_intc 7>,
 					      <&cpu9_intc 7>,
 					      <&cpu10_intc 7>,
 					      <&cpu11_intc 7>;
 		};
 
-		clint_mtimer3: timer@70ac030000 {
+		clint_mtimer3: timer@70ac034000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac030000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac034000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu12_intc 7>,
 					      <&cpu13_intc 7>,
 					      <&cpu14_intc 7>,
 					      <&cpu15_intc 7>;
 		};
 
-		clint_mtimer4: timer@70ac040000 {
+		clint_mtimer4: timer@70ac044000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac040000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac044000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu16_intc 7>,
 					      <&cpu17_intc 7>,
 					      <&cpu18_intc 7>,
 					      <&cpu19_intc 7>;
 		};
 
-		clint_mtimer5: timer@70ac050000 {
+		clint_mtimer5: timer@70ac054000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac050000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac054000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu20_intc 7>,
 					      <&cpu21_intc 7>,
 					      <&cpu22_intc 7>,
 					      <&cpu23_intc 7>;
 		};
 
-		clint_mtimer6: timer@70ac060000 {
+		clint_mtimer6: timer@70ac064000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac060000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac064000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu24_intc 7>,
 					      <&cpu25_intc 7>,
 					      <&cpu26_intc 7>,
 					      <&cpu27_intc 7>;
 		};
 
-		clint_mtimer7: timer@70ac070000 {
+		clint_mtimer7: timer@70ac074000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac070000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac074000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu28_intc 7>,
 					      <&cpu29_intc 7>,
 					      <&cpu30_intc 7>,
 					      <&cpu31_intc 7>;
 		};
 
-		clint_mtimer8: timer@70ac080000 {
+		clint_mtimer8: timer@70ac084000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac080000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac084000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu32_intc 7>,
 					      <&cpu33_intc 7>,
 					      <&cpu34_intc 7>,
 					      <&cpu35_intc 7>;
 		};
 
-		clint_mtimer9: timer@70ac090000 {
+		clint_mtimer9: timer@70ac094000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac090000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac094000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu36_intc 7>,
 					      <&cpu37_intc 7>,
 					      <&cpu38_intc 7>,
 					      <&cpu39_intc 7>;
 		};
 
-		clint_mtimer10: timer@70ac0a0000 {
+		clint_mtimer10: timer@70ac0a4000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac0a0000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac0a4000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu40_intc 7>,
 					      <&cpu41_intc 7>,
 					      <&cpu42_intc 7>,
 					      <&cpu43_intc 7>;
 		};
 
-		clint_mtimer11: timer@70ac0b0000 {
+		clint_mtimer11: timer@70ac0b4000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac0b0000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac0b4000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu44_intc 7>,
 					      <&cpu45_intc 7>,
 					      <&cpu46_intc 7>,
 					      <&cpu47_intc 7>;
 		};
 
-		clint_mtimer12: timer@70ac0c0000 {
+		clint_mtimer12: timer@70ac0c4000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac0c0000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac0c4000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu48_intc 7>,
 					      <&cpu49_intc 7>,
 					      <&cpu50_intc 7>,
 					      <&cpu51_intc 7>;
 		};
 
-		clint_mtimer13: timer@70ac0d0000 {
+		clint_mtimer13: timer@70ac0d4000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac0d0000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac0d4000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu52_intc 7>,
 					      <&cpu53_intc 7>,
 					      <&cpu54_intc 7>,
 					      <&cpu55_intc 7>;
 		};
 
-		clint_mtimer14: timer@70ac0e0000 {
+		clint_mtimer14: timer@70ac0e4000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac0e0000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac0e4000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu56_intc 7>,
 					      <&cpu57_intc 7>,
 					      <&cpu58_intc 7>,
 					      <&cpu59_intc 7>;
 		};
 
-		clint_mtimer15: timer@70ac0f0000 {
+		clint_mtimer15: timer@70ac0f4000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac0f0000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac0f4000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu60_intc 7>,
 					      <&cpu61_intc 7>,
 					      <&cpu62_intc 7>,
diff --git a/arch/riscv/boot/dts/starfive/jh7100.dtsi b/arch/riscv/boot/dts/starfive/jh7100.dtsi
index c216aaecac53..8bcf36d07f3f 100644
--- a/arch/riscv/boot/dts/starfive/jh7100.dtsi
+++ b/arch/riscv/boot/dts/starfive/jh7100.dtsi
@@ -96,14 +96,14 @@
 			thermal-sensors = <&sfctemp>;
 
 			trips {
-				cpu_alert0 {
+				cpu-alert0 {
 					/* milliCelsius */
 					temperature = <75000>;
 					hysteresis = <2000>;
 					type = "passive";
 				};
 
-				cpu_crit {
+				cpu-crit {
 					/* milliCelsius */
 					temperature = <90000>;
 					hysteresis = <2000>;
@@ -113,28 +113,28 @@
 		};
 	};
 
-	osc_sys: osc_sys {
+	osc_sys: osc-sys {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
 	};
 
-	osc_aud: osc_aud {
+	osc_aud: osc-aud {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
 	};
 
-	gmac_rmii_ref: gmac_rmii_ref {
+	gmac_rmii_ref: gmac-rmii-ref {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		/* Should be overridden by the board when needed */
 		clock-frequency = <0>;
 	};
 
-	gmac_gr_mii_rxclk: gmac_gr_mii_rxclk {
+	gmac_gr_mii_rxclk: gmac-gr-mii-rxclk {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		/* Should be overridden by the board when needed */
diff --git a/arch/riscv/boot/dts/starfive/jh7110.dtsi b/arch/riscv/boot/dts/starfive/jh7110.dtsi
index 45213cdf50dc..74ed3b9264d8 100644
--- a/arch/riscv/boot/dts/starfive/jh7110.dtsi
+++ b/arch/riscv/boot/dts/starfive/jh7110.dtsi
@@ -237,14 +237,14 @@
 			};
 
 			trips {
-				cpu_alert0: cpu_alert0 {
+				cpu_alert0: cpu-alert0 {
 					/* milliCelsius */
 					temperature = <85000>;
 					hysteresis = <2000>;
 					type = "passive";
 				};
 
-				cpu_crit {
+				cpu-crit {
 					/* milliCelsius */
 					temperature = <100000>;
 					hysteresis = <2000>;
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index 905881282a7c..eaf34e871e30 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -149,6 +149,7 @@ CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_DW=y
 CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_SH_SCI=y
+CONFIG_SERIAL_EARLYCON_RISCV_SBI=y
 CONFIG_VIRTIO_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_HW_RANDOM_VIRTIO=y
diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig
deleted file mode 100644
index 89b601e253a6..000000000000
--- a/arch/riscv/configs/rv32_defconfig
+++ /dev/null
@@ -1,139 +0,0 @@
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ_IDLE=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_BPF_SYSCALL=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_CGROUPS=y
-CONFIG_CGROUP_SCHED=y
-CONFIG_CFS_BANDWIDTH=y
-CONFIG_CGROUP_BPF=y
-CONFIG_NAMESPACES=y
-CONFIG_USER_NS=y
-CONFIG_CHECKPOINT_RESTORE=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-# CONFIG_SYSFS_SYSCALL is not set
-CONFIG_PROFILING=y
-CONFIG_SOC_SIFIVE=y
-CONFIG_SOC_VIRT=y
-CONFIG_NONPORTABLE=y
-CONFIG_ARCH_RV32I=y
-CONFIG_SMP=y
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PM=y
-CONFIG_CPU_IDLE=y
-CONFIG_VIRTUALIZATION=y
-CONFIG_KVM=m
-CONFIG_JUMP_LABEL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_IP_PNP_RARP=y
-CONFIG_NETLINK_DIAG=y
-CONFIG_NET_9P=y
-CONFIG_NET_9P_VIRTIO=y
-CONFIG_PCI=y
-CONFIG_PCIEPORTBUS=y
-CONFIG_PCI_HOST_GENERIC=y
-CONFIG_PCIE_XILINX=y
-CONFIG_DEVTMPFS=y
-CONFIG_DEVTMPFS_MOUNT=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_VIRTIO_BLK=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_BLK_DEV_SR=y
-CONFIG_SCSI_VIRTIO=y
-CONFIG_ATA=y
-CONFIG_SATA_AHCI=y
-CONFIG_SATA_AHCI_PLATFORM=y
-CONFIG_NETDEVICES=y
-CONFIG_VIRTIO_NET=y
-CONFIG_MACB=y
-CONFIG_E1000E=y
-CONFIG_R8169=y
-CONFIG_MICROSEMI_PHY=y
-CONFIG_INPUT_MOUSEDEV=y
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_OF_PLATFORM=y
-CONFIG_VIRTIO_CONSOLE=y
-CONFIG_HW_RANDOM=y
-CONFIG_HW_RANDOM_VIRTIO=y
-CONFIG_SPI=y
-CONFIG_SPI_SIFIVE=y
-# CONFIG_PTP_1588_CLOCK is not set
-CONFIG_DRM=y
-CONFIG_DRM_RADEON=y
-CONFIG_DRM_VIRTIO_GPU=y
-CONFIG_FB=y
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_USB=y
-CONFIG_USB_XHCI_HCD=y
-CONFIG_USB_XHCI_PLATFORM=y
-CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_EHCI_HCD_PLATFORM=y
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_OHCI_HCD_PLATFORM=y
-CONFIG_USB_STORAGE=y
-CONFIG_USB_UAS=y
-CONFIG_MMC=y
-CONFIG_MMC_SPI=y
-CONFIG_RTC_CLASS=y
-CONFIG_VIRTIO_PCI=y
-CONFIG_VIRTIO_BALLOON=y
-CONFIG_VIRTIO_INPUT=y
-CONFIG_VIRTIO_MMIO=y
-CONFIG_RPMSG_CHAR=y
-CONFIG_RPMSG_CTRL=y
-CONFIG_RPMSG_VIRTIO=y
-CONFIG_EXT4_FS=y
-CONFIG_EXT4_FS_POSIX_ACL=y
-CONFIG_AUTOFS_FS=y
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_TMPFS=y
-CONFIG_TMPFS_POSIX_ACL=y
-CONFIG_HUGETLBFS=y
-CONFIG_NFS_FS=y
-CONFIG_NFS_V4=y
-CONFIG_NFS_V4_1=y
-CONFIG_NFS_V4_2=y
-CONFIG_ROOT_NFS=y
-CONFIG_9P_FS=y
-CONFIG_CRYPTO_USER_API_HASH=y
-CONFIG_CRYPTO_DEV_VIRTIO=y
-CONFIG_PRINTK_TIME=y
-CONFIG_DEBUG_FS=y
-CONFIG_DEBUG_PAGEALLOC=y
-CONFIG_SCHED_STACK_END_CHECK=y
-CONFIG_DEBUG_VM=y
-CONFIG_DEBUG_VM_PGFLAGS=y
-CONFIG_DEBUG_MEMORY_INIT=y
-CONFIG_DEBUG_PER_CPU_MAPS=y
-CONFIG_SOFTLOCKUP_DETECTOR=y
-CONFIG_WQ_WATCHDOG=y
-CONFIG_DEBUG_TIMEKEEPING=y
-CONFIG_DEBUG_RT_MUTEXES=y
-CONFIG_DEBUG_SPINLOCK=y
-CONFIG_DEBUG_MUTEXES=y
-CONFIG_DEBUG_RWSEMS=y
-CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_STACKTRACE=y
-CONFIG_DEBUG_LIST=y
-CONFIG_DEBUG_PLIST=y
-CONFIG_DEBUG_SG=y
-# CONFIG_RCU_TRACE is not set
-CONFIG_RCU_EQS_DEBUG=y
-# CONFIG_FTRACE is not set
-# CONFIG_RUNTIME_TESTING_MENU is not set
-CONFIG_MEMTEST=y
diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c
index 0554ed4bf087..b1c410bbc1ae 100644
--- a/arch/riscv/errata/thead/errata.c
+++ b/arch/riscv/errata/thead/errata.c
@@ -12,8 +12,10 @@
 #include <asm/alternative.h>
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
+#include <asm/dma-noncoherent.h>
 #include <asm/errata_list.h>
 #include <asm/hwprobe.h>
+#include <asm/io.h>
 #include <asm/patch.h>
 #include <asm/vendorid_list.h>
 
@@ -33,6 +35,69 @@ static bool errata_probe_pbmt(unsigned int stage,
 	return false;
 }
 
+/*
+ * th.dcache.ipa rs1 (invalidate, physical address)
+ * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ *   0000001    01010      rs1       000      00000  0001011
+ * th.dcache.iva rs1 (invalidate, virtual address)
+ *   0000001    00110      rs1       000      00000  0001011
+ *
+ * th.dcache.cpa rs1 (clean, physical address)
+ * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ *   0000001    01001      rs1       000      00000  0001011
+ * th.dcache.cva rs1 (clean, virtual address)
+ *   0000001    00101      rs1       000      00000  0001011
+ *
+ * th.dcache.cipa rs1 (clean then invalidate, physical address)
+ * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ *   0000001    01011      rs1       000      00000  0001011
+ * th.dcache.civa rs1 (clean then invalidate, virtual address)
+ *   0000001    00111      rs1       000      00000  0001011
+ *
+ * th.sync.s (make sure all cache operations finished)
+ * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ *   0000000    11001     00000      000      00000  0001011
+ */
+#define THEAD_INVAL_A0	".long 0x02a5000b"
+#define THEAD_CLEAN_A0	".long 0x0295000b"
+#define THEAD_FLUSH_A0	".long 0x02b5000b"
+#define THEAD_SYNC_S	".long 0x0190000b"
+
+#define THEAD_CMO_OP(_op, _start, _size, _cachesize)			\
+asm volatile("mv a0, %1\n\t"						\
+	     "j 2f\n\t"							\
+	     "3:\n\t"							\
+	     THEAD_##_op##_A0 "\n\t"					\
+	     "add a0, a0, %0\n\t"					\
+	     "2:\n\t"							\
+	     "bltu a0, %2, 3b\n\t"					\
+	     THEAD_SYNC_S						\
+	     : : "r"(_cachesize),					\
+		 "r"((unsigned long)(_start) & ~((_cachesize) - 1UL)),	\
+		 "r"((unsigned long)(_start) + (_size))			\
+	     : "a0")
+
+static void thead_errata_cache_inv(phys_addr_t paddr, size_t size)
+{
+	THEAD_CMO_OP(INVAL, paddr, size, riscv_cbom_block_size);
+}
+
+static void thead_errata_cache_wback(phys_addr_t paddr, size_t size)
+{
+	THEAD_CMO_OP(CLEAN, paddr, size, riscv_cbom_block_size);
+}
+
+static void thead_errata_cache_wback_inv(phys_addr_t paddr, size_t size)
+{
+	THEAD_CMO_OP(FLUSH, paddr, size, riscv_cbom_block_size);
+}
+
+static const struct riscv_nonstd_cache_ops thead_errata_cmo_ops = {
+	.wback = &thead_errata_cache_wback,
+	.inv = &thead_errata_cache_inv,
+	.wback_inv = &thead_errata_cache_wback_inv,
+};
+
 static bool errata_probe_cmo(unsigned int stage,
 			     unsigned long arch_id, unsigned long impid)
 {
@@ -48,6 +113,7 @@ static bool errata_probe_cmo(unsigned int stage,
 	if (stage == RISCV_ALTERNATIVES_BOOT) {
 		riscv_cbom_block_size = L1_CACHE_BYTES;
 		riscv_noncoherent_supported();
+		riscv_noncoherent_register_cache_ops(&thead_errata_cmo_ops);
 	}
 
 	return true;
@@ -77,8 +143,7 @@ static u32 thead_errata_probe(unsigned int stage,
 	if (errata_probe_pbmt(stage, archid, impid))
 		cpu_req_errata |= BIT(ERRATA_THEAD_PBMT);
 
-	if (errata_probe_cmo(stage, archid, impid))
-		cpu_req_errata |= BIT(ERRATA_THEAD_CMO);
+	errata_probe_cmo(stage, archid, impid);
 
 	if (errata_probe_pmu(stage, archid, impid))
 		cpu_req_errata |= BIT(ERRATA_THEAD_PMU);
diff --git a/arch/riscv/include/asm/arch_hweight.h b/arch/riscv/include/asm/arch_hweight.h
new file mode 100644
index 000000000000..85b2c443823e
--- /dev/null
+++ b/arch/riscv/include/asm/arch_hweight.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Based on arch/x86/include/asm/arch_hweight.h
+ */
+
+#ifndef _ASM_RISCV_HWEIGHT_H
+#define _ASM_RISCV_HWEIGHT_H
+
+#include <asm/alternative-macros.h>
+#include <asm/hwcap.h>
+
+#if (BITS_PER_LONG == 64)
+#define CPOPW	"cpopw "
+#elif (BITS_PER_LONG == 32)
+#define CPOPW	"cpop "
+#else
+#error "Unexpected BITS_PER_LONG"
+#endif
+
+static __always_inline unsigned int __arch_hweight32(unsigned int w)
+{
+#ifdef CONFIG_RISCV_ISA_ZBB
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+				      RISCV_ISA_EXT_ZBB, 1)
+			  : : : : legacy);
+
+	asm (".option push\n"
+	     ".option arch,+zbb\n"
+	     CPOPW "%0, %0\n"
+	     ".option pop\n"
+	     : "+r" (w) : :);
+
+	return w;
+
+legacy:
+#endif
+	return __sw_hweight32(w);
+}
+
+static inline unsigned int __arch_hweight16(unsigned int w)
+{
+	return __arch_hweight32(w & 0xffff);
+}
+
+static inline unsigned int __arch_hweight8(unsigned int w)
+{
+	return __arch_hweight32(w & 0xff);
+}
+
+#if BITS_PER_LONG == 64
+static __always_inline unsigned long __arch_hweight64(__u64 w)
+{
+# ifdef CONFIG_RISCV_ISA_ZBB
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+				      RISCV_ISA_EXT_ZBB, 1)
+			  : : : : legacy);
+
+	asm (".option push\n"
+	     ".option arch,+zbb\n"
+	     "cpop %0, %0\n"
+	     ".option pop\n"
+	     : "+r" (w) : :);
+
+	return w;
+
+legacy:
+# endif
+	return __sw_hweight64(w);
+}
+#else /* BITS_PER_LONG == 64 */
+static inline unsigned long __arch_hweight64(__u64 w)
+{
+	return  __arch_hweight32((u32)w) +
+		__arch_hweight32((u32)(w >> 32));
+}
+#endif /* !(BITS_PER_LONG == 64) */
+
+#endif /* _ASM_RISCV_HWEIGHT_H */
diff --git a/arch/riscv/include/asm/archrandom.h b/arch/riscv/include/asm/archrandom.h
new file mode 100644
index 000000000000..5345360adfb9
--- /dev/null
+++ b/arch/riscv/include/asm/archrandom.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Kernel interface for the RISCV arch_random_* functions
+ *
+ * Copyright (c) 2023 Rivos Inc.
+ *
+ */
+
+#ifndef ASM_RISCV_ARCHRANDOM_H
+#define ASM_RISCV_ARCHRANDOM_H
+
+#include <asm/csr.h>
+#include <asm/processor.h>
+
+#define SEED_RETRY_LOOPS 100
+
+static inline bool __must_check csr_seed_long(unsigned long *v)
+{
+	unsigned int retry = SEED_RETRY_LOOPS, valid_seeds = 0;
+	const int needed_seeds = sizeof(long) / sizeof(u16);
+	u16 *entropy = (u16 *)v;
+
+	do {
+		/*
+		 * The SEED CSR must be accessed with a read-write instruction.
+		 */
+		unsigned long csr_seed = csr_swap(CSR_SEED, 0);
+		unsigned long opst = csr_seed & SEED_OPST_MASK;
+
+		switch (opst) {
+		case SEED_OPST_ES16:
+			entropy[valid_seeds++] = csr_seed & SEED_ENTROPY_MASK;
+			if (valid_seeds == needed_seeds)
+				return true;
+			break;
+
+		case SEED_OPST_DEAD:
+			pr_err_once("archrandom: Unrecoverable error\n");
+			return false;
+
+		case SEED_OPST_BIST:
+		case SEED_OPST_WAIT:
+		default:
+			cpu_relax();
+			continue;
+		}
+	} while (--retry);
+
+	return false;
+}
+
+static inline size_t __must_check arch_get_random_longs(unsigned long *v, size_t max_longs)
+{
+	return 0;
+}
+
+static inline size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs)
+{
+	if (!max_longs)
+		return 0;
+
+	/*
+	 * If Zkr is supported and csr_seed_long succeeds, we return one long
+	 * worth of entropy.
+	 */
+	if (riscv_has_extension_likely(RISCV_ISA_EXT_ZKR) && csr_seed_long(v))
+		return 1;
+
+	return 0;
+}
+
+#endif /* ASM_RISCV_ARCHRANDOM_H */
diff --git a/arch/riscv/include/asm/asm-extable.h b/arch/riscv/include/asm/asm-extable.h
index 00a96e7a9664..0c8bfd54fc4e 100644
--- a/arch/riscv/include/asm/asm-extable.h
+++ b/arch/riscv/include/asm/asm-extable.h
@@ -6,6 +6,7 @@
 #define EX_TYPE_FIXUP			1
 #define EX_TYPE_BPF			2
 #define EX_TYPE_UACCESS_ERR_ZERO	3
+#define EX_TYPE_LOAD_UNALIGNED_ZEROPAD	4
 
 #ifdef CONFIG_MMU
 
@@ -47,6 +48,11 @@
 #define EX_DATA_REG_ZERO_SHIFT	5
 #define EX_DATA_REG_ZERO	GENMASK(9, 5)
 
+#define EX_DATA_REG_DATA_SHIFT	0
+#define EX_DATA_REG_DATA	GENMASK(4, 0)
+#define EX_DATA_REG_ADDR_SHIFT	5
+#define EX_DATA_REG_ADDR	GENMASK(9, 5)
+
 #define EX_DATA_REG(reg, gpr)						\
 	"((.L__gpr_num_" #gpr ") << " __stringify(EX_DATA_REG_##reg##_SHIFT) ")"
 
@@ -62,6 +68,15 @@
 #define _ASM_EXTABLE_UACCESS_ERR(insn, fixup, err)			\
 	_ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, zero)
 
+#define _ASM_EXTABLE_LOAD_UNALIGNED_ZEROPAD(insn, fixup, data, addr)		\
+	__DEFINE_ASM_GPR_NUMS							\
+	__ASM_EXTABLE_RAW(#insn, #fixup,					\
+			  __stringify(EX_TYPE_LOAD_UNALIGNED_ZEROPAD),		\
+			  "("							\
+			    EX_DATA_REG(DATA, data) " | "			\
+			    EX_DATA_REG(ADDR, addr)				\
+			  ")")
+
 #endif /* __ASSEMBLY__ */
 
 #else /* CONFIG_MMU */
diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h
index 36b955c762ba..cd627ec289f1 100644
--- a/arch/riscv/include/asm/asm-prototypes.h
+++ b/arch/riscv/include/asm/asm-prototypes.h
@@ -9,6 +9,33 @@ long long __lshrti3(long long a, int b);
 long long __ashrti3(long long a, int b);
 long long __ashlti3(long long a, int b);
 
+#ifdef CONFIG_RISCV_ISA_V
+
+#ifdef CONFIG_MMU
+asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n);
+#endif /* CONFIG_MMU  */
+
+void xor_regs_2_(unsigned long bytes, unsigned long *__restrict p1,
+		 const unsigned long *__restrict p2);
+void xor_regs_3_(unsigned long bytes, unsigned long *__restrict p1,
+		 const unsigned long *__restrict p2,
+		 const unsigned long *__restrict p3);
+void xor_regs_4_(unsigned long bytes, unsigned long *__restrict p1,
+		 const unsigned long *__restrict p2,
+		 const unsigned long *__restrict p3,
+		 const unsigned long *__restrict p4);
+void xor_regs_5_(unsigned long bytes, unsigned long *__restrict p1,
+		 const unsigned long *__restrict p2,
+		 const unsigned long *__restrict p3,
+		 const unsigned long *__restrict p4,
+		 const unsigned long *__restrict p5);
+
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs);
+asmlinkage void riscv_v_context_nesting_end(struct pt_regs *regs);
+#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */
+
+#endif /* CONFIG_RISCV_ISA_V */
 
 #define DECLARE_DO_ERROR_INFO(name)	asmlinkage void name(struct pt_regs *regs)
 
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
index 224b4dc02b50..329d8244a9b3 100644
--- a/arch/riscv/include/asm/bitops.h
+++ b/arch/riscv/include/asm/bitops.h
@@ -39,7 +39,7 @@ static __always_inline unsigned long variable__ffs(unsigned long word)
 {
 	int num;
 
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
@@ -95,7 +95,7 @@ static __always_inline unsigned long variable__fls(unsigned long word)
 {
 	int num;
 
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
@@ -154,7 +154,7 @@ static __always_inline int variable_ffs(int x)
 	if (!x)
 		return 0;
 
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
@@ -209,7 +209,7 @@ static __always_inline int variable_fls(unsigned int x)
 	if (!x)
 		return 0;
 
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
@@ -271,7 +271,9 @@ legacy:
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/sched.h>
 
-#include <asm-generic/bitops/hweight.h>
+#include <asm/arch_hweight.h>
+
+#include <asm-generic/bitops/const_hweight.h>
 
 #if (BITS_PER_LONG == 64)
 #define __AMO(op)	"amo" #op ".d"
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index 3cb53c4df27c..a129dac4521d 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -37,7 +37,8 @@ static inline void flush_dcache_page(struct page *page)
 	flush_icache_mm(vma->vm_mm, 0)
 
 #ifdef CONFIG_64BIT
-#define flush_cache_vmap(start, end)	flush_tlb_kernel_range(start, end)
+#define flush_cache_vmap(start, end)		flush_tlb_kernel_range(start, end)
+#define flush_cache_vmap_early(start, end)	local_flush_tlb_kernel_range(start, end)
 #endif
 
 #ifndef CONFIG_SMP
diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h
new file mode 100644
index 000000000000..88e6f1499e88
--- /dev/null
+++ b/arch/riscv/include/asm/checksum.h
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Checksum routines
+ *
+ * Copyright (C) 2023 Rivos Inc.
+ */
+#ifndef __ASM_RISCV_CHECKSUM_H
+#define __ASM_RISCV_CHECKSUM_H
+
+#include <linux/in6.h>
+#include <linux/uaccess.h>
+
+#define ip_fast_csum ip_fast_csum
+
+extern unsigned int do_csum(const unsigned char *buff, int len);
+#define do_csum do_csum
+
+/* Default version is sufficient for 32 bit */
+#ifndef CONFIG_32BIT
+#define _HAVE_ARCH_IPV6_CSUM
+__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+			const struct in6_addr *daddr,
+			__u32 len, __u8 proto, __wsum sum);
+#endif
+
+/* Define riscv versions of functions before importing asm-generic/checksum.h */
+#include <asm-generic/checksum.h>
+
+/**
+ * Quickly compute an IP checksum with the assumption that IPv4 headers will
+ * always be in multiples of 32-bits, and have an ihl of at least 5.
+ *
+ * @ihl: the number of 32 bit segments and must be greater than or equal to 5.
+ * @iph: assumed to be word aligned given that NET_IP_ALIGN is set to 2 on
+ *  riscv, defining IP headers to be aligned.
+ */
+static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+	unsigned long csum = 0;
+	int pos = 0;
+
+	do {
+		csum += ((const unsigned int *)iph)[pos];
+		if (IS_ENABLED(CONFIG_32BIT))
+			csum += csum < ((const unsigned int *)iph)[pos];
+	} while (++pos < ihl);
+
+	/*
+	 * ZBB only saves three instructions on 32-bit and five on 64-bit so not
+	 * worth checking if supported without Alternatives.
+	 */
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) &&
+	    IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+		unsigned long fold_temp;
+
+		asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+					      RISCV_ISA_EXT_ZBB, 1)
+		    :
+		    :
+		    :
+		    : no_zbb);
+
+		if (IS_ENABLED(CONFIG_32BIT)) {
+			asm(".option push				\n\
+			.option arch,+zbb				\n\
+				not	%[fold_temp], %[csum]		\n\
+				rori	%[csum], %[csum], 16		\n\
+				sub	%[csum], %[fold_temp], %[csum]	\n\
+			.option pop"
+			: [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp));
+		} else {
+			asm(".option push				\n\
+			.option arch,+zbb				\n\
+				rori	%[fold_temp], %[csum], 32	\n\
+				add	%[csum], %[fold_temp], %[csum]	\n\
+				srli	%[csum], %[csum], 32		\n\
+				not	%[fold_temp], %[csum]		\n\
+				roriw	%[csum], %[csum], 16		\n\
+				subw	%[csum], %[fold_temp], %[csum]	\n\
+			.option pop"
+			: [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp));
+		}
+		return (__force __sum16)(csum >> 16);
+	}
+no_zbb:
+#ifndef CONFIG_32BIT
+	csum += ror64(csum, 32);
+	csum >>= 32;
+#endif
+	return csum_fold((__force __wsum)csum);
+}
+
+#endif /* __ASM_RISCV_CHECKSUM_H */
diff --git a/arch/riscv/include/asm/cpu_ops.h b/arch/riscv/include/asm/cpu_ops.h
index aa128466c4d4..176b570ef982 100644
--- a/arch/riscv/include/asm/cpu_ops.h
+++ b/arch/riscv/include/asm/cpu_ops.h
@@ -13,33 +13,23 @@
 /**
  * struct cpu_operations - Callback operations for hotplugging CPUs.
  *
- * @name:		Name of the boot protocol.
- * @cpu_prepare:	Early one-time preparation step for a cpu. If there
- *			is a mechanism for doing so, tests whether it is
- *			possible to boot the given HART.
  * @cpu_start:		Boots a cpu into the kernel.
- * @cpu_disable:	Prepares a cpu to die. May fail for some
- *			mechanism-specific reason, which will cause the hot
- *			unplug to be aborted. Called from the cpu to be killed.
  * @cpu_stop:		Makes a cpu leave the kernel. Must not fail. Called from
  *			the cpu being stopped.
  * @cpu_is_stopped:	Ensures a cpu has left the kernel. Called from another
  *			cpu.
  */
 struct cpu_operations {
-	const char	*name;
-	int		(*cpu_prepare)(unsigned int cpu);
 	int		(*cpu_start)(unsigned int cpu,
 				     struct task_struct *tidle);
 #ifdef CONFIG_HOTPLUG_CPU
-	int		(*cpu_disable)(unsigned int cpu);
 	void		(*cpu_stop)(void);
 	int		(*cpu_is_stopped)(unsigned int cpu);
 #endif
 };
 
 extern const struct cpu_operations cpu_ops_spinwait;
-extern const struct cpu_operations *cpu_ops[NR_CPUS];
-void __init cpu_set_ops(int cpu);
+extern const struct cpu_operations *cpu_ops;
+void __init cpu_set_ops(void);
 
 #endif /* ifndef __ASM_CPU_OPS_H */
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index a418c3112cd6..0bd11862b760 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -59,6 +59,8 @@ struct riscv_isa_ext_data {
 	const unsigned int id;
 	const char *name;
 	const char *property;
+	const unsigned int *subset_ext_ids;
+	const unsigned int subset_ext_size;
 };
 
 extern const struct riscv_isa_ext_data riscv_isa_ext[];
@@ -67,7 +69,7 @@ extern bool riscv_isa_fallback;
 
 unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap);
 
-bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit);
+bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned int bit);
 #define riscv_isa_extension_available(isa_bitmap, ext)	\
 	__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext)
 
@@ -78,7 +80,7 @@ riscv_has_extension_likely(const unsigned long ext)
 			   "ext must be < RISCV_ISA_EXT_MAX");
 
 	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
-		asm_volatile_goto(
+		asm goto(
 		ALTERNATIVE("j	%l[l_no]", "nop", 0, %[ext], 1)
 		:
 		: [ext] "i" (ext)
@@ -101,7 +103,7 @@ riscv_has_extension_unlikely(const unsigned long ext)
 			   "ext must be < RISCV_ISA_EXT_MAX");
 
 	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
-		asm_volatile_goto(
+		asm goto(
 		ALTERNATIVE("nop", "j	%l[l_yes]", 0, %[ext], 1)
 		:
 		: [ext] "i" (ext)
@@ -133,4 +135,6 @@ static __always_inline bool riscv_cpu_has_extension_unlikely(int cpu, const unsi
 	return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
 }
 
+DECLARE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key);
+
 #endif
diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
index 306a19a5509c..2468c55933cd 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -411,10 +411,20 @@
 #define CSR_VTYPE		0xc21
 #define CSR_VLENB		0xc22
 
+/* Scalar Crypto Extension - Entropy */
+#define CSR_SEED		0x015
+#define SEED_OPST_MASK		_AC(0xC0000000, UL)
+#define SEED_OPST_BIST		_AC(0x00000000, UL)
+#define SEED_OPST_WAIT		_AC(0x40000000, UL)
+#define SEED_OPST_ES16		_AC(0x80000000, UL)
+#define SEED_OPST_DEAD		_AC(0xC0000000, UL)
+#define SEED_ENTROPY_MASK	_AC(0xFFFF, UL)
+
 #ifdef CONFIG_RISCV_M_MODE
 # define CSR_STATUS	CSR_MSTATUS
 # define CSR_IE		CSR_MIE
 # define CSR_TVEC	CSR_MTVEC
+# define CSR_ENVCFG	CSR_MENVCFG
 # define CSR_SCRATCH	CSR_MSCRATCH
 # define CSR_EPC	CSR_MEPC
 # define CSR_CAUSE	CSR_MCAUSE
@@ -439,6 +449,7 @@
 # define CSR_STATUS	CSR_SSTATUS
 # define CSR_IE		CSR_SIE
 # define CSR_TVEC	CSR_STVEC
+# define CSR_ENVCFG	CSR_SENVCFG
 # define CSR_SCRATCH	CSR_SSCRATCH
 # define CSR_EPC	CSR_SEPC
 # define CSR_CAUSE	CSR_SCAUSE
diff --git a/arch/riscv/include/asm/entry-common.h b/arch/riscv/include/asm/entry-common.h
index 7ab5e34318c8..2293e535f865 100644
--- a/arch/riscv/include/asm/entry-common.h
+++ b/arch/riscv/include/asm/entry-common.h
@@ -4,6 +4,23 @@
 #define _ASM_RISCV_ENTRY_COMMON_H
 
 #include <asm/stacktrace.h>
+#include <asm/thread_info.h>
+#include <asm/vector.h>
+
+static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
+						  unsigned long ti_work)
+{
+	if (ti_work & _TIF_RISCV_V_DEFER_RESTORE) {
+		clear_thread_flag(TIF_RISCV_V_DEFER_RESTORE);
+		/*
+		 * We are already called with irq disabled, so go without
+		 * keeping track of riscv_v_flags.
+		 */
+		riscv_v_vstate_restore(&current->thread.vstate, regs);
+	}
+}
+
+#define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare
 
 void handle_page_fault(struct pt_regs *regs);
 void handle_break(struct pt_regs *regs);
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index 83ed25e43553..ea33288f8a25 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -24,9 +24,8 @@
 
 #ifdef CONFIG_ERRATA_THEAD
 #define	ERRATA_THEAD_PBMT 0
-#define	ERRATA_THEAD_CMO 1
-#define	ERRATA_THEAD_PMU 2
-#define	ERRATA_THEAD_NUMBER 3
+#define	ERRATA_THEAD_PMU 1
+#define	ERRATA_THEAD_NUMBER 2
 #endif
 
 #ifdef __ASSEMBLY__
@@ -94,54 +93,17 @@ asm volatile(ALTERNATIVE(						\
 #define ALT_THEAD_PMA(_val)
 #endif
 
-/*
- * th.dcache.ipa rs1 (invalidate, physical address)
- * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
- *   0000001    01010      rs1       000      00000  0001011
- * th.dache.iva rs1 (invalida, virtual address)
- *   0000001    00110      rs1       000      00000  0001011
- *
- * th.dcache.cpa rs1 (clean, physical address)
- * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
- *   0000001    01001      rs1       000      00000  0001011
- * th.dcache.cva rs1 (clean, virtual address)
- *   0000001    00101      rs1       000      00000  0001011
- *
- * th.dcache.cipa rs1 (clean then invalidate, physical address)
- * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
- *   0000001    01011      rs1       000      00000  0001011
- * th.dcache.civa rs1 (... virtual address)
- *   0000001    00111      rs1       000      00000  0001011
- *
- * th.sync.s (make sure all cache operations finished)
- * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
- *   0000000    11001     00000      000      00000  0001011
- */
-#define THEAD_INVAL_A0	".long 0x0265000b"
-#define THEAD_CLEAN_A0	".long 0x0255000b"
-#define THEAD_FLUSH_A0	".long 0x0275000b"
-#define THEAD_SYNC_S	".long 0x0190000b"
-
 #define ALT_CMO_OP(_op, _start, _size, _cachesize)			\
-asm volatile(ALTERNATIVE_2(						\
-	__nops(6),							\
+asm volatile(ALTERNATIVE(						\
+	__nops(5),							\
 	"mv a0, %1\n\t"							\
 	"j 2f\n\t"							\
 	"3:\n\t"							\
 	CBO_##_op(a0)							\
 	"add a0, a0, %0\n\t"						\
 	"2:\n\t"							\
-	"bltu a0, %2, 3b\n\t"						\
-	"nop", 0, RISCV_ISA_EXT_ZICBOM, CONFIG_RISCV_ISA_ZICBOM,	\
-	"mv a0, %1\n\t"							\
-	"j 2f\n\t"							\
-	"3:\n\t"							\
-	THEAD_##_op##_A0 "\n\t"						\
-	"add a0, a0, %0\n\t"						\
-	"2:\n\t"							\
-	"bltu a0, %2, 3b\n\t"						\
-	THEAD_SYNC_S, THEAD_VENDOR_ID,					\
-			ERRATA_THEAD_CMO, CONFIG_ERRATA_THEAD_CMO)	\
+	"bltu a0, %2, 3b\n\t",						\
+	0, RISCV_ISA_EXT_ZICBOM, CONFIG_RISCV_ISA_ZICBOM)		\
 	: : "r"(_cachesize),						\
 	    "r"((unsigned long)(_start) & ~((_cachesize) - 1UL)),	\
 	    "r"((unsigned long)(_start) + (_size))			\
diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
index 2b2f5df7ef2c..15055f9df4da 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -25,6 +25,11 @@
 
 #define ARCH_SUPPORTS_FTRACE_OPS 1
 #ifndef __ASSEMBLY__
+
+extern void *return_address(unsigned int level);
+
+#define ftrace_return_address(n) return_address(n)
+
 void MCOUNT_NAME(void);
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
@@ -128,7 +133,23 @@ do {									\
 struct dyn_ftrace;
 int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
 #define ftrace_init_nop ftrace_init_nop
-#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+struct ftrace_ops;
+struct ftrace_regs;
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *op, struct ftrace_regs *fregs);
+#define ftrace_graph_func ftrace_graph_func
+
+static inline void __arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr)
+{
+		regs->t1 = addr;
+}
+#define arch_ftrace_set_direct_caller(fregs, addr) \
+	__arch_ftrace_set_direct_caller(&(fregs)->regs, addr)
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+
+#endif /* __ASSEMBLY__ */
 
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h
index 4c5b0e929890..22deb7a2a6ec 100644
--- a/arch/riscv/include/asm/hugetlb.h
+++ b/arch/riscv/include/asm/hugetlb.h
@@ -11,6 +11,11 @@ static inline void arch_clear_hugepage_flags(struct page *page)
 }
 #define arch_clear_hugepage_flags arch_clear_hugepage_flags
 
+#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
+bool arch_hugetlb_migration_supported(struct hstate *h);
+#define arch_hugetlb_migration_supported arch_hugetlb_migration_supported
+#endif
+
 #ifdef CONFIG_RISCV_ISA_SVNAPOT
 #define __HAVE_ARCH_HUGE_PTE_CLEAR
 void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 06d30526ef3b..1f2d2599c655 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -11,19 +11,13 @@
 #include <uapi/asm/hwcap.h>
 
 #define RISCV_ISA_EXT_a		('a' - 'a')
-#define RISCV_ISA_EXT_b		('b' - 'a')
 #define RISCV_ISA_EXT_c		('c' - 'a')
 #define RISCV_ISA_EXT_d		('d' - 'a')
 #define RISCV_ISA_EXT_f		('f' - 'a')
 #define RISCV_ISA_EXT_h		('h' - 'a')
 #define RISCV_ISA_EXT_i		('i' - 'a')
-#define RISCV_ISA_EXT_j		('j' - 'a')
-#define RISCV_ISA_EXT_k		('k' - 'a')
 #define RISCV_ISA_EXT_m		('m' - 'a')
-#define RISCV_ISA_EXT_p		('p' - 'a')
 #define RISCV_ISA_EXT_q		('q' - 'a')
-#define RISCV_ISA_EXT_s		('s' - 'a')
-#define RISCV_ISA_EXT_u		('u' - 'a')
 #define RISCV_ISA_EXT_v		('v' - 'a')
 
 /*
@@ -57,8 +51,40 @@
 #define RISCV_ISA_EXT_ZIHPM		42
 #define RISCV_ISA_EXT_SMSTATEEN		43
 #define RISCV_ISA_EXT_ZICOND		44
+#define RISCV_ISA_EXT_ZBC		45
+#define RISCV_ISA_EXT_ZBKB		46
+#define RISCV_ISA_EXT_ZBKC		47
+#define RISCV_ISA_EXT_ZBKX		48
+#define RISCV_ISA_EXT_ZKND		49
+#define RISCV_ISA_EXT_ZKNE		50
+#define RISCV_ISA_EXT_ZKNH		51
+#define RISCV_ISA_EXT_ZKR		52
+#define RISCV_ISA_EXT_ZKSED		53
+#define RISCV_ISA_EXT_ZKSH		54
+#define RISCV_ISA_EXT_ZKT		55
+#define RISCV_ISA_EXT_ZVBB		56
+#define RISCV_ISA_EXT_ZVBC		57
+#define RISCV_ISA_EXT_ZVKB		58
+#define RISCV_ISA_EXT_ZVKG		59
+#define RISCV_ISA_EXT_ZVKNED		60
+#define RISCV_ISA_EXT_ZVKNHA		61
+#define RISCV_ISA_EXT_ZVKNHB		62
+#define RISCV_ISA_EXT_ZVKSED		63
+#define RISCV_ISA_EXT_ZVKSH		64
+#define RISCV_ISA_EXT_ZVKT		65
+#define RISCV_ISA_EXT_ZFH		66
+#define RISCV_ISA_EXT_ZFHMIN		67
+#define RISCV_ISA_EXT_ZIHINTNTL		68
+#define RISCV_ISA_EXT_ZVFH		69
+#define RISCV_ISA_EXT_ZVFHMIN		70
+#define RISCV_ISA_EXT_ZFA		71
+#define RISCV_ISA_EXT_ZTSO		72
+#define RISCV_ISA_EXT_ZACAS		73
 
-#define RISCV_ISA_EXT_MAX		64
+#define RISCV_ISA_EXT_XLINUXENVCFG	127
+
+#define RISCV_ISA_EXT_MAX		128
+#define RISCV_ISA_EXT_INVALID		U32_MAX
 
 #ifdef CONFIG_RISCV_M_MODE
 #define RISCV_ISA_EXT_SxAIA		RISCV_ISA_EXT_SMAIA
diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h
index 5c48f48e79a6..630507dff5ea 100644
--- a/arch/riscv/include/asm/hwprobe.h
+++ b/arch/riscv/include/asm/hwprobe.h
@@ -15,4 +15,28 @@ static inline bool riscv_hwprobe_key_is_valid(__s64 key)
 	return key >= 0 && key <= RISCV_HWPROBE_MAX_KEY;
 }
 
+static inline bool hwprobe_key_is_bitmask(__s64 key)
+{
+	switch (key) {
+	case RISCV_HWPROBE_KEY_BASE_BEHAVIOR:
+	case RISCV_HWPROBE_KEY_IMA_EXT_0:
+	case RISCV_HWPROBE_KEY_CPUPERF_0:
+		return true;
+	}
+
+	return false;
+}
+
+static inline bool riscv_hwprobe_pair_cmp(struct riscv_hwprobe *pair,
+					  struct riscv_hwprobe *other_pair)
+{
+	if (pair->key != other_pair->key)
+		return false;
+
+	if (hwprobe_key_is_bitmask(pair->key))
+		return (pair->value & other_pair->value) == other_pair->value;
+
+	return pair->value == other_pair->value;
+}
+
 #endif
diff --git a/arch/riscv/include/asm/jump_label.h b/arch/riscv/include/asm/jump_label.h
index 14a5ea8d8ef0..4a35d787c019 100644
--- a/arch/riscv/include/asm/jump_label.h
+++ b/arch/riscv/include/asm/jump_label.h
@@ -17,7 +17,7 @@
 static __always_inline bool arch_static_branch(struct static_key * const key,
 					       const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"	.align		2			\n\t"
 		"	.option push				\n\t"
 		"	.option norelax				\n\t"
@@ -39,7 +39,7 @@ label:
 static __always_inline bool arch_static_branch_jump(struct static_key * const key,
 						    const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"	.align		2			\n\t"
 		"	.option push				\n\t"
 		"	.option norelax				\n\t"
diff --git a/arch/riscv/include/asm/kfence.h b/arch/riscv/include/asm/kfence.h
index 0bbffd528096..7388edd88986 100644
--- a/arch/riscv/include/asm/kfence.h
+++ b/arch/riscv/include/asm/kfence.h
@@ -18,9 +18,9 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect)
 	pte_t *pte = virt_to_kpte(addr);
 
 	if (protect)
-		set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT));
+		set_pte(pte, __pte(pte_val(ptep_get(pte)) & ~_PAGE_PRESENT));
 	else
-		set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT));
+		set_pte(pte, __pte(pte_val(ptep_get(pte)) | _PAGE_PRESENT));
 
 	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
 
diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 0eefd9c991ae..484d04a92fa6 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -41,6 +41,7 @@
 	KVM_ARCH_REQ_FLAGS(4, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_HFENCE			\
 	KVM_ARCH_REQ_FLAGS(5, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_STEAL_UPDATE		KVM_ARCH_REQ(6)
 
 enum kvm_riscv_hfence_type {
 	KVM_RISCV_HFENCE_UNKNOWN = 0,
@@ -262,13 +263,17 @@ struct kvm_vcpu_arch {
 
 	/* 'static' configurations which are set only once */
 	struct kvm_vcpu_config cfg;
+
+	/* SBI steal-time accounting */
+	struct {
+		gpa_t shmem;
+		u64 last_steal;
+	} sta;
 };
 
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 
-#define KVM_ARCH_WANT_MMU_NOTIFIER
-
 #define KVM_RISCV_GSTAGE_TLB_MIN_ORDER		12
 
 void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid,
@@ -372,4 +377,7 @@ bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, u64 mask);
 void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu);
 
+void kvm_riscv_vcpu_sbi_sta_reset(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_record_steal_time(struct kvm_vcpu *vcpu);
+
 #endif /* __RISCV_KVM_HOST_H__ */
diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h
index 6a453f7f8b56..b96705258cf9 100644
--- a/arch/riscv/include/asm/kvm_vcpu_sbi.h
+++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h
@@ -15,9 +15,10 @@
 #define KVM_SBI_VERSION_MINOR 0
 
 enum kvm_riscv_sbi_ext_status {
-	KVM_RISCV_SBI_EXT_UNINITIALIZED,
-	KVM_RISCV_SBI_EXT_AVAILABLE,
-	KVM_RISCV_SBI_EXT_UNAVAILABLE,
+	KVM_RISCV_SBI_EXT_STATUS_UNINITIALIZED,
+	KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE,
+	KVM_RISCV_SBI_EXT_STATUS_ENABLED,
+	KVM_RISCV_SBI_EXT_STATUS_DISABLED,
 };
 
 struct kvm_vcpu_sbi_context {
@@ -36,7 +37,7 @@ struct kvm_vcpu_sbi_extension {
 	unsigned long extid_start;
 	unsigned long extid_end;
 
-	bool default_unavail;
+	bool default_disabled;
 
 	/**
 	 * SBI extension handler. It can be defined for a given extension or group of
@@ -59,11 +60,21 @@ int kvm_riscv_vcpu_set_reg_sbi_ext(struct kvm_vcpu *vcpu,
 				   const struct kvm_one_reg *reg);
 int kvm_riscv_vcpu_get_reg_sbi_ext(struct kvm_vcpu *vcpu,
 				   const struct kvm_one_reg *reg);
+int kvm_riscv_vcpu_set_reg_sbi(struct kvm_vcpu *vcpu,
+			       const struct kvm_one_reg *reg);
+int kvm_riscv_vcpu_get_reg_sbi(struct kvm_vcpu *vcpu,
+			       const struct kvm_one_reg *reg);
 const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext(
 				struct kvm_vcpu *vcpu, unsigned long extid);
+bool riscv_vcpu_supports_sbi_ext(struct kvm_vcpu *vcpu, int idx);
 int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run);
 void kvm_riscv_vcpu_sbi_init(struct kvm_vcpu *vcpu);
 
+int kvm_riscv_vcpu_get_reg_sbi_sta(struct kvm_vcpu *vcpu, unsigned long reg_num,
+				   unsigned long *reg_val);
+int kvm_riscv_vcpu_set_reg_sbi_sta(struct kvm_vcpu *vcpu, unsigned long reg_num,
+				   unsigned long reg_val);
+
 #ifdef CONFIG_RISCV_SBI_V01
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01;
 #endif
@@ -74,6 +85,7 @@ extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence;
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_srst;
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm;
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_dbcn;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_sta;
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_experimental;
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_vendor;
 
diff --git a/arch/riscv/include/asm/paravirt.h b/arch/riscv/include/asm/paravirt.h
new file mode 100644
index 000000000000..c0abde70fc2c
--- /dev/null
+++ b/arch/riscv/include/asm/paravirt.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_PARAVIRT_H
+#define _ASM_RISCV_PARAVIRT_H
+
+#ifdef CONFIG_PARAVIRT
+#include <linux/static_call_types.h>
+
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
+
+u64 dummy_steal_clock(int cpu);
+
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
+
+static inline u64 paravirt_steal_clock(int cpu)
+{
+	return static_call(pv_steal_clock)(cpu);
+}
+
+int __init pv_time_init(void);
+
+#else
+
+#define pv_time_init() do {} while (0)
+
+#endif /* CONFIG_PARAVIRT */
+#endif /* _ASM_RISCV_PARAVIRT_H */
diff --git a/arch/riscv/include/asm/paravirt_api_clock.h b/arch/riscv/include/asm/paravirt_api_clock.h
new file mode 100644
index 000000000000..65ac7cee0dad
--- /dev/null
+++ b/arch/riscv/include/asm/paravirt_api_clock.h
@@ -0,0 +1 @@
+#include <asm/paravirt.h>
diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h
index d169a4f41a2e..c80bb9990d32 100644
--- a/arch/riscv/include/asm/pgalloc.h
+++ b/arch/riscv/include/asm/pgalloc.h
@@ -95,7 +95,13 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 		__pud_free(mm, pud);
 }
 
-#define __pud_free_tlb(tlb, pud, addr)  pud_free((tlb)->mm, pud)
+#define __pud_free_tlb(tlb, pud, addr)					\
+do {									\
+	if (pgtable_l4_enabled) {					\
+		pagetable_pud_dtor(virt_to_ptdesc(pud));		\
+		tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pud));	\
+	}								\
+} while (0)
 
 #define p4d_alloc_one p4d_alloc_one
 static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr)
@@ -124,7 +130,11 @@ static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
 		__p4d_free(mm, p4d);
 }
 
-#define __p4d_free_tlb(tlb, p4d, addr)  p4d_free((tlb)->mm, p4d)
+#define __p4d_free_tlb(tlb, p4d, addr)					\
+do {									\
+	if (pgtable_l5_enabled)						\
+		tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(p4d));	\
+} while (0)
 #endif /* __PAGETABLE_PMD_FOLDED */
 
 static inline void sync_kernel_mappings(pgd_t *pgd)
@@ -149,7 +159,11 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 
 #ifndef __PAGETABLE_PMD_FOLDED
 
-#define __pmd_free_tlb(tlb, pmd, addr)  pmd_free((tlb)->mm, pmd)
+#define __pmd_free_tlb(tlb, pmd, addr)				\
+do {								\
+	pagetable_pmd_dtor(virt_to_ptdesc(pmd));		\
+	tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pmd));	\
+} while (0)
 
 #endif /* __PAGETABLE_PMD_FOLDED */
 
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index 9a2c780a11e9..b99bd66107a6 100644
--- a/arch/riscv/include/asm/pgtable-64.h
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -136,7 +136,7 @@ enum napot_cont_order {
  * 10010 - IO   Strongly-ordered, Non-cacheable, Non-bufferable, Shareable, Non-trustable
  */
 #define _PAGE_PMA_THEAD		((1UL << 62) | (1UL << 61) | (1UL << 60))
-#define _PAGE_NOCACHE_THEAD	((1UL < 61) | (1UL << 60))
+#define _PAGE_NOCACHE_THEAD	((1UL << 61) | (1UL << 60))
 #define _PAGE_IO_THEAD		((1UL << 63) | (1UL << 60))
 #define _PAGE_MTMASK_THEAD	(_PAGE_PMA_THEAD | _PAGE_IO_THEAD | (1UL << 59))
 
@@ -202,7 +202,7 @@ static inline int pud_user(pud_t pud)
 
 static inline void set_pud(pud_t *pudp, pud_t pud)
 {
-	*pudp = pud;
+	WRITE_ONCE(*pudp, pud);
 }
 
 static inline void pud_clear(pud_t *pudp)
@@ -278,7 +278,7 @@ static inline unsigned long _pmd_pfn(pmd_t pmd)
 static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
 {
 	if (pgtable_l4_enabled)
-		*p4dp = p4d;
+		WRITE_ONCE(*p4dp, p4d);
 	else
 		set_pud((pud_t *)p4dp, (pud_t){ p4d_val(p4d) });
 }
@@ -340,18 +340,12 @@ static inline struct page *p4d_page(p4d_t p4d)
 #define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
 
 #define pud_offset pud_offset
-static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
-{
-	if (pgtable_l4_enabled)
-		return p4d_pgtable(*p4d) + pud_index(address);
-
-	return (pud_t *)p4d;
-}
+pud_t *pud_offset(p4d_t *p4d, unsigned long address);
 
 static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
 	if (pgtable_l5_enabled)
-		*pgdp = pgd;
+		WRITE_ONCE(*pgdp, pgd);
 	else
 		set_p4d((p4d_t *)pgdp, (p4d_t){ pgd_val(pgd) });
 }
@@ -404,12 +398,6 @@ static inline struct page *pgd_page(pgd_t pgd)
 #define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1))
 
 #define p4d_offset p4d_offset
-static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
-{
-	if (pgtable_l5_enabled)
-		return pgd_pgtable(*pgd) + p4d_index(address);
-
-	return (p4d_t *)pgd;
-}
+p4d_t *p4d_offset(pgd_t *pgd, unsigned long address);
 
 #endif /* _ASM_RISCV_PGTABLE_64_H */
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 7b4287f36054..6066822e7396 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -84,7 +84,7 @@
  * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel
  * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled.
  */
-#define vmemmap		((struct page *)VMEMMAP_START)
+#define vmemmap		((struct page *)VMEMMAP_START - (phys_ram_base >> PAGE_SHIFT))
 
 #define PCI_IO_SIZE      SZ_16M
 #define PCI_IO_END       VMEMMAP_START
@@ -248,7 +248,7 @@ static inline int pmd_leaf(pmd_t pmd)
 
 static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
-	*pmdp = pmd;
+	WRITE_ONCE(*pmdp, pmd);
 }
 
 static inline void pmd_clear(pmd_t *pmdp)
@@ -439,6 +439,10 @@ static inline pte_t pte_mkhuge(pte_t pte)
 	return pte;
 }
 
+#define pte_leaf_size(pte)	(pte_napot(pte) ?				\
+					napot_cont_size(napot_cont_order(pte)) :\
+					PAGE_SIZE)
+
 #ifdef CONFIG_NUMA_BALANCING
 /*
  * See the comment in include/asm-generic/pgtable.h
@@ -510,7 +514,7 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b)
  */
 static inline void set_pte(pte_t *ptep, pte_t pteval)
 {
-	*ptep = pteval;
+	WRITE_ONCE(*ptep, pteval);
 }
 
 void flush_icache_pte(pte_t pte);
@@ -544,19 +548,12 @@ static inline void pte_clear(struct mm_struct *mm,
 	__set_pte_at(ptep, __pte(0));
 }
 
-#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
-static inline int ptep_set_access_flags(struct vm_area_struct *vma,
-					unsigned long address, pte_t *ptep,
-					pte_t entry, int dirty)
-{
-	if (!pte_same(*ptep, entry))
-		__set_pte_at(ptep, entry);
-	/*
-	 * update_mmu_cache will unconditionally execute, handling both
-	 * the case that the PTE changed and the spurious fault case.
-	 */
-	return true;
-}
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS	/* defined in mm/pgtable.c */
+extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
+				 pte_t *ptep, pte_t entry, int dirty);
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG	/* defined in mm/pgtable.c */
+extern int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address,
+				     pte_t *ptep);
 
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
@@ -569,16 +566,6 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 	return pte;
 }
 
-#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
-					    unsigned long address,
-					    pte_t *ptep)
-{
-	if (!pte_young(*ptep))
-		return 0;
-	return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep));
-}
-
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 static inline void ptep_set_wrprotect(struct mm_struct *mm,
 				      unsigned long address, pte_t *ptep)
@@ -882,7 +869,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
 #define TASK_SIZE_MIN	(PGDIR_SIZE_L3 * PTRS_PER_PGD / 2)
 
 #ifdef CONFIG_COMPAT
-#define TASK_SIZE_32	(_AC(0x80000000, UL) - PAGE_SIZE)
+#define TASK_SIZE_32	(_AC(0x80000000, UL))
 #define TASK_SIZE	(test_thread_flag(TIF_32BIT) ? \
 			 TASK_SIZE_32 : TASK_SIZE_64)
 #else
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index f19f861cda54..a8509cc31ab2 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -16,7 +16,7 @@
 
 #ifdef CONFIG_64BIT
 #define DEFAULT_MAP_WINDOW	(UL(1) << (MMAP_VA_BITS - 1))
-#define STACK_TOP_MAX		TASK_SIZE_64
+#define STACK_TOP_MAX		TASK_SIZE
 
 #define arch_get_mmap_end(addr, len, flags)			\
 ({								\
@@ -73,6 +73,43 @@
 struct task_struct;
 struct pt_regs;
 
+/*
+ * We use a flag to track in-kernel Vector context. Currently the flag has the
+ * following meaning:
+ *
+ *  - bit 0: indicates whether the in-kernel Vector context is active. The
+ *    activation of this state disables the preemption. On a non-RT kernel, it
+ *    also disable bh.
+ *  - bits 8: is used for tracking preemptible kernel-mode Vector, when
+ *    RISCV_ISA_V_PREEMPTIVE is enabled. Calling kernel_vector_begin() does not
+ *    disable the preemption if the thread's kernel_vstate.datap is allocated.
+ *    Instead, the kernel set this bit field. Then the trap entry/exit code
+ *    knows if we are entering/exiting the context that owns preempt_v.
+ *     - 0: the task is not using preempt_v
+ *     - 1: the task is actively using preempt_v. But whether does the task own
+ *          the preempt_v context is decided by bits in RISCV_V_CTX_DEPTH_MASK.
+ *  - bit 16-23 are RISCV_V_CTX_DEPTH_MASK, used by context tracking routine
+ *     when preempt_v starts:
+ *     - 0: the task is actively using, and own preempt_v context.
+ *     - non-zero: the task was using preempt_v, but then took a trap within.
+ *       Thus, the task does not own preempt_v. Any use of Vector will have to
+ *       save preempt_v, if dirty, and fallback to non-preemptible kernel-mode
+ *       Vector.
+ *  - bit 30: The in-kernel preempt_v context is saved, and requries to be
+ *    restored when returning to the context that owns the preempt_v.
+ *  - bit 31: The in-kernel preempt_v context is dirty, as signaled by the
+ *    trap entry code. Any context switches out-of current task need to save
+ *    it to the task's in-kernel V context. Also, any traps nesting on-top-of
+ *    preempt_v requesting to use V needs a save.
+ */
+#define RISCV_V_CTX_DEPTH_MASK		0x00ff0000
+
+#define RISCV_V_CTX_UNIT_DEPTH		0x00010000
+#define RISCV_KERNEL_MODE_V		0x00000001
+#define RISCV_PREEMPT_V			0x00000100
+#define RISCV_PREEMPT_V_DIRTY		0x80000000
+#define RISCV_PREEMPT_V_NEED_RESTORE	0x40000000
+
 /* CPU-specific state of a task */
 struct thread_struct {
 	/* Callee-saved registers */
@@ -81,9 +118,11 @@ struct thread_struct {
 	unsigned long s[12];	/* s[0]: frame pointer */
 	struct __riscv_d_ext_state fstate;
 	unsigned long bad_cause;
-	unsigned long vstate_ctrl;
+	u32 riscv_v_flags;
+	u32 vstate_ctrl;
 	struct __riscv_v_ext_state vstate;
 	unsigned long align_ctl;
+	struct __riscv_v_ext_state kernel_vstate;
 };
 
 /* Whitelist the fstate from the task_struct for hardened usercopy */
diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
index 0892f4421bc4..6e68f8dff76b 100644
--- a/arch/riscv/include/asm/sbi.h
+++ b/arch/riscv/include/asm/sbi.h
@@ -29,8 +29,10 @@ enum sbi_ext_id {
 	SBI_EXT_RFENCE = 0x52464E43,
 	SBI_EXT_HSM = 0x48534D,
 	SBI_EXT_SRST = 0x53525354,
+	SBI_EXT_SUSP = 0x53555350,
 	SBI_EXT_PMU = 0x504D55,
 	SBI_EXT_DBCN = 0x4442434E,
+	SBI_EXT_STA = 0x535441,
 
 	/* Experimentals extensions must lie within this range */
 	SBI_EXT_EXPERIMENTAL_START = 0x08000000,
@@ -114,6 +116,14 @@ enum sbi_srst_reset_reason {
 	SBI_SRST_RESET_REASON_SYS_FAILURE,
 };
 
+enum sbi_ext_susp_fid {
+	SBI_EXT_SUSP_SYSTEM_SUSPEND = 0,
+};
+
+enum sbi_ext_susp_sleep_type {
+	SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM = 0,
+};
+
 enum sbi_ext_pmu_fid {
 	SBI_EXT_PMU_NUM_COUNTERS = 0,
 	SBI_EXT_PMU_COUNTER_GET_INFO,
@@ -243,6 +253,22 @@ enum sbi_ext_dbcn_fid {
 	SBI_EXT_DBCN_CONSOLE_WRITE_BYTE = 2,
 };
 
+/* SBI STA (steal-time accounting) extension */
+enum sbi_ext_sta_fid {
+	SBI_EXT_STA_STEAL_TIME_SET_SHMEM = 0,
+};
+
+struct sbi_sta_struct {
+	__le32 sequence;
+	__le32 flags;
+	__le64 steal;
+	u8 preempted;
+	u8 pad[47];
+} __packed;
+
+#define SBI_STA_SHMEM_DISABLE		-1
+
+/* SBI spec version fields */
 #define SBI_SPEC_VERSION_DEFAULT	0x1
 #define SBI_SPEC_VERSION_MAJOR_SHIFT	24
 #define SBI_SPEC_VERSION_MAJOR_MASK	0x7f
@@ -271,8 +297,13 @@ struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
 			unsigned long arg3, unsigned long arg4,
 			unsigned long arg5);
 
+#ifdef CONFIG_RISCV_SBI_V01
 void sbi_console_putchar(int ch);
 int sbi_console_getchar(void);
+#else
+static inline void sbi_console_putchar(int ch) { }
+static inline int sbi_console_getchar(void) { return -ENOENT; }
+#endif
 long sbi_get_mvendorid(void);
 long sbi_get_marchid(void);
 long sbi_get_mimpid(void);
@@ -329,6 +360,11 @@ static inline unsigned long sbi_mk_version(unsigned long major,
 }
 
 int sbi_err_map_linux_errno(int err);
+
+extern bool sbi_debug_console_available;
+int sbi_debug_console_write(const char *bytes, unsigned int num_bytes);
+int sbi_debug_console_read(char *bytes, unsigned int num_bytes);
+
 #else /* CONFIG_RISCV_SBI */
 static inline int sbi_remote_fence_i(const struct cpumask *cpu_mask) { return -1; }
 static inline void sbi_init(void) {}
diff --git a/arch/riscv/include/asm/sections.h b/arch/riscv/include/asm/sections.h
index 32336e8a17cb..a393d5035c54 100644
--- a/arch/riscv/include/asm/sections.h
+++ b/arch/riscv/include/asm/sections.h
@@ -13,6 +13,7 @@ extern char _start_kernel[];
 extern char __init_data_begin[], __init_data_end[];
 extern char __init_text_begin[], __init_text_end[];
 extern char __alt_start[], __alt_end[];
+extern char __exittext_begin[], __exittext_end[];
 
 static inline bool is_va_kernel_text(uintptr_t va)
 {
diff --git a/arch/riscv/include/asm/simd.h b/arch/riscv/include/asm/simd.h
new file mode 100644
index 000000000000..54efbf523d49
--- /dev/null
+++ b/arch/riscv/include/asm/simd.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2023 SiFive
+ */
+
+#ifndef __ASM_SIMD_H
+#define __ASM_SIMD_H
+
+#include <linux/compiler.h>
+#include <linux/irqflags.h>
+#include <linux/percpu.h>
+#include <linux/preempt.h>
+#include <linux/types.h>
+#include <linux/thread_info.h>
+
+#include <asm/vector.h>
+
+#ifdef CONFIG_RISCV_ISA_V
+/*
+ * may_use_simd - whether it is allowable at this time to issue vector
+ *                instructions or access the vector register file
+ *
+ * Callers must not assume that the result remains true beyond the next
+ * preempt_enable() or return from softirq context.
+ */
+static __must_check inline bool may_use_simd(void)
+{
+	/*
+	 * RISCV_KERNEL_MODE_V is only set while preemption is disabled,
+	 * and is clear whenever preemption is enabled.
+	 */
+	if (in_hardirq() || in_nmi())
+		return false;
+
+	/*
+	 * Nesting is acheived in preempt_v by spreading the control for
+	 * preemptible and non-preemptible kernel-mode Vector into two fields.
+	 * Always try to match with prempt_v if kernel V-context exists. Then,
+	 * fallback to check non preempt_v if nesting happens, or if the config
+	 * is not set.
+	 */
+	if (IS_ENABLED(CONFIG_RISCV_ISA_V_PREEMPTIVE) && current->thread.kernel_vstate.datap) {
+		if (!riscv_preempt_v_started(current))
+			return true;
+	}
+	/*
+	 * Non-preemptible kernel-mode Vector temporarily disables bh. So we
+	 * must not return true on irq_disabled(). Otherwise we would fail the
+	 * lockdep check calling local_bh_enable()
+	 */
+	return !irqs_disabled() && !(riscv_v_flags() & RISCV_KERNEL_MODE_V);
+}
+
+#else /* ! CONFIG_RISCV_ISA_V */
+
+static __must_check inline bool may_use_simd(void)
+{
+	return false;
+}
+
+#endif /* ! CONFIG_RISCV_ISA_V */
+
+#endif
diff --git a/arch/riscv/include/asm/stacktrace.h b/arch/riscv/include/asm/stacktrace.h
index f7e8ef2418b9..b1495a7e06ce 100644
--- a/arch/riscv/include/asm/stacktrace.h
+++ b/arch/riscv/include/asm/stacktrace.h
@@ -21,4 +21,9 @@ static inline bool on_thread_stack(void)
 	return !(((unsigned long)(current->stack) ^ current_stack_pointer) & ~(THREAD_SIZE - 1));
 }
 
+
+#ifdef CONFIG_VMAP_STACK
+DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack);
+#endif /* CONFIG_VMAP_STACK */
+
 #endif /* _ASM_RISCV_STACKTRACE_H */
diff --git a/arch/riscv/include/asm/suspend.h b/arch/riscv/include/asm/suspend.h
index 02f87867389a..491296a335d0 100644
--- a/arch/riscv/include/asm/suspend.h
+++ b/arch/riscv/include/asm/suspend.h
@@ -14,6 +14,7 @@ struct suspend_context {
 	struct pt_regs regs;
 	/* Saved and restored by high-level functions */
 	unsigned long scratch;
+	unsigned long envcfg;
 	unsigned long tvec;
 	unsigned long ie;
 #ifdef CONFIG_MMU
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index f90d8e42f3c7..7efdb0584d47 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -53,8 +53,7 @@ static inline void __switch_to_fpu(struct task_struct *prev,
 	struct pt_regs *regs;
 
 	regs = task_pt_regs(prev);
-	if (unlikely(regs->status & SR_SD))
-		fstate_save(prev, regs);
+	fstate_save(prev, regs);
 	fstate_restore(next, task_pt_regs(next));
 }
 
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 574779900bfb..5d473343634b 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -28,7 +28,6 @@
 
 #define THREAD_SHIFT            (PAGE_SHIFT + THREAD_SIZE_ORDER)
 #define OVERFLOW_STACK_SIZE     SZ_4K
-#define SHADOW_OVERFLOW_STACK_SIZE (1024)
 
 #define IRQ_STACK_SIZE		THREAD_SIZE
 
@@ -103,12 +102,14 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 #define TIF_NOTIFY_SIGNAL	9	/* signal notifications exist */
 #define TIF_UPROBE		10	/* uprobe breakpoint or singlestep */
 #define TIF_32BIT		11	/* compat-mode 32bit process */
+#define TIF_RISCV_V_DEFER_RESTORE	12 /* restore Vector before returing to user */
 
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_SIGNAL	(1 << TIF_NOTIFY_SIGNAL)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
+#define _TIF_RISCV_V_DEFER_RESTORE	(1 << TIF_RISCV_V_DEFER_RESTORE)
 
 #define _TIF_WORK_MASK \
 	(_TIF_NOTIFY_RESUME | _TIF_SIGPENDING | _TIF_NEED_RESCHED | \
diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
index 1eb5682b2af6..50b63b5c15bd 100644
--- a/arch/riscv/include/asm/tlb.h
+++ b/arch/riscv/include/asm/tlb.h
@@ -16,7 +16,7 @@ static void tlb_flush(struct mmu_gather *tlb);
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
 #ifdef CONFIG_MMU
-	if (tlb->fullmm || tlb->need_flush_all)
+	if (tlb->fullmm || tlb->need_flush_all || tlb->freed_tables)
 		flush_tlb_mm(tlb->mm);
 	else
 		flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end,
diff --git a/arch/riscv/include/asm/tlbbatch.h b/arch/riscv/include/asm/tlbbatch.h
new file mode 100644
index 000000000000..46014f70b9da
--- /dev/null
+++ b/arch/riscv/include/asm/tlbbatch.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+#ifndef _ASM_RISCV_TLBBATCH_H
+#define _ASM_RISCV_TLBBATCH_H
+
+#include <linux/cpumask.h>
+
+struct arch_tlbflush_unmap_batch {
+	struct cpumask cpumask;
+};
+
+#endif /* _ASM_RISCV_TLBBATCH_H */
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 8f3418c5f172..4112cc8d1d69 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -41,11 +41,20 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr);
 void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		     unsigned long end);
 void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+void local_flush_tlb_kernel_range(unsigned long start, unsigned long end);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			unsigned long end);
 #endif
+
+bool arch_tlbbatch_should_defer(struct mm_struct *mm);
+void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
+			       struct mm_struct *mm,
+			       unsigned long uaddr);
+void arch_flush_tlb_batched_pending(struct mm_struct *mm);
+void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
+
 #else /* CONFIG_SMP && CONFIG_MMU */
 
 #define flush_tlb_all() local_flush_tlb_all()
@@ -66,6 +75,7 @@ static inline void flush_tlb_kernel_range(unsigned long start,
 
 #define flush_tlb_mm(mm) flush_tlb_all()
 #define flush_tlb_mm_range(mm, start, end, page_size) flush_tlb_all()
+#define local_flush_tlb_kernel_range(start, end) flush_tlb_all()
 #endif /* !CONFIG_SMP || !CONFIG_MMU */
 
 #endif /* _ASM_RISCV_TLBFLUSH_H */
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index 87aaef656257..0cd6f0a027d1 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -22,6 +22,18 @@
 extern unsigned long riscv_v_vsize;
 int riscv_v_setup_vsize(void);
 bool riscv_v_first_use_handler(struct pt_regs *regs);
+void kernel_vector_begin(void);
+void kernel_vector_end(void);
+void get_cpu_vector_context(void);
+void put_cpu_vector_context(void);
+void riscv_v_thread_free(struct task_struct *tsk);
+void __init riscv_v_setup_ctx_cache(void);
+void riscv_v_thread_alloc(struct task_struct *tsk);
+
+static inline u32 riscv_v_flags(void)
+{
+	return READ_ONCE(current->thread.riscv_v_flags);
+}
 
 static __always_inline bool has_vector(void)
 {
@@ -162,36 +174,89 @@ static inline void riscv_v_vstate_discard(struct pt_regs *regs)
 	__riscv_v_vstate_dirty(regs);
 }
 
-static inline void riscv_v_vstate_save(struct task_struct *task,
+static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate,
 				       struct pt_regs *regs)
 {
 	if ((regs->status & SR_VS) == SR_VS_DIRTY) {
-		struct __riscv_v_ext_state *vstate = &task->thread.vstate;
-
 		__riscv_v_vstate_save(vstate, vstate->datap);
 		__riscv_v_vstate_clean(regs);
 	}
 }
 
-static inline void riscv_v_vstate_restore(struct task_struct *task,
+static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate,
 					  struct pt_regs *regs)
 {
 	if ((regs->status & SR_VS) != SR_VS_OFF) {
-		struct __riscv_v_ext_state *vstate = &task->thread.vstate;
-
 		__riscv_v_vstate_restore(vstate, vstate->datap);
 		__riscv_v_vstate_clean(regs);
 	}
 }
 
+static inline void riscv_v_vstate_set_restore(struct task_struct *task,
+					      struct pt_regs *regs)
+{
+	if ((regs->status & SR_VS) != SR_VS_OFF) {
+		set_tsk_thread_flag(task, TIF_RISCV_V_DEFER_RESTORE);
+		riscv_v_vstate_on(regs);
+	}
+}
+
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+static inline bool riscv_preempt_v_dirty(struct task_struct *task)
+{
+	return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V_DIRTY);
+}
+
+static inline bool riscv_preempt_v_restore(struct task_struct *task)
+{
+	return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V_NEED_RESTORE);
+}
+
+static inline void riscv_preempt_v_clear_dirty(struct task_struct *task)
+{
+	barrier();
+	task->thread.riscv_v_flags &= ~RISCV_PREEMPT_V_DIRTY;
+}
+
+static inline void riscv_preempt_v_set_restore(struct task_struct *task)
+{
+	barrier();
+	task->thread.riscv_v_flags |= RISCV_PREEMPT_V_NEED_RESTORE;
+}
+
+static inline bool riscv_preempt_v_started(struct task_struct *task)
+{
+	return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V);
+}
+
+#else /* !CONFIG_RISCV_ISA_V_PREEMPTIVE */
+static inline bool riscv_preempt_v_dirty(struct task_struct *task) { return false; }
+static inline bool riscv_preempt_v_restore(struct task_struct *task) { return false; }
+static inline bool riscv_preempt_v_started(struct task_struct *task) { return false; }
+#define riscv_preempt_v_clear_dirty(tsk)	do {} while (0)
+#define riscv_preempt_v_set_restore(tsk)	do {} while (0)
+#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */
+
 static inline void __switch_to_vector(struct task_struct *prev,
 				      struct task_struct *next)
 {
 	struct pt_regs *regs;
 
-	regs = task_pt_regs(prev);
-	riscv_v_vstate_save(prev, regs);
-	riscv_v_vstate_restore(next, task_pt_regs(next));
+	if (riscv_preempt_v_started(prev)) {
+		if (riscv_preempt_v_dirty(prev)) {
+			__riscv_v_vstate_save(&prev->thread.kernel_vstate,
+					      prev->thread.kernel_vstate.datap);
+			riscv_preempt_v_clear_dirty(prev);
+		}
+	} else {
+		regs = task_pt_regs(prev);
+		riscv_v_vstate_save(&prev->thread.vstate, regs);
+	}
+
+	if (riscv_preempt_v_started(next))
+		riscv_preempt_v_set_restore(next);
+	else
+		riscv_v_vstate_set_restore(next, task_pt_regs(next));
 }
 
 void riscv_v_vstate_ctrl_init(struct task_struct *tsk);
@@ -208,11 +273,14 @@ static inline bool riscv_v_vstate_query(struct pt_regs *regs) { return false; }
 static inline bool riscv_v_vstate_ctrl_user_allowed(void) { return false; }
 #define riscv_v_vsize (0)
 #define riscv_v_vstate_discard(regs)		do {} while (0)
-#define riscv_v_vstate_save(task, regs)		do {} while (0)
-#define riscv_v_vstate_restore(task, regs)	do {} while (0)
+#define riscv_v_vstate_save(vstate, regs)	do {} while (0)
+#define riscv_v_vstate_restore(vstate, regs)	do {} while (0)
 #define __switch_to_vector(__prev, __next)	do {} while (0)
 #define riscv_v_vstate_off(regs)		do {} while (0)
 #define riscv_v_vstate_on(regs)			do {} while (0)
+#define riscv_v_thread_free(tsk)		do {} while (0)
+#define  riscv_v_setup_ctx_cache()		do {} while (0)
+#define riscv_v_thread_alloc(tsk)		do {} while (0)
 
 #endif /* CONFIG_RISCV_ISA_V */
 
diff --git a/arch/riscv/include/asm/vmalloc.h b/arch/riscv/include/asm/vmalloc.h
index 924d01b56c9a..51f6dfe19745 100644
--- a/arch/riscv/include/asm/vmalloc.h
+++ b/arch/riscv/include/asm/vmalloc.h
@@ -19,65 +19,6 @@ static inline bool arch_vmap_pmd_supported(pgprot_t prot)
 	return true;
 }
 
-#ifdef CONFIG_RISCV_ISA_SVNAPOT
-#include <linux/pgtable.h>
+#endif
 
-#define arch_vmap_pte_range_map_size arch_vmap_pte_range_map_size
-static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, unsigned long end,
-							 u64 pfn, unsigned int max_page_shift)
-{
-	unsigned long map_size = PAGE_SIZE;
-	unsigned long size, order;
-
-	if (!has_svnapot())
-		return map_size;
-
-	for_each_napot_order_rev(order) {
-		if (napot_cont_shift(order) > max_page_shift)
-			continue;
-
-		size = napot_cont_size(order);
-		if (end - addr < size)
-			continue;
-
-		if (!IS_ALIGNED(addr, size))
-			continue;
-
-		if (!IS_ALIGNED(PFN_PHYS(pfn), size))
-			continue;
-
-		map_size = size;
-		break;
-	}
-
-	return map_size;
-}
-
-#define arch_vmap_pte_supported_shift arch_vmap_pte_supported_shift
-static inline int arch_vmap_pte_supported_shift(unsigned long size)
-{
-	int shift = PAGE_SHIFT;
-	unsigned long order;
-
-	if (!has_svnapot())
-		return shift;
-
-	WARN_ON_ONCE(size >= PMD_SIZE);
-
-	for_each_napot_order_rev(order) {
-		if (napot_cont_size(order) > size)
-			continue;
-
-		if (!IS_ALIGNED(size, napot_cont_size(order)))
-			continue;
-
-		shift = napot_cont_shift(order);
-		break;
-	}
-
-	return shift;
-}
-
-#endif /* CONFIG_RISCV_ISA_SVNAPOT */
-#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
 #endif /* _ASM_RISCV_VMALLOC_H */
diff --git a/arch/riscv/include/asm/word-at-a-time.h b/arch/riscv/include/asm/word-at-a-time.h
index 7c086ac6ecd4..f3f031e34191 100644
--- a/arch/riscv/include/asm/word-at-a-time.h
+++ b/arch/riscv/include/asm/word-at-a-time.h
@@ -9,6 +9,7 @@
 #define _ASM_RISCV_WORD_AT_A_TIME_H
 
 
+#include <asm/asm-extable.h>
 #include <linux/kernel.h>
 
 struct word_at_a_time {
@@ -45,4 +46,30 @@ static inline unsigned long find_zero(unsigned long mask)
 /* The mask we created is directly usable as a bytemask */
 #define zero_bytemask(mask) (mask)
 
+#ifdef CONFIG_DCACHE_WORD_ACCESS
+
+/*
+ * Load an unaligned word from kernel space.
+ *
+ * In the (very unlikely) case of the word being a page-crosser
+ * and the next page not being mapped, take the exception and
+ * return zeroes in the non-existing part.
+ */
+static inline unsigned long load_unaligned_zeropad(const void *addr)
+{
+	unsigned long ret;
+
+	/* Load word from unaligned pointer addr */
+	asm(
+	"1:	" REG_L " %0, %2\n"
+	"2:\n"
+	_ASM_EXTABLE_LOAD_UNALIGNED_ZEROPAD(1b, 2b, %0, %1)
+	: "=&r" (ret)
+	: "r" (addr), "m" (*(unsigned long *)addr));
+
+	return ret;
+}
+
+#endif	/* CONFIG_DCACHE_WORD_ACCESS */
+
 #endif /* _ASM_RISCV_WORD_AT_A_TIME_H */
diff --git a/arch/riscv/include/asm/xip_fixup.h b/arch/riscv/include/asm/xip_fixup.h
index d4ffc3c37649..b65bf6306f69 100644
--- a/arch/riscv/include/asm/xip_fixup.h
+++ b/arch/riscv/include/asm/xip_fixup.h
@@ -13,7 +13,7 @@
         add \reg, \reg, t0
 .endm
 .macro XIP_FIXUP_FLASH_OFFSET reg
-	la t1, __data_loc
+	la t0, __data_loc
 	REG_L t1, _xip_phys_offset
 	sub \reg, \reg, t1
 	add \reg, \reg, t0
diff --git a/arch/riscv/include/asm/xor.h b/arch/riscv/include/asm/xor.h
new file mode 100644
index 000000000000..96011861e46b
--- /dev/null
+++ b/arch/riscv/include/asm/xor.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2021 SiFive
+ */
+
+#include <linux/hardirq.h>
+#include <asm-generic/xor.h>
+#ifdef CONFIG_RISCV_ISA_V
+#include <asm/vector.h>
+#include <asm/switch_to.h>
+#include <asm/asm-prototypes.h>
+
+static void xor_vector_2(unsigned long bytes, unsigned long *__restrict p1,
+			 const unsigned long *__restrict p2)
+{
+	kernel_vector_begin();
+	xor_regs_2_(bytes, p1, p2);
+	kernel_vector_end();
+}
+
+static void xor_vector_3(unsigned long bytes, unsigned long *__restrict p1,
+			 const unsigned long *__restrict p2,
+			 const unsigned long *__restrict p3)
+{
+	kernel_vector_begin();
+	xor_regs_3_(bytes, p1, p2, p3);
+	kernel_vector_end();
+}
+
+static void xor_vector_4(unsigned long bytes, unsigned long *__restrict p1,
+			 const unsigned long *__restrict p2,
+			 const unsigned long *__restrict p3,
+			 const unsigned long *__restrict p4)
+{
+	kernel_vector_begin();
+	xor_regs_4_(bytes, p1, p2, p3, p4);
+	kernel_vector_end();
+}
+
+static void xor_vector_5(unsigned long bytes, unsigned long *__restrict p1,
+			 const unsigned long *__restrict p2,
+			 const unsigned long *__restrict p3,
+			 const unsigned long *__restrict p4,
+			 const unsigned long *__restrict p5)
+{
+	kernel_vector_begin();
+	xor_regs_5_(bytes, p1, p2, p3, p4, p5);
+	kernel_vector_end();
+}
+
+static struct xor_block_template xor_block_rvv = {
+	.name = "rvv",
+	.do_2 = xor_vector_2,
+	.do_3 = xor_vector_3,
+	.do_4 = xor_vector_4,
+	.do_5 = xor_vector_5
+};
+
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES           \
+	do {        \
+		xor_speed(&xor_block_8regs);    \
+		xor_speed(&xor_block_32regs);    \
+		if (has_vector()) { \
+			xor_speed(&xor_block_rvv);\
+		} \
+	} while (0)
+#endif
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index b659ffcfcdb4..9f2a8e3ff204 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -30,6 +30,35 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZBB		(1 << 4)
 #define		RISCV_HWPROBE_EXT_ZBS		(1 << 5)
 #define		RISCV_HWPROBE_EXT_ZICBOZ	(1 << 6)
+#define		RISCV_HWPROBE_EXT_ZBC		(1 << 7)
+#define		RISCV_HWPROBE_EXT_ZBKB		(1 << 8)
+#define		RISCV_HWPROBE_EXT_ZBKC		(1 << 9)
+#define		RISCV_HWPROBE_EXT_ZBKX		(1 << 10)
+#define		RISCV_HWPROBE_EXT_ZKND		(1 << 11)
+#define		RISCV_HWPROBE_EXT_ZKNE		(1 << 12)
+#define		RISCV_HWPROBE_EXT_ZKNH		(1 << 13)
+#define		RISCV_HWPROBE_EXT_ZKSED		(1 << 14)
+#define		RISCV_HWPROBE_EXT_ZKSH		(1 << 15)
+#define		RISCV_HWPROBE_EXT_ZKT		(1 << 16)
+#define		RISCV_HWPROBE_EXT_ZVBB		(1 << 17)
+#define		RISCV_HWPROBE_EXT_ZVBC		(1 << 18)
+#define		RISCV_HWPROBE_EXT_ZVKB		(1 << 19)
+#define		RISCV_HWPROBE_EXT_ZVKG		(1 << 20)
+#define		RISCV_HWPROBE_EXT_ZVKNED	(1 << 21)
+#define		RISCV_HWPROBE_EXT_ZVKNHA	(1 << 22)
+#define		RISCV_HWPROBE_EXT_ZVKNHB	(1 << 23)
+#define		RISCV_HWPROBE_EXT_ZVKSED	(1 << 24)
+#define		RISCV_HWPROBE_EXT_ZVKSH		(1 << 25)
+#define		RISCV_HWPROBE_EXT_ZVKT		(1 << 26)
+#define		RISCV_HWPROBE_EXT_ZFH		(1 << 27)
+#define		RISCV_HWPROBE_EXT_ZFHMIN	(1 << 28)
+#define		RISCV_HWPROBE_EXT_ZIHINTNTL	(1 << 29)
+#define		RISCV_HWPROBE_EXT_ZVFH		(1 << 30)
+#define		RISCV_HWPROBE_EXT_ZVFHMIN	(1 << 31)
+#define		RISCV_HWPROBE_EXT_ZFA		(1ULL << 32)
+#define		RISCV_HWPROBE_EXT_ZTSO		(1ULL << 33)
+#define		RISCV_HWPROBE_EXT_ZACAS		(1ULL << 34)
+#define		RISCV_HWPROBE_EXT_ZICOND	(1ULL << 35)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)
@@ -40,4 +69,7 @@ struct riscv_hwprobe {
 #define RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE	6
 /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */
 
+/* Flags */
+#define RISCV_HWPROBE_WHICH_CPUS	(1 << 0)
+
 #endif
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index 60d3b21dead7..7499e88a947c 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -139,6 +139,33 @@ enum KVM_RISCV_ISA_EXT_ID {
 	KVM_RISCV_ISA_EXT_ZIHPM,
 	KVM_RISCV_ISA_EXT_SMSTATEEN,
 	KVM_RISCV_ISA_EXT_ZICOND,
+	KVM_RISCV_ISA_EXT_ZBC,
+	KVM_RISCV_ISA_EXT_ZBKB,
+	KVM_RISCV_ISA_EXT_ZBKC,
+	KVM_RISCV_ISA_EXT_ZBKX,
+	KVM_RISCV_ISA_EXT_ZKND,
+	KVM_RISCV_ISA_EXT_ZKNE,
+	KVM_RISCV_ISA_EXT_ZKNH,
+	KVM_RISCV_ISA_EXT_ZKR,
+	KVM_RISCV_ISA_EXT_ZKSED,
+	KVM_RISCV_ISA_EXT_ZKSH,
+	KVM_RISCV_ISA_EXT_ZKT,
+	KVM_RISCV_ISA_EXT_ZVBB,
+	KVM_RISCV_ISA_EXT_ZVBC,
+	KVM_RISCV_ISA_EXT_ZVKB,
+	KVM_RISCV_ISA_EXT_ZVKG,
+	KVM_RISCV_ISA_EXT_ZVKNED,
+	KVM_RISCV_ISA_EXT_ZVKNHA,
+	KVM_RISCV_ISA_EXT_ZVKNHB,
+	KVM_RISCV_ISA_EXT_ZVKSED,
+	KVM_RISCV_ISA_EXT_ZVKSH,
+	KVM_RISCV_ISA_EXT_ZVKT,
+	KVM_RISCV_ISA_EXT_ZFH,
+	KVM_RISCV_ISA_EXT_ZFHMIN,
+	KVM_RISCV_ISA_EXT_ZIHINTNTL,
+	KVM_RISCV_ISA_EXT_ZVFH,
+	KVM_RISCV_ISA_EXT_ZVFHMIN,
+	KVM_RISCV_ISA_EXT_ZFA,
 	KVM_RISCV_ISA_EXT_MAX,
 };
 
@@ -157,9 +184,16 @@ enum KVM_RISCV_SBI_EXT_ID {
 	KVM_RISCV_SBI_EXT_EXPERIMENTAL,
 	KVM_RISCV_SBI_EXT_VENDOR,
 	KVM_RISCV_SBI_EXT_DBCN,
+	KVM_RISCV_SBI_EXT_STA,
 	KVM_RISCV_SBI_EXT_MAX,
 };
 
+/* SBI STA extension registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
+struct kvm_riscv_sbi_sta {
+	unsigned long shmem_lo;
+	unsigned long shmem_hi;
+};
+
 /* Possible states for kvm_riscv_timer */
 #define KVM_RISCV_TIMER_STATE_OFF	0
 #define KVM_RISCV_TIMER_STATE_ON	1
@@ -241,6 +275,12 @@ enum KVM_RISCV_SBI_EXT_ID {
 #define KVM_REG_RISCV_VECTOR_REG(n)	\
 		((n) + sizeof(struct __riscv_v_ext_state) / sizeof(unsigned long))
 
+/* Registers for specific SBI extensions are mapped as type 10 */
+#define KVM_REG_RISCV_SBI_STATE		(0x0a << KVM_REG_RISCV_TYPE_SHIFT)
+#define KVM_REG_RISCV_SBI_STA		(0x0 << KVM_REG_RISCV_SUBTYPE_SHIFT)
+#define KVM_REG_RISCV_SBI_STA_REG(name)		\
+		(offsetof(struct kvm_riscv_sbi_sta, name) / sizeof(unsigned long))
+
 /* Device Control API: RISC-V AIA */
 #define KVM_DEV_RISCV_APLIC_ALIGN		0x1000
 #define KVM_DEV_RISCV_APLIC_SIZE		0x4000
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 82940b6a79a2..604d6bf7e476 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -7,6 +7,7 @@ ifdef CONFIG_FTRACE
 CFLAGS_REMOVE_ftrace.o	= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_patch.o	= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_sbi.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_return_address.o	= $(CC_FLAGS_FTRACE)
 endif
 CFLAGS_syscall_table.o	+= $(call cc-option,-Wno-override-init,)
 CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,)
@@ -46,10 +47,12 @@ obj-y	+= irq.o
 obj-y	+= process.o
 obj-y	+= ptrace.o
 obj-y	+= reset.o
+obj-y	+= return_address.o
 obj-y	+= setup.o
 obj-y	+= signal.o
 obj-y	+= syscall_table.o
 obj-y	+= sys_riscv.o
+obj-y	+= sys_hwprobe.o
 obj-y	+= time.o
 obj-y	+= traps.o
 obj-y	+= riscv_ksyms.o
@@ -63,6 +66,7 @@ obj-$(CONFIG_MMU) += vdso.o vdso/
 obj-$(CONFIG_RISCV_MISALIGNED)	+= traps_misaligned.o
 obj-$(CONFIG_FPU)		+= fpu.o
 obj-$(CONFIG_RISCV_ISA_V)	+= vector.o
+obj-$(CONFIG_RISCV_ISA_V)	+= kernel_mode_vector.o
 obj-$(CONFIG_SMP)		+= smpboot.o
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_SMP)		+= cpu_ops.o
@@ -85,6 +89,7 @@ obj-$(CONFIG_SMP)		+= sbi-ipi.o
 obj-$(CONFIG_SMP) += cpu_ops_sbi.o
 endif
 obj-$(CONFIG_HOTPLUG_CPU)	+= cpu-hotplug.o
+obj-$(CONFIG_PARAVIRT)		+= paravirt.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_KEXEC_CORE)	+= kexec_relocate.o crash_save_regs.o machine_kexec.o
 obj-$(CONFIG_KEXEC_FILE)	+= elf_kexec.o machine_kexec_file.o
diff --git a/arch/riscv/kernel/cpu-hotplug.c b/arch/riscv/kernel/cpu-hotplug.c
index 457a18efcb11..28b58fc5ad19 100644
--- a/arch/riscv/kernel/cpu-hotplug.c
+++ b/arch/riscv/kernel/cpu-hotplug.c
@@ -18,7 +18,7 @@
 
 bool cpu_has_hotplug(unsigned int cpu)
 {
-	if (cpu_ops[cpu]->cpu_stop)
+	if (cpu_ops->cpu_stop)
 		return true;
 
 	return false;
@@ -29,25 +29,18 @@ bool cpu_has_hotplug(unsigned int cpu)
  */
 int __cpu_disable(void)
 {
-	int ret = 0;
 	unsigned int cpu = smp_processor_id();
 
-	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_stop)
+	if (!cpu_ops->cpu_stop)
 		return -EOPNOTSUPP;
 
-	if (cpu_ops[cpu]->cpu_disable)
-		ret = cpu_ops[cpu]->cpu_disable(cpu);
-
-	if (ret)
-		return ret;
-
 	remove_cpu_topology(cpu);
 	numa_remove_cpu(cpu);
 	set_cpu_online(cpu, false);
 	riscv_ipi_disable();
 	irq_migrate_all_off_this_cpu();
 
-	return ret;
+	return 0;
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -62,8 +55,8 @@ void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu)
 	pr_notice("CPU%u: off\n", cpu);
 
 	/* Verify from the firmware if the cpu is really stopped*/
-	if (cpu_ops[cpu]->cpu_is_stopped)
-		ret = cpu_ops[cpu]->cpu_is_stopped(cpu);
+	if (cpu_ops->cpu_is_stopped)
+		ret = cpu_ops->cpu_is_stopped(cpu);
 	if (ret)
 		pr_warn("CPU%d may not have stopped: %d\n", cpu, ret);
 }
@@ -77,7 +70,7 @@ void __noreturn arch_cpu_idle_dead(void)
 
 	cpuhp_ap_report_dead();
 
-	cpu_ops[smp_processor_id()]->cpu_stop();
+	cpu_ops->cpu_stop();
 	/* It should never reach here */
 	BUG();
 }
diff --git a/arch/riscv/kernel/cpu_ops.c b/arch/riscv/kernel/cpu_ops.c
index eb479a88a954..6a8bd8f4db07 100644
--- a/arch/riscv/kernel/cpu_ops.c
+++ b/arch/riscv/kernel/cpu_ops.c
@@ -13,25 +13,21 @@
 #include <asm/sbi.h>
 #include <asm/smp.h>
 
-const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
+const struct cpu_operations *cpu_ops __ro_after_init = &cpu_ops_spinwait;
 
 extern const struct cpu_operations cpu_ops_sbi;
 #ifndef CONFIG_RISCV_BOOT_SPINWAIT
 const struct cpu_operations cpu_ops_spinwait = {
-	.name		= "",
-	.cpu_prepare	= NULL,
 	.cpu_start	= NULL,
 };
 #endif
 
-void __init cpu_set_ops(int cpuid)
+void __init cpu_set_ops(void)
 {
 #if IS_ENABLED(CONFIG_RISCV_SBI)
 	if (sbi_probe_extension(SBI_EXT_HSM)) {
-		if (!cpuid)
-			pr_info("SBI HSM extension detected\n");
-		cpu_ops[cpuid] = &cpu_ops_sbi;
-	} else
+		pr_info("SBI HSM extension detected\n");
+		cpu_ops = &cpu_ops_sbi;
+	}
 #endif
-		cpu_ops[cpuid] = &cpu_ops_spinwait;
 }
diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c
index efa0f0816634..1cc7df740edd 100644
--- a/arch/riscv/kernel/cpu_ops_sbi.c
+++ b/arch/riscv/kernel/cpu_ops_sbi.c
@@ -79,23 +79,7 @@ static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 	return sbi_hsm_hart_start(hartid, boot_addr, hsm_data);
 }
 
-static int sbi_cpu_prepare(unsigned int cpuid)
-{
-	if (!cpu_ops_sbi.cpu_start) {
-		pr_err("cpu start method not defined for CPU [%d]\n", cpuid);
-		return -ENODEV;
-	}
-	return 0;
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
-static int sbi_cpu_disable(unsigned int cpuid)
-{
-	if (!cpu_ops_sbi.cpu_stop)
-		return -EOPNOTSUPP;
-	return 0;
-}
-
 static void sbi_cpu_stop(void)
 {
 	int ret;
@@ -118,11 +102,8 @@ static int sbi_cpu_is_stopped(unsigned int cpuid)
 #endif
 
 const struct cpu_operations cpu_ops_sbi = {
-	.name		= "sbi",
-	.cpu_prepare	= sbi_cpu_prepare,
 	.cpu_start	= sbi_cpu_start,
 #ifdef CONFIG_HOTPLUG_CPU
-	.cpu_disable	= sbi_cpu_disable,
 	.cpu_stop	= sbi_cpu_stop,
 	.cpu_is_stopped	= sbi_cpu_is_stopped,
 #endif
diff --git a/arch/riscv/kernel/cpu_ops_spinwait.c b/arch/riscv/kernel/cpu_ops_spinwait.c
index d98d19226b5f..613872b0a21a 100644
--- a/arch/riscv/kernel/cpu_ops_spinwait.c
+++ b/arch/riscv/kernel/cpu_ops_spinwait.c
@@ -39,15 +39,6 @@ static void cpu_update_secondary_bootdata(unsigned int cpuid,
 	WRITE_ONCE(__cpu_spinwait_task_pointer[hartid], tidle);
 }
 
-static int spinwait_cpu_prepare(unsigned int cpuid)
-{
-	if (!cpu_ops_spinwait.cpu_start) {
-		pr_err("cpu start method not defined for CPU [%d]\n", cpuid);
-		return -ENODEV;
-	}
-	return 0;
-}
-
 static int spinwait_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 {
 	/*
@@ -64,7 +55,5 @@ static int spinwait_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 }
 
 const struct cpu_operations cpu_ops_spinwait = {
-	.name		= "spinwait",
-	.cpu_prepare	= spinwait_cpu_prepare,
 	.cpu_start	= spinwait_cpu_start,
 };
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index b3785ffc1570..79a5a35fab96 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -8,8 +8,10 @@
 
 #include <linux/acpi.h>
 #include <linux/bitmap.h>
+#include <linux/cpu.h>
 #include <linux/cpuhotplug.h>
 #include <linux/ctype.h>
+#include <linux/jump_label.h>
 #include <linux/log2.h>
 #include <linux/memory.h>
 #include <linux/module.h>
@@ -22,6 +24,7 @@
 #include <asm/hwprobe.h>
 #include <asm/patch.h>
 #include <asm/processor.h>
+#include <asm/sbi.h>
 #include <asm/vector.h>
 
 #include "copy-unaligned.h"
@@ -44,6 +47,8 @@ struct riscv_isainfo hart_isa[NR_CPUS];
 /* Performance information */
 DEFINE_PER_CPU(long, misaligned_access_speed);
 
+static cpumask_t fast_misaligned_access;
+
 /**
  * riscv_isa_extension_base() - Get base extension word
  *
@@ -70,7 +75,7 @@ EXPORT_SYMBOL_GPL(riscv_isa_extension_base);
  *
  * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used.
  */
-bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit)
+bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned int bit)
 {
 	const unsigned long *bmap = (isa_bitmap) ? isa_bitmap : riscv_isa;
 
@@ -102,17 +107,111 @@ static bool riscv_isa_extension_check(int id)
 			return false;
 		}
 		return true;
+	case RISCV_ISA_EXT_INVALID:
+		return false;
 	}
 
 	return true;
 }
 
-#define __RISCV_ISA_EXT_DATA(_name, _id) {	\
-	.name = #_name,				\
-	.property = #_name,			\
-	.id = _id,				\
+#define _RISCV_ISA_EXT_DATA(_name, _id, _subset_exts, _subset_exts_size) {	\
+	.name = #_name,								\
+	.property = #_name,							\
+	.id = _id,								\
+	.subset_ext_ids = _subset_exts,						\
+	.subset_ext_size = _subset_exts_size					\
 }
 
+#define __RISCV_ISA_EXT_DATA(_name, _id) _RISCV_ISA_EXT_DATA(_name, _id, NULL, 0)
+
+/* Used to declare pure "lasso" extension (Zk for instance) */
+#define __RISCV_ISA_EXT_BUNDLE(_name, _bundled_exts) \
+	_RISCV_ISA_EXT_DATA(_name, RISCV_ISA_EXT_INVALID, _bundled_exts, ARRAY_SIZE(_bundled_exts))
+
+/* Used to declare extensions that are a superset of other extensions (Zvbb for instance) */
+#define __RISCV_ISA_EXT_SUPERSET(_name, _id, _sub_exts) \
+	_RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts))
+
+static const unsigned int riscv_zk_bundled_exts[] = {
+	RISCV_ISA_EXT_ZBKB,
+	RISCV_ISA_EXT_ZBKC,
+	RISCV_ISA_EXT_ZBKX,
+	RISCV_ISA_EXT_ZKND,
+	RISCV_ISA_EXT_ZKNE,
+	RISCV_ISA_EXT_ZKR,
+	RISCV_ISA_EXT_ZKT,
+};
+
+static const unsigned int riscv_zkn_bundled_exts[] = {
+	RISCV_ISA_EXT_ZBKB,
+	RISCV_ISA_EXT_ZBKC,
+	RISCV_ISA_EXT_ZBKX,
+	RISCV_ISA_EXT_ZKND,
+	RISCV_ISA_EXT_ZKNE,
+	RISCV_ISA_EXT_ZKNH,
+};
+
+static const unsigned int riscv_zks_bundled_exts[] = {
+	RISCV_ISA_EXT_ZBKB,
+	RISCV_ISA_EXT_ZBKC,
+	RISCV_ISA_EXT_ZKSED,
+	RISCV_ISA_EXT_ZKSH
+};
+
+#define RISCV_ISA_EXT_ZVKN	\
+	RISCV_ISA_EXT_ZVKNED,	\
+	RISCV_ISA_EXT_ZVKNHB,	\
+	RISCV_ISA_EXT_ZVKB,	\
+	RISCV_ISA_EXT_ZVKT
+
+static const unsigned int riscv_zvkn_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKN
+};
+
+static const unsigned int riscv_zvknc_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKN,
+	RISCV_ISA_EXT_ZVBC
+};
+
+static const unsigned int riscv_zvkng_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKN,
+	RISCV_ISA_EXT_ZVKG
+};
+
+#define RISCV_ISA_EXT_ZVKS	\
+	RISCV_ISA_EXT_ZVKSED,	\
+	RISCV_ISA_EXT_ZVKSH,	\
+	RISCV_ISA_EXT_ZVKB,	\
+	RISCV_ISA_EXT_ZVKT
+
+static const unsigned int riscv_zvks_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKS
+};
+
+static const unsigned int riscv_zvksc_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKS,
+	RISCV_ISA_EXT_ZVBC
+};
+
+static const unsigned int riscv_zvksg_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKS,
+	RISCV_ISA_EXT_ZVKG
+};
+
+static const unsigned int riscv_zvbb_exts[] = {
+	RISCV_ISA_EXT_ZVKB
+};
+
+/*
+ * While the [ms]envcfg CSRs were not defined until version 1.12 of the RISC-V
+ * privileged ISA, the existence of the CSRs is implied by any extension which
+ * specifies [ms]envcfg bit(s). Hence, we define a custom ISA extension for the
+ * existence of the CSR, and treat it as a subset of those other extensions.
+ */
+static const unsigned int riscv_xlinuxenvcfg_exts[] = {
+	RISCV_ISA_EXT_XLINUXENVCFG
+};
+
 /*
  * The canonical order of ISA extension names in the ISA string is defined in
  * chapter 27 of the unprivileged specification.
@@ -160,23 +259,57 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(d, RISCV_ISA_EXT_d),
 	__RISCV_ISA_EXT_DATA(q, RISCV_ISA_EXT_q),
 	__RISCV_ISA_EXT_DATA(c, RISCV_ISA_EXT_c),
-	__RISCV_ISA_EXT_DATA(b, RISCV_ISA_EXT_b),
-	__RISCV_ISA_EXT_DATA(k, RISCV_ISA_EXT_k),
-	__RISCV_ISA_EXT_DATA(j, RISCV_ISA_EXT_j),
-	__RISCV_ISA_EXT_DATA(p, RISCV_ISA_EXT_p),
 	__RISCV_ISA_EXT_DATA(v, RISCV_ISA_EXT_v),
 	__RISCV_ISA_EXT_DATA(h, RISCV_ISA_EXT_h),
-	__RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM),
-	__RISCV_ISA_EXT_DATA(zicboz, RISCV_ISA_EXT_ZICBOZ),
+	__RISCV_ISA_EXT_SUPERSET(zicbom, RISCV_ISA_EXT_ZICBOM, riscv_xlinuxenvcfg_exts),
+	__RISCV_ISA_EXT_SUPERSET(zicboz, RISCV_ISA_EXT_ZICBOZ, riscv_xlinuxenvcfg_exts),
 	__RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR),
 	__RISCV_ISA_EXT_DATA(zicond, RISCV_ISA_EXT_ZICOND),
 	__RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR),
 	__RISCV_ISA_EXT_DATA(zifencei, RISCV_ISA_EXT_ZIFENCEI),
+	__RISCV_ISA_EXT_DATA(zihintntl, RISCV_ISA_EXT_ZIHINTNTL),
 	__RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
 	__RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM),
+	__RISCV_ISA_EXT_DATA(zacas, RISCV_ISA_EXT_ZACAS),
+	__RISCV_ISA_EXT_DATA(zfa, RISCV_ISA_EXT_ZFA),
+	__RISCV_ISA_EXT_DATA(zfh, RISCV_ISA_EXT_ZFH),
+	__RISCV_ISA_EXT_DATA(zfhmin, RISCV_ISA_EXT_ZFHMIN),
 	__RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA),
 	__RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB),
+	__RISCV_ISA_EXT_DATA(zbc, RISCV_ISA_EXT_ZBC),
+	__RISCV_ISA_EXT_DATA(zbkb, RISCV_ISA_EXT_ZBKB),
+	__RISCV_ISA_EXT_DATA(zbkc, RISCV_ISA_EXT_ZBKC),
+	__RISCV_ISA_EXT_DATA(zbkx, RISCV_ISA_EXT_ZBKX),
 	__RISCV_ISA_EXT_DATA(zbs, RISCV_ISA_EXT_ZBS),
+	__RISCV_ISA_EXT_BUNDLE(zk, riscv_zk_bundled_exts),
+	__RISCV_ISA_EXT_BUNDLE(zkn, riscv_zkn_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zknd, RISCV_ISA_EXT_ZKND),
+	__RISCV_ISA_EXT_DATA(zkne, RISCV_ISA_EXT_ZKNE),
+	__RISCV_ISA_EXT_DATA(zknh, RISCV_ISA_EXT_ZKNH),
+	__RISCV_ISA_EXT_DATA(zkr, RISCV_ISA_EXT_ZKR),
+	__RISCV_ISA_EXT_BUNDLE(zks, riscv_zks_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zkt, RISCV_ISA_EXT_ZKT),
+	__RISCV_ISA_EXT_DATA(zksed, RISCV_ISA_EXT_ZKSED),
+	__RISCV_ISA_EXT_DATA(zksh, RISCV_ISA_EXT_ZKSH),
+	__RISCV_ISA_EXT_DATA(ztso, RISCV_ISA_EXT_ZTSO),
+	__RISCV_ISA_EXT_SUPERSET(zvbb, RISCV_ISA_EXT_ZVBB, riscv_zvbb_exts),
+	__RISCV_ISA_EXT_DATA(zvbc, RISCV_ISA_EXT_ZVBC),
+	__RISCV_ISA_EXT_DATA(zvfh, RISCV_ISA_EXT_ZVFH),
+	__RISCV_ISA_EXT_DATA(zvfhmin, RISCV_ISA_EXT_ZVFHMIN),
+	__RISCV_ISA_EXT_DATA(zvkb, RISCV_ISA_EXT_ZVKB),
+	__RISCV_ISA_EXT_DATA(zvkg, RISCV_ISA_EXT_ZVKG),
+	__RISCV_ISA_EXT_BUNDLE(zvkn, riscv_zvkn_bundled_exts),
+	__RISCV_ISA_EXT_BUNDLE(zvknc, riscv_zvknc_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zvkned, RISCV_ISA_EXT_ZVKNED),
+	__RISCV_ISA_EXT_BUNDLE(zvkng, riscv_zvkng_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zvknha, RISCV_ISA_EXT_ZVKNHA),
+	__RISCV_ISA_EXT_DATA(zvknhb, RISCV_ISA_EXT_ZVKNHB),
+	__RISCV_ISA_EXT_BUNDLE(zvks, riscv_zvks_bundled_exts),
+	__RISCV_ISA_EXT_BUNDLE(zvksc, riscv_zvksc_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zvksed, RISCV_ISA_EXT_ZVKSED),
+	__RISCV_ISA_EXT_DATA(zvksh, RISCV_ISA_EXT_ZVKSH),
+	__RISCV_ISA_EXT_BUNDLE(zvksg, riscv_zvksg_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zvkt, RISCV_ISA_EXT_ZVKT),
 	__RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA),
 	__RISCV_ISA_EXT_DATA(smstateen, RISCV_ISA_EXT_SMSTATEEN),
 	__RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA),
@@ -189,6 +322,31 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 
 const size_t riscv_isa_ext_count = ARRAY_SIZE(riscv_isa_ext);
 
+static void __init match_isa_ext(const struct riscv_isa_ext_data *ext, const char *name,
+				 const char *name_end, struct riscv_isainfo *isainfo)
+{
+	if ((name_end - name == strlen(ext->name)) &&
+	     !strncasecmp(name, ext->name, name_end - name)) {
+		/*
+		 * If this is a bundle, enable all the ISA extensions that
+		 * comprise the bundle.
+		 */
+		if (ext->subset_ext_size) {
+			for (int i = 0; i < ext->subset_ext_size; i++) {
+				if (riscv_isa_extension_check(ext->subset_ext_ids[i]))
+					set_bit(ext->subset_ext_ids[i], isainfo->isa);
+			}
+		}
+
+		/*
+		 * This is valid even for bundle extensions which uses the RISCV_ISA_EXT_INVALID id
+		 * (rejected by riscv_isa_extension_check()).
+		 */
+		if (riscv_isa_extension_check(ext->id))
+			set_bit(ext->id, isainfo->isa);
+	}
+}
+
 static void __init riscv_parse_isa_string(unsigned long *this_hwcap, struct riscv_isainfo *isainfo,
 					  unsigned long *isa2hwcap, const char *isa)
 {
@@ -321,14 +479,6 @@ static void __init riscv_parse_isa_string(unsigned long *this_hwcap, struct risc
 		if (*isa == '_')
 			++isa;
 
-#define SET_ISA_EXT_MAP(name, bit)						\
-		do {								\
-			if ((ext_end - ext == strlen(name)) &&			\
-			     !strncasecmp(ext, name, strlen(name)) &&		\
-			     riscv_isa_extension_check(bit))			\
-				set_bit(bit, isainfo->isa);			\
-		} while (false)							\
-
 		if (unlikely(ext_err))
 			continue;
 		if (!ext_long) {
@@ -340,10 +490,8 @@ static void __init riscv_parse_isa_string(unsigned long *this_hwcap, struct risc
 			}
 		} else {
 			for (int i = 0; i < riscv_isa_ext_count; i++)
-				SET_ISA_EXT_MAP(riscv_isa_ext[i].name,
-						riscv_isa_ext[i].id);
+				match_isa_ext(&riscv_isa_ext[i], ext, ext_end, isainfo);
 		}
-#undef SET_ISA_EXT_MAP
 	}
 }
 
@@ -402,6 +550,20 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap)
 		}
 
 		/*
+		 * "V" in ISA strings is ambiguous in practice: it should mean
+		 * just the standard V-1.0 but vendors aren't well behaved.
+		 * Many vendors with T-Head CPU cores which implement the 0.7.1
+		 * version of the vector specification put "v" into their DTs.
+		 * CPU cores with the ratified spec will contain non-zero
+		 * marchid.
+		 */
+		if (acpi_disabled && riscv_cached_mvendorid(cpu) == THEAD_VENDOR_ID &&
+		    riscv_cached_marchid(cpu) == 0x0) {
+			this_hwcap &= ~isa2hwcap[RISCV_ISA_EXT_v];
+			clear_bit(RISCV_ISA_EXT_v, isainfo->isa);
+		}
+
+		/*
 		 * All "okay" hart should have same isa. Set HWCAP based on
 		 * common capabilities of every "okay" hart, in case they don't
 		 * have.
@@ -442,18 +604,26 @@ static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap)
 		}
 
 		for (int i = 0; i < riscv_isa_ext_count; i++) {
+			const struct riscv_isa_ext_data *ext = &riscv_isa_ext[i];
+
 			if (of_property_match_string(cpu_node, "riscv,isa-extensions",
-						     riscv_isa_ext[i].property) < 0)
+						     ext->property) < 0)
 				continue;
 
-			if (!riscv_isa_extension_check(riscv_isa_ext[i].id))
-				continue;
+			if (ext->subset_ext_size) {
+				for (int j = 0; j < ext->subset_ext_size; j++) {
+					if (riscv_isa_extension_check(ext->subset_ext_ids[i]))
+						set_bit(ext->subset_ext_ids[j], isainfo->isa);
+				}
+			}
 
-			/* Only single letter extensions get set in hwcap */
-			if (strnlen(riscv_isa_ext[i].name, 2) == 1)
-				this_hwcap |= isa2hwcap[riscv_isa_ext[i].id];
+			if (riscv_isa_extension_check(ext->id)) {
+				set_bit(ext->id, isainfo->isa);
 
-			set_bit(riscv_isa_ext[i].id, isainfo->isa);
+				/* Only single letter extensions get set in hwcap */
+				if (strnlen(riscv_isa_ext[i].name, 2) == 1)
+					this_hwcap |= isa2hwcap[riscv_isa_ext[i].id];
+			}
 		}
 
 		of_node_put(cpu_node);
@@ -643,6 +813,16 @@ static int check_unaligned_access(void *param)
 		(speed == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "slow");
 
 	per_cpu(misaligned_access_speed, cpu) = speed;
+
+	/*
+	 * Set the value of fast_misaligned_access of a CPU. These operations
+	 * are atomic to avoid race conditions.
+	 */
+	if (speed == RISCV_HWPROBE_MISALIGNED_FAST)
+		cpumask_set_cpu(cpu, &fast_misaligned_access);
+	else
+		cpumask_clear_cpu(cpu, &fast_misaligned_access);
+
 	return 0;
 }
 
@@ -655,13 +835,69 @@ static void check_unaligned_access_nonboot_cpu(void *param)
 		check_unaligned_access(pages[cpu]);
 }
 
+DEFINE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key);
+
+static void modify_unaligned_access_branches(cpumask_t *mask, int weight)
+{
+	if (cpumask_weight(mask) == weight)
+		static_branch_enable_cpuslocked(&fast_misaligned_access_speed_key);
+	else
+		static_branch_disable_cpuslocked(&fast_misaligned_access_speed_key);
+}
+
+static void set_unaligned_access_static_branches_except_cpu(int cpu)
+{
+	/*
+	 * Same as set_unaligned_access_static_branches, except excludes the
+	 * given CPU from the result. When a CPU is hotplugged into an offline
+	 * state, this function is called before the CPU is set to offline in
+	 * the cpumask, and thus the CPU needs to be explicitly excluded.
+	 */
+
+	cpumask_t fast_except_me;
+
+	cpumask_and(&fast_except_me, &fast_misaligned_access, cpu_online_mask);
+	cpumask_clear_cpu(cpu, &fast_except_me);
+
+	modify_unaligned_access_branches(&fast_except_me, num_online_cpus() - 1);
+}
+
+static void set_unaligned_access_static_branches(void)
+{
+	/*
+	 * This will be called after check_unaligned_access_all_cpus so the
+	 * result of unaligned access speed for all CPUs will be available.
+	 *
+	 * To avoid the number of online cpus changing between reading
+	 * cpu_online_mask and calling num_online_cpus, cpus_read_lock must be
+	 * held before calling this function.
+	 */
+
+	cpumask_t fast_and_online;
+
+	cpumask_and(&fast_and_online, &fast_misaligned_access, cpu_online_mask);
+
+	modify_unaligned_access_branches(&fast_and_online, num_online_cpus());
+}
+
+static int lock_and_set_unaligned_access_static_branch(void)
+{
+	cpus_read_lock();
+	set_unaligned_access_static_branches();
+	cpus_read_unlock();
+
+	return 0;
+}
+
+arch_initcall_sync(lock_and_set_unaligned_access_static_branch);
+
 static int riscv_online_cpu(unsigned int cpu)
 {
 	static struct page *buf;
 
 	/* We are already set since the last check */
 	if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN)
-		return 0;
+		goto exit;
 
 	buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
 	if (!buf) {
@@ -671,6 +907,17 @@ static int riscv_online_cpu(unsigned int cpu)
 
 	check_unaligned_access(buf);
 	__free_pages(buf, MISALIGNED_BUFFER_ORDER);
+
+exit:
+	set_unaligned_access_static_branches();
+
+	return 0;
+}
+
+static int riscv_offline_cpu(unsigned int cpu)
+{
+	set_unaligned_access_static_branches_except_cpu(cpu);
+
 	return 0;
 }
 
@@ -705,9 +952,12 @@ static int check_unaligned_access_all_cpus(void)
 	/* Check core 0. */
 	smp_call_on_cpu(0, check_unaligned_access, bufs[0], true);
 
-	/* Setup hotplug callback for any new CPUs that come online. */
+	/*
+	 * Setup hotplug callbacks for any new CPUs that come online or go
+	 * offline.
+	 */
 	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online",
-				  riscv_online_cpu, NULL);
+				  riscv_online_cpu, riscv_offline_cpu);
 
 out:
 	unaligned_emulation_finish();
@@ -725,7 +975,7 @@ arch_initcall(check_unaligned_access_all_cpus);
 void riscv_user_isa_enable(void)
 {
 	if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_ZICBOZ))
-		csr_set(CSR_SENVCFG, ENVCFG_CBZE);
+		csr_set(CSR_ENVCFG, ENVCFG_CBZE);
 }
 
 #ifdef CONFIG_RISCV_ALTERNATIVE
diff --git a/arch/riscv/kernel/efi.c b/arch/riscv/kernel/efi.c
index aa6209a74c83..b64bf1624a05 100644
--- a/arch/riscv/kernel/efi.c
+++ b/arch/riscv/kernel/efi.c
@@ -60,7 +60,7 @@ int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
 static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data)
 {
 	efi_memory_desc_t *md = data;
-	pte_t pte = READ_ONCE(*ptep);
+	pte_t pte = ptep_get(ptep);
 	unsigned long val;
 
 	if (md->attribute & EFI_MEMORY_RO) {
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 54ca4564a926..9d1a305d5508 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -83,6 +83,10 @@ SYM_CODE_START(handle_exception)
 	/* Load the kernel shadow call stack pointer if coming from userspace */
 	scs_load_current_if_task_changed s5
 
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	move a0, sp
+	call riscv_v_context_nesting_start
+#endif
 	move a0, sp /* pt_regs */
 	la ra, ret_from_exception
 
@@ -138,6 +142,10 @@ SYM_CODE_START_NOALIGN(ret_from_exception)
 	 */
 	csrw CSR_SCRATCH, tp
 1:
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	move a0, sp
+	call riscv_v_context_nesting_end
+#endif
 	REG_L a0, PT_STATUS(sp)
 	/*
 	 * The current load reservation is effectively part of the processor's
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 03a6434a8cdd..f5aa24d9e1c1 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -178,32 +178,28 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *op, struct ftrace_regs *fregs)
+{
+	struct pt_regs *regs = arch_ftrace_get_regs(fregs);
+	unsigned long *parent = (unsigned long *)&regs->ra;
+
+	prepare_ftrace_return(parent, ip, frame_pointer(regs));
+}
+#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 extern void ftrace_graph_call(void);
-extern void ftrace_graph_regs_call(void);
 int ftrace_enable_ftrace_graph_caller(void)
 {
-	int ret;
-
-	ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call,
-				    (unsigned long)&prepare_ftrace_return, true, true);
-	if (ret)
-		return ret;
-
-	return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call,
+	return __ftrace_modify_call((unsigned long)&ftrace_graph_call,
 				    (unsigned long)&prepare_ftrace_return, true, true);
 }
 
 int ftrace_disable_ftrace_graph_caller(void)
 {
-	int ret;
-
-	ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call,
-				    (unsigned long)&prepare_ftrace_return, false, true);
-	if (ret)
-		return ret;
-
-	return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call,
+	return __ftrace_modify_call((unsigned long)&ftrace_graph_call,
 				    (unsigned long)&prepare_ftrace_return, false, true);
 }
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 #endif /* CONFIG_DYNAMIC_FTRACE */
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 76ace1e0b46f..4236a69c35cb 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -11,7 +11,6 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/csr.h>
-#include <asm/cpu_ops_sbi.h>
 #include <asm/hwcap.h>
 #include <asm/image.h>
 #include <asm/scs.h>
@@ -89,6 +88,7 @@ relocate_enable_mmu:
 	/* Compute satp for kernel page tables, but don't load it yet */
 	srl a2, a0, PAGE_SHIFT
 	la a1, satp_mode
+	XIP_FIXUP_OFFSET a1
 	REG_L a1, 0(a1)
 	or a2, a2, a1
 
@@ -265,10 +265,12 @@ SYM_CODE_START(_start_kernel)
 	la sp, _end + THREAD_SIZE
 	XIP_FIXUP_OFFSET sp
 	mv s0, a0
+	mv s1, a1
 	call __copy_data
 
-	/* Restore a0 copy */
+	/* Restore a0 & a1 copy */
 	mv a0, s0
+	mv a1, s1
 #endif
 
 #ifndef CONFIG_XIP_KERNEL
diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c
new file mode 100644
index 000000000000..6afe80c7f03a
--- /dev/null
+++ b/arch/riscv/kernel/kernel_mode_vector.c
@@ -0,0 +1,247 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2021 SiFive
+ */
+#include <linux/compiler.h>
+#include <linux/irqflags.h>
+#include <linux/percpu.h>
+#include <linux/preempt.h>
+#include <linux/types.h>
+
+#include <asm/vector.h>
+#include <asm/switch_to.h>
+#include <asm/simd.h>
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+#include <asm/asm-prototypes.h>
+#endif
+
+static inline void riscv_v_flags_set(u32 flags)
+{
+	WRITE_ONCE(current->thread.riscv_v_flags, flags);
+}
+
+static inline void riscv_v_start(u32 flags)
+{
+	int orig;
+
+	orig = riscv_v_flags();
+	BUG_ON((orig & flags) != 0);
+	riscv_v_flags_set(orig | flags);
+	barrier();
+}
+
+static inline void riscv_v_stop(u32 flags)
+{
+	int orig;
+
+	barrier();
+	orig = riscv_v_flags();
+	BUG_ON((orig & flags) == 0);
+	riscv_v_flags_set(orig & ~flags);
+}
+
+/*
+ * Claim ownership of the CPU vector context for use by the calling context.
+ *
+ * The caller may freely manipulate the vector context metadata until
+ * put_cpu_vector_context() is called.
+ */
+void get_cpu_vector_context(void)
+{
+	/*
+	 * disable softirqs so it is impossible for softirqs to nest
+	 * get_cpu_vector_context() when kernel is actively using Vector.
+	 */
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_bh_disable();
+	else
+		preempt_disable();
+
+	riscv_v_start(RISCV_KERNEL_MODE_V);
+}
+
+/*
+ * Release the CPU vector context.
+ *
+ * Must be called from a context in which get_cpu_vector_context() was
+ * previously called, with no call to put_cpu_vector_context() in the
+ * meantime.
+ */
+void put_cpu_vector_context(void)
+{
+	riscv_v_stop(RISCV_KERNEL_MODE_V);
+
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_bh_enable();
+	else
+		preempt_enable();
+}
+
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+static __always_inline u32 *riscv_v_flags_ptr(void)
+{
+	return &current->thread.riscv_v_flags;
+}
+
+static inline void riscv_preempt_v_set_dirty(void)
+{
+	*riscv_v_flags_ptr() |= RISCV_PREEMPT_V_DIRTY;
+}
+
+static inline void riscv_preempt_v_reset_flags(void)
+{
+	*riscv_v_flags_ptr() &= ~(RISCV_PREEMPT_V_DIRTY | RISCV_PREEMPT_V_NEED_RESTORE);
+}
+
+static inline void riscv_v_ctx_depth_inc(void)
+{
+	*riscv_v_flags_ptr() += RISCV_V_CTX_UNIT_DEPTH;
+}
+
+static inline void riscv_v_ctx_depth_dec(void)
+{
+	*riscv_v_flags_ptr() -= RISCV_V_CTX_UNIT_DEPTH;
+}
+
+static inline u32 riscv_v_ctx_get_depth(void)
+{
+	return *riscv_v_flags_ptr() & RISCV_V_CTX_DEPTH_MASK;
+}
+
+static int riscv_v_stop_kernel_context(void)
+{
+	if (riscv_v_ctx_get_depth() != 0 || !riscv_preempt_v_started(current))
+		return 1;
+
+	riscv_preempt_v_clear_dirty(current);
+	riscv_v_stop(RISCV_PREEMPT_V);
+	return 0;
+}
+
+static int riscv_v_start_kernel_context(bool *is_nested)
+{
+	struct __riscv_v_ext_state *kvstate, *uvstate;
+
+	kvstate = &current->thread.kernel_vstate;
+	if (!kvstate->datap)
+		return -ENOENT;
+
+	if (riscv_preempt_v_started(current)) {
+		WARN_ON(riscv_v_ctx_get_depth() == 0);
+		*is_nested = true;
+		get_cpu_vector_context();
+		if (riscv_preempt_v_dirty(current)) {
+			__riscv_v_vstate_save(kvstate, kvstate->datap);
+			riscv_preempt_v_clear_dirty(current);
+		}
+		riscv_preempt_v_set_restore(current);
+		return 0;
+	}
+
+	/* Transfer the ownership of V from user to kernel, then save */
+	riscv_v_start(RISCV_PREEMPT_V | RISCV_PREEMPT_V_DIRTY);
+	if ((task_pt_regs(current)->status & SR_VS) == SR_VS_DIRTY) {
+		uvstate = &current->thread.vstate;
+		__riscv_v_vstate_save(uvstate, uvstate->datap);
+	}
+	riscv_preempt_v_clear_dirty(current);
+	return 0;
+}
+
+/* low-level V context handling code, called with irq disabled */
+asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs)
+{
+	int depth;
+
+	if (!riscv_preempt_v_started(current))
+		return;
+
+	depth = riscv_v_ctx_get_depth();
+	if (depth == 0 && (regs->status & SR_VS) == SR_VS_DIRTY)
+		riscv_preempt_v_set_dirty();
+
+	riscv_v_ctx_depth_inc();
+}
+
+asmlinkage void riscv_v_context_nesting_end(struct pt_regs *regs)
+{
+	struct __riscv_v_ext_state *vstate = &current->thread.kernel_vstate;
+	u32 depth;
+
+	WARN_ON(!irqs_disabled());
+
+	if (!riscv_preempt_v_started(current))
+		return;
+
+	riscv_v_ctx_depth_dec();
+	depth = riscv_v_ctx_get_depth();
+	if (depth == 0) {
+		if (riscv_preempt_v_restore(current)) {
+			__riscv_v_vstate_restore(vstate, vstate->datap);
+			__riscv_v_vstate_clean(regs);
+			riscv_preempt_v_reset_flags();
+		}
+	}
+}
+#else
+#define riscv_v_start_kernel_context(nested)	(-ENOENT)
+#define riscv_v_stop_kernel_context()		(-ENOENT)
+#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */
+
+/*
+ * kernel_vector_begin(): obtain the CPU vector registers for use by the calling
+ * context
+ *
+ * Must not be called unless may_use_simd() returns true.
+ * Task context in the vector registers is saved back to memory as necessary.
+ *
+ * A matching call to kernel_vector_end() must be made before returning from the
+ * calling context.
+ *
+ * The caller may freely use the vector registers until kernel_vector_end() is
+ * called.
+ */
+void kernel_vector_begin(void)
+{
+	bool nested = false;
+
+	if (WARN_ON(!has_vector()))
+		return;
+
+	BUG_ON(!may_use_simd());
+
+	if (riscv_v_start_kernel_context(&nested)) {
+		get_cpu_vector_context();
+		riscv_v_vstate_save(&current->thread.vstate, task_pt_regs(current));
+	}
+
+	if (!nested)
+		riscv_v_vstate_set_restore(current, task_pt_regs(current));
+
+	riscv_v_enable();
+}
+EXPORT_SYMBOL_GPL(kernel_vector_begin);
+
+/*
+ * kernel_vector_end(): give the CPU vector registers back to the current task
+ *
+ * Must be called from a context in which kernel_vector_begin() was previously
+ * called, with no call to kernel_vector_end() in the meantime.
+ *
+ * The caller must not use the vector registers after this function is called,
+ * unless kernel_vector_begin() is called again in the meantime.
+ */
+void kernel_vector_end(void)
+{
+	if (WARN_ON(!has_vector()))
+		return;
+
+	riscv_v_disable();
+
+	if (riscv_v_stop_kernel_context())
+		put_cpu_vector_context();
+}
+EXPORT_SYMBOL_GPL(kernel_vector_end);
diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S
index 58dd96a2a153..b7561288e8da 100644
--- a/arch/riscv/kernel/mcount-dyn.S
+++ b/arch/riscv/kernel/mcount-dyn.S
@@ -3,12 +3,12 @@
 
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/csr.h>
 #include <asm/unistd.h>
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
-#include <asm-generic/export.h>
 #include <asm/ftrace.h>
 
 	.text
@@ -57,31 +57,150 @@
 	.endm
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
-	.macro SAVE_ALL
+
+/**
+* SAVE_ABI_REGS - save regs against the pt_regs struct
+*
+* @all: tell if saving all the regs
+*
+* If all is set, all the regs will be saved, otherwise only ABI
+* related regs (a0-a7,epc,ra and optional s0) will be saved.
+*
+* After the stack is established,
+*
+* 0(sp) stores the PC of the traced function which can be accessed
+* by &(fregs)->regs->epc in tracing function. Note that the real
+* function entry address should be computed with -FENTRY_RA_OFFSET.
+*
+* 8(sp) stores the function return address (i.e. parent IP) that
+* can be accessed by &(fregs)->regs->ra in tracing function.
+*
+* The other regs are saved at the respective localtion and accessed
+* by the respective pt_regs member.
+*
+* Here is the layout of stack for your reference.
+*
+* PT_SIZE_ON_STACK  ->  +++++++++
+*                       + ..... +
+*                       + t3-t6 +
+*                       + s2-s11+
+*                       + a0-a7 + --++++-> ftrace_caller saved
+*                       + s1    +   +
+*                       + s0    + --+
+*                       + t0-t2 +   +
+*                       + tp    +   +
+*                       + gp    +   +
+*                       + sp    +   +
+*                       + ra    + --+ // parent IP
+*               sp  ->  + epc   + --+ // PC
+*                       +++++++++
+**/
+	.macro SAVE_ABI_REGS, all=0
 	addi	sp, sp, -PT_SIZE_ON_STACK
 
-	REG_S t0,  PT_EPC(sp)
-	REG_S x1,  PT_RA(sp)
-	REG_S x2,  PT_SP(sp)
-	REG_S x3,  PT_GP(sp)
-	REG_S x4,  PT_TP(sp)
-	REG_S x5,  PT_T0(sp)
-	save_from_x6_to_x31
+	REG_S	t0,  PT_EPC(sp)
+	REG_S	x1,  PT_RA(sp)
+
+	// save the ABI regs
+
+	REG_S	x10, PT_A0(sp)
+	REG_S	x11, PT_A1(sp)
+	REG_S	x12, PT_A2(sp)
+	REG_S	x13, PT_A3(sp)
+	REG_S	x14, PT_A4(sp)
+	REG_S	x15, PT_A5(sp)
+	REG_S	x16, PT_A6(sp)
+	REG_S	x17, PT_A7(sp)
+
+	// save the leftover regs
+
+	.if \all == 1
+	REG_S	x2, PT_SP(sp)
+	REG_S	x3, PT_GP(sp)
+	REG_S	x4, PT_TP(sp)
+	REG_S	x5, PT_T0(sp)
+	REG_S	x6, PT_T1(sp)
+	REG_S	x7, PT_T2(sp)
+	REG_S	x8, PT_S0(sp)
+	REG_S	x9, PT_S1(sp)
+	REG_S	x18, PT_S2(sp)
+	REG_S	x19, PT_S3(sp)
+	REG_S	x20, PT_S4(sp)
+	REG_S	x21, PT_S5(sp)
+	REG_S	x22, PT_S6(sp)
+	REG_S	x23, PT_S7(sp)
+	REG_S	x24, PT_S8(sp)
+	REG_S	x25, PT_S9(sp)
+	REG_S	x26, PT_S10(sp)
+	REG_S	x27, PT_S11(sp)
+	REG_S	x28, PT_T3(sp)
+	REG_S	x29, PT_T4(sp)
+	REG_S	x30, PT_T5(sp)
+	REG_S	x31, PT_T6(sp)
+
+	// save s0 if FP_TEST defined
+
+	.else
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	REG_S	x8, PT_S0(sp)
+#endif
+	.endif
 	.endm
 
-	.macro RESTORE_ALL
-	REG_L x1,  PT_RA(sp)
-	REG_L x2,  PT_SP(sp)
-	REG_L x3,  PT_GP(sp)
-	REG_L x4,  PT_TP(sp)
-	/* Restore t0 with PT_EPC */
-	REG_L x5,  PT_EPC(sp)
-	restore_from_x6_to_x31
+	.macro RESTORE_ABI_REGS, all=0
+	REG_L	t0, PT_EPC(sp)
+	REG_L	x1, PT_RA(sp)
+	REG_L	x10, PT_A0(sp)
+	REG_L	x11, PT_A1(sp)
+	REG_L	x12, PT_A2(sp)
+	REG_L	x13, PT_A3(sp)
+	REG_L	x14, PT_A4(sp)
+	REG_L	x15, PT_A5(sp)
+	REG_L	x16, PT_A6(sp)
+	REG_L	x17, PT_A7(sp)
 
+	.if \all == 1
+	REG_L	x2, PT_SP(sp)
+	REG_L	x3, PT_GP(sp)
+	REG_L	x4, PT_TP(sp)
+	REG_L	x6, PT_T1(sp)
+	REG_L	x7, PT_T2(sp)
+	REG_L	x8, PT_S0(sp)
+	REG_L	x9, PT_S1(sp)
+	REG_L	x18, PT_S2(sp)
+	REG_L	x19, PT_S3(sp)
+	REG_L	x20, PT_S4(sp)
+	REG_L	x21, PT_S5(sp)
+	REG_L	x22, PT_S6(sp)
+	REG_L	x23, PT_S7(sp)
+	REG_L	x24, PT_S8(sp)
+	REG_L	x25, PT_S9(sp)
+	REG_L	x26, PT_S10(sp)
+	REG_L	x27, PT_S11(sp)
+	REG_L	x28, PT_T3(sp)
+	REG_L	x29, PT_T4(sp)
+	REG_L	x30, PT_T5(sp)
+	REG_L	x31, PT_T6(sp)
+
+	.else
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	REG_L	x8, PT_S0(sp)
+#endif
+	.endif
 	addi	sp, sp, PT_SIZE_ON_STACK
 	.endm
+
+	.macro PREPARE_ARGS
+	addi	a0, t0, -FENTRY_RA_OFFSET
+	la	a1, function_trace_op
+	REG_L	a2, 0(a1)
+	mv	a1, ra
+	mv	a3, sp
+	.endm
+
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 
+#ifndef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 SYM_FUNC_START(ftrace_caller)
 	SAVE_ABI
 
@@ -105,34 +224,39 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 #endif
 	RESTORE_ABI
-	jr t0
+	jr	t0
 SYM_FUNC_END(ftrace_caller)
 
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 SYM_FUNC_START(ftrace_regs_caller)
-	SAVE_ALL
-
-	addi	a0, t0, -FENTRY_RA_OFFSET
-	la	a1, function_trace_op
-	REG_L	a2, 0(a1)
-	mv	a1, ra
-	mv	a3, sp
+	mv	t1, zero
+	SAVE_ABI_REGS 1
+	PREPARE_ARGS
 
 SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	addi	a0, sp, PT_RA
-	REG_L	a1, PT_EPC(sp)
-	addi	a1, a1, -FENTRY_RA_OFFSET
-#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
-	mv	a2, s0
-#endif
-SYM_INNER_LABEL(ftrace_graph_regs_call, SYM_L_GLOBAL)
+	RESTORE_ABI_REGS 1
+	bnez	t1, .Ldirect
+	jr	t0
+.Ldirect:
+	jr	t1
+SYM_FUNC_END(ftrace_regs_caller)
+
+SYM_FUNC_START(ftrace_caller)
+	SAVE_ABI_REGS 0
+	PREPARE_ARGS
+
+SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	call	ftrace_stub
-#endif
 
-	RESTORE_ALL
-	jr t0
-SYM_FUNC_END(ftrace_regs_caller)
+	RESTORE_ABI_REGS 0
+	jr	t0
+SYM_FUNC_END(ftrace_caller)
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+SYM_CODE_START(ftrace_stub_direct_tramp)
+	jr	t0
+SYM_CODE_END(ftrace_stub_direct_tramp)
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S
index b4dd9ed6849e..d7ec69ac6910 100644
--- a/arch/riscv/kernel/mcount.S
+++ b/arch/riscv/kernel/mcount.S
@@ -4,12 +4,12 @@
 #include <linux/init.h>
 #include <linux/linkage.h>
 #include <linux/cfi_types.h>
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/csr.h>
 #include <asm/unistd.h>
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
-#include <asm-generic/export.h>
 #include <asm/ftrace.h>
 
 	.text
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index aac019ed63b1..5e5a82644451 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -723,8 +723,8 @@ static int add_relocation_to_accumulate(struct module *me, int type,
 
 			if (!bucket) {
 				kfree(entry);
-				kfree(rel_head);
 				kfree(rel_head->rel_entry);
+				kfree(rel_head);
 				return -ENOMEM;
 			}
 
@@ -747,6 +747,10 @@ initialize_relocation_hashtable(unsigned int num_relocations,
 {
 	/* Can safely assume that bits is not greater than sizeof(long) */
 	unsigned long hashtable_size = roundup_pow_of_two(num_relocations);
+	/*
+	 * When hashtable_size == 1, hashtable_bits == 0.
+	 * This is valid because the hashing algorithm returns 0 in this case.
+	 */
 	unsigned int hashtable_bits = ilog2(hashtable_size);
 
 	/*
@@ -760,10 +764,10 @@ initialize_relocation_hashtable(unsigned int num_relocations,
 	hashtable_size <<= should_double_size;
 
 	*relocation_hashtable = kmalloc_array(hashtable_size,
-					      sizeof(*relocation_hashtable),
+					      sizeof(**relocation_hashtable),
 					      GFP_KERNEL);
 	if (!*relocation_hashtable)
-		return -ENOMEM;
+		return 0;
 
 	__hash_init(*relocation_hashtable, hashtable_size);
 
@@ -779,6 +783,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 	Elf_Sym *sym;
 	void *location;
 	unsigned int i, type;
+	unsigned int j_idx = 0;
 	Elf_Addr v;
 	int res;
 	unsigned int num_relocations = sechdrs[relsec].sh_size / sizeof(*rel);
@@ -789,8 +794,8 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 	hashtable_bits = initialize_relocation_hashtable(num_relocations,
 							 &relocation_hashtable);
 
-	if (hashtable_bits < 0)
-		return hashtable_bits;
+	if (!relocation_hashtable)
+		return -ENOMEM;
 
 	INIT_LIST_HEAD(&used_buckets_list);
 
@@ -829,9 +834,10 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 		v = sym->st_value + rel[i].r_addend;
 
 		if (type == R_RISCV_PCREL_LO12_I || type == R_RISCV_PCREL_LO12_S) {
-			unsigned int j;
+			unsigned int j = j_idx;
+			bool found = false;
 
-			for (j = 0; j < sechdrs[relsec].sh_size / sizeof(*rel); j++) {
+			do {
 				unsigned long hi20_loc =
 					sechdrs[sechdrs[relsec].sh_info].sh_addr
 					+ rel[j].r_offset;
@@ -860,16 +866,26 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 					hi20 = (offset + 0x800) & 0xfffff000;
 					lo12 = offset - hi20;
 					v = lo12;
+					found = true;
 
 					break;
 				}
-			}
-			if (j == sechdrs[relsec].sh_size / sizeof(*rel)) {
+
+				j++;
+				if (j > sechdrs[relsec].sh_size / sizeof(*rel))
+					j = 0;
+
+			} while (j_idx != j);
+
+			if (!found) {
 				pr_err(
 				  "%s: Can not find HI20 relocation information\n",
 				  me->name);
 				return -EINVAL;
 			}
+
+			/* Record the previous j-loop end index */
+			j_idx = j;
 		}
 
 		if (reloc_handlers[type].accumulate_handler)
@@ -894,7 +910,8 @@ void *module_alloc(unsigned long size)
 {
 	return __vmalloc_node_range(size, 1, MODULES_VADDR,
 				    MODULES_END, GFP_KERNEL,
-				    PAGE_KERNEL, 0, NUMA_NO_NODE,
+				    PAGE_KERNEL, VM_FLUSH_RESET_PERMS,
+				    NUMA_NO_NODE,
 				    __builtin_return_address(0));
 }
 #endif
diff --git a/arch/riscv/kernel/paravirt.c b/arch/riscv/kernel/paravirt.c
new file mode 100644
index 000000000000..0d6225fd3194
--- /dev/null
+++ b/arch/riscv/kernel/paravirt.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023 Ventana Micro Systems Inc.
+ */
+
+#define pr_fmt(fmt) "riscv-pv: " fmt
+
+#include <linux/cpuhotplug.h>
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/jump_label.h>
+#include <linux/kconfig.h>
+#include <linux/kernel.h>
+#include <linux/percpu-defs.h>
+#include <linux/printk.h>
+#include <linux/static_call.h>
+#include <linux/types.h>
+
+#include <asm/barrier.h>
+#include <asm/page.h>
+#include <asm/paravirt.h>
+#include <asm/sbi.h>
+
+struct static_key paravirt_steal_enabled;
+struct static_key paravirt_steal_rq_enabled;
+
+static u64 native_steal_clock(int cpu)
+{
+	return 0;
+}
+
+DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
+
+static bool steal_acc = true;
+static int __init parse_no_stealacc(char *arg)
+{
+	steal_acc = false;
+	return 0;
+}
+
+early_param("no-steal-acc", parse_no_stealacc);
+
+static DEFINE_PER_CPU(struct sbi_sta_struct, steal_time) __aligned(64);
+
+static bool __init has_pv_steal_clock(void)
+{
+	if (sbi_spec_version >= sbi_mk_version(2, 0) &&
+	    sbi_probe_extension(SBI_EXT_STA) > 0) {
+		pr_info("SBI STA extension detected\n");
+		return true;
+	}
+
+	return false;
+}
+
+static int sbi_sta_steal_time_set_shmem(unsigned long lo, unsigned long hi,
+					unsigned long flags)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_STA, SBI_EXT_STA_STEAL_TIME_SET_SHMEM,
+			lo, hi, flags, 0, 0, 0);
+	if (ret.error) {
+		if (lo == SBI_STA_SHMEM_DISABLE && hi == SBI_STA_SHMEM_DISABLE)
+			pr_warn("Failed to disable steal-time shmem");
+		else
+			pr_warn("Failed to set steal-time shmem");
+		return sbi_err_map_linux_errno(ret.error);
+	}
+
+	return 0;
+}
+
+static int pv_time_cpu_online(unsigned int cpu)
+{
+	struct sbi_sta_struct *st = this_cpu_ptr(&steal_time);
+	phys_addr_t pa = __pa(st);
+	unsigned long lo = (unsigned long)pa;
+	unsigned long hi = IS_ENABLED(CONFIG_32BIT) ? upper_32_bits((u64)pa) : 0;
+
+	return sbi_sta_steal_time_set_shmem(lo, hi, 0);
+}
+
+static int pv_time_cpu_down_prepare(unsigned int cpu)
+{
+	return sbi_sta_steal_time_set_shmem(SBI_STA_SHMEM_DISABLE,
+					    SBI_STA_SHMEM_DISABLE, 0);
+}
+
+static u64 pv_time_steal_clock(int cpu)
+{
+	struct sbi_sta_struct *st = per_cpu_ptr(&steal_time, cpu);
+	__le32 sequence;
+	__le64 steal;
+
+	/*
+	 * Check the sequence field before and after reading the steal
+	 * field. Repeat the read if it is different or odd.
+	 */
+	do {
+		sequence = READ_ONCE(st->sequence);
+		virt_rmb();
+		steal = READ_ONCE(st->steal);
+		virt_rmb();
+	} while ((le32_to_cpu(sequence) & 1) ||
+		 sequence != READ_ONCE(st->sequence));
+
+	return le64_to_cpu(steal);
+}
+
+int __init pv_time_init(void)
+{
+	int ret;
+
+	if (!has_pv_steal_clock())
+		return 0;
+
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+				"riscv/pv_time:online",
+				pv_time_cpu_online,
+				pv_time_cpu_down_prepare);
+	if (ret < 0)
+		return ret;
+
+	static_call_update(pv_steal_clock, pv_time_steal_clock);
+
+	static_key_slow_inc(&paravirt_steal_enabled);
+	if (steal_acc)
+		static_key_slow_inc(&paravirt_steal_rq_enabled);
+
+	pr_info("Computing paravirt steal-time\n");
+
+	return 0;
+}
diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
index 13ee7bf589a1..37e87fdcf6a0 100644
--- a/arch/riscv/kernel/patch.c
+++ b/arch/riscv/kernel/patch.c
@@ -14,6 +14,7 @@
 #include <asm/fixmap.h>
 #include <asm/ftrace.h>
 #include <asm/patch.h>
+#include <asm/sections.h>
 
 struct patch_insn {
 	void *addr;
@@ -25,6 +26,14 @@ struct patch_insn {
 int riscv_patch_in_stop_machine = false;
 
 #ifdef CONFIG_MMU
+
+static inline bool is_kernel_exittext(uintptr_t addr)
+{
+	return system_state < SYSTEM_RUNNING &&
+		addr >= (uintptr_t)__exittext_begin &&
+		addr < (uintptr_t)__exittext_end;
+}
+
 /*
  * The fix_to_virt(, idx) needs a const value (not a dynamic variable of
  * reg-a0) or BUILD_BUG_ON failed with "idx >= __end_of_fixed_addresses".
@@ -35,7 +44,7 @@ static __always_inline void *patch_map(void *addr, const unsigned int fixmap)
 	uintptr_t uintaddr = (uintptr_t) addr;
 	struct page *page;
 
-	if (core_kernel_text(uintaddr))
+	if (core_kernel_text(uintaddr) || is_kernel_exittext(uintaddr))
 		page = phys_to_page(__pa_symbol(addr));
 	else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
 		page = vmalloc_to_page(addr);
diff --git a/arch/riscv/kernel/pi/cmdline_early.c b/arch/riscv/kernel/pi/cmdline_early.c
index 68e786c84c94..f6d4dedffb84 100644
--- a/arch/riscv/kernel/pi/cmdline_early.c
+++ b/arch/riscv/kernel/pi/cmdline_early.c
@@ -38,8 +38,7 @@ static char *get_early_cmdline(uintptr_t dtb_pa)
 	if (IS_ENABLED(CONFIG_CMDLINE_EXTEND) ||
 	    IS_ENABLED(CONFIG_CMDLINE_FORCE) ||
 	    fdt_cmdline_size == 0 /* CONFIG_CMDLINE_FALLBACK */) {
-		strncat(early_cmdline, CONFIG_CMDLINE,
-			COMMAND_LINE_SIZE - fdt_cmdline_size);
+		strlcat(early_cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
 	}
 
 	return early_cmdline;
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 4f21d970a129..92922dbd5b5c 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -171,6 +171,7 @@ void flush_thread(void)
 	riscv_v_vstate_off(task_pt_regs(current));
 	kfree(current->thread.vstate.datap);
 	memset(&current->thread.vstate, 0, sizeof(struct __riscv_v_ext_state));
+	clear_tsk_thread_flag(current, TIF_RISCV_V_DEFER_RESTORE);
 #endif
 }
 
@@ -178,7 +179,7 @@ void arch_release_task_struct(struct task_struct *tsk)
 {
 	/* Free the vector context of datap. */
 	if (has_vector())
-		kfree(tsk->thread.vstate.datap);
+		riscv_v_thread_free(tsk);
 }
 
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
@@ -187,6 +188,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	*dst = *src;
 	/* clear entire V context, including datap for a new task */
 	memset(&dst->thread.vstate, 0, sizeof(struct __riscv_v_ext_state));
+	memset(&dst->thread.kernel_vstate, 0, sizeof(struct __riscv_v_ext_state));
+	clear_tsk_thread_flag(dst, TIF_RISCV_V_DEFER_RESTORE);
 
 	return 0;
 }
@@ -221,7 +224,15 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		childregs->a0 = 0; /* Return value of fork() */
 		p->thread.s[0] = 0;
 	}
+	p->thread.riscv_v_flags = 0;
+	if (has_vector())
+		riscv_v_thread_alloc(p);
 	p->thread.ra = (unsigned long)ret_from_fork;
 	p->thread.sp = (unsigned long)childregs; /* kernel sp */
 	return 0;
 }
+
+void __init arch_task_cache_init(void)
+{
+	riscv_v_setup_ctx_cache();
+}
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 2afe460de16a..e8515aa9d80b 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -99,8 +99,11 @@ static int riscv_vr_get(struct task_struct *target,
 	 * Ensure the vector registers have been saved to the memory before
 	 * copying them to membuf.
 	 */
-	if (target == current)
-		riscv_v_vstate_save(current, task_pt_regs(current));
+	if (target == current) {
+		get_cpu_vector_context();
+		riscv_v_vstate_save(&current->thread.vstate, task_pt_regs(current));
+		put_cpu_vector_context();
+	}
 
 	ptrace_vstate.vstart = vstate->vstart;
 	ptrace_vstate.vl = vstate->vl;
diff --git a/arch/riscv/kernel/return_address.c b/arch/riscv/kernel/return_address.c
new file mode 100644
index 000000000000..c8115ec8fb30
--- /dev/null
+++ b/arch/riscv/kernel/return_address.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * This code come from arch/arm64/kernel/return_address.c
+ *
+ * Copyright (C) 2023 SiFive.
+ */
+
+#include <linux/export.h>
+#include <linux/kprobes.h>
+#include <linux/stacktrace.h>
+
+struct return_address_data {
+	unsigned int level;
+	void *addr;
+};
+
+static bool save_return_addr(void *d, unsigned long pc)
+{
+	struct return_address_data *data = d;
+
+	if (!data->level) {
+		data->addr = (void *)pc;
+		return false;
+	}
+
+	--data->level;
+
+	return true;
+}
+NOKPROBE_SYMBOL(save_return_addr);
+
+noinline void *return_address(unsigned int level)
+{
+	struct return_address_data data;
+
+	data.level = level + 3;
+	data.addr = NULL;
+
+	arch_stack_walk(save_return_addr, &data, current, NULL);
+
+	if (!data.level)
+		return data.addr;
+	else
+		return NULL;
+
+}
+EXPORT_SYMBOL_GPL(return_address);
+NOKPROBE_SYMBOL(return_address);
diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c
index 5a62ed1da453..e66e0999a800 100644
--- a/arch/riscv/kernel/sbi.c
+++ b/arch/riscv/kernel/sbi.c
@@ -7,6 +7,7 @@
 
 #include <linux/bits.h>
 #include <linux/init.h>
+#include <linux/mm.h>
 #include <linux/pm.h>
 #include <linux/reboot.h>
 #include <asm/sbi.h>
@@ -571,6 +572,66 @@ long sbi_get_mimpid(void)
 }
 EXPORT_SYMBOL_GPL(sbi_get_mimpid);
 
+bool sbi_debug_console_available;
+
+int sbi_debug_console_write(const char *bytes, unsigned int num_bytes)
+{
+	phys_addr_t base_addr;
+	struct sbiret ret;
+
+	if (!sbi_debug_console_available)
+		return -EOPNOTSUPP;
+
+	if (is_vmalloc_addr(bytes))
+		base_addr = page_to_phys(vmalloc_to_page(bytes)) +
+			    offset_in_page(bytes);
+	else
+		base_addr = __pa(bytes);
+	if (PAGE_SIZE < (offset_in_page(bytes) + num_bytes))
+		num_bytes = PAGE_SIZE - offset_in_page(bytes);
+
+	if (IS_ENABLED(CONFIG_32BIT))
+		ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_WRITE,
+				num_bytes, lower_32_bits(base_addr),
+				upper_32_bits(base_addr), 0, 0, 0);
+	else
+		ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_WRITE,
+				num_bytes, base_addr, 0, 0, 0, 0);
+
+	if (ret.error == SBI_ERR_FAILURE)
+		return -EIO;
+	return ret.error ? sbi_err_map_linux_errno(ret.error) : ret.value;
+}
+
+int sbi_debug_console_read(char *bytes, unsigned int num_bytes)
+{
+	phys_addr_t base_addr;
+	struct sbiret ret;
+
+	if (!sbi_debug_console_available)
+		return -EOPNOTSUPP;
+
+	if (is_vmalloc_addr(bytes))
+		base_addr = page_to_phys(vmalloc_to_page(bytes)) +
+			    offset_in_page(bytes);
+	else
+		base_addr = __pa(bytes);
+	if (PAGE_SIZE < (offset_in_page(bytes) + num_bytes))
+		num_bytes = PAGE_SIZE - offset_in_page(bytes);
+
+	if (IS_ENABLED(CONFIG_32BIT))
+		ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_READ,
+				num_bytes, lower_32_bits(base_addr),
+				upper_32_bits(base_addr), 0, 0, 0);
+	else
+		ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_READ,
+				num_bytes, base_addr, 0, 0, 0, 0);
+
+	if (ret.error == SBI_ERR_FAILURE)
+		return -EIO;
+	return ret.error ? sbi_err_map_linux_errno(ret.error) : ret.value;
+}
+
 void __init sbi_init(void)
 {
 	int ret;
@@ -612,6 +673,11 @@ void __init sbi_init(void)
 			sbi_srst_reboot_nb.priority = 192;
 			register_restart_handler(&sbi_srst_reboot_nb);
 		}
+		if ((sbi_spec_version >= sbi_mk_version(2, 0)) &&
+		    (sbi_probe_extension(SBI_EXT_DBCN) > 0)) {
+			pr_info("SBI DBCN extension detected\n");
+			sbi_debug_console_available = true;
+		}
 	} else {
 		__sbi_set_timer = __sbi_set_timer_v01;
 		__sbi_send_ipi	= __sbi_send_ipi_v01;
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 535a837de55d..4f73c0ae44b2 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -26,7 +26,6 @@
 #include <asm/alternative.h>
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
-#include <asm/cpu_ops.h>
 #include <asm/early_ioremap.h>
 #include <asm/pgtable.h>
 #include <asm/setup.h>
@@ -51,7 +50,6 @@ atomic_t hart_lottery __section(".sdata")
 #endif
 ;
 unsigned long boot_cpu_hartid;
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
 
 /*
  * Place kernel memory regions on the resource tree so that
@@ -299,23 +297,10 @@ void __init setup_arch(char **cmdline_p)
 	riscv_user_isa_enable();
 }
 
-static int __init topology_init(void)
+bool arch_cpu_is_hotpluggable(int cpu)
 {
-	int i, ret;
-
-	for_each_possible_cpu(i) {
-		struct cpu *cpu = &per_cpu(cpu_devices, i);
-
-		cpu->hotpluggable = cpu_has_hotplug(i);
-		ret = register_cpu(cpu, i);
-		if (unlikely(ret))
-			pr_warn("Warning: %s: register_cpu %d failed (%d)\n",
-			       __func__, i, ret);
-	}
-
-	return 0;
+	return cpu_has_hotplug(cpu);
 }
-subsys_initcall(topology_init);
 
 void free_initmem(void)
 {
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 88b6220b2608..501e66debf69 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -86,12 +86,15 @@ static long save_v_state(struct pt_regs *regs, void __user **sc_vec)
 	/* datap is designed to be 16 byte aligned for better performance */
 	WARN_ON(unlikely(!IS_ALIGNED((unsigned long)datap, 16)));
 
-	riscv_v_vstate_save(current, regs);
+	get_cpu_vector_context();
+	riscv_v_vstate_save(&current->thread.vstate, regs);
+	put_cpu_vector_context();
+
 	/* Copy everything of vstate but datap. */
 	err = __copy_to_user(&state->v_state, &current->thread.vstate,
 			     offsetof(struct __riscv_v_ext_state, datap));
 	/* Copy the pointer datap itself. */
-	err |= __put_user(datap, &state->v_state.datap);
+	err |= __put_user((__force void *)datap, &state->v_state.datap);
 	/* Copy the whole vector content to user space datap. */
 	err |= __copy_to_user(datap, current->thread.vstate.datap, riscv_v_vsize);
 	/* Copy magic to the user space after saving  all vector conetext */
@@ -134,7 +137,7 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec)
 	if (unlikely(err))
 		return err;
 
-	riscv_v_vstate_restore(current, regs);
+	riscv_v_vstate_set_restore(current, regs);
 
 	return err;
 }
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index 40420afbb1a0..45dd4035416e 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -81,7 +81,7 @@ static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
 
 #ifdef CONFIG_HOTPLUG_CPU
 	if (cpu_has_hotplug(cpu))
-		cpu_ops[cpu]->cpu_stop();
+		cpu_ops->cpu_stop();
 #endif
 
 	for(;;)
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index d162bf339beb..519b6bd946e5 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -49,7 +49,6 @@ void __init smp_prepare_boot_cpu(void)
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	int cpuid;
-	int ret;
 	unsigned int curr_cpuid;
 
 	init_cpu_topology();
@@ -66,11 +65,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	for_each_possible_cpu(cpuid) {
 		if (cpuid == curr_cpuid)
 			continue;
-		if (cpu_ops[cpuid]->cpu_prepare) {
-			ret = cpu_ops[cpuid]->cpu_prepare(cpuid);
-			if (ret)
-				continue;
-		}
 		set_cpu_present(cpuid, true);
 		numa_store_cpu_info(cpuid);
 	}
@@ -125,18 +119,7 @@ static int __init acpi_parse_rintc(union acpi_subtable_headers *header, const un
 
 static void __init acpi_parse_and_init_cpus(void)
 {
-	int cpuid;
-
-	cpu_set_ops(0);
-
 	acpi_table_parse_madt(ACPI_MADT_TYPE_RINTC, acpi_parse_rintc, 0);
-
-	for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++) {
-		if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID) {
-			cpu_set_ops(cpuid);
-			set_cpu_possible(cpuid, true);
-		}
-	}
 }
 #else
 #define acpi_parse_and_init_cpus(...)	do { } while (0)
@@ -150,8 +133,6 @@ static void __init of_parse_and_init_cpus(void)
 	int cpuid = 1;
 	int rc;
 
-	cpu_set_ops(0);
-
 	for_each_of_cpu_node(dn) {
 		rc = riscv_early_of_processor_hartid(dn, &hart);
 		if (rc < 0)
@@ -179,27 +160,28 @@ static void __init of_parse_and_init_cpus(void)
 	if (cpuid > nr_cpu_ids)
 		pr_warn("Total number of cpus [%d] is greater than nr_cpus option value [%d]\n",
 			cpuid, nr_cpu_ids);
-
-	for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++) {
-		if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID) {
-			cpu_set_ops(cpuid);
-			set_cpu_possible(cpuid, true);
-		}
-	}
 }
 
 void __init setup_smp(void)
 {
+	int cpuid;
+
+	cpu_set_ops();
+
 	if (acpi_disabled)
 		of_parse_and_init_cpus();
 	else
 		acpi_parse_and_init_cpus();
+
+	for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++)
+		if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID)
+			set_cpu_possible(cpuid, true);
 }
 
 static int start_secondary_cpu(int cpu, struct task_struct *tidle)
 {
-	if (cpu_ops[cpu]->cpu_start)
-		return cpu_ops[cpu]->cpu_start(cpu, tidle);
+	if (cpu_ops->cpu_start)
+		return cpu_ops->cpu_start(cpu, tidle);
 
 	return -EOPNOTSUPP;
 }
diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c
index 3c89b8ec69c4..299795341e8a 100644
--- a/arch/riscv/kernel/suspend.c
+++ b/arch/riscv/kernel/suspend.c
@@ -4,13 +4,19 @@
  * Copyright (c) 2022 Ventana Micro Systems Inc.
  */
 
+#define pr_fmt(fmt) "suspend: " fmt
+
 #include <linux/ftrace.h>
+#include <linux/suspend.h>
 #include <asm/csr.h>
+#include <asm/sbi.h>
 #include <asm/suspend.h>
 
 void suspend_save_csrs(struct suspend_context *context)
 {
 	context->scratch = csr_read(CSR_SCRATCH);
+	if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_XLINUXENVCFG))
+		context->envcfg = csr_read(CSR_ENVCFG);
 	context->tvec = csr_read(CSR_TVEC);
 	context->ie = csr_read(CSR_IE);
 
@@ -32,6 +38,8 @@ void suspend_save_csrs(struct suspend_context *context)
 void suspend_restore_csrs(struct suspend_context *context)
 {
 	csr_write(CSR_SCRATCH, context->scratch);
+	if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_XLINUXENVCFG))
+		csr_write(CSR_ENVCFG, context->envcfg);
 	csr_write(CSR_TVEC, context->tvec);
 	csr_write(CSR_IE, context->ie);
 
@@ -85,3 +93,43 @@ int cpu_suspend(unsigned long arg,
 
 	return rc;
 }
+
+#ifdef CONFIG_RISCV_SBI
+static int sbi_system_suspend(unsigned long sleep_type,
+			      unsigned long resume_addr,
+			      unsigned long opaque)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_SUSP, SBI_EXT_SUSP_SYSTEM_SUSPEND,
+			sleep_type, resume_addr, opaque, 0, 0, 0);
+	if (ret.error)
+		return sbi_err_map_linux_errno(ret.error);
+
+	return ret.value;
+}
+
+static int sbi_system_suspend_enter(suspend_state_t state)
+{
+	return cpu_suspend(SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM, sbi_system_suspend);
+}
+
+static const struct platform_suspend_ops sbi_system_suspend_ops = {
+	.valid = suspend_valid_only_mem,
+	.enter = sbi_system_suspend_enter,
+};
+
+static int __init sbi_system_suspend_init(void)
+{
+	if (sbi_spec_version >= sbi_mk_version(2, 0) &&
+	    sbi_probe_extension(SBI_EXT_SUSP) > 0) {
+		pr_info("SBI SUSP extension detected\n");
+		if (IS_ENABLED(CONFIG_SUSPEND))
+			suspend_set_ops(&sbi_system_suspend_ops);
+	}
+
+	return 0;
+}
+
+arch_initcall(sbi_system_suspend_init);
+#endif /* CONFIG_RISCV_SBI */
diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
new file mode 100644
index 000000000000..a7c56b41efd2
--- /dev/null
+++ b/arch/riscv/kernel/sys_hwprobe.c
@@ -0,0 +1,411 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * The hwprobe interface, for allowing userspace to probe to see which features
+ * are supported by the hardware.  See Documentation/arch/riscv/hwprobe.rst for
+ * more details.
+ */
+#include <linux/syscalls.h>
+#include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
+#include <asm/hwprobe.h>
+#include <asm/sbi.h>
+#include <asm/switch_to.h>
+#include <asm/uaccess.h>
+#include <asm/unistd.h>
+#include <asm/vector.h>
+#include <vdso/vsyscall.h>
+
+
+static void hwprobe_arch_id(struct riscv_hwprobe *pair,
+			    const struct cpumask *cpus)
+{
+	u64 id = -1ULL;
+	bool first = true;
+	int cpu;
+
+	for_each_cpu(cpu, cpus) {
+		u64 cpu_id;
+
+		switch (pair->key) {
+		case RISCV_HWPROBE_KEY_MVENDORID:
+			cpu_id = riscv_cached_mvendorid(cpu);
+			break;
+		case RISCV_HWPROBE_KEY_MIMPID:
+			cpu_id = riscv_cached_mimpid(cpu);
+			break;
+		case RISCV_HWPROBE_KEY_MARCHID:
+			cpu_id = riscv_cached_marchid(cpu);
+			break;
+		}
+
+		if (first) {
+			id = cpu_id;
+			first = false;
+		}
+
+		/*
+		 * If there's a mismatch for the given set, return -1 in the
+		 * value.
+		 */
+		if (id != cpu_id) {
+			id = -1ULL;
+			break;
+		}
+	}
+
+	pair->value = id;
+}
+
+static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
+			     const struct cpumask *cpus)
+{
+	int cpu;
+	u64 missing = 0;
+
+	pair->value = 0;
+	if (has_fpu())
+		pair->value |= RISCV_HWPROBE_IMA_FD;
+
+	if (riscv_isa_extension_available(NULL, c))
+		pair->value |= RISCV_HWPROBE_IMA_C;
+
+	if (has_vector())
+		pair->value |= RISCV_HWPROBE_IMA_V;
+
+	/*
+	 * Loop through and record extensions that 1) anyone has, and 2) anyone
+	 * doesn't have.
+	 */
+	for_each_cpu(cpu, cpus) {
+		struct riscv_isainfo *isainfo = &hart_isa[cpu];
+
+#define EXT_KEY(ext)									\
+	do {										\
+		if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_EXT_##ext))	\
+			pair->value |= RISCV_HWPROBE_EXT_##ext;				\
+		else									\
+			missing |= RISCV_HWPROBE_EXT_##ext;				\
+	} while (false)
+
+		/*
+		 * Only use EXT_KEY() for extensions which can be exposed to userspace,
+		 * regardless of the kernel's configuration, as no other checks, besides
+		 * presence in the hart_isa bitmap, are made.
+		 */
+		EXT_KEY(ZBA);
+		EXT_KEY(ZBB);
+		EXT_KEY(ZBS);
+		EXT_KEY(ZICBOZ);
+		EXT_KEY(ZBC);
+
+		EXT_KEY(ZBKB);
+		EXT_KEY(ZBKC);
+		EXT_KEY(ZBKX);
+		EXT_KEY(ZKND);
+		EXT_KEY(ZKNE);
+		EXT_KEY(ZKNH);
+		EXT_KEY(ZKSED);
+		EXT_KEY(ZKSH);
+		EXT_KEY(ZKT);
+		EXT_KEY(ZIHINTNTL);
+		EXT_KEY(ZTSO);
+		EXT_KEY(ZACAS);
+		EXT_KEY(ZICOND);
+
+		if (has_vector()) {
+			EXT_KEY(ZVBB);
+			EXT_KEY(ZVBC);
+			EXT_KEY(ZVKB);
+			EXT_KEY(ZVKG);
+			EXT_KEY(ZVKNED);
+			EXT_KEY(ZVKNHA);
+			EXT_KEY(ZVKNHB);
+			EXT_KEY(ZVKSED);
+			EXT_KEY(ZVKSH);
+			EXT_KEY(ZVKT);
+			EXT_KEY(ZVFH);
+			EXT_KEY(ZVFHMIN);
+		}
+
+		if (has_fpu()) {
+			EXT_KEY(ZFH);
+			EXT_KEY(ZFHMIN);
+			EXT_KEY(ZFA);
+		}
+#undef EXT_KEY
+	}
+
+	/* Now turn off reporting features if any CPU is missing it. */
+	pair->value &= ~missing;
+}
+
+static bool hwprobe_ext0_has(const struct cpumask *cpus, unsigned long ext)
+{
+	struct riscv_hwprobe pair;
+
+	hwprobe_isa_ext0(&pair, cpus);
+	return (pair.value & ext);
+}
+
+static u64 hwprobe_misaligned(const struct cpumask *cpus)
+{
+	int cpu;
+	u64 perf = -1ULL;
+
+	for_each_cpu(cpu, cpus) {
+		int this_perf = per_cpu(misaligned_access_speed, cpu);
+
+		if (perf == -1ULL)
+			perf = this_perf;
+
+		if (perf != this_perf) {
+			perf = RISCV_HWPROBE_MISALIGNED_UNKNOWN;
+			break;
+		}
+	}
+
+	if (perf == -1ULL)
+		return RISCV_HWPROBE_MISALIGNED_UNKNOWN;
+
+	return perf;
+}
+
+static void hwprobe_one_pair(struct riscv_hwprobe *pair,
+			     const struct cpumask *cpus)
+{
+	switch (pair->key) {
+	case RISCV_HWPROBE_KEY_MVENDORID:
+	case RISCV_HWPROBE_KEY_MARCHID:
+	case RISCV_HWPROBE_KEY_MIMPID:
+		hwprobe_arch_id(pair, cpus);
+		break;
+	/*
+	 * The kernel already assumes that the base single-letter ISA
+	 * extensions are supported on all harts, and only supports the
+	 * IMA base, so just cheat a bit here and tell that to
+	 * userspace.
+	 */
+	case RISCV_HWPROBE_KEY_BASE_BEHAVIOR:
+		pair->value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA;
+		break;
+
+	case RISCV_HWPROBE_KEY_IMA_EXT_0:
+		hwprobe_isa_ext0(pair, cpus);
+		break;
+
+	case RISCV_HWPROBE_KEY_CPUPERF_0:
+		pair->value = hwprobe_misaligned(cpus);
+		break;
+
+	case RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE:
+		pair->value = 0;
+		if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOZ))
+			pair->value = riscv_cboz_block_size;
+		break;
+
+	/*
+	 * For forward compatibility, unknown keys don't fail the whole
+	 * call, but get their element key set to -1 and value set to 0
+	 * indicating they're unrecognized.
+	 */
+	default:
+		pair->key = -1;
+		pair->value = 0;
+		break;
+	}
+}
+
+static int hwprobe_get_values(struct riscv_hwprobe __user *pairs,
+			      size_t pair_count, size_t cpusetsize,
+			      unsigned long __user *cpus_user,
+			      unsigned int flags)
+{
+	size_t out;
+	int ret;
+	cpumask_t cpus;
+
+	/* Check the reserved flags. */
+	if (flags != 0)
+		return -EINVAL;
+
+	/*
+	 * The interface supports taking in a CPU mask, and returns values that
+	 * are consistent across that mask. Allow userspace to specify NULL and
+	 * 0 as a shortcut to all online CPUs.
+	 */
+	cpumask_clear(&cpus);
+	if (!cpusetsize && !cpus_user) {
+		cpumask_copy(&cpus, cpu_online_mask);
+	} else {
+		if (cpusetsize > cpumask_size())
+			cpusetsize = cpumask_size();
+
+		ret = copy_from_user(&cpus, cpus_user, cpusetsize);
+		if (ret)
+			return -EFAULT;
+
+		/*
+		 * Userspace must provide at least one online CPU, without that
+		 * there's no way to define what is supported.
+		 */
+		cpumask_and(&cpus, &cpus, cpu_online_mask);
+		if (cpumask_empty(&cpus))
+			return -EINVAL;
+	}
+
+	for (out = 0; out < pair_count; out++, pairs++) {
+		struct riscv_hwprobe pair;
+
+		if (get_user(pair.key, &pairs->key))
+			return -EFAULT;
+
+		pair.value = 0;
+		hwprobe_one_pair(&pair, &cpus);
+		ret = put_user(pair.key, &pairs->key);
+		if (ret == 0)
+			ret = put_user(pair.value, &pairs->value);
+
+		if (ret)
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int hwprobe_get_cpus(struct riscv_hwprobe __user *pairs,
+			    size_t pair_count, size_t cpusetsize,
+			    unsigned long __user *cpus_user,
+			    unsigned int flags)
+{
+	cpumask_t cpus, one_cpu;
+	bool clear_all = false;
+	size_t i;
+	int ret;
+
+	if (flags != RISCV_HWPROBE_WHICH_CPUS)
+		return -EINVAL;
+
+	if (!cpusetsize || !cpus_user)
+		return -EINVAL;
+
+	if (cpusetsize > cpumask_size())
+		cpusetsize = cpumask_size();
+
+	ret = copy_from_user(&cpus, cpus_user, cpusetsize);
+	if (ret)
+		return -EFAULT;
+
+	if (cpumask_empty(&cpus))
+		cpumask_copy(&cpus, cpu_online_mask);
+
+	cpumask_and(&cpus, &cpus, cpu_online_mask);
+
+	cpumask_clear(&one_cpu);
+
+	for (i = 0; i < pair_count; i++) {
+		struct riscv_hwprobe pair, tmp;
+		int cpu;
+
+		ret = copy_from_user(&pair, &pairs[i], sizeof(pair));
+		if (ret)
+			return -EFAULT;
+
+		if (!riscv_hwprobe_key_is_valid(pair.key)) {
+			clear_all = true;
+			pair = (struct riscv_hwprobe){ .key = -1, };
+			ret = copy_to_user(&pairs[i], &pair, sizeof(pair));
+			if (ret)
+				return -EFAULT;
+		}
+
+		if (clear_all)
+			continue;
+
+		tmp = (struct riscv_hwprobe){ .key = pair.key, };
+
+		for_each_cpu(cpu, &cpus) {
+			cpumask_set_cpu(cpu, &one_cpu);
+
+			hwprobe_one_pair(&tmp, &one_cpu);
+
+			if (!riscv_hwprobe_pair_cmp(&tmp, &pair))
+				cpumask_clear_cpu(cpu, &cpus);
+
+			cpumask_clear_cpu(cpu, &one_cpu);
+		}
+	}
+
+	if (clear_all)
+		cpumask_clear(&cpus);
+
+	ret = copy_to_user(cpus_user, &cpus, cpusetsize);
+	if (ret)
+		return -EFAULT;
+
+	return 0;
+}
+
+static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,
+			    size_t pair_count, size_t cpusetsize,
+			    unsigned long __user *cpus_user,
+			    unsigned int flags)
+{
+	if (flags & RISCV_HWPROBE_WHICH_CPUS)
+		return hwprobe_get_cpus(pairs, pair_count, cpusetsize,
+					cpus_user, flags);
+
+	return hwprobe_get_values(pairs, pair_count, cpusetsize,
+				  cpus_user, flags);
+}
+
+#ifdef CONFIG_MMU
+
+static int __init init_hwprobe_vdso_data(void)
+{
+	struct vdso_data *vd = __arch_get_k_vdso_data();
+	struct arch_vdso_data *avd = &vd->arch_data;
+	u64 id_bitsmash = 0;
+	struct riscv_hwprobe pair;
+	int key;
+
+	/*
+	 * Initialize vDSO data with the answers for the "all CPUs" case, to
+	 * save a syscall in the common case.
+	 */
+	for (key = 0; key <= RISCV_HWPROBE_MAX_KEY; key++) {
+		pair.key = key;
+		hwprobe_one_pair(&pair, cpu_online_mask);
+
+		WARN_ON_ONCE(pair.key < 0);
+
+		avd->all_cpu_hwprobe_values[key] = pair.value;
+		/*
+		 * Smash together the vendor, arch, and impl IDs to see if
+		 * they're all 0 or any negative.
+		 */
+		if (key <= RISCV_HWPROBE_KEY_MIMPID)
+			id_bitsmash |= pair.value;
+	}
+
+	/*
+	 * If the arch, vendor, and implementation ID are all the same across
+	 * all harts, then assume all CPUs are the same, and allow the vDSO to
+	 * answer queries for arbitrary masks. However if all values are 0 (not
+	 * populated) or any value returns -1 (varies across CPUs), then the
+	 * vDSO should defer to the kernel for exotic cpu masks.
+	 */
+	avd->homogeneous_cpus = id_bitsmash != 0 && id_bitsmash != -1;
+	return 0;
+}
+
+arch_initcall_sync(init_hwprobe_vdso_data);
+
+#endif /* CONFIG_MMU */
+
+SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs,
+		size_t, pair_count, size_t, cpusetsize, unsigned long __user *,
+		cpus, unsigned int, flags)
+{
+	return do_riscv_hwprobe(pairs, pair_count, cpusetsize,
+				cpus, flags);
+}
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index a2ca5b7756a5..f1c1416a9f1e 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -7,15 +7,7 @@
 
 #include <linux/syscalls.h>
 #include <asm/cacheflush.h>
-#include <asm/cpufeature.h>
-#include <asm/hwprobe.h>
-#include <asm/sbi.h>
-#include <asm/vector.h>
-#include <asm/switch_to.h>
-#include <asm/uaccess.h>
-#include <asm/unistd.h>
 #include <asm-generic/mman-common.h>
-#include <vdso/vsyscall.h>
 
 static long riscv_sys_mmap(unsigned long addr, unsigned long len,
 			   unsigned long prot, unsigned long flags,
@@ -77,283 +69,6 @@ SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end,
 	return 0;
 }
 
-/*
- * The hwprobe interface, for allowing userspace to probe to see which features
- * are supported by the hardware.  See Documentation/arch/riscv/hwprobe.rst for more
- * details.
- */
-static void hwprobe_arch_id(struct riscv_hwprobe *pair,
-			    const struct cpumask *cpus)
-{
-	u64 id = -1ULL;
-	bool first = true;
-	int cpu;
-
-	for_each_cpu(cpu, cpus) {
-		u64 cpu_id;
-
-		switch (pair->key) {
-		case RISCV_HWPROBE_KEY_MVENDORID:
-			cpu_id = riscv_cached_mvendorid(cpu);
-			break;
-		case RISCV_HWPROBE_KEY_MIMPID:
-			cpu_id = riscv_cached_mimpid(cpu);
-			break;
-		case RISCV_HWPROBE_KEY_MARCHID:
-			cpu_id = riscv_cached_marchid(cpu);
-			break;
-		}
-
-		if (first) {
-			id = cpu_id;
-			first = false;
-		}
-
-		/*
-		 * If there's a mismatch for the given set, return -1 in the
-		 * value.
-		 */
-		if (id != cpu_id) {
-			id = -1ULL;
-			break;
-		}
-	}
-
-	pair->value = id;
-}
-
-static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
-			     const struct cpumask *cpus)
-{
-	int cpu;
-	u64 missing = 0;
-
-	pair->value = 0;
-	if (has_fpu())
-		pair->value |= RISCV_HWPROBE_IMA_FD;
-
-	if (riscv_isa_extension_available(NULL, c))
-		pair->value |= RISCV_HWPROBE_IMA_C;
-
-	if (has_vector())
-		pair->value |= RISCV_HWPROBE_IMA_V;
-
-	/*
-	 * Loop through and record extensions that 1) anyone has, and 2) anyone
-	 * doesn't have.
-	 */
-	for_each_cpu(cpu, cpus) {
-		struct riscv_isainfo *isainfo = &hart_isa[cpu];
-
-#define EXT_KEY(ext)									\
-	do {										\
-		if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_EXT_##ext))	\
-			pair->value |= RISCV_HWPROBE_EXT_##ext;				\
-		else									\
-			missing |= RISCV_HWPROBE_EXT_##ext;				\
-	} while (false)
-
-		/*
-		 * Only use EXT_KEY() for extensions which can be exposed to userspace,
-		 * regardless of the kernel's configuration, as no other checks, besides
-		 * presence in the hart_isa bitmap, are made.
-		 */
-		EXT_KEY(ZBA);
-		EXT_KEY(ZBB);
-		EXT_KEY(ZBS);
-		EXT_KEY(ZICBOZ);
-#undef EXT_KEY
-	}
-
-	/* Now turn off reporting features if any CPU is missing it. */
-	pair->value &= ~missing;
-}
-
-static bool hwprobe_ext0_has(const struct cpumask *cpus, u64 ext)
-{
-	struct riscv_hwprobe pair;
-
-	hwprobe_isa_ext0(&pair, cpus);
-	return (pair.value & ext);
-}
-
-static u64 hwprobe_misaligned(const struct cpumask *cpus)
-{
-	int cpu;
-	u64 perf = -1ULL;
-
-	for_each_cpu(cpu, cpus) {
-		int this_perf = per_cpu(misaligned_access_speed, cpu);
-
-		if (perf == -1ULL)
-			perf = this_perf;
-
-		if (perf != this_perf) {
-			perf = RISCV_HWPROBE_MISALIGNED_UNKNOWN;
-			break;
-		}
-	}
-
-	if (perf == -1ULL)
-		return RISCV_HWPROBE_MISALIGNED_UNKNOWN;
-
-	return perf;
-}
-
-static void hwprobe_one_pair(struct riscv_hwprobe *pair,
-			     const struct cpumask *cpus)
-{
-	switch (pair->key) {
-	case RISCV_HWPROBE_KEY_MVENDORID:
-	case RISCV_HWPROBE_KEY_MARCHID:
-	case RISCV_HWPROBE_KEY_MIMPID:
-		hwprobe_arch_id(pair, cpus);
-		break;
-	/*
-	 * The kernel already assumes that the base single-letter ISA
-	 * extensions are supported on all harts, and only supports the
-	 * IMA base, so just cheat a bit here and tell that to
-	 * userspace.
-	 */
-	case RISCV_HWPROBE_KEY_BASE_BEHAVIOR:
-		pair->value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA;
-		break;
-
-	case RISCV_HWPROBE_KEY_IMA_EXT_0:
-		hwprobe_isa_ext0(pair, cpus);
-		break;
-
-	case RISCV_HWPROBE_KEY_CPUPERF_0:
-		pair->value = hwprobe_misaligned(cpus);
-		break;
-
-	case RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE:
-		pair->value = 0;
-		if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOZ))
-			pair->value = riscv_cboz_block_size;
-		break;
-
-	/*
-	 * For forward compatibility, unknown keys don't fail the whole
-	 * call, but get their element key set to -1 and value set to 0
-	 * indicating they're unrecognized.
-	 */
-	default:
-		pair->key = -1;
-		pair->value = 0;
-		break;
-	}
-}
-
-static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,
-			    size_t pair_count, size_t cpu_count,
-			    unsigned long __user *cpus_user,
-			    unsigned int flags)
-{
-	size_t out;
-	int ret;
-	cpumask_t cpus;
-
-	/* Check the reserved flags. */
-	if (flags != 0)
-		return -EINVAL;
-
-	/*
-	 * The interface supports taking in a CPU mask, and returns values that
-	 * are consistent across that mask. Allow userspace to specify NULL and
-	 * 0 as a shortcut to all online CPUs.
-	 */
-	cpumask_clear(&cpus);
-	if (!cpu_count && !cpus_user) {
-		cpumask_copy(&cpus, cpu_online_mask);
-	} else {
-		if (cpu_count > cpumask_size())
-			cpu_count = cpumask_size();
-
-		ret = copy_from_user(&cpus, cpus_user, cpu_count);
-		if (ret)
-			return -EFAULT;
-
-		/*
-		 * Userspace must provide at least one online CPU, without that
-		 * there's no way to define what is supported.
-		 */
-		cpumask_and(&cpus, &cpus, cpu_online_mask);
-		if (cpumask_empty(&cpus))
-			return -EINVAL;
-	}
-
-	for (out = 0; out < pair_count; out++, pairs++) {
-		struct riscv_hwprobe pair;
-
-		if (get_user(pair.key, &pairs->key))
-			return -EFAULT;
-
-		pair.value = 0;
-		hwprobe_one_pair(&pair, &cpus);
-		ret = put_user(pair.key, &pairs->key);
-		if (ret == 0)
-			ret = put_user(pair.value, &pairs->value);
-
-		if (ret)
-			return -EFAULT;
-	}
-
-	return 0;
-}
-
-#ifdef CONFIG_MMU
-
-static int __init init_hwprobe_vdso_data(void)
-{
-	struct vdso_data *vd = __arch_get_k_vdso_data();
-	struct arch_vdso_data *avd = &vd->arch_data;
-	u64 id_bitsmash = 0;
-	struct riscv_hwprobe pair;
-	int key;
-
-	/*
-	 * Initialize vDSO data with the answers for the "all CPUs" case, to
-	 * save a syscall in the common case.
-	 */
-	for (key = 0; key <= RISCV_HWPROBE_MAX_KEY; key++) {
-		pair.key = key;
-		hwprobe_one_pair(&pair, cpu_online_mask);
-
-		WARN_ON_ONCE(pair.key < 0);
-
-		avd->all_cpu_hwprobe_values[key] = pair.value;
-		/*
-		 * Smash together the vendor, arch, and impl IDs to see if
-		 * they're all 0 or any negative.
-		 */
-		if (key <= RISCV_HWPROBE_KEY_MIMPID)
-			id_bitsmash |= pair.value;
-	}
-
-	/*
-	 * If the arch, vendor, and implementation ID are all the same across
-	 * all harts, then assume all CPUs are the same, and allow the vDSO to
-	 * answer queries for arbitrary masks. However if all values are 0 (not
-	 * populated) or any value returns -1 (varies across CPUs), then the
-	 * vDSO should defer to the kernel for exotic cpu masks.
-	 */
-	avd->homogeneous_cpus = id_bitsmash != 0 && id_bitsmash != -1;
-	return 0;
-}
-
-arch_initcall_sync(init_hwprobe_vdso_data);
-
-#endif /* CONFIG_MMU */
-
-SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs,
-		size_t, pair_count, size_t, cpu_count, unsigned long __user *,
-		cpus, unsigned int, flags)
-{
-	return do_riscv_hwprobe(pairs, pair_count, cpu_count,
-				cpus, flags);
-}
-
 /* Not defined using SYSCALL_DEFINE0 to avoid error injection */
 asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *__unused)
 {
diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c
index 23641e82a9df..ba3477197789 100644
--- a/arch/riscv/kernel/time.c
+++ b/arch/riscv/kernel/time.c
@@ -12,6 +12,7 @@
 #include <asm/sbi.h>
 #include <asm/processor.h>
 #include <asm/timex.h>
+#include <asm/paravirt.h>
 
 unsigned long riscv_timebase __ro_after_init;
 EXPORT_SYMBOL_GPL(riscv_timebase);
@@ -45,4 +46,6 @@ void __init time_init(void)
 	timer_probe();
 
 	tick_setup_hrtimer_broadcast();
+
+	pv_time_init();
 }
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index 5255f8134aef..8ded225e8c5b 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -319,7 +319,7 @@ static inline int get_insn(struct pt_regs *regs, ulong mepc, ulong *r_insn)
 static inline int load_u8(struct pt_regs *regs, const u8 *addr, u8 *r_val)
 {
 	if (user_mode(regs)) {
-		return __get_user(*r_val, addr);
+		return __get_user(*r_val, (u8 __user *)addr);
 	} else {
 		*r_val = *addr;
 		return 0;
@@ -329,7 +329,7 @@ static inline int load_u8(struct pt_regs *regs, const u8 *addr, u8 *r_val)
 static inline int store_u8(struct pt_regs *regs, u8 *addr, u8 val)
 {
 	if (user_mode(regs)) {
-		return __put_user(val, addr);
+		return __put_user(val, (u8 __user *)addr);
 	} else {
 		*addr = val;
 		return 0;
@@ -343,7 +343,7 @@ static inline int store_u8(struct pt_regs *regs, u8 *addr, u8 val)
 	if (user_mode(regs)) {				\
 		__ret = __get_user(insn, insn_addr);	\
 	} else {					\
-		insn = *insn_addr;			\
+		insn = *(__force u16 *)insn_addr;	\
 		__ret = 0;				\
 	}						\
 							\
diff --git a/arch/riscv/kernel/vdso/hwprobe.c b/arch/riscv/kernel/vdso/hwprobe.c
index cadf725ef798..1e926e4b5881 100644
--- a/arch/riscv/kernel/vdso/hwprobe.c
+++ b/arch/riscv/kernel/vdso/hwprobe.c
@@ -3,26 +3,22 @@
  * Copyright 2023 Rivos, Inc
  */
 
+#include <linux/string.h>
 #include <linux/types.h>
 #include <vdso/datapage.h>
 #include <vdso/helpers.h>
 
 extern int riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-			 size_t cpu_count, unsigned long *cpus,
+			 size_t cpusetsize, unsigned long *cpus,
 			 unsigned int flags);
 
-/* Add a prototype to avoid -Wmissing-prototypes warning. */
-int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-			 size_t cpu_count, unsigned long *cpus,
-			 unsigned int flags);
-
-int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-			 size_t cpu_count, unsigned long *cpus,
-			 unsigned int flags)
+static int riscv_vdso_get_values(struct riscv_hwprobe *pairs, size_t pair_count,
+				 size_t cpusetsize, unsigned long *cpus,
+				 unsigned int flags)
 {
 	const struct vdso_data *vd = __arch_get_vdso_data();
 	const struct arch_vdso_data *avd = &vd->arch_data;
-	bool all_cpus = !cpu_count && !cpus;
+	bool all_cpus = !cpusetsize && !cpus;
 	struct riscv_hwprobe *p = pairs;
 	struct riscv_hwprobe *end = pairs + pair_count;
 
@@ -33,7 +29,7 @@ int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
 	 * masks.
 	 */
 	if ((flags != 0) || (!all_cpus && !avd->homogeneous_cpus))
-		return riscv_hwprobe(pairs, pair_count, cpu_count, cpus, flags);
+		return riscv_hwprobe(pairs, pair_count, cpusetsize, cpus, flags);
 
 	/* This is something we can handle, fill out the pairs. */
 	while (p < end) {
@@ -50,3 +46,71 @@ int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
 
 	return 0;
 }
+
+static int riscv_vdso_get_cpus(struct riscv_hwprobe *pairs, size_t pair_count,
+			       size_t cpusetsize, unsigned long *cpus,
+			       unsigned int flags)
+{
+	const struct vdso_data *vd = __arch_get_vdso_data();
+	const struct arch_vdso_data *avd = &vd->arch_data;
+	struct riscv_hwprobe *p = pairs;
+	struct riscv_hwprobe *end = pairs + pair_count;
+	unsigned char *c = (unsigned char *)cpus;
+	bool empty_cpus = true;
+	bool clear_all = false;
+	int i;
+
+	if (!cpusetsize || !cpus)
+		return -EINVAL;
+
+	for (i = 0; i < cpusetsize; i++) {
+		if (c[i]) {
+			empty_cpus = false;
+			break;
+		}
+	}
+
+	if (empty_cpus || flags != RISCV_HWPROBE_WHICH_CPUS || !avd->homogeneous_cpus)
+		return riscv_hwprobe(pairs, pair_count, cpusetsize, cpus, flags);
+
+	while (p < end) {
+		if (riscv_hwprobe_key_is_valid(p->key)) {
+			struct riscv_hwprobe t = {
+				.key = p->key,
+				.value = avd->all_cpu_hwprobe_values[p->key],
+			};
+
+			if (!riscv_hwprobe_pair_cmp(&t, p))
+				clear_all = true;
+		} else {
+			clear_all = true;
+			p->key = -1;
+			p->value = 0;
+		}
+		p++;
+	}
+
+	if (clear_all) {
+		for (i = 0; i < cpusetsize; i++)
+			c[i] = 0;
+	}
+
+	return 0;
+}
+
+/* Add a prototype to avoid -Wmissing-prototypes warning. */
+int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
+			 size_t cpusetsize, unsigned long *cpus,
+			 unsigned int flags);
+
+int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
+			 size_t cpusetsize, unsigned long *cpus,
+			 unsigned int flags)
+{
+	if (flags & RISCV_HWPROBE_WHICH_CPUS)
+		return riscv_vdso_get_cpus(pairs, pair_count, cpusetsize,
+					   cpus, flags);
+
+	return riscv_vdso_get_values(pairs, pair_count, cpusetsize,
+				     cpus, flags);
+}
diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
index 578b6292487e..6727d1d3b8f2 100644
--- a/arch/riscv/kernel/vector.c
+++ b/arch/riscv/kernel/vector.c
@@ -21,6 +21,10 @@
 #include <asm/bug.h>
 
 static bool riscv_v_implicit_uacc = IS_ENABLED(CONFIG_RISCV_ISA_V_DEFAULT_ENABLE);
+static struct kmem_cache *riscv_v_user_cachep;
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+static struct kmem_cache *riscv_v_kernel_cachep;
+#endif
 
 unsigned long riscv_v_vsize __read_mostly;
 EXPORT_SYMBOL_GPL(riscv_v_vsize);
@@ -47,6 +51,21 @@ int riscv_v_setup_vsize(void)
 	return 0;
 }
 
+void __init riscv_v_setup_ctx_cache(void)
+{
+	if (!has_vector())
+		return;
+
+	riscv_v_user_cachep = kmem_cache_create_usercopy("riscv_vector_ctx",
+							 riscv_v_vsize, 16, SLAB_PANIC,
+							 0, riscv_v_vsize, NULL);
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	riscv_v_kernel_cachep = kmem_cache_create("riscv_vector_kctx",
+						  riscv_v_vsize, 16,
+						  SLAB_PANIC, NULL);
+#endif
+}
+
 static bool insn_is_vector(u32 insn_buf)
 {
 	u32 opcode = insn_buf & __INSN_OPCODE_MASK;
@@ -80,20 +99,37 @@ static bool insn_is_vector(u32 insn_buf)
 	return false;
 }
 
-static int riscv_v_thread_zalloc(void)
+static int riscv_v_thread_zalloc(struct kmem_cache *cache,
+				 struct __riscv_v_ext_state *ctx)
 {
 	void *datap;
 
-	datap = kzalloc(riscv_v_vsize, GFP_KERNEL);
+	datap = kmem_cache_zalloc(cache, GFP_KERNEL);
 	if (!datap)
 		return -ENOMEM;
 
-	current->thread.vstate.datap = datap;
-	memset(&current->thread.vstate, 0, offsetof(struct __riscv_v_ext_state,
-						    datap));
+	ctx->datap = datap;
+	memset(ctx, 0, offsetof(struct __riscv_v_ext_state, datap));
 	return 0;
 }
 
+void riscv_v_thread_alloc(struct task_struct *tsk)
+{
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	riscv_v_thread_zalloc(riscv_v_kernel_cachep, &tsk->thread.kernel_vstate);
+#endif
+}
+
+void riscv_v_thread_free(struct task_struct *tsk)
+{
+	if (tsk->thread.vstate.datap)
+		kmem_cache_free(riscv_v_user_cachep, tsk->thread.vstate.datap);
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	if (tsk->thread.kernel_vstate.datap)
+		kmem_cache_free(riscv_v_kernel_cachep, tsk->thread.kernel_vstate.datap);
+#endif
+}
+
 #define VSTATE_CTRL_GET_CUR(x) ((x) & PR_RISCV_V_VSTATE_CTRL_CUR_MASK)
 #define VSTATE_CTRL_GET_NEXT(x) (((x) & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK) >> 2)
 #define VSTATE_CTRL_MAKE_NEXT(x) (((x) << 2) & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK)
@@ -122,7 +158,8 @@ static inline void riscv_v_ctrl_set(struct task_struct *tsk, int cur, int nxt,
 	ctrl |= VSTATE_CTRL_MAKE_NEXT(nxt);
 	if (inherit)
 		ctrl |= PR_RISCV_V_VSTATE_CTRL_INHERIT;
-	tsk->thread.vstate_ctrl = ctrl;
+	tsk->thread.vstate_ctrl &= ~PR_RISCV_V_VSTATE_CTRL_MASK;
+	tsk->thread.vstate_ctrl |= ctrl;
 }
 
 bool riscv_v_vstate_ctrl_user_allowed(void)
@@ -162,12 +199,12 @@ bool riscv_v_first_use_handler(struct pt_regs *regs)
 	 * context where VS has been off. So, try to allocate the user's V
 	 * context and resume execution.
 	 */
-	if (riscv_v_thread_zalloc()) {
+	if (riscv_v_thread_zalloc(riscv_v_user_cachep, &current->thread.vstate)) {
 		force_sig(SIGBUS);
 		return true;
 	}
 	riscv_v_vstate_on(regs);
-	riscv_v_vstate_restore(current, regs);
+	riscv_v_vstate_set_restore(current, regs);
 	return true;
 }
 
diff --git a/arch/riscv/kernel/vmlinux-xip.lds.S b/arch/riscv/kernel/vmlinux-xip.lds.S
index 50767647fbc6..8c3daa1b0531 100644
--- a/arch/riscv/kernel/vmlinux-xip.lds.S
+++ b/arch/riscv/kernel/vmlinux-xip.lds.S
@@ -29,10 +29,12 @@ SECTIONS
 	HEAD_TEXT_SECTION
 	INIT_TEXT_SECTION(PAGE_SIZE)
 	/* we have to discard exit text and such at runtime, not link time */
+	__exittext_begin = .;
 	.exit.text :
 	{
 		EXIT_TEXT
 	}
+	__exittext_end = .;
 
 	.text : {
 		_text = .;
diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S
index 492dd4b8f3d6..002ca58dd998 100644
--- a/arch/riscv/kernel/vmlinux.lds.S
+++ b/arch/riscv/kernel/vmlinux.lds.S
@@ -69,10 +69,12 @@ SECTIONS
 		__soc_builtin_dtb_table_end = .;
 	}
 	/* we have to discard exit text and such at runtime, not link time */
+	__exittext_begin = .;
 	.exit.text :
 	{
 		EXIT_TEXT
 	}
+	__exittext_end = .;
 
 	__init_text_end = .;
 	. = ALIGN(SECTION_ALIGN);
diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig
index dfc237d7875b..d490db943858 100644
--- a/arch/riscv/kvm/Kconfig
+++ b/arch/riscv/kvm/Kconfig
@@ -20,18 +20,17 @@ if VIRTUALIZATION
 config KVM
 	tristate "Kernel-based Virtual Machine (KVM) support (EXPERIMENTAL)"
 	depends on RISCV_SBI && MMU
-	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_IRQCHIP
-	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_MSI
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
+	select KVM_COMMON
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_GENERIC_HARDWARE_ENABLING
 	select KVM_MMIO
 	select KVM_XFER_TO_GUEST_WORK
-	select MMU_NOTIFIER
-	select PREEMPT_NOTIFIERS
+	select KVM_GENERIC_MMU_NOTIFIER
+	select SCHED_INFO
 	help
 	  Support hosting virtualized guest machines.
 
diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile
index 4c2067fc59fc..c9646521f113 100644
--- a/arch/riscv/kvm/Makefile
+++ b/arch/riscv/kvm/Makefile
@@ -26,6 +26,7 @@ kvm-$(CONFIG_RISCV_SBI_V01) += vcpu_sbi_v01.o
 kvm-y += vcpu_sbi_base.o
 kvm-y += vcpu_sbi_replace.o
 kvm-y += vcpu_sbi_hsm.o
+kvm-y += vcpu_sbi_sta.o
 kvm-y += vcpu_timer.o
 kvm-$(CONFIG_RISCV_PMU_SBI) += vcpu_pmu.o vcpu_sbi_pmu.o
 kvm-y += aia.o
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index 068c74593871..a9e2fd7245e1 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -103,7 +103,7 @@ static bool gstage_get_leaf_entry(struct kvm *kvm, gpa_t addr,
 	*ptep_level = current_level;
 	ptep = (pte_t *)kvm->arch.pgd;
 	ptep = &ptep[gstage_pte_index(addr, current_level)];
-	while (ptep && pte_val(*ptep)) {
+	while (ptep && pte_val(ptep_get(ptep))) {
 		if (gstage_pte_leaf(ptep)) {
 			*ptep_level = current_level;
 			*ptepp = ptep;
@@ -113,7 +113,7 @@ static bool gstage_get_leaf_entry(struct kvm *kvm, gpa_t addr,
 		if (current_level) {
 			current_level--;
 			*ptep_level = current_level;
-			ptep = (pte_t *)gstage_pte_page_vaddr(*ptep);
+			ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep));
 			ptep = &ptep[gstage_pte_index(addr, current_level)];
 		} else {
 			ptep = NULL;
@@ -149,25 +149,25 @@ static int gstage_set_pte(struct kvm *kvm, u32 level,
 		if (gstage_pte_leaf(ptep))
 			return -EEXIST;
 
-		if (!pte_val(*ptep)) {
+		if (!pte_val(ptep_get(ptep))) {
 			if (!pcache)
 				return -ENOMEM;
 			next_ptep = kvm_mmu_memory_cache_alloc(pcache);
 			if (!next_ptep)
 				return -ENOMEM;
-			*ptep = pfn_pte(PFN_DOWN(__pa(next_ptep)),
-					__pgprot(_PAGE_TABLE));
+			set_pte(ptep, pfn_pte(PFN_DOWN(__pa(next_ptep)),
+					      __pgprot(_PAGE_TABLE)));
 		} else {
 			if (gstage_pte_leaf(ptep))
 				return -EEXIST;
-			next_ptep = (pte_t *)gstage_pte_page_vaddr(*ptep);
+			next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep));
 		}
 
 		current_level--;
 		ptep = &next_ptep[gstage_pte_index(addr, current_level)];
 	}
 
-	*ptep = *new_pte;
+	set_pte(ptep, *new_pte);
 	if (gstage_pte_leaf(ptep))
 		gstage_remote_tlb_flush(kvm, current_level, addr);
 
@@ -239,11 +239,11 @@ static void gstage_op_pte(struct kvm *kvm, gpa_t addr,
 
 	BUG_ON(addr & (page_size - 1));
 
-	if (!pte_val(*ptep))
+	if (!pte_val(ptep_get(ptep)))
 		return;
 
 	if (ptep_level && !gstage_pte_leaf(ptep)) {
-		next_ptep = (pte_t *)gstage_pte_page_vaddr(*ptep);
+		next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep));
 		next_ptep_level = ptep_level - 1;
 		ret = gstage_level_to_page_size(next_ptep_level,
 						&next_page_size);
@@ -261,7 +261,7 @@ static void gstage_op_pte(struct kvm *kvm, gpa_t addr,
 		if (op == GSTAGE_OP_CLEAR)
 			set_pte(ptep, __pte(0));
 		else if (op == GSTAGE_OP_WP)
-			set_pte(ptep, __pte(pte_val(*ptep) & ~_PAGE_WRITE));
+			set_pte(ptep, __pte(pte_val(ptep_get(ptep)) & ~_PAGE_WRITE));
 		gstage_remote_tlb_flush(kvm, ptep_level, addr);
 	}
 }
@@ -603,7 +603,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 				   &ptep, &ptep_level))
 		return false;
 
-	return pte_young(*ptep);
+	return pte_young(ptep_get(ptep));
 }
 
 int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index e087c809073c..b5ca9f2e98ac 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -83,6 +83,8 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
 	vcpu->arch.hfence_tail = 0;
 	memset(vcpu->arch.hfence_queue, 0, sizeof(vcpu->arch.hfence_queue));
 
+	kvm_riscv_vcpu_sbi_sta_reset(vcpu);
+
 	/* Reset the guest CSRs for hotplug usecase */
 	if (loaded)
 		kvm_arch_vcpu_load(vcpu, smp_processor_id());
@@ -541,6 +543,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	kvm_riscv_vcpu_aia_load(vcpu, cpu);
 
+	kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
+
 	vcpu->cpu = cpu;
 }
 
@@ -614,6 +618,9 @@ static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu)
 
 		if (kvm_check_request(KVM_REQ_HFENCE, vcpu))
 			kvm_riscv_hfence_process(vcpu);
+
+		if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu))
+			kvm_riscv_vcpu_record_steal_time(vcpu);
 	}
 }
 
@@ -757,8 +764,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		/* Update HVIP CSR for current CPU */
 		kvm_riscv_update_hvip(vcpu);
 
-		if (ret <= 0 ||
-		    kvm_riscv_gstage_vmid_ver_changed(&vcpu->kvm->arch.vmid) ||
+		if (kvm_riscv_gstage_vmid_ver_changed(&vcpu->kvm->arch.vmid) ||
 		    kvm_request_pending(vcpu) ||
 		    xfer_to_guest_mode_work_pending()) {
 			vcpu->mode = OUTSIDE_GUEST_MODE;
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index f8c9fa0c03c5..5f7355e96008 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -42,15 +42,42 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	KVM_ISA_EXT_ARR(SVPBMT),
 	KVM_ISA_EXT_ARR(ZBA),
 	KVM_ISA_EXT_ARR(ZBB),
+	KVM_ISA_EXT_ARR(ZBC),
+	KVM_ISA_EXT_ARR(ZBKB),
+	KVM_ISA_EXT_ARR(ZBKC),
+	KVM_ISA_EXT_ARR(ZBKX),
 	KVM_ISA_EXT_ARR(ZBS),
+	KVM_ISA_EXT_ARR(ZFA),
+	KVM_ISA_EXT_ARR(ZFH),
+	KVM_ISA_EXT_ARR(ZFHMIN),
 	KVM_ISA_EXT_ARR(ZICBOM),
 	KVM_ISA_EXT_ARR(ZICBOZ),
 	KVM_ISA_EXT_ARR(ZICNTR),
 	KVM_ISA_EXT_ARR(ZICOND),
 	KVM_ISA_EXT_ARR(ZICSR),
 	KVM_ISA_EXT_ARR(ZIFENCEI),
+	KVM_ISA_EXT_ARR(ZIHINTNTL),
 	KVM_ISA_EXT_ARR(ZIHINTPAUSE),
 	KVM_ISA_EXT_ARR(ZIHPM),
+	KVM_ISA_EXT_ARR(ZKND),
+	KVM_ISA_EXT_ARR(ZKNE),
+	KVM_ISA_EXT_ARR(ZKNH),
+	KVM_ISA_EXT_ARR(ZKR),
+	KVM_ISA_EXT_ARR(ZKSED),
+	KVM_ISA_EXT_ARR(ZKSH),
+	KVM_ISA_EXT_ARR(ZKT),
+	KVM_ISA_EXT_ARR(ZVBB),
+	KVM_ISA_EXT_ARR(ZVBC),
+	KVM_ISA_EXT_ARR(ZVFH),
+	KVM_ISA_EXT_ARR(ZVFHMIN),
+	KVM_ISA_EXT_ARR(ZVKB),
+	KVM_ISA_EXT_ARR(ZVKG),
+	KVM_ISA_EXT_ARR(ZVKNED),
+	KVM_ISA_EXT_ARR(ZVKNHA),
+	KVM_ISA_EXT_ARR(ZVKNHB),
+	KVM_ISA_EXT_ARR(ZVKSED),
+	KVM_ISA_EXT_ARR(ZVKSH),
+	KVM_ISA_EXT_ARR(ZVKT),
 };
 
 static unsigned long kvm_riscv_vcpu_base2isa_ext(unsigned long base_ext)
@@ -92,13 +119,40 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_SVNAPOT:
 	case KVM_RISCV_ISA_EXT_ZBA:
 	case KVM_RISCV_ISA_EXT_ZBB:
+	case KVM_RISCV_ISA_EXT_ZBC:
+	case KVM_RISCV_ISA_EXT_ZBKB:
+	case KVM_RISCV_ISA_EXT_ZBKC:
+	case KVM_RISCV_ISA_EXT_ZBKX:
 	case KVM_RISCV_ISA_EXT_ZBS:
+	case KVM_RISCV_ISA_EXT_ZFA:
+	case KVM_RISCV_ISA_EXT_ZFH:
+	case KVM_RISCV_ISA_EXT_ZFHMIN:
 	case KVM_RISCV_ISA_EXT_ZICNTR:
 	case KVM_RISCV_ISA_EXT_ZICOND:
 	case KVM_RISCV_ISA_EXT_ZICSR:
 	case KVM_RISCV_ISA_EXT_ZIFENCEI:
+	case KVM_RISCV_ISA_EXT_ZIHINTNTL:
 	case KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
 	case KVM_RISCV_ISA_EXT_ZIHPM:
+	case KVM_RISCV_ISA_EXT_ZKND:
+	case KVM_RISCV_ISA_EXT_ZKNE:
+	case KVM_RISCV_ISA_EXT_ZKNH:
+	case KVM_RISCV_ISA_EXT_ZKR:
+	case KVM_RISCV_ISA_EXT_ZKSED:
+	case KVM_RISCV_ISA_EXT_ZKSH:
+	case KVM_RISCV_ISA_EXT_ZKT:
+	case KVM_RISCV_ISA_EXT_ZVBB:
+	case KVM_RISCV_ISA_EXT_ZVBC:
+	case KVM_RISCV_ISA_EXT_ZVFH:
+	case KVM_RISCV_ISA_EXT_ZVFHMIN:
+	case KVM_RISCV_ISA_EXT_ZVKB:
+	case KVM_RISCV_ISA_EXT_ZVKG:
+	case KVM_RISCV_ISA_EXT_ZVKNED:
+	case KVM_RISCV_ISA_EXT_ZVKNHA:
+	case KVM_RISCV_ISA_EXT_ZVKNHB:
+	case KVM_RISCV_ISA_EXT_ZVKSED:
+	case KVM_RISCV_ISA_EXT_ZVKSH:
+	case KVM_RISCV_ISA_EXT_ZVKT:
 		return false;
 	/* Extensions which can be disabled using Smstateen */
 	case KVM_RISCV_ISA_EXT_SSAIA:
@@ -485,7 +539,7 @@ static int kvm_riscv_vcpu_set_reg_csr(struct kvm_vcpu *vcpu,
 		if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN))
 			rc = kvm_riscv_vcpu_smstateen_set_csr(vcpu, reg_num,
 							      reg_val);
-break;
+		break;
 	default:
 		rc = -ENOENT;
 		break;
@@ -931,50 +985,106 @@ static inline unsigned long num_isa_ext_regs(const struct kvm_vcpu *vcpu)
 	return copy_isa_ext_reg_indices(vcpu, NULL);;
 }
 
-static inline unsigned long num_sbi_ext_regs(void)
+static int copy_sbi_ext_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 {
-	/*
-	 * number of KVM_REG_RISCV_SBI_SINGLE +
-	 * 2 x (number of KVM_REG_RISCV_SBI_MULTI)
-	 */
-	return KVM_RISCV_SBI_EXT_MAX + 2*(KVM_REG_RISCV_SBI_MULTI_REG_LAST+1);
-}
-
-static int copy_sbi_ext_reg_indices(u64 __user *uindices)
-{
-	int n;
+	unsigned int n = 0;
 
-	/* copy KVM_REG_RISCV_SBI_SINGLE */
-	n = KVM_RISCV_SBI_EXT_MAX;
-	for (int i = 0; i < n; i++) {
+	for (int i = 0; i < KVM_RISCV_SBI_EXT_MAX; i++) {
 		u64 size = IS_ENABLED(CONFIG_32BIT) ?
 			   KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64;
 		u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_SBI_EXT |
 			  KVM_REG_RISCV_SBI_SINGLE | i;
 
+		if (!riscv_vcpu_supports_sbi_ext(vcpu, i))
+			continue;
+
 		if (uindices) {
 			if (put_user(reg, uindices))
 				return -EFAULT;
 			uindices++;
 		}
+
+		n++;
 	}
 
-	/* copy KVM_REG_RISCV_SBI_MULTI */
-	n = KVM_REG_RISCV_SBI_MULTI_REG_LAST + 1;
-	for (int i = 0; i < n; i++) {
-		u64 size = IS_ENABLED(CONFIG_32BIT) ?
-			   KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64;
-		u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_SBI_EXT |
-			  KVM_REG_RISCV_SBI_MULTI_EN | i;
+	return n;
+}
+
+static unsigned long num_sbi_ext_regs(struct kvm_vcpu *vcpu)
+{
+	return copy_sbi_ext_reg_indices(vcpu, NULL);
+}
+
+static int copy_sbi_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
+{
+	struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context;
+	int total = 0;
+
+	if (scontext->ext_status[KVM_RISCV_SBI_EXT_STA] == KVM_RISCV_SBI_EXT_STATUS_ENABLED) {
+		u64 size = IS_ENABLED(CONFIG_32BIT) ? KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64;
+		int n = sizeof(struct kvm_riscv_sbi_sta) / sizeof(unsigned long);
+
+		for (int i = 0; i < n; i++) {
+			u64 reg = KVM_REG_RISCV | size |
+				  KVM_REG_RISCV_SBI_STATE |
+				  KVM_REG_RISCV_SBI_STA | i;
+
+			if (uindices) {
+				if (put_user(reg, uindices))
+					return -EFAULT;
+				uindices++;
+			}
+		}
+
+		total += n;
+	}
+
+	return total;
+}
+
+static inline unsigned long num_sbi_regs(struct kvm_vcpu *vcpu)
+{
+	return copy_sbi_reg_indices(vcpu, NULL);
+}
+
+static inline unsigned long num_vector_regs(const struct kvm_vcpu *vcpu)
+{
+	if (!riscv_isa_extension_available(vcpu->arch.isa, v))
+		return 0;
+
+	/* vstart, vl, vtype, vcsr, vlenb and 32 vector regs */
+	return 37;
+}
+
+static int copy_vector_reg_indices(const struct kvm_vcpu *vcpu,
+				u64 __user *uindices)
+{
+	const struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
+	int n = num_vector_regs(vcpu);
+	u64 reg, size;
+	int i;
+
+	if (n == 0)
+		return 0;
+
+	/* copy vstart, vl, vtype, vcsr and vlenb */
+	size = IS_ENABLED(CONFIG_32BIT) ? KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64;
+	for (i = 0; i < 5; i++) {
+		reg = KVM_REG_RISCV | size | KVM_REG_RISCV_VECTOR | i;
 
 		if (uindices) {
 			if (put_user(reg, uindices))
 				return -EFAULT;
 			uindices++;
 		}
+	}
 
-		reg = KVM_REG_RISCV | size | KVM_REG_RISCV_SBI_EXT |
-			  KVM_REG_RISCV_SBI_MULTI_DIS | i;
+	/* vector_regs have a variable 'vlenb' size */
+	size = __builtin_ctzl(cntx->vector.vlenb);
+	size <<= KVM_REG_SIZE_SHIFT;
+	for (i = 0; i < 32; i++) {
+		reg = KVM_REG_RISCV | KVM_REG_RISCV_VECTOR | size |
+			KVM_REG_RISCV_VECTOR_REG(i);
 
 		if (uindices) {
 			if (put_user(reg, uindices))
@@ -983,7 +1093,7 @@ static int copy_sbi_ext_reg_indices(u64 __user *uindices)
 		}
 	}
 
-	return num_sbi_ext_regs();
+	return n;
 }
 
 /*
@@ -1001,8 +1111,10 @@ unsigned long kvm_riscv_vcpu_num_regs(struct kvm_vcpu *vcpu)
 	res += num_timer_regs();
 	res += num_fp_f_regs(vcpu);
 	res += num_fp_d_regs(vcpu);
+	res += num_vector_regs(vcpu);
 	res += num_isa_ext_regs(vcpu);
-	res += num_sbi_ext_regs();
+	res += num_sbi_ext_regs(vcpu);
+	res += num_sbi_regs(vcpu);
 
 	return res;
 }
@@ -1045,14 +1157,25 @@ int kvm_riscv_vcpu_copy_reg_indices(struct kvm_vcpu *vcpu,
 		return ret;
 	uindices += ret;
 
+	ret = copy_vector_reg_indices(vcpu, uindices);
+	if (ret < 0)
+		return ret;
+	uindices += ret;
+
 	ret = copy_isa_ext_reg_indices(vcpu, uindices);
 	if (ret < 0)
 		return ret;
 	uindices += ret;
 
-	ret = copy_sbi_ext_reg_indices(uindices);
+	ret = copy_sbi_ext_reg_indices(vcpu, uindices);
 	if (ret < 0)
 		return ret;
+	uindices += ret;
+
+	ret = copy_sbi_reg_indices(vcpu, uindices);
+	if (ret < 0)
+		return ret;
+	uindices += ret;
 
 	return 0;
 }
@@ -1075,12 +1198,14 @@ int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu,
 	case KVM_REG_RISCV_FP_D:
 		return kvm_riscv_vcpu_set_reg_fp(vcpu, reg,
 						 KVM_REG_RISCV_FP_D);
+	case KVM_REG_RISCV_VECTOR:
+		return kvm_riscv_vcpu_set_reg_vector(vcpu, reg);
 	case KVM_REG_RISCV_ISA_EXT:
 		return kvm_riscv_vcpu_set_reg_isa_ext(vcpu, reg);
 	case KVM_REG_RISCV_SBI_EXT:
 		return kvm_riscv_vcpu_set_reg_sbi_ext(vcpu, reg);
-	case KVM_REG_RISCV_VECTOR:
-		return kvm_riscv_vcpu_set_reg_vector(vcpu, reg);
+	case KVM_REG_RISCV_SBI_STATE:
+		return kvm_riscv_vcpu_set_reg_sbi(vcpu, reg);
 	default:
 		break;
 	}
@@ -1106,12 +1231,14 @@ int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu,
 	case KVM_REG_RISCV_FP_D:
 		return kvm_riscv_vcpu_get_reg_fp(vcpu, reg,
 						 KVM_REG_RISCV_FP_D);
+	case KVM_REG_RISCV_VECTOR:
+		return kvm_riscv_vcpu_get_reg_vector(vcpu, reg);
 	case KVM_REG_RISCV_ISA_EXT:
 		return kvm_riscv_vcpu_get_reg_isa_ext(vcpu, reg);
 	case KVM_REG_RISCV_SBI_EXT:
 		return kvm_riscv_vcpu_get_reg_sbi_ext(vcpu, reg);
-	case KVM_REG_RISCV_VECTOR:
-		return kvm_riscv_vcpu_get_reg_vector(vcpu, reg);
+	case KVM_REG_RISCV_SBI_STATE:
+		return kvm_riscv_vcpu_get_reg_sbi(vcpu, reg);
 	default:
 		break;
 	}
diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c
index a04ff98085d9..72a2ffb8dcd1 100644
--- a/arch/riscv/kvm/vcpu_sbi.c
+++ b/arch/riscv/kvm/vcpu_sbi.c
@@ -71,6 +71,10 @@ static const struct kvm_riscv_sbi_extension_entry sbi_ext[] = {
 		.ext_ptr = &vcpu_sbi_ext_dbcn,
 	},
 	{
+		.ext_idx = KVM_RISCV_SBI_EXT_STA,
+		.ext_ptr = &vcpu_sbi_ext_sta,
+	},
+	{
 		.ext_idx = KVM_RISCV_SBI_EXT_EXPERIMENTAL,
 		.ext_ptr = &vcpu_sbi_ext_experimental,
 	},
@@ -80,6 +84,34 @@ static const struct kvm_riscv_sbi_extension_entry sbi_ext[] = {
 	},
 };
 
+static const struct kvm_riscv_sbi_extension_entry *
+riscv_vcpu_get_sbi_ext(struct kvm_vcpu *vcpu, unsigned long idx)
+{
+	const struct kvm_riscv_sbi_extension_entry *sext = NULL;
+
+	if (idx >= KVM_RISCV_SBI_EXT_MAX)
+		return NULL;
+
+	for (int i = 0; i < ARRAY_SIZE(sbi_ext); i++) {
+		if (sbi_ext[i].ext_idx == idx) {
+			sext = &sbi_ext[i];
+			break;
+		}
+	}
+
+	return sext;
+}
+
+bool riscv_vcpu_supports_sbi_ext(struct kvm_vcpu *vcpu, int idx)
+{
+	struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context;
+	const struct kvm_riscv_sbi_extension_entry *sext;
+
+	sext = riscv_vcpu_get_sbi_ext(vcpu, idx);
+
+	return sext && scontext->ext_status[sext->ext_idx] != KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE;
+}
+
 void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
@@ -140,28 +172,19 @@ static int riscv_vcpu_set_sbi_ext_single(struct kvm_vcpu *vcpu,
 					 unsigned long reg_num,
 					 unsigned long reg_val)
 {
-	unsigned long i;
-	const struct kvm_riscv_sbi_extension_entry *sext = NULL;
 	struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context;
-
-	if (reg_num >= KVM_RISCV_SBI_EXT_MAX)
-		return -ENOENT;
+	const struct kvm_riscv_sbi_extension_entry *sext;
 
 	if (reg_val != 1 && reg_val != 0)
 		return -EINVAL;
 
-	for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) {
-		if (sbi_ext[i].ext_idx == reg_num) {
-			sext = &sbi_ext[i];
-			break;
-		}
-	}
-	if (!sext)
+	sext = riscv_vcpu_get_sbi_ext(vcpu, reg_num);
+	if (!sext || scontext->ext_status[sext->ext_idx] == KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE)
 		return -ENOENT;
 
 	scontext->ext_status[sext->ext_idx] = (reg_val) ?
-			KVM_RISCV_SBI_EXT_AVAILABLE :
-			KVM_RISCV_SBI_EXT_UNAVAILABLE;
+			KVM_RISCV_SBI_EXT_STATUS_ENABLED :
+			KVM_RISCV_SBI_EXT_STATUS_DISABLED;
 
 	return 0;
 }
@@ -170,24 +193,16 @@ static int riscv_vcpu_get_sbi_ext_single(struct kvm_vcpu *vcpu,
 					 unsigned long reg_num,
 					 unsigned long *reg_val)
 {
-	unsigned long i;
-	const struct kvm_riscv_sbi_extension_entry *sext = NULL;
 	struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context;
+	const struct kvm_riscv_sbi_extension_entry *sext;
 
-	if (reg_num >= KVM_RISCV_SBI_EXT_MAX)
-		return -ENOENT;
-
-	for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) {
-		if (sbi_ext[i].ext_idx == reg_num) {
-			sext = &sbi_ext[i];
-			break;
-		}
-	}
-	if (!sext)
+	sext = riscv_vcpu_get_sbi_ext(vcpu, reg_num);
+	if (!sext || scontext->ext_status[sext->ext_idx] == KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE)
 		return -ENOENT;
 
 	*reg_val = scontext->ext_status[sext->ext_idx] ==
-				KVM_RISCV_SBI_EXT_AVAILABLE;
+				KVM_RISCV_SBI_EXT_STATUS_ENABLED;
+
 	return 0;
 }
 
@@ -310,6 +325,69 @@ int kvm_riscv_vcpu_get_reg_sbi_ext(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+int kvm_riscv_vcpu_set_reg_sbi(struct kvm_vcpu *vcpu,
+			       const struct kvm_one_reg *reg)
+{
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_SBI_STATE);
+	unsigned long reg_subtype, reg_val;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+
+	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK;
+	reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK;
+
+	switch (reg_subtype) {
+	case KVM_REG_RISCV_SBI_STA:
+		return kvm_riscv_vcpu_set_reg_sbi_sta(vcpu, reg_num, reg_val);
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int kvm_riscv_vcpu_get_reg_sbi(struct kvm_vcpu *vcpu,
+			       const struct kvm_one_reg *reg)
+{
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_SBI_STATE);
+	unsigned long reg_subtype, reg_val;
+	int ret;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+
+	reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK;
+	reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK;
+
+	switch (reg_subtype) {
+	case KVM_REG_RISCV_SBI_STA:
+		ret = kvm_riscv_vcpu_get_reg_sbi_sta(vcpu, reg_num, &reg_val);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (ret)
+		return ret;
+
+	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
+
 const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext(
 				struct kvm_vcpu *vcpu, unsigned long extid)
 {
@@ -325,7 +403,7 @@ const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext(
 		if (ext->extid_start <= extid && ext->extid_end >= extid) {
 			if (entry->ext_idx >= KVM_RISCV_SBI_EXT_MAX ||
 			    scontext->ext_status[entry->ext_idx] ==
-						KVM_RISCV_SBI_EXT_AVAILABLE)
+						KVM_RISCV_SBI_EXT_STATUS_ENABLED)
 				return ext;
 
 			return NULL;
@@ -413,12 +491,12 @@ void kvm_riscv_vcpu_sbi_init(struct kvm_vcpu *vcpu)
 
 		if (ext->probe && !ext->probe(vcpu)) {
 			scontext->ext_status[entry->ext_idx] =
-				KVM_RISCV_SBI_EXT_UNAVAILABLE;
+				KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE;
 			continue;
 		}
 
-		scontext->ext_status[entry->ext_idx] = ext->default_unavail ?
-					KVM_RISCV_SBI_EXT_UNAVAILABLE :
-					KVM_RISCV_SBI_EXT_AVAILABLE;
+		scontext->ext_status[entry->ext_idx] = ext->default_disabled ?
+					KVM_RISCV_SBI_EXT_STATUS_DISABLED :
+					KVM_RISCV_SBI_EXT_STATUS_ENABLED;
 	}
 }
diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c
index 23b57c931b15..9c2ab3dfa93a 100644
--- a/arch/riscv/kvm/vcpu_sbi_replace.c
+++ b/arch/riscv/kvm/vcpu_sbi_replace.c
@@ -204,6 +204,6 @@ static int kvm_sbi_ext_dbcn_handler(struct kvm_vcpu *vcpu,
 const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_dbcn = {
 	.extid_start = SBI_EXT_DBCN,
 	.extid_end = SBI_EXT_DBCN,
-	.default_unavail = true,
+	.default_disabled = true,
 	.handler = kvm_sbi_ext_dbcn_handler,
 };
diff --git a/arch/riscv/kvm/vcpu_sbi_sta.c b/arch/riscv/kvm/vcpu_sbi_sta.c
new file mode 100644
index 000000000000..d8cf9ca28c61
--- /dev/null
+++ b/arch/riscv/kvm/vcpu_sbi_sta.c
@@ -0,0 +1,212 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2023 Ventana Micro Systems Inc.
+ */
+
+#include <linux/kconfig.h>
+#include <linux/kernel.h>
+#include <linux/kvm_host.h>
+#include <linux/mm.h>
+#include <linux/sizes.h>
+
+#include <asm/bug.h>
+#include <asm/current.h>
+#include <asm/kvm_vcpu_sbi.h>
+#include <asm/page.h>
+#include <asm/sbi.h>
+#include <asm/uaccess.h>
+
+void kvm_riscv_vcpu_sbi_sta_reset(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.sta.shmem = INVALID_GPA;
+	vcpu->arch.sta.last_steal = 0;
+}
+
+void kvm_riscv_vcpu_record_steal_time(struct kvm_vcpu *vcpu)
+{
+	gpa_t shmem = vcpu->arch.sta.shmem;
+	u64 last_steal = vcpu->arch.sta.last_steal;
+	__le32 __user *sequence_ptr;
+	__le64 __user *steal_ptr;
+	__le32 sequence_le;
+	__le64 steal_le;
+	u32 sequence;
+	u64 steal;
+	unsigned long hva;
+	gfn_t gfn;
+
+	if (shmem == INVALID_GPA)
+		return;
+
+	/*
+	 * shmem is 64-byte aligned (see the enforcement in
+	 * kvm_sbi_sta_steal_time_set_shmem()) and the size of sbi_sta_struct
+	 * is 64 bytes, so we know all its offsets are in the same page.
+	 */
+	gfn = shmem >> PAGE_SHIFT;
+	hva = kvm_vcpu_gfn_to_hva(vcpu, gfn);
+
+	if (WARN_ON(kvm_is_error_hva(hva))) {
+		vcpu->arch.sta.shmem = INVALID_GPA;
+		return;
+	}
+
+	sequence_ptr = (__le32 __user *)(hva + offset_in_page(shmem) +
+			       offsetof(struct sbi_sta_struct, sequence));
+	steal_ptr = (__le64 __user *)(hva + offset_in_page(shmem) +
+			    offsetof(struct sbi_sta_struct, steal));
+
+	if (WARN_ON(get_user(sequence_le, sequence_ptr)))
+		return;
+
+	sequence = le32_to_cpu(sequence_le);
+	sequence += 1;
+
+	if (WARN_ON(put_user(cpu_to_le32(sequence), sequence_ptr)))
+		return;
+
+	if (!WARN_ON(get_user(steal_le, steal_ptr))) {
+		steal = le64_to_cpu(steal_le);
+		vcpu->arch.sta.last_steal = READ_ONCE(current->sched_info.run_delay);
+		steal += vcpu->arch.sta.last_steal - last_steal;
+		WARN_ON(put_user(cpu_to_le64(steal), steal_ptr));
+	}
+
+	sequence += 1;
+	WARN_ON(put_user(cpu_to_le32(sequence), sequence_ptr));
+
+	kvm_vcpu_mark_page_dirty(vcpu, gfn);
+}
+
+static int kvm_sbi_sta_steal_time_set_shmem(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+	unsigned long shmem_phys_lo = cp->a0;
+	unsigned long shmem_phys_hi = cp->a1;
+	u32 flags = cp->a2;
+	struct sbi_sta_struct zero_sta = {0};
+	unsigned long hva;
+	bool writable;
+	gpa_t shmem;
+	int ret;
+
+	if (flags != 0)
+		return SBI_ERR_INVALID_PARAM;
+
+	if (shmem_phys_lo == SBI_STA_SHMEM_DISABLE &&
+	    shmem_phys_hi == SBI_STA_SHMEM_DISABLE) {
+		vcpu->arch.sta.shmem = INVALID_GPA;
+		return 0;
+	}
+
+	if (shmem_phys_lo & (SZ_64 - 1))
+		return SBI_ERR_INVALID_PARAM;
+
+	shmem = shmem_phys_lo;
+
+	if (shmem_phys_hi != 0) {
+		if (IS_ENABLED(CONFIG_32BIT))
+			shmem |= ((gpa_t)shmem_phys_hi << 32);
+		else
+			return SBI_ERR_INVALID_ADDRESS;
+	}
+
+	hva = kvm_vcpu_gfn_to_hva_prot(vcpu, shmem >> PAGE_SHIFT, &writable);
+	if (kvm_is_error_hva(hva) || !writable)
+		return SBI_ERR_INVALID_ADDRESS;
+
+	ret = kvm_vcpu_write_guest(vcpu, shmem, &zero_sta, sizeof(zero_sta));
+	if (ret)
+		return SBI_ERR_FAILURE;
+
+	vcpu->arch.sta.shmem = shmem;
+	vcpu->arch.sta.last_steal = current->sched_info.run_delay;
+
+	return 0;
+}
+
+static int kvm_sbi_ext_sta_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
+				   struct kvm_vcpu_sbi_return *retdata)
+{
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+	unsigned long funcid = cp->a6;
+	int ret;
+
+	switch (funcid) {
+	case SBI_EXT_STA_STEAL_TIME_SET_SHMEM:
+		ret = kvm_sbi_sta_steal_time_set_shmem(vcpu);
+		break;
+	default:
+		ret = SBI_ERR_NOT_SUPPORTED;
+		break;
+	}
+
+	retdata->err_val = ret;
+
+	return 0;
+}
+
+static unsigned long kvm_sbi_ext_sta_probe(struct kvm_vcpu *vcpu)
+{
+	return !!sched_info_on();
+}
+
+const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_sta = {
+	.extid_start = SBI_EXT_STA,
+	.extid_end = SBI_EXT_STA,
+	.handler = kvm_sbi_ext_sta_handler,
+	.probe = kvm_sbi_ext_sta_probe,
+};
+
+int kvm_riscv_vcpu_get_reg_sbi_sta(struct kvm_vcpu *vcpu,
+				   unsigned long reg_num,
+				   unsigned long *reg_val)
+{
+	switch (reg_num) {
+	case KVM_REG_RISCV_SBI_STA_REG(shmem_lo):
+		*reg_val = (unsigned long)vcpu->arch.sta.shmem;
+		break;
+	case KVM_REG_RISCV_SBI_STA_REG(shmem_hi):
+		if (IS_ENABLED(CONFIG_32BIT))
+			*reg_val = upper_32_bits(vcpu->arch.sta.shmem);
+		else
+			*reg_val = 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int kvm_riscv_vcpu_set_reg_sbi_sta(struct kvm_vcpu *vcpu,
+				   unsigned long reg_num,
+				   unsigned long reg_val)
+{
+	switch (reg_num) {
+	case KVM_REG_RISCV_SBI_STA_REG(shmem_lo):
+		if (IS_ENABLED(CONFIG_32BIT)) {
+			gpa_t hi = upper_32_bits(vcpu->arch.sta.shmem);
+
+			vcpu->arch.sta.shmem = reg_val;
+			vcpu->arch.sta.shmem |= hi << 32;
+		} else {
+			vcpu->arch.sta.shmem = reg_val;
+		}
+		break;
+	case KVM_REG_RISCV_SBI_STA_REG(shmem_hi):
+		if (IS_ENABLED(CONFIG_32BIT)) {
+			gpa_t lo = lower_32_bits(vcpu->arch.sta.shmem);
+
+			vcpu->arch.sta.shmem = ((gpa_t)reg_val << 32);
+			vcpu->arch.sta.shmem |= lo;
+		} else if (reg_val != 0) {
+			return -EINVAL;
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
diff --git a/arch/riscv/kvm/vcpu_switch.S b/arch/riscv/kvm/vcpu_switch.S
index d74df8eb4d71..0c26189aa01c 100644
--- a/arch/riscv/kvm/vcpu_switch.S
+++ b/arch/riscv/kvm/vcpu_switch.S
@@ -15,7 +15,7 @@
 	.altmacro
 	.option norelax
 
-ENTRY(__kvm_riscv_switch_to)
+SYM_FUNC_START(__kvm_riscv_switch_to)
 	/* Save Host GPRs (except A0 and T0-T6) */
 	REG_S	ra, (KVM_ARCH_HOST_RA)(a0)
 	REG_S	sp, (KVM_ARCH_HOST_SP)(a0)
@@ -45,7 +45,7 @@ ENTRY(__kvm_riscv_switch_to)
 	REG_L	t0, (KVM_ARCH_GUEST_SSTATUS)(a0)
 	REG_L	t1, (KVM_ARCH_GUEST_HSTATUS)(a0)
 	REG_L	t2, (KVM_ARCH_GUEST_SCOUNTEREN)(a0)
-	la	t4, __kvm_switch_return
+	la	t4, .Lkvm_switch_return
 	REG_L	t5, (KVM_ARCH_GUEST_SEPC)(a0)
 
 	/* Save Host and Restore Guest SSTATUS */
@@ -113,7 +113,7 @@ ENTRY(__kvm_riscv_switch_to)
 
 	/* Back to Host */
 	.align 2
-__kvm_switch_return:
+.Lkvm_switch_return:
 	/* Swap Guest A0 with SSCRATCH */
 	csrrw	a0, CSR_SSCRATCH, a0
 
@@ -208,9 +208,9 @@ __kvm_switch_return:
 
 	/* Return to C code */
 	ret
-ENDPROC(__kvm_riscv_switch_to)
+SYM_FUNC_END(__kvm_riscv_switch_to)
 
-ENTRY(__kvm_riscv_unpriv_trap)
+SYM_CODE_START(__kvm_riscv_unpriv_trap)
 	/*
 	 * We assume that faulting unpriv load/store instruction is
 	 * 4-byte long and blindly increment SEPC by 4.
@@ -231,12 +231,10 @@ ENTRY(__kvm_riscv_unpriv_trap)
 	csrr	a1, CSR_HTINST
 	REG_S	a1, (KVM_ARCH_TRAP_HTINST)(a0)
 	sret
-ENDPROC(__kvm_riscv_unpriv_trap)
+SYM_CODE_END(__kvm_riscv_unpriv_trap)
 
 #ifdef	CONFIG_FPU
-	.align 3
-	.global __kvm_riscv_fp_f_save
-__kvm_riscv_fp_f_save:
+SYM_FUNC_START(__kvm_riscv_fp_f_save)
 	csrr t2, CSR_SSTATUS
 	li t1, SR_FS
 	csrs CSR_SSTATUS, t1
@@ -276,10 +274,9 @@ __kvm_riscv_fp_f_save:
 	sw t0, KVM_ARCH_FP_F_FCSR(a0)
 	csrw CSR_SSTATUS, t2
 	ret
+SYM_FUNC_END(__kvm_riscv_fp_f_save)
 
-	.align 3
-	.global __kvm_riscv_fp_d_save
-__kvm_riscv_fp_d_save:
+SYM_FUNC_START(__kvm_riscv_fp_d_save)
 	csrr t2, CSR_SSTATUS
 	li t1, SR_FS
 	csrs CSR_SSTATUS, t1
@@ -319,10 +316,9 @@ __kvm_riscv_fp_d_save:
 	sw t0, KVM_ARCH_FP_D_FCSR(a0)
 	csrw CSR_SSTATUS, t2
 	ret
+SYM_FUNC_END(__kvm_riscv_fp_d_save)
 
-	.align 3
-	.global __kvm_riscv_fp_f_restore
-__kvm_riscv_fp_f_restore:
+SYM_FUNC_START(__kvm_riscv_fp_f_restore)
 	csrr t2, CSR_SSTATUS
 	li t1, SR_FS
 	lw t0, KVM_ARCH_FP_F_FCSR(a0)
@@ -362,10 +358,9 @@ __kvm_riscv_fp_f_restore:
 	fscsr t0
 	csrw CSR_SSTATUS, t2
 	ret
+SYM_FUNC_END(__kvm_riscv_fp_f_restore)
 
-	.align 3
-	.global __kvm_riscv_fp_d_restore
-__kvm_riscv_fp_d_restore:
+SYM_FUNC_START(__kvm_riscv_fp_d_restore)
 	csrr t2, CSR_SSTATUS
 	li t1, SR_FS
 	lw t0, KVM_ARCH_FP_D_FCSR(a0)
@@ -405,4 +400,5 @@ __kvm_riscv_fp_d_restore:
 	fscsr t0
 	csrw CSR_SSTATUS, t2
 	ret
+SYM_FUNC_END(__kvm_riscv_fp_d_restore)
 #endif
diff --git a/arch/riscv/kvm/vcpu_vector.c b/arch/riscv/kvm/vcpu_vector.c
index b339a2682f25..d92d1348045c 100644
--- a/arch/riscv/kvm/vcpu_vector.c
+++ b/arch/riscv/kvm/vcpu_vector.c
@@ -76,6 +76,7 @@ int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu,
 	cntx->vector.datap = kmalloc(riscv_v_vsize, GFP_KERNEL);
 	if (!cntx->vector.datap)
 		return -ENOMEM;
+	cntx->vector.vlenb = riscv_v_vsize / 32;
 
 	vcpu->arch.host_context.vector.datap = kzalloc(riscv_v_vsize, GFP_KERNEL);
 	if (!vcpu->arch.host_context.vector.datap)
@@ -115,6 +116,9 @@ static int kvm_riscv_vcpu_vreg_addr(struct kvm_vcpu *vcpu,
 		case KVM_REG_RISCV_VECTOR_CSR_REG(vcsr):
 			*reg_addr = &cntx->vector.vcsr;
 			break;
+		case KVM_REG_RISCV_VECTOR_CSR_REG(vlenb):
+			*reg_addr = &cntx->vector.vlenb;
+			break;
 		case KVM_REG_RISCV_VECTOR_CSR_REG(datap):
 		default:
 			return -ENOENT;
@@ -173,6 +177,18 @@ int kvm_riscv_vcpu_set_reg_vector(struct kvm_vcpu *vcpu,
 	if (!riscv_isa_extension_available(isa, v))
 		return -ENOENT;
 
+	if (reg_num == KVM_REG_RISCV_VECTOR_CSR_REG(vlenb)) {
+		struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
+		unsigned long reg_val;
+
+		if (copy_from_user(&reg_val, uaddr, reg_size))
+			return -EFAULT;
+		if (reg_val != cntx->vector.vlenb)
+			return -EINVAL;
+
+		return 0;
+	}
+
 	rc = kvm_riscv_vcpu_vreg_addr(vcpu, reg_num, reg_size, &reg_addr);
 	if (rc)
 		return rc;
diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c
index 7e2b50c692c1..ce58bc48e5b8 100644
--- a/arch/riscv/kvm/vm.c
+++ b/arch/riscv/kvm/vm.c
@@ -179,7 +179,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = kvm_riscv_aia_available();
 		break;
 	case KVM_CAP_IOEVENTFD:
-	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_USER_MEMORY:
 	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
index 26cb2502ecf8..bd6e6c1b0497 100644
--- a/arch/riscv/lib/Makefile
+++ b/arch/riscv/lib/Makefile
@@ -6,8 +6,14 @@ lib-y			+= memmove.o
 lib-y			+= strcmp.o
 lib-y			+= strlen.o
 lib-y			+= strncmp.o
+lib-y			+= csum.o
+ifeq ($(CONFIG_MMU), y)
+lib-$(CONFIG_RISCV_ISA_V)	+= uaccess_vector.o
+endif
 lib-$(CONFIG_MMU)	+= uaccess.o
 lib-$(CONFIG_64BIT)	+= tishift.o
 lib-$(CONFIG_RISCV_ISA_ZICBOZ)	+= clear_page.o
 
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
+lib-$(CONFIG_RISCV_ISA_V)	+= xor.o
+lib-$(CONFIG_RISCV_ISA_V)	+= riscv_v_helpers.o
diff --git a/arch/riscv/lib/clear_page.S b/arch/riscv/lib/clear_page.S
index b22de1231144..20ff03f5b0f2 100644
--- a/arch/riscv/lib/clear_page.S
+++ b/arch/riscv/lib/clear_page.S
@@ -4,9 +4,9 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/alternative-macros.h>
-#include <asm-generic/export.h>
 #include <asm/hwcap.h>
 #include <asm/insn-def.h>
 #include <asm/page.h>
diff --git a/arch/riscv/lib/csum.c b/arch/riscv/lib/csum.c
new file mode 100644
index 000000000000..74af3ab520b6
--- /dev/null
+++ b/arch/riscv/lib/csum.c
@@ -0,0 +1,328 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Checksum library
+ *
+ * Influenced by arch/arm64/lib/csum.c
+ * Copyright (C) 2023 Rivos Inc.
+ */
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/jump_label.h>
+#include <linux/kasan-checks.h>
+#include <linux/kernel.h>
+
+#include <asm/cpufeature.h>
+
+#include <net/checksum.h>
+
+/* Default version is sufficient for 32 bit */
+#ifndef CONFIG_32BIT
+__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+			const struct in6_addr *daddr,
+			__u32 len, __u8 proto, __wsum csum)
+{
+	unsigned int ulen, uproto;
+	unsigned long sum = (__force unsigned long)csum;
+
+	sum += (__force unsigned long)saddr->s6_addr32[0];
+	sum += (__force unsigned long)saddr->s6_addr32[1];
+	sum += (__force unsigned long)saddr->s6_addr32[2];
+	sum += (__force unsigned long)saddr->s6_addr32[3];
+
+	sum += (__force unsigned long)daddr->s6_addr32[0];
+	sum += (__force unsigned long)daddr->s6_addr32[1];
+	sum += (__force unsigned long)daddr->s6_addr32[2];
+	sum += (__force unsigned long)daddr->s6_addr32[3];
+
+	ulen = (__force unsigned int)htonl((unsigned int)len);
+	sum += ulen;
+
+	uproto = (__force unsigned int)htonl(proto);
+	sum += uproto;
+
+	/*
+	 * Zbb support saves 4 instructions, so not worth checking without
+	 * alternatives if supported
+	 */
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) &&
+	    IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+		unsigned long fold_temp;
+
+		/*
+		 * Zbb is likely available when the kernel is compiled with Zbb
+		 * support, so nop when Zbb is available and jump when Zbb is
+		 * not available.
+		 */
+		asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+					      RISCV_ISA_EXT_ZBB, 1)
+				  :
+				  :
+				  :
+				  : no_zbb);
+		asm(".option push					\n\
+		.option arch,+zbb					\n\
+			rori	%[fold_temp], %[sum], 32		\n\
+			add	%[sum], %[fold_temp], %[sum]		\n\
+			srli	%[sum], %[sum], 32			\n\
+			not	%[fold_temp], %[sum]			\n\
+			roriw	%[sum], %[sum], 16			\n\
+			subw	%[sum], %[fold_temp], %[sum]		\n\
+		.option pop"
+		: [sum] "+r" (sum), [fold_temp] "=&r" (fold_temp));
+		return (__force __sum16)(sum >> 16);
+	}
+no_zbb:
+	sum += ror64(sum, 32);
+	sum >>= 32;
+	return csum_fold((__force __wsum)sum);
+}
+EXPORT_SYMBOL(csum_ipv6_magic);
+#endif /* !CONFIG_32BIT */
+
+#ifdef CONFIG_32BIT
+#define OFFSET_MASK 3
+#elif CONFIG_64BIT
+#define OFFSET_MASK 7
+#endif
+
+static inline __no_sanitize_address unsigned long
+do_csum_common(const unsigned long *ptr, const unsigned long *end,
+	       unsigned long data)
+{
+	unsigned int shift;
+	unsigned long csum = 0, carry = 0;
+
+	/*
+	 * Do 32-bit reads on RV32 and 64-bit reads otherwise. This should be
+	 * faster than doing 32-bit reads on architectures that support larger
+	 * reads.
+	 */
+	while (ptr < end) {
+		csum += data;
+		carry += csum < data;
+		data = *(ptr++);
+	}
+
+	/*
+	 * Perform alignment (and over-read) bytes on the tail if any bytes
+	 * leftover.
+	 */
+	shift = ((long)ptr - (long)end) * 8;
+#ifdef __LITTLE_ENDIAN
+	data = (data << shift) >> shift;
+#else
+	data = (data >> shift) << shift;
+#endif
+	csum += data;
+	carry += csum < data;
+	csum += carry;
+	csum += csum < carry;
+
+	return csum;
+}
+
+/*
+ * Algorithm accounts for buff being misaligned.
+ * If buff is not aligned, will over-read bytes but not use the bytes that it
+ * shouldn't. The same thing will occur on the tail-end of the read.
+ */
+static inline __no_sanitize_address unsigned int
+do_csum_with_alignment(const unsigned char *buff, int len)
+{
+	unsigned int offset, shift;
+	unsigned long csum, data;
+	const unsigned long *ptr, *end;
+
+	/*
+	 * Align address to closest word (double word on rv64) that comes before
+	 * buff. This should always be in the same page and cache line.
+	 * Directly call KASAN with the alignment we will be using.
+	 */
+	offset = (unsigned long)buff & OFFSET_MASK;
+	kasan_check_read(buff, len);
+	ptr = (const unsigned long *)(buff - offset);
+
+	/*
+	 * Clear the most significant bytes that were over-read if buff was not
+	 * aligned.
+	 */
+	shift = offset * 8;
+	data = *(ptr++);
+#ifdef __LITTLE_ENDIAN
+	data = (data >> shift) << shift;
+#else
+	data = (data << shift) >> shift;
+#endif
+	end = (const unsigned long *)(buff + len);
+	csum = do_csum_common(ptr, end, data);
+
+#ifdef CC_HAS_ASM_GOTO_TIED_OUTPUT
+	/*
+	 * Zbb support saves 6 instructions, so not worth checking without
+	 * alternatives if supported
+	 */
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) &&
+	    IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+		unsigned long fold_temp;
+
+		/*
+		 * Zbb is likely available when the kernel is compiled with Zbb
+		 * support, so nop when Zbb is available and jump when Zbb is
+		 * not available.
+		 */
+		asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+					      RISCV_ISA_EXT_ZBB, 1)
+				  :
+				  :
+				  :
+				  : no_zbb);
+
+#ifdef CONFIG_32BIT
+		asm_goto_output(".option push			\n\
+		.option arch,+zbb				\n\
+			rori	%[fold_temp], %[csum], 16	\n\
+			andi	%[offset], %[offset], 1		\n\
+			add	%[csum], %[fold_temp], %[csum]	\n\
+			beq	%[offset], zero, %l[end]	\n\
+			rev8	%[csum], %[csum]		\n\
+		.option pop"
+			: [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp)
+			: [offset] "r" (offset)
+			:
+			: end);
+
+		return (unsigned short)csum;
+#else /* !CONFIG_32BIT */
+		asm_goto_output(".option push			\n\
+		.option arch,+zbb				\n\
+			rori	%[fold_temp], %[csum], 32	\n\
+			add	%[csum], %[fold_temp], %[csum]	\n\
+			srli	%[csum], %[csum], 32		\n\
+			roriw	%[fold_temp], %[csum], 16	\n\
+			addw	%[csum], %[fold_temp], %[csum]	\n\
+			andi	%[offset], %[offset], 1		\n\
+			beq	%[offset], zero, %l[end]	\n\
+			rev8	%[csum], %[csum]		\n\
+		.option pop"
+			: [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp)
+			: [offset] "r" (offset)
+			:
+			: end);
+
+		return (csum << 16) >> 48;
+#endif /* !CONFIG_32BIT */
+end:
+		return csum >> 16;
+	}
+no_zbb:
+#endif /* CC_HAS_ASM_GOTO_TIED_OUTPUT */
+#ifndef CONFIG_32BIT
+	csum += ror64(csum, 32);
+	csum >>= 32;
+#endif
+	csum = (u32)csum + ror32((u32)csum, 16);
+	if (offset & 1)
+		return (u16)swab32(csum);
+	return csum >> 16;
+}
+
+/*
+ * Does not perform alignment, should only be used if machine has fast
+ * misaligned accesses, or when buff is known to be aligned.
+ */
+static inline __no_sanitize_address unsigned int
+do_csum_no_alignment(const unsigned char *buff, int len)
+{
+	unsigned long csum, data;
+	const unsigned long *ptr, *end;
+
+	ptr = (const unsigned long *)(buff);
+	data = *(ptr++);
+
+	kasan_check_read(buff, len);
+
+	end = (const unsigned long *)(buff + len);
+	csum = do_csum_common(ptr, end, data);
+
+	/*
+	 * Zbb support saves 6 instructions, so not worth checking without
+	 * alternatives if supported
+	 */
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) &&
+	    IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+		unsigned long fold_temp;
+
+		/*
+		 * Zbb is likely available when the kernel is compiled with Zbb
+		 * support, so nop when Zbb is available and jump when Zbb is
+		 * not available.
+		 */
+		asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+					      RISCV_ISA_EXT_ZBB, 1)
+				  :
+				  :
+				  :
+				  : no_zbb);
+
+#ifdef CONFIG_32BIT
+		asm (".option push				\n\
+		.option arch,+zbb				\n\
+			rori	%[fold_temp], %[csum], 16	\n\
+			add	%[csum], %[fold_temp], %[csum]	\n\
+		.option pop"
+			: [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp)
+			:
+			: );
+
+#else /* !CONFIG_32BIT */
+		asm (".option push				\n\
+		.option arch,+zbb				\n\
+			rori	%[fold_temp], %[csum], 32	\n\
+			add	%[csum], %[fold_temp], %[csum]	\n\
+			srli	%[csum], %[csum], 32		\n\
+			roriw	%[fold_temp], %[csum], 16	\n\
+			addw	%[csum], %[fold_temp], %[csum]	\n\
+		.option pop"
+			: [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp)
+			:
+			: );
+#endif /* !CONFIG_32BIT */
+		return csum >> 16;
+	}
+no_zbb:
+#ifndef CONFIG_32BIT
+	csum += ror64(csum, 32);
+	csum >>= 32;
+#endif
+	csum = (u32)csum + ror32((u32)csum, 16);
+	return csum >> 16;
+}
+
+/*
+ * Perform a checksum on an arbitrary memory address.
+ * Will do a light-weight address alignment if buff is misaligned, unless
+ * cpu supports fast misaligned accesses.
+ */
+unsigned int do_csum(const unsigned char *buff, int len)
+{
+	if (unlikely(len <= 0))
+		return 0;
+
+	/*
+	 * Significant performance gains can be seen by not doing alignment
+	 * on machines with fast misaligned accesses.
+	 *
+	 * There is some duplicate code between the "with_alignment" and
+	 * "no_alignment" implmentations, but the overlap is too awkward to be
+	 * able to fit in one function without introducing multiple static
+	 * branches. The largest chunk of overlap was delegated into the
+	 * do_csum_common function.
+	 */
+	if (static_branch_likely(&fast_misaligned_access_speed_key))
+		return do_csum_no_alignment(buff, len);
+
+	if (((unsigned long)buff & OFFSET_MASK) == 0)
+		return do_csum_no_alignment(buff, len);
+
+	return do_csum_with_alignment(buff, len);
+}
diff --git a/arch/riscv/lib/riscv_v_helpers.c b/arch/riscv/lib/riscv_v_helpers.c
new file mode 100644
index 000000000000..be38a93cedae
--- /dev/null
+++ b/arch/riscv/lib/riscv_v_helpers.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2023 SiFive
+ * Author: Andy Chiu <andy.chiu@sifive.com>
+ */
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+#include <asm/vector.h>
+#include <asm/simd.h>
+
+#ifdef CONFIG_MMU
+#include <asm/asm-prototypes.h>
+#endif
+
+#ifdef CONFIG_MMU
+size_t riscv_v_usercopy_threshold = CONFIG_RISCV_ISA_V_UCOPY_THRESHOLD;
+int __asm_vector_usercopy(void *dst, void *src, size_t n);
+int fallback_scalar_usercopy(void *dst, void *src, size_t n);
+asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n)
+{
+	size_t remain, copied;
+
+	/* skip has_vector() check because it has been done by the asm  */
+	if (!may_use_simd())
+		goto fallback;
+
+	kernel_vector_begin();
+	remain = __asm_vector_usercopy(dst, src, n);
+	kernel_vector_end();
+
+	if (remain) {
+		copied = n - remain;
+		dst += copied;
+		src += copied;
+		n = remain;
+		goto fallback;
+	}
+
+	return remain;
+
+fallback:
+	return fallback_scalar_usercopy(dst, src, n);
+}
+#endif
diff --git a/arch/riscv/lib/tishift.S b/arch/riscv/lib/tishift.S
index ef90075c4b0a..c8294bf72c06 100644
--- a/arch/riscv/lib/tishift.S
+++ b/arch/riscv/lib/tishift.S
@@ -4,7 +4,7 @@
  */
 
 #include <linux/linkage.h>
-#include <asm-generic/export.h>
+#include <linux/export.h>
 
 SYM_FUNC_START(__lshrti3)
 	beqz	a2, .L1
diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S
index 3ab438f30d13..bc22c078aba8 100644
--- a/arch/riscv/lib/uaccess.S
+++ b/arch/riscv/lib/uaccess.S
@@ -1,8 +1,10 @@
 #include <linux/linkage.h>
-#include <asm-generic/export.h>
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/asm-extable.h>
 #include <asm/csr.h>
+#include <asm/hwcap.h>
+#include <asm/alternative-macros.h>
 
 	.macro fixup op reg addr lbl
 100:
@@ -11,6 +13,13 @@
 	.endm
 
 SYM_FUNC_START(__asm_copy_to_user)
+#ifdef CONFIG_RISCV_ISA_V
+	ALTERNATIVE("j fallback_scalar_usercopy", "nop", 0, RISCV_ISA_EXT_v, CONFIG_RISCV_ISA_V)
+	REG_L	t0, riscv_v_usercopy_threshold
+	bltu	a2, t0, fallback_scalar_usercopy
+	tail enter_vector_usercopy
+#endif
+SYM_FUNC_START(fallback_scalar_usercopy)
 
 	/* Enable access to user memory */
 	li t6, SR_SUM
@@ -181,6 +190,7 @@ SYM_FUNC_START(__asm_copy_to_user)
 	sub a0, t5, a0
 	ret
 SYM_FUNC_END(__asm_copy_to_user)
+SYM_FUNC_END(fallback_scalar_usercopy)
 EXPORT_SYMBOL(__asm_copy_to_user)
 SYM_FUNC_ALIAS(__asm_copy_from_user, __asm_copy_to_user)
 EXPORT_SYMBOL(__asm_copy_from_user)
diff --git a/arch/riscv/lib/uaccess_vector.S b/arch/riscv/lib/uaccess_vector.S
new file mode 100644
index 000000000000..51ab5588e9ff
--- /dev/null
+++ b/arch/riscv/lib/uaccess_vector.S
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <linux/linkage.h>
+#include <asm-generic/export.h>
+#include <asm/asm.h>
+#include <asm/asm-extable.h>
+#include <asm/csr.h>
+
+#define pDst a0
+#define pSrc a1
+#define iNum a2
+
+#define iVL a3
+
+#define ELEM_LMUL_SETTING m8
+#define vData v0
+
+	.macro fixup op reg addr lbl
+100:
+	\op \reg, \addr
+	_asm_extable	100b, \lbl
+	.endm
+
+SYM_FUNC_START(__asm_vector_usercopy)
+	/* Enable access to user memory */
+	li	t6, SR_SUM
+	csrs	CSR_STATUS, t6
+
+loop:
+	vsetvli iVL, iNum, e8, ELEM_LMUL_SETTING, ta, ma
+	fixup vle8.v vData, (pSrc), 10f
+	sub iNum, iNum, iVL
+	add pSrc, pSrc, iVL
+	fixup vse8.v vData, (pDst), 11f
+	add pDst, pDst, iVL
+	bnez iNum, loop
+
+	/* Exception fixup for vector load is shared with normal exit */
+10:
+	/* Disable access to user memory */
+	csrc	CSR_STATUS, t6
+	mv	a0, iNum
+	ret
+
+	/* Exception fixup code for vector store. */
+11:
+	/* Undo the subtraction after vle8.v */
+	add	iNum, iNum, iVL
+	/* Make sure the scalar fallback skip already processed bytes */
+	csrr	t2, CSR_VSTART
+	sub	iNum, iNum, t2
+	j	10b
+SYM_FUNC_END(__asm_vector_usercopy)
diff --git a/arch/riscv/lib/xor.S b/arch/riscv/lib/xor.S
new file mode 100644
index 000000000000..b28f2430e52f
--- /dev/null
+++ b/arch/riscv/lib/xor.S
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2021 SiFive
+ */
+#include <linux/linkage.h>
+#include <linux/export.h>
+#include <asm/asm.h>
+
+SYM_FUNC_START(xor_regs_2_)
+	vsetvli a3, a0, e8, m8, ta, ma
+	vle8.v v0, (a1)
+	vle8.v v8, (a2)
+	sub a0, a0, a3
+	vxor.vv v16, v0, v8
+	add a2, a2, a3
+	vse8.v v16, (a1)
+	add a1, a1, a3
+	bnez a0, xor_regs_2_
+	ret
+SYM_FUNC_END(xor_regs_2_)
+EXPORT_SYMBOL(xor_regs_2_)
+
+SYM_FUNC_START(xor_regs_3_)
+	vsetvli a4, a0, e8, m8, ta, ma
+	vle8.v v0, (a1)
+	vle8.v v8, (a2)
+	sub a0, a0, a4
+	vxor.vv v0, v0, v8
+	vle8.v v16, (a3)
+	add a2, a2, a4
+	vxor.vv v16, v0, v16
+	add a3, a3, a4
+	vse8.v v16, (a1)
+	add a1, a1, a4
+	bnez a0, xor_regs_3_
+	ret
+SYM_FUNC_END(xor_regs_3_)
+EXPORT_SYMBOL(xor_regs_3_)
+
+SYM_FUNC_START(xor_regs_4_)
+	vsetvli a5, a0, e8, m8, ta, ma
+	vle8.v v0, (a1)
+	vle8.v v8, (a2)
+	sub a0, a0, a5
+	vxor.vv v0, v0, v8
+	vle8.v v16, (a3)
+	add a2, a2, a5
+	vxor.vv v0, v0, v16
+	vle8.v v24, (a4)
+	add a3, a3, a5
+	vxor.vv v16, v0, v24
+	add a4, a4, a5
+	vse8.v v16, (a1)
+	add a1, a1, a5
+	bnez a0, xor_regs_4_
+	ret
+SYM_FUNC_END(xor_regs_4_)
+EXPORT_SYMBOL(xor_regs_4_)
+
+SYM_FUNC_START(xor_regs_5_)
+	vsetvli a6, a0, e8, m8, ta, ma
+	vle8.v v0, (a1)
+	vle8.v v8, (a2)
+	sub a0, a0, a6
+	vxor.vv v0, v0, v8
+	vle8.v v16, (a3)
+	add a2, a2, a6
+	vxor.vv v0, v0, v16
+	vle8.v v24, (a4)
+	add a3, a3, a6
+	vxor.vv v0, v0, v24
+	vle8.v v8, (a5)
+	add a4, a4, a6
+	vxor.vv v16, v0, v8
+	add a5, a5, a6
+	vse8.v v16, (a1)
+	add a1, a1, a6
+	bnez a0, xor_regs_5_
+	ret
+SYM_FUNC_END(xor_regs_5_)
+EXPORT_SYMBOL(xor_regs_5_)
diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
index 3a4dfc8babcf..2c869f8026a8 100644
--- a/arch/riscv/mm/Makefile
+++ b/arch/riscv/mm/Makefile
@@ -13,10 +13,9 @@ endif
 KCOV_INSTRUMENT_init.o := n
 
 obj-y += init.o
-obj-$(CONFIG_MMU) += extable.o fault.o pageattr.o
+obj-$(CONFIG_MMU) += extable.o fault.o pageattr.o pgtable.o
 obj-y += cacheflush.o
 obj-y += context.o
-obj-y += pgtable.o
 obj-y += pmem.o
 
 ifeq ($(CONFIG_MMU),y)
diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c
index 4e4e469b8dd6..843107f834b2 100644
--- a/arch/riscv/mm/dma-noncoherent.c
+++ b/arch/riscv/mm/dma-noncoherent.c
@@ -129,7 +129,7 @@ void arch_dma_prep_coherent(struct page *page, size_t size)
 }
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-		const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	WARN_TAINT(!coherent && riscv_cbom_block_size > ARCH_DMA_MINALIGN,
 		   TAINT_CPU_OUT_OF_SPEC,
diff --git a/arch/riscv/mm/extable.c b/arch/riscv/mm/extable.c
index 35484d830fd6..dd1530af3ef1 100644
--- a/arch/riscv/mm/extable.c
+++ b/arch/riscv/mm/extable.c
@@ -27,6 +27,14 @@ static bool ex_handler_fixup(const struct exception_table_entry *ex,
 	return true;
 }
 
+static inline unsigned long regs_get_gpr(struct pt_regs *regs, unsigned int offset)
+{
+	if (unlikely(!offset || offset > MAX_REG_OFFSET))
+		return 0;
+
+	return *(unsigned long *)((unsigned long)regs + offset);
+}
+
 static inline void regs_set_gpr(struct pt_regs *regs, unsigned int offset,
 				unsigned long val)
 {
@@ -50,6 +58,27 @@ static bool ex_handler_uaccess_err_zero(const struct exception_table_entry *ex,
 	return true;
 }
 
+static bool
+ex_handler_load_unaligned_zeropad(const struct exception_table_entry *ex,
+				  struct pt_regs *regs)
+{
+	int reg_data = FIELD_GET(EX_DATA_REG_DATA, ex->data);
+	int reg_addr = FIELD_GET(EX_DATA_REG_ADDR, ex->data);
+	unsigned long data, addr, offset;
+
+	addr = regs_get_gpr(regs, reg_addr * sizeof(unsigned long));
+
+	offset = addr & 0x7UL;
+	addr &= ~0x7UL;
+
+	data = *(unsigned long *)addr >> (offset * 8);
+
+	regs_set_gpr(regs, reg_data * sizeof(unsigned long), data);
+
+	regs->epc = get_ex_fixup(ex);
+	return true;
+}
+
 bool fixup_exception(struct pt_regs *regs)
 {
 	const struct exception_table_entry *ex;
@@ -65,6 +94,8 @@ bool fixup_exception(struct pt_regs *regs)
 		return ex_handler_bpf(ex, regs);
 	case EX_TYPE_UACCESS_ERR_ZERO:
 		return ex_handler_uaccess_err_zero(ex, regs);
+	case EX_TYPE_LOAD_UNALIGNED_ZEROPAD:
+		return ex_handler_load_unaligned_zeropad(ex, regs);
 	}
 
 	BUG();
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 081339ddf47e..3ba1d4dde5dd 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -136,24 +136,24 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a
 	pgd = (pgd_t *)pfn_to_virt(pfn) + index;
 	pgd_k = init_mm.pgd + index;
 
-	if (!pgd_present(*pgd_k)) {
+	if (!pgd_present(pgdp_get(pgd_k))) {
 		no_context(regs, addr);
 		return;
 	}
-	set_pgd(pgd, *pgd_k);
+	set_pgd(pgd, pgdp_get(pgd_k));
 
 	p4d_k = p4d_offset(pgd_k, addr);
-	if (!p4d_present(*p4d_k)) {
+	if (!p4d_present(p4dp_get(p4d_k))) {
 		no_context(regs, addr);
 		return;
 	}
 
 	pud_k = pud_offset(p4d_k, addr);
-	if (!pud_present(*pud_k)) {
+	if (!pud_present(pudp_get(pud_k))) {
 		no_context(regs, addr);
 		return;
 	}
-	if (pud_leaf(*pud_k))
+	if (pud_leaf(pudp_get(pud_k)))
 		goto flush_tlb;
 
 	/*
@@ -161,11 +161,11 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a
 	 * to copy individual PTEs
 	 */
 	pmd_k = pmd_offset(pud_k, addr);
-	if (!pmd_present(*pmd_k)) {
+	if (!pmd_present(pmdp_get(pmd_k))) {
 		no_context(regs, addr);
 		return;
 	}
-	if (pmd_leaf(*pmd_k))
+	if (pmd_leaf(pmdp_get(pmd_k)))
 		goto flush_tlb;
 
 	/*
@@ -175,7 +175,7 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a
 	 * silently loop forever.
 	 */
 	pte_k = pte_offset_kernel(pmd_k, addr);
-	if (!pte_present(*pte_k)) {
+	if (!pte_present(ptep_get(pte_k))) {
 		no_context(regs, addr);
 		return;
 	}
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index b52f0210481f..5ef2a6891158 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -54,7 +54,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 	}
 
 	if (sz == PMD_SIZE) {
-		if (want_pmd_share(vma, addr) && pud_none(*pud))
+		if (want_pmd_share(vma, addr) && pud_none(pudp_get(pud)))
 			pte = huge_pmd_share(mm, vma, addr, pud);
 		else
 			pte = (pte_t *)pmd_alloc(mm, pud, addr);
@@ -93,11 +93,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 	pmd_t *pmd;
 
 	pgd = pgd_offset(mm, addr);
-	if (!pgd_present(*pgd))
+	if (!pgd_present(pgdp_get(pgd)))
 		return NULL;
 
 	p4d = p4d_offset(pgd, addr);
-	if (!p4d_present(*p4d))
+	if (!p4d_present(p4dp_get(p4d)))
 		return NULL;
 
 	pud = pud_offset(p4d, addr);
@@ -105,7 +105,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		/* must be pud huge, non-present or none */
 		return (pte_t *)pud;
 
-	if (!pud_present(*pud))
+	if (!pud_present(pudp_get(pud)))
 		return NULL;
 
 	pmd = pmd_offset(pud, addr);
@@ -113,7 +113,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		/* must be pmd huge, non-present or none */
 		return (pte_t *)pmd;
 
-	if (!pmd_present(*pmd))
+	if (!pmd_present(pmdp_get(pmd)))
 		return NULL;
 
 	for_each_napot_order(order) {
@@ -125,6 +125,26 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 	return pte;
 }
 
+unsigned long hugetlb_mask_last_page(struct hstate *h)
+{
+	unsigned long hp_size = huge_page_size(h);
+
+	switch (hp_size) {
+#ifndef __PAGETABLE_PMD_FOLDED
+	case PUD_SIZE:
+		return P4D_SIZE - PUD_SIZE;
+#endif
+	case PMD_SIZE:
+		return PUD_SIZE - PMD_SIZE;
+	case napot_cont_size(NAPOT_CONT64KB_ORDER):
+		return PMD_SIZE - napot_cont_size(NAPOT_CONT64KB_ORDER);
+	default:
+		break;
+	}
+
+	return 0UL;
+}
+
 static pte_t get_clear_contig(struct mm_struct *mm,
 			      unsigned long addr,
 			      pte_t *ptep,
@@ -177,13 +197,36 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
 	return entry;
 }
 
+static void clear_flush(struct mm_struct *mm,
+			unsigned long addr,
+			pte_t *ptep,
+			unsigned long pgsize,
+			unsigned long ncontig)
+{
+	struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
+	unsigned long i, saddr = addr;
+
+	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
+		ptep_get_and_clear(mm, addr, ptep);
+
+	flush_tlb_range(&vma, saddr, addr);
+}
+
+/*
+ * When dealing with NAPOT mappings, the privileged specification indicates that
+ * "if an update needs to be made, the OS generally should first mark all of the
+ * PTEs invalid, then issue SFENCE.VMA instruction(s) covering all 4 KiB regions
+ * within the range, [...] then update the PTE(s), as described in Section
+ * 4.2.1.". That's the equivalent of the Break-Before-Make approach used by
+ * arm64.
+ */
 void set_huge_pte_at(struct mm_struct *mm,
 		     unsigned long addr,
 		     pte_t *ptep,
 		     pte_t pte,
 		     unsigned long sz)
 {
-	unsigned long hugepage_shift;
+	unsigned long hugepage_shift, pgsize;
 	int i, pte_num;
 
 	if (sz >= PGDIR_SIZE)
@@ -198,7 +241,22 @@ void set_huge_pte_at(struct mm_struct *mm,
 		hugepage_shift = PAGE_SHIFT;
 
 	pte_num = sz >> hugepage_shift;
-	for (i = 0; i < pte_num; i++, ptep++, addr += (1 << hugepage_shift))
+	pgsize = 1 << hugepage_shift;
+
+	if (!pte_present(pte)) {
+		for (i = 0; i < pte_num; i++, ptep++, addr += pgsize)
+			set_ptes(mm, addr, ptep, pte, 1);
+		return;
+	}
+
+	if (!pte_napot(pte)) {
+		set_ptes(mm, addr, ptep, pte, 1);
+		return;
+	}
+
+	clear_flush(mm, addr, ptep, pgsize, pte_num);
+
+	for (i = 0; i < pte_num; i++, ptep++, addr += pgsize)
 		set_pte_at(mm, addr, ptep, pte);
 }
 
@@ -293,7 +351,7 @@ void huge_pte_clear(struct mm_struct *mm,
 		    pte_t *ptep,
 		    unsigned long sz)
 {
-	pte_t pte = READ_ONCE(*ptep);
+	pte_t pte = ptep_get(ptep);
 	int i, pte_num;
 
 	if (!pte_napot(pte)) {
@@ -306,7 +364,7 @@ void huge_pte_clear(struct mm_struct *mm,
 		pte_clear(mm, addr, ptep);
 }
 
-static __init bool is_napot_size(unsigned long size)
+static bool is_napot_size(unsigned long size)
 {
 	unsigned long order;
 
@@ -334,7 +392,7 @@ arch_initcall(napot_hugetlbpages_init);
 
 #else
 
-static __init bool is_napot_size(unsigned long size)
+static bool is_napot_size(unsigned long size)
 {
 	return false;
 }
@@ -351,7 +409,7 @@ int pmd_huge(pmd_t pmd)
 	return pmd_leaf(pmd);
 }
 
-bool __init arch_hugetlb_valid_size(unsigned long size)
+static bool __hugetlb_valid_size(unsigned long size)
 {
 	if (size == HPAGE_SIZE)
 		return true;
@@ -363,6 +421,18 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
 		return false;
 }
 
+bool __init arch_hugetlb_valid_size(unsigned long size)
+{
+	return __hugetlb_valid_size(size);
+}
+
+#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
+bool arch_hugetlb_migration_supported(struct hstate *h)
+{
+	return __hugetlb_valid_size(huge_page_size(h));
+}
+#endif
+
 #ifdef CONFIG_CONTIG_ALLOC
 static __init int gigantic_pages_init(void)
 {
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 2e011cbddf3a..fa34cf55037b 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -174,6 +174,9 @@ void __init mem_init(void)
 
 /* Limit the memory size via mem. */
 static phys_addr_t memory_limit;
+#ifdef CONFIG_XIP_KERNEL
+#define memory_limit	(*(phys_addr_t *)XIP_FIXUP(&memory_limit))
+#endif /* CONFIG_XIP_KERNEL */
 
 static int __init early_mem(char *p)
 {
@@ -952,7 +955,7 @@ static void __init create_fdt_early_page_table(uintptr_t fix_fdt_va,
 	 * setup_vm_final installs the linear mapping. For 32-bit kernel, as the
 	 * kernel is mapped in the linear mapping, that makes no difference.
 	 */
-	dtb_early_va = kernel_mapping_pa_to_va(XIP_FIXUP(dtb_pa));
+	dtb_early_va = kernel_mapping_pa_to_va(dtb_pa);
 #endif
 
 	dtb_early_pa = dtb_pa;
@@ -1055,9 +1058,13 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 #endif
 
 	kernel_map.virt_addr = KERNEL_LINK_ADDR + kernel_map.virt_offset;
-	kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL);
 
 #ifdef CONFIG_XIP_KERNEL
+#ifdef CONFIG_64BIT
+	kernel_map.page_offset = PAGE_OFFSET_L3;
+#else
+	kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL);
+#endif
 	kernel_map.xiprom = (uintptr_t)CONFIG_XIP_PHYS_ADDR;
 	kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom);
 
@@ -1067,6 +1074,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 
 	kernel_map.va_kernel_xip_pa_offset = kernel_map.virt_addr - kernel_map.xiprom;
 #else
+	kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL);
 	kernel_map.phys_addr = (uintptr_t)(&_start);
 	kernel_map.size = (uintptr_t)(&_end) - kernel_map.phys_addr;
 #endif
@@ -1377,16 +1385,39 @@ void __init misc_mem_init(void)
 	early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT);
 	arch_numa_init();
 	sparse_init();
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	/* The entire VMEMMAP region has been populated. Flush TLB for this region */
+	local_flush_tlb_kernel_range(VMEMMAP_START, VMEMMAP_END);
+#endif
 	zone_sizes_init();
 	arch_reserve_crashkernel();
 	memblock_dump_all();
 }
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
+void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node,
+			       unsigned long addr, unsigned long next)
+{
+	pmd_set_huge(pmd, virt_to_phys(p), PAGE_KERNEL);
+}
+
+int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node,
+				unsigned long addr, unsigned long next)
+{
+	vmemmap_verify((pte_t *)pmdp, node, addr, next);
+	return 1;
+}
+
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 			       struct vmem_altmap *altmap)
 {
-	return vmemmap_populate_basepages(start, end, node, NULL);
+	/*
+	 * Note that SPARSEMEM_VMEMMAP is only selected for rv64 and that we
+	 * can't use hugepage mappings for 2-level page table because in case of
+	 * memory hotplug, we are not able to update all the page tables with
+	 * the new PMDs.
+	 */
+	return vmemmap_populate_hugepages(start, end, node, NULL);
 }
 #endif
 
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index 5e39dcf23fdb..c301c8d291d2 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -31,7 +31,7 @@ static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned
 	phys_addr_t phys_addr;
 	pte_t *ptep, *p;
 
-	if (pmd_none(*pmd)) {
+	if (pmd_none(pmdp_get(pmd))) {
 		p = memblock_alloc(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE);
 		set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(p)), PAGE_TABLE));
 	}
@@ -39,7 +39,7 @@ static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned
 	ptep = pte_offset_kernel(pmd, vaddr);
 
 	do {
-		if (pte_none(*ptep)) {
+		if (pte_none(ptep_get(ptep))) {
 			phys_addr = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
 			set_pte(ptep, pfn_pte(PFN_DOWN(phys_addr), PAGE_KERNEL));
 			memset(__va(phys_addr), KASAN_SHADOW_INIT, PAGE_SIZE);
@@ -53,7 +53,7 @@ static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned
 	pmd_t *pmdp, *p;
 	unsigned long next;
 
-	if (pud_none(*pud)) {
+	if (pud_none(pudp_get(pud))) {
 		p = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE);
 		set_pud(pud, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE));
 	}
@@ -63,7 +63,8 @@ static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned
 	do {
 		next = pmd_addr_end(vaddr, end);
 
-		if (pmd_none(*pmdp) && IS_ALIGNED(vaddr, PMD_SIZE) && (next - vaddr) >= PMD_SIZE) {
+		if (pmd_none(pmdp_get(pmdp)) && IS_ALIGNED(vaddr, PMD_SIZE) &&
+		    (next - vaddr) >= PMD_SIZE) {
 			phys_addr = memblock_phys_alloc(PMD_SIZE, PMD_SIZE);
 			if (phys_addr) {
 				set_pmd(pmdp, pfn_pmd(PFN_DOWN(phys_addr), PAGE_KERNEL));
@@ -83,7 +84,7 @@ static void __init kasan_populate_pud(p4d_t *p4d,
 	pud_t *pudp, *p;
 	unsigned long next;
 
-	if (p4d_none(*p4d)) {
+	if (p4d_none(p4dp_get(p4d))) {
 		p = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE);
 		set_p4d(p4d, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE));
 	}
@@ -93,7 +94,8 @@ static void __init kasan_populate_pud(p4d_t *p4d,
 	do {
 		next = pud_addr_end(vaddr, end);
 
-		if (pud_none(*pudp) && IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE) {
+		if (pud_none(pudp_get(pudp)) && IS_ALIGNED(vaddr, PUD_SIZE) &&
+		    (next - vaddr) >= PUD_SIZE) {
 			phys_addr = memblock_phys_alloc(PUD_SIZE, PUD_SIZE);
 			if (phys_addr) {
 				set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_KERNEL));
@@ -113,7 +115,7 @@ static void __init kasan_populate_p4d(pgd_t *pgd,
 	p4d_t *p4dp, *p;
 	unsigned long next;
 
-	if (pgd_none(*pgd)) {
+	if (pgd_none(pgdp_get(pgd))) {
 		p = memblock_alloc(PTRS_PER_P4D * sizeof(p4d_t), PAGE_SIZE);
 		set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE));
 	}
@@ -123,7 +125,8 @@ static void __init kasan_populate_p4d(pgd_t *pgd,
 	do {
 		next = p4d_addr_end(vaddr, end);
 
-		if (p4d_none(*p4dp) && IS_ALIGNED(vaddr, P4D_SIZE) && (next - vaddr) >= P4D_SIZE) {
+		if (p4d_none(p4dp_get(p4dp)) && IS_ALIGNED(vaddr, P4D_SIZE) &&
+		    (next - vaddr) >= P4D_SIZE) {
 			phys_addr = memblock_phys_alloc(P4D_SIZE, P4D_SIZE);
 			if (phys_addr) {
 				set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_KERNEL));
@@ -145,7 +148,7 @@ static void __init kasan_populate_pgd(pgd_t *pgdp,
 	do {
 		next = pgd_addr_end(vaddr, end);
 
-		if (pgd_none(*pgdp) && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
+		if (pgd_none(pgdp_get(pgdp)) && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
 		    (next - vaddr) >= PGDIR_SIZE) {
 			phys_addr = memblock_phys_alloc(PGDIR_SIZE, PGDIR_SIZE);
 			if (phys_addr) {
@@ -168,7 +171,7 @@ static void __init kasan_early_clear_pud(p4d_t *p4dp,
 	if (!pgtable_l4_enabled) {
 		pudp = (pud_t *)p4dp;
 	} else {
-		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(*p4dp)));
+		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(p4dp_get(p4dp))));
 		pudp = base_pud + pud_index(vaddr);
 	}
 
@@ -193,7 +196,7 @@ static void __init kasan_early_clear_p4d(pgd_t *pgdp,
 	if (!pgtable_l5_enabled) {
 		p4dp = (p4d_t *)pgdp;
 	} else {
-		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgdp)));
+		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(pgdp_get(pgdp))));
 		p4dp = base_p4d + p4d_index(vaddr);
 	}
 
@@ -239,14 +242,14 @@ static void __init kasan_early_populate_pud(p4d_t *p4dp,
 	if (!pgtable_l4_enabled) {
 		pudp = (pud_t *)p4dp;
 	} else {
-		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(*p4dp)));
+		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(p4dp_get(p4dp))));
 		pudp = base_pud + pud_index(vaddr);
 	}
 
 	do {
 		next = pud_addr_end(vaddr, end);
 
-		if (pud_none(*pudp) && IS_ALIGNED(vaddr, PUD_SIZE) &&
+		if (pud_none(pudp_get(pudp)) && IS_ALIGNED(vaddr, PUD_SIZE) &&
 		    (next - vaddr) >= PUD_SIZE) {
 			phys_addr = __pa((uintptr_t)kasan_early_shadow_pmd);
 			set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_TABLE));
@@ -277,14 +280,14 @@ static void __init kasan_early_populate_p4d(pgd_t *pgdp,
 	if (!pgtable_l5_enabled) {
 		p4dp = (p4d_t *)pgdp;
 	} else {
-		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgdp)));
+		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(pgdp_get(pgdp))));
 		p4dp = base_p4d + p4d_index(vaddr);
 	}
 
 	do {
 		next = p4d_addr_end(vaddr, end);
 
-		if (p4d_none(*p4dp) && IS_ALIGNED(vaddr, P4D_SIZE) &&
+		if (p4d_none(p4dp_get(p4dp)) && IS_ALIGNED(vaddr, P4D_SIZE) &&
 		    (next - vaddr) >= P4D_SIZE) {
 			phys_addr = __pa((uintptr_t)kasan_early_shadow_pud);
 			set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_TABLE));
@@ -305,7 +308,7 @@ static void __init kasan_early_populate_pgd(pgd_t *pgdp,
 	do {
 		next = pgd_addr_end(vaddr, end);
 
-		if (pgd_none(*pgdp) && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
+		if (pgd_none(pgdp_get(pgdp)) && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
 		    (next - vaddr) >= PGDIR_SIZE) {
 			phys_addr = __pa((uintptr_t)kasan_early_shadow_p4d);
 			set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_TABLE));
@@ -381,7 +384,7 @@ static void __init kasan_shallow_populate_pud(p4d_t *p4d,
 	do {
 		next = pud_addr_end(vaddr, end);
 
-		if (pud_none(*pud_k)) {
+		if (pud_none(pudp_get(pud_k))) {
 			p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 			set_pud(pud_k, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE));
 			continue;
@@ -401,7 +404,7 @@ static void __init kasan_shallow_populate_p4d(pgd_t *pgd,
 	do {
 		next = p4d_addr_end(vaddr, end);
 
-		if (p4d_none(*p4d_k)) {
+		if (p4d_none(p4dp_get(p4d_k))) {
 			p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 			set_p4d(p4d_k, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE));
 			continue;
@@ -420,7 +423,7 @@ static void __init kasan_shallow_populate_pgd(unsigned long vaddr, unsigned long
 	do {
 		next = pgd_addr_end(vaddr, end);
 
-		if (pgd_none(*pgd_k)) {
+		if (pgd_none(pgdp_get(pgd_k))) {
 			p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 			set_pgd(pgd_k, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE));
 			continue;
@@ -438,6 +441,14 @@ static void __init kasan_shallow_populate(void *start, void *end)
 	kasan_shallow_populate_pgd(vaddr, vend);
 }
 
+#ifdef CONFIG_KASAN_VMALLOC
+void __init kasan_populate_early_vm_area_shadow(void *start, unsigned long size)
+{
+	kasan_populate(kasan_mem_to_shadow(start),
+		       kasan_mem_to_shadow(start + size));
+}
+#endif
+
 static void __init create_tmp_mapping(void)
 {
 	void *ptr;
@@ -451,7 +462,7 @@ static void __init create_tmp_mapping(void)
 
 	/* Copy the last p4d since it is shared with the kernel mapping. */
 	if (pgtable_l5_enabled) {
-		ptr = (p4d_t *)pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_END));
+		ptr = (p4d_t *)pgd_page_vaddr(pgdp_get(pgd_offset_k(KASAN_SHADOW_END)));
 		memcpy(tmp_p4d, ptr, sizeof(p4d_t) * PTRS_PER_P4D);
 		set_pgd(&tmp_pg_dir[pgd_index(KASAN_SHADOW_END)],
 			pfn_pgd(PFN_DOWN(__pa(tmp_p4d)), PAGE_TABLE));
@@ -462,7 +473,7 @@ static void __init create_tmp_mapping(void)
 
 	/* Copy the last pud since it is shared with the kernel mapping. */
 	if (pgtable_l4_enabled) {
-		ptr = (pud_t *)p4d_page_vaddr(*(base_p4d + p4d_index(KASAN_SHADOW_END)));
+		ptr = (pud_t *)p4d_page_vaddr(p4dp_get(base_p4d + p4d_index(KASAN_SHADOW_END)));
 		memcpy(tmp_pud, ptr, sizeof(pud_t) * PTRS_PER_PUD);
 		set_p4d(&base_p4d[p4d_index(KASAN_SHADOW_END)],
 			pfn_p4d(PFN_DOWN(__pa(tmp_pud)), PAGE_TABLE));
diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c
index fc5fc4f785c4..410056a50aa9 100644
--- a/arch/riscv/mm/pageattr.c
+++ b/arch/riscv/mm/pageattr.c
@@ -29,7 +29,7 @@ static unsigned long set_pageattr_masks(unsigned long val, struct mm_walk *walk)
 static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	p4d_t val = READ_ONCE(*p4d);
+	p4d_t val = p4dp_get(p4d);
 
 	if (p4d_leaf(val)) {
 		val = __p4d(set_pageattr_masks(p4d_val(val), walk));
@@ -42,7 +42,7 @@ static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr,
 static int pageattr_pud_entry(pud_t *pud, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	pud_t val = READ_ONCE(*pud);
+	pud_t val = pudp_get(pud);
 
 	if (pud_leaf(val)) {
 		val = __pud(set_pageattr_masks(pud_val(val), walk));
@@ -55,7 +55,7 @@ static int pageattr_pud_entry(pud_t *pud, unsigned long addr,
 static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	pmd_t val = READ_ONCE(*pmd);
+	pmd_t val = pmdp_get(pmd);
 
 	if (pmd_leaf(val)) {
 		val = __pmd(set_pageattr_masks(pmd_val(val), walk));
@@ -68,7 +68,7 @@ static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr,
 static int pageattr_pte_entry(pte_t *pte, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	pte_t val = READ_ONCE(*pte);
+	pte_t val = ptep_get(pte);
 
 	val = __pte(set_pageattr_masks(pte_val(val), walk));
 	set_pte(pte, val);
@@ -108,10 +108,10 @@ static int __split_linear_mapping_pmd(pud_t *pudp,
 		    vaddr <= (vaddr & PMD_MASK) && end >= next)
 			continue;
 
-		if (pmd_leaf(*pmdp)) {
+		if (pmd_leaf(pmdp_get(pmdp))) {
 			struct page *pte_page;
-			unsigned long pfn = _pmd_pfn(*pmdp);
-			pgprot_t prot = __pgprot(pmd_val(*pmdp) & ~_PAGE_PFN_MASK);
+			unsigned long pfn = _pmd_pfn(pmdp_get(pmdp));
+			pgprot_t prot = __pgprot(pmd_val(pmdp_get(pmdp)) & ~_PAGE_PFN_MASK);
 			pte_t *ptep_new;
 			int i;
 
@@ -148,10 +148,10 @@ static int __split_linear_mapping_pud(p4d_t *p4dp,
 		    vaddr <= (vaddr & PUD_MASK) && end >= next)
 			continue;
 
-		if (pud_leaf(*pudp)) {
+		if (pud_leaf(pudp_get(pudp))) {
 			struct page *pmd_page;
-			unsigned long pfn = _pud_pfn(*pudp);
-			pgprot_t prot = __pgprot(pud_val(*pudp) & ~_PAGE_PFN_MASK);
+			unsigned long pfn = _pud_pfn(pudp_get(pudp));
+			pgprot_t prot = __pgprot(pud_val(pudp_get(pudp)) & ~_PAGE_PFN_MASK);
 			pmd_t *pmdp_new;
 			int i;
 
@@ -197,10 +197,10 @@ static int __split_linear_mapping_p4d(pgd_t *pgdp,
 		    vaddr <= (vaddr & P4D_MASK) && end >= next)
 			continue;
 
-		if (p4d_leaf(*p4dp)) {
+		if (p4d_leaf(p4dp_get(p4dp))) {
 			struct page *pud_page;
-			unsigned long pfn = _p4d_pfn(*p4dp);
-			pgprot_t prot = __pgprot(p4d_val(*p4dp) & ~_PAGE_PFN_MASK);
+			unsigned long pfn = _p4d_pfn(p4dp_get(p4dp));
+			pgprot_t prot = __pgprot(p4d_val(p4dp_get(p4dp)) & ~_PAGE_PFN_MASK);
 			pud_t *pudp_new;
 			int i;
 
@@ -305,8 +305,13 @@ static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask,
 				goto unlock;
 		}
 	} else if (is_kernel_mapping(start) || is_linear_mapping(start)) {
-		lm_start = (unsigned long)lm_alias(start);
-		lm_end = (unsigned long)lm_alias(end);
+		if (is_kernel_mapping(start)) {
+			lm_start = (unsigned long)lm_alias(start);
+			lm_end = (unsigned long)lm_alias(end);
+		} else {
+			lm_start = start;
+			lm_end = end;
+		}
 
 		ret = split_linear_mapping(lm_start, lm_end);
 		if (ret)
@@ -378,7 +383,7 @@ int set_direct_map_invalid_noflush(struct page *page)
 int set_direct_map_default_noflush(struct page *page)
 {
 	return __set_memory((unsigned long)page_address(page), 1,
-			    PAGE_KERNEL, __pgprot(0));
+			    PAGE_KERNEL, __pgprot(_PAGE_EXEC));
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
@@ -406,29 +411,29 @@ bool kernel_page_present(struct page *page)
 	pte_t *pte;
 
 	pgd = pgd_offset_k(addr);
-	if (!pgd_present(*pgd))
+	if (!pgd_present(pgdp_get(pgd)))
 		return false;
-	if (pgd_leaf(*pgd))
+	if (pgd_leaf(pgdp_get(pgd)))
 		return true;
 
 	p4d = p4d_offset(pgd, addr);
-	if (!p4d_present(*p4d))
+	if (!p4d_present(p4dp_get(p4d)))
 		return false;
-	if (p4d_leaf(*p4d))
+	if (p4d_leaf(p4dp_get(p4d)))
 		return true;
 
 	pud = pud_offset(p4d, addr);
-	if (!pud_present(*pud))
+	if (!pud_present(pudp_get(pud)))
 		return false;
-	if (pud_leaf(*pud))
+	if (pud_leaf(pudp_get(pud)))
 		return true;
 
 	pmd = pmd_offset(pud, addr);
-	if (!pmd_present(*pmd))
+	if (!pmd_present(pmdp_get(pmd)))
 		return false;
-	if (pmd_leaf(*pmd))
+	if (pmd_leaf(pmdp_get(pmd)))
 		return true;
 
 	pte = pte_offset_kernel(pmd, addr);
-	return pte_present(*pte);
+	return pte_present(ptep_get(pte));
 }
diff --git a/arch/riscv/mm/pgtable.c b/arch/riscv/mm/pgtable.c
index fef4e7328e49..ef887efcb679 100644
--- a/arch/riscv/mm/pgtable.c
+++ b/arch/riscv/mm/pgtable.c
@@ -5,6 +5,47 @@
 #include <linux/kernel.h>
 #include <linux/pgtable.h>
 
+int ptep_set_access_flags(struct vm_area_struct *vma,
+			  unsigned long address, pte_t *ptep,
+			  pte_t entry, int dirty)
+{
+	if (!pte_same(ptep_get(ptep), entry))
+		__set_pte_at(ptep, entry);
+	/*
+	 * update_mmu_cache will unconditionally execute, handling both
+	 * the case that the PTE changed and the spurious fault case.
+	 */
+	return true;
+}
+
+int ptep_test_and_clear_young(struct vm_area_struct *vma,
+			      unsigned long address,
+			      pte_t *ptep)
+{
+	if (!pte_young(ptep_get(ptep)))
+		return 0;
+	return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep));
+}
+EXPORT_SYMBOL_GPL(ptep_test_and_clear_young);
+
+#ifdef CONFIG_64BIT
+pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+{
+	if (pgtable_l4_enabled)
+		return p4d_pgtable(p4dp_get(p4d)) + pud_index(address);
+
+	return (pud_t *)p4d;
+}
+
+p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+{
+	if (pgtable_l5_enabled)
+		return pgd_pgtable(pgdp_get(pgd)) + p4d_index(address);
+
+	return (p4d_t *)pgd;
+}
+#endif
+
 #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
 int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
 {
@@ -25,7 +66,7 @@ int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot)
 
 int pud_clear_huge(pud_t *pud)
 {
-	if (!pud_leaf(READ_ONCE(*pud)))
+	if (!pud_leaf(pudp_get(pud)))
 		return 0;
 	pud_clear(pud);
 	return 1;
@@ -33,7 +74,7 @@ int pud_clear_huge(pud_t *pud)
 
 int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 {
-	pmd_t *pmd = pud_pgtable(*pud);
+	pmd_t *pmd = pud_pgtable(pudp_get(pud));
 	int i;
 
 	pud_clear(pud);
@@ -63,7 +104,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot)
 
 int pmd_clear_huge(pmd_t *pmd)
 {
-	if (!pmd_leaf(READ_ONCE(*pmd)))
+	if (!pmd_leaf(pmdp_get(pmd)))
 		return 0;
 	pmd_clear(pmd);
 	return 1;
@@ -71,7 +112,7 @@ int pmd_clear_huge(pmd_t *pmd)
 
 int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 {
-	pte_t *pte = (pte_t *)pmd_page_vaddr(*pmd);
+	pte_t *pte = (pte_t *)pmd_page_vaddr(pmdp_get(pmd));
 
 	pmd_clear(pmd);
 
@@ -88,7 +129,7 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
 	pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
-	VM_BUG_ON(pmd_trans_huge(*pmdp));
+	VM_BUG_ON(pmd_trans_huge(pmdp_get(pmdp)));
 	/*
 	 * When leaf PTE entries (regular pages) are collapsed into a leaf
 	 * PMD entry (huge page), a valid non-leaf PTE is converted into a
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index e6659d7368b3..893566e004b7 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -66,6 +66,12 @@ static inline void local_flush_tlb_range_asid(unsigned long start,
 		local_flush_tlb_range_threshold_asid(start, size, stride, asid);
 }
 
+/* Flush a range of kernel pages without broadcasting */
+void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	local_flush_tlb_range_asid(start, end - start, PAGE_SIZE, FLUSH_TLB_NO_ASID);
+}
+
 static void __ipi_flush_tlb_all(void *info)
 {
 	local_flush_tlb_all();
@@ -93,29 +99,23 @@ static void __ipi_flush_tlb_range_asid(void *info)
 	local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid);
 }
 
-static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
-			      unsigned long size, unsigned long stride)
+static void __flush_tlb_range(struct cpumask *cmask, unsigned long asid,
+			      unsigned long start, unsigned long size,
+			      unsigned long stride)
 {
 	struct flush_tlb_range_data ftd;
-	const struct cpumask *cmask;
-	unsigned long asid = FLUSH_TLB_NO_ASID;
 	bool broadcast;
 
-	if (mm) {
-		unsigned int cpuid;
+	if (cpumask_empty(cmask))
+		return;
 
-		cmask = mm_cpumask(mm);
-		if (cpumask_empty(cmask))
-			return;
+	if (cmask != cpu_online_mask) {
+		unsigned int cpuid;
 
 		cpuid = get_cpu();
 		/* check if the tlbflush needs to be sent to other CPUs */
 		broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids;
-
-		if (static_branch_unlikely(&use_asid_allocator))
-			asid = atomic_long_read(&mm->context.id) & asid_mask;
 	} else {
-		cmask = cpu_online_mask;
 		broadcast = true;
 	}
 
@@ -135,25 +135,34 @@ static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
 		local_flush_tlb_range_asid(start, size, stride, asid);
 	}
 
-	if (mm)
+	if (cmask != cpu_online_mask)
 		put_cpu();
 }
 
+static inline unsigned long get_mm_asid(struct mm_struct *mm)
+{
+	return static_branch_unlikely(&use_asid_allocator) ?
+			atomic_long_read(&mm->context.id) & asid_mask : FLUSH_TLB_NO_ASID;
+}
+
 void flush_tlb_mm(struct mm_struct *mm)
 {
-	__flush_tlb_range(mm, 0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
+	__flush_tlb_range(mm_cpumask(mm), get_mm_asid(mm),
+			  0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
 }
 
 void flush_tlb_mm_range(struct mm_struct *mm,
 			unsigned long start, unsigned long end,
 			unsigned int page_size)
 {
-	__flush_tlb_range(mm, start, end - start, page_size);
+	__flush_tlb_range(mm_cpumask(mm), get_mm_asid(mm),
+			  start, end - start, page_size);
 }
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 {
-	__flush_tlb_range(vma->vm_mm, addr, PAGE_SIZE, PAGE_SIZE);
+	__flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
+			  addr, PAGE_SIZE, PAGE_SIZE);
 }
 
 void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
@@ -185,18 +194,45 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		}
 	}
 
-	__flush_tlb_range(vma->vm_mm, start, end - start, stride_size);
+	__flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
+			  start, end - start, stride_size);
 }
 
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
-	__flush_tlb_range(NULL, start, end - start, PAGE_SIZE);
+	__flush_tlb_range((struct cpumask *)cpu_online_mask, FLUSH_TLB_NO_ASID,
+			  start, end - start, PAGE_SIZE);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			unsigned long end)
 {
-	__flush_tlb_range(vma->vm_mm, start, end - start, PMD_SIZE);
+	__flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
+			  start, end - start, PMD_SIZE);
 }
 #endif
+
+bool arch_tlbbatch_should_defer(struct mm_struct *mm)
+{
+	return true;
+}
+
+void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
+			       struct mm_struct *mm,
+			       unsigned long uaddr)
+{
+	cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
+}
+
+void arch_flush_tlb_batched_pending(struct mm_struct *mm)
+{
+	flush_tlb_mm(mm);
+}
+
+void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
+{
+	__flush_tlb_range(&batch->cpumask, FLUSH_TLB_NO_ASID, 0,
+			  FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
+	cpumask_clear(&batch->cpumask);
+}
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 58dc64dd94a8..719a97e7edb2 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -795,6 +795,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 	struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
 	struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
 	struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
+	bool is_struct_ops = flags & BPF_TRAMP_F_INDIRECT;
 	void *orig_call = func_addr;
 	bool save_ret;
 	u32 insn;
@@ -878,7 +879,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 
 	stack_size = round_up(stack_size, 16);
 
-	if (func_addr) {
+	if (!is_struct_ops) {
 		/* For the trampoline called from function entry,
 		 * the frame of traced function and the frame of
 		 * trampoline need to be considered.
@@ -998,7 +999,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 
 	emit_ld(RV_REG_S1, -sreg_off, RV_REG_FP, ctx);
 
-	if (func_addr) {
+	if (!is_struct_ops) {
 		/* trampoline called from function entry */
 		emit_ld(RV_REG_T0, stack_size - 8, RV_REG_SP, ctx);
 		emit_ld(RV_REG_FP, stack_size - 16, RV_REG_SP, ctx);
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 8f39f0424796..fe565f3a3a91 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -216,7 +216,6 @@ config S390
 	select HAVE_VIRT_CPU_ACCOUNTING_IDLE
 	select IOMMU_HELPER		if PCI
 	select IOMMU_SUPPORT		if PCI
-	select KEXEC
 	select MMU_GATHER_MERGE_VMAS
 	select MMU_GATHER_NO_GATHER
 	select MMU_GATHER_RCU_TABLE_FREE
@@ -443,7 +442,7 @@ config COMMAND_LINE_SIZE
 	  line.
 
 config COMPAT
-	def_bool y
+	def_bool n
 	prompt "Kernel support for 31 bit emulation"
 	select ARCH_WANT_OLD_COMPAT_IPC
 	select COMPAT_OLD_SIGACTION
@@ -454,7 +453,9 @@ config COMPAT
 	  Select this option if you want to enable your system kernel to
 	  handle system-calls from ELF binaries for 31 bit ESA.  This option
 	  (and some other stuff like libraries and such) is needed for
-	  executing 31 bit applications.  It is safe to say "Y".
+	  executing 31 bit applications.
+
+	  If unsure say N.
 
 config SMP
 	def_bool y
diff --git a/arch/s390/configs/compat.config b/arch/s390/configs/compat.config
new file mode 100644
index 000000000000..6fd051453ae8
--- /dev/null
+++ b/arch/s390/configs/compat.config
@@ -0,0 +1,3 @@
+# Help: Enable compat support
+CONFIG_COMPAT=y
+CONFIG_COMPAT_32BIT_TIME=y
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 85490d9373fc..06756bad5e30 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -40,6 +40,7 @@ CONFIG_SCHED_AUTOGROUP=y
 CONFIG_EXPERT=y
 # CONFIG_SYSFS_SYSCALL is not set
 CONFIG_PROFILING=y
+CONFIG_KEXEC=y
 CONFIG_KEXEC_FILE=y
 CONFIG_KEXEC_SIG=y
 CONFIG_CRASH_DUMP=y
@@ -117,7 +118,6 @@ CONFIG_UNIX=y
 CONFIG_UNIX_DIAG=m
 CONFIG_XFRM_USER=m
 CONFIG_NET_KEY=m
-CONFIG_SMC=m
 CONFIG_SMC_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
@@ -373,6 +373,7 @@ CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
+CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
@@ -435,9 +436,6 @@ CONFIG_SCSI_DH_ALUA=m
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=y
 # CONFIG_MD_BITMAP_FILE is not set
-CONFIG_MD_LINEAR=m
-CONFIG_MD_MULTIPATH=m
-CONFIG_MD_FAULTY=m
 CONFIG_MD_CLUSTER=m
 CONFIG_BCACHE=m
 CONFIG_BLK_DEV_DM=y
@@ -637,7 +635,7 @@ CONFIG_CUSE=m
 CONFIG_VIRTIO_FS=m
 CONFIG_OVERLAY_FS=m
 CONFIG_NETFS_STATS=y
-CONFIG_FSCACHE=m
+CONFIG_FSCACHE=y
 CONFIG_CACHEFILES=m
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
@@ -707,7 +705,6 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y
 CONFIG_IMA_WRITE_POLICY=y
 CONFIG_IMA_APPRAISE=y
 CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
-CONFIG_INIT_STACK_NONE=y
 CONFIG_BUG_ON_DATA_CORRUPTION=y
 CONFIG_CRYPTO_USER=m
 # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
@@ -737,7 +734,6 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_ARC4=m
-CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_LRW=m
@@ -884,4 +880,3 @@ CONFIG_ATOMIC64_SELFTEST=y
 CONFIG_STRING_SELFTEST=y
 CONFIG_TEST_BITOPS=m
 CONFIG_TEST_BPF=m
-CONFIG_TEST_LIVEPATCH=m
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index fb690fbbf54b..d33f814f78b2 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -38,6 +38,7 @@ CONFIG_SCHED_AUTOGROUP=y
 CONFIG_EXPERT=y
 # CONFIG_SYSFS_SYSCALL is not set
 CONFIG_PROFILING=y
+CONFIG_KEXEC=y
 CONFIG_KEXEC_FILE=y
 CONFIG_KEXEC_SIG=y
 CONFIG_CRASH_DUMP=y
@@ -108,7 +109,6 @@ CONFIG_UNIX=y
 CONFIG_UNIX_DIAG=m
 CONFIG_XFRM_USER=m
 CONFIG_NET_KEY=m
-CONFIG_SMC=m
 CONFIG_SMC_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
@@ -363,6 +363,7 @@ CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
+CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
@@ -425,9 +426,6 @@ CONFIG_SCSI_DH_ALUA=m
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=y
 # CONFIG_MD_BITMAP_FILE is not set
-CONFIG_MD_LINEAR=m
-CONFIG_MD_MULTIPATH=m
-CONFIG_MD_FAULTY=m
 CONFIG_MD_CLUSTER=m
 CONFIG_BCACHE=m
 CONFIG_BLK_DEV_DM=y
@@ -622,7 +620,7 @@ CONFIG_CUSE=m
 CONFIG_VIRTIO_FS=m
 CONFIG_OVERLAY_FS=m
 CONFIG_NETFS_STATS=y
-CONFIG_FSCACHE=m
+CONFIG_FSCACHE=y
 CONFIG_CACHEFILES=m
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
@@ -691,7 +689,6 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y
 CONFIG_IMA_WRITE_POLICY=y
 CONFIG_IMA_APPRAISE=y
 CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
-CONFIG_INIT_STACK_NONE=y
 CONFIG_BUG_ON_DATA_CORRUPTION=y
 CONFIG_CRYPTO_FIPS=y
 CONFIG_CRYPTO_USER=m
@@ -722,11 +719,9 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_ARC4=m
-CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_AEGIS128=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
@@ -813,4 +808,3 @@ CONFIG_KPROBES_SANITY_TEST=m
 CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
 CONFIG_TEST_BPF=m
-CONFIG_TEST_LIVEPATCH=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 47028450eee1..c51f3ec4eb28 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -8,9 +8,9 @@ CONFIG_BPF_SYSCALL=y
 # CONFIG_NET_NS is not set
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_KEXEC=y
 CONFIG_CRASH_DUMP=y
 CONFIG_MARCH_Z13=y
-# CONFIG_COMPAT is not set
 CONFIG_NR_CPUS=2
 CONFIG_HZ_100=y
 # CONFIG_CHSC_SCH is not set
@@ -65,7 +65,6 @@ CONFIG_ZFCP=y
 # CONFIG_MISC_FILESYSTEMS is not set
 # CONFIG_NETWORK_FILESYSTEMS is not set
 CONFIG_LSM="yama,loadpin,safesetid,integrity"
-CONFIG_INIT_STACK_NONE=y
 # CONFIG_ZLIB_DFLTCC is not set
 CONFIG_XZ_DEC_MICROLZMA=y
 CONFIG_PRINTK_TIME=y
diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h
index 94b6919026df..796007125dff 100644
--- a/arch/s390/include/asm/facility.h
+++ b/arch/s390/include/asm/facility.h
@@ -111,4 +111,10 @@ static inline void stfle(u64 *stfle_fac_list, int size)
 	preempt_enable();
 }
 
+/**
+ * stfle_size - Actual size of the facility list as specified by stfle
+ * (number of double words)
+ */
+unsigned int stfle_size(void);
+
 #endif /* __ASM_FACILITY_H */
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index 895f774bbcc5..bf78cf381dfc 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -25,7 +25,7 @@
  */
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("0:	brcl 0,%l[label]\n"
+	asm goto("0:	brcl 0,%l[label]\n"
 			  ".pushsection __jump_table,\"aw\"\n"
 			  ".balign	8\n"
 			  ".long	0b-.,%l[label]-.\n"
@@ -39,7 +39,7 @@ label:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("0:	brcl 15,%l[label]\n"
+	asm goto("0:	brcl 15,%l[label]\n"
 			  ".pushsection __jump_table,\"aw\"\n"
 			  ".balign	8\n"
 			  ".long	0b-.,%l[label]-.\n"
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 67a298b6cf6e..52664105a473 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -818,7 +818,7 @@ struct s390_io_adapter {
 
 struct kvm_s390_cpu_model {
 	/* facility mask supported by kvm & hosting machine */
-	__u64 fac_mask[S390_ARCH_FAC_LIST_SIZE_U64];
+	__u64 fac_mask[S390_ARCH_FAC_MASK_SIZE_U64];
 	struct kvm_s390_vm_cpu_subfunc subfuncs;
 	/* facility list requested by guest (in dma page) */
 	__u64 *fac_list;
diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
index 287bb88f7698..2686bee800e3 100644
--- a/arch/s390/include/asm/pci_io.h
+++ b/arch/s390/include/asm/pci_io.h
@@ -11,6 +11,8 @@
 /* I/O size constraints */
 #define ZPCI_MAX_READ_SIZE	8
 #define ZPCI_MAX_WRITE_SIZE	128
+#define ZPCI_BOUNDARY_SIZE	(1 << 12)
+#define ZPCI_BOUNDARY_MASK	(ZPCI_BOUNDARY_SIZE - 1)
 
 /* I/O Map */
 #define ZPCI_IOMAP_SHIFT		48
@@ -125,16 +127,18 @@ out:
 int zpci_write_block(volatile void __iomem *dst, const void *src,
 		     unsigned long len);
 
-static inline u8 zpci_get_max_write_size(u64 src, u64 dst, int len, int max)
+static inline int zpci_get_max_io_size(u64 src, u64 dst, int len, int max)
 {
-	int count = len > max ? max : len, size = 1;
+	int offset = dst & ZPCI_BOUNDARY_MASK;
+	int size;
 
-	while (!(src & 0x1) && !(dst & 0x1) && ((size << 1) <= count)) {
-		dst = dst >> 1;
-		src = src >> 1;
-		size = size << 1;
-	}
-	return size;
+	size = min3(len, ZPCI_BOUNDARY_SIZE - offset, max);
+	if (IS_ALIGNED(src, 8) && IS_ALIGNED(dst, 8) && IS_ALIGNED(size, 8))
+		return size;
+
+	if (size >= 8)
+		return 8;
+	return rounddown_pow_of_two(size);
 }
 
 static inline int zpci_memcpy_fromio(void *dst,
@@ -144,9 +148,9 @@ static inline int zpci_memcpy_fromio(void *dst,
 	int size, rc = 0;
 
 	while (n > 0) {
-		size = zpci_get_max_write_size((u64 __force) src,
-					       (u64) dst, n,
-					       ZPCI_MAX_READ_SIZE);
+		size = zpci_get_max_io_size((u64 __force) src,
+					    (u64) dst, n,
+					    ZPCI_MAX_READ_SIZE);
 		rc = zpci_read_single(dst, src, size);
 		if (rc)
 			break;
@@ -166,9 +170,9 @@ static inline int zpci_memcpy_toio(volatile void __iomem *dst,
 		return -EINVAL;
 
 	while (n > 0) {
-		size = zpci_get_max_write_size((u64 __force) dst,
-					       (u64) src, n,
-					       ZPCI_MAX_WRITE_SIZE);
+		size = zpci_get_max_io_size((u64 __force) dst,
+					    (u64) src, n,
+					    ZPCI_MAX_WRITE_SIZE);
 		if (size > 8) /* main path */
 			rc = zpci_write_block(dst, src, size);
 		else
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 353def93973b..7a562b4199c8 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -41,7 +41,7 @@ obj-y	+= sysinfo.o lgr.o os_info.o ctlreg.o
 obj-y	+= runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o
 obj-y	+= entry.o reipl.o kdebugfs.o alternative.o
 obj-y	+= nospec-branch.o ipl_vmparm.o machine_kexec_reloc.o unwind_bc.o
-obj-y	+= smp.o text_amode31.o stacktrace.o abs_lowcore.o
+obj-y	+= smp.o text_amode31.o stacktrace.o abs_lowcore.o facility.o
 
 extra-y				+= vmlinux.lds
 
diff --git a/arch/s390/kernel/facility.c b/arch/s390/kernel/facility.c
new file mode 100644
index 000000000000..f02127219a27
--- /dev/null
+++ b/arch/s390/kernel/facility.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corp. 2023
+ */
+
+#include <asm/facility.h>
+
+unsigned int stfle_size(void)
+{
+	static unsigned int size;
+	unsigned int r;
+	u64 dummy;
+
+	r = READ_ONCE(size);
+	if (!r) {
+		r = __stfle_asm(&dummy, 1) + 1;
+		WRITE_ONCE(size, r);
+	}
+	return r;
+}
+EXPORT_SYMBOL(stfle_size);
diff --git a/arch/s390/kernel/fpu.c b/arch/s390/kernel/fpu.c
index 9e7c15fccfea..a4f3449cc814 100644
--- a/arch/s390/kernel/fpu.c
+++ b/arch/s390/kernel/fpu.c
@@ -208,7 +208,6 @@ void __load_fpu_regs(void)
 	}
 	clear_cpu_flag(CIF_FPU);
 }
-EXPORT_SYMBOL(__load_fpu_regs);
 
 void load_fpu_regs(void)
 {
diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c
index 39a91b00438a..bf8a672b15a4 100644
--- a/arch/s390/kernel/perf_pai_crypto.c
+++ b/arch/s390/kernel/perf_pai_crypto.c
@@ -111,11 +111,11 @@ static void paicrypt_event_destroy(struct perf_event *event)
 	mutex_unlock(&pai_reserve_mutex);
 }
 
-static u64 paicrypt_getctr(struct paicrypt_map *cpump, int nr, bool kernel)
+static u64 paicrypt_getctr(unsigned long *page, int nr, bool kernel)
 {
 	if (kernel)
 		nr += PAI_CRYPTO_MAXCTR;
-	return cpump->page[nr];
+	return page[nr];
 }
 
 /* Read the counter values. Return value from location in CMP. For event
@@ -129,13 +129,13 @@ static u64 paicrypt_getdata(struct perf_event *event, bool kernel)
 	int i;
 
 	if (event->attr.config != PAI_CRYPTO_BASE) {
-		return paicrypt_getctr(cpump,
+		return paicrypt_getctr(cpump->page,
 				       event->attr.config - PAI_CRYPTO_BASE,
 				       kernel);
 	}
 
 	for (i = 1; i <= paicrypt_cnt; i++) {
-		u64 val = paicrypt_getctr(cpump, i, kernel);
+		u64 val = paicrypt_getctr(cpump->page, i, kernel);
 
 		if (!val)
 			continue;
@@ -317,10 +317,14 @@ static void paicrypt_start(struct perf_event *event, int flags)
 	 * Events are added, deleted and re-added when 2 or more events
 	 * are active at the same time.
 	 */
-	if (!event->hw.last_tag) {
-		event->hw.last_tag = 1;
-		sum = paicrypt_getall(event);		/* Get current value */
-		local64_set(&event->hw.prev_count, sum);
+	if (!event->attr.sample_period) {	/* Counting */
+		if (!event->hw.last_tag) {
+			event->hw.last_tag = 1;
+			sum = paicrypt_getall(event);	/* Get current value */
+			local64_set(&event->hw.prev_count, sum);
+		}
+	} else {				/* Sampling */
+		perf_sched_cb_inc(event->pmu);
 	}
 }
 
@@ -336,19 +340,18 @@ static int paicrypt_add(struct perf_event *event, int flags)
 		local_ctl_set_bit(0, CR0_CRYPTOGRAPHY_COUNTER_BIT);
 	}
 	cpump->event = event;
-	if (flags & PERF_EF_START && !event->attr.sample_period) {
-		/* Only counting needs initial counter value */
+	if (flags & PERF_EF_START)
 		paicrypt_start(event, PERF_EF_RELOAD);
-	}
 	event->hw.state = 0;
-	if (event->attr.sample_period)
-		perf_sched_cb_inc(event->pmu);
 	return 0;
 }
 
 static void paicrypt_stop(struct perf_event *event, int flags)
 {
-	paicrypt_read(event);
+	if (!event->attr.sample_period)	/* Counting */
+		paicrypt_read(event);
+	else				/* Sampling */
+		perf_sched_cb_dec(event->pmu);
 	event->hw.state = PERF_HES_STOPPED;
 }
 
@@ -357,11 +360,7 @@ static void paicrypt_del(struct perf_event *event, int flags)
 	struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr);
 	struct paicrypt_map *cpump = mp->mapptr;
 
-	if (event->attr.sample_period)
-		perf_sched_cb_dec(event->pmu);
-	if (!event->attr.sample_period)
-		/* Only counting needs to read counter */
-		paicrypt_stop(event, PERF_EF_UPDATE);
+	paicrypt_stop(event, PERF_EF_UPDATE);
 	if (--cpump->active_events == 0) {
 		local_ctl_clear_bit(0, CR0_CRYPTOGRAPHY_COUNTER_BIT);
 		WRITE_ONCE(S390_lowcore.ccd, 0);
@@ -373,8 +372,7 @@ static void paicrypt_del(struct perf_event *event, int flags)
  * 2 bytes: Number of counter
  * 8 bytes: Value of counter
  */
-static size_t paicrypt_copy(struct pai_userdata *userdata,
-			    struct paicrypt_map *cpump,
+static size_t paicrypt_copy(struct pai_userdata *userdata, unsigned long *page,
 			    bool exclude_user, bool exclude_kernel)
 {
 	int i, outidx = 0;
@@ -383,9 +381,9 @@ static size_t paicrypt_copy(struct pai_userdata *userdata,
 		u64 val = 0;
 
 		if (!exclude_kernel)
-			val += paicrypt_getctr(cpump, i, true);
+			val += paicrypt_getctr(page, i, true);
 		if (!exclude_user)
-			val += paicrypt_getctr(cpump, i, false);
+			val += paicrypt_getctr(page, i, false);
 		if (val) {
 			userdata[outidx].num = i;
 			userdata[outidx].value = val;
@@ -395,25 +393,14 @@ static size_t paicrypt_copy(struct pai_userdata *userdata,
 	return outidx * sizeof(struct pai_userdata);
 }
 
-static int paicrypt_push_sample(void)
+static int paicrypt_push_sample(size_t rawsize, struct paicrypt_map *cpump,
+				struct perf_event *event)
 {
-	struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr);
-	struct paicrypt_map *cpump = mp->mapptr;
-	struct perf_event *event = cpump->event;
 	struct perf_sample_data data;
 	struct perf_raw_record raw;
 	struct pt_regs regs;
-	size_t rawsize;
 	int overflow;
 
-	if (!cpump->event)		/* No event active */
-		return 0;
-	rawsize = paicrypt_copy(cpump->save, cpump,
-				cpump->event->attr.exclude_user,
-				cpump->event->attr.exclude_kernel);
-	if (!rawsize)			/* No incremented counters */
-		return 0;
-
 	/* Setup perf sample */
 	memset(&regs, 0, sizeof(regs));
 	memset(&raw, 0, sizeof(raw));
@@ -444,6 +431,25 @@ static int paicrypt_push_sample(void)
 	return overflow;
 }
 
+/* Check if there is data to be saved on schedule out of a task. */
+static int paicrypt_have_sample(void)
+{
+	struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr);
+	struct paicrypt_map *cpump = mp->mapptr;
+	struct perf_event *event = cpump->event;
+	size_t rawsize;
+	int rc = 0;
+
+	if (!event)		/* No event active */
+		return 0;
+	rawsize = paicrypt_copy(cpump->save, cpump->page,
+				cpump->event->attr.exclude_user,
+				cpump->event->attr.exclude_kernel);
+	if (rawsize)			/* No incremented counters */
+		rc = paicrypt_push_sample(rawsize, cpump, event);
+	return rc;
+}
+
 /* Called on schedule-in and schedule-out. No access to event structure,
  * but for sampling only event CRYPTO_ALL is allowed.
  */
@@ -453,7 +459,7 @@ static void paicrypt_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sch
 	 * results on schedule_out and if page was dirty, clear values.
 	 */
 	if (!sched_in)
-		paicrypt_push_sample();
+		paicrypt_have_sample();
 }
 
 /* Attribute definitions for paicrypt interface. As with other CPU
diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c
index e7013a2e8960..af7f2b538c8f 100644
--- a/arch/s390/kernel/perf_pai_ext.c
+++ b/arch/s390/kernel/perf_pai_ext.c
@@ -276,9 +276,9 @@ static int paiext_event_init(struct perf_event *event)
 	return 0;
 }
 
-static u64 paiext_getctr(struct paiext_map *cpump, int nr)
+static u64 paiext_getctr(unsigned long *area, int nr)
 {
-	return cpump->area[nr];
+	return area[nr];
 }
 
 /* Read the counter values. Return value from location in buffer. For event
@@ -292,10 +292,11 @@ static u64 paiext_getdata(struct perf_event *event)
 	int i;
 
 	if (event->attr.config != PAI_NNPA_BASE)
-		return paiext_getctr(cpump, event->attr.config - PAI_NNPA_BASE);
+		return paiext_getctr(cpump->area,
+				     event->attr.config - PAI_NNPA_BASE);
 
 	for (i = 1; i <= paiext_cnt; i++)
-		sum += paiext_getctr(cpump, i);
+		sum += paiext_getctr(cpump->area, i);
 
 	return sum;
 }
@@ -320,11 +321,15 @@ static void paiext_start(struct perf_event *event, int flags)
 {
 	u64 sum;
 
-	if (event->hw.last_tag)
-		return;
-	event->hw.last_tag = 1;
-	sum = paiext_getall(event);		/* Get current value */
-	local64_set(&event->hw.prev_count, sum);
+	if (!event->attr.sample_period) {	/* Counting */
+		if (!event->hw.last_tag) {
+			event->hw.last_tag = 1;
+			sum = paiext_getall(event);	/* Get current value */
+			local64_set(&event->hw.prev_count, sum);
+		}
+	} else {				/* Sampling */
+		perf_sched_cb_inc(event->pmu);
+	}
 }
 
 static int paiext_add(struct perf_event *event, int flags)
@@ -341,21 +346,19 @@ static int paiext_add(struct perf_event *event, int flags)
 		debug_sprintf_event(paiext_dbg, 4, "%s 1508 %llx acc %llx\n",
 				    __func__, S390_lowcore.aicd, pcb->acc);
 	}
-	if (flags & PERF_EF_START && !event->attr.sample_period) {
-		/* Only counting needs initial counter value */
+	cpump->event = event;
+	if (flags & PERF_EF_START)
 		paiext_start(event, PERF_EF_RELOAD);
-	}
 	event->hw.state = 0;
-	if (event->attr.sample_period) {
-		cpump->event = event;
-		perf_sched_cb_inc(event->pmu);
-	}
 	return 0;
 }
 
 static void paiext_stop(struct perf_event *event, int flags)
 {
-	paiext_read(event);
+	if (!event->attr.sample_period)	/* Counting */
+		paiext_read(event);
+	else				/* Sampling */
+		perf_sched_cb_dec(event->pmu);
 	event->hw.state = PERF_HES_STOPPED;
 }
 
@@ -365,12 +368,7 @@ static void paiext_del(struct perf_event *event, int flags)
 	struct paiext_map *cpump = mp->mapptr;
 	struct paiext_cb *pcb = cpump->paiext_cb;
 
-	if (event->attr.sample_period)
-		perf_sched_cb_dec(event->pmu);
-	if (!event->attr.sample_period) {
-		/* Only counting needs to read counter */
-		paiext_stop(event, PERF_EF_UPDATE);
-	}
+	paiext_stop(event, PERF_EF_UPDATE);
 	if (--cpump->active_events == 0) {
 		/* Disable CPU instruction lookup for PAIE1 control block */
 		local_ctl_clear_bit(0, CR0_PAI_EXTENSION_BIT);
@@ -386,13 +384,12 @@ static void paiext_del(struct perf_event *event, int flags)
  * 2 bytes: Number of counter
  * 8 bytes: Value of counter
  */
-static size_t paiext_copy(struct paiext_map *cpump)
+static size_t paiext_copy(struct pai_userdata *userdata, unsigned long *area)
 {
-	struct pai_userdata *userdata = cpump->save;
 	int i, outidx = 0;
 
 	for (i = 1; i <= paiext_cnt; i++) {
-		u64 val = paiext_getctr(cpump, i);
+		u64 val = paiext_getctr(area, i);
 
 		if (val) {
 			userdata[outidx].num = i;
@@ -418,21 +415,14 @@ static size_t paiext_copy(struct paiext_map *cpump)
  * sched_task() callback. That callback is not active after paiext_del()
  * returns and has deleted the event on that CPU.
  */
-static int paiext_push_sample(void)
+static int paiext_push_sample(size_t rawsize, struct paiext_map *cpump,
+			      struct perf_event *event)
 {
-	struct paiext_mapptr *mp = this_cpu_ptr(paiext_root.mapptr);
-	struct paiext_map *cpump = mp->mapptr;
-	struct perf_event *event = cpump->event;
 	struct perf_sample_data data;
 	struct perf_raw_record raw;
 	struct pt_regs regs;
-	size_t rawsize;
 	int overflow;
 
-	rawsize = paiext_copy(cpump);
-	if (!rawsize)			/* No incremented counters */
-		return 0;
-
 	/* Setup perf sample */
 	memset(&regs, 0, sizeof(regs));
 	memset(&raw, 0, sizeof(raw));
@@ -461,6 +451,23 @@ static int paiext_push_sample(void)
 	return overflow;
 }
 
+/* Check if there is data to be saved on schedule out of a task. */
+static int paiext_have_sample(void)
+{
+	struct paiext_mapptr *mp = this_cpu_ptr(paiext_root.mapptr);
+	struct paiext_map *cpump = mp->mapptr;
+	struct perf_event *event = cpump->event;
+	size_t rawsize;
+	int rc = 0;
+
+	if (!event)
+		return 0;
+	rawsize = paiext_copy(cpump->save, cpump->area);
+	if (rawsize)			/* Incremented counters */
+		rc = paiext_push_sample(rawsize, cpump, event);
+	return rc;
+}
+
 /* Called on schedule-in and schedule-out. No access to event structure,
  * but for sampling only event NNPA_ALL is allowed.
  */
@@ -470,7 +477,7 @@ static void paiext_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched
 	 * results on schedule_out and if page was dirty, clear values.
 	 */
 	if (!sched_in)
-		paiext_push_sample();
+		paiext_have_sample();
 }
 
 /* Attribute definitions for pai extension1 interface. As with other CPU
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 2e6754b62b20..f1897a8bb221 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -917,7 +917,6 @@ static int s390_fpregs_set(struct task_struct *target,
 	else
 		memcpy(&fprs, target->thread.fpu.fprs, sizeof(fprs));
 
-	/* If setting FPC, must validate it first. */
 	if (count > 0 && pos < offsetof(s390_fp_regs, fprs)) {
 		u32 ufpc[2] = { target->thread.fpu.fpc, 0 };
 		rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ufpc,
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index 45fdf2a9b2e3..72e9b7dcdf7d 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -20,19 +20,16 @@ config KVM
 	def_tristate y
 	prompt "Kernel-based Virtual Machine (KVM) support"
 	depends on HAVE_KVM
-	select PREEMPT_NOTIFIERS
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
-	select HAVE_KVM_EVENTFD
 	select KVM_ASYNC_PF
 	select KVM_ASYNC_PF_SYNC
+	select KVM_COMMON
 	select HAVE_KVM_IRQCHIP
-	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_INVALID_WAKEUPS
 	select HAVE_KVM_NO_POLL
 	select KVM_VFIO
-	select INTERVAL_TREE
 	select MMU_NOTIFIER
 	help
 	  Support hosting paravirtualized guest machines using the SIE
diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c
index 3765c4223bf9..80879fc73c90 100644
--- a/arch/s390/kvm/guestdbg.c
+++ b/arch/s390/kvm/guestdbg.c
@@ -213,8 +213,8 @@ int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu,
 	else if (dbg->arch.nr_hw_bp > MAX_BP_COUNT)
 		return -EINVAL;
 
-	bp_data = memdup_user(dbg->arch.hw_bp,
-			      sizeof(*bp_data) * dbg->arch.nr_hw_bp);
+	bp_data = memdup_array_user(dbg->arch.hw_bp, dbg->arch.nr_hw_bp,
+				    sizeof(*bp_data));
 	if (IS_ERR(bp_data))
 		return PTR_ERR(bp_data);
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index acc81ca6492e..ea63ac769889 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -563,7 +563,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_S390_CSS_SUPPORT:
 	case KVM_CAP_IOEVENTFD:
-	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_S390_IRQCHIP:
 	case KVM_CAP_VM_ATTRIBUTES:
 	case KVM_CAP_MP_STATE:
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 621a17fd1a1b..f875a404a0a0 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -676,8 +676,12 @@ static int handle_pqap(struct kvm_vcpu *vcpu)
 	if (vcpu->kvm->arch.crypto.pqap_hook) {
 		pqap_hook = *vcpu->kvm->arch.crypto.pqap_hook;
 		ret = pqap_hook(vcpu);
-		if (!ret && vcpu->run->s.regs.gprs[1] & 0x00ff0000)
-			kvm_s390_set_psw_cc(vcpu, 3);
+		if (!ret) {
+			if (vcpu->run->s.regs.gprs[1] & 0x00ff0000)
+				kvm_s390_set_psw_cc(vcpu, 3);
+			else
+				kvm_s390_set_psw_cc(vcpu, 0);
+		}
 		up_read(&vcpu->kvm->arch.crypto.pqap_hook_rwsem);
 		return ret;
 	}
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 8207a892bbe2..3af3bd20ac7b 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -19,6 +19,7 @@
 #include <asm/nmi.h>
 #include <asm/dis.h>
 #include <asm/fpu/api.h>
+#include <asm/facility.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
 
@@ -984,12 +985,26 @@ static void retry_vsie_icpt(struct vsie_page *vsie_page)
 static int handle_stfle(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 {
 	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
-	__u32 fac = READ_ONCE(vsie_page->scb_o->fac) & 0x7ffffff8U;
+	__u32 fac = READ_ONCE(vsie_page->scb_o->fac);
 
+	/*
+	 * Alternate-STFLE-Interpretive-Execution facilities are not supported
+	 * -> format-0 flcb
+	 */
 	if (fac && test_kvm_facility(vcpu->kvm, 7)) {
 		retry_vsie_icpt(vsie_page);
+		/*
+		 * The facility list origin (FLO) is in bits 1 - 28 of the FLD
+		 * so we need to mask here before reading.
+		 */
+		fac = fac & 0x7ffffff8U;
+		/*
+		 * format-0 -> size of nested guest's facility list == guest's size
+		 * guest's size == host's size, since STFLE is interpretatively executed
+		 * using a format-0 for the guest, too.
+		 */
 		if (read_guest_real(vcpu, fac, &vsie_page->fac,
-				    sizeof(vsie_page->fac)))
+				    stfle_size() * sizeof(u64)))
 			return set_validity_icpt(scb_s, 0x1090U);
 		scb_s->fac = (__u32)(__u64) &vsie_page->fac;
 	}
@@ -1220,7 +1235,6 @@ static int acquire_gmap_shadow(struct kvm_vcpu *vcpu,
 	gmap = gmap_shadow(vcpu->arch.gmap, asce, edat);
 	if (IS_ERR(gmap))
 		return PTR_ERR(gmap);
-	gmap->private = vcpu->kvm;
 	vcpu->kvm->stat.gmap_shadow_create++;
 	WRITE_ONCE(vsie_page->gmap, gmap);
 	return 0;
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index ab4098886e56..ac4c78546d97 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -280,7 +280,6 @@ static void do_sigbus(struct pt_regs *regs)
 static void do_exception(struct pt_regs *regs, int access)
 {
 	struct vm_area_struct *vma;
-	struct task_struct *tsk;
 	unsigned long address;
 	struct mm_struct *mm;
 	enum fault_type type;
@@ -289,7 +288,6 @@ static void do_exception(struct pt_regs *regs, int access)
 	vm_fault_t fault;
 	bool is_write;
 
-	tsk = current;
 	/*
 	 * The instruction that caused the program check has
 	 * been nullified. Don't signal single step via SIGTRAP.
@@ -297,7 +295,7 @@ static void do_exception(struct pt_regs *regs, int access)
 	clear_thread_flag(TIF_PER_TRAP);
 	if (kprobe_page_fault(regs, 14))
 		return;
-	mm = tsk->mm;
+	mm = current->mm;
 	address = get_fault_address(regs);
 	is_write = fault_is_write(regs);
 	type = get_fault_type(regs);
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 6f96b5a71c63..8da39deb56ca 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -1691,6 +1691,7 @@ struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce,
 		return ERR_PTR(-ENOMEM);
 	new->mm = parent->mm;
 	new->parent = gmap_get(parent);
+	new->private = parent->private;
 	new->orig_asce = asce;
 	new->edat_level = edat_level;
 	new->initialized = false;
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 676ac74026a8..52a44e353796 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -252,7 +252,7 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res,
 /* combine single writes by using store-block insn */
 void __iowrite64_copy(void __iomem *to, const void *from, size_t count)
 {
-       zpci_memcpy_toio(to, from, count);
+	zpci_memcpy_toio(to, from, count * 8);
 }
 
 void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size,
diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c
index 588089332931..a90499c087f0 100644
--- a/arch/s390/pci/pci_mmio.c
+++ b/arch/s390/pci/pci_mmio.c
@@ -97,9 +97,9 @@ static inline int __memcpy_toio_inuser(void __iomem *dst,
 		return -EINVAL;
 
 	while (n > 0) {
-		size = zpci_get_max_write_size((u64 __force) dst,
-					       (u64 __force) src, n,
-					       ZPCI_MAX_WRITE_SIZE);
+		size = zpci_get_max_io_size((u64 __force) dst,
+					    (u64 __force) src, n,
+					    ZPCI_MAX_WRITE_SIZE);
 		if (size > 8) /* main path */
 			rc = __pcistb_mio_inuser(dst, src, size, &status);
 		else
@@ -242,9 +242,9 @@ static inline int __memcpy_fromio_inuser(void __user *dst,
 	u8 status;
 
 	while (n > 0) {
-		size = zpci_get_max_write_size((u64 __force) src,
-					       (u64 __force) dst, n,
-					       ZPCI_MAX_READ_SIZE);
+		size = zpci_get_max_io_size((u64 __force) src,
+					    (u64 __force) dst, n,
+					    ZPCI_MAX_READ_SIZE);
 		rc = __pcilg_mio_inuser(dst, src, size, &status);
 		if (rc)
 			break;
diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index 0f279360838a..30d117f9ad7e 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -1220,7 +1220,7 @@ static int __init arch_setup(void)
 		lcdc_info.ch[0].num_modes		= ARRAY_SIZE(ecovec_dvi_modes);
 
 		/* No backlight */
-		gpio_backlight_data.fbdev = NULL;
+		gpio_backlight_data.dev = NULL;
 
 		gpio_set_value(GPIO_PTA2, 1);
 		gpio_set_value(GPIO_PTU1, 1);
diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig
index cf59b98446e4..7b427c17fbfe 100644
--- a/arch/sh/configs/sdk7786_defconfig
+++ b/arch/sh/configs/sdk7786_defconfig
@@ -171,7 +171,8 @@ CONFIG_BTRFS_FS=y
 CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=y
 CONFIG_CUSE=m
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
 CONFIG_CACHEFILES=m
 CONFIG_ISO9660_FS=m
 CONFIG_JOLIET=y
diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h
index 878b6b551bd2..51112f54552b 100644
--- a/arch/sh/include/asm/cacheflush.h
+++ b/arch/sh/include/asm/cacheflush.h
@@ -90,6 +90,7 @@ extern void copy_from_user_page(struct vm_area_struct *vma,
 	unsigned long len);
 
 #define flush_cache_vmap(start, end)		local_flush_cache_all(NULL)
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		local_flush_cache_all(NULL)
 
 #define flush_dcache_mmap_lock(mapping)		do { } while (0)
diff --git a/arch/sh/kernel/vsyscall/Makefile b/arch/sh/kernel/vsyscall/Makefile
index 6e8664448048..118744d349e2 100644
--- a/arch/sh/kernel/vsyscall/Makefile
+++ b/arch/sh/kernel/vsyscall/Makefile
@@ -1,11 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-y += vsyscall.o vsyscall-syscall.o vsyscall-syms.o
 
-$(obj)/vsyscall-syscall.o: \
-	$(foreach F,trapa,$(obj)/vsyscall-$F.so)
+$(obj)/vsyscall-syscall.o: $(obj)/vsyscall-trapa.so
 
 # Teach kbuild about targets
-targets += $(foreach F,trapa,vsyscall-$F.o vsyscall-$F.so)
+targets += vsyscall-trapa.o vsyscall-traps.so
 targets += vsyscall-note.o vsyscall.lds vsyscall-dummy.o
 
 # The DSO images are built using a special linker script
diff --git a/arch/sparc/Makefile b/arch/sparc/Makefile
index 5f6035936131..2a03daa68f28 100644
--- a/arch/sparc/Makefile
+++ b/arch/sparc/Makefile
@@ -60,7 +60,7 @@ libs-y                 += arch/sparc/prom/
 libs-y                 += arch/sparc/lib/
 
 drivers-$(CONFIG_PM) += arch/sparc/power/
-drivers-$(CONFIG_FB) += arch/sparc/video/
+drivers-$(CONFIG_FB_CORE) += arch/sparc/video/
 
 boot := arch/sparc/boot
 
diff --git a/arch/sparc/include/asm/cacheflush_32.h b/arch/sparc/include/asm/cacheflush_32.h
index f3b7270bf71b..9fee0ccfccb8 100644
--- a/arch/sparc/include/asm/cacheflush_32.h
+++ b/arch/sparc/include/asm/cacheflush_32.h
@@ -48,6 +48,7 @@ static inline void flush_dcache_page(struct page *page)
 #define flush_dcache_mmap_unlock(mapping)	do { } while (0)
 
 #define flush_cache_vmap(start, end)		flush_cache_all()
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		flush_cache_all()
 
 /* When a context switch happens we must flush all user windows so that
diff --git a/arch/sparc/include/asm/cacheflush_64.h b/arch/sparc/include/asm/cacheflush_64.h
index 0e879004efff..2b1261b77ecd 100644
--- a/arch/sparc/include/asm/cacheflush_64.h
+++ b/arch/sparc/include/asm/cacheflush_64.h
@@ -75,6 +75,7 @@ void flush_ptrace_access(struct vm_area_struct *, struct page *,
 #define flush_dcache_mmap_unlock(mapping)	do { } while (0)
 
 #define flush_cache_vmap(start, end)		do { } while (0)
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		do { } while (0)
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h
index 94eb529dcb77..2718cbea826a 100644
--- a/arch/sparc/include/asm/jump_label.h
+++ b/arch/sparc/include/asm/jump_label.h
@@ -10,7 +10,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "nop\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
@@ -26,7 +26,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "b %l[l_yes]\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
diff --git a/arch/sparc/kernel/pci_sabre.c b/arch/sparc/kernel/pci_sabre.c
index 3c38ca40a22b..a84598568300 100644
--- a/arch/sparc/kernel/pci_sabre.c
+++ b/arch/sparc/kernel/pci_sabre.c
@@ -13,7 +13,10 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/interrupt.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
 
 #include <asm/apb.h>
 #include <asm/iommu.h>
@@ -456,7 +459,6 @@ static void sabre_pbm_init(struct pci_pbm_info *pbm,
 static const struct of_device_id sabre_match[];
 static int sabre_probe(struct platform_device *op)
 {
-	const struct of_device_id *match;
 	const struct linux_prom64_registers *pr_regs;
 	struct device_node *dp = op->dev.of_node;
 	struct pci_pbm_info *pbm;
@@ -466,8 +468,7 @@ static int sabre_probe(struct platform_device *op)
 	const u32 *vdma;
 	u64 clear_irq;
 
-	match = of_match_device(sabre_match, &op->dev);
-	hummingbird_p = match && (match->data != NULL);
+	hummingbird_p = (uintptr_t)device_get_match_data(&op->dev);
 	if (!hummingbird_p) {
 		struct device_node *cpu_dp;
 
diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c
index 23b47f7fdb1d..5d8dd4949586 100644
--- a/arch/sparc/kernel/pci_schizo.c
+++ b/arch/sparc/kernel/pci_schizo.c
@@ -11,7 +11,10 @@
 #include <linux/slab.h>
 #include <linux/export.h>
 #include <linux/interrupt.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/numa.h>
 
 #include <asm/iommu.h>
@@ -1459,15 +1462,13 @@ out_err:
 	return err;
 }
 
-static const struct of_device_id schizo_match[];
 static int schizo_probe(struct platform_device *op)
 {
-	const struct of_device_id *match;
+	unsigned long chip_type = (unsigned long)device_get_match_data(&op->dev);
 
-	match = of_match_device(schizo_match, &op->dev);
-	if (!match)
+	if (!chip_type)
 		return -EINVAL;
-	return __schizo_init(op, (unsigned long)match->data);
+	return __schizo_init(op, chip_type);
 }
 
 /* The ordering of this table is very important.  Some Tomatillo
diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile
index d08c3a0443f3..7f5eedf1f5e0 100644
--- a/arch/sparc/vdso/Makefile
+++ b/arch/sparc/vdso/Makefile
@@ -3,9 +3,6 @@
 # Building vDSO images for sparc.
 #
 
-VDSO64-$(CONFIG_SPARC64)	:= y
-VDSOCOMPAT-$(CONFIG_COMPAT)	:= y
-
 # files to link into the vdso
 vobjs-y := vdso-note.o vclock_gettime.o
 
@@ -13,22 +10,15 @@ vobjs-y := vdso-note.o vclock_gettime.o
 obj-y				+= vma.o
 
 # vDSO images to build
-vdso_img-$(VDSO64-y)		+= 64
-vdso_img-$(VDSOCOMPAT-y)	+= 32
+obj-$(CONFIG_SPARC64)		+= vdso-image-64.o
+obj-$(CONFIG_COMPAT)		+= vdso-image-32.o
 
-vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
+vobjs := $(addprefix $(obj)/, $(vobjs-y))
 
 $(obj)/vdso.o: $(obj)/vdso.so
 
 targets += vdso.lds $(vobjs-y)
-
-# Build the vDSO image C files and link them in.
-vdso_img_objs := $(vdso_img-y:%=vdso-image-%.o)
-vdso_img_cfiles := $(vdso_img-y:%=vdso-image-%.c)
-vdso_img_sodbg := $(vdso_img-y:%=vdso%.so.dbg)
-obj-y += $(vdso_img_objs)
-targets += $(vdso_img_cfiles)
-targets += $(vdso_img_sodbg) $(vdso_img-y:%=vdso%.so)
+targets += $(foreach x, 32 64, vdso-image-$(x).c vdso$(x).so vdso$(x).so.dbg)
 
 CPPFLAGS_vdso.lds += -P -C
 
diff --git a/arch/sparc/video/Makefile b/arch/sparc/video/Makefile
index 6baddbd58e4d..d4d83f1702c6 100644
--- a/arch/sparc/video/Makefile
+++ b/arch/sparc/video/Makefile
@@ -1,3 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
-obj-$(CONFIG_FB) += fbdev.o
+obj-$(CONFIG_FB_CORE) += fbdev.o
diff --git a/arch/um/Makefile b/arch/um/Makefile
index 82f05f250634..34957dcb88b9 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -115,7 +115,9 @@ archprepare:
 	$(Q)$(MAKE) $(build)=$(HOST_DIR)/um include/generated/user_constants.h
 
 LINK-$(CONFIG_LD_SCRIPT_STATIC) += -static
-LINK-$(CONFIG_LD_SCRIPT_DYN) += $(call cc-option, -no-pie)
+ifdef CONFIG_LD_SCRIPT_DYN
+LINK-$(call gcc-min-version, 60100)$(CONFIG_CC_IS_CLANG) += -no-pie
+endif
 LINK-$(CONFIG_LD_SCRIPT_DYN_RPATH) += -Wl,-rpath,/lib
 
 CFLAGS_NO_HARDENING := $(call cc-option, -fno-PIC,) $(call cc-option, -fno-pic,) \
diff --git a/arch/um/Makefile-skas b/arch/um/Makefile-skas
index ac35de5316a6..67323b028999 100644
--- a/arch/um/Makefile-skas
+++ b/arch/um/Makefile-skas
@@ -4,7 +4,12 @@
 #
 
 GPROF_OPT += -pg
+
+ifdef CONFIG_CC_IS_CLANG
+GCOV_OPT += -fprofile-instr-generate -fcoverage-mapping
+else
 GCOV_OPT += -fprofile-arcs -ftest-coverage
+endif
 
 CFLAGS-$(CONFIG_GCOV) += $(GCOV_OPT)
 CFLAGS-$(CONFIG_GPROF) += $(GPROF_OPT)
diff --git a/arch/um/drivers/chan.h b/arch/um/drivers/chan.h
index 3fec3b8406e9..e14b9cdf7a33 100644
--- a/arch/um/drivers/chan.h
+++ b/arch/um/drivers/chan.h
@@ -30,7 +30,7 @@ struct chan {
 extern void chan_interrupt(struct line *line, int irq);
 extern int parse_chan_pair(char *str, struct line *line, int device,
 			   const struct chan_opts *opts, char **error_out);
-extern int write_chan(struct chan *chan, const char *buf, int len,
+extern int write_chan(struct chan *chan, const u8 *buf, size_t len,
 			     int write_irq);
 extern int console_write_chan(struct chan *chan, const char *buf, 
 			      int len);
diff --git a/arch/um/drivers/chan_kern.c b/arch/um/drivers/chan_kern.c
index 26a702a06515..37538b4168da 100644
--- a/arch/um/drivers/chan_kern.c
+++ b/arch/um/drivers/chan_kern.c
@@ -33,14 +33,14 @@ static void not_configged_close(int fd, void *data)
 	       "UML\n");
 }
 
-static int not_configged_read(int fd, char *c_out, void *data)
+static int not_configged_read(int fd, u8 *c_out, void *data)
 {
 	printk(KERN_ERR "Using a channel type which is configured out of "
 	       "UML\n");
 	return -EIO;
 }
 
-static int not_configged_write(int fd, const char *buf, int len, void *data)
+static int not_configged_write(int fd, const u8 *buf, size_t len, void *data)
 {
 	printk(KERN_ERR "Using a channel type which is configured out of "
 	       "UML\n");
@@ -247,8 +247,7 @@ void deactivate_chan(struct chan *chan, int irq)
 		deactivate_fd(chan->fd, irq);
 }
 
-int write_chan(struct chan *chan, const char *buf, int len,
-	       int write_irq)
+int write_chan(struct chan *chan, const u8 *buf, size_t len, int write_irq)
 {
 	int n, ret = 0;
 
@@ -540,7 +539,7 @@ void chan_interrupt(struct line *line, int irq)
 	struct tty_port *port = &line->port;
 	struct chan *chan = line->chan_in;
 	int err;
-	char c;
+	u8 c;
 
 	if (!chan || !chan->ops->read)
 		goto out;
diff --git a/arch/um/drivers/chan_user.c b/arch/um/drivers/chan_user.c
index 25727ed648b7..ec04e47b9d79 100644
--- a/arch/um/drivers/chan_user.c
+++ b/arch/um/drivers/chan_user.c
@@ -19,7 +19,7 @@ void generic_close(int fd, void *unused)
 	close(fd);
 }
 
-int generic_read(int fd, char *c_out, void *unused)
+int generic_read(int fd, __u8 *c_out, void *unused)
 {
 	int n;
 
@@ -35,7 +35,7 @@ int generic_read(int fd, char *c_out, void *unused)
 
 /* XXX Trivial wrapper around write */
 
-int generic_write(int fd, const char *buf, int n, void *unused)
+int generic_write(int fd, const __u8 *buf, size_t n, void *unused)
 {
 	int err;
 
@@ -141,7 +141,7 @@ struct winch_data {
 	int pipe_fd;
 };
 
-static int winch_thread(void *arg)
+static __noreturn int winch_thread(void *arg)
 {
 	struct winch_data *data = arg;
 	sigset_t sigs;
@@ -153,8 +153,8 @@ static int winch_thread(void *arg)
 	pipe_fd = data->pipe_fd;
 	count = write(pipe_fd, &c, sizeof(c));
 	if (count != sizeof(c))
-		printk(UM_KERN_ERR "winch_thread : failed to write "
-		       "synchronization byte, err = %d\n", -count);
+		os_info("winch_thread : failed to write synchronization byte, err = %d\n",
+			-count);
 
 	/*
 	 * We are not using SIG_IGN on purpose, so don't fix it as I thought to
@@ -166,29 +166,29 @@ static int winch_thread(void *arg)
 	sigfillset(&sigs);
 	/* Block all signals possible. */
 	if (sigprocmask(SIG_SETMASK, &sigs, NULL) < 0) {
-		printk(UM_KERN_ERR "winch_thread : sigprocmask failed, "
-		       "errno = %d\n", errno);
-		exit(1);
+		os_info("winch_thread : sigprocmask failed, errno = %d\n",
+			errno);
+		goto wait_kill;
 	}
 	/* In sigsuspend(), block anything else than SIGWINCH. */
 	sigdelset(&sigs, SIGWINCH);
 
 	if (setsid() < 0) {
-		printk(UM_KERN_ERR "winch_thread : setsid failed, errno = %d\n",
+		os_info("winch_thread : setsid failed, errno = %d\n",
 		       errno);
-		exit(1);
+		goto wait_kill;
 	}
 
 	if (ioctl(pty_fd, TIOCSCTTY, 0) < 0) {
-		printk(UM_KERN_ERR "winch_thread : TIOCSCTTY failed on "
-		       "fd %d err = %d\n", pty_fd, errno);
-		exit(1);
+		os_info("winch_thread : TIOCSCTTY failed on "
+			"fd %d err = %d\n", pty_fd, errno);
+		goto wait_kill;
 	}
 
 	if (tcsetpgrp(pty_fd, os_getpid()) < 0) {
-		printk(UM_KERN_ERR "winch_thread : tcsetpgrp failed on "
-		       "fd %d err = %d\n", pty_fd, errno);
-		exit(1);
+		os_info("winch_thread : tcsetpgrp failed on fd %d err = %d\n",
+			pty_fd, errno);
+		goto wait_kill;
 	}
 
 	/*
@@ -199,8 +199,8 @@ static int winch_thread(void *arg)
 	 */
 	count = read(pipe_fd, &c, sizeof(c));
 	if (count != sizeof(c))
-		printk(UM_KERN_ERR "winch_thread : failed to read "
-		       "synchronization byte, err = %d\n", errno);
+		os_info("winch_thread : failed to read synchronization byte, err = %d\n",
+			errno);
 
 	while(1) {
 		/*
@@ -211,9 +211,15 @@ static int winch_thread(void *arg)
 
 		count = write(pipe_fd, &c, sizeof(c));
 		if (count != sizeof(c))
-			printk(UM_KERN_ERR "winch_thread : write failed, "
-			       "err = %d\n", errno);
+			os_info("winch_thread : write failed, err = %d\n",
+				errno);
 	}
+
+wait_kill:
+	c = 2;
+	count = write(pipe_fd, &c, sizeof(c));
+	while (1)
+		pause();
 }
 
 static int winch_tramp(int fd, struct tty_port *port, int *fd_out,
diff --git a/arch/um/drivers/chan_user.h b/arch/um/drivers/chan_user.h
index 4e51b85e2a23..e158e16fb3cc 100644
--- a/arch/um/drivers/chan_user.h
+++ b/arch/um/drivers/chan_user.h
@@ -7,6 +7,7 @@
 #define __CHAN_USER_H__
 
 #include <init.h>
+#include <linux/types.h>
 
 struct chan_opts {
 	void (*const announce)(char *dev_name, int dev);
@@ -19,8 +20,8 @@ struct chan_ops {
 	void *(*init)(char *, int, const struct chan_opts *);
 	int (*open)(int, int, int, void *, char **);
 	void (*close)(int, void *);
-	int (*read)(int, char *, void *);
-	int (*write)(int, const char *, int, void *);
+	int (*read)(int, __u8 *, void *);
+	int (*write)(int, const __u8 *, size_t, void *);
 	int (*console_write)(int, const char *, int);
 	int (*window_size)(int, void *, unsigned short *, unsigned short *);
 	void (*free)(void *);
@@ -31,8 +32,8 @@ extern const struct chan_ops fd_ops, null_ops, port_ops, pts_ops, pty_ops,
 	tty_ops, xterm_ops;
 
 extern void generic_close(int fd, void *unused);
-extern int generic_read(int fd, char *c_out, void *unused);
-extern int generic_write(int fd, const char *buf, int n, void *unused);
+extern int generic_read(int fd, __u8 *c_out, void *unused);
+extern int generic_write(int fd, const __u8 *buf, size_t n, void *unused);
 extern int generic_console_write(int fd, const char *buf, int n);
 extern int generic_window_size(int fd, void *unused, unsigned short *rows_out,
 			       unsigned short *cols_out);
diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c
index b98545f3edb5..ffc5cb92fa36 100644
--- a/arch/um/drivers/line.c
+++ b/arch/um/drivers/line.c
@@ -83,7 +83,7 @@ unsigned int line_chars_in_buffer(struct tty_struct *tty)
  *
  * Must be called while holding line->lock!
  */
-static int buffer_data(struct line *line, const char *buf, int len)
+static int buffer_data(struct line *line, const u8 *buf, size_t len)
 {
 	int end, room;
 
@@ -629,15 +629,18 @@ static irqreturn_t winch_interrupt(int irq, void *data)
 
 	if (fd != -1) {
 		err = generic_read(fd, &c, NULL);
-		if (err < 0) {
+		/* A read of 2 means the winch thread failed and has warned */
+		if (err < 0 || (err == 1 && c == 2)) {
 			if (err != -EAGAIN) {
 				winch->fd = -1;
 				list_del(&winch->list);
 				os_close_file(fd);
-				printk(KERN_ERR "winch_interrupt : "
-				       "read failed, errno = %d\n", -err);
-				printk(KERN_ERR "fd %d is losing SIGWINCH "
-				       "support\n", winch->tty_fd);
+				if (err < 0) {
+					printk(KERN_ERR "winch_interrupt : read failed, errno = %d\n",
+					       -err);
+					printk(KERN_ERR "fd %d is losing SIGWINCH support\n",
+					       winch->tty_fd);
+				}
 				INIT_WORK(&winch->work, __free_winch);
 				schedule_work(&winch->work);
 				return IRQ_HANDLED;
diff --git a/arch/um/drivers/line.h b/arch/um/drivers/line.h
index e84fb9b4165e..e8bd6f3dfb50 100644
--- a/arch/um/drivers/line.h
+++ b/arch/um/drivers/line.h
@@ -47,9 +47,9 @@ struct line {
 	 *
 	 * buffer points to a buffer allocated on demand, of length
 	 * LINE_BUFSIZE, head to the start of the ring, tail to the end.*/
-	char *buffer;
-	char *head;
-	char *tail;
+	u8 *buffer;
+	u8 *head;
+	u8 *tail;
 
 	int sigio;
 	struct delayed_work task;
diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c
index 3d7836c46507..cabcc501b448 100644
--- a/arch/um/drivers/net_kern.c
+++ b/arch/um/drivers/net_kern.c
@@ -204,7 +204,7 @@ static int uml_net_close(struct net_device *dev)
 	return 0;
 }
 
-static int uml_net_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t uml_net_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct uml_net_private *lp = netdev_priv(dev);
 	unsigned long flags;
diff --git a/arch/um/drivers/null.c b/arch/um/drivers/null.c
index 87087763a417..30d59b8481b4 100644
--- a/arch/um/drivers/null.c
+++ b/arch/um/drivers/null.c
@@ -28,7 +28,7 @@ static int null_open(int input, int output, int primary, void *d,
 	return (fd < 0) ? -errno : fd;
 }
 
-static int null_read(int fd, char *c_out, void *unused)
+static int null_read(int fd, __u8 *c_out, void *unused)
 {
 	return -ENODEV;
 }
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 92ee2697ff39..63fc062add70 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -108,8 +108,6 @@ static inline void ubd_set_bit(__u64 bit, unsigned char *data)
 static DEFINE_MUTEX(ubd_lock);
 static DEFINE_MUTEX(ubd_mutex); /* replaces BKL, might not be needed */
 
-static int ubd_open(struct gendisk *disk, blk_mode_t mode);
-static void ubd_release(struct gendisk *disk);
 static int ubd_ioctl(struct block_device *bdev, blk_mode_t mode,
 		     unsigned int cmd, unsigned long arg);
 static int ubd_getgeo(struct block_device *bdev, struct hd_geometry *geo);
@@ -118,16 +116,11 @@ static int ubd_getgeo(struct block_device *bdev, struct hd_geometry *geo);
 
 static const struct block_device_operations ubd_blops = {
         .owner		= THIS_MODULE,
-        .open		= ubd_open,
-        .release	= ubd_release,
         .ioctl		= ubd_ioctl,
         .compat_ioctl	= blkdev_compat_ptr_ioctl,
 	.getgeo		= ubd_getgeo,
 };
 
-/* Protected by ubd_lock */
-static struct gendisk *ubd_gendisk[MAX_DEV];
-
 #ifdef CONFIG_BLK_DEV_UBD_SYNC
 #define OPEN_FLAGS ((struct openflags) { .r = 1, .w = 1, .s = 1, .c = 0, \
 					 .cl = 1 })
@@ -155,7 +148,6 @@ struct ubd {
 	 * backing or the cow file. */
 	char *file;
 	char *serial;
-	int count;
 	int fd;
 	__u64 size;
 	struct openflags boot_openflags;
@@ -165,7 +157,7 @@ struct ubd {
 	unsigned no_trim:1;
 	struct cow cow;
 	struct platform_device pdev;
-	struct request_queue *queue;
+	struct gendisk *disk;
 	struct blk_mq_tag_set tag_set;
 	spinlock_t lock;
 };
@@ -181,7 +173,6 @@ struct ubd {
 #define DEFAULT_UBD { \
 	.file = 		NULL, \
 	.serial =		NULL, \
-	.count =		0, \
 	.fd =			-1, \
 	.size =			-1, \
 	.boot_openflags =	OPEN_FLAGS, \
@@ -774,8 +765,6 @@ static int ubd_open_dev(struct ubd *ubd_dev)
 	ubd_dev->fd = fd;
 
 	if(ubd_dev->cow.file != NULL){
-		blk_queue_max_hw_sectors(ubd_dev->queue, 8 * sizeof(long));
-
 		err = -ENOMEM;
 		ubd_dev->cow.bitmap = vmalloc(ubd_dev->cow.bitmap_len);
 		if(ubd_dev->cow.bitmap == NULL){
@@ -797,11 +786,6 @@ static int ubd_open_dev(struct ubd *ubd_dev)
 		if(err < 0) goto error;
 		ubd_dev->cow.fd = err;
 	}
-	if (ubd_dev->no_trim == 0) {
-		blk_queue_max_discard_sectors(ubd_dev->queue, UBD_MAX_REQUEST);
-		blk_queue_max_write_zeroes_sectors(ubd_dev->queue, UBD_MAX_REQUEST);
-	}
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, ubd_dev->queue);
 	return 0;
  error:
 	os_close_file(ubd_dev->fd);
@@ -851,27 +835,6 @@ static const struct attribute_group *ubd_attr_groups[] = {
 	NULL,
 };
 
-static int ubd_disk_register(int major, u64 size, int unit,
-			     struct gendisk *disk)
-{
-	disk->major = major;
-	disk->first_minor = unit << UBD_SHIFT;
-	disk->minors = 1 << UBD_SHIFT;
-	disk->fops = &ubd_blops;
-	set_capacity(disk, size / 512);
-	sprintf(disk->disk_name, "ubd%c", 'a' + unit);
-
-	ubd_devs[unit].pdev.id   = unit;
-	ubd_devs[unit].pdev.name = DRIVER_NAME;
-	ubd_devs[unit].pdev.dev.release = ubd_device_release;
-	dev_set_drvdata(&ubd_devs[unit].pdev.dev, &ubd_devs[unit]);
-	platform_device_register(&ubd_devs[unit].pdev);
-
-	disk->private_data = &ubd_devs[unit];
-	disk->queue = ubd_devs[unit].queue;
-	return device_add_disk(&ubd_devs[unit].pdev.dev, disk, ubd_attr_groups);
-}
-
 #define ROUND_BLOCK(n) ((n + (SECTOR_SIZE - 1)) & (-SECTOR_SIZE))
 
 static const struct blk_mq_ops ubd_mq_ops = {
@@ -881,18 +844,36 @@ static const struct blk_mq_ops ubd_mq_ops = {
 static int ubd_add(int n, char **error_out)
 {
 	struct ubd *ubd_dev = &ubd_devs[n];
+	struct queue_limits lim = {
+		.max_segments		= MAX_SG,
+		.seg_boundary_mask	= PAGE_SIZE - 1,
+	};
 	struct gendisk *disk;
 	int err = 0;
 
 	if(ubd_dev->file == NULL)
 		goto out;
 
+	if (ubd_dev->cow.file)
+		lim.max_hw_sectors = 8 * sizeof(long);
+	if (!ubd_dev->no_trim) {
+		lim.max_hw_discard_sectors = UBD_MAX_REQUEST;
+		lim.max_write_zeroes_sectors = UBD_MAX_REQUEST;
+	}
+
 	err = ubd_file_size(ubd_dev, &ubd_dev->size);
 	if(err < 0){
 		*error_out = "Couldn't determine size of device's file";
 		goto out;
 	}
 
+	err = ubd_open_dev(ubd_dev);
+	if (err) {
+		pr_err("ubd%c: Can't open \"%s\": errno = %d\n",
+			'a' + n, ubd_dev->file, -err);
+		goto out;
+	}
+
 	ubd_dev->size = ROUND_BLOCK(ubd_dev->size);
 
 	ubd_dev->tag_set.ops = &ubd_mq_ops;
@@ -904,29 +885,43 @@ static int ubd_add(int n, char **error_out)
 
 	err = blk_mq_alloc_tag_set(&ubd_dev->tag_set);
 	if (err)
-		goto out;
+		goto out_close;
 
-	disk = blk_mq_alloc_disk(&ubd_dev->tag_set, ubd_dev);
+	disk = blk_mq_alloc_disk(&ubd_dev->tag_set, &lim, ubd_dev);
 	if (IS_ERR(disk)) {
 		err = PTR_ERR(disk);
 		goto out_cleanup_tags;
 	}
-	ubd_dev->queue = disk->queue;
 
-	blk_queue_write_cache(ubd_dev->queue, true, false);
-	blk_queue_max_segments(ubd_dev->queue, MAX_SG);
-	blk_queue_segment_boundary(ubd_dev->queue, PAGE_SIZE - 1);
-	err = ubd_disk_register(UBD_MAJOR, ubd_dev->size, n, disk);
+	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
+	blk_queue_write_cache(disk->queue, true, false);
+	disk->major = UBD_MAJOR;
+	disk->first_minor = n << UBD_SHIFT;
+	disk->minors = 1 << UBD_SHIFT;
+	disk->fops = &ubd_blops;
+	set_capacity(disk, ubd_dev->size / 512);
+	sprintf(disk->disk_name, "ubd%c", 'a' + n);
+	disk->private_data = ubd_dev;
+	set_disk_ro(disk, !ubd_dev->openflags.w);
+
+	ubd_dev->pdev.id = n;
+	ubd_dev->pdev.name = DRIVER_NAME;
+	ubd_dev->pdev.dev.release = ubd_device_release;
+	dev_set_drvdata(&ubd_dev->pdev.dev, ubd_dev);
+	platform_device_register(&ubd_dev->pdev);
+
+	err = device_add_disk(&ubd_dev->pdev.dev, disk, ubd_attr_groups);
 	if (err)
 		goto out_cleanup_disk;
 
-	ubd_gendisk[n] = disk;
 	return 0;
 
 out_cleanup_disk:
 	put_disk(disk);
 out_cleanup_tags:
 	blk_mq_free_tag_set(&ubd_dev->tag_set);
+out_close:
+	ubd_close_dev(ubd_dev);
 out:
 	return err;
 }
@@ -1012,7 +1007,6 @@ static int ubd_id(char **str, int *start_out, int *end_out)
 
 static int ubd_remove(int n, char **error_out)
 {
-	struct gendisk *disk = ubd_gendisk[n];
 	struct ubd *ubd_dev;
 	int err = -ENODEV;
 
@@ -1023,15 +1017,15 @@ static int ubd_remove(int n, char **error_out)
 	if(ubd_dev->file == NULL)
 		goto out;
 
-	/* you cannot remove a open disk */
-	err = -EBUSY;
-	if(ubd_dev->count > 0)
-		goto out;
+	if (ubd_dev->disk) {
+		/* you cannot remove a open disk */
+		err = -EBUSY;
+		if (disk_openers(ubd_dev->disk))
+			goto out;
 
-	ubd_gendisk[n] = NULL;
-	if(disk != NULL){
-		del_gendisk(disk);
-		put_disk(disk);
+		del_gendisk(ubd_dev->disk);
+		ubd_close_dev(ubd_dev);
+		put_disk(ubd_dev->disk);
 	}
 
 	err = 0;
@@ -1153,37 +1147,6 @@ static int __init ubd_driver_init(void){
 
 device_initcall(ubd_driver_init);
 
-static int ubd_open(struct gendisk *disk, blk_mode_t mode)
-{
-	struct ubd *ubd_dev = disk->private_data;
-	int err = 0;
-
-	mutex_lock(&ubd_mutex);
-	if(ubd_dev->count == 0){
-		err = ubd_open_dev(ubd_dev);
-		if(err){
-			printk(KERN_ERR "%s: Can't open \"%s\": errno = %d\n",
-			       disk->disk_name, ubd_dev->file, -err);
-			goto out;
-		}
-	}
-	ubd_dev->count++;
-	set_disk_ro(disk, !ubd_dev->openflags.w);
-out:
-	mutex_unlock(&ubd_mutex);
-	return err;
-}
-
-static void ubd_release(struct gendisk *disk)
-{
-	struct ubd *ubd_dev = disk->private_data;
-
-	mutex_lock(&ubd_mutex);
-	if(--ubd_dev->count == 0)
-		ubd_close_dev(ubd_dev);
-	mutex_unlock(&ubd_mutex);
-}
-
 static void cowify_bitmap(__u64 io_offset, int length, unsigned long *cow_mask,
 			  __u64 *cow_offset, unsigned long *bitmap,
 			  __u64 bitmap_offset, unsigned long *bitmap_words,
diff --git a/arch/um/drivers/virt-pci.c b/arch/um/drivers/virt-pci.c
index ffe2ee8a0246..97a37c062997 100644
--- a/arch/um/drivers/virt-pci.c
+++ b/arch/um/drivers/virt-pci.c
@@ -971,7 +971,7 @@ static long um_pci_map_platform(unsigned long offset, size_t size,
 	*ops = &um_pci_device_bar_ops;
 	*priv = &um_pci_platform_device->resptr[0];
 
-	return 0;
+	return offset;
 }
 
 static const struct logic_iomem_region_ops um_pci_platform_ops = {
diff --git a/arch/um/include/asm/cpufeature.h b/arch/um/include/asm/cpufeature.h
index 4b6d1b526bc1..66fe06db872f 100644
--- a/arch/um/include/asm/cpufeature.h
+++ b/arch/um/include/asm/cpufeature.h
@@ -75,7 +75,7 @@ extern void setup_clear_cpu_cap(unsigned int bit);
  */
 static __always_inline bool _static_cpu_has(u16 bit)
 {
-	asm_volatile_goto("1: jmp 6f\n"
+	asm goto("1: jmp 6f\n"
 		 "2:\n"
 		 ".skip -(((5f-4f) - (2b-1b)) > 0) * "
 			 "((5f-4f) - (2b-1b)),0x90\n"
diff --git a/arch/um/include/asm/mmu.h b/arch/um/include/asm/mmu.h
index 5b072aba5b65..a7555e43ed14 100644
--- a/arch/um/include/asm/mmu.h
+++ b/arch/um/include/asm/mmu.h
@@ -12,7 +12,6 @@
 typedef struct mm_context {
 	struct mm_id id;
 	struct uml_arch_mm_context arch;
-	struct page *stub_pages[2];
 } mm_context_t;
 
 extern void __switch_mm(struct mm_id * mm_idp);
diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h
index 7414154b8e9a..6c3779541845 100644
--- a/arch/um/include/asm/processor-generic.h
+++ b/arch/um/include/asm/processor-generic.h
@@ -22,7 +22,6 @@ struct mm_struct;
 struct thread_struct {
 	struct pt_regs regs;
 	struct pt_regs *segv_regs;
-	int singlestep_syscall;
 	void *fault_addr;
 	jmp_buf *fault_catcher;
 	struct task_struct *prev_sched;
diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h
index d8b8b4f07e42..789b83013f35 100644
--- a/arch/um/include/shared/kern_util.h
+++ b/arch/um/include/shared/kern_util.h
@@ -34,7 +34,6 @@ extern int handle_page_fault(unsigned long address, unsigned long ip,
 
 extern unsigned int do_IRQ(int irq, struct uml_pt_regs *regs);
 extern void initial_thread_cb(void (*proc)(void *), void *arg);
-extern int is_syscall(unsigned long addr);
 
 extern void timer_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs);
 
@@ -50,7 +49,7 @@ extern void do_uml_exitcalls(void);
  * Are we disallowed to sleep? Used to choose between GFP_KERNEL and
  * GFP_ATOMIC.
  */
-extern int __cant_sleep(void);
+extern int __uml_cant_sleep(void);
 extern int get_current_pid(void);
 extern int copy_from_user_proc(void *to, void *from, int size);
 extern char *uml_strdup(const char *string);
@@ -58,7 +57,7 @@ extern char *uml_strdup(const char *string);
 extern unsigned long to_irq_stack(unsigned long *mask_out);
 extern unsigned long from_irq_stack(int nested);
 
-extern int singlestepping(void *t);
+extern int singlestepping(void);
 
 extern void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs);
 extern void bus_handler(int sig, struct siginfo *si, struct uml_pt_regs *regs);
diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h
index 0df646c6651e..aff8906304ea 100644
--- a/arch/um/include/shared/os.h
+++ b/arch/um/include/shared/os.h
@@ -323,9 +323,6 @@ extern void sigio_broken(int fd);
 extern int __add_sigio_fd(int fd);
 extern int __ignore_sigio_fd(int fd);
 
-/* prctl.c */
-extern int os_arch_prctl(int pid, int option, unsigned long *arg2);
-
 /* tty.c */
 extern int get_pty(void);
 
diff --git a/arch/um/include/shared/ptrace_user.h b/arch/um/include/shared/ptrace_user.h
index 95455e8996e7..8a705d8f96ce 100644
--- a/arch/um/include/shared/ptrace_user.h
+++ b/arch/um/include/shared/ptrace_user.h
@@ -12,45 +12,4 @@
 extern int ptrace_getregs(long pid, unsigned long *regs_out);
 extern int ptrace_setregs(long pid, unsigned long *regs_in);
 
-/* syscall emulation path in ptrace */
-
-#ifndef PTRACE_SYSEMU
-#define PTRACE_SYSEMU 31
-#endif
-#ifndef PTRACE_SYSEMU_SINGLESTEP
-#define PTRACE_SYSEMU_SINGLESTEP 32
-#endif
-
-/* On architectures, that started to support PTRACE_O_TRACESYSGOOD
- * in linux 2.4, there are two different definitions of
- * PTRACE_SETOPTIONS: linux 2.4 uses 21 while linux 2.6 uses 0x4200.
- * For binary compatibility, 2.6 also supports the old "21", named
- * PTRACE_OLDSETOPTION. On these architectures, UML always must use
- * "21", to ensure the kernel runs on 2.4 and 2.6 host without
- * recompilation. So, we use PTRACE_OLDSETOPTIONS in UML.
- * We also want to be able to build the kernel on 2.4, which doesn't
- * have PTRACE_OLDSETOPTIONS. So, if it is missing, we declare
- * PTRACE_OLDSETOPTIONS to be the same as PTRACE_SETOPTIONS.
- *
- * On architectures, that start to support PTRACE_O_TRACESYSGOOD on
- * linux 2.6, PTRACE_OLDSETOPTIONS never is defined, and also isn't
- * supported by the host kernel. In that case, our trick lets us use
- * the new 0x4200 with the name PTRACE_OLDSETOPTIONS.
- */
-#ifndef PTRACE_OLDSETOPTIONS
-#define PTRACE_OLDSETOPTIONS PTRACE_SETOPTIONS
-#endif
-
-void set_using_sysemu(int value);
-int get_using_sysemu(void);
-extern int sysemu_supported;
-
-#define SELECT_PTRACE_OPERATION(sysemu_mode, singlestep_mode) \
-	(((int[3][3] ) { \
-		{ PTRACE_SYSCALL, PTRACE_SYSCALL, PTRACE_SINGLESTEP }, \
-		{ PTRACE_SYSEMU, PTRACE_SYSEMU, PTRACE_SINGLESTEP }, \
-		{ PTRACE_SYSEMU, PTRACE_SYSEMU_SINGLESTEP, \
-		  PTRACE_SYSEMU_SINGLESTEP } }) \
-		[sysemu_mode][singlestep_mode])
-
 #endif
diff --git a/arch/um/include/shared/registers.h b/arch/um/include/shared/registers.h
index 2f9c3ce5b45e..a0450326521c 100644
--- a/arch/um/include/shared/registers.h
+++ b/arch/um/include/shared/registers.h
@@ -14,8 +14,6 @@ extern int save_fp_registers(int pid, unsigned long *fp_regs);
 extern int restore_fp_registers(int pid, unsigned long *fp_regs);
 extern int save_fpx_registers(int pid, unsigned long *fp_regs);
 extern int restore_fpx_registers(int pid, unsigned long *fp_regs);
-extern int save_registers(int pid, struct uml_pt_regs *regs);
-extern int restore_pid_registers(int pid, struct uml_pt_regs *regs);
 extern int init_pid_registers(int pid);
 extern void get_safe_registers(unsigned long *regs, unsigned long *fp_regs);
 extern int get_fp_registers(int pid, unsigned long *regs);
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 106b7da2f8d6..ab95648e93e1 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -220,7 +220,7 @@ void arch_cpu_idle(void)
 	um_idle_sleep();
 }
 
-int __cant_sleep(void) {
+int __uml_cant_sleep(void) {
 	return in_atomic() || irqs_disabled() || in_interrupt();
 	/* Is in_interrupt() really needed? */
 }
@@ -332,17 +332,9 @@ int __init make_proc_sysemu(void)
 
 late_initcall(make_proc_sysemu);
 
-int singlestepping(void * t)
+int singlestepping(void)
 {
-	struct task_struct *task = t ? t : current;
-
-	if (!test_thread_flag(TIF_SINGLESTEP))
-		return 0;
-
-	if (task->thread.singlestep_syscall)
-		return 1;
-
-	return 2;
+	return test_thread_flag(TIF_SINGLESTEP);
 }
 
 /*
diff --git a/arch/um/kernel/ptrace.c b/arch/um/kernel/ptrace.c
index 5154b27de580..6600a2782796 100644
--- a/arch/um/kernel/ptrace.c
+++ b/arch/um/kernel/ptrace.c
@@ -12,7 +12,6 @@
 void user_enable_single_step(struct task_struct *child)
 {
 	set_tsk_thread_flag(child, TIF_SINGLESTEP);
-	child->thread.singlestep_syscall = 0;
 
 #ifdef SUBARCH_SET_SINGLESTEPPING
 	SUBARCH_SET_SINGLESTEPPING(child, 1);
@@ -22,7 +21,6 @@ void user_enable_single_step(struct task_struct *child)
 void user_disable_single_step(struct task_struct *child)
 {
 	clear_tsk_thread_flag(child, TIF_SINGLESTEP);
-	child->thread.singlestep_syscall = 0;
 
 #ifdef SUBARCH_SET_SINGLESTEPPING
 	SUBARCH_SET_SINGLESTEPPING(child, 0);
diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c
index ae4658f576ab..a56b44522766 100644
--- a/arch/um/kernel/signal.c
+++ b/arch/um/kernel/signal.c
@@ -121,18 +121,6 @@ void do_signal(struct pt_regs *regs)
 	}
 
 	/*
-	 * This closes a way to execute a system call on the host.  If
-	 * you set a breakpoint on a system call instruction and singlestep
-	 * from it, the tracing thread used to PTRACE_SINGLESTEP the process
-	 * rather than PTRACE_SYSCALL it, allowing the system call to execute
-	 * on the host.  The tracing thread will check this flag and
-	 * PTRACE_SYSCALL if necessary.
-	 */
-	if (test_thread_flag(TIF_SINGLESTEP))
-		current->thread.singlestep_syscall =
-			is_syscall(PT_REGS_IP(&current->thread.regs));
-
-	/*
 	 * if there's no signal to deliver, we just put the saved sigmask
 	 * back
 	 */
diff --git a/arch/um/kernel/skas/uaccess.c b/arch/um/kernel/skas/uaccess.c
index aaee96f07172..198269e384c4 100644
--- a/arch/um/kernel/skas/uaccess.c
+++ b/arch/um/kernel/skas/uaccess.c
@@ -236,7 +236,9 @@ EXPORT_SYMBOL(strnlen_user);
  *			  argument and comparison of the previous
  *			  futex value with another constant.
  *
- * @encoded_op:	encoded operation to execute
+ * @op:		operation to execute
+ * @oparg:	argument to operation
+ * @oval:	old value at uaddr
  * @uaddr:	pointer to user space address
  *
  * Return:
diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c
index fddd1dec27e6..3e270da6b6f6 100644
--- a/arch/um/kernel/time.c
+++ b/arch/um/kernel/time.c
@@ -432,9 +432,29 @@ static void time_travel_update_time(unsigned long long next, bool idle)
 	time_travel_del_event(&ne);
 }
 
+static void time_travel_update_time_rel(unsigned long long offs)
+{
+	unsigned long flags;
+
+	/*
+	 * Disable interrupts before calculating the new time so
+	 * that a real timer interrupt (signal) can't happen at
+	 * a bad time e.g. after we read time_travel_time but
+	 * before we've completed updating the time.
+	 */
+	local_irq_save(flags);
+	time_travel_update_time(time_travel_time + offs, false);
+	local_irq_restore(flags);
+}
+
 void time_travel_ndelay(unsigned long nsec)
 {
-	time_travel_update_time(time_travel_time + nsec, false);
+	/*
+	 * Not strictly needed to use _rel() version since this is
+	 * only used in INFCPU/EXT modes, but it doesn't hurt and
+	 * is more readable too.
+	 */
+	time_travel_update_time_rel(nsec);
 }
 EXPORT_SYMBOL(time_travel_ndelay);
 
@@ -568,7 +588,11 @@ static void time_travel_set_start(void)
 #define time_travel_time 0
 #define time_travel_ext_waiting 0
 
-static inline void time_travel_update_time(unsigned long long ns, bool retearly)
+static inline void time_travel_update_time(unsigned long long ns, bool idle)
+{
+}
+
+static inline void time_travel_update_time_rel(unsigned long long offs)
 {
 }
 
@@ -720,9 +744,7 @@ static u64 timer_read(struct clocksource *cs)
 		 */
 		if (!irqs_disabled() && !in_interrupt() && !in_softirq() &&
 		    !time_travel_ext_waiting)
-			time_travel_update_time(time_travel_time +
-						TIMER_MULTIPLIER,
-						false);
+			time_travel_update_time_rel(TIMER_MULTIPLIER);
 		return time_travel_time / TIMER_MULTIPLIER;
 	}
 
diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c
index b459745f52e2..3cb8ac63be6e 100644
--- a/arch/um/os-Linux/helper.c
+++ b/arch/um/os-Linux/helper.c
@@ -46,7 +46,7 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv)
 	unsigned long stack, sp;
 	int pid, fds[2], ret, n;
 
-	stack = alloc_stack(0, __cant_sleep());
+	stack = alloc_stack(0, __uml_cant_sleep());
 	if (stack == 0)
 		return -ENOMEM;
 
@@ -70,7 +70,7 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv)
 	data.pre_data = pre_data;
 	data.argv = argv;
 	data.fd = fds[1];
-	data.buf = __cant_sleep() ? uml_kmalloc(PATH_MAX, UM_GFP_ATOMIC) :
+	data.buf = __uml_cant_sleep() ? uml_kmalloc(PATH_MAX, UM_GFP_ATOMIC) :
 					uml_kmalloc(PATH_MAX, UM_GFP_KERNEL);
 	pid = clone(helper_child, (void *) sp, CLONE_VM, &data);
 	if (pid < 0) {
@@ -121,7 +121,7 @@ int run_helper_thread(int (*proc)(void *), void *arg, unsigned int flags,
 	unsigned long stack, sp;
 	int pid, status, err;
 
-	stack = alloc_stack(0, __cant_sleep());
+	stack = alloc_stack(0, __uml_cant_sleep());
 	if (stack == 0)
 		return -ENOMEM;
 
diff --git a/arch/um/os-Linux/registers.c b/arch/um/os-Linux/registers.c
index b123955be7ac..bd80b921add0 100644
--- a/arch/um/os-Linux/registers.c
+++ b/arch/um/os-Linux/registers.c
@@ -11,26 +11,6 @@
 #include <sysdep/ptrace_user.h>
 #include <registers.h>
 
-int save_registers(int pid, struct uml_pt_regs *regs)
-{
-	int err;
-
-	err = ptrace(PTRACE_GETREGS, pid, 0, regs->gp);
-	if (err < 0)
-		return -errno;
-	return 0;
-}
-
-int restore_pid_registers(int pid, struct uml_pt_regs *regs)
-{
-	int err;
-
-	err = ptrace(PTRACE_SETREGS, pid, 0, regs->gp);
-	if (err < 0)
-		return -errno;
-	return 0;
-}
-
 /* This is set once at boot time and not changed thereafter */
 
 static unsigned long exec_regs[MAX_REG_NR];
diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index 9464833e741a..1f5c3f2523d1 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -177,48 +177,11 @@ static void handle_segv(int pid, struct uml_pt_regs *regs, unsigned long *aux_fp
 	segv(regs->faultinfo, 0, 1, NULL);
 }
 
-/*
- * To use the same value of using_sysemu as the caller, ask it that value
- * (in local_using_sysemu
- */
-static void handle_trap(int pid, struct uml_pt_regs *regs,
-			int local_using_sysemu)
+static void handle_trap(int pid, struct uml_pt_regs *regs)
 {
-	int err, status;
-
 	if ((UPT_IP(regs) >= STUB_START) && (UPT_IP(regs) < STUB_END))
 		fatal_sigsegv();
 
-	if (!local_using_sysemu)
-	{
-		err = ptrace(PTRACE_POKEUSER, pid, PT_SYSCALL_NR_OFFSET,
-			     __NR_getpid);
-		if (err < 0) {
-			printk(UM_KERN_ERR "%s - nullifying syscall failed, errno = %d\n",
-			       __func__, errno);
-			fatal_sigsegv();
-		}
-
-		err = ptrace(PTRACE_SYSCALL, pid, 0, 0);
-		if (err < 0) {
-			printk(UM_KERN_ERR "%s - continuing to end of syscall failed, errno = %d\n",
-			       __func__, errno);
-			fatal_sigsegv();
-		}
-
-		CATCH_EINTR(err = waitpid(pid, &status, WUNTRACED | __WALL));
-		if ((err < 0) || !WIFSTOPPED(status) ||
-		    (WSTOPSIG(status) != SIGTRAP + 0x80)) {
-			err = ptrace_dump_regs(pid);
-			if (err)
-				printk(UM_KERN_ERR "Failed to get registers from process, errno = %d\n",
-				       -err);
-			printk(UM_KERN_ERR "%s - failed to wait at end of syscall, errno = %d, status = %d\n",
-			       __func__, errno, status);
-			fatal_sigsegv();
-		}
-	}
-
 	handle_syscall(regs);
 }
 
@@ -226,7 +189,7 @@ extern char __syscall_stub_start[];
 
 /**
  * userspace_tramp() - userspace trampoline
- * @stack:	pointer to the new userspace stack page, can be NULL, if? FIXME:
+ * @stack:	pointer to the new userspace stack page
  *
  * The userspace trampoline is used to setup a new userspace process in start_userspace() after it was clone()'ed.
  * This function will run on a temporary stack page.
@@ -241,9 +204,13 @@ extern char __syscall_stub_start[];
  */
 static int userspace_tramp(void *stack)
 {
+	struct sigaction sa;
 	void *addr;
 	int fd;
 	unsigned long long offset;
+	unsigned long segv_handler = STUB_CODE +
+				     (unsigned long) stub_segv_handler -
+				     (unsigned long) __syscall_stub_start;
 
 	ptrace(PTRACE_TRACEME, 0, 0, 0);
 
@@ -254,39 +221,30 @@ static int userspace_tramp(void *stack)
 	addr = mmap64((void *) STUB_CODE, UM_KERN_PAGE_SIZE,
 		      PROT_EXEC, MAP_FIXED | MAP_PRIVATE, fd, offset);
 	if (addr == MAP_FAILED) {
-		printk(UM_KERN_ERR "mapping mmap stub at 0x%lx failed, errno = %d\n",
-		       STUB_CODE, errno);
+		os_info("mapping mmap stub at 0x%lx failed, errno = %d\n",
+			STUB_CODE, errno);
 		exit(1);
 	}
 
-	if (stack != NULL) {
-		fd = phys_mapping(uml_to_phys(stack), &offset);
-		addr = mmap((void *) STUB_DATA,
-			    STUB_DATA_PAGES * UM_KERN_PAGE_SIZE, PROT_READ | PROT_WRITE,
-			    MAP_FIXED | MAP_SHARED, fd, offset);
-		if (addr == MAP_FAILED) {
-			printk(UM_KERN_ERR "mapping segfault stack at 0x%lx failed, errno = %d\n",
-			       STUB_DATA, errno);
-			exit(1);
-		}
+	fd = phys_mapping(uml_to_phys(stack), &offset);
+	addr = mmap((void *) STUB_DATA,
+		    STUB_DATA_PAGES * UM_KERN_PAGE_SIZE, PROT_READ | PROT_WRITE,
+		    MAP_FIXED | MAP_SHARED, fd, offset);
+	if (addr == MAP_FAILED) {
+		os_info("mapping segfault stack at 0x%lx failed, errno = %d\n",
+			STUB_DATA, errno);
+		exit(1);
 	}
-	if (stack != NULL) {
-		struct sigaction sa;
-
-		unsigned long v = STUB_CODE +
-				  (unsigned long) stub_segv_handler -
-				  (unsigned long) __syscall_stub_start;
-
-		set_sigstack((void *) STUB_DATA, STUB_DATA_PAGES * UM_KERN_PAGE_SIZE);
-		sigemptyset(&sa.sa_mask);
-		sa.sa_flags = SA_ONSTACK | SA_NODEFER | SA_SIGINFO;
-		sa.sa_sigaction = (void *) v;
-		sa.sa_restorer = NULL;
-		if (sigaction(SIGSEGV, &sa, NULL) < 0) {
-			printk(UM_KERN_ERR "%s - setting SIGSEGV handler failed - errno = %d\n",
-			       __func__, errno);
-			exit(1);
-		}
+
+	set_sigstack((void *) STUB_DATA, STUB_DATA_PAGES * UM_KERN_PAGE_SIZE);
+	sigemptyset(&sa.sa_mask);
+	sa.sa_flags = SA_ONSTACK | SA_NODEFER | SA_SIGINFO;
+	sa.sa_sigaction = (void *) segv_handler;
+	sa.sa_restorer = NULL;
+	if (sigaction(SIGSEGV, &sa, NULL) < 0) {
+		os_info("%s - setting SIGSEGV handler failed - errno = %d\n",
+			__func__, errno);
+		exit(1);
 	}
 
 	kill(os_getpid(), SIGSTOP);
@@ -298,7 +256,7 @@ int kill_userspace_mm[NR_CPUS];
 
 /**
  * start_userspace() - prepare a new userspace process
- * @stub_stack:	pointer to the stub stack. Can be NULL, if? FIXME:
+ * @stub_stack:	pointer to the stub stack.
  *
  * Setups a new temporary stack page that is used while userspace_tramp() runs
  * Clones the kernel process into a new userspace process, with FDs only.
@@ -355,10 +313,10 @@ int start_userspace(unsigned long stub_stack)
 		goto out_kill;
 	}
 
-	if (ptrace(PTRACE_OLDSETOPTIONS, pid, NULL,
+	if (ptrace(PTRACE_SETOPTIONS, pid, NULL,
 		   (void *) PTRACE_O_TRACESYSGOOD) < 0) {
 		err = -errno;
-		printk(UM_KERN_ERR "%s : PTRACE_OLDSETOPTIONS failed, errno = %d\n",
+		printk(UM_KERN_ERR "%s : PTRACE_SETOPTIONS failed, errno = %d\n",
 		       __func__, errno);
 		goto out_kill;
 	}
@@ -380,8 +338,6 @@ int start_userspace(unsigned long stub_stack)
 void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs)
 {
 	int err, status, op, pid = userspace_pid[0];
-	/* To prevent races if using_sysemu changes under us.*/
-	int local_using_sysemu;
 	siginfo_t si;
 
 	/* Handle any immediate reschedules or signals */
@@ -411,11 +367,10 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs)
 			fatal_sigsegv();
 		}
 
-		/* Now we set local_using_sysemu to be used for one loop */
-		local_using_sysemu = get_using_sysemu();
-
-		op = SELECT_PTRACE_OPERATION(local_using_sysemu,
-					     singlestepping(NULL));
+		if (singlestepping())
+			op = PTRACE_SYSEMU_SINGLESTEP;
+		else
+			op = PTRACE_SYSEMU;
 
 		if (ptrace(op, pid, 0, 0)) {
 			printk(UM_KERN_ERR "%s - ptrace continue failed, op = %d, errno = %d\n",
@@ -474,7 +429,7 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs)
 				else handle_segv(pid, regs, aux_fp_regs);
 				break;
 			case SIGTRAP + 0x80:
-			        handle_trap(pid, regs, local_using_sysemu);
+				handle_trap(pid, regs);
 				break;
 			case SIGTRAP:
 				relay_signal(SIGTRAP, (struct siginfo *)&si, regs);
@@ -597,10 +552,10 @@ int copy_context_skas0(unsigned long new_stack, int pid)
 		goto out_kill;
 	}
 
-	if (ptrace(PTRACE_OLDSETOPTIONS, pid, NULL,
+	if (ptrace(PTRACE_SETOPTIONS, pid, NULL,
 		   (void *)PTRACE_O_TRACESYSGOOD) < 0) {
 		err = -errno;
-		printk(UM_KERN_ERR "%s : PTRACE_OLDSETOPTIONS failed, errno = %d\n",
+		printk(UM_KERN_ERR "%s : PTRACE_SETOPTIONS failed, errno = %d\n",
 		       __func__, errno);
 		goto out_kill;
 	}
diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c
index e3ee4db58b40..8b0e98ab842c 100644
--- a/arch/um/os-Linux/start_up.c
+++ b/arch/um/os-Linux/start_up.c
@@ -112,102 +112,32 @@ static int start_ptraced_child(void)
 	return pid;
 }
 
-/* When testing for SYSEMU support, if it is one of the broken versions, we
- * must just avoid using sysemu, not panic, but only if SYSEMU features are
- * broken.
- * So only for SYSEMU features we test mustpanic, while normal host features
- * must work anyway!
- */
-static int stop_ptraced_child(int pid, int exitcode, int mustexit)
+static void stop_ptraced_child(int pid, int exitcode)
 {
-	int status, n, ret = 0;
+	int status, n;
+
+	if (ptrace(PTRACE_CONT, pid, 0, 0) < 0)
+		fatal_perror("stop_ptraced_child : ptrace failed");
 
-	if (ptrace(PTRACE_CONT, pid, 0, 0) < 0) {
-		perror("stop_ptraced_child : ptrace failed");
-		return -1;
-	}
 	CATCH_EINTR(n = waitpid(pid, &status, 0));
 	if (!WIFEXITED(status) || (WEXITSTATUS(status) != exitcode)) {
 		int exit_with = WEXITSTATUS(status);
-		if (exit_with == 2)
-			non_fatal("check_ptrace : child exited with status 2. "
-				  "\nDisabling SYSEMU support.\n");
-		non_fatal("check_ptrace : child exited with exitcode %d, while "
-			  "expecting %d; status 0x%x\n", exit_with,
-			  exitcode, status);
-		if (mustexit)
-			exit(1);
-		ret = -1;
+		fatal("stop_ptraced_child : child exited with exitcode %d, "
+		      "while expecting %d; status 0x%x\n", exit_with,
+		      exitcode, status);
 	}
-
-	return ret;
-}
-
-/* Changed only during early boot */
-static int force_sysemu_disabled = 0;
-
-static int __init nosysemu_cmd_param(char *str, int* add)
-{
-	force_sysemu_disabled = 1;
-	return 0;
 }
 
-__uml_setup("nosysemu", nosysemu_cmd_param,
-"nosysemu\n"
-"    Turns off syscall emulation patch for ptrace (SYSEMU).\n"
-"    SYSEMU is a performance-patch introduced by Laurent Vivier. It changes\n"
-"    behaviour of ptrace() and helps reduce host context switch rates.\n"
-"    To make it work, you need a kernel patch for your host, too.\n"
-"    See http://perso.wanadoo.fr/laurent.vivier/UML/ for further \n"
-"    information.\n\n");
-
 static void __init check_sysemu(void)
 {
-	unsigned long regs[MAX_REG_NR];
 	int pid, n, status, count=0;
 
-	os_info("Checking syscall emulation patch for ptrace...");
-	sysemu_supported = 0;
-	pid = start_ptraced_child();
-
-	if (ptrace(PTRACE_SYSEMU, pid, 0, 0) < 0)
-		goto fail;
-
-	CATCH_EINTR(n = waitpid(pid, &status, WUNTRACED));
-	if (n < 0)
-		fatal_perror("check_sysemu : wait failed");
-	if (!WIFSTOPPED(status) || (WSTOPSIG(status) != SIGTRAP))
-		fatal("check_sysemu : expected SIGTRAP, got status = %d\n",
-		      status);
-
-	if (ptrace(PTRACE_GETREGS, pid, 0, regs) < 0)
-		fatal_perror("check_sysemu : PTRACE_GETREGS failed");
-	if (PT_SYSCALL_NR(regs) != __NR_getpid) {
-		non_fatal("check_sysemu got system call number %d, "
-			  "expected %d...", PT_SYSCALL_NR(regs), __NR_getpid);
-		goto fail;
-	}
-
-	n = ptrace(PTRACE_POKEUSER, pid, PT_SYSCALL_RET_OFFSET, os_getpid());
-	if (n < 0) {
-		non_fatal("check_sysemu : failed to modify system call "
-			  "return");
-		goto fail;
-	}
-
-	if (stop_ptraced_child(pid, 0, 0) < 0)
-		goto fail_stopped;
-
-	sysemu_supported = 1;
-	os_info("OK\n");
-	set_using_sysemu(!force_sysemu_disabled);
-
-	os_info("Checking advanced syscall emulation patch for ptrace...");
+	os_info("Checking syscall emulation for ptrace...");
 	pid = start_ptraced_child();
 
-	if ((ptrace(PTRACE_OLDSETOPTIONS, pid, 0,
+	if ((ptrace(PTRACE_SETOPTIONS, pid, 0,
 		   (void *) PTRACE_O_TRACESYSGOOD) < 0))
-		fatal_perror("check_sysemu: PTRACE_OLDSETOPTIONS failed");
+		fatal_perror("check_sysemu: PTRACE_SETOPTIONS failed");
 
 	while (1) {
 		count++;
@@ -240,20 +170,15 @@ static void __init check_sysemu(void)
 			goto fail;
 		}
 	}
-	if (stop_ptraced_child(pid, 0, 0) < 0)
-		goto fail_stopped;
+	stop_ptraced_child(pid, 0);
 
-	sysemu_supported = 2;
 	os_info("OK\n");
 
-	if (!force_sysemu_disabled)
-		set_using_sysemu(sysemu_supported);
 	return;
 
 fail:
-	stop_ptraced_child(pid, 1, 0);
-fail_stopped:
-	non_fatal("missing\n");
+	stop_ptraced_child(pid, 1);
+	fatal("missing\n");
 }
 
 static void __init check_ptrace(void)
@@ -263,9 +188,9 @@ static void __init check_ptrace(void)
 	os_info("Checking that ptrace can change system call numbers...");
 	pid = start_ptraced_child();
 
-	if ((ptrace(PTRACE_OLDSETOPTIONS, pid, 0,
+	if ((ptrace(PTRACE_SETOPTIONS, pid, 0,
 		   (void *) PTRACE_O_TRACESYSGOOD) < 0))
-		fatal_perror("check_ptrace: PTRACE_OLDSETOPTIONS failed");
+		fatal_perror("check_ptrace: PTRACE_SETOPTIONS failed");
 
 	while (1) {
 		if (ptrace(PTRACE_SYSCALL, pid, 0, 0) < 0)
@@ -291,7 +216,7 @@ static void __init check_ptrace(void)
 			break;
 		}
 	}
-	stop_ptraced_child(pid, 0, 1);
+	stop_ptraced_child(pid, 0);
 	os_info("OK\n");
 	check_sysemu();
 }
@@ -370,7 +295,7 @@ void __init os_early_checks(void)
 	pid = start_ptraced_child();
 	if (init_pid_registers(pid))
 		fatal("Failed to initialize default registers");
-	stop_ptraced_child(pid, 1, 1);
+	stop_ptraced_child(pid, 1);
 }
 
 int __init parse_iomem(char *str, int *add)
diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c
index fc0f2a9dee5a..1dca4ffbd572 100644
--- a/arch/um/os-Linux/util.c
+++ b/arch/um/os-Linux/util.c
@@ -173,23 +173,38 @@ __uml_setup("quiet", quiet_cmd_param,
 "quiet\n"
 "    Turns off information messages during boot.\n\n");
 
+/*
+ * The os_info/os_warn functions will be called by helper threads. These
+ * have a very limited stack size and using the libc formatting functions
+ * may overflow the stack.
+ * So pull in the kernel vscnprintf and use that instead with a fixed
+ * on-stack buffer.
+ */
+int vscnprintf(char *buf, size_t size, const char *fmt, va_list args);
+
 void os_info(const char *fmt, ...)
 {
+	char buf[256];
 	va_list list;
+	int len;
 
 	if (quiet_info)
 		return;
 
 	va_start(list, fmt);
-	vfprintf(stderr, fmt, list);
+	len = vscnprintf(buf, sizeof(buf), fmt, list);
+	fwrite(buf, len, 1, stderr);
 	va_end(list);
 }
 
 void os_warn(const char *fmt, ...)
 {
+	char buf[256];
 	va_list list;
+	int len;
 
 	va_start(list, fmt);
-	vfprintf(stderr, fmt, list);
+	len = vscnprintf(buf, sizeof(buf), fmt, list);
+	fwrite(buf, len, 1, stderr);
 	va_end(list);
 }
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 53f2e7797b1d..5edec175b9bf 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -59,6 +59,7 @@ config X86
 	#
 	select ACPI_LEGACY_TABLES_LOOKUP	if ACPI
 	select ACPI_SYSTEM_POWER_STATES_SUPPORT	if ACPI
+	select ACPI_HOTPLUG_CPU			if ACPI_PROCESSOR && HOTPLUG_CPU
 	select ARCH_32BIT_OFF_T			if X86_32
 	select ARCH_CLOCKSOURCE_INIT
 	select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE
@@ -71,6 +72,7 @@ config X86
 	select ARCH_HAS_CACHE_LINE_SIZE
 	select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
 	select ARCH_HAS_CPU_FINALIZE_INIT
+	select ARCH_HAS_CPU_PASID		if IOMMU_SVA
 	select ARCH_HAS_CURRENT_STACK_POINTER
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEBUG_VM_PGTABLE	if !X86_PAE
@@ -148,6 +150,7 @@ config X86
 	select GENERIC_CLOCKEVENTS_MIN_ADJUST
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_CPU_AUTOPROBE
+	select GENERIC_CPU_DEVICES
 	select GENERIC_CPU_VULNERABILITIES
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_ENTRY
@@ -1967,6 +1970,11 @@ config INTEL_TDX_HOST
 	depends on CPU_SUP_INTEL
 	depends on X86_64
 	depends on KVM_INTEL
+	depends on X86_X2APIC
+	select ARCH_KEEP_MEMBLOCK
+	depends on CONTIG_ALLOC
+	depends on !KEXEC_CORE
+	depends on X86_MCE
 	help
 	  Intel Trust Domain Extensions (TDX) protects guest VMs from malicious
 	  host and certain physical attacks.  This option enables necessary TDX
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index b9224cf2ee4d..2a7279d80460 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -379,7 +379,7 @@ config X86_CMOV
 config X86_MINIMUM_CPU_FAMILY
 	int
 	default "64" if X86_64
-	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8)
+	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCORE2 || MK7 || MK8)
 	default "5" if X86_32 && X86_CMPXCHG64
 	default "4"
 
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 1a068de12a56..da8f3caf2781 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -112,13 +112,13 @@ ifeq ($(CONFIG_X86_32),y)
         # temporary until string.h is fixed
         KBUILD_CFLAGS += -ffreestanding
 
-	ifeq ($(CONFIG_STACKPROTECTOR),y)
-		ifeq ($(CONFIG_SMP),y)
+    ifeq ($(CONFIG_STACKPROTECTOR),y)
+        ifeq ($(CONFIG_SMP),y)
 			KBUILD_CFLAGS += -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard
-		else
+        else
 			KBUILD_CFLAGS += -mstack-protector-guard=global
-		endif
-	endif
+        endif
+    endif
 else
         BITS := 64
         UTS_MACHINE := x86_64
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index b2771710ed98..a1bbedd989e4 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -106,8 +106,7 @@ extra_header_fields:
 	.word	0				# MinorSubsystemVersion
 	.long	0				# Win32VersionValue
 
-	.long	setup_size + ZO__end + pecompat_vsize
-						# SizeOfImage
+	.long	setup_size + ZO__end		# SizeOfImage
 
 	.long	salign				# SizeOfHeaders
 	.long	0				# CheckSum
@@ -143,7 +142,7 @@ section_table:
 	.ascii	".setup"
 	.byte	0
 	.byte	0
-	.long	setup_size - salign 		# VirtualSize
+	.long	pecompat_fstart - salign 	# VirtualSize
 	.long	salign				# VirtualAddress
 	.long	pecompat_fstart - salign	# SizeOfRawData
 	.long	salign				# PointerToRawData
@@ -156,8 +155,8 @@ section_table:
 #ifdef CONFIG_EFI_MIXED
 	.asciz	".compat"
 
-	.long	8				# VirtualSize
-	.long	setup_size + ZO__end		# VirtualAddress
+	.long	pecompat_fsize			# VirtualSize
+	.long	pecompat_fstart			# VirtualAddress
 	.long	pecompat_fsize			# SizeOfRawData
 	.long	pecompat_fstart			# PointerToRawData
 
@@ -172,17 +171,16 @@ section_table:
 	 * modes this image supports.
 	 */
 	.pushsection ".pecompat", "a", @progbits
-	.balign	falign
-	.set	pecompat_vsize, salign
+	.balign	salign
 	.globl	pecompat_fstart
 pecompat_fstart:
 	.byte	0x1				# Version
 	.byte	8				# Size
 	.word	IMAGE_FILE_MACHINE_I386		# PE machine type
 	.long	setup_size + ZO_efi32_pe_entry	# Entrypoint
+	.byte	0x0				# Sentinel
 	.popsection
 #else
-	.set	pecompat_vsize, 0
 	.set	pecompat_fstart, setup_size
 #endif
 	.ascii	".text"
diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld
index 83bb7efad8ae..3a2d1360abb0 100644
--- a/arch/x86/boot/setup.ld
+++ b/arch/x86/boot/setup.ld
@@ -24,6 +24,9 @@ SECTIONS
 	.text		: { *(.text .text.*) }
 	.text32		: { *(.text32) }
 
+	.pecompat	: { *(.pecompat) }
+	PROVIDE(pecompat_fsize = setup_size - pecompat_fstart);
+
 	. = ALIGN(16);
 	.rodata		: { *(.rodata*) }
 
@@ -36,9 +39,6 @@ SECTIONS
 	. = ALIGN(16);
 	.data		: { *(.data*) }
 
-	.pecompat	: { *(.pecompat) }
-	PROVIDE(pecompat_fsize = setup_size - pecompat_fstart);
-
 	.signature	: {
 		setup_sig = .;
 		LONG(0x5a5aaa55)
diff --git a/arch/x86/coco/tdx/tdx-shared.c b/arch/x86/coco/tdx/tdx-shared.c
index 78e413269791..1655aa56a0a5 100644
--- a/arch/x86/coco/tdx/tdx-shared.c
+++ b/arch/x86/coco/tdx/tdx-shared.c
@@ -22,13 +22,13 @@ static unsigned long try_accept_one(phys_addr_t start, unsigned long len,
 	 */
 	switch (pg_level) {
 	case PG_LEVEL_4K:
-		page_size = 0;
+		page_size = TDX_PS_4K;
 		break;
 	case PG_LEVEL_2M:
-		page_size = 1;
+		page_size = TDX_PS_2M;
 		break;
 	case PG_LEVEL_1G:
-		page_size = 2;
+		page_size = TDX_PS_1G;
 		break;
 	default:
 		return 0;
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index 8c8d38f0cb1d..003379049924 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -6,6 +6,9 @@
 #include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/msr-index.h>
+#include <asm/unwind_hints.h>
+#include <asm/segment.h>
+#include <asm/cache.h>
 
 .pushsection .noinstr.text, "ax"
 
@@ -20,3 +23,23 @@ SYM_FUNC_END(entry_ibpb)
 EXPORT_SYMBOL_GPL(entry_ibpb);
 
 .popsection
+
+/*
+ * Define the VERW operand that is disguised as entry code so that
+ * it can be referenced with KPTI enabled. This ensure VERW can be
+ * used late in exit-to-user path after page tables are switched.
+ */
+.pushsection .entry.text, "ax"
+
+.align L1_CACHE_BYTES, 0xcc
+SYM_CODE_START_NOALIGN(mds_verw_sel)
+	UNWIND_HINT_UNDEFINED
+	ANNOTATE_NOENDBR
+	.word __KERNEL_DS
+.align L1_CACHE_BYTES, 0xcc
+SYM_CODE_END(mds_verw_sel);
+/* For KVM */
+EXPORT_SYMBOL_GPL(mds_verw_sel);
+
+.popsection
+
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index c73047bf9f4b..fba427646805 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -885,6 +885,7 @@ SYM_FUNC_START(entry_SYSENTER_32)
 	BUG_IF_WRONG_CR3 no_user_check=1
 	popfl
 	popl	%eax
+	CLEAR_CPU_BUFFERS
 
 	/*
 	 * Return back to the vDSO, which will pop ecx and edx.
@@ -954,6 +955,7 @@ restore_all_switch_stack:
 
 	/* Restore user state */
 	RESTORE_REGS pop=4			# skip orig_eax/error_code
+	CLEAR_CPU_BUFFERS
 .Lirq_return:
 	/*
 	 * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
@@ -1146,6 +1148,7 @@ SYM_CODE_START(asm_exc_nmi)
 
 	/* Not on SYSENTER stack. */
 	call	exc_nmi
+	CLEAR_CPU_BUFFERS
 	jmp	.Lnmi_return
 
 .Lnmi_from_sysenter_stack:
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index c40f89ab1b4c..9bb485977629 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -161,6 +161,7 @@ syscall_return_via_sysret:
 SYM_INNER_LABEL(entry_SYSRETQ_unsafe_stack, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
 	swapgs
+	CLEAR_CPU_BUFFERS
 	sysretq
 SYM_INNER_LABEL(entry_SYSRETQ_end, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
@@ -573,6 +574,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 
 .Lswapgs_and_iret:
 	swapgs
+	CLEAR_CPU_BUFFERS
 	/* Assert that the IRET frame indicates user mode. */
 	testb	$3, 8(%rsp)
 	jnz	.Lnative_iret
@@ -723,6 +725,8 @@ native_irq_return_ldt:
 	 */
 	popq	%rax				/* Restore user RAX */
 
+	CLEAR_CPU_BUFFERS
+
 	/*
 	 * RSP now points to an ordinary IRET frame, except that the page
 	 * is read-only and RSP[31:16] are preloaded with the userspace
@@ -1450,6 +1454,12 @@ nmi_restore:
 	movq	$0, 5*8(%rsp)		/* clear "NMI executing" */
 
 	/*
+	 * Skip CLEAR_CPU_BUFFERS here, since it only helps in rare cases like
+	 * NMI in kernel after user state is restored. For an unprivileged user
+	 * these conditions are hard to meet.
+	 */
+
+	/*
 	 * iretq reads the "iret" frame and exits the NMI stack in a
 	 * single instruction.  We are returning to kernel mode, so this
 	 * cannot result in a fault.  Similarly, we don't need to worry
@@ -1466,6 +1476,7 @@ SYM_CODE_START(entry_SYSCALL32_ignore)
 	UNWIND_HINT_END_OF_STACK
 	ENDBR
 	mov	$-ENOSYS, %eax
+	CLEAR_CPU_BUFFERS
 	sysretl
 SYM_CODE_END(entry_SYSCALL32_ignore)
 
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index de94e2e84ecc..eabf48c4d4b4 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -270,6 +270,7 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_unsafe_stack, SYM_L_GLOBAL)
 	xorl	%r9d, %r9d
 	xorl	%r10d, %r10d
 	swapgs
+	CLEAR_CPU_BUFFERS
 	sysretl
 SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c
index 96e6c51515f5..cf1b78cb2d04 100644
--- a/arch/x86/hyperv/hv_vtl.c
+++ b/arch/x86/hyperv/hv_vtl.c
@@ -16,6 +16,11 @@
 extern struct boot_params boot_params;
 static struct real_mode_header hv_vtl_real_mode_header;
 
+static bool __init hv_vtl_msi_ext_dest_id(void)
+{
+	return true;
+}
+
 void __init hv_vtl_init_platform(void)
 {
 	pr_info("Linux runs in Hyper-V Virtual Trust Level\n");
@@ -38,6 +43,8 @@ void __init hv_vtl_init_platform(void)
 	x86_platform.legacy.warm_reset = 0;
 	x86_platform.legacy.reserve_bios_regions = 0;
 	x86_platform.legacy.devices.pnpbios = 0;
+
+	x86_init.hyper.msi_ext_dest_id = hv_vtl_msi_ext_dest_id;
 }
 
 static inline u64 hv_vtl_system_desc_base(struct ldttss_desc *desc)
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index 7dcbf153ad72..768d73de0d09 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -15,6 +15,7 @@
 #include <asm/io.h>
 #include <asm/coco.h>
 #include <asm/mem_encrypt.h>
+#include <asm/set_memory.h>
 #include <asm/mshyperv.h>
 #include <asm/hypervisor.h>
 #include <asm/mtrr.h>
@@ -503,6 +504,31 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[],
 }
 
 /*
+ * When transitioning memory between encrypted and decrypted, the caller
+ * of set_memory_encrypted() or set_memory_decrypted() is responsible for
+ * ensuring that the memory isn't in use and isn't referenced while the
+ * transition is in progress.  The transition has multiple steps, and the
+ * memory is in an inconsistent state until all steps are complete. A
+ * reference while the state is inconsistent could result in an exception
+ * that can't be cleanly fixed up.
+ *
+ * But the Linux kernel load_unaligned_zeropad() mechanism could cause a
+ * stray reference that can't be prevented by the caller, so Linux has
+ * specific code to handle this case. But when the #VC and #VE exceptions
+ * routed to a paravisor, the specific code doesn't work. To avoid this
+ * problem, mark the pages as "not present" while the transition is in
+ * progress. If load_unaligned_zeropad() causes a stray reference, a normal
+ * page fault is generated instead of #VC or #VE, and the page-fault-based
+ * handlers for load_unaligned_zeropad() resolve the reference.  When the
+ * transition is complete, hv_vtom_set_host_visibility() marks the pages
+ * as "present" again.
+ */
+static bool hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc)
+{
+	return !set_memory_np(kbuffer, pagecount);
+}
+
+/*
  * hv_vtom_set_host_visibility - Set specified memory visible to host.
  *
  * In Isolation VM, all guest memory is encrypted from host and guest
@@ -515,16 +541,28 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo
 	enum hv_mem_host_visibility visibility = enc ?
 			VMBUS_PAGE_NOT_VISIBLE : VMBUS_PAGE_VISIBLE_READ_WRITE;
 	u64 *pfn_array;
+	phys_addr_t paddr;
+	void *vaddr;
 	int ret = 0;
 	bool result = true;
 	int i, pfn;
 
 	pfn_array = kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
-	if (!pfn_array)
-		return false;
+	if (!pfn_array) {
+		result = false;
+		goto err_set_memory_p;
+	}
 
 	for (i = 0, pfn = 0; i < pagecount; i++) {
-		pfn_array[pfn] = virt_to_hvpfn((void *)kbuffer + i * HV_HYP_PAGE_SIZE);
+		/*
+		 * Use slow_virt_to_phys() because the PRESENT bit has been
+		 * temporarily cleared in the PTEs.  slow_virt_to_phys() works
+		 * without the PRESENT bit while virt_to_hvpfn() or similar
+		 * does not.
+		 */
+		vaddr = (void *)kbuffer + (i * HV_HYP_PAGE_SIZE);
+		paddr = slow_virt_to_phys(vaddr);
+		pfn_array[pfn] = paddr >> HV_HYP_PAGE_SHIFT;
 		pfn++;
 
 		if (pfn == HV_MAX_MODIFY_GPA_REP_COUNT || i == pagecount - 1) {
@@ -538,14 +576,30 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo
 		}
 	}
 
- err_free_pfn_array:
+err_free_pfn_array:
 	kfree(pfn_array);
+
+err_set_memory_p:
+	/*
+	 * Set the PTE PRESENT bits again to revert what hv_vtom_clear_present()
+	 * did. Do this even if there is an error earlier in this function in
+	 * order to avoid leaving the memory range in a "broken" state. Setting
+	 * the PRESENT bits shouldn't fail, but return an error if it does.
+	 */
+	if (set_memory_p(kbuffer, pagecount))
+		result = false;
+
 	return result;
 }
 
 static bool hv_vtom_tlb_flush_required(bool private)
 {
-	return true;
+	/*
+	 * Since hv_vtom_clear_present() marks the PTEs as "not present"
+	 * and flushes the TLB, they can't be in the TLB. That makes the
+	 * flush controlled by this function redundant, so return "false".
+	 */
+	return false;
 }
 
 static bool hv_vtom_cache_flush_required(void)
@@ -608,6 +662,7 @@ void __init hv_vtom_init(void)
 	x86_platform.hyper.is_private_mmio = hv_is_private_mmio;
 	x86_platform.guest.enc_cache_flush_required = hv_vtom_cache_flush_required;
 	x86_platform.guest.enc_tlb_flush_required = hv_vtom_tlb_flush_required;
+	x86_platform.guest.enc_status_change_prepare = hv_vtom_clear_present;
 	x86_platform.guest.enc_status_change_finish = hv_vtom_set_host_visibility;
 
 	/* Set WB as the default cache mode. */
diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h
index 6ae2d16a7613..76c310b19b11 100644
--- a/arch/x86/include/asm/coco.h
+++ b/arch/x86/include/asm/coco.h
@@ -10,13 +10,14 @@ enum cc_vendor {
 	CC_VENDOR_INTEL,
 };
 
-extern enum cc_vendor cc_vendor;
-
 #ifdef CONFIG_ARCH_HAS_CC_PLATFORM
+extern enum cc_vendor cc_vendor;
 void cc_set_mask(u64 mask);
 u64 cc_mkenc(u64 val);
 u64 cc_mkdec(u64 val);
 #else
+#define cc_vendor (CC_VENDOR_NONE)
+
 static inline u64 cc_mkenc(u64 val)
 {
 	return val;
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index fecc4fe1d68a..f8f9a9b79395 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -23,10 +23,6 @@ static inline void prefill_possible_map(void) {}
 
 #endif /* CONFIG_SMP */
 
-struct x86_cpu {
-	struct cpu cpu;
-};
-
 #ifdef CONFIG_HOTPLUG_CPU
 extern void soft_restart_cpu(void);
 #endif
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index a26bebbdff87..a1273698fc43 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -168,7 +168,7 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
  */
 static __always_inline bool _static_cpu_has(u16 bit)
 {
-	asm_volatile_goto(
+	asm goto(
 		ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]")
 		".pushsection .altinstr_aux,\"ax\"\n"
 		"6:\n"
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 632c26cdeeda..2b62cdd8dd12 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -81,10 +81,8 @@
 #define X86_FEATURE_K6_MTRR		( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
 #define X86_FEATURE_CYRIX_ARR		( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
 #define X86_FEATURE_CENTAUR_MCR		( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
-
-/* CPU types for specific tunings: */
 #define X86_FEATURE_K8			( 3*32+ 4) /* "" Opteron, Athlon64 */
-/* FREE, was #define X86_FEATURE_K7			( 3*32+ 5) "" Athlon */
+#define X86_FEATURE_ZEN5		( 3*32+ 5) /* "" CPU based on Zen5 microarchitecture */
 #define X86_FEATURE_P3			( 3*32+ 6) /* "" P3 */
 #define X86_FEATURE_P4			( 3*32+ 7) /* "" P4 */
 #define X86_FEATURE_CONSTANT_TSC	( 3*32+ 8) /* TSC ticks at a constant rate */
@@ -97,7 +95,7 @@
 #define X86_FEATURE_SYSENTER32		( 3*32+15) /* "" sysenter in IA32 userspace */
 #define X86_FEATURE_REP_GOOD		( 3*32+16) /* REP microcode works well */
 #define X86_FEATURE_AMD_LBR_V2		( 3*32+17) /* AMD Last Branch Record Extension Version 2 */
-/* FREE, was #define X86_FEATURE_LFENCE_RDTSC		( 3*32+18) "" LFENCE synchronizes RDTSC */
+#define X86_FEATURE_CLEAR_CPU_BUF	( 3*32+18) /* "" Clear CPU buffers using VERW */
 #define X86_FEATURE_ACC_POWER		( 3*32+19) /* AMD Accumulated Power Mechanism */
 #define X86_FEATURE_NOPL		( 3*32+20) /* The NOPL (0F 1F) instructions */
 #define X86_FEATURE_ALWAYS		( 3*32+21) /* "" Always-present feature */
@@ -198,6 +196,7 @@
 #define X86_FEATURE_CAT_L3		( 7*32+ 4) /* Cache Allocation Technology L3 */
 #define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
 #define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_TDX_HOST_PLATFORM	( 7*32+ 7) /* Platform supports being a TDX host */
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_XCOMPACTED		( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */
@@ -499,6 +498,7 @@
 #define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
 #define X86_BUG_SMT_RSB			X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */
 #define X86_BUG_GDS			X86_BUG(30) /* CPU is affected by Gather Data Sampling */
+#define X86_BUG_TDX_PW_MCE		X86_BUG(31) /* CPU may incur #MC if non-TD software does partial write to TDX private memory */
 
 /* BUG word 2 */
 #define X86_BUG_SRSO			X86_BUG(1*32 + 0) /* AMD SRSO bug */
diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h
index ce8f50192ae3..7e523bb3d2d3 100644
--- a/arch/x86/include/asm/entry-common.h
+++ b/arch/x86/include/asm/entry-common.h
@@ -91,7 +91,6 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 
 static __always_inline void arch_exit_to_user_mode(void)
 {
-	mds_user_clear_cpu_buffers();
 	amd_clear_divider();
 }
 #define arch_exit_to_user_mode arch_exit_to_user_mode
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 197316121f04..b65e9c46b922 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -162,6 +162,8 @@
 #define INTEL_FAM6_ATOM_CRESTMONT_X	0xAF /* Sierra Forest */
 #define INTEL_FAM6_ATOM_CRESTMONT	0xB6 /* Grand Ridge */
 
+#define INTEL_FAM6_ATOM_DARKMONT_X	0xDD /* Clearwater Forest */
+
 /* Xeon Phi */
 
 #define INTEL_FAM6_XEON_PHI_KNL		0x57 /* Knights Landing */
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 071572e23d3a..cbbef32517f0 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -24,7 +24,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:"
+	asm goto("1:"
 		"jmp %l[l_yes] # objtool NOPs this \n\t"
 		JUMP_TABLE_ENTRY
 		: :  "i" (key), "i" (2 | branch) : : l_yes);
@@ -38,7 +38,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch)
 {
-	asm_volatile_goto("1:"
+	asm goto("1:"
 		".byte " __stringify(BYTES_NOP5) "\n\t"
 		JUMP_TABLE_ENTRY
 		: :  "i" (key), "i" (branch) : : l_yes);
@@ -52,7 +52,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch)
 {
-	asm_volatile_goto("1:"
+	asm goto("1:"
 		"jmp %l[l_yes]\n\t"
 		JUMP_TABLE_ENTRY
 		: :  "i" (key), "i" (branch) : : l_yes);
diff --git a/arch/x86/include/asm/kmsan.h b/arch/x86/include/asm/kmsan.h
index 8fa6ac0e2d76..d91b37f5b4bb 100644
--- a/arch/x86/include/asm/kmsan.h
+++ b/arch/x86/include/asm/kmsan.h
@@ -64,6 +64,7 @@ static inline bool kmsan_virt_addr_valid(void *addr)
 {
 	unsigned long x = (unsigned long)addr;
 	unsigned long y = x - __START_KERNEL_map;
+	bool ret;
 
 	/* use the carry flag to determine if x was < __START_KERNEL_map */
 	if (unlikely(x > y)) {
@@ -79,7 +80,21 @@ static inline bool kmsan_virt_addr_valid(void *addr)
 			return false;
 	}
 
-	return pfn_valid(x >> PAGE_SHIFT);
+	/*
+	 * pfn_valid() relies on RCU, and may call into the scheduler on exiting
+	 * the critical section. However, this would result in recursion with
+	 * KMSAN. Therefore, disable preemption here, and re-enable preemption
+	 * below while suppressing reschedules to avoid recursion.
+	 *
+	 * Note, this sacrifices occasionally breaking scheduling guarantees.
+	 * Although, a kernel compiled with KMSAN has already given up on any
+	 * performance guarantees due to being heavily instrumented.
+	 */
+	preempt_disable();
+	ret = pfn_valid(x >> PAGE_SHIFT);
+	preempt_enable_no_resched();
+
+	return ret;
 }
 
 #endif /* !MODULE */
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 26b628d84594..378ed944b849 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -55,8 +55,10 @@ KVM_X86_OP(set_rflags)
 KVM_X86_OP(get_if_flag)
 KVM_X86_OP(flush_tlb_all)
 KVM_X86_OP(flush_tlb_current)
+#if IS_ENABLED(CONFIG_HYPERV)
 KVM_X86_OP_OPTIONAL(flush_remote_tlbs)
 KVM_X86_OP_OPTIONAL(flush_remote_tlbs_range)
+#endif
 KVM_X86_OP(flush_tlb_gva)
 KVM_X86_OP(flush_tlb_guest)
 KVM_X86_OP(vcpu_pre_run)
@@ -135,6 +137,7 @@ KVM_X86_OP(msr_filter_changed)
 KVM_X86_OP(complete_emulated_msr)
 KVM_X86_OP(vcpu_deliver_sipi_vector)
 KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
+KVM_X86_OP_OPTIONAL(get_untagged_addr)
 
 #undef KVM_X86_OP
 #undef KVM_X86_OP_OPTIONAL
diff --git a/arch/x86/include/asm/kvm-x86-pmu-ops.h b/arch/x86/include/asm/kvm-x86-pmu-ops.h
index 6c98f4bb4228..058bc636356a 100644
--- a/arch/x86/include/asm/kvm-x86-pmu-ops.h
+++ b/arch/x86/include/asm/kvm-x86-pmu-ops.h
@@ -22,7 +22,7 @@ KVM_X86_PMU_OP(get_msr)
 KVM_X86_PMU_OP(set_msr)
 KVM_X86_PMU_OP(refresh)
 KVM_X86_PMU_OP(init)
-KVM_X86_PMU_OP(reset)
+KVM_X86_PMU_OP_OPTIONAL(reset)
 KVM_X86_PMU_OP_OPTIONAL(deliver_pmi)
 KVM_X86_PMU_OP_OPTIONAL(cleanup)
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6711da000bb7..d271ba20a0b2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -133,7 +133,8 @@
 			  | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \
 			  | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \
 			  | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_VMXE \
-			  | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP))
+			  | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP \
+			  | X86_CR4_LAM_SUP))
 
 #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
 
@@ -500,8 +501,23 @@ struct kvm_pmc {
 	u8 idx;
 	bool is_paused;
 	bool intr;
+	/*
+	 * Base value of the PMC counter, relative to the *consumed* count in
+	 * the associated perf_event.  This value includes counter updates from
+	 * the perf_event and emulated_count since the last time the counter
+	 * was reprogrammed, but it is *not* the current value as seen by the
+	 * guest or userspace.
+	 *
+	 * The count is relative to the associated perf_event so that KVM
+	 * doesn't need to reprogram the perf_event every time the guest writes
+	 * to the counter.
+	 */
 	u64 counter;
-	u64 prev_counter;
+	/*
+	 * PMC events triggered by KVM emulation that haven't been fully
+	 * processed, i.e. haven't undergone overflow detection.
+	 */
+	u64 emulated_counter;
 	u64 eventsel;
 	struct perf_event *perf_event;
 	struct kvm_vcpu *vcpu;
@@ -937,8 +953,10 @@ struct kvm_vcpu_arch {
 	/* used for guest single stepping over the given code position */
 	unsigned long singlestep_rip;
 
+#ifdef CONFIG_KVM_HYPERV
 	bool hyperv_enabled;
 	struct kvm_vcpu_hv *hyperv;
+#endif
 #ifdef CONFIG_KVM_XEN
 	struct kvm_vcpu_xen xen;
 #endif
@@ -1095,6 +1113,7 @@ enum hv_tsc_page_status {
 	HV_TSC_PAGE_BROKEN,
 };
 
+#ifdef CONFIG_KVM_HYPERV
 /* Hyper-V emulation context */
 struct kvm_hv {
 	struct mutex hv_lock;
@@ -1125,9 +1144,11 @@ struct kvm_hv {
 	 */
 	unsigned int synic_auto_eoi_used;
 
-	struct hv_partition_assist_pg *hv_pa_pg;
 	struct kvm_hv_syndbg hv_syndbg;
+
+	bool xsaves_xsavec_checked;
 };
+#endif
 
 struct msr_bitmap_range {
 	u32 flags;
@@ -1136,6 +1157,7 @@ struct msr_bitmap_range {
 	unsigned long *bitmap;
 };
 
+#ifdef CONFIG_KVM_XEN
 /* Xen emulation context */
 struct kvm_xen {
 	struct mutex xen_lock;
@@ -1147,6 +1169,7 @@ struct kvm_xen {
 	struct idr evtchn_ports;
 	unsigned long poll_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)];
 };
+#endif
 
 enum kvm_irqchip_mode {
 	KVM_IRQCHIP_NONE,
@@ -1255,6 +1278,7 @@ enum kvm_apicv_inhibit {
 };
 
 struct kvm_arch {
+	unsigned long vm_type;
 	unsigned long n_used_mmu_pages;
 	unsigned long n_requested_mmu_pages;
 	unsigned long n_max_mmu_pages;
@@ -1347,8 +1371,13 @@ struct kvm_arch {
 	/* reads protected by irq_srcu, writes by irq_lock */
 	struct hlist_head mask_notifier_list;
 
+#ifdef CONFIG_KVM_HYPERV
 	struct kvm_hv hyperv;
+#endif
+
+#ifdef CONFIG_KVM_XEN
 	struct kvm_xen xen;
+#endif
 
 	bool backwards_tsc_observed;
 	bool boot_vcpu_runs_old_kvmclock;
@@ -1406,9 +1435,8 @@ struct kvm_arch {
 	 *	the MMU lock in read mode + RCU or
 	 *	the MMU lock in write mode
 	 *
-	 * For writes, this list is protected by:
-	 *	the MMU lock in read mode + the tdp_mmu_pages_lock or
-	 *	the MMU lock in write mode
+	 * For writes, this list is protected by tdp_mmu_pages_lock; see
+	 * below for the details.
 	 *
 	 * Roots will remain in the list until their tdp_mmu_root_count
 	 * drops to zero, at which point the thread that decremented the
@@ -1425,8 +1453,10 @@ struct kvm_arch {
 	 *  - possible_nx_huge_pages;
 	 *  - the possible_nx_huge_page_link field of kvm_mmu_page structs used
 	 *    by the TDP MMU
-	 * It is acceptable, but not necessary, to acquire this lock when
-	 * the thread holds the MMU lock in write mode.
+	 * Because the lock is only taken within the MMU lock, strictly
+	 * speaking it is redundant to acquire this lock when the thread
+	 * holds the MMU lock in write mode.  However it often simplifies
+	 * the code to do so.
 	 */
 	spinlock_t tdp_mmu_pages_lock;
 #endif /* CONFIG_X86_64 */
@@ -1441,6 +1471,7 @@ struct kvm_arch {
 #if IS_ENABLED(CONFIG_HYPERV)
 	hpa_t	hv_root_tdp;
 	spinlock_t hv_root_tdp_lock;
+	struct hv_partition_assist_pg *hv_pa_pg;
 #endif
 	/*
 	 * VM-scope maximum vCPU ID. Used to determine the size of structures
@@ -1613,9 +1644,11 @@ struct kvm_x86_ops {
 
 	void (*flush_tlb_all)(struct kvm_vcpu *vcpu);
 	void (*flush_tlb_current)(struct kvm_vcpu *vcpu);
+#if IS_ENABLED(CONFIG_HYPERV)
 	int  (*flush_remote_tlbs)(struct kvm *kvm);
 	int  (*flush_remote_tlbs_range)(struct kvm *kvm, gfn_t gfn,
 					gfn_t nr_pages);
+#endif
 
 	/*
 	 * Flush any TLB entries associated with the given GVA.
@@ -1761,6 +1794,8 @@ struct kvm_x86_ops {
 	 * Returns vCPU specific APICv inhibit reasons
 	 */
 	unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu);
+
+	gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags);
 };
 
 struct kvm_x86_nested_ops {
@@ -1824,6 +1859,7 @@ static inline struct kvm *kvm_arch_alloc_vm(void)
 #define __KVM_HAVE_ARCH_VM_FREE
 void kvm_arch_free_vm(struct kvm *kvm);
 
+#if IS_ENABLED(CONFIG_HYPERV)
 #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS
 static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 {
@@ -1835,6 +1871,15 @@ static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 }
 
 #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
+static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn,
+						   u64 nr_pages)
+{
+	if (!kvm_x86_ops.flush_remote_tlbs_range)
+		return -EOPNOTSUPP;
+
+	return static_call(kvm_x86_flush_remote_tlbs_range)(kvm, gfn, nr_pages);
+}
+#endif /* CONFIG_HYPERV */
 
 #define kvm_arch_pmi_in_guest(vcpu) \
 	((vcpu) && (vcpu)->arch.handling_intr_from_guest)
@@ -1848,6 +1893,9 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu);
 void kvm_mmu_init_vm(struct kvm *kvm);
 void kvm_mmu_uninit_vm(struct kvm *kvm);
 
+void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm,
+					    struct kvm_memory_slot *slot);
+
 void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu);
 void kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
@@ -2086,6 +2134,12 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd);
 void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level,
 		       int tdp_max_root_level, int tdp_huge_page_level);
 
+#ifdef CONFIG_KVM_PRIVATE_MEM
+#define kvm_arch_has_private_mem(kvm) ((kvm)->arch.vm_type != KVM_X86_DEFAULT_VM)
+#else
+#define kvm_arch_has_private_mem(kvm) false
+#endif
+
 static inline u16 kvm_read_ldt(void)
 {
 	u16 ldt;
@@ -2133,16 +2187,15 @@ enum {
 #define HF_SMM_MASK		(1 << 1)
 #define HF_SMM_INSIDE_NMI_MASK	(1 << 2)
 
-# define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
-# define KVM_ADDRESS_SPACE_NUM 2
+# define KVM_MAX_NR_ADDRESS_SPACES	2
+/* SMM is currently unsupported for guests with private memory. */
+# define kvm_arch_nr_memslot_as_ids(kvm) (kvm_arch_has_private_mem(kvm) ? 1 : 2)
 # define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
 # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
 #else
 # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0)
 #endif
 
-#define KVM_ARCH_WANT_MMU_NOTIFIER
-
 int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v);
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
 int kvm_cpu_has_extint(struct kvm_vcpu *v);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 737a52b89e64..f1bd7b91b3c6 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -541,6 +541,9 @@
 #define MSR_RELOAD_PMC0			0x000014c1
 #define MSR_RELOAD_FIXED_CTR0		0x00001309
 
+/* KeyID partitioning between MKTME and TDX */
+#define MSR_IA32_MKTME_KEYID_PARTITIONING	0x00000087
+
 /*
  * AMD64 MSRs. Not complete. See the architecture manual for a more
  * complete list.
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 262e65539f83..2aa52cab1e46 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -315,6 +315,17 @@
 #endif
 .endm
 
+/*
+ * Macro to execute VERW instruction that mitigate transient data sampling
+ * attacks such as MDS. On affected systems a microcode update overloaded VERW
+ * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF.
+ *
+ * Note: Only the memory operand variant of VERW clears the CPU buffers.
+ */
+.macro CLEAR_CPU_BUFFERS
+	ALTERNATIVE "", __stringify(verw _ASM_RIP(mds_verw_sel)), X86_FEATURE_CLEAR_CPU_BUF
+.endm
+
 #else /* __ASSEMBLY__ */
 
 #define ANNOTATE_RETPOLINE_SAFE					\
@@ -529,13 +540,14 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp);
 DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
-DECLARE_STATIC_KEY_FALSE(mds_user_clear);
 DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
 
 DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
 
 DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear);
 
+extern u16 mds_verw_sel;
+
 #include <asm/segment.h>
 
 /**
@@ -562,17 +574,6 @@ static __always_inline void mds_clear_cpu_buffers(void)
 }
 
 /**
- * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability
- *
- * Clear CPU buffers if the corresponding static key is enabled
- */
-static __always_inline void mds_user_clear_cpu_buffers(void)
-{
-	if (static_branch_likely(&mds_user_clear))
-		mds_clear_cpu_buffers();
-}
-
-/**
  * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability
  *
  * Clear CPU buffers if the corresponding static key is enabled
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index 4b081e0d3306..363266cbcada 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -13,7 +13,7 @@
 #define __GEN_RMWcc(fullop, _var, cc, clobbers, ...)			\
 ({									\
 	bool c = false;							\
-	asm_volatile_goto (fullop "; j" #cc " %l[cc_label]"		\
+	asm goto (fullop "; j" #cc " %l[cc_label]"		\
 			: : [var] "m" (_var), ## __VA_ARGS__		\
 			: clobbers : cc_label);				\
 	if (0) {							\
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index a5e89641bd2d..9aee31862b4a 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -47,6 +47,7 @@ int set_memory_uc(unsigned long addr, int numpages);
 int set_memory_wc(unsigned long addr, int numpages);
 int set_memory_wb(unsigned long addr, int numpages);
 int set_memory_np(unsigned long addr, int numpages);
+int set_memory_p(unsigned long addr, int numpages);
 int set_memory_4k(unsigned long addr, int numpages);
 int set_memory_encrypted(unsigned long addr, int numpages);
 int set_memory_decrypted(unsigned long addr, int numpages);
diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h
index ccce7ebd8677..fdfd41511b02 100644
--- a/arch/x86/include/asm/shared/tdx.h
+++ b/arch/x86/include/asm/shared/tdx.h
@@ -55,6 +55,12 @@
 	(TDX_RDX | TDX_RBX | TDX_RSI | TDX_RDI | TDX_R8  | TDX_R9  | \
 	 TDX_R10 | TDX_R11 | TDX_R12 | TDX_R13 | TDX_R14 | TDX_R15)
 
+/* TDX supported page sizes from the TDX module ABI. */
+#define TDX_PS_4K	0
+#define TDX_PS_2M	1
+#define TDX_PS_1G	2
+#define TDX_PS_NR	(TDX_PS_1G + 1)
+
 #ifndef __ASSEMBLY__
 
 #include <linux/compiler_attributes.h>
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index d6cd9344f6c7..48f8dd47cf68 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -205,7 +205,7 @@ static inline void clwb(volatile void *__p)
 #ifdef CONFIG_X86_USER_SHADOW_STACK
 static inline int write_user_shstk_64(u64 __user *addr, u64 val)
 {
-	asm_volatile_goto("1: wrussq %[val], (%[addr])\n"
+	asm goto("1: wrussq %[val], (%[addr])\n"
 			  _ASM_EXTABLE(1b, %l[fail])
 			  :: [addr] "r" (addr), [val] "r" (val)
 			  :: fail);
diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h
index 21f9407be5d3..7e88705e907f 100644
--- a/arch/x86/include/asm/syscall_wrapper.h
+++ b/arch/x86/include/asm/syscall_wrapper.h
@@ -58,12 +58,29 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
 		,,regs->di,,regs->si,,regs->dx				\
 		,,regs->r10,,regs->r8,,regs->r9)			\
 
+
+/* SYSCALL_PT_ARGS is Adapted from s390x */
+#define SYSCALL_PT_ARG6(m, t1, t2, t3, t4, t5, t6)			\
+	SYSCALL_PT_ARG5(m, t1, t2, t3, t4, t5), m(t6, (regs->bp))
+#define SYSCALL_PT_ARG5(m, t1, t2, t3, t4, t5)				\
+	SYSCALL_PT_ARG4(m, t1, t2, t3, t4),  m(t5, (regs->di))
+#define SYSCALL_PT_ARG4(m, t1, t2, t3, t4)				\
+	SYSCALL_PT_ARG3(m, t1, t2, t3),  m(t4, (regs->si))
+#define SYSCALL_PT_ARG3(m, t1, t2, t3)					\
+	SYSCALL_PT_ARG2(m, t1, t2), m(t3, (regs->dx))
+#define SYSCALL_PT_ARG2(m, t1, t2)					\
+	SYSCALL_PT_ARG1(m, t1), m(t2, (regs->cx))
+#define SYSCALL_PT_ARG1(m, t1) m(t1, (regs->bx))
+#define SYSCALL_PT_ARGS(x, ...) SYSCALL_PT_ARG##x(__VA_ARGS__)
+
+#define __SC_COMPAT_CAST(t, a)						\
+	(__typeof(__builtin_choose_expr(__TYPE_IS_L(t), 0, 0U)))	\
+	(unsigned int)a
+
 /* Mapping of registers to parameters for syscalls on i386 */
 #define SC_IA32_REGS_TO_ARGS(x, ...)					\
-	__MAP(x,__SC_ARGS						\
-	      ,,(unsigned int)regs->bx,,(unsigned int)regs->cx		\
-	      ,,(unsigned int)regs->dx,,(unsigned int)regs->si		\
-	      ,,(unsigned int)regs->di,,(unsigned int)regs->bp)
+	SYSCALL_PT_ARGS(x, __SC_COMPAT_CAST,				\
+			__MAP(x, __SC_TYPE, __VA_ARGS__))		\
 
 #define __SYS_STUB0(abi, name)						\
 	long __##abi##_##name(const struct pt_regs *regs);		\
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index f3d5305a60fc..eba178996d84 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -24,8 +24,16 @@
 #define TDX_SEAMCALL_GP			(TDX_SW_ERROR | X86_TRAP_GP)
 #define TDX_SEAMCALL_UD			(TDX_SW_ERROR | X86_TRAP_UD)
 
+/*
+ * TDX module SEAMCALL leaf function error codes
+ */
+#define TDX_SUCCESS		0ULL
+#define TDX_RND_NO_ENTROPY	0x8000020300000000ULL
+
 #ifndef __ASSEMBLY__
 
+#include <uapi/asm/mce.h>
+
 /*
  * Used by the #VE exception handler to gather the #VE exception
  * info from the TDX module. This is a software only structure
@@ -83,6 +91,36 @@ static inline long tdx_kvm_hypercall(unsigned int nr, unsigned long p1,
 u64 __seamcall(u64 fn, struct tdx_module_args *args);
 u64 __seamcall_ret(u64 fn, struct tdx_module_args *args);
 u64 __seamcall_saved_ret(u64 fn, struct tdx_module_args *args);
+void tdx_init(void);
+
+#include <asm/archrandom.h>
+
+typedef u64 (*sc_func_t)(u64 fn, struct tdx_module_args *args);
+
+static inline u64 sc_retry(sc_func_t func, u64 fn,
+			   struct tdx_module_args *args)
+{
+	int retry = RDRAND_RETRY_LOOPS;
+	u64 ret;
+
+	do {
+		ret = func(fn, args);
+	} while (ret == TDX_RND_NO_ENTROPY && --retry);
+
+	return ret;
+}
+
+#define seamcall(_fn, _args)		sc_retry(__seamcall, (_fn), (_args))
+#define seamcall_ret(_fn, _args)	sc_retry(__seamcall_ret, (_fn), (_args))
+#define seamcall_saved_ret(_fn, _args)	sc_retry(__seamcall_saved_ret, (_fn), (_args))
+int tdx_cpu_enable(void);
+int tdx_enable(void);
+const char *tdx_dump_mce_info(struct mce *m);
+#else
+static inline void tdx_init(void) { }
+static inline int tdx_cpu_enable(void) { return -ENODEV; }
+static inline int tdx_enable(void)  { return -ENODEV; }
+static inline const char *tdx_dump_mce_info(struct mce *m) { return NULL; }
 #endif	/* CONFIG_INTEL_TDX_HOST */
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 5c367c1290c3..237dc8cdd12b 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -133,7 +133,7 @@ extern int __get_user_bad(void);
 
 #ifdef CONFIG_X86_32
 #define __put_user_goto_u64(x, addr, label)			\
-	asm_volatile_goto("\n"					\
+	asm goto("\n"					\
 		     "1:	movl %%eax,0(%1)\n"		\
 		     "2:	movl %%edx,4(%1)\n"		\
 		     _ASM_EXTABLE_UA(1b, %l2)			\
@@ -295,7 +295,7 @@ do {									\
 } while (0)
 
 #define __get_user_asm(x, addr, itype, ltype, label)			\
-	asm_volatile_goto("\n"						\
+	asm_goto_output("\n"						\
 		     "1:	mov"itype" %[umem],%[output]\n"		\
 		     _ASM_EXTABLE_UA(1b, %l2)				\
 		     : [output] ltype(x)				\
@@ -375,7 +375,7 @@ do {									\
 	__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold);		\
 	__typeof__(*(_ptr)) __old = *_old;				\
 	__typeof__(*(_ptr)) __new = (_new);				\
-	asm_volatile_goto("\n"						\
+	asm_goto_output("\n"						\
 		     "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\
 		     _ASM_EXTABLE_UA(1b, %l[label])			\
 		     : CC_OUT(z) (success),				\
@@ -394,7 +394,7 @@ do {									\
 	__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold);		\
 	__typeof__(*(_ptr)) __old = *_old;				\
 	__typeof__(*(_ptr)) __new = (_new);				\
-	asm_volatile_goto("\n"						\
+	asm_goto_output("\n"						\
 		     "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n"		\
 		     _ASM_EXTABLE_UA(1b, %l[label])			\
 		     : CC_OUT(z) (success),				\
@@ -477,7 +477,7 @@ struct __large_struct { unsigned long buf[100]; };
  * aliasing issues.
  */
 #define __put_user_goto(x, addr, itype, ltype, label)			\
-	asm_volatile_goto("\n"						\
+	asm goto("\n"							\
 		"1:	mov"itype" %0,%1\n"				\
 		_ASM_EXTABLE_UA(1b, %l2)				\
 		: : ltype(x), "m" (__m(addr))				\
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index ab60a71a8dcb..472f0263dbc6 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -4,6 +4,7 @@
 
 #include <linux/seqlock.h>
 #include <uapi/asm/vsyscall.h>
+#include <asm/page_types.h>
 
 #ifdef CONFIG_X86_VSYSCALL_EMULATION
 extern void map_vsyscall(void);
@@ -24,4 +25,13 @@ static inline bool emulate_vsyscall(unsigned long error_code,
 }
 #endif
 
+/*
+ * The (legacy) vsyscall page is the long page in the kernel portion
+ * of the address space that has user-accessible permissions.
+ */
+static inline bool is_vsyscall_vaddr(unsigned long vaddr)
+{
+	return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR);
+}
+
 #endif /* _ASM_X86_VSYSCALL_H */
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 1a6a1f987949..a448d0964fc0 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -562,4 +562,7 @@ struct kvm_pmu_event_filter {
 /* x86-specific KVM_EXIT_HYPERCALL flags. */
 #define KVM_EXIT_HYPERCALL_LONG_MODE	BIT(0)
 
+#define KVM_X86_DEFAULT_VM	0
+#define KVM_X86_SW_PROTECTED_VM	1
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index cc130b57542a..1d85cb7071cb 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -403,7 +403,7 @@ noinstr void BUG_func(void)
 {
 	BUG();
 }
-EXPORT_SYMBOL_GPL(BUG_func);
+EXPORT_SYMBOL(BUG_func);
 
 #define CALL_RIP_REL_OPCODE	0xff
 #define CALL_RIP_REL_MODRM	0x15
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 4feaa670d578..89c0c8a3fc7e 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -259,10 +259,9 @@ static u32 __init search_agp_bridge(u32 *order, int *valid_agp)
 							order);
 				}
 
-				/* No multi-function device? */
 				type = read_pci_config_byte(bus, slot, func,
 							       PCI_HEADER_TYPE);
-				if (!(type & 0x80))
+				if (!(type & PCI_HEADER_TYPE_MFD))
 					break;
 			}
 		}
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 9f42d1c59e09..f3abca334199 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -538,7 +538,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 
 	/* Figure out Zen generations: */
 	switch (c->x86) {
-	case 0x17: {
+	case 0x17:
 		switch (c->x86_model) {
 		case 0x00 ... 0x2f:
 		case 0x50 ... 0x5f:
@@ -554,8 +554,8 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 			goto warn;
 		}
 		break;
-	}
-	case 0x19: {
+
+	case 0x19:
 		switch (c->x86_model) {
 		case 0x00 ... 0x0f:
 		case 0x20 ... 0x5f:
@@ -569,7 +569,20 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 			goto warn;
 		}
 		break;
-	}
+
+	case 0x1a:
+		switch (c->x86_model) {
+		case 0x00 ... 0x0f:
+		case 0x20 ... 0x2f:
+		case 0x40 ... 0x4f:
+		case 0x70 ... 0x7f:
+			setup_force_cpu_cap(X86_FEATURE_ZEN5);
+			break;
+		default:
+			goto warn;
+		}
+		break;
+
 	default:
 		break;
 	}
@@ -1039,6 +1052,11 @@ static void init_amd_zen4(struct cpuinfo_x86 *c)
 		msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT);
 }
 
+static void init_amd_zen5(struct cpuinfo_x86 *c)
+{
+	init_amd_zen_common();
+}
+
 static void init_amd(struct cpuinfo_x86 *c)
 {
 	u64 vm_cr;
@@ -1084,6 +1102,8 @@ static void init_amd(struct cpuinfo_x86 *c)
 		init_amd_zen3(c);
 	else if (boot_cpu_has(X86_FEATURE_ZEN4))
 		init_amd_zen4(c);
+	else if (boot_cpu_has(X86_FEATURE_ZEN5))
+		init_amd_zen5(c);
 
 	/*
 	 * Enable workaround for FXSAVE leak on CPUs
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index bb0ab8466b91..48d049cd74e7 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -111,9 +111,6 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 /* Control unconditional IBPB in switch_mm() */
 DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
-/* Control MDS CPU buffer clear before returning to user space */
-DEFINE_STATIC_KEY_FALSE(mds_user_clear);
-EXPORT_SYMBOL_GPL(mds_user_clear);
 /* Control MDS CPU buffer clear before idling (halt, mwait) */
 DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
 EXPORT_SYMBOL_GPL(mds_idle_clear);
@@ -252,7 +249,7 @@ static void __init mds_select_mitigation(void)
 		if (!boot_cpu_has(X86_FEATURE_MD_CLEAR))
 			mds_mitigation = MDS_MITIGATION_VMWERV;
 
-		static_branch_enable(&mds_user_clear);
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
 
 		if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) &&
 		    (mds_nosmt || cpu_mitigations_auto_nosmt()))
@@ -356,7 +353,7 @@ static void __init taa_select_mitigation(void)
 	 * For guests that can't determine whether the correct microcode is
 	 * present on host, enable the mitigation for UCODE_NEEDED as well.
 	 */
-	static_branch_enable(&mds_user_clear);
+	setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
 
 	if (taa_nosmt || cpu_mitigations_auto_nosmt())
 		cpu_smt_disable(false);
@@ -424,7 +421,7 @@ static void __init mmio_select_mitigation(void)
 	 */
 	if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) &&
 					      boot_cpu_has(X86_FEATURE_RTM)))
-		static_branch_enable(&mds_user_clear);
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
 	else
 		static_branch_enable(&mmio_stale_data_clear);
 
@@ -484,12 +481,12 @@ static void __init md_clear_update_mitigation(void)
 	if (cpu_mitigations_off())
 		return;
 
-	if (!static_key_enabled(&mds_user_clear))
+	if (!boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF))
 		goto out;
 
 	/*
-	 * mds_user_clear is now enabled. Update MDS, TAA and MMIO Stale Data
-	 * mitigation, if necessary.
+	 * X86_FEATURE_CLEAR_CPU_BUF is now enabled. Update MDS, TAA and MMIO
+	 * Stale Data mitigation, if necessary.
 	 */
 	if (mds_mitigation == MDS_MITIGATION_OFF &&
 	    boot_cpu_has_bug(X86_BUG_MDS)) {
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 94bff381ef20..fbc4e60d027c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -66,6 +66,7 @@
 #include <asm/set_memory.h>
 #include <asm/traps.h>
 #include <asm/sev.h>
+#include <asm/tdx.h>
 
 #include "cpu.h"
 
@@ -1588,6 +1589,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 		get_cpu_vendor(c);
 		get_cpu_cap(c);
 		setup_force_cpu_cap(X86_FEATURE_CPUID);
+		get_cpu_address_sizes(c);
 		cpu_parse_early_param();
 
 		if (this_cpu->c_early_init)
@@ -1600,10 +1602,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 			this_cpu->c_bsp_init(c);
 	} else {
 		setup_clear_cpu_cap(X86_FEATURE_CPUID);
+		get_cpu_address_sizes(c);
 	}
 
-	get_cpu_address_sizes(c);
-
 	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
 
 	cpu_set_bug_bits(c);
@@ -1986,6 +1987,7 @@ static __init void identify_boot_cpu(void)
 	setup_cr_pinning();
 
 	tsx_init();
+	tdx_init();
 	lkgs_init();
 }
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index a927a8fc9624..40dec9b56f87 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -184,6 +184,90 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
 	return false;
 }
 
+#define MSR_IA32_TME_ACTIVATE		0x982
+
+/* Helpers to access TME_ACTIVATE MSR */
+#define TME_ACTIVATE_LOCKED(x)		(x & 0x1)
+#define TME_ACTIVATE_ENABLED(x)		(x & 0x2)
+
+#define TME_ACTIVATE_POLICY(x)		((x >> 4) & 0xf)	/* Bits 7:4 */
+#define TME_ACTIVATE_POLICY_AES_XTS_128	0
+
+#define TME_ACTIVATE_KEYID_BITS(x)	((x >> 32) & 0xf)	/* Bits 35:32 */
+
+#define TME_ACTIVATE_CRYPTO_ALGS(x)	((x >> 48) & 0xffff)	/* Bits 63:48 */
+#define TME_ACTIVATE_CRYPTO_AES_XTS_128	1
+
+/* Values for mktme_status (SW only construct) */
+#define MKTME_ENABLED			0
+#define MKTME_DISABLED			1
+#define MKTME_UNINITIALIZED		2
+static int mktme_status = MKTME_UNINITIALIZED;
+
+static void detect_tme_early(struct cpuinfo_x86 *c)
+{
+	u64 tme_activate, tme_policy, tme_crypto_algs;
+	int keyid_bits = 0, nr_keyids = 0;
+	static u64 tme_activate_cpu0 = 0;
+
+	rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate);
+
+	if (mktme_status != MKTME_UNINITIALIZED) {
+		if (tme_activate != tme_activate_cpu0) {
+			/* Broken BIOS? */
+			pr_err_once("x86/tme: configuration is inconsistent between CPUs\n");
+			pr_err_once("x86/tme: MKTME is not usable\n");
+			mktme_status = MKTME_DISABLED;
+
+			/* Proceed. We may need to exclude bits from x86_phys_bits. */
+		}
+	} else {
+		tme_activate_cpu0 = tme_activate;
+	}
+
+	if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
+		pr_info_once("x86/tme: not enabled by BIOS\n");
+		mktme_status = MKTME_DISABLED;
+		return;
+	}
+
+	if (mktme_status != MKTME_UNINITIALIZED)
+		goto detect_keyid_bits;
+
+	pr_info("x86/tme: enabled by BIOS\n");
+
+	tme_policy = TME_ACTIVATE_POLICY(tme_activate);
+	if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128)
+		pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy);
+
+	tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate);
+	if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) {
+		pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n",
+				tme_crypto_algs);
+		mktme_status = MKTME_DISABLED;
+	}
+detect_keyid_bits:
+	keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate);
+	nr_keyids = (1UL << keyid_bits) - 1;
+	if (nr_keyids) {
+		pr_info_once("x86/mktme: enabled by BIOS\n");
+		pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids);
+	} else {
+		pr_info_once("x86/mktme: disabled by BIOS\n");
+	}
+
+	if (mktme_status == MKTME_UNINITIALIZED) {
+		/* MKTME is usable */
+		mktme_status = MKTME_ENABLED;
+	}
+
+	/*
+	 * KeyID bits effectively lower the number of physical address
+	 * bits.  Update cpuinfo_x86::x86_phys_bits accordingly.
+	 */
+	c->x86_phys_bits -= keyid_bits;
+}
+
 static void early_init_intel(struct cpuinfo_x86 *c)
 {
 	u64 misc_enable;
@@ -322,6 +406,13 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	 */
 	if (detect_extended_topology_early(c) < 0)
 		detect_ht_early(c);
+
+	/*
+	 * Adjust the number of physical bits early because it affects the
+	 * valid bits of the MTRR mask registers.
+	 */
+	if (cpu_has(c, X86_FEATURE_TME))
+		detect_tme_early(c);
 }
 
 static void bsp_init_intel(struct cpuinfo_x86 *c)
@@ -482,90 +573,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
 #endif
 }
 
-#define MSR_IA32_TME_ACTIVATE		0x982
-
-/* Helpers to access TME_ACTIVATE MSR */
-#define TME_ACTIVATE_LOCKED(x)		(x & 0x1)
-#define TME_ACTIVATE_ENABLED(x)		(x & 0x2)
-
-#define TME_ACTIVATE_POLICY(x)		((x >> 4) & 0xf)	/* Bits 7:4 */
-#define TME_ACTIVATE_POLICY_AES_XTS_128	0
-
-#define TME_ACTIVATE_KEYID_BITS(x)	((x >> 32) & 0xf)	/* Bits 35:32 */
-
-#define TME_ACTIVATE_CRYPTO_ALGS(x)	((x >> 48) & 0xffff)	/* Bits 63:48 */
-#define TME_ACTIVATE_CRYPTO_AES_XTS_128	1
-
-/* Values for mktme_status (SW only construct) */
-#define MKTME_ENABLED			0
-#define MKTME_DISABLED			1
-#define MKTME_UNINITIALIZED		2
-static int mktme_status = MKTME_UNINITIALIZED;
-
-static void detect_tme(struct cpuinfo_x86 *c)
-{
-	u64 tme_activate, tme_policy, tme_crypto_algs;
-	int keyid_bits = 0, nr_keyids = 0;
-	static u64 tme_activate_cpu0 = 0;
-
-	rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate);
-
-	if (mktme_status != MKTME_UNINITIALIZED) {
-		if (tme_activate != tme_activate_cpu0) {
-			/* Broken BIOS? */
-			pr_err_once("x86/tme: configuration is inconsistent between CPUs\n");
-			pr_err_once("x86/tme: MKTME is not usable\n");
-			mktme_status = MKTME_DISABLED;
-
-			/* Proceed. We may need to exclude bits from x86_phys_bits. */
-		}
-	} else {
-		tme_activate_cpu0 = tme_activate;
-	}
-
-	if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
-		pr_info_once("x86/tme: not enabled by BIOS\n");
-		mktme_status = MKTME_DISABLED;
-		return;
-	}
-
-	if (mktme_status != MKTME_UNINITIALIZED)
-		goto detect_keyid_bits;
-
-	pr_info("x86/tme: enabled by BIOS\n");
-
-	tme_policy = TME_ACTIVATE_POLICY(tme_activate);
-	if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128)
-		pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy);
-
-	tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate);
-	if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) {
-		pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n",
-				tme_crypto_algs);
-		mktme_status = MKTME_DISABLED;
-	}
-detect_keyid_bits:
-	keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate);
-	nr_keyids = (1UL << keyid_bits) - 1;
-	if (nr_keyids) {
-		pr_info_once("x86/mktme: enabled by BIOS\n");
-		pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids);
-	} else {
-		pr_info_once("x86/mktme: disabled by BIOS\n");
-	}
-
-	if (mktme_status == MKTME_UNINITIALIZED) {
-		/* MKTME is usable */
-		mktme_status = MKTME_ENABLED;
-	}
-
-	/*
-	 * KeyID bits effectively lower the number of physical address
-	 * bits.  Update cpuinfo_x86::x86_phys_bits accordingly.
-	 */
-	c->x86_phys_bits -= keyid_bits;
-}
-
 static void init_cpuid_fault(struct cpuinfo_x86 *c)
 {
 	u64 msr;
@@ -702,9 +709,6 @@ static void init_intel(struct cpuinfo_x86 *c)
 
 	init_ia32_feat_ctl(c);
 
-	if (cpu_has(c, X86_FEATURE_TME))
-		detect_tme(c);
-
 	init_intel_misc_features(c);
 
 	split_lock_init();
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index fd5ce12c4f9a..bc39252bc54f 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -53,6 +53,7 @@
 #include <asm/mce.h>
 #include <asm/msr.h>
 #include <asm/reboot.h>
+#include <asm/tdx.h>
 
 #include "internal.h"
 
@@ -229,12 +230,20 @@ static void wait_for_panic(void)
 	panic("Panicing machine check CPU died");
 }
 
+static const char *mce_dump_aux_info(struct mce *m)
+{
+	if (boot_cpu_has_bug(X86_BUG_TDX_PW_MCE))
+		return tdx_dump_mce_info(m);
+
+	return NULL;
+}
+
 static noinstr void mce_panic(const char *msg, struct mce *final, char *exp)
 {
 	struct llist_node *pending;
 	struct mce_evt_llist *l;
 	int apei_err = 0;
-	struct page *p;
+	const char *memmsg;
 
 	/*
 	 * Allow instrumentation around external facilities usage. Not that it
@@ -285,6 +294,11 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp)
 	}
 	if (exp)
 		pr_emerg(HW_ERR "Machine check: %s\n", exp);
+
+	memmsg = mce_dump_aux_info(final);
+	if (memmsg)
+		pr_emerg(HW_ERR "Machine check: %s\n", memmsg);
+
 	if (!fake_panic) {
 		if (panic_timeout == 0)
 			panic_timeout = mca_cfg.panic_timeout;
@@ -297,6 +311,7 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp)
 		 */
 		if (kexec_crash_loaded()) {
 			if (final && (final->status & MCI_STATUS_ADDRV)) {
+				struct page *p;
 				p = pfn_to_online_page(final->addr >> PAGE_SHIFT);
 				if (p)
 					SetPageHWPoison(p);
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index fb8cf953380d..b66f540de054 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1017,10 +1017,12 @@ void __init e820__reserve_setup_data(void)
 		e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
 
 		/*
-		 * SETUP_EFI and SETUP_IMA are supplied by kexec and do not need
-		 * to be reserved.
+		 * SETUP_EFI, SETUP_IMA and SETUP_RNG_SEED are supplied by
+		 * kexec and do not need to be reserved.
 		 */
-		if (data->type != SETUP_EFI && data->type != SETUP_IMA)
+		if (data->type != SETUP_EFI &&
+		    data->type != SETUP_IMA &&
+		    data->type != SETUP_RNG_SEED)
 			e820__range_update_kexec(pa_data,
 						 sizeof(*data) + data->len,
 						 E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index a6c1867fc7aa..59f4aefc6bc1 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -779,13 +779,13 @@ static int __init check_dev_quirk(int num, int slot, int func)
 	type = read_pci_config_byte(num, slot, func,
 				    PCI_HEADER_TYPE);
 
-	if ((type & 0x7f) == PCI_HEADER_TYPE_BRIDGE) {
+	if ((type & PCI_HEADER_TYPE_MASK) == PCI_HEADER_TYPE_BRIDGE) {
 		sec = read_pci_config_byte(num, slot, func, PCI_SECONDARY_BUS);
 		if (sec > num)
 			early_pci_scan_bus(sec);
 	}
 
-	if (!(type & 0x80))
+	if (!(type & PCI_HEADER_TYPE_MFD))
 		return -1;
 
 	return 0;
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 558076dbde5b..247f2225aa9f 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -274,12 +274,13 @@ static int __restore_fpregs_from_user(void __user *buf, u64 ufeatures,
  * Attempt to restore the FPU registers directly from user memory.
  * Pagefaults are handled and any errors returned are fatal.
  */
-static bool restore_fpregs_from_user(void __user *buf, u64 xrestore,
-				     bool fx_only, unsigned int size)
+static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only)
 {
 	struct fpu *fpu = &current->thread.fpu;
 	int ret;
 
+	/* Restore enabled features only. */
+	xrestore &= fpu->fpstate->user_xfeatures;
 retry:
 	fpregs_lock();
 	/* Ensure that XFD is up to date */
@@ -309,7 +310,7 @@ retry:
 		if (ret != X86_TRAP_PF)
 			return false;
 
-		if (!fault_in_readable(buf, size))
+		if (!fault_in_readable(buf, fpu->fpstate->user_size))
 			goto retry;
 		return false;
 	}
@@ -339,7 +340,6 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx,
 	struct user_i387_ia32_struct env;
 	bool success, fx_only = false;
 	union fpregs_state *fpregs;
-	unsigned int state_size;
 	u64 user_xfeatures = 0;
 
 	if (use_xsave()) {
@@ -349,17 +349,14 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx,
 			return false;
 
 		fx_only = !fx_sw_user.magic1;
-		state_size = fx_sw_user.xstate_size;
 		user_xfeatures = fx_sw_user.xfeatures;
 	} else {
 		user_xfeatures = XFEATURE_MASK_FPSSE;
-		state_size = fpu->fpstate->user_size;
 	}
 
 	if (likely(!ia32_fxstate)) {
 		/* Restore the FPU registers directly from user memory. */
-		return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only,
-						state_size);
+		return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only);
 	}
 
 	/*
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 8ff2bf921519..a38d0c93a66e 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -1438,7 +1438,7 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id)
 	memset(&curr_time, 0, sizeof(struct rtc_time));
 
 	if (hpet_rtc_flags & (RTC_UIE | RTC_AIE)) {
-		if (unlikely(mc146818_get_time(&curr_time) < 0)) {
+		if (unlikely(mc146818_get_time(&curr_time, 10) < 0)) {
 			pr_err_ratelimited("unable to read current time from RTC\n");
 			return IRQ_HANDLED;
 		}
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index dfe9945b9bec..428ee74002e1 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -434,7 +434,8 @@ static void __init sev_map_percpu_data(void)
 {
 	int cpu;
 
-	if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+	if (cc_vendor != CC_VENDOR_AMD ||
+	    !cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
 		return;
 
 	for_each_possible_cpu(cpu) {
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index a95d0900e8c6..5bb395551c44 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -24,8 +24,8 @@
 
 static int kvmclock __initdata = 1;
 static int kvmclock_vsyscall __initdata = 1;
-static int msr_kvm_system_time __ro_after_init = MSR_KVM_SYSTEM_TIME;
-static int msr_kvm_wall_clock __ro_after_init = MSR_KVM_WALL_CLOCK;
+static int msr_kvm_system_time __ro_after_init;
+static int msr_kvm_wall_clock __ro_after_init;
 static u64 kvm_sched_clock_offset __ro_after_init;
 
 static int __init parse_no_kvmclock(char *arg)
@@ -195,7 +195,8 @@ static void kvm_setup_secondary_clock(void)
 
 void kvmclock_disable(void)
 {
-	native_write_msr(msr_kvm_system_time, 0, 0);
+	if (msr_kvm_system_time)
+		native_write_msr(msr_kvm_system_time, 0, 0);
 }
 
 static void __init kvmclock_init_mem(void)
@@ -294,7 +295,10 @@ void __init kvmclock_init(void)
 	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) {
 		msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW;
 		msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW;
-	} else if (!kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
+	} else if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
+		msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
+		msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
+	} else {
 		return;
 	}
 
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 17e955ab69fe..3082cf24b69e 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -563,9 +563,6 @@ nmi_restart:
 	}
 	if (this_cpu_dec_return(nmi_state))
 		goto nmi_restart;
-
-	if (user_mode(regs))
-		mds_user_clear_cpu_buffers();
 }
 
 #if IS_ENABLED(CONFIG_KVM_INTEL)
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 1309b9b05338..2e7066980f3e 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -67,7 +67,7 @@ void mach_get_cmos_time(struct timespec64 *now)
 		return;
 	}
 
-	if (mc146818_get_time(&tm)) {
+	if (mc146818_get_time(&tm, 1000)) {
 		pr_err("Unable to read current time from RTC\n");
 		now->tv_sec = now->tv_nsec = 0;
 		return;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index ec2c21a1844e..84201071dfac 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1031,6 +1031,8 @@ void __init setup_arch(char **cmdline_p)
 	 *
 	 * Moreover, on machines with SandyBridge graphics or in setups that use
 	 * crashkernel the entire 1M is reserved anyway.
+	 *
+	 * Note the host kernel TDX also requires the first 1MB being reserved.
 	 */
 	x86_platform.realmode_reserve();
 
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index 0bab03130033..d42c28b8bfd8 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -35,38 +35,9 @@
 #include <asm/io_apic.h>
 #include <asm/cpu.h>
 
-static DEFINE_PER_CPU(struct x86_cpu, cpu_devices);
-
 #ifdef CONFIG_HOTPLUG_CPU
-int arch_register_cpu(int cpu)
+bool arch_cpu_is_hotpluggable(int cpu)
 {
-	struct x86_cpu *xc = per_cpu_ptr(&cpu_devices, cpu);
-
-	xc->cpu.hotpluggable = cpu > 0;
-	return register_cpu(&xc->cpu, cpu);
-}
-EXPORT_SYMBOL(arch_register_cpu);
-
-void arch_unregister_cpu(int num)
-{
-	unregister_cpu(&per_cpu(cpu_devices, num).cpu);
-}
-EXPORT_SYMBOL(arch_unregister_cpu);
-#else /* CONFIG_HOTPLUG_CPU */
-
-int __init arch_register_cpu(int num)
-{
-	return register_cpu(&per_cpu(cpu_devices, num).cpu, num);
+	return cpu > 0;
 }
 #endif /* CONFIG_HOTPLUG_CPU */
-
-static int __init topology_init(void)
-{
-	int i;
-
-	for_each_present_cpu(i)
-		arch_register_cpu(i);
-
-	return 0;
-}
-subsys_initcall(topology_init);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index b0737a15c470..c3b2f863acf0 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -566,7 +566,7 @@ static bool fixup_iopl_exception(struct pt_regs *regs)
  */
 static bool try_fixup_enqcmd_gp(void)
 {
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_ARCH_HAS_CPU_PASID
 	u32 pasid;
 
 	/*
@@ -592,7 +592,7 @@ static bool try_fixup_enqcmd_gp(void)
 	if (!mm_valid_pasid(current->mm))
 		return false;
 
-	pasid = current->mm->pasid;
+	pasid = mm_get_enqcmd_pasid(current->mm);
 
 	/*
 	 * Did this thread already have its PASID activated?
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 950c12868d30..65ed14b6540b 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -23,17 +23,15 @@ config KVM
 	depends on HAVE_KVM
 	depends on HIGH_RES_TIMERS
 	depends on X86_LOCAL_APIC
-	select PREEMPT_NOTIFIERS
-	select MMU_NOTIFIER
+	select KVM_COMMON
+	select KVM_GENERIC_MMU_NOTIFIER
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_PFNCACHE
-	select HAVE_KVM_IRQFD
 	select HAVE_KVM_DIRTY_RING_TSO
 	select HAVE_KVM_DIRTY_RING_ACQ_REL
 	select IRQ_BYPASS_MANAGER
 	select HAVE_KVM_IRQ_BYPASS
 	select HAVE_KVM_IRQ_ROUTING
-	select HAVE_KVM_EVENTFD
 	select KVM_ASYNC_PF
 	select USER_RETURN_NOTIFIER
 	select KVM_MMIO
@@ -46,7 +44,6 @@ config KVM
 	select KVM_XFER_TO_GUEST_WORK
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_VFIO
-	select INTERVAL_TREE
 	select HAVE_KVM_PM_NOTIFIER if PM
 	select KVM_GENERIC_HARDWARE_ENABLING
 	help
@@ -65,18 +62,31 @@ config KVM
 
 config KVM_WERROR
 	bool "Compile KVM with -Werror"
-	# KASAN may cause the build to fail due to larger frames
-	default y if X86_64 && !KASAN
-	# We use the dependency on !COMPILE_TEST to not be enabled
-	# blindly in allmodconfig or allyesconfig configurations
-	depends on KVM
-	depends on (X86_64 && !KASAN) || !COMPILE_TEST
-	depends on EXPERT
+	# Disallow KVM's -Werror if KASAN is enabled, e.g. to guard against
+	# randomized configs from selecting KVM_WERROR=y, which doesn't play
+	# nice with KASAN.  KASAN builds generates warnings for the default
+	# FRAME_WARN, i.e. KVM_WERROR=y with KASAN=y requires special tuning.
+	# Building KVM with -Werror and KASAN is still doable via enabling
+	# the kernel-wide WERROR=y.
+	depends on KVM && EXPERT && !KASAN
 	help
 	  Add -Werror to the build flags for KVM.
 
 	  If in doubt, say "N".
 
+config KVM_SW_PROTECTED_VM
+	bool "Enable support for KVM software-protected VMs"
+	depends on EXPERT
+	depends on KVM && X86_64
+	select KVM_GENERIC_PRIVATE_MEM
+	help
+	  Enable support for KVM software-protected VMs.  Currently, software-
+	  protected VMs are purely a development and testing vehicle for
+	  KVM_CREATE_GUEST_MEMFD.  Attempting to run a "real" VM workload as a
+	  software-protected VM will fail miserably.
+
+	  If unsure, say "N".
+
 config KVM_INTEL
 	tristate "KVM for Intel (and compatible) processors support"
 	depends on KVM && IA32_FEAT_CTL
@@ -129,6 +139,20 @@ config KVM_SMM
 
 	  If unsure, say Y.
 
+config KVM_HYPERV
+	bool "Support for Microsoft Hyper-V emulation"
+	depends on KVM
+	default y
+	help
+	  Provides KVM support for emulating Microsoft Hyper-V.  This allows KVM
+	  to expose a subset of the paravirtualized interfaces defined in the
+	  Hyper-V Hypervisor Top-Level Functional Specification (TLFS):
+	  https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/reference/tlfs
+	  These interfaces are required for the correct and performant functioning
+	  of Windows and Hyper-V guests on KVM.
+
+	  If unsure, say "Y".
+
 config KVM_XEN
 	bool "Support for Xen hypercall interface"
 	depends on KVM
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 80e3fe184d17..475b5fa917a6 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -11,25 +11,27 @@ include $(srctree)/virt/kvm/Makefile.kvm
 
 kvm-y			+= x86.o emulate.o i8259.o irq.o lapic.o \
 			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
-			   hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o \
+			   debugfs.o mmu/mmu.o mmu/page_track.o \
 			   mmu/spte.o
 
-ifdef CONFIG_HYPERV
-kvm-y			+= kvm_onhyperv.o
-endif
-
 kvm-$(CONFIG_X86_64) += mmu/tdp_iter.o mmu/tdp_mmu.o
+kvm-$(CONFIG_KVM_HYPERV) += hyperv.o
 kvm-$(CONFIG_KVM_XEN)	+= xen.o
 kvm-$(CONFIG_KVM_SMM)	+= smm.o
 
 kvm-intel-y		+= vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \
-			   vmx/hyperv.o vmx/nested.o vmx/posted_intr.o
+			   vmx/nested.o vmx/posted_intr.o
+
 kvm-intel-$(CONFIG_X86_SGX_KVM)	+= vmx/sgx.o
+kvm-intel-$(CONFIG_KVM_HYPERV)	+= vmx/hyperv.o vmx/hyperv_evmcs.o
 
 kvm-amd-y		+= svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o \
-			   svm/sev.o svm/hyperv.o
+			   svm/sev.o
+kvm-amd-$(CONFIG_KVM_HYPERV) += svm/hyperv.o
 
 ifdef CONFIG_HYPERV
+kvm-y			+= kvm_onhyperv.o
+kvm-intel-y		+= vmx/vmx_onhyperv.o vmx/hyperv_evmcs.o
 kvm-amd-y		+= svm/svm_onhyperv.o
 endif
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 42d3f47f4c07..adba49afb5fe 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -314,11 +314,15 @@ EXPORT_SYMBOL_GPL(kvm_update_cpuid_runtime);
 
 static bool kvm_cpuid_has_hyperv(struct kvm_cpuid_entry2 *entries, int nent)
 {
+#ifdef CONFIG_KVM_HYPERV
 	struct kvm_cpuid_entry2 *entry;
 
 	entry = cpuid_entry2_find(entries, nent, HYPERV_CPUID_INTERFACE,
 				  KVM_CPUID_INDEX_NOT_SIGNIFICANT);
 	return entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX;
+#else
+	return false;
+#endif
 }
 
 static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
@@ -433,11 +437,13 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2,
 		return 0;
 	}
 
+#ifdef CONFIG_KVM_HYPERV
 	if (kvm_cpuid_has_hyperv(e2, nent)) {
 		r = kvm_hv_vcpu_init(vcpu);
 		if (r)
 			return r;
 	}
+#endif
 
 	r = kvm_check_cpuid(vcpu, e2, nent);
 	if (r)
@@ -469,7 +475,7 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 		return -E2BIG;
 
 	if (cpuid->nent) {
-		e = vmemdup_user(entries, array_size(sizeof(*e), cpuid->nent));
+		e = vmemdup_array_user(entries, cpuid->nent, sizeof(*e));
 		if (IS_ERR(e))
 			return PTR_ERR(e);
 
@@ -513,7 +519,7 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
 		return -E2BIG;
 
 	if (cpuid->nent) {
-		e2 = vmemdup_user(entries, array_size(sizeof(*e2), cpuid->nent));
+		e2 = vmemdup_array_user(entries, cpuid->nent, sizeof(*e2));
 		if (IS_ERR(e2))
 			return PTR_ERR(e2);
 	}
@@ -671,7 +677,7 @@ void kvm_set_cpu_caps(void)
 	kvm_cpu_cap_mask(CPUID_7_1_EAX,
 		F(AVX_VNNI) | F(AVX512_BF16) | F(CMPCCXADD) |
 		F(FZRM) | F(FSRS) | F(FSRC) |
-		F(AMX_FP16) | F(AVX_IFMA)
+		F(AMX_FP16) | F(AVX_IFMA) | F(LAM)
 	);
 
 	kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX,
@@ -679,6 +685,11 @@ void kvm_set_cpu_caps(void)
 		F(AMX_COMPLEX)
 	);
 
+	kvm_cpu_cap_init_kvm_defined(CPUID_7_2_EDX,
+		F(INTEL_PSFD) | F(IPRED_CTRL) | F(RRSBA_CTRL) | F(DDPD_U) |
+		F(BHI_CTRL) | F(MCDT_NO)
+	);
+
 	kvm_cpu_cap_mask(CPUID_D_1_EAX,
 		F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) | f_xfd
 	);
@@ -960,13 +971,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		break;
 	/* function 7 has additional index. */
 	case 7:
-		entry->eax = min(entry->eax, 1u);
+		max_idx = entry->eax = min(entry->eax, 2u);
 		cpuid_entry_override(entry, CPUID_7_0_EBX);
 		cpuid_entry_override(entry, CPUID_7_ECX);
 		cpuid_entry_override(entry, CPUID_7_EDX);
 
-		/* KVM only supports 0x7.0 and 0x7.1, capped above via min(). */
-		if (entry->eax == 1) {
+		/* KVM only supports up to 0x7.2, capped above via min(). */
+		if (max_idx >= 1) {
 			entry = do_host_cpuid(array, function, 1);
 			if (!entry)
 				goto out;
@@ -976,6 +987,16 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 			entry->ebx = 0;
 			entry->ecx = 0;
 		}
+		if (max_idx >= 2) {
+			entry = do_host_cpuid(array, function, 2);
+			if (!entry)
+				goto out;
+
+			cpuid_entry_override(entry, CPUID_7_2_EDX);
+			entry->ecx = 0;
+			entry->ebx = 0;
+			entry->eax = 0;
+		}
 		break;
 	case 0xa: { /* Architectural Performance Monitoring */
 		union cpuid10_eax eax;
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 0b90532b6e26..856e3037e74f 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -47,11 +47,6 @@ static inline bool kvm_vcpu_is_legal_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
 	return !(gpa & vcpu->arch.reserved_gpa_bits);
 }
 
-static inline bool kvm_vcpu_is_illegal_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
-{
-	return !kvm_vcpu_is_legal_gpa(vcpu, gpa);
-}
-
 static inline bool kvm_vcpu_is_legal_aligned_gpa(struct kvm_vcpu *vcpu,
 						 gpa_t gpa, gpa_t alignment)
 {
@@ -279,4 +274,12 @@ static __always_inline bool guest_can_use(struct kvm_vcpu *vcpu,
 			vcpu->arch.governed_features.enabled);
 }
 
+static inline bool kvm_vcpu_is_legal_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
+{
+	if (guest_can_use(vcpu, X86_FEATURE_LAM))
+		cr3 &= ~(X86_CR3_LAM_U48 | X86_CR3_LAM_U57);
+
+	return kvm_vcpu_is_legal_gpa(vcpu, cr3);
+}
+
 #endif
diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c
index eea6ea7f14af..95ea1a1f7403 100644
--- a/arch/x86/kvm/debugfs.c
+++ b/arch/x86/kvm/debugfs.c
@@ -111,7 +111,7 @@ static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v)
 	mutex_lock(&kvm->slots_lock);
 	write_lock(&kvm->mmu_lock);
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		int bkt;
 
 		slots = __kvm_memslots(kvm, i);
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 2673cd5c46cb..e223043ef5b2 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -687,8 +687,8 @@ static unsigned insn_alignment(struct x86_emulate_ctxt *ctxt, unsigned size)
 static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
 				       struct segmented_address addr,
 				       unsigned *max_size, unsigned size,
-				       bool write, bool fetch,
-				       enum x86emul_mode mode, ulong *linear)
+				       enum x86emul_mode mode, ulong *linear,
+				       unsigned int flags)
 {
 	struct desc_struct desc;
 	bool usable;
@@ -701,7 +701,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
 	*max_size = 0;
 	switch (mode) {
 	case X86EMUL_MODE_PROT64:
-		*linear = la;
+		*linear = la = ctxt->ops->get_untagged_addr(ctxt, la, flags);
 		va_bits = ctxt_virt_addr_bits(ctxt);
 		if (!__is_canonical_address(la, va_bits))
 			goto bad;
@@ -717,11 +717,11 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
 		if (!usable)
 			goto bad;
 		/* code segment in protected mode or read-only data segment */
-		if ((((ctxt->mode != X86EMUL_MODE_REAL) && (desc.type & 8))
-					|| !(desc.type & 2)) && write)
+		if ((((ctxt->mode != X86EMUL_MODE_REAL) && (desc.type & 8)) || !(desc.type & 2)) &&
+		    (flags & X86EMUL_F_WRITE))
 			goto bad;
 		/* unreadable code segment */
-		if (!fetch && (desc.type & 8) && !(desc.type & 2))
+		if (!(flags & X86EMUL_F_FETCH) && (desc.type & 8) && !(desc.type & 2))
 			goto bad;
 		lim = desc_limit_scaled(&desc);
 		if (!(desc.type & 8) && (desc.type & 4)) {
@@ -757,8 +757,8 @@ static int linearize(struct x86_emulate_ctxt *ctxt,
 		     ulong *linear)
 {
 	unsigned max_size;
-	return __linearize(ctxt, addr, &max_size, size, write, false,
-			   ctxt->mode, linear);
+	return __linearize(ctxt, addr, &max_size, size, ctxt->mode, linear,
+			   write ? X86EMUL_F_WRITE : 0);
 }
 
 static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst)
@@ -771,7 +771,8 @@ static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst)
 
 	if (ctxt->op_bytes != sizeof(unsigned long))
 		addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1);
-	rc = __linearize(ctxt, addr, &max_size, 1, false, true, ctxt->mode, &linear);
+	rc = __linearize(ctxt, addr, &max_size, 1, ctxt->mode, &linear,
+			 X86EMUL_F_FETCH);
 	if (rc == X86EMUL_CONTINUE)
 		ctxt->_eip = addr.ea;
 	return rc;
@@ -907,8 +908,8 @@ static int __do_insn_fetch_bytes(struct x86_emulate_ctxt *ctxt, int op_size)
 	 * boundary check itself.  Instead, we use max_size to check
 	 * against op_size.
 	 */
-	rc = __linearize(ctxt, addr, &max_size, 0, false, true, ctxt->mode,
-			 &linear);
+	rc = __linearize(ctxt, addr, &max_size, 0, ctxt->mode, &linear,
+			 X86EMUL_F_FETCH);
 	if (unlikely(rc != X86EMUL_CONTINUE))
 		return rc;
 
@@ -3439,8 +3440,10 @@ static int em_invlpg(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
 	ulong linear;
+	unsigned int max_size;
 
-	rc = linearize(ctxt, ctxt->src.addr.mem, 1, false, &linear);
+	rc = __linearize(ctxt, ctxt->src.addr.mem, &max_size, 1, ctxt->mode,
+			 &linear, X86EMUL_F_INVLPG);
 	if (rc == X86EMUL_CONTINUE)
 		ctxt->ops->invlpg(ctxt, linear);
 	/* Disable writeback. */
diff --git a/arch/x86/kvm/governed_features.h b/arch/x86/kvm/governed_features.h
index 423a73395c10..ad463b1ed4e4 100644
--- a/arch/x86/kvm/governed_features.h
+++ b/arch/x86/kvm/governed_features.h
@@ -16,6 +16,7 @@ KVM_GOVERNED_X86_FEATURE(PAUSEFILTER)
 KVM_GOVERNED_X86_FEATURE(PFTHRESHOLD)
 KVM_GOVERNED_X86_FEATURE(VGIF)
 KVM_GOVERNED_X86_FEATURE(VNMI)
+KVM_GOVERNED_X86_FEATURE(LAM)
 
 #undef KVM_GOVERNED_X86_FEATURE
 #undef KVM_GOVERNED_FEATURE
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 4943f6b2bbee..8a47f8541eab 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1322,6 +1322,56 @@ static bool hv_check_msr_access(struct kvm_vcpu_hv *hv_vcpu, u32 msr)
 	return false;
 }
 
+#define KVM_HV_WIN2016_GUEST_ID 0x1040a00003839
+#define KVM_HV_WIN2016_GUEST_ID_MASK (~GENMASK_ULL(23, 16)) /* mask out the service version */
+
+/*
+ * Hyper-V enabled Windows Server 2016 SMP VMs fail to boot in !XSAVES && XSAVEC
+ * configuration.
+ * Such configuration can result from, for example, AMD Erratum 1386 workaround.
+ *
+ * Print a notice so users aren't left wondering what's suddenly gone wrong.
+ */
+static void __kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_hv *hv = to_kvm_hv(kvm);
+
+	/* Check again under the hv_lock.  */
+	if (hv->xsaves_xsavec_checked)
+		return;
+
+	if ((hv->hv_guest_os_id & KVM_HV_WIN2016_GUEST_ID_MASK) !=
+	    KVM_HV_WIN2016_GUEST_ID)
+		return;
+
+	hv->xsaves_xsavec_checked = true;
+
+	/* UP configurations aren't affected */
+	if (atomic_read(&kvm->online_vcpus) < 2)
+		return;
+
+	if (guest_cpuid_has(vcpu, X86_FEATURE_XSAVES) ||
+	    !guest_cpuid_has(vcpu, X86_FEATURE_XSAVEC))
+		return;
+
+	pr_notice_ratelimited("Booting SMP Windows KVM VM with !XSAVES && XSAVEC. "
+			      "If it fails to boot try disabling XSAVEC in the VM config.\n");
+}
+
+void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu)
+{
+	struct kvm_hv *hv = to_kvm_hv(vcpu->kvm);
+
+	if (!vcpu->arch.hyperv_enabled ||
+	    hv->xsaves_xsavec_checked)
+		return;
+
+	mutex_lock(&hv->hv_lock);
+	__kvm_hv_xsaves_xsavec_maybe_warn(vcpu);
+	mutex_unlock(&hv->hv_lock);
+}
+
 static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
 			     bool host)
 {
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index f83b8db72b11..923e64903da9 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -24,6 +24,8 @@
 #include <linux/kvm_host.h>
 #include "x86.h"
 
+#ifdef CONFIG_KVM_HYPERV
+
 /* "Hv#1" signature */
 #define HYPERV_CPUID_SIGNATURE_EAX 0x31237648
 
@@ -105,6 +107,17 @@ int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint);
 void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector);
 int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages);
 
+static inline bool kvm_hv_synic_has_vector(struct kvm_vcpu *vcpu, int vector)
+{
+	return to_hv_vcpu(vcpu) && test_bit(vector, to_hv_synic(vcpu)->vec_bitmap);
+}
+
+static inline bool kvm_hv_synic_auto_eoi_set(struct kvm_vcpu *vcpu, int vector)
+{
+	return to_hv_vcpu(vcpu) &&
+	       test_bit(vector, to_hv_synic(vcpu)->auto_eoi_bitmap);
+}
+
 void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu);
 
 bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu);
@@ -169,6 +182,8 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
 			   struct pvclock_vcpu_time_info *hv_clock);
 void kvm_hv_request_tsc_page_update(struct kvm *kvm);
 
+void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu);
+
 void kvm_hv_init_vm(struct kvm *kvm);
 void kvm_hv_destroy_vm(struct kvm *kvm);
 int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu);
@@ -236,6 +251,77 @@ static inline int kvm_hv_verify_vp_assist(struct kvm_vcpu *vcpu)
 	return kvm_hv_get_assist_page(vcpu);
 }
 
+static inline void kvm_hv_nested_transtion_tlb_flush(struct kvm_vcpu *vcpu,
+						     bool tdp_enabled)
+{
+	/*
+	 * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or
+	 * L2's VP_ID upon request from the guest. Make sure we check for
+	 * pending entries in the right FIFO upon L1/L2 transition as these
+	 * requests are put by other vCPUs asynchronously.
+	 */
+	if (to_hv_vcpu(vcpu) && tdp_enabled)
+		kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu);
+}
+
 int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu);
+#else /* CONFIG_KVM_HYPERV */
+static inline void kvm_hv_setup_tsc_page(struct kvm *kvm,
+					 struct pvclock_vcpu_time_info *hv_clock) {}
+static inline void kvm_hv_request_tsc_page_update(struct kvm *kvm) {}
+static inline void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu) {}
+static inline void kvm_hv_init_vm(struct kvm *kvm) {}
+static inline void kvm_hv_destroy_vm(struct kvm *kvm) {}
+static inline int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+static inline void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu) {}
+static inline bool kvm_hv_hypercall_enabled(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
+{
+	return HV_STATUS_ACCESS_DENIED;
+}
+static inline void kvm_hv_vcpu_purge_flush_tlb(struct kvm_vcpu *vcpu) {}
+static inline void kvm_hv_free_pa_page(struct kvm *kvm) {}
+static inline bool kvm_hv_synic_has_vector(struct kvm_vcpu *vcpu, int vector)
+{
+	return false;
+}
+static inline bool kvm_hv_synic_auto_eoi_set(struct kvm_vcpu *vcpu, int vector)
+{
+	return false;
+}
+static inline void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector) {}
+static inline bool kvm_hv_invtsc_suppressed(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu, bool hyperv_enabled) {}
+static inline bool kvm_hv_has_stimer_pending(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline bool kvm_hv_is_tlb_flush_hcall(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline bool guest_hv_cpuid_has_l2_tlb_flush(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline int kvm_hv_verify_vp_assist(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+static inline u32 kvm_hv_get_vpindex(struct kvm_vcpu *vcpu)
+{
+	return vcpu->vcpu_idx;
+}
+static inline void kvm_hv_nested_transtion_tlb_flush(struct kvm_vcpu *vcpu, bool tdp_enabled) {}
+#endif /* CONFIG_KVM_HYPERV */
 
-#endif
+#endif /* __ARCH_X86_KVM_HYPERV_H__ */
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index b2c397dd2bc6..ad9ca8a60144 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -118,8 +118,10 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v)
 	if (!lapic_in_kernel(v))
 		return v->arch.interrupt.nr;
 
+#ifdef CONFIG_KVM_XEN
 	if (kvm_xen_has_interrupt(v))
 		return v->kvm->arch.xen.upcall_vector;
+#endif
 
 	if (irqchip_split(v->kvm)) {
 		int vector = v->arch.pending_external_vector;
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 16d076a1b91a..68f3f6c26046 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -144,7 +144,7 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 	return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL);
 }
 
-
+#ifdef CONFIG_KVM_HYPERV
 static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
 		    struct kvm *kvm, int irq_source_id, int level,
 		    bool line_status)
@@ -154,6 +154,7 @@ static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
 
 	return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint);
 }
+#endif
 
 int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 			      struct kvm *kvm, int irq_source_id, int level,
@@ -163,9 +164,11 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 	int r;
 
 	switch (e->type) {
+#ifdef CONFIG_KVM_HYPERV
 	case KVM_IRQ_ROUTING_HV_SINT:
 		return kvm_hv_set_sint(e, kvm, irq_source_id, level,
 				       line_status);
+#endif
 
 	case KVM_IRQ_ROUTING_MSI:
 		if (kvm_msi_route_invalid(kvm, e))
@@ -314,11 +317,13 @@ int kvm_set_routing_entry(struct kvm *kvm,
 		if (kvm_msi_route_invalid(kvm, e))
 			return -EINVAL;
 		break;
+#ifdef CONFIG_KVM_HYPERV
 	case KVM_IRQ_ROUTING_HV_SINT:
 		e->set = kvm_hv_set_sint;
 		e->hv_sint.vcpu = ue->u.hv_sint.vcpu;
 		e->hv_sint.sint = ue->u.hv_sint.sint;
 		break;
+#endif
 #ifdef CONFIG_KVM_XEN
 	case KVM_IRQ_ROUTING_XEN_EVTCHN:
 		return kvm_xen_setup_evtchn(kvm, e, ue);
@@ -438,5 +443,7 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
 
 void kvm_arch_irq_routing_update(struct kvm *kvm)
 {
+#ifdef CONFIG_KVM_HYPERV
 	kvm_hv_irq_routing_update(kvm);
+#endif
 }
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index be7aeb9b8ea3..e6d149825169 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -88,6 +88,12 @@ struct x86_instruction_info {
 #define X86EMUL_IO_NEEDED       5 /* IO is needed to complete emulation */
 #define X86EMUL_INTERCEPTED     6 /* Intercepted by nested VMCB/VMCS */
 
+/* x86-specific emulation flags */
+#define X86EMUL_F_WRITE			BIT(0)
+#define X86EMUL_F_FETCH			BIT(1)
+#define X86EMUL_F_IMPLICIT		BIT(2)
+#define X86EMUL_F_INVLPG		BIT(3)
+
 struct x86_emulate_ops {
 	void (*vm_bugged)(struct x86_emulate_ctxt *ctxt);
 	/*
@@ -224,6 +230,9 @@ struct x86_emulate_ops {
 	int (*leave_smm)(struct x86_emulate_ctxt *ctxt);
 	void (*triple_fault)(struct x86_emulate_ctxt *ctxt);
 	int (*set_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr);
+
+	gva_t (*get_untagged_addr)(struct x86_emulate_ctxt *ctxt, gva_t addr,
+				   unsigned int flags);
 };
 
 /* Type, address-of, and value of an instruction's operand. */
diff --git a/arch/x86/kvm/kvm_onhyperv.h b/arch/x86/kvm/kvm_onhyperv.h
index f9ca3e7432b2..eefab3dc8498 100644
--- a/arch/x86/kvm/kvm_onhyperv.h
+++ b/arch/x86/kvm/kvm_onhyperv.h
@@ -10,6 +10,26 @@
 int hv_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, gfn_t nr_pages);
 int hv_flush_remote_tlbs(struct kvm *kvm);
 void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp);
+static inline hpa_t hv_get_partition_assist_page(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Partition assist page is something which Hyper-V running in L0
+	 * requires from KVM running in L1 before direct TLB flush for L2
+	 * guests can be enabled. KVM doesn't currently use the page but to
+	 * comply with TLFS it still needs to be allocated. For now, this
+	 * is a single page shared among all vCPUs.
+	 */
+	struct hv_partition_assist_pg **p_hv_pa_pg =
+		&vcpu->kvm->arch.hv_pa_pg;
+
+	if (!*p_hv_pa_pg)
+		*p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT);
+
+	if (!*p_hv_pa_pg)
+		return INVALID_PAGE;
+
+	return __pa(*p_hv_pa_pg);
+}
 #else /* !CONFIG_HYPERV */
 static inline int hv_flush_remote_tlbs(struct kvm *kvm)
 {
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 245b20973cae..3242f3da2457 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1475,8 +1475,7 @@ static int apic_set_eoi(struct kvm_lapic *apic)
 	apic_clear_isr(vector, apic);
 	apic_update_ppr(apic);
 
-	if (to_hv_vcpu(apic->vcpu) &&
-	    test_bit(vector, to_hv_synic(apic->vcpu)->vec_bitmap))
+	if (kvm_hv_synic_has_vector(apic->vcpu, vector))
 		kvm_hv_synic_send_eoi(apic->vcpu, vector);
 
 	kvm_ioapic_send_eoi(apic, vector);
@@ -2905,7 +2904,7 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
 	 */
 
 	apic_clear_irr(vector, apic);
-	if (to_hv_vcpu(vcpu) && test_bit(vector, to_hv_synic(vcpu)->auto_eoi_bitmap)) {
+	if (kvm_hv_synic_auto_eoi_set(vcpu, vector)) {
 		/*
 		 * For auto-EOI interrupts, there might be another pending
 		 * interrupt above PPR, so check whether to raise another
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index bb8c86eefac0..60f21bb4c27b 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -146,6 +146,14 @@ static inline unsigned long kvm_get_active_pcid(struct kvm_vcpu *vcpu)
 	return kvm_get_pcid(vcpu, kvm_read_cr3(vcpu));
 }
 
+static inline unsigned long kvm_get_active_cr3_lam_bits(struct kvm_vcpu *vcpu)
+{
+	if (!guest_can_use(vcpu, X86_FEATURE_LAM))
+		return 0;
+
+	return kvm_read_cr3(vcpu) & (X86_CR3_LAM_U48 | X86_CR3_LAM_U57);
+}
+
 static inline void kvm_mmu_load_pgd(struct kvm_vcpu *vcpu)
 {
 	u64 root_hpa = vcpu->arch.mmu->root.hpa;
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 0b1f991b9a31..0544700ca50b 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -271,15 +271,11 @@ static inline unsigned long kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu,
 
 static inline bool kvm_available_flush_remote_tlbs_range(void)
 {
+#if IS_ENABLED(CONFIG_HYPERV)
 	return kvm_x86_ops.flush_remote_tlbs_range;
-}
-
-int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages)
-{
-	if (!kvm_x86_ops.flush_remote_tlbs_range)
-		return -EOPNOTSUPP;
-
-	return static_call(kvm_x86_flush_remote_tlbs_range)(kvm, gfn, nr_pages);
+#else
+	return false;
+#endif
 }
 
 static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index);
@@ -795,16 +791,26 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn,
 	return &slot->arch.lpage_info[level - 2][idx];
 }
 
+/*
+ * The most significant bit in disallow_lpage tracks whether or not memory
+ * attributes are mixed, i.e. not identical for all gfns at the current level.
+ * The lower order bits are used to refcount other cases where a hugepage is
+ * disallowed, e.g. if KVM has shadow a page table at the gfn.
+ */
+#define KVM_LPAGE_MIXED_FLAG	BIT(31)
+
 static void update_gfn_disallow_lpage_count(const struct kvm_memory_slot *slot,
 					    gfn_t gfn, int count)
 {
 	struct kvm_lpage_info *linfo;
-	int i;
+	int old, i;
 
 	for (i = PG_LEVEL_2M; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) {
 		linfo = lpage_info_slot(gfn, slot, i);
+
+		old = linfo->disallow_lpage;
 		linfo->disallow_lpage += count;
-		WARN_ON_ONCE(linfo->disallow_lpage < 0);
+		WARN_ON_ONCE((old ^ linfo->disallow_lpage) & KVM_LPAGE_MIXED_FLAG);
 	}
 }
 
@@ -1382,7 +1388,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 		gfn_t end = slot->base_gfn + gfn_offset + __fls(mask);
 
 		if (READ_ONCE(eager_page_split))
-			kvm_mmu_try_split_huge_pages(kvm, slot, start, end, PG_LEVEL_4K);
+			kvm_mmu_try_split_huge_pages(kvm, slot, start, end + 1, PG_LEVEL_4K);
 
 		kvm_mmu_slot_gfn_write_protect(kvm, slot, start, PG_LEVEL_2M);
 
@@ -2840,9 +2846,9 @@ int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot,
 			/*
 			 * Recheck after taking the spinlock, a different vCPU
 			 * may have since marked the page unsync.  A false
-			 * positive on the unprotected check above is not
+			 * negative on the unprotected check above is not
 			 * possible as clearing sp->unsync _must_ hold mmu_lock
-			 * for write, i.e. unsync cannot transition from 0->1
+			 * for write, i.e. unsync cannot transition from 1->0
 			 * while this CPU holds mmu_lock for read (or write).
 			 */
 			if (READ_ONCE(sp->unsync))
@@ -3056,7 +3062,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
  *
  * There are several ways to safely use this helper:
  *
- * - Check mmu_invalidate_retry_hva() after grabbing the mapping level, before
+ * - Check mmu_invalidate_retry_gfn() after grabbing the mapping level, before
  *   consuming it.  In this case, mmu_lock doesn't need to be held during the
  *   lookup, but it does need to be held while checking the MMU notifier.
  *
@@ -3137,9 +3143,9 @@ out:
 	return level;
 }
 
-int kvm_mmu_max_mapping_level(struct kvm *kvm,
-			      const struct kvm_memory_slot *slot, gfn_t gfn,
-			      int max_level)
+static int __kvm_mmu_max_mapping_level(struct kvm *kvm,
+				       const struct kvm_memory_slot *slot,
+				       gfn_t gfn, int max_level, bool is_private)
 {
 	struct kvm_lpage_info *linfo;
 	int host_level;
@@ -3151,6 +3157,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
 			break;
 	}
 
+	if (is_private)
+		return max_level;
+
 	if (max_level == PG_LEVEL_4K)
 		return PG_LEVEL_4K;
 
@@ -3158,6 +3167,16 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
 	return min(host_level, max_level);
 }
 
+int kvm_mmu_max_mapping_level(struct kvm *kvm,
+			      const struct kvm_memory_slot *slot, gfn_t gfn,
+			      int max_level)
+{
+	bool is_private = kvm_slot_can_be_private(slot) &&
+			  kvm_mem_is_private(kvm, gfn);
+
+	return __kvm_mmu_max_mapping_level(kvm, slot, gfn, max_level, is_private);
+}
+
 void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
 	struct kvm_memory_slot *slot = fault->slot;
@@ -3178,8 +3197,9 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	 * Enforce the iTLB multihit workaround after capturing the requested
 	 * level, which will be used to do precise, accurate accounting.
 	 */
-	fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot,
-						     fault->gfn, fault->max_level);
+	fault->req_level = __kvm_mmu_max_mapping_level(vcpu->kvm, slot,
+						       fault->gfn, fault->max_level,
+						       fault->is_private);
 	if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed)
 		return;
 
@@ -3556,7 +3576,7 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
 		return;
 
 	if (is_tdp_mmu_page(sp))
-		kvm_tdp_mmu_put_root(kvm, sp, false);
+		kvm_tdp_mmu_put_root(kvm, sp);
 	else if (!--sp->root_count && sp->role.invalid)
 		kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
 
@@ -3739,7 +3759,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm)
 	    kvm_page_track_write_tracking_enabled(kvm))
 		goto out_success;
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		slots = __kvm_memslots(kvm, i);
 		kvm_for_each_memslot(slot, bkt, slots) {
 			/*
@@ -3782,7 +3802,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 	hpa_t root;
 
 	root_pgd = kvm_mmu_get_guest_pgd(vcpu, mmu);
-	root_gfn = root_pgd >> PAGE_SHIFT;
+	root_gfn = (root_pgd & __PT_BASE_ADDR_MASK) >> PAGE_SHIFT;
 
 	if (!kvm_vcpu_is_visible_gfn(vcpu, root_gfn)) {
 		mmu->root.hpa = kvm_mmu_get_dummy_root();
@@ -4259,6 +4279,55 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 	kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true, NULL);
 }
 
+static inline u8 kvm_max_level_for_order(int order)
+{
+	BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G);
+
+	KVM_MMU_WARN_ON(order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G) &&
+			order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M) &&
+			order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K));
+
+	if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G))
+		return PG_LEVEL_1G;
+
+	if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M))
+		return PG_LEVEL_2M;
+
+	return PG_LEVEL_4K;
+}
+
+static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
+					      struct kvm_page_fault *fault)
+{
+	kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT,
+				      PAGE_SIZE, fault->write, fault->exec,
+				      fault->is_private);
+}
+
+static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
+				   struct kvm_page_fault *fault)
+{
+	int max_order, r;
+
+	if (!kvm_slot_can_be_private(fault->slot)) {
+		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+		return -EFAULT;
+	}
+
+	r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn,
+			     &max_order);
+	if (r) {
+		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+		return r;
+	}
+
+	fault->max_level = min(kvm_max_level_for_order(max_order),
+			       fault->max_level);
+	fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY);
+
+	return RET_PF_CONTINUE;
+}
+
 static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
 	struct kvm_memory_slot *slot = fault->slot;
@@ -4291,6 +4360,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 			return RET_PF_EMULATE;
 	}
 
+	if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
+		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+		return -EFAULT;
+	}
+
+	if (fault->is_private)
+		return kvm_faultin_pfn_private(vcpu, fault);
+
 	async = false;
 	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async,
 					  fault->write, &fault->map_writable,
@@ -4328,6 +4405,31 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 	fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq;
 	smp_rmb();
 
+	/*
+	 * Check for a relevant mmu_notifier invalidation event before getting
+	 * the pfn from the primary MMU, and before acquiring mmu_lock.
+	 *
+	 * For mmu_lock, if there is an in-progress invalidation and the kernel
+	 * allows preemption, the invalidation task may drop mmu_lock and yield
+	 * in response to mmu_lock being contended, which is *very* counter-
+	 * productive as this vCPU can't actually make forward progress until
+	 * the invalidation completes.
+	 *
+	 * Retrying now can also avoid unnessary lock contention in the primary
+	 * MMU, as the primary MMU doesn't necessarily hold a single lock for
+	 * the duration of the invalidation, i.e. faulting in a conflicting pfn
+	 * can cause the invalidation to take longer by holding locks that are
+	 * needed to complete the invalidation.
+	 *
+	 * Do the pre-check even for non-preemtible kernels, i.e. even if KVM
+	 * will never yield mmu_lock in response to contention, as this vCPU is
+	 * *guaranteed* to need to retry, i.e. waiting until mmu_lock is held
+	 * to detect retry guarantees the worst case latency for the vCPU.
+	 */
+	if (fault->slot &&
+	    mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn))
+		return RET_PF_RETRY;
+
 	ret = __kvm_faultin_pfn(vcpu, fault);
 	if (ret != RET_PF_CONTINUE)
 		return ret;
@@ -4338,6 +4440,18 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 	if (unlikely(!fault->slot))
 		return kvm_handle_noslot_fault(vcpu, fault, access);
 
+	/*
+	 * Check again for a relevant mmu_notifier invalidation event purely to
+	 * avoid contending mmu_lock.  Most invalidations will be detected by
+	 * the previous check, but checking is extremely cheap relative to the
+	 * overall cost of failing to detect the invalidation until after
+	 * mmu_lock is acquired.
+	 */
+	if (mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) {
+		kvm_release_pfn_clean(fault->pfn);
+		return RET_PF_RETRY;
+	}
+
 	return RET_PF_CONTINUE;
 }
 
@@ -4365,8 +4479,13 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
 	if (!sp && kvm_test_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu))
 		return true;
 
+	/*
+	 * Check for a relevant mmu_notifier invalidation event one last time
+	 * now that mmu_lock is held, as the "unsafe" checks performed without
+	 * holding mmu_lock can get false negatives.
+	 */
 	return fault->slot &&
-	       mmu_invalidate_retry_hva(vcpu->kvm, fault->mmu_seq, fault->hva);
+	       mmu_invalidate_retry_gfn(vcpu->kvm, fault->mmu_seq, fault->gfn);
 }
 
 static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
@@ -6228,7 +6347,7 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e
 	if (!kvm_memslots_have_rmaps(kvm))
 		return flush;
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		slots = __kvm_memslots(kvm, i);
 
 		kvm_for_each_memslot_in_gfn_range(&iter, slots, gfn_start, gfn_end) {
@@ -6260,7 +6379,9 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 
 	write_lock(&kvm->mmu_lock);
 
-	kvm_mmu_invalidate_begin(kvm, 0, -1ul);
+	kvm_mmu_invalidate_begin(kvm);
+
+	kvm_mmu_invalidate_range_add(kvm, gfn_start, gfn_end);
 
 	flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end);
 
@@ -6270,7 +6391,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 	if (flush)
 		kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start);
 
-	kvm_mmu_invalidate_end(kvm, 0, -1ul);
+	kvm_mmu_invalidate_end(kvm);
 
 	write_unlock(&kvm->mmu_lock);
 }
@@ -6723,7 +6844,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen)
 	 * modifier prior to checking for a wrap of the MMIO generation so
 	 * that a wrap in any address space is detected.
 	 */
-	gen &= ~((u64)KVM_ADDRESS_SPACE_NUM - 1);
+	gen &= ~((u64)kvm_arch_nr_memslot_as_ids(kvm) - 1);
 
 	/*
 	 * The very rare case: if the MMIO generation number has wrapped,
@@ -7176,3 +7297,163 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
 	if (kvm->arch.nx_huge_page_recovery_thread)
 		kthread_stop(kvm->arch.nx_huge_page_recovery_thread);
 }
+
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
+					struct kvm_gfn_range *range)
+{
+	/*
+	 * Zap SPTEs even if the slot can't be mapped PRIVATE.  KVM x86 only
+	 * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM
+	 * can simply ignore such slots.  But if userspace is making memory
+	 * PRIVATE, then KVM must prevent the guest from accessing the memory
+	 * as shared.  And if userspace is making memory SHARED and this point
+	 * is reached, then at least one page within the range was previously
+	 * PRIVATE, i.e. the slot's possible hugepage ranges are changing.
+	 * Zapping SPTEs in this case ensures KVM will reassess whether or not
+	 * a hugepage can be used for affected ranges.
+	 */
+	if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm)))
+		return false;
+
+	return kvm_unmap_gfn_range(kvm, range);
+}
+
+static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+				int level)
+{
+	return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG;
+}
+
+static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+				 int level)
+{
+	lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG;
+}
+
+static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+			       int level)
+{
+	lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG;
+}
+
+static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot,
+			       gfn_t gfn, int level, unsigned long attrs)
+{
+	const unsigned long start = gfn;
+	const unsigned long end = start + KVM_PAGES_PER_HPAGE(level);
+
+	if (level == PG_LEVEL_2M)
+		return kvm_range_has_memory_attributes(kvm, start, end, attrs);
+
+	for (gfn = start; gfn < end; gfn += KVM_PAGES_PER_HPAGE(level - 1)) {
+		if (hugepage_test_mixed(slot, gfn, level - 1) ||
+		    attrs != kvm_get_memory_attributes(kvm, gfn))
+			return false;
+	}
+	return true;
+}
+
+bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
+					 struct kvm_gfn_range *range)
+{
+	unsigned long attrs = range->arg.attributes;
+	struct kvm_memory_slot *slot = range->slot;
+	int level;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+	lockdep_assert_held(&kvm->slots_lock);
+
+	/*
+	 * Calculate which ranges can be mapped with hugepages even if the slot
+	 * can't map memory PRIVATE.  KVM mustn't create a SHARED hugepage over
+	 * a range that has PRIVATE GFNs, and conversely converting a range to
+	 * SHARED may now allow hugepages.
+	 */
+	if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm)))
+		return false;
+
+	/*
+	 * The sequence matters here: upper levels consume the result of lower
+	 * level's scanning.
+	 */
+	for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) {
+		gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level);
+		gfn_t gfn = gfn_round_for_level(range->start, level);
+
+		/* Process the head page if it straddles the range. */
+		if (gfn != range->start || gfn + nr_pages > range->end) {
+			/*
+			 * Skip mixed tracking if the aligned gfn isn't covered
+			 * by the memslot, KVM can't use a hugepage due to the
+			 * misaligned address regardless of memory attributes.
+			 */
+			if (gfn >= slot->base_gfn) {
+				if (hugepage_has_attrs(kvm, slot, gfn, level, attrs))
+					hugepage_clear_mixed(slot, gfn, level);
+				else
+					hugepage_set_mixed(slot, gfn, level);
+			}
+			gfn += nr_pages;
+		}
+
+		/*
+		 * Pages entirely covered by the range are guaranteed to have
+		 * only the attributes which were just set.
+		 */
+		for ( ; gfn + nr_pages <= range->end; gfn += nr_pages)
+			hugepage_clear_mixed(slot, gfn, level);
+
+		/*
+		 * Process the last tail page if it straddles the range and is
+		 * contained by the memslot.  Like the head page, KVM can't
+		 * create a hugepage if the slot size is misaligned.
+		 */
+		if (gfn < range->end &&
+		    (gfn + nr_pages) <= (slot->base_gfn + slot->npages)) {
+			if (hugepage_has_attrs(kvm, slot, gfn, level, attrs))
+				hugepage_clear_mixed(slot, gfn, level);
+			else
+				hugepage_set_mixed(slot, gfn, level);
+		}
+	}
+	return false;
+}
+
+void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm,
+					    struct kvm_memory_slot *slot)
+{
+	int level;
+
+	if (!kvm_arch_has_private_mem(kvm))
+		return;
+
+	for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) {
+		/*
+		 * Don't bother tracking mixed attributes for pages that can't
+		 * be huge due to alignment, i.e. process only pages that are
+		 * entirely contained by the memslot.
+		 */
+		gfn_t end = gfn_round_for_level(slot->base_gfn + slot->npages, level);
+		gfn_t start = gfn_round_for_level(slot->base_gfn, level);
+		gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level);
+		gfn_t gfn;
+
+		if (start < slot->base_gfn)
+			start += nr_pages;
+
+		/*
+		 * Unlike setting attributes, every potential hugepage needs to
+		 * be manually checked as the attributes may already be mixed.
+		 */
+		for (gfn = start; gfn < end; gfn += nr_pages) {
+			unsigned long attrs = kvm_get_memory_attributes(kvm, gfn);
+
+			if (hugepage_has_attrs(kvm, slot, gfn, level, attrs))
+				hugepage_clear_mixed(slot, gfn, level);
+			else
+				hugepage_set_mixed(slot, gfn, level);
+		}
+	}
+}
+#endif
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index decc1f153669..0669a8a668ca 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -13,6 +13,7 @@
 #endif
 
 /* Page table builder macros common to shadow (host) PTEs and guest PTEs. */
+#define __PT_BASE_ADDR_MASK GENMASK_ULL(51, 12)
 #define __PT_LEVEL_SHIFT(level, bits_per_level)	\
 	(PAGE_SHIFT + ((level) - 1) * (bits_per_level))
 #define __PT_INDEX(address, level, bits_per_level) \
@@ -201,6 +202,7 @@ struct kvm_page_fault {
 
 	/* Derived from mmu and global state.  */
 	const bool is_tdp;
+	const bool is_private;
 	const bool nx_huge_page_workaround_enabled;
 
 	/*
@@ -296,6 +298,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 		.max_level = KVM_MAX_HUGEPAGE_LEVEL,
 		.req_level = PG_LEVEL_4K,
 		.goal_level = PG_LEVEL_4K,
+		.is_private = kvm_mem_is_private(vcpu->kvm, cr2_or_gpa >> PAGE_SHIFT),
 	};
 	int r;
 
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index c85255073f67..4d4e98fe4f35 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -62,7 +62,7 @@
 #endif
 
 /* Common logic, but per-type values.  These also need to be undefined. */
-#define PT_BASE_ADDR_MASK	((pt_element_t)(((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)))
+#define PT_BASE_ADDR_MASK	((pt_element_t)__PT_BASE_ADDR_MASK)
 #define PT_LVL_ADDR_MASK(lvl)	__PT_LVL_ADDR_MASK(PT_BASE_ADDR_MASK, lvl, PT_LEVEL_BITS)
 #define PT_LVL_OFFSET_MASK(lvl)	__PT_LVL_OFFSET_MASK(PT_BASE_ADDR_MASK, lvl, PT_LEVEL_BITS)
 #define PT_INDEX(addr, lvl)	__PT_INDEX(addr, lvl, PT_LEVEL_BITS)
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 6cd4dd631a2f..6ae19b4ee5b1 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -73,11 +73,8 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head)
 	tdp_mmu_free_sp(sp);
 }
 
-void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
-			  bool shared)
+void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root)
 {
-	kvm_lockdep_assert_mmu_lock_held(kvm, shared);
-
 	if (!refcount_dec_and_test(&root->tdp_mmu_root_count))
 		return;
 
@@ -106,10 +103,16 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
  */
 static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
 					      struct kvm_mmu_page *prev_root,
-					      bool shared, bool only_valid)
+					      bool only_valid)
 {
 	struct kvm_mmu_page *next_root;
 
+	/*
+	 * While the roots themselves are RCU-protected, fields such as
+	 * role.invalid are protected by mmu_lock.
+	 */
+	lockdep_assert_held(&kvm->mmu_lock);
+
 	rcu_read_lock();
 
 	if (prev_root)
@@ -132,7 +135,7 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
 	rcu_read_unlock();
 
 	if (prev_root)
-		kvm_tdp_mmu_put_root(kvm, prev_root, shared);
+		kvm_tdp_mmu_put_root(kvm, prev_root);
 
 	return next_root;
 }
@@ -144,26 +147,22 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
  * recent root. (Unless keeping a live reference is desirable.)
  *
  * If shared is set, this function is operating under the MMU lock in read
- * mode. In the unlikely event that this thread must free a root, the lock
- * will be temporarily dropped and reacquired in write mode.
+ * mode.
  */
-#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, _only_valid)\
-	for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, _only_valid);	\
-	     _root;								\
-	     _root = tdp_mmu_next_root(_kvm, _root, _shared, _only_valid))	\
-		if (kvm_lockdep_assert_mmu_lock_held(_kvm, _shared) &&		\
-		    kvm_mmu_page_as_id(_root) != _as_id) {			\
+#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _only_valid)\
+	for (_root = tdp_mmu_next_root(_kvm, NULL, _only_valid);	\
+	     ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root;	\
+	     _root = tdp_mmu_next_root(_kvm, _root, _only_valid))	\
+		if (kvm_mmu_page_as_id(_root) != _as_id) {		\
 		} else
 
-#define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared)	\
-	__for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, true)
+#define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id)	\
+	__for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, true)
 
-#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _shared)			\
-	for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, false);		\
-	     _root;								\
-	     _root = tdp_mmu_next_root(_kvm, _root, _shared, false))		\
-		if (!kvm_lockdep_assert_mmu_lock_held(_kvm, _shared)) {		\
-		} else
+#define for_each_tdp_mmu_root_yield_safe(_kvm, _root)			\
+	for (_root = tdp_mmu_next_root(_kvm, NULL, false);		\
+	     ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root;	\
+	     _root = tdp_mmu_next_root(_kvm, _root, false))
 
 /*
  * Iterate over all TDP MMU roots.  Requires that mmu_lock be held for write,
@@ -276,28 +275,18 @@ static void tdp_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
  *
  * @kvm: kvm instance
  * @sp: the page to be removed
- * @shared: This operation may not be running under the exclusive use of
- *	    the MMU lock and the operation must synchronize with other
- *	    threads that might be adding or removing pages.
  */
-static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp,
-			      bool shared)
+static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
 	tdp_unaccount_mmu_page(kvm, sp);
 
 	if (!sp->nx_huge_page_disallowed)
 		return;
 
-	if (shared)
-		spin_lock(&kvm->arch.tdp_mmu_pages_lock);
-	else
-		lockdep_assert_held_write(&kvm->mmu_lock);
-
+	spin_lock(&kvm->arch.tdp_mmu_pages_lock);
 	sp->nx_huge_page_disallowed = false;
 	untrack_possible_nx_huge_page(kvm, sp);
-
-	if (shared)
-		spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
+	spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
 }
 
 /**
@@ -326,7 +315,7 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared)
 
 	trace_kvm_mmu_prepare_zap_page(sp);
 
-	tdp_mmu_unlink_sp(kvm, sp, shared);
+	tdp_mmu_unlink_sp(kvm, sp);
 
 	for (i = 0; i < SPTE_ENT_PER_PAGE; i++) {
 		tdp_ptep_t sptep = pt + i;
@@ -832,7 +821,8 @@ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush)
 {
 	struct kvm_mmu_page *root;
 
-	for_each_tdp_mmu_root_yield_safe(kvm, root, false)
+	lockdep_assert_held_write(&kvm->mmu_lock);
+	for_each_tdp_mmu_root_yield_safe(kvm, root)
 		flush = tdp_mmu_zap_leafs(kvm, root, start, end, true, flush);
 
 	return flush;
@@ -854,7 +844,8 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm)
 	 * is being destroyed or the userspace VMM has exited.  In both cases,
 	 * KVM_RUN is unreachable, i.e. no vCPUs will ever service the request.
 	 */
-	for_each_tdp_mmu_root_yield_safe(kvm, root, false)
+	lockdep_assert_held_write(&kvm->mmu_lock);
+	for_each_tdp_mmu_root_yield_safe(kvm, root)
 		tdp_mmu_zap_root(kvm, root, false);
 }
 
@@ -868,7 +859,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
 
 	read_lock(&kvm->mmu_lock);
 
-	for_each_tdp_mmu_root_yield_safe(kvm, root, true) {
+	for_each_tdp_mmu_root_yield_safe(kvm, root) {
 		if (!root->tdp_mmu_scheduled_root_to_zap)
 			continue;
 
@@ -891,7 +882,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
 		 * the root must be reachable by mmu_notifiers while it's being
 		 * zapped
 		 */
-		kvm_tdp_mmu_put_root(kvm, root, true);
+		kvm_tdp_mmu_put_root(kvm, root);
 	}
 
 	read_unlock(&kvm->mmu_lock);
@@ -1125,7 +1116,7 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
 {
 	struct kvm_mmu_page *root;
 
-	__for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false, false)
+	__for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false)
 		flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end,
 					  range->may_block, flush);
 
@@ -1314,7 +1305,7 @@ bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm,
 
 	lockdep_assert_held_read(&kvm->mmu_lock);
 
-	for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
+	for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id)
 		spte_set |= wrprot_gfn_range(kvm, root, slot->base_gfn,
 			     slot->base_gfn + slot->npages, min_level);
 
@@ -1346,6 +1337,8 @@ static struct kvm_mmu_page *tdp_mmu_alloc_sp_for_split(struct kvm *kvm,
 {
 	struct kvm_mmu_page *sp;
 
+	kvm_lockdep_assert_mmu_lock_held(kvm, shared);
+
 	/*
 	 * Since we are allocating while under the MMU lock we have to be
 	 * careful about GFP flags. Use GFP_NOWAIT to avoid blocking on direct
@@ -1496,11 +1489,10 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm,
 	int r = 0;
 
 	kvm_lockdep_assert_mmu_lock_held(kvm, shared);
-
-	for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, shared) {
+	for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) {
 		r = tdp_mmu_split_huge_pages_root(kvm, root, start, end, target_level, shared);
 		if (r) {
-			kvm_tdp_mmu_put_root(kvm, root, shared);
+			kvm_tdp_mmu_put_root(kvm, root);
 			break;
 		}
 	}
@@ -1522,12 +1514,13 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 
 	rcu_read_lock();
 
-	tdp_root_for_each_leaf_pte(iter, root, start, end) {
+	tdp_root_for_each_pte(iter, root, start, end) {
 retry:
-		if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
+		if (!is_shadow_present_pte(iter.old_spte) ||
+		    !is_last_spte(iter.old_spte, iter.level))
 			continue;
 
-		if (!is_shadow_present_pte(iter.old_spte))
+		if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
 			continue;
 
 		KVM_MMU_WARN_ON(kvm_ad_enabled() &&
@@ -1560,8 +1553,7 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm,
 	bool spte_set = false;
 
 	lockdep_assert_held_read(&kvm->mmu_lock);
-
-	for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
+	for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id)
 		spte_set |= clear_dirty_gfn_range(kvm, root, slot->base_gfn,
 				slot->base_gfn + slot->npages);
 
@@ -1695,8 +1687,7 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
 	struct kvm_mmu_page *root;
 
 	lockdep_assert_held_read(&kvm->mmu_lock);
-
-	for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
+	for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id)
 		zap_collapsible_spte_range(kvm, root, slot);
 }
 
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 733a3aef3a96..20d97aa46c49 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -17,8 +17,7 @@ __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root)
 	return refcount_inc_not_zero(&root->tdp_mmu_root_count);
 }
 
-void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
-			  bool shared);
+void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root);
 
 bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush);
 bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp);
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 9ae07db6f0f6..87cc6c8809ad 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -127,9 +127,9 @@ static void kvm_perf_overflow(struct perf_event *perf_event,
 	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
 
 	/*
-	 * Ignore overflow events for counters that are scheduled to be
-	 * reprogrammed, e.g. if a PMI for the previous event races with KVM's
-	 * handling of a related guest WRMSR.
+	 * Ignore asynchronous overflow events for counters that are scheduled
+	 * to be reprogrammed, e.g. if a PMI for the previous event races with
+	 * KVM's handling of a related guest WRMSR.
 	 */
 	if (test_and_set_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi))
 		return;
@@ -161,6 +161,15 @@ static u64 pmc_get_pebs_precise_level(struct kvm_pmc *pmc)
 	return 1;
 }
 
+static u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value)
+{
+	u64 sample_period = (-counter_value) & pmc_bitmask(pmc);
+
+	if (!sample_period)
+		sample_period = pmc_bitmask(pmc) + 1;
+	return sample_period;
+}
+
 static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config,
 				 bool exclude_user, bool exclude_kernel,
 				 bool intr)
@@ -215,17 +224,30 @@ static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config,
 	return 0;
 }
 
-static void pmc_pause_counter(struct kvm_pmc *pmc)
+static bool pmc_pause_counter(struct kvm_pmc *pmc)
 {
 	u64 counter = pmc->counter;
-
-	if (!pmc->perf_event || pmc->is_paused)
-		return;
+	u64 prev_counter;
 
 	/* update counter, reset event value to avoid redundant accumulation */
-	counter += perf_event_pause(pmc->perf_event, true);
+	if (pmc->perf_event && !pmc->is_paused)
+		counter += perf_event_pause(pmc->perf_event, true);
+
+	/*
+	 * Snapshot the previous counter *after* accumulating state from perf.
+	 * If overflow already happened, hardware (via perf) is responsible for
+	 * generating a PMI.  KVM just needs to detect overflow on emulated
+	 * counter events that haven't yet been processed.
+	 */
+	prev_counter = counter & pmc_bitmask(pmc);
+
+	counter += pmc->emulated_counter;
 	pmc->counter = counter & pmc_bitmask(pmc);
+
+	pmc->emulated_counter = 0;
 	pmc->is_paused = true;
+
+	return pmc->counter < prev_counter;
 }
 
 static bool pmc_resume_counter(struct kvm_pmc *pmc)
@@ -250,6 +272,51 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc)
 	return true;
 }
 
+static void pmc_release_perf_event(struct kvm_pmc *pmc)
+{
+	if (pmc->perf_event) {
+		perf_event_release_kernel(pmc->perf_event);
+		pmc->perf_event = NULL;
+		pmc->current_config = 0;
+		pmc_to_pmu(pmc)->event_count--;
+	}
+}
+
+static void pmc_stop_counter(struct kvm_pmc *pmc)
+{
+	if (pmc->perf_event) {
+		pmc->counter = pmc_read_counter(pmc);
+		pmc_release_perf_event(pmc);
+	}
+}
+
+static void pmc_update_sample_period(struct kvm_pmc *pmc)
+{
+	if (!pmc->perf_event || pmc->is_paused ||
+	    !is_sampling_event(pmc->perf_event))
+		return;
+
+	perf_event_period(pmc->perf_event,
+			  get_sample_period(pmc, pmc->counter));
+}
+
+void pmc_write_counter(struct kvm_pmc *pmc, u64 val)
+{
+	/*
+	 * Drop any unconsumed accumulated counts, the WRMSR is a write, not a
+	 * read-modify-write.  Adjust the counter value so that its value is
+	 * relative to the current count, as reading the current count from
+	 * perf is faster than pausing and repgrogramming the event in order to
+	 * reset it to '0'.  Note, this very sneakily offsets the accumulated
+	 * emulated count too, by using pmc_read_counter()!
+	 */
+	pmc->emulated_counter = 0;
+	pmc->counter += val - pmc_read_counter(pmc);
+	pmc->counter &= pmc_bitmask(pmc);
+	pmc_update_sample_period(pmc);
+}
+EXPORT_SYMBOL_GPL(pmc_write_counter);
+
 static int filter_cmp(const void *pa, const void *pb, u64 mask)
 {
 	u64 a = *(u64 *)pa & mask;
@@ -383,14 +450,15 @@ static void reprogram_counter(struct kvm_pmc *pmc)
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
 	u64 eventsel = pmc->eventsel;
 	u64 new_config = eventsel;
+	bool emulate_overflow;
 	u8 fixed_ctr_ctrl;
 
-	pmc_pause_counter(pmc);
+	emulate_overflow = pmc_pause_counter(pmc);
 
 	if (!pmc_event_is_allowed(pmc))
 		goto reprogram_complete;
 
-	if (pmc->counter < pmc->prev_counter)
+	if (emulate_overflow)
 		__kvm_perf_overflow(pmc, false);
 
 	if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL)
@@ -430,7 +498,6 @@ static void reprogram_counter(struct kvm_pmc *pmc)
 
 reprogram_complete:
 	clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi);
-	pmc->prev_counter = 0;
 }
 
 void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
@@ -639,32 +706,60 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	return 0;
 }
 
-/* refresh PMU settings. This function generally is called when underlying
- * settings are changed (such as changes of PMU CPUID by guest VMs), which
- * should rarely happen.
+static void kvm_pmu_reset(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc;
+	int i;
+
+	pmu->need_cleanup = false;
+
+	bitmap_zero(pmu->reprogram_pmi, X86_PMC_IDX_MAX);
+
+	for_each_set_bit(i, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX) {
+		pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, i);
+		if (!pmc)
+			continue;
+
+		pmc_stop_counter(pmc);
+		pmc->counter = 0;
+		pmc->emulated_counter = 0;
+
+		if (pmc_is_gp(pmc))
+			pmc->eventsel = 0;
+	}
+
+	pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = 0;
+
+	static_call_cond(kvm_x86_pmu_reset)(vcpu);
+}
+
+
+/*
+ * Refresh the PMU configuration for the vCPU, e.g. if userspace changes CPUID
+ * and/or PERF_CAPABILITIES.
  */
 void kvm_pmu_refresh(struct kvm_vcpu *vcpu)
 {
 	if (KVM_BUG_ON(kvm_vcpu_has_run(vcpu), vcpu->kvm))
 		return;
 
+	/*
+	 * Stop/release all existing counters/events before realizing the new
+	 * vPMU model.
+	 */
+	kvm_pmu_reset(vcpu);
+
 	bitmap_zero(vcpu_to_pmu(vcpu)->all_valid_pmc_idx, X86_PMC_IDX_MAX);
 	static_call(kvm_x86_pmu_refresh)(vcpu);
 }
 
-void kvm_pmu_reset(struct kvm_vcpu *vcpu)
-{
-	static_call(kvm_x86_pmu_reset)(vcpu);
-}
-
 void kvm_pmu_init(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 
 	memset(pmu, 0, sizeof(*pmu));
 	static_call(kvm_x86_pmu_init)(vcpu);
-	pmu->event_count = 0;
-	pmu->need_cleanup = false;
 	kvm_pmu_refresh(vcpu);
 }
 
@@ -700,8 +795,7 @@ void kvm_pmu_destroy(struct kvm_vcpu *vcpu)
 
 static void kvm_pmu_incr_counter(struct kvm_pmc *pmc)
 {
-	pmc->prev_counter = pmc->counter;
-	pmc->counter = (pmc->counter + 1) & pmc_bitmask(pmc);
+	pmc->emulated_counter++;
 	kvm_pmu_request_counter_reprogram(pmc);
 }
 
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 1d64113de488..7caeb3d8d4fd 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -66,7 +66,8 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc)
 {
 	u64 counter, enabled, running;
 
-	counter = pmc->counter;
+	counter = pmc->counter + pmc->emulated_counter;
+
 	if (pmc->perf_event && !pmc->is_paused)
 		counter += perf_event_read_value(pmc->perf_event,
 						 &enabled, &running);
@@ -74,29 +75,7 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc)
 	return counter & pmc_bitmask(pmc);
 }
 
-static inline void pmc_write_counter(struct kvm_pmc *pmc, u64 val)
-{
-	pmc->counter += val - pmc_read_counter(pmc);
-	pmc->counter &= pmc_bitmask(pmc);
-}
-
-static inline void pmc_release_perf_event(struct kvm_pmc *pmc)
-{
-	if (pmc->perf_event) {
-		perf_event_release_kernel(pmc->perf_event);
-		pmc->perf_event = NULL;
-		pmc->current_config = 0;
-		pmc_to_pmu(pmc)->event_count--;
-	}
-}
-
-static inline void pmc_stop_counter(struct kvm_pmc *pmc)
-{
-	if (pmc->perf_event) {
-		pmc->counter = pmc_read_counter(pmc);
-		pmc_release_perf_event(pmc);
-	}
-}
+void pmc_write_counter(struct kvm_pmc *pmc, u64 val);
 
 static inline bool pmc_is_gp(struct kvm_pmc *pmc)
 {
@@ -146,25 +125,6 @@ static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr)
 	return NULL;
 }
 
-static inline u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value)
-{
-	u64 sample_period = (-counter_value) & pmc_bitmask(pmc);
-
-	if (!sample_period)
-		sample_period = pmc_bitmask(pmc) + 1;
-	return sample_period;
-}
-
-static inline void pmc_update_sample_period(struct kvm_pmc *pmc)
-{
-	if (!pmc->perf_event || pmc->is_paused ||
-	    !is_sampling_event(pmc->perf_event))
-		return;
-
-	perf_event_period(pmc->perf_event,
-			  get_sample_period(pmc, pmc->counter));
-}
-
 static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc)
 {
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
@@ -261,7 +221,6 @@ bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr);
 int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
 int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
 void kvm_pmu_refresh(struct kvm_vcpu *vcpu);
-void kvm_pmu_reset(struct kvm_vcpu *vcpu);
 void kvm_pmu_init(struct kvm_vcpu *vcpu);
 void kvm_pmu_cleanup(struct kvm_vcpu *vcpu);
 void kvm_pmu_destroy(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h
index b81650678375..aadefcaa9561 100644
--- a/arch/x86/kvm/reverse_cpuid.h
+++ b/arch/x86/kvm/reverse_cpuid.h
@@ -16,6 +16,7 @@ enum kvm_only_cpuid_leafs {
 	CPUID_7_1_EDX,
 	CPUID_8000_0007_EDX,
 	CPUID_8000_0022_EAX,
+	CPUID_7_2_EDX,
 	NR_KVM_CPU_CAPS,
 
 	NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS,
@@ -46,6 +47,14 @@ enum kvm_only_cpuid_leafs {
 #define X86_FEATURE_AMX_COMPLEX         KVM_X86_FEATURE(CPUID_7_1_EDX, 8)
 #define X86_FEATURE_PREFETCHITI         KVM_X86_FEATURE(CPUID_7_1_EDX, 14)
 
+/* Intel-defined sub-features, CPUID level 0x00000007:2 (EDX) */
+#define X86_FEATURE_INTEL_PSFD		KVM_X86_FEATURE(CPUID_7_2_EDX, 0)
+#define X86_FEATURE_IPRED_CTRL		KVM_X86_FEATURE(CPUID_7_2_EDX, 1)
+#define KVM_X86_FEATURE_RRSBA_CTRL	KVM_X86_FEATURE(CPUID_7_2_EDX, 2)
+#define X86_FEATURE_DDPD_U		KVM_X86_FEATURE(CPUID_7_2_EDX, 3)
+#define X86_FEATURE_BHI_CTRL		KVM_X86_FEATURE(CPUID_7_2_EDX, 4)
+#define X86_FEATURE_MCDT_NO		KVM_X86_FEATURE(CPUID_7_2_EDX, 5)
+
 /* CPUID level 0x80000007 (EDX). */
 #define KVM_X86_FEATURE_CONSTANT_TSC	KVM_X86_FEATURE(CPUID_8000_0007_EDX, 8)
 
@@ -80,6 +89,7 @@ static const struct cpuid_reg reverse_cpuid[] = {
 	[CPUID_8000_0007_EDX] = {0x80000007, 0, CPUID_EDX},
 	[CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX},
 	[CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX},
+	[CPUID_7_2_EDX]       = {         7, 2, CPUID_EDX},
 };
 
 /*
@@ -106,18 +116,19 @@ static __always_inline void reverse_cpuid_check(unsigned int x86_leaf)
  */
 static __always_inline u32 __feature_translate(int x86_feature)
 {
-	if (x86_feature == X86_FEATURE_SGX1)
-		return KVM_X86_FEATURE_SGX1;
-	else if (x86_feature == X86_FEATURE_SGX2)
-		return KVM_X86_FEATURE_SGX2;
-	else if (x86_feature == X86_FEATURE_SGX_EDECCSSA)
-		return KVM_X86_FEATURE_SGX_EDECCSSA;
-	else if (x86_feature == X86_FEATURE_CONSTANT_TSC)
-		return KVM_X86_FEATURE_CONSTANT_TSC;
-	else if (x86_feature == X86_FEATURE_PERFMON_V2)
-		return KVM_X86_FEATURE_PERFMON_V2;
-
-	return x86_feature;
+#define KVM_X86_TRANSLATE_FEATURE(f)	\
+	case X86_FEATURE_##f: return KVM_X86_FEATURE_##f
+
+	switch (x86_feature) {
+	KVM_X86_TRANSLATE_FEATURE(SGX1);
+	KVM_X86_TRANSLATE_FEATURE(SGX2);
+	KVM_X86_TRANSLATE_FEATURE(SGX_EDECCSSA);
+	KVM_X86_TRANSLATE_FEATURE(CONSTANT_TSC);
+	KVM_X86_TRANSLATE_FEATURE(PERFMON_V2);
+	KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL);
+	default:
+		return x86_feature;
+	}
 }
 
 static __always_inline u32 __feature_leaf(int x86_feature)
diff --git a/arch/x86/kvm/svm/hyperv.h b/arch/x86/kvm/svm/hyperv.h
index 02f4784b5d44..d3f8bfc05832 100644
--- a/arch/x86/kvm/svm/hyperv.h
+++ b/arch/x86/kvm/svm/hyperv.h
@@ -11,6 +11,7 @@
 #include "../hyperv.h"
 #include "svm.h"
 
+#ifdef CONFIG_KVM_HYPERV
 static inline void nested_svm_hv_update_vm_vp_ids(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -41,5 +42,13 @@ static inline bool nested_svm_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu)
 }
 
 void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu);
+#else /* CONFIG_KVM_HYPERV */
+static inline void nested_svm_hv_update_vm_vp_ids(struct kvm_vcpu *vcpu) {}
+static inline bool nested_svm_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu) {}
+#endif /* CONFIG_KVM_HYPERV */
 
 #endif /* __ARCH_X86_KVM_SVM_HYPERV_H__ */
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 3fea8c47679e..dee62362a360 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -187,7 +187,6 @@ void recalc_intercepts(struct vcpu_svm *svm)
  */
 static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 {
-	struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments;
 	int i;
 
 	/*
@@ -198,11 +197,16 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 	 * - Nested hypervisor (L1) is using Hyper-V emulation interface and
 	 * tells KVM (L0) there were no changes in MSR bitmap for L2.
 	 */
-	if (!svm->nested.force_msr_bitmap_recalc &&
-	    kvm_hv_hypercall_enabled(&svm->vcpu) &&
-	    hve->hv_enlightenments_control.msr_bitmap &&
-	    (svm->nested.ctl.clean & BIT(HV_VMCB_NESTED_ENLIGHTENMENTS)))
-		goto set_msrpm_base_pa;
+#ifdef CONFIG_KVM_HYPERV
+	if (!svm->nested.force_msr_bitmap_recalc) {
+		struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments;
+
+		if (kvm_hv_hypercall_enabled(&svm->vcpu) &&
+		    hve->hv_enlightenments_control.msr_bitmap &&
+		    (svm->nested.ctl.clean & BIT(HV_VMCB_NESTED_ENLIGHTENMENTS)))
+			goto set_msrpm_base_pa;
+	}
+#endif
 
 	if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT)))
 		return true;
@@ -230,7 +234,9 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 
 	svm->nested.force_msr_bitmap_recalc = false;
 
+#ifdef CONFIG_KVM_HYPERV
 set_msrpm_base_pa:
+#endif
 	svm->vmcb->control.msrpm_base_pa = __sme_set(__pa(svm->nested.msrpm));
 
 	return true;
@@ -247,18 +253,6 @@ static bool nested_svm_check_bitmap_pa(struct kvm_vcpu *vcpu, u64 pa, u32 size)
 	    kvm_vcpu_is_legal_gpa(vcpu, addr + size - 1);
 }
 
-static bool nested_svm_check_tlb_ctl(struct kvm_vcpu *vcpu, u8 tlb_ctl)
-{
-	/* Nested FLUSHBYASID is not supported yet.  */
-	switch(tlb_ctl) {
-		case TLB_CONTROL_DO_NOTHING:
-		case TLB_CONTROL_FLUSH_ALL_ASID:
-			return true;
-		default:
-			return false;
-	}
-}
-
 static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu,
 					 struct vmcb_ctrl_area_cached *control)
 {
@@ -278,9 +272,6 @@ static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu,
 					   IOPM_SIZE)))
 		return false;
 
-	if (CC(!nested_svm_check_tlb_ctl(vcpu, control->tlb_ctl)))
-		return false;
-
 	if (CC((control->int_ctl & V_NMI_ENABLE_MASK) &&
 	       !vmcb12_is_intercept(control, INTERCEPT_NMI))) {
 		return false;
@@ -311,7 +302,7 @@ static bool __nested_vmcb_check_save(struct kvm_vcpu *vcpu,
 	if ((save->efer & EFER_LME) && (save->cr0 & X86_CR0_PG)) {
 		if (CC(!(save->cr4 & X86_CR4_PAE)) ||
 		    CC(!(save->cr0 & X86_CR0_PE)) ||
-		    CC(kvm_vcpu_is_illegal_gpa(vcpu, save->cr3)))
+		    CC(!kvm_vcpu_is_legal_cr3(vcpu, save->cr3)))
 			return false;
 	}
 
@@ -378,12 +369,14 @@ void __nested_copy_vmcb_control_to_cache(struct kvm_vcpu *vcpu,
 	to->msrpm_base_pa &= ~0x0fffULL;
 	to->iopm_base_pa  &= ~0x0fffULL;
 
+#ifdef CONFIG_KVM_HYPERV
 	/* Hyper-V extensions (Enlightened VMCB) */
 	if (kvm_hv_hypercall_enabled(vcpu)) {
 		to->clean = from->clean;
 		memcpy(&to->hv_enlightenments, &from->hv_enlightenments,
 		       sizeof(to->hv_enlightenments));
 	}
+#endif
 }
 
 void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm,
@@ -487,14 +480,8 @@ static void nested_save_pending_event_to_vmcb12(struct vcpu_svm *svm,
 
 static void nested_svm_transition_tlb_flush(struct kvm_vcpu *vcpu)
 {
-	/*
-	 * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or
-	 * L2's VP_ID upon request from the guest. Make sure we check for
-	 * pending entries in the right FIFO upon L1/L2 transition as these
-	 * requests are put by other vCPUs asynchronously.
-	 */
-	if (to_hv_vcpu(vcpu) && npt_enabled)
-		kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu);
+	/* Handle pending Hyper-V TLB flush requests */
+	kvm_hv_nested_transtion_tlb_flush(vcpu, npt_enabled);
 
 	/*
 	 * TODO: optimize unconditional TLB flush/MMU sync.  A partial list of
@@ -520,7 +507,7 @@ static void nested_svm_transition_tlb_flush(struct kvm_vcpu *vcpu)
 static int nested_svm_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3,
 			       bool nested_npt, bool reload_pdptrs)
 {
-	if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3)))
+	if (CC(!kvm_vcpu_is_legal_cr3(vcpu, cr3)))
 		return -EINVAL;
 
 	if (reload_pdptrs && !nested_npt && is_pae_paging(vcpu) &&
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 373ff6a6687b..b6a7ad4d6914 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -161,7 +161,6 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER);
 	if (pmc) {
 		pmc_write_counter(pmc, data);
-		pmc_update_sample_period(pmc);
 		return 0;
 	}
 	/* MSR_EVNTSELn */
@@ -233,21 +232,6 @@ static void amd_pmu_init(struct kvm_vcpu *vcpu)
 	}
 }
 
-static void amd_pmu_reset(struct kvm_vcpu *vcpu)
-{
-	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-	int i;
-
-	for (i = 0; i < KVM_AMD_PMC_MAX_GENERIC; i++) {
-		struct kvm_pmc *pmc = &pmu->gp_counters[i];
-
-		pmc_stop_counter(pmc);
-		pmc->counter = pmc->prev_counter = pmc->eventsel = 0;
-	}
-
-	pmu->global_ctrl = pmu->global_status = 0;
-}
-
 struct kvm_pmu_ops amd_pmu_ops __initdata = {
 	.hw_event_available = amd_hw_event_available,
 	.pmc_idx_to_pmc = amd_pmc_idx_to_pmc,
@@ -259,7 +243,6 @@ struct kvm_pmu_ops amd_pmu_ops __initdata = {
 	.set_msr = amd_pmu_set_msr,
 	.refresh = amd_pmu_refresh,
 	.init = amd_pmu_init,
-	.reset = amd_pmu_reset,
 	.EVENTSEL_EVENT = AMD64_EVENTSEL_EVENT,
 	.MAX_NR_GP_COUNTERS = KVM_AMD_PMC_MAX_GENERIC,
 	.MIN_NR_GP_COUNTERS = AMD64_NUM_COUNTERS,
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 6ee925d66648..a8ce5226b3b5 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -57,7 +57,7 @@ static bool sev_es_enabled = true;
 module_param_named(sev_es, sev_es_enabled, bool, 0444);
 
 /* enable/disable SEV-ES DebugSwap support */
-static bool sev_es_debug_swap_enabled = true;
+static bool sev_es_debug_swap_enabled = false;
 module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444);
 #else
 #define sev_enabled false
@@ -612,8 +612,11 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm)
 	save->xss  = svm->vcpu.arch.ia32_xss;
 	save->dr6  = svm->vcpu.arch.dr6;
 
-	if (sev_es_debug_swap_enabled)
+	if (sev_es_debug_swap_enabled) {
 		save->sev_features |= SVM_SEV_FEAT_DEBUG_SWAP;
+		pr_warn_once("Enabling DebugSwap with KVM_SEV_ES_INIT. "
+			     "This will not work starting with Linux 6.10\n");
+	}
 
 	pr_debug("Virtual Machine Save Area (VMSA):\n");
 	print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false);
@@ -1975,20 +1978,22 @@ int sev_mem_enc_register_region(struct kvm *kvm,
 		goto e_free;
 	}
 
-	region->uaddr = range->addr;
-	region->size = range->size;
-
-	list_add_tail(&region->list, &sev->regions_list);
-	mutex_unlock(&kvm->lock);
-
 	/*
 	 * The guest may change the memory encryption attribute from C=0 -> C=1
 	 * or vice versa for this memory range. Lets make sure caches are
 	 * flushed to ensure that guest data gets written into memory with
-	 * correct C-bit.
+	 * correct C-bit.  Note, this must be done before dropping kvm->lock,
+	 * as region and its array of pages can be freed by a different task
+	 * once kvm->lock is released.
 	 */
 	sev_clflush_pages(region->pages, region->npages);
 
+	region->uaddr = range->addr;
+	region->size = range->size;
+
+	list_add_tail(&region->list, &sev->regions_list);
+	mutex_unlock(&kvm->lock);
+
 	return ret;
 
 e_free:
@@ -2191,10 +2196,13 @@ void __init sev_hardware_setup(void)
 	/*
 	 * SEV must obviously be supported in hardware.  Sanity check that the
 	 * CPU supports decode assists, which is mandatory for SEV guests to
-	 * support instruction emulation.
+	 * support instruction emulation.  Ditto for flushing by ASID, as SEV
+	 * guests are bound to a single ASID, i.e. KVM can't rotate to a new
+	 * ASID to effect a TLB flush.
 	 */
 	if (!boot_cpu_has(X86_FEATURE_SEV) ||
-	    WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_DECODEASSISTS)))
+	    WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_DECODEASSISTS)) ||
+	    WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_FLUSHBYASID)))
 		goto out;
 
 	/* Retrieve SEV CPUID information */
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 7fb51424fc74..e90b429c84f1 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3563,8 +3563,15 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu)
 	if (svm->nmi_l1_to_l2)
 		return;
 
-	svm->nmi_masked = true;
-	svm_set_iret_intercept(svm);
+	/*
+	 * No need to manually track NMI masking when vNMI is enabled, hardware
+	 * automatically sets V_NMI_BLOCKING_MASK as appropriate, including the
+	 * case where software directly injects an NMI.
+	 */
+	if (!is_vnmi_enabled(svm)) {
+		svm->nmi_masked = true;
+		svm_set_iret_intercept(svm);
+	}
 	++vcpu->stat.nmi_injections;
 }
 
@@ -5079,6 +5086,13 @@ static __init void svm_set_cpu_caps(void)
 		kvm_cpu_cap_set(X86_FEATURE_SVM);
 		kvm_cpu_cap_set(X86_FEATURE_VMCBCLEAN);
 
+		/*
+		 * KVM currently flushes TLBs on *every* nested SVM transition,
+		 * and so for all intents and purposes KVM supports flushing by
+		 * ASID, i.e. KVM is guaranteed to honor every L1 ASID flush.
+		 */
+		kvm_cpu_cap_set(X86_FEATURE_FLUSHBYASID);
+
 		if (nrips)
 			kvm_cpu_cap_set(X86_FEATURE_NRIPS);
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index c409f934c377..8ef95139cd24 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -148,7 +148,9 @@ struct vmcb_ctrl_area_cached {
 	u64 virt_ext;
 	u32 clean;
 	union {
+#if IS_ENABLED(CONFIG_HYPERV) || IS_ENABLED(CONFIG_KVM_HYPERV)
 		struct hv_vmcb_enlightenments hv_enlightenments;
+#endif
 		u8 reserved_sw[32];
 	};
 };
diff --git a/arch/x86/kvm/svm/svm_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c
index 7af8422d3382..3971b3ea5d04 100644
--- a/arch/x86/kvm/svm/svm_onhyperv.c
+++ b/arch/x86/kvm/svm/svm_onhyperv.c
@@ -18,18 +18,14 @@
 int svm_hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu)
 {
 	struct hv_vmcb_enlightenments *hve;
-	struct hv_partition_assist_pg **p_hv_pa_pg =
-			&to_kvm_hv(vcpu->kvm)->hv_pa_pg;
+	hpa_t partition_assist_page = hv_get_partition_assist_page(vcpu);
 
-	if (!*p_hv_pa_pg)
-		*p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL);
-
-	if (!*p_hv_pa_pg)
+	if (partition_assist_page == INVALID_PAGE)
 		return -ENOMEM;
 
 	hve = &to_svm(vcpu)->vmcb->control.hv_enlightenments;
 
-	hve->partition_assist_page = __pa(*p_hv_pa_pg);
+	hve->partition_assist_page = partition_assist_page;
 	hve->hv_vm_id = (unsigned long)vcpu->kvm;
 	if (!hve->hv_enlightenments_control.nested_flush_hypercall) {
 		hve->hv_enlightenments_control.nested_flush_hypercall = 1;
diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h
index 36c8af87a707..4e725854c63a 100644
--- a/arch/x86/kvm/svm/svm_ops.h
+++ b/arch/x86/kvm/svm/svm_ops.h
@@ -8,7 +8,7 @@
 
 #define svm_asm(insn, clobber...)				\
 do {								\
-	asm_volatile_goto("1: " __stringify(insn) "\n\t"	\
+	asm goto("1: " __stringify(insn) "\n\t"	\
 			  _ASM_EXTABLE(1b, %l[fault])		\
 			  ::: clobber : fault);			\
 	return;							\
@@ -18,7 +18,7 @@ fault:								\
 
 #define svm_asm1(insn, op1, clobber...)				\
 do {								\
-	asm_volatile_goto("1: "  __stringify(insn) " %0\n\t"	\
+	asm goto("1: "  __stringify(insn) " %0\n\t"	\
 			  _ASM_EXTABLE(1b, %l[fault])		\
 			  :: op1 : clobber : fault);		\
 	return;							\
@@ -28,7 +28,7 @@ fault:								\
 
 #define svm_asm2(insn, op1, op2, clobber...)				\
 do {									\
-	asm_volatile_goto("1: "  __stringify(insn) " %1, %0\n\t"	\
+	asm goto("1: "  __stringify(insn) " %1, %0\n\t"	\
 			  _ASM_EXTABLE(1b, %l[fault])			\
 			  :: op1, op2 : clobber : fault);		\
 	return;								\
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index ef2ebabb059c..9499f9c6b077 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -270,16 +270,16 @@ SYM_FUNC_START(__svm_vcpu_run)
 	RESTORE_GUEST_SPEC_CTRL_BODY
 	RESTORE_HOST_SPEC_CTRL_BODY
 
-10:	cmpb $0, kvm_rebooting
+10:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 2b
 	ud2
-30:	cmpb $0, kvm_rebooting
+30:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 4b
 	ud2
-50:	cmpb $0, kvm_rebooting
+50:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 6b
 	ud2
-70:	cmpb $0, kvm_rebooting
+70:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 8b
 	ud2
 
@@ -381,7 +381,7 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
 	RESTORE_GUEST_SPEC_CTRL_BODY
 	RESTORE_HOST_SPEC_CTRL_BODY
 
-3:	cmpb $0, kvm_rebooting
+3:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 2b
 	ud2
 
diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c
index 313b8bb5b8a7..fab6a1ad98dc 100644
--- a/arch/x86/kvm/vmx/hyperv.c
+++ b/arch/x86/kvm/vmx/hyperv.c
@@ -13,419 +13,6 @@
 
 #define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK
 
-/*
- * Enlightened VMCSv1 doesn't support these:
- *
- *	POSTED_INTR_NV                  = 0x00000002,
- *	GUEST_INTR_STATUS               = 0x00000810,
- *	APIC_ACCESS_ADDR		= 0x00002014,
- *	POSTED_INTR_DESC_ADDR           = 0x00002016,
- *	EOI_EXIT_BITMAP0                = 0x0000201c,
- *	EOI_EXIT_BITMAP1                = 0x0000201e,
- *	EOI_EXIT_BITMAP2                = 0x00002020,
- *	EOI_EXIT_BITMAP3                = 0x00002022,
- *	GUEST_PML_INDEX			= 0x00000812,
- *	PML_ADDRESS			= 0x0000200e,
- *	VM_FUNCTION_CONTROL             = 0x00002018,
- *	EPTP_LIST_ADDRESS               = 0x00002024,
- *	VMREAD_BITMAP                   = 0x00002026,
- *	VMWRITE_BITMAP                  = 0x00002028,
- *
- *	TSC_MULTIPLIER                  = 0x00002032,
- *	PLE_GAP                         = 0x00004020,
- *	PLE_WINDOW                      = 0x00004022,
- *	VMX_PREEMPTION_TIMER_VALUE      = 0x0000482E,
- *
- * Currently unsupported in KVM:
- *	GUEST_IA32_RTIT_CTL		= 0x00002814,
- */
-#define EVMCS1_SUPPORTED_PINCTRL					\
-	(PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR |				\
-	 PIN_BASED_EXT_INTR_MASK |					\
-	 PIN_BASED_NMI_EXITING |					\
-	 PIN_BASED_VIRTUAL_NMIS)
-
-#define EVMCS1_SUPPORTED_EXEC_CTRL					\
-	(CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR |				\
-	 CPU_BASED_HLT_EXITING |					\
-	 CPU_BASED_CR3_LOAD_EXITING |					\
-	 CPU_BASED_CR3_STORE_EXITING |					\
-	 CPU_BASED_UNCOND_IO_EXITING |					\
-	 CPU_BASED_MOV_DR_EXITING |					\
-	 CPU_BASED_USE_TSC_OFFSETTING |					\
-	 CPU_BASED_MWAIT_EXITING |					\
-	 CPU_BASED_MONITOR_EXITING |					\
-	 CPU_BASED_INVLPG_EXITING |					\
-	 CPU_BASED_RDPMC_EXITING |					\
-	 CPU_BASED_INTR_WINDOW_EXITING |				\
-	 CPU_BASED_CR8_LOAD_EXITING |					\
-	 CPU_BASED_CR8_STORE_EXITING |					\
-	 CPU_BASED_RDTSC_EXITING |					\
-	 CPU_BASED_TPR_SHADOW |						\
-	 CPU_BASED_USE_IO_BITMAPS |					\
-	 CPU_BASED_MONITOR_TRAP_FLAG |					\
-	 CPU_BASED_USE_MSR_BITMAPS |					\
-	 CPU_BASED_NMI_WINDOW_EXITING |					\
-	 CPU_BASED_PAUSE_EXITING |					\
-	 CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)
-
-#define EVMCS1_SUPPORTED_2NDEXEC					\
-	(SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |			\
-	 SECONDARY_EXEC_WBINVD_EXITING |				\
-	 SECONDARY_EXEC_ENABLE_VPID |					\
-	 SECONDARY_EXEC_ENABLE_EPT |					\
-	 SECONDARY_EXEC_UNRESTRICTED_GUEST |				\
-	 SECONDARY_EXEC_DESC |						\
-	 SECONDARY_EXEC_ENABLE_RDTSCP |					\
-	 SECONDARY_EXEC_ENABLE_INVPCID |				\
-	 SECONDARY_EXEC_ENABLE_XSAVES |					\
-	 SECONDARY_EXEC_RDSEED_EXITING |				\
-	 SECONDARY_EXEC_RDRAND_EXITING |				\
-	 SECONDARY_EXEC_TSC_SCALING |					\
-	 SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE |				\
-	 SECONDARY_EXEC_PT_USE_GPA |					\
-	 SECONDARY_EXEC_PT_CONCEAL_VMX |				\
-	 SECONDARY_EXEC_BUS_LOCK_DETECTION |				\
-	 SECONDARY_EXEC_NOTIFY_VM_EXITING |				\
-	 SECONDARY_EXEC_ENCLS_EXITING)
-
-#define EVMCS1_SUPPORTED_3RDEXEC (0ULL)
-
-#define EVMCS1_SUPPORTED_VMEXIT_CTRL					\
-	(VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |				\
-	 VM_EXIT_SAVE_DEBUG_CONTROLS |					\
-	 VM_EXIT_ACK_INTR_ON_EXIT |					\
-	 VM_EXIT_HOST_ADDR_SPACE_SIZE |					\
-	 VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL |				\
-	 VM_EXIT_SAVE_IA32_PAT |					\
-	 VM_EXIT_LOAD_IA32_PAT |					\
-	 VM_EXIT_SAVE_IA32_EFER |					\
-	 VM_EXIT_LOAD_IA32_EFER |					\
-	 VM_EXIT_CLEAR_BNDCFGS |					\
-	 VM_EXIT_PT_CONCEAL_PIP |					\
-	 VM_EXIT_CLEAR_IA32_RTIT_CTL)
-
-#define EVMCS1_SUPPORTED_VMENTRY_CTRL					\
-	(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR |				\
-	 VM_ENTRY_LOAD_DEBUG_CONTROLS |					\
-	 VM_ENTRY_IA32E_MODE |						\
-	 VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL |				\
-	 VM_ENTRY_LOAD_IA32_PAT |					\
-	 VM_ENTRY_LOAD_IA32_EFER |					\
-	 VM_ENTRY_LOAD_BNDCFGS |					\
-	 VM_ENTRY_PT_CONCEAL_PIP |					\
-	 VM_ENTRY_LOAD_IA32_RTIT_CTL)
-
-#define EVMCS1_SUPPORTED_VMFUNC (0)
-
-#define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x)
-#define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \
-		{EVMCS1_OFFSET(name), clean_field}
-
-const struct evmcs_field vmcs_field_to_evmcs_1[] = {
-	/* 64 bit rw */
-	EVMCS1_FIELD(GUEST_RIP, guest_rip,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	EVMCS1_FIELD(GUEST_RSP, guest_rsp,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC),
-	EVMCS1_FIELD(GUEST_RFLAGS, guest_rflags,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC),
-	EVMCS1_FIELD(HOST_IA32_PAT, host_ia32_pat,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_IA32_EFER, host_ia32_efer,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_CR0, host_cr0,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_CR3, host_cr3,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_CR4, host_cr4,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_IA32_SYSENTER_ESP, host_ia32_sysenter_esp,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_IA32_SYSENTER_EIP, host_ia32_sysenter_eip,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_RIP, host_rip,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(IO_BITMAP_A, io_bitmap_a,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP),
-	EVMCS1_FIELD(IO_BITMAP_B, io_bitmap_b,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP),
-	EVMCS1_FIELD(MSR_BITMAP, msr_bitmap,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP),
-	EVMCS1_FIELD(GUEST_ES_BASE, guest_es_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_CS_BASE, guest_cs_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_SS_BASE, guest_ss_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_DS_BASE, guest_ds_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_FS_BASE, guest_fs_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_GS_BASE, guest_gs_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_LDTR_BASE, guest_ldtr_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_TR_BASE, guest_tr_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_GDTR_BASE, guest_gdtr_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_IDTR_BASE, guest_idtr_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(TSC_OFFSET, tsc_offset,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
-	EVMCS1_FIELD(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
-	EVMCS1_FIELD(VMCS_LINK_POINTER, vmcs_link_pointer,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_IA32_PAT, guest_ia32_pat,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_IA32_EFER, guest_ia32_efer,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_IA32_PERF_GLOBAL_CTRL, guest_ia32_perf_global_ctrl,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_PDPTR0, guest_pdptr0,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_PDPTR1, guest_pdptr1,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_PDPTR2, guest_pdptr2,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_PDPTR3, guest_pdptr3,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_PENDING_DBG_EXCEPTIONS, guest_pending_dbg_exceptions,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_SYSENTER_ESP, guest_sysenter_esp,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_SYSENTER_EIP, guest_sysenter_eip,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(CR0_GUEST_HOST_MASK, cr0_guest_host_mask,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
-	EVMCS1_FIELD(CR4_GUEST_HOST_MASK, cr4_guest_host_mask,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
-	EVMCS1_FIELD(CR0_READ_SHADOW, cr0_read_shadow,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
-	EVMCS1_FIELD(CR4_READ_SHADOW, cr4_read_shadow,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
-	EVMCS1_FIELD(GUEST_CR0, guest_cr0,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
-	EVMCS1_FIELD(GUEST_CR3, guest_cr3,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
-	EVMCS1_FIELD(GUEST_CR4, guest_cr4,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
-	EVMCS1_FIELD(GUEST_DR7, guest_dr7,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
-	EVMCS1_FIELD(HOST_FS_BASE, host_fs_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
-	EVMCS1_FIELD(HOST_GS_BASE, host_gs_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
-	EVMCS1_FIELD(HOST_TR_BASE, host_tr_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
-	EVMCS1_FIELD(HOST_GDTR_BASE, host_gdtr_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
-	EVMCS1_FIELD(HOST_IDTR_BASE, host_idtr_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
-	EVMCS1_FIELD(HOST_RSP, host_rsp,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
-	EVMCS1_FIELD(EPT_POINTER, ept_pointer,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT),
-	EVMCS1_FIELD(GUEST_BNDCFGS, guest_bndcfgs,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(XSS_EXIT_BITMAP, xss_exit_bitmap,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
-	EVMCS1_FIELD(ENCLS_EXITING_BITMAP, encls_exiting_bitmap,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
-	EVMCS1_FIELD(TSC_MULTIPLIER, tsc_multiplier,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
-	/*
-	 * Not used by KVM:
-	 *
-	 * EVMCS1_FIELD(0x00006828, guest_ia32_s_cet,
-	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	 * EVMCS1_FIELD(0x0000682A, guest_ssp,
-	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC),
-	 * EVMCS1_FIELD(0x0000682C, guest_ia32_int_ssp_table_addr,
-	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	 * EVMCS1_FIELD(0x00002816, guest_ia32_lbr_ctl,
-	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	 * EVMCS1_FIELD(0x00006C18, host_ia32_s_cet,
-	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	 * EVMCS1_FIELD(0x00006C1A, host_ssp,
-	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	 * EVMCS1_FIELD(0x00006C1C, host_ia32_int_ssp_table_addr,
-	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	 */
-
-	/* 64 bit read only */
-	EVMCS1_FIELD(GUEST_PHYSICAL_ADDRESS, guest_physical_address,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	EVMCS1_FIELD(EXIT_QUALIFICATION, exit_qualification,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	/*
-	 * Not defined in KVM:
-	 *
-	 * EVMCS1_FIELD(0x00006402, exit_io_instruction_ecx,
-	 *		HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE);
-	 * EVMCS1_FIELD(0x00006404, exit_io_instruction_esi,
-	 *		HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE);
-	 * EVMCS1_FIELD(0x00006406, exit_io_instruction_esi,
-	 *		HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE);
-	 * EVMCS1_FIELD(0x00006408, exit_io_instruction_eip,
-	 *		HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE);
-	 */
-	EVMCS1_FIELD(GUEST_LINEAR_ADDRESS, guest_linear_address,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-
-	/*
-	 * No mask defined in the spec as Hyper-V doesn't currently support
-	 * these. Future proof by resetting the whole clean field mask on
-	 * access.
-	 */
-	EVMCS1_FIELD(VM_EXIT_MSR_STORE_ADDR, vm_exit_msr_store_addr,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
-	EVMCS1_FIELD(VM_EXIT_MSR_LOAD_ADDR, vm_exit_msr_load_addr,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
-	EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
-
-	/* 32 bit rw */
-	EVMCS1_FIELD(TPR_THRESHOLD, tpr_threshold,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	EVMCS1_FIELD(GUEST_INTERRUPTIBILITY_INFO, guest_interruptibility_info,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC),
-	EVMCS1_FIELD(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC),
-	EVMCS1_FIELD(EXCEPTION_BITMAP, exception_bitmap,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN),
-	EVMCS1_FIELD(VM_ENTRY_CONTROLS, vm_entry_controls,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY),
-	EVMCS1_FIELD(VM_ENTRY_INTR_INFO_FIELD, vm_entry_intr_info_field,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT),
-	EVMCS1_FIELD(VM_ENTRY_EXCEPTION_ERROR_CODE,
-		     vm_entry_exception_error_code,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT),
-	EVMCS1_FIELD(VM_ENTRY_INSTRUCTION_LEN, vm_entry_instruction_len,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT),
-	EVMCS1_FIELD(HOST_IA32_SYSENTER_CS, host_ia32_sysenter_cs,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1),
-	EVMCS1_FIELD(VM_EXIT_CONTROLS, vm_exit_controls,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1),
-	EVMCS1_FIELD(SECONDARY_VM_EXEC_CONTROL, secondary_vm_exec_control,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1),
-	EVMCS1_FIELD(GUEST_ES_LIMIT, guest_es_limit,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_CS_LIMIT, guest_cs_limit,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_SS_LIMIT, guest_ss_limit,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_DS_LIMIT, guest_ds_limit,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_FS_LIMIT, guest_fs_limit,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_GS_LIMIT, guest_gs_limit,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_LDTR_LIMIT, guest_ldtr_limit,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_TR_LIMIT, guest_tr_limit,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_GDTR_LIMIT, guest_gdtr_limit,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_IDTR_LIMIT, guest_idtr_limit,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_ES_AR_BYTES, guest_es_ar_bytes,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_CS_AR_BYTES, guest_cs_ar_bytes,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_SS_AR_BYTES, guest_ss_ar_bytes,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_DS_AR_BYTES, guest_ds_ar_bytes,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_FS_AR_BYTES, guest_fs_ar_bytes,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_GS_AR_BYTES, guest_gs_ar_bytes,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_LDTR_AR_BYTES, guest_ldtr_ar_bytes,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_TR_AR_BYTES, guest_tr_ar_bytes,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_ACTIVITY_STATE, guest_activity_state,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_SYSENTER_CS, guest_sysenter_cs,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-
-	/* 32 bit read only */
-	EVMCS1_FIELD(VM_INSTRUCTION_ERROR, vm_instruction_error,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	EVMCS1_FIELD(VM_EXIT_REASON, vm_exit_reason,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	EVMCS1_FIELD(VM_EXIT_INTR_INFO, vm_exit_intr_info,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	EVMCS1_FIELD(VM_EXIT_INTR_ERROR_CODE, vm_exit_intr_error_code,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	EVMCS1_FIELD(IDT_VECTORING_INFO_FIELD, idt_vectoring_info_field,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	EVMCS1_FIELD(IDT_VECTORING_ERROR_CODE, idt_vectoring_error_code,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	EVMCS1_FIELD(VM_EXIT_INSTRUCTION_LEN, vm_exit_instruction_len,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	EVMCS1_FIELD(VMX_INSTRUCTION_INFO, vmx_instruction_info,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-
-	/* No mask defined in the spec (not used) */
-	EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MASK, page_fault_error_code_mask,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
-	EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MATCH, page_fault_error_code_match,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
-	EVMCS1_FIELD(CR3_TARGET_COUNT, cr3_target_count,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
-	EVMCS1_FIELD(VM_EXIT_MSR_STORE_COUNT, vm_exit_msr_store_count,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
-	EVMCS1_FIELD(VM_EXIT_MSR_LOAD_COUNT, vm_exit_msr_load_count,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
-	EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_COUNT, vm_entry_msr_load_count,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
-
-	/* 16 bit rw */
-	EVMCS1_FIELD(HOST_ES_SELECTOR, host_es_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_CS_SELECTOR, host_cs_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_SS_SELECTOR, host_ss_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_DS_SELECTOR, host_ds_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_FS_SELECTOR, host_fs_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_GS_SELECTOR, host_gs_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_TR_SELECTOR, host_tr_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(GUEST_ES_SELECTOR, guest_es_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_CS_SELECTOR, guest_cs_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_SS_SELECTOR, guest_ss_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_DS_SELECTOR, guest_ds_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_FS_SELECTOR, guest_fs_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_GS_SELECTOR, guest_gs_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_LDTR_SELECTOR, guest_ldtr_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_TR_SELECTOR, guest_tr_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT),
-};
-const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1);
-
 u64 nested_get_evmptr(struct kvm_vcpu *vcpu)
 {
 	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
@@ -608,40 +195,6 @@ int nested_evmcs_check_controls(struct vmcs12 *vmcs12)
 	return 0;
 }
 
-#if IS_ENABLED(CONFIG_HYPERV)
-DEFINE_STATIC_KEY_FALSE(__kvm_is_using_evmcs);
-
-/*
- * KVM on Hyper-V always uses the latest known eVMCSv1 revision, the assumption
- * is: in case a feature has corresponding fields in eVMCS described and it was
- * exposed in VMX feature MSRs, KVM is free to use it. Warn if KVM meets a
- * feature which has no corresponding eVMCS field, this likely means that KVM
- * needs to be updated.
- */
-#define evmcs_check_vmcs_conf(field, ctrl)					\
-	do {									\
-		typeof(vmcs_conf->field) unsupported;				\
-										\
-		unsupported = vmcs_conf->field & ~EVMCS1_SUPPORTED_ ## ctrl;	\
-		if (unsupported) {						\
-			pr_warn_once(#field " unsupported with eVMCS: 0x%llx\n",\
-				     (u64)unsupported);				\
-			vmcs_conf->field &= EVMCS1_SUPPORTED_ ## ctrl;		\
-		}								\
-	}									\
-	while (0)
-
-void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf)
-{
-	evmcs_check_vmcs_conf(cpu_based_exec_ctrl, EXEC_CTRL);
-	evmcs_check_vmcs_conf(pin_based_exec_ctrl, PINCTRL);
-	evmcs_check_vmcs_conf(cpu_based_2nd_exec_ctrl, 2NDEXEC);
-	evmcs_check_vmcs_conf(cpu_based_3rd_exec_ctrl, 3RDEXEC);
-	evmcs_check_vmcs_conf(vmentry_ctrl, VMENTRY_CTRL);
-	evmcs_check_vmcs_conf(vmexit_ctrl, VMEXIT_CTRL);
-}
-#endif
-
 int nested_enable_evmcs(struct kvm_vcpu *vcpu,
 			uint16_t *vmcs_version)
 {
diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h
index 9623fe1651c4..a87407412615 100644
--- a/arch/x86/kvm/vmx/hyperv.h
+++ b/arch/x86/kvm/vmx/hyperv.h
@@ -2,199 +2,89 @@
 #ifndef __KVM_X86_VMX_HYPERV_H
 #define __KVM_X86_VMX_HYPERV_H
 
-#include <linux/jump_label.h>
-
-#include <asm/hyperv-tlfs.h>
-#include <asm/mshyperv.h>
-#include <asm/vmx.h>
-
-#include "../hyperv.h"
-
-#include "capabilities.h"
-#include "vmcs.h"
+#include <linux/kvm_host.h>
 #include "vmcs12.h"
+#include "vmx.h"
 
-struct vmcs_config;
-
-#define current_evmcs ((struct hv_enlightened_vmcs *)this_cpu_read(current_vmcs))
-
-#define KVM_EVMCS_VERSION 1
+#define EVMPTR_INVALID (-1ULL)
+#define EVMPTR_MAP_PENDING (-2ULL)
 
-struct evmcs_field {
-	u16 offset;
-	u16 clean_field;
+enum nested_evmptrld_status {
+	EVMPTRLD_DISABLED,
+	EVMPTRLD_SUCCEEDED,
+	EVMPTRLD_VMFAIL,
+	EVMPTRLD_ERROR,
 };
 
-extern const struct evmcs_field vmcs_field_to_evmcs_1[];
-extern const unsigned int nr_evmcs_1_fields;
-
-static __always_inline int evmcs_field_offset(unsigned long field,
-					      u16 *clean_field)
-{
-	unsigned int index = ROL16(field, 6);
-	const struct evmcs_field *evmcs_field;
-
-	if (unlikely(index >= nr_evmcs_1_fields))
-		return -ENOENT;
-
-	evmcs_field = &vmcs_field_to_evmcs_1[index];
-
-	/*
-	 * Use offset=0 to detect holes in eVMCS. This offset belongs to
-	 * 'revision_id' but this field has no encoding and is supposed to
-	 * be accessed directly.
-	 */
-	if (unlikely(!evmcs_field->offset))
-		return -ENOENT;
-
-	if (clean_field)
-		*clean_field = evmcs_field->clean_field;
-
-	return evmcs_field->offset;
-}
-
-static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs,
-				 unsigned long field, u16 offset)
+#ifdef CONFIG_KVM_HYPERV
+static inline bool evmptr_is_valid(u64 evmptr)
 {
-	/*
-	 * vmcs12_read_any() doesn't care whether the supplied structure
-	 * is 'struct vmcs12' or 'struct hv_enlightened_vmcs' as it takes
-	 * the exact offset of the required field, use it for convenience
-	 * here.
-	 */
-	return vmcs12_read_any((void *)evmcs, field, offset);
+	return evmptr != EVMPTR_INVALID && evmptr != EVMPTR_MAP_PENDING;
 }
 
-#if IS_ENABLED(CONFIG_HYPERV)
-
-DECLARE_STATIC_KEY_FALSE(__kvm_is_using_evmcs);
-
-static __always_inline bool kvm_is_using_evmcs(void)
+static inline bool nested_vmx_is_evmptr12_valid(struct vcpu_vmx *vmx)
 {
-	return static_branch_unlikely(&__kvm_is_using_evmcs);
+	return evmptr_is_valid(vmx->nested.hv_evmcs_vmptr);
 }
 
-static __always_inline int get_evmcs_offset(unsigned long field,
-					    u16 *clean_field)
+static inline bool evmptr_is_set(u64 evmptr)
 {
-	int offset = evmcs_field_offset(field, clean_field);
-
-	WARN_ONCE(offset < 0, "accessing unsupported EVMCS field %lx\n", field);
-	return offset;
+	return evmptr != EVMPTR_INVALID;
 }
 
-static __always_inline void evmcs_write64(unsigned long field, u64 value)
+static inline bool nested_vmx_is_evmptr12_set(struct vcpu_vmx *vmx)
 {
-	u16 clean_field;
-	int offset = get_evmcs_offset(field, &clean_field);
-
-	if (offset < 0)
-		return;
-
-	*(u64 *)((char *)current_evmcs + offset) = value;
-
-	current_evmcs->hv_clean_fields &= ~clean_field;
+	return evmptr_is_set(vmx->nested.hv_evmcs_vmptr);
 }
 
-static __always_inline void evmcs_write32(unsigned long field, u32 value)
+static inline struct hv_enlightened_vmcs *nested_vmx_evmcs(struct vcpu_vmx *vmx)
 {
-	u16 clean_field;
-	int offset = get_evmcs_offset(field, &clean_field);
-
-	if (offset < 0)
-		return;
-
-	*(u32 *)((char *)current_evmcs + offset) = value;
-	current_evmcs->hv_clean_fields &= ~clean_field;
+	return vmx->nested.hv_evmcs;
 }
 
-static __always_inline void evmcs_write16(unsigned long field, u16 value)
+static inline bool guest_cpuid_has_evmcs(struct kvm_vcpu *vcpu)
 {
-	u16 clean_field;
-	int offset = get_evmcs_offset(field, &clean_field);
-
-	if (offset < 0)
-		return;
-
-	*(u16 *)((char *)current_evmcs + offset) = value;
-	current_evmcs->hv_clean_fields &= ~clean_field;
+	/*
+	 * eVMCS is exposed to the guest if Hyper-V is enabled in CPUID and
+	 * eVMCS has been explicitly enabled by userspace.
+	 */
+	return vcpu->arch.hyperv_enabled &&
+	       to_vmx(vcpu)->nested.enlightened_vmcs_enabled;
 }
 
-static __always_inline u64 evmcs_read64(unsigned long field)
+u64 nested_get_evmptr(struct kvm_vcpu *vcpu);
+uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu);
+int nested_enable_evmcs(struct kvm_vcpu *vcpu,
+			uint16_t *vmcs_version);
+void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
+int nested_evmcs_check_controls(struct vmcs12 *vmcs12);
+bool nested_evmcs_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu);
+void vmx_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu);
+#else
+static inline bool evmptr_is_valid(u64 evmptr)
 {
-	int offset = get_evmcs_offset(field, NULL);
-
-	if (offset < 0)
-		return 0;
-
-	return *(u64 *)((char *)current_evmcs + offset);
+	return false;
 }
 
-static __always_inline u32 evmcs_read32(unsigned long field)
+static inline bool nested_vmx_is_evmptr12_valid(struct vcpu_vmx *vmx)
 {
-	int offset = get_evmcs_offset(field, NULL);
-
-	if (offset < 0)
-		return 0;
-
-	return *(u32 *)((char *)current_evmcs + offset);
+	return false;
 }
 
-static __always_inline u16 evmcs_read16(unsigned long field)
+static inline bool evmptr_is_set(u64 evmptr)
 {
-	int offset = get_evmcs_offset(field, NULL);
-
-	if (offset < 0)
-		return 0;
-
-	return *(u16 *)((char *)current_evmcs + offset);
+	return false;
 }
 
-static inline void evmcs_load(u64 phys_addr)
+static inline bool nested_vmx_is_evmptr12_set(struct vcpu_vmx *vmx)
 {
-	struct hv_vp_assist_page *vp_ap =
-		hv_get_vp_assist_page(smp_processor_id());
-
-	if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall)
-		vp_ap->nested_control.features.directhypercall = 1;
-	vp_ap->current_nested_vmcs = phys_addr;
-	vp_ap->enlighten_vmentry = 1;
+	return false;
 }
 
-void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf);
-#else /* !IS_ENABLED(CONFIG_HYPERV) */
-static __always_inline bool kvm_is_using_evmcs(void) { return false; }
-static __always_inline void evmcs_write64(unsigned long field, u64 value) {}
-static __always_inline void evmcs_write32(unsigned long field, u32 value) {}
-static __always_inline void evmcs_write16(unsigned long field, u16 value) {}
-static __always_inline u64 evmcs_read64(unsigned long field) { return 0; }
-static __always_inline u32 evmcs_read32(unsigned long field) { return 0; }
-static __always_inline u16 evmcs_read16(unsigned long field) { return 0; }
-static inline void evmcs_load(u64 phys_addr) {}
-#endif /* IS_ENABLED(CONFIG_HYPERV) */
-
-#define EVMPTR_INVALID (-1ULL)
-#define EVMPTR_MAP_PENDING (-2ULL)
-
-static inline bool evmptr_is_valid(u64 evmptr)
+static inline struct hv_enlightened_vmcs *nested_vmx_evmcs(struct vcpu_vmx *vmx)
 {
-	return evmptr != EVMPTR_INVALID && evmptr != EVMPTR_MAP_PENDING;
+	return NULL;
 }
-
-enum nested_evmptrld_status {
-	EVMPTRLD_DISABLED,
-	EVMPTRLD_SUCCEEDED,
-	EVMPTRLD_VMFAIL,
-	EVMPTRLD_ERROR,
-};
-
-u64 nested_get_evmptr(struct kvm_vcpu *vcpu);
-uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu);
-int nested_enable_evmcs(struct kvm_vcpu *vcpu,
-			uint16_t *vmcs_version);
-void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
-int nested_evmcs_check_controls(struct vmcs12 *vmcs12);
-bool nested_evmcs_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu);
-void vmx_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu);
+#endif
 
 #endif /* __KVM_X86_VMX_HYPERV_H */
diff --git a/arch/x86/kvm/vmx/hyperv_evmcs.c b/arch/x86/kvm/vmx/hyperv_evmcs.c
new file mode 100644
index 000000000000..904bfcd1519b
--- /dev/null
+++ b/arch/x86/kvm/vmx/hyperv_evmcs.c
@@ -0,0 +1,315 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This file contains common code for working with Enlightened VMCS which is
+ * used both by Hyper-V on KVM and KVM on Hyper-V.
+ */
+
+#include "hyperv_evmcs.h"
+
+#define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x)
+#define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \
+		{EVMCS1_OFFSET(name), clean_field}
+
+const struct evmcs_field vmcs_field_to_evmcs_1[] = {
+	/* 64 bit rw */
+	EVMCS1_FIELD(GUEST_RIP, guest_rip,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	EVMCS1_FIELD(GUEST_RSP, guest_rsp,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC),
+	EVMCS1_FIELD(GUEST_RFLAGS, guest_rflags,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC),
+	EVMCS1_FIELD(HOST_IA32_PAT, host_ia32_pat,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_IA32_EFER, host_ia32_efer,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_CR0, host_cr0,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_CR3, host_cr3,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_CR4, host_cr4,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_IA32_SYSENTER_ESP, host_ia32_sysenter_esp,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_IA32_SYSENTER_EIP, host_ia32_sysenter_eip,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_RIP, host_rip,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(IO_BITMAP_A, io_bitmap_a,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP),
+	EVMCS1_FIELD(IO_BITMAP_B, io_bitmap_b,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP),
+	EVMCS1_FIELD(MSR_BITMAP, msr_bitmap,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP),
+	EVMCS1_FIELD(GUEST_ES_BASE, guest_es_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_CS_BASE, guest_cs_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_SS_BASE, guest_ss_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_DS_BASE, guest_ds_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_FS_BASE, guest_fs_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_GS_BASE, guest_gs_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_LDTR_BASE, guest_ldtr_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_TR_BASE, guest_tr_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_GDTR_BASE, guest_gdtr_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_IDTR_BASE, guest_idtr_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(TSC_OFFSET, tsc_offset,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
+	EVMCS1_FIELD(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
+	EVMCS1_FIELD(VMCS_LINK_POINTER, vmcs_link_pointer,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_IA32_PAT, guest_ia32_pat,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_IA32_EFER, guest_ia32_efer,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_IA32_PERF_GLOBAL_CTRL, guest_ia32_perf_global_ctrl,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_PDPTR0, guest_pdptr0,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_PDPTR1, guest_pdptr1,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_PDPTR2, guest_pdptr2,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_PDPTR3, guest_pdptr3,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_PENDING_DBG_EXCEPTIONS, guest_pending_dbg_exceptions,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_SYSENTER_ESP, guest_sysenter_esp,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_SYSENTER_EIP, guest_sysenter_eip,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(CR0_GUEST_HOST_MASK, cr0_guest_host_mask,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
+	EVMCS1_FIELD(CR4_GUEST_HOST_MASK, cr4_guest_host_mask,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
+	EVMCS1_FIELD(CR0_READ_SHADOW, cr0_read_shadow,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
+	EVMCS1_FIELD(CR4_READ_SHADOW, cr4_read_shadow,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
+	EVMCS1_FIELD(GUEST_CR0, guest_cr0,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
+	EVMCS1_FIELD(GUEST_CR3, guest_cr3,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
+	EVMCS1_FIELD(GUEST_CR4, guest_cr4,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
+	EVMCS1_FIELD(GUEST_DR7, guest_dr7,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
+	EVMCS1_FIELD(HOST_FS_BASE, host_fs_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
+	EVMCS1_FIELD(HOST_GS_BASE, host_gs_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
+	EVMCS1_FIELD(HOST_TR_BASE, host_tr_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
+	EVMCS1_FIELD(HOST_GDTR_BASE, host_gdtr_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
+	EVMCS1_FIELD(HOST_IDTR_BASE, host_idtr_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
+	EVMCS1_FIELD(HOST_RSP, host_rsp,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
+	EVMCS1_FIELD(EPT_POINTER, ept_pointer,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT),
+	EVMCS1_FIELD(GUEST_BNDCFGS, guest_bndcfgs,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(XSS_EXIT_BITMAP, xss_exit_bitmap,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
+	EVMCS1_FIELD(ENCLS_EXITING_BITMAP, encls_exiting_bitmap,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
+	EVMCS1_FIELD(TSC_MULTIPLIER, tsc_multiplier,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
+	/*
+	 * Not used by KVM:
+	 *
+	 * EVMCS1_FIELD(0x00006828, guest_ia32_s_cet,
+	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	 * EVMCS1_FIELD(0x0000682A, guest_ssp,
+	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC),
+	 * EVMCS1_FIELD(0x0000682C, guest_ia32_int_ssp_table_addr,
+	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	 * EVMCS1_FIELD(0x00002816, guest_ia32_lbr_ctl,
+	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	 * EVMCS1_FIELD(0x00006C18, host_ia32_s_cet,
+	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	 * EVMCS1_FIELD(0x00006C1A, host_ssp,
+	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	 * EVMCS1_FIELD(0x00006C1C, host_ia32_int_ssp_table_addr,
+	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	 */
+
+	/* 64 bit read only */
+	EVMCS1_FIELD(GUEST_PHYSICAL_ADDRESS, guest_physical_address,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	EVMCS1_FIELD(EXIT_QUALIFICATION, exit_qualification,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	/*
+	 * Not defined in KVM:
+	 *
+	 * EVMCS1_FIELD(0x00006402, exit_io_instruction_ecx,
+	 *		HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE);
+	 * EVMCS1_FIELD(0x00006404, exit_io_instruction_esi,
+	 *		HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE);
+	 * EVMCS1_FIELD(0x00006406, exit_io_instruction_esi,
+	 *		HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE);
+	 * EVMCS1_FIELD(0x00006408, exit_io_instruction_eip,
+	 *		HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE);
+	 */
+	EVMCS1_FIELD(GUEST_LINEAR_ADDRESS, guest_linear_address,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+
+	/*
+	 * No mask defined in the spec as Hyper-V doesn't currently support
+	 * these. Future proof by resetting the whole clean field mask on
+	 * access.
+	 */
+	EVMCS1_FIELD(VM_EXIT_MSR_STORE_ADDR, vm_exit_msr_store_addr,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
+	EVMCS1_FIELD(VM_EXIT_MSR_LOAD_ADDR, vm_exit_msr_load_addr,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
+	EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
+
+	/* 32 bit rw */
+	EVMCS1_FIELD(TPR_THRESHOLD, tpr_threshold,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	EVMCS1_FIELD(GUEST_INTERRUPTIBILITY_INFO, guest_interruptibility_info,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC),
+	EVMCS1_FIELD(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC),
+	EVMCS1_FIELD(EXCEPTION_BITMAP, exception_bitmap,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN),
+	EVMCS1_FIELD(VM_ENTRY_CONTROLS, vm_entry_controls,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY),
+	EVMCS1_FIELD(VM_ENTRY_INTR_INFO_FIELD, vm_entry_intr_info_field,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT),
+	EVMCS1_FIELD(VM_ENTRY_EXCEPTION_ERROR_CODE,
+		     vm_entry_exception_error_code,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT),
+	EVMCS1_FIELD(VM_ENTRY_INSTRUCTION_LEN, vm_entry_instruction_len,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT),
+	EVMCS1_FIELD(HOST_IA32_SYSENTER_CS, host_ia32_sysenter_cs,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1),
+	EVMCS1_FIELD(VM_EXIT_CONTROLS, vm_exit_controls,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1),
+	EVMCS1_FIELD(SECONDARY_VM_EXEC_CONTROL, secondary_vm_exec_control,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1),
+	EVMCS1_FIELD(GUEST_ES_LIMIT, guest_es_limit,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_CS_LIMIT, guest_cs_limit,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_SS_LIMIT, guest_ss_limit,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_DS_LIMIT, guest_ds_limit,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_FS_LIMIT, guest_fs_limit,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_GS_LIMIT, guest_gs_limit,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_LDTR_LIMIT, guest_ldtr_limit,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_TR_LIMIT, guest_tr_limit,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_GDTR_LIMIT, guest_gdtr_limit,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_IDTR_LIMIT, guest_idtr_limit,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_ES_AR_BYTES, guest_es_ar_bytes,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_CS_AR_BYTES, guest_cs_ar_bytes,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_SS_AR_BYTES, guest_ss_ar_bytes,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_DS_AR_BYTES, guest_ds_ar_bytes,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_FS_AR_BYTES, guest_fs_ar_bytes,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_GS_AR_BYTES, guest_gs_ar_bytes,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_LDTR_AR_BYTES, guest_ldtr_ar_bytes,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_TR_AR_BYTES, guest_tr_ar_bytes,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_ACTIVITY_STATE, guest_activity_state,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_SYSENTER_CS, guest_sysenter_cs,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+
+	/* 32 bit read only */
+	EVMCS1_FIELD(VM_INSTRUCTION_ERROR, vm_instruction_error,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	EVMCS1_FIELD(VM_EXIT_REASON, vm_exit_reason,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	EVMCS1_FIELD(VM_EXIT_INTR_INFO, vm_exit_intr_info,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	EVMCS1_FIELD(VM_EXIT_INTR_ERROR_CODE, vm_exit_intr_error_code,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	EVMCS1_FIELD(IDT_VECTORING_INFO_FIELD, idt_vectoring_info_field,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	EVMCS1_FIELD(IDT_VECTORING_ERROR_CODE, idt_vectoring_error_code,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	EVMCS1_FIELD(VM_EXIT_INSTRUCTION_LEN, vm_exit_instruction_len,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	EVMCS1_FIELD(VMX_INSTRUCTION_INFO, vmx_instruction_info,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+
+	/* No mask defined in the spec (not used) */
+	EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MASK, page_fault_error_code_mask,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
+	EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MATCH, page_fault_error_code_match,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
+	EVMCS1_FIELD(CR3_TARGET_COUNT, cr3_target_count,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
+	EVMCS1_FIELD(VM_EXIT_MSR_STORE_COUNT, vm_exit_msr_store_count,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
+	EVMCS1_FIELD(VM_EXIT_MSR_LOAD_COUNT, vm_exit_msr_load_count,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
+	EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_COUNT, vm_entry_msr_load_count,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
+
+	/* 16 bit rw */
+	EVMCS1_FIELD(HOST_ES_SELECTOR, host_es_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_CS_SELECTOR, host_cs_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_SS_SELECTOR, host_ss_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_DS_SELECTOR, host_ds_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_FS_SELECTOR, host_fs_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_GS_SELECTOR, host_gs_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_TR_SELECTOR, host_tr_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(GUEST_ES_SELECTOR, guest_es_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_CS_SELECTOR, guest_cs_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_SS_SELECTOR, guest_ss_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_DS_SELECTOR, guest_ds_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_FS_SELECTOR, guest_fs_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_GS_SELECTOR, guest_gs_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_LDTR_SELECTOR, guest_ldtr_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_TR_SELECTOR, guest_tr_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT),
+};
+const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1);
diff --git a/arch/x86/kvm/vmx/hyperv_evmcs.h b/arch/x86/kvm/vmx/hyperv_evmcs.h
new file mode 100644
index 000000000000..a543fccfc574
--- /dev/null
+++ b/arch/x86/kvm/vmx/hyperv_evmcs.h
@@ -0,0 +1,166 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This file contains common definitions for working with Enlightened VMCS which
+ * are used both by Hyper-V on KVM and KVM on Hyper-V.
+ */
+#ifndef __KVM_X86_VMX_HYPERV_EVMCS_H
+#define __KVM_X86_VMX_HYPERV_EVMCS_H
+
+#include <asm/hyperv-tlfs.h>
+
+#include "capabilities.h"
+#include "vmcs12.h"
+
+#define KVM_EVMCS_VERSION 1
+
+/*
+ * Enlightened VMCSv1 doesn't support these:
+ *
+ *	POSTED_INTR_NV                  = 0x00000002,
+ *	GUEST_INTR_STATUS               = 0x00000810,
+ *	APIC_ACCESS_ADDR		= 0x00002014,
+ *	POSTED_INTR_DESC_ADDR           = 0x00002016,
+ *	EOI_EXIT_BITMAP0                = 0x0000201c,
+ *	EOI_EXIT_BITMAP1                = 0x0000201e,
+ *	EOI_EXIT_BITMAP2                = 0x00002020,
+ *	EOI_EXIT_BITMAP3                = 0x00002022,
+ *	GUEST_PML_INDEX			= 0x00000812,
+ *	PML_ADDRESS			= 0x0000200e,
+ *	VM_FUNCTION_CONTROL             = 0x00002018,
+ *	EPTP_LIST_ADDRESS               = 0x00002024,
+ *	VMREAD_BITMAP                   = 0x00002026,
+ *	VMWRITE_BITMAP                  = 0x00002028,
+ *
+ *	TSC_MULTIPLIER                  = 0x00002032,
+ *	PLE_GAP                         = 0x00004020,
+ *	PLE_WINDOW                      = 0x00004022,
+ *	VMX_PREEMPTION_TIMER_VALUE      = 0x0000482E,
+ *
+ * Currently unsupported in KVM:
+ *	GUEST_IA32_RTIT_CTL		= 0x00002814,
+ */
+#define EVMCS1_SUPPORTED_PINCTRL					\
+	(PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR |				\
+	 PIN_BASED_EXT_INTR_MASK |					\
+	 PIN_BASED_NMI_EXITING |					\
+	 PIN_BASED_VIRTUAL_NMIS)
+
+#define EVMCS1_SUPPORTED_EXEC_CTRL					\
+	(CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR |				\
+	 CPU_BASED_HLT_EXITING |					\
+	 CPU_BASED_CR3_LOAD_EXITING |					\
+	 CPU_BASED_CR3_STORE_EXITING |					\
+	 CPU_BASED_UNCOND_IO_EXITING |					\
+	 CPU_BASED_MOV_DR_EXITING |					\
+	 CPU_BASED_USE_TSC_OFFSETTING |					\
+	 CPU_BASED_MWAIT_EXITING |					\
+	 CPU_BASED_MONITOR_EXITING |					\
+	 CPU_BASED_INVLPG_EXITING |					\
+	 CPU_BASED_RDPMC_EXITING |					\
+	 CPU_BASED_INTR_WINDOW_EXITING |				\
+	 CPU_BASED_CR8_LOAD_EXITING |					\
+	 CPU_BASED_CR8_STORE_EXITING |					\
+	 CPU_BASED_RDTSC_EXITING |					\
+	 CPU_BASED_TPR_SHADOW |						\
+	 CPU_BASED_USE_IO_BITMAPS |					\
+	 CPU_BASED_MONITOR_TRAP_FLAG |					\
+	 CPU_BASED_USE_MSR_BITMAPS |					\
+	 CPU_BASED_NMI_WINDOW_EXITING |					\
+	 CPU_BASED_PAUSE_EXITING |					\
+	 CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)
+
+#define EVMCS1_SUPPORTED_2NDEXEC					\
+	(SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |			\
+	 SECONDARY_EXEC_WBINVD_EXITING |				\
+	 SECONDARY_EXEC_ENABLE_VPID |					\
+	 SECONDARY_EXEC_ENABLE_EPT |					\
+	 SECONDARY_EXEC_UNRESTRICTED_GUEST |				\
+	 SECONDARY_EXEC_DESC |						\
+	 SECONDARY_EXEC_ENABLE_RDTSCP |					\
+	 SECONDARY_EXEC_ENABLE_INVPCID |				\
+	 SECONDARY_EXEC_ENABLE_XSAVES |					\
+	 SECONDARY_EXEC_RDSEED_EXITING |				\
+	 SECONDARY_EXEC_RDRAND_EXITING |				\
+	 SECONDARY_EXEC_TSC_SCALING |					\
+	 SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE |				\
+	 SECONDARY_EXEC_PT_USE_GPA |					\
+	 SECONDARY_EXEC_PT_CONCEAL_VMX |				\
+	 SECONDARY_EXEC_BUS_LOCK_DETECTION |				\
+	 SECONDARY_EXEC_NOTIFY_VM_EXITING |				\
+	 SECONDARY_EXEC_ENCLS_EXITING)
+
+#define EVMCS1_SUPPORTED_3RDEXEC (0ULL)
+
+#define EVMCS1_SUPPORTED_VMEXIT_CTRL					\
+	(VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |				\
+	 VM_EXIT_SAVE_DEBUG_CONTROLS |					\
+	 VM_EXIT_ACK_INTR_ON_EXIT |					\
+	 VM_EXIT_HOST_ADDR_SPACE_SIZE |					\
+	 VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL |				\
+	 VM_EXIT_SAVE_IA32_PAT |					\
+	 VM_EXIT_LOAD_IA32_PAT |					\
+	 VM_EXIT_SAVE_IA32_EFER |					\
+	 VM_EXIT_LOAD_IA32_EFER |					\
+	 VM_EXIT_CLEAR_BNDCFGS |					\
+	 VM_EXIT_PT_CONCEAL_PIP |					\
+	 VM_EXIT_CLEAR_IA32_RTIT_CTL)
+
+#define EVMCS1_SUPPORTED_VMENTRY_CTRL					\
+	(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR |				\
+	 VM_ENTRY_LOAD_DEBUG_CONTROLS |					\
+	 VM_ENTRY_IA32E_MODE |						\
+	 VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL |				\
+	 VM_ENTRY_LOAD_IA32_PAT |					\
+	 VM_ENTRY_LOAD_IA32_EFER |					\
+	 VM_ENTRY_LOAD_BNDCFGS |					\
+	 VM_ENTRY_PT_CONCEAL_PIP |					\
+	 VM_ENTRY_LOAD_IA32_RTIT_CTL)
+
+#define EVMCS1_SUPPORTED_VMFUNC (0)
+
+struct evmcs_field {
+	u16 offset;
+	u16 clean_field;
+};
+
+extern const struct evmcs_field vmcs_field_to_evmcs_1[];
+extern const unsigned int nr_evmcs_1_fields;
+
+static __always_inline int evmcs_field_offset(unsigned long field,
+					      u16 *clean_field)
+{
+	const struct evmcs_field *evmcs_field;
+	unsigned int index = ROL16(field, 6);
+
+	if (unlikely(index >= nr_evmcs_1_fields))
+		return -ENOENT;
+
+	evmcs_field = &vmcs_field_to_evmcs_1[index];
+
+	/*
+	 * Use offset=0 to detect holes in eVMCS. This offset belongs to
+	 * 'revision_id' but this field has no encoding and is supposed to
+	 * be accessed directly.
+	 */
+	if (unlikely(!evmcs_field->offset))
+		return -ENOENT;
+
+	if (clean_field)
+		*clean_field = evmcs_field->clean_field;
+
+	return evmcs_field->offset;
+}
+
+static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs,
+				 unsigned long field, u16 offset)
+{
+	/*
+	 * vmcs12_read_any() doesn't care whether the supplied structure
+	 * is 'struct vmcs12' or 'struct hv_enlightened_vmcs' as it takes
+	 * the exact offset of the required field, use it for convenience
+	 * here.
+	 */
+	return vmcs12_read_any((void *)evmcs, field, offset);
+}
+
+#endif /* __KVM_X86_VMX_HYPERV_H */
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 65826fe23f33..6329a306856b 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -179,7 +179,7 @@ static int nested_vmx_failValid(struct kvm_vcpu *vcpu,
 	 * VM_INSTRUCTION_ERROR is not shadowed. Enlightened VMCS 'shadows' all
 	 * fields and thus must be synced.
 	 */
-	if (to_vmx(vcpu)->nested.hv_evmcs_vmptr != EVMPTR_INVALID)
+	if (nested_vmx_is_evmptr12_set(to_vmx(vcpu)))
 		to_vmx(vcpu)->nested.need_vmcs12_to_shadow_sync = true;
 
 	return kvm_skip_emulated_instruction(vcpu);
@@ -194,7 +194,7 @@ static int nested_vmx_fail(struct kvm_vcpu *vcpu, u32 vm_instruction_error)
 	 * can't be done if there isn't a current VMCS.
 	 */
 	if (vmx->nested.current_vmptr == INVALID_GPA &&
-	    !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))
+	    !nested_vmx_is_evmptr12_valid(vmx))
 		return nested_vmx_failInvalid(vcpu);
 
 	return nested_vmx_failValid(vcpu, vm_instruction_error);
@@ -226,10 +226,11 @@ static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
 
 static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
 {
+#ifdef CONFIG_KVM_HYPERV
 	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) {
+	if (nested_vmx_is_evmptr12_valid(vmx)) {
 		kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true);
 		vmx->nested.hv_evmcs = NULL;
 	}
@@ -241,6 +242,34 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
 		hv_vcpu->nested.vm_id = 0;
 		hv_vcpu->nested.vp_id = 0;
 	}
+#endif
+}
+
+static bool nested_evmcs_handle_vmclear(struct kvm_vcpu *vcpu, gpa_t vmptr)
+{
+#ifdef CONFIG_KVM_HYPERV
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	/*
+	 * When Enlightened VMEntry is enabled on the calling CPU we treat
+	 * memory area pointer by vmptr as Enlightened VMCS (as there's no good
+	 * way to distinguish it from VMCS12) and we must not corrupt it by
+	 * writing to the non-existent 'launch_state' field. The area doesn't
+	 * have to be the currently active EVMCS on the calling CPU and there's
+	 * nothing KVM has to do to transition it from 'active' to 'non-active'
+	 * state. It is possible that the area will stay mapped as
+	 * vmx->nested.hv_evmcs but this shouldn't be a problem.
+	 */
+	if (!guest_cpuid_has_evmcs(vcpu) ||
+	    !evmptr_is_valid(nested_get_evmptr(vcpu)))
+		return false;
+
+	if (nested_vmx_evmcs(vmx) && vmptr == vmx->nested.hv_evmcs_vmptr)
+		nested_release_evmcs(vcpu);
+
+	return true;
+#else
+	return false;
+#endif
 }
 
 static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx,
@@ -572,7 +601,6 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	int msr;
 	unsigned long *msr_bitmap_l1;
 	unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap;
-	struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;
 	struct kvm_host_map *map = &vmx->nested.msr_bitmap_map;
 
 	/* Nothing to do if the MSR bitmap is not in use.  */
@@ -588,10 +616,13 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	 * - Nested hypervisor (L1) has enabled 'Enlightened MSR Bitmap' feature
 	 *   and tells KVM (L0) there were no changes in MSR bitmap for L2.
 	 */
-	if (!vmx->nested.force_msr_bitmap_recalc && evmcs &&
-	    evmcs->hv_enlightenments_control.msr_bitmap &&
-	    evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP)
-		return true;
+	if (!vmx->nested.force_msr_bitmap_recalc) {
+		struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx);
+
+		if (evmcs && evmcs->hv_enlightenments_control.msr_bitmap &&
+		    evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP)
+			return true;
+	}
 
 	if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), map))
 		return false;
@@ -1085,7 +1116,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3,
 			       bool nested_ept, bool reload_pdptrs,
 			       enum vm_entry_failure_code *entry_failure_code)
 {
-	if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3))) {
+	if (CC(!kvm_vcpu_is_legal_cr3(vcpu, cr3))) {
 		*entry_failure_code = ENTRY_FAIL_DEFAULT;
 		return -EINVAL;
 	}
@@ -1139,14 +1170,8 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu,
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	/*
-	 * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or
-	 * L2's VP_ID upon request from the guest. Make sure we check for
-	 * pending entries in the right FIFO upon L1/L2 transition as these
-	 * requests are put by other vCPUs asynchronously.
-	 */
-	if (to_hv_vcpu(vcpu) && enable_ept)
-		kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu);
+	/* Handle pending Hyper-V TLB flush requests */
+	kvm_hv_nested_transtion_tlb_flush(vcpu, enable_ept);
 
 	/*
 	 * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings
@@ -1578,8 +1603,9 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
 
 static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields)
 {
+#ifdef CONFIG_KVM_HYPERV
 	struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12;
-	struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;
+	struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx);
 	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(&vmx->vcpu);
 
 	/* HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE */
@@ -1818,12 +1844,16 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields
 	 */
 
 	return;
+#else /* CONFIG_KVM_HYPERV */
+	KVM_BUG_ON(1, vmx->vcpu.kvm);
+#endif /* CONFIG_KVM_HYPERV */
 }
 
 static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx)
 {
+#ifdef CONFIG_KVM_HYPERV
 	struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12;
-	struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;
+	struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx);
 
 	/*
 	 * Should not be changed by KVM:
@@ -1992,6 +2022,9 @@ static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx)
 	evmcs->guest_bndcfgs = vmcs12->guest_bndcfgs;
 
 	return;
+#else /* CONFIG_KVM_HYPERV */
+	KVM_BUG_ON(1, vmx->vcpu.kvm);
+#endif /* CONFIG_KVM_HYPERV */
 }
 
 /*
@@ -2001,6 +2034,7 @@ static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx)
 static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld(
 	struct kvm_vcpu *vcpu, bool from_launch)
 {
+#ifdef CONFIG_KVM_HYPERV
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	bool evmcs_gpa_changed = false;
 	u64 evmcs_gpa;
@@ -2082,13 +2116,16 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld(
 	}
 
 	return EVMPTRLD_SUCCEEDED;
+#else
+	return EVMPTRLD_DISABLED;
+#endif
 }
 
 void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))
+	if (nested_vmx_is_evmptr12_valid(vmx))
 		copy_vmcs12_to_enlightened(vmx);
 	else
 		copy_vmcs12_to_shadow(vmx);
@@ -2242,7 +2279,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0
 	u32 exec_control;
 	u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12);
 
-	if (vmx->nested.dirty_vmcs12 || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))
+	if (vmx->nested.dirty_vmcs12 || nested_vmx_is_evmptr12_valid(vmx))
 		prepare_vmcs02_early_rare(vmx, vmcs12);
 
 	/*
@@ -2403,7 +2440,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0
 
 static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 {
-	struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs;
+	struct hv_enlightened_vmcs *hv_evmcs = nested_vmx_evmcs(vmx);
 
 	if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
 			   HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) {
@@ -2535,15 +2572,15 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 			  enum vm_entry_failure_code *entry_failure_code)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx);
 	bool load_guest_pdptrs_vmcs12 = false;
 
-	if (vmx->nested.dirty_vmcs12 || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) {
+	if (vmx->nested.dirty_vmcs12 || nested_vmx_is_evmptr12_valid(vmx)) {
 		prepare_vmcs02_rare(vmx, vmcs12);
 		vmx->nested.dirty_vmcs12 = false;
 
-		load_guest_pdptrs_vmcs12 = !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) ||
-			!(vmx->nested.hv_evmcs->hv_clean_fields &
-			  HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1);
+		load_guest_pdptrs_vmcs12 = !nested_vmx_is_evmptr12_valid(vmx) ||
+			!(evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1);
 	}
 
 	if (vmx->nested.nested_run_pending &&
@@ -2664,9 +2701,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	 * bits when it changes a field in eVMCS. Mark all fields as clean
 	 * here.
 	 */
-	if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))
-		vmx->nested.hv_evmcs->hv_clean_fields |=
-			HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+	if (nested_vmx_is_evmptr12_valid(vmx))
+		evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
 
 	return 0;
 }
@@ -2717,7 +2753,7 @@ static bool nested_vmx_check_eptp(struct kvm_vcpu *vcpu, u64 new_eptp)
 	}
 
 	/* Reserved bits should not be set */
-	if (CC(kvm_vcpu_is_illegal_gpa(vcpu, new_eptp) || ((new_eptp >> 7) & 0x1f)))
+	if (CC(!kvm_vcpu_is_legal_gpa(vcpu, new_eptp) || ((new_eptp >> 7) & 0x1f)))
 		return false;
 
 	/* AD, if set, should be supported */
@@ -2888,8 +2924,10 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu,
 	    nested_check_vm_entry_controls(vcpu, vmcs12))
 		return -EINVAL;
 
+#ifdef CONFIG_KVM_HYPERV
 	if (guest_cpuid_has_evmcs(vcpu))
 		return nested_evmcs_check_controls(vmcs12);
+#endif
 
 	return 0;
 }
@@ -2912,7 +2950,7 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 
 	if (CC(!nested_host_cr0_valid(vcpu, vmcs12->host_cr0)) ||
 	    CC(!nested_host_cr4_valid(vcpu, vmcs12->host_cr4)) ||
-	    CC(kvm_vcpu_is_illegal_gpa(vcpu, vmcs12->host_cr3)))
+	    CC(!kvm_vcpu_is_legal_cr3(vcpu, vmcs12->host_cr3)))
 		return -EINVAL;
 
 	if (CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu)) ||
@@ -3161,6 +3199,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+#ifdef CONFIG_KVM_HYPERV
 static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -3188,6 +3227,7 @@ static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu)
 
 	return true;
 }
+#endif
 
 static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 {
@@ -3279,6 +3319,7 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 
 static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu)
 {
+#ifdef CONFIG_KVM_HYPERV
 	/*
 	 * Note: nested_get_evmcs_page() also updates 'vp_assist_page' copy
 	 * in 'struct kvm_vcpu_hv' in case eVMCS is in use, this is mandatory
@@ -3295,6 +3336,7 @@ static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu)
 
 		return false;
 	}
+#endif
 
 	if (is_guest_mode(vcpu) && !nested_get_vmcs12_pages(vcpu))
 		return false;
@@ -3538,7 +3580,7 @@ vmentry_fail_vmexit:
 
 	load_vmcs12_host_state(vcpu, vmcs12);
 	vmcs12->vm_exit_reason = exit_reason.full;
-	if (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))
+	if (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx))
 		vmx->nested.need_vmcs12_to_shadow_sync = true;
 	return NVMX_VMENTRY_VMEXIT;
 }
@@ -3569,7 +3611,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	if (CC(evmptrld_status == EVMPTRLD_VMFAIL))
 		return nested_vmx_failInvalid(vcpu);
 
-	if (CC(!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) &&
+	if (CC(!nested_vmx_is_evmptr12_valid(vmx) &&
 	       vmx->nested.current_vmptr == INVALID_GPA))
 		return nested_vmx_failInvalid(vcpu);
 
@@ -3584,8 +3626,10 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	if (CC(vmcs12->hdr.shadow_vmcs))
 		return nested_vmx_failInvalid(vcpu);
 
-	if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) {
-		copy_enlightened_to_vmcs12(vmx, vmx->nested.hv_evmcs->hv_clean_fields);
+	if (nested_vmx_is_evmptr12_valid(vmx)) {
+		struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx);
+
+		copy_enlightened_to_vmcs12(vmx, evmcs->hv_clean_fields);
 		/* Enlightened VMCS doesn't have launch state */
 		vmcs12->launch_state = !launch;
 	} else if (enable_shadow_vmcs) {
@@ -4329,11 +4373,11 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))
+	if (nested_vmx_is_evmptr12_valid(vmx))
 		sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
 
 	vmx->nested.need_sync_vmcs02_to_vmcs12_rare =
-		!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr);
+		!nested_vmx_is_evmptr12_valid(vmx);
 
 	vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12);
 	vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12);
@@ -4732,6 +4776,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 	/* trying to cancel vmlaunch/vmresume is a bug */
 	WARN_ON_ONCE(vmx->nested.nested_run_pending);
 
+#ifdef CONFIG_KVM_HYPERV
 	if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) {
 		/*
 		 * KVM_REQ_GET_NESTED_STATE_PAGES is also used to map
@@ -4741,6 +4786,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 		 */
 		(void)nested_get_evmcs_page(vcpu);
 	}
+#endif
 
 	/* Service pending TLB flush requests for L2 before switching to L1. */
 	kvm_service_local_tlb_flush_requests(vcpu);
@@ -4854,7 +4900,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 	}
 
 	if ((vm_exit_reason != -1) &&
-	    (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)))
+	    (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx)))
 		vmx->nested.need_vmcs12_to_shadow_sync = true;
 
 	/* in case we halted in L2 */
@@ -4980,6 +5026,7 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
 		else
 			*ret = off;
 
+		*ret = vmx_get_untagged_addr(vcpu, *ret, 0);
 		/* Long mode: #GP(0)/#SS(0) if the memory address is in a
 		 * non-canonical form. This is the only check on the memory
 		 * destination for long mode!
@@ -5292,18 +5339,7 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
 	if (vmptr == vmx->nested.vmxon_ptr)
 		return nested_vmx_fail(vcpu, VMXERR_VMCLEAR_VMXON_POINTER);
 
-	/*
-	 * When Enlightened VMEntry is enabled on the calling CPU we treat
-	 * memory area pointer by vmptr as Enlightened VMCS (as there's no good
-	 * way to distinguish it from VMCS12) and we must not corrupt it by
-	 * writing to the non-existent 'launch_state' field. The area doesn't
-	 * have to be the currently active EVMCS on the calling CPU and there's
-	 * nothing KVM has to do to transition it from 'active' to 'non-active'
-	 * state. It is possible that the area will stay mapped as
-	 * vmx->nested.hv_evmcs but this shouldn't be a problem.
-	 */
-	if (likely(!guest_cpuid_has_evmcs(vcpu) ||
-		   !evmptr_is_valid(nested_get_evmptr(vcpu)))) {
+	if (likely(!nested_evmcs_handle_vmclear(vcpu, vmptr))) {
 		if (vmptr == vmx->nested.current_vmptr)
 			nested_release_vmcs12(vcpu);
 
@@ -5320,8 +5356,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
 					   vmptr + offsetof(struct vmcs12,
 							    launch_state),
 					   &zero, sizeof(zero));
-	} else if (vmx->nested.hv_evmcs && vmptr == vmx->nested.hv_evmcs_vmptr) {
-		nested_release_evmcs(vcpu);
 	}
 
 	return nested_vmx_succeed(vcpu);
@@ -5360,7 +5394,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 	/* Decode instruction info and find the field to read */
 	field = kvm_register_read(vcpu, (((instr_info) >> 28) & 0xf));
 
-	if (!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) {
+	if (!nested_vmx_is_evmptr12_valid(vmx)) {
 		/*
 		 * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA,
 		 * any VMREAD sets the ALU flags for VMfailInvalid.
@@ -5398,7 +5432,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 			return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
 
 		/* Read the field, zero-extended to a u64 value */
-		value = evmcs_read_any(vmx->nested.hv_evmcs, field, offset);
+		value = evmcs_read_any(nested_vmx_evmcs(vmx), field, offset);
 	}
 
 	/*
@@ -5586,7 +5620,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 		return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_VMXON_POINTER);
 
 	/* Forbid normal VMPTRLD if Enlightened version was used */
-	if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))
+	if (nested_vmx_is_evmptr12_valid(vmx))
 		return 1;
 
 	if (vmx->nested.current_vmptr != vmptr) {
@@ -5649,7 +5683,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (unlikely(evmptr_is_valid(to_vmx(vcpu)->nested.hv_evmcs_vmptr)))
+	if (unlikely(nested_vmx_is_evmptr12_valid(to_vmx(vcpu))))
 		return 1;
 
 	if (get_vmx_mem_address(vcpu, exit_qual, instr_info,
@@ -5797,6 +5831,10 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 	vpid02 = nested_get_vpid02(vcpu);
 	switch (type) {
 	case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:
+		/*
+		 * LAM doesn't apply to addresses that are inputs to TLB
+		 * invalidation.
+		 */
 		if (!operand.vpid ||
 		    is_noncanonical_address(operand.gla, vcpu))
 			return nested_vmx_fail(vcpu,
@@ -6208,11 +6246,13 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu,
 		 * Handle L2's bus locks in L0 directly.
 		 */
 		return true;
+#ifdef CONFIG_KVM_HYPERV
 	case EXIT_REASON_VMCALL:
 		/* Hyper-V L2 TLB flush hypercall is handled by L0 */
 		return guest_hv_cpuid_has_l2_tlb_flush(vcpu) &&
 			nested_evmcs_l2_tlb_flush_enabled(vcpu) &&
 			kvm_hv_is_tlb_flush_hcall(vcpu);
+#endif
 	default:
 		break;
 	}
@@ -6435,7 +6475,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
 			kvm_state.size += sizeof(user_vmx_nested_state->vmcs12);
 
 			/* 'hv_evmcs_vmptr' can also be EVMPTR_MAP_PENDING here */
-			if (vmx->nested.hv_evmcs_vmptr != EVMPTR_INVALID)
+			if (nested_vmx_is_evmptr12_set(vmx))
 				kvm_state.flags |= KVM_STATE_NESTED_EVMCS;
 
 			if (is_guest_mode(vcpu) &&
@@ -6491,7 +6531,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
 	} else  {
 		copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu));
 		if (!vmx->nested.need_vmcs12_to_shadow_sync) {
-			if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))
+			if (nested_vmx_is_evmptr12_valid(vmx))
 				/*
 				 * L1 hypervisor is not obliged to keep eVMCS
 				 * clean fields data always up-to-date while
@@ -6632,6 +6672,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 			return -EINVAL;
 
 		set_current_vmptr(vmx, kvm_state->hdr.vmx.vmcs12_pa);
+#ifdef CONFIG_KVM_HYPERV
 	} else if (kvm_state->flags & KVM_STATE_NESTED_EVMCS) {
 		/*
 		 * nested_vmx_handle_enlightened_vmptrld() cannot be called
@@ -6641,6 +6682,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 		 */
 		vmx->nested.hv_evmcs_vmptr = EVMPTR_MAP_PENDING;
 		kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
+#endif
 	} else {
 		return -EINVAL;
 	}
@@ -7096,7 +7138,9 @@ struct kvm_x86_nested_ops vmx_nested_ops = {
 	.set_state = vmx_set_nested_state,
 	.get_nested_state_pages = vmx_get_nested_state_pages,
 	.write_log_dirty = nested_vmx_write_pml_buffer,
+#ifdef CONFIG_KVM_HYPERV
 	.enable_evmcs = nested_enable_evmcs,
 	.get_evmcs_version = nested_get_evmcs_version,
 	.hv_inject_synthetic_vmexit_post_tlb_flush = vmx_hv_inject_synthetic_vmexit_post_tlb_flush,
+#endif
 };
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index b4b9d51438c6..cce4e2aa30fb 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -3,6 +3,7 @@
 #define __KVM_X86_VMX_NESTED_H
 
 #include "kvm_cache_regs.h"
+#include "hyperv.h"
 #include "vmcs12.h"
 #include "vmx.h"
 
@@ -57,7 +58,7 @@ static inline int vmx_has_valid_vmcs12(struct kvm_vcpu *vcpu)
 
 	/* 'hv_evmcs_vmptr' can also be EVMPTR_MAP_PENDING here */
 	return vmx->nested.current_vmptr != -1ull ||
-		vmx->nested.hv_evmcs_vmptr != EVMPTR_INVALID;
+		nested_vmx_is_evmptr12_set(vmx);
 }
 
 static inline u16 nested_get_vpid02(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 820d3e1f6b4f..315c7c2ba89b 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -71,7 +71,7 @@ static int fixed_pmc_events[] = {
 static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
 {
 	struct kvm_pmc *pmc;
-	u8 old_fixed_ctr_ctrl = pmu->fixed_ctr_ctrl;
+	u64 old_fixed_ctr_ctrl = pmu->fixed_ctr_ctrl;
 	int i;
 
 	pmu->fixed_ctr_ctrl = data;
@@ -437,11 +437,9 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			    !(msr & MSR_PMC_FULL_WIDTH_BIT))
 				data = (s64)(s32)data;
 			pmc_write_counter(pmc, data);
-			pmc_update_sample_period(pmc);
 			break;
 		} else if ((pmc = get_fixed_pmc(pmu, msr))) {
 			pmc_write_counter(pmc, data);
-			pmc_update_sample_period(pmc);
 			break;
 		} else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
 			reserved_bits = pmu->reserved_bits;
@@ -632,26 +630,6 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu)
 
 static void intel_pmu_reset(struct kvm_vcpu *vcpu)
 {
-	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-	struct kvm_pmc *pmc = NULL;
-	int i;
-
-	for (i = 0; i < KVM_INTEL_PMC_MAX_GENERIC; i++) {
-		pmc = &pmu->gp_counters[i];
-
-		pmc_stop_counter(pmc);
-		pmc->counter = pmc->prev_counter = pmc->eventsel = 0;
-	}
-
-	for (i = 0; i < KVM_PMC_MAX_FIXED; i++) {
-		pmc = &pmu->fixed_counters[i];
-
-		pmc_stop_counter(pmc);
-		pmc->counter = pmc->prev_counter = 0;
-	}
-
-	pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = 0;
-
 	intel_pmu_release_guest_lbr_event(vcpu);
 }
 
diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h
index edc3f16cc189..6a9bfdfbb6e5 100644
--- a/arch/x86/kvm/vmx/run_flags.h
+++ b/arch/x86/kvm/vmx/run_flags.h
@@ -2,7 +2,10 @@
 #ifndef __KVM_X86_VMX_RUN_FLAGS_H
 #define __KVM_X86_VMX_RUN_FLAGS_H
 
-#define VMX_RUN_VMRESUME	(1 << 0)
-#define VMX_RUN_SAVE_SPEC_CTRL	(1 << 1)
+#define VMX_RUN_VMRESUME_SHIFT		0
+#define VMX_RUN_SAVE_SPEC_CTRL_SHIFT	1
+
+#define VMX_RUN_VMRESUME		BIT(VMX_RUN_VMRESUME_SHIFT)
+#define VMX_RUN_SAVE_SPEC_CTRL		BIT(VMX_RUN_SAVE_SPEC_CTRL_SHIFT)
 
 #endif /* __KVM_X86_VMX_RUN_FLAGS_H */
diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c
index 3e822e582497..6fef01e0536e 100644
--- a/arch/x86/kvm/vmx/sgx.c
+++ b/arch/x86/kvm/vmx/sgx.c
@@ -37,6 +37,7 @@ static int sgx_get_encls_gva(struct kvm_vcpu *vcpu, unsigned long offset,
 	if (!IS_ALIGNED(*gva, alignment)) {
 		fault = true;
 	} else if (likely(is_64_bit_mode(vcpu))) {
+		*gva = vmx_get_untagged_addr(vcpu, *gva, 0);
 		fault = is_noncanonical_address(*gva, vcpu);
 	} else {
 		*gva &= 0xffffffff;
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index be275a0410a8..2bfbf758d061 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -139,7 +139,7 @@ SYM_FUNC_START(__vmx_vcpu_run)
 	mov (%_ASM_SP), %_ASM_AX
 
 	/* Check if vmlaunch or vmresume is needed */
-	test $VMX_RUN_VMRESUME, %ebx
+	bt   $VMX_RUN_VMRESUME_SHIFT, %ebx
 
 	/* Load guest registers.  Don't clobber flags. */
 	mov VCPU_RCX(%_ASM_AX), %_ASM_CX
@@ -161,8 +161,11 @@ SYM_FUNC_START(__vmx_vcpu_run)
 	/* Load guest RAX.  This kills the @regs pointer! */
 	mov VCPU_RAX(%_ASM_AX), %_ASM_AX
 
-	/* Check EFLAGS.ZF from 'test VMX_RUN_VMRESUME' above */
-	jz .Lvmlaunch
+	/* Clobbers EFLAGS.ZF */
+	CLEAR_CPU_BUFFERS
+
+	/* Check EFLAGS.CF from the VMX_RUN_VMRESUME bit test above. */
+	jnc .Lvmlaunch
 
 	/*
 	 * After a successful VMRESUME/VMLAUNCH, control flow "magically"
@@ -289,7 +292,7 @@ SYM_INNER_LABEL_ALIGN(vmx_vmexit, SYM_L_GLOBAL)
 	RET
 
 .Lfixup:
-	cmpb $0, kvm_rebooting
+	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne .Lvmfail
 	ud2
 .Lvmfail:
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index e0f86f11c345..88a4ff200d04 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -66,6 +66,7 @@
 #include "vmx.h"
 #include "x86.h"
 #include "smm.h"
+#include "vmx_onhyperv.h"
 
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
@@ -387,7 +388,16 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx)
 
 static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx)
 {
-	vmx->disable_fb_clear = (host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) &&
+	/*
+	 * Disable VERW's behavior of clearing CPU buffers for the guest if the
+	 * CPU isn't affected by MDS/TAA, and the host hasn't forcefully enabled
+	 * the mitigation. Disabling the clearing behavior provides a
+	 * performance boost for guests that aren't aware that manually clearing
+	 * CPU buffers is unnecessary, at the cost of MSR accesses on VM-Entry
+	 * and VM-Exit.
+	 */
+	vmx->disable_fb_clear = !cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF) &&
+				(host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) &&
 				!boot_cpu_has_bug(X86_BUG_MDS) &&
 				!boot_cpu_has_bug(X86_BUG_TAA);
 
@@ -523,22 +533,14 @@ module_param(enlightened_vmcs, bool, 0444);
 static int hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu)
 {
 	struct hv_enlightened_vmcs *evmcs;
-	struct hv_partition_assist_pg **p_hv_pa_pg =
-			&to_kvm_hv(vcpu->kvm)->hv_pa_pg;
-	/*
-	 * Synthetic VM-Exit is not enabled in current code and so All
-	 * evmcs in singe VM shares same assist page.
-	 */
-	if (!*p_hv_pa_pg)
-		*p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT);
+	hpa_t partition_assist_page = hv_get_partition_assist_page(vcpu);
 
-	if (!*p_hv_pa_pg)
+	if (partition_assist_page == INVALID_PAGE)
 		return -ENOMEM;
 
 	evmcs = (struct hv_enlightened_vmcs *)to_vmx(vcpu)->loaded_vmcs->vmcs;
 
-	evmcs->partition_assist_page =
-		__pa(*p_hv_pa_pg);
+	evmcs->partition_assist_page = partition_assist_page;
 	evmcs->hv_vm_id = (unsigned long)vcpu->kvm;
 	evmcs->hv_enlightenments_control.nested_flush_hypercall = 1;
 
@@ -745,7 +747,7 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx,
  */
 static int kvm_cpu_vmxoff(void)
 {
-	asm_volatile_goto("1: vmxoff\n\t"
+	asm goto("1: vmxoff\n\t"
 			  _ASM_EXTABLE(1b, %l[fault])
 			  ::: "cc", "memory" : fault);
 
@@ -2055,6 +2057,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index,
 				    &msr_info->data))
 			return 1;
+#ifdef CONFIG_KVM_HYPERV
 		/*
 		 * Enlightened VMCS v1 doesn't have certain VMCS fields but
 		 * instead of just ignoring the features, different Hyper-V
@@ -2065,6 +2068,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!msr_info->host_initiated && guest_cpuid_has_evmcs(vcpu))
 			nested_evmcs_filter_control_msr(vcpu, msr_info->index,
 							&msr_info->data);
+#endif
 		break;
 	case MSR_IA32_RTIT_CTL:
 		if (!vmx_pt_mode_is_host_guest())
@@ -2789,7 +2793,7 @@ static int kvm_cpu_vmxon(u64 vmxon_pointer)
 
 	cr4_set_bits(X86_CR4_VMXE);
 
-	asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t"
+	asm goto("1: vmxon %[vmxon_pointer]\n\t"
 			  _ASM_EXTABLE(1b, %l[fault])
 			  : : [vmxon_pointer] "m"(vmxon_pointer)
 			  : : fault);
@@ -3400,7 +3404,8 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa,
 			update_guest_cr3 = false;
 		vmx_ept_load_pdptrs(vcpu);
 	} else {
-		guest_cr3 = root_hpa | kvm_get_active_pcid(vcpu);
+		guest_cr3 = root_hpa | kvm_get_active_pcid(vcpu) |
+			    kvm_get_active_cr3_lam_bits(vcpu);
 	}
 
 	if (update_guest_cr3)
@@ -4833,7 +4838,10 @@ static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 	vmx->nested.posted_intr_nv = -1;
 	vmx->nested.vmxon_ptr = INVALID_GPA;
 	vmx->nested.current_vmptr = INVALID_GPA;
+
+#ifdef CONFIG_KVM_HYPERV
 	vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID;
+#endif
 
 	vcpu->arch.microcode_version = 0x100000000ULL;
 	vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED;
@@ -5782,7 +5790,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 	 * would also use advanced VM-exit information for EPT violations to
 	 * reconstruct the page fault error code.
 	 */
-	if (unlikely(allow_smaller_maxphyaddr && kvm_vcpu_is_illegal_gpa(vcpu, gpa)))
+	if (unlikely(allow_smaller_maxphyaddr && !kvm_vcpu_is_legal_gpa(vcpu, gpa)))
 		return kvm_emulate_instruction(vcpu, 0);
 
 	return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
@@ -6757,10 +6765,10 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu)
 		return;
 
 	/*
-	 * Grab the memslot so that the hva lookup for the mmu_notifier retry
-	 * is guaranteed to use the same memslot as the pfn lookup, i.e. rely
-	 * on the pfn lookup's validation of the memslot to ensure a valid hva
-	 * is used for the retry check.
+	 * Explicitly grab the memslot using KVM's internal slot ID to ensure
+	 * KVM doesn't unintentionally grab a userspace memslot.  It _should_
+	 * be impossible for userspace to create a memslot for the APIC when
+	 * APICv is enabled, but paranoia won't hurt in this case.
 	 */
 	slot = id_to_memslot(slots, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT);
 	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
@@ -6785,8 +6793,7 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu)
 		return;
 
 	read_lock(&vcpu->kvm->mmu_lock);
-	if (mmu_invalidate_retry_hva(kvm, mmu_seq,
-				     gfn_to_hva_memslot(slot, gfn))) {
+	if (mmu_invalidate_retry_gfn(kvm, mmu_seq, gfn)) {
 		kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
 		read_unlock(&vcpu->kvm->mmu_lock);
 		goto out;
@@ -7226,11 +7233,14 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 
 	guest_state_enter_irqoff();
 
-	/* L1D Flush includes CPU buffer clear to mitigate MDS */
+	/*
+	 * L1D Flush includes CPU buffer clear to mitigate MDS, but VERW
+	 * mitigation for MDS is done late in VMentry and is still
+	 * executed in spite of L1D Flush. This is because an extra VERW
+	 * should not matter much after the big hammer L1D Flush.
+	 */
 	if (static_branch_unlikely(&vmx_l1d_should_flush))
 		vmx_l1d_flush(vcpu);
-	else if (static_branch_unlikely(&mds_user_clear))
-		mds_clear_cpu_buffers();
 	else if (static_branch_unlikely(&mmio_stale_data_clear) &&
 		 kvm_arch_has_assigned_device(vcpu->kvm))
 		mds_clear_cpu_buffers();
@@ -7674,6 +7684,9 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
 	cr4_fixed1_update(X86_CR4_UMIP,       ecx, feature_bit(UMIP));
 	cr4_fixed1_update(X86_CR4_LA57,       ecx, feature_bit(LA57));
 
+	entry = kvm_find_cpuid_entry_index(vcpu, 0x7, 1);
+	cr4_fixed1_update(X86_CR4_LAM_SUP,    eax, feature_bit(LAM));
+
 #undef cr4_fixed1_update
 }
 
@@ -7760,6 +7773,7 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 		kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_XSAVES);
 
 	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VMX);
+	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_LAM);
 
 	vmx_setup_uret_msrs(vmx);
 
@@ -8206,6 +8220,50 @@ static void vmx_vm_destroy(struct kvm *kvm)
 	free_pages((unsigned long)kvm_vmx->pid_table, vmx_get_pid_table_order(kvm));
 }
 
+/*
+ * Note, the SDM states that the linear address is masked *after* the modified
+ * canonicality check, whereas KVM masks (untags) the address and then performs
+ * a "normal" canonicality check.  Functionally, the two methods are identical,
+ * and when the masking occurs relative to the canonicality check isn't visible
+ * to software, i.e. KVM's behavior doesn't violate the SDM.
+ */
+gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags)
+{
+	int lam_bit;
+	unsigned long cr3_bits;
+
+	if (flags & (X86EMUL_F_FETCH | X86EMUL_F_IMPLICIT | X86EMUL_F_INVLPG))
+		return gva;
+
+	if (!is_64_bit_mode(vcpu))
+		return gva;
+
+	/*
+	 * Bit 63 determines if the address should be treated as user address
+	 * or a supervisor address.
+	 */
+	if (!(gva & BIT_ULL(63))) {
+		cr3_bits = kvm_get_active_cr3_lam_bits(vcpu);
+		if (!(cr3_bits & (X86_CR3_LAM_U57 | X86_CR3_LAM_U48)))
+			return gva;
+
+		/* LAM_U48 is ignored if LAM_U57 is set. */
+		lam_bit = cr3_bits & X86_CR3_LAM_U57 ? 56 : 47;
+	} else {
+		if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_LAM_SUP))
+			return gva;
+
+		lam_bit = kvm_is_cr4_bit_set(vcpu, X86_CR4_LA57) ? 56 : 47;
+	}
+
+	/*
+	 * Untag the address by sign-extending the lam_bit, but NOT to bit 63.
+	 * Bit 63 is retained from the raw virtual address so that untagging
+	 * doesn't change a user access to a supervisor access, and vice versa.
+	 */
+	return (sign_extend64(gva, lam_bit) & ~BIT_ULL(63)) | (gva & BIT_ULL(63));
+}
+
 static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.name = KBUILD_MODNAME,
 
@@ -8346,6 +8404,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.complete_emulated_msr = kvm_complete_insn_gp,
 
 	.vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,
+
+	.get_untagged_addr = vmx_get_untagged_addr,
 };
 
 static unsigned int vmx_handle_intel_pt_intr(void)
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index c2130d2c8e24..e3b0985bb74a 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -241,9 +241,11 @@ struct nested_vmx {
 		bool guest_mode;
 	} smm;
 
+#ifdef CONFIG_KVM_HYPERV
 	gpa_t hv_evmcs_vmptr;
 	struct kvm_host_map hv_evmcs_map;
 	struct hv_enlightened_vmcs *hv_evmcs;
+#endif
 };
 
 struct vcpu_vmx {
@@ -420,6 +422,8 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type);
 u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu);
 u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu);
 
+gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags);
+
 static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr,
 					     int type, bool value)
 {
@@ -745,14 +749,4 @@ static inline bool vmx_can_use_ipiv(struct kvm_vcpu *vcpu)
 	return  lapic_in_kernel(vcpu) && enable_ipiv;
 }
 
-static inline bool guest_cpuid_has_evmcs(struct kvm_vcpu *vcpu)
-{
-	/*
-	 * eVMCS is exposed to the guest if Hyper-V is enabled in CPUID and
-	 * eVMCS has been explicitly enabled by userspace.
-	 */
-	return vcpu->arch.hyperv_enabled &&
-	       to_vmx(vcpu)->nested.enlightened_vmcs_enabled;
-}
-
 #endif /* __KVM_X86_VMX_H */
diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.c b/arch/x86/kvm/vmx/vmx_onhyperv.c
new file mode 100644
index 000000000000..b9a8b91166d0
--- /dev/null
+++ b/arch/x86/kvm/vmx/vmx_onhyperv.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "capabilities.h"
+#include "vmx_onhyperv.h"
+
+DEFINE_STATIC_KEY_FALSE(__kvm_is_using_evmcs);
+
+/*
+ * KVM on Hyper-V always uses the latest known eVMCSv1 revision, the assumption
+ * is: in case a feature has corresponding fields in eVMCS described and it was
+ * exposed in VMX feature MSRs, KVM is free to use it. Warn if KVM meets a
+ * feature which has no corresponding eVMCS field, this likely means that KVM
+ * needs to be updated.
+ */
+#define evmcs_check_vmcs_conf(field, ctrl)					\
+	do {									\
+		typeof(vmcs_conf->field) unsupported;				\
+										\
+		unsupported = vmcs_conf->field & ~EVMCS1_SUPPORTED_ ## ctrl;	\
+		if (unsupported) {						\
+			pr_warn_once(#field " unsupported with eVMCS: 0x%llx\n",\
+				     (u64)unsupported);				\
+			vmcs_conf->field &= EVMCS1_SUPPORTED_ ## ctrl;		\
+		}								\
+	}									\
+	while (0)
+
+void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf)
+{
+	evmcs_check_vmcs_conf(cpu_based_exec_ctrl, EXEC_CTRL);
+	evmcs_check_vmcs_conf(pin_based_exec_ctrl, PINCTRL);
+	evmcs_check_vmcs_conf(cpu_based_2nd_exec_ctrl, 2NDEXEC);
+	evmcs_check_vmcs_conf(cpu_based_3rd_exec_ctrl, 3RDEXEC);
+	evmcs_check_vmcs_conf(vmentry_ctrl, VMENTRY_CTRL);
+	evmcs_check_vmcs_conf(vmexit_ctrl, VMEXIT_CTRL);
+}
diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.h b/arch/x86/kvm/vmx/vmx_onhyperv.h
new file mode 100644
index 000000000000..eb48153bfd73
--- /dev/null
+++ b/arch/x86/kvm/vmx/vmx_onhyperv.h
@@ -0,0 +1,125 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ARCH_X86_KVM_VMX_ONHYPERV_H__
+#define __ARCH_X86_KVM_VMX_ONHYPERV_H__
+
+#include <asm/hyperv-tlfs.h>
+#include <asm/mshyperv.h>
+
+#include <linux/jump_label.h>
+
+#include "capabilities.h"
+#include "hyperv_evmcs.h"
+#include "vmcs12.h"
+
+#define current_evmcs ((struct hv_enlightened_vmcs *)this_cpu_read(current_vmcs))
+
+#if IS_ENABLED(CONFIG_HYPERV)
+
+DECLARE_STATIC_KEY_FALSE(__kvm_is_using_evmcs);
+
+static __always_inline bool kvm_is_using_evmcs(void)
+{
+	return static_branch_unlikely(&__kvm_is_using_evmcs);
+}
+
+static __always_inline int get_evmcs_offset(unsigned long field,
+					    u16 *clean_field)
+{
+	int offset = evmcs_field_offset(field, clean_field);
+
+	WARN_ONCE(offset < 0, "accessing unsupported EVMCS field %lx\n", field);
+	return offset;
+}
+
+static __always_inline void evmcs_write64(unsigned long field, u64 value)
+{
+	u16 clean_field;
+	int offset = get_evmcs_offset(field, &clean_field);
+
+	if (offset < 0)
+		return;
+
+	*(u64 *)((char *)current_evmcs + offset) = value;
+
+	current_evmcs->hv_clean_fields &= ~clean_field;
+}
+
+static __always_inline void evmcs_write32(unsigned long field, u32 value)
+{
+	u16 clean_field;
+	int offset = get_evmcs_offset(field, &clean_field);
+
+	if (offset < 0)
+		return;
+
+	*(u32 *)((char *)current_evmcs + offset) = value;
+	current_evmcs->hv_clean_fields &= ~clean_field;
+}
+
+static __always_inline void evmcs_write16(unsigned long field, u16 value)
+{
+	u16 clean_field;
+	int offset = get_evmcs_offset(field, &clean_field);
+
+	if (offset < 0)
+		return;
+
+	*(u16 *)((char *)current_evmcs + offset) = value;
+	current_evmcs->hv_clean_fields &= ~clean_field;
+}
+
+static __always_inline u64 evmcs_read64(unsigned long field)
+{
+	int offset = get_evmcs_offset(field, NULL);
+
+	if (offset < 0)
+		return 0;
+
+	return *(u64 *)((char *)current_evmcs + offset);
+}
+
+static __always_inline u32 evmcs_read32(unsigned long field)
+{
+	int offset = get_evmcs_offset(field, NULL);
+
+	if (offset < 0)
+		return 0;
+
+	return *(u32 *)((char *)current_evmcs + offset);
+}
+
+static __always_inline u16 evmcs_read16(unsigned long field)
+{
+	int offset = get_evmcs_offset(field, NULL);
+
+	if (offset < 0)
+		return 0;
+
+	return *(u16 *)((char *)current_evmcs + offset);
+}
+
+static inline void evmcs_load(u64 phys_addr)
+{
+	struct hv_vp_assist_page *vp_ap =
+		hv_get_vp_assist_page(smp_processor_id());
+
+	if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall)
+		vp_ap->nested_control.features.directhypercall = 1;
+	vp_ap->current_nested_vmcs = phys_addr;
+	vp_ap->enlighten_vmentry = 1;
+}
+
+void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf);
+#else /* !IS_ENABLED(CONFIG_HYPERV) */
+static __always_inline bool kvm_is_using_evmcs(void) { return false; }
+static __always_inline void evmcs_write64(unsigned long field, u64 value) {}
+static __always_inline void evmcs_write32(unsigned long field, u32 value) {}
+static __always_inline void evmcs_write16(unsigned long field, u16 value) {}
+static __always_inline u64 evmcs_read64(unsigned long field) { return 0; }
+static __always_inline u32 evmcs_read32(unsigned long field) { return 0; }
+static __always_inline u16 evmcs_read16(unsigned long field) { return 0; }
+static inline void evmcs_load(u64 phys_addr) {}
+#endif /* IS_ENABLED(CONFIG_HYPERV) */
+
+#endif /* __ARCH_X86_KVM_VMX_ONHYPERV_H__ */
diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h
index 33af7b4c6eb4..8060e5fc6dbd 100644
--- a/arch/x86/kvm/vmx/vmx_ops.h
+++ b/arch/x86/kvm/vmx/vmx_ops.h
@@ -6,7 +6,7 @@
 
 #include <asm/vmx.h>
 
-#include "hyperv.h"
+#include "vmx_onhyperv.h"
 #include "vmcs.h"
 #include "../x86.h"
 
@@ -94,7 +94,7 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field)
 
 #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
 
-	asm_volatile_goto("1: vmread %[field], %[output]\n\t"
+	asm_goto_output("1: vmread %[field], %[output]\n\t"
 			  "jna %l[do_fail]\n\t"
 
 			  _ASM_EXTABLE(1b, %l[do_exception])
@@ -188,7 +188,7 @@ static __always_inline unsigned long vmcs_readl(unsigned long field)
 
 #define vmx_asm1(insn, op1, error_args...)				\
 do {									\
-	asm_volatile_goto("1: " __stringify(insn) " %0\n\t"		\
+	asm goto("1: " __stringify(insn) " %0\n\t"			\
 			  ".byte 0x2e\n\t" /* branch not taken hint */	\
 			  "jna %l[error]\n\t"				\
 			  _ASM_EXTABLE(1b, %l[fault])			\
@@ -205,7 +205,7 @@ fault:									\
 
 #define vmx_asm2(insn, op1, op2, error_args...)				\
 do {									\
-	asm_volatile_goto("1: "  __stringify(insn) " %1, %0\n\t"	\
+	asm goto("1: "  __stringify(insn) " %1, %0\n\t"			\
 			  ".byte 0x2e\n\t" /* branch not taken hint */	\
 			  "jna %l[error]\n\t"				\
 			  _ASM_EXTABLE(1b, %l[fault])			\
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index cec0fc2a4b1c..e02cc710f56d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1284,7 +1284,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 	 * stuff CR3, e.g. for RSM emulation, and there is no guarantee that
 	 * the current vCPU mode is accurate.
 	 */
-	if (kvm_vcpu_is_illegal_gpa(vcpu, cr3))
+	if (!kvm_vcpu_is_legal_cr3(vcpu, cr3))
 		return 1;
 
 	if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, cr3))
@@ -1504,6 +1504,8 @@ static unsigned num_msrs_to_save;
 static const u32 emulated_msrs_all[] = {
 	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
 	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
+
+#ifdef CONFIG_KVM_HYPERV
 	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
 	HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC,
 	HV_X64_MSR_TSC_FREQUENCY, HV_X64_MSR_APIC_FREQUENCY,
@@ -1521,6 +1523,7 @@ static const u32 emulated_msrs_all[] = {
 	HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS,
 	HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER,
 	HV_X64_MSR_SYNDBG_PENDING_BUFFER,
+#endif
 
 	MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
 	MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK,
@@ -1701,22 +1704,17 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 	struct kvm_msr_entry msr;
 	int r;
 
+	/* Unconditionally clear the output for simplicity */
+	msr.data = 0;
 	msr.index = index;
 	r = kvm_get_msr_feature(&msr);
 
-	if (r == KVM_MSR_RET_INVALID) {
-		/* Unconditionally clear the output for simplicity */
-		*data = 0;
-		if (kvm_msr_ignored_check(index, 0, false))
-			r = 0;
-	}
-
-	if (r)
-		return r;
+	if (r == KVM_MSR_RET_INVALID && kvm_msr_ignored_check(index, 0, false))
+		r = 0;
 
 	*data = msr.data;
 
-	return 0;
+	return r;
 }
 
 static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
@@ -1779,6 +1777,10 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	if ((efer ^ old_efer) & KVM_MMU_EFER_ROLE_BITS)
 		kvm_mmu_reset_context(vcpu);
 
+	if (!static_cpu_has(X86_FEATURE_XSAVES) &&
+	    (efer & EFER_SVME))
+		kvm_hv_xsaves_xsavec_maybe_warn(vcpu);
+
 	return 0;
 }
 
@@ -2504,32 +2506,35 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
 }
 
 #ifdef CONFIG_X86_64
-static inline int gtod_is_based_on_tsc(int mode)
+static inline bool gtod_is_based_on_tsc(int mode)
 {
 	return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK;
 }
 #endif
 
-static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
+static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu, bool new_generation)
 {
 #ifdef CONFIG_X86_64
-	bool vcpus_matched;
 	struct kvm_arch *ka = &vcpu->kvm->arch;
 	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
 
-	vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 ==
-			 atomic_read(&vcpu->kvm->online_vcpus));
+	/*
+	 * To use the masterclock, the host clocksource must be based on TSC
+	 * and all vCPUs must have matching TSCs.  Note, the count for matching
+	 * vCPUs doesn't include the reference vCPU, hence "+1".
+	 */
+	bool use_master_clock = (ka->nr_vcpus_matched_tsc + 1 ==
+				 atomic_read(&vcpu->kvm->online_vcpus)) &&
+				gtod_is_based_on_tsc(gtod->clock.vclock_mode);
 
 	/*
-	 * Once the masterclock is enabled, always perform request in
-	 * order to update it.
-	 *
-	 * In order to enable masterclock, the host clocksource must be TSC
-	 * and the vcpus need to have matched TSCs.  When that happens,
-	 * perform request to enable masterclock.
+	 * Request a masterclock update if the masterclock needs to be toggled
+	 * on/off, or when starting a new generation and the masterclock is
+	 * enabled (compute_guest_tsc() requires the masterclock snapshot to be
+	 * taken _after_ the new generation is created).
 	 */
-	if (ka->use_master_clock ||
-	    (gtod_is_based_on_tsc(gtod->clock.vclock_mode) && vcpus_matched))
+	if ((ka->use_master_clock && new_generation) ||
+	    (ka->use_master_clock != use_master_clock))
 		kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
 
 	trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc,
@@ -2706,7 +2711,7 @@ static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc,
 	vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec;
 	vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write;
 
-	kvm_track_tsc_matching(vcpu);
+	kvm_track_tsc_matching(vcpu, !matched);
 }
 
 static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value)
@@ -3104,7 +3109,8 @@ u64 get_kvmclock_ns(struct kvm *kvm)
 
 static void kvm_setup_guest_pvclock(struct kvm_vcpu *v,
 				    struct gfn_to_pfn_cache *gpc,
-				    unsigned int offset)
+				    unsigned int offset,
+				    bool force_tsc_unstable)
 {
 	struct kvm_vcpu_arch *vcpu = &v->arch;
 	struct pvclock_vcpu_time_info *guest_hv_clock;
@@ -3141,6 +3147,10 @@ static void kvm_setup_guest_pvclock(struct kvm_vcpu *v,
 	}
 
 	memcpy(guest_hv_clock, &vcpu->hv_clock, sizeof(*guest_hv_clock));
+
+	if (force_tsc_unstable)
+		guest_hv_clock->flags &= ~PVCLOCK_TSC_STABLE_BIT;
+
 	smp_wmb();
 
 	guest_hv_clock->version = ++vcpu->hv_clock.version;
@@ -3161,6 +3171,16 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	u64 tsc_timestamp, host_tsc;
 	u8 pvclock_flags;
 	bool use_master_clock;
+#ifdef CONFIG_KVM_XEN
+	/*
+	 * For Xen guests we may need to override PVCLOCK_TSC_STABLE_BIT as unless
+	 * explicitly told to use TSC as its clocksource Xen will not set this bit.
+	 * This default behaviour led to bugs in some guest kernels which cause
+	 * problems if they observe PVCLOCK_TSC_STABLE_BIT in the pvclock flags.
+	 */
+	bool xen_pvclock_tsc_unstable =
+		ka->xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE;
+#endif
 
 	kernel_ns = 0;
 	host_tsc = 0;
@@ -3239,13 +3259,15 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	vcpu->hv_clock.flags = pvclock_flags;
 
 	if (vcpu->pv_time.active)
-		kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0);
+		kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0, false);
 #ifdef CONFIG_KVM_XEN
 	if (vcpu->xen.vcpu_info_cache.active)
 		kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_info_cache,
-					offsetof(struct compat_vcpu_info, time));
+					offsetof(struct compat_vcpu_info, time),
+					xen_pvclock_tsc_unstable);
 	if (vcpu->xen.vcpu_time_info_cache.active)
-		kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0);
+		kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0,
+					xen_pvclock_tsc_unstable);
 #endif
 	kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock);
 	return 0;
@@ -4020,6 +4042,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		 * the need to ignore the workaround.
 		 */
 		break;
+#ifdef CONFIG_KVM_HYPERV
 	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
 	case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
 	case HV_X64_MSR_SYNDBG_OPTIONS:
@@ -4032,6 +4055,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case HV_X64_MSR_TSC_INVARIANT_CONTROL:
 		return kvm_hv_set_msr_common(vcpu, msr, data,
 					     msr_info->host_initiated);
+#endif
 	case MSR_IA32_BBL_CR_CTL3:
 		/* Drop writes to this legacy MSR -- see rdmsr
 		 * counterpart for further detail.
@@ -4377,6 +4401,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		 */
 		msr_info->data = 0x20000000;
 		break;
+#ifdef CONFIG_KVM_HYPERV
 	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
 	case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
 	case HV_X64_MSR_SYNDBG_OPTIONS:
@@ -4390,6 +4415,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		return kvm_hv_get_msr_common(vcpu,
 					     msr_info->index, &msr_info->data,
 					     msr_info->host_initiated);
+#endif
 	case MSR_IA32_BBL_CR_CTL3:
 		/* This legacy MSR exists but isn't fully documented in current
 		 * silicon.  It is however accessed by winxp in very narrow
@@ -4527,6 +4553,7 @@ static inline bool kvm_can_mwait_in_guest(void)
 		boot_cpu_has(X86_FEATURE_ARAT);
 }
 
+#ifdef CONFIG_KVM_HYPERV
 static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu,
 					    struct kvm_cpuid2 __user *cpuid_arg)
 {
@@ -4547,6 +4574,14 @@ static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu,
 
 	return 0;
 }
+#endif
+
+static bool kvm_is_vm_type_supported(unsigned long type)
+{
+	return type == KVM_X86_DEFAULT_VM ||
+	       (type == KVM_X86_SW_PROTECTED_VM &&
+		IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_mmu_enabled);
+}
 
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 {
@@ -4573,9 +4608,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_PIT_STATE2:
 	case KVM_CAP_SET_IDENTITY_MAP_ADDR:
 	case KVM_CAP_VCPU_EVENTS:
+#ifdef CONFIG_KVM_HYPERV
 	case KVM_CAP_HYPERV:
 	case KVM_CAP_HYPERV_VAPIC:
 	case KVM_CAP_HYPERV_SPIN:
+	case KVM_CAP_HYPERV_TIME:
 	case KVM_CAP_HYPERV_SYNIC:
 	case KVM_CAP_HYPERV_SYNIC2:
 	case KVM_CAP_HYPERV_VP_INDEX:
@@ -4585,6 +4622,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_HYPERV_CPUID:
 	case KVM_CAP_HYPERV_ENFORCE_CPUID:
 	case KVM_CAP_SYS_HYPERV_CPUID:
+#endif
 	case KVM_CAP_PCI_SEGMENT:
 	case KVM_CAP_DEBUGREGS:
 	case KVM_CAP_X86_ROBUST_SINGLESTEP:
@@ -4594,7 +4632,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_GET_TSC_KHZ:
 	case KVM_CAP_KVMCLOCK_CTRL:
 	case KVM_CAP_READONLY_MEM:
-	case KVM_CAP_HYPERV_TIME:
 	case KVM_CAP_IOAPIC_POLARITY_IGNORED:
 	case KVM_CAP_TSC_DEADLINE_TIMER:
 	case KVM_CAP_DISABLE_QUIRKS:
@@ -4625,6 +4662,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES:
 	case KVM_CAP_IRQFD_RESAMPLE:
+	case KVM_CAP_MEMORY_FAULT_INFO:
 		r = 1;
 		break;
 	case KVM_CAP_EXIT_HYPERCALL:
@@ -4638,7 +4676,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		    KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL |
 		    KVM_XEN_HVM_CONFIG_SHARED_INFO |
 		    KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL |
-		    KVM_XEN_HVM_CONFIG_EVTCHN_SEND;
+		    KVM_XEN_HVM_CONFIG_EVTCHN_SEND |
+		    KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE;
 		if (sched_info_on())
 			r |= KVM_XEN_HVM_CONFIG_RUNSTATE |
 			     KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG;
@@ -4704,12 +4743,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = kvm_x86_ops.nested_ops->get_state ?
 			kvm_x86_ops.nested_ops->get_state(NULL, NULL, 0) : 0;
 		break;
+#ifdef CONFIG_KVM_HYPERV
 	case KVM_CAP_HYPERV_DIRECT_TLBFLUSH:
 		r = kvm_x86_ops.enable_l2_tlb_flush != NULL;
 		break;
 	case KVM_CAP_HYPERV_ENLIGHTENED_VMCS:
 		r = kvm_x86_ops.nested_ops->enable_evmcs != NULL;
 		break;
+#endif
 	case KVM_CAP_SMALLER_MAXPHYADDR:
 		r = (int) allow_smaller_maxphyaddr;
 		break;
@@ -4738,6 +4779,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_X86_NOTIFY_VMEXIT:
 		r = kvm_caps.has_notify_vmexit;
 		break;
+	case KVM_CAP_VM_TYPES:
+		r = BIT(KVM_X86_DEFAULT_VM);
+		if (kvm_is_vm_type_supported(KVM_X86_SW_PROTECTED_VM))
+			r |= BIT(KVM_X86_SW_PROTECTED_VM);
+		break;
 	default:
 		break;
 	}
@@ -4871,9 +4917,11 @@ long kvm_arch_dev_ioctl(struct file *filp,
 	case KVM_GET_MSRS:
 		r = msr_io(NULL, argp, do_get_msr_feature, 1);
 		break;
+#ifdef CONFIG_KVM_HYPERV
 	case KVM_GET_SUPPORTED_HV_CPUID:
 		r = kvm_ioctl_get_supported_hv_cpuid(NULL, argp);
 		break;
+#endif
 	case KVM_GET_DEVICE_ATTR: {
 		struct kvm_device_attr attr;
 		r = -EFAULT;
@@ -5405,7 +5453,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 	if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) {
 		vcpu->arch.nmi_pending = 0;
 		atomic_set(&vcpu->arch.nmi_queued, events->nmi.pending);
-		kvm_make_request(KVM_REQ_NMI, vcpu);
+		if (events->nmi.pending)
+			kvm_make_request(KVM_REQ_NMI, vcpu);
 	}
 	static_call(kvm_x86_set_nmi_mask)(vcpu, events->nmi.masked);
 
@@ -5699,14 +5748,11 @@ static int kvm_vcpu_ioctl_device_attr(struct kvm_vcpu *vcpu,
 static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 				     struct kvm_enable_cap *cap)
 {
-	int r;
-	uint16_t vmcs_version;
-	void __user *user_ptr;
-
 	if (cap->flags)
 		return -EINVAL;
 
 	switch (cap->cap) {
+#ifdef CONFIG_KVM_HYPERV
 	case KVM_CAP_HYPERV_SYNIC2:
 		if (cap->args[0])
 			return -EINVAL;
@@ -5718,16 +5764,22 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 		return kvm_hv_activate_synic(vcpu, cap->cap ==
 					     KVM_CAP_HYPERV_SYNIC2);
 	case KVM_CAP_HYPERV_ENLIGHTENED_VMCS:
-		if (!kvm_x86_ops.nested_ops->enable_evmcs)
-			return -ENOTTY;
-		r = kvm_x86_ops.nested_ops->enable_evmcs(vcpu, &vmcs_version);
-		if (!r) {
-			user_ptr = (void __user *)(uintptr_t)cap->args[0];
-			if (copy_to_user(user_ptr, &vmcs_version,
-					 sizeof(vmcs_version)))
-				r = -EFAULT;
+		{
+			int r;
+			uint16_t vmcs_version;
+			void __user *user_ptr;
+
+			if (!kvm_x86_ops.nested_ops->enable_evmcs)
+				return -ENOTTY;
+			r = kvm_x86_ops.nested_ops->enable_evmcs(vcpu, &vmcs_version);
+			if (!r) {
+				user_ptr = (void __user *)(uintptr_t)cap->args[0];
+				if (copy_to_user(user_ptr, &vmcs_version,
+						 sizeof(vmcs_version)))
+					r = -EFAULT;
+			}
+			return r;
 		}
-		return r;
 	case KVM_CAP_HYPERV_DIRECT_TLBFLUSH:
 		if (!kvm_x86_ops.enable_l2_tlb_flush)
 			return -ENOTTY;
@@ -5736,6 +5788,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 
 	case KVM_CAP_HYPERV_ENFORCE_CPUID:
 		return kvm_hv_set_enforce_cpuid(vcpu, cap->args[0]);
+#endif
 
 	case KVM_CAP_ENFORCE_PV_FEATURE_CPUID:
 		vcpu->arch.pv_cpuid.enforce = cap->args[0];
@@ -6128,9 +6181,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
+#ifdef CONFIG_KVM_HYPERV
 	case KVM_GET_SUPPORTED_HV_CPUID:
 		r = kvm_ioctl_get_supported_hv_cpuid(vcpu, argp);
 		break;
+#endif
 #ifdef CONFIG_KVM_XEN
 	case KVM_XEN_VCPU_GET_ATTR: {
 		struct kvm_xen_vcpu_attr xva;
@@ -6961,6 +7016,9 @@ set_identity_unlock:
 		r = -EEXIST;
 		if (kvm->arch.vpit)
 			goto create_pit_unlock;
+		r = -ENOENT;
+		if (!pic_in_kernel(kvm))
+			goto create_pit_unlock;
 		r = -ENOMEM;
 		kvm->arch.vpit = kvm_create_pit(kvm, u.pit_config.flags);
 		if (kvm->arch.vpit)
@@ -7188,6 +7246,7 @@ set_pit2_out:
 		r = static_call(kvm_x86_mem_enc_unregister_region)(kvm, &region);
 		break;
 	}
+#ifdef CONFIG_KVM_HYPERV
 	case KVM_HYPERV_EVENTFD: {
 		struct kvm_hyperv_eventfd hvevfd;
 
@@ -7197,6 +7256,7 @@ set_pit2_out:
 		r = kvm_vm_ioctl_hv_eventfd(kvm, &hvevfd);
 		break;
 	}
+#endif
 	case KVM_SET_PMU_EVENT_FILTER:
 		r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp);
 		break;
@@ -7947,6 +8007,16 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
 
 	if (r < 0)
 		return X86EMUL_UNHANDLEABLE;
+
+	/*
+	 * Mark the page dirty _before_ checking whether or not the CMPXCHG was
+	 * successful, as the old value is written back on failure.  Note, for
+	 * live migration, this is unnecessarily conservative as CMPXCHG writes
+	 * back the original value and the access is atomic, but KVM's ABI is
+	 * that all writes are dirty logged, regardless of the value written.
+	 */
+	kvm_vcpu_mark_page_dirty(vcpu, gpa_to_gfn(gpa));
+
 	if (r)
 		return X86EMUL_CMPXCHG_FAILED;
 
@@ -8432,6 +8502,15 @@ static void emulator_vm_bugged(struct x86_emulate_ctxt *ctxt)
 		kvm_vm_bugged(kvm);
 }
 
+static gva_t emulator_get_untagged_addr(struct x86_emulate_ctxt *ctxt,
+					gva_t addr, unsigned int flags)
+{
+	if (!kvm_x86_ops.get_untagged_addr)
+		return addr;
+
+	return static_call(kvm_x86_get_untagged_addr)(emul_to_vcpu(ctxt), addr, flags);
+}
+
 static const struct x86_emulate_ops emulate_ops = {
 	.vm_bugged           = emulator_vm_bugged,
 	.read_gpr            = emulator_read_gpr,
@@ -8476,6 +8555,7 @@ static const struct x86_emulate_ops emulate_ops = {
 	.leave_smm           = emulator_leave_smm,
 	.triple_fault        = emulator_triple_fault,
 	.set_xcr             = emulator_set_xcr,
+	.get_untagged_addr   = emulator_get_untagged_addr,
 };
 
 static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
@@ -10575,19 +10655,20 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 
 static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu)
 {
-	u64 eoi_exit_bitmap[4];
-
 	if (!kvm_apic_hw_enabled(vcpu->arch.apic))
 		return;
 
+#ifdef CONFIG_KVM_HYPERV
 	if (to_hv_vcpu(vcpu)) {
+		u64 eoi_exit_bitmap[4];
+
 		bitmap_or((ulong *)eoi_exit_bitmap,
 			  vcpu->arch.ioapic_handled_vectors,
 			  to_hv_synic(vcpu)->vec_bitmap, 256);
 		static_call_cond(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap);
 		return;
 	}
-
+#endif
 	static_call_cond(kvm_x86_load_eoi_exitmap)(
 		vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors);
 }
@@ -10678,9 +10759,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		 * the flushes are considered "remote" and not "local" because
 		 * the requests can be initiated from other vCPUs.
 		 */
+#ifdef CONFIG_KVM_HYPERV
 		if (kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu) &&
 		    kvm_hv_vcpu_flush_tlb(vcpu))
 			kvm_vcpu_flush_tlb_guest(vcpu);
+#endif
 
 		if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
@@ -10733,6 +10816,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			vcpu_load_eoi_exitmap(vcpu);
 		if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu))
 			kvm_vcpu_reload_apic_access_page(vcpu);
+#ifdef CONFIG_KVM_HYPERV
 		if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
 			vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH;
@@ -10763,6 +10847,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		 */
 		if (kvm_check_request(KVM_REQ_HV_STIMER, vcpu))
 			kvm_hv_process_stimers(vcpu);
+#endif
 		if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu))
 			kvm_vcpu_update_apicv(vcpu);
 		if (kvm_check_request(KVM_REQ_APF_READY, vcpu))
@@ -11081,6 +11166,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 {
 	int r;
 
+	vcpu->run->exit_reason = KVM_EXIT_UNKNOWN;
 	vcpu->arch.l1tf_flush_l1d = true;
 
 	for (;;) {
@@ -11598,7 +11684,7 @@ static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 		 */
 		if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA))
 			return false;
-		if (kvm_vcpu_is_illegal_gpa(vcpu, sregs->cr3))
+		if (!kvm_vcpu_is_legal_cr3(vcpu, sregs->cr3))
 			return false;
 	} else {
 		/*
@@ -12207,7 +12293,6 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	}
 
 	if (!init_event) {
-		kvm_pmu_reset(vcpu);
 		vcpu->arch.smbase = 0x30000;
 
 		vcpu->arch.msr_misc_features_enables = 0;
@@ -12424,7 +12509,9 @@ void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
 
 void kvm_arch_free_vm(struct kvm *kvm)
 {
-	kfree(to_kvm_hv(kvm)->hv_pa_pg);
+#if IS_ENABLED(CONFIG_HYPERV)
+	kfree(kvm->arch.hv_pa_pg);
+#endif
 	__kvm_arch_free_vm(kvm);
 }
 
@@ -12434,9 +12521,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	int ret;
 	unsigned long flags;
 
-	if (type)
+	if (!kvm_is_vm_type_supported(type))
 		return -EINVAL;
 
+	kvm->arch.vm_type = type;
+
 	ret = kvm_page_track_init(kvm);
 	if (ret)
 		goto out;
@@ -12575,8 +12664,8 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
 		hva = slot->userspace_addr;
 	}
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
-		struct kvm_userspace_memory_region m;
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
+		struct kvm_userspace_memory_region2 m;
 
 		m.slot = id | (i << 16);
 		m.flags = 0;
@@ -12726,6 +12815,10 @@ static int kvm_alloc_memslot_metadata(struct kvm *kvm,
 		}
 	}
 
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	kvm_mmu_init_memslot_memory_attributes(kvm, slot);
+#endif
+
 	if (kvm_page_track_create_memslot(kvm, slot, npages))
 		goto out_free;
 
@@ -13536,6 +13629,10 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva)
 
 	switch (type) {
 	case INVPCID_TYPE_INDIV_ADDR:
+		/*
+		 * LAM doesn't apply to addresses that are inputs to TLB
+		 * invalidation.
+		 */
 		if ((!pcid_enabled && (operand.pcid != 0)) ||
 		    is_noncanonical_address(operand.gla, vcpu)) {
 			kvm_inject_gp(vcpu, 0);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 5184fde1dc54..2f7e19166658 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -530,6 +530,8 @@ bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type);
 		__reserved_bits |= X86_CR4_VMXE;        \
 	if (!__cpu_has(__c, X86_FEATURE_PCID))          \
 		__reserved_bits |= X86_CR4_PCIDE;       \
+	if (!__cpu_has(__c, X86_FEATURE_LAM))           \
+		__reserved_bits |= X86_CR4_LAM_SUP;     \
 	__reserved_bits;                                \
 })
 
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 523bb6df5ac9..4b4e738c6f1b 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -1162,7 +1162,9 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc)
 {
 	/* Only some feature flags need to be *enabled* by userspace */
 	u32 permitted_flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL |
-		KVM_XEN_HVM_CONFIG_EVTCHN_SEND;
+		KVM_XEN_HVM_CONFIG_EVTCHN_SEND |
+		KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE;
+	u32 old_flags;
 
 	if (xhc->flags & ~permitted_flags)
 		return -EINVAL;
@@ -1183,9 +1185,14 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc)
 	else if (!xhc->msr && kvm->arch.xen_hvm_config.msr)
 		static_branch_slow_dec_deferred(&kvm_xen_enabled);
 
+	old_flags = kvm->arch.xen_hvm_config.flags;
 	memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc));
 
 	mutex_unlock(&kvm->arch.xen.xen_lock);
+
+	if ((old_flags ^ xhc->flags) & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE)
+		kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE);
+
 	return 0;
 }
 
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 20ef350a60fb..10d5ed8b5990 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -163,23 +163,23 @@ SYM_CODE_END(__get_user_8_handle_exception)
 #endif
 
 /* get_user */
-	_ASM_EXTABLE(1b, __get_user_handle_exception)
-	_ASM_EXTABLE(2b, __get_user_handle_exception)
-	_ASM_EXTABLE(3b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(1b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(2b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(3b, __get_user_handle_exception)
 #ifdef CONFIG_X86_64
-	_ASM_EXTABLE(4b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(4b, __get_user_handle_exception)
 #else
-	_ASM_EXTABLE(4b, __get_user_8_handle_exception)
-	_ASM_EXTABLE(5b, __get_user_8_handle_exception)
+	_ASM_EXTABLE_UA(4b, __get_user_8_handle_exception)
+	_ASM_EXTABLE_UA(5b, __get_user_8_handle_exception)
 #endif
 
 /* __get_user */
-	_ASM_EXTABLE(6b, __get_user_handle_exception)
-	_ASM_EXTABLE(7b, __get_user_handle_exception)
-	_ASM_EXTABLE(8b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(6b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(7b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(8b, __get_user_handle_exception)
 #ifdef CONFIG_X86_64
-	_ASM_EXTABLE(9b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(9b, __get_user_handle_exception)
 #else
-	_ASM_EXTABLE(9b, __get_user_8_handle_exception)
-	_ASM_EXTABLE(10b, __get_user_8_handle_exception)
+	_ASM_EXTABLE_UA(9b, __get_user_8_handle_exception)
+	_ASM_EXTABLE_UA(10b, __get_user_8_handle_exception)
 #endif
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 2877f5934177..975c9c18263d 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -133,15 +133,15 @@ SYM_CODE_START_LOCAL(__put_user_handle_exception)
 	RET
 SYM_CODE_END(__put_user_handle_exception)
 
-	_ASM_EXTABLE(1b, __put_user_handle_exception)
-	_ASM_EXTABLE(2b, __put_user_handle_exception)
-	_ASM_EXTABLE(3b, __put_user_handle_exception)
-	_ASM_EXTABLE(4b, __put_user_handle_exception)
-	_ASM_EXTABLE(5b, __put_user_handle_exception)
-	_ASM_EXTABLE(6b, __put_user_handle_exception)
-	_ASM_EXTABLE(7b, __put_user_handle_exception)
-	_ASM_EXTABLE(9b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(1b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(2b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(3b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(4b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(5b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(6b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(7b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(9b, __put_user_handle_exception)
 #ifdef CONFIG_X86_32
-	_ASM_EXTABLE(8b, __put_user_handle_exception)
-	_ASM_EXTABLE(10b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(8b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(10b, __put_user_handle_exception)
 #endif
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 679b09cfe241..d6375b3c633b 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -798,15 +798,6 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,
 	show_opcodes(regs, loglvl);
 }
 
-/*
- * The (legacy) vsyscall page is the long page in the kernel portion
- * of the address space that has user-accessible permissions.
- */
-static bool is_vsyscall_vaddr(unsigned long vaddr)
-{
-	return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR);
-}
-
 static void
 __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 		       unsigned long address, u32 pkey, int si_code)
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index 968d7005f4a7..f50cc210a981 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -26,18 +26,31 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 	for (; addr < end; addr = next) {
 		pud_t *pud = pud_page + pud_index(addr);
 		pmd_t *pmd;
+		bool use_gbpage;
 
 		next = (addr & PUD_MASK) + PUD_SIZE;
 		if (next > end)
 			next = end;
 
-		if (info->direct_gbpages) {
-			pud_t pudval;
+		/* if this is already a gbpage, this portion is already mapped */
+		if (pud_large(*pud))
+			continue;
+
+		/* Is using a gbpage allowed? */
+		use_gbpage = info->direct_gbpages;
 
-			if (pud_present(*pud))
-				continue;
+		/* Don't use gbpage if it maps more than the requested region. */
+		/* at the begining: */
+		use_gbpage &= ((addr & ~PUD_MASK) == 0);
+		/* ... or at the end: */
+		use_gbpage &= ((next & ~PUD_MASK) == 0);
+
+		/* Never overwrite existing mappings */
+		use_gbpage &= !pud_present(*pud);
+
+		if (use_gbpage) {
+			pud_t pudval;
 
-			addr &= PUD_MASK;
 			pudval = __pud((addr - info->offset) | info->page_flag);
 			set_pud(pud, pudval);
 			continue;
diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c
index 6993f026adec..42115ac079cf 100644
--- a/arch/x86/mm/maccess.c
+++ b/arch/x86/mm/maccess.c
@@ -3,6 +3,8 @@
 #include <linux/uaccess.h>
 #include <linux/kernel.h>
 
+#include <asm/vsyscall.h>
+
 #ifdef CONFIG_X86_64
 bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
 {
@@ -16,6 +18,14 @@ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
 		return false;
 
 	/*
+	 * Reading from the vsyscall page may cause an unhandled fault in
+	 * certain cases.  Though it is at an address above TASK_SIZE_MAX, it is
+	 * usually considered as a user space address.
+	 */
+	if (is_vsyscall_vaddr(vaddr))
+		return false;
+
+	/*
 	 * Allow everything during early boot before 'x86_virt_bits'
 	 * is initialized.  Needed for instruction decoding in early
 	 * exception handlers.
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index adc497b93f03..65e9a6e391c0 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -934,7 +934,7 @@ static int __init cmp_memblk(const void *a, const void *b)
 	const struct numa_memblk *ma = *(const struct numa_memblk **)a;
 	const struct numa_memblk *mb = *(const struct numa_memblk **)b;
 
-	return ma->start - mb->start;
+	return (ma->start > mb->start) - (ma->start < mb->start);
 }
 
 static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata;
@@ -944,14 +944,12 @@ static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata;
  * @start: address to begin fill
  * @end: address to end fill
  *
- * Find and extend numa_meminfo memblks to cover the @start-@end
- * physical address range, such that the first memblk includes
- * @start, the last memblk includes @end, and any gaps in between
- * are filled.
+ * Find and extend numa_meminfo memblks to cover the physical
+ * address range @start-@end
  *
  * RETURNS:
  * 0		  : Success
- * NUMA_NO_MEMBLK : No memblk exists in @start-@end range
+ * NUMA_NO_MEMBLK : No memblks exist in address range @start-@end
  */
 
 int __init numa_fill_memblks(u64 start, u64 end)
@@ -963,17 +961,14 @@ int __init numa_fill_memblks(u64 start, u64 end)
 
 	/*
 	 * Create a list of pointers to numa_meminfo memblks that
-	 * overlap start, end. Exclude (start == bi->end) since
-	 * end addresses in both a CFMWS range and a memblk range
-	 * are exclusive.
-	 *
-	 * This list of pointers is used to make in-place changes
-	 * that fill out the numa_meminfo memblks.
+	 * overlap start, end. The list is used to make in-place
+	 * changes that fill out the numa_meminfo memblks.
 	 */
 	for (int i = 0; i < mi->nr_blks; i++) {
 		struct numa_memblk *bi = &mi->blk[i];
 
-		if (start < bi->end && end >= bi->start) {
+		if (memblock_addrs_overlap(start, end - start, bi->start,
+					   bi->end - bi->start)) {
 			blk[count] = &mi->blk[i];
 			count++;
 		}
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index e9b448d1b1b7..102880404046 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -755,10 +755,14 @@ pmd_t *lookup_pmd_address(unsigned long address)
  * areas on 32-bit NUMA systems.  The percpu areas can
  * end up in this kind of memory, for instance.
  *
- * This could be optimized, but it is only intended to be
- * used at initialization time, and keeping it
- * unoptimized should increase the testing coverage for
- * the more obscure platforms.
+ * Note that as long as the PTEs are well-formed with correct PFNs, this
+ * works without checking the PRESENT bit in the leaf PTE.  This is unlike
+ * the similar vmalloc_to_page() and derivatives.  Callers may depend on
+ * this behavior.
+ *
+ * This could be optimized, but it is only used in paths that are not perf
+ * sensitive, and keeping it unoptimized should increase the testing coverage
+ * for the more obscure platforms.
  */
 phys_addr_t slow_virt_to_phys(void *__virt_addr)
 {
@@ -2041,17 +2045,12 @@ int set_mce_nospec(unsigned long pfn)
 	return rc;
 }
 
-static int set_memory_p(unsigned long *addr, int numpages)
-{
-	return change_page_attr_set(addr, numpages, __pgprot(_PAGE_PRESENT), 0);
-}
-
 /* Restore full speculative operation to the pfn. */
 int clear_mce_nospec(unsigned long pfn)
 {
 	unsigned long addr = (unsigned long) pfn_to_kaddr(pfn);
 
-	return set_memory_p(&addr, 1);
+	return set_memory_p(addr, 1);
 }
 EXPORT_SYMBOL_GPL(clear_mce_nospec);
 #endif /* CONFIG_X86_64 */
@@ -2104,6 +2103,11 @@ int set_memory_np_noalias(unsigned long addr, int numpages)
 					CPA_NO_CHECK_ALIAS, NULL);
 }
 
+int set_memory_p(unsigned long addr, int numpages)
+{
+	return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_PRESENT), 0);
+}
+
 int set_memory_4k(unsigned long addr, int numpages)
 {
 	return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index ea2eb2ec90e2..55c4b07ec1f6 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -283,6 +283,9 @@ static int setup_mcfg_map(struct acpi_pci_root_info *ci)
 	info->mcfg_added = false;
 	seg = info->sd.domain;
 
+	dev_dbg(dev, "%s(%04x %pR ECAM %pa)\n", __func__, seg,
+		&root->secondary, &root->mcfg_addr);
+
 	/* return success if MMCFG is not in use */
 	if (raw_pci_ext_ops && raw_pci_ext_ops != &pci_mmcfg)
 		return 0;
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 4b3efaa82ab7..0cc9520666ef 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * mmconfig-shared.c - Low-level direct PCI config space access via
- *                     MMCONFIG - common code between i386 and x86-64.
+ * Low-level direct PCI config space access via ECAM - common code between
+ * i386 and x86-64.
  *
  * This code does:
  * - known chipset handling
@@ -11,6 +11,8 @@
  * themselves.
  */
 
+#define pr_fmt(fmt) "PCI: " fmt
+
 #include <linux/acpi.h>
 #include <linux/efi.h>
 #include <linux/pci.h>
@@ -24,9 +26,7 @@
 #include <asm/pci_x86.h>
 #include <asm/acpi.h>
 
-#define PREFIX "PCI: "
-
-/* Indicate if the mmcfg resources have been placed into the resource table. */
+/* Indicate if the ECAM resources have been placed into the resource table */
 static bool pci_mmcfg_running_state;
 static bool pci_mmcfg_arch_init_failed;
 static DEFINE_MUTEX(pci_mmcfg_lock);
@@ -90,7 +90,7 @@ static struct pci_mmcfg_region *pci_mmconfig_alloc(int segment, int start,
 	res->end = addr + PCI_MMCFG_BUS_OFFSET(end + 1) - 1;
 	res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 	snprintf(new->name, PCI_MMCFG_RESOURCE_NAME_LEN,
-		 "PCI MMCONFIG %04x [bus %02x-%02x]", segment, start, end);
+		 "PCI ECAM %04x [bus %02x-%02x]", segment, start, end);
 	res->name = new->name;
 
 	return new;
@@ -102,16 +102,15 @@ struct pci_mmcfg_region *__init pci_mmconfig_add(int segment, int start,
 	struct pci_mmcfg_region *new;
 
 	new = pci_mmconfig_alloc(segment, start, end, addr);
-	if (new) {
-		mutex_lock(&pci_mmcfg_lock);
-		list_add_sorted(new);
-		mutex_unlock(&pci_mmcfg_lock);
+	if (!new)
+		return NULL;
 
-		pr_info(PREFIX
-		       "MMCONFIG for domain %04x [bus %02x-%02x] at %pR "
-		       "(base %#lx)\n",
-		       segment, start, end, &new->res, (unsigned long)addr);
-	}
+	mutex_lock(&pci_mmcfg_lock);
+	list_add_sorted(new);
+	mutex_unlock(&pci_mmcfg_lock);
+
+	pr_info("ECAM %pR (base %#lx) for domain %04x [bus %02x-%02x]\n",
+		&new->res, (unsigned long)addr, segment, start, end);
 
 	return new;
 }
@@ -205,7 +204,7 @@ static const char *__init pci_mmcfg_amd_fam10h(void)
 	msr <<= 32;
 	msr |= low;
 
-	/* mmconfig is not enable */
+	/* ECAM is not enabled */
 	if (!(msr & FAM10H_MMIO_CONF_ENABLE))
 		return NULL;
 
@@ -367,7 +366,7 @@ static int __init pci_mmcfg_check_hostbridge(void)
 			name = pci_mmcfg_probes[i].probe();
 
 		if (name)
-			pr_info(PREFIX "%s with MMCONFIG support\n", name);
+			pr_info("%s with ECAM support\n", name);
 	}
 
 	/* some end_bus_number is crazy, fix it */
@@ -443,9 +442,11 @@ static bool is_acpi_reserved(u64 start, u64 end, enum e820_type not_used)
 	return mcfg_res.flags;
 }
 
-static bool is_efi_mmio(u64 start, u64 end, enum e820_type not_used)
+static bool is_efi_mmio(struct resource *res)
 {
 #ifdef CONFIG_EFI
+	u64 start = res->start;
+	u64 end = res->start + resource_size(res);
 	efi_memory_desc_t *md;
 	u64 size, mmio_start, mmio_end;
 
@@ -455,11 +456,6 @@ static bool is_efi_mmio(u64 start, u64 end, enum e820_type not_used)
 			mmio_start = md->phys_addr;
 			mmio_end = mmio_start + size;
 
-			/*
-			 * N.B. Caller supplies (start, start + size),
-			 * so to match, mmio_end is the first address
-			 * *past* the EFI_MEMORY_MAPPED_IO area.
-			 */
 			if (mmio_start <= start && end <= mmio_end)
 				return true;
 		}
@@ -490,11 +486,10 @@ static bool __ref is_mmconf_reserved(check_reserved_t is_reserved,
 		return false;
 
 	if (dev)
-		dev_info(dev, "MMCONFIG at %pR reserved as %s\n",
+		dev_info(dev, "ECAM %pR reserved as %s\n",
 			 &cfg->res, method);
 	else
-		pr_info(PREFIX "MMCONFIG at %pR reserved as %s\n",
-		       &cfg->res, method);
+		pr_info("ECAM %pR reserved as %s\n", &cfg->res, method);
 
 	if (old_size != size) {
 		/* update end_bus */
@@ -503,47 +498,51 @@ static bool __ref is_mmconf_reserved(check_reserved_t is_reserved,
 		cfg->res.end = cfg->res.start +
 		    PCI_MMCFG_BUS_OFFSET(num_buses) - 1;
 		snprintf(cfg->name, PCI_MMCFG_RESOURCE_NAME_LEN,
-			 "PCI MMCONFIG %04x [bus %02x-%02x]",
+			 "PCI ECAM %04x [bus %02x-%02x]",
 			 cfg->segment, cfg->start_bus, cfg->end_bus);
 
 		if (dev)
-			dev_info(dev,
-				"MMCONFIG "
-				"at %pR (base %#lx) (size reduced!)\n",
-				&cfg->res, (unsigned long) cfg->address);
+			dev_info(dev, "ECAM %pR (base %#lx) (size reduced!)\n",
+				 &cfg->res, (unsigned long) cfg->address);
 		else
-			pr_info(PREFIX
-				"MMCONFIG for %04x [bus%02x-%02x] "
-				"at %pR (base %#lx) (size reduced!)\n",
-				cfg->segment, cfg->start_bus, cfg->end_bus,
-				&cfg->res, (unsigned long) cfg->address);
+			pr_info("ECAM %pR (base %#lx) for %04x [bus%02x-%02x] (size reduced!)\n",
+				&cfg->res, (unsigned long) cfg->address,
+				cfg->segment, cfg->start_bus, cfg->end_bus);
 	}
 
 	return true;
 }
 
-static bool __ref
-pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int early)
+static bool __ref pci_mmcfg_reserved(struct device *dev,
+				     struct pci_mmcfg_region *cfg, int early)
 {
+	struct resource *conflict;
+
 	if (!early && !acpi_disabled) {
 		if (is_mmconf_reserved(is_acpi_reserved, cfg, dev,
 				       "ACPI motherboard resource"))
 			return true;
 
 		if (dev)
-			dev_info(dev, FW_INFO
-				 "MMCONFIG at %pR not reserved in "
-				 "ACPI motherboard resources\n",
+			dev_info(dev, FW_INFO "ECAM %pR not reserved in ACPI motherboard resources\n",
 				 &cfg->res);
 		else
-			pr_info(FW_INFO PREFIX
-			       "MMCONFIG at %pR not reserved in "
-			       "ACPI motherboard resources\n",
-			       &cfg->res);
-
-		if (is_mmconf_reserved(is_efi_mmio, cfg, dev,
-				       "EfiMemoryMappedIO"))
+			pr_info(FW_INFO "ECAM %pR not reserved in ACPI motherboard resources\n",
+			        &cfg->res);
+
+		if (is_efi_mmio(&cfg->res)) {
+			pr_info("ECAM %pR is EfiMemoryMappedIO; assuming valid\n",
+				&cfg->res);
+			conflict = insert_resource_conflict(&iomem_resource,
+							    &cfg->res);
+			if (conflict)
+				pr_warn("ECAM %pR conflicts with %s %pR\n",
+					&cfg->res, conflict->name, conflict);
+			else
+				pr_info("ECAM %pR reserved to work around lack of ACPI motherboard _CRS\n",
+					&cfg->res);
 			return true;
+		}
 	}
 
 	/*
@@ -569,30 +568,31 @@ static void __init pci_mmcfg_reject_broken(int early)
 	struct pci_mmcfg_region *cfg;
 
 	list_for_each_entry(cfg, &pci_mmcfg_list, list) {
-		if (pci_mmcfg_check_reserved(NULL, cfg, early) == 0) {
-			pr_info(PREFIX "not using MMCONFIG\n");
+		if (!pci_mmcfg_reserved(NULL, cfg, early)) {
+			pr_info("not using ECAM (%pR not reserved)\n",
+				&cfg->res);
 			free_all_mmcfg();
 			return;
 		}
 	}
 }
 
-static int __init acpi_mcfg_check_entry(struct acpi_table_mcfg *mcfg,
-					struct acpi_mcfg_allocation *cfg)
+static bool __init acpi_mcfg_valid_entry(struct acpi_table_mcfg *mcfg,
+					 struct acpi_mcfg_allocation *cfg)
 {
 	if (cfg->address < 0xFFFFFFFF)
-		return 0;
+		return true;
 
 	if (!strncmp(mcfg->header.oem_id, "SGI", 3))
-		return 0;
+		return true;
 
 	if ((mcfg->header.revision >= 1) && (dmi_get_bios_year() >= 2010))
-		return 0;
+		return true;
 
-	pr_err(PREFIX "MCFG region for %04x [bus %02x-%02x] at %#llx "
-	       "is above 4GB, ignored\n", cfg->pci_segment,
-	       cfg->start_bus_number, cfg->end_bus_number, cfg->address);
-	return -EINVAL;
+	pr_err("ECAM at %#llx for %04x [bus %02x-%02x] is above 4GB, ignored\n",
+	       cfg->address, cfg->pci_segment, cfg->start_bus_number,
+	       cfg->end_bus_number);
+	return false;
 }
 
 static int __init pci_parse_mcfg(struct acpi_table_header *header)
@@ -616,21 +616,21 @@ static int __init pci_parse_mcfg(struct acpi_table_header *header)
 		i -= sizeof(struct acpi_mcfg_allocation);
 	}
 	if (entries == 0) {
-		pr_err(PREFIX "MMCONFIG has no entries\n");
+		pr_err("MCFG has no entries\n");
 		return -ENODEV;
 	}
 
 	cfg_table = (struct acpi_mcfg_allocation *) &mcfg[1];
 	for (i = 0; i < entries; i++) {
 		cfg = &cfg_table[i];
-		if (acpi_mcfg_check_entry(mcfg, cfg)) {
+		if (!acpi_mcfg_valid_entry(mcfg, cfg)) {
 			free_all_mmcfg();
 			return -ENODEV;
 		}
 
 		if (pci_mmconfig_add(cfg->pci_segment, cfg->start_bus_number,
 				   cfg->end_bus_number, cfg->address) == NULL) {
-			pr_warn(PREFIX "no memory for MCFG entries\n");
+			pr_warn("no memory for MCFG entries\n");
 			free_all_mmcfg();
 			return -ENOMEM;
 		}
@@ -667,6 +667,8 @@ static int pci_mmcfg_for_each_region(int (*func)(__u64 start, __u64 size,
 
 static void __init __pci_mmcfg_init(int early)
 {
+	pr_debug("%s(%s)\n", __func__, early ? "early" : "late");
+
 	pci_mmcfg_reject_broken(early);
 	if (list_empty(&pci_mmcfg_list))
 		return;
@@ -693,6 +695,8 @@ static int __initdata known_bridge;
 
 void __init pci_mmcfg_early_init(void)
 {
+	pr_debug("%s() pci_probe %#x\n", __func__, pci_probe);
+
 	if (pci_probe & PCI_PROBE_MMCONF) {
 		if (pci_mmcfg_check_hostbridge())
 			known_bridge = 1;
@@ -706,14 +710,16 @@ void __init pci_mmcfg_early_init(void)
 
 void __init pci_mmcfg_late_init(void)
 {
-	/* MMCONFIG disabled */
+	pr_debug("%s() pci_probe %#x\n", __func__, pci_probe);
+
+	/* ECAM disabled */
 	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
 		return;
 
 	if (known_bridge)
 		return;
 
-	/* MMCONFIG hasn't been enabled yet, try again */
+	/* ECAM hasn't been enabled yet, try again */
 	if (pci_probe & PCI_PROBE_MASK & ~PCI_PROBE_MMCONF) {
 		acpi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg);
 		__pci_mmcfg_init(0);
@@ -726,7 +732,9 @@ static int __init pci_mmcfg_late_insert_resources(void)
 
 	pci_mmcfg_running_state = true;
 
-	/* If we are not using MMCONFIG, don't insert the resources. */
+	pr_debug("%s() pci_probe %#x\n", __func__, pci_probe);
+
+	/* If we are not using ECAM, don't insert the resources. */
 	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
 		return 1;
 
@@ -735,21 +743,24 @@ static int __init pci_mmcfg_late_insert_resources(void)
 	 * marked so it won't cause request errors when __request_region is
 	 * called.
 	 */
-	list_for_each_entry(cfg, &pci_mmcfg_list, list)
-		if (!cfg->res.parent)
+	list_for_each_entry(cfg, &pci_mmcfg_list, list) {
+		if (!cfg->res.parent) {
+			pr_debug("%s() insert %pR\n", __func__, &cfg->res);
 			insert_resource(&iomem_resource, &cfg->res);
+		}
+	}
 
 	return 0;
 }
 
 /*
- * Perform MMCONFIG resource insertion after PCI initialization to allow for
+ * Perform ECAM resource insertion after PCI initialization to allow for
  * misprogrammed MCFG tables that state larger sizes but actually conflict
  * with other system resources.
  */
 late_initcall(pci_mmcfg_late_insert_resources);
 
-/* Add MMCFG information for host bridges */
+/* Add ECAM information for host bridges */
 int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
 			phys_addr_t addr)
 {
@@ -757,6 +768,8 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
 	struct resource *tmp = NULL;
 	struct pci_mmcfg_region *cfg;
 
+	dev_dbg(dev, "%s(%04x [bus %02x-%02x])\n", __func__, seg, start, end);
+
 	if (!(pci_probe & PCI_PROBE_MMCONF) || pci_mmcfg_arch_init_failed)
 		return -ENODEV;
 
@@ -767,15 +780,17 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
 	cfg = pci_mmconfig_lookup(seg, start);
 	if (cfg) {
 		if (cfg->end_bus < end)
-			dev_info(dev, FW_INFO
-				 "MMCONFIG for "
-				 "domain %04x [bus %02x-%02x] "
-				 "only partially covers this bridge\n",
-				  cfg->segment, cfg->start_bus, cfg->end_bus);
+			dev_info(dev, FW_INFO "ECAM %pR for domain %04x [bus %02x-%02x] only partially covers this bridge\n",
+				 &cfg->res, cfg->segment, cfg->start_bus,
+				 cfg->end_bus);
 		mutex_unlock(&pci_mmcfg_lock);
 		return -EEXIST;
 	}
 
+	/*
+	 * Don't move earlier; we must return -EEXIST, not -EINVAL, if
+	 * pci_mmconfig_lookup() finds something
+	 */
 	if (!addr) {
 		mutex_unlock(&pci_mmcfg_lock);
 		return -EINVAL;
@@ -784,10 +799,10 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
 	rc = -EBUSY;
 	cfg = pci_mmconfig_alloc(seg, start, end, addr);
 	if (cfg == NULL) {
-		dev_warn(dev, "fail to add MMCONFIG (out of memory)\n");
+		dev_warn(dev, "fail to add ECAM (out of memory)\n");
 		rc = -ENOMEM;
-	} else if (!pci_mmcfg_check_reserved(dev, cfg, 0)) {
-		dev_warn(dev, FW_BUG "MMCONFIG %pR isn't reserved\n",
+	} else if (!pci_mmcfg_reserved(dev, cfg, 0)) {
+		dev_warn(dev, FW_BUG "ECAM %pR isn't reserved\n",
 			 &cfg->res);
 	} else {
 		/* Insert resource if it's not in boot stage */
@@ -796,16 +811,13 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
 						       &cfg->res);
 
 		if (tmp) {
-			dev_warn(dev,
-				 "MMCONFIG %pR conflicts with "
-				 "%s %pR\n",
+			dev_warn(dev, "ECAM %pR conflicts with %s %pR\n",
 				 &cfg->res, tmp->name, tmp);
 		} else if (pci_mmcfg_arch_map(cfg)) {
-			dev_warn(dev, "fail to map MMCONFIG %pR.\n",
-				 &cfg->res);
+			dev_warn(dev, "fail to map ECAM %pR\n", &cfg->res);
 		} else {
 			list_add_sorted(cfg);
-			dev_info(dev, "MMCONFIG at %pR (base %#lx)\n",
+			dev_info(dev, "ECAM %pR (base %#lx)\n",
 				 &cfg->res, (unsigned long)addr);
 			cfg = NULL;
 			rc = 0;
@@ -823,7 +835,7 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
 	return rc;
 }
 
-/* Delete MMCFG information for host bridges */
+/* Delete ECAM information for host bridges */
 int pci_mmconfig_delete(u16 seg, u8 start, u8 end)
 {
 	struct pci_mmcfg_region *cfg;
diff --git a/arch/x86/pci/mmconfig_32.c b/arch/x86/pci/mmconfig_32.c
index bfa789875322..f9ef97c593cf 100644
--- a/arch/x86/pci/mmconfig_32.c
+++ b/arch/x86/pci/mmconfig_32.c
@@ -131,7 +131,7 @@ const struct pci_raw_ops pci_mmcfg = {
 
 int __init pci_mmcfg_arch_init(void)
 {
-	printk(KERN_INFO "PCI: Using MMCONFIG for extended config space\n");
+	printk(KERN_INFO "PCI: Using ECAM for extended config space\n");
 	raw_pci_ext_ops = &pci_mmcfg;
 	return 1;
 }
diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c
index 0c7b6e66c644..cb5aa79a759e 100644
--- a/arch/x86/pci/mmconfig_64.c
+++ b/arch/x86/pci/mmconfig_64.c
@@ -6,6 +6,8 @@
  * space mapped. This allows lockless config space operation.
  */
 
+#define pr_fmt(fmt) "PCI: " fmt
+
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/acpi.h>
@@ -14,8 +16,6 @@
 #include <asm/e820/api.h>
 #include <asm/pci_x86.h>
 
-#define PREFIX "PCI: "
-
 static char __iomem *pci_dev_base(unsigned int seg, unsigned int bus, unsigned int devfn)
 {
 	struct pci_mmcfg_region *cfg = pci_mmconfig_lookup(seg, bus);
@@ -111,6 +111,25 @@ static void __iomem *mcfg_ioremap(struct pci_mmcfg_region *cfg)
 	return addr;
 }
 
+int pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg)
+{
+	cfg->virt = mcfg_ioremap(cfg);
+	if (!cfg->virt) {
+		pr_err("can't map ECAM at %pR\n", &cfg->res);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void pci_mmcfg_arch_unmap(struct pci_mmcfg_region *cfg)
+{
+	if (cfg && cfg->virt) {
+		iounmap(cfg->virt + PCI_MMCFG_BUS_OFFSET(cfg->start_bus));
+		cfg->virt = NULL;
+	}
+}
+
 int __init pci_mmcfg_arch_init(void)
 {
 	struct pci_mmcfg_region *cfg;
@@ -133,22 +152,3 @@ void __init pci_mmcfg_arch_free(void)
 	list_for_each_entry(cfg, &pci_mmcfg_list, list)
 		pci_mmcfg_arch_unmap(cfg);
 }
-
-int pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg)
-{
-	cfg->virt = mcfg_ioremap(cfg);
-	if (!cfg->virt) {
-		pr_err(PREFIX "can't map MMCONFIG at %pR\n", &cfg->res);
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-void pci_mmcfg_arch_unmap(struct pci_mmcfg_region *cfg)
-{
-	if (cfg && cfg->virt) {
-		iounmap(cfg->virt + PCI_MMCFG_BUS_OFFSET(cfg->start_bus));
-		cfg->virt = NULL;
-	}
-}
diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c
index 4f15280732ed..244c643bb0b5 100644
--- a/arch/x86/pci/pcbios.c
+++ b/arch/x86/pci/pcbios.c
@@ -3,6 +3,8 @@
  * BIOS32 and PCI BIOS handling.
  */
 
+#include <linux/bits.h>
+#include <linux/bitfield.h>
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -29,8 +31,19 @@
 #define PCIBIOS_HW_TYPE1_SPEC		0x10
 #define PCIBIOS_HW_TYPE2_SPEC		0x20
 
+/*
+ * Returned in EAX:
+ * - AH: return code
+ */
+#define PCIBIOS_RETURN_CODE			GENMASK(15, 8)
+
 int pcibios_enabled;
 
+static u8 pcibios_get_return_code(u32 eax)
+{
+	return FIELD_GET(PCIBIOS_RETURN_CODE, eax);
+}
+
 /* According to the BIOS specification at:
  * http://members.datafast.net.au/dft0802/specs/bios21.pdf, we could
  * restrict the x zone to some pages and make it ro. But this may be
@@ -154,7 +167,7 @@ static int __init check_pcibios(void)
 			: "memory");
 		local_irq_restore(flags);
 
-		status = (eax >> 8) & 0xff;
+		status = pcibios_get_return_code(eax);
 		hw_mech = eax & 0xff;
 		major_ver = (ebx >> 8) & 0xff;
 		minor_ver = ebx & 0xff;
@@ -227,7 +240,7 @@ static int pci_bios_read(unsigned int seg, unsigned int bus,
 
 	raw_spin_unlock_irqrestore(&pci_config_lock, flags);
 
-	return (int)((result & 0xff00) >> 8);
+	return pcibios_get_return_code(result);
 }
 
 static int pci_bios_write(unsigned int seg, unsigned int bus,
@@ -269,7 +282,7 @@ static int pci_bios_write(unsigned int seg, unsigned int bus,
 
 	raw_spin_unlock_irqrestore(&pci_config_lock, flags);
 
-	return (int)((result & 0xff00) >> 8);
+	return pcibios_get_return_code(result);
 }
 
 
@@ -385,9 +398,10 @@ struct irq_routing_table * pcibios_get_irq_routing_table(void)
 		  "m" (opt)
 		: "memory");
 	DBG("OK  ret=%d, size=%d, map=%x\n", ret, opt.size, map);
-	if (ret & 0xff00)
-		printk(KERN_ERR "PCI: Error %02x when fetching IRQ routing table.\n", (ret >> 8) & 0xff);
-	else if (opt.size) {
+	ret = pcibios_get_return_code(ret);
+	if (ret) {
+		printk(KERN_ERR "PCI: Error %02x when fetching IRQ routing table.\n", ret);
+	} else if (opt.size) {
 		rt = kmalloc(sizeof(struct irq_routing_table) + opt.size, GFP_KERNEL);
 		if (rt) {
 			memset(rt, 0, sizeof(struct irq_routing_table));
@@ -415,7 +429,7 @@ int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq)
 		  "b" ((dev->bus->number << 8) | dev->devfn),
 		  "c" ((irq << 8) | (pin + 10)),
 		  "S" (&pci_indirect));
-	return !(ret & 0xff00);
+	return pcibios_get_return_code(ret) == PCIBIOS_SUCCESSFUL;
 }
 EXPORT_SYMBOL(pcibios_set_irq_routing);
 
diff --git a/arch/x86/um/asm/elf.h b/arch/x86/um/asm/elf.h
index 6523eb7c3bd1..6052200fe925 100644
--- a/arch/x86/um/asm/elf.h
+++ b/arch/x86/um/asm/elf.h
@@ -168,8 +168,8 @@ do {								\
 	(pr_reg)[18] = (_regs)->regs.gp[18];			\
 	(pr_reg)[19] = (_regs)->regs.gp[19];			\
 	(pr_reg)[20] = (_regs)->regs.gp[20];			\
-	(pr_reg)[21] = current->thread.arch.fs;			\
-	(pr_reg)[22] = 0;					\
+	(pr_reg)[21] = (_regs)->regs.gp[21];			\
+	(pr_reg)[22] = (_regs)->regs.gp[22];			\
 	(pr_reg)[23] = 0;					\
 	(pr_reg)[24] = 0;					\
 	(pr_reg)[25] = 0;					\
diff --git a/arch/x86/um/asm/processor_64.h b/arch/x86/um/asm/processor_64.h
index 1ef9c21877bc..f90159508936 100644
--- a/arch/x86/um/asm/processor_64.h
+++ b/arch/x86/um/asm/processor_64.h
@@ -10,13 +10,11 @@
 struct arch_thread {
         unsigned long debugregs[8];
         int debugregs_seq;
-        unsigned long fs;
         struct faultinfo faultinfo;
 };
 
 #define INIT_ARCH_THREAD { .debugregs  		= { [ 0 ... 7 ] = 0 }, \
 			   .debugregs_seq	= 0, \
-			   .fs			= 0, \
 			   .faultinfo		= { 0, 0, 0 } }
 
 #define STACKSLOTS_PER_LINE 4
@@ -28,7 +26,6 @@ static inline void arch_flush_thread(struct arch_thread *thread)
 static inline void arch_copy_thread(struct arch_thread *from,
                                     struct arch_thread *to)
 {
-	to->fs = from->fs;
 }
 
 #define current_sp() ({ void *sp; __asm__("movq %%rsp, %0" : "=r" (sp) : ); sp; })
diff --git a/arch/x86/um/os-Linux/Makefile b/arch/x86/um/os-Linux/Makefile
index ae169125d03f..5249bbc30dcd 100644
--- a/arch/x86/um/os-Linux/Makefile
+++ b/arch/x86/um/os-Linux/Makefile
@@ -6,7 +6,6 @@
 obj-y = registers.o task_size.o mcontext.o
 
 obj-$(CONFIG_X86_32) += tls.o
-obj-$(CONFIG_64BIT) += prctl.o
 
 USER_OBJS := $(obj-y)
 
diff --git a/arch/x86/um/os-Linux/prctl.c b/arch/x86/um/os-Linux/prctl.c
deleted file mode 100644
index 8431e87ac333..000000000000
--- a/arch/x86/um/os-Linux/prctl.c
+++ /dev/null
@@ -1,12 +0,0 @@
-/*
- * Copyright (C) 2007 Jeff Dike (jdike@{addtoit.com,linux.intel.com})
- * Licensed under the GPL
- */
-
-#include <sys/ptrace.h>
-#include <asm/ptrace.h>
-
-int os_arch_prctl(int pid, int option, unsigned long *arg2)
-{
-	return ptrace(PTRACE_ARCH_PRCTL, pid, (unsigned long) arg2, option);
-}
diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c
index 0bc4b73a9cde..7f1abde2c84b 100644
--- a/arch/x86/um/ptrace_32.c
+++ b/arch/x86/um/ptrace_32.c
@@ -25,30 +25,6 @@ void arch_switch_to(struct task_struct *to)
 		printk(KERN_WARNING "arch_switch_tls failed, errno = EINVAL\n");
 }
 
-int is_syscall(unsigned long addr)
-{
-	unsigned short instr;
-	int n;
-
-	n = copy_from_user(&instr, (void __user *) addr, sizeof(instr));
-	if (n) {
-		/* access_process_vm() grants access to vsyscall and stub,
-		 * while copy_from_user doesn't. Maybe access_process_vm is
-		 * slow, but that doesn't matter, since it will be called only
-		 * in case of singlestepping, if copy_from_user failed.
-		 */
-		n = access_process_vm(current, addr, &instr, sizeof(instr),
-				FOLL_FORCE);
-		if (n != sizeof(instr)) {
-			printk(KERN_ERR "is_syscall : failed to read "
-			       "instruction from 0x%lx\n", addr);
-			return 1;
-		}
-	}
-	/* int 0x80 or sysenter */
-	return (instr == 0x80cd) || (instr == 0x340f);
-}
-
 /* determines which flags the user has access to. */
 /* 1 = access 0 = no access */
 #define FLAG_MASK 0x00044dd5
diff --git a/arch/x86/um/ptrace_64.c b/arch/x86/um/ptrace_64.c
index 289d0159b041..aa68d83d3f44 100644
--- a/arch/x86/um/ptrace_64.c
+++ b/arch/x86/um/ptrace_64.c
@@ -188,32 +188,6 @@ int peek_user(struct task_struct *child, long addr, long data)
 	return put_user(tmp, (unsigned long *) data);
 }
 
-/* XXX Mostly copied from sys-i386 */
-int is_syscall(unsigned long addr)
-{
-	unsigned short instr;
-	int n;
-
-	n = copy_from_user(&instr, (void __user *) addr, sizeof(instr));
-	if (n) {
-		/*
-		 * access_process_vm() grants access to vsyscall and stub,
-		 * while copy_from_user doesn't. Maybe access_process_vm is
-		 * slow, but that doesn't matter, since it will be called only
-		 * in case of singlestepping, if copy_from_user failed.
-		 */
-		n = access_process_vm(current, addr, &instr, sizeof(instr),
-				FOLL_FORCE);
-		if (n != sizeof(instr)) {
-			printk("is_syscall : failed to read instruction from "
-			       "0x%lx\n", addr);
-			return 1;
-		}
-	}
-	/* sysenter */
-	return instr == 0x050f;
-}
-
 static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child)
 {
 	int err, n, cpu = ((struct thread_info *) child->stack)->cpu;
diff --git a/arch/x86/um/shared/sysdep/ptrace_32.h b/arch/x86/um/shared/sysdep/ptrace_32.h
index db8478a83a09..0c4989842fbe 100644
--- a/arch/x86/um/shared/sysdep/ptrace_32.h
+++ b/arch/x86/um/shared/sysdep/ptrace_32.h
@@ -8,10 +8,6 @@
 
 #define MAX_FP_NR HOST_FPX_SIZE
 
-void set_using_sysemu(int value);
-int get_using_sysemu(void);
-extern int sysemu_supported;
-
 #define UPT_SYSCALL_ARG1(r) UPT_BX(r)
 #define UPT_SYSCALL_ARG2(r) UPT_CX(r)
 #define UPT_SYSCALL_ARG3(r) UPT_DX(r)
diff --git a/arch/x86/um/shared/sysdep/ptrace_user.h b/arch/x86/um/shared/sysdep/ptrace_user.h
index 44782bbad41e..1d1a824fa652 100644
--- a/arch/x86/um/shared/sysdep/ptrace_user.h
+++ b/arch/x86/um/shared/sysdep/ptrace_user.h
@@ -15,14 +15,12 @@
 #define FP_SIZE ((HOST_FPX_SIZE > HOST_FP_SIZE) ? HOST_FPX_SIZE : HOST_FP_SIZE)
 #else
 #define FP_SIZE HOST_FP_SIZE
+#endif
 
 /*
- * x86_64 FC3 doesn't define this in /usr/include/linux/ptrace.h even though
- * it's defined in the kernel's include/linux/ptrace.h. Additionally, use the
- * 2.4 name and value for 2.4 host compatibility.
+ * glibc before 2.27 does not include PTRACE_SYSEMU_SINGLESTEP in its enum,
+ * ensure we have a definition by (re-)defining it here.
  */
-#ifndef PTRACE_OLDSETOPTIONS
-#define PTRACE_OLDSETOPTIONS 21
-#endif
-
+#ifndef PTRACE_SYSEMU_SINGLESTEP
+#define PTRACE_SYSEMU_SINGLESTEP 32
 #endif
diff --git a/arch/x86/um/shared/sysdep/stub_32.h b/arch/x86/um/shared/sysdep/stub_32.h
index 38fa894b65d0..ea8b5a2d67af 100644
--- a/arch/x86/um/shared/sysdep/stub_32.h
+++ b/arch/x86/um/shared/sysdep/stub_32.h
@@ -12,72 +12,79 @@
 #define STUB_MMAP_NR __NR_mmap2
 #define MMAP_OFFSET(o) ((o) >> UM_KERN_PAGE_SHIFT)
 
-static inline long stub_syscall0(long syscall)
+static __always_inline long stub_syscall0(long syscall)
 {
 	long ret;
 
-	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall));
+	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall)
+			: "memory");
 
 	return ret;
 }
 
-static inline long stub_syscall1(long syscall, long arg1)
+static __always_inline long stub_syscall1(long syscall, long arg1)
 {
 	long ret;
 
-	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1));
+	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1)
+			: "memory");
 
 	return ret;
 }
 
-static inline long stub_syscall2(long syscall, long arg1, long arg2)
+static __always_inline long stub_syscall2(long syscall, long arg1, long arg2)
 {
 	long ret;
 
 	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1),
-			"c" (arg2));
+			"c" (arg2)
+			: "memory");
 
 	return ret;
 }
 
-static inline long stub_syscall3(long syscall, long arg1, long arg2, long arg3)
+static __always_inline long stub_syscall3(long syscall, long arg1, long arg2,
+					  long arg3)
 {
 	long ret;
 
 	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1),
-			"c" (arg2), "d" (arg3));
+			"c" (arg2), "d" (arg3)
+			: "memory");
 
 	return ret;
 }
 
-static inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3,
-				 long arg4)
+static __always_inline long stub_syscall4(long syscall, long arg1, long arg2,
+					  long arg3, long arg4)
 {
 	long ret;
 
 	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1),
-			"c" (arg2), "d" (arg3), "S" (arg4));
+			"c" (arg2), "d" (arg3), "S" (arg4)
+			: "memory");
 
 	return ret;
 }
 
-static inline long stub_syscall5(long syscall, long arg1, long arg2, long arg3,
-				 long arg4, long arg5)
+static __always_inline long stub_syscall5(long syscall, long arg1, long arg2,
+					  long arg3, long arg4, long arg5)
 {
 	long ret;
 
 	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1),
-			"c" (arg2), "d" (arg3), "S" (arg4), "D" (arg5));
+			"c" (arg2), "d" (arg3), "S" (arg4), "D" (arg5)
+			: "memory");
 
 	return ret;
 }
 
-static inline void trap_myself(void)
+static __always_inline void trap_myself(void)
 {
 	__asm("int3");
 }
 
-static inline void remap_stack_and_trap(void)
+static __always_inline void remap_stack_and_trap(void)
 {
 	__asm__ volatile (
 		"movl %%esp,%%ebx ;"
diff --git a/arch/x86/um/shared/sysdep/stub_64.h b/arch/x86/um/shared/sysdep/stub_64.h
index 2de1c8f88173..b24168ef0ac4 100644
--- a/arch/x86/um/shared/sysdep/stub_64.h
+++ b/arch/x86/um/shared/sysdep/stub_64.h
@@ -16,7 +16,7 @@
 #define __syscall_clobber "r11","rcx","memory"
 #define __syscall "syscall"
 
-static inline long stub_syscall0(long syscall)
+static __always_inline long stub_syscall0(long syscall)
 {
 	long ret;
 
@@ -27,7 +27,7 @@ static inline long stub_syscall0(long syscall)
 	return ret;
 }
 
-static inline long stub_syscall2(long syscall, long arg1, long arg2)
+static __always_inline long stub_syscall2(long syscall, long arg1, long arg2)
 {
 	long ret;
 
@@ -38,7 +38,8 @@ static inline long stub_syscall2(long syscall, long arg1, long arg2)
 	return ret;
 }
 
-static inline long stub_syscall3(long syscall, long arg1, long arg2, long arg3)
+static __always_inline long stub_syscall3(long syscall, long arg1, long arg2,
+					  long arg3)
 {
 	long ret;
 
@@ -50,7 +51,7 @@ static inline long stub_syscall3(long syscall, long arg1, long arg2, long arg3)
 	return ret;
 }
 
-static inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3,
+static __always_inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3,
 				 long arg4)
 {
 	long ret;
@@ -64,8 +65,8 @@ static inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3,
 	return ret;
 }
 
-static inline long stub_syscall5(long syscall, long arg1, long arg2, long arg3,
-				 long arg4, long arg5)
+static __always_inline long stub_syscall5(long syscall, long arg1, long arg2,
+					  long arg3, long arg4, long arg5)
 {
 	long ret;
 
@@ -78,12 +79,12 @@ static inline long stub_syscall5(long syscall, long arg1, long arg2, long arg3,
 	return ret;
 }
 
-static inline void trap_myself(void)
+static __always_inline void trap_myself(void)
 {
 	__asm("int3");
 }
 
-static inline void remap_stack_and_trap(void)
+static __always_inline void remap_stack_and_trap(void)
 {
 	__asm__ volatile (
 		"movq %0,%%rax ;"
diff --git a/arch/x86/um/syscalls_64.c b/arch/x86/um/syscalls_64.c
index 27b29ae6c471..6a00a28c9cca 100644
--- a/arch/x86/um/syscalls_64.c
+++ b/arch/x86/um/syscalls_64.c
@@ -16,60 +16,24 @@
 long arch_prctl(struct task_struct *task, int option,
 		unsigned long __user *arg2)
 {
-	unsigned long *ptr = arg2, tmp;
-	long ret;
-	int pid = task->mm->context.id.u.pid;
-
-	/*
-	 * With ARCH_SET_FS (and ARCH_SET_GS is treated similarly to
-	 * be safe), we need to call arch_prctl on the host because
-	 * setting %fs may result in something else happening (like a
-	 * GDT or thread.fs being set instead).  So, we let the host
-	 * fiddle the registers and thread struct and restore the
-	 * registers afterwards.
-	 *
-	 * So, the saved registers are stored to the process (this
-	 * needed because a stub may have been the last thing to run),
-	 * arch_prctl is run on the host, then the registers are read
-	 * back.
-	 */
-	switch (option) {
-	case ARCH_SET_FS:
-	case ARCH_SET_GS:
-		ret = restore_pid_registers(pid, &current->thread.regs.regs);
-		if (ret)
-			return ret;
-		break;
-	case ARCH_GET_FS:
-	case ARCH_GET_GS:
-		/*
-		 * With these two, we read to a local pointer and
-		 * put_user it to the userspace pointer that we were
-		 * given.  If addr isn't valid (because it hasn't been
-		 * faulted in or is just bogus), we want put_user to
-		 * fault it in (or return -EFAULT) instead of having
-		 * the host return -EFAULT.
-		 */
-		ptr = &tmp;
-	}
-
-	ret = os_arch_prctl(pid, option, ptr);
-	if (ret)
-		return ret;
+	long ret = -EINVAL;
 
 	switch (option) {
 	case ARCH_SET_FS:
-		current->thread.arch.fs = (unsigned long) ptr;
-		ret = save_registers(pid, &current->thread.regs.regs);
+		current->thread.regs.regs.gp[FS_BASE / sizeof(unsigned long)] =
+			(unsigned long) arg2;
+		ret = 0;
 		break;
 	case ARCH_SET_GS:
-		ret = save_registers(pid, &current->thread.regs.regs);
+		current->thread.regs.regs.gp[GS_BASE / sizeof(unsigned long)] =
+			(unsigned long) arg2;
+		ret = 0;
 		break;
 	case ARCH_GET_FS:
-		ret = put_user(tmp, arg2);
+		ret = put_user(current->thread.regs.regs.gp[FS_BASE / sizeof(unsigned long)], arg2);
 		break;
 	case ARCH_GET_GS:
-		ret = put_user(tmp, arg2);
+		ret = put_user(current->thread.regs.regs.gp[GS_BASE / sizeof(unsigned long)], arg2);
 		break;
 	}
 
@@ -83,10 +47,10 @@ SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
 
 void arch_switch_to(struct task_struct *to)
 {
-	if ((to->thread.arch.fs == 0) || (to->mm == NULL))
-		return;
-
-	arch_prctl(to, ARCH_SET_FS, (void __user *) to->thread.arch.fs);
+	/*
+	 * Nothing needs to be done on x86_64.
+	 * The FS_BASE/GS_BASE registers are saved in the ptrace register set.
+	 */
 }
 
 SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
diff --git a/arch/x86/um/tls_64.c b/arch/x86/um/tls_64.c
index ebd3855d9b13..c51a613f6f5c 100644
--- a/arch/x86/um/tls_64.c
+++ b/arch/x86/um/tls_64.c
@@ -12,7 +12,7 @@ int arch_set_tls(struct task_struct *t, unsigned long tls)
 	 * If CLONE_SETTLS is set, we need to save the thread id
 	 * so it can be set during context switches.
 	 */
-	t->thread.arch.fs = tls;
+	t->thread.regs.regs.gp[FS_BASE / sizeof(unsigned long)] = tls;
 
 	return 0;
 }
diff --git a/arch/x86/virt/vmx/tdx/Makefile b/arch/x86/virt/vmx/tdx/Makefile
index 46ef8f73aebb..90da47eb85ee 100644
--- a/arch/x86/virt/vmx/tdx/Makefile
+++ b/arch/x86/virt/vmx/tdx/Makefile
@@ -1,2 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-y += seamcall.o
+obj-y += seamcall.o tdx.o
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
new file mode 100644
index 000000000000..4d6826a76f78
--- /dev/null
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -0,0 +1,1492 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright(c) 2023 Intel Corporation.
+ *
+ * Intel Trusted Domain Extensions (TDX) support
+ */
+
+#define pr_fmt(fmt)	"virt/tdx: " fmt
+
+#include <linux/types.h>
+#include <linux/cache.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/printk.h>
+#include <linux/cpu.h>
+#include <linux/spinlock.h>
+#include <linux/percpu-defs.h>
+#include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/memblock.h>
+#include <linux/memory.h>
+#include <linux/minmax.h>
+#include <linux/sizes.h>
+#include <linux/pfn.h>
+#include <linux/align.h>
+#include <linux/sort.h>
+#include <linux/log2.h>
+#include <linux/acpi.h>
+#include <linux/suspend.h>
+#include <linux/acpi.h>
+#include <asm/page.h>
+#include <asm/special_insns.h>
+#include <asm/msr-index.h>
+#include <asm/msr.h>
+#include <asm/cpufeature.h>
+#include <asm/tdx.h>
+#include <asm/intel-family.h>
+#include <asm/processor.h>
+#include <asm/mce.h>
+#include "tdx.h"
+
+static u32 tdx_global_keyid __ro_after_init;
+static u32 tdx_guest_keyid_start __ro_after_init;
+static u32 tdx_nr_guest_keyids __ro_after_init;
+
+static DEFINE_PER_CPU(bool, tdx_lp_initialized);
+
+static struct tdmr_info_list tdx_tdmr_list;
+
+static enum tdx_module_status_t tdx_module_status;
+static DEFINE_MUTEX(tdx_module_lock);
+
+/* All TDX-usable memory regions.  Protected by mem_hotplug_lock. */
+static LIST_HEAD(tdx_memlist);
+
+typedef void (*sc_err_func_t)(u64 fn, u64 err, struct tdx_module_args *args);
+
+static inline void seamcall_err(u64 fn, u64 err, struct tdx_module_args *args)
+{
+	pr_err("SEAMCALL (0x%016llx) failed: 0x%016llx\n", fn, err);
+}
+
+static inline void seamcall_err_ret(u64 fn, u64 err,
+				    struct tdx_module_args *args)
+{
+	seamcall_err(fn, err, args);
+	pr_err("RCX 0x%016llx RDX 0x%016llx R08 0x%016llx\n",
+			args->rcx, args->rdx, args->r8);
+	pr_err("R09 0x%016llx R10 0x%016llx R11 0x%016llx\n",
+			args->r9, args->r10, args->r11);
+}
+
+static inline int sc_retry_prerr(sc_func_t func, sc_err_func_t err_func,
+				 u64 fn, struct tdx_module_args *args)
+{
+	u64 sret = sc_retry(func, fn, args);
+
+	if (sret == TDX_SUCCESS)
+		return 0;
+
+	if (sret == TDX_SEAMCALL_VMFAILINVALID)
+		return -ENODEV;
+
+	if (sret == TDX_SEAMCALL_GP)
+		return -EOPNOTSUPP;
+
+	if (sret == TDX_SEAMCALL_UD)
+		return -EACCES;
+
+	err_func(fn, sret, args);
+	return -EIO;
+}
+
+#define seamcall_prerr(__fn, __args)						\
+	sc_retry_prerr(__seamcall, seamcall_err, (__fn), (__args))
+
+#define seamcall_prerr_ret(__fn, __args)					\
+	sc_retry_prerr(__seamcall_ret, seamcall_err_ret, (__fn), (__args))
+
+/*
+ * Do the module global initialization once and return its result.
+ * It can be done on any cpu.  It's always called with interrupts
+ * disabled.
+ */
+static int try_init_module_global(void)
+{
+	struct tdx_module_args args = {};
+	static DEFINE_RAW_SPINLOCK(sysinit_lock);
+	static bool sysinit_done;
+	static int sysinit_ret;
+
+	lockdep_assert_irqs_disabled();
+
+	raw_spin_lock(&sysinit_lock);
+
+	if (sysinit_done)
+		goto out;
+
+	/* RCX is module attributes and all bits are reserved */
+	args.rcx = 0;
+	sysinit_ret = seamcall_prerr(TDH_SYS_INIT, &args);
+
+	/*
+	 * The first SEAMCALL also detects the TDX module, thus
+	 * it can fail due to the TDX module is not loaded.
+	 * Dump message to let the user know.
+	 */
+	if (sysinit_ret == -ENODEV)
+		pr_err("module not loaded\n");
+
+	sysinit_done = true;
+out:
+	raw_spin_unlock(&sysinit_lock);
+	return sysinit_ret;
+}
+
+/**
+ * tdx_cpu_enable - Enable TDX on local cpu
+ *
+ * Do one-time TDX module per-cpu initialization SEAMCALL (and TDX module
+ * global initialization SEAMCALL if not done) on local cpu to make this
+ * cpu be ready to run any other SEAMCALLs.
+ *
+ * Always call this function via IPI function calls.
+ *
+ * Return 0 on success, otherwise errors.
+ */
+int tdx_cpu_enable(void)
+{
+	struct tdx_module_args args = {};
+	int ret;
+
+	if (!boot_cpu_has(X86_FEATURE_TDX_HOST_PLATFORM))
+		return -ENODEV;
+
+	lockdep_assert_irqs_disabled();
+
+	if (__this_cpu_read(tdx_lp_initialized))
+		return 0;
+
+	/*
+	 * The TDX module global initialization is the very first step
+	 * to enable TDX.  Need to do it first (if hasn't been done)
+	 * before the per-cpu initialization.
+	 */
+	ret = try_init_module_global();
+	if (ret)
+		return ret;
+
+	ret = seamcall_prerr(TDH_SYS_LP_INIT, &args);
+	if (ret)
+		return ret;
+
+	__this_cpu_write(tdx_lp_initialized, true);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(tdx_cpu_enable);
+
+/*
+ * Add a memory region as a TDX memory block.  The caller must make sure
+ * all memory regions are added in address ascending order and don't
+ * overlap.
+ */
+static int add_tdx_memblock(struct list_head *tmb_list, unsigned long start_pfn,
+			    unsigned long end_pfn, int nid)
+{
+	struct tdx_memblock *tmb;
+
+	tmb = kmalloc(sizeof(*tmb), GFP_KERNEL);
+	if (!tmb)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&tmb->list);
+	tmb->start_pfn = start_pfn;
+	tmb->end_pfn = end_pfn;
+	tmb->nid = nid;
+
+	/* @tmb_list is protected by mem_hotplug_lock */
+	list_add_tail(&tmb->list, tmb_list);
+	return 0;
+}
+
+static void free_tdx_memlist(struct list_head *tmb_list)
+{
+	/* @tmb_list is protected by mem_hotplug_lock */
+	while (!list_empty(tmb_list)) {
+		struct tdx_memblock *tmb = list_first_entry(tmb_list,
+				struct tdx_memblock, list);
+
+		list_del(&tmb->list);
+		kfree(tmb);
+	}
+}
+
+/*
+ * Ensure that all memblock memory regions are convertible to TDX
+ * memory.  Once this has been established, stash the memblock
+ * ranges off in a secondary structure because memblock is modified
+ * in memory hotplug while TDX memory regions are fixed.
+ */
+static int build_tdx_memlist(struct list_head *tmb_list)
+{
+	unsigned long start_pfn, end_pfn;
+	int i, nid, ret;
+
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
+		/*
+		 * The first 1MB is not reported as TDX convertible memory.
+		 * Although the first 1MB is always reserved and won't end up
+		 * to the page allocator, it is still in memblock's memory
+		 * regions.  Skip them manually to exclude them as TDX memory.
+		 */
+		start_pfn = max(start_pfn, PHYS_PFN(SZ_1M));
+		if (start_pfn >= end_pfn)
+			continue;
+
+		/*
+		 * Add the memory regions as TDX memory.  The regions in
+		 * memblock has already guaranteed they are in address
+		 * ascending order and don't overlap.
+		 */
+		ret = add_tdx_memblock(tmb_list, start_pfn, end_pfn, nid);
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+err:
+	free_tdx_memlist(tmb_list);
+	return ret;
+}
+
+static int read_sys_metadata_field(u64 field_id, u64 *data)
+{
+	struct tdx_module_args args = {};
+	int ret;
+
+	/*
+	 * TDH.SYS.RD -- reads one global metadata field
+	 *  - RDX (in): the field to read
+	 *  - R8 (out): the field data
+	 */
+	args.rdx = field_id;
+	ret = seamcall_prerr_ret(TDH_SYS_RD, &args);
+	if (ret)
+		return ret;
+
+	*data = args.r8;
+
+	return 0;
+}
+
+static int read_sys_metadata_field16(u64 field_id,
+				     int offset,
+				     struct tdx_tdmr_sysinfo *ts)
+{
+	u16 *ts_member = ((void *)ts) + offset;
+	u64 tmp;
+	int ret;
+
+	if (WARN_ON_ONCE(MD_FIELD_ID_ELE_SIZE_CODE(field_id) !=
+			MD_FIELD_ID_ELE_SIZE_16BIT))
+		return -EINVAL;
+
+	ret = read_sys_metadata_field(field_id, &tmp);
+	if (ret)
+		return ret;
+
+	*ts_member = tmp;
+
+	return 0;
+}
+
+struct field_mapping {
+	u64 field_id;
+	int offset;
+};
+
+#define TD_SYSINFO_MAP(_field_id, _offset) \
+	{ .field_id = MD_FIELD_ID_##_field_id,	   \
+	  .offset   = offsetof(struct tdx_tdmr_sysinfo, _offset) }
+
+/* Map TD_SYSINFO fields into 'struct tdx_tdmr_sysinfo': */
+static const struct field_mapping fields[] = {
+	TD_SYSINFO_MAP(MAX_TDMRS,	      max_tdmrs),
+	TD_SYSINFO_MAP(MAX_RESERVED_PER_TDMR, max_reserved_per_tdmr),
+	TD_SYSINFO_MAP(PAMT_4K_ENTRY_SIZE,    pamt_entry_size[TDX_PS_4K]),
+	TD_SYSINFO_MAP(PAMT_2M_ENTRY_SIZE,    pamt_entry_size[TDX_PS_2M]),
+	TD_SYSINFO_MAP(PAMT_1G_ENTRY_SIZE,    pamt_entry_size[TDX_PS_1G]),
+};
+
+static int get_tdx_tdmr_sysinfo(struct tdx_tdmr_sysinfo *tdmr_sysinfo)
+{
+	int ret;
+	int i;
+
+	/* Populate 'tdmr_sysinfo' fields using the mapping structure above: */
+	for (i = 0; i < ARRAY_SIZE(fields); i++) {
+		ret = read_sys_metadata_field16(fields[i].field_id,
+						fields[i].offset,
+						tdmr_sysinfo);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/* Calculate the actual TDMR size */
+static int tdmr_size_single(u16 max_reserved_per_tdmr)
+{
+	int tdmr_sz;
+
+	/*
+	 * The actual size of TDMR depends on the maximum
+	 * number of reserved areas.
+	 */
+	tdmr_sz = sizeof(struct tdmr_info);
+	tdmr_sz += sizeof(struct tdmr_reserved_area) * max_reserved_per_tdmr;
+
+	return ALIGN(tdmr_sz, TDMR_INFO_ALIGNMENT);
+}
+
+static int alloc_tdmr_list(struct tdmr_info_list *tdmr_list,
+			   struct tdx_tdmr_sysinfo *tdmr_sysinfo)
+{
+	size_t tdmr_sz, tdmr_array_sz;
+	void *tdmr_array;
+
+	tdmr_sz = tdmr_size_single(tdmr_sysinfo->max_reserved_per_tdmr);
+	tdmr_array_sz = tdmr_sz * tdmr_sysinfo->max_tdmrs;
+
+	/*
+	 * To keep things simple, allocate all TDMRs together.
+	 * The buffer needs to be physically contiguous to make
+	 * sure each TDMR is physically contiguous.
+	 */
+	tdmr_array = alloc_pages_exact(tdmr_array_sz,
+			GFP_KERNEL | __GFP_ZERO);
+	if (!tdmr_array)
+		return -ENOMEM;
+
+	tdmr_list->tdmrs = tdmr_array;
+
+	/*
+	 * Keep the size of TDMR to find the target TDMR
+	 * at a given index in the TDMR list.
+	 */
+	tdmr_list->tdmr_sz = tdmr_sz;
+	tdmr_list->max_tdmrs = tdmr_sysinfo->max_tdmrs;
+	tdmr_list->nr_consumed_tdmrs = 0;
+
+	return 0;
+}
+
+static void free_tdmr_list(struct tdmr_info_list *tdmr_list)
+{
+	free_pages_exact(tdmr_list->tdmrs,
+			tdmr_list->max_tdmrs * tdmr_list->tdmr_sz);
+}
+
+/* Get the TDMR from the list at the given index. */
+static struct tdmr_info *tdmr_entry(struct tdmr_info_list *tdmr_list,
+				    int idx)
+{
+	int tdmr_info_offset = tdmr_list->tdmr_sz * idx;
+
+	return (void *)tdmr_list->tdmrs + tdmr_info_offset;
+}
+
+#define TDMR_ALIGNMENT		SZ_1G
+#define TDMR_ALIGN_DOWN(_addr)	ALIGN_DOWN((_addr), TDMR_ALIGNMENT)
+#define TDMR_ALIGN_UP(_addr)	ALIGN((_addr), TDMR_ALIGNMENT)
+
+static inline u64 tdmr_end(struct tdmr_info *tdmr)
+{
+	return tdmr->base + tdmr->size;
+}
+
+/*
+ * Take the memory referenced in @tmb_list and populate the
+ * preallocated @tdmr_list, following all the special alignment
+ * and size rules for TDMR.
+ */
+static int fill_out_tdmrs(struct list_head *tmb_list,
+			  struct tdmr_info_list *tdmr_list)
+{
+	struct tdx_memblock *tmb;
+	int tdmr_idx = 0;
+
+	/*
+	 * Loop over TDX memory regions and fill out TDMRs to cover them.
+	 * To keep it simple, always try to use one TDMR to cover one
+	 * memory region.
+	 *
+	 * In practice TDX supports at least 64 TDMRs.  A 2-socket system
+	 * typically only consumes less than 10 of those.  This code is
+	 * dumb and simple and may use more TMDRs than is strictly
+	 * required.
+	 */
+	list_for_each_entry(tmb, tmb_list, list) {
+		struct tdmr_info *tdmr = tdmr_entry(tdmr_list, tdmr_idx);
+		u64 start, end;
+
+		start = TDMR_ALIGN_DOWN(PFN_PHYS(tmb->start_pfn));
+		end   = TDMR_ALIGN_UP(PFN_PHYS(tmb->end_pfn));
+
+		/*
+		 * A valid size indicates the current TDMR has already
+		 * been filled out to cover the previous memory region(s).
+		 */
+		if (tdmr->size) {
+			/*
+			 * Loop to the next if the current memory region
+			 * has already been fully covered.
+			 */
+			if (end <= tdmr_end(tdmr))
+				continue;
+
+			/* Otherwise, skip the already covered part. */
+			if (start < tdmr_end(tdmr))
+				start = tdmr_end(tdmr);
+
+			/*
+			 * Create a new TDMR to cover the current memory
+			 * region, or the remaining part of it.
+			 */
+			tdmr_idx++;
+			if (tdmr_idx >= tdmr_list->max_tdmrs) {
+				pr_warn("initialization failed: TDMRs exhausted.\n");
+				return -ENOSPC;
+			}
+
+			tdmr = tdmr_entry(tdmr_list, tdmr_idx);
+		}
+
+		tdmr->base = start;
+		tdmr->size = end - start;
+	}
+
+	/* @tdmr_idx is always the index of the last valid TDMR. */
+	tdmr_list->nr_consumed_tdmrs = tdmr_idx + 1;
+
+	/*
+	 * Warn early that kernel is about to run out of TDMRs.
+	 *
+	 * This is an indication that TDMR allocation has to be
+	 * reworked to be smarter to not run into an issue.
+	 */
+	if (tdmr_list->max_tdmrs - tdmr_list->nr_consumed_tdmrs < TDMR_NR_WARN)
+		pr_warn("consumed TDMRs reaching limit: %d used out of %d\n",
+				tdmr_list->nr_consumed_tdmrs,
+				tdmr_list->max_tdmrs);
+
+	return 0;
+}
+
+/*
+ * Calculate PAMT size given a TDMR and a page size.  The returned
+ * PAMT size is always aligned up to 4K page boundary.
+ */
+static unsigned long tdmr_get_pamt_sz(struct tdmr_info *tdmr, int pgsz,
+				      u16 pamt_entry_size)
+{
+	unsigned long pamt_sz, nr_pamt_entries;
+
+	switch (pgsz) {
+	case TDX_PS_4K:
+		nr_pamt_entries = tdmr->size >> PAGE_SHIFT;
+		break;
+	case TDX_PS_2M:
+		nr_pamt_entries = tdmr->size >> PMD_SHIFT;
+		break;
+	case TDX_PS_1G:
+		nr_pamt_entries = tdmr->size >> PUD_SHIFT;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+
+	pamt_sz = nr_pamt_entries * pamt_entry_size;
+	/* TDX requires PAMT size must be 4K aligned */
+	pamt_sz = ALIGN(pamt_sz, PAGE_SIZE);
+
+	return pamt_sz;
+}
+
+/*
+ * Locate a NUMA node which should hold the allocation of the @tdmr
+ * PAMT.  This node will have some memory covered by the TDMR.  The
+ * relative amount of memory covered is not considered.
+ */
+static int tdmr_get_nid(struct tdmr_info *tdmr, struct list_head *tmb_list)
+{
+	struct tdx_memblock *tmb;
+
+	/*
+	 * A TDMR must cover at least part of one TMB.  That TMB will end
+	 * after the TDMR begins.  But, that TMB may have started before
+	 * the TDMR.  Find the next 'tmb' that _ends_ after this TDMR
+	 * begins.  Ignore 'tmb' start addresses.  They are irrelevant.
+	 */
+	list_for_each_entry(tmb, tmb_list, list) {
+		if (tmb->end_pfn > PHYS_PFN(tdmr->base))
+			return tmb->nid;
+	}
+
+	/*
+	 * Fall back to allocating the TDMR's metadata from node 0 when
+	 * no TDX memory block can be found.  This should never happen
+	 * since TDMRs originate from TDX memory blocks.
+	 */
+	pr_warn("TDMR [0x%llx, 0x%llx): unable to find local NUMA node for PAMT allocation, fallback to use node 0.\n",
+			tdmr->base, tdmr_end(tdmr));
+	return 0;
+}
+
+/*
+ * Allocate PAMTs from the local NUMA node of some memory in @tmb_list
+ * within @tdmr, and set up PAMTs for @tdmr.
+ */
+static int tdmr_set_up_pamt(struct tdmr_info *tdmr,
+			    struct list_head *tmb_list,
+			    u16 pamt_entry_size[])
+{
+	unsigned long pamt_base[TDX_PS_NR];
+	unsigned long pamt_size[TDX_PS_NR];
+	unsigned long tdmr_pamt_base;
+	unsigned long tdmr_pamt_size;
+	struct page *pamt;
+	int pgsz, nid;
+
+	nid = tdmr_get_nid(tdmr, tmb_list);
+
+	/*
+	 * Calculate the PAMT size for each TDX supported page size
+	 * and the total PAMT size.
+	 */
+	tdmr_pamt_size = 0;
+	for (pgsz = TDX_PS_4K; pgsz < TDX_PS_NR; pgsz++) {
+		pamt_size[pgsz] = tdmr_get_pamt_sz(tdmr, pgsz,
+					pamt_entry_size[pgsz]);
+		tdmr_pamt_size += pamt_size[pgsz];
+	}
+
+	/*
+	 * Allocate one chunk of physically contiguous memory for all
+	 * PAMTs.  This helps minimize the PAMT's use of reserved areas
+	 * in overlapped TDMRs.
+	 */
+	pamt = alloc_contig_pages(tdmr_pamt_size >> PAGE_SHIFT, GFP_KERNEL,
+			nid, &node_online_map);
+	if (!pamt)
+		return -ENOMEM;
+
+	/*
+	 * Break the contiguous allocation back up into the
+	 * individual PAMTs for each page size.
+	 */
+	tdmr_pamt_base = page_to_pfn(pamt) << PAGE_SHIFT;
+	for (pgsz = TDX_PS_4K; pgsz < TDX_PS_NR; pgsz++) {
+		pamt_base[pgsz] = tdmr_pamt_base;
+		tdmr_pamt_base += pamt_size[pgsz];
+	}
+
+	tdmr->pamt_4k_base = pamt_base[TDX_PS_4K];
+	tdmr->pamt_4k_size = pamt_size[TDX_PS_4K];
+	tdmr->pamt_2m_base = pamt_base[TDX_PS_2M];
+	tdmr->pamt_2m_size = pamt_size[TDX_PS_2M];
+	tdmr->pamt_1g_base = pamt_base[TDX_PS_1G];
+	tdmr->pamt_1g_size = pamt_size[TDX_PS_1G];
+
+	return 0;
+}
+
+static void tdmr_get_pamt(struct tdmr_info *tdmr, unsigned long *pamt_base,
+			  unsigned long *pamt_size)
+{
+	unsigned long pamt_bs, pamt_sz;
+
+	/*
+	 * The PAMT was allocated in one contiguous unit.  The 4K PAMT
+	 * should always point to the beginning of that allocation.
+	 */
+	pamt_bs = tdmr->pamt_4k_base;
+	pamt_sz = tdmr->pamt_4k_size + tdmr->pamt_2m_size + tdmr->pamt_1g_size;
+
+	WARN_ON_ONCE((pamt_bs & ~PAGE_MASK) || (pamt_sz & ~PAGE_MASK));
+
+	*pamt_base = pamt_bs;
+	*pamt_size = pamt_sz;
+}
+
+static void tdmr_do_pamt_func(struct tdmr_info *tdmr,
+		void (*pamt_func)(unsigned long base, unsigned long size))
+{
+	unsigned long pamt_base, pamt_size;
+
+	tdmr_get_pamt(tdmr, &pamt_base, &pamt_size);
+
+	/* Do nothing if PAMT hasn't been allocated for this TDMR */
+	if (!pamt_size)
+		return;
+
+	if (WARN_ON_ONCE(!pamt_base))
+		return;
+
+	pamt_func(pamt_base, pamt_size);
+}
+
+static void free_pamt(unsigned long pamt_base, unsigned long pamt_size)
+{
+	free_contig_range(pamt_base >> PAGE_SHIFT, pamt_size >> PAGE_SHIFT);
+}
+
+static void tdmr_free_pamt(struct tdmr_info *tdmr)
+{
+	tdmr_do_pamt_func(tdmr, free_pamt);
+}
+
+static void tdmrs_free_pamt_all(struct tdmr_info_list *tdmr_list)
+{
+	int i;
+
+	for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++)
+		tdmr_free_pamt(tdmr_entry(tdmr_list, i));
+}
+
+/* Allocate and set up PAMTs for all TDMRs */
+static int tdmrs_set_up_pamt_all(struct tdmr_info_list *tdmr_list,
+				 struct list_head *tmb_list,
+				 u16 pamt_entry_size[])
+{
+	int i, ret = 0;
+
+	for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) {
+		ret = tdmr_set_up_pamt(tdmr_entry(tdmr_list, i), tmb_list,
+				pamt_entry_size);
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+err:
+	tdmrs_free_pamt_all(tdmr_list);
+	return ret;
+}
+
+/*
+ * Convert TDX private pages back to normal by using MOVDIR64B to
+ * clear these pages.  Note this function doesn't flush cache of
+ * these TDX private pages.  The caller should make sure of that.
+ */
+static void reset_tdx_pages(unsigned long base, unsigned long size)
+{
+	const void *zero_page = (const void *)page_address(ZERO_PAGE(0));
+	unsigned long phys, end;
+
+	end = base + size;
+	for (phys = base; phys < end; phys += 64)
+		movdir64b(__va(phys), zero_page);
+
+	/*
+	 * MOVDIR64B uses WC protocol.  Use memory barrier to
+	 * make sure any later user of these pages sees the
+	 * updated data.
+	 */
+	mb();
+}
+
+static void tdmr_reset_pamt(struct tdmr_info *tdmr)
+{
+	tdmr_do_pamt_func(tdmr, reset_tdx_pages);
+}
+
+static void tdmrs_reset_pamt_all(struct tdmr_info_list *tdmr_list)
+{
+	int i;
+
+	for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++)
+		tdmr_reset_pamt(tdmr_entry(tdmr_list, i));
+}
+
+static unsigned long tdmrs_count_pamt_kb(struct tdmr_info_list *tdmr_list)
+{
+	unsigned long pamt_size = 0;
+	int i;
+
+	for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) {
+		unsigned long base, size;
+
+		tdmr_get_pamt(tdmr_entry(tdmr_list, i), &base, &size);
+		pamt_size += size;
+	}
+
+	return pamt_size / 1024;
+}
+
+static int tdmr_add_rsvd_area(struct tdmr_info *tdmr, int *p_idx, u64 addr,
+			      u64 size, u16 max_reserved_per_tdmr)
+{
+	struct tdmr_reserved_area *rsvd_areas = tdmr->reserved_areas;
+	int idx = *p_idx;
+
+	/* Reserved area must be 4K aligned in offset and size */
+	if (WARN_ON(addr & ~PAGE_MASK || size & ~PAGE_MASK))
+		return -EINVAL;
+
+	if (idx >= max_reserved_per_tdmr) {
+		pr_warn("initialization failed: TDMR [0x%llx, 0x%llx): reserved areas exhausted.\n",
+				tdmr->base, tdmr_end(tdmr));
+		return -ENOSPC;
+	}
+
+	/*
+	 * Consume one reserved area per call.  Make no effort to
+	 * optimize or reduce the number of reserved areas which are
+	 * consumed by contiguous reserved areas, for instance.
+	 */
+	rsvd_areas[idx].offset = addr - tdmr->base;
+	rsvd_areas[idx].size = size;
+
+	*p_idx = idx + 1;
+
+	return 0;
+}
+
+/*
+ * Go through @tmb_list to find holes between memory areas.  If any of
+ * those holes fall within @tdmr, set up a TDMR reserved area to cover
+ * the hole.
+ */
+static int tdmr_populate_rsvd_holes(struct list_head *tmb_list,
+				    struct tdmr_info *tdmr,
+				    int *rsvd_idx,
+				    u16 max_reserved_per_tdmr)
+{
+	struct tdx_memblock *tmb;
+	u64 prev_end;
+	int ret;
+
+	/*
+	 * Start looking for reserved blocks at the
+	 * beginning of the TDMR.
+	 */
+	prev_end = tdmr->base;
+	list_for_each_entry(tmb, tmb_list, list) {
+		u64 start, end;
+
+		start = PFN_PHYS(tmb->start_pfn);
+		end   = PFN_PHYS(tmb->end_pfn);
+
+		/* Break if this region is after the TDMR */
+		if (start >= tdmr_end(tdmr))
+			break;
+
+		/* Exclude regions before this TDMR */
+		if (end < tdmr->base)
+			continue;
+
+		/*
+		 * Skip over memory areas that
+		 * have already been dealt with.
+		 */
+		if (start <= prev_end) {
+			prev_end = end;
+			continue;
+		}
+
+		/* Add the hole before this region */
+		ret = tdmr_add_rsvd_area(tdmr, rsvd_idx, prev_end,
+				start - prev_end,
+				max_reserved_per_tdmr);
+		if (ret)
+			return ret;
+
+		prev_end = end;
+	}
+
+	/* Add the hole after the last region if it exists. */
+	if (prev_end < tdmr_end(tdmr)) {
+		ret = tdmr_add_rsvd_area(tdmr, rsvd_idx, prev_end,
+				tdmr_end(tdmr) - prev_end,
+				max_reserved_per_tdmr);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * Go through @tdmr_list to find all PAMTs.  If any of those PAMTs
+ * overlaps with @tdmr, set up a TDMR reserved area to cover the
+ * overlapping part.
+ */
+static int tdmr_populate_rsvd_pamts(struct tdmr_info_list *tdmr_list,
+				    struct tdmr_info *tdmr,
+				    int *rsvd_idx,
+				    u16 max_reserved_per_tdmr)
+{
+	int i, ret;
+
+	for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) {
+		struct tdmr_info *tmp = tdmr_entry(tdmr_list, i);
+		unsigned long pamt_base, pamt_size, pamt_end;
+
+		tdmr_get_pamt(tmp, &pamt_base, &pamt_size);
+		/* Each TDMR must already have PAMT allocated */
+		WARN_ON_ONCE(!pamt_size || !pamt_base);
+
+		pamt_end = pamt_base + pamt_size;
+		/* Skip PAMTs outside of the given TDMR */
+		if ((pamt_end <= tdmr->base) ||
+				(pamt_base >= tdmr_end(tdmr)))
+			continue;
+
+		/* Only mark the part within the TDMR as reserved */
+		if (pamt_base < tdmr->base)
+			pamt_base = tdmr->base;
+		if (pamt_end > tdmr_end(tdmr))
+			pamt_end = tdmr_end(tdmr);
+
+		ret = tdmr_add_rsvd_area(tdmr, rsvd_idx, pamt_base,
+				pamt_end - pamt_base,
+				max_reserved_per_tdmr);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/* Compare function called by sort() for TDMR reserved areas */
+static int rsvd_area_cmp_func(const void *a, const void *b)
+{
+	struct tdmr_reserved_area *r1 = (struct tdmr_reserved_area *)a;
+	struct tdmr_reserved_area *r2 = (struct tdmr_reserved_area *)b;
+
+	if (r1->offset + r1->size <= r2->offset)
+		return -1;
+	if (r1->offset >= r2->offset + r2->size)
+		return 1;
+
+	/* Reserved areas cannot overlap.  The caller must guarantee. */
+	WARN_ON_ONCE(1);
+	return -1;
+}
+
+/*
+ * Populate reserved areas for the given @tdmr, including memory holes
+ * (via @tmb_list) and PAMTs (via @tdmr_list).
+ */
+static int tdmr_populate_rsvd_areas(struct tdmr_info *tdmr,
+				    struct list_head *tmb_list,
+				    struct tdmr_info_list *tdmr_list,
+				    u16 max_reserved_per_tdmr)
+{
+	int ret, rsvd_idx = 0;
+
+	ret = tdmr_populate_rsvd_holes(tmb_list, tdmr, &rsvd_idx,
+			max_reserved_per_tdmr);
+	if (ret)
+		return ret;
+
+	ret = tdmr_populate_rsvd_pamts(tdmr_list, tdmr, &rsvd_idx,
+			max_reserved_per_tdmr);
+	if (ret)
+		return ret;
+
+	/* TDX requires reserved areas listed in address ascending order */
+	sort(tdmr->reserved_areas, rsvd_idx, sizeof(struct tdmr_reserved_area),
+			rsvd_area_cmp_func, NULL);
+
+	return 0;
+}
+
+/*
+ * Populate reserved areas for all TDMRs in @tdmr_list, including memory
+ * holes (via @tmb_list) and PAMTs.
+ */
+static int tdmrs_populate_rsvd_areas_all(struct tdmr_info_list *tdmr_list,
+					 struct list_head *tmb_list,
+					 u16 max_reserved_per_tdmr)
+{
+	int i;
+
+	for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) {
+		int ret;
+
+		ret = tdmr_populate_rsvd_areas(tdmr_entry(tdmr_list, i),
+				tmb_list, tdmr_list, max_reserved_per_tdmr);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * Construct a list of TDMRs on the preallocated space in @tdmr_list
+ * to cover all TDX memory regions in @tmb_list based on the TDX module
+ * TDMR global information in @tdmr_sysinfo.
+ */
+static int construct_tdmrs(struct list_head *tmb_list,
+			   struct tdmr_info_list *tdmr_list,
+			   struct tdx_tdmr_sysinfo *tdmr_sysinfo)
+{
+	int ret;
+
+	ret = fill_out_tdmrs(tmb_list, tdmr_list);
+	if (ret)
+		return ret;
+
+	ret = tdmrs_set_up_pamt_all(tdmr_list, tmb_list,
+			tdmr_sysinfo->pamt_entry_size);
+	if (ret)
+		return ret;
+
+	ret = tdmrs_populate_rsvd_areas_all(tdmr_list, tmb_list,
+			tdmr_sysinfo->max_reserved_per_tdmr);
+	if (ret)
+		tdmrs_free_pamt_all(tdmr_list);
+
+	/*
+	 * The tdmr_info_list is read-only from here on out.
+	 * Ensure that these writes are seen by other CPUs.
+	 * Pairs with a smp_rmb() in is_pamt_page().
+	 */
+	smp_wmb();
+
+	return ret;
+}
+
+static int config_tdx_module(struct tdmr_info_list *tdmr_list, u64 global_keyid)
+{
+	struct tdx_module_args args = {};
+	u64 *tdmr_pa_array;
+	size_t array_sz;
+	int i, ret;
+
+	/*
+	 * TDMRs are passed to the TDX module via an array of physical
+	 * addresses of each TDMR.  The array itself also has certain
+	 * alignment requirement.
+	 */
+	array_sz = tdmr_list->nr_consumed_tdmrs * sizeof(u64);
+	array_sz = roundup_pow_of_two(array_sz);
+	if (array_sz < TDMR_INFO_PA_ARRAY_ALIGNMENT)
+		array_sz = TDMR_INFO_PA_ARRAY_ALIGNMENT;
+
+	tdmr_pa_array = kzalloc(array_sz, GFP_KERNEL);
+	if (!tdmr_pa_array)
+		return -ENOMEM;
+
+	for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++)
+		tdmr_pa_array[i] = __pa(tdmr_entry(tdmr_list, i));
+
+	args.rcx = __pa(tdmr_pa_array);
+	args.rdx = tdmr_list->nr_consumed_tdmrs;
+	args.r8 = global_keyid;
+	ret = seamcall_prerr(TDH_SYS_CONFIG, &args);
+
+	/* Free the array as it is not required anymore. */
+	kfree(tdmr_pa_array);
+
+	return ret;
+}
+
+static int do_global_key_config(void *unused)
+{
+	struct tdx_module_args args = {};
+
+	return seamcall_prerr(TDH_SYS_KEY_CONFIG, &args);
+}
+
+/*
+ * Attempt to configure the global KeyID on all physical packages.
+ *
+ * This requires running code on at least one CPU in each package.
+ * TDMR initialization) will fail will fail if any package in the
+ * system has no online CPUs.
+ *
+ * This code takes no affirmative steps to online CPUs.  Callers (aka.
+ * KVM) can ensure success by ensuring sufficient CPUs are online and
+ * can run SEAMCALLs.
+ */
+static int config_global_keyid(void)
+{
+	cpumask_var_t packages;
+	int cpu, ret = -EINVAL;
+
+	if (!zalloc_cpumask_var(&packages, GFP_KERNEL))
+		return -ENOMEM;
+
+	/*
+	 * Hardware doesn't guarantee cache coherency across different
+	 * KeyIDs.  The kernel needs to flush PAMT's dirty cachelines
+	 * (associated with KeyID 0) before the TDX module can use the
+	 * global KeyID to access the PAMT.  Given PAMTs are potentially
+	 * large (~1/256th of system RAM), just use WBINVD.
+	 */
+	wbinvd_on_all_cpus();
+
+	for_each_online_cpu(cpu) {
+		/*
+		 * The key configuration only needs to be done once per
+		 * package and will return an error if configured more
+		 * than once.  Avoid doing it multiple times per package.
+		 */
+		if (cpumask_test_and_set_cpu(topology_physical_package_id(cpu),
+					packages))
+			continue;
+
+		/*
+		 * TDH.SYS.KEY.CONFIG cannot run concurrently on
+		 * different cpus.  Do it one by one.
+		 */
+		ret = smp_call_on_cpu(cpu, do_global_key_config, NULL, true);
+		if (ret)
+			break;
+	}
+
+	free_cpumask_var(packages);
+	return ret;
+}
+
+static int init_tdmr(struct tdmr_info *tdmr)
+{
+	u64 next;
+
+	/*
+	 * Initializing a TDMR can be time consuming.  To avoid long
+	 * SEAMCALLs, the TDX module may only initialize a part of the
+	 * TDMR in each call.
+	 */
+	do {
+		struct tdx_module_args args = {
+			.rcx = tdmr->base,
+		};
+		int ret;
+
+		ret = seamcall_prerr_ret(TDH_SYS_TDMR_INIT, &args);
+		if (ret)
+			return ret;
+		/*
+		 * RDX contains 'next-to-initialize' address if
+		 * TDH.SYS.TDMR.INIT did not fully complete and
+		 * should be retried.
+		 */
+		next = args.rdx;
+		cond_resched();
+		/* Keep making SEAMCALLs until the TDMR is done */
+	} while (next < tdmr->base + tdmr->size);
+
+	return 0;
+}
+
+static int init_tdmrs(struct tdmr_info_list *tdmr_list)
+{
+	int i;
+
+	/*
+	 * This operation is costly.  It can be parallelized,
+	 * but keep it simple for now.
+	 */
+	for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) {
+		int ret;
+
+		ret = init_tdmr(tdmr_entry(tdmr_list, i));
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int init_tdx_module(void)
+{
+	struct tdx_tdmr_sysinfo tdmr_sysinfo;
+	int ret;
+
+	/*
+	 * To keep things simple, assume that all TDX-protected memory
+	 * will come from the page allocator.  Make sure all pages in the
+	 * page allocator are TDX-usable memory.
+	 *
+	 * Build the list of "TDX-usable" memory regions which cover all
+	 * pages in the page allocator to guarantee that.  Do it while
+	 * holding mem_hotplug_lock read-lock as the memory hotplug code
+	 * path reads the @tdx_memlist to reject any new memory.
+	 */
+	get_online_mems();
+
+	ret = build_tdx_memlist(&tdx_memlist);
+	if (ret)
+		goto out_put_tdxmem;
+
+	ret = get_tdx_tdmr_sysinfo(&tdmr_sysinfo);
+	if (ret)
+		goto err_free_tdxmem;
+
+	/* Allocate enough space for constructing TDMRs */
+	ret = alloc_tdmr_list(&tdx_tdmr_list, &tdmr_sysinfo);
+	if (ret)
+		goto err_free_tdxmem;
+
+	/* Cover all TDX-usable memory regions in TDMRs */
+	ret = construct_tdmrs(&tdx_memlist, &tdx_tdmr_list, &tdmr_sysinfo);
+	if (ret)
+		goto err_free_tdmrs;
+
+	/* Pass the TDMRs and the global KeyID to the TDX module */
+	ret = config_tdx_module(&tdx_tdmr_list, tdx_global_keyid);
+	if (ret)
+		goto err_free_pamts;
+
+	/* Config the key of global KeyID on all packages */
+	ret = config_global_keyid();
+	if (ret)
+		goto err_reset_pamts;
+
+	/* Initialize TDMRs to complete the TDX module initialization */
+	ret = init_tdmrs(&tdx_tdmr_list);
+	if (ret)
+		goto err_reset_pamts;
+
+	pr_info("%lu KB allocated for PAMT\n", tdmrs_count_pamt_kb(&tdx_tdmr_list));
+
+out_put_tdxmem:
+	/*
+	 * @tdx_memlist is written here and read at memory hotplug time.
+	 * Lock out memory hotplug code while building it.
+	 */
+	put_online_mems();
+	return ret;
+
+err_reset_pamts:
+	/*
+	 * Part of PAMTs may already have been initialized by the
+	 * TDX module.  Flush cache before returning PAMTs back
+	 * to the kernel.
+	 */
+	wbinvd_on_all_cpus();
+	/*
+	 * According to the TDX hardware spec, if the platform
+	 * doesn't have the "partial write machine check"
+	 * erratum, any kernel read/write will never cause #MC
+	 * in kernel space, thus it's OK to not convert PAMTs
+	 * back to normal.  But do the conversion anyway here
+	 * as suggested by the TDX spec.
+	 */
+	tdmrs_reset_pamt_all(&tdx_tdmr_list);
+err_free_pamts:
+	tdmrs_free_pamt_all(&tdx_tdmr_list);
+err_free_tdmrs:
+	free_tdmr_list(&tdx_tdmr_list);
+err_free_tdxmem:
+	free_tdx_memlist(&tdx_memlist);
+	goto out_put_tdxmem;
+}
+
+static int __tdx_enable(void)
+{
+	int ret;
+
+	ret = init_tdx_module();
+	if (ret) {
+		pr_err("module initialization failed (%d)\n", ret);
+		tdx_module_status = TDX_MODULE_ERROR;
+		return ret;
+	}
+
+	pr_info("module initialized\n");
+	tdx_module_status = TDX_MODULE_INITIALIZED;
+
+	return 0;
+}
+
+/**
+ * tdx_enable - Enable TDX module to make it ready to run TDX guests
+ *
+ * This function assumes the caller has: 1) held read lock of CPU hotplug
+ * lock to prevent any new cpu from becoming online; 2) done both VMXON
+ * and tdx_cpu_enable() on all online cpus.
+ *
+ * This function requires there's at least one online cpu for each CPU
+ * package to succeed.
+ *
+ * This function can be called in parallel by multiple callers.
+ *
+ * Return 0 if TDX is enabled successfully, otherwise error.
+ */
+int tdx_enable(void)
+{
+	int ret;
+
+	if (!boot_cpu_has(X86_FEATURE_TDX_HOST_PLATFORM))
+		return -ENODEV;
+
+	lockdep_assert_cpus_held();
+
+	mutex_lock(&tdx_module_lock);
+
+	switch (tdx_module_status) {
+	case TDX_MODULE_UNINITIALIZED:
+		ret = __tdx_enable();
+		break;
+	case TDX_MODULE_INITIALIZED:
+		/* Already initialized, great, tell the caller. */
+		ret = 0;
+		break;
+	default:
+		/* Failed to initialize in the previous attempts */
+		ret = -EINVAL;
+		break;
+	}
+
+	mutex_unlock(&tdx_module_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(tdx_enable);
+
+static bool is_pamt_page(unsigned long phys)
+{
+	struct tdmr_info_list *tdmr_list = &tdx_tdmr_list;
+	int i;
+
+	/* Ensure that all remote 'tdmr_list' writes are visible: */
+	smp_rmb();
+
+	/*
+	 * The TDX module is no longer returning TDX_SYS_NOT_READY and
+	 * is initialized.  The 'tdmr_list' was initialized long ago
+	 * and is now read-only.
+	 */
+	for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) {
+		unsigned long base, size;
+
+		tdmr_get_pamt(tdmr_entry(tdmr_list, i), &base, &size);
+
+		if (phys >= base && phys < (base + size))
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * Return whether the memory page at the given physical address is TDX
+ * private memory or not.
+ *
+ * This can be imprecise for two known reasons:
+ * 1. PAMTs are private memory and exist before the TDX module is
+ *    ready and TDH_PHYMEM_PAGE_RDMD works.  This is a relatively
+ *    short window that occurs once per boot.
+ * 2. TDH_PHYMEM_PAGE_RDMD reflects the TDX module's knowledge of the
+ *    page.  However, the page can still cause #MC until it has been
+ *    fully converted to shared using 64-byte writes like MOVDIR64B.
+ *    Buggy hosts might still leave #MC-causing memory in place which
+ *    this function can not detect.
+ */
+static bool paddr_is_tdx_private(unsigned long phys)
+{
+	struct tdx_module_args args = {
+		.rcx = phys & PAGE_MASK,
+	};
+	u64 sret;
+
+	if (!boot_cpu_has(X86_FEATURE_TDX_HOST_PLATFORM))
+		return false;
+
+	/* Get page type from the TDX module */
+	sret = __seamcall_ret(TDH_PHYMEM_PAGE_RDMD, &args);
+
+	/*
+	 * The SEAMCALL will not return success unless there is a
+	 * working, "ready" TDX module.  Assume an absence of TDX
+	 * private pages until SEAMCALL is working.
+	 */
+	if (sret)
+		return false;
+
+	/*
+	 * SEAMCALL was successful -- read page type (via RCX):
+	 *
+	 *  - PT_NDA:	Page is not used by the TDX module
+	 *  - PT_RSVD:	Reserved for Non-TDX use
+	 *  - Others:	Page is used by the TDX module
+	 *
+	 * Note PAMT pages are marked as PT_RSVD but they are also TDX
+	 * private memory.
+	 */
+	switch (args.rcx) {
+	case PT_NDA:
+		return false;
+	case PT_RSVD:
+		return is_pamt_page(phys);
+	default:
+		return true;
+	}
+}
+
+/*
+ * Some TDX-capable CPUs have an erratum.  A write to TDX private
+ * memory poisons that memory, and a subsequent read of that memory
+ * triggers #MC.
+ *
+ * Help distinguish erratum-triggered #MCs from a normal hardware one.
+ * Just print additional message to show such #MC may be result of the
+ * erratum.
+ */
+const char *tdx_dump_mce_info(struct mce *m)
+{
+	if (!m || !mce_is_memory_error(m) || !mce_usable_address(m))
+		return NULL;
+
+	if (!paddr_is_tdx_private(m->addr))
+		return NULL;
+
+	return "TDX private memory error. Possible kernel bug.";
+}
+
+static __init int record_keyid_partitioning(u32 *tdx_keyid_start,
+					    u32 *nr_tdx_keyids)
+{
+	u32 _nr_mktme_keyids, _tdx_keyid_start, _nr_tdx_keyids;
+	int ret;
+
+	/*
+	 * IA32_MKTME_KEYID_PARTIONING:
+	 *   Bit [31:0]:	Number of MKTME KeyIDs.
+	 *   Bit [63:32]:	Number of TDX private KeyIDs.
+	 */
+	ret = rdmsr_safe(MSR_IA32_MKTME_KEYID_PARTITIONING, &_nr_mktme_keyids,
+			&_nr_tdx_keyids);
+	if (ret || !_nr_tdx_keyids)
+		return -EINVAL;
+
+	/* TDX KeyIDs start after the last MKTME KeyID. */
+	_tdx_keyid_start = _nr_mktme_keyids + 1;
+
+	*tdx_keyid_start = _tdx_keyid_start;
+	*nr_tdx_keyids = _nr_tdx_keyids;
+
+	return 0;
+}
+
+static bool is_tdx_memory(unsigned long start_pfn, unsigned long end_pfn)
+{
+	struct tdx_memblock *tmb;
+
+	/*
+	 * This check assumes that the start_pfn<->end_pfn range does not
+	 * cross multiple @tdx_memlist entries.  A single memory online
+	 * event across multiple memblocks (from which @tdx_memlist
+	 * entries are derived at the time of module initialization) is
+	 * not possible.  This is because memory offline/online is done
+	 * on granularity of 'struct memory_block', and the hotpluggable
+	 * memory region (one memblock) must be multiple of memory_block.
+	 */
+	list_for_each_entry(tmb, &tdx_memlist, list) {
+		if (start_pfn >= tmb->start_pfn && end_pfn <= tmb->end_pfn)
+			return true;
+	}
+	return false;
+}
+
+static int tdx_memory_notifier(struct notifier_block *nb, unsigned long action,
+			       void *v)
+{
+	struct memory_notify *mn = v;
+
+	if (action != MEM_GOING_ONLINE)
+		return NOTIFY_OK;
+
+	/*
+	 * Empty list means TDX isn't enabled.  Allow any memory
+	 * to go online.
+	 */
+	if (list_empty(&tdx_memlist))
+		return NOTIFY_OK;
+
+	/*
+	 * The TDX memory configuration is static and can not be
+	 * changed.  Reject onlining any memory which is outside of
+	 * the static configuration whether it supports TDX or not.
+	 */
+	if (is_tdx_memory(mn->start_pfn, mn->start_pfn + mn->nr_pages))
+		return NOTIFY_OK;
+
+	return NOTIFY_BAD;
+}
+
+static struct notifier_block tdx_memory_nb = {
+	.notifier_call = tdx_memory_notifier,
+};
+
+static void __init check_tdx_erratum(void)
+{
+	/*
+	 * These CPUs have an erratum.  A partial write from non-TD
+	 * software (e.g. via MOVNTI variants or UC/WC mapping) to TDX
+	 * private memory poisons that memory, and a subsequent read of
+	 * that memory triggers #MC.
+	 */
+	switch (boot_cpu_data.x86_model) {
+	case INTEL_FAM6_SAPPHIRERAPIDS_X:
+	case INTEL_FAM6_EMERALDRAPIDS_X:
+		setup_force_cpu_bug(X86_BUG_TDX_PW_MCE);
+	}
+}
+
+void __init tdx_init(void)
+{
+	u32 tdx_keyid_start, nr_tdx_keyids;
+	int err;
+
+	err = record_keyid_partitioning(&tdx_keyid_start, &nr_tdx_keyids);
+	if (err)
+		return;
+
+	pr_info("BIOS enabled: private KeyID range [%u, %u)\n",
+			tdx_keyid_start, tdx_keyid_start + nr_tdx_keyids);
+
+	/*
+	 * The TDX module itself requires one 'global KeyID' to protect
+	 * its metadata.  If there's only one TDX KeyID, there won't be
+	 * any left for TDX guests thus there's no point to enable TDX
+	 * at all.
+	 */
+	if (nr_tdx_keyids < 2) {
+		pr_err("initialization failed: too few private KeyIDs available.\n");
+		return;
+	}
+
+	/*
+	 * At this point, hibernation_available() indicates whether or
+	 * not hibernation support has been permanently disabled.
+	 */
+	if (hibernation_available()) {
+		pr_err("initialization failed: Hibernation support is enabled\n");
+		return;
+	}
+
+	err = register_memory_notifier(&tdx_memory_nb);
+	if (err) {
+		pr_err("initialization failed: register_memory_notifier() failed (%d)\n",
+				err);
+		return;
+	}
+
+#if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND)
+	pr_info("Disable ACPI S3. Turn off TDX in the BIOS to use ACPI S3.\n");
+	acpi_suspend_lowlevel = NULL;
+#endif
+
+	/*
+	 * Just use the first TDX KeyID as the 'global KeyID' and
+	 * leave the rest for TDX guests.
+	 */
+	tdx_global_keyid = tdx_keyid_start;
+	tdx_guest_keyid_start = tdx_keyid_start + 1;
+	tdx_nr_guest_keyids = nr_tdx_keyids - 1;
+
+	setup_force_cpu_cap(X86_FEATURE_TDX_HOST_PLATFORM);
+
+	check_tdx_erratum();
+}
diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h
new file mode 100644
index 000000000000..b701f69485d3
--- /dev/null
+++ b/arch/x86/virt/vmx/tdx/tdx.h
@@ -0,0 +1,121 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _X86_VIRT_TDX_H
+#define _X86_VIRT_TDX_H
+
+#include <linux/bits.h>
+
+/*
+ * This file contains both macros and data structures defined by the TDX
+ * architecture and Linux defined software data structures and functions.
+ * The two should not be mixed together for better readability.  The
+ * architectural definitions come first.
+ */
+
+/*
+ * TDX module SEAMCALL leaf functions
+ */
+#define TDH_PHYMEM_PAGE_RDMD	24
+#define TDH_SYS_KEY_CONFIG	31
+#define TDH_SYS_INIT		33
+#define TDH_SYS_RD		34
+#define TDH_SYS_LP_INIT		35
+#define TDH_SYS_TDMR_INIT	36
+#define TDH_SYS_CONFIG		45
+
+/* TDX page types */
+#define	PT_NDA		0x0
+#define	PT_RSVD		0x1
+
+/*
+ * Global scope metadata field ID.
+ *
+ * See Table "Global Scope Metadata", TDX module 1.5 ABI spec.
+ */
+#define MD_FIELD_ID_MAX_TDMRS			0x9100000100000008ULL
+#define MD_FIELD_ID_MAX_RESERVED_PER_TDMR	0x9100000100000009ULL
+#define MD_FIELD_ID_PAMT_4K_ENTRY_SIZE		0x9100000100000010ULL
+#define MD_FIELD_ID_PAMT_2M_ENTRY_SIZE		0x9100000100000011ULL
+#define MD_FIELD_ID_PAMT_1G_ENTRY_SIZE		0x9100000100000012ULL
+
+/*
+ * Sub-field definition of metadata field ID.
+ *
+ * See Table "MD_FIELD_ID (Metadata Field Identifier / Sequence Header)
+ * Definition", TDX module 1.5 ABI spec.
+ *
+ *  - Bit 33:32: ELEMENT_SIZE_CODE -- size of a single element of metadata
+ *
+ *	0: 8 bits
+ *	1: 16 bits
+ *	2: 32 bits
+ *	3: 64 bits
+ */
+#define MD_FIELD_ID_ELE_SIZE_CODE(_field_id)	\
+		(((_field_id) & GENMASK_ULL(33, 32)) >> 32)
+
+#define MD_FIELD_ID_ELE_SIZE_16BIT	1
+
+struct tdmr_reserved_area {
+	u64 offset;
+	u64 size;
+} __packed;
+
+#define TDMR_INFO_ALIGNMENT	512
+#define TDMR_INFO_PA_ARRAY_ALIGNMENT	512
+
+struct tdmr_info {
+	u64 base;
+	u64 size;
+	u64 pamt_1g_base;
+	u64 pamt_1g_size;
+	u64 pamt_2m_base;
+	u64 pamt_2m_size;
+	u64 pamt_4k_base;
+	u64 pamt_4k_size;
+	/*
+	 * The actual number of reserved areas depends on the value of
+	 * field MD_FIELD_ID_MAX_RESERVED_PER_TDMR in the TDX module
+	 * global metadata.
+	 */
+	DECLARE_FLEX_ARRAY(struct tdmr_reserved_area, reserved_areas);
+} __packed __aligned(TDMR_INFO_ALIGNMENT);
+
+/*
+ * Do not put any hardware-defined TDX structure representations below
+ * this comment!
+ */
+
+/* Kernel defined TDX module status during module initialization. */
+enum tdx_module_status_t {
+	TDX_MODULE_UNINITIALIZED,
+	TDX_MODULE_INITIALIZED,
+	TDX_MODULE_ERROR
+};
+
+struct tdx_memblock {
+	struct list_head list;
+	unsigned long start_pfn;
+	unsigned long end_pfn;
+	int nid;
+};
+
+/* "TDMR info" part of "Global Scope Metadata" for constructing TDMRs */
+struct tdx_tdmr_sysinfo {
+	u16 max_tdmrs;
+	u16 max_reserved_per_tdmr;
+	u16 pamt_entry_size[TDX_PS_NR];
+};
+
+/* Warn if kernel has less than TDMR_NR_WARN TDMRs after allocation */
+#define TDMR_NR_WARN 4
+
+struct tdmr_info_list {
+	void *tdmrs;	/* Flexible array to hold 'tdmr_info's */
+	int nr_consumed_tdmrs;	/* How many 'tdmr_info's are in use */
+
+	/* Metadata for finding target 'tdmr_info' and freeing @tdmrs */
+	int tdmr_sz;	/* Size of one 'tdmr_info' */
+	int max_tdmrs;	/* How many 'tdmr_info's are allocated */
+};
+
+#endif
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 4b0d6fff88de..1fb9a1644d94 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -65,6 +65,8 @@ int xen_smp_intr_init(unsigned int cpu)
 	char *resched_name, *callfunc_name, *debug_name;
 
 	resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu);
+	if (!resched_name)
+		goto fail_mem;
 	per_cpu(xen_resched_irq, cpu).name = resched_name;
 	rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR,
 				    cpu,
@@ -77,6 +79,8 @@ int xen_smp_intr_init(unsigned int cpu)
 	per_cpu(xen_resched_irq, cpu).irq = rc;
 
 	callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu);
+	if (!callfunc_name)
+		goto fail_mem;
 	per_cpu(xen_callfunc_irq, cpu).name = callfunc_name;
 	rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR,
 				    cpu,
@@ -90,6 +94,9 @@ int xen_smp_intr_init(unsigned int cpu)
 
 	if (!xen_fifo_events) {
 		debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu);
+		if (!debug_name)
+			goto fail_mem;
+
 		per_cpu(xen_debug_irq, cpu).name = debug_name;
 		rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu,
 					     xen_debug_interrupt,
@@ -101,6 +108,9 @@ int xen_smp_intr_init(unsigned int cpu)
 	}
 
 	callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu);
+	if (!callfunc_name)
+		goto fail_mem;
+
 	per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name;
 	rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR,
 				    cpu,
@@ -114,6 +124,8 @@ int xen_smp_intr_init(unsigned int cpu)
 
 	return 0;
 
+ fail_mem:
+	rc = -ENOMEM;
  fail:
 	xen_smp_intr_free(cpu);
 	return rc;
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index e031eaf36c99..6f248d87e496 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -144,7 +144,7 @@ config XTENSA_VARIANT_CUSTOM_NAME
 	depends on XTENSA_VARIANT_CUSTOM
 	help
 	  Provide the name of a custom Xtensa processor variant.
-	  This CORENAME selects arch/xtensa/variant/CORENAME.
+	  This CORENAME selects arch/xtensa/variants/CORENAME.
 	  Don't forget you have to select MMU if you have one.
 
 config XTENSA_VARIANT_NAME
diff --git a/arch/xtensa/Makefile b/arch/xtensa/Makefile
index bfd8e433ed62..4c14a02179eb 100644
--- a/arch/xtensa/Makefile
+++ b/arch/xtensa/Makefile
@@ -35,15 +35,19 @@ KBUILD_CFLAGS += -ffreestanding -D__linux__
 KBUILD_CFLAGS += -pipe -mlongcalls -mtext-section-literals
 KBUILD_CFLAGS += $(call cc-option,-mforce-no-pic,)
 KBUILD_CFLAGS += $(call cc-option,-mno-serialize-volatile,)
+KBUILD_CFLAGS += $(call cc-option,-mno-fdpic,)
 ifneq ($(CONFIG_KERNEL_ABI_CALL0),)
 KBUILD_CFLAGS += -mabi=call0
 KBUILD_AFLAGS += -mabi=call0
 endif
 
 KBUILD_AFLAGS += -mlongcalls -mtext-section-literals
+KBUILD_AFLAGS += $(call cc-option,-mno-fdpic,)
+
+KBUILD_LDFLAGS += -m elf32xtensa
 
 ifneq ($(CONFIG_LD_NO_RELAX),)
-KBUILD_LDFLAGS := --no-relax
+KBUILD_LDFLAGS += --no-relax
 endif
 
 CHECKFLAGS += -D$(if $(CONFIG_CPU_BIG_ENDIAN),__XTENSA_EB__,__XTENSA_EL__)
diff --git a/arch/xtensa/include/asm/asmmacro.h b/arch/xtensa/include/asm/asmmacro.h
index 01bf7d9dbb19..a52d49a16ce7 100644
--- a/arch/xtensa/include/asm/asmmacro.h
+++ b/arch/xtensa/include/asm/asmmacro.h
@@ -11,7 +11,7 @@
 #ifndef _XTENSA_ASMMACRO_H
 #define _XTENSA_ASMMACRO_H
 
-#include <asm-generic/export.h>
+#include <linux/export.h>
 #include <asm/core.h>
 
 /*
diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h
index 785a00ce83c1..38bcecb0e457 100644
--- a/arch/xtensa/include/asm/cacheflush.h
+++ b/arch/xtensa/include/asm/cacheflush.h
@@ -116,8 +116,9 @@ void flush_cache_page(struct vm_area_struct*,
 #define flush_cache_mm(mm)		flush_cache_all()
 #define flush_cache_dup_mm(mm)		flush_cache_mm(mm)
 
-#define flush_cache_vmap(start,end)	flush_cache_all()
-#define flush_cache_vunmap(start,end)	flush_cache_all()
+#define flush_cache_vmap(start,end)		flush_cache_all()
+#define flush_cache_vmap_early(start,end)	do { } while (0)
+#define flush_cache_vunmap(start,end)		flush_cache_all()
 
 void flush_dcache_folio(struct folio *folio);
 #define flush_dcache_folio flush_dcache_folio
@@ -140,6 +141,7 @@ void local_flush_cache_page(struct vm_area_struct *vma,
 #define flush_cache_dup_mm(mm)				do { } while (0)
 
 #define flush_cache_vmap(start,end)			do { } while (0)
+#define flush_cache_vmap_early(start,end)		do { } while (0)
 #define flush_cache_vunmap(start,end)			do { } while (0)
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
diff --git a/arch/xtensa/include/asm/jump_label.h b/arch/xtensa/include/asm/jump_label.h
index c812bf85021c..46c8596259d2 100644
--- a/arch/xtensa/include/asm/jump_label.h
+++ b/arch/xtensa/include/asm/jump_label.h
@@ -13,7 +13,7 @@
 static __always_inline bool arch_static_branch(struct static_key *key,
 					       bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 			  "_nop\n\t"
 			  ".pushsection __jump_table,  \"aw\"\n\t"
 			  ".word 1b, %l[l_yes], %c0\n\t"
@@ -38,7 +38,7 @@ static __always_inline bool arch_static_branch_jump(struct static_key *key,
 	 * make it reachable and wrap both into a no-transform block
 	 * to avoid any assembler interference with this.
 	 */
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 			  ".begin no-transform\n\t"
 			  "_j %l[l_yes]\n\t"
 			  "2:\n\t"
diff --git a/arch/xtensa/lib/pci-auto.c b/arch/xtensa/lib/pci-auto.c
index aa6752237985..05fc02f9e1c7 100644
--- a/arch/xtensa/lib/pci-auto.c
+++ b/arch/xtensa/lib/pci-auto.c
@@ -11,6 +11,7 @@
  * Based on work from Matt Porter <mporter@mvista.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/pci.h>
@@ -222,10 +223,11 @@ pciauto_postscan_setup_bridge(struct pci_dev *dev, int current_bus, int sub_bus,
 
 int __init pciauto_bus_scan(struct pci_controller *pci_ctrl, int current_bus)
 {
-	int sub_bus, pci_devfn, pci_class, cmdstat, found_multi=0;
+	int sub_bus, pci_devfn, pci_class, cmdstat;
 	unsigned short vid;
 	unsigned char header_type;
 	struct pci_dev *dev = &pciauto_dev;
+	bool found_multi = false;
 
 	pciauto_dev.bus = &pciauto_bus;
 	pciauto_dev.sysdata = pci_ctrl;
@@ -261,11 +263,11 @@ int __init pciauto_bus_scan(struct pci_controller *pci_ctrl, int current_bus)
 			continue;
 
 		if (!PCI_FUNC(pci_devfn))
-			found_multi = header_type & 0x80;
+			found_multi = FIELD_GET(PCI_HEADER_TYPE_MFD, header_type);
 		pci_read_config_word(dev, PCI_VENDOR_ID, &vid);
 
 		if (vid == 0xffff || vid == 0x0000) {
-			found_multi = 0;
+			found_multi = false;
 			continue;
 		}
 
diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c
index 7d1f8b398a46..8896e691c051 100644
--- a/arch/xtensa/platforms/iss/console.c
+++ b/arch/xtensa/platforms/iss/console.c
@@ -65,7 +65,7 @@ static void rs_poll(struct timer_list *unused)
 	struct tty_port *port = &serial_port;
 	int i = 0;
 	int rd = 1;
-	unsigned char c;
+	u8 c;
 
 	while (simc_poll(0)) {
 		rd = simc_read(0, &c, 1);
diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c
index 178cf96ca10a..defc67909a9c 100644
--- a/arch/xtensa/platforms/iss/simdisk.c
+++ b/arch/xtensa/platforms/iss/simdisk.c
@@ -264,16 +264,18 @@ static int __init simdisk_setup(struct simdisk *dev, int which,
 		struct proc_dir_entry *procdir)
 {
 	char tmp[2] = { '0' + which, 0 };
-	int err = -ENOMEM;
+	int err;
 
 	dev->fd = -1;
 	dev->filename = NULL;
 	spin_lock_init(&dev->lock);
 	dev->users = 0;
 
-	dev->gd = blk_alloc_disk(NUMA_NO_NODE);
-	if (!dev->gd)
+	dev->gd = blk_alloc_disk(NULL, NUMA_NO_NODE);
+	if (IS_ERR(dev->gd)) {
+		err = PTR_ERR(dev->gd);
 		goto out;
+	}
 	dev->gd->major = simdisk_major;
 	dev->gd->first_minor = which;
 	dev->gd->minors = SIMDISK_MINORS;
diff --git a/block/bdev.c b/block/bdev.c
index e9f1b12bd75c..e7adaaf1c219 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -49,6 +49,12 @@ struct block_device *I_BDEV(struct inode *inode)
 }
 EXPORT_SYMBOL(I_BDEV);
 
+struct block_device *file_bdev(struct file *bdev_file)
+{
+	return I_BDEV(bdev_file->f_mapping->host);
+}
+EXPORT_SYMBOL(file_bdev);
+
 static void bdev_write_inode(struct block_device *bdev)
 {
 	struct inode *inode = bdev->bd_inode;
@@ -368,24 +374,24 @@ static struct file_system_type bd_type = {
 };
 
 struct super_block *blockdev_superblock __ro_after_init;
+struct vfsmount *blockdev_mnt __ro_after_init;
 EXPORT_SYMBOL_GPL(blockdev_superblock);
 
 void __init bdev_cache_init(void)
 {
 	int err;
-	static struct vfsmount *bd_mnt __ro_after_init;
 
 	bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
 			0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
-				SLAB_MEM_SPREAD|SLAB_ACCOUNT|SLAB_PANIC),
+				SLAB_ACCOUNT|SLAB_PANIC),
 			init_once);
 	err = register_filesystem(&bd_type);
 	if (err)
 		panic("Cannot register bdev pseudo-fs");
-	bd_mnt = kern_mount(&bd_type);
-	if (IS_ERR(bd_mnt))
+	blockdev_mnt = kern_mount(&bd_type);
+	if (IS_ERR(blockdev_mnt))
 		panic("Cannot create bdev pseudo-fs");
-	blockdev_superblock = bd_mnt->mnt_sb;   /* For writeback */
+	blockdev_superblock = blockdev_mnt->mnt_sb;   /* For writeback */
 }
 
 struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
@@ -696,6 +702,31 @@ out_blkdev_put:
 	return ret;
 }
 
+int bdev_permission(dev_t dev, blk_mode_t mode, void *holder)
+{
+	int ret;
+
+	ret = devcgroup_check_permission(DEVCG_DEV_BLOCK,
+			MAJOR(dev), MINOR(dev),
+			((mode & BLK_OPEN_READ) ? DEVCG_ACC_READ : 0) |
+			((mode & BLK_OPEN_WRITE) ? DEVCG_ACC_WRITE : 0));
+	if (ret)
+		return ret;
+
+	/* Blocking writes requires exclusive opener */
+	if (mode & BLK_OPEN_RESTRICT_WRITES && !holder)
+		return -EINVAL;
+
+	/*
+	 * We're using error pointers to indicate to ->release() when we
+	 * failed to open that block device. Also this doesn't make sense.
+	 */
+	if (WARN_ON_ONCE(IS_ERR(holder)))
+		return -EINVAL;
+
+	return 0;
+}
+
 static void blkdev_put_part(struct block_device *part)
 {
 	struct block_device *whole = bdev_whole(part);
@@ -775,83 +806,55 @@ static void bdev_claim_write_access(struct block_device *bdev, blk_mode_t mode)
 		bdev->bd_writers++;
 }
 
-static void bdev_yield_write_access(struct block_device *bdev, blk_mode_t mode)
+static void bdev_yield_write_access(struct file *bdev_file)
 {
+	struct block_device *bdev;
+
 	if (bdev_allow_write_mounted)
 		return;
 
+	bdev = file_bdev(bdev_file);
 	/* Yield exclusive or shared write access. */
-	if (mode & BLK_OPEN_RESTRICT_WRITES)
-		bdev_unblock_writes(bdev);
-	else if (mode & BLK_OPEN_WRITE)
-		bdev->bd_writers--;
+	if (bdev_file->f_mode & FMODE_WRITE) {
+		if (bdev_writes_blocked(bdev))
+			bdev_unblock_writes(bdev);
+		else
+			bdev->bd_writers--;
+	}
 }
 
 /**
- * bdev_open_by_dev - open a block device by device number
- * @dev: device number of block device to open
+ * bdev_open - open a block device
+ * @bdev: block device to open
  * @mode: open mode (BLK_OPEN_*)
  * @holder: exclusive holder identifier
  * @hops: holder operations
+ * @bdev_file: file for the block device
  *
- * Open the block device described by device number @dev. If @holder is not
- * %NULL, the block device is opened with exclusive access.  Exclusive opens may
- * nest for the same @holder.
- *
- * Use this interface ONLY if you really do not have anything better - i.e. when
- * you are behind a truly sucky interface and all you are given is a device
- * number.  Everything else should use bdev_open_by_path().
+ * Open the block device. If @holder is not %NULL, the block device is opened
+ * with exclusive access.  Exclusive opens may nest for the same @holder.
  *
  * CONTEXT:
  * Might sleep.
  *
  * RETURNS:
- * Handle with a reference to the block_device on success, ERR_PTR(-errno) on
- * failure.
+ * zero on success, -errno on failure.
  */
-struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
-				     const struct blk_holder_ops *hops)
+int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder,
+	      const struct blk_holder_ops *hops, struct file *bdev_file)
 {
-	struct bdev_handle *handle = kmalloc(sizeof(struct bdev_handle),
-					     GFP_KERNEL);
-	struct block_device *bdev;
 	bool unblock_events = true;
-	struct gendisk *disk;
+	struct gendisk *disk = bdev->bd_disk;
 	int ret;
 
-	if (!handle)
-		return ERR_PTR(-ENOMEM);
-
-	ret = devcgroup_check_permission(DEVCG_DEV_BLOCK,
-			MAJOR(dev), MINOR(dev),
-			((mode & BLK_OPEN_READ) ? DEVCG_ACC_READ : 0) |
-			((mode & BLK_OPEN_WRITE) ? DEVCG_ACC_WRITE : 0));
-	if (ret)
-		goto free_handle;
-
-	/* Blocking writes requires exclusive opener */
-	if (mode & BLK_OPEN_RESTRICT_WRITES && !holder) {
-		ret = -EINVAL;
-		goto free_handle;
-	}
-
-	bdev = blkdev_get_no_open(dev);
-	if (!bdev) {
-		ret = -ENXIO;
-		goto free_handle;
-	}
-	disk = bdev->bd_disk;
-
 	if (holder) {
 		mode |= BLK_OPEN_EXCL;
 		ret = bd_prepare_to_claim(bdev, holder, hops);
 		if (ret)
-			goto put_blkdev;
+			return ret;
 	} else {
-		if (WARN_ON_ONCE(mode & BLK_OPEN_EXCL)) {
-			ret = -EIO;
-			goto put_blkdev;
-		}
+		if (WARN_ON_ONCE(mode & BLK_OPEN_EXCL))
+			return -EIO;
 	}
 
 	disk_block_events(disk);
@@ -892,10 +895,16 @@ struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
 
 	if (unblock_events)
 		disk_unblock_events(disk);
-	handle->bdev = bdev;
-	handle->holder = holder;
-	handle->mode = mode;
-	return handle;
+
+	bdev_file->f_flags |= O_LARGEFILE;
+	bdev_file->f_mode |= FMODE_BUF_RASYNC | FMODE_CAN_ODIRECT;
+	if (bdev_nowait(bdev))
+		bdev_file->f_mode |= FMODE_NOWAIT;
+	bdev_file->f_mapping = bdev->bd_inode->i_mapping;
+	bdev_file->f_wb_err = filemap_sample_wb_err(bdev_file->f_mapping);
+	bdev_file->private_data = holder;
+
+	return 0;
 put_module:
 	module_put(disk->fops->owner);
 abort_claiming:
@@ -903,36 +912,80 @@ abort_claiming:
 		bd_abort_claiming(bdev, holder);
 	mutex_unlock(&disk->open_mutex);
 	disk_unblock_events(disk);
-put_blkdev:
-	blkdev_put_no_open(bdev);
-free_handle:
-	kfree(handle);
-	return ERR_PTR(ret);
+	return ret;
 }
-EXPORT_SYMBOL(bdev_open_by_dev);
 
-/**
- * bdev_open_by_path - open a block device by name
- * @path: path to the block device to open
- * @mode: open mode (BLK_OPEN_*)
- * @holder: exclusive holder identifier
- * @hops: holder operations
- *
- * Open the block device described by the device file at @path.  If @holder is
- * not %NULL, the block device is opened with exclusive access.  Exclusive opens
- * may nest for the same @holder.
- *
- * CONTEXT:
- * Might sleep.
+/*
+ * If BLK_OPEN_WRITE_IOCTL is set then this is a historical quirk
+ * associated with the floppy driver where it has allowed ioctls if the
+ * file was opened for writing, but does not allow reads or writes.
+ * Make sure that this quirk is reflected in @f_flags.
  *
- * RETURNS:
- * Handle with a reference to the block_device on success, ERR_PTR(-errno) on
- * failure.
+ * It can also happen if a block device is opened as O_RDWR | O_WRONLY.
  */
-struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode,
-		void *holder, const struct blk_holder_ops *hops)
+static unsigned blk_to_file_flags(blk_mode_t mode)
+{
+	unsigned int flags = 0;
+
+	if ((mode & (BLK_OPEN_READ | BLK_OPEN_WRITE)) ==
+	    (BLK_OPEN_READ | BLK_OPEN_WRITE))
+		flags |= O_RDWR;
+	else if (mode & BLK_OPEN_WRITE_IOCTL)
+		flags |= O_RDWR | O_WRONLY;
+	else if (mode & BLK_OPEN_WRITE)
+		flags |= O_WRONLY;
+	else if (mode & BLK_OPEN_READ)
+		flags |= O_RDONLY; /* homeopathic, because O_RDONLY is 0 */
+	else
+		WARN_ON_ONCE(true);
+
+	if (mode & BLK_OPEN_NDELAY)
+		flags |= O_NDELAY;
+
+	return flags;
+}
+
+struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
+				   const struct blk_holder_ops *hops)
 {
-	struct bdev_handle *handle;
+	struct file *bdev_file;
+	struct block_device *bdev;
+	unsigned int flags;
+	int ret;
+
+	ret = bdev_permission(dev, mode, holder);
+	if (ret)
+		return ERR_PTR(ret);
+
+	bdev = blkdev_get_no_open(dev);
+	if (!bdev)
+		return ERR_PTR(-ENXIO);
+
+	flags = blk_to_file_flags(mode);
+	bdev_file = alloc_file_pseudo_noaccount(bdev->bd_inode,
+			blockdev_mnt, "", flags | O_LARGEFILE, &def_blk_fops);
+	if (IS_ERR(bdev_file)) {
+		blkdev_put_no_open(bdev);
+		return bdev_file;
+	}
+	ihold(bdev->bd_inode);
+
+	ret = bdev_open(bdev, mode, holder, hops, bdev_file);
+	if (ret) {
+		/* We failed to open the block device. Let ->release() know. */
+		bdev_file->private_data = ERR_PTR(ret);
+		fput(bdev_file);
+		return ERR_PTR(ret);
+	}
+	return bdev_file;
+}
+EXPORT_SYMBOL(bdev_file_open_by_dev);
+
+struct file *bdev_file_open_by_path(const char *path, blk_mode_t mode,
+				    void *holder,
+				    const struct blk_holder_ops *hops)
+{
+	struct file *file;
 	dev_t dev;
 	int error;
 
@@ -940,22 +993,28 @@ struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode,
 	if (error)
 		return ERR_PTR(error);
 
-	handle = bdev_open_by_dev(dev, mode, holder, hops);
-	if (!IS_ERR(handle) && (mode & BLK_OPEN_WRITE) &&
-	    bdev_read_only(handle->bdev)) {
-		bdev_release(handle);
-		return ERR_PTR(-EACCES);
+	file = bdev_file_open_by_dev(dev, mode, holder, hops);
+	if (!IS_ERR(file) && (mode & BLK_OPEN_WRITE)) {
+		if (bdev_read_only(file_bdev(file))) {
+			fput(file);
+			file = ERR_PTR(-EACCES);
+		}
 	}
 
-	return handle;
+	return file;
 }
-EXPORT_SYMBOL(bdev_open_by_path);
+EXPORT_SYMBOL(bdev_file_open_by_path);
 
-void bdev_release(struct bdev_handle *handle)
+void bdev_release(struct file *bdev_file)
 {
-	struct block_device *bdev = handle->bdev;
+	struct block_device *bdev = file_bdev(bdev_file);
+	void *holder = bdev_file->private_data;
 	struct gendisk *disk = bdev->bd_disk;
 
+	/* We failed to open that block device. */
+	if (IS_ERR(holder))
+		goto put_no_open;
+
 	/*
 	 * Sync early if it looks like we're the last one.  If someone else
 	 * opens the block device between now and the decrement of bd_openers
@@ -967,10 +1026,10 @@ void bdev_release(struct bdev_handle *handle)
 		sync_blockdev(bdev);
 
 	mutex_lock(&disk->open_mutex);
-	bdev_yield_write_access(bdev, handle->mode);
+	bdev_yield_write_access(bdev_file);
 
-	if (handle->holder)
-		bd_end_claim(bdev, handle->holder);
+	if (holder)
+		bd_end_claim(bdev, holder);
 
 	/*
 	 * Trigger event checking and tell drivers to flush MEDIA_CHANGE
@@ -986,10 +1045,9 @@ void bdev_release(struct bdev_handle *handle)
 	mutex_unlock(&disk->open_mutex);
 
 	module_put(disk->fops->owner);
+put_no_open:
 	blkdev_put_no_open(bdev);
-	kfree(handle);
 }
-EXPORT_SYMBOL(bdev_release);
 
 /**
  * lookup_bdev() - Look up a struct block_device by name.
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 2c90e5de0acd..d442ee358fc2 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -127,7 +127,7 @@ static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats)
 	if (!bfqg_stats_waiting(stats))
 		return;
 
-	now = ktime_get_ns();
+	now = blk_time_get_ns();
 	if (now > stats->start_group_wait_time)
 		bfq_stat_add(&stats->group_wait_time,
 			      now - stats->start_group_wait_time);
@@ -144,7 +144,7 @@ static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
 		return;
 	if (bfqg == curr_bfqg)
 		return;
-	stats->start_group_wait_time = ktime_get_ns();
+	stats->start_group_wait_time = blk_time_get_ns();
 	bfqg_stats_mark_waiting(stats);
 }
 
@@ -156,7 +156,7 @@ static void bfqg_stats_end_empty_time(struct bfqg_stats *stats)
 	if (!bfqg_stats_empty(stats))
 		return;
 
-	now = ktime_get_ns();
+	now = blk_time_get_ns();
 	if (now > stats->start_empty_time)
 		bfq_stat_add(&stats->empty_time,
 			      now - stats->start_empty_time);
@@ -183,7 +183,7 @@ void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg)
 	if (bfqg_stats_empty(stats))
 		return;
 
-	stats->start_empty_time = ktime_get_ns();
+	stats->start_empty_time = blk_time_get_ns();
 	bfqg_stats_mark_empty(stats);
 }
 
@@ -192,7 +192,7 @@ void bfqg_stats_update_idle_time(struct bfq_group *bfqg)
 	struct bfqg_stats *stats = &bfqg->stats;
 
 	if (bfqg_stats_idling(stats)) {
-		u64 now = ktime_get_ns();
+		u64 now = blk_time_get_ns();
 
 		if (now > stats->start_idle_time)
 			bfq_stat_add(&stats->idle_time,
@@ -205,7 +205,7 @@ void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg)
 {
 	struct bfqg_stats *stats = &bfqg->stats;
 
-	stats->start_idle_time = ktime_get_ns();
+	stats->start_idle_time = blk_time_get_ns();
 	bfqg_stats_mark_idling(stats);
 }
 
@@ -242,7 +242,7 @@ void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns,
 				  u64 io_start_time_ns, blk_opf_t opf)
 {
 	struct bfqg_stats *stats = &bfqg->stats;
-	u64 now = ktime_get_ns();
+	u64 now = blk_time_get_ns();
 
 	if (now > io_start_time_ns)
 		blkg_rwstat_add(&stats->service_time, opf,
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 3cce6de464a7..4b88a54a9b76 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -1005,7 +1005,7 @@ static struct request *bfq_check_fifo(struct bfq_queue *bfqq,
 
 	rq = rq_entry_fifo(bfqq->fifo.next);
 
-	if (rq == last || ktime_get_ns() < rq->fifo_time)
+	if (rq == last || blk_time_get_ns() < rq->fifo_time)
 		return NULL;
 
 	bfq_log_bfqq(bfqq->bfqd, bfqq, "check_fifo: returned %p", rq);
@@ -1829,7 +1829,7 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
 		 * bfq_bfqq_update_budg_for_activation for
 		 * details on the usage of the next variable.
 		 */
-		arrived_in_time =  ktime_get_ns() <=
+		arrived_in_time =  blk_time_get_ns() <=
 			bfqq->ttime.last_end_request +
 			bfqd->bfq_slice_idle * 3;
 	unsigned int act_idx = bfq_actuator_index(bfqd, rq->bio);
@@ -2208,7 +2208,7 @@ static void bfq_add_request(struct request *rq)
 	struct request *next_rq, *prev;
 	unsigned int old_wr_coeff = bfqq->wr_coeff;
 	bool interactive = false;
-	u64 now_ns = ktime_get_ns();
+	u64 now_ns = blk_time_get_ns();
 
 	bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq));
 	bfqq->queued[rq_is_sync(rq)]++;
@@ -2262,7 +2262,7 @@ static void bfq_add_request(struct request *rq)
 		      bfqd->rqs_injected && bfqd->tot_rq_in_driver > 0)) &&
 		    time_is_before_eq_jiffies(bfqq->decrease_time_jif +
 					      msecs_to_jiffies(10))) {
-			bfqd->last_empty_occupied_ns = ktime_get_ns();
+			bfqd->last_empty_occupied_ns = blk_time_get_ns();
 			/*
 			 * Start the state machine for measuring the
 			 * total service time of rq: setting
@@ -3294,7 +3294,7 @@ static void bfq_set_budget_timeout(struct bfq_data *bfqd,
 	else
 		timeout_coeff = bfqq->entity.weight / bfqq->entity.orig_weight;
 
-	bfqd->last_budget_start = ktime_get();
+	bfqd->last_budget_start = blk_time_get();
 
 	bfqq->budget_timeout = jiffies +
 		bfqd->bfq_timeout * timeout_coeff;
@@ -3394,7 +3394,7 @@ static void bfq_arm_slice_timer(struct bfq_data *bfqd)
 	else if (bfqq->wr_coeff > 1)
 		sl = max_t(u32, sl, 20ULL * NSEC_PER_MSEC);
 
-	bfqd->last_idling_start = ktime_get();
+	bfqd->last_idling_start = blk_time_get();
 	bfqd->last_idling_start_jiffies = jiffies;
 
 	hrtimer_start(&bfqd->idle_slice_timer, ns_to_ktime(sl),
@@ -3433,7 +3433,7 @@ static void bfq_reset_rate_computation(struct bfq_data *bfqd,
 				       struct request *rq)
 {
 	if (rq != NULL) { /* new rq dispatch now, reset accordingly */
-		bfqd->last_dispatch = bfqd->first_dispatch = ktime_get_ns();
+		bfqd->last_dispatch = bfqd->first_dispatch = blk_time_get_ns();
 		bfqd->peak_rate_samples = 1;
 		bfqd->sequential_samples = 0;
 		bfqd->tot_sectors_dispatched = bfqd->last_rq_max_size =
@@ -3590,7 +3590,7 @@ reset_computation:
  */
 static void bfq_update_peak_rate(struct bfq_data *bfqd, struct request *rq)
 {
-	u64 now_ns = ktime_get_ns();
+	u64 now_ns = blk_time_get_ns();
 
 	if (bfqd->peak_rate_samples == 0) { /* first dispatch */
 		bfq_log(bfqd, "update_peak_rate: goto reset, samples %d",
@@ -4162,7 +4162,7 @@ static bool bfq_bfqq_is_slow(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	if (compensate)
 		delta_ktime = bfqd->last_idling_start;
 	else
-		delta_ktime = ktime_get();
+		delta_ktime = blk_time_get();
 	delta_ktime = ktime_sub(delta_ktime, bfqd->last_budget_start);
 	delta_usecs = ktime_to_us(delta_ktime);
 
@@ -5591,7 +5591,7 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 			  struct bfq_io_cq *bic, pid_t pid, int is_sync,
 			  unsigned int act_idx)
 {
-	u64 now_ns = ktime_get_ns();
+	u64 now_ns = blk_time_get_ns();
 
 	bfqq->actuator_idx = act_idx;
 	RB_CLEAR_NODE(&bfqq->entity.rb_node);
@@ -5903,7 +5903,7 @@ static void bfq_update_io_thinktime(struct bfq_data *bfqd,
 	 */
 	if (bfqq->dispatched || bfq_bfqq_busy(bfqq))
 		return;
-	elapsed = ktime_get_ns() - bfqq->ttime.last_end_request;
+	elapsed = blk_time_get_ns() - bfqq->ttime.last_end_request;
 	elapsed = min_t(u64, elapsed, 2ULL * bfqd->bfq_slice_idle);
 
 	ttime->ttime_samples = (7*ttime->ttime_samples + 256) / 8;
@@ -6194,7 +6194,7 @@ static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
 	bfq_add_request(rq);
 	idle_timer_disabled = waiting && !bfq_bfqq_wait_request(bfqq);
 
-	rq->fifo_time = ktime_get_ns() + bfqd->bfq_fifo_expire[rq_is_sync(rq)];
+	rq->fifo_time = blk_time_get_ns() + bfqd->bfq_fifo_expire[rq_is_sync(rq)];
 	list_add_tail(&rq->queuelist, &bfqq->fifo);
 
 	bfq_rq_enqueued(bfqd, bfqq, rq);
@@ -6370,7 +6370,7 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
 		bfq_weights_tree_remove(bfqq);
 	}
 
-	now_ns = ktime_get_ns();
+	now_ns = blk_time_get_ns();
 
 	bfqq->ttime.last_end_request = now_ns;
 
@@ -6585,7 +6585,7 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
 static void bfq_update_inject_limit(struct bfq_data *bfqd,
 				    struct bfq_queue *bfqq)
 {
-	u64 tot_time_ns = ktime_get_ns() - bfqd->last_empty_occupied_ns;
+	u64 tot_time_ns = blk_time_get_ns() - bfqd->last_empty_occupied_ns;
 	unsigned int old_limit = bfqq->inject_limit;
 
 	if (bfqq->last_serv_time_ns > 0 && bfqd->rqs_injected) {
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index feef615e2c9c..2e3e8e04961e 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -336,7 +336,7 @@ int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes,
 	if (nr_vecs > BIO_MAX_VECS)
 		return -E2BIG;
 	if (nr_vecs > UIO_FASTIOV) {
-		bvec = kcalloc(sizeof(*bvec), nr_vecs, GFP_KERNEL);
+		bvec = kcalloc(nr_vecs, sizeof(*bvec), GFP_KERNEL);
 		if (!bvec)
 			return -ENOMEM;
 		pages = NULL;
@@ -395,6 +395,7 @@ static blk_status_t bio_integrity_process(struct bio *bio,
 	iter.tuple_size = bi->tuple_size;
 	iter.seed = proc_iter->bi_sector;
 	iter.prot_buf = bvec_virt(bip->bip_vec);
+	iter.pi_offset = bi->pi_offset;
 
 	__bio_for_each_segment(bv, bio, bviter, *proc_iter) {
 		void *kaddr = bvec_kmap_local(&bv);
diff --git a/block/bio.c b/block/bio.c
index b9642a41f286..d24420ed1c4c 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -16,7 +16,6 @@
 #include <linux/workqueue.h>
 #include <linux/cgroup.h>
 #include <linux/highmem.h>
-#include <linux/sched/sysctl.h>
 #include <linux/blk-crypto.h>
 #include <linux/xarray.h>
 
@@ -251,6 +250,7 @@ void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table,
 	bio->bi_opf = opf;
 	bio->bi_flags = 0;
 	bio->bi_ioprio = 0;
+	bio->bi_write_hint = 0;
 	bio->bi_status = 0;
 	bio->bi_iter.bi_sector = 0;
 	bio->bi_iter.bi_size = 0;
@@ -762,29 +762,31 @@ static inline void bio_put_percpu_cache(struct bio *bio)
 	struct bio_alloc_cache *cache;
 
 	cache = per_cpu_ptr(bio->bi_pool->cache, get_cpu());
-	if (READ_ONCE(cache->nr_irq) + cache->nr > ALLOC_CACHE_MAX) {
-		put_cpu();
-		bio_free(bio);
-		return;
-	}
+	if (READ_ONCE(cache->nr_irq) + cache->nr > ALLOC_CACHE_MAX)
+		goto out_free;
 
-	bio_uninit(bio);
-
-	if ((bio->bi_opf & REQ_POLLED) && !WARN_ON_ONCE(in_interrupt())) {
+	if (in_task()) {
+		bio_uninit(bio);
 		bio->bi_next = cache->free_list;
+		/* Not necessary but helps not to iopoll already freed bios */
 		bio->bi_bdev = NULL;
 		cache->free_list = bio;
 		cache->nr++;
-	} else {
-		unsigned long flags;
+	} else if (in_hardirq()) {
+		lockdep_assert_irqs_disabled();
 
-		local_irq_save(flags);
+		bio_uninit(bio);
 		bio->bi_next = cache->free_list_irq;
 		cache->free_list_irq = bio;
 		cache->nr_irq++;
-		local_irq_restore(flags);
+	} else {
+		goto out_free;
 	}
 	put_cpu();
+	return;
+out_free:
+	put_cpu();
+	bio_free(bio);
 }
 
 /**
@@ -813,6 +815,7 @@ static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp)
 {
 	bio_set_flag(bio, BIO_CLONED);
 	bio->bi_ioprio = bio_src->bi_ioprio;
+	bio->bi_write_hint = bio_src->bi_write_hint;
 	bio->bi_iter = bio_src->bi_iter;
 
 	if (bio->bi_bdev) {
@@ -1152,7 +1155,7 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty)
 
 	bio_for_each_folio_all(fi, bio) {
 		struct page *page;
-		size_t done = 0;
+		size_t nr_pages;
 
 		if (mark_dirty) {
 			folio_lock(fi.folio);
@@ -1160,10 +1163,11 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty)
 			folio_unlock(fi.folio);
 		}
 		page = folio_page(fi.folio, fi.offset / PAGE_SIZE);
+		nr_pages = (fi.offset + fi.length - 1) / PAGE_SIZE -
+			   fi.offset / PAGE_SIZE + 1;
 		do {
 			bio_release_page(bio, page++);
-			done += PAGE_SIZE;
-		} while (done < fi.length);
+		} while (--nr_pages != 0);
 	}
 }
 EXPORT_SYMBOL_GPL(__bio_release_pages);
@@ -1369,21 +1373,12 @@ int submit_bio_wait(struct bio *bio)
 {
 	DECLARE_COMPLETION_ONSTACK_MAP(done,
 			bio->bi_bdev->bd_disk->lockdep_map);
-	unsigned long hang_check;
 
 	bio->bi_private = &done;
 	bio->bi_end_io = submit_bio_wait_endio;
 	bio->bi_opf |= REQ_SYNC;
 	submit_bio(bio);
-
-	/* Prevent hang_check timer from firing at us during very long I/O */
-	hang_check = sysctl_hung_task_timeout_secs;
-	if (hang_check)
-		while (!wait_for_completion_io_timeout(&done,
-					hang_check * (HZ/2)))
-			;
-	else
-		wait_for_completion_io(&done);
+	blk_wait_io(&done);
 
 	return blk_status_to_errno(bio->bi_status);
 }
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index e303fd317313..bdbb557feb5a 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -300,7 +300,7 @@ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg)
  * @disk: gendisk the new blkg is associated with
  * @gfp_mask: allocation mask to use
  *
- * Allocate a new blkg assocating @blkcg and @q.
+ * Allocate a new blkg associating @blkcg and @disk.
  */
 static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
 				   gfp_t gfp_mask)
@@ -1846,7 +1846,7 @@ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay)
 {
 	unsigned long pflags;
 	bool clamp;
-	u64 now = ktime_to_ns(ktime_get());
+	u64 now = blk_time_get_ns();
 	u64 exp;
 	u64 delay_nsec = 0;
 	int tok;
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index b927a4a0ad03..78b74106bf10 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -19,6 +19,7 @@
 #include <linux/kthread.h>
 #include <linux/blk-mq.h>
 #include <linux/llist.h>
+#include "blk.h"
 
 struct blkcg_gq;
 struct blkg_policy_data;
diff --git a/block/blk-core.c b/block/blk-core.c
index 11342af420d0..a16b5abdbbf5 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -49,6 +49,7 @@
 #include "blk-pm.h"
 #include "blk-cgroup.h"
 #include "blk-throttle.h"
+#include "blk-ioprio.h"
 
 struct dentry *blk_debugfs_root;
 
@@ -393,24 +394,34 @@ static void blk_timeout_work(struct work_struct *work)
 {
 }
 
-struct request_queue *blk_alloc_queue(int node_id)
+struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id)
 {
 	struct request_queue *q;
+	int error;
 
 	q = kmem_cache_alloc_node(blk_requestq_cachep, GFP_KERNEL | __GFP_ZERO,
 				  node_id);
 	if (!q)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	q->last_merge = NULL;
 
 	q->id = ida_alloc(&blk_queue_ida, GFP_KERNEL);
-	if (q->id < 0)
+	if (q->id < 0) {
+		error = q->id;
 		goto fail_q;
+	}
 
 	q->stats = blk_alloc_queue_stats();
-	if (!q->stats)
+	if (!q->stats) {
+		error = -ENOMEM;
 		goto fail_id;
+	}
+
+	error = blk_set_default_limits(lim);
+	if (error)
+		goto fail_stats;
+	q->limits = *lim;
 
 	q->node = node_id;
 
@@ -424,6 +435,7 @@ struct request_queue *blk_alloc_queue(int node_id)
 	mutex_init(&q->debugfs_mutex);
 	mutex_init(&q->sysfs_lock);
 	mutex_init(&q->sysfs_dir_lock);
+	mutex_init(&q->limits_lock);
 	mutex_init(&q->rq_qos_mutex);
 	spin_lock_init(&q->queue_lock);
 
@@ -434,12 +446,12 @@ struct request_queue *blk_alloc_queue(int node_id)
 	 * Init percpu_ref in atomic mode so that it's faster to shutdown.
 	 * See blk_register_queue() for details.
 	 */
-	if (percpu_ref_init(&q->q_usage_counter,
+	error = percpu_ref_init(&q->q_usage_counter,
 				blk_queue_usage_counter_release,
-				PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))
+				PERCPU_REF_INIT_ATOMIC, GFP_KERNEL);
+	if (error)
 		goto fail_stats;
 
-	blk_set_default_limits(&q->limits);
 	q->nr_requests = BLKDEV_DEFAULT_RQ;
 
 	return q;
@@ -450,7 +462,7 @@ fail_id:
 	ida_free(&blk_queue_ida, q->id);
 fail_q:
 	kmem_cache_free(blk_requestq_cachep, q);
-	return NULL;
+	return ERR_PTR(error);
 }
 
 /**
@@ -833,6 +845,14 @@ end_io:
 }
 EXPORT_SYMBOL(submit_bio_noacct);
 
+static void bio_set_ioprio(struct bio *bio)
+{
+	/* Nobody set ioprio so far? Initialize it based on task's nice value */
+	if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) == IOPRIO_CLASS_NONE)
+		bio->bi_ioprio = get_current_ioprio();
+	blkcg_set_ioprio(bio);
+}
+
 /**
  * submit_bio - submit a bio to the block device layer for I/O
  * @bio: The &struct bio which describes the I/O
@@ -855,6 +875,7 @@ void submit_bio(struct bio *bio)
 		count_vm_events(PGPGOUT, bio_sectors(bio));
 	}
 
+	bio_set_ioprio(bio);
 	submit_bio_noacct(bio);
 }
 EXPORT_SYMBOL(submit_bio);
@@ -1073,6 +1094,7 @@ void blk_start_plug_nr_ios(struct blk_plug *plug, unsigned short nr_ios)
 	if (tsk->plug)
 		return;
 
+	plug->cur_ktime = 0;
 	plug->mq_list = NULL;
 	plug->cached_rq = NULL;
 	plug->nr_ios = min_t(unsigned short, nr_ios, BLK_MAX_REQUEST_COUNT);
@@ -1172,6 +1194,8 @@ void __blk_flush_plug(struct blk_plug *plug, bool from_schedule)
 	 */
 	if (unlikely(!rq_list_empty(plug->cached_rq)))
 		blk_mq_free_plug_rqs(plug);
+
+	current->flags &= ~PF_BLOCK_TS;
 }
 
 /**
@@ -1219,8 +1243,7 @@ int __init blk_dev_init(void)
 	if (!kblockd_workqueue)
 		panic("Failed to create kblockd\n");
 
-	blk_requestq_cachep = kmem_cache_create("request_queue",
-			sizeof(struct request_queue), 0, SLAB_PANIC, NULL);
+	blk_requestq_cachep = KMEM_CACHE(request_queue, SLAB_PANIC);
 
 	blk_debugfs_root = debugfs_create_dir("block", NULL);
 
diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c
index e6468eab2681..b1e7415f8439 100644
--- a/block/blk-crypto-fallback.c
+++ b/block/blk-crypto-fallback.c
@@ -172,6 +172,7 @@ static struct bio *blk_crypto_fallback_clone_bio(struct bio *bio_src)
 	if (bio_flagged(bio_src, BIO_REMAPPED))
 		bio_set_flag(bio, BIO_REMAPPED);
 	bio->bi_ioprio		= bio_src->bi_ioprio;
+	bio->bi_write_hint	= bio_src->bi_write_hint;
 	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
 	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
 
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 3f4d41952ef2..b0f314f4bc14 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -143,7 +143,7 @@ static void blk_account_io_flush(struct request *rq)
 	part_stat_lock();
 	part_stat_inc(part, ios[STAT_FLUSH]);
 	part_stat_add(part, nsecs[STAT_FLUSH],
-		      ktime_get_ns() - rq->start_time_ns);
+		      blk_time_get_ns() - rq->start_time_ns);
 	part_stat_unlock();
 }
 
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index d4e9b4556d14..ccbeb6dfa87a 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -370,6 +370,7 @@ void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template
 	bi->profile = template->profile ? template->profile : &nop_profile;
 	bi->tuple_size = template->tuple_size;
 	bi->tag_size = template->tag_size;
+	bi->pi_offset = template->pi_offset;
 
 	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue);
 
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 089fcb9cfce3..9a85bfbbc45a 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -829,7 +829,7 @@ static int ioc_autop_idx(struct ioc *ioc, struct gendisk *disk)
 
 	/* step up/down based on the vrate */
 	vrate_pct = div64_u64(ioc->vtime_base_rate * 100, VTIME_PER_USEC);
-	now_ns = ktime_get_ns();
+	now_ns = blk_time_get_ns();
 
 	if (p->too_fast_vrate_pct && p->too_fast_vrate_pct <= vrate_pct) {
 		if (!ioc->autop_too_fast_at)
@@ -1044,7 +1044,7 @@ static void ioc_now(struct ioc *ioc, struct ioc_now *now)
 	unsigned seq;
 	u64 vrate;
 
-	now->now_ns = ktime_get();
+	now->now_ns = blk_time_get_ns();
 	now->now = ktime_to_us(now->now_ns);
 	vrate = atomic64_read(&ioc->vtime_rate);
 
@@ -1261,7 +1261,7 @@ static void weight_updated(struct ioc_gq *iocg, struct ioc_now *now)
 static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now)
 {
 	struct ioc *ioc = iocg->ioc;
-	u64 last_period, cur_period;
+	u64 __maybe_unused last_period, cur_period;
 	u64 vtime, vtarget;
 	int i;
 
@@ -1353,6 +1353,13 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now)
 
 	lockdep_assert_held(&iocg->waitq.lock);
 
+	/*
+	 * If the delay is set by another CPU, we may be in the past. No need to
+	 * change anything if so. This avoids decay calculation underflow.
+	 */
+	if (time_before64(now->now, iocg->delay_at))
+		return false;
+
 	/* calculate the current delay in effect - 1/2 every second */
 	tdelta = now->now - iocg->delay_at;
 	if (iocg->delay)
@@ -2810,7 +2817,7 @@ static void ioc_rqos_done(struct rq_qos *rqos, struct request *rq)
 		return;
 	}
 
-	on_q_ns = ktime_get_ns() - rq->alloc_time_ns;
+	on_q_ns = blk_time_get_ns() - rq->alloc_time_ns;
 	rq_wait_ns = rq->start_time_ns - rq->alloc_time_ns;
 	size_nsec = div64_u64(calc_size_vtime_cost(rq, ioc), VTIME_PER_NSEC);
 
@@ -2893,7 +2900,7 @@ static int blk_iocost_init(struct gendisk *disk)
 	ioc->vtime_base_rate = VTIME_PER_USEC;
 	atomic64_set(&ioc->vtime_rate, VTIME_PER_USEC);
 	seqcount_spinlock_init(&ioc->period_seqcount, &ioc->lock);
-	ioc->period_at = ktime_to_us(ktime_get());
+	ioc->period_at = ktime_to_us(blk_time_get());
 	atomic64_set(&ioc->cur_period, 0);
 	atomic_set(&ioc->hweight_gen, 0);
 
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index c1a6aba1d59e..ebb522788d97 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -609,7 +609,7 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio)
 	if (!iolat->blkiolat->enabled)
 		return;
 
-	now = ktime_to_ns(ktime_get());
+	now = blk_time_get_ns();
 	while (blkg && blkg->parent) {
 		iolat = blkg_to_lat(blkg);
 		if (!iolat) {
@@ -661,7 +661,7 @@ static void blkiolatency_timer_fn(struct timer_list *t)
 	struct blk_iolatency *blkiolat = from_timer(blkiolat, t, timer);
 	struct blkcg_gq *blkg;
 	struct cgroup_subsys_state *pos_css;
-	u64 now = ktime_to_ns(ktime_get());
+	u64 now = blk_time_get_ns();
 
 	rcu_read_lock();
 	blkg_for_each_descendant_pre(blkg, pos_css,
@@ -985,7 +985,7 @@ static void iolatency_pd_init(struct blkg_policy_data *pd)
 	struct blkcg_gq *blkg = lat_to_blkg(iolat);
 	struct rq_qos *rqos = iolat_rq_qos(blkg->q);
 	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
-	u64 now = ktime_to_ns(ktime_get());
+	u64 now = blk_time_get_ns();
 	int cpu;
 
 	if (blk_queue_nonrot(blkg->q))
diff --git a/block/blk-lib.c b/block/blk-lib.c
index e59c3069e835..dc8e35d0a51d 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -35,6 +35,26 @@ static sector_t bio_discard_limit(struct block_device *bdev, sector_t sector)
 	return round_down(UINT_MAX, discard_granularity) >> SECTOR_SHIFT;
 }
 
+static void await_bio_endio(struct bio *bio)
+{
+	complete(bio->bi_private);
+	bio_put(bio);
+}
+
+/*
+ * await_bio_chain - ends @bio and waits for every chained bio to complete
+ */
+static void await_bio_chain(struct bio *bio)
+{
+	DECLARE_COMPLETION_ONSTACK_MAP(done,
+			bio->bi_bdev->bd_disk->lockdep_map);
+
+	bio->bi_private = &done;
+	bio->bi_end_io = await_bio_endio;
+	bio_endio(bio);
+	blk_wait_io(&done);
+}
+
 int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop)
 {
@@ -77,6 +97,10 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		 * is disabled.
 		 */
 		cond_resched();
+		if (fatal_signal_pending(current)) {
+			await_bio_chain(bio);
+			return -EINTR;
+		}
 	}
 
 	*biop = bio;
@@ -120,32 +144,33 @@ static int __blkdev_issue_write_zeroes(struct block_device *bdev,
 		struct bio **biop, unsigned flags)
 {
 	struct bio *bio = *biop;
-	unsigned int max_write_zeroes_sectors;
+	unsigned int max_sectors;
 
 	if (bdev_read_only(bdev))
 		return -EPERM;
 
-	/* Ensure that max_write_zeroes_sectors doesn't overflow bi_size */
-	max_write_zeroes_sectors = bdev_write_zeroes_sectors(bdev);
+	/* Ensure that max_sectors doesn't overflow bi_size */
+	max_sectors = bdev_write_zeroes_sectors(bdev);
 
-	if (max_write_zeroes_sectors == 0)
+	if (max_sectors == 0)
 		return -EOPNOTSUPP;
 
 	while (nr_sects) {
+		unsigned int len = min_t(sector_t, nr_sects, max_sectors);
+
 		bio = blk_next_bio(bio, bdev, 0, REQ_OP_WRITE_ZEROES, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		if (flags & BLKDEV_ZERO_NOUNMAP)
 			bio->bi_opf |= REQ_NOUNMAP;
 
-		if (nr_sects > max_write_zeroes_sectors) {
-			bio->bi_iter.bi_size = max_write_zeroes_sectors << 9;
-			nr_sects -= max_write_zeroes_sectors;
-			sector += max_write_zeroes_sectors;
-		} else {
-			bio->bi_iter.bi_size = nr_sects << 9;
-			nr_sects = 0;
-		}
+		bio->bi_iter.bi_size = len << SECTOR_SHIFT;
+		nr_sects -= len;
+		sector += len;
 		cond_resched();
+		if (fatal_signal_pending(current)) {
+			await_bio_chain(bio);
+			return -EINTR;
+		}
 	}
 
 	*biop = bio;
@@ -190,6 +215,10 @@ static int __blkdev_issue_zero_pages(struct block_device *bdev,
 				break;
 		}
 		cond_resched();
+		if (fatal_signal_pending(current)) {
+			await_bio_chain(bio);
+			return -EINTR;
+		}
 	}
 
 	*biop = bio;
@@ -280,7 +309,7 @@ retry:
 		bio_put(bio);
 	}
 	blk_finish_plug(&plug);
-	if (ret && try_write_zeroes) {
+	if (ret && ret != -EINTR && try_write_zeroes) {
 		if (!(flags & BLKDEV_ZERO_NOFALLBACK)) {
 			try_write_zeroes = false;
 			goto retry;
@@ -322,7 +351,7 @@ int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
 		return -EPERM;
 
 	blk_start_plug(&plug);
-	for (;;) {
+	while (nr_sects) {
 		unsigned int len = min_t(sector_t, nr_sects, max_sectors);
 
 		bio = blk_next_bio(bio, bdev, 0, REQ_OP_SECURE_ERASE, gfp);
@@ -331,12 +360,17 @@ int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
 
 		sector += len;
 		nr_sects -= len;
-		if (!nr_sects) {
-			ret = submit_bio_wait(bio);
-			bio_put(bio);
+		cond_resched();
+		if (fatal_signal_pending(current)) {
+			await_bio_chain(bio);
+			ret = -EINTR;
+			bio = NULL;
 			break;
 		}
-		cond_resched();
+	}
+	if (bio) {
+		ret = submit_bio_wait(bio);
+		bio_put(bio);
 	}
 	blk_finish_plug(&plug);
 
diff --git a/block/blk-map.c b/block/blk-map.c
index 8584babf3ea0..71210cdb3442 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -205,12 +205,19 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data,
 	/*
 	 * success
 	 */
-	if ((iov_iter_rw(iter) == WRITE &&
-	     (!map_data || !map_data->null_mapped)) ||
-	    (map_data && map_data->from_user)) {
+	if (iov_iter_rw(iter) == WRITE &&
+	     (!map_data || !map_data->null_mapped)) {
 		ret = bio_copy_from_iter(bio, iter);
 		if (ret)
 			goto cleanup;
+	} else if (map_data && map_data->from_user) {
+		struct iov_iter iter2 = *iter;
+
+		/* This is the copy-in part of SG_DXFER_TO_FROM_DEV. */
+		iter2.data_source = ITER_SOURCE;
+		ret = bio_copy_from_iter(bio, &iter2);
+		if (ret)
+			goto cleanup;
 	} else {
 		if (bmd->is_our_pages)
 			zero_fill_bio(bio);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 2d470cf2173e..2a06fd33039d 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -810,6 +810,10 @@ static struct request *attempt_merge(struct request_queue *q,
 	if (rq_data_dir(req) != rq_data_dir(next))
 		return NULL;
 
+	/* Don't merge requests with different write hints. */
+	if (req->write_hint != next->write_hint)
+		return NULL;
+
 	if (req->ioprio != next->ioprio)
 		return NULL;
 
@@ -937,6 +941,10 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (!bio_crypt_rq_ctx_compatible(rq, bio))
 		return false;
 
+	/* Don't merge requests with different write hints. */
+	if (rq->write_hint != bio->bi_write_hint)
+		return false;
+
 	if (rq->ioprio != bio_prio(bio))
 		return false;
 
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 5cbeb9344f2f..94668e72ab09 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -479,23 +479,6 @@ out:
 	return res;
 }
 
-static int hctx_run_show(void *data, struct seq_file *m)
-{
-	struct blk_mq_hw_ctx *hctx = data;
-
-	seq_printf(m, "%lu\n", hctx->run);
-	return 0;
-}
-
-static ssize_t hctx_run_write(void *data, const char __user *buf, size_t count,
-			      loff_t *ppos)
-{
-	struct blk_mq_hw_ctx *hctx = data;
-
-	hctx->run = 0;
-	return count;
-}
-
 static int hctx_active_show(void *data, struct seq_file *m)
 {
 	struct blk_mq_hw_ctx *hctx = data;
@@ -624,7 +607,6 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
 	{"tags_bitmap", 0400, hctx_tags_bitmap_show},
 	{"sched_tags", 0400, hctx_sched_tags_show},
 	{"sched_tags_bitmap", 0400, hctx_sched_tags_bitmap_show},
-	{"run", 0600, hctx_run_show, hctx_run_write},
 	{"active", 0400, hctx_active_show},
 	{"dispatch_busy", 0400, hctx_dispatch_busy_show},
 	{"type", 0400, hctx_type_show},
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 67c95f31b15b..451a2c1f1f32 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -324,8 +324,6 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)))
 		return;
 
-	hctx->run++;
-
 	/*
 	 * A return of -EAGAIN is an indication that hctx->dispatch is not
 	 * empty and we must run again in order to avoid starving flushes.
diff --git a/block/blk-mq.c b/block/blk-mq.c
index c11c97afa0bc..555ada922cf0 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -21,7 +21,6 @@
 #include <linux/llist.h>
 #include <linux/cpu.h>
 #include <linux/cache.h>
-#include <linux/sched/sysctl.h>
 #include <linux/sched/topology.h>
 #include <linux/sched/signal.h>
 #include <linux/delay.h>
@@ -40,7 +39,6 @@
 #include "blk-stat.h"
 #include "blk-mq-sched.h"
 #include "blk-rq-qos.h"
-#include "blk-ioprio.h"
 
 static DEFINE_PER_CPU(struct llist_head, blk_cpu_done);
 static DEFINE_PER_CPU(call_single_data_t, blk_cpu_csd);
@@ -323,7 +321,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	RB_CLEAR_NODE(&rq->rb_node);
 	rq->tag = BLK_MQ_NO_TAG;
 	rq->internal_tag = BLK_MQ_NO_TAG;
-	rq->start_time_ns = ktime_get_ns();
+	rq->start_time_ns = blk_time_get_ns();
 	rq->part = NULL;
 	blk_crypto_rq_set_defaults(rq);
 }
@@ -333,7 +331,7 @@ EXPORT_SYMBOL(blk_rq_init);
 static inline void blk_mq_rq_time_init(struct request *rq, u64 alloc_time_ns)
 {
 	if (blk_mq_need_time_stamp(rq))
-		rq->start_time_ns = ktime_get_ns();
+		rq->start_time_ns = blk_time_get_ns();
 	else
 		rq->start_time_ns = 0;
 
@@ -444,7 +442,7 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
 
 	/* alloc_time includes depth and tag waits */
 	if (blk_queue_rq_alloc_time(q))
-		alloc_time_ns = ktime_get_ns();
+		alloc_time_ns = blk_time_get_ns();
 
 	if (data->cmd_flags & REQ_NOWAIT)
 		data->flags |= BLK_MQ_REQ_NOWAIT;
@@ -629,7 +627,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 
 	/* alloc_time includes depth and tag waits */
 	if (blk_queue_rq_alloc_time(q))
-		alloc_time_ns = ktime_get_ns();
+		alloc_time_ns = blk_time_get_ns();
 
 	/*
 	 * If the tag allocator sleeps we could get an allocation for a
@@ -772,11 +770,16 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 		/*
 		 * Partial zone append completions cannot be supported as the
 		 * BIO fragments may end up not being written sequentially.
+		 * For such case, force the completed nbytes to be equal to
+		 * the BIO size so that bio_advance() sets the BIO remaining
+		 * size to 0 and we end up calling bio_endio() before returning.
 		 */
-		if (bio->bi_iter.bi_size != nbytes)
+		if (bio->bi_iter.bi_size != nbytes) {
 			bio->bi_status = BLK_STS_IOERR;
-		else
+			nbytes = bio->bi_iter.bi_size;
+		} else {
 			bio->bi_iter.bi_sector = rq->__sector;
+		}
 	}
 
 	bio_advance(bio, nbytes);
@@ -1037,7 +1040,7 @@ static inline void __blk_mq_end_request_acct(struct request *rq, u64 now)
 inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
 {
 	if (blk_mq_need_time_stamp(rq))
-		__blk_mq_end_request_acct(rq, ktime_get_ns());
+		__blk_mq_end_request_acct(rq, blk_time_get_ns());
 
 	blk_mq_finish_request(rq);
 
@@ -1080,7 +1083,7 @@ void blk_mq_end_request_batch(struct io_comp_batch *iob)
 	u64 now = 0;
 
 	if (iob->need_ts)
-		now = ktime_get_ns();
+		now = blk_time_get_ns();
 
 	while ((rq = rq_list_pop(&iob->req_list)) != NULL) {
 		prefetch(rq->bio);
@@ -1163,10 +1166,11 @@ static inline bool blk_mq_complete_need_ipi(struct request *rq)
 	if (force_irqthreads())
 		return false;
 
-	/* same CPU or cache domain?  Complete locally */
+	/* same CPU or cache domain and capacity?  Complete locally */
 	if (cpu == rq->mq_ctx->cpu ||
 	    (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags) &&
-	     cpus_share_cache(cpu, rq->mq_ctx->cpu)))
+	     cpus_share_cache(cpu, rq->mq_ctx->cpu) &&
+	     cpus_equal_capacity(cpu, rq->mq_ctx->cpu)))
 		return false;
 
 	/* don't try to IPI to an offline CPU */
@@ -1250,7 +1254,7 @@ void blk_mq_start_request(struct request *rq)
 
 	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags) &&
 	    !blk_rq_is_passthrough(rq)) {
-		rq->io_start_time_ns = ktime_get_ns();
+		rq->io_start_time_ns = blk_time_get_ns();
 		rq->stats_sectors = blk_rq_sectors(rq);
 		rq->rq_flags |= RQF_STATS;
 		rq_qos_issue(q, rq);
@@ -1405,22 +1409,10 @@ blk_status_t blk_execute_rq(struct request *rq, bool at_head)
 	blk_mq_insert_request(rq, at_head ? BLK_MQ_INSERT_AT_HEAD : 0);
 	blk_mq_run_hw_queue(hctx, false);
 
-	if (blk_rq_is_poll(rq)) {
+	if (blk_rq_is_poll(rq))
 		blk_rq_poll_completion(rq, &wait.done);
-	} else {
-		/*
-		 * Prevent hang_check timer from firing at us during very long
-		 * I/O
-		 */
-		unsigned long hang_check = sysctl_hung_task_timeout_secs;
-
-		if (hang_check)
-			while (!wait_for_completion_io_timeout(&wait.done,
-					hang_check * (HZ/2)))
-				;
-		else
-			wait_for_completion_io(&wait.done);
-	}
+	else
+		blk_wait_io(&wait.done);
 
 	return wait.ret;
 }
@@ -1860,6 +1852,22 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 	__add_wait_queue(wq, wait);
 
 	/*
+	 * Add one explicit barrier since blk_mq_get_driver_tag() may
+	 * not imply barrier in case of failure.
+	 *
+	 * Order adding us to wait queue and allocating driver tag.
+	 *
+	 * The pair is the one implied in sbitmap_queue_wake_up() which
+	 * orders clearing sbitmap tag bits and waitqueue_active() in
+	 * __sbitmap_queue_wake_up(), since waitqueue_active() is lockless
+	 *
+	 * Otherwise, re-order of adding wait queue and getting driver tag
+	 * may cause __sbitmap_queue_wake_up() to wake up nothing because
+	 * the waitqueue_active() may not observe us in wait queue.
+	 */
+	smp_mb();
+
+	/*
 	 * It's possible that a tag was freed in the window between the
 	 * allocation failure and adding the hardware queue to the wait
 	 * queue.
@@ -2564,6 +2572,7 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
 		rq->cmd_flags |= REQ_FAILFAST_MASK;
 
 	rq->__sector = bio->bi_iter.bi_sector;
+	rq->write_hint = bio->bi_write_hint;
 	blk_rq_bio_prep(rq, bio, nr_segs);
 
 	/* This can't fail, since GFP_NOIO includes __GFP_DIRECT_RECLAIM. */
@@ -2871,9 +2880,6 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
 	};
 	struct request *rq;
 
-	if (blk_mq_attempt_bio_merge(q, bio, nsegs))
-		return NULL;
-
 	rq_qos_throttle(q, bio);
 
 	if (plug) {
@@ -2891,20 +2897,32 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
 	return NULL;
 }
 
-/* return true if this @rq can be used for @bio */
-static bool blk_mq_can_use_cached_rq(struct request *rq, struct blk_plug *plug,
-		struct bio *bio)
+/*
+ * Check if there is a suitable cached request and return it.
+ */
+static struct request *blk_mq_peek_cached_request(struct blk_plug *plug,
+		struct request_queue *q, blk_opf_t opf)
 {
-	enum hctx_type type = blk_mq_get_hctx_type(bio->bi_opf);
-	enum hctx_type hctx_type = rq->mq_hctx->type;
+	enum hctx_type type = blk_mq_get_hctx_type(opf);
+	struct request *rq;
 
-	WARN_ON_ONCE(rq_list_peek(&plug->cached_rq) != rq);
+	if (!plug)
+		return NULL;
+	rq = rq_list_peek(&plug->cached_rq);
+	if (!rq || rq->q != q)
+		return NULL;
+	if (type != rq->mq_hctx->type &&
+	    (type != HCTX_TYPE_READ || rq->mq_hctx->type != HCTX_TYPE_DEFAULT))
+		return NULL;
+	if (op_is_flush(rq->cmd_flags) != op_is_flush(opf))
+		return NULL;
+	return rq;
+}
 
-	if (type != hctx_type &&
-	    !(type == HCTX_TYPE_READ && hctx_type == HCTX_TYPE_DEFAULT))
-		return false;
-	if (op_is_flush(rq->cmd_flags) != op_is_flush(bio->bi_opf))
-		return false;
+static void blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
+		struct bio *bio)
+{
+	WARN_ON_ONCE(rq_list_peek(&plug->cached_rq) != rq);
 
 	/*
 	 * If any qos ->throttle() end up blocking, we will have flushed the
@@ -2917,15 +2935,6 @@ static bool blk_mq_can_use_cached_rq(struct request *rq, struct blk_plug *plug,
 	blk_mq_rq_time_init(rq, 0);
 	rq->cmd_flags = bio->bi_opf;
 	INIT_LIST_HEAD(&rq->queuelist);
-	return true;
-}
-
-static void bio_set_ioprio(struct bio *bio)
-{
-	/* Nobody set ioprio so far? Initialize it based on task's nice value */
-	if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) == IOPRIO_CLASS_NONE)
-		bio->bi_ioprio = get_current_ioprio();
-	blkcg_set_ioprio(bio);
 }
 
 /**
@@ -2947,47 +2956,43 @@ void blk_mq_submit_bio(struct bio *bio)
 	struct blk_plug *plug = blk_mq_plug(bio);
 	const int is_sync = op_is_sync(bio->bi_opf);
 	struct blk_mq_hw_ctx *hctx;
-	struct request *rq = NULL;
 	unsigned int nr_segs = 1;
+	struct request *rq;
 	blk_status_t ret;
 
 	bio = blk_queue_bounce(bio, q);
-	if (bio_may_exceed_limits(bio, &q->limits)) {
+
+	/*
+	 * If the plug has a cached request for this queue, try use it.
+	 *
+	 * The cached request already holds a q_usage_counter reference and we
+	 * don't have to acquire a new one if we use it.
+	 */
+	rq = blk_mq_peek_cached_request(plug, q, bio->bi_opf);
+	if (!rq) {
+		if (unlikely(bio_queue_enter(bio)))
+			return;
+	}
+
+	if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
 		bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
 		if (!bio)
-			return;
+			goto queue_exit;
 	}
+	if (!bio_integrity_prep(bio))
+		goto queue_exit;
 
-	bio_set_ioprio(bio);
+	if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
+		goto queue_exit;
 
-	if (plug) {
-		rq = rq_list_peek(&plug->cached_rq);
-		if (rq && rq->q != q)
-			rq = NULL;
-	}
-	if (rq) {
-		if (!bio_integrity_prep(bio))
-			return;
-		if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
-			return;
-		if (blk_mq_can_use_cached_rq(rq, plug, bio))
-			goto done;
-		percpu_ref_get(&q->q_usage_counter);
+	if (!rq) {
+		rq = blk_mq_get_new_requests(q, plug, bio, nr_segs);
+		if (unlikely(!rq))
+			goto queue_exit;
 	} else {
-		if (unlikely(bio_queue_enter(bio)))
-			return;
-		if (!bio_integrity_prep(bio))
-			goto fail;
-	}
-
-	rq = blk_mq_get_new_requests(q, plug, bio, nr_segs);
-	if (unlikely(!rq)) {
-fail:
-		blk_queue_exit(q);
-		return;
+		blk_mq_use_cached_rq(rq, plug, bio);
 	}
 
-done:
 	trace_block_getrq(bio);
 
 	rq_qos_track(q, rq, bio);
@@ -3018,6 +3023,15 @@ done:
 	} else {
 		blk_mq_run_dispatch_ops(q, blk_mq_try_issue_directly(hctx, rq));
 	}
+	return;
+
+queue_exit:
+	/*
+	 * Don't drop the queue reference if we were trying to use a cached
+	 * request and thus didn't acquire one.
+	 */
+	if (!rq)
+		blk_queue_exit(q);
 }
 
 #ifdef CONFIG_BLK_MQ_STACKING
@@ -3079,7 +3093,7 @@ blk_status_t blk_insert_cloned_request(struct request *rq)
 	blk_mq_run_dispatch_ops(q,
 			ret = blk_mq_request_issue_directly(rq, true));
 	if (ret)
-		blk_account_io_done(rq, ktime_get_ns());
+		blk_account_io_done(rq, blk_time_get_ns());
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
@@ -3157,6 +3171,7 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 	}
 	rq->nr_phys_segments = rq_src->nr_phys_segments;
 	rq->ioprio = rq_src->ioprio;
+	rq->write_hint = rq_src->write_hint;
 
 	if (rq->bio && blk_crypto_rq_bio_prep(rq, rq->bio, gfp_mask) < 0)
 		goto free_and_out;
@@ -4058,15 +4073,16 @@ void blk_mq_release(struct request_queue *q)
 	blk_mq_sysfs_deinit(q);
 }
 
-static struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set,
-		void *queuedata)
+struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set,
+		struct queue_limits *lim, void *queuedata)
 {
+	struct queue_limits default_lim = { };
 	struct request_queue *q;
 	int ret;
 
-	q = blk_alloc_queue(set->numa_node);
-	if (!q)
-		return ERR_PTR(-ENOMEM);
+	q = blk_alloc_queue(lim ? lim : &default_lim, set->numa_node);
+	if (IS_ERR(q))
+		return q;
 	q->queuedata = queuedata;
 	ret = blk_mq_init_allocated_queue(set, q);
 	if (ret) {
@@ -4075,20 +4091,15 @@ static struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set,
 	}
 	return q;
 }
-
-struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
-{
-	return blk_mq_init_queue_data(set, NULL);
-}
-EXPORT_SYMBOL(blk_mq_init_queue);
+EXPORT_SYMBOL(blk_mq_alloc_queue);
 
 /**
  * blk_mq_destroy_queue - shutdown a request queue
  * @q: request queue to shutdown
  *
- * This shuts down a request queue allocated by blk_mq_init_queue(). All future
+ * This shuts down a request queue allocated by blk_mq_alloc_queue(). All future
  * requests will be failed with -ENODEV. The caller is responsible for dropping
- * the reference from blk_mq_init_queue() by calling blk_put_queue().
+ * the reference from blk_mq_alloc_queue() by calling blk_put_queue().
  *
  * Context: can sleep
  */
@@ -4109,13 +4120,14 @@ void blk_mq_destroy_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_mq_destroy_queue);
 
-struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata,
+struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set,
+		struct queue_limits *lim, void *queuedata,
 		struct lock_class_key *lkclass)
 {
 	struct request_queue *q;
 	struct gendisk *disk;
 
-	q = blk_mq_init_queue_data(set, queuedata);
+	q = blk_mq_alloc_queue(set, lim, queuedata);
 	if (IS_ERR(q))
 		return ERR_CAST(q);
 
@@ -4369,7 +4381,7 @@ static void blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 	if (set->nr_maps == 1)
 		set->map[HCTX_TYPE_DEFAULT].nr_queues = set->nr_hw_queues;
 
-	if (set->ops->map_queues && !is_kdump_kernel()) {
+	if (set->ops->map_queues) {
 		int i;
 
 		/*
@@ -4468,14 +4480,12 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 
 	/*
 	 * If a crashdump is active, then we are potentially in a very
-	 * memory constrained environment. Limit us to 1 queue and
-	 * 64 tags to prevent using too much memory.
+	 * memory constrained environment. Limit us to  64 tags to prevent
+	 * using too much memory.
 	 */
-	if (is_kdump_kernel()) {
-		set->nr_hw_queues = 1;
-		set->nr_maps = 1;
+	if (is_kdump_kernel())
 		set->queue_depth = min(64U, set->queue_depth);
-	}
+
 	/*
 	 * There is no use for more h/w queues than cpus if we just have
 	 * a single map
@@ -4505,7 +4515,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 						  GFP_KERNEL, set->numa_node);
 		if (!set->map[i].mq_map)
 			goto out_free_mq_map;
-		set->map[i].nr_queues = is_kdump_kernel() ? 1 : set->nr_hw_queues;
+		set->map[i].nr_queues = set->nr_hw_queues;
 	}
 
 	blk_mq_update_queue_map(set);
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 06ea91e51b8b..3c7d8d638ab5 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -26,52 +26,21 @@ void blk_queue_rq_timeout(struct request_queue *q, unsigned int timeout)
 EXPORT_SYMBOL_GPL(blk_queue_rq_timeout);
 
 /**
- * blk_set_default_limits - reset limits to default values
- * @lim:  the queue_limits structure to reset
- *
- * Description:
- *   Returns a queue_limit struct to its default state.
- */
-void blk_set_default_limits(struct queue_limits *lim)
-{
-	lim->max_segments = BLK_MAX_SEGMENTS;
-	lim->max_discard_segments = 1;
-	lim->max_integrity_segments = 0;
-	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
-	lim->virt_boundary_mask = 0;
-	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
-	lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
-	lim->max_user_sectors = lim->max_dev_sectors = 0;
-	lim->chunk_sectors = 0;
-	lim->max_write_zeroes_sectors = 0;
-	lim->max_zone_append_sectors = 0;
-	lim->max_discard_sectors = 0;
-	lim->max_hw_discard_sectors = 0;
-	lim->max_secure_erase_sectors = 0;
-	lim->discard_granularity = 512;
-	lim->discard_alignment = 0;
-	lim->discard_misaligned = 0;
-	lim->logical_block_size = lim->physical_block_size = lim->io_min = 512;
-	lim->bounce = BLK_BOUNCE_NONE;
-	lim->alignment_offset = 0;
-	lim->io_opt = 0;
-	lim->misaligned = 0;
-	lim->zoned = false;
-	lim->zone_write_granularity = 0;
-	lim->dma_alignment = 511;
-}
-
-/**
  * blk_set_stacking_limits - set default limits for stacking devices
  * @lim:  the queue_limits structure to reset
  *
- * Description:
- *   Returns a queue_limit struct to its default state. Should be used
- *   by stacking drivers like DM that have no internal limits.
+ * Prepare queue limits for applying limits from underlying devices using
+ * blk_stack_limits().
  */
 void blk_set_stacking_limits(struct queue_limits *lim)
 {
-	blk_set_default_limits(lim);
+	memset(lim, 0, sizeof(*lim));
+	lim->logical_block_size = SECTOR_SIZE;
+	lim->physical_block_size = SECTOR_SIZE;
+	lim->io_min = SECTOR_SIZE;
+	lim->discard_granularity = SECTOR_SIZE;
+	lim->dma_alignment = SECTOR_SIZE - 1;
+	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
 
 	/* Inherit limits from component devices */
 	lim->max_segments = USHRT_MAX;
@@ -82,9 +51,239 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 	lim->max_dev_sectors = UINT_MAX;
 	lim->max_write_zeroes_sectors = UINT_MAX;
 	lim->max_zone_append_sectors = UINT_MAX;
+	lim->max_user_discard_sectors = UINT_MAX;
 }
 EXPORT_SYMBOL(blk_set_stacking_limits);
 
+static void blk_apply_bdi_limits(struct backing_dev_info *bdi,
+		struct queue_limits *lim)
+{
+	/*
+	 * For read-ahead of large files to be effective, we need to read ahead
+	 * at least twice the optimal I/O size.
+	 */
+	bdi->ra_pages = max(lim->io_opt * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
+	bdi->io_pages = lim->max_sectors >> PAGE_SECTORS_SHIFT;
+}
+
+static int blk_validate_zoned_limits(struct queue_limits *lim)
+{
+	if (!lim->zoned) {
+		if (WARN_ON_ONCE(lim->max_open_zones) ||
+		    WARN_ON_ONCE(lim->max_active_zones) ||
+		    WARN_ON_ONCE(lim->zone_write_granularity) ||
+		    WARN_ON_ONCE(lim->max_zone_append_sectors))
+			return -EINVAL;
+		return 0;
+	}
+
+	if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED)))
+		return -EINVAL;
+
+	if (lim->zone_write_granularity < lim->logical_block_size)
+		lim->zone_write_granularity = lim->logical_block_size;
+
+	if (lim->max_zone_append_sectors) {
+		/*
+		 * The Zone Append size is limited by the maximum I/O size
+		 * and the zone size given that it can't span zones.
+		 */
+		lim->max_zone_append_sectors =
+			min3(lim->max_hw_sectors,
+			     lim->max_zone_append_sectors,
+			     lim->chunk_sectors);
+	}
+
+	return 0;
+}
+
+/*
+ * Check that the limits in lim are valid, initialize defaults for unset
+ * values, and cap values based on others where needed.
+ */
+static int blk_validate_limits(struct queue_limits *lim)
+{
+	unsigned int max_hw_sectors;
+
+	/*
+	 * Unless otherwise specified, default to 512 byte logical blocks and a
+	 * physical block size equal to the logical block size.
+	 */
+	if (!lim->logical_block_size)
+		lim->logical_block_size = SECTOR_SIZE;
+	if (lim->physical_block_size < lim->logical_block_size)
+		lim->physical_block_size = lim->logical_block_size;
+
+	/*
+	 * The minimum I/O size defaults to the physical block size unless
+	 * explicitly overridden.
+	 */
+	if (lim->io_min < lim->physical_block_size)
+		lim->io_min = lim->physical_block_size;
+
+	/*
+	 * max_hw_sectors has a somewhat weird default for historical reason,
+	 * but driver really should set their own instead of relying on this
+	 * value.
+	 *
+	 * The block layer relies on the fact that every driver can
+	 * handle at lest a page worth of data per I/O, and needs the value
+	 * aligned to the logical block size.
+	 */
+	if (!lim->max_hw_sectors)
+		lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
+	if (WARN_ON_ONCE(lim->max_hw_sectors < PAGE_SECTORS))
+		return -EINVAL;
+	lim->max_hw_sectors = round_down(lim->max_hw_sectors,
+			lim->logical_block_size >> SECTOR_SHIFT);
+
+	/*
+	 * The actual max_sectors value is a complex beast and also takes the
+	 * max_dev_sectors value (set by SCSI ULPs) and a user configurable
+	 * value into account.  The ->max_sectors value is always calculated
+	 * from these, so directly setting it won't have any effect.
+	 */
+	max_hw_sectors = min_not_zero(lim->max_hw_sectors,
+				lim->max_dev_sectors);
+	if (lim->max_user_sectors) {
+		if (lim->max_user_sectors > max_hw_sectors ||
+		    lim->max_user_sectors < PAGE_SIZE / SECTOR_SIZE)
+			return -EINVAL;
+		lim->max_sectors = min(max_hw_sectors, lim->max_user_sectors);
+	} else {
+		lim->max_sectors = min(max_hw_sectors, BLK_DEF_MAX_SECTORS_CAP);
+	}
+	lim->max_sectors = round_down(lim->max_sectors,
+			lim->logical_block_size >> SECTOR_SHIFT);
+
+	/*
+	 * Random default for the maximum number of segments.  Driver should not
+	 * rely on this and set their own.
+	 */
+	if (!lim->max_segments)
+		lim->max_segments = BLK_MAX_SEGMENTS;
+
+	lim->max_discard_sectors =
+		min(lim->max_hw_discard_sectors, lim->max_user_discard_sectors);
+
+	if (!lim->max_discard_segments)
+		lim->max_discard_segments = 1;
+
+	if (lim->discard_granularity < lim->physical_block_size)
+		lim->discard_granularity = lim->physical_block_size;
+
+	/*
+	 * By default there is no limit on the segment boundary alignment,
+	 * but if there is one it can't be smaller than the page size as
+	 * that would break all the normal I/O patterns.
+	 */
+	if (!lim->seg_boundary_mask)
+		lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
+	if (WARN_ON_ONCE(lim->seg_boundary_mask < PAGE_SIZE - 1))
+		return -EINVAL;
+
+	/*
+	 * Devices that require a virtual boundary do not support scatter/gather
+	 * I/O natively, but instead require a descriptor list entry for each
+	 * page (which might not be identical to the Linux PAGE_SIZE).  Because
+	 * of that they are not limited by our notion of "segment size".
+	 */
+	if (lim->virt_boundary_mask) {
+		if (WARN_ON_ONCE(lim->max_segment_size &&
+				 lim->max_segment_size != UINT_MAX))
+			return -EINVAL;
+		lim->max_segment_size = UINT_MAX;
+	} else {
+		/*
+		 * The maximum segment size has an odd historic 64k default that
+		 * drivers probably should override.  Just like the I/O size we
+		 * require drivers to at least handle a full page per segment.
+		 */
+		if (!lim->max_segment_size)
+			lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
+		if (WARN_ON_ONCE(lim->max_segment_size < PAGE_SIZE))
+			return -EINVAL;
+	}
+
+	/*
+	 * We require drivers to at least do logical block aligned I/O, but
+	 * historically could not check for that due to the separate calls
+	 * to set the limits.  Once the transition is finished the check
+	 * below should be narrowed down to check the logical block size.
+	 */
+	if (!lim->dma_alignment)
+		lim->dma_alignment = SECTOR_SIZE - 1;
+	if (WARN_ON_ONCE(lim->dma_alignment > PAGE_SIZE))
+		return -EINVAL;
+
+	if (lim->alignment_offset) {
+		lim->alignment_offset &= (lim->physical_block_size - 1);
+		lim->misaligned = 0;
+	}
+
+	return blk_validate_zoned_limits(lim);
+}
+
+/*
+ * Set the default limits for a newly allocated queue.  @lim contains the
+ * initial limits set by the driver, which could be no limit in which case
+ * all fields are cleared to zero.
+ */
+int blk_set_default_limits(struct queue_limits *lim)
+{
+	/*
+	 * Most defaults are set by capping the bounds in blk_validate_limits,
+	 * but max_user_discard_sectors is special and needs an explicit
+	 * initialization to the max value here.
+	 */
+	lim->max_user_discard_sectors = UINT_MAX;
+	return blk_validate_limits(lim);
+}
+
+/**
+ * queue_limits_commit_update - commit an atomic update of queue limits
+ * @q:		queue to update
+ * @lim:	limits to apply
+ *
+ * Apply the limits in @lim that were obtained from queue_limits_start_update()
+ * and updated by the caller to @q.
+ *
+ * Returns 0 if successful, else a negative error code.
+ */
+int queue_limits_commit_update(struct request_queue *q,
+		struct queue_limits *lim)
+	__releases(q->limits_lock)
+{
+	int error = blk_validate_limits(lim);
+
+	if (!error) {
+		q->limits = *lim;
+		if (q->disk)
+			blk_apply_bdi_limits(q->disk->bdi, lim);
+	}
+	mutex_unlock(&q->limits_lock);
+	return error;
+}
+EXPORT_SYMBOL_GPL(queue_limits_commit_update);
+
+/**
+ * queue_limits_set - apply queue limits to queue
+ * @q:		queue to update
+ * @lim:	limits to apply
+ *
+ * Apply the limits in @lim that were freshly initialized to @q.
+ * To update existing limits use queue_limits_start_update() and
+ * queue_limits_commit_update() instead.
+ *
+ * Returns 0 if successful, else a negative error code.
+ */
+int queue_limits_set(struct request_queue *q, struct queue_limits *lim)
+{
+	mutex_lock(&q->limits_lock);
+	return queue_limits_commit_update(q, lim);
+}
+EXPORT_SYMBOL_GPL(queue_limits_set);
+
 /**
  * blk_queue_bounce_limit - set bounce buffer limit for queue
  * @q: the request queue for the device
@@ -177,8 +376,11 @@ EXPORT_SYMBOL(blk_queue_chunk_sectors);
 void blk_queue_max_discard_sectors(struct request_queue *q,
 		unsigned int max_discard_sectors)
 {
-	q->limits.max_hw_discard_sectors = max_discard_sectors;
-	q->limits.max_discard_sectors = max_discard_sectors;
+	struct queue_limits *lim = &q->limits;
+
+	lim->max_hw_discard_sectors = max_discard_sectors;
+	lim->max_discard_sectors =
+		min(max_discard_sectors, lim->max_user_discard_sectors);
 }
 EXPORT_SYMBOL(blk_queue_max_discard_sectors);
 
@@ -393,15 +595,7 @@ EXPORT_SYMBOL(blk_queue_alignment_offset);
 
 void disk_update_readahead(struct gendisk *disk)
 {
-	struct request_queue *q = disk->queue;
-
-	/*
-	 * For read-ahead of large files to be effective, we need to read ahead
-	 * at least twice the optimal I/O size.
-	 */
-	disk->bdi->ra_pages =
-		max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
-	disk->bdi->io_pages = queue_max_sectors(q) >> (PAGE_SHIFT - 9);
+	blk_apply_bdi_limits(disk->bdi, &disk->queue->limits);
 }
 EXPORT_SYMBOL_GPL(disk_update_readahead);
 
@@ -689,33 +883,38 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	t->zone_write_granularity = max(t->zone_write_granularity,
 					b->zone_write_granularity);
 	t->zoned = max(t->zoned, b->zoned);
+	if (!t->zoned) {
+		t->zone_write_granularity = 0;
+		t->max_zone_append_sectors = 0;
+	}
 	return ret;
 }
 EXPORT_SYMBOL(blk_stack_limits);
 
 /**
- * disk_stack_limits - adjust queue limits for stacked drivers
- * @disk:  MD/DM gendisk (top)
+ * queue_limits_stack_bdev - adjust queue_limits for stacked devices
+ * @t:	the stacking driver limits (top device)
  * @bdev:  the underlying block device (bottom)
  * @offset:  offset to beginning of data within component device
+ * @pfx: prefix to use for warnings logged
  *
  * Description:
- *    Merges the limits for a top level gendisk and a bottom level
- *    block_device.
+ *    This function is used by stacking drivers like MD and DM to ensure
+ *    that all component devices have compatible block sizes and
+ *    alignments.  The stacking driver must provide a queue_limits
+ *    struct (top) and then iteratively call the stacking function for
+ *    all component (bottom) devices.  The stacking function will
+ *    attempt to combine the values and ensure proper alignment.
  */
-void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
-		       sector_t offset)
+void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev,
+		sector_t offset, const char *pfx)
 {
-	struct request_queue *t = disk->queue;
-
-	if (blk_stack_limits(&t->limits, &bdev_get_queue(bdev)->limits,
-			get_start_sect(bdev) + (offset >> 9)) < 0)
+	if (blk_stack_limits(t, &bdev_get_queue(bdev)->limits,
+			get_start_sect(bdev) + offset))
 		pr_notice("%s: Warning: Device %pg is misaligned\n",
-			disk->disk_name, bdev);
-
-	disk_update_readahead(disk);
+			pfx, bdev);
 }
-EXPORT_SYMBOL(disk_stack_limits);
+EXPORT_SYMBOL_GPL(queue_limits_stack_bdev);
 
 /**
  * blk_queue_update_dma_pad - update pad mask
diff --git a/block/blk-stat.c b/block/blk-stat.c
index 7ff76ae6c76a..e42c263e53fb 100644
--- a/block/blk-stat.c
+++ b/block/blk-stat.c
@@ -27,7 +27,7 @@ void blk_rq_stat_init(struct blk_rq_stat *stat)
 /* src is a per-cpu stat, mean isn't initialized */
 void blk_rq_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
 {
-	if (!src->nr_samples)
+	if (dst->nr_samples + src->nr_samples <= dst->nr_samples)
 		return;
 
 	dst->min = min(dst->min, src->min);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 6b2429cad81a..8c8f69d8ba48 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -174,23 +174,29 @@ static ssize_t queue_discard_max_show(struct request_queue *q, char *page)
 static ssize_t queue_discard_max_store(struct request_queue *q,
 				       const char *page, size_t count)
 {
-	unsigned long max_discard;
-	ssize_t ret = queue_var_store(&max_discard, page, count);
+	unsigned long max_discard_bytes;
+	struct queue_limits lim;
+	ssize_t ret;
+	int err;
 
+	ret = queue_var_store(&max_discard_bytes, page, count);
 	if (ret < 0)
 		return ret;
 
-	if (max_discard & (q->limits.discard_granularity - 1))
+	if (max_discard_bytes & (q->limits.discard_granularity - 1))
 		return -EINVAL;
 
-	max_discard >>= 9;
-	if (max_discard > UINT_MAX)
+	if ((max_discard_bytes >> SECTOR_SHIFT) > UINT_MAX)
 		return -EINVAL;
 
-	if (max_discard > q->limits.max_hw_discard_sectors)
-		max_discard = q->limits.max_hw_discard_sectors;
+	blk_mq_freeze_queue(q);
+	lim = queue_limits_start_update(q);
+	lim.max_user_discard_sectors = max_discard_bytes >> SECTOR_SHIFT;
+	err = queue_limits_commit_update(q, &lim);
+	blk_mq_unfreeze_queue(q);
 
-	q->limits.max_discard_sectors = max_discard;
+	if (err)
+		return err;
 	return ret;
 }
 
@@ -226,35 +232,22 @@ static ssize_t queue_zone_append_max_show(struct request_queue *q, char *page)
 static ssize_t
 queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 {
-	unsigned long var;
-	unsigned int max_sectors_kb,
-		max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1,
-			page_kb = 1 << (PAGE_SHIFT - 10);
-	ssize_t ret = queue_var_store(&var, page, count);
+	unsigned long max_sectors_kb;
+	struct queue_limits lim;
+	ssize_t ret;
+	int err;
 
+	ret = queue_var_store(&max_sectors_kb, page, count);
 	if (ret < 0)
 		return ret;
 
-	max_sectors_kb = (unsigned int)var;
-	max_hw_sectors_kb = min_not_zero(max_hw_sectors_kb,
-					 q->limits.max_dev_sectors >> 1);
-	if (max_sectors_kb == 0) {
-		q->limits.max_user_sectors = 0;
-		max_sectors_kb = min(max_hw_sectors_kb,
-				     BLK_DEF_MAX_SECTORS_CAP >> 1);
-	} else {
-		if (max_sectors_kb > max_hw_sectors_kb ||
-		    max_sectors_kb < page_kb)
-			return -EINVAL;
-		q->limits.max_user_sectors = max_sectors_kb << 1;
-	}
-
-	spin_lock_irq(&q->queue_lock);
-	q->limits.max_sectors = max_sectors_kb << 1;
-	if (q->disk)
-		q->disk->bdi->io_pages = max_sectors_kb >> (PAGE_SHIFT - 10);
-	spin_unlock_irq(&q->queue_lock);
-
+	blk_mq_freeze_queue(q);
+	lim = queue_limits_start_update(q);
+	lim.max_user_sectors = max_sectors_kb << 1;
+	err = queue_limits_commit_update(q, &lim);
+	blk_mq_unfreeze_queue(q);
+	if (err)
+		return err;
 	return ret;
 }
 
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 16f5766620a4..f4850a6f860b 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1098,7 +1098,7 @@ static int throtl_dispatch_tg(struct throtl_grp *tg)
 	while ((bio = throtl_peek_queued(&sq->queued[READ])) &&
 	       tg_may_dispatch(tg, bio, NULL)) {
 
-		tg_dispatch_one_bio(tg, bio_data_dir(bio));
+		tg_dispatch_one_bio(tg, READ);
 		nr_reads++;
 
 		if (nr_reads >= max_nr_reads)
@@ -1108,7 +1108,7 @@ static int throtl_dispatch_tg(struct throtl_grp *tg)
 	while ((bio = throtl_peek_queued(&sq->queued[WRITE])) &&
 	       tg_may_dispatch(tg, bio, NULL)) {
 
-		tg_dispatch_one_bio(tg, bio_data_dir(bio));
+		tg_dispatch_one_bio(tg, WRITE);
 		nr_writes++;
 
 		if (nr_writes >= max_nr_writes)
@@ -1815,7 +1815,7 @@ static bool throtl_tg_is_idle(struct throtl_grp *tg)
 	time = min_t(unsigned long, MAX_IDLE_TIME, 4 * tg->idletime_threshold);
 	ret = tg->latency_target == DFL_LATENCY_TARGET ||
 	      tg->idletime_threshold == DFL_IDLE_THRESHOLD ||
-	      (ktime_get_ns() >> 10) - tg->last_finish_time > time ||
+	      (blk_time_get_ns() >> 10) - tg->last_finish_time > time ||
 	      tg->avg_idletime > tg->idletime_threshold ||
 	      (tg->latency_target && tg->bio_cnt &&
 		tg->bad_bio_cnt * 5 < tg->bio_cnt);
@@ -2060,7 +2060,7 @@ static void blk_throtl_update_idletime(struct throtl_grp *tg)
 	if (last_finish_time == 0)
 		return;
 
-	now = ktime_get_ns() >> 10;
+	now = blk_time_get_ns() >> 10;
 	if (now <= last_finish_time ||
 	    last_finish_time == tg->checked_last_finish_time)
 		return;
@@ -2327,7 +2327,7 @@ void blk_throtl_bio_endio(struct bio *bio)
 	if (!tg->td->limit_valid[LIMIT_LOW])
 		return;
 
-	finish_time_ns = ktime_get_ns();
+	finish_time_ns = blk_time_get_ns();
 	tg->last_finish_time = finish_time_ns >> 10;
 
 	start_time = bio_issue_time(&bio->bi_issue) >> 10;
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 5ba3cd574eac..64472134dd26 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -29,6 +29,7 @@
 #include "blk-wbt.h"
 #include "blk-rq-qos.h"
 #include "elevator.h"
+#include "blk.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/wbt.h>
@@ -163,9 +164,9 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var)
  */
 static bool wb_recent_wait(struct rq_wb *rwb)
 {
-	struct bdi_writeback *wb = &rwb->rqos.disk->bdi->wb;
+	struct backing_dev_info *bdi = rwb->rqos.disk->bdi;
 
-	return time_before(jiffies, wb->dirty_sleep + HZ);
+	return time_before(jiffies, bdi->last_bdp_sleep + HZ);
 }
 
 static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb,
@@ -274,13 +275,12 @@ static inline bool stat_sample_valid(struct blk_rq_stat *stat)
 
 static u64 rwb_sync_issue_lat(struct rq_wb *rwb)
 {
-	u64 now, issue = READ_ONCE(rwb->sync_issue);
+	u64 issue = READ_ONCE(rwb->sync_issue);
 
 	if (!issue || !rwb->sync_cookie)
 		return 0;
 
-	now = ktime_to_ns(ktime_get());
-	return now - issue;
+	return blk_time_get_ns() - issue;
 }
 
 static inline unsigned int wbt_inflight(struct rq_wb *rwb)
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index d343e5756a9c..da0f4b2a8fa0 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -11,7 +11,6 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/rbtree.h>
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
 #include <linux/mm.h>
@@ -177,8 +176,7 @@ static int blk_zone_need_reset_cb(struct blk_zone *zone, unsigned int idx,
 	}
 }
 
-static int blkdev_zone_reset_all_emulated(struct block_device *bdev,
-					  gfp_t gfp_mask)
+static int blkdev_zone_reset_all_emulated(struct block_device *bdev)
 {
 	struct gendisk *disk = bdev->bd_disk;
 	sector_t capacity = bdev_nr_sectors(bdev);
@@ -205,7 +203,7 @@ static int blkdev_zone_reset_all_emulated(struct block_device *bdev,
 		}
 
 		bio = blk_next_bio(bio, bdev, 0, REQ_OP_ZONE_RESET | REQ_SYNC,
-				   gfp_mask);
+				   GFP_KERNEL);
 		bio->bi_iter.bi_sector = sector;
 		sector += zone_sectors;
 
@@ -223,7 +221,7 @@ out_free_need_reset:
 	return ret;
 }
 
-static int blkdev_zone_reset_all(struct block_device *bdev, gfp_t gfp_mask)
+static int blkdev_zone_reset_all(struct block_device *bdev)
 {
 	struct bio bio;
 
@@ -238,7 +236,6 @@ static int blkdev_zone_reset_all(struct block_device *bdev, gfp_t gfp_mask)
  * @sector:	Start sector of the first zone to operate on
  * @nr_sectors:	Number of sectors, should be at least the length of one zone and
  *		must be zone size aligned.
- * @gfp_mask:	Memory allocation flags (for bio_alloc)
  *
  * Description:
  *    Perform the specified operation on the range of zones specified by
@@ -248,7 +245,7 @@ static int blkdev_zone_reset_all(struct block_device *bdev, gfp_t gfp_mask)
  *    or finish request.
  */
 int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
-		     sector_t sector, sector_t nr_sectors, gfp_t gfp_mask)
+		     sector_t sector, sector_t nr_sectors)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 	sector_t zone_sectors = bdev_zone_sectors(bdev);
@@ -285,12 +282,12 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
 	 */
 	if (op == REQ_OP_ZONE_RESET && sector == 0 && nr_sectors == capacity) {
 		if (!blk_queue_zone_resetall(q))
-			return blkdev_zone_reset_all_emulated(bdev, gfp_mask);
-		return blkdev_zone_reset_all(bdev, gfp_mask);
+			return blkdev_zone_reset_all_emulated(bdev);
+		return blkdev_zone_reset_all(bdev);
 	}
 
 	while (sector < end_sector) {
-		bio = blk_next_bio(bio, bdev, 0, op | REQ_SYNC, gfp_mask);
+		bio = blk_next_bio(bio, bdev, 0, op | REQ_SYNC, GFP_KERNEL);
 		bio->bi_iter.bi_sector = sector;
 		sector += zone_sectors;
 
@@ -419,8 +416,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 		return -ENOTTY;
 	}
 
-	ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors,
-			       GFP_KERNEL);
+	ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors);
 
 fail:
 	if (cmd == BLKRESETZONE)
diff --git a/block/blk.h b/block/blk.h
index 1ef920f72e0f..a19b7b42e650 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -4,6 +4,8 @@
 
 #include <linux/blk-crypto.h>
 #include <linux/memblock.h>	/* for max_pfn/max_low_pfn */
+#include <linux/sched/sysctl.h>
+#include <linux/timekeeping.h>
 #include <xen/xen.h>
 #include "blk-crypto-internal.h"
 
@@ -70,6 +72,18 @@ static inline int bio_queue_enter(struct bio *bio)
 	return __bio_queue_enter(q, bio);
 }
 
+static inline void blk_wait_io(struct completion *done)
+{
+	/* Prevent hang_check timer from firing at us during very long I/O */
+	unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2;
+
+	if (timeout)
+		while (!wait_for_completion_io_timeout(done, timeout))
+			;
+	else
+		wait_for_completion_io(done);
+}
+
 #define BIO_INLINE_VECS 4
 struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs,
 		gfp_t gfp_mask);
@@ -329,7 +343,7 @@ void blk_rq_set_mixed_merge(struct request *rq);
 bool blk_rq_merge_ok(struct request *rq, struct bio *bio);
 enum elv_merge blk_try_merge(struct request *rq, struct bio *bio);
 
-void blk_set_default_limits(struct queue_limits *lim);
+int blk_set_default_limits(struct queue_limits *lim);
 int blk_dev_init(void);
 
 /*
@@ -447,7 +461,7 @@ static inline void bio_release_page(struct bio *bio, struct page *page)
 		unpin_user_page(page);
 }
 
-struct request_queue *blk_alloc_queue(int node_id);
+struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id);
 
 int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode);
 
@@ -516,4 +530,75 @@ static inline int req_ref_read(struct request *req)
 	return atomic_read(&req->ref);
 }
 
+static inline u64 blk_time_get_ns(void)
+{
+	struct blk_plug *plug = current->plug;
+
+	if (!plug)
+		return ktime_get_ns();
+
+	/*
+	 * 0 could very well be a valid time, but rather than flag "this is
+	 * a valid timestamp" separately, just accept that we'll do an extra
+	 * ktime_get_ns() if we just happen to get 0 as the current time.
+	 */
+	if (!plug->cur_ktime) {
+		plug->cur_ktime = ktime_get_ns();
+		current->flags |= PF_BLOCK_TS;
+	}
+	return plug->cur_ktime;
+}
+
+static inline ktime_t blk_time_get(void)
+{
+	return ns_to_ktime(blk_time_get_ns());
+}
+
+/*
+ * From most significant bit:
+ * 1 bit: reserved for other usage, see below
+ * 12 bits: original size of bio
+ * 51 bits: issue time of bio
+ */
+#define BIO_ISSUE_RES_BITS      1
+#define BIO_ISSUE_SIZE_BITS     12
+#define BIO_ISSUE_RES_SHIFT     (64 - BIO_ISSUE_RES_BITS)
+#define BIO_ISSUE_SIZE_SHIFT    (BIO_ISSUE_RES_SHIFT - BIO_ISSUE_SIZE_BITS)
+#define BIO_ISSUE_TIME_MASK     ((1ULL << BIO_ISSUE_SIZE_SHIFT) - 1)
+#define BIO_ISSUE_SIZE_MASK     \
+	(((1ULL << BIO_ISSUE_SIZE_BITS) - 1) << BIO_ISSUE_SIZE_SHIFT)
+#define BIO_ISSUE_RES_MASK      (~((1ULL << BIO_ISSUE_RES_SHIFT) - 1))
+
+/* Reserved bit for blk-throtl */
+#define BIO_ISSUE_THROTL_SKIP_LATENCY (1ULL << 63)
+
+static inline u64 __bio_issue_time(u64 time)
+{
+	return time & BIO_ISSUE_TIME_MASK;
+}
+
+static inline u64 bio_issue_time(struct bio_issue *issue)
+{
+	return __bio_issue_time(issue->value);
+}
+
+static inline sector_t bio_issue_size(struct bio_issue *issue)
+{
+	return ((issue->value & BIO_ISSUE_SIZE_MASK) >> BIO_ISSUE_SIZE_SHIFT);
+}
+
+static inline void bio_issue_init(struct bio_issue *issue,
+				       sector_t size)
+{
+	size &= (1ULL << BIO_ISSUE_SIZE_BITS) - 1;
+	issue->value = ((issue->value & BIO_ISSUE_RES_MASK) |
+			(blk_time_get_ns() & BIO_ISSUE_TIME_MASK) |
+			((u64)size << BIO_ISSUE_SIZE_SHIFT));
+}
+
+void bdev_release(struct file *bdev_file);
+int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder,
+	      const struct blk_holder_ops *hops, struct file *bdev_file);
+int bdev_permission(dev_t dev, blk_mode_t mode, void *holder);
+
 #endif /* BLK_INTERNAL_H */
diff --git a/block/bounce.c b/block/bounce.c
index 7cfcb242f9a1..d6a5219f29dd 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -169,6 +169,7 @@ static struct bio *bounce_clone_bio(struct bio *bio_src)
 	if (bio_flagged(bio_src, BIO_REMAPPED))
 		bio_set_flag(bio, BIO_REMAPPED);
 	bio->bi_ioprio		= bio_src->bi_ioprio;
+	bio->bi_write_hint	= bio_src->bi_write_hint;
 	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
 	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
 
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index b3acdbdb6e7e..bcc7dee6abce 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -383,7 +383,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
 	if (blk_mq_alloc_tag_set(set))
 		goto out_tag_set;
 
-	q = blk_mq_init_queue(set);
+	q = blk_mq_alloc_queue(set, NULL, NULL);
 	if (IS_ERR(q)) {
 		ret = PTR_ERR(q);
 		goto out_queue;
diff --git a/block/fops.c b/block/fops.c
index 0cf8cf72cdfa..679d9b752fe8 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -73,6 +73,7 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 		bio_init(&bio, bdev, vecs, nr_pages, dio_bio_write_op(iocb));
 	}
 	bio.bi_iter.bi_sector = pos >> SECTOR_SHIFT;
+	bio.bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint;
 	bio.bi_ioprio = iocb->ki_ioprio;
 
 	ret = bio_iov_iter_get_pages(&bio, iter);
@@ -203,6 +204,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 
 	for (;;) {
 		bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
+		bio->bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint;
 		bio->bi_private = dio;
 		bio->bi_end_io = blkdev_bio_end_io;
 		bio->bi_ioprio = iocb->ki_ioprio;
@@ -321,6 +323,7 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 	dio->flags = 0;
 	dio->iocb = iocb;
 	bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
+	bio->bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint;
 	bio->bi_end_io = blkdev_bio_end_io_async;
 	bio->bi_ioprio = iocb->ki_ioprio;
 
@@ -482,7 +485,7 @@ static void blkdev_readahead(struct readahead_control *rac)
 }
 
 static int blkdev_map_blocks(struct iomap_writepage_ctx *wpc,
-		struct inode *inode, loff_t offset)
+		struct inode *inode, loff_t offset, unsigned int len)
 {
 	loff_t isize = i_size_read(inode);
 
@@ -569,18 +572,17 @@ static int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
 blk_mode_t file_to_blk_mode(struct file *file)
 {
 	blk_mode_t mode = 0;
-	struct bdev_handle *handle = file->private_data;
 
 	if (file->f_mode & FMODE_READ)
 		mode |= BLK_OPEN_READ;
 	if (file->f_mode & FMODE_WRITE)
 		mode |= BLK_OPEN_WRITE;
 	/*
-	 * do_dentry_open() clears O_EXCL from f_flags, use handle->mode to
-	 * determine whether the open was exclusive for already open files.
+	 * do_dentry_open() clears O_EXCL from f_flags, use file->private_data
+	 * to determine whether the open was exclusive for already open files.
 	 */
-	if (handle)
-		mode |= handle->mode & BLK_OPEN_EXCL;
+	if (file->private_data)
+		mode |= BLK_OPEN_EXCL;
 	else if (file->f_flags & O_EXCL)
 		mode |= BLK_OPEN_EXCL;
 	if (file->f_flags & O_NDELAY)
@@ -599,36 +601,31 @@ blk_mode_t file_to_blk_mode(struct file *file)
 
 static int blkdev_open(struct inode *inode, struct file *filp)
 {
-	struct bdev_handle *handle;
+	struct block_device *bdev;
 	blk_mode_t mode;
-
-	/*
-	 * Preserve backwards compatibility and allow large file access
-	 * even if userspace doesn't ask for it explicitly. Some mkfs
-	 * binary needs it. We might want to drop this workaround
-	 * during an unstable branch.
-	 */
-	filp->f_flags |= O_LARGEFILE;
-	filp->f_mode |= FMODE_BUF_RASYNC | FMODE_CAN_ODIRECT;
+	int ret;
 
 	mode = file_to_blk_mode(filp);
-	handle = bdev_open_by_dev(inode->i_rdev, mode,
-			mode & BLK_OPEN_EXCL ? filp : NULL, NULL);
-	if (IS_ERR(handle))
-		return PTR_ERR(handle);
+	/* Use the file as the holder. */
+	if (mode & BLK_OPEN_EXCL)
+		filp->private_data = filp;
+	ret = bdev_permission(inode->i_rdev, mode, filp->private_data);
+	if (ret)
+		return ret;
 
-	if (bdev_nowait(handle->bdev))
-		filp->f_mode |= FMODE_NOWAIT;
+	bdev = blkdev_get_no_open(inode->i_rdev);
+	if (!bdev)
+		return -ENXIO;
 
-	filp->f_mapping = handle->bdev->bd_inode->i_mapping;
-	filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
-	filp->private_data = handle;
-	return 0;
+	ret = bdev_open(bdev, mode, filp->private_data, NULL, filp);
+	if (ret)
+		blkdev_put_no_open(bdev);
+	return ret;
 }
 
 static int blkdev_release(struct inode *inode, struct file *filp)
 {
-	bdev_release(filp->private_data);
+	bdev_release(filp);
 	return 0;
 }
 
diff --git a/block/genhd.c b/block/genhd.c
index d74fb5b4ae68..bb29a68e1d67 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -342,7 +342,7 @@ EXPORT_SYMBOL_GPL(disk_uevent);
 
 int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode)
 {
-	struct bdev_handle *handle;
+	struct file *file;
 	int ret = 0;
 
 	if (disk->flags & (GENHD_FL_NO_PART | GENHD_FL_HIDDEN))
@@ -366,12 +366,12 @@ int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode)
 	}
 
 	set_bit(GD_NEED_PART_SCAN, &disk->state);
-	handle = bdev_open_by_dev(disk_devt(disk), mode & ~BLK_OPEN_EXCL, NULL,
-				  NULL);
-	if (IS_ERR(handle))
-		ret = PTR_ERR(handle);
+	file = bdev_file_open_by_dev(disk_devt(disk), mode & ~BLK_OPEN_EXCL,
+				     NULL, NULL);
+	if (IS_ERR(file))
+		ret = PTR_ERR(file);
 	else
-		bdev_release(handle);
+		fput(file);
 
 	/*
 	 * If blkdev_get_by_dev() failed early, GD_NEED_PART_SCAN is still set,
@@ -1201,7 +1201,7 @@ static int block_uevent(const struct device *dev, struct kobj_uevent_env *env)
 	return add_uevent_var(env, "DISKSEQ=%llu", disk->diskseq);
 }
 
-struct class block_class = {
+const struct class block_class = {
 	.name		= "block",
 	.dev_uevent	= block_uevent,
 };
@@ -1391,19 +1391,21 @@ out_free_disk:
 	return NULL;
 }
 
-struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass)
+struct gendisk *__blk_alloc_disk(struct queue_limits *lim, int node,
+		struct lock_class_key *lkclass)
 {
+	struct queue_limits default_lim = { };
 	struct request_queue *q;
 	struct gendisk *disk;
 
-	q = blk_alloc_queue(node);
-	if (!q)
-		return NULL;
+	q = blk_alloc_queue(lim ? lim : &default_lim, node);
+	if (IS_ERR(q))
+		return ERR_CAST(q);
 
 	disk = __alloc_disk_node(q, node, lkclass);
 	if (!disk) {
 		blk_put_queue(q);
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 	set_bit(GD_OWNS_QUEUE, &disk->state);
 	return disk;
diff --git a/block/holder.c b/block/holder.c
index 37d18c13d958..791091a7eac2 100644
--- a/block/holder.c
+++ b/block/holder.c
@@ -8,6 +8,8 @@ struct bd_holder_disk {
 	int			refcnt;
 };
 
+static DEFINE_MUTEX(blk_holder_mutex);
+
 static struct bd_holder_disk *bd_find_holder_disk(struct block_device *bdev,
 						  struct gendisk *disk)
 {
@@ -80,7 +82,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
 	kobject_get(bdev->bd_holder_dir);
 	mutex_unlock(&bdev->bd_disk->open_mutex);
 
-	mutex_lock(&disk->open_mutex);
+	mutex_lock(&blk_holder_mutex);
 	WARN_ON_ONCE(!bdev->bd_holder);
 
 	holder = bd_find_holder_disk(bdev, disk);
@@ -108,7 +110,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
 		goto out_del_symlink;
 	list_add(&holder->list, &disk->slave_bdevs);
 
-	mutex_unlock(&disk->open_mutex);
+	mutex_unlock(&blk_holder_mutex);
 	return 0;
 
 out_del_symlink:
@@ -116,7 +118,7 @@ out_del_symlink:
 out_free_holder:
 	kfree(holder);
 out_unlock:
-	mutex_unlock(&disk->open_mutex);
+	mutex_unlock(&blk_holder_mutex);
 	if (ret)
 		kobject_put(bdev->bd_holder_dir);
 	return ret;
@@ -140,7 +142,7 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk)
 	if (WARN_ON_ONCE(!disk->slave_dir))
 		return;
 
-	mutex_lock(&disk->open_mutex);
+	mutex_lock(&blk_holder_mutex);
 	holder = bd_find_holder_disk(bdev, disk);
 	if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) {
 		del_symlink(disk->slave_dir, bdev_kobj(bdev));
@@ -149,6 +151,6 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk)
 		list_del_init(&holder->list);
 		kfree(holder);
 	}
-	mutex_unlock(&disk->open_mutex);
+	mutex_unlock(&blk_holder_mutex);
 }
 EXPORT_SYMBOL_GPL(bd_unlink_disk_holder);
diff --git a/block/ioctl.c b/block/ioctl.c
index 9c73a763ef88..0c76137adcaa 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -18,10 +18,8 @@ static int blkpg_do_ioctl(struct block_device *bdev,
 {
 	struct gendisk *disk = bdev->bd_disk;
 	struct blkpg_partition p;
-	sector_t start, length;
+	sector_t start, length, capacity, end;
 
-	if (disk->flags & GENHD_FL_NO_PART)
-		return -EINVAL;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
 	if (copy_from_user(&p, upart, sizeof(struct blkpg_partition)))
@@ -43,6 +41,13 @@ static int blkpg_do_ioctl(struct block_device *bdev,
 
 	start = p.start >> SECTOR_SHIFT;
 	length = p.length >> SECTOR_SHIFT;
+	capacity = get_capacity(disk);
+
+	if (check_add_overflow(start, length, &end))
+		return -EINVAL;
+
+	if (start >= capacity || end > capacity)
+		return -EINVAL;
 
 	switch (op) {
 	case BLKPG_ADD_PARTITION:
@@ -471,7 +476,7 @@ static int blkdev_bszset(struct block_device *bdev, blk_mode_t mode,
 		int __user *argp)
 {
 	int ret, n;
-	struct bdev_handle *handle;
+	struct file *file;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
@@ -483,12 +488,11 @@ static int blkdev_bszset(struct block_device *bdev, blk_mode_t mode,
 	if (mode & BLK_OPEN_EXCL)
 		return set_blocksize(bdev, n);
 
-	handle = bdev_open_by_dev(bdev->bd_dev, mode, &bdev, NULL);
-	if (IS_ERR(handle))
+	file = bdev_file_open_by_dev(bdev->bd_dev, mode, &bdev, NULL);
+	if (IS_ERR(file))
 		return -EBUSY;
 	ret = set_blocksize(bdev, n);
-	bdev_release(handle);
-
+	fput(file);
 	return ret;
 }
 
diff --git a/block/ioprio.c b/block/ioprio.c
index b5a942519a79..73301a261429 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -139,32 +139,6 @@ out:
 	return ret;
 }
 
-/*
- * If the task has set an I/O priority, use that. Otherwise, return
- * the default I/O priority.
- *
- * Expected to be called for current task or with task_lock() held to keep
- * io_context stable.
- */
-int __get_task_ioprio(struct task_struct *p)
-{
-	struct io_context *ioc = p->io_context;
-	int prio;
-
-	if (p != current)
-		lockdep_assert_held(&p->alloc_lock);
-	if (ioc)
-		prio = ioc->ioprio;
-	else
-		prio = IOPRIO_DEFAULT;
-
-	if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE)
-		prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p),
-					 task_nice_ioprio(p));
-	return prio;
-}
-EXPORT_SYMBOL_GPL(__get_task_ioprio);
-
 static int get_task_ioprio(struct task_struct *p)
 {
 	int ret;
diff --git a/block/opal_proto.h b/block/opal_proto.h
index dec7ce3a3edb..d247a457bf6e 100644
--- a/block/opal_proto.h
+++ b/block/opal_proto.h
@@ -71,6 +71,7 @@ enum opal_response_token {
 #define SHORT_ATOM_BYTE  0xBF
 #define MEDIUM_ATOM_BYTE 0xDF
 #define LONG_ATOM_BYTE   0xE3
+#define EMPTY_ATOM_BYTE  0xFF
 
 #define OPAL_INVAL_PARAM 12
 #define OPAL_MANUFACTURED_INACTIVE 0x08
diff --git a/block/partitions/core.c b/block/partitions/core.c
index e6ac73617f3e..b11e88c82c8c 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -419,26 +419,20 @@ static bool partition_overlaps(struct gendisk *disk, sector_t start,
 int bdev_add_partition(struct gendisk *disk, int partno, sector_t start,
 		sector_t length)
 {
-	sector_t capacity = get_capacity(disk), end;
 	struct block_device *part;
 	int ret;
 
 	mutex_lock(&disk->open_mutex);
-	if (check_add_overflow(start, length, &end)) {
-		ret = -EINVAL;
+	if (!disk_live(disk)) {
+		ret = -ENXIO;
 		goto out;
 	}
 
-	if (start >= capacity || end > capacity) {
+	if (disk->flags & GENHD_FL_NO_PART) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	if (!disk_live(disk)) {
-		ret = -ENXIO;
-		goto out;
-	}
-
 	if (partition_overlaps(disk, start, length, -1)) {
 		ret = -EBUSY;
 		goto out;
@@ -562,8 +556,8 @@ static bool blk_add_partition(struct gendisk *disk,
 	part = add_partition(disk, p, from, size, state->parts[p].flags,
 			     &state->parts[p].info);
 	if (IS_ERR(part) && PTR_ERR(part) != -ENXIO) {
-		printk(KERN_ERR " %s: p%d could not be added: %ld\n",
-		       disk->disk_name, p, -PTR_ERR(part));
+		printk(KERN_ERR " %s: p%d could not be added: %pe\n",
+		       disk->disk_name, p, part);
 		return true;
 	}
 
diff --git a/block/partitions/mac.c b/block/partitions/mac.c
index 7b521df00a39..c80183156d68 100644
--- a/block/partitions/mac.c
+++ b/block/partitions/mac.c
@@ -20,6 +20,7 @@ extern void note_bootable_part(dev_t dev, int part, int goodness);
  * Code to understand MacOS partition tables.
  */
 
+#ifdef CONFIG_PPC_PMAC
 static inline void mac_fix_string(char *stg, int len)
 {
 	int i;
@@ -27,6 +28,7 @@ static inline void mac_fix_string(char *stg, int len)
 	for (i = len - 1; i >= 0 && stg[i] == ' '; i--)
 		stg[i] = 0;
 }
+#endif
 
 int mac_partition(struct parsed_partitions *state)
 {
diff --git a/block/sed-opal.c b/block/sed-opal.c
index 3d9e9cd250bd..14fe0fef811c 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -1056,16 +1056,20 @@ static int response_parse(const u8 *buf, size_t length,
 			token_length = response_parse_medium(iter, pos);
 		else if (pos[0] <= LONG_ATOM_BYTE) /* long atom */
 			token_length = response_parse_long(iter, pos);
+		else if (pos[0] == EMPTY_ATOM_BYTE) /* empty atom */
+			token_length = 1;
 		else /* TOKEN */
 			token_length = response_parse_token(iter, pos);
 
 		if (token_length < 0)
 			return token_length;
 
+		if (pos[0] != EMPTY_ATOM_BYTE)
+			num_entries++;
+
 		pos += token_length;
 		total -= token_length;
 		iter++;
-		num_entries++;
 	}
 
 	resp->num = num_entries;
@@ -1208,7 +1212,7 @@ static int cmd_start(struct opal_dev *dev, const u8 *uid, const u8 *method)
 static int start_opal_session_cont(struct opal_dev *dev)
 {
 	u32 hsn, tsn;
-	int error = 0;
+	int error;
 
 	error = parse_and_check_status(dev);
 	if (error)
@@ -1350,7 +1354,7 @@ static int get_active_key_cont(struct opal_dev *dev)
 {
 	const char *activekey;
 	size_t keylen;
-	int error = 0;
+	int error;
 
 	error = parse_and_check_status(dev);
 	if (error)
@@ -2153,7 +2157,7 @@ static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
 	u8 lr_buffer[OPAL_UID_LENGTH];
 	struct opal_lock_unlock *lkul = data;
 	u8 read_locked = 1, write_locked = 1;
-	int err = 0;
+	int err;
 
 	if (build_locking_range(lr_buffer, sizeof(lr_buffer),
 				lkul->session.opal_key.lr) < 0)
@@ -2576,7 +2580,7 @@ static int opal_get_discv(struct opal_dev *dev, struct opal_discovery *discv)
 	const struct opal_step discovery0_step = {
 		opal_discovery0, discv
 	};
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&dev->dev_lock);
 	setup_opal_dev(dev);
@@ -3065,7 +3069,7 @@ bool opal_unlock_from_suspend(struct opal_dev *dev)
 {
 	struct opal_suspend_data *suspend;
 	bool was_failure = false;
-	int ret = 0;
+	int ret;
 
 	if (!dev)
 		return false;
@@ -3108,10 +3112,9 @@ static int opal_read_table(struct opal_dev *dev,
 		{ read_table_data, rw_tbl },
 		{ end_opal_session, }
 	};
-	int ret = 0;
 
 	if (!rw_tbl->size)
-		return ret;
+		return 0;
 
 	return execute_steps(dev, read_table_steps,
 			     ARRAY_SIZE(read_table_steps));
@@ -3125,10 +3128,9 @@ static int opal_write_table(struct opal_dev *dev,
 		{ write_table_data, rw_tbl },
 		{ end_opal_session, }
 	};
-	int ret = 0;
 
 	if (!rw_tbl->size)
-		return ret;
+		return 0;
 
 	return execute_steps(dev, write_table_steps,
 			     ARRAY_SIZE(write_table_steps));
diff --git a/block/t10-pi.c b/block/t10-pi.c
index 914d8cddd43a..d90892fd6f2a 100644
--- a/block/t10-pi.c
+++ b/block/t10-pi.c
@@ -12,14 +12,14 @@
 #include <net/checksum.h>
 #include <asm/unaligned.h>
 
-typedef __be16 (csum_fn) (void *, unsigned int);
+typedef __be16 (csum_fn) (__be16, void *, unsigned int);
 
-static __be16 t10_pi_crc_fn(void *data, unsigned int len)
+static __be16 t10_pi_crc_fn(__be16 crc, void *data, unsigned int len)
 {
-	return cpu_to_be16(crc_t10dif(data, len));
+	return cpu_to_be16(crc_t10dif_update(be16_to_cpu(crc), data, len));
 }
 
-static __be16 t10_pi_ip_fn(void *data, unsigned int len)
+static __be16 t10_pi_ip_fn(__be16 csum, void *data, unsigned int len)
 {
 	return (__force __be16)ip_compute_csum(data, len);
 }
@@ -32,12 +32,16 @@ static __be16 t10_pi_ip_fn(void *data, unsigned int len)
 static blk_status_t t10_pi_generate(struct blk_integrity_iter *iter,
 		csum_fn *fn, enum t10_dif_type type)
 {
+	u8 offset = iter->pi_offset;
 	unsigned int i;
 
 	for (i = 0 ; i < iter->data_size ; i += iter->interval) {
-		struct t10_pi_tuple *pi = iter->prot_buf;
+		struct t10_pi_tuple *pi = iter->prot_buf + offset;
 
-		pi->guard_tag = fn(iter->data_buf, iter->interval);
+		pi->guard_tag = fn(0, iter->data_buf, iter->interval);
+		if (offset)
+			pi->guard_tag = fn(pi->guard_tag, iter->prot_buf,
+					   offset);
 		pi->app_tag = 0;
 
 		if (type == T10_PI_TYPE1_PROTECTION)
@@ -56,12 +60,13 @@ static blk_status_t t10_pi_generate(struct blk_integrity_iter *iter,
 static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
 		csum_fn *fn, enum t10_dif_type type)
 {
+	u8 offset = iter->pi_offset;
 	unsigned int i;
 
 	BUG_ON(type == T10_PI_TYPE0_PROTECTION);
 
 	for (i = 0 ; i < iter->data_size ; i += iter->interval) {
-		struct t10_pi_tuple *pi = iter->prot_buf;
+		struct t10_pi_tuple *pi = iter->prot_buf + offset;
 		__be16 csum;
 
 		if (type == T10_PI_TYPE1_PROTECTION ||
@@ -83,7 +88,9 @@ static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
 				goto next;
 		}
 
-		csum = fn(iter->data_buf, iter->interval);
+		csum = fn(0, iter->data_buf, iter->interval);
+		if (offset)
+			csum = fn(csum, iter->prot_buf, offset);
 
 		if (pi->guard_tag != csum) {
 			pr_err("%s: guard tag error at sector %llu " \
@@ -134,8 +141,10 @@ static blk_status_t t10_pi_type1_verify_ip(struct blk_integrity_iter *iter)
  */
 static void t10_pi_type1_prepare(struct request *rq)
 {
-	const int tuple_sz = rq->q->integrity.tuple_size;
+	struct blk_integrity *bi = &rq->q->integrity;
+	const int tuple_sz = bi->tuple_size;
 	u32 ref_tag = t10_pi_ref_tag(rq);
+	u8 offset = bi->pi_offset;
 	struct bio *bio;
 
 	__rq_for_each_bio(bio, rq) {
@@ -154,7 +163,7 @@ static void t10_pi_type1_prepare(struct request *rq)
 
 			p = bvec_kmap_local(&iv);
 			for (j = 0; j < iv.bv_len; j += tuple_sz) {
-				struct t10_pi_tuple *pi = p;
+				struct t10_pi_tuple *pi = p + offset;
 
 				if (be32_to_cpu(pi->ref_tag) == virt)
 					pi->ref_tag = cpu_to_be32(ref_tag);
@@ -183,9 +192,11 @@ static void t10_pi_type1_prepare(struct request *rq)
  */
 static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 {
-	unsigned intervals = nr_bytes >> rq->q->integrity.interval_exp;
-	const int tuple_sz = rq->q->integrity.tuple_size;
+	struct blk_integrity *bi = &rq->q->integrity;
+	unsigned intervals = nr_bytes >> bi->interval_exp;
+	const int tuple_sz = bi->tuple_size;
 	u32 ref_tag = t10_pi_ref_tag(rq);
+	u8 offset = bi->pi_offset;
 	struct bio *bio;
 
 	__rq_for_each_bio(bio, rq) {
@@ -200,7 +211,7 @@ static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 
 			p = bvec_kmap_local(&iv);
 			for (j = 0; j < iv.bv_len && intervals; j += tuple_sz) {
-				struct t10_pi_tuple *pi = p;
+				struct t10_pi_tuple *pi = p + offset;
 
 				if (be32_to_cpu(pi->ref_tag) == ref_tag)
 					pi->ref_tag = cpu_to_be32(virt);
@@ -280,20 +291,24 @@ const struct blk_integrity_profile t10_pi_type3_ip = {
 };
 EXPORT_SYMBOL(t10_pi_type3_ip);
 
-static __be64 ext_pi_crc64(void *data, unsigned int len)
+static __be64 ext_pi_crc64(u64 crc, void *data, unsigned int len)
 {
-	return cpu_to_be64(crc64_rocksoft(data, len));
+	return cpu_to_be64(crc64_rocksoft_update(crc, data, len));
 }
 
 static blk_status_t ext_pi_crc64_generate(struct blk_integrity_iter *iter,
 					enum t10_dif_type type)
 {
+	u8 offset = iter->pi_offset;
 	unsigned int i;
 
 	for (i = 0 ; i < iter->data_size ; i += iter->interval) {
-		struct crc64_pi_tuple *pi = iter->prot_buf;
+		struct crc64_pi_tuple *pi = iter->prot_buf + offset;
 
-		pi->guard_tag = ext_pi_crc64(iter->data_buf, iter->interval);
+		pi->guard_tag = ext_pi_crc64(0, iter->data_buf, iter->interval);
+		if (offset)
+			pi->guard_tag = ext_pi_crc64(be64_to_cpu(pi->guard_tag),
+					iter->prot_buf, offset);
 		pi->app_tag = 0;
 
 		if (type == T10_PI_TYPE1_PROTECTION)
@@ -319,10 +334,11 @@ static bool ext_pi_ref_escape(u8 *ref_tag)
 static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter,
 				      enum t10_dif_type type)
 {
+	u8 offset = iter->pi_offset;
 	unsigned int i;
 
 	for (i = 0; i < iter->data_size; i += iter->interval) {
-		struct crc64_pi_tuple *pi = iter->prot_buf;
+		struct crc64_pi_tuple *pi = iter->prot_buf + offset;
 		u64 ref, seed;
 		__be64 csum;
 
@@ -343,7 +359,11 @@ static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter,
 				goto next;
 		}
 
-		csum = ext_pi_crc64(iter->data_buf, iter->interval);
+		csum = ext_pi_crc64(0, iter->data_buf, iter->interval);
+		if (offset)
+			csum = ext_pi_crc64(be64_to_cpu(csum), iter->prot_buf,
+					    offset);
+
 		if (pi->guard_tag != csum) {
 			pr_err("%s: guard tag error at sector %llu " \
 			       "(rcvd %016llx, want %016llx)\n",
@@ -373,8 +393,10 @@ static blk_status_t ext_pi_type1_generate_crc64(struct blk_integrity_iter *iter)
 
 static void ext_pi_type1_prepare(struct request *rq)
 {
-	const int tuple_sz = rq->q->integrity.tuple_size;
+	struct blk_integrity *bi = &rq->q->integrity;
+	const int tuple_sz = bi->tuple_size;
 	u64 ref_tag = ext_pi_ref_tag(rq);
+	u8 offset = bi->pi_offset;
 	struct bio *bio;
 
 	__rq_for_each_bio(bio, rq) {
@@ -393,7 +415,7 @@ static void ext_pi_type1_prepare(struct request *rq)
 
 			p = bvec_kmap_local(&iv);
 			for (j = 0; j < iv.bv_len; j += tuple_sz) {
-				struct crc64_pi_tuple *pi = p;
+				struct crc64_pi_tuple *pi = p +  offset;
 				u64 ref = get_unaligned_be48(pi->ref_tag);
 
 				if (ref == virt)
@@ -411,9 +433,11 @@ static void ext_pi_type1_prepare(struct request *rq)
 
 static void ext_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 {
-	unsigned intervals = nr_bytes >> rq->q->integrity.interval_exp;
-	const int tuple_sz = rq->q->integrity.tuple_size;
+	struct blk_integrity *bi = &rq->q->integrity;
+	unsigned intervals = nr_bytes >> bi->interval_exp;
+	const int tuple_sz = bi->tuple_size;
 	u64 ref_tag = ext_pi_ref_tag(rq);
+	u8 offset = bi->pi_offset;
 	struct bio *bio;
 
 	__rq_for_each_bio(bio, rq) {
@@ -428,7 +452,7 @@ static void ext_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 
 			p = bvec_kmap_local(&iv);
 			for (j = 0; j < iv.bv_len && intervals; j += tuple_sz) {
-				struct crc64_pi_tuple *pi = p;
+				struct crc64_pi_tuple *pi = p + offset;
 				u64 ref = get_unaligned_be48(pi->ref_tag);
 
 				if (ref == ref_tag)
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 82c44d4899b9..e24c829d7a01 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -91,13 +91,13 @@ static int hash_sendmsg(struct socket *sock, struct msghdr *msg,
 		if (!(msg->msg_flags & MSG_MORE)) {
 			err = hash_alloc_result(sk, ctx);
 			if (err)
-				goto unlock_free;
+				goto unlock_free_result;
 			ahash_request_set_crypt(&ctx->req, NULL,
 						ctx->result, 0);
 			err = crypto_wait_req(crypto_ahash_final(&ctx->req),
 					      &ctx->wait);
 			if (err)
-				goto unlock_free;
+				goto unlock_free_result;
 		}
 		goto done_more;
 	}
@@ -170,6 +170,7 @@ unlock:
 
 unlock_free:
 	af_alg_free_sg(&ctx->sgl);
+unlock_free_result:
 	hash_free_result(sk, ctx);
 	ctx->more = false;
 	goto unlock;
diff --git a/crypto/cbc.c b/crypto/cbc.c
index eedddef9ce40..e81918ca68b7 100644
--- a/crypto/cbc.c
+++ b/crypto/cbc.c
@@ -148,6 +148,9 @@ static int crypto_cbc_create(struct crypto_template *tmpl, struct rtattr **tb)
 	if (!is_power_of_2(inst->alg.co.base.cra_blocksize))
 		goto out_free_inst;
 
+	if (inst->alg.co.statesize)
+		goto out_free_inst;
+
 	inst->alg.encrypt = crypto_cbc_encrypt;
 	inst->alg.decrypt = crypto_cbc_decrypt;
 
diff --git a/crypto/lskcipher.c b/crypto/lskcipher.c
index 0b6dd8aa21f2..0f1bd7dcde24 100644
--- a/crypto/lskcipher.c
+++ b/crypto/lskcipher.c
@@ -212,13 +212,12 @@ static int crypto_lskcipher_crypt_sg(struct skcipher_request *req,
 
 	ivsize = crypto_lskcipher_ivsize(tfm);
 	ivs = PTR_ALIGN(ivs, crypto_skcipher_alignmask(skcipher) + 1);
+	memcpy(ivs, req->iv, ivsize);
 
 	flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	if (req->base.flags & CRYPTO_SKCIPHER_REQ_CONT)
 		flags |= CRYPTO_LSKCIPHER_FLAG_CONT;
-	else
-		memcpy(ivs, req->iv, ivsize);
 
 	if (!(req->base.flags & CRYPTO_SKCIPHER_REQ_NOTFINAL))
 		flags |= CRYPTO_LSKCIPHER_FLAG_FINAL;
@@ -234,8 +233,7 @@ static int crypto_lskcipher_crypt_sg(struct skcipher_request *req,
 		flags |= CRYPTO_LSKCIPHER_FLAG_CONT;
 	}
 
-	if (flags & CRYPTO_LSKCIPHER_FLAG_FINAL)
-		memcpy(req->iv, ivs, ivsize);
+	memcpy(req->iv, ivs, ivsize);
 
 	return err;
 }
diff --git a/drivers/accel/ivpu/ivpu_debugfs.c b/drivers/accel/ivpu/ivpu_debugfs.c
index 19035230563d..7cb962e21453 100644
--- a/drivers/accel/ivpu/ivpu_debugfs.c
+++ b/drivers/accel/ivpu/ivpu_debugfs.c
@@ -102,7 +102,7 @@ static int reset_pending_show(struct seq_file *s, void *v)
 {
 	struct ivpu_device *vdev = seq_to_ivpu(s);
 
-	seq_printf(s, "%d\n", atomic_read(&vdev->pm->in_reset));
+	seq_printf(s, "%d\n", atomic_read(&vdev->pm->reset_pending));
 	return 0;
 }
 
@@ -130,7 +130,9 @@ dvfs_mode_fops_write(struct file *file, const char __user *user_buf, size_t size
 
 	fw->dvfs_mode = dvfs_mode;
 
-	ivpu_pm_schedule_recovery(vdev);
+	ret = pci_try_reset_function(to_pci_dev(vdev->drm.dev));
+	if (ret)
+		return ret;
 
 	return size;
 }
@@ -190,7 +192,10 @@ fw_profiling_freq_fops_write(struct file *file, const char __user *user_buf,
 		return ret;
 
 	ivpu_hw_profiling_freq_drive(vdev, enable);
-	ivpu_pm_schedule_recovery(vdev);
+
+	ret = pci_try_reset_function(to_pci_dev(vdev->drm.dev));
+	if (ret)
+		return ret;
 
 	return size;
 }
@@ -301,11 +306,18 @@ static ssize_t
 ivpu_force_recovery_fn(struct file *file, const char __user *user_buf, size_t size, loff_t *pos)
 {
 	struct ivpu_device *vdev = file->private_data;
+	int ret;
 
 	if (!size)
 		return -EINVAL;
 
-	ivpu_pm_schedule_recovery(vdev);
+	ret = ivpu_rpm_get(vdev);
+	if (ret)
+		return ret;
+
+	ivpu_pm_trigger_recovery(vdev, "debugfs");
+	flush_work(&vdev->pm->recovery_work);
+	ivpu_rpm_put(vdev);
 	return size;
 }
 
diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 64927682161b..4b0640226986 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -6,6 +6,7 @@
 #include <linux/firmware.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/pm_runtime.h>
 
 #include <drm/drm_accel.h>
 #include <drm/drm_file.h>
@@ -17,6 +18,7 @@
 #include "ivpu_debugfs.h"
 #include "ivpu_drv.h"
 #include "ivpu_fw.h"
+#include "ivpu_fw_log.h"
 #include "ivpu_gem.h"
 #include "ivpu_hw.h"
 #include "ivpu_ipc.h"
@@ -65,22 +67,20 @@ struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv)
 	return file_priv;
 }
 
-struct ivpu_file_priv *ivpu_file_priv_get_by_ctx_id(struct ivpu_device *vdev, unsigned long id)
+static void file_priv_unbind(struct ivpu_device *vdev, struct ivpu_file_priv *file_priv)
 {
-	struct ivpu_file_priv *file_priv;
-
-	xa_lock_irq(&vdev->context_xa);
-	file_priv = xa_load(&vdev->context_xa, id);
-	/* file_priv may still be in context_xa during file_priv_release() */
-	if (file_priv && !kref_get_unless_zero(&file_priv->ref))
-		file_priv = NULL;
-	xa_unlock_irq(&vdev->context_xa);
-
-	if (file_priv)
-		ivpu_dbg(vdev, KREF, "file_priv get by id: ctx %u refcount %u\n",
-			 file_priv->ctx.id, kref_read(&file_priv->ref));
-
-	return file_priv;
+	mutex_lock(&file_priv->lock);
+	if (file_priv->bound) {
+		ivpu_dbg(vdev, FILE, "file_priv unbind: ctx %u\n", file_priv->ctx.id);
+
+		ivpu_cmdq_release_all_locked(file_priv);
+		ivpu_jsm_context_release(vdev, file_priv->ctx.id);
+		ivpu_bo_unbind_all_bos_from_context(vdev, &file_priv->ctx);
+		ivpu_mmu_user_context_fini(vdev, &file_priv->ctx);
+		file_priv->bound = false;
+		drm_WARN_ON(&vdev->drm, !xa_erase_irq(&vdev->context_xa, file_priv->ctx.id));
+	}
+	mutex_unlock(&file_priv->lock);
 }
 
 static void file_priv_release(struct kref *ref)
@@ -88,13 +88,15 @@ static void file_priv_release(struct kref *ref)
 	struct ivpu_file_priv *file_priv = container_of(ref, struct ivpu_file_priv, ref);
 	struct ivpu_device *vdev = file_priv->vdev;
 
-	ivpu_dbg(vdev, FILE, "file_priv release: ctx %u\n", file_priv->ctx.id);
+	ivpu_dbg(vdev, FILE, "file_priv release: ctx %u bound %d\n",
+		 file_priv->ctx.id, (bool)file_priv->bound);
+
+	pm_runtime_get_sync(vdev->drm.dev);
+	mutex_lock(&vdev->context_list_lock);
+	file_priv_unbind(vdev, file_priv);
+	mutex_unlock(&vdev->context_list_lock);
+	pm_runtime_put_autosuspend(vdev->drm.dev);
 
-	ivpu_cmdq_release_all(file_priv);
-	ivpu_jsm_context_release(vdev, file_priv->ctx.id);
-	ivpu_bo_remove_all_bos_from_context(vdev, &file_priv->ctx);
-	ivpu_mmu_user_context_fini(vdev, &file_priv->ctx);
-	drm_WARN_ON(&vdev->drm, xa_erase_irq(&vdev->context_xa, file_priv->ctx.id) != file_priv);
 	mutex_destroy(&file_priv->lock);
 	kfree(file_priv);
 }
@@ -176,9 +178,6 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f
 	case DRM_IVPU_PARAM_CONTEXT_BASE_ADDRESS:
 		args->value = vdev->hw->ranges.user.start;
 		break;
-	case DRM_IVPU_PARAM_CONTEXT_PRIORITY:
-		args->value = file_priv->priority;
-		break;
 	case DRM_IVPU_PARAM_CONTEXT_ID:
 		args->value = file_priv->ctx.id;
 		break;
@@ -218,17 +217,10 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f
 
 static int ivpu_set_param_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 {
-	struct ivpu_file_priv *file_priv = file->driver_priv;
 	struct drm_ivpu_param *args = data;
 	int ret = 0;
 
 	switch (args->param) {
-	case DRM_IVPU_PARAM_CONTEXT_PRIORITY:
-		if (args->value <= DRM_IVPU_CONTEXT_PRIORITY_REALTIME)
-			file_priv->priority = args->value;
-		else
-			ret = -EINVAL;
-		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -241,50 +233,53 @@ static int ivpu_open(struct drm_device *dev, struct drm_file *file)
 	struct ivpu_device *vdev = to_ivpu_device(dev);
 	struct ivpu_file_priv *file_priv;
 	u32 ctx_id;
-	void *old;
-	int ret;
+	int idx, ret;
 
-	ret = xa_alloc_irq(&vdev->context_xa, &ctx_id, NULL, vdev->context_xa_limit, GFP_KERNEL);
-	if (ret) {
-		ivpu_err(vdev, "Failed to allocate context id: %d\n", ret);
-		return ret;
-	}
+	if (!drm_dev_enter(dev, &idx))
+		return -ENODEV;
 
 	file_priv = kzalloc(sizeof(*file_priv), GFP_KERNEL);
 	if (!file_priv) {
 		ret = -ENOMEM;
-		goto err_xa_erase;
+		goto err_dev_exit;
 	}
 
 	file_priv->vdev = vdev;
-	file_priv->priority = DRM_IVPU_CONTEXT_PRIORITY_NORMAL;
+	file_priv->bound = true;
 	kref_init(&file_priv->ref);
 	mutex_init(&file_priv->lock);
 
+	mutex_lock(&vdev->context_list_lock);
+
+	ret = xa_alloc_irq(&vdev->context_xa, &ctx_id, file_priv,
+			   vdev->context_xa_limit, GFP_KERNEL);
+	if (ret) {
+		ivpu_err(vdev, "Failed to allocate context id: %d\n", ret);
+		goto err_unlock;
+	}
+
 	ret = ivpu_mmu_user_context_init(vdev, &file_priv->ctx, ctx_id);
 	if (ret)
-		goto err_mutex_destroy;
+		goto err_xa_erase;
 
-	old = xa_store_irq(&vdev->context_xa, ctx_id, file_priv, GFP_KERNEL);
-	if (xa_is_err(old)) {
-		ret = xa_err(old);
-		ivpu_err(vdev, "Failed to store context %u: %d\n", ctx_id, ret);
-		goto err_ctx_fini;
-	}
+	mutex_unlock(&vdev->context_list_lock);
+	drm_dev_exit(idx);
+
+	file->driver_priv = file_priv;
 
 	ivpu_dbg(vdev, FILE, "file_priv create: ctx %u process %s pid %d\n",
 		 ctx_id, current->comm, task_pid_nr(current));
 
-	file->driver_priv = file_priv;
 	return 0;
 
-err_ctx_fini:
-	ivpu_mmu_user_context_fini(vdev, &file_priv->ctx);
-err_mutex_destroy:
-	mutex_destroy(&file_priv->lock);
-	kfree(file_priv);
 err_xa_erase:
 	xa_erase_irq(&vdev->context_xa, ctx_id);
+err_unlock:
+	mutex_unlock(&vdev->context_list_lock);
+	mutex_destroy(&file_priv->lock);
+	kfree(file_priv);
+err_dev_exit:
+	drm_dev_exit(idx);
 	return ret;
 }
 
@@ -340,8 +335,6 @@ static int ivpu_wait_for_ready(struct ivpu_device *vdev)
 
 	if (!ret)
 		ivpu_dbg(vdev, PM, "VPU ready message received successfully\n");
-	else
-		ivpu_hw_diagnose_failure(vdev);
 
 	return ret;
 }
@@ -369,6 +362,9 @@ int ivpu_boot(struct ivpu_device *vdev)
 	ret = ivpu_wait_for_ready(vdev);
 	if (ret) {
 		ivpu_err(vdev, "Failed to boot the firmware: %d\n", ret);
+		ivpu_hw_diagnose_failure(vdev);
+		ivpu_mmu_evtq_dump(vdev);
+		ivpu_fw_log_dump(vdev);
 		return ret;
 	}
 
@@ -484,9 +480,8 @@ static int ivpu_pci_init(struct ivpu_device *vdev)
 	/* Clear any pending errors */
 	pcie_capability_clear_word(pdev, PCI_EXP_DEVSTA, 0x3f);
 
-	/* VPU 37XX does not require 10m D3hot delay */
-	if (ivpu_hw_gen(vdev) == IVPU_HW_37XX)
-		pdev->d3hot_delay = 0;
+	/* NPU does not require 10m D3hot delay */
+	pdev->d3hot_delay = 0;
 
 	ret = pcim_enable_device(pdev);
 	if (ret) {
@@ -540,6 +535,10 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 	lockdep_set_class(&vdev->submitted_jobs_xa.xa_lock, &submitted_jobs_xa_lock_class_key);
 	INIT_LIST_HEAD(&vdev->bo_list);
 
+	ret = drmm_mutex_init(&vdev->drm, &vdev->context_list_lock);
+	if (ret)
+		goto err_xa_destroy;
+
 	ret = drmm_mutex_init(&vdev->drm, &vdev->bo_list_lock);
 	if (ret)
 		goto err_xa_destroy;
@@ -611,14 +610,30 @@ err_xa_destroy:
 	return ret;
 }
 
+static void ivpu_bo_unbind_all_user_contexts(struct ivpu_device *vdev)
+{
+	struct ivpu_file_priv *file_priv;
+	unsigned long ctx_id;
+
+	mutex_lock(&vdev->context_list_lock);
+
+	xa_for_each(&vdev->context_xa, ctx_id, file_priv)
+		file_priv_unbind(vdev, file_priv);
+
+	mutex_unlock(&vdev->context_list_lock);
+}
+
 static void ivpu_dev_fini(struct ivpu_device *vdev)
 {
 	ivpu_pm_disable(vdev);
 	ivpu_shutdown(vdev);
 	if (IVPU_WA(d3hot_after_power_off))
 		pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
+
+	ivpu_jobs_abort_all(vdev);
 	ivpu_job_done_consumer_fini(vdev);
 	ivpu_pm_cancel_recovery(vdev);
+	ivpu_bo_unbind_all_user_contexts(vdev);
 
 	ivpu_ipc_fini(vdev);
 	ivpu_fw_fini(vdev);
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index ebc4b84f27b2..069ace4adb2d 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -56,6 +56,7 @@
 #define IVPU_DBG_JSM	 BIT(10)
 #define IVPU_DBG_KREF	 BIT(11)
 #define IVPU_DBG_RPM	 BIT(12)
+#define IVPU_DBG_MMU_MAP BIT(13)
 
 #define ivpu_err(vdev, fmt, ...) \
 	drm_err(&(vdev)->drm, "%s(): " fmt, __func__, ##__VA_ARGS__)
@@ -114,6 +115,7 @@ struct ivpu_device {
 
 	struct ivpu_mmu_context gctx;
 	struct ivpu_mmu_context rctx;
+	struct mutex context_list_lock; /* Protects user context addition/removal */
 	struct xarray context_xa;
 	struct xa_limit context_xa_limit;
 
@@ -145,8 +147,8 @@ struct ivpu_file_priv {
 	struct mutex lock; /* Protects cmdq */
 	struct ivpu_cmdq *cmdq[IVPU_NUM_ENGINES];
 	struct ivpu_mmu_context ctx;
-	u32 priority;
 	bool has_mmu_faults;
+	bool bound;
 };
 
 extern int ivpu_dbg_mask;
@@ -162,7 +164,6 @@ extern bool ivpu_disable_mmu_cont_pages;
 extern int ivpu_test_mode;
 
 struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv);
-struct ivpu_file_priv *ivpu_file_priv_get_by_ctx_id(struct ivpu_device *vdev, unsigned long id);
 void ivpu_file_priv_put(struct ivpu_file_priv **link);
 
 int ivpu_boot(struct ivpu_device *vdev);
diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index 6576232f3e67..5fa8bd4603d5 100644
--- a/drivers/accel/ivpu/ivpu_fw.c
+++ b/drivers/accel/ivpu/ivpu_fw.c
@@ -222,7 +222,6 @@ ivpu_fw_init_wa(struct ivpu_device *vdev)
 	const struct vpu_firmware_header *fw_hdr = (const void *)vdev->fw->file->data;
 
 	if (IVPU_FW_CHECK_API_VER_LT(vdev, fw_hdr, BOOT, 3, 17) ||
-	    (ivpu_hw_gen(vdev) > IVPU_HW_37XX) ||
 	    (ivpu_test_mode & IVPU_TEST_MODE_D0I3_MSG_DISABLE))
 		vdev->wa.disable_d0i3_msg = true;
 
diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c
index 1dda4f38ea25..e9ddbe9f50eb 100644
--- a/drivers/accel/ivpu/ivpu_gem.c
+++ b/drivers/accel/ivpu/ivpu_gem.c
@@ -24,14 +24,11 @@ static const struct drm_gem_object_funcs ivpu_gem_funcs;
 
 static inline void ivpu_dbg_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, const char *action)
 {
-	if (bo->ctx)
-		ivpu_dbg(vdev, BO, "%6s: size %zu has_pages %d dma_mapped %d handle %u ctx %d vpu_addr 0x%llx mmu_mapped %d\n",
-			 action, ivpu_bo_size(bo), (bool)bo->base.pages, (bool)bo->base.sgt,
-			 bo->handle, bo->ctx->id, bo->vpu_addr, bo->mmu_mapped);
-	else
-		ivpu_dbg(vdev, BO, "%6s: size %zu has_pages %d dma_mapped %d handle %u (not added to context)\n",
-			 action, ivpu_bo_size(bo), (bool)bo->base.pages, (bool)bo->base.sgt,
-			 bo->handle);
+	ivpu_dbg(vdev, BO,
+		 "%6s: bo %8p vpu_addr %9llx size %8zu ctx %d has_pages %d dma_mapped %d mmu_mapped %d wc %d imported %d\n",
+		 action, bo, bo->vpu_addr, ivpu_bo_size(bo), bo->ctx ? bo->ctx->id : 0,
+		 (bool)bo->base.pages, (bool)bo->base.sgt, bo->mmu_mapped, bo->base.map_wc,
+		 (bool)bo->base.base.import_attach);
 }
 
 /*
@@ -49,12 +46,7 @@ int __must_check ivpu_bo_pin(struct ivpu_bo *bo)
 	mutex_lock(&bo->lock);
 
 	ivpu_dbg_bo(vdev, bo, "pin");
-
-	if (!bo->ctx) {
-		ivpu_err(vdev, "vpu_addr not allocated for BO %d\n", bo->handle);
-		ret = -EINVAL;
-		goto unlock;
-	}
+	drm_WARN_ON(&vdev->drm, !bo->ctx);
 
 	if (!bo->mmu_mapped) {
 		struct sg_table *sgt = drm_gem_shmem_get_pages_sgt(&bo->base);
@@ -85,7 +77,10 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx,
 		       const struct ivpu_addr_range *range)
 {
 	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
-	int ret;
+	int idx, ret;
+
+	if (!drm_dev_enter(&vdev->drm, &idx))
+		return -ENODEV;
 
 	mutex_lock(&bo->lock);
 
@@ -101,6 +96,8 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx,
 
 	mutex_unlock(&bo->lock);
 
+	drm_dev_exit(idx);
+
 	return ret;
 }
 
@@ -108,11 +105,7 @@ static void ivpu_bo_unbind_locked(struct ivpu_bo *bo)
 {
 	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
 
-	lockdep_assert_held(&bo->lock);
-
-	ivpu_dbg_bo(vdev, bo, "unbind");
-
-	/* TODO: dma_unmap */
+	lockdep_assert(lockdep_is_held(&bo->lock) || !kref_read(&bo->base.base.refcount));
 
 	if (bo->mmu_mapped) {
 		drm_WARN_ON(&vdev->drm, !bo->ctx);
@@ -124,19 +117,23 @@ static void ivpu_bo_unbind_locked(struct ivpu_bo *bo)
 
 	if (bo->ctx) {
 		ivpu_mmu_context_remove_node(bo->ctx, &bo->mm_node);
-		bo->vpu_addr = 0;
 		bo->ctx = NULL;
 	}
-}
 
-static void ivpu_bo_unbind(struct ivpu_bo *bo)
-{
-	mutex_lock(&bo->lock);
-	ivpu_bo_unbind_locked(bo);
-	mutex_unlock(&bo->lock);
+	if (bo->base.base.import_attach)
+		return;
+
+	dma_resv_lock(bo->base.base.resv, NULL);
+	if (bo->base.sgt) {
+		dma_unmap_sgtable(vdev->drm.dev, bo->base.sgt, DMA_BIDIRECTIONAL, 0);
+		sg_free_table(bo->base.sgt);
+		kfree(bo->base.sgt);
+		bo->base.sgt = NULL;
+	}
+	dma_resv_unlock(bo->base.base.resv);
 }
 
-void ivpu_bo_remove_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx)
+void ivpu_bo_unbind_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx)
 {
 	struct ivpu_bo *bo;
 
@@ -146,8 +143,10 @@ void ivpu_bo_remove_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_m
 	mutex_lock(&vdev->bo_list_lock);
 	list_for_each_entry(bo, &vdev->bo_list, bo_list_node) {
 		mutex_lock(&bo->lock);
-		if (bo->ctx == ctx)
+		if (bo->ctx == ctx) {
+			ivpu_dbg_bo(vdev, bo, "unbind");
 			ivpu_bo_unbind_locked(bo);
+		}
 		mutex_unlock(&bo->lock);
 	}
 	mutex_unlock(&vdev->bo_list_lock);
@@ -199,9 +198,6 @@ ivpu_bo_create(struct ivpu_device *vdev, u64 size, u32 flags)
 	list_add_tail(&bo->bo_list_node, &vdev->bo_list);
 	mutex_unlock(&vdev->bo_list_lock);
 
-	ivpu_dbg(vdev, BO, "create: vpu_addr 0x%llx size %zu flags 0x%x\n",
-		 bo->vpu_addr, bo->base.base.size, flags);
-
 	return bo;
 }
 
@@ -212,6 +208,12 @@ static int ivpu_bo_open(struct drm_gem_object *obj, struct drm_file *file)
 	struct ivpu_bo *bo = to_ivpu_bo(obj);
 	struct ivpu_addr_range *range;
 
+	if (bo->ctx) {
+		ivpu_warn(vdev, "Can't add BO to ctx %u: already in ctx %u\n",
+			  file_priv->ctx.id, bo->ctx->id);
+		return -EALREADY;
+	}
+
 	if (bo->flags & DRM_IVPU_BO_SHAVE_MEM)
 		range = &vdev->hw->ranges.shave;
 	else if (bo->flags & DRM_IVPU_BO_DMA_MEM)
@@ -227,62 +229,24 @@ static void ivpu_bo_free(struct drm_gem_object *obj)
 	struct ivpu_device *vdev = to_ivpu_device(obj->dev);
 	struct ivpu_bo *bo = to_ivpu_bo(obj);
 
+	ivpu_dbg_bo(vdev, bo, "free");
+
 	mutex_lock(&vdev->bo_list_lock);
 	list_del(&bo->bo_list_node);
 	mutex_unlock(&vdev->bo_list_lock);
 
 	drm_WARN_ON(&vdev->drm, !dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ));
 
-	ivpu_dbg_bo(vdev, bo, "free");
-
-	ivpu_bo_unbind(bo);
+	ivpu_bo_unbind_locked(bo);
 	mutex_destroy(&bo->lock);
 
 	drm_WARN_ON(obj->dev, bo->base.pages_use_count > 1);
 	drm_gem_shmem_free(&bo->base);
 }
 
-static const struct dma_buf_ops ivpu_bo_dmabuf_ops =  {
-	.cache_sgt_mapping = true,
-	.attach = drm_gem_map_attach,
-	.detach = drm_gem_map_detach,
-	.map_dma_buf = drm_gem_map_dma_buf,
-	.unmap_dma_buf = drm_gem_unmap_dma_buf,
-	.release = drm_gem_dmabuf_release,
-	.mmap = drm_gem_dmabuf_mmap,
-	.vmap = drm_gem_dmabuf_vmap,
-	.vunmap = drm_gem_dmabuf_vunmap,
-};
-
-static struct dma_buf *ivpu_bo_export(struct drm_gem_object *obj, int flags)
-{
-	struct drm_device *dev = obj->dev;
-	struct dma_buf_export_info exp_info = {
-		.exp_name = KBUILD_MODNAME,
-		.owner = dev->driver->fops->owner,
-		.ops = &ivpu_bo_dmabuf_ops,
-		.size = obj->size,
-		.flags = flags,
-		.priv = obj,
-		.resv = obj->resv,
-	};
-	void *sgt;
-
-	/*
-	 * Make sure that pages are allocated and dma-mapped before exporting the bo.
-	 * DMA-mapping is required if the bo will be imported to the same device.
-	 */
-	sgt = drm_gem_shmem_get_pages_sgt(to_drm_gem_shmem_obj(obj));
-	if (IS_ERR(sgt))
-		return sgt;
-
-	return drm_gem_dmabuf_export(dev, &exp_info);
-}
-
 static const struct drm_gem_object_funcs ivpu_gem_funcs = {
 	.free = ivpu_bo_free,
 	.open = ivpu_bo_open,
-	.export = ivpu_bo_export,
 	.print_info = drm_gem_shmem_object_print_info,
 	.pin = drm_gem_shmem_object_pin,
 	.unpin = drm_gem_shmem_object_unpin,
@@ -315,11 +279,9 @@ int ivpu_bo_create_ioctl(struct drm_device *dev, void *data, struct drm_file *fi
 		return PTR_ERR(bo);
 	}
 
-	ret = drm_gem_handle_create(file, &bo->base.base, &bo->handle);
-	if (!ret) {
+	ret = drm_gem_handle_create(file, &bo->base.base, &args->handle);
+	if (!ret)
 		args->vpu_addr = bo->vpu_addr;
-		args->handle = bo->handle;
-	}
 
 	drm_gem_object_put(&bo->base.base);
 
@@ -361,7 +323,9 @@ ivpu_bo_alloc_internal(struct ivpu_device *vdev, u64 vpu_addr, u64 size, u32 fla
 	if (ret)
 		goto err_put;
 
+	dma_resv_lock(bo->base.base.resv, NULL);
 	ret = drm_gem_shmem_vmap(&bo->base, &map);
+	dma_resv_unlock(bo->base.base.resv);
 	if (ret)
 		goto err_put;
 
@@ -376,7 +340,10 @@ void ivpu_bo_free_internal(struct ivpu_bo *bo)
 {
 	struct iosys_map map = IOSYS_MAP_INIT_VADDR(bo->base.vaddr);
 
+	dma_resv_lock(bo->base.base.resv, NULL);
 	drm_gem_shmem_vunmap(&bo->base, &map);
+	dma_resv_unlock(bo->base.base.resv);
+
 	drm_gem_object_put(&bo->base.base);
 }
 
@@ -432,19 +399,11 @@ int ivpu_bo_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 
 static void ivpu_bo_print_info(struct ivpu_bo *bo, struct drm_printer *p)
 {
-	unsigned long dma_refcount = 0;
-
 	mutex_lock(&bo->lock);
 
-	if (bo->base.base.dma_buf && bo->base.base.dma_buf->file)
-		dma_refcount = atomic_long_read(&bo->base.base.dma_buf->file->f_count);
-
-	drm_printf(p, "%-3u %-6d 0x%-12llx %-10lu 0x%-8x %-4u %-8lu",
-		   bo->ctx->id, bo->handle, bo->vpu_addr, bo->base.base.size,
-		   bo->flags, kref_read(&bo->base.base.refcount), dma_refcount);
-
-	if (bo->base.base.import_attach)
-		drm_printf(p, " imported");
+	drm_printf(p, "%-9p %-3u 0x%-12llx %-10lu 0x%-8x %-4u",
+		   bo, bo->ctx->id, bo->vpu_addr, bo->base.base.size,
+		   bo->flags, kref_read(&bo->base.base.refcount));
 
 	if (bo->base.pages)
 		drm_printf(p, " has_pages");
@@ -452,6 +411,9 @@ static void ivpu_bo_print_info(struct ivpu_bo *bo, struct drm_printer *p)
 	if (bo->mmu_mapped)
 		drm_printf(p, " mmu_mapped");
 
+	if (bo->base.base.import_attach)
+		drm_printf(p, " imported");
+
 	drm_printf(p, "\n");
 
 	mutex_unlock(&bo->lock);
@@ -462,8 +424,8 @@ void ivpu_bo_list(struct drm_device *dev, struct drm_printer *p)
 	struct ivpu_device *vdev = to_ivpu_device(dev);
 	struct ivpu_bo *bo;
 
-	drm_printf(p, "%-3s %-6s %-14s %-10s %-10s %-4s %-8s %s\n",
-		   "ctx", "handle", "vpu_addr", "size", "flags", "refs", "dma_refs", "attribs");
+	drm_printf(p, "%-9s %-3s %-14s %-10s %-10s %-4s %s\n",
+		   "bo", "ctx", "vpu_addr", "size", "flags", "refs", "attribs");
 
 	mutex_lock(&vdev->bo_list_lock);
 	list_for_each_entry(bo, &vdev->bo_list, bo_list_node)
diff --git a/drivers/accel/ivpu/ivpu_gem.h b/drivers/accel/ivpu/ivpu_gem.h
index d75cad0d3c74..a8559211c70d 100644
--- a/drivers/accel/ivpu/ivpu_gem.h
+++ b/drivers/accel/ivpu/ivpu_gem.h
@@ -19,14 +19,13 @@ struct ivpu_bo {
 
 	struct mutex lock; /* Protects: ctx, mmu_mapped, vpu_addr */
 	u64 vpu_addr;
-	u32 handle;
 	u32 flags;
 	u32 job_status; /* Valid only for command buffer */
 	bool mmu_mapped;
 };
 
 int ivpu_bo_pin(struct ivpu_bo *bo);
-void ivpu_bo_remove_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx);
+void ivpu_bo_unbind_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx);
 
 struct drm_gem_object *ivpu_gem_create_object(struct drm_device *dev, size_t size);
 struct ivpu_bo *ivpu_bo_alloc_internal(struct ivpu_device *vdev, u64 vpu_addr, u64 size, u32 flags);
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index 574cdeefb66b..89af1006df55 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -510,22 +510,12 @@ static int ivpu_boot_pwr_domain_enable(struct ivpu_device *vdev)
 	return ret;
 }
 
-static int ivpu_boot_pwr_domain_disable(struct ivpu_device *vdev)
-{
-	ivpu_boot_dpu_active_drive(vdev, false);
-	ivpu_boot_pwr_island_isolation_drive(vdev, true);
-	ivpu_boot_pwr_island_trickle_drive(vdev, false);
-	ivpu_boot_pwr_island_drive(vdev, false);
-
-	return ivpu_boot_wait_for_pwr_island_status(vdev, 0x0);
-}
-
 static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
 {
 	u32 val = REGV_RD32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES);
 
 	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, NOSNOOP_OVERRIDE_EN, val);
-	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val);
+	val = REG_CLR_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val);
 	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AR_NOSNOOP_OVERRIDE, val);
 
 	REGV_WR32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, val);
@@ -616,12 +606,37 @@ static int ivpu_hw_37xx_info_init(struct ivpu_device *vdev)
 	return 0;
 }
 
+static int ivpu_hw_37xx_ip_reset(struct ivpu_device *vdev)
+{
+	int ret;
+	u32 val;
+
+	if (IVPU_WA(punit_disabled))
+		return 0;
+
+	ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US);
+	if (ret) {
+		ivpu_err(vdev, "Timed out waiting for TRIGGER bit\n");
+		return ret;
+	}
+
+	val = REGB_RD32(VPU_37XX_BUTTRESS_VPU_IP_RESET);
+	val = REG_SET_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, val);
+	REGB_WR32(VPU_37XX_BUTTRESS_VPU_IP_RESET, val);
+
+	ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US);
+	if (ret)
+		ivpu_err(vdev, "Timed out waiting for RESET completion\n");
+
+	return ret;
+}
+
 static int ivpu_hw_37xx_reset(struct ivpu_device *vdev)
 {
 	int ret = 0;
 
-	if (ivpu_boot_pwr_domain_disable(vdev)) {
-		ivpu_err(vdev, "Failed to disable power domain\n");
+	if (ivpu_hw_37xx_ip_reset(vdev)) {
+		ivpu_err(vdev, "Failed to reset NPU\n");
 		ret = -EIO;
 	}
 
@@ -661,6 +676,11 @@ static int ivpu_hw_37xx_power_up(struct ivpu_device *vdev)
 {
 	int ret;
 
+	/* PLL requests may fail when powering down, so issue WP 0 here */
+	ret = ivpu_pll_disable(vdev);
+	if (ret)
+		ivpu_warn(vdev, "Failed to disable PLL: %d\n", ret);
+
 	ret = ivpu_hw_37xx_d0i3_disable(vdev);
 	if (ret)
 		ivpu_warn(vdev, "Failed to disable D0I3: %d\n", ret);
@@ -875,24 +895,18 @@ static void ivpu_hw_37xx_irq_disable(struct ivpu_device *vdev)
 
 static void ivpu_hw_37xx_irq_wdt_nce_handler(struct ivpu_device *vdev)
 {
-	ivpu_err_ratelimited(vdev, "WDT NCE irq\n");
-
-	ivpu_pm_schedule_recovery(vdev);
+	ivpu_pm_trigger_recovery(vdev, "WDT NCE IRQ");
 }
 
 static void ivpu_hw_37xx_irq_wdt_mss_handler(struct ivpu_device *vdev)
 {
-	ivpu_err_ratelimited(vdev, "WDT MSS irq\n");
-
 	ivpu_hw_wdt_disable(vdev);
-	ivpu_pm_schedule_recovery(vdev);
+	ivpu_pm_trigger_recovery(vdev, "WDT MSS IRQ");
 }
 
 static void ivpu_hw_37xx_irq_noc_firewall_handler(struct ivpu_device *vdev)
 {
-	ivpu_err_ratelimited(vdev, "NOC Firewall irq\n");
-
-	ivpu_pm_schedule_recovery(vdev);
+	ivpu_pm_trigger_recovery(vdev, "NOC Firewall IRQ");
 }
 
 /* Handler for IRQs from VPU core (irqV) */
@@ -970,7 +984,7 @@ static bool ivpu_hw_37xx_irqb_handler(struct ivpu_device *vdev, int irq)
 		REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, status);
 
 	if (schedule_recovery)
-		ivpu_pm_schedule_recovery(vdev);
+		ivpu_pm_trigger_recovery(vdev, "Buttress IRQ");
 
 	return true;
 }
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index eba2fdef2ace..a1523d0b1ef3 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -24,7 +24,7 @@
 #define SKU_HW_ID_SHIFT              16u
 #define SKU_HW_ID_MASK               0xffff0000u
 
-#define PLL_CONFIG_DEFAULT           0x1
+#define PLL_CONFIG_DEFAULT           0x0
 #define PLL_CDYN_DEFAULT             0x80
 #define PLL_EPP_DEFAULT              0x80
 #define PLL_REF_CLK_FREQ	     (50 * 1000000)
@@ -530,7 +530,7 @@ static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
 	u32 val = REGV_RD32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES);
 
 	val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, SNOOP_OVERRIDE_EN, val);
-	val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val);
+	val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val);
 	val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AR_SNOOP_OVERRIDE, val);
 
 	REGV_WR32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, val);
@@ -704,7 +704,6 @@ static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev)
 {
 	struct ivpu_hw_info *hw = vdev->hw;
 	u32 tile_disable;
-	u32 tile_enable;
 	u32 fuse;
 
 	fuse = REGB_RD32(VPU_40XX_BUTTRESS_TILE_FUSE);
@@ -725,10 +724,6 @@ static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev)
 	else
 		ivpu_dbg(vdev, MISC, "Fuse: All %d tiles enabled\n", TILE_MAX_NUM);
 
-	tile_enable = (~tile_disable) & TILE_MAX_MASK;
-
-	hw->sku = REG_SET_FLD_NUM(SKU, HW_ID, LNL_HW_ID, hw->sku);
-	hw->sku = REG_SET_FLD_NUM(SKU, TILE, tile_enable, hw->sku);
 	hw->tile_fuse = tile_disable;
 	hw->pll.profiling_freq = PLL_PROFILING_FREQ_DEFAULT;
 
@@ -746,7 +741,7 @@ static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev)
 	return 0;
 }
 
-static int ivpu_hw_40xx_reset(struct ivpu_device *vdev)
+static int ivpu_hw_40xx_ip_reset(struct ivpu_device *vdev)
 {
 	int ret;
 	u32 val;
@@ -768,6 +763,23 @@ static int ivpu_hw_40xx_reset(struct ivpu_device *vdev)
 	return ret;
 }
 
+static int ivpu_hw_40xx_reset(struct ivpu_device *vdev)
+{
+	int ret = 0;
+
+	if (ivpu_hw_40xx_ip_reset(vdev)) {
+		ivpu_err(vdev, "Failed to reset VPU IP\n");
+		ret = -EIO;
+	}
+
+	if (ivpu_pll_disable(vdev)) {
+		ivpu_err(vdev, "Failed to disable PLL\n");
+		ret = -EIO;
+	}
+
+	return ret;
+}
+
 static int ivpu_hw_40xx_d0i3_enable(struct ivpu_device *vdev)
 {
 	int ret;
@@ -913,7 +925,7 @@ static int ivpu_hw_40xx_power_down(struct ivpu_device *vdev)
 
 	ivpu_hw_40xx_save_d0i3_entry_timestamp(vdev);
 
-	if (!ivpu_hw_40xx_is_idle(vdev) && ivpu_hw_40xx_reset(vdev))
+	if (!ivpu_hw_40xx_is_idle(vdev) && ivpu_hw_40xx_ip_reset(vdev))
 		ivpu_warn(vdev, "Failed to reset the VPU\n");
 
 	if (ivpu_pll_disable(vdev)) {
@@ -1032,18 +1044,18 @@ static void ivpu_hw_40xx_irq_disable(struct ivpu_device *vdev)
 static void ivpu_hw_40xx_irq_wdt_nce_handler(struct ivpu_device *vdev)
 {
 	/* TODO: For LNN hang consider engine reset instead of full recovery */
-	ivpu_pm_schedule_recovery(vdev);
+	ivpu_pm_trigger_recovery(vdev, "WDT NCE IRQ");
 }
 
 static void ivpu_hw_40xx_irq_wdt_mss_handler(struct ivpu_device *vdev)
 {
 	ivpu_hw_wdt_disable(vdev);
-	ivpu_pm_schedule_recovery(vdev);
+	ivpu_pm_trigger_recovery(vdev, "WDT MSS IRQ");
 }
 
 static void ivpu_hw_40xx_irq_noc_firewall_handler(struct ivpu_device *vdev)
 {
-	ivpu_pm_schedule_recovery(vdev);
+	ivpu_pm_trigger_recovery(vdev, "NOC Firewall IRQ");
 }
 
 /* Handler for IRQs from VPU core (irqV) */
@@ -1137,7 +1149,7 @@ static bool ivpu_hw_40xx_irqb_handler(struct ivpu_device *vdev, int irq)
 	REGB_WR32(VPU_40XX_BUTTRESS_INTERRUPT_STAT, status);
 
 	if (schedule_recovery)
-		ivpu_pm_schedule_recovery(vdev);
+		ivpu_pm_trigger_recovery(vdev, "Buttress IRQ");
 
 	return true;
 }
diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c
index e86621f16f85..fa66c39b57ec 100644
--- a/drivers/accel/ivpu/ivpu_ipc.c
+++ b/drivers/accel/ivpu/ivpu_ipc.c
@@ -343,10 +343,8 @@ int ivpu_ipc_send_receive_active(struct ivpu_device *vdev, struct vpu_jsm_msg *r
 	hb_ret = ivpu_ipc_send_receive_internal(vdev, &hb_req, VPU_JSM_MSG_QUERY_ENGINE_HB_DONE,
 						&hb_resp, VPU_IPC_CHAN_ASYNC_CMD,
 						vdev->timeout.jsm);
-	if (hb_ret == -ETIMEDOUT) {
-		ivpu_hw_diagnose_failure(vdev);
-		ivpu_pm_schedule_recovery(vdev);
-	}
+	if (hb_ret == -ETIMEDOUT)
+		ivpu_pm_trigger_recovery(vdev, "IPC timeout");
 
 	return ret;
 }
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 7206cf9cdb4a..e70cfb859339 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -112,22 +112,20 @@ static void ivpu_cmdq_release_locked(struct ivpu_file_priv *file_priv, u16 engin
 	}
 }
 
-void ivpu_cmdq_release_all(struct ivpu_file_priv *file_priv)
+void ivpu_cmdq_release_all_locked(struct ivpu_file_priv *file_priv)
 {
 	int i;
 
-	mutex_lock(&file_priv->lock);
+	lockdep_assert_held(&file_priv->lock);
 
 	for (i = 0; i < IVPU_NUM_ENGINES; i++)
 		ivpu_cmdq_release_locked(file_priv, i);
-
-	mutex_unlock(&file_priv->lock);
 }
 
 /*
  * Mark the doorbell as unregistered and reset job queue pointers.
  * This function needs to be called when the VPU hardware is restarted
- * and FW looses job queue state. The next time job queue is used it
+ * and FW loses job queue state. The next time job queue is used it
  * will be registered again.
  */
 static void ivpu_cmdq_reset_locked(struct ivpu_file_priv *file_priv, u16 engine)
@@ -161,15 +159,13 @@ void ivpu_cmdq_reset_all_contexts(struct ivpu_device *vdev)
 	struct ivpu_file_priv *file_priv;
 	unsigned long ctx_id;
 
-	xa_for_each(&vdev->context_xa, ctx_id, file_priv) {
-		file_priv = ivpu_file_priv_get_by_ctx_id(vdev, ctx_id);
-		if (!file_priv)
-			continue;
+	mutex_lock(&vdev->context_list_lock);
 
+	xa_for_each(&vdev->context_xa, ctx_id, file_priv)
 		ivpu_cmdq_reset_all(file_priv);
 
-		ivpu_file_priv_put(&file_priv);
-	}
+	mutex_unlock(&vdev->context_list_lock);
+
 }
 
 static int ivpu_cmdq_push_job(struct ivpu_cmdq *cmdq, struct ivpu_job *job)
@@ -243,60 +239,32 @@ static struct dma_fence *ivpu_fence_create(struct ivpu_device *vdev)
 	return &fence->base;
 }
 
-static void job_get(struct ivpu_job *job, struct ivpu_job **link)
+static void ivpu_job_destroy(struct ivpu_job *job)
 {
 	struct ivpu_device *vdev = job->vdev;
-
-	kref_get(&job->ref);
-	*link = job;
-
-	ivpu_dbg(vdev, KREF, "Job get: id %u refcount %u\n", job->job_id, kref_read(&job->ref));
-}
-
-static void job_release(struct kref *ref)
-{
-	struct ivpu_job *job = container_of(ref, struct ivpu_job, ref);
-	struct ivpu_device *vdev = job->vdev;
 	u32 i;
 
+	ivpu_dbg(vdev, JOB, "Job destroyed: id %3u ctx %2d engine %d",
+		 job->job_id, job->file_priv->ctx.id, job->engine_idx);
+
 	for (i = 0; i < job->bo_count; i++)
 		if (job->bos[i])
 			drm_gem_object_put(&job->bos[i]->base.base);
 
 	dma_fence_put(job->done_fence);
 	ivpu_file_priv_put(&job->file_priv);
-
-	ivpu_dbg(vdev, KREF, "Job released: id %u\n", job->job_id);
 	kfree(job);
-
-	/* Allow the VPU to get suspended, must be called after ivpu_file_priv_put() */
-	ivpu_rpm_put(vdev);
-}
-
-static void job_put(struct ivpu_job *job)
-{
-	struct ivpu_device *vdev = job->vdev;
-
-	ivpu_dbg(vdev, KREF, "Job put: id %u refcount %u\n", job->job_id, kref_read(&job->ref));
-	kref_put(&job->ref, job_release);
 }
 
 static struct ivpu_job *
-ivpu_create_job(struct ivpu_file_priv *file_priv, u32 engine_idx, u32 bo_count)
+ivpu_job_create(struct ivpu_file_priv *file_priv, u32 engine_idx, u32 bo_count)
 {
 	struct ivpu_device *vdev = file_priv->vdev;
 	struct ivpu_job *job;
-	int ret;
-
-	ret = ivpu_rpm_get(vdev);
-	if (ret < 0)
-		return NULL;
 
 	job = kzalloc(struct_size(job, bos, bo_count), GFP_KERNEL);
 	if (!job)
-		goto err_rpm_put;
-
-	kref_init(&job->ref);
+		return NULL;
 
 	job->vdev = vdev;
 	job->engine_idx = engine_idx;
@@ -310,17 +278,14 @@ ivpu_create_job(struct ivpu_file_priv *file_priv, u32 engine_idx, u32 bo_count)
 	job->file_priv = ivpu_file_priv_get(file_priv);
 
 	ivpu_dbg(vdev, JOB, "Job created: ctx %2d engine %d", file_priv->ctx.id, job->engine_idx);
-
 	return job;
 
 err_free_job:
 	kfree(job);
-err_rpm_put:
-	ivpu_rpm_put(vdev);
 	return NULL;
 }
 
-static int ivpu_job_done(struct ivpu_device *vdev, u32 job_id, u32 job_status)
+static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32 job_status)
 {
 	struct ivpu_job *job;
 
@@ -329,7 +294,7 @@ static int ivpu_job_done(struct ivpu_device *vdev, u32 job_id, u32 job_status)
 		return -ENOENT;
 
 	if (job->file_priv->has_mmu_faults)
-		job_status = VPU_JSM_STATUS_ABORTED;
+		job_status = DRM_IVPU_JOB_STATUS_ABORTED;
 
 	job->bos[CMD_BUF_IDX]->job_status = job_status;
 	dma_fence_signal(job->done_fence);
@@ -337,9 +302,10 @@ static int ivpu_job_done(struct ivpu_device *vdev, u32 job_id, u32 job_status)
 	ivpu_dbg(vdev, JOB, "Job complete:  id %3u ctx %2d engine %d status 0x%x\n",
 		 job->job_id, job->file_priv->ctx.id, job->engine_idx, job_status);
 
+	ivpu_job_destroy(job);
 	ivpu_stop_job_timeout_detection(vdev);
 
-	job_put(job);
+	ivpu_rpm_put(vdev);
 	return 0;
 }
 
@@ -349,10 +315,10 @@ void ivpu_jobs_abort_all(struct ivpu_device *vdev)
 	unsigned long id;
 
 	xa_for_each(&vdev->submitted_jobs_xa, id, job)
-		ivpu_job_done(vdev, id, VPU_JSM_STATUS_ABORTED);
+		ivpu_job_signal_and_destroy(vdev, id, DRM_IVPU_JOB_STATUS_ABORTED);
 }
 
-static int ivpu_direct_job_submission(struct ivpu_job *job)
+static int ivpu_job_submit(struct ivpu_job *job)
 {
 	struct ivpu_file_priv *file_priv = job->file_priv;
 	struct ivpu_device *vdev = job->vdev;
@@ -360,53 +326,65 @@ static int ivpu_direct_job_submission(struct ivpu_job *job)
 	struct ivpu_cmdq *cmdq;
 	int ret;
 
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
 	mutex_lock(&file_priv->lock);
 
 	cmdq = ivpu_cmdq_acquire(job->file_priv, job->engine_idx);
 	if (!cmdq) {
-		ivpu_warn(vdev, "Failed get job queue, ctx %d engine %d\n",
-			  file_priv->ctx.id, job->engine_idx);
+		ivpu_warn_ratelimited(vdev, "Failed get job queue, ctx %d engine %d\n",
+				      file_priv->ctx.id, job->engine_idx);
 		ret = -EINVAL;
-		goto err_unlock;
+		goto err_unlock_file_priv;
 	}
 
 	job_id_range.min = FIELD_PREP(JOB_ID_CONTEXT_MASK, (file_priv->ctx.id - 1));
 	job_id_range.max = job_id_range.min | JOB_ID_JOB_MASK;
 
-	job_get(job, &job);
-	ret = xa_alloc(&vdev->submitted_jobs_xa, &job->job_id, job, job_id_range, GFP_KERNEL);
+	xa_lock(&vdev->submitted_jobs_xa);
+	ret = __xa_alloc(&vdev->submitted_jobs_xa, &job->job_id, job, job_id_range, GFP_KERNEL);
 	if (ret) {
-		ivpu_warn_ratelimited(vdev, "Failed to allocate job id: %d\n", ret);
-		goto err_job_put;
+		ivpu_dbg(vdev, JOB, "Too many active jobs in ctx %d\n",
+			 file_priv->ctx.id);
+		ret = -EBUSY;
+		goto err_unlock_submitted_jobs_xa;
 	}
 
 	ret = ivpu_cmdq_push_job(cmdq, job);
 	if (ret)
-		goto err_xa_erase;
+		goto err_erase_xa;
 
 	ivpu_start_job_timeout_detection(vdev);
 
-	ivpu_dbg(vdev, JOB, "Job submitted: id %3u addr 0x%llx ctx %2d engine %d next %d\n",
-		 job->job_id, job->cmd_buf_vpu_addr, file_priv->ctx.id,
-		 job->engine_idx, cmdq->jobq->header.tail);
-
-	if (ivpu_test_mode & IVPU_TEST_MODE_NULL_HW) {
-		ivpu_job_done(vdev, job->job_id, VPU_JSM_STATUS_SUCCESS);
+	if (unlikely(ivpu_test_mode & IVPU_TEST_MODE_NULL_HW)) {
 		cmdq->jobq->header.head = cmdq->jobq->header.tail;
 		wmb(); /* Flush WC buffer for jobq header */
 	} else {
 		ivpu_cmdq_ring_db(vdev, cmdq);
 	}
 
+	ivpu_dbg(vdev, JOB, "Job submitted: id %3u ctx %2d engine %d addr 0x%llx next %d\n",
+		 job->job_id, file_priv->ctx.id, job->engine_idx,
+		 job->cmd_buf_vpu_addr, cmdq->jobq->header.tail);
+
+	xa_unlock(&vdev->submitted_jobs_xa);
+
 	mutex_unlock(&file_priv->lock);
+
+	if (unlikely(ivpu_test_mode & IVPU_TEST_MODE_NULL_HW))
+		ivpu_job_signal_and_destroy(vdev, job->job_id, VPU_JSM_STATUS_SUCCESS);
+
 	return 0;
 
-err_xa_erase:
-	xa_erase(&vdev->submitted_jobs_xa, job->job_id);
-err_job_put:
-	job_put(job);
-err_unlock:
+err_erase_xa:
+	__xa_erase(&vdev->submitted_jobs_xa, job->job_id);
+err_unlock_submitted_jobs_xa:
+	xa_unlock(&vdev->submitted_jobs_xa);
+err_unlock_file_priv:
 	mutex_unlock(&file_priv->lock);
+	ivpu_rpm_put(vdev);
 	return ret;
 }
 
@@ -488,6 +466,9 @@ int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	if (params->engine > DRM_IVPU_ENGINE_COPY)
 		return -EINVAL;
 
+	if (params->priority > DRM_IVPU_JOB_PRIORITY_REALTIME)
+		return -EINVAL;
+
 	if (params->buffer_count == 0 || params->buffer_count > JOB_MAX_BUFFER_COUNT)
 		return -EINVAL;
 
@@ -509,44 +490,49 @@ int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 			     params->buffer_count * sizeof(u32));
 	if (ret) {
 		ret = -EFAULT;
-		goto free_handles;
+		goto err_free_handles;
 	}
 
 	if (!drm_dev_enter(&vdev->drm, &idx)) {
 		ret = -ENODEV;
-		goto free_handles;
+		goto err_free_handles;
 	}
 
 	ivpu_dbg(vdev, JOB, "Submit ioctl: ctx %u buf_count %u\n",
 		 file_priv->ctx.id, params->buffer_count);
 
-	job = ivpu_create_job(file_priv, params->engine, params->buffer_count);
+	job = ivpu_job_create(file_priv, params->engine, params->buffer_count);
 	if (!job) {
 		ivpu_err(vdev, "Failed to create job\n");
 		ret = -ENOMEM;
-		goto dev_exit;
+		goto err_exit_dev;
 	}
 
 	ret = ivpu_job_prepare_bos_for_submit(file, job, buf_handles, params->buffer_count,
 					      params->commands_offset);
 	if (ret) {
-		ivpu_err(vdev, "Failed to prepare job, ret %d\n", ret);
-		goto job_put;
+		ivpu_err(vdev, "Failed to prepare job: %d\n", ret);
+		goto err_destroy_job;
 	}
 
-	ret = ivpu_direct_job_submission(job);
-	if (ret) {
-		dma_fence_signal(job->done_fence);
-		ivpu_err(vdev, "Failed to submit job to the HW, ret %d\n", ret);
-	}
+	down_read(&vdev->pm->reset_lock);
+	ret = ivpu_job_submit(job);
+	up_read(&vdev->pm->reset_lock);
+	if (ret)
+		goto err_signal_fence;
 
-job_put:
-	job_put(job);
-dev_exit:
 	drm_dev_exit(idx);
-free_handles:
 	kfree(buf_handles);
+	return ret;
 
+err_signal_fence:
+	dma_fence_signal(job->done_fence);
+err_destroy_job:
+	ivpu_job_destroy(job);
+err_exit_dev:
+	drm_dev_exit(idx);
+err_free_handles:
+	kfree(buf_handles);
 	return ret;
 }
 
@@ -568,7 +554,7 @@ ivpu_job_done_callback(struct ivpu_device *vdev, struct ivpu_ipc_hdr *ipc_hdr,
 	}
 
 	payload = (struct vpu_ipc_msg_payload_job_done *)&jsm_msg->payload;
-	ret = ivpu_job_done(vdev, payload->job_id, payload->job_status);
+	ret = ivpu_job_signal_and_destroy(vdev, payload->job_id, payload->job_status);
 	if (!ret && !xa_empty(&vdev->submitted_jobs_xa))
 		ivpu_start_job_timeout_detection(vdev);
 }
diff --git a/drivers/accel/ivpu/ivpu_job.h b/drivers/accel/ivpu/ivpu_job.h
index 45a2f2ec82e5..ca4984071cc7 100644
--- a/drivers/accel/ivpu/ivpu_job.h
+++ b/drivers/accel/ivpu/ivpu_job.h
@@ -43,7 +43,6 @@ struct ivpu_cmdq {
 			  will update the job status
  */
 struct ivpu_job {
-	struct kref ref;
 	struct ivpu_device *vdev;
 	struct ivpu_file_priv *file_priv;
 	struct dma_fence *done_fence;
@@ -56,7 +55,7 @@ struct ivpu_job {
 
 int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file);
 
-void ivpu_cmdq_release_all(struct ivpu_file_priv *file_priv);
+void ivpu_cmdq_release_all_locked(struct ivpu_file_priv *file_priv);
 void ivpu_cmdq_reset_all_contexts(struct ivpu_device *vdev);
 
 void ivpu_job_done_consumer_init(struct ivpu_device *vdev);
diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
index 2228c44b115f..91bd640655ab 100644
--- a/drivers/accel/ivpu/ivpu_mmu.c
+++ b/drivers/accel/ivpu/ivpu_mmu.c
@@ -7,6 +7,7 @@
 #include <linux/highmem.h>
 
 #include "ivpu_drv.h"
+#include "ivpu_hw.h"
 #include "ivpu_hw_reg_io.h"
 #include "ivpu_mmu.h"
 #include "ivpu_mmu_context.h"
@@ -71,10 +72,10 @@
 
 #define IVPU_MMU_Q_COUNT_LOG2		4 /* 16 entries */
 #define IVPU_MMU_Q_COUNT		((u32)1 << IVPU_MMU_Q_COUNT_LOG2)
-#define IVPU_MMU_Q_WRAP_BIT		(IVPU_MMU_Q_COUNT << 1)
-#define IVPU_MMU_Q_WRAP_MASK		(IVPU_MMU_Q_WRAP_BIT - 1)
-#define IVPU_MMU_Q_IDX_MASK		(IVPU_MMU_Q_COUNT - 1)
+#define IVPU_MMU_Q_WRAP_MASK            GENMASK(IVPU_MMU_Q_COUNT_LOG2, 0)
+#define IVPU_MMU_Q_IDX_MASK             (IVPU_MMU_Q_COUNT - 1)
 #define IVPU_MMU_Q_IDX(val)		((val) & IVPU_MMU_Q_IDX_MASK)
+#define IVPU_MMU_Q_WRP(val)             ((val) & IVPU_MMU_Q_COUNT)
 
 #define IVPU_MMU_CMDQ_CMD_SIZE		16
 #define IVPU_MMU_CMDQ_SIZE		(IVPU_MMU_Q_COUNT * IVPU_MMU_CMDQ_CMD_SIZE)
@@ -474,20 +475,32 @@ static int ivpu_mmu_cmdq_wait_for_cons(struct ivpu_device *vdev)
 	return 0;
 }
 
+static bool ivpu_mmu_queue_is_full(struct ivpu_mmu_queue *q)
+{
+	return ((IVPU_MMU_Q_IDX(q->prod) == IVPU_MMU_Q_IDX(q->cons)) &&
+		(IVPU_MMU_Q_WRP(q->prod) != IVPU_MMU_Q_WRP(q->cons)));
+}
+
+static bool ivpu_mmu_queue_is_empty(struct ivpu_mmu_queue *q)
+{
+	return ((IVPU_MMU_Q_IDX(q->prod) == IVPU_MMU_Q_IDX(q->cons)) &&
+		(IVPU_MMU_Q_WRP(q->prod) == IVPU_MMU_Q_WRP(q->cons)));
+}
+
 static int ivpu_mmu_cmdq_cmd_write(struct ivpu_device *vdev, const char *name, u64 data0, u64 data1)
 {
-	struct ivpu_mmu_queue *q = &vdev->mmu->cmdq;
-	u64 *queue_buffer = q->base;
-	int idx = IVPU_MMU_Q_IDX(q->prod) * (IVPU_MMU_CMDQ_CMD_SIZE / sizeof(*queue_buffer));
+	struct ivpu_mmu_queue *cmdq = &vdev->mmu->cmdq;
+	u64 *queue_buffer = cmdq->base;
+	int idx = IVPU_MMU_Q_IDX(cmdq->prod) * (IVPU_MMU_CMDQ_CMD_SIZE / sizeof(*queue_buffer));
 
-	if (!CIRC_SPACE(IVPU_MMU_Q_IDX(q->prod), IVPU_MMU_Q_IDX(q->cons), IVPU_MMU_Q_COUNT)) {
+	if (ivpu_mmu_queue_is_full(cmdq)) {
 		ivpu_err(vdev, "Failed to write MMU CMD %s\n", name);
 		return -EBUSY;
 	}
 
 	queue_buffer[idx] = data0;
 	queue_buffer[idx + 1] = data1;
-	q->prod = (q->prod + 1) & IVPU_MMU_Q_WRAP_MASK;
+	cmdq->prod = (cmdq->prod + 1) & IVPU_MMU_Q_WRAP_MASK;
 
 	ivpu_dbg(vdev, MMU, "CMD write: %s data: 0x%llx 0x%llx\n", name, data0, data1);
 
@@ -518,6 +531,7 @@ static int ivpu_mmu_cmdq_sync(struct ivpu_device *vdev)
 
 		ivpu_err(vdev, "Timed out waiting for MMU consumer: %d, error: %s\n", ret,
 			 ivpu_mmu_cmdq_err_to_str(err));
+		ivpu_hw_diagnose_failure(vdev);
 	}
 
 	return ret;
@@ -558,7 +572,6 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev)
 	mmu->cmdq.cons = 0;
 
 	memset(mmu->evtq.base, 0, IVPU_MMU_EVTQ_SIZE);
-	clflush_cache_range(mmu->evtq.base, IVPU_MMU_EVTQ_SIZE);
 	mmu->evtq.prod = 0;
 	mmu->evtq.cons = 0;
 
@@ -872,20 +885,15 @@ static u32 *ivpu_mmu_get_event(struct ivpu_device *vdev)
 	u32 *evt = evtq->base + (idx * IVPU_MMU_EVTQ_CMD_SIZE);
 
 	evtq->prod = REGV_RD32(IVPU_MMU_REG_EVTQ_PROD_SEC);
-	if (!CIRC_CNT(IVPU_MMU_Q_IDX(evtq->prod), IVPU_MMU_Q_IDX(evtq->cons), IVPU_MMU_Q_COUNT))
+	if (ivpu_mmu_queue_is_empty(evtq))
 		return NULL;
 
-	clflush_cache_range(evt, IVPU_MMU_EVTQ_CMD_SIZE);
-
 	evtq->cons = (evtq->cons + 1) & IVPU_MMU_Q_WRAP_MASK;
-	REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, evtq->cons);
-
 	return evt;
 }
 
 void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev)
 {
-	bool schedule_recovery = false;
 	u32 *event;
 	u32 ssid;
 
@@ -895,14 +903,22 @@ void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev)
 		ivpu_mmu_dump_event(vdev, event);
 
 		ssid = FIELD_GET(IVPU_MMU_EVT_SSID_MASK, event[0]);
-		if (ssid == IVPU_GLOBAL_CONTEXT_MMU_SSID)
-			schedule_recovery = true;
-		else
-			ivpu_mmu_user_context_mark_invalid(vdev, ssid);
+		if (ssid == IVPU_GLOBAL_CONTEXT_MMU_SSID) {
+			ivpu_pm_trigger_recovery(vdev, "MMU event");
+			return;
+		}
+
+		ivpu_mmu_user_context_mark_invalid(vdev, ssid);
+		REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, vdev->mmu->evtq.cons);
 	}
+}
 
-	if (schedule_recovery)
-		ivpu_pm_schedule_recovery(vdev);
+void ivpu_mmu_evtq_dump(struct ivpu_device *vdev)
+{
+	u32 *event;
+
+	while ((event = ivpu_mmu_get_event(vdev)) != NULL)
+		ivpu_mmu_dump_event(vdev, event);
 }
 
 void ivpu_mmu_irq_gerr_handler(struct ivpu_device *vdev)
diff --git a/drivers/accel/ivpu/ivpu_mmu.h b/drivers/accel/ivpu/ivpu_mmu.h
index cb551126806b..6fa35c240710 100644
--- a/drivers/accel/ivpu/ivpu_mmu.h
+++ b/drivers/accel/ivpu/ivpu_mmu.h
@@ -46,5 +46,6 @@ int ivpu_mmu_invalidate_tlb(struct ivpu_device *vdev, u16 ssid);
 
 void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev);
 void ivpu_mmu_irq_gerr_handler(struct ivpu_device *vdev);
+void ivpu_mmu_evtq_dump(struct ivpu_device *vdev);
 
 #endif /* __IVPU_MMU_H__ */
diff --git a/drivers/accel/ivpu/ivpu_mmu_context.c b/drivers/accel/ivpu/ivpu_mmu_context.c
index 12a8c09d4547..fe6161299236 100644
--- a/drivers/accel/ivpu/ivpu_mmu_context.c
+++ b/drivers/accel/ivpu/ivpu_mmu_context.c
@@ -355,6 +355,9 @@ ivpu_mmu_context_map_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
 		dma_addr_t dma_addr = sg_dma_address(sg) - sg->offset;
 		size_t size = sg_dma_len(sg) + sg->offset;
 
+		ivpu_dbg(vdev, MMU_MAP, "Map ctx: %u dma_addr: 0x%llx vpu_addr: 0x%llx size: %lu\n",
+			 ctx->id, dma_addr, vpu_addr, size);
+
 		ret = ivpu_mmu_context_map_pages(vdev, ctx, vpu_addr, dma_addr, size, prot);
 		if (ret) {
 			ivpu_err(vdev, "Failed to map context pages\n");
@@ -366,6 +369,7 @@ ivpu_mmu_context_map_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
 
 	/* Ensure page table modifications are flushed from wc buffers to memory */
 	wmb();
+
 	mutex_unlock(&ctx->lock);
 
 	ret = ivpu_mmu_invalidate_tlb(vdev, ctx->id);
@@ -388,14 +392,19 @@ ivpu_mmu_context_unmap_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ct
 	mutex_lock(&ctx->lock);
 
 	for_each_sgtable_dma_sg(sgt, sg, i) {
+		dma_addr_t dma_addr = sg_dma_address(sg) - sg->offset;
 		size_t size = sg_dma_len(sg) + sg->offset;
 
+		ivpu_dbg(vdev, MMU_MAP, "Unmap ctx: %u dma_addr: 0x%llx vpu_addr: 0x%llx size: %lu\n",
+			 ctx->id, dma_addr, vpu_addr, size);
+
 		ivpu_mmu_context_unmap_pages(ctx, vpu_addr, size);
 		vpu_addr += size;
 	}
 
 	/* Ensure page table modifications are flushed from wc buffers to memory */
 	wmb();
+
 	mutex_unlock(&ctx->lock);
 
 	ret = ivpu_mmu_invalidate_tlb(vdev, ctx->id);
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index 0af8864cb3b5..5f73854234ba 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -13,6 +13,7 @@
 #include "ivpu_drv.h"
 #include "ivpu_hw.h"
 #include "ivpu_fw.h"
+#include "ivpu_fw_log.h"
 #include "ivpu_ipc.h"
 #include "ivpu_job.h"
 #include "ivpu_jsm_msg.h"
@@ -57,11 +58,14 @@ static int ivpu_suspend(struct ivpu_device *vdev)
 {
 	int ret;
 
+	/* Save PCI state before powering down as it sometimes gets corrupted if NPU hangs */
+	pci_save_state(to_pci_dev(vdev->drm.dev));
+
 	ret = ivpu_shutdown(vdev);
-	if (ret) {
+	if (ret)
 		ivpu_err(vdev, "Failed to shutdown VPU: %d\n", ret);
-		return ret;
-	}
+
+	pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
 
 	return ret;
 }
@@ -70,6 +74,9 @@ static int ivpu_resume(struct ivpu_device *vdev)
 {
 	int ret;
 
+	pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D0);
+	pci_restore_state(to_pci_dev(vdev->drm.dev));
+
 retry:
 	ret = ivpu_hw_power_up(vdev);
 	if (ret) {
@@ -111,22 +118,37 @@ static void ivpu_pm_recovery_work(struct work_struct *work)
 	char *evt[2] = {"IVPU_PM_EVENT=IVPU_RECOVER", NULL};
 	int ret;
 
-retry:
-	ret = pci_try_reset_function(to_pci_dev(vdev->drm.dev));
-	if (ret == -EAGAIN && !drm_dev_is_unplugged(&vdev->drm)) {
-		cond_resched();
-		goto retry;
-	}
+	ivpu_err(vdev, "Recovering the VPU (reset #%d)\n", atomic_read(&vdev->pm->reset_counter));
 
-	if (ret && ret != -EAGAIN)
-		ivpu_err(vdev, "Failed to reset VPU: %d\n", ret);
+	ret = pm_runtime_resume_and_get(vdev->drm.dev);
+	if (ret)
+		ivpu_err(vdev, "Failed to resume VPU: %d\n", ret);
+
+	ivpu_fw_log_dump(vdev);
+
+	atomic_inc(&vdev->pm->reset_counter);
+	atomic_set(&vdev->pm->reset_pending, 1);
+	down_write(&vdev->pm->reset_lock);
+
+	ivpu_suspend(vdev);
+	ivpu_pm_prepare_cold_boot(vdev);
+	ivpu_jobs_abort_all(vdev);
+
+	ret = ivpu_resume(vdev);
+	if (ret)
+		ivpu_err(vdev, "Failed to resume NPU: %d\n", ret);
+
+	up_write(&vdev->pm->reset_lock);
+	atomic_set(&vdev->pm->reset_pending, 0);
 
 	kobject_uevent_env(&vdev->drm.dev->kobj, KOBJ_CHANGE, evt);
+	pm_runtime_mark_last_busy(vdev->drm.dev);
+	pm_runtime_put_autosuspend(vdev->drm.dev);
 }
 
-void ivpu_pm_schedule_recovery(struct ivpu_device *vdev)
+void ivpu_pm_trigger_recovery(struct ivpu_device *vdev, const char *reason)
 {
-	struct ivpu_pm_info *pm = vdev->pm;
+	ivpu_err(vdev, "Recovery triggered by %s\n", reason);
 
 	if (ivpu_disable_recovery) {
 		ivpu_err(vdev, "Recovery not available when disable_recovery param is set\n");
@@ -138,10 +160,11 @@ void ivpu_pm_schedule_recovery(struct ivpu_device *vdev)
 		return;
 	}
 
-	/* Schedule recovery if it's not in progress */
-	if (atomic_cmpxchg(&pm->in_reset, 0, 1) == 0) {
-		ivpu_hw_irq_disable(vdev);
-		queue_work(system_long_wq, &pm->recovery_work);
+	/* Trigger recovery if it's not in progress */
+	if (atomic_cmpxchg(&vdev->pm->reset_pending, 0, 1) == 0) {
+		ivpu_hw_diagnose_failure(vdev);
+		ivpu_hw_irq_disable(vdev); /* Disable IRQ early to protect from IRQ storm */
+		queue_work(system_long_wq, &vdev->pm->recovery_work);
 	}
 }
 
@@ -149,12 +172,8 @@ static void ivpu_job_timeout_work(struct work_struct *work)
 {
 	struct ivpu_pm_info *pm = container_of(work, struct ivpu_pm_info, job_timeout_work.work);
 	struct ivpu_device *vdev = pm->vdev;
-	unsigned long timeout_ms = ivpu_tdr_timeout_ms ? ivpu_tdr_timeout_ms : vdev->timeout.tdr;
-
-	ivpu_err(vdev, "TDR detected, timeout %lu ms", timeout_ms);
-	ivpu_hw_diagnose_failure(vdev);
 
-	ivpu_pm_schedule_recovery(vdev);
+	ivpu_pm_trigger_recovery(vdev, "TDR");
 }
 
 void ivpu_start_job_timeout_detection(struct ivpu_device *vdev)
@@ -192,9 +211,6 @@ int ivpu_pm_suspend_cb(struct device *dev)
 	ivpu_suspend(vdev);
 	ivpu_pm_prepare_warm_boot(vdev);
 
-	pci_save_state(to_pci_dev(dev));
-	pci_set_power_state(to_pci_dev(dev), PCI_D3hot);
-
 	ivpu_dbg(vdev, PM, "Suspend done.\n");
 
 	return 0;
@@ -208,9 +224,6 @@ int ivpu_pm_resume_cb(struct device *dev)
 
 	ivpu_dbg(vdev, PM, "Resume..\n");
 
-	pci_set_power_state(to_pci_dev(dev), PCI_D0);
-	pci_restore_state(to_pci_dev(dev));
-
 	ret = ivpu_resume(vdev);
 	if (ret)
 		ivpu_err(vdev, "Failed to resume: %d\n", ret);
@@ -227,6 +240,9 @@ int ivpu_pm_runtime_suspend_cb(struct device *dev)
 	bool hw_is_idle = true;
 	int ret;
 
+	drm_WARN_ON(&vdev->drm, !xa_empty(&vdev->submitted_jobs_xa));
+	drm_WARN_ON(&vdev->drm, work_pending(&vdev->pm->recovery_work));
+
 	ivpu_dbg(vdev, PM, "Runtime suspend..\n");
 
 	if (!ivpu_hw_is_idle(vdev) && vdev->pm->suspend_reschedule_counter) {
@@ -247,7 +263,8 @@ int ivpu_pm_runtime_suspend_cb(struct device *dev)
 		ivpu_err(vdev, "Failed to set suspend VPU: %d\n", ret);
 
 	if (!hw_is_idle) {
-		ivpu_warn(vdev, "VPU failed to enter idle, force suspended.\n");
+		ivpu_err(vdev, "VPU failed to enter idle, force suspended.\n");
+		ivpu_fw_log_dump(vdev);
 		ivpu_pm_prepare_cold_boot(vdev);
 	} else {
 		ivpu_pm_prepare_warm_boot(vdev);
@@ -308,11 +325,12 @@ void ivpu_pm_reset_prepare_cb(struct pci_dev *pdev)
 {
 	struct ivpu_device *vdev = pci_get_drvdata(pdev);
 
-	pm_runtime_get_sync(vdev->drm.dev);
-
 	ivpu_dbg(vdev, PM, "Pre-reset..\n");
 	atomic_inc(&vdev->pm->reset_counter);
-	atomic_set(&vdev->pm->in_reset, 1);
+	atomic_set(&vdev->pm->reset_pending, 1);
+
+	pm_runtime_get_sync(vdev->drm.dev);
+	down_write(&vdev->pm->reset_lock);
 	ivpu_prepare_for_reset(vdev);
 	ivpu_hw_reset(vdev);
 	ivpu_pm_prepare_cold_boot(vdev);
@@ -329,9 +347,11 @@ void ivpu_pm_reset_done_cb(struct pci_dev *pdev)
 	ret = ivpu_resume(vdev);
 	if (ret)
 		ivpu_err(vdev, "Failed to set RESUME state: %d\n", ret);
-	atomic_set(&vdev->pm->in_reset, 0);
+	up_write(&vdev->pm->reset_lock);
+	atomic_set(&vdev->pm->reset_pending, 0);
 	ivpu_dbg(vdev, PM, "Post-reset done.\n");
 
+	pm_runtime_mark_last_busy(vdev->drm.dev);
 	pm_runtime_put_autosuspend(vdev->drm.dev);
 }
 
@@ -344,7 +364,10 @@ void ivpu_pm_init(struct ivpu_device *vdev)
 	pm->vdev = vdev;
 	pm->suspend_reschedule_counter = PM_RESCHEDULE_LIMIT;
 
-	atomic_set(&pm->in_reset, 0);
+	init_rwsem(&pm->reset_lock);
+	atomic_set(&pm->reset_pending, 0);
+	atomic_set(&pm->reset_counter, 0);
+
 	INIT_WORK(&pm->recovery_work, ivpu_pm_recovery_work);
 	INIT_DELAYED_WORK(&pm->job_timeout_work, ivpu_job_timeout_work);
 
diff --git a/drivers/accel/ivpu/ivpu_pm.h b/drivers/accel/ivpu/ivpu_pm.h
index 97c6e0b0aa42..ec60fbeefefc 100644
--- a/drivers/accel/ivpu/ivpu_pm.h
+++ b/drivers/accel/ivpu/ivpu_pm.h
@@ -6,6 +6,7 @@
 #ifndef __IVPU_PM_H__
 #define __IVPU_PM_H__
 
+#include <linux/rwsem.h>
 #include <linux/types.h>
 
 struct ivpu_device;
@@ -14,8 +15,9 @@ struct ivpu_pm_info {
 	struct ivpu_device *vdev;
 	struct delayed_work job_timeout_work;
 	struct work_struct recovery_work;
-	atomic_t in_reset;
+	struct rw_semaphore reset_lock;
 	atomic_t reset_counter;
+	atomic_t reset_pending;
 	bool is_warmboot;
 	u32 suspend_reschedule_counter;
 };
@@ -37,7 +39,7 @@ int __must_check ivpu_rpm_get(struct ivpu_device *vdev);
 int __must_check ivpu_rpm_get_if_active(struct ivpu_device *vdev);
 void ivpu_rpm_put(struct ivpu_device *vdev);
 
-void ivpu_pm_schedule_recovery(struct ivpu_device *vdev);
+void ivpu_pm_trigger_recovery(struct ivpu_device *vdev, const char *reason);
 void ivpu_start_job_timeout_detection(struct ivpu_device *vdev);
 void ivpu_stop_job_timeout_detection(struct ivpu_device *vdev);
 
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 6f2bfcf7645c..3c3f8037ebed 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -314,7 +314,6 @@ config ACPI_HOTPLUG_CPU
 	bool
 	depends on ACPI_PROCESSOR && HOTPLUG_CPU
 	select ACPI_CONTAINER
-	default y
 
 config ACPI_PROCESSOR_AGGREGATOR
 	tristate "Processor Aggregator"
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index 0f5218e361df..4fe2ef54088c 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -184,24 +184,6 @@ static void __init acpi_pcc_cpufreq_init(void) {}
 
 /* Initialization */
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
-int __weak acpi_map_cpu(acpi_handle handle,
-		phys_cpuid_t physid, u32 acpi_id, int *pcpu)
-{
-	return -ENODEV;
-}
-
-int __weak acpi_unmap_cpu(int cpu)
-{
-	return -ENODEV;
-}
-
-int __weak arch_register_cpu(int cpu)
-{
-	return -ENODEV;
-}
-
-void __weak arch_unregister_cpu(int cpu) {}
-
 static int acpi_processor_hotadd_init(struct acpi_processor *pr)
 {
 	unsigned long long sta;
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index dbdee2924594..02255795b800 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -525,10 +525,12 @@ static void acpi_ec_clear(struct acpi_ec *ec)
 
 static void acpi_ec_enable_event(struct acpi_ec *ec)
 {
-	spin_lock(&ec->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ec->lock, flags);
 	if (acpi_ec_started(ec))
 		__acpi_ec_enable_event(ec);
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 
 	/* Drain additional events if hardware requires that */
 	if (EC_FLAGS_CLEAR_ON_RESUME)
@@ -544,9 +546,11 @@ static void __acpi_ec_flush_work(void)
 
 static void acpi_ec_disable_event(struct acpi_ec *ec)
 {
-	spin_lock(&ec->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ec->lock, flags);
 	__acpi_ec_disable_event(ec);
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 
 	/*
 	 * When ec_freeze_events is true, we need to flush events in
@@ -567,9 +571,10 @@ void acpi_ec_flush_work(void)
 
 static bool acpi_ec_guard_event(struct acpi_ec *ec)
 {
+	unsigned long flags;
 	bool guarded;
 
-	spin_lock(&ec->lock);
+	spin_lock_irqsave(&ec->lock, flags);
 	/*
 	 * If firmware SCI_EVT clearing timing is "event", we actually
 	 * don't know when the SCI_EVT will be cleared by firmware after
@@ -585,29 +590,31 @@ static bool acpi_ec_guard_event(struct acpi_ec *ec)
 	guarded = ec_event_clearing == ACPI_EC_EVT_TIMING_EVENT &&
 		ec->event_state != EC_EVENT_READY &&
 		(!ec->curr || ec->curr->command != ACPI_EC_COMMAND_QUERY);
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 	return guarded;
 }
 
 static int ec_transaction_polled(struct acpi_ec *ec)
 {
+	unsigned long flags;
 	int ret = 0;
 
-	spin_lock(&ec->lock);
+	spin_lock_irqsave(&ec->lock, flags);
 	if (ec->curr && (ec->curr->flags & ACPI_EC_COMMAND_POLL))
 		ret = 1;
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 	return ret;
 }
 
 static int ec_transaction_completed(struct acpi_ec *ec)
 {
+	unsigned long flags;
 	int ret = 0;
 
-	spin_lock(&ec->lock);
+	spin_lock_irqsave(&ec->lock, flags);
 	if (ec->curr && (ec->curr->flags & ACPI_EC_COMMAND_COMPLETE))
 		ret = 1;
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 	return ret;
 }
 
@@ -749,6 +756,7 @@ static int ec_guard(struct acpi_ec *ec)
 
 static int ec_poll(struct acpi_ec *ec)
 {
+	unsigned long flags;
 	int repeat = 5; /* number of command restarts */
 
 	while (repeat--) {
@@ -757,14 +765,14 @@ static int ec_poll(struct acpi_ec *ec)
 		do {
 			if (!ec_guard(ec))
 				return 0;
-			spin_lock(&ec->lock);
+			spin_lock_irqsave(&ec->lock, flags);
 			advance_transaction(ec, false);
-			spin_unlock(&ec->lock);
+			spin_unlock_irqrestore(&ec->lock, flags);
 		} while (time_before(jiffies, delay));
 		pr_debug("controller reset, restart transaction\n");
-		spin_lock(&ec->lock);
+		spin_lock_irqsave(&ec->lock, flags);
 		start_transaction(ec);
-		spin_unlock(&ec->lock);
+		spin_unlock_irqrestore(&ec->lock, flags);
 	}
 	return -ETIME;
 }
@@ -772,10 +780,11 @@ static int ec_poll(struct acpi_ec *ec)
 static int acpi_ec_transaction_unlocked(struct acpi_ec *ec,
 					struct transaction *t)
 {
+	unsigned long tmp;
 	int ret = 0;
 
 	/* start transaction */
-	spin_lock(&ec->lock);
+	spin_lock_irqsave(&ec->lock, tmp);
 	/* Enable GPE for command processing (IBF=0/OBF=1) */
 	if (!acpi_ec_submit_flushable_request(ec)) {
 		ret = -EINVAL;
@@ -786,11 +795,11 @@ static int acpi_ec_transaction_unlocked(struct acpi_ec *ec,
 	ec->curr = t;
 	ec_dbg_req("Command(%s) started", acpi_ec_cmd_string(t->command));
 	start_transaction(ec);
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, tmp);
 
 	ret = ec_poll(ec);
 
-	spin_lock(&ec->lock);
+	spin_lock_irqsave(&ec->lock, tmp);
 	if (t->irq_count == ec_storm_threshold)
 		acpi_ec_unmask_events(ec);
 	ec_dbg_req("Command(%s) stopped", acpi_ec_cmd_string(t->command));
@@ -799,7 +808,7 @@ static int acpi_ec_transaction_unlocked(struct acpi_ec *ec,
 	acpi_ec_complete_request(ec);
 	ec_dbg_ref(ec, "Decrease command");
 unlock:
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, tmp);
 	return ret;
 }
 
@@ -927,7 +936,9 @@ EXPORT_SYMBOL(ec_get_handle);
 
 static void acpi_ec_start(struct acpi_ec *ec, bool resuming)
 {
-	spin_lock(&ec->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ec->lock, flags);
 	if (!test_and_set_bit(EC_FLAGS_STARTED, &ec->flags)) {
 		ec_dbg_drv("Starting EC");
 		/* Enable GPE for event processing (SCI_EVT=1) */
@@ -937,28 +948,31 @@ static void acpi_ec_start(struct acpi_ec *ec, bool resuming)
 		}
 		ec_log_drv("EC started");
 	}
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 }
 
 static bool acpi_ec_stopped(struct acpi_ec *ec)
 {
+	unsigned long flags;
 	bool flushed;
 
-	spin_lock(&ec->lock);
+	spin_lock_irqsave(&ec->lock, flags);
 	flushed = acpi_ec_flushed(ec);
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 	return flushed;
 }
 
 static void acpi_ec_stop(struct acpi_ec *ec, bool suspending)
 {
-	spin_lock(&ec->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ec->lock, flags);
 	if (acpi_ec_started(ec)) {
 		ec_dbg_drv("Stopping EC");
 		set_bit(EC_FLAGS_STOPPED, &ec->flags);
-		spin_unlock(&ec->lock);
+		spin_unlock_irqrestore(&ec->lock, flags);
 		wait_event(ec->wait, acpi_ec_stopped(ec));
-		spin_lock(&ec->lock);
+		spin_lock_irqsave(&ec->lock, flags);
 		/* Disable GPE for event processing (SCI_EVT=1) */
 		if (!suspending) {
 			acpi_ec_complete_request(ec);
@@ -969,25 +983,29 @@ static void acpi_ec_stop(struct acpi_ec *ec, bool suspending)
 		clear_bit(EC_FLAGS_STOPPED, &ec->flags);
 		ec_log_drv("EC stopped");
 	}
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 }
 
 static void acpi_ec_enter_noirq(struct acpi_ec *ec)
 {
-	spin_lock(&ec->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ec->lock, flags);
 	ec->busy_polling = true;
 	ec->polling_guard = 0;
 	ec_log_drv("interrupt blocked");
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 }
 
 static void acpi_ec_leave_noirq(struct acpi_ec *ec)
 {
-	spin_lock(&ec->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ec->lock, flags);
 	ec->busy_polling = ec_busy_polling;
 	ec->polling_guard = ec_polling_guard;
 	ec_log_drv("interrupt unblocked");
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 }
 
 void acpi_ec_block_transactions(void)
@@ -1119,9 +1137,9 @@ static void acpi_ec_event_processor(struct work_struct *work)
 
 	ec_dbg_evt("Query(0x%02x) stopped", handler->query_bit);
 
-	spin_lock(&ec->lock);
+	spin_lock_irq(&ec->lock);
 	ec->queries_in_progress--;
-	spin_unlock(&ec->lock);
+	spin_unlock_irq(&ec->lock);
 
 	acpi_ec_put_query_handler(handler);
 	kfree(q);
@@ -1184,12 +1202,12 @@ static int acpi_ec_submit_query(struct acpi_ec *ec)
 	 */
 	ec_dbg_evt("Query(0x%02x) scheduled", value);
 
-	spin_lock(&ec->lock);
+	spin_lock_irq(&ec->lock);
 
 	ec->queries_in_progress++;
 	queue_work(ec_query_wq, &q->work);
 
-	spin_unlock(&ec->lock);
+	spin_unlock_irq(&ec->lock);
 
 	return 0;
 
@@ -1205,14 +1223,14 @@ static void acpi_ec_event_handler(struct work_struct *work)
 
 	ec_dbg_evt("Event started");
 
-	spin_lock(&ec->lock);
+	spin_lock_irq(&ec->lock);
 
 	while (ec->events_to_process) {
-		spin_unlock(&ec->lock);
+		spin_unlock_irq(&ec->lock);
 
 		acpi_ec_submit_query(ec);
 
-		spin_lock(&ec->lock);
+		spin_lock_irq(&ec->lock);
 
 		ec->events_to_process--;
 	}
@@ -1229,11 +1247,11 @@ static void acpi_ec_event_handler(struct work_struct *work)
 
 		ec_dbg_evt("Event stopped");
 
-		spin_unlock(&ec->lock);
+		spin_unlock_irq(&ec->lock);
 
 		guard_timeout = !!ec_guard(ec);
 
-		spin_lock(&ec->lock);
+		spin_lock_irq(&ec->lock);
 
 		/* Take care of SCI_EVT unless someone else is doing that. */
 		if (guard_timeout && !ec->curr)
@@ -1246,7 +1264,7 @@ static void acpi_ec_event_handler(struct work_struct *work)
 
 	ec->events_in_progress--;
 
-	spin_unlock(&ec->lock);
+	spin_unlock_irq(&ec->lock);
 }
 
 static void clear_gpe_and_advance_transaction(struct acpi_ec *ec, bool interrupt)
@@ -1271,11 +1289,13 @@ static void clear_gpe_and_advance_transaction(struct acpi_ec *ec, bool interrupt
 
 static void acpi_ec_handle_interrupt(struct acpi_ec *ec)
 {
-	spin_lock(&ec->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ec->lock, flags);
 
 	clear_gpe_and_advance_transaction(ec, true);
 
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 }
 
 static u32 acpi_ec_gpe_handler(acpi_handle gpe_device,
@@ -2085,7 +2105,7 @@ bool acpi_ec_dispatch_gpe(void)
 	 * Dispatch the EC GPE in-band, but do not report wakeup in any case
 	 * to allow the caller to process events properly after that.
 	 */
-	spin_lock(&first_ec->lock);
+	spin_lock_irq(&first_ec->lock);
 
 	if (acpi_ec_gpe_status_set(first_ec)) {
 		pm_pr_dbg("ACPI EC GPE status set\n");
@@ -2094,7 +2114,7 @@ bool acpi_ec_dispatch_gpe(void)
 		work_in_progress = acpi_ec_work_in_progress(first_ec);
 	}
 
-	spin_unlock(&first_ec->lock);
+	spin_unlock_irq(&first_ec->lock);
 
 	if (!work_in_progress)
 		return false;
@@ -2107,11 +2127,11 @@ bool acpi_ec_dispatch_gpe(void)
 
 		pm_pr_dbg("ACPI EC work flushed\n");
 
-		spin_lock(&first_ec->lock);
+		spin_lock_irq(&first_ec->lock);
 
 		work_in_progress = acpi_ec_work_in_progress(first_ec);
 
-		spin_unlock(&first_ec->lock);
+		spin_unlock_irq(&first_ec->lock);
 	} while (work_in_progress && !pm_wakeup_pending());
 
 	return false;
diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index 9ef5f1bdcfdb..d6b85f0f6082 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -58,14 +58,22 @@ struct target_cache {
 	struct node_cache_attrs cache_attrs;
 };
 
+enum {
+	NODE_ACCESS_CLASS_0 = 0,
+	NODE_ACCESS_CLASS_1,
+	NODE_ACCESS_CLASS_GENPORT_SINK,
+	NODE_ACCESS_CLASS_MAX,
+};
+
 struct memory_target {
 	struct list_head node;
 	unsigned int memory_pxm;
 	unsigned int processor_pxm;
 	struct resource memregions;
-	struct node_hmem_attrs hmem_attrs[2];
+	struct access_coordinate coord[NODE_ACCESS_CLASS_MAX];
 	struct list_head caches;
 	struct node_cache_attrs cache_attrs;
+	u8 gen_port_device_handle[ACPI_SRAT_DEVICE_HANDLE_SIZE];
 	bool registered;
 };
 
@@ -100,6 +108,47 @@ static struct memory_target *find_mem_target(unsigned int mem_pxm)
 	return NULL;
 }
 
+static struct memory_target *acpi_find_genport_target(u32 uid)
+{
+	struct memory_target *target;
+	u32 target_uid;
+	u8 *uid_ptr;
+
+	list_for_each_entry(target, &targets, node) {
+		uid_ptr = target->gen_port_device_handle + 8;
+		target_uid = *(u32 *)uid_ptr;
+		if (uid == target_uid)
+			return target;
+	}
+
+	return NULL;
+}
+
+/**
+ * acpi_get_genport_coordinates - Retrieve the access coordinates for a generic port
+ * @uid: ACPI unique id
+ * @coord: The access coordinates written back out for the generic port
+ *
+ * Return: 0 on success. Errno on failure.
+ *
+ * Only supports device handles that are ACPI. Assume ACPI0016 HID for CXL.
+ */
+int acpi_get_genport_coordinates(u32 uid,
+				 struct access_coordinate *coord)
+{
+	struct memory_target *target;
+
+	guard(mutex)(&target_lock);
+	target = acpi_find_genport_target(uid);
+	if (!target)
+		return -ENOENT;
+
+	*coord = target->coord[NODE_ACCESS_CLASS_GENPORT_SINK];
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(acpi_get_genport_coordinates, CXL);
+
 static __init void alloc_memory_initiator(unsigned int cpu_pxm)
 {
 	struct memory_initiator *initiator;
@@ -120,8 +169,7 @@ static __init void alloc_memory_initiator(unsigned int cpu_pxm)
 	list_add_tail(&initiator->node, &initiators);
 }
 
-static __init void alloc_memory_target(unsigned int mem_pxm,
-		resource_size_t start, resource_size_t len)
+static __init struct memory_target *alloc_target(unsigned int mem_pxm)
 {
 	struct memory_target *target;
 
@@ -129,7 +177,7 @@ static __init void alloc_memory_target(unsigned int mem_pxm,
 	if (!target) {
 		target = kzalloc(sizeof(*target), GFP_KERNEL);
 		if (!target)
-			return;
+			return NULL;
 		target->memory_pxm = mem_pxm;
 		target->processor_pxm = PXM_INVAL;
 		target->memregions = (struct resource) {
@@ -142,6 +190,19 @@ static __init void alloc_memory_target(unsigned int mem_pxm,
 		INIT_LIST_HEAD(&target->caches);
 	}
 
+	return target;
+}
+
+static __init void alloc_memory_target(unsigned int mem_pxm,
+				       resource_size_t start,
+				       resource_size_t len)
+{
+	struct memory_target *target;
+
+	target = alloc_target(mem_pxm);
+	if (!target)
+		return;
+
 	/*
 	 * There are potentially multiple ranges per PXM, so record each
 	 * in the per-target memregions resource tree.
@@ -152,6 +213,18 @@ static __init void alloc_memory_target(unsigned int mem_pxm,
 				start, start + len, mem_pxm);
 }
 
+static __init void alloc_genport_target(unsigned int mem_pxm, u8 *handle)
+{
+	struct memory_target *target;
+
+	target = alloc_target(mem_pxm);
+	if (!target)
+		return;
+
+	memcpy(target->gen_port_device_handle, handle,
+	       ACPI_SRAT_DEVICE_HANDLE_SIZE);
+}
+
 static __init const char *hmat_data_type(u8 type)
 {
 	switch (type) {
@@ -228,24 +301,24 @@ static void hmat_update_target_access(struct memory_target *target,
 {
 	switch (type) {
 	case ACPI_HMAT_ACCESS_LATENCY:
-		target->hmem_attrs[access].read_latency = value;
-		target->hmem_attrs[access].write_latency = value;
+		target->coord[access].read_latency = value;
+		target->coord[access].write_latency = value;
 		break;
 	case ACPI_HMAT_READ_LATENCY:
-		target->hmem_attrs[access].read_latency = value;
+		target->coord[access].read_latency = value;
 		break;
 	case ACPI_HMAT_WRITE_LATENCY:
-		target->hmem_attrs[access].write_latency = value;
+		target->coord[access].write_latency = value;
 		break;
 	case ACPI_HMAT_ACCESS_BANDWIDTH:
-		target->hmem_attrs[access].read_bandwidth = value;
-		target->hmem_attrs[access].write_bandwidth = value;
+		target->coord[access].read_bandwidth = value;
+		target->coord[access].write_bandwidth = value;
 		break;
 	case ACPI_HMAT_READ_BANDWIDTH:
-		target->hmem_attrs[access].read_bandwidth = value;
+		target->coord[access].read_bandwidth = value;
 		break;
 	case ACPI_HMAT_WRITE_BANDWIDTH:
-		target->hmem_attrs[access].write_bandwidth = value;
+		target->coord[access].write_bandwidth = value;
 		break;
 	default:
 		break;
@@ -291,11 +364,28 @@ static __init void hmat_add_locality(struct acpi_hmat_locality *hmat_loc)
 	}
 }
 
+static __init void hmat_update_target(unsigned int tgt_pxm, unsigned int init_pxm,
+				      u8 mem_hier, u8 type, u32 value)
+{
+	struct memory_target *target = find_mem_target(tgt_pxm);
+
+	if (mem_hier != ACPI_HMAT_MEMORY)
+		return;
+
+	if (target && target->processor_pxm == init_pxm) {
+		hmat_update_target_access(target, type, value,
+					  NODE_ACCESS_CLASS_0);
+		/* If the node has a CPU, update access 1 */
+		if (node_state(pxm_to_node(init_pxm), N_CPU))
+			hmat_update_target_access(target, type, value,
+						  NODE_ACCESS_CLASS_1);
+	}
+}
+
 static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 				      const unsigned long end)
 {
 	struct acpi_hmat_locality *hmat_loc = (void *)header;
-	struct memory_target *target;
 	unsigned int init, targ, total_size, ipds, tpds;
 	u32 *inits, *targs, value;
 	u16 *entries;
@@ -336,15 +426,8 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 				inits[init], targs[targ], value,
 				hmat_data_type_suffix(type));
 
-			if (mem_hier == ACPI_HMAT_MEMORY) {
-				target = find_mem_target(targs[targ]);
-				if (target && target->processor_pxm == inits[init]) {
-					hmat_update_target_access(target, type, value, 0);
-					/* If the node has a CPU, update access 1 */
-					if (node_state(pxm_to_node(inits[init]), N_CPU))
-						hmat_update_target_access(target, type, value, 1);
-				}
-			}
+			hmat_update_target(targs[targ], inits[init],
+					   mem_hier, type, value);
 		}
 	}
 
@@ -491,6 +574,27 @@ static __init int srat_parse_mem_affinity(union acpi_subtable_headers *header,
 	return 0;
 }
 
+static __init int srat_parse_genport_affinity(union acpi_subtable_headers *header,
+					      const unsigned long end)
+{
+	struct acpi_srat_generic_affinity *ga = (void *)header;
+
+	if (!ga)
+		return -EINVAL;
+
+	if (!(ga->flags & ACPI_SRAT_GENERIC_AFFINITY_ENABLED))
+		return 0;
+
+	/* Skip PCI device_handle for now */
+	if (ga->device_handle_type != 0)
+		return 0;
+
+	alloc_genport_target(ga->proximity_domain,
+			     (u8 *)ga->device_handle);
+
+	return 0;
+}
+
 static u32 hmat_initiator_perf(struct memory_target *target,
 			       struct memory_initiator *initiator,
 			       struct acpi_hmat_locality *hmat_loc)
@@ -592,6 +696,11 @@ static void hmat_update_target_attrs(struct memory_target *target,
 	u32 best = 0;
 	int i;
 
+	/* Don't update for generic port if there's no device handle */
+	if (access == NODE_ACCESS_CLASS_GENPORT_SINK &&
+	    !(*(u16 *)target->gen_port_device_handle))
+		return;
+
 	bitmap_zero(p_nodes, MAX_NUMNODES);
 	/*
 	 * If the Address Range Structure provides a local processor pxm, set
@@ -661,6 +770,14 @@ static void __hmat_register_target_initiators(struct memory_target *target,
 	}
 }
 
+static void hmat_register_generic_target_initiators(struct memory_target *target)
+{
+	static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
+
+	__hmat_register_target_initiators(target, p_nodes,
+					  NODE_ACCESS_CLASS_GENPORT_SINK);
+}
+
 static void hmat_register_target_initiators(struct memory_target *target)
 {
 	static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
@@ -681,7 +798,7 @@ static void hmat_register_target_cache(struct memory_target *target)
 static void hmat_register_target_perf(struct memory_target *target, int access)
 {
 	unsigned mem_nid = pxm_to_node(target->memory_pxm);
-	node_set_perf_attrs(mem_nid, &target->hmem_attrs[access], access);
+	node_set_perf_attrs(mem_nid, &target->coord[access], access);
 }
 
 static void hmat_register_target_devices(struct memory_target *target)
@@ -713,6 +830,17 @@ static void hmat_register_target(struct memory_target *target)
 	hmat_register_target_devices(target);
 
 	/*
+	 * Register generic port perf numbers. The nid may not be
+	 * initialized and is still NUMA_NO_NODE.
+	 */
+	mutex_lock(&target_lock);
+	if (*(u16 *)target->gen_port_device_handle) {
+		hmat_register_generic_target_initiators(target);
+		target->registered = true;
+	}
+	mutex_unlock(&target_lock);
+
+	/*
 	 * Skip offline nodes. This can happen when memory
 	 * marked EFI_MEMORY_SP, "specific purpose", is applied
 	 * to all the memory in a proximity domain leading to
@@ -726,8 +854,8 @@ static void hmat_register_target(struct memory_target *target)
 	if (!target->registered) {
 		hmat_register_target_initiators(target);
 		hmat_register_target_cache(target);
-		hmat_register_target_perf(target, 0);
-		hmat_register_target_perf(target, 1);
+		hmat_register_target_perf(target, NODE_ACCESS_CLASS_0);
+		hmat_register_target_perf(target, NODE_ACCESS_CLASS_1);
 		target->registered = true;
 	}
 	mutex_unlock(&target_lock);
@@ -765,7 +893,7 @@ static int hmat_set_default_dram_perf(void)
 	int rc;
 	int nid, pxm;
 	struct memory_target *target;
-	struct node_hmem_attrs *attrs;
+	struct access_coordinate *attrs;
 
 	if (!default_dram_type)
 		return -EIO;
@@ -775,7 +903,7 @@ static int hmat_set_default_dram_perf(void)
 		target = find_mem_target(pxm);
 		if (!target)
 			continue;
-		attrs = &target->hmem_attrs[1];
+		attrs = &target->coord[1];
 		rc = mt_set_default_dram_perf(nid, attrs, "ACPI HMAT");
 		if (rc)
 			return rc;
@@ -789,7 +917,7 @@ static int hmat_calculate_adistance(struct notifier_block *self,
 {
 	static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
 	struct memory_target *target;
-	struct node_hmem_attrs *perf;
+	struct access_coordinate *perf;
 	int *adist = data;
 	int pxm;
 
@@ -802,7 +930,7 @@ static int hmat_calculate_adistance(struct notifier_block *self,
 	hmat_update_target_attrs(target, p_nodes, 1);
 	mutex_unlock(&target_lock);
 
-	perf = &target->hmem_attrs[1];
+	perf = &target->coord[1];
 
 	if (mt_perf_to_adistance(perf, adist))
 		return NOTIFY_OK;
@@ -870,6 +998,13 @@ static __init int hmat_init(void)
 				ACPI_SRAT_TYPE_MEMORY_AFFINITY,
 				srat_parse_mem_affinity, 0) < 0)
 		goto out_put;
+
+	if (acpi_table_parse_entries(ACPI_SIG_SRAT,
+				     sizeof(struct acpi_table_srat),
+				     ACPI_SRAT_TYPE_GENERIC_PORT_AFFINITY,
+				     srat_parse_genport_affinity, 0) < 0)
+		goto out_put;
+
 	acpi_put_table(tbl);
 
 	status = acpi_get_table(ACPI_SIG_HMAT, 0, &tbl);
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 07d76fb740b6..a6ead5204046 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -881,6 +881,7 @@ static struct fwnode_handle *acpi_parse_string_ref(const struct fwnode_handle *f
  * @index: Index of the reference to return
  * @num_args: Maximum number of arguments after each reference
  * @args: Location to store the returned reference with optional arguments
+ *	  (may be NULL)
  *
  * Find property with @name, verifify that it is a package containing at least
  * one object reference and if so, store the ACPI device object pointer to the
@@ -938,6 +939,9 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 		if (!device)
 			return -EINVAL;
 
+		if (!args)
+			return 0;
+
 		args->fwnode = acpi_fwnode_handle(device);
 		args->nargs = 0;
 
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 0e2c397b1399..dacad1d846c0 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -462,6 +462,13 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = {
 		},
 	},
 	{
+		/* Asus ExpertBook B1502CGA */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "B1502CGA"),
+		},
+	},
+	{
 		/* Asus ExpertBook B2402CBA */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
@@ -483,6 +490,20 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = {
 		},
 	},
 	{
+		/* Asus Vivobook E1504GA */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "E1504GA"),
+		},
+	},
+	{
+		/* Asus Vivobook E1504GAB */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "E1504GAB"),
+		},
+	},
+	{
 		/* LG Electronics 17U70P */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"),
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 0ba008773b00..e6ed1ba91e5c 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1561,8 +1561,7 @@ static inline const struct iommu_ops *acpi_iommu_fwspec_ops(struct device *dev)
 	return fwspec ? fwspec->ops : NULL;
 }
 
-static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
-						       const u32 *id_in)
+static int acpi_iommu_configure_id(struct device *dev, const u32 *id_in)
 {
 	int err;
 	const struct iommu_ops *ops;
@@ -1576,7 +1575,7 @@ static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
 	ops = acpi_iommu_fwspec_ops(dev);
 	if (ops) {
 		mutex_unlock(&iommu_probe_device_lock);
-		return ops;
+		return 0;
 	}
 
 	err = iort_iommu_configure_id(dev, id_in);
@@ -1593,12 +1592,14 @@ static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
 
 	/* Ignore all other errors apart from EPROBE_DEFER */
 	if (err == -EPROBE_DEFER) {
-		return ERR_PTR(err);
+		return err;
 	} else if (err) {
 		dev_dbg(dev, "Adding to IOMMU failed: %d\n", err);
-		return NULL;
+		return -ENODEV;
 	}
-	return acpi_iommu_fwspec_ops(dev);
+	if (!acpi_iommu_fwspec_ops(dev))
+		return -ENODEV;
+	return 0;
 }
 
 #else /* !CONFIG_IOMMU_API */
@@ -1610,10 +1611,9 @@ int acpi_iommu_fwspec_init(struct device *dev, u32 id,
 	return -ENODEV;
 }
 
-static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
-						       const u32 *id_in)
+static int acpi_iommu_configure_id(struct device *dev, const u32 *id_in)
 {
-	return NULL;
+	return -ENODEV;
 }
 
 #endif /* !CONFIG_IOMMU_API */
@@ -1627,7 +1627,7 @@ static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
 int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr,
 			  const u32 *input_id)
 {
-	const struct iommu_ops *iommu;
+	int ret;
 
 	if (attr == DEV_DMA_NOT_SUPPORTED) {
 		set_dma_ops(dev, &dma_dummy_ops);
@@ -1636,12 +1636,16 @@ int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr,
 
 	acpi_arch_dma_setup(dev);
 
-	iommu = acpi_iommu_configure_id(dev, input_id);
-	if (PTR_ERR(iommu) == -EPROBE_DEFER)
+	ret = acpi_iommu_configure_id(dev, input_id);
+	if (ret == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 
-	arch_setup_dma_ops(dev, 0, U64_MAX,
-				iommu, attr == DEV_DMA_COHERENT);
+	/*
+	 * Historically this routine doesn't fail driver probing due to errors
+	 * in acpi_iommu_configure_id()
+	 */
+
+	arch_setup_dma_ops(dev, 0, U64_MAX, attr == DEV_DMA_COHERENT);
 
 	return 0;
 }
diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index c1516337f668..b07f7d091d13 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -251,8 +251,9 @@ int __init_or_acpilib acpi_table_parse_entries_array(
 		return -ENODEV;
 	}
 
-	count = acpi_parse_entries_array(id, table_size, table_header,
-			proc, proc_num, max_entries);
+	count = acpi_parse_entries_array(id, table_size,
+					 (union fw_table_header *)table_header,
+					 proc, proc_num, max_entries);
 
 	acpi_put_table(table_header);
 	return count;
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 7658103ba760..eca24f41556d 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -478,6 +478,16 @@ binder_enqueue_thread_work_ilocked(struct binder_thread *thread,
 {
 	WARN_ON(!list_empty(&thread->waiting_thread_node));
 	binder_enqueue_work_ilocked(work, &thread->todo);
+
+	/* (e)poll-based threads require an explicit wakeup signal when
+	 * queuing their own work; they rely on these events to consume
+	 * messages without I/O block. Without it, threads risk waiting
+	 * indefinitely without handling the work.
+	 */
+	if (thread->looper & BINDER_LOOPER_STATE_POLL &&
+	    thread->pid == current->pid && !thread->process_todo)
+		wake_up_interruptible_sync(&thread->wait);
+
 	thread->process_todo = true;
 }
 
@@ -2077,9 +2087,8 @@ static void binder_transaction_buffer_release(struct binder_proc *proc,
 			 * Convert the address to an offset relative to
 			 * the base of the transaction buffer.
 			 */
-			fda_offset =
-			    (parent->buffer - (uintptr_t)buffer->user_data) +
-			    fda->parent_offset;
+			fda_offset = parent->buffer - buffer->user_data +
+				fda->parent_offset;
 			for (fd_index = 0; fd_index < fda->num_fds;
 			     fd_index++) {
 				u32 fd;
@@ -2597,7 +2606,7 @@ static int binder_translate_fd_array(struct list_head *pf_head,
 	 * Convert the address to an offset relative to
 	 * the base of the transaction buffer.
 	 */
-	fda_offset = (parent->buffer - (uintptr_t)t->buffer->user_data) +
+	fda_offset = parent->buffer - t->buffer->user_data +
 		fda->parent_offset;
 	sender_ufda_base = (void __user *)(uintptr_t)sender_uparent->buffer +
 				fda->parent_offset;
@@ -2672,8 +2681,9 @@ static int binder_fixup_parent(struct list_head *pf_head,
 				  proc->pid, thread->pid);
 		return -EINVAL;
 	}
-	buffer_offset = bp->parent_offset +
-			(uintptr_t)parent->buffer - (uintptr_t)b->user_data;
+
+	buffer_offset = bp->parent_offset + parent->buffer - b->user_data;
+
 	return binder_add_fixup(pf_head, buffer_offset, bp->buffer, 0);
 }
 
@@ -3225,7 +3235,7 @@ static void binder_transaction(struct binder_proc *proc,
 
 	t->buffer = binder_alloc_new_buf(&target_proc->alloc, tr->data_size,
 		tr->offsets_size, extra_buffers_size,
-		!reply && (t->flags & TF_ONE_WAY), current->tgid);
+		!reply && (t->flags & TF_ONE_WAY));
 	if (IS_ERR(t->buffer)) {
 		char *s;
 
@@ -3250,7 +3260,7 @@ static void binder_transaction(struct binder_proc *proc,
 				    ALIGN(extra_buffers_size, sizeof(void *)) -
 				    ALIGN(secctx_sz, sizeof(u64));
 
-		t->security_ctx = (uintptr_t)t->buffer->user_data + buf_offset;
+		t->security_ctx = t->buffer->user_data + buf_offset;
 		err = binder_alloc_copy_to_buffer(&target_proc->alloc,
 						  t->buffer, buf_offset,
 						  secctx, secctx_sz);
@@ -3527,8 +3537,7 @@ static void binder_transaction(struct binder_proc *proc,
 				goto err_translate_failed;
 			}
 			/* Fixup buffer pointer to target proc address space */
-			bp->buffer = (uintptr_t)
-				t->buffer->user_data + sg_buf_offset;
+			bp->buffer = t->buffer->user_data + sg_buf_offset;
 			sg_buf_offset += ALIGN(bp->length, sizeof(u64));
 
 			num_valid = (buffer_offset - off_start_offset) /
@@ -4698,7 +4707,7 @@ retry:
 		}
 		trd->data_size = t->buffer->data_size;
 		trd->offsets_size = t->buffer->offsets_size;
-		trd->data.ptr.buffer = (uintptr_t)t->buffer->user_data;
+		trd->data.ptr.buffer = t->buffer->user_data;
 		trd->data.ptr.offsets = trd->data.ptr.buffer +
 					ALIGN(t->buffer->data_size,
 					    sizeof(void *));
@@ -5030,7 +5039,7 @@ static __poll_t binder_poll(struct file *filp,
 
 	thread = binder_get_thread(proc);
 	if (!thread)
-		return POLLERR;
+		return EPOLLERR;
 
 	binder_inner_proc_lock(thread->proc);
 	thread->looper |= BINDER_LOOPER_STATE_POLL;
@@ -5981,9 +5990,9 @@ static void print_binder_transaction_ilocked(struct seq_file *m,
 	}
 	if (buffer->target_node)
 		seq_printf(m, " node %d", buffer->target_node->debug_id);
-	seq_printf(m, " size %zd:%zd data %pK\n",
+	seq_printf(m, " size %zd:%zd offset %lx\n",
 		   buffer->data_size, buffer->offsets_size,
-		   buffer->user_data);
+		   proc->alloc.buffer - buffer->user_data);
 }
 
 static void print_binder_work_ilocked(struct seq_file *m,
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index f69d30c9f50f..e0e4dc38b692 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -26,7 +26,7 @@
 #include "binder_alloc.h"
 #include "binder_trace.h"
 
-struct list_lru binder_alloc_lru;
+struct list_lru binder_freelist;
 
 static DEFINE_MUTEX(binder_alloc_mmap_lock);
 
@@ -125,23 +125,20 @@ static void binder_insert_allocated_buffer_locked(
 
 static struct binder_buffer *binder_alloc_prepare_to_free_locked(
 		struct binder_alloc *alloc,
-		uintptr_t user_ptr)
+		unsigned long user_ptr)
 {
 	struct rb_node *n = alloc->allocated_buffers.rb_node;
 	struct binder_buffer *buffer;
-	void __user *uptr;
-
-	uptr = (void __user *)user_ptr;
 
 	while (n) {
 		buffer = rb_entry(n, struct binder_buffer, rb_node);
 		BUG_ON(buffer->free);
 
-		if (uptr < buffer->user_data)
+		if (user_ptr < buffer->user_data) {
 			n = n->rb_left;
-		else if (uptr > buffer->user_data)
+		} else if (user_ptr > buffer->user_data) {
 			n = n->rb_right;
-		else {
+		} else {
 			/*
 			 * Guard against user threads attempting to
 			 * free the buffer when in use by kernel or
@@ -168,145 +165,168 @@ static struct binder_buffer *binder_alloc_prepare_to_free_locked(
  * Return:	Pointer to buffer or NULL
  */
 struct binder_buffer *binder_alloc_prepare_to_free(struct binder_alloc *alloc,
-						   uintptr_t user_ptr)
+						   unsigned long user_ptr)
 {
 	struct binder_buffer *buffer;
 
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	buffer = binder_alloc_prepare_to_free_locked(alloc, user_ptr);
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 	return buffer;
 }
 
-static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
-				    void __user *start, void __user *end)
+static inline void
+binder_set_installed_page(struct binder_lru_page *lru_page,
+			  struct page *page)
+{
+	/* Pairs with acquire in binder_get_installed_page() */
+	smp_store_release(&lru_page->page_ptr, page);
+}
+
+static inline struct page *
+binder_get_installed_page(struct binder_lru_page *lru_page)
+{
+	/* Pairs with release in binder_set_installed_page() */
+	return smp_load_acquire(&lru_page->page_ptr);
+}
+
+static void binder_lru_freelist_add(struct binder_alloc *alloc,
+				    unsigned long start, unsigned long end)
 {
-	void __user *page_addr;
-	unsigned long user_page_addr;
 	struct binder_lru_page *page;
-	struct vm_area_struct *vma = NULL;
-	struct mm_struct *mm = NULL;
-	bool need_mm = false;
+	unsigned long page_addr;
 
-	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-		     "%d: %s pages %pK-%pK\n", alloc->pid,
-		     allocate ? "allocate" : "free", start, end);
+	trace_binder_update_page_range(alloc, false, start, end);
 
-	if (end <= start)
-		return 0;
+	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
+		size_t index;
+		int ret;
 
-	trace_binder_update_page_range(alloc, allocate, start, end);
+		index = (page_addr - alloc->buffer) / PAGE_SIZE;
+		page = &alloc->pages[index];
 
-	if (allocate == 0)
-		goto free_range;
+		if (!binder_get_installed_page(page))
+			continue;
 
-	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
-		page = &alloc->pages[(page_addr - alloc->buffer) / PAGE_SIZE];
-		if (!page->page_ptr) {
-			need_mm = true;
-			break;
-		}
+		trace_binder_free_lru_start(alloc, index);
+
+		ret = list_lru_add_obj(&binder_freelist, &page->lru);
+		WARN_ON(!ret);
+
+		trace_binder_free_lru_end(alloc, index);
 	}
+}
+
+static int binder_install_single_page(struct binder_alloc *alloc,
+				      struct binder_lru_page *lru_page,
+				      unsigned long addr)
+{
+	struct page *page;
+	int ret = 0;
 
-	if (need_mm && mmget_not_zero(alloc->mm))
-		mm = alloc->mm;
+	if (!mmget_not_zero(alloc->mm))
+		return -ESRCH;
 
-	if (mm) {
-		mmap_write_lock(mm);
-		vma = alloc->vma;
+	/*
+	 * Protected with mmap_sem in write mode as multiple tasks
+	 * might race to install the same page.
+	 */
+	mmap_write_lock(alloc->mm);
+	if (binder_get_installed_page(lru_page))
+		goto out;
+
+	if (!alloc->vma) {
+		pr_err("%d: %s failed, no vma\n", alloc->pid, __func__);
+		ret = -ESRCH;
+		goto out;
 	}
 
-	if (!vma && need_mm) {
-		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
-				   "%d: binder_alloc_buf failed to map pages in userspace, no vma\n",
-				   alloc->pid);
-		goto err_no_vma;
+	page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
+	if (!page) {
+		pr_err("%d: failed to allocate page\n", alloc->pid);
+		ret = -ENOMEM;
+		goto out;
 	}
 
-	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
+	ret = vm_insert_page(alloc->vma, addr, page);
+	if (ret) {
+		pr_err("%d: %s failed to insert page at offset %lx with %d\n",
+		       alloc->pid, __func__, addr - alloc->buffer, ret);
+		__free_page(page);
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	/* Mark page installation complete and safe to use */
+	binder_set_installed_page(lru_page, page);
+out:
+	mmap_write_unlock(alloc->mm);
+	mmput_async(alloc->mm);
+	return ret;
+}
+
+static int binder_install_buffer_pages(struct binder_alloc *alloc,
+				       struct binder_buffer *buffer,
+				       size_t size)
+{
+	struct binder_lru_page *page;
+	unsigned long start, final;
+	unsigned long page_addr;
+
+	start = buffer->user_data & PAGE_MASK;
+	final = PAGE_ALIGN(buffer->user_data + size);
+
+	for (page_addr = start; page_addr < final; page_addr += PAGE_SIZE) {
+		unsigned long index;
 		int ret;
-		bool on_lru;
-		size_t index;
 
 		index = (page_addr - alloc->buffer) / PAGE_SIZE;
 		page = &alloc->pages[index];
 
-		if (page->page_ptr) {
-			trace_binder_alloc_lru_start(alloc, index);
-
-			on_lru = list_lru_del_obj(&binder_alloc_lru, &page->lru);
-			WARN_ON(!on_lru);
-
-			trace_binder_alloc_lru_end(alloc, index);
+		if (binder_get_installed_page(page))
 			continue;
-		}
-
-		if (WARN_ON(!vma))
-			goto err_page_ptr_cleared;
 
 		trace_binder_alloc_page_start(alloc, index);
-		page->page_ptr = alloc_page(GFP_KERNEL |
-					    __GFP_HIGHMEM |
-					    __GFP_ZERO);
-		if (!page->page_ptr) {
-			pr_err("%d: binder_alloc_buf failed for page at %pK\n",
-				alloc->pid, page_addr);
-			goto err_alloc_page_failed;
-		}
-		page->alloc = alloc;
-		INIT_LIST_HEAD(&page->lru);
-
-		user_page_addr = (uintptr_t)page_addr;
-		ret = vm_insert_page(vma, user_page_addr, page[0].page_ptr);
-		if (ret) {
-			pr_err("%d: binder_alloc_buf failed to map page at %lx in userspace\n",
-			       alloc->pid, user_page_addr);
-			goto err_vm_insert_page_failed;
-		}
 
-		if (index + 1 > alloc->pages_high)
-			alloc->pages_high = index + 1;
+		ret = binder_install_single_page(alloc, page, page_addr);
+		if (ret)
+			return ret;
 
 		trace_binder_alloc_page_end(alloc, index);
 	}
-	if (mm) {
-		mmap_write_unlock(mm);
-		mmput(mm);
-	}
+
 	return 0;
+}
 
-free_range:
-	for (page_addr = end - PAGE_SIZE; 1; page_addr -= PAGE_SIZE) {
-		bool ret;
-		size_t index;
+/* The range of pages should exclude those shared with other buffers */
+static void binder_lru_freelist_del(struct binder_alloc *alloc,
+				    unsigned long start, unsigned long end)
+{
+	struct binder_lru_page *page;
+	unsigned long page_addr;
+
+	trace_binder_update_page_range(alloc, true, start, end);
+
+	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
+		unsigned long index;
+		bool on_lru;
 
 		index = (page_addr - alloc->buffer) / PAGE_SIZE;
 		page = &alloc->pages[index];
 
-		trace_binder_free_lru_start(alloc, index);
+		if (page->page_ptr) {
+			trace_binder_alloc_lru_start(alloc, index);
 
-		ret = list_lru_add_obj(&binder_alloc_lru, &page->lru);
-		WARN_ON(!ret);
+			on_lru = list_lru_del_obj(&binder_freelist, &page->lru);
+			WARN_ON(!on_lru);
 
-		trace_binder_free_lru_end(alloc, index);
-		if (page_addr == start)
-			break;
-		continue;
-
-err_vm_insert_page_failed:
-		__free_page(page->page_ptr);
-		page->page_ptr = NULL;
-err_alloc_page_failed:
-err_page_ptr_cleared:
-		if (page_addr == start)
-			break;
-	}
-err_no_vma:
-	if (mm) {
-		mmap_write_unlock(mm);
-		mmput(mm);
+			trace_binder_alloc_lru_end(alloc, index);
+			continue;
+		}
+
+		if (index + 1 > alloc->pages_high)
+			alloc->pages_high = index + 1;
 	}
-	return vma ? -ENOMEM : -ESRCH;
 }
 
 static inline void binder_alloc_set_vma(struct binder_alloc *alloc,
@@ -323,7 +343,44 @@ static inline struct vm_area_struct *binder_alloc_get_vma(
 	return smp_load_acquire(&alloc->vma);
 }
 
-static bool debug_low_async_space_locked(struct binder_alloc *alloc, int pid)
+static void debug_no_space_locked(struct binder_alloc *alloc)
+{
+	size_t largest_alloc_size = 0;
+	struct binder_buffer *buffer;
+	size_t allocated_buffers = 0;
+	size_t largest_free_size = 0;
+	size_t total_alloc_size = 0;
+	size_t total_free_size = 0;
+	size_t free_buffers = 0;
+	size_t buffer_size;
+	struct rb_node *n;
+
+	for (n = rb_first(&alloc->allocated_buffers); n; n = rb_next(n)) {
+		buffer = rb_entry(n, struct binder_buffer, rb_node);
+		buffer_size = binder_alloc_buffer_size(alloc, buffer);
+		allocated_buffers++;
+		total_alloc_size += buffer_size;
+		if (buffer_size > largest_alloc_size)
+			largest_alloc_size = buffer_size;
+	}
+
+	for (n = rb_first(&alloc->free_buffers); n; n = rb_next(n)) {
+		buffer = rb_entry(n, struct binder_buffer, rb_node);
+		buffer_size = binder_alloc_buffer_size(alloc, buffer);
+		free_buffers++;
+		total_free_size += buffer_size;
+		if (buffer_size > largest_free_size)
+			largest_free_size = buffer_size;
+	}
+
+	binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
+			   "allocated: %zd (num: %zd largest: %zd), free: %zd (num: %zd largest: %zd)\n",
+			   total_alloc_size, allocated_buffers,
+			   largest_alloc_size, total_free_size,
+			   free_buffers, largest_free_size);
+}
+
+static bool debug_low_async_space_locked(struct binder_alloc *alloc)
 {
 	/*
 	 * Find the amount and size of buffers allocated by the current caller;
@@ -332,10 +389,20 @@ static bool debug_low_async_space_locked(struct binder_alloc *alloc, int pid)
 	 * and at some point we'll catch them in the act. This is more efficient
 	 * than keeping a map per pid.
 	 */
-	struct rb_node *n;
 	struct binder_buffer *buffer;
 	size_t total_alloc_size = 0;
+	int pid = current->tgid;
 	size_t num_buffers = 0;
+	struct rb_node *n;
+
+	/*
+	 * Only start detecting spammers once we have less than 20% of async
+	 * space left (which is less than 10% of total buffer size).
+	 */
+	if (alloc->free_async_space >= alloc->buffer_size / 10) {
+		alloc->oneway_spam_detected = false;
+		return false;
+	}
 
 	for (n = rb_first(&alloc->allocated_buffers); n != NULL;
 		 n = rb_next(n)) {
@@ -344,8 +411,7 @@ static bool debug_low_async_space_locked(struct binder_alloc *alloc, int pid)
 			continue;
 		if (!buffer->async_transaction)
 			continue;
-		total_alloc_size += binder_alloc_buffer_size(alloc, buffer)
-			+ sizeof(struct binder_buffer);
+		total_alloc_size += binder_alloc_buffer_size(alloc, buffer);
 		num_buffers++;
 	}
 
@@ -366,58 +432,28 @@ static bool debug_low_async_space_locked(struct binder_alloc *alloc, int pid)
 	return false;
 }
 
+/* Callers preallocate @new_buffer, it is freed by this function if unused */
 static struct binder_buffer *binder_alloc_new_buf_locked(
 				struct binder_alloc *alloc,
-				size_t data_size,
-				size_t offsets_size,
-				size_t extra_buffers_size,
-				int is_async,
-				int pid)
+				struct binder_buffer *new_buffer,
+				size_t size,
+				int is_async)
 {
 	struct rb_node *n = alloc->free_buffers.rb_node;
+	struct rb_node *best_fit = NULL;
 	struct binder_buffer *buffer;
+	unsigned long next_used_page;
+	unsigned long curr_last_page;
 	size_t buffer_size;
-	struct rb_node *best_fit = NULL;
-	void __user *has_page_addr;
-	void __user *end_page_addr;
-	size_t size, data_offsets_size;
-	int ret;
 
-	/* Check binder_alloc is fully initialized */
-	if (!binder_alloc_get_vma(alloc)) {
-		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
-				   "%d: binder_alloc_buf, no vma\n",
-				   alloc->pid);
-		return ERR_PTR(-ESRCH);
-	}
-
-	data_offsets_size = ALIGN(data_size, sizeof(void *)) +
-		ALIGN(offsets_size, sizeof(void *));
-
-	if (data_offsets_size < data_size || data_offsets_size < offsets_size) {
-		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				"%d: got transaction with invalid size %zd-%zd\n",
-				alloc->pid, data_size, offsets_size);
-		return ERR_PTR(-EINVAL);
-	}
-	size = data_offsets_size + ALIGN(extra_buffers_size, sizeof(void *));
-	if (size < data_offsets_size || size < extra_buffers_size) {
-		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				"%d: got transaction with invalid extra_buffers_size %zd\n",
-				alloc->pid, extra_buffers_size);
-		return ERR_PTR(-EINVAL);
-	}
-	if (is_async &&
-	    alloc->free_async_space < size + sizeof(struct binder_buffer)) {
+	if (is_async && alloc->free_async_space < size) {
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
 			     "%d: binder_alloc_buf size %zd failed, no async space left\n",
 			      alloc->pid, size);
-		return ERR_PTR(-ENOSPC);
+		buffer = ERR_PTR(-ENOSPC);
+		goto out;
 	}
 
-	/* Pad 0-size buffers so they get assigned unique addresses */
-	size = max(size, sizeof(void *));
-
 	while (n) {
 		buffer = rb_entry(n, struct binder_buffer, rb_node);
 		BUG_ON(!buffer->free);
@@ -426,121 +462,92 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 		if (size < buffer_size) {
 			best_fit = n;
 			n = n->rb_left;
-		} else if (size > buffer_size)
+		} else if (size > buffer_size) {
 			n = n->rb_right;
-		else {
+		} else {
 			best_fit = n;
 			break;
 		}
 	}
-	if (best_fit == NULL) {
-		size_t allocated_buffers = 0;
-		size_t largest_alloc_size = 0;
-		size_t total_alloc_size = 0;
-		size_t free_buffers = 0;
-		size_t largest_free_size = 0;
-		size_t total_free_size = 0;
-
-		for (n = rb_first(&alloc->allocated_buffers); n != NULL;
-		     n = rb_next(n)) {
-			buffer = rb_entry(n, struct binder_buffer, rb_node);
-			buffer_size = binder_alloc_buffer_size(alloc, buffer);
-			allocated_buffers++;
-			total_alloc_size += buffer_size;
-			if (buffer_size > largest_alloc_size)
-				largest_alloc_size = buffer_size;
-		}
-		for (n = rb_first(&alloc->free_buffers); n != NULL;
-		     n = rb_next(n)) {
-			buffer = rb_entry(n, struct binder_buffer, rb_node);
-			buffer_size = binder_alloc_buffer_size(alloc, buffer);
-			free_buffers++;
-			total_free_size += buffer_size;
-			if (buffer_size > largest_free_size)
-				largest_free_size = buffer_size;
-		}
+
+	if (unlikely(!best_fit)) {
 		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
 				   "%d: binder_alloc_buf size %zd failed, no address space\n",
 				   alloc->pid, size);
-		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
-				   "allocated: %zd (num: %zd largest: %zd), free: %zd (num: %zd largest: %zd)\n",
-				   total_alloc_size, allocated_buffers,
-				   largest_alloc_size, total_free_size,
-				   free_buffers, largest_free_size);
-		return ERR_PTR(-ENOSPC);
+		debug_no_space_locked(alloc);
+		buffer = ERR_PTR(-ENOSPC);
+		goto out;
 	}
-	if (n == NULL) {
+
+	if (buffer_size != size) {
+		/* Found an oversized buffer and needs to be split */
 		buffer = rb_entry(best_fit, struct binder_buffer, rb_node);
 		buffer_size = binder_alloc_buffer_size(alloc, buffer);
+
+		WARN_ON(n || buffer_size == size);
+		new_buffer->user_data = buffer->user_data + size;
+		list_add(&new_buffer->entry, &buffer->entry);
+		new_buffer->free = 1;
+		binder_insert_free_buffer(alloc, new_buffer);
+		new_buffer = NULL;
 	}
 
 	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
 		     "%d: binder_alloc_buf size %zd got buffer %pK size %zd\n",
 		      alloc->pid, size, buffer, buffer_size);
 
-	has_page_addr = (void __user *)
-		(((uintptr_t)buffer->user_data + buffer_size) & PAGE_MASK);
-	WARN_ON(n && buffer_size != size);
-	end_page_addr =
-		(void __user *)PAGE_ALIGN((uintptr_t)buffer->user_data + size);
-	if (end_page_addr > has_page_addr)
-		end_page_addr = has_page_addr;
-	ret = binder_update_page_range(alloc, 1, (void __user *)
-		PAGE_ALIGN((uintptr_t)buffer->user_data), end_page_addr);
-	if (ret)
-		return ERR_PTR(ret);
-
-	if (buffer_size != size) {
-		struct binder_buffer *new_buffer;
-
-		new_buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
-		if (!new_buffer) {
-			pr_err("%s: %d failed to alloc new buffer struct\n",
-			       __func__, alloc->pid);
-			goto err_alloc_buf_struct_failed;
-		}
-		new_buffer->user_data = (u8 __user *)buffer->user_data + size;
-		list_add(&new_buffer->entry, &buffer->entry);
-		new_buffer->free = 1;
-		binder_insert_free_buffer(alloc, new_buffer);
-	}
+	/*
+	 * Now we remove the pages from the freelist. A clever calculation
+	 * with buffer_size determines if the last page is shared with an
+	 * adjacent in-use buffer. In such case, the page has been already
+	 * removed from the freelist so we trim our range short.
+	 */
+	next_used_page = (buffer->user_data + buffer_size) & PAGE_MASK;
+	curr_last_page = PAGE_ALIGN(buffer->user_data + size);
+	binder_lru_freelist_del(alloc, PAGE_ALIGN(buffer->user_data),
+				min(next_used_page, curr_last_page));
 
-	rb_erase(best_fit, &alloc->free_buffers);
+	rb_erase(&buffer->rb_node, &alloc->free_buffers);
 	buffer->free = 0;
 	buffer->allow_user_free = 0;
 	binder_insert_allocated_buffer_locked(alloc, buffer);
-	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-		     "%d: binder_alloc_buf size %zd got %pK\n",
-		      alloc->pid, size, buffer);
-	buffer->data_size = data_size;
-	buffer->offsets_size = offsets_size;
 	buffer->async_transaction = is_async;
-	buffer->extra_buffers_size = extra_buffers_size;
-	buffer->pid = pid;
 	buffer->oneway_spam_suspect = false;
 	if (is_async) {
-		alloc->free_async_space -= size + sizeof(struct binder_buffer);
+		alloc->free_async_space -= size;
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
 			     "%d: binder_alloc_buf size %zd async free %zd\n",
 			      alloc->pid, size, alloc->free_async_space);
-		if (alloc->free_async_space < alloc->buffer_size / 10) {
-			/*
-			 * Start detecting spammers once we have less than 20%
-			 * of async space left (which is less than 10% of total
-			 * buffer size).
-			 */
-			buffer->oneway_spam_suspect = debug_low_async_space_locked(alloc, pid);
-		} else {
-			alloc->oneway_spam_detected = false;
-		}
+		if (debug_low_async_space_locked(alloc))
+			buffer->oneway_spam_suspect = true;
 	}
+
+out:
+	/* Discard possibly unused new_buffer */
+	kfree(new_buffer);
 	return buffer;
+}
 
-err_alloc_buf_struct_failed:
-	binder_update_page_range(alloc, 0, (void __user *)
-				 PAGE_ALIGN((uintptr_t)buffer->user_data),
-				 end_page_addr);
-	return ERR_PTR(-ENOMEM);
+/* Calculate the sanitized total size, returns 0 for invalid request */
+static inline size_t sanitized_size(size_t data_size,
+				    size_t offsets_size,
+				    size_t extra_buffers_size)
+{
+	size_t total, tmp;
+
+	/* Align to pointer size and check for overflows */
+	tmp = ALIGN(data_size, sizeof(void *)) +
+		ALIGN(offsets_size, sizeof(void *));
+	if (tmp < data_size || tmp < offsets_size)
+		return 0;
+	total = tmp + ALIGN(extra_buffers_size, sizeof(void *));
+	if (total < tmp || total < extra_buffers_size)
+		return 0;
+
+	/* Pad 0-sized buffers so they get a unique address */
+	total = max(total, sizeof(void *));
+
+	return total;
 }
 
 /**
@@ -550,87 +557,101 @@ err_alloc_buf_struct_failed:
  * @offsets_size:       user specified buffer offset
  * @extra_buffers_size: size of extra space for meta-data (eg, security context)
  * @is_async:           buffer for async transaction
- * @pid:				pid to attribute allocation to (used for debugging)
  *
  * Allocate a new buffer given the requested sizes. Returns
  * the kernel version of the buffer pointer. The size allocated
  * is the sum of the three given sizes (each rounded up to
  * pointer-sized boundary)
  *
- * Return:	The allocated buffer or %NULL if error
+ * Return:	The allocated buffer or %ERR_PTR(-errno) if error
  */
 struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 					   size_t data_size,
 					   size_t offsets_size,
 					   size_t extra_buffers_size,
-					   int is_async,
-					   int pid)
+					   int is_async)
 {
-	struct binder_buffer *buffer;
+	struct binder_buffer *buffer, *next;
+	size_t size;
+	int ret;
+
+	/* Check binder_alloc is fully initialized */
+	if (!binder_alloc_get_vma(alloc)) {
+		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
+				   "%d: binder_alloc_buf, no vma\n",
+				   alloc->pid);
+		return ERR_PTR(-ESRCH);
+	}
+
+	size = sanitized_size(data_size, offsets_size, extra_buffers_size);
+	if (unlikely(!size)) {
+		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
+				   "%d: got transaction with invalid size %zd-%zd-%zd\n",
+				   alloc->pid, data_size, offsets_size,
+				   extra_buffers_size);
+		return ERR_PTR(-EINVAL);
+	}
 
-	mutex_lock(&alloc->mutex);
-	buffer = binder_alloc_new_buf_locked(alloc, data_size, offsets_size,
-					     extra_buffers_size, is_async, pid);
-	mutex_unlock(&alloc->mutex);
+	/* Preallocate the next buffer */
+	next = kzalloc(sizeof(*next), GFP_KERNEL);
+	if (!next)
+		return ERR_PTR(-ENOMEM);
+
+	spin_lock(&alloc->lock);
+	buffer = binder_alloc_new_buf_locked(alloc, next, size, is_async);
+	if (IS_ERR(buffer)) {
+		spin_unlock(&alloc->lock);
+		goto out;
+	}
+
+	buffer->data_size = data_size;
+	buffer->offsets_size = offsets_size;
+	buffer->extra_buffers_size = extra_buffers_size;
+	buffer->pid = current->tgid;
+	spin_unlock(&alloc->lock);
+
+	ret = binder_install_buffer_pages(alloc, buffer, size);
+	if (ret) {
+		binder_alloc_free_buf(alloc, buffer);
+		buffer = ERR_PTR(ret);
+	}
+out:
 	return buffer;
 }
 
-static void __user *buffer_start_page(struct binder_buffer *buffer)
+static unsigned long buffer_start_page(struct binder_buffer *buffer)
 {
-	return (void __user *)((uintptr_t)buffer->user_data & PAGE_MASK);
+	return buffer->user_data & PAGE_MASK;
 }
 
-static void __user *prev_buffer_end_page(struct binder_buffer *buffer)
+static unsigned long prev_buffer_end_page(struct binder_buffer *buffer)
 {
-	return (void __user *)
-		(((uintptr_t)(buffer->user_data) - 1) & PAGE_MASK);
+	return (buffer->user_data - 1) & PAGE_MASK;
 }
 
 static void binder_delete_free_buffer(struct binder_alloc *alloc,
 				      struct binder_buffer *buffer)
 {
-	struct binder_buffer *prev, *next = NULL;
-	bool to_free = true;
+	struct binder_buffer *prev, *next;
+
+	if (PAGE_ALIGNED(buffer->user_data))
+		goto skip_freelist;
 
 	BUG_ON(alloc->buffers.next == &buffer->entry);
 	prev = binder_buffer_prev(buffer);
 	BUG_ON(!prev->free);
-	if (prev_buffer_end_page(prev) == buffer_start_page(buffer)) {
-		to_free = false;
-		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				   "%d: merge free, buffer %pK share page with %pK\n",
-				   alloc->pid, buffer->user_data,
-				   prev->user_data);
-	}
+	if (prev_buffer_end_page(prev) == buffer_start_page(buffer))
+		goto skip_freelist;
 
 	if (!list_is_last(&buffer->entry, &alloc->buffers)) {
 		next = binder_buffer_next(buffer);
-		if (buffer_start_page(next) == buffer_start_page(buffer)) {
-			to_free = false;
-			binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-					   "%d: merge free, buffer %pK share page with %pK\n",
-					   alloc->pid,
-					   buffer->user_data,
-					   next->user_data);
-		}
-	}
-
-	if (PAGE_ALIGNED(buffer->user_data)) {
-		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				   "%d: merge free, buffer start %pK is page aligned\n",
-				   alloc->pid, buffer->user_data);
-		to_free = false;
+		if (buffer_start_page(next) == buffer_start_page(buffer))
+			goto skip_freelist;
 	}
 
-	if (to_free) {
-		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				   "%d: merge free, buffer %pK do not share page with %pK or %pK\n",
-				   alloc->pid, buffer->user_data,
-				   prev->user_data,
-				   next ? next->user_data : NULL);
-		binder_update_page_range(alloc, 0, buffer_start_page(buffer),
-					 buffer_start_page(buffer) + PAGE_SIZE);
-	}
+	binder_lru_freelist_add(alloc, buffer_start_page(buffer),
+				buffer_start_page(buffer) + PAGE_SIZE);
+skip_freelist:
 	list_del(&buffer->entry);
 	kfree(buffer);
 }
@@ -657,17 +678,14 @@ static void binder_free_buf_locked(struct binder_alloc *alloc,
 	BUG_ON(buffer->user_data > alloc->buffer + alloc->buffer_size);
 
 	if (buffer->async_transaction) {
-		alloc->free_async_space += buffer_size + sizeof(struct binder_buffer);
-
+		alloc->free_async_space += buffer_size;
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
 			     "%d: binder_free_buf size %zd async free %zd\n",
 			      alloc->pid, size, alloc->free_async_space);
 	}
 
-	binder_update_page_range(alloc, 0,
-		(void __user *)PAGE_ALIGN((uintptr_t)buffer->user_data),
-		(void __user *)(((uintptr_t)
-			  buffer->user_data + buffer_size) & PAGE_MASK));
+	binder_lru_freelist_add(alloc, PAGE_ALIGN(buffer->user_data),
+				(buffer->user_data + buffer_size) & PAGE_MASK);
 
 	rb_erase(&buffer->rb_node, &alloc->allocated_buffers);
 	buffer->free = 1;
@@ -691,8 +709,68 @@ static void binder_free_buf_locked(struct binder_alloc *alloc,
 	binder_insert_free_buffer(alloc, buffer);
 }
 
+/**
+ * binder_alloc_get_page() - get kernel pointer for given buffer offset
+ * @alloc: binder_alloc for this proc
+ * @buffer: binder buffer to be accessed
+ * @buffer_offset: offset into @buffer data
+ * @pgoffp: address to copy final page offset to
+ *
+ * Lookup the struct page corresponding to the address
+ * at @buffer_offset into @buffer->user_data. If @pgoffp is not
+ * NULL, the byte-offset into the page is written there.
+ *
+ * The caller is responsible to ensure that the offset points
+ * to a valid address within the @buffer and that @buffer is
+ * not freeable by the user. Since it can't be freed, we are
+ * guaranteed that the corresponding elements of @alloc->pages[]
+ * cannot change.
+ *
+ * Return: struct page
+ */
+static struct page *binder_alloc_get_page(struct binder_alloc *alloc,
+					  struct binder_buffer *buffer,
+					  binder_size_t buffer_offset,
+					  pgoff_t *pgoffp)
+{
+	binder_size_t buffer_space_offset = buffer_offset +
+		(buffer->user_data - alloc->buffer);
+	pgoff_t pgoff = buffer_space_offset & ~PAGE_MASK;
+	size_t index = buffer_space_offset >> PAGE_SHIFT;
+	struct binder_lru_page *lru_page;
+
+	lru_page = &alloc->pages[index];
+	*pgoffp = pgoff;
+	return lru_page->page_ptr;
+}
+
+/**
+ * binder_alloc_clear_buf() - zero out buffer
+ * @alloc: binder_alloc for this proc
+ * @buffer: binder buffer to be cleared
+ *
+ * memset the given buffer to 0
+ */
 static void binder_alloc_clear_buf(struct binder_alloc *alloc,
-				   struct binder_buffer *buffer);
+				   struct binder_buffer *buffer)
+{
+	size_t bytes = binder_alloc_buffer_size(alloc, buffer);
+	binder_size_t buffer_offset = 0;
+
+	while (bytes) {
+		unsigned long size;
+		struct page *page;
+		pgoff_t pgoff;
+
+		page = binder_alloc_get_page(alloc, buffer,
+					     buffer_offset, &pgoff);
+		size = min_t(size_t, bytes, PAGE_SIZE - pgoff);
+		memset_page(page, pgoff, 0, size);
+		bytes -= size;
+		buffer_offset += size;
+	}
+}
+
 /**
  * binder_alloc_free_buf() - free a binder buffer
  * @alloc:	binder_alloc for this proc
@@ -706,18 +784,18 @@ void binder_alloc_free_buf(struct binder_alloc *alloc,
 	/*
 	 * We could eliminate the call to binder_alloc_clear_buf()
 	 * from binder_alloc_deferred_release() by moving this to
-	 * binder_alloc_free_buf_locked(). However, that could
-	 * increase contention for the alloc mutex if clear_on_free
-	 * is used frequently for large buffers. The mutex is not
+	 * binder_free_buf_locked(). However, that could
+	 * increase contention for the alloc->lock if clear_on_free
+	 * is used frequently for large buffers. This lock is not
 	 * needed for correctness here.
 	 */
 	if (buffer->clear_on_free) {
 		binder_alloc_clear_buf(alloc, buffer);
 		buffer->clear_on_free = false;
 	}
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	binder_free_buf_locked(alloc, buffer);
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 }
 
 /**
@@ -736,9 +814,9 @@ void binder_alloc_free_buf(struct binder_alloc *alloc,
 int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 			      struct vm_area_struct *vma)
 {
-	int ret;
-	const char *failure_string;
 	struct binder_buffer *buffer;
+	const char *failure_string;
+	int ret, i;
 
 	if (unlikely(vma->vm_mm != alloc->mm)) {
 		ret = -EINVAL;
@@ -756,7 +834,7 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 				   SZ_4M);
 	mutex_unlock(&binder_alloc_mmap_lock);
 
-	alloc->buffer = (void __user *)vma->vm_start;
+	alloc->buffer = vma->vm_start;
 
 	alloc->pages = kcalloc(alloc->buffer_size / PAGE_SIZE,
 			       sizeof(alloc->pages[0]),
@@ -767,6 +845,11 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 		goto err_alloc_pages_failed;
 	}
 
+	for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
+		alloc->pages[i].alloc = alloc;
+		INIT_LIST_HEAD(&alloc->pages[i].lru);
+	}
+
 	buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
 	if (!buffer) {
 		ret = -ENOMEM;
@@ -789,7 +872,7 @@ err_alloc_buf_struct_failed:
 	kfree(alloc->pages);
 	alloc->pages = NULL;
 err_alloc_pages_failed:
-	alloc->buffer = NULL;
+	alloc->buffer = 0;
 	mutex_lock(&binder_alloc_mmap_lock);
 	alloc->buffer_size = 0;
 err_already_mapped:
@@ -810,7 +893,7 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 	struct binder_buffer *buffer;
 
 	buffers = 0;
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	BUG_ON(alloc->vma);
 
 	while ((n = rb_first(&alloc->allocated_buffers))) {
@@ -842,25 +925,25 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 		int i;
 
 		for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
-			void __user *page_addr;
+			unsigned long page_addr;
 			bool on_lru;
 
 			if (!alloc->pages[i].page_ptr)
 				continue;
 
-			on_lru = list_lru_del_obj(&binder_alloc_lru,
-					      &alloc->pages[i].lru);
+			on_lru = list_lru_del_obj(&binder_freelist,
+						  &alloc->pages[i].lru);
 			page_addr = alloc->buffer + i * PAGE_SIZE;
 			binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				     "%s: %d: page %d at %pK %s\n",
-				     __func__, alloc->pid, i, page_addr,
+				     "%s: %d: page %d %s\n",
+				     __func__, alloc->pid, i,
 				     on_lru ? "on lru" : "active");
 			__free_page(alloc->pages[i].page_ptr);
 			page_count++;
 		}
 		kfree(alloc->pages);
 	}
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 	if (alloc->mm)
 		mmdrop(alloc->mm);
 
@@ -869,16 +952,6 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 		     __func__, alloc->pid, buffers, page_count);
 }
 
-static void print_binder_buffer(struct seq_file *m, const char *prefix,
-				struct binder_buffer *buffer)
-{
-	seq_printf(m, "%s %d: %pK size %zd:%zd:%zd %s\n",
-		   prefix, buffer->debug_id, buffer->user_data,
-		   buffer->data_size, buffer->offsets_size,
-		   buffer->extra_buffers_size,
-		   buffer->transaction ? "active" : "delivered");
-}
-
 /**
  * binder_alloc_print_allocated() - print buffer info
  * @m:     seq_file for output via seq_printf()
@@ -890,13 +963,20 @@ static void print_binder_buffer(struct seq_file *m, const char *prefix,
 void binder_alloc_print_allocated(struct seq_file *m,
 				  struct binder_alloc *alloc)
 {
+	struct binder_buffer *buffer;
 	struct rb_node *n;
 
-	mutex_lock(&alloc->mutex);
-	for (n = rb_first(&alloc->allocated_buffers); n != NULL; n = rb_next(n))
-		print_binder_buffer(m, "  buffer",
-				    rb_entry(n, struct binder_buffer, rb_node));
-	mutex_unlock(&alloc->mutex);
+	spin_lock(&alloc->lock);
+	for (n = rb_first(&alloc->allocated_buffers); n; n = rb_next(n)) {
+		buffer = rb_entry(n, struct binder_buffer, rb_node);
+		seq_printf(m, "  buffer %d: %lx size %zd:%zd:%zd %s\n",
+			   buffer->debug_id,
+			   buffer->user_data - alloc->buffer,
+			   buffer->data_size, buffer->offsets_size,
+			   buffer->extra_buffers_size,
+			   buffer->transaction ? "active" : "delivered");
+	}
+	spin_unlock(&alloc->lock);
 }
 
 /**
@@ -913,7 +993,7 @@ void binder_alloc_print_pages(struct seq_file *m,
 	int lru = 0;
 	int free = 0;
 
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	/*
 	 * Make sure the binder_alloc is fully initialized, otherwise we might
 	 * read inconsistent state.
@@ -929,7 +1009,7 @@ void binder_alloc_print_pages(struct seq_file *m,
 				lru++;
 		}
 	}
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 	seq_printf(m, "  pages: %d:%d:%d\n", active, lru, free);
 	seq_printf(m, "  pages high watermark: %zu\n", alloc->pages_high);
 }
@@ -945,10 +1025,10 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc)
 	struct rb_node *n;
 	int count = 0;
 
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	for (n = rb_first(&alloc->allocated_buffers); n != NULL; n = rb_next(n))
 		count++;
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 	return count;
 }
 
@@ -981,33 +1061,39 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 				       void *cb_arg)
 	__must_hold(lock)
 {
-	struct mm_struct *mm = NULL;
-	struct binder_lru_page *page = container_of(item,
-						    struct binder_lru_page,
-						    lru);
-	struct binder_alloc *alloc;
-	uintptr_t page_addr;
-	size_t index;
+	struct binder_lru_page *page = container_of(item, typeof(*page), lru);
+	struct binder_alloc *alloc = page->alloc;
+	struct mm_struct *mm = alloc->mm;
 	struct vm_area_struct *vma;
+	struct page *page_to_free;
+	unsigned long page_addr;
+	size_t index;
 
-	alloc = page->alloc;
-	if (!mutex_trylock(&alloc->mutex))
-		goto err_get_alloc_mutex_failed;
-
+	if (!mmget_not_zero(mm))
+		goto err_mmget;
+	if (!mmap_read_trylock(mm))
+		goto err_mmap_read_lock_failed;
+	if (!spin_trylock(&alloc->lock))
+		goto err_get_alloc_lock_failed;
 	if (!page->page_ptr)
 		goto err_page_already_freed;
 
 	index = page - alloc->pages;
-	page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE;
+	page_addr = alloc->buffer + index * PAGE_SIZE;
 
-	mm = alloc->mm;
-	if (!mmget_not_zero(mm))
-		goto err_mmget;
-	if (!mmap_read_trylock(mm))
-		goto err_mmap_read_lock_failed;
-	vma = binder_alloc_get_vma(alloc);
+	vma = vma_lookup(mm, page_addr);
+	if (vma && vma != binder_alloc_get_vma(alloc))
+		goto err_invalid_vma;
+
+	trace_binder_unmap_kernel_start(alloc, index);
+
+	page_to_free = page->page_ptr;
+	page->page_ptr = NULL;
+
+	trace_binder_unmap_kernel_end(alloc, index);
 
 	list_lru_isolate(lru, item);
+	spin_unlock(&alloc->lock);
 	spin_unlock(lock);
 
 	if (vma) {
@@ -1017,39 +1103,35 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 
 		trace_binder_unmap_user_end(alloc, index);
 	}
+
 	mmap_read_unlock(mm);
 	mmput_async(mm);
-
-	trace_binder_unmap_kernel_start(alloc, index);
-
-	__free_page(page->page_ptr);
-	page->page_ptr = NULL;
-
-	trace_binder_unmap_kernel_end(alloc, index);
+	__free_page(page_to_free);
 
 	spin_lock(lock);
-	mutex_unlock(&alloc->mutex);
 	return LRU_REMOVED_RETRY;
 
+err_invalid_vma:
+err_page_already_freed:
+	spin_unlock(&alloc->lock);
+err_get_alloc_lock_failed:
+	mmap_read_unlock(mm);
 err_mmap_read_lock_failed:
 	mmput_async(mm);
 err_mmget:
-err_page_already_freed:
-	mutex_unlock(&alloc->mutex);
-err_get_alloc_mutex_failed:
 	return LRU_SKIP;
 }
 
 static unsigned long
 binder_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 {
-	return list_lru_count(&binder_alloc_lru);
+	return list_lru_count(&binder_freelist);
 }
 
 static unsigned long
 binder_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 {
-	return list_lru_walk(&binder_alloc_lru, binder_alloc_free_page,
+	return list_lru_walk(&binder_freelist, binder_alloc_free_page,
 			    NULL, sc->nr_to_scan);
 }
 
@@ -1067,7 +1149,7 @@ void binder_alloc_init(struct binder_alloc *alloc)
 	alloc->pid = current->group_leader->pid;
 	alloc->mm = current->mm;
 	mmgrab(alloc->mm);
-	mutex_init(&alloc->mutex);
+	spin_lock_init(&alloc->lock);
 	INIT_LIST_HEAD(&alloc->buffers);
 }
 
@@ -1075,13 +1157,13 @@ int binder_alloc_shrinker_init(void)
 {
 	int ret;
 
-	ret = list_lru_init(&binder_alloc_lru);
+	ret = list_lru_init(&binder_freelist);
 	if (ret)
 		return ret;
 
 	binder_shrinker = shrinker_alloc(0, "android-binder");
 	if (!binder_shrinker) {
-		list_lru_destroy(&binder_alloc_lru);
+		list_lru_destroy(&binder_freelist);
 		return -ENOMEM;
 	}
 
@@ -1096,7 +1178,7 @@ int binder_alloc_shrinker_init(void)
 void binder_alloc_shrinker_exit(void)
 {
 	shrinker_free(binder_shrinker);
-	list_lru_destroy(&binder_alloc_lru);
+	list_lru_destroy(&binder_freelist);
 }
 
 /**
@@ -1132,68 +1214,6 @@ static inline bool check_buffer(struct binder_alloc *alloc,
 }
 
 /**
- * binder_alloc_get_page() - get kernel pointer for given buffer offset
- * @alloc: binder_alloc for this proc
- * @buffer: binder buffer to be accessed
- * @buffer_offset: offset into @buffer data
- * @pgoffp: address to copy final page offset to
- *
- * Lookup the struct page corresponding to the address
- * at @buffer_offset into @buffer->user_data. If @pgoffp is not
- * NULL, the byte-offset into the page is written there.
- *
- * The caller is responsible to ensure that the offset points
- * to a valid address within the @buffer and that @buffer is
- * not freeable by the user. Since it can't be freed, we are
- * guaranteed that the corresponding elements of @alloc->pages[]
- * cannot change.
- *
- * Return: struct page
- */
-static struct page *binder_alloc_get_page(struct binder_alloc *alloc,
-					  struct binder_buffer *buffer,
-					  binder_size_t buffer_offset,
-					  pgoff_t *pgoffp)
-{
-	binder_size_t buffer_space_offset = buffer_offset +
-		(buffer->user_data - alloc->buffer);
-	pgoff_t pgoff = buffer_space_offset & ~PAGE_MASK;
-	size_t index = buffer_space_offset >> PAGE_SHIFT;
-	struct binder_lru_page *lru_page;
-
-	lru_page = &alloc->pages[index];
-	*pgoffp = pgoff;
-	return lru_page->page_ptr;
-}
-
-/**
- * binder_alloc_clear_buf() - zero out buffer
- * @alloc: binder_alloc for this proc
- * @buffer: binder buffer to be cleared
- *
- * memset the given buffer to 0
- */
-static void binder_alloc_clear_buf(struct binder_alloc *alloc,
-				   struct binder_buffer *buffer)
-{
-	size_t bytes = binder_alloc_buffer_size(alloc, buffer);
-	binder_size_t buffer_offset = 0;
-
-	while (bytes) {
-		unsigned long size;
-		struct page *page;
-		pgoff_t pgoff;
-
-		page = binder_alloc_get_page(alloc, buffer,
-					     buffer_offset, &pgoff);
-		size = min_t(size_t, bytes, PAGE_SIZE - pgoff);
-		memset_page(page, pgoff, 0, size);
-		bytes -= size;
-		buffer_offset += size;
-	}
-}
-
-/**
  * binder_alloc_copy_user_to_buffer() - copy src user to tgt user
  * @alloc: binder_alloc for this proc
  * @buffer: binder buffer to be accessed
diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h
index dc1e2b01dd64..70387234477e 100644
--- a/drivers/android/binder_alloc.h
+++ b/drivers/android/binder_alloc.h
@@ -9,13 +9,13 @@
 #include <linux/rbtree.h>
 #include <linux/list.h>
 #include <linux/mm.h>
-#include <linux/rtmutex.h>
+#include <linux/spinlock.h>
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/list_lru.h>
 #include <uapi/linux/android/binder.h>
 
-extern struct list_lru binder_alloc_lru;
+extern struct list_lru binder_freelist;
 struct binder_transaction;
 
 /**
@@ -49,21 +49,19 @@ struct binder_buffer {
 	unsigned async_transaction:1;
 	unsigned oneway_spam_suspect:1;
 	unsigned debug_id:27;
-
 	struct binder_transaction *transaction;
-
 	struct binder_node *target_node;
 	size_t data_size;
 	size_t offsets_size;
 	size_t extra_buffers_size;
-	void __user *user_data;
-	int    pid;
+	unsigned long user_data;
+	int pid;
 };
 
 /**
  * struct binder_lru_page - page object used for binder shrinker
  * @page_ptr: pointer to physical page in mmap'd space
- * @lru:      entry in binder_alloc_lru
+ * @lru:      entry in binder_freelist
  * @alloc:    binder_alloc for a proc
  */
 struct binder_lru_page {
@@ -74,7 +72,7 @@ struct binder_lru_page {
 
 /**
  * struct binder_alloc - per-binder proc state for binder allocator
- * @mutex:              protects binder_alloc fields
+ * @lock:               protects binder_alloc fields
  * @vma:                vm_area_struct passed to mmap_handler
  *                      (invariant after mmap)
  * @mm:                 copy of task->mm (invariant after open)
@@ -98,10 +96,10 @@ struct binder_lru_page {
  * struct binder_buffer objects used to track the user buffers
  */
 struct binder_alloc {
-	struct mutex mutex;
+	spinlock_t lock;
 	struct vm_area_struct *vma;
 	struct mm_struct *mm;
-	void __user *buffer;
+	unsigned long buffer;
 	struct list_head buffers;
 	struct rb_root free_buffers;
 	struct rb_root allocated_buffers;
@@ -121,27 +119,26 @@ static inline void binder_selftest_alloc(struct binder_alloc *alloc) {}
 enum lru_status binder_alloc_free_page(struct list_head *item,
 				       struct list_lru_one *lru,
 				       spinlock_t *lock, void *cb_arg);
-extern struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
-						  size_t data_size,
-						  size_t offsets_size,
-						  size_t extra_buffers_size,
-						  int is_async,
-						  int pid);
-extern void binder_alloc_init(struct binder_alloc *alloc);
-extern int binder_alloc_shrinker_init(void);
-extern void binder_alloc_shrinker_exit(void);
-extern void binder_alloc_vma_close(struct binder_alloc *alloc);
-extern struct binder_buffer *
+struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
+					   size_t data_size,
+					   size_t offsets_size,
+					   size_t extra_buffers_size,
+					   int is_async);
+void binder_alloc_init(struct binder_alloc *alloc);
+int binder_alloc_shrinker_init(void);
+void binder_alloc_shrinker_exit(void);
+void binder_alloc_vma_close(struct binder_alloc *alloc);
+struct binder_buffer *
 binder_alloc_prepare_to_free(struct binder_alloc *alloc,
-			     uintptr_t user_ptr);
-extern void binder_alloc_free_buf(struct binder_alloc *alloc,
-				  struct binder_buffer *buffer);
-extern int binder_alloc_mmap_handler(struct binder_alloc *alloc,
-				     struct vm_area_struct *vma);
-extern void binder_alloc_deferred_release(struct binder_alloc *alloc);
-extern int binder_alloc_get_allocated_count(struct binder_alloc *alloc);
-extern void binder_alloc_print_allocated(struct seq_file *m,
-					 struct binder_alloc *alloc);
+			     unsigned long user_ptr);
+void binder_alloc_free_buf(struct binder_alloc *alloc,
+			   struct binder_buffer *buffer);
+int binder_alloc_mmap_handler(struct binder_alloc *alloc,
+			      struct vm_area_struct *vma);
+void binder_alloc_deferred_release(struct binder_alloc *alloc);
+int binder_alloc_get_allocated_count(struct binder_alloc *alloc);
+void binder_alloc_print_allocated(struct seq_file *m,
+				  struct binder_alloc *alloc);
 void binder_alloc_print_pages(struct seq_file *m,
 			      struct binder_alloc *alloc);
 
@@ -156,9 +153,9 @@ binder_alloc_get_free_async_space(struct binder_alloc *alloc)
 {
 	size_t free_async_space;
 
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	free_async_space = alloc->free_async_space;
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 	return free_async_space;
 }
 
diff --git a/drivers/android/binder_alloc_selftest.c b/drivers/android/binder_alloc_selftest.c
index c2b323bc3b3a..81442fe20a69 100644
--- a/drivers/android/binder_alloc_selftest.c
+++ b/drivers/android/binder_alloc_selftest.c
@@ -72,6 +72,10 @@ enum buf_end_align_type {
 	 * buf1 ]|[ buf2 | buf2 | buf2 ][ ...
 	 */
 	NEXT_NEXT_UNALIGNED,
+	/**
+	 * @LOOP_END: The number of enum values in &buf_end_align_type.
+	 * It is used for controlling loop termination.
+	 */
 	LOOP_END,
 };
 
@@ -93,11 +97,11 @@ static bool check_buffer_pages_allocated(struct binder_alloc *alloc,
 					 struct binder_buffer *buffer,
 					 size_t size)
 {
-	void __user *page_addr;
-	void __user *end;
+	unsigned long page_addr;
+	unsigned long end;
 	int page_index;
 
-	end = (void __user *)PAGE_ALIGN((uintptr_t)buffer->user_data + size);
+	end = PAGE_ALIGN(buffer->user_data + size);
 	page_addr = buffer->user_data;
 	for (; page_addr < end; page_addr += PAGE_SIZE) {
 		page_index = (page_addr - alloc->buffer) / PAGE_SIZE;
@@ -119,7 +123,7 @@ static void binder_selftest_alloc_buf(struct binder_alloc *alloc,
 	int i;
 
 	for (i = 0; i < BUFFER_NUM; i++) {
-		buffers[i] = binder_alloc_new_buf(alloc, sizes[i], 0, 0, 0, 0);
+		buffers[i] = binder_alloc_new_buf(alloc, sizes[i], 0, 0, 0);
 		if (IS_ERR(buffers[i]) ||
 		    !check_buffer_pages_allocated(alloc, buffers[i],
 						  sizes[i])) {
@@ -158,8 +162,8 @@ static void binder_selftest_free_page(struct binder_alloc *alloc)
 	int i;
 	unsigned long count;
 
-	while ((count = list_lru_count(&binder_alloc_lru))) {
-		list_lru_walk(&binder_alloc_lru, binder_alloc_free_page,
+	while ((count = list_lru_count(&binder_freelist))) {
+		list_lru_walk(&binder_freelist, binder_alloc_free_page,
 			      NULL, count);
 	}
 
@@ -183,7 +187,7 @@ static void binder_selftest_alloc_free(struct binder_alloc *alloc,
 
 	/* Allocate from lru. */
 	binder_selftest_alloc_buf(alloc, buffers, sizes, seq);
-	if (list_lru_count(&binder_alloc_lru))
+	if (list_lru_count(&binder_freelist))
 		pr_err("lru list should be empty but is not\n");
 
 	binder_selftest_free_buf(alloc, buffers, sizes, seq, end);
diff --git a/drivers/android/binder_trace.h b/drivers/android/binder_trace.h
index 8cc07e6a4273..fe38c6fc65d0 100644
--- a/drivers/android/binder_trace.h
+++ b/drivers/android/binder_trace.h
@@ -317,7 +317,7 @@ DEFINE_EVENT(binder_buffer_class, binder_transaction_update_buffer_release,
 
 TRACE_EVENT(binder_update_page_range,
 	TP_PROTO(struct binder_alloc *alloc, bool allocate,
-		 void __user *start, void __user *end),
+		 unsigned long start, unsigned long end),
 	TP_ARGS(alloc, allocate, start, end),
 	TP_STRUCT__entry(
 		__field(int, proc)
diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c
index 1224ab7aa070..3001d754ac36 100644
--- a/drivers/android/binderfs.c
+++ b/drivers/android/binderfs.c
@@ -29,7 +29,6 @@
 #include <linux/uaccess.h>
 #include <linux/user_namespace.h>
 #include <linux/xarray.h>
-#include <uapi/asm-generic/errno-base.h>
 #include <uapi/linux/android/binder.h>
 #include <uapi/linux/android/binderfs.h>
 
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 3a5f3255f51b..682ff550ccfb 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -48,6 +48,7 @@ enum {
 enum board_ids {
 	/* board IDs by feature in alphabetical order */
 	board_ahci,
+	board_ahci_43bit_dma,
 	board_ahci_ign_iferr,
 	board_ahci_low_power,
 	board_ahci_no_debounce_delay,
@@ -128,6 +129,13 @@ static const struct ata_port_info ahci_port_info[] = {
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &ahci_ops,
 	},
+	[board_ahci_43bit_dma] = {
+		AHCI_HFLAGS	(AHCI_HFLAG_43BIT_ONLY),
+		.flags		= AHCI_FLAG_COMMON,
+		.pio_mask	= ATA_PIO4,
+		.udma_mask	= ATA_UDMA6,
+		.port_ops	= &ahci_ops,
+	},
 	[board_ahci_ign_iferr] = {
 		AHCI_HFLAGS	(AHCI_HFLAG_IGN_IRQ_IF_ERR),
 		.flags		= AHCI_FLAG_COMMON,
@@ -597,14 +605,14 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(PROMISE, 0x3f20), board_ahci },	/* PDC42819 */
 	{ PCI_VDEVICE(PROMISE, 0x3781), board_ahci },   /* FastTrak TX8660 ahci-mode */
 
-	/* Asmedia */
-	{ PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci },	/* ASM1060 */
-	{ PCI_VDEVICE(ASMEDIA, 0x0602), board_ahci },	/* ASM1060 */
-	{ PCI_VDEVICE(ASMEDIA, 0x0611), board_ahci },	/* ASM1061 */
-	{ PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci },	/* ASM1062 */
-	{ PCI_VDEVICE(ASMEDIA, 0x0621), board_ahci },   /* ASM1061R */
-	{ PCI_VDEVICE(ASMEDIA, 0x0622), board_ahci },   /* ASM1062R */
-	{ PCI_VDEVICE(ASMEDIA, 0x0624), board_ahci },   /* ASM1062+JMB575 */
+	/* ASMedia */
+	{ PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci_43bit_dma },	/* ASM1060 */
+	{ PCI_VDEVICE(ASMEDIA, 0x0602), board_ahci_43bit_dma },	/* ASM1060 */
+	{ PCI_VDEVICE(ASMEDIA, 0x0611), board_ahci_43bit_dma },	/* ASM1061 */
+	{ PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci_43bit_dma },	/* ASM1061/1062 */
+	{ PCI_VDEVICE(ASMEDIA, 0x0621), board_ahci_43bit_dma },	/* ASM1061R */
+	{ PCI_VDEVICE(ASMEDIA, 0x0622), board_ahci_43bit_dma },	/* ASM1062R */
+	{ PCI_VDEVICE(ASMEDIA, 0x0624), board_ahci_43bit_dma },	/* ASM1062+JMB575 */
 	{ PCI_VDEVICE(ASMEDIA, 0x1062), board_ahci },	/* ASM1062A */
 	{ PCI_VDEVICE(ASMEDIA, 0x1064), board_ahci },	/* ASM1064 */
 	{ PCI_VDEVICE(ASMEDIA, 0x1164), board_ahci },   /* ASM1164 */
@@ -663,6 +671,19 @@ MODULE_PARM_DESC(mobile_lpm_policy, "Default LPM policy for mobile chipsets");
 static void ahci_pci_save_initial_config(struct pci_dev *pdev,
 					 struct ahci_host_priv *hpriv)
 {
+	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA) {
+		switch (pdev->device) {
+		case 0x1166:
+			dev_info(&pdev->dev, "ASM1166 has only six ports\n");
+			hpriv->saved_port_map = 0x3f;
+			break;
+		case 0x1064:
+			dev_info(&pdev->dev, "ASM1064 has only four ports\n");
+			hpriv->saved_port_map = 0xf;
+			break;
+		}
+	}
+
 	if (pdev->vendor == PCI_VENDOR_ID_JMICRON && pdev->device == 0x2361) {
 		dev_info(&pdev->dev, "JMB361 has only one port\n");
 		hpriv->saved_port_map = 1;
@@ -949,11 +970,20 @@ static int ahci_pci_device_resume(struct device *dev)
 
 #endif /* CONFIG_PM */
 
-static int ahci_configure_dma_masks(struct pci_dev *pdev, int using_dac)
+static int ahci_configure_dma_masks(struct pci_dev *pdev,
+				    struct ahci_host_priv *hpriv)
 {
-	const int dma_bits = using_dac ? 64 : 32;
+	int dma_bits;
 	int rc;
 
+	if (hpriv->cap & HOST_CAP_64) {
+		dma_bits = 64;
+		if (hpriv->flags & AHCI_HFLAG_43BIT_ONLY)
+			dma_bits = 43;
+	} else {
+		dma_bits = 32;
+	}
+
 	/*
 	 * If the device fixup already set the dma_mask to some non-standard
 	 * value, don't extend it here. This happens on STA2X11, for example.
@@ -1926,7 +1956,7 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	ahci_gtf_filter_workaround(host);
 
 	/* initialize adapter */
-	rc = ahci_configure_dma_masks(pdev, hpriv->cap & HOST_CAP_64);
+	rc = ahci_configure_dma_masks(pdev, hpriv);
 	if (rc)
 		return rc;
 
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 4bae95b06ae3..df8f8a1a3a34 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -247,6 +247,7 @@ enum {
 	AHCI_HFLAG_SUSPEND_PHYS		= BIT(26), /* handle PHYs during
 						      suspend/resume */
 	AHCI_HFLAG_NO_SXS		= BIT(28), /* SXS not supported */
+	AHCI_HFLAG_43BIT_ONLY		= BIT(29), /* 43bit DMA addr limit */
 
 	/* ap->flags bits */
 
diff --git a/drivers/ata/ahci_ceva.c b/drivers/ata/ahci_ceva.c
index 64f7f7d6ba84..11a2c199a7c2 100644
--- a/drivers/ata/ahci_ceva.c
+++ b/drivers/ata/ahci_ceva.c
@@ -88,7 +88,6 @@ struct ceva_ahci_priv {
 	u32 axicc;
 	bool is_cci_enabled;
 	int flags;
-	struct reset_control *rst;
 };
 
 static unsigned int ceva_ahci_read_id(struct ata_device *dev,
@@ -189,6 +188,60 @@ static const struct scsi_host_template ahci_platform_sht = {
 	AHCI_SHT(DRV_NAME),
 };
 
+static int ceva_ahci_platform_enable_resources(struct ahci_host_priv *hpriv)
+{
+	int rc, i;
+
+	rc = ahci_platform_enable_regulators(hpriv);
+	if (rc)
+		return rc;
+
+	rc = ahci_platform_enable_clks(hpriv);
+	if (rc)
+		goto disable_regulator;
+
+	/* Assert the controller reset */
+	rc = ahci_platform_assert_rsts(hpriv);
+	if (rc)
+		goto disable_clks;
+
+	for (i = 0; i < hpriv->nports; i++) {
+		rc = phy_init(hpriv->phys[i]);
+		if (rc)
+			goto disable_rsts;
+	}
+
+	/* De-assert the controller reset */
+	ahci_platform_deassert_rsts(hpriv);
+
+	for (i = 0; i < hpriv->nports; i++) {
+		rc = phy_power_on(hpriv->phys[i]);
+		if (rc) {
+			phy_exit(hpriv->phys[i]);
+			goto disable_phys;
+		}
+	}
+
+	return 0;
+
+disable_rsts:
+	ahci_platform_deassert_rsts(hpriv);
+
+disable_phys:
+	while (--i >= 0) {
+		phy_power_off(hpriv->phys[i]);
+		phy_exit(hpriv->phys[i]);
+	}
+
+disable_clks:
+	ahci_platform_disable_clks(hpriv);
+
+disable_regulator:
+	ahci_platform_disable_regulators(hpriv);
+
+	return rc;
+}
+
 static int ceva_ahci_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
@@ -203,47 +256,19 @@ static int ceva_ahci_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	cevapriv->ahci_pdev = pdev;
-
-	cevapriv->rst = devm_reset_control_get_optional_exclusive(&pdev->dev,
-								  NULL);
-	if (IS_ERR(cevapriv->rst))
-		dev_err_probe(&pdev->dev, PTR_ERR(cevapriv->rst),
-			      "failed to get reset\n");
-
 	hpriv = ahci_platform_get_resources(pdev, 0);
 	if (IS_ERR(hpriv))
 		return PTR_ERR(hpriv);
 
-	if (!cevapriv->rst) {
-		rc = ahci_platform_enable_resources(hpriv);
-		if (rc)
-			return rc;
-	} else {
-		int i;
+	hpriv->rsts = devm_reset_control_get_optional_exclusive(&pdev->dev,
+								NULL);
+	if (IS_ERR(hpriv->rsts))
+		return dev_err_probe(&pdev->dev, PTR_ERR(hpriv->rsts),
+				     "failed to get reset\n");
 
-		rc = ahci_platform_enable_clks(hpriv);
-		if (rc)
-			return rc;
-		/* Assert the controller reset */
-		reset_control_assert(cevapriv->rst);
-
-		for (i = 0; i < hpriv->nports; i++) {
-			rc = phy_init(hpriv->phys[i]);
-			if (rc)
-				return rc;
-		}
-
-		/* De-assert the controller reset */
-		reset_control_deassert(cevapriv->rst);
-
-		for (i = 0; i < hpriv->nports; i++) {
-			rc = phy_power_on(hpriv->phys[i]);
-			if (rc) {
-				phy_exit(hpriv->phys[i]);
-				return rc;
-			}
-		}
-	}
+	rc = ceva_ahci_platform_enable_resources(hpriv);
+	if (rc)
+		return rc;
 
 	if (of_property_read_bool(np, "ceva,broken-gen2"))
 		cevapriv->flags = CEVA_FLAG_BROKEN_GEN2;
@@ -252,52 +277,60 @@ static int ceva_ahci_probe(struct platform_device *pdev)
 	if (of_property_read_u8_array(np, "ceva,p0-cominit-params",
 					(u8 *)&cevapriv->pp2c[0], 4) < 0) {
 		dev_warn(dev, "ceva,p0-cominit-params property not defined\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto disable_resources;
 	}
 
 	if (of_property_read_u8_array(np, "ceva,p1-cominit-params",
 					(u8 *)&cevapriv->pp2c[1], 4) < 0) {
 		dev_warn(dev, "ceva,p1-cominit-params property not defined\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto disable_resources;
 	}
 
 	/* Read OOB timing value for COMWAKE from device-tree*/
 	if (of_property_read_u8_array(np, "ceva,p0-comwake-params",
 					(u8 *)&cevapriv->pp3c[0], 4) < 0) {
 		dev_warn(dev, "ceva,p0-comwake-params property not defined\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto disable_resources;
 	}
 
 	if (of_property_read_u8_array(np, "ceva,p1-comwake-params",
 					(u8 *)&cevapriv->pp3c[1], 4) < 0) {
 		dev_warn(dev, "ceva,p1-comwake-params property not defined\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto disable_resources;
 	}
 
 	/* Read phy BURST timing value from device-tree */
 	if (of_property_read_u8_array(np, "ceva,p0-burst-params",
 					(u8 *)&cevapriv->pp4c[0], 4) < 0) {
 		dev_warn(dev, "ceva,p0-burst-params property not defined\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto disable_resources;
 	}
 
 	if (of_property_read_u8_array(np, "ceva,p1-burst-params",
 					(u8 *)&cevapriv->pp4c[1], 4) < 0) {
 		dev_warn(dev, "ceva,p1-burst-params property not defined\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto disable_resources;
 	}
 
 	/* Read phy RETRY interval timing value from device-tree */
 	if (of_property_read_u16_array(np, "ceva,p0-retry-params",
 					(u16 *)&cevapriv->pp5c[0], 2) < 0) {
 		dev_warn(dev, "ceva,p0-retry-params property not defined\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto disable_resources;
 	}
 
 	if (of_property_read_u16_array(np, "ceva,p1-retry-params",
 					(u16 *)&cevapriv->pp5c[1], 2) < 0) {
 		dev_warn(dev, "ceva,p1-retry-params property not defined\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto disable_resources;
 	}
 
 	/*
@@ -335,7 +368,7 @@ static int __maybe_unused ceva_ahci_resume(struct device *dev)
 	struct ahci_host_priv *hpriv = host->private_data;
 	int rc;
 
-	rc = ahci_platform_enable_resources(hpriv);
+	rc = ceva_ahci_platform_enable_resources(hpriv);
 	if (rc)
 		return rc;
 
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 09ed67772fae..be3412cdb22e 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2001,6 +2001,33 @@ bool ata_dev_power_init_tf(struct ata_device *dev, struct ata_taskfile *tf,
 	return true;
 }
 
+static bool ata_dev_power_is_active(struct ata_device *dev)
+{
+	struct ata_taskfile tf;
+	unsigned int err_mask;
+
+	ata_tf_init(dev, &tf);
+	tf.flags |= ATA_TFLAG_DEVICE | ATA_TFLAG_ISADDR;
+	tf.protocol = ATA_PROT_NODATA;
+	tf.command = ATA_CMD_CHK_POWER;
+
+	err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0);
+	if (err_mask) {
+		ata_dev_err(dev, "Check power mode failed (err_mask=0x%x)\n",
+			    err_mask);
+		/*
+		 * Assume we are in standby mode so that we always force a
+		 * spinup in ata_dev_power_set_active().
+		 */
+		return false;
+	}
+
+	ata_dev_dbg(dev, "Power mode: 0x%02x\n", tf.nsect);
+
+	/* Active or idle */
+	return tf.nsect == 0xff;
+}
+
 /**
  *	ata_dev_power_set_standby - Set a device power mode to standby
  *	@dev: target device
@@ -2017,6 +2044,11 @@ void ata_dev_power_set_standby(struct ata_device *dev)
 	struct ata_taskfile tf;
 	unsigned int err_mask;
 
+	/* If the device is already sleeping or in standby, do nothing. */
+	if ((dev->flags & ATA_DFLAG_SLEEPING) ||
+	    !ata_dev_power_is_active(dev))
+		return;
+
 	/*
 	 * Some odd clown BIOSes issue spindown on power off (ACPI S4 or S5)
 	 * causing some drives to spin up and down again. For these, do nothing
@@ -2042,33 +2074,6 @@ void ata_dev_power_set_standby(struct ata_device *dev)
 			    err_mask);
 }
 
-static bool ata_dev_power_is_active(struct ata_device *dev)
-{
-	struct ata_taskfile tf;
-	unsigned int err_mask;
-
-	ata_tf_init(dev, &tf);
-	tf.flags |= ATA_TFLAG_DEVICE | ATA_TFLAG_ISADDR;
-	tf.protocol = ATA_PROT_NODATA;
-	tf.command = ATA_CMD_CHK_POWER;
-
-	err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0);
-	if (err_mask) {
-		ata_dev_err(dev, "Check power mode failed (err_mask=0x%x)\n",
-			    err_mask);
-		/*
-		 * Assume we are in standby mode so that we always force a
-		 * spinup in ata_dev_power_set_active().
-		 */
-		return false;
-	}
-
-	ata_dev_dbg(dev, "Power mode: 0x%02x\n", tf.nsect);
-
-	/* Active or idle */
-	return tf.nsect == 0xff;
-}
-
 /**
  *	ata_dev_power_set_active -  Set a device power mode to active
  *	@dev: target device
diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c
index b6656c287175..0fb1934875f2 100644
--- a/drivers/ata/libata-sata.c
+++ b/drivers/ata/libata-sata.c
@@ -784,7 +784,7 @@ bool sata_lpm_ignore_phy_events(struct ata_link *link)
 EXPORT_SYMBOL_GPL(sata_lpm_ignore_phy_events);
 
 static const char *ata_lpm_policy_names[] = {
-	[ATA_LPM_UNKNOWN]		= "max_performance",
+	[ATA_LPM_UNKNOWN]		= "keep_firmware_settings",
 	[ATA_LPM_MAX_POWER]		= "max_performance",
 	[ATA_LPM_MED_POWER]		= "medium_power",
 	[ATA_LPM_MED_POWER_WITH_DIPM]	= "med_power_with_dipm",
diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c
index e327a0229dc1..e7f713cd70d3 100644
--- a/drivers/atm/idt77252.c
+++ b/drivers/atm/idt77252.c
@@ -2930,6 +2930,8 @@ open_card_ubr0(struct idt77252_dev *card)
 	vc->scq = alloc_scq(card, vc->class);
 	if (!vc->scq) {
 		printk("%s: can't get SCQ.\n", card->name);
+		kfree(card->vcs[0]);
+		card->vcs[0] = NULL;
 		return -ENOMEM;
 	}
 
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 5aaa0865625d..024b78a0cfc1 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -219,20 +219,34 @@ static DECLARE_WORK(update_topology_flags_work, update_topology_flags_workfn);
 
 static DEVICE_ATTR_RO(cpu_capacity);
 
-static int register_cpu_capacity_sysctl(void)
+static int cpu_capacity_sysctl_add(unsigned int cpu)
 {
-	int i;
-	struct device *cpu;
+	struct device *cpu_dev = get_cpu_device(cpu);
 
-	for_each_possible_cpu(i) {
-		cpu = get_cpu_device(i);
-		if (!cpu) {
-			pr_err("%s: too early to get CPU%d device!\n",
-			       __func__, i);
-			continue;
-		}
-		device_create_file(cpu, &dev_attr_cpu_capacity);
-	}
+	if (!cpu_dev)
+		return -ENOENT;
+
+	device_create_file(cpu_dev, &dev_attr_cpu_capacity);
+
+	return 0;
+}
+
+static int cpu_capacity_sysctl_remove(unsigned int cpu)
+{
+	struct device *cpu_dev = get_cpu_device(cpu);
+
+	if (!cpu_dev)
+		return -ENOENT;
+
+	device_remove_file(cpu_dev, &dev_attr_cpu_capacity);
+
+	return 0;
+}
+
+static int register_cpu_capacity_sysctl(void)
+{
+	cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "topology/cpu-capacity",
+			  cpu_capacity_sysctl_add, cpu_capacity_sysctl_remove);
 
 	return 0;
 }
@@ -417,9 +431,6 @@ init_cpu_capacity_callback(struct notifier_block *nb,
 	struct cpufreq_policy *policy = data;
 	int cpu;
 
-	if (!raw_capacity)
-		return 0;
-
 	if (val != CPUFREQ_CREATE_POLICY)
 		return 0;
 
@@ -436,9 +447,11 @@ init_cpu_capacity_callback(struct notifier_block *nb,
 	}
 
 	if (cpumask_empty(cpus_to_visit)) {
-		topology_normalize_cpu_scale();
-		schedule_work(&update_topology_flags_work);
-		free_raw_capacity();
+		if (raw_capacity) {
+			topology_normalize_cpu_scale();
+			schedule_work(&update_topology_flags_work);
+			free_raw_capacity();
+		}
 		pr_debug("cpu_capacity: parsing done\n");
 		schedule_work(&parsing_done_work);
 	}
@@ -458,7 +471,7 @@ static int __init register_cpufreq_notifier(void)
 	 * On ACPI-based systems skip registering cpufreq notifier as cpufreq
 	 * information is not needed for cpu capacity initialization.
 	 */
-	if (!acpi_disabled || !raw_capacity)
+	if (!acpi_disabled)
 		return -EINVAL;
 
 	if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL))
diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c
index 4d4c2c8d26c4..d3a2c40c2f12 100644
--- a/drivers/base/auxiliary.c
+++ b/drivers/base/auxiliary.c
@@ -244,7 +244,7 @@ static void auxiliary_bus_shutdown(struct device *dev)
 		auxdrv->shutdown(auxdev);
 }
 
-static struct bus_type auxiliary_bus_type = {
+static const struct bus_type auxiliary_bus_type = {
 	.name = "auxiliary",
 	.probe = auxiliary_bus_probe,
 	.remove = auxiliary_bus_remove,
diff --git a/drivers/base/base.h b/drivers/base/base.h
index eb4c0ace9242..0738ccad08b2 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -207,7 +207,7 @@ static inline int devtmpfs_init(void) { return 0; }
 #endif
 
 #ifdef CONFIG_BLOCK
-extern struct class block_class;
+extern const struct class block_class;
 static inline bool is_blockdev(struct device *dev)
 {
 	return dev->class == &block_class;
diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 84a21084d67d..daee55c9b2d9 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -1030,7 +1030,7 @@ static void device_insertion_sort_klist(struct device *a, struct list_head *list
 	list_move_tail(&a->p->knode_bus.n_node, list);
 }
 
-void bus_sort_breadthfirst(struct bus_type *bus,
+void bus_sort_breadthfirst(const struct bus_type *bus,
 			   int (*compare)(const struct device *a,
 					  const struct device *b))
 {
@@ -1194,7 +1194,7 @@ static void system_root_device_release(struct device *dev)
 	kfree(dev);
 }
 
-static int subsys_register(struct bus_type *subsys,
+static int subsys_register(const struct bus_type *subsys,
 			   const struct attribute_group **groups,
 			   struct kobject *parent_of_root)
 {
@@ -1264,7 +1264,7 @@ err_sp:
  * directory itself and not some create fake root-device placed in
  * /sys/devices/system/<name>.
  */
-int subsys_system_register(struct bus_type *subsys,
+int subsys_system_register(const struct bus_type *subsys,
 			   const struct attribute_group **groups)
 {
 	return subsys_register(subsys, groups, &system_kset->kobj);
@@ -1282,7 +1282,7 @@ EXPORT_SYMBOL_GPL(subsys_system_register);
  * There's no restriction on device naming.  This is for kernel software
  * constructs which need sysfs interface.
  */
-int subsys_virtual_register(struct bus_type *subsys,
+int subsys_virtual_register(const struct bus_type *subsys,
 			    const struct attribute_group **groups)
 {
 	struct kobject *virtual_dir;
diff --git a/drivers/base/class.c b/drivers/base/class.c
index 7e78aee0fd6c..7b38fdf8e1d7 100644
--- a/drivers/base/class.c
+++ b/drivers/base/class.c
@@ -213,6 +213,7 @@ int class_register(const struct class *cls)
 	return 0;
 
 err_out:
+	lockdep_unregister_key(key);
 	kfree(cp);
 	return error;
 }
diff --git a/drivers/base/container.c b/drivers/base/container.c
index 1ba42d2d3532..f40588ebc3f5 100644
--- a/drivers/base/container.c
+++ b/drivers/base/container.c
@@ -24,7 +24,7 @@ static int container_offline(struct device *dev)
 	return cdev->offline ? cdev->offline(cdev) : 0;
 }
 
-struct bus_type container_subsys = {
+const struct bus_type container_subsys = {
 	.name = CONTAINER_BUS_NAME,
 	.dev_name = CONTAINER_BUS_NAME,
 	.online = trivial_online,
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 67ba592afc77..9828da9b933c 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -125,7 +125,7 @@ static void __fwnode_link_del(struct fwnode_link *link)
  */
 static void __fwnode_link_cycle(struct fwnode_link *link)
 {
-	pr_debug("%pfwf: Relaxing link with %pfwf\n",
+	pr_debug("%pfwf: cycle: depends on %pfwf\n",
 		 link->consumer, link->supplier);
 	link->flags |= FWLINK_FLAG_CYCLE;
 }
@@ -284,10 +284,12 @@ static bool device_is_ancestor(struct device *dev, struct device *target)
 	return false;
 }
 
+#define DL_MARKER_FLAGS		(DL_FLAG_INFERRED | \
+				 DL_FLAG_CYCLE | \
+				 DL_FLAG_MANAGED)
 static inline bool device_link_flag_is_sync_state_only(u32 flags)
 {
-	return (flags & ~(DL_FLAG_INFERRED | DL_FLAG_CYCLE)) ==
-		(DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED);
+	return (flags & ~DL_MARKER_FLAGS) == DL_FLAG_SYNC_STATE_ONLY;
 }
 
 /**
@@ -298,7 +300,7 @@ static inline bool device_link_flag_is_sync_state_only(u32 flags)
  * Check if @target depends on @dev or any device dependent on it (its child or
  * its consumer etc).  Return 1 if that is the case or 0 otherwise.
  */
-int device_is_dependent(struct device *dev, void *target)
+static int device_is_dependent(struct device *dev, void *target)
 {
 	struct device_link *link;
 	int ret;
@@ -1641,7 +1643,7 @@ static void device_links_purge(struct device *dev)
 #define FW_DEVLINK_FLAGS_RPM		(FW_DEVLINK_FLAGS_ON | \
 					 DL_FLAG_PM_RUNTIME)
 
-static u32 fw_devlink_flags = FW_DEVLINK_FLAGS_ON;
+static u32 fw_devlink_flags = FW_DEVLINK_FLAGS_RPM;
 static int __init fw_devlink_setup(char *arg)
 {
 	if (!arg)
@@ -1943,6 +1945,7 @@ static bool __fw_devlink_relax_cycles(struct device *con,
 
 	/* Termination condition. */
 	if (sup_dev == con) {
+		pr_debug("----- cycle: start -----\n");
 		ret = true;
 		goto out;
 	}
@@ -1974,8 +1977,11 @@ static bool __fw_devlink_relax_cycles(struct device *con,
 	else
 		par_dev = fwnode_get_next_parent_dev(sup_handle);
 
-	if (par_dev && __fw_devlink_relax_cycles(con, par_dev->fwnode))
+	if (par_dev && __fw_devlink_relax_cycles(con, par_dev->fwnode)) {
+		pr_debug("%pfwf: cycle: child of %pfwf\n", sup_handle,
+			 par_dev->fwnode);
 		ret = true;
+	}
 
 	if (!sup_dev)
 		goto out;
@@ -1991,6 +1997,8 @@ static bool __fw_devlink_relax_cycles(struct device *con,
 
 		if (__fw_devlink_relax_cycles(con,
 					      dev_link->supplier->fwnode)) {
+			pr_debug("%pfwf: cycle: depends on %pfwf\n", sup_handle,
+				 dev_link->supplier->fwnode);
 			fw_devlink_relax_link(dev_link);
 			dev_link->flags |= DL_FLAG_CYCLE;
 			ret = true;
@@ -2058,13 +2066,19 @@ static int fw_devlink_create_devlink(struct device *con,
 
 	/*
 	 * SYNC_STATE_ONLY device links don't block probing and supports cycles.
-	 * So cycle detection isn't necessary and shouldn't be done.
+	 * So, one might expect that cycle detection isn't necessary for them.
+	 * However, if the device link was marked as SYNC_STATE_ONLY because
+	 * it's part of a cycle, then we still need to do cycle detection. This
+	 * is because the consumer and supplier might be part of multiple cycles
+	 * and we need to detect all those cycles.
 	 */
-	if (!(flags & DL_FLAG_SYNC_STATE_ONLY)) {
+	if (!device_link_flag_is_sync_state_only(flags) ||
+	    flags & DL_FLAG_CYCLE) {
 		device_links_write_lock();
 		if (__fw_devlink_relax_cycles(con, sup_handle)) {
 			__fwnode_link_cycle(link);
 			flags = fw_devlink_get_flags(link->flags);
+			pr_debug("----- cycle: end -----\n");
 			dev_info(con, "Fixed dependency cycle(s) with %pfwf\n",
 				 sup_handle);
 		}
@@ -4944,13 +4958,14 @@ define_dev_printk_level(_dev_info, KERN_INFO);
  *
  * 	return dev_err_probe(dev, err, ...);
  *
- * Note that it is deemed acceptable to use this function for error
- * prints during probe even if the @err is known to never be -EPROBE_DEFER.
+ * Using this helper in your probe function is totally fine even if @err is
+ * known to never be -EPROBE_DEFER.
  * The benefit compared to a normal dev_err() is the standardized format
- * of the error code and the fact that the error code is returned.
+ * of the error code, it being emitted symbolically (i.e. you get "EAGAIN"
+ * instead of "-35") and the fact that the error code is returned which allows
+ * more compact error paths.
  *
  * Returns @err.
- *
  */
 int dev_err_probe(const struct device *dev, int err, const char *fmt, ...)
 {
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 548491de818e..47de0f140ba6 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -525,19 +525,42 @@ bool cpu_is_hotpluggable(unsigned int cpu)
 EXPORT_SYMBOL_GPL(cpu_is_hotpluggable);
 
 #ifdef CONFIG_GENERIC_CPU_DEVICES
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
-#endif
+DEFINE_PER_CPU(struct cpu, cpu_devices);
+
+bool __weak arch_cpu_is_hotpluggable(int cpu)
+{
+	return false;
+}
+
+int __weak arch_register_cpu(int cpu)
+{
+	struct cpu *c = &per_cpu(cpu_devices, cpu);
+
+	c->hotpluggable = arch_cpu_is_hotpluggable(cpu);
+
+	return register_cpu(c, cpu);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+void __weak arch_unregister_cpu(int num)
+{
+	unregister_cpu(&per_cpu(cpu_devices, num));
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+#endif /* CONFIG_GENERIC_CPU_DEVICES */
 
 static void __init cpu_dev_register_generic(void)
 {
-#ifdef CONFIG_GENERIC_CPU_DEVICES
-	int i;
+	int i, ret;
 
-	for_each_possible_cpu(i) {
-		if (register_cpu(&per_cpu(cpu_devices, i), i))
-			panic("Failed to register CPU device");
+	if (!IS_ENABLED(CONFIG_GENERIC_CPU_DEVICES))
+		return;
+
+	for_each_present_cpu(i) {
+		ret = arch_register_cpu(i);
+		if (ret)
+			pr_warn("register_cpu %d failed (%d)\n", i, ret);
 	}
-#endif
 }
 
 #ifdef CONFIG_GENERIC_CPU_VULNERABILITIES
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 0c3725c3eefa..85152537dbf1 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -313,7 +313,7 @@ static void deferred_probe_timeout_work_func(struct work_struct *work)
 
 	mutex_lock(&deferred_probe_mutex);
 	list_for_each_entry(p, &deferred_probe_pending_list, deferred_probe)
-		dev_info(p->device, "deferred probe pending\n");
+		dev_info(p->device, "deferred probe pending: %s", p->deferred_probe_reason ?: "(reason unknown)\n");
 	mutex_unlock(&deferred_probe_mutex);
 
 	fw_devlink_probing_done();
diff --git a/drivers/base/init.c b/drivers/base/init.c
index 397eb9880cec..c4954835128c 100644
--- a/drivers/base/init.c
+++ b/drivers/base/init.c
@@ -35,8 +35,8 @@ void __init driver_init(void)
 	of_core_init();
 	platform_bus_init();
 	auxiliary_bus_init();
-	cpu_dev_init();
 	memory_dev_init();
 	node_dev_init();
+	cpu_dev_init();
 	container_dev_init();
 }
diff --git a/drivers/base/isa.c b/drivers/base/isa.c
index 675ad3139224..e23d0b49a793 100644
--- a/drivers/base/isa.c
+++ b/drivers/base/isa.c
@@ -82,7 +82,7 @@ static int isa_bus_resume(struct device *dev)
 	return 0;
 }
 
-static struct bus_type isa_bus_type = {
+static const struct bus_type isa_bus_type = {
 	.name		= "isa",
 	.match		= isa_bus_match,
 	.probe		= isa_bus_probe,
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 8a13babd826c..14f964a7719b 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -68,7 +68,7 @@ static inline unsigned long phys_to_block_id(unsigned long phys)
 static int memory_subsys_online(struct device *dev);
 static int memory_subsys_offline(struct device *dev);
 
-static struct bus_type memory_subsys = {
+static const struct bus_type memory_subsys = {
 	.name = MEMORY_CLASS_NAME,
 	.dev_name = MEMORY_CLASS_NAME,
 	.online = memory_subsys_online,
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 493d533f8375..1c05640461dd 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -21,7 +21,7 @@
 #include <linux/swap.h>
 #include <linux/slab.h>
 
-static struct bus_type node_subsys = {
+static const struct bus_type node_subsys = {
 	.name = "node",
 	.dev_name = "node",
 };
@@ -74,14 +74,14 @@ static BIN_ATTR_RO(cpulist, CPULIST_FILE_MAX_BYTES);
  * @dev:	Device for this memory access class
  * @list_node:	List element in the node's access list
  * @access:	The access class rank
- * @hmem_attrs: Heterogeneous memory performance attributes
+ * @coord:	Heterogeneous memory performance coordinates
  */
 struct node_access_nodes {
 	struct device		dev;
 	struct list_head	list_node;
 	unsigned int		access;
 #ifdef CONFIG_HMEM_REPORTING
-	struct node_hmem_attrs	hmem_attrs;
+	struct access_coordinate	coord;
 #endif
 };
 #define to_access_nodes(dev) container_of(dev, struct node_access_nodes, dev)
@@ -167,7 +167,7 @@ static ssize_t property##_show(struct device *dev,			\
 			   char *buf)					\
 {									\
 	return sysfs_emit(buf, "%u\n",					\
-			  to_access_nodes(dev)->hmem_attrs.property);	\
+			  to_access_nodes(dev)->coord.property);	\
 }									\
 static DEVICE_ATTR_RO(property)
 
@@ -187,10 +187,10 @@ static struct attribute *access_attrs[] = {
 /**
  * node_set_perf_attrs - Set the performance values for given access class
  * @nid: Node identifier to be set
- * @hmem_attrs: Heterogeneous memory performance attributes
+ * @coord: Heterogeneous memory performance coordinates
  * @access: The access class the for the given attributes
  */
-void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs,
+void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord,
 			 unsigned int access)
 {
 	struct node_access_nodes *c;
@@ -205,7 +205,7 @@ void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs,
 	if (!c)
 		return;
 
-	c->hmem_attrs = *hmem_attrs;
+	c->coord = *coord;
 	for (i = 0; access_attrs[i] != NULL; i++) {
 		if (sysfs_add_file_to_group(&c->dev.kobj, access_attrs[i],
 					    "initiators")) {
@@ -868,11 +868,15 @@ int __register_one_node(int nid)
 {
 	int error;
 	int cpu;
+	struct node *node;
 
-	node_devices[nid] = kzalloc(sizeof(struct node), GFP_KERNEL);
-	if (!node_devices[nid])
+	node = kzalloc(sizeof(struct node), GFP_KERNEL);
+	if (!node)
 		return -ENOMEM;
 
+	INIT_LIST_HEAD(&node->access_list);
+	node_devices[nid] = node;
+
 	error = register_node(node_devices[nid], nid);
 
 	/* link cpu under this node */
@@ -881,7 +885,6 @@ int __register_one_node(int nid)
 			register_cpu_under_node(cpu, nid);
 	}
 
-	INIT_LIST_HEAD(&node_devices[nid]->access_list);
 	node_init_caches(nid);
 
 	return error;
diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index 4110c19c08dc..e18ba676cdf6 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -793,7 +793,7 @@ static int pm_clk_notify(struct notifier_block *nb,
  * the remaining members of @clknb should be populated prior to calling this
  * routine.
  */
-void pm_clk_add_notifier(struct bus_type *bus,
+void pm_clk_add_notifier(const struct bus_type *bus,
 				 struct pm_clk_notifier_block *clknb)
 {
 	if (!bus || !clknb)
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 9c5a5f4dba5a..fadcd0379dc2 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -579,7 +579,7 @@ bool dev_pm_skip_resume(struct device *dev)
 }
 
 /**
- * __device_resume_noirq - Execute a "noirq resume" callback for given device.
+ * device_resume_noirq - Execute a "noirq resume" callback for given device.
  * @dev: Device to handle.
  * @state: PM transition of the system being carried out.
  * @async: If true, the device is being resumed asynchronously.
@@ -587,7 +587,7 @@ bool dev_pm_skip_resume(struct device *dev)
  * The driver of @dev will not receive interrupts while this function is being
  * executed.
  */
-static void __device_resume_noirq(struct device *dev, pm_message_t state, bool async)
+static void device_resume_noirq(struct device *dev, pm_message_t state, bool async)
 {
 	pm_callback_t callback = NULL;
 	const char *info = NULL;
@@ -674,16 +674,22 @@ static bool dpm_async_fn(struct device *dev, async_func_t func)
 {
 	reinit_completion(&dev->power.completion);
 
-	if (!is_async(dev))
-		return false;
-
-	get_device(dev);
+	if (is_async(dev)) {
+		dev->power.async_in_progress = true;
 
-	if (async_schedule_dev_nocall(func, dev))
-		return true;
+		get_device(dev);
 
-	put_device(dev);
+		if (async_schedule_dev_nocall(func, dev))
+			return true;
 
+		put_device(dev);
+	}
+	/*
+	 * Because async_schedule_dev_nocall() above has returned false or it
+	 * has not been called at all, func() is not running and it is safe to
+	 * update the async_in_progress flag without extra synchronization.
+	 */
+	dev->power.async_in_progress = false;
 	return false;
 }
 
@@ -691,18 +697,10 @@ static void async_resume_noirq(void *data, async_cookie_t cookie)
 {
 	struct device *dev = data;
 
-	__device_resume_noirq(dev, pm_transition, true);
+	device_resume_noirq(dev, pm_transition, true);
 	put_device(dev);
 }
 
-static void device_resume_noirq(struct device *dev)
-{
-	if (dpm_async_fn(dev, async_resume_noirq))
-		return;
-
-	__device_resume_noirq(dev, pm_transition, false);
-}
-
 static void dpm_noirq_resume_devices(pm_message_t state)
 {
 	struct device *dev;
@@ -712,18 +710,28 @@ static void dpm_noirq_resume_devices(pm_message_t state)
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
 
+	/*
+	 * Trigger the resume of "async" devices upfront so they don't have to
+	 * wait for the "non-async" ones they don't depend on.
+	 */
+	list_for_each_entry(dev, &dpm_noirq_list, power.entry)
+		dpm_async_fn(dev, async_resume_noirq);
+
 	while (!list_empty(&dpm_noirq_list)) {
 		dev = to_device(dpm_noirq_list.next);
-		get_device(dev);
 		list_move_tail(&dev->power.entry, &dpm_late_early_list);
 
-		mutex_unlock(&dpm_list_mtx);
+		if (!dev->power.async_in_progress) {
+			get_device(dev);
 
-		device_resume_noirq(dev);
+			mutex_unlock(&dpm_list_mtx);
 
-		put_device(dev);
+			device_resume_noirq(dev, state, false);
 
-		mutex_lock(&dpm_list_mtx);
+			put_device(dev);
+
+			mutex_lock(&dpm_list_mtx);
+		}
 	}
 	mutex_unlock(&dpm_list_mtx);
 	async_synchronize_full();
@@ -747,14 +755,14 @@ void dpm_resume_noirq(pm_message_t state)
 }
 
 /**
- * __device_resume_early - Execute an "early resume" callback for given device.
+ * device_resume_early - Execute an "early resume" callback for given device.
  * @dev: Device to handle.
  * @state: PM transition of the system being carried out.
  * @async: If true, the device is being resumed asynchronously.
  *
  * Runtime PM is disabled for @dev while this function is being executed.
  */
-static void __device_resume_early(struct device *dev, pm_message_t state, bool async)
+static void device_resume_early(struct device *dev, pm_message_t state, bool async)
 {
 	pm_callback_t callback = NULL;
 	const char *info = NULL;
@@ -820,18 +828,10 @@ static void async_resume_early(void *data, async_cookie_t cookie)
 {
 	struct device *dev = data;
 
-	__device_resume_early(dev, pm_transition, true);
+	device_resume_early(dev, pm_transition, true);
 	put_device(dev);
 }
 
-static void device_resume_early(struct device *dev)
-{
-	if (dpm_async_fn(dev, async_resume_early))
-		return;
-
-	__device_resume_early(dev, pm_transition, false);
-}
-
 /**
  * dpm_resume_early - Execute "early resume" callbacks for all devices.
  * @state: PM transition of the system being carried out.
@@ -845,18 +845,28 @@ void dpm_resume_early(pm_message_t state)
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
 
+	/*
+	 * Trigger the resume of "async" devices upfront so they don't have to
+	 * wait for the "non-async" ones they don't depend on.
+	 */
+	list_for_each_entry(dev, &dpm_late_early_list, power.entry)
+		dpm_async_fn(dev, async_resume_early);
+
 	while (!list_empty(&dpm_late_early_list)) {
 		dev = to_device(dpm_late_early_list.next);
-		get_device(dev);
 		list_move_tail(&dev->power.entry, &dpm_suspended_list);
 
-		mutex_unlock(&dpm_list_mtx);
+		if (!dev->power.async_in_progress) {
+			get_device(dev);
 
-		device_resume_early(dev);
+			mutex_unlock(&dpm_list_mtx);
 
-		put_device(dev);
+			device_resume_early(dev, state, false);
 
-		mutex_lock(&dpm_list_mtx);
+			put_device(dev);
+
+			mutex_lock(&dpm_list_mtx);
+		}
 	}
 	mutex_unlock(&dpm_list_mtx);
 	async_synchronize_full();
@@ -876,12 +886,12 @@ void dpm_resume_start(pm_message_t state)
 EXPORT_SYMBOL_GPL(dpm_resume_start);
 
 /**
- * __device_resume - Execute "resume" callbacks for given device.
+ * device_resume - Execute "resume" callbacks for given device.
  * @dev: Device to handle.
  * @state: PM transition of the system being carried out.
  * @async: If true, the device is being resumed asynchronously.
  */
-static void __device_resume(struct device *dev, pm_message_t state, bool async)
+static void device_resume(struct device *dev, pm_message_t state, bool async)
 {
 	pm_callback_t callback = NULL;
 	const char *info = NULL;
@@ -975,18 +985,10 @@ static void async_resume(void *data, async_cookie_t cookie)
 {
 	struct device *dev = data;
 
-	__device_resume(dev, pm_transition, true);
+	device_resume(dev, pm_transition, true);
 	put_device(dev);
 }
 
-static void device_resume(struct device *dev)
-{
-	if (dpm_async_fn(dev, async_resume))
-		return;
-
-	__device_resume(dev, pm_transition, false);
-}
-
 /**
  * dpm_resume - Execute "resume" callbacks for non-sysdev devices.
  * @state: PM transition of the system being carried out.
@@ -1006,16 +1008,25 @@ void dpm_resume(pm_message_t state)
 	pm_transition = state;
 	async_error = 0;
 
+	/*
+	 * Trigger the resume of "async" devices upfront so they don't have to
+	 * wait for the "non-async" ones they don't depend on.
+	 */
+	list_for_each_entry(dev, &dpm_suspended_list, power.entry)
+		dpm_async_fn(dev, async_resume);
+
 	while (!list_empty(&dpm_suspended_list)) {
 		dev = to_device(dpm_suspended_list.next);
 
 		get_device(dev);
 
-		mutex_unlock(&dpm_list_mtx);
+		if (!dev->power.async_in_progress) {
+			mutex_unlock(&dpm_list_mtx);
 
-		device_resume(dev);
+			device_resume(dev, state, false);
 
-		mutex_lock(&dpm_list_mtx);
+			mutex_lock(&dpm_list_mtx);
+		}
 
 		if (!list_empty(&dev->power.entry))
 			list_move_tail(&dev->power.entry, &dpm_prepared_list);
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 8e93167f1783..bd77f6734f14 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -201,7 +201,7 @@ static int dev_pm_qos_constraints_allocate(struct device *dev)
 	if (!qos)
 		return -ENOMEM;
 
-	n = kzalloc(3 * sizeof(*n), GFP_KERNEL);
+	n = kcalloc(3, sizeof(*n), GFP_KERNEL);
 	if (!n) {
 		kfree(qos);
 		return -ENOMEM;
diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c
index 72b7a92337b1..cd6e559648b2 100644
--- a/drivers/base/power/trace.c
+++ b/drivers/base/power/trace.c
@@ -120,7 +120,7 @@ static unsigned int read_magic_time(void)
 	struct rtc_time time;
 	unsigned int val;
 
-	if (mc146818_get_time(&time) < 0) {
+	if (mc146818_get_time(&time, 1000) < 0) {
 		pr_err("Unable to read current time from RTC\n");
 		return 0;
 	}
diff --git a/drivers/base/property.c b/drivers/base/property.c
index b79608ee0b46..a1b01ab42052 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -473,7 +473,7 @@ int fwnode_property_match_string(const struct fwnode_handle *fwnode,
 	const char **values;
 	int nval, ret;
 
-	nval = fwnode_property_read_string_array(fwnode, propname, NULL, 0);
+	nval = fwnode_property_string_array_count(fwnode, propname);
 	if (nval < 0)
 		return nval;
 
@@ -499,6 +499,41 @@ out_free:
 EXPORT_SYMBOL_GPL(fwnode_property_match_string);
 
 /**
+ * fwnode_property_match_property_string - find a property string value in an array and return index
+ * @fwnode: Firmware node to get the property of
+ * @propname: Name of the property holding the string value
+ * @array: String array to search in
+ * @n: Size of the @array
+ *
+ * Find a property string value in a given @array and if it is found return
+ * the index back.
+ *
+ * Return: index, starting from %0, if the string value was found in the @array (success),
+ *	   %-ENOENT when the string value was not found in the @array,
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO or %-EILSEQ if the property is not a string,
+ *	   %-ENXIO if no suitable firmware interface is present.
+ */
+int fwnode_property_match_property_string(const struct fwnode_handle *fwnode,
+	const char *propname, const char * const *array, size_t n)
+{
+	const char *string;
+	int ret;
+
+	ret = fwnode_property_read_string(fwnode, propname, &string);
+	if (ret)
+		return ret;
+
+	ret = match_string(array, n, string);
+	if (ret < 0)
+		ret = -ENOENT;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(fwnode_property_match_property_string);
+
+/**
  * fwnode_property_get_reference_args() - Find a reference with arguments
  * @fwnode:	Firmware node where to look for the reference
  * @prop:	The name of the property
@@ -508,6 +543,7 @@ EXPORT_SYMBOL_GPL(fwnode_property_match_string);
  * @nargs:	Number of arguments. Ignored if @nargs_prop is non-NULL.
  * @index:	Index of the reference, from zero onwards.
  * @args:	Result structure with reference and integer arguments.
+ *		May be NULL.
  *
  * Obtain a reference based on a named property in an fwnode, with
  * integer arguments.
diff --git a/drivers/base/regmap/regmap-kunit.c b/drivers/base/regmap/regmap-kunit.c
index 026bdcb45127..0d957c5f1bcc 100644
--- a/drivers/base/regmap/regmap-kunit.c
+++ b/drivers/base/regmap/regmap-kunit.c
@@ -9,6 +9,23 @@
 
 #define BLOCK_TEST_SIZE 12
 
+static void get_changed_bytes(void *orig, void *new, size_t size)
+{
+	char *o = orig;
+	char *n = new;
+	int i;
+
+	get_random_bytes(new, size);
+
+	/*
+	 * This could be nicer and more efficient but we shouldn't
+	 * super care.
+	 */
+	for (i = 0; i < size; i++)
+		while (n[i] == o[i])
+			get_random_bytes(&n[i], 1);
+}
+
 static const struct regmap_config test_regmap_config = {
 	.max_register = BLOCK_TEST_SIZE,
 	.reg_stride = 1,
@@ -1202,7 +1219,8 @@ static void raw_noinc_write(struct kunit *test)
 	struct regmap *map;
 	struct regmap_config config;
 	struct regmap_ram_data *data;
-	unsigned int val, val_test, val_last;
+	unsigned int val;
+	u16 val_test, val_last;
 	u16 val_array[BLOCK_TEST_SIZE];
 
 	config = raw_regmap_config;
@@ -1251,7 +1269,7 @@ static void raw_sync(struct kunit *test)
 	struct regmap *map;
 	struct regmap_config config;
 	struct regmap_ram_data *data;
-	u16 val[2];
+	u16 val[3];
 	u16 *hw_buf;
 	unsigned int rval;
 	int i;
@@ -1265,17 +1283,13 @@ static void raw_sync(struct kunit *test)
 
 	hw_buf = (u16 *)data->vals;
 
-	get_random_bytes(&val, sizeof(val));
+	get_changed_bytes(&hw_buf[2], &val[0], sizeof(val));
 
 	/* Do a regular write and a raw write in cache only mode */
 	regcache_cache_only(map, true);
-	KUNIT_EXPECT_EQ(test, 0, regmap_raw_write(map, 2, val, sizeof(val)));
-	if (config.val_format_endian == REGMAP_ENDIAN_BIG)
-		KUNIT_EXPECT_EQ(test, 0, regmap_write(map, 6,
-						      be16_to_cpu(val[0])));
-	else
-		KUNIT_EXPECT_EQ(test, 0, regmap_write(map, 6,
-						      le16_to_cpu(val[0])));
+	KUNIT_EXPECT_EQ(test, 0, regmap_raw_write(map, 2, val,
+						  sizeof(u16) * 2));
+	KUNIT_EXPECT_EQ(test, 0, regmap_write(map, 4, val[2]));
 
 	/* We should read back the new values, and defaults for the rest */
 	for (i = 0; i < config.max_register + 1; i++) {
@@ -1284,24 +1298,34 @@ static void raw_sync(struct kunit *test)
 		switch (i) {
 		case 2:
 		case 3:
-		case 6:
 			if (config.val_format_endian == REGMAP_ENDIAN_BIG) {
 				KUNIT_EXPECT_EQ(test, rval,
-						be16_to_cpu(val[i % 2]));
+						be16_to_cpu(val[i - 2]));
 			} else {
 				KUNIT_EXPECT_EQ(test, rval,
-						le16_to_cpu(val[i % 2]));
+						le16_to_cpu(val[i - 2]));
 			}
 			break;
+		case 4:
+			KUNIT_EXPECT_EQ(test, rval, val[i - 2]);
+			break;
 		default:
 			KUNIT_EXPECT_EQ(test, config.reg_defaults[i].def, rval);
 			break;
 		}
 	}
+
+	/*
+	 * The value written via _write() was translated by the core,
+	 * translate the original copy for comparison purposes.
+	 */
+	if (config.val_format_endian == REGMAP_ENDIAN_BIG)
+		val[2] = cpu_to_be16(val[2]);
+	else
+		val[2] = cpu_to_le16(val[2]);
 	
 	/* The values should not appear in the "hardware" */
-	KUNIT_EXPECT_MEMNEQ(test, &hw_buf[2], val, sizeof(val));
-	KUNIT_EXPECT_MEMNEQ(test, &hw_buf[6], val, sizeof(u16));
+	KUNIT_EXPECT_MEMNEQ(test, &hw_buf[2], &val[0], sizeof(val));
 
 	for (i = 0; i < config.max_register + 1; i++)
 		data->written[i] = false;
@@ -1312,8 +1336,7 @@ static void raw_sync(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, 0, regcache_sync(map));
 
 	/* The values should now appear in the "hardware" */
-	KUNIT_EXPECT_MEMEQ(test, &hw_buf[2], val, sizeof(val));
-	KUNIT_EXPECT_MEMEQ(test, &hw_buf[6], val, sizeof(u16));
+	KUNIT_EXPECT_MEMEQ(test, &hw_buf[2], &val[0], sizeof(val));
 
 	regmap_exit(map);
 }
diff --git a/drivers/base/soc.c b/drivers/base/soc.c
index 8dec5228fde3..282c38aece0d 100644
--- a/drivers/base/soc.c
+++ b/drivers/base/soc.c
@@ -28,7 +28,7 @@ struct soc_device {
 	int soc_dev_num;
 };
 
-static struct bus_type soc_bus_type = {
+static const struct bus_type soc_bus_type = {
 	.name  = "soc",
 };
 static bool soc_bus_registered;
@@ -106,7 +106,7 @@ static void soc_release(struct device *dev)
 {
 	struct soc_device *soc_dev = container_of(dev, struct soc_device, dev);
 
-	ida_simple_remove(&soc_ida, soc_dev->soc_dev_num);
+	ida_free(&soc_ida, soc_dev->soc_dev_num);
 	kfree(soc_dev->dev.groups);
 	kfree(soc_dev);
 }
@@ -155,7 +155,7 @@ struct soc_device *soc_device_register(struct soc_device_attribute *soc_dev_attr
 	soc_attr_groups[1] = soc_dev_attr->custom_attr_group;
 
 	/* Fetch a unique (reclaimable) SOC ID. */
-	ret = ida_simple_get(&soc_ida, 0, 0, GFP_KERNEL);
+	ret = ida_alloc(&soc_ida, GFP_KERNEL);
 	if (ret < 0)
 		goto out3;
 	soc_dev->soc_dev_num = ret;
diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c
index 1886995a0b3a..36512fb75a20 100644
--- a/drivers/base/swnode.c
+++ b/drivers/base/swnode.c
@@ -541,6 +541,9 @@ software_node_get_reference_args(const struct fwnode_handle *fwnode,
 	if (nargs > NR_FWNODE_REFERENCE_ARGS)
 		return -EINVAL;
 
+	if (!args)
+		return 0;
+
 	args->fwnode = software_node_get(refnode);
 	args->nargs = nargs;
 
@@ -747,10 +750,10 @@ static void software_node_release(struct kobject *kobj)
 	struct swnode *swnode = kobj_to_swnode(kobj);
 
 	if (swnode->parent) {
-		ida_simple_remove(&swnode->parent->child_ids, swnode->id);
+		ida_free(&swnode->parent->child_ids, swnode->id);
 		list_del(&swnode->entry);
 	} else {
-		ida_simple_remove(&swnode_root_ids, swnode->id);
+		ida_free(&swnode_root_ids, swnode->id);
 	}
 
 	if (swnode->allocated)
@@ -776,8 +779,8 @@ swnode_register(const struct software_node *node, struct swnode *parent,
 	if (!swnode)
 		return ERR_PTR(-ENOMEM);
 
-	ret = ida_simple_get(parent ? &parent->child_ids : &swnode_root_ids,
-			     0, 0, GFP_KERNEL);
+	ret = ida_alloc(parent ? &parent->child_ids : &swnode_root_ids,
+			GFP_KERNEL);
 	if (ret < 0) {
 		kfree(swnode);
 		return ERR_PTR(ret);
diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c
index 2b98114a9fe0..a25414228e47 100644
--- a/drivers/block/amiflop.c
+++ b/drivers/block/amiflop.c
@@ -1779,7 +1779,7 @@ static int fd_alloc_disk(int drive, int system)
 	struct gendisk *disk;
 	int err;
 
-	disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL);
+	disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL, NULL);
 	if (IS_ERR(disk))
 		return PTR_ERR(disk);
 
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index d2dbf8aaccb5..b6dac8cee70f 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -24,8 +24,8 @@ static DEFINE_MUTEX(aoeblk_mutex);
 static struct kmem_cache *buf_pool_cache;
 static struct dentry *aoe_debugfs_dir;
 
-/* GPFS needs a larger value than the default. */
-static int aoe_maxsectors;
+/* random default picked from the historic block max_sectors cap */
+static int aoe_maxsectors = 2560;
 module_param(aoe_maxsectors, int, 0644);
 MODULE_PARM_DESC(aoe_maxsectors,
 	"When nonzero, set the maximum number of sectors per I/O request");
@@ -333,6 +333,11 @@ aoeblk_gdalloc(void *vp)
 	struct gendisk *gd;
 	mempool_t *mp;
 	struct blk_mq_tag_set *set;
+	sector_t ssize;
+	struct queue_limits lim = {
+		.max_hw_sectors		= aoe_maxsectors,
+		.io_opt			= SZ_2M,
+	};
 	ulong flags;
 	int late = 0;
 	int err;
@@ -370,7 +375,7 @@ aoeblk_gdalloc(void *vp)
 		goto err_mempool;
 	}
 
-	gd = blk_mq_alloc_disk(set, d);
+	gd = blk_mq_alloc_disk(set, &lim, d);
 	if (IS_ERR(gd)) {
 		pr_err("aoe: cannot allocate block queue for %ld.%d\n",
 			d->aoemajor, d->aoeminor);
@@ -383,20 +388,15 @@ aoeblk_gdalloc(void *vp)
 	WARN_ON(d->flags & DEVFL_TKILL);
 	WARN_ON(d->gd);
 	WARN_ON(d->flags & DEVFL_UP);
-	/* random number picked from the history block max_sectors cap */
-	blk_queue_max_hw_sectors(gd->queue, 2560u);
-	blk_queue_io_opt(gd->queue, SZ_2M);
 	d->bufpool = mp;
 	d->blkq = gd->queue;
 	d->gd = gd;
-	if (aoe_maxsectors)
-		blk_queue_max_hw_sectors(gd->queue, aoe_maxsectors);
 	gd->major = AOE_MAJOR;
 	gd->first_minor = d->sysminor;
 	gd->minors = AOE_PARTITIONS;
 	gd->fops = &aoe_bdops;
 	gd->private_data = d;
-	set_capacity(gd, d->ssize);
+	ssize = d->ssize;
 	snprintf(gd->disk_name, sizeof gd->disk_name, "etherd/e%ld.%d",
 		d->aoemajor, d->aoeminor);
 
@@ -405,6 +405,8 @@ aoeblk_gdalloc(void *vp)
 
 	spin_unlock_irqrestore(&d->lock, flags);
 
+	set_capacity(gd, ssize);
+
 	err = device_add_disk(NULL, gd, aoe_attr_groups);
 	if (err)
 		goto out_disk_cleanup;
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index d7317425be51..cc9077b588d7 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -419,13 +419,16 @@ aoecmd_cfg_pkts(ushort aoemajor, unsigned char aoeminor, struct sk_buff_head *qu
 	rcu_read_lock();
 	for_each_netdev_rcu(&init_net, ifp) {
 		dev_hold(ifp);
-		if (!is_aoe_netif(ifp))
-			goto cont;
+		if (!is_aoe_netif(ifp)) {
+			dev_put(ifp);
+			continue;
+		}
 
 		skb = new_skb(sizeof *h + sizeof *ch);
 		if (skb == NULL) {
 			printk(KERN_INFO "aoe: skb alloc failure\n");
-			goto cont;
+			dev_put(ifp);
+			continue;
 		}
 		skb_put(skb, sizeof *h + sizeof *ch);
 		skb->dev = ifp;
@@ -440,9 +443,6 @@ aoecmd_cfg_pkts(ushort aoemajor, unsigned char aoeminor, struct sk_buff_head *qu
 		h->major = cpu_to_be16(aoemajor);
 		h->minor = aoeminor;
 		h->cmd = AOECMD_CFG;
-
-cont:
-		dev_put(ifp);
 	}
 	rcu_read_unlock();
 }
diff --git a/drivers/block/aoe/aoenet.c b/drivers/block/aoe/aoenet.c
index c51ea95bc2ce..923a134fd766 100644
--- a/drivers/block/aoe/aoenet.c
+++ b/drivers/block/aoe/aoenet.c
@@ -63,6 +63,7 @@ tx(int id) __must_hold(&txlock)
 			pr_warn("aoe: packet could not be sent on %s.  %s\n",
 				ifp ? ifp->name : "netif",
 				"consider increasing tx_queue_len");
+		dev_put(ifp);
 		spin_lock_irq(&txlock);
 	}
 	return 0;
diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index 50949207798d..cacc4ba942a8 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -1994,7 +1994,7 @@ static int ataflop_alloc_disk(unsigned int drive, unsigned int type)
 {
 	struct gendisk *disk;
 
-	disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL);
+	disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL, NULL);
 	if (IS_ERR(disk))
 		return PTR_ERR(disk);
 
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 970bd6ff38c4..e322cef6596b 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -318,6 +318,16 @@ static int brd_alloc(int i)
 	struct gendisk *disk;
 	char buf[DISK_NAME_LEN];
 	int err = -ENOMEM;
+	struct queue_limits lim = {
+		/*
+		 * This is so fdisk will align partitions on 4k, because of
+		 * direct_access API needing 4k alignment, returning a PFN
+		 * (This is only a problem on very small devices <= 4M,
+		 *  otherwise fdisk will align on 1M. Regardless this call
+		 *  is harmless)
+		 */
+		.physical_block_size	= PAGE_SIZE,
+	};
 
 	list_for_each_entry(brd, &brd_devices, brd_list)
 		if (brd->brd_number == i)
@@ -335,10 +345,11 @@ static int brd_alloc(int i)
 		debugfs_create_u64(buf, 0444, brd_debugfs_dir,
 				&brd->brd_nr_pages);
 
-	disk = brd->brd_disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!disk)
+	disk = brd->brd_disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(disk)) {
+		err = PTR_ERR(disk);
 		goto out_free_dev;
-
+	}
 	disk->major		= RAMDISK_MAJOR;
 	disk->first_minor	= i * max_part;
 	disk->minors		= max_part;
@@ -347,15 +358,6 @@ static int brd_alloc(int i)
 	strscpy(disk->disk_name, buf, DISK_NAME_LEN);
 	set_capacity(disk, rd_size * 2);
 	
-	/*
-	 * This is so fdisk will align partitions on 4k, because of
-	 * direct_access API needing 4k alignment, returning a PFN
-	 * (This is only a problem on very small devices <= 4M,
-	 *  otherwise fdisk will align on 1M. Regardless this call
-	 *  is harmless)
-	 */
-	blk_queue_physical_block_size(disk->queue, PAGE_SIZE);
-
 	/* Tell the block layer that this is not a rotational device */
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
 	blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, disk->queue);
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index c21e3732759e..94dc0a235919 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -524,9 +524,9 @@ struct drbd_md {
 
 struct drbd_backing_dev {
 	struct block_device *backing_bdev;
-	struct bdev_handle *backing_bdev_handle;
+	struct file *backing_bdev_file;
 	struct block_device *md_bdev;
-	struct bdev_handle *md_bdev_handle;
+	struct file *f_md_bdev;
 	struct drbd_md md;
 	struct disk_conf *disk_conf; /* RCU, for updates: resource->conf_update */
 	sector_t known_size; /* last known size of that backing device */
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 6bc86106c7b2..113b441d4d36 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2690,6 +2690,14 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 	int id;
 	int vnr = adm_ctx->volume;
 	enum drbd_ret_code err = ERR_NOMEM;
+	struct queue_limits lim = {
+		/*
+		 * Setting the max_hw_sectors to an odd value of 8kibyte here.
+		 * This triggers a max_bio_size message upon first attach or
+		 * connect.
+		 */
+		.max_hw_sectors		= DRBD_MAX_BIO_SIZE_SAFE >> 8,
+	};
 
 	device = minor_to_device(minor);
 	if (device)
@@ -2708,9 +2716,11 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 	drbd_init_set_defaults(device);
 
-	disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!disk)
+	disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(disk)) {
+		err = PTR_ERR(disk);
 		goto out_no_disk;
+	}
 
 	device->vdisk = disk;
 	device->rq_queue = disk->queue;
@@ -2727,9 +2737,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue);
 	blk_queue_write_cache(disk->queue, true, true);
-	/* Setting the max_hw_sectors to an odd value of 8kibyte here
-	   This triggers a max_bio_size message upon first attach or connect */
-	blk_queue_max_hw_sectors(disk->queue, DRBD_MAX_BIO_SIZE_SAFE >> 8);
 
 	device->md_io.page = alloc_page(GFP_KERNEL);
 	if (!device->md_io.page)
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 43747a1aae43..5d65c9754d83 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1189,9 +1189,31 @@ static int drbd_check_al_size(struct drbd_device *device, struct disk_conf *dc)
 	return 0;
 }
 
-static void blk_queue_discard_granularity(struct request_queue *q, unsigned int granularity)
+static unsigned int drbd_max_peer_bio_size(struct drbd_device *device)
 {
-	q->limits.discard_granularity = granularity;
+	/*
+	 * We may ignore peer limits if the peer is modern enough.  From 8.3.8
+	 * onwards the peer can use multiple BIOs for a single peer_request.
+	 */
+	if (device->state.conn < C_WF_REPORT_PARAMS)
+		return device->peer_max_bio_size;
+
+	if (first_peer_device(device)->connection->agreed_pro_version < 94)
+		return min(device->peer_max_bio_size, DRBD_MAX_SIZE_H80_PACKET);
+
+	/*
+	 * Correct old drbd (up to 8.3.7) if it believes it can do more than
+	 * 32KiB.
+	 */
+	if (first_peer_device(device)->connection->agreed_pro_version == 94)
+		return DRBD_MAX_SIZE_H80_PACKET;
+
+	/*
+	 * drbd 8.3.8 onwards, before 8.4.0
+	 */
+	if (first_peer_device(device)->connection->agreed_pro_version < 100)
+		return DRBD_MAX_BIO_SIZE_P95;
+	return DRBD_MAX_BIO_SIZE;
 }
 
 static unsigned int drbd_max_discard_sectors(struct drbd_connection *connection)
@@ -1204,149 +1226,119 @@ static unsigned int drbd_max_discard_sectors(struct drbd_connection *connection)
 	return AL_EXTENT_SIZE >> 9;
 }
 
-static void decide_on_discard_support(struct drbd_device *device,
+static bool drbd_discard_supported(struct drbd_connection *connection,
 		struct drbd_backing_dev *bdev)
 {
-	struct drbd_connection *connection =
-		first_peer_device(device)->connection;
-	struct request_queue *q = device->rq_queue;
-	unsigned int max_discard_sectors;
-
 	if (bdev && !bdev_max_discard_sectors(bdev->backing_bdev))
-		goto not_supported;
+		return false;
 
 	if (connection->cstate >= C_CONNECTED &&
 	    !(connection->agreed_features & DRBD_FF_TRIM)) {
 		drbd_info(connection,
 			"peer DRBD too old, does not support TRIM: disabling discards\n");
-		goto not_supported;
+		return false;
 	}
 
-	/*
-	 * We don't care for the granularity, really.
-	 *
-	 * Stacking limits below should fix it for the local device.  Whether or
-	 * not it is a suitable granularity on the remote device is not our
-	 * problem, really. If you care, you need to use devices with similar
-	 * topology on all peers.
-	 */
-	blk_queue_discard_granularity(q, 512);
-	max_discard_sectors = drbd_max_discard_sectors(connection);
-	blk_queue_max_discard_sectors(q, max_discard_sectors);
-	blk_queue_max_write_zeroes_sectors(q, max_discard_sectors);
-	return;
-
-not_supported:
-	blk_queue_discard_granularity(q, 0);
-	blk_queue_max_discard_sectors(q, 0);
+	return true;
 }
 
-static void fixup_write_zeroes(struct drbd_device *device, struct request_queue *q)
+/* This is the workaround for "bio would need to, but cannot, be split" */
+static unsigned int drbd_backing_dev_max_segments(struct drbd_device *device)
 {
-	/* Fixup max_write_zeroes_sectors after blk_stack_limits():
-	 * if we can handle "zeroes" efficiently on the protocol,
-	 * we want to do that, even if our backend does not announce
-	 * max_write_zeroes_sectors itself. */
-	struct drbd_connection *connection = first_peer_device(device)->connection;
-	/* If the peer announces WZEROES support, use it.  Otherwise, rather
-	 * send explicit zeroes than rely on some discard-zeroes-data magic. */
-	if (connection->agreed_features & DRBD_FF_WZEROES)
-		q->limits.max_write_zeroes_sectors = DRBD_MAX_BBIO_SECTORS;
-	else
-		q->limits.max_write_zeroes_sectors = 0;
-}
+	unsigned int max_segments;
 
-static void fixup_discard_support(struct drbd_device *device, struct request_queue *q)
-{
-	unsigned int max_discard = device->rq_queue->limits.max_discard_sectors;
-	unsigned int discard_granularity =
-		device->rq_queue->limits.discard_granularity >> SECTOR_SHIFT;
+	rcu_read_lock();
+	max_segments = rcu_dereference(device->ldev->disk_conf)->max_bio_bvecs;
+	rcu_read_unlock();
 
-	if (discard_granularity > max_discard) {
-		blk_queue_discard_granularity(q, 0);
-		blk_queue_max_discard_sectors(q, 0);
-	}
+	if (!max_segments)
+		return BLK_MAX_SEGMENTS;
+	return max_segments;
 }
 
-static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backing_dev *bdev,
-				   unsigned int max_bio_size, struct o_qlim *o)
+void drbd_reconsider_queue_parameters(struct drbd_device *device,
+		struct drbd_backing_dev *bdev, struct o_qlim *o)
 {
+	struct drbd_connection *connection =
+		first_peer_device(device)->connection;
 	struct request_queue * const q = device->rq_queue;
-	unsigned int max_hw_sectors = max_bio_size >> 9;
-	unsigned int max_segments = 0;
+	unsigned int now = queue_max_hw_sectors(q) << 9;
+	struct queue_limits lim;
 	struct request_queue *b = NULL;
-	struct disk_conf *dc;
+	unsigned int new;
 
 	if (bdev) {
 		b = bdev->backing_bdev->bd_disk->queue;
 
-		max_hw_sectors = min(queue_max_hw_sectors(b), max_bio_size >> 9);
-		rcu_read_lock();
-		dc = rcu_dereference(device->ldev->disk_conf);
-		max_segments = dc->max_bio_bvecs;
-		rcu_read_unlock();
-
-		blk_set_stacking_limits(&q->limits);
+		device->local_max_bio_size =
+			queue_max_hw_sectors(b) << SECTOR_SHIFT;
 	}
 
-	blk_queue_max_hw_sectors(q, max_hw_sectors);
-	/* This is the workaround for "bio would need to, but cannot, be split" */
-	blk_queue_max_segments(q, max_segments ? max_segments : BLK_MAX_SEGMENTS);
-	blk_queue_segment_boundary(q, PAGE_SIZE-1);
-	decide_on_discard_support(device, bdev);
-
-	if (b) {
-		blk_stack_limits(&q->limits, &b->limits, 0);
-		disk_update_readahead(device->vdisk);
+	/*
+	 * We may later detach and re-attach on a disconnected Primary.  Avoid
+	 * decreasing the value in this case.
+	 *
+	 * We want to store what we know the peer DRBD can handle, not what the
+	 * peer IO backend can handle.
+	 */
+	new = min3(DRBD_MAX_BIO_SIZE, device->local_max_bio_size,
+		max(drbd_max_peer_bio_size(device), device->peer_max_bio_size));
+	if (new != now) {
+		if (device->state.role == R_PRIMARY && new < now)
+			drbd_err(device, "ASSERT FAILED new < now; (%u < %u)\n",
+					new, now);
+		drbd_info(device, "max BIO size = %u\n", new);
 	}
-	fixup_write_zeroes(device, q);
-	fixup_discard_support(device, q);
-}
-
-void drbd_reconsider_queue_parameters(struct drbd_device *device, struct drbd_backing_dev *bdev, struct o_qlim *o)
-{
-	unsigned int now, new, local, peer;
-
-	now = queue_max_hw_sectors(device->rq_queue) << 9;
-	local = device->local_max_bio_size; /* Eventually last known value, from volatile memory */
-	peer = device->peer_max_bio_size; /* Eventually last known value, from meta data */
 
+	lim = queue_limits_start_update(q);
 	if (bdev) {
-		local = queue_max_hw_sectors(bdev->backing_bdev->bd_disk->queue) << 9;
-		device->local_max_bio_size = local;
+		blk_set_stacking_limits(&lim);
+		lim.max_segments = drbd_backing_dev_max_segments(device);
+	} else {
+		lim.max_segments = BLK_MAX_SEGMENTS;
 	}
-	local = min(local, DRBD_MAX_BIO_SIZE);
 
-	/* We may ignore peer limits if the peer is modern enough.
-	   Because new from 8.3.8 onwards the peer can use multiple
-	   BIOs for a single peer_request */
-	if (device->state.conn >= C_WF_REPORT_PARAMS) {
-		if (first_peer_device(device)->connection->agreed_pro_version < 94)
-			peer = min(device->peer_max_bio_size, DRBD_MAX_SIZE_H80_PACKET);
-			/* Correct old drbd (up to 8.3.7) if it believes it can do more than 32KiB */
-		else if (first_peer_device(device)->connection->agreed_pro_version == 94)
-			peer = DRBD_MAX_SIZE_H80_PACKET;
-		else if (first_peer_device(device)->connection->agreed_pro_version < 100)
-			peer = DRBD_MAX_BIO_SIZE_P95;  /* drbd 8.3.8 onwards, before 8.4.0 */
-		else
-			peer = DRBD_MAX_BIO_SIZE;
+	lim.max_hw_sectors = new >> SECTOR_SHIFT;
+	lim.seg_boundary_mask = PAGE_SIZE - 1;
 
-		/* We may later detach and re-attach on a disconnected Primary.
-		 * Avoid this setting to jump back in that case.
-		 * We want to store what we know the peer DRBD can handle,
-		 * not what the peer IO backend can handle. */
-		if (peer > device->peer_max_bio_size)
-			device->peer_max_bio_size = peer;
+	/*
+	 * We don't care for the granularity, really.
+	 *
+	 * Stacking limits below should fix it for the local device.  Whether or
+	 * not it is a suitable granularity on the remote device is not our
+	 * problem, really. If you care, you need to use devices with similar
+	 * topology on all peers.
+	 */
+	if (drbd_discard_supported(connection, bdev)) {
+		lim.discard_granularity = 512;
+		lim.max_hw_discard_sectors =
+			drbd_max_discard_sectors(connection);
+	} else {
+		lim.discard_granularity = 0;
+		lim.max_hw_discard_sectors = 0;
 	}
-	new = min(local, peer);
 
-	if (device->state.role == R_PRIMARY && new < now)
-		drbd_err(device, "ASSERT FAILED new < now; (%u < %u)\n", new, now);
+	if (bdev)
+		blk_stack_limits(&lim, &b->limits, 0);
 
-	if (new != now)
-		drbd_info(device, "max BIO size = %u\n", new);
+	/*
+	 * If we can handle "zeroes" efficiently on the protocol, we want to do
+	 * that, even if our backend does not announce max_write_zeroes_sectors
+	 * itself.
+	 */
+	if (connection->agreed_features & DRBD_FF_WZEROES)
+		lim.max_write_zeroes_sectors = DRBD_MAX_BBIO_SECTORS;
+	else
+		lim.max_write_zeroes_sectors = 0;
+
+	if ((lim.discard_granularity >> SECTOR_SHIFT) >
+	    lim.max_hw_discard_sectors) {
+		lim.discard_granularity = 0;
+		lim.max_hw_discard_sectors = 0;
+	}
 
-	drbd_setup_queue_param(device, bdev, new, o);
+	if (queue_limits_commit_update(q, &lim))
+		drbd_err(device, "setting new queue limits failed\n");
 }
 
 /* Starts the worker thread */
@@ -1635,45 +1627,45 @@ success:
 	return 0;
 }
 
-static struct bdev_handle *open_backing_dev(struct drbd_device *device,
+static struct file *open_backing_dev(struct drbd_device *device,
 		const char *bdev_path, void *claim_ptr, bool do_bd_link)
 {
-	struct bdev_handle *handle;
+	struct file *file;
 	int err = 0;
 
-	handle = bdev_open_by_path(bdev_path, BLK_OPEN_READ | BLK_OPEN_WRITE,
-				   claim_ptr, NULL);
-	if (IS_ERR(handle)) {
+	file = bdev_file_open_by_path(bdev_path, BLK_OPEN_READ | BLK_OPEN_WRITE,
+				      claim_ptr, NULL);
+	if (IS_ERR(file)) {
 		drbd_err(device, "open(\"%s\") failed with %ld\n",
-				bdev_path, PTR_ERR(handle));
-		return handle;
+				bdev_path, PTR_ERR(file));
+		return file;
 	}
 
 	if (!do_bd_link)
-		return handle;
+		return file;
 
-	err = bd_link_disk_holder(handle->bdev, device->vdisk);
+	err = bd_link_disk_holder(file_bdev(file), device->vdisk);
 	if (err) {
-		bdev_release(handle);
+		fput(file);
 		drbd_err(device, "bd_link_disk_holder(\"%s\", ...) failed with %d\n",
 				bdev_path, err);
-		handle = ERR_PTR(err);
+		file = ERR_PTR(err);
 	}
-	return handle;
+	return file;
 }
 
 static int open_backing_devices(struct drbd_device *device,
 		struct disk_conf *new_disk_conf,
 		struct drbd_backing_dev *nbc)
 {
-	struct bdev_handle *handle;
+	struct file *file;
 
-	handle = open_backing_dev(device, new_disk_conf->backing_dev, device,
+	file = open_backing_dev(device, new_disk_conf->backing_dev, device,
 				  true);
-	if (IS_ERR(handle))
+	if (IS_ERR(file))
 		return ERR_OPEN_DISK;
-	nbc->backing_bdev = handle->bdev;
-	nbc->backing_bdev_handle = handle;
+	nbc->backing_bdev = file_bdev(file);
+	nbc->backing_bdev_file = file;
 
 	/*
 	 * meta_dev_idx >= 0: external fixed size, possibly multiple
@@ -1683,7 +1675,7 @@ static int open_backing_devices(struct drbd_device *device,
 	 * should check it for you already; but if you don't, or
 	 * someone fooled it, we need to double check here)
 	 */
-	handle = open_backing_dev(device, new_disk_conf->meta_dev,
+	file = open_backing_dev(device, new_disk_conf->meta_dev,
 		/* claim ptr: device, if claimed exclusively; shared drbd_m_holder,
 		 * if potentially shared with other drbd minors */
 			(new_disk_conf->meta_dev_idx < 0) ? (void*)device : (void*)drbd_m_holder,
@@ -1691,21 +1683,21 @@ static int open_backing_devices(struct drbd_device *device,
 		 * as would happen with internal metadata. */
 			(new_disk_conf->meta_dev_idx != DRBD_MD_INDEX_FLEX_INT &&
 			 new_disk_conf->meta_dev_idx != DRBD_MD_INDEX_INTERNAL));
-	if (IS_ERR(handle))
+	if (IS_ERR(file))
 		return ERR_OPEN_MD_DISK;
-	nbc->md_bdev = handle->bdev;
-	nbc->md_bdev_handle = handle;
+	nbc->md_bdev = file_bdev(file);
+	nbc->f_md_bdev = file;
 	return NO_ERROR;
 }
 
 static void close_backing_dev(struct drbd_device *device,
-		struct bdev_handle *handle, bool do_bd_unlink)
+		struct file *bdev_file, bool do_bd_unlink)
 {
-	if (!handle)
+	if (!bdev_file)
 		return;
 	if (do_bd_unlink)
-		bd_unlink_disk_holder(handle->bdev, device->vdisk);
-	bdev_release(handle);
+		bd_unlink_disk_holder(file_bdev(bdev_file), device->vdisk);
+	fput(bdev_file);
 }
 
 void drbd_backing_dev_free(struct drbd_device *device, struct drbd_backing_dev *ldev)
@@ -1713,9 +1705,9 @@ void drbd_backing_dev_free(struct drbd_device *device, struct drbd_backing_dev *
 	if (ldev == NULL)
 		return;
 
-	close_backing_dev(device, ldev->md_bdev_handle,
+	close_backing_dev(device, ldev->f_md_bdev,
 			  ldev->md_bdev != ldev->backing_bdev);
-	close_backing_dev(device, ldev->backing_bdev_handle, true);
+	close_backing_dev(device, ldev->backing_bdev_file, true);
 
 	kfree(ldev->disk_conf);
 	kfree(ldev);
@@ -2131,9 +2123,9 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
  fail:
 	conn_reconfig_done(connection);
 	if (nbc) {
-		close_backing_dev(device, nbc->md_bdev_handle,
+		close_backing_dev(device, nbc->f_md_bdev,
 			  nbc->md_bdev != nbc->backing_bdev);
-		close_backing_dev(device, nbc->backing_bdev_handle, true);
+		close_backing_dev(device, nbc->backing_bdev_file, true);
 		kfree(nbc);
 	}
 	kfree(new_disk_conf);
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index 287a8d1d3f70..e858e7e0383f 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -1542,9 +1542,10 @@ int drbd_bitmap_io_from_worker(struct drbd_device *device,
 
 int notify_resource_state_change(struct sk_buff *skb,
 				  unsigned int seq,
-				  struct drbd_resource_state_change *resource_state_change,
+				  void *state_change,
 				  enum drbd_notification_type type)
 {
+	struct drbd_resource_state_change *resource_state_change = state_change;
 	struct drbd_resource *resource = resource_state_change->resource;
 	struct resource_info resource_info = {
 		.res_role = resource_state_change->role[NEW],
@@ -1558,13 +1559,14 @@ int notify_resource_state_change(struct sk_buff *skb,
 
 int notify_connection_state_change(struct sk_buff *skb,
 				    unsigned int seq,
-				    struct drbd_connection_state_change *connection_state_change,
+				    void *state_change,
 				    enum drbd_notification_type type)
 {
-	struct drbd_connection *connection = connection_state_change->connection;
+	struct drbd_connection_state_change *p = state_change;
+	struct drbd_connection *connection = p->connection;
 	struct connection_info connection_info = {
-		.conn_connection_state = connection_state_change->cstate[NEW],
-		.conn_role = connection_state_change->peer_role[NEW],
+		.conn_connection_state = p->cstate[NEW],
+		.conn_role = p->peer_role[NEW],
 	};
 
 	return notify_connection_state(skb, seq, connection, &connection_info, type);
@@ -1572,9 +1574,10 @@ int notify_connection_state_change(struct sk_buff *skb,
 
 int notify_device_state_change(struct sk_buff *skb,
 				unsigned int seq,
-				struct drbd_device_state_change *device_state_change,
+				void *state_change,
 				enum drbd_notification_type type)
 {
+	struct drbd_device_state_change *device_state_change = state_change;
 	struct drbd_device *device = device_state_change->device;
 	struct device_info device_info = {
 		.dev_disk_state = device_state_change->disk_state[NEW],
@@ -1585,9 +1588,10 @@ int notify_device_state_change(struct sk_buff *skb,
 
 int notify_peer_device_state_change(struct sk_buff *skb,
 				     unsigned int seq,
-				     struct drbd_peer_device_state_change *p,
+				     void *state_change,
 				     enum drbd_notification_type type)
 {
+	struct drbd_peer_device_state_change *p = state_change;
 	struct drbd_peer_device *peer_device = p->peer_device;
 	struct peer_device_info peer_device_info = {
 		.peer_repl_state = p->repl_state[NEW],
@@ -1605,8 +1609,8 @@ static void broadcast_state_change(struct drbd_state_change *state_change)
 	struct drbd_resource_state_change *resource_state_change = &state_change->resource[0];
 	bool resource_state_has_changed;
 	unsigned int n_device, n_connection, n_peer_device, n_peer_devices;
-	int (*last_func)(struct sk_buff *, unsigned int, void *,
-			  enum drbd_notification_type) = NULL;
+	int (*last_func)(struct sk_buff *, unsigned int,
+		void *, enum drbd_notification_type) = NULL;
 	void *last_arg = NULL;
 
 #define HAS_CHANGED(state) ((state)[OLD] != (state)[NEW])
@@ -1616,7 +1620,7 @@ static void broadcast_state_change(struct drbd_state_change *state_change)
 	})
 #define REMEMBER_STATE_CHANGE(func, arg, type) \
 	({ FINAL_STATE_CHANGE(type | NOTIFY_CONTINUES); \
-	   last_func = (typeof(last_func))func; \
+	   last_func = func; \
 	   last_arg = arg; \
 	 })
 
diff --git a/drivers/block/drbd/drbd_state_change.h b/drivers/block/drbd/drbd_state_change.h
index 9d78d8e3912e..a56a57d67686 100644
--- a/drivers/block/drbd/drbd_state_change.h
+++ b/drivers/block/drbd/drbd_state_change.h
@@ -46,19 +46,19 @@ extern void forget_state_change(struct drbd_state_change *);
 
 extern int notify_resource_state_change(struct sk_buff *,
 					 unsigned int,
-					 struct drbd_resource_state_change *,
+					 void *,
 					 enum drbd_notification_type type);
 extern int notify_connection_state_change(struct sk_buff *,
 					   unsigned int,
-					   struct drbd_connection_state_change *,
+					   void *,
 					   enum drbd_notification_type type);
 extern int notify_device_state_change(struct sk_buff *,
 				       unsigned int,
-				       struct drbd_device_state_change *,
+				       void *,
 				       enum drbd_notification_type type);
 extern int notify_peer_device_state_change(struct sk_buff *,
 					    unsigned int,
-					    struct drbd_peer_device_state_change *,
+					    void *,
 					    enum drbd_notification_type type);
 
 #endif  /* DRBD_STATE_CHANGE_H */
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index d0e41d52d6a9..1b399ec8c07d 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -530,14 +530,13 @@ static struct format_descr format_req;
 static char *floppy_track_buffer;
 static int max_buffer_sectors;
 
-typedef void (*done_f)(int);
 static const struct cont_t {
 	void (*interrupt)(void);
 				/* this is called after the interrupt of the
 				 * main command */
 	void (*redo)(void);	/* this is called to retry the operation */
 	void (*error)(void);	/* this is called to tally an error */
-	done_f done;		/* this is called to say if the operation has
+	void (*done)(int);	/* this is called to say if the operation has
 				 * succeeded/failed */
 } *cont;
 
@@ -985,6 +984,10 @@ static void empty(void)
 {
 }
 
+static void empty_done(int result)
+{
+}
+
 static void (*floppy_work_fn)(void);
 
 static void floppy_work_workfn(struct work_struct *work)
@@ -1998,14 +2001,14 @@ static const struct cont_t wakeup_cont = {
 	.interrupt	= empty,
 	.redo		= do_wakeup,
 	.error		= empty,
-	.done		= (done_f)empty
+	.done		= empty_done,
 };
 
 static const struct cont_t intr_cont = {
 	.interrupt	= empty,
 	.redo		= process_fd_request,
 	.error		= empty,
-	.done		= (done_f)empty
+	.done		= empty_done,
 };
 
 /* schedules handler, waiting for completion. May be interrupted, will then
@@ -4513,13 +4516,15 @@ static bool floppy_available(int drive)
 
 static int floppy_alloc_disk(unsigned int drive, unsigned int type)
 {
+	struct queue_limits lim = {
+		.max_hw_sectors = 64,
+	};
 	struct gendisk *disk;
 
-	disk = blk_mq_alloc_disk(&tag_sets[drive], NULL);
+	disk = blk_mq_alloc_disk(&tag_sets[drive], &lim, NULL);
 	if (IS_ERR(disk))
 		return PTR_ERR(disk);
 
-	blk_queue_max_hw_sectors(disk->queue, 64);
 	disk->major = FLOPPY_MAJOR;
 	disk->first_minor = TOMINOR(drive) | (type << 2);
 	disk->minors = 1;
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 146b32fa7b47..28a95fd366fe 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -165,39 +165,37 @@ static loff_t get_loop_size(struct loop_device *lo, struct file *file)
 	return get_size(lo->lo_offset, lo->lo_sizelimit, file);
 }
 
+/*
+ * We support direct I/O only if lo_offset is aligned with the logical I/O size
+ * of backing device, and the logical block size of loop is bigger than that of
+ * the backing device.
+ */
+static bool lo_bdev_can_use_dio(struct loop_device *lo,
+		struct block_device *backing_bdev)
+{
+	unsigned short sb_bsize = bdev_logical_block_size(backing_bdev);
+
+	if (queue_logical_block_size(lo->lo_queue) < sb_bsize)
+		return false;
+	if (lo->lo_offset & (sb_bsize - 1))
+		return false;
+	return true;
+}
+
 static void __loop_update_dio(struct loop_device *lo, bool dio)
 {
 	struct file *file = lo->lo_backing_file;
-	struct address_space *mapping = file->f_mapping;
-	struct inode *inode = mapping->host;
-	unsigned short sb_bsize = 0;
-	unsigned dio_align = 0;
+	struct inode *inode = file->f_mapping->host;
+	struct block_device *backing_bdev = NULL;
 	bool use_dio;
 
-	if (inode->i_sb->s_bdev) {
-		sb_bsize = bdev_logical_block_size(inode->i_sb->s_bdev);
-		dio_align = sb_bsize - 1;
-	}
+	if (S_ISBLK(inode->i_mode))
+		backing_bdev = I_BDEV(inode);
+	else if (inode->i_sb->s_bdev)
+		backing_bdev = inode->i_sb->s_bdev;
 
-	/*
-	 * We support direct I/O only if lo_offset is aligned with the
-	 * logical I/O size of backing device, and the logical block
-	 * size of loop is bigger than the backing device's.
-	 *
-	 * TODO: the above condition may be loosed in the future, and
-	 * direct I/O may be switched runtime at that time because most
-	 * of requests in sane applications should be PAGE_SIZE aligned
-	 */
-	if (dio) {
-		if (queue_logical_block_size(lo->lo_queue) >= sb_bsize &&
-		    !(lo->lo_offset & dio_align) &&
-		    (file->f_mode & FMODE_CAN_ODIRECT))
-			use_dio = true;
-		else
-			use_dio = false;
-	} else {
-		use_dio = false;
-	}
+	use_dio = dio && (file->f_mode & FMODE_CAN_ODIRECT) &&
+		(!backing_bdev || lo_bdev_can_use_dio(lo, backing_bdev));
 
 	if (lo->use_dio == use_dio)
 		return;
@@ -752,12 +750,13 @@ static void loop_sysfs_exit(struct loop_device *lo)
 				   &loop_attribute_group);
 }
 
-static void loop_config_discard(struct loop_device *lo)
+static void loop_config_discard(struct loop_device *lo,
+		struct queue_limits *lim)
 {
 	struct file *file = lo->lo_backing_file;
 	struct inode *inode = file->f_mapping->host;
-	struct request_queue *q = lo->lo_queue;
-	u32 granularity, max_discard_sectors;
+	u32 granularity = 0, max_discard_sectors = 0;
+	struct kstatfs sbuf;
 
 	/*
 	 * If the backing device is a block device, mirror its zeroing
@@ -777,29 +776,17 @@ static void loop_config_discard(struct loop_device *lo)
 	 * We use punch hole to reclaim the free space used by the
 	 * image a.k.a. discard.
 	 */
-	} else if (!file->f_op->fallocate) {
-		max_discard_sectors = 0;
-		granularity = 0;
-
-	} else {
-		struct kstatfs sbuf;
-
+	} else if (file->f_op->fallocate && !vfs_statfs(&file->f_path, &sbuf)) {
 		max_discard_sectors = UINT_MAX >> 9;
-		if (!vfs_statfs(&file->f_path, &sbuf))
-			granularity = sbuf.f_bsize;
-		else
-			max_discard_sectors = 0;
+		granularity = sbuf.f_bsize;
 	}
 
-	if (max_discard_sectors) {
-		q->limits.discard_granularity = granularity;
-		blk_queue_max_discard_sectors(q, max_discard_sectors);
-		blk_queue_max_write_zeroes_sectors(q, max_discard_sectors);
-	} else {
-		q->limits.discard_granularity = 0;
-		blk_queue_max_discard_sectors(q, 0);
-		blk_queue_max_write_zeroes_sectors(q, 0);
-	}
+	lim->max_hw_discard_sectors = max_discard_sectors;
+	lim->max_write_zeroes_sectors = max_discard_sectors;
+	if (max_discard_sectors)
+		lim->discard_granularity = granularity;
+	else
+		lim->discard_granularity = 0;
 }
 
 struct loop_worker {
@@ -988,6 +975,20 @@ loop_set_status_from_info(struct loop_device *lo,
 	return 0;
 }
 
+static int loop_reconfigure_limits(struct loop_device *lo, unsigned short bsize,
+		bool update_discard_settings)
+{
+	struct queue_limits lim;
+
+	lim = queue_limits_start_update(lo->lo_queue);
+	lim.logical_block_size = bsize;
+	lim.physical_block_size = bsize;
+	lim.io_min = bsize;
+	if (update_discard_settings)
+		loop_config_discard(lo, &lim);
+	return queue_limits_commit_update(lo->lo_queue, &lim);
+}
+
 static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 			  struct block_device *bdev,
 			  const struct loop_config *config)
@@ -1085,11 +1086,10 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 	else
 		bsize = 512;
 
-	blk_queue_logical_block_size(lo->lo_queue, bsize);
-	blk_queue_physical_block_size(lo->lo_queue, bsize);
-	blk_queue_io_min(lo->lo_queue, bsize);
+	error = loop_reconfigure_limits(lo, bsize, true);
+	if (WARN_ON_ONCE(error))
+		goto out_unlock;
 
-	loop_config_discard(lo);
 	loop_update_rotational(lo);
 	loop_update_dio(lo);
 	loop_sysfs_init(lo);
@@ -1156,9 +1156,7 @@ static void __loop_clr_fd(struct loop_device *lo, bool release)
 	lo->lo_offset = 0;
 	lo->lo_sizelimit = 0;
 	memset(lo->lo_file_name, 0, LO_NAME_SIZE);
-	blk_queue_logical_block_size(lo->lo_queue, 512);
-	blk_queue_physical_block_size(lo->lo_queue, 512);
-	blk_queue_io_min(lo->lo_queue, 512);
+	loop_reconfigure_limits(lo, 512, false);
 	invalidate_disk(lo->lo_disk);
 	loop_sysfs_exit(lo);
 	/* let user-space know about this change */
@@ -1490,9 +1488,7 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
 	invalidate_bdev(lo->lo_device);
 
 	blk_mq_freeze_queue(lo->lo_queue);
-	blk_queue_logical_block_size(lo->lo_queue, arg);
-	blk_queue_physical_block_size(lo->lo_queue, arg);
-	blk_queue_io_min(lo->lo_queue, arg);
+	err = loop_reconfigure_limits(lo, arg, false);
 	loop_update_dio(lo);
 	blk_mq_unfreeze_queue(lo->lo_queue);
 
@@ -1984,6 +1980,12 @@ static const struct blk_mq_ops loop_mq_ops = {
 
 static int loop_add(int i)
 {
+	struct queue_limits lim = {
+		/*
+		 * Random number picked from the historic block max_sectors cap.
+		 */
+		.max_hw_sectors		= 2560u,
+	};
 	struct loop_device *lo;
 	struct gendisk *disk;
 	int err;
@@ -2027,16 +2029,13 @@ static int loop_add(int i)
 	if (err)
 		goto out_free_idr;
 
-	disk = lo->lo_disk = blk_mq_alloc_disk(&lo->tag_set, lo);
+	disk = lo->lo_disk = blk_mq_alloc_disk(&lo->tag_set, &lim, lo);
 	if (IS_ERR(disk)) {
 		err = PTR_ERR(disk);
 		goto out_cleanup_tags;
 	}
 	lo->lo_queue = lo->lo_disk->queue;
 
-	/* random number picked from the history block max_sectors cap */
-	blk_queue_max_hw_sectors(lo->lo_queue, 2560u);
-
 	/*
 	 * By default, we do buffer IO, so it doesn't make sense to enable
 	 * merge because the I/O submitted to backing file is handled page by
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index b200950e8fb5..43a187609ef7 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -3401,6 +3401,12 @@ static const struct blk_mq_ops mtip_mq_ops = {
  */
 static int mtip_block_initialize(struct driver_data *dd)
 {
+	struct queue_limits lim = {
+		.physical_block_size	= 4096,
+		.max_hw_sectors		= 0xffff,
+		.max_segments		= MTIP_MAX_SG,
+		.max_segment_size	= 0x400000,
+	};
 	int rv = 0, wait_for_rebuild = 0;
 	sector_t capacity;
 	unsigned int index = 0;
@@ -3431,7 +3437,7 @@ static int mtip_block_initialize(struct driver_data *dd)
 		goto block_queue_alloc_tag_error;
 	}
 
-	dd->disk = blk_mq_alloc_disk(&dd->tags, dd);
+	dd->disk = blk_mq_alloc_disk(&dd->tags, &lim, dd);
 	if (IS_ERR(dd->disk)) {
 		dev_err(&dd->pdev->dev,
 			"Unable to allocate request queue\n");
@@ -3481,12 +3487,7 @@ skip_create_disk:
 	/* Set device limits. */
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, dd->queue);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, dd->queue);
-	blk_queue_max_segments(dd->queue, MTIP_MAX_SG);
-	blk_queue_physical_block_size(dd->queue, 4096);
-	blk_queue_max_hw_sectors(dd->queue, 0xffff);
-	blk_queue_max_segment_size(dd->queue, 0x400000);
 	dma_set_max_seg_size(&dd->pdev->dev, 0x400000);
-	blk_queue_io_min(dd->queue, 4096);
 
 	/* Set the capacity of the device in 512 byte sectors. */
 	if (!(mtip_hw_get_capacity(dd, &capacity))) {
diff --git a/drivers/block/n64cart.c b/drivers/block/n64cart.c
index d914156db2d8..27b2187e7a6d 100644
--- a/drivers/block/n64cart.c
+++ b/drivers/block/n64cart.c
@@ -114,6 +114,10 @@ static const struct block_device_operations n64cart_fops = {
  */
 static int __init n64cart_probe(struct platform_device *pdev)
 {
+	struct queue_limits lim = {
+		.physical_block_size	= 4096,
+		.logical_block_size	= 4096,
+	};
 	struct gendisk *disk;
 	int err = -ENOMEM;
 
@@ -131,9 +135,11 @@ static int __init n64cart_probe(struct platform_device *pdev)
 	if (IS_ERR(reg_base))
 		return PTR_ERR(reg_base);
 
-	disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!disk)
+	disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(disk)) {
+		err = PTR_ERR(disk);
 		goto out;
+	}
 
 	disk->first_minor = 0;
 	disk->flags = GENHD_FL_NO_PART;
@@ -145,8 +151,6 @@ static int __init n64cart_probe(struct platform_device *pdev)
 	set_disk_ro(disk, 1);
 
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
-	blk_queue_physical_block_size(disk->queue, 4096);
-	blk_queue_logical_block_size(disk->queue, 4096);
 
 	err = add_disk(disk);
 	if (err)
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 4e72ec4e25ac..9d4ec9273bf9 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -316,9 +316,12 @@ static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock,
 	nsock->sent = 0;
 }
 
-static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
+static int __nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
 		loff_t blksize)
 {
+	struct queue_limits lim;
+	int error;
+
 	if (!blksize)
 		blksize = 1u << NBD_DEF_BLKSIZE_BITS;
 
@@ -334,10 +337,16 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
 	if (!nbd->pid)
 		return 0;
 
+	lim = queue_limits_start_update(nbd->disk->queue);
 	if (nbd->config->flags & NBD_FLAG_SEND_TRIM)
-		blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX);
-	blk_queue_logical_block_size(nbd->disk->queue, blksize);
-	blk_queue_physical_block_size(nbd->disk->queue, blksize);
+		lim.max_hw_discard_sectors = UINT_MAX;
+	else
+		lim.max_hw_discard_sectors = 0;
+	lim.logical_block_size = blksize;
+	lim.physical_block_size = blksize;
+	error = queue_limits_commit_update(nbd->disk->queue, &lim);
+	if (error)
+		return error;
 
 	if (max_part)
 		set_bit(GD_NEED_PART_SCAN, &nbd->disk->state);
@@ -346,6 +355,18 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
 	return 0;
 }
 
+static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
+		loff_t blksize)
+{
+	int error;
+
+	blk_mq_freeze_queue(nbd->disk->queue);
+	error = __nbd_set_size(nbd, bytesize, blksize);
+	blk_mq_unfreeze_queue(nbd->disk->queue);
+
+	return error;
+}
+
 static void nbd_complete_rq(struct request *req)
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
@@ -508,7 +529,7 @@ static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send,
 		       struct iov_iter *iter, int msg_flags, int *sent)
 {
 	int result;
-	struct msghdr msg;
+	struct msghdr msg = {} ;
 	unsigned int noreclaim_flag;
 
 	if (unlikely(!sock)) {
@@ -524,10 +545,6 @@ static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send,
 	do {
 		sock->sk->sk_allocation = GFP_NOIO | __GFP_MEMALLOC;
 		sock->sk->sk_use_task_frag = false;
-		msg.msg_name = NULL;
-		msg.msg_namelen = 0;
-		msg.msg_control = NULL;
-		msg.msg_controllen = 0;
 		msg.msg_flags = msg_flags | MSG_NOSIGNAL;
 
 		if (send)
@@ -1355,7 +1372,6 @@ static void nbd_config_put(struct nbd_device *nbd)
 		nbd->config = NULL;
 
 		nbd->tag_set.timeout = 0;
-		blk_queue_max_discard_sectors(nbd->disk->queue, 0);
 
 		mutex_unlock(&nbd->config_lock);
 		nbd_put(nbd);
@@ -1787,6 +1803,12 @@ static const struct blk_mq_ops nbd_mq_ops = {
 
 static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
 {
+	struct queue_limits lim = {
+		.max_hw_sectors		= 65536,
+		.max_user_sectors	= 256,
+		.max_segments		= USHRT_MAX,
+		.max_segment_size	= UINT_MAX,
+	};
 	struct nbd_device *nbd;
 	struct gendisk *disk;
 	int err = -ENOMEM;
@@ -1827,7 +1849,7 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
 	if (err < 0)
 		goto out_free_tags;
 
-	disk = blk_mq_alloc_disk(&nbd->tag_set, NULL);
+	disk = blk_mq_alloc_disk(&nbd->tag_set, &lim, NULL);
 	if (IS_ERR(disk)) {
 		err = PTR_ERR(disk);
 		goto out_free_idr;
@@ -1847,11 +1869,6 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
 	 * Tell the block layer that we are not a rotational device
 	 */
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
-	blk_queue_max_discard_sectors(disk->queue, 0);
-	blk_queue_max_segment_size(disk->queue, UINT_MAX);
-	blk_queue_max_segments(disk->queue, USHRT_MAX);
-	blk_queue_max_hw_sectors(disk->queue, 65536);
-	disk->queue->limits.max_sectors = 256;
 
 	mutex_init(&nbd->config_lock);
 	refcount_set(&nbd->config_refs, 0);
@@ -2437,6 +2454,12 @@ static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	dev_list = nla_nest_start_noflag(reply, NBD_ATTR_DEVICE_LIST);
+	if (!dev_list) {
+		nlmsg_free(reply);
+		ret = -EMSGSIZE;
+		goto out;
+	}
+
 	if (index == -1) {
 		ret = idr_for_each(&nbd_index_idr, &status_cb, reply);
 		if (ret) {
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 9f7695f00c2d..71c39bcd872c 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -115,6 +115,18 @@ module_param_string(init_hctx, g_init_hctx_str, sizeof(g_init_hctx_str), 0444);
 MODULE_PARM_DESC(init_hctx, "Fault injection to fail hctx init. init_hctx=<interval>,<probability>,<space>,<times>");
 #endif
 
+/*
+ * Historic queue modes.
+ *
+ * These days nothing but NULL_Q_MQ is actually supported, but we keep it the
+ * enum for error reporting.
+ */
+enum {
+	NULL_Q_BIO	= 0,
+	NULL_Q_RQ	= 1,
+	NULL_Q_MQ	= 2,
+};
+
 static int g_queue_mode = NULL_Q_MQ;
 
 static int null_param_store_val(const char *str, int *val, int min, int max)
@@ -165,8 +177,8 @@ static bool g_blocking;
 module_param_named(blocking, g_blocking, bool, 0444);
 MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device");
 
-static bool shared_tags;
-module_param(shared_tags, bool, 0444);
+static bool g_shared_tags;
+module_param_named(shared_tags, g_shared_tags, bool, 0444);
 MODULE_PARM_DESC(shared_tags, "Share tag set between devices for blk-mq");
 
 static bool g_shared_tag_bitmap;
@@ -426,6 +438,7 @@ NULLB_DEVICE_ATTR(zone_max_open, uint, NULL);
 NULLB_DEVICE_ATTR(zone_max_active, uint, NULL);
 NULLB_DEVICE_ATTR(virt_boundary, bool, NULL);
 NULLB_DEVICE_ATTR(no_sched, bool, NULL);
+NULLB_DEVICE_ATTR(shared_tags, bool, NULL);
 NULLB_DEVICE_ATTR(shared_tag_bitmap, bool, NULL);
 
 static ssize_t nullb_device_power_show(struct config_item *item, char *page)
@@ -571,6 +584,7 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_zone_offline,
 	&nullb_device_attr_virt_boundary,
 	&nullb_device_attr_no_sched,
+	&nullb_device_attr_shared_tags,
 	&nullb_device_attr_shared_tag_bitmap,
 	NULL,
 };
@@ -653,10 +667,11 @@ static ssize_t memb_group_features_show(struct config_item *item, char *page)
 			"badblocks,blocking,blocksize,cache_size,"
 			"completion_nsec,discard,home_node,hw_queue_depth,"
 			"irqmode,max_sectors,mbps,memory_backed,no_sched,"
-			"poll_queues,power,queue_mode,shared_tag_bitmap,size,"
-			"submit_queues,use_per_node_hctx,virt_boundary,zoned,"
-			"zone_capacity,zone_max_active,zone_max_open,"
-			"zone_nr_conv,zone_offline,zone_readonly,zone_size\n");
+			"poll_queues,power,queue_mode,shared_tag_bitmap,"
+			"shared_tags,size,submit_queues,use_per_node_hctx,"
+			"virt_boundary,zoned,zone_capacity,zone_max_active,"
+			"zone_max_open,zone_nr_conv,zone_offline,zone_readonly,"
+			"zone_size\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);
@@ -738,6 +753,7 @@ static struct nullb_device *null_alloc_dev(void)
 	dev->zone_max_active = g_zone_max_active;
 	dev->virt_boundary = g_virt_boundary;
 	dev->no_sched = g_no_sched;
+	dev->shared_tags = g_shared_tags;
 	dev->shared_tag_bitmap = g_shared_tag_bitmap;
 	return dev;
 }
@@ -752,98 +768,11 @@ static void null_free_dev(struct nullb_device *dev)
 	kfree(dev);
 }
 
-static void put_tag(struct nullb_queue *nq, unsigned int tag)
-{
-	clear_bit_unlock(tag, nq->tag_map);
-
-	if (waitqueue_active(&nq->wait))
-		wake_up(&nq->wait);
-}
-
-static unsigned int get_tag(struct nullb_queue *nq)
-{
-	unsigned int tag;
-
-	do {
-		tag = find_first_zero_bit(nq->tag_map, nq->queue_depth);
-		if (tag >= nq->queue_depth)
-			return -1U;
-	} while (test_and_set_bit_lock(tag, nq->tag_map));
-
-	return tag;
-}
-
-static void free_cmd(struct nullb_cmd *cmd)
-{
-	put_tag(cmd->nq, cmd->tag);
-}
-
-static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer);
-
-static struct nullb_cmd *__alloc_cmd(struct nullb_queue *nq)
-{
-	struct nullb_cmd *cmd;
-	unsigned int tag;
-
-	tag = get_tag(nq);
-	if (tag != -1U) {
-		cmd = &nq->cmds[tag];
-		cmd->tag = tag;
-		cmd->error = BLK_STS_OK;
-		cmd->nq = nq;
-		if (nq->dev->irqmode == NULL_IRQ_TIMER) {
-			hrtimer_init(&cmd->timer, CLOCK_MONOTONIC,
-				     HRTIMER_MODE_REL);
-			cmd->timer.function = null_cmd_timer_expired;
-		}
-		return cmd;
-	}
-
-	return NULL;
-}
-
-static struct nullb_cmd *alloc_cmd(struct nullb_queue *nq, struct bio *bio)
-{
-	struct nullb_cmd *cmd;
-	DEFINE_WAIT(wait);
-
-	do {
-		/*
-		 * This avoids multiple return statements, multiple calls to
-		 * __alloc_cmd() and a fast path call to prepare_to_wait().
-		 */
-		cmd = __alloc_cmd(nq);
-		if (cmd) {
-			cmd->bio = bio;
-			return cmd;
-		}
-		prepare_to_wait(&nq->wait, &wait, TASK_UNINTERRUPTIBLE);
-		io_schedule();
-		finish_wait(&nq->wait, &wait);
-	} while (1);
-}
-
-static void end_cmd(struct nullb_cmd *cmd)
-{
-	int queue_mode = cmd->nq->dev->queue_mode;
-
-	switch (queue_mode)  {
-	case NULL_Q_MQ:
-		blk_mq_end_request(cmd->rq, cmd->error);
-		return;
-	case NULL_Q_BIO:
-		cmd->bio->bi_status = cmd->error;
-		bio_endio(cmd->bio);
-		break;
-	}
-
-	free_cmd(cmd);
-}
-
 static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer)
 {
-	end_cmd(container_of(timer, struct nullb_cmd, timer));
+	struct nullb_cmd *cmd = container_of(timer, struct nullb_cmd, timer);
 
+	blk_mq_end_request(blk_mq_rq_from_pdu(cmd), cmd->error);
 	return HRTIMER_NORESTART;
 }
 
@@ -856,7 +785,9 @@ static void null_cmd_end_timer(struct nullb_cmd *cmd)
 
 static void null_complete_rq(struct request *rq)
 {
-	end_cmd(blk_mq_rq_to_pdu(rq));
+	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq);
+
+	blk_mq_end_request(rq, cmd->error);
 }
 
 static struct nullb_page *null_alloc_page(void)
@@ -1273,7 +1204,7 @@ static int null_transfer(struct nullb *nullb, struct page *page,
 
 static int null_handle_rq(struct nullb_cmd *cmd)
 {
-	struct request *rq = cmd->rq;
+	struct request *rq = blk_mq_rq_from_pdu(cmd);
 	struct nullb *nullb = cmd->nq->dev->nullb;
 	int err;
 	unsigned int len;
@@ -1298,63 +1229,21 @@ static int null_handle_rq(struct nullb_cmd *cmd)
 	return 0;
 }
 
-static int null_handle_bio(struct nullb_cmd *cmd)
-{
-	struct bio *bio = cmd->bio;
-	struct nullb *nullb = cmd->nq->dev->nullb;
-	int err;
-	unsigned int len;
-	sector_t sector = bio->bi_iter.bi_sector;
-	struct bio_vec bvec;
-	struct bvec_iter iter;
-
-	spin_lock_irq(&nullb->lock);
-	bio_for_each_segment(bvec, bio, iter) {
-		len = bvec.bv_len;
-		err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset,
-				     op_is_write(bio_op(bio)), sector,
-				     bio->bi_opf & REQ_FUA);
-		if (err) {
-			spin_unlock_irq(&nullb->lock);
-			return err;
-		}
-		sector += len >> SECTOR_SHIFT;
-	}
-	spin_unlock_irq(&nullb->lock);
-	return 0;
-}
-
-static void null_stop_queue(struct nullb *nullb)
-{
-	struct request_queue *q = nullb->q;
-
-	if (nullb->dev->queue_mode == NULL_Q_MQ)
-		blk_mq_stop_hw_queues(q);
-}
-
-static void null_restart_queue_async(struct nullb *nullb)
-{
-	struct request_queue *q = nullb->q;
-
-	if (nullb->dev->queue_mode == NULL_Q_MQ)
-		blk_mq_start_stopped_hw_queues(q, true);
-}
-
 static inline blk_status_t null_handle_throttled(struct nullb_cmd *cmd)
 {
 	struct nullb_device *dev = cmd->nq->dev;
 	struct nullb *nullb = dev->nullb;
 	blk_status_t sts = BLK_STS_OK;
-	struct request *rq = cmd->rq;
+	struct request *rq = blk_mq_rq_from_pdu(cmd);
 
 	if (!hrtimer_active(&nullb->bw_timer))
 		hrtimer_restart(&nullb->bw_timer);
 
 	if (atomic_long_sub_return(blk_rq_bytes(rq), &nullb->cur_bytes) < 0) {
-		null_stop_queue(nullb);
+		blk_mq_stop_hw_queues(nullb->q);
 		/* race with timer */
 		if (atomic_long_read(&nullb->cur_bytes) > 0)
-			null_restart_queue_async(nullb);
+			blk_mq_start_stopped_hw_queues(nullb->q, true);
 		/* requeue request */
 		sts = BLK_STS_DEV_RESOURCE;
 	}
@@ -1381,37 +1270,29 @@ static inline blk_status_t null_handle_memory_backed(struct nullb_cmd *cmd,
 						     sector_t nr_sectors)
 {
 	struct nullb_device *dev = cmd->nq->dev;
-	int err;
 
 	if (op == REQ_OP_DISCARD)
 		return null_handle_discard(dev, sector, nr_sectors);
+	return errno_to_blk_status(null_handle_rq(cmd));
 
-	if (dev->queue_mode == NULL_Q_BIO)
-		err = null_handle_bio(cmd);
-	else
-		err = null_handle_rq(cmd);
-
-	return errno_to_blk_status(err);
 }
 
 static void nullb_zero_read_cmd_buffer(struct nullb_cmd *cmd)
 {
+	struct request *rq = blk_mq_rq_from_pdu(cmd);
 	struct nullb_device *dev = cmd->nq->dev;
 	struct bio *bio;
 
-	if (dev->memory_backed)
-		return;
-
-	if (dev->queue_mode == NULL_Q_BIO && bio_op(cmd->bio) == REQ_OP_READ) {
-		zero_fill_bio(cmd->bio);
-	} else if (req_op(cmd->rq) == REQ_OP_READ) {
-		__rq_for_each_bio(bio, cmd->rq)
+	if (!dev->memory_backed && req_op(rq) == REQ_OP_READ) {
+		__rq_for_each_bio(bio, rq)
 			zero_fill_bio(bio);
 	}
 }
 
 static inline void nullb_complete_cmd(struct nullb_cmd *cmd)
 {
+	struct request *rq = blk_mq_rq_from_pdu(cmd);
+
 	/*
 	 * Since root privileges are required to configure the null_blk
 	 * driver, it is fine that this driver does not initialize the
@@ -1425,20 +1306,10 @@ static inline void nullb_complete_cmd(struct nullb_cmd *cmd)
 	/* Complete IO by inline, softirq or timer */
 	switch (cmd->nq->dev->irqmode) {
 	case NULL_IRQ_SOFTIRQ:
-		switch (cmd->nq->dev->queue_mode) {
-		case NULL_Q_MQ:
-			blk_mq_complete_request(cmd->rq);
-			break;
-		case NULL_Q_BIO:
-			/*
-			 * XXX: no proper submitting cpu information available.
-			 */
-			end_cmd(cmd);
-			break;
-		}
+		blk_mq_complete_request(rq);
 		break;
 	case NULL_IRQ_NONE:
-		end_cmd(cmd);
+		blk_mq_end_request(rq, cmd->error);
 		break;
 	case NULL_IRQ_TIMER:
 		null_cmd_end_timer(cmd);
@@ -1499,7 +1370,7 @@ static enum hrtimer_restart nullb_bwtimer_fn(struct hrtimer *timer)
 		return HRTIMER_NORESTART;
 
 	atomic_long_set(&nullb->cur_bytes, mb_per_tick(mbps));
-	null_restart_queue_async(nullb);
+	blk_mq_start_stopped_hw_queues(nullb->q, true);
 
 	hrtimer_forward_now(&nullb->bw_timer, timer_interval);
 
@@ -1516,26 +1387,6 @@ static void nullb_setup_bwtimer(struct nullb *nullb)
 	hrtimer_start(&nullb->bw_timer, timer_interval, HRTIMER_MODE_REL);
 }
 
-static struct nullb_queue *nullb_to_queue(struct nullb *nullb)
-{
-	int index = 0;
-
-	if (nullb->nr_queues != 1)
-		index = raw_smp_processor_id() / ((nr_cpu_ids + nullb->nr_queues - 1) / nullb->nr_queues);
-
-	return &nullb->queues[index];
-}
-
-static void null_submit_bio(struct bio *bio)
-{
-	sector_t sector = bio->bi_iter.bi_sector;
-	sector_t nr_sectors = bio_sectors(bio);
-	struct nullb *nullb = bio->bi_bdev->bd_disk->private_data;
-	struct nullb_queue *nq = nullb_to_queue(nullb);
-
-	null_handle_cmd(alloc_cmd(nq, bio), sector, nr_sectors, bio_op(bio));
-}
-
 #ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
 
 static bool should_timeout_request(struct request *rq)
@@ -1655,7 +1506,7 @@ static int null_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 						blk_rq_sectors(req));
 		if (!blk_mq_add_to_batch(req, iob, (__force int) cmd->error,
 					blk_mq_end_request_batch))
-			end_cmd(cmd);
+			blk_mq_end_request(req, cmd->error);
 		nr++;
 	}
 
@@ -1711,7 +1562,6 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
 		hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 		cmd->timer.function = null_cmd_timer_expired;
 	}
-	cmd->rq = rq;
 	cmd->error = BLK_STS_OK;
 	cmd->nq = nq;
 	cmd->fake_timeout = should_timeout_request(rq) ||
@@ -1770,34 +1620,8 @@ static void null_queue_rqs(struct request **rqlist)
 	*rqlist = requeue_list;
 }
 
-static void cleanup_queue(struct nullb_queue *nq)
-{
-	bitmap_free(nq->tag_map);
-	kfree(nq->cmds);
-}
-
-static void cleanup_queues(struct nullb *nullb)
-{
-	int i;
-
-	for (i = 0; i < nullb->nr_queues; i++)
-		cleanup_queue(&nullb->queues[i]);
-
-	kfree(nullb->queues);
-}
-
-static void null_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
-{
-	struct nullb_queue *nq = hctx->driver_data;
-	struct nullb *nullb = nq->dev->nullb;
-
-	nullb->nr_queues--;
-}
-
 static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq)
 {
-	init_waitqueue_head(&nq->wait);
-	nq->queue_depth = nullb->queue_depth;
 	nq->dev = nullb->dev;
 	INIT_LIST_HEAD(&nq->poll_list);
 	spin_lock_init(&nq->poll_lock);
@@ -1815,7 +1639,6 @@ static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data,
 	nq = &nullb->queues[hctx_idx];
 	hctx->driver_data = nq;
 	null_init_queue(nullb, nq);
-	nullb->nr_queues++;
 
 	return 0;
 }
@@ -1828,7 +1651,6 @@ static const struct blk_mq_ops null_mq_ops = {
 	.poll		= null_poll,
 	.map_queues	= null_map_queues,
 	.init_hctx	= null_init_hctx,
-	.exit_hctx	= null_exit_hctx,
 };
 
 static void null_del_dev(struct nullb *nullb)
@@ -1840,7 +1662,7 @@ static void null_del_dev(struct nullb *nullb)
 
 	dev = nullb->dev;
 
-	ida_simple_remove(&nullb_indexes, nullb->index);
+	ida_free(&nullb_indexes, nullb->index);
 
 	list_del_init(&nullb->list);
 
@@ -1849,21 +1671,20 @@ static void null_del_dev(struct nullb *nullb)
 	if (test_bit(NULLB_DEV_FL_THROTTLED, &nullb->dev->flags)) {
 		hrtimer_cancel(&nullb->bw_timer);
 		atomic_long_set(&nullb->cur_bytes, LONG_MAX);
-		null_restart_queue_async(nullb);
+		blk_mq_start_stopped_hw_queues(nullb->q, true);
 	}
 
 	put_disk(nullb->disk);
-	if (dev->queue_mode == NULL_Q_MQ &&
-	    nullb->tag_set == &nullb->__tag_set)
+	if (nullb->tag_set == &nullb->__tag_set)
 		blk_mq_free_tag_set(nullb->tag_set);
-	cleanup_queues(nullb);
+	kfree(nullb->queues);
 	if (null_cache_active(nullb))
 		null_free_device_storage(nullb->dev, true);
 	kfree(nullb);
 	dev->nullb = NULL;
 }
 
-static void null_config_discard(struct nullb *nullb)
+static void null_config_discard(struct nullb *nullb, struct queue_limits *lim)
 {
 	if (nullb->dev->discard == false)
 		return;
@@ -1880,43 +1701,14 @@ static void null_config_discard(struct nullb *nullb)
 		return;
 	}
 
-	blk_queue_max_discard_sectors(nullb->q, UINT_MAX >> 9);
+	lim->max_hw_discard_sectors = UINT_MAX >> 9;
 }
 
-static const struct block_device_operations null_bio_ops = {
-	.owner		= THIS_MODULE,
-	.submit_bio	= null_submit_bio,
-	.report_zones	= null_report_zones,
-};
-
-static const struct block_device_operations null_rq_ops = {
+static const struct block_device_operations null_ops = {
 	.owner		= THIS_MODULE,
 	.report_zones	= null_report_zones,
 };
 
-static int setup_commands(struct nullb_queue *nq)
-{
-	struct nullb_cmd *cmd;
-	int i;
-
-	nq->cmds = kcalloc(nq->queue_depth, sizeof(*cmd), GFP_KERNEL);
-	if (!nq->cmds)
-		return -ENOMEM;
-
-	nq->tag_map = bitmap_zalloc(nq->queue_depth, GFP_KERNEL);
-	if (!nq->tag_map) {
-		kfree(nq->cmds);
-		return -ENOMEM;
-	}
-
-	for (i = 0; i < nq->queue_depth; i++) {
-		cmd = &nq->cmds[i];
-		cmd->tag = -1U;
-	}
-
-	return 0;
-}
-
 static int setup_queues(struct nullb *nullb)
 {
 	int nqueues = nr_cpu_ids;
@@ -1929,101 +1721,66 @@ static int setup_queues(struct nullb *nullb)
 	if (!nullb->queues)
 		return -ENOMEM;
 
-	nullb->queue_depth = nullb->dev->hw_queue_depth;
 	return 0;
 }
 
-static int init_driver_queues(struct nullb *nullb)
+static int null_init_tag_set(struct blk_mq_tag_set *set, int poll_queues)
 {
-	struct nullb_queue *nq;
-	int i, ret = 0;
-
-	for (i = 0; i < nullb->dev->submit_queues; i++) {
-		nq = &nullb->queues[i];
-
-		null_init_queue(nullb, nq);
-
-		ret = setup_commands(nq);
-		if (ret)
-			return ret;
-		nullb->nr_queues++;
+	set->ops = &null_mq_ops;
+	set->cmd_size = sizeof(struct nullb_cmd);
+	set->timeout = 5 * HZ;
+	set->nr_maps = 1;
+	if (poll_queues) {
+		set->nr_hw_queues += poll_queues;
+		set->nr_maps += 2;
 	}
-	return 0;
+	return blk_mq_alloc_tag_set(set);
 }
 
-static int null_gendisk_register(struct nullb *nullb)
+static int null_init_global_tag_set(void)
 {
-	sector_t size = ((sector_t)nullb->dev->size * SZ_1M) >> SECTOR_SHIFT;
-	struct gendisk *disk = nullb->disk;
+	int error;
 
-	set_capacity(disk, size);
-
-	disk->major		= null_major;
-	disk->first_minor	= nullb->index;
-	disk->minors		= 1;
-	if (queue_is_mq(nullb->q))
-		disk->fops		= &null_rq_ops;
-	else
-		disk->fops		= &null_bio_ops;
-	disk->private_data	= nullb;
-	strscpy_pad(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
+	if (tag_set.ops)
+		return 0;
 
-	if (nullb->dev->zoned) {
-		int ret = null_register_zoned_dev(nullb);
+	tag_set.nr_hw_queues = g_submit_queues;
+	tag_set.queue_depth = g_hw_queue_depth;
+	tag_set.numa_node = g_home_node;
+	tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	if (g_no_sched)
+		tag_set.flags |= BLK_MQ_F_NO_SCHED;
+	if (g_shared_tag_bitmap)
+		tag_set.flags |= BLK_MQ_F_TAG_HCTX_SHARED;
+	if (g_blocking)
+		tag_set.flags |= BLK_MQ_F_BLOCKING;
 
-		if (ret)
-			return ret;
-	}
-
-	return add_disk(disk);
+	error = null_init_tag_set(&tag_set, g_poll_queues);
+	if (error)
+		tag_set.ops = NULL;
+	return error;
 }
 
-static int null_init_tag_set(struct nullb *nullb, struct blk_mq_tag_set *set)
+static int null_setup_tagset(struct nullb *nullb)
 {
-	unsigned int flags = BLK_MQ_F_SHOULD_MERGE;
-	int hw_queues, numa_node;
-	unsigned int queue_depth;
-	int poll_queues;
-
-	if (nullb) {
-		hw_queues = nullb->dev->submit_queues;
-		poll_queues = nullb->dev->poll_queues;
-		queue_depth = nullb->dev->hw_queue_depth;
-		numa_node = nullb->dev->home_node;
-		if (nullb->dev->no_sched)
-			flags |= BLK_MQ_F_NO_SCHED;
-		if (nullb->dev->shared_tag_bitmap)
-			flags |= BLK_MQ_F_TAG_HCTX_SHARED;
-		if (nullb->dev->blocking)
-			flags |= BLK_MQ_F_BLOCKING;
-	} else {
-		hw_queues = g_submit_queues;
-		poll_queues = g_poll_queues;
-		queue_depth = g_hw_queue_depth;
-		numa_node = g_home_node;
-		if (g_no_sched)
-			flags |= BLK_MQ_F_NO_SCHED;
-		if (g_shared_tag_bitmap)
-			flags |= BLK_MQ_F_TAG_HCTX_SHARED;
-		if (g_blocking)
-			flags |= BLK_MQ_F_BLOCKING;
-	}
-
-	set->ops = &null_mq_ops;
-	set->cmd_size	= sizeof(struct nullb_cmd);
-	set->flags = flags;
-	set->driver_data = nullb;
-	set->nr_hw_queues = hw_queues;
-	set->queue_depth = queue_depth;
-	set->numa_node = numa_node;
-	if (poll_queues) {
-		set->nr_hw_queues += poll_queues;
-		set->nr_maps = 3;
-	} else {
-		set->nr_maps = 1;
+	if (nullb->dev->shared_tags) {
+		nullb->tag_set = &tag_set;
+		return null_init_global_tag_set();
 	}
 
-	return blk_mq_alloc_tag_set(set);
+	nullb->tag_set = &nullb->__tag_set;
+	nullb->tag_set->driver_data = nullb;
+	nullb->tag_set->nr_hw_queues = nullb->dev->submit_queues;
+	nullb->tag_set->queue_depth = nullb->dev->hw_queue_depth;
+	nullb->tag_set->numa_node = nullb->dev->home_node;
+	nullb->tag_set->flags = BLK_MQ_F_SHOULD_MERGE;
+	if (nullb->dev->no_sched)
+		nullb->tag_set->flags |= BLK_MQ_F_NO_SCHED;
+	if (nullb->dev->shared_tag_bitmap)
+		nullb->tag_set->flags |= BLK_MQ_F_TAG_HCTX_SHARED;
+	if (nullb->dev->blocking)
+		nullb->tag_set->flags |= BLK_MQ_F_BLOCKING;
+	return null_init_tag_set(nullb->tag_set, nullb->dev->poll_queues);
 }
 
 static int null_validate_conf(struct nullb_device *dev)
@@ -2032,11 +1789,15 @@ static int null_validate_conf(struct nullb_device *dev)
 		pr_err("legacy IO path is no longer available\n");
 		return -EINVAL;
 	}
+	if (dev->queue_mode == NULL_Q_BIO) {
+		pr_err("BIO-based IO path is no longer available, using blk-mq instead.\n");
+		dev->queue_mode = NULL_Q_MQ;
+	}
 
 	dev->blocksize = round_down(dev->blocksize, 512);
 	dev->blocksize = clamp_t(unsigned int, dev->blocksize, 512, 4096);
 
-	if (dev->queue_mode == NULL_Q_MQ && dev->use_per_node_hctx) {
+	if (dev->use_per_node_hctx) {
 		if (dev->submit_queues != nr_online_nodes)
 			dev->submit_queues = nr_online_nodes;
 	} else if (dev->submit_queues > nr_cpu_ids)
@@ -2048,8 +1809,6 @@ static int null_validate_conf(struct nullb_device *dev)
 	if (dev->poll_queues > g_poll_queues)
 		dev->poll_queues = g_poll_queues;
 	dev->prev_poll_queues = dev->poll_queues;
-
-	dev->queue_mode = min_t(unsigned int, dev->queue_mode, NULL_Q_MQ);
 	dev->irqmode = min_t(unsigned int, dev->irqmode, NULL_IRQ_TIMER);
 
 	/* Do memory allocation, so set blocking */
@@ -2060,9 +1819,6 @@ static int null_validate_conf(struct nullb_device *dev)
 	dev->cache_size = min_t(unsigned long, ULONG_MAX / 1024 / 1024,
 						dev->cache_size);
 	dev->mbps = min_t(unsigned int, 1024 * 40, dev->mbps);
-	/* can not stop a queue */
-	if (dev->queue_mode == NULL_Q_BIO)
-		dev->mbps = 0;
 
 	if (dev->zoned &&
 	    (!dev->zone_size || !is_power_of_2(dev->zone_size))) {
@@ -2102,6 +1858,12 @@ static bool null_setup_fault(void)
 
 static int null_add_dev(struct nullb_device *dev)
 {
+	struct queue_limits lim = {
+		.logical_block_size	= dev->blocksize,
+		.physical_block_size	= dev->blocksize,
+		.max_hw_sectors		= dev->max_sectors,
+	};
+
 	struct nullb *nullb;
 	int rv;
 
@@ -2123,36 +1885,25 @@ static int null_add_dev(struct nullb_device *dev)
 	if (rv)
 		goto out_free_nullb;
 
-	if (dev->queue_mode == NULL_Q_MQ) {
-		if (shared_tags) {
-			nullb->tag_set = &tag_set;
-			rv = 0;
-		} else {
-			nullb->tag_set = &nullb->__tag_set;
-			rv = null_init_tag_set(nullb, nullb->tag_set);
-		}
+	rv = null_setup_tagset(nullb);
+	if (rv)
+		goto out_cleanup_queues;
 
+	if (dev->virt_boundary)
+		lim.virt_boundary_mask = PAGE_SIZE - 1;
+	null_config_discard(nullb, &lim);
+	if (dev->zoned) {
+		rv = null_init_zoned_dev(dev, &lim);
 		if (rv)
-			goto out_cleanup_queues;
-
-		nullb->tag_set->timeout = 5 * HZ;
-		nullb->disk = blk_mq_alloc_disk(nullb->tag_set, nullb);
-		if (IS_ERR(nullb->disk)) {
-			rv = PTR_ERR(nullb->disk);
 			goto out_cleanup_tags;
-		}
-		nullb->q = nullb->disk->queue;
-	} else if (dev->queue_mode == NULL_Q_BIO) {
-		rv = -ENOMEM;
-		nullb->disk = blk_alloc_disk(nullb->dev->home_node);
-		if (!nullb->disk)
-			goto out_cleanup_queues;
+	}
 
-		nullb->q = nullb->disk->queue;
-		rv = init_driver_queues(nullb);
-		if (rv)
-			goto out_cleanup_disk;
+	nullb->disk = blk_mq_alloc_disk(nullb->tag_set, &lim, nullb);
+	if (IS_ERR(nullb->disk)) {
+		rv = PTR_ERR(nullb->disk);
+		goto out_cleanup_zone;
 	}
+	nullb->q = nullb->disk->queue;
 
 	if (dev->mbps) {
 		set_bit(NULLB_DEV_FL_THROTTLED, &dev->flags);
@@ -2164,35 +1915,19 @@ static int null_add_dev(struct nullb_device *dev)
 		blk_queue_write_cache(nullb->q, true, true);
 	}
 
-	if (dev->zoned) {
-		rv = null_init_zoned_dev(dev, nullb->q);
-		if (rv)
-			goto out_cleanup_disk;
-	}
-
 	nullb->q->queuedata = nullb;
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q);
 
 	mutex_lock(&lock);
-	rv = ida_simple_get(&nullb_indexes, 0, 0, GFP_KERNEL);
+	rv = ida_alloc(&nullb_indexes, GFP_KERNEL);
 	if (rv < 0) {
 		mutex_unlock(&lock);
-		goto out_cleanup_zone;
+		goto out_cleanup_disk;
 	}
 	nullb->index = rv;
 	dev->index = rv;
 	mutex_unlock(&lock);
 
-	blk_queue_logical_block_size(nullb->q, dev->blocksize);
-	blk_queue_physical_block_size(nullb->q, dev->blocksize);
-	if (dev->max_sectors)
-		blk_queue_max_hw_sectors(nullb->q, dev->max_sectors);
-
-	if (dev->virt_boundary)
-		blk_queue_virt_boundary(nullb->q, PAGE_SIZE - 1);
-
-	null_config_discard(nullb);
-
 	if (config_item_name(&dev->group.cg_item)) {
 		/* Use configfs dir name as the device name */
 		snprintf(nullb->disk_name, sizeof(nullb->disk_name),
@@ -2201,7 +1936,22 @@ static int null_add_dev(struct nullb_device *dev)
 		sprintf(nullb->disk_name, "nullb%d", nullb->index);
 	}
 
-	rv = null_gendisk_register(nullb);
+	set_capacity(nullb->disk,
+		((sector_t)nullb->dev->size * SZ_1M) >> SECTOR_SHIFT);
+	nullb->disk->major = null_major;
+	nullb->disk->first_minor = nullb->index;
+	nullb->disk->minors = 1;
+	nullb->disk->fops = &null_ops;
+	nullb->disk->private_data = nullb;
+	strscpy_pad(nullb->disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
+
+	if (nullb->dev->zoned) {
+		rv = null_register_zoned_dev(nullb);
+		if (rv)
+			goto out_ida_free;
+	}
+
+	rv = add_disk(nullb->disk);
 	if (rv)
 		goto out_ida_free;
 
@@ -2220,10 +1970,10 @@ out_cleanup_zone:
 out_cleanup_disk:
 	put_disk(nullb->disk);
 out_cleanup_tags:
-	if (dev->queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set)
+	if (nullb->tag_set == &nullb->__tag_set)
 		blk_mq_free_tag_set(nullb->tag_set);
 out_cleanup_queues:
-	cleanup_queues(nullb);
+	kfree(nullb->queues);
 out_free_nullb:
 	kfree(nullb);
 	dev->nullb = NULL;
@@ -2299,7 +2049,7 @@ static int __init null_init(void)
 		return -EINVAL;
 	}
 
-	if (g_queue_mode == NULL_Q_MQ && g_use_per_node_hctx) {
+	if (g_use_per_node_hctx) {
 		if (g_submit_queues != nr_online_nodes) {
 			pr_warn("submit_queues param is set to %u.\n",
 				nr_online_nodes);
@@ -2311,18 +2061,12 @@ static int __init null_init(void)
 		g_submit_queues = 1;
 	}
 
-	if (g_queue_mode == NULL_Q_MQ && shared_tags) {
-		ret = null_init_tag_set(NULL, &tag_set);
-		if (ret)
-			return ret;
-	}
-
 	config_group_init(&nullb_subsys.su_group);
 	mutex_init(&nullb_subsys.su_mutex);
 
 	ret = configfs_register_subsystem(&nullb_subsys);
 	if (ret)
-		goto err_tagset;
+		return ret;
 
 	mutex_init(&lock);
 
@@ -2349,9 +2093,6 @@ err_dev:
 	unregister_blkdev(null_major, "nullb");
 err_conf:
 	configfs_unregister_subsystem(&nullb_subsys);
-err_tagset:
-	if (g_queue_mode == NULL_Q_MQ && shared_tags)
-		blk_mq_free_tag_set(&tag_set);
 	return ret;
 }
 
@@ -2370,7 +2111,7 @@ static void __exit null_exit(void)
 	}
 	mutex_unlock(&lock);
 
-	if (g_queue_mode == NULL_Q_MQ && shared_tags)
+	if (tag_set.ops)
 		blk_mq_free_tag_set(&tag_set);
 }
 
diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h
index 929f659dd255..477b97746823 100644
--- a/drivers/block/null_blk/null_blk.h
+++ b/drivers/block/null_blk/null_blk.h
@@ -16,11 +16,6 @@
 #include <linux/mutex.h>
 
 struct nullb_cmd {
-	union {
-		struct request *rq;
-		struct bio *bio;
-	};
-	unsigned int tag;
 	blk_status_t error;
 	bool fake_timeout;
 	struct nullb_queue *nq;
@@ -28,16 +23,11 @@ struct nullb_cmd {
 };
 
 struct nullb_queue {
-	unsigned long *tag_map;
-	wait_queue_head_t wait;
-	unsigned int queue_depth;
 	struct nullb_device *dev;
 	unsigned int requeue_selection;
 
 	struct list_head poll_list;
 	spinlock_t poll_lock;
-
-	struct nullb_cmd *cmds;
 };
 
 struct nullb_zone {
@@ -60,13 +50,6 @@ struct nullb_zone {
 	unsigned int capacity;
 };
 
-/* Queue modes */
-enum {
-	NULL_Q_BIO	= 0,
-	NULL_Q_RQ	= 1,
-	NULL_Q_MQ	= 2,
-};
-
 struct nullb_device {
 	struct nullb *nullb;
 	struct config_group group;
@@ -119,6 +102,7 @@ struct nullb_device {
 	bool zoned; /* if device is zoned */
 	bool virt_boundary; /* virtual boundary on/off for the device */
 	bool no_sched; /* no IO scheduler for the device */
+	bool shared_tags; /* share tag set between devices for blk-mq */
 	bool shared_tag_bitmap; /* use hostwide shared tags */
 };
 
@@ -130,14 +114,12 @@ struct nullb {
 	struct gendisk *disk;
 	struct blk_mq_tag_set *tag_set;
 	struct blk_mq_tag_set __tag_set;
-	unsigned int queue_depth;
 	atomic_long_t cur_bytes;
 	struct hrtimer bw_timer;
 	unsigned long cache_flush_pos;
 	spinlock_t lock;
 
 	struct nullb_queue *queues;
-	unsigned int nr_queues;
 	char disk_name[DISK_NAME_LEN];
 };
 
@@ -147,7 +129,7 @@ blk_status_t null_process_cmd(struct nullb_cmd *cmd, enum req_op op,
 			      sector_t sector, unsigned int nr_sectors);
 
 #ifdef CONFIG_BLK_DEV_ZONED
-int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q);
+int null_init_zoned_dev(struct nullb_device *dev, struct queue_limits *lim);
 int null_register_zoned_dev(struct nullb *nullb);
 void null_free_zoned_dev(struct nullb_device *dev);
 int null_report_zones(struct gendisk *disk, sector_t sector,
@@ -160,7 +142,7 @@ ssize_t zone_cond_store(struct nullb_device *dev, const char *page,
 			size_t count, enum blk_zone_cond cond);
 #else
 static inline int null_init_zoned_dev(struct nullb_device *dev,
-				      struct request_queue *q)
+		struct queue_limits *lim)
 {
 	pr_err("CONFIG_BLK_DEV_ZONED not enabled\n");
 	return -EINVAL;
diff --git a/drivers/block/null_blk/trace.h b/drivers/block/null_blk/trace.h
index 6b2b370e786f..ef2d05d5f0df 100644
--- a/drivers/block/null_blk/trace.h
+++ b/drivers/block/null_blk/trace.h
@@ -41,10 +41,11 @@ TRACE_EVENT(nullb_zone_op,
 		__field(unsigned int, zone_cond)
 	    ),
 	    TP_fast_assign(
-		__entry->op = req_op(cmd->rq);
+		__entry->op = req_op(blk_mq_rq_from_pdu(cmd));
 		__entry->zone_no = zone_no;
 		__entry->zone_cond = zone_cond;
-		__assign_disk_name(__entry->disk, cmd->rq->q->disk);
+		__assign_disk_name(__entry->disk,
+			blk_mq_rq_from_pdu(cmd)->q->disk);
 	    ),
 	    TP_printk("%s req=%-15s zone_no=%u zone_cond=%-10s",
 		      __print_disk_name(__entry->disk),
diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c
index 6f5e0994862e..1689e2584104 100644
--- a/drivers/block/null_blk/zoned.c
+++ b/drivers/block/null_blk/zoned.c
@@ -58,7 +58,8 @@ static inline void null_unlock_zone(struct nullb_device *dev,
 		mutex_unlock(&zone->mutex);
 }
 
-int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
+int null_init_zoned_dev(struct nullb_device *dev,
+			struct queue_limits *lim)
 {
 	sector_t dev_capacity_sects, zone_capacity_sects;
 	struct nullb_zone *zone;
@@ -151,27 +152,22 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
 		sector += dev->zone_size_sects;
 	}
 
+	lim->zoned = true;
+	lim->chunk_sectors = dev->zone_size_sects;
+	lim->max_zone_append_sectors = dev->zone_size_sects;
+	lim->max_open_zones = dev->zone_max_open;
+	lim->max_active_zones = dev->zone_max_active;
 	return 0;
 }
 
 int null_register_zoned_dev(struct nullb *nullb)
 {
-	struct nullb_device *dev = nullb->dev;
 	struct request_queue *q = nullb->q;
 
-	disk_set_zoned(nullb->disk);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 	blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);
-	blk_queue_chunk_sectors(q, dev->zone_size_sects);
 	nullb->disk->nr_zones = bdev_nr_zones(nullb->disk->part0);
-	blk_queue_max_zone_append_sectors(q, dev->zone_size_sects);
-	disk_set_max_open_zones(nullb->disk, dev->zone_max_open);
-	disk_set_max_active_zones(nullb->disk, dev->zone_max_active);
-
-	if (queue_is_mq(q))
-		return blk_revalidate_disk_zones(nullb->disk, NULL);
-
-	return 0;
+	return blk_revalidate_disk_zones(nullb->disk, NULL);
 }
 
 void null_free_zoned_dev(struct nullb_device *dev)
@@ -394,10 +390,7 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 	 */
 	if (append) {
 		sector = zone->wp;
-		if (dev->queue_mode == NULL_Q_MQ)
-			cmd->rq->__sector = sector;
-		else
-			cmd->bio->bi_iter.bi_sector = sector;
+		blk_mq_rq_from_pdu(cmd)->__sector = sector;
 	} else if (sector != zone->wp) {
 		ret = BLK_STS_IOERR;
 		goto unlock;
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index d56d972aadb3..21728e9ea5c3 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -340,8 +340,8 @@ static ssize_t device_map_show(const struct class *c, const struct class_attribu
 		n += sysfs_emit_at(data, n, "%s %u:%u %u:%u\n",
 			pd->disk->disk_name,
 			MAJOR(pd->pkt_dev), MINOR(pd->pkt_dev),
-			MAJOR(pd->bdev_handle->bdev->bd_dev),
-			MINOR(pd->bdev_handle->bdev->bd_dev));
+			MAJOR(file_bdev(pd->bdev_file)->bd_dev),
+			MINOR(file_bdev(pd->bdev_file)->bd_dev));
 	}
 	mutex_unlock(&ctl_mutex);
 	return n;
@@ -438,7 +438,7 @@ static int pkt_seq_show(struct seq_file *m, void *p)
 	int states[PACKET_NUM_STATES];
 
 	seq_printf(m, "Writer %s mapped to %pg:\n", pd->disk->disk_name,
-		   pd->bdev_handle->bdev);
+		   file_bdev(pd->bdev_file));
 
 	seq_printf(m, "\nSettings:\n");
 	seq_printf(m, "\tpacket size:\t\t%dkB\n", pd->settings.size / 2);
@@ -715,7 +715,7 @@ static void pkt_rbtree_insert(struct pktcdvd_device *pd, struct pkt_rb_node *nod
  */
 static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *cgc)
 {
-	struct request_queue *q = bdev_get_queue(pd->bdev_handle->bdev);
+	struct request_queue *q = bdev_get_queue(file_bdev(pd->bdev_file));
 	struct scsi_cmnd *scmd;
 	struct request *rq;
 	int ret = 0;
@@ -828,6 +828,12 @@ static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd,
  */
 static void pkt_queue_bio(struct pktcdvd_device *pd, struct bio *bio)
 {
+	/*
+	 * Some CDRW drives can not handle writes larger than one packet,
+	 * even if the size is a multiple of the packet size.
+	 */
+	bio->bi_opf |= REQ_NOMERGE;
+
 	spin_lock(&pd->iosched.lock);
 	if (bio_data_dir(bio) == READ)
 		bio_list_add(&pd->iosched.read_queue, bio);
@@ -1048,7 +1054,7 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt)
 			continue;
 
 		bio = pkt->r_bios[f];
-		bio_init(bio, pd->bdev_handle->bdev, bio->bi_inline_vecs, 1,
+		bio_init(bio, file_bdev(pd->bdev_file), bio->bi_inline_vecs, 1,
 			 REQ_OP_READ);
 		bio->bi_iter.bi_sector = pkt->sector + f * (CD_FRAMESIZE >> 9);
 		bio->bi_end_io = pkt_end_io_read;
@@ -1264,7 +1270,7 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt)
 	struct device *ddev = disk_to_dev(pd->disk);
 	int f;
 
-	bio_init(pkt->w_bio, pd->bdev_handle->bdev, pkt->w_bio->bi_inline_vecs,
+	bio_init(pkt->w_bio, file_bdev(pd->bdev_file), pkt->w_bio->bi_inline_vecs,
 		 pkt->frames, REQ_OP_WRITE);
 	pkt->w_bio->bi_iter.bi_sector = pkt->sector;
 	pkt->w_bio->bi_end_io = pkt_end_io_packet_write;
@@ -2162,20 +2168,20 @@ static int pkt_open_dev(struct pktcdvd_device *pd, bool write)
 	int ret;
 	long lba;
 	struct request_queue *q;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 
 	/*
 	 * We need to re-open the cdrom device without O_NONBLOCK to be able
 	 * to read/write from/to it. It is already opened in O_NONBLOCK mode
 	 * so open should not fail.
 	 */
-	bdev_handle = bdev_open_by_dev(pd->bdev_handle->bdev->bd_dev,
+	bdev_file = bdev_file_open_by_dev(file_bdev(pd->bdev_file)->bd_dev,
 				       BLK_OPEN_READ, pd, NULL);
-	if (IS_ERR(bdev_handle)) {
-		ret = PTR_ERR(bdev_handle);
+	if (IS_ERR(bdev_file)) {
+		ret = PTR_ERR(bdev_file);
 		goto out;
 	}
-	pd->open_bdev_handle = bdev_handle;
+	pd->f_open_bdev = bdev_file;
 
 	ret = pkt_get_last_written(pd, &lba);
 	if (ret) {
@@ -2184,18 +2190,13 @@ static int pkt_open_dev(struct pktcdvd_device *pd, bool write)
 	}
 
 	set_capacity(pd->disk, lba << 2);
-	set_capacity_and_notify(pd->bdev_handle->bdev->bd_disk, lba << 2);
+	set_capacity_and_notify(file_bdev(pd->bdev_file)->bd_disk, lba << 2);
 
-	q = bdev_get_queue(pd->bdev_handle->bdev);
+	q = bdev_get_queue(file_bdev(pd->bdev_file));
 	if (write) {
 		ret = pkt_open_write(pd);
 		if (ret)
 			goto out_putdev;
-		/*
-		 * Some CDRW drives can not handle writes larger than one packet,
-		 * even if the size is a multiple of the packet size.
-		 */
-		blk_queue_max_hw_sectors(q, pd->settings.size);
 		set_bit(PACKET_WRITABLE, &pd->flags);
 	} else {
 		pkt_set_speed(pd, MAX_SPEED, MAX_SPEED);
@@ -2218,7 +2219,7 @@ static int pkt_open_dev(struct pktcdvd_device *pd, bool write)
 	return 0;
 
 out_putdev:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 out:
 	return ret;
 }
@@ -2237,8 +2238,8 @@ static void pkt_release_dev(struct pktcdvd_device *pd, int flush)
 	pkt_lock_door(pd, 0);
 
 	pkt_set_speed(pd, MAX_SPEED, MAX_SPEED);
-	bdev_release(pd->open_bdev_handle);
-	pd->open_bdev_handle = NULL;
+	fput(pd->f_open_bdev);
+	pd->f_open_bdev = NULL;
 
 	pkt_shrink_pktlist(pd);
 }
@@ -2326,7 +2327,7 @@ static void pkt_end_io_read_cloned(struct bio *bio)
 
 static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio)
 {
-	struct bio *cloned_bio = bio_alloc_clone(pd->bdev_handle->bdev, bio,
+	struct bio *cloned_bio = bio_alloc_clone(file_bdev(pd->bdev_file), bio,
 		GFP_NOIO, &pkt_bio_set);
 	struct packet_stacked_data *psd = mempool_alloc(&psd_pool, GFP_NOIO);
 
@@ -2338,9 +2339,9 @@ static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio)
 	pkt_queue_bio(pd, cloned_bio);
 }
 
-static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
+static void pkt_make_request_write(struct bio *bio)
 {
-	struct pktcdvd_device *pd = q->queuedata;
+	struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->private_data;
 	sector_t zone;
 	struct packet_data *pkt;
 	int was_empty, blocked_bio;
@@ -2432,7 +2433,7 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
 
 static void pkt_submit_bio(struct bio *bio)
 {
-	struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->queue->queuedata;
+	struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->private_data;
 	struct device *ddev = disk_to_dev(pd->disk);
 	struct bio *split;
 
@@ -2476,7 +2477,7 @@ static void pkt_submit_bio(struct bio *bio)
 			split = bio;
 		}
 
-		pkt_make_request_write(bio->bi_bdev->bd_disk->queue, split);
+		pkt_make_request_write(split);
 	} while (split != bio);
 
 	return;
@@ -2484,20 +2485,11 @@ end_io:
 	bio_io_error(bio);
 }
 
-static void pkt_init_queue(struct pktcdvd_device *pd)
-{
-	struct request_queue *q = pd->disk->queue;
-
-	blk_queue_logical_block_size(q, CD_FRAMESIZE);
-	blk_queue_max_hw_sectors(q, PACKET_MAX_SECTORS);
-	q->queuedata = pd;
-}
-
 static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 {
 	struct device *ddev = disk_to_dev(pd->disk);
 	int i;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct scsi_device *sdev;
 
 	if (pd->pkt_dev == dev) {
@@ -2508,9 +2500,9 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 		struct pktcdvd_device *pd2 = pkt_devs[i];
 		if (!pd2)
 			continue;
-		if (pd2->bdev_handle->bdev->bd_dev == dev) {
+		if (file_bdev(pd2->bdev_file)->bd_dev == dev) {
 			dev_err(ddev, "%pg already setup\n",
-				pd2->bdev_handle->bdev);
+				file_bdev(pd2->bdev_file));
 			return -EBUSY;
 		}
 		if (pd2->pkt_dev == dev) {
@@ -2519,13 +2511,13 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 		}
 	}
 
-	bdev_handle = bdev_open_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_NDELAY,
+	bdev_file = bdev_file_open_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_NDELAY,
 				       NULL, NULL);
-	if (IS_ERR(bdev_handle))
-		return PTR_ERR(bdev_handle);
-	sdev = scsi_device_from_queue(bdev_handle->bdev->bd_disk->queue);
+	if (IS_ERR(bdev_file))
+		return PTR_ERR(bdev_file);
+	sdev = scsi_device_from_queue(file_bdev(bdev_file)->bd_disk->queue);
 	if (!sdev) {
-		bdev_release(bdev_handle);
+		fput(bdev_file);
 		return -EINVAL;
 	}
 	put_device(&sdev->sdev_gendev);
@@ -2533,10 +2525,8 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 	/* This is safe, since we have a reference from open(). */
 	__module_get(THIS_MODULE);
 
-	pd->bdev_handle = bdev_handle;
-	set_blocksize(bdev_handle->bdev, CD_FRAMESIZE);
-
-	pkt_init_queue(pd);
+	pd->bdev_file = bdev_file;
+	set_blocksize(file_bdev(bdev_file), CD_FRAMESIZE);
 
 	atomic_set(&pd->cdrw.pending_bios, 0);
 	pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->disk->disk_name);
@@ -2546,11 +2536,11 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 	}
 
 	proc_create_single_data(pd->disk->disk_name, 0, pkt_proc, pkt_seq_show, pd);
-	dev_notice(ddev, "writer mapped to %pg\n", bdev_handle->bdev);
+	dev_notice(ddev, "writer mapped to %pg\n", file_bdev(bdev_file));
 	return 0;
 
 out_mem:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 	/* This is safe: open() is still holding a reference. */
 	module_put(THIS_MODULE);
 	return -ENOMEM;
@@ -2605,9 +2595,9 @@ static unsigned int pkt_check_events(struct gendisk *disk,
 
 	if (!pd)
 		return 0;
-	if (!pd->bdev_handle)
+	if (!pd->bdev_file)
 		return 0;
-	attached_disk = pd->bdev_handle->bdev->bd_disk;
+	attached_disk = file_bdev(pd->bdev_file)->bd_disk;
 	if (!attached_disk || !attached_disk->fops->check_events)
 		return 0;
 	return attached_disk->fops->check_events(attached_disk, clearing);
@@ -2634,6 +2624,10 @@ static const struct block_device_operations pktcdvd_ops = {
  */
 static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
 {
+	struct queue_limits lim = {
+		.max_hw_sectors		= PACKET_MAX_SECTORS,
+		.logical_block_size	= CD_FRAMESIZE,
+	};
 	int idx;
 	int ret = -ENOMEM;
 	struct pktcdvd_device *pd;
@@ -2673,10 +2667,11 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
 	pd->write_congestion_on  = write_congestion_on;
 	pd->write_congestion_off = write_congestion_off;
 
-	ret = -ENOMEM;
-	disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!disk)
+	disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(disk)) {
+		ret = PTR_ERR(disk);
 		goto out_mem;
+	}
 	pd->disk = disk;
 	disk->major = pktdev_major;
 	disk->first_minor = idx;
@@ -2692,7 +2687,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
 		goto out_mem2;
 
 	/* inherit events of the host device */
-	disk->events = pd->bdev_handle->bdev->bd_disk->events;
+	disk->events = file_bdev(pd->bdev_file)->bd_disk->events;
 
 	ret = add_disk(disk);
 	if (ret)
@@ -2757,7 +2752,7 @@ static int pkt_remove_dev(dev_t pkt_dev)
 	pkt_debugfs_dev_remove(pd);
 	pkt_sysfs_dev_remove(pd);
 
-	bdev_release(pd->bdev_handle);
+	fput(pd->bdev_file);
 
 	remove_proc_entry(pd->disk->disk_name, pkt_proc);
 	dev_notice(ddev, "writer unmapped\n");
@@ -2784,7 +2779,7 @@ static void pkt_get_status(struct pkt_ctrl_command *ctrl_cmd)
 
 	pd = pkt_find_dev_from_minor(ctrl_cmd->dev_index);
 	if (pd) {
-		ctrl_cmd->dev = new_encode_dev(pd->bdev_handle->bdev->bd_dev);
+		ctrl_cmd->dev = new_encode_dev(file_bdev(pd->bdev_file)->bd_dev);
 		ctrl_cmd->pkt_dev = new_encode_dev(pd->pkt_dev);
 	} else {
 		ctrl_cmd->dev = 0;
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index 36d7b36c60c7..b810ac0a5c4b 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -382,6 +382,14 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
 	struct ps3disk_private *priv;
 	int error;
 	unsigned int devidx;
+	struct queue_limits lim = {
+		.logical_block_size	= dev->blk_size,
+		.max_hw_sectors		= dev->bounce_size >> 9,
+		.max_segments		= -1,
+		.max_segment_size	= dev->bounce_size,
+		.dma_alignment		= dev->blk_size - 1,
+	};
+
 	struct request_queue *queue;
 	struct gendisk *gendisk;
 
@@ -431,7 +439,7 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
 	if (error)
 		goto fail_teardown;
 
-	gendisk = blk_mq_alloc_disk(&priv->tag_set, dev);
+	gendisk = blk_mq_alloc_disk(&priv->tag_set, &lim, dev);
 	if (IS_ERR(gendisk)) {
 		dev_err(&dev->sbd.core, "%s:%u: blk_mq_alloc_disk failed\n",
 			__func__, __LINE__);
@@ -441,15 +449,8 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
 
 	queue = gendisk->queue;
 
-	blk_queue_max_hw_sectors(queue, dev->bounce_size >> 9);
-	blk_queue_dma_alignment(queue, dev->blk_size-1);
-	blk_queue_logical_block_size(queue, dev->blk_size);
-
 	blk_queue_write_cache(queue, true, false);
 
-	blk_queue_max_segments(queue, -1);
-	blk_queue_max_segment_size(queue, dev->bounce_size);
-
 	priv->gendisk = gendisk;
 	gendisk->major = ps3disk_major;
 	gendisk->first_minor = devidx * PS3DISK_MINORS;
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index 38d42af01b25..bdcf083b45e2 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -730,10 +730,10 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev)
 
 	ps3vram_proc_init(dev);
 
-	gendisk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!gendisk) {
+	gendisk = blk_alloc_disk(NULL, NUMA_NO_NODE);
+	if (IS_ERR(gendisk)) {
 		dev_err(&dev->core, "blk_alloc_disk failed\n");
-		error = -ENOMEM;
+		error = PTR_ERR(gendisk);
 		goto out_cache_cleanup;
 	}
 
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index a999b698b131..26ff5cd2bf0a 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -575,7 +575,7 @@ static const struct attribute_group rbd_bus_group = {
 };
 __ATTRIBUTE_GROUPS(rbd_bus);
 
-static struct bus_type rbd_bus_type = {
+static const struct bus_type rbd_bus_type = {
 	.name		= "rbd",
 	.bus_groups	= rbd_bus_groups,
 };
@@ -3452,14 +3452,15 @@ static bool rbd_lock_add_request(struct rbd_img_request *img_req)
 static void rbd_lock_del_request(struct rbd_img_request *img_req)
 {
 	struct rbd_device *rbd_dev = img_req->rbd_dev;
-	bool need_wakeup;
+	bool need_wakeup = false;
 
 	lockdep_assert_held(&rbd_dev->lock_rwsem);
 	spin_lock(&rbd_dev->lock_lists_lock);
-	rbd_assert(!list_empty(&img_req->lock_item));
-	list_del_init(&img_req->lock_item);
-	need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING &&
-		       list_empty(&rbd_dev->running_list));
+	if (!list_empty(&img_req->lock_item)) {
+		list_del_init(&img_req->lock_item);
+		need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING &&
+			       list_empty(&rbd_dev->running_list));
+	}
 	spin_unlock(&rbd_dev->lock_lists_lock);
 	if (need_wakeup)
 		complete(&rbd_dev->releasing_wait);
@@ -3842,14 +3843,19 @@ static void wake_lock_waiters(struct rbd_device *rbd_dev, int result)
 		return;
 	}
 
-	list_for_each_entry(img_req, &rbd_dev->acquiring_list, lock_item) {
+	while (!list_empty(&rbd_dev->acquiring_list)) {
+		img_req = list_first_entry(&rbd_dev->acquiring_list,
+					   struct rbd_img_request, lock_item);
 		mutex_lock(&img_req->state_mutex);
 		rbd_assert(img_req->state == RBD_IMG_EXCLUSIVE_LOCK);
+		if (!result)
+			list_move_tail(&img_req->lock_item,
+				       &rbd_dev->running_list);
+		else
+			list_del_init(&img_req->lock_item);
 		rbd_img_schedule(img_req, result);
 		mutex_unlock(&img_req->state_mutex);
 	}
-
-	list_splice_tail_init(&rbd_dev->acquiring_list, &rbd_dev->running_list);
 }
 
 static bool locker_equal(const struct ceph_locker *lhs,
@@ -4946,6 +4952,14 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	struct request_queue *q;
 	unsigned int objset_bytes =
 	    rbd_dev->layout.object_size * rbd_dev->layout.stripe_count;
+	struct queue_limits lim = {
+		.max_hw_sectors		= objset_bytes >> SECTOR_SHIFT,
+		.max_user_sectors	= objset_bytes >> SECTOR_SHIFT,
+		.io_min			= rbd_dev->opts->alloc_size,
+		.io_opt			= rbd_dev->opts->alloc_size,
+		.max_segments		= USHRT_MAX,
+		.max_segment_size	= UINT_MAX,
+	};
 	int err;
 
 	memset(&rbd_dev->tag_set, 0, sizeof(rbd_dev->tag_set));
@@ -4960,7 +4974,13 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	if (err)
 		return err;
 
-	disk = blk_mq_alloc_disk(&rbd_dev->tag_set, rbd_dev);
+	if (rbd_dev->opts->trim) {
+		lim.discard_granularity = rbd_dev->opts->alloc_size;
+		lim.max_hw_discard_sectors = objset_bytes >> SECTOR_SHIFT;
+		lim.max_write_zeroes_sectors = objset_bytes >> SECTOR_SHIFT;
+	}
+
+	disk = blk_mq_alloc_disk(&rbd_dev->tag_set, &lim, rbd_dev);
 	if (IS_ERR(disk)) {
 		err = PTR_ERR(disk);
 		goto out_tag_set;
@@ -4981,19 +5001,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
 	/* QUEUE_FLAG_ADD_RANDOM is off by default for blk-mq */
 
-	blk_queue_max_hw_sectors(q, objset_bytes >> SECTOR_SHIFT);
-	q->limits.max_sectors = queue_max_hw_sectors(q);
-	blk_queue_max_segments(q, USHRT_MAX);
-	blk_queue_max_segment_size(q, UINT_MAX);
-	blk_queue_io_min(q, rbd_dev->opts->alloc_size);
-	blk_queue_io_opt(q, rbd_dev->opts->alloc_size);
-
-	if (rbd_dev->opts->trim) {
-		q->limits.discard_granularity = rbd_dev->opts->alloc_size;
-		blk_queue_max_discard_sectors(q, objset_bytes >> SECTOR_SHIFT);
-		blk_queue_max_write_zeroes_sectors(q, objset_bytes >> SECTOR_SHIFT);
-	}
-
 	if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
 		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
 
@@ -5326,7 +5333,7 @@ static void rbd_dev_release(struct device *dev)
 
 	if (need_put) {
 		destroy_workqueue(rbd_dev->task_wq);
-		ida_simple_remove(&rbd_dev_id_ida, rbd_dev->dev_id);
+		ida_free(&rbd_dev_id_ida, rbd_dev->dev_id);
 	}
 
 	rbd_dev_free(rbd_dev);
@@ -5402,9 +5409,9 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc,
 		return NULL;
 
 	/* get an id and fill in device name */
-	rbd_dev->dev_id = ida_simple_get(&rbd_dev_id_ida, 0,
-					 minor_to_rbd_dev_id(1 << MINORBITS),
-					 GFP_KERNEL);
+	rbd_dev->dev_id = ida_alloc_max(&rbd_dev_id_ida,
+					minor_to_rbd_dev_id(1 << MINORBITS) - 1,
+					GFP_KERNEL);
 	if (rbd_dev->dev_id < 0)
 		goto fail_rbd_dev;
 
@@ -5425,7 +5432,7 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc,
 	return rbd_dev;
 
 fail_dev_id:
-	ida_simple_remove(&rbd_dev_id_ida, rbd_dev->dev_id);
+	ida_free(&rbd_dev_id_ida, rbd_dev->dev_id);
 fail_rbd_dev:
 	rbd_dev_free(rbd_dev);
 	return NULL;
diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c
index 4044c369d22a..b7ffe03c6160 100644
--- a/drivers/block/rnbd/rnbd-clt.c
+++ b/drivers/block/rnbd/rnbd-clt.c
@@ -1329,43 +1329,6 @@ static void rnbd_init_mq_hw_queues(struct rnbd_clt_dev *dev)
 	}
 }
 
-static void setup_request_queue(struct rnbd_clt_dev *dev,
-				struct rnbd_msg_open_rsp *rsp)
-{
-	blk_queue_logical_block_size(dev->queue,
-				     le16_to_cpu(rsp->logical_block_size));
-	blk_queue_physical_block_size(dev->queue,
-				      le16_to_cpu(rsp->physical_block_size));
-	blk_queue_max_hw_sectors(dev->queue,
-				 dev->sess->max_io_size / SECTOR_SIZE);
-
-	/*
-	 * we don't support discards to "discontiguous" segments
-	 * in on request
-	 */
-	blk_queue_max_discard_segments(dev->queue, 1);
-
-	blk_queue_max_discard_sectors(dev->queue,
-				      le32_to_cpu(rsp->max_discard_sectors));
-	dev->queue->limits.discard_granularity =
-					le32_to_cpu(rsp->discard_granularity);
-	dev->queue->limits.discard_alignment =
-					le32_to_cpu(rsp->discard_alignment);
-	if (le16_to_cpu(rsp->secure_discard))
-		blk_queue_max_secure_erase_sectors(dev->queue,
-					le32_to_cpu(rsp->max_discard_sectors));
-	blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, dev->queue);
-	blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, dev->queue);
-	blk_queue_max_segments(dev->queue, dev->sess->max_segments);
-	blk_queue_io_opt(dev->queue, dev->sess->max_io_size);
-	blk_queue_virt_boundary(dev->queue, SZ_4K - 1);
-	blk_queue_write_cache(dev->queue,
-			      !!(rsp->cache_policy & RNBD_WRITEBACK),
-			      !!(rsp->cache_policy & RNBD_FUA));
-	blk_queue_max_write_zeroes_sectors(dev->queue,
-					   le32_to_cpu(rsp->max_write_zeroes_sectors));
-}
-
 static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev,
 				   struct rnbd_msg_open_rsp *rsp, int idx)
 {
@@ -1403,18 +1366,41 @@ static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev,
 static int rnbd_client_setup_device(struct rnbd_clt_dev *dev,
 				    struct rnbd_msg_open_rsp *rsp)
 {
+	struct queue_limits lim = {
+		.logical_block_size	= le16_to_cpu(rsp->logical_block_size),
+		.physical_block_size	= le16_to_cpu(rsp->physical_block_size),
+		.io_opt			= dev->sess->max_io_size,
+		.max_hw_sectors		= dev->sess->max_io_size / SECTOR_SIZE,
+		.max_hw_discard_sectors	= le32_to_cpu(rsp->max_discard_sectors),
+		.discard_granularity	= le32_to_cpu(rsp->discard_granularity),
+		.discard_alignment	= le32_to_cpu(rsp->discard_alignment),
+		.max_segments		= dev->sess->max_segments,
+		.virt_boundary_mask	= SZ_4K - 1,
+		.max_write_zeroes_sectors =
+			le32_to_cpu(rsp->max_write_zeroes_sectors),
+	};
 	int idx = dev->clt_device_id;
 
 	dev->size = le64_to_cpu(rsp->nsectors) *
 			le16_to_cpu(rsp->logical_block_size);
 
-	dev->gd = blk_mq_alloc_disk(&dev->sess->tag_set, dev);
+	if (rsp->secure_discard) {
+		lim.max_secure_erase_sectors =
+			le32_to_cpu(rsp->max_discard_sectors);
+	}
+
+	dev->gd = blk_mq_alloc_disk(&dev->sess->tag_set, &lim, dev);
 	if (IS_ERR(dev->gd))
 		return PTR_ERR(dev->gd);
 	dev->queue = dev->gd->queue;
 	rnbd_init_mq_hw_queues(dev);
 
-	setup_request_queue(dev, rsp);
+	blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, dev->queue);
+	blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, dev->queue);
+	blk_queue_write_cache(dev->queue,
+			      !!(rsp->cache_policy & RNBD_WRITEBACK),
+			      !!(rsp->cache_policy & RNBD_FUA));
+
 	return rnbd_clt_setup_gen_disk(dev, rsp, idx);
 }
 
diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c
index 3a0d5dcec6f2..f6e3a3c4b76c 100644
--- a/drivers/block/rnbd/rnbd-srv.c
+++ b/drivers/block/rnbd/rnbd-srv.c
@@ -145,7 +145,7 @@ static int process_rdma(struct rnbd_srv_session *srv_sess,
 	priv->sess_dev = sess_dev;
 	priv->id = id;
 
-	bio = bio_alloc(sess_dev->bdev_handle->bdev, 1,
+	bio = bio_alloc(file_bdev(sess_dev->bdev_file), 1,
 			rnbd_to_bio_flags(le32_to_cpu(msg->rw)), GFP_KERNEL);
 	if (bio_add_page(bio, virt_to_page(data), datalen,
 			offset_in_page(data)) != datalen) {
@@ -219,7 +219,7 @@ void rnbd_destroy_sess_dev(struct rnbd_srv_sess_dev *sess_dev, bool keep_id)
 	rnbd_put_sess_dev(sess_dev);
 	wait_for_completion(&dc); /* wait for inflights to drop to zero */
 
-	bdev_release(sess_dev->bdev_handle);
+	fput(sess_dev->bdev_file);
 	mutex_lock(&sess_dev->dev->lock);
 	list_del(&sess_dev->dev_list);
 	if (!sess_dev->readonly)
@@ -534,7 +534,7 @@ rnbd_srv_get_or_create_srv_dev(struct block_device *bdev,
 static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp,
 					struct rnbd_srv_sess_dev *sess_dev)
 {
-	struct block_device *bdev = sess_dev->bdev_handle->bdev;
+	struct block_device *bdev = file_bdev(sess_dev->bdev_file);
 
 	rsp->hdr.type = cpu_to_le16(RNBD_MSG_OPEN_RSP);
 	rsp->device_id = cpu_to_le32(sess_dev->device_id);
@@ -560,7 +560,7 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp,
 static struct rnbd_srv_sess_dev *
 rnbd_srv_create_set_sess_dev(struct rnbd_srv_session *srv_sess,
 			      const struct rnbd_msg_open *open_msg,
-			      struct bdev_handle *handle, bool readonly,
+			      struct file *bdev_file, bool readonly,
 			      struct rnbd_srv_dev *srv_dev)
 {
 	struct rnbd_srv_sess_dev *sdev = rnbd_sess_dev_alloc(srv_sess);
@@ -572,7 +572,7 @@ rnbd_srv_create_set_sess_dev(struct rnbd_srv_session *srv_sess,
 
 	strscpy(sdev->pathname, open_msg->dev_name, sizeof(sdev->pathname));
 
-	sdev->bdev_handle	= handle;
+	sdev->bdev_file		= bdev_file;
 	sdev->sess		= srv_sess;
 	sdev->dev		= srv_dev;
 	sdev->readonly		= readonly;
@@ -678,7 +678,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess,
 	struct rnbd_srv_dev *srv_dev;
 	struct rnbd_srv_sess_dev *srv_sess_dev;
 	const struct rnbd_msg_open *open_msg = msg;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	blk_mode_t open_flags = BLK_OPEN_READ;
 	char *full_path;
 	struct rnbd_msg_open_rsp *rsp = data;
@@ -716,15 +716,15 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess,
 		goto reject;
 	}
 
-	bdev_handle = bdev_open_by_path(full_path, open_flags, NULL, NULL);
-	if (IS_ERR(bdev_handle)) {
-		ret = PTR_ERR(bdev_handle);
+	bdev_file = bdev_file_open_by_path(full_path, open_flags, NULL, NULL);
+	if (IS_ERR(bdev_file)) {
+		ret = PTR_ERR(bdev_file);
 		pr_err("Opening device '%s' on session %s failed, failed to open the block device, err: %pe\n",
-		       full_path, srv_sess->sessname, bdev_handle);
+		       full_path, srv_sess->sessname, bdev_file);
 		goto free_path;
 	}
 
-	srv_dev = rnbd_srv_get_or_create_srv_dev(bdev_handle->bdev, srv_sess,
+	srv_dev = rnbd_srv_get_or_create_srv_dev(file_bdev(bdev_file), srv_sess,
 						  open_msg->access_mode);
 	if (IS_ERR(srv_dev)) {
 		pr_err("Opening device '%s' on session %s failed, creating srv_dev failed, err: %pe\n",
@@ -734,7 +734,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess,
 	}
 
 	srv_sess_dev = rnbd_srv_create_set_sess_dev(srv_sess, open_msg,
-				bdev_handle,
+				bdev_file,
 				open_msg->access_mode == RNBD_ACCESS_RO,
 				srv_dev);
 	if (IS_ERR(srv_sess_dev)) {
@@ -750,7 +750,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess,
 	 */
 	mutex_lock(&srv_dev->lock);
 	if (!srv_dev->dev_kobj.state_in_sysfs) {
-		ret = rnbd_srv_create_dev_sysfs(srv_dev, bdev_handle->bdev);
+		ret = rnbd_srv_create_dev_sysfs(srv_dev, file_bdev(bdev_file));
 		if (ret) {
 			mutex_unlock(&srv_dev->lock);
 			rnbd_srv_err(srv_sess_dev,
@@ -793,7 +793,7 @@ srv_dev_put:
 	}
 	rnbd_put_srv_dev(srv_dev);
 blkdev_put:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 free_path:
 	kfree(full_path);
 reject:
diff --git a/drivers/block/rnbd/rnbd-srv.h b/drivers/block/rnbd/rnbd-srv.h
index 343cc682b617..18d873808b8d 100644
--- a/drivers/block/rnbd/rnbd-srv.h
+++ b/drivers/block/rnbd/rnbd-srv.h
@@ -46,7 +46,7 @@ struct rnbd_srv_dev {
 struct rnbd_srv_sess_dev {
 	/* Entry inside rnbd_srv_dev struct */
 	struct list_head		dev_list;
-	struct bdev_handle		*bdev_handle;
+	struct file			*bdev_file;
 	struct rnbd_srv_session		*sess;
 	struct rnbd_srv_dev		*dev;
 	struct kobject                  kobj;
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 7bf4b48e2282..c99dd6698977 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -784,6 +784,14 @@ static const struct blk_mq_ops vdc_mq_ops = {
 
 static int probe_disk(struct vdc_port *port)
 {
+	struct queue_limits lim = {
+		.physical_block_size		= port->vdisk_phys_blksz,
+		.max_hw_sectors			= port->max_xfer_size,
+		/* Each segment in a request is up to an aligned page in size. */
+		.seg_boundary_mask		= PAGE_SIZE - 1,
+		.max_segment_size		= PAGE_SIZE,
+		.max_segments			= port->ring_cookies,
+	};
 	struct request_queue *q;
 	struct gendisk *g;
 	int err;
@@ -824,7 +832,7 @@ static int probe_disk(struct vdc_port *port)
 	if (err)
 		return err;
 
-	g = blk_mq_alloc_disk(&port->tag_set, port);
+	g = blk_mq_alloc_disk(&port->tag_set, &lim, port);
 	if (IS_ERR(g)) {
 		printk(KERN_ERR PFX "%s: Could not allocate gendisk.\n",
 		       port->vio.name);
@@ -835,12 +843,6 @@ static int probe_disk(struct vdc_port *port)
 	port->disk = g;
 	q = g->queue;
 
-	/* Each segment in a request is up to an aligned page in size. */
-	blk_queue_segment_boundary(q, PAGE_SIZE - 1);
-	blk_queue_max_segment_size(q, PAGE_SIZE);
-
-	blk_queue_max_segments(q, port->ring_cookies);
-	blk_queue_max_hw_sectors(q, port->max_xfer_size);
 	g->major = vdc_major;
 	g->first_minor = port->vio.vdev->dev_no << PARTITION_SHIFT;
 	g->minors = 1 << PARTITION_SHIFT;
@@ -872,8 +874,6 @@ static int probe_disk(struct vdc_port *port)
 		}
 	}
 
-	blk_queue_physical_block_size(q, port->vdisk_phys_blksz);
-
 	pr_info(PFX "%s: %u sectors (%u MB) protocol %d.%d\n",
 	       g->disk_name,
 	       port->vdisk_size, (port->vdisk_size >> (20 - 9)),
diff --git a/drivers/block/swim.c b/drivers/block/swim.c
index f85b6af414b4..6731678f3a41 100644
--- a/drivers/block/swim.c
+++ b/drivers/block/swim.c
@@ -820,7 +820,7 @@ static int swim_floppy_init(struct swim_priv *swd)
 			goto exit_put_disks;
 
 		swd->unit[drive].disk =
-			blk_mq_alloc_disk(&swd->unit[drive].tag_set,
+			blk_mq_alloc_disk(&swd->unit[drive].tag_set, NULL,
 					  &swd->unit[drive]);
 		if (IS_ERR(swd->unit[drive].disk)) {
 			blk_mq_free_tag_set(&swd->unit[drive].tag_set);
@@ -916,7 +916,7 @@ out:
 	return ret;
 }
 
-static int swim_remove(struct platform_device *dev)
+static void swim_remove(struct platform_device *dev)
 {
 	struct swim_priv *swd = platform_get_drvdata(dev);
 	int drive;
@@ -937,13 +937,11 @@ static int swim_remove(struct platform_device *dev)
 		release_mem_region(res->start, resource_size(res));
 
 	kfree(swd);
-
-	return 0;
 }
 
 static struct platform_driver swim_driver = {
 	.probe  = swim_probe,
-	.remove = swim_remove,
+	.remove_new = swim_remove,
 	.driver   = {
 		.name	= CARDNAME,
 	},
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index c2bc85826358..a04756ac778e 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -1210,7 +1210,7 @@ static int swim3_attach(struct macio_dev *mdev,
 	if (rc)
 		goto out_unregister;
 
-	disk = blk_mq_alloc_disk(&fs->tag_set, fs);
+	disk = blk_mq_alloc_disk(&fs->tag_set, NULL, fs);
 	if (IS_ERR(disk)) {
 		rc = PTR_ERR(disk);
 		goto out_free_tag_set;
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 1dfb2e77898b..bea3d5cf8a83 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -246,21 +246,12 @@ static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)
 	return 0;
 }
 
-static int ublk_dev_param_zoned_apply(struct ublk_device *ub)
+static void ublk_dev_param_zoned_apply(struct ublk_device *ub)
 {
-	const struct ublk_param_zoned *p = &ub->params.zoned;
-
-	disk_set_zoned(ub->ub_disk);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ub->ub_disk->queue);
 	blk_queue_required_elevator_features(ub->ub_disk->queue,
 					     ELEVATOR_F_ZBD_SEQ_WRITE);
-	disk_set_max_active_zones(ub->ub_disk, p->max_active_zones);
-	disk_set_max_open_zones(ub->ub_disk, p->max_open_zones);
-	blk_queue_max_zone_append_sectors(ub->ub_disk->queue, p->max_zone_append_sectors);
-
 	ub->ub_disk->nr_zones = ublk_get_nr_zones(ub);
-
-	return 0;
 }
 
 /* Based on virtblk_alloc_report_buffer */
@@ -432,9 +423,8 @@ static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)
 	return -EOPNOTSUPP;
 }
 
-static int ublk_dev_param_zoned_apply(struct ublk_device *ub)
+static void ublk_dev_param_zoned_apply(struct ublk_device *ub)
 {
-	return -EOPNOTSUPP;
 }
 
 static int ublk_revalidate_disk_zones(struct ublk_device *ub)
@@ -498,11 +488,6 @@ static void ublk_dev_param_basic_apply(struct ublk_device *ub)
 	struct request_queue *q = ub->ub_disk->queue;
 	const struct ublk_param_basic *p = &ub->params.basic;
 
-	blk_queue_logical_block_size(q, 1 << p->logical_bs_shift);
-	blk_queue_physical_block_size(q, 1 << p->physical_bs_shift);
-	blk_queue_io_min(q, 1 << p->io_min_shift);
-	blk_queue_io_opt(q, 1 << p->io_opt_shift);
-
 	blk_queue_write_cache(q, p->attrs & UBLK_ATTR_VOLATILE_CACHE,
 			p->attrs & UBLK_ATTR_FUA);
 	if (p->attrs & UBLK_ATTR_ROTATIONAL)
@@ -510,29 +495,12 @@ static void ublk_dev_param_basic_apply(struct ublk_device *ub)
 	else
 		blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
 
-	blk_queue_max_hw_sectors(q, p->max_sectors);
-	blk_queue_chunk_sectors(q, p->chunk_sectors);
-	blk_queue_virt_boundary(q, p->virt_boundary_mask);
-
 	if (p->attrs & UBLK_ATTR_READ_ONLY)
 		set_disk_ro(ub->ub_disk, true);
 
 	set_capacity(ub->ub_disk, p->dev_sectors);
 }
 
-static void ublk_dev_param_discard_apply(struct ublk_device *ub)
-{
-	struct request_queue *q = ub->ub_disk->queue;
-	const struct ublk_param_discard *p = &ub->params.discard;
-
-	q->limits.discard_alignment = p->discard_alignment;
-	q->limits.discard_granularity = p->discard_granularity;
-	blk_queue_max_discard_sectors(q, p->max_discard_sectors);
-	blk_queue_max_write_zeroes_sectors(q,
-			p->max_write_zeroes_sectors);
-	blk_queue_max_discard_segments(q, p->max_discard_segments);
-}
-
 static int ublk_validate_params(const struct ublk_device *ub)
 {
 	/* basic param is the only one which must be set */
@@ -576,20 +544,12 @@ static int ublk_validate_params(const struct ublk_device *ub)
 	return 0;
 }
 
-static int ublk_apply_params(struct ublk_device *ub)
+static void ublk_apply_params(struct ublk_device *ub)
 {
-	if (!(ub->params.types & UBLK_PARAM_TYPE_BASIC))
-		return -EINVAL;
-
 	ublk_dev_param_basic_apply(ub);
 
-	if (ub->params.types & UBLK_PARAM_TYPE_DISCARD)
-		ublk_dev_param_discard_apply(ub);
-
 	if (ub->params.types & UBLK_PARAM_TYPE_ZONED)
-		return ublk_dev_param_zoned_apply(ub);
-
-	return 0;
+		ublk_dev_param_zoned_apply(ub);
 }
 
 static inline bool ublk_support_user_copy(const struct ublk_queue *ubq)
@@ -645,14 +605,16 @@ static inline bool ublk_need_get_data(const struct ublk_queue *ubq)
 	return ubq->flags & UBLK_F_NEED_GET_DATA;
 }
 
-static struct ublk_device *ublk_get_device(struct ublk_device *ub)
+/* Called in slow path only, keep it noinline for trace purpose */
+static noinline struct ublk_device *ublk_get_device(struct ublk_device *ub)
 {
 	if (kobject_get_unless_zero(&ub->cdev_dev.kobj))
 		return ub;
 	return NULL;
 }
 
-static void ublk_put_device(struct ublk_device *ub)
+/* Called in slow path only, keep it noinline for trace purpose */
+static noinline void ublk_put_device(struct ublk_device *ub)
 {
 	put_device(&ub->cdev_dev);
 }
@@ -711,7 +673,7 @@ static void ublk_free_disk(struct gendisk *disk)
 	struct ublk_device *ub = disk->private_data;
 
 	clear_bit(UB_STATE_USED, &ub->state);
-	put_device(&ub->cdev_dev);
+	ublk_put_device(ub);
 }
 
 static void ublk_store_owner_uid_gid(unsigned int *owner_uid,
@@ -2182,7 +2144,7 @@ static void ublk_remove(struct ublk_device *ub)
 	cancel_work_sync(&ub->stop_work);
 	cancel_work_sync(&ub->quiesce_work);
 	cdev_device_del(&ub->cdev, &ub->cdev_dev);
-	put_device(&ub->cdev_dev);
+	ublk_put_device(ub);
 	ublks_added--;
 }
 
@@ -2205,12 +2167,47 @@ static struct ublk_device *ublk_get_device_from_id(int idx)
 static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
 {
 	const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
+	const struct ublk_param_basic *p = &ub->params.basic;
 	int ublksrv_pid = (int)header->data[0];
+	struct queue_limits lim = {
+		.logical_block_size	= 1 << p->logical_bs_shift,
+		.physical_block_size	= 1 << p->physical_bs_shift,
+		.io_min			= 1 << p->io_min_shift,
+		.io_opt			= 1 << p->io_opt_shift,
+		.max_hw_sectors		= p->max_sectors,
+		.chunk_sectors		= p->chunk_sectors,
+		.virt_boundary_mask	= p->virt_boundary_mask,
+
+	};
 	struct gendisk *disk;
 	int ret = -EINVAL;
 
 	if (ublksrv_pid <= 0)
 		return -EINVAL;
+	if (!(ub->params.types & UBLK_PARAM_TYPE_BASIC))
+		return -EINVAL;
+
+	if (ub->params.types & UBLK_PARAM_TYPE_DISCARD) {
+		const struct ublk_param_discard *pd = &ub->params.discard;
+
+		lim.discard_alignment = pd->discard_alignment;
+		lim.discard_granularity = pd->discard_granularity;
+		lim.max_hw_discard_sectors = pd->max_discard_sectors;
+		lim.max_write_zeroes_sectors = pd->max_write_zeroes_sectors;
+		lim.max_discard_segments = pd->max_discard_segments;
+	}
+
+	if (ub->params.types & UBLK_PARAM_TYPE_ZONED) {
+		const struct ublk_param_zoned *p = &ub->params.zoned;
+
+		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED))
+			return -EOPNOTSUPP;
+
+		lim.zoned = true;
+		lim.max_active_zones = p->max_active_zones;
+		lim.max_open_zones =  p->max_open_zones;
+		lim.max_zone_append_sectors = p->max_zone_append_sectors;
+	}
 
 	if (wait_for_completion_interruptible(&ub->completion) != 0)
 		return -EINTR;
@@ -2222,7 +2219,7 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
 		goto out_unlock;
 	}
 
-	disk = blk_mq_alloc_disk(&ub->tag_set, NULL);
+	disk = blk_mq_alloc_disk(&ub->tag_set, &lim, NULL);
 	if (IS_ERR(disk)) {
 		ret = PTR_ERR(disk);
 		goto out_unlock;
@@ -2234,15 +2231,13 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
 	ub->dev_info.ublksrv_pid = ublksrv_pid;
 	ub->ub_disk = disk;
 
-	ret = ublk_apply_params(ub);
-	if (ret)
-		goto out_put_disk;
+	ublk_apply_params(ub);
 
 	/* don't probe partitions if any one ubq daemon is un-trusted */
 	if (ub->nr_privileged_daemon != ub->nr_queues_ready)
 		set_bit(GD_SUPPRESS_PART_SCAN, &disk->state);
 
-	get_device(&ub->cdev_dev);
+	ublk_get_device(ub);
 	ub->dev_info.state = UBLK_S_DEV_LIVE;
 
 	if (ublk_dev_is_zoned(ub)) {
@@ -2262,7 +2257,6 @@ out_put_cdev:
 		ub->dev_info.state = UBLK_S_DEV_DEAD;
 		ublk_put_device(ub);
 	}
-out_put_disk:
 	if (ret)
 		put_disk(disk);
 out_unlock:
@@ -2474,7 +2468,7 @@ static inline bool ublk_idr_freed(int id)
 	return ptr == NULL;
 }
 
-static int ublk_ctrl_del_dev(struct ublk_device **p_ub)
+static int ublk_ctrl_del_dev(struct ublk_device **p_ub, bool wait)
 {
 	struct ublk_device *ub = *p_ub;
 	int idx = ub->ub_number;
@@ -2508,7 +2502,7 @@ static int ublk_ctrl_del_dev(struct ublk_device **p_ub)
 	 * - the device number is freed already, we will not find this
 	 *   device via ublk_get_device_from_id()
 	 */
-	if (wait_event_interruptible(ublk_idr_wq, ublk_idr_freed(idx)))
+	if (wait && wait_event_interruptible(ublk_idr_wq, ublk_idr_freed(idx)))
 		return -EINTR;
 	return 0;
 }
@@ -2907,7 +2901,10 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
 		ret = ublk_ctrl_add_dev(cmd);
 		break;
 	case UBLK_CMD_DEL_DEV:
-		ret = ublk_ctrl_del_dev(&ub);
+		ret = ublk_ctrl_del_dev(&ub, true);
+		break;
+	case UBLK_U_CMD_DEL_DEV_ASYNC:
+		ret = ublk_ctrl_del_dev(&ub, false);
 		break;
 	case UBLK_CMD_GET_QUEUE_AFFINITY:
 		ret = ublk_ctrl_get_queue_affinity(ub, cmd);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 3b6b9abb8ce1..42dea7601d87 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -367,8 +367,6 @@ static void virtblk_done(struct virtqueue *vq)
 				blk_mq_complete_request(req);
 			req_done = true;
 		}
-		if (unlikely(virtqueue_is_broken(vq)))
-			break;
 	} while (!virtqueue_enable_cb(vq));
 
 	/* In case queue is stopped waiting for more buffers. */
@@ -722,25 +720,24 @@ fail_report:
 	return ret;
 }
 
-static int virtblk_probe_zoned_device(struct virtio_device *vdev,
-				       struct virtio_blk *vblk,
-				       struct request_queue *q)
+static int virtblk_read_zoned_limits(struct virtio_blk *vblk,
+		struct queue_limits *lim)
 {
+	struct virtio_device *vdev = vblk->vdev;
 	u32 v, wg;
 
 	dev_dbg(&vdev->dev, "probing host-managed zoned device\n");
 
-	disk_set_zoned(vblk->disk);
-	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
+	lim->zoned = true;
 
 	virtio_cread(vdev, struct virtio_blk_config,
 		     zoned.max_open_zones, &v);
-	disk_set_max_open_zones(vblk->disk, v);
+	lim->max_open_zones = v;
 	dev_dbg(&vdev->dev, "max open zones = %u\n", v);
 
 	virtio_cread(vdev, struct virtio_blk_config,
 		     zoned.max_active_zones, &v);
-	disk_set_max_active_zones(vblk->disk, v);
+	lim->max_active_zones = v;
 	dev_dbg(&vdev->dev, "max active zones = %u\n", v);
 
 	virtio_cread(vdev, struct virtio_blk_config,
@@ -749,8 +746,8 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev,
 		dev_warn(&vdev->dev, "zero write granularity reported\n");
 		return -ENODEV;
 	}
-	blk_queue_physical_block_size(q, wg);
-	blk_queue_io_min(q, wg);
+	lim->physical_block_size = wg;
+	lim->io_min = wg;
 
 	dev_dbg(&vdev->dev, "write granularity = %u\n", wg);
 
@@ -766,13 +763,13 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev,
 			vblk->zone_sectors);
 		return -ENODEV;
 	}
-	blk_queue_chunk_sectors(q, vblk->zone_sectors);
+	lim->chunk_sectors = vblk->zone_sectors;
 	dev_dbg(&vdev->dev, "zone sectors = %u\n", vblk->zone_sectors);
 
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) {
 		dev_warn(&vblk->vdev->dev,
 			 "ignoring negotiated F_DISCARD for zoned device\n");
-		blk_queue_max_discard_sectors(q, 0);
+		lim->max_hw_discard_sectors = 0;
 	}
 
 	virtio_cread(vdev, struct virtio_blk_config,
@@ -787,25 +784,21 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev,
 			wg, v);
 		return -ENODEV;
 	}
-	blk_queue_max_zone_append_sectors(q, v);
+	lim->max_zone_append_sectors = v;
 	dev_dbg(&vdev->dev, "max append sectors = %u\n", v);
 
-	return blk_revalidate_disk_zones(vblk->disk, NULL);
+	return 0;
 }
-
 #else
-
 /*
- * Zoned block device support is not configured in this kernel.
- * Host-managed zoned devices can't be supported, but others are
- * good to go as regular block devices.
+ * Zoned block device support is not configured in this kernel, host-managed
+ * zoned devices can't be supported.
  */
 #define virtblk_report_zones       NULL
-
-static inline int virtblk_probe_zoned_device(struct virtio_device *vdev,
-			struct virtio_blk *vblk, struct request_queue *q)
+static inline int virtblk_read_zoned_limits(struct virtio_blk *vblk,
+		struct queue_limits *lim)
 {
-	dev_err(&vdev->dev,
+	dev_err(&vblk->vdev->dev,
 		"virtio_blk: zoned devices are not supported");
 	return -EOPNOTSUPP;
 }
@@ -1250,31 +1243,17 @@ static const struct blk_mq_ops virtio_mq_ops = {
 static unsigned int virtblk_queue_depth;
 module_param_named(queue_depth, virtblk_queue_depth, uint, 0444);
 
-static int virtblk_probe(struct virtio_device *vdev)
+static int virtblk_read_limits(struct virtio_blk *vblk,
+		struct queue_limits *lim)
 {
-	struct virtio_blk *vblk;
-	struct request_queue *q;
-	int err, index;
-
+	struct virtio_device *vdev = vblk->vdev;
 	u32 v, blk_size, max_size, sg_elems, opt_io_size;
 	u32 max_discard_segs = 0;
 	u32 discard_granularity = 0;
 	u16 min_io_size;
 	u8 physical_block_exp, alignment_offset;
-	unsigned int queue_depth;
 	size_t max_dma_size;
-
-	if (!vdev->config->get) {
-		dev_err(&vdev->dev, "%s failure: config access disabled\n",
-			__func__);
-		return -EINVAL;
-	}
-
-	err = ida_alloc_range(&vd_index_ida, 0,
-			      minor_to_index(1 << MINORBITS) - 1, GFP_KERNEL);
-	if (err < 0)
-		goto out;
-	index = err;
+	int err;
 
 	/* We need to know how many segments before we allocate. */
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_SEG_MAX,
@@ -1288,78 +1267,11 @@ static int virtblk_probe(struct virtio_device *vdev)
 	/* Prevent integer overflows and honor max vq size */
 	sg_elems = min_t(u32, sg_elems, VIRTIO_BLK_MAX_SG_ELEMS - 2);
 
-	vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL);
-	if (!vblk) {
-		err = -ENOMEM;
-		goto out_free_index;
-	}
-
-	mutex_init(&vblk->vdev_mutex);
-
-	vblk->vdev = vdev;
-
-	INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
-
-	err = init_vq(vblk);
-	if (err)
-		goto out_free_vblk;
-
-	/* Default queue sizing is to fill the ring. */
-	if (!virtblk_queue_depth) {
-		queue_depth = vblk->vqs[0].vq->num_free;
-		/* ... but without indirect descs, we use 2 descs per req */
-		if (!virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC))
-			queue_depth /= 2;
-	} else {
-		queue_depth = virtblk_queue_depth;
-	}
-
-	memset(&vblk->tag_set, 0, sizeof(vblk->tag_set));
-	vblk->tag_set.ops = &virtio_mq_ops;
-	vblk->tag_set.queue_depth = queue_depth;
-	vblk->tag_set.numa_node = NUMA_NO_NODE;
-	vblk->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
-	vblk->tag_set.cmd_size =
-		sizeof(struct virtblk_req) +
-		sizeof(struct scatterlist) * VIRTIO_BLK_INLINE_SG_CNT;
-	vblk->tag_set.driver_data = vblk;
-	vblk->tag_set.nr_hw_queues = vblk->num_vqs;
-	vblk->tag_set.nr_maps = 1;
-	if (vblk->io_queues[HCTX_TYPE_POLL])
-		vblk->tag_set.nr_maps = 3;
-
-	err = blk_mq_alloc_tag_set(&vblk->tag_set);
-	if (err)
-		goto out_free_vq;
-
-	vblk->disk = blk_mq_alloc_disk(&vblk->tag_set, vblk);
-	if (IS_ERR(vblk->disk)) {
-		err = PTR_ERR(vblk->disk);
-		goto out_free_tags;
-	}
-	q = vblk->disk->queue;
-
-	virtblk_name_format("vd", index, vblk->disk->disk_name, DISK_NAME_LEN);
-
-	vblk->disk->major = major;
-	vblk->disk->first_minor = index_to_minor(index);
-	vblk->disk->minors = 1 << PART_BITS;
-	vblk->disk->private_data = vblk;
-	vblk->disk->fops = &virtblk_fops;
-	vblk->index = index;
-
-	/* configure queue flush support */
-	virtblk_update_cache_mode(vdev);
-
-	/* If disk is read-only in the host, the guest should obey */
-	if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO))
-		set_disk_ro(vblk->disk, 1);
-
 	/* We can handle whatever the host told us to handle. */
-	blk_queue_max_segments(q, sg_elems);
+	lim->max_segments = sg_elems;
 
 	/* No real sector limit. */
-	blk_queue_max_hw_sectors(q, UINT_MAX);
+	lim->max_hw_sectors = UINT_MAX;
 
 	max_dma_size = virtio_max_dma_size(vdev);
 	max_size = max_dma_size > U32_MAX ? U32_MAX : max_dma_size;
@@ -1371,7 +1283,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 	if (!err)
 		max_size = min(max_size, v);
 
-	blk_queue_max_segment_size(q, max_size);
+	lim->max_segment_size = max_size;
 
 	/* Host can optionally specify the block size of the device */
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_BLK_SIZE,
@@ -1383,38 +1295,37 @@ static int virtblk_probe(struct virtio_device *vdev)
 			dev_err(&vdev->dev,
 				"virtio_blk: invalid block size: 0x%x\n",
 				blk_size);
-			goto out_cleanup_disk;
+			return err;
 		}
 
-		blk_queue_logical_block_size(q, blk_size);
+		lim->logical_block_size = blk_size;
 	} else
-		blk_size = queue_logical_block_size(q);
+		blk_size = lim->logical_block_size;
 
 	/* Use topology information if available */
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
 				   struct virtio_blk_config, physical_block_exp,
 				   &physical_block_exp);
 	if (!err && physical_block_exp)
-		blk_queue_physical_block_size(q,
-				blk_size * (1 << physical_block_exp));
+		lim->physical_block_size = blk_size * (1 << physical_block_exp);
 
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
 				   struct virtio_blk_config, alignment_offset,
 				   &alignment_offset);
 	if (!err && alignment_offset)
-		blk_queue_alignment_offset(q, blk_size * alignment_offset);
+		lim->alignment_offset = blk_size * alignment_offset;
 
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
 				   struct virtio_blk_config, min_io_size,
 				   &min_io_size);
 	if (!err && min_io_size)
-		blk_queue_io_min(q, blk_size * min_io_size);
+		lim->io_min = blk_size * min_io_size;
 
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
 				   struct virtio_blk_config, opt_io_size,
 				   &opt_io_size);
 	if (!err && opt_io_size)
-		blk_queue_io_opt(q, blk_size * opt_io_size);
+		lim->io_opt = blk_size * opt_io_size;
 
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) {
 		virtio_cread(vdev, struct virtio_blk_config,
@@ -1422,7 +1333,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 
 		virtio_cread(vdev, struct virtio_blk_config,
 			     max_discard_sectors, &v);
-		blk_queue_max_discard_sectors(q, v ? v : UINT_MAX);
+		lim->max_hw_discard_sectors = v ? v : UINT_MAX;
 
 		virtio_cread(vdev, struct virtio_blk_config, max_discard_seg,
 			     &max_discard_segs);
@@ -1431,7 +1342,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_WRITE_ZEROES)) {
 		virtio_cread(vdev, struct virtio_blk_config,
 			     max_write_zeroes_sectors, &v);
-		blk_queue_max_write_zeroes_sectors(q, v ? v : UINT_MAX);
+		lim->max_write_zeroes_sectors = v ? v : UINT_MAX;
 	}
 
 	/* The discard and secure erase limits are combined since the Linux
@@ -1457,8 +1368,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 		if (!v) {
 			dev_err(&vdev->dev,
 				"virtio_blk: secure_erase_sector_alignment can't be 0\n");
-			err = -EINVAL;
-			goto out_cleanup_disk;
+			return -EINVAL;
 		}
 
 		discard_granularity = min_not_zero(discard_granularity, v);
@@ -1472,11 +1382,10 @@ static int virtblk_probe(struct virtio_device *vdev)
 		if (!v) {
 			dev_err(&vdev->dev,
 				"virtio_blk: max_secure_erase_sectors can't be 0\n");
-			err = -EINVAL;
-			goto out_cleanup_disk;
+			return -EINVAL;
 		}
 
-		blk_queue_max_secure_erase_sectors(q, v);
+		lim->max_secure_erase_sectors = v;
 
 		virtio_cread(vdev, struct virtio_blk_config,
 			     max_secure_erase_seg, &v);
@@ -1487,8 +1396,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 		if (!v) {
 			dev_err(&vdev->dev,
 				"virtio_blk: max_secure_erase_seg can't be 0\n");
-			err = -EINVAL;
-			goto out_cleanup_disk;
+			return -EINVAL;
 		}
 
 		max_discard_segs = min_not_zero(max_discard_segs, v);
@@ -1504,45 +1412,142 @@ static int virtblk_probe(struct virtio_device *vdev)
 		if (!max_discard_segs)
 			max_discard_segs = sg_elems;
 
-		blk_queue_max_discard_segments(q,
-					       min(max_discard_segs, MAX_DISCARD_SEGMENTS));
+		lim->max_discard_segments =
+			min(max_discard_segs, MAX_DISCARD_SEGMENTS);
 
 		if (discard_granularity)
-			q->limits.discard_granularity = discard_granularity << SECTOR_SHIFT;
+			lim->discard_granularity =
+				discard_granularity << SECTOR_SHIFT;
 		else
-			q->limits.discard_granularity = blk_size;
+			lim->discard_granularity = blk_size;
 	}
 
-	virtblk_update_capacity(vblk, false);
-	virtio_device_ready(vdev);
-
-	/*
-	 * All steps that follow use the VQs therefore they need to be
-	 * placed after the virtio_device_ready() call above.
-	 */
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_ZONED)) {
 		u8 model;
 
-		virtio_cread(vdev, struct virtio_blk_config, zoned.model,
-				&model);
+		virtio_cread(vdev, struct virtio_blk_config, zoned.model, &model);
 		switch (model) {
 		case VIRTIO_BLK_Z_NONE:
 		case VIRTIO_BLK_Z_HA:
-			/* Present the host-aware device as non-zoned */
-			break;
+			/* treat host-aware devices as non-zoned */
+			return 0;
 		case VIRTIO_BLK_Z_HM:
-			err = virtblk_probe_zoned_device(vdev, vblk, q);
+			err = virtblk_read_zoned_limits(vblk, lim);
 			if (err)
-				goto out_cleanup_disk;
+				return err;
 			break;
 		default:
-			dev_err(&vdev->dev, "unsupported zone model %d\n",
-				model);
-			err = -EINVAL;
-			goto out_cleanup_disk;
+			dev_err(&vdev->dev, "unsupported zone model %d\n", model);
+			return -EINVAL;
 		}
 	}
 
+	return 0;
+}
+
+static int virtblk_probe(struct virtio_device *vdev)
+{
+	struct virtio_blk *vblk;
+	struct queue_limits lim = { };
+	int err, index;
+	unsigned int queue_depth;
+
+	if (!vdev->config->get) {
+		dev_err(&vdev->dev, "%s failure: config access disabled\n",
+			__func__);
+		return -EINVAL;
+	}
+
+	err = ida_alloc_range(&vd_index_ida, 0,
+			      minor_to_index(1 << MINORBITS) - 1, GFP_KERNEL);
+	if (err < 0)
+		goto out;
+	index = err;
+
+	vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL);
+	if (!vblk) {
+		err = -ENOMEM;
+		goto out_free_index;
+	}
+
+	mutex_init(&vblk->vdev_mutex);
+
+	vblk->vdev = vdev;
+
+	INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
+
+	err = init_vq(vblk);
+	if (err)
+		goto out_free_vblk;
+
+	/* Default queue sizing is to fill the ring. */
+	if (!virtblk_queue_depth) {
+		queue_depth = vblk->vqs[0].vq->num_free;
+		/* ... but without indirect descs, we use 2 descs per req */
+		if (!virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC))
+			queue_depth /= 2;
+	} else {
+		queue_depth = virtblk_queue_depth;
+	}
+
+	memset(&vblk->tag_set, 0, sizeof(vblk->tag_set));
+	vblk->tag_set.ops = &virtio_mq_ops;
+	vblk->tag_set.queue_depth = queue_depth;
+	vblk->tag_set.numa_node = NUMA_NO_NODE;
+	vblk->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	vblk->tag_set.cmd_size =
+		sizeof(struct virtblk_req) +
+		sizeof(struct scatterlist) * VIRTIO_BLK_INLINE_SG_CNT;
+	vblk->tag_set.driver_data = vblk;
+	vblk->tag_set.nr_hw_queues = vblk->num_vqs;
+	vblk->tag_set.nr_maps = 1;
+	if (vblk->io_queues[HCTX_TYPE_POLL])
+		vblk->tag_set.nr_maps = 3;
+
+	err = blk_mq_alloc_tag_set(&vblk->tag_set);
+	if (err)
+		goto out_free_vq;
+
+	err = virtblk_read_limits(vblk, &lim);
+	if (err)
+		goto out_free_tags;
+
+	vblk->disk = blk_mq_alloc_disk(&vblk->tag_set, &lim, vblk);
+	if (IS_ERR(vblk->disk)) {
+		err = PTR_ERR(vblk->disk);
+		goto out_free_tags;
+	}
+
+	virtblk_name_format("vd", index, vblk->disk->disk_name, DISK_NAME_LEN);
+
+	vblk->disk->major = major;
+	vblk->disk->first_minor = index_to_minor(index);
+	vblk->disk->minors = 1 << PART_BITS;
+	vblk->disk->private_data = vblk;
+	vblk->disk->fops = &virtblk_fops;
+	vblk->index = index;
+
+	/* configure queue flush support */
+	virtblk_update_cache_mode(vdev);
+
+	/* If disk is read-only in the host, the guest should obey */
+	if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO))
+		set_disk_ro(vblk->disk, 1);
+
+	virtblk_update_capacity(vblk, false);
+	virtio_device_ready(vdev);
+
+	/*
+	 * All steps that follow use the VQs therefore they need to be
+	 * placed after the virtio_device_ready() call above.
+	 */
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && lim.zoned) {
+		blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, vblk->disk->queue);
+		err = blk_revalidate_disk_zones(vblk->disk, NULL);
+		if (err)
+			goto out_cleanup_disk;
+	}
+
 	err = device_add_disk(&vdev->dev, vblk->disk, virtblk_attr_groups);
 	if (err)
 		goto out_cleanup_disk;
@@ -1595,14 +1600,15 @@ static int virtblk_freeze(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk = vdev->priv;
 
+	/* Ensure no requests in virtqueues before deleting vqs. */
+	blk_mq_freeze_queue(vblk->disk->queue);
+
 	/* Ensure we don't receive any more interrupts */
 	virtio_reset_device(vdev);
 
 	/* Make sure no work handler is accessing the device. */
 	flush_work(&vblk->config_work);
 
-	blk_mq_quiesce_queue(vblk->disk->queue);
-
 	vdev->config->del_vqs(vdev);
 	kfree(vblk->vqs);
 
@@ -1620,7 +1626,7 @@ static int virtblk_restore(struct virtio_device *vdev)
 
 	virtio_device_ready(vdev);
 
-	blk_mq_unquiesce_queue(vblk->disk->queue);
+	blk_mq_unfreeze_queue(vblk->disk->queue);
 	return 0;
 }
 #endif
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 4defd7f387c7..944576d582fb 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -465,7 +465,7 @@ static int xen_vbd_translate(struct phys_req *req, struct xen_blkif *blkif,
 	}
 
 	req->dev  = vbd->pdevice;
-	req->bdev = vbd->bdev_handle->bdev;
+	req->bdev = file_bdev(vbd->bdev_file);
 	rc = 0;
 
  out:
@@ -969,7 +969,7 @@ static int dispatch_discard_io(struct xen_blkif_ring *ring,
 	int err = 0;
 	int status = BLKIF_RSP_OKAY;
 	struct xen_blkif *blkif = ring->blkif;
-	struct block_device *bdev = blkif->vbd.bdev_handle->bdev;
+	struct block_device *bdev = file_bdev(blkif->vbd.bdev_file);
 	struct phys_req preq;
 
 	xen_blkif_get(blkif);
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index 1432c83183d0..b427d54bc120 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -221,7 +221,7 @@ struct xen_vbd {
 	unsigned char		type;
 	/* phys device that this vbd maps to. */
 	u32			pdevice;
-	struct bdev_handle	*bdev_handle;
+	struct file		*bdev_file;
 	/* Cached size parameter. */
 	sector_t		size;
 	unsigned int		flush_support:1;
@@ -360,7 +360,7 @@ struct pending_req {
 };
 
 
-#define vbd_sz(_v)	bdev_nr_sectors((_v)->bdev_handle->bdev)
+#define vbd_sz(_v)	bdev_nr_sectors(file_bdev((_v)->bdev_file))
 
 #define xen_blkif_get(_b) (atomic_inc(&(_b)->refcnt))
 #define xen_blkif_put(_b)				\
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index e34219ea2b05..0621878940ae 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -81,7 +81,7 @@ static void xen_update_blkif_status(struct xen_blkif *blkif)
 	int i;
 
 	/* Not ready to connect? */
-	if (!blkif->rings || !blkif->rings[0].irq || !blkif->vbd.bdev_handle)
+	if (!blkif->rings || !blkif->rings[0].irq || !blkif->vbd.bdev_file)
 		return;
 
 	/* Already connected? */
@@ -99,13 +99,12 @@ static void xen_update_blkif_status(struct xen_blkif *blkif)
 		return;
 	}
 
-	err = sync_blockdev(blkif->vbd.bdev_handle->bdev);
+	err = sync_blockdev(file_bdev(blkif->vbd.bdev_file));
 	if (err) {
 		xenbus_dev_error(blkif->be->dev, err, "block flush");
 		return;
 	}
-	invalidate_inode_pages2(
-			blkif->vbd.bdev_handle->bdev->bd_inode->i_mapping);
+	invalidate_inode_pages2(blkif->vbd.bdev_file->f_mapping);
 
 	for (i = 0; i < blkif->nr_rings; i++) {
 		ring = &blkif->rings[i];
@@ -473,9 +472,9 @@ static void xenvbd_sysfs_delif(struct xenbus_device *dev)
 
 static void xen_vbd_free(struct xen_vbd *vbd)
 {
-	if (vbd->bdev_handle)
-		bdev_release(vbd->bdev_handle);
-	vbd->bdev_handle = NULL;
+	if (vbd->bdev_file)
+		fput(vbd->bdev_file);
+	vbd->bdev_file = NULL;
 }
 
 static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
@@ -483,7 +482,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 			  int cdrom)
 {
 	struct xen_vbd *vbd;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 
 	vbd = &blkif->vbd;
 	vbd->handle   = handle;
@@ -492,17 +491,17 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 
 	vbd->pdevice  = MKDEV(major, minor);
 
-	bdev_handle = bdev_open_by_dev(vbd->pdevice, vbd->readonly ?
+	bdev_file = bdev_file_open_by_dev(vbd->pdevice, vbd->readonly ?
 				 BLK_OPEN_READ : BLK_OPEN_WRITE, NULL, NULL);
 
-	if (IS_ERR(bdev_handle)) {
+	if (IS_ERR(bdev_file)) {
 		pr_warn("xen_vbd_create: device %08x could not be opened\n",
 			vbd->pdevice);
 		return -ENOENT;
 	}
 
-	vbd->bdev_handle = bdev_handle;
-	if (vbd->bdev_handle->bdev->bd_disk == NULL) {
+	vbd->bdev_file = bdev_file;
+	if (file_bdev(vbd->bdev_file)->bd_disk == NULL) {
 		pr_warn("xen_vbd_create: device %08x doesn't exist\n",
 			vbd->pdevice);
 		xen_vbd_free(vbd);
@@ -510,14 +509,14 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 	}
 	vbd->size = vbd_sz(vbd);
 
-	if (cdrom || disk_to_cdi(vbd->bdev_handle->bdev->bd_disk))
+	if (cdrom || disk_to_cdi(file_bdev(vbd->bdev_file)->bd_disk))
 		vbd->type |= VDISK_CDROM;
-	if (vbd->bdev_handle->bdev->bd_disk->flags & GENHD_FL_REMOVABLE)
+	if (file_bdev(vbd->bdev_file)->bd_disk->flags & GENHD_FL_REMOVABLE)
 		vbd->type |= VDISK_REMOVABLE;
 
-	if (bdev_write_cache(bdev_handle->bdev))
+	if (bdev_write_cache(file_bdev(bdev_file)))
 		vbd->flush_support = true;
-	if (bdev_max_secure_erase_sectors(bdev_handle->bdev))
+	if (bdev_max_secure_erase_sectors(file_bdev(bdev_file)))
 		vbd->discard_secure = true;
 
 	pr_debug("Successful creation of handle=%04x (dom=%u)\n",
@@ -570,7 +569,7 @@ static void xen_blkbk_discard(struct xenbus_transaction xbt, struct backend_info
 	struct xen_blkif *blkif = be->blkif;
 	int err;
 	int state = 0;
-	struct block_device *bdev = be->blkif->vbd.bdev_handle->bdev;
+	struct block_device *bdev = file_bdev(be->blkif->vbd.bdev_file);
 
 	if (!xenbus_read_unsigned(dev->nodename, "discard-enable", 1))
 		return;
@@ -932,7 +931,7 @@ again:
 	}
 	err = xenbus_printf(xbt, dev->nodename, "sector-size", "%lu",
 			    (unsigned long)bdev_logical_block_size(
-					be->blkif->vbd.bdev_handle->bdev));
+					file_bdev(be->blkif->vbd.bdev_file)));
 	if (err) {
 		xenbus_dev_fatal(dev, err, "writing %s/sector-size",
 				 dev->nodename);
@@ -940,7 +939,7 @@ again:
 	}
 	err = xenbus_printf(xbt, dev->nodename, "physical-sector-size", "%u",
 			    bdev_physical_block_size(
-					be->blkif->vbd.bdev_handle->bdev));
+					file_bdev(be->blkif->vbd.bdev_file)));
 	if (err)
 		xenbus_dev_error(dev, err, "writing %s/physical-sector-size",
 				 dev->nodename);
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 434fab306777..fd7c0ff2139c 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -941,39 +941,35 @@ static const struct blk_mq_ops blkfront_mq_ops = {
 	.complete = blkif_complete_rq,
 };
 
-static void blkif_set_queue_limits(struct blkfront_info *info)
+static void blkif_set_queue_limits(const struct blkfront_info *info,
+		struct queue_limits *lim)
 {
-	struct request_queue *rq = info->rq;
-	struct gendisk *gd = info->gd;
 	unsigned int segments = info->max_indirect_segments ? :
 				BLKIF_MAX_SEGMENTS_PER_REQUEST;
 
-	blk_queue_flag_set(QUEUE_FLAG_VIRT, rq);
-
 	if (info->feature_discard) {
-		blk_queue_max_discard_sectors(rq, get_capacity(gd));
-		rq->limits.discard_granularity = info->discard_granularity ?:
-						 info->physical_sector_size;
-		rq->limits.discard_alignment = info->discard_alignment;
+		lim->max_hw_discard_sectors = UINT_MAX;
+		if (info->discard_granularity)
+			lim->discard_granularity = info->discard_granularity;
+		lim->discard_alignment = info->discard_alignment;
 		if (info->feature_secdiscard)
-			blk_queue_max_secure_erase_sectors(rq,
-							   get_capacity(gd));
+			lim->max_secure_erase_sectors = UINT_MAX;
 	}
 
 	/* Hard sector size and max sectors impersonate the equiv. hardware. */
-	blk_queue_logical_block_size(rq, info->sector_size);
-	blk_queue_physical_block_size(rq, info->physical_sector_size);
-	blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512);
+	lim->logical_block_size = info->sector_size;
+	lim->physical_block_size = info->physical_sector_size;
+	lim->max_hw_sectors = (segments * XEN_PAGE_SIZE) / 512;
 
 	/* Each segment in a request is up to an aligned page in size. */
-	blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
-	blk_queue_max_segment_size(rq, PAGE_SIZE);
+	lim->seg_boundary_mask = PAGE_SIZE - 1;
+	lim->max_segment_size = PAGE_SIZE;
 
 	/* Ensure a merged request will fit in a single I/O ring slot. */
-	blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG);
+	lim->max_segments = segments / GRANTS_PER_PSEG;
 
 	/* Make sure buffer addresses are sector-aligned. */
-	blk_queue_dma_alignment(rq, 511);
+	lim->dma_alignment = 511;
 }
 
 static const char *flush_info(struct blkfront_info *info)
@@ -1070,6 +1066,7 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 		struct blkfront_info *info, u16 sector_size,
 		unsigned int physical_sector_size)
 {
+	struct queue_limits lim = {};
 	struct gendisk *gd;
 	int nr_minors = 1;
 	int err;
@@ -1136,11 +1133,13 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	if (err)
 		goto out_release_minors;
 
-	gd = blk_mq_alloc_disk(&info->tag_set, info);
+	blkif_set_queue_limits(info, &lim);
+	gd = blk_mq_alloc_disk(&info->tag_set, &lim, info);
 	if (IS_ERR(gd)) {
 		err = PTR_ERR(gd);
 		goto out_free_tag_set;
 	}
+	blk_queue_flag_set(QUEUE_FLAG_VIRT, gd->queue);
 
 	strcpy(gd->disk_name, DEV_NAME);
 	ptr = encode_disk_name(gd->disk_name + sizeof(DEV_NAME) - 1, offset);
@@ -1162,7 +1161,6 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	info->gd = gd;
 	info->sector_size = sector_size;
 	info->physical_sector_size = physical_sector_size;
-	blkif_set_queue_limits(info);
 
 	xlvbd_flush(info);
 
@@ -2006,18 +2004,19 @@ static int blkfront_probe(struct xenbus_device *dev,
 
 static int blkif_recover(struct blkfront_info *info)
 {
+	struct queue_limits lim;
 	unsigned int r_index;
 	struct request *req, *n;
 	int rc;
 	struct bio *bio;
-	unsigned int segs;
 	struct blkfront_ring_info *rinfo;
 
+	lim = queue_limits_start_update(info->rq);
 	blkfront_gather_backend_features(info);
-	/* Reset limits changed by blk_mq_update_nr_hw_queues(). */
-	blkif_set_queue_limits(info);
-	segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST;
-	blk_queue_max_segments(info->rq, segs / GRANTS_PER_PSEG);
+	blkif_set_queue_limits(info, &lim);
+	rc = queue_limits_commit_update(info->rq, &lim);
+	if (rc)
+		return rc;
 
 	for_each_rinfo(info, rinfo, r_index) {
 		rc = blkfront_setup_indirect(rinfo);
@@ -2037,7 +2036,9 @@ static int blkif_recover(struct blkfront_info *info)
 	list_for_each_entry_safe(req, n, &info->requests, queuelist) {
 		/* Requeue pending requests (flush or discard) */
 		list_del_init(&req->queuelist);
-		BUG_ON(req->nr_phys_segments > segs);
+		BUG_ON(req->nr_phys_segments >
+		       (info->max_indirect_segments ? :
+			BLKIF_MAX_SEGMENTS_PER_REQUEST));
 		blk_mq_requeue_request(req, false);
 	}
 	blk_mq_start_stopped_hw_queues(info->rq, true);
diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c
index 11493167b0a8..7c5f4e4d9b50 100644
--- a/drivers/block/z2ram.c
+++ b/drivers/block/z2ram.c
@@ -318,7 +318,7 @@ static int z2ram_register_disk(int minor)
 	struct gendisk *disk;
 	int err;
 
-	disk = blk_mq_alloc_disk(&tag_set, NULL);
+	disk = blk_mq_alloc_disk(&tag_set, NULL, NULL);
 	if (IS_ERR(disk))
 		return PTR_ERR(disk);
 
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 6772e0c654fa..da7a20fa6152 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -426,11 +426,11 @@ static void reset_bdev(struct zram *zram)
 	if (!zram->backing_dev)
 		return;
 
-	bdev_release(zram->bdev_handle);
+	fput(zram->bdev_file);
 	/* hope filp_close flush all of IO */
 	filp_close(zram->backing_dev, NULL);
 	zram->backing_dev = NULL;
-	zram->bdev_handle = NULL;
+	zram->bdev_file = NULL;
 	zram->disk->fops = &zram_devops;
 	kvfree(zram->bitmap);
 	zram->bitmap = NULL;
@@ -476,7 +476,7 @@ static ssize_t backing_dev_store(struct device *dev,
 	struct address_space *mapping;
 	unsigned int bitmap_sz;
 	unsigned long nr_pages, *bitmap = NULL;
-	struct bdev_handle *bdev_handle = NULL;
+	struct file *bdev_file = NULL;
 	int err;
 	struct zram *zram = dev_to_zram(dev);
 
@@ -513,11 +513,11 @@ static ssize_t backing_dev_store(struct device *dev,
 		goto out;
 	}
 
-	bdev_handle = bdev_open_by_dev(inode->i_rdev,
+	bdev_file = bdev_file_open_by_dev(inode->i_rdev,
 				BLK_OPEN_READ | BLK_OPEN_WRITE, zram, NULL);
-	if (IS_ERR(bdev_handle)) {
-		err = PTR_ERR(bdev_handle);
-		bdev_handle = NULL;
+	if (IS_ERR(bdev_file)) {
+		err = PTR_ERR(bdev_file);
+		bdev_file = NULL;
 		goto out;
 	}
 
@@ -531,7 +531,7 @@ static ssize_t backing_dev_store(struct device *dev,
 
 	reset_bdev(zram);
 
-	zram->bdev_handle = bdev_handle;
+	zram->bdev_file = bdev_file;
 	zram->backing_dev = backing_dev;
 	zram->bitmap = bitmap;
 	zram->nr_pages = nr_pages;
@@ -544,8 +544,8 @@ static ssize_t backing_dev_store(struct device *dev,
 out:
 	kvfree(bitmap);
 
-	if (bdev_handle)
-		bdev_release(bdev_handle);
+	if (bdev_file)
+		fput(bdev_file);
 
 	if (backing_dev)
 		filp_close(backing_dev, NULL);
@@ -587,7 +587,7 @@ static void read_from_bdev_async(struct zram *zram, struct page *page,
 {
 	struct bio *bio;
 
-	bio = bio_alloc(zram->bdev_handle->bdev, 1, parent->bi_opf, GFP_NOIO);
+	bio = bio_alloc(file_bdev(zram->bdev_file), 1, parent->bi_opf, GFP_NOIO);
 	bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9);
 	__bio_add_page(bio, page, PAGE_SIZE, 0);
 	bio_chain(bio, parent);
@@ -703,7 +703,7 @@ static ssize_t writeback_store(struct device *dev,
 			continue;
 		}
 
-		bio_init(&bio, zram->bdev_handle->bdev, &bio_vec, 1,
+		bio_init(&bio, file_bdev(zram->bdev_file), &bio_vec, 1,
 			 REQ_OP_WRITE | REQ_SYNC);
 		bio.bi_iter.bi_sector = blk_idx * (PAGE_SIZE >> 9);
 		__bio_add_page(&bio, page, PAGE_SIZE, 0);
@@ -785,7 +785,7 @@ static void zram_sync_read(struct work_struct *work)
 	struct bio_vec bv;
 	struct bio bio;
 
-	bio_init(&bio, zw->zram->bdev_handle->bdev, &bv, 1, REQ_OP_READ);
+	bio_init(&bio, file_bdev(zw->zram->bdev_file), &bv, 1, REQ_OP_READ);
 	bio.bi_iter.bi_sector = zw->entry * (PAGE_SIZE >> 9);
 	__bio_add_page(&bio, zw->page, PAGE_SIZE, 0);
 	zw->error = submit_bio_wait(&bio);
@@ -2177,6 +2177,28 @@ ATTRIBUTE_GROUPS(zram_disk);
  */
 static int zram_add(void)
 {
+	struct queue_limits lim = {
+		.logical_block_size		= ZRAM_LOGICAL_BLOCK_SIZE,
+		/*
+		 * To ensure that we always get PAGE_SIZE aligned and
+		 * n*PAGE_SIZED sized I/O requests.
+		 */
+		.physical_block_size		= PAGE_SIZE,
+		.io_min				= PAGE_SIZE,
+		.io_opt				= PAGE_SIZE,
+		.max_hw_discard_sectors		= UINT_MAX,
+		/*
+		 * zram_bio_discard() will clear all logical blocks if logical
+		 * block size is identical with physical block size(PAGE_SIZE).
+		 * But if it is different, we will skip discarding some parts of
+		 * logical blocks in the part of the request range which isn't
+		 * aligned to physical block size.  So we can't ensure that all
+		 * discarded logical blocks are zeroed.
+		 */
+#if ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE
+		.max_write_zeroes_sectors	= UINT_MAX,
+#endif
+	};
 	struct zram *zram;
 	int ret, device_id;
 
@@ -2195,11 +2217,11 @@ static int zram_add(void)
 #endif
 
 	/* gendisk structure */
-	zram->disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!zram->disk) {
+	zram->disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(zram->disk)) {
 		pr_err("Error allocating disk structure for device %d\n",
 			device_id);
-		ret = -ENOMEM;
+		ret = PTR_ERR(zram->disk);
 		goto out_free_idr;
 	}
 
@@ -2216,29 +2238,6 @@ static int zram_add(void)
 	/* zram devices sort of resembles non-rotational disks */
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, zram->disk->queue);
 	blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, zram->disk->queue);
-
-	/*
-	 * To ensure that we always get PAGE_SIZE aligned
-	 * and n*PAGE_SIZED sized I/O requests.
-	 */
-	blk_queue_physical_block_size(zram->disk->queue, PAGE_SIZE);
-	blk_queue_logical_block_size(zram->disk->queue,
-					ZRAM_LOGICAL_BLOCK_SIZE);
-	blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
-	blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
-	blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX);
-
-	/*
-	 * zram_bio_discard() will clear all logical blocks if logical block
-	 * size is identical with physical block size(PAGE_SIZE). But if it is
-	 * different, we will skip discarding some parts of logical blocks in
-	 * the part of the request range which isn't aligned to physical block
-	 * size.  So we can't ensure that all discarded logical blocks are
-	 * zeroed.
-	 */
-	if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
-		blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);
-
 	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, zram->disk->queue);
 	ret = device_add_disk(NULL, zram->disk, zram_disk_groups);
 	if (ret)
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index 3b94d12f41b4..37bf29f34d26 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -132,7 +132,7 @@ struct zram {
 	spinlock_t wb_limit_lock;
 	bool wb_limit_enable;
 	u64 bd_wb_limit;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	unsigned long *bitmap;
 	unsigned long nr_pages;
 #endif
diff --git a/drivers/bluetooth/btmtkuart.c b/drivers/bluetooth/btmtkuart.c
index 203a000a84e3..3c84fcbda01a 100644
--- a/drivers/bluetooth/btmtkuart.c
+++ b/drivers/bluetooth/btmtkuart.c
@@ -383,8 +383,8 @@ static void btmtkuart_recv(struct hci_dev *hdev, const u8 *data, size_t count)
 	}
 }
 
-static int btmtkuart_receive_buf(struct serdev_device *serdev, const u8 *data,
-				 size_t count)
+static ssize_t btmtkuart_receive_buf(struct serdev_device *serdev,
+				     const u8 *data, size_t count)
 {
 	struct btmtkuart_dev *bdev = serdev_device_get_drvdata(serdev);
 
diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index b7c56be078f8..1d592ac413d1 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -1264,8 +1264,8 @@ static const struct h4_recv_pkt nxp_recv_pkts[] = {
 	{ NXP_RECV_FW_REQ_V3,   .recv = nxp_recv_fw_req_v3 },
 };
 
-static int btnxpuart_receive_buf(struct serdev_device *serdev, const u8 *data,
-				 size_t count)
+static ssize_t btnxpuart_receive_buf(struct serdev_device *serdev,
+				     const u8 *data, size_t count)
 {
 	struct btnxpuart_dev *nxpdev = serdev_device_get_drvdata(serdev);
 
diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
index fdb0fae88d1c..b40b32fa7f1c 100644
--- a/drivers/bluetooth/btqca.c
+++ b/drivers/bluetooth/btqca.c
@@ -152,7 +152,7 @@ static int qca_send_patch_config_cmd(struct hci_dev *hdev)
 	bt_dev_dbg(hdev, "QCA Patch config");
 
 	skb = __hci_cmd_sync_ev(hdev, EDL_PATCH_CMD_OPCODE, sizeof(cmd),
-				cmd, HCI_EV_VENDOR, HCI_INIT_TIMEOUT);
+				cmd, 0, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		err = PTR_ERR(skb);
 		bt_dev_err(hdev, "Sending QCA Patch config failed (%d)", err);
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 7835170b1d66..d31edad7a056 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -4796,10 +4796,8 @@ static struct usb_driver btusb_driver = {
 	.disable_hub_initiated_lpm = 1,
 
 #ifdef CONFIG_DEV_COREDUMP
-	.drvwrap = {
-		.driver = {
-			.coredump = btusb_coredump,
-		},
+	.driver = {
+		.coredump = btusb_coredump,
 	},
 #endif
 };
diff --git a/drivers/bluetooth/hci_bcm4377.c b/drivers/bluetooth/hci_bcm4377.c
index a61757835695..9a7243d5db71 100644
--- a/drivers/bluetooth/hci_bcm4377.c
+++ b/drivers/bluetooth/hci_bcm4377.c
@@ -1417,7 +1417,7 @@ static int bcm4377_check_bdaddr(struct bcm4377_data *bcm4377)
 
 	bda = (struct hci_rp_read_bd_addr *)skb->data;
 	if (!bcm4377_is_valid_bdaddr(bcm4377, &bda->bdaddr))
-		set_bit(HCI_QUIRK_INVALID_BDADDR, &bcm4377->hdev->quirks);
+		set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &bcm4377->hdev->quirks);
 
 	kfree_skb(skb);
 	return 0;
@@ -2368,7 +2368,6 @@ static int bcm4377_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	hdev->set_bdaddr = bcm4377_hci_set_bdaddr;
 	hdev->setup = bcm4377_hci_setup;
 
-	set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks);
 	if (bcm4377->hw->broken_mws_transport_config)
 		set_bit(HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG, &hdev->quirks);
 	if (bcm4377->hw->broken_ext_scan)
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 94b8c406f0c0..edd2a81b4d5e 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -7,6 +7,7 @@
  *
  *  Copyright (C) 2007 Texas Instruments, Inc.
  *  Copyright (c) 2010, 2012, 2018 The Linux Foundation. All rights reserved.
+ *  Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
  *
  *  Acknowledgements:
  *  This file is based on hci_ll.c, which was...
@@ -1806,13 +1807,12 @@ static int qca_power_on(struct hci_dev *hdev)
 
 static void hci_coredump_qca(struct hci_dev *hdev)
 {
+	int err;
 	static const u8 param[] = { 0x26 };
-	struct sk_buff *skb;
 
-	skb = __hci_cmd_sync(hdev, 0xfc0c, 1, param, HCI_CMD_TIMEOUT);
-	if (IS_ERR(skb))
-		bt_dev_err(hdev, "%s: trigger crash failed (%ld)", __func__, PTR_ERR(skb));
-	kfree_skb(skb);
+	err = __hci_cmd_send(hdev, 0xfc0c, 1, param);
+	if (err < 0)
+		bt_dev_err(hdev, "%s: trigger crash failed (%d)", __func__, err);
 }
 
 static int qca_get_data_path_id(struct hci_dev *hdev, __u8 *data_path_id)
@@ -1904,7 +1904,17 @@ retry:
 	case QCA_WCN6750:
 	case QCA_WCN6855:
 	case QCA_WCN7850:
-		set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks);
+
+		/* Set BDA quirk bit for reading BDA value from fwnode property
+		 * only if that property exist in DT.
+		 */
+		if (fwnode_property_present(dev_fwnode(hdev->dev.parent), "local-bd-address")) {
+			set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks);
+			bt_dev_info(hdev, "setting quirk bit to read BDA from fwnode later");
+		} else {
+			bt_dev_dbg(hdev, "local-bd-address` is not present in the devicetree so not setting quirk bit for BDA");
+		}
+
 		hci_set_aosp_capable(hdev);
 
 		ret = qca_read_soc_version(hdev, &ver, soc_type);
diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c
index f16fd79bc02b..39c8b567da3c 100644
--- a/drivers/bluetooth/hci_serdev.c
+++ b/drivers/bluetooth/hci_serdev.c
@@ -271,8 +271,8 @@ static void hci_uart_write_wakeup(struct serdev_device *serdev)
  *
  * Return: number of processed bytes
  */
-static int hci_uart_receive_buf(struct serdev_device *serdev, const u8 *data,
-				   size_t count)
+static ssize_t hci_uart_receive_buf(struct serdev_device *serdev,
+				    const u8 *data, size_t count)
 {
 	struct hci_uart *hu = serdev_device_get_drvdata(serdev);
 
diff --git a/drivers/bus/imx-weim.c b/drivers/bus/imx-weim.c
index 6b5da73c8541..837bf9d51c6e 100644
--- a/drivers/bus/imx-weim.c
+++ b/drivers/bus/imx-weim.c
@@ -120,7 +120,7 @@ static int imx_weim_gpr_setup(struct platform_device *pdev)
 		i++;
 	}
 
-	if (i == 0 || i % 4)
+	if (i == 0)
 		goto err;
 
 	for (i = 0; i < ARRAY_SIZE(gprvals); i++) {
diff --git a/drivers/bus/mhi/ep/internal.h b/drivers/bus/mhi/ep/internal.h
index a2125fa5fe2f..577965f95fda 100644
--- a/drivers/bus/mhi/ep/internal.h
+++ b/drivers/bus/mhi/ep/internal.h
@@ -126,6 +126,7 @@ struct mhi_ep_ring {
 	union mhi_ep_ring_ctx *ring_ctx;
 	struct mhi_ring_element *ring_cache;
 	enum mhi_ep_ring_type type;
+	struct delayed_work intmodt_work;
 	u64 rbase;
 	size_t rd_offset;
 	size_t wr_offset;
@@ -135,7 +136,9 @@ struct mhi_ep_ring {
 	u32 ch_id;
 	u32 er_index;
 	u32 irq_vector;
+	u32 intmodt;
 	bool started;
+	bool irq_pending;
 };
 
 struct mhi_ep_cmd {
@@ -159,6 +162,7 @@ struct mhi_ep_chan {
 	void (*xfer_cb)(struct mhi_ep_device *mhi_dev, struct mhi_result *result);
 	enum mhi_ch_state state;
 	enum dma_data_direction dir;
+	size_t rd_offset;
 	u64 tre_loc;
 	u32 tre_size;
 	u32 tre_bytes_left;
diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index 600881808982..65fc1d738bec 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -54,11 +54,27 @@ static int mhi_ep_send_event(struct mhi_ep_cntrl *mhi_cntrl, u32 ring_idx,
 	mutex_unlock(&mhi_cntrl->event_lock);
 
 	/*
-	 * Raise IRQ to host only if the BEI flag is not set in TRE. Host might
-	 * set this flag for interrupt moderation as per MHI protocol.
+	 * As per the MHI specification, section 4.3, Interrupt moderation:
+	 *
+	 * 1. If BEI flag is not set, cancel any pending intmodt work if started
+	 * for the event ring and raise IRQ immediately.
+	 *
+	 * 2. If both BEI and intmodt are set, and if no IRQ is pending for the
+	 * same event ring, start the IRQ delayed work as per the value of
+	 * intmodt. If previous IRQ is pending, then do nothing as the pending
+	 * IRQ is enough for the host to process the current event ring element.
+	 *
+	 * 3. If BEI is set and intmodt is not set, no need to raise IRQ.
 	 */
-	if (!bei)
+	if (!bei) {
+		if (READ_ONCE(ring->irq_pending))
+			cancel_delayed_work(&ring->intmodt_work);
+
 		mhi_cntrl->raise_irq(mhi_cntrl, ring->irq_vector);
+	} else if (ring->intmodt && !READ_ONCE(ring->irq_pending)) {
+		WRITE_ONCE(ring->irq_pending, true);
+		schedule_delayed_work(&ring->intmodt_work, msecs_to_jiffies(ring->intmodt));
+	}
 
 	return 0;
 
@@ -71,45 +87,77 @@ err_unlock:
 static int mhi_ep_send_completion_event(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_ring *ring,
 					struct mhi_ring_element *tre, u32 len, enum mhi_ev_ccs code)
 {
-	struct mhi_ring_element event = {};
+	struct mhi_ring_element *event;
+	int ret;
+
+	event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL | GFP_DMA);
+	if (!event)
+		return -ENOMEM;
 
-	event.ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(*tre));
-	event.dword[0] = MHI_TRE_EV_DWORD0(code, len);
-	event.dword[1] = MHI_TRE_EV_DWORD1(ring->ch_id, MHI_PKT_TYPE_TX_EVENT);
+	event->ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(*tre));
+	event->dword[0] = MHI_TRE_EV_DWORD0(code, len);
+	event->dword[1] = MHI_TRE_EV_DWORD1(ring->ch_id, MHI_PKT_TYPE_TX_EVENT);
 
-	return mhi_ep_send_event(mhi_cntrl, ring->er_index, &event, MHI_TRE_DATA_GET_BEI(tre));
+	ret = mhi_ep_send_event(mhi_cntrl, ring->er_index, event, MHI_TRE_DATA_GET_BEI(tre));
+	kmem_cache_free(mhi_cntrl->ev_ring_el_cache, event);
+
+	return ret;
 }
 
 int mhi_ep_send_state_change_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_state state)
 {
-	struct mhi_ring_element event = {};
+	struct mhi_ring_element *event;
+	int ret;
 
-	event.dword[0] = MHI_SC_EV_DWORD0(state);
-	event.dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_STATE_CHANGE_EVENT);
+	event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL | GFP_DMA);
+	if (!event)
+		return -ENOMEM;
 
-	return mhi_ep_send_event(mhi_cntrl, 0, &event, 0);
+	event->dword[0] = MHI_SC_EV_DWORD0(state);
+	event->dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_STATE_CHANGE_EVENT);
+
+	ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0);
+	kmem_cache_free(mhi_cntrl->ev_ring_el_cache, event);
+
+	return ret;
 }
 
 int mhi_ep_send_ee_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ee_type exec_env)
 {
-	struct mhi_ring_element event = {};
+	struct mhi_ring_element *event;
+	int ret;
 
-	event.dword[0] = MHI_EE_EV_DWORD0(exec_env);
-	event.dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_EE_EVENT);
+	event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL | GFP_DMA);
+	if (!event)
+		return -ENOMEM;
+
+	event->dword[0] = MHI_EE_EV_DWORD0(exec_env);
+	event->dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_EE_EVENT);
 
-	return mhi_ep_send_event(mhi_cntrl, 0, &event, 0);
+	ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0);
+	kmem_cache_free(mhi_cntrl->ev_ring_el_cache, event);
+
+	return ret;
 }
 
 static int mhi_ep_send_cmd_comp_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ev_ccs code)
 {
 	struct mhi_ep_ring *ring = &mhi_cntrl->mhi_cmd->ring;
-	struct mhi_ring_element event = {};
+	struct mhi_ring_element *event;
+	int ret;
+
+	event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL | GFP_DMA);
+	if (!event)
+		return -ENOMEM;
+
+	event->ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(struct mhi_ring_element));
+	event->dword[0] = MHI_CC_EV_DWORD0(code);
+	event->dword[1] = MHI_CC_EV_DWORD1(MHI_PKT_TYPE_CMD_COMPLETION_EVENT);
 
-	event.ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(struct mhi_ring_element));
-	event.dword[0] = MHI_CC_EV_DWORD0(code);
-	event.dword[1] = MHI_CC_EV_DWORD1(MHI_PKT_TYPE_CMD_COMPLETION_EVENT);
+	ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0);
+	kmem_cache_free(mhi_cntrl->ev_ring_el_cache, event);
 
-	return mhi_ep_send_event(mhi_cntrl, 0, &event, 0);
+	return ret;
 }
 
 static int mhi_ep_process_cmd_ring(struct mhi_ep_ring *ring, struct mhi_ring_element *el)
@@ -151,6 +199,8 @@ static int mhi_ep_process_cmd_ring(struct mhi_ep_ring *ring, struct mhi_ring_ele
 
 				goto err_unlock;
 			}
+
+			mhi_chan->rd_offset = ch_ring->rd_offset;
 		}
 
 		/* Set channel state to RUNNING */
@@ -280,22 +330,85 @@ bool mhi_ep_queue_is_empty(struct mhi_ep_device *mhi_dev, enum dma_data_directio
 	struct mhi_ep_cntrl *mhi_cntrl = mhi_dev->mhi_cntrl;
 	struct mhi_ep_ring *ring = &mhi_cntrl->mhi_chan[mhi_chan->chan].ring;
 
-	return !!(ring->rd_offset == ring->wr_offset);
+	return !!(mhi_chan->rd_offset == ring->wr_offset);
 }
 EXPORT_SYMBOL_GPL(mhi_ep_queue_is_empty);
 
+static void mhi_ep_read_completion(struct mhi_ep_buf_info *buf_info)
+{
+	struct mhi_ep_device *mhi_dev = buf_info->mhi_dev;
+	struct mhi_ep_cntrl *mhi_cntrl = mhi_dev->mhi_cntrl;
+	struct mhi_ep_chan *mhi_chan = mhi_dev->ul_chan;
+	struct mhi_ep_ring *ring = &mhi_cntrl->mhi_chan[mhi_chan->chan].ring;
+	struct mhi_ring_element *el = &ring->ring_cache[ring->rd_offset];
+	struct mhi_result result = {};
+	int ret;
+
+	if (mhi_chan->xfer_cb) {
+		result.buf_addr = buf_info->cb_buf;
+		result.dir = mhi_chan->dir;
+		result.bytes_xferd = buf_info->size;
+
+		mhi_chan->xfer_cb(mhi_dev, &result);
+	}
+
+	/*
+	 * The host will split the data packet into multiple TREs if it can't fit
+	 * the packet in a single TRE. In that case, CHAIN flag will be set by the
+	 * host for all TREs except the last one.
+	 */
+	if (buf_info->code != MHI_EV_CC_OVERFLOW) {
+		if (MHI_TRE_DATA_GET_CHAIN(el)) {
+			/*
+			 * IEOB (Interrupt on End of Block) flag will be set by the host if
+			 * it expects the completion event for all TREs of a TD.
+			 */
+			if (MHI_TRE_DATA_GET_IEOB(el)) {
+				ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el,
+							     MHI_TRE_DATA_GET_LEN(el),
+							     MHI_EV_CC_EOB);
+				if (ret < 0) {
+					dev_err(&mhi_chan->mhi_dev->dev,
+						"Error sending transfer compl. event\n");
+					goto err_free_tre_buf;
+				}
+			}
+		} else {
+			/*
+			 * IEOT (Interrupt on End of Transfer) flag will be set by the host
+			 * for the last TRE of the TD and expects the completion event for
+			 * the same.
+			 */
+			if (MHI_TRE_DATA_GET_IEOT(el)) {
+				ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el,
+							     MHI_TRE_DATA_GET_LEN(el),
+							     MHI_EV_CC_EOT);
+				if (ret < 0) {
+					dev_err(&mhi_chan->mhi_dev->dev,
+						"Error sending transfer compl. event\n");
+					goto err_free_tre_buf;
+				}
+			}
+		}
+	}
+
+	mhi_ep_ring_inc_index(ring);
+
+err_free_tre_buf:
+	kmem_cache_free(mhi_cntrl->tre_buf_cache, buf_info->cb_buf);
+}
+
 static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl,
-				struct mhi_ep_ring *ring,
-				struct mhi_result *result,
-				u32 len)
+			       struct mhi_ep_ring *ring)
 {
 	struct mhi_ep_chan *mhi_chan = &mhi_cntrl->mhi_chan[ring->ch_id];
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
 	size_t tr_len, read_offset, write_offset;
+	struct mhi_ep_buf_info buf_info = {};
+	u32 len = MHI_EP_DEFAULT_MTU;
 	struct mhi_ring_element *el;
 	bool tr_done = false;
-	void *write_addr;
-	u64 read_addr;
+	void *buf_addr;
 	u32 buf_left;
 	int ret;
 
@@ -308,7 +421,7 @@ static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl,
 			return -ENODEV;
 		}
 
-		el = &ring->ring_cache[ring->rd_offset];
+		el = &ring->ring_cache[mhi_chan->rd_offset];
 
 		/* Check if there is data pending to be read from previous read operation */
 		if (mhi_chan->tre_bytes_left) {
@@ -324,81 +437,51 @@ static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl,
 
 		read_offset = mhi_chan->tre_size - mhi_chan->tre_bytes_left;
 		write_offset = len - buf_left;
-		read_addr = mhi_chan->tre_loc + read_offset;
-		write_addr = result->buf_addr + write_offset;
+
+		buf_addr = kmem_cache_zalloc(mhi_cntrl->tre_buf_cache, GFP_KERNEL | GFP_DMA);
+		if (!buf_addr)
+			return -ENOMEM;
+
+		buf_info.host_addr = mhi_chan->tre_loc + read_offset;
+		buf_info.dev_addr = buf_addr + write_offset;
+		buf_info.size = tr_len;
+		buf_info.cb = mhi_ep_read_completion;
+		buf_info.cb_buf = buf_addr;
+		buf_info.mhi_dev = mhi_chan->mhi_dev;
+
+		if (mhi_chan->tre_bytes_left - tr_len)
+			buf_info.code = MHI_EV_CC_OVERFLOW;
 
 		dev_dbg(dev, "Reading %zd bytes from channel (%u)\n", tr_len, ring->ch_id);
-		ret = mhi_cntrl->read_from_host(mhi_cntrl, read_addr, write_addr, tr_len);
+		ret = mhi_cntrl->read_async(mhi_cntrl, &buf_info);
 		if (ret < 0) {
 			dev_err(&mhi_chan->mhi_dev->dev, "Error reading from channel\n");
-			return ret;
+			goto err_free_buf_addr;
 		}
 
 		buf_left -= tr_len;
 		mhi_chan->tre_bytes_left -= tr_len;
 
-		/*
-		 * Once the TRE (Transfer Ring Element) of a TD (Transfer Descriptor) has been
-		 * read completely:
-		 *
-		 * 1. Send completion event to the host based on the flags set in TRE.
-		 * 2. Increment the local read offset of the transfer ring.
-		 */
 		if (!mhi_chan->tre_bytes_left) {
-			/*
-			 * The host will split the data packet into multiple TREs if it can't fit
-			 * the packet in a single TRE. In that case, CHAIN flag will be set by the
-			 * host for all TREs except the last one.
-			 */
-			if (MHI_TRE_DATA_GET_CHAIN(el)) {
-				/*
-				 * IEOB (Interrupt on End of Block) flag will be set by the host if
-				 * it expects the completion event for all TREs of a TD.
-				 */
-				if (MHI_TRE_DATA_GET_IEOB(el)) {
-					ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el,
-								     MHI_TRE_DATA_GET_LEN(el),
-								     MHI_EV_CC_EOB);
-					if (ret < 0) {
-						dev_err(&mhi_chan->mhi_dev->dev,
-							"Error sending transfer compl. event\n");
-						return ret;
-					}
-				}
-			} else {
-				/*
-				 * IEOT (Interrupt on End of Transfer) flag will be set by the host
-				 * for the last TRE of the TD and expects the completion event for
-				 * the same.
-				 */
-				if (MHI_TRE_DATA_GET_IEOT(el)) {
-					ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el,
-								     MHI_TRE_DATA_GET_LEN(el),
-								     MHI_EV_CC_EOT);
-					if (ret < 0) {
-						dev_err(&mhi_chan->mhi_dev->dev,
-							"Error sending transfer compl. event\n");
-						return ret;
-					}
-				}
-
+			if (MHI_TRE_DATA_GET_IEOT(el))
 				tr_done = true;
-			}
 
-			mhi_ep_ring_inc_index(ring);
+			mhi_chan->rd_offset = (mhi_chan->rd_offset + 1) % ring->ring_size;
 		}
-
-		result->bytes_xferd += tr_len;
 	} while (buf_left && !tr_done);
 
 	return 0;
+
+err_free_buf_addr:
+	kmem_cache_free(mhi_cntrl->tre_buf_cache, buf_addr);
+
+	return ret;
 }
 
-static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring, struct mhi_ring_element *el)
+static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring)
 {
 	struct mhi_ep_cntrl *mhi_cntrl = ring->mhi_cntrl;
 	struct mhi_result result = {};
-	u32 len = MHI_EP_DEFAULT_MTU;
 	struct mhi_ep_chan *mhi_chan;
 	int ret;
 
@@ -419,44 +502,59 @@ static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring, struct mhi_ring_elem
 		mhi_chan->xfer_cb(mhi_chan->mhi_dev, &result);
 	} else {
 		/* UL channel */
-		result.buf_addr = kzalloc(len, GFP_KERNEL);
-		if (!result.buf_addr)
-			return -ENOMEM;
-
 		do {
-			ret = mhi_ep_read_channel(mhi_cntrl, ring, &result, len);
+			ret = mhi_ep_read_channel(mhi_cntrl, ring);
 			if (ret < 0) {
 				dev_err(&mhi_chan->mhi_dev->dev, "Failed to read channel\n");
-				kfree(result.buf_addr);
 				return ret;
 			}
 
-			result.dir = mhi_chan->dir;
-			mhi_chan->xfer_cb(mhi_chan->mhi_dev, &result);
-			result.bytes_xferd = 0;
-			memset(result.buf_addr, 0, len);
-
 			/* Read until the ring becomes empty */
 		} while (!mhi_ep_queue_is_empty(mhi_chan->mhi_dev, DMA_TO_DEVICE));
-
-		kfree(result.buf_addr);
 	}
 
 	return 0;
 }
 
+static void mhi_ep_skb_completion(struct mhi_ep_buf_info *buf_info)
+{
+	struct mhi_ep_device *mhi_dev = buf_info->mhi_dev;
+	struct mhi_ep_cntrl *mhi_cntrl = mhi_dev->mhi_cntrl;
+	struct mhi_ep_chan *mhi_chan = mhi_dev->dl_chan;
+	struct mhi_ep_ring *ring = &mhi_cntrl->mhi_chan[mhi_chan->chan].ring;
+	struct mhi_ring_element *el = &ring->ring_cache[ring->rd_offset];
+	struct device *dev = &mhi_dev->dev;
+	struct mhi_result result = {};
+	int ret;
+
+	if (mhi_chan->xfer_cb) {
+		result.buf_addr = buf_info->cb_buf;
+		result.dir = mhi_chan->dir;
+		result.bytes_xferd = buf_info->size;
+
+		mhi_chan->xfer_cb(mhi_dev, &result);
+	}
+
+	ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el, buf_info->size,
+					   buf_info->code);
+	if (ret) {
+		dev_err(dev, "Error sending transfer completion event\n");
+		return;
+	}
+
+	mhi_ep_ring_inc_index(ring);
+}
+
 /* TODO: Handle partially formed TDs */
 int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb)
 {
 	struct mhi_ep_cntrl *mhi_cntrl = mhi_dev->mhi_cntrl;
 	struct mhi_ep_chan *mhi_chan = mhi_dev->dl_chan;
 	struct device *dev = &mhi_chan->mhi_dev->dev;
+	struct mhi_ep_buf_info buf_info = {};
 	struct mhi_ring_element *el;
 	u32 buf_left, read_offset;
 	struct mhi_ep_ring *ring;
-	enum mhi_ev_ccs code;
-	void *read_addr;
-	u64 write_addr;
 	size_t tr_len;
 	u32 tre_len;
 	int ret;
@@ -480,40 +578,44 @@ int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb)
 			goto err_exit;
 		}
 
-		el = &ring->ring_cache[ring->rd_offset];
+		el = &ring->ring_cache[mhi_chan->rd_offset];
 		tre_len = MHI_TRE_DATA_GET_LEN(el);
 
 		tr_len = min(buf_left, tre_len);
 		read_offset = skb->len - buf_left;
-		read_addr = skb->data + read_offset;
-		write_addr = MHI_TRE_DATA_GET_PTR(el);
 
-		dev_dbg(dev, "Writing %zd bytes to channel (%u)\n", tr_len, ring->ch_id);
-		ret = mhi_cntrl->write_to_host(mhi_cntrl, read_addr, write_addr, tr_len);
-		if (ret < 0) {
-			dev_err(dev, "Error writing to the channel\n");
-			goto err_exit;
-		}
+		buf_info.dev_addr = skb->data + read_offset;
+		buf_info.host_addr = MHI_TRE_DATA_GET_PTR(el);
+		buf_info.size = tr_len;
+		buf_info.cb = mhi_ep_skb_completion;
+		buf_info.cb_buf = skb;
+		buf_info.mhi_dev = mhi_dev;
 
-		buf_left -= tr_len;
 		/*
 		 * For all TREs queued by the host for DL channel, only the EOT flag will be set.
 		 * If the packet doesn't fit into a single TRE, send the OVERFLOW event to
 		 * the host so that the host can adjust the packet boundary to next TREs. Else send
 		 * the EOT event to the host indicating the packet boundary.
 		 */
-		if (buf_left)
-			code = MHI_EV_CC_OVERFLOW;
+		if (buf_left - tr_len)
+			buf_info.code = MHI_EV_CC_OVERFLOW;
 		else
-			code = MHI_EV_CC_EOT;
+			buf_info.code = MHI_EV_CC_EOT;
 
-		ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el, tr_len, code);
-		if (ret) {
-			dev_err(dev, "Error sending transfer completion event\n");
+		dev_dbg(dev, "Writing %zd bytes to channel (%u)\n", tr_len, ring->ch_id);
+		ret = mhi_cntrl->write_async(mhi_cntrl, &buf_info);
+		if (ret < 0) {
+			dev_err(dev, "Error writing to the channel\n");
 			goto err_exit;
 		}
 
-		mhi_ep_ring_inc_index(ring);
+		buf_left -= tr_len;
+
+		/*
+		 * Update the read offset cached in mhi_chan. Actual read offset
+		 * will be updated by the completion handler.
+		 */
+		mhi_chan->rd_offset = (mhi_chan->rd_offset + 1) % ring->ring_size;
 	} while (buf_left);
 
 	mutex_unlock(&mhi_chan->lock);
@@ -714,7 +816,6 @@ static void mhi_ep_ch_ring_worker(struct work_struct *work)
 	struct mhi_ep_cntrl *mhi_cntrl = container_of(work, struct mhi_ep_cntrl, ch_ring_work);
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
 	struct mhi_ep_ring_item *itr, *tmp;
-	struct mhi_ring_element *el;
 	struct mhi_ep_ring *ring;
 	struct mhi_ep_chan *chan;
 	unsigned long flags;
@@ -748,31 +849,29 @@ static void mhi_ep_ch_ring_worker(struct work_struct *work)
 		if (ret) {
 			dev_err(dev, "Error updating write offset for ring\n");
 			mutex_unlock(&chan->lock);
-			kfree(itr);
+			kmem_cache_free(mhi_cntrl->ring_item_cache, itr);
 			continue;
 		}
 
 		/* Sanity check to make sure there are elements in the ring */
-		if (ring->rd_offset == ring->wr_offset) {
+		if (chan->rd_offset == ring->wr_offset) {
 			mutex_unlock(&chan->lock);
-			kfree(itr);
+			kmem_cache_free(mhi_cntrl->ring_item_cache, itr);
 			continue;
 		}
 
-		el = &ring->ring_cache[ring->rd_offset];
-
 		dev_dbg(dev, "Processing the ring for channel (%u)\n", ring->ch_id);
-		ret = mhi_ep_process_ch_ring(ring, el);
+		ret = mhi_ep_process_ch_ring(ring);
 		if (ret) {
 			dev_err(dev, "Error processing ring for channel (%u): %d\n",
 				ring->ch_id, ret);
 			mutex_unlock(&chan->lock);
-			kfree(itr);
+			kmem_cache_free(mhi_cntrl->ring_item_cache, itr);
 			continue;
 		}
 
 		mutex_unlock(&chan->lock);
-		kfree(itr);
+		kmem_cache_free(mhi_cntrl->ring_item_cache, itr);
 	}
 }
 
@@ -828,7 +927,7 @@ static void mhi_ep_queue_channel_db(struct mhi_ep_cntrl *mhi_cntrl, unsigned lon
 		u32 ch_id = ch_idx + i;
 
 		ring = &mhi_cntrl->mhi_chan[ch_id].ring;
-		item = kzalloc(sizeof(*item), GFP_ATOMIC);
+		item = kmem_cache_zalloc(mhi_cntrl->ring_item_cache, GFP_ATOMIC);
 		if (!item)
 			return;
 
@@ -1365,6 +1464,10 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 	if (!mhi_cntrl || !mhi_cntrl->cntrl_dev || !mhi_cntrl->mmio || !mhi_cntrl->irq)
 		return -EINVAL;
 
+	if (!mhi_cntrl->read_sync || !mhi_cntrl->write_sync ||
+	    !mhi_cntrl->read_async || !mhi_cntrl->write_async)
+		return -EINVAL;
+
 	ret = mhi_ep_chan_init(mhi_cntrl, config);
 	if (ret)
 		return ret;
@@ -1375,6 +1478,29 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 		goto err_free_ch;
 	}
 
+	mhi_cntrl->ev_ring_el_cache = kmem_cache_create("mhi_ep_event_ring_el",
+							sizeof(struct mhi_ring_element), 0,
+							SLAB_CACHE_DMA, NULL);
+	if (!mhi_cntrl->ev_ring_el_cache) {
+		ret = -ENOMEM;
+		goto err_free_cmd;
+	}
+
+	mhi_cntrl->tre_buf_cache = kmem_cache_create("mhi_ep_tre_buf", MHI_EP_DEFAULT_MTU, 0,
+						      SLAB_CACHE_DMA, NULL);
+	if (!mhi_cntrl->tre_buf_cache) {
+		ret = -ENOMEM;
+		goto err_destroy_ev_ring_el_cache;
+	}
+
+	mhi_cntrl->ring_item_cache = kmem_cache_create("mhi_ep_ring_item",
+							sizeof(struct mhi_ep_ring_item), 0,
+							0, NULL);
+	if (!mhi_cntrl->ev_ring_el_cache) {
+		ret = -ENOMEM;
+		goto err_destroy_tre_buf_cache;
+	}
+
 	INIT_WORK(&mhi_cntrl->state_work, mhi_ep_state_worker);
 	INIT_WORK(&mhi_cntrl->reset_work, mhi_ep_reset_worker);
 	INIT_WORK(&mhi_cntrl->cmd_ring_work, mhi_ep_cmd_ring_worker);
@@ -1383,7 +1509,7 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 	mhi_cntrl->wq = alloc_workqueue("mhi_ep_wq", 0, 0);
 	if (!mhi_cntrl->wq) {
 		ret = -ENOMEM;
-		goto err_free_cmd;
+		goto err_destroy_ring_item_cache;
 	}
 
 	INIT_LIST_HEAD(&mhi_cntrl->st_transition_list);
@@ -1442,6 +1568,12 @@ err_ida_free:
 	ida_free(&mhi_ep_cntrl_ida, mhi_cntrl->index);
 err_destroy_wq:
 	destroy_workqueue(mhi_cntrl->wq);
+err_destroy_ring_item_cache:
+	kmem_cache_destroy(mhi_cntrl->ring_item_cache);
+err_destroy_ev_ring_el_cache:
+	kmem_cache_destroy(mhi_cntrl->ev_ring_el_cache);
+err_destroy_tre_buf_cache:
+	kmem_cache_destroy(mhi_cntrl->tre_buf_cache);
 err_free_cmd:
 	kfree(mhi_cntrl->mhi_cmd);
 err_free_ch:
@@ -1463,6 +1595,9 @@ void mhi_ep_unregister_controller(struct mhi_ep_cntrl *mhi_cntrl)
 
 	free_irq(mhi_cntrl->irq, mhi_cntrl);
 
+	kmem_cache_destroy(mhi_cntrl->tre_buf_cache);
+	kmem_cache_destroy(mhi_cntrl->ev_ring_el_cache);
+	kmem_cache_destroy(mhi_cntrl->ring_item_cache);
 	kfree(mhi_cntrl->mhi_cmd);
 	kfree(mhi_cntrl->mhi_chan);
 
diff --git a/drivers/bus/mhi/ep/ring.c b/drivers/bus/mhi/ep/ring.c
index 115518ec76a4..aeb53b2c34a8 100644
--- a/drivers/bus/mhi/ep/ring.c
+++ b/drivers/bus/mhi/ep/ring.c
@@ -30,7 +30,8 @@ static int __mhi_ep_cache_ring(struct mhi_ep_ring *ring, size_t end)
 {
 	struct mhi_ep_cntrl *mhi_cntrl = ring->mhi_cntrl;
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
-	size_t start, copy_size;
+	struct mhi_ep_buf_info buf_info = {};
+	size_t start;
 	int ret;
 
 	/* Don't proceed in the case of event ring. This happens during mhi_ep_ring_start(). */
@@ -43,30 +44,34 @@ static int __mhi_ep_cache_ring(struct mhi_ep_ring *ring, size_t end)
 
 	start = ring->wr_offset;
 	if (start < end) {
-		copy_size = (end - start) * sizeof(struct mhi_ring_element);
-		ret = mhi_cntrl->read_from_host(mhi_cntrl, ring->rbase +
-						(start * sizeof(struct mhi_ring_element)),
-						&ring->ring_cache[start], copy_size);
+		buf_info.size = (end - start) * sizeof(struct mhi_ring_element);
+		buf_info.host_addr = ring->rbase + (start * sizeof(struct mhi_ring_element));
+		buf_info.dev_addr = &ring->ring_cache[start];
+
+		ret = mhi_cntrl->read_sync(mhi_cntrl, &buf_info);
 		if (ret < 0)
 			return ret;
 	} else {
-		copy_size = (ring->ring_size - start) * sizeof(struct mhi_ring_element);
-		ret = mhi_cntrl->read_from_host(mhi_cntrl, ring->rbase +
-						(start * sizeof(struct mhi_ring_element)),
-						&ring->ring_cache[start], copy_size);
+		buf_info.size = (ring->ring_size - start) * sizeof(struct mhi_ring_element);
+		buf_info.host_addr = ring->rbase + (start * sizeof(struct mhi_ring_element));
+		buf_info.dev_addr = &ring->ring_cache[start];
+
+		ret = mhi_cntrl->read_sync(mhi_cntrl, &buf_info);
 		if (ret < 0)
 			return ret;
 
 		if (end) {
-			ret = mhi_cntrl->read_from_host(mhi_cntrl, ring->rbase,
-							&ring->ring_cache[0],
-							end * sizeof(struct mhi_ring_element));
+			buf_info.host_addr = ring->rbase;
+			buf_info.dev_addr = &ring->ring_cache[0];
+			buf_info.size = end * sizeof(struct mhi_ring_element);
+
+			ret = mhi_cntrl->read_sync(mhi_cntrl, &buf_info);
 			if (ret < 0)
 				return ret;
 		}
 	}
 
-	dev_dbg(dev, "Cached ring: start %zu end %zu size %zu\n", start, end, copy_size);
+	dev_dbg(dev, "Cached ring: start %zu end %zu size %zu\n", start, end, buf_info.size);
 
 	return 0;
 }
@@ -102,6 +107,7 @@ int mhi_ep_ring_add_element(struct mhi_ep_ring *ring, struct mhi_ring_element *e
 {
 	struct mhi_ep_cntrl *mhi_cntrl = ring->mhi_cntrl;
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+	struct mhi_ep_buf_info buf_info = {};
 	size_t old_offset = 0;
 	u32 num_free_elem;
 	__le64 rp;
@@ -133,12 +139,11 @@ int mhi_ep_ring_add_element(struct mhi_ep_ring *ring, struct mhi_ring_element *e
 	rp = cpu_to_le64(ring->rd_offset * sizeof(*el) + ring->rbase);
 	memcpy_toio((void __iomem *) &ring->ring_ctx->generic.rp, &rp, sizeof(u64));
 
-	ret = mhi_cntrl->write_to_host(mhi_cntrl, el, ring->rbase + (old_offset * sizeof(*el)),
-				       sizeof(*el));
-	if (ret < 0)
-		return ret;
+	buf_info.host_addr = ring->rbase + (old_offset * sizeof(*el));
+	buf_info.dev_addr = el;
+	buf_info.size = sizeof(*el);
 
-	return 0;
+	return mhi_cntrl->write_sync(mhi_cntrl, &buf_info);
 }
 
 void mhi_ep_ring_init(struct mhi_ep_ring *ring, enum mhi_ep_ring_type type, u32 id)
@@ -157,6 +162,15 @@ void mhi_ep_ring_init(struct mhi_ep_ring *ring, enum mhi_ep_ring_type type, u32
 	}
 }
 
+static void mhi_ep_raise_irq(struct work_struct *work)
+{
+	struct mhi_ep_ring *ring = container_of(work, struct mhi_ep_ring, intmodt_work.work);
+	struct mhi_ep_cntrl *mhi_cntrl = ring->mhi_cntrl;
+
+	mhi_cntrl->raise_irq(mhi_cntrl, ring->irq_vector);
+	WRITE_ONCE(ring->irq_pending, false);
+}
+
 int mhi_ep_ring_start(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_ring *ring,
 			union mhi_ep_ring_ctx *ctx)
 {
@@ -173,8 +187,13 @@ int mhi_ep_ring_start(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_ring *ring,
 	if (ring->type == RING_TYPE_CH)
 		ring->er_index = le32_to_cpu(ring->ring_ctx->ch.erindex);
 
-	if (ring->type == RING_TYPE_ER)
+	if (ring->type == RING_TYPE_ER) {
 		ring->irq_vector = le32_to_cpu(ring->ring_ctx->ev.msivec);
+		ring->intmodt = FIELD_GET(EV_CTX_INTMODT_MASK,
+					  le32_to_cpu(ring->ring_ctx->ev.intmod));
+
+		INIT_DELAYED_WORK(&ring->intmodt_work, mhi_ep_raise_irq);
+	}
 
 	/* During ring init, both rp and wp are equal */
 	memcpy_fromio(&val, (void __iomem *) &ring->ring_ctx->generic.rp, sizeof(u64));
@@ -201,6 +220,9 @@ int mhi_ep_ring_start(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_ring *ring,
 
 void mhi_ep_ring_reset(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_ring *ring)
 {
+	if (ring->type == RING_TYPE_ER)
+		cancel_delayed_work_sync(&ring->intmodt_work);
+
 	ring->started = false;
 	kfree(ring->ring_cache);
 	ring->ring_cache = NULL;
diff --git a/drivers/bus/mhi/host/init.c b/drivers/bus/mhi/host/init.c
index f78aefd2d7a3..65ceac1837f9 100644
--- a/drivers/bus/mhi/host/init.c
+++ b/drivers/bus/mhi/host/init.c
@@ -881,6 +881,7 @@ static int parse_config(struct mhi_controller *mhi_cntrl,
 	if (!mhi_cntrl->timeout_ms)
 		mhi_cntrl->timeout_ms = MHI_TIMEOUT_MS;
 
+	mhi_cntrl->ready_timeout_ms = config->ready_timeout_ms;
 	mhi_cntrl->bounce_buf = config->use_bounce_buf;
 	mhi_cntrl->buffer_len = config->buf_len;
 	if (!mhi_cntrl->buffer_len)
diff --git a/drivers/bus/mhi/host/internal.h b/drivers/bus/mhi/host/internal.h
index 2e139e76de4c..30ac415a3000 100644
--- a/drivers/bus/mhi/host/internal.h
+++ b/drivers/bus/mhi/host/internal.h
@@ -321,7 +321,7 @@ int __must_check mhi_read_reg_field(struct mhi_controller *mhi_cntrl,
 				    u32 *out);
 int __must_check mhi_poll_reg_field(struct mhi_controller *mhi_cntrl,
 				    void __iomem *base, u32 offset, u32 mask,
-				    u32 val, u32 delayus);
+				    u32 val, u32 delayus, u32 timeout_ms);
 void mhi_write_reg(struct mhi_controller *mhi_cntrl, void __iomem *base,
 		   u32 offset, u32 val);
 int __must_check mhi_write_reg_field(struct mhi_controller *mhi_cntrl,
diff --git a/drivers/bus/mhi/host/main.c b/drivers/bus/mhi/host/main.c
index dcf627b36e82..abb561db9ae1 100644
--- a/drivers/bus/mhi/host/main.c
+++ b/drivers/bus/mhi/host/main.c
@@ -40,10 +40,11 @@ int __must_check mhi_read_reg_field(struct mhi_controller *mhi_cntrl,
 
 int __must_check mhi_poll_reg_field(struct mhi_controller *mhi_cntrl,
 				    void __iomem *base, u32 offset,
-				    u32 mask, u32 val, u32 delayus)
+				    u32 mask, u32 val, u32 delayus,
+				    u32 timeout_ms)
 {
 	int ret;
-	u32 out, retry = (mhi_cntrl->timeout_ms * 1000) / delayus;
+	u32 out, retry = (timeout_ms * 1000) / delayus;
 
 	while (retry--) {
 		ret = mhi_read_reg_field(mhi_cntrl, base, offset, mask, &out);
@@ -268,7 +269,8 @@ static void mhi_del_ring_element(struct mhi_controller *mhi_cntrl,
 
 static bool is_valid_ring_ptr(struct mhi_ring *ring, dma_addr_t addr)
 {
-	return addr >= ring->iommu_base && addr < ring->iommu_base + ring->len;
+	return addr >= ring->iommu_base && addr < ring->iommu_base + ring->len &&
+			!(addr & (sizeof(struct mhi_ring_element) - 1));
 }
 
 int mhi_destroy_device(struct device *dev, void *data)
@@ -642,6 +644,8 @@ static int parse_xfer_event(struct mhi_controller *mhi_cntrl,
 			mhi_del_ring_element(mhi_cntrl, tre_ring);
 			local_rp = tre_ring->rp;
 
+			read_unlock_bh(&mhi_chan->lock);
+
 			/* notify client */
 			mhi_chan->xfer_cb(mhi_chan->mhi_dev, &result);
 
@@ -667,6 +671,8 @@ static int parse_xfer_event(struct mhi_controller *mhi_cntrl,
 					kfree(buf_info->cb_buf);
 				}
 			}
+
+			read_lock_bh(&mhi_chan->lock);
 		}
 		break;
 	} /* CC_EOT */
@@ -1122,17 +1128,15 @@ static int mhi_queue(struct mhi_device *mhi_dev, struct mhi_buf_info *buf_info,
 	if (unlikely(MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state)))
 		return -EIO;
 
-	read_lock_irqsave(&mhi_cntrl->pm_lock, flags);
-
 	ret = mhi_is_ring_full(mhi_cntrl, tre_ring);
-	if (unlikely(ret)) {
-		ret = -EAGAIN;
-		goto exit_unlock;
-	}
+	if (unlikely(ret))
+		return -EAGAIN;
 
 	ret = mhi_gen_tre(mhi_cntrl, mhi_chan, buf_info, mflags);
 	if (unlikely(ret))
-		goto exit_unlock;
+		return ret;
+
+	read_lock_irqsave(&mhi_cntrl->pm_lock, flags);
 
 	/* Packet is queued, take a usage ref to exit M3 if necessary
 	 * for host->device buffer, balanced put is done on buffer completion
@@ -1152,7 +1156,6 @@ static int mhi_queue(struct mhi_device *mhi_dev, struct mhi_buf_info *buf_info,
 	if (dir == DMA_FROM_DEVICE)
 		mhi_cntrl->runtime_put(mhi_cntrl);
 
-exit_unlock:
 	read_unlock_irqrestore(&mhi_cntrl->pm_lock, flags);
 
 	return ret;
@@ -1204,6 +1207,9 @@ int mhi_gen_tre(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan,
 	int eot, eob, chain, bei;
 	int ret;
 
+	/* Protect accesses for reading and incrementing WP */
+	write_lock_bh(&mhi_chan->lock);
+
 	buf_ring = &mhi_chan->buf_ring;
 	tre_ring = &mhi_chan->tre_ring;
 
@@ -1221,8 +1227,10 @@ int mhi_gen_tre(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan,
 
 	if (!info->pre_mapped) {
 		ret = mhi_cntrl->map_single(mhi_cntrl, buf_info);
-		if (ret)
+		if (ret) {
+			write_unlock_bh(&mhi_chan->lock);
 			return ret;
+		}
 	}
 
 	eob = !!(flags & MHI_EOB);
@@ -1239,6 +1247,8 @@ int mhi_gen_tre(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan,
 	mhi_add_ring_element(mhi_cntrl, tre_ring);
 	mhi_add_ring_element(mhi_cntrl, buf_ring);
 
+	write_unlock_bh(&mhi_chan->lock);
+
 	return 0;
 }
 
diff --git a/drivers/bus/mhi/host/pci_generic.c b/drivers/bus/mhi/host/pci_generic.c
index 08f3f039dbdd..cd6cd14b3d29 100644
--- a/drivers/bus/mhi/host/pci_generic.c
+++ b/drivers/bus/mhi/host/pci_generic.c
@@ -269,6 +269,16 @@ static struct mhi_event_config modem_qcom_v1_mhi_events[] = {
 	MHI_EVENT_CONFIG_HW_DATA(5, 2048, 101)
 };
 
+static const struct mhi_controller_config modem_qcom_v2_mhiv_config = {
+	.max_channels = 128,
+	.timeout_ms = 8000,
+	.ready_timeout_ms = 50000,
+	.num_channels = ARRAY_SIZE(modem_qcom_v1_mhi_channels),
+	.ch_cfg = modem_qcom_v1_mhi_channels,
+	.num_events = ARRAY_SIZE(modem_qcom_v1_mhi_events),
+	.event_cfg = modem_qcom_v1_mhi_events,
+};
+
 static const struct mhi_controller_config modem_qcom_v1_mhiv_config = {
 	.max_channels = 128,
 	.timeout_ms = 8000,
@@ -278,6 +288,16 @@ static const struct mhi_controller_config modem_qcom_v1_mhiv_config = {
 	.event_cfg = modem_qcom_v1_mhi_events,
 };
 
+static const struct mhi_pci_dev_info mhi_qcom_sdx75_info = {
+	.name = "qcom-sdx75m",
+	.fw = "qcom/sdx75m/xbl.elf",
+	.edl = "qcom/sdx75m/edl.mbn",
+	.config = &modem_qcom_v2_mhiv_config,
+	.bar_num = MHI_PCI_DEFAULT_BAR_NUM,
+	.dma_data_width = 32,
+	.sideband_wake = false,
+};
+
 static const struct mhi_pci_dev_info mhi_qcom_sdx65_info = {
 	.name = "qcom-sdx65m",
 	.fw = "qcom/sdx65m/xbl.elf",
@@ -600,6 +620,8 @@ static const struct pci_device_id mhi_pci_id_table[] = {
 		.driver_data = (kernel_ulong_t) &mhi_telit_fn990_info },
 	{ PCI_DEVICE(PCI_VENDOR_ID_QCOM, 0x0308),
 		.driver_data = (kernel_ulong_t) &mhi_qcom_sdx65_info },
+	{ PCI_DEVICE(PCI_VENDOR_ID_QCOM, 0x0309),
+		.driver_data = (kernel_ulong_t) &mhi_qcom_sdx75_info },
 	{ PCI_DEVICE(PCI_VENDOR_ID_QUECTEL, 0x1001), /* EM120R-GL (sdx24) */
 		.driver_data = (kernel_ulong_t) &mhi_quectel_em1xx_info },
 	{ PCI_DEVICE(PCI_VENDOR_ID_QUECTEL, 0x1002), /* EM160R-GL (sdx24) */
diff --git a/drivers/bus/mhi/host/pm.c b/drivers/bus/mhi/host/pm.c
index 8a4362d75fc4..a2f2feef1476 100644
--- a/drivers/bus/mhi/host/pm.c
+++ b/drivers/bus/mhi/host/pm.c
@@ -163,6 +163,7 @@ int mhi_ready_state_transition(struct mhi_controller *mhi_cntrl)
 	enum mhi_pm_state cur_state;
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
 	u32 interval_us = 25000; /* poll register field every 25 milliseconds */
+	u32 timeout_ms;
 	int ret, i;
 
 	/* Check if device entered error state */
@@ -173,14 +174,18 @@ int mhi_ready_state_transition(struct mhi_controller *mhi_cntrl)
 
 	/* Wait for RESET to be cleared and READY bit to be set by the device */
 	ret = mhi_poll_reg_field(mhi_cntrl, mhi_cntrl->regs, MHICTRL,
-				 MHICTRL_RESET_MASK, 0, interval_us);
+				 MHICTRL_RESET_MASK, 0, interval_us,
+				 mhi_cntrl->timeout_ms);
 	if (ret) {
 		dev_err(dev, "Device failed to clear MHI Reset\n");
 		return ret;
 	}
 
+	timeout_ms = mhi_cntrl->ready_timeout_ms ?
+		mhi_cntrl->ready_timeout_ms : mhi_cntrl->timeout_ms;
 	ret = mhi_poll_reg_field(mhi_cntrl, mhi_cntrl->regs, MHISTATUS,
-				 MHISTATUS_READY_MASK, 1, interval_us);
+				 MHISTATUS_READY_MASK, 1, interval_us,
+				 timeout_ms);
 	if (ret) {
 		dev_err(dev, "Device failed to enter MHI Ready\n");
 		return ret;
@@ -479,7 +484,7 @@ static void mhi_pm_disable_transition(struct mhi_controller *mhi_cntrl)
 
 		/* Wait for the reset bit to be cleared by the device */
 		ret = mhi_poll_reg_field(mhi_cntrl, mhi_cntrl->regs, MHICTRL,
-				 MHICTRL_RESET_MASK, 0, 25000);
+				 MHICTRL_RESET_MASK, 0, 25000, mhi_cntrl->timeout_ms);
 		if (ret)
 			dev_err(dev, "Device failed to clear MHI Reset\n");
 
@@ -492,8 +497,8 @@ static void mhi_pm_disable_transition(struct mhi_controller *mhi_cntrl)
 		if (!MHI_IN_PBL(mhi_get_exec_env(mhi_cntrl))) {
 			/* wait for ready to be set */
 			ret = mhi_poll_reg_field(mhi_cntrl, mhi_cntrl->regs,
-						 MHISTATUS,
-						 MHISTATUS_READY_MASK, 1, 25000);
+						 MHISTATUS, MHISTATUS_READY_MASK,
+						 1, 25000, mhi_cntrl->timeout_ms);
 			if (ret)
 				dev_err(dev, "Device failed to enter READY state\n");
 		}
@@ -1111,7 +1116,8 @@ int mhi_async_power_up(struct mhi_controller *mhi_cntrl)
 	if (state == MHI_STATE_SYS_ERR) {
 		mhi_set_mhi_state(mhi_cntrl, MHI_STATE_RESET);
 		ret = mhi_poll_reg_field(mhi_cntrl, mhi_cntrl->regs, MHICTRL,
-				 MHICTRL_RESET_MASK, 0, interval_us);
+				 MHICTRL_RESET_MASK, 0, interval_us,
+				 mhi_cntrl->timeout_ms);
 		if (ret) {
 			dev_info(dev, "Failed to reset MHI due to syserr state\n");
 			goto error_exit;
@@ -1202,14 +1208,18 @@ EXPORT_SYMBOL_GPL(mhi_power_down);
 int mhi_sync_power_up(struct mhi_controller *mhi_cntrl)
 {
 	int ret = mhi_async_power_up(mhi_cntrl);
+	u32 timeout_ms;
 
 	if (ret)
 		return ret;
 
+	/* Some devices need more time to set ready during power up */
+	timeout_ms = mhi_cntrl->ready_timeout_ms ?
+		mhi_cntrl->ready_timeout_ms : mhi_cntrl->timeout_ms;
 	wait_event_timeout(mhi_cntrl->state_event,
 			   MHI_IN_MISSION_MODE(mhi_cntrl->ee) ||
 			   MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state),
-			   msecs_to_jiffies(mhi_cntrl->timeout_ms));
+			   msecs_to_jiffies(timeout_ms));
 
 	ret = (MHI_IN_MISSION_MODE(mhi_cntrl->ee)) ? 0 : -ETIMEDOUT;
 	if (ret)
diff --git a/drivers/bus/moxtet.c b/drivers/bus/moxtet.c
index e384fbc6c1d9..641c1a6adc8a 100644
--- a/drivers/bus/moxtet.c
+++ b/drivers/bus/moxtet.c
@@ -102,7 +102,7 @@ static int moxtet_match(struct device *dev, struct device_driver *drv)
 	return 0;
 }
 
-static struct bus_type moxtet_bus_type = {
+static const struct bus_type moxtet_bus_type = {
 	.name		= "moxtet",
 	.dev_groups	= moxtet_dev_groups,
 	.match		= moxtet_match,
diff --git a/drivers/cache/ax45mp_cache.c b/drivers/cache/ax45mp_cache.c
index 57186c58dc84..1d7dd3d2c101 100644
--- a/drivers/cache/ax45mp_cache.c
+++ b/drivers/cache/ax45mp_cache.c
@@ -129,8 +129,12 @@ static void ax45mp_dma_cache_wback(phys_addr_t paddr, size_t size)
 	unsigned long line_size;
 	unsigned long flags;
 
+	if (unlikely(start == end))
+		return;
+
 	line_size = ax45mp_priv.ax45mp_cache_line_size;
 	start = start & (~(line_size - 1));
+	end = ((end + line_size - 1) & (~(line_size - 1)));
 	local_irq_save(flags);
 	ax45mp_cpu_dcache_wb_range(start, end);
 	local_irq_restore(flags);
diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c
index d668b174ace9..eefdd422ad8e 100644
--- a/drivers/cdrom/gdrom.c
+++ b/drivers/cdrom/gdrom.c
@@ -724,11 +724,6 @@ static void probe_gdrom_setupdisk(void)
 
 static int probe_gdrom_setupqueue(void)
 {
-	blk_queue_logical_block_size(gd.gdrom_rq, GDROM_HARD_SECTOR);
-	/* using DMA so memory will need to be contiguous */
-	blk_queue_max_segments(gd.gdrom_rq, 1);
-	/* set a large max size to get most from DMA */
-	blk_queue_max_segment_size(gd.gdrom_rq, 0x40000);
 	gd.disk->queue = gd.gdrom_rq;
 	return gdrom_init_dma_mode();
 }
@@ -743,6 +738,13 @@ static const struct blk_mq_ops gdrom_mq_ops = {
  */
 static int probe_gdrom(struct platform_device *devptr)
 {
+	struct queue_limits lim = {
+		.logical_block_size		= GDROM_HARD_SECTOR,
+		/* using DMA so memory will need to be contiguous */
+		.max_segments			= 1,
+		/* set a large max size to get most from DMA */
+		.max_segment_size		= 0x40000,
+	};
 	int err;
 
 	/*
@@ -778,7 +780,7 @@ static int probe_gdrom(struct platform_device *devptr)
 	if (err)
 		goto probe_fail_free_cd_info;
 
-	gd.disk = blk_mq_alloc_disk(&gd.tag_set, NULL);
+	gd.disk = blk_mq_alloc_disk(&gd.tag_set, &lim, NULL);
 	if (IS_ERR(gd.disk)) {
 		err = PTR_ERR(gd.disk);
 		goto probe_fail_free_tag_set;
@@ -829,7 +831,7 @@ probe_fail_no_mem:
 	return err;
 }
 
-static int remove_gdrom(struct platform_device *devptr)
+static void remove_gdrom(struct platform_device *devptr)
 {
 	blk_mq_free_tag_set(&gd.tag_set);
 	free_irq(HW_EVENT_GDROM_CMD, &gd);
@@ -840,13 +842,11 @@ static int remove_gdrom(struct platform_device *devptr)
 	unregister_cdrom(gd.cd_info);
 	kfree(gd.cd_info);
 	kfree(gd.toc);
-
-	return 0;
 }
 
 static struct platform_driver gdrom_driver = {
 	.probe = probe_gdrom,
-	.remove = remove_gdrom,
+	.remove_new = remove_gdrom,
 	.driver = {
 			.name = GDROM_DEV_NAME,
 	},
diff --git a/drivers/cdx/cdx.c b/drivers/cdx/cdx.c
index 4461c6c9313f..b74d76afccb6 100644
--- a/drivers/cdx/cdx.c
+++ b/drivers/cdx/cdx.c
@@ -57,13 +57,17 @@
 
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/idr.h>
 #include <linux/cdx/cdx_bus.h>
 #include <linux/iommu.h>
 #include <linux/dma-map-ops.h>
+#include <linux/debugfs.h>
 #include "cdx.h"
 
 /* Default DMA mask for devices on a CDX bus */
@@ -74,9 +78,13 @@
 static DEFINE_IDA(cdx_controller_ida);
 /* Lock to protect controller ops */
 static DEFINE_MUTEX(cdx_controller_lock);
+/* Debugfs dir for cdx bus */
+static struct dentry *cdx_debugfs_dir;
 
 static char *compat_node_name = "xlnx,versal-net-cdx";
 
+static void cdx_destroy_res_attr(struct cdx_device *cdx_dev, int num);
+
 /**
  * cdx_dev_reset - Reset a CDX device
  * @dev: CDX device
@@ -145,6 +153,8 @@ static int cdx_unregister_device(struct device *dev,
 		if (cdx_dev->enabled && cdx->ops->bus_disable)
 			cdx->ops->bus_disable(cdx, cdx_dev->bus_num);
 	} else {
+		cdx_destroy_res_attr(cdx_dev, MAX_CDX_DEV_RESOURCES);
+		debugfs_remove_recursive(cdx_dev->debugfs_dir);
 		kfree(cdx_dev->driver_override);
 		cdx_dev->driver_override = NULL;
 	}
@@ -548,6 +558,31 @@ static const struct attribute_group *cdx_dev_groups[] = {
 	NULL,
 };
 
+static int cdx_debug_resource_show(struct seq_file *s, void *data)
+{
+	struct cdx_device *cdx_dev = s->private;
+	int i;
+
+	for (i = 0; i < MAX_CDX_DEV_RESOURCES; i++) {
+		struct resource *res =  &cdx_dev->res[i];
+
+		seq_printf(s, "%pr\n", res);
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(cdx_debug_resource);
+
+static void cdx_device_debugfs_init(struct cdx_device *cdx_dev)
+{
+	cdx_dev->debugfs_dir = debugfs_create_dir(dev_name(&cdx_dev->dev), cdx_debugfs_dir);
+	if (IS_ERR(cdx_dev->debugfs_dir))
+		return;
+
+	debugfs_create_file("resource", 0444, cdx_dev->debugfs_dir, cdx_dev,
+			    &cdx_debug_resource_fops);
+}
+
 static ssize_t rescan_store(const struct bus_type *bus,
 			    const char *buf, size_t count)
 {
@@ -569,12 +604,12 @@ static ssize_t rescan_store(const struct bus_type *bus,
 
 	/* Rescan all the devices */
 	for_each_compatible_node(np, NULL, compat_node_name) {
-		if (!np)
-			return -EINVAL;
-
 		pd = of_find_device_by_node(np);
-		if (!pd)
-			return -EINVAL;
+		if (!pd) {
+			of_node_put(np);
+			count = -EINVAL;
+			goto unlock;
+		}
 
 		cdx = platform_get_drvdata(pd);
 		if (cdx && cdx->controller_registered && cdx->ops->scan)
@@ -583,6 +618,7 @@ static ssize_t rescan_store(const struct bus_type *bus,
 		put_device(&pd->dev);
 	}
 
+unlock:
 	mutex_unlock(&cdx_controller_lock);
 
 	return count;
@@ -640,11 +676,105 @@ static void cdx_device_release(struct device *dev)
 	kfree(cdx_dev);
 }
 
+static const struct vm_operations_struct cdx_phys_vm_ops = {
+#ifdef CONFIG_HAVE_IOREMAP_PROT
+	.access = generic_access_phys,
+#endif
+};
+
+/**
+ * cdx_mmap_resource - map a CDX resource into user memory space
+ * @fp: File pointer. Not used in this function, but required where
+ *      this API is registered as a callback.
+ * @kobj: kobject for mapping
+ * @attr: struct bin_attribute for the file being mapped
+ * @vma: struct vm_area_struct passed into the mmap
+ *
+ * Use the regular CDX mapping routines to map a CDX resource into userspace.
+ *
+ * Return: true on success, false otherwise.
+ */
+static int cdx_mmap_resource(struct file *fp, struct kobject *kobj,
+			     struct bin_attribute *attr,
+			     struct vm_area_struct *vma)
+{
+	struct cdx_device *cdx_dev = to_cdx_device(kobj_to_dev(kobj));
+	int num = (unsigned long)attr->private;
+	struct resource *res;
+	unsigned long size;
+
+	res = &cdx_dev->res[num];
+	if (iomem_is_exclusive(res->start))
+		return -EINVAL;
+
+	/* Make sure the caller is mapping a valid resource for this device */
+	size = ((cdx_resource_len(cdx_dev, num) - 1) >> PAGE_SHIFT) + 1;
+	if (vma->vm_pgoff + vma_pages(vma) > size)
+		return -EINVAL;
+
+	/*
+	 * Map memory region and vm->vm_pgoff is expected to be an
+	 * offset within that region.
+	 */
+	vma->vm_page_prot = pgprot_device(vma->vm_page_prot);
+	vma->vm_pgoff += (cdx_resource_start(cdx_dev, num) >> PAGE_SHIFT);
+	vma->vm_ops = &cdx_phys_vm_ops;
+	return io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+				  vma->vm_end - vma->vm_start,
+				  vma->vm_page_prot);
+}
+
+static void cdx_destroy_res_attr(struct cdx_device *cdx_dev, int num)
+{
+	int i;
+
+	/* removing the bin attributes */
+	for (i = 0; i < num; i++) {
+		struct bin_attribute *res_attr;
+
+		res_attr = cdx_dev->res_attr[i];
+		if (res_attr) {
+			sysfs_remove_bin_file(&cdx_dev->dev.kobj, res_attr);
+			kfree(res_attr);
+		}
+	}
+}
+
+#define CDX_RES_ATTR_NAME_LEN	10
+static int cdx_create_res_attr(struct cdx_device *cdx_dev, int num)
+{
+	struct bin_attribute *res_attr;
+	char *res_attr_name;
+	int ret;
+
+	res_attr = kzalloc(sizeof(*res_attr) + CDX_RES_ATTR_NAME_LEN, GFP_ATOMIC);
+	if (!res_attr)
+		return -ENOMEM;
+
+	res_attr_name = (char *)(res_attr + 1);
+
+	sysfs_bin_attr_init(res_attr);
+
+	cdx_dev->res_attr[num] = res_attr;
+	sprintf(res_attr_name, "resource%d", num);
+
+	res_attr->mmap = cdx_mmap_resource;
+	res_attr->attr.name = res_attr_name;
+	res_attr->attr.mode = 0600;
+	res_attr->size = cdx_resource_len(cdx_dev, num);
+	res_attr->private = (void *)(unsigned long)num;
+	ret = sysfs_create_bin_file(&cdx_dev->dev.kobj, res_attr);
+	if (ret)
+		kfree(res_attr);
+
+	return ret;
+}
+
 int cdx_device_add(struct cdx_dev_params *dev_params)
 {
 	struct cdx_controller *cdx = dev_params->cdx;
 	struct cdx_device *cdx_dev;
-	int ret;
+	int ret, i;
 
 	cdx_dev = kzalloc(sizeof(*cdx_dev), GFP_KERNEL);
 	if (!cdx_dev)
@@ -687,7 +817,28 @@ int cdx_device_add(struct cdx_dev_params *dev_params)
 		goto fail;
 	}
 
+	/* Create resource<N> attributes */
+	for (i = 0; i < MAX_CDX_DEV_RESOURCES; i++) {
+		if (cdx_resource_flags(cdx_dev, i) & IORESOURCE_MEM) {
+			/* skip empty resources */
+			if (!cdx_resource_len(cdx_dev, i))
+				continue;
+
+			ret = cdx_create_res_attr(cdx_dev, i);
+			if (ret != 0) {
+				dev_err(&cdx_dev->dev,
+					"cdx device resource<%d> file creation failed: %d", i, ret);
+				goto resource_create_fail;
+			}
+		}
+	}
+
+	cdx_device_debugfs_init(cdx_dev);
+
 	return 0;
+resource_create_fail:
+	cdx_destroy_res_attr(cdx_dev, i);
+	device_del(&cdx_dev->dev);
 fail:
 	/*
 	 * Do not free cdx_dev here as it would be freed in
@@ -788,6 +939,12 @@ EXPORT_SYMBOL_NS_GPL(cdx_unregister_controller, CDX_BUS_CONTROLLER);
 
 static int __init cdx_bus_init(void)
 {
-	return bus_register(&cdx_bus_type);
+	int ret;
+
+	ret = bus_register(&cdx_bus_type);
+	if (!ret)
+		cdx_debugfs_dir = debugfs_create_dir(cdx_bus_type.name, NULL);
+
+	return ret;
 }
 postcore_initcall(cdx_bus_init);
diff --git a/drivers/char/ppdev.c b/drivers/char/ppdev.c
index 4c188e9e477c..ee951b265213 100644
--- a/drivers/char/ppdev.c
+++ b/drivers/char/ppdev.c
@@ -299,7 +299,7 @@ static int register_device(int minor, struct pp_struct *pp)
 		goto err;
 	}
 
-	index = ida_simple_get(&ida_index, 0, 0, GFP_KERNEL);
+	index = ida_alloc(&ida_index, GFP_KERNEL);
 	memset(&ppdev_cb, 0, sizeof(ppdev_cb));
 	ppdev_cb.irq_func = pp_irq;
 	ppdev_cb.flags = (pp->flags & PP_EXCL) ? PARPORT_FLAG_EXCL : 0;
@@ -310,7 +310,7 @@ static int register_device(int minor, struct pp_struct *pp)
 	if (!pdev) {
 		pr_warn("%s: failed to register device!\n", name);
 		rc = -ENXIO;
-		ida_simple_remove(&ida_index, index);
+		ida_free(&ida_index, index);
 		goto err;
 	}
 
@@ -750,7 +750,7 @@ static int pp_release(struct inode *inode, struct file *file)
 
 	if (pp->pdev) {
 		parport_unregister_device(pp->pdev);
-		ida_simple_remove(&ida_index, pp->index);
+		ida_free(&ida_index, pp->index);
 		pp->pdev = NULL;
 		pr_debug(CHRDEV "%x: unregistered pardevice\n", minor);
 	}
diff --git a/drivers/char/ttyprintk.c b/drivers/char/ttyprintk.c
index 5af804c17a75..4c806a189ee5 100644
--- a/drivers/char/ttyprintk.c
+++ b/drivers/char/ttyprintk.c
@@ -40,7 +40,7 @@ static struct ttyprintk_port tpk_port;
 
 static int tpk_curr;
 
-static char tpk_buffer[TPK_STR_SIZE + 4];
+static u8 tpk_buffer[TPK_STR_SIZE + 4];
 
 static void tpk_flush(void)
 {
@@ -51,9 +51,9 @@ static void tpk_flush(void)
 	}
 }
 
-static int tpk_printk(const u8 *buf, int count)
+static int tpk_printk(const u8 *buf, size_t count)
 {
-	int i;
+	size_t i;
 
 	for (i = 0; i < count; i++) {
 		if (tpk_curr >= TPK_STR_SIZE) {
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 431e9e5bf9c1..035f89f1a251 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -230,9 +230,6 @@ struct port {
 	bool guest_connected;
 };
 
-/* This is the very early arch-specified put chars function. */
-static int (*early_put_chars)(u32, const char *, int);
-
 static struct port *find_port_by_vtermno(u32 vtermno)
 {
 	struct port *port;
@@ -653,7 +650,7 @@ done:
  * Give out the data that's requested from the buffer that we have
  * queued up.
  */
-static ssize_t fill_readbuf(struct port *port, char __user *out_buf,
+static ssize_t fill_readbuf(struct port *port, u8 __user *out_buf,
 			    size_t out_count, bool to_user)
 {
 	struct port_buffer *buf;
@@ -672,7 +669,7 @@ static ssize_t fill_readbuf(struct port *port, char __user *out_buf,
 		if (ret)
 			return -EFAULT;
 	} else {
-		memcpy((__force char *)out_buf, buf->buf + buf->offset,
+		memcpy((__force u8 *)out_buf, buf->buf + buf->offset,
 		       out_count);
 	}
 
@@ -1107,16 +1104,13 @@ static const struct file_operations port_fops = {
  * it to finish: inefficient in theory, but in practice
  * implementations will do it immediately.
  */
-static int put_chars(u32 vtermno, const char *buf, int count)
+static ssize_t put_chars(u32 vtermno, const u8 *buf, size_t count)
 {
 	struct port *port;
 	struct scatterlist sg[1];
 	void *data;
 	int ret;
 
-	if (unlikely(early_put_chars))
-		return early_put_chars(vtermno, buf, count);
-
 	port = find_port_by_vtermno(vtermno);
 	if (!port)
 		return -EPIPE;
@@ -1138,14 +1132,10 @@ static int put_chars(u32 vtermno, const char *buf, int count)
  * We call out to fill_readbuf that gets us the required data from the
  * buffers that are queued up.
  */
-static int get_chars(u32 vtermno, char *buf, int count)
+static ssize_t get_chars(u32 vtermno, u8 *buf, size_t count)
 {
 	struct port *port;
 
-	/* If we've not set up the port yet, we have no input to give. */
-	if (unlikely(early_put_chars))
-		return 0;
-
 	port = find_port_by_vtermno(vtermno);
 	if (!port)
 		return -EPIPE;
@@ -1153,7 +1143,7 @@ static int get_chars(u32 vtermno, char *buf, int count)
 	/* If we don't have an input queue yet, we can't get input. */
 	BUG_ON(!port->in_vq);
 
-	return fill_readbuf(port, (__force char __user *)buf, count, false);
+	return fill_readbuf(port, (__force u8 __user *)buf, count, false);
 }
 
 static void resize_console(struct port *port)
@@ -1201,21 +1191,6 @@ static const struct hv_ops hv_ops = {
 	.notifier_hangup = notifier_del_vio,
 };
 
-/*
- * Console drivers are initialized very early so boot messages can go
- * out, so we do things slightly differently from the generic virtio
- * initialization of the net and block drivers.
- *
- * At this stage, the console is output-only.  It's too early to set
- * up a virtqueue, so we let the drivers do some boutique early-output
- * thing.
- */
-int __init virtio_cons_early_init(int (*put_chars)(u32, const char *, int))
-{
-	early_put_chars = put_chars;
-	return hvc_instantiate(0, 0, &hv_ops);
-}
-
 static int init_port_console(struct port *port)
 {
 	int ret;
@@ -1256,13 +1231,6 @@ static int init_port_console(struct port *port)
 	spin_unlock_irq(&pdrvdata_lock);
 	port->guest_connected = true;
 
-	/*
-	 * Start using the new console output if this is the first
-	 * console to come up.
-	 */
-	if (early_put_chars)
-		early_put_chars = NULL;
-
 	/* Notify host of port being opened */
 	send_control_msg(port, VIRTIO_CONSOLE_PORT_OPEN, 1);
 
@@ -1999,7 +1967,6 @@ static int virtcons_probe(struct virtio_device *vdev)
 	struct ports_device *portdev;
 	int err;
 	bool multiport;
-	bool early = early_put_chars != NULL;
 
 	/* We only need a config space if features are offered */
 	if (!vdev->config->get &&
@@ -2010,9 +1977,6 @@ static int virtcons_probe(struct virtio_device *vdev)
 		return -EINVAL;
 	}
 
-	/* Ensure to read early_put_chars now */
-	barrier();
-
 	portdev = kmalloc(sizeof(*portdev), GFP_KERNEL);
 	if (!portdev) {
 		err = -ENOMEM;
@@ -2100,18 +2064,6 @@ static int virtcons_probe(struct virtio_device *vdev)
 	__send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
 			   VIRTIO_CONSOLE_DEVICE_READY, 1);
 
-	/*
-	 * If there was an early virtio console, assume that there are no
-	 * other consoles. We need to wait until the hvc_alloc matches the
-	 * hvc_instantiate, otherwise tty_open will complain, resulting in
-	 * a "Warning: unable to open an initial console" boot failure.
-	 * Without multiport this is done in add_port above. With multiport
-	 * this might take some host<->guest communication - thus we have to
-	 * wait.
-	 */
-	if (multiport && early)
-		wait_for_completion(&early_console_added);
-
 	return 0;
 
 free_chrdev:
diff --git a/drivers/clk/qcom/gcc-x1e80100.c b/drivers/clk/qcom/gcc-x1e80100.c
index 74db7fef237b..d7182d6e9783 100644
--- a/drivers/clk/qcom/gcc-x1e80100.c
+++ b/drivers/clk/qcom/gcc-x1e80100.c
@@ -4,8 +4,9 @@
  */
 
 #include <linux/clk-provider.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/platform_device.h>
 #include <linux/regmap.h>
 
 #include <dt-bindings/clock/qcom,x1e80100-gcc.h>
diff --git a/drivers/clk/samsung/clk-gs101.c b/drivers/clk/samsung/clk-gs101.c
index 0964bb11657f..782993951fff 100644
--- a/drivers/clk/samsung/clk-gs101.c
+++ b/drivers/clk/samsung/clk-gs101.c
@@ -2475,7 +2475,7 @@ static const struct samsung_cmu_info misc_cmu_info __initconst = {
 	.nr_clk_ids		= CLKS_NR_MISC,
 	.clk_regs		= misc_clk_regs,
 	.nr_clk_regs		= ARRAY_SIZE(misc_clk_regs),
-	.clk_name		= "dout_cmu_misc_bus",
+	.clk_name		= "bus",
 };
 
 /* ---- platform_driver ----------------------------------------------------- */
diff --git a/drivers/clocksource/timer-cadence-ttc.c b/drivers/clocksource/timer-cadence-ttc.c
index 32daaac9b132..ca7a06489c40 100644
--- a/drivers/clocksource/timer-cadence-ttc.c
+++ b/drivers/clocksource/timer-cadence-ttc.c
@@ -69,7 +69,7 @@
  * @base_addr:	Base address of timer
  * @freq:	Timer input clock frequency
  * @clk:	Associated clock source
- * @clk_rate_change_nb	Notifier block for clock rate changes
+ * @clk_rate_change_nb:	Notifier block for clock rate changes
  */
 struct ttc_timer {
 	void __iomem *base_addr;
@@ -134,7 +134,7 @@ static void ttc_set_interval(struct ttc_timer *timer,
  * @irq:	IRQ number of the Timer
  * @dev_id:	void pointer to the ttc_timer instance
  *
- * returns: Always IRQ_HANDLED - success
+ * Returns: Always IRQ_HANDLED - success
  **/
 static irqreturn_t ttc_clock_event_interrupt(int irq, void *dev_id)
 {
@@ -151,8 +151,9 @@ static irqreturn_t ttc_clock_event_interrupt(int irq, void *dev_id)
 
 /**
  * __ttc_clocksource_read - Reads the timer counter register
+ * @cs: &clocksource to read from
  *
- * returns: Current timer counter register value
+ * Returns: Current timer counter register value
  **/
 static u64 __ttc_clocksource_read(struct clocksource *cs)
 {
@@ -173,7 +174,7 @@ static u64 notrace ttc_sched_clock_read(void)
  * @cycles:	Timer interval ticks
  * @evt:	Address of clock event instance
  *
- * returns: Always 0 - success
+ * Returns: Always %0 - success
  **/
 static int ttc_set_next_event(unsigned long cycles,
 					struct clock_event_device *evt)
@@ -186,9 +187,12 @@ static int ttc_set_next_event(unsigned long cycles,
 }
 
 /**
- * ttc_set_{shutdown|oneshot|periodic} - Sets the state of timer
- *
+ * ttc_shutdown - Sets the state of timer
  * @evt:	Address of clock event instance
+ *
+ * Used for shutdown or oneshot.
+ *
+ * Returns: Always %0 - success
  **/
 static int ttc_shutdown(struct clock_event_device *evt)
 {
@@ -202,6 +206,12 @@ static int ttc_shutdown(struct clock_event_device *evt)
 	return 0;
 }
 
+/**
+ * ttc_set_periodic - Sets the state of timer
+ * @evt:	Address of clock event instance
+ *
+ * Returns: Always %0 - success
+ */
 static int ttc_set_periodic(struct clock_event_device *evt)
 {
 	struct ttc_timer_clockevent *ttce = to_ttc_timer_clkevent(evt);
diff --git a/drivers/clocksource/timer-ep93xx.c b/drivers/clocksource/timer-ep93xx.c
index bc0ca6e12334..6981ff3ac8a9 100644
--- a/drivers/clocksource/timer-ep93xx.c
+++ b/drivers/clocksource/timer-ep93xx.c
@@ -155,9 +155,8 @@ static int __init ep93xx_timer_of_init(struct device_node *np)
 	ep93xx_tcu = tcu;
 
 	irq = irq_of_parse_and_map(np, 0);
-	if (irq == 0)
-		irq = -EINVAL;
-	if (irq < 0) {
+	if (!irq) {
+		ret = -EINVAL;
 		pr_err("EP93XX Timer Can't parse IRQ %d", irq);
 		goto out_free;
 	}
diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c
index 57857c0dfba9..e66dcbd66566 100644
--- a/drivers/clocksource/timer-riscv.c
+++ b/drivers/clocksource/timer-riscv.c
@@ -61,12 +61,19 @@ static int riscv_clock_next_event(unsigned long delta,
 	return 0;
 }
 
+static int riscv_clock_shutdown(struct clock_event_device *evt)
+{
+	riscv_clock_event_stop();
+	return 0;
+}
+
 static unsigned int riscv_clock_event_irq;
 static DEFINE_PER_CPU(struct clock_event_device, riscv_clock_event) = {
 	.name			= "riscv_timer_clockevent",
 	.features		= CLOCK_EVT_FEAT_ONESHOT,
 	.rating			= 100,
 	.set_next_event		= riscv_clock_next_event,
+	.set_state_shutdown	= riscv_clock_shutdown,
 };
 
 /*
diff --git a/drivers/clocksource/timer-ti-dm.c b/drivers/clocksource/timer-ti-dm.c
index 5f60f6bd3386..56acf2617262 100644
--- a/drivers/clocksource/timer-ti-dm.c
+++ b/drivers/clocksource/timer-ti-dm.c
@@ -183,7 +183,7 @@ static inline u32 dmtimer_read(struct dmtimer *timer, u32 reg)
  * dmtimer_write - write timer registers in posted and non-posted mode
  * @timer:      timer pointer over which write operation is to perform
  * @reg:        lowest byte holds the register offset
- * @value:      data to write into the register
+ * @val:        data to write into the register
  *
  * The posted mode bit is encoded in reg. Note that in posted mode, the write
  * pending bit must be checked. Otherwise a write on a register which has a
@@ -949,7 +949,7 @@ static int omap_dm_timer_set_int_enable(struct omap_dm_timer *cookie,
 
 /**
  * omap_dm_timer_set_int_disable - disable timer interrupts
- * @timer:	pointer to timer handle
+ * @cookie:	pointer to timer cookie
  * @mask:	bit mask of interrupts to be disabled
  *
  * Disables the specified timer interrupts for a timer.
diff --git a/drivers/comedi/comedi_fops.c b/drivers/comedi/comedi_fops.c
index 1548dea15df1..1b481731df96 100644
--- a/drivers/comedi/comedi_fops.c
+++ b/drivers/comedi/comedi_fops.c
@@ -1714,8 +1714,8 @@ static int __comedi_get_user_chanlist(struct comedi_device *dev,
 
 	lockdep_assert_held(&dev->mutex);
 	cmd->chanlist = NULL;
-	chanlist = memdup_user(user_chanlist,
-			       cmd->chanlist_len * sizeof(unsigned int));
+	chanlist = memdup_array_user(user_chanlist,
+				     cmd->chanlist_len, sizeof(unsigned int));
 	if (IS_ERR(chanlist))
 		return PTR_ERR(chanlist);
 
diff --git a/drivers/comedi/drivers/comedi_8255.c b/drivers/comedi/drivers/comedi_8255.c
index e4974b508328..a933ef53845a 100644
--- a/drivers/comedi/drivers/comedi_8255.c
+++ b/drivers/comedi/drivers/comedi_8255.c
@@ -159,6 +159,7 @@ static int __subdev_8255_init(struct comedi_device *dev,
 		return -ENOMEM;
 
 	spriv->context = context;
+	spriv->io      = io;
 
 	s->type		= COMEDI_SUBD_DIO;
 	s->subdev_flags	= SDF_READABLE | SDF_WRITABLE;
diff --git a/drivers/comedi/drivers/comedi_test.c b/drivers/comedi/drivers/comedi_test.c
index 30ea8b53ebf8..05ae9122823f 100644
--- a/drivers/comedi/drivers/comedi_test.c
+++ b/drivers/comedi/drivers/comedi_test.c
@@ -87,6 +87,8 @@ struct waveform_private {
 	struct comedi_device *dev;	/* parent comedi device */
 	u64 ao_last_scan_time;		/* time of previous AO scan in usec */
 	unsigned int ao_scan_period;	/* AO scan period in usec */
+	bool ai_timer_enable:1;		/* should AI timer be running? */
+	bool ao_timer_enable:1;		/* should AO timer be running? */
 	unsigned short ao_loopbacks[N_CHANS];
 };
 
@@ -236,8 +238,12 @@ static void waveform_ai_timer(struct timer_list *t)
 			time_increment = devpriv->ai_convert_time - now;
 		else
 			time_increment = 1;
-		mod_timer(&devpriv->ai_timer,
-			  jiffies + usecs_to_jiffies(time_increment));
+		spin_lock(&dev->spinlock);
+		if (devpriv->ai_timer_enable) {
+			mod_timer(&devpriv->ai_timer,
+				  jiffies + usecs_to_jiffies(time_increment));
+		}
+		spin_unlock(&dev->spinlock);
 	}
 
 overrun:
@@ -393,9 +399,12 @@ static int waveform_ai_cmd(struct comedi_device *dev,
 	 * Seem to need an extra jiffy here, otherwise timer expires slightly
 	 * early!
 	 */
+	spin_lock_bh(&dev->spinlock);
+	devpriv->ai_timer_enable = true;
 	devpriv->ai_timer.expires =
 		jiffies + usecs_to_jiffies(devpriv->ai_convert_period) + 1;
 	add_timer(&devpriv->ai_timer);
+	spin_unlock_bh(&dev->spinlock);
 	return 0;
 }
 
@@ -404,6 +413,9 @@ static int waveform_ai_cancel(struct comedi_device *dev,
 {
 	struct waveform_private *devpriv = dev->private;
 
+	spin_lock_bh(&dev->spinlock);
+	devpriv->ai_timer_enable = false;
+	spin_unlock_bh(&dev->spinlock);
 	if (in_softirq()) {
 		/* Assume we were called from the timer routine itself. */
 		del_timer(&devpriv->ai_timer);
@@ -495,8 +507,12 @@ static void waveform_ao_timer(struct timer_list *t)
 		unsigned int time_inc = devpriv->ao_last_scan_time +
 					devpriv->ao_scan_period - now;
 
-		mod_timer(&devpriv->ao_timer,
-			  jiffies + usecs_to_jiffies(time_inc));
+		spin_lock(&dev->spinlock);
+		if (devpriv->ao_timer_enable) {
+			mod_timer(&devpriv->ao_timer,
+				  jiffies + usecs_to_jiffies(time_inc));
+		}
+		spin_unlock(&dev->spinlock);
 	}
 
 underrun:
@@ -517,9 +533,12 @@ static int waveform_ao_inttrig_start(struct comedi_device *dev,
 	async->inttrig = NULL;
 
 	devpriv->ao_last_scan_time = ktime_to_us(ktime_get());
+	spin_lock_bh(&dev->spinlock);
+	devpriv->ao_timer_enable = true;
 	devpriv->ao_timer.expires =
 		jiffies + usecs_to_jiffies(devpriv->ao_scan_period);
 	add_timer(&devpriv->ao_timer);
+	spin_unlock_bh(&dev->spinlock);
 
 	return 1;
 }
@@ -604,6 +623,9 @@ static int waveform_ao_cancel(struct comedi_device *dev,
 	struct waveform_private *devpriv = dev->private;
 
 	s->async->inttrig = NULL;
+	spin_lock_bh(&dev->spinlock);
+	devpriv->ao_timer_enable = false;
+	spin_unlock_bh(&dev->spinlock);
 	if (in_softirq()) {
 		/* Assume we were called from the timer routine itself. */
 		del_timer(&devpriv->ao_timer);
diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index 3d5e6d705fc6..44b19e696176 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -108,9 +108,8 @@ static inline void send_msg(struct cn_msg *msg)
 		filter_data[1] = 0;
 	}
 
-	if (cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT,
-			     cn_filter, (void *)filter_data) == -ESRCH)
-		atomic_set(&proc_event_num_listeners, 0);
+	cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT,
+			     cn_filter, (void *)filter_data);
 
 	local_unlock(&local_event.lock);
 }
diff --git a/drivers/counter/counter-core.c b/drivers/counter/counter-core.c
index 09c77afb33ca..3f24481fc04a 100644
--- a/drivers/counter/counter-core.c
+++ b/drivers/counter/counter-core.c
@@ -31,10 +31,11 @@ struct counter_device_allochelper {
 	struct counter_device counter;
 
 	/*
-	 * This is cache line aligned to ensure private data behaves like if it
-	 * were kmalloced separately.
+	 * This ensures private data behaves like if it were kmalloced
+	 * separately. Also ensures the minimum alignment for safe DMA
+	 * operations (which may or may not mean cache alignment).
 	 */
-	unsigned long privdata[] ____cacheline_aligned;
+	unsigned long privdata[] __aligned(ARCH_DMA_MINALIGN);
 };
 
 static void counter_device_release(struct device *dev)
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 1f6186475715..1791d37fbc53 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -1232,14 +1232,13 @@ static void amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
 	max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq);
 	min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq);
 
+	WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf);
+	WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf);
+
 	max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf,
 			cpudata->max_limit_perf);
 	min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf,
 			cpudata->max_limit_perf);
-
-	WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf);
-	WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf);
-
 	value = READ_ONCE(cpudata->cppc_req_cached);
 
 	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 3c69040920b8..79619227ea51 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -302,7 +302,10 @@ static bool hwp_forced __read_mostly;
 
 static struct cpufreq_driver *intel_pstate_driver __read_mostly;
 
-#define HYBRID_SCALING_FACTOR	78741
+#define HYBRID_SCALING_FACTOR		78741
+#define HYBRID_SCALING_FACTOR_MTL	80000
+
+static int hybrid_scaling_factor = HYBRID_SCALING_FACTOR;
 
 static inline int core_get_scaling(void)
 {
@@ -422,7 +425,7 @@ static int intel_pstate_cppc_get_scaling(int cpu)
 	 */
 	if (!ret && cppc_perf.nominal_perf && cppc_perf.nominal_freq &&
 	    cppc_perf.nominal_perf * 100 != cppc_perf.nominal_freq)
-		return HYBRID_SCALING_FACTOR;
+		return hybrid_scaling_factor;
 
 	return core_get_scaling();
 }
@@ -526,6 +529,30 @@ static int intel_pstate_cppc_get_scaling(int cpu)
 }
 #endif /* CONFIG_ACPI_CPPC_LIB */
 
+static int intel_pstate_freq_to_hwp_rel(struct cpudata *cpu, int freq,
+					unsigned int relation)
+{
+	if (freq == cpu->pstate.turbo_freq)
+		return cpu->pstate.turbo_pstate;
+
+	if (freq == cpu->pstate.max_freq)
+		return cpu->pstate.max_pstate;
+
+	switch (relation) {
+	case CPUFREQ_RELATION_H:
+		return freq / cpu->pstate.scaling;
+	case CPUFREQ_RELATION_C:
+		return DIV_ROUND_CLOSEST(freq, cpu->pstate.scaling);
+	}
+
+	return DIV_ROUND_UP(freq, cpu->pstate.scaling);
+}
+
+static int intel_pstate_freq_to_hwp(struct cpudata *cpu, int freq)
+{
+	return intel_pstate_freq_to_hwp_rel(cpu, freq, CPUFREQ_RELATION_L);
+}
+
 /**
  * intel_pstate_hybrid_hwp_adjust - Calibrate HWP performance levels.
  * @cpu: Target CPU.
@@ -543,6 +570,7 @@ static void intel_pstate_hybrid_hwp_adjust(struct cpudata *cpu)
 	int perf_ctl_scaling = cpu->pstate.perf_ctl_scaling;
 	int perf_ctl_turbo = pstate_funcs.get_turbo(cpu->cpu);
 	int scaling = cpu->pstate.scaling;
+	int freq;
 
 	pr_debug("CPU%d: perf_ctl_max_phys = %d\n", cpu->cpu, perf_ctl_max_phys);
 	pr_debug("CPU%d: perf_ctl_turbo = %d\n", cpu->cpu, perf_ctl_turbo);
@@ -556,16 +584,16 @@ static void intel_pstate_hybrid_hwp_adjust(struct cpudata *cpu)
 	cpu->pstate.max_freq = rounddown(cpu->pstate.max_pstate * scaling,
 					 perf_ctl_scaling);
 
-	cpu->pstate.max_pstate_physical =
-			DIV_ROUND_UP(perf_ctl_max_phys * perf_ctl_scaling,
-				     scaling);
+	freq = perf_ctl_max_phys * perf_ctl_scaling;
+	cpu->pstate.max_pstate_physical = intel_pstate_freq_to_hwp(cpu, freq);
 
-	cpu->pstate.min_freq = cpu->pstate.min_pstate * perf_ctl_scaling;
+	freq = cpu->pstate.min_pstate * perf_ctl_scaling;
+	cpu->pstate.min_freq = freq;
 	/*
 	 * Cast the min P-state value retrieved via pstate_funcs.get_min() to
 	 * the effective range of HWP performance levels.
 	 */
-	cpu->pstate.min_pstate = DIV_ROUND_UP(cpu->pstate.min_freq, scaling);
+	cpu->pstate.min_pstate = intel_pstate_freq_to_hwp(cpu, freq);
 }
 
 static inline void update_turbo_state(void)
@@ -1968,7 +1996,7 @@ static int hwp_get_cpu_scaling(int cpu)
 	smp_call_function_single(cpu, hybrid_get_type, &cpu_type, 1);
 	/* P-cores have a smaller perf level-to-freqency scaling factor. */
 	if (cpu_type == 0x40)
-		return HYBRID_SCALING_FACTOR;
+		return hybrid_scaling_factor;
 
 	/* Use default core scaling for E-cores */
 	if (cpu_type == 0x20)
@@ -2525,13 +2553,12 @@ static void intel_pstate_update_perf_limits(struct cpudata *cpu,
 	 * abstract values to represent performance rather than pure ratios.
 	 */
 	if (hwp_active && cpu->pstate.scaling != perf_ctl_scaling) {
-		int scaling = cpu->pstate.scaling;
 		int freq;
 
 		freq = max_policy_perf * perf_ctl_scaling;
-		max_policy_perf = DIV_ROUND_UP(freq, scaling);
+		max_policy_perf = intel_pstate_freq_to_hwp(cpu, freq);
 		freq = min_policy_perf * perf_ctl_scaling;
-		min_policy_perf = DIV_ROUND_UP(freq, scaling);
+		min_policy_perf = intel_pstate_freq_to_hwp(cpu, freq);
 	}
 
 	pr_debug("cpu:%d min_policy_perf:%d max_policy_perf:%d\n",
@@ -2905,18 +2932,7 @@ static int intel_cpufreq_target(struct cpufreq_policy *policy,
 
 	cpufreq_freq_transition_begin(policy, &freqs);
 
-	switch (relation) {
-	case CPUFREQ_RELATION_L:
-		target_pstate = DIV_ROUND_UP(freqs.new, cpu->pstate.scaling);
-		break;
-	case CPUFREQ_RELATION_H:
-		target_pstate = freqs.new / cpu->pstate.scaling;
-		break;
-	default:
-		target_pstate = DIV_ROUND_CLOSEST(freqs.new, cpu->pstate.scaling);
-		break;
-	}
-
+	target_pstate = intel_pstate_freq_to_hwp_rel(cpu, freqs.new, relation);
 	target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, false);
 
 	freqs.new = target_pstate * cpu->pstate.scaling;
@@ -2934,7 +2950,7 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy,
 
 	update_turbo_state();
 
-	target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling);
+	target_pstate = intel_pstate_freq_to_hwp(cpu, target_freq);
 
 	target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, true);
 
@@ -2971,6 +2987,9 @@ static void intel_cpufreq_adjust_perf(unsigned int cpunum,
 	if (min_pstate < cpu->min_perf_ratio)
 		min_pstate = cpu->min_perf_ratio;
 
+	if (min_pstate > cpu->max_perf_ratio)
+		min_pstate = cpu->max_perf_ratio;
+
 	max_pstate = min(cap_pstate, cpu->max_perf_ratio);
 	if (max_pstate < min_pstate)
 		max_pstate = min_pstate;
@@ -3399,6 +3418,11 @@ static const struct x86_cpu_id intel_epp_balance_perf[] = {
 	{}
 };
 
+static const struct x86_cpu_id intel_hybrid_scaling_factor[] = {
+	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, HYBRID_SCALING_FACTOR_MTL),
+	{}
+};
+
 static int __init intel_pstate_init(void)
 {
 	static struct cpudata **_all_cpu_data;
@@ -3489,9 +3513,16 @@ hwp_cpu_matched:
 
 	if (hwp_active) {
 		const struct x86_cpu_id *id = x86_match_cpu(intel_epp_balance_perf);
+		const struct x86_cpu_id *hybrid_id = x86_match_cpu(intel_hybrid_scaling_factor);
 
 		if (id)
 			epp_values[EPP_INDEX_BALANCE_PERFORMANCE] = id->driver_data;
+
+		if (hybrid_id) {
+			hybrid_scaling_factor = hybrid_id->driver_data;
+			pr_debug("hybrid scaling factor: %d\n", hybrid_scaling_factor);
+		}
+
 	}
 
 	mutex_lock(&intel_pstate_driver_lock);
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c
index 1262a7773ef3..de50c00ba218 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c
@@ -299,22 +299,6 @@ theend:
 	return err;
 }
 
-static void sun8i_ce_cipher_run(struct crypto_engine *engine, void *areq)
-{
-	struct skcipher_request *breq = container_of(areq, struct skcipher_request, base);
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(breq);
-	struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
-	struct sun8i_ce_dev *ce = op->ce;
-	struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(breq);
-	int flow, err;
-
-	flow = rctx->flow;
-	err = sun8i_ce_run_task(ce, flow, crypto_tfm_alg_name(breq->base.tfm));
-	local_bh_disable();
-	crypto_finalize_skcipher_request(engine, breq, err);
-	local_bh_enable();
-}
-
 static void sun8i_ce_cipher_unprepare(struct crypto_engine *engine,
 				      void *async_req)
 {
@@ -360,6 +344,23 @@ static void sun8i_ce_cipher_unprepare(struct crypto_engine *engine,
 	dma_unmap_single(ce->dev, rctx->addr_key, op->keylen, DMA_TO_DEVICE);
 }
 
+static void sun8i_ce_cipher_run(struct crypto_engine *engine, void *areq)
+{
+	struct skcipher_request *breq = container_of(areq, struct skcipher_request, base);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(breq);
+	struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
+	struct sun8i_ce_dev *ce = op->ce;
+	struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(breq);
+	int flow, err;
+
+	flow = rctx->flow;
+	err = sun8i_ce_run_task(ce, flow, crypto_tfm_alg_name(breq->base.tfm));
+	sun8i_ce_cipher_unprepare(engine, areq);
+	local_bh_disable();
+	crypto_finalize_skcipher_request(engine, breq, err);
+	local_bh_enable();
+}
+
 int sun8i_ce_cipher_do_one(struct crypto_engine *engine, void *areq)
 {
 	int err = sun8i_ce_cipher_prepare(engine, areq);
@@ -368,7 +369,6 @@ int sun8i_ce_cipher_do_one(struct crypto_engine *engine, void *areq)
 		return err;
 
 	sun8i_ce_cipher_run(engine, areq);
-	sun8i_ce_cipher_unprepare(engine, areq);
 	return 0;
 }
 
diff --git a/drivers/crypto/caam/caamalg_qi2.c b/drivers/crypto/caam/caamalg_qi2.c
index a148ff1f0872..a4f6884416a0 100644
--- a/drivers/crypto/caam/caamalg_qi2.c
+++ b/drivers/crypto/caam/caamalg_qi2.c
@@ -4545,6 +4545,7 @@ struct caam_hash_alg {
 	struct list_head entry;
 	struct device *dev;
 	int alg_type;
+	bool is_hmac;
 	struct ahash_alg ahash_alg;
 };
 
@@ -4571,7 +4572,7 @@ static int caam_hash_cra_init(struct crypto_tfm *tfm)
 
 	ctx->dev = caam_hash->dev;
 
-	if (alg->setkey) {
+	if (caam_hash->is_hmac) {
 		ctx->adata.key_dma = dma_map_single_attrs(ctx->dev, ctx->key,
 							  ARRAY_SIZE(ctx->key),
 							  DMA_TO_DEVICE,
@@ -4611,7 +4612,7 @@ static int caam_hash_cra_init(struct crypto_tfm *tfm)
 	 * For keyed hash algorithms shared descriptors
 	 * will be created later in setkey() callback
 	 */
-	return alg->setkey ? 0 : ahash_set_sh_desc(ahash);
+	return caam_hash->is_hmac ? 0 : ahash_set_sh_desc(ahash);
 }
 
 static void caam_hash_cra_exit(struct crypto_tfm *tfm)
@@ -4646,12 +4647,14 @@ static struct caam_hash_alg *caam_hash_alloc(struct device *dev,
 			 template->hmac_name);
 		snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
 			 template->hmac_driver_name);
+		t_alg->is_hmac = true;
 	} else {
 		snprintf(alg->cra_name, CRYPTO_MAX_ALG_NAME, "%s",
 			 template->name);
 		snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
 			 template->driver_name);
 		t_alg->ahash_alg.setkey = NULL;
+		t_alg->is_hmac = false;
 	}
 	alg->cra_module = THIS_MODULE;
 	alg->cra_init = caam_hash_cra_init;
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 290c8500c247..fdd724228c2f 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -1753,6 +1753,7 @@ static struct caam_hash_template driver_hash[] = {
 struct caam_hash_alg {
 	struct list_head entry;
 	int alg_type;
+	bool is_hmac;
 	struct ahash_engine_alg ahash_alg;
 };
 
@@ -1804,7 +1805,7 @@ static int caam_hash_cra_init(struct crypto_tfm *tfm)
 	} else {
 		if (priv->era >= 6) {
 			ctx->dir = DMA_BIDIRECTIONAL;
-			ctx->key_dir = alg->setkey ? DMA_TO_DEVICE : DMA_NONE;
+			ctx->key_dir = caam_hash->is_hmac ? DMA_TO_DEVICE : DMA_NONE;
 		} else {
 			ctx->dir = DMA_TO_DEVICE;
 			ctx->key_dir = DMA_NONE;
@@ -1862,7 +1863,7 @@ static int caam_hash_cra_init(struct crypto_tfm *tfm)
 	 * For keyed hash algorithms shared descriptors
 	 * will be created later in setkey() callback
 	 */
-	return alg->setkey ? 0 : ahash_set_sh_desc(ahash);
+	return caam_hash->is_hmac ? 0 : ahash_set_sh_desc(ahash);
 }
 
 static void caam_hash_cra_exit(struct crypto_tfm *tfm)
@@ -1915,12 +1916,14 @@ caam_hash_alloc(struct caam_hash_template *template,
 			 template->hmac_name);
 		snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
 			 template->hmac_driver_name);
+		t_alg->is_hmac = true;
 	} else {
 		snprintf(alg->cra_name, CRYPTO_MAX_ALG_NAME, "%s",
 			 template->name);
 		snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
 			 template->driver_name);
 		halg->setkey = NULL;
+		t_alg->is_hmac = false;
 	}
 	alg->cra_module = THIS_MODULE;
 	alg->cra_init = caam_hash_cra_init;
diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index e4d3f45242f6..b04bc1d3d627 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -534,10 +534,16 @@ EXPORT_SYMBOL_GPL(sev_platform_init);
 
 static int __sev_platform_shutdown_locked(int *error)
 {
-	struct sev_device *sev = psp_master->sev_data;
+	struct psp_device *psp = psp_master;
+	struct sev_device *sev;
 	int ret;
 
-	if (!sev || sev->state == SEV_STATE_UNINIT)
+	if (!psp || !psp->sev_data)
+		return 0;
+
+	sev = psp->sev_data;
+
+	if (sev->state == SEV_STATE_UNINIT)
 		return 0;
 
 	ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, NULL, error);
diff --git a/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c b/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c
index 479062aa5e6b..94a0ebb03d8c 100644
--- a/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c
+++ b/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c
@@ -463,6 +463,7 @@ void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data, u32 dev_id)
 		hw_data->fw_name = ADF_402XX_FW;
 		hw_data->fw_mmp_name = ADF_402XX_MMP;
 		hw_data->uof_get_name = uof_get_name_402xx;
+		hw_data->get_ena_thd_mask = get_ena_thd_mask;
 		break;
 	case ADF_401XX_PCI_DEVICE_ID:
 		hw_data->fw_name = ADF_4XXX_FW;
diff --git a/drivers/crypto/rockchip/rk3288_crypto_ahash.c b/drivers/crypto/rockchip/rk3288_crypto_ahash.c
index 1b13b4aa16ec..a235e6c300f1 100644
--- a/drivers/crypto/rockchip/rk3288_crypto_ahash.c
+++ b/drivers/crypto/rockchip/rk3288_crypto_ahash.c
@@ -332,12 +332,12 @@ static int rk_hash_run(struct crypto_engine *engine, void *breq)
 theend:
 	pm_runtime_put_autosuspend(rkc->dev);
 
+	rk_hash_unprepare(engine, breq);
+
 	local_bh_disable();
 	crypto_finalize_hash_request(engine, breq, err);
 	local_bh_enable();
 
-	rk_hash_unprepare(engine, breq);
-
 	return 0;
 }
 
diff --git a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c
index 2621ff8a9376..de53eddf6796 100644
--- a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c
+++ b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c
@@ -104,7 +104,8 @@ static void virtio_crypto_dataq_akcipher_callback(struct virtio_crypto_request *
 }
 
 static int virtio_crypto_alg_akcipher_init_session(struct virtio_crypto_akcipher_ctx *ctx,
-		struct virtio_crypto_ctrl_header *header, void *para,
+		struct virtio_crypto_ctrl_header *header,
+		struct virtio_crypto_akcipher_session_para *para,
 		const uint8_t *key, unsigned int keylen)
 {
 	struct scatterlist outhdr_sg, key_sg, inhdr_sg, *sgs[3];
@@ -128,7 +129,7 @@ static int virtio_crypto_alg_akcipher_init_session(struct virtio_crypto_akcipher
 
 	ctrl = &vc_ctrl_req->ctrl;
 	memcpy(&ctrl->header, header, sizeof(ctrl->header));
-	memcpy(&ctrl->u, para, sizeof(ctrl->u));
+	memcpy(&ctrl->u.akcipher_create_session.para, para, sizeof(*para));
 	input = &vc_ctrl_req->input;
 	input->status = cpu_to_le32(VIRTIO_CRYPTO_ERR);
 
diff --git a/drivers/cxl/Kconfig b/drivers/cxl/Kconfig
index 8ea1d340e438..67998dbd1d46 100644
--- a/drivers/cxl/Kconfig
+++ b/drivers/cxl/Kconfig
@@ -5,6 +5,7 @@ menuconfig CXL_BUS
 	select FW_LOADER
 	select FW_UPLOAD
 	select PCI_DOE
+	select FIRMWARE_TABLE
 	help
 	  CXL is a bus that is electrically compatible with PCI Express, but
 	  layers three protocols on that signalling (CXL.io, CXL.cache, and
@@ -54,8 +55,10 @@ config CXL_MEM_RAW_COMMANDS
 config CXL_ACPI
 	tristate "CXL ACPI: Platform Support"
 	depends on ACPI
+	depends on ACPI_NUMA
 	default CXL_BUS
 	select ACPI_TABLE_LIB
+	select ACPI_HMAT
 	help
 	  Enable support for host managed device memory (HDM) resources
 	  published by a platform's ACPI CXL memory layout description.  See
diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c
index 2034eb4ce83f..1a3e6aafbdcc 100644
--- a/drivers/cxl/acpi.c
+++ b/drivers/cxl/acpi.c
@@ -6,6 +6,7 @@
 #include <linux/kernel.h>
 #include <linux/acpi.h>
 #include <linux/pci.h>
+#include <linux/node.h>
 #include <asm/div64.h>
 #include "cxlpci.h"
 #include "cxl.h"
@@ -17,6 +18,10 @@ struct cxl_cxims_data {
 	u64 xormaps[] __counted_by(nr_maps);
 };
 
+static const guid_t acpi_cxl_qtg_id_guid =
+	GUID_INIT(0xF365F9A6, 0xA7DE, 0x4071,
+		  0xA6, 0x6A, 0xB4, 0x0C, 0x0B, 0x4F, 0x8E, 0x52);
+
 /*
  * Find a targets entry (n) in the host bridge interleave list.
  * CXL Specification 3.0 Table 9-22
@@ -194,31 +199,144 @@ struct cxl_cfmws_context {
 	int id;
 };
 
-static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg,
-			   const unsigned long end)
+/**
+ * cxl_acpi_evaluate_qtg_dsm - Retrieve QTG ids via ACPI _DSM
+ * @handle: ACPI handle
+ * @coord: performance access coordinates
+ * @entries: number of QTG IDs to return
+ * @qos_class: int array provided by caller to return QTG IDs
+ *
+ * Return: number of QTG IDs returned, or -errno for errors
+ *
+ * Issue QTG _DSM with accompanied bandwidth and latency data in order to get
+ * the QTG IDs that are suitable for the performance point in order of most
+ * suitable to least suitable. Write back array of QTG IDs and return the
+ * actual number of QTG IDs written back.
+ */
+static int
+cxl_acpi_evaluate_qtg_dsm(acpi_handle handle, struct access_coordinate *coord,
+			  int entries, int *qos_class)
+{
+	union acpi_object *out_obj, *out_buf, *obj;
+	union acpi_object in_array[4] = {
+		[0].integer = { ACPI_TYPE_INTEGER, coord->read_latency },
+		[1].integer = { ACPI_TYPE_INTEGER, coord->write_latency },
+		[2].integer = { ACPI_TYPE_INTEGER, coord->read_bandwidth },
+		[3].integer = { ACPI_TYPE_INTEGER, coord->write_bandwidth },
+	};
+	union acpi_object in_obj = {
+		.package = {
+			.type = ACPI_TYPE_PACKAGE,
+			.count = 4,
+			.elements = in_array,
+		},
+	};
+	int count, pkg_entries, i;
+	u16 max_qtg;
+	int rc;
+
+	if (!entries)
+		return -EINVAL;
+
+	out_obj = acpi_evaluate_dsm(handle, &acpi_cxl_qtg_id_guid, 1, 1, &in_obj);
+	if (!out_obj)
+		return -ENXIO;
+
+	if (out_obj->type != ACPI_TYPE_PACKAGE) {
+		rc = -ENXIO;
+		goto out;
+	}
+
+	/* Check Max QTG ID */
+	obj = &out_obj->package.elements[0];
+	if (obj->type != ACPI_TYPE_INTEGER) {
+		rc = -ENXIO;
+		goto out;
+	}
+
+	max_qtg = obj->integer.value;
+
+	/* It's legal to have 0 QTG entries */
+	pkg_entries = out_obj->package.count;
+	if (pkg_entries <= 1) {
+		rc = 0;
+		goto out;
+	}
+
+	/* Retrieve QTG IDs package */
+	obj = &out_obj->package.elements[1];
+	if (obj->type != ACPI_TYPE_PACKAGE) {
+		rc = -ENXIO;
+		goto out;
+	}
+
+	pkg_entries = obj->package.count;
+	count = min(entries, pkg_entries);
+	for (i = 0; i < count; i++) {
+		u16 qtg_id;
+
+		out_buf = &obj->package.elements[i];
+		if (out_buf->type != ACPI_TYPE_INTEGER) {
+			rc = -ENXIO;
+			goto out;
+		}
+
+		qtg_id = out_buf->integer.value;
+		if (qtg_id > max_qtg)
+			pr_warn("QTG ID %u greater than MAX %u\n",
+				qtg_id, max_qtg);
+
+		qos_class[i] = qtg_id;
+	}
+	rc = count;
+
+out:
+	ACPI_FREE(out_obj);
+	return rc;
+}
+
+static int cxl_acpi_qos_class(struct cxl_root *cxl_root,
+			      struct access_coordinate *coord, int entries,
+			      int *qos_class)
+{
+	struct device *dev = cxl_root->port.uport_dev;
+	acpi_handle handle;
+
+	if (!dev_is_platform(dev))
+		return -ENODEV;
+
+	handle = ACPI_HANDLE(dev);
+	if (!handle)
+		return -ENODEV;
+
+	return cxl_acpi_evaluate_qtg_dsm(handle, coord, entries, qos_class);
+}
+
+static const struct cxl_root_ops acpi_root_ops = {
+	.qos_class = cxl_acpi_qos_class,
+};
+
+static int __cxl_parse_cfmws(struct acpi_cedt_cfmws *cfmws,
+			     struct cxl_cfmws_context *ctx)
 {
 	int target_map[CXL_DECODER_MAX_INTERLEAVE];
-	struct cxl_cfmws_context *ctx = arg;
 	struct cxl_port *root_port = ctx->root_port;
 	struct resource *cxl_res = ctx->cxl_res;
 	struct cxl_cxims_context cxims_ctx;
 	struct cxl_root_decoder *cxlrd;
 	struct device *dev = ctx->dev;
-	struct acpi_cedt_cfmws *cfmws;
 	cxl_calc_hb_fn cxl_calc_hb;
 	struct cxl_decoder *cxld;
 	unsigned int ways, i, ig;
 	struct resource *res;
 	int rc;
 
-	cfmws = (struct acpi_cedt_cfmws *) header;
-
 	rc = cxl_acpi_cfmws_verify(dev, cfmws);
 	if (rc) {
 		dev_err(dev, "CFMWS range %#llx-%#llx not registered\n",
 			cfmws->base_hpa,
 			cfmws->base_hpa + cfmws->window_size - 1);
-		return 0;
+		return rc;
 	}
 
 	rc = eiw_to_ways(cfmws->interleave_ways, &ways);
@@ -254,7 +372,7 @@ static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg,
 
 	cxlrd = cxl_root_decoder_alloc(root_port, ways, cxl_calc_hb);
 	if (IS_ERR(cxlrd))
-		return 0;
+		return PTR_ERR(cxlrd);
 
 	cxld = &cxlrd->cxlsd.cxld;
 	cxld->flags = cfmws_to_decoder_flags(cfmws->restrictions);
@@ -298,16 +416,7 @@ err_xormap:
 		put_device(&cxld->dev);
 	else
 		rc = cxl_decoder_autoremove(dev, cxld);
-	if (rc) {
-		dev_err(dev, "Failed to add decode range: %pr", res);
-		return rc;
-	}
-	dev_dbg(dev, "add: %s node: %d range [%#llx - %#llx]\n",
-		dev_name(&cxld->dev),
-		phys_to_target_node(cxld->hpa_range.start),
-		cxld->hpa_range.start, cxld->hpa_range.end);
-
-	return 0;
+	return rc;
 
 err_insert:
 	kfree(res->name);
@@ -316,6 +425,29 @@ err_name:
 	return -ENOMEM;
 }
 
+static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg,
+			   const unsigned long end)
+{
+	struct acpi_cedt_cfmws *cfmws = (struct acpi_cedt_cfmws *)header;
+	struct cxl_cfmws_context *ctx = arg;
+	struct device *dev = ctx->dev;
+	int rc;
+
+	rc = __cxl_parse_cfmws(cfmws, ctx);
+	if (rc)
+		dev_err(dev,
+			"Failed to add decode range: [%#llx - %#llx] (%d)\n",
+			cfmws->base_hpa,
+			cfmws->base_hpa + cfmws->window_size - 1, rc);
+	else
+		dev_dbg(dev, "decode range: node: %d range [%#llx - %#llx]\n",
+			phys_to_target_node(cfmws->base_hpa), cfmws->base_hpa,
+			cfmws->base_hpa + cfmws->window_size - 1);
+
+	/* never fail cxl_acpi load for a single window failure */
+	return 0;
+}
+
 __mock struct acpi_device *to_cxl_host_bridge(struct device *host,
 					      struct device *dev)
 {
@@ -389,8 +521,29 @@ static int cxl_get_chbs(struct device *dev, struct acpi_device *hb,
 	return 0;
 }
 
+static int get_genport_coordinates(struct device *dev, struct cxl_dport *dport)
+{
+	struct acpi_device *hb = to_cxl_host_bridge(NULL, dev);
+	u32 uid;
+	int rc;
+
+	if (kstrtou32(acpi_device_uid(hb), 0, &uid))
+		return -EINVAL;
+
+	rc = acpi_get_genport_coordinates(uid, &dport->hb_coord);
+	if (rc < 0)
+		return rc;
+
+	/* Adjust back to picoseconds from nanoseconds */
+	dport->hb_coord.read_latency *= 1000;
+	dport->hb_coord.write_latency *= 1000;
+
+	return 0;
+}
+
 static int add_host_bridge_dport(struct device *match, void *arg)
 {
+	int ret;
 	acpi_status rc;
 	struct device *bridge;
 	struct cxl_dport *dport;
@@ -440,6 +593,10 @@ static int add_host_bridge_dport(struct device *match, void *arg)
 	if (IS_ERR(dport))
 		return PTR_ERR(dport);
 
+	ret = get_genport_coordinates(match, dport);
+	if (ret)
+		dev_dbg(match, "Failed to get generic port perf coordinates.\n");
+
 	return 0;
 }
 
@@ -656,6 +813,7 @@ static int cxl_acpi_probe(struct platform_device *pdev)
 {
 	int rc;
 	struct resource *cxl_res;
+	struct cxl_root *cxl_root;
 	struct cxl_port *root_port;
 	struct device *host = &pdev->dev;
 	struct acpi_device *adev = ACPI_COMPANION(host);
@@ -675,9 +833,10 @@ static int cxl_acpi_probe(struct platform_device *pdev)
 	cxl_res->end = -1;
 	cxl_res->flags = IORESOURCE_MEM;
 
-	root_port = devm_cxl_add_port(host, host, CXL_RESOURCE_NONE, NULL);
-	if (IS_ERR(root_port))
-		return PTR_ERR(root_port);
+	cxl_root = devm_cxl_add_root(host, &acpi_root_ops);
+	if (IS_ERR(cxl_root))
+		return PTR_ERR(cxl_root);
+	root_port = &cxl_root->port;
 
 	rc = bus_for_each_dev(adev->dev.bus, NULL, root_port,
 			      add_host_bridge_dport);
diff --git a/drivers/cxl/core/Makefile b/drivers/cxl/core/Makefile
index 1f66b5d4d935..9259bcc6773c 100644
--- a/drivers/cxl/core/Makefile
+++ b/drivers/cxl/core/Makefile
@@ -13,5 +13,6 @@ cxl_core-y += mbox.o
 cxl_core-y += pci.o
 cxl_core-y += hdm.o
 cxl_core-y += pmu.o
+cxl_core-y += cdat.o
 cxl_core-$(CONFIG_TRACING) += trace.o
 cxl_core-$(CONFIG_CXL_REGION) += region.o
diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
new file mode 100644
index 000000000000..08fd0baea7a0
--- /dev/null
+++ b/drivers/cxl/core/cdat.c
@@ -0,0 +1,487 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2023 Intel Corporation. All rights reserved. */
+#include <linux/acpi.h>
+#include <linux/xarray.h>
+#include <linux/fw_table.h>
+#include <linux/node.h>
+#include <linux/overflow.h>
+#include "cxlpci.h"
+#include "cxlmem.h"
+#include "core.h"
+#include "cxl.h"
+
+struct dsmas_entry {
+	struct range dpa_range;
+	u8 handle;
+	struct access_coordinate coord;
+
+	int entries;
+	int qos_class;
+};
+
+static int cdat_dsmas_handler(union acpi_subtable_headers *header, void *arg,
+			      const unsigned long end)
+{
+	struct acpi_cdat_header *hdr = &header->cdat;
+	struct acpi_cdat_dsmas *dsmas;
+	int size = sizeof(*hdr) + sizeof(*dsmas);
+	struct xarray *dsmas_xa = arg;
+	struct dsmas_entry *dent;
+	u16 len;
+	int rc;
+
+	len = le16_to_cpu((__force __le16)hdr->length);
+	if (len != size || (unsigned long)hdr + len > end) {
+		pr_warn("Malformed DSMAS table length: (%u:%u)\n", size, len);
+		return -EINVAL;
+	}
+
+	/* Skip common header */
+	dsmas = (struct acpi_cdat_dsmas *)(hdr + 1);
+
+	dent = kzalloc(sizeof(*dent), GFP_KERNEL);
+	if (!dent)
+		return -ENOMEM;
+
+	dent->handle = dsmas->dsmad_handle;
+	dent->dpa_range.start = le64_to_cpu((__force __le64)dsmas->dpa_base_address);
+	dent->dpa_range.end = le64_to_cpu((__force __le64)dsmas->dpa_base_address) +
+			      le64_to_cpu((__force __le64)dsmas->dpa_length) - 1;
+
+	rc = xa_insert(dsmas_xa, dent->handle, dent, GFP_KERNEL);
+	if (rc) {
+		kfree(dent);
+		return rc;
+	}
+
+	return 0;
+}
+
+static void cxl_access_coordinate_set(struct access_coordinate *coord,
+				      int access, unsigned int val)
+{
+	switch (access) {
+	case ACPI_HMAT_ACCESS_LATENCY:
+		coord->read_latency = val;
+		coord->write_latency = val;
+		break;
+	case ACPI_HMAT_READ_LATENCY:
+		coord->read_latency = val;
+		break;
+	case ACPI_HMAT_WRITE_LATENCY:
+		coord->write_latency = val;
+		break;
+	case ACPI_HMAT_ACCESS_BANDWIDTH:
+		coord->read_bandwidth = val;
+		coord->write_bandwidth = val;
+		break;
+	case ACPI_HMAT_READ_BANDWIDTH:
+		coord->read_bandwidth = val;
+		break;
+	case ACPI_HMAT_WRITE_BANDWIDTH:
+		coord->write_bandwidth = val;
+		break;
+	}
+}
+
+static int cdat_dslbis_handler(union acpi_subtable_headers *header, void *arg,
+			       const unsigned long end)
+{
+	struct acpi_cdat_header *hdr = &header->cdat;
+	struct acpi_cdat_dslbis *dslbis;
+	int size = sizeof(*hdr) + sizeof(*dslbis);
+	struct xarray *dsmas_xa = arg;
+	struct dsmas_entry *dent;
+	__le64 le_base;
+	__le16 le_val;
+	u64 val;
+	u16 len;
+	int rc;
+
+	len = le16_to_cpu((__force __le16)hdr->length);
+	if (len != size || (unsigned long)hdr + len > end) {
+		pr_warn("Malformed DSLBIS table length: (%u:%u)\n", size, len);
+		return -EINVAL;
+	}
+
+	/* Skip common header */
+	dslbis = (struct acpi_cdat_dslbis *)(hdr + 1);
+
+	/* Skip unrecognized data type */
+	if (dslbis->data_type > ACPI_HMAT_WRITE_BANDWIDTH)
+		return 0;
+
+	/* Not a memory type, skip */
+	if ((dslbis->flags & ACPI_HMAT_MEMORY_HIERARCHY) != ACPI_HMAT_MEMORY)
+		return 0;
+
+	dent = xa_load(dsmas_xa, dslbis->handle);
+	if (!dent) {
+		pr_warn("No matching DSMAS entry for DSLBIS entry.\n");
+		return 0;
+	}
+
+	le_base = (__force __le64)dslbis->entry_base_unit;
+	le_val = (__force __le16)dslbis->entry[0];
+	rc = check_mul_overflow(le64_to_cpu(le_base),
+				le16_to_cpu(le_val), &val);
+	if (rc)
+		pr_warn("DSLBIS value overflowed.\n");
+
+	cxl_access_coordinate_set(&dent->coord, dslbis->data_type, val);
+
+	return 0;
+}
+
+static int cdat_table_parse_output(int rc)
+{
+	if (rc < 0)
+		return rc;
+	if (rc == 0)
+		return -ENOENT;
+
+	return 0;
+}
+
+static int cxl_cdat_endpoint_process(struct cxl_port *port,
+				     struct xarray *dsmas_xa)
+{
+	int rc;
+
+	rc = cdat_table_parse(ACPI_CDAT_TYPE_DSMAS, cdat_dsmas_handler,
+			      dsmas_xa, port->cdat.table);
+	rc = cdat_table_parse_output(rc);
+	if (rc)
+		return rc;
+
+	rc = cdat_table_parse(ACPI_CDAT_TYPE_DSLBIS, cdat_dslbis_handler,
+			      dsmas_xa, port->cdat.table);
+	return cdat_table_parse_output(rc);
+}
+
+static int cxl_port_perf_data_calculate(struct cxl_port *port,
+					struct xarray *dsmas_xa)
+{
+	struct access_coordinate c;
+	struct dsmas_entry *dent;
+	int valid_entries = 0;
+	unsigned long index;
+	int rc;
+
+	rc = cxl_endpoint_get_perf_coordinates(port, &c);
+	if (rc) {
+		dev_dbg(&port->dev, "Failed to retrieve perf coordinates.\n");
+		return rc;
+	}
+
+	struct cxl_root *cxl_root __free(put_cxl_root) = find_cxl_root(port);
+
+	if (!cxl_root)
+		return -ENODEV;
+
+	if (!cxl_root->ops || !cxl_root->ops->qos_class)
+		return -EOPNOTSUPP;
+
+	xa_for_each(dsmas_xa, index, dent) {
+		int qos_class;
+
+		dent->coord.read_latency = dent->coord.read_latency +
+					   c.read_latency;
+		dent->coord.write_latency = dent->coord.write_latency +
+					    c.write_latency;
+		dent->coord.read_bandwidth = min_t(int, c.read_bandwidth,
+						   dent->coord.read_bandwidth);
+		dent->coord.write_bandwidth = min_t(int, c.write_bandwidth,
+						    dent->coord.write_bandwidth);
+
+		dent->entries = 1;
+		rc = cxl_root->ops->qos_class(cxl_root, &dent->coord, 1,
+					      &qos_class);
+		if (rc != 1)
+			continue;
+
+		valid_entries++;
+		dent->qos_class = qos_class;
+	}
+
+	if (!valid_entries)
+		return -ENOENT;
+
+	return 0;
+}
+
+static void update_perf_entry(struct device *dev, struct dsmas_entry *dent,
+			      struct cxl_dpa_perf *dpa_perf)
+{
+	dpa_perf->dpa_range = dent->dpa_range;
+	dpa_perf->coord = dent->coord;
+	dpa_perf->qos_class = dent->qos_class;
+	dev_dbg(dev,
+		"DSMAS: dpa: %#llx qos: %d read_bw: %d write_bw %d read_lat: %d write_lat: %d\n",
+		dent->dpa_range.start, dpa_perf->qos_class,
+		dent->coord.read_bandwidth, dent->coord.write_bandwidth,
+		dent->coord.read_latency, dent->coord.write_latency);
+}
+
+static void cxl_memdev_set_qos_class(struct cxl_dev_state *cxlds,
+				     struct xarray *dsmas_xa)
+{
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+	struct device *dev = cxlds->dev;
+	struct range pmem_range = {
+		.start = cxlds->pmem_res.start,
+		.end = cxlds->pmem_res.end,
+	};
+	struct range ram_range = {
+		.start = cxlds->ram_res.start,
+		.end = cxlds->ram_res.end,
+	};
+	struct dsmas_entry *dent;
+	unsigned long index;
+
+	xa_for_each(dsmas_xa, index, dent) {
+		if (resource_size(&cxlds->ram_res) &&
+		    range_contains(&ram_range, &dent->dpa_range))
+			update_perf_entry(dev, dent, &mds->ram_perf);
+		else if (resource_size(&cxlds->pmem_res) &&
+			 range_contains(&pmem_range, &dent->dpa_range))
+			update_perf_entry(dev, dent, &mds->pmem_perf);
+		else
+			dev_dbg(dev, "no partition for dsmas dpa: %#llx\n",
+				dent->dpa_range.start);
+	}
+}
+
+static int match_cxlrd_qos_class(struct device *dev, void *data)
+{
+	int dev_qos_class = *(int *)data;
+	struct cxl_root_decoder *cxlrd;
+
+	if (!is_root_decoder(dev))
+		return 0;
+
+	cxlrd = to_cxl_root_decoder(dev);
+	if (cxlrd->qos_class == CXL_QOS_CLASS_INVALID)
+		return 0;
+
+	if (cxlrd->qos_class == dev_qos_class)
+		return 1;
+
+	return 0;
+}
+
+static void reset_dpa_perf(struct cxl_dpa_perf *dpa_perf)
+{
+	*dpa_perf = (struct cxl_dpa_perf) {
+		.qos_class = CXL_QOS_CLASS_INVALID,
+	};
+}
+
+static bool cxl_qos_match(struct cxl_port *root_port,
+			  struct cxl_dpa_perf *dpa_perf)
+{
+	if (dpa_perf->qos_class == CXL_QOS_CLASS_INVALID)
+		return false;
+
+	if (!device_for_each_child(&root_port->dev, &dpa_perf->qos_class,
+				   match_cxlrd_qos_class))
+		return false;
+
+	return true;
+}
+
+static int match_cxlrd_hb(struct device *dev, void *data)
+{
+	struct device *host_bridge = data;
+	struct cxl_switch_decoder *cxlsd;
+	struct cxl_root_decoder *cxlrd;
+
+	if (!is_root_decoder(dev))
+		return 0;
+
+	cxlrd = to_cxl_root_decoder(dev);
+	cxlsd = &cxlrd->cxlsd;
+
+	guard(rwsem_read)(&cxl_region_rwsem);
+	for (int i = 0; i < cxlsd->nr_targets; i++) {
+		if (host_bridge == cxlsd->target[i]->dport_dev)
+			return 1;
+	}
+
+	return 0;
+}
+
+static int cxl_qos_class_verify(struct cxl_memdev *cxlmd)
+{
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+	struct cxl_port *root_port;
+	int rc;
+
+	struct cxl_root *cxl_root __free(put_cxl_root) =
+		find_cxl_root(cxlmd->endpoint);
+
+	if (!cxl_root)
+		return -ENODEV;
+
+	root_port = &cxl_root->port;
+
+	/* Check that the QTG IDs are all sane between end device and root decoders */
+	if (!cxl_qos_match(root_port, &mds->ram_perf))
+		reset_dpa_perf(&mds->ram_perf);
+	if (!cxl_qos_match(root_port, &mds->pmem_perf))
+		reset_dpa_perf(&mds->pmem_perf);
+
+	/* Check to make sure that the device's host bridge is under a root decoder */
+	rc = device_for_each_child(&root_port->dev,
+				   cxlmd->endpoint->host_bridge, match_cxlrd_hb);
+	if (!rc) {
+		reset_dpa_perf(&mds->ram_perf);
+		reset_dpa_perf(&mds->pmem_perf);
+	}
+
+	return rc;
+}
+
+static void discard_dsmas(struct xarray *xa)
+{
+	unsigned long index;
+	void *ent;
+
+	xa_for_each(xa, index, ent) {
+		xa_erase(xa, index);
+		kfree(ent);
+	}
+	xa_destroy(xa);
+}
+DEFINE_FREE(dsmas, struct xarray *, if (_T) discard_dsmas(_T))
+
+void cxl_endpoint_parse_cdat(struct cxl_port *port)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct xarray __dsmas_xa;
+	struct xarray *dsmas_xa __free(dsmas) = &__dsmas_xa;
+	int rc;
+
+	xa_init(&__dsmas_xa);
+	if (!port->cdat.table)
+		return;
+
+	rc = cxl_cdat_endpoint_process(port, dsmas_xa);
+	if (rc < 0) {
+		dev_dbg(&port->dev, "Failed to parse CDAT: %d\n", rc);
+		return;
+	}
+
+	rc = cxl_port_perf_data_calculate(port, dsmas_xa);
+	if (rc) {
+		dev_dbg(&port->dev, "Failed to do perf coord calculations.\n");
+		return;
+	}
+
+	cxl_memdev_set_qos_class(cxlds, dsmas_xa);
+	cxl_qos_class_verify(cxlmd);
+	cxl_memdev_update_perf(cxlmd);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_endpoint_parse_cdat, CXL);
+
+static int cdat_sslbis_handler(union acpi_subtable_headers *header, void *arg,
+			       const unsigned long end)
+{
+	struct acpi_cdat_sslbis *sslbis;
+	int size = sizeof(header->cdat) + sizeof(*sslbis);
+	struct cxl_port *port = arg;
+	struct device *dev = &port->dev;
+	struct acpi_cdat_sslbe *entry;
+	int remain, entries, i;
+	u16 len;
+
+	len = le16_to_cpu((__force __le16)header->cdat.length);
+	remain = len - size;
+	if (!remain || remain % sizeof(*entry) ||
+	    (unsigned long)header + len > end) {
+		dev_warn(dev, "Malformed SSLBIS table length: (%u)\n", len);
+		return -EINVAL;
+	}
+
+	/* Skip common header */
+	sslbis = (struct acpi_cdat_sslbis *)((unsigned long)header +
+					     sizeof(header->cdat));
+
+	/* Unrecognized data type, we can skip */
+	if (sslbis->data_type > ACPI_HMAT_WRITE_BANDWIDTH)
+		return 0;
+
+	entries = remain / sizeof(*entry);
+	entry = (struct acpi_cdat_sslbe *)((unsigned long)header + sizeof(*sslbis));
+
+	for (i = 0; i < entries; i++) {
+		u16 x = le16_to_cpu((__force __le16)entry->portx_id);
+		u16 y = le16_to_cpu((__force __le16)entry->porty_id);
+		__le64 le_base;
+		__le16 le_val;
+		struct cxl_dport *dport;
+		unsigned long index;
+		u16 dsp_id;
+		u64 val;
+
+		switch (x) {
+		case ACPI_CDAT_SSLBIS_US_PORT:
+			dsp_id = y;
+			break;
+		case ACPI_CDAT_SSLBIS_ANY_PORT:
+			switch (y) {
+			case ACPI_CDAT_SSLBIS_US_PORT:
+				dsp_id = x;
+				break;
+			case ACPI_CDAT_SSLBIS_ANY_PORT:
+				dsp_id = ACPI_CDAT_SSLBIS_ANY_PORT;
+				break;
+			default:
+				dsp_id = y;
+				break;
+			}
+			break;
+		default:
+			dsp_id = x;
+			break;
+		}
+
+		le_base = (__force __le64)sslbis->entry_base_unit;
+		le_val = (__force __le16)entry->latency_or_bandwidth;
+
+		if (check_mul_overflow(le64_to_cpu(le_base),
+				       le16_to_cpu(le_val), &val))
+			dev_warn(dev, "SSLBIS value overflowed!\n");
+
+		xa_for_each(&port->dports, index, dport) {
+			if (dsp_id == ACPI_CDAT_SSLBIS_ANY_PORT ||
+			    dsp_id == dport->port_id)
+				cxl_access_coordinate_set(&dport->sw_coord,
+							  sslbis->data_type,
+							  val);
+		}
+
+		entry++;
+	}
+
+	return 0;
+}
+
+void cxl_switch_parse_cdat(struct cxl_port *port)
+{
+	int rc;
+
+	if (!port->cdat.table)
+		return;
+
+	rc = cdat_table_parse(ACPI_CDAT_TYPE_SSLBIS, cdat_sslbis_handler,
+			      port, port->cdat.table);
+	rc = cdat_table_parse_output(rc);
+	if (rc)
+		dev_dbg(&port->dev, "Failed to parse SSLBIS: %d\n", rc);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_switch_parse_cdat, CXL);
+
+MODULE_IMPORT_NS(CXL);
diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 86d7ba23235e..3b64fb1b9ed0 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -88,4 +88,6 @@ enum cxl_poison_trace_type {
 	CXL_POISON_TRACE_CLEAR,
 };
 
+long cxl_pci_get_latency(struct pci_dev *pdev);
+
 #endif /* __CXL_CORE_H__ */
diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 36270dcfb42e..9adda4795eb7 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -63,6 +63,7 @@ static struct cxl_mem_command cxl_mem_commands[CXL_MEM_COMMAND_ID_MAX] = {
 	CXL_CMD(GET_SHUTDOWN_STATE, 0, 0x1, 0),
 	CXL_CMD(SET_SHUTDOWN_STATE, 0x1, 0, 0),
 	CXL_CMD(GET_SCAN_MEDIA_CAPS, 0x10, 0x4, 0),
+	CXL_CMD(GET_TIMESTAMP, 0, 0x8, 0),
 };
 
 /*
@@ -836,54 +837,37 @@ out:
 }
 EXPORT_SYMBOL_NS_GPL(cxl_enumerate_cmds, CXL);
 
-/*
- * General Media Event Record
- * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
- */
-static const uuid_t gen_media_event_uuid =
-	UUID_INIT(0xfbcd0a77, 0xc260, 0x417f,
-		  0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6);
-
-/*
- * DRAM Event Record
- * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
- */
-static const uuid_t dram_event_uuid =
-	UUID_INIT(0x601dcbb3, 0x9c06, 0x4eab,
-		  0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24);
-
-/*
- * Memory Module Event Record
- * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
- */
-static const uuid_t mem_mod_event_uuid =
-	UUID_INIT(0xfe927475, 0xdd59, 0x4339,
-		  0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74);
-
-static void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
-				   enum cxl_event_log_type type,
-				   struct cxl_event_record_raw *record)
+void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
+			    enum cxl_event_log_type type,
+			    enum cxl_event_type event_type,
+			    const uuid_t *uuid, union cxl_event *evt)
 {
-	uuid_t *id = &record->hdr.id;
-
-	if (uuid_equal(id, &gen_media_event_uuid)) {
-		struct cxl_event_gen_media *rec =
-				(struct cxl_event_gen_media *)record;
+	if (event_type == CXL_CPER_EVENT_GEN_MEDIA)
+		trace_cxl_general_media(cxlmd, type, &evt->gen_media);
+	else if (event_type == CXL_CPER_EVENT_DRAM)
+		trace_cxl_dram(cxlmd, type, &evt->dram);
+	else if (event_type == CXL_CPER_EVENT_MEM_MODULE)
+		trace_cxl_memory_module(cxlmd, type, &evt->mem_module);
+	else
+		trace_cxl_generic_event(cxlmd, type, uuid, &evt->generic);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_event_trace_record, CXL);
 
-		trace_cxl_general_media(cxlmd, type, rec);
-	} else if (uuid_equal(id, &dram_event_uuid)) {
-		struct cxl_event_dram *rec = (struct cxl_event_dram *)record;
+static void __cxl_event_trace_record(const struct cxl_memdev *cxlmd,
+				     enum cxl_event_log_type type,
+				     struct cxl_event_record_raw *record)
+{
+	enum cxl_event_type ev_type = CXL_CPER_EVENT_GENERIC;
+	const uuid_t *uuid = &record->id;
 
-		trace_cxl_dram(cxlmd, type, rec);
-	} else if (uuid_equal(id, &mem_mod_event_uuid)) {
-		struct cxl_event_mem_module *rec =
-				(struct cxl_event_mem_module *)record;
+	if (uuid_equal(uuid, &CXL_EVENT_GEN_MEDIA_UUID))
+		ev_type = CXL_CPER_EVENT_GEN_MEDIA;
+	else if (uuid_equal(uuid, &CXL_EVENT_DRAM_UUID))
+		ev_type = CXL_CPER_EVENT_DRAM;
+	else if (uuid_equal(uuid, &CXL_EVENT_MEM_MODULE_UUID))
+		ev_type = CXL_CPER_EVENT_MEM_MODULE;
 
-		trace_cxl_memory_module(cxlmd, type, rec);
-	} else {
-		/* For unknown record types print just the header */
-		trace_cxl_generic_event(cxlmd, type, record);
-	}
+	cxl_event_trace_record(cxlmd, type, ev_type, uuid, &record->event);
 }
 
 static int cxl_clear_event_record(struct cxl_memdev_state *mds,
@@ -926,7 +910,10 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds,
 	 */
 	i = 0;
 	for (cnt = 0; cnt < total; cnt++) {
-		payload->handles[i++] = get_pl->records[cnt].hdr.handle;
+		struct cxl_event_record_raw *raw = &get_pl->records[cnt];
+		struct cxl_event_generic *gen = &raw->event.generic;
+
+		payload->handles[i++] = gen->hdr.handle;
 		dev_dbg(mds->cxlds.dev, "Event log '%d': Clearing %u\n", log,
 			le16_to_cpu(payload->handles[i]));
 
@@ -991,8 +978,8 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds,
 			break;
 
 		for (i = 0; i < nr_rec; i++)
-			cxl_event_trace_record(cxlmd, type,
-					       &payload->records[i]);
+			__cxl_event_trace_record(cxlmd, type,
+						 &payload->records[i]);
 
 		if (payload->flags & CXL_GET_EVENT_FLAG_OVERFLOW)
 			trace_cxl_overflow(cxlmd, type, payload);
@@ -1404,6 +1391,8 @@ struct cxl_memdev_state *cxl_memdev_state_create(struct device *dev)
 	mds->cxlds.reg_map.host = dev;
 	mds->cxlds.reg_map.resource = CXL_RESOURCE_NONE;
 	mds->cxlds.type = CXL_DEVTYPE_CLASSMEM;
+	mds->ram_perf.qos_class = CXL_QOS_CLASS_INVALID;
+	mds->pmem_perf.qos_class = CXL_QOS_CLASS_INVALID;
 
 	return mds;
 }
diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c
index 2f43d368ba07..d4e259f3a7e9 100644
--- a/drivers/cxl/core/memdev.c
+++ b/drivers/cxl/core/memdev.c
@@ -114,7 +114,7 @@ static DEVICE_ATTR_RO(serial);
 static ssize_t numa_node_show(struct device *dev, struct device_attribute *attr,
 			      char *buf)
 {
-	return sprintf(buf, "%d\n", dev_to_node(dev));
+	return sysfs_emit(buf, "%d\n", dev_to_node(dev));
 }
 static DEVICE_ATTR_RO(numa_node);
 
@@ -447,13 +447,41 @@ static struct attribute *cxl_memdev_attributes[] = {
 	NULL,
 };
 
+static ssize_t pmem_qos_class_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+
+	return sysfs_emit(buf, "%d\n", mds->pmem_perf.qos_class);
+}
+
+static struct device_attribute dev_attr_pmem_qos_class =
+	__ATTR(qos_class, 0444, pmem_qos_class_show, NULL);
+
 static struct attribute *cxl_memdev_pmem_attributes[] = {
 	&dev_attr_pmem_size.attr,
+	&dev_attr_pmem_qos_class.attr,
 	NULL,
 };
 
+static ssize_t ram_qos_class_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+
+	return sysfs_emit(buf, "%d\n", mds->ram_perf.qos_class);
+}
+
+static struct device_attribute dev_attr_ram_qos_class =
+	__ATTR(qos_class, 0444, ram_qos_class_show, NULL);
+
 static struct attribute *cxl_memdev_ram_attributes[] = {
 	&dev_attr_ram_size.attr,
+	&dev_attr_ram_qos_class.attr,
 	NULL,
 };
 
@@ -477,14 +505,42 @@ static struct attribute_group cxl_memdev_attribute_group = {
 	.is_visible = cxl_memdev_visible,
 };
 
+static umode_t cxl_ram_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+
+	if (a == &dev_attr_ram_qos_class.attr)
+		if (mds->ram_perf.qos_class == CXL_QOS_CLASS_INVALID)
+			return 0;
+
+	return a->mode;
+}
+
 static struct attribute_group cxl_memdev_ram_attribute_group = {
 	.name = "ram",
 	.attrs = cxl_memdev_ram_attributes,
+	.is_visible = cxl_ram_visible,
 };
 
+static umode_t cxl_pmem_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+
+	if (a == &dev_attr_pmem_qos_class.attr)
+		if (mds->pmem_perf.qos_class == CXL_QOS_CLASS_INVALID)
+			return 0;
+
+	return a->mode;
+}
+
 static struct attribute_group cxl_memdev_pmem_attribute_group = {
 	.name = "pmem",
 	.attrs = cxl_memdev_pmem_attributes,
+	.is_visible = cxl_pmem_visible,
 };
 
 static umode_t cxl_memdev_security_visible(struct kobject *kobj,
@@ -519,6 +575,13 @@ static const struct attribute_group *cxl_memdev_attribute_groups[] = {
 	NULL,
 };
 
+void cxl_memdev_update_perf(struct cxl_memdev *cxlmd)
+{
+	sysfs_update_group(&cxlmd->dev.kobj, &cxl_memdev_ram_attribute_group);
+	sysfs_update_group(&cxlmd->dev.kobj, &cxl_memdev_pmem_attribute_group);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_memdev_update_perf, CXL);
+
 static const struct device_type cxl_memdev_type = {
 	.name = "cxl_memdev",
 	.release = cxl_memdev_release,
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 37e1652afbc7..e9e6c81ce034 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright(c) 2021 Intel Corporation. All rights reserved. */
+#include <linux/units.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/device.h>
 #include <linux/delay.h>
@@ -476,9 +477,9 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm,
 		allowed++;
 	}
 
-	if (!allowed) {
-		cxl_set_mem_enable(cxlds, 0);
-		info->mem_enabled = 0;
+	if (!allowed && info->mem_enabled) {
+		dev_err(dev, "Range register decodes outside platform defined CXL ranges.\n");
+		return -ENXIO;
 	}
 
 	/*
@@ -931,11 +932,21 @@ static void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds) { }
 void cxl_cor_error_detected(struct pci_dev *pdev)
 {
 	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
+	struct device *dev = &cxlds->cxlmd->dev;
+
+	scoped_guard(device, dev) {
+		if (!dev->driver) {
+			dev_warn(&pdev->dev,
+				 "%s: memdev disabled, abort error handling\n",
+				 dev_name(dev));
+			return;
+		}
 
-	if (cxlds->rcd)
-		cxl_handle_rdport_errors(cxlds);
+		if (cxlds->rcd)
+			cxl_handle_rdport_errors(cxlds);
 
-	cxl_handle_endpoint_cor_ras(cxlds);
+		cxl_handle_endpoint_cor_ras(cxlds);
+	}
 }
 EXPORT_SYMBOL_NS_GPL(cxl_cor_error_detected, CXL);
 
@@ -947,16 +958,25 @@ pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
 	struct device *dev = &cxlmd->dev;
 	bool ue;
 
-	if (cxlds->rcd)
-		cxl_handle_rdport_errors(cxlds);
+	scoped_guard(device, dev) {
+		if (!dev->driver) {
+			dev_warn(&pdev->dev,
+				 "%s: memdev disabled, abort error handling\n",
+				 dev_name(dev));
+			return PCI_ERS_RESULT_DISCONNECT;
+		}
+
+		if (cxlds->rcd)
+			cxl_handle_rdport_errors(cxlds);
+		/*
+		 * A frozen channel indicates an impending reset which is fatal to
+		 * CXL.mem operation, and will likely crash the system. On the off
+		 * chance the situation is recoverable dump the status of the RAS
+		 * capability registers and bounce the active state of the memdev.
+		 */
+		ue = cxl_handle_endpoint_ras(cxlds);
+	}
 
-	/*
-	 * A frozen channel indicates an impending reset which is fatal to
-	 * CXL.mem operation, and will likely crash the system. On the off
-	 * chance the situation is recoverable dump the status of the RAS
-	 * capability registers and bounce the active state of the memdev.
-	 */
-	ue = cxl_handle_endpoint_ras(cxlds);
 
 	switch (state) {
 	case pci_channel_io_normal:
@@ -979,3 +999,38 @@ pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
 	return PCI_ERS_RESULT_NEED_RESET;
 }
 EXPORT_SYMBOL_NS_GPL(cxl_error_detected, CXL);
+
+static int cxl_flit_size(struct pci_dev *pdev)
+{
+	if (cxl_pci_flit_256(pdev))
+		return 256;
+
+	return 68;
+}
+
+/**
+ * cxl_pci_get_latency - calculate the link latency for the PCIe link
+ * @pdev: PCI device
+ *
+ * return: calculated latency or 0 for no latency
+ *
+ * CXL Memory Device SW Guide v1.0 2.11.4 Link latency calculation
+ * Link latency = LinkPropagationLatency + FlitLatency + RetimerLatency
+ * LinkProgationLatency is negligible, so 0 will be used
+ * RetimerLatency is assumed to be negligible and 0 will be used
+ * FlitLatency = FlitSize / LinkBandwidth
+ * FlitSize is defined by spec. CXL rev3.0 4.2.1.
+ * 68B flit is used up to 32GT/s. >32GT/s, 256B flit size is used.
+ * The FlitLatency is converted to picoseconds.
+ */
+long cxl_pci_get_latency(struct pci_dev *pdev)
+{
+	long bw;
+
+	bw = pcie_link_speed_mbps(pdev);
+	if (bw < 0)
+		return 0;
+	bw /= BITS_PER_BYTE;
+
+	return cxl_flit_size(pdev) * MEGA / bw;
+}
diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c
index fc94f5240327..e69625a8d6a1 100644
--- a/drivers/cxl/core/pmem.c
+++ b/drivers/cxl/core/pmem.c
@@ -64,14 +64,14 @@ static int match_nvdimm_bridge(struct device *dev, void *data)
 
 struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_memdev *cxlmd)
 {
-	struct cxl_port *port = find_cxl_root(cxlmd->endpoint);
+	struct cxl_root *cxl_root __free(put_cxl_root) =
+		find_cxl_root(cxlmd->endpoint);
 	struct device *dev;
 
-	if (!port)
+	if (!cxl_root)
 		return NULL;
 
-	dev = device_find_child(&port->dev, NULL, match_nvdimm_bridge);
-	put_device(&port->dev);
+	dev = device_find_child(&cxl_root->port.dev, NULL, match_nvdimm_bridge);
 
 	if (!dev)
 		return NULL;
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index b7c93bb18f6e..e59d9d37aa65 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -9,6 +9,7 @@
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/idr.h>
+#include <linux/node.h>
 #include <cxlmem.h>
 #include <cxlpci.h>
 #include <cxl.h>
@@ -172,14 +173,10 @@ static ssize_t target_list_show(struct device *dev,
 {
 	struct cxl_switch_decoder *cxlsd = to_cxl_switch_decoder(dev);
 	ssize_t offset;
-	unsigned int seq;
 	int rc;
 
-	do {
-		seq = read_seqbegin(&cxlsd->target_lock);
-		rc = emit_target_list(cxlsd, buf);
-	} while (read_seqretry(&cxlsd->target_lock, seq));
-
+	guard(rwsem_read)(&cxl_region_rwsem);
+	rc = emit_target_list(cxlsd, buf);
 	if (rc < 0)
 		return rc;
 	offset = rc;
@@ -541,7 +538,10 @@ static void cxl_port_release(struct device *dev)
 	xa_destroy(&port->dports);
 	xa_destroy(&port->regions);
 	ida_free(&cxl_port_ida, port->id);
-	kfree(port);
+	if (is_cxl_root(port))
+		kfree(to_cxl_root(port));
+	else
+		kfree(port);
 }
 
 static ssize_t decoders_committed_show(struct device *dev,
@@ -669,17 +669,31 @@ static struct lock_class_key cxl_port_key;
 static struct cxl_port *cxl_port_alloc(struct device *uport_dev,
 				       struct cxl_dport *parent_dport)
 {
-	struct cxl_port *port;
+	struct cxl_root *cxl_root __free(kfree) = NULL;
+	struct cxl_port *port, *_port __free(kfree) = NULL;
 	struct device *dev;
 	int rc;
 
-	port = kzalloc(sizeof(*port), GFP_KERNEL);
-	if (!port)
-		return ERR_PTR(-ENOMEM);
+	/* No parent_dport, root cxl_port */
+	if (!parent_dport) {
+		cxl_root = kzalloc(sizeof(*cxl_root), GFP_KERNEL);
+		if (!cxl_root)
+			return ERR_PTR(-ENOMEM);
+	} else {
+		_port = kzalloc(sizeof(*port), GFP_KERNEL);
+		if (!_port)
+			return ERR_PTR(-ENOMEM);
+	}
 
 	rc = ida_alloc(&cxl_port_ida, GFP_KERNEL);
 	if (rc < 0)
-		goto err;
+		return ERR_PTR(rc);
+
+	if (cxl_root)
+		port = &no_free_ptr(cxl_root)->port;
+	else
+		port = no_free_ptr(_port);
+
 	port->id = rc;
 	port->uport_dev = uport_dev;
 
@@ -731,10 +745,6 @@ static struct cxl_port *cxl_port_alloc(struct device *uport_dev,
 	dev->type = &cxl_port_type;
 
 	return port;
-
-err:
-	kfree(port);
-	return ERR_PTR(rc);
 }
 
 static int cxl_setup_comp_regs(struct device *host, struct cxl_register_map *map,
@@ -841,6 +851,9 @@ static struct cxl_port *__devm_cxl_add_port(struct device *host,
 	if (rc)
 		return ERR_PTR(rc);
 
+	if (parent_dport && dev_is_pci(uport_dev))
+		port->pci_latency = cxl_pci_get_latency(to_pci_dev(uport_dev));
+
 	return port;
 
 err:
@@ -884,6 +897,22 @@ struct cxl_port *devm_cxl_add_port(struct device *host,
 }
 EXPORT_SYMBOL_NS_GPL(devm_cxl_add_port, CXL);
 
+struct cxl_root *devm_cxl_add_root(struct device *host,
+				   const struct cxl_root_ops *ops)
+{
+	struct cxl_root *cxl_root;
+	struct cxl_port *port;
+
+	port = devm_cxl_add_port(host, host, CXL_RESOURCE_NONE, NULL);
+	if (IS_ERR(port))
+		return (struct cxl_root *)port;
+
+	cxl_root = to_cxl_root(port);
+	cxl_root->ops = ops;
+	return cxl_root;
+}
+EXPORT_SYMBOL_NS_GPL(devm_cxl_add_root, CXL);
+
 struct pci_bus *cxl_port_to_pci_bus(struct cxl_port *port)
 {
 	/* There is no pci_bus associated with a CXL platform-root port */
@@ -939,7 +968,7 @@ static bool dev_is_cxl_root_child(struct device *dev)
 	return false;
 }
 
-struct cxl_port *find_cxl_root(struct cxl_port *port)
+struct cxl_root *find_cxl_root(struct cxl_port *port)
 {
 	struct cxl_port *iter = port;
 
@@ -949,10 +978,19 @@ struct cxl_port *find_cxl_root(struct cxl_port *port)
 	if (!iter)
 		return NULL;
 	get_device(&iter->dev);
-	return iter;
+	return to_cxl_root(iter);
 }
 EXPORT_SYMBOL_NS_GPL(find_cxl_root, CXL);
 
+void put_cxl_root(struct cxl_root *cxl_root)
+{
+	if (!cxl_root)
+		return;
+
+	put_device(&cxl_root->port.dev);
+}
+EXPORT_SYMBOL_NS_GPL(put_cxl_root, CXL);
+
 static struct cxl_dport *find_dport(struct cxl_port *port, int id)
 {
 	struct cxl_dport *dport;
@@ -1108,6 +1146,9 @@ __devm_cxl_add_dport(struct cxl_port *port, struct device *dport_dev,
 	if (rc)
 		return ERR_PTR(rc);
 
+	if (dev_is_pci(dport_dev))
+		dport->link_latency = cxl_pci_get_latency(to_pci_dev(dport_dev));
+
 	return dport;
 }
 
@@ -1633,7 +1674,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_mem_find_port, CXL);
 static int decoder_populate_targets(struct cxl_switch_decoder *cxlsd,
 				    struct cxl_port *port, int *target_map)
 {
-	int i, rc = 0;
+	int i;
 
 	if (!target_map)
 		return 0;
@@ -1643,19 +1684,16 @@ static int decoder_populate_targets(struct cxl_switch_decoder *cxlsd,
 	if (xa_empty(&port->dports))
 		return -EINVAL;
 
-	write_seqlock(&cxlsd->target_lock);
-	for (i = 0; i < cxlsd->nr_targets; i++) {
+	guard(rwsem_write)(&cxl_region_rwsem);
+	for (i = 0; i < cxlsd->cxld.interleave_ways; i++) {
 		struct cxl_dport *dport = find_dport(port, target_map[i]);
 
-		if (!dport) {
-			rc = -ENXIO;
-			break;
-		}
+		if (!dport)
+			return -ENXIO;
 		cxlsd->target[i] = dport;
 	}
-	write_sequnlock(&cxlsd->target_lock);
 
-	return rc;
+	return 0;
 }
 
 struct cxl_dport *cxl_hb_modulo(struct cxl_root_decoder *cxlrd, int pos)
@@ -1725,7 +1763,6 @@ static int cxl_switch_decoder_init(struct cxl_port *port,
 		return -EINVAL;
 
 	cxlsd->nr_targets = nr_targets;
-	seqlock_init(&cxlsd->target_lock);
 	return cxl_decoder_init(port, &cxlsd->cxld);
 }
 
@@ -2059,6 +2096,80 @@ bool schedule_cxl_memdev_detach(struct cxl_memdev *cxlmd)
 }
 EXPORT_SYMBOL_NS_GPL(schedule_cxl_memdev_detach, CXL);
 
+static void combine_coordinates(struct access_coordinate *c1,
+				struct access_coordinate *c2)
+{
+		if (c2->write_bandwidth)
+			c1->write_bandwidth = min(c1->write_bandwidth,
+						  c2->write_bandwidth);
+		c1->write_latency += c2->write_latency;
+
+		if (c2->read_bandwidth)
+			c1->read_bandwidth = min(c1->read_bandwidth,
+						 c2->read_bandwidth);
+		c1->read_latency += c2->read_latency;
+}
+
+/**
+ * cxl_endpoint_get_perf_coordinates - Retrieve performance numbers stored in dports
+ *				   of CXL path
+ * @port: endpoint cxl_port
+ * @coord: output performance data
+ *
+ * Return: errno on failure, 0 on success.
+ */
+int cxl_endpoint_get_perf_coordinates(struct cxl_port *port,
+				      struct access_coordinate *coord)
+{
+	struct access_coordinate c = {
+		.read_bandwidth = UINT_MAX,
+		.write_bandwidth = UINT_MAX,
+	};
+	struct cxl_port *iter = port;
+	struct cxl_dport *dport;
+	struct pci_dev *pdev;
+	unsigned int bw;
+
+	if (!is_cxl_endpoint(port))
+		return -EINVAL;
+
+	dport = iter->parent_dport;
+
+	/*
+	 * Exit the loop when the parent port of the current port is cxl root.
+	 * The iterative loop starts at the endpoint and gathers the
+	 * latency of the CXL link from the current iter to the next downstream
+	 * port each iteration. If the parent is cxl root then there is
+	 * nothing to gather.
+	 */
+	while (iter && !is_cxl_root(to_cxl_port(iter->dev.parent))) {
+		combine_coordinates(&c, &dport->sw_coord);
+		c.write_latency += dport->link_latency;
+		c.read_latency += dport->link_latency;
+
+		iter = to_cxl_port(iter->dev.parent);
+		dport = iter->parent_dport;
+	}
+
+	/* Augment with the generic port (host bridge) perf data */
+	combine_coordinates(&c, &dport->hb_coord);
+
+	/* Get the calculated PCI paths bandwidth */
+	pdev = to_pci_dev(port->uport_dev->parent);
+	bw = pcie_bandwidth_available(pdev, NULL, NULL, NULL);
+	if (bw == 0)
+		return -ENXIO;
+	bw /= BITS_PER_BYTE;
+
+	c.write_bandwidth = min(c.write_bandwidth, bw);
+	c.read_bandwidth = min(c.read_bandwidth, bw);
+
+	*coord = c;
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_endpoint_get_perf_coordinates, CXL);
+
 /* for user tooling to ensure port disable work has completed */
 static ssize_t flush_store(const struct bus_type *bus, const char *buf, size_t count)
 {
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 3e817a6f94c6..4c7fd2d5cccb 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -397,7 +397,7 @@ static ssize_t interleave_ways_store(struct device *dev,
 		return rc;
 
 	/*
-	 * Even for x3, x9, and x12 interleaves the region interleave must be a
+	 * Even for x3, x6, and x12 interleaves the region interleave must be a
 	 * power of 2 multiple of the host bridge interleave.
 	 */
 	if (!is_power_of_2(val / cxld->interleave_ways) ||
@@ -525,7 +525,7 @@ static int alloc_hpa(struct cxl_region *cxlr, resource_size_t size)
 	struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent);
 	struct cxl_region_params *p = &cxlr->params;
 	struct resource *res;
-	u32 remainder = 0;
+	u64 remainder = 0;
 
 	lockdep_assert_held_write(&cxl_region_rwsem);
 
@@ -545,15 +545,16 @@ static int alloc_hpa(struct cxl_region *cxlr, resource_size_t size)
 	    (cxlr->mode == CXL_DECODER_PMEM && uuid_is_null(&p->uuid)))
 		return -ENXIO;
 
-	div_u64_rem(size, SZ_256M * p->interleave_ways, &remainder);
+	div64_u64_rem(size, (u64)SZ_256M * p->interleave_ways, &remainder);
 	if (remainder)
 		return -EINVAL;
 
 	res = alloc_free_mem_region(cxlrd->res, size, SZ_256M,
 				    dev_name(&cxlr->dev));
 	if (IS_ERR(res)) {
-		dev_dbg(&cxlr->dev, "failed to allocate HPA: %ld\n",
-			PTR_ERR(res));
+		dev_dbg(&cxlr->dev,
+			"HPA allocation error (%ld) for size:%pap in %s %pr\n",
+			PTR_ERR(res), &size, cxlrd->res->name, cxlrd->res);
 		return PTR_ERR(res);
 	}
 
@@ -729,12 +730,17 @@ static int match_auto_decoder(struct device *dev, void *data)
 	return 0;
 }
 
-static struct cxl_decoder *cxl_region_find_decoder(struct cxl_port *port,
-						   struct cxl_region *cxlr)
+static struct cxl_decoder *
+cxl_region_find_decoder(struct cxl_port *port,
+			struct cxl_endpoint_decoder *cxled,
+			struct cxl_region *cxlr)
 {
 	struct device *dev;
 	int id = 0;
 
+	if (port == cxled_to_port(cxled))
+		return &cxled->cxld;
+
 	if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags))
 		dev = device_find_child(&port->dev, &cxlr->params,
 					match_auto_decoder);
@@ -752,8 +758,31 @@ static struct cxl_decoder *cxl_region_find_decoder(struct cxl_port *port,
 	return to_cxl_decoder(dev);
 }
 
-static struct cxl_region_ref *alloc_region_ref(struct cxl_port *port,
-					       struct cxl_region *cxlr)
+static bool auto_order_ok(struct cxl_port *port, struct cxl_region *cxlr_iter,
+			  struct cxl_decoder *cxld)
+{
+	struct cxl_region_ref *rr = cxl_rr_load(port, cxlr_iter);
+	struct cxl_decoder *cxld_iter = rr->decoder;
+
+	/*
+	 * Allow the out of order assembly of auto-discovered regions.
+	 * Per CXL Spec 3.1 8.2.4.20.12 software must commit decoders
+	 * in HPA order. Confirm that the decoder with the lesser HPA
+	 * starting address has the lesser id.
+	 */
+	dev_dbg(&cxld->dev, "check for HPA violation %s:%d < %s:%d\n",
+		dev_name(&cxld->dev), cxld->id,
+		dev_name(&cxld_iter->dev), cxld_iter->id);
+
+	if (cxld_iter->id > cxld->id)
+		return true;
+
+	return false;
+}
+
+static struct cxl_region_ref *
+alloc_region_ref(struct cxl_port *port, struct cxl_region *cxlr,
+		 struct cxl_endpoint_decoder *cxled)
 {
 	struct cxl_region_params *p = &cxlr->params;
 	struct cxl_region_ref *cxl_rr, *iter;
@@ -763,16 +792,21 @@ static struct cxl_region_ref *alloc_region_ref(struct cxl_port *port,
 	xa_for_each(&port->regions, index, iter) {
 		struct cxl_region_params *ip = &iter->region->params;
 
-		if (!ip->res)
+		if (!ip->res || ip->res->start < p->res->start)
 			continue;
 
-		if (ip->res->start > p->res->start) {
-			dev_dbg(&cxlr->dev,
-				"%s: HPA order violation %s:%pr vs %pr\n",
-				dev_name(&port->dev),
-				dev_name(&iter->region->dev), ip->res, p->res);
-			return ERR_PTR(-EBUSY);
+		if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) {
+			struct cxl_decoder *cxld;
+
+			cxld = cxl_region_find_decoder(port, cxled, cxlr);
+			if (auto_order_ok(port, iter->region, cxld))
+				continue;
 		}
+		dev_dbg(&cxlr->dev, "%s: HPA order violation %s:%pr vs %pr\n",
+			dev_name(&port->dev),
+			dev_name(&iter->region->dev), ip->res, p->res);
+
+		return ERR_PTR(-EBUSY);
 	}
 
 	cxl_rr = kzalloc(sizeof(*cxl_rr), GFP_KERNEL);
@@ -852,10 +886,7 @@ static int cxl_rr_alloc_decoder(struct cxl_port *port, struct cxl_region *cxlr,
 {
 	struct cxl_decoder *cxld;
 
-	if (port == cxled_to_port(cxled))
-		cxld = &cxled->cxld;
-	else
-		cxld = cxl_region_find_decoder(port, cxlr);
+	cxld = cxl_region_find_decoder(port, cxled, cxlr);
 	if (!cxld) {
 		dev_dbg(&cxlr->dev, "%s: no decoder available\n",
 			dev_name(&port->dev));
@@ -952,7 +983,7 @@ static int cxl_port_attach_region(struct cxl_port *port,
 			nr_targets_inc = true;
 		}
 	} else {
-		cxl_rr = alloc_region_ref(port, cxlr);
+		cxl_rr = alloc_region_ref(port, cxlr, cxled);
 		if (IS_ERR(cxl_rr)) {
 			dev_dbg(&cxlr->dev,
 				"%s: failed to allocate region reference\n",
@@ -2083,13 +2114,13 @@ static struct cxl_region *to_cxl_region(struct device *dev)
 	return container_of(dev, struct cxl_region, dev);
 }
 
-static void unregister_region(void *dev)
+static void unregister_region(void *_cxlr)
 {
-	struct cxl_region *cxlr = to_cxl_region(dev);
+	struct cxl_region *cxlr = _cxlr;
 	struct cxl_region_params *p = &cxlr->params;
 	int i;
 
-	device_del(dev);
+	device_del(&cxlr->dev);
 
 	/*
 	 * Now that region sysfs is shutdown, the parameter block is now
@@ -2100,7 +2131,7 @@ static void unregister_region(void *dev)
 		detach_target(cxlr, i);
 
 	cxl_region_iomem_release(cxlr);
-	put_device(dev);
+	put_device(&cxlr->dev);
 }
 
 static struct lock_class_key cxl_region_key;
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index a0b5819bc70b..bdf117a33744 100644
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -181,6 +181,7 @@ TRACE_EVENT(cxl_overflow,
  *	1) Add CXL_EVT_TP_entry to TP_STRUCT__entry
  *	2) Use CXL_EVT_TP_fast_assign within TP_fast_assign;
  *	   pass the dev, log, and CXL event header
+ *	   NOTE: The uuid must be assigned by the specific trace event
  *	3) Use CXL_EVT_TP_printk() instead of TP_printk()
  *
  * See the generic_event tracepoint as an example.
@@ -203,7 +204,6 @@ TRACE_EVENT(cxl_overflow,
 	__assign_str(host, dev_name((cxlmd)->dev.parent));			\
 	__entry->log = (l);							\
 	__entry->serial = (cxlmd)->cxlds->serial;				\
-	memcpy(&__entry->hdr_uuid, &(hdr).id, sizeof(uuid_t));			\
 	__entry->hdr_length = (hdr).length;					\
 	__entry->hdr_flags = get_unaligned_le24((hdr).flags);			\
 	__entry->hdr_handle = le16_to_cpu((hdr).handle);			\
@@ -225,9 +225,9 @@ TRACE_EVENT(cxl_overflow,
 TRACE_EVENT(cxl_generic_event,
 
 	TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log,
-		 struct cxl_event_record_raw *rec),
+		 const uuid_t *uuid, struct cxl_event_generic *gen_rec),
 
-	TP_ARGS(cxlmd, log, rec),
+	TP_ARGS(cxlmd, log, uuid, gen_rec),
 
 	TP_STRUCT__entry(
 		CXL_EVT_TP_entry
@@ -235,8 +235,9 @@ TRACE_EVENT(cxl_generic_event,
 	),
 
 	TP_fast_assign(
-		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
-		memcpy(__entry->data, &rec->data, CXL_EVENT_RECORD_DATA_LENGTH);
+		CXL_EVT_TP_fast_assign(cxlmd, log, gen_rec->hdr);
+		memcpy(&__entry->hdr_uuid, uuid, sizeof(uuid_t));
+		memcpy(__entry->data, gen_rec->data, CXL_EVENT_RECORD_DATA_LENGTH);
 	),
 
 	CXL_EVT_TP_printk("%s",
@@ -337,6 +338,7 @@ TRACE_EVENT(cxl_general_media,
 
 	TP_fast_assign(
 		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+		__entry->hdr_uuid = CXL_EVENT_GEN_MEDIA_UUID;
 
 		/* General Media */
 		__entry->dpa = le64_to_cpu(rec->phys_addr);
@@ -423,6 +425,7 @@ TRACE_EVENT(cxl_dram,
 
 	TP_fast_assign(
 		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+		__entry->hdr_uuid = CXL_EVENT_DRAM_UUID;
 
 		/* DRAM */
 		__entry->dpa = le64_to_cpu(rec->phys_addr);
@@ -570,6 +573,7 @@ TRACE_EVENT(cxl_memory_module,
 
 	TP_fast_assign(
 		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+		__entry->hdr_uuid = CXL_EVENT_MEM_MODULE_UUID;
 
 		/* Memory Module Event */
 		__entry->event_type = rec->event_type;
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 687043ece101..003feebab79b 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -8,6 +8,7 @@
 #include <linux/bitfield.h>
 #include <linux/bitops.h>
 #include <linux/log2.h>
+#include <linux/node.h>
 #include <linux/io.h>
 
 /**
@@ -412,7 +413,6 @@ struct cxl_endpoint_decoder {
 /**
  * struct cxl_switch_decoder - Switch specific CXL HDM Decoder
  * @cxld: base cxl_decoder object
- * @target_lock: coordinate coherent reads of the target list
  * @nr_targets: number of elements in @target
  * @target: active ordered target list in current decoder configuration
  *
@@ -424,7 +424,6 @@ struct cxl_endpoint_decoder {
  */
 struct cxl_switch_decoder {
 	struct cxl_decoder cxld;
-	seqlock_t target_lock;
 	int nr_targets;
 	struct cxl_dport *target[];
 };
@@ -590,6 +589,7 @@ struct cxl_dax_region {
  * @depth: How deep this port is relative to the root. depth 0 is the root.
  * @cdat: Cached CDAT data
  * @cdat_available: Should a CDAT attribute be available in sysfs
+ * @pci_latency: Upstream latency in picoseconds
  */
 struct cxl_port {
 	struct device dev;
@@ -612,6 +612,30 @@ struct cxl_port {
 		size_t length;
 	} cdat;
 	bool cdat_available;
+	long pci_latency;
+};
+
+/**
+ * struct cxl_root - logical collection of root cxl_port items
+ *
+ * @port: cxl_port member
+ * @ops: cxl root operations
+ */
+struct cxl_root {
+	struct cxl_port port;
+	const struct cxl_root_ops *ops;
+};
+
+static inline struct cxl_root *
+to_cxl_root(const struct cxl_port *port)
+{
+	return container_of(port, struct cxl_root, port);
+}
+
+struct cxl_root_ops {
+	int (*qos_class)(struct cxl_root *cxl_root,
+			 struct access_coordinate *coord, int entries,
+			 int *qos_class);
 };
 
 static inline struct cxl_dport *
@@ -634,6 +658,9 @@ struct cxl_rcrb_info {
  * @rch: Indicate whether this dport was enumerated in RCH or VH mode
  * @port: reference to cxl_port that contains this downstream port
  * @regs: Dport parsed register blocks
+ * @sw_coord: access coordinates (performance) for switch from CDAT
+ * @hb_coord: access coordinates (performance) from ACPI generic port (host bridge)
+ * @link_latency: calculated PCIe downstream latency
  */
 struct cxl_dport {
 	struct device *dport_dev;
@@ -643,6 +670,9 @@ struct cxl_dport {
 	bool rch;
 	struct cxl_port *port;
 	struct cxl_regs regs;
+	struct access_coordinate sw_coord;
+	struct access_coordinate hb_coord;
+	long link_latency;
 };
 
 /**
@@ -700,7 +730,12 @@ struct cxl_port *devm_cxl_add_port(struct device *host,
 				   struct device *uport_dev,
 				   resource_size_t component_reg_phys,
 				   struct cxl_dport *parent_dport);
-struct cxl_port *find_cxl_root(struct cxl_port *port);
+struct cxl_root *devm_cxl_add_root(struct device *host,
+				   const struct cxl_root_ops *ops);
+struct cxl_root *find_cxl_root(struct cxl_port *port);
+void put_cxl_root(struct cxl_root *cxl_root);
+DEFINE_FREE(put_cxl_root, struct cxl_root *, if (_T) put_cxl_root(_T))
+
 int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd);
 void cxl_bus_rescan(void);
 void cxl_bus_drain(void);
@@ -839,6 +874,14 @@ static inline struct cxl_dax_region *to_cxl_dax_region(struct device *dev)
 }
 #endif
 
+void cxl_endpoint_parse_cdat(struct cxl_port *port);
+void cxl_switch_parse_cdat(struct cxl_port *port);
+
+int cxl_endpoint_get_perf_coordinates(struct cxl_port *port,
+				      struct access_coordinate *coord);
+
+void cxl_memdev_update_perf(struct cxl_memdev *cxlmd);
+
 /*
  * Unit test builds overrides this to __weak, find the 'strong' version
  * of these symbols in tools/testing/cxl/.
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index a2fcbca253f3..20fb3b35e89e 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -6,6 +6,8 @@
 #include <linux/cdev.h>
 #include <linux/uuid.h>
 #include <linux/rcuwait.h>
+#include <linux/cxl-event.h>
+#include <linux/node.h>
 #include "cxl.h"
 
 /* CXL 2.0 8.2.8.5.1.1 Memory Device Status Register */
@@ -392,6 +394,18 @@ enum cxl_devtype {
 };
 
 /**
+ * struct cxl_dpa_perf - DPA performance property entry
+ * @dpa_range - range for DPA address
+ * @coord - QoS performance data (i.e. latency, bandwidth)
+ * @qos_class - QoS Class cookies
+ */
+struct cxl_dpa_perf {
+	struct range dpa_range;
+	struct access_coordinate coord;
+	int qos_class;
+};
+
+/**
  * struct cxl_dev_state - The driver device state
  *
  * cxl_dev_state represents the CXL driver/device state.  It provides an
@@ -455,6 +469,8 @@ struct cxl_dev_state {
  * @security: security driver state info
  * @fw: firmware upload / activation state
  * @mbox_send: @dev specific transport for transmitting mailbox commands
+ * @ram_perf: performance data entry matched to RAM partition
+ * @pmem_perf: performance data entry matched to PMEM partition
  *
  * See CXL 3.0 8.2.9.8.2 Capacity Configuration and Label Storage for
  * details on capacity parameters.
@@ -475,6 +491,10 @@ struct cxl_memdev_state {
 	u64 active_persistent_bytes;
 	u64 next_volatile_bytes;
 	u64 next_persistent_bytes;
+
+	struct cxl_dpa_perf ram_perf;
+	struct cxl_dpa_perf pmem_perf;
+
 	struct cxl_event_state event;
 	struct cxl_poison_state poison;
 	struct cxl_security_state security;
@@ -503,6 +523,7 @@ enum cxl_opcode {
 	CXL_MBOX_OP_GET_FW_INFO		= 0x0200,
 	CXL_MBOX_OP_TRANSFER_FW		= 0x0201,
 	CXL_MBOX_OP_ACTIVATE_FW		= 0x0202,
+	CXL_MBOX_OP_GET_TIMESTAMP	= 0x0300,
 	CXL_MBOX_OP_SET_TIMESTAMP	= 0x0301,
 	CXL_MBOX_OP_GET_SUPPORTED_LOGS	= 0x0400,
 	CXL_MBOX_OP_GET_LOG		= 0x0401,
@@ -580,25 +601,28 @@ struct cxl_mbox_identify {
 } __packed;
 
 /*
- * Common Event Record Format
- * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
+ * General Media Event Record UUID
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
  */
-struct cxl_event_record_hdr {
-	uuid_t id;
-	u8 length;
-	u8 flags[3];
-	__le16 handle;
-	__le16 related_handle;
-	__le64 timestamp;
-	u8 maint_op_class;
-	u8 reserved[15];
-} __packed;
+#define CXL_EVENT_GEN_MEDIA_UUID                                            \
+	UUID_INIT(0xfbcd0a77, 0xc260, 0x417f, 0x85, 0xa9, 0x08, 0x8b, 0x16, \
+		  0x21, 0xeb, 0xa6)
 
-#define CXL_EVENT_RECORD_DATA_LENGTH 0x50
-struct cxl_event_record_raw {
-	struct cxl_event_record_hdr hdr;
-	u8 data[CXL_EVENT_RECORD_DATA_LENGTH];
-} __packed;
+/*
+ * DRAM Event Record UUID
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
+ */
+#define CXL_EVENT_DRAM_UUID                                                 \
+	UUID_INIT(0x601dcbb3, 0x9c06, 0x4eab, 0xb8, 0xaf, 0x4e, 0x9b, 0xfb, \
+		  0x5c, 0x96, 0x24)
+
+/*
+ * Memory Module Event Record UUID
+ * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+#define CXL_EVENT_MEM_MODULE_UUID                                           \
+	UUID_INIT(0xfe927475, 0xdd59, 0x4339, 0xa5, 0x86, 0x79, 0xba, 0xb1, \
+		  0x13, 0xb7, 0x74)
 
 /*
  * Get Event Records output payload
@@ -641,74 +665,6 @@ struct cxl_mbox_clear_event_payload {
 } __packed;
 #define CXL_CLEAR_EVENT_MAX_HANDLES U8_MAX
 
-/*
- * General Media Event Record
- * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
- */
-#define CXL_EVENT_GEN_MED_COMP_ID_SIZE	0x10
-struct cxl_event_gen_media {
-	struct cxl_event_record_hdr hdr;
-	__le64 phys_addr;
-	u8 descriptor;
-	u8 type;
-	u8 transaction_type;
-	u8 validity_flags[2];
-	u8 channel;
-	u8 rank;
-	u8 device[3];
-	u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
-	u8 reserved[46];
-} __packed;
-
-/*
- * DRAM Event Record - DER
- * CXL rev 3.0 section 8.2.9.2.1.2; Table 3-44
- */
-#define CXL_EVENT_DER_CORRECTION_MASK_SIZE	0x20
-struct cxl_event_dram {
-	struct cxl_event_record_hdr hdr;
-	__le64 phys_addr;
-	u8 descriptor;
-	u8 type;
-	u8 transaction_type;
-	u8 validity_flags[2];
-	u8 channel;
-	u8 rank;
-	u8 nibble_mask[3];
-	u8 bank_group;
-	u8 bank;
-	u8 row[3];
-	u8 column[2];
-	u8 correction_mask[CXL_EVENT_DER_CORRECTION_MASK_SIZE];
-	u8 reserved[0x17];
-} __packed;
-
-/*
- * Get Health Info Record
- * CXL rev 3.0 section 8.2.9.8.3.1; Table 8-100
- */
-struct cxl_get_health_info {
-	u8 health_status;
-	u8 media_status;
-	u8 add_status;
-	u8 life_used;
-	u8 device_temp[2];
-	u8 dirty_shutdown_cnt[4];
-	u8 cor_vol_err_cnt[4];
-	u8 cor_per_err_cnt[4];
-} __packed;
-
-/*
- * Memory Module Event Record
- * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
- */
-struct cxl_event_mem_module {
-	struct cxl_event_record_hdr hdr;
-	u8 event_type;
-	struct cxl_get_health_info info;
-	u8 reserved[0x3d];
-} __packed;
-
 struct cxl_mbox_get_partition_info {
 	__le64 active_volatile_cap;
 	__le64 active_persistent_cap;
@@ -866,6 +822,10 @@ void set_exclusive_cxl_commands(struct cxl_memdev_state *mds,
 void clear_exclusive_cxl_commands(struct cxl_memdev_state *mds,
 				  unsigned long *cmds);
 void cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status);
+void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
+			    enum cxl_event_log_type type,
+			    enum cxl_event_type event_type,
+			    const uuid_t *uuid, union cxl_event *evt);
 int cxl_set_timestamp(struct cxl_memdev_state *mds);
 int cxl_poison_state_init(struct cxl_memdev_state *mds);
 int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len,
diff --git a/drivers/cxl/cxlpci.h b/drivers/cxl/cxlpci.h
index 0fa4799ea316..711b05d9a370 100644
--- a/drivers/cxl/cxlpci.h
+++ b/drivers/cxl/cxlpci.h
@@ -85,6 +85,19 @@ struct cdat_entry_header {
 	__le16 length;
 } __packed;
 
+/*
+ * CXL v3.0 6.2.3 Table 6-4
+ * The table indicates that if PCIe Flit Mode is set, then CXL is in 256B flits
+ * mode, otherwise it's 68B flits mode.
+ */
+static inline bool cxl_pci_flit_256(struct pci_dev *pdev)
+{
+	u16 lnksta2;
+
+	pcie_capability_read_word(pdev, PCI_EXP_LNKSTA2, &lnksta2);
+	return lnksta2 & PCI_EXP_LNKSTA2_FLIT;
+}
+
 int devm_cxl_port_enumerate_dports(struct cxl_port *port);
 struct cxl_dev_state;
 int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm,
diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c
index e087febf9af0..0c79d9ce877c 100644
--- a/drivers/cxl/mem.c
+++ b/drivers/cxl/mem.c
@@ -217,16 +217,15 @@ static DEVICE_ATTR_WO(trigger_poison_list);
 
 static umode_t cxl_mem_visible(struct kobject *kobj, struct attribute *a, int n)
 {
-	if (a == &dev_attr_trigger_poison_list.attr) {
-		struct device *dev = kobj_to_dev(kobj);
-		struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
-		struct cxl_memdev_state *mds =
-			to_cxl_memdev_state(cxlmd->cxlds);
+	struct device *dev = kobj_to_dev(kobj);
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
 
+	if (a == &dev_attr_trigger_poison_list.attr)
 		if (!test_bit(CXL_POISON_ENABLED_LIST,
 			      mds->poison.enabled_cmds))
 			return 0;
-	}
+
 	return a->mode;
 }
 
diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index 0155fb66b580..2ff361e756d6 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright(c) 2020 Intel Corporation. All rights reserved. */
+#include <asm-generic/unaligned.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/moduleparam.h>
 #include <linux/module.h>
@@ -381,7 +382,7 @@ static int cxl_pci_mbox_send(struct cxl_memdev_state *mds,
 	return rc;
 }
 
-static int cxl_pci_setup_mailbox(struct cxl_memdev_state *mds)
+static int cxl_pci_setup_mailbox(struct cxl_memdev_state *mds, bool irq_avail)
 {
 	struct cxl_dev_state *cxlds = &mds->cxlds;
 	const int cap = readl(cxlds->regs.mbox + CXLDEV_MBOX_CAPS_OFFSET);
@@ -440,7 +441,7 @@ static int cxl_pci_setup_mailbox(struct cxl_memdev_state *mds)
 	INIT_DELAYED_WORK(&mds->security.poll_dwork, cxl_mbox_sanitize_work);
 
 	/* background command interrupts are optional */
-	if (!(cap & CXLDEV_MBOX_CAP_BG_CMD_IRQ))
+	if (!(cap & CXLDEV_MBOX_CAP_BG_CMD_IRQ) || !irq_avail)
 		return 0;
 
 	msgnum = FIELD_GET(CXLDEV_MBOX_CAP_IRQ_MSGNUM_MASK, cap);
@@ -587,7 +588,7 @@ static int cxl_mem_alloc_event_buf(struct cxl_memdev_state *mds)
 	return devm_add_action_or_reset(mds->cxlds.dev, free_event_buf, buf);
 }
 
-static int cxl_alloc_irq_vectors(struct pci_dev *pdev)
+static bool cxl_alloc_irq_vectors(struct pci_dev *pdev)
 {
 	int nvecs;
 
@@ -604,9 +605,9 @@ static int cxl_alloc_irq_vectors(struct pci_dev *pdev)
 				      PCI_IRQ_MSIX | PCI_IRQ_MSI);
 	if (nvecs < 1) {
 		dev_dbg(&pdev->dev, "Failed to alloc irq vectors: %d\n", nvecs);
-		return -ENXIO;
+		return false;
 	}
-	return 0;
+	return true;
 }
 
 static irqreturn_t cxl_event_thread(int irq, void *id)
@@ -742,7 +743,7 @@ static bool cxl_event_int_is_fw(u8 setting)
 }
 
 static int cxl_event_config(struct pci_host_bridge *host_bridge,
-			    struct cxl_memdev_state *mds)
+			    struct cxl_memdev_state *mds, bool irq_avail)
 {
 	struct cxl_event_interrupt_policy policy;
 	int rc;
@@ -754,6 +755,11 @@ static int cxl_event_config(struct pci_host_bridge *host_bridge,
 	if (!host_bridge->native_cxl_error)
 		return 0;
 
+	if (!irq_avail) {
+		dev_info(mds->cxlds.dev, "No interrupt support, disable event processing.\n");
+		return 0;
+	}
+
 	rc = cxl_mem_alloc_event_buf(mds);
 	if (rc)
 		return rc;
@@ -788,6 +794,7 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	struct cxl_register_map map;
 	struct cxl_memdev *cxlmd;
 	int i, rc, pmu_count;
+	bool irq_avail;
 
 	/*
 	 * Double check the anonymous union trickery in struct cxl_regs
@@ -845,11 +852,9 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	else
 		dev_warn(&pdev->dev, "Media not active (%d)\n", rc);
 
-	rc = cxl_alloc_irq_vectors(pdev);
-	if (rc)
-		return rc;
+	irq_avail = cxl_alloc_irq_vectors(pdev);
 
-	rc = cxl_pci_setup_mailbox(mds);
+	rc = cxl_pci_setup_mailbox(mds, irq_avail);
 	if (rc)
 		return rc;
 
@@ -908,7 +913,7 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		}
 	}
 
-	rc = cxl_event_config(host_bridge, mds);
+	rc = cxl_event_config(host_bridge, mds, irq_avail);
 	if (rc)
 		return rc;
 
@@ -969,6 +974,6 @@ static struct pci_driver cxl_pci_driver = {
 	},
 };
 
-MODULE_LICENSE("GPL v2");
 module_pci_driver(cxl_pci_driver);
+MODULE_LICENSE("GPL v2");
 MODULE_IMPORT_NS(CXL);
diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c
index 47bc8e0b8590..97c21566677a 100644
--- a/drivers/cxl/port.c
+++ b/drivers/cxl/port.c
@@ -69,6 +69,8 @@ static int cxl_switch_port_probe(struct cxl_port *port)
 	if (rc < 0)
 		return rc;
 
+	cxl_switch_parse_cdat(port);
+
 	cxlhdm = devm_cxl_setup_hdm(port, NULL);
 	if (!IS_ERR(cxlhdm))
 		return devm_cxl_enumerate_decoders(cxlhdm, NULL);
@@ -109,6 +111,7 @@ static int cxl_endpoint_port_probe(struct cxl_port *port)
 
 	/* Cache the data early to ensure is_visible() works */
 	read_cdat_data(port);
+	cxl_endpoint_parse_cdat(port);
 
 	get_device(&cxlmd->dev);
 	rc = devm_add_action_or_reset(&port->dev, schedule_detach, cxlmd);
@@ -127,14 +130,15 @@ static int cxl_endpoint_port_probe(struct cxl_port *port)
 	 * This can't fail in practice as CXL root exit unregisters all
 	 * descendant ports and that in turn synchronizes with cxl_port_probe()
 	 */
-	root = find_cxl_root(port);
+	struct cxl_root *cxl_root __free(put_cxl_root) = find_cxl_root(port);
+
+	root = &cxl_root->port;
 
 	/*
 	 * Now that all endpoint decoders are successfully enumerated, try to
 	 * assemble regions from committed decoders
 	 */
 	device_for_each_child(&port->dev, root, discover_region);
-	put_device(&root->dev);
 
 	return 0;
 }
diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c
index ee899f8e6721..4a63567e93ba 100644
--- a/drivers/dma-buf/heaps/cma_heap.c
+++ b/drivers/dma-buf/heaps/cma_heap.c
@@ -168,10 +168,7 @@ static vm_fault_t cma_heap_vm_fault(struct vm_fault *vmf)
 	if (vmf->pgoff > buffer->pagecount)
 		return VM_FAULT_SIGBUS;
 
-	vmf->page = buffer->pages[vmf->pgoff];
-	get_page(vmf->page);
-
-	return 0;
+	return vmf_insert_pfn(vma, vmf->address, page_to_pfn(buffer->pages[vmf->pgoff]));
 }
 
 static const struct vm_operations_struct dma_heap_vm_ops = {
@@ -185,6 +182,8 @@ static int cma_heap_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma)
 	if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) == 0)
 		return -EINVAL;
 
+	vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP);
+
 	vma->vm_ops = &dma_heap_vm_ops;
 	vma->vm_private_data = buffer;
 
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 70ba506dabab..e928f2ca0f1e 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -378,6 +378,20 @@ config LPC18XX_DMAMUX
 	  Enable support for DMA on NXP LPC18xx/43xx platforms
 	  with PL080 and multiplexed DMA request lines.
 
+config LS2X_APB_DMA
+	tristate "Loongson LS2X APB DMA support"
+	depends on LOONGARCH || COMPILE_TEST
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Support for the Loongson LS2X APB DMA controller driver. The
+	  DMA controller is having single DMA channel which can be
+	  configured for different peripherals like audio, nand, sdio
+	  etc which is in APB bus.
+
+	  This DMA controller transfers data from memory to peripheral fifo.
+	  It does not support memory to memory data transfer.
+
 config MCF_EDMA
 	tristate "Freescale eDMA engine support, ColdFire mcf5441x SoCs"
 	depends on M5441x || COMPILE_TEST
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 83553a97a010..dfd40d14e408 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -48,6 +48,7 @@ obj-$(CONFIG_INTEL_IOATDMA) += ioat/
 obj-y += idxd/
 obj-$(CONFIG_K3_DMA) += k3dma.o
 obj-$(CONFIG_LPC18XX_DMAMUX) += lpc18xx-dmamux.o
+obj-$(CONFIG_LS2X_APB_DMA) += ls2x-apb-dma.o
 obj-$(CONFIG_MILBEAUT_HDMAC) += milbeaut-hdmac.o
 obj-$(CONFIG_MILBEAUT_XDMAC) += milbeaut-xdmac.o
 obj-$(CONFIG_MMP_PDMA) += mmp_pdma.o
diff --git a/drivers/dma/apple-admac.c b/drivers/dma/apple-admac.c
index 5b63996640d9..9588773dd2eb 100644
--- a/drivers/dma/apple-admac.c
+++ b/drivers/dma/apple-admac.c
@@ -57,6 +57,8 @@
 
 #define REG_BUS_WIDTH(ch)	(0x8040 + (ch) * 0x200)
 
+#define BUS_WIDTH_WORD_SIZE	GENMASK(3, 0)
+#define BUS_WIDTH_FRAME_SIZE	GENMASK(7, 4)
 #define BUS_WIDTH_8BIT		0x00
 #define BUS_WIDTH_16BIT		0x01
 #define BUS_WIDTH_32BIT		0x02
@@ -740,7 +742,8 @@ static int admac_device_config(struct dma_chan *chan,
 	struct admac_data *ad = adchan->host;
 	bool is_tx = admac_chan_direction(adchan->no) == DMA_MEM_TO_DEV;
 	int wordsize = 0;
-	u32 bus_width = 0;
+	u32 bus_width = readl_relaxed(ad->base + REG_BUS_WIDTH(adchan->no)) &
+		~(BUS_WIDTH_WORD_SIZE | BUS_WIDTH_FRAME_SIZE);
 
 	switch (is_tx ? config->dst_addr_width : config->src_addr_width) {
 	case DMA_SLAVE_BUSWIDTH_1_BYTE:
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index fb89ecbf0cc5..40052d1bd0b5 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -222,8 +222,14 @@ struct atdma_sg {
  * @vd: pointer to the virtual dma descriptor.
  * @atchan: pointer to the atmel dma channel.
  * @total_len: total transaction byte count
- * @sg_len: number of sg entries.
+ * @sglen: number of sg entries.
  * @sg: array of sgs.
+ * @boundary: number of transfers to perform before the automatic address increment operation
+ * @dst_hole: value to add to the destination address when the boundary has been reached
+ * @src_hole: value to add to the source address when the boundary has been reached
+ * @memset_buffer: buffer used for the memset operation
+ * @memset_paddr: physical address of the buffer used for the memset operation
+ * @memset_vaddr: virtual address of the buffer used for the memset operation
  */
 struct at_desc {
 	struct				virt_dma_desc vd;
@@ -245,7 +251,10 @@ struct at_desc {
 /*--  Channels  --------------------------------------------------------*/
 
 /**
- * atc_status - information bits stored in channel status flag
+ * enum atc_status - information bits stored in channel status flag
+ *
+ * @ATC_IS_PAUSED: If channel is pauses
+ * @ATC_IS_CYCLIC: If channel is cyclic
  *
  * Manipulated with atomic operations.
  */
@@ -282,7 +291,6 @@ struct at_dma_chan {
 	u32			save_cfg;
 	u32			save_dscr;
 	struct dma_slave_config	dma_sconfig;
-	bool			cyclic;
 	struct at_desc		*desc;
 };
 
@@ -328,12 +336,12 @@ static inline u8 convert_buswidth(enum dma_slave_buswidth addr_width)
 /**
  * struct at_dma - internal representation of an Atmel HDMA Controller
  * @dma_device: dmaengine dma_device object members
- * @atdma_devtype: identifier of DMA controller compatibility
- * @ch_regs: memory mapped register base
+ * @regs: memory mapped register base
  * @clk: dma controller clock
  * @save_imr: interrupt mask register that is saved on suspend/resume cycle
  * @all_chan_mask: all channels availlable in a mask
  * @lli_pool: hw lli table
+ * @memset_pool: hw memset pool
  * @chan: channels table to store at_dma_chan structures
  */
 struct at_dma {
@@ -626,6 +634,9 @@ static inline u32 atc_calc_bytes_left(u32 current_len, u32 ctrla)
 
 /**
  * atc_get_llis_residue - Get residue for a hardware linked list transfer
+ * @atchan: pointer to an atmel hdmac channel.
+ * @desc: pointer to the descriptor for which the residue is calculated.
+ * @residue: residue to be set to dma_tx_state.
  *
  * Calculate the residue by removing the length of the Linked List Item (LLI)
  * already transferred from the total length. To get the current LLI we can use
@@ -661,10 +672,8 @@ static inline u32 atc_calc_bytes_left(u32 current_len, u32 ctrla)
  * two DSCR values are different, we read again the CTRLA then the DSCR till two
  * consecutive read values from DSCR are equal or till the maximum trials is
  * reach. This algorithm is very unlikely not to find a stable value for DSCR.
- * @atchan: pointer to an atmel hdmac channel.
- * @desc: pointer to the descriptor for which the residue is calculated.
- * @residue: residue to be set to dma_tx_state.
- * Returns 0 on success, -errno otherwise.
+ *
+ * Returns: %0 on success, -errno otherwise.
  */
 static int atc_get_llis_residue(struct at_dma_chan *atchan,
 				struct at_desc *desc, u32 *residue)
@@ -731,7 +740,8 @@ static int atc_get_llis_residue(struct at_dma_chan *atchan,
  * @chan: DMA channel
  * @cookie: transaction identifier to check status of
  * @residue: residue to be updated.
- * Return 0 on success, -errono otherwise.
+ *
+ * Return: %0 on success, -errno otherwise.
  */
 static int atc_get_residue(struct dma_chan *chan, dma_cookie_t cookie,
 			   u32 *residue)
@@ -1710,7 +1720,7 @@ static void atc_issue_pending(struct dma_chan *chan)
  * atc_alloc_chan_resources - allocate resources for DMA channel
  * @chan: allocate descriptor resources for this channel
  *
- * return - the number of allocated descriptors
+ * Return: the number of allocated descriptors
  */
 static int atc_alloc_chan_resources(struct dma_chan *chan)
 {
diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c
index 2457a420c13d..4e339c04fc1e 100644
--- a/drivers/dma/dma-axi-dmac.c
+++ b/drivers/dma/dma-axi-dmac.c
@@ -81,9 +81,13 @@
 #define AXI_DMAC_REG_CURRENT_DEST_ADDR	0x438
 #define AXI_DMAC_REG_PARTIAL_XFER_LEN	0x44c
 #define AXI_DMAC_REG_PARTIAL_XFER_ID	0x450
+#define AXI_DMAC_REG_CURRENT_SG_ID	0x454
+#define AXI_DMAC_REG_SG_ADDRESS		0x47c
+#define AXI_DMAC_REG_SG_ADDRESS_HIGH	0x4bc
 
 #define AXI_DMAC_CTRL_ENABLE		BIT(0)
 #define AXI_DMAC_CTRL_PAUSE		BIT(1)
+#define AXI_DMAC_CTRL_ENABLE_SG		BIT(2)
 
 #define AXI_DMAC_IRQ_SOT		BIT(0)
 #define AXI_DMAC_IRQ_EOT		BIT(1)
@@ -97,20 +101,35 @@
 /* The maximum ID allocated by the hardware is 31 */
 #define AXI_DMAC_SG_UNUSED 32U
 
+/* Flags for axi_dmac_hw_desc.flags */
+#define AXI_DMAC_HW_FLAG_LAST		BIT(0)
+#define AXI_DMAC_HW_FLAG_IRQ		BIT(1)
+
+struct axi_dmac_hw_desc {
+	u32 flags;
+	u32 id;
+	u64 dest_addr;
+	u64 src_addr;
+	u64 next_sg_addr;
+	u32 y_len;
+	u32 x_len;
+	u32 src_stride;
+	u32 dst_stride;
+	u64 __pad[2];
+};
+
 struct axi_dmac_sg {
-	dma_addr_t src_addr;
-	dma_addr_t dest_addr;
-	unsigned int x_len;
-	unsigned int y_len;
-	unsigned int dest_stride;
-	unsigned int src_stride;
-	unsigned int id;
 	unsigned int partial_len;
 	bool schedule_when_free;
+
+	struct axi_dmac_hw_desc *hw;
+	dma_addr_t hw_phys;
 };
 
 struct axi_dmac_desc {
 	struct virt_dma_desc vdesc;
+	struct axi_dmac_chan *chan;
+
 	bool cyclic;
 	bool have_partial_xfer;
 
@@ -139,6 +158,7 @@ struct axi_dmac_chan {
 	bool hw_partial_xfer;
 	bool hw_cyclic;
 	bool hw_2d;
+	bool hw_sg;
 };
 
 struct axi_dmac {
@@ -213,9 +233,11 @@ static void axi_dmac_start_transfer(struct axi_dmac_chan *chan)
 	unsigned int flags = 0;
 	unsigned int val;
 
-	val = axi_dmac_read(dmac, AXI_DMAC_REG_START_TRANSFER);
-	if (val) /* Queue is full, wait for the next SOT IRQ */
-		return;
+	if (!chan->hw_sg) {
+		val = axi_dmac_read(dmac, AXI_DMAC_REG_START_TRANSFER);
+		if (val) /* Queue is full, wait for the next SOT IRQ */
+			return;
+	}
 
 	desc = chan->next_desc;
 
@@ -229,14 +251,15 @@ static void axi_dmac_start_transfer(struct axi_dmac_chan *chan)
 	sg = &desc->sg[desc->num_submitted];
 
 	/* Already queued in cyclic mode. Wait for it to finish */
-	if (sg->id != AXI_DMAC_SG_UNUSED) {
+	if (sg->hw->id != AXI_DMAC_SG_UNUSED) {
 		sg->schedule_when_free = true;
 		return;
 	}
 
-	desc->num_submitted++;
-	if (desc->num_submitted == desc->num_sgs ||
-	    desc->have_partial_xfer) {
+	if (chan->hw_sg) {
+		chan->next_desc = NULL;
+	} else if (++desc->num_submitted == desc->num_sgs ||
+		   desc->have_partial_xfer) {
 		if (desc->cyclic)
 			desc->num_submitted = 0; /* Start again */
 		else
@@ -246,32 +269,42 @@ static void axi_dmac_start_transfer(struct axi_dmac_chan *chan)
 		chan->next_desc = desc;
 	}
 
-	sg->id = axi_dmac_read(dmac, AXI_DMAC_REG_TRANSFER_ID);
+	sg->hw->id = axi_dmac_read(dmac, AXI_DMAC_REG_TRANSFER_ID);
 
-	if (axi_dmac_dest_is_mem(chan)) {
-		axi_dmac_write(dmac, AXI_DMAC_REG_DEST_ADDRESS, sg->dest_addr);
-		axi_dmac_write(dmac, AXI_DMAC_REG_DEST_STRIDE, sg->dest_stride);
-	}
+	if (!chan->hw_sg) {
+		if (axi_dmac_dest_is_mem(chan)) {
+			axi_dmac_write(dmac, AXI_DMAC_REG_DEST_ADDRESS, sg->hw->dest_addr);
+			axi_dmac_write(dmac, AXI_DMAC_REG_DEST_STRIDE, sg->hw->dst_stride);
+		}
 
-	if (axi_dmac_src_is_mem(chan)) {
-		axi_dmac_write(dmac, AXI_DMAC_REG_SRC_ADDRESS, sg->src_addr);
-		axi_dmac_write(dmac, AXI_DMAC_REG_SRC_STRIDE, sg->src_stride);
+		if (axi_dmac_src_is_mem(chan)) {
+			axi_dmac_write(dmac, AXI_DMAC_REG_SRC_ADDRESS, sg->hw->src_addr);
+			axi_dmac_write(dmac, AXI_DMAC_REG_SRC_STRIDE, sg->hw->src_stride);
+		}
 	}
 
 	/*
 	 * If the hardware supports cyclic transfers and there is no callback to
-	 * call and only a single segment, enable hw cyclic mode to avoid
-	 * unnecessary interrupts.
+	 * call, enable hw cyclic mode to avoid unnecessary interrupts.
 	 */
-	if (chan->hw_cyclic && desc->cyclic && !desc->vdesc.tx.callback &&
-		desc->num_sgs == 1)
-		flags |= AXI_DMAC_FLAG_CYCLIC;
+	if (chan->hw_cyclic && desc->cyclic && !desc->vdesc.tx.callback) {
+		if (chan->hw_sg)
+			desc->sg[desc->num_sgs - 1].hw->flags &= ~AXI_DMAC_HW_FLAG_IRQ;
+		else if (desc->num_sgs == 1)
+			flags |= AXI_DMAC_FLAG_CYCLIC;
+	}
 
 	if (chan->hw_partial_xfer)
 		flags |= AXI_DMAC_FLAG_PARTIAL_REPORT;
 
-	axi_dmac_write(dmac, AXI_DMAC_REG_X_LENGTH, sg->x_len - 1);
-	axi_dmac_write(dmac, AXI_DMAC_REG_Y_LENGTH, sg->y_len - 1);
+	if (chan->hw_sg) {
+		axi_dmac_write(dmac, AXI_DMAC_REG_SG_ADDRESS, (u32)sg->hw_phys);
+		axi_dmac_write(dmac, AXI_DMAC_REG_SG_ADDRESS_HIGH,
+			       (u64)sg->hw_phys >> 32);
+	} else {
+		axi_dmac_write(dmac, AXI_DMAC_REG_X_LENGTH, sg->hw->x_len);
+		axi_dmac_write(dmac, AXI_DMAC_REG_Y_LENGTH, sg->hw->y_len);
+	}
 	axi_dmac_write(dmac, AXI_DMAC_REG_FLAGS, flags);
 	axi_dmac_write(dmac, AXI_DMAC_REG_START_TRANSFER, 1);
 }
@@ -286,9 +319,9 @@ static inline unsigned int axi_dmac_total_sg_bytes(struct axi_dmac_chan *chan,
 	struct axi_dmac_sg *sg)
 {
 	if (chan->hw_2d)
-		return sg->x_len * sg->y_len;
+		return (sg->hw->x_len + 1) * (sg->hw->y_len + 1);
 	else
-		return sg->x_len;
+		return (sg->hw->x_len + 1);
 }
 
 static void axi_dmac_dequeue_partial_xfers(struct axi_dmac_chan *chan)
@@ -307,9 +340,9 @@ static void axi_dmac_dequeue_partial_xfers(struct axi_dmac_chan *chan)
 		list_for_each_entry(desc, &chan->active_descs, vdesc.node) {
 			for (i = 0; i < desc->num_sgs; i++) {
 				sg = &desc->sg[i];
-				if (sg->id == AXI_DMAC_SG_UNUSED)
+				if (sg->hw->id == AXI_DMAC_SG_UNUSED)
 					continue;
-				if (sg->id == id) {
+				if (sg->hw->id == id) {
 					desc->have_partial_xfer = true;
 					sg->partial_len = len;
 					found_sg = true;
@@ -348,6 +381,9 @@ static void axi_dmac_compute_residue(struct axi_dmac_chan *chan,
 	rslt->result = DMA_TRANS_NOERROR;
 	rslt->residue = 0;
 
+	if (chan->hw_sg)
+		return;
+
 	/*
 	 * We get here if the last completed segment is partial, which
 	 * means we can compute the residue from that segment onwards
@@ -374,36 +410,47 @@ static bool axi_dmac_transfer_done(struct axi_dmac_chan *chan,
 	    (completed_transfers & AXI_DMAC_FLAG_PARTIAL_XFER_DONE))
 		axi_dmac_dequeue_partial_xfers(chan);
 
-	do {
-		sg = &active->sg[active->num_completed];
-		if (sg->id == AXI_DMAC_SG_UNUSED) /* Not yet submitted */
-			break;
-		if (!(BIT(sg->id) & completed_transfers))
-			break;
-		active->num_completed++;
-		sg->id = AXI_DMAC_SG_UNUSED;
-		if (sg->schedule_when_free) {
-			sg->schedule_when_free = false;
-			start_next = true;
+	if (chan->hw_sg) {
+		if (active->cyclic) {
+			vchan_cyclic_callback(&active->vdesc);
+		} else {
+			list_del(&active->vdesc.node);
+			vchan_cookie_complete(&active->vdesc);
+			active = axi_dmac_active_desc(chan);
+			start_next = !!active;
 		}
+	} else {
+		do {
+			sg = &active->sg[active->num_completed];
+			if (sg->hw->id == AXI_DMAC_SG_UNUSED) /* Not yet submitted */
+				break;
+			if (!(BIT(sg->hw->id) & completed_transfers))
+				break;
+			active->num_completed++;
+			sg->hw->id = AXI_DMAC_SG_UNUSED;
+			if (sg->schedule_when_free) {
+				sg->schedule_when_free = false;
+				start_next = true;
+			}
 
-		if (sg->partial_len)
-			axi_dmac_compute_residue(chan, active);
+			if (sg->partial_len)
+				axi_dmac_compute_residue(chan, active);
 
-		if (active->cyclic)
-			vchan_cyclic_callback(&active->vdesc);
+			if (active->cyclic)
+				vchan_cyclic_callback(&active->vdesc);
 
-		if (active->num_completed == active->num_sgs ||
-		    sg->partial_len) {
-			if (active->cyclic) {
-				active->num_completed = 0; /* wrap around */
-			} else {
-				list_del(&active->vdesc.node);
-				vchan_cookie_complete(&active->vdesc);
-				active = axi_dmac_active_desc(chan);
+			if (active->num_completed == active->num_sgs ||
+			    sg->partial_len) {
+				if (active->cyclic) {
+					active->num_completed = 0; /* wrap around */
+				} else {
+					list_del(&active->vdesc.node);
+					vchan_cookie_complete(&active->vdesc);
+					active = axi_dmac_active_desc(chan);
+				}
 			}
-		}
-	} while (active);
+		} while (active);
+	}
 
 	return start_next;
 }
@@ -467,8 +514,12 @@ static void axi_dmac_issue_pending(struct dma_chan *c)
 	struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
 	struct axi_dmac *dmac = chan_to_axi_dmac(chan);
 	unsigned long flags;
+	u32 ctrl = AXI_DMAC_CTRL_ENABLE;
 
-	axi_dmac_write(dmac, AXI_DMAC_REG_CTRL, AXI_DMAC_CTRL_ENABLE);
+	if (chan->hw_sg)
+		ctrl |= AXI_DMAC_CTRL_ENABLE_SG;
+
+	axi_dmac_write(dmac, AXI_DMAC_REG_CTRL, ctrl);
 
 	spin_lock_irqsave(&chan->vchan.lock, flags);
 	if (vchan_issue_pending(&chan->vchan))
@@ -476,22 +527,58 @@ static void axi_dmac_issue_pending(struct dma_chan *c)
 	spin_unlock_irqrestore(&chan->vchan.lock, flags);
 }
 
-static struct axi_dmac_desc *axi_dmac_alloc_desc(unsigned int num_sgs)
+static struct axi_dmac_desc *
+axi_dmac_alloc_desc(struct axi_dmac_chan *chan, unsigned int num_sgs)
 {
+	struct axi_dmac *dmac = chan_to_axi_dmac(chan);
+	struct device *dev = dmac->dma_dev.dev;
+	struct axi_dmac_hw_desc *hws;
 	struct axi_dmac_desc *desc;
+	dma_addr_t hw_phys;
 	unsigned int i;
 
 	desc = kzalloc(struct_size(desc, sg, num_sgs), GFP_NOWAIT);
 	if (!desc)
 		return NULL;
 	desc->num_sgs = num_sgs;
+	desc->chan = chan;
+
+	hws = dma_alloc_coherent(dev, PAGE_ALIGN(num_sgs * sizeof(*hws)),
+				&hw_phys, GFP_ATOMIC);
+	if (!hws) {
+		kfree(desc);
+		return NULL;
+	}
 
-	for (i = 0; i < num_sgs; i++)
-		desc->sg[i].id = AXI_DMAC_SG_UNUSED;
+	for (i = 0; i < num_sgs; i++) {
+		desc->sg[i].hw = &hws[i];
+		desc->sg[i].hw_phys = hw_phys + i * sizeof(*hws);
+
+		hws[i].id = AXI_DMAC_SG_UNUSED;
+		hws[i].flags = 0;
+
+		/* Link hardware descriptors */
+		hws[i].next_sg_addr = hw_phys + (i + 1) * sizeof(*hws);
+	}
+
+	/* The last hardware descriptor will trigger an interrupt */
+	desc->sg[num_sgs - 1].hw->flags = AXI_DMAC_HW_FLAG_LAST | AXI_DMAC_HW_FLAG_IRQ;
 
 	return desc;
 }
 
+static void axi_dmac_free_desc(struct axi_dmac_desc *desc)
+{
+	struct axi_dmac *dmac = chan_to_axi_dmac(desc->chan);
+	struct device *dev = dmac->dma_dev.dev;
+	struct axi_dmac_hw_desc *hw = desc->sg[0].hw;
+	dma_addr_t hw_phys = desc->sg[0].hw_phys;
+
+	dma_free_coherent(dev, PAGE_ALIGN(desc->num_sgs * sizeof(*hw)),
+			  hw, hw_phys);
+	kfree(desc);
+}
+
 static struct axi_dmac_sg *axi_dmac_fill_linear_sg(struct axi_dmac_chan *chan,
 	enum dma_transfer_direction direction, dma_addr_t addr,
 	unsigned int num_periods, unsigned int period_len,
@@ -508,26 +595,24 @@ static struct axi_dmac_sg *axi_dmac_fill_linear_sg(struct axi_dmac_chan *chan,
 	segment_size = ((segment_size - 1) | chan->length_align_mask) + 1;
 
 	for (i = 0; i < num_periods; i++) {
-		len = period_len;
-
-		while (len > segment_size) {
+		for (len = period_len; len > segment_size; sg++) {
 			if (direction == DMA_DEV_TO_MEM)
-				sg->dest_addr = addr;
+				sg->hw->dest_addr = addr;
 			else
-				sg->src_addr = addr;
-			sg->x_len = segment_size;
-			sg->y_len = 1;
-			sg++;
+				sg->hw->src_addr = addr;
+			sg->hw->x_len = segment_size - 1;
+			sg->hw->y_len = 0;
+			sg->hw->flags = 0;
 			addr += segment_size;
 			len -= segment_size;
 		}
 
 		if (direction == DMA_DEV_TO_MEM)
-			sg->dest_addr = addr;
+			sg->hw->dest_addr = addr;
 		else
-			sg->src_addr = addr;
-		sg->x_len = len;
-		sg->y_len = 1;
+			sg->hw->src_addr = addr;
+		sg->hw->x_len = len - 1;
+		sg->hw->y_len = 0;
 		sg++;
 		addr += len;
 	}
@@ -554,7 +639,7 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_slave_sg(
 	for_each_sg(sgl, sg, sg_len, i)
 		num_sgs += DIV_ROUND_UP(sg_dma_len(sg), chan->max_length);
 
-	desc = axi_dmac_alloc_desc(num_sgs);
+	desc = axi_dmac_alloc_desc(chan, num_sgs);
 	if (!desc)
 		return NULL;
 
@@ -563,7 +648,7 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_slave_sg(
 	for_each_sg(sgl, sg, sg_len, i) {
 		if (!axi_dmac_check_addr(chan, sg_dma_address(sg)) ||
 		    !axi_dmac_check_len(chan, sg_dma_len(sg))) {
-			kfree(desc);
+			axi_dmac_free_desc(desc);
 			return NULL;
 		}
 
@@ -583,7 +668,7 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_dma_cyclic(
 {
 	struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
 	struct axi_dmac_desc *desc;
-	unsigned int num_periods, num_segments;
+	unsigned int num_periods, num_segments, num_sgs;
 
 	if (direction != chan->direction)
 		return NULL;
@@ -597,11 +682,16 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_dma_cyclic(
 
 	num_periods = buf_len / period_len;
 	num_segments = DIV_ROUND_UP(period_len, chan->max_length);
+	num_sgs = num_periods * num_segments;
 
-	desc = axi_dmac_alloc_desc(num_periods * num_segments);
+	desc = axi_dmac_alloc_desc(chan, num_sgs);
 	if (!desc)
 		return NULL;
 
+	/* Chain the last descriptor to the first, and remove its "last" flag */
+	desc->sg[num_sgs - 1].hw->next_sg_addr = desc->sg[0].hw_phys;
+	desc->sg[num_sgs - 1].hw->flags &= ~AXI_DMAC_HW_FLAG_LAST;
+
 	axi_dmac_fill_linear_sg(chan, direction, buf_addr, num_periods,
 		period_len, desc->sg);
 
@@ -653,26 +743,26 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_interleaved(
 			return NULL;
 	}
 
-	desc = axi_dmac_alloc_desc(1);
+	desc = axi_dmac_alloc_desc(chan, 1);
 	if (!desc)
 		return NULL;
 
 	if (axi_dmac_src_is_mem(chan)) {
-		desc->sg[0].src_addr = xt->src_start;
-		desc->sg[0].src_stride = xt->sgl[0].size + src_icg;
+		desc->sg[0].hw->src_addr = xt->src_start;
+		desc->sg[0].hw->src_stride = xt->sgl[0].size + src_icg;
 	}
 
 	if (axi_dmac_dest_is_mem(chan)) {
-		desc->sg[0].dest_addr = xt->dst_start;
-		desc->sg[0].dest_stride = xt->sgl[0].size + dst_icg;
+		desc->sg[0].hw->dest_addr = xt->dst_start;
+		desc->sg[0].hw->dst_stride = xt->sgl[0].size + dst_icg;
 	}
 
 	if (chan->hw_2d) {
-		desc->sg[0].x_len = xt->sgl[0].size;
-		desc->sg[0].y_len = xt->numf;
+		desc->sg[0].hw->x_len = xt->sgl[0].size - 1;
+		desc->sg[0].hw->y_len = xt->numf - 1;
 	} else {
-		desc->sg[0].x_len = xt->sgl[0].size * xt->numf;
-		desc->sg[0].y_len = 1;
+		desc->sg[0].hw->x_len = xt->sgl[0].size * xt->numf - 1;
+		desc->sg[0].hw->y_len = 0;
 	}
 
 	if (flags & DMA_CYCLIC)
@@ -688,7 +778,7 @@ static void axi_dmac_free_chan_resources(struct dma_chan *c)
 
 static void axi_dmac_desc_free(struct virt_dma_desc *vdesc)
 {
-	kfree(container_of(vdesc, struct axi_dmac_desc, vdesc));
+	axi_dmac_free_desc(to_axi_dmac_desc(vdesc));
 }
 
 static bool axi_dmac_regmap_rdwr(struct device *dev, unsigned int reg)
@@ -714,6 +804,9 @@ static bool axi_dmac_regmap_rdwr(struct device *dev, unsigned int reg)
 	case AXI_DMAC_REG_CURRENT_DEST_ADDR:
 	case AXI_DMAC_REG_PARTIAL_XFER_LEN:
 	case AXI_DMAC_REG_PARTIAL_XFER_ID:
+	case AXI_DMAC_REG_CURRENT_SG_ID:
+	case AXI_DMAC_REG_SG_ADDRESS:
+	case AXI_DMAC_REG_SG_ADDRESS_HIGH:
 		return true;
 	default:
 		return false;
@@ -866,6 +959,10 @@ static int axi_dmac_detect_caps(struct axi_dmac *dmac, unsigned int version)
 	if (axi_dmac_read(dmac, AXI_DMAC_REG_FLAGS) == AXI_DMAC_FLAG_CYCLIC)
 		chan->hw_cyclic = true;
 
+	axi_dmac_write(dmac, AXI_DMAC_REG_SG_ADDRESS, 0xffffffff);
+	if (axi_dmac_read(dmac, AXI_DMAC_REG_SG_ADDRESS))
+		chan->hw_sg = true;
+
 	axi_dmac_write(dmac, AXI_DMAC_REG_Y_LENGTH, 1);
 	if (axi_dmac_read(dmac, AXI_DMAC_REG_Y_LENGTH) == 1)
 		chan->hw_2d = true;
@@ -911,6 +1008,7 @@ static int axi_dmac_probe(struct platform_device *pdev)
 	struct axi_dmac *dmac;
 	struct regmap *regmap;
 	unsigned int version;
+	u32 irq_mask = 0;
 	int ret;
 
 	dmac = devm_kzalloc(&pdev->dev, sizeof(*dmac), GFP_KERNEL);
@@ -966,6 +1064,7 @@ static int axi_dmac_probe(struct platform_device *pdev)
 	dma_dev->dst_addr_widths = BIT(dmac->chan.dest_width);
 	dma_dev->directions = BIT(dmac->chan.direction);
 	dma_dev->residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+	dma_dev->max_sg_burst = 31; /* 31 SGs maximum in one burst */
 	INIT_LIST_HEAD(&dma_dev->channels);
 
 	dmac->chan.vchan.desc_free = axi_dmac_desc_free;
@@ -977,7 +1076,10 @@ static int axi_dmac_probe(struct platform_device *pdev)
 
 	dma_dev->copy_align = (dmac->chan.address_align_mask + 1);
 
-	axi_dmac_write(dmac, AXI_DMAC_REG_IRQ_MASK, 0x00);
+	if (dmac->chan.hw_sg)
+		irq_mask |= AXI_DMAC_IRQ_SOT;
+
+	axi_dmac_write(dmac, AXI_DMAC_REG_IRQ_MASK, irq_mask);
 
 	if (of_dma_is_coherent(pdev->dev.of_node)) {
 		ret = axi_dmac_read(dmac, AXI_DMAC_REG_COHERENCY_DESC);
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index b7388ae62d7f..491b22240221 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -1103,6 +1103,9 @@ EXPORT_SYMBOL_GPL(dma_async_device_channel_register);
 static void __dma_async_device_channel_unregister(struct dma_device *device,
 						  struct dma_chan *chan)
 {
+	if (chan->local == NULL)
+		return;
+
 	WARN_ONCE(!device->device_release && chan->client_count,
 		  "%s called while %d clients hold a reference\n",
 		  __func__, chan->client_count);
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index ffe621695e47..a4f608837849 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -21,6 +21,10 @@
 #include <linux/slab.h>
 #include <linux/wait.h>
 
+static bool nobounce;
+module_param(nobounce, bool, 0644);
+MODULE_PARM_DESC(nobounce, "Prevent using swiotlb buffer (default: use swiotlb buffer)");
+
 static unsigned int test_buf_size = 16384;
 module_param(test_buf_size, uint, 0644);
 MODULE_PARM_DESC(test_buf_size, "Size of the memcpy test buffer");
@@ -90,6 +94,7 @@ MODULE_PARM_DESC(polled, "Use polling for completion instead of interrupts");
 
 /**
  * struct dmatest_params - test parameters.
+ * @nobounce:		prevent using swiotlb buffer
  * @buf_size:		size of the memcpy test buffer
  * @channel:		bus ID of the channel to test
  * @device:		bus ID of the DMA Engine to test
@@ -106,6 +111,7 @@ MODULE_PARM_DESC(polled, "Use polling for completion instead of interrupts");
  * @polled:		use polling for completion instead of interrupts
  */
 struct dmatest_params {
+	bool		nobounce;
 	unsigned int	buf_size;
 	char		channel[20];
 	char		device[32];
@@ -215,6 +221,7 @@ struct dmatest_done {
 struct dmatest_data {
 	u8		**raw;
 	u8		**aligned;
+	gfp_t		gfp_flags;
 	unsigned int	cnt;
 	unsigned int	off;
 };
@@ -533,7 +540,7 @@ static int dmatest_alloc_test_data(struct dmatest_data *d,
 		goto err;
 
 	for (i = 0; i < d->cnt; i++) {
-		d->raw[i] = kmalloc(buf_size + align, GFP_KERNEL);
+		d->raw[i] = kmalloc(buf_size + align, d->gfp_flags);
 		if (!d->raw[i])
 			goto err;
 
@@ -655,6 +662,13 @@ static int dmatest_func(void *data)
 		goto err_free_coefs;
 	}
 
+	src->gfp_flags = GFP_KERNEL;
+	dst->gfp_flags = GFP_KERNEL;
+	if (params->nobounce) {
+		src->gfp_flags = GFP_DMA;
+		dst->gfp_flags = GFP_DMA;
+	}
+
 	if (dmatest_alloc_test_data(src, buf_size, align) < 0)
 		goto err_free_coefs;
 
@@ -1093,6 +1107,7 @@ static void add_threaded_test(struct dmatest_info *info)
 	struct dmatest_params *params = &info->params;
 
 	/* Copy test parameters */
+	params->nobounce = nobounce;
 	params->buf_size = test_buf_size;
 	strscpy(params->channel, strim(test_channel), sizeof(params->channel));
 	strscpy(params->device, strim(test_device), sizeof(params->device));
diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c
index b38786f0ad79..b75fdaffad9a 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-core.c
+++ b/drivers/dma/dw-edma/dw-edma-v0-core.c
@@ -346,6 +346,20 @@ static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
 	dw_edma_v0_write_ll_link(chunk, i, control, chunk->ll_region.paddr);
 }
 
+static void dw_edma_v0_sync_ll_data(struct dw_edma_chunk *chunk)
+{
+	/*
+	 * In case of remote eDMA engine setup, the DW PCIe RP/EP internal
+	 * configuration registers and application memory are normally accessed
+	 * over different buses. Ensure LL-data reaches the memory before the
+	 * doorbell register is toggled by issuing the dummy-read from the remote
+	 * LL memory in a hope that the MRd TLP will return only after the
+	 * last MWr TLP is completed
+	 */
+	if (!(chunk->chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL))
+		readl(chunk->ll_region.vaddr.io);
+}
+
 static void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 {
 	struct dw_edma_chan *chan = chunk->chan;
@@ -412,6 +426,9 @@ static void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 		SET_CH_32(dw, chan->dir, chan->id, llp.msb,
 			  upper_32_bits(chunk->ll_region.paddr));
 	}
+
+	dw_edma_v0_sync_ll_data(chunk);
+
 	/* Doorbell */
 	SET_RW_32(dw, chan->dir, doorbell,
 		  FIELD_PREP(EDMA_V0_DOORBELL_CH_MASK, chan->id));
diff --git a/drivers/dma/dw-edma/dw-edma-v0-debugfs.c b/drivers/dma/dw-edma/dw-edma-v0-debugfs.c
index 0745d9e7d259..406f169b09a7 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-debugfs.c
+++ b/drivers/dma/dw-edma/dw-edma-v0-debugfs.c
@@ -176,7 +176,7 @@ dw_edma_debugfs_regs_wr(struct dw_edma *dw, struct dentry *dent)
 	};
 	struct dentry *regs_dent, *ch_dent;
 	int nr_entries, i;
-	char name[16];
+	char name[32];
 
 	regs_dent = debugfs_create_dir(WRITE_STR, dent);
 
@@ -239,7 +239,7 @@ static noinline_for_stack void dw_edma_debugfs_regs_rd(struct dw_edma *dw,
 	};
 	struct dentry *regs_dent, *ch_dent;
 	int nr_entries, i;
-	char name[16];
+	char name[32];
 
 	regs_dent = debugfs_create_dir(READ_STR, dent);
 
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-core.c b/drivers/dma/dw-edma/dw-hdma-v0-core.c
index 00b735a0202a..10e8f0715114 100644
--- a/drivers/dma/dw-edma/dw-hdma-v0-core.c
+++ b/drivers/dma/dw-edma/dw-hdma-v0-core.c
@@ -65,18 +65,12 @@ static void dw_hdma_v0_core_off(struct dw_edma *dw)
 
 static u16 dw_hdma_v0_core_ch_count(struct dw_edma *dw, enum dw_edma_dir dir)
 {
-	u32 num_ch = 0;
-	int id;
-
-	for (id = 0; id < HDMA_V0_MAX_NR_CH; id++) {
-		if (GET_CH_32(dw, id, dir, ch_en) & BIT(0))
-			num_ch++;
-	}
-
-	if (num_ch > HDMA_V0_MAX_NR_CH)
-		num_ch = HDMA_V0_MAX_NR_CH;
-
-	return (u16)num_ch;
+	/*
+	 * The HDMA IP have no way to know the number of hardware channels
+	 * available, we set it to maximum channels and let the platform
+	 * set the right number of channels.
+	 */
+	return HDMA_V0_MAX_NR_CH;
 }
 
 static enum dma_status dw_hdma_v0_core_ch_status(struct dw_edma_chan *chan)
@@ -228,6 +222,20 @@ static void dw_hdma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
 	dw_hdma_v0_write_ll_link(chunk, i, control, chunk->ll_region.paddr);
 }
 
+static void dw_hdma_v0_sync_ll_data(struct dw_edma_chunk *chunk)
+{
+	/*
+	 * In case of remote HDMA engine setup, the DW PCIe RP/EP internal
+	 * configuration registers and application memory are normally accessed
+	 * over different buses. Ensure LL-data reaches the memory before the
+	 * doorbell register is toggled by issuing the dummy-read from the remote
+	 * LL memory in a hope that the MRd TLP will return only after the
+	 * last MWr TLP is completed
+	 */
+	if (!(chunk->chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL))
+		readl(chunk->ll_region.vaddr.io);
+}
+
 static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 {
 	struct dw_edma_chan *chan = chunk->chan;
@@ -242,7 +250,9 @@ static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 		/* Interrupt enable&unmask - done, abort */
 		tmp = GET_CH_32(dw, chan->dir, chan->id, int_setup) |
 		      HDMA_V0_STOP_INT_MASK | HDMA_V0_ABORT_INT_MASK |
-		      HDMA_V0_LOCAL_STOP_INT_EN | HDMA_V0_LOCAL_STOP_INT_EN;
+		      HDMA_V0_LOCAL_STOP_INT_EN | HDMA_V0_LOCAL_ABORT_INT_EN;
+		if (!(dw->chip->flags & DW_EDMA_CHIP_LOCAL))
+			tmp |= HDMA_V0_REMOTE_STOP_INT_EN | HDMA_V0_REMOTE_ABORT_INT_EN;
 		SET_CH_32(dw, chan->dir, chan->id, int_setup, tmp);
 		/* Channel control */
 		SET_CH_32(dw, chan->dir, chan->id, control1, HDMA_V0_LINKLIST_EN);
@@ -256,6 +266,9 @@ static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 	/* Set consumer cycle */
 	SET_CH_32(dw, chan->dir, chan->id, cycle_sync,
 		  HDMA_V0_CONSUMER_CYCLE_STAT | HDMA_V0_CONSUMER_CYCLE_BIT);
+
+	dw_hdma_v0_sync_ll_data(chunk);
+
 	/* Doorbell */
 	SET_CH_32(dw, chan->dir, chan->id, doorbell, HDMA_V0_DOORBELL_START);
 }
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c b/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c
index 520c81978b08..dcdc57fe976c 100644
--- a/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c
+++ b/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c
@@ -116,7 +116,7 @@ static void dw_hdma_debugfs_regs_ch(struct dw_edma *dw, enum dw_edma_dir dir,
 static void dw_hdma_debugfs_regs_wr(struct dw_edma *dw, struct dentry *dent)
 {
 	struct dentry *regs_dent, *ch_dent;
-	char name[16];
+	char name[32];
 	int i;
 
 	regs_dent = debugfs_create_dir(WRITE_STR, dent);
@@ -133,7 +133,7 @@ static void dw_hdma_debugfs_regs_wr(struct dw_edma *dw, struct dentry *dent)
 static void dw_hdma_debugfs_regs_rd(struct dw_edma *dw, struct dentry *dent)
 {
 	struct dentry *regs_dent, *ch_dent;
-	char name[16];
+	char name[32];
 	int i;
 
 	regs_dent = debugfs_create_dir(READ_STR, dent);
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-regs.h b/drivers/dma/dw-edma/dw-hdma-v0-regs.h
index a974abdf8aaf..eab5fd7177e5 100644
--- a/drivers/dma/dw-edma/dw-hdma-v0-regs.h
+++ b/drivers/dma/dw-edma/dw-hdma-v0-regs.h
@@ -15,7 +15,7 @@
 #define HDMA_V0_LOCAL_ABORT_INT_EN		BIT(6)
 #define HDMA_V0_REMOTE_ABORT_INT_EN		BIT(5)
 #define HDMA_V0_LOCAL_STOP_INT_EN		BIT(4)
-#define HDMA_V0_REMOTEL_STOP_INT_EN		BIT(3)
+#define HDMA_V0_REMOTE_STOP_INT_EN		BIT(3)
 #define HDMA_V0_ABORT_INT_MASK			BIT(2)
 #define HDMA_V0_STOP_INT_MASK			BIT(0)
 #define HDMA_V0_LINKLIST_EN			BIT(0)
diff --git a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c
index 7958ac33e36c..5a8061a307cd 100644
--- a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c
+++ b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c
@@ -38,15 +38,17 @@ static int dpaa2_qdma_alloc_chan_resources(struct dma_chan *chan)
 	if (!dpaa2_chan->fd_pool)
 		goto err;
 
-	dpaa2_chan->fl_pool = dma_pool_create("fl_pool", dev,
-					      sizeof(struct dpaa2_fl_entry),
-					      sizeof(struct dpaa2_fl_entry), 0);
+	dpaa2_chan->fl_pool =
+		dma_pool_create("fl_pool", dev,
+				 sizeof(struct dpaa2_fl_entry) * 3,
+				 sizeof(struct dpaa2_fl_entry), 0);
+
 	if (!dpaa2_chan->fl_pool)
 		goto err_fd;
 
 	dpaa2_chan->sdd_pool =
 		dma_pool_create("sdd_pool", dev,
-				sizeof(struct dpaa2_qdma_sd_d),
+				sizeof(struct dpaa2_qdma_sd_d) * 2,
 				sizeof(struct dpaa2_qdma_sd_d), 0);
 	if (!dpaa2_chan->sdd_pool)
 		goto err_fl;
diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c
index b53f46245c37..793f1a7ad5e3 100644
--- a/drivers/dma/fsl-edma-common.c
+++ b/drivers/dma/fsl-edma-common.c
@@ -503,7 +503,7 @@ void fsl_edma_fill_tcd(struct fsl_edma_chan *fsl_chan,
 	if (fsl_chan->is_multi_fifo) {
 		/* set mloff to support multiple fifo */
 		burst = cfg->direction == DMA_DEV_TO_MEM ?
-				cfg->src_addr_width : cfg->dst_addr_width;
+				cfg->src_maxburst : cfg->dst_maxburst;
 		nbytes |= EDMA_V3_TCD_NBYTES_MLOFF(-(burst * 4));
 		/* enable DMLOE/SMLOE */
 		if (cfg->direction == DMA_MEM_TO_DEV) {
diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h
index bb5221158a77..f5e216b157c7 100644
--- a/drivers/dma/fsl-edma-common.h
+++ b/drivers/dma/fsl-edma-common.h
@@ -30,8 +30,9 @@
 #define EDMA_TCD_ATTR_SSIZE(x)		(((x) & GENMASK(2, 0)) << 8)
 #define EDMA_TCD_ATTR_SMOD(x)		(((x) & GENMASK(4, 0)) << 11)
 
-#define EDMA_TCD_CITER_CITER(x)		((x) & GENMASK(14, 0))
-#define EDMA_TCD_BITER_BITER(x)		((x) & GENMASK(14, 0))
+#define EDMA_TCD_ITER_MASK		GENMASK(14, 0)
+#define EDMA_TCD_CITER_CITER(x)		((x) & EDMA_TCD_ITER_MASK)
+#define EDMA_TCD_BITER_BITER(x)		((x) & EDMA_TCD_ITER_MASK)
 
 #define EDMA_TCD_CSR_START		BIT(0)
 #define EDMA_TCD_CSR_INT_MAJOR		BIT(1)
diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
index 238a69bd0d6f..d36e28b9c767 100644
--- a/drivers/dma/fsl-edma-main.c
+++ b/drivers/dma/fsl-edma-main.c
@@ -9,6 +9,8 @@
  * Vybrid and Layerscape SoCs.
  */
 
+#include <dt-bindings/dma/fsl-edma.h>
+#include <linux/bitfield.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/clk.h>
@@ -21,10 +23,6 @@
 
 #include "fsl-edma-common.h"
 
-#define ARGS_RX                         BIT(0)
-#define ARGS_REMOTE                     BIT(1)
-#define ARGS_MULTI_FIFO                 BIT(2)
-
 static void fsl_edma_synchronize(struct dma_chan *chan)
 {
 	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
@@ -153,9 +151,15 @@ static struct dma_chan *fsl_edma3_xlate(struct of_phandle_args *dma_spec,
 		i = fsl_chan - fsl_edma->chans;
 
 		fsl_chan->priority = dma_spec->args[1];
-		fsl_chan->is_rxchan = dma_spec->args[2] & ARGS_RX;
-		fsl_chan->is_remote = dma_spec->args[2] & ARGS_REMOTE;
-		fsl_chan->is_multi_fifo = dma_spec->args[2] & ARGS_MULTI_FIFO;
+		fsl_chan->is_rxchan = dma_spec->args[2] & FSL_EDMA_RX;
+		fsl_chan->is_remote = dma_spec->args[2] & FSL_EDMA_REMOTE;
+		fsl_chan->is_multi_fifo = dma_spec->args[2] & FSL_EDMA_MULTI_FIFO;
+
+		if ((dma_spec->args[2] & FSL_EDMA_EVEN_CH) && (i & 0x1))
+			continue;
+
+		if ((dma_spec->args[2] & FSL_EDMA_ODD_CH) && !(i & 0x1))
+			continue;
 
 		if (!b_chmux && i == dma_spec->args[0]) {
 			chan = dma_get_slave_channel(chan);
@@ -579,7 +583,8 @@ static int fsl_edma_probe(struct platform_device *pdev)
 					DMAENGINE_ALIGN_32_BYTES;
 
 	/* Per worst case 'nbytes = 1' take CITER as the max_seg_size */
-	dma_set_max_seg_size(fsl_edma->dma_dev.dev, 0x3fff);
+	dma_set_max_seg_size(fsl_edma->dma_dev.dev,
+			     FIELD_GET(EDMA_TCD_ITER_MASK, EDMA_TCD_ITER_MASK));
 
 	fsl_edma->dma_dev.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
 
diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c
index 47cb28468049..5005e138fc23 100644
--- a/drivers/dma/fsl-qdma.c
+++ b/drivers/dma/fsl-qdma.c
@@ -109,6 +109,7 @@
 #define FSL_QDMA_CMD_WTHROTL_OFFSET	20
 #define FSL_QDMA_CMD_DSEN_OFFSET	19
 #define FSL_QDMA_CMD_LWC_OFFSET		16
+#define FSL_QDMA_CMD_PF			BIT(17)
 
 /* Field definition for Descriptor status */
 #define QDMA_CCDF_STATUS_RTE		BIT(5)
@@ -160,6 +161,10 @@ struct fsl_qdma_format {
 			u8 __reserved1[2];
 			u8 cfg8b_w1;
 		} __packed;
+		struct {
+			__le32 __reserved2;
+			__le32 cmd;
+		} __packed;
 		__le64 data;
 	};
 } __packed;
@@ -354,7 +359,6 @@ static void fsl_qdma_free_chan_resources(struct dma_chan *chan)
 static void fsl_qdma_comp_fill_memcpy(struct fsl_qdma_comp *fsl_comp,
 				      dma_addr_t dst, dma_addr_t src, u32 len)
 {
-	u32 cmd;
 	struct fsl_qdma_format *sdf, *ddf;
 	struct fsl_qdma_format *ccdf, *csgf_desc, *csgf_src, *csgf_dest;
 
@@ -383,14 +387,11 @@ static void fsl_qdma_comp_fill_memcpy(struct fsl_qdma_comp *fsl_comp,
 	/* This entry is the last entry. */
 	qdma_csgf_set_f(csgf_dest, len);
 	/* Descriptor Buffer */
-	cmd = cpu_to_le32(FSL_QDMA_CMD_RWTTYPE <<
-			  FSL_QDMA_CMD_RWTTYPE_OFFSET);
-	sdf->data = QDMA_SDDF_CMD(cmd);
-
-	cmd = cpu_to_le32(FSL_QDMA_CMD_RWTTYPE <<
-			  FSL_QDMA_CMD_RWTTYPE_OFFSET);
-	cmd |= cpu_to_le32(FSL_QDMA_CMD_LWC << FSL_QDMA_CMD_LWC_OFFSET);
-	ddf->data = QDMA_SDDF_CMD(cmd);
+	sdf->cmd = cpu_to_le32((FSL_QDMA_CMD_RWTTYPE << FSL_QDMA_CMD_RWTTYPE_OFFSET) |
+			       FSL_QDMA_CMD_PF);
+
+	ddf->cmd = cpu_to_le32((FSL_QDMA_CMD_RWTTYPE << FSL_QDMA_CMD_RWTTYPE_OFFSET) |
+			       (FSL_QDMA_CMD_LWC << FSL_QDMA_CMD_LWC_OFFSET));
 }
 
 /*
@@ -514,11 +515,11 @@ static struct fsl_qdma_queue
 			queue_temp = queue_head + i + (j * queue_num);
 
 			queue_temp->cq =
-			dma_alloc_coherent(&pdev->dev,
-					   sizeof(struct fsl_qdma_format) *
-					   queue_size[i],
-					   &queue_temp->bus_addr,
-					   GFP_KERNEL);
+			dmam_alloc_coherent(&pdev->dev,
+					    sizeof(struct fsl_qdma_format) *
+					    queue_size[i],
+					    &queue_temp->bus_addr,
+					    GFP_KERNEL);
 			if (!queue_temp->cq)
 				return NULL;
 			queue_temp->block_base = fsl_qdma->block_base +
@@ -563,15 +564,14 @@ static struct fsl_qdma_queue
 	/*
 	 * Buffer for queue command
 	 */
-	status_head->cq = dma_alloc_coherent(&pdev->dev,
-					     sizeof(struct fsl_qdma_format) *
-					     status_size,
-					     &status_head->bus_addr,
-					     GFP_KERNEL);
-	if (!status_head->cq) {
-		devm_kfree(&pdev->dev, status_head);
+	status_head->cq = dmam_alloc_coherent(&pdev->dev,
+					      sizeof(struct fsl_qdma_format) *
+					      status_size,
+					      &status_head->bus_addr,
+					      GFP_KERNEL);
+	if (!status_head->cq)
 		return NULL;
-	}
+
 	status_head->n_cq = status_size;
 	status_head->virt_head = status_head->cq;
 	status_head->virt_tail = status_head->cq;
@@ -625,7 +625,7 @@ static int fsl_qdma_halt(struct fsl_qdma_engine *fsl_qdma)
 
 static int
 fsl_qdma_queue_transfer_complete(struct fsl_qdma_engine *fsl_qdma,
-				 void *block,
+				 __iomem void *block,
 				 int id)
 {
 	bool duplicate;
@@ -805,7 +805,7 @@ fsl_qdma_irq_init(struct platform_device *pdev,
 	int i;
 	int cpu;
 	int ret;
-	char irq_name[20];
+	char irq_name[32];
 
 	fsl_qdma->error_irq =
 		platform_get_irq_byname(pdev, "qdma-error");
@@ -1197,10 +1197,6 @@ static int fsl_qdma_probe(struct platform_device *pdev)
 	if (!fsl_qdma->queue)
 		return -ENOMEM;
 
-	ret = fsl_qdma_irq_init(pdev, fsl_qdma);
-	if (ret)
-		return ret;
-
 	fsl_qdma->irq_base = platform_get_irq_byname(pdev, "qdma-queue0");
 	if (fsl_qdma->irq_base < 0)
 		return fsl_qdma->irq_base;
@@ -1239,16 +1235,19 @@ static int fsl_qdma_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, fsl_qdma);
 
-	ret = dma_async_device_register(&fsl_qdma->dma_dev);
+	ret = fsl_qdma_reg_init(fsl_qdma);
 	if (ret) {
-		dev_err(&pdev->dev,
-			"Can't register NXP Layerscape qDMA engine.\n");
+		dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n");
 		return ret;
 	}
 
-	ret = fsl_qdma_reg_init(fsl_qdma);
+	ret = fsl_qdma_irq_init(pdev, fsl_qdma);
+	if (ret)
+		return ret;
+
+	ret = dma_async_device_register(&fsl_qdma->dma_dev);
 	if (ret) {
-		dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n");
+		dev_err(&pdev->dev, "Can't register NXP Layerscape qDMA engine.\n");
 		return ret;
 	}
 
@@ -1268,8 +1267,6 @@ static void fsl_qdma_cleanup_vchan(struct dma_device *dmadev)
 
 static void fsl_qdma_remove(struct platform_device *pdev)
 {
-	int i;
-	struct fsl_qdma_queue *status;
 	struct device_node *np = pdev->dev.of_node;
 	struct fsl_qdma_engine *fsl_qdma = platform_get_drvdata(pdev);
 
@@ -1277,12 +1274,6 @@ static void fsl_qdma_remove(struct platform_device *pdev)
 	fsl_qdma_cleanup_vchan(&fsl_qdma->dma_dev);
 	of_dma_controller_free(np);
 	dma_async_device_unregister(&fsl_qdma->dma_dev);
-
-	for (i = 0; i < fsl_qdma->block_number; i++) {
-		status = fsl_qdma->status[i];
-		dma_free_coherent(&pdev->dev, sizeof(struct fsl_qdma_format) *
-				status->n_cq, status->cq, status->bus_addr);
-	}
 }
 
 static const struct of_device_id fsl_qdma_dt_ids[] = {
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index 1d918d45d9f6..e5a94a93a3cc 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -165,7 +165,7 @@ static void idxd_cdev_dev_release(struct device *dev)
 	struct idxd_wq *wq = idxd_cdev->wq;
 
 	cdev_ctx = &ictx[wq->idxd->data->type];
-	ida_simple_remove(&cdev_ctx->minor_ida, idxd_cdev->minor);
+	ida_free(&cdev_ctx->minor_ida, idxd_cdev->minor);
 	kfree(idxd_cdev);
 }
 
@@ -345,7 +345,7 @@ static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid)
 	spin_lock(&evl->lock);
 	status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
 	t = status.tail;
-	h = evl->head;
+	h = status.head;
 	size = evl->size;
 
 	while (h != t) {
@@ -463,7 +463,7 @@ int idxd_wq_add_cdev(struct idxd_wq *wq)
 	cdev = &idxd_cdev->cdev;
 	dev = cdev_dev(idxd_cdev);
 	cdev_ctx = &ictx[wq->idxd->data->type];
-	minor = ida_simple_get(&cdev_ctx->minor_ida, 0, MINORMASK, GFP_KERNEL);
+	minor = ida_alloc_max(&cdev_ctx->minor_ida, MINORMASK, GFP_KERNEL);
 	if (minor < 0) {
 		kfree(idxd_cdev);
 		return minor;
diff --git a/drivers/dma/idxd/debugfs.c b/drivers/dma/idxd/debugfs.c
index 9cfbd9b14c4c..f3f25ee676f3 100644
--- a/drivers/dma/idxd/debugfs.c
+++ b/drivers/dma/idxd/debugfs.c
@@ -68,9 +68,9 @@ static int debugfs_evl_show(struct seq_file *s, void *d)
 
 	spin_lock(&evl->lock);
 
-	h = evl->head;
 	evl_status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
 	t = evl_status.tail;
+	h = evl_status.head;
 	evl_size = evl->size;
 
 	seq_printf(s, "Event Log head %u tail %u interrupt pending %u\n\n",
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index f43d81128b96..ecfdf4a8f1f8 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -807,6 +807,9 @@ err_bmap:
 
 static void idxd_device_evl_free(struct idxd_device *idxd)
 {
+	void *evl_log;
+	unsigned int evl_log_size;
+	dma_addr_t evl_dma;
 	union gencfg_reg gencfg;
 	union genctrl_reg genctrl;
 	struct device *dev = &idxd->pdev->dev;
@@ -827,11 +830,15 @@ static void idxd_device_evl_free(struct idxd_device *idxd)
 	iowrite64(0, idxd->reg_base + IDXD_EVLCFG_OFFSET);
 	iowrite64(0, idxd->reg_base + IDXD_EVLCFG_OFFSET + 8);
 
-	dma_free_coherent(dev, evl->log_size, evl->log, evl->dma);
 	bitmap_free(evl->bmap);
+	evl_log = evl->log;
+	evl_log_size = evl->log_size;
+	evl_dma = evl->dma;
 	evl->log = NULL;
 	evl->size = IDXD_EVL_SIZE_MIN;
 	spin_unlock(&evl->lock);
+
+	dma_free_coherent(dev, evl_log_size, evl_log, evl_dma);
 }
 
 static void idxd_group_config_write(struct idxd_group *group)
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index 47de3f93ff1e..d0f5db6cf1ed 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -300,7 +300,6 @@ struct idxd_evl {
 	unsigned int log_size;
 	/* The number of entries in the event log. */
 	u16 size;
-	u16 head;
 	unsigned long *bmap;
 	bool batch_fail[IDXD_MAX_BATCH_IDENT];
 };
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index 14df1f1347a8..4954adc6bb60 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -343,7 +343,9 @@ static void idxd_cleanup_internals(struct idxd_device *idxd)
 static int idxd_init_evl(struct idxd_device *idxd)
 {
 	struct device *dev = &idxd->pdev->dev;
+	unsigned int evl_cache_size;
 	struct idxd_evl *evl;
+	const char *idxd_name;
 
 	if (idxd->hw.gen_cap.evl_support == 0)
 		return 0;
@@ -355,9 +357,16 @@ static int idxd_init_evl(struct idxd_device *idxd)
 	spin_lock_init(&evl->lock);
 	evl->size = IDXD_EVL_SIZE_MIN;
 
-	idxd->evl_cache = kmem_cache_create(dev_name(idxd_confdev(idxd)),
-					    sizeof(struct idxd_evl_fault) + evl_ent_size(idxd),
-					    0, 0, NULL);
+	idxd_name = dev_name(idxd_confdev(idxd));
+	evl_cache_size = sizeof(struct idxd_evl_fault) + evl_ent_size(idxd);
+	/*
+	 * Since completion record in evl_cache will be copied to user
+	 * when handling completion record page fault, need to create
+	 * the cache suitable for user copy.
+	 */
+	idxd->evl_cache = kmem_cache_create_usercopy(idxd_name, evl_cache_size,
+						     0, 0, 0, evl_cache_size,
+						     NULL);
 	if (!idxd->evl_cache) {
 		kfree(evl);
 		return -ENOMEM;
diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
index c8a0aa874b11..348aa21389a9 100644
--- a/drivers/dma/idxd/irq.c
+++ b/drivers/dma/idxd/irq.c
@@ -367,9 +367,9 @@ static void process_evl_entries(struct idxd_device *idxd)
 	/* Clear interrupt pending bit */
 	iowrite32(evl_status.bits_upper32,
 		  idxd->reg_base + IDXD_EVLSTATUS_OFFSET + sizeof(u32));
-	h = evl->head;
 	evl_status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
 	t = evl_status.tail;
+	h = evl_status.head;
 	size = idxd->evl->size;
 
 	while (h != t) {
@@ -378,7 +378,6 @@ static void process_evl_entries(struct idxd_device *idxd)
 		h = (h + 1) % size;
 	}
 
-	evl->head = h;
 	evl_status.head = h;
 	iowrite32(evl_status.bits_lower32, idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
 	spin_unlock(&evl->lock);
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index f81ecf5863e8..9b42f5e96b1e 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -421,9 +421,7 @@ struct sdma_desc {
  * @shp_addr:		value for gReg[6]
  * @per_addr:		value for gReg[2]
  * @status:		status of dma channel
- * @context_loaded:	ensure context is only loaded once
  * @data:		specific sdma interface structure
- * @bd_pool:		dma_pool for bd
  * @terminate_worker:	used to call back into terminate work function
  * @terminated:		terminated list
  * @is_ram_script:	flag for script in ram
@@ -486,8 +484,6 @@ struct sdma_channel {
  * @num_script_addrs:	Number of script addresses in this image
  * @ram_code_start:	offset of SDMA ram image in this firmware image
  * @ram_code_size:	size of SDMA ram image
- * @script_addrs:	Stores the start address of the SDMA scripts
- *			(in SDMA memory space)
  */
 struct sdma_firmware_header {
 	u32	magic;
diff --git a/drivers/dma/ls2x-apb-dma.c b/drivers/dma/ls2x-apb-dma.c
new file mode 100644
index 000000000000..a49913f3ed3f
--- /dev/null
+++ b/drivers/dma/ls2x-apb-dma.c
@@ -0,0 +1,705 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Driver for the Loongson LS2X APB DMA Controller
+ *
+ * Copyright (C) 2017-2023 Loongson Corporation
+ */
+
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_dma.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "dmaengine.h"
+#include "virt-dma.h"
+
+/* Global Configuration Register */
+#define LDMA_ORDER_ERG		0x0
+
+/* Bitfield definitions */
+
+/* Bitfields in Global Configuration Register */
+#define LDMA_64BIT_EN		BIT(0) /* 1: 64 bit support */
+#define LDMA_UNCOHERENT_EN	BIT(1) /* 0: cache, 1: uncache */
+#define LDMA_ASK_VALID		BIT(2)
+#define LDMA_START		BIT(3) /* DMA start operation */
+#define LDMA_STOP		BIT(4) /* DMA stop operation */
+#define LDMA_CONFIG_MASK	GENMASK(4, 0) /* DMA controller config bits mask */
+
+/* Bitfields in ndesc_addr field of HW decriptor */
+#define LDMA_DESC_EN		BIT(0) /*1: The next descriptor is valid */
+#define LDMA_DESC_ADDR_LOW	GENMASK(31, 1)
+
+/* Bitfields in cmd field of HW decriptor */
+#define LDMA_INT		BIT(1) /* Enable DMA interrupts */
+#define LDMA_DATA_DIRECTION	BIT(12) /* 1: write to device, 0: read from device */
+
+#define LDMA_SLAVE_BUSWIDTHS	(BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) | \
+				 BIT(DMA_SLAVE_BUSWIDTH_8_BYTES))
+
+#define LDMA_MAX_TRANS_LEN	U32_MAX
+
+/*--  descriptors  -----------------------------------------------------*/
+
+/*
+ * struct ls2x_dma_hw_desc - DMA HW descriptor
+ * @ndesc_addr: the next descriptor low address.
+ * @mem_addr: memory low address.
+ * @apb_addr: device buffer address.
+ * @len: length of a piece of carried content, in words.
+ * @step_len: length between two moved memory data blocks.
+ * @step_times: number of blocks to be carried in a single DMA operation.
+ * @cmd: descriptor command or state.
+ * @stats: DMA status.
+ * @high_ndesc_addr: the next descriptor high address.
+ * @high_mem_addr: memory high address.
+ * @reserved: reserved
+ */
+struct ls2x_dma_hw_desc {
+	u32 ndesc_addr;
+	u32 mem_addr;
+	u32 apb_addr;
+	u32 len;
+	u32 step_len;
+	u32 step_times;
+	u32 cmd;
+	u32 stats;
+	u32 high_ndesc_addr;
+	u32 high_mem_addr;
+	u32 reserved[2];
+} __packed;
+
+/*
+ * struct ls2x_dma_sg - ls2x dma scatter gather entry
+ * @hw: the pointer to DMA HW descriptor.
+ * @llp: physical address of the DMA HW descriptor.
+ * @phys: destination or source address(mem).
+ * @len: number of Bytes to read.
+ */
+struct ls2x_dma_sg {
+	struct ls2x_dma_hw_desc	*hw;
+	dma_addr_t		llp;
+	dma_addr_t		phys;
+	u32			len;
+};
+
+/*
+ * struct ls2x_dma_desc - software descriptor
+ * @vdesc: pointer to the virtual dma descriptor.
+ * @cyclic: flag to dma cyclic
+ * @burst_size: burst size of transaction, in words.
+ * @desc_num: number of sg entries.
+ * @direction: transfer direction, to or from device.
+ * @status: dma controller status.
+ * @sg: array of sgs.
+ */
+struct ls2x_dma_desc {
+	struct virt_dma_desc		vdesc;
+	bool				cyclic;
+	size_t				burst_size;
+	u32				desc_num;
+	enum dma_transfer_direction	direction;
+	enum dma_status			status;
+	struct ls2x_dma_sg		sg[] __counted_by(desc_num);
+};
+
+/*--  Channels  --------------------------------------------------------*/
+
+/*
+ * struct ls2x_dma_chan - internal representation of an LS2X APB DMA channel
+ * @vchan: virtual dma channel entry.
+ * @desc: pointer to the ls2x sw dma descriptor.
+ * @pool: hw desc table
+ * @irq: irq line
+ * @sconfig: configuration for slave transfers, passed via .device_config
+ */
+struct ls2x_dma_chan {
+	struct virt_dma_chan	vchan;
+	struct ls2x_dma_desc	*desc;
+	void			*pool;
+	int			irq;
+	struct dma_slave_config	sconfig;
+};
+
+/*--  Controller  ------------------------------------------------------*/
+
+/*
+ * struct ls2x_dma_priv - LS2X APB DMAC specific information
+ * @ddev: dmaengine dma_device object members
+ * @dma_clk: DMAC clock source
+ * @regs: memory mapped register base
+ * @lchan: channel to store ls2x_dma_chan structures
+ */
+struct ls2x_dma_priv {
+	struct dma_device	ddev;
+	struct clk		*dma_clk;
+	void __iomem		*regs;
+	struct ls2x_dma_chan	lchan;
+};
+
+/*--  Helper functions  ------------------------------------------------*/
+
+static inline struct ls2x_dma_desc *to_ldma_desc(struct virt_dma_desc *vdesc)
+{
+	return container_of(vdesc, struct ls2x_dma_desc, vdesc);
+}
+
+static inline struct ls2x_dma_chan *to_ldma_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct ls2x_dma_chan, vchan.chan);
+}
+
+static inline struct ls2x_dma_priv *to_ldma_priv(struct dma_device *ddev)
+{
+	return container_of(ddev, struct ls2x_dma_priv, ddev);
+}
+
+static struct device *chan2dev(struct dma_chan *chan)
+{
+	return &chan->dev->device;
+}
+
+static void ls2x_dma_desc_free(struct virt_dma_desc *vdesc)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(vdesc->tx.chan);
+	struct ls2x_dma_desc *desc = to_ldma_desc(vdesc);
+	int i;
+
+	for (i = 0; i < desc->desc_num; i++) {
+		if (desc->sg[i].hw)
+			dma_pool_free(lchan->pool, desc->sg[i].hw,
+				      desc->sg[i].llp);
+	}
+
+	kfree(desc);
+}
+
+static void ls2x_dma_write_cmd(struct ls2x_dma_chan *lchan, bool cmd)
+{
+	struct ls2x_dma_priv *priv = to_ldma_priv(lchan->vchan.chan.device);
+	u64 val;
+
+	val = lo_hi_readq(priv->regs + LDMA_ORDER_ERG) & ~LDMA_CONFIG_MASK;
+	val |= LDMA_64BIT_EN | cmd;
+	lo_hi_writeq(val, priv->regs + LDMA_ORDER_ERG);
+}
+
+static void ls2x_dma_start_transfer(struct ls2x_dma_chan *lchan)
+{
+	struct ls2x_dma_priv *priv = to_ldma_priv(lchan->vchan.chan.device);
+	struct ls2x_dma_sg *ldma_sg;
+	struct virt_dma_desc *vdesc;
+	u64 val;
+
+	/* Get the next descriptor */
+	vdesc = vchan_next_desc(&lchan->vchan);
+	if (!vdesc) {
+		lchan->desc = NULL;
+		return;
+	}
+
+	list_del(&vdesc->node);
+	lchan->desc = to_ldma_desc(vdesc);
+	ldma_sg = &lchan->desc->sg[0];
+
+	/* Start DMA */
+	lo_hi_writeq(0, priv->regs + LDMA_ORDER_ERG);
+	val = (ldma_sg->llp & ~LDMA_CONFIG_MASK) | LDMA_64BIT_EN | LDMA_START;
+	lo_hi_writeq(val, priv->regs + LDMA_ORDER_ERG);
+}
+
+static size_t ls2x_dmac_detect_burst(struct ls2x_dma_chan *lchan)
+{
+	u32 maxburst, buswidth;
+
+	/* Reject definitely invalid configurations */
+	if ((lchan->sconfig.src_addr_width & LDMA_SLAVE_BUSWIDTHS) &&
+	    (lchan->sconfig.dst_addr_width & LDMA_SLAVE_BUSWIDTHS))
+		return 0;
+
+	if (lchan->sconfig.direction == DMA_MEM_TO_DEV) {
+		maxburst = lchan->sconfig.dst_maxburst;
+		buswidth = lchan->sconfig.dst_addr_width;
+	} else {
+		maxburst = lchan->sconfig.src_maxburst;
+		buswidth = lchan->sconfig.src_addr_width;
+	}
+
+	/* If maxburst is zero, fallback to LDMA_MAX_TRANS_LEN */
+	return maxburst ? (maxburst * buswidth) >> 2 : LDMA_MAX_TRANS_LEN;
+}
+
+static void ls2x_dma_fill_desc(struct ls2x_dma_chan *lchan, u32 sg_index,
+			       struct ls2x_dma_desc *desc)
+{
+	struct ls2x_dma_sg *ldma_sg = &desc->sg[sg_index];
+	u32 num_segments, segment_size;
+
+	if (desc->direction == DMA_MEM_TO_DEV) {
+		ldma_sg->hw->cmd = LDMA_INT | LDMA_DATA_DIRECTION;
+		ldma_sg->hw->apb_addr = lchan->sconfig.dst_addr;
+	} else {
+		ldma_sg->hw->cmd = LDMA_INT;
+		ldma_sg->hw->apb_addr = lchan->sconfig.src_addr;
+	}
+
+	ldma_sg->hw->mem_addr = lower_32_bits(ldma_sg->phys);
+	ldma_sg->hw->high_mem_addr = upper_32_bits(ldma_sg->phys);
+
+	/* Split into multiple equally sized segments if necessary */
+	num_segments = DIV_ROUND_UP((ldma_sg->len + 3) >> 2, desc->burst_size);
+	segment_size = DIV_ROUND_UP((ldma_sg->len + 3) >> 2, num_segments);
+
+	/* Word count register takes input in words */
+	ldma_sg->hw->len = segment_size;
+	ldma_sg->hw->step_times = num_segments;
+	ldma_sg->hw->step_len = 0;
+
+	/* lets make a link list */
+	if (sg_index) {
+		desc->sg[sg_index - 1].hw->ndesc_addr = ldma_sg->llp | LDMA_DESC_EN;
+		desc->sg[sg_index - 1].hw->high_ndesc_addr = upper_32_bits(ldma_sg->llp);
+	}
+}
+
+/*--  DMA Engine API  --------------------------------------------------*/
+
+/*
+ * ls2x_dma_alloc_chan_resources - allocate resources for DMA channel
+ * @chan: allocate descriptor resources for this channel
+ *
+ * return - the number of allocated descriptors
+ */
+static int ls2x_dma_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+
+	/* Create a pool of consistent memory blocks for hardware descriptors */
+	lchan->pool = dma_pool_create(dev_name(chan2dev(chan)),
+				      chan->device->dev, PAGE_SIZE,
+				      __alignof__(struct ls2x_dma_hw_desc), 0);
+	if (!lchan->pool) {
+		dev_err(chan2dev(chan), "No memory for descriptors\n");
+		return -ENOMEM;
+	}
+
+	return 1;
+}
+
+/*
+ * ls2x_dma_free_chan_resources - free all channel resources
+ * @chan: DMA channel
+ */
+static void ls2x_dma_free_chan_resources(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+
+	vchan_free_chan_resources(to_virt_chan(chan));
+	dma_pool_destroy(lchan->pool);
+	lchan->pool = NULL;
+}
+
+/*
+ * ls2x_dma_prep_slave_sg - prepare descriptors for a DMA_SLAVE transaction
+ * @chan: DMA channel
+ * @sgl: scatterlist to transfer to/from
+ * @sg_len: number of entries in @scatterlist
+ * @direction: DMA direction
+ * @flags: tx descriptor status flags
+ * @context: transaction context (ignored)
+ *
+ * Return: Async transaction descriptor on success and NULL on failure
+ */
+static struct dma_async_tx_descriptor *
+ls2x_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
+		       u32 sg_len, enum dma_transfer_direction direction,
+		       unsigned long flags, void *context)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+	struct ls2x_dma_desc *desc;
+	struct scatterlist *sg;
+	size_t burst_size;
+	int i;
+
+	if (unlikely(!sg_len || !is_slave_direction(direction)))
+		return NULL;
+
+	burst_size = ls2x_dmac_detect_burst(lchan);
+	if (!burst_size)
+		return NULL;
+
+	desc = kzalloc(struct_size(desc, sg, sg_len), GFP_NOWAIT);
+	if (!desc)
+		return NULL;
+
+	desc->desc_num = sg_len;
+	desc->direction = direction;
+	desc->burst_size = burst_size;
+
+	for_each_sg(sgl, sg, sg_len, i) {
+		struct ls2x_dma_sg *ldma_sg = &desc->sg[i];
+
+		/* Allocate DMA capable memory for hardware descriptor */
+		ldma_sg->hw = dma_pool_alloc(lchan->pool, GFP_NOWAIT, &ldma_sg->llp);
+		if (!ldma_sg->hw) {
+			desc->desc_num = i;
+			ls2x_dma_desc_free(&desc->vdesc);
+			return NULL;
+		}
+
+		ldma_sg->phys = sg_dma_address(sg);
+		ldma_sg->len = sg_dma_len(sg);
+
+		ls2x_dma_fill_desc(lchan, i, desc);
+	}
+
+	/* Setting the last descriptor enable bit */
+	desc->sg[sg_len - 1].hw->ndesc_addr &= ~LDMA_DESC_EN;
+	desc->status = DMA_IN_PROGRESS;
+
+	return vchan_tx_prep(&lchan->vchan, &desc->vdesc, flags);
+}
+
+/*
+ * ls2x_dma_prep_dma_cyclic - prepare the cyclic DMA transfer
+ * @chan: the DMA channel to prepare
+ * @buf_addr: physical DMA address where the buffer starts
+ * @buf_len: total number of bytes for the entire buffer
+ * @period_len: number of bytes for each period
+ * @direction: transfer direction, to or from device
+ * @flags: tx descriptor status flags
+ *
+ * Return: Async transaction descriptor on success and NULL on failure
+ */
+static struct dma_async_tx_descriptor *
+ls2x_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
+			 size_t period_len, enum dma_transfer_direction direction,
+			 unsigned long flags)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+	struct ls2x_dma_desc *desc;
+	size_t burst_size;
+	u32 num_periods;
+	int i;
+
+	if (unlikely(!buf_len || !period_len))
+		return NULL;
+
+	if (unlikely(!is_slave_direction(direction)))
+		return NULL;
+
+	burst_size = ls2x_dmac_detect_burst(lchan);
+	if (!burst_size)
+		return NULL;
+
+	num_periods = buf_len / period_len;
+	desc = kzalloc(struct_size(desc, sg, num_periods), GFP_NOWAIT);
+	if (!desc)
+		return NULL;
+
+	desc->desc_num = num_periods;
+	desc->direction = direction;
+	desc->burst_size = burst_size;
+
+	/* Build cyclic linked list */
+	for (i = 0; i < num_periods; i++) {
+		struct ls2x_dma_sg *ldma_sg = &desc->sg[i];
+
+		/* Allocate DMA capable memory for hardware descriptor */
+		ldma_sg->hw = dma_pool_alloc(lchan->pool, GFP_NOWAIT, &ldma_sg->llp);
+		if (!ldma_sg->hw) {
+			desc->desc_num = i;
+			ls2x_dma_desc_free(&desc->vdesc);
+			return NULL;
+		}
+
+		ldma_sg->phys = buf_addr + period_len * i;
+		ldma_sg->len = period_len;
+
+		ls2x_dma_fill_desc(lchan, i, desc);
+	}
+
+	/* Lets make a cyclic list */
+	desc->sg[num_periods - 1].hw->ndesc_addr = desc->sg[0].llp | LDMA_DESC_EN;
+	desc->sg[num_periods - 1].hw->high_ndesc_addr = upper_32_bits(desc->sg[0].llp);
+	desc->cyclic = true;
+	desc->status = DMA_IN_PROGRESS;
+
+	return vchan_tx_prep(&lchan->vchan, &desc->vdesc, flags);
+}
+
+/*
+ * ls2x_slave_config - set slave configuration for channel
+ * @chan: dma channel
+ * @cfg: slave configuration
+ *
+ * Sets slave configuration for channel
+ */
+static int ls2x_dma_slave_config(struct dma_chan *chan,
+				 struct dma_slave_config *config)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+
+	memcpy(&lchan->sconfig, config, sizeof(*config));
+	return 0;
+}
+
+/*
+ * ls2x_dma_issue_pending - push pending transactions to the hardware
+ * @chan: channel
+ *
+ * When this function is called, all pending transactions are pushed to the
+ * hardware and executed.
+ */
+static void ls2x_dma_issue_pending(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&lchan->vchan.lock, flags);
+	if (vchan_issue_pending(&lchan->vchan) && !lchan->desc)
+		ls2x_dma_start_transfer(lchan);
+	spin_unlock_irqrestore(&lchan->vchan.lock, flags);
+}
+
+/*
+ * ls2x_dma_terminate_all - terminate all transactions
+ * @chan: channel
+ *
+ * Stops all DMA transactions.
+ */
+static int ls2x_dma_terminate_all(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&lchan->vchan.lock, flags);
+	/* Setting stop cmd */
+	ls2x_dma_write_cmd(lchan, LDMA_STOP);
+	if (lchan->desc) {
+		vchan_terminate_vdesc(&lchan->desc->vdesc);
+		lchan->desc = NULL;
+	}
+
+	vchan_get_all_descriptors(&lchan->vchan, &head);
+	spin_unlock_irqrestore(&lchan->vchan.lock, flags);
+
+	vchan_dma_desc_free_list(&lchan->vchan, &head);
+	return 0;
+}
+
+/*
+ * ls2x_dma_synchronize - Synchronizes the termination of transfers to the
+ * current context.
+ * @chan: channel
+ */
+static void ls2x_dma_synchronize(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+
+	vchan_synchronize(&lchan->vchan);
+}
+
+static int ls2x_dma_pause(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&lchan->vchan.lock, flags);
+	if (lchan->desc && lchan->desc->status == DMA_IN_PROGRESS) {
+		ls2x_dma_write_cmd(lchan, LDMA_STOP);
+		lchan->desc->status = DMA_PAUSED;
+	}
+	spin_unlock_irqrestore(&lchan->vchan.lock, flags);
+
+	return 0;
+}
+
+static int ls2x_dma_resume(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&lchan->vchan.lock, flags);
+	if (lchan->desc && lchan->desc->status == DMA_PAUSED) {
+		lchan->desc->status = DMA_IN_PROGRESS;
+		ls2x_dma_write_cmd(lchan, LDMA_START);
+	}
+	spin_unlock_irqrestore(&lchan->vchan.lock, flags);
+
+	return 0;
+}
+
+/*
+ * ls2x_dma_isr - LS2X DMA Interrupt handler
+ * @irq: IRQ number
+ * @dev_id: Pointer to ls2x_dma_chan
+ *
+ * Return: IRQ_HANDLED/IRQ_NONE
+ */
+static irqreturn_t ls2x_dma_isr(int irq, void *dev_id)
+{
+	struct ls2x_dma_chan *lchan = dev_id;
+	struct ls2x_dma_desc *desc;
+
+	spin_lock(&lchan->vchan.lock);
+	desc = lchan->desc;
+	if (desc) {
+		if (desc->cyclic) {
+			vchan_cyclic_callback(&desc->vdesc);
+		} else {
+			desc->status = DMA_COMPLETE;
+			vchan_cookie_complete(&desc->vdesc);
+			ls2x_dma_start_transfer(lchan);
+		}
+
+		/* ls2x_dma_start_transfer() updates lchan->desc */
+		if (!lchan->desc)
+			ls2x_dma_write_cmd(lchan, LDMA_STOP);
+	}
+	spin_unlock(&lchan->vchan.lock);
+
+	return IRQ_HANDLED;
+}
+
+static int ls2x_dma_chan_init(struct platform_device *pdev,
+			      struct ls2x_dma_priv *priv)
+{
+	struct ls2x_dma_chan *lchan = &priv->lchan;
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	lchan->irq = platform_get_irq(pdev, 0);
+	if (lchan->irq < 0)
+		return lchan->irq;
+
+	ret = devm_request_irq(dev, lchan->irq, ls2x_dma_isr, IRQF_TRIGGER_RISING,
+			       dev_name(&pdev->dev), lchan);
+	if (ret)
+		return ret;
+
+	/* Initialize channels related values */
+	INIT_LIST_HEAD(&priv->ddev.channels);
+	lchan->vchan.desc_free = ls2x_dma_desc_free;
+	vchan_init(&lchan->vchan, &priv->ddev);
+
+	return 0;
+}
+
+/*
+ * ls2x_dma_probe - Driver probe function
+ * @pdev: Pointer to the platform_device structure
+ *
+ * Return: '0' on success and failure value on error
+ */
+static int ls2x_dma_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct ls2x_dma_priv *priv;
+	struct dma_device *ddev;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(priv->regs))
+		return dev_err_probe(dev, PTR_ERR(priv->regs),
+				     "devm_platform_ioremap_resource failed.\n");
+
+	priv->dma_clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(priv->dma_clk))
+		return dev_err_probe(dev, PTR_ERR(priv->dma_clk), "devm_clk_get failed.\n");
+
+	ret = clk_prepare_enable(priv->dma_clk);
+	if (ret)
+		return dev_err_probe(dev, ret, "clk_prepare_enable failed.\n");
+
+	ret = ls2x_dma_chan_init(pdev, priv);
+	if (ret)
+		goto disable_clk;
+
+	ddev = &priv->ddev;
+	ddev->dev = dev;
+	dma_cap_zero(ddev->cap_mask);
+	dma_cap_set(DMA_SLAVE, ddev->cap_mask);
+	dma_cap_set(DMA_CYCLIC, ddev->cap_mask);
+
+	ddev->device_alloc_chan_resources = ls2x_dma_alloc_chan_resources;
+	ddev->device_free_chan_resources = ls2x_dma_free_chan_resources;
+	ddev->device_tx_status = dma_cookie_status;
+	ddev->device_issue_pending = ls2x_dma_issue_pending;
+	ddev->device_prep_slave_sg = ls2x_dma_prep_slave_sg;
+	ddev->device_prep_dma_cyclic = ls2x_dma_prep_dma_cyclic;
+	ddev->device_config = ls2x_dma_slave_config;
+	ddev->device_terminate_all = ls2x_dma_terminate_all;
+	ddev->device_synchronize = ls2x_dma_synchronize;
+	ddev->device_pause = ls2x_dma_pause;
+	ddev->device_resume = ls2x_dma_resume;
+
+	ddev->src_addr_widths = LDMA_SLAVE_BUSWIDTHS;
+	ddev->dst_addr_widths = LDMA_SLAVE_BUSWIDTHS;
+	ddev->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+
+	ret = dma_async_device_register(&priv->ddev);
+	if (ret < 0)
+		goto disable_clk;
+
+	ret = of_dma_controller_register(dev->of_node, of_dma_xlate_by_chan_id, priv);
+	if (ret < 0)
+		goto unregister_dmac;
+
+	platform_set_drvdata(pdev, priv);
+
+	dev_info(dev, "Loongson LS2X APB DMA driver registered successfully.\n");
+	return 0;
+
+unregister_dmac:
+	dma_async_device_unregister(&priv->ddev);
+disable_clk:
+	clk_disable_unprepare(priv->dma_clk);
+
+	return ret;
+}
+
+/*
+ * ls2x_dma_remove - Driver remove function
+ * @pdev: Pointer to the platform_device structure
+ */
+static void ls2x_dma_remove(struct platform_device *pdev)
+{
+	struct ls2x_dma_priv *priv = platform_get_drvdata(pdev);
+
+	of_dma_controller_free(pdev->dev.of_node);
+	dma_async_device_unregister(&priv->ddev);
+	clk_disable_unprepare(priv->dma_clk);
+}
+
+static const struct of_device_id ls2x_dma_of_match_table[] = {
+	{ .compatible = "loongson,ls2k1000-apbdma" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, ls2x_dma_of_match_table);
+
+static struct platform_driver ls2x_dmac_driver = {
+	.probe		= ls2x_dma_probe,
+	.remove_new	= ls2x_dma_remove,
+	.driver = {
+		.name	= "ls2x-apbdma",
+		.of_match_table	= ls2x_dma_of_match_table,
+	},
+};
+module_platform_driver(ls2x_dmac_driver);
+
+MODULE_DESCRIPTION("Loongson LS2X APB DMA Controller driver");
+MODULE_AUTHOR("Loongson Technology Corporation Limited");
+MODULE_LICENSE("GPL");
diff --git a/drivers/dma/milbeaut-hdmac.c b/drivers/dma/milbeaut-hdmac.c
index 1b0a95892627..7b41c670970a 100644
--- a/drivers/dma/milbeaut-hdmac.c
+++ b/drivers/dma/milbeaut-hdmac.c
@@ -531,7 +531,7 @@ disable_clk:
 	return ret;
 }
 
-static int milbeaut_hdmac_remove(struct platform_device *pdev)
+static void milbeaut_hdmac_remove(struct platform_device *pdev)
 {
 	struct milbeaut_hdmac_device *mdev = platform_get_drvdata(pdev);
 	struct dma_chan *chan;
@@ -546,16 +546,21 @@ static int milbeaut_hdmac_remove(struct platform_device *pdev)
 	 */
 	list_for_each_entry(chan, &mdev->ddev.channels, device_node) {
 		ret = dmaengine_terminate_sync(chan);
-		if (ret)
-			return ret;
+		if (ret) {
+			/*
+			 * This results in resource leakage and maybe also
+			 * use-after-free errors as e.g. *mdev is kfreed.
+			 */
+			dev_alert(&pdev->dev, "Failed to terminate channel %d (%pe)\n",
+				  chan->chan_id, ERR_PTR(ret));
+			return;
+		}
 		milbeaut_hdmac_free_chan_resources(chan);
 	}
 
 	of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(&mdev->ddev);
 	clk_disable_unprepare(mdev->clk);
-
-	return 0;
 }
 
 static const struct of_device_id milbeaut_hdmac_match[] = {
@@ -566,7 +571,7 @@ MODULE_DEVICE_TABLE(of, milbeaut_hdmac_match);
 
 static struct platform_driver milbeaut_hdmac_driver = {
 	.probe = milbeaut_hdmac_probe,
-	.remove = milbeaut_hdmac_remove,
+	.remove_new = milbeaut_hdmac_remove,
 	.driver = {
 		.name = "milbeaut-m10v-hdmac",
 		.of_match_table = milbeaut_hdmac_match,
diff --git a/drivers/dma/milbeaut-xdmac.c b/drivers/dma/milbeaut-xdmac.c
index d29d01e730aa..2cce529b448e 100644
--- a/drivers/dma/milbeaut-xdmac.c
+++ b/drivers/dma/milbeaut-xdmac.c
@@ -368,7 +368,7 @@ disable_xdmac:
 	return ret;
 }
 
-static int milbeaut_xdmac_remove(struct platform_device *pdev)
+static void milbeaut_xdmac_remove(struct platform_device *pdev)
 {
 	struct milbeaut_xdmac_device *mdev = platform_get_drvdata(pdev);
 	struct dma_chan *chan;
@@ -383,8 +383,15 @@ static int milbeaut_xdmac_remove(struct platform_device *pdev)
 	 */
 	list_for_each_entry(chan, &mdev->ddev.channels, device_node) {
 		ret = dmaengine_terminate_sync(chan);
-		if (ret)
-			return ret;
+		if (ret) {
+			/*
+			 * This results in resource leakage and maybe also
+			 * use-after-free errors as e.g. *mdev is kfreed.
+			 */
+			dev_alert(&pdev->dev, "Failed to terminate channel %d (%pe)\n",
+				  chan->chan_id, ERR_PTR(ret));
+			return;
+		}
 		milbeaut_xdmac_free_chan_resources(chan);
 	}
 
@@ -392,8 +399,6 @@ static int milbeaut_xdmac_remove(struct platform_device *pdev)
 	dma_async_device_unregister(&mdev->ddev);
 
 	disable_xdmac(mdev);
-
-	return 0;
 }
 
 static const struct of_device_id milbeaut_xdmac_match[] = {
@@ -404,7 +409,7 @@ MODULE_DEVICE_TABLE(of, milbeaut_xdmac_match);
 
 static struct platform_driver milbeaut_xdmac_driver = {
 	.probe = milbeaut_xdmac_probe,
-	.remove = milbeaut_xdmac_remove,
+	.remove_new = milbeaut_xdmac_remove,
 	.driver = {
 		.name = "milbeaut-m10v-xdmac",
 		.of_match_table = milbeaut_xdmac_match,
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 3cf0b38387ae..c29744bfdf2c 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -1053,6 +1053,9 @@ static bool _trigger(struct pl330_thread *thrd)
 
 	thrd->req_running = idx;
 
+	if (desc->rqtype == DMA_MEM_TO_DEV || desc->rqtype == DMA_DEV_TO_MEM)
+		UNTIL(thrd, PL330_STATE_WFP);
+
 	return true;
 }
 
diff --git a/drivers/dma/ptdma/ptdma-dmaengine.c b/drivers/dma/ptdma/ptdma-dmaengine.c
index 1aa65e5de0f3..f79240734807 100644
--- a/drivers/dma/ptdma/ptdma-dmaengine.c
+++ b/drivers/dma/ptdma/ptdma-dmaengine.c
@@ -385,8 +385,6 @@ int pt_dmaengine_register(struct pt_device *pt)
 	chan->vc.desc_free = pt_do_cleanup;
 	vchan_init(&chan->vc, dma_dev);
 
-	dma_set_mask_and_coherent(pt->dev, DMA_BIT_MASK(64));
-
 	ret = dma_async_device_register(dma_dev);
 	if (ret)
 		goto err_reg;
diff --git a/drivers/dma/sf-pdma/sf-pdma.c b/drivers/dma/sf-pdma/sf-pdma.c
index 3125a2f162b4..428473611115 100644
--- a/drivers/dma/sf-pdma/sf-pdma.c
+++ b/drivers/dma/sf-pdma/sf-pdma.c
@@ -20,10 +20,13 @@
 #include <linux/mod_devicetable.h>
 #include <linux/dma-mapping.h>
 #include <linux/of.h>
+#include <linux/of_dma.h>
 #include <linux/slab.h>
 
 #include "sf-pdma.h"
 
+#define PDMA_QUIRK_NO_STRICT_ORDERING   BIT(0)
+
 #ifndef readq
 static inline unsigned long long readq(void __iomem *addr)
 {
@@ -65,7 +68,7 @@ static struct sf_pdma_desc *sf_pdma_alloc_desc(struct sf_pdma_chan *chan)
 static void sf_pdma_fill_desc(struct sf_pdma_desc *desc,
 			      u64 dst, u64 src, u64 size)
 {
-	desc->xfer_type = PDMA_FULL_SPEED;
+	desc->xfer_type =  desc->chan->pdma->transfer_type;
 	desc->xfer_size = size;
 	desc->dst_addr = dst;
 	desc->src_addr = src;
@@ -492,6 +495,7 @@ static void sf_pdma_setup_chans(struct sf_pdma *pdma)
 
 static int sf_pdma_probe(struct platform_device *pdev)
 {
+	const struct sf_pdma_driver_platdata *ddata;
 	struct sf_pdma *pdma;
 	int ret, n_chans;
 	const enum dma_slave_buswidth widths =
@@ -517,6 +521,14 @@ static int sf_pdma_probe(struct platform_device *pdev)
 
 	pdma->n_chans = n_chans;
 
+	pdma->transfer_type = PDMA_FULL_SPEED | PDMA_STRICT_ORDERING;
+
+	ddata  = device_get_match_data(&pdev->dev);
+	if (ddata) {
+		if (ddata->quirks & PDMA_QUIRK_NO_STRICT_ORDERING)
+			pdma->transfer_type &= ~PDMA_STRICT_ORDERING;
+	}
+
 	pdma->membase = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(pdma->membase))
 		return PTR_ERR(pdma->membase);
@@ -563,7 +575,20 @@ static int sf_pdma_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	ret = of_dma_controller_register(pdev->dev.of_node,
+					 of_dma_xlate_by_chan_id, pdma);
+	if (ret < 0) {
+		dev_err(&pdev->dev,
+			"Can't register SiFive Platform OF_DMA. (%d)\n", ret);
+		goto err_unregister;
+	}
+
 	return 0;
+
+err_unregister:
+	dma_async_device_unregister(&pdma->dma_dev);
+
+	return ret;
 }
 
 static void sf_pdma_remove(struct platform_device *pdev)
@@ -583,12 +608,25 @@ static void sf_pdma_remove(struct platform_device *pdev)
 		tasklet_kill(&ch->err_tasklet);
 	}
 
+	if (pdev->dev.of_node)
+		of_dma_controller_free(pdev->dev.of_node);
+
 	dma_async_device_unregister(&pdma->dma_dev);
 }
 
+static const struct sf_pdma_driver_platdata mpfs_pdma = {
+	.quirks = PDMA_QUIRK_NO_STRICT_ORDERING,
+};
+
 static const struct of_device_id sf_pdma_dt_ids[] = {
-	{ .compatible = "sifive,fu540-c000-pdma" },
-	{ .compatible = "sifive,pdma0" },
+	{
+		.compatible = "sifive,fu540-c000-pdma",
+	}, {
+		.compatible = "sifive,pdma0",
+	}, {
+		.compatible = "microchip,mpfs-pdma",
+		.data	    = &mpfs_pdma,
+	},
 	{},
 };
 MODULE_DEVICE_TABLE(of, sf_pdma_dt_ids);
diff --git a/drivers/dma/sf-pdma/sf-pdma.h b/drivers/dma/sf-pdma/sf-pdma.h
index d05772b5d8d3..215e07183d7e 100644
--- a/drivers/dma/sf-pdma/sf-pdma.h
+++ b/drivers/dma/sf-pdma/sf-pdma.h
@@ -48,7 +48,8 @@
 #define PDMA_ERR_STATUS_MASK				GENMASK(31, 31)
 
 /* Transfer Type */
-#define PDMA_FULL_SPEED					0xFF000008
+#define PDMA_FULL_SPEED					0xFF000000
+#define PDMA_STRICT_ORDERING				BIT(3)
 
 /* Error Recovery */
 #define MAX_RETRY					1
@@ -112,8 +113,13 @@ struct sf_pdma {
 	struct dma_device       dma_dev;
 	void __iomem            *membase;
 	void __iomem            *mappedbase;
+	u32			transfer_type;
 	u32			n_chans;
 	struct sf_pdma_chan	chans[] __counted_by(n_chans);
 };
 
+struct sf_pdma_driver_platdata {
+	u32 quirks;
+};
+
 #endif /* _SF_PDMA_H */
diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c
index fea5bda34bc2..1f1e86ba5c66 100644
--- a/drivers/dma/sh/rz-dmac.c
+++ b/drivers/dma/sh/rz-dmac.c
@@ -755,11 +755,11 @@ static struct dma_chan *rz_dmac_of_xlate(struct of_phandle_args *dma_spec,
 
 static int rz_dmac_chan_probe(struct rz_dmac *dmac,
 			      struct rz_dmac_chan *channel,
-			      unsigned int index)
+			      u8 index)
 {
 	struct platform_device *pdev = to_platform_device(dmac->dev);
 	struct rz_lmdesc *lmdesc;
-	char pdev_irqname[5];
+	char pdev_irqname[6];
 	char *irqname;
 	int ret;
 
@@ -767,7 +767,7 @@ static int rz_dmac_chan_probe(struct rz_dmac *dmac,
 	channel->mid_rid = -EINVAL;
 
 	/* Request the channel interrupt. */
-	sprintf(pdev_irqname, "ch%u", index);
+	scnprintf(pdev_irqname, sizeof(pdev_irqname), "ch%u", index);
 	channel->irq = platform_get_irq_byname(pdev, pdev_irqname);
 	if (channel->irq < 0)
 		return channel->irq;
@@ -845,9 +845,9 @@ static int rz_dmac_probe(struct platform_device *pdev)
 	struct dma_device *engine;
 	struct rz_dmac *dmac;
 	int channel_num;
-	unsigned int i;
 	int ret;
 	int irq;
+	u8 i;
 
 	dmac = devm_kzalloc(&pdev->dev, sizeof(*dmac), GFP_KERNEL);
 	if (!dmac)
diff --git a/drivers/dma/sh/shdma.h b/drivers/dma/sh/shdma.h
index 9c121a4b33ad..f97d80343aea 100644
--- a/drivers/dma/sh/shdma.h
+++ b/drivers/dma/sh/shdma.h
@@ -25,7 +25,7 @@ struct sh_dmae_chan {
 	const struct sh_dmae_slave_config *config; /* Slave DMA configuration */
 	int xmit_shift;			/* log_2(bytes_per_xfer) */
 	void __iomem *base;
-	char dev_id[16];		/* unique name per DMAC of channel */
+	char dev_id[32];		/* unique name per DMAC of channel */
 	int pm_error;
 	dma_addr_t slave_addr;
 };
diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c
index a9b4302f6050..f7cd0cad056c 100644
--- a/drivers/dma/sh/usb-dmac.c
+++ b/drivers/dma/sh/usb-dmac.c
@@ -706,10 +706,10 @@ static const struct dev_pm_ops usb_dmac_pm = {
 
 static int usb_dmac_chan_probe(struct usb_dmac *dmac,
 			       struct usb_dmac_chan *uchan,
-			       unsigned int index)
+			       u8 index)
 {
 	struct platform_device *pdev = to_platform_device(dmac->dev);
-	char pdev_irqname[5];
+	char pdev_irqname[6];
 	char *irqname;
 	int ret;
 
@@ -717,7 +717,7 @@ static int usb_dmac_chan_probe(struct usb_dmac *dmac,
 	uchan->iomem = dmac->iomem + USB_DMAC_CHAN_OFFSET(index);
 
 	/* Request the channel interrupt. */
-	sprintf(pdev_irqname, "ch%u", index);
+	scnprintf(pdev_irqname, sizeof(pdev_irqname), "ch%u", index);
 	uchan->irq = platform_get_irq_byname(pdev, pdev_irqname);
 	if (uchan->irq < 0)
 		return -ENODEV;
@@ -768,8 +768,8 @@ static int usb_dmac_probe(struct platform_device *pdev)
 	const enum dma_slave_buswidth widths = USB_DMAC_SLAVE_BUSWIDTH;
 	struct dma_device *engine;
 	struct usb_dmac *dmac;
-	unsigned int i;
 	int ret;
+	u8 i;
 
 	dmac = devm_kzalloc(&pdev->dev, sizeof(*dmac), GFP_KERNEL);
 	if (!dmac)
@@ -869,7 +869,7 @@ static void usb_dmac_chan_remove(struct usb_dmac *dmac,
 static void usb_dmac_remove(struct platform_device *pdev)
 {
 	struct usb_dmac *dmac = platform_get_drvdata(pdev);
-	int i;
+	u8 i;
 
 	for (i = 0; i < dmac->n_channels; ++i)
 		usb_dmac_chan_remove(dmac, &dmac->channels[i]);
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 002833fb1fa0..2c489299148e 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -31,13 +31,11 @@
 /**
  * struct stedma40_platform_data - Configuration struct for the dma device.
  *
- * @dev_tx: mapping between destination event line and io address
- * @dev_rx: mapping between source event line and io address
  * @disabled_channels: A vector, ending with -1, that marks physical channels
  * that are for different reasons not available for the driver.
  * @soft_lli_chans: A vector, that marks physical channels will use LLI by SW
  * which avoids HW bug that exists in some versions of the controller.
- * SoftLLI introduces relink overhead that could impact performace for
+ * SoftLLI introduces relink overhead that could impact performance for
  * certain use cases.
  * @num_of_soft_lli_chans: The number of channels that needs to be configured
  * to use SoftLLI.
@@ -184,7 +182,7 @@ static __maybe_unused u32 d40_backup_regs[] = {
 
 /*
  * since 9540 and 8540 has the same HW revision
- * use v4a for 9540 or ealier
+ * use v4a for 9540 or earlier
  * use v4b for 8540 or later
  * HW revision:
  * DB8500ed has revision 0
@@ -411,7 +409,7 @@ struct d40_desc {
  *
  * @base: The virtual address of LCLA. 18 bit aligned.
  * @dma_addr: DMA address, if mapped
- * @base_unaligned: The orignal kmalloc pointer, if kmalloc is used.
+ * @base_unaligned: The original kmalloc pointer, if kmalloc is used.
  * This pointer is only there for clean-up on error.
  * @pages: The number of pages needed for all physical channels.
  * Only used later for clean-up on error
@@ -1655,7 +1653,7 @@ static void dma_tasklet(struct tasklet_struct *t)
 
 	return;
  check_pending_tx:
-	/* Rescue manouver if receiving double interrupts */
+	/* Rescue maneuver if receiving double interrupts */
 	if (d40c->pending_tx > 0)
 		d40c->pending_tx--;
 	spin_unlock_irqrestore(&d40c->lock, flags);
@@ -3412,7 +3410,7 @@ static int __init d40_lcla_allocate(struct d40_base *base)
 		base->lcla_pool.base = (void *)page_list[i];
 	} else {
 		/*
-		 * After many attempts and no succees with finding the correct
+		 * After many attempts and no success with finding the correct
 		 * alignment, try with allocating a big buffer.
 		 */
 		dev_warn(base->dev,
diff --git a/drivers/dma/tegra186-gpc-dma.c b/drivers/dma/tegra186-gpc-dma.c
index fa4d4142a68a..88547a23825b 100644
--- a/drivers/dma/tegra186-gpc-dma.c
+++ b/drivers/dma/tegra186-gpc-dma.c
@@ -1348,8 +1348,8 @@ static int tegra_dma_program_sid(struct tegra_dma_channel *tdc, int stream_id)
 static int tegra_dma_probe(struct platform_device *pdev)
 {
 	const struct tegra_dma_chip_data *cdata = NULL;
-	struct iommu_fwspec *iommu_spec;
-	unsigned int stream_id, i;
+	unsigned int i;
+	u32 stream_id;
 	struct tegra_dma *tdma;
 	int ret;
 
@@ -1378,12 +1378,10 @@ static int tegra_dma_probe(struct platform_device *pdev)
 
 	tdma->dma_dev.dev = &pdev->dev;
 
-	iommu_spec = dev_iommu_fwspec_get(&pdev->dev);
-	if (!iommu_spec) {
+	if (!tegra_dev_iommu_get_stream_id(&pdev->dev, &stream_id)) {
 		dev_err(&pdev->dev, "Missing iommu stream-id\n");
 		return -EINVAL;
 	}
-	stream_id = iommu_spec->ids[0] & 0xffff;
 
 	ret = device_property_read_u32(&pdev->dev, "dma-channel-mask",
 				       &tdma->chan_mask);
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index 7a0586633bf3..24ad7077c53b 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -153,6 +153,7 @@ struct tegra_adma {
 	void __iomem			*base_addr;
 	struct clk			*ahub_clk;
 	unsigned int			nr_channels;
+	unsigned long			*dma_chan_mask;
 	unsigned long			rx_requests_reserved;
 	unsigned long			tx_requests_reserved;
 
@@ -741,6 +742,10 @@ static int __maybe_unused tegra_adma_runtime_suspend(struct device *dev)
 
 	for (i = 0; i < tdma->nr_channels; i++) {
 		tdc = &tdma->channels[i];
+		/* skip for reserved channels */
+		if (!tdc->tdma)
+			continue;
+
 		ch_reg = &tdc->ch_regs;
 		ch_reg->cmd = tdma_ch_read(tdc, ADMA_CH_CMD);
 		/* skip if channel is not active */
@@ -779,6 +784,9 @@ static int __maybe_unused tegra_adma_runtime_resume(struct device *dev)
 
 	for (i = 0; i < tdma->nr_channels; i++) {
 		tdc = &tdma->channels[i];
+		/* skip for reserved channels */
+		if (!tdc->tdma)
+			continue;
 		ch_reg = &tdc->ch_regs;
 		/* skip if channel was not active earlier */
 		if (!ch_reg->cmd)
@@ -867,10 +875,31 @@ static int tegra_adma_probe(struct platform_device *pdev)
 		return PTR_ERR(tdma->ahub_clk);
 	}
 
+	tdma->dma_chan_mask = devm_kzalloc(&pdev->dev,
+					   BITS_TO_LONGS(tdma->nr_channels) * sizeof(unsigned long),
+					   GFP_KERNEL);
+	if (!tdma->dma_chan_mask)
+		return -ENOMEM;
+
+	/* Enable all channels by default */
+	bitmap_fill(tdma->dma_chan_mask, tdma->nr_channels);
+
+	ret = of_property_read_u32_array(pdev->dev.of_node, "dma-channel-mask",
+					 (u32 *)tdma->dma_chan_mask,
+					 BITS_TO_U32(tdma->nr_channels));
+	if (ret < 0 && (ret != -EINVAL)) {
+		dev_err(&pdev->dev, "dma-channel-mask is not complete.\n");
+		return ret;
+	}
+
 	INIT_LIST_HEAD(&tdma->dma_dev.channels);
 	for (i = 0; i < tdma->nr_channels; i++) {
 		struct tegra_adma_chan *tdc = &tdma->channels[i];
 
+		/* skip for reserved channels */
+		if (!test_bit(i, tdma->dma_chan_mask))
+			continue;
+
 		tdc->chan_addr = tdma->base_addr + cdata->ch_base_offset
 				 + (cdata->ch_reg_size * i);
 
@@ -957,8 +986,10 @@ static void tegra_adma_remove(struct platform_device *pdev)
 	of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(&tdma->dma_dev);
 
-	for (i = 0; i < tdma->nr_channels; ++i)
-		irq_dispose_mapping(tdma->channels[i].irq);
+	for (i = 0; i < tdma->nr_channels; ++i) {
+		if (tdma->channels[i].irq)
+			irq_dispose_mapping(tdma->channels[i].irq);
+	}
 
 	pm_runtime_disable(&pdev->dev);
 }
diff --git a/drivers/dma/ti/Makefile b/drivers/dma/ti/Makefile
index acc950bf609c..d376c117cecf 100644
--- a/drivers/dma/ti/Makefile
+++ b/drivers/dma/ti/Makefile
@@ -12,6 +12,7 @@ k3-psil-lib-objs := k3-psil.o \
 		    k3-psil-j721s2.o \
 		    k3-psil-am62.o \
 		    k3-psil-am62a.o \
-		    k3-psil-j784s4.o
+		    k3-psil-j784s4.o \
+		    k3-psil-am62p.o
 obj-$(CONFIG_TI_K3_PSIL) += k3-psil-lib.o
 obj-$(CONFIG_TI_DMA_CROSSBAR) += dma-crossbar.o
diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c
index f1f920861fa9..5f8d2e93ff3f 100644
--- a/drivers/dma/ti/edma.c
+++ b/drivers/dma/ti/edma.c
@@ -2404,6 +2404,11 @@ static int edma_probe(struct platform_device *pdev)
 	if (irq > 0) {
 		irq_name = devm_kasprintf(dev, GFP_KERNEL, "%s_ccint",
 					  dev_name(dev));
+		if (!irq_name) {
+			ret = -ENOMEM;
+			goto err_disable_pm;
+		}
+
 		ret = devm_request_irq(dev, irq, dma_irq_handler, 0, irq_name,
 				       ecc);
 		if (ret) {
@@ -2420,6 +2425,11 @@ static int edma_probe(struct platform_device *pdev)
 	if (irq > 0) {
 		irq_name = devm_kasprintf(dev, GFP_KERNEL, "%s_ccerrint",
 					  dev_name(dev));
+		if (!irq_name) {
+			ret = -ENOMEM;
+			goto err_disable_pm;
+		}
+
 		ret = devm_request_irq(dev, irq, dma_ccerr_handler, 0, irq_name,
 				       ecc);
 		if (ret) {
diff --git a/drivers/dma/ti/k3-psil-am62p.c b/drivers/dma/ti/k3-psil-am62p.c
new file mode 100644
index 000000000000..0f338e16d971
--- /dev/null
+++ b/drivers/dma/ti/k3-psil-am62p.c
@@ -0,0 +1,325 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com
+ */
+
+#include <linux/kernel.h>
+
+#include "k3-psil-priv.h"
+
+#define PSIL_PDMA_XY_TR(x)					\
+	{							\
+		.thread_id = x,					\
+		.ep_config = {					\
+			.ep_type = PSIL_EP_PDMA_XY,		\
+			.mapped_channel_id = -1,		\
+			.default_flow_id = -1,			\
+		},						\
+	}
+
+#define PSIL_PDMA_XY_PKT(x)					\
+	{							\
+		.thread_id = x,					\
+		.ep_config = {					\
+			.ep_type = PSIL_EP_PDMA_XY,		\
+			.mapped_channel_id = -1,		\
+			.default_flow_id = -1,			\
+			.pkt_mode = 1,				\
+		},						\
+	}
+
+#define PSIL_ETHERNET(x, ch, flow_base, flow_cnt)		\
+	{							\
+		.thread_id = x,					\
+		.ep_config = {					\
+			.ep_type = PSIL_EP_NATIVE,		\
+			.pkt_mode = 1,				\
+			.needs_epib = 1,			\
+			.psd_size = 16,				\
+			.mapped_channel_id = ch,		\
+			.flow_start = flow_base,		\
+			.flow_num = flow_cnt,			\
+			.default_flow_id = flow_base,		\
+		},						\
+	}
+
+#define PSIL_SAUL(x, ch, flow_base, flow_cnt, default_flow, tx)	\
+	{							\
+		.thread_id = x,					\
+		.ep_config = {					\
+			.ep_type = PSIL_EP_NATIVE,		\
+			.pkt_mode = 1,				\
+			.needs_epib = 1,			\
+			.psd_size = 64,				\
+			.mapped_channel_id = ch,		\
+			.flow_start = flow_base,		\
+			.flow_num = flow_cnt,			\
+			.default_flow_id = default_flow,	\
+			.notdpkt = tx,				\
+		},						\
+	}
+
+#define PSIL_PDMA_MCASP(x)				\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_PDMA_XY,	\
+			.pdma_acc32 = 1,		\
+			.pdma_burst = 1,		\
+		},					\
+	}
+
+#define PSIL_CSI2RX(x)					\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_NATIVE,	\
+		},					\
+	}
+
+/* PSI-L source thread IDs, used for RX (DMA_DEV_TO_MEM) */
+static struct psil_ep am62p_src_ep_map[] = {
+	/* SAUL */
+	PSIL_SAUL(0x7504, 20, 35, 8, 35, 0),
+	PSIL_SAUL(0x7505, 21, 35, 8, 36, 0),
+	PSIL_SAUL(0x7506, 22, 43, 8, 43, 0),
+	PSIL_SAUL(0x7507, 23, 43, 8, 44, 0),
+	/* PDMA_MAIN0 - SPI0-2 */
+	PSIL_PDMA_XY_PKT(0x4300),
+	PSIL_PDMA_XY_PKT(0x4301),
+	PSIL_PDMA_XY_PKT(0x4302),
+	PSIL_PDMA_XY_PKT(0x4303),
+	PSIL_PDMA_XY_PKT(0x4304),
+	PSIL_PDMA_XY_PKT(0x4305),
+	PSIL_PDMA_XY_PKT(0x4306),
+	PSIL_PDMA_XY_PKT(0x4307),
+	PSIL_PDMA_XY_PKT(0x4308),
+	PSIL_PDMA_XY_PKT(0x4309),
+	PSIL_PDMA_XY_PKT(0x430a),
+	PSIL_PDMA_XY_PKT(0x430b),
+	/* PDMA_MAIN1 - UART0-6 */
+	PSIL_PDMA_XY_PKT(0x4400),
+	PSIL_PDMA_XY_PKT(0x4401),
+	PSIL_PDMA_XY_PKT(0x4402),
+	PSIL_PDMA_XY_PKT(0x4403),
+	PSIL_PDMA_XY_PKT(0x4404),
+	PSIL_PDMA_XY_PKT(0x4405),
+	PSIL_PDMA_XY_PKT(0x4406),
+	/* PDMA_MAIN2 - MCASP0-2 */
+	PSIL_PDMA_MCASP(0x4500),
+	PSIL_PDMA_MCASP(0x4501),
+	PSIL_PDMA_MCASP(0x4502),
+	/* CPSW3G */
+	PSIL_ETHERNET(0x4600, 19, 19, 16),
+	/* CSI2RX */
+	PSIL_CSI2RX(0x5000),
+	PSIL_CSI2RX(0x5001),
+	PSIL_CSI2RX(0x5002),
+	PSIL_CSI2RX(0x5003),
+	PSIL_CSI2RX(0x5004),
+	PSIL_CSI2RX(0x5005),
+	PSIL_CSI2RX(0x5006),
+	PSIL_CSI2RX(0x5007),
+	PSIL_CSI2RX(0x5008),
+	PSIL_CSI2RX(0x5009),
+	PSIL_CSI2RX(0x500a),
+	PSIL_CSI2RX(0x500b),
+	PSIL_CSI2RX(0x500c),
+	PSIL_CSI2RX(0x500d),
+	PSIL_CSI2RX(0x500e),
+	PSIL_CSI2RX(0x500f),
+	PSIL_CSI2RX(0x5010),
+	PSIL_CSI2RX(0x5011),
+	PSIL_CSI2RX(0x5012),
+	PSIL_CSI2RX(0x5013),
+	PSIL_CSI2RX(0x5014),
+	PSIL_CSI2RX(0x5015),
+	PSIL_CSI2RX(0x5016),
+	PSIL_CSI2RX(0x5017),
+	PSIL_CSI2RX(0x5018),
+	PSIL_CSI2RX(0x5019),
+	PSIL_CSI2RX(0x501a),
+	PSIL_CSI2RX(0x501b),
+	PSIL_CSI2RX(0x501c),
+	PSIL_CSI2RX(0x501d),
+	PSIL_CSI2RX(0x501e),
+	PSIL_CSI2RX(0x501f),
+	PSIL_CSI2RX(0x5000),
+	PSIL_CSI2RX(0x5001),
+	PSIL_CSI2RX(0x5002),
+	PSIL_CSI2RX(0x5003),
+	PSIL_CSI2RX(0x5004),
+	PSIL_CSI2RX(0x5005),
+	PSIL_CSI2RX(0x5006),
+	PSIL_CSI2RX(0x5007),
+	PSIL_CSI2RX(0x5008),
+	PSIL_CSI2RX(0x5009),
+	PSIL_CSI2RX(0x500a),
+	PSIL_CSI2RX(0x500b),
+	PSIL_CSI2RX(0x500c),
+	PSIL_CSI2RX(0x500d),
+	PSIL_CSI2RX(0x500e),
+	PSIL_CSI2RX(0x500f),
+	PSIL_CSI2RX(0x5010),
+	PSIL_CSI2RX(0x5011),
+	PSIL_CSI2RX(0x5012),
+	PSIL_CSI2RX(0x5013),
+	PSIL_CSI2RX(0x5014),
+	PSIL_CSI2RX(0x5015),
+	PSIL_CSI2RX(0x5016),
+	PSIL_CSI2RX(0x5017),
+	PSIL_CSI2RX(0x5018),
+	PSIL_CSI2RX(0x5019),
+	PSIL_CSI2RX(0x501a),
+	PSIL_CSI2RX(0x501b),
+	PSIL_CSI2RX(0x501c),
+	PSIL_CSI2RX(0x501d),
+	PSIL_CSI2RX(0x501e),
+	PSIL_CSI2RX(0x501f),
+	/* CSIRX 1-3 (only for J722S) */
+	PSIL_CSI2RX(0x5100),
+	PSIL_CSI2RX(0x5101),
+	PSIL_CSI2RX(0x5102),
+	PSIL_CSI2RX(0x5103),
+	PSIL_CSI2RX(0x5104),
+	PSIL_CSI2RX(0x5105),
+	PSIL_CSI2RX(0x5106),
+	PSIL_CSI2RX(0x5107),
+	PSIL_CSI2RX(0x5108),
+	PSIL_CSI2RX(0x5109),
+	PSIL_CSI2RX(0x510a),
+	PSIL_CSI2RX(0x510b),
+	PSIL_CSI2RX(0x510c),
+	PSIL_CSI2RX(0x510d),
+	PSIL_CSI2RX(0x510e),
+	PSIL_CSI2RX(0x510f),
+	PSIL_CSI2RX(0x5110),
+	PSIL_CSI2RX(0x5111),
+	PSIL_CSI2RX(0x5112),
+	PSIL_CSI2RX(0x5113),
+	PSIL_CSI2RX(0x5114),
+	PSIL_CSI2RX(0x5115),
+	PSIL_CSI2RX(0x5116),
+	PSIL_CSI2RX(0x5117),
+	PSIL_CSI2RX(0x5118),
+	PSIL_CSI2RX(0x5119),
+	PSIL_CSI2RX(0x511a),
+	PSIL_CSI2RX(0x511b),
+	PSIL_CSI2RX(0x511c),
+	PSIL_CSI2RX(0x511d),
+	PSIL_CSI2RX(0x511e),
+	PSIL_CSI2RX(0x511f),
+	PSIL_CSI2RX(0x5200),
+	PSIL_CSI2RX(0x5201),
+	PSIL_CSI2RX(0x5202),
+	PSIL_CSI2RX(0x5203),
+	PSIL_CSI2RX(0x5204),
+	PSIL_CSI2RX(0x5205),
+	PSIL_CSI2RX(0x5206),
+	PSIL_CSI2RX(0x5207),
+	PSIL_CSI2RX(0x5208),
+	PSIL_CSI2RX(0x5209),
+	PSIL_CSI2RX(0x520a),
+	PSIL_CSI2RX(0x520b),
+	PSIL_CSI2RX(0x520c),
+	PSIL_CSI2RX(0x520d),
+	PSIL_CSI2RX(0x520e),
+	PSIL_CSI2RX(0x520f),
+	PSIL_CSI2RX(0x5210),
+	PSIL_CSI2RX(0x5211),
+	PSIL_CSI2RX(0x5212),
+	PSIL_CSI2RX(0x5213),
+	PSIL_CSI2RX(0x5214),
+	PSIL_CSI2RX(0x5215),
+	PSIL_CSI2RX(0x5216),
+	PSIL_CSI2RX(0x5217),
+	PSIL_CSI2RX(0x5218),
+	PSIL_CSI2RX(0x5219),
+	PSIL_CSI2RX(0x521a),
+	PSIL_CSI2RX(0x521b),
+	PSIL_CSI2RX(0x521c),
+	PSIL_CSI2RX(0x521d),
+	PSIL_CSI2RX(0x521e),
+	PSIL_CSI2RX(0x521f),
+	PSIL_CSI2RX(0x5300),
+	PSIL_CSI2RX(0x5301),
+	PSIL_CSI2RX(0x5302),
+	PSIL_CSI2RX(0x5303),
+	PSIL_CSI2RX(0x5304),
+	PSIL_CSI2RX(0x5305),
+	PSIL_CSI2RX(0x5306),
+	PSIL_CSI2RX(0x5307),
+	PSIL_CSI2RX(0x5308),
+	PSIL_CSI2RX(0x5309),
+	PSIL_CSI2RX(0x530a),
+	PSIL_CSI2RX(0x530b),
+	PSIL_CSI2RX(0x530c),
+	PSIL_CSI2RX(0x530d),
+	PSIL_CSI2RX(0x530e),
+	PSIL_CSI2RX(0x530f),
+	PSIL_CSI2RX(0x5310),
+	PSIL_CSI2RX(0x5311),
+	PSIL_CSI2RX(0x5312),
+	PSIL_CSI2RX(0x5313),
+	PSIL_CSI2RX(0x5314),
+	PSIL_CSI2RX(0x5315),
+	PSIL_CSI2RX(0x5316),
+	PSIL_CSI2RX(0x5317),
+	PSIL_CSI2RX(0x5318),
+	PSIL_CSI2RX(0x5319),
+	PSIL_CSI2RX(0x531a),
+	PSIL_CSI2RX(0x531b),
+	PSIL_CSI2RX(0x531c),
+	PSIL_CSI2RX(0x531d),
+	PSIL_CSI2RX(0x531e),
+	PSIL_CSI2RX(0x531f),
+};
+
+/* PSI-L destination thread IDs, used for TX (DMA_MEM_TO_DEV) */
+static struct psil_ep am62p_dst_ep_map[] = {
+	/* SAUL */
+	PSIL_SAUL(0xf500, 27, 83, 8, 83, 1),
+	PSIL_SAUL(0xf501, 28, 91, 8, 91, 1),
+	/* PDMA_MAIN0 - SPI0-2 */
+	PSIL_PDMA_XY_PKT(0xc300),
+	PSIL_PDMA_XY_PKT(0xc301),
+	PSIL_PDMA_XY_PKT(0xc302),
+	PSIL_PDMA_XY_PKT(0xc303),
+	PSIL_PDMA_XY_PKT(0xc304),
+	PSIL_PDMA_XY_PKT(0xc305),
+	PSIL_PDMA_XY_PKT(0xc306),
+	PSIL_PDMA_XY_PKT(0xc307),
+	PSIL_PDMA_XY_PKT(0xc308),
+	PSIL_PDMA_XY_PKT(0xc309),
+	PSIL_PDMA_XY_PKT(0xc30a),
+	PSIL_PDMA_XY_PKT(0xc30b),
+	/* PDMA_MAIN1 - UART0-6 */
+	PSIL_PDMA_XY_PKT(0xc400),
+	PSIL_PDMA_XY_PKT(0xc401),
+	PSIL_PDMA_XY_PKT(0xc402),
+	PSIL_PDMA_XY_PKT(0xc403),
+	PSIL_PDMA_XY_PKT(0xc404),
+	PSIL_PDMA_XY_PKT(0xc405),
+	PSIL_PDMA_XY_PKT(0xc406),
+	/* PDMA_MAIN2 - MCASP0-2 */
+	PSIL_PDMA_MCASP(0xc500),
+	PSIL_PDMA_MCASP(0xc501),
+	PSIL_PDMA_MCASP(0xc502),
+	/* CPSW3G */
+	PSIL_ETHERNET(0xc600, 19, 19, 8),
+	PSIL_ETHERNET(0xc601, 20, 27, 8),
+	PSIL_ETHERNET(0xc602, 21, 35, 8),
+	PSIL_ETHERNET(0xc603, 22, 43, 8),
+	PSIL_ETHERNET(0xc604, 23, 51, 8),
+	PSIL_ETHERNET(0xc605, 24, 59, 8),
+	PSIL_ETHERNET(0xc606, 25, 67, 8),
+	PSIL_ETHERNET(0xc607, 26, 75, 8),
+};
+
+struct psil_ep_map am62p_ep_map = {
+	.name = "am62p",
+	.src = am62p_src_ep_map,
+	.src_count = ARRAY_SIZE(am62p_src_ep_map),
+	.dst = am62p_dst_ep_map,
+	.dst_count = ARRAY_SIZE(am62p_dst_ep_map),
+};
diff --git a/drivers/dma/ti/k3-psil-priv.h b/drivers/dma/ti/k3-psil-priv.h
index c383723d1c8f..a577be97e344 100644
--- a/drivers/dma/ti/k3-psil-priv.h
+++ b/drivers/dma/ti/k3-psil-priv.h
@@ -45,5 +45,6 @@ extern struct psil_ep_map j721s2_ep_map;
 extern struct psil_ep_map am62_ep_map;
 extern struct psil_ep_map am62a_ep_map;
 extern struct psil_ep_map j784s4_ep_map;
+extern struct psil_ep_map am62p_ep_map;
 
 #endif /* K3_PSIL_PRIV_H_ */
diff --git a/drivers/dma/ti/k3-psil.c b/drivers/dma/ti/k3-psil.c
index c11389d67a3f..25148d952472 100644
--- a/drivers/dma/ti/k3-psil.c
+++ b/drivers/dma/ti/k3-psil.c
@@ -26,6 +26,8 @@ static const struct soc_device_attribute k3_soc_devices[] = {
 	{ .family = "AM62X", .data = &am62_ep_map },
 	{ .family = "AM62AX", .data = &am62a_ep_map },
 	{ .family = "J784S4", .data = &j784s4_ep_map },
+	{ .family = "AM62PX", .data = &am62p_ep_map },
+	{ .family = "J722S", .data = &am62p_ep_map },
 	{ /* sentinel */ }
 };
 
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index 30fd2f386f36..6400d06588a2 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -3968,6 +3968,7 @@ static void udma_desc_pre_callback(struct virt_dma_chan *vc,
 {
 	struct udma_chan *uc = to_udma_chan(&vc->chan);
 	struct udma_desc *d;
+	u8 status;
 
 	if (!vd)
 		return;
@@ -3977,12 +3978,12 @@ static void udma_desc_pre_callback(struct virt_dma_chan *vc,
 	if (d->metadata_size)
 		udma_fetch_epib(uc, d);
 
-	/* Provide residue information for the client */
 	if (result) {
 		void *desc_vaddr = udma_curr_cppi5_desc_vaddr(d, d->desc_idx);
 
 		if (cppi5_desc_get_type(desc_vaddr) ==
 		    CPPI5_INFO0_DESC_TYPE_VAL_HOST) {
+			/* Provide residue information for the client */
 			result->residue = d->residue -
 					  cppi5_hdesc_get_pktlen(desc_vaddr);
 			if (result->residue)
@@ -3991,7 +3992,12 @@ static void udma_desc_pre_callback(struct virt_dma_chan *vc,
 				result->result = DMA_TRANS_NOERROR;
 		} else {
 			result->residue = 0;
-			result->result = DMA_TRANS_NOERROR;
+			/* Propagate TR Response errors to the client */
+			status = d->hwdesc[0].tr_resp_base->status;
+			if (status)
+				result->result = DMA_TRANS_ABORTED;
+			else
+				result->result = DMA_TRANS_NOERROR;
 		}
 	}
 }
@@ -4441,6 +4447,8 @@ static const struct soc_device_attribute k3_soc_devices[] = {
 	{ .family = "AM62X", .data = &am64_soc_data },
 	{ .family = "AM62AX", .data = &am64_soc_data },
 	{ .family = "J784S4", .data = &j721e_soc_data },
+	{ .family = "AM62PX", .data = &am64_soc_data },
+	{ .family = "J722S", .data = &am64_soc_data },
 	{ /* sentinel */ }
 };
 
diff --git a/drivers/dma/uniphier-mdmac.c b/drivers/dma/uniphier-mdmac.c
index 618839df0748..ad7125f6e2ca 100644
--- a/drivers/dma/uniphier-mdmac.c
+++ b/drivers/dma/uniphier-mdmac.c
@@ -453,7 +453,7 @@ disable_clk:
 	return ret;
 }
 
-static int uniphier_mdmac_remove(struct platform_device *pdev)
+static void uniphier_mdmac_remove(struct platform_device *pdev)
 {
 	struct uniphier_mdmac_device *mdev = platform_get_drvdata(pdev);
 	struct dma_chan *chan;
@@ -468,16 +468,21 @@ static int uniphier_mdmac_remove(struct platform_device *pdev)
 	 */
 	list_for_each_entry(chan, &mdev->ddev.channels, device_node) {
 		ret = dmaengine_terminate_sync(chan);
-		if (ret)
-			return ret;
+		if (ret) {
+			/*
+			 * This results in resource leakage and maybe also
+			 * use-after-free errors as e.g. *mdev is kfreed.
+			 */
+			dev_alert(&pdev->dev, "Failed to terminate channel %d (%pe)\n",
+				  chan->chan_id, ERR_PTR(ret));
+			return;
+		}
 		uniphier_mdmac_free_chan_resources(chan);
 	}
 
 	of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(&mdev->ddev);
 	clk_disable_unprepare(mdev->clk);
-
-	return 0;
 }
 
 static const struct of_device_id uniphier_mdmac_match[] = {
@@ -488,7 +493,7 @@ MODULE_DEVICE_TABLE(of, uniphier_mdmac_match);
 
 static struct platform_driver uniphier_mdmac_driver = {
 	.probe = uniphier_mdmac_probe,
-	.remove = uniphier_mdmac_remove,
+	.remove_new = uniphier_mdmac_remove,
 	.driver = {
 		.name = "uniphier-mio-dmac",
 		.of_match_table = uniphier_mdmac_match,
diff --git a/drivers/dma/uniphier-xdmac.c b/drivers/dma/uniphier-xdmac.c
index 3a8ee2b173b5..3ce2dc2ad9de 100644
--- a/drivers/dma/uniphier-xdmac.c
+++ b/drivers/dma/uniphier-xdmac.c
@@ -563,7 +563,7 @@ out_unregister_dmac:
 	return ret;
 }
 
-static int uniphier_xdmac_remove(struct platform_device *pdev)
+static void uniphier_xdmac_remove(struct platform_device *pdev)
 {
 	struct uniphier_xdmac_device *xdev = platform_get_drvdata(pdev);
 	struct dma_device *ddev = &xdev->ddev;
@@ -579,15 +579,20 @@ static int uniphier_xdmac_remove(struct platform_device *pdev)
 	 */
 	list_for_each_entry(chan, &ddev->channels, device_node) {
 		ret = dmaengine_terminate_sync(chan);
-		if (ret)
-			return ret;
+		if (ret) {
+			/*
+			 * This results in resource leakage and maybe also
+			 * use-after-free errors as e.g. *xdev is kfreed.
+			 */
+			dev_alert(&pdev->dev, "Failed to terminate channel %d (%pe)\n",
+				  chan->chan_id, ERR_PTR(ret));
+			return;
+		}
 		uniphier_xdmac_free_chan_resources(chan);
 	}
 
 	of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(ddev);
-
-	return 0;
 }
 
 static const struct of_device_id uniphier_xdmac_match[] = {
@@ -598,7 +603,7 @@ MODULE_DEVICE_TABLE(of, uniphier_xdmac_match);
 
 static struct platform_driver uniphier_xdmac_driver = {
 	.probe = uniphier_xdmac_probe,
-	.remove = uniphier_xdmac_remove,
+	.remove_new = uniphier_xdmac_remove,
 	.driver = {
 		.name = "uniphier-xdmac",
 		.of_match_table = uniphier_xdmac_match,
diff --git a/drivers/dma/xilinx/xdma-regs.h b/drivers/dma/xilinx/xdma-regs.h
index e641a5083e14..98f5f6fb9ff9 100644
--- a/drivers/dma/xilinx/xdma-regs.h
+++ b/drivers/dma/xilinx/xdma-regs.h
@@ -64,9 +64,10 @@ struct xdma_hw_desc {
 	__le64		next_desc;
 };
 
-#define XDMA_DESC_SIZE		sizeof(struct xdma_hw_desc)
-#define XDMA_DESC_BLOCK_SIZE	(XDMA_DESC_SIZE * XDMA_DESC_ADJACENT)
-#define XDMA_DESC_BLOCK_ALIGN	4096
+#define XDMA_DESC_SIZE			sizeof(struct xdma_hw_desc)
+#define XDMA_DESC_BLOCK_SIZE		(XDMA_DESC_SIZE * XDMA_DESC_ADJACENT)
+#define XDMA_DESC_BLOCK_ALIGN		32
+#define XDMA_DESC_BLOCK_BOUNDARY	4096
 
 /*
  * Channel registers
@@ -76,6 +77,7 @@ struct xdma_hw_desc {
 #define XDMA_CHAN_CONTROL_W1S		0x8
 #define XDMA_CHAN_CONTROL_W1C		0xc
 #define XDMA_CHAN_STATUS		0x40
+#define XDMA_CHAN_STATUS_RC		0x44
 #define XDMA_CHAN_COMPLETED_DESC	0x48
 #define XDMA_CHAN_ALIGNMENTS		0x4c
 #define XDMA_CHAN_INTR_ENABLE		0x90
@@ -101,6 +103,7 @@ struct xdma_hw_desc {
 #define CHAN_CTRL_IE_MAGIC_STOPPED		BIT(4)
 #define CHAN_CTRL_IE_IDLE_STOPPED		BIT(6)
 #define CHAN_CTRL_IE_READ_ERROR			GENMASK(13, 9)
+#define CHAN_CTRL_IE_WRITE_ERROR		GENMASK(18, 14)
 #define CHAN_CTRL_IE_DESC_ERROR			GENMASK(23, 19)
 #define CHAN_CTRL_NON_INCR_ADDR			BIT(25)
 #define CHAN_CTRL_POLL_MODE_WB			BIT(26)
@@ -111,8 +114,17 @@ struct xdma_hw_desc {
 			 CHAN_CTRL_IE_DESC_ALIGN_MISMATCH |		\
 			 CHAN_CTRL_IE_MAGIC_STOPPED |			\
 			 CHAN_CTRL_IE_READ_ERROR |			\
+			 CHAN_CTRL_IE_WRITE_ERROR |			\
 			 CHAN_CTRL_IE_DESC_ERROR)
 
+#define XDMA_CHAN_STATUS_MASK CHAN_CTRL_START
+
+#define XDMA_CHAN_ERROR_MASK (CHAN_CTRL_IE_DESC_ALIGN_MISMATCH |	\
+			      CHAN_CTRL_IE_MAGIC_STOPPED |		\
+			      CHAN_CTRL_IE_READ_ERROR |			\
+			      CHAN_CTRL_IE_WRITE_ERROR |		\
+			      CHAN_CTRL_IE_DESC_ERROR)
+
 /* bits of the channel interrupt enable mask */
 #define CHAN_IM_DESC_ERROR			BIT(19)
 #define CHAN_IM_READ_ERROR			BIT(9)
@@ -134,18 +146,6 @@ struct xdma_hw_desc {
 #define XDMA_SGDMA_DESC_ADJ	0x4088
 #define XDMA_SGDMA_DESC_CREDIT	0x408c
 
-/* bits of the SG DMA control register */
-#define XDMA_CTRL_RUN_STOP			BIT(0)
-#define XDMA_CTRL_IE_DESC_STOPPED		BIT(1)
-#define XDMA_CTRL_IE_DESC_COMPLETED		BIT(2)
-#define XDMA_CTRL_IE_DESC_ALIGN_MISMATCH	BIT(3)
-#define XDMA_CTRL_IE_MAGIC_STOPPED		BIT(4)
-#define XDMA_CTRL_IE_IDLE_STOPPED		BIT(6)
-#define XDMA_CTRL_IE_READ_ERROR			GENMASK(13, 9)
-#define XDMA_CTRL_IE_DESC_ERROR			GENMASK(23, 19)
-#define XDMA_CTRL_NON_INCR_ADDR			BIT(25)
-#define XDMA_CTRL_POLL_MODE_WB			BIT(26)
-
 /*
  * interrupt registers
  */
diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index 84a88029226f..170017ff2aad 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -78,27 +78,31 @@ struct xdma_chan {
  * @vdesc: Virtual DMA descriptor
  * @chan: DMA channel pointer
  * @dir: Transferring direction of the request
- * @dev_addr: Physical address on DMA device side
  * @desc_blocks: Hardware descriptor blocks
  * @dblk_num: Number of hardware descriptor blocks
  * @desc_num: Number of hardware descriptors
  * @completed_desc_num: Completed hardware descriptors
  * @cyclic: Cyclic transfer vs. scatter-gather
+ * @interleaved_dma: Interleaved DMA transfer
  * @periods: Number of periods in the cyclic transfer
  * @period_size: Size of a period in bytes in cyclic transfers
+ * @frames_left: Number of frames left in interleaved DMA transfer
+ * @error: tx error flag
  */
 struct xdma_desc {
 	struct virt_dma_desc		vdesc;
 	struct xdma_chan		*chan;
 	enum dma_transfer_direction	dir;
-	u64				dev_addr;
 	struct xdma_desc_block		*desc_blocks;
 	u32				dblk_num;
 	u32				desc_num;
 	u32				completed_desc_num;
 	bool				cyclic;
+	bool				interleaved_dma;
 	u32				periods;
 	u32				period_size;
+	u32				frames_left;
+	bool				error;
 };
 
 #define XDMA_DEV_STATUS_REG_DMA		BIT(0)
@@ -276,6 +280,7 @@ xdma_alloc_desc(struct xdma_chan *chan, u32 desc_num, bool cyclic)
 	sw_desc->chan = chan;
 	sw_desc->desc_num = desc_num;
 	sw_desc->cyclic = cyclic;
+	sw_desc->error = false;
 	dblk_num = DIV_ROUND_UP(desc_num, XDMA_DESC_ADJACENT);
 	sw_desc->desc_blocks = kcalloc(dblk_num, sizeof(*sw_desc->desc_blocks),
 				       GFP_NOWAIT);
@@ -371,6 +376,31 @@ static int xdma_xfer_start(struct xdma_chan *xchan)
 		return ret;
 
 	xchan->busy = true;
+
+	return 0;
+}
+
+/**
+ * xdma_xfer_stop - Stop DMA transfer
+ * @xchan: DMA channel pointer
+ */
+static int xdma_xfer_stop(struct xdma_chan *xchan)
+{
+	int ret;
+	u32 val;
+	struct xdma_device *xdev = xchan->xdev_hdl;
+
+	/* clear run stop bit to prevent any further auto-triggering */
+	ret = regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_CONTROL_W1C,
+			   CHAN_CTRL_RUN_STOP);
+	if (ret)
+		return ret;
+
+	/* Clear the channel status register */
+	ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_STATUS_RC, &val);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 
@@ -476,6 +506,84 @@ static void xdma_issue_pending(struct dma_chan *chan)
 }
 
 /**
+ * xdma_terminate_all - Terminate all transactions
+ * @chan: DMA channel pointer
+ */
+static int xdma_terminate_all(struct dma_chan *chan)
+{
+	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
+	struct virt_dma_desc *vd;
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	xdma_xfer_stop(xdma_chan);
+
+	spin_lock_irqsave(&xdma_chan->vchan.lock, flags);
+
+	xdma_chan->busy = false;
+	vd = vchan_next_desc(&xdma_chan->vchan);
+	if (vd) {
+		list_del(&vd->node);
+		dma_cookie_complete(&vd->tx);
+		vchan_terminate_vdesc(vd);
+	}
+	vchan_get_all_descriptors(&xdma_chan->vchan, &head);
+	list_splice_tail(&head, &xdma_chan->vchan.desc_terminated);
+
+	spin_unlock_irqrestore(&xdma_chan->vchan.lock, flags);
+
+	return 0;
+}
+
+/**
+ * xdma_synchronize - Synchronize terminated transactions
+ * @chan: DMA channel pointer
+ */
+static void xdma_synchronize(struct dma_chan *chan)
+{
+	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
+
+	vchan_synchronize(&xdma_chan->vchan);
+}
+
+/**
+ * xdma_fill_descs - Fill hardware descriptors with contiguous memory block addresses
+ * @sw_desc: tx descriptor state container
+ * @src_addr: Value for a ->src_addr field of a first descriptor
+ * @dst_addr: Value for a ->dst_addr field of a first descriptor
+ * @size: Total size of a contiguous memory block
+ * @filled_descs_num: Number of filled hardware descriptors for corresponding sw_desc
+ */
+static inline u32 xdma_fill_descs(struct xdma_desc *sw_desc, u64 src_addr,
+				  u64 dst_addr, u32 size, u32 filled_descs_num)
+{
+	u32 left = size, len, desc_num = filled_descs_num;
+	struct xdma_desc_block *dblk;
+	struct xdma_hw_desc *desc;
+
+	dblk = sw_desc->desc_blocks + (desc_num / XDMA_DESC_ADJACENT);
+	desc = dblk->virt_addr;
+	desc += desc_num & XDMA_DESC_ADJACENT_MASK;
+	do {
+		len = min_t(u32, left, XDMA_DESC_BLEN_MAX);
+		/* set hardware descriptor */
+		desc->bytes = cpu_to_le32(len);
+		desc->src_addr = cpu_to_le64(src_addr);
+		desc->dst_addr = cpu_to_le64(dst_addr);
+		if (!(++desc_num & XDMA_DESC_ADJACENT_MASK))
+			desc = (++dblk)->virt_addr;
+		else
+			desc++;
+
+		src_addr += len;
+		dst_addr += len;
+		left -= len;
+	} while (left);
+
+	return desc_num - filled_descs_num;
+}
+
+/**
  * xdma_prep_device_sg - prepare a descriptor for a DMA transaction
  * @chan: DMA channel pointer
  * @sgl: Transfer scatter gather list
@@ -491,13 +599,10 @@ xdma_prep_device_sg(struct dma_chan *chan, struct scatterlist *sgl,
 {
 	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
 	struct dma_async_tx_descriptor *tx_desc;
-	u32 desc_num = 0, i, len, rest;
-	struct xdma_desc_block *dblk;
-	struct xdma_hw_desc *desc;
 	struct xdma_desc *sw_desc;
-	u64 dev_addr, *src, *dst;
+	u32 desc_num = 0, i;
+	u64 addr, dev_addr, *src, *dst;
 	struct scatterlist *sg;
-	u64 addr;
 
 	for_each_sg(sgl, sg, sg_len, i)
 		desc_num += DIV_ROUND_UP(sg_dma_len(sg), XDMA_DESC_BLEN_MAX);
@@ -506,6 +611,8 @@ xdma_prep_device_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	if (!sw_desc)
 		return NULL;
 	sw_desc->dir = dir;
+	sw_desc->cyclic = false;
+	sw_desc->interleaved_dma = false;
 
 	if (dir == DMA_MEM_TO_DEV) {
 		dev_addr = xdma_chan->cfg.dst_addr;
@@ -517,32 +624,11 @@ xdma_prep_device_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		dst = &addr;
 	}
 
-	dblk = sw_desc->desc_blocks;
-	desc = dblk->virt_addr;
-	desc_num = 1;
+	desc_num = 0;
 	for_each_sg(sgl, sg, sg_len, i) {
 		addr = sg_dma_address(sg);
-		rest = sg_dma_len(sg);
-
-		do {
-			len = min_t(u32, rest, XDMA_DESC_BLEN_MAX);
-			/* set hardware descriptor */
-			desc->bytes = cpu_to_le32(len);
-			desc->src_addr = cpu_to_le64(*src);
-			desc->dst_addr = cpu_to_le64(*dst);
-
-			if (!(desc_num & XDMA_DESC_ADJACENT_MASK)) {
-				dblk++;
-				desc = dblk->virt_addr;
-			} else {
-				desc++;
-			}
-
-			desc_num++;
-			dev_addr += len;
-			addr += len;
-			rest -= len;
-		} while (rest);
+		desc_num += xdma_fill_descs(sw_desc, *src, *dst, sg_dma_len(sg), desc_num);
+		dev_addr += sg_dma_len(sg);
 	}
 
 	tx_desc = vchan_tx_prep(&xdma_chan->vchan, &sw_desc->vdesc, flags);
@@ -576,9 +662,9 @@ xdma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t address,
 	struct xdma_device *xdev = xdma_chan->xdev_hdl;
 	unsigned int periods = size / period_size;
 	struct dma_async_tx_descriptor *tx_desc;
-	struct xdma_desc_block *dblk;
-	struct xdma_hw_desc *desc;
 	struct xdma_desc *sw_desc;
+	u64 addr, dev_addr, *src, *dst;
+	u32 desc_num;
 	unsigned int i;
 
 	/*
@@ -602,22 +688,23 @@ xdma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t address,
 	sw_desc->periods = periods;
 	sw_desc->period_size = period_size;
 	sw_desc->dir = dir;
+	sw_desc->interleaved_dma = false;
 
-	dblk = sw_desc->desc_blocks;
-	desc = dblk->virt_addr;
+	addr = address;
+	if (dir == DMA_MEM_TO_DEV) {
+		dev_addr = xdma_chan->cfg.dst_addr;
+		src = &addr;
+		dst = &dev_addr;
+	} else {
+		dev_addr = xdma_chan->cfg.src_addr;
+		src = &dev_addr;
+		dst = &addr;
+	}
 
-	/* fill hardware descriptor */
+	desc_num = 0;
 	for (i = 0; i < periods; i++) {
-		desc->bytes = cpu_to_le32(period_size);
-		if (dir == DMA_MEM_TO_DEV) {
-			desc->src_addr = cpu_to_le64(address + i * period_size);
-			desc->dst_addr = cpu_to_le64(xdma_chan->cfg.dst_addr);
-		} else {
-			desc->src_addr = cpu_to_le64(xdma_chan->cfg.src_addr);
-			desc->dst_addr = cpu_to_le64(address + i * period_size);
-		}
-
-		desc++;
+		desc_num += xdma_fill_descs(sw_desc, *src, *dst, period_size, desc_num);
+		addr += i * period_size;
 	}
 
 	tx_desc = vchan_tx_prep(&xdma_chan->vchan, &sw_desc->vdesc, flags);
@@ -633,6 +720,57 @@ failed:
 }
 
 /**
+ * xdma_prep_interleaved_dma - Prepare virtual descriptor for interleaved DMA transfers
+ * @chan: DMA channel
+ * @xt: DMA transfer template
+ * @flags: tx flags
+ */
+static struct dma_async_tx_descriptor *
+xdma_prep_interleaved_dma(struct dma_chan *chan,
+			  struct dma_interleaved_template *xt,
+			  unsigned long flags)
+{
+	int i;
+	u32 desc_num = 0, period_size = 0;
+	struct dma_async_tx_descriptor *tx_desc;
+	struct xdma_chan *xchan = to_xdma_chan(chan);
+	struct xdma_desc *sw_desc;
+	u64 src_addr, dst_addr;
+
+	for (i = 0; i < xt->frame_size; ++i)
+		desc_num += DIV_ROUND_UP(xt->sgl[i].size, XDMA_DESC_BLEN_MAX);
+
+	sw_desc = xdma_alloc_desc(xchan, desc_num, false);
+	if (!sw_desc)
+		return NULL;
+	sw_desc->dir = xt->dir;
+	sw_desc->interleaved_dma = true;
+	sw_desc->cyclic = flags & DMA_PREP_REPEAT;
+	sw_desc->frames_left = xt->numf;
+	sw_desc->periods = xt->numf;
+
+	desc_num = 0;
+	src_addr = xt->src_start;
+	dst_addr = xt->dst_start;
+	for (i = 0; i < xt->frame_size; ++i) {
+		desc_num += xdma_fill_descs(sw_desc, src_addr, dst_addr, xt->sgl[i].size, desc_num);
+		src_addr += dmaengine_get_src_icg(xt, &xt->sgl[i]) + (xt->src_inc ?
+							      xt->sgl[i].size : 0);
+		dst_addr += dmaengine_get_dst_icg(xt, &xt->sgl[i]) + (xt->dst_inc ?
+							      xt->sgl[i].size : 0);
+		period_size += xt->sgl[i].size;
+	}
+	sw_desc->period_size = period_size;
+
+	tx_desc = vchan_tx_prep(&xchan->vchan, &sw_desc->vdesc, flags);
+	if (tx_desc)
+		return tx_desc;
+
+	xdma_free_desc(&sw_desc->vdesc);
+	return NULL;
+}
+
+/**
  * xdma_device_config - Configure the DMA channel
  * @chan: DMA channel
  * @cfg: channel configuration
@@ -677,9 +815,8 @@ static int xdma_alloc_chan_resources(struct dma_chan *chan)
 		return -EINVAL;
 	}
 
-	xdma_chan->desc_pool = dma_pool_create(dma_chan_name(chan),
-					       dev, XDMA_DESC_BLOCK_SIZE,
-					       XDMA_DESC_BLOCK_ALIGN, 0);
+	xdma_chan->desc_pool = dma_pool_create(dma_chan_name(chan), dev, XDMA_DESC_BLOCK_SIZE,
+					       XDMA_DESC_BLOCK_ALIGN, XDMA_DESC_BLOCK_BOUNDARY);
 	if (!xdma_chan->desc_pool) {
 		xdma_err(xdev, "unable to allocate descriptor pool");
 		return -ENOMEM;
@@ -706,20 +843,20 @@ static enum dma_status xdma_tx_status(struct dma_chan *chan, dma_cookie_t cookie
 	spin_lock_irqsave(&xdma_chan->vchan.lock, flags);
 
 	vd = vchan_find_desc(&xdma_chan->vchan, cookie);
-	if (vd)
-		desc = to_xdma_desc(vd);
-	if (!desc || !desc->cyclic) {
-		spin_unlock_irqrestore(&xdma_chan->vchan.lock, flags);
-		return ret;
-	}
-
-	period_idx = desc->completed_desc_num % desc->periods;
-	residue = (desc->periods - period_idx) * desc->period_size;
+	if (!vd)
+		goto out;
 
+	desc = to_xdma_desc(vd);
+	if (desc->error) {
+		ret = DMA_ERROR;
+	} else if (desc->cyclic) {
+		period_idx = desc->completed_desc_num % desc->periods;
+		residue = (desc->periods - period_idx) * desc->period_size;
+		dma_set_residue(state, residue);
+	}
+out:
 	spin_unlock_irqrestore(&xdma_chan->vchan.lock, flags);
 
-	dma_set_residue(state, residue);
-
 	return ret;
 }
 
@@ -732,11 +869,12 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
 {
 	struct xdma_chan *xchan = dev_id;
 	u32 complete_desc_num = 0;
-	struct xdma_device *xdev;
-	struct virt_dma_desc *vd;
+	struct xdma_device *xdev = xchan->xdev_hdl;
+	struct virt_dma_desc *vd, *next_vd;
 	struct xdma_desc *desc;
 	int ret;
 	u32 st;
+	bool repeat_tx;
 
 	spin_lock(&xchan->vchan.lock);
 
@@ -745,45 +883,76 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
 	if (!vd)
 		goto out;
 
-	xchan->busy = false;
+	/* Clear-on-read the status register */
+	ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_STATUS_RC, &st);
+	if (ret)
+		goto out;
+
 	desc = to_xdma_desc(vd);
-	xdev = xchan->xdev_hdl;
+
+	st &= XDMA_CHAN_STATUS_MASK;
+	if ((st & XDMA_CHAN_ERROR_MASK) ||
+	    !(st & (CHAN_CTRL_IE_DESC_COMPLETED | CHAN_CTRL_IE_DESC_STOPPED))) {
+		desc->error = true;
+		xdma_err(xdev, "channel error, status register value: 0x%x", st);
+		goto out;
+	}
 
 	ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_COMPLETED_DESC,
 			  &complete_desc_num);
 	if (ret)
 		goto out;
 
-	desc->completed_desc_num += complete_desc_num;
+	if (desc->interleaved_dma) {
+		xchan->busy = false;
+		desc->completed_desc_num += complete_desc_num;
+		if (complete_desc_num == XDMA_DESC_BLOCK_NUM * XDMA_DESC_ADJACENT) {
+			xdma_xfer_start(xchan);
+			goto out;
+		}
 
-	if (desc->cyclic) {
-		ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_STATUS,
-				  &st);
-		if (ret)
+		/* last desc of any frame */
+		desc->frames_left--;
+		if (desc->frames_left)
+			goto out;
+
+		/* last desc of the last frame  */
+		repeat_tx = vd->tx.flags & DMA_PREP_REPEAT;
+		next_vd = list_first_entry_or_null(&vd->node, struct virt_dma_desc, node);
+		if (next_vd)
+			repeat_tx = repeat_tx && !(next_vd->tx.flags & DMA_PREP_LOAD_EOT);
+		if (repeat_tx) {
+			desc->frames_left = desc->periods;
+			desc->completed_desc_num = 0;
+			vchan_cyclic_callback(vd);
+		} else {
+			list_del(&vd->node);
+			vchan_cookie_complete(vd);
+		}
+		/* start (or continue) the tx of a first desc on the vc.desc_issued list, if any */
+		xdma_xfer_start(xchan);
+	} else if (!desc->cyclic) {
+		xchan->busy = false;
+		desc->completed_desc_num += complete_desc_num;
+
+		/* if all data blocks are transferred, remove and complete the request */
+		if (desc->completed_desc_num == desc->desc_num) {
+			list_del(&vd->node);
+			vchan_cookie_complete(vd);
 			goto out;
+		}
 
-		regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_STATUS, st);
+		if (desc->completed_desc_num > desc->desc_num ||
+		    complete_desc_num != XDMA_DESC_BLOCK_NUM * XDMA_DESC_ADJACENT)
+			goto out;
 
+		/* transfer the rest of data */
+		xdma_xfer_start(xchan);
+	} else {
+		desc->completed_desc_num = complete_desc_num;
 		vchan_cyclic_callback(vd);
-		goto out;
-	}
-
-	/*
-	 * if all data blocks are transferred, remove and complete the request
-	 */
-	if (desc->completed_desc_num == desc->desc_num) {
-		list_del(&vd->node);
-		vchan_cookie_complete(vd);
-		goto out;
 	}
 
-	if (desc->completed_desc_num > desc->desc_num ||
-	    complete_desc_num != XDMA_DESC_BLOCK_NUM * XDMA_DESC_ADJACENT)
-		goto out;
-
-	/* transfer the rest of data (SG only) */
-	xdma_xfer_start(xchan);
-
 out:
 	spin_unlock(&xchan->vchan.lock);
 	return IRQ_HANDLED;
@@ -1080,6 +1249,9 @@ static int xdma_probe(struct platform_device *pdev)
 	dma_cap_set(DMA_SLAVE, xdev->dma_dev.cap_mask);
 	dma_cap_set(DMA_PRIVATE, xdev->dma_dev.cap_mask);
 	dma_cap_set(DMA_CYCLIC, xdev->dma_dev.cap_mask);
+	dma_cap_set(DMA_INTERLEAVE, xdev->dma_dev.cap_mask);
+	dma_cap_set(DMA_REPEAT, xdev->dma_dev.cap_mask);
+	dma_cap_set(DMA_LOAD_EOT, xdev->dma_dev.cap_mask);
 
 	xdev->dma_dev.dev = &pdev->dev;
 	xdev->dma_dev.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
@@ -1089,10 +1261,13 @@ static int xdma_probe(struct platform_device *pdev)
 	xdev->dma_dev.device_prep_slave_sg = xdma_prep_device_sg;
 	xdev->dma_dev.device_config = xdma_device_config;
 	xdev->dma_dev.device_issue_pending = xdma_issue_pending;
+	xdev->dma_dev.device_terminate_all = xdma_terminate_all;
+	xdev->dma_dev.device_synchronize = xdma_synchronize;
 	xdev->dma_dev.filter.map = pdata->device_map;
 	xdev->dma_dev.filter.mapcnt = pdata->device_map_cnt;
 	xdev->dma_dev.filter.fn = xdma_filter_fn;
 	xdev->dma_dev.device_prep_dma_cyclic = xdma_prep_dma_cyclic;
+	xdev->dma_dev.device_prep_interleaved_dma = xdma_prep_interleaved_dma;
 
 	ret = dma_async_device_register(&xdev->dma_dev);
 	if (ret) {
diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c
index 69587d85a7cd..b82815e64d24 100644
--- a/drivers/dma/xilinx/xilinx_dpdma.c
+++ b/drivers/dma/xilinx/xilinx_dpdma.c
@@ -309,7 +309,7 @@ static ssize_t xilinx_dpdma_debugfs_desc_done_irq_read(char *buf)
 
 	out_str_len = strlen(XILINX_DPDMA_DEBUGFS_UINT16_MAX_STR);
 	out_str_len = min_t(size_t, XILINX_DPDMA_DEBUGFS_READ_MAX_SIZE,
-			    out_str_len);
+			    out_str_len + 1);
 	snprintf(buf, out_str_len, "%d",
 		 dpdma_debugfs.xilinx_dpdma_irq_done_count);
 
diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c
index 1eca8cc271f8..7f686d179fc9 100644
--- a/drivers/dpll/dpll_core.c
+++ b/drivers/dpll/dpll_core.c
@@ -29,8 +29,6 @@ static u32 dpll_pin_xa_id;
 	WARN_ON_ONCE(!xa_get_mark(&dpll_device_xa, (d)->id, DPLL_REGISTERED))
 #define ASSERT_DPLL_NOT_REGISTERED(d)	\
 	WARN_ON_ONCE(xa_get_mark(&dpll_device_xa, (d)->id, DPLL_REGISTERED))
-#define ASSERT_PIN_REGISTERED(p)	\
-	WARN_ON_ONCE(!xa_get_mark(&dpll_pin_xa, (p)->id, DPLL_REGISTERED))
 
 struct dpll_device_registration {
 	struct list_head list;
@@ -425,6 +423,53 @@ void dpll_device_unregister(struct dpll_device *dpll,
 }
 EXPORT_SYMBOL_GPL(dpll_device_unregister);
 
+static void dpll_pin_prop_free(struct dpll_pin_properties *prop)
+{
+	kfree(prop->package_label);
+	kfree(prop->panel_label);
+	kfree(prop->board_label);
+	kfree(prop->freq_supported);
+}
+
+static int dpll_pin_prop_dup(const struct dpll_pin_properties *src,
+			     struct dpll_pin_properties *dst)
+{
+	memcpy(dst, src, sizeof(*dst));
+	if (src->freq_supported && src->freq_supported_num) {
+		size_t freq_size = src->freq_supported_num *
+				   sizeof(*src->freq_supported);
+		dst->freq_supported = kmemdup(src->freq_supported,
+					      freq_size, GFP_KERNEL);
+		if (!src->freq_supported)
+			return -ENOMEM;
+	}
+	if (src->board_label) {
+		dst->board_label = kstrdup(src->board_label, GFP_KERNEL);
+		if (!dst->board_label)
+			goto err_board_label;
+	}
+	if (src->panel_label) {
+		dst->panel_label = kstrdup(src->panel_label, GFP_KERNEL);
+		if (!dst->panel_label)
+			goto err_panel_label;
+	}
+	if (src->package_label) {
+		dst->package_label = kstrdup(src->package_label, GFP_KERNEL);
+		if (!dst->package_label)
+			goto err_package_label;
+	}
+
+	return 0;
+
+err_package_label:
+	kfree(dst->panel_label);
+err_panel_label:
+	kfree(dst->board_label);
+err_board_label:
+	kfree(dst->freq_supported);
+	return -ENOMEM;
+}
+
 static struct dpll_pin *
 dpll_pin_alloc(u64 clock_id, u32 pin_idx, struct module *module,
 	       const struct dpll_pin_properties *prop)
@@ -441,24 +486,48 @@ dpll_pin_alloc(u64 clock_id, u32 pin_idx, struct module *module,
 	if (WARN_ON(prop->type < DPLL_PIN_TYPE_MUX ||
 		    prop->type > DPLL_PIN_TYPE_MAX)) {
 		ret = -EINVAL;
-		goto err;
+		goto err_pin_prop;
 	}
-	pin->prop = prop;
+	ret = dpll_pin_prop_dup(prop, &pin->prop);
+	if (ret)
+		goto err_pin_prop;
 	refcount_set(&pin->refcount, 1);
 	xa_init_flags(&pin->dpll_refs, XA_FLAGS_ALLOC);
 	xa_init_flags(&pin->parent_refs, XA_FLAGS_ALLOC);
 	ret = xa_alloc_cyclic(&dpll_pin_xa, &pin->id, pin, xa_limit_32b,
 			      &dpll_pin_xa_id, GFP_KERNEL);
 	if (ret)
-		goto err;
+		goto err_xa_alloc;
 	return pin;
-err:
+err_xa_alloc:
 	xa_destroy(&pin->dpll_refs);
 	xa_destroy(&pin->parent_refs);
+	dpll_pin_prop_free(&pin->prop);
+err_pin_prop:
 	kfree(pin);
 	return ERR_PTR(ret);
 }
 
+static void dpll_netdev_pin_assign(struct net_device *dev, struct dpll_pin *dpll_pin)
+{
+	rtnl_lock();
+	rcu_assign_pointer(dev->dpll_pin, dpll_pin);
+	rtnl_unlock();
+}
+
+void dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin)
+{
+	WARN_ON(!dpll_pin);
+	dpll_netdev_pin_assign(dev, dpll_pin);
+}
+EXPORT_SYMBOL(dpll_netdev_pin_set);
+
+void dpll_netdev_pin_clear(struct net_device *dev)
+{
+	dpll_netdev_pin_assign(dev, NULL);
+}
+EXPORT_SYMBOL(dpll_netdev_pin_clear);
+
 /**
  * dpll_pin_get - find existing or create new dpll pin
  * @clock_id: clock_id of creator
@@ -514,7 +583,8 @@ void dpll_pin_put(struct dpll_pin *pin)
 		xa_destroy(&pin->dpll_refs);
 		xa_destroy(&pin->parent_refs);
 		xa_erase(&dpll_pin_xa, pin->id);
-		kfree(pin);
+		dpll_pin_prop_free(&pin->prop);
+		kfree_rcu(pin, rcu);
 	}
 	mutex_unlock(&dpll_lock);
 }
@@ -564,8 +634,6 @@ dpll_pin_register(struct dpll_device *dpll, struct dpll_pin *pin,
 	    WARN_ON(!ops->state_on_dpll_get) ||
 	    WARN_ON(!ops->direction_get))
 		return -EINVAL;
-	if (ASSERT_DPLL_REGISTERED(dpll))
-		return -EINVAL;
 
 	mutex_lock(&dpll_lock);
 	if (WARN_ON(!(dpll->module == pin->module &&
@@ -636,15 +704,13 @@ int dpll_pin_on_pin_register(struct dpll_pin *parent, struct dpll_pin *pin,
 	unsigned long i, stop;
 	int ret;
 
-	if (WARN_ON(parent->prop->type != DPLL_PIN_TYPE_MUX))
+	if (WARN_ON(parent->prop.type != DPLL_PIN_TYPE_MUX))
 		return -EINVAL;
 
 	if (WARN_ON(!ops) ||
 	    WARN_ON(!ops->state_on_pin_get) ||
 	    WARN_ON(!ops->direction_get))
 		return -EINVAL;
-	if (ASSERT_PIN_REGISTERED(parent))
-		return -EINVAL;
 
 	mutex_lock(&dpll_lock);
 	ret = dpll_xa_ref_pin_add(&pin->parent_refs, parent, ops, priv);
diff --git a/drivers/dpll/dpll_core.h b/drivers/dpll/dpll_core.h
index 5585873c5c1b..2b6d8ef1cdf3 100644
--- a/drivers/dpll/dpll_core.h
+++ b/drivers/dpll/dpll_core.h
@@ -44,9 +44,10 @@ struct dpll_device {
  * @module:		module of creator
  * @dpll_refs:		hold referencees to dplls pin was registered with
  * @parent_refs:	hold references to parent pins pin was registered with
- * @prop:		pointer to pin properties given by registerer
+ * @prop:		pin properties copied from the registerer
  * @rclk_dev_name:	holds name of device when pin can recover clock from it
  * @refcount:		refcount
+ * @rcu:		rcu_head for kfree_rcu()
  **/
 struct dpll_pin {
 	u32 id;
@@ -55,8 +56,9 @@ struct dpll_pin {
 	struct module *module;
 	struct xarray dpll_refs;
 	struct xarray parent_refs;
-	const struct dpll_pin_properties *prop;
+	struct dpll_pin_properties prop;
 	refcount_t refcount;
+	struct rcu_head rcu;
 };
 
 /**
diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c
index 3370dbddb86b..b57355e0c214 100644
--- a/drivers/dpll/dpll_netlink.c
+++ b/drivers/dpll/dpll_netlink.c
@@ -8,6 +8,7 @@
  */
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/netdevice.h>
 #include <net/genetlink.h>
 #include "dpll_core.h"
 #include "dpll_netlink.h"
@@ -48,18 +49,6 @@ dpll_msg_add_dev_parent_handle(struct sk_buff *msg, u32 id)
 }
 
 /**
- * dpll_msg_pin_handle_size - get size of pin handle attribute for given pin
- * @pin: pin pointer
- *
- * Return: byte size of pin handle attribute for given pin.
- */
-size_t dpll_msg_pin_handle_size(struct dpll_pin *pin)
-{
-	return pin ? nla_total_size(4) : 0; /* DPLL_A_PIN_ID */
-}
-EXPORT_SYMBOL_GPL(dpll_msg_pin_handle_size);
-
-/**
  * dpll_msg_add_pin_handle - attach pin handle attribute to a given message
  * @msg: pointer to sk_buff message to attach a pin handle
  * @pin: pin pointer
@@ -68,7 +57,7 @@ EXPORT_SYMBOL_GPL(dpll_msg_pin_handle_size);
  * * 0 - success
  * * -EMSGSIZE - no space in message to attach pin handle
  */
-int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin)
+static int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin)
 {
 	if (!pin)
 		return 0;
@@ -76,7 +65,28 @@ int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin)
 		return -EMSGSIZE;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dpll_msg_add_pin_handle);
+
+static struct dpll_pin *dpll_netdev_pin(const struct net_device *dev)
+{
+	return rcu_dereference_rtnl(dev->dpll_pin);
+}
+
+/**
+ * dpll_netdev_pin_handle_size - get size of pin handle attribute of a netdev
+ * @dev: netdev from which to get the pin
+ *
+ * Return: byte size of pin handle attribute, or 0 if @dev has no pin.
+ */
+size_t dpll_netdev_pin_handle_size(const struct net_device *dev)
+{
+	return dpll_netdev_pin(dev) ? nla_total_size(4) : 0; /* DPLL_A_PIN_ID */
+}
+
+int dpll_netdev_add_pin_handle(struct sk_buff *msg,
+			       const struct net_device *dev)
+{
+	return dpll_msg_add_pin_handle(msg, dpll_netdev_pin(dev));
+}
 
 static int
 dpll_msg_add_mode(struct sk_buff *msg, struct dpll_device *dpll,
@@ -303,17 +313,17 @@ dpll_msg_add_pin_freq(struct sk_buff *msg, struct dpll_pin *pin,
 	if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY, sizeof(freq), &freq,
 			  DPLL_A_PIN_PAD))
 		return -EMSGSIZE;
-	for (fs = 0; fs < pin->prop->freq_supported_num; fs++) {
+	for (fs = 0; fs < pin->prop.freq_supported_num; fs++) {
 		nest = nla_nest_start(msg, DPLL_A_PIN_FREQUENCY_SUPPORTED);
 		if (!nest)
 			return -EMSGSIZE;
-		freq = pin->prop->freq_supported[fs].min;
+		freq = pin->prop.freq_supported[fs].min;
 		if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY_MIN, sizeof(freq),
 				  &freq, DPLL_A_PIN_PAD)) {
 			nla_nest_cancel(msg, nest);
 			return -EMSGSIZE;
 		}
-		freq = pin->prop->freq_supported[fs].max;
+		freq = pin->prop.freq_supported[fs].max;
 		if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY_MAX, sizeof(freq),
 				  &freq, DPLL_A_PIN_PAD)) {
 			nla_nest_cancel(msg, nest);
@@ -329,9 +339,9 @@ static bool dpll_pin_is_freq_supported(struct dpll_pin *pin, u32 freq)
 {
 	int fs;
 
-	for (fs = 0; fs < pin->prop->freq_supported_num; fs++)
-		if (freq >= pin->prop->freq_supported[fs].min &&
-		    freq <= pin->prop->freq_supported[fs].max)
+	for (fs = 0; fs < pin->prop.freq_supported_num; fs++)
+		if (freq >= pin->prop.freq_supported[fs].min &&
+		    freq <= pin->prop.freq_supported[fs].max)
 			return true;
 	return false;
 }
@@ -421,7 +431,7 @@ static int
 dpll_cmd_pin_get_one(struct sk_buff *msg, struct dpll_pin *pin,
 		     struct netlink_ext_ack *extack)
 {
-	const struct dpll_pin_properties *prop = pin->prop;
+	const struct dpll_pin_properties *prop = &pin->prop;
 	struct dpll_pin_ref *ref;
 	int ret;
 
@@ -553,6 +563,24 @@ __dpll_device_change_ntf(struct dpll_device *dpll)
 	return dpll_device_event_send(DPLL_CMD_DEVICE_CHANGE_NTF, dpll);
 }
 
+static bool dpll_pin_available(struct dpll_pin *pin)
+{
+	struct dpll_pin_ref *par_ref;
+	unsigned long i;
+
+	if (!xa_get_mark(&dpll_pin_xa, pin->id, DPLL_REGISTERED))
+		return false;
+	xa_for_each(&pin->parent_refs, i, par_ref)
+		if (xa_get_mark(&dpll_pin_xa, par_ref->pin->id,
+				DPLL_REGISTERED))
+			return true;
+	xa_for_each(&pin->dpll_refs, i, par_ref)
+		if (xa_get_mark(&dpll_device_xa, par_ref->dpll->id,
+				DPLL_REGISTERED))
+			return true;
+	return false;
+}
+
 /**
  * dpll_device_change_ntf - notify that the dpll device has been changed
  * @dpll: registered dpll pointer
@@ -579,7 +607,7 @@ dpll_pin_event_send(enum dpll_cmd event, struct dpll_pin *pin)
 	int ret = -ENOMEM;
 	void *hdr;
 
-	if (WARN_ON(!xa_get_mark(&dpll_pin_xa, pin->id, DPLL_REGISTERED)))
+	if (!dpll_pin_available(pin))
 		return -ENODEV;
 
 	msg = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
@@ -717,7 +745,7 @@ dpll_pin_on_pin_state_set(struct dpll_pin *pin, u32 parent_idx,
 	int ret;
 
 	if (!(DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE &
-	      pin->prop->capabilities)) {
+	      pin->prop.capabilities)) {
 		NL_SET_ERR_MSG(extack, "state changing is not allowed");
 		return -EOPNOTSUPP;
 	}
@@ -753,7 +781,7 @@ dpll_pin_state_set(struct dpll_device *dpll, struct dpll_pin *pin,
 	int ret;
 
 	if (!(DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE &
-	      pin->prop->capabilities)) {
+	      pin->prop.capabilities)) {
 		NL_SET_ERR_MSG(extack, "state changing is not allowed");
 		return -EOPNOTSUPP;
 	}
@@ -780,7 +808,7 @@ dpll_pin_prio_set(struct dpll_device *dpll, struct dpll_pin *pin,
 	int ret;
 
 	if (!(DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE &
-	      pin->prop->capabilities)) {
+	      pin->prop.capabilities)) {
 		NL_SET_ERR_MSG(extack, "prio changing is not allowed");
 		return -EOPNOTSUPP;
 	}
@@ -808,7 +836,7 @@ dpll_pin_direction_set(struct dpll_pin *pin, struct dpll_device *dpll,
 	int ret;
 
 	if (!(DPLL_PIN_CAPABILITIES_DIRECTION_CAN_CHANGE &
-	      pin->prop->capabilities)) {
+	      pin->prop.capabilities)) {
 		NL_SET_ERR_MSG(extack, "direction changing is not allowed");
 		return -EOPNOTSUPP;
 	}
@@ -838,8 +866,8 @@ dpll_pin_phase_adj_set(struct dpll_pin *pin, struct nlattr *phase_adj_attr,
 	int ret;
 
 	phase_adj = nla_get_s32(phase_adj_attr);
-	if (phase_adj > pin->prop->phase_range.max ||
-	    phase_adj < pin->prop->phase_range.min) {
+	if (phase_adj > pin->prop.phase_range.max ||
+	    phase_adj < pin->prop.phase_range.min) {
 		NL_SET_ERR_MSG_ATTR(extack, phase_adj_attr,
 				    "phase adjust value not supported");
 		return -EINVAL;
@@ -1023,7 +1051,7 @@ dpll_pin_find(u64 clock_id, struct nlattr *mod_name_attr,
 	unsigned long i;
 
 	xa_for_each_marked(&dpll_pin_xa, i, pin, DPLL_REGISTERED) {
-		prop = pin->prop;
+		prop = &pin->prop;
 		cid_match = clock_id ? pin->clock_id == clock_id : true;
 		mod_match = mod_name_attr && module_name(pin->module) ?
 			!nla_strcmp(mod_name_attr,
@@ -1130,6 +1158,10 @@ int dpll_nl_pin_id_get_doit(struct sk_buff *skb, struct genl_info *info)
 	}
 	pin = dpll_pin_find_from_nlattr(info);
 	if (!IS_ERR(pin)) {
+		if (!dpll_pin_available(pin)) {
+			nlmsg_free(msg);
+			return -ENODEV;
+		}
 		ret = dpll_msg_add_pin_handle(msg, pin);
 		if (ret) {
 			nlmsg_free(msg);
@@ -1177,8 +1209,11 @@ int dpll_nl_pin_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	unsigned long i;
 	int ret = 0;
 
+	mutex_lock(&dpll_lock);
 	xa_for_each_marked_start(&dpll_pin_xa, i, pin, DPLL_REGISTERED,
 				 ctx->idx) {
+		if (!dpll_pin_available(pin))
+			continue;
 		hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid,
 				  cb->nlh->nlmsg_seq,
 				  &dpll_nl_family, NLM_F_MULTI,
@@ -1194,6 +1229,8 @@ int dpll_nl_pin_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 		}
 		genlmsg_end(skb, hdr);
 	}
+	mutex_unlock(&dpll_lock);
+
 	if (ret == -EMSGSIZE) {
 		ctx->idx = i;
 		return skb->len;
@@ -1349,6 +1386,7 @@ int dpll_nl_device_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	unsigned long i;
 	int ret = 0;
 
+	mutex_lock(&dpll_lock);
 	xa_for_each_marked_start(&dpll_device_xa, i, dpll, DPLL_REGISTERED,
 				 ctx->idx) {
 		hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid,
@@ -1365,6 +1403,8 @@ int dpll_nl_device_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 		}
 		genlmsg_end(skb, hdr);
 	}
+	mutex_unlock(&dpll_lock);
+
 	if (ret == -EMSGSIZE) {
 		ctx->idx = i;
 		return skb->len;
@@ -1415,20 +1455,6 @@ dpll_unlock_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 	mutex_unlock(&dpll_lock);
 }
 
-int dpll_lock_dumpit(struct netlink_callback *cb)
-{
-	mutex_lock(&dpll_lock);
-
-	return 0;
-}
-
-int dpll_unlock_dumpit(struct netlink_callback *cb)
-{
-	mutex_unlock(&dpll_lock);
-
-	return 0;
-}
-
 int dpll_pin_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 		      struct genl_info *info)
 {
@@ -1441,7 +1467,8 @@ int dpll_pin_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 	}
 	info->user_ptr[0] = xa_load(&dpll_pin_xa,
 				    nla_get_u32(info->attrs[DPLL_A_PIN_ID]));
-	if (!info->user_ptr[0]) {
+	if (!info->user_ptr[0] ||
+	    !dpll_pin_available(info->user_ptr[0])) {
 		NL_SET_ERR_MSG(info->extack, "pin not found");
 		ret = -ENODEV;
 		goto unlock_dev;
diff --git a/drivers/dpll/dpll_nl.c b/drivers/dpll/dpll_nl.c
index eaee5be7aa64..1e95f5397cfc 100644
--- a/drivers/dpll/dpll_nl.c
+++ b/drivers/dpll/dpll_nl.c
@@ -95,9 +95,7 @@ static const struct genl_split_ops dpll_nl_ops[] = {
 	},
 	{
 		.cmd	= DPLL_CMD_DEVICE_GET,
-		.start	= dpll_lock_dumpit,
 		.dumpit	= dpll_nl_device_get_dumpit,
-		.done	= dpll_unlock_dumpit,
 		.flags	= GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
 	},
 	{
@@ -129,9 +127,7 @@ static const struct genl_split_ops dpll_nl_ops[] = {
 	},
 	{
 		.cmd		= DPLL_CMD_PIN_GET,
-		.start		= dpll_lock_dumpit,
 		.dumpit		= dpll_nl_pin_get_dumpit,
-		.done		= dpll_unlock_dumpit,
 		.policy		= dpll_pin_get_dump_nl_policy,
 		.maxattr	= DPLL_A_PIN_ID,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
diff --git a/drivers/dpll/dpll_nl.h b/drivers/dpll/dpll_nl.h
index 92d4c9c4f788..f491262bee4f 100644
--- a/drivers/dpll/dpll_nl.h
+++ b/drivers/dpll/dpll_nl.h
@@ -30,8 +30,6 @@ dpll_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 void
 dpll_pin_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 		   struct genl_info *info);
-int dpll_lock_dumpit(struct netlink_callback *cb);
-int dpll_unlock_dumpit(struct netlink_callback *cb);
 
 int dpll_nl_device_id_get_doit(struct sk_buff *skb, struct genl_info *info);
 int dpll_nl_device_get_doit(struct sk_buff *skb, struct genl_info *info);
diff --git a/drivers/edac/edac_device.h b/drivers/edac/edac_device.h
index 3f44e6b9d387..7db22a4c83ef 100644
--- a/drivers/edac/edac_device.h
+++ b/drivers/edac/edac_device.h
@@ -176,7 +176,7 @@ struct edac_device_ctl_info {
 	struct edac_dev_sysfs_attribute *sysfs_attributes;
 
 	/* pointer to main 'edac' subsys in sysfs */
-	struct bus_type *edac_subsys;
+	const struct bus_type *edac_subsys;
 
 	/* the internal state of this controller instance */
 	int op_state;
diff --git a/drivers/edac/edac_device_sysfs.c b/drivers/edac/edac_device_sysfs.c
index 010c26be5846..237a542e045a 100644
--- a/drivers/edac/edac_device_sysfs.c
+++ b/drivers/edac/edac_device_sysfs.c
@@ -229,7 +229,7 @@ static struct kobj_type ktype_device_ctrl = {
 int edac_device_register_sysfs_main_kobj(struct edac_device_ctl_info *edac_dev)
 {
 	struct device *dev_root;
-	struct bus_type *edac_subsys;
+	const struct bus_type *edac_subsys;
 	int err = -ENODEV;
 
 	edac_dbg(1, "\n");
diff --git a/drivers/edac/edac_module.c b/drivers/edac/edac_module.c
index 32a931d0cb71..1c9f62382666 100644
--- a/drivers/edac/edac_module.c
+++ b/drivers/edac/edac_module.c
@@ -67,7 +67,7 @@ char *edac_op_state_to_string(int opstate)
  * sysfs object: /sys/devices/system/edac
  *	need to export to other files
  */
-static struct bus_type edac_subsys = {
+static const struct bus_type edac_subsys = {
 	.name = "edac",
 	.dev_name = "edac",
 };
@@ -90,7 +90,7 @@ static void edac_subsys_exit(void)
 }
 
 /* return pointer to the 'edac' node in sysfs */
-struct bus_type *edac_get_sysfs_subsys(void)
+const struct bus_type *edac_get_sysfs_subsys(void)
 {
 	return &edac_subsys;
 }
diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c
index 901d4cd3ca38..7b44afcf48db 100644
--- a/drivers/edac/edac_pci_sysfs.c
+++ b/drivers/edac/edac_pci_sysfs.c
@@ -338,7 +338,7 @@ static struct kobj_type ktype_edac_pci_main_kobj = {
 static int edac_pci_main_kobj_setup(void)
 {
 	int err = -ENODEV;
-	struct bus_type *edac_subsys;
+	const struct bus_type *edac_subsys;
 	struct device *dev_root;
 
 	edac_dbg(0, "\n");
diff --git a/drivers/edac/versal_edac.c b/drivers/edac/versal_edac.c
index 8625de20fc71..62caf454b567 100644
--- a/drivers/edac/versal_edac.c
+++ b/drivers/edac/versal_edac.c
@@ -1005,7 +1005,7 @@ static int mc_probe(struct platform_device *pdev)
 		goto free_edac_mc;
 	}
 
-	rc = xlnx_register_event(PM_NOTIFY_CB, EVENT_ERROR_PMC_ERR1,
+	rc = xlnx_register_event(PM_NOTIFY_CB, VERSAL_EVENT_ERROR_PMC_ERR1,
 				 XPM_EVENT_ERROR_MASK_DDRMC_CR | XPM_EVENT_ERROR_MASK_DDRMC_NCR |
 				 XPM_EVENT_ERROR_MASK_NOC_CR | XPM_EVENT_ERROR_MASK_NOC_NCR,
 				 false, err_callback, mci);
@@ -1042,7 +1042,7 @@ static int mc_remove(struct platform_device *pdev)
 	debugfs_remove_recursive(priv->debugfs);
 #endif
 
-	xlnx_unregister_event(PM_NOTIFY_CB, EVENT_ERROR_PMC_ERR1,
+	xlnx_unregister_event(PM_NOTIFY_CB, VERSAL_EVENT_ERROR_PMC_ERR1,
 			      XPM_EVENT_ERROR_MASK_DDRMC_CR |
 			      XPM_EVENT_ERROR_MASK_NOC_CR |
 			      XPM_EVENT_ERROR_MASK_NOC_NCR |
diff --git a/drivers/extcon/extcon-qcom-spmi-misc.c b/drivers/extcon/extcon-qcom-spmi-misc.c
index f72e90ceca53..53de581a393a 100644
--- a/drivers/extcon/extcon-qcom-spmi-misc.c
+++ b/drivers/extcon/extcon-qcom-spmi-misc.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
  * extcon-qcom-spmi-misc.c - Qualcomm USB extcon driver to support USB ID
  *			and VBUS detection based on extcon-usb-gpio.c.
  *
diff --git a/drivers/extcon/extcon-usbc-tusb320.c b/drivers/extcon/extcon-usbc-tusb320.c
index 4d08c2123e59..2eab341de6b7 100644
--- a/drivers/extcon/extcon-usbc-tusb320.c
+++ b/drivers/extcon/extcon-usbc-tusb320.c
@@ -17,6 +17,7 @@
 #include <linux/usb/typec.h>
 #include <linux/usb/typec_altmode.h>
 #include <linux/usb/role.h>
+#include <linux/irq.h>
 
 #define TUSB320_REG8				0x8
 #define TUSB320_REG8_CURRENT_MODE_ADVERTISE	GENMASK(7, 6)
@@ -515,6 +516,8 @@ static int tusb320_probe(struct i2c_client *client)
 	const void *match_data;
 	unsigned int revision;
 	int ret;
+	u32 irq_trigger_type = IRQF_TRIGGER_FALLING;
+	struct irq_data *irq_d;
 
 	priv = devm_kzalloc(&client->dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -568,9 +571,13 @@ static int tusb320_probe(struct i2c_client *client)
 		 */
 		tusb320_state_update_handler(priv, true);
 
+	irq_d = irq_get_irq_data(client->irq);
+	if (irq_d)
+		irq_trigger_type = irqd_get_trigger_type(irq_d);
+
 	ret = devm_request_threaded_irq(priv->dev, client->irq, NULL,
 					tusb320_irq_handler,
-					IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+					IRQF_ONESHOT | irq_trigger_type,
 					client->name, priv);
 	if (ret)
 		tusb320_typec_remove(priv);
diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c
index 6f7a60d2ed91..e7f55c021e56 100644
--- a/drivers/extcon/extcon.c
+++ b/drivers/extcon/extcon.c
@@ -1280,8 +1280,6 @@ int extcon_dev_register(struct extcon_dev *edev)
 
 	edev->id = ret;
 
-	dev_set_name(&edev->dev, "extcon%d", edev->id);
-
 	ret = extcon_alloc_cables(edev);
 	if (ret < 0)
 		goto err_alloc_cables;
@@ -1310,6 +1308,7 @@ int extcon_dev_register(struct extcon_dev *edev)
 	RAW_INIT_NOTIFIER_HEAD(&edev->nh_all);
 
 	dev_set_drvdata(&edev->dev, edev);
+	dev_set_name(&edev->dev, "extcon%d", edev->id);
 	edev->state = 0;
 
 	ret = device_register(&edev->dev);
diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c
index 6ac5ff20a2fe..401a77e3b5fa 100644
--- a/drivers/firewire/core-card.c
+++ b/drivers/firewire/core-card.c
@@ -429,7 +429,23 @@ static void bm_work(struct work_struct *work)
 	 */
 	card->bm_generation = generation;
 
-	if (root_device == NULL) {
+	if (card->gap_count == 0) {
+		/*
+		 * If self IDs have inconsistent gap counts, do a
+		 * bus reset ASAP. The config rom read might never
+		 * complete, so don't wait for it. However, still
+		 * send a PHY configuration packet prior to the
+		 * bus reset. The PHY configuration packet might
+		 * fail, but 1394-2008 8.4.5.2 explicitly permits
+		 * it in this case, so it should be safe to try.
+		 */
+		new_root_id = local_id;
+		/*
+		 * We must always send a bus reset if the gap count
+		 * is inconsistent, so bypass the 5-reset limit.
+		 */
+		card->bm_retries = 0;
+	} else if (root_device == NULL) {
 		/*
 		 * Either link_on is false, or we failed to read the
 		 * config rom.  In either case, pick another root.
@@ -484,7 +500,19 @@ static void bm_work(struct work_struct *work)
 		fw_notice(card, "phy config: new root=%x, gap_count=%d\n",
 			  new_root_id, gap_count);
 		fw_send_phy_config(card, new_root_id, generation, gap_count);
-		reset_bus(card, true);
+		/*
+		 * Where possible, use a short bus reset to minimize
+		 * disruption to isochronous transfers. But in the event
+		 * of a gap count inconsistency, use a long bus reset.
+		 *
+		 * As noted in 1394a 8.4.6.2, nodes on a mixed 1394/1394a bus
+		 * may set different gap counts after a bus reset. On a mixed
+		 * 1394/1394a bus, a short bus reset can get doubled. Some
+		 * nodes may treat the double reset as one bus reset and others
+		 * may treat it as two, causing a gap count inconsistency
+		 * again. Using a long bus reset prevents this.
+		 */
+		reset_bus(card, card->gap_count != 0);
 		/* Will allocate broadcast channel after the reset. */
 		goto out;
 	}
diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c
index 0547253d16fe..7d3346b3a2bf 100644
--- a/drivers/firewire/core-device.c
+++ b/drivers/firewire/core-device.c
@@ -118,10 +118,9 @@ static int textual_leaf_to_string(const u32 *block, char *buf, size_t size)
  * @buf:	where to put the string
  * @size:	size of @buf, in bytes
  *
- * The string is taken from a minimal ASCII text descriptor leaf after
- * the immediate entry with @key.  The string is zero-terminated.
- * An overlong string is silently truncated such that it and the
- * zero byte fit into @size.
+ * The string is taken from a minimal ASCII text descriptor leaf just after the entry with the
+ * @key. The string is zero-terminated. An overlong string is silently truncated such that it
+ * and the zero byte fit into @size.
  *
  * Returns strlen(buf) or a negative error code.
  */
@@ -368,8 +367,17 @@ static ssize_t show_text_leaf(struct device *dev,
 	for (i = 0; i < ARRAY_SIZE(directories) && !!directories[i]; ++i) {
 		int result = fw_csr_string(directories[i], attr->key, buf, bufsize);
 		// Detected.
-		if (result >= 0)
+		if (result >= 0) {
 			ret = result;
+		} else if (i == 0 && attr->key == CSR_VENDOR) {
+			// Sony DVMC-DA1 has configuration ROM such that the descriptor leaf entry
+			// in the root directory follows to the directory entry for vendor ID
+			// instead of the immediate value for vendor ID.
+			result = fw_csr_string(directories[i], CSR_DIRECTORY | attr->key, buf,
+					       bufsize);
+			if (result >= 0)
+				ret = result;
+		}
 	}
 
 	if (ret >= 0) {
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 9db9290c3269..7bc71f4be64a 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -3773,6 +3773,7 @@ static int pci_probe(struct pci_dev *dev,
 	return 0;
 
  fail_msi:
+	devm_free_irq(&dev->dev, dev->irq, ohci);
 	pci_disable_msi(dev);
 
 	return err;
@@ -3800,6 +3801,7 @@ static void pci_remove(struct pci_dev *dev)
 
 	software_reset(ohci);
 
+	devm_free_irq(&dev->dev, dev->irq, ohci);
 	pci_disable_msi(dev);
 
 	dev_notice(&dev->dev, "removing fw-ohci device\n");
diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index 6146b2927d5c..f2556a8e9401 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -107,12 +107,12 @@ struct ffa_drv_info {
 	struct work_struct notif_pcpu_work;
 	struct work_struct irq_work;
 	struct xarray partition_info;
-	unsigned int partition_count;
 	DECLARE_HASHTABLE(notifier_hash, ilog2(FFA_MAX_NOTIFICATIONS));
 	struct mutex notify_lock; /* lock to protect notifier hashtable  */
 };
 
 static struct ffa_drv_info *drv_info;
+static void ffa_partitions_cleanup(void);
 
 /*
  * The driver must be able to support all the versions from the earliest
@@ -733,6 +733,11 @@ static void __do_sched_recv_cb(u16 part_id, u16 vcpu, bool is_per_vcpu)
 	void *cb_data;
 
 	partition = xa_load(&drv_info->partition_info, part_id);
+	if (!partition) {
+		pr_err("%s: Invalid partition ID 0x%x\n", __func__, part_id);
+		return;
+	}
+
 	read_lock(&partition->rw_lock);
 	callback = partition->callback;
 	cb_data = partition->cb_data;
@@ -915,6 +920,11 @@ static int ffa_sched_recv_cb_update(u16 part_id, ffa_sched_recv_cb callback,
 		return -EOPNOTSUPP;
 
 	partition = xa_load(&drv_info->partition_info, part_id);
+	if (!partition) {
+		pr_err("%s: Invalid partition ID 0x%x\n", __func__, part_id);
+		return -EINVAL;
+	}
+
 	write_lock(&partition->rw_lock);
 
 	cb_valid = !!partition->callback;
@@ -1186,9 +1196,9 @@ void ffa_device_match_uuid(struct ffa_device *ffa_dev, const uuid_t *uuid)
 	kfree(pbuf);
 }
 
-static void ffa_setup_partitions(void)
+static int ffa_setup_partitions(void)
 {
-	int count, idx;
+	int count, idx, ret;
 	uuid_t uuid;
 	struct ffa_device *ffa_dev;
 	struct ffa_dev_part_info *info;
@@ -1197,7 +1207,7 @@ static void ffa_setup_partitions(void)
 	count = ffa_partition_probe(&uuid_null, &pbuf);
 	if (count <= 0) {
 		pr_info("%s: No partitions found, error %d\n", __func__, count);
-		return;
+		return -EINVAL;
 	}
 
 	xa_init(&drv_info->partition_info);
@@ -1226,40 +1236,53 @@ static void ffa_setup_partitions(void)
 			ffa_device_unregister(ffa_dev);
 			continue;
 		}
-		xa_store(&drv_info->partition_info, tpbuf->id, info, GFP_KERNEL);
+		rwlock_init(&info->rw_lock);
+		ret = xa_insert(&drv_info->partition_info, tpbuf->id,
+				info, GFP_KERNEL);
+		if (ret) {
+			pr_err("%s: failed to save partition ID 0x%x - ret:%d\n",
+			       __func__, tpbuf->id, ret);
+			ffa_device_unregister(ffa_dev);
+			kfree(info);
+		}
 	}
-	drv_info->partition_count = count;
 
 	kfree(pbuf);
 
 	/* Allocate for the host */
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
-	if (!info)
-		return;
-	xa_store(&drv_info->partition_info, drv_info->vm_id, info, GFP_KERNEL);
-	drv_info->partition_count++;
+	if (!info) {
+		pr_err("%s: failed to alloc Host partition ID 0x%x. Abort.\n",
+		       __func__, drv_info->vm_id);
+		/* Already registered devices are freed on bus_exit */
+		ffa_partitions_cleanup();
+		return -ENOMEM;
+	}
+
+	rwlock_init(&info->rw_lock);
+	ret = xa_insert(&drv_info->partition_info, drv_info->vm_id,
+			info, GFP_KERNEL);
+	if (ret) {
+		pr_err("%s: failed to save Host partition ID 0x%x - ret:%d. Abort.\n",
+		       __func__, drv_info->vm_id, ret);
+		kfree(info);
+		/* Already registered devices are freed on bus_exit */
+		ffa_partitions_cleanup();
+	}
+
+	return ret;
 }
 
 static void ffa_partitions_cleanup(void)
 {
-	struct ffa_dev_part_info **info;
-	int idx, count = drv_info->partition_count;
-
-	if (!count)
-		return;
-
-	info = kcalloc(count, sizeof(*info), GFP_KERNEL);
-	if (!info)
-		return;
-
-	xa_extract(&drv_info->partition_info, (void **)info, 0, VM_ID_MASK,
-		   count, XA_PRESENT);
+	struct ffa_dev_part_info *info;
+	unsigned long idx;
 
-	for (idx = 0; idx < count; idx++)
-		kfree(info[idx]);
-	kfree(info);
+	xa_for_each(&drv_info->partition_info, idx, info) {
+		xa_erase(&drv_info->partition_info, idx);
+		kfree(info);
+	}
 
-	drv_info->partition_count = 0;
 	xa_destroy(&drv_info->partition_info);
 }
 
@@ -1508,7 +1531,11 @@ static int __init ffa_init(void)
 
 	ffa_notifications_setup();
 
-	ffa_setup_partitions();
+	ret = ffa_setup_partitions();
+	if (ret) {
+		pr_err("failed to setup partitions\n");
+		goto cleanup_notifs;
+	}
 
 	ret = ffa_sched_recv_cb_update(drv_info->vm_id, ffa_self_notif_handle,
 				       drv_info, true);
@@ -1516,6 +1543,9 @@ static int __init ffa_init(void)
 		pr_info("Failed to register driver sched callback %d\n", ret);
 
 	return 0;
+
+cleanup_notifs:
+	ffa_notifications_cleanup();
 free_pages:
 	if (drv_info->tx_buffer)
 		free_pages_exact(drv_info->tx_buffer, RXTX_BUFFER_SIZE);
@@ -1535,7 +1565,6 @@ static void __exit ffa_exit(void)
 	ffa_rxtx_unmap(drv_info->vm_id);
 	free_pages_exact(drv_info->tx_buffer, RXTX_BUFFER_SIZE);
 	free_pages_exact(drv_info->rx_buffer, RXTX_BUFFER_SIZE);
-	xa_destroy(&drv_info->partition_info);
 	kfree(drv_info);
 	arm_ffa_bus_exit();
 }
diff --git a/drivers/firmware/arm_scmi/clock.c b/drivers/firmware/arm_scmi/clock.c
index c0644558042a..e2050adbf85c 100644
--- a/drivers/firmware/arm_scmi/clock.c
+++ b/drivers/firmware/arm_scmi/clock.c
@@ -13,7 +13,7 @@
 #include "notify.h"
 
 /* Updated only after ALL the mandatory features for that version are merged */
-#define SCMI_PROTOCOL_SUPPORTED_VERSION		0x20001
+#define SCMI_PROTOCOL_SUPPORTED_VERSION		0x20000
 
 enum scmi_clock_protocol_cmd {
 	CLOCK_ATTRIBUTES = 0x3,
@@ -954,8 +954,7 @@ static int scmi_clock_protocol_init(const struct scmi_protocol_handle *ph)
 			scmi_clock_describe_rates_get(ph, clkid, clk);
 	}
 
-	if (PROTOCOL_REV_MAJOR(version) >= 0x2 &&
-	    PROTOCOL_REV_MINOR(version) >= 0x1) {
+	if (PROTOCOL_REV_MAJOR(version) >= 0x3) {
 		cinfo->clock_config_set = scmi_clock_config_set_v2;
 		cinfo->clock_config_get = scmi_clock_config_get_v2;
 	} else {
diff --git a/drivers/firmware/arm_scmi/common.h b/drivers/firmware/arm_scmi/common.h
index c46dc5215af7..00b165d1f502 100644
--- a/drivers/firmware/arm_scmi/common.h
+++ b/drivers/firmware/arm_scmi/common.h
@@ -314,6 +314,7 @@ void shmem_fetch_notification(struct scmi_shared_mem __iomem *shmem,
 void shmem_clear_channel(struct scmi_shared_mem __iomem *shmem);
 bool shmem_poll_done(struct scmi_shared_mem __iomem *shmem,
 		     struct scmi_xfer *xfer);
+bool shmem_channel_free(struct scmi_shared_mem __iomem *shmem);
 
 /* declarations for message passing transports */
 struct scmi_msg_payld;
diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c
index a9f70e6e58ac..3ea64b22cf0d 100644
--- a/drivers/firmware/arm_scmi/driver.c
+++ b/drivers/firmware/arm_scmi/driver.c
@@ -2834,7 +2834,7 @@ clear_ida:
 	return ret;
 }
 
-static int scmi_remove(struct platform_device *pdev)
+static void scmi_remove(struct platform_device *pdev)
 {
 	int id;
 	struct scmi_info *info = platform_get_drvdata(pdev);
@@ -2868,8 +2868,6 @@ static int scmi_remove(struct platform_device *pdev)
 	scmi_cleanup_txrx_channels(info);
 
 	ida_free(&scmi_id, info->id);
-
-	return 0;
 }
 
 static ssize_t protocol_version_show(struct device *dev,
@@ -2947,7 +2945,7 @@ static struct platform_driver scmi_driver = {
 		   .dev_groups = versions_groups,
 		   },
 	.probe = scmi_probe,
-	.remove = scmi_remove,
+	.remove_new = scmi_remove,
 };
 
 /**
diff --git a/drivers/firmware/arm_scmi/mailbox.c b/drivers/firmware/arm_scmi/mailbox.c
index 19246ed1f01f..b8d470417e8f 100644
--- a/drivers/firmware/arm_scmi/mailbox.c
+++ b/drivers/firmware/arm_scmi/mailbox.c
@@ -45,6 +45,20 @@ static void rx_callback(struct mbox_client *cl, void *m)
 {
 	struct scmi_mailbox *smbox = client_to_scmi_mailbox(cl);
 
+	/*
+	 * An A2P IRQ is NOT valid when received while the platform still has
+	 * the ownership of the channel, because the platform at first releases
+	 * the SMT channel and then sends the completion interrupt.
+	 *
+	 * This addresses a possible race condition in which a spurious IRQ from
+	 * a previous timed-out reply which arrived late could be wrongly
+	 * associated with the next pending transaction.
+	 */
+	if (cl->knows_txdone && !shmem_channel_free(smbox->shmem)) {
+		dev_warn(smbox->cinfo->dev, "Ignoring spurious A2P IRQ !\n");
+		return;
+	}
+
 	scmi_rx_callback(smbox->cinfo, shmem_read_header(smbox->shmem), NULL);
 }
 
diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c
index 8ea2a7b3d35d..211e8e0aef2c 100644
--- a/drivers/firmware/arm_scmi/perf.c
+++ b/drivers/firmware/arm_scmi/perf.c
@@ -350,8 +350,8 @@ process_response_opp(struct scmi_opp *opp, unsigned int loop_idx,
 }
 
 static inline void
-process_response_opp_v4(struct perf_dom_info *dom, struct scmi_opp *opp,
-			unsigned int loop_idx,
+process_response_opp_v4(struct device *dev, struct perf_dom_info *dom,
+			struct scmi_opp *opp, unsigned int loop_idx,
 			const struct scmi_msg_resp_perf_describe_levels_v4 *r)
 {
 	opp->perf = le32_to_cpu(r->opp[loop_idx].perf_val);
@@ -362,10 +362,23 @@ process_response_opp_v4(struct perf_dom_info *dom, struct scmi_opp *opp,
 	/* Note that PERF v4 reports always five 32-bit words */
 	opp->indicative_freq = le32_to_cpu(r->opp[loop_idx].indicative_freq);
 	if (dom->level_indexing_mode) {
+		int ret;
+
 		opp->level_index = le32_to_cpu(r->opp[loop_idx].level_index);
 
-		xa_store(&dom->opps_by_idx, opp->level_index, opp, GFP_KERNEL);
-		xa_store(&dom->opps_by_lvl, opp->perf, opp, GFP_KERNEL);
+		ret = xa_insert(&dom->opps_by_idx, opp->level_index, opp,
+				GFP_KERNEL);
+		if (ret)
+			dev_warn(dev,
+				 "Failed to add opps_by_idx at %d - ret:%d\n",
+				 opp->level_index, ret);
+
+		ret = xa_insert(&dom->opps_by_lvl, opp->perf, opp, GFP_KERNEL);
+		if (ret)
+			dev_warn(dev,
+				 "Failed to add opps_by_lvl at %d - ret:%d\n",
+				 opp->perf, ret);
+
 		hash_add(dom->opps_by_freq, &opp->hash, opp->indicative_freq);
 	}
 }
@@ -382,7 +395,7 @@ iter_perf_levels_process_response(const struct scmi_protocol_handle *ph,
 	if (PROTOCOL_REV_MAJOR(p->version) <= 0x3)
 		process_response_opp(opp, st->loop_idx, response);
 	else
-		process_response_opp_v4(p->perf_dom, opp, st->loop_idx,
+		process_response_opp_v4(ph->dev, p->perf_dom, opp, st->loop_idx,
 					response);
 	p->perf_dom->opp_count++;
 
diff --git a/drivers/firmware/arm_scmi/raw_mode.c b/drivers/firmware/arm_scmi/raw_mode.c
index 0493aa3c12bf..350573518503 100644
--- a/drivers/firmware/arm_scmi/raw_mode.c
+++ b/drivers/firmware/arm_scmi/raw_mode.c
@@ -1111,7 +1111,6 @@ static int scmi_raw_mode_setup(struct scmi_raw_mode_info *raw,
 		int i;
 
 		for (i = 0; i < num_chans; i++) {
-			void *xret;
 			struct scmi_raw_queue *q;
 
 			q = scmi_raw_queue_init(raw);
@@ -1120,13 +1119,12 @@ static int scmi_raw_mode_setup(struct scmi_raw_mode_info *raw,
 				goto err_xa;
 			}
 
-			xret = xa_store(&raw->chans_q, channels[i], q,
+			ret = xa_insert(&raw->chans_q, channels[i], q,
 					GFP_KERNEL);
-			if (xa_err(xret)) {
+			if (ret) {
 				dev_err(dev,
 					"Fail to allocate Raw queue 0x%02X\n",
 					channels[i]);
-				ret = xa_err(xret);
 				goto err_xa;
 			}
 		}
@@ -1322,6 +1320,12 @@ void scmi_raw_message_report(void *r, struct scmi_xfer *xfer,
 	dev = raw->handle->dev;
 	q = scmi_raw_queue_select(raw, idx,
 				  SCMI_XFER_IS_CHAN_SET(xfer) ? chan_id : 0);
+	if (!q) {
+		dev_warn(dev,
+			 "RAW[%d] - NO queue for chan 0x%X. Dropping report.\n",
+			 idx, chan_id);
+		return;
+	}
 
 	/*
 	 * Grab the msg_q_lock upfront to avoid a possible race between
diff --git a/drivers/firmware/arm_scmi/shmem.c b/drivers/firmware/arm_scmi/shmem.c
index 87b4f4d35f06..8bf495bcad09 100644
--- a/drivers/firmware/arm_scmi/shmem.c
+++ b/drivers/firmware/arm_scmi/shmem.c
@@ -10,7 +10,7 @@
 #include <linux/processor.h>
 #include <linux/types.h>
 
-#include <asm-generic/bug.h>
+#include <linux/bug.h>
 
 #include "common.h"
 
@@ -122,3 +122,9 @@ bool shmem_poll_done(struct scmi_shared_mem __iomem *shmem,
 		(SCMI_SHMEM_CHAN_STAT_CHANNEL_ERROR |
 		 SCMI_SHMEM_CHAN_STAT_CHANNEL_FREE);
 }
+
+bool shmem_channel_free(struct scmi_shared_mem __iomem *shmem)
+{
+	return (ioread32(&shmem->channel_status) &
+			SCMI_SHMEM_CHAN_STAT_CHANNEL_FREE);
+}
diff --git a/drivers/firmware/arm_scpi.c b/drivers/firmware/arm_scpi.c
index 3f123f592cb4..94a6b4e667de 100644
--- a/drivers/firmware/arm_scpi.c
+++ b/drivers/firmware/arm_scpi.c
@@ -863,7 +863,7 @@ static void scpi_free_channels(void *data)
 		mbox_free_channel(info->channels[i].chan);
 }
 
-static int scpi_remove(struct platform_device *pdev)
+static void scpi_remove(struct platform_device *pdev)
 {
 	int i;
 	struct scpi_drvinfo *info = platform_get_drvdata(pdev);
@@ -874,8 +874,6 @@ static int scpi_remove(struct platform_device *pdev)
 		kfree(info->dvfs[i]->opps);
 		kfree(info->dvfs[i]);
 	}
-
-	return 0;
 }
 
 #define MAX_SCPI_XFERS		10
@@ -1048,7 +1046,7 @@ static struct platform_driver scpi_driver = {
 		.dev_groups = versions_groups,
 	},
 	.probe = scpi_probe,
-	.remove = scpi_remove,
+	.remove_new = scpi_remove,
 };
 module_platform_driver(scpi_driver);
 
diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
index 83f5bb57fa4c..83092d93f36a 100644
--- a/drivers/firmware/efi/arm-runtime.c
+++ b/drivers/firmware/efi/arm-runtime.c
@@ -107,7 +107,7 @@ static int __init arm_enable_runtime_services(void)
 		efi_memory_desc_t *md;
 
 		for_each_efi_memory_desc(md) {
-			int md_size = md->num_pages << EFI_PAGE_SHIFT;
+			u64 md_size = md->num_pages << EFI_PAGE_SHIFT;
 			struct resource *res;
 
 			if (!(md->attribute & EFI_MEMORY_SP))
diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c
index 3e8d4b51a814..97bafb5f7038 100644
--- a/drivers/firmware/efi/capsule-loader.c
+++ b/drivers/firmware/efi/capsule-loader.c
@@ -292,7 +292,7 @@ static int efi_capsule_open(struct inode *inode, struct file *file)
 		return -ENOMEM;
 	}
 
-	cap_info->phys = kzalloc(sizeof(void *), GFP_KERNEL);
+	cap_info->phys = kzalloc(sizeof(phys_addr_t), GFP_KERNEL);
 	if (!cap_info->phys) {
 		kfree(cap_info->pages);
 		kfree(cap_info);
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index 35c37f667781..9b3884ff81e6 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -523,6 +523,17 @@ static void cper_print_tstamp(const char *pfx,
 	}
 }
 
+struct ignore_section {
+	guid_t guid;
+	const char *name;
+};
+
+static const struct ignore_section ignore_sections[] = {
+	{ .guid = CPER_SEC_CXL_GEN_MEDIA_GUID, .name = "CXL General Media Event" },
+	{ .guid = CPER_SEC_CXL_DRAM_GUID, .name = "CXL DRAM Event" },
+	{ .guid = CPER_SEC_CXL_MEM_MODULE_GUID, .name = "CXL Memory Module Event" },
+};
+
 static void
 cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata,
 			   int sec_no)
@@ -543,6 +554,14 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata
 		printk("%s""fru_text: %.20s\n", pfx, gdata->fru_text);
 
 	snprintf(newpfx, sizeof(newpfx), "%s ", pfx);
+
+	for (int i = 0; i < ARRAY_SIZE(ignore_sections); i++) {
+		if (guid_equal(sec_type, &ignore_sections[i].guid)) {
+			printk("%ssection_type: %s\n", newpfx, ignore_sections[i].name);
+			return;
+		}
+	}
+
 	if (guid_equal(sec_type, &CPER_SEC_PROC_GENERIC)) {
 		struct cper_sec_proc_generic *proc_err = acpi_hest_get_payload(gdata);
 
diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c
index d4987d013080..a00e07b853f2 100644
--- a/drivers/firmware/efi/efi-init.c
+++ b/drivers/firmware/efi/efi-init.c
@@ -144,15 +144,6 @@ static __init int is_usable_memory(efi_memory_desc_t *md)
 	case EFI_CONVENTIONAL_MEMORY:
 	case EFI_PERSISTENT_MEMORY:
 		/*
-		 * Special purpose memory is 'soft reserved', which means it
-		 * is set aside initially, but can be hotplugged back in or
-		 * be assigned to the dax driver after boot.
-		 */
-		if (efi_soft_reserve_enabled() &&
-		    (md->attribute & EFI_MEMORY_SP))
-			return false;
-
-		/*
 		 * According to the spec, these regions are no longer reserved
 		 * after calling ExitBootServices(). However, we can only use
 		 * them as System RAM if they can be mapped writeback cacheable.
@@ -196,6 +187,16 @@ static __init void reserve_regions(void)
 		size = npages << PAGE_SHIFT;
 
 		if (is_memory(md)) {
+			/*
+			 * Special purpose memory is 'soft reserved', which
+			 * means it is set aside initially. Don't add a memblock
+			 * for it now so that it can be hotplugged back in or
+			 * be assigned to the dax driver after boot.
+			 */
+			if (efi_soft_reserve_enabled() &&
+			    (md->attribute & EFI_MEMORY_SP))
+				continue;
+
 			early_init_dt_add_memory_arch(paddr, size);
 
 			if (!is_usable_memory(md))
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 06964a3c130f..73f4810f6db3 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -28,7 +28,7 @@ cflags-$(CONFIG_ARM)		+= -DEFI_HAVE_STRLEN -DEFI_HAVE_STRNLEN \
 				   -DEFI_HAVE_MEMCHR -DEFI_HAVE_STRRCHR \
 				   -DEFI_HAVE_STRCMP -fno-builtin -fpic \
 				   $(call cc-option,-mno-single-pic-base)
-cflags-$(CONFIG_RISCV)		+= -fpic -DNO_ALTERNATIVE
+cflags-$(CONFIG_RISCV)		+= -fpic -DNO_ALTERNATIVE -mno-relax
 cflags-$(CONFIG_LOONGARCH)	+= -fpie
 
 cflags-$(CONFIG_EFI_PARAMS_FROM_FDT)	+= -I$(srctree)/scripts/dtc/libfdt
@@ -143,7 +143,7 @@ STUBCOPY_RELOC-$(CONFIG_ARM64)	:= R_AARCH64_ABS
 # exist.
 STUBCOPY_FLAGS-$(CONFIG_RISCV)	+= --prefix-alloc-sections=.init \
 				   --prefix-symbols=__efistub_
-STUBCOPY_RELOC-$(CONFIG_RISCV)	:= R_RISCV_HI20
+STUBCOPY_RELOC-$(CONFIG_RISCV)	:= -E R_RISCV_HI20\|R_RISCV_$(BITS)\|R_RISCV_RELAX
 
 # For LoongArch, keep all the symbols in .init section and make sure that no
 # absolute symbols references exist.
diff --git a/drivers/firmware/efi/libstub/alignedmem.c b/drivers/firmware/efi/libstub/alignedmem.c
index 6b83c492c3b8..31928bd87e0f 100644
--- a/drivers/firmware/efi/libstub/alignedmem.c
+++ b/drivers/firmware/efi/libstub/alignedmem.c
@@ -14,6 +14,7 @@
  * @max:	the address that the last allocated memory page shall not
  *		exceed
  * @align:	minimum alignment of the base of the allocation
+ * @memory_type: the type of memory to allocate
  *
  * Allocate pages as EFI_LOADER_DATA. The allocated pages are aligned according
  * to @align, which should be >= EFI_ALLOC_ALIGN. The last allocated page will
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index 212687c30d79..c04b82ea40f2 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -956,7 +956,8 @@ efi_status_t efi_get_random_bytes(unsigned long size, u8 *out);
 
 efi_status_t efi_random_alloc(unsigned long size, unsigned long align,
 			      unsigned long *addr, unsigned long random_seed,
-			      int memory_type, unsigned long alloc_limit);
+			      int memory_type, unsigned long alloc_min,
+			      unsigned long alloc_max);
 
 efi_status_t efi_random_get_seed(void);
 
diff --git a/drivers/firmware/efi/libstub/kaslr.c b/drivers/firmware/efi/libstub/kaslr.c
index 62d63f7a2645..1a9808012abd 100644
--- a/drivers/firmware/efi/libstub/kaslr.c
+++ b/drivers/firmware/efi/libstub/kaslr.c
@@ -119,7 +119,7 @@ efi_status_t efi_kaslr_relocate_kernel(unsigned long *image_addr,
 		 */
 		status = efi_random_alloc(*reserve_size, min_kimg_align,
 					  reserve_addr, phys_seed,
-					  EFI_LOADER_CODE, EFI_ALLOC_LIMIT);
+					  EFI_LOADER_CODE, 0, EFI_ALLOC_LIMIT);
 		if (status != EFI_SUCCESS)
 			efi_warn("efi_random_alloc() failed: 0x%lx\n", status);
 	} else {
diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c
index 674a064b8f7a..4e96a855fdf4 100644
--- a/drivers/firmware/efi/libstub/randomalloc.c
+++ b/drivers/firmware/efi/libstub/randomalloc.c
@@ -17,7 +17,7 @@
 static unsigned long get_entry_num_slots(efi_memory_desc_t *md,
 					 unsigned long size,
 					 unsigned long align_shift,
-					 u64 alloc_limit)
+					 u64 alloc_min, u64 alloc_max)
 {
 	unsigned long align = 1UL << align_shift;
 	u64 first_slot, last_slot, region_end;
@@ -30,11 +30,11 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md,
 		return 0;
 
 	region_end = min(md->phys_addr + md->num_pages * EFI_PAGE_SIZE - 1,
-			 alloc_limit);
+			 alloc_max);
 	if (region_end < size)
 		return 0;
 
-	first_slot = round_up(md->phys_addr, align);
+	first_slot = round_up(max(md->phys_addr, alloc_min), align);
 	last_slot = round_down(region_end - size + 1, align);
 
 	if (first_slot > last_slot)
@@ -56,7 +56,8 @@ efi_status_t efi_random_alloc(unsigned long size,
 			      unsigned long *addr,
 			      unsigned long random_seed,
 			      int memory_type,
-			      unsigned long alloc_limit)
+			      unsigned long alloc_min,
+			      unsigned long alloc_max)
 {
 	unsigned long total_slots = 0, target_slot;
 	unsigned long total_mirrored_slots = 0;
@@ -78,7 +79,8 @@ efi_status_t efi_random_alloc(unsigned long size,
 		efi_memory_desc_t *md = (void *)map->map + map_offset;
 		unsigned long slots;
 
-		slots = get_entry_num_slots(md, size, ilog2(align), alloc_limit);
+		slots = get_entry_num_slots(md, size, ilog2(align), alloc_min,
+					    alloc_max);
 		MD_NUM_SLOTS(md) = slots;
 		total_slots += slots;
 		if (md->attribute & EFI_MEMORY_MORE_RELIABLE)
diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c
index 0d510c9a06a4..99429bc4b0c7 100644
--- a/drivers/firmware/efi/libstub/x86-stub.c
+++ b/drivers/firmware/efi/libstub/x86-stub.c
@@ -223,8 +223,8 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params)
 	}
 }
 
-void efi_adjust_memory_range_protection(unsigned long start,
-					unsigned long size)
+efi_status_t efi_adjust_memory_range_protection(unsigned long start,
+						unsigned long size)
 {
 	efi_status_t status;
 	efi_gcd_memory_space_desc_t desc;
@@ -236,13 +236,17 @@ void efi_adjust_memory_range_protection(unsigned long start,
 	rounded_end = roundup(start + size, EFI_PAGE_SIZE);
 
 	if (memattr != NULL) {
-		efi_call_proto(memattr, clear_memory_attributes, rounded_start,
-			       rounded_end - rounded_start, EFI_MEMORY_XP);
-		return;
+		status = efi_call_proto(memattr, clear_memory_attributes,
+					rounded_start,
+					rounded_end - rounded_start,
+					EFI_MEMORY_XP);
+		if (status != EFI_SUCCESS)
+			efi_warn("Failed to clear EFI_MEMORY_XP attribute\n");
+		return status;
 	}
 
 	if (efi_dxe_table == NULL)
-		return;
+		return EFI_SUCCESS;
 
 	/*
 	 * Don't modify memory region attributes, they are
@@ -255,7 +259,7 @@ void efi_adjust_memory_range_protection(unsigned long start,
 		status = efi_dxe_call(get_memory_space_descriptor, start, &desc);
 
 		if (status != EFI_SUCCESS)
-			return;
+			break;
 
 		next = desc.base_address + desc.length;
 
@@ -280,8 +284,10 @@ void efi_adjust_memory_range_protection(unsigned long start,
 				 unprotect_start,
 				 unprotect_start + unprotect_size,
 				 status);
+			break;
 		}
 	}
+	return EFI_SUCCESS;
 }
 
 static void setup_unaccepted_memory(void)
@@ -793,6 +799,7 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry)
 
 	status = efi_random_alloc(alloc_size, CONFIG_PHYSICAL_ALIGN, &addr,
 				  seed[0], EFI_LOADER_CODE,
+				  LOAD_PHYSICAL_ADDR,
 				  EFI_X86_KERNEL_ALLOC_LIMIT);
 	if (status != EFI_SUCCESS)
 		return status;
@@ -805,9 +812,7 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry)
 
 	*kernel_entry = addr + entry;
 
-	efi_adjust_memory_range_protection(addr, kernel_total_size);
-
-	return EFI_SUCCESS;
+	return efi_adjust_memory_range_protection(addr, kernel_total_size);
 }
 
 static void __noreturn enter_kernel(unsigned long kernel_addr,
diff --git a/drivers/firmware/efi/libstub/x86-stub.h b/drivers/firmware/efi/libstub/x86-stub.h
index 37c5a36b9d8c..1c20e99a6494 100644
--- a/drivers/firmware/efi/libstub/x86-stub.h
+++ b/drivers/firmware/efi/libstub/x86-stub.h
@@ -5,8 +5,8 @@
 extern void trampoline_32bit_src(void *, bool);
 extern const u16 trampoline_ljmp_imm_offset;
 
-void efi_adjust_memory_range_protection(unsigned long start,
-					unsigned long size);
+efi_status_t efi_adjust_memory_range_protection(unsigned long start,
+						unsigned long size);
 
 #ifdef CONFIG_X86_64
 efi_status_t efi_setup_5level_paging(void);
diff --git a/drivers/firmware/efi/libstub/zboot.c b/drivers/firmware/efi/libstub/zboot.c
index bdb17eac0cb4..1ceace956758 100644
--- a/drivers/firmware/efi/libstub/zboot.c
+++ b/drivers/firmware/efi/libstub/zboot.c
@@ -119,7 +119,7 @@ efi_zboot_entry(efi_handle_t handle, efi_system_table_t *systab)
 		}
 
 		status = efi_random_alloc(alloc_size, min_kimg_align, &image_base,
-					  seed, EFI_LOADER_CODE, EFI_ALLOC_LIMIT);
+					  seed, EFI_LOADER_CODE, 0, EFI_ALLOC_LIMIT);
 		if (status != EFI_SUCCESS) {
 			efi_err("Failed to allocate memory\n");
 			goto free_cmdline;
diff --git a/drivers/firmware/efi/riscv-runtime.c b/drivers/firmware/efi/riscv-runtime.c
index 09525fb5c240..01f0f90ea418 100644
--- a/drivers/firmware/efi/riscv-runtime.c
+++ b/drivers/firmware/efi/riscv-runtime.c
@@ -85,7 +85,7 @@ static int __init riscv_enable_runtime_services(void)
 		efi_memory_desc_t *md;
 
 		for_each_efi_memory_desc(md) {
-			int md_size = md->num_pages << EFI_PAGE_SHIFT;
+			u64 md_size = md->num_pages << EFI_PAGE_SHIFT;
 			struct resource *res;
 
 			if (!(md->attribute & EFI_MEMORY_SP))
diff --git a/drivers/firmware/imx/imx-dsp.c b/drivers/firmware/imx/imx-dsp.c
index a48a58e0c61f..01c8ef14eaec 100644
--- a/drivers/firmware/imx/imx-dsp.c
+++ b/drivers/firmware/imx/imx-dsp.c
@@ -160,7 +160,7 @@ static int imx_dsp_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int imx_dsp_remove(struct platform_device *pdev)
+static void imx_dsp_remove(struct platform_device *pdev)
 {
 	struct imx_dsp_chan *dsp_chan;
 	struct imx_dsp_ipc *dsp_ipc;
@@ -173,8 +173,6 @@ static int imx_dsp_remove(struct platform_device *pdev)
 		mbox_free_channel(dsp_chan->ch);
 		kfree(dsp_chan->name);
 	}
-
-	return 0;
 }
 
 static struct platform_driver imx_dsp_driver = {
@@ -182,7 +180,7 @@ static struct platform_driver imx_dsp_driver = {
 		.name = "imx-dsp",
 	},
 	.probe = imx_dsp_probe,
-	.remove = imx_dsp_remove,
+	.remove_new = imx_dsp_remove,
 };
 builtin_platform_driver(imx_dsp_driver);
 
diff --git a/drivers/firmware/microchip/mpfs-auto-update.c b/drivers/firmware/microchip/mpfs-auto-update.c
index 81f5f62e34fc..fbeeaee4ac85 100644
--- a/drivers/firmware/microchip/mpfs-auto-update.c
+++ b/drivers/firmware/microchip/mpfs-auto-update.c
@@ -167,7 +167,7 @@ static int mpfs_auto_update_verify_image(struct fw_upload *fw_uploader)
 	u32 *response_msg;
 	int ret;
 
-	response_msg = devm_kzalloc(priv->dev, AUTO_UPDATE_FEATURE_RESP_SIZE * sizeof(response_msg),
+	response_msg = devm_kzalloc(priv->dev, AUTO_UPDATE_FEATURE_RESP_SIZE * sizeof(*response_msg),
 				    GFP_KERNEL);
 	if (!response_msg)
 		return -ENOMEM;
@@ -384,7 +384,8 @@ static int mpfs_auto_update_available(struct mpfs_auto_update_priv *priv)
 	u32 *response_msg;
 	int ret;
 
-	response_msg = devm_kzalloc(priv->dev, AUTO_UPDATE_FEATURE_RESP_SIZE * sizeof(response_msg),
+	response_msg = devm_kzalloc(priv->dev,
+				    AUTO_UPDATE_FEATURE_RESP_SIZE * sizeof(*response_msg),
 				    GFP_KERNEL);
 	if (!response_msg)
 		return -ENOMEM;
diff --git a/drivers/firmware/mtk-adsp-ipc.c b/drivers/firmware/mtk-adsp-ipc.c
index 85e94ddc7204..a762302978de 100644
--- a/drivers/firmware/mtk-adsp-ipc.c
+++ b/drivers/firmware/mtk-adsp-ipc.c
@@ -116,7 +116,7 @@ static int mtk_adsp_ipc_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int mtk_adsp_ipc_remove(struct platform_device *pdev)
+static void mtk_adsp_ipc_remove(struct platform_device *pdev)
 {
 	struct mtk_adsp_ipc *adsp_ipc = dev_get_drvdata(&pdev->dev);
 	struct mtk_adsp_chan *adsp_chan;
@@ -126,8 +126,6 @@ static int mtk_adsp_ipc_remove(struct platform_device *pdev)
 		adsp_chan = &adsp_ipc->chans[i];
 		mbox_free_channel(adsp_chan->ch);
 	}
-
-	return 0;
 }
 
 static struct platform_driver mtk_adsp_ipc_driver = {
@@ -135,7 +133,7 @@ static struct platform_driver mtk_adsp_ipc_driver = {
 		.name = "mtk-adsp-ipc",
 	},
 	.probe = mtk_adsp_ipc_probe,
-	.remove = mtk_adsp_ipc_remove,
+	.remove_new = mtk_adsp_ipc_remove,
 };
 builtin_platform_driver(mtk_adsp_ipc_driver);
 
diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c
index 1448f61173b3..03da9a4354f8 100644
--- a/drivers/firmware/qemu_fw_cfg.c
+++ b/drivers/firmware/qemu_fw_cfg.c
@@ -731,7 +731,7 @@ err_sel:
 	return err;
 }
 
-static int fw_cfg_sysfs_remove(struct platform_device *pdev)
+static void fw_cfg_sysfs_remove(struct platform_device *pdev)
 {
 	pr_debug("fw_cfg: unloading.\n");
 	fw_cfg_sysfs_cache_cleanup();
@@ -739,7 +739,6 @@ static int fw_cfg_sysfs_remove(struct platform_device *pdev)
 	fw_cfg_io_cleanup();
 	fw_cfg_kset_unregister_recursive(fw_cfg_fname_kset);
 	fw_cfg_kobj_cleanup(fw_cfg_sel_ko);
-	return 0;
 }
 
 static const struct of_device_id fw_cfg_sysfs_mmio_match[] = {
@@ -758,7 +757,7 @@ MODULE_DEVICE_TABLE(acpi, fw_cfg_sysfs_acpi_match);
 
 static struct platform_driver fw_cfg_sysfs_driver = {
 	.probe = fw_cfg_sysfs_probe,
-	.remove = fw_cfg_sysfs_remove,
+	.remove_new = fw_cfg_sysfs_remove,
 	.driver = {
 		.name = "fw_cfg",
 		.of_match_table = fw_cfg_sysfs_mmio_match,
diff --git a/drivers/firmware/raspberrypi.c b/drivers/firmware/raspberrypi.c
index 4cd290a60fba..322aada20f74 100644
--- a/drivers/firmware/raspberrypi.c
+++ b/drivers/firmware/raspberrypi.c
@@ -317,7 +317,7 @@ static void rpi_firmware_shutdown(struct platform_device *pdev)
 	rpi_firmware_property(fw, RPI_FIRMWARE_NOTIFY_REBOOT, NULL, 0);
 }
 
-static int rpi_firmware_remove(struct platform_device *pdev)
+static void rpi_firmware_remove(struct platform_device *pdev)
 {
 	struct rpi_firmware *fw = platform_get_drvdata(pdev);
 
@@ -327,8 +327,6 @@ static int rpi_firmware_remove(struct platform_device *pdev)
 	rpi_clk = NULL;
 
 	rpi_firmware_put(fw);
-
-	return 0;
 }
 
 static const struct of_device_id rpi_firmware_of_match[] = {
@@ -406,7 +404,7 @@ static struct platform_driver rpi_firmware_driver = {
 	},
 	.probe		= rpi_firmware_probe,
 	.shutdown	= rpi_firmware_shutdown,
-	.remove		= rpi_firmware_remove,
+	.remove_new	= rpi_firmware_remove,
 };
 module_platform_driver(rpi_firmware_driver);
 
diff --git a/drivers/firmware/stratix10-rsu.c b/drivers/firmware/stratix10-rsu.c
index 4f7a7abada48..e20cee9c2d32 100644
--- a/drivers/firmware/stratix10-rsu.c
+++ b/drivers/firmware/stratix10-rsu.c
@@ -793,17 +793,16 @@ static int stratix10_rsu_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int stratix10_rsu_remove(struct platform_device *pdev)
+static void stratix10_rsu_remove(struct platform_device *pdev)
 {
 	struct stratix10_rsu_priv *priv = platform_get_drvdata(pdev);
 
 	stratix10_svc_free_channel(priv->chan);
-	return 0;
 }
 
 static struct platform_driver stratix10_rsu_driver = {
 	.probe = stratix10_rsu_probe,
-	.remove = stratix10_rsu_remove,
+	.remove_new = stratix10_rsu_remove,
 	.driver = {
 		.name = "stratix10-rsu",
 		.dev_groups = rsu_groups,
diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c
index c693da60e9a9..528f37417aea 100644
--- a/drivers/firmware/stratix10-svc.c
+++ b/drivers/firmware/stratix10-svc.c
@@ -1251,7 +1251,7 @@ err_destroy_pool:
 	return ret;
 }
 
-static int stratix10_svc_drv_remove(struct platform_device *pdev)
+static void stratix10_svc_drv_remove(struct platform_device *pdev)
 {
 	struct stratix10_svc *svc = dev_get_drvdata(&pdev->dev);
 	struct stratix10_svc_controller *ctrl = platform_get_drvdata(pdev);
@@ -1267,13 +1267,11 @@ static int stratix10_svc_drv_remove(struct platform_device *pdev)
 	if (ctrl->genpool)
 		gen_pool_destroy(ctrl->genpool);
 	list_del(&ctrl->node);
-
-	return 0;
 }
 
 static struct platform_driver stratix10_svc_driver = {
 	.probe = stratix10_svc_drv_probe,
-	.remove = stratix10_svc_drv_remove,
+	.remove_new = stratix10_svc_drv_remove,
 	.driver = {
 		.name = "stratix10-svc",
 		.of_match_table = stratix10_svc_drv_match,
diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c
index 19706bd2642a..3c197db42c9d 100644
--- a/drivers/firmware/sysfb.c
+++ b/drivers/firmware/sysfb.c
@@ -71,7 +71,7 @@ EXPORT_SYMBOL_GPL(sysfb_disable);
 
 static __init int sysfb_init(void)
 {
-	const struct screen_info *si = &screen_info;
+	struct screen_info *si = &screen_info;
 	struct simplefb_platform_data mode;
 	const char *name;
 	bool compatible;
@@ -119,18 +119,6 @@ static __init int sysfb_init(void)
 	if (ret)
 		goto err;
 
-	/*
-	 * The firmware framebuffer is now maintained by the created
-	 * device. Disable screen_info after we've consumed it. Prevents
-	 * invalid access during kexec reboots.
-	 *
-	 * TODO: Vgacon still relies on the global screen_info. Make
-	 *       vgacon work with the platform device, so we can clear
-	 *       the screen_info unconditionally.
-	 */
-	if (strcmp(name, "platform-framebuffer"))
-		screen_info.orig_video_isVGA = 0;
-
 	goto unlock_mutex;
 err:
 	platform_device_put(pd);
@@ -140,4 +128,4 @@ unlock_mutex:
 }
 
 /* must execute after PCI subsystem for EFI quirks */
-subsys_initcall_sync(sysfb_init);
+device_initcall(sysfb_init);
diff --git a/drivers/firmware/turris-mox-rwtm.c b/drivers/firmware/turris-mox-rwtm.c
index 2de0fb139ce1..31d962cdd6eb 100644
--- a/drivers/firmware/turris-mox-rwtm.c
+++ b/drivers/firmware/turris-mox-rwtm.c
@@ -554,7 +554,7 @@ put_kobj:
 	return ret;
 }
 
-static int turris_mox_rwtm_remove(struct platform_device *pdev)
+static void turris_mox_rwtm_remove(struct platform_device *pdev)
 {
 	struct mox_rwtm *rwtm = platform_get_drvdata(pdev);
 
@@ -562,8 +562,6 @@ static int turris_mox_rwtm_remove(struct platform_device *pdev)
 	sysfs_remove_files(rwtm_to_kobj(rwtm), mox_rwtm_attrs);
 	kobject_put(rwtm_to_kobj(rwtm));
 	mbox_free_channel(rwtm->mbox);
-
-	return 0;
 }
 
 static const struct of_device_id turris_mox_rwtm_match[] = {
@@ -576,7 +574,7 @@ MODULE_DEVICE_TABLE(of, turris_mox_rwtm_match);
 
 static struct platform_driver turris_mox_rwtm_driver = {
 	.probe	= turris_mox_rwtm_probe,
-	.remove	= turris_mox_rwtm_remove,
+	.remove_new = turris_mox_rwtm_remove,
 	.driver	= {
 		.name		= DRIVER_NAME,
 		.of_match_table	= turris_mox_rwtm_match,
diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index b0d22d4455d9..79789f0563f6 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -92,6 +92,8 @@ static int zynqmp_pm_ret_code(u32 ret_status)
 		return 0;
 	case XST_PM_NO_FEATURE:
 		return -ENOTSUPP;
+	case XST_PM_INVALID_VERSION:
+		return -EOPNOTSUPP;
 	case XST_PM_NO_ACCESS:
 		return -EACCES;
 	case XST_PM_ABORT_SUSPEND:
@@ -101,13 +103,13 @@ static int zynqmp_pm_ret_code(u32 ret_status)
 	case XST_PM_INTERNAL:
 	case XST_PM_CONFLICT:
 	case XST_PM_INVALID_NODE:
+	case XST_PM_INVALID_CRC:
 	default:
 		return -EINVAL;
 	}
 }
 
-static noinline int do_fw_call_fail(u64 arg0, u64 arg1, u64 arg2,
-				    u32 *ret_payload)
+static noinline int do_fw_call_fail(u32 *ret_payload, u32 num_args, ...)
 {
 	return -ENODEV;
 }
@@ -116,25 +118,35 @@ static noinline int do_fw_call_fail(u64 arg0, u64 arg1, u64 arg2,
  * PM function call wrapper
  * Invoke do_fw_call_smc or do_fw_call_hvc, depending on the configuration
  */
-static int (*do_fw_call)(u64, u64, u64, u32 *ret_payload) = do_fw_call_fail;
+static int (*do_fw_call)(u32 *ret_payload, u32, ...) = do_fw_call_fail;
 
 /**
  * do_fw_call_smc() - Call system-level platform management layer (SMC)
- * @arg0:		Argument 0 to SMC call
- * @arg1:		Argument 1 to SMC call
- * @arg2:		Argument 2 to SMC call
+ * @num_args:		Number of variable arguments should be <= 8
  * @ret_payload:	Returned value array
  *
  * Invoke platform management function via SMC call (no hypervisor present).
  *
  * Return: Returns status, either success or error+reason
  */
-static noinline int do_fw_call_smc(u64 arg0, u64 arg1, u64 arg2,
-				   u32 *ret_payload)
+static noinline int do_fw_call_smc(u32 *ret_payload, u32 num_args, ...)
 {
 	struct arm_smccc_res res;
+	u64 args[8] = {0};
+	va_list arg_list;
+	u8 i;
 
-	arm_smccc_smc(arg0, arg1, arg2, 0, 0, 0, 0, 0, &res);
+	if (num_args > 8)
+		return -EINVAL;
+
+	va_start(arg_list, num_args);
+
+	for (i = 0; i < num_args; i++)
+		args[i] = va_arg(arg_list, u64);
+
+	va_end(arg_list);
+
+	arm_smccc_smc(args[0], args[1], args[2], args[3], args[4], args[5], args[6], args[7], &res);
 
 	if (ret_payload) {
 		ret_payload[0] = lower_32_bits(res.a0);
@@ -148,9 +160,7 @@ static noinline int do_fw_call_smc(u64 arg0, u64 arg1, u64 arg2,
 
 /**
  * do_fw_call_hvc() - Call system-level platform management layer (HVC)
- * @arg0:		Argument 0 to HVC call
- * @arg1:		Argument 1 to HVC call
- * @arg2:		Argument 2 to HVC call
+ * @num_args:		Number of variable arguments should be <= 8
  * @ret_payload:	Returned value array
  *
  * Invoke platform management function via HVC
@@ -159,12 +169,24 @@ static noinline int do_fw_call_smc(u64 arg0, u64 arg1, u64 arg2,
  *
  * Return: Returns status, either success or error+reason
  */
-static noinline int do_fw_call_hvc(u64 arg0, u64 arg1, u64 arg2,
-				   u32 *ret_payload)
+static noinline int do_fw_call_hvc(u32 *ret_payload, u32 num_args, ...)
 {
 	struct arm_smccc_res res;
+	u64 args[8] = {0};
+	va_list arg_list;
+	u8 i;
+
+	if (num_args > 8)
+		return -EINVAL;
+
+	va_start(arg_list, num_args);
+
+	for (i = 0; i < num_args; i++)
+		args[i] = va_arg(arg_list, u64);
+
+	va_end(arg_list);
 
-	arm_smccc_hvc(arg0, arg1, arg2, 0, 0, 0, 0, 0, &res);
+	arm_smccc_hvc(args[0], args[1], args[2], args[3], args[4], args[5], args[6], args[7], &res);
 
 	if (ret_payload) {
 		ret_payload[0] = lower_32_bits(res.a0);
@@ -180,11 +202,31 @@ static int __do_feature_check_call(const u32 api_id, u32 *ret_payload)
 {
 	int ret;
 	u64 smc_arg[2];
+	u32 module_id;
+	u32 feature_check_api_id;
 
-	smc_arg[0] = PM_SIP_SVC | PM_FEATURE_CHECK;
-	smc_arg[1] = api_id;
+	module_id = FIELD_GET(MODULE_ID_MASK, api_id);
 
-	ret = do_fw_call(smc_arg[0], smc_arg[1], 0, ret_payload);
+	/*
+	 * Feature check of APIs belonging to PM, XSEM, and TF-A are handled by calling
+	 * PM_FEATURE_CHECK API. For other modules, call PM_API_FEATURES API.
+	 */
+	if (module_id == PM_MODULE_ID || module_id == XSEM_MODULE_ID || module_id == TF_A_MODULE_ID)
+		feature_check_api_id = PM_FEATURE_CHECK;
+	else
+		feature_check_api_id = PM_API_FEATURES;
+
+	/*
+	 * Feature check of TF-A APIs is done in the TF-A layer and it expects for
+	 * MODULE_ID_MASK bits of SMC's arg[0] to be the same as PM_MODULE_ID.
+	 */
+	if (module_id == TF_A_MODULE_ID)
+		module_id = PM_MODULE_ID;
+
+	smc_arg[0] = PM_SIP_SVC | FIELD_PREP(MODULE_ID_MASK, module_id) | feature_check_api_id;
+	smc_arg[1] = (api_id & API_ID_MASK);
+
+	ret = do_fw_call(ret_payload, 2, smc_arg[0], smc_arg[1]);
 	if (ret)
 		ret = -EOPNOTSUPP;
 	else
@@ -295,11 +337,8 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_is_function_supported);
  * zynqmp_pm_invoke_fn() - Invoke the system-level platform management layer
  *			   caller function depending on the configuration
  * @pm_api_id:		Requested PM-API call
- * @arg0:		Argument 0 to requested PM-API call
- * @arg1:		Argument 1 to requested PM-API call
- * @arg2:		Argument 2 to requested PM-API call
- * @arg3:		Argument 3 to requested PM-API call
  * @ret_payload:	Returned value array
+ * @num_args:		Number of arguments to requested PM-API call
  *
  * Invoke platform management function for SMC or HVC call, depending on
  * configuration.
@@ -316,26 +355,38 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_is_function_supported);
  *
  * Return: Returns status, either success or error+reason
  */
-int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1,
-			u32 arg2, u32 arg3, u32 *ret_payload)
+int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 *ret_payload, u32 num_args, ...)
 {
 	/*
 	 * Added SIP service call Function Identifier
 	 * Make sure to stay in x0 register
 	 */
-	u64 smc_arg[4];
-	int ret;
+	u64 smc_arg[8];
+	int ret, i;
+	va_list arg_list;
+	u32 args[14] = {0};
+
+	if (num_args > 14)
+		return -EINVAL;
+
+	va_start(arg_list, num_args);
 
 	/* Check if feature is supported or not */
 	ret = zynqmp_pm_feature(pm_api_id);
 	if (ret < 0)
 		return ret;
 
+	for (i = 0; i < num_args; i++)
+		args[i] = va_arg(arg_list, u32);
+
+	va_end(arg_list);
+
 	smc_arg[0] = PM_SIP_SVC | pm_api_id;
-	smc_arg[1] = ((u64)arg1 << 32) | arg0;
-	smc_arg[2] = ((u64)arg3 << 32) | arg2;
+	for (i = 0; i < 7; i++)
+		smc_arg[i + 1] = ((u64)args[(i * 2) + 1] << 32) | args[i * 2];
 
-	return do_fw_call(smc_arg[0], smc_arg[1], smc_arg[2], ret_payload);
+	return do_fw_call(ret_payload, 8, smc_arg[0], smc_arg[1], smc_arg[2], smc_arg[3],
+			  smc_arg[4], smc_arg[5], smc_arg[6], smc_arg[7]);
 }
 
 static u32 pm_api_version;
@@ -347,14 +398,12 @@ int zynqmp_pm_register_sgi(u32 sgi_num, u32 reset)
 {
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(TF_A_PM_REGISTER_SGI, sgi_num, reset, 0, 0,
-				  NULL);
-	if (!ret)
+	ret = zynqmp_pm_invoke_fn(TF_A_PM_REGISTER_SGI, NULL, 2, sgi_num, reset);
+	if (ret != -EOPNOTSUPP && !ret)
 		return ret;
 
 	/* try old implementation as fallback strategy if above fails */
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_REGISTER_SGI, sgi_num,
-				   reset, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 3, IOCTL_REGISTER_SGI, sgi_num, reset);
 }
 
 /**
@@ -376,7 +425,7 @@ int zynqmp_pm_get_api_version(u32 *version)
 		*version = pm_api_version;
 		return 0;
 	}
-	ret = zynqmp_pm_invoke_fn(PM_GET_API_VERSION, 0, 0, 0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_GET_API_VERSION, ret_payload, 0);
 	*version = ret_payload[1];
 
 	return ret;
@@ -399,7 +448,7 @@ int zynqmp_pm_get_chipid(u32 *idcode, u32 *version)
 	if (!idcode || !version)
 		return -EINVAL;
 
-	ret = zynqmp_pm_invoke_fn(PM_GET_CHIPID, 0, 0, 0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_GET_CHIPID, ret_payload, 0);
 	*idcode = ret_payload[1];
 	*version = ret_payload[2];
 
@@ -414,7 +463,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_get_chipid);
  *
  * Return: Returns status, either success or error+reason
  */
-static int zynqmp_pm_get_family_info(u32 *family, u32 *subfamily)
+int zynqmp_pm_get_family_info(u32 *family, u32 *subfamily)
 {
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	u32 idcode;
@@ -427,7 +476,7 @@ static int zynqmp_pm_get_family_info(u32 *family, u32 *subfamily)
 		return 0;
 	}
 
-	ret = zynqmp_pm_invoke_fn(PM_GET_CHIPID, 0, 0, 0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_GET_CHIPID, ret_payload, 0);
 	if (ret < 0)
 		return ret;
 
@@ -439,6 +488,7 @@ static int zynqmp_pm_get_family_info(u32 *family, u32 *subfamily)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(zynqmp_pm_get_family_info);
 
 /**
  * zynqmp_pm_get_trustzone_version() - Get secure trustzone firmware version
@@ -459,8 +509,7 @@ static int zynqmp_pm_get_trustzone_version(u32 *version)
 		*version = pm_tz_version;
 		return 0;
 	}
-	ret = zynqmp_pm_invoke_fn(PM_GET_TRUSTZONE_VERSION, 0, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_GET_TRUSTZONE_VERSION, ret_payload, 0);
 	*version = ret_payload[1];
 
 	return ret;
@@ -507,8 +556,8 @@ int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out)
 {
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(PM_QUERY_DATA, qdata.qid, qdata.arg1,
-				  qdata.arg2, qdata.arg3, out);
+	ret = zynqmp_pm_invoke_fn(PM_QUERY_DATA, out, 4, qdata.qid, qdata.arg1, qdata.arg2,
+				  qdata.arg3);
 
 	/*
 	 * For clock name query, all bytes in SMC response are clock name
@@ -530,7 +579,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_query_data);
  */
 int zynqmp_pm_clock_enable(u32 clock_id)
 {
-	return zynqmp_pm_invoke_fn(PM_CLOCK_ENABLE, clock_id, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_CLOCK_ENABLE, NULL, 1, clock_id);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_clock_enable);
 
@@ -545,7 +594,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_clock_enable);
  */
 int zynqmp_pm_clock_disable(u32 clock_id)
 {
-	return zynqmp_pm_invoke_fn(PM_CLOCK_DISABLE, clock_id, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_CLOCK_DISABLE, NULL, 1, clock_id);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_clock_disable);
 
@@ -564,8 +613,7 @@ int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state)
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETSTATE, clock_id, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETSTATE, ret_payload, 1, clock_id);
 	*state = ret_payload[1];
 
 	return ret;
@@ -584,8 +632,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_clock_getstate);
  */
 int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider)
 {
-	return zynqmp_pm_invoke_fn(PM_CLOCK_SETDIVIDER, clock_id, divider,
-				   0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_CLOCK_SETDIVIDER, NULL, 2, clock_id, divider);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_clock_setdivider);
 
@@ -604,8 +651,7 @@ int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider)
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETDIVIDER, clock_id, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETDIVIDER, ret_payload, 1, clock_id);
 	*divider = ret_payload[1];
 
 	return ret;
@@ -613,47 +659,6 @@ int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider)
 EXPORT_SYMBOL_GPL(zynqmp_pm_clock_getdivider);
 
 /**
- * zynqmp_pm_clock_setrate() - Set the clock rate for given id
- * @clock_id:	ID of the clock
- * @rate:	rate value in hz
- *
- * This function is used by master to set rate for any clock.
- *
- * Return: Returns status, either success or error+reason
- */
-int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate)
-{
-	return zynqmp_pm_invoke_fn(PM_CLOCK_SETRATE, clock_id,
-				   lower_32_bits(rate),
-				   upper_32_bits(rate),
-				   0, NULL);
-}
-EXPORT_SYMBOL_GPL(zynqmp_pm_clock_setrate);
-
-/**
- * zynqmp_pm_clock_getrate() - Get the clock rate for given id
- * @clock_id:	ID of the clock
- * @rate:	rate value in hz
- *
- * This function is used by master to get rate
- * for any clock.
- *
- * Return: Returns status, either success or error+reason
- */
-int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate)
-{
-	u32 ret_payload[PAYLOAD_ARG_CNT];
-	int ret;
-
-	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETRATE, clock_id, 0,
-				  0, 0, ret_payload);
-	*rate = ((u64)ret_payload[2] << 32) | ret_payload[1];
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(zynqmp_pm_clock_getrate);
-
-/**
  * zynqmp_pm_clock_setparent() - Set the clock parent for given id
  * @clock_id:	ID of the clock
  * @parent_id:	parent id
@@ -664,8 +669,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_clock_getrate);
  */
 int zynqmp_pm_clock_setparent(u32 clock_id, u32 parent_id)
 {
-	return zynqmp_pm_invoke_fn(PM_CLOCK_SETPARENT, clock_id,
-				   parent_id, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_CLOCK_SETPARENT, NULL, 2, clock_id, parent_id);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_clock_setparent);
 
@@ -684,8 +688,7 @@ int zynqmp_pm_clock_getparent(u32 clock_id, u32 *parent_id)
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETPARENT, clock_id, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETPARENT, ret_payload, 1, clock_id);
 	*parent_id = ret_payload[1];
 
 	return ret;
@@ -704,8 +707,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_clock_getparent);
  */
 int zynqmp_pm_set_pll_frac_mode(u32 clk_id, u32 mode)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_SET_PLL_FRAC_MODE,
-				   clk_id, mode, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, 0, IOCTL_SET_PLL_FRAC_MODE, clk_id, mode);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_pll_frac_mode);
 
@@ -721,8 +723,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_pll_frac_mode);
  */
 int zynqmp_pm_get_pll_frac_mode(u32 clk_id, u32 *mode)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_GET_PLL_FRAC_MODE,
-				   clk_id, 0, mode);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, mode, 3, 0, IOCTL_GET_PLL_FRAC_MODE, clk_id);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_get_pll_frac_mode);
 
@@ -739,8 +740,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_get_pll_frac_mode);
  */
 int zynqmp_pm_set_pll_frac_data(u32 clk_id, u32 data)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_SET_PLL_FRAC_DATA,
-				   clk_id, data, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, 0, IOCTL_SET_PLL_FRAC_DATA, clk_id, data);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_pll_frac_data);
 
@@ -756,8 +756,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_pll_frac_data);
  */
 int zynqmp_pm_get_pll_frac_data(u32 clk_id, u32 *data)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_GET_PLL_FRAC_DATA,
-				   clk_id, 0, data);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, data, 3, 0, IOCTL_GET_PLL_FRAC_DATA, clk_id);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_get_pll_frac_data);
 
@@ -778,9 +777,8 @@ int zynqmp_pm_set_sd_tapdelay(u32 node_id, u32 type, u32 value)
 	u32 mask = (node_id == NODE_SD_0) ? GENMASK(15, 0) : GENMASK(31, 16);
 
 	if (value) {
-		return zynqmp_pm_invoke_fn(PM_IOCTL, node_id,
-					   IOCTL_SET_SD_TAPDELAY,
-					   type, value, NULL);
+		return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, node_id, IOCTL_SET_SD_TAPDELAY, type,
+					   value);
 	}
 
 	/*
@@ -798,7 +796,7 @@ int zynqmp_pm_set_sd_tapdelay(u32 node_id, u32 type, u32 value)
 	 * Use PM_MMIO_READ/PM_MMIO_WRITE to re-implement the missing counter
 	 * part of IOCTL_SET_SD_TAPDELAY which clears SDx_ITAPDLYENA bits.
 	 */
-	return zynqmp_pm_invoke_fn(PM_MMIO_WRITE, reg, mask, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_MMIO_WRITE, NULL, 2, reg, mask);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_sd_tapdelay);
 
@@ -814,8 +812,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_sd_tapdelay);
  */
 int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, node_id, IOCTL_SD_DLL_RESET,
-				   type, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 3, node_id, IOCTL_SD_DLL_RESET, type);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_sd_dll_reset);
 
@@ -831,8 +828,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_sd_dll_reset);
  */
 int zynqmp_pm_ospi_mux_select(u32 dev_id, u32 select)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, dev_id, IOCTL_OSPI_MUX_SELECT,
-				   select, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 3, dev_id, IOCTL_OSPI_MUX_SELECT, select);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_ospi_mux_select);
 
@@ -847,8 +843,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_ospi_mux_select);
  */
 int zynqmp_pm_write_ggs(u32 index, u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_WRITE_GGS,
-				   index, value, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, 0, IOCTL_WRITE_GGS, index, value);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_write_ggs);
 
@@ -863,8 +858,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_write_ggs);
  */
 int zynqmp_pm_read_ggs(u32 index, u32 *value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_READ_GGS,
-				   index, 0, value);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, value, 3, 0, IOCTL_READ_GGS, index);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_read_ggs);
 
@@ -880,8 +874,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_read_ggs);
  */
 int zynqmp_pm_write_pggs(u32 index, u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_WRITE_PGGS, index, value,
-				   NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, 0, IOCTL_WRITE_PGGS, index, value);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_write_pggs);
 
@@ -897,15 +890,13 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_write_pggs);
  */
 int zynqmp_pm_read_pggs(u32 index, u32 *value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_READ_PGGS, index, 0,
-				   value);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, value, 3, 0, IOCTL_READ_PGGS, index);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_read_pggs);
 
 int zynqmp_pm_set_tapdelay_bypass(u32 index, u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_SET_TAPDELAY_BYPASS,
-				   index, value, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, 0, IOCTL_SET_TAPDELAY_BYPASS, index, value);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_tapdelay_bypass);
 
@@ -920,8 +911,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_tapdelay_bypass);
  */
 int zynqmp_pm_set_boot_health_status(u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_SET_BOOT_HEALTH_STATUS,
-				   value, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 3, 0, IOCTL_SET_BOOT_HEALTH_STATUS, value);
 }
 
 /**
@@ -935,8 +925,7 @@ int zynqmp_pm_set_boot_health_status(u32 value)
 int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset,
 			   const enum zynqmp_pm_reset_action assert_flag)
 {
-	return zynqmp_pm_invoke_fn(PM_RESET_ASSERT, reset, assert_flag,
-				   0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_RESET_ASSERT, NULL, 2, reset, assert_flag);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_reset_assert);
 
@@ -955,8 +944,7 @@ int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, u32 *status)
 	if (!status)
 		return -EINVAL;
 
-	ret = zynqmp_pm_invoke_fn(PM_RESET_GET_STATUS, reset, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_RESET_GET_STATUS, ret_payload, 1, reset);
 	*status = ret_payload[1];
 
 	return ret;
@@ -981,9 +969,8 @@ int zynqmp_pm_fpga_load(const u64 address, const u32 size, const u32 flags)
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(PM_FPGA_LOAD, lower_32_bits(address),
-				  upper_32_bits(address), size, flags,
-				  ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_FPGA_LOAD, ret_payload, 4, lower_32_bits(address),
+				  upper_32_bits(address), size, flags);
 	if (ret_payload[0])
 		return -ret_payload[0];
 
@@ -1008,7 +995,7 @@ int zynqmp_pm_fpga_get_status(u32 *value)
 	if (!value)
 		return -EINVAL;
 
-	ret = zynqmp_pm_invoke_fn(PM_FPGA_GET_STATUS, 0, 0, 0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_FPGA_GET_STATUS, ret_payload, 0);
 	*value = ret_payload[1];
 
 	return ret;
@@ -1036,11 +1023,9 @@ int zynqmp_pm_fpga_get_config_status(u32 *value)
 	lower_addr = lower_32_bits((u64)&buf);
 	upper_addr = upper_32_bits((u64)&buf);
 
-	ret = zynqmp_pm_invoke_fn(PM_FPGA_READ,
-				  XILINX_ZYNQMP_PM_FPGA_CONFIG_STAT_OFFSET,
-				  lower_addr, upper_addr,
-				  XILINX_ZYNQMP_PM_FPGA_READ_CONFIG_REG,
-				  ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_FPGA_READ, ret_payload, 4,
+				  XILINX_ZYNQMP_PM_FPGA_CONFIG_STAT_OFFSET, lower_addr, upper_addr,
+				  XILINX_ZYNQMP_PM_FPGA_READ_CONFIG_REG);
 
 	*value = ret_payload[1];
 
@@ -1058,7 +1043,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_fpga_get_config_status);
  */
 int zynqmp_pm_pinctrl_request(const u32 pin)
 {
-	return zynqmp_pm_invoke_fn(PM_PINCTRL_REQUEST, pin, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_PINCTRL_REQUEST, NULL, 1, pin);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_request);
 
@@ -1072,36 +1057,11 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_request);
  */
 int zynqmp_pm_pinctrl_release(const u32 pin)
 {
-	return zynqmp_pm_invoke_fn(PM_PINCTRL_RELEASE, pin, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_PINCTRL_RELEASE, NULL, 1, pin);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_release);
 
 /**
- * zynqmp_pm_pinctrl_get_function - Read function id set for the given pin
- * @pin: Pin number
- * @id: Buffer to store function ID
- *
- * This function provides the function currently set for the given pin.
- *
- * Return: Returns status, either success or error+reason
- */
-int zynqmp_pm_pinctrl_get_function(const u32 pin, u32 *id)
-{
-	u32 ret_payload[PAYLOAD_ARG_CNT];
-	int ret;
-
-	if (!id)
-		return -EINVAL;
-
-	ret = zynqmp_pm_invoke_fn(PM_PINCTRL_GET_FUNCTION, pin, 0,
-				  0, 0, ret_payload);
-	*id = ret_payload[1];
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_get_function);
-
-/**
  * zynqmp_pm_pinctrl_set_function - Set requested function for the pin
  * @pin: Pin number
  * @id: Function ID to set
@@ -1112,8 +1072,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_get_function);
  */
 int zynqmp_pm_pinctrl_set_function(const u32 pin, const u32 id)
 {
-	return zynqmp_pm_invoke_fn(PM_PINCTRL_SET_FUNCTION, pin, id,
-				   0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_PINCTRL_SET_FUNCTION, NULL, 2, pin, id);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_set_function);
 
@@ -1136,8 +1095,7 @@ int zynqmp_pm_pinctrl_get_config(const u32 pin, const u32 param,
 	if (!value)
 		return -EINVAL;
 
-	ret = zynqmp_pm_invoke_fn(PM_PINCTRL_CONFIG_PARAM_GET, pin, param,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_PINCTRL_CONFIG_PARAM_GET, ret_payload, 2, pin, param);
 	*value = ret_payload[1];
 
 	return ret;
@@ -1166,8 +1124,7 @@ int zynqmp_pm_pinctrl_set_config(const u32 pin, const u32 param,
 			return -EOPNOTSUPP;
 	}
 
-	return zynqmp_pm_invoke_fn(PM_PINCTRL_CONFIG_PARAM_SET, pin,
-				   param, value, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_PINCTRL_CONFIG_PARAM_SET, NULL, 3, pin, param, value);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_set_config);
 
@@ -1185,8 +1142,7 @@ unsigned int zynqmp_pm_bootmode_read(u32 *ps_mode)
 	unsigned int ret;
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 
-	ret = zynqmp_pm_invoke_fn(PM_MMIO_READ, CRL_APB_BOOT_PIN_CTRL, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_MMIO_READ, ret_payload, 1, CRL_APB_BOOT_PIN_CTRL);
 
 	*ps_mode = ret_payload[1];
 
@@ -1205,8 +1161,8 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_bootmode_read);
  */
 int zynqmp_pm_bootmode_write(u32 ps_mode)
 {
-	return zynqmp_pm_invoke_fn(PM_MMIO_WRITE, CRL_APB_BOOT_PIN_CTRL,
-				   CRL_APB_BOOTPIN_CTRL_MASK, ps_mode, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_MMIO_WRITE, NULL, 3, CRL_APB_BOOT_PIN_CTRL,
+				   CRL_APB_BOOTPIN_CTRL_MASK, ps_mode);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_bootmode_write);
 
@@ -1221,7 +1177,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_bootmode_write);
  */
 int zynqmp_pm_init_finalize(void)
 {
-	return zynqmp_pm_invoke_fn(PM_PM_INIT_FINALIZE, 0, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_PM_INIT_FINALIZE, NULL, 0);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_init_finalize);
 
@@ -1235,7 +1191,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_init_finalize);
  */
 int zynqmp_pm_set_suspend_mode(u32 mode)
 {
-	return zynqmp_pm_invoke_fn(PM_SET_SUSPEND_MODE, mode, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_SET_SUSPEND_MODE, NULL, 1, mode);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_suspend_mode);
 
@@ -1254,8 +1210,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_suspend_mode);
 int zynqmp_pm_request_node(const u32 node, const u32 capabilities,
 			   const u32 qos, const enum zynqmp_pm_request_ack ack)
 {
-	return zynqmp_pm_invoke_fn(PM_REQUEST_NODE, node, capabilities,
-				   qos, ack, NULL);
+	return zynqmp_pm_invoke_fn(PM_REQUEST_NODE, NULL, 4, node, capabilities, qos, ack);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_request_node);
 
@@ -1271,7 +1226,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_request_node);
  */
 int zynqmp_pm_release_node(const u32 node)
 {
-	return zynqmp_pm_invoke_fn(PM_RELEASE_NODE, node, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_RELEASE_NODE, NULL, 1, node);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_release_node);
 
@@ -1290,8 +1245,7 @@ int zynqmp_pm_get_rpu_mode(u32 node_id, enum rpu_oper_mode *rpu_mode)
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(PM_IOCTL, node_id,
-				  IOCTL_GET_RPU_OPER_MODE, 0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_IOCTL, ret_payload, 2, node_id, IOCTL_GET_RPU_OPER_MODE);
 
 	/* only set rpu_mode if no error */
 	if (ret == XST_PM_SUCCESS)
@@ -1313,9 +1267,8 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_get_rpu_mode);
  */
 int zynqmp_pm_set_rpu_mode(u32 node_id, enum rpu_oper_mode rpu_mode)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, node_id,
-				   IOCTL_SET_RPU_OPER_MODE, (u32)rpu_mode,
-				   0, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 3, node_id, IOCTL_SET_RPU_OPER_MODE,
+				   (u32)rpu_mode);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_rpu_mode);
 
@@ -1331,9 +1284,8 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_rpu_mode);
  */
 int zynqmp_pm_set_tcm_config(u32 node_id, enum rpu_tcm_comb tcm_mode)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, node_id,
-				   IOCTL_TCM_COMB_CONFIG, (u32)tcm_mode, 0,
-				   NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 3, node_id, IOCTL_TCM_COMB_CONFIG,
+				   (u32)tcm_mode);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_tcm_config);
 
@@ -1348,7 +1300,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_tcm_config);
 int zynqmp_pm_force_pwrdwn(const u32 node,
 			   const enum zynqmp_pm_request_ack ack)
 {
-	return zynqmp_pm_invoke_fn(PM_FORCE_POWERDOWN, node, ack, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_FORCE_POWERDOWN, NULL, 2, node, ack);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_force_pwrdwn);
 
@@ -1367,8 +1319,8 @@ int zynqmp_pm_request_wake(const u32 node,
 			   const enum zynqmp_pm_request_ack ack)
 {
 	/* set_addr flag is encoded into 1st bit of address */
-	return zynqmp_pm_invoke_fn(PM_REQUEST_WAKEUP, node, address | set_addr,
-				   address >> 32, ack, NULL);
+	return zynqmp_pm_invoke_fn(PM_REQUEST_WAKEUP, NULL, 4, node, address | set_addr,
+				   address >> 32, ack);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_request_wake);
 
@@ -1388,15 +1340,14 @@ int zynqmp_pm_set_requirement(const u32 node, const u32 capabilities,
 			      const u32 qos,
 			      const enum zynqmp_pm_request_ack ack)
 {
-	return zynqmp_pm_invoke_fn(PM_SET_REQUIREMENT, node, capabilities,
-				   qos, ack, NULL);
+	return zynqmp_pm_invoke_fn(PM_SET_REQUIREMENT, NULL, 4, node, capabilities, qos, ack);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_requirement);
 
 /**
  * zynqmp_pm_load_pdi - Load and process PDI
- * @src:       Source device where PDI is located
- * @address:   PDI src address
+ * @src:	Source device where PDI is located
+ * @address:	PDI src address
  *
  * This function provides support to load PDI from linux
  *
@@ -1404,9 +1355,8 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_requirement);
  */
 int zynqmp_pm_load_pdi(const u32 src, const u64 address)
 {
-	return zynqmp_pm_invoke_fn(PM_LOAD_PDI, src,
-				   lower_32_bits(address),
-				   upper_32_bits(address), 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_LOAD_PDI, NULL, 3, src, lower_32_bits(address),
+				   upper_32_bits(address));
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_load_pdi);
 
@@ -1426,9 +1376,8 @@ int zynqmp_pm_aes_engine(const u64 address, u32 *out)
 	if (!out)
 		return -EINVAL;
 
-	ret = zynqmp_pm_invoke_fn(PM_SECURE_AES, upper_32_bits(address),
-				  lower_32_bits(address),
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_SECURE_AES, ret_payload, 2, upper_32_bits(address),
+				  lower_32_bits(address));
 	*out = ret_payload[1];
 
 	return ret;
@@ -1456,8 +1405,7 @@ int zynqmp_pm_sha_hash(const u64 address, const u32 size, const u32 flags)
 	u32 lower_addr = lower_32_bits(address);
 	u32 upper_addr = upper_32_bits(address);
 
-	return zynqmp_pm_invoke_fn(PM_SECURE_SHA, upper_addr, lower_addr,
-				   size, flags, NULL);
+	return zynqmp_pm_invoke_fn(PM_SECURE_SHA, NULL, 4, upper_addr, lower_addr, size, flags);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_sha_hash);
 
@@ -1479,8 +1427,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_sha_hash);
 int zynqmp_pm_register_notifier(const u32 node, const u32 event,
 				const u32 wake, const u32 enable)
 {
-	return zynqmp_pm_invoke_fn(PM_REGISTER_NOTIFIER, node, event,
-				   wake, enable, NULL);
+	return zynqmp_pm_invoke_fn(PM_REGISTER_NOTIFIER, NULL, 4, node, event, wake, enable);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_register_notifier);
 
@@ -1493,8 +1440,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_register_notifier);
  */
 int zynqmp_pm_system_shutdown(const u32 type, const u32 subtype)
 {
-	return zynqmp_pm_invoke_fn(PM_SYSTEM_SHUTDOWN, type, subtype,
-				   0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_SYSTEM_SHUTDOWN, NULL, 2, type, subtype);
 }
 
 /**
@@ -1506,8 +1452,7 @@ int zynqmp_pm_system_shutdown(const u32 type, const u32 subtype)
  */
 int zynqmp_pm_set_feature_config(enum pm_feature_config_id id, u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_SET_FEATURE_CONFIG,
-				   id, value, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, 0, IOCTL_SET_FEATURE_CONFIG, id, value);
 }
 
 /**
@@ -1520,8 +1465,7 @@ int zynqmp_pm_set_feature_config(enum pm_feature_config_id id, u32 value)
 int zynqmp_pm_get_feature_config(enum pm_feature_config_id id,
 				 u32 *payload)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_GET_FEATURE_CONFIG,
-				   id, 0, payload);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, payload, 3, 0, IOCTL_GET_FEATURE_CONFIG, id);
 }
 
 /**
@@ -1534,8 +1478,7 @@ int zynqmp_pm_get_feature_config(enum pm_feature_config_id id,
  */
 int zynqmp_pm_set_sd_config(u32 node, enum pm_sd_config_type config, u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, node, IOCTL_SET_SD_CONFIG,
-				   config, value, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, node, IOCTL_SET_SD_CONFIG, config, value);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_sd_config);
 
@@ -1550,8 +1493,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_sd_config);
 int zynqmp_pm_set_gem_config(u32 node, enum pm_gem_config_type config,
 			     u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, node, IOCTL_SET_GEM_CONFIG,
-				   config, value, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, node, IOCTL_SET_GEM_CONFIG, config, value);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_gem_config);
 
@@ -1916,7 +1858,6 @@ ATTRIBUTE_GROUPS(zynqmp_firmware);
 static int zynqmp_firmware_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct device_node *np;
 	struct zynqmp_devinfo *devinfo;
 	int ret;
 
@@ -1924,22 +1865,9 @@ static int zynqmp_firmware_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	np = of_find_compatible_node(NULL, NULL, "xlnx,zynqmp");
-	if (!np) {
-		np = of_find_compatible_node(NULL, NULL, "xlnx,versal");
-		if (!np)
-			return 0;
-
+	ret = do_feature_check_call(PM_FEATURE_CHECK);
+	if (ret >= 0 && ((ret & FIRMWARE_VERSION_MASK) >= PM_API_VERSION_1))
 		feature_check_enabled = true;
-	}
-
-	if (!feature_check_enabled) {
-		ret = do_feature_check_call(PM_FEATURE_CHECK);
-		if (ret >= 0)
-			feature_check_enabled = true;
-	}
-
-	of_node_put(np);
 
 	devinfo = devm_kzalloc(dev, sizeof(*devinfo), GFP_KERNEL);
 	if (!devinfo)
@@ -1992,19 +1920,17 @@ static int zynqmp_firmware_probe(struct platform_device *pdev)
 
 	zynqmp_pm_api_debugfs_init();
 
-	np = of_find_compatible_node(NULL, NULL, "xlnx,versal");
-	if (np) {
+	if (pm_family_code == VERSAL_FAMILY_CODE) {
 		em_dev = platform_device_register_data(&pdev->dev, "xlnx_event_manager",
 						       -1, NULL, 0);
 		if (IS_ERR(em_dev))
 			dev_err_probe(&pdev->dev, PTR_ERR(em_dev), "EM register fail with error\n");
 	}
-	of_node_put(np);
 
 	return of_platform_populate(dev->of_node, NULL, NULL, dev);
 }
 
-static int zynqmp_firmware_remove(struct platform_device *pdev)
+static void zynqmp_firmware_remove(struct platform_device *pdev)
 {
 	struct pm_api_feature_data *feature_data;
 	struct hlist_node *tmp;
@@ -2019,8 +1945,6 @@ static int zynqmp_firmware_remove(struct platform_device *pdev)
 	}
 
 	platform_device_unregister(em_dev);
-
-	return 0;
 }
 
 static const struct of_device_id zynqmp_firmware_of_match[] = {
@@ -2037,6 +1961,6 @@ static struct platform_driver zynqmp_firmware_driver = {
 		.dev_groups = zynqmp_firmware_groups,
 	},
 	.probe = zynqmp_firmware_probe,
-	.remove = zynqmp_firmware_remove,
+	.remove_new = zynqmp_firmware_remove,
 };
 module_platform_driver(zynqmp_firmware_driver);
diff --git a/drivers/fpga/altera-fpga2sdram.c b/drivers/fpga/altera-fpga2sdram.c
index 1fa2ccc321ab..6b60ca004345 100644
--- a/drivers/fpga/altera-fpga2sdram.c
+++ b/drivers/fpga/altera-fpga2sdram.c
@@ -147,20 +147,18 @@ static int alt_fpga_bridge_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int alt_fpga_bridge_remove(struct platform_device *pdev)
+static void alt_fpga_bridge_remove(struct platform_device *pdev)
 {
 	struct fpga_bridge *br = platform_get_drvdata(pdev);
 
 	fpga_bridge_unregister(br);
-
-	return 0;
 }
 
 MODULE_DEVICE_TABLE(of, altera_fpga_of_match);
 
 static struct platform_driver altera_fpga_driver = {
 	.probe = alt_fpga_bridge_probe,
-	.remove = alt_fpga_bridge_remove,
+	.remove_new = alt_fpga_bridge_remove,
 	.driver = {
 		.name	= "altera_fpga2sdram_bridge",
 		.of_match_table = of_match_ptr(altera_fpga_of_match),
diff --git a/drivers/fpga/altera-freeze-bridge.c b/drivers/fpga/altera-freeze-bridge.c
index 0c3fb8226908..44061cb16f87 100644
--- a/drivers/fpga/altera-freeze-bridge.c
+++ b/drivers/fpga/altera-freeze-bridge.c
@@ -253,18 +253,16 @@ static int altera_freeze_br_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int altera_freeze_br_remove(struct platform_device *pdev)
+static void altera_freeze_br_remove(struct platform_device *pdev)
 {
 	struct fpga_bridge *br = platform_get_drvdata(pdev);
 
 	fpga_bridge_unregister(br);
-
-	return 0;
 }
 
 static struct platform_driver altera_freeze_br_driver = {
 	.probe = altera_freeze_br_probe,
-	.remove = altera_freeze_br_remove,
+	.remove_new = altera_freeze_br_remove,
 	.driver = {
 		.name	= "altera_freeze_br",
 		.of_match_table = altera_freeze_br_of_match,
diff --git a/drivers/fpga/altera-hps2fpga.c b/drivers/fpga/altera-hps2fpga.c
index 578663503297..6f8e24be19c6 100644
--- a/drivers/fpga/altera-hps2fpga.c
+++ b/drivers/fpga/altera-hps2fpga.c
@@ -191,7 +191,7 @@ err:
 	return ret;
 }
 
-static int alt_fpga_bridge_remove(struct platform_device *pdev)
+static void alt_fpga_bridge_remove(struct platform_device *pdev)
 {
 	struct fpga_bridge *bridge = platform_get_drvdata(pdev);
 	struct altera_hps2fpga_data *priv = bridge->priv;
@@ -199,15 +199,13 @@ static int alt_fpga_bridge_remove(struct platform_device *pdev)
 	fpga_bridge_unregister(bridge);
 
 	clk_disable_unprepare(priv->clk);
-
-	return 0;
 }
 
 MODULE_DEVICE_TABLE(of, altera_fpga_of_match);
 
 static struct platform_driver alt_fpga_bridge_driver = {
 	.probe = alt_fpga_bridge_probe,
-	.remove = alt_fpga_bridge_remove,
+	.remove_new = alt_fpga_bridge_remove,
 	.driver = {
 		.name	= "altera_hps2fpga_bridge",
 		.of_match_table = of_match_ptr(altera_fpga_of_match),
diff --git a/drivers/fpga/dfl-afu-main.c b/drivers/fpga/dfl-afu-main.c
index 7f621e96d3b8..c0a75ca360d6 100644
--- a/drivers/fpga/dfl-afu-main.c
+++ b/drivers/fpga/dfl-afu-main.c
@@ -932,15 +932,13 @@ exit:
 	return ret;
 }
 
-static int afu_remove(struct platform_device *pdev)
+static void afu_remove(struct platform_device *pdev)
 {
 	dev_dbg(&pdev->dev, "%s\n", __func__);
 
 	dfl_fpga_dev_ops_unregister(pdev);
 	dfl_fpga_dev_feature_uinit(pdev);
 	afu_dev_destroy(pdev);
-
-	return 0;
 }
 
 static const struct attribute_group *afu_dev_groups[] = {
@@ -956,7 +954,7 @@ static struct platform_driver afu_driver = {
 		.dev_groups = afu_dev_groups,
 	},
 	.probe   = afu_probe,
-	.remove  = afu_remove,
+	.remove_new = afu_remove,
 };
 
 static int __init afu_init(void)
diff --git a/drivers/fpga/dfl-fme-br.c b/drivers/fpga/dfl-fme-br.c
index 808d1f4d76df..0b01b3895277 100644
--- a/drivers/fpga/dfl-fme-br.c
+++ b/drivers/fpga/dfl-fme-br.c
@@ -78,7 +78,7 @@ static int fme_br_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int fme_br_remove(struct platform_device *pdev)
+static void fme_br_remove(struct platform_device *pdev)
 {
 	struct fpga_bridge *br = platform_get_drvdata(pdev);
 	struct fme_br_priv *priv = br->priv;
@@ -89,8 +89,6 @@ static int fme_br_remove(struct platform_device *pdev)
 		put_device(&priv->port_pdev->dev);
 	if (priv->port_ops)
 		dfl_fpga_port_ops_put(priv->port_ops);
-
-	return 0;
 }
 
 static struct platform_driver fme_br_driver = {
@@ -98,7 +96,7 @@ static struct platform_driver fme_br_driver = {
 		.name    = DFL_FPGA_FME_BRIDGE,
 	},
 	.probe   = fme_br_probe,
-	.remove  = fme_br_remove,
+	.remove_new = fme_br_remove,
 };
 
 module_platform_driver(fme_br_driver);
diff --git a/drivers/fpga/dfl-fme-main.c b/drivers/fpga/dfl-fme-main.c
index 3dcf990bd261..a2b5da0093da 100644
--- a/drivers/fpga/dfl-fme-main.c
+++ b/drivers/fpga/dfl-fme-main.c
@@ -730,13 +730,11 @@ exit:
 	return ret;
 }
 
-static int fme_remove(struct platform_device *pdev)
+static void fme_remove(struct platform_device *pdev)
 {
 	dfl_fpga_dev_ops_unregister(pdev);
 	dfl_fpga_dev_feature_uinit(pdev);
 	fme_dev_destroy(pdev);
-
-	return 0;
 }
 
 static const struct attribute_group *fme_dev_groups[] = {
@@ -751,7 +749,7 @@ static struct platform_driver fme_driver = {
 		.dev_groups = fme_dev_groups,
 	},
 	.probe   = fme_probe,
-	.remove  = fme_remove,
+	.remove_new = fme_remove,
 };
 
 module_platform_driver(fme_driver);
diff --git a/drivers/fpga/dfl-fme-region.c b/drivers/fpga/dfl-fme-region.c
index 4aebde0a7f1c..71616f8b4982 100644
--- a/drivers/fpga/dfl-fme-region.c
+++ b/drivers/fpga/dfl-fme-region.c
@@ -61,15 +61,13 @@ eprobe_mgr_put:
 	return ret;
 }
 
-static int fme_region_remove(struct platform_device *pdev)
+static void fme_region_remove(struct platform_device *pdev)
 {
 	struct fpga_region *region = platform_get_drvdata(pdev);
 	struct fpga_manager *mgr = region->mgr;
 
 	fpga_region_unregister(region);
 	fpga_mgr_put(mgr);
-
-	return 0;
 }
 
 static struct platform_driver fme_region_driver = {
@@ -77,7 +75,7 @@ static struct platform_driver fme_region_driver = {
 		.name    = DFL_FPGA_FME_REGION,
 	},
 	.probe   = fme_region_probe,
-	.remove  = fme_region_remove,
+	.remove_new = fme_region_remove,
 };
 
 module_platform_driver(fme_region_driver);
diff --git a/drivers/fpga/dfl.c b/drivers/fpga/dfl.c
index e73f88050f08..e6d12fbab653 100644
--- a/drivers/fpga/dfl.c
+++ b/drivers/fpga/dfl.c
@@ -2008,8 +2008,8 @@ long dfl_feature_ioctl_set_irq(struct platform_device *pdev,
 	    (hdr.start + hdr.count < hdr.start))
 		return -EINVAL;
 
-	fds = memdup_user((void __user *)(arg + sizeof(hdr)),
-			  array_size(hdr.count, sizeof(s32)));
+	fds = memdup_array_user((void __user *)(arg + sizeof(hdr)),
+				hdr.count, sizeof(s32));
 	if (IS_ERR(fds))
 		return PTR_ERR(fds);
 
diff --git a/drivers/fpga/intel-m10-bmc-sec-update.c b/drivers/fpga/intel-m10-bmc-sec-update.c
index 31af2e08c825..89851b133709 100644
--- a/drivers/fpga/intel-m10-bmc-sec-update.c
+++ b/drivers/fpga/intel-m10-bmc-sec-update.c
@@ -730,15 +730,13 @@ fw_name_fail:
 	return ret;
 }
 
-static int m10bmc_sec_remove(struct platform_device *pdev)
+static void m10bmc_sec_remove(struct platform_device *pdev)
 {
 	struct m10bmc_sec *sec = dev_get_drvdata(&pdev->dev);
 
 	firmware_upload_unregister(sec->fwl);
 	kfree(sec->fw_name);
 	xa_erase(&fw_upload_xa, sec->fw_name_id);
-
-	return 0;
 }
 
 static const struct platform_device_id intel_m10bmc_sec_ids[] = {
@@ -760,7 +758,7 @@ MODULE_DEVICE_TABLE(platform, intel_m10bmc_sec_ids);
 
 static struct platform_driver intel_m10bmc_sec_driver = {
 	.probe = m10bmc_sec_probe,
-	.remove = m10bmc_sec_remove,
+	.remove_new = m10bmc_sec_remove,
 	.driver = {
 		.name = "intel-m10bmc-sec-update",
 		.dev_groups = m10bmc_sec_attr_groups,
diff --git a/drivers/fpga/of-fpga-region.c b/drivers/fpga/of-fpga-region.c
index a6affd83f275..8526a5a86f0c 100644
--- a/drivers/fpga/of-fpga-region.c
+++ b/drivers/fpga/of-fpga-region.c
@@ -425,20 +425,18 @@ eprobe_mgr_put:
 	return ret;
 }
 
-static int of_fpga_region_remove(struct platform_device *pdev)
+static void of_fpga_region_remove(struct platform_device *pdev)
 {
 	struct fpga_region *region = platform_get_drvdata(pdev);
 	struct fpga_manager *mgr = region->mgr;
 
 	fpga_region_unregister(region);
 	fpga_mgr_put(mgr);
-
-	return 0;
 }
 
 static struct platform_driver of_fpga_region_driver = {
 	.probe = of_fpga_region_probe,
-	.remove = of_fpga_region_remove,
+	.remove_new = of_fpga_region_remove,
 	.driver = {
 		.name	= "of-fpga-region",
 		.of_match_table = of_match_ptr(fpga_region_of_match),
diff --git a/drivers/fpga/socfpga-a10.c b/drivers/fpga/socfpga-a10.c
index cc4861e345c9..4c03513b8f03 100644
--- a/drivers/fpga/socfpga-a10.c
+++ b/drivers/fpga/socfpga-a10.c
@@ -517,15 +517,13 @@ static int socfpga_a10_fpga_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int socfpga_a10_fpga_remove(struct platform_device *pdev)
+static void socfpga_a10_fpga_remove(struct platform_device *pdev)
 {
 	struct fpga_manager *mgr = platform_get_drvdata(pdev);
 	struct a10_fpga_priv *priv = mgr->priv;
 
 	fpga_mgr_unregister(mgr);
 	clk_disable_unprepare(priv->clk);
-
-	return 0;
 }
 
 static const struct of_device_id socfpga_a10_fpga_of_match[] = {
@@ -537,7 +535,7 @@ MODULE_DEVICE_TABLE(of, socfpga_a10_fpga_of_match);
 
 static struct platform_driver socfpga_a10_fpga_driver = {
 	.probe = socfpga_a10_fpga_probe,
-	.remove = socfpga_a10_fpga_remove,
+	.remove_new = socfpga_a10_fpga_remove,
 	.driver = {
 		.name	= "socfpga_a10_fpga_manager",
 		.of_match_table = socfpga_a10_fpga_of_match,
diff --git a/drivers/fpga/stratix10-soc.c b/drivers/fpga/stratix10-soc.c
index cacb9cc5757e..2c0def7d7cbb 100644
--- a/drivers/fpga/stratix10-soc.c
+++ b/drivers/fpga/stratix10-soc.c
@@ -436,15 +436,13 @@ probe_err:
 	return ret;
 }
 
-static int s10_remove(struct platform_device *pdev)
+static void s10_remove(struct platform_device *pdev)
 {
 	struct fpga_manager *mgr = platform_get_drvdata(pdev);
 	struct s10_priv *priv = mgr->priv;
 
 	fpga_mgr_unregister(mgr);
 	stratix10_svc_free_channel(priv->chan);
-
-	return 0;
 }
 
 static const struct of_device_id s10_of_match[] = {
@@ -457,7 +455,7 @@ MODULE_DEVICE_TABLE(of, s10_of_match);
 
 static struct platform_driver s10_driver = {
 	.probe = s10_probe,
-	.remove = s10_remove,
+	.remove_new = s10_remove,
 	.driver = {
 		.name	= "Stratix10 SoC FPGA manager",
 		.of_match_table = of_match_ptr(s10_of_match),
diff --git a/drivers/fpga/xilinx-pr-decoupler.c b/drivers/fpga/xilinx-pr-decoupler.c
index 68835896f180..788dd2f63a65 100644
--- a/drivers/fpga/xilinx-pr-decoupler.c
+++ b/drivers/fpga/xilinx-pr-decoupler.c
@@ -150,7 +150,7 @@ err_clk:
 	return err;
 }
 
-static int xlnx_pr_decoupler_remove(struct platform_device *pdev)
+static void xlnx_pr_decoupler_remove(struct platform_device *pdev)
 {
 	struct fpga_bridge *bridge = platform_get_drvdata(pdev);
 	struct xlnx_pr_decoupler_data *p = bridge->priv;
@@ -158,13 +158,11 @@ static int xlnx_pr_decoupler_remove(struct platform_device *pdev)
 	fpga_bridge_unregister(bridge);
 
 	clk_unprepare(p->clk);
-
-	return 0;
 }
 
 static struct platform_driver xlnx_pr_decoupler_driver = {
 	.probe = xlnx_pr_decoupler_probe,
-	.remove = xlnx_pr_decoupler_remove,
+	.remove_new = xlnx_pr_decoupler_remove,
 	.driver = {
 		.name = "xlnx_pr_decoupler",
 		.of_match_table = xlnx_pr_decoupler_of_match,
diff --git a/drivers/fpga/zynq-fpga.c b/drivers/fpga/zynq-fpga.c
index 96611d424a10..0ac93183d201 100644
--- a/drivers/fpga/zynq-fpga.c
+++ b/drivers/fpga/zynq-fpga.c
@@ -618,7 +618,7 @@ static int zynq_fpga_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int zynq_fpga_remove(struct platform_device *pdev)
+static void zynq_fpga_remove(struct platform_device *pdev)
 {
 	struct zynq_fpga_priv *priv;
 	struct fpga_manager *mgr;
@@ -629,8 +629,6 @@ static int zynq_fpga_remove(struct platform_device *pdev)
 	fpga_mgr_unregister(mgr);
 
 	clk_unprepare(priv->clk);
-
-	return 0;
 }
 
 #ifdef CONFIG_OF
@@ -644,7 +642,7 @@ MODULE_DEVICE_TABLE(of, zynq_fpga_of_match);
 
 static struct platform_driver zynq_fpga_driver = {
 	.probe = zynq_fpga_probe,
-	.remove = zynq_fpga_remove,
+	.remove_new = zynq_fpga_remove,
 	.driver = {
 		.name = "zynq_fpga_manager",
 		.of_match_table = of_match_ptr(zynq_fpga_of_match),
diff --git a/drivers/gnss/serial.c b/drivers/gnss/serial.c
index 5d8e9bfb24d0..baa956494e79 100644
--- a/drivers/gnss/serial.c
+++ b/drivers/gnss/serial.c
@@ -80,8 +80,8 @@ static const struct gnss_operations gnss_serial_gnss_ops = {
 	.write_raw	= gnss_serial_write_raw,
 };
 
-static int gnss_serial_receive_buf(struct serdev_device *serdev,
-					const unsigned char *buf, size_t count)
+static ssize_t gnss_serial_receive_buf(struct serdev_device *serdev,
+				       const u8 *buf, size_t count)
 {
 	struct gnss_serial *gserial = serdev_device_get_drvdata(serdev);
 	struct gnss_device *gdev = gserial->gdev;
diff --git a/drivers/gnss/sirf.c b/drivers/gnss/sirf.c
index bcb53ccfee4d..6801a8fb2040 100644
--- a/drivers/gnss/sirf.c
+++ b/drivers/gnss/sirf.c
@@ -160,8 +160,8 @@ static const struct gnss_operations sirf_gnss_ops = {
 	.write_raw	= sirf_write_raw,
 };
 
-static int sirf_receive_buf(struct serdev_device *serdev,
-				const unsigned char *buf, size_t count)
+static ssize_t sirf_receive_buf(struct serdev_device *serdev,
+				const u8 *buf, size_t count)
 {
 	struct sirf_data *data = serdev_device_get_drvdata(serdev);
 	struct gnss_device *gdev = data->gdev;
diff --git a/drivers/gpio/gpio-74x164.c b/drivers/gpio/gpio-74x164.c
index e00c33310517..753e7be039e4 100644
--- a/drivers/gpio/gpio-74x164.c
+++ b/drivers/gpio/gpio-74x164.c
@@ -127,8 +127,6 @@ static int gen_74x164_probe(struct spi_device *spi)
 	if (IS_ERR(chip->gpiod_oe))
 		return PTR_ERR(chip->gpiod_oe);
 
-	gpiod_set_value_cansleep(chip->gpiod_oe, 1);
-
 	spi_set_drvdata(spi, chip);
 
 	chip->gpio_chip.label = spi->modalias;
@@ -153,6 +151,8 @@ static int gen_74x164_probe(struct spi_device *spi)
 		goto exit_destroy;
 	}
 
+	gpiod_set_value_cansleep(chip->gpiod_oe, 1);
+
 	ret = gpiochip_add_data(&chip->gpio_chip, chip);
 	if (!ret)
 		return 0;
diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c
index be7f2fa5aa7b..806b88d8dfb7 100644
--- a/drivers/gpio/gpio-eic-sprd.c
+++ b/drivers/gpio/gpio-eic-sprd.c
@@ -330,20 +330,27 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type)
 		switch (flow_type) {
 		case IRQ_TYPE_LEVEL_HIGH:
 			sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IEV, 1);
+			sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IC, 1);
 			break;
 		case IRQ_TYPE_LEVEL_LOW:
 			sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IEV, 0);
+			sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IC, 1);
 			break;
 		case IRQ_TYPE_EDGE_RISING:
 		case IRQ_TYPE_EDGE_FALLING:
 		case IRQ_TYPE_EDGE_BOTH:
 			state = sprd_eic_get(chip, offset);
-			if (state)
+			if (state) {
 				sprd_eic_update(chip, offset,
 						SPRD_EIC_DBNC_IEV, 0);
-			else
+				sprd_eic_update(chip, offset,
+						SPRD_EIC_DBNC_IC, 1);
+			} else {
 				sprd_eic_update(chip, offset,
 						SPRD_EIC_DBNC_IEV, 1);
+				sprd_eic_update(chip, offset,
+						SPRD_EIC_DBNC_IC, 1);
+			}
 			break;
 		default:
 			return -ENOTSUPP;
@@ -355,20 +362,27 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type)
 		switch (flow_type) {
 		case IRQ_TYPE_LEVEL_HIGH:
 			sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTPOL, 0);
+			sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTCLR, 1);
 			break;
 		case IRQ_TYPE_LEVEL_LOW:
 			sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTPOL, 1);
+			sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTCLR, 1);
 			break;
 		case IRQ_TYPE_EDGE_RISING:
 		case IRQ_TYPE_EDGE_FALLING:
 		case IRQ_TYPE_EDGE_BOTH:
 			state = sprd_eic_get(chip, offset);
-			if (state)
+			if (state) {
 				sprd_eic_update(chip, offset,
 						SPRD_EIC_LATCH_INTPOL, 0);
-			else
+				sprd_eic_update(chip, offset,
+						SPRD_EIC_LATCH_INTCLR, 1);
+			} else {
 				sprd_eic_update(chip, offset,
 						SPRD_EIC_LATCH_INTPOL, 1);
+				sprd_eic_update(chip, offset,
+						SPRD_EIC_LATCH_INTCLR, 1);
+			}
 			break;
 		default:
 			return -ENOTSUPP;
@@ -382,29 +396,34 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type)
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 1);
+			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1);
 			irq_set_handler_locked(data, handle_edge_irq);
 			break;
 		case IRQ_TYPE_EDGE_FALLING:
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 0);
+			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1);
 			irq_set_handler_locked(data, handle_edge_irq);
 			break;
 		case IRQ_TYPE_EDGE_BOTH:
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 1);
+			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1);
 			irq_set_handler_locked(data, handle_edge_irq);
 			break;
 		case IRQ_TYPE_LEVEL_HIGH:
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 1);
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 1);
+			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1);
 			irq_set_handler_locked(data, handle_level_irq);
 			break;
 		case IRQ_TYPE_LEVEL_LOW:
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 1);
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 0);
+			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1);
 			irq_set_handler_locked(data, handle_level_irq);
 			break;
 		default:
@@ -417,29 +436,34 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type)
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 1);
+			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1);
 			irq_set_handler_locked(data, handle_edge_irq);
 			break;
 		case IRQ_TYPE_EDGE_FALLING:
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 0);
+			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1);
 			irq_set_handler_locked(data, handle_edge_irq);
 			break;
 		case IRQ_TYPE_EDGE_BOTH:
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 1);
+			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1);
 			irq_set_handler_locked(data, handle_edge_irq);
 			break;
 		case IRQ_TYPE_LEVEL_HIGH:
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 1);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 1);
+			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1);
 			irq_set_handler_locked(data, handle_level_irq);
 			break;
 		case IRQ_TYPE_LEVEL_LOW:
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 1);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 0);
+			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1);
 			irq_set_handler_locked(data, handle_level_irq);
 			break;
 		default:
diff --git a/drivers/gpio/gpio-en7523.c b/drivers/gpio/gpio-en7523.c
index f836a8db4c1d..69834db2c1cf 100644
--- a/drivers/gpio/gpio-en7523.c
+++ b/drivers/gpio/gpio-en7523.c
@@ -12,11 +12,11 @@
 #define AIROHA_GPIO_MAX		32
 
 /**
- * airoha_gpio_ctrl - Airoha GPIO driver data
+ * struct airoha_gpio_ctrl - Airoha GPIO driver data
  * @gc: Associated gpio_chip instance.
  * @data: The data register.
- * @dir0: The direction register for the lower 16 pins.
- * @dir1: The direction register for the higher 16 pins.
+ * @dir: [0] The direction register for the lower 16 pins.
+ * [1]: The direction register for the higher 16 pins.
  * @output: The output enable register.
  */
 struct airoha_gpio_ctrl {
diff --git a/drivers/gpio/gpio-mlxbf3.c b/drivers/gpio/gpio-mlxbf3.c
index 7a3e1760fc5b..d5906d419b0a 100644
--- a/drivers/gpio/gpio-mlxbf3.c
+++ b/drivers/gpio/gpio-mlxbf3.c
@@ -215,6 +215,8 @@ static int mlxbf3_gpio_probe(struct platform_device *pdev)
 			gs->gpio_clr_io + MLXBF_GPIO_FW_DATA_OUT_CLEAR,
 			gs->gpio_set_io + MLXBF_GPIO_FW_OUTPUT_ENABLE_SET,
 			gs->gpio_clr_io + MLXBF_GPIO_FW_OUTPUT_ENABLE_CLEAR, 0);
+	if (ret)
+		return dev_err_probe(dev, ret, "%s: bgpio_init() failed", __func__);
 
 	gc->request = gpiochip_generic_request;
 	gc->free = gpiochip_generic_free;
diff --git a/drivers/gpio/gpio-rtd.c b/drivers/gpio/gpio-rtd.c
index a7939bd0aa56..bf7f008f58d7 100644
--- a/drivers/gpio/gpio-rtd.c
+++ b/drivers/gpio/gpio-rtd.c
@@ -525,18 +525,21 @@ static int rtd_gpio_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct gpio_irq_chip *irq_chip;
 	struct rtd_gpio *data;
+	int ret;
 
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
-	data->irqs[0] = platform_get_irq(pdev, 0);
-	if (data->irqs[0] < 0)
-		return data->irqs[0];
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0)
+		return ret;
+	data->irqs[0] = ret;
 
-	data->irqs[1] = platform_get_irq(pdev, 1);
-	if (data->irqs[1] < 0)
-		return data->irqs[1];
+	ret = platform_get_irq(pdev, 1);
+	if (ret < 0)
+		return ret;
+	data->irqs[1] = ret;
 
 	data->info = device_get_match_data(dev);
 	if (!data->info)
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 88066826d8e5..cd3e9657cc36 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -1651,6 +1651,20 @@ static const struct dmi_system_id gpiolib_acpi_quirks[] __initconst = {
 			.ignore_interrupt = "INT33FC:00@3",
 		},
 	},
+	{
+		/*
+		 * Spurious wakeups from TP_ATTN# pin
+		 * Found in BIOS 0.35
+		 * https://gitlab.freedesktop.org/drm/amd/-/issues/3073
+		 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "GPD"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "G1619-04"),
+		},
+		.driver_data = &(struct acpi_gpiolib_dmi_quirk) {
+			.ignore_wake = "PNP0C50:00@8",
+		},
+	},
 	{} /* Terminating entry */
 };
 
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 402f7d99b0c1..e7770eedd146 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -184,7 +184,7 @@ static void of_gpio_try_fixup_polarity(const struct device_node *np,
 		const char *propname;
 		bool active_high;
 	} gpios[] = {
-#if !IS_ENABLED(CONFIG_LCD_HX8357)
+#if IS_ENABLED(CONFIG_LCD_HX8357)
 		/*
 		 * Himax LCD controllers used incorrectly named
 		 * "gpios-reset" property and also specified wrong
@@ -478,7 +478,7 @@ static struct gpio_desc *of_find_gpio_rename(struct device_node *np,
 		 */
 		const char *compatible;
 	} gpios[] = {
-#if !IS_ENABLED(CONFIG_LCD_HX8357)
+#if IS_ENABLED(CONFIG_LCD_HX8357)
 		/* Himax LCD controllers used "gpios-reset" */
 		{ "reset",	"gpios-reset",	"himax,hx8357" },
 		{ "reset",	"gpios-reset",	"himax,hx8369" },
diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c
index 4dbf298bb5dd..6bf5332136e5 100644
--- a/drivers/gpio/gpiolib-sysfs.c
+++ b/drivers/gpio/gpiolib-sysfs.c
@@ -768,25 +768,6 @@ int gpiochip_sysfs_register(struct gpio_device *gdev)
 	return 0;
 }
 
-int gpiochip_sysfs_register_all(void)
-{
-	struct gpio_device *gdev;
-	int ret;
-
-	guard(rwsem_read)(&gpio_devices_sem);
-
-	list_for_each_entry(gdev, &gpio_devices, list) {
-		if (gdev->mockdev)
-			continue;
-
-		ret = gpiochip_sysfs_register(gdev);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
 void gpiochip_sysfs_unregister(struct gpio_device *gdev)
 {
 	struct gpio_desc *desc;
@@ -811,7 +792,9 @@ void gpiochip_sysfs_unregister(struct gpio_device *gdev)
 
 static int __init gpiolib_sysfs_init(void)
 {
-	int status;
+	int		status;
+	unsigned long	flags;
+	struct gpio_device *gdev;
 
 	status = class_register(&gpio_class);
 	if (status < 0)
@@ -823,6 +806,26 @@ static int __init gpiolib_sysfs_init(void)
 	 * We run before arch_initcall() so chip->dev nodes can have
 	 * registered, and so arch_initcall() can always gpiod_export().
 	 */
-	return gpiochip_sysfs_register_all();
+	spin_lock_irqsave(&gpio_lock, flags);
+	list_for_each_entry(gdev, &gpio_devices, list) {
+		if (gdev->mockdev)
+			continue;
+
+		/*
+		 * TODO we yield gpio_lock here because
+		 * gpiochip_sysfs_register() acquires a mutex. This is unsafe
+		 * and needs to be fixed.
+		 *
+		 * Also it would be nice to use gpio_device_find() here so we
+		 * can keep gpio_chips local to gpiolib.c, but the yield of
+		 * gpio_lock prevents us from doing this.
+		 */
+		spin_unlock_irqrestore(&gpio_lock, flags);
+		status = gpiochip_sysfs_register(gdev);
+		spin_lock_irqsave(&gpio_lock, flags);
+	}
+	spin_unlock_irqrestore(&gpio_lock, flags);
+
+	return status;
 }
 postcore_initcall(gpiolib_sysfs_init);
diff --git a/drivers/gpio/gpiolib-sysfs.h b/drivers/gpio/gpiolib-sysfs.h
index ab157cec0b4b..b794b396d6a5 100644
--- a/drivers/gpio/gpiolib-sysfs.h
+++ b/drivers/gpio/gpiolib-sysfs.h
@@ -8,7 +8,6 @@ struct gpio_device;
 #ifdef CONFIG_GPIO_SYSFS
 
 int gpiochip_sysfs_register(struct gpio_device *gdev);
-int gpiochip_sysfs_register_all(void);
 void gpiochip_sysfs_unregister(struct gpio_device *gdev);
 
 #else
@@ -18,11 +17,6 @@ static inline int gpiochip_sysfs_register(struct gpio_device *gdev)
 	return 0;
 }
 
-static inline int gpiochip_sysfs_register_all(void)
-{
-	return 0;
-}
-
 static inline void gpiochip_sysfs_unregister(struct gpio_device *gdev)
 {
 }
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 4c93cf73a826..75be4a3ca7f8 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -2,7 +2,6 @@
 
 #include <linux/acpi.h>
 #include <linux/bitmap.h>
-#include <linux/cleanup.h>
 #include <linux/compat.h>
 #include <linux/debugfs.h>
 #include <linux/device.h>
@@ -16,7 +15,6 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/module.h>
-#include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/seq_file.h>
@@ -83,9 +81,7 @@ DEFINE_SPINLOCK(gpio_lock);
 
 static DEFINE_MUTEX(gpio_lookup_lock);
 static LIST_HEAD(gpio_lookup_list);
-
 LIST_HEAD(gpio_devices);
-DECLARE_RWSEM(gpio_devices_sem);
 
 static DEFINE_MUTEX(gpio_machine_hogs_mutex);
 static LIST_HEAD(gpio_machine_hogs);
@@ -117,15 +113,20 @@ static inline void desc_set_label(struct gpio_desc *d, const char *label)
 struct gpio_desc *gpio_to_desc(unsigned gpio)
 {
 	struct gpio_device *gdev;
+	unsigned long flags;
 
-	scoped_guard(rwsem_read, &gpio_devices_sem) {
-		list_for_each_entry(gdev, &gpio_devices, list) {
-			if (gdev->base <= gpio &&
-			    gdev->base + gdev->ngpio > gpio)
-				return &gdev->descs[gpio - gdev->base];
+	spin_lock_irqsave(&gpio_lock, flags);
+
+	list_for_each_entry(gdev, &gpio_devices, list) {
+		if (gdev->base <= gpio &&
+		    gdev->base + gdev->ngpio > gpio) {
+			spin_unlock_irqrestore(&gpio_lock, flags);
+			return &gdev->descs[gpio - gdev->base];
 		}
 	}
 
+	spin_unlock_irqrestore(&gpio_lock, flags);
+
 	if (!gpio_is_valid(gpio))
 		pr_warn("invalid GPIO %d\n", gpio);
 
@@ -398,21 +399,26 @@ static int gpiodev_add_to_list_unlocked(struct gpio_device *gdev)
 static struct gpio_desc *gpio_name_to_desc(const char * const name)
 {
 	struct gpio_device *gdev;
+	unsigned long flags;
 
 	if (!name)
 		return NULL;
 
-	guard(rwsem_read)(&gpio_devices_sem);
+	spin_lock_irqsave(&gpio_lock, flags);
 
 	list_for_each_entry(gdev, &gpio_devices, list) {
 		struct gpio_desc *desc;
 
 		for_each_gpio_desc(gdev->chip, desc) {
-			if (desc->name && !strcmp(desc->name, name))
+			if (desc->name && !strcmp(desc->name, name)) {
+				spin_unlock_irqrestore(&gpio_lock, flags);
 				return desc;
+			}
 		}
 	}
 
+	spin_unlock_irqrestore(&gpio_lock, flags);
+
 	return NULL;
 }
 
@@ -807,6 +813,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 			       struct lock_class_key *request_key)
 {
 	struct gpio_device *gdev;
+	unsigned long flags;
 	unsigned int i;
 	int base = 0;
 	int ret = 0;
@@ -871,46 +878,49 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 
 	gdev->ngpio = gc->ngpio;
 
-	scoped_guard(rwsem_write, &gpio_devices_sem) {
-		/*
-		 * TODO: this allocates a Linux GPIO number base in the global
-		 * GPIO numberspace for this chip. In the long run we want to
-		 * get *rid* of this numberspace and use only descriptors, but
-		 * it may be a pipe dream. It will not happen before we get rid
-		 * of the sysfs interface anyways.
-		 */
-		base = gc->base;
+	spin_lock_irqsave(&gpio_lock, flags);
 
+	/*
+	 * TODO: this allocates a Linux GPIO number base in the global
+	 * GPIO numberspace for this chip. In the long run we want to
+	 * get *rid* of this numberspace and use only descriptors, but
+	 * it may be a pipe dream. It will not happen before we get rid
+	 * of the sysfs interface anyways.
+	 */
+	base = gc->base;
+	if (base < 0) {
+		base = gpiochip_find_base_unlocked(gc->ngpio);
 		if (base < 0) {
-			base = gpiochip_find_base_unlocked(gc->ngpio);
-			if (base < 0) {
-				ret = base;
-				base = 0;
-				goto err_free_label;
-			}
-			/*
-			 * TODO: it should not be necessary to reflect the assigned
-			 * base outside of the GPIO subsystem. Go over drivers and
-			 * see if anyone makes use of this, else drop this and assign
-			 * a poison instead.
-			 */
-			gc->base = base;
-		} else {
-			dev_warn(&gdev->dev,
-				 "Static allocation of GPIO base is deprecated, use dynamic allocation.\n");
-		}
-		gdev->base = base;
-
-		ret = gpiodev_add_to_list_unlocked(gdev);
-		if (ret) {
-			chip_err(gc, "GPIO integer space overlap, cannot add chip\n");
+			spin_unlock_irqrestore(&gpio_lock, flags);
+			ret = base;
+			base = 0;
 			goto err_free_label;
 		}
+		/*
+		 * TODO: it should not be necessary to reflect the assigned
+		 * base outside of the GPIO subsystem. Go over drivers and
+		 * see if anyone makes use of this, else drop this and assign
+		 * a poison instead.
+		 */
+		gc->base = base;
+	} else {
+		dev_warn(&gdev->dev,
+			 "Static allocation of GPIO base is deprecated, use dynamic allocation.\n");
+	}
+	gdev->base = base;
 
-		for (i = 0; i < gc->ngpio; i++)
-			gdev->descs[i].gdev = gdev;
+	ret = gpiodev_add_to_list_unlocked(gdev);
+	if (ret) {
+		spin_unlock_irqrestore(&gpio_lock, flags);
+		chip_err(gc, "GPIO integer space overlap, cannot add chip\n");
+		goto err_free_label;
 	}
 
+	for (i = 0; i < gc->ngpio; i++)
+		gdev->descs[i].gdev = gdev;
+
+	spin_unlock_irqrestore(&gpio_lock, flags);
+
 	BLOCKING_INIT_NOTIFIER_HEAD(&gdev->line_state_notifier);
 	BLOCKING_INIT_NOTIFIER_HEAD(&gdev->device_notifier);
 	init_rwsem(&gdev->sem);
@@ -958,11 +968,11 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 
 	ret = gpiochip_irqchip_init_valid_mask(gc);
 	if (ret)
-		goto err_remove_acpi_chip;
+		goto err_free_hogs;
 
 	ret = gpiochip_irqchip_init_hw(gc);
 	if (ret)
-		goto err_remove_acpi_chip;
+		goto err_remove_irqchip_mask;
 
 	ret = gpiochip_add_irqchip(gc, lock_key, request_key);
 	if (ret)
@@ -987,22 +997,23 @@ err_remove_irqchip:
 	gpiochip_irqchip_remove(gc);
 err_remove_irqchip_mask:
 	gpiochip_irqchip_free_valid_mask(gc);
-err_remove_acpi_chip:
+err_free_hogs:
+	gpiochip_free_hogs(gc);
 	acpi_gpiochip_remove(gc);
+	gpiochip_remove_pin_ranges(gc);
 err_remove_of_chip:
-	gpiochip_free_hogs(gc);
 	of_gpiochip_remove(gc);
 err_free_gpiochip_mask:
-	gpiochip_remove_pin_ranges(gc);
 	gpiochip_free_valid_mask(gc);
+err_remove_from_list:
+	spin_lock_irqsave(&gpio_lock, flags);
+	list_del(&gdev->list);
+	spin_unlock_irqrestore(&gpio_lock, flags);
 	if (gdev->dev.release) {
 		/* release() has been registered by gpiochip_setup_dev() */
 		gpio_device_put(gdev);
 		goto err_print_message;
 	}
-err_remove_from_list:
-	scoped_guard(rwsem_write, &gpio_devices_sem)
-		list_del(&gdev->list);
 err_free_label:
 	kfree_const(gdev->label);
 err_free_descs:
@@ -1065,7 +1076,7 @@ void gpiochip_remove(struct gpio_chip *gc)
 		dev_crit(&gdev->dev,
 			 "REMOVING GPIOCHIP WITH GPIOS STILL REQUESTED\n");
 
-	scoped_guard(rwsem_write, &gpio_devices_sem)
+	scoped_guard(spinlock_irqsave, &gpio_lock)
 		list_del(&gdev->list);
 
 	/*
@@ -1114,7 +1125,7 @@ struct gpio_device *gpio_device_find(void *data,
 	 */
 	might_sleep();
 
-	guard(rwsem_read)(&gpio_devices_sem);
+	guard(spinlock_irqsave)(&gpio_lock);
 
 	list_for_each_entry(gdev, &gpio_devices, list) {
 		if (gdev->chip && match(gdev->chip, data))
@@ -2031,6 +2042,11 @@ EXPORT_SYMBOL_GPL(gpiochip_generic_free);
 int gpiochip_generic_config(struct gpio_chip *gc, unsigned int offset,
 			    unsigned long config)
 {
+#ifdef CONFIG_PINCTRL
+	if (list_empty(&gc->gpiodev->pin_ranges))
+		return -ENOTSUPP;
+#endif
+
 	return pinctrl_gpio_set_config(gc, offset, config);
 }
 EXPORT_SYMBOL_GPL(gpiochip_generic_config);
@@ -4725,33 +4741,35 @@ static void gpiolib_dbg_show(struct seq_file *s, struct gpio_device *gdev)
 
 static void *gpiolib_seq_start(struct seq_file *s, loff_t *pos)
 {
+	unsigned long flags;
 	struct gpio_device *gdev = NULL;
 	loff_t index = *pos;
 
 	s->private = "";
 
-	guard(rwsem_read)(&gpio_devices_sem);
-
-	list_for_each_entry(gdev, &gpio_devices, list) {
-		if (index-- == 0)
+	spin_lock_irqsave(&gpio_lock, flags);
+	list_for_each_entry(gdev, &gpio_devices, list)
+		if (index-- == 0) {
+			spin_unlock_irqrestore(&gpio_lock, flags);
 			return gdev;
-	}
+		}
+	spin_unlock_irqrestore(&gpio_lock, flags);
 
 	return NULL;
 }
 
 static void *gpiolib_seq_next(struct seq_file *s, void *v, loff_t *pos)
 {
+	unsigned long flags;
 	struct gpio_device *gdev = v;
 	void *ret = NULL;
 
-	scoped_guard(rwsem_read, &gpio_devices_sem) {
-		if (list_is_last(&gdev->list, &gpio_devices))
-			ret = NULL;
-		else
-			ret = list_first_entry(&gdev->list, struct gpio_device,
-					       list);
-	}
+	spin_lock_irqsave(&gpio_lock, flags);
+	if (list_is_last(&gdev->list, &gpio_devices))
+		ret = NULL;
+	else
+		ret = list_first_entry(&gdev->list, struct gpio_device, list);
+	spin_unlock_irqrestore(&gpio_lock, flags);
 
 	s->private = "\n";
 	++*pos;
diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h
index 97df54abf57a..a4a2520b5f31 100644
--- a/drivers/gpio/gpiolib.h
+++ b/drivers/gpio/gpiolib.h
@@ -15,7 +15,6 @@
 #include <linux/gpio/consumer.h> /* for enum gpiod_flags */
 #include <linux/gpio/driver.h>
 #include <linux/module.h>
-#include <linux/mutex.h>
 #include <linux/notifier.h>
 #include <linux/rwsem.h>
 
@@ -137,7 +136,6 @@ int gpiod_set_transitory(struct gpio_desc *desc, bool transitory);
 
 extern spinlock_t gpio_lock;
 extern struct list_head gpio_devices;
-extern struct rw_semaphore gpio_devices_sem;
 
 void gpiod_line_state_notify(struct gpio_desc *desc, unsigned long action);
 
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 2520db0b776e..c7edba18a6f0 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -199,7 +199,7 @@ config DRM_TTM
 config DRM_TTM_KUNIT_TEST
         tristate "KUnit tests for TTM" if !KUNIT_ALL_TESTS
         default n
-        depends on DRM && KUNIT && MMU
+        depends on DRM && KUNIT && MMU && (UML || COMPILE_TEST)
         select DRM_TTM
         select DRM_EXPORT_FOR_TESTS if m
         select DRM_KUNIT_TEST_HELPERS
@@ -207,7 +207,8 @@ config DRM_TTM_KUNIT_TEST
         help
           Enables unit tests for TTM, a GPU memory manager subsystem used
           to manage memory buffers. This option is mostly useful for kernel
-          developers.
+          developers. It depends on (UML || COMPILE_TEST) since no other driver
+          which uses TTM can be loaded while running the tests.
 
           If in doubt, say "N".
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 9da14436a373..79827a6dcd7f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -200,6 +200,7 @@ extern uint amdgpu_dc_debug_mask;
 extern uint amdgpu_dc_visual_confirm;
 extern uint amdgpu_dm_abm_level;
 extern int amdgpu_backlight;
+extern int amdgpu_damage_clips;
 extern struct amdgpu_mgpu_info mgpu_info;
 extern int amdgpu_ras_enable;
 extern uint amdgpu_ras_mask;
@@ -254,8 +255,6 @@ extern int amdgpu_agp;
 
 extern int amdgpu_wbrf;
 
-extern int fw_bo_location;
-
 #define AMDGPU_VM_MAX_NUM_CTX			4096
 #define AMDGPU_SG_THRESHOLD			(256*1024*1024)
 #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS	        3000
@@ -1080,6 +1079,8 @@ struct amdgpu_device {
 	bool				in_s3;
 	bool				in_s4;
 	bool				in_s0ix;
+	/* indicate amdgpu suspension status */
+	bool				suspend_complete;
 
 	enum pp_mp1_state               mp1_state;
 	struct amdgpu_doorbell_index doorbell_index;
@@ -1146,6 +1147,7 @@ struct amdgpu_device {
 	bool                            debug_vm;
 	bool                            debug_largebar;
 	bool                            debug_disable_soft_recovery;
+	bool                            debug_use_vram_fw_buf;
 };
 
 static inline uint32_t amdgpu_ip_version(const struct amdgpu_device *adev,
@@ -1548,9 +1550,11 @@ static inline int amdgpu_acpi_smart_shift_update(struct drm_device *dev,
 #if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND)
 bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev);
 bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev);
+void amdgpu_choose_low_power_state(struct amdgpu_device *adev);
 #else
 static inline bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) { return false; }
 static inline bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev) { return false; }
+static inline void amdgpu_choose_low_power_state(struct amdgpu_device *adev) { }
 #endif
 
 #if defined(CONFIG_DRM_AMD_DC)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 2deebece810e..7099ff9cf8c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -1519,4 +1519,22 @@ bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev)
 #endif /* CONFIG_AMD_PMC */
 }
 
+/**
+ * amdgpu_choose_low_power_state
+ *
+ * @adev: amdgpu_device_pointer
+ *
+ * Choose the target low power state for the GPU
+ */
+void amdgpu_choose_low_power_state(struct amdgpu_device *adev)
+{
+	if (adev->in_runpm)
+		return;
+
+	if (amdgpu_acpi_is_s0ix_active(adev))
+		adev->in_s0ix = true;
+	else if (amdgpu_acpi_is_s3_active(adev))
+		adev->in_s3 = true;
+}
+
 #endif /* CONFIG_SUSPEND */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 067690ba7bff..41db030ddc4e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -138,11 +138,34 @@ static void amdgpu_amdkfd_reset_work(struct work_struct *work)
 	amdgpu_device_gpu_recover(adev, NULL, &reset_context);
 }
 
+static const struct drm_client_funcs kfd_client_funcs = {
+	.unregister	= drm_client_release,
+};
+
+int amdgpu_amdkfd_drm_client_create(struct amdgpu_device *adev)
+{
+	int ret;
+
+	if (!adev->kfd.init_complete)
+		return 0;
+
+	ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd",
+			      &kfd_client_funcs);
+	if (ret) {
+		dev_err(adev->dev, "Failed to init DRM client: %d\n",
+			ret);
+		return ret;
+	}
+
+	drm_client_register(&adev->kfd.client);
+
+	return 0;
+}
+
 void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 {
 	int i;
 	int last_valid_bit;
-	int ret;
 
 	amdgpu_amdkfd_gpuvm_init_mem_limits();
 
@@ -161,12 +184,6 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 			.enable_mes = adev->enable_mes,
 		};
 
-		ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd", NULL);
-		if (ret) {
-			dev_err(adev->dev, "Failed to init DRM client: %d\n", ret);
-			return;
-		}
-
 		/* this is going to have a few of the MSBs set that we need to
 		 * clear
 		 */
@@ -205,10 +222,6 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 
 		adev->kfd.init_complete = kgd2kfd_device_init(adev->kfd.dev,
 							&gpu_resources);
-		if (adev->kfd.init_complete)
-			drm_client_register(&adev->kfd.client);
-		else
-			drm_client_release(&adev->kfd.client);
 
 		amdgpu_amdkfd_total_mem_size += adev->gmc.real_vram_size;
 
@@ -695,10 +708,8 @@ err:
 void amdgpu_amdkfd_set_compute_idle(struct amdgpu_device *adev, bool idle)
 {
 	enum amd_powergating_state state = idle ? AMD_PG_STATE_GATE : AMD_PG_STATE_UNGATE;
-	/* Temporary workaround to fix issues observed in some
-	 * compute applications when GFXOFF is enabled on GFX11.
-	 */
-	if (IP_VERSION_MAJ(amdgpu_ip_version(adev, GC_HWIP, 0)) == 11) {
+	if (IP_VERSION_MAJ(amdgpu_ip_version(adev, GC_HWIP, 0)) == 11 &&
+	    ((adev->mes.kiq_version & AMDGPU_MES_VERSION_MASK) <= 64)) {
 		pr_debug("GFXOFF is %s\n", idle ? "enabled" : "disabled");
 		amdgpu_gfx_off_ctrl(adev, idle);
 	} else if ((IP_VERSION_MAJ(amdgpu_ip_version(adev, GC_HWIP, 0)) == 9) &&
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index cf6ed5fce291..27c61c535e29 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -182,6 +182,8 @@ int amdgpu_queue_mask_bit_to_set_resource_bit(struct amdgpu_device *adev,
 struct amdgpu_amdkfd_fence *amdgpu_amdkfd_fence_create(u64 context,
 				struct mm_struct *mm,
 				struct svm_range_bo *svm_bo);
+
+int amdgpu_amdkfd_drm_client_create(struct amdgpu_device *adev);
 #if defined(CONFIG_DEBUG_FS)
 int kfd_debugfs_kfd_mem_limits(struct seq_file *m, void *data);
 #endif
@@ -301,7 +303,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(struct amdgpu_device *adev,
 					  struct kgd_mem *mem, void *drm_priv);
 int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
 		struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv);
-void amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv);
+int amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv);
 int amdgpu_amdkfd_gpuvm_sync_memory(
 		struct amdgpu_device *adev, struct kgd_mem *mem, bool intr);
 int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_mem *mem,
@@ -311,7 +313,7 @@ void amdgpu_amdkfd_gpuvm_unmap_gtt_bo_from_kernel(struct kgd_mem *mem);
 int amdgpu_amdkfd_map_gtt_bo_to_gart(struct amdgpu_device *adev, struct amdgpu_bo *bo);
 
 int amdgpu_amdkfd_gpuvm_restore_process_bos(void *process_info,
-					    struct dma_fence **ef);
+					    struct dma_fence __rcu **ef);
 int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct amdgpu_device *adev,
 					      struct kfd_vm_fault_info *info);
 int amdgpu_amdkfd_gpuvm_import_dmabuf_fd(struct amdgpu_device *adev, int fd,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
index 899e31e3a5e8..3a3f3ce09f00 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
@@ -290,7 +290,7 @@ static int suspend_resume_compute_scheduler(struct amdgpu_device *adev, bool sus
 	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 		struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];
 
-		if (!(ring && drm_sched_wqueue_ready(&ring->sched)))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 
 		/* stop secheduler and drain ring. */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index d17b2452cb1f..231fd927dcfb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -2085,21 +2085,35 @@ out:
 	return ret;
 }
 
-void amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv)
+int amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv)
 {
 	struct kfd_mem_attachment *entry;
 	struct amdgpu_vm *vm;
+	int ret;
 
 	vm = drm_priv_to_vm(drm_priv);
 
 	mutex_lock(&mem->lock);
 
+	ret = amdgpu_bo_reserve(mem->bo, true);
+	if (ret)
+		goto out;
+
 	list_for_each_entry(entry, &mem->attachments, list) {
-		if (entry->bo_va->base.vm == vm)
-			kfd_mem_dmaunmap_attachment(mem, entry);
+		if (entry->bo_va->base.vm != vm)
+			continue;
+		if (entry->bo_va->base.bo->tbo.ttm &&
+		    !entry->bo_va->base.bo->tbo.ttm->sg)
+			continue;
+
+		kfd_mem_dmaunmap_attachment(mem, entry);
 	}
 
+	amdgpu_bo_unreserve(mem->bo);
+out:
 	mutex_unlock(&mem->lock);
+
+	return ret;
 }
 
 int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
@@ -2802,7 +2816,7 @@ unlock_out:
 	put_task_struct(usertask);
 }
 
-static void replace_eviction_fence(struct dma_fence **ef,
+static void replace_eviction_fence(struct dma_fence __rcu **ef,
 				   struct dma_fence *new_ef)
 {
 	struct dma_fence *old_ef = rcu_replace_pointer(*ef, new_ef, true
@@ -2837,7 +2851,7 @@ static void replace_eviction_fence(struct dma_fence **ef,
  * 7.  Add fence to all PD and PT BOs.
  * 8.  Unreserve all BOs
  */
-int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
+int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu **ef)
 {
 	struct amdkfd_process_info *process_info = info;
 	struct amdgpu_vm *peer_vm;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index e485dd3357c6..1afbb2e932c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1678,7 +1678,7 @@ static int amdgpu_debugfs_test_ib_show(struct seq_file *m, void *unused)
 	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
-		if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 		drm_sched_wqueue_stop(&ring->sched);
 	}
@@ -1694,7 +1694,7 @@ static int amdgpu_debugfs_test_ib_show(struct seq_file *m, void *unused)
 	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
-		if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 		drm_sched_wqueue_start(&ring->sched);
 	}
@@ -1916,8 +1916,8 @@ static int amdgpu_debugfs_ib_preempt(void *data, u64 val)
 
 	ring = adev->rings[val];
 
-	if (!ring || !ring->funcs->preempt_ib ||
-	    !drm_sched_wqueue_ready(&ring->sched))
+	if (!amdgpu_ring_sched_ready(ring) ||
+	    !ring->funcs->preempt_ib)
 		return -EINVAL;
 
 	/* the last preemption failed */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 5bb444bb36ce..94bdb5fa6ebc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1544,6 +1544,7 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev)
 				return true;
 
 			fw_ver = *((uint32_t *)adev->pm.fw->data + 69);
+			release_firmware(adev->pm.fw);
 			if (fw_ver < 0x00160e00)
 				return true;
 		}
@@ -4120,23 +4121,13 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 				}
 			}
 		} else {
-			switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
-			case IP_VERSION(13, 0, 0):
-			case IP_VERSION(13, 0, 7):
-			case IP_VERSION(13, 0, 10):
-				r = psp_gpu_reset(adev);
-				break;
-			default:
-				tmp = amdgpu_reset_method;
-				/* It should do a default reset when loading or reloading the driver,
-				 * regardless of the module parameter reset_method.
-				 */
-				amdgpu_reset_method = AMD_RESET_METHOD_NONE;
-				r = amdgpu_asic_reset(adev);
-				amdgpu_reset_method = tmp;
-				break;
-			}
-
+			tmp = amdgpu_reset_method;
+			/* It should do a default reset when loading or reloading the driver,
+			 * regardless of the module parameter reset_method.
+			 */
+			amdgpu_reset_method = AMD_RESET_METHOD_NONE;
+			r = amdgpu_asic_reset(adev);
+			amdgpu_reset_method = tmp;
 			if (r) {
 				dev_err(adev->dev, "asic reset on init failed\n");
 				goto failed;
@@ -4523,13 +4514,15 @@ int amdgpu_device_prepare(struct drm_device *dev)
 	struct amdgpu_device *adev = drm_to_adev(dev);
 	int i, r;
 
+	amdgpu_choose_low_power_state(adev);
+
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
 	/* Evict the majority of BOs before starting suspend sequence */
 	r = amdgpu_device_evict_resources(adev);
 	if (r)
-		return r;
+		goto unprepare;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if (!adev->ip_blocks[i].status.valid)
@@ -4538,10 +4531,15 @@ int amdgpu_device_prepare(struct drm_device *dev)
 			continue;
 		r = adev->ip_blocks[i].version->funcs->prepare_suspend((void *)adev);
 		if (r)
-			return r;
+			goto unprepare;
 	}
 
 	return 0;
+
+unprepare:
+	adev->in_s0ix = adev->in_s3 = false;
+
+	return r;
 }
 
 /**
@@ -4578,7 +4576,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 		drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true);
 
 	cancel_delayed_work_sync(&adev->delayed_init_work);
-	flush_delayed_work(&adev->gfx.gfx_off_delay_work);
 
 	amdgpu_ras_suspend(adev);
 
@@ -5030,7 +5027,7 @@ bool amdgpu_device_has_job_running(struct amdgpu_device *adev)
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
-		if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 
 		spin_lock(&ring->sched.job_list_lock);
@@ -5169,7 +5166,7 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
-		if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 
 		/* Clear job fence from fence drv to avoid force_completion
@@ -5245,7 +5242,6 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 	struct amdgpu_device *tmp_adev = NULL;
 	bool need_full_reset, skip_hw_reset, vram_lost = false;
 	int r = 0;
-	bool gpu_reset_for_dev_remove = 0;
 
 	/* Try reset handler method first */
 	tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device,
@@ -5265,10 +5261,6 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 		test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags);
 	skip_hw_reset = test_bit(AMDGPU_SKIP_HW_RESET, &reset_context->flags);
 
-	gpu_reset_for_dev_remove =
-		test_bit(AMDGPU_RESET_FOR_DEVICE_REMOVE, &reset_context->flags) &&
-			test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags);
-
 	/*
 	 * ASIC reset has to be done on all XGMI hive nodes ASAP
 	 * to allow proper links negotiation in FW (within 1 sec)
@@ -5311,18 +5303,6 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 		amdgpu_ras_intr_cleared();
 	}
 
-	/* Since the mode1 reset affects base ip blocks, the
-	 * phase1 ip blocks need to be resumed. Otherwise there
-	 * will be a BIOS signature error and the psp bootloader
-	 * can't load kdb on the next amdgpu install.
-	 */
-	if (gpu_reset_for_dev_remove) {
-		list_for_each_entry(tmp_adev, device_list_handle, reset_list)
-			amdgpu_device_ip_resume_phase1(tmp_adev);
-
-		goto end;
-	}
-
 	list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
 		if (need_full_reset) {
 			/* post card */
@@ -5559,11 +5539,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	int i, r = 0;
 	bool need_emergency_restart = false;
 	bool audio_suspended = false;
-	bool gpu_reset_for_dev_remove = false;
-
-	gpu_reset_for_dev_remove =
-			test_bit(AMDGPU_RESET_FOR_DEVICE_REMOVE, &reset_context->flags) &&
-				test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags);
 
 	/*
 	 * Special case: RAS triggered and full reset isn't supported
@@ -5601,7 +5576,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	if (!amdgpu_sriov_vf(adev) && (adev->gmc.xgmi.num_physical_nodes > 1)) {
 		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
 			list_add_tail(&tmp_adev->reset_list, &device_list);
-			if (gpu_reset_for_dev_remove && adev->shutdown)
+			if (adev->shutdown)
 				tmp_adev->shutdown = true;
 		}
 		if (!list_is_first(&adev->reset_list, &device_list))
@@ -5658,7 +5633,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 			struct amdgpu_ring *ring = tmp_adev->rings[i];
 
-			if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+			if (!amdgpu_ring_sched_ready(ring))
 				continue;
 
 			drm_sched_stop(&ring->sched, job ? &job->base : NULL);
@@ -5686,10 +5661,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 
 retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 	list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
-		if (gpu_reset_for_dev_remove) {
-			/* Workaroud for ASICs need to disable SMC first */
-			amdgpu_device_smu_fini_early(tmp_adev);
-		}
 		r = amdgpu_device_pre_asic_reset(tmp_adev, reset_context);
 		/*TODO Should we stop ?*/
 		if (r) {
@@ -5721,9 +5692,6 @@ retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 		r = amdgpu_do_asic_reset(device_list_handle, reset_context);
 		if (r && r == -EAGAIN)
 			goto retry;
-
-		if (!r && gpu_reset_for_dev_remove)
-			goto recover_end;
 	}
 
 skip_hw_reset:
@@ -5734,7 +5702,7 @@ skip_hw_reset:
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 			struct amdgpu_ring *ring = tmp_adev->rings[i];
 
-			if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+			if (!amdgpu_ring_sched_ready(ring))
 				continue;
 
 			drm_sched_start(&ring->sched, true);
@@ -5779,7 +5747,6 @@ skip_sched_resume:
 		amdgpu_ras_set_error_query_ready(tmp_adev, true);
 	}
 
-recover_end:
 	tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device,
 					    reset_list);
 	amdgpu_device_unlock_reset_domain(tmp_adev->reset_domain);
@@ -6090,7 +6057,7 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 			struct amdgpu_ring *ring = adev->rings[i];
 
-			if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+			if (!amdgpu_ring_sched_ready(ring))
 				continue;
 
 			drm_sched_stop(&ring->sched, NULL);
@@ -6218,7 +6185,7 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
-		if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 
 		drm_sched_start(&ring->sched, true);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 0431eafa86b5..c7d60dd0fb97 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -1963,8 +1963,6 @@ static int amdgpu_discovery_set_gc_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
 		break;
 	case IP_VERSION(9, 4, 3):
-		if (!amdgpu_exp_hw_support)
-			return -EINVAL;
 		amdgpu_device_ip_block_add(adev, &gfx_v9_4_3_ip_block);
 		break;
 	case IP_VERSION(10, 1, 10):
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 852cec98ff26..586f4d03039d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -128,6 +128,7 @@ enum AMDGPU_DEBUG_MASK {
 	AMDGPU_DEBUG_VM = BIT(0),
 	AMDGPU_DEBUG_LARGEBAR = BIT(1),
 	AMDGPU_DEBUG_DISABLE_GPU_SOFT_RECOVERY = BIT(2),
+	AMDGPU_DEBUG_USE_VRAM_FW_BUF = BIT(3),
 };
 
 unsigned int amdgpu_vram_limit = UINT_MAX;
@@ -210,7 +211,7 @@ int amdgpu_seamless = -1; /* auto */
 uint amdgpu_debug_mask;
 int amdgpu_agp = -1; /* auto */
 int amdgpu_wbrf = -1;
-int fw_bo_location = -1;
+int amdgpu_damage_clips = -1; /* auto */
 
 static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work);
 
@@ -860,6 +861,18 @@ MODULE_PARM_DESC(backlight, "Backlight control (0 = pwm, 1 = aux, -1 auto (defau
 module_param_named(backlight, amdgpu_backlight, bint, 0444);
 
 /**
+ * DOC: damageclips (int)
+ * Enable or disable damage clips support. If damage clips support is disabled,
+ * we will force full frame updates, irrespective of what user space sends to
+ * us.
+ *
+ * Defaults to -1 (where it is enabled unless a PSR-SU display is detected).
+ */
+MODULE_PARM_DESC(damageclips,
+		 "Damage clips support (0 = disable, 1 = enable, -1 auto (default))");
+module_param_named(damageclips, amdgpu_damage_clips, int, 0444);
+
+/**
  * DOC: tmz (int)
  * Trusted Memory Zone (TMZ) is a method to protect data being written
  * to or read from memory.
@@ -990,10 +1003,6 @@ MODULE_PARM_DESC(wbrf,
 	"Enable Wifi RFI interference mitigation (0 = disabled, 1 = enabled, -1 = auto(default)");
 module_param_named(wbrf, amdgpu_wbrf, int, 0444);
 
-MODULE_PARM_DESC(fw_bo_location,
-	"location to put firmware bo for frontdoor loading (-1 = auto (default), 0 = on ram, 1 = on vram");
-module_param(fw_bo_location, int, 0644);
-
 /* These devices are not supported by amdgpu.
  * They are supported by the mach64, r128, radeon drivers
  */
@@ -2122,6 +2131,11 @@ static void amdgpu_init_debug_options(struct amdgpu_device *adev)
 		pr_info("debug: soft reset for GPU recovery disabled\n");
 		adev->debug_disable_soft_recovery = true;
 	}
+
+	if (amdgpu_debug_mask & AMDGPU_DEBUG_USE_VRAM_FW_BUF) {
+		pr_info("debug: place fw in vram for frontdoor loading\n");
+		adev->debug_use_vram_fw_buf = true;
+	}
 }
 
 static unsigned long amdgpu_fix_asic_type(struct pci_dev *pdev, unsigned long flags)
@@ -2233,6 +2247,8 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 
 	pci_set_drvdata(pdev, ddev);
 
+	amdgpu_init_debug_options(adev);
+
 	ret = amdgpu_driver_load_kms(adev, flags);
 	if (ret)
 		goto err_pci;
@@ -2252,6 +2268,10 @@ retry_init:
 	if (ret)
 		goto err_pci;
 
+	ret = amdgpu_amdkfd_drm_client_create(adev);
+	if (ret)
+		goto err_pci;
+
 	/*
 	 * 1. don't init fbdev on hw without DCE
 	 * 2. don't init fbdev if there are no connectors
@@ -2313,8 +2333,6 @@ retry_init:
 			amdgpu_get_secondary_funcs(adev);
 	}
 
-	amdgpu_init_debug_options(adev);
-
 	return 0;
 
 err_pci:
@@ -2336,38 +2354,6 @@ amdgpu_pci_remove(struct pci_dev *pdev)
 		pm_runtime_forbid(dev->dev);
 	}
 
-	if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 2) &&
-	    !amdgpu_sriov_vf(adev)) {
-		bool need_to_reset_gpu = false;
-
-		if (adev->gmc.xgmi.num_physical_nodes > 1) {
-			struct amdgpu_hive_info *hive;
-
-			hive = amdgpu_get_xgmi_hive(adev);
-			if (hive->device_remove_count == 0)
-				need_to_reset_gpu = true;
-			hive->device_remove_count++;
-			amdgpu_put_xgmi_hive(hive);
-		} else {
-			need_to_reset_gpu = true;
-		}
-
-		/* Workaround for ASICs need to reset SMU.
-		 * Called only when the first device is removed.
-		 */
-		if (need_to_reset_gpu) {
-			struct amdgpu_reset_context reset_context;
-
-			adev->shutdown = true;
-			memset(&reset_context, 0, sizeof(reset_context));
-			reset_context.method = AMD_RESET_METHOD_NONE;
-			reset_context.reset_req_dev = adev;
-			set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
-			set_bit(AMDGPU_RESET_FOR_DEVICE_REMOVE, &reset_context.flags);
-			amdgpu_device_gpu_recover(adev, NULL, &reset_context);
-		}
-	}
-
 	amdgpu_driver_unload_kms(dev);
 
 	/*
@@ -2503,6 +2489,7 @@ static int amdgpu_pmops_suspend(struct device *dev)
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 
+	adev->suspend_complete = false;
 	if (amdgpu_acpi_is_s0ix_active(adev))
 		adev->in_s0ix = true;
 	else if (amdgpu_acpi_is_s3_active(adev))
@@ -2517,6 +2504,7 @@ static int amdgpu_pmops_suspend_noirq(struct device *dev)
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 
+	adev->suspend_complete = true;
 	if (amdgpu_acpi_should_gpu_reset(adev))
 		return amdgpu_asic_reset(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index 73b8cca35bab..c623e23049d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -121,6 +121,7 @@ int amdgpu_gart_table_ram_alloc(struct amdgpu_device *adev)
 	struct amdgpu_bo_param bp;
 	dma_addr_t dma_addr;
 	struct page *p;
+	unsigned long x;
 	int ret;
 
 	if (adev->gart.bo != NULL)
@@ -130,6 +131,10 @@ int amdgpu_gart_table_ram_alloc(struct amdgpu_device *adev)
 	if (!p)
 		return -ENOMEM;
 
+	/* assign pages to this device */
+	for (x = 0; x < (1UL << order); x++)
+		p[x].mapping = adev->mman.bdev.dev_mapping;
+
 	/* If the hardware does not support UTCL2 snooping of the CPU caches
 	 * then set_memory_wc() could be used as a workaround to mark the pages
 	 * as write combine memory.
@@ -223,6 +228,7 @@ void amdgpu_gart_table_ram_free(struct amdgpu_device *adev)
 	unsigned int order = get_order(adev->gart.table_size);
 	struct sg_table *sg = adev->gart.bo->tbo.sg;
 	struct page *p;
+	unsigned long x;
 	int ret;
 
 	ret = amdgpu_bo_reserve(adev->gart.bo, false);
@@ -234,6 +240,8 @@ void amdgpu_gart_table_ram_free(struct amdgpu_device *adev)
 	sg_free_table(sg);
 	kfree(sg);
 	p = virt_to_page(adev->gart.ptr);
+	for (x = 0; x < (1UL << order); x++)
+		p[x].mapping = NULL;
 	__free_pages(p, order);
 
 	adev->gart.ptr = NULL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index b9674c57c436..6ddc8e3360e2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -723,8 +723,15 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
 
 		if (adev->gfx.gfx_off_req_count == 0 &&
 		    !adev->gfx.gfx_off_state) {
-			schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
+			/* If going to s2idle, no need to wait */
+			if (adev->in_s0ix) {
+				if (!amdgpu_dpm_set_powergating_by_smu(adev,
+						AMD_IP_BLOCK_TYPE_GFX, true))
+					adev->gfx.gfx_off_state = true;
+			} else {
+				schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
 					      delay);
+			}
 		}
 	} else {
 		if (adev->gfx.gfx_off_req_count == 0) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index d2f273d77e59..55784a9f26c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -1045,21 +1045,28 @@ int amdgpu_gmc_vram_checking(struct amdgpu_device *adev)
 	 * seconds, so here, we just pick up three parts for emulation.
 	 */
 	ret = memcmp(vram_ptr, cptr, 10);
-	if (ret)
-		return ret;
+	if (ret) {
+		ret = -EIO;
+		goto release_buffer;
+	}
 
 	ret = memcmp(vram_ptr + (size / 2), cptr, 10);
-	if (ret)
-		return ret;
+	if (ret) {
+		ret = -EIO;
+		goto release_buffer;
+	}
 
 	ret = memcmp(vram_ptr + size - 10, cptr, 10);
-	if (ret)
-		return ret;
+	if (ret) {
+		ret = -EIO;
+		goto release_buffer;
+	}
 
+release_buffer:
 	amdgpu_bo_free_kernel(&vram_bo, &vram_gpu,
 			&vram_ptr);
 
-	return 0;
+	return ret;
 }
 
 static ssize_t current_memory_partition_show(
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
index 82608df43396..d79cb13e1aa8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
@@ -175,7 +175,6 @@ struct amdgpu_i2c_chan *amdgpu_i2c_create(struct drm_device *dev,
 
 	i2c->rec = *rec;
 	i2c->adapter.owner = THIS_MODULE;
-	i2c->adapter.class = I2C_CLASS_DDC;
 	i2c->adapter.dev.parent = dev->dev;
 	i2c->dev = dev;
 	i2c_set_adapdata(&i2c->adapter, i2c);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index b5ebafd4a3ad..bf4f48fe438d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -1105,7 +1105,12 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 			if (amdgpu_dpm_read_sensor(adev,
 						   AMDGPU_PP_SENSOR_GPU_AVG_POWER,
 						   (void *)&ui32, &ui32_size)) {
-				return -EINVAL;
+				/* fall back to input power for backwards compat */
+				if (amdgpu_dpm_read_sensor(adev,
+							   AMDGPU_PP_SENSOR_GPU_INPUT_POWER,
+							   (void *)&ui32, &ui32_size)) {
+					return -EINVAL;
+				}
 			}
 			ui32 >>= 8;
 			break;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 2addbdf88394..0328616473f8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -466,7 +466,7 @@ static int psp_sw_init(void *handle)
 	}
 
 	ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
-				      (amdgpu_sriov_vf(adev) || fw_bo_location == 1) ?
+				      (amdgpu_sriov_vf(adev) || adev->debug_use_vram_fw_buf) ?
 				      AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
 				      &psp->fw_pri_bo,
 				      &psp->fw_pri_mc_addr,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
index 468a67b302d4..ca5c86e5f7cd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
@@ -362,7 +362,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 		}
 	}
 
-	if (copy_to_user((char *)buf, context->mem_context.shared_buf, shared_buf_len))
+	if (copy_to_user((char *)&buf[copy_pos], context->mem_context.shared_buf, shared_buf_len))
 		ret = -EFAULT;
 
 err_free_shared_buf:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index fc42fb6ee191..31823a30dea2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -305,11 +305,13 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f,
 			return -EINVAL;
 
 		data->head.block = block_id;
-		/* only ue and ce errors are supported */
+		/* only ue, ce and poison errors are supported */
 		if (!memcmp("ue", err, 2))
 			data->head.type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
 		else if (!memcmp("ce", err, 2))
 			data->head.type = AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE;
+		else if (!memcmp("poison", err, 6))
+			data->head.type = AMDGPU_RAS_ERROR__POISON;
 		else
 			return -EINVAL;
 
@@ -431,9 +433,10 @@ static void amdgpu_ras_instance_mask_check(struct amdgpu_device *adev,
  * The block is one of: umc, sdma, gfx, etc.
  *	see ras_block_string[] for details
  *
- * The error type is one of: ue, ce, where,
+ * The error type is one of: ue, ce and poison where,
  *	ue is multi-uncorrectable
  *	ce is single-correctable
+ *	poison is poison
  *
  * The sub-block is a the sub-block index, pass 0 if there is no sub-block.
  * The address and value are hexadecimal numbers, leading 0x is optional.
@@ -1067,8 +1070,7 @@ static void amdgpu_ras_error_print_error_data(struct amdgpu_device *adev,
 			mcm_info = &err_info->mcm_info;
 			if (err_info->ce_count) {
 				dev_info(adev->dev, "socket: %d, die: %d, "
-					 "%lld new correctable hardware errors detected in %s block, "
-					 "no user action is needed\n",
+					 "%lld new correctable hardware errors detected in %s block\n",
 					 mcm_info->socket_id,
 					 mcm_info->die_id,
 					 err_info->ce_count,
@@ -1080,8 +1082,7 @@ static void amdgpu_ras_error_print_error_data(struct amdgpu_device *adev,
 			err_info = &err_node->err_info;
 			mcm_info = &err_info->mcm_info;
 			dev_info(adev->dev, "socket: %d, die: %d, "
-				 "%lld correctable hardware errors detected in total in %s block, "
-				 "no user action is needed\n",
+				 "%lld correctable hardware errors detected in total in %s block\n",
 				 mcm_info->socket_id, mcm_info->die_id, err_info->ce_count, blk_name);
 		}
 	}
@@ -1108,16 +1109,14 @@ static void amdgpu_ras_error_generate_report(struct amdgpu_device *adev,
 			   adev->smuio.funcs->get_die_id) {
 			dev_info(adev->dev, "socket: %d, die: %d "
 				 "%ld correctable hardware errors "
-				 "detected in %s block, no user "
-				 "action is needed.\n",
+				 "detected in %s block\n",
 				 adev->smuio.funcs->get_socket_id(adev),
 				 adev->smuio.funcs->get_die_id(adev),
 				 ras_mgr->err_data.ce_count,
 				 blk_name);
 		} else {
 			dev_info(adev->dev, "%ld correctable hardware errors "
-				 "detected in %s block, no user "
-				 "action is needed.\n",
+				 "detected in %s block\n",
 				 ras_mgr->err_data.ce_count,
 				 blk_name);
 		}
@@ -1920,7 +1919,7 @@ static void amdgpu_ras_interrupt_poison_creation_handler(struct ras_manager *obj
 				struct amdgpu_iv_entry *entry)
 {
 	dev_info(obj->adev->dev,
-		"Poison is created, no user action is needed.\n");
+		"Poison is created\n");
 }
 
 static void amdgpu_ras_interrupt_umc_handler(struct ras_manager *obj,
@@ -2920,6 +2919,11 @@ int amdgpu_ras_init(struct amdgpu_device *adev)
 
 	amdgpu_ras_query_poison_mode(adev);
 
+	/* Packed socket_id to ras feature mask bits[31:29] */
+	if (adev->smuio.funcs &&
+	    adev->smuio.funcs->get_socket_id)
+		con->features |= ((adev->smuio.funcs->get_socket_id(adev)) << 29);
+
 	/* Get RAS schema for particular SOC */
 	con->schema = amdgpu_get_ras_schema(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
index b0335a1c5e90..19899f6b9b2b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
@@ -32,7 +32,6 @@ enum AMDGPU_RESET_FLAGS {
 
 	AMDGPU_NEED_FULL_RESET = 0,
 	AMDGPU_SKIP_HW_RESET = 1,
-	AMDGPU_RESET_FOR_DEVICE_REMOVE = 2,
 };
 
 struct amdgpu_reset_context {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 45424ebf9681..5505d646f43a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -635,6 +635,7 @@ int amdgpu_ring_test_helper(struct amdgpu_ring *ring)
 			      ring->name);
 
 	ring->sched.ready = !r;
+
 	return r;
 }
 
@@ -717,3 +718,14 @@ void amdgpu_ring_ib_on_emit_de(struct amdgpu_ring *ring)
 	if (ring->is_sw_ring)
 		amdgpu_sw_ring_ib_mark_offset(ring, AMDGPU_MUX_OFFSET_TYPE_DE);
 }
+
+bool amdgpu_ring_sched_ready(struct amdgpu_ring *ring)
+{
+	if (!ring)
+		return false;
+
+	if (ring->no_scheduler || !drm_sched_wqueue_ready(&ring->sched))
+		return false;
+
+	return true;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index bbb53720a018..fe1a61eb6e4c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -450,5 +450,5 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 int amdgpu_ib_pool_init(struct amdgpu_device *adev);
 void amdgpu_ib_pool_fini(struct amdgpu_device *adev);
 int amdgpu_ib_ring_tests(struct amdgpu_device *adev);
-
+bool amdgpu_ring_sched_ready(struct amdgpu_ring *ring);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index d334e42fe0eb..3e12763e477a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -1062,7 +1062,7 @@ int amdgpu_ucode_create_bo(struct amdgpu_device *adev)
 {
 	if (adev->firmware.load_type != AMDGPU_FW_LOAD_DIRECT) {
 		amdgpu_bo_create_kernel(adev, adev->firmware.fw_size, PAGE_SIZE,
-			(amdgpu_sriov_vf(adev) || fw_bo_location == 1) ?
+			(amdgpu_sriov_vf(adev) || adev->debug_use_vram_fw_buf) ?
 			AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
 			&adev->firmware.fw_buf,
 			&adev->firmware.fw_buf_mc,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index b6cd565562ad..4740dd65b99d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -116,7 +116,7 @@ struct amdgpu_mem_stats;
 #define AMDGPU_VM_FAULT_STOP_FIRST	1
 #define AMDGPU_VM_FAULT_STOP_ALWAYS	2
 
-/* Reserve 4MB VRAM for page tables */
+/* How much VRAM be reserved for page tables */
 #define AMDGPU_VM_RESERVED_VRAM		(8ULL << 20)
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
index 6f149b54d4d3..b9a15d51eb5c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
@@ -59,11 +59,8 @@ static inline uint16_t complete_integer_division_u16(
 
 static uint16_t vpe_u1_8_from_fraction(uint16_t numerator, uint16_t denominator)
 {
-	bool arg1_negative = numerator < 0;
-	bool arg2_negative = denominator < 0;
-
-	uint16_t arg1_value = (uint16_t)(arg1_negative ? -numerator : numerator);
-	uint16_t arg2_value = (uint16_t)(arg2_negative ? -denominator : denominator);
+	u16 arg1_value = numerator;
+	u16 arg2_value = denominator;
 
 	uint16_t remainder;
 
@@ -100,9 +97,6 @@ static uint16_t vpe_u1_8_from_fraction(uint16_t numerator, uint16_t denominator)
 		res_value += summand;
 	}
 
-	if (arg1_negative ^ arg2_negative)
-		res_value = -res_value;
-
 	return res_value;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 08916538a615..8db880244324 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -221,8 +221,23 @@ static struct attribute *amdgpu_vram_mgr_attributes[] = {
 	NULL
 };
 
+static umode_t amdgpu_vram_attrs_is_visible(struct kobject *kobj,
+					    struct attribute *attr, int i)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+
+	if (attr == &dev_attr_mem_info_vram_vendor.attr &&
+	    !adev->gmc.vram_vendor)
+		return 0;
+
+	return attr->mode;
+}
+
 const struct attribute_group amdgpu_vram_mgr_attr_group = {
-	.attrs = amdgpu_vram_mgr_attributes
+	.attrs = amdgpu_vram_mgr_attributes,
+	.is_visible = amdgpu_vram_attrs_is_visible
 };
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
index 6cab882e8061..1592c63b3099 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
@@ -43,7 +43,6 @@ struct amdgpu_hive_info {
 	} pstate;
 
 	struct amdgpu_reset_domain *reset_domain;
-	uint32_t device_remove_count;
 	atomic_t ras_recovery;
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c b/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c
index f0737fb3a999..d1bba9c64e16 100644
--- a/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c
@@ -30,6 +30,8 @@
 
 #define regATHUB_MISC_CNTL_V3_0_1			0x00d7
 #define regATHUB_MISC_CNTL_V3_0_1_BASE_IDX		0
+#define regATHUB_MISC_CNTL_V3_3_0			0x00d8
+#define regATHUB_MISC_CNTL_V3_3_0_BASE_IDX		0
 
 
 static uint32_t athub_v3_0_get_cg_cntl(struct amdgpu_device *adev)
@@ -40,6 +42,9 @@ static uint32_t athub_v3_0_get_cg_cntl(struct amdgpu_device *adev)
 	case IP_VERSION(3, 0, 1):
 		data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_0_1);
 		break;
+	case IP_VERSION(3, 3, 0):
+		data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_3_0);
+		break;
 	default:
 		data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL);
 		break;
@@ -53,6 +58,9 @@ static void athub_v3_0_set_cg_cntl(struct amdgpu_device *adev, uint32_t data)
 	case IP_VERSION(3, 0, 1):
 		WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_0_1, data);
 		break;
+	case IP_VERSION(3, 3, 0):
+		WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_3_0, data);
+		break;
 	default:
 		WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL, data);
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
index 6f7c031dd197..f24e34dc33d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
@@ -204,6 +204,12 @@ static u32 cik_ih_get_wptr(struct amdgpu_device *adev,
 		tmp = RREG32(mmIH_RB_CNTL);
 		tmp |= IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK;
 		WREG32(mmIH_RB_CNTL, tmp);
+
+		/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+		 * can be detected.
+		 */
+		tmp &= ~IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK;
+		WREG32(mmIH_RB_CNTL, tmp);
 	}
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
index b8c47e0cf37a..c19681492efa 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
@@ -216,6 +216,11 @@ static u32 cz_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32(mmIH_RB_CNTL, tmp);
 
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32(mmIH_RB_CNTL, tmp);
 
 out:
 	return (wptr & ih->ptr_mask);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 73f6d7e72c73..dcdecb18b230 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -3996,16 +3996,13 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 
 	if (!amdgpu_sriov_vf(adev)) {
 		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", ucode_prefix);
-		err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw, fw_name);
-		/* don't check this.  There are apparently firmwares in the wild with
-		 * incorrect size in the header
-		 */
-		if (err == -ENODEV)
-			goto out;
+		err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev);
 		if (err)
-			dev_dbg(adev->dev,
-				"gfx10: amdgpu_ucode_request() failed \"%s\"\n",
-				fw_name);
+			goto out;
+
+		/* don't validate this firmware. There are apparently firmwares
+		 * in the wild with incorrect size in the header
+		 */
 		rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
 		version_major = le16_to_cpu(rlc_hdr->header.header_version_major);
 		version_minor = le16_to_cpu(rlc_hdr->header.header_version_minor);
@@ -4030,8 +4027,6 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 		err = 0;
 		adev->gfx.mec2_fw = NULL;
 	}
-	amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2);
-	amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2_JT);
 
 	gfx_v10_0_check_fw_write_wait(adev);
 out:
@@ -6592,7 +6587,7 @@ static int gfx_v10_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 #ifdef __BIG_ENDIAN
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, ENDIAN_SWAP, 1);
 #endif
-	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 0);
+	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 1);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TUNNEL_DISPATCH,
 			    prop->allow_tunneling);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 2fbcd9765980..4f3bfdc75b37 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -107,23 +107,6 @@ static const struct soc15_reg_golden golden_settings_gc_11_0_1[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, regTCP_CNTL2, 0xfcffffff, 0x0000000a)
 };
 
-static const struct soc15_reg_golden golden_settings_gc_11_5_0[] = {
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regDB_DEBUG5, 0xffffffff, 0x00000800),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGB_ADDR_CONFIG, 0x0c1807ff, 0x00000242),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2A_ADDR_MATCH_MASK, 0xffffffff, 0xfffffff3),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_ADDR_MATCH_MASK, 0xffffffff, 0xfffffff3),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL, 0xffffffff, 0xf37fff3f),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL3, 0xfffffffb, 0x00f40188),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL4, 0xf0ffffff, 0x8000b007),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regPA_CL_ENHANCE, 0xf1ffffff, 0x00880007),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regPC_CONFIG_CNTL_1, 0xffffffff, 0x00010000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regTA_CNTL_AUX, 0xf7f7ffff, 0x01030000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regTA_CNTL2, 0x007f0000, 0x00000000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regTCP_CNTL2, 0xffcfffff, 0x0000200a),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regUTCL1_CTRL_2, 0xffffffff, 0x0000048f)
-};
-
 #define DEFAULT_SH_MEM_CONFIG \
 	((SH_MEM_ADDRESS_MODE_64 << SH_MEM_CONFIG__ADDRESS_MODE__SHIFT) | \
 	 (SH_MEM_ALIGNMENT_MODE_UNALIGNED << SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | \
@@ -304,11 +287,6 @@ static void gfx_v11_0_init_golden_registers(struct amdgpu_device *adev)
 						golden_settings_gc_11_0_1,
 						(const u32)ARRAY_SIZE(golden_settings_gc_11_0_1));
 		break;
-	case IP_VERSION(11, 5, 0):
-		soc15_program_register_sequence(adev,
-						golden_settings_gc_11_5_0,
-						(const u32)ARRAY_SIZE(golden_settings_gc_11_5_0));
-		break;
 	default:
 		break;
 	}
@@ -3846,7 +3824,7 @@ static int gfx_v11_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 			    (order_base_2(prop->queue_size / 4) - 1));
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, RPTR_BLOCK_SIZE,
 			    (order_base_2(AMDGPU_GPU_PAGE_SIZE / 4) - 1));
-	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 0);
+	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 1);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TUNNEL_DISPATCH,
 			    prop->allow_tunneling);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
@@ -6383,6 +6361,9 @@ static int gfx_v11_0_get_cu_info(struct amdgpu_device *adev,
 	mutex_lock(&adev->grbm_idx_mutex);
 	for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
 		for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
+			bitmap = i * adev->gfx.config.max_sh_per_se + j;
+			if (!((gfx_v11_0_get_sa_active_bitmap(adev) >> bitmap) & 1))
+				continue;
 			mask = 1;
 			counter = 0;
 			gfx_v11_0_select_se_sh(adev, i, j, 0xffffffff, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 69c500910746..3bc6943365a4 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3034,6 +3034,14 @@ static int gfx_v9_0_cp_gfx_start(struct amdgpu_device *adev)
 
 	gfx_v9_0_cp_gfx_enable(adev, true);
 
+	/* Now only limit the quirk on the APU gfx9 series and already
+	 * confirmed that the APU gfx10/gfx11 needn't such update.
+	 */
+	if (adev->flags & AMD_IS_APU &&
+			adev->in_s3 && !adev->suspend_complete) {
+		DRM_INFO(" Will skip the CSB packet resubmit\n");
+		return 0;
+	}
 	r = amdgpu_ring_alloc(ring, gfx_v9_0_get_csb_size(adev) + 4 + 3);
 	if (r) {
 		DRM_ERROR("amdgpu: cp failed to lock ring (%d).\n", r);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
index 95d06da544e2..49aecdcee006 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
@@ -456,10 +456,12 @@ static void gfxhub_v1_2_xcc_gart_disable(struct amdgpu_device *adev,
 		WREG32_SOC15_RLC(GC, GET_INST(GC, j), regMC_VM_MX_L1_TLB_CNTL, tmp);
 
 		/* Setup L2 cache */
-		tmp = RREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL);
-		tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_L2_CACHE, 0);
-		WREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL, tmp);
-		WREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL3, 0);
+		if (!amdgpu_sriov_vf(adev)) {
+			tmp = RREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL);
+			tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_L2_CACHE, 0);
+			WREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL, tmp);
+			WREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL3, 0);
+		}
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index 42e103d7077d..59d9215e5556 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -915,8 +915,8 @@ static int gmc_v6_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 static int gmc_v6_0_hw_fini(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index efc16e580f1e..45a2f8e031a2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -1099,8 +1099,8 @@ static int gmc_v7_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 static int gmc_v7_0_hw_fini(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index ff4ae73d27ec..4422b27a3cc2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -1219,8 +1219,8 @@ static int gmc_v8_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 static int gmc_v8_0_hw_fini(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index f9039d64ff2d..e67a62db9e12 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1947,13 +1947,6 @@ static int gmc_v9_0_init_mem_ranges(struct amdgpu_device *adev)
 
 static void gmc_v9_4_3_init_vram_info(struct amdgpu_device *adev)
 {
-	static const u32 regBIF_BIOS_SCRATCH_4 = 0x50;
-	u32 vram_info;
-
-	if (!amdgpu_sriov_vf(adev)) {
-		vram_info = RREG32(regBIF_BIOS_SCRATCH_4);
-		adev->gmc.vram_vendor = vram_info & 0xF;
-	}
 	adev->gmc.vram_type = AMDGPU_VRAM_TYPE_HBM;
 	adev->gmc.vram_width = 128 * 64;
 }
@@ -2340,8 +2333,8 @@ static int gmc_v9_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
index aecad530b10a..2c02ae69883d 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
@@ -215,6 +215,11 @@ static u32 iceland_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32(mmIH_RB_CNTL, tmp);
 
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32(mmIH_RB_CNTL, tmp);
 
 out:
 	return (wptr & ih->ptr_mask);
diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
index d9ed7332d805..ad4ad39f128f 100644
--- a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
@@ -418,6 +418,12 @@ static u32 ih_v6_0_get_wptr(struct amdgpu_device *adev,
 	tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl);
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
 out:
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c
index 8fb05eae340a..b8da0fc29378 100644
--- a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c
@@ -418,6 +418,13 @@ static u32 ih_v6_1_get_wptr(struct amdgpu_device *adev,
 	tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl);
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
 out:
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
index bc38b90f8cf8..88ea58d5c4ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
@@ -674,14 +674,6 @@ static int jpeg_v4_0_set_powergating_state(void *handle,
 	return ret;
 }
 
-static int jpeg_v4_0_set_interrupt_state(struct amdgpu_device *adev,
-					struct amdgpu_irq_src *source,
-					unsigned type,
-					enum amdgpu_interrupt_state state)
-{
-	return 0;
-}
-
 static int jpeg_v4_0_set_ras_interrupt_state(struct amdgpu_device *adev,
 					struct amdgpu_irq_src *source,
 					unsigned int type,
@@ -765,7 +757,6 @@ static void jpeg_v4_0_set_dec_ring_funcs(struct amdgpu_device *adev)
 }
 
 static const struct amdgpu_irq_src_funcs jpeg_v4_0_irq_funcs = {
-	.set = jpeg_v4_0_set_interrupt_state,
 	.process = jpeg_v4_0_process_interrupt,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
index 6ede85b28cc8..78b74daf4eeb 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
@@ -181,7 +181,6 @@ static int jpeg_v4_0_5_hw_fini(void *handle)
 			RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS))
 			jpeg_v4_0_5_set_powergating_state(adev, AMD_PG_STATE_GATE);
 	}
-	amdgpu_irq_put(adev, &adev->jpeg.inst->irq, 0);
 
 	return 0;
 }
@@ -516,14 +515,6 @@ static int jpeg_v4_0_5_set_powergating_state(void *handle,
 	return ret;
 }
 
-static int jpeg_v4_0_5_set_interrupt_state(struct amdgpu_device *adev,
-					struct amdgpu_irq_src *source,
-					unsigned type,
-					enum amdgpu_interrupt_state state)
-{
-	return 0;
-}
-
 static int jpeg_v4_0_5_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_irq_src *source,
 				      struct amdgpu_iv_entry *entry)
@@ -603,7 +594,6 @@ static void jpeg_v4_0_5_set_dec_ring_funcs(struct amdgpu_device *adev)
 }
 
 static const struct amdgpu_irq_src_funcs jpeg_v4_0_5_irq_funcs = {
-	.set = jpeg_v4_0_5_set_interrupt_state,
 	.process = jpeg_v4_0_5_process_interrupt,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
index e64b33115848..de93614726c9 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
@@ -442,6 +442,12 @@ static u32 navi10_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl);
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
 out:
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index 6d24c84924cb..19986ff6a48d 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -401,8 +401,7 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device
 
 			if (err_data.ce_count)
 				dev_info(adev->dev, "%ld correctable hardware "
-						"errors detected in %s block, "
-						"no user action is needed.\n",
+						"errors detected in %s block\n",
 						obj->err_data.ce_count,
 						get_ras_block_str(adev->nbio.ras_if));
 
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
index 25a3da83e0fb..b4723d68eab0 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
@@ -431,6 +431,12 @@ static void nbio_v7_9_init_registers(struct amdgpu_device *adev)
 	u32 inst_mask;
 	int i;
 
+	if (amdgpu_sriov_vf(adev))
+		adev->rmmio_remap.reg_offset =
+			SOC15_REG_OFFSET(
+				NBIO, 0,
+				regBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL)
+			<< 2;
 	WREG32_SOC15(NBIO, 0, regXCC_DOORBELL_FENCE,
 		0xff & ~(adev->gfx.xcc_mask));
 
@@ -597,8 +603,7 @@ static void nbio_v7_9_handle_ras_controller_intr_no_bifring(struct amdgpu_device
 
 			if (err_data.ce_count)
 				dev_info(adev->dev, "%ld correctable hardware "
-						"errors detected in %s block, "
-						"no user action is needed.\n",
+						"errors detected in %s block\n",
 						obj->err_data.ce_count,
 						get_ras_block_str(adev->nbio.ras_if));
 
diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c b/drivers/gpu/drm/amd/amdgpu/si_ih.c
index 9a24f17a5750..cada9f300a7f 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c
@@ -119,6 +119,12 @@ static u32 si_ih_get_wptr(struct amdgpu_device *adev,
 		tmp = RREG32(IH_RB_CNTL);
 		tmp |= IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK;
 		WREG32(IH_RB_CNTL, tmp);
+
+		/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+		 * can be detected.
+		 */
+		tmp &= ~IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK;
+		WREG32(IH_RB_CNTL, tmp);
 	}
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 15033efec2ba..1c614451dead 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -574,11 +574,34 @@ soc15_asic_reset_method(struct amdgpu_device *adev)
 		return AMD_RESET_METHOD_MODE1;
 }
 
+static bool soc15_need_reset_on_resume(struct amdgpu_device *adev)
+{
+	u32 sol_reg;
+
+	sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
+
+	/* Will reset for the following suspend abort cases.
+	 * 1) Only reset limit on APU side, dGPU hasn't checked yet.
+	 * 2) S3 suspend abort and TOS already launched.
+	 */
+	if (adev->flags & AMD_IS_APU && adev->in_s3 &&
+			!adev->suspend_complete &&
+			sol_reg)
+		return true;
+
+	return false;
+}
+
 static int soc15_asic_reset(struct amdgpu_device *adev)
 {
 	/* original raven doesn't have full asic reset */
-	if ((adev->apu_flags & AMD_APU_IS_RAVEN) ||
-	    (adev->apu_flags & AMD_APU_IS_RAVEN2))
+	/* On the latest Raven, the GPU reset can be performed
+	 * successfully. So now, temporarily enable it for the
+	 * S3 suspend abort case.
+	 */
+	if (((adev->apu_flags & AMD_APU_IS_RAVEN) ||
+	    (adev->apu_flags & AMD_APU_IS_RAVEN2)) &&
+		!soc15_need_reset_on_resume(adev))
 		return 0;
 
 	switch (soc15_asic_reset_method(adev)) {
@@ -1302,6 +1325,10 @@ static int soc15_common_resume(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (soc15_need_reset_on_resume(adev)) {
+		dev_info(adev->dev, "S3 suspend abort case, let's reset ASIC.\n");
+		soc15_asic_reset(adev);
+	}
 	return soc15_common_hw_init(adev);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 48c6efcdeac9..4d7188912edf 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -50,13 +50,13 @@ static const struct amd_ip_funcs soc21_common_ip_funcs;
 /* SOC21 */
 static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn0[] = {
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
 
 static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn1[] = {
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 };
 
 static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_encode_vcn0 = {
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
index 917707bba7f3..450b6e831509 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
@@ -219,6 +219,12 @@ static u32 tonga_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32(mmIH_RB_CNTL, tmp);
 
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32(mmIH_RB_CNTL, tmp);
+
 out:
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
index 530549314ce4..a3ee3c4c650f 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
@@ -64,7 +64,7 @@ static void umc_v6_7_query_error_status_helper(struct amdgpu_device *adev,
 	uint64_t reg_value;
 
 	if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1)
-		dev_info(adev->dev, "Deferred error, no user action is needed.\n");
+		dev_info(adev->dev, "Deferred error\n");
 
 	if (mc_umc_status)
 		dev_info(adev->dev, "MCA STATUS 0x%llx, umc_reg_offset 0x%x\n", mc_umc_status, umc_reg_offset);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index 169ed400ee7b..8ab01ae919d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -2018,22 +2018,6 @@ static int vcn_v4_0_set_powergating_state(void *handle, enum amd_powergating_sta
 }
 
 /**
- * vcn_v4_0_set_interrupt_state - set VCN block interrupt state
- *
- * @adev: amdgpu_device pointer
- * @source: interrupt sources
- * @type: interrupt types
- * @state: interrupt states
- *
- * Set VCN block interrupt state
- */
-static int vcn_v4_0_set_interrupt_state(struct amdgpu_device *adev, struct amdgpu_irq_src *source,
-      unsigned type, enum amdgpu_interrupt_state state)
-{
-	return 0;
-}
-
-/**
  * vcn_v4_0_set_ras_interrupt_state - set VCN block RAS interrupt state
  *
  * @adev: amdgpu_device pointer
@@ -2097,7 +2081,6 @@ static int vcn_v4_0_process_interrupt(struct amdgpu_device *adev, struct amdgpu_
 }
 
 static const struct amdgpu_irq_src_funcs vcn_v4_0_irq_funcs = {
-	.set = vcn_v4_0_set_interrupt_state,
 	.process = vcn_v4_0_process_interrupt,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
index 2eda30e78f61..49e4c3c09aca 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -269,8 +269,6 @@ static int vcn_v4_0_5_hw_fini(void *handle)
 				vcn_v4_0_5_set_powergating_state(adev, AMD_PG_STATE_GATE);
 			}
 		}
-
-		amdgpu_irq_put(adev, &adev->vcn.inst[i].irq, 0);
 	}
 
 	return 0;
@@ -1669,22 +1667,6 @@ static int vcn_v4_0_5_set_powergating_state(void *handle, enum amd_powergating_s
 }
 
 /**
- * vcn_v4_0_5_set_interrupt_state - set VCN block interrupt state
- *
- * @adev: amdgpu_device pointer
- * @source: interrupt sources
- * @type: interrupt types
- * @state: interrupt states
- *
- * Set VCN block interrupt state
- */
-static int vcn_v4_0_5_set_interrupt_state(struct amdgpu_device *adev, struct amdgpu_irq_src *source,
-		unsigned type, enum amdgpu_interrupt_state state)
-{
-	return 0;
-}
-
-/**
  * vcn_v4_0_5_process_interrupt - process VCN block interrupt
  *
  * @adev: amdgpu_device pointer
@@ -1726,7 +1708,6 @@ static int vcn_v4_0_5_process_interrupt(struct amdgpu_device *adev, struct amdgp
 }
 
 static const struct amdgpu_irq_src_funcs vcn_v4_0_5_irq_funcs = {
-	.set = vcn_v4_0_5_set_interrupt_state,
 	.process = vcn_v4_0_5_process_interrupt,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
index d364c6dd152c..bf68e18e3824 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
@@ -373,6 +373,12 @@ static u32 vega10_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
 
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
 out:
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
index ddfc6941f9d5..db66e6cccaf2 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
@@ -421,6 +421,12 @@ static u32 vega20_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
 
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
 out:
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
index df75863393fc..d1caaf0e6a7c 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
@@ -674,7 +674,7 @@ static const uint32_t cwsr_trap_gfx9_hex[] = {
 	0x86ea6a6a, 0x8f6e837a,
 	0xb96ee0c2, 0xbf800002,
 	0xb97a0002, 0xbf8a0000,
-	0xbe801f6c, 0xbf810000,
+	0xbe801f6c, 0xbf9b0000,
 };
 
 static const uint32_t cwsr_trap_nv1x_hex[] = {
@@ -1091,7 +1091,7 @@ static const uint32_t cwsr_trap_nv1x_hex[] = {
 	0xb9eef807, 0x876dff6d,
 	0x0000ffff, 0x87fe7e7e,
 	0x87ea6a6a, 0xb9faf802,
-	0xbe80226c, 0xbf810000,
+	0xbe80226c, 0xbf9b0000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0x00000000,
@@ -1574,7 +1574,7 @@ static const uint32_t cwsr_trap_arcturus_hex[] = {
 	0x86ea6a6a, 0x8f6e837a,
 	0xb96ee0c2, 0xbf800002,
 	0xb97a0002, 0xbf8a0000,
-	0xbe801f6c, 0xbf810000,
+	0xbe801f6c, 0xbf9b0000,
 };
 
 static const uint32_t cwsr_trap_aldebaran_hex[] = {
@@ -2065,7 +2065,7 @@ static const uint32_t cwsr_trap_aldebaran_hex[] = {
 	0x86ea6a6a, 0x8f6e837a,
 	0xb96ee0c2, 0xbf800002,
 	0xb97a0002, 0xbf8a0000,
-	0xbe801f6c, 0xbf810000,
+	0xbe801f6c, 0xbf9b0000,
 };
 
 static const uint32_t cwsr_trap_gfx10_hex[] = {
@@ -2500,7 +2500,7 @@ static const uint32_t cwsr_trap_gfx10_hex[] = {
 	0x876dff6d, 0x0000ffff,
 	0x87fe7e7e, 0x87ea6a6a,
 	0xb9faf802, 0xbe80226c,
-	0xbf810000, 0xbf9f0000,
+	0xbf9b0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
 };
@@ -2944,7 +2944,7 @@ static const uint32_t cwsr_trap_gfx11_hex[] = {
 	0xb8eef802, 0xbf0d866e,
 	0xbfa20002, 0xb97af802,
 	0xbe80486c, 0xb97af802,
-	0xbe804a6c, 0xbfb00000,
+	0xbe804a6c, 0xbfb10000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0x00000000,
@@ -3436,5 +3436,5 @@ static const uint32_t cwsr_trap_gfx9_4_3_hex[] = {
 	0x86ea6a6a, 0x8f6e837a,
 	0xb96ee0c2, 0xbf800002,
 	0xb97a0002, 0xbf8a0000,
-	0xbe801f6c, 0xbf810000,
+	0xbe801f6c, 0xbf9b0000,
 };
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
index e0140df0b0ec..71b3dc0c7363 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
@@ -1104,7 +1104,7 @@ L_RETURN_WITHOUT_PRIV:
 	s_rfe_b64	s_restore_pc_lo						//Return to the main shader program and resume execution
 
 L_END_PGM:
-	s_endpgm
+	s_endpgm_saved
 end
 
 function write_hwreg_to_mem(s, s_rsrc, s_mem_offset)
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
index e506411ad28a..bb26338204f4 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
@@ -921,7 +921,7 @@ L_RESTORE:
 /*			the END						  */
 /**************************************************************************/
 L_END_PGM:
-    s_endpgm
+    s_endpgm_saved
 
 end
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index ce4c52ec34d8..80e90fdef291 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1442,7 +1442,9 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
 			kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT);
 
 		/* Remove dma mapping after tlb flush to avoid IO_PAGE_FAULT */
-		amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv);
+		err = amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv);
+		if (err)
+			goto sync_memory_failed;
 	}
 
 	mutex_unlock(&p->mutex);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index d630100b9e91..bdc01ca9609a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -574,7 +574,7 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 	pr_debug("svms 0x%p [0x%lx 0x%lx]\n", prange->svms, prange->start,
 		 prange->last);
 
-	addr = prange->start << PAGE_SHIFT;
+	addr = migrate->start;
 
 	src = (uint64_t *)(scratch + npages);
 	dst = scratch;
@@ -1026,7 +1026,7 @@ int kgd2kfd_init_zone_device(struct amdgpu_device *adev)
 	} else {
 		res = devm_request_free_mem_region(adev->dev, &iomem_resource, size);
 		if (IS_ERR(res))
-			return -ENOMEM;
+			return PTR_ERR(res);
 		pgmap->range.start = res->start;
 		pgmap->range.end = res->end;
 		pgmap->type = MEMORY_DEVICE_PRIVATE;
@@ -1042,10 +1042,10 @@ int kgd2kfd_init_zone_device(struct amdgpu_device *adev)
 	r = devm_memremap_pages(adev->dev, pgmap);
 	if (IS_ERR(r)) {
 		pr_err("failed to register HMM device memory\n");
-		/* Disable SVM support capability */
-		pgmap->type = 0;
 		if (pgmap->type == MEMORY_DEVICE_PRIVATE)
 			devm_release_mem_region(adev->dev, res->start, resource_size(res));
+		/* Disable SVM support capability */
+		pgmap->type = 0;
 		return PTR_ERR(r);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
index 8b7fed913526..22cbfa1bdadd 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
@@ -170,6 +170,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
 	m->cp_hqd_pq_control |=
 			ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
index 15277f1d5cf0..826bc4f6c8a7 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
@@ -55,8 +55,8 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
 	m = get_mqd(mqd);
 
 	if (has_wa_flag) {
-		uint32_t wa_mask = minfo->update_flag == UPDATE_FLAG_DBG_WA_ENABLE ?
-						0xffff : 0xffffffff;
+		uint32_t wa_mask =
+			(minfo->update_flag & UPDATE_FLAG_DBG_WA_ENABLE) ? 0xffff : 0xffffffff;
 
 		m->compute_static_thread_mgmt_se0 = wa_mask;
 		m->compute_static_thread_mgmt_se1 = wa_mask;
@@ -224,6 +224,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
 	m->cp_hqd_pq_control |=
 			ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index 42d881809dc7..697b6d530d12 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -303,6 +303,15 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 		update_cu_mask(mm, mqd, minfo, 0);
 	set_priority(m, q);
 
+	if (minfo && KFD_GC_VERSION(mm->dev) >= IP_VERSION(9, 4, 2)) {
+		if (minfo->update_flag & UPDATE_FLAG_IS_GWS)
+			m->compute_resource_limits |=
+				COMPUTE_RESOURCE_LIMITS__FORCE_SIMD_DIST_MASK;
+		else
+			m->compute_resource_limits &=
+				~COMPUTE_RESOURCE_LIMITS__FORCE_SIMD_DIST_MASK;
+	}
+
 	q->is_active = QUEUE_IS_ACTIVE(*q);
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 745024b31340..80320b8603fc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -532,6 +532,7 @@ struct queue_properties {
 enum mqd_update_flag {
 	UPDATE_FLAG_DBG_WA_ENABLE = 1,
 	UPDATE_FLAG_DBG_WA_DISABLE = 2,
+	UPDATE_FLAG_IS_GWS = 4, /* quirk for gfx9 IP */
 };
 
 struct mqd_update_info {
@@ -917,7 +918,7 @@ struct kfd_process {
 	 * fence will be triggered during eviction and new one will be created
 	 * during restore
 	 */
-	struct dma_fence *ef;
+	struct dma_fence __rcu *ef;
 
 	/* Work items for evicting and restoring BOs */
 	struct delayed_work eviction_work;
@@ -1488,10 +1489,15 @@ void kfd_dec_compute_active(struct kfd_node *dev);
 
 /* Cgroup Support */
 /* Check with device cgroup if @kfd device is accessible */
-static inline int kfd_devcgroup_check_permission(struct kfd_node *kfd)
+static inline int kfd_devcgroup_check_permission(struct kfd_node *node)
 {
 #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF)
-	struct drm_device *ddev = adev_to_drm(kfd->adev);
+	struct drm_device *ddev;
+
+	if (node->xcp)
+		ddev = node->xcp->ddev;
+	else
+		ddev = adev_to_drm(node->adev);
 
 	return devcgroup_check_permission(DEVCG_DEV_CHAR, DRM_MAJOR,
 					  ddev->render->index,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 71df51fcc1b0..717a60d7a4ea 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1110,6 +1110,7 @@ static void kfd_process_wq_release(struct work_struct *work)
 {
 	struct kfd_process *p = container_of(work, struct kfd_process,
 					     release_work);
+	struct dma_fence *ef;
 
 	kfd_process_dequeue_from_all_devices(p);
 	pqm_uninit(&p->pqm);
@@ -1118,7 +1119,9 @@ static void kfd_process_wq_release(struct work_struct *work)
 	 * destroyed. This allows any BOs to be freed without
 	 * triggering pointless evictions or waiting for fences.
 	 */
-	dma_fence_signal(p->ef);
+	synchronize_rcu();
+	ef = rcu_access_pointer(p->ef);
+	dma_fence_signal(ef);
 
 	kfd_process_remove_sysfs(p);
 
@@ -1127,7 +1130,7 @@ static void kfd_process_wq_release(struct work_struct *work)
 	svm_range_list_fini(p);
 
 	kfd_process_destroy_pdds(p);
-	dma_fence_put(p->ef);
+	dma_fence_put(ef);
 
 	kfd_event_free_process(p);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 43eff221eae5..4858112f9a53 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -95,6 +95,7 @@ void kfd_process_dequeue_from_device(struct kfd_process_device *pdd)
 int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid,
 			void *gws)
 {
+	struct mqd_update_info minfo = {0};
 	struct kfd_node *dev = NULL;
 	struct process_queue_node *pqn;
 	struct kfd_process_device *pdd;
@@ -146,9 +147,10 @@ int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid,
 	}
 
 	pdd->qpd.num_gws = gws ? dev->adev->gds.gws_size : 0;
+	minfo.update_flag = gws ? UPDATE_FLAG_IS_GWS : 0;
 
 	return pqn->q->device->dqm->ops.update_queue(pqn->q->device->dqm,
-							pqn->q, NULL);
+							pqn->q, &minfo);
 }
 
 void kfd_process_dequeue_from_all_devices(struct kfd_process *p)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index ac84c4a2ca07..c50a0dc9c9c0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -404,14 +404,9 @@ static void svm_range_bo_release(struct kref *kref)
 		spin_lock(&svm_bo->list_lock);
 	}
 	spin_unlock(&svm_bo->list_lock);
-	if (!dma_fence_is_signaled(&svm_bo->eviction_fence->base)) {
-		/* We're not in the eviction worker.
-		 * Signal the fence and synchronize with any
-		 * pending eviction work.
-		 */
+	if (!dma_fence_is_signaled(&svm_bo->eviction_fence->base))
+		/* We're not in the eviction worker. Signal the fence. */
 		dma_fence_signal(&svm_bo->eviction_fence->base);
-		cancel_work_sync(&svm_bo->eviction_work);
-	}
 	dma_fence_put(&svm_bo->eviction_fence->base);
 	amdgpu_bo_unref(&svm_bo->bo);
 	kfree(svm_bo);
@@ -2345,8 +2340,10 @@ retry:
 		mutex_unlock(&svms->lock);
 		mmap_write_unlock(mm);
 
-		/* Pairs with mmget in svm_range_add_list_work */
-		mmput(mm);
+		/* Pairs with mmget in svm_range_add_list_work. If dropping the
+		 * last mm refcount, schedule release work to avoid circular locking
+		 */
+		mmput_async(mm);
 
 		spin_lock(&svms->deferred_list_lock);
 	}
@@ -2657,6 +2654,7 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr,
 {
 	struct vm_area_struct *vma;
 	struct interval_tree_node *node;
+	struct rb_node *rb_node;
 	unsigned long start_limit, end_limit;
 
 	vma = vma_lookup(p->mm, addr << PAGE_SHIFT);
@@ -2676,16 +2674,15 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr,
 	if (node) {
 		end_limit = min(end_limit, node->start);
 		/* Last range that ends before the fault address */
-		node = container_of(rb_prev(&node->rb),
-				    struct interval_tree_node, rb);
+		rb_node = rb_prev(&node->rb);
 	} else {
 		/* Last range must end before addr because
 		 * there was no range after addr
 		 */
-		node = container_of(rb_last(&p->svms.objects.rb_root),
-				    struct interval_tree_node, rb);
+		rb_node = rb_last(&p->svms.objects.rb_root);
 	}
-	if (node) {
+	if (rb_node) {
+		node = container_of(rb_node, struct interval_tree_node, rb);
 		if (node->last >= addr) {
 			WARN(1, "Overlap with prev node and page fault addr\n");
 			return -EFAULT;
@@ -3432,13 +3429,14 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange,
 
 int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence)
 {
-	if (!fence)
-		return -EINVAL;
-
-	if (dma_fence_is_signaled(&fence->base))
-		return 0;
-
-	if (fence->svm_bo) {
+	/* Dereferencing fence->svm_bo is safe here because the fence hasn't
+	 * signaled yet and we're under the protection of the fence->lock.
+	 * After the fence is signaled in svm_range_bo_release, we cannot get
+	 * here any more.
+	 *
+	 * Reference is dropped in svm_range_evict_svm_bo_worker.
+	 */
+	if (svm_bo_ref_unless_zero(fence->svm_bo)) {
 		WRITE_ONCE(fence->svm_bo->evicting, 1);
 		schedule_work(&fence->svm_bo->eviction_work);
 	}
@@ -3453,8 +3451,6 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 	int r = 0;
 
 	svm_bo = container_of(work, struct svm_range_bo, eviction_work);
-	if (!svm_bo_ref_unless_zero(svm_bo))
-		return; /* svm_bo was freed while eviction was pending */
 
 	if (mmget_not_zero(svm_bo->eviction_fence->mm)) {
 		mm = svm_bo->eviction_fence->mm;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index e5f7c92eebcb..6ed2ec381aaa 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1638,12 +1638,10 @@ static int fill_in_l2_l3_pcache(struct kfd_cache_properties **props_ext,
 		else
 			mode = UNKNOWN_MEMORY_PARTITION_MODE;
 
-		if (pcache->cache_level == 2)
-			pcache->cache_size = pcache_info[cache_type].cache_size * num_xcc;
-		else if (mode)
-			pcache->cache_size = pcache_info[cache_type].cache_size / mode;
-		else
-			pcache->cache_size = pcache_info[cache_type].cache_size;
+		pcache->cache_size = pcache_info[cache_type].cache_size;
+		/* Partition mode only affects L3 cache size */
+		if (mode && pcache->cache_level == 3)
+			pcache->cache_size /= mode;
 
 		if (pcache_info[cache_type].flags & CRAT_CACHE_FLAGS_DATA_CACHE)
 			pcache->cache_type |= HSA_CACHE_TYPE_DATA;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index f6575d7dee97..1a9bbb04bd5e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -272,6 +272,7 @@ static int dm_crtc_get_scanoutpos(struct amdgpu_device *adev, int crtc,
 {
 	u32 v_blank_start, v_blank_end, h_position, v_position;
 	struct amdgpu_crtc *acrtc = NULL;
+	struct dc *dc = adev->dm.dc;
 
 	if ((crtc < 0) || (crtc >= adev->mode_info.num_crtc))
 		return -EINVAL;
@@ -284,6 +285,9 @@ static int dm_crtc_get_scanoutpos(struct amdgpu_device *adev, int crtc,
 		return 0;
 	}
 
+	if (dc && dc->caps.ips_support && dc->idle_optimizations_allowed)
+		dc_allow_idle_optimizations(dc, false);
+
 	/*
 	 * TODO rework base driver to use values directly.
 	 * for now parse it back into reg-format
@@ -1715,7 +1719,10 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 	init_data.nbio_reg_offsets = adev->reg_offset[NBIO_HWIP][0];
 	init_data.clk_reg_offsets = adev->reg_offset[CLK_HWIP][0];
 
-	init_data.flags.disable_ips = DMUB_IPS_DISABLE_ALL;
+	if (amdgpu_dc_debug_mask & DC_DISABLE_IPS)
+		init_data.flags.disable_ips = DMUB_IPS_DISABLE_ALL;
+
+	init_data.flags.disable_ips_in_vpb = 1;
 
 	/* Enable DWB for tested platforms only */
 	if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= IP_VERSION(3, 0, 0))
@@ -1836,21 +1843,12 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 			DRM_ERROR("amdgpu: fail to register dmub aux callback");
 			goto error;
 		}
-		if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD, dmub_hpd_callback, true)) {
-			DRM_ERROR("amdgpu: fail to register dmub hpd callback");
-			goto error;
-		}
-		if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD_IRQ, dmub_hpd_callback, true)) {
-			DRM_ERROR("amdgpu: fail to register dmub hpd callback");
-			goto error;
-		}
-	}
-
-	/* Enable outbox notification only after IRQ handlers are registered and DMUB is alive.
-	 * It is expected that DMUB will resend any pending notifications at this point, for
-	 * example HPD from DPIA.
-	 */
-	if (dc_is_dmub_outbox_supported(adev->dm.dc)) {
+		/* Enable outbox notification only after IRQ handlers are registered and DMUB is alive.
+		 * It is expected that DMUB will resend any pending notifications at this point. Note
+		 * that hpd and hpd_irq handler registration are deferred to register_hpd_handlers() to
+		 * align legacy interface initialization sequence. Connection status will be proactivly
+		 * detected once in the amdgpu_dm_initialize_drm_device.
+		 */
 		dc_enable_dmub_outbox(adev->dm.dc);
 
 		/* DPIA trace goes to dmesg logs only if outbox is enabled */
@@ -1949,7 +1947,7 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev)
 				      &adev->dm.dmub_bo_gpu_addr,
 				      &adev->dm.dmub_bo_cpu_addr);
 
-	if (adev->dm.hpd_rx_offload_wq) {
+	if (adev->dm.hpd_rx_offload_wq && adev->dm.dc) {
 		for (i = 0; i < adev->dm.dc->caps.max_links; i++) {
 			if (adev->dm.hpd_rx_offload_wq[i].wq) {
 				destroy_workqueue(adev->dm.hpd_rx_offload_wq[i].wq);
@@ -2280,6 +2278,7 @@ static int dm_sw_fini(void *handle)
 
 	if (adev->dm.dmub_srv) {
 		dmub_srv_destroy(adev->dm.dmub_srv);
+		kfree(adev->dm.dmub_srv);
 		adev->dm.dmub_srv = NULL;
 	}
 
@@ -3529,6 +3528,14 @@ static void register_hpd_handlers(struct amdgpu_device *adev)
 	int_params.requested_polarity = INTERRUPT_POLARITY_DEFAULT;
 	int_params.current_polarity = INTERRUPT_POLARITY_DEFAULT;
 
+	if (dc_is_dmub_outbox_supported(adev->dm.dc)) {
+		if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD, dmub_hpd_callback, true))
+			DRM_ERROR("amdgpu: fail to register dmub hpd callback");
+
+		if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD_IRQ, dmub_hpd_callback, true))
+			DRM_ERROR("amdgpu: fail to register dmub hpd callback");
+	}
+
 	list_for_each_entry(connector,
 			&dev->mode_config.connector_list, head)	{
 
@@ -3557,10 +3564,6 @@ static void register_hpd_handlers(struct amdgpu_device *adev)
 					handle_hpd_rx_irq,
 					(void *) aconnector);
 		}
-
-		if (adev->dm.hpd_rx_offload_wq)
-			adev->dm.hpd_rx_offload_wq[connector->index].aconnector =
-				aconnector;
 	}
 }
 
@@ -4554,6 +4557,10 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 			goto fail;
 		}
 
+		if (dm->hpd_rx_offload_wq)
+			dm->hpd_rx_offload_wq[aconnector->base.index].aconnector =
+				aconnector;
+
 		if (!dc_link_detect_connection_type(link, &new_connection_type))
 			DRM_ERROR("KMS: Failed to detect connector\n");
 
@@ -5212,6 +5219,7 @@ static void fill_dc_dirty_rects(struct drm_plane *plane,
 				struct drm_plane_state *new_plane_state,
 				struct drm_crtc_state *crtc_state,
 				struct dc_flip_addrs *flip_addrs,
+				bool is_psr_su,
 				bool *dirty_regions_changed)
 {
 	struct dm_crtc_state *dm_crtc_state = to_dm_crtc_state(crtc_state);
@@ -5236,6 +5244,10 @@ static void fill_dc_dirty_rects(struct drm_plane *plane,
 	num_clips = drm_plane_get_damage_clips_count(new_plane_state);
 	clips = drm_plane_get_damage_clips(new_plane_state);
 
+	if (num_clips && (!amdgpu_damage_clips || (amdgpu_damage_clips < 0 &&
+						   is_psr_su)))
+		goto ffu;
+
 	if (!dm_crtc_state->mpo_requested) {
 		if (!num_clips || num_clips > DC_MAX_DIRTY_RECTS)
 			goto ffu;
@@ -6187,7 +6199,9 @@ create_stream_for_sink(struct drm_connector *connector,
 		if (recalculate_timing) {
 			freesync_mode = get_highest_refresh_rate_mode(aconnector, false);
 			drm_mode_copy(&saved_mode, &mode);
+			saved_mode.picture_aspect_ratio = mode.picture_aspect_ratio;
 			drm_mode_copy(&mode, freesync_mode);
+			mode.picture_aspect_ratio = saved_mode.picture_aspect_ratio;
 		} else {
 			decide_crtc_timing_for_drm_display_mode(
 					&mode, preferred_mode, scale);
@@ -6520,10 +6534,15 @@ amdgpu_dm_connector_late_register(struct drm_connector *connector)
 static void amdgpu_dm_connector_funcs_force(struct drm_connector *connector)
 {
 	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
-	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 	struct dc_link *dc_link = aconnector->dc_link;
 	struct dc_sink *dc_em_sink = aconnector->dc_em_sink;
 	struct edid *edid;
+	struct i2c_adapter *ddc;
+
+	if (dc_link && dc_link->aux_mode)
+		ddc = &aconnector->dm_dp_aux.aux.ddc;
+	else
+		ddc = &aconnector->i2c->base;
 
 	/*
 	 * Note: drm_get_edid gets edid in the following order:
@@ -6531,7 +6550,7 @@ static void amdgpu_dm_connector_funcs_force(struct drm_connector *connector)
 	 * 2) firmware EDID if set via edid_firmware module parameter
 	 * 3) regular DDC read.
 	 */
-	edid = drm_get_edid(connector, &amdgpu_connector->ddc_bus->aux.ddc);
+	edid = drm_get_edid(connector, ddc);
 	if (!edid) {
 		DRM_ERROR("No EDID found on connector: %s.\n", connector->name);
 		return;
@@ -6572,12 +6591,18 @@ static int get_modes(struct drm_connector *connector)
 static void create_eml_sink(struct amdgpu_dm_connector *aconnector)
 {
 	struct drm_connector *connector = &aconnector->base;
-	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(&aconnector->base);
+	struct dc_link *dc_link = aconnector->dc_link;
 	struct dc_sink_init_data init_params = {
 			.link = aconnector->dc_link,
 			.sink_signal = SIGNAL_TYPE_VIRTUAL
 	};
 	struct edid *edid;
+	struct i2c_adapter *ddc;
+
+	if (dc_link->aux_mode)
+		ddc = &aconnector->dm_dp_aux.aux.ddc;
+	else
+		ddc = &aconnector->i2c->base;
 
 	/*
 	 * Note: drm_get_edid gets edid in the following order:
@@ -6585,7 +6610,7 @@ static void create_eml_sink(struct amdgpu_dm_connector *aconnector)
 	 * 2) firmware EDID if set via edid_firmware module parameter
 	 * 3) regular DDC read.
 	 */
-	edid = drm_get_edid(connector, &amdgpu_connector->ddc_bus->aux.ddc);
+	edid = drm_get_edid(connector, ddc);
 	if (!edid) {
 		DRM_ERROR("No EDID found on connector: %s.\n", connector->name);
 		return;
@@ -7615,7 +7640,6 @@ create_i2c(struct ddc_service *ddc_service,
 	if (!i2c)
 		return NULL;
 	i2c->base.owner = THIS_MODULE;
-	i2c->base.class = I2C_CLASS_DDC;
 	i2c->base.dev.parent = &adev->pdev->dev;
 	i2c->base.algo = &amdgpu_dm_i2c_algo;
 	snprintf(i2c->base.name, sizeof(i2c->base.name), "AMDGPU DM i2c hw bus %d", link_index);
@@ -8292,6 +8316,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			fill_dc_dirty_rects(plane, old_plane_state,
 					    new_plane_state, new_crtc_state,
 					    &bundle->flip_addrs[planes_count],
+					    acrtc_state->stream->link->psr_settings.psr_version ==
+					    DC_PSR_VERSION_SU_1,
 					    &dirty_rects_changed);
 
 			/*
@@ -8977,16 +9003,8 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 
 	trace_amdgpu_dm_atomic_commit_tail_begin(state);
 
-	if (dm->dc->caps.ips_support) {
-		for_each_oldnew_connector_in_state(state, connector, old_con_state, new_con_state, i) {
-			if (new_con_state->crtc &&
-				new_con_state->crtc->state->active &&
-				drm_atomic_crtc_needs_modeset(new_con_state->crtc->state)) {
-				dc_dmub_srv_apply_idle_power_optimizations(dm->dc, false);
-				break;
-			}
-		}
-	}
+	if (dm->dc->caps.ips_support && dm->dc->idle_optimizations_allowed)
+		dc_allow_idle_optimizations(dm->dc, false);
 
 	drm_atomic_helper_update_legacy_modeset_state(dev, state);
 	drm_dp_mst_atomic_wait_for_dependencies(state);
@@ -9189,6 +9207,10 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		 * To fix this, DC should permit updating only stream properties.
 		 */
 		dummy_updates = kzalloc(sizeof(struct dc_surface_update) * MAX_SURFACES, GFP_ATOMIC);
+		if (!dummy_updates) {
+			DRM_ERROR("Failed to allocate memory for dummy_updates.\n");
+			continue;
+		}
 		for (j = 0; j < status->plane_count; j++)
 			dummy_updates[j].surface = status->plane_states[0];
 
@@ -9293,10 +9315,10 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		if (!new_con_state->writeback_job)
 			continue;
 
-		new_crtc_state = NULL;
+		new_crtc_state = drm_atomic_get_new_crtc_state(state, &acrtc->base);
 
-		if (acrtc)
-			new_crtc_state = drm_atomic_get_new_crtc_state(state, &acrtc->base);
+		if (!new_crtc_state)
+			continue;
 
 		if (acrtc->wb_enabled)
 			continue;
@@ -10729,11 +10751,13 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 			goto fail;
 		}
 
-		ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars);
-		if (ret) {
-			DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n");
-			ret = -EINVAL;
-			goto fail;
+		if (dc_resource_is_dsc_encoding_supported(dc)) {
+			ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars);
+			if (ret) {
+				DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n");
+				ret = -EINVAL;
+				goto fail;
+			}
 		}
 
 		ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context, vars);
@@ -10753,7 +10777,7 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 			DRM_DEBUG_DRIVER("drm_dp_mst_atomic_check() failed\n");
 			goto fail;
 		}
-		status = dc_validate_global_state(dc, dm_state->context, false);
+		status = dc_validate_global_state(dc, dm_state->context, true);
 		if (status != DC_OK) {
 			DRM_DEBUG_DRIVER("DC global validation failure: %s (%d)",
 				       dc_status_to_str(status), status);
@@ -11145,14 +11169,23 @@ void amdgpu_dm_update_freesync_caps(struct drm_connector *connector,
 				if (range->flags != 1)
 					continue;
 
-				amdgpu_dm_connector->min_vfreq = range->min_vfreq;
-				amdgpu_dm_connector->max_vfreq = range->max_vfreq;
-				amdgpu_dm_connector->pixel_clock_mhz =
-					range->pixel_clock_mhz * 10;
-
 				connector->display_info.monitor_range.min_vfreq = range->min_vfreq;
 				connector->display_info.monitor_range.max_vfreq = range->max_vfreq;
 
+				if (edid->revision >= 4) {
+					if (data->pad2 & DRM_EDID_RANGE_OFFSET_MIN_VFREQ)
+						connector->display_info.monitor_range.min_vfreq += 255;
+					if (data->pad2 & DRM_EDID_RANGE_OFFSET_MAX_VFREQ)
+						connector->display_info.monitor_range.max_vfreq += 255;
+				}
+
+				amdgpu_dm_connector->min_vfreq =
+					connector->display_info.monitor_range.min_vfreq;
+				amdgpu_dm_connector->max_vfreq =
+					connector->display_info.monitor_range.max_vfreq;
+				amdgpu_dm_connector->pixel_clock_mhz =
+					range->pixel_clock_mhz * 10;
+
 				break;
 			}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
index 9b527bffe11a..c87b64e464ed 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
@@ -1239,7 +1239,7 @@ int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc,
 	if (has_crtc_cm_degamma && ret != -EINVAL) {
 		drm_dbg_kms(crtc->base.crtc->dev,
 			    "doesn't support plane and CRTC degamma at the same time\n");
-			return -EINVAL;
+		return -EINVAL;
 	}
 
 	/* If we are here, it means we don't have plane degamma settings, check
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index eaf8d9f48244..c27063305a13 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -67,6 +67,8 @@ static void apply_edid_quirks(struct edid *edid, struct dc_edid_caps *edid_caps)
 	/* Workaround for some monitors that do not clear DPCD 0x317 if FreeSync is unsupported */
 	case drm_edid_encode_panel_id('A', 'U', 'O', 0xA7AB):
 	case drm_edid_encode_panel_id('A', 'U', 'O', 0xE69B):
+	case drm_edid_encode_panel_id('B', 'O', 'E', 0x092A):
+	case drm_edid_encode_panel_id('L', 'G', 'D', 0x06D1):
 		DRM_DEBUG_DRIVER("Clearing DPCD 0x317 on monitor with panel id %X\n", panel_id);
 		edid_caps->panel_patch.remove_sink_ext_caps = true;
 		break;
@@ -120,6 +122,8 @@ enum dc_edid_status dm_helpers_parse_edid_caps(
 
 	edid_caps->edid_hdmi = connector->display_info.is_hdmi;
 
+	apply_edid_quirks(edid_buf, edid_caps);
+
 	sad_count = drm_edid_to_sad((struct edid *) edid->raw_edid, &sads);
 	if (sad_count <= 0)
 		return result;
@@ -146,8 +150,6 @@ enum dc_edid_status dm_helpers_parse_edid_caps(
 	else
 		edid_caps->speaker_flags = DEFAULT_SPEAKER_LOCATION;
 
-	apply_edid_quirks(edid_buf, edid_caps);
-
 	kfree(sads);
 	kfree(sadb);
 
@@ -979,6 +981,11 @@ int dm_helper_dmub_aux_transfer_sync(
 		struct aux_payload *payload,
 		enum aux_return_code_type *operation_result)
 {
+	if (!link->hpd_status) {
+		*operation_result = AUX_RET_ERROR_HPD_DISCON;
+		return -1;
+	}
+
 	return amdgpu_dm_process_dmub_aux_transfer_sync(ctx, link->link_index, payload,
 			operation_result);
 }
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index 58b880acb087..3390f0d8420a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -711,7 +711,7 @@ static inline int dm_irq_state(struct amdgpu_device *adev,
 {
 	bool st;
 	enum dc_irq_source irq_source;
-
+	struct dc *dc = adev->dm.dc;
 	struct amdgpu_crtc *acrtc = adev->mode_info.crtcs[crtc_id];
 
 	if (!acrtc) {
@@ -729,6 +729,9 @@ static inline int dm_irq_state(struct amdgpu_device *adev,
 
 	st = (state == AMDGPU_IRQ_STATE_ENABLE);
 
+	if (dc && dc->caps.ips_support && dc->idle_optimizations_allowed)
+		dc_allow_idle_optimizations(dc, false);
+
 	dc_interrupt_set(adev->dm.dc, irq_source, st);
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c b/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c
index f2dfa96f9ef5..39530b2ea495 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c
@@ -94,7 +94,7 @@ static void calculate_bandwidth(
 	const uint32_t s_high = 7;
 	const uint32_t dmif_chunk_buff_margin = 1;
 
-	uint32_t max_chunks_fbc_mode;
+	uint32_t max_chunks_fbc_mode = 0;
 	int32_t num_cursor_lines;
 
 	int32_t i, j, k;
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index 960c4b4f6ddf..05f392501c0a 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -1850,19 +1850,21 @@ static enum bp_result get_firmware_info_v3_2(
 		/* Vega12 */
 		smu_info_v3_2 = GET_IMAGE(struct atom_smu_info_v3_2,
 							DATA_TABLES(smu_info));
-		DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_2->gpuclk_ss_percentage);
 		if (!smu_info_v3_2)
 			return BP_RESULT_BADBIOSTABLE;
 
+		DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_2->gpuclk_ss_percentage);
+
 		info->default_engine_clk = smu_info_v3_2->bootup_dcefclk_10khz * 10;
 	} else if (revision.minor == 3) {
 		/* Vega20 */
 		smu_info_v3_3 = GET_IMAGE(struct atom_smu_info_v3_3,
 							DATA_TABLES(smu_info));
-		DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_3->gpuclk_ss_percentage);
 		if (!smu_info_v3_3)
 			return BP_RESULT_BADBIOSTABLE;
 
+		DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_3->gpuclk_ss_percentage);
+
 		info->default_engine_clk = smu_info_v3_3->bootup_dcefclk_10khz * 10;
 	}
 
@@ -2422,10 +2424,11 @@ static enum bp_result get_integrated_info_v11(
 	info_v11 = GET_IMAGE(struct atom_integrated_system_info_v1_11,
 					DATA_TABLES(integratedsysteminfo));
 
-	DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v11->gpuclk_ss_percentage);
 	if (info_v11 == NULL)
 		return BP_RESULT_BADBIOSTABLE;
 
+	DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v11->gpuclk_ss_percentage);
+
 	info->gpu_cap_info =
 	le32_to_cpu(info_v11->gpucapinfo);
 	/*
@@ -2637,11 +2640,12 @@ static enum bp_result get_integrated_info_v2_1(
 
 	info_v2_1 = GET_IMAGE(struct atom_integrated_system_info_v2_1,
 					DATA_TABLES(integratedsysteminfo));
-	DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_1->gpuclk_ss_percentage);
 
 	if (info_v2_1 == NULL)
 		return BP_RESULT_BADBIOSTABLE;
 
+	DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_1->gpuclk_ss_percentage);
+
 	info->gpu_cap_info =
 	le32_to_cpu(info_v2_1->gpucapinfo);
 	/*
@@ -2799,11 +2803,11 @@ static enum bp_result get_integrated_info_v2_2(
 	info_v2_2 = GET_IMAGE(struct atom_integrated_system_info_v2_2,
 					DATA_TABLES(integratedsysteminfo));
 
-	DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_2->gpuclk_ss_percentage);
-
 	if (info_v2_2 == NULL)
 		return BP_RESULT_BADBIOSTABLE;
 
+	DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_2->gpuclk_ss_percentage);
+
 	info->gpu_cap_info =
 	le32_to_cpu(info_v2_2->gpucapinfo);
 	/*
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
index a5489fe6875f..aa9fd1dc550a 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
@@ -546,6 +546,8 @@ static unsigned int find_dcfclk_for_voltage(const struct vg_dpm_clocks *clock_ta
 	int i;
 
 	for (i = 0; i < VG_NUM_SOC_VOLTAGE_LEVELS; i++) {
+		if (i >= VG_NUM_DCFCLK_DPM_LEVELS)
+			break;
 		if (clock_table->SocVoltage[i] == voltage)
 			return clock_table->DcfClocks[i];
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
index 757528256326..a84f1e376dee 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
@@ -87,6 +87,20 @@ static const struct IP_BASE CLK_BASE = { { { { 0x00016C00, 0x02401800, 0, 0, 0,
 #define CLK1_CLK_PLL_REQ__PllSpineDiv_MASK	0x0000F000L
 #define CLK1_CLK_PLL_REQ__FbMult_frac_MASK	0xFFFF0000L
 
+#define regCLK1_CLK2_BYPASS_CNTL			0x029c
+#define regCLK1_CLK2_BYPASS_CNTL_BASE_IDX	0
+
+#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL__SHIFT	0x0
+#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_DIV__SHIFT	0x10
+#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL_MASK		0x00000007L
+#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_DIV_MASK		0x000F0000L
+
+#define regCLK6_0_CLK6_spll_field_8				0x464b
+#define regCLK6_0_CLK6_spll_field_8_BASE_IDX	0
+
+#define CLK6_0_CLK6_spll_field_8__spll_ssc_en__SHIFT	0xd
+#define CLK6_0_CLK6_spll_field_8__spll_ssc_en_MASK		0x00002000L
+
 #define REG(reg_name) \
 	(CLK_BASE.instance[0].segment[reg ## reg_name ## _BASE_IDX] + reg ## reg_name)
 
@@ -131,35 +145,63 @@ static int dcn314_get_active_display_cnt_wa(
 	return display_count;
 }
 
-static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable)
+static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context,
+				  bool safe_to_lower, bool disable)
 {
 	struct dc *dc = clk_mgr_base->ctx->dc;
 	int i;
 
 	for (i = 0; i < dc->res_pool->pipe_count; ++i) {
-		struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *pipe = safe_to_lower
+			? &context->res_ctx.pipe_ctx[i]
+			: &dc->current_state->res_ctx.pipe_ctx[i];
 
 		if (pipe->top_pipe || pipe->prev_odm_pipe)
 			continue;
 		if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal))) {
-			struct stream_encoder *stream_enc = pipe->stream_res.stream_enc;
-
 			if (disable) {
-				if (stream_enc && stream_enc->funcs->disable_fifo)
-					pipe->stream_res.stream_enc->funcs->disable_fifo(stream_enc);
+				if (pipe->stream_res.tg && pipe->stream_res.tg->funcs->immediate_disable_crtc)
+					pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg);
 
-				pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg);
 				reset_sync_context_for_pipe(dc, context, i);
 			} else {
 				pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg);
-
-				if (stream_enc && stream_enc->funcs->enable_fifo)
-					pipe->stream_res.stream_enc->funcs->enable_fifo(stream_enc);
 			}
 		}
 	}
 }
 
+bool dcn314_is_spll_ssc_enabled(struct clk_mgr *clk_mgr_base)
+{
+	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
+	uint32_t ssc_enable;
+
+	REG_GET(CLK6_0_CLK6_spll_field_8, spll_ssc_en, &ssc_enable);
+
+	return ssc_enable == 1;
+}
+
+void dcn314_init_clocks(struct clk_mgr *clk_mgr)
+{
+	struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr);
+	uint32_t ref_dtbclk = clk_mgr->clks.ref_dtbclk_khz;
+
+	memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks));
+	// Assumption is that boot state always supports pstate
+	clk_mgr->clks.ref_dtbclk_khz = ref_dtbclk;	// restore ref_dtbclk
+	clk_mgr->clks.p_state_change_support = true;
+	clk_mgr->clks.prev_p_state_change_support = true;
+	clk_mgr->clks.pwr_state = DCN_PWR_STATE_UNKNOWN;
+	clk_mgr->clks.zstate_support = DCN_ZSTATE_SUPPORT_UNKNOWN;
+
+	// to adjust dp_dto reference clock if ssc is enable otherwise to apply dprefclk
+	if (dcn314_is_spll_ssc_enabled(clk_mgr))
+		clk_mgr->dp_dto_source_clock_in_khz =
+			dce_adjust_dp_ref_freq_for_ss(clk_mgr_int, clk_mgr->dprefclk_khz);
+	else
+		clk_mgr->dp_dto_source_clock_in_khz = clk_mgr->dprefclk_khz;
+}
+
 void dcn314_update_clocks(struct clk_mgr *clk_mgr_base,
 			struct dc_state *context,
 			bool safe_to_lower)
@@ -252,11 +294,11 @@ void dcn314_update_clocks(struct clk_mgr *clk_mgr_base,
 	}
 
 	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) {
-		dcn314_disable_otg_wa(clk_mgr_base, context, true);
+		dcn314_disable_otg_wa(clk_mgr_base, context, safe_to_lower, true);
 
 		clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz;
 		dcn314_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz);
-		dcn314_disable_otg_wa(clk_mgr_base, context, false);
+		dcn314_disable_otg_wa(clk_mgr_base, context, safe_to_lower, false);
 
 		update_dispclk = true;
 	}
@@ -436,6 +478,11 @@ static DpmClocks314_t dummy_clocks;
 
 static struct dcn314_watermarks dummy_wms = { 0 };
 
+static struct dcn314_ss_info_table ss_info_table = {
+	.ss_divider = 1000,
+	.ss_percentage = {0, 0, 375, 375, 375}
+};
+
 static void dcn314_build_watermark_ranges(struct clk_bw_params *bw_params, struct dcn314_watermarks *table)
 {
 	int i, num_valid_sets;
@@ -708,13 +755,31 @@ static struct clk_mgr_funcs dcn314_funcs = {
 	.get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz,
 	.get_dtb_ref_clk_frequency = dcn31_get_dtb_ref_freq_khz,
 	.update_clocks = dcn314_update_clocks,
-	.init_clocks = dcn31_init_clocks,
+	.init_clocks = dcn314_init_clocks,
 	.enable_pme_wa = dcn314_enable_pme_wa,
 	.are_clock_states_equal = dcn314_are_clock_states_equal,
 	.notify_wm_ranges = dcn314_notify_wm_ranges
 };
 extern struct clk_mgr_funcs dcn3_fpga_funcs;
 
+static void dcn314_read_ss_info_from_lut(struct clk_mgr_internal *clk_mgr)
+{
+	uint32_t clock_source;
+	//uint32_t ssc_enable;
+
+	REG_GET(CLK1_CLK2_BYPASS_CNTL, CLK2_BYPASS_SEL, &clock_source);
+	//REG_GET(CLK6_0_CLK6_spll_field_8, spll_ssc_en, &ssc_enable);
+
+	if (dcn314_is_spll_ssc_enabled(&clk_mgr->base) && (clock_source < ARRAY_SIZE(ss_info_table.ss_percentage))) {
+		clk_mgr->dprefclk_ss_percentage = ss_info_table.ss_percentage[clock_source];
+
+		if (clk_mgr->dprefclk_ss_percentage != 0) {
+			clk_mgr->ss_on_dprefclk = true;
+			clk_mgr->dprefclk_ss_divider = ss_info_table.ss_divider;
+		}
+	}
+}
+
 void dcn314_clk_mgr_construct(
 		struct dc_context *ctx,
 		struct clk_mgr_dcn314 *clk_mgr,
@@ -782,6 +847,7 @@ void dcn314_clk_mgr_construct(
 	clk_mgr->base.base.dprefclk_khz = 600000;
 	clk_mgr->base.base.clks.ref_dtbclk_khz = 600000;
 	dce_clock_read_ss_info(&clk_mgr->base);
+	dcn314_read_ss_info_from_lut(&clk_mgr->base);
 	/*if bios enabled SS, driver needs to adjust dtb clock, only enable with correct bios*/
 
 	clk_mgr->base.base.bw_params = &dcn314_bw_params;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
index 171f84340eb2..002c28e80720 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
@@ -28,6 +28,8 @@
 #define __DCN314_CLK_MGR_H__
 #include "clk_mgr_internal.h"
 
+#define DCN314_NUM_CLOCK_SOURCES   5
+
 struct dcn314_watermarks;
 
 struct dcn314_smu_watermark_set {
@@ -40,9 +42,18 @@ struct clk_mgr_dcn314 {
 	struct dcn314_smu_watermark_set smu_wm_set;
 };
 
+struct dcn314_ss_info_table {
+	uint32_t ss_divider;
+	uint32_t ss_percentage[DCN314_NUM_CLOCK_SOURCES];
+};
+
 bool dcn314_are_clock_states_equal(struct dc_clocks *a,
 		struct dc_clocks *b);
 
+bool dcn314_is_spll_ssc_enabled(struct clk_mgr *clk_mgr_base);
+
+void dcn314_init_clocks(struct clk_mgr *clk_mgr);
+
 void dcn314_update_clocks(struct clk_mgr *clk_mgr_base,
 			struct dc_state *context,
 			bool safe_to_lower);
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
index 9c660d1facc7..e64890259235 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
@@ -437,32 +437,32 @@ static struct wm_table ddr5_wm_table = {
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 	}
@@ -474,32 +474,32 @@ static struct wm_table lpddr5_wm_table = {
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 	}
@@ -655,10 +655,13 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
 	struct clk_limit_table_entry def_max = bw_params->clk_table.entries[bw_params->clk_table.num_entries - 1];
 	uint32_t max_fclk = 0, min_pstate = 0, max_dispclk = 0, max_dppclk = 0;
 	uint32_t max_pstate = 0, max_dram_speed_mts = 0, min_dram_speed_mts = 0;
+	uint32_t num_memps, num_fclk, num_dcfclk;
 	int i;
 
 	/* Determine min/max p-state values. */
-	for (i = 0; i < clock_table->NumMemPstatesEnabled; i++) {
+	num_memps = (clock_table->NumMemPstatesEnabled > NUM_MEM_PSTATE_LEVELS) ? NUM_MEM_PSTATE_LEVELS :
+		clock_table->NumMemPstatesEnabled;
+	for (i = 0; i < num_memps; i++) {
 		uint32_t dram_speed_mts = calc_dram_speed_mts(&clock_table->MemPstateTable[i]);
 
 		if (is_valid_clock_value(dram_speed_mts) && dram_speed_mts > max_dram_speed_mts) {
@@ -670,7 +673,7 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
 	min_dram_speed_mts = max_dram_speed_mts;
 	min_pstate = max_pstate;
 
-	for (i = 0; i < clock_table->NumMemPstatesEnabled; i++) {
+	for (i = 0; i < num_memps; i++) {
 		uint32_t dram_speed_mts = calc_dram_speed_mts(&clock_table->MemPstateTable[i]);
 
 		if (is_valid_clock_value(dram_speed_mts) && dram_speed_mts < min_dram_speed_mts) {
@@ -699,9 +702,13 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
 	/* Base the clock table on dcfclk, need at least one entry regardless of pmfw table */
 	ASSERT(clock_table->NumDcfClkLevelsEnabled > 0);
 
-	max_fclk = find_max_clk_value(clock_table->FclkClocks_Freq, clock_table->NumFclkLevelsEnabled);
+	num_fclk = (clock_table->NumFclkLevelsEnabled > NUM_FCLK_DPM_LEVELS) ? NUM_FCLK_DPM_LEVELS :
+		clock_table->NumFclkLevelsEnabled;
+	max_fclk = find_max_clk_value(clock_table->FclkClocks_Freq, num_fclk);
 
-	for (i = 0; i < clock_table->NumDcfClkLevelsEnabled; i++) {
+	num_dcfclk = (clock_table->NumFclkLevelsEnabled > NUM_DCFCLK_DPM_LEVELS) ? NUM_DCFCLK_DPM_LEVELS :
+		clock_table->NumDcfClkLevelsEnabled;
+	for (i = 0; i < num_dcfclk; i++) {
 		int j;
 
 		/* First search defaults for the clocks we don't read using closest lower or equal default dcfclk */
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 2d7205058c64..2c424e435962 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -411,12 +411,9 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 	 * avoid conflicting with firmware updates.
 	 */
 	if (dc->ctx->dce_version > DCE_VERSION_MAX)
-		if (dc->optimized_required)
+		if (dc->optimized_required || dc->wm_optimized_required)
 			return false;
 
-	if (!memcmp(&stream->adjust, adjust, sizeof(*adjust)))
-		return true;
-
 	stream->adjust.v_total_max = adjust->v_total_max;
 	stream->adjust.v_total_mid = adjust->v_total_mid;
 	stream->adjust.v_total_mid_frame_num = adjust->v_total_mid_frame_num;
@@ -2230,6 +2227,7 @@ void dc_post_update_surfaces_to_stream(struct dc *dc)
 	}
 
 	dc->optimized_required = false;
+	dc->wm_optimized_required = false;
 }
 
 bool dc_set_generic_gpio_for_stereo(bool enable,
@@ -2652,6 +2650,8 @@ enum surface_update_type dc_check_update_surfaces_for_stream(
 		} else if (memcmp(&dc->current_state->bw_ctx.bw.dcn.clk, &dc->clk_mgr->clks, offsetof(struct dc_clocks, prev_p_state_change_support)) != 0) {
 			dc->optimized_required = true;
 		}
+
+		dc->optimized_required |= dc->wm_optimized_required;
 	}
 
 	return type;
@@ -2859,6 +2859,9 @@ static void copy_stream_update_to_stream(struct dc *dc,
 	if (update->vrr_active_fixed)
 		stream->vrr_active_fixed = *update->vrr_active_fixed;
 
+	if (update->crtc_timing_adjust)
+		stream->adjust = *update->crtc_timing_adjust;
+
 	if (update->dpms_off)
 		stream->dpms_off = *update->dpms_off;
 
@@ -3519,7 +3522,7 @@ static void commit_planes_for_stream(struct dc *dc,
 	top_pipe_to_program = resource_get_otg_master_for_stream(
 				&context->res_ctx,
 				stream);
-
+	ASSERT(top_pipe_to_program != NULL);
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i];
 
@@ -3814,7 +3817,9 @@ static void commit_planes_for_stream(struct dc *dc,
 		 * programming has completed (we turn on phantom OTG in order
 		 * to complete the plane disable for phantom pipes).
 		 */
-		dc->hwss.apply_ctx_to_hw(dc, context);
+
+		if (dc->hwss.disable_phantom_streams)
+			dc->hwss.disable_phantom_streams(dc, context);
 	}
 
 	if (update_type != UPDATE_TYPE_FAST)
@@ -4288,7 +4293,8 @@ static bool full_update_required(struct dc *dc,
 			stream_update->mst_bw_update ||
 			stream_update->func_shaper ||
 			stream_update->lut3d_func ||
-			stream_update->pending_test_pattern))
+			stream_update->pending_test_pattern ||
+			stream_update->crtc_timing_adjust))
 		return true;
 
 	if (stream) {
@@ -4341,6 +4347,8 @@ static bool should_commit_minimal_transition_for_windowed_mpo_odm(struct dc *dc,
 
 	cur_pipe = resource_get_otg_master_for_stream(&dc->current_state->res_ctx, stream);
 	new_pipe = resource_get_otg_master_for_stream(&context->res_ctx, stream);
+	if (!cur_pipe || !new_pipe)
+		return false;
 	cur_is_odm_in_use = resource_get_odm_slice_count(cur_pipe) > 1;
 	new_is_odm_in_use = resource_get_odm_slice_count(new_pipe) > 1;
 	if (cur_is_odm_in_use == new_is_odm_in_use)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 57f0ddd15923..9fbdb09697fd 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -2194,6 +2194,10 @@ void resource_log_pipe_topology_update(struct dc *dc, struct dc_state *state)
 	for (stream_idx = 0; stream_idx < state->stream_count; stream_idx++) {
 		otg_master = resource_get_otg_master_for_stream(
 				&state->res_ctx, state->streams[stream_idx]);
+		if (!otg_master	|| otg_master->stream_res.tg == NULL) {
+			DC_LOG_DC("topology update: otg_master NULL stream_idx %d!\n", stream_idx);
+			return;
+		}
 		slice_count = resource_get_opp_heads_for_otg_master(otg_master,
 				&state->res_ctx, opp_heads);
 		for (slice_idx = 0; slice_idx < slice_count; slice_idx++) {
@@ -4986,20 +4990,6 @@ enum dc_status update_dp_encoder_resources_for_test_harness(const struct dc *dc,
 	return DC_OK;
 }
 
-bool resource_subvp_in_use(struct dc *dc,
-		struct dc_state *context)
-{
-	uint32_t i;
-
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
-
-		if (dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_NONE)
-			return true;
-	}
-	return false;
-}
-
 bool check_subvp_sw_cursor_fallback_req(const struct dc *dc, struct dc_stream_state *stream)
 {
 	if (!dc->debug.disable_subvp_high_refresh && is_subvp_high_refresh_candidate(stream))
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
index 460a8010c79f..180ac47868c2 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
@@ -267,7 +267,8 @@ void dc_state_construct(struct dc *dc, struct dc_state *state)
 	state->clk_mgr = dc->clk_mgr;
 
 	/* Initialise DIG link encoder resource tracking variables. */
-	link_enc_cfg_init(dc, state);
+	if (dc->res_pool)
+		link_enc_cfg_init(dc, state);
 }
 
 void dc_state_destruct(struct dc_state *state)
@@ -290,11 +291,14 @@ void dc_state_destruct(struct dc_state *state)
 		dc_stream_release(state->phantom_streams[i]);
 		state->phantom_streams[i] = NULL;
 	}
+	state->phantom_stream_count = 0;
 
 	for (i = 0; i < state->phantom_plane_count; i++) {
 		dc_plane_state_release(state->phantom_planes[i]);
 		state->phantom_planes[i] = NULL;
 	}
+	state->phantom_plane_count = 0;
+
 	state->stream_mask = 0;
 	memset(&state->res_ctx, 0, sizeof(state->res_ctx));
 	memset(&state->pp_display_cfg, 0, sizeof(state->pp_display_cfg));
@@ -433,8 +437,9 @@ bool dc_state_add_plane(
 
 	otg_master_pipe = resource_get_otg_master_for_stream(
 			&state->res_ctx, stream);
-	added = resource_append_dpp_pipes_for_plane_composition(state,
-			dc->current_state, pool, otg_master_pipe, plane_state);
+	if (otg_master_pipe)
+		added = resource_append_dpp_pipes_for_plane_composition(state,
+				dc->current_state, pool, otg_master_pipe, plane_state);
 
 	if (added) {
 		stream_status->plane_states[stream_status->plane_count] =
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index f30a341bc090..c9317ea0258e 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -51,7 +51,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.265"
+#define DC_VER "3.2.266"
 
 #define MAX_SURFACES 3
 #define MAX_PLANES 6
@@ -434,6 +434,7 @@ struct dc_config {
 	bool EnableMinDispClkODM;
 	bool enable_auto_dpm_test_logs;
 	unsigned int disable_ips;
+	unsigned int disable_ips_in_vpb;
 };
 
 enum visual_confirm {
@@ -1036,6 +1037,7 @@ struct dc {
 
 	/* Require to optimize clocks and bandwidth for added/removed planes */
 	bool optimized_required;
+	bool wm_optimized_required;
 	bool idle_optimizations_allowed;
 	bool enable_c20_dtm_b0;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
index 2b79a0e5638e..363d522603a2 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
@@ -125,7 +125,7 @@ bool dc_dmub_srv_cmd_list_queue_execute(struct dc_dmub_srv *dc_dmub_srv,
 		unsigned int count,
 		union dmub_rb_cmd *cmd_list)
 {
-	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+	struct dc_context *dc_ctx;
 	struct dmub_srv *dmub;
 	enum dmub_status status;
 	int i;
@@ -133,6 +133,7 @@ bool dc_dmub_srv_cmd_list_queue_execute(struct dc_dmub_srv *dc_dmub_srv,
 	if (!dc_dmub_srv || !dc_dmub_srv->dmub)
 		return false;
 
+	dc_ctx = dc_dmub_srv->ctx;
 	dmub = dc_dmub_srv->dmub;
 
 	for (i = 0 ; i < count; i++) {
@@ -1161,7 +1162,7 @@ void dc_dmub_srv_subvp_save_surf_addr(const struct dc_dmub_srv *dc_dmub_srv, con
 
 bool dc_dmub_srv_is_hw_pwr_up(struct dc_dmub_srv *dc_dmub_srv, bool wait)
 {
-	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+	struct dc_context *dc_ctx;
 	enum dmub_status status;
 
 	if (!dc_dmub_srv || !dc_dmub_srv->dmub)
@@ -1170,6 +1171,8 @@ bool dc_dmub_srv_is_hw_pwr_up(struct dc_dmub_srv *dc_dmub_srv, bool wait)
 	if (dc_dmub_srv->ctx->dc->debug.dmcub_emulation)
 		return true;
 
+	dc_ctx = dc_dmub_srv->ctx;
+
 	if (wait) {
 		if (dc_dmub_srv->ctx->dc->debug.disable_timeout) {
 			do {
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index a23eebd9933b..ee10941caa59 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -139,6 +139,7 @@ union stream_update_flags {
 		uint32_t wb_update:1;
 		uint32_t dsc_changed : 1;
 		uint32_t mst_bw : 1;
+		uint32_t crtc_timing_adjust : 1;
 		uint32_t fams_changed : 1;
 	} bits;
 
@@ -325,6 +326,7 @@ struct dc_stream_update {
 	struct dc_3dlut *lut3d_func;
 
 	struct test_pattern *pending_test_pattern;
+	struct dc_crtc_timing_adjust *crtc_timing_adjust;
 };
 
 bool dc_is_stream_unchanged(
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index 4f276169e05a..9900dda2eef5 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -1034,6 +1034,7 @@ enum replay_FW_Message_type {
 	Replay_Msg_Not_Support = -1,
 	Replay_Set_Timing_Sync_Supported,
 	Replay_Set_Residency_Frameupdate_Timer,
+	Replay_Set_Pseudo_VTotal,
 };
 
 union replay_error_status {
@@ -1089,6 +1090,10 @@ struct replay_settings {
 	uint16_t coasting_vtotal_table[PR_COASTING_TYPE_NUM];
 	/* Maximum link off frame count */
 	enum replay_link_off_frame_count_level link_off_frame_count_level;
+	/* Replay pseudo vtotal for abm + ips on full screen video which can improve ips residency */
+	uint16_t abm_with_ips_on_full_screen_video_pseudo_vtotal;
+	/* Replay last pseudo vtotal set to DMUB */
+	uint16_t last_pseudo_vtotal;
 };
 
 /* To split out "global" and "per-panel" config settings.
@@ -1140,23 +1145,25 @@ struct dc_panel_config {
 	} ilr;
 };
 
+#define MAX_SINKS_PER_LINK 4
+
 /*
  *  USB4 DPIA BW ALLOCATION STRUCTS
  */
 struct dc_dpia_bw_alloc {
-	int sink_verified_bw;  // The Verified BW that sink can allocated and use that has been verified already
-	int sink_allocated_bw; // The Actual Allocated BW that sink currently allocated
-	int sink_max_bw;       // The Max BW that sink can require/support
+	int remote_sink_req_bw[MAX_SINKS_PER_LINK]; // BW requested by remote sinks
+	int link_verified_bw;  // The Verified BW that link can allocated and use that has been verified already
+	int link_max_bw;       // The Max BW that link can require/support
+	int allocated_bw;      // The Actual Allocated BW for this DPIA
 	int estimated_bw;      // The estimated available BW for this DPIA
 	int bw_granularity;    // BW Granularity
+	int dp_overhead;       // DP overhead in dp tunneling
 	bool bw_alloc_enabled; // The BW Alloc Mode Support is turned ON for all 3:  DP-Tx & Dpia & CM
 	bool response_ready;   // Response ready from the CM side
 	uint8_t nrd_max_lane_count; // Non-reduced max lane count
 	uint8_t nrd_max_link_rate; // Non-reduced max link rate
 };
 
-#define MAX_SINKS_PER_LINK 4
-
 enum dc_hpd_enable_select {
 	HPD_EN_FOR_ALL_EDP = 0,
 	HPD_EN_FOR_PRIMARY_EDP_ONLY,
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c
index 140598f18bbd..f0458b8f00af 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c
@@ -782,7 +782,7 @@ static void get_azalia_clock_info_dp(
 	/*audio_dto_module = dpDtoSourceClockInkhz * 10,000;
 	 *  [khz] ->[100Hz] */
 	azalia_clock_info->audio_dto_module =
-		pll_info->dp_dto_source_clock_in_khz * 10;
+		pll_info->audio_dto_source_clock_in_khz * 10;
 }
 
 void dce_aud_wall_dto_setup(
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
index 5d3f6fa1011e..970644b695cd 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
@@ -975,6 +975,9 @@ static bool dcn31_program_pix_clk(
 			look_up_in_video_optimized_rate_tlb(pix_clk_params->requested_pix_clk_100hz / 10);
 	struct bp_pixel_clock_parameters bp_pc_params = {0};
 	enum transmitter_color_depth bp_pc_colour_depth = TRANSMITTER_COLOR_DEPTH_24;
+
+	if (clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz != 0)
+		dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz;
 	// For these signal types Driver to program DP_DTO without calling VBIOS Command table
 	if (dc_is_dp_signal(pix_clk_params->signal_type) || dc_is_virtual_signal(pix_clk_params->signal_type)) {
 		if (e) {
@@ -1088,6 +1091,10 @@ static bool get_pixel_clk_frequency_100hz(
 	struct dce110_clk_src *clk_src = TO_DCE110_CLK_SRC(clock_source);
 	unsigned int clock_hz = 0;
 	unsigned int modulo_hz = 0;
+	unsigned int dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dprefclk_khz;
+
+	if (clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz != 0)
+		dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz;
 
 	if (clock_source->id == CLOCK_SOURCE_ID_DP_DTO) {
 		clock_hz = REG_READ(PHASE[inst]);
@@ -1100,7 +1107,7 @@ static bool get_pixel_clk_frequency_100hz(
 			modulo_hz = REG_READ(MODULO[inst]);
 			if (modulo_hz)
 				*pixel_clk_khz = div_u64((uint64_t)clock_hz*
-					clock_source->ctx->dc->clk_mgr->dprefclk_khz*10,
+					dp_dto_ref_khz*10,
 					modulo_hz);
 			else
 				*pixel_clk_khz = 0;
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
index e8570060d007..5bca67407c5b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
@@ -290,4 +290,5 @@ void dce_panel_cntl_construct(
 	dce_panel_cntl->base.funcs = &dce_link_panel_cntl_funcs;
 	dce_panel_cntl->base.ctx = init_data->ctx;
 	dce_panel_cntl->base.inst = init_data->inst;
+	dce_panel_cntl->base.pwrseq_inst = 0;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c
index e43f77c11c00..5f97a868ada3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c
@@ -56,16 +56,13 @@ static void dpp3_enable_cm_block(
 
 static enum dc_lut_mode dpp30_get_gamcor_current(struct dpp *dpp_base)
 {
-	enum dc_lut_mode mode;
+	enum dc_lut_mode mode = LUT_BYPASS;
 	uint32_t state_mode;
 	uint32_t lut_mode;
 	struct dcn3_dpp *dpp = TO_DCN30_DPP(dpp_base);
 
 	REG_GET(CM_GAMCOR_CONTROL, CM_GAMCOR_MODE_CURRENT, &state_mode);
 
-	if (state_mode == 0)
-		mode = LUT_BYPASS;
-
 	if (state_mode == 2) {//Programmable RAM LUT
 		REG_GET(CM_GAMCOR_CONTROL, CM_GAMCOR_SELECT_CURRENT, &lut_mode);
 		if (lut_mode == 0)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c
index ad0df1a72a90..9e96a3ace207 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c
@@ -215,4 +215,5 @@ void dcn301_panel_cntl_construct(
 	dcn301_panel_cntl->base.funcs = &dcn301_link_panel_cntl_funcs;
 	dcn301_panel_cntl->base.ctx = init_data->ctx;
 	dcn301_panel_cntl->base.inst = init_data->inst;
+	dcn301_panel_cntl->base.pwrseq_inst = 0;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c
index 03248422d6ff..281be20b1a10 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c
@@ -154,8 +154,24 @@ void dcn31_panel_cntl_construct(
 	struct dcn31_panel_cntl *dcn31_panel_cntl,
 	const struct panel_cntl_init_data *init_data)
 {
+	uint8_t pwrseq_inst = 0xF;
+
 	dcn31_panel_cntl->base.funcs = &dcn31_link_panel_cntl_funcs;
 	dcn31_panel_cntl->base.ctx = init_data->ctx;
 	dcn31_panel_cntl->base.inst = init_data->inst;
-	dcn31_panel_cntl->base.pwrseq_inst = init_data->pwrseq_inst;
+
+	switch (init_data->eng_id) {
+	case ENGINE_ID_DIGA:
+		pwrseq_inst = 0;
+		break;
+	case ENGINE_ID_DIGB:
+		pwrseq_inst = 1;
+		break;
+	default:
+		DC_LOG_WARNING("Unsupported pwrseq engine id: %d!\n", init_data->eng_id);
+		ASSERT(false);
+		break;
+	}
+
+	dcn31_panel_cntl->base.pwrseq_inst = pwrseq_inst;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c
index 501388014855..d761b0df2878 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c
@@ -203,12 +203,12 @@ void dcn32_link_encoder_construct(
 	enc10->base.hpd_source = init_data->hpd_source;
 	enc10->base.connector = init_data->connector;
 
-	if (enc10->base.connector.id == CONNECTOR_ID_USBC)
-		enc10->base.features.flags.bits.DP_IS_USB_C = 1;
 
 	enc10->base.preferred_engine = ENGINE_ID_UNKNOWN;
 
 	enc10->base.features = *enc_features;
+	if (enc10->base.connector.id == CONNECTOR_ID_USBC)
+		enc10->base.features.flags.bits.DP_IS_USB_C = 1;
 
 	enc10->base.transmitter = init_data->transmitter;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
index e4a328b45c8a..87760600e154 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
@@ -183,6 +183,20 @@ bool dcn32_all_pipes_have_stream_and_plane(struct dc *dc,
 	return true;
 }
 
+bool dcn32_subvp_in_use(struct dc *dc,
+		struct dc_state *context)
+{
+	uint32_t i;
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
+
+		if (dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_NONE)
+			return true;
+	}
+	return false;
+}
+
 bool dcn32_mpo_in_use(struct dc_state *context)
 {
 	uint32_t i;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c
index da94e5309fba..81e349d5835b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c
@@ -184,8 +184,6 @@ void dcn35_link_encoder_construct(
 	enc10->base.hpd_source = init_data->hpd_source;
 	enc10->base.connector = init_data->connector;
 
-	if (enc10->base.connector.id == CONNECTOR_ID_USBC)
-		enc10->base.features.flags.bits.DP_IS_USB_C = 1;
 
 	enc10->base.preferred_engine = ENGINE_ID_UNKNOWN;
 
@@ -240,6 +238,8 @@ void dcn35_link_encoder_construct(
 	}
 
 	enc10->base.features.flags.bits.HDMI_6GB_EN = 1;
+	if (enc10->base.connector.id == CONNECTOR_ID_USBC)
+		enc10->base.features.flags.bits.DP_IS_USB_C = 1;
 
 	if (bp_funcs->get_connector_speed_cap_info)
 		result = bp_funcs->get_connector_speed_cap_info(enc10->base.ctx->dc_bios,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 6042a5a6a44f..59ade76ffb18 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -72,11 +72,11 @@ CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn10/dcn10_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/dcn20_fpu.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags)
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index aa68d010cbfd..a0a65e099104 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -33,7 +33,6 @@
 #include "dcn30/dcn30_resource.h"
 #include "link.h"
 #include "dc_state_priv.h"
-#include "resource.h"
 
 #define DC_LOGGER_INIT(logger)
 
@@ -292,7 +291,7 @@ int dcn32_find_dummy_latency_index_for_fw_based_mclk_switch(struct dc *dc,
 
 		/* for subvp + DRR case, if subvp pipes are still present we support pstate */
 		if (vba->DRAMClockChangeSupport[vlevel][vba->maxMpcComb] == dm_dram_clock_change_unsupported &&
-				resource_subvp_in_use(dc, context))
+				dcn32_subvp_in_use(dc, context))
 			vba->DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] = temp_clock_change_support;
 
 		if (vlevel < context->bw_ctx.dml.vba.soc.num_states &&
@@ -1113,7 +1112,7 @@ struct pipe_slice_table {
 		struct pipe_ctx *pri_pipe;
 		struct dc_plane_state *plane;
 		int slice_count;
-	} mpc_combines[MAX_SURFACES];
+	} mpc_combines[MAX_PLANES];
 	int mpc_combine_count;
 };
 
@@ -1289,7 +1288,7 @@ static bool update_pipes_with_split_flags(struct dc *dc, struct dc_state *contex
 	return updated;
 }
 
-static bool should_allow_odm_power_optimization(struct dc *dc,
+static bool should_apply_odm_power_optimization(struct dc *dc,
 		struct dc_state *context, struct vba_vars_st *v, int *split,
 		bool *merge)
 {
@@ -1393,9 +1392,12 @@ static void try_odm_power_optimization_and_revalidate(
 {
 	int i;
 	unsigned int new_vlevel;
+	unsigned int cur_policy[MAX_PIPES];
 
-	for (i = 0; i < pipe_cnt; i++)
+	for (i = 0; i < pipe_cnt; i++) {
+		cur_policy[i] = pipes[i].pipe.dest.odm_combine_policy;
 		pipes[i].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1;
+	}
 
 	new_vlevel = dml_get_voltage_level(&context->bw_ctx.dml, pipes, pipe_cnt);
 
@@ -1404,6 +1406,9 @@ static void try_odm_power_optimization_and_revalidate(
 		memset(merge, 0, MAX_PIPES * sizeof(bool));
 		*vlevel = dcn20_validate_apply_pipe_split_flags(dc, context, new_vlevel, split, merge);
 		context->bw_ctx.dml.vba.VoltageLevel = *vlevel;
+	} else {
+		for (i = 0; i < pipe_cnt; i++)
+			pipes[i].pipe.dest.odm_combine_policy = cur_policy[i];
 	}
 }
 
@@ -1581,7 +1586,7 @@ static void dcn32_full_validate_bw_helper(struct dc *dc,
 		}
 	}
 
-	if (should_allow_odm_power_optimization(dc, context, vba, split, merge))
+	if (should_apply_odm_power_optimization(dc, context, vba, split, merge))
 		try_odm_power_optimization_and_revalidate(
 				dc, context, pipes, split, merge, vlevel, *pipe_cnt);
 
@@ -2210,7 +2215,8 @@ bool dcn32_internal_validate_bw(struct dc *dc,
 		int i;
 
 		pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes, fast_validate);
-		dcn32_update_dml_pipes_odm_policy_based_on_context(dc, context, pipes);
+		if (!dc->config.enable_windowed_mpo_odm)
+			dcn32_update_dml_pipes_odm_policy_based_on_context(dc, context, pipes);
 
 		/* repopulate_pipes = 1 means the pipes were either split or merged. In this case
 		 * we have to re-calculate the DET allocation and run through DML once more to
@@ -2273,7 +2279,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context,
 	unsigned int dummy_latency_index = 0;
 	int maxMpcComb = context->bw_ctx.dml.vba.maxMpcComb;
 	unsigned int min_dram_speed_mts = context->bw_ctx.dml.vba.DRAMSpeed;
-	bool subvp_active = resource_subvp_in_use(dc, context);
+	bool subvp_in_use = dcn32_subvp_in_use(dc, context);
 	unsigned int min_dram_speed_mts_margin;
 	bool need_fclk_lat_as_dummy = false;
 	bool is_subvp_p_drr = false;
@@ -2282,7 +2288,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context,
 	dc_assert_fp_enabled();
 
 	/* need to find dummy latency index for subvp */
-	if (subvp_active) {
+	if (subvp_in_use) {
 		/* Override DRAMClockChangeSupport for SubVP + DRR case where the DRR cannot switch without stretching it's VBLANK */
 		if (!pstate_en) {
 			context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][maxMpcComb] = dm_dram_clock_change_vblank_w_mall_sub_vp;
@@ -2468,7 +2474,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context,
 				dc->clk_mgr->bw_params->clk_table.entries[min_dram_speed_mts_offset].memclk_mhz * 16;
 		}
 
-		if (!context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching && !subvp_active) {
+		if (!context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching && !subvp_in_use) {
 			/* find largest table entry that is lower than dram speed,
 			 * but lower than DPM0 still uses DPM0
 			 */
@@ -3528,7 +3534,7 @@ void dcn32_set_clock_limits(const struct _vcs_dpi_soc_bounding_box_st *soc_bb)
 void dcn32_override_min_req_memclk(struct dc *dc, struct dc_state *context)
 {
 	// WA: restrict FPO and SubVP to use first non-strobe mode (DCN32 BW issue)
-	if ((context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || resource_subvp_in_use(dc, context)) &&
+	if ((context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || dcn32_subvp_in_use(dc, context)) &&
 			dc->dml.soc.num_chans <= 8) {
 		int num_mclk_levels = dc->clk_mgr->bw_params->clk_table.num_entries_per_clk.num_memclk_levels;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
index 3d12dabd39e4..7ea2bd5374d5 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
@@ -164,11 +164,11 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 		},
 	},
 	.num_states = 5,
-	.sr_exit_time_us = 14.0,
-	.sr_enter_plus_exit_time_us = 16.0,
-	.sr_exit_z8_time_us = 525.0,
-	.sr_enter_plus_exit_z8_time_us = 715.0,
-	.fclk_change_latency_us = 20.0,
+	.sr_exit_time_us = 28.0,
+	.sr_enter_plus_exit_time_us = 30.0,
+	.sr_exit_z8_time_us = 210.0,
+	.sr_enter_plus_exit_z8_time_us = 320.0,
+	.fclk_change_latency_us = 24.0,
 	.usr_retraining_latency_us = 2,
 	.writeback_latency_us = 12.0,
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
index b95bf27f2fe2..9be5ebf3a8c0 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
@@ -6229,7 +6229,7 @@ static void set_calculate_prefetch_schedule_params(struct display_mode_lib_st *m
 				CalculatePrefetchSchedule_params->GPUVMEnable = mode_lib->ms.cache_display_cfg.plane.GPUVMEnable;
 				CalculatePrefetchSchedule_params->HostVMEnable = mode_lib->ms.cache_display_cfg.plane.HostVMEnable;
 				CalculatePrefetchSchedule_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
-				CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
+				CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
 				CalculatePrefetchSchedule_params->DynamicMetadataEnable = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataEnable[k];
 				CalculatePrefetchSchedule_params->DynamicMetadataVMEnabled = mode_lib->ms.ip.dynamic_metadata_vm_enabled;
 				CalculatePrefetchSchedule_params->DynamicMetadataLinesBeforeActiveRequired = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataLinesBeforeActiveRequired[k];
@@ -6329,7 +6329,7 @@ static void dml_prefetch_check(struct display_mode_lib_st *mode_lib)
 				mode_lib->ms.NoOfDPPThisState,
 				mode_lib->ms.dpte_group_bytes,
 				s->HostVMInefficiencyFactor,
-				mode_lib->ms.soc.hostvm_min_page_size_kbytes,
+				mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024,
 				mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels);
 
 		s->NextMaxVStartup = s->MaxVStartupAllPlanes[j];
@@ -6542,7 +6542,7 @@ static void dml_prefetch_check(struct display_mode_lib_st *mode_lib)
 						mode_lib->ms.cache_display_cfg.plane.HostVMEnable,
 						mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels,
 						mode_lib->ms.cache_display_cfg.plane.GPUVMEnable,
-						mode_lib->ms.soc.hostvm_min_page_size_kbytes,
+						mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024,
 						mode_lib->ms.PDEAndMetaPTEBytesPerFrame[j][k],
 						mode_lib->ms.MetaRowBytes[j][k],
 						mode_lib->ms.DPTEBytesPerRow[j][k],
@@ -7687,7 +7687,7 @@ dml_bool_t dml_core_mode_support(struct display_mode_lib_st *mode_lib)
 		CalculateVMRowAndSwath_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
 		CalculateVMRowAndSwath_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels;
 		CalculateVMRowAndSwath_params->GPUVMMinPageSizeKBytes = mode_lib->ms.cache_display_cfg.plane.GPUVMMinPageSizeKBytes;
-		CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
+		CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
 		CalculateVMRowAndSwath_params->PTEBufferModeOverrideEn = mode_lib->ms.cache_display_cfg.plane.PTEBufferModeOverrideEn;
 		CalculateVMRowAndSwath_params->PTEBufferModeOverrideVal = mode_lib->ms.cache_display_cfg.plane.PTEBufferMode;
 		CalculateVMRowAndSwath_params->PTEBufferSizeNotExceeded = mode_lib->ms.PTEBufferSizeNotExceededPerState;
@@ -7957,7 +7957,7 @@ dml_bool_t dml_core_mode_support(struct display_mode_lib_st *mode_lib)
 		UseMinimumDCFCLK_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels;
 		UseMinimumDCFCLK_params->HostVMEnable = mode_lib->ms.cache_display_cfg.plane.HostVMEnable;
 		UseMinimumDCFCLK_params->NumberOfActiveSurfaces = mode_lib->ms.num_active_planes;
-		UseMinimumDCFCLK_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
+		UseMinimumDCFCLK_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
 		UseMinimumDCFCLK_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
 		UseMinimumDCFCLK_params->DynamicMetadataVMEnabled = mode_lib->ms.ip.dynamic_metadata_vm_enabled;
 		UseMinimumDCFCLK_params->ImmediateFlipRequirement = s->ImmediateFlipRequiredFinal;
@@ -8699,7 +8699,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
 	CalculateVMRowAndSwath_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
 	CalculateVMRowAndSwath_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels;
 	CalculateVMRowAndSwath_params->GPUVMMinPageSizeKBytes = mode_lib->ms.cache_display_cfg.plane.GPUVMMinPageSizeKBytes;
-	CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
+	CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
 	CalculateVMRowAndSwath_params->PTEBufferModeOverrideEn = mode_lib->ms.cache_display_cfg.plane.PTEBufferModeOverrideEn;
 	CalculateVMRowAndSwath_params->PTEBufferModeOverrideVal = mode_lib->ms.cache_display_cfg.plane.PTEBufferMode;
 	CalculateVMRowAndSwath_params->PTEBufferSizeNotExceeded = s->dummy_boolean_array[0];
@@ -8805,7 +8805,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
 			mode_lib->ms.cache_display_cfg.hw.DPPPerSurface,
 			locals->dpte_group_bytes,
 			s->HostVMInefficiencyFactor,
-			mode_lib->ms.soc.hostvm_min_page_size_kbytes,
+			mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024,
 			mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels);
 
 	locals->TCalc = 24.0 / locals->DCFCLKDeepSleep;
@@ -8995,7 +8995,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
 			CalculatePrefetchSchedule_params->GPUVMEnable = mode_lib->ms.cache_display_cfg.plane.GPUVMEnable;
 			CalculatePrefetchSchedule_params->HostVMEnable = mode_lib->ms.cache_display_cfg.plane.HostVMEnable;
 			CalculatePrefetchSchedule_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
-			CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
+			CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
 			CalculatePrefetchSchedule_params->DynamicMetadataEnable = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataEnable[k];
 			CalculatePrefetchSchedule_params->DynamicMetadataVMEnabled = mode_lib->ms.ip.dynamic_metadata_vm_enabled;
 			CalculatePrefetchSchedule_params->DynamicMetadataLinesBeforeActiveRequired = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataLinesBeforeActiveRequired[k];
@@ -9240,7 +9240,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
 						mode_lib->ms.cache_display_cfg.plane.HostVMEnable,
 						mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels,
 						mode_lib->ms.cache_display_cfg.plane.GPUVMEnable,
-						mode_lib->ms.soc.hostvm_min_page_size_kbytes,
+						mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024,
 						locals->PDEAndMetaPTEBytesFrame[k],
 						locals->MetaRowByte[k],
 						locals->PixelPTEBytesPerRow[k],
@@ -9446,13 +9446,13 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
 		CalculateWatermarks_params->CompressedBufferSizeInkByte = locals->CompressedBufferSizeInkByte;
 
 		// Output
-		CalculateWatermarks_params->Watermark = &s->dummy_watermark; // Watermarks *Watermark
-		CalculateWatermarks_params->DRAMClockChangeSupport = &mode_lib->ms.support.DRAMClockChangeSupport[0];
-		CalculateWatermarks_params->MaxActiveDRAMClockChangeLatencySupported = &s->dummy_single_array[0][0]; // dml_float_t *MaxActiveDRAMClockChangeLatencySupported[]
-		CalculateWatermarks_params->SubViewportLinesNeededInMALL = &mode_lib->ms.SubViewportLinesNeededInMALL[j]; // dml_uint_t SubViewportLinesNeededInMALL[]
-		CalculateWatermarks_params->FCLKChangeSupport = &mode_lib->ms.support.FCLKChangeSupport[0];
-		CalculateWatermarks_params->MaxActiveFCLKChangeLatencySupported = &s->dummy_single[0]; // dml_float_t *MaxActiveFCLKChangeLatencySupported
-		CalculateWatermarks_params->USRRetrainingSupport = &mode_lib->ms.support.USRRetrainingSupport[0];
+		CalculateWatermarks_params->Watermark = &locals->Watermark; // Watermarks *Watermark
+		CalculateWatermarks_params->DRAMClockChangeSupport = &locals->DRAMClockChangeSupport;
+		CalculateWatermarks_params->MaxActiveDRAMClockChangeLatencySupported = locals->MaxActiveDRAMClockChangeLatencySupported; // dml_float_t *MaxActiveDRAMClockChangeLatencySupported[]
+		CalculateWatermarks_params->SubViewportLinesNeededInMALL = locals->SubViewportLinesNeededInMALL; // dml_uint_t SubViewportLinesNeededInMALL[]
+		CalculateWatermarks_params->FCLKChangeSupport = &locals->FCLKChangeSupport;
+		CalculateWatermarks_params->MaxActiveFCLKChangeLatencySupported = &locals->MaxActiveFCLKChangeLatencySupported; // dml_float_t *MaxActiveFCLKChangeLatencySupported
+		CalculateWatermarks_params->USRRetrainingSupport = &locals->USRRetrainingSupport;
 
 		CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
 			&mode_lib->scratch,
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index fa6a93dd9629..1ba6933d2b36 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -341,9 +341,6 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc,
 		break;
 	}
 
-	if (dml2->config.bbox_overrides.clks_table.num_states)
-			p->in_states->num_states = dml2->config.bbox_overrides.clks_table.num_states;
-
 	/* Override from passed values, if available */
 	for (i = 0; i < p->in_states->num_states; i++) {
 		if (dml2->config.bbox_overrides.sr_exit_latency_us) {
@@ -400,7 +397,7 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc,
 	}
 	/* Copy clocks tables entries, if available */
 	if (dml2->config.bbox_overrides.clks_table.num_states) {
-
+		p->in_states->num_states = dml2->config.bbox_overrides.clks_table.num_states;
 		for (i = 0; i < dml2->config.bbox_overrides.clks_table.num_entries_per_clk.num_dcfclk_levels; i++) {
 			p->in_states->state_array[i].dcfclk_mhz = dml2->config.bbox_overrides.clks_table.clk_entries[i].dcfclk_mhz;
 		}
@@ -439,6 +436,14 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc,
 	}
 
 	dml2_policy_build_synthetic_soc_states(s, p);
+	if (dml2->v20.dml_core_ctx.project == dml_project_dcn35 ||
+		dml2->v20.dml_core_ctx.project == dml_project_dcn351) {
+		// Override last out_state with data from last in_state
+		// This will ensure that out_state contains max fclk
+		memcpy(&p->out_states->state_array[p->out_states->num_states - 1],
+				&p->in_states->state_array[p->in_states->num_states - 1],
+				sizeof(struct soc_state_bounding_box_st));
+	}
 }
 
 void dml2_translate_ip_params(const struct dc *in, struct ip_params_st *out)
@@ -626,8 +631,8 @@ static void populate_dml_output_cfg_from_stream_state(struct dml_output_cfg_st *
 		if (is_dp2p0_output_encoder(pipe))
 			out->OutputEncoder[location] = dml_dp2p0;
 		break;
-		out->OutputEncoder[location] = dml_edp;
 	case SIGNAL_TYPE_EDP:
+		out->OutputEncoder[location] = dml_edp;
 		break;
 	case SIGNAL_TYPE_HDMI_TYPE_A:
 	case SIGNAL_TYPE_DVI_SINGLE_LINK:
@@ -793,35 +798,28 @@ static void populate_dml_surface_cfg_from_plane_state(enum dml_project_id dml2_p
 	}
 }
 
-/*TODO no support for mpc combine, need rework - should calculate scaling params based on plane+stream*/
-static struct scaler_data get_scaler_data_for_plane(const struct dc_plane_state *in, const struct dc_state *context)
+static struct scaler_data get_scaler_data_for_plane(const struct dc_plane_state *in, struct dc_state *context)
 {
 	int i;
-	struct scaler_data data = { 0 };
+	struct pipe_ctx *temp_pipe = &context->res_ctx.temp_pipe;
+
+	memset(temp_pipe, 0, sizeof(struct pipe_ctx));
 
 	for (i = 0; i < MAX_PIPES; i++)	{
 		const struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
 
 		if (pipe->plane_state == in && !pipe->prev_odm_pipe) {
-			const struct pipe_ctx *next_pipe = pipe->next_odm_pipe;
-
-			data = context->res_ctx.pipe_ctx[i].plane_res.scl_data;
-			while (next_pipe) {
-				data.h_active += next_pipe->plane_res.scl_data.h_active;
-				data.recout.width += next_pipe->plane_res.scl_data.recout.width;
-				if (in->rotation == ROTATION_ANGLE_0 || in->rotation == ROTATION_ANGLE_180) {
-					data.viewport.width += next_pipe->plane_res.scl_data.viewport.width;
-				} else {
-					data.viewport.height += next_pipe->plane_res.scl_data.viewport.height;
-				}
-				next_pipe = next_pipe->next_odm_pipe;
-			}
+			temp_pipe->stream = pipe->stream;
+			temp_pipe->plane_state = pipe->plane_state;
+			temp_pipe->plane_res.scl_data.taps = pipe->plane_res.scl_data.taps;
+
+			resource_build_scaling_params(temp_pipe);
 			break;
 		}
 	}
 
 	ASSERT(i < MAX_PIPES);
-	return data;
+	return temp_pipe->plane_res.scl_data;
 }
 
 static void populate_dummy_dml_plane_cfg(struct dml_plane_cfg_st *out, unsigned int location, const struct dc_stream_state *in)
@@ -866,7 +864,7 @@ static void populate_dummy_dml_plane_cfg(struct dml_plane_cfg_st *out, unsigned
 	out->ScalerEnabled[location] = false;
 }
 
-static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out, unsigned int location, const struct dc_plane_state *in, const struct dc_state *context)
+static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out, unsigned int location, const struct dc_plane_state *in, struct dc_state *context)
 {
 	const struct scaler_data scaler_data = get_scaler_data_for_plane(in, context);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
index 26307e599614..2a58a7687bdb 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
@@ -76,6 +76,11 @@ static void map_hw_resources(struct dml2_context *dml2,
 			in_out_display_cfg->hw.DLGRefClkFreqMHz = 50;
 		}
 		for (j = 0; j < mode_support_info->DPPPerSurface[i]; j++) {
+			if (i >= __DML2_WRAPPER_MAX_STREAMS_PLANES__) {
+				dml_print("DML::%s: Index out of bounds: i=%d, __DML2_WRAPPER_MAX_STREAMS_PLANES__=%d\n",
+					  __func__, i, __DML2_WRAPPER_MAX_STREAMS_PLANES__);
+				break;
+			}
 			dml2->v20.scratch.dml_to_dc_pipe_mapping.dml_pipe_idx_to_stream_id[num_pipes] = dml2->v20.scratch.dml_to_dc_pipe_mapping.disp_cfg_to_stream_id[i];
 			dml2->v20.scratch.dml_to_dc_pipe_mapping.dml_pipe_idx_to_stream_id_valid[num_pipes] = true;
 			dml2->v20.scratch.dml_to_dc_pipe_mapping.dml_pipe_idx_to_plane_id[num_pipes] = dml2->v20.scratch.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id[i];
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
index fb328cd06cea..01493c49bd7a 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
@@ -1183,9 +1183,9 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx)
 		dto_params.timing = &pipe_ctx->stream->timing;
 		dp_hpo_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst;
 		if (dccg) {
-			dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
 			dccg->funcs->disable_symclk32_se(dccg, dp_hpo_inst);
 			dccg->funcs->set_dpstreamclk(dccg, REFCLK, tg->inst, dp_hpo_inst);
+			dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
 		}
 	} else if (dccg && dccg->funcs->disable_symclk_se) {
 		dccg->funcs->disable_symclk_se(dccg, stream_enc->stream_enc_inst,
@@ -1354,7 +1354,7 @@ static void build_audio_output(
 	if (state->clk_mgr &&
 		(pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT ||
 			pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)) {
-		audio_output->pll_info.dp_dto_source_clock_in_khz =
+		audio_output->pll_info.audio_dto_source_clock_in_khz =
 				state->clk_mgr->funcs->get_dp_ref_clk_frequency(
 						state->clk_mgr);
 	}
@@ -1476,7 +1476,7 @@ static enum dc_status dce110_enable_stream_timing(
 	return DC_OK;
 }
 
-static enum dc_status apply_single_controller_ctx_to_hw(
+enum dc_status dce110_apply_single_controller_ctx_to_hw(
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context,
 		struct dc *dc)
@@ -2302,7 +2302,7 @@ enum dc_status dce110_apply_ctx_to_hw(
 		if (pipe_ctx->top_pipe || pipe_ctx->prev_odm_pipe)
 			continue;
 
-		status = apply_single_controller_ctx_to_hw(
+		status = dce110_apply_single_controller_ctx_to_hw(
 				pipe_ctx,
 				context,
 				dc);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
index 08028a1779ae..ed3cc3648e8e 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
@@ -39,6 +39,10 @@ enum dc_status dce110_apply_ctx_to_hw(
 		struct dc *dc,
 		struct dc_state *context);
 
+enum dc_status dce110_apply_single_controller_ctx_to_hw(
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context,
+		struct dc *dc);
 
 void dce110_enable_stream(struct pipe_ctx *pipe_ctx);
 
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
index 51dd2ae09b2a..6dd479e8a348 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
@@ -3076,7 +3076,7 @@ void dcn10_prepare_bandwidth(
 			context,
 			false);
 
-	dc->optimized_required |= hubbub->funcs->program_watermarks(hubbub,
+	dc->wm_optimized_required = hubbub->funcs->program_watermarks(hubbub,
 			&context->bw_ctx.bw.dcn.watermarks,
 			dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000,
 			true);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
index bc71a9b058fe..931ac8ed7069 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
@@ -1882,42 +1882,6 @@ static void dcn20_program_pipe(
 	}
 }
 
-static void update_vmin_vmax_fams(struct dc *dc,
-		struct dc_state *context)
-{
-	uint32_t i;
-	struct drr_params params = {0};
-	bool subvp_in_use = resource_subvp_in_use(dc, context);
-
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
-
-		if (resource_is_pipe_type(pipe, OTG_MASTER) &&
-				((subvp_in_use && dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_PHANTOM &&
-				pipe->stream->allow_freesync) || (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching && pipe->stream->fpo_in_use))) {
-			if (!pipe->stream->vrr_active_variable && !pipe->stream->vrr_active_fixed) {
-				struct timing_generator *tg = context->res_ctx.pipe_ctx[i].stream_res.tg;
-
-				/* DRR should be configured already if we're in active variable
-				 * or active fixed, so only program if we're not in this state
-				 */
-				params.vertical_total_min = pipe->stream->timing.v_total;
-				params.vertical_total_max = pipe->stream->timing.v_total;
-				tg->funcs->set_drr(tg, &params);
-			}
-		} else {
-			if (resource_is_pipe_type(pipe, OTG_MASTER) &&
-					!pipe->stream->vrr_active_variable &&
-					!pipe->stream->vrr_active_fixed) {
-				struct timing_generator *tg = context->res_ctx.pipe_ctx[i].stream_res.tg;
-				params.vertical_total_min = 0;
-				params.vertical_total_max = 0;
-				tg->funcs->set_drr(tg, &params);
-			}
-		}
-	}
-}
-
 void dcn20_program_front_end_for_ctx(
 		struct dc *dc,
 		struct dc_state *context)
@@ -1994,7 +1958,6 @@ void dcn20_program_front_end_for_ctx(
 				&& context->res_ctx.pipe_ctx[i].stream)
 			hws->funcs.blank_pixel_data(dc, &context->res_ctx.pipe_ctx[i], true);
 
-	update_vmin_vmax_fams(dc, context);
 
 	/* Disconnect mpcc */
 	for (i = 0; i < dc->res_pool->pipe_count; i++)
@@ -2196,10 +2159,10 @@ void dcn20_prepare_bandwidth(
 	}
 
 	/* program dchubbub watermarks:
-	 * For assigning optimized_required, use |= operator since we don't want
+	 * For assigning wm_optimized_required, use |= operator since we don't want
 	 * to clear the value if the optimize has not happened yet
 	 */
-	dc->optimized_required |= hubbub->funcs->program_watermarks(hubbub,
+	dc->wm_optimized_required |= hubbub->funcs->program_watermarks(hubbub,
 					&context->bw_ctx.bw.dcn.watermarks,
 					dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000,
 					false);
@@ -2212,10 +2175,10 @@ void dcn20_prepare_bandwidth(
 	if (hubbub->funcs->program_compbuf_size) {
 		if (context->bw_ctx.dml.ip.min_comp_buffer_size_kbytes) {
 			compbuf_size_kb = context->bw_ctx.dml.ip.min_comp_buffer_size_kbytes;
-			dc->optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.dml.ip.min_comp_buffer_size_kbytes);
+			dc->wm_optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.dml.ip.min_comp_buffer_size_kbytes);
 		} else {
 			compbuf_size_kb = context->bw_ctx.bw.dcn.compbuf_size_kb;
-			dc->optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.bw.dcn.compbuf_size_kb);
+			dc->wm_optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.bw.dcn.compbuf_size_kb);
 		}
 
 		hubbub->funcs->program_compbuf_size(hubbub, compbuf_size_kb, false);
@@ -2598,7 +2561,7 @@ void dcn20_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx)
 		tg->funcs->setup_vertical_interrupt2(tg, start_line);
 }
 
-static void dcn20_reset_back_end_for_pipe(
+void dcn20_reset_back_end_for_pipe(
 		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context)
@@ -2827,18 +2790,17 @@ void dcn20_enable_stream(struct pipe_ctx *pipe_ctx)
 	}
 
 	if (dc->link_srv->dp_is_128b_132b_signal(pipe_ctx)) {
-		dp_hpo_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst;
-		dccg->funcs->set_dpstreamclk(dccg, DTBCLK0, tg->inst, dp_hpo_inst);
-
-		phyd32clk = get_phyd32clk_src(link);
-		dccg->funcs->enable_symclk32_se(dccg, dp_hpo_inst, phyd32clk);
-
 		dto_params.otg_inst = tg->inst;
 		dto_params.pixclk_khz = pipe_ctx->stream->timing.pix_clk_100hz / 10;
 		dto_params.num_odm_segments = get_odm_segment_count(pipe_ctx);
 		dto_params.timing = &pipe_ctx->stream->timing;
 		dto_params.ref_dtbclk_khz = dc->clk_mgr->funcs->get_dtb_ref_clk_frequency(dc->clk_mgr);
 		dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
+		dp_hpo_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst;
+		dccg->funcs->set_dpstreamclk(dccg, DTBCLK0, tg->inst, dp_hpo_inst);
+
+		phyd32clk = get_phyd32clk_src(link);
+		dccg->funcs->enable_symclk32_se(dccg, dp_hpo_inst, phyd32clk);
 	} else {
 		if (dccg->funcs->enable_symclk_se)
 			dccg->funcs->enable_symclk_se(dccg, stream_enc->stream_enc_inst,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
index b94c85340abf..d950b3e54ec2 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
@@ -84,6 +84,10 @@ enum dc_status dcn20_enable_stream_timing(
 void dcn20_disable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx);
 void dcn20_enable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx);
 void dcn20_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn20_reset_back_end_for_pipe(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context);
 void dcn20_init_blank(
 		struct dc *dc,
 		struct timing_generator *tg);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
index 8e88dcaf88f5..7252f5f781f0 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
@@ -206,28 +206,32 @@ void dcn21_set_abm_immediate_disable(struct pipe_ctx *pipe_ctx)
 void dcn21_set_pipe(struct pipe_ctx *pipe_ctx)
 {
 	struct abm *abm = pipe_ctx->stream_res.abm;
-	uint32_t otg_inst = pipe_ctx->stream_res.tg->inst;
+	struct timing_generator *tg = pipe_ctx->stream_res.tg;
 	struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl;
 	struct dmcu *dmcu = pipe_ctx->stream->ctx->dc->res_pool->dmcu;
+	uint32_t otg_inst;
+
+	if (!abm || !tg || !panel_cntl)
+		return;
+
+	otg_inst = tg->inst;
 
 	if (dmcu) {
 		dce110_set_pipe(pipe_ctx);
 		return;
 	}
 
-	if (abm && panel_cntl) {
-		if (abm->funcs && abm->funcs->set_pipe_ex) {
-			abm->funcs->set_pipe_ex(abm,
+	if (abm->funcs && abm->funcs->set_pipe_ex) {
+		abm->funcs->set_pipe_ex(abm,
 					otg_inst,
 					SET_ABM_PIPE_NORMAL,
 					panel_cntl->inst,
 					panel_cntl->pwrseq_inst);
-		} else {
-				dmub_abm_set_pipe(abm, otg_inst,
-						SET_ABM_PIPE_NORMAL,
-						panel_cntl->inst,
-						panel_cntl->pwrseq_inst);
-		}
+	} else {
+		dmub_abm_set_pipe(abm, otg_inst,
+				  SET_ABM_PIPE_NORMAL,
+				  panel_cntl->inst,
+				  panel_cntl->pwrseq_inst);
 	}
 }
 
@@ -237,34 +241,35 @@ bool dcn21_set_backlight_level(struct pipe_ctx *pipe_ctx,
 {
 	struct dc_context *dc = pipe_ctx->stream->ctx;
 	struct abm *abm = pipe_ctx->stream_res.abm;
+	struct timing_generator *tg = pipe_ctx->stream_res.tg;
 	struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl;
+	uint32_t otg_inst;
+
+	if (!abm || !tg || !panel_cntl)
+		return false;
+
+	otg_inst = tg->inst;
 
 	if (dc->dc->res_pool->dmcu) {
 		dce110_set_backlight_level(pipe_ctx, backlight_pwm_u16_16, frame_ramp);
 		return true;
 	}
 
-	if (abm != NULL) {
-		uint32_t otg_inst = pipe_ctx->stream_res.tg->inst;
-
-		if (abm && panel_cntl) {
-			if (abm->funcs && abm->funcs->set_pipe_ex) {
-				abm->funcs->set_pipe_ex(abm,
-						otg_inst,
-						SET_ABM_PIPE_NORMAL,
-						panel_cntl->inst,
-						panel_cntl->pwrseq_inst);
-			} else {
-					dmub_abm_set_pipe(abm,
-							otg_inst,
-							SET_ABM_PIPE_NORMAL,
-							panel_cntl->inst,
-							panel_cntl->pwrseq_inst);
-			}
-		}
+	if (abm->funcs && abm->funcs->set_pipe_ex) {
+		abm->funcs->set_pipe_ex(abm,
+					otg_inst,
+					SET_ABM_PIPE_NORMAL,
+					panel_cntl->inst,
+					panel_cntl->pwrseq_inst);
+	} else {
+		dmub_abm_set_pipe(abm,
+				  otg_inst,
+				  SET_ABM_PIPE_NORMAL,
+				  panel_cntl->inst,
+				  panel_cntl->pwrseq_inst);
 	}
 
-	if (abm && abm->funcs && abm->funcs->set_backlight_level_pwm)
+	if (abm->funcs && abm->funcs->set_backlight_level_pwm)
 		abm->funcs->set_backlight_level_pwm(abm, backlight_pwm_u16_16,
 			frame_ramp, 0, panel_cntl->inst);
 	else
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
index 6c9299c7683d..aa36d7a56ca8 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
@@ -1474,9 +1474,44 @@ void dcn32_update_dsc_pg(struct dc *dc,
 	}
 }
 
+void dcn32_disable_phantom_streams(struct dc *dc, struct dc_state *context)
+{
+	struct dce_hwseq *hws = dc->hwseq;
+	int i;
+
+	for (i = dc->res_pool->pipe_count - 1; i >= 0 ; i--) {
+		struct pipe_ctx *pipe_ctx_old =
+			&dc->current_state->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+		if (!pipe_ctx_old->stream)
+			continue;
+
+		if (dc_state_get_pipe_subvp_type(dc->current_state, pipe_ctx_old) != SUBVP_PHANTOM)
+			continue;
+
+		if (pipe_ctx_old->top_pipe || pipe_ctx_old->prev_odm_pipe)
+			continue;
+
+		if (!pipe_ctx->stream || pipe_need_reprogram(pipe_ctx_old, pipe_ctx) ||
+				(pipe_ctx->stream && dc_state_get_pipe_subvp_type(context, pipe_ctx) != SUBVP_PHANTOM)) {
+			struct clock_source *old_clk = pipe_ctx_old->clock_source;
+
+			if (hws->funcs.reset_back_end_for_pipe)
+				hws->funcs.reset_back_end_for_pipe(dc, pipe_ctx_old, dc->current_state);
+			if (hws->funcs.enable_stream_gating)
+				hws->funcs.enable_stream_gating(dc, pipe_ctx_old);
+			if (old_clk)
+				old_clk->funcs->cs_power_down(old_clk);
+		}
+	}
+}
+
 void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context)
 {
 	unsigned int i;
+	enum dc_status status = DC_OK;
+	struct dce_hwseq *hws = dc->hwseq;
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
@@ -1497,16 +1532,39 @@ void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context)
 		}
 	}
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i];
-
-		if (new_pipe->stream && dc_state_get_pipe_subvp_type(context, new_pipe) == SUBVP_PHANTOM) {
-			// If old context or new context has phantom pipes, apply
-			// the phantom timings now. We can't change the phantom
-			// pipe configuration safely without driver acquiring
-			// the DMCUB lock first.
-			dc->hwss.apply_ctx_to_hw(dc, context);
-			break;
+		struct pipe_ctx *pipe_ctx_old =
+					&dc->current_state->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+		if (pipe_ctx->stream == NULL)
+			continue;
+
+		if (dc_state_get_pipe_subvp_type(context, pipe_ctx) != SUBVP_PHANTOM)
+			continue;
+
+		if (pipe_ctx->stream == pipe_ctx_old->stream &&
+			pipe_ctx->stream->link->link_state_valid) {
+			continue;
 		}
+
+		if (pipe_ctx_old->stream && !pipe_need_reprogram(pipe_ctx_old, pipe_ctx))
+			continue;
+
+		if (pipe_ctx->top_pipe || pipe_ctx->prev_odm_pipe)
+			continue;
+
+		if (hws->funcs.apply_single_controller_ctx_to_hw)
+			status = hws->funcs.apply_single_controller_ctx_to_hw(
+					pipe_ctx,
+					context,
+					dc);
+
+		ASSERT(status == DC_OK);
+
+#ifdef CONFIG_DRM_AMD_DC_FP
+		if (hws->funcs.resync_fifo_dccg_dio)
+			hws->funcs.resync_fifo_dccg_dio(hws, dc, context);
+#endif
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
index cecf7f0f5671..069e20bc87c0 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
@@ -111,6 +111,8 @@ void dcn32_update_dsc_pg(struct dc *dc,
 
 void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context);
 
+void dcn32_disable_phantom_streams(struct dc *dc, struct dc_state *context);
+
 void dcn32_init_blank(
 		struct dc *dc,
 		struct timing_generator *tg);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
index 427cfc8c24a4..e8ac94a005b8 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
@@ -109,6 +109,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = {
 	.get_dcc_en_bits = dcn10_get_dcc_en_bits,
 	.commit_subvp_config = dcn32_commit_subvp_config,
 	.enable_phantom_streams = dcn32_enable_phantom_streams,
+	.disable_phantom_streams = dcn32_disable_phantom_streams,
 	.subvp_pipe_control_lock = dcn32_subvp_pipe_control_lock,
 	.update_visual_confirm_color = dcn10_update_visual_confirm_color,
 	.subvp_pipe_control_lock_fast = dcn32_subvp_pipe_control_lock_fast,
@@ -159,6 +160,8 @@ static const struct hwseq_private_funcs dcn32_private_funcs = {
 	.set_pixels_per_cycle = dcn32_set_pixels_per_cycle,
 	.resync_fifo_dccg_dio = dcn32_resync_fifo_dccg_dio,
 	.is_dp_dig_pixel_rate_div_policy = dcn32_is_dp_dig_pixel_rate_div_policy,
+	.apply_single_controller_ctx_to_hw = dce110_apply_single_controller_ctx_to_hw,
+	.reset_back_end_for_pipe = dcn20_reset_back_end_for_pipe,
 };
 
 void dcn32_hw_sequencer_init_functions(struct dc *dc)
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
index 9c806385ecbd..8b6c49622f3b 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
@@ -680,7 +680,7 @@ void dcn35_power_down_on_boot(struct dc *dc)
 bool dcn35_apply_idle_power_optimizations(struct dc *dc, bool enable)
 {
 	struct dc_link *edp_links[MAX_NUM_EDP];
-	int edp_num;
+	int i, edp_num;
 	if (dc->debug.dmcub_emulation)
 		return true;
 
@@ -688,6 +688,13 @@ bool dcn35_apply_idle_power_optimizations(struct dc *dc, bool enable)
 		dc_get_edp_links(dc, edp_links, &edp_num);
 		if (edp_num == 0 || edp_num > 1)
 			return false;
+
+		for (i = 0; i < dc->current_state->stream_count; ++i) {
+			struct dc_stream_state *stream = dc->current_state->streams[i];
+
+			if (!stream->dpms_off && !dc_is_embedded_signal(stream->signal))
+				return false;
+		}
 	}
 
 	// TODO: review other cases when idle optimization is allowed
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
index a54399383318..64ca7c66509b 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
@@ -379,6 +379,7 @@ struct hw_sequencer_funcs {
 			struct dc_cursor_attributes *cursor_attr);
 	void (*commit_subvp_config)(struct dc *dc, struct dc_state *context);
 	void (*enable_phantom_streams)(struct dc *dc, struct dc_state *context);
+	void (*disable_phantom_streams)(struct dc *dc, struct dc_state *context);
 	void (*subvp_pipe_control_lock)(struct dc *dc,
 			struct dc_state *context,
 			bool lock,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
index 6137cf09aa54..b3c62a82cb1c 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
@@ -165,8 +165,15 @@ struct hwseq_private_funcs {
 	void (*set_pixels_per_cycle)(struct pipe_ctx *pipe_ctx);
 	void (*resync_fifo_dccg_dio)(struct dce_hwseq *hws, struct dc *dc,
 			struct dc_state *context);
+	enum dc_status (*apply_single_controller_ctx_to_hw)(
+			struct pipe_ctx *pipe_ctx,
+			struct dc_state *context,
+			struct dc *dc);
 	bool (*is_dp_dig_pixel_rate_div_policy)(struct pipe_ctx *pipe_ctx);
 #endif
+	void (*reset_back_end_for_pipe)(struct dc *dc,
+			struct pipe_ctx *pipe_ctx,
+			struct dc_state *context);
 };
 
 struct dce_hwseq {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index f74ae0d41d3c..3a6bf77a6873 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -469,6 +469,8 @@ struct resource_context {
 	unsigned int hpo_dp_link_enc_to_link_idx[MAX_HPO_DP2_LINK_ENCODERS];
 	int hpo_dp_link_enc_ref_cnts[MAX_HPO_DP2_LINK_ENCODERS];
 	bool is_mpc_3dlut_acquired[MAX_PIPES];
+	/* solely used for build scalar data in dml2 */
+	struct pipe_ctx temp_pipe;
 };
 
 struct dce_bw_output {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
index cbba39d251e5..17e014d3bdc8 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
@@ -333,6 +333,7 @@ struct clk_mgr {
 	bool force_smu_not_present;
 	bool dc_mode_softmax_enabled;
 	int dprefclk_khz; // Used by program pixel clock in clock source funcs, need to figureout where this goes
+	int dp_dto_source_clock_in_khz; // Used to program DP DTO with ss adjustment on DCN314
 	int dentist_vco_freq_khz;
 	struct clk_state_registers_and_bypass boot_snapshot;
 	struct clk_bw_params *bw_params;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h b/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h
index 5dcbaa2db964..e97d964a1791 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h
@@ -57,7 +57,7 @@ struct panel_cntl_funcs {
 struct panel_cntl_init_data {
 	struct dc_context *ctx;
 	uint32_t inst;
-	uint32_t pwrseq_inst;
+	uint32_t eng_id;
 };
 
 struct panel_cntl {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h
index 1d51fed12e20..77a60aa9f27b 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/resource.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h
@@ -427,22 +427,18 @@ struct pipe_ctx *resource_get_primary_dpp_pipe(const struct pipe_ctx *dpp_pipe);
 int resource_get_mpc_slice_index(const struct pipe_ctx *dpp_pipe);
 
 /*
- * Get number of MPC "cuts" of the plane associated with the pipe. MPC slice
- * count is equal to MPC splits + 1. For example if a plane is cut 3 times, it
- * will have 4 pieces of slice.
- * return - 0 if pipe is not used for a plane with MPCC combine. otherwise
- * the number of MPC "cuts" for the plane.
+ * Get the number of MPC slices associated with the pipe.
+ * The function returns 0 if the pipe is not associated with an MPC combine
+ * pipe topology.
  */
-int resource_get_mpc_slice_count(const struct pipe_ctx *opp_head);
+int resource_get_mpc_slice_count(const struct pipe_ctx *pipe);
 
 /*
- * Get number of ODM "cuts" of the timing associated with the pipe. ODM slice
- * count is equal to ODM splits + 1. For example if a timing is cut 3 times, it
- * will have 4 pieces of slice.
- * return - 0 if pipe is not used for ODM combine. otherwise
- * the number of ODM "cuts" for the timing.
+ * Get the number of ODM slices associated with the pipe.
+ * The function returns 0 if the pipe is not associated with an ODM combine
+ * pipe topology.
  */
-int resource_get_odm_slice_count(const struct pipe_ctx *otg_master);
+int resource_get_odm_slice_count(const struct pipe_ctx *pipe);
 
 /* Get the ODM slice index counting from 0 from left most slice */
 int resource_get_odm_slice_index(const struct pipe_ctx *opp_head);
@@ -609,9 +605,6 @@ bool dc_resource_acquire_secondary_pipe_for_mpc_odm_legacy(
 		struct pipe_ctx *sec_pipe,
 		bool odm);
 
-bool resource_subvp_in_use(struct dc *dc,
-		struct dc_state *context);
-
 /* A test harness interface that modifies dp encoder resources in the given dc
  * state and bypasses the need to revalidate. The interface assumes that the
  * test harness interface is called with pre-validated link config stored in the
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
index 5fe8b4871c77..3cbfbf8d107e 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
@@ -900,11 +900,15 @@ bool link_set_dsc_pps_packet(struct pipe_ctx *pipe_ctx, bool enable, bool immedi
 {
 	struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc;
 	struct dc_stream_state *stream = pipe_ctx->stream;
-	DC_LOGGER_INIT(dsc->ctx->logger);
 
-	if (!pipe_ctx->stream->timing.flags.DSC || !dsc)
+	if (!pipe_ctx->stream->timing.flags.DSC)
 		return false;
 
+	if (!dsc)
+		return false;
+
+	DC_LOGGER_INIT(dsc->ctx->logger);
+
 	if (enable) {
 		struct dsc_config dsc_cfg;
 		uint8_t dsc_packed_pps[128];
@@ -2005,17 +2009,11 @@ static enum dc_status enable_link_dp(struct dc_state *state,
 		}
 	}
 
-	/*
-	 * If the link is DP-over-USB4 do the following:
-	 * - Train with fallback when enabling DPIA link. Conventional links are
+	/* Train with fallback when enabling DPIA link. Conventional links are
 	 * trained with fallback during sink detection.
-	 * - Allocate only what the stream needs for bw in Gbps. Inform the CM
-	 * in case stream needs more or less bw from what has been allocated
-	 * earlier at plug time.
 	 */
-	if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) {
+	if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA)
 		do_fallback = true;
-	}
 
 	/*
 	 * Temporary w/a to get DP2.0 link rates to work with SST.
@@ -2197,6 +2195,32 @@ static enum dc_status enable_link(
 	return status;
 }
 
+static bool allocate_usb4_bandwidth_for_stream(struct dc_stream_state *stream, int bw)
+{
+	return true;
+}
+
+static bool allocate_usb4_bandwidth(struct dc_stream_state *stream)
+{
+	bool ret;
+
+	int bw = dc_bandwidth_in_kbps_from_timing(&stream->timing,
+			dc_link_get_highest_encoding_format(stream->sink->link));
+
+	ret = allocate_usb4_bandwidth_for_stream(stream, bw);
+
+	return ret;
+}
+
+static bool deallocate_usb4_bandwidth(struct dc_stream_state *stream)
+{
+	bool ret;
+
+	ret = allocate_usb4_bandwidth_for_stream(stream, 0);
+
+	return ret;
+}
+
 void link_set_dpms_off(struct pipe_ctx *pipe_ctx)
 {
 	struct dc  *dc = pipe_ctx->stream->ctx->dc;
@@ -2232,6 +2256,9 @@ void link_set_dpms_off(struct pipe_ctx *pipe_ctx)
 	update_psp_stream_config(pipe_ctx, true);
 	dc->hwss.blank_stream(pipe_ctx);
 
+	if (pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA)
+		deallocate_usb4_bandwidth(pipe_ctx->stream);
+
 	if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
 		deallocate_mst_payload(pipe_ctx);
 	else if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT &&
@@ -2474,6 +2501,9 @@ void link_set_dpms_on(
 		}
 	}
 
+	if (pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA)
+		allocate_usb4_bandwidth(pipe_ctx->stream);
+
 	if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
 		allocate_mst_payload(pipe_ctx);
 	else if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT &&
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_factory.c b/drivers/gpu/drm/amd/display/dc/link/link_factory.c
index 37d3027c32dc..cf22b8f28ba6 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_factory.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_factory.c
@@ -370,30 +370,6 @@ static enum transmitter translate_encoder_to_transmitter(
 	}
 }
 
-static uint8_t translate_dig_inst_to_pwrseq_inst(struct dc_link *link)
-{
-	uint8_t pwrseq_inst = 0xF;
-	struct dc_context *dc_ctx = link->dc->ctx;
-
-	DC_LOGGER_INIT(dc_ctx->logger);
-
-	switch (link->eng_id) {
-	case ENGINE_ID_DIGA:
-		pwrseq_inst = 0;
-		break;
-	case ENGINE_ID_DIGB:
-		pwrseq_inst = 1;
-		break;
-	default:
-		DC_LOG_WARNING("Unsupported pwrseq engine id: %d!\n", link->eng_id);
-		ASSERT(false);
-		break;
-	}
-
-	return pwrseq_inst;
-}
-
-
 static void link_destruct(struct dc_link *link)
 {
 	int i;
@@ -657,7 +633,7 @@ static bool construct_phy(struct dc_link *link,
 			link->link_id.id == CONNECTOR_ID_LVDS)) {
 		panel_cntl_init_data.ctx = dc_ctx;
 		panel_cntl_init_data.inst = panel_cntl_init_data.ctx->dc_edp_id_count;
-		panel_cntl_init_data.pwrseq_inst = translate_dig_inst_to_pwrseq_inst(link);
+		panel_cntl_init_data.eng_id = link->eng_id;
 		link->panel_cntl =
 			link->dc->res_pool->funcs->panel_cntl_create(
 								&panel_cntl_init_data);
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_validation.c b/drivers/gpu/drm/amd/display/dc/link/link_validation.c
index b45fda96eaf6..5b0bc7f6a188 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_validation.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_validation.c
@@ -346,23 +346,61 @@ enum dc_status link_validate_mode_timing(
 	return DC_OK;
 }
 
+/*
+ * This function calculates the bandwidth required for the stream timing
+ * and aggregates the stream bandwidth for the respective dpia link
+ *
+ * @stream: pointer to the dc_stream_state struct instance
+ * @num_streams: number of streams to be validated
+ *
+ * return: true if validation is succeeded
+ */
 bool link_validate_dpia_bandwidth(const struct dc_stream_state *stream, const unsigned int num_streams)
 {
-	bool ret = true;
-	int bw_needed[MAX_DPIA_NUM];
-	struct dc_link *link[MAX_DPIA_NUM];
+	int bw_needed[MAX_DPIA_NUM] = {0};
+	struct dc_link *dpia_link[MAX_DPIA_NUM] = {0};
+	int num_dpias = 0;
+
+	for (unsigned int i = 0; i < num_streams; ++i) {
+		if (stream[i].signal == SIGNAL_TYPE_DISPLAY_PORT) {
+			/* new dpia sst stream, check whether it exceeds max dpia */
+			if (num_dpias >= MAX_DPIA_NUM)
+				return false;
 
-	if (!num_streams || num_streams > MAX_DPIA_NUM)
-		return ret;
+			dpia_link[num_dpias] = stream[i].link;
+			bw_needed[num_dpias] = dc_bandwidth_in_kbps_from_timing(&stream[i].timing,
+					dc_link_get_highest_encoding_format(dpia_link[num_dpias]));
+			num_dpias++;
+		} else if (stream[i].signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
+			uint8_t j = 0;
+			/* check whether its a known dpia link */
+			for (; j < num_dpias; ++j) {
+				if (dpia_link[j] == stream[i].link)
+					break;
+			}
+
+			if (j == num_dpias) {
+				/* new dpia mst stream, check whether it exceeds max dpia */
+				if (num_dpias >= MAX_DPIA_NUM)
+					return false;
+				else {
+					dpia_link[j] = stream[i].link;
+					num_dpias++;
+				}
+			}
+
+			bw_needed[j] += dc_bandwidth_in_kbps_from_timing(&stream[i].timing,
+				dc_link_get_highest_encoding_format(dpia_link[j]));
+		}
+	}
 
-	for (uint8_t i = 0; i < num_streams; ++i) {
+	/* Include dp overheads */
+	for (uint8_t i = 0; i < num_dpias; ++i) {
+		int dp_overhead = 0;
 
-		link[i] = stream[i].link;
-		bw_needed[i] = dc_bandwidth_in_kbps_from_timing(&stream[i].timing,
-				dc_link_get_highest_encoding_format(link[i]));
+		dp_overhead = link_dp_dpia_get_dp_overhead_in_dp_tunneling(dpia_link[i]);
+		bw_needed[i] += dp_overhead;
 	}
 
-	ret = dpia_validate_usb4_bw(link, bw_needed, num_streams);
-
-	return ret;
+	return dpia_validate_usb4_bw(dpia_link, bw_needed, num_dpias);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.c
index 982eda3c46f5..6af42ba9885c 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.c
@@ -82,25 +82,33 @@ bool dpia_query_hpd_status(struct dc_link *link)
 {
 	union dmub_rb_cmd cmd = {0};
 	struct dc_dmub_srv *dmub_srv = link->ctx->dmub_srv;
-	bool is_hpd_high = false;
 
 	/* prepare QUERY_HPD command */
 	cmd.query_hpd.header.type = DMUB_CMD__QUERY_HPD_STATE;
 	cmd.query_hpd.data.instance = link->link_id.enum_id - ENUM_ID_1;
 	cmd.query_hpd.data.ch_type = AUX_CHANNEL_DPIA;
 
-	/* Return HPD status reported by DMUB if query successfully executed. */
-	if (dc_wake_and_execute_dmub_cmd(dmub_srv->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY) &&
-	    cmd.query_hpd.data.status == AUX_RET_SUCCESS)
-		is_hpd_high = cmd.query_hpd.data.result;
-
-	DC_LOG_DEBUG("%s: link(%d) dpia(%d) cmd_status(%d) result(%d)\n",
-		__func__,
-		link->link_index,
-		link->link_id.enum_id - ENUM_ID_1,
-		cmd.query_hpd.data.status,
-		cmd.query_hpd.data.result);
-
-	return is_hpd_high;
+	/* Query dpia hpd status from dmub */
+	if (dc_wake_and_execute_dmub_cmd(dmub_srv->ctx, &cmd,
+		DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY) &&
+	    cmd.query_hpd.data.status == AUX_RET_SUCCESS) {
+		DC_LOG_DEBUG("%s: for link(%d) dpia(%d) success, current_hpd_status(%d) new_hpd_status(%d)\n",
+			__func__,
+			link->link_index,
+			link->link_id.enum_id - ENUM_ID_1,
+			link->hpd_status,
+			cmd.query_hpd.data.result);
+		link->hpd_status = cmd.query_hpd.data.result;
+	} else {
+		DC_LOG_ERROR("%s: for link(%d) dpia(%d) failed with status(%d), current_hpd_status(%d) new_hpd_status(0)\n",
+			__func__,
+			link->link_index,
+			link->link_id.enum_id - ENUM_ID_1,
+			cmd.query_hpd.data.status,
+			link->hpd_status);
+		link->hpd_status = false;
+	}
+
+	return link->hpd_status;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
index a7aa8c9da868..5491b707cec8 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
@@ -54,12 +54,18 @@ static bool get_bw_alloc_proceed_flag(struct dc_link *tmp)
 static void reset_bw_alloc_struct(struct dc_link *link)
 {
 	link->dpia_bw_alloc_config.bw_alloc_enabled = false;
-	link->dpia_bw_alloc_config.sink_verified_bw = 0;
-	link->dpia_bw_alloc_config.sink_max_bw = 0;
+	link->dpia_bw_alloc_config.link_verified_bw = 0;
+	link->dpia_bw_alloc_config.link_max_bw = 0;
+	link->dpia_bw_alloc_config.allocated_bw = 0;
 	link->dpia_bw_alloc_config.estimated_bw = 0;
 	link->dpia_bw_alloc_config.bw_granularity = 0;
+	link->dpia_bw_alloc_config.dp_overhead = 0;
 	link->dpia_bw_alloc_config.response_ready = false;
-	link->dpia_bw_alloc_config.sink_allocated_bw = 0;
+	link->dpia_bw_alloc_config.nrd_max_lane_count = 0;
+	link->dpia_bw_alloc_config.nrd_max_link_rate = 0;
+	for (int i = 0; i < MAX_SINKS_PER_LINK; i++)
+		link->dpia_bw_alloc_config.remote_sink_req_bw[i] = 0;
+	DC_LOG_DEBUG("reset usb4 bw alloc of link(%d)\n", link->link_index);
 }
 
 #define BW_GRANULARITY_0 4 // 0.25 Gbps
@@ -190,7 +196,7 @@ static int get_host_router_total_dp_tunnel_bw(const struct dc *dc, uint8_t hr_in
 	struct dc_link *link_dpia_primary, *link_dpia_secondary;
 	int total_bw = 0;
 
-	for (uint8_t i = 0; i < MAX_PIPES * 2; ++i) {
+	for (uint8_t i = 0; i < (MAX_PIPES * 2) - 1; ++i) {
 
 		if (!dc->links[i] || dc->links[i]->ep_type != DISPLAY_ENDPOINT_USB4_DPIA)
 			continue;
@@ -210,8 +216,8 @@ static int get_host_router_total_dp_tunnel_bw(const struct dc *dc, uint8_t hr_in
 				link_dpia_primary->dpia_bw_alloc_config.bw_alloc_enabled) &&
 				(link_dpia_secondary->hpd_status &&
 				link_dpia_secondary->dpia_bw_alloc_config.bw_alloc_enabled)) {
-				total_bw += link_dpia_primary->dpia_bw_alloc_config.estimated_bw +
-					link_dpia_secondary->dpia_bw_alloc_config.sink_allocated_bw;
+					total_bw += link_dpia_primary->dpia_bw_alloc_config.estimated_bw +
+						link_dpia_secondary->dpia_bw_alloc_config.allocated_bw;
 			} else if (link_dpia_primary->hpd_status &&
 					link_dpia_primary->dpia_bw_alloc_config.bw_alloc_enabled) {
 				total_bw = link_dpia_primary->dpia_bw_alloc_config.estimated_bw;
@@ -264,7 +270,7 @@ static void set_usb4_req_bw_req(struct dc_link *link, int req_bw)
 
 	/* Error check whether requested and allocated are equal */
 	req_bw = requested_bw * (Kbps_TO_Gbps / link->dpia_bw_alloc_config.bw_granularity);
-	if (req_bw == link->dpia_bw_alloc_config.sink_allocated_bw) {
+	if (req_bw == link->dpia_bw_alloc_config.allocated_bw) {
 		DC_LOG_ERROR("%s: Request bw equals to allocated bw for link(%d)\n",
 			__func__, link->link_index);
 	}
@@ -387,9 +393,9 @@ void dpia_handle_bw_alloc_response(struct dc_link *link, uint8_t bw, uint8_t res
 		DC_LOG_DEBUG("%s: BW REQ SUCCESS for DP-TX Request for link(%d)\n",
 			__func__, link->link_index);
 		DC_LOG_DEBUG("%s: current allocated_bw(%d), new allocated_bw(%d)\n",
-			__func__, link->dpia_bw_alloc_config.sink_allocated_bw, bw_needed);
+			__func__, link->dpia_bw_alloc_config.allocated_bw, bw_needed);
 
-		link->dpia_bw_alloc_config.sink_allocated_bw = bw_needed;
+		link->dpia_bw_alloc_config.allocated_bw = bw_needed;
 
 		link->dpia_bw_alloc_config.response_ready = true;
 		break;
@@ -427,8 +433,8 @@ int dpia_handle_usb4_bandwidth_allocation_for_link(struct dc_link *link, int pea
 	if (link->hpd_status && peak_bw > 0) {
 
 		// If DP over USB4 then we need to check BW allocation
-		link->dpia_bw_alloc_config.sink_max_bw = peak_bw;
-		set_usb4_req_bw_req(link, link->dpia_bw_alloc_config.sink_max_bw);
+		link->dpia_bw_alloc_config.link_max_bw = peak_bw;
+		set_usb4_req_bw_req(link, link->dpia_bw_alloc_config.link_max_bw);
 
 		do {
 			if (timeout > 0)
@@ -440,8 +446,8 @@ int dpia_handle_usb4_bandwidth_allocation_for_link(struct dc_link *link, int pea
 
 		if (!timeout)
 			ret = 0;// ERROR TIMEOUT waiting for response for allocating bw
-		else if (link->dpia_bw_alloc_config.sink_allocated_bw > 0)
-			ret = link->dpia_bw_alloc_config.sink_allocated_bw;
+		else if (link->dpia_bw_alloc_config.allocated_bw > 0)
+			ret = link->dpia_bw_alloc_config.allocated_bw;
 	}
 	//2. Cold Unplug
 	else if (!link->hpd_status)
@@ -450,7 +456,6 @@ int dpia_handle_usb4_bandwidth_allocation_for_link(struct dc_link *link, int pea
 out:
 	return ret;
 }
-
 bool link_dp_dpia_allocate_usb4_bandwidth_for_stream(struct dc_link *link, int req_bw)
 {
 	bool ret = false;
@@ -458,7 +463,7 @@ bool link_dp_dpia_allocate_usb4_bandwidth_for_stream(struct dc_link *link, int r
 
 	DC_LOG_DEBUG("%s: ENTER: link(%d), hpd_status(%d), current allocated_bw(%d), req_bw(%d)\n",
 		__func__, link->link_index, link->hpd_status,
-		link->dpia_bw_alloc_config.sink_allocated_bw, req_bw);
+		link->dpia_bw_alloc_config.allocated_bw, req_bw);
 
 	if (!get_bw_alloc_proceed_flag(link))
 		goto out;
@@ -523,3 +528,30 @@ bool dpia_validate_usb4_bw(struct dc_link **link, int *bw_needed_per_dpia, const
 
 	return ret;
 }
+
+int link_dp_dpia_get_dp_overhead_in_dp_tunneling(struct dc_link *link)
+{
+	int dp_overhead = 0, link_mst_overhead = 0;
+
+	if (!get_bw_alloc_proceed_flag((link)))
+		return dp_overhead;
+
+	/* if its mst link, add MTPH overhead */
+	if ((link->type == dc_connection_mst_branch) &&
+		!link->dpcd_caps.channel_coding_cap.bits.DP_128b_132b_SUPPORTED) {
+		/* For 8b/10b encoding: MTP is 64 time slots long, slot 0 is used for MTPH
+		 * MST overhead is 1/64 of link bandwidth (excluding any overhead)
+		 */
+		const struct dc_link_settings *link_cap =
+			dc_link_get_link_cap(link);
+		uint32_t link_bw_in_kbps = (uint32_t)link_cap->link_rate *
+					   (uint32_t)link_cap->lane_count *
+					   LINK_RATE_REF_FREQ_IN_KHZ * 8;
+		link_mst_overhead = (link_bw_in_kbps / 64) + ((link_bw_in_kbps % 64) ? 1 : 0);
+	}
+
+	/* add all the overheads */
+	dp_overhead = link_mst_overhead;
+
+	return dp_overhead;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h
index 981bc4eb6120..3b6d8494f9d5 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h
@@ -99,4 +99,13 @@ void dpia_handle_bw_alloc_response(struct dc_link *link, uint8_t bw, uint8_t res
  */
 bool dpia_validate_usb4_bw(struct dc_link **link, int *bw_needed, const unsigned int num_dpias);
 
+/*
+ * Obtain all the DP overheads in dp tunneling for the dpia link
+ *
+ * @link: pointer to the dc_link struct instance
+ *
+ * return: DP overheads in DP tunneling
+ */
+int link_dp_dpia_get_dp_overhead_in_dp_tunneling(struct dc_link *link);
+
 #endif /* DC_INC_LINK_DP_DPIA_BW_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
index 5a0b04518956..16a62e018712 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
@@ -517,6 +517,7 @@ enum link_training_result dp_check_link_loss_status(
 {
 	enum link_training_result status = LINK_TRAINING_SUCCESS;
 	union lane_status lane_status;
+	union lane_align_status_updated dpcd_lane_status_updated;
 	uint8_t dpcd_buf[6] = {0};
 	uint32_t lane;
 
@@ -532,10 +533,12 @@ enum link_training_result dp_check_link_loss_status(
 		 * check lanes status
 		 */
 		lane_status.raw = dp_get_nibble_at_index(&dpcd_buf[2], lane);
+		dpcd_lane_status_updated.raw = dpcd_buf[4];
 
 		if (!lane_status.bits.CHANNEL_EQ_DONE_0 ||
 			!lane_status.bits.CR_DONE_0 ||
-			!lane_status.bits.SYMBOL_LOCKED_0) {
+			!lane_status.bits.SYMBOL_LOCKED_0 ||
+			!dp_is_interlane_aligned(dpcd_lane_status_updated)) {
 			/* if one of the channel equalization, clock
 			 * recovery or symbol lock is dropped
 			 * consider it as (link has been
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c
index e8dda44b23cb..5d36bab0029c 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c
@@ -619,7 +619,7 @@ static enum link_training_result dpia_training_eq_non_transparent(
 	uint32_t retries_eq = 0;
 	enum dc_status status;
 	enum dc_dp_training_pattern tr_pattern;
-	uint32_t wait_time_microsec;
+	uint32_t wait_time_microsec = 0;
 	enum dc_lane_count lane_count = lt_settings->link_settings.lane_count;
 	union lane_align_status_updated dpcd_lane_status_updated = {0};
 	union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = {0};
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c
index 5c9a30211c10..fc50931c2aec 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c
@@ -205,7 +205,7 @@ enum dc_status core_link_read_dpcd(
 	uint32_t extended_size;
 	/* size of the remaining partitioned address space */
 	uint32_t size_left_to_read;
-	enum dc_status status;
+	enum dc_status status = DC_ERROR_UNEXPECTED;
 	/* size of the next partition to be read from */
 	uint32_t partition_size;
 	uint32_t data_index = 0;
@@ -234,7 +234,7 @@ enum dc_status core_link_write_dpcd(
 {
 	uint32_t partition_size;
 	uint32_t data_index = 0;
-	enum dc_status status;
+	enum dc_status status = DC_ERROR_UNEXPECTED;
 
 	while (size) {
 		partition_size = dpcd_get_next_partition_size(address, size);
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
index 7f1196528218..046d3e205415 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
@@ -930,8 +930,8 @@ bool edp_get_replay_state(const struct dc_link *link, uint64_t *state)
 bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream)
 {
 	/* To-do: Setup Replay */
-	struct dc *dc = link->ctx->dc;
-	struct dmub_replay *replay = dc->res_pool->replay;
+	struct dc *dc;
+	struct dmub_replay *replay;
 	int i;
 	unsigned int panel_inst;
 	struct replay_context replay_context = { 0 };
@@ -947,6 +947,10 @@ bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream
 	if (!link)
 		return false;
 
+	dc = link->ctx->dc;
+
+	replay = dc->res_pool->replay;
+
 	if (!replay)
 		return false;
 
@@ -975,8 +979,7 @@ bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream
 
 	replay_context.line_time_in_ns = lineTimeInNs;
 
-	if (replay)
-		link->replay_settings.replay_feature_enabled =
+	link->replay_settings.replay_feature_enabled =
 			replay->funcs->replay_copy_settings(replay, link, &replay_context, panel_inst);
 	if (link->replay_settings.replay_feature_enabled) {
 
diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c
index 91ea0d4da06a..823493543325 100644
--- a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c
@@ -166,12 +166,6 @@ static bool optc32_disable_crtc(struct timing_generator *optc)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
-	/* disable otg request until end of the first line
-	 * in the vertical blank region
-	 */
-	REG_UPDATE(OTG_CONTROL,
-			OTG_MASTER_EN, 0);
-
 	REG_UPDATE_5(OPTC_DATA_SOURCE_SELECT,
 			OPTC_SEG0_SRC_SEL, 0xf,
 			OPTC_SEG1_SRC_SEL, 0xf,
@@ -179,6 +173,15 @@ static bool optc32_disable_crtc(struct timing_generator *optc)
 			OPTC_SEG3_SRC_SEL, 0xf,
 			OPTC_NUM_OF_INPUT_SEGMENT, 0);
 
+	REG_UPDATE(OPTC_MEMORY_CONFIG,
+			OPTC_MEM_SEL, 0);
+
+	/* disable otg request until end of the first line
+	 * in the vertical blank region
+	 */
+	REG_UPDATE(OTG_CONTROL,
+			OTG_MASTER_EN, 0);
+
 	REG_UPDATE(CONTROL,
 			VTG0_ENABLE, 0);
 
@@ -205,6 +208,13 @@ static void optc32_disable_phantom_otg(struct timing_generator *optc)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
+	REG_UPDATE_5(OPTC_DATA_SOURCE_SELECT,
+			OPTC_SEG0_SRC_SEL, 0xf,
+			OPTC_SEG1_SRC_SEL, 0xf,
+			OPTC_SEG2_SRC_SEL, 0xf,
+			OPTC_SEG3_SRC_SEL, 0xf,
+			OPTC_NUM_OF_INPUT_SEGMENT, 0);
+
 	REG_UPDATE(OTG_CONTROL, OTG_MASTER_EN, 0);
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c
index 08a59cf449ca..5b1547508850 100644
--- a/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c
@@ -138,12 +138,6 @@ static bool optc35_disable_crtc(struct timing_generator *optc)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
-	/* disable otg request until end of the first line
-	 * in the vertical blank region
-	 */
-	REG_UPDATE(OTG_CONTROL,
-			OTG_MASTER_EN, 0);
-
 	REG_UPDATE_5(OPTC_DATA_SOURCE_SELECT,
 			OPTC_SEG0_SRC_SEL, 0xf,
 			OPTC_SEG1_SRC_SEL, 0xf,
@@ -151,6 +145,15 @@ static bool optc35_disable_crtc(struct timing_generator *optc)
 			OPTC_SEG3_SRC_SEL, 0xf,
 			OPTC_NUM_OF_INPUT_SEGMENT, 0);
 
+	REG_UPDATE(OPTC_MEMORY_CONFIG,
+			OPTC_MEM_SEL, 0);
+
+	/* disable otg request until end of the first line
+	 * in the vertical blank region
+	 */
+	REG_UPDATE(OTG_CONTROL,
+			OTG_MASTER_EN, 0);
+
 	REG_UPDATE(CONTROL,
 			VTG0_ENABLE, 0);
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
index 511ff6b5b985..7538b548c572 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
@@ -999,7 +999,7 @@ static struct stream_encoder *dcn301_stream_encoder_create(enum engine_id eng_id
 	vpg = dcn301_vpg_create(ctx, vpg_inst);
 	afmt = dcn301_afmt_create(ctx, afmt_inst);
 
-	if (!enc1 || !vpg || !afmt) {
+	if (!enc1 || !vpg || !afmt || eng_id >= ARRAY_SIZE(stream_enc_regs)) {
 		kfree(enc1);
 		kfree(vpg);
 		kfree(afmt);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
index ac04a9c9a3d8..6f10052caeef 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
@@ -1829,7 +1829,21 @@ int dcn32_populate_dml_pipes_from_context(
 		dcn32_zero_pipe_dcc_fraction(pipes, pipe_cnt);
 		DC_FP_END();
 		pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch;
-		pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+		if (dc->config.enable_windowed_mpo_odm &&
+				dc->debug.enable_single_display_2to1_odm_policy) {
+			switch (resource_get_odm_slice_count(pipe)) {
+			case 2:
+				pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1;
+				break;
+			case 4:
+				pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_4to1;
+				break;
+			default:
+				pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+			}
+		} else {
+			pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+		}
 		pipes[pipe_cnt].pipe.src.gpuvm_min_page_size_kbytes = 256; // according to spreadsheet
 		pipes[pipe_cnt].pipe.src.unbounded_req_mode = false;
 		pipes[pipe_cnt].pipe.scale_ratio_depth.lb_depth = dm_lb_19;
@@ -1899,7 +1913,7 @@ int dcn32_populate_dml_pipes_from_context(
 
 static struct dc_cap_funcs cap_funcs = {
 	.get_dcc_compression_cap = dcn20_get_dcc_compression_cap,
-	.get_subvp_en = resource_subvp_in_use,
+	.get_subvp_en = dcn32_subvp_in_use,
 };
 
 void dcn32_calculate_wm_and_dlg(struct dc *dc, struct dc_state *context,
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
index 62611acd4bcb..0c87b0fabba7 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
@@ -131,6 +131,9 @@ void dcn32_merge_pipes_for_subvp(struct dc *dc,
 bool dcn32_all_pipes_have_stream_and_plane(struct dc *dc,
 		struct dc_state *context);
 
+bool dcn32_subvp_in_use(struct dc *dc,
+		struct dc_state *context);
+
 bool dcn32_mpo_in_use(struct dc_state *context);
 
 bool dcn32_any_surfaces_rotated(struct dc *dc, struct dc_state *context);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
index e1ab207c46f1..74412e5f03fe 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
@@ -1574,7 +1574,7 @@ static void dcn321_destroy_resource_pool(struct resource_pool **pool)
 
 static struct dc_cap_funcs cap_funcs = {
 	.get_dcc_compression_cap = dcn20_get_dcc_compression_cap,
-	.get_subvp_en = resource_subvp_in_use,
+	.get_subvp_en = dcn32_subvp_in_use,
 };
 
 static void dcn321_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params)
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
index 761ec9891875..5fdcda8f8602 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
@@ -780,8 +780,8 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.disable_z10 = false,
 	.ignore_pg = true,
 	.psp_disabled_wa = true,
-	.ips2_eval_delay_us = 200,
-	.ips2_entry_delay_us = 400,
+	.ips2_eval_delay_us = 2000,
+	.ips2_entry_delay_us = 800,
 	.static_screen_wait_frames = 2,
 };
 
@@ -2130,6 +2130,7 @@ static bool dcn35_resource_construct(
 	dc->dml2_options.dcn_pipe_count = pool->base.pipe_count;
 	dc->dml2_options.use_native_pstate_optimization = true;
 	dc->dml2_options.use_native_soc_bb_construction = true;
+	dc->dml2_options.minimize_dispclk_using_odm = false;
 	if (dc->config.EnableMinDispClkODM)
 		dc->dml2_options.minimize_dispclk_using_odm = true;
 	dc->dml2_options.enable_windowed_mpo_odm = dc->config.enable_windowed_mpo_odm;
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index c64b6c848ef7..e699731ee68e 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -2832,6 +2832,7 @@ struct dmub_rb_cmd_psr_set_power_opt {
 #define REPLAY_RESIDENCY_MODE_MASK             (0x1 << REPLAY_RESIDENCY_MODE_SHIFT)
 # define REPLAY_RESIDENCY_MODE_PHY             (0x0 << REPLAY_RESIDENCY_MODE_SHIFT)
 # define REPLAY_RESIDENCY_MODE_ALPM            (0x1 << REPLAY_RESIDENCY_MODE_SHIFT)
+# define REPLAY_RESIDENCY_MODE_IPS             0x10
 
 #define REPLAY_RESIDENCY_ENABLE_MASK           (0x1 << REPLAY_RESIDENCY_ENABLE_SHIFT)
 # define REPLAY_RESIDENCY_DISABLE              (0x0 << REPLAY_RESIDENCY_ENABLE_SHIFT)
@@ -2894,6 +2895,10 @@ enum dmub_cmd_replay_type {
 	 * Set Residency Frameupdate Timer.
 	 */
 	DMUB_CMD__REPLAY_SET_RESIDENCY_FRAMEUPDATE_TIMER = 6,
+	/**
+	 * Set pseudo vtotal
+	 */
+	DMUB_CMD__REPLAY_SET_PSEUDO_VTOTAL = 7,
 };
 
 /**
@@ -3077,6 +3082,26 @@ struct dmub_cmd_replay_set_timing_sync_data {
 };
 
 /**
+ * Data passed from driver to FW in a DMUB_CMD__REPLAY_SET_PSEUDO_VTOTAL command.
+ */
+struct dmub_cmd_replay_set_pseudo_vtotal {
+	/**
+	 * Panel Instance.
+	 * Panel isntance to identify which replay_state to use
+	 * Currently the support is only for 0 or 1
+	 */
+	uint8_t panel_inst;
+	/**
+	 * Source Vtotal that Replay + IPS + ABM full screen video src vtotal
+	 */
+	uint16_t vtotal;
+	/**
+	 * Explicit padding to 4 byte boundary.
+	 */
+	uint8_t pad;
+};
+
+/**
  * Definition of a DMUB_CMD__SET_REPLAY_POWER_OPT command.
  */
 struct dmub_rb_cmd_replay_set_power_opt {
@@ -3157,6 +3182,20 @@ struct dmub_rb_cmd_replay_set_timing_sync {
 };
 
 /**
+ * Definition of a DMUB_CMD__REPLAY_SET_PSEUDO_VTOTAL command.
+ */
+struct dmub_rb_cmd_replay_set_pseudo_vtotal {
+	/**
+	 * Command header.
+	 */
+	struct dmub_cmd_header header;
+	/**
+	 * Definition of DMUB_CMD__REPLAY_SET_PSEUDO_VTOTAL command.
+	 */
+	struct dmub_cmd_replay_set_pseudo_vtotal data;
+};
+
+/**
  * Data passed from driver to FW in  DMUB_CMD__REPLAY_SET_RESIDENCY_FRAMEUPDATE_TIMER command.
  */
 struct dmub_cmd_replay_frameupdate_timer_data {
@@ -3207,6 +3246,10 @@ union dmub_replay_cmd_set {
 	 * Definition of DMUB_CMD__REPLAY_SET_RESIDENCY_FRAMEUPDATE_TIMER command data.
 	 */
 	struct dmub_cmd_replay_frameupdate_timer_data timer_data;
+	/**
+	 * Definition of DMUB_CMD__REPLAY_SET_PSEUDO_VTOTAL command data.
+	 */
+	struct dmub_cmd_replay_set_pseudo_vtotal pseudo_vtotal_data;
 };
 
 /**
@@ -4358,6 +4401,10 @@ union dmub_rb_cmd {
 	 * Definition of a DMUB_CMD__REPLAY_SET_RESIDENCY_FRAMEUPDATE_TIMER command.
 	 */
 	struct dmub_rb_cmd_replay_set_frameupdate_timer replay_set_frameupdate_timer;
+	/**
+	 * Definition of a DMUB_CMD__REPLAY_SET_PSEUDO_VTOTAL command.
+	 */
+	struct dmub_rb_cmd_replay_set_pseudo_vtotal replay_set_pseudo_vtotal;
 };
 
 /**
diff --git a/drivers/gpu/drm/amd/display/include/audio_types.h b/drivers/gpu/drm/amd/display/include/audio_types.h
index 66a54da0641c..915a031a43cb 100644
--- a/drivers/gpu/drm/amd/display/include/audio_types.h
+++ b/drivers/gpu/drm/amd/display/include/audio_types.h
@@ -64,7 +64,7 @@ enum audio_dto_source {
 /* PLL information required for AZALIA DTO calculation */
 
 struct audio_pll_info {
-	uint32_t dp_dto_source_clock_in_khz;
+	uint32_t audio_dto_source_clock_in_khz;
 	uint32_t feed_back_divider;
 	enum audio_dto_source dto_source;
 	bool ss_enabled;
diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
index ad98e504c00d..e304e8435fb8 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
@@ -980,6 +980,11 @@ void set_replay_coasting_vtotal(struct dc_link *link,
 	link->replay_settings.coasting_vtotal_table[type] = vtotal;
 }
 
+void set_replay_ips_full_screen_video_src_vtotal(struct dc_link *link, uint16_t vtotal)
+{
+	link->replay_settings.abm_with_ips_on_full_screen_video_pseudo_vtotal = vtotal;
+}
+
 void calculate_replay_link_off_frame_count(struct dc_link *link,
 	uint16_t vtotal, uint16_t htotal)
 {
diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
index c17bbc6fb38c..bef4815e1703 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
@@ -57,6 +57,7 @@ void init_replay_config(struct dc_link *link, struct replay_config *pr_config);
 void set_replay_coasting_vtotal(struct dc_link *link,
 	enum replay_coasting_vtotal_type type,
 	uint16_t vtotal);
+void set_replay_ips_full_screen_video_src_vtotal(struct dc_link *link, uint16_t vtotal);
 void calculate_replay_link_off_frame_count(struct dc_link *link,
 	uint16_t vtotal, uint16_t htotal);
 
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index 1dc5dd9b7bf7..df2c7ffe190f 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -258,6 +258,7 @@ enum DC_DEBUG_MASK {
 	DC_ENABLE_DML2 = 0x100,
 	DC_DISABLE_PSR_SU = 0x200,
 	DC_DISABLE_REPLAY = 0x400,
+	DC_DISABLE_IPS = 0x800,
 };
 
 enum amd_dpm_forced_level;
diff --git a/drivers/gpu/drm/amd/include/amdgpu_reg_state.h b/drivers/gpu/drm/amd/include/amdgpu_reg_state.h
index be519c8edf49..335980e2afbf 100644
--- a/drivers/gpu/drm/amd/include/amdgpu_reg_state.h
+++ b/drivers/gpu/drm/amd/include/amdgpu_reg_state.h
@@ -138,7 +138,7 @@ static inline size_t amdgpu_reginst_size(uint16_t num_inst, size_t inst_size,
 }
 
 #define amdgpu_asic_get_reg_state_supported(adev) \
-	((adev)->asic_funcs->get_reg_state ? 1 : 0)
+	(((adev)->asic_funcs && (adev)->asic_funcs->get_reg_state) ? 1 : 0)
 
 #define amdgpu_asic_get_reg_state(adev, state, buf, size)                  \
 	((adev)->asic_funcs->get_reg_state ?                               \
diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
index 7ee3d291120d..6f80bfa7e41a 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
@@ -8707,10 +8707,10 @@
 #define regBIF_BX1_MM_CFGREGS_CNTL_BASE_IDX                                                             2
 #define regBIF_BX1_BX_RESET_CNTL                                                                        0x00f0
 #define regBIF_BX1_BX_RESET_CNTL_BASE_IDX                                                               2
-#define regBIF_BX1_INTERRUPT_CNTL                                                                       0x8e11
-#define regBIF_BX1_INTERRUPT_CNTL_BASE_IDX                                                              5
-#define regBIF_BX1_INTERRUPT_CNTL2                                                                      0x8e12
-#define regBIF_BX1_INTERRUPT_CNTL2_BASE_IDX                                                             5
+#define regBIF_BX1_INTERRUPT_CNTL                                                                       0x00f1
+#define regBIF_BX1_INTERRUPT_CNTL_BASE_IDX                                                              2
+#define regBIF_BX1_INTERRUPT_CNTL2                                                                      0x00f2
+#define regBIF_BX1_INTERRUPT_CNTL2_BASE_IDX                                                             2
 #define regBIF_BX1_CLKREQB_PAD_CNTL                                                                     0x00f8
 #define regBIF_BX1_CLKREQB_PAD_CNTL_BASE_IDX                                                            2
 #define regBIF_BX1_BIF_FEATURES_CONTROL_MISC                                                            0x00fb
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index f3cb490fe79b..39c5e1dfa275 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -2558,6 +2558,7 @@ static ssize_t amdgpu_hwmon_set_pwm1_enable(struct device *dev,
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
 	int err, ret;
+	u32 pwm_mode;
 	int value;
 
 	if (amdgpu_in_reset(adev))
@@ -2569,13 +2570,22 @@ static ssize_t amdgpu_hwmon_set_pwm1_enable(struct device *dev,
 	if (err)
 		return err;
 
+	if (value == 0)
+		pwm_mode = AMD_FAN_CTRL_NONE;
+	else if (value == 1)
+		pwm_mode = AMD_FAN_CTRL_MANUAL;
+	else if (value == 2)
+		pwm_mode = AMD_FAN_CTRL_AUTO;
+	else
+		return -EINVAL;
+
 	ret = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (ret < 0) {
 		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return ret;
 	}
 
-	ret = amdgpu_dpm_set_fan_control_mode(adev, value);
+	ret = amdgpu_dpm_set_fan_control_mode(adev, pwm_mode);
 
 	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
 	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
@@ -4349,11 +4359,19 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a
 	if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VDDNB, (void *)&value, &size))
 		seq_printf(m, "\t%u mV (VDDNB)\n", value);
 	size = sizeof(uint32_t);
-	if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_AVG_POWER, (void *)&query, &size))
-		seq_printf(m, "\t%u.%02u W (average GPU)\n", query >> 8, query & 0xff);
+	if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_AVG_POWER, (void *)&query, &size)) {
+		if (adev->flags & AMD_IS_APU)
+			seq_printf(m, "\t%u.%02u W (average SoC including CPU)\n", query >> 8, query & 0xff);
+		else
+			seq_printf(m, "\t%u.%02u W (average SoC)\n", query >> 8, query & 0xff);
+	}
 	size = sizeof(uint32_t);
-	if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_INPUT_POWER, (void *)&query, &size))
-		seq_printf(m, "\t%u.%02u W (current GPU)\n", query >> 8, query & 0xff);
+	if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_INPUT_POWER, (void *)&query, &size)) {
+		if (adev->flags & AMD_IS_APU)
+			seq_printf(m, "\t%u.%02u W (current SoC including CPU)\n", query >> 8, query & 0xff);
+		else
+			seq_printf(m, "\t%u.%02u W (current SoC)\n", query >> 8, query & 0xff);
+	}
 	size = sizeof(value);
 	seq_printf(m, "\n");
 
@@ -4379,9 +4397,9 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a
 		/* VCN clocks */
 		if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCN_POWER_STATE, (void *)&value, &size)) {
 			if (!value) {
-				seq_printf(m, "VCN: Disabled\n");
+				seq_printf(m, "VCN: Powered down\n");
 			} else {
-				seq_printf(m, "VCN: Enabled\n");
+				seq_printf(m, "VCN: Powered up\n");
 				if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_DCLK, (void *)&value, &size))
 					seq_printf(m, "\t%u MHz (DCLK)\n", value/100);
 				if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_VCLK, (void *)&value, &size))
@@ -4393,9 +4411,9 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a
 		/* UVD clocks */
 		if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_POWER, (void *)&value, &size)) {
 			if (!value) {
-				seq_printf(m, "UVD: Disabled\n");
+				seq_printf(m, "UVD: Powered down\n");
 			} else {
-				seq_printf(m, "UVD: Enabled\n");
+				seq_printf(m, "UVD: Powered up\n");
 				if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_DCLK, (void *)&value, &size))
 					seq_printf(m, "\t%u MHz (DCLK)\n", value/100);
 				if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_VCLK, (void *)&value, &size))
@@ -4407,9 +4425,9 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a
 		/* VCE clocks */
 		if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCE_POWER, (void *)&value, &size)) {
 			if (!value) {
-				seq_printf(m, "VCE: Disabled\n");
+				seq_printf(m, "VCE: Powered down\n");
 			} else {
-				seq_printf(m, "VCE: Enabled\n");
+				seq_printf(m, "VCE: Powered up\n");
 				if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCE_ECCLK, (void *)&value, &size))
 					seq_printf(m, "\t%u MHz (ECCLK)\n", value/100);
 			}
diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
index df4f20293c16..eb4da3666e05 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
@@ -6925,6 +6925,23 @@ static int si_dpm_enable(struct amdgpu_device *adev)
 	return 0;
 }
 
+static int si_set_temperature_range(struct amdgpu_device *adev)
+{
+	int ret;
+
+	ret = si_thermal_enable_alert(adev, false);
+	if (ret)
+		return ret;
+	ret = si_thermal_set_temperature_range(adev, R600_TEMP_RANGE_MIN, R600_TEMP_RANGE_MAX);
+	if (ret)
+		return ret;
+	ret = si_thermal_enable_alert(adev, true);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+
 static void si_dpm_disable(struct amdgpu_device *adev)
 {
 	struct rv7xx_power_info *pi = rv770_get_pi(adev);
@@ -7608,6 +7625,18 @@ static int si_dpm_process_interrupt(struct amdgpu_device *adev,
 
 static int si_dpm_late_init(void *handle)
 {
+	int ret;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	if (!adev->pm.dpm_enabled)
+		return 0;
+
+	ret = si_set_temperature_range(adev);
+	if (ret)
+		return ret;
+#if 0 //TODO ?
+	si_dpm_powergate_uvd(adev, true);
+#endif
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c
index f2a55c1413f5..17882f8dfdd3 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c
@@ -200,7 +200,7 @@ static int get_platform_power_management_table(
 		struct pp_hwmgr *hwmgr,
 		ATOM_Tonga_PPM_Table *atom_ppm_table)
 {
-	struct phm_ppm_table *ptr = kzalloc(sizeof(ATOM_Tonga_PPM_Table), GFP_KERNEL);
+	struct phm_ppm_table *ptr = kzalloc(sizeof(*ptr), GFP_KERNEL);
 	struct phm_ppt_v1_information *pp_table_information =
 		(struct phm_ppt_v1_information *)(hwmgr->pptable);
 
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
index b1a8799e2dee..aa91730e4eaf 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
@@ -3999,6 +3999,7 @@ static int smu7_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 	uint32_t sclk, mclk, activity_percent;
 	uint32_t offset, val_vid;
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct amdgpu_device *adev = hwmgr->adev;
 
 	/* size must be at least 4 bytes for all sensors */
 	if (*size < 4)
@@ -4042,7 +4043,21 @@ static int smu7_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 		*size = 4;
 		return 0;
 	case AMDGPU_PP_SENSOR_GPU_INPUT_POWER:
-		return smu7_get_gpu_power(hwmgr, (uint32_t *)value);
+		if ((adev->asic_type != CHIP_HAWAII) &&
+		    (adev->asic_type != CHIP_BONAIRE) &&
+		    (adev->asic_type != CHIP_FIJI) &&
+		    (adev->asic_type != CHIP_TONGA))
+			return smu7_get_gpu_power(hwmgr, (uint32_t *)value);
+		else
+			return -EOPNOTSUPP;
+	case AMDGPU_PP_SENSOR_GPU_AVG_POWER:
+		if ((adev->asic_type != CHIP_HAWAII) &&
+		    (adev->asic_type != CHIP_BONAIRE) &&
+		    (adev->asic_type != CHIP_FIJI) &&
+		    (adev->asic_type != CHIP_TONGA))
+			return -EOPNOTSUPP;
+		else
+			return smu7_get_gpu_power(hwmgr, (uint32_t *)value);
 	case AMDGPU_PP_SENSOR_VDDGFX:
 		if ((data->vr_config & VRCONF_VDDGFX_MASK) ==
 		    (VR_SVI2_PLANE_2 << VRCONF_VDDGFX_SHIFT))
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index c16703868e5c..0ad947df777a 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -24,6 +24,7 @@
 
 #include <linux/firmware.h>
 #include <linux/pci.h>
+#include <linux/power_supply.h>
 #include <linux/reboot.h>
 
 #include "amdgpu.h"
@@ -733,7 +734,7 @@ static int smu_early_init(void *handle)
 	smu->adev = adev;
 	smu->pm_enabled = !!amdgpu_dpm;
 	smu->is_apu = false;
-	smu->smu_baco.state = SMU_BACO_STATE_NONE;
+	smu->smu_baco.state = SMU_BACO_STATE_EXIT;
 	smu->smu_baco.platform_support = false;
 	smu->user_dpm_profile.fan_mode = -1;
 
@@ -817,16 +818,8 @@ static int smu_late_init(void *handle)
 	 * handle the switch automatically. Driver involvement
 	 * is unnecessary.
 	 */
-	if (!smu->dc_controlled_by_gpio) {
-		ret = smu_set_power_source(smu,
-					   adev->pm.ac_power ? SMU_POWER_SOURCE_AC :
-					   SMU_POWER_SOURCE_DC);
-		if (ret) {
-			dev_err(adev->dev, "Failed to switch to %s mode!\n",
-				adev->pm.ac_power ? "AC" : "DC");
-			return ret;
-		}
-	}
+	adev->pm.ac_power = power_supply_is_system_supplied() > 0;
+	smu_set_ac_dc(smu);
 
 	if ((amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 1)) ||
 	    (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 3)))
@@ -1961,31 +1954,10 @@ static int smu_smc_hw_cleanup(struct smu_context *smu)
 	return 0;
 }
 
-static int smu_reset_mp1_state(struct smu_context *smu)
-{
-	struct amdgpu_device *adev = smu->adev;
-	int ret = 0;
-
-	if ((!adev->in_runpm) && (!adev->in_suspend) &&
-		(!amdgpu_in_reset(adev)))
-		switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
-		case IP_VERSION(13, 0, 0):
-		case IP_VERSION(13, 0, 7):
-		case IP_VERSION(13, 0, 10):
-			ret = smu_set_mp1_state(smu, PP_MP1_STATE_UNLOAD);
-			break;
-		default:
-			break;
-		}
-
-	return ret;
-}
-
 static int smu_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct smu_context *smu = adev->powerplay.pp_handle;
-	int ret;
 
 	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
 		return 0;
@@ -2003,15 +1975,7 @@ static int smu_hw_fini(void *handle)
 
 	adev->pm.dpm_enabled = false;
 
-	ret = smu_smc_hw_cleanup(smu);
-	if (ret)
-		return ret;
-
-	ret = smu_reset_mp1_state(smu);
-	if (ret)
-		return ret;
-
-	return 0;
+	return smu_smc_hw_cleanup(smu);
 }
 
 static void smu_late_fini(void *handle)
@@ -2710,6 +2674,7 @@ int smu_get_power_limit(void *handle,
 		case SMU_PPT_LIMIT_CURRENT:
 			switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
 			case IP_VERSION(13, 0, 2):
+			case IP_VERSION(13, 0, 6):
 			case IP_VERSION(11, 0, 7):
 			case IP_VERSION(11, 0, 11):
 			case IP_VERSION(11, 0, 12):
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index 2aa4fea87314..66e84defd0b6 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -424,7 +424,6 @@ enum smu_reset_mode {
 enum smu_baco_state {
 	SMU_BACO_STATE_ENTER = 0,
 	SMU_BACO_STATE_EXIT,
-	SMU_BACO_STATE_NONE,
 };
 
 struct smu_baco_context {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
index 4cd43bbec910..bcad42534da4 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -1303,13 +1303,12 @@ static int arcturus_get_power_limit(struct smu_context *smu,
 	if (default_power_limit)
 		*default_power_limit = power_limit;
 
-	if (smu->od_enabled) {
+	if (smu->od_enabled)
 		od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
-		od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
-	} else {
+	else
 		od_percent_upper = 0;
-		od_percent_lower = 100;
-	}
+
+	od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
 
 	dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
 							od_percent_upper, od_percent_lower, power_limit);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index 8d1d29ffb0f1..ed189a3878eb 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -2357,13 +2357,12 @@ static int navi10_get_power_limit(struct smu_context *smu,
 		*default_power_limit = power_limit;
 
 	if (smu->od_enabled &&
-		    navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_POWER_LIMIT)) {
+		    navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_POWER_LIMIT))
 		od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
-		od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
-	} else {
+	else
 		od_percent_upper = 0;
-		od_percent_lower = 100;
-	}
+
+	od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
 
 	dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
 					od_percent_upper, od_percent_lower, power_limit);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index 21fc033528fa..e2ad2b972ab0 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -640,13 +640,12 @@ static int sienna_cichlid_get_power_limit(struct smu_context *smu,
 	if (default_power_limit)
 		*default_power_limit = power_limit;
 
-	if (smu->od_enabled) {
+	if (smu->od_enabled)
 		od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]);
-		od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]);
-	} else {
+	else
 		od_percent_upper = 0;
-		od_percent_lower = 100;
-	}
+
+	od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]);
 
 	dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
 					od_percent_upper, od_percent_lower, power_limit);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index 5a314d0316c1..c7bfa68bf00f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -1442,10 +1442,12 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev,
 			case 0x3:
 				dev_dbg(adev->dev, "Switched to AC mode!\n");
 				schedule_work(&smu->interrupt_work);
+				adev->pm.ac_power = true;
 				break;
 			case 0x4:
 				dev_dbg(adev->dev, "Switched to DC mode!\n");
 				schedule_work(&smu->interrupt_work);
+				adev->pm.ac_power = false;
 				break;
 			case 0x7:
 				/*
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index f1440869d1ce..dd9bcbd630a1 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -1530,7 +1530,6 @@ static int aldebaran_i2c_control_init(struct smu_context *smu)
 	smu_i2c->port = 0;
 	mutex_init(&smu_i2c->mutex);
 	control->owner = THIS_MODULE;
-	control->class = I2C_CLASS_SPD;
 	control->dev.parent = &adev->pdev->dev;
 	control->algo = &aldebaran_i2c_algo;
 	snprintf(control->name, sizeof(control->name), "AMDGPU SMU 0");
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index 771a3d457c33..c486182ff275 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -1379,10 +1379,12 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev,
 			case 0x3:
 				dev_dbg(adev->dev, "Switched to AC mode!\n");
 				smu_v13_0_ack_ac_dc_interrupt(smu);
+				adev->pm.ac_power = true;
 				break;
 			case 0x4:
 				dev_dbg(adev->dev, "Switched to DC mode!\n");
 				smu_v13_0_ack_ac_dc_interrupt(smu);
+				adev->pm.ac_power = false;
 				break;
 			case 0x7:
 				/*
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index 231122622a9c..9b80f18ea6c3 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -2357,6 +2357,7 @@ static int smu_v13_0_0_get_power_limit(struct smu_context *smu,
 	PPTable_t *pptable = table_context->driver_pptable;
 	SkuTable_t *skutable = &pptable->SkuTable;
 	uint32_t power_limit, od_percent_upper, od_percent_lower;
+	uint32_t msg_limit = skutable->MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC];
 
 	if (smu_v13_0_get_current_power_limit(smu, &power_limit))
 		power_limit = smu->adev->pm.ac_power ?
@@ -2368,19 +2369,18 @@ static int smu_v13_0_0_get_power_limit(struct smu_context *smu,
 	if (default_power_limit)
 		*default_power_limit = power_limit;
 
-	if (smu->od_enabled) {
+	if (smu->od_enabled)
 		od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]);
-		od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]);
-	} else {
+	else
 		od_percent_upper = 0;
-		od_percent_lower = 100;
-	}
+
+	od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]);
 
 	dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
 					od_percent_upper, od_percent_lower, power_limit);
 
 	if (max_power_limit) {
-		*max_power_limit = power_limit * (100 + od_percent_upper);
+		*max_power_limit = msg_limit * (100 + od_percent_upper);
 		*max_power_limit /= 100;
 	}
 
@@ -2696,7 +2696,6 @@ static int smu_v13_0_0_i2c_control_init(struct smu_context *smu)
 		smu_i2c->port = i;
 		mutex_init(&smu_i2c->mutex);
 		control->owner = THIS_MODULE;
-		control->class = I2C_CLASS_SPD;
 		control->dev.parent = &adev->pdev->dev;
 		control->algo = &smu_v13_0_0_i2c_algo;
 		snprintf(control->name, sizeof(control->name), "AMDGPU SMU %d", i);
@@ -2748,13 +2747,7 @@ static int smu_v13_0_0_set_mp1_state(struct smu_context *smu,
 
 	switch (mp1_state) {
 	case PP_MP1_STATE_UNLOAD:
-		ret = smu_cmn_send_smc_msg_with_param(smu,
-											  SMU_MSG_PrepareMp1ForUnload,
-											  0x55, NULL);
-
-		if (!ret && smu->smu_baco.state == SMU_BACO_STATE_EXIT)
-			ret = smu_v13_0_disable_pmfw_state(smu);
-
+		ret = smu_cmn_set_mp1_state(smu, mp1_state);
 		break;
 	default:
 		/* Ignore others */
@@ -2950,7 +2943,7 @@ static bool smu_v13_0_0_wbrf_support_check(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 
-	switch (adev->ip_versions[MP1_HWIP][0]) {
+	switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
 	case IP_VERSION(13, 0, 0):
 		return smu->smc_fw_version >= 0x004e6300;
 	case IP_VERSION(13, 0, 10):
@@ -2960,6 +2953,55 @@ static bool smu_v13_0_0_wbrf_support_check(struct smu_context *smu)
 	}
 }
 
+static int smu_v13_0_0_set_power_limit(struct smu_context *smu,
+				       enum smu_ppt_limit_type limit_type,
+				       uint32_t limit)
+{
+	PPTable_t *pptable = smu->smu_table.driver_pptable;
+	SkuTable_t *skutable = &pptable->SkuTable;
+	uint32_t msg_limit = skutable->MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC];
+	struct smu_table_context *table_context = &smu->smu_table;
+	OverDriveTableExternal_t *od_table =
+		(OverDriveTableExternal_t *)table_context->overdrive_table;
+	int ret = 0;
+
+	if (limit_type != SMU_DEFAULT_PPT_LIMIT)
+		return -EINVAL;
+
+	if (limit <= msg_limit) {
+		if (smu->current_power_limit > msg_limit) {
+			od_table->OverDriveTable.Ppt = 0;
+			od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_PPT_BIT;
+
+			ret = smu_v13_0_0_upload_overdrive_table(smu, od_table);
+			if (ret) {
+				dev_err(smu->adev->dev, "Failed to upload overdrive table!\n");
+				return ret;
+			}
+		}
+		return smu_v13_0_set_power_limit(smu, limit_type, limit);
+	} else if (smu->od_enabled) {
+		ret = smu_v13_0_set_power_limit(smu, limit_type, msg_limit);
+		if (ret)
+			return ret;
+
+		od_table->OverDriveTable.Ppt = (limit * 100) / msg_limit - 100;
+		od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_PPT_BIT;
+
+		ret = smu_v13_0_0_upload_overdrive_table(smu, od_table);
+		if (ret) {
+		  dev_err(smu->adev->dev, "Failed to upload overdrive table!\n");
+		  return ret;
+		}
+
+		smu->current_power_limit = limit;
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct pptable_funcs smu_v13_0_0_ppt_funcs = {
 	.get_allowed_feature_mask = smu_v13_0_0_get_allowed_feature_mask,
 	.set_default_dpm_table = smu_v13_0_0_set_default_dpm_table,
@@ -3014,7 +3056,7 @@ static const struct pptable_funcs smu_v13_0_0_ppt_funcs = {
 	.set_fan_control_mode = smu_v13_0_set_fan_control_mode,
 	.enable_mgpu_fan_boost = smu_v13_0_0_enable_mgpu_fan_boost,
 	.get_power_limit = smu_v13_0_0_get_power_limit,
-	.set_power_limit = smu_v13_0_set_power_limit,
+	.set_power_limit = smu_v13_0_0_set_power_limit,
 	.set_power_source = smu_v13_0_set_power_source,
 	.get_power_profile_mode = smu_v13_0_0_get_power_profile_mode,
 	.set_power_profile_mode = smu_v13_0_0_set_power_profile_mode,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 4ebc6b421c2c..7e1941cf1796 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -160,8 +160,8 @@ static const struct cmn2asic_msg_mapping smu_v13_0_6_message_map[SMU_MSG_MAX_COU
 	MSG_MAP(GfxDriverResetRecovery,		     PPSMC_MSG_GfxDriverResetRecovery,		0),
 	MSG_MAP(GetMinGfxclkFrequency,               PPSMC_MSG_GetMinGfxDpmFreq,                1),
 	MSG_MAP(GetMaxGfxclkFrequency,               PPSMC_MSG_GetMaxGfxDpmFreq,                1),
-	MSG_MAP(SetSoftMinGfxclk,                    PPSMC_MSG_SetSoftMinGfxClk,                0),
-	MSG_MAP(SetSoftMaxGfxClk,                    PPSMC_MSG_SetSoftMaxGfxClk,                0),
+	MSG_MAP(SetSoftMinGfxclk,                    PPSMC_MSG_SetSoftMinGfxClk,                1),
+	MSG_MAP(SetSoftMaxGfxClk,                    PPSMC_MSG_SetSoftMaxGfxClk,                1),
 	MSG_MAP(PrepareMp1ForUnload,                 PPSMC_MSG_PrepareForDriverUnload,          0),
 	MSG_MAP(GetCTFLimit,                         PPSMC_MSG_GetCTFLimit,                     0),
 	MSG_MAP(GetThermalLimit,                     PPSMC_MSG_ReadThrottlerLimit,              0),
@@ -970,7 +970,9 @@ static int smu_v13_0_6_print_clks(struct smu_context *smu, char *buf, int size,
 			if (i < (clocks.num_levels - 1))
 				clk2 = clocks.data[i + 1].clocks_in_khz / 1000;
 
-			if (curr_clk >= clk1 && curr_clk < clk2) {
+			if (curr_clk == clk1) {
+				level = i;
+			} else if (curr_clk >= clk1 && curr_clk < clk2) {
 				level = (curr_clk - clk1) <= (clk2 - curr_clk) ?
 						i :
 						i + 1;
@@ -1936,7 +1938,6 @@ static int smu_v13_0_6_i2c_control_init(struct smu_context *smu)
 		smu_i2c->port = i;
 		mutex_init(&smu_i2c->mutex);
 		control->owner = THIS_MODULE;
-		control->class = I2C_CLASS_SPD;
 		control->dev.parent = &adev->pdev->dev;
 		control->algo = &smu_v13_0_6_i2c_algo;
 		snprintf(control->name, sizeof(control->name), "AMDGPU SMU %d", i);
@@ -2235,17 +2236,18 @@ static int smu_v13_0_6_mode2_reset(struct smu_context *smu)
 			continue;
 		}
 
-		if (ret) {
-			dev_err(adev->dev,
-				"failed to send mode2 message \tparam: 0x%08x error code %d\n",
-				SMU_RESET_MODE_2, ret);
+		if (ret)
 			goto out;
-		}
+
 	} while (ret == -ETIME && timeout);
 
 out:
 	mutex_unlock(&smu->message_lock);
 
+	if (ret)
+		dev_err(adev->dev, "failed to send mode2 reset, error code %d",
+			ret);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index 59606a19e3d2..3dc7b60cb075 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -2321,6 +2321,7 @@ static int smu_v13_0_7_get_power_limit(struct smu_context *smu,
 	PPTable_t *pptable = table_context->driver_pptable;
 	SkuTable_t *skutable = &pptable->SkuTable;
 	uint32_t power_limit, od_percent_upper, od_percent_lower;
+	uint32_t msg_limit = skutable->MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC];
 
 	if (smu_v13_0_get_current_power_limit(smu, &power_limit))
 		power_limit = smu->adev->pm.ac_power ?
@@ -2332,19 +2333,18 @@ static int smu_v13_0_7_get_power_limit(struct smu_context *smu,
 	if (default_power_limit)
 		*default_power_limit = power_limit;
 
-	if (smu->od_enabled) {
+	if (smu->od_enabled)
 		od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]);
-		od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]);
-	} else {
+	else
 		od_percent_upper = 0;
-		od_percent_lower = 100;
-	}
+
+	od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]);
 
 	dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
 					od_percent_upper, od_percent_lower, power_limit);
 
 	if (max_power_limit) {
-		*max_power_limit = power_limit * (100 + od_percent_upper);
+		*max_power_limit = msg_limit * (100 + od_percent_upper);
 		*max_power_limit /= 100;
 	}
 
@@ -2504,13 +2504,7 @@ static int smu_v13_0_7_set_mp1_state(struct smu_context *smu,
 
 	switch (mp1_state) {
 	case PP_MP1_STATE_UNLOAD:
-		ret = smu_cmn_send_smc_msg_with_param(smu,
-											  SMU_MSG_PrepareMp1ForUnload,
-											  0x55, NULL);
-
-		if (!ret && smu->smu_baco.state == SMU_BACO_STATE_EXIT)
-			ret = smu_v13_0_disable_pmfw_state(smu);
-
+		ret = smu_cmn_set_mp1_state(smu, mp1_state);
 		break;
 	default:
 		/* Ignore others */
@@ -2545,6 +2539,55 @@ static bool smu_v13_0_7_wbrf_support_check(struct smu_context *smu)
 	return smu->smc_fw_version > 0x00524600;
 }
 
+static int smu_v13_0_7_set_power_limit(struct smu_context *smu,
+				       enum smu_ppt_limit_type limit_type,
+				       uint32_t limit)
+{
+	PPTable_t *pptable = smu->smu_table.driver_pptable;
+	SkuTable_t *skutable = &pptable->SkuTable;
+	uint32_t msg_limit = skutable->MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC];
+	struct smu_table_context *table_context = &smu->smu_table;
+	OverDriveTableExternal_t *od_table =
+		(OverDriveTableExternal_t *)table_context->overdrive_table;
+	int ret = 0;
+
+	if (limit_type != SMU_DEFAULT_PPT_LIMIT)
+		return -EINVAL;
+
+	if (limit <= msg_limit) {
+		if (smu->current_power_limit > msg_limit) {
+			od_table->OverDriveTable.Ppt = 0;
+			od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_PPT_BIT;
+
+			ret = smu_v13_0_7_upload_overdrive_table(smu, od_table);
+			if (ret) {
+				dev_err(smu->adev->dev, "Failed to upload overdrive table!\n");
+				return ret;
+			}
+		}
+		return smu_v13_0_set_power_limit(smu, limit_type, limit);
+	} else if (smu->od_enabled) {
+		ret = smu_v13_0_set_power_limit(smu, limit_type, msg_limit);
+		if (ret)
+			return ret;
+
+		od_table->OverDriveTable.Ppt = (limit * 100) / msg_limit - 100;
+		od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_PPT_BIT;
+
+		ret = smu_v13_0_7_upload_overdrive_table(smu, od_table);
+		if (ret) {
+		  dev_err(smu->adev->dev, "Failed to upload overdrive table!\n");
+		  return ret;
+		}
+
+		smu->current_power_limit = limit;
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct pptable_funcs smu_v13_0_7_ppt_funcs = {
 	.get_allowed_feature_mask = smu_v13_0_7_get_allowed_feature_mask,
 	.set_default_dpm_table = smu_v13_0_7_set_default_dpm_table,
@@ -2596,7 +2639,7 @@ static const struct pptable_funcs smu_v13_0_7_ppt_funcs = {
 	.set_fan_control_mode = smu_v13_0_set_fan_control_mode,
 	.enable_mgpu_fan_boost = smu_v13_0_7_enable_mgpu_fan_boost,
 	.get_power_limit = smu_v13_0_7_get_power_limit,
-	.set_power_limit = smu_v13_0_set_power_limit,
+	.set_power_limit = smu_v13_0_7_set_power_limit,
 	.set_power_source = smu_v13_0_set_power_source,
 	.get_power_profile_mode = smu_v13_0_7_get_power_profile_mode,
 	.set_power_profile_mode = smu_v13_0_7_set_power_profile_mode,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
index 4894f7ee737b..6dae5ad74ff0 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
@@ -229,8 +229,6 @@ int smu_v14_0_check_fw_version(struct smu_context *smu)
 		smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_2;
 		break;
 	case IP_VERSION(14, 0, 0):
-		if ((smu->smc_fw_version < 0x5d3a00))
-			dev_warn(smu->adev->dev, "The PMFW version(%x) is behind in this BIOS!\n", smu->smc_fw_version);
 		smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_0;
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
index 47fdbae4adfc..9310c4758e38 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
@@ -261,7 +261,10 @@ static int smu_v14_0_0_get_smu_metrics_data(struct smu_context *smu,
 		*value = metrics->MpipuclkFrequency;
 		break;
 	case METRICS_AVERAGE_GFXACTIVITY:
-		*value = metrics->GfxActivity / 100;
+		if ((smu->smc_fw_version > 0x5d4600))
+			*value = metrics->GfxActivity;
+		else
+			*value = metrics->GfxActivity / 100;
 		break;
 	case METRICS_AVERAGE_VCNACTIVITY:
 		*value = metrics->VcnActivity / 100;
diff --git a/drivers/gpu/drm/ast/ast_i2c.c b/drivers/gpu/drm/ast/ast_i2c.c
index 0e845e7acd9b..e5d3f7121de4 100644
--- a/drivers/gpu/drm/ast/ast_i2c.c
+++ b/drivers/gpu/drm/ast/ast_i2c.c
@@ -120,7 +120,6 @@ struct ast_i2c_chan *ast_i2c_create(struct drm_device *dev)
 		return NULL;
 
 	i2c->adapter.owner = THIS_MODULE;
-	i2c->adapter.class = I2C_CLASS_DDC;
 	i2c->adapter.dev.parent = dev->dev;
 	i2c->dev = dev;
 	i2c_set_adapdata(&i2c->adapter, i2c);
diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.c b/drivers/gpu/drm/bridge/analogix/anx7625.c
index ef31033439bc..29d91493b101 100644
--- a/drivers/gpu/drm/bridge/analogix/anx7625.c
+++ b/drivers/gpu/drm/bridge/analogix/anx7625.c
@@ -1762,6 +1762,7 @@ static ssize_t anx7625_aux_transfer(struct drm_dp_aux *aux,
 	u8 request = msg->request & ~DP_AUX_I2C_MOT;
 	int ret = 0;
 
+	mutex_lock(&ctx->aux_lock);
 	pm_runtime_get_sync(dev);
 	msg->reply = 0;
 	switch (request) {
@@ -1778,6 +1779,7 @@ static ssize_t anx7625_aux_transfer(struct drm_dp_aux *aux,
 					msg->size, msg->buffer);
 	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
+	mutex_unlock(&ctx->aux_lock);
 
 	return ret;
 }
@@ -2474,7 +2476,9 @@ static void anx7625_bridge_atomic_disable(struct drm_bridge *bridge,
 	ctx->connector = NULL;
 	anx7625_dp_stop(ctx);
 
-	pm_runtime_put_sync(dev);
+	mutex_lock(&ctx->aux_lock);
+	pm_runtime_put_sync_suspend(dev);
+	mutex_unlock(&ctx->aux_lock);
 }
 
 static enum drm_connector_status
@@ -2668,6 +2672,7 @@ static int anx7625_i2c_probe(struct i2c_client *client)
 
 	mutex_init(&platform->lock);
 	mutex_init(&platform->hdcp_wq_lock);
+	mutex_init(&platform->aux_lock);
 
 	INIT_DELAYED_WORK(&platform->hdcp_work, hdcp_check_work_func);
 	platform->hdcp_workqueue = create_workqueue("hdcp workqueue");
diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.h b/drivers/gpu/drm/bridge/analogix/anx7625.h
index 66ebee7f3d83..39ed35d33836 100644
--- a/drivers/gpu/drm/bridge/analogix/anx7625.h
+++ b/drivers/gpu/drm/bridge/analogix/anx7625.h
@@ -475,6 +475,8 @@ struct anx7625_data {
 	struct workqueue_struct *hdcp_workqueue;
 	/* Lock for hdcp work queue */
 	struct mutex hdcp_wq_lock;
+	/* Lock for aux transfer and disable */
+	struct mutex aux_lock;
 	char edid_block;
 	struct display_timing dt;
 	u8 display_timing_valid;
diff --git a/drivers/gpu/drm/bridge/aux-hpd-bridge.c b/drivers/gpu/drm/bridge/aux-hpd-bridge.c
index bb55f697a181..6886db2d9e00 100644
--- a/drivers/gpu/drm/bridge/aux-hpd-bridge.c
+++ b/drivers/gpu/drm/bridge/aux-hpd-bridge.c
@@ -25,20 +25,18 @@ static void drm_aux_hpd_bridge_release(struct device *dev)
 	ida_free(&drm_aux_hpd_bridge_ida, adev->id);
 
 	of_node_put(adev->dev.platform_data);
+	of_node_put(adev->dev.of_node);
 
 	kfree(adev);
 }
 
-static void drm_aux_hpd_bridge_unregister_adev(void *_adev)
+static void drm_aux_hpd_bridge_free_adev(void *_adev)
 {
-	struct auxiliary_device *adev = _adev;
-
-	auxiliary_device_delete(adev);
-	auxiliary_device_uninit(adev);
+	auxiliary_device_uninit(_adev);
 }
 
 /**
- * drm_dp_hpd_bridge_register - Create a simple HPD DisplayPort bridge
+ * devm_drm_dp_hpd_bridge_alloc - allocate a HPD DisplayPort bridge
  * @parent: device instance providing this bridge
  * @np: device node pointer corresponding to this bridge instance
  *
@@ -46,11 +44,9 @@ static void drm_aux_hpd_bridge_unregister_adev(void *_adev)
  * DRM_MODE_CONNECTOR_DisplayPort, which terminates the bridge chain and is
  * able to send the HPD events.
  *
- * Return: device instance that will handle created bridge or an error code
- * encoded into the pointer.
+ * Return: bridge auxiliary device pointer or an error pointer
  */
-struct device *drm_dp_hpd_bridge_register(struct device *parent,
-					  struct device_node *np)
+struct auxiliary_device *devm_drm_dp_hpd_bridge_alloc(struct device *parent, struct device_node *np)
 {
 	struct auxiliary_device *adev;
 	int ret;
@@ -74,18 +70,62 @@ struct device *drm_dp_hpd_bridge_register(struct device *parent,
 
 	ret = auxiliary_device_init(adev);
 	if (ret) {
+		of_node_put(adev->dev.platform_data);
+		of_node_put(adev->dev.of_node);
 		ida_free(&drm_aux_hpd_bridge_ida, adev->id);
 		kfree(adev);
 		return ERR_PTR(ret);
 	}
 
-	ret = auxiliary_device_add(adev);
-	if (ret) {
-		auxiliary_device_uninit(adev);
+	ret = devm_add_action_or_reset(parent, drm_aux_hpd_bridge_free_adev, adev);
+	if (ret)
 		return ERR_PTR(ret);
-	}
 
-	ret = devm_add_action_or_reset(parent, drm_aux_hpd_bridge_unregister_adev, adev);
+	return adev;
+}
+EXPORT_SYMBOL_GPL(devm_drm_dp_hpd_bridge_alloc);
+
+static void drm_aux_hpd_bridge_del_adev(void *_adev)
+{
+	auxiliary_device_delete(_adev);
+}
+
+/**
+ * devm_drm_dp_hpd_bridge_add - register a HDP DisplayPort bridge
+ * @dev: struct device to tie registration lifetime to
+ * @adev: bridge auxiliary device to be registered
+ *
+ * Returns: zero on success or a negative errno
+ */
+int devm_drm_dp_hpd_bridge_add(struct device *dev, struct auxiliary_device *adev)
+{
+	int ret;
+
+	ret = auxiliary_device_add(adev);
+	if (ret)
+		return ret;
+
+	return devm_add_action_or_reset(dev, drm_aux_hpd_bridge_del_adev, adev);
+}
+EXPORT_SYMBOL_GPL(devm_drm_dp_hpd_bridge_add);
+
+/**
+ * drm_dp_hpd_bridge_register - allocate and register a HDP DisplayPort bridge
+ * @parent: device instance providing this bridge
+ * @np: device node pointer corresponding to this bridge instance
+ *
+ * Return: device instance that will handle created bridge or an error pointer
+ */
+struct device *drm_dp_hpd_bridge_register(struct device *parent, struct device_node *np)
+{
+	struct auxiliary_device *adev;
+	int ret;
+
+	adev = devm_drm_dp_hpd_bridge_alloc(parent, np);
+	if (IS_ERR(adev))
+		return ERR_CAST(adev);
+
+	ret = devm_drm_dp_hpd_bridge_add(parent, adev);
 	if (ret)
 		return ERR_PTR(ret);
 
diff --git a/drivers/gpu/drm/bridge/parade-ps8640.c b/drivers/gpu/drm/bridge/parade-ps8640.c
index 541e4f5afc4c..14d4dcf239da 100644
--- a/drivers/gpu/drm/bridge/parade-ps8640.c
+++ b/drivers/gpu/drm/bridge/parade-ps8640.c
@@ -107,6 +107,7 @@ struct ps8640 {
 	struct device_link *link;
 	bool pre_enabled;
 	bool need_post_hpd_delay;
+	struct mutex aux_lock;
 };
 
 static const struct regmap_config ps8640_regmap_config[] = {
@@ -345,11 +346,20 @@ static ssize_t ps8640_aux_transfer(struct drm_dp_aux *aux,
 	struct device *dev = &ps_bridge->page[PAGE0_DP_CNTL]->dev;
 	int ret;
 
+	mutex_lock(&ps_bridge->aux_lock);
 	pm_runtime_get_sync(dev);
+	ret = _ps8640_wait_hpd_asserted(ps_bridge, 200 * 1000);
+	if (ret) {
+		pm_runtime_put_sync_suspend(dev);
+		goto exit;
+	}
 	ret = ps8640_aux_transfer_msg(aux, msg);
 	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
+exit:
+	mutex_unlock(&ps_bridge->aux_lock);
+
 	return ret;
 }
 
@@ -470,7 +480,18 @@ static void ps8640_atomic_post_disable(struct drm_bridge *bridge,
 	ps_bridge->pre_enabled = false;
 
 	ps8640_bridge_vdo_control(ps_bridge, DISABLE);
+
+	/*
+	 * The bridge seems to expect everything to be power cycled at the
+	 * disable process, so grab a lock here to make sure
+	 * ps8640_aux_transfer() is not holding a runtime PM reference and
+	 * preventing the bridge from suspend.
+	 */
+	mutex_lock(&ps_bridge->aux_lock);
+
 	pm_runtime_put_sync_suspend(&ps_bridge->page[PAGE0_DP_CNTL]->dev);
+
+	mutex_unlock(&ps_bridge->aux_lock);
 }
 
 static int ps8640_bridge_attach(struct drm_bridge *bridge,
@@ -619,6 +640,8 @@ static int ps8640_probe(struct i2c_client *client)
 	if (!ps_bridge)
 		return -ENOMEM;
 
+	mutex_init(&ps_bridge->aux_lock);
+
 	ps_bridge->supplies[0].supply = "vdd12";
 	ps_bridge->supplies[1].supply = "vdd33";
 	ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(ps_bridge->supplies),
diff --git a/drivers/gpu/drm/bridge/samsung-dsim.c b/drivers/gpu/drm/bridge/samsung-dsim.c
index be5914caa17d..63a1a0c88be4 100644
--- a/drivers/gpu/drm/bridge/samsung-dsim.c
+++ b/drivers/gpu/drm/bridge/samsung-dsim.c
@@ -969,10 +969,6 @@ static int samsung_dsim_init_link(struct samsung_dsim *dsi)
 	reg = samsung_dsim_read(dsi, DSIM_ESCMODE_REG);
 	reg &= ~DSIM_STOP_STATE_CNT_MASK;
 	reg |= DSIM_STOP_STATE_CNT(driver_data->reg_values[STOP_STATE_CNT]);
-
-	if (!samsung_dsim_hw_is_exynos(dsi->plat_data->hw_type))
-		reg |= DSIM_FORCE_STOP_STATE;
-
 	samsung_dsim_write(dsi, DSIM_ESCMODE_REG, reg);
 
 	reg = DSIM_BTA_TIMEOUT(0xff) | DSIM_LPDR_TIMEOUT(0xffff);
@@ -1431,18 +1427,6 @@ static void samsung_dsim_disable_irq(struct samsung_dsim *dsi)
 	disable_irq(dsi->irq);
 }
 
-static void samsung_dsim_set_stop_state(struct samsung_dsim *dsi, bool enable)
-{
-	u32 reg = samsung_dsim_read(dsi, DSIM_ESCMODE_REG);
-
-	if (enable)
-		reg |= DSIM_FORCE_STOP_STATE;
-	else
-		reg &= ~DSIM_FORCE_STOP_STATE;
-
-	samsung_dsim_write(dsi, DSIM_ESCMODE_REG, reg);
-}
-
 static int samsung_dsim_init(struct samsung_dsim *dsi)
 {
 	const struct samsung_dsim_driver_data *driver_data = dsi->driver_data;
@@ -1492,9 +1476,6 @@ static void samsung_dsim_atomic_pre_enable(struct drm_bridge *bridge,
 		ret = samsung_dsim_init(dsi);
 		if (ret)
 			return;
-
-		samsung_dsim_set_display_mode(dsi);
-		samsung_dsim_set_display_enable(dsi, true);
 	}
 }
 
@@ -1503,12 +1484,8 @@ static void samsung_dsim_atomic_enable(struct drm_bridge *bridge,
 {
 	struct samsung_dsim *dsi = bridge_to_dsi(bridge);
 
-	if (samsung_dsim_hw_is_exynos(dsi->plat_data->hw_type)) {
-		samsung_dsim_set_display_mode(dsi);
-		samsung_dsim_set_display_enable(dsi, true);
-	} else {
-		samsung_dsim_set_stop_state(dsi, false);
-	}
+	samsung_dsim_set_display_mode(dsi);
+	samsung_dsim_set_display_enable(dsi, true);
 
 	dsi->state |= DSIM_STATE_VIDOUT_AVAILABLE;
 }
@@ -1521,9 +1498,6 @@ static void samsung_dsim_atomic_disable(struct drm_bridge *bridge,
 	if (!(dsi->state & DSIM_STATE_ENABLED))
 		return;
 
-	if (!samsung_dsim_hw_is_exynos(dsi->plat_data->hw_type))
-		samsung_dsim_set_stop_state(dsi, true);
-
 	dsi->state &= ~DSIM_STATE_VIDOUT_AVAILABLE;
 }
 
@@ -1828,8 +1802,6 @@ static ssize_t samsung_dsim_host_transfer(struct mipi_dsi_host *host,
 	if (ret)
 		return ret;
 
-	samsung_dsim_set_stop_state(dsi, false);
-
 	ret = mipi_dsi_create_packet(&xfer.packet, msg);
 	if (ret < 0)
 		return ret;
diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c
index 2bdc5b439beb..4560ae9cbce1 100644
--- a/drivers/gpu/drm/bridge/sii902x.c
+++ b/drivers/gpu/drm/bridge/sii902x.c
@@ -1080,6 +1080,26 @@ static int sii902x_init(struct sii902x *sii902x)
 			return ret;
 	}
 
+	ret = sii902x_audio_codec_init(sii902x, dev);
+	if (ret)
+		return ret;
+
+	i2c_set_clientdata(sii902x->i2c, sii902x);
+
+	sii902x->i2cmux = i2c_mux_alloc(sii902x->i2c->adapter, dev,
+					1, 0, I2C_MUX_GATE,
+					sii902x_i2c_bypass_select,
+					sii902x_i2c_bypass_deselect);
+	if (!sii902x->i2cmux) {
+		ret = -ENOMEM;
+		goto err_unreg_audio;
+	}
+
+	sii902x->i2cmux->priv = sii902x;
+	ret = i2c_mux_add_adapter(sii902x->i2cmux, 0, 0, 0);
+	if (ret)
+		goto err_unreg_audio;
+
 	sii902x->bridge.funcs = &sii902x_bridge_funcs;
 	sii902x->bridge.of_node = dev->of_node;
 	sii902x->bridge.timings = &default_sii902x_timings;
@@ -1090,19 +1110,13 @@ static int sii902x_init(struct sii902x *sii902x)
 
 	drm_bridge_add(&sii902x->bridge);
 
-	sii902x_audio_codec_init(sii902x, dev);
-
-	i2c_set_clientdata(sii902x->i2c, sii902x);
+	return 0;
 
-	sii902x->i2cmux = i2c_mux_alloc(sii902x->i2c->adapter, dev,
-					1, 0, I2C_MUX_GATE,
-					sii902x_i2c_bypass_select,
-					sii902x_i2c_bypass_deselect);
-	if (!sii902x->i2cmux)
-		return -ENOMEM;
+err_unreg_audio:
+	if (!PTR_ERR_OR_ZERO(sii902x->audio.pdev))
+		platform_device_unregister(sii902x->audio.pdev);
 
-	sii902x->i2cmux->priv = sii902x;
-	return i2c_mux_add_adapter(sii902x->i2cmux, 0, 0, 0);
+	return ret;
 }
 
 static int sii902x_probe(struct i2c_client *client)
@@ -1170,12 +1184,14 @@ static int sii902x_probe(struct i2c_client *client)
 }
 
 static void sii902x_remove(struct i2c_client *client)
-
 {
 	struct sii902x *sii902x = i2c_get_clientdata(client);
 
-	i2c_mux_del_adapters(sii902x->i2cmux);
 	drm_bridge_remove(&sii902x->bridge);
+	i2c_mux_del_adapters(sii902x->i2cmux);
+
+	if (!PTR_ERR_OR_ZERO(sii902x->audio.pdev))
+		platform_device_unregister(sii902x->audio.pdev);
 }
 
 static const struct of_device_id sii902x_dt_ids[] = {
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
index 52d91a0df85e..aca5bb0866f8 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
@@ -515,7 +515,6 @@ static struct i2c_adapter *dw_hdmi_i2c_adapter(struct dw_hdmi *hdmi)
 	init_completion(&i2c->cmp);
 
 	adap = &i2c->adap;
-	adap->class = I2C_CLASS_DDC;
 	adap->owner = THIS_MODULE;
 	adap->dev.parent = hdmi->dev;
 	adap->algo = &dw_hdmi_algorithm;
diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c
index d72b6f9a352c..b1ca3a1100da 100644
--- a/drivers/gpu/drm/display/drm_dp_helper.c
+++ b/drivers/gpu/drm/display/drm_dp_helper.c
@@ -2102,7 +2102,6 @@ int drm_dp_aux_register(struct drm_dp_aux *aux)
 	if (!aux->ddc.algo)
 		drm_dp_aux_init(aux);
 
-	aux->ddc.class = I2C_CLASS_DDC;
 	aux->ddc.owner = THIS_MODULE;
 	aux->ddc.dev.parent = aux->dev;
 
diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c
index 8ca01a6bf645..f7c6b60629c2 100644
--- a/drivers/gpu/drm/display/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c
@@ -5491,6 +5491,7 @@ EXPORT_SYMBOL(drm_dp_mst_atomic_enable_dsc);
  *   - 0 if the new state is valid
  *   - %-ENOSPC, if the new state is invalid, because of BW limitation
  *         @failing_port is set to:
+ *
  *         - The non-root port where a BW limit check failed
  *           with all the ports downstream of @failing_port passing
  *           the BW limit check.
@@ -5499,6 +5500,7 @@ EXPORT_SYMBOL(drm_dp_mst_atomic_enable_dsc);
  *         - %NULL if the BW limit check failed at the root port
  *           with all the ports downstream of the root port passing
  *           the BW limit check.
+ *
  *   - %-EINVAL, if the new state is invalid, because the root port has
  *     too many payloads.
  */
@@ -5926,7 +5928,6 @@ static int drm_dp_mst_register_i2c_bus(struct drm_dp_mst_port *port)
 	aux->ddc.algo_data = aux;
 	aux->ddc.retries = 3;
 
-	aux->ddc.class = I2C_CLASS_DDC;
 	aux->ddc.owner = THIS_MODULE;
 	/* FIXME: set the kdev of the port's connector as parent */
 	aux->ddc.dev.parent = parent_dev;
diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c
index f57e6d74fb0e..5ebdd6f8f36e 100644
--- a/drivers/gpu/drm/drm_buddy.c
+++ b/drivers/gpu/drm/drm_buddy.c
@@ -332,6 +332,7 @@ alloc_range_bias(struct drm_buddy *mm,
 		 u64 start, u64 end,
 		 unsigned int order)
 {
+	u64 req_size = mm->chunk_size << order;
 	struct drm_buddy_block *block;
 	struct drm_buddy_block *buddy;
 	LIST_HEAD(dfs);
@@ -367,6 +368,15 @@ alloc_range_bias(struct drm_buddy *mm,
 		if (drm_buddy_block_is_allocated(block))
 			continue;
 
+		if (block_start < start || block_end > end) {
+			u64 adjusted_start = max(block_start, start);
+			u64 adjusted_end = min(block_end, end);
+
+			if (round_down(adjusted_end + 1, req_size) <=
+			    round_up(adjusted_start, req_size))
+				continue;
+		}
+
 		if (contains(start, end, block_start, block_end) &&
 		    order == drm_buddy_block_order(block)) {
 			/*
@@ -538,7 +548,13 @@ static int __alloc_range(struct drm_buddy *mm,
 		list_add(&block->left->tmp_link, dfs);
 	} while (1);
 
+	if (total_allocated < size) {
+		err = -ENOSPC;
+		goto err_free;
+	}
+
 	list_splice_tail(&allocated, blocks);
+
 	return 0;
 
 err_undo:
@@ -755,8 +771,12 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm,
 		return -EINVAL;
 
 	/* Actual range allocation */
-	if (start + size == end)
+	if (start + size == end) {
+		if (!IS_ALIGNED(start | end, min_block_size))
+			return -EINVAL;
+
 		return __drm_buddy_alloc_range(mm, start, size, NULL, blocks);
+	}
 
 	original_size = size;
 	original_min_size = min_block_size;
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index cb90e70d85e8..65f9f66933bb 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -904,6 +904,7 @@ out:
 	connector_set = NULL;
 	fb = NULL;
 	mode = NULL;
+	num_connectors = 0;
 
 	DRM_MODESET_LOCK_ALL_END(dev, ctx, ret);
 
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 834a5e28abbe..7352bde299d5 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -820,7 +820,7 @@ struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev,
 	if (max_segment == 0)
 		max_segment = UINT_MAX;
 	err = sg_alloc_table_from_pages_segment(sg, pages, nr_pages, 0,
-						nr_pages << PAGE_SHIFT,
+						(unsigned long)nr_pages << PAGE_SHIFT,
 						max_segment, GFP_KERNEL);
 	if (err) {
 		kfree(sg);
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index 3f479483d7d8..23b4e9a3361d 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -760,9 +760,11 @@ static void output_poll_execute(struct work_struct *work)
 	changed = dev->mode_config.delayed_event;
 	dev->mode_config.delayed_event = false;
 
-	if (!drm_kms_helper_poll && dev->mode_config.poll_running) {
-		drm_kms_helper_disable_hpd(dev);
-		dev->mode_config.poll_running = false;
+	if (!drm_kms_helper_poll) {
+		if (dev->mode_config.poll_running) {
+			drm_kms_helper_disable_hpd(dev);
+			dev->mode_config.poll_running = false;
+		}
 		goto out;
 	}
 
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index 84101baeecc6..a6c19de46292 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -1040,7 +1040,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
 	uint64_t *points;
 	uint32_t signaled_count, i;
 
-	if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT)
+	if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT |
+		     DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE))
 		lockdep_assert_none_held_once();
 
 	points = kmalloc_array(count, sizeof(*points), GFP_KERNEL);
@@ -1109,7 +1110,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
 	 * fallthough and try a 0 timeout wait!
 	 */
 
-	if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) {
+	if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT |
+		     DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE)) {
 		for (i = 0; i < count; ++i)
 			drm_syncobj_fence_add_wait(syncobjs[i], &entries[i]);
 	}
@@ -1416,10 +1418,21 @@ syncobj_eventfd_entry_func(struct drm_syncobj *syncobj,
 
 	/* This happens inside the syncobj lock */
 	fence = dma_fence_get(rcu_dereference_protected(syncobj->fence, 1));
+	if (!fence)
+		return;
+
 	ret = dma_fence_chain_find_seqno(&fence, entry->point);
-	if (ret != 0 || !fence) {
+	if (ret != 0) {
+		/* The given seqno has not been submitted yet. */
 		dma_fence_put(fence);
 		return;
+	} else if (!fence) {
+		/* If dma_fence_chain_find_seqno returns 0 but sets the fence
+		 * to NULL, it implies that the given seqno is signaled and a
+		 * later seqno has already been submitted. Assign a stub fence
+		 * so that the eventfd still gets signaled below.
+		 */
+		fence = dma_fence_get_stub();
 	}
 
 	list_del_init(&entry->node);
diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 776f2f0b602d..0ef7bc8848b0 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -319,9 +319,9 @@ static void decon_win_set_bldmod(struct decon_context *ctx, unsigned int win,
 static void decon_win_set_pixfmt(struct decon_context *ctx, unsigned int win,
 				 struct drm_framebuffer *fb)
 {
-	struct exynos_drm_plane plane = ctx->planes[win];
+	struct exynos_drm_plane *plane = &ctx->planes[win];
 	struct exynos_drm_plane_state *state =
-		to_exynos_plane_state(plane.base.state);
+		to_exynos_plane_state(plane->base.state);
 	unsigned int alpha = state->base.alpha;
 	unsigned int pixel_alpha;
 	unsigned long val;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index a9f1c5c05894..f2145227a1e0 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -480,7 +480,7 @@ static void fimd_commit(struct exynos_drm_crtc *crtc)
 	struct fimd_context *ctx = crtc->ctx;
 	struct drm_display_mode *mode = &crtc->base.state->adjusted_mode;
 	const struct fimd_driver_data *driver_data = ctx->driver_data;
-	void *timing_base = ctx->regs + driver_data->timing_base;
+	void __iomem *timing_base = ctx->regs + driver_data->timing_base;
 	u32 val;
 
 	if (ctx->suspended)
@@ -661,9 +661,9 @@ static void fimd_win_set_bldmod(struct fimd_context *ctx, unsigned int win,
 static void fimd_win_set_pixfmt(struct fimd_context *ctx, unsigned int win,
 				struct drm_framebuffer *fb, int width)
 {
-	struct exynos_drm_plane plane = ctx->planes[win];
+	struct exynos_drm_plane *plane = &ctx->planes[win];
 	struct exynos_drm_plane_state *state =
-		to_exynos_plane_state(plane.base.state);
+		to_exynos_plane_state(plane->base.state);
 	uint32_t pixel_format = fb->format->format;
 	unsigned int alpha = state->base.alpha;
 	u32 val = WINCONx_ENWIN;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index e9a769590415..180507a47700 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -1341,7 +1341,7 @@ static int __maybe_unused gsc_runtime_resume(struct device *dev)
 	for (i = 0; i < ctx->num_clocks; i++) {
 		ret = clk_prepare_enable(ctx->clocks[i]);
 		if (ret) {
-			while (--i > 0)
+			while (--i >= 0)
 				clk_disable_unprepare(ctx->clocks[i]);
 			return ret;
 		}
diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c
index 8992a95076f2..dd1eb7e9877d 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_dp.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c
@@ -855,7 +855,6 @@ cdv_intel_dp_i2c_init(struct gma_connector *connector,
 
 	memset(&intel_dp->adapter, '\0', sizeof (intel_dp->adapter));
 	intel_dp->adapter.owner = THIS_MODULE;
-	intel_dp->adapter.class = I2C_CLASS_DDC;
 	strncpy (intel_dp->adapter.name, name, sizeof(intel_dp->adapter.name) - 1);
 	intel_dp->adapter.name[sizeof(intel_dp->adapter.name) - 1] = '\0';
 	intel_dp->adapter.algo_data = &intel_dp->algo;
diff --git a/drivers/gpu/drm/gma500/intel_gmbus.c b/drivers/gpu/drm/gma500/intel_gmbus.c
index 09cedabf4776..aa45509859f2 100644
--- a/drivers/gpu/drm/gma500/intel_gmbus.c
+++ b/drivers/gpu/drm/gma500/intel_gmbus.c
@@ -411,7 +411,6 @@ int gma_intel_setup_gmbus(struct drm_device *dev)
 		struct intel_gmbus *bus = &dev_priv->gmbus[i];
 
 		bus->adapter.owner = THIS_MODULE;
-		bus->adapter.class = I2C_CLASS_DDC;
 		snprintf(bus->adapter.name,
 			 sizeof(bus->adapter.name),
 			 "gma500 gmbus %s",
diff --git a/drivers/gpu/drm/gma500/oaktrail_hdmi_i2c.c b/drivers/gpu/drm/gma500/oaktrail_hdmi_i2c.c
index fc9a34ed58bd..6daa6669ed23 100644
--- a/drivers/gpu/drm/gma500/oaktrail_hdmi_i2c.c
+++ b/drivers/gpu/drm/gma500/oaktrail_hdmi_i2c.c
@@ -168,7 +168,6 @@ static struct i2c_adapter oaktrail_hdmi_i2c_adapter = {
 	.name		= "oaktrail_hdmi_i2c",
 	.nr		= 3,
 	.owner		= THIS_MODULE,
-	.class		= I2C_CLASS_DDC,
 	.algo		= &oaktrail_hdmi_i2c_algorithm,
 };
 
diff --git a/drivers/gpu/drm/gma500/psb_intel_sdvo.c b/drivers/gpu/drm/gma500/psb_intel_sdvo.c
index d6fd5d726216..e4f914deceba 100644
--- a/drivers/gpu/drm/gma500/psb_intel_sdvo.c
+++ b/drivers/gpu/drm/gma500/psb_intel_sdvo.c
@@ -2426,7 +2426,6 @@ psb_intel_sdvo_init_ddc_proxy(struct psb_intel_sdvo *sdvo,
 			  struct drm_device *dev)
 {
 	sdvo->ddc.owner = THIS_MODULE;
-	sdvo->ddc.class = I2C_CLASS_DDC;
 	snprintf(sdvo->ddc.name, I2C_NAME_SIZE, "SDVO DDC proxy");
 	sdvo->ddc.dev.parent = dev->dev;
 	sdvo->ddc.algo_data = sdvo;
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c
index 410bd019bb35..e6e48651c15c 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c
@@ -81,7 +81,6 @@ int hibmc_ddc_create(struct drm_device *drm_dev,
 		     struct hibmc_connector *connector)
 {
 	connector->adapter.owner = THIS_MODULE;
-	connector->adapter.class = I2C_CLASS_DDC;
 	snprintf(connector->adapter.name, I2C_NAME_SIZE, "HIS i2c bit bus");
 	connector->adapter.dev.parent = drm_dev->dev;
 	i2c_set_adapdata(&connector->adapter, connector);
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index b5d6e3352071..3089029abba4 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -140,7 +140,7 @@ config DRM_I915_GVT_KVMGT
 
 	  Note that this driver only supports newer device from Broadwell on.
 	  For further information and setup guide, you can visit:
-	  http://01.org/igvt-g.
+	  https://github.com/intel/gvt-linux/wiki.
 
 	  If in doubt, say "N".
 
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index e777686190ca..c13f14edb508 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -17,7 +17,6 @@ subdir-ccflags-y += $(call cc-option, -Wunused-const-variable)
 subdir-ccflags-y += $(call cc-option, -Wpacked-not-aligned)
 subdir-ccflags-y += $(call cc-option, -Wformat-overflow)
 subdir-ccflags-y += $(call cc-option, -Wformat-truncation)
-subdir-ccflags-y += $(call cc-option, -Wstringop-overflow)
 subdir-ccflags-y += $(call cc-option, -Wstringop-truncation)
 # The following turn off the warnings enabled by -Wextra
 ifeq ($(findstring 2, $(KBUILD_EXTRA_WARN)),)
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index ac456a2275db..eda4a8b88590 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -1155,6 +1155,7 @@ static void gen11_dsi_powerup_panel(struct intel_encoder *encoder)
 	}
 
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_INIT_OTP);
+	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_ON);
 
 	/* ensure all panel commands dispatched before enabling transcoder */
 	wait_for_cmds_dispatched_to_panel(encoder);
@@ -1255,8 +1256,6 @@ static void gen11_dsi_enable(struct intel_atomic_state *state,
 	/* step6d: enable dsi transcoder */
 	gen11_dsi_enable_transcoder(encoder);
 
-	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_ON);
-
 	/* step7: enable backlight */
 	intel_backlight_enable(crtc_state, conn_state);
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_BACKLIGHT_ON);
diff --git a/drivers/gpu/drm/i915/display/intel_cx0_phy.c b/drivers/gpu/drm/i915/display/intel_cx0_phy.c
index 884a1da36089..6b25e195232f 100644
--- a/drivers/gpu/drm/i915/display/intel_cx0_phy.c
+++ b/drivers/gpu/drm/i915/display/intel_cx0_phy.c
@@ -3067,24 +3067,29 @@ static void intel_c20pll_state_verify(const struct intel_crtc_state *state,
 {
 	struct drm_i915_private *i915 = to_i915(crtc->base.dev);
 	const struct intel_c20pll_state *mpll_sw_state = &state->cx0pll_state.c20;
-	bool use_mplla;
+	bool sw_use_mpllb = mpll_sw_state->tx[0] & C20_PHY_USE_MPLLB;
+	bool hw_use_mpllb = mpll_hw_state->tx[0] & C20_PHY_USE_MPLLB;
 	int i;
 
-	use_mplla = intel_c20_use_mplla(mpll_hw_state->clock);
-	if (use_mplla) {
-		for (i = 0; i < ARRAY_SIZE(mpll_sw_state->mplla); i++) {
-			I915_STATE_WARN(i915, mpll_hw_state->mplla[i] != mpll_sw_state->mplla[i],
-					"[CRTC:%d:%s] mismatch in C20MPLLA: Register[%d] (expected 0x%04x, found 0x%04x)",
-					crtc->base.base.id, crtc->base.name, i,
-					mpll_sw_state->mplla[i], mpll_hw_state->mplla[i]);
-		}
-	} else {
+	I915_STATE_WARN(i915, sw_use_mpllb != hw_use_mpllb,
+			"[CRTC:%d:%s] mismatch in C20: Register MPLLB selection (expected %d, found %d)",
+			crtc->base.base.id, crtc->base.name,
+			sw_use_mpllb, hw_use_mpllb);
+
+	if (hw_use_mpllb) {
 		for (i = 0; i < ARRAY_SIZE(mpll_sw_state->mpllb); i++) {
 			I915_STATE_WARN(i915, mpll_hw_state->mpllb[i] != mpll_sw_state->mpllb[i],
 					"[CRTC:%d:%s] mismatch in C20MPLLB: Register[%d] (expected 0x%04x, found 0x%04x)",
 					crtc->base.base.id, crtc->base.name, i,
 					mpll_sw_state->mpllb[i], mpll_hw_state->mpllb[i]);
 		}
+	} else {
+		for (i = 0; i < ARRAY_SIZE(mpll_sw_state->mplla); i++) {
+			I915_STATE_WARN(i915, mpll_hw_state->mplla[i] != mpll_sw_state->mplla[i],
+					"[CRTC:%d:%s] mismatch in C20MPLLA: Register[%d] (expected 0x%04x, found 0x%04x)",
+					crtc->base.base.id, crtc->base.name, i,
+					mpll_sw_state->mplla[i], mpll_hw_state->mplla[i]);
+		}
 	}
 
 	for (i = 0; i < ARRAY_SIZE(mpll_sw_state->tx); i++) {
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 5f091502719b..6fd4fa52253a 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -405,8 +405,8 @@ print_async_put_domains_state(struct i915_power_domains *power_domains)
 						     struct drm_i915_private,
 						     display.power.domains);
 
-	drm_dbg(&i915->drm, "async_put_wakeref %lu\n",
-		power_domains->async_put_wakeref);
+	drm_dbg(&i915->drm, "async_put_wakeref: %s\n",
+		str_yes_no(power_domains->async_put_wakeref));
 
 	print_power_domains(power_domains, "async_put_domains[0]",
 			    &power_domains->async_put_domains[0]);
diff --git a/drivers/gpu/drm/i915/display/intel_display_power_well.c b/drivers/gpu/drm/i915/display/intel_display_power_well.c
index 47cd6bb04366..06900ff307b2 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power_well.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power_well.c
@@ -246,7 +246,14 @@ static enum phy icl_aux_pw_to_phy(struct drm_i915_private *i915,
 	enum aux_ch aux_ch = icl_aux_pw_to_ch(power_well);
 	struct intel_digital_port *dig_port = aux_ch_to_digital_port(i915, aux_ch);
 
-	return intel_port_to_phy(i915, dig_port->base.port);
+	/*
+	 * FIXME should we care about the (VBT defined) dig_port->aux_ch
+	 * relationship or should this be purely defined by the hardware layout?
+	 * Currently if the port doesn't appear in the VBT, or if it's declared
+	 * as HDMI-only and routed to a combo PHY, the encoder either won't be
+	 * present at all or it will not have an aux_ch assigned.
+	 */
+	return dig_port ? intel_port_to_phy(i915, dig_port->base.port) : PHY_NONE;
 }
 
 static void hsw_wait_for_power_well_enable(struct drm_i915_private *dev_priv,
@@ -414,7 +421,8 @@ icl_combo_phy_aux_power_well_enable(struct drm_i915_private *dev_priv,
 
 	intel_de_rmw(dev_priv, regs->driver, 0, HSW_PWR_WELL_CTL_REQ(pw_idx));
 
-	if (DISPLAY_VER(dev_priv) < 12)
+	/* FIXME this is a mess */
+	if (phy != PHY_NONE)
 		intel_de_rmw(dev_priv, ICL_PORT_CL_DW12(phy),
 			     0, ICL_LANE_ENABLE_AUX);
 
@@ -437,7 +445,10 @@ icl_combo_phy_aux_power_well_disable(struct drm_i915_private *dev_priv,
 
 	drm_WARN_ON(&dev_priv->drm, !IS_ICELAKE(dev_priv));
 
-	intel_de_rmw(dev_priv, ICL_PORT_CL_DW12(phy), ICL_LANE_ENABLE_AUX, 0);
+	/* FIXME this is a mess */
+	if (phy != PHY_NONE)
+		intel_de_rmw(dev_priv, ICL_PORT_CL_DW12(phy),
+			     ICL_LANE_ENABLE_AUX, 0);
 
 	intel_de_rmw(dev_priv, regs->driver, HSW_PWR_WELL_CTL_REQ(pw_idx), 0);
 
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 3fdd8a517983..ac7fe6281afe 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -609,6 +609,13 @@ struct intel_connector {
 	 * and active (i.e. dpms ON state). */
 	bool (*get_hw_state)(struct intel_connector *);
 
+	/*
+	 * Optional hook called during init/resume to sync any state
+	 * stored in the connector (eg. DSC state) wrt. the HW state.
+	 */
+	void (*sync_state)(struct intel_connector *connector,
+			   const struct intel_crtc_state *crtc_state);
+
 	/* Panel info for eDP and LVDS */
 	struct intel_panel panel;
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 7d2b8ce48fda..94d2a15d8444 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -2101,7 +2101,7 @@ static int intel_dp_dsc_compute_pipe_bpp(struct intel_dp *intel_dp,
 		}
 	}
 
-	dsc_max_bpc = intel_dp_dsc_min_src_input_bpc(i915);
+	dsc_max_bpc = intel_dp_dsc_max_src_input_bpc(i915);
 	if (!dsc_max_bpc)
 		return -EINVAL;
 
@@ -2355,6 +2355,9 @@ intel_dp_compute_config_limits(struct intel_dp *intel_dp,
 	limits->min_rate = intel_dp_common_rate(intel_dp, 0);
 	limits->max_rate = intel_dp_max_link_rate(intel_dp);
 
+	/* FIXME 128b/132b SST support missing */
+	limits->max_rate = min(limits->max_rate, 810000);
+
 	limits->min_lane_count = 1;
 	limits->max_lane_count = intel_dp_max_lane_count(intel_dp);
 
@@ -5696,6 +5699,9 @@ intel_dp_detect(struct drm_connector *connector,
 		goto out;
 	}
 
+	if (!intel_dp_is_edp(intel_dp))
+		intel_psr_init_dpcd(intel_dp);
+
 	intel_dp_detect_dsc_caps(intel_dp, intel_connector);
 
 	intel_dp_configure_mst(intel_dp);
@@ -5856,6 +5862,19 @@ intel_dp_connector_unregister(struct drm_connector *connector)
 	intel_connector_unregister(connector);
 }
 
+void intel_dp_connector_sync_state(struct intel_connector *connector,
+				   const struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *i915 = to_i915(connector->base.dev);
+
+	if (crtc_state && crtc_state->dsc.compression_enable) {
+		drm_WARN_ON(&i915->drm, !connector->dp.dsc_decompression_aux);
+		connector->dp.dsc_decompression_enabled = true;
+	} else {
+		connector->dp.dsc_decompression_enabled = false;
+	}
+}
+
 void intel_dp_encoder_flush_work(struct drm_encoder *encoder)
 {
 	struct intel_digital_port *dig_port = enc_to_dig_port(to_intel_encoder(encoder));
diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h
index 05db46b111f2..375d0677cd8c 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.h
+++ b/drivers/gpu/drm/i915/display/intel_dp.h
@@ -45,6 +45,8 @@ bool intel_dp_limited_color_range(const struct intel_crtc_state *crtc_state,
 int intel_dp_min_bpp(enum intel_output_format output_format);
 bool intel_dp_init_connector(struct intel_digital_port *dig_port,
 			     struct intel_connector *intel_connector);
+void intel_dp_connector_sync_state(struct intel_connector *connector,
+				   const struct intel_crtc_state *crtc_state);
 void intel_dp_set_link_params(struct intel_dp *intel_dp,
 			      int link_rate, int lane_count);
 int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp,
diff --git a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
index 3a595cd433d4..8538d1ce2fcb 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
@@ -330,23 +330,13 @@ static const struct hdcp2_dp_msg_data hdcp2_dp_msg_data[] = {
 	  0, 0 },
 };
 
-static struct drm_dp_aux *
-intel_dp_hdcp_get_aux(struct intel_connector *connector)
-{
-	struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
-
-	if (intel_encoder_is_mst(connector->encoder))
-		return &connector->port->aux;
-	else
-		return &dig_port->dp.aux;
-}
-
 static int
 intel_dp_hdcp2_read_rx_status(struct intel_connector *connector,
 			      u8 *rx_status)
 {
 	struct drm_i915_private *i915 = to_i915(connector->base.dev);
-	struct drm_dp_aux *aux = intel_dp_hdcp_get_aux(connector);
+	struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
+	struct drm_dp_aux *aux = &dig_port->dp.aux;
 	ssize_t ret;
 
 	ret = drm_dp_dpcd_read(aux,
@@ -399,7 +389,9 @@ intel_dp_hdcp2_wait_for_msg(struct intel_connector *connector,
 			    const struct hdcp2_dp_msg_data *hdcp2_msg_data)
 {
 	struct drm_i915_private *i915 = to_i915(connector->base.dev);
-	struct intel_hdcp *hdcp = &connector->hdcp;
+	struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
+	struct intel_dp *dp = &dig_port->dp;
+	struct intel_hdcp *hdcp = &dp->attached_connector->hdcp;
 	u8 msg_id = hdcp2_msg_data->msg_id;
 	int ret, timeout;
 	bool msg_ready = false;
@@ -454,8 +446,9 @@ int intel_dp_hdcp2_write_msg(struct intel_connector *connector,
 	unsigned int offset;
 	u8 *byte = buf;
 	ssize_t ret, bytes_to_write, len;
+	struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
+	struct drm_dp_aux *aux = &dig_port->dp.aux;
 	const struct hdcp2_dp_msg_data *hdcp2_msg_data;
-	struct drm_dp_aux *aux;
 
 	hdcp2_msg_data = get_hdcp2_dp_msg_data(*byte);
 	if (!hdcp2_msg_data)
@@ -463,8 +456,6 @@ int intel_dp_hdcp2_write_msg(struct intel_connector *connector,
 
 	offset = hdcp2_msg_data->offset;
 
-	aux = intel_dp_hdcp_get_aux(connector);
-
 	/* No msg_id in DP HDCP2.2 msgs */
 	bytes_to_write = size - 1;
 	byte++;
@@ -490,7 +481,8 @@ static
 ssize_t get_receiver_id_list_rx_info(struct intel_connector *connector,
 				     u32 *dev_cnt, u8 *byte)
 {
-	struct drm_dp_aux *aux = intel_dp_hdcp_get_aux(connector);
+	struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
+	struct drm_dp_aux *aux = &dig_port->dp.aux;
 	ssize_t ret;
 	u8 *rx_info = byte;
 
@@ -515,8 +507,9 @@ int intel_dp_hdcp2_read_msg(struct intel_connector *connector,
 {
 	struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
 	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
-	struct intel_hdcp *hdcp = &connector->hdcp;
-	struct drm_dp_aux *aux;
+	struct drm_dp_aux *aux = &dig_port->dp.aux;
+	struct intel_dp *dp = &dig_port->dp;
+	struct intel_hdcp *hdcp = &dp->attached_connector->hdcp;
 	unsigned int offset;
 	u8 *byte = buf;
 	ssize_t ret, bytes_to_recv, len;
@@ -530,8 +523,6 @@ int intel_dp_hdcp2_read_msg(struct intel_connector *connector,
 		return -EINVAL;
 	offset = hdcp2_msg_data->offset;
 
-	aux = intel_dp_hdcp_get_aux(connector);
-
 	ret = intel_dp_hdcp2_wait_for_msg(connector, hdcp2_msg_data);
 	if (ret < 0)
 		return ret;
@@ -561,13 +552,8 @@ int intel_dp_hdcp2_read_msg(struct intel_connector *connector,
 
 		/* Entire msg read timeout since initiate of msg read */
 		if (bytes_to_recv == size - 1 && hdcp2_msg_data->msg_read_timeout > 0) {
-			if (intel_encoder_is_mst(connector->encoder))
-				msg_end = ktime_add_ms(ktime_get_raw(),
-						       hdcp2_msg_data->msg_read_timeout *
-						       connector->port->parent->num_ports);
-			else
-				msg_end = ktime_add_ms(ktime_get_raw(),
-						       hdcp2_msg_data->msg_read_timeout);
+			msg_end = ktime_add_ms(ktime_get_raw(),
+					       hdcp2_msg_data->msg_read_timeout);
 		}
 
 		ret = drm_dp_dpcd_read(aux, offset,
@@ -651,12 +637,11 @@ static
 int intel_dp_hdcp2_capable(struct intel_connector *connector,
 			   bool *capable)
 {
-	struct drm_dp_aux *aux;
+	struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
+	struct drm_dp_aux *aux = &dig_port->dp.aux;
 	u8 rx_caps[3];
 	int ret;
 
-	aux = intel_dp_hdcp_get_aux(connector);
-
 	*capable = false;
 	ret = drm_dp_dpcd_read(aux,
 			       DP_HDCP_2_2_REG_RX_CAPS_OFFSET,
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 8a9432335030..a01a59f57ae5 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -1534,6 +1534,7 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
 		return NULL;
 
 	intel_connector->get_hw_state = intel_dp_mst_get_hw_state;
+	intel_connector->sync_state = intel_dp_connector_sync_state;
 	intel_connector->mst_port = intel_dp;
 	intel_connector->port = port;
 	drm_dp_mst_get_port_malloc(port);
diff --git a/drivers/gpu/drm/i915/display/intel_gmbus.c b/drivers/gpu/drm/i915/display/intel_gmbus.c
index 40d7b6f3f489..e9e4dcf345f9 100644
--- a/drivers/gpu/drm/i915/display/intel_gmbus.c
+++ b/drivers/gpu/drm/i915/display/intel_gmbus.c
@@ -899,7 +899,6 @@ int intel_gmbus_setup(struct drm_i915_private *i915)
 		}
 
 		bus->adapter.owner = THIS_MODULE;
-		bus->adapter.class = I2C_CLASS_DDC;
 		snprintf(bus->adapter.name,
 			 sizeof(bus->adapter.name),
 			 "i915 gmbus %s", gmbus_pin->name);
diff --git a/drivers/gpu/drm/i915/display/intel_modeset_setup.c b/drivers/gpu/drm/i915/display/intel_modeset_setup.c
index 94eece7f63be..caeca3a8442c 100644
--- a/drivers/gpu/drm/i915/display/intel_modeset_setup.c
+++ b/drivers/gpu/drm/i915/display/intel_modeset_setup.c
@@ -318,12 +318,6 @@ static void intel_modeset_update_connector_atomic_state(struct drm_i915_private
 			const struct intel_crtc_state *crtc_state =
 				to_intel_crtc_state(crtc->base.state);
 
-			if (crtc_state->dsc.compression_enable) {
-				drm_WARN_ON(&i915->drm, !connector->dp.dsc_decompression_aux);
-				connector->dp.dsc_decompression_enabled = true;
-			} else {
-				connector->dp.dsc_decompression_enabled = false;
-			}
 			conn_state->max_bpc = (crtc_state->pipe_bpp ?: 24) / 3;
 		}
 	}
@@ -775,8 +769,9 @@ static void intel_modeset_readout_hw_state(struct drm_i915_private *i915)
 
 	drm_connector_list_iter_begin(&i915->drm, &conn_iter);
 	for_each_intel_connector_iter(connector, &conn_iter) {
+		struct intel_crtc_state *crtc_state = NULL;
+
 		if (connector->get_hw_state(connector)) {
-			struct intel_crtc_state *crtc_state;
 			struct intel_crtc *crtc;
 
 			connector->base.dpms = DRM_MODE_DPMS_ON;
@@ -802,6 +797,10 @@ static void intel_modeset_readout_hw_state(struct drm_i915_private *i915)
 			connector->base.dpms = DRM_MODE_DPMS_OFF;
 			connector->base.encoder = NULL;
 		}
+
+		if (connector->sync_state)
+			connector->sync_state(connector, crtc_state);
+
 		drm_dbg_kms(&i915->drm,
 			    "[CONNECTOR:%d:%s] hw state readout: %s\n",
 			    connector->base.base.id, connector->base.name,
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index b6e2e70e1290..4faaf4b3fc53 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -1525,8 +1525,18 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp,
 	 * can rely on frontbuffer tracking.
 	 */
 	mask = EDP_PSR_DEBUG_MASK_MEMUP |
-	       EDP_PSR_DEBUG_MASK_HPD |
-	       EDP_PSR_DEBUG_MASK_LPSP;
+	       EDP_PSR_DEBUG_MASK_HPD;
+
+	/*
+	 * For some unknown reason on HSW non-ULT (or at least on
+	 * Dell Latitude E6540) external displays start to flicker
+	 * when PSR is enabled on the eDP. SR/PC6 residency is much
+	 * higher than should be possible with an external display.
+	 * As a workaround leave LPSP unmasked to prevent PSR entry
+	 * when external displays are active.
+	 */
+	if (DISPLAY_VER(dev_priv) >= 8 || IS_HASWELL_ULT(dev_priv))
+		mask |= EDP_PSR_DEBUG_MASK_LPSP;
 
 	if (DISPLAY_VER(dev_priv) < 20)
 		mask |= EDP_PSR_DEBUG_MASK_MAX_SLEEP;
@@ -2766,9 +2776,6 @@ void intel_psr_init(struct intel_dp *intel_dp)
 	if (!(HAS_PSR(dev_priv) || HAS_DP20(dev_priv)))
 		return;
 
-	if (!intel_dp_is_edp(intel_dp))
-		intel_psr_init_dpcd(intel_dp);
-
 	/*
 	 * HSW spec explicitly says PSR is tied to port A.
 	 * BDW+ platforms have a instance of PSR registers per transcoder but
@@ -3319,11 +3326,11 @@ void intel_psr_connector_debugfs_add(struct intel_connector *connector)
 	struct drm_i915_private *i915 = to_i915(connector->base.dev);
 	struct dentry *root = connector->base.debugfs_entry;
 
-	if (connector->base.connector_type != DRM_MODE_CONNECTOR_eDP) {
-		if (!(HAS_DP20(i915) &&
-		      connector->base.connector_type == DRM_MODE_CONNECTOR_DisplayPort))
-			return;
-	}
+	/* TODO: Add support for MST connectors as well. */
+	if ((connector->base.connector_type != DRM_MODE_CONNECTOR_eDP &&
+	     connector->base.connector_type != DRM_MODE_CONNECTOR_DisplayPort) ||
+	    connector->mst_port)
+		return;
 
 	debugfs_create_file("i915_psr_sink_status", 0444, root,
 			    connector, &i915_psr_sink_status_fops);
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index 9218047495fb..2915d7afe5cc 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -1209,7 +1209,7 @@ static bool intel_sdvo_set_tv_format(struct intel_sdvo *intel_sdvo,
 	struct intel_sdvo_tv_format format;
 	u32 format_map;
 
-	format_map = 1 << conn_state->tv.mode;
+	format_map = 1 << conn_state->tv.legacy_mode;
 	memset(&format, 0, sizeof(format));
 	memcpy(&format, &format_map, min(sizeof(format), sizeof(format_map)));
 
@@ -2298,7 +2298,7 @@ static int intel_sdvo_get_tv_modes(struct drm_connector *connector)
 	 * Read the list of supported input resolutions for the selected TV
 	 * format.
 	 */
-	format_map = 1 << conn_state->tv.mode;
+	format_map = 1 << conn_state->tv.legacy_mode;
 	memcpy(&tv_res, &format_map,
 	       min(sizeof(format_map), sizeof(struct intel_sdvo_sdtv_resolution_request)));
 
@@ -2363,7 +2363,7 @@ intel_sdvo_connector_atomic_get_property(struct drm_connector *connector,
 		int i;
 
 		for (i = 0; i < intel_sdvo_connector->format_supported_num; i++)
-			if (state->tv.mode == intel_sdvo_connector->tv_format_supported[i]) {
+			if (state->tv.legacy_mode == intel_sdvo_connector->tv_format_supported[i]) {
 				*val = i;
 
 				return 0;
@@ -2419,7 +2419,7 @@ intel_sdvo_connector_atomic_set_property(struct drm_connector *connector,
 	struct intel_sdvo_connector_state *sdvo_state = to_intel_sdvo_connector_state(state);
 
 	if (property == intel_sdvo_connector->tv_format) {
-		state->tv.mode = intel_sdvo_connector->tv_format_supported[val];
+		state->tv.legacy_mode = intel_sdvo_connector->tv_format_supported[val];
 
 		if (state->crtc) {
 			struct drm_crtc_state *crtc_state =
@@ -3076,7 +3076,7 @@ static bool intel_sdvo_tv_create_property(struct intel_sdvo *intel_sdvo,
 		drm_property_add_enum(intel_sdvo_connector->tv_format, i,
 				      tv_format_names[intel_sdvo_connector->tv_format_supported[i]]);
 
-	intel_sdvo_connector->base.base.state->tv.mode = intel_sdvo_connector->tv_format_supported[0];
+	intel_sdvo_connector->base.base.state->tv.legacy_mode = intel_sdvo_connector->tv_format_supported[0];
 	drm_object_attach_property(&intel_sdvo_connector->base.base.base,
 				   intel_sdvo_connector->tv_format, 0);
 	return true;
@@ -3327,7 +3327,6 @@ intel_sdvo_init_ddc_proxy(struct intel_sdvo_ddc *ddc,
 	ddc->ddc_bus = ddc_bus;
 
 	ddc->ddc.owner = THIS_MODULE;
-	ddc->ddc.class = I2C_CLASS_DDC;
 	snprintf(ddc->ddc.name, I2C_NAME_SIZE, "SDVO %c DDC%d",
 		 port_name(sdvo->base.port), ddc_bus);
 	ddc->ddc.dev.parent = &pdev->dev;
diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c
index d4386cb3569e..992a725de751 100644
--- a/drivers/gpu/drm/i915/display/intel_tv.c
+++ b/drivers/gpu/drm/i915/display/intel_tv.c
@@ -949,7 +949,7 @@ intel_disable_tv(struct intel_atomic_state *state,
 
 static const struct tv_mode *intel_tv_mode_find(const struct drm_connector_state *conn_state)
 {
-	int format = conn_state->tv.mode;
+	int format = conn_state->tv.legacy_mode;
 
 	return &tv_modes[format];
 }
@@ -1704,7 +1704,7 @@ static void intel_tv_find_better_format(struct drm_connector *connector)
 			break;
 	}
 
-	connector->state->tv.mode = i;
+	connector->state->tv.legacy_mode = i;
 }
 
 static int
@@ -1859,7 +1859,7 @@ static int intel_tv_atomic_check(struct drm_connector *connector,
 	old_state = drm_atomic_get_old_connector_state(state, connector);
 	new_crtc_state = drm_atomic_get_new_crtc_state(state, new_state->crtc);
 
-	if (old_state->tv.mode != new_state->tv.mode ||
+	if (old_state->tv.legacy_mode != new_state->tv.legacy_mode ||
 	    old_state->tv.margins.left != new_state->tv.margins.left ||
 	    old_state->tv.margins.right != new_state->tv.margins.right ||
 	    old_state->tv.margins.top != new_state->tv.margins.top ||
@@ -1896,7 +1896,7 @@ static void intel_tv_add_properties(struct drm_connector *connector)
 	conn_state->tv.margins.right = 46;
 	conn_state->tv.margins.bottom = 37;
 
-	conn_state->tv.mode = 0;
+	conn_state->tv.legacy_mode = 0;
 
 	/* Create TV properties then attach current values */
 	for (i = 0; i < ARRAY_SIZE(tv_modes); i++) {
@@ -1910,7 +1910,7 @@ static void intel_tv_add_properties(struct drm_connector *connector)
 
 	drm_object_attach_property(&connector->base,
 				   i915->drm.mode_config.legacy_tv_mode_property,
-				   conn_state->tv.mode);
+				   conn_state->tv.legacy_mode);
 	drm_object_attach_property(&connector->base,
 				   i915->drm.mode_config.tv_left_margin_property,
 				   conn_state->tv.margins.left);
diff --git a/drivers/gpu/drm/i915/display/intel_vdsc_regs.h b/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
index 64f440fdc22b..8b21dc8e26d5 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
+++ b/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
@@ -51,8 +51,8 @@
 #define DSCC_PICTURE_PARAMETER_SET_0		_MMIO(0x6BA00)
 #define _DSCA_PPS_0				0x6B200
 #define _DSCC_PPS_0				0x6BA00
-#define DSCA_PPS(pps)				_MMIO(_DSCA_PPS_0 + (pps) * 4)
-#define DSCC_PPS(pps)				_MMIO(_DSCC_PPS_0 + (pps) * 4)
+#define DSCA_PPS(pps)				_MMIO(_DSCA_PPS_0 + ((pps) < 12 ? (pps) : (pps) + 12) * 4)
+#define DSCC_PPS(pps)				_MMIO(_DSCC_PPS_0 + ((pps) < 12 ? (pps) : (pps) + 12) * 4)
 #define _ICL_DSC0_PICTURE_PARAMETER_SET_0_PB	0x78270
 #define _ICL_DSC1_PICTURE_PARAMETER_SET_0_PB	0x78370
 #define _ICL_DSC0_PICTURE_PARAMETER_SET_0_PC	0x78470
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index c573c067779f..03bc7f9d191b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -412,9 +412,9 @@ struct i915_gem_context {
 
 	/** @stale: tracks stale engines to be destroyed */
 	struct {
-		/** @lock: guards engines */
+		/** @stale.lock: guards engines */
 		spinlock_t lock;
-		/** @engines: list of stale engines */
+		/** @stale.engines: list of stale engines */
 		struct list_head engines;
 	} stale;
 };
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 1d3ebdf4069b..c08b67593565 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -379,6 +379,9 @@ i915_gem_userptr_release(struct drm_i915_gem_object *obj)
 {
 	GEM_WARN_ON(obj->userptr.page_ref);
 
+	if (!obj->userptr.notifier.mm)
+		return;
+
 	mmu_interval_notifier_remove(&obj->userptr.notifier);
 	obj->userptr.notifier.mm = NULL;
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_gsc.h b/drivers/gpu/drm/i915/gt/intel_gsc.h
index 7ab3ca0f9f26..013c64251448 100644
--- a/drivers/gpu/drm/i915/gt/intel_gsc.h
+++ b/drivers/gpu/drm/i915/gt/intel_gsc.h
@@ -21,8 +21,11 @@ struct mei_aux_device;
 /**
  * struct intel_gsc - graphics security controller
  *
- * @gem_obj: scratch memory GSC operations
- * @intf : gsc interface
+ * @intf: gsc interface
+ * @intf.adev: MEI aux. device for this @intf
+ * @intf.gem_obj: scratch memory GSC operations
+ * @intf.irq: IRQ for this device (%-1 for no IRQ)
+ * @intf.id: this interface's id number/index
  */
 struct intel_gsc {
 	struct intel_gsc_intf {
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index e22c12ce245a..813cc888e6fa 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -105,61 +105,67 @@ struct intel_guc {
 	 */
 	struct {
 		/**
-		 * @lock: protects everything in submission_state,
-		 * ce->guc_id.id, and ce->guc_id.ref when transitioning in and
-		 * out of zero
+		 * @submission_state.lock: protects everything in
+		 * submission_state, ce->guc_id.id, and ce->guc_id.ref
+		 * when transitioning in and out of zero
 		 */
 		spinlock_t lock;
 		/**
-		 * @guc_ids: used to allocate new guc_ids, single-lrc
+		 * @submission_state.guc_ids: used to allocate new
+		 * guc_ids, single-lrc
 		 */
 		struct ida guc_ids;
 		/**
-		 * @num_guc_ids: Number of guc_ids, selftest feature to be able
-		 * to reduce this number while testing.
+		 * @submission_state.num_guc_ids: Number of guc_ids, selftest
+		 * feature to be able to reduce this number while testing.
 		 */
 		int num_guc_ids;
 		/**
-		 * @guc_ids_bitmap: used to allocate new guc_ids, multi-lrc
+		 * @submission_state.guc_ids_bitmap: used to allocate
+		 * new guc_ids, multi-lrc
 		 */
 		unsigned long *guc_ids_bitmap;
 		/**
-		 * @guc_id_list: list of intel_context with valid guc_ids but no
-		 * refs
+		 * @submission_state.guc_id_list: list of intel_context
+		 * with valid guc_ids but no refs
 		 */
 		struct list_head guc_id_list;
 		/**
-		 * @guc_ids_in_use: Number single-lrc guc_ids in use
+		 * @submission_state.guc_ids_in_use: Number single-lrc
+		 * guc_ids in use
 		 */
 		unsigned int guc_ids_in_use;
 		/**
-		 * @destroyed_contexts: list of contexts waiting to be destroyed
-		 * (deregistered with the GuC)
+		 * @submission_state.destroyed_contexts: list of contexts
+		 * waiting to be destroyed (deregistered with the GuC)
 		 */
 		struct list_head destroyed_contexts;
 		/**
-		 * @destroyed_worker: worker to deregister contexts, need as we
-		 * need to take a GT PM reference and can't from destroy
-		 * function as it might be in an atomic context (no sleeping)
+		 * @submission_state.destroyed_worker: worker to deregister
+		 * contexts, need as we need to take a GT PM reference and
+		 * can't from destroy function as it might be in an atomic
+		 * context (no sleeping)
 		 */
 		struct work_struct destroyed_worker;
 		/**
-		 * @reset_fail_worker: worker to trigger a GT reset after an
-		 * engine reset fails
+		 * @submission_state.reset_fail_worker: worker to trigger
+		 * a GT reset after an engine reset fails
 		 */
 		struct work_struct reset_fail_worker;
 		/**
-		 * @reset_fail_mask: mask of engines that failed to reset
+		 * @submission_state.reset_fail_mask: mask of engines that
+		 * failed to reset
 		 */
 		intel_engine_mask_t reset_fail_mask;
 		/**
-		 * @sched_disable_delay_ms: schedule disable delay, in ms, for
-		 * contexts
+		 * @submission_state.sched_disable_delay_ms: schedule
+		 * disable delay, in ms, for contexts
 		 */
 		unsigned int sched_disable_delay_ms;
 		/**
-		 * @sched_disable_gucid_threshold: threshold of min remaining available
-		 * guc_ids before we start bypassing the schedule disable delay
+		 * @submission_state.sched_disable_gucid_threshold:
+		 * threshold of min remaining available guc_ids before
+		 * we start bypassing the schedule disable delay
 		 */
 		unsigned int sched_disable_gucid_threshold;
 	} submission_state;
@@ -243,37 +249,40 @@ struct intel_guc {
 	 */
 	struct {
 		/**
-		 * @lock: Lock protecting the below fields and the engine stats.
+		 * @timestamp.lock: Lock protecting the below fields and
+		 * the engine stats.
 		 */
 		spinlock_t lock;
 
 		/**
-		 * @gt_stamp: 64 bit extended value of the GT timestamp.
+		 * @timestamp.gt_stamp: 64-bit extended value of the GT
+		 * timestamp.
 		 */
 		u64 gt_stamp;
 
 		/**
-		 * @ping_delay: Period for polling the GT timestamp for
-		 * overflow.
+		 * @timestamp.ping_delay: Period for polling the GT
+		 * timestamp for overflow.
 		 */
 		unsigned long ping_delay;
 
 		/**
-		 * @work: Periodic work to adjust GT timestamp, engine and
-		 * context usage for overflows.
+		 * @timestamp.work: Periodic work to adjust GT timestamp,
+		 * engine and context usage for overflows.
 		 */
 		struct delayed_work work;
 
 		/**
-		 * @shift: Right shift value for the gpm timestamp
+		 * @timestamp.shift: Right shift value for the gpm timestamp
 		 */
 		u32 shift;
 
 		/**
-		 * @last_stat_jiffies: jiffies at last actual stats collection time
-		 * We use this timestamp to ensure we don't oversample the
-		 * stats because runtime power management events can trigger
-		 * stats collection at much higher rates than required.
+		 * @timestamp.last_stat_jiffies: jiffies at last actual
+		 * stats collection time. We use this timestamp to ensure
+		 * we don't oversample the stats because runtime power
+		 * management events can trigger stats collection at much
+		 * higher rates than required.
 		 */
 		unsigned long last_stat_jiffies;
 	} timestamp;
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 90f6c1ece57d..efcb00472be2 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -2849,8 +2849,7 @@ static int handle_mmio(struct intel_gvt_mmio_table_iter *iter, u32 offset,
 	for (i = start; i < end; i += 4) {
 		p = intel_gvt_find_mmio_info(gvt, i);
 		if (p) {
-			WARN(1, "dup mmio definition offset %x\n",
-				info->offset);
+			WARN(1, "dup mmio definition offset %x\n", i);
 
 			/* We return -EEXIST here to make GVT-g load fail.
 			 * So duplicated MMIO can be found as soon as
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index 13b1ae9b96c7..46445248d193 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -291,7 +291,8 @@ struct i915_perf_stream {
 		int size_exponent;
 
 		/**
-		 * @ptr_lock: Locks reads and writes to all head/tail state
+		 * @oa_buffer.ptr_lock: Locks reads and writes to all
+		 * head/tail state
 		 *
 		 * Consider: the head and tail pointer state needs to be read
 		 * consistently from a hrtimer callback (atomic context) and
@@ -313,7 +314,8 @@ struct i915_perf_stream {
 		spinlock_t ptr_lock;
 
 		/**
-		 * @head: Although we can always read back the head pointer register,
+		 * @oa_buffer.head: Although we can always read back
+		 * the head pointer register,
 		 * we prefer to avoid trusting the HW state, just to avoid any
 		 * risk that some hardware condition could * somehow bump the
 		 * head pointer unpredictably and cause us to forward the wrong
@@ -322,7 +324,8 @@ struct i915_perf_stream {
 		u32 head;
 
 		/**
-		 * @tail: The last verified tail that can be read by userspace.
+		 * @oa_buffer.tail: The last verified tail that can be
+		 * read by userspace.
 		 */
 		u32 tail;
 	} oa_buffer;
diff --git a/drivers/gpu/drm/i915/intel_gvt.c b/drivers/gpu/drm/i915/intel_gvt.c
index e98b6d69a91a..9b6d87c8b583 100644
--- a/drivers/gpu/drm/i915/intel_gvt.c
+++ b/drivers/gpu/drm/i915/intel_gvt.c
@@ -41,7 +41,7 @@
  * To virtualize GPU resources GVT-g driver depends on hypervisor technology
  * e.g KVM/VFIO/mdev, Xen, etc. to provide resource access trapping capability
  * and be virtualized within GVT-g device module. More architectural design
- * doc is available on https://01.org/group/2230/documentation-list.
+ * doc is available on https://github.com/intel/gvt-linux/wiki.
  */
 
 static LIST_HEAD(intel_gvt_devices);
diff --git a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c
index 2990dd4d4a0d..e14ac0ab1314 100644
--- a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c
+++ b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c
@@ -3,6 +3,8 @@
  * Copyright © 2021 Intel Corporation
  */
 
+#include <linux/jiffies.h>
+
 //#include "gt/intel_engine_user.h"
 #include "gt/intel_gt.h"
 #include "i915_drv.h"
@@ -12,7 +14,7 @@
 
 #define REDUCED_TIMESLICE	5
 #define REDUCED_PREEMPT		10
-#define WAIT_FOR_RESET_TIME	10000
+#define WAIT_FOR_RESET_TIME_MS	10000
 
 struct intel_engine_cs *intel_selftest_find_any_engine(struct intel_gt *gt)
 {
@@ -91,7 +93,7 @@ int intel_selftest_wait_for_rq(struct i915_request *rq)
 {
 	long ret;
 
-	ret = i915_request_wait(rq, 0, WAIT_FOR_RESET_TIME);
+	ret = i915_request_wait(rq, 0, msecs_to_jiffies(WAIT_FOR_RESET_TIME_MS));
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/gpu/drm/loongson/lsdc_i2c.c b/drivers/gpu/drm/loongson/lsdc_i2c.c
index 9625d0b1d0b4..ce90c25536d2 100644
--- a/drivers/gpu/drm/loongson/lsdc_i2c.c
+++ b/drivers/gpu/drm/loongson/lsdc_i2c.c
@@ -154,7 +154,6 @@ int lsdc_create_i2c_chan(struct drm_device *ddev,
 	adapter = &li2c->adapter;
 	adapter->algo_data = &li2c->bit;
 	adapter->owner = THIS_MODULE;
-	adapter->class = I2C_CLASS_DDC;
 	adapter->dev.parent = ddev->dev;
 	adapter->nr = -1;
 
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c b/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c
index d675c954befe..54e46e440e0f 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c
@@ -297,7 +297,6 @@ static int mtk_hdmi_ddc_probe(struct platform_device *pdev)
 
 	strscpy(ddc->adap.name, "mediatek-hdmi-ddc", sizeof(ddc->adap.name));
 	ddc->adap.owner = THIS_MODULE;
-	ddc->adap.class = I2C_CLASS_DDC;
 	ddc->adap.algo = &mtk_hdmi_ddc_algorithm;
 	ddc->adap.retries = 3;
 	ddc->adap.dev.of_node = dev->of_node;
diff --git a/drivers/gpu/drm/meson/meson_encoder_cvbs.c b/drivers/gpu/drm/meson/meson_encoder_cvbs.c
index 3f73b211fa8e..3407450435e2 100644
--- a/drivers/gpu/drm/meson/meson_encoder_cvbs.c
+++ b/drivers/gpu/drm/meson/meson_encoder_cvbs.c
@@ -294,6 +294,5 @@ void meson_encoder_cvbs_remove(struct meson_drm *priv)
 	if (priv->encoders[MESON_ENC_CVBS]) {
 		meson_encoder_cvbs = priv->encoders[MESON_ENC_CVBS];
 		drm_bridge_remove(&meson_encoder_cvbs->bridge);
-		drm_bridge_remove(meson_encoder_cvbs->next_bridge);
 	}
 }
diff --git a/drivers/gpu/drm/meson/meson_encoder_dsi.c b/drivers/gpu/drm/meson/meson_encoder_dsi.c
index 3f93c70488ca..311b91630fbe 100644
--- a/drivers/gpu/drm/meson/meson_encoder_dsi.c
+++ b/drivers/gpu/drm/meson/meson_encoder_dsi.c
@@ -168,6 +168,5 @@ void meson_encoder_dsi_remove(struct meson_drm *priv)
 	if (priv->encoders[MESON_ENC_DSI]) {
 		meson_encoder_dsi = priv->encoders[MESON_ENC_DSI];
 		drm_bridge_remove(&meson_encoder_dsi->bridge);
-		drm_bridge_remove(meson_encoder_dsi->next_bridge);
 	}
 }
diff --git a/drivers/gpu/drm/meson/meson_encoder_hdmi.c b/drivers/gpu/drm/meson/meson_encoder_hdmi.c
index 25ea76558690..c4686568c9ca 100644
--- a/drivers/gpu/drm/meson/meson_encoder_hdmi.c
+++ b/drivers/gpu/drm/meson/meson_encoder_hdmi.c
@@ -474,6 +474,5 @@ void meson_encoder_hdmi_remove(struct meson_drm *priv)
 	if (priv->encoders[MESON_ENC_HDMI]) {
 		meson_encoder_hdmi = priv->encoders[MESON_ENC_HDMI];
 		drm_bridge_remove(&meson_encoder_hdmi->bridge);
-		drm_bridge_remove(meson_encoder_hdmi->next_bridge);
 	}
 }
diff --git a/drivers/gpu/drm/mgag200/mgag200_i2c.c b/drivers/gpu/drm/mgag200/mgag200_i2c.c
index 0c48bdf3e7f8..423eb302be7e 100644
--- a/drivers/gpu/drm/mgag200/mgag200_i2c.c
+++ b/drivers/gpu/drm/mgag200/mgag200_i2c.c
@@ -106,7 +106,6 @@ int mgag200_i2c_init(struct mga_device *mdev, struct mga_i2c_chan *i2c)
 	i2c->data = BIT(info->i2c.data_bit);
 	i2c->clock = BIT(info->i2c.clock_bit);
 	i2c->adapter.owner = THIS_MODULE;
-	i2c->adapter.class = I2C_CLASS_DDC;
 	i2c->adapter.dev.parent = dev->dev;
 	i2c->dev = dev;
 	i2c_set_adapdata(&i2c->adapter, i2c);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index c0bc924cd302..c9c55e2ea584 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1287,7 +1287,7 @@ static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu)
 	gpu->ubwc_config.highest_bank_bit = 15;
 
 	if (adreno_is_a610(gpu)) {
-		gpu->ubwc_config.highest_bank_bit = 14;
+		gpu->ubwc_config.highest_bank_bit = 13;
 		gpu->ubwc_config.min_acc_len = 1;
 		gpu->ubwc_config.ubwc_mode = 1;
 	}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 83380bc92a00..6a4b489d44e5 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -144,10 +144,6 @@ enum dpu_enc_rc_states {
  *			to track crtc in the disable() hook which is called
  *			_after_ encoder_mask is cleared.
  * @connector:		If a mode is set, cached pointer to the active connector
- * @crtc_kickoff_cb:		Callback into CRTC that will flush & start
- *				all CTL paths
- * @crtc_kickoff_cb_data:	Opaque user data given to crtc_kickoff_cb
- * @debugfs_root:		Debug file system root file node
  * @enc_lock:			Lock around physical encoder
  *				create/destroy/enable/disable
  * @frame_busy_mask:		Bitmask tracking which phys_enc we are still
@@ -2072,7 +2068,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 	}
 
 	/* reset the merge 3D HW block */
-	if (phys_enc->hw_pp->merge_3d) {
+	if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) {
 		phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d,
 				BLEND_3D_NONE);
 		if (phys_enc->hw_ctl->ops.update_pending_flush_merge_3d)
@@ -2103,7 +2099,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 	if (phys_enc->hw_wb)
 		intf_cfg.wb = phys_enc->hw_wb->idx;
 
-	if (phys_enc->hw_pp->merge_3d)
+	if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d)
 		intf_cfg.merge_3d = phys_enc->hw_pp->merge_3d->idx;
 
 	if (ctl->ops.reset_intf_cfg)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
index b58a9c2ae326..724537ab776d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
@@ -29,7 +29,6 @@ static inline bool reserved_by_other(uint32_t *res_map, int idx,
 /**
  * struct dpu_rm_requirements - Reservation requirements parameter bundle
  * @topology:  selected topology for the display
- * @hw_res:	   Hardware resources required as reported by the encoders
  */
 struct dpu_rm_requirements {
 	struct msm_display_topology topology;
@@ -204,6 +203,8 @@ static bool _dpu_rm_needs_split_display(const struct msm_display_topology *top)
  * _dpu_rm_get_lm_peer - get the id of a mixer which is a peer of the primary
  * @rm: dpu resource manager handle
  * @primary_idx: index of primary mixer in rm->mixer_blks[]
+ *
+ * Returns: lm peer mixed id on success or %-EINVAL on error
  */
 static int _dpu_rm_get_lm_peer(struct dpu_rm *rm, int primary_idx)
 {
diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c
index 77a8d9366ed7..fb588fde298a 100644
--- a/drivers/gpu/drm/msm/dp/dp_ctrl.c
+++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c
@@ -135,11 +135,6 @@ static void dp_ctrl_config_ctrl(struct dp_ctrl_private *ctrl)
 	tbd = dp_link_get_test_bits_depth(ctrl->link,
 			ctrl->panel->dp_mode.bpp);
 
-	if (tbd == DP_TEST_BIT_DEPTH_UNKNOWN) {
-		pr_debug("BIT_DEPTH not set. Configure default\n");
-		tbd = DP_TEST_BIT_DEPTH_8;
-	}
-
 	config |= tbd << DP_CONFIGURATION_CTRL_BPC_SHIFT;
 
 	/* Num of Lanes */
diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
index d37d599aec27..4c72124ffb5d 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -329,10 +329,26 @@ static const struct component_ops dp_display_comp_ops = {
 	.unbind = dp_display_unbind,
 };
 
+static void dp_display_send_hpd_event(struct msm_dp *dp_display)
+{
+	struct dp_display_private *dp;
+	struct drm_connector *connector;
+
+	dp = container_of(dp_display, struct dp_display_private, dp_display);
+
+	connector = dp->dp_display.connector;
+	drm_helper_hpd_irq_event(connector->dev);
+}
+
 static int dp_display_send_hpd_notification(struct dp_display_private *dp,
 					    bool hpd)
 {
-	struct drm_bridge *bridge = dp->dp_display.bridge;
+	if ((hpd && dp->dp_display.link_ready) ||
+			(!hpd && !dp->dp_display.link_ready)) {
+		drm_dbg_dp(dp->drm_dev, "HPD already %s\n",
+				(hpd ? "on" : "off"));
+		return 0;
+	}
 
 	/* reset video pattern flag on disconnect */
 	if (!hpd) {
@@ -348,7 +364,7 @@ static int dp_display_send_hpd_notification(struct dp_display_private *dp,
 
 	drm_dbg_dp(dp->drm_dev, "type=%d hpd=%d\n",
 			dp->dp_display.connector_type, hpd);
-	drm_bridge_hpd_notify(bridge, dp->dp_display.link_ready);
+	dp_display_send_hpd_event(&dp->dp_display);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c
index 98427d45e9a7..49dfac1fd1ef 100644
--- a/drivers/gpu/drm/msm/dp/dp_link.c
+++ b/drivers/gpu/drm/msm/dp/dp_link.c
@@ -7,6 +7,7 @@
 
 #include <drm/drm_print.h>
 
+#include "dp_reg.h"
 #include "dp_link.h"
 #include "dp_panel.h"
 
@@ -1082,7 +1083,7 @@ int dp_link_process_request(struct dp_link *dp_link)
 
 int dp_link_get_colorimetry_config(struct dp_link *dp_link)
 {
-	u32 cc;
+	u32 cc = DP_MISC0_COLORIMERY_CFG_LEGACY_RGB;
 	struct dp_link_private *link;
 
 	if (!dp_link) {
@@ -1096,10 +1097,11 @@ int dp_link_get_colorimetry_config(struct dp_link *dp_link)
 	 * Unless a video pattern CTS test is ongoing, use RGB_VESA
 	 * Only RGB_VESA and RGB_CEA supported for now
 	 */
-	if (dp_link_is_video_pattern_requested(link))
-		cc = link->dp_link.test_video.test_dyn_range;
-	else
-		cc = DP_TEST_DYNAMIC_RANGE_VESA;
+	if (dp_link_is_video_pattern_requested(link)) {
+		if (link->dp_link.test_video.test_dyn_range &
+					DP_TEST_DYNAMIC_RANGE_CEA)
+			cc = DP_MISC0_COLORIMERY_CFG_CEA_RGB;
+	}
 
 	return cc;
 }
@@ -1179,6 +1181,9 @@ void dp_link_reset_phy_params_vx_px(struct dp_link *dp_link)
 u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp)
 {
 	u32 tbd;
+	struct dp_link_private *link;
+
+	link = container_of(dp_link, struct dp_link_private, dp_link);
 
 	/*
 	 * Few simplistic rules and assumptions made here:
@@ -1196,12 +1201,13 @@ u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp)
 		tbd = DP_TEST_BIT_DEPTH_10;
 		break;
 	default:
-		tbd = DP_TEST_BIT_DEPTH_UNKNOWN;
+		drm_dbg_dp(link->drm_dev, "bpp=%d not supported, use bpc=8\n",
+			   bpp);
+		tbd = DP_TEST_BIT_DEPTH_8;
 		break;
 	}
 
-	if (tbd != DP_TEST_BIT_DEPTH_UNKNOWN)
-		tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT);
+	tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT);
 
 	return tbd;
 }
diff --git a/drivers/gpu/drm/msm/dp/dp_reg.h b/drivers/gpu/drm/msm/dp/dp_reg.h
index ea85a691e72b..78785ed4b40c 100644
--- a/drivers/gpu/drm/msm/dp/dp_reg.h
+++ b/drivers/gpu/drm/msm/dp/dp_reg.h
@@ -143,6 +143,9 @@
 #define DP_MISC0_COLORIMETRY_CFG_SHIFT		(0x00000001)
 #define DP_MISC0_TEST_BITS_DEPTH_SHIFT		(0x00000005)
 
+#define DP_MISC0_COLORIMERY_CFG_LEGACY_RGB	(0)
+#define DP_MISC0_COLORIMERY_CFG_CEA_RGB		(0x04)
+
 #define REG_DP_VALID_BOUNDARY			(0x00000030)
 #define REG_DP_VALID_BOUNDARY_2			(0x00000034)
 
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c b/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c
index de182c004843..7aa500d24240 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c
@@ -249,7 +249,6 @@ struct i2c_adapter *msm_hdmi_i2c_init(struct hdmi *hdmi)
 
 
 	i2c->owner = THIS_MODULE;
-	i2c->class = I2C_CLASS_DDC;
 	snprintf(i2c->name, sizeof(i2c->name), "msm hdmi i2c");
 	i2c->dev.parent = &hdmi->pdev->dev;
 	i2c->algo = &msm_hdmi_i2c_algorithm;
diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c
index 5f68e31a3e4e..0915f3b68752 100644
--- a/drivers/gpu/drm/msm/msm_gem_prime.c
+++ b/drivers/gpu/drm/msm/msm_gem_prime.c
@@ -26,7 +26,7 @@ int msm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map)
 {
 	void *vaddr;
 
-	vaddr = msm_gem_get_vaddr(obj);
+	vaddr = msm_gem_get_vaddr_locked(obj);
 	if (IS_ERR(vaddr))
 		return PTR_ERR(vaddr);
 	iosys_map_set_vaddr(map, vaddr);
@@ -36,7 +36,7 @@ int msm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map)
 
 void msm_gem_prime_vunmap(struct drm_gem_object *obj, struct iosys_map *map)
 {
-	msm_gem_put_vaddr(obj);
+	msm_gem_put_vaddr_locked(obj);
 }
 
 struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev,
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 095390774f22..655002b21b0d 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -751,12 +751,14 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	struct msm_ringbuffer *ring = submit->ring;
 	unsigned long flags;
 
-	pm_runtime_get_sync(&gpu->pdev->dev);
+	WARN_ON(!mutex_is_locked(&gpu->lock));
 
-	mutex_lock(&gpu->lock);
+	pm_runtime_get_sync(&gpu->pdev->dev);
 
 	msm_gpu_hw_init(gpu);
 
+	submit->seqno = submit->hw_fence->seqno;
+
 	update_sw_cntrs(gpu);
 
 	/*
@@ -781,11 +783,8 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	gpu->funcs->submit(gpu, submit);
 	gpu->cur_ctx_seqno = submit->queue->ctx->seqno;
 
-	hangcheck_timer_reset(gpu);
-
-	mutex_unlock(&gpu->lock);
-
 	pm_runtime_put(&gpu->pdev->dev);
+	hangcheck_timer_reset(gpu);
 }
 
 /*
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 5cc8d358cc97..d5512037c38b 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -21,6 +21,8 @@ struct msm_iommu_pagetable {
 	struct msm_mmu base;
 	struct msm_mmu *parent;
 	struct io_pgtable_ops *pgtbl_ops;
+	const struct iommu_flush_ops *tlb;
+	struct device *iommu_dev;
 	unsigned long pgsize_bitmap;	/* Bitmap of page sizes in use */
 	phys_addr_t ttbr;
 	u32 asid;
@@ -201,11 +203,33 @@ static const struct msm_mmu_funcs pagetable_funcs = {
 
 static void msm_iommu_tlb_flush_all(void *cookie)
 {
+	struct msm_iommu_pagetable *pagetable = cookie;
+	struct adreno_smmu_priv *adreno_smmu;
+
+	if (!pm_runtime_get_if_in_use(pagetable->iommu_dev))
+		return;
+
+	adreno_smmu = dev_get_drvdata(pagetable->parent->dev);
+
+	pagetable->tlb->tlb_flush_all((void *)adreno_smmu->cookie);
+
+	pm_runtime_put_autosuspend(pagetable->iommu_dev);
 }
 
 static void msm_iommu_tlb_flush_walk(unsigned long iova, size_t size,
 		size_t granule, void *cookie)
 {
+	struct msm_iommu_pagetable *pagetable = cookie;
+	struct adreno_smmu_priv *adreno_smmu;
+
+	if (!pm_runtime_get_if_in_use(pagetable->iommu_dev))
+		return;
+
+	adreno_smmu = dev_get_drvdata(pagetable->parent->dev);
+
+	pagetable->tlb->tlb_flush_walk(iova, size, granule, (void *)adreno_smmu->cookie);
+
+	pm_runtime_put_autosuspend(pagetable->iommu_dev);
 }
 
 static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
@@ -213,7 +237,7 @@ static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
 {
 }
 
-static const struct iommu_flush_ops null_tlb_ops = {
+static const struct iommu_flush_ops tlb_ops = {
 	.tlb_flush_all = msm_iommu_tlb_flush_all,
 	.tlb_flush_walk = msm_iommu_tlb_flush_walk,
 	.tlb_add_page = msm_iommu_tlb_add_page,
@@ -254,10 +278,10 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent)
 
 	/* The incoming cfg will have the TTBR1 quirk enabled */
 	ttbr0_cfg.quirks &= ~IO_PGTABLE_QUIRK_ARM_TTBR1;
-	ttbr0_cfg.tlb = &null_tlb_ops;
+	ttbr0_cfg.tlb = &tlb_ops;
 
 	pagetable->pgtbl_ops = alloc_io_pgtable_ops(ARM_64_LPAE_S1,
-		&ttbr0_cfg, iommu->domain);
+		&ttbr0_cfg, pagetable);
 
 	if (!pagetable->pgtbl_ops) {
 		kfree(pagetable);
@@ -279,6 +303,8 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent)
 
 	/* Needed later for TLB flush */
 	pagetable->parent = parent;
+	pagetable->tlb = ttbr1_cfg->tlb;
+	pagetable->iommu_dev = ttbr1_cfg->iommu_dev;
 	pagetable->pgsize_bitmap = ttbr0_cfg.pgsize_bitmap;
 	pagetable->ttbr = ttbr0_cfg.arm_lpae_s1_cfg.ttbr;
 
diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c
index 455b2e3a0cdd..35423d10aafa 100644
--- a/drivers/gpu/drm/msm/msm_mdss.c
+++ b/drivers/gpu/drm/msm/msm_mdss.c
@@ -562,6 +562,7 @@ static const struct msm_mdss_data sdm670_data = {
 	.ubwc_enc_version = UBWC_2_0,
 	.ubwc_dec_version = UBWC_2_0,
 	.highest_bank_bit = 1,
+	.reg_bus_bw = 76800,
 };
 
 static const struct msm_mdss_data sdm845_data = {
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 4bc13f7d005a..9d6655f96f0c 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -21,8 +21,6 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
 
 	msm_fence_init(submit->hw_fence, fctx);
 
-	submit->seqno = submit->hw_fence->seqno;
-
 	mutex_lock(&priv->lru.lock);
 
 	for (i = 0; i < submit->nr_bos; i++) {
@@ -35,8 +33,13 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
 
 	mutex_unlock(&priv->lru.lock);
 
+	/* TODO move submit path over to using a per-ring lock.. */
+	mutex_lock(&gpu->lock);
+
 	msm_gpu_submit(gpu, submit);
 
+	mutex_unlock(&gpu->lock);
+
 	return dma_fence_get(submit->hw_fence);
 }
 
diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig
index 1e6aaf95ff7c..ceef470c9fbf 100644
--- a/drivers/gpu/drm/nouveau/Kconfig
+++ b/drivers/gpu/drm/nouveau/Kconfig
@@ -100,3 +100,11 @@ config DRM_NOUVEAU_SVM
 	help
 	  Say Y here if you want to enable experimental support for
 	  Shared Virtual Memory (SVM).
+
+config DRM_NOUVEAU_GSP_DEFAULT
+	bool "Use GSP firmware for Turing/Ampere (needs firmware installed)"
+	depends on DRM_NOUVEAU
+	default n
+	help
+	  Say Y here if you want to use the GSP codepaths by default on
+	  Turing and Ampere GPUs.
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/client.h b/drivers/gpu/drm/nouveau/include/nvkm/core/client.h
index 0d9fc741a719..932c9fd0b2d8 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/client.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/client.h
@@ -11,6 +11,7 @@ struct nvkm_client {
 	u32 debug;
 
 	struct rb_root objroot;
+	spinlock_t obj_lock;
 
 	void *data;
 	int (*event)(u64 token, void *argv, u32 argc);
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
index d1437c08645f..6f5d376d8fcc 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
@@ -9,7 +9,7 @@
 #define GSP_PAGE_SIZE  BIT(GSP_PAGE_SHIFT)
 
 struct nvkm_gsp_mem {
-	u32 size;
+	size_t size;
 	void *data;
 	dma_addr_t addr;
 };
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index a04156ca8390..80f74ee0fc78 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -128,12 +128,14 @@ nouveau_abi16_chan_fini(struct nouveau_abi16 *abi16,
 	struct nouveau_abi16_ntfy *ntfy, *temp;
 
 	/* Cancel all jobs from the entity's queue. */
-	drm_sched_entity_fini(&chan->sched.entity);
+	if (chan->sched)
+		drm_sched_entity_fini(&chan->sched->entity);
 
 	if (chan->chan)
 		nouveau_channel_idle(chan->chan);
 
-	nouveau_sched_fini(&chan->sched);
+	if (chan->sched)
+		nouveau_sched_destroy(&chan->sched);
 
 	/* cleanup notifier state */
 	list_for_each_entry_safe(ntfy, temp, &chan->notifiers, head) {
@@ -197,6 +199,7 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS)
 	struct nouveau_cli *cli = nouveau_cli(file_priv);
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nvif_device *device = &drm->client.device;
+	struct nvkm_device *nvkm_device = nvxx_device(&drm->client.device);
 	struct nvkm_gr *gr = nvxx_gr(device);
 	struct drm_nouveau_getparam *getparam = data;
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
@@ -261,6 +264,14 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS)
 		getparam->value = nouveau_exec_push_max_from_ib_max(ib_max);
 		break;
 	}
+	case NOUVEAU_GETPARAM_VRAM_BAR_SIZE:
+		getparam->value = nvkm_device->func->resource_size(nvkm_device, 1);
+		break;
+	case NOUVEAU_GETPARAM_VRAM_USED: {
+		struct ttm_resource_manager *vram_mgr = ttm_manager_type(&drm->ttm.bdev, TTM_PL_VRAM);
+		getparam->value = (u64)ttm_resource_manager_usage(vram_mgr);
+		break;
+	}
 	default:
 		NV_PRINTK(dbg, cli, "unknown parameter %lld\n", getparam->param);
 		return -EINVAL;
@@ -337,10 +348,16 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS)
 	if (ret)
 		goto done;
 
-	ret = nouveau_sched_init(&chan->sched, drm, drm->sched_wq,
-				 chan->chan->dma.ib_max);
-	if (ret)
-		goto done;
+	/* If we're not using the VM_BIND uAPI, we don't need a scheduler.
+	 *
+	 * The client lock is already acquired by nouveau_abi16_get().
+	 */
+	if (nouveau_cli_uvmm(cli)) {
+		ret = nouveau_sched_create(&chan->sched, drm, drm->sched_wq,
+					   chan->chan->dma.ib_max);
+		if (ret)
+			goto done;
+	}
 
 	init->channel = chan->chan->chid;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.h b/drivers/gpu/drm/nouveau/nouveau_abi16.h
index 1f5e243c0c75..11c8c4a80079 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.h
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.h
@@ -26,7 +26,7 @@ struct nouveau_abi16_chan {
 	struct nouveau_bo *ntfy;
 	struct nouveau_vma *ntfy_vma;
 	struct nvkm_mm  heap;
-	struct nouveau_sched sched;
+	struct nouveau_sched *sched;
 };
 
 struct nouveau_abi16 {
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 6f6c31a9937b..a947e1d5f309 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -201,7 +201,8 @@ nouveau_cli_fini(struct nouveau_cli *cli)
 	WARN_ON(!list_empty(&cli->worker));
 
 	usif_client_fini(cli);
-	nouveau_sched_fini(&cli->sched);
+	if (cli->sched)
+		nouveau_sched_destroy(&cli->sched);
 	if (uvmm)
 		nouveau_uvmm_fini(uvmm);
 	nouveau_vmm_fini(&cli->svm);
@@ -311,7 +312,7 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname,
 	cli->mem = &mems[ret];
 
 	/* Don't pass in the (shared) sched_wq in order to let
-	 * nouveau_sched_init() create a dedicated one for VM_BIND jobs.
+	 * nouveau_sched_create() create a dedicated one for VM_BIND jobs.
 	 *
 	 * This is required to ensure that for VM_BIND jobs free_job() work and
 	 * run_job() work can always run concurrently and hence, free_job() work
@@ -320,7 +321,7 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname,
 	 * locks which indirectly or directly are held for allocations
 	 * elsewhere.
 	 */
-	ret = nouveau_sched_init(&cli->sched, drm, NULL, 1);
+	ret = nouveau_sched_create(&cli->sched, drm, NULL, 1);
 	if (ret)
 		goto done;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 8a6d94c8b163..e239c6bf4afa 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -98,7 +98,7 @@ struct nouveau_cli {
 		bool disabled;
 	} uvmm;
 
-	struct nouveau_sched sched;
+	struct nouveau_sched *sched;
 
 	const struct nvif_mclass *mem;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_exec.c b/drivers/gpu/drm/nouveau/nouveau_exec.c
index bc5d71b79ab2..e65c0ef23bc7 100644
--- a/drivers/gpu/drm/nouveau/nouveau_exec.c
+++ b/drivers/gpu/drm/nouveau/nouveau_exec.c
@@ -389,7 +389,7 @@ nouveau_exec_ioctl_exec(struct drm_device *dev,
 	if (ret)
 		goto out;
 
-	args.sched = &chan16->sched;
+	args.sched = chan16->sched;
 	args.file_priv = file_priv;
 	args.chan = chan;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index 5057d976fa57..93f08f9479d8 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -62,7 +62,7 @@ nouveau_fence_signal(struct nouveau_fence *fence)
 	if (test_bit(DMA_FENCE_FLAG_USER_BITS, &fence->base.flags)) {
 		struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
 
-		if (atomic_dec_and_test(&fctx->notify_ref))
+		if (!--fctx->notify_ref)
 			drop = 1;
 	}
 
@@ -103,7 +103,7 @@ nouveau_fence_context_kill(struct nouveau_fence_chan *fctx, int error)
 void
 nouveau_fence_context_del(struct nouveau_fence_chan *fctx)
 {
-	cancel_work_sync(&fctx->allow_block_work);
+	cancel_work_sync(&fctx->uevent_work);
 	nouveau_fence_context_kill(fctx, 0);
 	nvif_event_dtor(&fctx->event);
 	fctx->dead = 1;
@@ -146,12 +146,13 @@ nouveau_fence_update(struct nouveau_channel *chan, struct nouveau_fence_chan *fc
 	return drop;
 }
 
-static int
-nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc)
+static void
+nouveau_fence_uevent_work(struct work_struct *work)
 {
-	struct nouveau_fence_chan *fctx = container_of(event, typeof(*fctx), event);
+	struct nouveau_fence_chan *fctx = container_of(work, struct nouveau_fence_chan,
+						       uevent_work);
 	unsigned long flags;
-	int ret = NVIF_EVENT_KEEP;
+	int drop = 0;
 
 	spin_lock_irqsave(&fctx->lock, flags);
 	if (!list_empty(&fctx->pending)) {
@@ -161,23 +162,20 @@ nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc
 		fence = list_entry(fctx->pending.next, typeof(*fence), head);
 		chan = rcu_dereference_protected(fence->channel, lockdep_is_held(&fctx->lock));
 		if (nouveau_fence_update(chan, fctx))
-			ret = NVIF_EVENT_DROP;
+			drop = 1;
 	}
-	spin_unlock_irqrestore(&fctx->lock, flags);
+	if (drop)
+		nvif_event_block(&fctx->event);
 
-	return ret;
+	spin_unlock_irqrestore(&fctx->lock, flags);
 }
 
-static void
-nouveau_fence_work_allow_block(struct work_struct *work)
+static int
+nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc)
 {
-	struct nouveau_fence_chan *fctx = container_of(work, struct nouveau_fence_chan,
-						       allow_block_work);
-
-	if (atomic_read(&fctx->notify_ref) == 0)
-		nvif_event_block(&fctx->event);
-	else
-		nvif_event_allow(&fctx->event);
+	struct nouveau_fence_chan *fctx = container_of(event, typeof(*fctx), event);
+	schedule_work(&fctx->uevent_work);
+	return NVIF_EVENT_KEEP;
 }
 
 void
@@ -191,7 +189,7 @@ nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_cha
 	} args;
 	int ret;
 
-	INIT_WORK(&fctx->allow_block_work, nouveau_fence_work_allow_block);
+	INIT_WORK(&fctx->uevent_work, nouveau_fence_uevent_work);
 	INIT_LIST_HEAD(&fctx->flip);
 	INIT_LIST_HEAD(&fctx->pending);
 	spin_lock_init(&fctx->lock);
@@ -535,19 +533,15 @@ static bool nouveau_fence_enable_signaling(struct dma_fence *f)
 	struct nouveau_fence *fence = from_fence(f);
 	struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
 	bool ret;
-	bool do_work;
 
-	if (atomic_inc_return(&fctx->notify_ref) == 0)
-		do_work = true;
+	if (!fctx->notify_ref++)
+		nvif_event_allow(&fctx->event);
 
 	ret = nouveau_fence_no_signaling(f);
 	if (ret)
 		set_bit(DMA_FENCE_FLAG_USER_BITS, &fence->base.flags);
-	else if (atomic_dec_and_test(&fctx->notify_ref))
-		do_work = true;
-
-	if (do_work)
-		schedule_work(&fctx->allow_block_work);
+	else if (!--fctx->notify_ref)
+		nvif_event_block(&fctx->event);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h
index 28f5cf013b89..8bc065acfe35 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.h
@@ -3,7 +3,6 @@
 #define __NOUVEAU_FENCE_H__
 
 #include <linux/dma-fence.h>
-#include <linux/workqueue.h>
 #include <nvif/event.h>
 
 struct nouveau_drm;
@@ -45,10 +44,9 @@ struct nouveau_fence_chan {
 	u32 context;
 	char name[32];
 
+	struct work_struct uevent_work;
 	struct nvif_event event;
-	struct work_struct allow_block_work;
-	atomic_t notify_ref;
-	int dead, killed;
+	int notify_ref, dead, killed;
 };
 
 struct nouveau_fence_priv {
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 49c2bcbef129..5a887d67dc0e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -764,7 +764,7 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data,
 		return -ENOMEM;
 
 	if (unlikely(nouveau_cli_uvmm(cli)))
-		return -ENOSYS;
+		return nouveau_abi16_put(abi16, -ENOSYS);
 
 	list_for_each_entry(temp, &abi16->channels, head) {
 		if (temp->chan->chid == req->channel) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c
index dd98f6910f9c..32fa2e273965 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sched.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sched.c
@@ -398,7 +398,7 @@ static const struct drm_sched_backend_ops nouveau_sched_ops = {
 	.free_job = nouveau_sched_free_job,
 };
 
-int
+static int
 nouveau_sched_init(struct nouveau_sched *sched, struct nouveau_drm *drm,
 		   struct workqueue_struct *wq, u32 credit_limit)
 {
@@ -453,7 +453,30 @@ fail_wq:
 	return ret;
 }
 
-void
+int
+nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm,
+		     struct workqueue_struct *wq, u32 credit_limit)
+{
+	struct nouveau_sched *sched;
+	int ret;
+
+	sched = kzalloc(sizeof(*sched), GFP_KERNEL);
+	if (!sched)
+		return -ENOMEM;
+
+	ret = nouveau_sched_init(sched, drm, wq, credit_limit);
+	if (ret) {
+		kfree(sched);
+		return ret;
+	}
+
+	*psched = sched;
+
+	return 0;
+}
+
+
+static void
 nouveau_sched_fini(struct nouveau_sched *sched)
 {
 	struct drm_gpu_scheduler *drm_sched = &sched->base;
@@ -471,3 +494,14 @@ nouveau_sched_fini(struct nouveau_sched *sched)
 	if (sched->wq)
 		destroy_workqueue(sched->wq);
 }
+
+void
+nouveau_sched_destroy(struct nouveau_sched **psched)
+{
+	struct nouveau_sched *sched = *psched;
+
+	nouveau_sched_fini(sched);
+	kfree(sched);
+
+	*psched = NULL;
+}
diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.h b/drivers/gpu/drm/nouveau/nouveau_sched.h
index a6528f5981e6..e1f01a23e6f6 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sched.h
+++ b/drivers/gpu/drm/nouveau/nouveau_sched.h
@@ -111,8 +111,8 @@ struct nouveau_sched {
 	} job;
 };
 
-int nouveau_sched_init(struct nouveau_sched *sched, struct nouveau_drm *drm,
-		       struct workqueue_struct *wq, u32 credit_limit);
-void nouveau_sched_fini(struct nouveau_sched *sched);
+int nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm,
+			 struct workqueue_struct *wq, u32 credit_limit);
+void nouveau_sched_destroy(struct nouveau_sched **psched);
 
 #endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index cc03e0c22ff3..5e4565c5011a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -1011,7 +1011,7 @@ nouveau_svm_fault_buffer_ctor(struct nouveau_svm *svm, s32 oclass, int id)
 	if (ret)
 		return ret;
 
-	buffer->fault = kvcalloc(sizeof(*buffer->fault), buffer->entries, GFP_KERNEL);
+	buffer->fault = kvcalloc(buffer->entries, sizeof(*buffer->fault), GFP_KERNEL);
 	if (!buffer->fault)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
index 4f223c972c6a..0a0a11dc9ec0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
@@ -1740,7 +1740,7 @@ nouveau_uvmm_ioctl_vm_bind(struct drm_device *dev,
 	if (ret)
 		return ret;
 
-	args.sched = &cli->sched;
+	args.sched = cli->sched;
 	args.file_priv = file_priv;
 
 	ret = nouveau_uvmm_vm_bind(&args);
diff --git a/drivers/gpu/drm/nouveau/nouveau_vmm.c b/drivers/gpu/drm/nouveau/nouveau_vmm.c
index a6602c012671..3dda885df5b2 100644
--- a/drivers/gpu/drm/nouveau/nouveau_vmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_vmm.c
@@ -108,6 +108,9 @@ nouveau_vma_new(struct nouveau_bo *nvbo, struct nouveau_vmm *vmm,
 	} else {
 		ret = nvif_vmm_get(&vmm->vmm, PTES, false, mem->mem.page, 0,
 				   mem->mem.size, &tmp);
+		if (ret)
+			goto done;
+
 		vma->addr = tmp.addr;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/client.c b/drivers/gpu/drm/nouveau/nvkm/core/client.c
index ebdeb8eb9e77..c55662937ab2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/client.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/client.c
@@ -180,6 +180,7 @@ nvkm_client_new(const char *name, u64 device, const char *cfg, const char *dbg,
 	client->device = device;
 	client->debug = nvkm_dbgopt(dbg, "CLIENT");
 	client->objroot = RB_ROOT;
+	spin_lock_init(&client->obj_lock);
 	client->event = event;
 	INIT_LIST_HEAD(&client->umem);
 	spin_lock_init(&client->lock);
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/object.c b/drivers/gpu/drm/nouveau/nvkm/core/object.c
index 7c554c14e884..aea3ba72027a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/object.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/object.c
@@ -30,8 +30,10 @@ nvkm_object_search(struct nvkm_client *client, u64 handle,
 		   const struct nvkm_object_func *func)
 {
 	struct nvkm_object *object;
+	unsigned long flags;
 
 	if (handle) {
+		spin_lock_irqsave(&client->obj_lock, flags);
 		struct rb_node *node = client->objroot.rb_node;
 		while (node) {
 			object = rb_entry(node, typeof(*object), node);
@@ -40,9 +42,12 @@ nvkm_object_search(struct nvkm_client *client, u64 handle,
 			else
 			if (handle > object->object)
 				node = node->rb_right;
-			else
+			else {
+				spin_unlock_irqrestore(&client->obj_lock, flags);
 				goto done;
+			}
 		}
+		spin_unlock_irqrestore(&client->obj_lock, flags);
 		return ERR_PTR(-ENOENT);
 	} else {
 		object = &client->object;
@@ -57,30 +62,39 @@ done:
 void
 nvkm_object_remove(struct nvkm_object *object)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&object->client->obj_lock, flags);
 	if (!RB_EMPTY_NODE(&object->node))
 		rb_erase(&object->node, &object->client->objroot);
+	spin_unlock_irqrestore(&object->client->obj_lock, flags);
 }
 
 bool
 nvkm_object_insert(struct nvkm_object *object)
 {
-	struct rb_node **ptr = &object->client->objroot.rb_node;
+	struct rb_node **ptr;
 	struct rb_node *parent = NULL;
+	unsigned long flags;
 
+	spin_lock_irqsave(&object->client->obj_lock, flags);
+	ptr = &object->client->objroot.rb_node;
 	while (*ptr) {
 		struct nvkm_object *this = rb_entry(*ptr, typeof(*this), node);
 		parent = *ptr;
-		if (object->object < this->object)
+		if (object->object < this->object) {
 			ptr = &parent->rb_left;
-		else
-		if (object->object > this->object)
+		} else if (object->object > this->object) {
 			ptr = &parent->rb_right;
-		else
+		} else {
+			spin_unlock_irqrestore(&object->client->obj_lock, flags);
 			return false;
+		}
 	}
 
 	rb_link_node(&object->node, parent, ptr);
 	rb_insert_color(&object->node, &object->client->objroot);
+	spin_unlock_irqrestore(&object->client->obj_lock, flags);
 	return true;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c
index c8ce7ff18713..e74493a4569e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c
@@ -550,6 +550,10 @@ ga100_fifo_nonstall_ctor(struct nvkm_fifo *fifo)
 		struct nvkm_engn *engn = list_first_entry(&runl->engns, typeof(*engn), head);
 
 		runl->nonstall.vector = engn->func->nonstall(engn);
+
+		/* if no nonstall vector just keep going */
+		if (runl->nonstall.vector == -1)
+			continue;
 		if (runl->nonstall.vector < 0) {
 			RUNL_ERROR(runl, "nonstall %d", runl->nonstall.vector);
 			return runl->nonstall.vector;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c
index b903785056b5..3454c7d29502 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c
@@ -351,7 +351,7 @@ r535_engn_nonstall(struct nvkm_engn *engn)
 	int ret;
 
 	ret = nvkm_gsp_intr_nonstall(subdev->device->gsp, subdev->type, subdev->inst);
-	WARN_ON(ret < 0);
+	WARN_ON(ret == -ENOENT);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bar/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bar/r535.c
index 4135690326f4..3a30bea30e36 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bar/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bar/r535.c
@@ -168,12 +168,11 @@ r535_bar_new_(const struct nvkm_bar_func *hw, struct nvkm_device *device,
 	rm->flush = r535_bar_flush;
 
 	ret = gf100_bar_new_(rm, device, type, inst, &bar);
-	*pbar = bar;
 	if (ret) {
-		if (!bar)
-			kfree(rm);
+		kfree(rm);
 		return ret;
 	}
+	*pbar = bar;
 
 	bar->flushBAR2PhysMode = ioremap(device->func->resource_addr(device, 3), PAGE_SIZE);
 	if (!bar->flushBAR2PhysMode)
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
index 19188683c8fc..8c2bf1c16f2a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
@@ -154,11 +154,17 @@ shadow_fw_init(struct nvkm_bios *bios, const char *name)
 	return (void *)fw;
 }
 
+static void
+shadow_fw_release(void *fw)
+{
+	release_firmware(fw);
+}
+
 static const struct nvbios_source
 shadow_fw = {
 	.name = "firmware",
 	.init = shadow_fw_init,
-	.fini = (void(*)(void *))release_firmware,
+	.fini = shadow_fw_release,
 	.read = shadow_fw_read,
 	.rw = false,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/base.c
index 04bceaa28a19..da1bebb896f7 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/base.c
@@ -25,12 +25,8 @@ int
 nvkm_gsp_intr_nonstall(struct nvkm_gsp *gsp, enum nvkm_subdev_type type, int inst)
 {
 	for (int i = 0; i < gsp->intr_nr; i++) {
-		if (gsp->intr[i].type == type && gsp->intr[i].inst == inst) {
-			if (gsp->intr[i].nonstall != ~0)
-				return gsp->intr[i].nonstall;
-
-			return -EINVAL;
-		}
+		if (gsp->intr[i].type == type && gsp->intr[i].inst == inst)
+			return gsp->intr[i].nonstall;
 	}
 
 	return -ENOENT;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index 9ee58e2a0eb2..a73a5b589790 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -997,6 +997,32 @@ r535_gsp_rpc_get_gsp_static_info(struct nvkm_gsp *gsp)
 	return 0;
 }
 
+static void
+nvkm_gsp_mem_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_mem *mem)
+{
+	if (mem->data) {
+		/*
+		 * Poison the buffer to catch any unexpected access from
+		 * GSP-RM if the buffer was prematurely freed.
+		 */
+		memset(mem->data, 0xFF, mem->size);
+
+		dma_free_coherent(gsp->subdev.device->dev, mem->size, mem->data, mem->addr);
+		memset(mem, 0, sizeof(*mem));
+	}
+}
+
+static int
+nvkm_gsp_mem_ctor(struct nvkm_gsp *gsp, size_t size, struct nvkm_gsp_mem *mem)
+{
+	mem->size = size;
+	mem->data = dma_alloc_coherent(gsp->subdev.device->dev, size, &mem->addr, GFP_KERNEL);
+	if (WARN_ON(!mem->data))
+		return -ENOMEM;
+
+	return 0;
+}
+
 static int
 r535_gsp_postinit(struct nvkm_gsp *gsp)
 {
@@ -1024,6 +1050,11 @@ r535_gsp_postinit(struct nvkm_gsp *gsp)
 
 	nvkm_inth_allow(&gsp->subdev.inth);
 	nvkm_wr32(device, 0x110004, 0x00000040);
+
+	/* Release the DMA buffers that were needed only for boot and init */
+	nvkm_gsp_mem_dtor(gsp, &gsp->boot.fw);
+	nvkm_gsp_mem_dtor(gsp, &gsp->libos);
+
 	return ret;
 }
 
@@ -1078,7 +1109,6 @@ r535_gsp_rpc_set_registry(struct nvkm_gsp *gsp)
 	if (IS_ERR(rpc))
 		return PTR_ERR(rpc);
 
-	rpc->size = sizeof(*rpc);
 	rpc->numEntries = NV_GSP_REG_NUM_ENTRIES;
 
 	str_offset = offsetof(typeof(*rpc), entries[NV_GSP_REG_NUM_ENTRIES]);
@@ -1094,6 +1124,7 @@ r535_gsp_rpc_set_registry(struct nvkm_gsp *gsp)
 		strings += name_len;
 		str_offset += name_len;
 	}
+	rpc->size = str_offset;
 
 	return nvkm_gsp_rpc_wr(gsp, rpc, false);
 }
@@ -1532,27 +1563,6 @@ r535_gsp_msg_run_cpu_sequencer(void *priv, u32 fn, void *repv, u32 repc)
 	return 0;
 }
 
-static void
-nvkm_gsp_mem_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_mem *mem)
-{
-	if (mem->data) {
-		dma_free_coherent(gsp->subdev.device->dev, mem->size, mem->data, mem->addr);
-		mem->data = NULL;
-	}
-}
-
-static int
-nvkm_gsp_mem_ctor(struct nvkm_gsp *gsp, u32 size, struct nvkm_gsp_mem *mem)
-{
-	mem->size = size;
-	mem->data = dma_alloc_coherent(gsp->subdev.device->dev, size, &mem->addr, GFP_KERNEL);
-	if (WARN_ON(!mem->data))
-		return -ENOMEM;
-
-	return 0;
-}
-
-
 static int
 r535_gsp_booter_unload(struct nvkm_gsp *gsp, u32 mbox0, u32 mbox1)
 {
@@ -1938,20 +1948,20 @@ nvkm_gsp_radix3_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_radix3 *rx3)
  * See kgspCreateRadix3_IMPL
  */
 static int
-nvkm_gsp_radix3_sg(struct nvkm_device *device, struct sg_table *sgt, u64 size,
+nvkm_gsp_radix3_sg(struct nvkm_gsp *gsp, struct sg_table *sgt, u64 size,
 		   struct nvkm_gsp_radix3 *rx3)
 {
 	u64 addr;
 
 	for (int i = ARRAY_SIZE(rx3->mem) - 1; i >= 0; i--) {
 		u64 *ptes;
-		int idx;
+		size_t bufsize;
+		int ret, idx;
 
-		rx3->mem[i].size = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
-		rx3->mem[i].data = dma_alloc_coherent(device->dev, rx3->mem[i].size,
-						      &rx3->mem[i].addr, GFP_KERNEL);
-		if (WARN_ON(!rx3->mem[i].data))
-			return -ENOMEM;
+		bufsize = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
+		ret = nvkm_gsp_mem_ctor(gsp, bufsize, &rx3->mem[i]);
+		if (ret)
+			return ret;
 
 		ptes = rx3->mem[i].data;
 		if (i == 2) {
@@ -1991,7 +2001,7 @@ r535_gsp_fini(struct nvkm_gsp *gsp, bool suspend)
 		if (ret)
 			return ret;
 
-		ret = nvkm_gsp_radix3_sg(gsp->subdev.device, &gsp->sr.sgt, len, &gsp->sr.radix3);
+		ret = nvkm_gsp_radix3_sg(gsp, &gsp->sr.sgt, len, &gsp->sr.radix3);
 		if (ret)
 			return ret;
 
@@ -2150,6 +2160,13 @@ r535_gsp_dtor(struct nvkm_gsp *gsp)
 	mutex_destroy(&gsp->cmdq.mutex);
 
 	r535_gsp_dtor_fws(gsp);
+
+	nvkm_gsp_mem_dtor(gsp, &gsp->rmargs);
+	nvkm_gsp_mem_dtor(gsp, &gsp->wpr_meta);
+	nvkm_gsp_mem_dtor(gsp, &gsp->shm.mem);
+	nvkm_gsp_mem_dtor(gsp, &gsp->loginit);
+	nvkm_gsp_mem_dtor(gsp, &gsp->logintr);
+	nvkm_gsp_mem_dtor(gsp, &gsp->logrm);
 }
 
 int
@@ -2194,7 +2211,7 @@ r535_gsp_oneinit(struct nvkm_gsp *gsp)
 	memcpy(gsp->sig.data, data, size);
 
 	/* Build radix3 page table for ELF image. */
-	ret = nvkm_gsp_radix3_sg(device, &gsp->fw.mem.sgt, gsp->fw.len, &gsp->radix3);
+	ret = nvkm_gsp_radix3_sg(gsp, &gsp->fw.mem.sgt, gsp->fw.len, &gsp->radix3);
 	if (ret)
 		return ret;
 
@@ -2295,8 +2312,12 @@ r535_gsp_load(struct nvkm_gsp *gsp, int ver, const struct nvkm_gsp_fwif *fwif)
 {
 	struct nvkm_subdev *subdev = &gsp->subdev;
 	int ret;
+	bool enable_gsp = fwif->enable;
 
-	if (!nvkm_boolopt(subdev->device->cfgopt, "NvGspRm", fwif->enable))
+#if IS_ENABLED(CONFIG_DRM_NOUVEAU_GSP_DEFAULT)
+	enable_gsp = true;
+#endif
+	if (!nvkm_boolopt(subdev->device->cfgopt, "NvGspRm", enable_gsp))
 		return -EINVAL;
 
 	if ((ret = r535_gsp_load_fw(gsp, "gsp", fwif->ver, &gsp->fws.rm)) ||
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp10b.c
index e7e8fdf3adab..29682722b0b3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp10b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp10b.c
@@ -28,19 +28,14 @@ static void
 gp10b_ltc_init(struct nvkm_ltc *ltc)
 {
 	struct nvkm_device *device = ltc->subdev.device;
-	struct iommu_fwspec *spec;
+	u32 sid;
 
 	nvkm_wr32(device, 0x17e27c, ltc->ltc_nr);
 	nvkm_wr32(device, 0x17e000, ltc->ltc_nr);
 	nvkm_wr32(device, 0x100800, ltc->ltc_nr);
 
-	spec = dev_iommu_fwspec_get(device->dev);
-	if (spec) {
-		u32 sid = spec->ids[0] & 0xffff;
-
-		/* stream ID */
+	if (tegra_dev_iommu_get_stream_id(device->dev, &sid))
 		nvkm_wr32(device, 0x160000, sid << 2);
-	}
 }
 
 static const struct nvkm_ltc_func
diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig
index dad938cf6dec..8f3783742208 100644
--- a/drivers/gpu/drm/panel/Kconfig
+++ b/drivers/gpu/drm/panel/Kconfig
@@ -539,6 +539,8 @@ config DRM_PANEL_RAYDIUM_RM692E5
 	depends on OF
 	depends on DRM_MIPI_DSI
 	depends on BACKLIGHT_CLASS_DEVICE
+	select DRM_DISPLAY_DP_HELPER
+	select DRM_DISPLAY_HELPER
 	help
 	  Say Y here if you want to enable support for Raydium RM692E5-based
 	  display panels, such as the one found in the Fairphone 5 smartphone.
diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
index c4c0f08e9202..4945a1e787eb 100644
--- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
+++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
@@ -1768,11 +1768,11 @@ static const struct panel_desc starry_qfh032011_53g_desc = {
 };
 
 static const struct drm_display_mode starry_himax83102_j02_default_mode = {
-	.clock = 162850,
+	.clock = 162680,
 	.hdisplay = 1200,
-	.hsync_start = 1200 + 50,
-	.hsync_end = 1200 + 50 + 20,
-	.htotal = 1200 + 50 + 20 + 50,
+	.hsync_start = 1200 + 60,
+	.hsync_end = 1200 + 60 + 20,
+	.htotal = 1200 + 60 + 20 + 40,
 	.vdisplay = 1920,
 	.vsync_start = 1920 + 116,
 	.vsync_end = 1920 + 116 + 8,
diff --git a/drivers/gpu/drm/panel/panel-samsung-s6d7aa0.c b/drivers/gpu/drm/panel/panel-samsung-s6d7aa0.c
index ea5a85779382..f23d8832a1ad 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6d7aa0.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6d7aa0.c
@@ -309,7 +309,7 @@ static const struct s6d7aa0_panel_desc s6d7aa0_lsl080al02_desc = {
 	.off_func = s6d7aa0_lsl080al02_off,
 	.drm_mode = &s6d7aa0_lsl080al02_mode,
 	.mode_flags = MIPI_DSI_MODE_VSYNC_FLUSH | MIPI_DSI_MODE_VIDEO_NO_HFP,
-	.bus_flags = DRM_BUS_FLAG_DE_HIGH,
+	.bus_flags = 0,
 
 	.has_backlight = false,
 	.use_passwd3 = false,
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 2214cb09678c..d493ee735c73 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -3948,6 +3948,7 @@ static const struct panel_desc tianma_tm070jdhg30 = {
 	},
 	.bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG,
 	.connector_type = DRM_MODE_CONNECTOR_LVDS,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH,
 };
 
 static const struct panel_desc tianma_tm070jvhg33 = {
@@ -3960,6 +3961,7 @@ static const struct panel_desc tianma_tm070jvhg33 = {
 	},
 	.bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG,
 	.connector_type = DRM_MODE_CONNECTOR_LVDS,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH,
 };
 
 static const struct display_timing tianma_tm070rvhg71_timing = {
diff --git a/drivers/gpu/drm/radeon/radeon_i2c.c b/drivers/gpu/drm/radeon/radeon_i2c.c
index 314d066e68e9..3d174390a8af 100644
--- a/drivers/gpu/drm/radeon/radeon_i2c.c
+++ b/drivers/gpu/drm/radeon/radeon_i2c.c
@@ -918,7 +918,6 @@ struct radeon_i2c_chan *radeon_i2c_create(struct drm_device *dev,
 
 	i2c->rec = *rec;
 	i2c->adapter.owner = THIS_MODULE;
-	i2c->adapter.class = I2C_CLASS_DDC;
 	i2c->adapter.dev.parent = dev->dev;
 	i2c->dev = dev;
 	i2c_set_adapdata(&i2c->adapter, i2c);
diff --git a/drivers/gpu/drm/rockchip/inno_hdmi.c b/drivers/gpu/drm/rockchip/inno_hdmi.c
index f6d819803c0e..e6fbe040ccf6 100644
--- a/drivers/gpu/drm/rockchip/inno_hdmi.c
+++ b/drivers/gpu/drm/rockchip/inno_hdmi.c
@@ -792,7 +792,6 @@ static struct i2c_adapter *inno_hdmi_i2c_adapter(struct inno_hdmi *hdmi)
 	init_completion(&i2c->cmp);
 
 	adap = &i2c->adap;
-	adap->class = I2C_CLASS_DDC;
 	adap->owner = THIS_MODULE;
 	adap->dev.parent = hdmi->dev;
 	adap->dev.of_node = hdmi->dev->of_node;
diff --git a/drivers/gpu/drm/rockchip/rk3066_hdmi.c b/drivers/gpu/drm/rockchip/rk3066_hdmi.c
index 62e6d8187de7..95cd1b49eda8 100644
--- a/drivers/gpu/drm/rockchip/rk3066_hdmi.c
+++ b/drivers/gpu/drm/rockchip/rk3066_hdmi.c
@@ -715,7 +715,6 @@ static struct i2c_adapter *rk3066_hdmi_i2c_adapter(struct rk3066_hdmi *hdmi)
 	init_completion(&i2c->cmpltn);
 
 	adap = &i2c->adap;
-	adap->class = I2C_CLASS_DDC;
 	adap->owner = THIS_MODULE;
 	adap->dev.parent = hdmi->dev;
 	adap->dev.of_node = hdmi->dev->of_node;
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
index 574103fc79f9..fdd768bbd487 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
@@ -35,7 +35,6 @@
 
 #include "rockchip_drm_drv.h"
 #include "rockchip_drm_gem.h"
-#include "rockchip_drm_fb.h"
 #include "rockchip_drm_vop2.h"
 #include "rockchip_rgb.h"
 
@@ -1681,7 +1680,6 @@ static unsigned long rk3588_calc_cru_cfg(struct vop2_video_port *vp, int id,
 	unsigned long dclk_core_rate = v_pixclk >> 2;
 	unsigned long dclk_rate = v_pixclk;
 	unsigned long dclk_out_rate;
-	unsigned long if_dclk_rate;
 	unsigned long if_pixclk_rate;
 	int K = 1;
 
@@ -1696,8 +1694,8 @@ static unsigned long rk3588_calc_cru_cfg(struct vop2_video_port *vp, int id,
 		}
 
 		if_pixclk_rate = (dclk_core_rate << 1) / K;
-		if_dclk_rate = dclk_core_rate / K;
 		/*
+		 * if_dclk_rate = dclk_core_rate / K;
 		 * *if_pixclk_div = dclk_rate / if_pixclk_rate;
 		 * *if_dclk_div = dclk_rate / if_dclk_rate;
 		 */
@@ -1987,8 +1985,10 @@ static void vop2_crtc_atomic_enable(struct drm_crtc *crtc,
 		clock = vop2_set_intf_mux(vp, rkencoder->crtc_endpoint_id, polflags);
 	}
 
-	if (!clock)
+	if (!clock) {
+		vop2_unlock(vop2);
 		return;
+	}
 
 	if (vcstate->output_mode == ROCKCHIP_OUT_MODE_AAAA &&
 	    !(vp_data->feature & VOP2_VP_FEATURE_OUTPUT_10BIT))
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 550492a7a031..d442b893275b 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -1184,14 +1184,16 @@ static void drm_sched_run_job_work(struct work_struct *w)
 	if (READ_ONCE(sched->pause_submit))
 		return;
 
+	/* Find entity with a ready job */
 	entity = drm_sched_select_entity(sched);
 	if (!entity)
-		return;
+		return;	/* No more work */
 
 	sched_job = drm_sched_entity_pop_job(entity);
 	if (!sched_job) {
 		complete_all(&entity->entity_idle);
-		return;	/* No more work */
+		drm_sched_run_job_queue(sched);
+		return;
 	}
 
 	s_fence = sched_job->s_fence;
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_i2c.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_i2c.c
index d1a65a921f5a..f5f62eb0eeca 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_i2c.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_i2c.c
@@ -302,7 +302,6 @@ int sun4i_hdmi_i2c_create(struct device *dev, struct sun4i_hdmi *hdmi)
 		return -ENOMEM;
 
 	adap->owner = THIS_MODULE;
-	adap->class = I2C_CLASS_DDC;
 	adap->algo = &sun4i_hdmi_i2c_algorithm;
 	strscpy(adap->name, "sun4i_hdmi_i2c adapter", sizeof(adap->name));
 	i2c_set_adapdata(adap, hdmi);
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index ff36171c8fb7..03d1c76aec2d 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -960,7 +960,8 @@ int host1x_client_iommu_attach(struct host1x_client *client)
 	 * not the shared IOMMU domain, don't try to attach it to a different
 	 * domain. This allows using the IOMMU-backed DMA API.
 	 */
-	if (domain && domain != tegra->domain)
+	if (domain && domain->type != IOMMU_DOMAIN_IDENTITY &&
+	    domain != tegra->domain)
 		return 0;
 
 	if (tegra->domain) {
@@ -1242,9 +1243,26 @@ static int host1x_drm_probe(struct host1x_device *dev)
 
 	drm_mode_config_reset(drm);
 
-	err = drm_aperture_remove_framebuffers(&tegra_drm_driver);
-	if (err < 0)
-		goto hub;
+	/*
+	 * Only take over from a potential firmware framebuffer if any CRTCs
+	 * have been registered. This must not be a fatal error because there
+	 * are other accelerators that are exposed via this driver.
+	 *
+	 * Another case where this happens is on Tegra234 where the display
+	 * hardware is no longer part of the host1x complex, so this driver
+	 * will not expose any modesetting features.
+	 */
+	if (drm->mode_config.num_crtc > 0) {
+		err = drm_aperture_remove_framebuffers(&tegra_drm_driver);
+		if (err < 0)
+			goto hub;
+	} else {
+		/*
+		 * Indicate to userspace that this doesn't expose any display
+		 * capabilities.
+		 */
+		drm->driver_features &= ~(DRIVER_MODESET | DRIVER_ATOMIC);
+	}
 
 	err = drm_dev_register(drm, 0);
 	if (err < 0)
diff --git a/drivers/gpu/drm/tests/drm_buddy_test.c b/drivers/gpu/drm/tests/drm_buddy_test.c
index ea2af6bd9abe..e48863a44556 100644
--- a/drivers/gpu/drm/tests/drm_buddy_test.c
+++ b/drivers/gpu/drm/tests/drm_buddy_test.c
@@ -8,16 +8,308 @@
 
 #include <linux/prime_numbers.h>
 #include <linux/sched/signal.h>
+#include <linux/sizes.h>
 
 #include <drm/drm_buddy.h>
 
 #include "../lib/drm_random.h"
 
+static unsigned int random_seed;
+
 static inline u64 get_size(int order, u64 chunk_size)
 {
 	return (1 << order) * chunk_size;
 }
 
+static void drm_test_buddy_alloc_range_bias(struct kunit *test)
+{
+	u32 mm_size, ps, bias_size, bias_start, bias_end, bias_rem;
+	DRM_RND_STATE(prng, random_seed);
+	unsigned int i, count, *order;
+	struct drm_buddy mm;
+	LIST_HEAD(allocated);
+
+	bias_size = SZ_1M;
+	ps = roundup_pow_of_two(prandom_u32_state(&prng) % bias_size);
+	ps = max(SZ_4K, ps);
+	mm_size = (SZ_8M-1) & ~(ps-1); /* Multiple roots */
+
+	kunit_info(test, "mm_size=%u, ps=%u\n", mm_size, ps);
+
+	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, ps),
+			       "buddy_init failed\n");
+
+	count = mm_size / bias_size;
+	order = drm_random_order(count, &prng);
+	KUNIT_EXPECT_TRUE(test, order);
+
+	/*
+	 * Idea is to split the address space into uniform bias ranges, and then
+	 * in some random order allocate within each bias, using various
+	 * patterns within. This should detect if allocations leak out from a
+	 * given bias, for example.
+	 */
+
+	for (i = 0; i < count; i++) {
+		LIST_HEAD(tmp);
+		u32 size;
+
+		bias_start = order[i] * bias_size;
+		bias_end = bias_start + bias_size;
+		bias_rem = bias_size;
+
+		/* internal round_up too big */
+		KUNIT_ASSERT_TRUE_MSG(test,
+				      drm_buddy_alloc_blocks(&mm, bias_start,
+							     bias_end, bias_size + ps, bias_size,
+							     &allocated,
+							     DRM_BUDDY_RANGE_ALLOCATION),
+				      "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
+				      bias_start, bias_end, bias_size, bias_size);
+
+		/* size too big */
+		KUNIT_ASSERT_TRUE_MSG(test,
+				      drm_buddy_alloc_blocks(&mm, bias_start,
+							     bias_end, bias_size + ps, ps,
+							     &allocated,
+							     DRM_BUDDY_RANGE_ALLOCATION),
+				      "buddy_alloc didn't fail with bias(%x-%x), size=%u, ps=%u\n",
+				      bias_start, bias_end, bias_size + ps, ps);
+
+		/* bias range too small for size */
+		KUNIT_ASSERT_TRUE_MSG(test,
+				      drm_buddy_alloc_blocks(&mm, bias_start + ps,
+							     bias_end, bias_size, ps,
+							     &allocated,
+							     DRM_BUDDY_RANGE_ALLOCATION),
+				      "buddy_alloc didn't fail with bias(%x-%x), size=%u, ps=%u\n",
+				      bias_start + ps, bias_end, bias_size, ps);
+
+		/* bias misaligned */
+		KUNIT_ASSERT_TRUE_MSG(test,
+				      drm_buddy_alloc_blocks(&mm, bias_start + ps,
+							     bias_end - ps,
+							     bias_size >> 1, bias_size >> 1,
+							     &allocated,
+							     DRM_BUDDY_RANGE_ALLOCATION),
+				      "buddy_alloc h didn't fail with bias(%x-%x), size=%u, ps=%u\n",
+				      bias_start + ps, bias_end - ps, bias_size >> 1, bias_size >> 1);
+
+		/* single big page */
+		KUNIT_ASSERT_FALSE_MSG(test,
+				       drm_buddy_alloc_blocks(&mm, bias_start,
+							      bias_end, bias_size, bias_size,
+							      &tmp,
+							      DRM_BUDDY_RANGE_ALLOCATION),
+				       "buddy_alloc i failed with bias(%x-%x), size=%u, ps=%u\n",
+				       bias_start, bias_end, bias_size, bias_size);
+		drm_buddy_free_list(&mm, &tmp);
+
+		/* single page with internal round_up */
+		KUNIT_ASSERT_FALSE_MSG(test,
+				       drm_buddy_alloc_blocks(&mm, bias_start,
+							      bias_end, ps, bias_size,
+							      &tmp,
+							      DRM_BUDDY_RANGE_ALLOCATION),
+				       "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
+				       bias_start, bias_end, ps, bias_size);
+		drm_buddy_free_list(&mm, &tmp);
+
+		/* random size within */
+		size = max(round_up(prandom_u32_state(&prng) % bias_rem, ps), ps);
+		if (size)
+			KUNIT_ASSERT_FALSE_MSG(test,
+					       drm_buddy_alloc_blocks(&mm, bias_start,
+								      bias_end, size, ps,
+								      &tmp,
+								      DRM_BUDDY_RANGE_ALLOCATION),
+					       "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
+					       bias_start, bias_end, size, ps);
+
+		bias_rem -= size;
+		/* too big for current avail */
+		KUNIT_ASSERT_TRUE_MSG(test,
+				      drm_buddy_alloc_blocks(&mm, bias_start,
+							     bias_end, bias_rem + ps, ps,
+							     &allocated,
+							     DRM_BUDDY_RANGE_ALLOCATION),
+				      "buddy_alloc didn't fail with bias(%x-%x), size=%u, ps=%u\n",
+				      bias_start, bias_end, bias_rem + ps, ps);
+
+		if (bias_rem) {
+			/* random fill of the remainder */
+			size = max(round_up(prandom_u32_state(&prng) % bias_rem, ps), ps);
+			size = max(size, ps);
+
+			KUNIT_ASSERT_FALSE_MSG(test,
+					       drm_buddy_alloc_blocks(&mm, bias_start,
+								      bias_end, size, ps,
+								      &allocated,
+								      DRM_BUDDY_RANGE_ALLOCATION),
+					       "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
+					       bias_start, bias_end, size, ps);
+			/*
+			 * Intentionally allow some space to be left
+			 * unallocated, and ideally not always on the bias
+			 * boundaries.
+			 */
+			drm_buddy_free_list(&mm, &tmp);
+		} else {
+			list_splice_tail(&tmp, &allocated);
+		}
+	}
+
+	kfree(order);
+	drm_buddy_free_list(&mm, &allocated);
+	drm_buddy_fini(&mm);
+
+	/*
+	 * Something more free-form. Idea is to pick a random starting bias
+	 * range within the address space and then start filling it up. Also
+	 * randomly grow the bias range in both directions as we go along. This
+	 * should give us bias start/end which is not always uniform like above,
+	 * and in some cases will require the allocator to jump over already
+	 * allocated nodes in the middle of the address space.
+	 */
+
+	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, ps),
+			       "buddy_init failed\n");
+
+	bias_start = round_up(prandom_u32_state(&prng) % (mm_size - ps), ps);
+	bias_end = round_up(bias_start + prandom_u32_state(&prng) % (mm_size - bias_start), ps);
+	bias_end = max(bias_end, bias_start + ps);
+	bias_rem = bias_end - bias_start;
+
+	do {
+		u32 size = max(round_up(prandom_u32_state(&prng) % bias_rem, ps), ps);
+
+		KUNIT_ASSERT_FALSE_MSG(test,
+				       drm_buddy_alloc_blocks(&mm, bias_start,
+							      bias_end, size, ps,
+							      &allocated,
+							      DRM_BUDDY_RANGE_ALLOCATION),
+				       "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
+				       bias_start, bias_end, size, ps);
+		bias_rem -= size;
+
+		/*
+		 * Try to randomly grow the bias range in both directions, or
+		 * only one, or perhaps don't grow at all.
+		 */
+		do {
+			u32 old_bias_start = bias_start;
+			u32 old_bias_end = bias_end;
+
+			if (bias_start)
+				bias_start -= round_up(prandom_u32_state(&prng) % bias_start, ps);
+			if (bias_end != mm_size)
+				bias_end += round_up(prandom_u32_state(&prng) % (mm_size - bias_end), ps);
+
+			bias_rem += old_bias_start - bias_start;
+			bias_rem += bias_end - old_bias_end;
+		} while (!bias_rem && (bias_start || bias_end != mm_size));
+	} while (bias_rem);
+
+	KUNIT_ASSERT_EQ(test, bias_start, 0);
+	KUNIT_ASSERT_EQ(test, bias_end, mm_size);
+	KUNIT_ASSERT_TRUE_MSG(test,
+			      drm_buddy_alloc_blocks(&mm, bias_start, bias_end,
+						     ps, ps,
+						     &allocated,
+						     DRM_BUDDY_RANGE_ALLOCATION),
+			      "buddy_alloc passed with bias(%x-%x), size=%u\n",
+			      bias_start, bias_end, ps);
+
+	drm_buddy_free_list(&mm, &allocated);
+	drm_buddy_fini(&mm);
+}
+
+static void drm_test_buddy_alloc_contiguous(struct kunit *test)
+{
+	const unsigned long ps = SZ_4K, mm_size = 16 * 3 * SZ_4K;
+	unsigned long i, n_pages, total;
+	struct drm_buddy_block *block;
+	struct drm_buddy mm;
+	LIST_HEAD(left);
+	LIST_HEAD(middle);
+	LIST_HEAD(right);
+	LIST_HEAD(allocated);
+
+	KUNIT_EXPECT_FALSE(test, drm_buddy_init(&mm, mm_size, ps));
+
+	/*
+	 * Idea is to fragment the address space by alternating block
+	 * allocations between three different lists; one for left, middle and
+	 * right. We can then free a list to simulate fragmentation. In
+	 * particular we want to exercise the DRM_BUDDY_CONTIGUOUS_ALLOCATION,
+	 * including the try_harder path.
+	 */
+
+	i = 0;
+	n_pages = mm_size / ps;
+	do {
+		struct list_head *list;
+		int slot = i % 3;
+
+		if (slot == 0)
+			list = &left;
+		else if (slot == 1)
+			list = &middle;
+		else
+			list = &right;
+		KUNIT_ASSERT_FALSE_MSG(test,
+				       drm_buddy_alloc_blocks(&mm, 0, mm_size,
+							      ps, ps, list, 0),
+				       "buddy_alloc hit an error size=%lu\n",
+				       ps);
+	} while (++i < n_pages);
+
+	KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+							   3 * ps, ps, &allocated,
+							   DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+			       "buddy_alloc didn't error size=%lu\n", 3 * ps);
+
+	drm_buddy_free_list(&mm, &middle);
+	KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+							   3 * ps, ps, &allocated,
+							   DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+			       "buddy_alloc didn't error size=%lu\n", 3 * ps);
+	KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+							   2 * ps, ps, &allocated,
+							   DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+			       "buddy_alloc didn't error size=%lu\n", 2 * ps);
+
+	drm_buddy_free_list(&mm, &right);
+	KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+							   3 * ps, ps, &allocated,
+							   DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+			       "buddy_alloc didn't error size=%lu\n", 3 * ps);
+	/*
+	 * At this point we should have enough contiguous space for 2 blocks,
+	 * however they are never buddies (since we freed middle and right) so
+	 * will require the try_harder logic to find them.
+	 */
+	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+							    2 * ps, ps, &allocated,
+							    DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+			       "buddy_alloc hit an error size=%lu\n", 2 * ps);
+
+	drm_buddy_free_list(&mm, &left);
+	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+							    3 * ps, ps, &allocated,
+							    DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+			       "buddy_alloc hit an error size=%lu\n", 3 * ps);
+
+	total = 0;
+	list_for_each_entry(block, &allocated, link)
+		total += drm_buddy_block_size(&mm, block);
+
+	KUNIT_ASSERT_EQ(test, total, ps * 2 + ps * 3);
+
+	drm_buddy_free_list(&mm, &allocated);
+	drm_buddy_fini(&mm);
+}
+
 static void drm_test_buddy_alloc_pathological(struct kunit *test)
 {
 	u64 mm_size, size, start = 0;
@@ -275,16 +567,30 @@ static void drm_test_buddy_alloc_limit(struct kunit *test)
 	drm_buddy_fini(&mm);
 }
 
+static int drm_buddy_suite_init(struct kunit_suite *suite)
+{
+	while (!random_seed)
+		random_seed = get_random_u32();
+
+	kunit_info(suite, "Testing DRM buddy manager, with random_seed=0x%x\n",
+		   random_seed);
+
+	return 0;
+}
+
 static struct kunit_case drm_buddy_tests[] = {
 	KUNIT_CASE(drm_test_buddy_alloc_limit),
 	KUNIT_CASE(drm_test_buddy_alloc_optimistic),
 	KUNIT_CASE(drm_test_buddy_alloc_pessimistic),
 	KUNIT_CASE(drm_test_buddy_alloc_pathological),
+	KUNIT_CASE(drm_test_buddy_alloc_contiguous),
+	KUNIT_CASE(drm_test_buddy_alloc_range_bias),
 	{}
 };
 
 static struct kunit_suite drm_buddy_test_suite = {
 	.name = "drm_buddy",
+	.suite_init = drm_buddy_suite_init,
 	.test_cases = drm_buddy_tests,
 };
 
diff --git a/drivers/gpu/drm/tests/drm_mm_test.c b/drivers/gpu/drm/tests/drm_mm_test.c
index 4e9247cf9977..f37c0d765865 100644
--- a/drivers/gpu/drm/tests/drm_mm_test.c
+++ b/drivers/gpu/drm/tests/drm_mm_test.c
@@ -157,7 +157,7 @@ static void drm_test_mm_init(struct kunit *test)
 
 	/* After creation, it should all be one massive hole */
 	if (!assert_one_hole(test, &mm, 0, size)) {
-		KUNIT_FAIL(test, "");
+		KUNIT_FAIL(test, "mm not one hole on creation");
 		goto out;
 	}
 
@@ -171,14 +171,14 @@ static void drm_test_mm_init(struct kunit *test)
 
 	/* After filling the range entirely, there should be no holes */
 	if (!assert_no_holes(test, &mm)) {
-		KUNIT_FAIL(test, "");
+		KUNIT_FAIL(test, "mm has holes when filled");
 		goto out;
 	}
 
 	/* And then after emptying it again, the massive hole should be back */
 	drm_mm_remove_node(&tmp);
 	if (!assert_one_hole(test, &mm, 0, size)) {
-		KUNIT_FAIL(test, "");
+		KUNIT_FAIL(test, "mm does not have single hole after emptying");
 		goto out;
 	}
 
@@ -188,13 +188,13 @@ out:
 
 static void drm_test_mm_debug(struct kunit *test)
 {
+	struct drm_printer p = drm_debug_printer(test->name);
 	struct drm_mm mm;
 	struct drm_mm_node nodes[2];
 
 	/* Create a small drm_mm with a couple of nodes and a few holes, and
 	 * check that the debug iterator doesn't explode over a trivial drm_mm.
 	 */
-
 	drm_mm_init(&mm, 0, 4096);
 
 	memset(nodes, 0, sizeof(nodes));
@@ -209,6 +209,9 @@ static void drm_test_mm_debug(struct kunit *test)
 	KUNIT_ASSERT_FALSE_MSG(test, drm_mm_reserve_node(&mm, &nodes[1]),
 			       "failed to reserve node[0] {start=%lld, size=%lld)\n",
 			       nodes[0].start, nodes[0].size);
+
+	drm_mm_print(&mm, &p);
+	KUNIT_SUCCEED(test);
 }
 
 static bool expect_insert(struct kunit *test, struct drm_mm *mm,
diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c
index f5187b384ae9..76027960054f 100644
--- a/drivers/gpu/drm/ttm/ttm_device.c
+++ b/drivers/gpu/drm/ttm/ttm_device.c
@@ -95,11 +95,17 @@ static int ttm_global_init(void)
 	ttm_pool_mgr_init(num_pages);
 	ttm_tt_mgr_init(num_pages, num_dma32);
 
-	glob->dummy_read_page = alloc_page(__GFP_ZERO | GFP_DMA32);
+	glob->dummy_read_page = alloc_page(__GFP_ZERO | GFP_DMA32 |
+					   __GFP_NOWARN);
 
+	/* Retry without GFP_DMA32 for platforms DMA32 is not available */
 	if (unlikely(glob->dummy_read_page == NULL)) {
-		ret = -ENOMEM;
-		goto out;
+		glob->dummy_read_page = alloc_page(__GFP_ZERO);
+		if (unlikely(glob->dummy_read_page == NULL)) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		pr_warn("Using GFP_DMA32 fallback for dummy_read_page\n");
 	}
 
 	INIT_LIST_HEAD(&glob->device_list);
@@ -195,7 +201,7 @@ int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *func
 		    bool use_dma_alloc, bool use_dma32)
 {
 	struct ttm_global *glob = &ttm_glob;
-	int ret;
+	int ret, nid;
 
 	if (WARN_ON(vma_manager == NULL))
 		return -EINVAL;
@@ -215,7 +221,12 @@ int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *func
 
 	ttm_sys_man_init(bdev);
 
-	ttm_pool_init(&bdev->pool, dev, dev_to_node(dev), use_dma_alloc, use_dma32);
+	if (dev)
+		nid = dev_to_node(dev);
+	else
+		nid = NUMA_NO_NODE;
+
+	ttm_pool_init(&bdev->pool, dev, nid, use_dma_alloc, use_dma32);
 
 	bdev->vma_manager = vma_manager;
 	spin_lock_init(&bdev->lru_lock);
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index b62f420a9f96..112438d965ff 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -387,7 +387,7 @@ static void ttm_pool_free_range(struct ttm_pool *pool, struct ttm_tt *tt,
 				enum ttm_caching caching,
 				pgoff_t start_page, pgoff_t end_page)
 {
-	struct page **pages = tt->pages;
+	struct page **pages = &tt->pages[start_page];
 	unsigned int order;
 	pgoff_t i, nr;
 
diff --git a/drivers/gpu/drm/v3d/v3d_debugfs.c b/drivers/gpu/drm/v3d/v3d_debugfs.c
index f843a50d5dce..94eafcecc65b 100644
--- a/drivers/gpu/drm/v3d/v3d_debugfs.c
+++ b/drivers/gpu/drm/v3d/v3d_debugfs.c
@@ -62,9 +62,9 @@ static const struct v3d_reg_def v3d_core_reg_defs[] = {
 	REGDEF(33, 71, V3D_PTB_BPCA),
 	REGDEF(33, 71, V3D_PTB_BPCS),
 
-	REGDEF(33, 41, V3D_GMP_STATUS(33)),
-	REGDEF(33, 41, V3D_GMP_CFG(33)),
-	REGDEF(33, 41, V3D_GMP_VIO_ADDR(33)),
+	REGDEF(33, 42, V3D_GMP_STATUS(33)),
+	REGDEF(33, 42, V3D_GMP_CFG(33)),
+	REGDEF(33, 42, V3D_GMP_VIO_ADDR(33)),
 
 	REGDEF(33, 71, V3D_ERR_FDBGO),
 	REGDEF(33, 71, V3D_ERR_FDBGB),
@@ -74,13 +74,13 @@ static const struct v3d_reg_def v3d_core_reg_defs[] = {
 
 static const struct v3d_reg_def v3d_csd_reg_defs[] = {
 	REGDEF(41, 71, V3D_CSD_STATUS),
-	REGDEF(41, 41, V3D_CSD_CURRENT_CFG0(41)),
-	REGDEF(41, 41, V3D_CSD_CURRENT_CFG1(41)),
-	REGDEF(41, 41, V3D_CSD_CURRENT_CFG2(41)),
-	REGDEF(41, 41, V3D_CSD_CURRENT_CFG3(41)),
-	REGDEF(41, 41, V3D_CSD_CURRENT_CFG4(41)),
-	REGDEF(41, 41, V3D_CSD_CURRENT_CFG5(41)),
-	REGDEF(41, 41, V3D_CSD_CURRENT_CFG6(41)),
+	REGDEF(41, 42, V3D_CSD_CURRENT_CFG0(41)),
+	REGDEF(41, 42, V3D_CSD_CURRENT_CFG1(41)),
+	REGDEF(41, 42, V3D_CSD_CURRENT_CFG2(41)),
+	REGDEF(41, 42, V3D_CSD_CURRENT_CFG3(41)),
+	REGDEF(41, 42, V3D_CSD_CURRENT_CFG4(41)),
+	REGDEF(41, 42, V3D_CSD_CURRENT_CFG5(41)),
+	REGDEF(41, 42, V3D_CSD_CURRENT_CFG6(41)),
 	REGDEF(71, 71, V3D_CSD_CURRENT_CFG0(71)),
 	REGDEF(71, 71, V3D_CSD_CURRENT_CFG1(71)),
 	REGDEF(71, 71, V3D_CSD_CURRENT_CFG2(71)),
diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c
index fcff41dd2315..88f63d526b22 100644
--- a/drivers/gpu/drm/v3d/v3d_submit.c
+++ b/drivers/gpu/drm/v3d/v3d_submit.c
@@ -147,6 +147,13 @@ v3d_job_allocate(void **container, size_t size)
 	return 0;
 }
 
+static void
+v3d_job_deallocate(void **container)
+{
+	kfree(*container);
+	*container = NULL;
+}
+
 static int
 v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv,
 	     struct v3d_job *job, void (*free)(struct kref *ref),
@@ -273,8 +280,10 @@ v3d_setup_csd_jobs_and_bos(struct drm_file *file_priv,
 
 	ret = v3d_job_init(v3d, file_priv, &(*job)->base,
 			   v3d_job_free, args->in_sync, se, V3D_CSD);
-	if (ret)
+	if (ret) {
+		v3d_job_deallocate((void *)job);
 		return ret;
+	}
 
 	ret = v3d_job_allocate((void *)clean_job, sizeof(**clean_job));
 	if (ret)
@@ -282,8 +291,10 @@ v3d_setup_csd_jobs_and_bos(struct drm_file *file_priv,
 
 	ret = v3d_job_init(v3d, file_priv, *clean_job,
 			   v3d_job_free, 0, NULL, V3D_CACHE_CLEAN);
-	if (ret)
+	if (ret) {
+		v3d_job_deallocate((void *)clean_job);
 		return ret;
+	}
 
 	(*job)->args = *args;
 
@@ -860,8 +871,10 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 
 	ret = v3d_job_init(v3d, file_priv, &render->base,
 			   v3d_render_job_free, args->in_sync_rcl, &se, V3D_RENDER);
-	if (ret)
+	if (ret) {
+		v3d_job_deallocate((void *)&render);
 		goto fail;
+	}
 
 	render->start = args->rcl_start;
 	render->end = args->rcl_end;
@@ -874,8 +887,10 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 
 		ret = v3d_job_init(v3d, file_priv, &bin->base,
 				   v3d_job_free, args->in_sync_bcl, &se, V3D_BIN);
-		if (ret)
+		if (ret) {
+			v3d_job_deallocate((void *)&bin);
 			goto fail;
+		}
 
 		bin->start = args->bcl_start;
 		bin->end = args->bcl_end;
@@ -892,8 +907,10 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 
 		ret = v3d_job_init(v3d, file_priv, clean_job,
 				   v3d_job_free, 0, NULL, V3D_CACHE_CLEAN);
-		if (ret)
+		if (ret) {
+			v3d_job_deallocate((void *)&clean_job);
 			goto fail;
+		}
 
 		last_job = clean_job;
 	} else {
@@ -1015,8 +1032,10 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data,
 
 	ret = v3d_job_init(v3d, file_priv, &job->base,
 			   v3d_job_free, args->in_sync, &se, V3D_TFU);
-	if (ret)
+	if (ret) {
+		v3d_job_deallocate((void *)&job);
 		goto fail;
+	}
 
 	job->base.bo = kcalloc(ARRAY_SIZE(args->bo_handles),
 			       sizeof(*job->base.bo), GFP_KERNEL);
@@ -1233,8 +1252,10 @@ v3d_submit_cpu_ioctl(struct drm_device *dev, void *data,
 
 	ret = v3d_job_init(v3d, file_priv, &cpu_job->base,
 			   v3d_job_free, 0, &se, V3D_CPU);
-	if (ret)
+	if (ret) {
+		v3d_job_deallocate((void *)&cpu_job);
 		goto fail;
+	}
 
 	clean_job = cpu_job->indirect_csd.clean_job;
 	csd_job = cpu_job->indirect_csd.job;
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c
index f8e9abe647b9..9539aa28937f 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.c
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.c
@@ -94,6 +94,7 @@ static int virtio_gpu_probe(struct virtio_device *vdev)
 			goto err_free;
 	}
 
+	dma_set_max_seg_size(dev->dev, dma_max_mapping_size(dev->dev) ?: UINT_MAX);
 	ret = virtio_gpu_init(vdev, dev);
 	if (ret)
 		goto err_free;
diff --git a/drivers/gpu/drm/xe/Kconfig b/drivers/gpu/drm/xe/Kconfig
index 1cced50d8d8c..e36ae1f0d885 100644
--- a/drivers/gpu/drm/xe/Kconfig
+++ b/drivers/gpu/drm/xe/Kconfig
@@ -47,7 +47,7 @@ config DRM_XE
 
 config DRM_XE_DISPLAY
 	bool "Enable display support"
-	depends on DRM_XE && EXPERT && DRM_XE=m
+	depends on DRM_XE && DRM_XE=m
 	select FB_IOMEM_HELPERS
 	select I2C
 	select I2C_ALGOBIT
diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index 53bd2a8ba1ae..efcf0ab7a1a6 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -17,7 +17,6 @@ subdir-ccflags-y += $(call cc-option, -Wunused-const-variable)
 subdir-ccflags-y += $(call cc-option, -Wpacked-not-aligned)
 subdir-ccflags-y += $(call cc-option, -Wformat-overflow)
 subdir-ccflags-y += $(call cc-option, -Wformat-truncation)
-subdir-ccflags-y += $(call cc-option, -Wstringop-overflow)
 subdir-ccflags-y += $(call cc-option, -Wstringop-truncation)
 # The following turn off the warnings enabled by -Wextra
 ifeq ($(findstring 2, $(KBUILD_EXTRA_WARN)),)
diff --git a/drivers/gpu/drm/xe/abi/guc_actions_abi.h b/drivers/gpu/drm/xe/abi/guc_actions_abi.h
index 3062e0e0d467..79ba98a169f9 100644
--- a/drivers/gpu/drm/xe/abi/guc_actions_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_actions_abi.h
@@ -50,8 +50,8 @@
 
 #define HOST2GUC_SELF_CFG_REQUEST_MSG_LEN		(GUC_HXG_REQUEST_MSG_MIN_LEN + 3u)
 #define HOST2GUC_SELF_CFG_REQUEST_MSG_0_MBZ		GUC_HXG_REQUEST_MSG_0_DATA0
-#define HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_KEY		(0xffff << 16)
-#define HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_LEN		(0xffff << 0)
+#define HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_KEY		(0xffffu << 16)
+#define HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_LEN		(0xffffu << 0)
 #define HOST2GUC_SELF_CFG_REQUEST_MSG_2_VALUE32		GUC_HXG_REQUEST_MSG_n_DATAn
 #define HOST2GUC_SELF_CFG_REQUEST_MSG_3_VALUE64		GUC_HXG_REQUEST_MSG_n_DATAn
 
diff --git a/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h b/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h
index 811add10c30d..c165e26c0976 100644
--- a/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h
@@ -242,8 +242,8 @@ struct slpc_shared_data {
 		(HOST2GUC_PC_SLPC_REQUEST_REQUEST_MSG_MIN_LEN + \
 			HOST2GUC_PC_SLPC_EVENT_MAX_INPUT_ARGS)
 #define HOST2GUC_PC_SLPC_REQUEST_MSG_0_MBZ		GUC_HXG_REQUEST_MSG_0_DATA0
-#define HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ID		(0xff << 8)
-#define HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ARGC	(0xff << 0)
+#define HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ID		(0xffu << 8)
+#define HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ARGC	(0xffu << 0)
 #define HOST2GUC_PC_SLPC_REQUEST_MSG_N_EVENT_DATA_N	GUC_HXG_REQUEST_MSG_n_DATAn
 
 #endif
diff --git a/drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h b/drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h
index 3b83f907ece4..0b1146d0c997 100644
--- a/drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h
@@ -82,11 +82,11 @@ static_assert(sizeof(struct guc_ct_buffer_desc) == 64);
 #define GUC_CTB_HDR_LEN				1u
 #define GUC_CTB_MSG_MIN_LEN			GUC_CTB_HDR_LEN
 #define GUC_CTB_MSG_MAX_LEN			256u
-#define GUC_CTB_MSG_0_FENCE			(0xffff << 16)
-#define GUC_CTB_MSG_0_FORMAT			(0xf << 12)
+#define GUC_CTB_MSG_0_FENCE			(0xffffu << 16)
+#define GUC_CTB_MSG_0_FORMAT			(0xfu << 12)
 #define   GUC_CTB_FORMAT_HXG			0u
-#define GUC_CTB_MSG_0_RESERVED			(0xf << 8)
-#define GUC_CTB_MSG_0_NUM_DWORDS		(0xff << 0)
+#define GUC_CTB_MSG_0_RESERVED			(0xfu << 8)
+#define GUC_CTB_MSG_0_NUM_DWORDS		(0xffu << 0)
 
 /**
  * DOC: CTB HXG Message
diff --git a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
index 47094b9b044c..0400bc0fccdc 100644
--- a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
@@ -31,9 +31,9 @@
  */
 
 #define GUC_KLV_LEN_MIN				1u
-#define GUC_KLV_0_KEY				(0xffff << 16)
-#define GUC_KLV_0_LEN				(0xffff << 0)
-#define GUC_KLV_n_VALUE				(0xffffffff << 0)
+#define GUC_KLV_0_KEY				(0xffffu << 16)
+#define GUC_KLV_0_LEN				(0xffffu << 0)
+#define GUC_KLV_n_VALUE				(0xffffffffu << 0)
 
 /**
  * DOC: GuC Self Config KLVs
diff --git a/drivers/gpu/drm/xe/abi/guc_messages_abi.h b/drivers/gpu/drm/xe/abi/guc_messages_abi.h
index 3d199016cf88..29e414c82d56 100644
--- a/drivers/gpu/drm/xe/abi/guc_messages_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_messages_abi.h
@@ -40,18 +40,18 @@
  */
 
 #define GUC_HXG_MSG_MIN_LEN			1u
-#define GUC_HXG_MSG_0_ORIGIN			(0x1 << 31)
+#define GUC_HXG_MSG_0_ORIGIN			(0x1u << 31)
 #define   GUC_HXG_ORIGIN_HOST			0u
 #define   GUC_HXG_ORIGIN_GUC			1u
-#define GUC_HXG_MSG_0_TYPE			(0x7 << 28)
+#define GUC_HXG_MSG_0_TYPE			(0x7u << 28)
 #define   GUC_HXG_TYPE_REQUEST			0u
 #define   GUC_HXG_TYPE_EVENT			1u
 #define   GUC_HXG_TYPE_NO_RESPONSE_BUSY		3u
 #define   GUC_HXG_TYPE_NO_RESPONSE_RETRY	5u
 #define   GUC_HXG_TYPE_RESPONSE_FAILURE		6u
 #define   GUC_HXG_TYPE_RESPONSE_SUCCESS		7u
-#define GUC_HXG_MSG_0_AUX			(0xfffffff << 0)
-#define GUC_HXG_MSG_n_PAYLOAD			(0xffffffff << 0)
+#define GUC_HXG_MSG_0_AUX			(0xfffffffu << 0)
+#define GUC_HXG_MSG_n_PAYLOAD			(0xffffffffu << 0)
 
 /**
  * DOC: HXG Request
@@ -85,8 +85,8 @@
  */
 
 #define GUC_HXG_REQUEST_MSG_MIN_LEN		GUC_HXG_MSG_MIN_LEN
-#define GUC_HXG_REQUEST_MSG_0_DATA0		(0xfff << 16)
-#define GUC_HXG_REQUEST_MSG_0_ACTION		(0xffff << 0)
+#define GUC_HXG_REQUEST_MSG_0_DATA0		(0xfffu << 16)
+#define GUC_HXG_REQUEST_MSG_0_ACTION		(0xffffu << 0)
 #define GUC_HXG_REQUEST_MSG_n_DATAn		GUC_HXG_MSG_n_PAYLOAD
 
 /**
@@ -117,8 +117,8 @@
  */
 
 #define GUC_HXG_EVENT_MSG_MIN_LEN		GUC_HXG_MSG_MIN_LEN
-#define GUC_HXG_EVENT_MSG_0_DATA0		(0xfff << 16)
-#define GUC_HXG_EVENT_MSG_0_ACTION		(0xffff << 0)
+#define GUC_HXG_EVENT_MSG_0_DATA0		(0xfffu << 16)
+#define GUC_HXG_EVENT_MSG_0_ACTION		(0xffffu << 0)
 #define GUC_HXG_EVENT_MSG_n_DATAn		GUC_HXG_MSG_n_PAYLOAD
 
 /**
@@ -188,8 +188,8 @@
  */
 
 #define GUC_HXG_FAILURE_MSG_LEN			GUC_HXG_MSG_MIN_LEN
-#define GUC_HXG_FAILURE_MSG_0_HINT		(0xfff << 16)
-#define GUC_HXG_FAILURE_MSG_0_ERROR		(0xffff << 0)
+#define GUC_HXG_FAILURE_MSG_0_HINT		(0xfffu << 16)
+#define GUC_HXG_FAILURE_MSG_0_ERROR		(0xffffu << 0)
 
 /**
  * DOC: HXG Response
diff --git a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h
index 5f19550cc845..777c20ceabab 100644
--- a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h
@@ -10,7 +10,7 @@
 
 #include "xe_bo.h"
 
-#define i915_gem_object_is_shmem(obj) ((obj)->flags & XE_BO_CREATE_SYSTEM_BIT)
+#define i915_gem_object_is_shmem(obj) (0) /* We don't use shmem */
 
 static inline dma_addr_t i915_gem_object_get_dma_address(const struct xe_bo *bo, pgoff_t n)
 {
@@ -35,12 +35,10 @@ static inline int i915_gem_object_read_from_page(struct xe_bo *bo,
 					  u32 ofs, u64 *ptr, u32 size)
 {
 	struct ttm_bo_kmap_obj map;
-	void *virtual;
+	void *src;
 	bool is_iomem;
 	int ret;
 
-	XE_WARN_ON(size != 8);
-
 	ret = xe_bo_lock(bo, true);
 	if (ret)
 		return ret;
@@ -50,11 +48,12 @@ static inline int i915_gem_object_read_from_page(struct xe_bo *bo,
 		goto out_unlock;
 
 	ofs &= ~PAGE_MASK;
-	virtual = ttm_kmap_obj_virtual(&map, &is_iomem);
+	src = ttm_kmap_obj_virtual(&map, &is_iomem);
+	src += ofs;
 	if (is_iomem)
-		*ptr = readq((void __iomem *)(virtual + ofs));
+		memcpy_fromio(ptr, (void __iomem *)src, size);
 	else
-		*ptr = *(u64 *)(virtual + ofs);
+		memcpy(ptr, src, size);
 
 	ttm_bo_kunmap(&map);
 out_unlock:
diff --git a/drivers/gpu/drm/xe/tests/xe_bo.c b/drivers/gpu/drm/xe/tests/xe_bo.c
index 412b2e7ce40c..3436fd9cf2b2 100644
--- a/drivers/gpu/drm/xe/tests/xe_bo.c
+++ b/drivers/gpu/drm/xe/tests/xe_bo.c
@@ -125,14 +125,13 @@ static void ccs_test_run_tile(struct xe_device *xe, struct xe_tile *tile,
 
 	bo = xe_bo_create_user(xe, NULL, NULL, SZ_1M, DRM_XE_GEM_CPU_CACHING_WC,
 			       ttm_bo_type_device, bo_flags);
-
-	xe_bo_lock(bo, false);
-
 	if (IS_ERR(bo)) {
 		KUNIT_FAIL(test, "Failed to create bo.\n");
 		return;
 	}
 
+	xe_bo_lock(bo, false);
+
 	kunit_info(test, "Verifying that CCS data is cleared on creation.\n");
 	ret = ccs_test_migrate(tile, bo, false, 0ULL, 0xdeadbeefdeadbeefULL,
 			       test);
diff --git a/drivers/gpu/drm/xe/tests/xe_migrate.c b/drivers/gpu/drm/xe/tests/xe_migrate.c
index 7a32faa2f688..c347e2c29f81 100644
--- a/drivers/gpu/drm/xe/tests/xe_migrate.c
+++ b/drivers/gpu/drm/xe/tests/xe_migrate.c
@@ -114,21 +114,21 @@ static void test_copy(struct xe_migrate *m, struct xe_bo *bo,
 						   region |
 						   XE_BO_NEEDS_CPU_ACCESS);
 	if (IS_ERR(remote)) {
-		KUNIT_FAIL(test, "Failed to allocate remote bo for %s: %li\n",
-			   str, PTR_ERR(remote));
+		KUNIT_FAIL(test, "Failed to allocate remote bo for %s: %pe\n",
+			   str, remote);
 		return;
 	}
 
 	err = xe_bo_validate(remote, NULL, false);
 	if (err) {
-		KUNIT_FAIL(test, "Failed to validate system bo for %s: %li\n",
+		KUNIT_FAIL(test, "Failed to validate system bo for %s: %i\n",
 			   str, err);
 		goto out_unlock;
 	}
 
 	err = xe_bo_vmap(remote);
 	if (err) {
-		KUNIT_FAIL(test, "Failed to vmap system bo for %s: %li\n",
+		KUNIT_FAIL(test, "Failed to vmap system bo for %s: %i\n",
 			   str, err);
 		goto out_unlock;
 	}
@@ -331,7 +331,7 @@ static void xe_migrate_sanity_test(struct xe_migrate *m, struct kunit *test)
 		xe_res_first_sg(xe_bo_sg(pt), 0, pt->size, &src_it);
 
 	emit_pte(m, bb, NUM_KERNEL_PDE - 1, xe_bo_is_vram(pt), false,
-		 &src_it, XE_PAGE_SIZE, pt);
+		 &src_it, XE_PAGE_SIZE, pt->ttm.resource);
 
 	run_sanity_job(m, xe, bb, bb->len, "Writing PTE for our fake PT", test);
 
diff --git a/drivers/gpu/drm/xe/tests/xe_mocs_test.c b/drivers/gpu/drm/xe/tests/xe_mocs_test.c
index ef56bd517b28..421b819fd4ba 100644
--- a/drivers/gpu/drm/xe/tests/xe_mocs_test.c
+++ b/drivers/gpu/drm/xe/tests/xe_mocs_test.c
@@ -21,4 +21,5 @@ kunit_test_suite(xe_mocs_test_suite);
 
 MODULE_AUTHOR("Intel Corporation");
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("xe_mocs kunit test");
 MODULE_IMPORT_NS(EXPORTED_FOR_KUNIT_TESTING);
diff --git a/drivers/gpu/drm/xe/tests/xe_wa_test.c b/drivers/gpu/drm/xe/tests/xe_wa_test.c
index a53c22a19582..b4715b78ef3b 100644
--- a/drivers/gpu/drm/xe/tests/xe_wa_test.c
+++ b/drivers/gpu/drm/xe/tests/xe_wa_test.c
@@ -74,9 +74,6 @@ static const struct platform_test_case cases[] = {
 	SUBPLATFORM_CASE(DG2, G11, B1),
 	SUBPLATFORM_CASE(DG2, G12, A0),
 	SUBPLATFORM_CASE(DG2, G12, A1),
-	PLATFORM_CASE(PVC, B0),
-	PLATFORM_CASE(PVC, B1),
-	PLATFORM_CASE(PVC, C0),
 	GMDID_CASE(METEORLAKE, 1270, A0, 1300, A0),
 	GMDID_CASE(METEORLAKE, 1271, A0, 1300, A0),
 	GMDID_CASE(LUNARLAKE, 2004, A0, 2000, A0),
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 8e4a3b1f6b93..4d3b80ec906d 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -28,6 +28,14 @@
 #include "xe_ttm_stolen_mgr.h"
 #include "xe_vm.h"
 
+const char *const xe_mem_type_to_name[TTM_NUM_MEM_TYPES]  = {
+	[XE_PL_SYSTEM] = "system",
+	[XE_PL_TT] = "gtt",
+	[XE_PL_VRAM0] = "vram0",
+	[XE_PL_VRAM1] = "vram1",
+	[XE_PL_STOLEN] = "stolen"
+};
+
 static const struct ttm_place sys_placement_flags = {
 	.fpfn = 0,
 	.lpfn = 0,
@@ -125,9 +133,9 @@ static struct xe_mem_region *res_to_mem_region(struct ttm_resource *res)
 static void try_add_system(struct xe_device *xe, struct xe_bo *bo,
 			   u32 bo_flags, u32 *c)
 {
-	xe_assert(xe, *c < ARRAY_SIZE(bo->placements));
-
 	if (bo_flags & XE_BO_CREATE_SYSTEM_BIT) {
+		xe_assert(xe, *c < ARRAY_SIZE(bo->placements));
+
 		bo->placements[*c] = (struct ttm_place) {
 			.mem_type = XE_PL_TT,
 		};
@@ -145,6 +153,8 @@ static void add_vram(struct xe_device *xe, struct xe_bo *bo,
 	struct xe_mem_region *vram;
 	u64 io_size;
 
+	xe_assert(xe, *c < ARRAY_SIZE(bo->placements));
+
 	vram = to_xe_ttm_vram_mgr(ttm_manager_type(&xe->ttm, mem_type))->vram;
 	xe_assert(xe, vram && vram->usable_size);
 	io_size = vram->io_size;
@@ -175,8 +185,6 @@ static void add_vram(struct xe_device *xe, struct xe_bo *bo,
 static void try_add_vram(struct xe_device *xe, struct xe_bo *bo,
 			 u32 bo_flags, u32 *c)
 {
-	xe_assert(xe, *c < ARRAY_SIZE(bo->placements));
-
 	if (bo->props.preferred_gt == XE_GT1) {
 		if (bo_flags & XE_BO_CREATE_VRAM1_BIT)
 			add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM1, c);
@@ -193,9 +201,9 @@ static void try_add_vram(struct xe_device *xe, struct xe_bo *bo,
 static void try_add_stolen(struct xe_device *xe, struct xe_bo *bo,
 			   u32 bo_flags, u32 *c)
 {
-	xe_assert(xe, *c < ARRAY_SIZE(bo->placements));
-
 	if (bo_flags & XE_BO_CREATE_STOLEN_BIT) {
+		xe_assert(xe, *c < ARRAY_SIZE(bo->placements));
+
 		bo->placements[*c] = (struct ttm_place) {
 			.mem_type = XE_PL_STOLEN,
 			.flags = bo_flags & (XE_BO_CREATE_PINNED_BIT |
@@ -442,7 +450,7 @@ static int xe_ttm_io_mem_reserve(struct ttm_device *bdev,
 
 		if (vram->mapping &&
 		    mem->placement & TTM_PL_FLAG_CONTIGUOUS)
-			mem->bus.addr = (u8 *)vram->mapping +
+			mem->bus.addr = (u8 __force *)vram->mapping +
 				mem->bus.offset;
 
 		mem->bus.offset += vram->io_start;
@@ -713,8 +721,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
 		migrate = xe->tiles[0].migrate;
 
 	xe_assert(xe, migrate);
-
-	trace_xe_bo_move(bo);
+	trace_xe_bo_move(bo, new_mem->mem_type, old_mem_type, move_lacks_source);
 	xe_device_mem_access_get(xe);
 
 	if (xe_bo_is_pinned(bo) && !xe_bo_is_user(bo)) {
@@ -734,7 +741,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
 			/* Create a new VMAP once kernel BO back in VRAM */
 			if (!ret && resource_is_vram(new_mem)) {
 				struct xe_mem_region *vram = res_to_mem_region(new_mem);
-				void *new_addr = vram->mapping +
+				void __iomem *new_addr = vram->mapping +
 					(new_mem->start << PAGE_SHIFT);
 
 				if (XE_WARN_ON(new_mem->start == XE_BO_INVALID_OFFSET)) {
diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h
index 9b1279aca127..8be42ac6cd07 100644
--- a/drivers/gpu/drm/xe/xe_bo.h
+++ b/drivers/gpu/drm/xe/xe_bo.h
@@ -243,6 +243,7 @@ int xe_bo_evict_pinned(struct xe_bo *bo);
 int xe_bo_restore_pinned(struct xe_bo *bo);
 
 extern struct ttm_device_funcs xe_ttm_funcs;
+extern const char *const xe_mem_type_to_name[];
 
 int xe_gem_create_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file);
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index d9ae77fe7382..5176c27e4b6a 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -83,9 +83,6 @@ static int xe_file_open(struct drm_device *dev, struct drm_file *file)
 	return 0;
 }
 
-static void device_kill_persistent_exec_queues(struct xe_device *xe,
-					       struct xe_file *xef);
-
 static void xe_file_close(struct drm_device *dev, struct drm_file *file)
 {
 	struct xe_device *xe = to_xe_device(dev);
@@ -102,8 +99,6 @@ static void xe_file_close(struct drm_device *dev, struct drm_file *file)
 	mutex_unlock(&xef->exec_queue.lock);
 	xa_destroy(&xef->exec_queue.xa);
 	mutex_destroy(&xef->exec_queue.lock);
-	device_kill_persistent_exec_queues(xe, xef);
-
 	mutex_lock(&xef->vm.lock);
 	xa_for_each(&xef->vm.xa, idx, vm)
 		xe_vm_close_and_put(vm);
@@ -255,9 +250,6 @@ struct xe_device *xe_device_create(struct pci_dev *pdev,
 			xa_erase(&xe->usm.asid_to_vm, asid);
 	}
 
-	drmm_mutex_init(&xe->drm, &xe->persistent_engines.lock);
-	INIT_LIST_HEAD(&xe->persistent_engines.list);
-
 	spin_lock_init(&xe->pinned.lock);
 	INIT_LIST_HEAD(&xe->pinned.kernel_bo_present);
 	INIT_LIST_HEAD(&xe->pinned.external_vram);
@@ -484,7 +476,7 @@ int xe_device_probe(struct xe_device *xe)
 
 	err = xe_device_set_has_flat_ccs(xe);
 	if (err)
-		return err;
+		goto err_irq_shutdown;
 
 	err = xe_mmio_probe_vram(xe);
 	if (err)
@@ -570,37 +562,6 @@ void xe_device_shutdown(struct xe_device *xe)
 {
 }
 
-void xe_device_add_persistent_exec_queues(struct xe_device *xe, struct xe_exec_queue *q)
-{
-	mutex_lock(&xe->persistent_engines.lock);
-	list_add_tail(&q->persistent.link, &xe->persistent_engines.list);
-	mutex_unlock(&xe->persistent_engines.lock);
-}
-
-void xe_device_remove_persistent_exec_queues(struct xe_device *xe,
-					     struct xe_exec_queue *q)
-{
-	mutex_lock(&xe->persistent_engines.lock);
-	if (!list_empty(&q->persistent.link))
-		list_del(&q->persistent.link);
-	mutex_unlock(&xe->persistent_engines.lock);
-}
-
-static void device_kill_persistent_exec_queues(struct xe_device *xe,
-					       struct xe_file *xef)
-{
-	struct xe_exec_queue *q, *next;
-
-	mutex_lock(&xe->persistent_engines.lock);
-	list_for_each_entry_safe(q, next, &xe->persistent_engines.list,
-				 persistent.link)
-		if (q->persistent.xef == xef) {
-			xe_exec_queue_kill(q);
-			list_del_init(&q->persistent.link);
-		}
-	mutex_unlock(&xe->persistent_engines.lock);
-}
-
 void xe_device_wmb(struct xe_device *xe)
 {
 	struct xe_gt *gt = xe_root_mmio_gt(xe);
@@ -613,7 +574,7 @@ void xe_device_wmb(struct xe_device *xe)
 u32 xe_device_ccs_bytes(struct xe_device *xe, u64 size)
 {
 	return xe_device_has_flat_ccs(xe) ?
-		DIV_ROUND_UP(size, NUM_BYTES_PER_CCS_BYTE(xe)) : 0;
+		DIV_ROUND_UP_ULL(size, NUM_BYTES_PER_CCS_BYTE(xe)) : 0;
 }
 
 bool xe_device_mem_access_ongoing(struct xe_device *xe)
diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
index 3da83b233206..08d8b72c7731 100644
--- a/drivers/gpu/drm/xe/xe_device.h
+++ b/drivers/gpu/drm/xe/xe_device.h
@@ -42,10 +42,6 @@ int xe_device_probe(struct xe_device *xe);
 void xe_device_remove(struct xe_device *xe);
 void xe_device_shutdown(struct xe_device *xe);
 
-void xe_device_add_persistent_exec_queues(struct xe_device *xe, struct xe_exec_queue *q);
-void xe_device_remove_persistent_exec_queues(struct xe_device *xe,
-					     struct xe_exec_queue *q);
-
 void xe_device_wmb(struct xe_device *xe);
 
 static inline struct xe_file *to_xe_file(const struct drm_file *file)
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index c45ef17b3473..e8491979a6f2 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -97,7 +97,7 @@ struct xe_mem_region {
 	 */
 	resource_size_t actual_physical_size;
 	/** @mapping: pointer to VRAM mappable space */
-	void *__iomem mapping;
+	void __iomem *mapping;
 };
 
 /**
@@ -146,7 +146,7 @@ struct xe_tile {
 		size_t size;
 
 		/** @regs: pointer to tile's MMIO space (starting with registers) */
-		void *regs;
+		void __iomem *regs;
 	} mmio;
 
 	/**
@@ -159,7 +159,7 @@ struct xe_tile {
 		size_t size;
 
 		/** @regs: pointer to tile's additional MMIO-extension space */
-		void *regs;
+		void __iomem *regs;
 	} mmio_ext;
 
 	/** @mem: memory management info for tile */
@@ -301,7 +301,7 @@ struct xe_device {
 		/** @size: size of MMIO space for device */
 		size_t size;
 		/** @regs: pointer to MMIO space for device */
-		void *regs;
+		void __iomem *regs;
 	} mmio;
 
 	/** @mem: memory info for device */
@@ -341,14 +341,6 @@ struct xe_device {
 		struct mutex lock;
 	} usm;
 
-	/** @persistent_engines: engines that are closed but still running */
-	struct {
-		/** @lock: protects persistent engines */
-		struct mutex lock;
-		/** @list: list of persistent engines */
-		struct list_head list;
-	} persistent_engines;
-
 	/** @pinned: pinned BO state */
 	struct {
 		/** @lock: protected pinned BO list state */
diff --git a/drivers/gpu/drm/xe/xe_display.c b/drivers/gpu/drm/xe/xe_display.c
index 74391d9b11ae..e4db069f0db3 100644
--- a/drivers/gpu/drm/xe/xe_display.c
+++ b/drivers/gpu/drm/xe/xe_display.c
@@ -134,8 +134,6 @@ static void xe_display_fini_nommio(struct drm_device *dev, void *dummy)
 
 int xe_display_init_nommio(struct xe_device *xe)
 {
-	int err;
-
 	if (!xe->info.enable_display)
 		return 0;
 
@@ -145,10 +143,6 @@ int xe_display_init_nommio(struct xe_device *xe)
 	/* This must be called before any calls to HAS_PCH_* */
 	intel_detect_pch(xe);
 
-	err = intel_power_domains_init(xe);
-	if (err)
-		return err;
-
 	return drmm_add_action_or_reset(&xe->drm, xe_display_fini_nommio, xe);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c
index 64ed303728fd..da2627ed6ae7 100644
--- a/drivers/gpu/drm/xe/xe_dma_buf.c
+++ b/drivers/gpu/drm/xe/xe_dma_buf.c
@@ -175,7 +175,7 @@ static int xe_dma_buf_begin_cpu_access(struct dma_buf *dma_buf,
 	return 0;
 }
 
-const struct dma_buf_ops xe_dmabuf_ops = {
+static const struct dma_buf_ops xe_dmabuf_ops = {
 	.attach = xe_dma_buf_attach,
 	.detach = xe_dma_buf_detach,
 	.pin = xe_dma_buf_pin,
diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c
index 82d1305e831f..6040e4d22b28 100644
--- a/drivers/gpu/drm/xe/xe_drm_client.c
+++ b/drivers/gpu/drm/xe/xe_drm_client.c
@@ -131,14 +131,6 @@ static void bo_meminfo(struct xe_bo *bo,
 
 static void show_meminfo(struct drm_printer *p, struct drm_file *file)
 {
-	static const char *const mem_type_to_name[TTM_NUM_MEM_TYPES]  = {
-		[XE_PL_SYSTEM] = "system",
-		[XE_PL_TT] = "gtt",
-		[XE_PL_VRAM0] = "vram0",
-		[XE_PL_VRAM1] = "vram1",
-		[4 ... 6] = NULL,
-		[XE_PL_STOLEN] = "stolen"
-	};
 	struct drm_memory_stats stats[TTM_NUM_MEM_TYPES] = {};
 	struct xe_file *xef = file->driver_priv;
 	struct ttm_device *bdev = &xef->xe->ttm;
@@ -171,7 +163,7 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file)
 	spin_unlock(&client->bos_lock);
 
 	for (mem_type = XE_PL_SYSTEM; mem_type < TTM_NUM_MEM_TYPES; ++mem_type) {
-		if (!mem_type_to_name[mem_type])
+		if (!xe_mem_type_to_name[mem_type])
 			continue;
 
 		man = ttm_manager_type(bdev, mem_type);
@@ -182,7 +174,7 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file)
 					       DRM_GEM_OBJECT_RESIDENT |
 					       (mem_type != XE_PL_SYSTEM ? 0 :
 					       DRM_GEM_OBJECT_PURGEABLE),
-					       mem_type_to_name[mem_type]);
+					       xe_mem_type_to_name[mem_type]);
 		}
 	}
 }
diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index d30c0d0689bc..17f26952e665 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -111,11 +111,11 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	u64 addresses[XE_HW_ENGINE_MAX_INSTANCE];
 	struct drm_gpuvm_exec vm_exec = {.extra.fn = xe_exec_fn};
 	struct drm_exec *exec = &vm_exec.exec;
-	u32 i, num_syncs = 0;
+	u32 i, num_syncs = 0, num_ufence = 0;
 	struct xe_sched_job *job;
 	struct dma_fence *rebind_fence;
 	struct xe_vm *vm;
-	bool write_locked;
+	bool write_locked, skip_retry = false;
 	ktime_t end = 0;
 	int err = 0;
 
@@ -157,6 +157,14 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 					   SYNC_PARSE_FLAG_LR_MODE : 0));
 		if (err)
 			goto err_syncs;
+
+		if (xe_sync_is_ufence(&syncs[i]))
+			num_ufence++;
+	}
+
+	if (XE_IOCTL_DBG(xe, num_ufence > 1)) {
+		err = -EINVAL;
+		goto err_syncs;
 	}
 
 	if (xe_exec_queue_is_parallel(q)) {
@@ -227,7 +235,8 @@ retry:
 	}
 
 	if (xe_exec_queue_is_lr(q) && xe_exec_queue_ring_full(q)) {
-		err = -EWOULDBLOCK;
+		err = -EWOULDBLOCK;	/* Aliased to -EAGAIN */
+		skip_retry = true;
 		goto err_exec;
 	}
 
@@ -337,7 +346,7 @@ err_unlock_list:
 		up_write(&vm->lock);
 	else
 		up_read(&vm->lock);
-	if (err == -EAGAIN)
+	if (err == -EAGAIN && !skip_retry)
 		goto retry;
 err_syncs:
 	for (i = 0; i < num_syncs; i++)
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 44fe8097b7cd..49223026c89f 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -60,13 +60,17 @@ static struct xe_exec_queue *__xe_exec_queue_create(struct xe_device *xe,
 	q->fence_irq = &gt->fence_irq[hwe->class];
 	q->ring_ops = gt->ring_ops[hwe->class];
 	q->ops = gt->exec_queue_ops;
-	INIT_LIST_HEAD(&q->persistent.link);
 	INIT_LIST_HEAD(&q->compute.link);
 	INIT_LIST_HEAD(&q->multi_gt_link);
 
 	q->sched_props.timeslice_us = hwe->eclass->sched_props.timeslice_us;
 	q->sched_props.preempt_timeout_us =
 				hwe->eclass->sched_props.preempt_timeout_us;
+	if (q->flags & EXEC_QUEUE_FLAG_KERNEL &&
+	    q->flags & EXEC_QUEUE_FLAG_HIGH_PRIORITY)
+		q->sched_props.priority = XE_EXEC_QUEUE_PRIORITY_KERNEL;
+	else
+		q->sched_props.priority = XE_EXEC_QUEUE_PRIORITY_NORMAL;
 
 	if (xe_exec_queue_is_parallel(q)) {
 		q->parallel.composite_fence_ctx = dma_fence_context_alloc(1);
@@ -305,102 +309,6 @@ static int exec_queue_set_timeslice(struct xe_device *xe, struct xe_exec_queue *
 	return q->ops->set_timeslice(q, value);
 }
 
-static int exec_queue_set_preemption_timeout(struct xe_device *xe,
-					     struct xe_exec_queue *q, u64 value,
-					     bool create)
-{
-	u32 min = 0, max = 0;
-
-	xe_exec_queue_get_prop_minmax(q->hwe->eclass,
-				      XE_EXEC_QUEUE_PREEMPT_TIMEOUT, &min, &max);
-
-	if (xe_exec_queue_enforce_schedule_limit() &&
-	    !xe_hw_engine_timeout_in_range(value, min, max))
-		return -EINVAL;
-
-	return q->ops->set_preempt_timeout(q, value);
-}
-
-static int exec_queue_set_persistence(struct xe_device *xe, struct xe_exec_queue *q,
-				      u64 value, bool create)
-{
-	if (XE_IOCTL_DBG(xe, !create))
-		return -EINVAL;
-
-	if (XE_IOCTL_DBG(xe, xe_vm_in_preempt_fence_mode(q->vm)))
-		return -EINVAL;
-
-	if (value)
-		q->flags |= EXEC_QUEUE_FLAG_PERSISTENT;
-	else
-		q->flags &= ~EXEC_QUEUE_FLAG_PERSISTENT;
-
-	return 0;
-}
-
-static int exec_queue_set_job_timeout(struct xe_device *xe, struct xe_exec_queue *q,
-				      u64 value, bool create)
-{
-	u32 min = 0, max = 0;
-
-	if (XE_IOCTL_DBG(xe, !create))
-		return -EINVAL;
-
-	xe_exec_queue_get_prop_minmax(q->hwe->eclass,
-				      XE_EXEC_QUEUE_JOB_TIMEOUT, &min, &max);
-
-	if (xe_exec_queue_enforce_schedule_limit() &&
-	    !xe_hw_engine_timeout_in_range(value, min, max))
-		return -EINVAL;
-
-	return q->ops->set_job_timeout(q, value);
-}
-
-static int exec_queue_set_acc_trigger(struct xe_device *xe, struct xe_exec_queue *q,
-				      u64 value, bool create)
-{
-	if (XE_IOCTL_DBG(xe, !create))
-		return -EINVAL;
-
-	if (XE_IOCTL_DBG(xe, !xe->info.has_usm))
-		return -EINVAL;
-
-	q->usm.acc_trigger = value;
-
-	return 0;
-}
-
-static int exec_queue_set_acc_notify(struct xe_device *xe, struct xe_exec_queue *q,
-				     u64 value, bool create)
-{
-	if (XE_IOCTL_DBG(xe, !create))
-		return -EINVAL;
-
-	if (XE_IOCTL_DBG(xe, !xe->info.has_usm))
-		return -EINVAL;
-
-	q->usm.acc_notify = value;
-
-	return 0;
-}
-
-static int exec_queue_set_acc_granularity(struct xe_device *xe, struct xe_exec_queue *q,
-					  u64 value, bool create)
-{
-	if (XE_IOCTL_DBG(xe, !create))
-		return -EINVAL;
-
-	if (XE_IOCTL_DBG(xe, !xe->info.has_usm))
-		return -EINVAL;
-
-	if (value > DRM_XE_ACC_GRANULARITY_64M)
-		return -EINVAL;
-
-	q->usm.acc_granularity = value;
-
-	return 0;
-}
-
 typedef int (*xe_exec_queue_set_property_fn)(struct xe_device *xe,
 					     struct xe_exec_queue *q,
 					     u64 value, bool create);
@@ -408,12 +316,6 @@ typedef int (*xe_exec_queue_set_property_fn)(struct xe_device *xe,
 static const xe_exec_queue_set_property_fn exec_queue_set_property_funcs[] = {
 	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY] = exec_queue_set_priority,
 	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE] = exec_queue_set_timeslice,
-	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_PREEMPTION_TIMEOUT] = exec_queue_set_preemption_timeout,
-	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_PERSISTENCE] = exec_queue_set_persistence,
-	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_JOB_TIMEOUT] = exec_queue_set_job_timeout,
-	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_TRIGGER] = exec_queue_set_acc_trigger,
-	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_NOTIFY] = exec_queue_set_acc_notify,
-	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_GRANULARITY] = exec_queue_set_acc_granularity,
 };
 
 static int exec_queue_user_ext_set_property(struct xe_device *xe,
@@ -432,10 +334,15 @@ static int exec_queue_user_ext_set_property(struct xe_device *xe,
 
 	if (XE_IOCTL_DBG(xe, ext.property >=
 			 ARRAY_SIZE(exec_queue_set_property_funcs)) ||
-	    XE_IOCTL_DBG(xe, ext.pad))
+	    XE_IOCTL_DBG(xe, ext.pad) ||
+	    XE_IOCTL_DBG(xe, ext.property != DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY &&
+			 ext.property != DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE))
 		return -EINVAL;
 
 	idx = array_index_nospec(ext.property, ARRAY_SIZE(exec_queue_set_property_funcs));
+	if (!exec_queue_set_property_funcs[idx])
+		return -EINVAL;
+
 	return exec_queue_set_property_funcs[idx](xe, q, ext.value,  create);
 }
 
@@ -699,9 +606,7 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
 		}
 
 		q = xe_exec_queue_create(xe, vm, logical_mask,
-					 args->width, hwe,
-					 xe_vm_in_lr_mode(vm) ? 0 :
-					 EXEC_QUEUE_FLAG_PERSISTENT);
+					 args->width, hwe, 0);
 		up_read(&vm->lock);
 		xe_vm_put(vm);
 		if (IS_ERR(q))
@@ -723,8 +628,6 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
 			goto kill_exec_queue;
 	}
 
-	q->persistent.xef = xef;
-
 	mutex_lock(&xef->exec_queue.lock);
 	err = xa_alloc(&xef->exec_queue.xa, &id, q, xa_limit_32b, GFP_KERNEL);
 	mutex_unlock(&xef->exec_queue.lock);
@@ -867,10 +770,7 @@ int xe_exec_queue_destroy_ioctl(struct drm_device *dev, void *data,
 	if (XE_IOCTL_DBG(xe, !q))
 		return -ENOENT;
 
-	if (!(q->flags & EXEC_QUEUE_FLAG_PERSISTENT))
-		xe_exec_queue_kill(q);
-	else
-		xe_device_add_persistent_exec_queues(xe, q);
+	xe_exec_queue_kill(q);
 
 	trace_xe_exec_queue_close(q);
 	xe_exec_queue_put(q);
@@ -921,20 +821,24 @@ void xe_exec_queue_last_fence_put_unlocked(struct xe_exec_queue *q)
  * @q: The exec queue
  * @vm: The VM the engine does a bind or exec for
  *
- * Get last fence, does not take a ref
+ * Get last fence, takes a ref
  *
  * Returns: last fence if not signaled, dma fence stub if signaled
  */
 struct dma_fence *xe_exec_queue_last_fence_get(struct xe_exec_queue *q,
 					       struct xe_vm *vm)
 {
+	struct dma_fence *fence;
+
 	xe_exec_queue_last_fence_lockdep_assert(q, vm);
 
 	if (q->last_fence &&
 	    test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &q->last_fence->flags))
 		xe_exec_queue_last_fence_put(q, vm);
 
-	return q->last_fence ? q->last_fence : dma_fence_get_stub();
+	fence = q->last_fence ? q->last_fence : dma_fence_get_stub();
+	dma_fence_get(fence);
+	return fence;
 }
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index 3d7e704ec3d9..36f4901d8d7e 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -52,8 +52,6 @@ struct xe_exec_queue {
 	struct xe_vm *vm;
 	/** @class: class of this exec queue */
 	enum xe_engine_class class;
-	/** @priority: priority of this exec queue */
-	enum xe_exec_queue_priority priority;
 	/**
 	 * @logical_mask: logical mask of where job submitted to exec queue can run
 	 */
@@ -84,6 +82,8 @@ struct xe_exec_queue {
 #define EXEC_QUEUE_FLAG_VM			BIT(4)
 /* child of VM queue for multi-tile VM jobs */
 #define EXEC_QUEUE_FLAG_BIND_ENGINE_CHILD	BIT(5)
+/* kernel exec_queue only, set priority to highest level */
+#define EXEC_QUEUE_FLAG_HIGH_PRIORITY		BIT(6)
 
 	/**
 	 * @flags: flags for this exec queue, should statically setup aside from ban
@@ -105,16 +105,6 @@ struct xe_exec_queue {
 		struct xe_guc_exec_queue *guc;
 	};
 
-	/**
-	 * @persistent: persistent exec queue state
-	 */
-	struct {
-		/** @xef: file which this exec queue belongs to */
-		struct xe_file *xef;
-		/** @link: link in list of persistent exec queues */
-		struct list_head link;
-	} persistent;
-
 	union {
 		/**
 		 * @parallel: parallel submission state
@@ -142,6 +132,8 @@ struct xe_exec_queue {
 		u32 timeslice_us;
 		/** @preempt_timeout_us: preemption timeout in micro-seconds */
 		u32 preempt_timeout_us;
+		/** @priority: priority of this exec queue */
+		enum xe_exec_queue_priority priority;
 	} sched_props;
 
 	/** @compute: compute exec queue state */
@@ -158,16 +150,6 @@ struct xe_exec_queue {
 		spinlock_t lock;
 	} compute;
 
-	/** @usm: unified shared memory state */
-	struct {
-		/** @acc_trigger: access counter trigger */
-		u32 acc_trigger;
-		/** @acc_notify: access counter notify */
-		u32 acc_notify;
-		/** @acc_granularity: access counter granularity */
-		u32 acc_granularity;
-	} usm;
-
 	/** @ops: submission backend exec queue operations */
 	const struct xe_exec_queue_ops *ops;
 
diff --git a/drivers/gpu/drm/xe/xe_execlist.c b/drivers/gpu/drm/xe/xe_execlist.c
index 96b5224eb478..acb4d9f38fd7 100644
--- a/drivers/gpu/drm/xe/xe_execlist.c
+++ b/drivers/gpu/drm/xe/xe_execlist.c
@@ -212,7 +212,7 @@ static void xe_execlist_port_wake_locked(struct xe_execlist_port *port,
 static void xe_execlist_make_active(struct xe_execlist_exec_queue *exl)
 {
 	struct xe_execlist_port *port = exl->port;
-	enum xe_exec_queue_priority priority = exl->active_priority;
+	enum xe_exec_queue_priority priority = exl->q->sched_props.priority;
 
 	XE_WARN_ON(priority == XE_EXEC_QUEUE_PRIORITY_UNSET);
 	XE_WARN_ON(priority < 0);
@@ -378,8 +378,6 @@ static void execlist_exec_queue_fini_async(struct work_struct *w)
 		list_del(&exl->active_link);
 	spin_unlock_irqrestore(&exl->port->lock, flags);
 
-	if (q->flags & EXEC_QUEUE_FLAG_PERSISTENT)
-		xe_device_remove_persistent_exec_queues(xe, q);
 	drm_sched_entity_fini(&exl->entity);
 	drm_sched_fini(&exl->sched);
 	kfree(exl);
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 3af2adec1295..35474ddbaf97 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -437,7 +437,10 @@ static int all_fw_domain_init(struct xe_gt *gt)
 		 * USM has its only SA pool to non-block behind user operations
 		 */
 		if (gt_to_xe(gt)->info.has_usm) {
-			gt->usm.bb_pool = xe_sa_bo_manager_init(gt_to_tile(gt), SZ_1M, 16);
+			struct xe_device *xe = gt_to_xe(gt);
+
+			gt->usm.bb_pool = xe_sa_bo_manager_init(gt_to_tile(gt),
+								IS_DGFX(xe) ? SZ_1M : SZ_512K, 16);
 			if (IS_ERR(gt->usm.bb_pool)) {
 				err = PTR_ERR(gt->usm.bb_pool);
 				goto err_force_wake;
diff --git a/drivers/gpu/drm/xe/xe_gt_freq.c b/drivers/gpu/drm/xe/xe_gt_freq.c
index 3adfa6686e7c..e5b0f4ecdbe8 100644
--- a/drivers/gpu/drm/xe/xe_gt_freq.c
+++ b/drivers/gpu/drm/xe/xe_gt_freq.c
@@ -196,6 +196,9 @@ void xe_gt_freq_init(struct xe_gt *gt)
 	struct xe_device *xe = gt_to_xe(gt);
 	int err;
 
+	if (xe->info.skip_guc_pc)
+		return;
+
 	gt->freq = kobject_create_and_add("freq0", gt->sysfs);
 	if (!gt->freq) {
 		drm_warn(&xe->drm, "failed to add freq0 directory to %s\n",
diff --git a/drivers/gpu/drm/xe/xe_gt_idle.c b/drivers/gpu/drm/xe/xe_gt_idle.c
index 9358f7336889..9fcae65b6469 100644
--- a/drivers/gpu/drm/xe/xe_gt_idle.c
+++ b/drivers/gpu/drm/xe/xe_gt_idle.c
@@ -145,10 +145,10 @@ void xe_gt_idle_sysfs_init(struct xe_gt_idle *gtidle)
 	}
 
 	if (xe_gt_is_media_type(gt)) {
-		sprintf(gtidle->name, "gt%d-mc\n", gt->info.id);
+		sprintf(gtidle->name, "gt%d-mc", gt->info.id);
 		gtidle->idle_residency = xe_guc_pc_mc6_residency;
 	} else {
-		sprintf(gtidle->name, "gt%d-rc\n", gt->info.id);
+		sprintf(gtidle->name, "gt%d-rc", gt->info.id);
 		gtidle->idle_residency = xe_guc_pc_rc6_residency;
 	}
 
diff --git a/drivers/gpu/drm/xe/xe_gt_mcr.c b/drivers/gpu/drm/xe/xe_gt_mcr.c
index 77925b35cf8d..8546cd3cc50d 100644
--- a/drivers/gpu/drm/xe/xe_gt_mcr.c
+++ b/drivers/gpu/drm/xe/xe_gt_mcr.c
@@ -480,7 +480,7 @@ static bool xe_gt_mcr_get_nonterminated_steering(struct xe_gt *gt,
  * to synchronize with external clients (e.g., firmware), so a semaphore
  * register will also need to be taken.
  */
-static void mcr_lock(struct xe_gt *gt)
+static void mcr_lock(struct xe_gt *gt) __acquires(&gt->mcr_lock)
 {
 	struct xe_device *xe = gt_to_xe(gt);
 	int ret = 0;
@@ -500,7 +500,7 @@ static void mcr_lock(struct xe_gt *gt)
 	drm_WARN_ON_ONCE(&xe->drm, ret == -ETIMEDOUT);
 }
 
-static void mcr_unlock(struct xe_gt *gt)
+static void mcr_unlock(struct xe_gt *gt) __releases(&gt->mcr_lock)
 {
 	/* Release hardware semaphore - this is done by writing 1 to the register */
 	if (GRAPHICS_VERx100(gt_to_xe(gt)) >= 1270)
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 59a70d2e0a7a..73f08f1924df 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -165,7 +165,8 @@ retry_userptr:
 		goto unlock_vm;
 	}
 
-	if (!xe_vma_is_userptr(vma) || !xe_vma_userptr_check_repin(vma)) {
+	if (!xe_vma_is_userptr(vma) ||
+	    !xe_vma_userptr_check_repin(to_userptr_vma(vma))) {
 		downgrade_write(&vm->lock);
 		write_locked = false;
 	}
@@ -181,11 +182,13 @@ retry_userptr:
 	/* TODO: Validate fault */
 
 	if (xe_vma_is_userptr(vma) && write_locked) {
+		struct xe_userptr_vma *uvma = to_userptr_vma(vma);
+
 		spin_lock(&vm->userptr.invalidated_lock);
-		list_del_init(&vma->userptr.invalidate_link);
+		list_del_init(&uvma->userptr.invalidate_link);
 		spin_unlock(&vm->userptr.invalidated_lock);
 
-		ret = xe_vma_userptr_pin_pages(vma);
+		ret = xe_vma_userptr_pin_pages(uvma);
 		if (ret)
 			goto unlock_vm;
 
@@ -220,7 +223,7 @@ retry_userptr:
 	dma_fence_put(fence);
 
 	if (xe_vma_is_userptr(vma))
-		ret = xe_vma_userptr_check_repin(vma);
+		ret = xe_vma_userptr_check_repin(to_userptr_vma(vma));
 	vma->usm.tile_invalidated &= ~BIT(tile->id);
 
 unlock_dma_resv:
@@ -332,7 +335,7 @@ int xe_guc_pagefault_handler(struct xe_guc *guc, u32 *msg, u32 len)
 		return -EPROTO;
 
 	asid = FIELD_GET(PFD_ASID, msg[1]);
-	pf_queue = &gt->usm.pf_queue[asid % NUM_PF_QUEUE];
+	pf_queue = gt->usm.pf_queue + (asid % NUM_PF_QUEUE);
 
 	spin_lock_irqsave(&pf_queue->lock, flags);
 	full = pf_queue_full(pf_queue);
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index 7eef23a00d77..f4c485289dbe 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -247,6 +247,14 @@ int xe_gt_tlb_invalidation_vma(struct xe_gt *gt,
 
 	xe_gt_assert(gt, vma);
 
+	/* Execlists not supported */
+	if (gt_to_xe(gt)->info.force_execlist) {
+		if (fence)
+			__invalidation_fence_signal(fence);
+
+		return 0;
+	}
+
 	action[len++] = XE_GUC_ACTION_TLB_INVALIDATION;
 	action[len++] = 0; /* seqno, replaced in send_tlb_invalidation */
 	if (!xe->info.has_range_tlb_invalidation) {
@@ -317,6 +325,10 @@ int xe_gt_tlb_invalidation_wait(struct xe_gt *gt, int seqno)
 	struct drm_printer p = drm_err_printer(__func__);
 	int ret;
 
+	/* Execlists not supported */
+	if (gt_to_xe(gt)->info.force_execlist)
+		return 0;
+
 	/*
 	 * XXX: See above, this algorithm only works if seqno are always in
 	 * order
diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
index 482cb0df9f15..0a61390c64a7 100644
--- a/drivers/gpu/drm/xe/xe_guc.c
+++ b/drivers/gpu/drm/xe/xe_guc.c
@@ -60,7 +60,12 @@ static u32 guc_ctl_debug_flags(struct xe_guc *guc)
 
 static u32 guc_ctl_feature_flags(struct xe_guc *guc)
 {
-	return GUC_CTL_ENABLE_SLPC;
+	u32 flags = 0;
+
+	if (!guc_to_xe(guc)->info.skip_guc_pc)
+		flags |= GUC_CTL_ENABLE_SLPC;
+
+	return flags;
 }
 
 static u32 guc_ctl_log_params_flags(struct xe_guc *guc)
diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index f71085228cb3..d91702592520 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -963,7 +963,9 @@ void xe_guc_pc_fini(struct xe_guc_pc *pc)
 	struct xe_device *xe = pc_to_xe(pc);
 
 	if (xe->info.skip_guc_pc) {
+		xe_device_mem_access_get(xe);
 		xe_gt_idle_disable_c6(pc_to_gt(pc));
+		xe_device_mem_access_put(xe);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 21ac68e3246f..f22ae717b0b2 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -421,7 +421,7 @@ static void init_policies(struct xe_guc *guc, struct xe_exec_queue *q)
 {
 	struct exec_queue_policy policy;
 	struct xe_device *xe = guc_to_xe(guc);
-	enum xe_exec_queue_priority prio = q->priority;
+	enum xe_exec_queue_priority prio = q->sched_props.priority;
 	u32 timeslice_us = q->sched_props.timeslice_us;
 	u32 preempt_timeout_us = q->sched_props.preempt_timeout_us;
 
@@ -1028,8 +1028,6 @@ static void __guc_exec_queue_fini_async(struct work_struct *w)
 
 	if (xe_exec_queue_is_lr(q))
 		cancel_work_sync(&ge->lr_tdr);
-	if (q->flags & EXEC_QUEUE_FLAG_PERSISTENT)
-		xe_device_remove_persistent_exec_queues(gt_to_xe(q->gt), q);
 	release_guc_id(guc, q);
 	xe_sched_entity_fini(&ge->entity);
 	xe_sched_fini(&ge->sched);
@@ -1231,7 +1229,6 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
 	err = xe_sched_entity_init(&ge->entity, sched);
 	if (err)
 		goto err_sched;
-	q->priority = XE_EXEC_QUEUE_PRIORITY_NORMAL;
 
 	if (xe_exec_queue_is_lr(q))
 		INIT_WORK(&q->guc->lr_tdr, xe_guc_exec_queue_lr_cleanup);
@@ -1301,15 +1298,15 @@ static int guc_exec_queue_set_priority(struct xe_exec_queue *q,
 {
 	struct xe_sched_msg *msg;
 
-	if (q->priority == priority || exec_queue_killed_or_banned(q))
+	if (q->sched_props.priority == priority || exec_queue_killed_or_banned(q))
 		return 0;
 
 	msg = kmalloc(sizeof(*msg), GFP_KERNEL);
 	if (!msg)
 		return -ENOMEM;
 
+	q->sched_props.priority = priority;
 	guc_exec_queue_add_msg(q, msg, SET_SCHED_PROPS);
-	q->priority = priority;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/xe/xe_hw_fence.c b/drivers/gpu/drm/xe/xe_hw_fence.c
index a6094c81f2ad..a5de3e7b0bd6 100644
--- a/drivers/gpu/drm/xe/xe_hw_fence.c
+++ b/drivers/gpu/drm/xe/xe_hw_fence.c
@@ -217,13 +217,13 @@ struct xe_hw_fence *xe_hw_fence_create(struct xe_hw_fence_ctx *ctx,
 	if (!fence)
 		return ERR_PTR(-ENOMEM);
 
-	dma_fence_init(&fence->dma, &xe_hw_fence_ops, &ctx->irq->lock,
-		       ctx->dma_fence_ctx, ctx->next_seqno++);
-
 	fence->ctx = ctx;
 	fence->seqno_map = seqno_map;
 	INIT_LIST_HEAD(&fence->irq_link);
 
+	dma_fence_init(&fence->dma, &xe_hw_fence_ops, &ctx->irq->lock,
+		       ctx->dma_fence_ctx, ctx->next_seqno++);
+
 	trace_xe_hw_fence_create(fence);
 
 	return fence;
diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c
index 6ef2aa1eae8b..174ed2185481 100644
--- a/drivers/gpu/drm/xe/xe_hwmon.c
+++ b/drivers/gpu/drm/xe/xe_hwmon.c
@@ -419,7 +419,7 @@ static int xe_hwmon_pcode_read_i1(struct xe_gt *gt, u32 *uval)
 
 	return xe_pcode_read(gt, PCODE_MBOX(PCODE_POWER_SETUP,
 			     POWER_SETUP_SUBCOMMAND_READ_I1, 0),
-			     uval, 0);
+			     uval, NULL);
 }
 
 static int xe_hwmon_pcode_write_i1(struct xe_gt *gt, u32 uval)
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index b7fa3831b684..b38319d2801e 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -21,10 +21,10 @@
 #include "xe_map.h"
 #include "xe_vm.h"
 
-#define CTX_VALID				(1 << 0)
-#define CTX_PRIVILEGE				(1 << 8)
-#define CTX_ADDRESSING_MODE_SHIFT		3
-#define LEGACY_64B_CONTEXT			3
+#define LRC_VALID				(1 << 0)
+#define LRC_PRIVILEGE				(1 << 8)
+#define LRC_ADDRESSING_MODE_SHIFT		3
+#define LRC_LEGACY_64B_CONTEXT			3
 
 #define ENGINE_CLASS_SHIFT			61
 #define ENGINE_INSTANCE_SHIFT			48
@@ -682,8 +682,6 @@ static void xe_lrc_set_ppgtt(struct xe_lrc *lrc, struct xe_vm *vm)
 
 #define PVC_CTX_ASID		(0x2e + 1)
 #define PVC_CTX_ACC_CTR_THOLD	(0x2a + 1)
-#define ACC_GRANULARITY_S       20
-#define ACC_NOTIFY_S            16
 
 int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 		struct xe_exec_queue *q, struct xe_vm *vm, u32 ring_size)
@@ -754,23 +752,17 @@ int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 	xe_lrc_write_ctx_reg(lrc, CTX_RING_CTL,
 			     RING_CTL_SIZE(lrc->ring.size) | RING_VALID);
 	if (xe->info.has_asid && vm)
-		xe_lrc_write_ctx_reg(lrc, PVC_CTX_ASID,
-				     (q->usm.acc_granularity <<
-				      ACC_GRANULARITY_S) | vm->usm.asid);
-	if (xe->info.has_usm && vm)
-		xe_lrc_write_ctx_reg(lrc, PVC_CTX_ACC_CTR_THOLD,
-				     (q->usm.acc_notify << ACC_NOTIFY_S) |
-				     q->usm.acc_trigger);
-
-	lrc->desc = CTX_VALID;
-	lrc->desc |= LEGACY_64B_CONTEXT << CTX_ADDRESSING_MODE_SHIFT;
+		xe_lrc_write_ctx_reg(lrc, PVC_CTX_ASID, vm->usm.asid);
+
+	lrc->desc = LRC_VALID;
+	lrc->desc |= LRC_LEGACY_64B_CONTEXT << LRC_ADDRESSING_MODE_SHIFT;
 	/* TODO: Priority */
 
 	/* While this appears to have something about privileged batches or
 	 * some such, it really just means PPGTT mode.
 	 */
 	if (vm)
-		lrc->desc |= CTX_PRIVILEGE;
+		lrc->desc |= LRC_PRIVILEGE;
 
 	if (GRAPHICS_VERx100(xe) < 1250) {
 		lrc->desc |= (u64)hwe->instance << ENGINE_INSTANCE_SHIFT;
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index adf1dab5eba2..70480c305602 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -62,6 +62,8 @@ struct xe_migrate {
 	 * out of the pt_bo.
 	 */
 	struct drm_suballoc_manager vm_update_sa;
+	/** @min_chunk_size: For dgfx, Minimum chunk size */
+	u64 min_chunk_size;
 };
 
 #define MAX_PREEMPTDISABLE_TRANSFER SZ_8M /* Around 1ms. */
@@ -168,11 +170,6 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 	if (!IS_DGFX(xe)) {
 		/* Write out batch too */
 		m->batch_base_ofs = NUM_PT_SLOTS * XE_PAGE_SIZE;
-		if (xe->info.has_usm) {
-			batch = tile->primary_gt->usm.bb_pool->bo;
-			m->usm_batch_base_ofs = m->batch_base_ofs;
-		}
-
 		for (i = 0; i < batch->size;
 		     i += vm->flags & XE_VM_FLAG_64K ? XE_64K_PAGE_SIZE :
 		     XE_PAGE_SIZE) {
@@ -183,6 +180,24 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 				  entry);
 			level++;
 		}
+		if (xe->info.has_usm) {
+			xe_tile_assert(tile, batch->size == SZ_1M);
+
+			batch = tile->primary_gt->usm.bb_pool->bo;
+			m->usm_batch_base_ofs = m->batch_base_ofs + SZ_1M;
+			xe_tile_assert(tile, batch->size == SZ_512K);
+
+			for (i = 0; i < batch->size;
+			     i += vm->flags & XE_VM_FLAG_64K ? XE_64K_PAGE_SIZE :
+			     XE_PAGE_SIZE) {
+				entry = vm->pt_ops->pte_encode_bo(batch, i,
+								  pat_index, 0);
+
+				xe_map_wr(xe, &bo->vmap, map_ofs + level * 8, u64,
+					  entry);
+				level++;
+			}
+		}
 	} else {
 		u64 batch_addr = xe_bo_addr(batch, 0, XE_PAGE_SIZE);
 
@@ -344,7 +359,8 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
 
 		m->q = xe_exec_queue_create(xe, vm, logical_mask, 1, hwe,
 					    EXEC_QUEUE_FLAG_KERNEL |
-					    EXEC_QUEUE_FLAG_PERMANENT);
+					    EXEC_QUEUE_FLAG_PERMANENT |
+					    EXEC_QUEUE_FLAG_HIGH_PRIORITY);
 	} else {
 		m->q = xe_exec_queue_create_class(xe, primary_gt, vm,
 						  XE_ENGINE_CLASS_COPY,
@@ -355,8 +371,6 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
 		xe_vm_close_and_put(vm);
 		return ERR_CAST(m->q);
 	}
-	if (xe->info.has_usm)
-		m->q->priority = XE_EXEC_QUEUE_PRIORITY_KERNEL;
 
 	mutex_init(&m->job_mutex);
 
@@ -364,6 +378,19 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
 	if (err)
 		return ERR_PTR(err);
 
+	if (IS_DGFX(xe)) {
+		if (xe_device_has_flat_ccs(xe))
+			/* min chunk size corresponds to 4K of CCS Metadata */
+			m->min_chunk_size = SZ_4K * SZ_64K /
+				xe_device_ccs_bytes(xe, SZ_64K);
+		else
+			/* Somewhat arbitrary to avoid a huge amount of blits */
+			m->min_chunk_size = SZ_64K;
+		m->min_chunk_size = roundup_pow_of_two(m->min_chunk_size);
+		drm_dbg(&xe->drm, "Migrate min chunk size is 0x%08llx\n",
+			(unsigned long long)m->min_chunk_size);
+	}
+
 	return m;
 }
 
@@ -375,16 +402,35 @@ static u64 max_mem_transfer_per_pass(struct xe_device *xe)
 	return MAX_PREEMPTDISABLE_TRANSFER;
 }
 
-static u64 xe_migrate_res_sizes(struct xe_device *xe, struct xe_res_cursor *cur)
+static u64 xe_migrate_res_sizes(struct xe_migrate *m, struct xe_res_cursor *cur)
 {
-	/*
-	 * For VRAM we use identity mapped pages so we are limited to current
-	 * cursor size. For system we program the pages ourselves so we have no
-	 * such limitation.
-	 */
-	return min_t(u64, max_mem_transfer_per_pass(xe),
-		     mem_type_is_vram(cur->mem_type) ? cur->size :
-		     cur->remaining);
+	struct xe_device *xe = tile_to_xe(m->tile);
+	u64 size = min_t(u64, max_mem_transfer_per_pass(xe), cur->remaining);
+
+	if (mem_type_is_vram(cur->mem_type)) {
+		/*
+		 * VRAM we want to blit in chunks with sizes aligned to
+		 * min_chunk_size in order for the offset to CCS metadata to be
+		 * page-aligned. If it's the last chunk it may be smaller.
+		 *
+		 * Another constraint is that we need to limit the blit to
+		 * the VRAM block size, unless size is smaller than
+		 * min_chunk_size.
+		 */
+		u64 chunk = max_t(u64, cur->size, m->min_chunk_size);
+
+		size = min_t(u64, size, chunk);
+		if (size > m->min_chunk_size)
+			size = round_down(size, m->min_chunk_size);
+	}
+
+	return size;
+}
+
+static bool xe_migrate_allow_identity(u64 size, const struct xe_res_cursor *cur)
+{
+	/* If the chunk is not fragmented, allow identity map. */
+	return cur->size >= size;
 }
 
 static u32 pte_update_size(struct xe_migrate *m,
@@ -397,7 +443,12 @@ static u32 pte_update_size(struct xe_migrate *m,
 	u32 cmds = 0;
 
 	*L0_pt = pt_ofs;
-	if (!is_vram) {
+	if (is_vram && xe_migrate_allow_identity(*L0, cur)) {
+		/* Offset into identity map. */
+		*L0_ofs = xe_migrate_vram_ofs(tile_to_xe(m->tile),
+					      cur->start + vram_region_gpu_offset(res));
+		cmds += cmd_size;
+	} else {
 		/* Clip L0 to available size */
 		u64 size = min(*L0, (u64)avail_pts * SZ_2M);
 		u64 num_4k_pages = DIV_ROUND_UP(size, XE_PAGE_SIZE);
@@ -413,11 +464,6 @@ static u32 pte_update_size(struct xe_migrate *m,
 
 		/* Each chunk has a single blit command */
 		cmds += cmd_size;
-	} else {
-		/* Offset into identity map. */
-		*L0_ofs = xe_migrate_vram_ofs(tile_to_xe(m->tile),
-					      cur->start + vram_region_gpu_offset(res));
-		cmds += cmd_size;
 	}
 
 	return cmds;
@@ -427,10 +473,10 @@ static void emit_pte(struct xe_migrate *m,
 		     struct xe_bb *bb, u32 at_pt,
 		     bool is_vram, bool is_comp_pte,
 		     struct xe_res_cursor *cur,
-		     u32 size, struct xe_bo *bo)
+		     u32 size, struct ttm_resource *res)
 {
 	struct xe_device *xe = tile_to_xe(m->tile);
-
+	struct xe_vm *vm = m->q->vm;
 	u16 pat_index;
 	u32 ptes;
 	u64 ofs = at_pt * XE_PAGE_SIZE;
@@ -439,17 +485,10 @@ static void emit_pte(struct xe_migrate *m,
 	/* Indirect access needs compression enabled uncached PAT index */
 	if (GRAPHICS_VERx100(xe) >= 2000)
 		pat_index = is_comp_pte ? xe->pat.idx[XE_CACHE_NONE_COMPRESSION] :
-					  xe->pat.idx[XE_CACHE_NONE];
+					  xe->pat.idx[XE_CACHE_WB];
 	else
 		pat_index = xe->pat.idx[XE_CACHE_WB];
 
-	/*
-	 * FIXME: Emitting VRAM PTEs to L0 PTs is forbidden. Currently
-	 * we're only emitting VRAM PTEs during sanity tests, so when
-	 * that's moved to a Kunit test, we should condition VRAM PTEs
-	 * on running tests.
-	 */
-
 	ptes = DIV_ROUND_UP(size, XE_PAGE_SIZE);
 
 	while (ptes) {
@@ -469,20 +508,22 @@ static void emit_pte(struct xe_migrate *m,
 
 			addr = xe_res_dma(cur) & PAGE_MASK;
 			if (is_vram) {
-				/* Is this a 64K PTE entry? */
-				if ((m->q->vm->flags & XE_VM_FLAG_64K) &&
-				    !(cur_ofs & (16 * 8 - 1))) {
-					xe_tile_assert(m->tile, IS_ALIGNED(addr, SZ_64K));
+				if (vm->flags & XE_VM_FLAG_64K) {
+					u64 va = cur_ofs * XE_PAGE_SIZE / 8;
+
+					xe_assert(xe, (va & (SZ_64K - 1)) ==
+						  (addr & (SZ_64K - 1)));
+
 					flags |= XE_PTE_PS64;
 				}
 
-				addr += vram_region_gpu_offset(bo->ttm.resource);
+				addr += vram_region_gpu_offset(res);
 				devmem = true;
 			}
 
-			addr = m->q->vm->pt_ops->pte_encode_addr(m->tile->xe,
-								 addr, pat_index,
-								 0, devmem, flags);
+			addr = vm->pt_ops->pte_encode_addr(m->tile->xe,
+							   addr, pat_index,
+							   0, devmem, flags);
 			bb->cs[bb->len++] = lower_32_bits(addr);
 			bb->cs[bb->len++] = upper_32_bits(addr);
 
@@ -694,8 +735,8 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 		bool usm = xe->info.has_usm;
 		u32 avail_pts = max_mem_transfer_per_pass(xe) / LEVEL0_PAGE_TABLE_ENCODE_SIZE;
 
-		src_L0 = xe_migrate_res_sizes(xe, &src_it);
-		dst_L0 = xe_migrate_res_sizes(xe, &dst_it);
+		src_L0 = xe_migrate_res_sizes(m, &src_it);
+		dst_L0 = xe_migrate_res_sizes(m, &dst_it);
 
 		drm_dbg(&xe->drm, "Pass %u, sizes: %llu & %llu\n",
 			pass++, src_L0, dst_L0);
@@ -716,6 +757,7 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 						      &ccs_ofs, &ccs_pt, 0,
 						      2 * avail_pts,
 						      avail_pts);
+			xe_assert(xe, IS_ALIGNED(ccs_it.start, PAGE_SIZE));
 		}
 
 		/* Add copy commands size here */
@@ -728,20 +770,20 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 			goto err_sync;
 		}
 
-		if (!src_is_vram)
-			emit_pte(m, bb, src_L0_pt, src_is_vram, true, &src_it, src_L0,
-				 src_bo);
-		else
+		if (src_is_vram && xe_migrate_allow_identity(src_L0, &src_it))
 			xe_res_next(&src_it, src_L0);
-
-		if (!dst_is_vram)
-			emit_pte(m, bb, dst_L0_pt, dst_is_vram, true, &dst_it, src_L0,
-				 dst_bo);
 		else
+			emit_pte(m, bb, src_L0_pt, src_is_vram, copy_system_ccs,
+				 &src_it, src_L0, src);
+
+		if (dst_is_vram && xe_migrate_allow_identity(src_L0, &dst_it))
 			xe_res_next(&dst_it, src_L0);
+		else
+			emit_pte(m, bb, dst_L0_pt, dst_is_vram, copy_system_ccs,
+				 &dst_it, src_L0, dst);
 
 		if (copy_system_ccs)
-			emit_pte(m, bb, ccs_pt, false, false, &ccs_it, ccs_size, src_bo);
+			emit_pte(m, bb, ccs_pt, false, false, &ccs_it, ccs_size, src);
 
 		bb->cs[bb->len++] = MI_BATCH_BUFFER_END;
 		update_idx = bb->len;
@@ -950,7 +992,7 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 		bool usm = xe->info.has_usm;
 		u32 avail_pts = max_mem_transfer_per_pass(xe) / LEVEL0_PAGE_TABLE_ENCODE_SIZE;
 
-		clear_L0 = xe_migrate_res_sizes(xe, &src_it);
+		clear_L0 = xe_migrate_res_sizes(m, &src_it);
 
 		drm_dbg(&xe->drm, "Pass %u, size: %llu\n", pass++, clear_L0);
 
@@ -977,12 +1019,12 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 
 		size -= clear_L0;
 		/* Preemption is enabled again by the ring ops. */
-		if (!clear_vram) {
-			emit_pte(m, bb, clear_L0_pt, clear_vram, true, &src_it, clear_L0,
-				 bo);
-		} else {
+		if (clear_vram && xe_migrate_allow_identity(clear_L0, &src_it))
 			xe_res_next(&src_it, clear_L0);
-		}
+		else
+			emit_pte(m, bb, clear_L0_pt, clear_vram, clear_system_ccs,
+				 &src_it, clear_L0, dst);
+
 		bb->cs[bb->len++] = MI_BATCH_BUFFER_END;
 		update_idx = bb->len;
 
@@ -1175,8 +1217,11 @@ static bool no_in_syncs(struct xe_vm *vm, struct xe_exec_queue *q,
 	}
 	if (q) {
 		fence = xe_exec_queue_last_fence_get(q, vm);
-		if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
+		if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
+			dma_fence_put(fence);
 			return false;
+		}
+		dma_fence_put(fence);
 	}
 
 	return true;
diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c
index f660cfb79f50..02f7808f28ca 100644
--- a/drivers/gpu/drm/xe/xe_mmio.c
+++ b/drivers/gpu/drm/xe/xe_mmio.c
@@ -105,7 +105,7 @@ static void xe_resize_vram_bar(struct xe_device *xe)
 
 	pci_bus_for_each_resource(root, root_res, i) {
 		if (root_res && root_res->flags & (IORESOURCE_MEM | IORESOURCE_MEM_64) &&
-		    root_res->start > 0x100000000ull)
+		    (u64)root_res->start > 0x100000000ul)
 			break;
 	}
 
@@ -272,8 +272,8 @@ int xe_mmio_probe_vram(struct xe_device *xe)
 		drm_info(&xe->drm, "VRAM[%u, %u]: Actual physical size %pa, usable size exclude stolen %pa, CPU accessible size %pa\n", id,
 			 tile->id, &tile->mem.vram.actual_physical_size, &tile->mem.vram.usable_size, &tile->mem.vram.io_size);
 		drm_info(&xe->drm, "VRAM[%u, %u]: DPA range: [%pa-%llx], io range: [%pa-%llx]\n", id, tile->id,
-			 &tile->mem.vram.dpa_base, tile->mem.vram.dpa_base + tile->mem.vram.actual_physical_size,
-			 &tile->mem.vram.io_start, tile->mem.vram.io_start + tile->mem.vram.io_size);
+			 &tile->mem.vram.dpa_base, tile->mem.vram.dpa_base + (u64)tile->mem.vram.actual_physical_size,
+			 &tile->mem.vram.io_start, tile->mem.vram.io_start + (u64)tile->mem.vram.io_size);
 
 		/* calculate total size using tile size to get the correct HW sizing */
 		total_size += tile_size;
@@ -303,7 +303,7 @@ void xe_mmio_probe_tiles(struct xe_device *xe)
 	u8 id, tile_count = xe->info.tile_count;
 	struct xe_gt *gt = xe_root_mmio_gt(xe);
 	struct xe_tile *tile;
-	void *regs;
+	void __iomem *regs;
 	u32 mtcfg;
 
 	if (tile_count == 1)
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index de1030a47588..6653c045f3c9 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -20,8 +20,8 @@
 
 struct xe_pt_dir {
 	struct xe_pt pt;
-	/** @dir: Directory structure for the xe_pt_walk functionality */
-	struct xe_ptw_dir dir;
+	/** @children: Array of page-table child nodes */
+	struct xe_ptw *children[XE_PDES];
 };
 
 #if IS_ENABLED(CONFIG_DRM_XE_DEBUG_VM)
@@ -44,7 +44,7 @@ static struct xe_pt_dir *as_xe_pt_dir(struct xe_pt *pt)
 
 static struct xe_pt *xe_pt_entry(struct xe_pt_dir *pt_dir, unsigned int index)
 {
-	return container_of(pt_dir->dir.entries[index], struct xe_pt, base);
+	return container_of(pt_dir->children[index], struct xe_pt, base);
 }
 
 static u64 __xe_pt_empty_pte(struct xe_tile *tile, struct xe_vm *vm,
@@ -65,6 +65,14 @@ static u64 __xe_pt_empty_pte(struct xe_tile *tile, struct xe_vm *vm,
 		XE_PTE_NULL;
 }
 
+static void xe_pt_free(struct xe_pt *pt)
+{
+	if (pt->level)
+		kfree(as_xe_pt_dir(pt));
+	else
+		kfree(pt);
+}
+
 /**
  * xe_pt_create() - Create a page-table.
  * @vm: The vm to create for.
@@ -85,15 +93,19 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile,
 {
 	struct xe_pt *pt;
 	struct xe_bo *bo;
-	size_t size;
 	int err;
 
-	size = !level ?  sizeof(struct xe_pt) : sizeof(struct xe_pt_dir) +
-		XE_PDES * sizeof(struct xe_ptw *);
-	pt = kzalloc(size, GFP_KERNEL);
+	if (level) {
+		struct xe_pt_dir *dir = kzalloc(sizeof(*dir), GFP_KERNEL);
+
+		pt = (dir) ? &dir->pt : NULL;
+	} else {
+		pt = kzalloc(sizeof(*pt), GFP_KERNEL);
+	}
 	if (!pt)
 		return ERR_PTR(-ENOMEM);
 
+	pt->level = level;
 	bo = xe_bo_create_pin_map(vm->xe, tile, vm, SZ_4K,
 				  ttm_bo_type_kernel,
 				  XE_BO_CREATE_VRAM_IF_DGFX(tile) |
@@ -106,8 +118,7 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile,
 		goto err_kfree;
 	}
 	pt->bo = bo;
-	pt->level = level;
-	pt->base.dir = level ? &as_xe_pt_dir(pt)->dir : NULL;
+	pt->base.children = level ? as_xe_pt_dir(pt)->children : NULL;
 
 	if (vm->xef)
 		xe_drm_client_add_bo(vm->xef->client, pt->bo);
@@ -116,7 +127,7 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile,
 	return pt;
 
 err_kfree:
-	kfree(pt);
+	xe_pt_free(pt);
 	return ERR_PTR(err);
 }
 
@@ -193,7 +204,7 @@ void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred)
 					      deferred);
 		}
 	}
-	kfree(pt);
+	xe_pt_free(pt);
 }
 
 /**
@@ -358,7 +369,7 @@ xe_pt_insert_entry(struct xe_pt_stage_bind_walk *xe_walk, struct xe_pt *parent,
 		struct iosys_map *map = &parent->bo->vmap;
 
 		if (unlikely(xe_child))
-			parent->base.dir->entries[offset] = &xe_child->base;
+			parent->base.children[offset] = &xe_child->base;
 
 		xe_pt_write(xe_walk->vm->xe, map, offset, pte);
 		parent->num_live++;
@@ -488,10 +499,12 @@ xe_pt_stage_bind_entry(struct xe_ptw *parent, pgoff_t offset,
 		 * this device *requires* 64K PTE size for VRAM, fail.
 		 */
 		if (level == 0 && !xe_parent->is_compact) {
-			if (xe_pt_is_pte_ps64K(addr, next, xe_walk))
+			if (xe_pt_is_pte_ps64K(addr, next, xe_walk)) {
+				xe_walk->vma->gpuva.flags |= XE_VMA_PTE_64K;
 				pte |= XE_PTE_PS64;
-			else if (XE_WARN_ON(xe_walk->needs_64K))
+			} else if (XE_WARN_ON(xe_walk->needs_64K)) {
 				return -EINVAL;
+			}
 		}
 
 		ret = xe_pt_insert_entry(xe_walk, xe_parent, offset, NULL, pte);
@@ -534,13 +547,16 @@ xe_pt_stage_bind_entry(struct xe_ptw *parent, pgoff_t offset,
 		*child = &xe_child->base;
 
 		/*
-		 * Prefer the compact pagetable layout for L0 if possible.
+		 * Prefer the compact pagetable layout for L0 if possible. Only
+		 * possible if VMA covers entire 2MB region as compact 64k and
+		 * 4k pages cannot be mixed within a 2MB region.
 		 * TODO: Suballocate the pt bo to avoid wasting a lot of
 		 * memory.
 		 */
 		if (GRAPHICS_VERx100(tile_to_xe(xe_walk->tile)) >= 1250 && level == 1 &&
 		    covers && xe_pt_scan_64K(addr, next, xe_walk)) {
 			walk->shifts = xe_compact_pt_shifts;
+			xe_walk->vma->gpuva.flags |= XE_VMA_PTE_COMPACT;
 			flags |= XE_PDE_64K;
 			xe_child->is_compact = true;
 		}
@@ -618,8 +634,8 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma,
 
 	if (!xe_vma_is_null(vma)) {
 		if (xe_vma_is_userptr(vma))
-			xe_res_first_sg(vma->userptr.sg, 0, xe_vma_size(vma),
-					&curs);
+			xe_res_first_sg(to_userptr_vma(vma)->userptr.sg, 0,
+					xe_vma_size(vma), &curs);
 		else if (xe_bo_is_vram(bo) || xe_bo_is_stolen(bo))
 			xe_res_first(bo->ttm.resource, xe_vma_bo_offset(vma),
 				     xe_vma_size(vma), &curs);
@@ -853,7 +869,7 @@ static void xe_pt_commit_bind(struct xe_vma *vma,
 				xe_pt_destroy(xe_pt_entry(pt_dir, j_),
 					      xe_vma_vm(vma)->flags, deferred);
 
-			pt_dir->dir.entries[j_] = &newpte->base;
+			pt_dir->children[j_] = &newpte->base;
 		}
 		kfree(entries[i].pt_entries);
 	}
@@ -906,17 +922,17 @@ static void xe_vm_dbg_print_entries(struct xe_device *xe,
 
 #ifdef CONFIG_DRM_XE_USERPTR_INVAL_INJECT
 
-static int xe_pt_userptr_inject_eagain(struct xe_vma *vma)
+static int xe_pt_userptr_inject_eagain(struct xe_userptr_vma *uvma)
 {
-	u32 divisor = vma->userptr.divisor ? vma->userptr.divisor : 2;
+	u32 divisor = uvma->userptr.divisor ? uvma->userptr.divisor : 2;
 	static u32 count;
 
 	if (count++ % divisor == divisor - 1) {
-		struct xe_vm *vm = xe_vma_vm(vma);
+		struct xe_vm *vm = xe_vma_vm(&uvma->vma);
 
-		vma->userptr.divisor = divisor << 1;
+		uvma->userptr.divisor = divisor << 1;
 		spin_lock(&vm->userptr.invalidated_lock);
-		list_move_tail(&vma->userptr.invalidate_link,
+		list_move_tail(&uvma->userptr.invalidate_link,
 			       &vm->userptr.invalidated);
 		spin_unlock(&vm->userptr.invalidated_lock);
 		return true;
@@ -927,7 +943,7 @@ static int xe_pt_userptr_inject_eagain(struct xe_vma *vma)
 
 #else
 
-static bool xe_pt_userptr_inject_eagain(struct xe_vma *vma)
+static bool xe_pt_userptr_inject_eagain(struct xe_userptr_vma *uvma)
 {
 	return false;
 }
@@ -1000,9 +1016,9 @@ static int xe_pt_userptr_pre_commit(struct xe_migrate_pt_update *pt_update)
 {
 	struct xe_pt_migrate_pt_update *userptr_update =
 		container_of(pt_update, typeof(*userptr_update), base);
-	struct xe_vma *vma = pt_update->vma;
-	unsigned long notifier_seq = vma->userptr.notifier_seq;
-	struct xe_vm *vm = xe_vma_vm(vma);
+	struct xe_userptr_vma *uvma = to_userptr_vma(pt_update->vma);
+	unsigned long notifier_seq = uvma->userptr.notifier_seq;
+	struct xe_vm *vm = xe_vma_vm(&uvma->vma);
 	int err = xe_pt_vm_dependencies(pt_update->job,
 					&vm->rftree[pt_update->tile_id],
 					pt_update->start,
@@ -1023,7 +1039,7 @@ static int xe_pt_userptr_pre_commit(struct xe_migrate_pt_update *pt_update)
 	 */
 	do {
 		down_read(&vm->userptr.notifier_lock);
-		if (!mmu_interval_read_retry(&vma->userptr.notifier,
+		if (!mmu_interval_read_retry(&uvma->userptr.notifier,
 					     notifier_seq))
 			break;
 
@@ -1032,11 +1048,11 @@ static int xe_pt_userptr_pre_commit(struct xe_migrate_pt_update *pt_update)
 		if (userptr_update->bind)
 			return -EAGAIN;
 
-		notifier_seq = mmu_interval_read_begin(&vma->userptr.notifier);
+		notifier_seq = mmu_interval_read_begin(&uvma->userptr.notifier);
 	} while (true);
 
 	/* Inject errors to test_whether they are handled correctly */
-	if (userptr_update->bind && xe_pt_userptr_inject_eagain(vma)) {
+	if (userptr_update->bind && xe_pt_userptr_inject_eagain(uvma)) {
 		up_read(&vm->userptr.notifier_lock);
 		return -EAGAIN;
 	}
@@ -1297,7 +1313,7 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue
 		vma->tile_present |= BIT(tile->id);
 
 		if (bind_pt_update.locked) {
-			vma->userptr.initial_bind = true;
+			to_userptr_vma(vma)->userptr.initial_bind = true;
 			up_read(&vm->userptr.notifier_lock);
 			xe_bo_put_commit(&deferred);
 		}
@@ -1507,7 +1523,7 @@ xe_pt_commit_unbind(struct xe_vma *vma,
 					xe_pt_destroy(xe_pt_entry(pt_dir, i),
 						      xe_vma_vm(vma)->flags, deferred);
 
-				pt_dir->dir.entries[i] = NULL;
+				pt_dir->children[i] = NULL;
 			}
 		}
 	}
@@ -1642,7 +1658,7 @@ __xe_pt_unbind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queu
 
 		if (!vma->tile_present) {
 			spin_lock(&vm->userptr.invalidated_lock);
-			list_del_init(&vma->userptr.invalidate_link);
+			list_del_init(&to_userptr_vma(vma)->userptr.invalidate_link);
 			spin_unlock(&vm->userptr.invalidated_lock);
 		}
 		up_read(&vm->userptr.notifier_lock);
diff --git a/drivers/gpu/drm/xe/xe_pt_walk.c b/drivers/gpu/drm/xe/xe_pt_walk.c
index 8f6c8d063f39..b8b3d2aea492 100644
--- a/drivers/gpu/drm/xe/xe_pt_walk.c
+++ b/drivers/gpu/drm/xe/xe_pt_walk.c
@@ -74,7 +74,7 @@ int xe_pt_walk_range(struct xe_ptw *parent, unsigned int level,
 		     u64 addr, u64 end, struct xe_pt_walk *walk)
 {
 	pgoff_t offset = xe_pt_offset(addr, level, walk);
-	struct xe_ptw **entries = parent->dir ? parent->dir->entries : NULL;
+	struct xe_ptw **entries = parent->children ? parent->children : NULL;
 	const struct xe_pt_walk_ops *ops = walk->ops;
 	enum page_walk_action action;
 	struct xe_ptw *child;
diff --git a/drivers/gpu/drm/xe/xe_pt_walk.h b/drivers/gpu/drm/xe/xe_pt_walk.h
index ec3d1e9efa6d..5ecc4d2f0f65 100644
--- a/drivers/gpu/drm/xe/xe_pt_walk.h
+++ b/drivers/gpu/drm/xe/xe_pt_walk.h
@@ -8,28 +8,15 @@
 #include <linux/pagewalk.h>
 #include <linux/types.h>
 
-struct xe_ptw_dir;
-
 /**
  * struct xe_ptw - base class for driver pagetable subclassing.
- * @dir: Pointer to an array of children if any.
+ * @children: Pointer to an array of children if any.
  *
  * Drivers could subclass this, and if it's a page-directory, typically
- * embed the xe_ptw_dir::entries array in the same allocation.
+ * embed an array of xe_ptw pointers.
  */
 struct xe_ptw {
-	struct xe_ptw_dir *dir;
-};
-
-/**
- * struct xe_ptw_dir - page directory structure
- * @entries: Array holding page directory children.
- *
- * It is the responsibility of the user to ensure @entries is
- * correctly sized.
- */
-struct xe_ptw_dir {
-	struct xe_ptw *entries[0];
+	struct xe_ptw **children;
 };
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c
index 9b35673b286c..7e924faeeea0 100644
--- a/drivers/gpu/drm/xe/xe_query.c
+++ b/drivers/gpu/drm/xe/xe_query.c
@@ -459,21 +459,21 @@ static size_t calc_topo_query_size(struct xe_device *xe)
 		 sizeof_field(struct xe_gt, fuse_topo.eu_mask_per_dss));
 }
 
-static void __user *copy_mask(void __user *ptr,
-			      struct drm_xe_query_topology_mask *topo,
-			      void *mask, size_t mask_size)
+static int copy_mask(void __user **ptr,
+		     struct drm_xe_query_topology_mask *topo,
+		     void *mask, size_t mask_size)
 {
 	topo->num_bytes = mask_size;
 
-	if (copy_to_user(ptr, topo, sizeof(*topo)))
-		return ERR_PTR(-EFAULT);
-	ptr += sizeof(topo);
+	if (copy_to_user(*ptr, topo, sizeof(*topo)))
+		return -EFAULT;
+	*ptr += sizeof(topo);
 
-	if (copy_to_user(ptr, mask, mask_size))
-		return ERR_PTR(-EFAULT);
-	ptr += mask_size;
+	if (copy_to_user(*ptr, mask, mask_size))
+		return -EFAULT;
+	*ptr += mask_size;
 
-	return ptr;
+	return 0;
 }
 
 static int query_gt_topology(struct xe_device *xe,
@@ -493,28 +493,28 @@ static int query_gt_topology(struct xe_device *xe,
 	}
 
 	for_each_gt(gt, xe, id) {
+		int err;
+
 		topo.gt_id = id;
 
 		topo.type = DRM_XE_TOPO_DSS_GEOMETRY;
-		query_ptr = copy_mask(query_ptr, &topo,
-				      gt->fuse_topo.g_dss_mask,
-				      sizeof(gt->fuse_topo.g_dss_mask));
-		if (IS_ERR(query_ptr))
-			return PTR_ERR(query_ptr);
+		err = copy_mask(&query_ptr, &topo, gt->fuse_topo.g_dss_mask,
+				sizeof(gt->fuse_topo.g_dss_mask));
+		if (err)
+			return err;
 
 		topo.type = DRM_XE_TOPO_DSS_COMPUTE;
-		query_ptr = copy_mask(query_ptr, &topo,
-				      gt->fuse_topo.c_dss_mask,
-				      sizeof(gt->fuse_topo.c_dss_mask));
-		if (IS_ERR(query_ptr))
-			return PTR_ERR(query_ptr);
+		err = copy_mask(&query_ptr, &topo, gt->fuse_topo.c_dss_mask,
+				sizeof(gt->fuse_topo.c_dss_mask));
+		if (err)
+			return err;
 
 		topo.type = DRM_XE_TOPO_EU_PER_DSS;
-		query_ptr = copy_mask(query_ptr, &topo,
-				      gt->fuse_topo.eu_mask_per_dss,
-				      sizeof(gt->fuse_topo.eu_mask_per_dss));
-		if (IS_ERR(query_ptr))
-			return PTR_ERR(query_ptr);
+		err = copy_mask(&query_ptr, &topo,
+				gt->fuse_topo.eu_mask_per_dss,
+				sizeof(gt->fuse_topo.eu_mask_per_dss));
+		if (err)
+			return err;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/xe/xe_range_fence.c b/drivers/gpu/drm/xe/xe_range_fence.c
index d35d9ec58e86..372378e89e98 100644
--- a/drivers/gpu/drm/xe/xe_range_fence.c
+++ b/drivers/gpu/drm/xe/xe_range_fence.c
@@ -151,6 +151,11 @@ xe_range_fence_tree_next(struct xe_range_fence *rfence, u64 start, u64 last)
 	return xe_range_fence_tree_iter_next(rfence, start, last);
 }
 
+static void xe_range_fence_free(struct xe_range_fence *rfence)
+{
+	kfree(rfence);
+}
+
 const struct xe_range_fence_ops xe_range_fence_kfree_ops = {
-	.free = (void (*)(struct xe_range_fence *rfence)) kfree,
+	.free = xe_range_fence_free,
 };
diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c
index 01106a1156ad..4e2ccad0e52f 100644
--- a/drivers/gpu/drm/xe/xe_sched_job.c
+++ b/drivers/gpu/drm/xe/xe_sched_job.c
@@ -274,7 +274,6 @@ int xe_sched_job_last_fence_add_dep(struct xe_sched_job *job, struct xe_vm *vm)
 	struct dma_fence *fence;
 
 	fence = xe_exec_queue_last_fence_get(job->q, vm);
-	dma_fence_get(fence);
 
 	return drm_sched_job_add_dependency(&job->drm, fence);
 }
diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index e4c220cf9115..02c9577fe418 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -19,7 +19,7 @@
 #include "xe_macros.h"
 #include "xe_sched_job_types.h"
 
-struct user_fence {
+struct xe_user_fence {
 	struct xe_device *xe;
 	struct kref refcount;
 	struct dma_fence_cb cb;
@@ -27,31 +27,32 @@ struct user_fence {
 	struct mm_struct *mm;
 	u64 __user *addr;
 	u64 value;
+	int signalled;
 };
 
 static void user_fence_destroy(struct kref *kref)
 {
-	struct user_fence *ufence = container_of(kref, struct user_fence,
+	struct xe_user_fence *ufence = container_of(kref, struct xe_user_fence,
 						 refcount);
 
 	mmdrop(ufence->mm);
 	kfree(ufence);
 }
 
-static void user_fence_get(struct user_fence *ufence)
+static void user_fence_get(struct xe_user_fence *ufence)
 {
 	kref_get(&ufence->refcount);
 }
 
-static void user_fence_put(struct user_fence *ufence)
+static void user_fence_put(struct xe_user_fence *ufence)
 {
 	kref_put(&ufence->refcount, user_fence_destroy);
 }
 
-static struct user_fence *user_fence_create(struct xe_device *xe, u64 addr,
-					    u64 value)
+static struct xe_user_fence *user_fence_create(struct xe_device *xe, u64 addr,
+					       u64 value)
 {
-	struct user_fence *ufence;
+	struct xe_user_fence *ufence;
 
 	ufence = kmalloc(sizeof(*ufence), GFP_KERNEL);
 	if (!ufence)
@@ -69,7 +70,7 @@ static struct user_fence *user_fence_create(struct xe_device *xe, u64 addr,
 
 static void user_fence_worker(struct work_struct *w)
 {
-	struct user_fence *ufence = container_of(w, struct user_fence, worker);
+	struct xe_user_fence *ufence = container_of(w, struct xe_user_fence, worker);
 
 	if (mmget_not_zero(ufence->mm)) {
 		kthread_use_mm(ufence->mm);
@@ -80,10 +81,11 @@ static void user_fence_worker(struct work_struct *w)
 	}
 
 	wake_up_all(&ufence->xe->ufence_wq);
+	WRITE_ONCE(ufence->signalled, 1);
 	user_fence_put(ufence);
 }
 
-static void kick_ufence(struct user_fence *ufence, struct dma_fence *fence)
+static void kick_ufence(struct xe_user_fence *ufence, struct dma_fence *fence)
 {
 	INIT_WORK(&ufence->worker, user_fence_worker);
 	queue_work(ufence->xe->ordered_wq, &ufence->worker);
@@ -92,7 +94,7 @@ static void kick_ufence(struct user_fence *ufence, struct dma_fence *fence)
 
 static void user_fence_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
 {
-	struct user_fence *ufence = container_of(cb, struct user_fence, cb);
+	struct xe_user_fence *ufence = container_of(cb, struct xe_user_fence, cb);
 
 	kick_ufence(ufence, fence);
 }
@@ -307,7 +309,6 @@ xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync,
 	/* Easy case... */
 	if (!num_in_fence) {
 		fence = xe_exec_queue_last_fence_get(q, vm);
-		dma_fence_get(fence);
 		return fence;
 	}
 
@@ -322,7 +323,6 @@ xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync,
 		}
 	}
 	fences[current_fence++] = xe_exec_queue_last_fence_get(q, vm);
-	dma_fence_get(fences[current_fence - 1]);
 	cf = dma_fence_array_create(num_in_fence, fences,
 				    vm->composite_fence_ctx,
 				    vm->composite_fence_seqno++,
@@ -342,3 +342,39 @@ err_out:
 
 	return ERR_PTR(-ENOMEM);
 }
+
+/**
+ * xe_sync_ufence_get() - Get user fence from sync
+ * @sync: input sync
+ *
+ * Get a user fence reference from sync.
+ *
+ * Return: xe_user_fence pointer with reference
+ */
+struct xe_user_fence *xe_sync_ufence_get(struct xe_sync_entry *sync)
+{
+	user_fence_get(sync->ufence);
+
+	return sync->ufence;
+}
+
+/**
+ * xe_sync_ufence_put() - Put user fence reference
+ * @ufence: user fence reference
+ *
+ */
+void xe_sync_ufence_put(struct xe_user_fence *ufence)
+{
+	user_fence_put(ufence);
+}
+
+/**
+ * xe_sync_ufence_get_status() - Get user fence status
+ * @ufence: user fence
+ *
+ * Return: 1 if signalled, 0 not signalled, <0 on error
+ */
+int xe_sync_ufence_get_status(struct xe_user_fence *ufence)
+{
+	return READ_ONCE(ufence->signalled);
+}
diff --git a/drivers/gpu/drm/xe/xe_sync.h b/drivers/gpu/drm/xe/xe_sync.h
index d284afbe917c..0fd0d51208e6 100644
--- a/drivers/gpu/drm/xe/xe_sync.h
+++ b/drivers/gpu/drm/xe/xe_sync.h
@@ -33,4 +33,13 @@ struct dma_fence *
 xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync,
 		     struct xe_exec_queue *q, struct xe_vm *vm);
 
+static inline bool xe_sync_is_ufence(struct xe_sync_entry *sync)
+{
+	return !!sync->ufence;
+}
+
+struct xe_user_fence *xe_sync_ufence_get(struct xe_sync_entry *sync);
+void xe_sync_ufence_put(struct xe_user_fence *ufence);
+int xe_sync_ufence_get_status(struct xe_user_fence *ufence);
+
 #endif
diff --git a/drivers/gpu/drm/xe/xe_sync_types.h b/drivers/gpu/drm/xe/xe_sync_types.h
index 852db5e7884f..30ac3f51993b 100644
--- a/drivers/gpu/drm/xe/xe_sync_types.h
+++ b/drivers/gpu/drm/xe/xe_sync_types.h
@@ -18,7 +18,7 @@ struct xe_sync_entry {
 	struct drm_syncobj *syncobj;
 	struct dma_fence *fence;
 	struct dma_fence_chain *chain_fence;
-	struct user_fence *ufence;
+	struct xe_user_fence *ufence;
 	u64 addr;
 	u64 timeline_value;
 	u32 type;
diff --git a/drivers/gpu/drm/xe/xe_tile.c b/drivers/gpu/drm/xe/xe_tile.c
index 044c20881de7..0650b2fa75ef 100644
--- a/drivers/gpu/drm/xe/xe_tile.c
+++ b/drivers/gpu/drm/xe/xe_tile.c
@@ -167,9 +167,10 @@ int xe_tile_init_noalloc(struct xe_tile *tile)
 		goto err_mem_access;
 
 	tile->mem.kernel_bb_pool = xe_sa_bo_manager_init(tile, SZ_1M, 16);
-	if (IS_ERR(tile->mem.kernel_bb_pool))
+	if (IS_ERR(tile->mem.kernel_bb_pool)) {
 		err = PTR_ERR(tile->mem.kernel_bb_pool);
-
+		goto err_mem_access;
+	}
 	xe_wa_apply_tile_workarounds(tile);
 
 	xe_tile_sysfs_init(tile);
diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h
index 95163c303f3e..4ddc55527f9a 100644
--- a/drivers/gpu/drm/xe/xe_trace.h
+++ b/drivers/gpu/drm/xe/xe_trace.h
@@ -12,6 +12,7 @@
 #include <linux/tracepoint.h>
 #include <linux/types.h>
 
+#include "xe_bo.h"
 #include "xe_bo_types.h"
 #include "xe_exec_queue_types.h"
 #include "xe_gpu_scheduler_types.h"
@@ -26,16 +27,16 @@ DECLARE_EVENT_CLASS(xe_gt_tlb_invalidation_fence,
 		    TP_ARGS(fence),
 
 		    TP_STRUCT__entry(
-			     __field(u64, fence)
+			     __field(struct xe_gt_tlb_invalidation_fence *, fence)
 			     __field(int, seqno)
 			     ),
 
 		    TP_fast_assign(
-			   __entry->fence = (u64)fence;
+			   __entry->fence = fence;
 			   __entry->seqno = fence->seqno;
 			   ),
 
-		    TP_printk("fence=0x%016llx, seqno=%d",
+		    TP_printk("fence=%p, seqno=%d",
 			      __entry->fence, __entry->seqno)
 );
 
@@ -82,16 +83,16 @@ DECLARE_EVENT_CLASS(xe_bo,
 		    TP_STRUCT__entry(
 			     __field(size_t, size)
 			     __field(u32, flags)
-			     __field(u64, vm)
+			     __field(struct xe_vm *, vm)
 			     ),
 
 		    TP_fast_assign(
 			   __entry->size = bo->size;
 			   __entry->flags = bo->flags;
-			   __entry->vm = (unsigned long)bo->vm;
+			   __entry->vm = bo->vm;
 			   ),
 
-		    TP_printk("size=%zu, flags=0x%02x, vm=0x%016llx",
+		    TP_printk("size=%zu, flags=0x%02x, vm=%p",
 			      __entry->size, __entry->flags, __entry->vm)
 );
 
@@ -100,9 +101,31 @@ DEFINE_EVENT(xe_bo, xe_bo_cpu_fault,
 	     TP_ARGS(bo)
 );
 
-DEFINE_EVENT(xe_bo, xe_bo_move,
-	     TP_PROTO(struct xe_bo *bo),
-	     TP_ARGS(bo)
+TRACE_EVENT(xe_bo_move,
+	    TP_PROTO(struct xe_bo *bo, uint32_t new_placement, uint32_t old_placement,
+		     bool move_lacks_source),
+	    TP_ARGS(bo, new_placement, old_placement, move_lacks_source),
+	    TP_STRUCT__entry(
+		     __field(struct xe_bo *, bo)
+		     __field(size_t, size)
+		     __field(u32, new_placement)
+		     __field(u32, old_placement)
+		     __array(char, device_id, 12)
+		     __field(bool, move_lacks_source)
+			),
+
+	    TP_fast_assign(
+		   __entry->bo      = bo;
+		   __entry->size = bo->size;
+		   __entry->new_placement = new_placement;
+		   __entry->old_placement = old_placement;
+		   strscpy(__entry->device_id, dev_name(xe_bo_device(__entry->bo)->drm.dev), 12);
+		   __entry->move_lacks_source = move_lacks_source;
+		   ),
+	    TP_printk("move_lacks_source:%s, migrate object %p [size %zu] from %s to %s device_id:%s",
+		      __entry->move_lacks_source ? "yes" : "no", __entry->bo, __entry->size,
+		      xe_mem_type_to_name[__entry->old_placement],
+		      xe_mem_type_to_name[__entry->new_placement], __entry->device_id)
 );
 
 DECLARE_EVENT_CLASS(xe_exec_queue,
@@ -327,16 +350,16 @@ DECLARE_EVENT_CLASS(xe_hw_fence,
 		    TP_STRUCT__entry(
 			     __field(u64, ctx)
 			     __field(u32, seqno)
-			     __field(u64, fence)
+			     __field(struct xe_hw_fence *, fence)
 			     ),
 
 		    TP_fast_assign(
 			   __entry->ctx = fence->dma.context;
 			   __entry->seqno = fence->dma.seqno;
-			   __entry->fence = (unsigned long)fence;
+			   __entry->fence = fence;
 			   ),
 
-		    TP_printk("ctx=0x%016llx, fence=0x%016llx, seqno=%u",
+		    TP_printk("ctx=0x%016llx, fence=%p, seqno=%u",
 			      __entry->ctx, __entry->fence, __entry->seqno)
 );
 
@@ -365,7 +388,7 @@ DECLARE_EVENT_CLASS(xe_vma,
 		    TP_ARGS(vma),
 
 		    TP_STRUCT__entry(
-			     __field(u64, vma)
+			     __field(struct xe_vma *, vma)
 			     __field(u32, asid)
 			     __field(u64, start)
 			     __field(u64, end)
@@ -373,14 +396,14 @@ DECLARE_EVENT_CLASS(xe_vma,
 			     ),
 
 		    TP_fast_assign(
-			   __entry->vma = (unsigned long)vma;
+			   __entry->vma = vma;
 			   __entry->asid = xe_vma_vm(vma)->usm.asid;
 			   __entry->start = xe_vma_start(vma);
 			   __entry->end = xe_vma_end(vma) - 1;
 			   __entry->ptr = xe_vma_userptr(vma);
 			   ),
 
-		    TP_printk("vma=0x%016llx, asid=0x%05x, start=0x%012llx, end=0x%012llx, ptr=0x%012llx,",
+		    TP_printk("vma=%p, asid=0x%05x, start=0x%012llx, end=0x%012llx, userptr=0x%012llx,",
 			      __entry->vma, __entry->asid, __entry->start,
 			      __entry->end, __entry->ptr)
 )
@@ -465,16 +488,16 @@ DECLARE_EVENT_CLASS(xe_vm,
 		    TP_ARGS(vm),
 
 		    TP_STRUCT__entry(
-			     __field(u64, vm)
+			     __field(struct xe_vm *, vm)
 			     __field(u32, asid)
 			     ),
 
 		    TP_fast_assign(
-			   __entry->vm = (unsigned long)vm;
+			   __entry->vm = vm;
 			   __entry->asid = vm->usm.asid;
 			   ),
 
-		    TP_printk("vm=0x%016llx, asid=0x%05x",  __entry->vm,
+		    TP_printk("vm=%p, asid=0x%05x",  __entry->vm,
 			      __entry->asid)
 );
 
diff --git a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
index d2b00d0bf1e2..e5d7d5e2bec1 100644
--- a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
+++ b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
@@ -31,7 +31,7 @@ struct xe_ttm_stolen_mgr {
 	/* GPU base offset */
 	resource_size_t stolen_base;
 
-	void *__iomem mapping;
+	void __iomem *mapping;
 };
 
 static inline struct xe_ttm_stolen_mgr *
@@ -275,7 +275,7 @@ static int __xe_ttm_stolen_io_mem_reserve_bar2(struct xe_device *xe,
 	drm_WARN_ON(&xe->drm, !(mem->placement & TTM_PL_FLAG_CONTIGUOUS));
 
 	if (mem->placement & TTM_PL_FLAG_CONTIGUOUS && mgr->mapping)
-		mem->bus.addr = (u8 *)mgr->mapping + mem->bus.offset;
+		mem->bus.addr = (u8 __force *)mgr->mapping + mem->bus.offset;
 
 	mem->bus.offset += mgr->io_base;
 	mem->bus.is_iomem = true;
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 0cfe7289b97e..3b21afe5b488 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -37,8 +37,6 @@
 #include "generated/xe_wa_oob.h"
 #include "xe_wa.h"
 
-#define TEST_VM_ASYNC_OPS_ERROR
-
 static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm)
 {
 	return vm->gpuvm.r_obj;
@@ -46,7 +44,7 @@ static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm)
 
 /**
  * xe_vma_userptr_check_repin() - Advisory check for repin needed
- * @vma: The userptr vma
+ * @uvma: The userptr vma
  *
  * Check if the userptr vma has been invalidated since last successful
  * repin. The check is advisory only and can the function can be called
@@ -56,15 +54,17 @@ static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm)
  *
  * Return: 0 if userptr vma is valid, -EAGAIN otherwise; repin recommended.
  */
-int xe_vma_userptr_check_repin(struct xe_vma *vma)
+int xe_vma_userptr_check_repin(struct xe_userptr_vma *uvma)
 {
-	return mmu_interval_check_retry(&vma->userptr.notifier,
-					vma->userptr.notifier_seq) ?
+	return mmu_interval_check_retry(&uvma->userptr.notifier,
+					uvma->userptr.notifier_seq) ?
 		-EAGAIN : 0;
 }
 
-int xe_vma_userptr_pin_pages(struct xe_vma *vma)
+int xe_vma_userptr_pin_pages(struct xe_userptr_vma *uvma)
 {
+	struct xe_userptr *userptr = &uvma->userptr;
+	struct xe_vma *vma = &uvma->vma;
 	struct xe_vm *vm = xe_vma_vm(vma);
 	struct xe_device *xe = vm->xe;
 	const unsigned long num_pages = xe_vma_size(vma) >> PAGE_SHIFT;
@@ -80,30 +80,30 @@ retry:
 	if (vma->gpuva.flags & XE_VMA_DESTROYED)
 		return 0;
 
-	notifier_seq = mmu_interval_read_begin(&vma->userptr.notifier);
-	if (notifier_seq == vma->userptr.notifier_seq)
+	notifier_seq = mmu_interval_read_begin(&userptr->notifier);
+	if (notifier_seq == userptr->notifier_seq)
 		return 0;
 
 	pages = kvmalloc_array(num_pages, sizeof(*pages), GFP_KERNEL);
 	if (!pages)
 		return -ENOMEM;
 
-	if (vma->userptr.sg) {
+	if (userptr->sg) {
 		dma_unmap_sgtable(xe->drm.dev,
-				  vma->userptr.sg,
+				  userptr->sg,
 				  read_only ? DMA_TO_DEVICE :
 				  DMA_BIDIRECTIONAL, 0);
-		sg_free_table(vma->userptr.sg);
-		vma->userptr.sg = NULL;
+		sg_free_table(userptr->sg);
+		userptr->sg = NULL;
 	}
 
 	pinned = ret = 0;
 	if (in_kthread) {
-		if (!mmget_not_zero(vma->userptr.notifier.mm)) {
+		if (!mmget_not_zero(userptr->notifier.mm)) {
 			ret = -EFAULT;
 			goto mm_closed;
 		}
-		kthread_use_mm(vma->userptr.notifier.mm);
+		kthread_use_mm(userptr->notifier.mm);
 	}
 
 	while (pinned < num_pages) {
@@ -112,43 +112,40 @@ retry:
 					  num_pages - pinned,
 					  read_only ? 0 : FOLL_WRITE,
 					  &pages[pinned]);
-		if (ret < 0) {
-			if (in_kthread)
-				ret = 0;
+		if (ret < 0)
 			break;
-		}
 
 		pinned += ret;
 		ret = 0;
 	}
 
 	if (in_kthread) {
-		kthread_unuse_mm(vma->userptr.notifier.mm);
-		mmput(vma->userptr.notifier.mm);
+		kthread_unuse_mm(userptr->notifier.mm);
+		mmput(userptr->notifier.mm);
 	}
 mm_closed:
 	if (ret)
 		goto out;
 
-	ret = sg_alloc_table_from_pages_segment(&vma->userptr.sgt, pages,
+	ret = sg_alloc_table_from_pages_segment(&userptr->sgt, pages,
 						pinned, 0,
 						(u64)pinned << PAGE_SHIFT,
 						xe_sg_segment_size(xe->drm.dev),
 						GFP_KERNEL);
 	if (ret) {
-		vma->userptr.sg = NULL;
+		userptr->sg = NULL;
 		goto out;
 	}
-	vma->userptr.sg = &vma->userptr.sgt;
+	userptr->sg = &userptr->sgt;
 
-	ret = dma_map_sgtable(xe->drm.dev, vma->userptr.sg,
+	ret = dma_map_sgtable(xe->drm.dev, userptr->sg,
 			      read_only ? DMA_TO_DEVICE :
 			      DMA_BIDIRECTIONAL,
 			      DMA_ATTR_SKIP_CPU_SYNC |
 			      DMA_ATTR_NO_KERNEL_MAPPING);
 	if (ret) {
-		sg_free_table(vma->userptr.sg);
-		vma->userptr.sg = NULL;
+		sg_free_table(userptr->sg);
+		userptr->sg = NULL;
 		goto out;
 	}
 
@@ -167,8 +164,8 @@ out:
 	kvfree(pages);
 
 	if (!(ret < 0)) {
-		vma->userptr.notifier_seq = notifier_seq;
-		if (xe_vma_userptr_check_repin(vma) == -EAGAIN)
+		userptr->notifier_seq = notifier_seq;
+		if (xe_vma_userptr_check_repin(uvma) == -EAGAIN)
 			goto retry;
 	}
 
@@ -335,13 +332,13 @@ int xe_vm_add_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q)
 	down_write(&vm->lock);
 	err = drm_gpuvm_exec_lock(&vm_exec);
 	if (err)
-		return err;
+		goto out_up_write;
 
 	pfence = xe_preempt_fence_create(q, q->compute.context,
 					 ++q->compute.seqno);
 	if (!pfence) {
 		err = -ENOMEM;
-		goto out_unlock;
+		goto out_fini;
 	}
 
 	list_add(&q->compute.link, &vm->preempt.exec_queues);
@@ -364,8 +361,9 @@ int xe_vm_add_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q)
 
 	up_read(&vm->userptr.notifier_lock);
 
-out_unlock:
+out_fini:
 	drm_exec_fini(exec);
+out_up_write:
 	up_write(&vm->lock);
 
 	return err;
@@ -634,7 +632,9 @@ static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
 				   const struct mmu_notifier_range *range,
 				   unsigned long cur_seq)
 {
-	struct xe_vma *vma = container_of(mni, struct xe_vma, userptr.notifier);
+	struct xe_userptr *userptr = container_of(mni, typeof(*userptr), notifier);
+	struct xe_userptr_vma *uvma = container_of(userptr, typeof(*uvma), userptr);
+	struct xe_vma *vma = &uvma->vma;
 	struct xe_vm *vm = xe_vma_vm(vma);
 	struct dma_resv_iter cursor;
 	struct dma_fence *fence;
@@ -650,7 +650,7 @@ static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
 	mmu_interval_set_seq(mni, cur_seq);
 
 	/* No need to stop gpu access if the userptr is not yet bound. */
-	if (!vma->userptr.initial_bind) {
+	if (!userptr->initial_bind) {
 		up_write(&vm->userptr.notifier_lock);
 		return true;
 	}
@@ -662,7 +662,7 @@ static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
 	if (!xe_vm_in_fault_mode(vm) &&
 	    !(vma->gpuva.flags & XE_VMA_DESTROYED) && vma->tile_present) {
 		spin_lock(&vm->userptr.invalidated_lock);
-		list_move_tail(&vma->userptr.invalidate_link,
+		list_move_tail(&userptr->invalidate_link,
 			       &vm->userptr.invalidated);
 		spin_unlock(&vm->userptr.invalidated_lock);
 	}
@@ -702,7 +702,7 @@ static const struct mmu_interval_notifier_ops vma_userptr_notifier_ops = {
 
 int xe_vm_userptr_pin(struct xe_vm *vm)
 {
-	struct xe_vma *vma, *next;
+	struct xe_userptr_vma *uvma, *next;
 	int err = 0;
 	LIST_HEAD(tmp_evict);
 
@@ -710,22 +710,23 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 
 	/* Collect invalidated userptrs */
 	spin_lock(&vm->userptr.invalidated_lock);
-	list_for_each_entry_safe(vma, next, &vm->userptr.invalidated,
+	list_for_each_entry_safe(uvma, next, &vm->userptr.invalidated,
 				 userptr.invalidate_link) {
-		list_del_init(&vma->userptr.invalidate_link);
-		list_move_tail(&vma->combined_links.userptr,
+		list_del_init(&uvma->userptr.invalidate_link);
+		list_move_tail(&uvma->userptr.repin_link,
 			       &vm->userptr.repin_list);
 	}
 	spin_unlock(&vm->userptr.invalidated_lock);
 
 	/* Pin and move to temporary list */
-	list_for_each_entry_safe(vma, next, &vm->userptr.repin_list,
-				 combined_links.userptr) {
-		err = xe_vma_userptr_pin_pages(vma);
+	list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list,
+				 userptr.repin_link) {
+		err = xe_vma_userptr_pin_pages(uvma);
 		if (err < 0)
 			return err;
 
-		list_move_tail(&vma->combined_links.userptr, &vm->rebind_list);
+		list_del_init(&uvma->userptr.repin_link);
+		list_move_tail(&uvma->vma.combined_links.rebind, &vm->rebind_list);
 	}
 
 	return 0;
@@ -781,6 +782,14 @@ struct dma_fence *xe_vm_rebind(struct xe_vm *vm, bool rebind_worker)
 	return fence;
 }
 
+static void xe_vma_free(struct xe_vma *vma)
+{
+	if (xe_vma_is_userptr(vma))
+		kfree(to_userptr_vma(vma));
+	else
+		kfree(vma);
+}
+
 #define VMA_CREATE_FLAG_READ_ONLY	BIT(0)
 #define VMA_CREATE_FLAG_IS_NULL		BIT(1)
 
@@ -799,14 +808,26 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 	xe_assert(vm->xe, start < end);
 	xe_assert(vm->xe, end < vm->size);
 
-	if (!bo && !is_null)	/* userptr */
+	/*
+	 * Allocate and ensure that the xe_vma_is_userptr() return
+	 * matches what was allocated.
+	 */
+	if (!bo && !is_null) {
+		struct xe_userptr_vma *uvma = kzalloc(sizeof(*uvma), GFP_KERNEL);
+
+		if (!uvma)
+			return ERR_PTR(-ENOMEM);
+
+		vma = &uvma->vma;
+	} else {
 		vma = kzalloc(sizeof(*vma), GFP_KERNEL);
-	else
-		vma = kzalloc(sizeof(*vma) - sizeof(struct xe_userptr),
-			      GFP_KERNEL);
-	if (!vma) {
-		vma = ERR_PTR(-ENOMEM);
-		return vma;
+		if (!vma)
+			return ERR_PTR(-ENOMEM);
+
+		if (is_null)
+			vma->gpuva.flags |= DRM_GPUVA_SPARSE;
+		if (bo)
+			vma->gpuva.gem.obj = &bo->ttm.base;
 	}
 
 	INIT_LIST_HEAD(&vma->combined_links.rebind);
@@ -817,8 +838,6 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 	vma->gpuva.va.range = end - start + 1;
 	if (read_only)
 		vma->gpuva.flags |= XE_VMA_READ_ONLY;
-	if (is_null)
-		vma->gpuva.flags |= DRM_GPUVA_SPARSE;
 
 	for_each_tile(tile, vm->xe, id)
 		vma->tile_mask |= 0x1 << id;
@@ -835,35 +854,35 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 
 		vm_bo = drm_gpuvm_bo_obtain(vma->gpuva.vm, &bo->ttm.base);
 		if (IS_ERR(vm_bo)) {
-			kfree(vma);
+			xe_vma_free(vma);
 			return ERR_CAST(vm_bo);
 		}
 
 		drm_gpuvm_bo_extobj_add(vm_bo);
 		drm_gem_object_get(&bo->ttm.base);
-		vma->gpuva.gem.obj = &bo->ttm.base;
 		vma->gpuva.gem.offset = bo_offset_or_userptr;
 		drm_gpuva_link(&vma->gpuva, vm_bo);
 		drm_gpuvm_bo_put(vm_bo);
 	} else /* userptr or null */ {
 		if (!is_null) {
+			struct xe_userptr *userptr = &to_userptr_vma(vma)->userptr;
 			u64 size = end - start + 1;
 			int err;
 
-			INIT_LIST_HEAD(&vma->userptr.invalidate_link);
+			INIT_LIST_HEAD(&userptr->invalidate_link);
+			INIT_LIST_HEAD(&userptr->repin_link);
 			vma->gpuva.gem.offset = bo_offset_or_userptr;
 
-			err = mmu_interval_notifier_insert(&vma->userptr.notifier,
+			err = mmu_interval_notifier_insert(&userptr->notifier,
 							   current->mm,
 							   xe_vma_userptr(vma), size,
 							   &vma_userptr_notifier_ops);
 			if (err) {
-				kfree(vma);
-				vma = ERR_PTR(err);
-				return vma;
+				xe_vma_free(vma);
+				return ERR_PTR(err);
 			}
 
-			vma->userptr.notifier_seq = LONG_MAX;
+			userptr->notifier_seq = LONG_MAX;
 		}
 
 		xe_vm_get(vm);
@@ -878,14 +897,21 @@ static void xe_vma_destroy_late(struct xe_vma *vma)
 	struct xe_device *xe = vm->xe;
 	bool read_only = xe_vma_read_only(vma);
 
+	if (vma->ufence) {
+		xe_sync_ufence_put(vma->ufence);
+		vma->ufence = NULL;
+	}
+
 	if (xe_vma_is_userptr(vma)) {
-		if (vma->userptr.sg) {
+		struct xe_userptr *userptr = &to_userptr_vma(vma)->userptr;
+
+		if (userptr->sg) {
 			dma_unmap_sgtable(xe->drm.dev,
-					  vma->userptr.sg,
+					  userptr->sg,
 					  read_only ? DMA_TO_DEVICE :
 					  DMA_BIDIRECTIONAL, 0);
-			sg_free_table(vma->userptr.sg);
-			vma->userptr.sg = NULL;
+			sg_free_table(userptr->sg);
+			userptr->sg = NULL;
 		}
 
 		/*
@@ -893,7 +919,7 @@ static void xe_vma_destroy_late(struct xe_vma *vma)
 		 * the notifer until we're sure the GPU is not accessing
 		 * them anymore
 		 */
-		mmu_interval_notifier_remove(&vma->userptr.notifier);
+		mmu_interval_notifier_remove(&userptr->notifier);
 		xe_vm_put(vm);
 	} else if (xe_vma_is_null(vma)) {
 		xe_vm_put(vm);
@@ -901,7 +927,7 @@ static void xe_vma_destroy_late(struct xe_vma *vma)
 		xe_bo_put(xe_vma_bo(vma));
 	}
 
-	kfree(vma);
+	xe_vma_free(vma);
 }
 
 static void vma_destroy_work_func(struct work_struct *w)
@@ -932,7 +958,7 @@ static void xe_vma_destroy(struct xe_vma *vma, struct dma_fence *fence)
 		xe_assert(vm->xe, vma->gpuva.flags & XE_VMA_DESTROYED);
 
 		spin_lock(&vm->userptr.invalidated_lock);
-		list_del(&vma->userptr.invalidate_link);
+		list_del(&to_userptr_vma(vma)->userptr.invalidate_link);
 		spin_unlock(&vm->userptr.invalidated_lock);
 	} else if (!xe_vma_is_null(vma)) {
 		xe_bo_assert_held(xe_vma_bo(vma));
@@ -974,9 +1000,16 @@ int xe_vm_prepare_vma(struct drm_exec *exec, struct xe_vma *vma,
 	int err;
 
 	XE_WARN_ON(!vm);
-	err = drm_exec_prepare_obj(exec, xe_vm_obj(vm), num_shared);
-	if (!err && bo && !bo->vm)
-		err = drm_exec_prepare_obj(exec, &bo->ttm.base, num_shared);
+	if (num_shared)
+		err = drm_exec_prepare_obj(exec, xe_vm_obj(vm), num_shared);
+	else
+		err = drm_exec_lock_obj(exec, xe_vm_obj(vm));
+	if (!err && bo && !bo->vm) {
+		if (num_shared)
+			err = drm_exec_prepare_obj(exec, &bo->ttm.base, num_shared);
+		else
+			err = drm_exec_lock_obj(exec, &bo->ttm.base);
+	}
 
 	return err;
 }
@@ -1580,6 +1613,16 @@ xe_vm_unbind_vma(struct xe_vma *vma, struct xe_exec_queue *q,
 
 	trace_xe_vma_unbind(vma);
 
+	if (vma->ufence) {
+		struct xe_user_fence * const f = vma->ufence;
+
+		if (!xe_sync_ufence_get_status(f))
+			return ERR_PTR(-EBUSY);
+
+		vma->ufence = NULL;
+		xe_sync_ufence_put(f);
+	}
+
 	if (number_tiles > 1) {
 		fences = kmalloc_array(number_tiles, sizeof(*fences),
 				       GFP_KERNEL);
@@ -1713,6 +1756,21 @@ err_fences:
 	return ERR_PTR(err);
 }
 
+static struct xe_user_fence *
+find_ufence_get(struct xe_sync_entry *syncs, u32 num_syncs)
+{
+	unsigned int i;
+
+	for (i = 0; i < num_syncs; i++) {
+		struct xe_sync_entry *e = &syncs[i];
+
+		if (xe_sync_is_ufence(e))
+			return xe_sync_ufence_get(e);
+	}
+
+	return NULL;
+}
+
 static int __xe_vm_bind(struct xe_vm *vm, struct xe_vma *vma,
 			struct xe_exec_queue *q, struct xe_sync_entry *syncs,
 			u32 num_syncs, bool immediate, bool first_op,
@@ -1720,9 +1778,16 @@ static int __xe_vm_bind(struct xe_vm *vm, struct xe_vma *vma,
 {
 	struct dma_fence *fence;
 	struct xe_exec_queue *wait_exec_queue = to_wait_exec_queue(vm, q);
+	struct xe_user_fence *ufence;
 
 	xe_vm_assert_held(vm);
 
+	ufence = find_ufence_get(syncs, num_syncs);
+	if (vma->ufence && ufence)
+		xe_sync_ufence_put(vma->ufence);
+
+	vma->ufence = ufence ?: vma->ufence;
+
 	if (immediate) {
 		fence = xe_vm_bind_vma(vma, q, syncs, num_syncs, first_op,
 				       last_op);
@@ -1854,10 +1919,8 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 	mutex_lock(&xef->vm.lock);
 	err = xa_alloc(&xef->vm.xa, &id, vm, xa_limit_32b, GFP_KERNEL);
 	mutex_unlock(&xef->vm.lock);
-	if (err) {
-		xe_vm_close_and_put(vm);
-		return err;
-	}
+	if (err)
+		goto err_close_and_put;
 
 	if (xe->info.has_asid) {
 		mutex_lock(&xe->usm.lock);
@@ -1865,11 +1928,9 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 				      XA_LIMIT(1, XE_MAX_ASID - 1),
 				      &xe->usm.next_asid, GFP_KERNEL);
 		mutex_unlock(&xe->usm.lock);
-		if (err < 0) {
-			xe_vm_close_and_put(vm);
-			return err;
-		}
-		err = 0;
+		if (err < 0)
+			goto err_free_id;
+
 		vm->usm.asid = asid;
 	}
 
@@ -1887,6 +1948,15 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 #endif
 
 	return 0;
+
+err_free_id:
+	mutex_lock(&xef->vm.lock);
+	xa_erase(&xef->vm.xa, id);
+	mutex_unlock(&xef->vm.lock);
+err_close_and_put:
+	xe_vm_close_and_put(vm);
+
+	return err;
 }
 
 int xe_vm_destroy_ioctl(struct drm_device *dev, void *data,
@@ -1953,6 +2023,7 @@ static int xe_vm_prefetch(struct xe_vm *vm, struct xe_vma *vma,
 					xe_exec_queue_last_fence_get(wait_exec_queue, vm);
 
 				xe_sync_entry_signal(&syncs[i], NULL, fence);
+				dma_fence_put(fence);
 			}
 		}
 
@@ -2033,7 +2104,6 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
 	struct drm_gem_object *obj = bo ? &bo->ttm.base : NULL;
 	struct drm_gpuva_ops *ops;
 	struct drm_gpuva_op *__op;
-	struct xe_vma_op *op;
 	struct drm_gpuvm_bo *vm_bo;
 	int err;
 
@@ -2063,9 +2133,11 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
 		if (err)
 			return ERR_PTR(err);
 
-		vm_bo = drm_gpuvm_bo_find(&vm->gpuvm, obj);
-		if (!vm_bo)
-			break;
+		vm_bo = drm_gpuvm_bo_obtain(&vm->gpuvm, obj);
+		if (IS_ERR(vm_bo)) {
+			xe_bo_unlock(bo);
+			return ERR_CAST(vm_bo);
+		}
 
 		ops = drm_gpuvm_bo_unmap_ops_create(vm_bo);
 		drm_gpuvm_bo_put(vm_bo);
@@ -2078,23 +2150,10 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
 	if (IS_ERR(ops))
 		return ops;
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-	if (operation & FORCE_ASYNC_OP_ERROR) {
-		op = list_first_entry_or_null(&ops->list, struct xe_vma_op,
-					      base.entry);
-		if (op)
-			op->inject_error = true;
-	}
-#endif
-
 	drm_gpuva_for_each_op(__op, ops) {
 		struct xe_vma_op *op = gpuva_op_to_vma_op(__op);
 
 		if (__op->op == DRM_GPUVA_OP_MAP) {
-			op->map.immediate =
-				flags & DRM_XE_VM_BIND_FLAG_IMMEDIATE;
-			op->map.read_only =
-				flags & DRM_XE_VM_BIND_FLAG_READONLY;
 			op->map.is_null = flags & DRM_XE_VM_BIND_FLAG_NULL;
 			op->map.pat_index = pat_index;
 		} else if (__op->op == DRM_GPUVA_OP_PREFETCH) {
@@ -2142,7 +2201,7 @@ static struct xe_vma *new_vma(struct xe_vm *vm, struct drm_gpuva_op_map *op,
 		drm_exec_fini(&exec);
 
 	if (xe_vma_is_userptr(vma)) {
-		err = xe_vma_userptr_pin_pages(vma);
+		err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
 		if (err) {
 			prep_vma_destroy(vm, vma, false);
 			xe_vma_destroy_unlocked(vma);
@@ -2164,13 +2223,17 @@ static u64 xe_vma_max_pte_size(struct xe_vma *vma)
 {
 	if (vma->gpuva.flags & XE_VMA_PTE_1G)
 		return SZ_1G;
-	else if (vma->gpuva.flags & XE_VMA_PTE_2M)
+	else if (vma->gpuva.flags & (XE_VMA_PTE_2M | XE_VMA_PTE_COMPACT))
 		return SZ_2M;
+	else if (vma->gpuva.flags & XE_VMA_PTE_64K)
+		return SZ_64K;
+	else if (vma->gpuva.flags & XE_VMA_PTE_4K)
+		return SZ_4K;
 
-	return SZ_4K;
+	return SZ_1G;	/* Uninitialized, used max size */
 }
 
-static u64 xe_vma_set_pte_size(struct xe_vma *vma, u64 size)
+static void xe_vma_set_pte_size(struct xe_vma *vma, u64 size)
 {
 	switch (size) {
 	case SZ_1G:
@@ -2179,9 +2242,13 @@ static u64 xe_vma_set_pte_size(struct xe_vma *vma, u64 size)
 	case SZ_2M:
 		vma->gpuva.flags |= XE_VMA_PTE_2M;
 		break;
+	case SZ_64K:
+		vma->gpuva.flags |= XE_VMA_PTE_64K;
+		break;
+	case SZ_4K:
+		vma->gpuva.flags |= XE_VMA_PTE_4K;
+		break;
 	}
-
-	return SZ_4K;
 }
 
 static int xe_vma_op_commit(struct xe_vm *vm, struct xe_vma_op *op)
@@ -2279,8 +2346,6 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct xe_exec_queue *q,
 		switch (op->base.op) {
 		case DRM_GPUVA_OP_MAP:
 		{
-			flags |= op->map.read_only ?
-				VMA_CREATE_FLAG_READ_ONLY : 0;
 			flags |= op->map.is_null ?
 				VMA_CREATE_FLAG_IS_NULL : 0;
 
@@ -2411,7 +2476,7 @@ static int op_execute(struct drm_exec *exec, struct xe_vm *vm,
 	case DRM_GPUVA_OP_MAP:
 		err = xe_vm_bind(vm, vma, op->q, xe_vma_bo(vma),
 				 op->syncs, op->num_syncs,
-				 op->map.immediate || !xe_vm_in_fault_mode(vm),
+				 !xe_vm_in_fault_mode(vm),
 				 op->flags & XE_VMA_OP_FIRST,
 				 op->flags & XE_VMA_OP_LAST);
 		break;
@@ -2497,13 +2562,25 @@ retry_userptr:
 	}
 	drm_exec_fini(&exec);
 
-	if (err == -EAGAIN && xe_vma_is_userptr(vma)) {
+	if (err == -EAGAIN) {
 		lockdep_assert_held_write(&vm->lock);
-		err = xe_vma_userptr_pin_pages(vma);
-		if (!err)
-			goto retry_userptr;
 
-		trace_xe_vma_fail(vma);
+		if (op->base.op == DRM_GPUVA_OP_REMAP) {
+			if (!op->remap.unmap_done)
+				vma = gpuva_to_vma(op->base.remap.unmap->va);
+			else if (op->remap.prev)
+				vma = op->remap.prev;
+			else
+				vma = op->remap.next;
+		}
+
+		if (xe_vma_is_userptr(vma)) {
+			err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
+			if (!err)
+				goto retry_userptr;
+
+			trace_xe_vma_fail(vma);
+		}
 	}
 
 	return err;
@@ -2515,13 +2592,6 @@ static int xe_vma_op_execute(struct xe_vm *vm, struct xe_vma_op *op)
 
 	lockdep_assert_held_write(&vm->lock);
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-	if (op->inject_error) {
-		op->inject_error = false;
-		return -ENOMEM;
-	}
-#endif
-
 	switch (op->base.op) {
 	case DRM_GPUVA_OP_MAP:
 		ret = __xe_vma_op_execute(vm, op->map.vma, op);
@@ -2636,7 +2706,7 @@ static void vm_bind_ioctl_ops_unwind(struct xe_vm *vm,
 {
 	int i;
 
-	for (i = num_ops_list - 1; i; ++i) {
+	for (i = num_ops_list - 1; i >= 0; --i) {
 		struct drm_gpuva_ops *__ops = ops[i];
 		struct drm_gpuva_op *__op;
 
@@ -2681,21 +2751,11 @@ static int vm_bind_ioctl_ops_execute(struct xe_vm *vm,
 	return 0;
 }
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-#define SUPPORTED_FLAGS	\
-	(FORCE_ASYNC_OP_ERROR | DRM_XE_VM_BIND_FLAG_READONLY | \
-	 DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL | 0xffff)
-#else
-#define SUPPORTED_FLAGS	\
-	(DRM_XE_VM_BIND_FLAG_READONLY | \
-	 DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL | \
-	 0xffff)
-#endif
+#define SUPPORTED_FLAGS	(DRM_XE_VM_BIND_FLAG_NULL | \
+	 DRM_XE_VM_BIND_FLAG_DUMPABLE)
 #define XE_64K_PAGE_MASK 0xffffull
 #define ALL_DRM_XE_SYNCS_FLAGS (DRM_XE_SYNCS_FLAG_WAIT_FOR_OP)
 
-#define MAX_BINDS	512	/* FIXME: Picking random upper limit */
-
 static int vm_bind_ioctl_check_args(struct xe_device *xe,
 				    struct drm_xe_vm_bind *args,
 				    struct drm_xe_vm_bind_op **bind_ops)
@@ -2707,16 +2767,16 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe,
 	    XE_IOCTL_DBG(xe, args->reserved[0] || args->reserved[1]))
 		return -EINVAL;
 
-	if (XE_IOCTL_DBG(xe, args->extensions) ||
-	    XE_IOCTL_DBG(xe, args->num_binds > MAX_BINDS))
+	if (XE_IOCTL_DBG(xe, args->extensions))
 		return -EINVAL;
 
 	if (args->num_binds > 1) {
 		u64 __user *bind_user =
 			u64_to_user_ptr(args->vector_of_binds);
 
-		*bind_ops = kmalloc(sizeof(struct drm_xe_vm_bind_op) *
-				    args->num_binds, GFP_KERNEL);
+		*bind_ops = kvmalloc_array(args->num_binds,
+					   sizeof(struct drm_xe_vm_bind_op),
+					   GFP_KERNEL | __GFP_ACCOUNT);
 		if (!*bind_ops)
 			return -ENOMEM;
 
@@ -2806,7 +2866,7 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe,
 
 free_bind_ops:
 	if (args->num_binds > 1)
-		kfree(*bind_ops);
+		kvfree(*bind_ops);
 	return err;
 }
 
@@ -2843,7 +2903,7 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	struct drm_gpuva_ops **ops = NULL;
 	struct xe_vm *vm;
 	struct xe_exec_queue *q = NULL;
-	u32 num_syncs;
+	u32 num_syncs, num_ufence = 0;
 	struct xe_sync_entry *syncs = NULL;
 	struct drm_xe_vm_bind_op *bind_ops;
 	LIST_HEAD(ops_list);
@@ -2894,13 +2954,15 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	}
 
 	if (args->num_binds) {
-		bos = kcalloc(args->num_binds, sizeof(*bos), GFP_KERNEL);
+		bos = kvcalloc(args->num_binds, sizeof(*bos),
+			       GFP_KERNEL | __GFP_ACCOUNT);
 		if (!bos) {
 			err = -ENOMEM;
 			goto release_vm_lock;
 		}
 
-		ops = kcalloc(args->num_binds, sizeof(*ops), GFP_KERNEL);
+		ops = kvcalloc(args->num_binds, sizeof(*ops),
+			       GFP_KERNEL | __GFP_ACCOUNT);
 		if (!ops) {
 			err = -ENOMEM;
 			goto release_vm_lock;
@@ -2980,6 +3042,14 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 					   SYNC_PARSE_FLAG_DISALLOW_USER_FENCE : 0));
 		if (err)
 			goto free_syncs;
+
+		if (xe_sync_is_ufence(&syncs[num_syncs]))
+			num_ufence++;
+	}
+
+	if (XE_IOCTL_DBG(xe, num_ufence > 1)) {
+		err = -EINVAL;
+		goto free_syncs;
 	}
 
 	if (!args->num_binds) {
@@ -3033,10 +3103,10 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	for (i = 0; bos && i < args->num_binds; ++i)
 		xe_bo_put(bos[i]);
 
-	kfree(bos);
-	kfree(ops);
+	kvfree(bos);
+	kvfree(ops);
 	if (args->num_binds > 1)
-		kfree(bind_ops);
+		kvfree(bind_ops);
 
 	return err;
 
@@ -3060,10 +3130,10 @@ put_exec_queue:
 	if (q)
 		xe_exec_queue_put(q);
 free_objs:
-	kfree(bos);
-	kfree(ops);
+	kvfree(bos);
+	kvfree(ops);
 	if (args->num_binds > 1)
-		kfree(bind_ops);
+		kvfree(bind_ops);
 	return err;
 }
 
@@ -3122,8 +3192,8 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
 		if (xe_vma_is_userptr(vma)) {
 			WARN_ON_ONCE(!mmu_interval_check_retry
-				     (&vma->userptr.notifier,
-				      vma->userptr.notifier_seq));
+				     (&to_userptr_vma(vma)->userptr.notifier,
+				      to_userptr_vma(vma)->userptr.notifier_seq));
 			WARN_ON_ONCE(!dma_resv_test_signaled(xe_vm_resv(xe_vma_vm(vma)),
 							     DMA_RESV_USAGE_BOOKKEEP));
 
@@ -3184,11 +3254,11 @@ int xe_analyze_vm(struct drm_printer *p, struct xe_vm *vm, int gt_id)
 		if (is_null) {
 			addr = 0;
 		} else if (is_userptr) {
+			struct sg_table *sg = to_userptr_vma(vma)->userptr.sg;
 			struct xe_res_cursor cur;
 
-			if (vma->userptr.sg) {
-				xe_res_first_sg(vma->userptr.sg, 0, XE_PAGE_SIZE,
-						&cur);
+			if (sg) {
+				xe_res_first_sg(sg, 0, XE_PAGE_SIZE, &cur);
 				addr = xe_res_dma(&cur);
 			} else {
 				addr = 0;
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index cf2f96e8c1ab..9654a0612fc2 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -160,6 +160,18 @@ static inline bool xe_vma_is_userptr(struct xe_vma *vma)
 	return xe_vma_has_no_bo(vma) && !xe_vma_is_null(vma);
 }
 
+/**
+ * to_userptr_vma() - Return a pointer to an embedding userptr vma
+ * @vma: Pointer to the embedded struct xe_vma
+ *
+ * Return: Pointer to the embedding userptr vma
+ */
+static inline struct xe_userptr_vma *to_userptr_vma(struct xe_vma *vma)
+{
+	xe_assert(xe_vma_vm(vma)->xe, xe_vma_is_userptr(vma));
+	return container_of(vma, struct xe_userptr_vma, vma);
+}
+
 u64 xe_vm_pdp4_descriptor(struct xe_vm *vm, struct xe_tile *tile);
 
 int xe_vm_create_ioctl(struct drm_device *dev, void *data,
@@ -224,9 +236,9 @@ static inline void xe_vm_reactivate_rebind(struct xe_vm *vm)
 	}
 }
 
-int xe_vma_userptr_pin_pages(struct xe_vma *vma);
+int xe_vma_userptr_pin_pages(struct xe_userptr_vma *uvma);
 
-int xe_vma_userptr_check_repin(struct xe_vma *vma);
+int xe_vma_userptr_check_repin(struct xe_userptr_vma *uvma);
 
 bool xe_vm_validate_should_retry(struct drm_exec *exec, int err, ktime_t *end);
 
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 63e8a50b88e9..7300eea5394b 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -19,11 +19,9 @@
 
 struct xe_bo;
 struct xe_sync_entry;
+struct xe_user_fence;
 struct xe_vm;
 
-#define TEST_VM_ASYNC_OPS_ERROR
-#define FORCE_ASYNC_OP_ERROR	BIT(31)
-
 #define XE_VMA_READ_ONLY	DRM_GPUVA_USERBITS
 #define XE_VMA_DESTROYED	(DRM_GPUVA_USERBITS << 1)
 #define XE_VMA_ATOMIC_PTE_BIT	(DRM_GPUVA_USERBITS << 2)
@@ -32,11 +30,15 @@ struct xe_vm;
 #define XE_VMA_PTE_4K		(DRM_GPUVA_USERBITS << 5)
 #define XE_VMA_PTE_2M		(DRM_GPUVA_USERBITS << 6)
 #define XE_VMA_PTE_1G		(DRM_GPUVA_USERBITS << 7)
+#define XE_VMA_PTE_64K		(DRM_GPUVA_USERBITS << 8)
+#define XE_VMA_PTE_COMPACT	(DRM_GPUVA_USERBITS << 9)
 
 /** struct xe_userptr - User pointer */
 struct xe_userptr {
 	/** @invalidate_link: Link for the vm::userptr.invalidated list */
 	struct list_head invalidate_link;
+	/** @userptr: link into VM repin list if userptr. */
+	struct list_head repin_link;
 	/**
 	 * @notifier: MMU notifier for user pointer (invalidation call back)
 	 */
@@ -68,8 +70,6 @@ struct xe_vma {
 	 * resv.
 	 */
 	union {
-		/** @userptr: link into VM repin list if userptr. */
-		struct list_head userptr;
 		/** @rebind: link into VM if this VMA needs rebinding. */
 		struct list_head rebind;
 		/** @destroy: link to contested list when VM is being closed. */
@@ -107,9 +107,19 @@ struct xe_vma {
 	u16 pat_index;
 
 	/**
-	 * @userptr: user pointer state, only allocated for VMAs that are
-	 * user pointers
+	 * @ufence: The user fence that was provided with MAP.
+	 * Needs to be signalled before UNMAP can be processed.
 	 */
+	struct xe_user_fence *ufence;
+};
+
+/**
+ * struct xe_userptr_vma - A userptr vma subclass
+ * @vma: The vma.
+ * @userptr: Additional userptr information.
+ */
+struct xe_userptr_vma {
+	struct xe_vma vma;
 	struct xe_userptr userptr;
 };
 
@@ -285,10 +295,6 @@ struct xe_vm {
 struct xe_vma_op_map {
 	/** @vma: VMA to map */
 	struct xe_vma *vma;
-	/** @immediate: Immediate bind */
-	bool immediate;
-	/** @read_only: Read only */
-	bool read_only;
 	/** @is_null: is NULL binding */
 	bool is_null;
 	/** @pat_index: The pat index to use for this operation. */
@@ -356,11 +362,6 @@ struct xe_vma_op {
 	/** @flags: operation flags */
 	enum xe_vma_op_flags flags;
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-	/** @inject_error: inject error to test async op error handling */
-	bool inject_error;
-#endif
-
 	union {
 		/** @map: VMA map operation specific data */
 		struct xe_vma_op_map map;
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index 42fd504abbcd..89983d7d73ca 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/drivers/gpu/host1x/dev.c
@@ -169,6 +169,7 @@ static const struct host1x_info host1x06_info = {
 	.num_sid_entries = ARRAY_SIZE(tegra186_sid_table),
 	.sid_table = tegra186_sid_table,
 	.reserve_vblank_syncpts = false,
+	.skip_reset_assert = true,
 };
 
 static const struct host1x_sid_entry tegra194_sid_table[] = {
@@ -680,13 +681,15 @@ static int __maybe_unused host1x_runtime_suspend(struct device *dev)
 	host1x_intr_stop(host);
 	host1x_syncpt_save(host);
 
-	err = reset_control_bulk_assert(host->nresets, host->resets);
-	if (err) {
-		dev_err(dev, "failed to assert reset: %d\n", err);
-		goto resume_host1x;
-	}
+	if (!host->info->skip_reset_assert) {
+		err = reset_control_bulk_assert(host->nresets, host->resets);
+		if (err) {
+			dev_err(dev, "failed to assert reset: %d\n", err);
+			goto resume_host1x;
+		}
 
-	usleep_range(1000, 2000);
+		usleep_range(1000, 2000);
+	}
 
 	clk_disable_unprepare(host->clk);
 	reset_control_bulk_release(host->nresets, host->resets);
diff --git a/drivers/gpu/host1x/dev.h b/drivers/gpu/host1x/dev.h
index c8e302de7625..925a118db23f 100644
--- a/drivers/gpu/host1x/dev.h
+++ b/drivers/gpu/host1x/dev.h
@@ -116,6 +116,12 @@ struct host1x_info {
 	 * the display driver disables VBLANK increments.
 	 */
 	bool reserve_vblank_syncpts;
+	/*
+	 * On Tegra186, secure world applications may require access to
+	 * host1x during suspend/resume. To allow this, we need to leave
+	 * host1x not in reset.
+	 */
+	bool skip_reset_assert;
 };
 
 struct host1x {
diff --git a/drivers/greybus/gb-beagleplay.c b/drivers/greybus/gb-beagleplay.c
index 43318c1993ba..c3e90025064b 100644
--- a/drivers/greybus/gb-beagleplay.c
+++ b/drivers/greybus/gb-beagleplay.c
@@ -85,17 +85,31 @@ struct hdlc_payload {
 	void *buf;
 };
 
+/**
+ * struct hdlc_greybus_frame - Structure to represent greybus HDLC frame payload
+ *
+ * @cport: cport id
+ * @hdr: greybus operation header
+ * @payload: greybus message payload
+ *
+ * The HDLC payload sent over UART for greybus address has cport preappended to greybus message
+ */
+struct hdlc_greybus_frame {
+	__le16 cport;
+	struct gb_operation_msg_hdr hdr;
+	u8 payload[];
+} __packed;
+
 static void hdlc_rx_greybus_frame(struct gb_beagleplay *bg, u8 *buf, u16 len)
 {
-	u16 cport_id;
-	struct gb_operation_msg_hdr *hdr = (struct gb_operation_msg_hdr *)buf;
-
-	memcpy(&cport_id, hdr->pad, sizeof(cport_id));
+	struct hdlc_greybus_frame *gb_frame = (struct hdlc_greybus_frame *)buf;
+	u16 cport_id = le16_to_cpu(gb_frame->cport);
+	u16 gb_msg_len = le16_to_cpu(gb_frame->hdr.size);
 
 	dev_dbg(&bg->sd->dev, "Greybus Operation %u type %X cport %u status %u received",
-		hdr->operation_id, hdr->type, cport_id, hdr->result);
+		gb_frame->hdr.operation_id, gb_frame->hdr.type, cport_id, gb_frame->hdr.result);
 
-	greybus_data_rcvd(bg->gb_hd, cport_id, buf, len);
+	greybus_data_rcvd(bg->gb_hd, cport_id, (u8 *)&gb_frame->hdr, gb_msg_len);
 }
 
 static void hdlc_rx_dbg_frame(const struct gb_beagleplay *bg, const char *buf, u16 len)
@@ -257,7 +271,7 @@ static void hdlc_rx_frame(struct gb_beagleplay *bg)
 	}
 }
 
-static int hdlc_rx(struct gb_beagleplay *bg, const u8 *data, size_t count)
+static ssize_t hdlc_rx(struct gb_beagleplay *bg, const u8 *data, size_t count)
 {
 	size_t i;
 	u8 c;
@@ -317,7 +331,8 @@ static void hdlc_deinit(struct gb_beagleplay *bg)
 	flush_work(&bg->tx_work);
 }
 
-static int gb_tty_receive(struct serdev_device *sd, const unsigned char *data, size_t count)
+static ssize_t gb_tty_receive(struct serdev_device *sd, const u8 *data,
+			      size_t count)
 {
 	struct gb_beagleplay *bg = serdev_device_get_drvdata(sd);
 
@@ -336,25 +351,39 @@ static struct serdev_device_ops gb_beagleplay_ops = {
 	.write_wakeup = gb_tty_wakeup,
 };
 
+/**
+ * gb_message_send() - Send greybus message using HDLC over UART
+ *
+ * @hd: pointer to greybus host device
+ * @cport: AP cport where message originates
+ * @msg: greybus message to send
+ * @mask: gfp mask
+ *
+ * Greybus HDLC frame has the following payload:
+ * 1. le16 cport
+ * 2. gb_operation_msg_hdr msg_header
+ * 3. u8 *msg_payload
+ */
 static int gb_message_send(struct gb_host_device *hd, u16 cport, struct gb_message *msg, gfp_t mask)
 {
 	struct gb_beagleplay *bg = dev_get_drvdata(&hd->dev);
-	struct hdlc_payload payloads[2];
+	struct hdlc_payload payloads[3];
+	__le16 cport_id = cpu_to_le16(cport);
 
 	dev_dbg(&hd->dev, "Sending greybus message with Operation %u, Type: %X on Cport %u",
 		msg->header->operation_id, msg->header->type, cport);
 
-	if (msg->header->size > RX_HDLC_PAYLOAD)
+	if (le16_to_cpu(msg->header->size) > RX_HDLC_PAYLOAD)
 		return dev_err_probe(&hd->dev, -E2BIG, "Greybus message too big");
 
-	memcpy(msg->header->pad, &cport, sizeof(cport));
-
-	payloads[0].buf = msg->header;
-	payloads[0].len = sizeof(*msg->header);
-	payloads[1].buf = msg->payload;
-	payloads[1].len = msg->payload_size;
+	payloads[0].buf = &cport_id;
+	payloads[0].len = sizeof(cport_id);
+	payloads[1].buf = msg->header;
+	payloads[1].len = sizeof(*msg->header);
+	payloads[2].buf = msg->payload;
+	payloads[2].len = msg->payload_size;
 
-	hdlc_tx_frames(bg, ADDRESS_GREYBUS, 0x03, payloads, 2);
+	hdlc_tx_frames(bg, ADDRESS_GREYBUS, 0x03, payloads, 3);
 	greybus_message_sent(bg->gb_hd, msg, 0);
 
 	return 0;
diff --git a/drivers/hid/bpf/hid_bpf_dispatch.c b/drivers/hid/bpf/hid_bpf_dispatch.c
index d9ef45fcaeab..470ae2c29c94 100644
--- a/drivers/hid/bpf/hid_bpf_dispatch.c
+++ b/drivers/hid/bpf/hid_bpf_dispatch.c
@@ -143,6 +143,9 @@ u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, u8 *rdesc, unsigned int *s
 }
 EXPORT_SYMBOL_GPL(call_hid_bpf_rdesc_fixup);
 
+/* Disables missing prototype warnings */
+__bpf_kfunc_start_defs();
+
 /**
  * hid_bpf_get_data - Get the kernel memory pointer associated with the context @ctx
  *
@@ -152,7 +155,7 @@ EXPORT_SYMBOL_GPL(call_hid_bpf_rdesc_fixup);
  *
  * @returns %NULL on error, an %__u8 memory pointer on success
  */
-noinline __u8 *
+__bpf_kfunc __u8 *
 hid_bpf_get_data(struct hid_bpf_ctx *ctx, unsigned int offset, const size_t rdwr_buf_size)
 {
 	struct hid_bpf_ctx_kern *ctx_kern;
@@ -167,6 +170,7 @@ hid_bpf_get_data(struct hid_bpf_ctx *ctx, unsigned int offset, const size_t rdwr
 
 	return ctx_kern->data + offset;
 }
+__bpf_kfunc_end_defs();
 
 /*
  * The following set contains all functions we agree BPF programs
@@ -241,6 +245,42 @@ int hid_bpf_reconnect(struct hid_device *hdev)
 	return 0;
 }
 
+static int do_hid_bpf_attach_prog(struct hid_device *hdev, int prog_fd, struct bpf_prog *prog,
+				  __u32 flags)
+{
+	int fd, err, prog_type;
+
+	prog_type = hid_bpf_get_prog_attach_type(prog);
+	if (prog_type < 0)
+		return prog_type;
+
+	if (prog_type >= HID_BPF_PROG_TYPE_MAX)
+		return -EINVAL;
+
+	if (prog_type == HID_BPF_PROG_TYPE_DEVICE_EVENT) {
+		err = hid_bpf_allocate_event_data(hdev);
+		if (err)
+			return err;
+	}
+
+	fd = __hid_bpf_attach_prog(hdev, prog_type, prog_fd, prog, flags);
+	if (fd < 0)
+		return fd;
+
+	if (prog_type == HID_BPF_PROG_TYPE_RDESC_FIXUP) {
+		err = hid_bpf_reconnect(hdev);
+		if (err) {
+			close_fd(fd);
+			return err;
+		}
+	}
+
+	return fd;
+}
+
+/* Disables missing prototype warnings */
+__bpf_kfunc_start_defs();
+
 /**
  * hid_bpf_attach_prog - Attach the given @prog_fd to the given HID device
  *
@@ -253,22 +293,17 @@ int hid_bpf_reconnect(struct hid_device *hdev)
  * is pinned to the BPF file system).
  */
 /* called from syscall */
-noinline int
+__bpf_kfunc int
 hid_bpf_attach_prog(unsigned int hid_id, int prog_fd, __u32 flags)
 {
 	struct hid_device *hdev;
+	struct bpf_prog *prog;
 	struct device *dev;
-	int fd, err, prog_type = hid_bpf_get_prog_attach_type(prog_fd);
+	int err, fd;
 
 	if (!hid_bpf_ops)
 		return -EINVAL;
 
-	if (prog_type < 0)
-		return prog_type;
-
-	if (prog_type >= HID_BPF_PROG_TYPE_MAX)
-		return -EINVAL;
-
 	if ((flags & ~HID_BPF_FLAG_MASK))
 		return -EINVAL;
 
@@ -278,25 +313,29 @@ hid_bpf_attach_prog(unsigned int hid_id, int prog_fd, __u32 flags)
 
 	hdev = to_hid_device(dev);
 
-	if (prog_type == HID_BPF_PROG_TYPE_DEVICE_EVENT) {
-		err = hid_bpf_allocate_event_data(hdev);
-		if (err)
-			return err;
+	/*
+	 * take a ref on the prog itself, it will be released
+	 * on errors or when it'll be detached
+	 */
+	prog = bpf_prog_get(prog_fd);
+	if (IS_ERR(prog)) {
+		err = PTR_ERR(prog);
+		goto out_dev_put;
 	}
 
-	fd = __hid_bpf_attach_prog(hdev, prog_type, prog_fd, flags);
-	if (fd < 0)
-		return fd;
-
-	if (prog_type == HID_BPF_PROG_TYPE_RDESC_FIXUP) {
-		err = hid_bpf_reconnect(hdev);
-		if (err) {
-			close_fd(fd);
-			return err;
-		}
+	fd = do_hid_bpf_attach_prog(hdev, prog_fd, prog, flags);
+	if (fd < 0) {
+		err = fd;
+		goto out_prog_put;
 	}
 
 	return fd;
+
+ out_prog_put:
+	bpf_prog_put(prog);
+ out_dev_put:
+	put_device(dev);
+	return err;
 }
 
 /**
@@ -306,7 +345,7 @@ hid_bpf_attach_prog(unsigned int hid_id, int prog_fd, __u32 flags)
  *
  * @returns A pointer to &struct hid_bpf_ctx on success, %NULL on error.
  */
-noinline struct hid_bpf_ctx *
+__bpf_kfunc struct hid_bpf_ctx *
 hid_bpf_allocate_context(unsigned int hid_id)
 {
 	struct hid_device *hdev;
@@ -323,8 +362,10 @@ hid_bpf_allocate_context(unsigned int hid_id)
 	hdev = to_hid_device(dev);
 
 	ctx_kern = kzalloc(sizeof(*ctx_kern), GFP_KERNEL);
-	if (!ctx_kern)
+	if (!ctx_kern) {
+		put_device(dev);
 		return NULL;
+	}
 
 	ctx_kern->ctx.hid = hdev;
 
@@ -337,14 +378,19 @@ hid_bpf_allocate_context(unsigned int hid_id)
  * @ctx: the HID-BPF context to release
  *
  */
-noinline void
+__bpf_kfunc void
 hid_bpf_release_context(struct hid_bpf_ctx *ctx)
 {
 	struct hid_bpf_ctx_kern *ctx_kern;
+	struct hid_device *hid;
 
 	ctx_kern = container_of(ctx, struct hid_bpf_ctx_kern, ctx);
+	hid = (struct hid_device *)ctx_kern->ctx.hid; /* ignore const */
 
 	kfree(ctx_kern);
+
+	/* get_device() is called by bus_find_device() */
+	put_device(&hid->dev);
 }
 
 /**
@@ -358,7 +404,7 @@ hid_bpf_release_context(struct hid_bpf_ctx *ctx)
  *
  * @returns %0 on success, a negative error code otherwise.
  */
-noinline int
+__bpf_kfunc int
 hid_bpf_hw_request(struct hid_bpf_ctx *ctx, __u8 *buf, size_t buf__sz,
 		   enum hid_report_type rtype, enum hid_class_request reqtype)
 {
@@ -426,6 +472,7 @@ hid_bpf_hw_request(struct hid_bpf_ctx *ctx, __u8 *buf, size_t buf__sz,
 	kfree(dma_data);
 	return ret;
 }
+__bpf_kfunc_end_defs();
 
 /* our HID-BPF entrypoints */
 BTF_SET8_START(hid_bpf_fmodret_ids)
diff --git a/drivers/hid/bpf/hid_bpf_dispatch.h b/drivers/hid/bpf/hid_bpf_dispatch.h
index 63dfc8605cd2..fbe0639d09f2 100644
--- a/drivers/hid/bpf/hid_bpf_dispatch.h
+++ b/drivers/hid/bpf/hid_bpf_dispatch.h
@@ -12,9 +12,9 @@ struct hid_bpf_ctx_kern {
 
 int hid_bpf_preload_skel(void);
 void hid_bpf_free_links_and_skel(void);
-int hid_bpf_get_prog_attach_type(int prog_fd);
+int hid_bpf_get_prog_attach_type(struct bpf_prog *prog);
 int __hid_bpf_attach_prog(struct hid_device *hdev, enum hid_bpf_prog_type prog_type, int prog_fd,
-			  __u32 flags);
+			  struct bpf_prog *prog, __u32 flags);
 void __hid_bpf_destroy_device(struct hid_device *hdev);
 int hid_bpf_prog_run(struct hid_device *hdev, enum hid_bpf_prog_type type,
 		     struct hid_bpf_ctx_kern *ctx_kern);
diff --git a/drivers/hid/bpf/hid_bpf_jmp_table.c b/drivers/hid/bpf/hid_bpf_jmp_table.c
index eca34b7372f9..aa8e1c79cdf5 100644
--- a/drivers/hid/bpf/hid_bpf_jmp_table.c
+++ b/drivers/hid/bpf/hid_bpf_jmp_table.c
@@ -196,6 +196,7 @@ static void __hid_bpf_do_release_prog(int map_fd, unsigned int idx)
 static void hid_bpf_release_progs(struct work_struct *work)
 {
 	int i, j, n, map_fd = -1;
+	bool hdev_destroyed;
 
 	if (!jmp_table.map)
 		return;
@@ -220,6 +221,12 @@ static void hid_bpf_release_progs(struct work_struct *work)
 		if (entry->hdev) {
 			hdev = entry->hdev;
 			type = entry->type;
+			/*
+			 * hdev is still valid, even if we are called after hid_destroy_device():
+			 * when hid_bpf_attach() gets called, it takes a ref on the dev through
+			 * bus_find_device()
+			 */
+			hdev_destroyed = hdev->bpf.destroyed;
 
 			hid_bpf_populate_hdev(hdev, type);
 
@@ -232,12 +239,19 @@ static void hid_bpf_release_progs(struct work_struct *work)
 				if (test_bit(next->idx, jmp_table.enabled))
 					continue;
 
-				if (next->hdev == hdev && next->type == type)
+				if (next->hdev == hdev && next->type == type) {
+					/*
+					 * clear the hdev reference and decrement the device ref
+					 * that was taken during bus_find_device() while calling
+					 * hid_bpf_attach()
+					 */
 					next->hdev = NULL;
+					put_device(&hdev->dev);
+				}
 			}
 
-			/* if type was rdesc fixup, reconnect device */
-			if (type == HID_BPF_PROG_TYPE_RDESC_FIXUP)
+			/* if type was rdesc fixup and the device is not gone, reconnect device */
+			if (type == HID_BPF_PROG_TYPE_RDESC_FIXUP && !hdev_destroyed)
 				hid_bpf_reconnect(hdev);
 		}
 	}
@@ -333,15 +347,10 @@ static int hid_bpf_insert_prog(int prog_fd, struct bpf_prog *prog)
 	return err;
 }
 
-int hid_bpf_get_prog_attach_type(int prog_fd)
+int hid_bpf_get_prog_attach_type(struct bpf_prog *prog)
 {
-	struct bpf_prog *prog = NULL;
-	int i;
 	int prog_type = HID_BPF_PROG_TYPE_UNDEF;
-
-	prog = bpf_prog_get(prog_fd);
-	if (IS_ERR(prog))
-		return PTR_ERR(prog);
+	int i;
 
 	for (i = 0; i < HID_BPF_PROG_TYPE_MAX; i++) {
 		if (hid_bpf_btf_ids[i] == prog->aux->attach_btf_id) {
@@ -350,8 +359,6 @@ int hid_bpf_get_prog_attach_type(int prog_fd)
 		}
 	}
 
-	bpf_prog_put(prog);
-
 	return prog_type;
 }
 
@@ -388,19 +395,13 @@ static const struct bpf_link_ops hid_bpf_link_lops = {
 /* called from syscall */
 noinline int
 __hid_bpf_attach_prog(struct hid_device *hdev, enum hid_bpf_prog_type prog_type,
-		      int prog_fd, __u32 flags)
+		      int prog_fd, struct bpf_prog *prog, __u32 flags)
 {
 	struct bpf_link_primer link_primer;
 	struct hid_bpf_link *link;
-	struct bpf_prog *prog = NULL;
 	struct hid_bpf_prog_entry *prog_entry;
 	int cnt, err = -EINVAL, prog_table_idx = -1;
 
-	/* take a ref on the prog itself */
-	prog = bpf_prog_get(prog_fd);
-	if (IS_ERR(prog))
-		return PTR_ERR(prog);
-
 	mutex_lock(&hid_bpf_attach_lock);
 
 	link = kzalloc(sizeof(*link), GFP_USER);
@@ -467,7 +468,6 @@ __hid_bpf_attach_prog(struct hid_device *hdev, enum hid_bpf_prog_type prog_type,
  err_unlock:
 	mutex_unlock(&hid_bpf_attach_lock);
 
-	bpf_prog_put(prog);
 	kfree(link);
 
 	return err;
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index fb30e228d35f..828a5c022c64 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -298,6 +298,9 @@
 
 #define USB_VENDOR_ID_CIDC		0x1677
 
+#define I2C_VENDOR_ID_CIRQUE           0x0488
+#define I2C_PRODUCT_ID_CIRQUE_1063     0x1063
+
 #define USB_VENDOR_ID_CJTOUCH		0x24b8
 #define USB_DEVICE_ID_CJTOUCH_MULTI_TOUCH_0020	0x0020
 #define USB_DEVICE_ID_CJTOUCH_MULTI_TOUCH_0040	0x0040
diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c
index fd6d8f1d9b8f..d2f3f234f29d 100644
--- a/drivers/hid/hid-logitech-hidpp.c
+++ b/drivers/hid/hid-logitech-hidpp.c
@@ -203,6 +203,8 @@ struct hidpp_device {
 	struct hidpp_scroll_counter vertical_wheel_counter;
 
 	u8 wireless_feature_index;
+
+	bool connected_once;
 };
 
 /* HID++ 1.0 error codes */
@@ -988,8 +990,13 @@ static int hidpp_root_get_protocol_version(struct hidpp_device *hidpp)
 	hidpp->protocol_minor = response.rap.params[1];
 
 print_version:
-	hid_info(hidpp->hid_dev, "HID++ %u.%u device connected.\n",
-		 hidpp->protocol_major, hidpp->protocol_minor);
+	if (!hidpp->connected_once) {
+		hid_info(hidpp->hid_dev, "HID++ %u.%u device connected.\n",
+			 hidpp->protocol_major, hidpp->protocol_minor);
+		hidpp->connected_once = true;
+	} else
+		hid_dbg(hidpp->hid_dev, "HID++ %u.%u device connected.\n",
+			 hidpp->protocol_major, hidpp->protocol_minor);
 	return 0;
 }
 
@@ -4184,7 +4191,7 @@ static void hidpp_connect_event(struct work_struct *work)
 	/* Get device version to check if it is connected */
 	ret = hidpp_root_get_protocol_version(hidpp);
 	if (ret) {
-		hid_info(hidpp->hid_dev, "Disconnected\n");
+		hid_dbg(hidpp->hid_dev, "Disconnected\n");
 		if (hidpp->battery.ps) {
 			hidpp->battery.online = false;
 			hidpp->battery.status = POWER_SUPPLY_STATUS_UNKNOWN;
@@ -4610,6 +4617,8 @@ static const struct hid_device_id hidpp_devices[] = {
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC088) },
 	{ /* Logitech G Pro X Superlight Gaming Mouse over USB */
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC094) },
+	{ /* Logitech G Pro X Superlight 2 Gaming Mouse over USB */
+	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC09b) },
 
 	{ /* G935 Gaming Headset */
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0x0a87),
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index fd5b0637dad6..3e91e4d6ba6f 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -2153,6 +2153,10 @@ static const struct hid_device_id mt_devices[] = {
 
 	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT,
 		HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
+			USB_VENDOR_ID_SYNAPTICS, 0xcddc) },
+
+	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT,
+		HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
 			USB_VENDOR_ID_SYNAPTICS, 0xce08) },
 
 	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT,
diff --git a/drivers/hid/hid-nvidia-shield.c b/drivers/hid/hid-nvidia-shield.c
index 82d0a77359c4..58b15750dbb0 100644
--- a/drivers/hid/hid-nvidia-shield.c
+++ b/drivers/hid/hid-nvidia-shield.c
@@ -800,6 +800,8 @@ static inline int thunderstrike_led_create(struct thunderstrike *ts)
 
 	led->name = devm_kasprintf(&ts->base.hdev->dev, GFP_KERNEL,
 				   "thunderstrike%d:blue:led", ts->id);
+	if (!led->name)
+		return -ENOMEM;
 	led->max_brightness = 1;
 	led->flags = LED_CORE_SUSPENDRESUME | LED_RETAIN_AT_SHUTDOWN;
 	led->brightness_get = &thunderstrike_led_get_brightness;
@@ -831,6 +833,8 @@ static inline int thunderstrike_psy_create(struct shield_device *shield_dev)
 	shield_dev->battery_dev.desc.name =
 		devm_kasprintf(&ts->base.hdev->dev, GFP_KERNEL,
 			       "thunderstrike_%d", ts->id);
+	if (!shield_dev->battery_dev.desc.name)
+		return -ENOMEM;
 
 	shield_dev->battery_dev.psy = power_supply_register(
 		&hdev->dev, &shield_dev->battery_dev.desc, &psy_cfg);
diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c
index b3c4e50e248a..b08a5ab58528 100644
--- a/drivers/hid/hid-steam.c
+++ b/drivers/hid/hid-steam.c
@@ -1109,10 +1109,9 @@ static int steam_probe(struct hid_device *hdev,
 		return hid_hw_start(hdev, HID_CONNECT_DEFAULT);
 
 	steam = devm_kzalloc(&hdev->dev, sizeof(*steam), GFP_KERNEL);
-	if (!steam) {
-		ret = -ENOMEM;
-		goto steam_alloc_fail;
-	}
+	if (!steam)
+		return -ENOMEM;
+
 	steam->hdev = hdev;
 	hid_set_drvdata(hdev, steam);
 	spin_lock_init(&steam->lock);
@@ -1129,14 +1128,14 @@ static int steam_probe(struct hid_device *hdev,
 	 */
 	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT & ~HID_CONNECT_HIDRAW);
 	if (ret)
-		goto hid_hw_start_fail;
+		goto err_cancel_work;
 
 	ret = hid_hw_open(hdev);
 	if (ret) {
 		hid_err(hdev,
 			"%s:hid_hw_open\n",
 			__func__);
-		goto hid_hw_open_fail;
+		goto err_hw_stop;
 	}
 
 	if (steam->quirks & STEAM_QUIRK_WIRELESS) {
@@ -1152,36 +1151,37 @@ static int steam_probe(struct hid_device *hdev,
 			hid_err(hdev,
 				"%s:steam_register failed with error %d\n",
 				__func__, ret);
-			goto input_register_fail;
+			goto err_hw_close;
 		}
 	}
 
 	steam->client_hdev = steam_create_client_hid(hdev);
 	if (IS_ERR(steam->client_hdev)) {
 		ret = PTR_ERR(steam->client_hdev);
-		goto client_hdev_fail;
+		goto err_stream_unregister;
 	}
 	steam->client_hdev->driver_data = steam;
 
 	ret = hid_add_device(steam->client_hdev);
 	if (ret)
-		goto client_hdev_add_fail;
+		goto err_destroy;
 
 	return 0;
 
-client_hdev_add_fail:
-	hid_hw_stop(hdev);
-client_hdev_fail:
+err_destroy:
 	hid_destroy_device(steam->client_hdev);
-input_register_fail:
-hid_hw_open_fail:
-hid_hw_start_fail:
+err_stream_unregister:
+	if (steam->connected)
+		steam_unregister(steam);
+err_hw_close:
+	hid_hw_close(hdev);
+err_hw_stop:
+	hid_hw_stop(hdev);
+err_cancel_work:
 	cancel_work_sync(&steam->work_connect);
 	cancel_delayed_work_sync(&steam->mode_switch);
 	cancel_work_sync(&steam->rumble_work);
-steam_alloc_fail:
-	hid_err(hdev, "%s: failed with error %d\n",
-			__func__, ret);
+
 	return ret;
 }
 
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index 13c8dd8cd350..2bc762d31ac7 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -357,8 +357,11 @@ static int hidraw_release(struct inode * inode, struct file * file)
 	down_write(&minors_rwsem);
 
 	spin_lock_irqsave(&hidraw_table[minor]->list_lock, flags);
-	for (int i = list->tail; i < list->head; i++)
-		kfree(list->buffer[i].value);
+	while (list->tail != list->head) {
+		kfree(list->buffer[list->tail].value);
+		list->buffer[list->tail].value = NULL;
+		list->tail = (list->tail + 1) & (HIDRAW_BUFFER_SIZE - 1);
+	}
 	list_del(&list->node);
 	spin_unlock_irqrestore(&hidraw_table[minor]->list_lock, flags);
 	kfree(list);
diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c
index 90f316ae9819..2df1ab3c31cc 100644
--- a/drivers/hid/i2c-hid/i2c-hid-core.c
+++ b/drivers/hid/i2c-hid/i2c-hid-core.c
@@ -49,6 +49,7 @@
 #define I2C_HID_QUIRK_RESET_ON_RESUME		BIT(2)
 #define I2C_HID_QUIRK_BAD_INPUT_SIZE		BIT(3)
 #define I2C_HID_QUIRK_NO_WAKEUP_AFTER_RESET	BIT(4)
+#define I2C_HID_QUIRK_NO_SLEEP_ON_SUSPEND	BIT(5)
 
 /* Command opcodes */
 #define I2C_HID_OPCODE_RESET			0x01
@@ -131,6 +132,8 @@ static const struct i2c_hid_quirks {
 		 I2C_HID_QUIRK_RESET_ON_RESUME },
 	{ USB_VENDOR_ID_ITE, I2C_DEVICE_ID_ITE_LENOVO_LEGION_Y720,
 		I2C_HID_QUIRK_BAD_INPUT_SIZE },
+	{ I2C_VENDOR_ID_CIRQUE, I2C_PRODUCT_ID_CIRQUE_1063,
+		I2C_HID_QUIRK_NO_SLEEP_ON_SUSPEND },
 	/*
 	 * Sending the wakeup after reset actually break ELAN touchscreen controller
 	 */
@@ -956,7 +959,8 @@ static int i2c_hid_core_suspend(struct i2c_hid *ihid, bool force_poweroff)
 		return ret;
 
 	/* Save some power */
-	i2c_hid_set_power(ihid, I2C_HID_PWR_SLEEP);
+	if (!(ihid->quirks & I2C_HID_QUIRK_NO_SLEEP_ON_SUSPEND))
+		i2c_hid_set_power(ihid, I2C_HID_PWR_SLEEP);
 
 	disable_irq(client->irq);
 
diff --git a/drivers/hid/i2c-hid/i2c-hid-of.c b/drivers/hid/i2c-hid/i2c-hid-of.c
index c4e1fa0273c8..8be4d576da77 100644
--- a/drivers/hid/i2c-hid/i2c-hid-of.c
+++ b/drivers/hid/i2c-hid/i2c-hid-of.c
@@ -87,6 +87,7 @@ static int i2c_hid_of_probe(struct i2c_client *client)
 	if (!ihid_of)
 		return -ENOMEM;
 
+	ihid_of->client = client;
 	ihid_of->ops.power_up = i2c_hid_of_power_up;
 	ihid_of->ops.power_down = i2c_hid_of_power_down;
 
diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c
index aa6cb033bb06..03d5601ce807 100644
--- a/drivers/hid/intel-ish-hid/ishtp/bus.c
+++ b/drivers/hid/intel-ish-hid/ishtp/bus.c
@@ -722,6 +722,8 @@ void ishtp_bus_remove_all_clients(struct ishtp_device *ishtp_dev,
 	spin_lock_irqsave(&ishtp_dev->cl_list_lock, flags);
 	list_for_each_entry(cl, &ishtp_dev->cl_list, link) {
 		cl->state = ISHTP_CL_DISCONNECTED;
+		if (warm_reset && cl->device->reference_count)
+			continue;
 
 		/*
 		 * Wake any pending process. The waiter would check dev->state
diff --git a/drivers/hid/intel-ish-hid/ishtp/client.c b/drivers/hid/intel-ish-hid/ishtp/client.c
index 82c907f01bd3..8a7f2f6a4f86 100644
--- a/drivers/hid/intel-ish-hid/ishtp/client.c
+++ b/drivers/hid/intel-ish-hid/ishtp/client.c
@@ -49,7 +49,9 @@ static void ishtp_read_list_flush(struct ishtp_cl *cl)
 	list_for_each_entry_safe(rb, next, &cl->dev->read_list.list, list)
 		if (rb->cl && ishtp_cl_cmp_id(cl, rb->cl)) {
 			list_del(&rb->list);
-			ishtp_io_rb_free(rb);
+			spin_lock(&cl->free_list_spinlock);
+			list_add_tail(&rb->list, &cl->free_rb_list.list);
+			spin_unlock(&cl->free_list_spinlock);
 		}
 	spin_unlock_irqrestore(&cl->dev->read_list_spinlock, flags);
 }
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index b613f11ed949..2bc45b24075c 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -2087,7 +2087,7 @@ static int wacom_allocate_inputs(struct wacom *wacom)
 	return 0;
 }
 
-static int wacom_register_inputs(struct wacom *wacom)
+static int wacom_setup_inputs(struct wacom *wacom)
 {
 	struct input_dev *pen_input_dev, *touch_input_dev, *pad_input_dev;
 	struct wacom_wac *wacom_wac = &(wacom->wacom_wac);
@@ -2106,10 +2106,6 @@ static int wacom_register_inputs(struct wacom *wacom)
 		input_free_device(pen_input_dev);
 		wacom_wac->pen_input = NULL;
 		pen_input_dev = NULL;
-	} else {
-		error = input_register_device(pen_input_dev);
-		if (error)
-			goto fail;
 	}
 
 	error = wacom_setup_touch_input_capabilities(touch_input_dev, wacom_wac);
@@ -2118,10 +2114,6 @@ static int wacom_register_inputs(struct wacom *wacom)
 		input_free_device(touch_input_dev);
 		wacom_wac->touch_input = NULL;
 		touch_input_dev = NULL;
-	} else {
-		error = input_register_device(touch_input_dev);
-		if (error)
-			goto fail;
 	}
 
 	error = wacom_setup_pad_input_capabilities(pad_input_dev, wacom_wac);
@@ -2130,7 +2122,34 @@ static int wacom_register_inputs(struct wacom *wacom)
 		input_free_device(pad_input_dev);
 		wacom_wac->pad_input = NULL;
 		pad_input_dev = NULL;
-	} else {
+	}
+
+	return 0;
+}
+
+static int wacom_register_inputs(struct wacom *wacom)
+{
+	struct input_dev *pen_input_dev, *touch_input_dev, *pad_input_dev;
+	struct wacom_wac *wacom_wac = &(wacom->wacom_wac);
+	int error = 0;
+
+	pen_input_dev = wacom_wac->pen_input;
+	touch_input_dev = wacom_wac->touch_input;
+	pad_input_dev = wacom_wac->pad_input;
+
+	if (pen_input_dev) {
+		error = input_register_device(pen_input_dev);
+		if (error)
+			goto fail;
+	}
+
+	if (touch_input_dev) {
+		error = input_register_device(touch_input_dev);
+		if (error)
+			goto fail;
+	}
+
+	if (pad_input_dev) {
 		error = input_register_device(pad_input_dev);
 		if (error)
 			goto fail;
@@ -2383,6 +2402,20 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless)
 	if (error)
 		goto fail;
 
+	error = wacom_setup_inputs(wacom);
+	if (error)
+		goto fail;
+
+	if (features->type == HID_GENERIC)
+		connect_mask |= HID_CONNECT_DRIVER;
+
+	/* Regular HID work starts now */
+	error = hid_hw_start(hdev, connect_mask);
+	if (error) {
+		hid_err(hdev, "hw start failed\n");
+		goto fail;
+	}
+
 	error = wacom_register_inputs(wacom);
 	if (error)
 		goto fail;
@@ -2397,16 +2430,6 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless)
 			goto fail;
 	}
 
-	if (features->type == HID_GENERIC)
-		connect_mask |= HID_CONNECT_DRIVER;
-
-	/* Regular HID work starts now */
-	error = hid_hw_start(hdev, connect_mask);
-	if (error) {
-		hid_err(hdev, "hw start failed\n");
-		goto fail;
-	}
-
 	if (!wireless) {
 		/* Note that if query fails it is not a hard failure */
 		wacom_query_tablet_data(wacom);
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index da8a01fedd39..fbe10fbc5769 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -2575,7 +2575,14 @@ static void wacom_wac_pen_report(struct hid_device *hdev,
 				wacom_wac->hid_data.tipswitch);
 		input_report_key(input, wacom_wac->tool[0], sense);
 		if (wacom_wac->serial[0]) {
-			input_event(input, EV_MSC, MSC_SERIAL, wacom_wac->serial[0]);
+			/*
+			 * xf86-input-wacom does not accept a serial number
+			 * of '0'. Report the low 32 bits if possible, but
+			 * if they are zero, report the upper ones instead.
+			 */
+			__u32 serial_lo = wacom_wac->serial[0] & 0xFFFFFFFFu;
+			__u32 serial_hi = wacom_wac->serial[0] >> 32;
+			input_event(input, EV_MSC, MSC_SERIAL, (int)(serial_lo ? serial_lo : serial_hi));
 			input_report_abs(input, ABS_MISC, sense ? id : 0);
 		}
 
diff --git a/drivers/hsi/controllers/omap_ssi_core.c b/drivers/hsi/controllers/omap_ssi_core.c
index 4c1a00f9929e..6802efb4d6cd 100644
--- a/drivers/hsi/controllers/omap_ssi_core.c
+++ b/drivers/hsi/controllers/omap_ssi_core.c
@@ -355,7 +355,7 @@ static int ssi_add_controller(struct hsi_controller *ssi,
 	if (!omap_ssi)
 		return -ENOMEM;
 
-	err = ida_simple_get(&platform_omap_ssi_ida, 0, 0, GFP_KERNEL);
+	err = ida_alloc(&platform_omap_ssi_ida, GFP_KERNEL);
 	if (err < 0)
 		return err;
 	ssi->id = err;
@@ -417,7 +417,7 @@ static int ssi_add_controller(struct hsi_controller *ssi,
 	return 0;
 
 out_err:
-	ida_simple_remove(&platform_omap_ssi_ida, ssi->id);
+	ida_free(&platform_omap_ssi_ida, ssi->id);
 	return err;
 }
 
@@ -451,7 +451,7 @@ static void ssi_remove_controller(struct hsi_controller *ssi)
 	tasklet_kill(&omap_ssi->gdd_tasklet);
 	hsi_unregister_controller(ssi);
 	clk_notifier_unregister(omap_ssi->fck, &omap_ssi->fck_nb);
-	ida_simple_remove(&platform_omap_ssi_ida, id);
+	ida_free(&platform_omap_ssi_ida, id);
 }
 
 static inline int ssi_of_get_available_ports_count(const struct device_node *np)
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 56f7e06c673e..adbf674355b2 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -322,125 +322,89 @@ static int create_gpadl_header(enum hv_gpadl_type type, void *kbuffer,
 
 	pagecount = hv_gpadl_size(type, size) >> HV_HYP_PAGE_SHIFT;
 
-	/* do we need a gpadl body msg */
 	pfnsize = MAX_SIZE_CHANNEL_MESSAGE -
 		  sizeof(struct vmbus_channel_gpadl_header) -
 		  sizeof(struct gpa_range);
+	pfncount = umin(pagecount, pfnsize / sizeof(u64));
+
+	msgsize = sizeof(struct vmbus_channel_msginfo) +
+		  sizeof(struct vmbus_channel_gpadl_header) +
+		  sizeof(struct gpa_range) + pfncount * sizeof(u64);
+	msgheader =  kzalloc(msgsize, GFP_KERNEL);
+	if (!msgheader)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&msgheader->submsglist);
+	msgheader->msgsize = msgsize;
+
+	gpadl_header = (struct vmbus_channel_gpadl_header *)
+		msgheader->msg;
+	gpadl_header->rangecount = 1;
+	gpadl_header->range_buflen = sizeof(struct gpa_range) +
+				 pagecount * sizeof(u64);
+	gpadl_header->range[0].byte_offset = 0;
+	gpadl_header->range[0].byte_count = hv_gpadl_size(type, size);
+	for (i = 0; i < pfncount; i++)
+		gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn(
+			type, kbuffer, size, send_offset, i);
+	*msginfo = msgheader;
+
+	pfnsum = pfncount;
+	pfnleft = pagecount - pfncount;
+
+	/* how many pfns can we fit in a body message */
+	pfnsize = MAX_SIZE_CHANNEL_MESSAGE -
+		  sizeof(struct vmbus_channel_gpadl_body);
 	pfncount = pfnsize / sizeof(u64);
 
-	if (pagecount > pfncount) {
-		/* we need a gpadl body */
-		/* fill in the header */
+	/*
+	 * If pfnleft is zero, everything fits in the header and no body
+	 * messages are needed
+	 */
+	while (pfnleft) {
+		pfncurr = umin(pfncount, pfnleft);
 		msgsize = sizeof(struct vmbus_channel_msginfo) +
-			  sizeof(struct vmbus_channel_gpadl_header) +
-			  sizeof(struct gpa_range) + pfncount * sizeof(u64);
-		msgheader =  kzalloc(msgsize, GFP_KERNEL);
-		if (!msgheader)
-			goto nomem;
-
-		INIT_LIST_HEAD(&msgheader->submsglist);
-		msgheader->msgsize = msgsize;
-
-		gpadl_header = (struct vmbus_channel_gpadl_header *)
-			msgheader->msg;
-		gpadl_header->rangecount = 1;
-		gpadl_header->range_buflen = sizeof(struct gpa_range) +
-					 pagecount * sizeof(u64);
-		gpadl_header->range[0].byte_offset = 0;
-		gpadl_header->range[0].byte_count = hv_gpadl_size(type, size);
-		for (i = 0; i < pfncount; i++)
-			gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn(
-				type, kbuffer, size, send_offset, i);
-		*msginfo = msgheader;
-
-		pfnsum = pfncount;
-		pfnleft = pagecount - pfncount;
-
-		/* how many pfns can we fit */
-		pfnsize = MAX_SIZE_CHANNEL_MESSAGE -
-			  sizeof(struct vmbus_channel_gpadl_body);
-		pfncount = pfnsize / sizeof(u64);
-
-		/* fill in the body */
-		while (pfnleft) {
-			if (pfnleft > pfncount)
-				pfncurr = pfncount;
-			else
-				pfncurr = pfnleft;
-
-			msgsize = sizeof(struct vmbus_channel_msginfo) +
-				  sizeof(struct vmbus_channel_gpadl_body) +
-				  pfncurr * sizeof(u64);
-			msgbody = kzalloc(msgsize, GFP_KERNEL);
-
-			if (!msgbody) {
-				struct vmbus_channel_msginfo *pos = NULL;
-				struct vmbus_channel_msginfo *tmp = NULL;
-				/*
-				 * Free up all the allocated messages.
-				 */
-				list_for_each_entry_safe(pos, tmp,
-					&msgheader->submsglist,
-					msglistentry) {
-
-					list_del(&pos->msglistentry);
-					kfree(pos);
-				}
-
-				goto nomem;
-			}
-
-			msgbody->msgsize = msgsize;
-			gpadl_body =
-				(struct vmbus_channel_gpadl_body *)msgbody->msg;
+			  sizeof(struct vmbus_channel_gpadl_body) +
+			  pfncurr * sizeof(u64);
+		msgbody = kzalloc(msgsize, GFP_KERNEL);
 
+		if (!msgbody) {
+			struct vmbus_channel_msginfo *pos = NULL;
+			struct vmbus_channel_msginfo *tmp = NULL;
 			/*
-			 * Gpadl is u32 and we are using a pointer which could
-			 * be 64-bit
-			 * This is governed by the guest/host protocol and
-			 * so the hypervisor guarantees that this is ok.
+			 * Free up all the allocated messages.
 			 */
-			for (i = 0; i < pfncurr; i++)
-				gpadl_body->pfn[i] = hv_gpadl_hvpfn(type,
-					kbuffer, size, send_offset, pfnsum + i);
-
-			/* add to msg header */
-			list_add_tail(&msgbody->msglistentry,
-				      &msgheader->submsglist);
-			pfnsum += pfncurr;
-			pfnleft -= pfncurr;
+			list_for_each_entry_safe(pos, tmp,
+				&msgheader->submsglist,
+				msglistentry) {
+
+				list_del(&pos->msglistentry);
+				kfree(pos);
+			}
+			kfree(msgheader);
+			return -ENOMEM;
 		}
-	} else {
-		/* everything fits in a header */
-		msgsize = sizeof(struct vmbus_channel_msginfo) +
-			  sizeof(struct vmbus_channel_gpadl_header) +
-			  sizeof(struct gpa_range) + pagecount * sizeof(u64);
-		msgheader = kzalloc(msgsize, GFP_KERNEL);
-		if (msgheader == NULL)
-			goto nomem;
-
-		INIT_LIST_HEAD(&msgheader->submsglist);
-		msgheader->msgsize = msgsize;
-
-		gpadl_header = (struct vmbus_channel_gpadl_header *)
-			msgheader->msg;
-		gpadl_header->rangecount = 1;
-		gpadl_header->range_buflen = sizeof(struct gpa_range) +
-					 pagecount * sizeof(u64);
-		gpadl_header->range[0].byte_offset = 0;
-		gpadl_header->range[0].byte_count = hv_gpadl_size(type, size);
-		for (i = 0; i < pagecount; i++)
-			gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn(
-				type, kbuffer, size, send_offset, i);
-
-		*msginfo = msgheader;
+
+		msgbody->msgsize = msgsize;
+		gpadl_body = (struct vmbus_channel_gpadl_body *)msgbody->msg;
+
+		/*
+		 * Gpadl is u32 and we are using a pointer which could
+		 * be 64-bit
+		 * This is governed by the guest/host protocol and
+		 * so the hypervisor guarantees that this is ok.
+		 */
+		for (i = 0; i < pfncurr; i++)
+			gpadl_body->pfn[i] = hv_gpadl_hvpfn(type,
+				kbuffer, size, send_offset, pfnsum + i);
+
+		/* add to msg header */
+		list_add_tail(&msgbody->msglistentry, &msgheader->submsglist);
+		pfnsum += pfncurr;
+		pfnleft -= pfncurr;
 	}
 
 	return 0;
-nomem:
-	kfree(msgheader);
-	kfree(msgbody);
-	return -ENOMEM;
 }
 
 /*
diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
index 4372f5d146ab..0285a74363b3 100644
--- a/drivers/hv/hv_common.c
+++ b/drivers/hv/hv_common.c
@@ -488,7 +488,7 @@ void hv_setup_dma_ops(struct device *dev, bool coherent)
 	 * Hyper-V does not offer a vIOMMU in the guest
 	 * VM, so pass 0/NULL for the IOMMU settings
 	 */
-	arch_setup_dma_ops(dev, 0, 0, NULL, coherent);
+	arch_setup_dma_ops(dev, 0, 0, coherent);
 }
 EXPORT_SYMBOL_GPL(hv_setup_dma_ops);
 
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 42aec2c5606a..9c97c4065fe7 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -296,6 +296,11 @@ static struct {
 	spinlock_t			lock;
 } host_ts;
 
+static bool timesync_implicit;
+
+module_param(timesync_implicit, bool, 0644);
+MODULE_PARM_DESC(timesync_implicit, "If set treat SAMPLE as SYNC when clock is behind");
+
 static inline u64 reftime_to_ns(u64 reftime)
 {
 	return (reftime - WLTIMEDELTA) * 100;
@@ -345,6 +350,29 @@ static void hv_set_host_time(struct work_struct *work)
 }
 
 /*
+ * Due to a bug on Hyper-V hosts, the sync flag may not always be sent on resume.
+ * Force a sync if the guest is behind.
+ */
+static inline bool hv_implicit_sync(u64 host_time)
+{
+	struct timespec64 new_ts;
+	struct timespec64 threshold_ts;
+
+	new_ts = ns_to_timespec64(reftime_to_ns(host_time));
+	ktime_get_real_ts64(&threshold_ts);
+
+	threshold_ts.tv_sec += 5;
+
+	/*
+	 * If guest behind the host by 5 or more seconds.
+	 */
+	if (timespec64_compare(&new_ts, &threshold_ts) >= 0)
+		return true;
+
+	return false;
+}
+
+/*
  * Synchronize time with host after reboot, restore, etc.
  *
  * ICTIMESYNCFLAG_SYNC flag bit indicates reboot, restore events of the VM.
@@ -384,7 +412,8 @@ static inline void adj_guesttime(u64 hosttime, u64 reftime, u8 adj_flags)
 	spin_unlock_irqrestore(&host_ts.lock, flags);
 
 	/* Schedule work to do do_settimeofday64() */
-	if (adj_flags & ICTIMESYNCFLAG_SYNC)
+	if ((adj_flags & ICTIMESYNCFLAG_SYNC) ||
+	    (timesync_implicit && hv_implicit_sync(host_ts.host_time)))
 		schedule_work(&adj_time_work);
 }
 
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index b33d5abd9beb..7f7965f3d187 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -988,7 +988,7 @@ static const struct dev_pm_ops vmbus_pm = {
 };
 
 /* The one and only one */
-static struct bus_type  hv_bus = {
+static const struct bus_type  hv_bus = {
 	.name =		"vmbus",
 	.match =		vmbus_match,
 	.shutdown =		vmbus_shutdown,
diff --git a/drivers/hwmon/aspeed-pwm-tacho.c b/drivers/hwmon/aspeed-pwm-tacho.c
index f6e1e55e8292..4acc1858d8ac 100644
--- a/drivers/hwmon/aspeed-pwm-tacho.c
+++ b/drivers/hwmon/aspeed-pwm-tacho.c
@@ -195,6 +195,8 @@ struct aspeed_pwm_tacho_data {
 	u8 fan_tach_ch_source[MAX_ASPEED_FAN_TACH_CHANNELS];
 	struct aspeed_cooling_device *cdev[8];
 	const struct attribute_group *groups[3];
+	/* protects access to shared ASPEED_PTCR_RESULT */
+	struct mutex tach_lock;
 };
 
 enum type { TYPEM, TYPEN, TYPEO };
@@ -529,6 +531,8 @@ static int aspeed_get_fan_tach_ch_rpm(struct aspeed_pwm_tacho_data *priv,
 	u8 fan_tach_ch_source, type, mode, both;
 	int ret;
 
+	mutex_lock(&priv->tach_lock);
+
 	regmap_write(priv->regmap, ASPEED_PTCR_TRIGGER, 0);
 	regmap_write(priv->regmap, ASPEED_PTCR_TRIGGER, 0x1 << fan_tach_ch);
 
@@ -546,6 +550,8 @@ static int aspeed_get_fan_tach_ch_rpm(struct aspeed_pwm_tacho_data *priv,
 		ASPEED_RPM_STATUS_SLEEP_USEC,
 		usec);
 
+	mutex_unlock(&priv->tach_lock);
+
 	/* return -ETIMEDOUT if we didn't get an answer. */
 	if (ret)
 		return ret;
@@ -915,6 +921,7 @@ static int aspeed_pwm_tacho_probe(struct platform_device *pdev)
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
+	mutex_init(&priv->tach_lock);
 	priv->regmap = devm_regmap_init(dev, NULL, (__force void *)regs,
 			&aspeed_pwm_tacho_regmap_config);
 	if (IS_ERR(priv->regmap))
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index ba82d1e79c13..b8fc8d1ef20d 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -41,7 +41,7 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
 
 #define PKG_SYSFS_ATTR_NO	1	/* Sysfs attribute for package temp */
 #define BASE_SYSFS_ATTR_NO	2	/* Sysfs Base attr no for coretemp */
-#define NUM_REAL_CORES		128	/* Number of Real cores per cpu */
+#define NUM_REAL_CORES		512	/* Number of Real cores per cpu */
 #define CORETEMP_NAME_LENGTH	28	/* String Length of attrs */
 #define MAX_CORE_ATTRS		4	/* Maximum no of basic attrs */
 #define TOTAL_ATTRS		(MAX_CORE_ATTRS + 1)
@@ -419,7 +419,7 @@ static ssize_t show_temp(struct device *dev,
 }
 
 static int create_core_attrs(struct temp_data *tdata, struct device *dev,
-			     int attr_no)
+			     int index)
 {
 	int i;
 	static ssize_t (*const rd_ptr[TOTAL_ATTRS]) (struct device *dev,
@@ -431,13 +431,20 @@ static int create_core_attrs(struct temp_data *tdata, struct device *dev,
 	};
 
 	for (i = 0; i < tdata->attr_size; i++) {
+		/*
+		 * We map the attr number to core id of the CPU
+		 * The attr number is always core id + 2
+		 * The Pkgtemp will always show up as temp1_*, if available
+		 */
+		int attr_no = tdata->is_pkg_data ? 1 : tdata->cpu_core_id + 2;
+
 		snprintf(tdata->attr_name[i], CORETEMP_NAME_LENGTH,
 			 "temp%d_%s", attr_no, suffixes[i]);
 		sysfs_attr_init(&tdata->sd_attrs[i].dev_attr.attr);
 		tdata->sd_attrs[i].dev_attr.attr.name = tdata->attr_name[i];
 		tdata->sd_attrs[i].dev_attr.attr.mode = 0444;
 		tdata->sd_attrs[i].dev_attr.show = rd_ptr[i];
-		tdata->sd_attrs[i].index = attr_no;
+		tdata->sd_attrs[i].index = index;
 		tdata->attrs[i] = &tdata->sd_attrs[i].dev_attr.attr;
 	}
 	tdata->attr_group.attrs = tdata->attrs;
@@ -495,30 +502,25 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
 	struct platform_data *pdata = platform_get_drvdata(pdev);
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	u32 eax, edx;
-	int err, index, attr_no;
+	int err, index;
 
 	if (!housekeeping_cpu(cpu, HK_TYPE_MISC))
 		return 0;
 
 	/*
-	 * Find attr number for sysfs:
-	 * We map the attr number to core id of the CPU
-	 * The attr number is always core id + 2
-	 * The Pkgtemp will always show up as temp1_*, if available
+	 * Get the index of tdata in pdata->core_data[]
+	 * tdata for package: pdata->core_data[1]
+	 * tdata for core: pdata->core_data[2] .. pdata->core_data[NUM_REAL_CORES + 1]
 	 */
 	if (pkg_flag) {
-		attr_no = PKG_SYSFS_ATTR_NO;
+		index = PKG_SYSFS_ATTR_NO;
 	} else {
-		index = ida_alloc(&pdata->ida, GFP_KERNEL);
+		index = ida_alloc_max(&pdata->ida, NUM_REAL_CORES - 1, GFP_KERNEL);
 		if (index < 0)
 			return index;
-		pdata->cpu_map[index] = topology_core_id(cpu);
-		attr_no = index + BASE_SYSFS_ATTR_NO;
-	}
 
-	if (attr_no > MAX_CORE_DATA - 1) {
-		err = -ERANGE;
-		goto ida_free;
+		pdata->cpu_map[index] = topology_core_id(cpu);
+		index += BASE_SYSFS_ATTR_NO;
 	}
 
 	tdata = init_temp_data(cpu, pkg_flag);
@@ -544,20 +546,20 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
 		if (get_ttarget(tdata, &pdev->dev) >= 0)
 			tdata->attr_size++;
 
-	pdata->core_data[attr_no] = tdata;
+	pdata->core_data[index] = tdata;
 
 	/* Create sysfs interfaces */
-	err = create_core_attrs(tdata, pdata->hwmon_dev, attr_no);
+	err = create_core_attrs(tdata, pdata->hwmon_dev, index);
 	if (err)
 		goto exit_free;
 
 	return 0;
 exit_free:
-	pdata->core_data[attr_no] = NULL;
+	pdata->core_data[index] = NULL;
 	kfree(tdata);
 ida_free:
 	if (!pkg_flag)
-		ida_free(&pdata->ida, index);
+		ida_free(&pdata->ida, index - BASE_SYSFS_ATTR_NO);
 	return err;
 }
 
diff --git a/drivers/hwmon/gigabyte_waterforce.c b/drivers/hwmon/gigabyte_waterforce.c
index 85e523775714..8129d7b3ceaf 100644
--- a/drivers/hwmon/gigabyte_waterforce.c
+++ b/drivers/hwmon/gigabyte_waterforce.c
@@ -146,7 +146,7 @@ static int waterforce_get_status(struct waterforce_data *priv)
 	/* Send command for getting status */
 	ret = waterforce_write_expanded(priv, get_status_cmd, GET_STATUS_CMD_LENGTH);
 	if (ret < 0)
-		return ret;
+		goto unlock_and_return;
 
 	ret = wait_for_completion_interruptible_timeout(&priv->status_report_received,
 							msecs_to_jiffies(STATUS_VALIDITY));
diff --git a/drivers/hwmon/nct6775-core.c b/drivers/hwmon/nct6775-core.c
index 8d2ef3145bca..9fbab8f02334 100644
--- a/drivers/hwmon/nct6775-core.c
+++ b/drivers/hwmon/nct6775-core.c
@@ -3512,6 +3512,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data,
 	const u16 *reg_temp_mon, *reg_temp_alternate, *reg_temp_crit;
 	const u16 *reg_temp_crit_l = NULL, *reg_temp_crit_h = NULL;
 	int num_reg_temp, num_reg_temp_mon, num_reg_tsi_temp;
+	int num_reg_temp_config;
 	struct device *hwmon_dev;
 	struct sensor_template_group tsi_temp_tg;
 
@@ -3594,6 +3595,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data,
 		reg_temp_over = NCT6106_REG_TEMP_OVER;
 		reg_temp_hyst = NCT6106_REG_TEMP_HYST;
 		reg_temp_config = NCT6106_REG_TEMP_CONFIG;
+		num_reg_temp_config = ARRAY_SIZE(NCT6106_REG_TEMP_CONFIG);
 		reg_temp_alternate = NCT6106_REG_TEMP_ALTERNATE;
 		reg_temp_crit = NCT6106_REG_TEMP_CRIT;
 		reg_temp_crit_l = NCT6106_REG_TEMP_CRIT_L;
@@ -3669,6 +3671,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data,
 		reg_temp_over = NCT6106_REG_TEMP_OVER;
 		reg_temp_hyst = NCT6106_REG_TEMP_HYST;
 		reg_temp_config = NCT6106_REG_TEMP_CONFIG;
+		num_reg_temp_config = ARRAY_SIZE(NCT6106_REG_TEMP_CONFIG);
 		reg_temp_alternate = NCT6106_REG_TEMP_ALTERNATE;
 		reg_temp_crit = NCT6106_REG_TEMP_CRIT;
 		reg_temp_crit_l = NCT6106_REG_TEMP_CRIT_L;
@@ -3746,6 +3749,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data,
 		reg_temp_over = NCT6775_REG_TEMP_OVER;
 		reg_temp_hyst = NCT6775_REG_TEMP_HYST;
 		reg_temp_config = NCT6775_REG_TEMP_CONFIG;
+		num_reg_temp_config = ARRAY_SIZE(NCT6775_REG_TEMP_CONFIG);
 		reg_temp_alternate = NCT6775_REG_TEMP_ALTERNATE;
 		reg_temp_crit = NCT6775_REG_TEMP_CRIT;
 
@@ -3821,6 +3825,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data,
 		reg_temp_over = NCT6775_REG_TEMP_OVER;
 		reg_temp_hyst = NCT6775_REG_TEMP_HYST;
 		reg_temp_config = NCT6776_REG_TEMP_CONFIG;
+		num_reg_temp_config = ARRAY_SIZE(NCT6776_REG_TEMP_CONFIG);
 		reg_temp_alternate = NCT6776_REG_TEMP_ALTERNATE;
 		reg_temp_crit = NCT6776_REG_TEMP_CRIT;
 
@@ -3900,6 +3905,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data,
 		reg_temp_over = NCT6779_REG_TEMP_OVER;
 		reg_temp_hyst = NCT6779_REG_TEMP_HYST;
 		reg_temp_config = NCT6779_REG_TEMP_CONFIG;
+		num_reg_temp_config = ARRAY_SIZE(NCT6779_REG_TEMP_CONFIG);
 		reg_temp_alternate = NCT6779_REG_TEMP_ALTERNATE;
 		reg_temp_crit = NCT6779_REG_TEMP_CRIT;
 
@@ -4034,6 +4040,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data,
 		reg_temp_over = NCT6779_REG_TEMP_OVER;
 		reg_temp_hyst = NCT6779_REG_TEMP_HYST;
 		reg_temp_config = NCT6779_REG_TEMP_CONFIG;
+		num_reg_temp_config = ARRAY_SIZE(NCT6779_REG_TEMP_CONFIG);
 		reg_temp_alternate = NCT6779_REG_TEMP_ALTERNATE;
 		reg_temp_crit = NCT6779_REG_TEMP_CRIT;
 
@@ -4123,6 +4130,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data,
 		reg_temp_over = NCT6798_REG_TEMP_OVER;
 		reg_temp_hyst = NCT6798_REG_TEMP_HYST;
 		reg_temp_config = NCT6779_REG_TEMP_CONFIG;
+		num_reg_temp_config = ARRAY_SIZE(NCT6779_REG_TEMP_CONFIG);
 		reg_temp_alternate = NCT6798_REG_TEMP_ALTERNATE;
 		reg_temp_crit = NCT6798_REG_TEMP_CRIT;
 
@@ -4204,7 +4212,8 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data,
 				  = reg_temp_crit[src - 1];
 			if (reg_temp_crit_l && reg_temp_crit_l[i])
 				data->reg_temp[4][src - 1] = reg_temp_crit_l[i];
-			data->reg_temp_config[src - 1] = reg_temp_config[i];
+			if (i < num_reg_temp_config)
+				data->reg_temp_config[src - 1] = reg_temp_config[i];
 			data->temp_src[src - 1] = src;
 			continue;
 		}
@@ -4217,7 +4226,8 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data,
 		data->reg_temp[0][s] = reg_temp[i];
 		data->reg_temp[1][s] = reg_temp_over[i];
 		data->reg_temp[2][s] = reg_temp_hyst[i];
-		data->reg_temp_config[s] = reg_temp_config[i];
+		if (i < num_reg_temp_config)
+			data->reg_temp_config[s] = reg_temp_config[i];
 		if (reg_temp_crit_h && reg_temp_crit_h[i])
 			data->reg_temp[3][s] = reg_temp_crit_h[i];
 		else if (reg_temp_crit[src - 1])
diff --git a/drivers/hwmon/npcm750-pwm-fan.c b/drivers/hwmon/npcm750-pwm-fan.c
index d9733da8ea34..904816abb7c4 100644
--- a/drivers/hwmon/npcm750-pwm-fan.c
+++ b/drivers/hwmon/npcm750-pwm-fan.c
@@ -195,6 +195,7 @@ struct npcm7xx_cooling_device {
 struct npcm7xx_pwm_fan_data {
 	void __iomem *pwm_base;
 	void __iomem *fan_base;
+	int pwm_modules;
 	unsigned long pwm_clk_freq;
 	unsigned long fan_clk_freq;
 	struct clk *pwm_clk;
@@ -710,7 +711,7 @@ static u32 npcm7xx_pwm_init(struct npcm7xx_pwm_fan_data *data)
 	/* Setting PWM Prescale Register value register to both modules */
 	prescale_val |= (prescale_val << NPCM7XX_PWM_PRESCALE_SHIFT_CH01);
 
-	for (m = 0; m < NPCM7XX_PWM_MAX_MODULES  ; m++) {
+	for (m = 0; m < data->pwm_modules; m++) {
 		iowrite32(prescale_val, NPCM7XX_PWM_REG_PR(data->pwm_base, m));
 		iowrite32(NPCM7XX_PWM_PRESCALE2_DEFAULT,
 			  NPCM7XX_PWM_REG_CSR(data->pwm_base, m));
@@ -946,6 +947,8 @@ static int npcm7xx_pwm_fan_probe(struct platform_device *pdev)
 	if (!data->info)
 		return -EINVAL;
 
+	data->pwm_modules = data->info->pwm_max_channel / NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE;
+
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "pwm");
 	if (!res) {
 		dev_err(dev, "pwm resource not found\n");
@@ -983,7 +986,7 @@ static int npcm7xx_pwm_fan_probe(struct platform_device *pdev)
 	output_freq = npcm7xx_pwm_init(data);
 	npcm7xx_fan_init(data);
 
-	for (cnt = 0; cnt < NPCM7XX_PWM_MAX_MODULES  ; cnt++)
+	for (cnt = 0; cnt < data->pwm_modules; cnt++)
 		mutex_init(&data->pwm_lock[cnt]);
 
 	for (i = 0; i < NPCM7XX_FAN_MAX_MODULE; i++) {
diff --git a/drivers/hwmon/pmbus/mp2975.c b/drivers/hwmon/pmbus/mp2975.c
index b9bb469e2d8f..e5fa10b3b8bc 100644
--- a/drivers/hwmon/pmbus/mp2975.c
+++ b/drivers/hwmon/pmbus/mp2975.c
@@ -126,6 +126,21 @@ static const struct regulator_desc __maybe_unused mp2975_reg_desc[] = {
 
 #define to_mp2975_data(x)  container_of(x, struct mp2975_data, info)
 
+static int mp2975_read_byte_data(struct i2c_client *client, int page, int reg)
+{
+	switch (reg) {
+	case PMBUS_VOUT_MODE:
+		/*
+		 * Report direct format as configured by MFR_DC_LOOP_CTRL.
+		 * Unlike on MP2971/MP2973 the reported VOUT_MODE isn't automatically
+		 * internally updated, but always reads as PB_VOUT_MODE_VID.
+		 */
+		return PB_VOUT_MODE_DIRECT;
+	default:
+		return -ENODATA;
+	}
+}
+
 static int
 mp2975_read_word_helper(struct i2c_client *client, int page, int phase, u8 reg,
 			u16 mask)
@@ -869,6 +884,7 @@ static struct pmbus_driver_info mp2975_info = {
 		PMBUS_HAVE_IIN | PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT |
 		PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP | PMBUS_HAVE_POUT |
 		PMBUS_HAVE_PIN | PMBUS_HAVE_STATUS_INPUT | PMBUS_PHASE_VIRTUAL,
+	.read_byte_data = mp2975_read_byte_data,
 	.read_word_data = mp2975_read_word_data,
 #if IS_ENABLED(CONFIG_SENSORS_MP2975_REGULATOR)
 	.num_regulators = 1,
diff --git a/drivers/hwspinlock/hwspinlock_core.c b/drivers/hwspinlock/hwspinlock_core.c
index ada694ba9f95..0c0a932c00f3 100644
--- a/drivers/hwspinlock/hwspinlock_core.c
+++ b/drivers/hwspinlock/hwspinlock_core.c
@@ -84,8 +84,9 @@ static DEFINE_MUTEX(hwspinlock_tree_lock);
  * should decide between spin_trylock, spin_trylock_irq and
  * spin_trylock_irqsave.
  *
- * Returns 0 if we successfully locked the hwspinlock or -EBUSY if
+ * Returns: %0 if we successfully locked the hwspinlock or -EBUSY if
  * the hwspinlock was already taken.
+ *
  * This function will never sleep.
  */
 int __hwspin_trylock(struct hwspinlock *hwlock, int mode, unsigned long *flags)
@@ -171,7 +172,7 @@ EXPORT_SYMBOL_GPL(__hwspin_trylock);
 /**
  * __hwspin_lock_timeout() - lock an hwspinlock with timeout limit
  * @hwlock: the hwspinlock to be locked
- * @timeout: timeout value in msecs
+ * @to: timeout value in msecs
  * @mode: mode which controls whether local interrupts are disabled or not
  * @flags: a pointer to where the caller's interrupt state will be saved at (if
  *         requested)
@@ -199,9 +200,11 @@ EXPORT_SYMBOL_GPL(__hwspin_trylock);
  * to choose the appropriate @mode of operation, exactly the same way users
  * should decide between spin_lock, spin_lock_irq and spin_lock_irqsave.
  *
- * Returns 0 when the @hwlock was successfully taken, and an appropriate
+ * Returns: %0 when the @hwlock was successfully taken, and an appropriate
  * error code otherwise (most notably -ETIMEDOUT if the @hwlock is still
- * busy after @timeout msecs). The function will never sleep.
+ * busy after @timeout msecs).
+ *
+ * The function will never sleep.
  */
 int __hwspin_lock_timeout(struct hwspinlock *hwlock, unsigned int to,
 					int mode, unsigned long *flags)
@@ -304,13 +307,12 @@ EXPORT_SYMBOL_GPL(__hwspin_unlock);
 
 /**
  * of_hwspin_lock_simple_xlate - translate hwlock_spec to return a lock id
- * @bank: the hwspinlock device bank
  * @hwlock_spec: hwlock specifier as found in the device tree
  *
  * This is a simple translation function, suitable for hwspinlock platform
  * drivers that only has a lock specifier length of 1.
  *
- * Returns a relative index of the lock within a specified bank on success,
+ * Returns: a relative index of the lock within a specified bank on success,
  * or -EINVAL on invalid specifier cell count.
  */
 static inline int
@@ -332,9 +334,10 @@ of_hwspin_lock_simple_xlate(const struct of_phandle_args *hwlock_spec)
  * hwspinlock device, so that it can be requested using the normal
  * hwspin_lock_request_specific() API.
  *
- * Returns the global lock id number on success, -EPROBE_DEFER if the hwspinlock
- * device is not yet registered, -EINVAL on invalid args specifier value or an
- * appropriate error as returned from the OF parsing of the DT client node.
+ * Returns: the global lock id number on success, -EPROBE_DEFER if the
+ * hwspinlock device is not yet registered, -EINVAL on invalid args
+ * specifier value or an appropriate error as returned from the OF parsing
+ * of the DT client node.
  */
 int of_hwspin_lock_get_id(struct device_node *np, int index)
 {
@@ -399,9 +402,10 @@ EXPORT_SYMBOL_GPL(of_hwspin_lock_get_id);
  * the hwspinlock device, so that it can be requested using the normal
  * hwspin_lock_request_specific() API.
  *
- * Returns the global lock id number on success, -EPROBE_DEFER if the hwspinlock
- * device is not yet registered, -EINVAL on invalid args specifier value or an
- * appropriate error as returned from the OF parsing of the DT client node.
+ * Returns: the global lock id number on success, -EPROBE_DEFER if the
+ * hwspinlock device is not yet registered, -EINVAL on invalid args
+ * specifier value or an appropriate error as returned from the OF parsing
+ * of the DT client node.
  */
 int of_hwspin_lock_get_id_byname(struct device_node *np, const char *name)
 {
@@ -481,7 +485,7 @@ out:
  *
  * Should be called from a process context (might sleep)
  *
- * Returns 0 on success, or an appropriate error code on failure
+ * Returns: %0 on success, or an appropriate error code on failure
  */
 int hwspin_lock_register(struct hwspinlock_device *bank, struct device *dev,
 		const struct hwspinlock_ops *ops, int base_id, int num_locks)
@@ -529,7 +533,7 @@ EXPORT_SYMBOL_GPL(hwspin_lock_register);
  *
  * Should be called from a process context (might sleep)
  *
- * Returns 0 on success, or an appropriate error code on failure
+ * Returns: %0 on success, or an appropriate error code on failure
  */
 int hwspin_lock_unregister(struct hwspinlock_device *bank)
 {
@@ -578,7 +582,7 @@ static int devm_hwspin_lock_device_match(struct device *dev, void *res,
  *
  * Should be called from a process context (might sleep)
  *
- * Returns 0 on success, or an appropriate error code on failure
+ * Returns: %0 on success, or an appropriate error code on failure
  */
 int devm_hwspin_lock_unregister(struct device *dev,
 				struct hwspinlock_device *bank)
@@ -607,7 +611,7 @@ EXPORT_SYMBOL_GPL(devm_hwspin_lock_unregister);
  *
  * Should be called from a process context (might sleep)
  *
- * Returns 0 on success, or an appropriate error code on failure
+ * Returns: %0 on success, or an appropriate error code on failure
  */
 int devm_hwspin_lock_register(struct device *dev,
 			      struct hwspinlock_device *bank,
@@ -635,12 +639,13 @@ EXPORT_SYMBOL_GPL(devm_hwspin_lock_register);
 
 /**
  * __hwspin_lock_request() - tag an hwspinlock as used and power it up
+ * @hwlock: the target hwspinlock
  *
  * This is an internal function that prepares an hwspinlock instance
  * before it is given to the user. The function assumes that
  * hwspinlock_tree_lock is taken.
  *
- * Returns 0 or positive to indicate success, and a negative value to
+ * Returns: %0 or positive to indicate success, and a negative value to
  * indicate an error (with the appropriate error code)
  */
 static int __hwspin_lock_request(struct hwspinlock *hwlock)
@@ -680,7 +685,7 @@ static int __hwspin_lock_request(struct hwspinlock *hwlock)
  * hwspin_lock_get_id() - retrieve id number of a given hwspinlock
  * @hwlock: a valid hwspinlock instance
  *
- * Returns the id number of a given @hwlock, or -EINVAL if @hwlock is invalid.
+ * Returns: the id number of a given @hwlock, or -EINVAL if @hwlock is invalid.
  */
 int hwspin_lock_get_id(struct hwspinlock *hwlock)
 {
@@ -704,7 +709,7 @@ EXPORT_SYMBOL_GPL(hwspin_lock_get_id);
  *
  * Should be called from a process context (might sleep)
  *
- * Returns the address of the assigned hwspinlock, or NULL on error
+ * Returns: the address of the assigned hwspinlock, or %NULL on error
  */
 struct hwspinlock *hwspin_lock_request(void)
 {
@@ -747,7 +752,7 @@ EXPORT_SYMBOL_GPL(hwspin_lock_request);
  *
  * Should be called from a process context (might sleep)
  *
- * Returns the address of the assigned hwspinlock, or NULL on error
+ * Returns: the address of the assigned hwspinlock, or %NULL on error
  */
 struct hwspinlock *hwspin_lock_request_specific(unsigned int id)
 {
@@ -795,7 +800,7 @@ EXPORT_SYMBOL_GPL(hwspin_lock_request_specific);
  *
  * Should be called from a process context (might sleep)
  *
- * Returns 0 on success, or an appropriate error code on failure
+ * Returns: %0 on success, or an appropriate error code on failure
  */
 int hwspin_lock_free(struct hwspinlock *hwlock)
 {
@@ -865,7 +870,7 @@ static void devm_hwspin_lock_release(struct device *dev, void *res)
  *
  * Should be called from a process context (might sleep)
  *
- * Returns 0 on success, or an appropriate error code on failure
+ * Returns: %0 on success, or an appropriate error code on failure
  */
 int devm_hwspin_lock_free(struct device *dev, struct hwspinlock *hwlock)
 {
@@ -891,7 +896,7 @@ EXPORT_SYMBOL_GPL(devm_hwspin_lock_free);
  *
  * Should be called from a process context (might sleep)
  *
- * Returns the address of the assigned hwspinlock, or NULL on error
+ * Returns: the address of the assigned hwspinlock, or %NULL on error
  */
 struct hwspinlock *devm_hwspin_lock_request(struct device *dev)
 {
@@ -926,7 +931,7 @@ EXPORT_SYMBOL_GPL(devm_hwspin_lock_request);
  *
  * Should be called from a process context (might sleep)
  *
- * Returns the address of the assigned hwspinlock, or NULL on error
+ * Returns: the address of the assigned hwspinlock, or %NULL on error
  */
 struct hwspinlock *devm_hwspin_lock_request_specific(struct device *dev,
 						     unsigned int id)
diff --git a/drivers/hwspinlock/qcom_hwspinlock.c b/drivers/hwspinlock/qcom_hwspinlock.c
index a0fd67fd2934..814dfe8697bf 100644
--- a/drivers/hwspinlock/qcom_hwspinlock.c
+++ b/drivers/hwspinlock/qcom_hwspinlock.c
@@ -115,7 +115,6 @@ static const struct of_device_id qcom_hwspinlock_of_match[] = {
 	{ .compatible = "qcom,sfpb-mutex", .data = &of_sfpb_mutex },
 	{ .compatible = "qcom,tcsr-mutex", .data = &of_tcsr_mutex },
 	{ .compatible = "qcom,apq8084-tcsr-mutex", .data = &of_msm8226_tcsr_mutex },
-	{ .compatible = "qcom,ipq6018-tcsr-mutex", .data = &of_msm8226_tcsr_mutex },
 	{ .compatible = "qcom,msm8226-tcsr-mutex", .data = &of_msm8226_tcsr_mutex },
 	{ .compatible = "qcom,msm8974-tcsr-mutex", .data = &of_msm8226_tcsr_mutex },
 	{ .compatible = "qcom,msm8994-tcsr-mutex", .data = &of_msm8226_tcsr_mutex },
diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c
index 9fabe00a40d6..d7f0e231feb9 100644
--- a/drivers/hwtracing/coresight/coresight-core.c
+++ b/drivers/hwtracing/coresight/coresight-core.c
@@ -1093,6 +1093,7 @@ static int coresight_validate_source(struct coresight_device *csdev,
 
 	if (subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_PROC &&
 	    subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE &&
+	    subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM &&
 	    subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS) {
 		dev_err(&csdev->dev, "wrong device subtype in %s\n", function);
 		return -EINVAL;
@@ -1162,6 +1163,7 @@ int coresight_enable(struct coresight_device *csdev)
 		per_cpu(tracer_path, cpu) = path;
 		break;
 	case CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE:
+	case CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM:
 	case CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS:
 		/*
 		 * Use the hash of source's device name as ID
@@ -1212,6 +1214,7 @@ void coresight_disable(struct coresight_device *csdev)
 		per_cpu(tracer_path, cpu) = NULL;
 		break;
 	case CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE:
+	case CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM:
 	case CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS:
 		hash = hashlen_hash(hashlen_string(NULL, dev_name(&csdev->dev)));
 		/* Find the path by the hash. */
diff --git a/drivers/hwtracing/coresight/coresight-dummy.c b/drivers/hwtracing/coresight/coresight-dummy.c
index e4deafae7bc2..ac70c0b491be 100644
--- a/drivers/hwtracing/coresight/coresight-dummy.c
+++ b/drivers/hwtracing/coresight/coresight-dummy.c
@@ -122,14 +122,13 @@ static int dummy_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int dummy_remove(struct platform_device *pdev)
+static void dummy_remove(struct platform_device *pdev)
 {
 	struct dummy_drvdata *drvdata = platform_get_drvdata(pdev);
 	struct device *dev = &pdev->dev;
 
 	pm_runtime_disable(dev);
 	coresight_unregister(drvdata->csdev);
-	return 0;
 }
 
 static const struct of_device_id dummy_match[] = {
@@ -140,7 +139,7 @@ static const struct of_device_id dummy_match[] = {
 
 static struct platform_driver dummy_driver = {
 	.probe	= dummy_probe,
-	.remove	= dummy_remove,
+	.remove_new = dummy_remove,
 	.driver	= {
 		.name   = "coresight-dummy",
 		.of_match_table = dummy_match,
diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c
index 89e8ed214ea4..a52cfcce25d6 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.c
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.c
@@ -68,6 +68,7 @@ PMU_FORMAT_ATTR(preset,		"config:0-3");
 PMU_FORMAT_ATTR(sinkid,		"config2:0-31");
 /* config ID - set if a system configuration is selected */
 PMU_FORMAT_ATTR(configid,	"config2:32-63");
+PMU_FORMAT_ATTR(cc_threshold,	"config3:0-11");
 
 
 /*
@@ -101,6 +102,7 @@ static struct attribute *etm_config_formats_attr[] = {
 	&format_attr_preset.attr,
 	&format_attr_configid.attr,
 	&format_attr_branch_broadcast.attr,
+	&format_attr_cc_threshold.attr,
 	NULL,
 };
 
diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c
index 34aee59dd147..ce1995a2827f 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x-core.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c
@@ -644,7 +644,7 @@ static int etm4_parse_event_config(struct coresight_device *csdev,
 	struct etmv4_config *config = &drvdata->config;
 	struct perf_event_attr *attr = &event->attr;
 	unsigned long cfg_hash;
-	int preset;
+	int preset, cc_threshold;
 
 	/* Clear configuration from previous run */
 	memset(config, 0, sizeof(struct etmv4_config));
@@ -667,7 +667,12 @@ static int etm4_parse_event_config(struct coresight_device *csdev,
 	if (attr->config & BIT(ETM_OPT_CYCACC)) {
 		config->cfg |= TRCCONFIGR_CCI;
 		/* TRM: Must program this for cycacc to work */
-		config->ccctlr = ETM_CYC_THRESHOLD_DEFAULT;
+		cc_threshold = attr->config3 & ETM_CYC_THRESHOLD_MASK;
+		if (!cc_threshold)
+			cc_threshold = ETM_CYC_THRESHOLD_DEFAULT;
+		if (cc_threshold < drvdata->ccitmin)
+			cc_threshold = drvdata->ccitmin;
+		config->ccctlr = cc_threshold;
 	}
 	if (attr->config & BIT(ETM_OPT_TS)) {
 		/*
@@ -1150,6 +1155,41 @@ static void cpu_detect_trace_filtering(struct etmv4_drvdata *drvdata)
 	drvdata->trfcr = trfcr;
 }
 
+/*
+ * The following errata on applicable cpu ranges, affect the CCITMIN filed
+ * in TCRIDR3 register. Software read for the field returns 0x100 limiting
+ * the cycle threshold granularity, whereas the right value should have
+ * been 0x4, which is well supported in the hardware.
+ */
+static struct midr_range etm_wrong_ccitmin_cpus[] = {
+	/* Erratum #1490853 - Cortex-A76 */
+	MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 4, 0),
+	/* Erratum #1490853 - Neoverse-N1 */
+	MIDR_RANGE(MIDR_NEOVERSE_N1, 0, 0, 4, 0),
+	/* Erratum #1491015 - Cortex-A77 */
+	MIDR_RANGE(MIDR_CORTEX_A77, 0, 0, 1, 0),
+	/* Erratum #1502854 - Cortex-X1 */
+	MIDR_REV(MIDR_CORTEX_X1, 0, 0),
+	/* Erratum #1619801 - Neoverse-V1 */
+	MIDR_REV(MIDR_NEOVERSE_V1, 0, 0),
+	{},
+};
+
+static void etm4_fixup_wrong_ccitmin(struct etmv4_drvdata *drvdata)
+{
+	/*
+	 * Erratum affected cpus will read 256 as the minimum
+	 * instruction trace cycle counting threshold whereas
+	 * the correct value should be 4 instead. Override the
+	 * recorded value for 'drvdata->ccitmin' to workaround
+	 * this problem.
+	 */
+	if (is_midr_in_range_list(read_cpuid_id(), etm_wrong_ccitmin_cpus)) {
+		if (drvdata->ccitmin == 256)
+			drvdata->ccitmin = 4;
+	}
+}
+
 static void etm4_init_arch_data(void *info)
 {
 	u32 etmidr0;
@@ -1214,6 +1254,8 @@ static void etm4_init_arch_data(void *info)
 	etmidr3 = etm4x_relaxed_read32(csa, TRCIDR3);
 	/* CCITMIN, bits[11:0] minimum threshold value that can be programmed */
 	drvdata->ccitmin = FIELD_GET(TRCIDR3_CCITMIN_MASK, etmidr3);
+	etm4_fixup_wrong_ccitmin(drvdata);
+
 	/* EXLEVEL_S, bits[19:16] Secure state instruction tracing */
 	drvdata->s_ex_level = FIELD_GET(TRCIDR3_EXLEVEL_S_MASK, etmidr3);
 	drvdata->config.s_ex_level = drvdata->s_ex_level;
@@ -2261,7 +2303,7 @@ static void etm4_remove_amba(struct amba_device *adev)
 		etm4_remove_dev(drvdata);
 }
 
-static int etm4_remove_platform_dev(struct platform_device *pdev)
+static void etm4_remove_platform_dev(struct platform_device *pdev)
 {
 	struct etmv4_drvdata *drvdata = dev_get_drvdata(&pdev->dev);
 
@@ -2271,8 +2313,6 @@ static int etm4_remove_platform_dev(struct platform_device *pdev)
 
 	if (drvdata && !IS_ERR_OR_NULL(drvdata->pclk))
 		clk_put(drvdata->pclk);
-
-	return 0;
 }
 
 static const struct amba_id etm4_ids[] = {
@@ -2358,7 +2398,7 @@ MODULE_DEVICE_TABLE(acpi, etm4x_acpi_ids);
 
 static struct platform_driver etm4_platform_driver = {
 	.probe		= etm4_probe_platform_dev,
-	.remove		= etm4_remove_platform_dev,
+	.remove_new	= etm4_remove_platform_dev,
 	.driver			= {
 		.name			= "coresight-etm4x",
 		.of_match_table		= etm4_sysreg_match,
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h
index 20e2e4cb7614..da17b6c49b0f 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.h
+++ b/drivers/hwtracing/coresight/coresight-etm4x.h
@@ -1036,7 +1036,7 @@ struct etmv4_drvdata {
 	u8				ctxid_size;
 	u8				vmid_size;
 	u8				ccsize;
-	u8				ccitmin;
+	u16				ccitmin;
 	u8				s_ex_level;
 	u8				ns_ex_level;
 	u8				q_support;
diff --git a/drivers/hwtracing/coresight/coresight-funnel.c b/drivers/hwtracing/coresight/coresight-funnel.c
index b8e150e45b27..a5b1fc787766 100644
--- a/drivers/hwtracing/coresight/coresight-funnel.c
+++ b/drivers/hwtracing/coresight/coresight-funnel.c
@@ -335,11 +335,10 @@ static int static_funnel_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int static_funnel_remove(struct platform_device *pdev)
+static void static_funnel_remove(struct platform_device *pdev)
 {
 	funnel_remove(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-	return 0;
 }
 
 static const struct of_device_id static_funnel_match[] = {
@@ -360,7 +359,7 @@ MODULE_DEVICE_TABLE(acpi, static_funnel_ids);
 
 static struct platform_driver static_funnel_driver = {
 	.probe          = static_funnel_probe,
-	.remove          = static_funnel_remove,
+	.remove_new      = static_funnel_remove,
 	.driver         = {
 		.name   = "coresight-static-funnel",
 		/* THIS_MODULE is taken care of by platform_driver_register() */
diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c
index b6be73034996..91d93060dda5 100644
--- a/drivers/hwtracing/coresight/coresight-replicator.c
+++ b/drivers/hwtracing/coresight/coresight-replicator.c
@@ -320,11 +320,10 @@ static int static_replicator_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int static_replicator_remove(struct platform_device *pdev)
+static void static_replicator_remove(struct platform_device *pdev)
 {
 	replicator_remove(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -373,7 +372,7 @@ MODULE_DEVICE_TABLE(acpi, static_replicator_acpi_ids);
 
 static struct platform_driver static_replicator_driver = {
 	.probe          = static_replicator_probe,
-	.remove         = static_replicator_remove,
+	.remove_new     = static_replicator_remove,
 	.driver         = {
 		.name   = "coresight-static-replicator",
 		/* THIS_MODULE is taken care of by platform_driver_register() */
diff --git a/drivers/hwtracing/coresight/coresight-tmc-core.c b/drivers/hwtracing/coresight/coresight-tmc-core.c
index c106d142e632..7ec5365e2b64 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-core.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-core.c
@@ -10,6 +10,7 @@
 #include <linux/device.h>
 #include <linux/idr.h>
 #include <linux/io.h>
+#include <linux/iommu.h>
 #include <linux/err.h>
 #include <linux/fs.h>
 #include <linux/miscdevice.h>
@@ -344,7 +345,14 @@ static const struct attribute_group coresight_tmc_mgmt_group = {
 	.name = "mgmt",
 };
 
-static const struct attribute_group *coresight_tmc_groups[] = {
+static const struct attribute_group *coresight_etf_groups[] = {
+	&coresight_tmc_group,
+	&coresight_tmc_mgmt_group,
+	NULL,
+};
+
+static const struct attribute_group *coresight_etr_groups[] = {
+	&coresight_etr_group,
 	&coresight_tmc_group,
 	&coresight_tmc_mgmt_group,
 	NULL,
@@ -465,6 +473,7 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
 	drvdata->memwidth = tmc_get_memwidth(devid);
 	/* This device is not associated with a session */
 	drvdata->pid = -1;
+	drvdata->etr_mode = ETR_MODE_AUTO;
 
 	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
 		drvdata->size = tmc_etr_get_default_buffer_size(dev);
@@ -474,16 +483,17 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
 	}
 
 	desc.dev = dev;
-	desc.groups = coresight_tmc_groups;
 
 	switch (drvdata->config_type) {
 	case TMC_CONFIG_TYPE_ETB:
+		desc.groups = coresight_etf_groups;
 		desc.type = CORESIGHT_DEV_TYPE_SINK;
 		desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER;
 		desc.ops = &tmc_etb_cs_ops;
 		dev_list = &etb_devs;
 		break;
 	case TMC_CONFIG_TYPE_ETR:
+		desc.groups = coresight_etr_groups;
 		desc.type = CORESIGHT_DEV_TYPE_SINK;
 		desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_SYSMEM;
 		desc.ops = &tmc_etr_cs_ops;
@@ -496,6 +506,7 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
 		dev_list = &etr_devs;
 		break;
 	case TMC_CONFIG_TYPE_ETF:
+		desc.groups = coresight_etf_groups;
 		desc.type = CORESIGHT_DEV_TYPE_LINKSINK;
 		desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER;
 		desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_FIFO;
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c
index 8311e1028ddb..af02ba5d5f15 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etr.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c
@@ -26,6 +26,12 @@ struct etr_flat_buf {
 	size_t		size;
 };
 
+struct etr_buf_hw {
+	bool	has_iommu;
+	bool	has_etr_sg;
+	bool	has_catu;
+};
+
 /*
  * etr_perf_buffer - Perf buffer used for ETR
  * @drvdata		- The ETR drvdaga this buffer has been allocated for.
@@ -830,6 +836,22 @@ static inline int tmc_etr_mode_alloc_buf(int mode,
 	}
 }
 
+static void get_etr_buf_hw(struct device *dev, struct etr_buf_hw *buf_hw)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	buf_hw->has_iommu = iommu_get_domain_for_dev(dev->parent);
+	buf_hw->has_etr_sg = tmc_etr_has_cap(drvdata, TMC_ETR_SG);
+	buf_hw->has_catu = !!tmc_etr_get_catu_device(drvdata);
+}
+
+static bool etr_can_use_flat_mode(struct etr_buf_hw *buf_hw, ssize_t etr_buf_size)
+{
+	bool has_sg = buf_hw->has_catu || buf_hw->has_etr_sg;
+
+	return !has_sg || buf_hw->has_iommu || etr_buf_size < SZ_1M;
+}
+
 /*
  * tmc_alloc_etr_buf: Allocate a buffer use by ETR.
  * @drvdata	: ETR device details.
@@ -843,23 +865,22 @@ static struct etr_buf *tmc_alloc_etr_buf(struct tmc_drvdata *drvdata,
 					 int node, void **pages)
 {
 	int rc = -ENOMEM;
-	bool has_etr_sg, has_iommu;
-	bool has_sg, has_catu;
 	struct etr_buf *etr_buf;
+	struct etr_buf_hw buf_hw;
 	struct device *dev = &drvdata->csdev->dev;
 
-	has_etr_sg = tmc_etr_has_cap(drvdata, TMC_ETR_SG);
-	has_iommu = iommu_get_domain_for_dev(dev->parent);
-	has_catu = !!tmc_etr_get_catu_device(drvdata);
-
-	has_sg = has_catu || has_etr_sg;
-
+	get_etr_buf_hw(dev, &buf_hw);
 	etr_buf = kzalloc(sizeof(*etr_buf), GFP_KERNEL);
 	if (!etr_buf)
 		return ERR_PTR(-ENOMEM);
 
 	etr_buf->size = size;
 
+	/* If there is user directive for buffer mode, try that first */
+	if (drvdata->etr_mode != ETR_MODE_AUTO)
+		rc = tmc_etr_mode_alloc_buf(drvdata->etr_mode, drvdata,
+					    etr_buf, node, pages);
+
 	/*
 	 * If we have to use an existing list of pages, we cannot reliably
 	 * use a contiguous DMA memory (even if we have an IOMMU). Otherwise,
@@ -872,14 +893,13 @@ static struct etr_buf *tmc_alloc_etr_buf(struct tmc_drvdata *drvdata,
 	 * Fallback to available mechanisms.
 	 *
 	 */
-	if (!pages &&
-	    (!has_sg || has_iommu || size < SZ_1M))
+	if (rc && !pages && etr_can_use_flat_mode(&buf_hw, size))
 		rc = tmc_etr_mode_alloc_buf(ETR_MODE_FLAT, drvdata,
 					    etr_buf, node, pages);
-	if (rc && has_etr_sg)
+	if (rc && buf_hw.has_etr_sg)
 		rc = tmc_etr_mode_alloc_buf(ETR_MODE_ETR_SG, drvdata,
 					    etr_buf, node, pages);
-	if (rc && has_catu)
+	if (rc && buf_hw.has_catu)
 		rc = tmc_etr_mode_alloc_buf(ETR_MODE_CATU, drvdata,
 					    etr_buf, node, pages);
 	if (rc) {
@@ -1804,3 +1824,70 @@ int tmc_read_unprepare_etr(struct tmc_drvdata *drvdata)
 
 	return 0;
 }
+
+static const char *const buf_modes_str[] = {
+	[ETR_MODE_FLAT]		= "flat",
+	[ETR_MODE_ETR_SG]	= "tmc-sg",
+	[ETR_MODE_CATU]		= "catu",
+	[ETR_MODE_AUTO]		= "auto",
+};
+
+static ssize_t buf_modes_available_show(struct device *dev,
+					    struct device_attribute *attr, char *buf)
+{
+	struct etr_buf_hw buf_hw;
+	ssize_t size = 0;
+
+	get_etr_buf_hw(dev, &buf_hw);
+	size += sysfs_emit(buf, "%s ", buf_modes_str[ETR_MODE_AUTO]);
+	size += sysfs_emit_at(buf, size, "%s ", buf_modes_str[ETR_MODE_FLAT]);
+	if (buf_hw.has_etr_sg)
+		size += sysfs_emit_at(buf, size, "%s ", buf_modes_str[ETR_MODE_ETR_SG]);
+
+	if (buf_hw.has_catu)
+		size += sysfs_emit_at(buf, size, "%s ", buf_modes_str[ETR_MODE_CATU]);
+
+	size += sysfs_emit_at(buf, size, "\n");
+	return size;
+}
+static DEVICE_ATTR_RO(buf_modes_available);
+
+static ssize_t buf_mode_preferred_show(struct device *dev,
+					 struct device_attribute *attr, char *buf)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	return sysfs_emit(buf, "%s\n", buf_modes_str[drvdata->etr_mode]);
+}
+
+static ssize_t buf_mode_preferred_store(struct device *dev,
+					  struct device_attribute *attr,
+					  const char *buf, size_t size)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etr_buf_hw buf_hw;
+
+	get_etr_buf_hw(dev, &buf_hw);
+	if (sysfs_streq(buf, buf_modes_str[ETR_MODE_FLAT]))
+		drvdata->etr_mode = ETR_MODE_FLAT;
+	else if (sysfs_streq(buf, buf_modes_str[ETR_MODE_ETR_SG]) && buf_hw.has_etr_sg)
+		drvdata->etr_mode = ETR_MODE_ETR_SG;
+	else if (sysfs_streq(buf, buf_modes_str[ETR_MODE_CATU]) && buf_hw.has_catu)
+		drvdata->etr_mode = ETR_MODE_CATU;
+	else if (sysfs_streq(buf, buf_modes_str[ETR_MODE_AUTO]))
+		drvdata->etr_mode = ETR_MODE_AUTO;
+	else
+		return -EINVAL;
+	return size;
+}
+static DEVICE_ATTR_RW(buf_mode_preferred);
+
+static struct attribute *coresight_etr_attrs[] = {
+	&dev_attr_buf_modes_available.attr,
+	&dev_attr_buf_mode_preferred.attr,
+	NULL,
+};
+
+const struct attribute_group coresight_etr_group = {
+	.attrs = coresight_etr_attrs,
+};
diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h
index 0ee48c5ba764..8dcb426ac3e7 100644
--- a/drivers/hwtracing/coresight/coresight-tmc.h
+++ b/drivers/hwtracing/coresight/coresight-tmc.h
@@ -135,6 +135,7 @@ enum etr_mode {
 	ETR_MODE_FLAT,		/* Uses contiguous flat buffer */
 	ETR_MODE_ETR_SG,	/* Uses in-built TMC ETR SG mechanism */
 	ETR_MODE_CATU,		/* Use SG mechanism in CATU */
+	ETR_MODE_AUTO,		/* Use the default mechanism */
 };
 
 struct etr_buf_operations;
@@ -207,6 +208,7 @@ struct tmc_drvdata {
 	enum tmc_mem_intf_width	memwidth;
 	u32			trigger_cntr;
 	u32			etr_caps;
+	enum etr_mode		etr_mode;
 	struct idr		idr;
 	struct mutex		idr_mutex;
 	struct etr_buf		*sysfs_buf;
@@ -334,5 +336,6 @@ void tmc_etr_set_catu_ops(const struct etr_buf_operations *catu);
 void tmc_etr_remove_catu_ops(void);
 struct etr_buf *tmc_etr_get_buffer(struct coresight_device *csdev,
 				   enum cs_mode mode, void *data);
+extern const struct attribute_group coresight_etr_group;
 
 #endif
diff --git a/drivers/hwtracing/coresight/coresight-tpda.c b/drivers/hwtracing/coresight/coresight-tpda.c
index 8d2b9d29237d..5f82737c37bb 100644
--- a/drivers/hwtracing/coresight/coresight-tpda.c
+++ b/drivers/hwtracing/coresight/coresight-tpda.c
@@ -21,6 +21,80 @@
 
 DEFINE_CORESIGHT_DEVLIST(tpda_devs, "tpda");
 
+static bool coresight_device_is_tpdm(struct coresight_device *csdev)
+{
+	return (csdev->type == CORESIGHT_DEV_TYPE_SOURCE) &&
+	       (csdev->subtype.source_subtype ==
+			CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM);
+}
+
+/*
+ * Read the DSB element size from the TPDM device
+ * Returns
+ *    The dsb element size read from the devicetree if available.
+ *    0 - Otherwise, with a warning once.
+ */
+static int tpdm_read_dsb_element_size(struct coresight_device *csdev)
+{
+	int rc = 0;
+	u8 size = 0;
+
+	rc = fwnode_property_read_u8(dev_fwnode(csdev->dev.parent),
+			"qcom,dsb-element-size", &size);
+	if (rc)
+		dev_warn_once(&csdev->dev,
+			"Failed to read TPDM DSB Element size: %d\n", rc);
+
+	return size;
+}
+
+/*
+ * Search and read element data size from the TPDM node in
+ * the devicetree. Each input port of TPDA is connected to
+ * a TPDM. Different TPDM supports different types of dataset,
+ * and some may support more than one type of dataset.
+ * Parameter "inport" is used to pass in the input port number
+ * of TPDA, and it is set to -1 in the recursize call.
+ */
+static int tpda_get_element_size(struct coresight_device *csdev,
+				 int inport)
+{
+	int dsb_size = -ENOENT;
+	int i, size;
+	struct coresight_device *in;
+
+	for (i = 0; i < csdev->pdata->nr_inconns; i++) {
+		in = csdev->pdata->in_conns[i]->src_dev;
+		if (!in)
+			continue;
+
+		/* Ignore the paths that do not match port */
+		if (inport > 0 &&
+		    csdev->pdata->in_conns[i]->dest_port != inport)
+			continue;
+
+		if (coresight_device_is_tpdm(in)) {
+			size = tpdm_read_dsb_element_size(in);
+		} else {
+			/* Recurse down the path */
+			size = tpda_get_element_size(in, -1);
+		}
+
+		if (size < 0)
+			return size;
+
+		if (dsb_size < 0) {
+			/* Found a size, save it. */
+			dsb_size = size;
+		} else {
+			/* Found duplicate TPDMs */
+			return -EEXIST;
+		}
+	}
+
+	return dsb_size;
+}
+
 /* Settings pre enabling port control register */
 static void tpda_enable_pre_port(struct tpda_drvdata *drvdata)
 {
@@ -32,26 +106,55 @@ static void tpda_enable_pre_port(struct tpda_drvdata *drvdata)
 	writel_relaxed(val, drvdata->base + TPDA_CR);
 }
 
-static void tpda_enable_port(struct tpda_drvdata *drvdata, int port)
+static int tpda_enable_port(struct tpda_drvdata *drvdata, int port)
 {
 	u32 val;
+	int size;
 
 	val = readl_relaxed(drvdata->base + TPDA_Pn_CR(port));
+	/*
+	 * Configure aggregator port n DSB data set element size
+	 * Set the bit to 0 if the size is 32
+	 * Set the bit to 1 if the size is 64
+	 */
+	size = tpda_get_element_size(drvdata->csdev, port);
+	switch (size) {
+	case 32:
+		val &= ~TPDA_Pn_CR_DSBSIZE;
+		break;
+	case 64:
+		val |= TPDA_Pn_CR_DSBSIZE;
+		break;
+	case 0:
+		return -EEXIST;
+	case -EEXIST:
+		dev_warn_once(&drvdata->csdev->dev,
+			"Detected multiple TPDMs on port %d", -EEXIST);
+		return -EEXIST;
+	default:
+		return -EINVAL;
+	}
+
 	/* Enable the port */
 	val |= TPDA_Pn_CR_ENA;
 	writel_relaxed(val, drvdata->base + TPDA_Pn_CR(port));
+
+	return 0;
 }
 
-static void __tpda_enable(struct tpda_drvdata *drvdata, int port)
+static int __tpda_enable(struct tpda_drvdata *drvdata, int port)
 {
+	int ret;
+
 	CS_UNLOCK(drvdata->base);
 
 	if (!drvdata->csdev->enable)
 		tpda_enable_pre_port(drvdata);
 
-	tpda_enable_port(drvdata, port);
-
+	ret = tpda_enable_port(drvdata, port);
 	CS_LOCK(drvdata->base);
+
+	return ret;
 }
 
 static int tpda_enable(struct coresight_device *csdev,
@@ -59,16 +162,19 @@ static int tpda_enable(struct coresight_device *csdev,
 		       struct coresight_connection *out)
 {
 	struct tpda_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	int ret = 0;
 
 	spin_lock(&drvdata->spinlock);
-	if (atomic_read(&in->dest_refcnt) == 0)
-		__tpda_enable(drvdata, in->dest_port);
+	if (atomic_read(&in->dest_refcnt) == 0) {
+		ret = __tpda_enable(drvdata, in->dest_port);
+		if (!ret) {
+			atomic_inc(&in->dest_refcnt);
+			dev_dbg(drvdata->dev, "TPDA inport %d enabled.\n", in->dest_port);
+		}
+	}
 
-	atomic_inc(&in->dest_refcnt);
 	spin_unlock(&drvdata->spinlock);
-
-	dev_dbg(drvdata->dev, "TPDA inport %d enabled.\n", in->dest_port);
-	return 0;
+	return ret;
 }
 
 static void __tpda_disable(struct tpda_drvdata *drvdata, int port)
diff --git a/drivers/hwtracing/coresight/coresight-tpda.h b/drivers/hwtracing/coresight/coresight-tpda.h
index 0399678df312..b3b38fd41b64 100644
--- a/drivers/hwtracing/coresight/coresight-tpda.h
+++ b/drivers/hwtracing/coresight/coresight-tpda.h
@@ -10,6 +10,8 @@
 #define TPDA_Pn_CR(n)		(0x004 + (n * 4))
 /* Aggregator port enable bit */
 #define TPDA_Pn_CR_ENA		BIT(0)
+/* Aggregator port DSB data set element size bit */
+#define TPDA_Pn_CR_DSBSIZE		BIT(8)
 
 #define TPDA_MAX_INPORTS	32
 
diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c
index f4854af0431e..97654aa4b772 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.c
+++ b/drivers/hwtracing/coresight/coresight-tpdm.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/amba/bus.h>
+#include <linux/bitfield.h>
 #include <linux/bitmap.h>
 #include <linux/coresight.h>
 #include <linux/coresight-pmu.h>
@@ -20,23 +21,265 @@
 
 DEFINE_CORESIGHT_DEVLIST(tpdm_devs, "tpdm");
 
-static void tpdm_enable_dsb(struct tpdm_drvdata *drvdata)
+/* Read dataset array member with the index number */
+static ssize_t tpdm_simple_dataset_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct tpdm_dataset_attribute *tpdm_attr =
+		container_of(attr, struct tpdm_dataset_attribute, attr);
+
+	switch (tpdm_attr->mem) {
+	case DSB_EDGE_CTRL:
+		if (tpdm_attr->idx >= TPDM_DSB_MAX_EDCR)
+			return -EINVAL;
+		return sysfs_emit(buf, "0x%x\n",
+			drvdata->dsb->edge_ctrl[tpdm_attr->idx]);
+	case DSB_EDGE_CTRL_MASK:
+		if (tpdm_attr->idx >= TPDM_DSB_MAX_EDCMR)
+			return -EINVAL;
+		return sysfs_emit(buf, "0x%x\n",
+			drvdata->dsb->edge_ctrl_mask[tpdm_attr->idx]);
+	case DSB_TRIG_PATT:
+		if (tpdm_attr->idx >= TPDM_DSB_MAX_PATT)
+			return -EINVAL;
+		return sysfs_emit(buf, "0x%x\n",
+			drvdata->dsb->trig_patt[tpdm_attr->idx]);
+	case DSB_TRIG_PATT_MASK:
+		if (tpdm_attr->idx >= TPDM_DSB_MAX_PATT)
+			return -EINVAL;
+		return sysfs_emit(buf, "0x%x\n",
+			drvdata->dsb->trig_patt_mask[tpdm_attr->idx]);
+	case DSB_PATT:
+		if (tpdm_attr->idx >= TPDM_DSB_MAX_PATT)
+			return -EINVAL;
+		return sysfs_emit(buf, "0x%x\n",
+			drvdata->dsb->patt_val[tpdm_attr->idx]);
+	case DSB_PATT_MASK:
+		if (tpdm_attr->idx >= TPDM_DSB_MAX_PATT)
+			return -EINVAL;
+		return sysfs_emit(buf, "0x%x\n",
+			drvdata->dsb->patt_mask[tpdm_attr->idx]);
+	case DSB_MSR:
+		if (tpdm_attr->idx >= drvdata->dsb_msr_num)
+			return -EINVAL;
+		return sysfs_emit(buf, "0x%x\n",
+				drvdata->dsb->msr[tpdm_attr->idx]);
+	}
+	return -EINVAL;
+}
+
+/* Write dataset array member with the index number */
+static ssize_t tpdm_simple_dataset_store(struct device *dev,
+					 struct device_attribute *attr,
+					 const char *buf,
+					 size_t size)
+{
+	unsigned long val;
+	ssize_t ret = size;
+
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct tpdm_dataset_attribute *tpdm_attr =
+		container_of(attr, struct tpdm_dataset_attribute, attr);
+
+	if (kstrtoul(buf, 0, &val))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	switch (tpdm_attr->mem) {
+	case DSB_TRIG_PATT:
+		if (tpdm_attr->idx < TPDM_DSB_MAX_PATT)
+			drvdata->dsb->trig_patt[tpdm_attr->idx] = val;
+		else
+			ret = -EINVAL;
+		break;
+	case DSB_TRIG_PATT_MASK:
+		if (tpdm_attr->idx < TPDM_DSB_MAX_PATT)
+			drvdata->dsb->trig_patt_mask[tpdm_attr->idx] = val;
+		else
+			ret = -EINVAL;
+		break;
+	case DSB_PATT:
+		if (tpdm_attr->idx < TPDM_DSB_MAX_PATT)
+			drvdata->dsb->patt_val[tpdm_attr->idx] = val;
+		else
+			ret = -EINVAL;
+		break;
+	case DSB_PATT_MASK:
+		if (tpdm_attr->idx < TPDM_DSB_MAX_PATT)
+			drvdata->dsb->patt_mask[tpdm_attr->idx] = val;
+		else
+			ret = -EINVAL;
+		break;
+	case DSB_MSR:
+		if (tpdm_attr->idx < drvdata->dsb_msr_num)
+			drvdata->dsb->msr[tpdm_attr->idx] = val;
+		else
+			ret = -EINVAL;
+		break;
+	default:
+		ret = -EINVAL;
+	}
+	spin_unlock(&drvdata->spinlock);
+
+	return ret;
+}
+
+static bool tpdm_has_dsb_dataset(struct tpdm_drvdata *drvdata)
+{
+	return (drvdata->datasets & TPDM_PIDR0_DS_DSB);
+}
+
+static umode_t tpdm_dsb_is_visible(struct kobject *kobj,
+				   struct attribute *attr, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	if (drvdata && tpdm_has_dsb_dataset(drvdata))
+		return attr->mode;
+
+	return 0;
+}
+
+static umode_t tpdm_dsb_msr_is_visible(struct kobject *kobj,
+				       struct attribute *attr, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct device_attribute *dev_attr =
+		container_of(attr, struct device_attribute, attr);
+	struct tpdm_dataset_attribute *tpdm_attr =
+		container_of(dev_attr, struct tpdm_dataset_attribute, attr);
+
+	if (tpdm_attr->idx < drvdata->dsb_msr_num)
+		return attr->mode;
+
+	return 0;
+}
+
+static void tpdm_reset_datasets(struct tpdm_drvdata *drvdata)
+{
+	if (tpdm_has_dsb_dataset(drvdata)) {
+		memset(drvdata->dsb, 0, sizeof(struct dsb_dataset));
+
+		drvdata->dsb->trig_ts = true;
+		drvdata->dsb->trig_type = false;
+	}
+}
+
+static void set_dsb_mode(struct tpdm_drvdata *drvdata, u32 *val)
+{
+	u32 mode;
+
+	/* Set the test accurate mode */
+	mode = TPDM_DSB_MODE_TEST(drvdata->dsb->mode);
+	*val &= ~TPDM_DSB_CR_TEST_MODE;
+	*val |= FIELD_PREP(TPDM_DSB_CR_TEST_MODE, mode);
+
+	/* Set the byte lane for high-performance mode */
+	mode = TPDM_DSB_MODE_HPBYTESEL(drvdata->dsb->mode);
+	*val &= ~TPDM_DSB_CR_HPSEL;
+	*val |= FIELD_PREP(TPDM_DSB_CR_HPSEL, mode);
+
+	/* Set the performance mode */
+	if (drvdata->dsb->mode & TPDM_DSB_MODE_PERF)
+		*val |= TPDM_DSB_CR_MODE;
+	else
+		*val &= ~TPDM_DSB_CR_MODE;
+}
+
+static void set_dsb_tier(struct tpdm_drvdata *drvdata)
 {
 	u32 val;
 
-	/* Set the enable bit of DSB control register to 1 */
+	val = readl_relaxed(drvdata->base + TPDM_DSB_TIER);
+
+	/* Clear all relevant fields */
+	val &= ~(TPDM_DSB_TIER_PATT_TSENAB | TPDM_DSB_TIER_PATT_TYPE |
+		 TPDM_DSB_TIER_XTRIG_TSENAB);
+
+	/* Set pattern timestamp type and enablement */
+	if (drvdata->dsb->patt_ts) {
+		val |= TPDM_DSB_TIER_PATT_TSENAB;
+		if (drvdata->dsb->patt_type)
+			val |= TPDM_DSB_TIER_PATT_TYPE;
+		else
+			val &= ~TPDM_DSB_TIER_PATT_TYPE;
+	} else {
+		val &= ~TPDM_DSB_TIER_PATT_TSENAB;
+	}
+
+	/* Set trigger timestamp */
+	if (drvdata->dsb->trig_ts)
+		val |= TPDM_DSB_TIER_XTRIG_TSENAB;
+	else
+		val &= ~TPDM_DSB_TIER_XTRIG_TSENAB;
+
+	writel_relaxed(val, drvdata->base + TPDM_DSB_TIER);
+}
+
+static void set_dsb_msr(struct tpdm_drvdata *drvdata)
+{
+	int i;
+
+	for (i = 0; i < drvdata->dsb_msr_num; i++)
+		writel_relaxed(drvdata->dsb->msr[i],
+			   drvdata->base + TPDM_DSB_MSR(i));
+}
+
+static void tpdm_enable_dsb(struct tpdm_drvdata *drvdata)
+{
+	u32 val, i;
+
+	for (i = 0; i < TPDM_DSB_MAX_EDCR; i++)
+		writel_relaxed(drvdata->dsb->edge_ctrl[i],
+			   drvdata->base + TPDM_DSB_EDCR(i));
+	for (i = 0; i < TPDM_DSB_MAX_EDCMR; i++)
+		writel_relaxed(drvdata->dsb->edge_ctrl_mask[i],
+			   drvdata->base + TPDM_DSB_EDCMR(i));
+	for (i = 0; i < TPDM_DSB_MAX_PATT; i++) {
+		writel_relaxed(drvdata->dsb->patt_val[i],
+			   drvdata->base + TPDM_DSB_TPR(i));
+		writel_relaxed(drvdata->dsb->patt_mask[i],
+			   drvdata->base + TPDM_DSB_TPMR(i));
+		writel_relaxed(drvdata->dsb->trig_patt[i],
+			   drvdata->base + TPDM_DSB_XPR(i));
+		writel_relaxed(drvdata->dsb->trig_patt_mask[i],
+			   drvdata->base + TPDM_DSB_XPMR(i));
+	}
+
+	set_dsb_tier(drvdata);
+
+	set_dsb_msr(drvdata);
+
 	val = readl_relaxed(drvdata->base + TPDM_DSB_CR);
+	/* Set the mode of DSB dataset */
+	set_dsb_mode(drvdata, &val);
+	/* Set trigger type */
+	if (drvdata->dsb->trig_type)
+		val |= TPDM_DSB_CR_TRIG_TYPE;
+	else
+		val &= ~TPDM_DSB_CR_TRIG_TYPE;
+	/* Set the enable bit of DSB control register to 1 */
 	val |= TPDM_DSB_CR_ENA;
 	writel_relaxed(val, drvdata->base + TPDM_DSB_CR);
 }
 
-/* TPDM enable operations */
+/*
+ * TPDM enable operations
+ * The TPDM or Monitor serves as data collection component for various
+ * dataset types. It covers Basic Counts(BC), Tenure Counts(TC),
+ * Continuous Multi-Bit(CMB), Multi-lane CMB(MCMB) and Discrete Single
+ * Bit(DSB). This function will initialize the configuration according
+ * to the dataset type supported by the TPDM.
+ */
 static void __tpdm_enable(struct tpdm_drvdata *drvdata)
 {
 	CS_UNLOCK(drvdata->base);
 
-	/* Check if DSB datasets is present for TPDM. */
-	if (drvdata->datasets & TPDM_PIDR0_DS_DSB)
+	if (tpdm_has_dsb_dataset(drvdata))
 		tpdm_enable_dsb(drvdata);
 
 	CS_LOCK(drvdata->base);
@@ -76,8 +319,7 @@ static void __tpdm_disable(struct tpdm_drvdata *drvdata)
 {
 	CS_UNLOCK(drvdata->base);
 
-	/* Check if DSB datasets is present for TPDM. */
-	if (drvdata->datasets & TPDM_PIDR0_DS_DSB)
+	if (tpdm_has_dsb_dataset(drvdata))
 		tpdm_disable_dsb(drvdata);
 
 	CS_LOCK(drvdata->base);
@@ -110,16 +352,45 @@ static const struct coresight_ops tpdm_cs_ops = {
 	.source_ops	= &tpdm_source_ops,
 };
 
-static void tpdm_init_default_data(struct tpdm_drvdata *drvdata)
+static int tpdm_datasets_setup(struct tpdm_drvdata *drvdata)
 {
 	u32 pidr;
 
-	CS_UNLOCK(drvdata->base);
 	/*  Get the datasets present on the TPDM. */
 	pidr = readl_relaxed(drvdata->base + CORESIGHT_PERIPHIDR0);
 	drvdata->datasets |= pidr & GENMASK(TPDM_DATASETS - 1, 0);
-	CS_LOCK(drvdata->base);
+
+	if (tpdm_has_dsb_dataset(drvdata) && (!drvdata->dsb)) {
+		drvdata->dsb = devm_kzalloc(drvdata->dev,
+						sizeof(*drvdata->dsb), GFP_KERNEL);
+		if (!drvdata->dsb)
+			return -ENOMEM;
+	}
+	tpdm_reset_datasets(drvdata);
+
+	return 0;
+}
+
+static ssize_t reset_dataset_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf,
+				   size_t size)
+{
+	int ret = 0;
+	unsigned long val;
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 0, &val);
+	if (ret || val != 1)
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	tpdm_reset_datasets(drvdata);
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
 }
+static DEVICE_ATTR_WO(reset_dataset);
 
 /*
  * value 1: 64 bits test data
@@ -161,6 +432,7 @@ static ssize_t integration_test_store(struct device *dev,
 static DEVICE_ATTR_WO(integration_test);
 
 static struct attribute *tpdm_attrs[] = {
+	&dev_attr_reset_dataset.attr,
 	&dev_attr_integration_test.attr,
 	NULL,
 };
@@ -169,8 +441,421 @@ static struct attribute_group tpdm_attr_grp = {
 	.attrs = tpdm_attrs,
 };
 
+static ssize_t dsb_mode_show(struct device *dev,
+			     struct device_attribute *attr,
+			     char *buf)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	return sysfs_emit(buf, "%x\n", drvdata->dsb->mode);
+}
+
+static ssize_t dsb_mode_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf,
+			      size_t size)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val;
+
+	if ((kstrtoul(buf, 0, &val)) || (val < 0) ||
+			(val & ~TPDM_DSB_MODE_MASK))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->dsb->mode = val & TPDM_DSB_MODE_MASK;
+	spin_unlock(&drvdata->spinlock);
+	return size;
+}
+static DEVICE_ATTR_RW(dsb_mode);
+
+static ssize_t ctrl_idx_show(struct device *dev,
+			     struct device_attribute *attr,
+			     char *buf)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	return sysfs_emit(buf, "%u\n",
+			(unsigned int)drvdata->dsb->edge_ctrl_idx);
+}
+
+/*
+ * The EDCR registers can include up to 16 32-bit registers, and each
+ * one can be configured to control up to 16 edge detections(2 bits
+ * control one edge detection). So a total 256 edge detections can be
+ * configured. This function provides a way to set the index number of
+ * the edge detection which needs to be configured.
+ */
+static ssize_t ctrl_idx_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf,
+			      size_t size)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val;
+
+	if ((kstrtoul(buf, 0, &val)) || (val >= TPDM_DSB_MAX_LINES))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->dsb->edge_ctrl_idx = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(ctrl_idx);
+
+/*
+ * This function is used to control the edge detection according
+ * to the index number that has been set.
+ * "edge_ctrl" should be one of the following values.
+ * 0 - Rising edge detection
+ * 1 - Falling edge detection
+ * 2 - Rising and falling edge detection (toggle detection)
+ */
+static ssize_t ctrl_val_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf,
+			      size_t size)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val, edge_ctrl;
+	int reg;
+
+	if ((kstrtoul(buf, 0, &edge_ctrl)) || (edge_ctrl > 0x2))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	/*
+	 * There are 2 bit per DSB Edge Control line.
+	 * Thus we have 16 lines in a 32bit word.
+	 */
+	reg = EDCR_TO_WORD_IDX(drvdata->dsb->edge_ctrl_idx);
+	val = drvdata->dsb->edge_ctrl[reg];
+	val &= ~EDCR_TO_WORD_MASK(drvdata->dsb->edge_ctrl_idx);
+	val |= EDCR_TO_WORD_VAL(edge_ctrl, drvdata->dsb->edge_ctrl_idx);
+	drvdata->dsb->edge_ctrl[reg] = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_WO(ctrl_val);
+
+static ssize_t ctrl_mask_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf,
+			       size_t size)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val;
+	u32 set;
+	int reg;
+
+	if ((kstrtoul(buf, 0, &val)) || (val & ~1UL))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	/*
+	 * There is 1 bit per DSB Edge Control Mark line.
+	 * Thus we have 32 lines in a 32bit word.
+	 */
+	reg = EDCMR_TO_WORD_IDX(drvdata->dsb->edge_ctrl_idx);
+	set = drvdata->dsb->edge_ctrl_mask[reg];
+	if (val)
+		set |= BIT(EDCMR_TO_WORD_SHIFT(drvdata->dsb->edge_ctrl_idx));
+	else
+		set &= ~BIT(EDCMR_TO_WORD_SHIFT(drvdata->dsb->edge_ctrl_idx));
+	drvdata->dsb->edge_ctrl_mask[reg] = set;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_WO(ctrl_mask);
+
+static ssize_t enable_ts_show(struct device *dev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	return sysfs_emit(buf, "%u\n",
+			 (unsigned int)drvdata->dsb->patt_ts);
+}
+
+/*
+ * value 1: Enable/Disable DSB pattern timestamp
+ */
+static ssize_t enable_ts_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf,
+			       size_t size)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val;
+
+	if ((kstrtoul(buf, 0, &val)) || (val & ~1UL))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->dsb->patt_ts = !!val;
+	spin_unlock(&drvdata->spinlock);
+	return size;
+}
+static DEVICE_ATTR_RW(enable_ts);
+
+static ssize_t set_type_show(struct device *dev,
+			     struct device_attribute *attr,
+			     char *buf)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	return sysfs_emit(buf, "%u\n",
+			 (unsigned int)drvdata->dsb->patt_type);
+}
+
+/*
+ * value 1: Set DSB pattern type
+ */
+static ssize_t set_type_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val;
+
+	if ((kstrtoul(buf, 0, &val)) || (val & ~1UL))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->dsb->patt_type = val;
+	spin_unlock(&drvdata->spinlock);
+	return size;
+}
+static DEVICE_ATTR_RW(set_type);
+
+static ssize_t dsb_trig_type_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	return sysfs_emit(buf, "%u\n",
+			 (unsigned int)drvdata->dsb->trig_type);
+}
+
+/*
+ * Trigger type (boolean):
+ * false - Disable trigger type.
+ * true  - Enable trigger type.
+ */
+static ssize_t dsb_trig_type_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf,
+				   size_t size)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val;
+
+	if ((kstrtoul(buf, 0, &val)) || (val & ~1UL))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	if (val)
+		drvdata->dsb->trig_type = true;
+	else
+		drvdata->dsb->trig_type = false;
+	spin_unlock(&drvdata->spinlock);
+	return size;
+}
+static DEVICE_ATTR_RW(dsb_trig_type);
+
+static ssize_t dsb_trig_ts_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	return sysfs_emit(buf, "%u\n",
+			 (unsigned int)drvdata->dsb->trig_ts);
+}
+
+/*
+ * Trigger timestamp (boolean):
+ * false - Disable trigger timestamp.
+ * true  - Enable trigger timestamp.
+ */
+static ssize_t dsb_trig_ts_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf,
+				 size_t size)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val;
+
+	if ((kstrtoul(buf, 0, &val)) || (val & ~1UL))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	if (val)
+		drvdata->dsb->trig_ts = true;
+	else
+		drvdata->dsb->trig_ts = false;
+	spin_unlock(&drvdata->spinlock);
+	return size;
+}
+static DEVICE_ATTR_RW(dsb_trig_ts);
+
+static struct attribute *tpdm_dsb_edge_attrs[] = {
+	&dev_attr_ctrl_idx.attr,
+	&dev_attr_ctrl_val.attr,
+	&dev_attr_ctrl_mask.attr,
+	DSB_EDGE_CTRL_ATTR(0),
+	DSB_EDGE_CTRL_ATTR(1),
+	DSB_EDGE_CTRL_ATTR(2),
+	DSB_EDGE_CTRL_ATTR(3),
+	DSB_EDGE_CTRL_ATTR(4),
+	DSB_EDGE_CTRL_ATTR(5),
+	DSB_EDGE_CTRL_ATTR(6),
+	DSB_EDGE_CTRL_ATTR(7),
+	DSB_EDGE_CTRL_ATTR(8),
+	DSB_EDGE_CTRL_ATTR(9),
+	DSB_EDGE_CTRL_ATTR(10),
+	DSB_EDGE_CTRL_ATTR(11),
+	DSB_EDGE_CTRL_ATTR(12),
+	DSB_EDGE_CTRL_ATTR(13),
+	DSB_EDGE_CTRL_ATTR(14),
+	DSB_EDGE_CTRL_ATTR(15),
+	DSB_EDGE_CTRL_MASK_ATTR(0),
+	DSB_EDGE_CTRL_MASK_ATTR(1),
+	DSB_EDGE_CTRL_MASK_ATTR(2),
+	DSB_EDGE_CTRL_MASK_ATTR(3),
+	DSB_EDGE_CTRL_MASK_ATTR(4),
+	DSB_EDGE_CTRL_MASK_ATTR(5),
+	DSB_EDGE_CTRL_MASK_ATTR(6),
+	DSB_EDGE_CTRL_MASK_ATTR(7),
+	NULL,
+};
+
+static struct attribute *tpdm_dsb_trig_patt_attrs[] = {
+	DSB_TRIG_PATT_ATTR(0),
+	DSB_TRIG_PATT_ATTR(1),
+	DSB_TRIG_PATT_ATTR(2),
+	DSB_TRIG_PATT_ATTR(3),
+	DSB_TRIG_PATT_ATTR(4),
+	DSB_TRIG_PATT_ATTR(5),
+	DSB_TRIG_PATT_ATTR(6),
+	DSB_TRIG_PATT_ATTR(7),
+	DSB_TRIG_PATT_MASK_ATTR(0),
+	DSB_TRIG_PATT_MASK_ATTR(1),
+	DSB_TRIG_PATT_MASK_ATTR(2),
+	DSB_TRIG_PATT_MASK_ATTR(3),
+	DSB_TRIG_PATT_MASK_ATTR(4),
+	DSB_TRIG_PATT_MASK_ATTR(5),
+	DSB_TRIG_PATT_MASK_ATTR(6),
+	DSB_TRIG_PATT_MASK_ATTR(7),
+	NULL,
+};
+
+static struct attribute *tpdm_dsb_patt_attrs[] = {
+	DSB_PATT_ATTR(0),
+	DSB_PATT_ATTR(1),
+	DSB_PATT_ATTR(2),
+	DSB_PATT_ATTR(3),
+	DSB_PATT_ATTR(4),
+	DSB_PATT_ATTR(5),
+	DSB_PATT_ATTR(6),
+	DSB_PATT_ATTR(7),
+	DSB_PATT_MASK_ATTR(0),
+	DSB_PATT_MASK_ATTR(1),
+	DSB_PATT_MASK_ATTR(2),
+	DSB_PATT_MASK_ATTR(3),
+	DSB_PATT_MASK_ATTR(4),
+	DSB_PATT_MASK_ATTR(5),
+	DSB_PATT_MASK_ATTR(6),
+	DSB_PATT_MASK_ATTR(7),
+	&dev_attr_enable_ts.attr,
+	&dev_attr_set_type.attr,
+	NULL,
+};
+
+static struct attribute *tpdm_dsb_msr_attrs[] = {
+	DSB_MSR_ATTR(0),
+	DSB_MSR_ATTR(1),
+	DSB_MSR_ATTR(2),
+	DSB_MSR_ATTR(3),
+	DSB_MSR_ATTR(4),
+	DSB_MSR_ATTR(5),
+	DSB_MSR_ATTR(6),
+	DSB_MSR_ATTR(7),
+	DSB_MSR_ATTR(8),
+	DSB_MSR_ATTR(9),
+	DSB_MSR_ATTR(10),
+	DSB_MSR_ATTR(11),
+	DSB_MSR_ATTR(12),
+	DSB_MSR_ATTR(13),
+	DSB_MSR_ATTR(14),
+	DSB_MSR_ATTR(15),
+	DSB_MSR_ATTR(16),
+	DSB_MSR_ATTR(17),
+	DSB_MSR_ATTR(18),
+	DSB_MSR_ATTR(19),
+	DSB_MSR_ATTR(20),
+	DSB_MSR_ATTR(21),
+	DSB_MSR_ATTR(22),
+	DSB_MSR_ATTR(23),
+	DSB_MSR_ATTR(24),
+	DSB_MSR_ATTR(25),
+	DSB_MSR_ATTR(26),
+	DSB_MSR_ATTR(27),
+	DSB_MSR_ATTR(28),
+	DSB_MSR_ATTR(29),
+	DSB_MSR_ATTR(30),
+	DSB_MSR_ATTR(31),
+	NULL,
+};
+
+static struct attribute *tpdm_dsb_attrs[] = {
+	&dev_attr_dsb_mode.attr,
+	&dev_attr_dsb_trig_ts.attr,
+	&dev_attr_dsb_trig_type.attr,
+	NULL,
+};
+
+static struct attribute_group tpdm_dsb_attr_grp = {
+	.attrs = tpdm_dsb_attrs,
+	.is_visible = tpdm_dsb_is_visible,
+};
+
+static struct attribute_group tpdm_dsb_edge_grp = {
+	.attrs = tpdm_dsb_edge_attrs,
+	.is_visible = tpdm_dsb_is_visible,
+	.name = "dsb_edge",
+};
+
+static struct attribute_group tpdm_dsb_trig_patt_grp = {
+	.attrs = tpdm_dsb_trig_patt_attrs,
+	.is_visible = tpdm_dsb_is_visible,
+	.name = "dsb_trig_patt",
+};
+
+static struct attribute_group tpdm_dsb_patt_grp = {
+	.attrs = tpdm_dsb_patt_attrs,
+	.is_visible = tpdm_dsb_is_visible,
+	.name = "dsb_patt",
+};
+
+static struct attribute_group tpdm_dsb_msr_grp = {
+	.attrs = tpdm_dsb_msr_attrs,
+	.is_visible = tpdm_dsb_msr_is_visible,
+	.name = "dsb_msr",
+};
+
 static const struct attribute_group *tpdm_attr_grps[] = {
 	&tpdm_attr_grp,
+	&tpdm_dsb_attr_grp,
+	&tpdm_dsb_edge_grp,
+	&tpdm_dsb_trig_patt_grp,
+	&tpdm_dsb_patt_grp,
+	&tpdm_dsb_msr_grp,
 	NULL,
 };
 
@@ -181,6 +866,7 @@ static int tpdm_probe(struct amba_device *adev, const struct amba_id *id)
 	struct coresight_platform_data *pdata;
 	struct tpdm_drvdata *drvdata;
 	struct coresight_desc desc = { 0 };
+	int ret;
 
 	pdata = coresight_get_platform_data(dev);
 	if (IS_ERR(pdata))
@@ -200,12 +886,20 @@ static int tpdm_probe(struct amba_device *adev, const struct amba_id *id)
 
 	drvdata->base = base;
 
+	ret = tpdm_datasets_setup(drvdata);
+	if (ret)
+		return ret;
+
+	if (drvdata && tpdm_has_dsb_dataset(drvdata))
+		of_property_read_u32(drvdata->dev->of_node,
+			   "qcom,dsb-msrs-num", &drvdata->dsb_msr_num);
+
 	/* Set up coresight component description */
 	desc.name = coresight_alloc_device_name(&tpdm_devs, dev);
 	if (!desc.name)
 		return -ENOMEM;
 	desc.type = CORESIGHT_DEV_TYPE_SOURCE;
-	desc.subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS;
+	desc.subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM;
 	desc.ops = &tpdm_cs_ops;
 	desc.pdata = adev->dev.platform_data;
 	desc.dev = &adev->dev;
@@ -216,7 +910,7 @@ static int tpdm_probe(struct amba_device *adev, const struct amba_id *id)
 		return PTR_ERR(drvdata->csdev);
 
 	spin_lock_init(&drvdata->spinlock);
-	tpdm_init_default_data(drvdata);
+
 	/* Decrease pm refcount when probe is done.*/
 	pm_runtime_put(&adev->dev);
 
diff --git a/drivers/hwtracing/coresight/coresight-tpdm.h b/drivers/hwtracing/coresight/coresight-tpdm.h
index 543854043a2d..4115b2a17b8d 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.h
+++ b/drivers/hwtracing/coresight/coresight-tpdm.h
@@ -11,8 +11,52 @@
 
 /* DSB Subunit Registers */
 #define TPDM_DSB_CR		(0x780)
+#define TPDM_DSB_TIER		(0x784)
+#define TPDM_DSB_TPR(n)		(0x788 + (n * 4))
+#define TPDM_DSB_TPMR(n)	(0x7A8 + (n * 4))
+#define TPDM_DSB_XPR(n)		(0x7C8 + (n * 4))
+#define TPDM_DSB_XPMR(n)	(0x7E8 + (n * 4))
+#define TPDM_DSB_EDCR(n)	(0x808 + (n * 4))
+#define TPDM_DSB_EDCMR(n)	(0x848 + (n * 4))
+#define TPDM_DSB_MSR(n)		(0x980 + (n * 4))
+
 /* Enable bit for DSB subunit */
 #define TPDM_DSB_CR_ENA		BIT(0)
+/* Enable bit for DSB subunit perfmance mode */
+#define TPDM_DSB_CR_MODE		BIT(1)
+/* Enable bit for DSB subunit trigger type */
+#define TPDM_DSB_CR_TRIG_TYPE		BIT(12)
+/* Data bits for DSB high performace mode */
+#define TPDM_DSB_CR_HPSEL		GENMASK(6, 2)
+/* Data bits for DSB test mode */
+#define TPDM_DSB_CR_TEST_MODE		GENMASK(10, 9)
+
+/* Enable bit for DSB subunit pattern timestamp */
+#define TPDM_DSB_TIER_PATT_TSENAB		BIT(0)
+/* Enable bit for DSB subunit trigger timestamp */
+#define TPDM_DSB_TIER_XTRIG_TSENAB		BIT(1)
+/* Bit for DSB subunit pattern type */
+#define TPDM_DSB_TIER_PATT_TYPE			BIT(2)
+
+/* DSB programming modes */
+/* DSB mode bits mask */
+#define TPDM_DSB_MODE_MASK			GENMASK(8, 0)
+/* Test mode control bit*/
+#define TPDM_DSB_MODE_TEST(val)	(val & GENMASK(1, 0))
+/* Performance mode */
+#define TPDM_DSB_MODE_PERF		BIT(3)
+/* High performance mode */
+#define TPDM_DSB_MODE_HPBYTESEL(val)	(val & GENMASK(8, 4))
+
+#define EDCRS_PER_WORD			16
+#define EDCR_TO_WORD_IDX(r)		((r) / EDCRS_PER_WORD)
+#define EDCR_TO_WORD_SHIFT(r)		((r % EDCRS_PER_WORD) * 2)
+#define EDCR_TO_WORD_VAL(val, r)	(val << EDCR_TO_WORD_SHIFT(r))
+#define EDCR_TO_WORD_MASK(r)		EDCR_TO_WORD_VAL(0x3, r)
+
+#define EDCMRS_PER_WORD				32
+#define EDCMR_TO_WORD_IDX(r)		((r) / EDCMRS_PER_WORD)
+#define EDCMR_TO_WORD_SHIFT(r)		((r) % EDCMRS_PER_WORD)
 
 /* TPDM integration test registers */
 #define TPDM_ITATBCNTRL		(0xEF0)
@@ -40,6 +84,95 @@
 #define TPDM_PIDR0_DS_IMPDEF	BIT(0)
 #define TPDM_PIDR0_DS_DSB	BIT(1)
 
+#define TPDM_DSB_MAX_LINES	256
+/* MAX number of EDCR registers */
+#define TPDM_DSB_MAX_EDCR	16
+/* MAX number of EDCMR registers */
+#define TPDM_DSB_MAX_EDCMR	8
+/* MAX number of DSB pattern */
+#define TPDM_DSB_MAX_PATT	8
+/* MAX number of DSB MSR */
+#define TPDM_DSB_MAX_MSR 32
+
+#define tpdm_simple_dataset_ro(name, mem, idx)			\
+	(&((struct tpdm_dataset_attribute[]) {			\
+	   {								\
+		__ATTR(name, 0444, tpdm_simple_dataset_show, NULL),	\
+		mem,							\
+		idx,							\
+	   }								\
+	})[0].attr.attr)
+
+#define tpdm_simple_dataset_rw(name, mem, idx)			\
+	(&((struct tpdm_dataset_attribute[]) {			\
+	   {								\
+		__ATTR(name, 0644, tpdm_simple_dataset_show,		\
+		tpdm_simple_dataset_store),		\
+		mem,							\
+		idx,							\
+	   }								\
+	})[0].attr.attr)
+
+#define DSB_EDGE_CTRL_ATTR(nr)					\
+		tpdm_simple_dataset_ro(edcr##nr,		\
+		DSB_EDGE_CTRL, nr)
+
+#define DSB_EDGE_CTRL_MASK_ATTR(nr)				\
+		tpdm_simple_dataset_ro(edcmr##nr,		\
+		DSB_EDGE_CTRL_MASK, nr)
+
+#define DSB_TRIG_PATT_ATTR(nr)					\
+		tpdm_simple_dataset_rw(xpr##nr,			\
+		DSB_TRIG_PATT, nr)
+
+#define DSB_TRIG_PATT_MASK_ATTR(nr)				\
+		tpdm_simple_dataset_rw(xpmr##nr,		\
+		DSB_TRIG_PATT_MASK, nr)
+
+#define DSB_PATT_ATTR(nr)					\
+		tpdm_simple_dataset_rw(tpr##nr,			\
+		DSB_PATT, nr)
+
+#define DSB_PATT_MASK_ATTR(nr)					\
+		tpdm_simple_dataset_rw(tpmr##nr,		\
+		DSB_PATT_MASK, nr)
+
+#define DSB_MSR_ATTR(nr)					\
+		tpdm_simple_dataset_rw(msr##nr,			\
+		DSB_MSR, nr)
+
+/**
+ * struct dsb_dataset - specifics associated to dsb dataset
+ * @mode:             DSB programming mode
+ * @edge_ctrl_idx     Index number of the edge control
+ * @edge_ctrl:        Save value for edge control
+ * @edge_ctrl_mask:   Save value for edge control mask
+ * @patt_val:         Save value for pattern
+ * @patt_mask:        Save value for pattern mask
+ * @trig_patt:        Save value for trigger pattern
+ * @trig_patt_mask:   Save value for trigger pattern mask
+ * @msr               Save value for MSR
+ * @patt_ts:          Enable/Disable pattern timestamp
+ * @patt_type:        Set pattern type
+ * @trig_ts:          Enable/Disable trigger timestamp.
+ * @trig_type:        Enable/Disable trigger type.
+ */
+struct dsb_dataset {
+	u32			mode;
+	u32			edge_ctrl_idx;
+	u32			edge_ctrl[TPDM_DSB_MAX_EDCR];
+	u32			edge_ctrl_mask[TPDM_DSB_MAX_EDCMR];
+	u32			patt_val[TPDM_DSB_MAX_PATT];
+	u32			patt_mask[TPDM_DSB_MAX_PATT];
+	u32			trig_patt[TPDM_DSB_MAX_PATT];
+	u32			trig_patt_mask[TPDM_DSB_MAX_PATT];
+	u32			msr[TPDM_DSB_MAX_MSR];
+	bool			patt_ts;
+	bool			patt_type;
+	bool			trig_ts;
+	bool			trig_type;
+};
+
 /**
  * struct tpdm_drvdata - specifics associated to an TPDM component
  * @base:       memory mapped base address for this component.
@@ -48,6 +181,8 @@
  * @spinlock:   lock for the drvdata value.
  * @enable:     enable status of the component.
  * @datasets:   The datasets types present of the TPDM.
+ * @dsb         Specifics associated to TPDM DSB.
+ * @dsb_msr_num Number of MSR supported by DSB TPDM
  */
 
 struct tpdm_drvdata {
@@ -57,6 +192,32 @@ struct tpdm_drvdata {
 	spinlock_t		spinlock;
 	bool			enable;
 	unsigned long		datasets;
+	struct dsb_dataset	*dsb;
+	u32			dsb_msr_num;
+};
+
+/* Enumerate members of various datasets */
+enum dataset_mem {
+	DSB_EDGE_CTRL,
+	DSB_EDGE_CTRL_MASK,
+	DSB_TRIG_PATT,
+	DSB_TRIG_PATT_MASK,
+	DSB_PATT,
+	DSB_PATT_MASK,
+	DSB_MSR,
+};
+
+/**
+ * struct tpdm_dataset_attribute - Record the member variables and
+ * index number of datasets that need to be operated by sysfs file
+ * @attr:       The device attribute
+ * @mem:        The member in the dataset data structure
+ * @idx:        The index number of the array data
+ */
+struct tpdm_dataset_attribute {
+	struct device_attribute attr;
+	enum dataset_mem mem;
+	u32 idx;
 };
 
 #endif  /* _CORESIGHT_CORESIGHT_TPDM_H */
diff --git a/drivers/hwtracing/coresight/coresight-trbe.c b/drivers/hwtracing/coresight/coresight-trbe.c
index e20c1c6acc73..6136776482e6 100644
--- a/drivers/hwtracing/coresight/coresight-trbe.c
+++ b/drivers/hwtracing/coresight/coresight-trbe.c
@@ -1253,8 +1253,18 @@ static void arm_trbe_register_coresight_cpu(struct trbe_drvdata *drvdata, int cp
 	desc.name = devm_kasprintf(dev, GFP_KERNEL, "trbe%d", cpu);
 	if (!desc.name)
 		goto cpu_clear;
-
-	desc.pdata = coresight_get_platform_data(dev);
+	/*
+	 * TRBE coresight devices do not need regular connections
+	 * information, as the paths get built between all percpu
+	 * source and their respective percpu sink devices. Though
+	 * coresight_register() expect device connections via the
+	 * platform_data, which TRBE devices do not have. As they
+	 * are not real ACPI devices, coresight_get_platform_data()
+	 * ends up failing. Instead let's allocate a dummy zeroed
+	 * coresight_platform_data structure and assign that back
+	 * into the device for that purpose.
+	 */
+	desc.pdata = devm_kzalloc(dev, sizeof(*desc.pdata), GFP_KERNEL);
 	if (IS_ERR(desc.pdata))
 		goto cpu_clear;
 
@@ -1520,14 +1530,13 @@ probe_failed:
 	return ret;
 }
 
-static int arm_trbe_device_remove(struct platform_device *pdev)
+static void arm_trbe_device_remove(struct platform_device *pdev)
 {
 	struct trbe_drvdata *drvdata = platform_get_drvdata(pdev);
 
 	arm_trbe_remove_cpuhp(drvdata);
 	arm_trbe_remove_coresight(drvdata);
 	arm_trbe_remove_irq(drvdata);
-	return 0;
 }
 
 static const struct of_device_id arm_trbe_of_match[] = {
@@ -1536,14 +1545,23 @@ static const struct of_device_id arm_trbe_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, arm_trbe_of_match);
 
+#ifdef CONFIG_ACPI
+static const struct platform_device_id arm_trbe_acpi_match[] = {
+	{ ARMV8_TRBE_PDEV_NAME, 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(platform, arm_trbe_acpi_match);
+#endif
+
 static struct platform_driver arm_trbe_driver = {
+	.id_table = ACPI_PTR(arm_trbe_acpi_match),
 	.driver	= {
 		.name = DRVNAME,
 		.of_match_table = of_match_ptr(arm_trbe_of_match),
 		.suppress_bind_attrs = true,
 	},
 	.probe	= arm_trbe_device_probe,
-	.remove	= arm_trbe_device_remove,
+	.remove_new = arm_trbe_device_remove,
 };
 
 static int __init arm_trbe_init(void)
diff --git a/drivers/hwtracing/coresight/coresight-trbe.h b/drivers/hwtracing/coresight/coresight-trbe.h
index e915e749be55..45202c48acce 100644
--- a/drivers/hwtracing/coresight/coresight-trbe.h
+++ b/drivers/hwtracing/coresight/coresight-trbe.h
@@ -7,11 +7,13 @@
  *
  * Author: Anshuman Khandual <anshuman.khandual@arm.com>
  */
+#include <linux/acpi.h>
 #include <linux/coresight.h>
 #include <linux/device.h>
 #include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/of.h>
+#include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>
 #include <linux/smp.h>
 
diff --git a/drivers/hwtracing/coresight/ultrasoc-smb.c b/drivers/hwtracing/coresight/ultrasoc-smb.c
index 6e32d31a95fe..10e886455b8b 100644
--- a/drivers/hwtracing/coresight/ultrasoc-smb.c
+++ b/drivers/hwtracing/coresight/ultrasoc-smb.c
@@ -97,27 +97,19 @@ static int smb_open(struct inode *inode, struct file *file)
 {
 	struct smb_drv_data *drvdata = container_of(file->private_data,
 					struct smb_drv_data, miscdev);
-	int ret = 0;
 
-	spin_lock(&drvdata->spinlock);
+	guard(spinlock)(&drvdata->spinlock);
 
-	if (drvdata->reading) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (drvdata->reading)
+		return -EBUSY;
 
-	if (atomic_read(&drvdata->csdev->refcnt)) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (atomic_read(&drvdata->csdev->refcnt))
+		return -EBUSY;
 
 	smb_update_data_size(drvdata);
-
 	drvdata->reading = true;
-out:
-	spin_unlock(&drvdata->spinlock);
 
-	return ret;
+	return 0;
 }
 
 static ssize_t smb_read(struct file *file, char __user *data, size_t len,
@@ -160,9 +152,8 @@ static int smb_release(struct inode *inode, struct file *file)
 	struct smb_drv_data *drvdata = container_of(file->private_data,
 					struct smb_drv_data, miscdev);
 
-	spin_lock(&drvdata->spinlock);
+	guard(spinlock)(&drvdata->spinlock);
 	drvdata->reading = false;
-	spin_unlock(&drvdata->spinlock);
 
 	return 0;
 }
@@ -255,19 +246,15 @@ static int smb_enable(struct coresight_device *csdev, enum cs_mode mode,
 	struct smb_drv_data *drvdata = dev_get_drvdata(csdev->dev.parent);
 	int ret = 0;
 
-	spin_lock(&drvdata->spinlock);
+	guard(spinlock)(&drvdata->spinlock);
 
 	/* Do nothing, the trace data is reading by other interface now */
-	if (drvdata->reading) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (drvdata->reading)
+		return -EBUSY;
 
 	/* Do nothing, the SMB is already enabled as other mode */
-	if (drvdata->mode != CS_MODE_DISABLED && drvdata->mode != mode) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (drvdata->mode != CS_MODE_DISABLED && drvdata->mode != mode)
+		return -EBUSY;
 
 	switch (mode) {
 	case CS_MODE_SYSFS:
@@ -281,13 +268,10 @@ static int smb_enable(struct coresight_device *csdev, enum cs_mode mode,
 	}
 
 	if (ret)
-		goto out;
+		return ret;
 
 	atomic_inc(&csdev->refcnt);
-
 	dev_dbg(&csdev->dev, "Ultrasoc SMB enabled\n");
-out:
-	spin_unlock(&drvdata->spinlock);
 
 	return ret;
 }
@@ -295,19 +279,14 @@ out:
 static int smb_disable(struct coresight_device *csdev)
 {
 	struct smb_drv_data *drvdata = dev_get_drvdata(csdev->dev.parent);
-	int ret = 0;
 
-	spin_lock(&drvdata->spinlock);
+	guard(spinlock)(&drvdata->spinlock);
 
-	if (drvdata->reading) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (drvdata->reading)
+		return -EBUSY;
 
-	if (atomic_dec_return(&csdev->refcnt)) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (atomic_dec_return(&csdev->refcnt))
+		return -EBUSY;
 
 	/* Complain if we (somehow) got out of sync */
 	WARN_ON_ONCE(drvdata->mode == CS_MODE_DISABLED);
@@ -317,12 +296,9 @@ static int smb_disable(struct coresight_device *csdev)
 	/* Dissociate from the target process. */
 	drvdata->pid = -1;
 	drvdata->mode = CS_MODE_DISABLED;
-
 	dev_dbg(&csdev->dev, "Ultrasoc SMB disabled\n");
-out:
-	spin_unlock(&drvdata->spinlock);
 
-	return ret;
+	return 0;
 }
 
 static void *smb_alloc_buffer(struct coresight_device *csdev,
@@ -395,17 +371,17 @@ static unsigned long smb_update_buffer(struct coresight_device *csdev,
 	struct smb_drv_data *drvdata = dev_get_drvdata(csdev->dev.parent);
 	struct smb_data_buffer *sdb = &drvdata->sdb;
 	struct cs_buffers *buf = sink_config;
-	unsigned long data_size = 0;
+	unsigned long data_size;
 	bool lost = false;
 
 	if (!buf)
 		return 0;
 
-	spin_lock(&drvdata->spinlock);
+	guard(spinlock)(&drvdata->spinlock);
 
 	/* Don't do anything if another tracer is using this sink. */
 	if (atomic_read(&csdev->refcnt) != 1)
-		goto out;
+		return 0;
 
 	smb_disable_hw(drvdata);
 	smb_update_data_size(drvdata);
@@ -424,8 +400,6 @@ static unsigned long smb_update_buffer(struct coresight_device *csdev,
 	smb_sync_perf_buffer(drvdata, buf, handle->head);
 	if (!buf->snapshot && lost)
 		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
-out:
-	spin_unlock(&drvdata->spinlock);
 
 	return data_size;
 }
@@ -601,15 +575,13 @@ static int smb_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int smb_remove(struct platform_device *pdev)
+static void smb_remove(struct platform_device *pdev)
 {
 	struct smb_drv_data *drvdata = platform_get_drvdata(pdev);
 
 	smb_unregister_sink(drvdata);
 
 	smb_config_inport(&pdev->dev, false);
-
-	return 0;
 }
 
 #ifdef CONFIG_ACPI
@@ -627,7 +599,7 @@ static struct platform_driver smb_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = smb_probe,
-	.remove = smb_remove,
+	.remove_new = smb_remove,
 };
 module_platform_driver(smb_driver);
 
diff --git a/drivers/hwtracing/ptt/hisi_ptt.c b/drivers/hwtracing/ptt/hisi_ptt.c
index a991ecb7515a..c1b5fd2b8974 100644
--- a/drivers/hwtracing/ptt/hisi_ptt.c
+++ b/drivers/hwtracing/ptt/hisi_ptt.c
@@ -183,6 +183,10 @@ static void hisi_ptt_wait_dma_reset_done(struct hisi_ptt *hisi_ptt)
 static void hisi_ptt_trace_end(struct hisi_ptt *hisi_ptt)
 {
 	writel(0, hisi_ptt->iobase + HISI_PTT_TRACE_CTRL);
+
+	/* Mask the interrupt on the end */
+	writel(HISI_PTT_TRACE_INT_MASK_ALL, hisi_ptt->iobase + HISI_PTT_TRACE_INT_MASK);
+
 	hisi_ptt->trace_ctrl.started = false;
 }
 
@@ -270,15 +274,14 @@ static int hisi_ptt_update_aux(struct hisi_ptt *hisi_ptt, int index, bool stop)
 	buf->pos += size;
 
 	/*
-	 * Just commit the traced data if we're going to stop. Otherwise if the
-	 * resident AUX buffer cannot contain the data of next trace buffer,
-	 * apply a new one.
+	 * Always commit the data to the AUX buffer in time to make sure
+	 * userspace got enough time to consume the data.
+	 *
+	 * If we're not going to stop, apply a new one and check whether
+	 * there's enough room for the next trace.
 	 */
-	if (stop) {
-		perf_aux_output_end(handle, buf->pos);
-	} else if (buf->length - buf->pos < HISI_PTT_TRACE_BUF_SIZE) {
-		perf_aux_output_end(handle, buf->pos);
-
+	perf_aux_output_end(handle, size);
+	if (!stop) {
 		buf = perf_aux_output_begin(handle, event);
 		if (!buf)
 			return -EINVAL;
diff --git a/drivers/hwtracing/ptt/hisi_ptt.h b/drivers/hwtracing/ptt/hisi_ptt.h
index e17f045d7e72..46030aa88081 100644
--- a/drivers/hwtracing/ptt/hisi_ptt.h
+++ b/drivers/hwtracing/ptt/hisi_ptt.h
@@ -47,6 +47,7 @@
 #define HISI_PTT_TRACE_INT_STAT		0x0890
 #define   HISI_PTT_TRACE_INT_STAT_MASK	GENMASK(3, 0)
 #define HISI_PTT_TRACE_INT_MASK		0x0894
+#define   HISI_PTT_TRACE_INT_MASK_ALL	GENMASK(3, 0)
 #define HISI_PTT_TUNING_INT_STAT	0x0898
 #define   HISI_PTT_TUNING_INT_STAT_MASK	BIT(0)
 #define HISI_PTT_TRACE_WR_STS		0x08a0
diff --git a/drivers/i2c/busses/Makefile b/drivers/i2c/busses/Makefile
index 3757b9391e60..aa0ee8ecd6f2 100644
--- a/drivers/i2c/busses/Makefile
+++ b/drivers/i2c/busses/Makefile
@@ -90,10 +90,8 @@ obj-$(CONFIG_I2C_NPCM)		+= i2c-npcm7xx.o
 obj-$(CONFIG_I2C_OCORES)	+= i2c-ocores.o
 obj-$(CONFIG_I2C_OMAP)		+= i2c-omap.o
 obj-$(CONFIG_I2C_OWL)		+= i2c-owl.o
-i2c-pasemi-objs := i2c-pasemi-core.o i2c-pasemi-pci.o
-obj-$(CONFIG_I2C_PASEMI)	+= i2c-pasemi.o
-i2c-apple-objs := i2c-pasemi-core.o i2c-pasemi-platform.o
-obj-$(CONFIG_I2C_APPLE)	+= i2c-apple.o
+obj-$(CONFIG_I2C_PASEMI)	+= i2c-pasemi-core.o i2c-pasemi-pci.o
+obj-$(CONFIG_I2C_APPLE)		+= i2c-pasemi-core.o i2c-pasemi-platform.o
 obj-$(CONFIG_I2C_PCA_PLATFORM)	+= i2c-pca-platform.o
 obj-$(CONFIG_I2C_PNX)		+= i2c-pnx.o
 obj-$(CONFIG_I2C_PXA)		+= i2c-pxa.o
diff --git a/drivers/i2c/busses/i2c-ali1535.c b/drivers/i2c/busses/i2c-ali1535.c
index ee83c4581bce..461eb23f9d47 100644
--- a/drivers/i2c/busses/i2c-ali1535.c
+++ b/drivers/i2c/busses/i2c-ali1535.c
@@ -477,7 +477,7 @@ static const struct i2c_algorithm smbus_algorithm = {
 
 static struct i2c_adapter ali1535_adapter = {
 	.owner		= THIS_MODULE,
-	.class          = I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class          = I2C_CLASS_HWMON,
 	.algo		= &smbus_algorithm,
 };
 
diff --git a/drivers/i2c/busses/i2c-ali1563.c b/drivers/i2c/busses/i2c-ali1563.c
index 55a9e93fbfeb..307fb0666ecb 100644
--- a/drivers/i2c/busses/i2c-ali1563.c
+++ b/drivers/i2c/busses/i2c-ali1563.c
@@ -390,7 +390,7 @@ static const struct i2c_algorithm ali1563_algorithm = {
 
 static struct i2c_adapter ali1563_adapter = {
 	.owner	= THIS_MODULE,
-	.class	= I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class	= I2C_CLASS_HWMON,
 	.algo	= &ali1563_algorithm,
 };
 
diff --git a/drivers/i2c/busses/i2c-ali15x3.c b/drivers/i2c/busses/i2c-ali15x3.c
index 0231c5be6354..d2fa30deb054 100644
--- a/drivers/i2c/busses/i2c-ali15x3.c
+++ b/drivers/i2c/busses/i2c-ali15x3.c
@@ -461,7 +461,7 @@ static const struct i2c_algorithm smbus_algorithm = {
 
 static struct i2c_adapter ali15x3_adapter = {
 	.owner		= THIS_MODULE,
-	.class          = I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class          = I2C_CLASS_HWMON,
 	.algo		= &smbus_algorithm,
 };
 
diff --git a/drivers/i2c/busses/i2c-amd756.c b/drivers/i2c/busses/i2c-amd756.c
index ef1307a258e9..208310db906d 100644
--- a/drivers/i2c/busses/i2c-amd756.c
+++ b/drivers/i2c/busses/i2c-amd756.c
@@ -285,7 +285,7 @@ static const struct i2c_algorithm smbus_algorithm = {
 
 struct i2c_adapter amd756_smbus = {
 	.owner		= THIS_MODULE,
-	.class          = I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class          = I2C_CLASS_HWMON,
 	.algo		= &smbus_algorithm,
 };
 
diff --git a/drivers/i2c/busses/i2c-amd8111.c b/drivers/i2c/busses/i2c-amd8111.c
index 1ed7e945bb6d..42a9b1221065 100644
--- a/drivers/i2c/busses/i2c-amd8111.c
+++ b/drivers/i2c/busses/i2c-amd8111.c
@@ -449,7 +449,7 @@ static int amd8111_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	smbus->adapter.owner = THIS_MODULE;
 	snprintf(smbus->adapter.name, sizeof(smbus->adapter.name),
 		"SMBus2 AMD8111 adapter at %04x", smbus->base);
-	smbus->adapter.class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	smbus->adapter.class = I2C_CLASS_HWMON;
 	smbus->adapter.algo = &smbus_algorithm;
 	smbus->adapter.algo_data = smbus;
 
diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c
index 5511fd46a65e..ce8c4846b7fa 100644
--- a/drivers/i2c/busses/i2c-aspeed.c
+++ b/drivers/i2c/busses/i2c-aspeed.c
@@ -445,6 +445,7 @@ static u32 aspeed_i2c_master_irq(struct aspeed_i2c_bus *bus, u32 irq_status)
 			irq_status);
 		irq_handled |= (irq_status & ASPEED_I2CD_INTR_MASTER_ERRORS);
 		if (bus->master_state != ASPEED_I2C_MASTER_INACTIVE) {
+			irq_handled = irq_status;
 			bus->cmd_err = ret;
 			bus->master_state = ASPEED_I2C_MASTER_INACTIVE;
 			goto out_complete;
diff --git a/drivers/i2c/busses/i2c-cpm.c b/drivers/i2c/busses/i2c-cpm.c
index 9a664abf734d..4404b4aac676 100644
--- a/drivers/i2c/busses/i2c-cpm.c
+++ b/drivers/i2c/busses/i2c-cpm.c
@@ -658,7 +658,7 @@ static int cpm_i2c_probe(struct platform_device *ofdev)
 	/* register new adapter to i2c module... */
 
 	data = of_get_property(ofdev->dev.of_node, "linux,i2c-index", &len);
-	cpm->adap.nr = (data && len == 4) ? be32_to_cpup(data) : -1;
+	cpm->adap.nr = (data && len == 4) ? *data : -1;
 	result = i2c_add_numbered_adapter(&cpm->adap);
 
 	if (result < 0)
diff --git a/drivers/i2c/busses/i2c-elektor.c b/drivers/i2c/busses/i2c-elektor.c
index b0f50dce9d0f..cfe8665cacd2 100644
--- a/drivers/i2c/busses/i2c-elektor.c
+++ b/drivers/i2c/busses/i2c-elektor.c
@@ -188,7 +188,7 @@ static struct i2c_algo_pcf_data pcf_isa_data = {
 
 static struct i2c_adapter pcf_isa_ops = {
 	.owner		= THIS_MODULE,
-	.class		= I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class		= I2C_CLASS_HWMON,
 	.algo_data	= &pcf_isa_data,
 	.name		= "i2c-elektor",
 };
diff --git a/drivers/i2c/busses/i2c-gpio.c b/drivers/i2c/busses/i2c-gpio.c
index fb35a75fe0e3..4f1411b1a775 100644
--- a/drivers/i2c/busses/i2c-gpio.c
+++ b/drivers/i2c/busses/i2c-gpio.c
@@ -25,7 +25,6 @@ struct i2c_gpio_private_data {
 	struct i2c_algo_bit_data bit_data;
 	struct i2c_gpio_platform_data pdata;
 #ifdef CONFIG_I2C_GPIO_FAULT_INJECTOR
-	struct dentry *debug_dir;
 	/* these must be protected by bus lock */
 	struct completion scl_irq_completion;
 	u64 scl_irq_data;
@@ -72,7 +71,6 @@ static int i2c_gpio_getscl(void *data)
 }
 
 #ifdef CONFIG_I2C_GPIO_FAULT_INJECTOR
-static struct dentry *i2c_gpio_debug_dir;
 
 #define setsda(bd, val)	((bd)->setsda((bd)->data, val))
 #define setscl(bd, val)	((bd)->setscl((bd)->data, val))
@@ -258,41 +256,23 @@ static void i2c_gpio_fault_injector_init(struct platform_device *pdev)
 {
 	struct i2c_gpio_private_data *priv = platform_get_drvdata(pdev);
 
-	/*
-	 * If there will be a debugfs-dir per i2c adapter somewhen, put the
-	 * 'fault-injector' dir there. Until then, we have a global dir with
-	 * all adapters as subdirs.
-	 */
-	if (!i2c_gpio_debug_dir)
-		i2c_gpio_debug_dir = debugfs_create_dir("i2c-fault-injector", NULL);
-
-	priv->debug_dir = debugfs_create_dir(pdev->name, i2c_gpio_debug_dir);
-
 	init_completion(&priv->scl_irq_completion);
 
-	debugfs_create_file_unsafe("incomplete_address_phase", 0200, priv->debug_dir,
+	debugfs_create_file_unsafe("incomplete_address_phase", 0200, priv->adap.debugfs,
 				   priv, &fops_incomplete_addr_phase);
-	debugfs_create_file_unsafe("incomplete_write_byte", 0200, priv->debug_dir,
+	debugfs_create_file_unsafe("incomplete_write_byte", 0200, priv->adap.debugfs,
 				   priv, &fops_incomplete_write_byte);
 	if (priv->bit_data.getscl) {
-		debugfs_create_file_unsafe("inject_panic", 0200, priv->debug_dir,
+		debugfs_create_file_unsafe("inject_panic", 0200, priv->adap.debugfs,
 					   priv, &fops_inject_panic);
-		debugfs_create_file_unsafe("lose_arbitration", 0200, priv->debug_dir,
+		debugfs_create_file_unsafe("lose_arbitration", 0200, priv->adap.debugfs,
 					   priv, &fops_lose_arbitration);
 	}
-	debugfs_create_file_unsafe("scl", 0600, priv->debug_dir, priv, &fops_scl);
-	debugfs_create_file_unsafe("sda", 0600, priv->debug_dir, priv, &fops_sda);
-}
-
-static void i2c_gpio_fault_injector_exit(struct platform_device *pdev)
-{
-	struct i2c_gpio_private_data *priv = platform_get_drvdata(pdev);
-
-	debugfs_remove_recursive(priv->debug_dir);
+	debugfs_create_file_unsafe("scl", 0600, priv->adap.debugfs, priv, &fops_scl);
+	debugfs_create_file_unsafe("sda", 0600, priv->adap.debugfs, priv, &fops_sda);
 }
 #else
 static inline void i2c_gpio_fault_injector_init(struct platform_device *pdev) {}
-static inline void i2c_gpio_fault_injector_exit(struct platform_device *pdev) {}
 #endif /* CONFIG_I2C_GPIO_FAULT_INJECTOR*/
 
 /* Get i2c-gpio properties from DT or ACPI table */
@@ -444,7 +424,7 @@ static int i2c_gpio_probe(struct platform_device *pdev)
 		snprintf(adap->name, sizeof(adap->name), "i2c-gpio%d", pdev->id);
 
 	adap->algo_data = bit_data;
-	adap->class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	adap->class = I2C_CLASS_HWMON;
 	adap->dev.parent = dev;
 	device_set_node(&adap->dev, fwnode);
 
@@ -475,8 +455,6 @@ static void i2c_gpio_remove(struct platform_device *pdev)
 	struct i2c_gpio_private_data *priv;
 	struct i2c_adapter *adap;
 
-	i2c_gpio_fault_injector_exit(pdev);
-
 	priv = platform_get_drvdata(pdev);
 	adap = &priv->adap;
 
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index 070999139c6d..274e987e4cfa 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -498,11 +498,10 @@ static int i801_block_transaction_by_block(struct i801_priv *priv,
 	/* Set block buffer mode */
 	outb_p(inb_p(SMBAUXCTL(priv)) | SMBAUXCTL_E32B, SMBAUXCTL(priv));
 
-	inb_p(SMBHSTCNT(priv)); /* reset the data buffer index */
-
 	if (read_write == I2C_SMBUS_WRITE) {
 		len = data->block[0];
 		outb_p(len, SMBHSTDAT0(priv));
+		inb_p(SMBHSTCNT(priv));	/* reset the data buffer index */
 		for (i = 0; i < len; i++)
 			outb_p(data->block[i+1], SMBBLKDAT(priv));
 	}
@@ -520,6 +519,7 @@ static int i801_block_transaction_by_block(struct i801_priv *priv,
 		}
 
 		data->block[0] = len;
+		inb_p(SMBHSTCNT(priv));	/* reset the data buffer index */
 		for (i = 0; i < len; i++)
 			data->block[i + 1] = inb_p(SMBBLKDAT(priv));
 	}
@@ -1230,8 +1230,10 @@ static const struct {
 	 * Additional individual entries were added after verification.
 	 */
 	{ "Latitude 5480",      0x29 },
+	{ "Precision 3540",     0x29 },
 	{ "Vostro V131",        0x1d },
 	{ "Vostro 5568",        0x29 },
+	{ "XPS 15 7590",        0x29 },
 };
 
 static void register_dell_lis3lv02d_i2c_device(struct i801_priv *priv)
@@ -1414,7 +1416,6 @@ static void i801_add_mux(struct i801_priv *priv)
 		lookup->table[i] = GPIO_LOOKUP(mux_config->gpio_chip,
 					       mux_config->gpios[i], "mux", 0);
 	gpiod_add_lookup_table(lookup);
-	priv->lookup = lookup;
 
 	/*
 	 * Register the mux device, we use PLATFORM_DEVID_NONE here
@@ -1428,7 +1429,10 @@ static void i801_add_mux(struct i801_priv *priv)
 				sizeof(struct i2c_mux_gpio_platform_data));
 	if (IS_ERR(priv->mux_pdev)) {
 		gpiod_remove_lookup_table(lookup);
+		devm_kfree(dev, lookup);
 		dev_err(dev, "Failed to register i2c-mux-gpio device\n");
+	} else {
+		priv->lookup = lookup;
 	}
 }
 
@@ -1740,9 +1744,9 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 
 	i801_enable_host_notify(&priv->adapter);
 
-	i801_probe_optional_slaves(priv);
 	/* We ignore errors - multiplexing is optional */
 	i801_add_mux(priv);
+	i801_probe_optional_slaves(priv);
 
 	pci_set_drvdata(dev, priv);
 
diff --git a/drivers/i2c/busses/i2c-ibm_iic.c b/drivers/i2c/busses/i2c-ibm_iic.c
index 408820319ec4..7fb87b78923e 100644
--- a/drivers/i2c/busses/i2c-ibm_iic.c
+++ b/drivers/i2c/busses/i2c-ibm_iic.c
@@ -739,7 +739,7 @@ static int iic_probe(struct platform_device *ofdev)
 	adap->dev.of_node = of_node_get(np);
 	strscpy(adap->name, "IBM IIC", sizeof(adap->name));
 	i2c_set_adapdata(adap, dev);
-	adap->class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	adap->class = I2C_CLASS_HWMON;
 	adap->algo = &iic_algo;
 	adap->timeout = HZ;
 
diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index 1775a79aeba2..60e813137f84 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -803,6 +803,11 @@ static irqreturn_t i2c_imx_slave_handle(struct imx_i2c_struct *i2c_imx,
 		ctl &= ~I2CR_MTX;
 		imx_i2c_write_reg(ctl, i2c_imx, IMX_I2C_I2CR);
 		imx_i2c_read_reg(i2c_imx, IMX_I2C_I2DR);
+
+		/* flag the last byte as processed */
+		i2c_imx_slave_event(i2c_imx,
+				    I2C_SLAVE_READ_PROCESSED, &value);
+
 		i2c_imx_slave_finish_op(i2c_imx);
 		return IRQ_HANDLED;
 	}
@@ -1401,7 +1406,7 @@ static int i2c_imx_init_recovery_info(struct imx_i2c_struct *i2c_imx,
 			PINCTRL_STATE_DEFAULT);
 	i2c_imx->pinctrl_pins_gpio = pinctrl_lookup_state(i2c_imx->pinctrl,
 			"gpio");
-	rinfo->sda_gpiod = devm_gpiod_get(&pdev->dev, "sda", GPIOD_IN);
+	rinfo->sda_gpiod = devm_gpiod_get_optional(&pdev->dev, "sda", GPIOD_IN);
 	rinfo->scl_gpiod = devm_gpiod_get(&pdev->dev, "scl", GPIOD_OUT_HIGH_OPEN_DRAIN);
 
 	if (PTR_ERR(rinfo->sda_gpiod) == -EPROBE_DEFER ||
diff --git a/drivers/i2c/busses/i2c-iop3xx.c b/drivers/i2c/busses/i2c-iop3xx.c
index f2f7ebeeaecb..2e5f0165c3d3 100644
--- a/drivers/i2c/busses/i2c-iop3xx.c
+++ b/drivers/i2c/busses/i2c-iop3xx.c
@@ -478,7 +478,7 @@ iop3xx_i2c_probe(struct platform_device *pdev)
 
 	memcpy(new_adapter->name, pdev->name, strlen(pdev->name));
 	new_adapter->owner = THIS_MODULE;
-	new_adapter->class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	new_adapter->class = I2C_CLASS_HWMON;
 	new_adapter->dev.parent = &pdev->dev;
 	new_adapter->dev.of_node = pdev->dev.of_node;
 	new_adapter->nr = pdev->id;
diff --git a/drivers/i2c/busses/i2c-isch.c b/drivers/i2c/busses/i2c-isch.c
index 1dc1ceaa4443..416a9968ed28 100644
--- a/drivers/i2c/busses/i2c-isch.c
+++ b/drivers/i2c/busses/i2c-isch.c
@@ -249,7 +249,7 @@ static const struct i2c_algorithm smbus_algorithm = {
 
 static struct i2c_adapter sch_adapter = {
 	.owner		= THIS_MODULE,
-	.class		= I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class		= I2C_CLASS_HWMON,
 	.algo		= &smbus_algorithm,
 };
 
diff --git a/drivers/i2c/busses/i2c-kempld.c b/drivers/i2c/busses/i2c-kempld.c
index e01d75308288..c3a529a73b5b 100644
--- a/drivers/i2c/busses/i2c-kempld.c
+++ b/drivers/i2c/busses/i2c-kempld.c
@@ -283,8 +283,7 @@ static const struct i2c_algorithm kempld_i2c_algorithm = {
 static const struct i2c_adapter kempld_i2c_adapter = {
 	.owner		= THIS_MODULE,
 	.name		= "i2c-kempld",
-	.class		= I2C_CLASS_HWMON | I2C_CLASS_SPD |
-			  I2C_CLASS_DEPRECATED,
+	.class		= I2C_CLASS_HWMON | I2C_CLASS_DEPRECATED,
 	.algo		= &kempld_i2c_algorithm,
 };
 
diff --git a/drivers/i2c/busses/i2c-mlxcpld.c b/drivers/i2c/busses/i2c-mlxcpld.c
index 6fec64ea67fb..099291a0411d 100644
--- a/drivers/i2c/busses/i2c-mlxcpld.c
+++ b/drivers/i2c/busses/i2c-mlxcpld.c
@@ -477,7 +477,7 @@ static const struct i2c_adapter_quirks mlxcpld_i2c_quirks_ext2 = {
 static struct i2c_adapter mlxcpld_i2c_adapter = {
 	.owner          = THIS_MODULE,
 	.name           = "i2c-mlxcpld",
-	.class          = I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class          = I2C_CLASS_HWMON,
 	.algo           = &mlxcpld_i2c_algo,
 	.quirks		= &mlxcpld_i2c_quirks,
 	.retries	= MLXCPLD_I2C_RETR_NUM,
diff --git a/drivers/i2c/busses/i2c-nforce2.c b/drivers/i2c/busses/i2c-nforce2.c
index 38d203d93eee..fab662e6bc08 100644
--- a/drivers/i2c/busses/i2c-nforce2.c
+++ b/drivers/i2c/busses/i2c-nforce2.c
@@ -349,7 +349,7 @@ static int nforce2_probe_smb(struct pci_dev *dev, int bar, int alt_reg,
 		return -EBUSY;
 	}
 	smbus->adapter.owner = THIS_MODULE;
-	smbus->adapter.class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	smbus->adapter.class = I2C_CLASS_HWMON;
 	smbus->adapter.algo = &smbus_algorithm;
 	smbus->adapter.algo_data = smbus;
 	smbus->adapter.dev.parent = &dev->dev;
diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c
index ae4bae63ad4f..54181b3f1919 100644
--- a/drivers/i2c/busses/i2c-npcm7xx.c
+++ b/drivers/i2c/busses/i2c-npcm7xx.c
@@ -326,7 +326,6 @@ struct npcm_i2c {
 	u8 slv_rd_buf[MAX_I2C_HW_FIFO_SIZE];
 	u8 slv_wr_buf[MAX_I2C_HW_FIFO_SIZE];
 #endif
-	struct dentry *debugfs; /* debugfs device directory */
 	u64 ber_cnt;
 	u64 rec_succ_cnt;
 	u64 rec_fail_cnt;
@@ -2250,27 +2249,15 @@ static const struct i2c_algorithm npcm_i2c_algo = {
 #endif
 };
 
-/* i2c debugfs directory: used to keep health monitor of i2c devices */
-static struct dentry *npcm_i2c_debugfs_dir;
-
 static void npcm_i2c_init_debugfs(struct platform_device *pdev,
 				  struct npcm_i2c *bus)
 {
-	struct dentry *d;
-
-	if (!npcm_i2c_debugfs_dir)
-		return;
-	d = debugfs_create_dir(dev_name(&pdev->dev), npcm_i2c_debugfs_dir);
-	if (IS_ERR_OR_NULL(d))
-		return;
-	debugfs_create_u64("ber_cnt", 0444, d, &bus->ber_cnt);
-	debugfs_create_u64("nack_cnt", 0444, d, &bus->nack_cnt);
-	debugfs_create_u64("rec_succ_cnt", 0444, d, &bus->rec_succ_cnt);
-	debugfs_create_u64("rec_fail_cnt", 0444, d, &bus->rec_fail_cnt);
-	debugfs_create_u64("timeout_cnt", 0444, d, &bus->timeout_cnt);
-	debugfs_create_u64("tx_complete_cnt", 0444, d, &bus->tx_complete_cnt);
-
-	bus->debugfs = d;
+	debugfs_create_u64("ber_cnt", 0444, bus->adap.debugfs, &bus->ber_cnt);
+	debugfs_create_u64("nack_cnt", 0444, bus->adap.debugfs, &bus->nack_cnt);
+	debugfs_create_u64("rec_succ_cnt", 0444, bus->adap.debugfs, &bus->rec_succ_cnt);
+	debugfs_create_u64("rec_fail_cnt", 0444, bus->adap.debugfs, &bus->rec_fail_cnt);
+	debugfs_create_u64("timeout_cnt", 0444, bus->adap.debugfs, &bus->timeout_cnt);
+	debugfs_create_u64("tx_complete_cnt", 0444, bus->adap.debugfs, &bus->tx_complete_cnt);
 }
 
 static int npcm_i2c_probe_bus(struct platform_device *pdev)
@@ -2362,7 +2349,6 @@ static void npcm_i2c_remove_bus(struct platform_device *pdev)
 	unsigned long lock_flags;
 	struct npcm_i2c *bus = platform_get_drvdata(pdev);
 
-	debugfs_remove_recursive(bus->debugfs);
 	spin_lock_irqsave(&bus->lock, lock_flags);
 	npcm_i2c_disable(bus);
 	spin_unlock_irqrestore(&bus->lock, lock_flags);
@@ -2385,28 +2371,7 @@ static struct platform_driver npcm_i2c_bus_driver = {
 	}
 };
 
-static int __init npcm_i2c_init(void)
-{
-	int ret;
-
-	npcm_i2c_debugfs_dir = debugfs_create_dir("npcm_i2c", NULL);
-
-	ret = platform_driver_register(&npcm_i2c_bus_driver);
-	if (ret) {
-		debugfs_remove_recursive(npcm_i2c_debugfs_dir);
-		return ret;
-	}
-
-	return 0;
-}
-module_init(npcm_i2c_init);
-
-static void __exit npcm_i2c_exit(void)
-{
-	platform_driver_unregister(&npcm_i2c_bus_driver);
-	debugfs_remove_recursive(npcm_i2c_debugfs_dir);
-}
-module_exit(npcm_i2c_exit);
+module_platform_driver(npcm_i2c_bus_driver);
 
 MODULE_AUTHOR("Avi Fishman <avi.fishman@gmail.com>");
 MODULE_AUTHOR("Tali Perry <tali.perry@nuvoton.com>");
diff --git a/drivers/i2c/busses/i2c-pasemi-core.c b/drivers/i2c/busses/i2c-pasemi-core.c
index 7d54a9f34c74..bd8becbdeeb2 100644
--- a/drivers/i2c/busses/i2c-pasemi-core.c
+++ b/drivers/i2c/busses/i2c-pasemi-core.c
@@ -369,6 +369,7 @@ int pasemi_i2c_common_probe(struct pasemi_smbus *smbus)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pasemi_i2c_common_probe);
 
 irqreturn_t pasemi_irq_handler(int irq, void *dev_id)
 {
@@ -378,3 +379,8 @@ irqreturn_t pasemi_irq_handler(int irq, void *dev_id)
 	complete(&smbus->irq_completion);
 	return IRQ_HANDLED;
 }
+EXPORT_SYMBOL_GPL(pasemi_irq_handler);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Olof Johansson <olof@lixom.net>");
+MODULE_DESCRIPTION("PA Semi PWRficient SMBus driver");
diff --git a/drivers/i2c/busses/i2c-pasemi-pci.c b/drivers/i2c/busses/i2c-pasemi-pci.c
index cfc89e04eb94..77f90c7436ed 100644
--- a/drivers/i2c/busses/i2c-pasemi-pci.c
+++ b/drivers/i2c/busses/i2c-pasemi-pci.c
@@ -56,7 +56,7 @@ static int pasemi_smb_pci_probe(struct pci_dev *dev,
 	if (!smbus->ioaddr)
 		return -EBUSY;
 
-	smbus->adapter.class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	smbus->adapter.class = I2C_CLASS_HWMON;
 	error = pasemi_i2c_common_probe(smbus);
 	if (error)
 		return error;
diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c
index 809fbd014cd6..6a0392172b2f 100644
--- a/drivers/i2c/busses/i2c-piix4.c
+++ b/drivers/i2c/busses/i2c-piix4.c
@@ -943,7 +943,7 @@ static int piix4_add_adapter(struct pci_dev *dev, unsigned short smba,
 	}
 
 	adap->owner = THIS_MODULE;
-	adap->class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	adap->class = I2C_CLASS_HWMON;
 	adap->algo = sb800_main ? &piix4_smbus_algorithm_sb800
 				: &smbus_algorithm;
 
diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c
index 0d2e7171e3a6..da94df466e83 100644
--- a/drivers/i2c/busses/i2c-qcom-geni.c
+++ b/drivers/i2c/busses/i2c-qcom-geni.c
@@ -613,20 +613,20 @@ static int geni_i2c_gpi_xfer(struct geni_i2c_dev *gi2c, struct i2c_msg msgs[], i
 
 		peripheral.addr = msgs[i].addr;
 
+		ret =  geni_i2c_gpi(gi2c, &msgs[i], &config,
+				    &tx_addr, &tx_buf, I2C_WRITE, gi2c->tx_c);
+		if (ret)
+			goto err;
+
 		if (msgs[i].flags & I2C_M_RD) {
 			ret =  geni_i2c_gpi(gi2c, &msgs[i], &config,
 					    &rx_addr, &rx_buf, I2C_READ, gi2c->rx_c);
 			if (ret)
 				goto err;
-		}
-
-		ret =  geni_i2c_gpi(gi2c, &msgs[i], &config,
-				    &tx_addr, &tx_buf, I2C_WRITE, gi2c->tx_c);
-		if (ret)
-			goto err;
 
-		if (msgs[i].flags & I2C_M_RD)
 			dma_async_issue_pending(gi2c->rx_c);
+		}
+
 		dma_async_issue_pending(gi2c->tx_c);
 
 		timeout = wait_for_completion_timeout(&gi2c->done, XFER_TIMEOUT);
diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c
index 829ac053bbb7..828aa2ea0fe4 100644
--- a/drivers/i2c/busses/i2c-rcar.c
+++ b/drivers/i2c/busses/i2c-rcar.c
@@ -89,6 +89,7 @@
 #define TMDMAE	BIT(0)	/* DMA Master Transmitted Enable */
 
 /* ICCCR2 */
+#define FMPE	BIT(7)	/* Fast Mode Plus Enable */
 #define CDFD	BIT(2)	/* CDF Disable */
 #define HLSE	BIT(1)	/* HIGH/LOW Separate Control Enable */
 #define SME	BIT(0)	/* SCL Mask Enable */
@@ -122,16 +123,18 @@
 #define ID_NACK			BIT(4)
 #define ID_EPROTO		BIT(5)
 /* persistent flags */
+#define ID_P_FMPLUS		BIT(27)
 #define ID_P_NOT_ATOMIC		BIT(28)
 #define ID_P_HOST_NOTIFY	BIT(29)
 #define ID_P_NO_RXDMA		BIT(30) /* HW forbids RXDMA sometimes */
 #define ID_P_PM_BLOCKED		BIT(31)
-#define ID_P_MASK		GENMASK(31, 28)
+#define ID_P_MASK		GENMASK(31, 27)
 
 enum rcar_i2c_type {
 	I2C_RCAR_GEN1,
 	I2C_RCAR_GEN2,
 	I2C_RCAR_GEN3,
+	I2C_RCAR_GEN4,
 };
 
 struct rcar_i2c_priv {
@@ -148,6 +151,7 @@ struct rcar_i2c_priv {
 	u32 icccr;
 	u16 schd;
 	u16 scld;
+	u8 smd;
 	u8 recovery_icmcr;	/* protected by adapter lock */
 	enum rcar_i2c_type devtype;
 	struct i2c_client *slave;
@@ -239,9 +243,14 @@ static void rcar_i2c_init(struct rcar_i2c_priv *priv)
 	if (priv->devtype < I2C_RCAR_GEN3) {
 		rcar_i2c_write(priv, ICCCR, priv->icccr);
 	} else {
-		rcar_i2c_write(priv, ICCCR2, CDFD | HLSE | SME);
+		u32 icccr2 = CDFD | HLSE | SME;
+
+		if (priv->flags & ID_P_FMPLUS)
+			icccr2 |= FMPE;
+
+		rcar_i2c_write(priv, ICCCR2, icccr2);
 		rcar_i2c_write(priv, ICCCR, priv->icccr);
-		rcar_i2c_write(priv, ICMPR, RCAR_DEFAULT_SMD);
+		rcar_i2c_write(priv, ICMPR, priv->smd);
 		rcar_i2c_write(priv, ICHPR, priv->schd);
 		rcar_i2c_write(priv, ICLPR, priv->scld);
 		rcar_i2c_write(priv, ICFBSCR, TCYC17);
@@ -278,6 +287,7 @@ static int rcar_i2c_clock_calculate(struct rcar_i2c_priv *priv)
 
 	/* Fall back to previously used values if not supplied */
 	i2c_parse_fw_timings(dev, &t, false);
+	priv->smd = RCAR_DEFAULT_SMD;
 
 	/*
 	 * calculate SCL clock
@@ -303,6 +313,11 @@ static int rcar_i2c_clock_calculate(struct rcar_i2c_priv *priv)
 	if (cdf >= 1U << cdf_width)
 		goto err_no_val;
 
+	if (t.bus_freq_hz > I2C_MAX_FAST_MODE_FREQ && priv->devtype >= I2C_RCAR_GEN4)
+		priv->flags |= ID_P_FMPLUS;
+	else
+		priv->flags &= ~ID_P_FMPLUS;
+
 	/* On Gen3+, we use cdf only for the filters, not as a SCL divider */
 	ick = rate / (priv->devtype < I2C_RCAR_GEN3 ? (cdf + 1) : 1);
 
@@ -344,30 +359,30 @@ static int rcar_i2c_clock_calculate(struct rcar_i2c_priv *priv)
 		 * x as a base value for the SCLD/SCHD ratio:
 		 *
 		 * SCL = clkp / (8 + 2 * SMD + SCLD + SCHD + F[(ticf + tr + intd) * clkp])
-		 * SCL = clkp / (8 + 2 * RCAR_DEFAULT_SMD + RCAR_SCLD_RATIO * x
+		 * SCL = clkp / (8 + 2 * SMD + RCAR_SCLD_RATIO * x
 		 *		 + RCAR_SCHD_RATIO * x + F[...])
 		 *
 		 * with: sum_ratio = RCAR_SCLD_RATIO + RCAR_SCHD_RATIO
-		 * and:  smd = RCAR_DEFAULT_SMD
 		 *
 		 * SCL = clkp / (8 + 2 * smd + sum_ratio * x + F[...])
 		 * 8 + 2 * smd + sum_ratio * x + F[...] = clkp / SCL
 		 * x = ((clkp / SCL) - 8 - 2 * smd - F[...]) / sum_ratio
 		 */
 		x = DIV_ROUND_UP(rate, t.bus_freq_hz ?: 1);
-		x = DIV_ROUND_UP(x - 8 - 2 * RCAR_DEFAULT_SMD - round, sum_ratio);
-		scl = rate / (8 + 2 * RCAR_DEFAULT_SMD + sum_ratio * x + round);
+		x = DIV_ROUND_UP(x - 8 - 2 * priv->smd - round, sum_ratio);
+		scl = rate / (8 + 2 * priv->smd + sum_ratio * x + round);
 
-		/* Bail out if values don't fit into 16 bit or SMD became too large */
-		if (x * RCAR_SCLD_RATIO > 0xffff || RCAR_DEFAULT_SMD > x * RCAR_SCHD_RATIO)
+		if (x == 0 || x * RCAR_SCLD_RATIO > 0xffff)
 			goto err_no_val;
 
 		priv->icccr = cdf;
 		priv->schd = RCAR_SCHD_RATIO * x;
 		priv->scld = RCAR_SCLD_RATIO * x;
+		if (priv->smd >= priv->schd)
+			priv->smd = priv->schd - 1;
 
-		dev_dbg(dev, "clk %u/%u(%lu), round %u, CDF: %u SCHD %u SCLD %u\n",
-			scl, t.bus_freq_hz, rate, round, cdf, priv->schd, priv->scld);
+		dev_dbg(dev, "clk %u/%u(%lu), round %u, CDF: %u SCHD %u SCLD %u SMD %u\n",
+			scl, t.bus_freq_hz, rate, round, cdf, priv->schd, priv->scld, priv->smd);
 	}
 
 	return 0;
@@ -431,8 +446,8 @@ static void rcar_i2c_cleanup_dma(struct rcar_i2c_priv *priv, bool terminate)
 	dma_unmap_single(chan->device->dev, sg_dma_address(&priv->sg),
 			 sg_dma_len(&priv->sg), priv->dma_direction);
 
-	/* Gen3 can only do one RXDMA per transfer and we just completed it */
-	if (priv->devtype == I2C_RCAR_GEN3 &&
+	/* Gen3+ can only do one RXDMA per transfer and we just completed it */
+	if (priv->devtype >= I2C_RCAR_GEN3 &&
 	    priv->dma_direction == DMA_FROM_DEVICE)
 		priv->flags |= ID_P_NO_RXDMA;
 
@@ -886,8 +901,8 @@ static int rcar_i2c_master_xfer(struct i2c_adapter *adap,
 	if (ret < 0)
 		goto out;
 
-	/* Gen3 needs a reset before allowing RXDMA once */
-	if (priv->devtype == I2C_RCAR_GEN3) {
+	/* Gen3+ needs a reset. That also allows RXDMA once */
+	if (priv->devtype >= I2C_RCAR_GEN3) {
 		priv->flags &= ~ID_P_NO_RXDMA;
 		ret = rcar_i2c_do_reset(priv);
 		if (ret)
@@ -1072,10 +1087,12 @@ static const struct of_device_id rcar_i2c_dt_ids[] = {
 	{ .compatible = "renesas,i2c-r8a7794", .data = (void *)I2C_RCAR_GEN2 },
 	{ .compatible = "renesas,i2c-r8a7795", .data = (void *)I2C_RCAR_GEN3 },
 	{ .compatible = "renesas,i2c-r8a7796", .data = (void *)I2C_RCAR_GEN3 },
+	/* S4 has no FM+ bit */
+	{ .compatible = "renesas,i2c-r8a779f0", .data = (void *)I2C_RCAR_GEN3 },
 	{ .compatible = "renesas,rcar-gen1-i2c", .data = (void *)I2C_RCAR_GEN1 },
 	{ .compatible = "renesas,rcar-gen2-i2c", .data = (void *)I2C_RCAR_GEN2 },
 	{ .compatible = "renesas,rcar-gen3-i2c", .data = (void *)I2C_RCAR_GEN3 },
-	{ .compatible = "renesas,rcar-gen4-i2c", .data = (void *)I2C_RCAR_GEN3 },
+	{ .compatible = "renesas,rcar-gen4-i2c", .data = (void *)I2C_RCAR_GEN4 },
 	{},
 };
 MODULE_DEVICE_TABLE(of, rcar_i2c_dt_ids);
@@ -1151,7 +1168,7 @@ static int rcar_i2c_probe(struct platform_device *pdev)
 	if (of_property_read_bool(dev->of_node, "smbus"))
 		priv->flags |= ID_P_HOST_NOTIFY;
 
-	if (priv->devtype == I2C_RCAR_GEN3) {
+	if (priv->devtype >= I2C_RCAR_GEN3) {
 		priv->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL);
 		if (IS_ERR(priv->rstc)) {
 			ret = PTR_ERR(priv->rstc);
diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c
index 4362db7c5789..086fdf262e7b 100644
--- a/drivers/i2c/busses/i2c-rk3x.c
+++ b/drivers/i2c/busses/i2c-rk3x.c
@@ -1295,8 +1295,12 @@ static int rk3x_i2c_probe(struct platform_device *pdev)
 			return -EINVAL;
 		}
 
-		/* 27+i: write mask, 11+i: value */
-		value = BIT(27 + bus_nr) | BIT(11 + bus_nr);
+		/* rv1126 i2c2 uses non-sequential write mask 20, value 4 */
+		if (i2c->soc_data == &rv1126_soc_data && bus_nr == 2)
+			value = BIT(20) | BIT(4);
+		else
+			/* 27+i: write mask, 11+i: value */
+			value = BIT(27 + bus_nr) | BIT(11 + bus_nr);
 
 		ret = regmap_write(grf, i2c->soc_data->grf_offset, value);
 		if (ret != 0) {
diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c
index c56886af724e..275f7c42165c 100644
--- a/drivers/i2c/busses/i2c-s3c2410.c
+++ b/drivers/i2c/busses/i2c-s3c2410.c
@@ -76,6 +76,7 @@
 #define QUIRK_HDMIPHY		(1 << 1)
 #define QUIRK_NO_GPIO		(1 << 2)
 #define QUIRK_POLL		(1 << 3)
+#define QUIRK_ATOMIC		(1 << 4)
 
 /* Max time to wait for bus to become idle after a xfer (in us) */
 #define S3C2410_IDLE_TIMEOUT	5000
@@ -174,7 +175,7 @@ static inline void s3c24xx_i2c_master_complete(struct s3c24xx_i2c *i2c, int ret)
 	if (ret)
 		i2c->msg_idx = ret;
 
-	if (!(i2c->quirks & QUIRK_POLL))
+	if (!(i2c->quirks & (QUIRK_POLL | QUIRK_ATOMIC)))
 		wake_up(&i2c->wait);
 }
 
@@ -216,8 +217,17 @@ static bool is_ack(struct s3c24xx_i2c *i2c)
 	int tries;
 
 	for (tries = 50; tries; --tries) {
-		if (readl(i2c->regs + S3C2410_IICCON)
-			& S3C2410_IICCON_IRQPEND) {
+		unsigned long tmp = readl(i2c->regs + S3C2410_IICCON);
+
+		if (!(tmp & S3C2410_IICCON_ACKEN)) {
+			/*
+			 * Wait a bit for the bus to stabilize,
+			 * delay estimated experimentally.
+			 */
+			usleep_range(100, 200);
+			return true;
+		}
+		if (tmp & S3C2410_IICCON_IRQPEND) {
 			if (!(readl(i2c->regs + S3C2410_IICSTAT)
 				& S3C2410_IICSTAT_LASTBIT))
 				return true;
@@ -270,16 +280,6 @@ static void s3c24xx_i2c_message_start(struct s3c24xx_i2c *i2c,
 
 	stat |= S3C2410_IICSTAT_START;
 	writel(stat, i2c->regs + S3C2410_IICSTAT);
-
-	if (i2c->quirks & QUIRK_POLL) {
-		while ((i2c->msg_num != 0) && is_ack(i2c)) {
-			i2c_s3c_irq_nextbyte(i2c, stat);
-			stat = readl(i2c->regs + S3C2410_IICSTAT);
-
-			if (stat & S3C2410_IICSTAT_ARBITR)
-				dev_err(i2c->dev, "deal with arbitration loss\n");
-		}
-	}
 }
 
 static inline void s3c24xx_i2c_stop(struct s3c24xx_i2c *i2c, int ret)
@@ -685,7 +685,7 @@ static void s3c24xx_i2c_wait_idle(struct s3c24xx_i2c *i2c)
 static int s3c24xx_i2c_doxfer(struct s3c24xx_i2c *i2c,
 			      struct i2c_msg *msgs, int num)
 {
-	unsigned long timeout;
+	unsigned long timeout = 0;
 	int ret;
 
 	ret = s3c24xx_i2c_set_master(i2c);
@@ -704,17 +704,20 @@ static int s3c24xx_i2c_doxfer(struct s3c24xx_i2c *i2c,
 	s3c24xx_i2c_enable_irq(i2c);
 	s3c24xx_i2c_message_start(i2c, msgs);
 
-	if (i2c->quirks & QUIRK_POLL) {
-		ret = i2c->msg_idx;
+	if (i2c->quirks & (QUIRK_POLL | QUIRK_ATOMIC)) {
+		while ((i2c->msg_num != 0) && is_ack(i2c)) {
+			unsigned long stat = readl(i2c->regs + S3C2410_IICSTAT);
 
-		if (ret != num)
-			dev_dbg(i2c->dev, "incomplete xfer (%d)\n", ret);
+			i2c_s3c_irq_nextbyte(i2c, stat);
 
-		goto out;
+			stat = readl(i2c->regs + S3C2410_IICSTAT);
+			if (stat & S3C2410_IICSTAT_ARBITR)
+				dev_err(i2c->dev, "deal with arbitration loss\n");
+		}
+	} else {
+		timeout = wait_event_timeout(i2c->wait, i2c->msg_num == 0, HZ * 5);
 	}
 
-	timeout = wait_event_timeout(i2c->wait, i2c->msg_num == 0, HZ * 5);
-
 	ret = i2c->msg_idx;
 
 	/*
@@ -773,6 +776,21 @@ static int s3c24xx_i2c_xfer(struct i2c_adapter *adap,
 	return -EREMOTEIO;
 }
 
+static int s3c24xx_i2c_xfer_atomic(struct i2c_adapter *adap,
+				   struct i2c_msg *msgs, int num)
+{
+	struct s3c24xx_i2c *i2c = (struct s3c24xx_i2c *)adap->algo_data;
+	int ret;
+
+	disable_irq(i2c->irq);
+	i2c->quirks |= QUIRK_ATOMIC;
+	ret = s3c24xx_i2c_xfer(adap, msgs, num);
+	i2c->quirks &= ~QUIRK_ATOMIC;
+	enable_irq(i2c->irq);
+
+	return ret;
+}
+
 /* declare our i2c functionality */
 static u32 s3c24xx_i2c_func(struct i2c_adapter *adap)
 {
@@ -783,6 +801,7 @@ static u32 s3c24xx_i2c_func(struct i2c_adapter *adap)
 /* i2c bus registration info */
 static const struct i2c_algorithm s3c24xx_i2c_algorithm = {
 	.master_xfer		= s3c24xx_i2c_xfer,
+	.master_xfer_atomic     = s3c24xx_i2c_xfer_atomic,
 	.functionality		= s3c24xx_i2c_func,
 };
 
diff --git a/drivers/i2c/busses/i2c-scmi.c b/drivers/i2c/busses/i2c-scmi.c
index 421735acfa14..d7af8e0d7599 100644
--- a/drivers/i2c/busses/i2c-scmi.c
+++ b/drivers/i2c/busses/i2c-scmi.c
@@ -385,7 +385,7 @@ static int smbus_cmi_probe(struct platform_device *device)
 	smbus_cmi->adapter.owner = THIS_MODULE;
 	smbus_cmi->adapter.algo = &acpi_smbus_cmi_algorithm;
 	smbus_cmi->adapter.algo_data = smbus_cmi;
-	smbus_cmi->adapter.class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	smbus_cmi->adapter.class = I2C_CLASS_HWMON;
 	smbus_cmi->adapter.dev.parent = &device->dev;
 
 	ret = i2c_add_adapter(&smbus_cmi->adapter);
diff --git a/drivers/i2c/busses/i2c-sh7760.c b/drivers/i2c/busses/i2c-sh7760.c
index 1ad2a26156d1..8a043f5fca1e 100644
--- a/drivers/i2c/busses/i2c-sh7760.c
+++ b/drivers/i2c/busses/i2c-sh7760.c
@@ -477,7 +477,7 @@ static int sh7760_i2c_probe(struct platform_device *pdev)
 
 	id->adap.nr = pdev->id;
 	id->adap.algo = &sh7760_i2c_algo;
-	id->adap.class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	id->adap.class = I2C_CLASS_HWMON;
 	id->adap.retries = 3;
 	id->adap.algo_data = id;
 	id->adap.dev.parent = &pdev->dev;
diff --git a/drivers/i2c/busses/i2c-sibyte.c b/drivers/i2c/busses/i2c-sibyte.c
index 8f71f01cb169..49f8f4f1b0f0 100644
--- a/drivers/i2c/busses/i2c-sibyte.c
+++ b/drivers/i2c/busses/i2c-sibyte.c
@@ -142,7 +142,7 @@ static struct i2c_algo_sibyte_data sibyte_board_data[2] = {
 static struct i2c_adapter sibyte_board_adapter[2] = {
 	{
 		.owner		= THIS_MODULE,
-		.class		= I2C_CLASS_HWMON | I2C_CLASS_SPD,
+		.class		= I2C_CLASS_HWMON,
 		.algo		= NULL,
 		.algo_data	= &sibyte_board_data[0],
 		.nr		= 0,
@@ -150,7 +150,7 @@ static struct i2c_adapter sibyte_board_adapter[2] = {
 	},
 	{
 		.owner		= THIS_MODULE,
-		.class		= I2C_CLASS_HWMON | I2C_CLASS_SPD,
+		.class		= I2C_CLASS_HWMON,
 		.algo		= NULL,
 		.algo_data	= &sibyte_board_data[1],
 		.nr		= 1,
diff --git a/drivers/i2c/busses/i2c-sis5595.c b/drivers/i2c/busses/i2c-sis5595.c
index 486f1e9dfb74..32476dc10ad6 100644
--- a/drivers/i2c/busses/i2c-sis5595.c
+++ b/drivers/i2c/busses/i2c-sis5595.c
@@ -353,7 +353,7 @@ static const struct i2c_algorithm smbus_algorithm = {
 
 static struct i2c_adapter sis5595_adapter = {
 	.owner		= THIS_MODULE,
-	.class          = I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class          = I2C_CLASS_HWMON,
 	.algo		= &smbus_algorithm,
 };
 
diff --git a/drivers/i2c/busses/i2c-sis630.c b/drivers/i2c/busses/i2c-sis630.c
index 87d56250d78a..3505cf29cedd 100644
--- a/drivers/i2c/busses/i2c-sis630.c
+++ b/drivers/i2c/busses/i2c-sis630.c
@@ -493,7 +493,7 @@ static const struct i2c_algorithm smbus_algorithm = {
 
 static struct i2c_adapter sis630_adapter = {
 	.owner		= THIS_MODULE,
-	.class		= I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class		= I2C_CLASS_HWMON,
 	.algo		= &smbus_algorithm,
 	.retries	= 3
 };
diff --git a/drivers/i2c/busses/i2c-sis96x.c b/drivers/i2c/busses/i2c-sis96x.c
index cde8003985a5..77529dda6fcd 100644
--- a/drivers/i2c/busses/i2c-sis96x.c
+++ b/drivers/i2c/busses/i2c-sis96x.c
@@ -228,7 +228,7 @@ static const struct i2c_algorithm smbus_algorithm = {
 
 static struct i2c_adapter sis96x_adapter = {
 	.owner		= THIS_MODULE,
-	.class		= I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class		= I2C_CLASS_HWMON,
 	.algo		= &smbus_algorithm,
 };
 
diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c
index 983509936727..01210452216b 100644
--- a/drivers/i2c/busses/i2c-stm32f7.c
+++ b/drivers/i2c/busses/i2c-stm32f7.c
@@ -50,6 +50,7 @@
 #define STM32F7_I2C_TXDR			0x28
 
 /* STM32F7 I2C control 1 */
+#define STM32_I2C_CR1_FMP			BIT(24)
 #define STM32F7_I2C_CR1_PECEN			BIT(23)
 #define STM32F7_I2C_CR1_ALERTEN			BIT(22)
 #define STM32F7_I2C_CR1_SMBHEN			BIT(20)
@@ -226,6 +227,8 @@ struct stm32f7_i2c_spec {
  * @rise_time: Rise time (ns)
  * @fall_time: Fall time (ns)
  * @fmp_clr_offset: Fast Mode Plus clear register offset from set register
+ * @single_it_line: Only a single IT line is used for both events/errors
+ * @fmp_cr1_bit: Fast Mode Plus control is done via a bit in CR1
  */
 struct stm32f7_i2c_setup {
 	u32 speed_freq;
@@ -233,6 +236,8 @@ struct stm32f7_i2c_setup {
 	u32 rise_time;
 	u32 fall_time;
 	u32 fmp_clr_offset;
+	bool single_it_line;
+	bool fmp_cr1_bit;
 };
 
 /**
@@ -418,6 +423,13 @@ static const struct stm32f7_i2c_setup stm32mp13_setup = {
 	.fmp_clr_offset = 0x4,
 };
 
+static const struct stm32f7_i2c_setup stm32mp25_setup = {
+	.rise_time = STM32F7_I2C_RISE_TIME_DEFAULT,
+	.fall_time = STM32F7_I2C_FALL_TIME_DEFAULT,
+	.single_it_line = true,
+	.fmp_cr1_bit = true,
+};
+
 static inline void stm32f7_i2c_set_bits(void __iomem *reg, u32 mask)
 {
 	writel_relaxed(readl_relaxed(reg) | mask, reg);
@@ -1419,15 +1431,13 @@ static bool stm32f7_i2c_is_slave_busy(struct stm32f7_i2c_dev *i2c_dev)
 	return i == busy;
 }
 
-static irqreturn_t stm32f7_i2c_slave_isr_event(struct stm32f7_i2c_dev *i2c_dev)
+static irqreturn_t stm32f7_i2c_slave_isr_event(struct stm32f7_i2c_dev *i2c_dev, u32 status)
 {
 	void __iomem *base = i2c_dev->base;
-	u32 cr2, status, mask;
+	u32 cr2, mask;
 	u8 val;
 	int ret;
 
-	status = readl_relaxed(i2c_dev->base + STM32F7_I2C_ISR);
-
 	/* Slave transmitter mode */
 	if (status & STM32F7_I2C_ISR_TXIS) {
 		i2c_slave_event(i2c_dev->slave_running,
@@ -1494,23 +1504,81 @@ static irqreturn_t stm32f7_i2c_slave_isr_event(struct stm32f7_i2c_dev *i2c_dev)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data)
+static irqreturn_t stm32f7_i2c_handle_isr_errs(struct stm32f7_i2c_dev *i2c_dev, u32 status)
 {
-	struct stm32f7_i2c_dev *i2c_dev = data;
 	struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg;
-	struct stm32_i2c_dma *dma = i2c_dev->dma;
+	u16 addr = f7_msg->addr;
 	void __iomem *base = i2c_dev->base;
-	u32 status, mask;
-	int ret = IRQ_HANDLED;
+	struct device *dev = i2c_dev->dev;
+	struct stm32_i2c_dma *dma = i2c_dev->dma;
 
-	/* Check if the interrupt if for a slave device */
-	if (!i2c_dev->master_mode) {
-		ret = stm32f7_i2c_slave_isr_event(i2c_dev);
-		return ret;
+	/* Bus error */
+	if (status & STM32F7_I2C_ISR_BERR) {
+		dev_err(dev, "Bus error accessing addr 0x%x\n", addr);
+		writel_relaxed(STM32F7_I2C_ICR_BERRCF, base + STM32F7_I2C_ICR);
+		stm32f7_i2c_release_bus(&i2c_dev->adap);
+		f7_msg->result = -EIO;
+	}
+
+	/* Arbitration loss */
+	if (status & STM32F7_I2C_ISR_ARLO) {
+		dev_dbg(dev, "Arbitration loss accessing addr 0x%x\n", addr);
+		writel_relaxed(STM32F7_I2C_ICR_ARLOCF, base + STM32F7_I2C_ICR);
+		f7_msg->result = -EAGAIN;
+	}
+
+	if (status & STM32F7_I2C_ISR_PECERR) {
+		dev_err(dev, "PEC error in reception accessing addr 0x%x\n", addr);
+		writel_relaxed(STM32F7_I2C_ICR_PECCF, base + STM32F7_I2C_ICR);
+		f7_msg->result = -EINVAL;
 	}
 
+	if (status & STM32F7_I2C_ISR_ALERT) {
+		dev_dbg(dev, "SMBus alert received\n");
+		writel_relaxed(STM32F7_I2C_ICR_ALERTCF, base + STM32F7_I2C_ICR);
+		i2c_handle_smbus_alert(i2c_dev->alert->ara);
+		return IRQ_HANDLED;
+	}
+
+	if (!i2c_dev->slave_running) {
+		u32 mask;
+		/* Disable interrupts */
+		if (stm32f7_i2c_is_slave_registered(i2c_dev))
+			mask = STM32F7_I2C_XFER_IRQ_MASK;
+		else
+			mask = STM32F7_I2C_ALL_IRQ_MASK;
+		stm32f7_i2c_disable_irq(i2c_dev, mask);
+	}
+
+	/* Disable dma */
+	if (i2c_dev->use_dma) {
+		stm32f7_i2c_disable_dma_req(i2c_dev);
+		dmaengine_terminate_async(dma->chan_using);
+	}
+
+	i2c_dev->master_mode = false;
+	complete(&i2c_dev->complete);
+
+	return IRQ_HANDLED;
+}
+
+#define STM32F7_ERR_EVENTS (STM32F7_I2C_ISR_BERR | STM32F7_I2C_ISR_ARLO |\
+			    STM32F7_I2C_ISR_PECERR | STM32F7_I2C_ISR_ALERT)
+static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data)
+{
+	struct stm32f7_i2c_dev *i2c_dev = data;
+	u32 status;
+
 	status = readl_relaxed(i2c_dev->base + STM32F7_I2C_ISR);
 
+	/*
+	 * Check if the interrupt is for a slave device or related
+	 * to errors flags (in case of single it line mode)
+	 */
+	if (!i2c_dev->master_mode ||
+	    (i2c_dev->setup.single_it_line && (status & STM32F7_ERR_EVENTS)))
+		return IRQ_WAKE_THREAD;
+
 	/* Tx empty */
 	if (status & STM32F7_I2C_ISR_TXIS)
 		stm32f7_i2c_write_tx_data(i2c_dev);
@@ -1519,6 +1587,33 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data)
 	if (status & STM32F7_I2C_ISR_RXNE)
 		stm32f7_i2c_read_rx_data(i2c_dev);
 
+	/* Wake up the thread if other flags are raised */
+	if (status &
+	    (STM32F7_I2C_ISR_NACKF | STM32F7_I2C_ISR_STOPF |
+	     STM32F7_I2C_ISR_TC | STM32F7_I2C_ISR_TCR))
+		return IRQ_WAKE_THREAD;
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data)
+{
+	struct stm32f7_i2c_dev *i2c_dev = data;
+	struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg;
+	struct stm32_i2c_dma *dma = i2c_dev->dma;
+	void __iomem *base = i2c_dev->base;
+	u32 status, mask;
+	int ret;
+
+	status = readl_relaxed(i2c_dev->base + STM32F7_I2C_ISR);
+
+	if (!i2c_dev->master_mode)
+		return stm32f7_i2c_slave_isr_event(i2c_dev, status);
+
+	/* Handle errors in case of this handler is used for events/errors */
+	if (i2c_dev->setup.single_it_line && (status & STM32F7_ERR_EVENTS))
+		return stm32f7_i2c_handle_isr_errs(i2c_dev, status);
+
 	/* NACK received */
 	if (status & STM32F7_I2C_ISR_NACKF) {
 		dev_dbg(i2c_dev->dev, "<%s>: Receive NACK (addr %x)\n",
@@ -1531,33 +1626,28 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data)
 		f7_msg->result = -ENXIO;
 	}
 
-	/* STOP detection flag */
-	if (status & STM32F7_I2C_ISR_STOPF) {
-		/* Disable interrupts */
-		if (stm32f7_i2c_is_slave_registered(i2c_dev))
-			mask = STM32F7_I2C_XFER_IRQ_MASK;
+	if (status & STM32F7_I2C_ISR_TCR) {
+		if (f7_msg->smbus)
+			stm32f7_i2c_smbus_reload(i2c_dev);
 		else
-			mask = STM32F7_I2C_ALL_IRQ_MASK;
-		stm32f7_i2c_disable_irq(i2c_dev, mask);
-
-		/* Clear STOP flag */
-		writel_relaxed(STM32F7_I2C_ICR_STOPCF, base + STM32F7_I2C_ICR);
-
-		if (i2c_dev->use_dma && !f7_msg->result) {
-			ret = IRQ_WAKE_THREAD;
-		} else {
-			i2c_dev->master_mode = false;
-			complete(&i2c_dev->complete);
-		}
+			stm32f7_i2c_reload(i2c_dev);
 	}
 
 	/* Transfer complete */
 	if (status & STM32F7_I2C_ISR_TC) {
+		/* Wait for dma transfer completion before sending next message */
+		if (i2c_dev->use_dma && !f7_msg->result) {
+			ret = wait_for_completion_timeout(&i2c_dev->dma->dma_complete, HZ);
+			if (!ret) {
+				dev_dbg(i2c_dev->dev, "<%s>: Timed out\n", __func__);
+				stm32f7_i2c_disable_dma_req(i2c_dev);
+				dmaengine_terminate_async(dma->chan_using);
+				f7_msg->result = -ETIMEDOUT;
+			}
+		}
 		if (f7_msg->stop) {
 			mask = STM32F7_I2C_CR2_STOP;
 			stm32f7_i2c_set_bits(base + STM32F7_I2C_CR2, mask);
-		} else if (i2c_dev->use_dma && !f7_msg->result) {
-			ret = IRQ_WAKE_THREAD;
 		} else if (f7_msg->smbus) {
 			stm32f7_i2c_smbus_rep_start(i2c_dev);
 		} else {
@@ -1567,47 +1657,18 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data)
 		}
 	}
 
-	if (status & STM32F7_I2C_ISR_TCR) {
-		if (f7_msg->smbus)
-			stm32f7_i2c_smbus_reload(i2c_dev);
+	/* STOP detection flag */
+	if (status & STM32F7_I2C_ISR_STOPF) {
+		/* Disable interrupts */
+		if (stm32f7_i2c_is_slave_registered(i2c_dev))
+			mask = STM32F7_I2C_XFER_IRQ_MASK;
 		else
-			stm32f7_i2c_reload(i2c_dev);
-	}
-
-	return ret;
-}
-
-static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data)
-{
-	struct stm32f7_i2c_dev *i2c_dev = data;
-	struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg;
-	struct stm32_i2c_dma *dma = i2c_dev->dma;
-	u32 status;
-	int ret;
-
-	/*
-	 * Wait for dma transfer completion before sending next message or
-	 * notity the end of xfer to the client
-	 */
-	ret = wait_for_completion_timeout(&i2c_dev->dma->dma_complete, HZ);
-	if (!ret) {
-		dev_dbg(i2c_dev->dev, "<%s>: Timed out\n", __func__);
-		stm32f7_i2c_disable_dma_req(i2c_dev);
-		dmaengine_terminate_async(dma->chan_using);
-		f7_msg->result = -ETIMEDOUT;
-	}
+			mask = STM32F7_I2C_ALL_IRQ_MASK;
+		stm32f7_i2c_disable_irq(i2c_dev, mask);
 
-	status = readl_relaxed(i2c_dev->base + STM32F7_I2C_ISR);
+		/* Clear STOP flag */
+		writel_relaxed(STM32F7_I2C_ICR_STOPCF, base + STM32F7_I2C_ICR);
 
-	if (status & STM32F7_I2C_ISR_TC) {
-		if (f7_msg->smbus) {
-			stm32f7_i2c_smbus_rep_start(i2c_dev);
-		} else {
-			i2c_dev->msg_id++;
-			i2c_dev->msg++;
-			stm32f7_i2c_xfer_msg(i2c_dev, i2c_dev->msg);
-		}
-	} else {
 		i2c_dev->master_mode = false;
 		complete(&i2c_dev->complete);
 	}
@@ -1615,68 +1676,14 @@ static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t stm32f7_i2c_isr_error(int irq, void *data)
+static irqreturn_t stm32f7_i2c_isr_error_thread(int irq, void *data)
 {
 	struct stm32f7_i2c_dev *i2c_dev = data;
-	struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg;
-	void __iomem *base = i2c_dev->base;
-	struct device *dev = i2c_dev->dev;
-	struct stm32_i2c_dma *dma = i2c_dev->dma;
 	u32 status;
 
 	status = readl_relaxed(i2c_dev->base + STM32F7_I2C_ISR);
 
-	/* Bus error */
-	if (status & STM32F7_I2C_ISR_BERR) {
-		dev_err(dev, "<%s>: Bus error accessing addr 0x%x\n",
-			__func__, f7_msg->addr);
-		writel_relaxed(STM32F7_I2C_ICR_BERRCF, base + STM32F7_I2C_ICR);
-		stm32f7_i2c_release_bus(&i2c_dev->adap);
-		f7_msg->result = -EIO;
-	}
-
-	/* Arbitration loss */
-	if (status & STM32F7_I2C_ISR_ARLO) {
-		dev_dbg(dev, "<%s>: Arbitration loss accessing addr 0x%x\n",
-			__func__, f7_msg->addr);
-		writel_relaxed(STM32F7_I2C_ICR_ARLOCF, base + STM32F7_I2C_ICR);
-		f7_msg->result = -EAGAIN;
-	}
-
-	if (status & STM32F7_I2C_ISR_PECERR) {
-		dev_err(dev, "<%s>: PEC error in reception accessing addr 0x%x\n",
-			__func__, f7_msg->addr);
-		writel_relaxed(STM32F7_I2C_ICR_PECCF, base + STM32F7_I2C_ICR);
-		f7_msg->result = -EINVAL;
-	}
-
-	if (status & STM32F7_I2C_ISR_ALERT) {
-		dev_dbg(dev, "<%s>: SMBus alert received\n", __func__);
-		writel_relaxed(STM32F7_I2C_ICR_ALERTCF, base + STM32F7_I2C_ICR);
-		i2c_handle_smbus_alert(i2c_dev->alert->ara);
-		return IRQ_HANDLED;
-	}
-
-	if (!i2c_dev->slave_running) {
-		u32 mask;
-		/* Disable interrupts */
-		if (stm32f7_i2c_is_slave_registered(i2c_dev))
-			mask = STM32F7_I2C_XFER_IRQ_MASK;
-		else
-			mask = STM32F7_I2C_ALL_IRQ_MASK;
-		stm32f7_i2c_disable_irq(i2c_dev, mask);
-	}
-
-	/* Disable dma */
-	if (i2c_dev->use_dma) {
-		stm32f7_i2c_disable_dma_req(i2c_dev);
-		dmaengine_terminate_async(dma->chan_using);
-	}
-
-	i2c_dev->master_mode = false;
-	complete(&i2c_dev->complete);
-
-	return IRQ_HANDLED;
+	return stm32f7_i2c_handle_isr_errs(i2c_dev, status);
 }
 
 static int stm32f7_i2c_wait_polling(struct stm32f7_i2c_dev *i2c_dev)
@@ -2012,23 +2019,27 @@ static int stm32f7_i2c_unreg_slave(struct i2c_client *slave)
 static int stm32f7_i2c_write_fm_plus_bits(struct stm32f7_i2c_dev *i2c_dev,
 					  bool enable)
 {
-	int ret;
+	int ret = 0;
 
 	if (i2c_dev->bus_rate <= I2C_MAX_FAST_MODE_FREQ ||
-	    IS_ERR_OR_NULL(i2c_dev->regmap))
+	    (!i2c_dev->setup.fmp_cr1_bit && IS_ERR_OR_NULL(i2c_dev->regmap)))
 		/* Optional */
 		return 0;
 
-	if (i2c_dev->fmp_sreg == i2c_dev->fmp_creg)
-		ret = regmap_update_bits(i2c_dev->regmap,
-					 i2c_dev->fmp_sreg,
-					 i2c_dev->fmp_mask,
-					 enable ? i2c_dev->fmp_mask : 0);
-	else
-		ret = regmap_write(i2c_dev->regmap,
-				   enable ? i2c_dev->fmp_sreg :
-					    i2c_dev->fmp_creg,
-				   i2c_dev->fmp_mask);
+	if (i2c_dev->setup.fmp_cr1_bit) {
+		if (enable)
+			stm32f7_i2c_set_bits(i2c_dev->base + STM32F7_I2C_CR1, STM32_I2C_CR1_FMP);
+		else
+			stm32f7_i2c_clr_bits(i2c_dev->base + STM32F7_I2C_CR1, STM32_I2C_CR1_FMP);
+	} else {
+		if (i2c_dev->fmp_sreg == i2c_dev->fmp_creg)
+			ret = regmap_update_bits(i2c_dev->regmap, i2c_dev->fmp_sreg,
+						 i2c_dev->fmp_mask, enable ? i2c_dev->fmp_mask : 0);
+		else
+			ret = regmap_write(i2c_dev->regmap,
+					   enable ? i2c_dev->fmp_sreg : i2c_dev->fmp_creg,
+					   i2c_dev->fmp_mask);
+	}
 
 	return ret;
 }
@@ -2162,6 +2173,13 @@ static int stm32f7_i2c_probe(struct platform_device *pdev)
 	if (!i2c_dev)
 		return -ENOMEM;
 
+	setup = of_device_get_match_data(&pdev->dev);
+	if (!setup) {
+		dev_err(&pdev->dev, "Can't get device data\n");
+		return -ENODEV;
+	}
+	i2c_dev->setup = *setup;
+
 	i2c_dev->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(i2c_dev->base))
 		return PTR_ERR(i2c_dev->base);
@@ -2171,10 +2189,6 @@ static int stm32f7_i2c_probe(struct platform_device *pdev)
 	if (irq_event < 0)
 		return irq_event;
 
-	irq_error = platform_get_irq(pdev, 1);
-	if (irq_error < 0)
-		return irq_error;
-
 	i2c_dev->wakeup_src = of_property_read_bool(pdev->dev.of_node,
 						    "wakeup-source");
 
@@ -2199,26 +2213,22 @@ static int stm32f7_i2c_probe(struct platform_device *pdev)
 					stm32f7_i2c_isr_event_thread,
 					IRQF_ONESHOT,
 					pdev->name, i2c_dev);
-	if (ret) {
-		dev_err(&pdev->dev, "Failed to request irq event %i\n",
-			irq_event);
-		return ret;
-	}
-
-	ret = devm_request_irq(&pdev->dev, irq_error, stm32f7_i2c_isr_error, 0,
-			       pdev->name, i2c_dev);
-	if (ret) {
-		dev_err(&pdev->dev, "Failed to request irq error %i\n",
-			irq_error);
-		return ret;
-	}
-
-	setup = of_device_get_match_data(&pdev->dev);
-	if (!setup) {
-		dev_err(&pdev->dev, "Can't get device data\n");
-		return -ENODEV;
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "Failed to request irq event\n");
+
+	if (!i2c_dev->setup.single_it_line) {
+		irq_error = platform_get_irq(pdev, 1);
+		if (irq_error < 0)
+			return irq_error;
+
+		ret = devm_request_threaded_irq(&pdev->dev, irq_error,
+						NULL,
+						stm32f7_i2c_isr_error_thread,
+						IRQF_ONESHOT,
+						pdev->name, i2c_dev);
+		if (ret)
+			return dev_err_probe(&pdev->dev, ret, "Failed to request irq error\n");
 	}
-	i2c_dev->setup = *setup;
 
 	ret = stm32f7_i2c_setup_timing(i2c_dev, &i2c_dev->setup);
 	if (ret)
@@ -2226,9 +2236,12 @@ static int stm32f7_i2c_probe(struct platform_device *pdev)
 
 	/* Setup Fast mode plus if necessary */
 	if (i2c_dev->bus_rate > I2C_MAX_FAST_MODE_FREQ) {
-		ret = stm32f7_i2c_setup_fm_plus_bits(pdev, i2c_dev);
-		if (ret)
-			return ret;
+		if (!i2c_dev->setup.fmp_cr1_bit) {
+			ret = stm32f7_i2c_setup_fm_plus_bits(pdev, i2c_dev);
+			if (ret)
+				return ret;
+		}
+
 		ret = stm32f7_i2c_write_fm_plus_bits(i2c_dev, true);
 		if (ret)
 			return ret;
@@ -2507,6 +2520,7 @@ static const struct of_device_id stm32f7_i2c_match[] = {
 	{ .compatible = "st,stm32f7-i2c", .data = &stm32f7_setup},
 	{ .compatible = "st,stm32mp15-i2c", .data = &stm32mp15_setup},
 	{ .compatible = "st,stm32mp13-i2c", .data = &stm32mp13_setup},
+	{ .compatible = "st,stm32mp25-i2c", .data = &stm32mp25_setup},
 	{},
 };
 MODULE_DEVICE_TABLE(of, stm32f7_i2c_match);
diff --git a/drivers/i2c/busses/i2c-via.c b/drivers/i2c/busses/i2c-via.c
index ad4f09c7f027..7ed29992a97f 100644
--- a/drivers/i2c/busses/i2c-via.c
+++ b/drivers/i2c/busses/i2c-via.c
@@ -70,7 +70,7 @@ static struct i2c_algo_bit_data bit_data = {
 
 static struct i2c_adapter vt586b_adapter = {
 	.owner		= THIS_MODULE,
-	.class          = I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class          = I2C_CLASS_HWMON,
 	.name		= "VIA i2c",
 	.algo_data	= &bit_data,
 };
diff --git a/drivers/i2c/busses/i2c-viapro.c b/drivers/i2c/busses/i2c-viapro.c
index 970ccdcbb889..2cc7bba3b8bf 100644
--- a/drivers/i2c/busses/i2c-viapro.c
+++ b/drivers/i2c/busses/i2c-viapro.c
@@ -304,7 +304,7 @@ static const struct i2c_algorithm smbus_algorithm = {
 
 static struct i2c_adapter vt596_adapter = {
 	.owner		= THIS_MODULE,
-	.class		= I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class		= I2C_CLASS_HWMON,
 	.algo		= &smbus_algorithm,
 };
 
diff --git a/drivers/i2c/busses/i2c-wmt.c b/drivers/i2c/busses/i2c-wmt.c
index 76118abc6e10..198afee5233c 100644
--- a/drivers/i2c/busses/i2c-wmt.c
+++ b/drivers/i2c/busses/i2c-wmt.c
@@ -74,9 +74,6 @@
 #define MCR_APB_96M		7
 #define MCR_APB_166M		12
 
-#define I2C_MODE_STANDARD	0
-#define I2C_MODE_FAST		1
-
 #define WMT_I2C_TIMEOUT		(msecs_to_jiffies(1000))
 
 struct wmt_i2c_dev {
@@ -85,7 +82,7 @@ struct wmt_i2c_dev {
 	struct device		*dev;
 	void __iomem		*base;
 	struct clk		*clk;
-	int			mode;
+	u16			tcr;
 	int			irq;
 	u16			cmd_status;
 };
@@ -109,6 +106,12 @@ static int wmt_i2c_wait_bus_not_busy(struct wmt_i2c_dev *i2c_dev)
 static int wmt_check_status(struct wmt_i2c_dev *i2c_dev)
 {
 	int ret = 0;
+	unsigned long wait_result;
+
+	wait_result = wait_for_completion_timeout(&i2c_dev->complete,
+						msecs_to_jiffies(500));
+	if (!wait_result)
+		return -ETIMEDOUT;
 
 	if (i2c_dev->cmd_status & ISR_NACK_ADDR)
 		ret = -EIO;
@@ -119,21 +122,13 @@ static int wmt_check_status(struct wmt_i2c_dev *i2c_dev)
 	return ret;
 }
 
-static int wmt_i2c_write(struct i2c_adapter *adap, struct i2c_msg *pmsg,
+static int wmt_i2c_write(struct wmt_i2c_dev *i2c_dev, struct i2c_msg *pmsg,
 			 int last)
 {
-	struct wmt_i2c_dev *i2c_dev = i2c_get_adapdata(adap);
-	u16 val, tcr_val;
+	u16 val, tcr_val = i2c_dev->tcr;
 	int ret;
-	unsigned long wait_result;
 	int xfer_len = 0;
 
-	if (!(pmsg->flags & I2C_M_NOSTART)) {
-		ret = wmt_i2c_wait_bus_not_busy(i2c_dev);
-		if (ret < 0)
-			return ret;
-	}
-
 	if (pmsg->len == 0) {
 		/*
 		 * We still need to run through the while (..) once, so
@@ -148,20 +143,12 @@ static int wmt_i2c_write(struct i2c_adapter *adap, struct i2c_msg *pmsg,
 	if (!(pmsg->flags & I2C_M_NOSTART)) {
 		val = readw(i2c_dev->base + REG_CR);
 		val &= ~CR_TX_END;
-		writew(val, i2c_dev->base + REG_CR);
-
-		val = readw(i2c_dev->base + REG_CR);
 		val |= CR_CPU_RDY;
 		writew(val, i2c_dev->base + REG_CR);
 	}
 
 	reinit_completion(&i2c_dev->complete);
 
-	if (i2c_dev->mode == I2C_MODE_STANDARD)
-		tcr_val = TCR_STANDARD_MODE;
-	else
-		tcr_val = TCR_FAST_MODE;
-
 	tcr_val |= (TCR_MASTER_WRITE | (pmsg->addr & TCR_SLAVE_ADDR_MASK));
 
 	writew(tcr_val, i2c_dev->base + REG_TCR);
@@ -173,12 +160,6 @@ static int wmt_i2c_write(struct i2c_adapter *adap, struct i2c_msg *pmsg,
 	}
 
 	while (xfer_len < pmsg->len) {
-		wait_result = wait_for_completion_timeout(&i2c_dev->complete,
-							msecs_to_jiffies(500));
-
-		if (wait_result == 0)
-			return -ETIMEDOUT;
-
 		ret = wmt_check_status(i2c_dev);
 		if (ret)
 			return ret;
@@ -210,47 +191,24 @@ static int wmt_i2c_write(struct i2c_adapter *adap, struct i2c_msg *pmsg,
 	return 0;
 }
 
-static int wmt_i2c_read(struct i2c_adapter *adap, struct i2c_msg *pmsg,
-			int last)
+static int wmt_i2c_read(struct wmt_i2c_dev *i2c_dev, struct i2c_msg *pmsg)
 {
-	struct wmt_i2c_dev *i2c_dev = i2c_get_adapdata(adap);
-	u16 val, tcr_val;
+	u16 val, tcr_val = i2c_dev->tcr;
 	int ret;
-	unsigned long wait_result;
 	u32 xfer_len = 0;
 
-	if (!(pmsg->flags & I2C_M_NOSTART)) {
-		ret = wmt_i2c_wait_bus_not_busy(i2c_dev);
-		if (ret < 0)
-			return ret;
-	}
-
 	val = readw(i2c_dev->base + REG_CR);
-	val &= ~CR_TX_END;
-	writew(val, i2c_dev->base + REG_CR);
+	val &= ~(CR_TX_END | CR_TX_NEXT_NO_ACK);
 
-	val = readw(i2c_dev->base + REG_CR);
-	val &= ~CR_TX_NEXT_NO_ACK;
-	writew(val, i2c_dev->base + REG_CR);
-
-	if (!(pmsg->flags & I2C_M_NOSTART)) {
-		val = readw(i2c_dev->base + REG_CR);
+	if (!(pmsg->flags & I2C_M_NOSTART))
 		val |= CR_CPU_RDY;
-		writew(val, i2c_dev->base + REG_CR);
-	}
 
-	if (pmsg->len == 1) {
-		val = readw(i2c_dev->base + REG_CR);
+	if (pmsg->len == 1)
 		val |= CR_TX_NEXT_NO_ACK;
-		writew(val, i2c_dev->base + REG_CR);
-	}
 
-	reinit_completion(&i2c_dev->complete);
+	writew(val, i2c_dev->base + REG_CR);
 
-	if (i2c_dev->mode == I2C_MODE_STANDARD)
-		tcr_val = TCR_STANDARD_MODE;
-	else
-		tcr_val = TCR_FAST_MODE;
+	reinit_completion(&i2c_dev->complete);
 
 	tcr_val |= TCR_MASTER_READ | (pmsg->addr & TCR_SLAVE_ADDR_MASK);
 
@@ -263,12 +221,6 @@ static int wmt_i2c_read(struct i2c_adapter *adap, struct i2c_msg *pmsg,
 	}
 
 	while (xfer_len < pmsg->len) {
-		wait_result = wait_for_completion_timeout(&i2c_dev->complete,
-							msecs_to_jiffies(500));
-
-		if (!wait_result)
-			return -ETIMEDOUT;
-
 		ret = wmt_check_status(i2c_dev);
 		if (ret)
 			return ret;
@@ -276,15 +228,10 @@ static int wmt_i2c_read(struct i2c_adapter *adap, struct i2c_msg *pmsg,
 		pmsg->buf[xfer_len] = readw(i2c_dev->base + REG_CDR) >> 8;
 		xfer_len++;
 
-		if (xfer_len == pmsg->len - 1) {
-			val = readw(i2c_dev->base + REG_CR);
-			val |= (CR_TX_NEXT_NO_ACK | CR_CPU_RDY);
-			writew(val, i2c_dev->base + REG_CR);
-		} else {
-			val = readw(i2c_dev->base + REG_CR);
-			val |= CR_CPU_RDY;
-			writew(val, i2c_dev->base + REG_CR);
-		}
+		val = readw(i2c_dev->base + REG_CR) | CR_CPU_RDY;
+		if (xfer_len == pmsg->len - 1)
+			val |= CR_TX_NEXT_NO_ACK;
+		writew(val, i2c_dev->base + REG_CR);
 	}
 
 	return 0;
@@ -295,17 +242,22 @@ static int wmt_i2c_xfer(struct i2c_adapter *adap,
 			int num)
 {
 	struct i2c_msg *pmsg;
-	int i, is_last;
+	int i;
 	int ret = 0;
+	struct wmt_i2c_dev *i2c_dev = i2c_get_adapdata(adap);
 
 	for (i = 0; ret >= 0 && i < num; i++) {
-		is_last = ((i + 1) == num);
-
 		pmsg = &msgs[i];
+		if (!(pmsg->flags & I2C_M_NOSTART)) {
+			ret = wmt_i2c_wait_bus_not_busy(i2c_dev);
+			if (ret < 0)
+				return ret;
+		}
+
 		if (pmsg->flags & I2C_M_RD)
-			ret = wmt_i2c_read(adap, pmsg, is_last);
+			ret = wmt_i2c_read(i2c_dev, pmsg);
 		else
-			ret = wmt_i2c_write(adap, pmsg, is_last);
+			ret = wmt_i2c_write(i2c_dev, pmsg, (i + 1) == num);
 	}
 
 	return (ret < 0) ? ret : i;
@@ -359,10 +311,10 @@ static int wmt_i2c_reset_hardware(struct wmt_i2c_dev *i2c_dev)
 	readw(i2c_dev->base + REG_CSR);		/* read clear */
 	writew(ISR_WRITE_ALL, i2c_dev->base + REG_ISR);
 
-	if (i2c_dev->mode == I2C_MODE_STANDARD)
-		writew(SCL_TIMEOUT(128) | TR_STD, i2c_dev->base + REG_TR);
-	else
+	if (i2c_dev->tcr == TCR_FAST_MODE)
 		writew(SCL_TIMEOUT(128) | TR_HS, i2c_dev->base + REG_TR);
+	else
+		writew(SCL_TIMEOUT(128) | TR_STD, i2c_dev->base + REG_TR);
 
 	return 0;
 }
@@ -395,10 +347,9 @@ static int wmt_i2c_probe(struct platform_device *pdev)
 		return PTR_ERR(i2c_dev->clk);
 	}
 
-	i2c_dev->mode = I2C_MODE_STANDARD;
 	err = of_property_read_u32(np, "clock-frequency", &clk_rate);
 	if (!err && (clk_rate == I2C_MAX_FAST_MODE_FREQ))
-		i2c_dev->mode = I2C_MODE_FAST;
+		i2c_dev->tcr = TCR_FAST_MODE;
 
 	i2c_dev->dev = &pdev->dev;
 
@@ -427,11 +378,15 @@ static int wmt_i2c_probe(struct platform_device *pdev)
 
 	err = i2c_add_adapter(adap);
 	if (err)
-		return err;
+		goto err_disable_clk;
 
 	platform_set_drvdata(pdev, i2c_dev);
 
 	return 0;
+
+err_disable_clk:
+	clk_disable_unprepare(i2c_dev->clk);
+	return err;
 }
 
 static void wmt_i2c_remove(struct platform_device *pdev)
diff --git a/drivers/i2c/busses/scx200_acb.c b/drivers/i2c/busses/scx200_acb.c
index 83c1db610f54..3648382b885a 100644
--- a/drivers/i2c/busses/scx200_acb.c
+++ b/drivers/i2c/busses/scx200_acb.c
@@ -427,7 +427,7 @@ static struct scx200_acb_iface *scx200_create_iface(const char *text,
 	snprintf(adapter->name, sizeof(adapter->name), "%s ACB%d", text, index);
 	adapter->owner = THIS_MODULE;
 	adapter->algo = &scx200_acb_algorithm;
-	adapter->class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	adapter->class = I2C_CLASS_HWMON;
 	adapter->dev.parent = dev;
 
 	mutex_init(&iface->mutex);
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index eac90a3cf61a..3bd48d4b6318 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -16,6 +16,7 @@
 #include <linux/acpi.h>
 #include <linux/clk/clk-conf.h>
 #include <linux/completion.h>
+#include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/errno.h>
@@ -67,6 +68,8 @@ static int i2c_detect(struct i2c_adapter *adapter, struct i2c_driver *driver);
 static DEFINE_STATIC_KEY_FALSE(i2c_trace_msg_key);
 static bool is_registered;
 
+static struct dentry *i2c_debugfs_root;
+
 int i2c_transfer_trace_reg(void)
 {
 	static_branch_inc(&i2c_trace_msg_key);
@@ -689,7 +692,7 @@ static struct attribute *i2c_dev_attrs[] = {
 };
 ATTRIBUTE_GROUPS(i2c_dev);
 
-struct bus_type i2c_bus_type = {
+const struct bus_type i2c_bus_type = {
 	.name		= "i2c",
 	.match		= i2c_device_match,
 	.probe		= i2c_device_probe,
@@ -1524,6 +1527,8 @@ static int i2c_register_adapter(struct i2c_adapter *adap)
 		goto out_list;
 	}
 
+	adap->debugfs = debugfs_create_dir(dev_name(&adap->dev), i2c_debugfs_root);
+
 	res = i2c_setup_smbus_alert(adap);
 	if (res)
 		goto out_reg;
@@ -1563,6 +1568,7 @@ static int i2c_register_adapter(struct i2c_adapter *adap)
 	return 0;
 
 out_reg:
+	debugfs_remove_recursive(adap->debugfs);
 	init_completion(&adap->dev_released);
 	device_unregister(&adap->dev);
 	wait_for_completion(&adap->dev_released);
@@ -1764,6 +1770,8 @@ void i2c_del_adapter(struct i2c_adapter *adap)
 
 	i2c_host_notify_irq_teardown(adap);
 
+	debugfs_remove_recursive(adap->debugfs);
+
 	/* wait until all references to the device are gone
 	 *
 	 * FIXME: This is old code and should ideally be replaced by an
@@ -2061,6 +2069,8 @@ static int __init i2c_init(void)
 
 	is_registered = true;
 
+	i2c_debugfs_root = debugfs_create_dir("i2c", NULL);
+
 #ifdef CONFIG_I2C_COMPAT
 	i2c_adapter_compat_class = class_compat_register("i2c-adapter");
 	if (!i2c_adapter_compat_class) {
@@ -2099,6 +2109,7 @@ static void __exit i2c_exit(void)
 #ifdef CONFIG_I2C_COMPAT
 	class_compat_unregister(i2c_adapter_compat_class);
 #endif
+	debugfs_remove_recursive(i2c_debugfs_root);
 	bus_unregister(&i2c_bus_type);
 	tracepoint_synchronize_unregister();
 }
diff --git a/drivers/i2c/i2c-smbus.c b/drivers/i2c/i2c-smbus.c
index 138c3f5e0093..74807c6db596 100644
--- a/drivers/i2c/i2c-smbus.c
+++ b/drivers/i2c/i2c-smbus.c
@@ -308,8 +308,8 @@ EXPORT_SYMBOL_GPL(i2c_free_slave_host_notify_device);
  * target systems are the same.
  * Restrictions to automatic SPD instantiation:
  *  - Only works if all filled slots have the same memory type
- *  - Only works for DDR2, DDR3 and DDR4 for now
- *  - Only works on systems with 1 to 4 memory slots
+ *  - Only works for DDR, DDR2, DDR3 and DDR4 for now
+ *  - Only works on systems with 1 to 8 memory slots
  */
 #if IS_ENABLED(CONFIG_DMI)
 void i2c_register_spd(struct i2c_adapter *adap)
@@ -354,9 +354,9 @@ void i2c_register_spd(struct i2c_adapter *adap)
 	dev_info(&adap->dev, "%d/%d memory slots populated (from DMI)\n",
 		 dimm_count, slot_count);
 
-	if (slot_count > 4) {
+	if (slot_count > 8) {
 		dev_warn(&adap->dev,
-			 "Systems with more than 4 memory slots not supported yet, not instantiating SPD\n");
+			 "Systems with more than 8 memory slots not supported yet, not instantiating SPD\n");
 		return;
 	}
 
diff --git a/drivers/i2c/i2c-stub.c b/drivers/i2c/i2c-stub.c
index d642cad219d9..09e7b7bf4c5f 100644
--- a/drivers/i2c/i2c-stub.c
+++ b/drivers/i2c/i2c-stub.c
@@ -308,7 +308,7 @@ static const struct i2c_algorithm smbus_algorithm = {
 
 static struct i2c_adapter stub_adapter = {
 	.owner		= THIS_MODULE,
-	.class		= I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class		= I2C_CLASS_HWMON,
 	.algo		= &smbus_algorithm,
 	.name		= "SMBus stub driver",
 };
diff --git a/drivers/i2c/muxes/i2c-mux-reg.c b/drivers/i2c/muxes/i2c-mux-reg.c
index 9efc1ed01577..8489971babd3 100644
--- a/drivers/i2c/muxes/i2c-mux-reg.c
+++ b/drivers/i2c/muxes/i2c-mux-reg.c
@@ -159,7 +159,6 @@ static int i2c_mux_reg_probe(struct platform_device *pdev)
 	struct regmux *mux;
 	struct i2c_adapter *parent;
 	struct resource *res;
-	unsigned int class;
 	int i, ret, nr;
 
 	mux = devm_kzalloc(&pdev->dev, sizeof(*mux), GFP_KERNEL);
@@ -213,9 +212,8 @@ static int i2c_mux_reg_probe(struct platform_device *pdev)
 
 	for (i = 0; i < mux->data.n_values; i++) {
 		nr = mux->data.base_nr ? (mux->data.base_nr + i) : 0;
-		class = mux->data.classes ? mux->data.classes[i] : 0;
 
-		ret = i2c_mux_add_adapter(muxc, nr, mux->data.values[i], class);
+		ret = i2c_mux_add_adapter(muxc, nr, mux->data.values[i], 0);
 		if (ret)
 			goto err_del_mux_adapters;
 	}
diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c
index 95caa162706f..3afa530c5e32 100644
--- a/drivers/i3c/master.c
+++ b/drivers/i3c/master.c
@@ -557,6 +557,88 @@ static ssize_t i2c_scl_frequency_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(i2c_scl_frequency);
 
+static int i3c_set_hotjoin(struct i3c_master_controller *master, bool enable)
+{
+	int ret;
+
+	if (!master || !master->ops)
+		return -EINVAL;
+
+	if (!master->ops->enable_hotjoin || !master->ops->disable_hotjoin)
+		return -EINVAL;
+
+	i3c_bus_normaluse_lock(&master->bus);
+
+	if (enable)
+		ret = master->ops->enable_hotjoin(master);
+	else
+		ret = master->ops->disable_hotjoin(master);
+
+	master->hotjoin = enable;
+
+	i3c_bus_normaluse_unlock(&master->bus);
+
+	return ret;
+}
+
+static ssize_t hotjoin_store(struct device *dev, struct device_attribute *attr,
+			     const char *buf, size_t count)
+{
+	struct i3c_bus *i3cbus = dev_to_i3cbus(dev);
+	int ret;
+	bool res;
+
+	if (!i3cbus->cur_master)
+		return -EINVAL;
+
+	if (kstrtobool(buf, &res))
+		return -EINVAL;
+
+	ret = i3c_set_hotjoin(i3cbus->cur_master->common.master, res);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+/*
+ * i3c_master_enable_hotjoin - Enable hotjoin
+ * @master: I3C master object
+ *
+ * Return: a 0 in case of success, an negative error code otherwise.
+ */
+int i3c_master_enable_hotjoin(struct i3c_master_controller *master)
+{
+	return i3c_set_hotjoin(master, true);
+}
+EXPORT_SYMBOL_GPL(i3c_master_enable_hotjoin);
+
+/*
+ * i3c_master_disable_hotjoin - Disable hotjoin
+ * @master: I3C master object
+ *
+ * Return: a 0 in case of success, an negative error code otherwise.
+ */
+int i3c_master_disable_hotjoin(struct i3c_master_controller *master)
+{
+	return i3c_set_hotjoin(master, false);
+}
+EXPORT_SYMBOL_GPL(i3c_master_disable_hotjoin);
+
+static ssize_t hotjoin_show(struct device *dev, struct device_attribute *da, char *buf)
+{
+	struct i3c_bus *i3cbus = dev_to_i3cbus(dev);
+	ssize_t ret;
+
+	i3c_bus_normaluse_lock(i3cbus);
+	ret = sysfs_emit(buf, "%d\n", i3cbus->cur_master->common.master->hotjoin);
+	i3c_bus_normaluse_unlock(i3cbus);
+
+	return ret;
+}
+
+static DEVICE_ATTR_RW(hotjoin);
+
 static struct attribute *i3c_masterdev_attrs[] = {
 	&dev_attr_mode.attr,
 	&dev_attr_current_master.attr,
@@ -567,6 +649,7 @@ static struct attribute *i3c_masterdev_attrs[] = {
 	&dev_attr_pid.attr,
 	&dev_attr_dynamic_address.attr,
 	&dev_attr_hdrcap.attr,
+	&dev_attr_hotjoin.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(i3c_masterdev);
@@ -1130,8 +1213,16 @@ static int i3c_master_getmxds_locked(struct i3c_master_controller *master,
 
 	i3c_ccc_cmd_init(&cmd, true, I3C_CCC_GETMXDS, &dest, 1);
 	ret = i3c_master_send_ccc_cmd_locked(master, &cmd);
-	if (ret)
-		goto out;
+	if (ret) {
+		/*
+		 * Retry when the device does not support max read turnaround
+		 * while expecting shorter length from this CCC command.
+		 */
+		dest.payload.len -= 3;
+		ret = i3c_master_send_ccc_cmd_locked(master, &cmd);
+		if (ret)
+			goto out;
+	}
 
 	if (dest.payload.len != 2 && dest.payload.len != 5) {
 		ret = -EIO;
diff --git a/drivers/i3c/master/i3c-master-cdns.c b/drivers/i3c/master/i3c-master-cdns.c
index bcbe8f914149..c1627f3552ce 100644
--- a/drivers/i3c/master/i3c-master-cdns.c
+++ b/drivers/i3c/master/i3c-master-cdns.c
@@ -76,7 +76,8 @@
 #define PRESCL_CTRL0			0x14
 #define PRESCL_CTRL0_I2C(x)		((x) << 16)
 #define PRESCL_CTRL0_I3C(x)		(x)
-#define PRESCL_CTRL0_MAX		GENMASK(9, 0)
+#define PRESCL_CTRL0_I3C_MAX		GENMASK(9, 0)
+#define PRESCL_CTRL0_I2C_MAX		GENMASK(15, 0)
 
 #define PRESCL_CTRL1			0x18
 #define PRESCL_CTRL1_PP_LOW_MASK	GENMASK(15, 8)
@@ -1233,7 +1234,7 @@ static int cdns_i3c_master_bus_init(struct i3c_master_controller *m)
 		return -EINVAL;
 
 	pres = DIV_ROUND_UP(sysclk_rate, (bus->scl_rate.i3c * 4)) - 1;
-	if (pres > PRESCL_CTRL0_MAX)
+	if (pres > PRESCL_CTRL0_I3C_MAX)
 		return -ERANGE;
 
 	bus->scl_rate.i3c = sysclk_rate / ((pres + 1) * 4);
@@ -1246,7 +1247,7 @@ static int cdns_i3c_master_bus_init(struct i3c_master_controller *m)
 	max_i2cfreq = bus->scl_rate.i2c;
 
 	pres = (sysclk_rate / (max_i2cfreq * 5)) - 1;
-	if (pres > PRESCL_CTRL0_MAX)
+	if (pres > PRESCL_CTRL0_I2C_MAX)
 		return -ERANGE;
 
 	bus->scl_rate.i2c = sysclk_rate / ((pres + 1) * 5);
diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
index 2b2323aa6714..638b054d6c92 100644
--- a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
+++ b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
@@ -298,7 +298,7 @@ static int hci_cmd_v1_daa(struct i3c_hci *hci)
 	unsigned int dcr, bcr;
 	DECLARE_COMPLETION_ONSTACK(done);
 
-	xfer = hci_alloc_xfer(2);
+	xfer = hci_alloc_xfer(1);
 	if (!xfer)
 		return -ENOMEM;
 
@@ -339,12 +339,13 @@ static int hci_cmd_v1_daa(struct i3c_hci *hci)
 			ret = -ETIME;
 			break;
 		}
-		if (RESP_STATUS(xfer[0].response) == RESP_ERR_NACK &&
+		if ((RESP_STATUS(xfer->response) == RESP_ERR_ADDR_HEADER ||
+		     RESP_STATUS(xfer->response) == RESP_ERR_NACK) &&
 		    RESP_DATA_LENGTH(xfer->response) == 1) {
 			ret = 0;  /* no more devices to be assigned */
 			break;
 		}
-		if (RESP_STATUS(xfer[0].response) != RESP_SUCCESS) {
+		if (RESP_STATUS(xfer->response) != RESP_SUCCESS) {
 			ret = -EIO;
 			break;
 		}
diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index 1ae56a5699c6..d7e966a25583 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -245,7 +245,14 @@ static int i3c_hci_send_ccc_cmd(struct i3c_master_controller *m,
 		if (ccc->rnw)
 			ccc->dests[i - prefixed].payload.len =
 				RESP_DATA_LENGTH(xfer[i].response);
-		if (RESP_STATUS(xfer[i].response) != RESP_SUCCESS) {
+		switch (RESP_STATUS(xfer[i].response)) {
+		case RESP_SUCCESS:
+			continue;
+		case RESP_ERR_ADDR_HEADER:
+		case RESP_ERR_NACK:
+			ccc->err = I3C_ERROR_M2;
+			fallthrough;
+		default:
 			ret = -EIO;
 			goto out;
 		}
@@ -269,6 +276,34 @@ static int i3c_hci_daa(struct i3c_master_controller *m)
 	return hci->cmd->perform_daa(hci);
 }
 
+static int i3c_hci_alloc_safe_xfer_buf(struct i3c_hci *hci,
+				       struct hci_xfer *xfer)
+{
+	if (hci->io != &mipi_i3c_hci_dma ||
+	    xfer->data == NULL || !is_vmalloc_addr(xfer->data))
+		return 0;
+
+	if (xfer->rnw)
+		xfer->bounce_buf = kzalloc(xfer->data_len, GFP_KERNEL);
+	else
+		xfer->bounce_buf = kmemdup(xfer->data,
+					   xfer->data_len, GFP_KERNEL);
+
+	return xfer->bounce_buf == NULL ? -ENOMEM : 0;
+}
+
+static void i3c_hci_free_safe_xfer_buf(struct i3c_hci *hci,
+				       struct hci_xfer *xfer)
+{
+	if (hci->io != &mipi_i3c_hci_dma || xfer->bounce_buf == NULL)
+		return;
+
+	if (xfer->rnw)
+		memcpy(xfer->data, xfer->bounce_buf, xfer->data_len);
+
+	kfree(xfer->bounce_buf);
+}
+
 static int i3c_hci_priv_xfers(struct i3c_dev_desc *dev,
 			      struct i3c_priv_xfer *i3c_xfers,
 			      int nxfers)
@@ -302,6 +337,9 @@ static int i3c_hci_priv_xfers(struct i3c_dev_desc *dev,
 		}
 		hci->cmd->prep_i3c_xfer(hci, dev, &xfer[i]);
 		xfer[i].cmd_desc[0] |= CMD_0_ROC;
+		ret = i3c_hci_alloc_safe_xfer_buf(hci, &xfer[i]);
+		if (ret)
+			goto out;
 	}
 	last = i - 1;
 	xfer[last].cmd_desc[0] |= CMD_0_TOC;
@@ -325,6 +363,9 @@ static int i3c_hci_priv_xfers(struct i3c_dev_desc *dev,
 	}
 
 out:
+	for (i = 0; i < nxfers; i++)
+		i3c_hci_free_safe_xfer_buf(hci, &xfer[i]);
+
 	hci_free_xfer(xfer, nxfers);
 	return ret;
 }
@@ -350,6 +391,9 @@ static int i3c_hci_i2c_xfers(struct i2c_dev_desc *dev,
 		xfer[i].rnw = i2c_xfers[i].flags & I2C_M_RD;
 		hci->cmd->prep_i2c_xfer(hci, dev, &xfer[i]);
 		xfer[i].cmd_desc[0] |= CMD_0_ROC;
+		ret = i3c_hci_alloc_safe_xfer_buf(hci, &xfer[i]);
+		if (ret)
+			goto out;
 	}
 	last = i - 1;
 	xfer[last].cmd_desc[0] |= CMD_0_TOC;
@@ -371,6 +415,9 @@ static int i3c_hci_i2c_xfers(struct i2c_dev_desc *dev,
 	}
 
 out:
+	for (i = 0; i < nxfers; i++)
+		i3c_hci_free_safe_xfer_buf(hci, &xfer[i]);
+
 	hci_free_xfer(xfer, nxfers);
 	return ret;
 }
diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index c805a8497319..4e01a95cc4d0 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -362,6 +362,7 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 	struct hci_rh_data *rh;
 	unsigned int i, ring, enqueue_ptr;
 	u32 op1_val, op2_val;
+	void *buf;
 
 	/* For now we only use ring 0 */
 	ring = 0;
@@ -390,9 +391,10 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 
 		/* 2nd and 3rd words of Data Buffer Descriptor Structure */
 		if (xfer->data) {
+			buf = xfer->bounce_buf ? xfer->bounce_buf : xfer->data;
 			xfer->data_dma =
 				dma_map_single(&hci->master.dev,
-					       xfer->data,
+					       buf,
 					       xfer->data_len,
 					       xfer->rnw ?
 						  DMA_FROM_DEVICE :
diff --git a/drivers/i3c/master/mipi-i3c-hci/hci.h b/drivers/i3c/master/mipi-i3c-hci/hci.h
index f109923f6c3f..f94d95e024be 100644
--- a/drivers/i3c/master/mipi-i3c-hci/hci.h
+++ b/drivers/i3c/master/mipi-i3c-hci/hci.h
@@ -90,6 +90,7 @@ struct hci_xfer {
 		struct {
 			/* DMA specific */
 			dma_addr_t data_dma;
+			void *bounce_buf;
 			int ring_number;
 			int ring_entry;
 		};
diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c
index cf703c00f633..5ee4db68988e 100644
--- a/drivers/i3c/master/svc-i3c-master.c
+++ b/drivers/i3c/master/svc-i3c-master.c
@@ -128,13 +128,17 @@
 /* This parameter depends on the implementation and may be tuned */
 #define SVC_I3C_FIFO_SIZE 16
 
+#define SVC_I3C_EVENT_IBI	BIT(0)
+#define SVC_I3C_EVENT_HOTJOIN	BIT(1)
+
 struct svc_i3c_cmd {
 	u8 addr;
 	bool rnw;
 	u8 *in;
 	const void *out;
 	unsigned int len;
-	unsigned int read_len;
+	unsigned int actual_len;
+	struct i3c_priv_xfer *xfer;
 	bool continued;
 };
 
@@ -177,6 +181,7 @@ struct svc_i3c_regs_save {
  * @ibi.tbq_slot: To be queued IBI slot
  * @ibi.lock: IBI lock
  * @lock: Transfer lock, protect between IBI work thread and callbacks from master
+ * @enabled_events: Bit masks for enable events (IBI, HotJoin).
  */
 struct svc_i3c_master {
 	struct i3c_master_controller base;
@@ -206,6 +211,7 @@ struct svc_i3c_master {
 		spinlock_t lock;
 	} ibi;
 	struct mutex lock;
+	int enabled_events;
 };
 
 /**
@@ -220,6 +226,11 @@ struct svc_i3c_i2c_dev_data {
 	struct i3c_generic_ibi_pool *ibi_pool;
 };
 
+static inline bool is_events_enabled(struct svc_i3c_master *master, u32 mask)
+{
+	return !!(master->enabled_events & mask);
+}
+
 static bool svc_i3c_master_error(struct svc_i3c_master *master)
 {
 	u32 mstatus, merrwarn;
@@ -429,13 +440,16 @@ static void svc_i3c_master_ibi_work(struct work_struct *work)
 	switch (ibitype) {
 	case SVC_I3C_MSTATUS_IBITYPE_IBI:
 		dev = svc_i3c_master_dev_from_addr(master, ibiaddr);
-		if (!dev)
+		if (!dev || !is_events_enabled(master, SVC_I3C_EVENT_IBI))
 			svc_i3c_master_nack_ibi(master);
 		else
 			svc_i3c_master_handle_ibi(master, dev);
 		break;
 	case SVC_I3C_MSTATUS_IBITYPE_HOT_JOIN:
-		svc_i3c_master_ack_ibi(master, false);
+		if (is_events_enabled(master, SVC_I3C_EVENT_HOTJOIN))
+			svc_i3c_master_ack_ibi(master, false);
+		else
+			svc_i3c_master_nack_ibi(master);
 		break;
 	case SVC_I3C_MSTATUS_IBITYPE_MASTER_REQUEST:
 		svc_i3c_master_nack_ibi(master);
@@ -472,7 +486,9 @@ static void svc_i3c_master_ibi_work(struct work_struct *work)
 		svc_i3c_master_emit_stop(master);
 		break;
 	case SVC_I3C_MSTATUS_IBITYPE_HOT_JOIN:
-		queue_work(master->base.wq, &master->hj_work);
+		svc_i3c_master_emit_stop(master);
+		if (is_events_enabled(master, SVC_I3C_EVENT_HOTJOIN))
+			queue_work(master->base.wq, &master->hj_work);
 		break;
 	case SVC_I3C_MSTATUS_IBITYPE_MASTER_REQUEST:
 	default:
@@ -1024,7 +1040,7 @@ static int svc_i3c_master_write(struct svc_i3c_master *master,
 static int svc_i3c_master_xfer(struct svc_i3c_master *master,
 			       bool rnw, unsigned int xfer_type, u8 addr,
 			       u8 *in, const u8 *out, unsigned int xfer_len,
-			       unsigned int *read_len, bool continued)
+			       unsigned int *actual_len, bool continued)
 {
 	u32 reg;
 	int ret;
@@ -1037,7 +1053,7 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master,
 	       SVC_I3C_MCTRL_IBIRESP_NACK |
 	       SVC_I3C_MCTRL_DIR(rnw) |
 	       SVC_I3C_MCTRL_ADDR(addr) |
-	       SVC_I3C_MCTRL_RDTERM(*read_len),
+	       SVC_I3C_MCTRL_RDTERM(*actual_len),
 	       master->regs + SVC_I3C_MCTRL);
 
 	ret = readl_poll_timeout(master->regs + SVC_I3C_MSTATUS, reg,
@@ -1047,6 +1063,7 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master,
 
 	if (readl(master->regs + SVC_I3C_MERRWARN) & SVC_I3C_MERRWARN_NACK) {
 		ret = -ENXIO;
+		*actual_len = 0;
 		goto emit_stop;
 	}
 
@@ -1064,6 +1081,7 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master,
 	 */
 	if (SVC_I3C_MSTATUS_IBIWON(reg)) {
 		ret = -ENXIO;
+		*actual_len = 0;
 		goto emit_stop;
 	}
 
@@ -1075,7 +1093,7 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master,
 		goto emit_stop;
 
 	if (rnw)
-		*read_len = ret;
+		*actual_len = ret;
 
 	ret = readl_poll_timeout(master->regs + SVC_I3C_MSTATUS, reg,
 				 SVC_I3C_MSTATUS_COMPLETE(reg), 0, 1000);
@@ -1157,8 +1175,12 @@ static void svc_i3c_master_start_xfer_locked(struct svc_i3c_master *master)
 
 		ret = svc_i3c_master_xfer(master, cmd->rnw, xfer->type,
 					  cmd->addr, cmd->in, cmd->out,
-					  cmd->len, &cmd->read_len,
+					  cmd->len, &cmd->actual_len,
 					  cmd->continued);
+		/* cmd->xfer is NULL if I2C or CCC transfer */
+		if (cmd->xfer)
+			cmd->xfer->actual_len = cmd->actual_len;
+
 		if (ret)
 			break;
 	}
@@ -1243,7 +1265,7 @@ static int svc_i3c_master_send_bdcast_ccc_cmd(struct svc_i3c_master *master,
 	cmd->in = NULL;
 	cmd->out = buf;
 	cmd->len = xfer_len;
-	cmd->read_len = 0;
+	cmd->actual_len = 0;
 	cmd->continued = false;
 
 	mutex_lock(&master->lock);
@@ -1263,7 +1285,7 @@ static int svc_i3c_master_send_direct_ccc_cmd(struct svc_i3c_master *master,
 					      struct i3c_ccc_cmd *ccc)
 {
 	unsigned int xfer_len = ccc->dests[0].payload.len;
-	unsigned int read_len = ccc->rnw ? xfer_len : 0;
+	unsigned int actual_len = ccc->rnw ? xfer_len : 0;
 	struct svc_i3c_xfer *xfer;
 	struct svc_i3c_cmd *cmd;
 	int ret;
@@ -1281,7 +1303,7 @@ static int svc_i3c_master_send_direct_ccc_cmd(struct svc_i3c_master *master,
 	cmd->in = NULL;
 	cmd->out = &ccc->id;
 	cmd->len = 1;
-	cmd->read_len = 0;
+	cmd->actual_len = 0;
 	cmd->continued = true;
 
 	/* Directed message */
@@ -1291,7 +1313,7 @@ static int svc_i3c_master_send_direct_ccc_cmd(struct svc_i3c_master *master,
 	cmd->in = ccc->rnw ? ccc->dests[0].payload.data : NULL;
 	cmd->out = ccc->rnw ? NULL : ccc->dests[0].payload.data,
 	cmd->len = xfer_len;
-	cmd->read_len = read_len;
+	cmd->actual_len = actual_len;
 	cmd->continued = false;
 
 	mutex_lock(&master->lock);
@@ -1300,8 +1322,8 @@ static int svc_i3c_master_send_direct_ccc_cmd(struct svc_i3c_master *master,
 		svc_i3c_master_dequeue_xfer(master, xfer);
 	mutex_unlock(&master->lock);
 
-	if (cmd->read_len != xfer_len)
-		ccc->dests[0].payload.len = cmd->read_len;
+	if (cmd->actual_len != xfer_len)
+		ccc->dests[0].payload.len = cmd->actual_len;
 
 	ret = xfer->ret;
 	svc_i3c_master_free_xfer(xfer);
@@ -1346,12 +1368,13 @@ static int svc_i3c_master_priv_xfers(struct i3c_dev_desc *dev,
 	for (i = 0; i < nxfers; i++) {
 		struct svc_i3c_cmd *cmd = &xfer->cmds[i];
 
+		cmd->xfer = &xfers[i];
 		cmd->addr = master->addrs[data->index];
 		cmd->rnw = xfers[i].rnw;
 		cmd->in = xfers[i].rnw ? xfers[i].data.in : NULL;
 		cmd->out = xfers[i].rnw ? NULL : xfers[i].data.out;
 		cmd->len = xfers[i].len;
-		cmd->read_len = xfers[i].rnw ? xfers[i].len : 0;
+		cmd->actual_len = xfers[i].rnw ? xfers[i].len : 0;
 		cmd->continued = (i + 1) < nxfers;
 	}
 
@@ -1391,7 +1414,7 @@ static int svc_i3c_master_i2c_xfers(struct i2c_dev_desc *dev,
 		cmd->in = cmd->rnw ? xfers[i].buf : NULL;
 		cmd->out = cmd->rnw ? NULL : xfers[i].buf;
 		cmd->len = xfers[i].len;
-		cmd->read_len = cmd->rnw ? xfers[i].len : 0;
+		cmd->actual_len = cmd->rnw ? xfers[i].len : 0;
 		cmd->continued = (i + 1 < nxfers);
 	}
 
@@ -1472,6 +1495,7 @@ static int svc_i3c_master_enable_ibi(struct i3c_dev_desc *dev)
 		return ret;
 	}
 
+	master->enabled_events |= SVC_I3C_EVENT_IBI;
 	svc_i3c_master_enable_interrupts(master, SVC_I3C_MINT_SLVSTART);
 
 	return i3c_master_enec_locked(m, dev->info.dyn_addr, I3C_CCC_EVENT_SIR);
@@ -1483,7 +1507,9 @@ static int svc_i3c_master_disable_ibi(struct i3c_dev_desc *dev)
 	struct svc_i3c_master *master = to_svc_i3c_master(m);
 	int ret;
 
-	svc_i3c_master_disable_interrupts(master);
+	master->enabled_events &= ~SVC_I3C_EVENT_IBI;
+	if (!master->enabled_events)
+		svc_i3c_master_disable_interrupts(master);
 
 	ret = i3c_master_disec_locked(m, dev->info.dyn_addr, I3C_CCC_EVENT_SIR);
 
@@ -1493,6 +1519,39 @@ static int svc_i3c_master_disable_ibi(struct i3c_dev_desc *dev)
 	return ret;
 }
 
+static int svc_i3c_master_enable_hotjoin(struct i3c_master_controller *m)
+{
+	struct svc_i3c_master *master = to_svc_i3c_master(m);
+	int ret;
+
+	ret = pm_runtime_resume_and_get(master->dev);
+	if (ret < 0) {
+		dev_err(master->dev, "<%s> Cannot get runtime PM.\n", __func__);
+		return ret;
+	}
+
+	master->enabled_events |= SVC_I3C_EVENT_HOTJOIN;
+
+	svc_i3c_master_enable_interrupts(master, SVC_I3C_MINT_SLVSTART);
+
+	return 0;
+}
+
+static int svc_i3c_master_disable_hotjoin(struct i3c_master_controller *m)
+{
+	struct svc_i3c_master *master = to_svc_i3c_master(m);
+
+	master->enabled_events &= ~SVC_I3C_EVENT_HOTJOIN;
+
+	if (!master->enabled_events)
+		svc_i3c_master_disable_interrupts(master);
+
+	pm_runtime_mark_last_busy(master->dev);
+	pm_runtime_put_autosuspend(master->dev);
+
+	return 0;
+}
+
 static void svc_i3c_master_recycle_ibi_slot(struct i3c_dev_desc *dev,
 					    struct i3c_ibi_slot *slot)
 {
@@ -1519,6 +1578,8 @@ static const struct i3c_master_controller_ops svc_i3c_master_ops = {
 	.recycle_ibi_slot = svc_i3c_master_recycle_ibi_slot,
 	.enable_ibi = svc_i3c_master_enable_ibi,
 	.disable_ibi = svc_i3c_master_disable_ibi,
+	.enable_hotjoin = svc_i3c_master_enable_hotjoin,
+	.disable_hotjoin = svc_i3c_master_disable_hotjoin,
 };
 
 static int svc_i3c_master_prepare_clks(struct svc_i3c_master *master)
diff --git a/drivers/iio/accel/Kconfig b/drivers/iio/accel/Kconfig
index f113dae59048..c9d7afe489e8 100644
--- a/drivers/iio/accel/Kconfig
+++ b/drivers/iio/accel/Kconfig
@@ -219,10 +219,12 @@ config BMA400
 
 config BMA400_I2C
 	tristate
+	select REGMAP_I2C
 	depends on BMA400
 
 config BMA400_SPI
 	tristate
+	select REGMAP_SPI
 	depends on BMA400
 
 config BMC150_ACCEL
@@ -260,10 +262,11 @@ config BMI088_ACCEL
 	select REGMAP
 	select BMI088_ACCEL_SPI
 	help
-	  Say yes here to build support for the Bosch BMI088 accelerometer.
+	  Say yes here to build support for the following Bosch accelerometers:
+	  BMI088, BMI085, BMI090L. Note that all of these are combo module that
+	  include both accelerometer and gyroscope.
 
-	  This is a combo module with both accelerometer and gyroscope. This
-	  driver only implements the accelerometer part, which has its own
+	  This driver only implements the accelerometer part, which has its own
 	  address and register map. BMG160 provides the gyroscope driver.
 
 config BMI088_ACCEL_SPI
diff --git a/drivers/iio/accel/adxl367.c b/drivers/iio/accel/adxl367.c
index 90b7ae6d42b7..484fe2e9fb17 100644
--- a/drivers/iio/accel/adxl367.c
+++ b/drivers/iio/accel/adxl367.c
@@ -1429,9 +1429,11 @@ static int adxl367_verify_devid(struct adxl367_state *st)
 	unsigned int val;
 	int ret;
 
-	ret = regmap_read_poll_timeout(st->regmap, ADXL367_REG_DEVID, val,
-				       val == ADXL367_DEVID_AD, 1000, 10000);
+	ret = regmap_read(st->regmap, ADXL367_REG_DEVID, &val);
 	if (ret)
+		return dev_err_probe(st->dev, ret, "Failed to read dev id\n");
+
+	if (val != ADXL367_DEVID_AD)
 		return dev_err_probe(st->dev, -ENODEV,
 				     "Invalid dev id 0x%02X, expected 0x%02X\n",
 				     val, ADXL367_DEVID_AD);
@@ -1510,6 +1512,8 @@ int adxl367_probe(struct device *dev, const struct adxl367_ops *ops,
 	if (ret)
 		return ret;
 
+	fsleep(15000);
+
 	ret = adxl367_verify_devid(st);
 	if (ret)
 		return ret;
diff --git a/drivers/iio/accel/adxl367_i2c.c b/drivers/iio/accel/adxl367_i2c.c
index b595fe94f3a3..62c74bdc0d77 100644
--- a/drivers/iio/accel/adxl367_i2c.c
+++ b/drivers/iio/accel/adxl367_i2c.c
@@ -11,7 +11,7 @@
 
 #include "adxl367.h"
 
-#define ADXL367_I2C_FIFO_DATA	0x42
+#define ADXL367_I2C_FIFO_DATA	0x18
 
 struct adxl367_i2c_state {
 	struct regmap *regmap;
diff --git a/drivers/iio/accel/bmi088-accel-core.c b/drivers/iio/accel/bmi088-accel-core.c
index 84edcc78d796..4d989708e6c3 100644
--- a/drivers/iio/accel/bmi088-accel-core.c
+++ b/drivers/iio/accel/bmi088-accel-core.c
@@ -2,6 +2,8 @@
 /*
  * 3-axis accelerometer driver supporting following Bosch-Sensortec chips:
  *  - BMI088
+ *  - BMI085
+ *  - BMI090L
  *
  * Copyright (c) 2018-2021, Topic Embedded Products
  */
diff --git a/drivers/iio/accel/bmi088-accel-spi.c b/drivers/iio/accel/bmi088-accel-spi.c
index ee540edd8412..7b419a7b2478 100644
--- a/drivers/iio/accel/bmi088-accel-spi.c
+++ b/drivers/iio/accel/bmi088-accel-spi.c
@@ -2,6 +2,8 @@
 /*
  * 3-axis accelerometer driver supporting following Bosch-Sensortec chips:
  *  - BMI088
+ *  - BMI085
+ *  - BMI090L
  *
  * Copyright (c) 2018-2020, Topic Embedded Products
  */
diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 35f9867da12c..3b73c509bd68 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -36,13 +36,29 @@ config AD4130
 	  To compile this driver as a module, choose M here: the module will be
 	  called ad4130.
 
+config AD7091R
+	tristate
+
 config AD7091R5
 	tristate "Analog Devices AD7091R5 ADC Driver"
 	depends on I2C
+	select AD7091R
 	select REGMAP_I2C
 	help
 	  Say yes here to build support for Analog Devices AD7091R-5 ADC.
 
+config AD7091R8
+	tristate "Analog Devices AD7091R8 ADC Driver"
+	depends on SPI
+	select AD7091R
+	select REGMAP_SPI
+	help
+	  Say yes here to build support for Analog Devices AD7091R-2, AD7091R-4,
+	  and AD7091R-8 ADC.
+
+	  To compile this driver as a module, choose M here: the module will be
+	  called ad7091r8.
+
 config AD7124
 	tristate "Analog Devices AD7124 and similar sigma-delta ADCs driver"
 	depends on SPI_MASTER
@@ -292,7 +308,7 @@ config ADI_AXI_ADC
 	select IIO_BUFFER
 	select IIO_BUFFER_HW_CONSUMER
 	select IIO_BUFFER_DMAENGINE
-	depends on HAS_IOMEM
+	select REGMAP_MMIO
 	depends on OF
 	help
 	  Say yes here to build support for Analog Devices Generic
@@ -745,6 +761,17 @@ config MAX1363
 	  To compile this driver as a module, choose M here: the module will be
 	  called max1363.
 
+config MAX34408
+	tristate "Maxim max34408/max344089 ADC driver"
+	depends on I2C
+	help
+	  Say yes here to build support for Maxim max34408/max34409 current sense
+	  monitor with 8-bits ADC interface with overcurrent delay/threshold and
+	  shutdown delay.
+
+	  To compile this driver as a module, choose M here: the module will be
+	  called max34408.
+
 config MAX77541_ADC
 	tristate "Analog Devices MAX77541 ADC driver"
 	depends on MFD_MAX77541
diff --git a/drivers/iio/adc/Makefile b/drivers/iio/adc/Makefile
index bee11d442af4..d2fda54a3259 100644
--- a/drivers/iio/adc/Makefile
+++ b/drivers/iio/adc/Makefile
@@ -7,7 +7,9 @@
 obj-$(CONFIG_AB8500_GPADC) += ab8500-gpadc.o
 obj-$(CONFIG_AD_SIGMA_DELTA) += ad_sigma_delta.o
 obj-$(CONFIG_AD4130) += ad4130.o
-obj-$(CONFIG_AD7091R5) += ad7091r5.o ad7091r-base.o
+obj-$(CONFIG_AD7091R) += ad7091r-base.o
+obj-$(CONFIG_AD7091R5) += ad7091r5.o
+obj-$(CONFIG_AD7091R8) += ad7091r8.o
 obj-$(CONFIG_AD7124) += ad7124.o
 obj-$(CONFIG_AD7192) += ad7192.o
 obj-$(CONFIG_AD7266) += ad7266.o
@@ -68,6 +70,7 @@ obj-$(CONFIG_MAX11205) += max11205.o
 obj-$(CONFIG_MAX11410) += max11410.o
 obj-$(CONFIG_MAX1241) += max1241.o
 obj-$(CONFIG_MAX1363) += max1363.o
+obj-$(CONFIG_MAX34408) += max34408.o
 obj-$(CONFIG_MAX77541_ADC) += max77541-adc.o
 obj-$(CONFIG_MAX9611) += max9611.o
 obj-$(CONFIG_MCP320X) += mcp320x.o
diff --git a/drivers/iio/adc/ad4130.c b/drivers/iio/adc/ad4130.c
index feb86fe6c422..62490424b6ae 100644
--- a/drivers/iio/adc/ad4130.c
+++ b/drivers/iio/adc/ad4130.c
@@ -1821,7 +1821,7 @@ static int ad4130_setup_int_clk(struct ad4130_state *st)
 {
 	struct device *dev = &st->spi->dev;
 	struct device_node *of_node = dev_of_node(dev);
-	struct clk_init_data init;
+	struct clk_init_data init = {};
 	const char *clk_name;
 	int ret;
 
@@ -1891,10 +1891,14 @@ static int ad4130_setup(struct iio_dev *indio_dev)
 		return ret;
 
 	/*
-	 * Configure all GPIOs for output. If configured, the interrupt function
-	 * of P2 takes priority over the GPIO out function.
+	 * Configure unused GPIOs for output. If configured, the interrupt
+	 * function of P2 takes priority over the GPIO out function.
 	 */
-	val =  AD4130_IO_CONTROL_GPIO_CTRL_MASK;
+	val = 0;
+	for (i = 0; i < AD4130_MAX_GPIOS; i++)
+		if (st->pins_fn[i + AD4130_AIN2_P1] == AD4130_PIN_FN_NONE)
+			val |= FIELD_PREP(AD4130_IO_CONTROL_GPIO_CTRL_MASK, BIT(i));
+
 	val |= FIELD_PREP(AD4130_IO_CONTROL_INT_PIN_SEL_MASK, st->int_pin_sel);
 
 	ret = regmap_write(st->regmap, AD4130_IO_CONTROL_REG, val);
diff --git a/drivers/iio/adc/ad7091r-base.c b/drivers/iio/adc/ad7091r-base.c
index 8e252cde735b..f4255b91acfc 100644
--- a/drivers/iio/adc/ad7091r-base.c
+++ b/drivers/iio/adc/ad7091r-base.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/bitops.h>
+#include <linux/bitfield.h>
 #include <linux/iio/events.h>
 #include <linux/iio/iio.h>
 #include <linux/interrupt.h>
@@ -15,67 +16,26 @@
 
 #include "ad7091r-base.h"
 
-#define AD7091R_REG_RESULT  0
-#define AD7091R_REG_CHANNEL 1
-#define AD7091R_REG_CONF    2
-#define AD7091R_REG_ALERT   3
-#define AD7091R_REG_CH_LOW_LIMIT(ch) ((ch) * 3 + 4)
-#define AD7091R_REG_CH_HIGH_LIMIT(ch) ((ch) * 3 + 5)
-#define AD7091R_REG_CH_HYSTERESIS(ch) ((ch) * 3 + 6)
-
-/* AD7091R_REG_RESULT */
-#define AD7091R_REG_RESULT_CH_ID(x)	    (((x) >> 13) & 0x3)
-#define AD7091R_REG_RESULT_CONV_RESULT(x)   ((x) & 0xfff)
-
-/* AD7091R_REG_CONF */
-#define AD7091R_REG_CONF_AUTO   BIT(8)
-#define AD7091R_REG_CONF_CMD    BIT(10)
-
-#define AD7091R_REG_CONF_MODE_MASK  \
-	(AD7091R_REG_CONF_AUTO | AD7091R_REG_CONF_CMD)
-
-enum ad7091r_mode {
-	AD7091R_MODE_SAMPLE,
-	AD7091R_MODE_COMMAND,
-	AD7091R_MODE_AUTOCYCLE,
+const struct iio_event_spec ad7091r_events[] = {
+	{
+		.type = IIO_EV_TYPE_THRESH,
+		.dir = IIO_EV_DIR_RISING,
+		.mask_separate = BIT(IIO_EV_INFO_VALUE) |
+				 BIT(IIO_EV_INFO_ENABLE),
+	},
+	{
+		.type = IIO_EV_TYPE_THRESH,
+		.dir = IIO_EV_DIR_FALLING,
+		.mask_separate = BIT(IIO_EV_INFO_VALUE) |
+				 BIT(IIO_EV_INFO_ENABLE),
+	},
+	{
+		.type = IIO_EV_TYPE_THRESH,
+		.dir = IIO_EV_DIR_EITHER,
+		.mask_separate = BIT(IIO_EV_INFO_HYSTERESIS),
+	},
 };
-
-struct ad7091r_state {
-	struct device *dev;
-	struct regmap *map;
-	struct regulator *vref;
-	const struct ad7091r_chip_info *chip_info;
-	enum ad7091r_mode mode;
-	struct mutex lock; /*lock to prevent concurent reads */
-};
-
-static int ad7091r_set_mode(struct ad7091r_state *st, enum ad7091r_mode mode)
-{
-	int ret, conf;
-
-	switch (mode) {
-	case AD7091R_MODE_SAMPLE:
-		conf = 0;
-		break;
-	case AD7091R_MODE_COMMAND:
-		conf = AD7091R_REG_CONF_CMD;
-		break;
-	case AD7091R_MODE_AUTOCYCLE:
-		conf = AD7091R_REG_CONF_AUTO;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	ret = regmap_update_bits(st->map, AD7091R_REG_CONF,
-				 AD7091R_REG_CONF_MODE_MASK, conf);
-	if (ret)
-		return ret;
-
-	st->mode = mode;
-
-	return 0;
-}
+EXPORT_SYMBOL_NS_GPL(ad7091r_events, IIO_AD7091R);
 
 static int ad7091r_set_channel(struct ad7091r_state *st, unsigned int channel)
 {
@@ -110,7 +70,7 @@ static int ad7091r_read_one(struct iio_dev *iio_dev,
 	if (ret)
 		return ret;
 
-	if (AD7091R_REG_RESULT_CH_ID(val) != channel)
+	if (st->chip_info->reg_result_chan_id(val) != channel)
 		return -EIO;
 
 	*read_val = AD7091R_REG_RESULT_CONV_RESULT(val);
@@ -168,14 +128,148 @@ unlock:
 	return ret;
 }
 
+static int ad7091r_read_event_config(struct iio_dev *indio_dev,
+				     const struct iio_chan_spec *chan,
+				     enum iio_event_type type,
+				     enum iio_event_direction dir)
+{
+	struct ad7091r_state *st = iio_priv(indio_dev);
+	int val, ret;
+
+	switch (dir) {
+	case IIO_EV_DIR_RISING:
+		ret = regmap_read(st->map,
+				  AD7091R_REG_CH_HIGH_LIMIT(chan->channel),
+				  &val);
+		if (ret)
+			return ret;
+		return val != AD7091R_HIGH_LIMIT;
+	case IIO_EV_DIR_FALLING:
+		ret = regmap_read(st->map,
+				  AD7091R_REG_CH_LOW_LIMIT(chan->channel),
+				  &val);
+		if (ret)
+			return ret;
+		return val != AD7091R_LOW_LIMIT;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int ad7091r_write_event_config(struct iio_dev *indio_dev,
+				      const struct iio_chan_spec *chan,
+				      enum iio_event_type type,
+				      enum iio_event_direction dir, int state)
+{
+	struct ad7091r_state *st = iio_priv(indio_dev);
+
+	if (state) {
+		return regmap_set_bits(st->map, AD7091R_REG_CONF,
+				       AD7091R_REG_CONF_ALERT_EN);
+	} else {
+		/*
+		 * Set thresholds either to 0 or to 2^12 - 1 as appropriate to
+		 * prevent alerts and thus disable event generation.
+		 */
+		switch (dir) {
+		case IIO_EV_DIR_RISING:
+			return regmap_write(st->map,
+					    AD7091R_REG_CH_HIGH_LIMIT(chan->channel),
+					    AD7091R_HIGH_LIMIT);
+		case IIO_EV_DIR_FALLING:
+			return regmap_write(st->map,
+					    AD7091R_REG_CH_LOW_LIMIT(chan->channel),
+					    AD7091R_LOW_LIMIT);
+		default:
+			return -EINVAL;
+		}
+	}
+}
+
+static int ad7091r_read_event_value(struct iio_dev *indio_dev,
+				    const struct iio_chan_spec *chan,
+				    enum iio_event_type type,
+				    enum iio_event_direction dir,
+				    enum iio_event_info info, int *val, int *val2)
+{
+	struct ad7091r_state *st = iio_priv(indio_dev);
+	int ret;
+
+	switch (info) {
+	case IIO_EV_INFO_VALUE:
+		switch (dir) {
+		case IIO_EV_DIR_RISING:
+			ret = regmap_read(st->map,
+					  AD7091R_REG_CH_HIGH_LIMIT(chan->channel),
+					  val);
+			if (ret)
+				return ret;
+			return IIO_VAL_INT;
+		case IIO_EV_DIR_FALLING:
+			ret = regmap_read(st->map,
+					  AD7091R_REG_CH_LOW_LIMIT(chan->channel),
+					  val);
+			if (ret)
+				return ret;
+			return IIO_VAL_INT;
+		default:
+			return -EINVAL;
+		}
+	case IIO_EV_INFO_HYSTERESIS:
+		ret = regmap_read(st->map,
+				  AD7091R_REG_CH_HYSTERESIS(chan->channel),
+				  val);
+		if (ret)
+			return ret;
+		return IIO_VAL_INT;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int ad7091r_write_event_value(struct iio_dev *indio_dev,
+				     const struct iio_chan_spec *chan,
+				     enum iio_event_type type,
+				     enum iio_event_direction dir,
+				     enum iio_event_info info, int val, int val2)
+{
+	struct ad7091r_state *st = iio_priv(indio_dev);
+
+	switch (info) {
+	case IIO_EV_INFO_VALUE:
+		switch (dir) {
+		case IIO_EV_DIR_RISING:
+			return regmap_write(st->map,
+					    AD7091R_REG_CH_HIGH_LIMIT(chan->channel),
+					    val);
+		case IIO_EV_DIR_FALLING:
+			return regmap_write(st->map,
+					    AD7091R_REG_CH_LOW_LIMIT(chan->channel),
+					    val);
+		default:
+			return -EINVAL;
+		}
+	case IIO_EV_INFO_HYSTERESIS:
+		return regmap_write(st->map,
+				    AD7091R_REG_CH_HYSTERESIS(chan->channel),
+				    val);
+	default:
+		return -EINVAL;
+	}
+}
+
 static const struct iio_info ad7091r_info = {
 	.read_raw = ad7091r_read_raw,
+	.read_event_config = &ad7091r_read_event_config,
+	.write_event_config = &ad7091r_write_event_config,
+	.read_event_value = &ad7091r_read_event_value,
+	.write_event_value = &ad7091r_write_event_value,
 };
 
 static irqreturn_t ad7091r_event_handler(int irq, void *private)
 {
-	struct ad7091r_state *st = (struct ad7091r_state *) private;
-	struct iio_dev *iio_dev = dev_get_drvdata(st->dev);
+	struct iio_dev *iio_dev = private;
+	struct ad7091r_state *st = iio_priv(iio_dev);
 	unsigned int i, read_val;
 	int ret;
 	s64 timestamp = iio_get_time_ns(iio_dev);
@@ -207,9 +301,8 @@ static void ad7091r_remove(void *data)
 	regulator_disable(st->vref);
 }
 
-int ad7091r_probe(struct device *dev, const char *name,
-		const struct ad7091r_chip_info *chip_info,
-		struct regmap *map, int irq)
+int ad7091r_probe(struct device *dev, const struct ad7091r_init_info *init_info,
+		  int irq)
 {
 	struct iio_dev *iio_dev;
 	struct ad7091r_state *st;
@@ -221,29 +314,54 @@ int ad7091r_probe(struct device *dev, const char *name,
 
 	st = iio_priv(iio_dev);
 	st->dev = dev;
-	st->chip_info = chip_info;
-	st->map = map;
+	init_info->init_adc_regmap(st, init_info->regmap_config);
+	if (IS_ERR(st->map))
+		return dev_err_probe(st->dev, PTR_ERR(st->map),
+				     "Error initializing regmap\n");
 
-	iio_dev->name = name;
 	iio_dev->info = &ad7091r_info;
 	iio_dev->modes = INDIO_DIRECT_MODE;
 
-	iio_dev->num_channels = chip_info->num_channels;
-	iio_dev->channels = chip_info->channels;
+	if (init_info->setup) {
+		ret = init_info->setup(st);
+		if (ret < 0)
+			return ret;
+	}
 
 	if (irq) {
+		st->chip_info = init_info->info_irq;
+		ret = regmap_update_bits(st->map, AD7091R_REG_CONF,
+					 AD7091R_REG_CONF_ALERT_EN, BIT(4));
+		if (ret)
+			return ret;
+
 		ret = devm_request_threaded_irq(dev, irq, NULL,
-				ad7091r_event_handler,
-				IRQF_TRIGGER_FALLING | IRQF_ONESHOT, name, st);
+						ad7091r_event_handler,
+						IRQF_TRIGGER_FALLING |
+						IRQF_ONESHOT,
+						st->chip_info->name, iio_dev);
 		if (ret)
 			return ret;
+	} else {
+		st->chip_info = init_info->info_no_irq;
 	}
 
+	iio_dev->name = st->chip_info->name;
+	iio_dev->num_channels = st->chip_info->num_channels;
+	iio_dev->channels = st->chip_info->channels;
+
 	st->vref = devm_regulator_get_optional(dev, "vref");
 	if (IS_ERR(st->vref)) {
 		if (PTR_ERR(st->vref) == -EPROBE_DEFER)
 			return -EPROBE_DEFER;
+
 		st->vref = NULL;
+		/* Enable internal vref */
+		ret = regmap_set_bits(st->map, AD7091R_REG_CONF,
+				      AD7091R_REG_CONF_INT_VREF);
+		if (ret)
+			return dev_err_probe(st->dev, ret,
+					     "Error on enable internal reference\n");
 	} else {
 		ret = regulator_enable(st->vref);
 		if (ret)
@@ -254,7 +372,7 @@ int ad7091r_probe(struct device *dev, const char *name,
 	}
 
 	/* Use command mode by default to convert only desired channels*/
-	ret = ad7091r_set_mode(st, AD7091R_MODE_COMMAND);
+	ret = st->chip_info->set_mode(st, AD7091R_MODE_COMMAND);
 	if (ret)
 		return ret;
 
@@ -262,7 +380,7 @@ int ad7091r_probe(struct device *dev, const char *name,
 }
 EXPORT_SYMBOL_NS_GPL(ad7091r_probe, IIO_AD7091R);
 
-static bool ad7091r_writeable_reg(struct device *dev, unsigned int reg)
+bool ad7091r_writeable_reg(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
 	case AD7091R_REG_RESULT:
@@ -272,8 +390,9 @@ static bool ad7091r_writeable_reg(struct device *dev, unsigned int reg)
 		return true;
 	}
 }
+EXPORT_SYMBOL_NS_GPL(ad7091r_writeable_reg, IIO_AD7091R);
 
-static bool ad7091r_volatile_reg(struct device *dev, unsigned int reg)
+bool ad7091r_volatile_reg(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
 	case AD7091R_REG_RESULT:
@@ -283,14 +402,7 @@ static bool ad7091r_volatile_reg(struct device *dev, unsigned int reg)
 		return false;
 	}
 }
-
-const struct regmap_config ad7091r_regmap_config = {
-	.reg_bits = 8,
-	.val_bits = 16,
-	.writeable_reg = ad7091r_writeable_reg,
-	.volatile_reg = ad7091r_volatile_reg,
-};
-EXPORT_SYMBOL_NS_GPL(ad7091r_regmap_config, IIO_AD7091R);
+EXPORT_SYMBOL_NS_GPL(ad7091r_volatile_reg, IIO_AD7091R);
 
 MODULE_AUTHOR("Beniamin Bia <beniamin.bia@analog.com>");
 MODULE_DESCRIPTION("Analog Devices AD7091Rx multi-channel converters");
diff --git a/drivers/iio/adc/ad7091r-base.h b/drivers/iio/adc/ad7091r-base.h
index 509748aef9b1..696bf7a897bb 100644
--- a/drivers/iio/adc/ad7091r-base.h
+++ b/drivers/iio/adc/ad7091r-base.h
@@ -8,19 +8,92 @@
 #ifndef __DRIVERS_IIO_ADC_AD7091R_BASE_H__
 #define __DRIVERS_IIO_ADC_AD7091R_BASE_H__
 
+#include <linux/regmap.h>
+
+#define AD7091R_REG_RESULT  0
+#define AD7091R_REG_CHANNEL 1
+#define AD7091R_REG_CONF    2
+#define AD7091R_REG_ALERT   3
+#define AD7091R_REG_CH_LOW_LIMIT(ch) ((ch) * 3 + 4)
+#define AD7091R_REG_CH_HIGH_LIMIT(ch) ((ch) * 3 + 5)
+#define AD7091R_REG_CH_HYSTERESIS(ch) ((ch) * 3 + 6)
+
+/* AD7091R_REG_RESULT */
+#define AD7091R5_REG_RESULT_CH_ID(x)	    (((x) >> 13) & 0x3)
+#define AD7091R8_REG_RESULT_CH_ID(x)	    (((x) >> 13) & 0x7)
+#define AD7091R_REG_RESULT_CONV_RESULT(x)   ((x) & 0xfff)
+
+/* AD7091R_REG_CONF */
+#define AD7091R_REG_CONF_INT_VREF	BIT(0)
+#define AD7091R_REG_CONF_ALERT_EN	BIT(4)
+#define AD7091R_REG_CONF_AUTO		BIT(8)
+#define AD7091R_REG_CONF_CMD		BIT(10)
+
+#define AD7091R_REG_CONF_MODE_MASK  \
+	(AD7091R_REG_CONF_AUTO | AD7091R_REG_CONF_CMD)
+
+/* AD7091R_REG_CH_LIMIT */
+#define AD7091R_HIGH_LIMIT		0xFFF
+#define AD7091R_LOW_LIMIT		0x0
+
+#define AD7091R_CHANNEL(idx, bits, ev, num_ev) {			\
+	.type = IIO_VOLTAGE,						\
+	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),			\
+	.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),		\
+	.indexed = 1,							\
+	.channel = idx,							\
+	.event_spec = ev,						\
+	.num_event_specs = num_ev,					\
+	.scan_type.storagebits = 16,					\
+	.scan_type.realbits = bits,					\
+}
+
 struct device;
-struct ad7091r_state;
+struct gpio_desc;
+
+enum ad7091r_mode {
+	AD7091R_MODE_SAMPLE,
+	AD7091R_MODE_COMMAND,
+	AD7091R_MODE_AUTOCYCLE,
+};
+
+struct ad7091r_state {
+	struct device *dev;
+	struct regmap *map;
+	struct gpio_desc *convst_gpio;
+	struct gpio_desc *reset_gpio;
+	struct regulator *vref;
+	const struct ad7091r_chip_info *chip_info;
+	enum ad7091r_mode mode;
+	struct mutex lock; /*lock to prevent concurent reads */
+	__be16 tx_buf __aligned(IIO_DMA_MINALIGN);
+	__be16 rx_buf;
+};
 
 struct ad7091r_chip_info {
+	const char *name;
 	unsigned int num_channels;
 	const struct iio_chan_spec *channels;
 	unsigned int vref_mV;
+	unsigned int (*reg_result_chan_id)(unsigned int val);
+	int (*set_mode)(struct ad7091r_state *st, enum ad7091r_mode mode);
 };
 
-extern const struct regmap_config ad7091r_regmap_config;
+struct ad7091r_init_info {
+	const struct ad7091r_chip_info *info_irq;
+	const struct ad7091r_chip_info *info_no_irq;
+	const struct regmap_config *regmap_config;
+	void (*init_adc_regmap)(struct ad7091r_state *st,
+				const struct regmap_config *regmap_conf);
+	int (*setup)(struct ad7091r_state *st);
+};
+
+extern const struct iio_event_spec ad7091r_events[3];
+
+int ad7091r_probe(struct device *dev, const struct ad7091r_init_info *init_info,
+		  int irq);
 
-int ad7091r_probe(struct device *dev, const char *name,
-		const struct ad7091r_chip_info *chip_info,
-		struct regmap *map, int irq);
+bool ad7091r_volatile_reg(struct device *dev, unsigned int reg);
+bool ad7091r_writeable_reg(struct device *dev, unsigned int reg);
 
 #endif /* __DRIVERS_IIO_ADC_AD7091R_BASE_H__ */
diff --git a/drivers/iio/adc/ad7091r5.c b/drivers/iio/adc/ad7091r5.c
index 2f048527b7b7..a75837334157 100644
--- a/drivers/iio/adc/ad7091r5.c
+++ b/drivers/iio/adc/ad7091r5.c
@@ -12,42 +12,11 @@
 
 #include "ad7091r-base.h"
 
-static const struct iio_event_spec ad7091r5_events[] = {
-	{
-		.type = IIO_EV_TYPE_THRESH,
-		.dir = IIO_EV_DIR_RISING,
-		.mask_separate = BIT(IIO_EV_INFO_VALUE) |
-				 BIT(IIO_EV_INFO_ENABLE),
-	},
-	{
-		.type = IIO_EV_TYPE_THRESH,
-		.dir = IIO_EV_DIR_FALLING,
-		.mask_separate = BIT(IIO_EV_INFO_VALUE) |
-				 BIT(IIO_EV_INFO_ENABLE),
-	},
-	{
-		.type = IIO_EV_TYPE_THRESH,
-		.dir = IIO_EV_DIR_EITHER,
-		.mask_separate = BIT(IIO_EV_INFO_HYSTERESIS),
-	},
-};
-
-#define AD7091R_CHANNEL(idx, bits, ev, num_ev) { \
-	.type = IIO_VOLTAGE, \
-	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW), \
-	.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), \
-	.indexed = 1, \
-	.channel = idx, \
-	.event_spec = ev, \
-	.num_event_specs = num_ev, \
-	.scan_type.storagebits = 16, \
-	.scan_type.realbits = bits, \
-}
 static const struct iio_chan_spec ad7091r5_channels_irq[] = {
-	AD7091R_CHANNEL(0, 12, ad7091r5_events, ARRAY_SIZE(ad7091r5_events)),
-	AD7091R_CHANNEL(1, 12, ad7091r5_events, ARRAY_SIZE(ad7091r5_events)),
-	AD7091R_CHANNEL(2, 12, ad7091r5_events, ARRAY_SIZE(ad7091r5_events)),
-	AD7091R_CHANNEL(3, 12, ad7091r5_events, ARRAY_SIZE(ad7091r5_events)),
+	AD7091R_CHANNEL(0, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(1, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(2, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(3, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
 };
 
 static const struct iio_chan_spec ad7091r5_channels_noirq[] = {
@@ -57,43 +26,98 @@ static const struct iio_chan_spec ad7091r5_channels_noirq[] = {
 	AD7091R_CHANNEL(3, 12, NULL, 0),
 };
 
+static int ad7091r5_set_mode(struct ad7091r_state *st, enum ad7091r_mode mode)
+{
+	int ret, conf;
+
+	switch (mode) {
+	case AD7091R_MODE_SAMPLE:
+		conf = 0;
+		break;
+	case AD7091R_MODE_COMMAND:
+		conf = AD7091R_REG_CONF_CMD;
+		break;
+	case AD7091R_MODE_AUTOCYCLE:
+		conf = AD7091R_REG_CONF_AUTO;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ret = regmap_update_bits(st->map, AD7091R_REG_CONF,
+				 AD7091R_REG_CONF_MODE_MASK, conf);
+	if (ret)
+		return ret;
+
+	st->mode = mode;
+
+	return 0;
+}
+
+static unsigned int ad7091r5_reg_result_chan_id(unsigned int val)
+{
+	return AD7091R5_REG_RESULT_CH_ID(val);
+}
+
 static const struct ad7091r_chip_info ad7091r5_chip_info_irq = {
+	.name = "ad7091r-5",
 	.channels = ad7091r5_channels_irq,
 	.num_channels = ARRAY_SIZE(ad7091r5_channels_irq),
 	.vref_mV = 2500,
+	.reg_result_chan_id = &ad7091r5_reg_result_chan_id,
+	.set_mode = &ad7091r5_set_mode,
 };
 
 static const struct ad7091r_chip_info ad7091r5_chip_info_noirq = {
+	.name = "ad7091r-5",
 	.channels = ad7091r5_channels_noirq,
 	.num_channels = ARRAY_SIZE(ad7091r5_channels_noirq),
 	.vref_mV = 2500,
+	.reg_result_chan_id = &ad7091r5_reg_result_chan_id,
+	.set_mode = &ad7091r5_set_mode,
 };
 
-static int ad7091r5_i2c_probe(struct i2c_client *i2c)
+static const struct regmap_config ad7091r_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 16,
+	.writeable_reg = ad7091r_writeable_reg,
+	.volatile_reg = ad7091r_volatile_reg,
+};
+
+static void ad7091r5_regmap_init(struct ad7091r_state *st,
+				 const struct regmap_config *regmap_conf)
 {
-	const struct i2c_device_id *id = i2c_client_get_device_id(i2c);
-	const struct ad7091r_chip_info *chip_info;
-	struct regmap *map = devm_regmap_init_i2c(i2c, &ad7091r_regmap_config);
+	struct i2c_client *i2c = container_of(st->dev, struct i2c_client, dev);
 
-	if (IS_ERR(map))
-		return PTR_ERR(map);
+	st->map = devm_regmap_init_i2c(i2c, regmap_conf);
+}
+
+static struct ad7091r_init_info ad7091r5_init_info = {
+	.info_irq = &ad7091r5_chip_info_irq,
+	.info_no_irq = &ad7091r5_chip_info_noirq,
+	.regmap_config = &ad7091r_regmap_config,
+	.init_adc_regmap = &ad7091r5_regmap_init
+};
+
+static int ad7091r5_i2c_probe(struct i2c_client *i2c)
+{
+	const struct ad7091r_init_info *init_info;
 
-	if (i2c->irq)
-		chip_info = &ad7091r5_chip_info_irq;
-	else
-		chip_info = &ad7091r5_chip_info_noirq;
+	init_info = i2c_get_match_data(i2c);
+	if (!init_info)
+		return -EINVAL;
 
-	return ad7091r_probe(&i2c->dev, id->name, chip_info, map, i2c->irq);
+	return ad7091r_probe(&i2c->dev, init_info, i2c->irq);
 }
 
 static const struct of_device_id ad7091r5_dt_ids[] = {
-	{ .compatible = "adi,ad7091r5" },
+	{ .compatible = "adi,ad7091r5", .data = &ad7091r5_init_info },
 	{},
 };
 MODULE_DEVICE_TABLE(of, ad7091r5_dt_ids);
 
 static const struct i2c_device_id ad7091r5_i2c_ids[] = {
-	{"ad7091r5", 0},
+	{"ad7091r5", (kernel_ulong_t)&ad7091r5_init_info },
 	{}
 };
 MODULE_DEVICE_TABLE(i2c, ad7091r5_i2c_ids);
diff --git a/drivers/iio/adc/ad7091r8.c b/drivers/iio/adc/ad7091r8.c
new file mode 100644
index 000000000000..700564305057
--- /dev/null
+++ b/drivers/iio/adc/ad7091r8.c
@@ -0,0 +1,272 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Analog Devices AD7091R8 12-bit SAR ADC driver
+ *
+ * Copyright 2023 Analog Devices Inc.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/iio/iio.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/gpio/consumer.h>
+#include <linux/spi/spi.h>
+
+#include "ad7091r-base.h"
+
+#define AD7091R8_REG_ADDR_MSK				GENMASK(15, 11)
+#define AD7091R8_RD_WR_FLAG_MSK				BIT(10)
+#define AD7091R8_REG_DATA_MSK				GENMASK(9, 0)
+
+#define AD7091R_SPI_REGMAP_CONFIG(n) {					\
+	.reg_bits = 8,							\
+	.val_bits = 16,							\
+	.volatile_reg = ad7091r_volatile_reg,				\
+	.writeable_reg = ad7091r_writeable_reg,				\
+	.max_register = AD7091R_REG_CH_HYSTERESIS(n),			\
+}
+
+static int ad7091r8_set_mode(struct ad7091r_state *st, enum ad7091r_mode mode)
+{
+	/* AD7091R-2/-4/-8 don't set sample/command/autocycle mode in conf reg */
+	st->mode = mode;
+	return 0;
+}
+
+static unsigned int ad7091r8_reg_result_chan_id(unsigned int val)
+{
+	return AD7091R8_REG_RESULT_CH_ID(val);
+}
+
+#define AD7091R_SPI_CHIP_INFO(_n, _name) {				\
+	.name = _name,							\
+	.channels = ad7091r##_n##_channels,				\
+	.num_channels = ARRAY_SIZE(ad7091r##_n##_channels),		\
+	.vref_mV = 2500,						\
+	.reg_result_chan_id = &ad7091r8_reg_result_chan_id,	\
+	.set_mode = &ad7091r8_set_mode,				\
+}
+
+#define AD7091R_SPI_CHIP_INFO_IRQ(_n, _name) {				\
+	.name = _name,							\
+	.channels = ad7091r##_n##_channels_irq,				\
+	.num_channels = ARRAY_SIZE(ad7091r##_n##_channels_irq),		\
+	.vref_mV = 2500,						\
+	.reg_result_chan_id = &ad7091r8_reg_result_chan_id,	\
+	.set_mode = &ad7091r8_set_mode,				\
+}
+
+enum ad7091r8_info_ids {
+	AD7091R2_INFO,
+	AD7091R4_INFO,
+	AD7091R4_INFO_IRQ,
+	AD7091R8_INFO,
+	AD7091R8_INFO_IRQ,
+};
+
+static const struct iio_chan_spec ad7091r2_channels[] = {
+	AD7091R_CHANNEL(0, 12, NULL, 0),
+	AD7091R_CHANNEL(1, 12, NULL, 0),
+};
+
+static const struct iio_chan_spec ad7091r4_channels[] = {
+	AD7091R_CHANNEL(0, 12, NULL, 0),
+	AD7091R_CHANNEL(1, 12, NULL, 0),
+	AD7091R_CHANNEL(2, 12, NULL, 0),
+	AD7091R_CHANNEL(3, 12, NULL, 0),
+};
+
+static const struct iio_chan_spec ad7091r4_channels_irq[] = {
+	AD7091R_CHANNEL(0, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(1, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(2, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(3, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+};
+
+static const struct iio_chan_spec ad7091r8_channels[] = {
+	AD7091R_CHANNEL(0, 12, NULL, 0),
+	AD7091R_CHANNEL(1, 12, NULL, 0),
+	AD7091R_CHANNEL(2, 12, NULL, 0),
+	AD7091R_CHANNEL(3, 12, NULL, 0),
+	AD7091R_CHANNEL(4, 12, NULL, 0),
+	AD7091R_CHANNEL(5, 12, NULL, 0),
+	AD7091R_CHANNEL(6, 12, NULL, 0),
+	AD7091R_CHANNEL(7, 12, NULL, 0),
+};
+
+static const struct iio_chan_spec ad7091r8_channels_irq[] = {
+	AD7091R_CHANNEL(0, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(1, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(2, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(3, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(4, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(5, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(6, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(7, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+};
+
+static void ad7091r_pulse_convst(struct ad7091r_state *st)
+{
+	gpiod_set_value_cansleep(st->convst_gpio, 1);
+	gpiod_set_value_cansleep(st->convst_gpio, 0);
+}
+
+static int ad7091r_regmap_bus_reg_read(void *context, unsigned int reg,
+				       unsigned int *val)
+{
+	struct ad7091r_state *st = context;
+	struct spi_device *spi = container_of(st->dev, struct spi_device, dev);
+	int ret;
+
+	struct spi_transfer t[] = {
+		{
+			.tx_buf = &st->tx_buf,
+			.len = 2,
+			.cs_change = 1,
+		}, {
+			.rx_buf = &st->rx_buf,
+			.len = 2,
+		}
+	};
+
+	if (reg == AD7091R_REG_RESULT)
+		ad7091r_pulse_convst(st);
+
+	st->tx_buf = cpu_to_be16(reg << 11);
+
+	ret = spi_sync_transfer(spi, t, ARRAY_SIZE(t));
+	if (ret < 0)
+		return ret;
+
+	*val = be16_to_cpu(st->rx_buf);
+	return 0;
+}
+
+static int ad7091r_regmap_bus_reg_write(void *context, unsigned int reg,
+					unsigned int val)
+{
+	struct ad7091r_state *st = context;
+	struct spi_device *spi = container_of(st->dev, struct spi_device, dev);
+
+	/*
+	 * AD7091R-2/-4/-8 protocol (datasheet page 31) is to do a single SPI
+	 * transfer with reg address set in bits B15:B11 and value set in B9:B0.
+	 */
+	st->tx_buf = cpu_to_be16(FIELD_PREP(AD7091R8_REG_DATA_MSK, val) |
+				 FIELD_PREP(AD7091R8_RD_WR_FLAG_MSK, 1) |
+				 FIELD_PREP(AD7091R8_REG_ADDR_MSK, reg));
+
+	return spi_write(spi, &st->tx_buf, 2);
+}
+
+static struct regmap_bus ad7091r8_regmap_bus = {
+	.reg_read = ad7091r_regmap_bus_reg_read,
+	.reg_write = ad7091r_regmap_bus_reg_write,
+	.reg_format_endian_default = REGMAP_ENDIAN_BIG,
+	.val_format_endian_default = REGMAP_ENDIAN_BIG,
+};
+
+static const struct ad7091r_chip_info ad7091r8_infos[] = {
+	[AD7091R2_INFO] = AD7091R_SPI_CHIP_INFO(2, "ad7091r-2"),
+	[AD7091R4_INFO] = AD7091R_SPI_CHIP_INFO(4, "ad7091r-4"),
+	[AD7091R4_INFO_IRQ] = AD7091R_SPI_CHIP_INFO_IRQ(4, "ad7091r-4"),
+	[AD7091R8_INFO] = AD7091R_SPI_CHIP_INFO(8, "ad7091r-8"),
+	[AD7091R8_INFO_IRQ] = AD7091R_SPI_CHIP_INFO_IRQ(8, "ad7091r-8")
+};
+
+static const struct regmap_config ad7091r2_reg_conf = AD7091R_SPI_REGMAP_CONFIG(2);
+static const struct regmap_config ad7091r4_reg_conf = AD7091R_SPI_REGMAP_CONFIG(4);
+static const struct regmap_config ad7091r8_reg_conf = AD7091R_SPI_REGMAP_CONFIG(8);
+
+static void ad7091r8_regmap_init(struct ad7091r_state *st,
+				 const struct regmap_config *regmap_conf)
+{
+	st->map = devm_regmap_init(st->dev, &ad7091r8_regmap_bus, st,
+				   regmap_conf);
+}
+
+static int ad7091r8_gpio_setup(struct ad7091r_state *st)
+{
+	st->convst_gpio = devm_gpiod_get(st->dev, "convst", GPIOD_OUT_LOW);
+	if (IS_ERR(st->convst_gpio))
+		return dev_err_probe(st->dev, PTR_ERR(st->convst_gpio),
+				     "Error getting convst GPIO\n");
+
+	st->reset_gpio = devm_gpiod_get_optional(st->dev, "reset",
+						 GPIOD_OUT_HIGH);
+	if (IS_ERR(st->reset_gpio))
+		return dev_err_probe(st->dev, PTR_ERR(st->reset_gpio),
+				     "Error on requesting reset GPIO\n");
+
+	if (st->reset_gpio) {
+		fsleep(20);
+		gpiod_set_value_cansleep(st->reset_gpio, 0);
+	}
+
+	return 0;
+}
+
+static struct ad7091r_init_info ad7091r2_init_info = {
+	.info_no_irq = &ad7091r8_infos[AD7091R2_INFO],
+	.regmap_config = &ad7091r2_reg_conf,
+	.init_adc_regmap = &ad7091r8_regmap_init,
+	.setup = &ad7091r8_gpio_setup
+};
+
+static struct ad7091r_init_info ad7091r4_init_info = {
+	.info_no_irq = &ad7091r8_infos[AD7091R4_INFO],
+	.info_irq = &ad7091r8_infos[AD7091R4_INFO_IRQ],
+	.regmap_config = &ad7091r4_reg_conf,
+	.init_adc_regmap = &ad7091r8_regmap_init,
+	.setup = &ad7091r8_gpio_setup
+};
+
+static struct ad7091r_init_info ad7091r8_init_info = {
+	.info_no_irq = &ad7091r8_infos[AD7091R8_INFO],
+	.info_irq = &ad7091r8_infos[AD7091R8_INFO_IRQ],
+	.regmap_config = &ad7091r8_reg_conf,
+	.init_adc_regmap = &ad7091r8_regmap_init,
+	.setup = &ad7091r8_gpio_setup
+};
+
+static int ad7091r8_spi_probe(struct spi_device *spi)
+{
+	const struct ad7091r_init_info *init_info;
+
+	init_info = spi_get_device_match_data(spi);
+	if (!init_info)
+		return -EINVAL;
+
+	return ad7091r_probe(&spi->dev, init_info, spi->irq);
+}
+
+static const struct of_device_id ad7091r8_of_match[] = {
+	{ .compatible = "adi,ad7091r2", .data = &ad7091r2_init_info },
+	{ .compatible = "adi,ad7091r4", .data = &ad7091r4_init_info },
+	{ .compatible = "adi,ad7091r8", .data = &ad7091r8_init_info },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ad7091r8_of_match);
+
+static const struct spi_device_id ad7091r8_spi_id[] = {
+	{ "ad7091r2", (kernel_ulong_t)&ad7091r2_init_info },
+	{ "ad7091r4", (kernel_ulong_t)&ad7091r4_init_info },
+	{ "ad7091r8", (kernel_ulong_t)&ad7091r8_init_info },
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, ad7091r8_spi_id);
+
+static struct spi_driver ad7091r8_driver = {
+	.driver = {
+		.name = "ad7091r8",
+		.of_match_table = ad7091r8_of_match,
+	},
+	.probe = ad7091r8_spi_probe,
+	.id_table = ad7091r8_spi_id,
+};
+module_spi_driver(ad7091r8_driver);
+
+MODULE_AUTHOR("Marcelo Schmitt <marcelo.schmitt@analog.com>");
+MODULE_DESCRIPTION("Analog Devices AD7091R8 ADC driver");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(IIO_AD7091R);
diff --git a/drivers/iio/adc/ad9467.c b/drivers/iio/adc/ad9467.c
index 39eccc28debe..6581fce4ba95 100644
--- a/drivers/iio/adc/ad9467.c
+++ b/drivers/iio/adc/ad9467.c
@@ -4,8 +4,9 @@
  *
  * Copyright 2012-2020 Analog Devices Inc.
  */
-
+#include <linux/cleanup.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -100,12 +101,6 @@
 #define AD9467_DEF_OUTPUT_MODE		0x08
 #define AD9467_REG_VREF_MASK		0x0F
 
-enum {
-	ID_AD9265,
-	ID_AD9434,
-	ID_AD9467,
-};
-
 struct ad9467_chip_info {
 	struct adi_axi_adc_chip_info	axi_adc_info;
 	unsigned int			default_output_mode;
@@ -119,9 +114,11 @@ struct ad9467_state {
 	struct spi_device		*spi;
 	struct clk			*clk;
 	unsigned int			output_mode;
+	unsigned int                    (*scales)[2];
 
 	struct gpio_desc		*pwrdown_gpio;
-	struct gpio_desc		*reset_gpio;
+	/* ensure consistent state obtained on multiple related accesses */
+	struct mutex			lock;
 };
 
 static int ad9467_spi_read(struct spi_device *spi, unsigned int reg)
@@ -161,11 +158,13 @@ static int ad9467_reg_access(struct adi_axi_adc_conv *conv, unsigned int reg,
 	struct spi_device *spi = st->spi;
 	int ret;
 
-	if (readval == NULL) {
+	if (!readval) {
+		guard(mutex)(&st->lock);
 		ret = ad9467_spi_write(spi, reg, writeval);
-		ad9467_spi_write(spi, AN877_ADC_REG_TRANSFER,
-				 AN877_ADC_TRANSFER_SYNC);
-		return ret;
+		if (ret)
+			return ret;
+		return ad9467_spi_write(spi, AN877_ADC_REG_TRANSFER,
+					AN877_ADC_TRANSFER_SYNC);
 	}
 
 	ret = ad9467_spi_read(spi, reg);
@@ -212,6 +211,7 @@ static void __ad9467_get_scale(struct adi_axi_adc_conv *conv, int index,
 	.channel = _chan,						\
 	.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE) |		\
 		BIT(IIO_CHAN_INFO_SAMP_FREQ),				\
+	.info_mask_shared_by_type_available = BIT(IIO_CHAN_INFO_SCALE), \
 	.scan_index = _si,						\
 	.scan_type = {							\
 		.sign = _sign,						\
@@ -228,43 +228,46 @@ static const struct iio_chan_spec ad9467_channels[] = {
 	AD9467_CHAN(0, 0, 16, 'S'),
 };
 
-static const struct ad9467_chip_info ad9467_chip_tbl[] = {
-	[ID_AD9265] = {
-		.axi_adc_info = {
-			.id = CHIPID_AD9265,
-			.max_rate = 125000000UL,
-			.scale_table = ad9265_scale_table,
-			.num_scales = ARRAY_SIZE(ad9265_scale_table),
-			.channels = ad9467_channels,
-			.num_channels = ARRAY_SIZE(ad9467_channels),
-		},
-		.default_output_mode = AD9265_DEF_OUTPUT_MODE,
-		.vref_mask = AD9265_REG_VREF_MASK,
+static const struct ad9467_chip_info ad9467_chip_tbl = {
+	.axi_adc_info = {
+		.name = "ad9467",
+		.id = CHIPID_AD9467,
+		.max_rate = 250000000UL,
+		.scale_table = ad9467_scale_table,
+		.num_scales = ARRAY_SIZE(ad9467_scale_table),
+		.channels = ad9467_channels,
+		.num_channels = ARRAY_SIZE(ad9467_channels),
 	},
-	[ID_AD9434] = {
-		.axi_adc_info = {
-			.id = CHIPID_AD9434,
-			.max_rate = 500000000UL,
-			.scale_table = ad9434_scale_table,
-			.num_scales = ARRAY_SIZE(ad9434_scale_table),
-			.channels = ad9434_channels,
-			.num_channels = ARRAY_SIZE(ad9434_channels),
-		},
-		.default_output_mode = AD9434_DEF_OUTPUT_MODE,
-		.vref_mask = AD9434_REG_VREF_MASK,
+	.default_output_mode = AD9467_DEF_OUTPUT_MODE,
+	.vref_mask = AD9467_REG_VREF_MASK,
+};
+
+static const struct ad9467_chip_info ad9434_chip_tbl = {
+	.axi_adc_info = {
+		.name = "ad9434",
+		.id = CHIPID_AD9434,
+		.max_rate = 500000000UL,
+		.scale_table = ad9434_scale_table,
+		.num_scales = ARRAY_SIZE(ad9434_scale_table),
+		.channels = ad9434_channels,
+		.num_channels = ARRAY_SIZE(ad9434_channels),
 	},
-	[ID_AD9467] = {
-		.axi_adc_info = {
-			.id = CHIPID_AD9467,
-			.max_rate = 250000000UL,
-			.scale_table = ad9467_scale_table,
-			.num_scales = ARRAY_SIZE(ad9467_scale_table),
-			.channels = ad9467_channels,
-			.num_channels = ARRAY_SIZE(ad9467_channels),
-		},
-		.default_output_mode = AD9467_DEF_OUTPUT_MODE,
-		.vref_mask = AD9467_REG_VREF_MASK,
+	.default_output_mode = AD9434_DEF_OUTPUT_MODE,
+	.vref_mask = AD9434_REG_VREF_MASK,
+};
+
+static const struct ad9467_chip_info ad9265_chip_tbl = {
+	.axi_adc_info = {
+		.name = "ad9265",
+		.id = CHIPID_AD9265,
+		.max_rate = 125000000UL,
+		.scale_table = ad9265_scale_table,
+		.num_scales = ARRAY_SIZE(ad9265_scale_table),
+		.channels = ad9467_channels,
+		.num_channels = ARRAY_SIZE(ad9467_channels),
 	},
+	.default_output_mode = AD9265_DEF_OUTPUT_MODE,
+	.vref_mask = AD9265_REG_VREF_MASK,
 };
 
 static int ad9467_get_scale(struct adi_axi_adc_conv *conv, int *val, int *val2)
@@ -273,10 +276,13 @@ static int ad9467_get_scale(struct adi_axi_adc_conv *conv, int *val, int *val2)
 	const struct ad9467_chip_info *info1 = to_ad9467_chip_info(info);
 	struct ad9467_state *st = adi_axi_adc_conv_priv(conv);
 	unsigned int i, vref_val;
+	int ret;
 
-	vref_val = ad9467_spi_read(st->spi, AN877_ADC_REG_VREF);
+	ret = ad9467_spi_read(st->spi, AN877_ADC_REG_VREF);
+	if (ret < 0)
+		return ret;
 
-	vref_val &= info1->vref_mask;
+	vref_val = ret & info1->vref_mask;
 
 	for (i = 0; i < info->num_scales; i++) {
 		if (vref_val == info->scale_table[i][1])
@@ -297,6 +303,7 @@ static int ad9467_set_scale(struct adi_axi_adc_conv *conv, int val, int val2)
 	struct ad9467_state *st = adi_axi_adc_conv_priv(conv);
 	unsigned int scale_val[2];
 	unsigned int i;
+	int ret;
 
 	if (val != 0)
 		return -EINVAL;
@@ -306,11 +313,14 @@ static int ad9467_set_scale(struct adi_axi_adc_conv *conv, int val, int val2)
 		if (scale_val[0] != val || scale_val[1] != val2)
 			continue;
 
-		ad9467_spi_write(st->spi, AN877_ADC_REG_VREF,
-				 info->scale_table[i][1]);
-		ad9467_spi_write(st->spi, AN877_ADC_REG_TRANSFER,
-				 AN877_ADC_TRANSFER_SYNC);
-		return 0;
+		guard(mutex)(&st->lock);
+		ret = ad9467_spi_write(st->spi, AN877_ADC_REG_VREF,
+				       info->scale_table[i][1]);
+		if (ret < 0)
+			return ret;
+
+		return ad9467_spi_write(st->spi, AN877_ADC_REG_TRANSFER,
+					AN877_ADC_TRANSFER_SYNC);
 	}
 
 	return -EINVAL;
@@ -359,6 +369,26 @@ static int ad9467_write_raw(struct adi_axi_adc_conv *conv,
 	}
 }
 
+static int ad9467_read_avail(struct adi_axi_adc_conv *conv,
+			     struct iio_chan_spec const *chan,
+			     const int **vals, int *type, int *length,
+			     long mask)
+{
+	const struct adi_axi_adc_chip_info *info = conv->chip_info;
+	struct ad9467_state *st = adi_axi_adc_conv_priv(conv);
+
+	switch (mask) {
+	case IIO_CHAN_INFO_SCALE:
+		*vals = (const int *)st->scales;
+		*type = IIO_VAL_INT_PLUS_MICRO;
+		/* Values are stored in a 2D matrix */
+		*length = info->num_scales * 2;
+		return IIO_AVAIL_LIST;
+	default:
+		return -EINVAL;
+	}
+}
+
 static int ad9467_outputmode_set(struct spi_device *spi, unsigned int mode)
 {
 	int ret;
@@ -371,6 +401,26 @@ static int ad9467_outputmode_set(struct spi_device *spi, unsigned int mode)
 				AN877_ADC_TRANSFER_SYNC);
 }
 
+static int ad9467_scale_fill(struct adi_axi_adc_conv *conv)
+{
+	const struct adi_axi_adc_chip_info *info = conv->chip_info;
+	struct ad9467_state *st = adi_axi_adc_conv_priv(conv);
+	unsigned int i, val1, val2;
+
+	st->scales = devm_kmalloc_array(&st->spi->dev, info->num_scales,
+					sizeof(*st->scales), GFP_KERNEL);
+	if (!st->scales)
+		return -ENOMEM;
+
+	for (i = 0; i < info->num_scales; i++) {
+		__ad9467_get_scale(conv, i, &val1, &val2);
+		st->scales[i][0] = val1;
+		st->scales[i][1] = val2;
+	}
+
+	return 0;
+}
+
 static int ad9467_preenable_setup(struct adi_axi_adc_conv *conv)
 {
 	struct ad9467_state *st = adi_axi_adc_conv_priv(conv);
@@ -378,6 +428,21 @@ static int ad9467_preenable_setup(struct adi_axi_adc_conv *conv)
 	return ad9467_outputmode_set(st->spi, st->output_mode);
 }
 
+static int ad9467_reset(struct device *dev)
+{
+	struct gpio_desc *gpio;
+
+	gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR_OR_NULL(gpio))
+		return PTR_ERR_OR_ZERO(gpio);
+
+	fsleep(1);
+	gpiod_set_value_cansleep(gpio, 0);
+	fsleep(10 * USEC_PER_MSEC);
+
+	return 0;
+}
+
 static int ad9467_probe(struct spi_device *spi)
 {
 	const struct ad9467_chip_info *info;
@@ -386,9 +451,7 @@ static int ad9467_probe(struct spi_device *spi)
 	unsigned int id;
 	int ret;
 
-	info = of_device_get_match_data(&spi->dev);
-	if (!info)
-		info = (void *)spi_get_device_id(spi)->driver_data;
+	info = spi_get_device_match_data(spi);
 	if (!info)
 		return -ENODEV;
 
@@ -408,21 +471,16 @@ static int ad9467_probe(struct spi_device *spi)
 	if (IS_ERR(st->pwrdown_gpio))
 		return PTR_ERR(st->pwrdown_gpio);
 
-	st->reset_gpio = devm_gpiod_get_optional(&spi->dev, "reset",
-						 GPIOD_OUT_LOW);
-	if (IS_ERR(st->reset_gpio))
-		return PTR_ERR(st->reset_gpio);
-
-	if (st->reset_gpio) {
-		udelay(1);
-		ret = gpiod_direction_output(st->reset_gpio, 1);
-		if (ret)
-			return ret;
-		mdelay(10);
-	}
+	ret = ad9467_reset(&spi->dev);
+	if (ret)
+		return ret;
 
 	conv->chip_info = &info->axi_adc_info;
 
+	ret = ad9467_scale_fill(conv);
+	if (ret)
+		return ret;
+
 	id = ad9467_spi_read(spi, AN877_ADC_REG_CHIP_ID);
 	if (id != conv->chip_info->id) {
 		dev_err(&spi->dev, "Mismatch CHIP_ID, got 0x%X, expected 0x%X\n",
@@ -433,6 +491,7 @@ static int ad9467_probe(struct spi_device *spi)
 	conv->reg_access = ad9467_reg_access;
 	conv->write_raw = ad9467_write_raw;
 	conv->read_raw = ad9467_read_raw;
+	conv->read_avail = ad9467_read_avail;
 	conv->preenable_setup = ad9467_preenable_setup;
 
 	st->output_mode = info->default_output_mode |
@@ -442,17 +501,17 @@ static int ad9467_probe(struct spi_device *spi)
 }
 
 static const struct of_device_id ad9467_of_match[] = {
-	{ .compatible = "adi,ad9265", .data = &ad9467_chip_tbl[ID_AD9265], },
-	{ .compatible = "adi,ad9434", .data = &ad9467_chip_tbl[ID_AD9434], },
-	{ .compatible = "adi,ad9467", .data = &ad9467_chip_tbl[ID_AD9467], },
+	{ .compatible = "adi,ad9265", .data = &ad9265_chip_tbl, },
+	{ .compatible = "adi,ad9434", .data = &ad9434_chip_tbl, },
+	{ .compatible = "adi,ad9467", .data = &ad9467_chip_tbl, },
 	{}
 };
 MODULE_DEVICE_TABLE(of, ad9467_of_match);
 
 static const struct spi_device_id ad9467_ids[] = {
-	{ "ad9265", (kernel_ulong_t)&ad9467_chip_tbl[ID_AD9265] },
-	{ "ad9434", (kernel_ulong_t)&ad9467_chip_tbl[ID_AD9434] },
-	{ "ad9467", (kernel_ulong_t)&ad9467_chip_tbl[ID_AD9467] },
+	{ "ad9265", (kernel_ulong_t)&ad9265_chip_tbl },
+	{ "ad9434", (kernel_ulong_t)&ad9434_chip_tbl },
+	{ "ad9467", (kernel_ulong_t)&ad9467_chip_tbl },
 	{}
 };
 MODULE_DEVICE_TABLE(spi, ad9467_ids);
diff --git a/drivers/iio/adc/adi-axi-adc.c b/drivers/iio/adc/adi-axi-adc.c
index aff0532a974a..c247ff1541d2 100644
--- a/drivers/iio/adc/adi-axi-adc.c
+++ b/drivers/iio/adc/adi-axi-adc.c
@@ -14,6 +14,7 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/property.h>
+#include <linux/regmap.h>
 #include <linux/slab.h>
 
 #include <linux/iio/iio.h>
@@ -62,7 +63,7 @@ struct adi_axi_adc_state {
 	struct mutex				lock;
 
 	struct adi_axi_adc_client		*client;
-	void __iomem				*regs;
+	struct regmap				*regmap;
 };
 
 struct adi_axi_adc_client {
@@ -90,19 +91,6 @@ void *adi_axi_adc_conv_priv(struct adi_axi_adc_conv *conv)
 }
 EXPORT_SYMBOL_NS_GPL(adi_axi_adc_conv_priv, IIO_ADI_AXI);
 
-static void adi_axi_adc_write(struct adi_axi_adc_state *st,
-			      unsigned int reg,
-			      unsigned int val)
-{
-	iowrite32(val, st->regs + reg);
-}
-
-static unsigned int adi_axi_adc_read(struct adi_axi_adc_state *st,
-				     unsigned int reg)
-{
-	return ioread32(st->regs + reg);
-}
-
 static int adi_axi_adc_config_dma_buffer(struct device *dev,
 					 struct iio_dev *indio_dev)
 {
@@ -144,22 +132,39 @@ static int adi_axi_adc_write_raw(struct iio_dev *indio_dev,
 	return conv->write_raw(conv, chan, val, val2, mask);
 }
 
+static int adi_axi_adc_read_avail(struct iio_dev *indio_dev,
+				  struct iio_chan_spec const *chan,
+				  const int **vals, int *type, int *length,
+				  long mask)
+{
+	struct adi_axi_adc_state *st = iio_priv(indio_dev);
+	struct adi_axi_adc_conv *conv = &st->client->conv;
+
+	if (!conv->read_avail)
+		return -EOPNOTSUPP;
+
+	return conv->read_avail(conv, chan, vals, type, length, mask);
+}
+
 static int adi_axi_adc_update_scan_mode(struct iio_dev *indio_dev,
 					const unsigned long *scan_mask)
 {
 	struct adi_axi_adc_state *st = iio_priv(indio_dev);
 	struct adi_axi_adc_conv *conv = &st->client->conv;
-	unsigned int i, ctrl;
+	unsigned int i;
+	int ret;
 
 	for (i = 0; i < conv->chip_info->num_channels; i++) {
-		ctrl = adi_axi_adc_read(st, ADI_AXI_REG_CHAN_CTRL(i));
-
 		if (test_bit(i, scan_mask))
-			ctrl |= ADI_AXI_REG_CHAN_CTRL_ENABLE;
+			ret = regmap_set_bits(st->regmap,
+					      ADI_AXI_REG_CHAN_CTRL(i),
+					      ADI_AXI_REG_CHAN_CTRL_ENABLE);
 		else
-			ctrl &= ~ADI_AXI_REG_CHAN_CTRL_ENABLE;
-
-		adi_axi_adc_write(st, ADI_AXI_REG_CHAN_CTRL(i), ctrl);
+			ret = regmap_clear_bits(st->regmap,
+						ADI_AXI_REG_CHAN_CTRL(i),
+						ADI_AXI_REG_CHAN_CTRL_ENABLE);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
@@ -228,69 +233,11 @@ struct adi_axi_adc_conv *devm_adi_axi_adc_conv_register(struct device *dev,
 }
 EXPORT_SYMBOL_NS_GPL(devm_adi_axi_adc_conv_register, IIO_ADI_AXI);
 
-static ssize_t in_voltage_scale_available_show(struct device *dev,
-					       struct device_attribute *attr,
-					       char *buf)
-{
-	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
-	struct adi_axi_adc_state *st = iio_priv(indio_dev);
-	struct adi_axi_adc_conv *conv = &st->client->conv;
-	size_t len = 0;
-	int i;
-
-	for (i = 0; i < conv->chip_info->num_scales; i++) {
-		const unsigned int *s = conv->chip_info->scale_table[i];
-
-		len += scnprintf(buf + len, PAGE_SIZE - len,
-				 "%u.%06u ", s[0], s[1]);
-	}
-	buf[len - 1] = '\n';
-
-	return len;
-}
-
-static IIO_DEVICE_ATTR_RO(in_voltage_scale_available, 0);
-
-enum {
-	ADI_AXI_ATTR_SCALE_AVAIL,
-};
-
-#define ADI_AXI_ATTR(_en_, _file_)			\
-	[ADI_AXI_ATTR_##_en_] = &iio_dev_attr_##_file_.dev_attr.attr
-
-static struct attribute *adi_axi_adc_attributes[] = {
-	ADI_AXI_ATTR(SCALE_AVAIL, in_voltage_scale_available),
-	NULL
-};
-
-static umode_t axi_adc_attr_is_visible(struct kobject *kobj,
-				       struct attribute *attr, int n)
-{
-	struct device *dev = kobj_to_dev(kobj);
-	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
-	struct adi_axi_adc_state *st = iio_priv(indio_dev);
-	struct adi_axi_adc_conv *conv = &st->client->conv;
-
-	switch (n) {
-	case ADI_AXI_ATTR_SCALE_AVAIL:
-		if (!conv->chip_info->num_scales)
-			return 0;
-		return attr->mode;
-	default:
-		return attr->mode;
-	}
-}
-
-static const struct attribute_group adi_axi_adc_attribute_group = {
-	.attrs = adi_axi_adc_attributes,
-	.is_visible = axi_adc_attr_is_visible,
-};
-
 static const struct iio_info adi_axi_adc_info = {
 	.read_raw = &adi_axi_adc_read_raw,
 	.write_raw = &adi_axi_adc_write_raw,
-	.attrs = &adi_axi_adc_attribute_group,
 	.update_scan_mode = &adi_axi_adc_update_scan_mode,
+	.read_avail = &adi_axi_adc_read_avail,
 };
 
 static const struct adi_axi_adc_core_info adi_axi_adc_10_0_a_info = {
@@ -354,21 +301,32 @@ static int adi_axi_adc_setup_channels(struct device *dev,
 	}
 
 	for (i = 0; i < conv->chip_info->num_channels; i++) {
-		adi_axi_adc_write(st, ADI_AXI_REG_CHAN_CTRL(i),
-				  ADI_AXI_REG_CHAN_CTRL_DEFAULTS);
+		ret = regmap_write(st->regmap, ADI_AXI_REG_CHAN_CTRL(i),
+				   ADI_AXI_REG_CHAN_CTRL_DEFAULTS);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
 }
 
-static void axi_adc_reset(struct adi_axi_adc_state *st)
+static int axi_adc_reset(struct adi_axi_adc_state *st)
 {
-	adi_axi_adc_write(st, ADI_AXI_REG_RSTN, 0);
+	int ret;
+
+	ret = regmap_write(st->regmap, ADI_AXI_REG_RSTN, 0);
+	if (ret)
+		return ret;
+
 	mdelay(10);
-	adi_axi_adc_write(st, ADI_AXI_REG_RSTN, ADI_AXI_REG_RSTN_MMCM_RSTN);
+	ret = regmap_write(st->regmap, ADI_AXI_REG_RSTN,
+			   ADI_AXI_REG_RSTN_MMCM_RSTN);
+	if (ret)
+		return ret;
+
 	mdelay(10);
-	adi_axi_adc_write(st, ADI_AXI_REG_RSTN,
-			  ADI_AXI_REG_RSTN_RSTN | ADI_AXI_REG_RSTN_MMCM_RSTN);
+	return regmap_write(st->regmap, ADI_AXI_REG_RSTN,
+			    ADI_AXI_REG_RSTN_RSTN | ADI_AXI_REG_RSTN_MMCM_RSTN);
 }
 
 static void adi_axi_adc_cleanup(void *data)
@@ -379,12 +337,20 @@ static void adi_axi_adc_cleanup(void *data)
 	module_put(cl->dev->driver->owner);
 }
 
+static const struct regmap_config axi_adc_regmap_config = {
+	.val_bits = 32,
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.max_register = 0x0800,
+};
+
 static int adi_axi_adc_probe(struct platform_device *pdev)
 {
 	struct adi_axi_adc_conv *conv;
 	struct iio_dev *indio_dev;
 	struct adi_axi_adc_client *cl;
 	struct adi_axi_adc_state *st;
+	void __iomem *base;
 	unsigned int ver;
 	int ret;
 
@@ -405,15 +371,24 @@ static int adi_axi_adc_probe(struct platform_device *pdev)
 	cl->state = st;
 	mutex_init(&st->lock);
 
-	st->regs = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(st->regs))
-		return PTR_ERR(st->regs);
+	base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	st->regmap = devm_regmap_init_mmio(&pdev->dev, base,
+					   &axi_adc_regmap_config);
+	if (IS_ERR(st->regmap))
+		return PTR_ERR(st->regmap);
 
 	conv = &st->client->conv;
 
-	axi_adc_reset(st);
+	ret = axi_adc_reset(st);
+	if (ret)
+		return ret;
 
-	ver = adi_axi_adc_read(st, ADI_AXI_REG_VERSION);
+	ret = regmap_read(st->regmap, ADI_AXI_REG_VERSION, &ver);
+	if (ret)
+		return ret;
 
 	if (cl->info->version > ver) {
 		dev_err(&pdev->dev,
diff --git a/drivers/iio/adc/max34408.c b/drivers/iio/adc/max34408.c
new file mode 100644
index 000000000000..6c2ea2bc52c6
--- /dev/null
+++ b/drivers/iio/adc/max34408.c
@@ -0,0 +1,276 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * IIO driver for Maxim MAX34409/34408 ADC, 4-Channels/2-Channels, 8bits, I2C
+ *
+ * Datasheet: https://www.analog.com/media/en/technical-documentation/data-sheets/MAX34408-MAX34409.pdf
+ *
+ * TODO: ALERT interrupt, Overcurrent delay, Shutdown delay
+ */
+
+#include <linux/bitfield.h>
+#include <linux/init.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/mod_devicetable.h>
+#include <linux/property.h>
+#include <linux/regmap.h>
+
+#include <linux/iio/iio.h>
+#include <linux/iio/types.h>
+
+#define MAX34408_STATUS_REG		0x0
+#define MAX34408_CONTROL_REG		0x1
+#define MAX34408_OCDELAY_REG		0x2
+#define MAX34408_SDDELAY_REG		0x3
+
+#define MAX34408_ADC1_REG		0x4
+#define MAX34408_ADC2_REG		0x5
+/* ADC3 & ADC4 always returns 0x0 on 34408 */
+#define MAX34409_ADC3_REG		0x6
+#define MAX34409_ADC4_REG		0x7
+
+#define MAX34408_OCT1_REG		0x8
+#define MAX34408_OCT2_REG		0x9
+#define MAX34409_OCT3_REG		0xA
+#define MAX34409_OCT4_REG		0xB
+
+#define MAX34408_DID_REG		0xC
+#define MAX34408_DCYY_REG		0xD
+#define MAX34408_DCWW_REG		0xE
+
+/* Bit masks for status register */
+#define MAX34408_STATUS_OC_MSK		GENMASK(1, 0)
+#define MAX34409_STATUS_OC_MSK		GENMASK(3, 0)
+#define MAX34408_STATUS_SHTDN		BIT(4)
+#define MAX34408_STATUS_ENA		BIT(5)
+
+/* Bit masks for control register */
+#define MAX34408_CONTROL_AVG0		BIT(0)
+#define MAX34408_CONTROL_AVG1		BIT(1)
+#define MAX34408_CONTROL_AVG2		BIT(2)
+#define MAX34408_CONTROL_ALERT		BIT(3)
+
+#define MAX34408_DEFAULT_AVG		0x4
+
+/* Bit masks for over current delay */
+#define MAX34408_OCDELAY_OCD_MSK	GENMASK(6, 0)
+#define MAX34408_OCDELAY_RESET		BIT(7)
+
+/* Bit masks for shutdown delay */
+#define MAX34408_SDDELAY_SHD_MSK	GENMASK(6, 0)
+#define MAX34408_SDDELAY_RESET		BIT(7)
+
+#define MAX34408_DEFAULT_RSENSE		1000
+
+/**
+ * struct max34408_data - max34408/max34409 specific data.
+ * @regmap:	device register map.
+ * @dev:	max34408 device.
+ * @lock:	lock for protecting access to device hardware registers, mostly
+ *		for read modify write cycles for control registers.
+ * @input_rsense:	Rsense values in uOhm, will be overwritten by
+ *			values from channel nodes.
+ */
+struct max34408_data {
+	struct regmap *regmap;
+	struct device *dev;
+	struct mutex lock;
+	u32 input_rsense[4];
+};
+
+static const struct regmap_config max34408_regmap_config = {
+	.reg_bits	= 8,
+	.val_bits	= 8,
+	.max_register	= MAX34408_DCWW_REG,
+};
+
+struct max34408_adc_model_data {
+	const char *model_name;
+	const struct iio_chan_spec *channels;
+	const int num_channels;
+};
+
+#define MAX34008_CHANNEL(_index, _address)			\
+	{							\
+		.type = IIO_CURRENT,				\
+		.info_mask_separate	= BIT(IIO_CHAN_INFO_RAW) | \
+					  BIT(IIO_CHAN_INFO_SCALE) | \
+					  BIT(IIO_CHAN_INFO_OFFSET), \
+		.channel = (_index),				\
+		.address = (_address),				\
+		.indexed = 1,					\
+	}
+
+static const struct iio_chan_spec max34408_channels[] = {
+	MAX34008_CHANNEL(0, MAX34408_ADC1_REG),
+	MAX34008_CHANNEL(1, MAX34408_ADC2_REG),
+};
+
+static const struct iio_chan_spec max34409_channels[] = {
+	MAX34008_CHANNEL(0, MAX34408_ADC1_REG),
+	MAX34008_CHANNEL(1, MAX34408_ADC2_REG),
+	MAX34008_CHANNEL(2, MAX34409_ADC3_REG),
+	MAX34008_CHANNEL(3, MAX34409_ADC4_REG),
+};
+
+static int max34408_read_adc_avg(struct max34408_data *max34408,
+				 const struct iio_chan_spec *chan, int *val)
+{
+	unsigned int ctrl;
+	int rc;
+
+	guard(mutex)(&max34408->lock);
+	rc = regmap_read(max34408->regmap, MAX34408_CONTROL_REG, (u32 *)&ctrl);
+	if (rc)
+		return rc;
+
+	/* set averaging (0b100) default values*/
+	rc = regmap_write(max34408->regmap, MAX34408_CONTROL_REG,
+			  MAX34408_DEFAULT_AVG);
+	if (rc) {
+		dev_err(max34408->dev,
+			"Error (%d) writing control register\n", rc);
+		return rc;
+	}
+
+	rc = regmap_read(max34408->regmap, chan->address, val);
+	if (rc)
+		return rc;
+
+	/* back to old values */
+	rc = regmap_write(max34408->regmap, MAX34408_CONTROL_REG, ctrl);
+	if (rc)
+		dev_err(max34408->dev,
+			"Error (%d) writing control register\n", rc);
+
+	return rc;
+}
+
+static int max34408_read_raw(struct iio_dev *indio_dev,
+			     struct iio_chan_spec const *chan,
+			     int *val, int *val2, long mask)
+{
+	struct max34408_data *max34408 = iio_priv(indio_dev);
+	int rc;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		rc = max34408_read_adc_avg(max34408, chan, val);
+		if (rc)
+			return rc;
+		return IIO_VAL_INT;
+	case IIO_CHAN_INFO_SCALE:
+		/*
+		 * calcluate current for 8bit ADC with Rsense
+		 * value.
+		 * 10 mV * 1000 / Rsense uOhm = max current
+		 * (max current * adc val * 1000) / (2^8 - 1) mA
+		 */
+		*val = 10000 / max34408->input_rsense[chan->channel];
+		*val2 = 8;
+		return IIO_VAL_FRACTIONAL_LOG2;
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct iio_info max34408_info = {
+	.read_raw	= max34408_read_raw,
+};
+
+static const struct max34408_adc_model_data max34408_model_data = {
+	.model_name = "max34408",
+	.channels = max34408_channels,
+	.num_channels = 2,
+};
+
+static const struct max34408_adc_model_data max34409_model_data = {
+	.model_name = "max34409",
+	.channels = max34409_channels,
+	.num_channels = 4,
+};
+
+static int max34408_probe(struct i2c_client *client)
+{
+	const struct max34408_adc_model_data *model_data;
+	struct device *dev = &client->dev;
+	struct max34408_data *max34408;
+	struct fwnode_handle *node;
+	struct iio_dev *indio_dev;
+	struct regmap *regmap;
+	int rc, i = 0;
+
+	model_data = i2c_get_match_data(client);
+	if (!model_data)
+		return -EINVAL;
+
+	regmap = devm_regmap_init_i2c(client, &max34408_regmap_config);
+	if (IS_ERR(regmap)) {
+		dev_err_probe(dev, PTR_ERR(regmap),
+			      "regmap_init failed\n");
+		return PTR_ERR(regmap);
+	}
+
+	indio_dev = devm_iio_device_alloc(dev, sizeof(*max34408));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	max34408 = iio_priv(indio_dev);
+	max34408->regmap = regmap;
+	max34408->dev = dev;
+	mutex_init(&max34408->lock);
+
+	device_for_each_child_node(dev, node) {
+		fwnode_property_read_u32(node, "maxim,rsense-val-micro-ohms",
+					 &max34408->input_rsense[i]);
+		i++;
+	}
+
+	/* disable ALERT and averaging */
+	rc = regmap_write(max34408->regmap, MAX34408_CONTROL_REG, 0x0);
+	if (rc)
+		return rc;
+
+	indio_dev->channels = model_data->channels;
+	indio_dev->num_channels = model_data->num_channels;
+	indio_dev->name = model_data->model_name;
+
+	indio_dev->info = &max34408_info;
+	indio_dev->modes = INDIO_DIRECT_MODE;
+
+	return devm_iio_device_register(dev, indio_dev);
+}
+
+static const struct of_device_id max34408_of_match[] = {
+	{
+		.compatible = "maxim,max34408",
+		.data = &max34408_model_data,
+	},
+	{
+		.compatible = "maxim,max34409",
+		.data = &max34409_model_data,
+	},
+	{}
+};
+MODULE_DEVICE_TABLE(of, max34408_of_match);
+
+static const struct i2c_device_id max34408_id[] = {
+	{ "max34408", (kernel_ulong_t)&max34408_model_data },
+	{ "max34409", (kernel_ulong_t)&max34409_model_data },
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, max34408_id);
+
+static struct i2c_driver max34408_driver = {
+	.driver = {
+		.name   = "max34408",
+		.of_match_table = max34408_of_match,
+	},
+	.probe = max34408_probe,
+	.id_table = max34408_id,
+};
+module_i2c_driver(max34408_driver);
+
+MODULE_AUTHOR("Ivan Mikhaylov <fr0st61te@gmail.com>");
+MODULE_DESCRIPTION("Maxim MAX34408/34409 ADC driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/iio/adc/mcp3911.c b/drivers/iio/adc/mcp3911.c
index d864558bc087..7a32e7a1be9d 100644
--- a/drivers/iio/adc/mcp3911.c
+++ b/drivers/iio/adc/mcp3911.c
@@ -7,6 +7,7 @@
  */
 #include <linux/bitfield.h>
 #include <linux/bits.h>
+#include <linux/cleanup.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/err.h>
@@ -316,47 +317,37 @@ static int mcp3911_read_raw(struct iio_dev *indio_dev,
 			    int *val2, long mask)
 {
 	struct mcp3911 *adc = iio_priv(indio_dev);
-	int ret = -EINVAL;
+	int ret;
 
-	mutex_lock(&adc->lock);
+	guard(mutex)(&adc->lock);
 	switch (mask) {
 	case IIO_CHAN_INFO_RAW:
 		ret = mcp3911_read(adc,
 				   MCP3911_CHANNEL(channel->channel), val, 3);
 		if (ret)
-			goto out;
+			return ret;
 
 		*val = sign_extend32(*val, 23);
-
-		ret = IIO_VAL_INT;
-		break;
-
+		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_OFFSET:
-
 		ret = adc->chip->get_offset(adc, channel->channel, val);
 		if (ret)
-			goto out;
+			return ret;
 
-		ret = IIO_VAL_INT;
-		break;
+		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_OVERSAMPLING_RATIO:
 		ret = adc->chip->get_osr(adc, val);
 		if (ret)
-			goto out;
-
-		ret = IIO_VAL_INT;
-		break;
+			return ret;
 
+		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_SCALE:
 		*val = mcp3911_scale_table[ilog2(adc->gain[channel->channel])][0];
 		*val2 = mcp3911_scale_table[ilog2(adc->gain[channel->channel])][1];
-		ret = IIO_VAL_INT_PLUS_NANO;
-		break;
+		return IIO_VAL_INT_PLUS_NANO;
+	default:
+		return -EINVAL;
 	}
-
-out:
-	mutex_unlock(&adc->lock);
-	return ret;
 }
 
 static int mcp3911_write_raw(struct iio_dev *indio_dev,
@@ -364,9 +355,8 @@ static int mcp3911_write_raw(struct iio_dev *indio_dev,
 			     int val2, long mask)
 {
 	struct mcp3911 *adc = iio_priv(indio_dev);
-	int ret = -EINVAL;
 
-	mutex_lock(&adc->lock);
+	guard(mutex)(&adc->lock);
 	switch (mask) {
 	case IIO_CHAN_INFO_SCALE:
 		for (int i = 0; i < MCP3911_NUM_SCALES; i++) {
@@ -374,32 +364,25 @@ static int mcp3911_write_raw(struct iio_dev *indio_dev,
 			    val2 == mcp3911_scale_table[i][1]) {
 
 				adc->gain[channel->channel] = BIT(i);
-				ret = adc->chip->set_scale(adc, channel->channel, i);
+				return adc->chip->set_scale(adc, channel->channel, i);
 			}
 		}
-		break;
+		return -EINVAL;
 	case IIO_CHAN_INFO_OFFSET:
-		if (val2 != 0) {
-			ret = -EINVAL;
-			goto out;
-		}
-
-		ret = adc->chip->set_offset(adc, channel->channel, val);
-		break;
+		if (val2 != 0)
+			return -EINVAL;
 
+		return adc->chip->set_offset(adc, channel->channel, val);
 	case IIO_CHAN_INFO_OVERSAMPLING_RATIO:
 		for (int i = 0; i < ARRAY_SIZE(mcp3911_osr_table); i++) {
 			if (val == mcp3911_osr_table[i]) {
-				ret = adc->chip->set_osr(adc, i);
-				break;
+				return adc->chip->set_osr(adc, i);
 			}
 		}
-		break;
+		return -EINVAL;
+	default:
+		return -EINVAL;
 	}
-
-out:
-	mutex_unlock(&adc->lock);
-	return ret;
 }
 
 static int mcp3911_calc_scale_table(struct mcp3911 *adc)
@@ -532,7 +515,7 @@ static irqreturn_t mcp3911_trigger_handler(int irq, void *p)
 	int i = 0;
 	int ret;
 
-	mutex_lock(&adc->lock);
+	guard(mutex)(&adc->lock);
 	adc->tx_buf = MCP3911_REG_READ(MCP3911_CHANNEL(0), adc->dev_addr);
 	ret = spi_sync_transfer(adc->spi, xfer, ARRAY_SIZE(xfer));
 	if (ret < 0) {
@@ -549,7 +532,6 @@ static irqreturn_t mcp3911_trigger_handler(int irq, void *p)
 	iio_push_to_buffers_with_timestamp(indio_dev, &adc->scan,
 					   iio_get_time_ns(indio_dev));
 out:
-	mutex_unlock(&adc->lock);
 	iio_trigger_notify_done(indio_dev->trig);
 
 	return IRQ_HANDLED;
diff --git a/drivers/iio/amplifiers/hmc425a.c b/drivers/iio/amplifiers/hmc425a.c
index e87d35d50a95..ed4d72922696 100644
--- a/drivers/iio/amplifiers/hmc425a.c
+++ b/drivers/iio/amplifiers/hmc425a.c
@@ -5,6 +5,7 @@
  * Copyright 2020 Analog Devices Inc.
  */
 
+#include <linux/bitops.h>
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/gpio/consumer.h>
@@ -22,6 +23,7 @@
 enum hmc425a_type {
 	ID_HMC425A,
 	ID_HMC540S,
+	ID_ADRF5740
 };
 
 struct hmc425a_chip_info {
@@ -74,6 +76,10 @@ static int hmc425a_read_raw(struct iio_dev *indio_dev,
 		case ID_HMC540S:
 			gain = ~code * -1000;
 			break;
+		case ID_ADRF5740:
+			code = code & BIT(3) ? code & ~BIT(2) : code;
+			gain = code * -2000;
+			break;
 		}
 
 		*val = gain / 1000;
@@ -113,6 +119,10 @@ static int hmc425a_write_raw(struct iio_dev *indio_dev,
 	case ID_HMC540S:
 		code = ~((abs(gain) / 1000) & 0xF);
 		break;
+	case ID_ADRF5740:
+		code = (abs(gain) / 2000) & 0xF;
+		code = code & BIT(3) ? code | BIT(2) : code;
+		break;
 	}
 
 	mutex_lock(&st->lock);
@@ -165,6 +175,7 @@ static const struct iio_chan_spec hmc425a_channels[] = {
 static const struct of_device_id hmc425a_of_match[] = {
 	{ .compatible = "adi,hmc425a", .data = (void *)ID_HMC425A },
 	{ .compatible = "adi,hmc540s", .data = (void *)ID_HMC540S },
+	{ .compatible = "adi,adrf5740", .data = (void *)ID_ADRF5740 },
 	{},
 };
 MODULE_DEVICE_TABLE(of, hmc425a_of_match);
@@ -188,6 +199,15 @@ static struct hmc425a_chip_info hmc425a_chip_info_tbl[] = {
 		.gain_max = 0,
 		.default_gain = -0x10, /* set default gain -15.0db*/
 	},
+	[ID_ADRF5740] = {
+		.name = "adrf5740",
+		.channels = hmc425a_channels,
+		.num_channels = ARRAY_SIZE(hmc425a_channels),
+		.num_gpios = 4,
+		.gain_min = -22000,
+		.gain_max = 0,
+		.default_gain = 0xF, /* set default gain -22.0db*/
+	},
 };
 
 static int hmc425a_probe(struct platform_device *pdev)
@@ -229,6 +249,9 @@ static int hmc425a_probe(struct platform_device *pdev)
 	indio_dev->info = &hmc425a_info;
 	indio_dev->modes = INDIO_DIRECT_MODE;
 
+	/* Set default gain */
+	hmc425a_write(indio_dev, st->gain);
+
 	return devm_iio_device_register(&pdev->dev, indio_dev);
 }
 
diff --git a/drivers/iio/buffer/industrialio-buffer-dma.c b/drivers/iio/buffer/industrialio-buffer-dma.c
index d348af8b9705..5610ba67925e 100644
--- a/drivers/iio/buffer/industrialio-buffer-dma.c
+++ b/drivers/iio/buffer/industrialio-buffer-dma.c
@@ -179,7 +179,7 @@ static struct iio_dma_buffer_block *iio_dma_buffer_alloc_block(
 	}
 
 	block->size = size;
-	block->state = IIO_BLOCK_STATE_DEQUEUED;
+	block->state = IIO_BLOCK_STATE_DONE;
 	block->queue = queue;
 	INIT_LIST_HEAD(&block->head);
 	kref_init(&block->kref);
@@ -191,16 +191,8 @@ static struct iio_dma_buffer_block *iio_dma_buffer_alloc_block(
 
 static void _iio_dma_buffer_block_done(struct iio_dma_buffer_block *block)
 {
-	struct iio_dma_buffer_queue *queue = block->queue;
-
-	/*
-	 * The buffer has already been freed by the application, just drop the
-	 * reference.
-	 */
-	if (block->state != IIO_BLOCK_STATE_DEAD) {
+	if (block->state != IIO_BLOCK_STATE_DEAD)
 		block->state = IIO_BLOCK_STATE_DONE;
-		list_add_tail(&block->head, &queue->outgoing);
-	}
 }
 
 /**
@@ -261,7 +253,6 @@ static bool iio_dma_block_reusable(struct iio_dma_buffer_block *block)
 	 * not support abort and has not given back the block yet.
 	 */
 	switch (block->state) {
-	case IIO_BLOCK_STATE_DEQUEUED:
 	case IIO_BLOCK_STATE_QUEUED:
 	case IIO_BLOCK_STATE_DONE:
 		return true;
@@ -317,7 +308,6 @@ int iio_dma_buffer_request_update(struct iio_buffer *buffer)
 	 * dead. This means we can reset the lists without having to fear
 	 * corrution.
 	 */
-	INIT_LIST_HEAD(&queue->outgoing);
 	spin_unlock_irq(&queue->list_lock);
 
 	INIT_LIST_HEAD(&queue->incoming);
@@ -356,6 +346,29 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(iio_dma_buffer_request_update);
 
+static void iio_dma_buffer_fileio_free(struct iio_dma_buffer_queue *queue)
+{
+	unsigned int i;
+
+	spin_lock_irq(&queue->list_lock);
+	for (i = 0; i < ARRAY_SIZE(queue->fileio.blocks); i++) {
+		if (!queue->fileio.blocks[i])
+			continue;
+		queue->fileio.blocks[i]->state = IIO_BLOCK_STATE_DEAD;
+	}
+	spin_unlock_irq(&queue->list_lock);
+
+	INIT_LIST_HEAD(&queue->incoming);
+
+	for (i = 0; i < ARRAY_SIZE(queue->fileio.blocks); i++) {
+		if (!queue->fileio.blocks[i])
+			continue;
+		iio_buffer_block_put(queue->fileio.blocks[i]);
+		queue->fileio.blocks[i] = NULL;
+	}
+	queue->fileio.active_block = NULL;
+}
+
 static void iio_dma_buffer_submit_block(struct iio_dma_buffer_queue *queue,
 	struct iio_dma_buffer_block *block)
 {
@@ -456,14 +469,20 @@ static struct iio_dma_buffer_block *iio_dma_buffer_dequeue(
 	struct iio_dma_buffer_queue *queue)
 {
 	struct iio_dma_buffer_block *block;
+	unsigned int idx;
 
 	spin_lock_irq(&queue->list_lock);
-	block = list_first_entry_or_null(&queue->outgoing, struct
-		iio_dma_buffer_block, head);
-	if (block != NULL) {
-		list_del(&block->head);
-		block->state = IIO_BLOCK_STATE_DEQUEUED;
+
+	idx = queue->fileio.next_dequeue;
+	block = queue->fileio.blocks[idx];
+
+	if (block->state == IIO_BLOCK_STATE_DONE) {
+		idx = (idx + 1) % ARRAY_SIZE(queue->fileio.blocks);
+		queue->fileio.next_dequeue = idx;
+	} else {
+		block = NULL;
 	}
+
 	spin_unlock_irq(&queue->list_lock);
 
 	return block;
@@ -539,6 +558,7 @@ size_t iio_dma_buffer_data_available(struct iio_buffer *buf)
 	struct iio_dma_buffer_queue *queue = iio_buffer_to_queue(buf);
 	struct iio_dma_buffer_block *block;
 	size_t data_available = 0;
+	unsigned int i;
 
 	/*
 	 * For counting the available bytes we'll use the size of the block not
@@ -552,8 +572,15 @@ size_t iio_dma_buffer_data_available(struct iio_buffer *buf)
 		data_available += queue->fileio.active_block->size;
 
 	spin_lock_irq(&queue->list_lock);
-	list_for_each_entry(block, &queue->outgoing, head)
-		data_available += block->size;
+
+	for (i = 0; i < ARRAY_SIZE(queue->fileio.blocks); i++) {
+		block = queue->fileio.blocks[i];
+
+		if (block != queue->fileio.active_block
+		    && block->state == IIO_BLOCK_STATE_DONE)
+			data_available += block->size;
+	}
+
 	spin_unlock_irq(&queue->list_lock);
 	mutex_unlock(&queue->lock);
 
@@ -617,7 +644,6 @@ int iio_dma_buffer_init(struct iio_dma_buffer_queue *queue,
 	queue->ops = ops;
 
 	INIT_LIST_HEAD(&queue->incoming);
-	INIT_LIST_HEAD(&queue->outgoing);
 
 	mutex_init(&queue->lock);
 	spin_lock_init(&queue->list_lock);
@@ -635,28 +661,9 @@ EXPORT_SYMBOL_GPL(iio_dma_buffer_init);
  */
 void iio_dma_buffer_exit(struct iio_dma_buffer_queue *queue)
 {
-	unsigned int i;
-
 	mutex_lock(&queue->lock);
 
-	spin_lock_irq(&queue->list_lock);
-	for (i = 0; i < ARRAY_SIZE(queue->fileio.blocks); i++) {
-		if (!queue->fileio.blocks[i])
-			continue;
-		queue->fileio.blocks[i]->state = IIO_BLOCK_STATE_DEAD;
-	}
-	INIT_LIST_HEAD(&queue->outgoing);
-	spin_unlock_irq(&queue->list_lock);
-
-	INIT_LIST_HEAD(&queue->incoming);
-
-	for (i = 0; i < ARRAY_SIZE(queue->fileio.blocks); i++) {
-		if (!queue->fileio.blocks[i])
-			continue;
-		iio_buffer_block_put(queue->fileio.blocks[i]);
-		queue->fileio.blocks[i] = NULL;
-	}
-	queue->fileio.active_block = NULL;
+	iio_dma_buffer_fileio_free(queue);
 	queue->ops = NULL;
 
 	mutex_unlock(&queue->lock);
diff --git a/drivers/iio/chemical/Kconfig b/drivers/iio/chemical/Kconfig
index c30657e10ee1..02649ab81b3c 100644
--- a/drivers/iio/chemical/Kconfig
+++ b/drivers/iio/chemical/Kconfig
@@ -5,6 +5,17 @@
 
 menu "Chemical Sensors"
 
+config AOSONG_AGS02MA
+	tristate "Aosong AGS02MA TVOC sensor driver"
+	depends on I2C
+	select CRC8
+	help
+	  Say Y here to build support for Aosong AGS02MA TVOC (Total Volatile
+	  Organic Compounds) sensor.
+
+	  To compile this driver as module, choose M here: the module will be
+	  called ags02ma.
+
 config ATLAS_PH_SENSOR
 	tristate "Atlas Scientific OEM SM sensors"
 	depends on I2C
diff --git a/drivers/iio/chemical/Makefile b/drivers/iio/chemical/Makefile
index a11e777a7a00..2f3dee8bb779 100644
--- a/drivers/iio/chemical/Makefile
+++ b/drivers/iio/chemical/Makefile
@@ -4,6 +4,7 @@
 #
 
 # When adding new entries keep the list in alphabetical order
+obj-$(CONFIG_AOSONG_AGS02MA)	+= ags02ma.o
 obj-$(CONFIG_ATLAS_PH_SENSOR)	+= atlas-sensor.o
 obj-$(CONFIG_ATLAS_EZO_SENSOR)	+= atlas-ezo-sensor.o
 obj-$(CONFIG_BME680) += bme680_core.o
diff --git a/drivers/iio/chemical/ags02ma.c b/drivers/iio/chemical/ags02ma.c
new file mode 100644
index 000000000000..8fcd80946543
--- /dev/null
+++ b/drivers/iio/chemical/ags02ma.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2023 Anshul Dalal <anshulusr@gmail.com>
+ *
+ * Driver for Aosong AGS02MA
+ *
+ * Datasheet:
+ *   https://asairsensors.com/wp-content/uploads/2021/09/AGS02MA.pdf
+ * Product Page:
+ *   http://www.aosong.com/m/en/products-33.html
+ */
+
+#include <linux/crc8.h>
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+
+#include <linux/iio/iio.h>
+
+#define AGS02MA_TVOC_READ_REG		   0x00
+#define AGS02MA_VERSION_REG		   0x11
+
+#define AGS02MA_VERSION_PROCESSING_DELAY   30
+#define AGS02MA_TVOC_READ_PROCESSING_DELAY 1500
+
+#define AGS02MA_CRC8_INIT		   0xff
+#define AGS02MA_CRC8_POLYNOMIAL		   0x31
+
+DECLARE_CRC8_TABLE(ags02ma_crc8_table);
+
+struct ags02ma_data {
+	struct i2c_client *client;
+};
+
+struct ags02ma_reading {
+	__be32 data;
+	u8 crc;
+} __packed;
+
+static int ags02ma_register_read(struct i2c_client *client, u8 reg, u16 delay,
+				 u32 *val)
+{
+	int ret;
+	u8 crc;
+	struct ags02ma_reading read_buffer;
+
+	ret = i2c_master_send(client, &reg, sizeof(reg));
+	if (ret < 0) {
+		dev_err(&client->dev,
+			"Failed to send data to register 0x%x: %d", reg, ret);
+		return ret;
+	}
+
+	/* Processing Delay, Check Table 7.7 in the datasheet */
+	msleep_interruptible(delay);
+
+	ret = i2c_master_recv(client, (u8 *)&read_buffer, sizeof(read_buffer));
+	if (ret < 0) {
+		dev_err(&client->dev,
+			"Failed to receive from register 0x%x: %d", reg, ret);
+		return ret;
+	}
+
+	crc = crc8(ags02ma_crc8_table, (u8 *)&read_buffer.data,
+		   sizeof(read_buffer.data), AGS02MA_CRC8_INIT);
+	if (crc != read_buffer.crc) {
+		dev_err(&client->dev, "CRC error\n");
+		return -EIO;
+	}
+
+	*val = be32_to_cpu(read_buffer.data);
+	return 0;
+}
+
+static int ags02ma_read_raw(struct iio_dev *iio_device,
+			    struct iio_chan_spec const *chan, int *val,
+			    int *val2, long mask)
+{
+	int ret;
+	struct ags02ma_data *data = iio_priv(iio_device);
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		ret = ags02ma_register_read(data->client, AGS02MA_TVOC_READ_REG,
+					    AGS02MA_TVOC_READ_PROCESSING_DELAY,
+					    val);
+		if (ret < 0)
+			return ret;
+		return IIO_VAL_INT;
+	case IIO_CHAN_INFO_SCALE:
+		/* The sensor reads data as ppb */
+		*val = 0;
+		*val2 = 100;
+		return IIO_VAL_INT_PLUS_NANO;
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct iio_info ags02ma_info = {
+	.read_raw = ags02ma_read_raw,
+};
+
+static const struct iio_chan_spec ags02ma_channel = {
+	.type = IIO_CONCENTRATION,
+	.channel2 = IIO_MOD_VOC,
+	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+		BIT(IIO_CHAN_INFO_SCALE),
+};
+
+static int ags02ma_probe(struct i2c_client *client)
+{
+	int ret;
+	struct ags02ma_data *data;
+	struct iio_dev *indio_dev;
+	u32 version;
+
+	indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*data));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	crc8_populate_msb(ags02ma_crc8_table, AGS02MA_CRC8_POLYNOMIAL);
+
+	ret = ags02ma_register_read(client, AGS02MA_VERSION_REG,
+				    AGS02MA_VERSION_PROCESSING_DELAY, &version);
+	if (ret < 0)
+		return dev_err_probe(&client->dev, ret,
+			      "Failed to read device version\n");
+	dev_dbg(&client->dev, "Aosong AGS02MA, Version: 0x%x", version);
+
+	data = iio_priv(indio_dev);
+	data->client = client;
+	indio_dev->info = &ags02ma_info;
+	indio_dev->channels = &ags02ma_channel;
+	indio_dev->num_channels = 1;
+	indio_dev->name = "ags02ma";
+
+	return devm_iio_device_register(&client->dev, indio_dev);
+}
+
+static const struct i2c_device_id ags02ma_id_table[] = {
+	{ "ags02ma" },
+	{ /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(i2c, ags02ma_id_table);
+
+static const struct of_device_id ags02ma_of_table[] = {
+	{ .compatible = "aosong,ags02ma" },
+	{ /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, ags02ma_of_table);
+
+static struct i2c_driver ags02ma_driver = {
+	.driver = {
+		.name = "ags02ma",
+		.of_match_table = ags02ma_of_table,
+	},
+	.id_table = ags02ma_id_table,
+	.probe = ags02ma_probe,
+};
+module_i2c_driver(ags02ma_driver);
+
+MODULE_AUTHOR("Anshul Dalal <anshulusr@gmail.com>");
+MODULE_DESCRIPTION("Aosong AGS02MA TVOC Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/iio/chemical/pms7003.c b/drivers/iio/chemical/pms7003.c
index e9857d93b307..b5cf15a515d2 100644
--- a/drivers/iio/chemical/pms7003.c
+++ b/drivers/iio/chemical/pms7003.c
@@ -211,13 +211,13 @@ static bool pms7003_frame_is_okay(struct pms7003_frame *frame)
 	return checksum == pms7003_calc_checksum(frame);
 }
 
-static int pms7003_receive_buf(struct serdev_device *serdev,
-			       const unsigned char *buf, size_t size)
+static ssize_t pms7003_receive_buf(struct serdev_device *serdev, const u8 *buf,
+				   size_t size)
 {
 	struct iio_dev *indio_dev = serdev_device_get_drvdata(serdev);
 	struct pms7003_state *state = iio_priv(indio_dev);
 	struct pms7003_frame *frame = &state->frame;
-	int num;
+	size_t num;
 
 	if (!frame->expected_length) {
 		u16 magic;
diff --git a/drivers/iio/chemical/scd30_serial.c b/drivers/iio/chemical/scd30_serial.c
index 3c519103d30b..a47654591e55 100644
--- a/drivers/iio/chemical/scd30_serial.c
+++ b/drivers/iio/chemical/scd30_serial.c
@@ -174,13 +174,13 @@ static int scd30_serdev_command(struct scd30_state *state, enum scd30_cmd cmd, u
 	return 0;
 }
 
-static int scd30_serdev_receive_buf(struct serdev_device *serdev,
-				    const unsigned char *buf, size_t size)
+static ssize_t scd30_serdev_receive_buf(struct serdev_device *serdev,
+					const u8 *buf, size_t size)
 {
 	struct iio_dev *indio_dev = serdev_device_get_drvdata(serdev);
 	struct scd30_serdev_priv *priv;
 	struct scd30_state *state;
-	int num;
+	size_t num;
 
 	if (!indio_dev)
 		return 0;
diff --git a/drivers/iio/chemical/sps30_serial.c b/drivers/iio/chemical/sps30_serial.c
index 164f4b3e025c..3afa89f8acc3 100644
--- a/drivers/iio/chemical/sps30_serial.c
+++ b/drivers/iio/chemical/sps30_serial.c
@@ -74,8 +74,8 @@ static int sps30_serial_xfer(struct sps30_state *state, const unsigned char *buf
 }
 
 static const struct {
-	unsigned char byte;
-	unsigned char byte2;
+	u8 byte;
+	u8 byte2;
 } sps30_serial_bytes[] = {
 	{ 0x11, 0x31 },
 	{ 0x13, 0x33 },
@@ -83,7 +83,7 @@ static const struct {
 	{ 0x7d, 0x5d },
 };
 
-static int sps30_serial_put_byte(unsigned char *buf, unsigned char byte)
+static int sps30_serial_put_byte(u8 *buf, u8 byte)
 {
 	int i;
 
@@ -102,7 +102,7 @@ static int sps30_serial_put_byte(unsigned char *buf, unsigned char byte)
 	return 1;
 }
 
-static char sps30_serial_get_byte(bool escaped, unsigned char byte2)
+static u8 sps30_serial_get_byte(bool escaped, u8 byte2)
 {
 	int i;
 
@@ -130,8 +130,8 @@ static unsigned char sps30_serial_calc_chksum(const unsigned char *buf, size_t n
 	return ~chksum;
 }
 
-static int sps30_serial_prep_frame(unsigned char *buf, unsigned char cmd,
-				   const unsigned char *arg, size_t arg_size)
+static int sps30_serial_prep_frame(u8 *buf, u8 cmd, const u8 *arg,
+				   size_t arg_size)
 {
 	unsigned char chksum;
 	int num = 0;
@@ -210,14 +210,14 @@ static int sps30_serial_command(struct sps30_state *state, unsigned char cmd,
 	return rsp_size;
 }
 
-static int sps30_serial_receive_buf(struct serdev_device *serdev,
-				    const unsigned char *buf, size_t size)
+static ssize_t sps30_serial_receive_buf(struct serdev_device *serdev,
+					const u8 *buf, size_t size)
 {
 	struct iio_dev *indio_dev = dev_get_drvdata(&serdev->dev);
 	struct sps30_serial_priv *priv;
 	struct sps30_state *state;
-	unsigned char byte;
 	size_t i;
+	u8 byte;
 
 	if (!indio_dev)
 		return 0;
diff --git a/drivers/iio/dac/Kconfig b/drivers/iio/dac/Kconfig
index 93b8be183de6..34eb40bb9529 100644
--- a/drivers/iio/dac/Kconfig
+++ b/drivers/iio/dac/Kconfig
@@ -400,6 +400,16 @@ config MCP4728
 	  To compile this driver as a module, choose M here: the module
 	  will be called mcp4728.
 
+config MCP4821
+	tristate "MCP4801/02/11/12/21/22 DAC driver"
+	depends on SPI
+	help
+	  Say yes here to build the driver for the Microchip MCP4801
+	  MCP4802, MCP4811, MCP4812, MCP4821 and MCP4822 DAC devices.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called mcp4821.
+
 config MCP4922
 	tristate "MCP4902, MCP4912, MCP4922 DAC driver"
 	depends on SPI
diff --git a/drivers/iio/dac/Makefile b/drivers/iio/dac/Makefile
index 5b2bac900d5a..55bf89739d14 100644
--- a/drivers/iio/dac/Makefile
+++ b/drivers/iio/dac/Makefile
@@ -42,6 +42,7 @@ obj-$(CONFIG_MAX5522) += max5522.o
 obj-$(CONFIG_MAX5821) += max5821.o
 obj-$(CONFIG_MCP4725) += mcp4725.o
 obj-$(CONFIG_MCP4728) += mcp4728.o
+obj-$(CONFIG_MCP4821) += mcp4821.o
 obj-$(CONFIG_MCP4922) += mcp4922.o
 obj-$(CONFIG_STM32_DAC_CORE) += stm32-dac-core.o
 obj-$(CONFIG_STM32_DAC) += stm32-dac.o
diff --git a/drivers/iio/dac/ad5791.c b/drivers/iio/dac/ad5791.c
index a4167454da81..75b549827e15 100644
--- a/drivers/iio/dac/ad5791.c
+++ b/drivers/iio/dac/ad5791.c
@@ -345,6 +345,7 @@ static int ad5791_probe(struct spi_device *spi)
 	struct iio_dev *indio_dev;
 	struct ad5791_state *st;
 	int ret, pos_voltage_uv = 0, neg_voltage_uv = 0;
+	bool use_rbuf_gain2;
 
 	indio_dev = devm_iio_device_alloc(&spi->dev, sizeof(*st));
 	if (!indio_dev)
@@ -379,6 +380,12 @@ static int ad5791_probe(struct spi_device *spi)
 	st->pwr_down = true;
 	st->spi = spi;
 
+	if (pdata)
+		use_rbuf_gain2 = pdata->use_rbuf_gain2;
+	else
+		use_rbuf_gain2 = device_property_read_bool(&spi->dev,
+							   "adi,rbuf-gain2-en");
+
 	if (!IS_ERR(st->reg_vss) && !IS_ERR(st->reg_vdd)) {
 		st->vref_mv = (pos_voltage_uv + neg_voltage_uv) / 1000;
 		st->vref_neg_mv = neg_voltage_uv / 1000;
@@ -398,7 +405,7 @@ static int ad5791_probe(struct spi_device *spi)
 
 
 	st->ctrl = AD5761_CTRL_LINCOMP(st->chip_info->get_lin_comp(st->vref_mv))
-		  | ((pdata && pdata->use_rbuf_gain2) ? 0 : AD5791_CTRL_RBUF) |
+		  | (use_rbuf_gain2 ? 0 : AD5791_CTRL_RBUF) |
 		  AD5791_CTRL_BIN2SC;
 
 	ret = ad5791_spi_write(st, AD5791_ADDR_CTRL, st->ctrl |
diff --git a/drivers/iio/dac/mcp4821.c b/drivers/iio/dac/mcp4821.c
new file mode 100644
index 000000000000..8a0480d33845
--- /dev/null
+++ b/drivers/iio/dac/mcp4821.c
@@ -0,0 +1,236 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2023 Anshul Dalal <anshulusr@gmail.com>
+ *
+ * Driver for Microchip MCP4801, MCP4802, MCP4811, MCP4812, MCP4821 and MCP4822
+ *
+ * Based on the work of:
+ *	Michael Welling (MCP4922 Driver)
+ *
+ * Datasheet:
+ *	MCP48x1: https://ww1.microchip.com/downloads/en/DeviceDoc/22244B.pdf
+ *	MCP48x2: https://ww1.microchip.com/downloads/en/DeviceDoc/20002249B.pdf
+ *
+ * TODO:
+ *	- Configurable gain
+ *	- Regulator control
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/spi/spi.h>
+
+#include <linux/iio/iio.h>
+#include <linux/iio/types.h>
+
+#include <asm/unaligned.h>
+
+#define MCP4821_ACTIVE_MODE BIT(12)
+#define MCP4802_SECOND_CHAN BIT(15)
+
+/* DAC uses an internal Voltage reference of 4.096V at a gain of 2x */
+#define MCP4821_2X_GAIN_VREF_MV 4096
+
+enum mcp4821_supported_drvice_ids {
+	ID_MCP4801,
+	ID_MCP4802,
+	ID_MCP4811,
+	ID_MCP4812,
+	ID_MCP4821,
+	ID_MCP4822,
+};
+
+struct mcp4821_state {
+	struct spi_device *spi;
+	u16 dac_value[2];
+};
+
+struct mcp4821_chip_info {
+	const char *name;
+	int num_channels;
+	const struct iio_chan_spec channels[2];
+};
+
+#define MCP4821_CHAN(channel_id, resolution)                          \
+	{                                                             \
+		.type = IIO_VOLTAGE, .output = 1, .indexed = 1,       \
+		.channel = (channel_id),                              \
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),         \
+		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), \
+		.scan_type = {                                        \
+			.realbits = (resolution),                     \
+			.shift = 12 - (resolution),                   \
+		},                                                    \
+	}
+
+static const struct mcp4821_chip_info mcp4821_chip_info_table[6] = {
+	[ID_MCP4801] = {
+			.name = "mcp4801",
+			.num_channels = 1,
+			.channels = {
+				MCP4821_CHAN(0, 8),
+			},
+	},
+	[ID_MCP4802] = {
+			.name = "mcp4802",
+			.num_channels = 2,
+			.channels = {
+				MCP4821_CHAN(0, 8),
+				MCP4821_CHAN(1, 8),
+			},
+	},
+	[ID_MCP4811] = {
+			.name = "mcp4811",
+			.num_channels = 1,
+			.channels = {
+				MCP4821_CHAN(0, 10),
+			},
+	},
+	[ID_MCP4812] = {
+			.name = "mcp4812",
+			.num_channels = 2,
+			.channels = {
+				MCP4821_CHAN(0, 10),
+				MCP4821_CHAN(1, 10),
+			},
+	},
+	[ID_MCP4821] = {
+			.name = "mcp4821",
+			.num_channels = 1,
+			.channels = {
+				MCP4821_CHAN(0, 12),
+			},
+	},
+	[ID_MCP4822] = {
+			.name = "mcp4822",
+			.num_channels = 2,
+			.channels = {
+				MCP4821_CHAN(0, 12),
+				MCP4821_CHAN(1, 12),
+			},
+	},
+};
+
+static int mcp4821_read_raw(struct iio_dev *indio_dev,
+			    struct iio_chan_spec const *chan, int *val,
+			    int *val2, long mask)
+{
+	struct mcp4821_state *state;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		state = iio_priv(indio_dev);
+		*val = state->dac_value[chan->channel];
+		return IIO_VAL_INT;
+	case IIO_CHAN_INFO_SCALE:
+		*val = MCP4821_2X_GAIN_VREF_MV;
+		*val2 = chan->scan_type.realbits;
+		return IIO_VAL_FRACTIONAL_LOG2;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int mcp4821_write_raw(struct iio_dev *indio_dev,
+			     struct iio_chan_spec const *chan, int val,
+			     int val2, long mask)
+{
+	struct mcp4821_state *state = iio_priv(indio_dev);
+	u16 write_val;
+	__be16 write_buffer;
+	int ret;
+
+	if (val2 != 0)
+		return -EINVAL;
+
+	if (val < 0 || val >= BIT(chan->scan_type.realbits))
+		return -EINVAL;
+
+	if (mask != IIO_CHAN_INFO_RAW)
+		return -EINVAL;
+
+	write_val = MCP4821_ACTIVE_MODE | val << chan->scan_type.shift;
+	if (chan->channel)
+		write_val |= MCP4802_SECOND_CHAN;
+
+	write_buffer = cpu_to_be16(write_val);
+	ret = spi_write(state->spi, &write_buffer, sizeof(write_buffer));
+	if (ret) {
+		dev_err(&state->spi->dev, "Failed to write to device: %d", ret);
+		return ret;
+	}
+
+	state->dac_value[chan->channel] = val;
+
+	return 0;
+}
+
+static const struct iio_info mcp4821_info = {
+	.read_raw = &mcp4821_read_raw,
+	.write_raw = &mcp4821_write_raw,
+};
+
+static int mcp4821_probe(struct spi_device *spi)
+{
+	struct iio_dev *indio_dev;
+	struct mcp4821_state *state;
+	const struct mcp4821_chip_info *info;
+
+	indio_dev = devm_iio_device_alloc(&spi->dev, sizeof(*state));
+	if (indio_dev == NULL)
+		return -ENOMEM;
+
+	state = iio_priv(indio_dev);
+	state->spi = spi;
+
+	info = spi_get_device_match_data(spi);
+	indio_dev->name = info->name;
+	indio_dev->info = &mcp4821_info;
+	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->channels = info->channels;
+	indio_dev->num_channels = info->num_channels;
+
+	return devm_iio_device_register(&spi->dev, indio_dev);
+}
+
+#define MCP4821_COMPATIBLE(of_compatible, id)        \
+	{                                            \
+		.compatible = of_compatible,         \
+		.data = &mcp4821_chip_info_table[id] \
+	}
+
+static const struct of_device_id mcp4821_of_table[] = {
+	MCP4821_COMPATIBLE("microchip,mcp4801", ID_MCP4801),
+	MCP4821_COMPATIBLE("microchip,mcp4802", ID_MCP4802),
+	MCP4821_COMPATIBLE("microchip,mcp4811", ID_MCP4811),
+	MCP4821_COMPATIBLE("microchip,mcp4812", ID_MCP4812),
+	MCP4821_COMPATIBLE("microchip,mcp4821", ID_MCP4821),
+	MCP4821_COMPATIBLE("microchip,mcp4822", ID_MCP4822),
+	{ /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, mcp4821_of_table);
+
+static const struct spi_device_id mcp4821_id_table[] = {
+	{ "mcp4801", (kernel_ulong_t)&mcp4821_chip_info_table[ID_MCP4801]},
+	{ "mcp4802", (kernel_ulong_t)&mcp4821_chip_info_table[ID_MCP4802]},
+	{ "mcp4811", (kernel_ulong_t)&mcp4821_chip_info_table[ID_MCP4811]},
+	{ "mcp4812", (kernel_ulong_t)&mcp4821_chip_info_table[ID_MCP4812]},
+	{ "mcp4821", (kernel_ulong_t)&mcp4821_chip_info_table[ID_MCP4821]},
+	{ "mcp4822", (kernel_ulong_t)&mcp4821_chip_info_table[ID_MCP4822]},
+	{ /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(spi, mcp4821_id_table);
+
+static struct spi_driver mcp4821_driver = {
+	.driver = {
+		.name = "mcp4821",
+		.of_match_table = mcp4821_of_table,
+	},
+	.probe = mcp4821_probe,
+	.id_table = mcp4821_id_table,
+};
+module_spi_driver(mcp4821_driver);
+
+MODULE_AUTHOR("Anshul Dalal <anshulusr@gmail.com>");
+MODULE_DESCRIPTION("Microchip MCP4821 DAC Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/iio/frequency/adf4377.c b/drivers/iio/frequency/adf4377.c
index 26abecbd51e0..9284c13f1abb 100644
--- a/drivers/iio/frequency/adf4377.c
+++ b/drivers/iio/frequency/adf4377.c
@@ -870,7 +870,6 @@ static const struct iio_chan_spec adf4377_channels[] = {
 static int adf4377_properties_parse(struct adf4377_state *st)
 {
 	struct spi_device *spi = st->spi;
-	const char *str;
 	int ret;
 
 	st->clkin = devm_clk_get_enabled(&spi->dev, "ref_in");
@@ -896,16 +895,13 @@ static int adf4377_properties_parse(struct adf4377_state *st)
 		return dev_err_probe(&spi->dev, PTR_ERR(st->gpio_enclk2),
 				     "failed to get the CE GPIO\n");
 
-	ret = device_property_read_string(&spi->dev, "adi,muxout-select", &str);
-	if (ret) {
-		st->muxout_select = ADF4377_MUXOUT_HIGH_Z;
-	} else {
-		ret = match_string(adf4377_muxout_modes, ARRAY_SIZE(adf4377_muxout_modes), str);
-		if (ret < 0)
-			return ret;
-
+	ret = device_property_match_property_string(&spi->dev, "adi,muxout-select",
+						    adf4377_muxout_modes,
+						    ARRAY_SIZE(adf4377_muxout_modes));
+	if (ret >= 0)
 		st->muxout_select = ret;
-	}
+	else
+		st->muxout_select = ADF4377_MUXOUT_HIGH_Z;
 
 	return 0;
 }
diff --git a/drivers/iio/frequency/admv1014.c b/drivers/iio/frequency/admv1014.c
index bb5e1feef42b..b46b73b89eb7 100644
--- a/drivers/iio/frequency/admv1014.c
+++ b/drivers/iio/frequency/admv1014.c
@@ -710,7 +710,6 @@ static int admv1014_init(struct admv1014_state *st)
 
 static int admv1014_properties_parse(struct admv1014_state *st)
 {
-	const char *str;
 	unsigned int i;
 	struct spi_device *spi = st->spi;
 	int ret;
@@ -719,27 +718,21 @@ static int admv1014_properties_parse(struct admv1014_state *st)
 
 	st->p1db_comp = device_property_read_bool(&spi->dev, "adi,p1db-compensation-enable");
 
-	ret = device_property_read_string(&spi->dev, "adi,input-mode", &str);
-	if (ret) {
-		st->input_mode = ADMV1014_IQ_MODE;
-	} else {
-		ret = match_string(input_mode_names, ARRAY_SIZE(input_mode_names), str);
-		if (ret < 0)
-			return ret;
-
+	ret = device_property_match_property_string(&spi->dev, "adi,input-mode",
+						    input_mode_names,
+						    ARRAY_SIZE(input_mode_names));
+	if (ret >= 0)
 		st->input_mode = ret;
-	}
-
-	ret = device_property_read_string(&spi->dev, "adi,quad-se-mode", &str);
-	if (ret) {
-		st->quad_se_mode = ADMV1014_SE_MODE_POS;
-	} else {
-		ret = match_string(quad_se_mode_names, ARRAY_SIZE(quad_se_mode_names), str);
-		if (ret < 0)
-			return ret;
+	else
+		st->input_mode = ADMV1014_IQ_MODE;
 
+	ret = device_property_match_property_string(&spi->dev, "adi,quad-se-mode",
+						    quad_se_mode_names,
+						    ARRAY_SIZE(quad_se_mode_names));
+	if (ret >= 0)
 		st->quad_se_mode = ADMV1014_SE_MODE_POS + (ret * 3);
-	}
+	else
+		st->quad_se_mode = ADMV1014_SE_MODE_POS;
 
 	for (i = 0; i < ADMV1014_NUM_REGULATORS; ++i)
 		st->regulators[i].supply = admv1014_reg_name[i];
diff --git a/drivers/iio/humidity/Kconfig b/drivers/iio/humidity/Kconfig
index 2de5494e7c22..b15b7a3b66d5 100644
--- a/drivers/iio/humidity/Kconfig
+++ b/drivers/iio/humidity/Kconfig
@@ -48,6 +48,18 @@ config HDC2010
 	  To compile this driver as a module, choose M here: the module
 	  will be called hdc2010.
 
+config HDC3020
+	tristate "TI HDC3020 relative humidity and temperature sensor"
+	depends on I2C
+	select CRC8
+	help
+	  Say yes here to build support for the Texas Instruments
+	  HDC3020, HDC3021 and HDC3022 relative humidity and temperature
+	  sensors.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called hdc3020.
+
 config HID_SENSOR_HUMIDITY
 	tristate "HID Environmental humidity sensor"
 	depends on HID_SENSOR_HUB
diff --git a/drivers/iio/humidity/Makefile b/drivers/iio/humidity/Makefile
index f19ff3de97c5..5fbeef299f61 100644
--- a/drivers/iio/humidity/Makefile
+++ b/drivers/iio/humidity/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_AM2315) += am2315.o
 obj-$(CONFIG_DHT11) += dht11.o
 obj-$(CONFIG_HDC100X) += hdc100x.o
 obj-$(CONFIG_HDC2010) += hdc2010.o
+obj-$(CONFIG_HDC3020) += hdc3020.o
 obj-$(CONFIG_HID_SENSOR_HUMIDITY) += hid-sensor-humidity.o
 
 hts221-y := hts221_core.o \
diff --git a/drivers/iio/humidity/hdc3020.c b/drivers/iio/humidity/hdc3020.c
new file mode 100644
index 000000000000..ed70415512f6
--- /dev/null
+++ b/drivers/iio/humidity/hdc3020.c
@@ -0,0 +1,473 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * hdc3020.c - Support for the TI HDC3020,HDC3021 and HDC3022
+ * temperature + relative humidity sensors
+ *
+ * Copyright (C) 2023
+ *
+ * Datasheet: https://www.ti.com/lit/ds/symlink/hdc3020.pdf
+ */
+
+#include <linux/bitops.h>
+#include <linux/cleanup.h>
+#include <linux/crc8.h>
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+
+#include <asm/unaligned.h>
+
+#include <linux/iio/iio.h>
+
+#define HDC3020_HEATER_CMD_MSB		0x30 /* shared by all heater commands */
+#define HDC3020_HEATER_ENABLE		0x6D
+#define HDC3020_HEATER_DISABLE		0x66
+#define HDC3020_HEATER_CONFIG		0x6E
+
+#define HDC3020_READ_RETRY_TIMES	10
+#define HDC3020_BUSY_DELAY_MS		10
+
+#define HDC3020_CRC8_POLYNOMIAL		0x31
+
+static const u8 HDC3020_S_AUTO_10HZ_MOD0[2] = { 0x27, 0x37 };
+
+static const u8 HDC3020_EXIT_AUTO[2] = { 0x30, 0x93 };
+
+static const u8 HDC3020_R_T_RH_AUTO[2] = { 0xE0, 0x00 };
+static const u8 HDC3020_R_T_LOW_AUTO[2] = { 0xE0, 0x02 };
+static const u8 HDC3020_R_T_HIGH_AUTO[2] = { 0xE0, 0x03 };
+static const u8 HDC3020_R_RH_LOW_AUTO[2] = { 0xE0, 0x04 };
+static const u8 HDC3020_R_RH_HIGH_AUTO[2] = { 0xE0, 0x05 };
+
+struct hdc3020_data {
+	struct i2c_client *client;
+	/*
+	 * Ensure that the sensor configuration (currently only heater is
+	 * supported) will not be changed during the process of reading
+	 * sensor data (this driver will try HDC3020_READ_RETRY_TIMES times
+	 * if the device does not respond).
+	 */
+	struct mutex lock;
+};
+
+static const int hdc3020_heater_vals[] = {0, 1, 0x3FFF};
+
+static const struct iio_chan_spec hdc3020_channels[] = {
+	{
+		.type = IIO_TEMP,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+		BIT(IIO_CHAN_INFO_SCALE) | BIT(IIO_CHAN_INFO_PEAK) |
+		BIT(IIO_CHAN_INFO_TROUGH) | BIT(IIO_CHAN_INFO_OFFSET),
+	},
+	{
+		.type = IIO_HUMIDITYRELATIVE,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+		BIT(IIO_CHAN_INFO_SCALE) | BIT(IIO_CHAN_INFO_PEAK) |
+		BIT(IIO_CHAN_INFO_TROUGH),
+	},
+	{
+		/*
+		 * For setting the internal heater, which can be switched on to
+		 * prevent or remove any condensation that may develop when the
+		 * ambient environment approaches its dew point temperature.
+		 */
+		.type = IIO_CURRENT,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
+		.info_mask_separate_available = BIT(IIO_CHAN_INFO_RAW),
+		.output = 1,
+	},
+};
+
+DECLARE_CRC8_TABLE(hdc3020_crc8_table);
+
+static int hdc3020_write_bytes(struct hdc3020_data *data, const u8 *buf, u8 len)
+{
+	struct i2c_client *client = data->client;
+	struct i2c_msg msg;
+	int ret, cnt;
+
+	msg.addr = client->addr;
+	msg.flags = 0;
+	msg.buf = (char *)buf;
+	msg.len = len;
+
+	/*
+	 * During the measurement process, HDC3020 will not return data.
+	 * So wait for a while and try again
+	 */
+	for (cnt = 0; cnt < HDC3020_READ_RETRY_TIMES; cnt++) {
+		ret = i2c_transfer(client->adapter, &msg, 1);
+		if (ret == 1)
+			return 0;
+
+		mdelay(HDC3020_BUSY_DELAY_MS);
+	}
+	dev_err(&client->dev, "Could not write sensor command\n");
+
+	return -ETIMEDOUT;
+}
+
+static int hdc3020_read_bytes(struct hdc3020_data *data, const u8 *buf,
+			      void *val, int len)
+{
+	int ret, cnt;
+	struct i2c_client *client = data->client;
+	struct i2c_msg msg[2] = {
+		[0] = {
+			.addr = client->addr,
+			.flags = 0,
+			.buf = (char *)buf,
+			.len = 2,
+		},
+		[1] = {
+			.addr = client->addr,
+			.flags = I2C_M_RD,
+			.buf = val,
+			.len = len,
+		},
+	};
+
+	/*
+	 * During the measurement process, HDC3020 will not return data.
+	 * So wait for a while and try again
+	 */
+	for (cnt = 0; cnt < HDC3020_READ_RETRY_TIMES; cnt++) {
+		ret = i2c_transfer(client->adapter, msg, 2);
+		if (ret == 2)
+			return 0;
+
+		mdelay(HDC3020_BUSY_DELAY_MS);
+	}
+	dev_err(&client->dev, "Could not read sensor data\n");
+
+	return -ETIMEDOUT;
+}
+
+static int hdc3020_read_measurement(struct hdc3020_data *data,
+				    enum iio_chan_type type, int *val)
+{
+	u8 crc, buf[6];
+	int ret;
+
+	ret = hdc3020_read_bytes(data, HDC3020_R_T_RH_AUTO, buf, 6);
+	if (ret < 0)
+		return ret;
+
+	/* CRC check of the temperature measurement */
+	crc = crc8(hdc3020_crc8_table, buf, 2, CRC8_INIT_VALUE);
+	if (crc != buf[2])
+		return -EINVAL;
+
+	/* CRC check of the relative humidity measurement */
+	crc = crc8(hdc3020_crc8_table, buf + 3, 2, CRC8_INIT_VALUE);
+	if (crc != buf[5])
+		return -EINVAL;
+
+	if (type == IIO_TEMP)
+		*val = get_unaligned_be16(buf);
+	else if (type == IIO_HUMIDITYRELATIVE)
+		*val = get_unaligned_be16(&buf[3]);
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * After exiting the automatic measurement mode or resetting, the peak
+ * value will be reset to the default value
+ * This method is used to get the highest temp measured during automatic
+ * measurement
+ */
+static int hdc3020_read_high_peak_t(struct hdc3020_data *data, int *val)
+{
+	u8 crc, buf[3];
+	int ret;
+
+	ret = hdc3020_read_bytes(data, HDC3020_R_T_HIGH_AUTO, buf, 3);
+	if (ret < 0)
+		return ret;
+
+	crc = crc8(hdc3020_crc8_table, buf, 2, CRC8_INIT_VALUE);
+	if (crc != buf[2])
+		return -EINVAL;
+
+	*val = get_unaligned_be16(buf);
+
+	return 0;
+}
+
+/*
+ * This method is used to get the lowest temp measured during automatic
+ * measurement
+ */
+static int hdc3020_read_low_peak_t(struct hdc3020_data *data, int *val)
+{
+	u8 crc, buf[3];
+	int ret;
+
+	ret = hdc3020_read_bytes(data, HDC3020_R_T_LOW_AUTO, buf, 3);
+	if (ret < 0)
+		return ret;
+
+	crc = crc8(hdc3020_crc8_table, buf, 2, CRC8_INIT_VALUE);
+	if (crc != buf[2])
+		return -EINVAL;
+
+	*val = get_unaligned_be16(buf);
+
+	return 0;
+}
+
+/*
+ * This method is used to get the highest humidity measured during automatic
+ * measurement
+ */
+static int hdc3020_read_high_peak_rh(struct hdc3020_data *data, int *val)
+{
+	u8 crc, buf[3];
+	int ret;
+
+	ret = hdc3020_read_bytes(data, HDC3020_R_RH_HIGH_AUTO, buf, 3);
+	if (ret < 0)
+		return ret;
+
+	crc = crc8(hdc3020_crc8_table, buf, 2, CRC8_INIT_VALUE);
+	if (crc != buf[2])
+		return -EINVAL;
+
+	*val = get_unaligned_be16(buf);
+
+	return 0;
+}
+
+/*
+ * This method is used to get the lowest humidity measured during automatic
+ * measurement
+ */
+static int hdc3020_read_low_peak_rh(struct hdc3020_data *data, int *val)
+{
+	u8 crc, buf[3];
+	int ret;
+
+	ret = hdc3020_read_bytes(data, HDC3020_R_RH_LOW_AUTO, buf, 3);
+	if (ret < 0)
+		return ret;
+
+	crc = crc8(hdc3020_crc8_table, buf, 2, CRC8_INIT_VALUE);
+	if (crc != buf[2])
+		return -EINVAL;
+
+	*val = get_unaligned_be16(buf);
+
+	return 0;
+}
+
+static int hdc3020_read_raw(struct iio_dev *indio_dev,
+			    struct iio_chan_spec const *chan, int *val,
+			    int *val2, long mask)
+{
+	struct hdc3020_data *data = iio_priv(indio_dev);
+	int ret;
+
+	if (chan->type != IIO_TEMP && chan->type != IIO_HUMIDITYRELATIVE)
+		return -EINVAL;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW: {
+		guard(mutex)(&data->lock);
+		ret = hdc3020_read_measurement(data, chan->type, val);
+		if (ret < 0)
+			return ret;
+
+		return IIO_VAL_INT;
+	}
+	case IIO_CHAN_INFO_PEAK: {
+		guard(mutex)(&data->lock);
+		if (chan->type == IIO_TEMP) {
+			ret = hdc3020_read_high_peak_t(data, val);
+			if (ret < 0)
+				return ret;
+		} else {
+			ret = hdc3020_read_high_peak_rh(data, val);
+			if (ret < 0)
+				return ret;
+		}
+		return IIO_VAL_INT;
+	}
+	case IIO_CHAN_INFO_TROUGH: {
+		guard(mutex)(&data->lock);
+		if (chan->type == IIO_TEMP) {
+			ret = hdc3020_read_low_peak_t(data, val);
+			if (ret < 0)
+				return ret;
+		} else {
+			ret = hdc3020_read_low_peak_rh(data, val);
+			if (ret < 0)
+				return ret;
+		}
+		return IIO_VAL_INT;
+	}
+	case IIO_CHAN_INFO_SCALE:
+		*val2 = 65536;
+		if (chan->type == IIO_TEMP)
+			*val = 175;
+		else
+			*val = 100;
+		return IIO_VAL_FRACTIONAL;
+
+	case IIO_CHAN_INFO_OFFSET:
+		if (chan->type != IIO_TEMP)
+			return -EINVAL;
+
+		*val = -16852;
+		return IIO_VAL_INT;
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static int hdc3020_read_available(struct iio_dev *indio_dev,
+				  struct iio_chan_spec const *chan,
+				  const int **vals,
+				  int *type, int *length, long mask)
+{
+	if (mask != IIO_CHAN_INFO_RAW || chan->type != IIO_CURRENT)
+		return -EINVAL;
+
+	*vals = hdc3020_heater_vals;
+	*type = IIO_VAL_INT;
+
+	return IIO_AVAIL_RANGE;
+}
+
+static int hdc3020_update_heater(struct hdc3020_data *data, int val)
+{
+	u8 buf[5];
+	int ret;
+
+	if (val < hdc3020_heater_vals[0] || val > hdc3020_heater_vals[2])
+		return -EINVAL;
+
+	buf[0] = HDC3020_HEATER_CMD_MSB;
+
+	if (!val) {
+		buf[1] = HDC3020_HEATER_DISABLE;
+		return hdc3020_write_bytes(data, buf, 2);
+	}
+
+	buf[1] = HDC3020_HEATER_CONFIG;
+	put_unaligned_be16(val & GENMASK(13, 0), &buf[2]);
+	buf[4] = crc8(hdc3020_crc8_table, buf + 2, 2, CRC8_INIT_VALUE);
+	ret = hdc3020_write_bytes(data, buf, 5);
+	if (ret < 0)
+		return ret;
+
+	buf[1] = HDC3020_HEATER_ENABLE;
+
+	return hdc3020_write_bytes(data, buf, 2);
+}
+
+static int hdc3020_write_raw(struct iio_dev *indio_dev,
+			     struct iio_chan_spec const *chan,
+			     int val, int val2, long mask)
+{
+	struct hdc3020_data *data = iio_priv(indio_dev);
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		if (chan->type != IIO_CURRENT)
+			return -EINVAL;
+
+		guard(mutex)(&data->lock);
+		return hdc3020_update_heater(data, val);
+	}
+
+	return -EINVAL;
+}
+
+static const struct iio_info hdc3020_info = {
+	.read_raw = hdc3020_read_raw,
+	.write_raw = hdc3020_write_raw,
+	.read_avail = hdc3020_read_available,
+};
+
+static void hdc3020_stop(void *data)
+{
+	hdc3020_write_bytes((struct hdc3020_data *)data, HDC3020_EXIT_AUTO, 2);
+}
+
+static int hdc3020_probe(struct i2c_client *client)
+{
+	struct iio_dev *indio_dev;
+	struct hdc3020_data *data;
+	int ret;
+
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C))
+		return -EOPNOTSUPP;
+
+	indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*data));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	data = iio_priv(indio_dev);
+	data->client = client;
+	mutex_init(&data->lock);
+
+	crc8_populate_msb(hdc3020_crc8_table, HDC3020_CRC8_POLYNOMIAL);
+
+	indio_dev->name = "hdc3020";
+	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->info = &hdc3020_info;
+	indio_dev->channels = hdc3020_channels;
+	indio_dev->num_channels = ARRAY_SIZE(hdc3020_channels);
+
+	ret = hdc3020_write_bytes(data, HDC3020_S_AUTO_10HZ_MOD0, 2);
+	if (ret)
+		return dev_err_probe(&client->dev, ret,
+				     "Unable to set up measurement\n");
+
+	ret = devm_add_action_or_reset(&data->client->dev, hdc3020_stop, data);
+	if (ret)
+		return ret;
+
+	ret = devm_iio_device_register(&data->client->dev, indio_dev);
+	if (ret)
+		return dev_err_probe(&client->dev, ret, "Failed to add device");
+
+	return 0;
+}
+
+static const struct i2c_device_id hdc3020_id[] = {
+	{ "hdc3020" },
+	{ "hdc3021" },
+	{ "hdc3022" },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, hdc3020_id);
+
+static const struct of_device_id hdc3020_dt_ids[] = {
+	{ .compatible = "ti,hdc3020" },
+	{ .compatible = "ti,hdc3021" },
+	{ .compatible = "ti,hdc3022" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, hdc3020_dt_ids);
+
+static struct i2c_driver hdc3020_driver = {
+	.driver = {
+		.name = "hdc3020",
+		.of_match_table = hdc3020_dt_ids,
+	},
+	.probe = hdc3020_probe,
+	.id_table = hdc3020_id,
+};
+module_i2c_driver(hdc3020_driver);
+
+MODULE_AUTHOR("Javier Carrasco <javier.carrasco.cruz@gmail.com>");
+MODULE_AUTHOR("Li peiyu <579lpy@gmail.com>");
+MODULE_DESCRIPTION("TI HDC3020 humidity and temperature sensor driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/iio/imu/Kconfig b/drivers/iio/imu/Kconfig
index c2f97629e9cd..52a155ff3250 100644
--- a/drivers/iio/imu/Kconfig
+++ b/drivers/iio/imu/Kconfig
@@ -53,6 +53,7 @@ config ADIS16480
 	  ADIS16485, ADIS16488 inertial sensors.
 
 source "drivers/iio/imu/bmi160/Kconfig"
+source "drivers/iio/imu/bmi323/Kconfig"
 source "drivers/iio/imu/bno055/Kconfig"
 
 config FXOS8700
diff --git a/drivers/iio/imu/Makefile b/drivers/iio/imu/Makefile
index 6eb612034722..7e2d7d5c3b7b 100644
--- a/drivers/iio/imu/Makefile
+++ b/drivers/iio/imu/Makefile
@@ -15,6 +15,7 @@ adis_lib-$(CONFIG_IIO_ADIS_LIB_BUFFER) += adis_buffer.o
 obj-$(CONFIG_IIO_ADIS_LIB) += adis_lib.o
 
 obj-y += bmi160/
+obj-y += bmi323/
 obj-y += bno055/
 
 obj-$(CONFIG_FXOS8700) += fxos8700_core.o
diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c
index bc40240b29e2..495caf4ce87a 100644
--- a/drivers/iio/imu/adis.c
+++ b/drivers/iio/imu/adis.c
@@ -44,8 +44,6 @@ int __adis_write_reg(struct adis *adis, unsigned int reg, unsigned int value,
 			.cs_change = 1,
 			.delay.value = adis->data->write_delay,
 			.delay.unit = SPI_DELAY_UNIT_USECS,
-			.cs_change_delay.value = adis->data->cs_change_delay,
-			.cs_change_delay.unit = SPI_DELAY_UNIT_USECS,
 		}, {
 			.tx_buf = adis->tx + 2,
 			.bits_per_word = 8,
@@ -53,8 +51,6 @@ int __adis_write_reg(struct adis *adis, unsigned int reg, unsigned int value,
 			.cs_change = 1,
 			.delay.value = adis->data->write_delay,
 			.delay.unit = SPI_DELAY_UNIT_USECS,
-			.cs_change_delay.value = adis->data->cs_change_delay,
-			.cs_change_delay.unit = SPI_DELAY_UNIT_USECS,
 		}, {
 			.tx_buf = adis->tx + 4,
 			.bits_per_word = 8,
@@ -62,8 +58,6 @@ int __adis_write_reg(struct adis *adis, unsigned int reg, unsigned int value,
 			.cs_change = 1,
 			.delay.value = adis->data->write_delay,
 			.delay.unit = SPI_DELAY_UNIT_USECS,
-			.cs_change_delay.value = adis->data->cs_change_delay,
-			.cs_change_delay.unit = SPI_DELAY_UNIT_USECS,
 		}, {
 			.tx_buf = adis->tx + 6,
 			.bits_per_word = 8,
@@ -144,8 +138,6 @@ int __adis_read_reg(struct adis *adis, unsigned int reg, unsigned int *val,
 			.cs_change = 1,
 			.delay.value = adis->data->write_delay,
 			.delay.unit = SPI_DELAY_UNIT_USECS,
-			.cs_change_delay.value = adis->data->cs_change_delay,
-			.cs_change_delay.unit = SPI_DELAY_UNIT_USECS,
 		}, {
 			.tx_buf = adis->tx + 2,
 			.bits_per_word = 8,
@@ -153,8 +145,6 @@ int __adis_read_reg(struct adis *adis, unsigned int reg, unsigned int *val,
 			.cs_change = 1,
 			.delay.value = adis->data->read_delay,
 			.delay.unit = SPI_DELAY_UNIT_USECS,
-			.cs_change_delay.value = adis->data->cs_change_delay,
-			.cs_change_delay.unit = SPI_DELAY_UNIT_USECS,
 		}, {
 			.tx_buf = adis->tx + 4,
 			.rx_buf = adis->rx,
@@ -163,8 +153,6 @@ int __adis_read_reg(struct adis *adis, unsigned int reg, unsigned int *val,
 			.cs_change = 1,
 			.delay.value = adis->data->read_delay,
 			.delay.unit = SPI_DELAY_UNIT_USECS,
-			.cs_change_delay.value = adis->data->cs_change_delay,
-			.cs_change_delay.unit = SPI_DELAY_UNIT_USECS,
 		}, {
 			.rx_buf = adis->rx + 2,
 			.bits_per_word = 8,
@@ -524,6 +512,12 @@ int adis_init(struct adis *adis, struct iio_dev *indio_dev,
 	}
 
 	mutex_init(&adis->state_lock);
+
+	if (!spi->cs_inactive.value) {
+		spi->cs_inactive.value = data->cs_change_delay;
+		spi->cs_inactive.unit = SPI_DELAY_UNIT_USECS;
+	}
+
 	adis->spi = spi;
 	adis->data = data;
 	iio_device_set_drvdata(indio_dev, adis);
diff --git a/drivers/iio/imu/bmi323/Kconfig b/drivers/iio/imu/bmi323/Kconfig
new file mode 100644
index 000000000000..ab37b285393c
--- /dev/null
+++ b/drivers/iio/imu/bmi323/Kconfig
@@ -0,0 +1,33 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# BMI323 IMU driver
+#
+
+config BMI323
+	tristate
+	select IIO_BUFFER
+	select IIO_TRIGGERED_BUFFER
+
+config BMI323_I2C
+	tristate "Bosch BMI323 I2C driver"
+	depends on I2C
+	select BMI323
+	select REGMAP_I2C
+	help
+	  Enable support for the Bosch BMI323 6-Axis IMU connected to I2C
+	  interface.
+
+	  This driver can also be built as a module. If so, the module will be
+	  called bmi323_i2c.
+
+config BMI323_SPI
+	tristate "Bosch BMI323 SPI driver"
+	depends on SPI
+	select BMI323
+	select REGMAP_SPI
+	help
+	  Enable support for the Bosch BMI323 6-Axis IMU connected to SPI
+	  interface.
+
+	  This driver can also be built as a module. If so, the module will be
+	  called bmi323_spi.
diff --git a/drivers/iio/imu/bmi323/Makefile b/drivers/iio/imu/bmi323/Makefile
new file mode 100644
index 000000000000..a6a6dc0207c9
--- /dev/null
+++ b/drivers/iio/imu/bmi323/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for Bosch BMI323 IMU
+#
+obj-$(CONFIG_BMI323) += bmi323_core.o
+obj-$(CONFIG_BMI323_I2C) += bmi323_i2c.o
+obj-$(CONFIG_BMI323_SPI) += bmi323_spi.o
diff --git a/drivers/iio/imu/bmi323/bmi323.h b/drivers/iio/imu/bmi323/bmi323.h
new file mode 100644
index 000000000000..dff126d41658
--- /dev/null
+++ b/drivers/iio/imu/bmi323/bmi323.h
@@ -0,0 +1,209 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * IIO driver for Bosch BMI323 6-Axis IMU
+ *
+ * Copyright (C) 2023, Jagath Jog J <jagathjog1996@gmail.com>
+ */
+
+#ifndef _BMI323_H_
+#define _BMI323_H_
+
+#include <linux/bits.h>
+#include <linux/regmap.h>
+#include <linux/units.h>
+
+#define BMI323_I2C_DUMMY			2
+#define BMI323_SPI_DUMMY			1
+
+/* Register map */
+
+#define BMI323_CHIP_ID_REG			0x00
+#define BMI323_CHIP_ID_VAL			0x0043
+#define BMI323_CHIP_ID_MSK			GENMASK(7, 0)
+#define BMI323_ERR_REG				0x01
+#define BMI323_STATUS_REG			0x02
+#define BMI323_STATUS_POR_MSK			BIT(0)
+
+/* Accelero/Gyro/Temp data registers */
+#define BMI323_ACCEL_X_REG			0x03
+#define BMI323_GYRO_X_REG			0x06
+#define BMI323_TEMP_REG				0x09
+#define BMI323_ALL_CHAN_MSK			GENMASK(5, 0)
+
+/* Status registers */
+#define BMI323_STATUS_INT1_REG			0x0D
+#define BMI323_STATUS_INT2_REG			0x0E
+#define BMI323_STATUS_NOMOTION_MSK		BIT(0)
+#define BMI323_STATUS_MOTION_MSK		BIT(1)
+#define BMI323_STATUS_STP_WTR_MSK		BIT(5)
+#define BMI323_STATUS_TAP_MSK			BIT(8)
+#define BMI323_STATUS_ERROR_MSK			BIT(10)
+#define BMI323_STATUS_TMP_DRDY_MSK		BIT(11)
+#define BMI323_STATUS_GYR_DRDY_MSK		BIT(12)
+#define BMI323_STATUS_ACC_DRDY_MSK		BIT(13)
+#define BMI323_STATUS_ACC_GYR_DRDY_MSK		GENMASK(13, 12)
+#define BMI323_STATUS_FIFO_WTRMRK_MSK		BIT(14)
+#define BMI323_STATUS_FIFO_FULL_MSK		BIT(15)
+
+/* Feature registers */
+#define BMI323_FEAT_IO0_REG			0x10
+#define BMI323_FEAT_IO0_XYZ_NOMOTION_MSK	GENMASK(2, 0)
+#define BMI323_FEAT_IO0_XYZ_MOTION_MSK		GENMASK(5, 3)
+#define BMI323_FEAT_XYZ_MSK			GENMASK(2, 0)
+#define BMI323_FEAT_IO0_STP_CNT_MSK		BIT(9)
+#define BMI323_FEAT_IO0_S_TAP_MSK		BIT(12)
+#define BMI323_FEAT_IO0_D_TAP_MSK		BIT(13)
+#define BMI323_FEAT_IO1_REG			0x11
+#define BMI323_FEAT_IO1_ERR_MSK			GENMASK(3, 0)
+#define BMI323_FEAT_IO2_REG			0x12
+#define BMI323_FEAT_IO_STATUS_REG		0x14
+#define BMI323_FEAT_IO_STATUS_MSK		BIT(0)
+#define BMI323_FEAT_ENG_POLL			2000
+#define BMI323_FEAT_ENG_TIMEOUT			10000
+
+/* FIFO registers */
+#define BMI323_FIFO_FILL_LEVEL_REG		0x15
+#define BMI323_FIFO_DATA_REG			0x16
+
+/* Accelero/Gyro config registers */
+#define BMI323_ACC_CONF_REG			0x20
+#define BMI323_GYRO_CONF_REG			0x21
+#define BMI323_ACC_GYRO_CONF_MODE_MSK		GENMASK(14, 12)
+#define BMI323_ACC_GYRO_CONF_ODR_MSK		GENMASK(3, 0)
+#define BMI323_ACC_GYRO_CONF_SCL_MSK		GENMASK(6, 4)
+#define BMI323_ACC_GYRO_CONF_BW_MSK		BIT(7)
+#define BMI323_ACC_GYRO_CONF_AVG_MSK		GENMASK(10, 8)
+
+/* FIFO registers */
+#define BMI323_FIFO_WTRMRK_REG			0x35
+#define BMI323_FIFO_CONF_REG			0x36
+#define BMI323_FIFO_CONF_STP_FUL_MSK		BIT(0)
+#define BMI323_FIFO_CONF_ACC_GYR_EN_MSK		GENMASK(10, 9)
+#define BMI323_FIFO_ACC_GYR_MSK			GENMASK(1, 0)
+#define BMI323_FIFO_CTRL_REG			0x37
+#define BMI323_FIFO_FLUSH_MSK			BIT(0)
+
+/* Interrupt pin config registers */
+#define BMI323_IO_INT_CTR_REG			0x38
+#define BMI323_IO_INT1_LVL_MSK			BIT(0)
+#define BMI323_IO_INT1_OD_MSK			BIT(1)
+#define BMI323_IO_INT1_OP_EN_MSK		BIT(2)
+#define BMI323_IO_INT1_LVL_OD_OP_MSK		GENMASK(2, 0)
+#define BMI323_IO_INT2_LVL_MSK			BIT(8)
+#define BMI323_IO_INT2_OD_MSK			BIT(9)
+#define BMI323_IO_INT2_OP_EN_MSK		BIT(10)
+#define BMI323_IO_INT2_LVL_OD_OP_MSK		GENMASK(10, 8)
+#define BMI323_IO_INT_CONF_REG			0x39
+#define BMI323_IO_INT_LTCH_MSK			BIT(0)
+#define BMI323_INT_MAP1_REG			0x3A
+#define BMI323_INT_MAP2_REG			0x3B
+#define BMI323_NOMOTION_MSK			GENMASK(1, 0)
+#define BMI323_MOTION_MSK			GENMASK(3, 2)
+#define BMI323_STEP_CNT_MSK			GENMASK(11, 10)
+#define BMI323_TAP_MSK				GENMASK(1, 0)
+#define BMI323_TMP_DRDY_MSK			GENMASK(7, 6)
+#define BMI323_GYR_DRDY_MSK			GENMASK(9, 8)
+#define BMI323_ACC_DRDY_MSK			GENMASK(11, 10)
+#define BMI323_FIFO_WTRMRK_MSK			GENMASK(13, 12)
+#define BMI323_FIFO_FULL_MSK			GENMASK(15, 14)
+
+/* Feature registers */
+#define BMI323_FEAT_CTRL_REG			0x40
+#define BMI323_FEAT_ENG_EN_MSK			BIT(0)
+#define BMI323_FEAT_DATA_ADDR			0x41
+#define BMI323_FEAT_DATA_TX			0x42
+#define BMI323_FEAT_DATA_STATUS			0x43
+#define BMI323_FEAT_DATA_TX_RDY_MSK		BIT(1)
+#define BMI323_FEAT_EVNT_EXT_REG		0x47
+#define BMI323_FEAT_EVNT_EXT_S_MSK		BIT(3)
+#define BMI323_FEAT_EVNT_EXT_D_MSK		BIT(4)
+
+#define BMI323_CMD_REG				0x7E
+#define BMI323_RST_VAL				0xDEAF
+#define BMI323_CFG_RES_REG			0x7F
+
+/* Extended registers */
+#define BMI323_GEN_SET1_REG			0x02
+#define BMI323_GEN_SET1_MODE_MSK		BIT(0)
+#define BMI323_GEN_HOLD_DUR_MSK			GENMASK(4, 1)
+
+/* Any Motion/No Motion config registers */
+#define BMI323_ANYMO1_REG			0x05
+#define BMI323_NOMO1_REG			0x08
+#define BMI323_MO2_OFFSET			0x01
+#define BMI323_MO3_OFFSET			0x02
+#define BMI323_MO1_REF_UP_MSK			BIT(12)
+#define BMI323_MO1_SLOPE_TH_MSK			GENMASK(11, 0)
+#define BMI323_MO2_HYSTR_MSK			GENMASK(9, 0)
+#define BMI323_MO3_DURA_MSK			GENMASK(12, 0)
+
+/* Step counter config registers */
+#define BMI323_STEP_SC1_REG			0x10
+#define BMI323_STEP_SC1_WTRMRK_MSK		GENMASK(9, 0)
+#define BMI323_STEP_SC1_RST_CNT_MSK		BIT(10)
+#define BMI323_STEP_SC1_REG			0x10
+#define BMI323_STEP_LEN				2
+
+/* Tap gesture config registers */
+#define BMI323_TAP1_REG				0x1E
+#define BMI323_TAP1_AXIS_SEL_MSK		GENMASK(1, 0)
+#define BMI323_AXIS_XYZ_MSK			GENMASK(1, 0)
+#define BMI323_TAP1_TIMOUT_MSK			BIT(2)
+#define BMI323_TAP1_MAX_PEAKS_MSK		GENMASK(5, 3)
+#define BMI323_TAP1_MODE_MSK			GENMASK(7, 6)
+#define BMI323_TAP2_REG				0x1F
+#define BMI323_TAP2_THRES_MSK			GENMASK(9, 0)
+#define BMI323_TAP2_MAX_DUR_MSK			GENMASK(15, 10)
+#define BMI323_TAP3_REG				0x20
+#define BMI323_TAP3_QUIET_TIM_MSK		GENMASK(15, 12)
+#define BMI323_TAP3_QT_BW_TAP_MSK		GENMASK(11, 8)
+#define BMI323_TAP3_QT_AFT_GES_MSK		GENMASK(15, 12)
+
+#define BMI323_MOTION_THRES_SCALE		512
+#define BMI323_MOTION_HYSTR_SCALE		512
+#define BMI323_MOTION_DURAT_SCALE		50
+#define BMI323_TAP_THRES_SCALE			512
+#define BMI323_DUR_BW_TAP_SCALE			200
+#define BMI323_QUITE_TIM_GES_SCALE		25
+#define BMI323_MAX_GES_DUR_SCALE		25
+
+/*
+ * The formula to calculate temperature in C.
+ * See datasheet section 6.1.1, Register Map Overview
+ *
+ * T_C = (temp_raw / 512) + 23
+ */
+#define BMI323_TEMP_OFFSET			11776
+#define BMI323_TEMP_SCALE			1953125
+
+/*
+ * The BMI323 features a FIFO with a capacity of 2048 bytes. Each frame
+ * consists of accelerometer (X, Y, Z) data and gyroscope (X, Y, Z) data,
+ * totaling 6 words or 12 bytes. The FIFO buffer can hold a total of
+ * 170 frames.
+ *
+ * If a watermark interrupt is configured for 170 frames, the interrupt will
+ * trigger when the FIFO reaches 169 frames, so limit the maximum watermark
+ * level to 169 frames. In terms of data, 169 frames would equal 1014 bytes,
+ * which is approximately 2 frames before the FIFO reaches its full capacity.
+ * See datasheet section 5.7.3 FIFO Buffer Interrupts
+ */
+#define BMI323_BYTES_PER_SAMPLE			2
+#define BMI323_FIFO_LENGTH_IN_BYTES		2048
+#define BMI323_FIFO_FRAME_LENGTH		6
+#define BMI323_FIFO_FULL_IN_FRAMES		\
+	((BMI323_FIFO_LENGTH_IN_BYTES /		\
+	(BMI323_BYTES_PER_SAMPLE * BMI323_FIFO_FRAME_LENGTH)) - 1)
+#define BMI323_FIFO_FULL_IN_WORDS		\
+	(BMI323_FIFO_FULL_IN_FRAMES * BMI323_FIFO_FRAME_LENGTH)
+
+#define BMI323_INT_MICRO_TO_RAW(val, val2, scale) ((val) * (scale) + \
+						  ((val2) * (scale)) / MEGA)
+
+#define BMI323_RAW_TO_MICRO(raw, scale) ((((raw) % (scale)) * MEGA) / scale)
+
+struct device;
+int bmi323_core_probe(struct device *dev);
+extern const struct regmap_config bmi323_regmap_config;
+
+#endif
diff --git a/drivers/iio/imu/bmi323/bmi323_core.c b/drivers/iio/imu/bmi323/bmi323_core.c
new file mode 100644
index 000000000000..183af482828f
--- /dev/null
+++ b/drivers/iio/imu/bmi323/bmi323_core.c
@@ -0,0 +1,2139 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * IIO core driver for Bosch BMI323 6-Axis IMU.
+ *
+ * Copyright (C) 2023, Jagath Jog J <jagathjog1996@gmail.com>
+ *
+ * Datasheet: https://www.bosch-sensortec.com/media/boschsensortec/downloads/datasheets/bst-bmi323-ds000.pdf
+ */
+
+#include <linux/bitfield.h>
+#include <linux/cleanup.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/minmax.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/property.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+#include <linux/units.h>
+
+#include <asm/unaligned.h>
+
+#include <linux/iio/buffer.h>
+#include <linux/iio/events.h>
+#include <linux/iio/iio.h>
+#include <linux/iio/sysfs.h>
+#include <linux/iio/trigger.h>
+#include <linux/iio/trigger_consumer.h>
+#include <linux/iio/triggered_buffer.h>
+
+#include "bmi323.h"
+
+enum bmi323_sensor_type {
+	BMI323_ACCEL,
+	BMI323_GYRO,
+	BMI323_SENSORS_CNT,
+};
+
+enum bmi323_opr_mode {
+	ACC_GYRO_MODE_DISABLE = 0x00,
+	GYRO_DRIVE_MODE_ENABLED = 0x01,
+	ACC_GYRO_MODE_DUTYCYCLE = 0x03,
+	ACC_GYRO_MODE_CONTINOUS = 0x04,
+	ACC_GYRO_MODE_HIGH_PERF = 0x07,
+};
+
+enum bmi323_state {
+	BMI323_IDLE,
+	BMI323_BUFFER_DRDY_TRIGGERED,
+	BMI323_BUFFER_FIFO,
+};
+
+enum bmi323_irq_pin {
+	BMI323_IRQ_DISABLED,
+	BMI323_IRQ_INT1,
+	BMI323_IRQ_INT2,
+};
+
+enum bmi323_3db_bw {
+	BMI323_BW_ODR_BY_2,
+	BMI323_BW_ODR_BY_4,
+};
+
+enum bmi323_scan {
+	BMI323_ACCEL_X,
+	BMI323_ACCEL_Y,
+	BMI323_ACCEL_Z,
+	BMI323_GYRO_X,
+	BMI323_GYRO_Y,
+	BMI323_GYRO_Z,
+	BMI323_CHAN_MAX
+};
+
+struct bmi323_hw {
+	u8 data;
+	u8 config;
+	const int (*scale_table)[2];
+	int scale_table_len;
+};
+
+/*
+ * The accelerometer supports +-2G/4G/8G/16G ranges, and the resolution of
+ * each sample is 16 bits, signed.
+ * At +-8G the scale can calculated by
+ * ((8 + 8) * 9.80665 / (2^16 - 1)) * 10^6 = 2394.23819 scale in micro
+ *
+ */
+static const int bmi323_accel_scale[][2] = {
+	{ 0, 598 },
+	{ 0, 1197 },
+	{ 0, 2394 },
+	{ 0, 4788 },
+};
+
+static const int bmi323_gyro_scale[][2] = {
+	{ 0, 66 },
+	{ 0, 133 },
+	{ 0, 266 },
+	{ 0, 532 },
+	{ 0, 1065 },
+};
+
+static const int bmi323_accel_gyro_avrg[] = {0, 2, 4, 8, 16, 32, 64};
+
+static const struct bmi323_hw bmi323_hw[2] = {
+	[BMI323_ACCEL] = {
+		.data = BMI323_ACCEL_X_REG,
+		.config = BMI323_ACC_CONF_REG,
+		.scale_table = bmi323_accel_scale,
+		.scale_table_len = ARRAY_SIZE(bmi323_accel_scale),
+	},
+	[BMI323_GYRO] = {
+		.data = BMI323_GYRO_X_REG,
+		.config = BMI323_GYRO_CONF_REG,
+		.scale_table = bmi323_gyro_scale,
+		.scale_table_len = ARRAY_SIZE(bmi323_gyro_scale),
+	},
+};
+
+struct bmi323_data {
+	struct device *dev;
+	struct regmap *regmap;
+	struct iio_mount_matrix orientation;
+	enum bmi323_irq_pin irq_pin;
+	struct iio_trigger *trig;
+	bool drdy_trigger_enabled;
+	enum bmi323_state state;
+	s64 fifo_tstamp, old_fifo_tstamp;
+	u32 odrns[BMI323_SENSORS_CNT];
+	u32 odrhz[BMI323_SENSORS_CNT];
+	unsigned int feature_events;
+
+	/*
+	 * Lock to protect the members of device's private data from concurrent
+	 * access and also to serialize the access of extended registers.
+	 * See bmi323_write_ext_reg(..) for more info.
+	 */
+	struct mutex mutex;
+	int watermark;
+	__le16 fifo_buff[BMI323_FIFO_FULL_IN_WORDS] __aligned(IIO_DMA_MINALIGN);
+	struct {
+		__le16 channels[BMI323_CHAN_MAX];
+		s64 ts __aligned(8);
+	} buffer;
+	__le16 steps_count[BMI323_STEP_LEN];
+};
+
+static const struct iio_mount_matrix *
+bmi323_get_mount_matrix(const struct iio_dev *idev,
+			const struct iio_chan_spec *chan)
+{
+	struct bmi323_data *data = iio_priv(idev);
+
+	return &data->orientation;
+}
+
+static const struct iio_chan_spec_ext_info bmi323_ext_info[] = {
+	IIO_MOUNT_MATRIX(IIO_SHARED_BY_TYPE, bmi323_get_mount_matrix),
+	{ }
+};
+
+static const struct iio_event_spec bmi323_step_wtrmrk_event = {
+	.type = IIO_EV_TYPE_CHANGE,
+	.dir = IIO_EV_DIR_NONE,
+	.mask_shared_by_type = BIT(IIO_EV_INFO_ENABLE) |
+			       BIT(IIO_EV_INFO_VALUE),
+};
+
+static const struct iio_event_spec bmi323_accel_event[] = {
+	{
+		.type = IIO_EV_TYPE_MAG,
+		.dir = IIO_EV_DIR_FALLING,
+		.mask_shared_by_type = BIT(IIO_EV_INFO_VALUE) |
+				       BIT(IIO_EV_INFO_PERIOD) |
+				       BIT(IIO_EV_INFO_HYSTERESIS) |
+				       BIT(IIO_EV_INFO_ENABLE),
+	},
+	{
+		.type = IIO_EV_TYPE_MAG,
+		.dir = IIO_EV_DIR_RISING,
+		.mask_shared_by_type = BIT(IIO_EV_INFO_VALUE) |
+				       BIT(IIO_EV_INFO_PERIOD) |
+				       BIT(IIO_EV_INFO_HYSTERESIS) |
+				       BIT(IIO_EV_INFO_ENABLE),
+	},
+	{
+		.type = IIO_EV_TYPE_GESTURE,
+		.dir = IIO_EV_DIR_SINGLETAP,
+		.mask_shared_by_type = BIT(IIO_EV_INFO_ENABLE) |
+				       BIT(IIO_EV_INFO_VALUE) |
+				       BIT(IIO_EV_INFO_RESET_TIMEOUT),
+	},
+	{
+		.type = IIO_EV_TYPE_GESTURE,
+		.dir = IIO_EV_DIR_DOUBLETAP,
+		.mask_shared_by_type = BIT(IIO_EV_INFO_ENABLE) |
+				       BIT(IIO_EV_INFO_VALUE) |
+				       BIT(IIO_EV_INFO_RESET_TIMEOUT) |
+				       BIT(IIO_EV_INFO_TAP2_MIN_DELAY),
+	},
+};
+
+#define BMI323_ACCEL_CHANNEL(_type, _axis, _index) {			\
+	.type = _type,							\
+	.modified = 1,							\
+	.channel2 = IIO_MOD_##_axis,					\
+	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),			\
+	.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SAMP_FREQ) |	\
+				    BIT(IIO_CHAN_INFO_SCALE) |		\
+				    BIT(IIO_CHAN_INFO_OVERSAMPLING_RATIO), \
+	.info_mask_shared_by_type_available =				\
+				    BIT(IIO_CHAN_INFO_SAMP_FREQ) |	\
+				    BIT(IIO_CHAN_INFO_SCALE) |		\
+				    BIT(IIO_CHAN_INFO_OVERSAMPLING_RATIO), \
+	.scan_index = _index,						\
+	.scan_type = {							\
+		.sign = 's',						\
+		.realbits = 16,						\
+		.storagebits = 16,					\
+		.endianness = IIO_LE,					\
+	},								\
+	.ext_info = bmi323_ext_info,					\
+	.event_spec = bmi323_accel_event,				\
+	.num_event_specs = ARRAY_SIZE(bmi323_accel_event),		\
+}
+
+#define BMI323_GYRO_CHANNEL(_type, _axis, _index) {			\
+	.type = _type,							\
+	.modified = 1,							\
+	.channel2 = IIO_MOD_##_axis,					\
+	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),			\
+	.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SAMP_FREQ) |	\
+				    BIT(IIO_CHAN_INFO_SCALE) |		\
+				    BIT(IIO_CHAN_INFO_OVERSAMPLING_RATIO), \
+	.info_mask_shared_by_type_available =				\
+				    BIT(IIO_CHAN_INFO_SAMP_FREQ) |	\
+				    BIT(IIO_CHAN_INFO_SCALE) |		\
+				    BIT(IIO_CHAN_INFO_OVERSAMPLING_RATIO), \
+	.scan_index = _index,						\
+	.scan_type = {							\
+		.sign = 's',						\
+		.realbits = 16,						\
+		.storagebits = 16,					\
+		.endianness = IIO_LE,					\
+	},								\
+	.ext_info = bmi323_ext_info,					\
+}
+
+static const struct iio_chan_spec bmi323_channels[] = {
+	BMI323_ACCEL_CHANNEL(IIO_ACCEL, X, BMI323_ACCEL_X),
+	BMI323_ACCEL_CHANNEL(IIO_ACCEL, Y, BMI323_ACCEL_Y),
+	BMI323_ACCEL_CHANNEL(IIO_ACCEL, Z, BMI323_ACCEL_Z),
+	BMI323_GYRO_CHANNEL(IIO_ANGL_VEL, X, BMI323_GYRO_X),
+	BMI323_GYRO_CHANNEL(IIO_ANGL_VEL, Y, BMI323_GYRO_Y),
+	BMI323_GYRO_CHANNEL(IIO_ANGL_VEL, Z, BMI323_GYRO_Z),
+	{
+		.type = IIO_TEMP,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+				      BIT(IIO_CHAN_INFO_OFFSET) |
+				      BIT(IIO_CHAN_INFO_SCALE),
+		.scan_index = -1,
+	},
+	{
+		.type = IIO_STEPS,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED) |
+				      BIT(IIO_CHAN_INFO_ENABLE),
+		.scan_index = -1,
+		.event_spec = &bmi323_step_wtrmrk_event,
+		.num_event_specs = 1,
+
+	},
+	IIO_CHAN_SOFT_TIMESTAMP(BMI323_CHAN_MAX),
+};
+
+static const int bmi323_acc_gyro_odr[][2] = {
+	{ 0, 781250 },
+	{ 1, 562500 },
+	{ 3, 125000 },
+	{ 6, 250000 },
+	{ 12, 500000 },
+	{ 25, 0 },
+	{ 50, 0 },
+	{ 100, 0 },
+	{ 200, 0 },
+	{ 400, 0 },
+	{ 800, 0 },
+};
+
+static const int bmi323_acc_gyro_odrns[] = {
+	1280 * MEGA,
+	640 * MEGA,
+	320 * MEGA,
+	160 * MEGA,
+	80 * MEGA,
+	40 * MEGA,
+	20 * MEGA,
+	10 * MEGA,
+	5 * MEGA,
+	2500 * KILO,
+	1250 * KILO,
+};
+
+static enum bmi323_sensor_type bmi323_iio_to_sensor(enum iio_chan_type iio_type)
+{
+	switch (iio_type) {
+	case IIO_ACCEL:
+		return BMI323_ACCEL;
+	case IIO_ANGL_VEL:
+		return BMI323_GYRO;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int bmi323_set_mode(struct bmi323_data *data,
+			   enum bmi323_sensor_type sensor,
+			   enum bmi323_opr_mode mode)
+{
+	guard(mutex)(&data->mutex);
+	return regmap_update_bits(data->regmap, bmi323_hw[sensor].config,
+				  BMI323_ACC_GYRO_CONF_MODE_MSK,
+				  FIELD_PREP(BMI323_ACC_GYRO_CONF_MODE_MSK,
+					     mode));
+}
+
+/*
+ * When writing data to extended register there must be no communication to
+ * any other register before write transaction is complete.
+ * See datasheet section 6.2 Extended Register Map Description.
+ */
+static int bmi323_write_ext_reg(struct bmi323_data *data, unsigned int ext_addr,
+				unsigned int ext_data)
+{
+	int ret, feature_status;
+
+	ret = regmap_read(data->regmap, BMI323_FEAT_DATA_STATUS,
+			  &feature_status);
+	if (ret)
+		return ret;
+
+	if (!FIELD_GET(BMI323_FEAT_DATA_TX_RDY_MSK, feature_status))
+		return -EBUSY;
+
+	ret = regmap_write(data->regmap, BMI323_FEAT_DATA_ADDR, ext_addr);
+	if (ret)
+		return ret;
+
+	return regmap_write(data->regmap, BMI323_FEAT_DATA_TX, ext_data);
+}
+
+/*
+ * When reading data from extended register there must be no communication to
+ * any other register before read transaction is complete.
+ * See datasheet section 6.2 Extended Register Map Description.
+ */
+static int bmi323_read_ext_reg(struct bmi323_data *data, unsigned int ext_addr,
+			       unsigned int *ext_data)
+{
+	int ret, feature_status;
+
+	ret = regmap_read(data->regmap, BMI323_FEAT_DATA_STATUS,
+			  &feature_status);
+	if (ret)
+		return ret;
+
+	if (!FIELD_GET(BMI323_FEAT_DATA_TX_RDY_MSK, feature_status))
+		return -EBUSY;
+
+	ret = regmap_write(data->regmap, BMI323_FEAT_DATA_ADDR, ext_addr);
+	if (ret)
+		return ret;
+
+	return regmap_read(data->regmap, BMI323_FEAT_DATA_TX, ext_data);
+}
+
+static int bmi323_update_ext_reg(struct bmi323_data *data,
+				 unsigned int ext_addr,
+				 unsigned int mask, unsigned int ext_data)
+{
+	unsigned int value;
+	int ret;
+
+	ret = bmi323_read_ext_reg(data, ext_addr, &value);
+	if (ret)
+		return ret;
+
+	set_mask_bits(&value, mask, ext_data);
+
+	return bmi323_write_ext_reg(data, ext_addr, value);
+}
+
+static int bmi323_get_error_status(struct bmi323_data *data)
+{
+	int error, ret;
+
+	guard(mutex)(&data->mutex);
+	ret = regmap_read(data->regmap, BMI323_ERR_REG, &error);
+	if (ret)
+		return ret;
+
+	if (error)
+		dev_err(data->dev, "Sensor error 0x%x\n", error);
+
+	return error;
+}
+
+static int bmi323_feature_engine_events(struct bmi323_data *data,
+					const unsigned int event_mask,
+					bool state)
+{
+	unsigned int value;
+	int ret;
+
+	ret = regmap_read(data->regmap, BMI323_FEAT_IO0_REG, &value);
+	if (ret)
+		return ret;
+
+	/* Register must be cleared before changing an active config */
+	ret = regmap_write(data->regmap, BMI323_FEAT_IO0_REG, 0);
+	if (ret)
+		return ret;
+
+	if (state)
+		value |= event_mask;
+	else
+		value &= ~event_mask;
+
+	ret = regmap_write(data->regmap, BMI323_FEAT_IO0_REG, value);
+	if (ret)
+		return ret;
+
+	return regmap_write(data->regmap, BMI323_FEAT_IO_STATUS_REG,
+			    BMI323_FEAT_IO_STATUS_MSK);
+}
+
+static int bmi323_step_wtrmrk_en(struct bmi323_data *data, int state)
+{
+	enum bmi323_irq_pin step_irq;
+	int ret;
+
+	guard(mutex)(&data->mutex);
+	if (!FIELD_GET(BMI323_FEAT_IO0_STP_CNT_MSK, data->feature_events))
+		return -EINVAL;
+
+	if (state)
+		step_irq = data->irq_pin;
+	else
+		step_irq = BMI323_IRQ_DISABLED;
+
+	ret = bmi323_update_ext_reg(data, BMI323_STEP_SC1_REG,
+				    BMI323_STEP_SC1_WTRMRK_MSK,
+				    FIELD_PREP(BMI323_STEP_SC1_WTRMRK_MSK,
+					       state ? 1 : 0));
+	if (ret)
+		return ret;
+
+	return regmap_update_bits(data->regmap, BMI323_INT_MAP1_REG,
+				  BMI323_STEP_CNT_MSK,
+				  FIELD_PREP(BMI323_STEP_CNT_MSK, step_irq));
+}
+
+static int bmi323_motion_config_reg(enum iio_event_direction dir)
+{
+	switch (dir) {
+	case IIO_EV_DIR_RISING:
+		return BMI323_ANYMO1_REG;
+	case IIO_EV_DIR_FALLING:
+		return BMI323_NOMO1_REG;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int bmi323_motion_event_en(struct bmi323_data *data,
+				  enum iio_event_direction dir, int state)
+{
+	unsigned int state_value = state ? BMI323_FEAT_XYZ_MSK : 0;
+	int config, ret, msk, raw, field_value;
+	enum bmi323_irq_pin motion_irq;
+	int irq_msk, irq_field_val;
+
+	if (state)
+		motion_irq = data->irq_pin;
+	else
+		motion_irq = BMI323_IRQ_DISABLED;
+
+	switch (dir) {
+	case IIO_EV_DIR_RISING:
+		msk = BMI323_FEAT_IO0_XYZ_MOTION_MSK;
+		raw = 512;
+		config = BMI323_ANYMO1_REG;
+		irq_msk = BMI323_MOTION_MSK;
+		irq_field_val = FIELD_PREP(BMI323_MOTION_MSK, motion_irq);
+		field_value = FIELD_PREP(BMI323_FEAT_IO0_XYZ_MOTION_MSK,
+					 state_value);
+		break;
+	case IIO_EV_DIR_FALLING:
+		msk = BMI323_FEAT_IO0_XYZ_NOMOTION_MSK;
+		raw = 0;
+		config = BMI323_NOMO1_REG;
+		irq_msk = BMI323_NOMOTION_MSK;
+		irq_field_val = FIELD_PREP(BMI323_NOMOTION_MSK, motion_irq);
+		field_value = FIELD_PREP(BMI323_FEAT_IO0_XYZ_NOMOTION_MSK,
+					 state_value);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	guard(mutex)(&data->mutex);
+	ret = bmi323_feature_engine_events(data, msk, state);
+	if (ret)
+		return ret;
+
+	ret = bmi323_update_ext_reg(data, config,
+				    BMI323_MO1_REF_UP_MSK,
+				    FIELD_PREP(BMI323_MO1_REF_UP_MSK, 0));
+	if (ret)
+		return ret;
+
+	/* Set initial value to avoid interrupts while enabling*/
+	ret = bmi323_update_ext_reg(data, config,
+				    BMI323_MO1_SLOPE_TH_MSK,
+				    FIELD_PREP(BMI323_MO1_SLOPE_TH_MSK, raw));
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(data->regmap, BMI323_INT_MAP1_REG, irq_msk,
+				 irq_field_val);
+	if (ret)
+		return ret;
+
+	set_mask_bits(&data->feature_events, msk, field_value);
+
+	return 0;
+}
+
+static int bmi323_tap_event_en(struct bmi323_data *data,
+			       enum iio_event_direction dir, int state)
+{
+	enum bmi323_irq_pin tap_irq;
+	int ret, tap_enabled;
+
+	guard(mutex)(&data->mutex);
+
+	if (data->odrhz[BMI323_ACCEL] < 200) {
+		dev_err(data->dev, "Invalid accelerometer parameter\n");
+		return -EINVAL;
+	}
+
+	switch (dir) {
+	case IIO_EV_DIR_SINGLETAP:
+		ret = bmi323_feature_engine_events(data,
+						   BMI323_FEAT_IO0_S_TAP_MSK,
+						   state);
+		if (ret)
+			return ret;
+
+		set_mask_bits(&data->feature_events, BMI323_FEAT_IO0_S_TAP_MSK,
+			      FIELD_PREP(BMI323_FEAT_IO0_S_TAP_MSK, state));
+		break;
+	case IIO_EV_DIR_DOUBLETAP:
+		ret = bmi323_feature_engine_events(data,
+						   BMI323_FEAT_IO0_D_TAP_MSK,
+						   state);
+		if (ret)
+			return ret;
+
+		set_mask_bits(&data->feature_events, BMI323_FEAT_IO0_D_TAP_MSK,
+			      FIELD_PREP(BMI323_FEAT_IO0_D_TAP_MSK, state));
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	tap_enabled = FIELD_GET(BMI323_FEAT_IO0_S_TAP_MSK |
+				BMI323_FEAT_IO0_D_TAP_MSK,
+				data->feature_events);
+
+	if (tap_enabled)
+		tap_irq = data->irq_pin;
+	else
+		tap_irq = BMI323_IRQ_DISABLED;
+
+	ret = regmap_update_bits(data->regmap, BMI323_INT_MAP2_REG,
+				 BMI323_TAP_MSK,
+				 FIELD_PREP(BMI323_TAP_MSK, tap_irq));
+	if (ret)
+		return ret;
+
+	if (!state)
+		return 0;
+
+	ret = bmi323_update_ext_reg(data, BMI323_TAP1_REG,
+				    BMI323_TAP1_MAX_PEAKS_MSK,
+				    FIELD_PREP(BMI323_TAP1_MAX_PEAKS_MSK,
+					       0x04));
+	if (ret)
+		return ret;
+
+	ret = bmi323_update_ext_reg(data, BMI323_TAP1_REG,
+				    BMI323_TAP1_AXIS_SEL_MSK,
+				    FIELD_PREP(BMI323_TAP1_AXIS_SEL_MSK,
+					       BMI323_AXIS_XYZ_MSK));
+	if (ret)
+		return ret;
+
+	return bmi323_update_ext_reg(data, BMI323_TAP1_REG,
+				     BMI323_TAP1_TIMOUT_MSK,
+				     FIELD_PREP(BMI323_TAP1_TIMOUT_MSK,
+						0));
+}
+
+static ssize_t in_accel_gesture_tap_wait_dur_show(struct device *dev,
+						  struct device_attribute *attr,
+						  char *buf)
+{
+	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct bmi323_data *data = iio_priv(indio_dev);
+	unsigned int reg_value, raw;
+	int ret, val[2];
+
+	scoped_guard(mutex, &data->mutex) {
+		ret = bmi323_read_ext_reg(data, BMI323_TAP2_REG, &reg_value);
+		if (ret)
+			return ret;
+	}
+
+	raw = FIELD_GET(BMI323_TAP2_MAX_DUR_MSK, reg_value);
+	val[0] = raw / BMI323_MAX_GES_DUR_SCALE;
+	val[1] = BMI323_RAW_TO_MICRO(raw, BMI323_MAX_GES_DUR_SCALE);
+
+	return iio_format_value(buf, IIO_VAL_INT_PLUS_MICRO, ARRAY_SIZE(val),
+				val);
+}
+
+static ssize_t in_accel_gesture_tap_wait_dur_store(struct device *dev,
+						   struct device_attribute *attr,
+						   const char *buf, size_t len)
+{
+	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct bmi323_data *data = iio_priv(indio_dev);
+	int ret, val_int, val_fract, raw;
+
+	ret = iio_str_to_fixpoint(buf, 100000, &val_int, &val_fract);
+	if (ret)
+		return ret;
+
+	raw = BMI323_INT_MICRO_TO_RAW(val_int, val_fract,
+				      BMI323_MAX_GES_DUR_SCALE);
+	if (!in_range(raw, 0, 64))
+		return -EINVAL;
+
+	guard(mutex)(&data->mutex);
+	ret = bmi323_update_ext_reg(data, BMI323_TAP2_REG,
+				    BMI323_TAP2_MAX_DUR_MSK,
+				    FIELD_PREP(BMI323_TAP2_MAX_DUR_MSK, raw));
+	if (ret)
+		return ret;
+
+	return len;
+}
+
+/*
+ * Maximum duration from first tap within the second tap is expected to happen.
+ * This timeout is applicable only if gesture_tap_wait_timeout is enabled.
+ */
+static IIO_DEVICE_ATTR_RW(in_accel_gesture_tap_wait_dur, 0);
+
+static ssize_t in_accel_gesture_tap_wait_timeout_show(struct device *dev,
+						      struct device_attribute *attr,
+						      char *buf)
+{
+	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct bmi323_data *data = iio_priv(indio_dev);
+	unsigned int reg_value, raw;
+	int ret;
+
+	scoped_guard(mutex, &data->mutex) {
+		ret = bmi323_read_ext_reg(data, BMI323_TAP1_REG, &reg_value);
+		if (ret)
+			return ret;
+	}
+
+	raw = FIELD_GET(BMI323_TAP1_TIMOUT_MSK, reg_value);
+
+	return iio_format_value(buf, IIO_VAL_INT, 1, &raw);
+}
+
+static ssize_t in_accel_gesture_tap_wait_timeout_store(struct device *dev,
+						       struct device_attribute *attr,
+						       const char *buf,
+						       size_t len)
+{
+	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct bmi323_data *data = iio_priv(indio_dev);
+	bool val;
+	int ret;
+
+	ret = kstrtobool(buf, &val);
+	if (ret)
+		return ret;
+
+	guard(mutex)(&data->mutex);
+	ret = bmi323_update_ext_reg(data, BMI323_TAP1_REG,
+				    BMI323_TAP1_TIMOUT_MSK,
+				    FIELD_PREP(BMI323_TAP1_TIMOUT_MSK, val));
+	if (ret)
+		return ret;
+
+	return len;
+}
+
+/* Enable/disable gesture confirmation with wait time */
+static IIO_DEVICE_ATTR_RW(in_accel_gesture_tap_wait_timeout, 0);
+
+static IIO_CONST_ATTR(in_accel_gesture_tap_wait_dur_available,
+		      "[0.0 0.04 2.52]");
+
+static IIO_CONST_ATTR(in_accel_gesture_doubletap_tap2_min_delay_available,
+		      "[0.005 0.005 0.075]");
+
+static IIO_CONST_ATTR(in_accel_gesture_tap_reset_timeout_available,
+		      "[0.04 0.04 0.6]");
+
+static IIO_CONST_ATTR(in_accel_gesture_tap_value_available, "[0.0 0.002 1.99]");
+
+static IIO_CONST_ATTR(in_accel_mag_value_available, "[0.0 0.002 7.99]");
+
+static IIO_CONST_ATTR(in_accel_mag_period_available, "[0.0 0.02 162.0]");
+
+static IIO_CONST_ATTR(in_accel_mag_hysteresis_available, "[0.0 0.002 1.99]");
+
+static struct attribute *bmi323_event_attributes[] = {
+	&iio_const_attr_in_accel_gesture_tap_value_available.dev_attr.attr,
+	&iio_const_attr_in_accel_gesture_tap_reset_timeout_available.dev_attr.attr,
+	&iio_const_attr_in_accel_gesture_doubletap_tap2_min_delay_available.dev_attr.attr,
+	&iio_const_attr_in_accel_gesture_tap_wait_dur_available.dev_attr.attr,
+	&iio_dev_attr_in_accel_gesture_tap_wait_timeout.dev_attr.attr,
+	&iio_dev_attr_in_accel_gesture_tap_wait_dur.dev_attr.attr,
+	&iio_const_attr_in_accel_mag_value_available.dev_attr.attr,
+	&iio_const_attr_in_accel_mag_period_available.dev_attr.attr,
+	&iio_const_attr_in_accel_mag_hysteresis_available.dev_attr.attr,
+	NULL
+};
+
+static const struct attribute_group bmi323_event_attribute_group = {
+	.attrs = bmi323_event_attributes,
+};
+
+static int bmi323_write_event_config(struct iio_dev *indio_dev,
+				     const struct iio_chan_spec *chan,
+				     enum iio_event_type type,
+				     enum iio_event_direction dir, int state)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+
+	switch (type) {
+	case IIO_EV_TYPE_MAG:
+		return bmi323_motion_event_en(data, dir, state);
+	case IIO_EV_TYPE_GESTURE:
+		return bmi323_tap_event_en(data, dir, state);
+	case IIO_EV_TYPE_CHANGE:
+		return bmi323_step_wtrmrk_en(data, state);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int bmi323_read_event_config(struct iio_dev *indio_dev,
+				    const struct iio_chan_spec *chan,
+				    enum iio_event_type type,
+				    enum iio_event_direction dir)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+	int ret, value, reg_val;
+
+	guard(mutex)(&data->mutex);
+
+	switch (chan->type) {
+	case IIO_ACCEL:
+		switch (dir) {
+		case IIO_EV_DIR_SINGLETAP:
+			ret = FIELD_GET(BMI323_FEAT_IO0_S_TAP_MSK,
+					data->feature_events);
+			break;
+		case IIO_EV_DIR_DOUBLETAP:
+			ret = FIELD_GET(BMI323_FEAT_IO0_D_TAP_MSK,
+					data->feature_events);
+			break;
+		case IIO_EV_DIR_RISING:
+			value = FIELD_GET(BMI323_FEAT_IO0_XYZ_MOTION_MSK,
+					  data->feature_events);
+			ret = value ? 1 : 0;
+			break;
+		case IIO_EV_DIR_FALLING:
+			value = FIELD_GET(BMI323_FEAT_IO0_XYZ_NOMOTION_MSK,
+					  data->feature_events);
+			ret = value ? 1 : 0;
+			break;
+		default:
+			ret = -EINVAL;
+			break;
+		}
+		return ret;
+	case IIO_STEPS:
+		ret = regmap_read(data->regmap, BMI323_INT_MAP1_REG, &reg_val);
+		if (ret)
+			return ret;
+
+		return FIELD_GET(BMI323_STEP_CNT_MSK, reg_val) ? 1 : 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int bmi323_write_event_value(struct iio_dev *indio_dev,
+				    const struct iio_chan_spec *chan,
+				    enum iio_event_type type,
+				    enum iio_event_direction dir,
+				    enum iio_event_info info,
+				    int val, int val2)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+	unsigned int raw;
+	int reg;
+
+	guard(mutex)(&data->mutex);
+
+	switch (type) {
+	case IIO_EV_TYPE_GESTURE:
+		switch (info) {
+		case IIO_EV_INFO_VALUE:
+			if (!in_range(val, 0, 2))
+				return -EINVAL;
+
+			raw = BMI323_INT_MICRO_TO_RAW(val, val2,
+						      BMI323_TAP_THRES_SCALE);
+
+			return bmi323_update_ext_reg(data, BMI323_TAP2_REG,
+						     BMI323_TAP2_THRES_MSK,
+						     FIELD_PREP(BMI323_TAP2_THRES_MSK,
+								raw));
+		case IIO_EV_INFO_RESET_TIMEOUT:
+			if (val || !in_range(val2, 40000, 560001))
+				return -EINVAL;
+
+			raw = BMI323_INT_MICRO_TO_RAW(val, val2,
+						      BMI323_QUITE_TIM_GES_SCALE);
+
+			return bmi323_update_ext_reg(data, BMI323_TAP3_REG,
+						     BMI323_TAP3_QT_AFT_GES_MSK,
+						     FIELD_PREP(BMI323_TAP3_QT_AFT_GES_MSK,
+								raw));
+		case IIO_EV_INFO_TAP2_MIN_DELAY:
+			if (val || !in_range(val2, 5000, 70001))
+				return -EINVAL;
+
+			raw = BMI323_INT_MICRO_TO_RAW(val, val2,
+						      BMI323_DUR_BW_TAP_SCALE);
+
+			return bmi323_update_ext_reg(data, BMI323_TAP3_REG,
+						     BMI323_TAP3_QT_BW_TAP_MSK,
+						     FIELD_PREP(BMI323_TAP3_QT_BW_TAP_MSK,
+								raw));
+		default:
+			return -EINVAL;
+		}
+	case IIO_EV_TYPE_MAG:
+		reg = bmi323_motion_config_reg(dir);
+		if (reg < 0)
+			return -EINVAL;
+
+		switch (info) {
+		case IIO_EV_INFO_VALUE:
+			if (!in_range(val, 0, 8))
+				return -EINVAL;
+
+			raw = BMI323_INT_MICRO_TO_RAW(val, val2,
+						      BMI323_MOTION_THRES_SCALE);
+
+			return bmi323_update_ext_reg(data, reg,
+						     BMI323_MO1_SLOPE_TH_MSK,
+						     FIELD_PREP(BMI323_MO1_SLOPE_TH_MSK,
+								raw));
+		case IIO_EV_INFO_PERIOD:
+			if (!in_range(val, 0, 163))
+				return -EINVAL;
+
+			raw = BMI323_INT_MICRO_TO_RAW(val, val2,
+						      BMI323_MOTION_DURAT_SCALE);
+
+			return bmi323_update_ext_reg(data,
+						     reg + BMI323_MO3_OFFSET,
+						     BMI323_MO3_DURA_MSK,
+						     FIELD_PREP(BMI323_MO3_DURA_MSK,
+								raw));
+		case IIO_EV_INFO_HYSTERESIS:
+			if (!in_range(val, 0, 2))
+				return -EINVAL;
+
+			raw = BMI323_INT_MICRO_TO_RAW(val, val2,
+						      BMI323_MOTION_HYSTR_SCALE);
+
+			return bmi323_update_ext_reg(data,
+						     reg + BMI323_MO2_OFFSET,
+						     BMI323_MO2_HYSTR_MSK,
+						     FIELD_PREP(BMI323_MO2_HYSTR_MSK,
+								raw));
+		default:
+			return -EINVAL;
+		}
+	case IIO_EV_TYPE_CHANGE:
+		if (!in_range(val, 0, 20461))
+			return -EINVAL;
+
+		raw = val / 20;
+		return bmi323_update_ext_reg(data, BMI323_STEP_SC1_REG,
+					     BMI323_STEP_SC1_WTRMRK_MSK,
+					     FIELD_PREP(BMI323_STEP_SC1_WTRMRK_MSK,
+							raw));
+	default:
+		return -EINVAL;
+	}
+}
+
+static int bmi323_read_event_value(struct iio_dev *indio_dev,
+				   const struct iio_chan_spec *chan,
+				   enum iio_event_type type,
+				   enum iio_event_direction dir,
+				   enum iio_event_info info,
+				   int *val, int *val2)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+	unsigned int raw, reg_value;
+	int ret, reg;
+
+	guard(mutex)(&data->mutex);
+
+	switch (type) {
+	case IIO_EV_TYPE_GESTURE:
+		switch (info) {
+		case IIO_EV_INFO_VALUE:
+			ret = bmi323_read_ext_reg(data, BMI323_TAP2_REG,
+						  &reg_value);
+			if (ret)
+				return ret;
+
+			raw = FIELD_GET(BMI323_TAP2_THRES_MSK, reg_value);
+			*val = raw / BMI323_TAP_THRES_SCALE;
+			*val2 = BMI323_RAW_TO_MICRO(raw, BMI323_TAP_THRES_SCALE);
+			return IIO_VAL_INT_PLUS_MICRO;
+		case IIO_EV_INFO_RESET_TIMEOUT:
+			ret = bmi323_read_ext_reg(data, BMI323_TAP3_REG,
+						  &reg_value);
+			if (ret)
+				return ret;
+
+			raw = FIELD_GET(BMI323_TAP3_QT_AFT_GES_MSK, reg_value);
+			*val = 0;
+			*val2 = BMI323_RAW_TO_MICRO(raw,
+						    BMI323_QUITE_TIM_GES_SCALE);
+			return IIO_VAL_INT_PLUS_MICRO;
+		case IIO_EV_INFO_TAP2_MIN_DELAY:
+			ret = bmi323_read_ext_reg(data, BMI323_TAP3_REG,
+						  &reg_value);
+			if (ret)
+				return ret;
+
+			raw = FIELD_GET(BMI323_TAP3_QT_BW_TAP_MSK, reg_value);
+			*val = 0;
+			*val2 = BMI323_RAW_TO_MICRO(raw,
+						    BMI323_DUR_BW_TAP_SCALE);
+			return IIO_VAL_INT_PLUS_MICRO;
+		default:
+			return -EINVAL;
+		}
+	case IIO_EV_TYPE_MAG:
+		reg = bmi323_motion_config_reg(dir);
+		if (reg < 0)
+			return -EINVAL;
+
+		switch (info) {
+		case IIO_EV_INFO_VALUE:
+			ret = bmi323_read_ext_reg(data, reg, &reg_value);
+			if (ret)
+				return ret;
+
+			raw = FIELD_GET(BMI323_MO1_SLOPE_TH_MSK, reg_value);
+			*val = raw / BMI323_MOTION_THRES_SCALE;
+			*val2 = BMI323_RAW_TO_MICRO(raw,
+						    BMI323_MOTION_THRES_SCALE);
+			return IIO_VAL_INT_PLUS_MICRO;
+		case IIO_EV_INFO_PERIOD:
+			ret = bmi323_read_ext_reg(data,
+						  reg + BMI323_MO3_OFFSET,
+						  &reg_value);
+			if (ret)
+				return ret;
+
+			raw = FIELD_GET(BMI323_MO3_DURA_MSK, reg_value);
+			*val = raw / BMI323_MOTION_DURAT_SCALE;
+			*val2 = BMI323_RAW_TO_MICRO(raw,
+						    BMI323_MOTION_DURAT_SCALE);
+			return IIO_VAL_INT_PLUS_MICRO;
+		case IIO_EV_INFO_HYSTERESIS:
+			ret = bmi323_read_ext_reg(data,
+						  reg + BMI323_MO2_OFFSET,
+						  &reg_value);
+			if (ret)
+				return ret;
+
+			raw = FIELD_GET(BMI323_MO2_HYSTR_MSK, reg_value);
+			*val = raw / BMI323_MOTION_HYSTR_SCALE;
+			*val2 = BMI323_RAW_TO_MICRO(raw,
+						    BMI323_MOTION_HYSTR_SCALE);
+			return IIO_VAL_INT_PLUS_MICRO;
+		default:
+			return -EINVAL;
+		}
+	case IIO_EV_TYPE_CHANGE:
+		ret = bmi323_read_ext_reg(data, BMI323_STEP_SC1_REG,
+					  &reg_value);
+		if (ret)
+			return ret;
+
+		raw = FIELD_GET(BMI323_STEP_SC1_WTRMRK_MSK, reg_value);
+		*val = raw * 20;
+		return IIO_VAL_INT;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int __bmi323_fifo_flush(struct iio_dev *indio_dev)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+	int i, ret, fifo_lvl, frame_count, bit, index;
+	__le16 *frame, *pchannels;
+	u64 sample_period;
+	s64 tstamp;
+
+	guard(mutex)(&data->mutex);
+	ret = regmap_read(data->regmap, BMI323_FIFO_FILL_LEVEL_REG, &fifo_lvl);
+	if (ret)
+		return ret;
+
+	fifo_lvl = min(fifo_lvl, BMI323_FIFO_FULL_IN_WORDS);
+
+	frame_count = fifo_lvl / BMI323_FIFO_FRAME_LENGTH;
+	if (!frame_count)
+		return -EINVAL;
+
+	if (fifo_lvl % BMI323_FIFO_FRAME_LENGTH)
+		dev_warn(data->dev, "Bad FIFO alignment\n");
+
+	/*
+	 * Approximate timestamps for each of the sample based on the sampling
+	 * frequency, timestamp for last sample and number of samples.
+	 */
+	if (data->old_fifo_tstamp) {
+		sample_period = data->fifo_tstamp - data->old_fifo_tstamp;
+		do_div(sample_period, frame_count);
+	} else {
+		sample_period = data->odrns[BMI323_ACCEL];
+	}
+
+	tstamp = data->fifo_tstamp - (frame_count - 1) * sample_period;
+
+	ret = regmap_noinc_read(data->regmap, BMI323_FIFO_DATA_REG,
+				&data->fifo_buff[0],
+				fifo_lvl * BMI323_BYTES_PER_SAMPLE);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < frame_count; i++) {
+		frame = &data->fifo_buff[i * BMI323_FIFO_FRAME_LENGTH];
+		pchannels = &data->buffer.channels[0];
+
+		index = 0;
+		for_each_set_bit(bit, indio_dev->active_scan_mask,
+				 BMI323_CHAN_MAX)
+			pchannels[index++] = frame[bit];
+
+		iio_push_to_buffers_with_timestamp(indio_dev, &data->buffer,
+						   tstamp);
+
+		tstamp += sample_period;
+	}
+
+	return frame_count;
+}
+
+static int bmi323_set_watermark(struct iio_dev *indio_dev, unsigned int val)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+
+	val = min(val, (u32)BMI323_FIFO_FULL_IN_FRAMES);
+
+	guard(mutex)(&data->mutex);
+	data->watermark = val;
+
+	return 0;
+}
+
+static int bmi323_fifo_disable(struct bmi323_data *data)
+{
+	int ret;
+
+	guard(mutex)(&data->mutex);
+	ret = regmap_write(data->regmap, BMI323_FIFO_CONF_REG, 0);
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(data->regmap, BMI323_INT_MAP2_REG,
+				 BMI323_FIFO_WTRMRK_MSK,
+				 FIELD_PREP(BMI323_FIFO_WTRMRK_MSK, 0));
+	if (ret)
+		return ret;
+
+	data->fifo_tstamp = 0;
+	data->state = BMI323_IDLE;
+
+	return 0;
+}
+
+static int bmi323_buffer_predisable(struct iio_dev *indio_dev)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+
+	if (iio_device_get_current_mode(indio_dev) == INDIO_BUFFER_TRIGGERED)
+		return 0;
+
+	return bmi323_fifo_disable(data);
+}
+
+static int bmi323_update_watermark(struct bmi323_data *data)
+{
+	int wtrmrk;
+
+	wtrmrk = data->watermark * BMI323_FIFO_FRAME_LENGTH;
+
+	return regmap_write(data->regmap, BMI323_FIFO_WTRMRK_REG, wtrmrk);
+}
+
+static int bmi323_fifo_enable(struct bmi323_data *data)
+{
+	int ret;
+
+	guard(mutex)(&data->mutex);
+	ret = regmap_update_bits(data->regmap, BMI323_FIFO_CONF_REG,
+				 BMI323_FIFO_CONF_ACC_GYR_EN_MSK,
+				 FIELD_PREP(BMI323_FIFO_CONF_ACC_GYR_EN_MSK,
+					    BMI323_FIFO_ACC_GYR_MSK));
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(data->regmap, BMI323_INT_MAP2_REG,
+				 BMI323_FIFO_WTRMRK_MSK,
+				 FIELD_PREP(BMI323_FIFO_WTRMRK_MSK,
+					    data->irq_pin));
+	if (ret)
+		return ret;
+
+	ret = bmi323_update_watermark(data);
+	if (ret)
+		return ret;
+
+	ret = regmap_write(data->regmap, BMI323_FIFO_CTRL_REG,
+			   BMI323_FIFO_FLUSH_MSK);
+	if (ret)
+		return ret;
+
+	data->state = BMI323_BUFFER_FIFO;
+
+	return 0;
+}
+
+static int bmi323_buffer_preenable(struct iio_dev *indio_dev)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+
+	guard(mutex)(&data->mutex);
+	/*
+	 * When the ODR of the accelerometer and gyroscope do not match, the
+	 * maximum ODR value between the accelerometer and gyroscope is used
+	 * for FIFO and the signal with lower ODR will insert dummy frame.
+	 * So allow buffer read only when ODR's of accelero and gyro are equal.
+	 * See datasheet section 5.7 "FIFO Data Buffering".
+	 */
+	if (data->odrns[BMI323_ACCEL] != data->odrns[BMI323_GYRO]) {
+		dev_err(data->dev, "Accelero and Gyro ODR doesn't match\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int bmi323_buffer_postenable(struct iio_dev *indio_dev)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+
+	if (iio_device_get_current_mode(indio_dev) == INDIO_BUFFER_TRIGGERED)
+		return 0;
+
+	return bmi323_fifo_enable(data);
+}
+
+static ssize_t hwfifo_watermark_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct bmi323_data *data = iio_priv(indio_dev);
+	int wm;
+
+	scoped_guard(mutex, &data->mutex)
+		wm = data->watermark;
+
+	return sysfs_emit(buf, "%d\n", wm);
+}
+static IIO_DEVICE_ATTR_RO(hwfifo_watermark, 0);
+
+static ssize_t hwfifo_enabled_show(struct device *dev,
+				   struct device_attribute *attr,
+				   char *buf)
+{
+	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct bmi323_data *data = iio_priv(indio_dev);
+	bool state;
+
+	scoped_guard(mutex, &data->mutex)
+		state = data->state == BMI323_BUFFER_FIFO;
+
+	return sysfs_emit(buf, "%d\n", state);
+}
+static IIO_DEVICE_ATTR_RO(hwfifo_enabled, 0);
+
+static const struct iio_dev_attr *bmi323_fifo_attributes[] = {
+	&iio_dev_attr_hwfifo_watermark,
+	&iio_dev_attr_hwfifo_enabled,
+	NULL
+};
+
+static const struct iio_buffer_setup_ops bmi323_buffer_ops = {
+	.preenable = bmi323_buffer_preenable,
+	.postenable = bmi323_buffer_postenable,
+	.predisable = bmi323_buffer_predisable,
+};
+
+static irqreturn_t bmi323_irq_thread_handler(int irq, void *private)
+{
+	struct iio_dev *indio_dev = private;
+	struct bmi323_data *data = iio_priv(indio_dev);
+	unsigned int status_addr, status, feature_event;
+	s64 timestamp = iio_get_time_ns(indio_dev);
+	int ret;
+
+	if (data->irq_pin == BMI323_IRQ_INT1)
+		status_addr = BMI323_STATUS_INT1_REG;
+	else
+		status_addr = BMI323_STATUS_INT2_REG;
+
+	scoped_guard(mutex, &data->mutex) {
+		ret = regmap_read(data->regmap, status_addr, &status);
+		if (ret)
+			return IRQ_NONE;
+	}
+
+	if (!status || FIELD_GET(BMI323_STATUS_ERROR_MSK, status))
+		return IRQ_NONE;
+
+	if (FIELD_GET(BMI323_STATUS_FIFO_WTRMRK_MSK, status)) {
+		data->old_fifo_tstamp = data->fifo_tstamp;
+		data->fifo_tstamp = iio_get_time_ns(indio_dev);
+		ret = __bmi323_fifo_flush(indio_dev);
+		if (ret < 0)
+			return IRQ_NONE;
+	}
+
+	if (FIELD_GET(BMI323_STATUS_ACC_GYR_DRDY_MSK, status))
+		iio_trigger_poll_nested(data->trig);
+
+	if (FIELD_GET(BMI323_STATUS_MOTION_MSK, status))
+		iio_push_event(indio_dev, IIO_MOD_EVENT_CODE(IIO_ACCEL, 0,
+							     IIO_MOD_X_OR_Y_OR_Z,
+							     IIO_EV_TYPE_MAG,
+							     IIO_EV_DIR_RISING),
+			       timestamp);
+
+	if (FIELD_GET(BMI323_STATUS_NOMOTION_MSK, status))
+		iio_push_event(indio_dev, IIO_MOD_EVENT_CODE(IIO_ACCEL, 0,
+							     IIO_MOD_X_OR_Y_OR_Z,
+							     IIO_EV_TYPE_MAG,
+							     IIO_EV_DIR_FALLING),
+			       timestamp);
+
+	if (FIELD_GET(BMI323_STATUS_STP_WTR_MSK, status))
+		iio_push_event(indio_dev, IIO_MOD_EVENT_CODE(IIO_STEPS, 0,
+							     IIO_NO_MOD,
+							     IIO_EV_TYPE_CHANGE,
+							     IIO_EV_DIR_NONE),
+			       timestamp);
+
+	if (FIELD_GET(BMI323_STATUS_TAP_MSK, status)) {
+		scoped_guard(mutex, &data->mutex) {
+			ret = regmap_read(data->regmap,
+					  BMI323_FEAT_EVNT_EXT_REG,
+					  &feature_event);
+			if (ret)
+				return IRQ_NONE;
+		}
+
+		if (FIELD_GET(BMI323_FEAT_EVNT_EXT_S_MSK, feature_event)) {
+			iio_push_event(indio_dev,
+				       IIO_MOD_EVENT_CODE(IIO_ACCEL, 0,
+							  IIO_MOD_X_OR_Y_OR_Z,
+							  IIO_EV_TYPE_GESTURE,
+							  IIO_EV_DIR_SINGLETAP),
+				       timestamp);
+		}
+
+		if (FIELD_GET(BMI323_FEAT_EVNT_EXT_D_MSK, feature_event))
+			iio_push_event(indio_dev,
+				       IIO_MOD_EVENT_CODE(IIO_ACCEL, 0,
+							  IIO_MOD_X_OR_Y_OR_Z,
+							  IIO_EV_TYPE_GESTURE,
+							  IIO_EV_DIR_DOUBLETAP),
+				       timestamp);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int bmi323_set_drdy_irq(struct bmi323_data *data,
+			       enum bmi323_irq_pin irq_pin)
+{
+	int ret;
+
+	ret = regmap_update_bits(data->regmap, BMI323_INT_MAP2_REG,
+				 BMI323_GYR_DRDY_MSK,
+				 FIELD_PREP(BMI323_GYR_DRDY_MSK, irq_pin));
+	if (ret)
+		return ret;
+
+	return regmap_update_bits(data->regmap, BMI323_INT_MAP2_REG,
+				  BMI323_ACC_DRDY_MSK,
+				  FIELD_PREP(BMI323_ACC_DRDY_MSK, irq_pin));
+}
+
+static int bmi323_data_rdy_trigger_set_state(struct iio_trigger *trig,
+					     bool state)
+{
+	struct bmi323_data *data = iio_trigger_get_drvdata(trig);
+	enum bmi323_irq_pin irq_pin;
+
+	guard(mutex)(&data->mutex);
+
+	if (data->state == BMI323_BUFFER_FIFO) {
+		dev_warn(data->dev, "Can't set trigger when FIFO enabled\n");
+		return -EBUSY;
+	}
+
+	if (state) {
+		data->state = BMI323_BUFFER_DRDY_TRIGGERED;
+		irq_pin = data->irq_pin;
+	} else {
+		data->state = BMI323_IDLE;
+		irq_pin = BMI323_IRQ_DISABLED;
+	}
+
+	return bmi323_set_drdy_irq(data, irq_pin);
+}
+
+static const struct iio_trigger_ops bmi323_trigger_ops = {
+	.set_trigger_state = &bmi323_data_rdy_trigger_set_state,
+};
+
+static irqreturn_t bmi323_trigger_handler(int irq, void *p)
+{
+	struct iio_poll_func *pf = p;
+	struct iio_dev *indio_dev = pf->indio_dev;
+	struct bmi323_data *data = iio_priv(indio_dev);
+	int ret, bit, index = 0;
+
+	/* Lock to protect the data->buffer */
+	guard(mutex)(&data->mutex);
+
+	if (*indio_dev->active_scan_mask == BMI323_ALL_CHAN_MSK) {
+		ret = regmap_bulk_read(data->regmap, BMI323_ACCEL_X_REG,
+				       &data->buffer.channels,
+				       ARRAY_SIZE(data->buffer.channels));
+		if (ret)
+			return IRQ_NONE;
+	} else {
+		for_each_set_bit(bit, indio_dev->active_scan_mask,
+				 BMI323_CHAN_MAX) {
+			ret = regmap_raw_read(data->regmap,
+					      BMI323_ACCEL_X_REG + bit,
+					      &data->buffer.channels[index++],
+					      BMI323_BYTES_PER_SAMPLE);
+			if (ret)
+				return IRQ_NONE;
+		}
+	}
+
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->buffer,
+					   iio_get_time_ns(indio_dev));
+
+	iio_trigger_notify_done(indio_dev->trig);
+
+	return IRQ_HANDLED;
+}
+
+static int bmi323_set_average(struct bmi323_data *data,
+			      enum bmi323_sensor_type sensor, int avg)
+{
+	int raw = ARRAY_SIZE(bmi323_accel_gyro_avrg);
+
+	while (raw--)
+		if (avg == bmi323_accel_gyro_avrg[raw])
+			break;
+	if (raw < 0)
+		return -EINVAL;
+
+	guard(mutex)(&data->mutex);
+	return regmap_update_bits(data->regmap, bmi323_hw[sensor].config,
+				 BMI323_ACC_GYRO_CONF_AVG_MSK,
+				 FIELD_PREP(BMI323_ACC_GYRO_CONF_AVG_MSK,
+					    raw));
+}
+
+static int bmi323_get_average(struct bmi323_data *data,
+			      enum bmi323_sensor_type sensor, int *avg)
+{
+	int ret, value, raw;
+
+	scoped_guard(mutex, &data->mutex) {
+		ret = regmap_read(data->regmap, bmi323_hw[sensor].config, &value);
+		if (ret)
+			return ret;
+	}
+
+	raw = FIELD_GET(BMI323_ACC_GYRO_CONF_AVG_MSK, value);
+	*avg = bmi323_accel_gyro_avrg[raw];
+
+	return IIO_VAL_INT;
+}
+
+static int bmi323_enable_steps(struct bmi323_data *data, int val)
+{
+	int ret;
+
+	guard(mutex)(&data->mutex);
+	if (data->odrhz[BMI323_ACCEL] < 200) {
+		dev_err(data->dev, "Invalid accelerometer parameter\n");
+		return -EINVAL;
+	}
+
+	ret = bmi323_feature_engine_events(data, BMI323_FEAT_IO0_STP_CNT_MSK,
+					   val ? 1 : 0);
+	if (ret)
+		return ret;
+
+	set_mask_bits(&data->feature_events, BMI323_FEAT_IO0_STP_CNT_MSK,
+		      FIELD_PREP(BMI323_FEAT_IO0_STP_CNT_MSK, val ? 1 : 0));
+
+	return 0;
+}
+
+static int bmi323_read_steps(struct bmi323_data *data, int *val)
+{
+	int ret;
+
+	guard(mutex)(&data->mutex);
+	if (!FIELD_GET(BMI323_FEAT_IO0_STP_CNT_MSK, data->feature_events))
+		return -EINVAL;
+
+	ret = regmap_bulk_read(data->regmap, BMI323_FEAT_IO2_REG,
+			       data->steps_count,
+			       ARRAY_SIZE(data->steps_count));
+	if (ret)
+		return ret;
+
+	*val = get_unaligned_le32(data->steps_count);
+
+	return IIO_VAL_INT;
+}
+
+static int bmi323_read_axis(struct bmi323_data *data,
+			    struct iio_chan_spec const *chan, int *val)
+{
+	enum bmi323_sensor_type sensor;
+	unsigned int value;
+	u8 addr;
+	int ret;
+
+	ret = bmi323_get_error_status(data);
+	if (ret)
+		return -EINVAL;
+
+	sensor = bmi323_iio_to_sensor(chan->type);
+	addr = bmi323_hw[sensor].data + (chan->channel2 - IIO_MOD_X);
+
+	scoped_guard(mutex, &data->mutex) {
+		ret = regmap_read(data->regmap, addr, &value);
+		if (ret)
+			return ret;
+	}
+
+	*val = sign_extend32(value, chan->scan_type.realbits - 1);
+
+	return IIO_VAL_INT;
+}
+
+static int bmi323_get_temp_data(struct bmi323_data *data, int *val)
+{
+	unsigned int value;
+	int ret;
+
+	ret = bmi323_get_error_status(data);
+	if (ret)
+		return -EINVAL;
+
+	scoped_guard(mutex, &data->mutex) {
+		ret = regmap_read(data->regmap, BMI323_TEMP_REG, &value);
+		if (ret)
+			return ret;
+	}
+
+	*val = sign_extend32(value, 15);
+
+	return IIO_VAL_INT;
+}
+
+static int bmi323_get_odr(struct bmi323_data *data,
+			  enum bmi323_sensor_type sensor, int *odr, int *uodr)
+{
+	int ret, value, odr_raw;
+
+	scoped_guard(mutex, &data->mutex) {
+		ret = regmap_read(data->regmap, bmi323_hw[sensor].config, &value);
+		if (ret)
+			return ret;
+	}
+
+	odr_raw = FIELD_GET(BMI323_ACC_GYRO_CONF_ODR_MSK, value);
+	*odr = bmi323_acc_gyro_odr[odr_raw - 1][0];
+	*uodr = bmi323_acc_gyro_odr[odr_raw - 1][1];
+
+	return IIO_VAL_INT_PLUS_MICRO;
+}
+
+static int bmi323_configure_power_mode(struct bmi323_data *data,
+				       enum bmi323_sensor_type sensor,
+				       int odr_index)
+{
+	enum bmi323_opr_mode mode;
+
+	if (bmi323_acc_gyro_odr[odr_index][0] > 25)
+		mode = ACC_GYRO_MODE_CONTINOUS;
+	else
+		mode = ACC_GYRO_MODE_DUTYCYCLE;
+
+	return bmi323_set_mode(data, sensor, mode);
+}
+
+static int bmi323_set_odr(struct bmi323_data *data,
+			  enum bmi323_sensor_type sensor, int odr, int uodr)
+{
+	int odr_raw, ret;
+
+	odr_raw = ARRAY_SIZE(bmi323_acc_gyro_odr);
+
+	while (odr_raw--)
+		if (odr == bmi323_acc_gyro_odr[odr_raw][0] &&
+		    uodr == bmi323_acc_gyro_odr[odr_raw][1])
+			break;
+	if (odr_raw < 0)
+		return -EINVAL;
+
+	ret = bmi323_configure_power_mode(data, sensor, odr_raw);
+	if (ret)
+		return -EINVAL;
+
+	guard(mutex)(&data->mutex);
+	data->odrhz[sensor] = bmi323_acc_gyro_odr[odr_raw][0];
+	data->odrns[sensor] = bmi323_acc_gyro_odrns[odr_raw];
+
+	odr_raw++;
+
+	return regmap_update_bits(data->regmap, bmi323_hw[sensor].config,
+				  BMI323_ACC_GYRO_CONF_ODR_MSK,
+				  FIELD_PREP(BMI323_ACC_GYRO_CONF_ODR_MSK,
+					     odr_raw));
+}
+
+static int bmi323_get_scale(struct bmi323_data *data,
+			    enum bmi323_sensor_type sensor, int *val2)
+{
+	int ret, value, scale_raw;
+
+	scoped_guard(mutex, &data->mutex) {
+		ret = regmap_read(data->regmap, bmi323_hw[sensor].config,
+				  &value);
+		if (ret)
+			return ret;
+	}
+
+	scale_raw = FIELD_GET(BMI323_ACC_GYRO_CONF_SCL_MSK, value);
+	*val2 = bmi323_hw[sensor].scale_table[scale_raw][1];
+
+	return IIO_VAL_INT_PLUS_MICRO;
+}
+
+static int bmi323_set_scale(struct bmi323_data *data,
+			    enum bmi323_sensor_type sensor, int val, int val2)
+{
+	int scale_raw;
+
+	scale_raw = bmi323_hw[sensor].scale_table_len;
+
+	while (scale_raw--)
+		if (val == bmi323_hw[sensor].scale_table[scale_raw][0] &&
+		    val2 == bmi323_hw[sensor].scale_table[scale_raw][1])
+			break;
+	if (scale_raw < 0)
+		return -EINVAL;
+
+	guard(mutex)(&data->mutex);
+	return regmap_update_bits(data->regmap, bmi323_hw[sensor].config,
+				  BMI323_ACC_GYRO_CONF_SCL_MSK,
+				  FIELD_PREP(BMI323_ACC_GYRO_CONF_SCL_MSK,
+					     scale_raw));
+}
+
+static int bmi323_read_avail(struct iio_dev *indio_dev,
+			     struct iio_chan_spec const *chan,
+			     const int **vals, int *type, int *length,
+			     long mask)
+{
+	enum bmi323_sensor_type sensor;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_SAMP_FREQ:
+		*type = IIO_VAL_INT_PLUS_MICRO;
+		*vals = (const int *)bmi323_acc_gyro_odr;
+		*length = ARRAY_SIZE(bmi323_acc_gyro_odr) * 2;
+		return IIO_AVAIL_LIST;
+	case IIO_CHAN_INFO_SCALE:
+		sensor = bmi323_iio_to_sensor(chan->type);
+		*type = IIO_VAL_INT_PLUS_MICRO;
+		*vals = (const int *)bmi323_hw[sensor].scale_table;
+		*length = bmi323_hw[sensor].scale_table_len * 2;
+		return IIO_AVAIL_LIST;
+	case IIO_CHAN_INFO_OVERSAMPLING_RATIO:
+		*type = IIO_VAL_INT;
+		*vals = (const int *)bmi323_accel_gyro_avrg;
+		*length = ARRAY_SIZE(bmi323_accel_gyro_avrg);
+		return IIO_AVAIL_LIST;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int bmi323_write_raw(struct iio_dev *indio_dev,
+			    struct iio_chan_spec const *chan, int val,
+			    int val2, long mask)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+	int ret;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_SAMP_FREQ:
+		ret = iio_device_claim_direct_mode(indio_dev);
+		if (ret)
+			return ret;
+
+		ret = bmi323_set_odr(data, bmi323_iio_to_sensor(chan->type),
+				     val, val2);
+		iio_device_release_direct_mode(indio_dev);
+		return ret;
+	case IIO_CHAN_INFO_SCALE:
+		ret = iio_device_claim_direct_mode(indio_dev);
+		if (ret)
+			return ret;
+
+		ret = bmi323_set_scale(data, bmi323_iio_to_sensor(chan->type),
+				       val, val2);
+		iio_device_release_direct_mode(indio_dev);
+		return ret;
+	case IIO_CHAN_INFO_OVERSAMPLING_RATIO:
+		ret = iio_device_claim_direct_mode(indio_dev);
+		if (ret)
+			return ret;
+
+		ret = bmi323_set_average(data, bmi323_iio_to_sensor(chan->type),
+					 val);
+
+		iio_device_release_direct_mode(indio_dev);
+		return ret;
+	case IIO_CHAN_INFO_ENABLE:
+		return bmi323_enable_steps(data, val);
+	case IIO_CHAN_INFO_PROCESSED:
+		scoped_guard(mutex, &data->mutex) {
+			if (val || !FIELD_GET(BMI323_FEAT_IO0_STP_CNT_MSK,
+					      data->feature_events))
+				return -EINVAL;
+
+			/* Clear step counter value */
+			ret = bmi323_update_ext_reg(data, BMI323_STEP_SC1_REG,
+						    BMI323_STEP_SC1_RST_CNT_MSK,
+						    FIELD_PREP(BMI323_STEP_SC1_RST_CNT_MSK,
+							       1));
+		}
+		return ret;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int bmi323_read_raw(struct iio_dev *indio_dev,
+			   struct iio_chan_spec const *chan, int *val,
+			   int *val2, long mask)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+	int ret;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_PROCESSED:
+		return bmi323_read_steps(data, val);
+	case IIO_CHAN_INFO_RAW:
+		switch (chan->type) {
+		case IIO_ACCEL:
+		case IIO_ANGL_VEL:
+			ret = iio_device_claim_direct_mode(indio_dev);
+			if (ret)
+				return ret;
+
+			ret = bmi323_read_axis(data, chan, val);
+
+			iio_device_release_direct_mode(indio_dev);
+			return ret;
+		case IIO_TEMP:
+			return bmi323_get_temp_data(data, val);
+		default:
+			return -EINVAL;
+		}
+	case IIO_CHAN_INFO_SAMP_FREQ:
+		return bmi323_get_odr(data, bmi323_iio_to_sensor(chan->type),
+				      val, val2);
+	case IIO_CHAN_INFO_SCALE:
+		switch (chan->type) {
+		case IIO_ACCEL:
+		case IIO_ANGL_VEL:
+			*val = 0;
+			return bmi323_get_scale(data,
+						bmi323_iio_to_sensor(chan->type),
+						val2);
+		case IIO_TEMP:
+			*val = BMI323_TEMP_SCALE / MEGA;
+			*val2 = BMI323_TEMP_SCALE % MEGA;
+			return IIO_VAL_INT_PLUS_MICRO;
+		default:
+			return -EINVAL;
+		}
+	case IIO_CHAN_INFO_OVERSAMPLING_RATIO:
+		return bmi323_get_average(data,
+					  bmi323_iio_to_sensor(chan->type),
+					  val);
+	case IIO_CHAN_INFO_OFFSET:
+		switch (chan->type) {
+		case IIO_TEMP:
+			*val = BMI323_TEMP_OFFSET;
+			return IIO_VAL_INT;
+		default:
+			return -EINVAL;
+		}
+	case IIO_CHAN_INFO_ENABLE:
+		scoped_guard(mutex, &data->mutex)
+			*val = FIELD_GET(BMI323_FEAT_IO0_STP_CNT_MSK,
+					 data->feature_events);
+		return IIO_VAL_INT;
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct iio_info bmi323_info = {
+	.read_raw = bmi323_read_raw,
+	.write_raw = bmi323_write_raw,
+	.read_avail = bmi323_read_avail,
+	.hwfifo_set_watermark = bmi323_set_watermark,
+	.write_event_config = bmi323_write_event_config,
+	.read_event_config = bmi323_read_event_config,
+	.write_event_value = bmi323_write_event_value,
+	.read_event_value = bmi323_read_event_value,
+	.event_attrs = &bmi323_event_attribute_group,
+};
+
+#define BMI323_SCAN_MASK_ACCEL_3AXIS		\
+	(BIT(BMI323_ACCEL_X) | BIT(BMI323_ACCEL_Y) | BIT(BMI323_ACCEL_Z))
+
+#define BMI323_SCAN_MASK_GYRO_3AXIS		\
+	(BIT(BMI323_GYRO_X) | BIT(BMI323_GYRO_Y) | BIT(BMI323_GYRO_Z))
+
+static const unsigned long bmi323_avail_scan_masks[] = {
+	/* 3-axis accel */
+	BMI323_SCAN_MASK_ACCEL_3AXIS,
+	/* 3-axis gyro */
+	BMI323_SCAN_MASK_GYRO_3AXIS,
+	/* 3-axis accel + 3-axis gyro */
+	BMI323_SCAN_MASK_ACCEL_3AXIS | BMI323_SCAN_MASK_GYRO_3AXIS,
+	0
+};
+
+static int bmi323_int_pin_config(struct bmi323_data *data,
+				 enum bmi323_irq_pin irq_pin,
+				 bool active_high, bool open_drain, bool latch)
+{
+	unsigned int mask, field_value;
+	int ret;
+
+	ret = regmap_update_bits(data->regmap, BMI323_IO_INT_CONF_REG,
+				 BMI323_IO_INT_LTCH_MSK,
+				 FIELD_PREP(BMI323_IO_INT_LTCH_MSK, latch));
+	if (ret)
+		return ret;
+
+	ret = bmi323_update_ext_reg(data, BMI323_GEN_SET1_REG,
+				    BMI323_GEN_HOLD_DUR_MSK,
+				    FIELD_PREP(BMI323_GEN_HOLD_DUR_MSK, 0));
+	if (ret)
+		return ret;
+
+	switch (irq_pin) {
+	case BMI323_IRQ_INT1:
+		mask = BMI323_IO_INT1_LVL_OD_OP_MSK;
+
+		field_value = FIELD_PREP(BMI323_IO_INT1_LVL_MSK, active_high) |
+			      FIELD_PREP(BMI323_IO_INT1_OD_MSK, open_drain) |
+			      FIELD_PREP(BMI323_IO_INT1_OP_EN_MSK, 1);
+		break;
+	case BMI323_IRQ_INT2:
+		mask = BMI323_IO_INT2_LVL_OD_OP_MSK;
+
+		field_value = FIELD_PREP(BMI323_IO_INT2_LVL_MSK, active_high) |
+			      FIELD_PREP(BMI323_IO_INT2_OD_MSK, open_drain) |
+			      FIELD_PREP(BMI323_IO_INT2_OP_EN_MSK, 1);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return regmap_update_bits(data->regmap, BMI323_IO_INT_CTR_REG, mask,
+				  field_value);
+}
+
+static int bmi323_trigger_probe(struct bmi323_data *data,
+				struct iio_dev *indio_dev)
+{
+	bool open_drain, active_high, latch;
+	struct fwnode_handle *fwnode;
+	enum bmi323_irq_pin irq_pin;
+	int ret, irq, irq_type;
+	struct irq_data *desc;
+
+	fwnode = dev_fwnode(data->dev);
+	if (!fwnode)
+		return -ENODEV;
+
+	irq = fwnode_irq_get_byname(fwnode, "INT1");
+	if (irq > 0) {
+		irq_pin = BMI323_IRQ_INT1;
+	} else {
+		irq = fwnode_irq_get_byname(fwnode, "INT2");
+		if (irq < 0)
+			return 0;
+
+		irq_pin = BMI323_IRQ_INT2;
+	}
+
+	desc = irq_get_irq_data(irq);
+	if (!desc)
+		return dev_err_probe(data->dev, -EINVAL,
+				     "Could not find IRQ %d\n", irq);
+
+	irq_type = irqd_get_trigger_type(desc);
+	switch (irq_type) {
+	case IRQF_TRIGGER_RISING:
+		latch = false;
+		active_high = true;
+		break;
+	case IRQF_TRIGGER_HIGH:
+		latch = true;
+		active_high = true;
+		break;
+	case IRQF_TRIGGER_FALLING:
+		latch = false;
+		active_high = false;
+		break;
+	case IRQF_TRIGGER_LOW:
+		latch = true;
+		active_high = false;
+		break;
+	default:
+		return dev_err_probe(data->dev, -EINVAL,
+				     "Invalid interrupt type 0x%x specified\n",
+				     irq_type);
+	}
+
+	open_drain = fwnode_property_read_bool(fwnode, "drive-open-drain");
+
+	ret = bmi323_int_pin_config(data, irq_pin, active_high, open_drain,
+				    latch);
+	if (ret)
+		return dev_err_probe(data->dev, ret,
+				     "Failed to configure irq line\n");
+
+	data->trig = devm_iio_trigger_alloc(data->dev, "%s-trig-%d",
+					    indio_dev->name, irq_pin);
+	if (!data->trig)
+		return -ENOMEM;
+
+	data->trig->ops = &bmi323_trigger_ops;
+	iio_trigger_set_drvdata(data->trig, data);
+
+	ret = devm_request_threaded_irq(data->dev, irq, NULL,
+					bmi323_irq_thread_handler,
+					IRQF_ONESHOT, "bmi323-int", indio_dev);
+	if (ret)
+		return dev_err_probe(data->dev, ret, "Failed to request IRQ\n");
+
+	ret = devm_iio_trigger_register(data->dev, data->trig);
+	if (ret)
+		return dev_err_probe(data->dev, ret,
+				     "Trigger registration failed\n");
+
+	data->irq_pin = irq_pin;
+
+	return 0;
+}
+
+static int bmi323_feature_engine_enable(struct bmi323_data *data, bool en)
+{
+	unsigned int feature_status;
+	int ret;
+
+	if (!en)
+		return regmap_write(data->regmap, BMI323_FEAT_CTRL_REG, 0);
+
+	ret = regmap_write(data->regmap, BMI323_FEAT_IO2_REG, 0x012c);
+	if (ret)
+		return ret;
+
+	ret = regmap_write(data->regmap, BMI323_FEAT_IO_STATUS_REG,
+			   BMI323_FEAT_IO_STATUS_MSK);
+	if (ret)
+		return ret;
+
+	ret = regmap_write(data->regmap, BMI323_FEAT_CTRL_REG,
+			   BMI323_FEAT_ENG_EN_MSK);
+	if (ret)
+		return ret;
+
+	/*
+	 * It takes around 4 msec to enable the Feature engine, so check
+	 * the status of the feature engine every 2 msec for a maximum
+	 * of 5 trials.
+	 */
+	ret = regmap_read_poll_timeout(data->regmap, BMI323_FEAT_IO1_REG,
+				       feature_status,
+				       FIELD_GET(BMI323_FEAT_IO1_ERR_MSK,
+						 feature_status) == 1,
+				       BMI323_FEAT_ENG_POLL,
+				       BMI323_FEAT_ENG_TIMEOUT);
+	if (ret)
+		return dev_err_probe(data->dev, -EINVAL,
+				"Failed to enable feature engine\n");
+
+	return 0;
+}
+
+static void bmi323_disable(void *data_ptr)
+{
+	struct bmi323_data *data = data_ptr;
+
+	bmi323_set_mode(data, BMI323_ACCEL, ACC_GYRO_MODE_DISABLE);
+	bmi323_set_mode(data, BMI323_GYRO, ACC_GYRO_MODE_DISABLE);
+}
+
+static int bmi323_set_bw(struct bmi323_data *data,
+			 enum bmi323_sensor_type sensor, enum bmi323_3db_bw bw)
+{
+	return regmap_update_bits(data->regmap, bmi323_hw[sensor].config,
+				  BMI323_ACC_GYRO_CONF_BW_MSK,
+				  FIELD_PREP(BMI323_ACC_GYRO_CONF_BW_MSK, bw));
+}
+
+static int bmi323_init(struct bmi323_data *data)
+{
+	int ret, val;
+
+	/*
+	 * Perform soft reset to make sure the device is in a known state after
+	 * start up. A delay of 1.5 ms is required after reset.
+	 * See datasheet section 5.17 "Soft Reset".
+	 */
+	ret = regmap_write(data->regmap, BMI323_CMD_REG, BMI323_RST_VAL);
+	if (ret)
+		return ret;
+
+	usleep_range(1500, 2000);
+
+	/*
+	 * Dummy read is required to enable SPI interface after reset.
+	 * See datasheet section 7.2.1 "Protocol Selection".
+	 */
+	regmap_read(data->regmap, BMI323_CHIP_ID_REG, &val);
+
+	ret = regmap_read(data->regmap, BMI323_STATUS_REG, &val);
+	if (ret)
+		return ret;
+
+	if (!FIELD_GET(BMI323_STATUS_POR_MSK, val))
+		return dev_err_probe(data->dev, -EINVAL,
+				     "Sensor initialization error\n");
+
+	ret = regmap_read(data->regmap, BMI323_CHIP_ID_REG, &val);
+	if (ret)
+		return ret;
+
+	if (FIELD_GET(BMI323_CHIP_ID_MSK, val) != BMI323_CHIP_ID_VAL)
+		return dev_err_probe(data->dev, -EINVAL, "Chip ID mismatch\n");
+
+	ret = bmi323_feature_engine_enable(data, true);
+	if (ret)
+		return ret;
+
+	ret = regmap_read(data->regmap, BMI323_ERR_REG, &val);
+	if (ret)
+		return ret;
+
+	if (val)
+		return dev_err_probe(data->dev, -EINVAL,
+				     "Sensor power error = 0x%x\n", val);
+
+	/*
+	 * Set the Bandwidth coefficient which defines the 3 dB cutoff
+	 * frequency in relation to the ODR.
+	 */
+	ret = bmi323_set_bw(data, BMI323_ACCEL, BMI323_BW_ODR_BY_2);
+	if (ret)
+		return ret;
+
+	ret = bmi323_set_bw(data, BMI323_GYRO, BMI323_BW_ODR_BY_2);
+	if (ret)
+		return ret;
+
+	ret = bmi323_set_odr(data, BMI323_ACCEL, 25, 0);
+	if (ret)
+		return ret;
+
+	ret = bmi323_set_odr(data, BMI323_GYRO, 25, 0);
+	if (ret)
+		return ret;
+
+	return devm_add_action_or_reset(data->dev, bmi323_disable, data);
+}
+
+int bmi323_core_probe(struct device *dev)
+{
+	static const char * const regulator_names[] = { "vdd", "vddio" };
+	struct iio_dev *indio_dev;
+	struct bmi323_data *data;
+	struct regmap *regmap;
+	int ret;
+
+	regmap = dev_get_regmap(dev, NULL);
+	if (!regmap)
+		return dev_err_probe(dev, -ENODEV, "Failed to get regmap\n");
+
+	indio_dev = devm_iio_device_alloc(dev, sizeof(*data));
+	if (!indio_dev)
+		return dev_err_probe(dev, -ENOMEM,
+				     "Failed to allocate device\n");
+
+	ret = devm_regulator_bulk_get_enable(dev, ARRAY_SIZE(regulator_names),
+					     regulator_names);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to enable regulators\n");
+
+	data = iio_priv(indio_dev);
+	data->dev = dev;
+	data->regmap = regmap;
+	mutex_init(&data->mutex);
+
+	ret = bmi323_init(data);
+	if (ret)
+		return -EINVAL;
+
+	ret = iio_read_mount_matrix(dev, &data->orientation);
+	if (ret)
+		return ret;
+
+	indio_dev->name = "bmi323-imu";
+	indio_dev->info = &bmi323_info;
+	indio_dev->channels = bmi323_channels;
+	indio_dev->num_channels = ARRAY_SIZE(bmi323_channels);
+	indio_dev->available_scan_masks = bmi323_avail_scan_masks;
+	indio_dev->modes = INDIO_DIRECT_MODE | INDIO_BUFFER_SOFTWARE;
+	dev_set_drvdata(data->dev, indio_dev);
+
+	ret = bmi323_trigger_probe(data, indio_dev);
+	if (ret)
+		return -EINVAL;
+
+	ret = devm_iio_triggered_buffer_setup_ext(data->dev, indio_dev,
+						  &iio_pollfunc_store_time,
+						  bmi323_trigger_handler,
+						  IIO_BUFFER_DIRECTION_IN,
+						  &bmi323_buffer_ops,
+						  bmi323_fifo_attributes);
+	if (ret)
+		return dev_err_probe(data->dev, ret,
+				     "Failed to setup trigger buffer\n");
+
+	ret = devm_iio_device_register(data->dev, indio_dev);
+	if (ret)
+		return dev_err_probe(data->dev, ret,
+				     "Unable to register iio device\n");
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(bmi323_core_probe, IIO_BMI323);
+
+MODULE_DESCRIPTION("Bosch BMI323 IMU driver");
+MODULE_AUTHOR("Jagath Jog J <jagathjog1996@gmail.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/iio/imu/bmi323/bmi323_i2c.c b/drivers/iio/imu/bmi323/bmi323_i2c.c
new file mode 100644
index 000000000000..20a8001b9956
--- /dev/null
+++ b/drivers/iio/imu/bmi323/bmi323_i2c.c
@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * I2C driver for Bosch BMI323 6-Axis IMU.
+ *
+ * Copyright (C) 2023, Jagath Jog J <jagathjog1996@gmail.com>
+ */
+
+#include <linux/i2c.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+
+#include "bmi323.h"
+
+struct bmi323_i2c_priv {
+	struct i2c_client *i2c;
+	u8 i2c_rx_buffer[BMI323_FIFO_LENGTH_IN_BYTES + BMI323_I2C_DUMMY];
+};
+
+/*
+ * From BMI323 datasheet section 4: Notes on the Serial Interface Support.
+ * Each I2C register read operation requires to read two dummy bytes before
+ * the actual payload.
+ */
+static int bmi323_regmap_i2c_read(void *context, const void *reg_buf,
+				  size_t reg_size, void *val_buf,
+				  size_t val_size)
+{
+	struct bmi323_i2c_priv *priv = context;
+	struct i2c_msg msgs[2];
+	int ret;
+
+	msgs[0].addr = priv->i2c->addr;
+	msgs[0].flags = priv->i2c->flags;
+	msgs[0].len = reg_size;
+	msgs[0].buf = (u8 *)reg_buf;
+
+	msgs[1].addr = priv->i2c->addr;
+	msgs[1].len = val_size + BMI323_I2C_DUMMY;
+	msgs[1].buf = priv->i2c_rx_buffer;
+	msgs[1].flags = priv->i2c->flags | I2C_M_RD;
+
+	ret = i2c_transfer(priv->i2c->adapter, msgs, ARRAY_SIZE(msgs));
+	if (ret < 0)
+		return -EIO;
+
+	memcpy(val_buf, priv->i2c_rx_buffer + BMI323_I2C_DUMMY, val_size);
+
+	return 0;
+}
+
+static int bmi323_regmap_i2c_write(void *context, const void *data,
+				   size_t count)
+{
+	struct bmi323_i2c_priv *priv = context;
+	u8 reg;
+
+	reg = *(u8 *)data;
+	return i2c_smbus_write_i2c_block_data(priv->i2c, reg,
+					      count - sizeof(u8),
+					      data + sizeof(u8));
+}
+
+static struct regmap_bus bmi323_regmap_bus = {
+	.read = bmi323_regmap_i2c_read,
+	.write = bmi323_regmap_i2c_write,
+};
+
+static const struct regmap_config bmi323_i2c_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 16,
+	.max_register = BMI323_CFG_RES_REG,
+	.val_format_endian = REGMAP_ENDIAN_LITTLE,
+};
+
+static int bmi323_i2c_probe(struct i2c_client *i2c)
+{
+	struct device *dev = &i2c->dev;
+	struct bmi323_i2c_priv *priv;
+	struct regmap *regmap;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->i2c = i2c;
+	regmap = devm_regmap_init(dev, &bmi323_regmap_bus, priv,
+				  &bmi323_i2c_regmap_config);
+	if (IS_ERR(regmap))
+		return dev_err_probe(dev, PTR_ERR(regmap),
+				     "Failed to initialize I2C Regmap\n");
+
+	return bmi323_core_probe(dev);
+}
+
+static const struct i2c_device_id bmi323_i2c_ids[] = {
+	{ "bmi323" },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, bmi323_i2c_ids);
+
+static const struct of_device_id bmi323_of_i2c_match[] = {
+	{ .compatible = "bosch,bmi323" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, bmi323_of_i2c_match);
+
+static struct i2c_driver bmi323_i2c_driver = {
+	.driver = {
+		.name = "bmi323",
+		.of_match_table = bmi323_of_i2c_match,
+	},
+	.probe = bmi323_i2c_probe,
+	.id_table = bmi323_i2c_ids,
+};
+module_i2c_driver(bmi323_i2c_driver);
+
+MODULE_DESCRIPTION("Bosch BMI323 IMU driver");
+MODULE_AUTHOR("Jagath Jog J <jagathjog1996@gmail.com>");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(IIO_BMI323);
diff --git a/drivers/iio/imu/bmi323/bmi323_spi.c b/drivers/iio/imu/bmi323/bmi323_spi.c
new file mode 100644
index 000000000000..7b1e8127d0dd
--- /dev/null
+++ b/drivers/iio/imu/bmi323/bmi323_spi.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * SPI driver for Bosch BMI323 6-Axis IMU.
+ *
+ * Copyright (C) 2023, Jagath Jog J <jagathjog1996@gmail.com>
+ */
+
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/spi/spi.h>
+
+#include "bmi323.h"
+
+/*
+ * From BMI323 datasheet section 4: Notes on the Serial Interface Support.
+ * Each SPI register read operation requires to read one dummy byte before
+ * the actual payload.
+ */
+static int bmi323_regmap_spi_read(void *context, const void *reg_buf,
+				  size_t reg_size, void *val_buf,
+				  size_t val_size)
+{
+	struct spi_device *spi = context;
+
+	return spi_write_then_read(spi, reg_buf, reg_size, val_buf, val_size);
+}
+
+static int bmi323_regmap_spi_write(void *context, const void *data,
+				   size_t count)
+{
+	struct spi_device *spi = context;
+	u8 *data_buff = (u8 *)data;
+
+	data_buff[1] = data_buff[0];
+	return spi_write(spi, data_buff + 1, count - 1);
+}
+
+static struct regmap_bus bmi323_regmap_bus = {
+	.read = bmi323_regmap_spi_read,
+	.write = bmi323_regmap_spi_write,
+};
+
+static const struct regmap_config bmi323_spi_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 16,
+	.pad_bits = 8,
+	.read_flag_mask = BIT(7),
+	.max_register = BMI323_CFG_RES_REG,
+	.val_format_endian = REGMAP_ENDIAN_LITTLE,
+};
+
+static int bmi323_spi_probe(struct spi_device *spi)
+{
+	struct device *dev = &spi->dev;
+	struct regmap *regmap;
+
+	regmap = devm_regmap_init(dev, &bmi323_regmap_bus, dev,
+				  &bmi323_spi_regmap_config);
+	if (IS_ERR(regmap))
+		return dev_err_probe(dev, PTR_ERR(regmap),
+				     "Failed to initialize SPI Regmap\n");
+
+	return bmi323_core_probe(dev);
+}
+
+static const struct spi_device_id bmi323_spi_ids[] = {
+	{ "bmi323" },
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, bmi323_spi_ids);
+
+static const struct of_device_id bmi323_of_spi_match[] = {
+	{ .compatible = "bosch,bmi323" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, bmi323_of_spi_match);
+
+static struct spi_driver bmi323_spi_driver = {
+	.driver = {
+		.name = "bmi323",
+		.of_match_table = bmi323_of_spi_match,
+	},
+	.probe = bmi323_spi_probe,
+	.id_table = bmi323_spi_ids,
+};
+module_spi_driver(bmi323_spi_driver);
+
+MODULE_DESCRIPTION("Bosch BMI323 IMU driver");
+MODULE_AUTHOR("Jagath Jog J <jagathjog1996@gmail.com>");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(IIO_BMI323);
diff --git a/drivers/iio/imu/bno055/Kconfig b/drivers/iio/imu/bno055/Kconfig
index 83e53acfbe88..c7f5866a177d 100644
--- a/drivers/iio/imu/bno055/Kconfig
+++ b/drivers/iio/imu/bno055/Kconfig
@@ -8,6 +8,7 @@ config BOSCH_BNO055
 config BOSCH_BNO055_SERIAL
 	tristate "Bosch BNO055 attached via UART"
 	depends on SERIAL_DEV_BUS
+	select REGMAP
 	select BOSCH_BNO055
 	help
 	  Enable this to support Bosch BNO055 IMUs attached via UART.
diff --git a/drivers/iio/imu/bno055/bno055_ser_core.c b/drivers/iio/imu/bno055/bno055_ser_core.c
index 57728a568471..5677bdf4f846 100644
--- a/drivers/iio/imu/bno055/bno055_ser_core.c
+++ b/drivers/iio/imu/bno055/bno055_ser_core.c
@@ -378,12 +378,12 @@ static void bno055_ser_handle_rx(struct bno055_ser_priv *priv, int status)
  * Also, we assume to RX one pkt per time (i.e. the HW doesn't send anything
  * unless we require to AND we don't queue more than one request per time).
  */
-static int bno055_ser_receive_buf(struct serdev_device *serdev,
-				  const unsigned char *buf, size_t size)
+static ssize_t bno055_ser_receive_buf(struct serdev_device *serdev,
+				      const u8 *buf, size_t size)
 {
 	int status;
 	struct bno055_ser_priv *priv = serdev_device_get_drvdata(serdev);
-	int remaining = size;
+	size_t remaining = size;
 
 	if (size == 0)
 		return 0;
diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c
index b1e4fde27d25..f67bd5a39beb 100644
--- a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c
+++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c
@@ -137,10 +137,7 @@ static int inv_icm42600_accel_update_scan_mode(struct iio_dev *indio_dev,
 out_unlock:
 	mutex_unlock(&st->lock);
 	/* sleep maximum required time */
-	if (sleep_accel > sleep_temp)
-		sleep = sleep_accel;
-	else
-		sleep = sleep_temp;
+	sleep = max(sleep_accel, sleep_temp);
 	if (sleep)
 		msleep(sleep);
 	return ret;
diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c
index 6ef1df9d60b7..b52f328fd26c 100644
--- a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c
+++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c
@@ -424,10 +424,7 @@ out_unlock:
 	mutex_unlock(&st->lock);
 
 	/* sleep maximum required time */
-	if (sleep_sensor > sleep_temp)
-		sleep = sleep_sensor;
-	else
-		sleep = sleep_temp;
+	sleep = max(sleep_sensor, sleep_temp);
 	if (sleep)
 		msleep(sleep);
 
diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c
index 3bf946e56e1d..3df0a715e885 100644
--- a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c
+++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c
@@ -137,10 +137,7 @@ static int inv_icm42600_gyro_update_scan_mode(struct iio_dev *indio_dev,
 out_unlock:
 	mutex_unlock(&st->lock);
 	/* sleep maximum required time */
-	if (sleep_gyro > sleep_temp)
-		sleep = sleep_gyro;
-	else
-		sleep = sleep_temp;
+	sleep = max(sleep_gyro, sleep_temp);
 	if (sleep)
 		msleep(sleep);
 	return ret;
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
index 6b034dccc3b1..0e94e5335e93 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
@@ -567,15 +567,12 @@ static int inv_mpu6050_init_config(struct iio_dev *indio_dev)
 static int inv_mpu6050_sensor_set(struct inv_mpu6050_state  *st, int reg,
 				int axis, int val)
 {
-	int ind, result;
+	int ind;
 	__be16 d = cpu_to_be16(val);
 
 	ind = (axis - IIO_MOD_X) * 2;
-	result = regmap_bulk_write(st->map, reg + ind, &d, sizeof(d));
-	if (result)
-		return -EINVAL;
 
-	return 0;
+	return regmap_bulk_write(st->map, reg + ind, &d, sizeof(d));
 }
 
 static int inv_mpu6050_sensor_show(struct inv_mpu6050_state  *st, int reg,
@@ -587,7 +584,7 @@ static int inv_mpu6050_sensor_show(struct inv_mpu6050_state  *st, int reg,
 	ind = (axis - IIO_MOD_X) * 2;
 	result = regmap_bulk_read(st->map, reg + ind, &d, sizeof(d));
 	if (result)
-		return -EINVAL;
+		return result;
 	*val = (short)be16_to_cpup(&d);
 
 	return IIO_VAL_INT;
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
index 66d4ba088e70..d4f9b5d8d28d 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
@@ -109,6 +109,8 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p)
 	/* compute and process only all complete datum */
 	nb = fifo_count / bytes_per_datum;
 	fifo_count = nb * bytes_per_datum;
+	if (nb == 0)
+		goto end_session;
 	/* Each FIFO data contains all sensors, so same number for FIFO and sensor data */
 	fifo_period = NSEC_PER_SEC / INV_MPU6050_DIVIDER_TO_FIFO_RATE(st->chip_config.divider);
 	inv_sensors_timestamp_interrupt(&st->timestamp, fifo_period, nb, nb, pf->timestamp);
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
index 676704f9151f..e6e6e94452a3 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
@@ -111,6 +111,7 @@ int inv_mpu6050_prepare_fifo(struct inv_mpu6050_state *st, bool enable)
 	if (enable) {
 		/* reset timestamping */
 		inv_sensors_timestamp_reset(&st->timestamp);
+		inv_sensors_timestamp_apply_odr(&st->timestamp, 0, 0, 0);
 		/* reset FIFO */
 		d = st->chip_config.user_ctrl | INV_MPU6050_BIT_FIFO_RST;
 		ret = regmap_write(st->map, st->reg->user_ctrl, d);
@@ -184,6 +185,10 @@ static int inv_mpu6050_set_enable(struct iio_dev *indio_dev, bool enable)
 		if (result)
 			goto error_power_off;
 	} else {
+		st->chip_config.gyro_fifo_enable = 0;
+		st->chip_config.accl_fifo_enable = 0;
+		st->chip_config.temp_fifo_enable = 0;
+		st->chip_config.magn_fifo_enable = 0;
 		result = inv_mpu6050_prepare_fifo(st, false);
 		if (result)
 			goto error_power_off;
diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index 176d31d9f9d8..b581a7e80566 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -413,6 +413,22 @@ static const unsigned long *iio_scan_mask_match(const unsigned long *av_masks,
 {
 	if (bitmap_empty(mask, masklength))
 		return NULL;
+	/*
+	 * The condition here do not handle multi-long masks correctly.
+	 * It only checks the first long to be zero, and will use such mask
+	 * as a terminator even if there was bits set after the first long.
+	 *
+	 * Correct check would require using:
+	 * while (!bitmap_empty(av_masks, masklength))
+	 * instead. This is potentially hazardous because the
+	 * avaliable_scan_masks is a zero terminated array of longs - and
+	 * using the proper bitmap_empty() check for multi-long wide masks
+	 * would require the array to be terminated with multiple zero longs -
+	 * which is not such an usual pattern.
+	 *
+	 * As writing of this no multi-long wide masks were found in-tree, so
+	 * the simple while (*av_masks) check is working.
+	 */
 	while (*av_masks) {
 		if (strict) {
 			if (bitmap_equal(mask, av_masks, masklength))
@@ -600,7 +616,7 @@ static int iio_buffer_add_channel_sysfs(struct iio_dev *indio_dev,
 				     &iio_show_fixed_type,
 				     NULL,
 				     0,
-				     0,
+				     IIO_SEPARATE,
 				     &indio_dev->dev,
 				     buffer,
 				     &buffer->buffer_attr_list);
@@ -613,7 +629,7 @@ static int iio_buffer_add_channel_sysfs(struct iio_dev *indio_dev,
 					     &iio_scan_el_show,
 					     &iio_scan_el_store,
 					     chan->scan_index,
-					     0,
+					     IIO_SEPARATE,
 					     &indio_dev->dev,
 					     buffer,
 					     &buffer->buffer_attr_list);
@@ -623,7 +639,7 @@ static int iio_buffer_add_channel_sysfs(struct iio_dev *indio_dev,
 					     &iio_scan_el_ts_show,
 					     &iio_scan_el_ts_store,
 					     chan->scan_index,
-					     0,
+					     IIO_SEPARATE,
 					     &indio_dev->dev,
 					     buffer,
 					     &buffer->buffer_attr_list);
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index c77745b594bd..173dc00762a1 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -117,6 +117,8 @@ static const char * const iio_modifier_names[] = {
 	[IIO_MOD_LIGHT_GREEN] = "green",
 	[IIO_MOD_LIGHT_BLUE] = "blue",
 	[IIO_MOD_LIGHT_UV] = "uv",
+	[IIO_MOD_LIGHT_UVA] = "uva",
+	[IIO_MOD_LIGHT_UVB] = "uvb",
 	[IIO_MOD_LIGHT_DUV] = "duv",
 	[IIO_MOD_QUATERNION] = "quaternion",
 	[IIO_MOD_TEMP_AMBIENT] = "ambient",
@@ -182,6 +184,7 @@ static const char * const iio_chan_info_postfix[] = {
 	[IIO_CHAN_INFO_THERMOCOUPLE_TYPE] = "thermocouple_type",
 	[IIO_CHAN_INFO_CALIBAMBIENT] = "calibambient",
 	[IIO_CHAN_INFO_ZEROPOINT] = "zeropoint",
+	[IIO_CHAN_INFO_TROUGH] = "trough_raw",
 };
 /**
  * iio_device_id() - query the unique ID for the device
@@ -1581,10 +1584,13 @@ static int iio_device_register_sysfs(struct iio_dev *indio_dev)
 	ret = iio_device_register_sysfs_group(indio_dev,
 					      &iio_dev_opaque->chan_attr_group);
 	if (ret)
-		goto error_clear_attrs;
+		goto error_free_chan_attrs;
 
 	return 0;
 
+error_free_chan_attrs:
+	kfree(iio_dev_opaque->chan_attr_group.attrs);
+	iio_dev_opaque->chan_attr_group.attrs = NULL;
 error_clear_attrs:
 	iio_free_chan_devattr_list(&iio_dev_opaque->channel_attr_list);
 
@@ -1896,6 +1902,66 @@ static int iio_check_extended_name(const struct iio_dev *indio_dev)
 
 static const struct iio_buffer_setup_ops noop_ring_setup_ops;
 
+static void iio_sanity_check_avail_scan_masks(struct iio_dev *indio_dev)
+{
+	unsigned int num_masks, masklength, longs_per_mask;
+	const unsigned long *av_masks;
+	int i;
+
+	av_masks = indio_dev->available_scan_masks;
+	masklength = indio_dev->masklength;
+	longs_per_mask = BITS_TO_LONGS(masklength);
+
+	/*
+	 * The code determining how many available_scan_masks is in the array
+	 * will be assuming the end of masks when first long with all bits
+	 * zeroed is encountered. This is incorrect for masks where mask
+	 * consists of more than one long, and where some of the available masks
+	 * has long worth of bits zeroed (but has subsequent bit(s) set). This
+	 * is a safety measure against bug where array of masks is terminated by
+	 * a single zero while mask width is greater than width of a long.
+	 */
+	if (longs_per_mask > 1)
+		dev_warn(indio_dev->dev.parent,
+			 "multi long available scan masks not fully supported\n");
+
+	if (bitmap_empty(av_masks, masklength))
+		dev_warn(indio_dev->dev.parent, "empty scan mask\n");
+
+	for (num_masks = 0; *av_masks; num_masks++)
+		av_masks += longs_per_mask;
+
+	if (num_masks < 2)
+		return;
+
+	av_masks = indio_dev->available_scan_masks;
+
+	/*
+	 * Go through all the masks from first to one before the last, and see
+	 * that no mask found later from the available_scan_masks array is a
+	 * subset of mask found earlier. If this happens, then the mask found
+	 * later will never get used because scanning the array is stopped when
+	 * the first suitable mask is found. Drivers should order the array of
+	 * available masks in the order of preference (presumably the least
+	 * costy to access masks first).
+	 */
+	for (i = 0; i < num_masks - 1; i++) {
+		const unsigned long *mask1;
+		int j;
+
+		mask1 = av_masks + i * longs_per_mask;
+		for (j = i + 1; j < num_masks; j++) {
+			const unsigned long *mask2;
+
+			mask2 = av_masks + j * longs_per_mask;
+			if (bitmap_subset(mask2, mask1, masklength))
+				dev_warn(indio_dev->dev.parent,
+					 "available_scan_mask %d subset of %d. Never used\n",
+					 j, i);
+		}
+	}
+}
+
 int __iio_device_register(struct iio_dev *indio_dev, struct module *this_mod)
 {
 	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
@@ -1934,6 +2000,9 @@ int __iio_device_register(struct iio_dev *indio_dev, struct module *this_mod)
 		goto error_unreg_debugfs;
 	}
 
+	if (indio_dev->available_scan_masks)
+		iio_sanity_check_avail_scan_masks(indio_dev);
+
 	ret = iio_device_register_sysfs(indio_dev);
 	if (ret) {
 		dev_err(indio_dev->dev.parent,
diff --git a/drivers/iio/light/Kconfig b/drivers/iio/light/Kconfig
index 45edba797e4c..143003232d1c 100644
--- a/drivers/iio/light/Kconfig
+++ b/drivers/iio/light/Kconfig
@@ -252,6 +252,21 @@ config ISL29125
 	  To compile this driver as a module, choose M here: the module will be
 	  called isl29125.
 
+config ISL76682
+	tristate "Intersil ISL76682 Light Sensor"
+	depends on I2C
+	select REGMAP_I2C
+	help
+	  Say Y here if you want to build a driver for the Intersil ISL76682
+	  Ambient Light Sensor and IR Intensity sensor. This driver provides
+	  the readouts via standard IIO sysfs and device interface. Both ALS
+	  illuminance and IR illuminance are provided raw with separate scale
+	  setting which can be configured via sysfs, the default scale is 1000
+	  lux, other options are 4000/16000/64000 lux.
+
+	  To compile this driver as a module, choose M here: the module will be
+	  called isl76682.
+
 config HID_SENSOR_ALS
 	depends on HID_SENSOR_HUB
 	select IIO_BUFFER
@@ -347,6 +362,17 @@ config SENSORS_LM3533
 	  changes. The ALS-control output values can be set per zone for the
 	  three current output channels.
 
+config LTR390
+	tristate "LTR-390UV-01 ambient light and UV sensor"
+	depends on I2C
+	select REGMAP_I2C
+	help
+	  If you say yes here you get support for the Lite-On LTR-390UV-01
+	  ambient light and UV sensor.
+
+	  This driver can also be built as a module.  If so, the module
+	  will be called ltr390.
+
 config LTR501
 	tristate "LTR-501ALS-01 light sensor"
 	depends on I2C
@@ -637,6 +663,17 @@ config VEML6070
 	  To compile this driver as a module, choose M here: the
 	  module will be called veml6070.
 
+config VEML6075
+	tristate "VEML6075 UVA and UVB light sensor"
+	select REGMAP_I2C
+	depends on I2C
+	help
+	  Say Y here if you want to build a driver for the Vishay VEML6075 UVA
+	  and UVB light sensor.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called veml6075.
+
 config VL6180
 	tristate "VL6180 ALS, range and proximity sensor"
 	depends on I2C
diff --git a/drivers/iio/light/Makefile b/drivers/iio/light/Makefile
index c0db4c4c36ec..2e5fdb33e0e9 100644
--- a/drivers/iio/light/Makefile
+++ b/drivers/iio/light/Makefile
@@ -28,8 +28,10 @@ obj-$(CONFIG_IQS621_ALS)	+= iqs621-als.o
 obj-$(CONFIG_SENSORS_ISL29018)	+= isl29018.o
 obj-$(CONFIG_SENSORS_ISL29028)	+= isl29028.o
 obj-$(CONFIG_ISL29125)		+= isl29125.o
+obj-$(CONFIG_ISL76682)		+= isl76682.o
 obj-$(CONFIG_JSA1212)		+= jsa1212.o
 obj-$(CONFIG_SENSORS_LM3533)	+= lm3533-als.o
+obj-$(CONFIG_LTR390)		+= ltr390.o
 obj-$(CONFIG_LTR501)		+= ltr501.o
 obj-$(CONFIG_LTRF216A)		+= ltrf216a.o
 obj-$(CONFIG_LV0104CS)		+= lv0104cs.o
@@ -60,5 +62,6 @@ obj-$(CONFIG_VCNL4000)		+= vcnl4000.o
 obj-$(CONFIG_VCNL4035)		+= vcnl4035.o
 obj-$(CONFIG_VEML6030)		+= veml6030.o
 obj-$(CONFIG_VEML6070)		+= veml6070.o
+obj-$(CONFIG_VEML6075)		+= veml6075.o
 obj-$(CONFIG_VL6180)		+= vl6180.o
 obj-$(CONFIG_ZOPT2201)		+= zopt2201.o
diff --git a/drivers/iio/light/hid-sensor-als.c b/drivers/iio/light/hid-sensor-als.c
index 5cd27f04b45e..b6c4bef2a7bb 100644
--- a/drivers/iio/light/hid-sensor-als.c
+++ b/drivers/iio/light/hid-sensor-als.c
@@ -226,6 +226,7 @@ static int als_capture_sample(struct hid_sensor_hub_device *hsdev,
 	case HID_USAGE_SENSOR_TIME_TIMESTAMP:
 		als_state->timestamp = hid_sensor_convert_timestamp(&als_state->common_attributes,
 								    *(s64 *)raw_data);
+		ret = 0;
 		break;
 	default:
 		break;
diff --git a/drivers/iio/light/isl76682.c b/drivers/iio/light/isl76682.c
new file mode 100644
index 000000000000..cf6ddee44ffc
--- /dev/null
+++ b/drivers/iio/light/isl76682.c
@@ -0,0 +1,345 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * IIO driver for the light sensor ISL76682.
+ * ISL76682 is Ambient Light Sensor
+ *
+ * Copyright (c) 2023 Marek Vasut <marex@denx.de>
+ */
+
+#include <linux/array_size.h>
+#include <linux/bits.h>
+#include <linux/cleanup.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/regmap.h>
+#include <linux/types.h>
+
+#include <linux/iio/iio.h>
+
+#define ISL76682_REG_COMMAND			0x00
+
+#define ISL76682_COMMAND_EN			BIT(7)
+#define ISL76682_COMMAND_MODE_CONTINUOUS	BIT(6)
+#define ISL76682_COMMAND_LIGHT_IR		BIT(5)
+
+#define ISL76682_COMMAND_RANGE_LUX_1K		0x0
+#define ISL76682_COMMAND_RANGE_LUX_4K		0x1
+#define ISL76682_COMMAND_RANGE_LUX_16K		0x2
+#define ISL76682_COMMAND_RANGE_LUX_64K		0x3
+#define ISL76682_COMMAND_RANGE_LUX_MASK		GENMASK(1, 0)
+
+#define ISL76682_REG_ALSIR_L			0x01
+
+#define ISL76682_REG_ALSIR_U			0x02
+
+#define ISL76682_NUM_REGS			(ISL76682_REG_ALSIR_U + 1)
+
+#define ISL76682_CONV_TIME_MS			100
+#define ISL76682_INT_TIME_US			90000
+
+#define ISL76682_ADC_MAX			(BIT(16) - 1)
+
+struct isl76682_chip {
+	/*
+	 * Lock to synchronize access to device command register
+	 * and the content of range variable below.
+	 */
+	struct mutex			lock;
+	struct regmap			*regmap;
+	u8				range;
+	u8				command;
+};
+
+struct isl76682_range {
+	u8				range;
+	u32				als;
+	u32				ir;
+};
+
+static struct isl76682_range isl76682_range_table[] = {
+	{ ISL76682_COMMAND_RANGE_LUX_1K, 15000, 10500 },
+	{ ISL76682_COMMAND_RANGE_LUX_4K, 60000, 42000 },
+	{ ISL76682_COMMAND_RANGE_LUX_16K, 240000, 168000 },
+	{ ISL76682_COMMAND_RANGE_LUX_64K, 960000, 673000 }
+};
+
+static int isl76682_get(struct isl76682_chip *chip, bool mode_ir, int *data)
+{
+	u8 command;
+	int ret;
+
+	command = ISL76682_COMMAND_EN | ISL76682_COMMAND_MODE_CONTINUOUS |
+		  chip->range;
+
+	if (mode_ir)
+		command |= ISL76682_COMMAND_LIGHT_IR;
+
+	if (command != chip->command) {
+		ret = regmap_write(chip->regmap, ISL76682_REG_COMMAND, command);
+		if (ret)
+			return ret;
+
+		/* Need to wait for conversion time if ALS/IR mode enabled */
+		msleep(ISL76682_CONV_TIME_MS);
+
+		chip->command = command;
+	}
+
+	ret = regmap_bulk_read(chip->regmap, ISL76682_REG_ALSIR_L, data, 2);
+	*data &= ISL76682_ADC_MAX;
+	return ret;
+}
+
+static int isl76682_write_raw(struct iio_dev *indio_dev,
+			      struct iio_chan_spec const *chan,
+			      int val, int val2, long mask)
+{
+	struct isl76682_chip *chip = iio_priv(indio_dev);
+	int i;
+
+	if (mask != IIO_CHAN_INFO_SCALE)
+		return -EINVAL;
+
+	if (val != 0)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(isl76682_range_table); i++) {
+		if (chan->type == IIO_LIGHT && val2 != isl76682_range_table[i].als)
+			continue;
+		if (chan->type == IIO_INTENSITY && val2 != isl76682_range_table[i].ir)
+			continue;
+
+		scoped_guard(mutex, &chip->lock)
+			chip->range = isl76682_range_table[i].range;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int isl76682_read_raw(struct iio_dev *indio_dev,
+			     struct iio_chan_spec const *chan,
+			     int *val, int *val2, long mask)
+{
+	struct isl76682_chip *chip = iio_priv(indio_dev);
+	int ret;
+	int i;
+
+	guard(mutex)(&chip->lock);
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		switch (chan->type) {
+		case IIO_LIGHT:
+			ret = isl76682_get(chip, false, val);
+			return (ret < 0) ? ret : IIO_VAL_INT;
+		case IIO_INTENSITY:
+			ret = isl76682_get(chip, true, val);
+			return (ret < 0) ? ret : IIO_VAL_INT;
+		default:
+			return -EINVAL;
+		}
+	case IIO_CHAN_INFO_SCALE:
+		for (i = 0; i < ARRAY_SIZE(isl76682_range_table); i++) {
+			if (chip->range != isl76682_range_table[i].range)
+				continue;
+
+			*val = 0;
+			switch (chan->type) {
+			case IIO_LIGHT:
+				*val2 = isl76682_range_table[i].als;
+				return IIO_VAL_INT_PLUS_MICRO;
+			case IIO_INTENSITY:
+				*val2 = isl76682_range_table[i].ir;
+				return IIO_VAL_INT_PLUS_MICRO;
+			default:
+				return -EINVAL;
+			}
+		}
+		return -EINVAL;
+	case IIO_CHAN_INFO_INT_TIME:
+		*val = 0;
+		*val2 = ISL76682_INT_TIME_US;
+		return IIO_VAL_INT_PLUS_MICRO;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int illuminance_scale_available[] = {
+	0, 15000,
+	0, 60000,
+	0, 240000,
+	0, 960000,
+};
+
+static int intensity_scale_available[] = {
+	0, 10500,
+	0, 42000,
+	0, 168000,
+	0, 673000,
+};
+
+static int isl76682_read_avail(struct iio_dev *indio_dev,
+			       struct iio_chan_spec const *chan,
+			       const int **vals, int *type,
+			       int *length, long mask)
+{
+	switch (mask) {
+	case IIO_CHAN_INFO_SCALE:
+		switch (chan->type) {
+		case IIO_LIGHT:
+			*vals = illuminance_scale_available;
+			*length = ARRAY_SIZE(illuminance_scale_available);
+			*type = IIO_VAL_INT_PLUS_MICRO;
+			return IIO_AVAIL_LIST;
+		case IIO_INTENSITY:
+			*vals = intensity_scale_available;
+			*length = ARRAY_SIZE(intensity_scale_available);
+			*type = IIO_VAL_INT_PLUS_MICRO;
+			return IIO_AVAIL_LIST;
+		default:
+			return -EINVAL;
+		}
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct iio_chan_spec isl76682_channels[] = {
+	{
+		.type = IIO_LIGHT,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+				      BIT(IIO_CHAN_INFO_SCALE),
+		.info_mask_shared_by_type_available = BIT(IIO_CHAN_INFO_SCALE),
+		.info_mask_shared_by_all = BIT(IIO_CHAN_INFO_INT_TIME),
+	}, {
+		.type = IIO_INTENSITY,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+				      BIT(IIO_CHAN_INFO_SCALE),
+		.info_mask_shared_by_type_available = BIT(IIO_CHAN_INFO_SCALE),
+		.info_mask_shared_by_all = BIT(IIO_CHAN_INFO_INT_TIME),
+	}
+};
+
+static const struct iio_info isl76682_info = {
+	.read_avail	= isl76682_read_avail,
+	.read_raw	= isl76682_read_raw,
+	.write_raw	= isl76682_write_raw,
+};
+
+static int isl76682_clear_configure_reg(struct isl76682_chip *chip)
+{
+	struct device *dev = regmap_get_device(chip->regmap);
+	int ret;
+
+	ret = regmap_write(chip->regmap, ISL76682_REG_COMMAND, 0x0);
+	if (ret < 0)
+		dev_err(dev, "Error %d clearing the CONFIGURE register\n", ret);
+
+	/*
+	 * In the success case, the command register was zeroed out.
+	 *
+	 * In the error case, we do not know in which state the command
+	 * register is, so we assume it is zeroed out, so that it would
+	 * be reprogrammed at the next data read out, and at that time
+	 * we hope it would be reprogrammed successfully. That is very
+	 * much a best effort approach.
+	 */
+	chip->command = 0;
+
+	return ret;
+}
+
+static void isl76682_reset_action(void *chip)
+{
+	isl76682_clear_configure_reg(chip);
+}
+
+static bool isl76682_is_volatile_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case ISL76682_REG_ALSIR_L:
+	case ISL76682_REG_ALSIR_U:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static const struct regmap_config isl76682_regmap_config = {
+	.reg_bits		= 8,
+	.val_bits		= 8,
+	.volatile_reg		= isl76682_is_volatile_reg,
+	.max_register		= ISL76682_NUM_REGS - 1,
+	.num_reg_defaults_raw	= ISL76682_NUM_REGS,
+	.cache_type		= REGCACHE_FLAT,
+};
+
+static int isl76682_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct isl76682_chip *chip;
+	struct iio_dev *indio_dev;
+	int ret;
+
+	indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*chip));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	chip = iio_priv(indio_dev);
+
+	mutex_init(&chip->lock);
+
+	chip->regmap = devm_regmap_init_i2c(client, &isl76682_regmap_config);
+	ret = PTR_ERR_OR_ZERO(chip->regmap);
+	if (ret)
+		return dev_err_probe(dev, ret, "Error initializing regmap\n");
+
+	chip->range = ISL76682_COMMAND_RANGE_LUX_1K;
+
+	ret = isl76682_clear_configure_reg(chip);
+	if (ret < 0)
+		return ret;
+
+	ret = devm_add_action_or_reset(dev, isl76682_reset_action, chip);
+	if (ret)
+		return ret;
+
+	indio_dev->info = &isl76682_info;
+	indio_dev->channels = isl76682_channels;
+	indio_dev->num_channels = ARRAY_SIZE(isl76682_channels);
+	indio_dev->name = "isl76682";
+	indio_dev->modes = INDIO_DIRECT_MODE;
+
+	return devm_iio_device_register(dev, indio_dev);
+}
+
+static const struct i2c_device_id isl76682_id[] = {
+	{ "isl76682" },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, isl76682_id);
+
+static const struct of_device_id isl76682_of_match[] = {
+	{ .compatible = "isil,isl76682" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, isl76682_of_match);
+
+static struct i2c_driver isl76682_driver = {
+	.driver  = {
+		.name		= "isl76682",
+		.of_match_table	= isl76682_of_match,
+	},
+	.probe		= isl76682_probe,
+	.id_table	= isl76682_id,
+};
+module_i2c_driver(isl76682_driver);
+
+MODULE_DESCRIPTION("ISL76682 Ambient Light Sensor driver");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Marek Vasut <marex@denx.de>");
diff --git a/drivers/iio/light/ltr390.c b/drivers/iio/light/ltr390.c
new file mode 100644
index 000000000000..fff1e899097d
--- /dev/null
+++ b/drivers/iio/light/ltr390.c
@@ -0,0 +1,196 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * IIO driver for Lite-On LTR390 ALS and UV sensor
+ * (7-bit I2C slave address 0x53)
+ *
+ * Based on the work of:
+ *   Shreeya Patel and Shi Zhigang (LTRF216 Driver)
+ *
+ * Copyright (C) 2023 Anshul Dalal <anshulusr@gmail.com>
+ *
+ * Datasheet:
+ *   https://optoelectronics.liteon.com/upload/download/DS86-2015-0004/LTR-390UV_Final_%20DS_V1%201.pdf
+ *
+ * TODO:
+ *   - Support for configurable gain and resolution
+ *   - Sensor suspend/resume support
+ *   - Add support for reading the ALS
+ *   - Interrupt support
+ */
+
+#include <linux/i2c.h>
+#include <linux/math.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/regmap.h>
+
+#include <linux/iio/iio.h>
+
+#include <asm/unaligned.h>
+
+#define LTR390_MAIN_CTRL      0x00
+#define LTR390_PART_ID	      0x06
+#define LTR390_UVS_DATA	      0x10
+
+#define LTR390_SW_RESET	      BIT(4)
+#define LTR390_UVS_MODE	      BIT(3)
+#define LTR390_SENSOR_ENABLE  BIT(1)
+
+#define LTR390_PART_NUMBER_ID 0xb
+
+/*
+ * At 20-bit resolution (integration time: 400ms) and 18x gain, 2300 counts of
+ * the sensor are equal to 1 UV Index [Datasheet Page#8].
+ *
+ * For the default resolution of 18-bit (integration time: 100ms) and default
+ * gain of 3x, the counts/uvi are calculated as follows:
+ * 2300 / ((3/18) * (100/400)) = 95.83
+ */
+#define LTR390_COUNTS_PER_UVI 96
+
+/*
+ * Window Factor is needed when the device is under Window glass with coated
+ * tinted ink. This is to compensate for the light loss due to the lower
+ * transmission rate of the window glass and helps * in calculating lux.
+ */
+#define LTR390_WINDOW_FACTOR 1
+
+struct ltr390_data {
+	struct regmap *regmap;
+	struct i2c_client *client;
+	/* Protects device from simulataneous reads */
+	struct mutex lock;
+};
+
+static const struct regmap_config ltr390_regmap_config = {
+	.name = "ltr390",
+	.reg_bits = 8,
+	.reg_stride = 1,
+	.val_bits = 8,
+};
+
+static int ltr390_register_read(struct ltr390_data *data, u8 register_address)
+{
+	struct device *dev = &data->client->dev;
+	int ret;
+	u8 recieve_buffer[3];
+
+	guard(mutex)(&data->lock);
+
+	ret = regmap_bulk_read(data->regmap, register_address, recieve_buffer,
+			       sizeof(recieve_buffer));
+	if (ret) {
+		dev_err(dev, "failed to read measurement data");
+		return ret;
+	}
+
+	return get_unaligned_le24(recieve_buffer);
+}
+
+static int ltr390_read_raw(struct iio_dev *iio_device,
+			   struct iio_chan_spec const *chan, int *val,
+			   int *val2, long mask)
+{
+	int ret;
+	struct ltr390_data *data = iio_priv(iio_device);
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		ret = ltr390_register_read(data, LTR390_UVS_DATA);
+		if (ret < 0)
+			return ret;
+		*val = ret;
+		return IIO_VAL_INT;
+	case IIO_CHAN_INFO_SCALE:
+		*val = LTR390_WINDOW_FACTOR;
+		*val2 = LTR390_COUNTS_PER_UVI;
+		return IIO_VAL_FRACTIONAL;
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct iio_info ltr390_info = {
+	.read_raw = ltr390_read_raw,
+};
+
+static const struct iio_chan_spec ltr390_channel = {
+	.type = IIO_UVINDEX,
+	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE)
+};
+
+static int ltr390_probe(struct i2c_client *client)
+{
+	struct ltr390_data *data;
+	struct iio_dev *indio_dev;
+	struct device *dev;
+	int ret, part_number;
+
+	dev = &client->dev;
+	indio_dev = devm_iio_device_alloc(dev, sizeof(*data));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	data = iio_priv(indio_dev);
+
+	data->regmap = devm_regmap_init_i2c(client, &ltr390_regmap_config);
+	if (IS_ERR(data->regmap))
+		return dev_err_probe(dev, PTR_ERR(data->regmap),
+				     "regmap initialization failed\n");
+
+	data->client = client;
+	mutex_init(&data->lock);
+
+	indio_dev->info = &ltr390_info;
+	indio_dev->channels = &ltr390_channel;
+	indio_dev->num_channels = 1;
+	indio_dev->name = "ltr390";
+
+	ret = regmap_read(data->regmap, LTR390_PART_ID, &part_number);
+	if (ret)
+		return dev_err_probe(dev, ret,
+				     "failed to get sensor's part id\n");
+	/* Lower 4 bits of `part_number` change with hardware revisions */
+	if (part_number >> 4 != LTR390_PART_NUMBER_ID)
+		dev_info(dev, "received invalid product id: 0x%x", part_number);
+	dev_dbg(dev, "LTR390, product id: 0x%x\n", part_number);
+
+	/* reset sensor, chip fails to respond to this, so ignore any errors */
+	regmap_set_bits(data->regmap, LTR390_MAIN_CTRL, LTR390_SW_RESET);
+
+	/* Wait for the registers to reset before proceeding */
+	usleep_range(1000, 2000);
+
+	ret = regmap_set_bits(data->regmap, LTR390_MAIN_CTRL,
+			      LTR390_SENSOR_ENABLE | LTR390_UVS_MODE);
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to enable the sensor\n");
+
+	return devm_iio_device_register(dev, indio_dev);
+}
+
+static const struct i2c_device_id ltr390_id[] = {
+	{ "ltr390" },
+	{ /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(i2c, ltr390_id);
+
+static const struct of_device_id ltr390_of_table[] = {
+	{ .compatible = "liteon,ltr390" },
+	{ /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, ltr390_of_table);
+
+static struct i2c_driver ltr390_driver = {
+	.driver = {
+		.name = "ltr390",
+		.of_match_table = ltr390_of_table,
+	},
+	.probe = ltr390_probe,
+	.id_table = ltr390_id,
+};
+module_i2c_driver(ltr390_driver);
+
+MODULE_AUTHOR("Anshul Dalal <anshulusr@gmail.com>");
+MODULE_DESCRIPTION("Lite-On LTR390 ALS and UV sensor Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/iio/light/ltrf216a.c b/drivers/iio/light/ltrf216a.c
index 8de4dd849936..68dc48420a88 100644
--- a/drivers/iio/light/ltrf216a.c
+++ b/drivers/iio/light/ltrf216a.c
@@ -234,7 +234,7 @@ static int ltrf216a_read_data(struct ltrf216a_data *data, u8 addr)
 static int ltrf216a_get_lux(struct ltrf216a_data *data)
 {
 	int ret, greendata;
-	u64 lux, div;
+	u64 lux;
 
 	ret = ltrf216a_set_power_state(data, true);
 	if (ret)
@@ -246,10 +246,9 @@ static int ltrf216a_get_lux(struct ltrf216a_data *data)
 
 	ltrf216a_set_power_state(data, false);
 
-	lux = greendata * 45 * LTRF216A_WIN_FAC * 100;
-	div = data->als_gain_fac * data->int_time_fac * 100;
+	lux = greendata * 45 * LTRF216A_WIN_FAC;
 
-	return div_u64(lux, div);
+	return lux;
 }
 
 static int ltrf216a_read_raw(struct iio_dev *indio_dev,
@@ -279,7 +278,8 @@ static int ltrf216a_read_raw(struct iio_dev *indio_dev,
 		if (ret < 0)
 			return ret;
 		*val = ret;
-		return IIO_VAL_INT;
+		*val2 = data->als_gain_fac * data->int_time_fac;
+		return IIO_VAL_FRACTIONAL;
 	case IIO_CHAN_INFO_INT_TIME:
 		mutex_lock(&data->lock);
 		ret = ltrf216a_get_int_time(data, val, val2);
diff --git a/drivers/iio/light/pa12203001.c b/drivers/iio/light/pa12203001.c
index ed241598aefb..636432c45651 100644
--- a/drivers/iio/light/pa12203001.c
+++ b/drivers/iio/light/pa12203001.c
@@ -472,7 +472,7 @@ static struct i2c_driver pa12203001_driver = {
 	.driver = {
 		.name = PA12203001_DRIVER_NAME,
 		.pm = &pa12203001_pm_ops,
-		.acpi_match_table = ACPI_PTR(pa12203001_acpi_match),
+		.acpi_match_table = pa12203001_acpi_match,
 	},
 	.probe = pa12203001_probe,
 	.remove = pa12203001_remove,
diff --git a/drivers/iio/light/rohm-bu27008.c b/drivers/iio/light/rohm-bu27008.c
index 6a6d77805091..0f010eff1981 100644
--- a/drivers/iio/light/rohm-bu27008.c
+++ b/drivers/iio/light/rohm-bu27008.c
@@ -130,6 +130,7 @@
  * @BU27008_BLUE:	Blue channel. Via data2 (when used).
  * @BU27008_CLEAR:	Clear channel. Via data2 or data3 (when used).
  * @BU27008_IR:		IR channel. Via data3 (when used).
+ * @BU27008_LUX:	Illuminance channel, computed using RGB and IR.
  * @BU27008_NUM_CHANS:	Number of channel types.
  */
 enum bu27008_chan_type {
@@ -138,6 +139,7 @@ enum bu27008_chan_type {
 	BU27008_BLUE,
 	BU27008_CLEAR,
 	BU27008_IR,
+	BU27008_LUX,
 	BU27008_NUM_CHANS
 };
 
@@ -172,6 +174,8 @@ static const unsigned long bu27008_scan_masks[] = {
 	ALWAYS_SCANNABLE | BIT(BU27008_CLEAR) | BIT(BU27008_IR),
 	/* buffer is R, G, B, IR */
 	ALWAYS_SCANNABLE | BIT(BU27008_BLUE) | BIT(BU27008_IR),
+	/* buffer is R, G, B, IR, LUX */
+	ALWAYS_SCANNABLE | BIT(BU27008_BLUE) | BIT(BU27008_IR) | BIT(BU27008_LUX),
 	0
 };
 
@@ -331,6 +335,19 @@ static const struct iio_chan_spec bu27008_channels[] = {
 	 * Hence we don't advertise available ones either.
 	 */
 	BU27008_CHAN(IR, DATA3, 0),
+	{
+		.type = IIO_LIGHT,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+				      BIT(IIO_CHAN_INFO_SCALE),
+		.channel = BU27008_LUX,
+		.scan_index = BU27008_LUX,
+		.scan_type = {
+			.sign = 'u',
+			.realbits = 64,
+			.storagebits = 64,
+			.endianness = IIO_CPU,
+		},
+	},
 	IIO_CHAN_SOFT_TIMESTAMP(BU27008_NUM_CHANS),
 };
 
@@ -1004,6 +1021,169 @@ static int bu27008_read_one(struct bu27008_data *data, struct iio_dev *idev,
 	return ret;
 }
 
+#define BU27008_LUX_DATA_RED	0
+#define BU27008_LUX_DATA_GREEN	1
+#define BU27008_LUX_DATA_BLUE	2
+#define BU27008_LUX_DATA_IR	3
+#define LUX_DATA_SIZE (BU27008_NUM_HW_CHANS * sizeof(__le16))
+
+static int bu27008_read_lux_chans(struct bu27008_data *data, unsigned int time,
+				  __le16 *chan_data)
+{
+	int ret, chan_sel, tmpret, valid;
+
+	chan_sel = BU27008_BLUE2_IR3 << (ffs(data->cd->chan_sel_mask) - 1);
+
+	ret = regmap_update_bits(data->regmap, data->cd->chan_sel_reg,
+				 data->cd->chan_sel_mask, chan_sel);
+	if (ret)
+		return ret;
+
+	ret = bu27008_meas_set(data, true);
+	if (ret)
+		return ret;
+
+	msleep(time / USEC_PER_MSEC);
+
+	ret = regmap_read_poll_timeout(data->regmap, data->cd->valid_reg,
+				       valid, (valid & BU27008_MASK_VALID),
+				       BU27008_VALID_RESULT_WAIT_QUANTA_US,
+				       BU27008_MAX_VALID_RESULT_WAIT_US);
+	if (ret)
+		goto out;
+
+	ret = regmap_bulk_read(data->regmap, BU27008_REG_DATA0_LO, chan_data,
+			       LUX_DATA_SIZE);
+	if (ret)
+		goto out;
+out:
+	tmpret = bu27008_meas_set(data, false);
+	if (tmpret)
+		dev_warn(data->dev, "Stopping measurement failed\n");
+
+	return ret;
+}
+
+/*
+ * Following equation for computing lux out of register values was given by
+ * ROHM HW colleagues;
+ *
+ * Red = RedData*1024 / Gain * 20 / meas_mode
+ * Green = GreenData* 1024 / Gain * 20 / meas_mode
+ * Blue = BlueData* 1024 / Gain * 20 / meas_mode
+ * IR = IrData* 1024 / Gain * 20 / meas_mode
+ *
+ * where meas_mode is the integration time in mS / 10
+ *
+ * IRratio = (IR > 0.18 * Green) ? 0 : 1
+ *
+ * Lx = max(c1*Red + c2*Green + c3*Blue,0)
+ *
+ * for
+ * IRratio 0: c1 = -0.00002237, c2 = 0.0003219, c3 = -0.000120371
+ * IRratio 1: c1 = -0.00001074, c2 = 0.000305415, c3 = -0.000129367
+ */
+
+/*
+ * The max chan data is 0xffff. When we multiply it by 1024 * 20, we'll get
+ * 0x4FFFB000 which still fits in 32-bit integer. This won't overflow.
+ */
+#define NORM_CHAN_DATA_FOR_LX_CALC(chan, gain, time) (le16_to_cpu(chan) * \
+				   1024 * 20 / (gain) / (time))
+static u64 bu27008_calc_nlux(struct bu27008_data *data, __le16 *lux_data,
+		unsigned int gain, unsigned int gain_ir, unsigned int time)
+{
+	unsigned int red, green, blue, ir;
+	s64 c1, c2, c3, nlux;
+
+	time /= 10000;
+	ir = NORM_CHAN_DATA_FOR_LX_CALC(lux_data[BU27008_LUX_DATA_IR], gain_ir, time);
+	red = NORM_CHAN_DATA_FOR_LX_CALC(lux_data[BU27008_LUX_DATA_RED], gain, time);
+	green = NORM_CHAN_DATA_FOR_LX_CALC(lux_data[BU27008_LUX_DATA_GREEN], gain, time);
+	blue = NORM_CHAN_DATA_FOR_LX_CALC(lux_data[BU27008_LUX_DATA_BLUE], gain, time);
+
+	if ((u64)ir * 100LLU > (u64)green * 18LLU) {
+		c1 = -22370;
+		c2 = 321900;
+		c3 = -120371;
+	} else {
+		c1 = -10740;
+		c2 = 305415;
+		c3 = -129367;
+	}
+	nlux = c1 * red + c2 * green + c3 * blue;
+
+	return max_t(s64, 0, nlux);
+}
+
+static int bu27008_get_time_n_gains(struct bu27008_data *data,
+		unsigned int *gain, unsigned int *gain_ir, unsigned int *time)
+{
+	int ret;
+
+	ret = bu27008_get_gain(data, &data->gts, gain);
+	if (ret < 0)
+		return ret;
+
+	ret = bu27008_get_gain(data, &data->gts_ir, gain_ir);
+	if (ret < 0)
+		return ret;
+
+	ret = bu27008_get_int_time_us(data);
+	if (ret < 0)
+		return ret;
+
+	/* Max integration time is 400000. Fits in signed int. */
+	*time = ret;
+
+	return 0;
+}
+
+struct bu27008_buf {
+	__le16 chan[BU27008_NUM_HW_CHANS];
+	u64 lux __aligned(8);
+	s64 ts __aligned(8);
+};
+
+static int bu27008_buffer_fill_lux(struct bu27008_data *data,
+				   struct bu27008_buf *raw)
+{
+	unsigned int gain, gain_ir, time;
+	int ret;
+
+	ret = bu27008_get_time_n_gains(data, &gain, &gain_ir, &time);
+	if (ret)
+		return ret;
+
+	raw->lux = bu27008_calc_nlux(data, raw->chan, gain, gain_ir, time);
+
+	return 0;
+}
+
+static int bu27008_read_lux(struct bu27008_data *data, struct iio_dev *idev,
+			    struct iio_chan_spec const *chan,
+			    int *val, int *val2)
+{
+	__le16 lux_data[BU27008_NUM_HW_CHANS];
+	unsigned int gain, gain_ir, time;
+	u64 nlux;
+	int ret;
+
+	ret = bu27008_get_time_n_gains(data, &gain, &gain_ir, &time);
+	if (ret)
+		return ret;
+
+	ret = bu27008_read_lux_chans(data, time, lux_data);
+	if (ret)
+		return ret;
+
+	nlux = bu27008_calc_nlux(data, lux_data, gain, gain_ir, time);
+	*val = (int)nlux;
+	*val2 = nlux >> 32LLU;
+
+	return IIO_VAL_INT_64;
+}
+
 static int bu27008_read_raw(struct iio_dev *idev,
 			   struct iio_chan_spec const *chan,
 			   int *val, int *val2, long mask)
@@ -1018,7 +1198,10 @@ static int bu27008_read_raw(struct iio_dev *idev,
 			return -EBUSY;
 
 		mutex_lock(&data->mutex);
-		ret = bu27008_read_one(data, idev, chan, val, val2);
+		if (chan->type == IIO_LIGHT)
+			ret = bu27008_read_lux(data, idev, chan, val, val2);
+		else
+			ret = bu27008_read_one(data, idev, chan, val, val2);
 		mutex_unlock(&data->mutex);
 
 		iio_device_release_direct_mode(idev);
@@ -1026,6 +1209,11 @@ static int bu27008_read_raw(struct iio_dev *idev,
 		return ret;
 
 	case IIO_CHAN_INFO_SCALE:
+		if (chan->type == IIO_LIGHT) {
+			*val = 0;
+			*val2 = 1;
+			return IIO_VAL_INT_PLUS_NANO;
+		}
 		ret = bu27008_get_scale(data, chan->scan_index == BU27008_IR,
 					val, val2);
 		if (ret)
@@ -1236,10 +1424,7 @@ static irqreturn_t bu27008_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *idev = pf->indio_dev;
 	struct bu27008_data *data = iio_priv(idev);
-	struct {
-		__le16 chan[BU27008_NUM_HW_CHANS];
-		s64 ts __aligned(8);
-	} raw;
+	struct bu27008_buf raw;
 	int ret, dummy;
 
 	memset(&raw, 0, sizeof(raw));
@@ -1257,6 +1442,12 @@ static irqreturn_t bu27008_trigger_handler(int irq, void *p)
 	if (ret < 0)
 		goto err_read;
 
+	if (test_bit(BU27008_LUX, idev->active_scan_mask)) {
+		ret = bu27008_buffer_fill_lux(data, &raw);
+		if (ret)
+			goto err_read;
+	}
+
 	iio_push_to_buffers_with_timestamp(idev, &raw, pf->timestamp);
 err_read:
 	iio_trigger_notify_done(idev->trig);
diff --git a/drivers/iio/light/veml6075.c b/drivers/iio/light/veml6075.c
new file mode 100644
index 000000000000..05d4c0e9015d
--- /dev/null
+++ b/drivers/iio/light/veml6075.c
@@ -0,0 +1,474 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Vishay VEML6075 UVA and UVB light sensor
+ *
+ * Copyright 2023 Javier Carrasco <javier.carrasco.cruz@gmail.com>
+ *
+ * 7-bit I2C slave, address 0x10
+ */
+
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/regmap.h>
+#include <linux/units.h>
+
+#include <linux/iio/iio.h>
+
+#define VEML6075_CMD_CONF	0x00 /* configuration register */
+#define VEML6075_CMD_UVA	0x07 /* UVA channel */
+#define VEML6075_CMD_UVB	0x09 /* UVB channel */
+#define VEML6075_CMD_COMP1	0x0A /* visible light compensation */
+#define VEML6075_CMD_COMP2	0x0B /* infrarred light compensation */
+#define VEML6075_CMD_ID		0x0C /* device ID */
+
+#define VEML6075_CONF_IT	GENMASK(6, 4) /* intregration time */
+#define VEML6075_CONF_HD	BIT(3) /* dynamic setting */
+#define VEML6075_CONF_TRIG	BIT(2) /* trigger */
+#define VEML6075_CONF_AF	BIT(1) /* active force enable */
+#define VEML6075_CONF_SD	BIT(0) /* shutdown */
+
+#define VEML6075_IT_50_MS	0x00
+#define VEML6075_IT_100_MS	0x01
+#define VEML6075_IT_200_MS	0x02
+#define VEML6075_IT_400_MS	0x03
+#define VEML6075_IT_800_MS	0x04
+
+#define VEML6075_AF_DISABLE	0x00
+#define VEML6075_AF_ENABLE	0x01
+
+#define VEML6075_SD_DISABLE	0x00
+#define VEML6075_SD_ENABLE	0x01
+
+/* Open-air coefficients and responsivity */
+#define VEML6075_A_COEF		2220
+#define VEML6075_B_COEF		1330
+#define VEML6075_C_COEF		2950
+#define VEML6075_D_COEF		1740
+#define VEML6075_UVA_RESP	1461
+#define VEML6075_UVB_RESP	2591
+
+static const int veml6075_it_ms[] = { 50, 100, 200, 400, 800 };
+
+struct veml6075_data {
+	struct i2c_client *client;
+	struct regmap *regmap;
+	/*
+	 * prevent integration time modification and triggering
+	 * measurements while a measurement is underway.
+	 */
+	struct mutex lock;
+};
+
+/* channel number */
+enum veml6075_chan {
+	CH_UVA,
+	CH_UVB,
+};
+
+static const struct iio_chan_spec veml6075_channels[] = {
+	{
+		.type = IIO_INTENSITY,
+		.channel = CH_UVA,
+		.modified = 1,
+		.channel2 = IIO_MOD_LIGHT_UVA,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+			BIT(IIO_CHAN_INFO_SCALE),
+		.info_mask_shared_by_all = BIT(IIO_CHAN_INFO_INT_TIME),
+		.info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_INT_TIME),
+	},
+	{
+		.type = IIO_INTENSITY,
+		.channel = CH_UVB,
+		.modified = 1,
+		.channel2 = IIO_MOD_LIGHT_UVB,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+			BIT(IIO_CHAN_INFO_SCALE),
+		.info_mask_shared_by_all = BIT(IIO_CHAN_INFO_INT_TIME),
+		.info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_INT_TIME),
+	},
+	{
+		.type = IIO_UVINDEX,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED),
+		.info_mask_shared_by_all = BIT(IIO_CHAN_INFO_INT_TIME),
+		.info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_INT_TIME),
+	},
+};
+
+static int veml6075_request_measurement(struct veml6075_data *data)
+{
+	int ret, conf, int_time;
+
+	ret = regmap_read(data->regmap, VEML6075_CMD_CONF, &conf);
+	if (ret < 0)
+		return ret;
+
+	/* disable shutdown and trigger measurement */
+	ret = regmap_write(data->regmap, VEML6075_CMD_CONF,
+			   (conf | VEML6075_CONF_TRIG) & ~VEML6075_CONF_SD);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * A measurement requires between 1.30 and 1.40 times the integration
+	 * time for all possible configurations. Using a 1.50 factor simplifies
+	 * operations and ensures reliability under all circumstances.
+	 */
+	int_time = veml6075_it_ms[FIELD_GET(VEML6075_CONF_IT, conf)];
+	msleep(int_time + (int_time / 2));
+
+	/* shutdown again, data registers are still accessible */
+	return regmap_update_bits(data->regmap, VEML6075_CMD_CONF,
+				  VEML6075_CONF_SD, VEML6075_CONF_SD);
+}
+
+static int veml6075_uva_comp(int raw_uva, int comp1, int comp2)
+{
+	int comp1a_c, comp2a_c, uva_comp;
+
+	comp1a_c = (comp1 * VEML6075_A_COEF) / 1000U;
+	comp2a_c = (comp2 * VEML6075_B_COEF) / 1000U;
+	uva_comp = raw_uva - comp1a_c - comp2a_c;
+
+	return clamp_val(uva_comp, 0, U16_MAX);
+}
+
+static int veml6075_uvb_comp(int raw_uvb, int comp1, int comp2)
+{
+	int comp1b_c, comp2b_c, uvb_comp;
+
+	comp1b_c = (comp1 * VEML6075_C_COEF) / 1000U;
+	comp2b_c = (comp2 * VEML6075_D_COEF) / 1000U;
+	uvb_comp = raw_uvb - comp1b_c - comp2b_c;
+
+	return clamp_val(uvb_comp, 0, U16_MAX);
+}
+
+static int veml6075_read_comp(struct veml6075_data *data, int *c1, int *c2)
+{
+	int ret;
+
+	ret = regmap_read(data->regmap, VEML6075_CMD_COMP1, c1);
+	if (ret < 0)
+		return ret;
+
+	return regmap_read(data->regmap, VEML6075_CMD_COMP2, c2);
+}
+
+static int veml6075_read_uv_direct(struct veml6075_data *data, int chan,
+				   int *val)
+{
+	int c1, c2, ret;
+
+	guard(mutex)(&data->lock);
+
+	ret = veml6075_request_measurement(data);
+	if (ret < 0)
+		return ret;
+
+	ret = veml6075_read_comp(data, &c1, &c2);
+	if (ret < 0)
+		return ret;
+
+	switch (chan) {
+	case CH_UVA:
+		ret = regmap_read(data->regmap, VEML6075_CMD_UVA, val);
+		if (ret < 0)
+			return ret;
+
+		*val = veml6075_uva_comp(*val, c1, c2);
+		return IIO_VAL_INT;
+	case CH_UVB:
+		ret = regmap_read(data->regmap, VEML6075_CMD_UVB, val);
+		if (ret < 0)
+			return ret;
+
+		*val = veml6075_uvb_comp(*val, c1, c2);
+		return IIO_VAL_INT;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int veml6075_read_int_time_index(struct veml6075_data *data)
+{
+	int ret, conf;
+
+	ret = regmap_read(data->regmap, VEML6075_CMD_CONF, &conf);
+	if (ret < 0)
+		return ret;
+
+	return FIELD_GET(VEML6075_CONF_IT, conf);
+}
+
+static int veml6075_read_int_time_ms(struct veml6075_data *data, int *val)
+{
+	int int_index;
+
+	guard(mutex)(&data->lock);
+	int_index = veml6075_read_int_time_index(data);
+	if (int_index < 0)
+		return int_index;
+
+	*val = veml6075_it_ms[int_index];
+
+	return IIO_VAL_INT;
+}
+
+static int veml6075_get_uvi_micro(struct veml6075_data *data, int uva_comp,
+				  int uvb_comp)
+{
+	int uvia_micro = uva_comp * VEML6075_UVA_RESP;
+	int uvib_micro = uvb_comp * VEML6075_UVB_RESP;
+	int int_index;
+
+	int_index = veml6075_read_int_time_index(data);
+	if (int_index < 0)
+		return int_index;
+
+	switch (int_index) {
+	case VEML6075_IT_50_MS:
+		return uvia_micro + uvib_micro;
+	case VEML6075_IT_100_MS:
+	case VEML6075_IT_200_MS:
+	case VEML6075_IT_400_MS:
+	case VEML6075_IT_800_MS:
+		return (uvia_micro + uvib_micro) / (2 << int_index);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int veml6075_read_uvi(struct veml6075_data *data, int *val, int *val2)
+{
+	int ret, c1, c2, uva, uvb, uvi_micro;
+
+	guard(mutex)(&data->lock);
+
+	ret = veml6075_request_measurement(data);
+	if (ret < 0)
+		return ret;
+
+	ret = veml6075_read_comp(data, &c1, &c2);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_read(data->regmap, VEML6075_CMD_UVA, &uva);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_read(data->regmap, VEML6075_CMD_UVB, &uvb);
+	if (ret < 0)
+		return ret;
+
+	uvi_micro = veml6075_get_uvi_micro(data, veml6075_uva_comp(uva, c1, c2),
+					   veml6075_uvb_comp(uvb, c1, c2));
+	if (uvi_micro < 0)
+		return uvi_micro;
+
+	*val = uvi_micro / MICRO;
+	*val2 = uvi_micro % MICRO;
+
+	return IIO_VAL_INT_PLUS_MICRO;
+}
+
+static int veml6075_read_responsivity(int chan, int *val, int *val2)
+{
+	/* scale = 1 / resp */
+	switch (chan) {
+	case CH_UVA:
+		/* resp = 0.93 c/uW/cm2: scale = 1.75268817 */
+		*val = 1;
+		*val2 = 75268817;
+		return IIO_VAL_INT_PLUS_NANO;
+	case CH_UVB:
+		/* resp = 2.1 c/uW/cm2: scale = 0.476190476 */
+		*val = 0;
+		*val2 = 476190476;
+		return IIO_VAL_INT_PLUS_NANO;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int veml6075_read_avail(struct iio_dev *indio_dev,
+			       struct iio_chan_spec const *chan,
+			       const int **vals, int *type, int *length,
+			       long mask)
+{
+	switch (mask) {
+	case IIO_CHAN_INFO_INT_TIME:
+		*length = ARRAY_SIZE(veml6075_it_ms);
+		*vals = veml6075_it_ms;
+		*type = IIO_VAL_INT;
+		return IIO_AVAIL_LIST;
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static int veml6075_read_raw(struct iio_dev *indio_dev,
+			     struct iio_chan_spec const *chan,
+			     int *val, int *val2, long mask)
+{
+	struct veml6075_data *data = iio_priv(indio_dev);
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		return veml6075_read_uv_direct(data, chan->channel, val);
+	case IIO_CHAN_INFO_PROCESSED:
+		return veml6075_read_uvi(data, val, val2);
+	case IIO_CHAN_INFO_INT_TIME:
+		return veml6075_read_int_time_ms(data, val);
+	case IIO_CHAN_INFO_SCALE:
+		return veml6075_read_responsivity(chan->channel, val, val2);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int veml6075_write_int_time_ms(struct veml6075_data *data, int val)
+{
+	int i = ARRAY_SIZE(veml6075_it_ms);
+
+	guard(mutex)(&data->lock);
+
+	while (i-- > 0) {
+		if (val == veml6075_it_ms[i])
+			break;
+	}
+	if (i < 0)
+		return -EINVAL;
+
+	return regmap_update_bits(data->regmap, VEML6075_CMD_CONF,
+				  VEML6075_CONF_IT,
+				  FIELD_PREP(VEML6075_CONF_IT, i));
+}
+
+static int veml6075_write_raw(struct iio_dev *indio_dev,
+			      struct iio_chan_spec const *chan,
+			      int val, int val2, long mask)
+{
+	struct veml6075_data *data = iio_priv(indio_dev);
+
+	switch (mask) {
+	case IIO_CHAN_INFO_INT_TIME:
+		return veml6075_write_int_time_ms(data, val);
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct iio_info veml6075_info = {
+	.read_avail = veml6075_read_avail,
+	.read_raw = veml6075_read_raw,
+	.write_raw = veml6075_write_raw,
+};
+
+static bool veml6075_readable_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case VEML6075_CMD_CONF:
+	case VEML6075_CMD_UVA:
+	case VEML6075_CMD_UVB:
+	case VEML6075_CMD_COMP1:
+	case VEML6075_CMD_COMP2:
+	case VEML6075_CMD_ID:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool veml6075_writable_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case VEML6075_CMD_CONF:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static const struct regmap_config veml6075_regmap_config = {
+	.name = "veml6075",
+	.reg_bits = 8,
+	.val_bits = 16,
+	.max_register = VEML6075_CMD_ID,
+	.readable_reg = veml6075_readable_reg,
+	.writeable_reg = veml6075_writable_reg,
+	.val_format_endian = REGMAP_ENDIAN_LITTLE,
+};
+
+static int veml6075_probe(struct i2c_client *client)
+{
+	struct veml6075_data *data;
+	struct iio_dev *indio_dev;
+	struct regmap *regmap;
+	int config, ret;
+
+	indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*data));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	regmap = devm_regmap_init_i2c(client, &veml6075_regmap_config);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	data = iio_priv(indio_dev);
+	data->client = client;
+	data->regmap = regmap;
+
+	mutex_init(&data->lock);
+
+	indio_dev->name = "veml6075";
+	indio_dev->info = &veml6075_info;
+	indio_dev->channels = veml6075_channels;
+	indio_dev->num_channels = ARRAY_SIZE(veml6075_channels);
+	indio_dev->modes = INDIO_DIRECT_MODE;
+
+	ret = devm_regulator_get_enable(&client->dev, "vdd");
+	if (ret < 0)
+		return ret;
+
+	/* default: 100ms integration time, active force enable, shutdown */
+	config = FIELD_PREP(VEML6075_CONF_IT, VEML6075_IT_100_MS) |
+		FIELD_PREP(VEML6075_CONF_AF, VEML6075_AF_ENABLE) |
+		FIELD_PREP(VEML6075_CONF_SD, VEML6075_SD_ENABLE);
+	ret = regmap_write(data->regmap, VEML6075_CMD_CONF, config);
+	if (ret < 0)
+		return ret;
+
+	return devm_iio_device_register(&client->dev, indio_dev);
+}
+
+static const struct i2c_device_id veml6075_id[] = {
+	{ "veml6075" },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, veml6075_id);
+
+static const struct of_device_id veml6075_of_match[] = {
+	{ .compatible = "vishay,veml6075" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, veml6075_of_match);
+
+static struct i2c_driver veml6075_driver = {
+	.driver = {
+		.name   = "veml6075",
+		.of_match_table = veml6075_of_match,
+	},
+	.probe = veml6075_probe,
+	.id_table = veml6075_id,
+};
+
+module_i2c_driver(veml6075_driver);
+
+MODULE_AUTHOR("Javier Carrasco <javier.carrasco.cruz@gmail.com>");
+MODULE_DESCRIPTION("Vishay VEML6075 UVA and UVB light sensor driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/iio/magnetometer/rm3100-core.c b/drivers/iio/magnetometer/rm3100-core.c
index 69938204456f..42b70cd42b39 100644
--- a/drivers/iio/magnetometer/rm3100-core.c
+++ b/drivers/iio/magnetometer/rm3100-core.c
@@ -530,6 +530,7 @@ int rm3100_common_probe(struct device *dev, struct regmap *regmap, int irq)
 	struct rm3100_data *data;
 	unsigned int tmp;
 	int ret;
+	int samp_rate_index;
 
 	indio_dev = devm_iio_device_alloc(dev, sizeof(*data));
 	if (!indio_dev)
@@ -586,9 +587,14 @@ int rm3100_common_probe(struct device *dev, struct regmap *regmap, int irq)
 	ret = regmap_read(regmap, RM3100_REG_TMRC, &tmp);
 	if (ret < 0)
 		return ret;
+
+	samp_rate_index = tmp - RM3100_TMRC_OFFSET;
+	if (samp_rate_index < 0 || samp_rate_index >=  RM3100_SAMP_NUM) {
+		dev_err(dev, "The value read from RM3100_REG_TMRC is invalid!\n");
+		return -EINVAL;
+	}
 	/* Initializing max wait time, which is double conversion time. */
-	data->conversion_time = rm3100_samp_rates[tmp - RM3100_TMRC_OFFSET][2]
-				* 2;
+	data->conversion_time = rm3100_samp_rates[samp_rate_index][2] * 2;
 
 	/* Cycle count values may not be what we want. */
 	if ((tmp - RM3100_TMRC_OFFSET) == 0)
diff --git a/drivers/iio/magnetometer/tmag5273.c b/drivers/iio/magnetometer/tmag5273.c
index e8c4ca142d21..218b1ce076c1 100644
--- a/drivers/iio/magnetometer/tmag5273.c
+++ b/drivers/iio/magnetometer/tmag5273.c
@@ -497,17 +497,13 @@ static int tmag5273_set_operating_mode(struct tmag5273_data *data,
 static void tmag5273_read_device_property(struct tmag5273_data *data)
 {
 	struct device *dev = data->dev;
-	const char *str;
 	int ret;
 
 	data->angle_measurement = TMAG5273_ANGLE_EN_X_Y;
 
-	ret = device_property_read_string(dev, "ti,angle-measurement", &str);
-	if (ret)
-		return;
-
-	ret = match_string(tmag5273_angle_names,
-			   ARRAY_SIZE(tmag5273_angle_names), str);
+	ret = device_property_match_property_string(dev, "ti,angle-measurement",
+						    tmag5273_angle_names,
+						    ARRAY_SIZE(tmag5273_angle_names));
 	if (ret >= 0)
 		data->angle_measurement = ret;
 }
diff --git a/drivers/iio/pressure/Kconfig b/drivers/iio/pressure/Kconfig
index 95efa32e4289..79adfd059c3a 100644
--- a/drivers/iio/pressure/Kconfig
+++ b/drivers/iio/pressure/Kconfig
@@ -109,6 +109,28 @@ config HP03
 	  To compile this driver as a module, choose M here: the module
 	  will be called hp03.
 
+config HSC030PA
+	tristate "Honeywell HSC/SSC TruStability pressure sensor series"
+	depends on (I2C || SPI_MASTER)
+	select HSC030PA_I2C if I2C
+	select HSC030PA_SPI if SPI_MASTER
+	help
+	  Say Y here to build support for the Honeywell TruStability
+	  HSC and SSC pressure and temperature sensor series.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called hsc030pa.
+
+config HSC030PA_I2C
+	tristate
+	depends on HSC030PA
+	depends on I2C
+
+config HSC030PA_SPI
+	tristate
+	depends on HSC030PA
+	depends on SPI_MASTER
+
 config ICP10100
 	tristate "InvenSense ICP-101xx pressure and temperature sensor"
 	depends on I2C
diff --git a/drivers/iio/pressure/Makefile b/drivers/iio/pressure/Makefile
index 436aec7e65f3..b0f8b94662f2 100644
--- a/drivers/iio/pressure/Makefile
+++ b/drivers/iio/pressure/Makefile
@@ -15,6 +15,9 @@ obj-$(CONFIG_DPS310) += dps310.o
 obj-$(CONFIG_IIO_CROS_EC_BARO) += cros_ec_baro.o
 obj-$(CONFIG_HID_SENSOR_PRESS)   += hid-sensor-press.o
 obj-$(CONFIG_HP03) += hp03.o
+obj-$(CONFIG_HSC030PA) += hsc030pa.o
+obj-$(CONFIG_HSC030PA_I2C) += hsc030pa_i2c.o
+obj-$(CONFIG_HSC030PA_SPI) += hsc030pa_spi.o
 obj-$(CONFIG_ICP10100) += icp10100.o
 obj-$(CONFIG_MPL115) += mpl115.o
 obj-$(CONFIG_MPL115_I2C) += mpl115_i2c.o
diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c
index a2ef1373a274..fe8734468ed3 100644
--- a/drivers/iio/pressure/bmp280-core.c
+++ b/drivers/iio/pressure/bmp280-core.c
@@ -13,6 +13,7 @@
  * https://www.bosch-sensortec.com/media/boschsensortec/downloads/datasheets/bst-bmp280-ds001.pdf
  * https://www.bosch-sensortec.com/media/boschsensortec/downloads/datasheets/bst-bme280-ds002.pdf
  * https://www.bosch-sensortec.com/media/boschsensortec/downloads/datasheets/bst-bmp388-ds001.pdf
+ * https://www.bosch-sensortec.com/media/boschsensortec/downloads/datasheets/bst-bmp390-ds002.pdf
  * https://www.bosch-sensortec.com/media/boschsensortec/downloads/datasheets/bst-bmp581-ds004.pdf
  *
  * Notice:
@@ -794,10 +795,12 @@ static int bmp280_chip_config(struct bmp280_data *data)
 }
 
 static const int bmp280_oversampling_avail[] = { 1, 2, 4, 8, 16 };
+static const u8 bmp280_chip_ids[] = { BMP280_CHIP_ID };
 
 const struct bmp280_chip_info bmp280_chip_info = {
 	.id_reg = BMP280_REG_ID,
-	.chip_id = BMP280_CHIP_ID,
+	.chip_id = bmp280_chip_ids,
+	.num_chip_id = ARRAY_SIZE(bmp280_chip_ids),
 	.regmap_config = &bmp280_regmap_config,
 	.start_up_time = 2000,
 	.channels = bmp280_channels,
@@ -846,9 +849,12 @@ static int bme280_chip_config(struct bmp280_data *data)
 	return bmp280_chip_config(data);
 }
 
+static const u8 bme280_chip_ids[] = { BME280_CHIP_ID };
+
 const struct bmp280_chip_info bme280_chip_info = {
 	.id_reg = BMP280_REG_ID,
-	.chip_id = BME280_CHIP_ID,
+	.chip_id = bme280_chip_ids,
+	.num_chip_id = ARRAY_SIZE(bme280_chip_ids),
 	.regmap_config = &bmp280_regmap_config,
 	.start_up_time = 2000,
 	.channels = bmp280_channels,
@@ -920,7 +926,7 @@ static int bmp380_cmd(struct bmp280_data *data, u8 cmd)
 }
 
 /*
- * Returns temperature in Celsius dregrees, resolution is 0.01º C. Output value of
+ * Returns temperature in Celsius degrees, resolution is 0.01º C. Output value of
  * "5123" equals 51.2º C. t_fine carries fine temperature as global value.
  *
  * Taken from datasheet, Section Appendix 9, "Compensation formula" and repo
@@ -1220,10 +1226,12 @@ static int bmp380_chip_config(struct bmp280_data *data)
 
 static const int bmp380_oversampling_avail[] = { 1, 2, 4, 8, 16, 32 };
 static const int bmp380_iir_filter_coeffs_avail[] = { 1, 2, 4, 8, 16, 32, 64, 128};
+static const u8 bmp380_chip_ids[] = { BMP380_CHIP_ID, BMP390_CHIP_ID };
 
 const struct bmp280_chip_info bmp380_chip_info = {
 	.id_reg = BMP380_REG_ID,
-	.chip_id = BMP380_CHIP_ID,
+	.chip_id = bmp380_chip_ids,
+	.num_chip_id = ARRAY_SIZE(bmp380_chip_ids),
 	.regmap_config = &bmp380_regmap_config,
 	.start_up_time = 2000,
 	.channels = bmp380_channels,
@@ -1385,7 +1393,7 @@ static int bmp580_read_temp(struct bmp280_data *data, int *val, int *val2)
 
 	/*
 	 * Temperature is returned in Celsius degrees in fractional
-	 * form down 2^16. We reescale by x1000 to return milli Celsius
+	 * form down 2^16. We rescale by x1000 to return milli Celsius
 	 * to respect IIO ABI.
 	 */
 	*val = raw_temp * 1000;
@@ -1412,7 +1420,7 @@ static int bmp580_read_press(struct bmp280_data *data, int *val, int *val2)
 	}
 	/*
 	 * Pressure is returned in Pascals in fractional form down 2^16.
-	 * We reescale /1000 to convert to kilopascal to respect IIO ABI.
+	 * We rescale /1000 to convert to kilopascal to respect IIO ABI.
 	 */
 	*val = raw_press;
 	*val2 = 64000; /* 2^6 * 1000 */
@@ -1720,10 +1728,12 @@ static int bmp580_chip_config(struct bmp280_data *data)
 }
 
 static const int bmp580_oversampling_avail[] = { 1, 2, 4, 8, 16, 32, 64, 128 };
+static const u8 bmp580_chip_ids[] = { BMP580_CHIP_ID, BMP580_CHIP_ID_ALT };
 
 const struct bmp280_chip_info bmp580_chip_info = {
 	.id_reg = BMP580_REG_CHIP_ID,
-	.chip_id = BMP580_CHIP_ID,
+	.chip_id = bmp580_chip_ids,
+	.num_chip_id = ARRAY_SIZE(bmp580_chip_ids),
 	.regmap_config = &bmp580_regmap_config,
 	.start_up_time = 2000,
 	.channels = bmp380_channels,
@@ -1983,10 +1993,12 @@ static int bmp180_chip_config(struct bmp280_data *data)
 
 static const int bmp180_oversampling_temp_avail[] = { 1 };
 static const int bmp180_oversampling_press_avail[] = { 1, 2, 4, 8 };
+static const u8 bmp180_chip_ids[] = { BMP180_CHIP_ID };
 
 const struct bmp280_chip_info bmp180_chip_info = {
 	.id_reg = BMP280_REG_ID,
-	.chip_id = BMP180_CHIP_ID,
+	.chip_id = bmp180_chip_ids,
+	.num_chip_id = ARRAY_SIZE(bmp180_chip_ids),
 	.regmap_config = &bmp180_regmap_config,
 	.start_up_time = 2000,
 	.channels = bmp280_channels,
@@ -2077,6 +2089,7 @@ int bmp280_common_probe(struct device *dev,
 	struct bmp280_data *data;
 	struct gpio_desc *gpiod;
 	unsigned int chip_id;
+	unsigned int i;
 	int ret;
 
 	indio_dev = devm_iio_device_alloc(dev, sizeof(*data));
@@ -2142,12 +2155,17 @@ int bmp280_common_probe(struct device *dev,
 	ret = regmap_read(regmap, data->chip_info->id_reg, &chip_id);
 	if (ret < 0)
 		return ret;
-	if (chip_id != data->chip_info->chip_id) {
-		dev_err(dev, "bad chip id: expected %x got %x\n",
-			data->chip_info->chip_id, chip_id);
-		return -EINVAL;
+
+	for (i = 0; i < data->chip_info->num_chip_id; i++) {
+		if (chip_id == data->chip_info->chip_id[i]) {
+			dev_info(dev, "0x%x is a known chip id for %s\n", chip_id, name);
+			break;
+		}
 	}
 
+	if (i == data->chip_info->num_chip_id)
+		dev_warn(dev, "bad chip id: 0x%x is not a known chip id\n", chip_id);
+
 	if (data->chip_info->preinit) {
 		ret = data->chip_info->preinit(data);
 		if (ret)
diff --git a/drivers/iio/pressure/bmp280-i2c.c b/drivers/iio/pressure/bmp280-i2c.c
index dbe630ad05b5..34e3bc758493 100644
--- a/drivers/iio/pressure/bmp280-i2c.c
+++ b/drivers/iio/pressure/bmp280-i2c.c
@@ -7,13 +7,11 @@
 
 static int bmp280_i2c_probe(struct i2c_client *client)
 {
-	struct regmap *regmap;
-	const struct bmp280_chip_info *chip_info;
 	const struct i2c_device_id *id = i2c_client_get_device_id(client);
+	const struct bmp280_chip_info *chip_info;
+	struct regmap *regmap;
 
-	chip_info = device_get_match_data(&client->dev);
-	if (!chip_info)
-		chip_info = (const struct bmp280_chip_info *) id->driver_data;
+	chip_info = i2c_get_match_data(client);
 
 	regmap = devm_regmap_init_i2c(client, chip_info->regmap_config);
 	if (IS_ERR(regmap)) {
diff --git a/drivers/iio/pressure/bmp280-spi.c b/drivers/iio/pressure/bmp280-spi.c
index 1dff9bb7c4e9..a444d4b2978b 100644
--- a/drivers/iio/pressure/bmp280-spi.c
+++ b/drivers/iio/pressure/bmp280-spi.c
@@ -4,6 +4,7 @@
  *
  * Inspired by the older BMP085 driver drivers/misc/bmp085-spi.c
  */
+#include <linux/bits.h>
 #include <linux/module.h>
 #include <linux/spi/spi.h>
 #include <linux/err.h>
@@ -14,8 +15,7 @@
 static int bmp280_regmap_spi_write(void *context, const void *data,
                                    size_t count)
 {
-	struct device *dev = context;
-	struct spi_device *spi = to_spi_device(dev);
+	struct spi_device *spi = to_spi_device(context);
 	u8 buf[2];
 
 	memcpy(buf, data, 2);
@@ -31,12 +31,39 @@ static int bmp280_regmap_spi_write(void *context, const void *data,
 static int bmp280_regmap_spi_read(void *context, const void *reg,
                                   size_t reg_size, void *val, size_t val_size)
 {
-	struct device *dev = context;
-	struct spi_device *spi = to_spi_device(dev);
+	struct spi_device *spi = to_spi_device(context);
 
 	return spi_write_then_read(spi, reg, reg_size, val, val_size);
 }
 
+static int bmp380_regmap_spi_read(void *context, const void *reg,
+				  size_t reg_size, void *val, size_t val_size)
+{
+	struct spi_device *spi = to_spi_device(context);
+	u8 rx_buf[4];
+	ssize_t status;
+
+	/*
+	 * Maximum number of consecutive bytes read for a temperature or
+	 * pressure measurement is 3.
+	 */
+	if (val_size > 3)
+		return -EINVAL;
+
+	/*
+	 * According to the BMP3xx datasheets, for a basic SPI read opertion,
+	 * the first byte needs to be dropped and the rest are the requested
+	 * data.
+	 */
+	status = spi_write_then_read(spi, reg, 1, rx_buf, val_size + 1);
+	if (status)
+		return status;
+
+	memcpy(val, rx_buf + 1, val_size);
+
+	return 0;
+}
+
 static struct regmap_bus bmp280_regmap_bus = {
 	.write = bmp280_regmap_spi_write,
 	.read = bmp280_regmap_spi_read,
@@ -44,10 +71,19 @@ static struct regmap_bus bmp280_regmap_bus = {
 	.val_format_endian_default = REGMAP_ENDIAN_BIG,
 };
 
+static struct regmap_bus bmp380_regmap_bus = {
+	.write = bmp280_regmap_spi_write,
+	.read = bmp380_regmap_spi_read,
+	.read_flag_mask = BIT(7),
+	.reg_format_endian_default = REGMAP_ENDIAN_BIG,
+	.val_format_endian_default = REGMAP_ENDIAN_BIG,
+};
+
 static int bmp280_spi_probe(struct spi_device *spi)
 {
 	const struct spi_device_id *id = spi_get_device_id(spi);
 	const struct bmp280_chip_info *chip_info;
+	struct regmap_bus *bmp_regmap_bus;
 	struct regmap *regmap;
 	int ret;
 
@@ -58,12 +94,20 @@ static int bmp280_spi_probe(struct spi_device *spi)
 		return ret;
 	}
 
-	chip_info = device_get_match_data(&spi->dev);
-	if (!chip_info)
-		chip_info = (const struct bmp280_chip_info *) id->driver_data;
+	chip_info = spi_get_device_match_data(spi);
+
+	switch (chip_info->chip_id[0]) {
+	case BMP380_CHIP_ID:
+	case BMP390_CHIP_ID:
+		bmp_regmap_bus = &bmp380_regmap_bus;
+		break;
+	default:
+		bmp_regmap_bus = &bmp280_regmap_bus;
+		break;
+	}
 
 	regmap = devm_regmap_init(&spi->dev,
-				  &bmp280_regmap_bus,
+				  bmp_regmap_bus,
 				  &spi->dev,
 				  chip_info->regmap_config);
 	if (IS_ERR(regmap)) {
@@ -91,6 +135,7 @@ static const struct of_device_id bmp280_of_spi_match[] = {
 MODULE_DEVICE_TABLE(of, bmp280_of_spi_match);
 
 static const struct spi_device_id bmp280_spi_id[] = {
+	{ "bmp085", (kernel_ulong_t)&bmp180_chip_info },
 	{ "bmp180", (kernel_ulong_t)&bmp180_chip_info },
 	{ "bmp181", (kernel_ulong_t)&bmp180_chip_info },
 	{ "bmp280", (kernel_ulong_t)&bmp280_chip_info },
diff --git a/drivers/iio/pressure/bmp280.h b/drivers/iio/pressure/bmp280.h
index 5c0563ce7572..4012387d7956 100644
--- a/drivers/iio/pressure/bmp280.h
+++ b/drivers/iio/pressure/bmp280.h
@@ -292,6 +292,7 @@
 #define BMP580_CHIP_ID_ALT		0x51
 #define BMP180_CHIP_ID			0x55
 #define BMP280_CHIP_ID			0x58
+#define BMP390_CHIP_ID			0x60
 #define BME280_CHIP_ID			0x60
 #define BMP280_SOFT_RESET_VAL		0xB6
 
@@ -410,7 +411,7 @@ struct bmp280_data {
 		__le16 bmp280_cal_buf[BMP280_CONTIGUOUS_CALIB_REGS / 2];
 		__be16 bmp180_cal_buf[BMP180_REG_CALIB_COUNT / 2];
 		u8 bmp380_cal_buf[BMP380_CALIB_REG_COUNT];
-		/* Miscellaneous, endianess-aware data buffers */
+		/* Miscellaneous, endianness-aware data buffers */
 		__le16 le16;
 		__be16 be16;
 	} __aligned(IIO_DMA_MINALIGN);
@@ -418,7 +419,8 @@ struct bmp280_data {
 
 struct bmp280_chip_info {
 	unsigned int id_reg;
-	const unsigned int chip_id;
+	const u8 *chip_id;
+	int num_chip_id;
 
 	const struct regmap_config *regmap_config;
 
diff --git a/drivers/iio/pressure/dlhl60d.c b/drivers/iio/pressure/dlhl60d.c
index 28c8269ba65d..0bba4c5a8d40 100644
--- a/drivers/iio/pressure/dlhl60d.c
+++ b/drivers/iio/pressure/dlhl60d.c
@@ -250,18 +250,17 @@ static irqreturn_t dlh_trigger_handler(int irq, void *private)
 	struct dlh_state *st = iio_priv(indio_dev);
 	int ret;
 	unsigned int chn, i = 0;
-	__be32 tmp_buf[2];
+	__be32 tmp_buf[2] = { };
 
 	ret = dlh_start_capture_and_read(st);
 	if (ret)
 		goto out;
 
 	for_each_set_bit(chn, indio_dev->active_scan_mask,
-		indio_dev->masklength) {
-		memcpy(tmp_buf + i,
+			 indio_dev->masklength) {
+		memcpy(&tmp_buf[i++],
 			&st->rx_buf[1] + chn * DLH_NUM_DATA_BYTES,
 			DLH_NUM_DATA_BYTES);
-		i++;
 	}
 
 	iio_push_to_buffers(indio_dev, tmp_buf);
diff --git a/drivers/iio/pressure/hsc030pa.c b/drivers/iio/pressure/hsc030pa.c
new file mode 100644
index 000000000000..d6a51f0c335f
--- /dev/null
+++ b/drivers/iio/pressure/hsc030pa.c
@@ -0,0 +1,494 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Honeywell TruStability HSC Series pressure/temperature sensor
+ *
+ * Copyright (c) 2023 Petre Rodan <petre.rodan@subdimension.ro>
+ *
+ * Datasheet: https://prod-edam.honeywell.com/content/dam/honeywell-edam/sps/siot/en-us/products/sensors/pressure-sensors/board-mount-pressure-sensors/trustability-hsc-series/documents/sps-siot-trustability-hsc-series-high-accuracy-board-mount-pressure-sensors-50099148-a-en-ciid-151133.pdf
+ */
+
+#include <linux/array_size.h>
+#include <linux/bitfield.h>
+#include <linux/bits.h>
+#include <linux/cleanup.h>
+#include <linux/init.h>
+#include <linux/math64.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+#include <linux/property.h>
+#include <linux/regulator/consumer.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/units.h>
+
+#include <linux/iio/iio.h>
+#include <linux/iio/sysfs.h>
+
+#include <asm/unaligned.h>
+
+#include "hsc030pa.h"
+
+/*
+ * HSC_PRESSURE_TRIPLET_LEN - length for the string that defines the
+ * pressure range, measurement unit and type as per the part nomenclature.
+ * Consult honeywell,pressure-triplet in the bindings file for details.
+ */
+#define HSC_PRESSURE_TRIPLET_LEN 6
+#define HSC_STATUS_MASK          GENMASK(7, 6)
+#define HSC_TEMPERATURE_MASK     GENMASK(15, 5)
+#define HSC_PRESSURE_MASK        GENMASK(29, 16)
+
+struct hsc_func_spec {
+	u32 output_min;
+	u32 output_max;
+};
+
+/*
+ * function A: 10% - 90% of 2^14
+ * function B:  5% - 95% of 2^14
+ * function C:  5% - 85% of 2^14
+ * function F:  4% - 94% of 2^14
+ */
+static const struct hsc_func_spec hsc_func_spec[] = {
+	[HSC_FUNCTION_A] = { .output_min = 1638, .output_max = 14746 },
+	[HSC_FUNCTION_B] = { .output_min =  819, .output_max = 15565 },
+	[HSC_FUNCTION_C] = { .output_min =  819, .output_max = 13926 },
+	[HSC_FUNCTION_F] = { .output_min =  655, .output_max = 15401 },
+};
+
+enum hsc_variants {
+	HSC001BA = 0x00, HSC1_6BA = 0x01, HSC2_5BA = 0x02, HSC004BA = 0x03,
+	HSC006BA = 0x04, HSC010BA = 0x05, HSC1_6MD = 0x06, HSC2_5MD = 0x07,
+	HSC004MD = 0x08, HSC006MD = 0x09, HSC010MD = 0x0a, HSC016MD = 0x0b,
+	HSC025MD = 0x0c, HSC040MD = 0x0d, HSC060MD = 0x0e, HSC100MD = 0x0f,
+	HSC160MD = 0x10, HSC250MD = 0x11, HSC400MD = 0x12, HSC600MD = 0x13,
+	HSC001BD = 0x14, HSC1_6BD = 0x15, HSC2_5BD = 0x16, HSC004BD = 0x17,
+	HSC2_5MG = 0x18, HSC004MG = 0x19, HSC006MG = 0x1a, HSC010MG = 0x1b,
+	HSC016MG = 0x1c, HSC025MG = 0x1d, HSC040MG = 0x1e, HSC060MG = 0x1f,
+	HSC100MG = 0x20, HSC160MG = 0x21, HSC250MG = 0x22, HSC400MG = 0x23,
+	HSC600MG = 0x24, HSC001BG = 0x25, HSC1_6BG = 0x26, HSC2_5BG = 0x27,
+	HSC004BG = 0x28, HSC006BG = 0x29, HSC010BG = 0x2a, HSC100KA = 0x2b,
+	HSC160KA = 0x2c, HSC250KA = 0x2d, HSC400KA = 0x2e, HSC600KA = 0x2f,
+	HSC001GA = 0x30, HSC160LD = 0x31, HSC250LD = 0x32, HSC400LD = 0x33,
+	HSC600LD = 0x34, HSC001KD = 0x35, HSC1_6KD = 0x36, HSC2_5KD = 0x37,
+	HSC004KD = 0x38, HSC006KD = 0x39, HSC010KD = 0x3a, HSC016KD = 0x3b,
+	HSC025KD = 0x3c, HSC040KD = 0x3d, HSC060KD = 0x3e, HSC100KD = 0x3f,
+	HSC160KD = 0x40, HSC250KD = 0x41, HSC400KD = 0x42, HSC250LG = 0x43,
+	HSC400LG = 0x44, HSC600LG = 0x45, HSC001KG = 0x46, HSC1_6KG = 0x47,
+	HSC2_5KG = 0x48, HSC004KG = 0x49, HSC006KG = 0x4a, HSC010KG = 0x4b,
+	HSC016KG = 0x4c, HSC025KG = 0x4d, HSC040KG = 0x4e, HSC060KG = 0x4f,
+	HSC100KG = 0x50, HSC160KG = 0x51, HSC250KG = 0x52, HSC400KG = 0x53,
+	HSC600KG = 0x54, HSC001GG = 0x55, HSC015PA = 0x56, HSC030PA = 0x57,
+	HSC060PA = 0x58, HSC100PA = 0x59, HSC150PA = 0x5a, HSC0_5ND = 0x5b,
+	HSC001ND = 0x5c, HSC002ND = 0x5d, HSC004ND = 0x5e, HSC005ND = 0x5f,
+	HSC010ND = 0x60, HSC020ND = 0x61, HSC030ND = 0x62, HSC001PD = 0x63,
+	HSC005PD = 0x64, HSC015PD = 0x65, HSC030PD = 0x66, HSC060PD = 0x67,
+	HSC001NG = 0x68, HSC002NG = 0x69, HSC004NG = 0x6a, HSC005NG = 0x6b,
+	HSC010NG = 0x6c, HSC020NG = 0x6d, HSC030NG = 0x6e, HSC001PG = 0x6f,
+	HSC005PG = 0x70, HSC015PG = 0x71, HSC030PG = 0x72, HSC060PG = 0x73,
+	HSC100PG = 0x74, HSC150PG = 0x75, HSC_VARIANTS_MAX
+};
+
+static const char * const hsc_triplet_variants[HSC_VARIANTS_MAX] = {
+	[HSC001BA] = "001BA", [HSC1_6BA] = "1.6BA", [HSC2_5BA] = "2.5BA",
+	[HSC004BA] = "004BA", [HSC006BA] = "006BA", [HSC010BA] = "010BA",
+	[HSC1_6MD] = "1.6MD", [HSC2_5MD] = "2.5MD", [HSC004MD] = "004MD",
+	[HSC006MD] = "006MD", [HSC010MD] = "010MD", [HSC016MD] = "016MD",
+	[HSC025MD] = "025MD", [HSC040MD] = "040MD", [HSC060MD] = "060MD",
+	[HSC100MD] = "100MD", [HSC160MD] = "160MD", [HSC250MD] = "250MD",
+	[HSC400MD] = "400MD", [HSC600MD] = "600MD", [HSC001BD] = "001BD",
+	[HSC1_6BD] = "1.6BD", [HSC2_5BD] = "2.5BD", [HSC004BD] = "004BD",
+	[HSC2_5MG] = "2.5MG", [HSC004MG] = "004MG", [HSC006MG] = "006MG",
+	[HSC010MG] = "010MG", [HSC016MG] = "016MG", [HSC025MG] = "025MG",
+	[HSC040MG] = "040MG", [HSC060MG] = "060MG", [HSC100MG] = "100MG",
+	[HSC160MG] = "160MG", [HSC250MG] = "250MG", [HSC400MG] = "400MG",
+	[HSC600MG] = "600MG", [HSC001BG] = "001BG", [HSC1_6BG] = "1.6BG",
+	[HSC2_5BG] = "2.5BG", [HSC004BG] = "004BG", [HSC006BG] = "006BG",
+	[HSC010BG] = "010BG", [HSC100KA] = "100KA", [HSC160KA] = "160KA",
+	[HSC250KA] = "250KA", [HSC400KA] = "400KA", [HSC600KA] = "600KA",
+	[HSC001GA] = "001GA", [HSC160LD] = "160LD", [HSC250LD] = "250LD",
+	[HSC400LD] = "400LD", [HSC600LD] = "600LD", [HSC001KD] = "001KD",
+	[HSC1_6KD] = "1.6KD", [HSC2_5KD] = "2.5KD", [HSC004KD] = "004KD",
+	[HSC006KD] = "006KD", [HSC010KD] = "010KD", [HSC016KD] = "016KD",
+	[HSC025KD] = "025KD", [HSC040KD] = "040KD", [HSC060KD] = "060KD",
+	[HSC100KD] = "100KD", [HSC160KD] = "160KD", [HSC250KD] = "250KD",
+	[HSC400KD] = "400KD", [HSC250LG] = "250LG", [HSC400LG] = "400LG",
+	[HSC600LG] = "600LG", [HSC001KG] = "001KG", [HSC1_6KG] = "1.6KG",
+	[HSC2_5KG] = "2.5KG", [HSC004KG] = "004KG", [HSC006KG] = "006KG",
+	[HSC010KG] = "010KG", [HSC016KG] = "016KG", [HSC025KG] = "025KG",
+	[HSC040KG] = "040KG", [HSC060KG] = "060KG", [HSC100KG] = "100KG",
+	[HSC160KG] = "160KG", [HSC250KG] = "250KG", [HSC400KG] = "400KG",
+	[HSC600KG] = "600KG", [HSC001GG] = "001GG", [HSC015PA] = "015PA",
+	[HSC030PA] = "030PA", [HSC060PA] = "060PA", [HSC100PA] = "100PA",
+	[HSC150PA] = "150PA", [HSC0_5ND] = "0.5ND", [HSC001ND] = "001ND",
+	[HSC002ND] = "002ND", [HSC004ND] = "004ND", [HSC005ND] = "005ND",
+	[HSC010ND] = "010ND", [HSC020ND] = "020ND", [HSC030ND] = "030ND",
+	[HSC001PD] = "001PD", [HSC005PD] = "005PD", [HSC015PD] = "015PD",
+	[HSC030PD] = "030PD", [HSC060PD] = "060PD", [HSC001NG] = "001NG",
+	[HSC002NG] = "002NG", [HSC004NG] = "004NG", [HSC005NG] = "005NG",
+	[HSC010NG] = "010NG", [HSC020NG] = "020NG", [HSC030NG] = "030NG",
+	[HSC001PG] = "001PG", [HSC005PG] = "005PG", [HSC015PG] = "015PG",
+	[HSC030PG] = "030PG", [HSC060PG] = "060PG", [HSC100PG] = "100PG",
+	[HSC150PG] = "150PG",
+};
+
+/**
+ * struct hsc_range_config - list of pressure ranges based on nomenclature
+ * @pmin: lowest pressure that can be measured
+ * @pmax: highest pressure that can be measured
+ */
+struct hsc_range_config {
+	const s32 pmin;
+	const s32 pmax;
+};
+
+/* All min max limits have been converted to pascals */
+static const struct hsc_range_config hsc_range_config[HSC_VARIANTS_MAX] = {
+	[HSC001BA] = { .pmin =       0, .pmax =  100000 },
+	[HSC1_6BA] = { .pmin =       0, .pmax =  160000 },
+	[HSC2_5BA] = { .pmin =       0, .pmax =  250000 },
+	[HSC004BA] = { .pmin =       0, .pmax =  400000 },
+	[HSC006BA] = { .pmin =       0, .pmax =  600000 },
+	[HSC010BA] = { .pmin =       0, .pmax = 1000000 },
+	[HSC1_6MD] = { .pmin =    -160, .pmax =     160 },
+	[HSC2_5MD] = { .pmin =    -250, .pmax =     250 },
+	[HSC004MD] = { .pmin =    -400, .pmax =     400 },
+	[HSC006MD] = { .pmin =    -600, .pmax =     600 },
+	[HSC010MD] = { .pmin =   -1000, .pmax =    1000 },
+	[HSC016MD] = { .pmin =   -1600, .pmax =    1600 },
+	[HSC025MD] = { .pmin =   -2500, .pmax =    2500 },
+	[HSC040MD] = { .pmin =   -4000, .pmax =    4000 },
+	[HSC060MD] = { .pmin =   -6000, .pmax =    6000 },
+	[HSC100MD] = { .pmin =  -10000, .pmax =   10000 },
+	[HSC160MD] = { .pmin =  -16000, .pmax =   16000 },
+	[HSC250MD] = { .pmin =  -25000, .pmax =   25000 },
+	[HSC400MD] = { .pmin =  -40000, .pmax =   40000 },
+	[HSC600MD] = { .pmin =  -60000, .pmax =   60000 },
+	[HSC001BD] = { .pmin = -100000, .pmax =  100000 },
+	[HSC1_6BD] = { .pmin = -160000, .pmax =  160000 },
+	[HSC2_5BD] = { .pmin = -250000, .pmax =  250000 },
+	[HSC004BD] = { .pmin = -400000, .pmax =  400000 },
+	[HSC2_5MG] = { .pmin =       0, .pmax =     250 },
+	[HSC004MG] = { .pmin =       0, .pmax =     400 },
+	[HSC006MG] = { .pmin =       0, .pmax =     600 },
+	[HSC010MG] = { .pmin =       0, .pmax =    1000 },
+	[HSC016MG] = { .pmin =       0, .pmax =    1600 },
+	[HSC025MG] = { .pmin =       0, .pmax =    2500 },
+	[HSC040MG] = { .pmin =       0, .pmax =    4000 },
+	[HSC060MG] = { .pmin =       0, .pmax =    6000 },
+	[HSC100MG] = { .pmin =       0, .pmax =   10000 },
+	[HSC160MG] = { .pmin =       0, .pmax =   16000 },
+	[HSC250MG] = { .pmin =       0, .pmax =   25000 },
+	[HSC400MG] = { .pmin =       0, .pmax =   40000 },
+	[HSC600MG] = { .pmin =       0, .pmax =   60000 },
+	[HSC001BG] = { .pmin =       0, .pmax =  100000 },
+	[HSC1_6BG] = { .pmin =       0, .pmax =  160000 },
+	[HSC2_5BG] = { .pmin =       0, .pmax =  250000 },
+	[HSC004BG] = { .pmin =       0, .pmax =  400000 },
+	[HSC006BG] = { .pmin =       0, .pmax =  600000 },
+	[HSC010BG] = { .pmin =       0, .pmax = 1000000 },
+	[HSC100KA] = { .pmin =       0, .pmax =  100000 },
+	[HSC160KA] = { .pmin =       0, .pmax =  160000 },
+	[HSC250KA] = { .pmin =       0, .pmax =  250000 },
+	[HSC400KA] = { .pmin =       0, .pmax =  400000 },
+	[HSC600KA] = { .pmin =       0, .pmax =  600000 },
+	[HSC001GA] = { .pmin =       0, .pmax = 1000000 },
+	[HSC160LD] = { .pmin =    -160, .pmax =     160 },
+	[HSC250LD] = { .pmin =    -250, .pmax =     250 },
+	[HSC400LD] = { .pmin =    -400, .pmax =     400 },
+	[HSC600LD] = { .pmin =    -600, .pmax =     600 },
+	[HSC001KD] = { .pmin =   -1000, .pmax =    1000 },
+	[HSC1_6KD] = { .pmin =   -1600, .pmax =    1600 },
+	[HSC2_5KD] = { .pmin =   -2500, .pmax =    2500 },
+	[HSC004KD] = { .pmin =   -4000, .pmax =    4000 },
+	[HSC006KD] = { .pmin =   -6000, .pmax =    6000 },
+	[HSC010KD] = { .pmin =  -10000, .pmax =   10000 },
+	[HSC016KD] = { .pmin =  -16000, .pmax =   16000 },
+	[HSC025KD] = { .pmin =  -25000, .pmax =   25000 },
+	[HSC040KD] = { .pmin =  -40000, .pmax =   40000 },
+	[HSC060KD] = { .pmin =  -60000, .pmax =   60000 },
+	[HSC100KD] = { .pmin = -100000, .pmax =  100000 },
+	[HSC160KD] = { .pmin = -160000, .pmax =  160000 },
+	[HSC250KD] = { .pmin = -250000, .pmax =  250000 },
+	[HSC400KD] = { .pmin = -400000, .pmax =  400000 },
+	[HSC250LG] = { .pmin =       0, .pmax =     250 },
+	[HSC400LG] = { .pmin =       0, .pmax =     400 },
+	[HSC600LG] = { .pmin =       0, .pmax =     600 },
+	[HSC001KG] = { .pmin =       0, .pmax =    1000 },
+	[HSC1_6KG] = { .pmin =       0, .pmax =    1600 },
+	[HSC2_5KG] = { .pmin =       0, .pmax =    2500 },
+	[HSC004KG] = { .pmin =       0, .pmax =    4000 },
+	[HSC006KG] = { .pmin =       0, .pmax =    6000 },
+	[HSC010KG] = { .pmin =       0, .pmax =   10000 },
+	[HSC016KG] = { .pmin =       0, .pmax =   16000 },
+	[HSC025KG] = { .pmin =       0, .pmax =   25000 },
+	[HSC040KG] = { .pmin =       0, .pmax =   40000 },
+	[HSC060KG] = { .pmin =       0, .pmax =   60000 },
+	[HSC100KG] = { .pmin =       0, .pmax =  100000 },
+	[HSC160KG] = { .pmin =       0, .pmax =  160000 },
+	[HSC250KG] = { .pmin =       0, .pmax =  250000 },
+	[HSC400KG] = { .pmin =       0, .pmax =  400000 },
+	[HSC600KG] = { .pmin =       0, .pmax =  600000 },
+	[HSC001GG] = { .pmin =       0, .pmax = 1000000 },
+	[HSC015PA] = { .pmin =       0, .pmax =  103421 },
+	[HSC030PA] = { .pmin =       0, .pmax =  206843 },
+	[HSC060PA] = { .pmin =       0, .pmax =  413685 },
+	[HSC100PA] = { .pmin =       0, .pmax =  689476 },
+	[HSC150PA] = { .pmin =       0, .pmax = 1034214 },
+	[HSC0_5ND] = { .pmin =    -125, .pmax =     125 },
+	[HSC001ND] = { .pmin =    -249, .pmax =     249 },
+	[HSC002ND] = { .pmin =    -498, .pmax =     498 },
+	[HSC004ND] = { .pmin =    -996, .pmax =     996 },
+	[HSC005ND] = { .pmin =   -1245, .pmax =    1245 },
+	[HSC010ND] = { .pmin =   -2491, .pmax =    2491 },
+	[HSC020ND] = { .pmin =   -4982, .pmax =    4982 },
+	[HSC030ND] = { .pmin =   -7473, .pmax =    7473 },
+	[HSC001PD] = { .pmin =   -6895, .pmax =    6895 },
+	[HSC005PD] = { .pmin =  -34474, .pmax =   34474 },
+	[HSC015PD] = { .pmin = -103421, .pmax =  103421 },
+	[HSC030PD] = { .pmin = -206843, .pmax =  206843 },
+	[HSC060PD] = { .pmin = -413685, .pmax =  413685 },
+	[HSC001NG] = { .pmin =       0, .pmax =     249 },
+	[HSC002NG] = { .pmin =       0, .pmax =     498 },
+	[HSC004NG] = { .pmin =       0, .pmax =     996 },
+	[HSC005NG] = { .pmin =       0, .pmax =    1245 },
+	[HSC010NG] = { .pmin =       0, .pmax =    2491 },
+	[HSC020NG] = { .pmin =       0, .pmax =    4982 },
+	[HSC030NG] = { .pmin =       0, .pmax =    7473 },
+	[HSC001PG] = { .pmin =       0, .pmax =    6895 },
+	[HSC005PG] = { .pmin =       0, .pmax =   34474 },
+	[HSC015PG] = { .pmin =       0, .pmax =  103421 },
+	[HSC030PG] = { .pmin =       0, .pmax =  206843 },
+	[HSC060PG] = { .pmin =       0, .pmax =  413685 },
+	[HSC100PG] = { .pmin =       0, .pmax =  689476 },
+	[HSC150PG] = { .pmin =       0, .pmax = 1034214 },
+};
+
+/**
+ * hsc_measurement_is_valid() - validate last conversion via status bits
+ * @data: structure containing instantiated sensor data
+ * Return: true only if both status bits are zero
+ *
+ * the two MSB from the first transfered byte contain a status code
+ *   00 - normal operation, valid data
+ *   01 - device in factory programming mode
+ *   10 - stale data
+ *   11 - diagnostic condition
+ */
+static bool hsc_measurement_is_valid(struct hsc_data *data)
+{
+	return !(data->buffer[0] & HSC_STATUS_MASK);
+}
+
+static int hsc_get_measurement(struct hsc_data *data)
+{
+	const struct hsc_chip_data *chip = data->chip;
+	int ret;
+
+	ret = data->recv_cb(data);
+	if (ret < 0)
+		return ret;
+
+	data->is_valid = chip->valid(data);
+	if (!data->is_valid)
+		return -EAGAIN;
+
+	return 0;
+}
+
+/*
+ * IIO ABI expects
+ * value = (conv + offset) * scale
+ *
+ * datasheet provides the following formula for determining the temperature
+ * temp[C] = conv * a + b
+ *   where a = 200/2047; b = -50
+ *
+ *  temp[C] = (conv + (b/a)) * a * (1000)
+ *  =>
+ *  scale = a * 1000 = .097703957 * 1000 = 97.703957
+ *  offset = b/a = -50 / .097703957 = -50000000 / 97704
+ *
+ *  based on the datasheet
+ *  pressure = (conv - Omin) * Q + Pmin =
+ *          ((conv - Omin) + Pmin/Q) * Q
+ *  =>
+ *  scale = Q = (Pmax - Pmin) / (Omax - Omin)
+ *  offset = Pmin/Q - Omin = Pmin * (Omax - Omin) / (Pmax - Pmin) - Omin
+ */
+static int hsc_read_raw(struct iio_dev *indio_dev,
+			struct iio_chan_spec const *channel, int *val,
+			int *val2, long mask)
+{
+	struct hsc_data *data = iio_priv(indio_dev);
+	int ret;
+	u32 recvd;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		ret = hsc_get_measurement(data);
+		if (ret)
+			return ret;
+
+		recvd = get_unaligned_be32(data->buffer);
+		switch (channel->type) {
+		case IIO_PRESSURE:
+			*val = FIELD_GET(HSC_PRESSURE_MASK, recvd);
+			return IIO_VAL_INT;
+		case IIO_TEMP:
+			*val = FIELD_GET(HSC_TEMPERATURE_MASK, recvd);
+			return IIO_VAL_INT;
+		default:
+			return -EINVAL;
+		}
+
+	case IIO_CHAN_INFO_SCALE:
+		switch (channel->type) {
+		case IIO_TEMP:
+			*val = 97;
+			*val2 = 703957;
+			return IIO_VAL_INT_PLUS_MICRO;
+		case IIO_PRESSURE:
+			*val = data->p_scale;
+			*val2 = data->p_scale_dec;
+			return IIO_VAL_INT_PLUS_NANO;
+		default:
+			return -EINVAL;
+		}
+
+	case IIO_CHAN_INFO_OFFSET:
+		switch (channel->type) {
+		case IIO_TEMP:
+			*val = -50000000;
+			*val2 = 97704;
+			return IIO_VAL_FRACTIONAL;
+		case IIO_PRESSURE:
+			*val = data->p_offset;
+			*val2 = data->p_offset_dec;
+			return IIO_VAL_INT_PLUS_MICRO;
+		default:
+			return -EINVAL;
+		}
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct iio_chan_spec hsc_channels[] = {
+	{
+		.type = IIO_PRESSURE,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+				      BIT(IIO_CHAN_INFO_SCALE) |
+				      BIT(IIO_CHAN_INFO_OFFSET),
+	},
+	{
+		.type = IIO_TEMP,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+				      BIT(IIO_CHAN_INFO_SCALE) |
+				      BIT(IIO_CHAN_INFO_OFFSET),
+	},
+};
+
+static const struct iio_info hsc_info = {
+	.read_raw = hsc_read_raw,
+};
+
+static const struct hsc_chip_data hsc_chip = {
+	.valid = hsc_measurement_is_valid,
+	.channels = hsc_channels,
+	.num_channels = ARRAY_SIZE(hsc_channels),
+};
+
+int hsc_common_probe(struct device *dev, hsc_recv_fn recv)
+{
+	struct hsc_data *hsc;
+	struct iio_dev *indio_dev;
+	const char *triplet;
+	u64 tmp;
+	int ret;
+
+	indio_dev = devm_iio_device_alloc(dev, sizeof(*hsc));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	hsc = iio_priv(indio_dev);
+
+	hsc->chip = &hsc_chip;
+	hsc->recv_cb = recv;
+	hsc->dev = dev;
+
+	ret = device_property_read_u32(dev, "honeywell,transfer-function",
+				       &hsc->function);
+	if (ret)
+		return dev_err_probe(dev, ret,
+			    "honeywell,transfer-function could not be read\n");
+	if (hsc->function > HSC_FUNCTION_F)
+		return dev_err_probe(dev, -EINVAL,
+				     "honeywell,transfer-function %d invalid\n",
+				     hsc->function);
+
+	ret = device_property_read_string(dev, "honeywell,pressure-triplet",
+					  &triplet);
+	if (ret)
+		return dev_err_probe(dev, ret,
+			     "honeywell,pressure-triplet could not be read\n");
+
+	if (str_has_prefix(triplet, "NA")) {
+		ret = device_property_read_u32(dev, "honeywell,pmin-pascal",
+					       &hsc->pmin);
+		if (ret)
+			return dev_err_probe(dev, ret,
+				  "honeywell,pmin-pascal could not be read\n");
+
+		ret = device_property_read_u32(dev, "honeywell,pmax-pascal",
+					       &hsc->pmax);
+		if (ret)
+			return dev_err_probe(dev, ret,
+				  "honeywell,pmax-pascal could not be read\n");
+	} else {
+		ret = device_property_match_property_string(dev,
+						  "honeywell,pressure-triplet",
+						  hsc_triplet_variants,
+						  HSC_VARIANTS_MAX);
+		if (ret < 0)
+			return dev_err_probe(dev, -EINVAL,
+				    "honeywell,pressure-triplet is invalid\n");
+
+		hsc->pmin = hsc_range_config[ret].pmin;
+		hsc->pmax = hsc_range_config[ret].pmax;
+	}
+
+	if (hsc->pmin >= hsc->pmax)
+		return dev_err_probe(dev, -EINVAL,
+				     "pressure limits are invalid\n");
+
+	ret = devm_regulator_get_enable(dev, "vdd");
+	if (ret)
+		return dev_err_probe(dev, ret, "can't get vdd supply\n");
+
+	hsc->outmin = hsc_func_spec[hsc->function].output_min;
+	hsc->outmax = hsc_func_spec[hsc->function].output_max;
+
+	tmp = div_s64(((s64)(hsc->pmax - hsc->pmin)) * MICRO,
+		      hsc->outmax - hsc->outmin);
+	hsc->p_scale = div_s64_rem(tmp, NANO, &hsc->p_scale_dec);
+	tmp = div_s64(((s64)hsc->pmin * (s64)(hsc->outmax - hsc->outmin)) * MICRO,
+		      hsc->pmax - hsc->pmin);
+	tmp -= (s64)hsc->outmin * MICRO;
+	hsc->p_offset = div_s64_rem(tmp, MICRO, &hsc->p_offset_dec);
+
+	indio_dev->name = "hsc030pa";
+	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->info = &hsc_info;
+	indio_dev->channels = hsc->chip->channels;
+	indio_dev->num_channels = hsc->chip->num_channels;
+
+	return devm_iio_device_register(dev, indio_dev);
+}
+EXPORT_SYMBOL_NS(hsc_common_probe, IIO_HONEYWELL_HSC030PA);
+
+MODULE_AUTHOR("Petre Rodan <petre.rodan@subdimension.ro>");
+MODULE_DESCRIPTION("Honeywell HSC and SSC pressure sensor core driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/iio/pressure/hsc030pa.h b/drivers/iio/pressure/hsc030pa.h
new file mode 100644
index 000000000000..d20420dba4f6
--- /dev/null
+++ b/drivers/iio/pressure/hsc030pa.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Honeywell TruStability HSC Series pressure/temperature sensor
+ *
+ * Copyright (c) 2023 Petre Rodan <petre.rodan@subdimension.ro>
+ */
+
+#ifndef _HSC030PA_H
+#define _HSC030PA_H
+
+#include <linux/types.h>
+
+#define HSC_REG_MEASUREMENT_RD_SIZE 4
+
+struct device;
+
+struct iio_chan_spec;
+struct iio_dev;
+
+struct hsc_data;
+struct hsc_chip_data;
+
+typedef int (*hsc_recv_fn)(struct hsc_data *);
+
+/**
+ * struct hsc_data
+ * @dev: current device structure
+ * @chip: structure containing chip's channel properties
+ * @recv_cb: function that implements the chip reads
+ * @is_valid: true if last transfer has been validated
+ * @pmin: minimum measurable pressure limit
+ * @pmax: maximum measurable pressure limit
+ * @outmin: minimum raw pressure in counts (based on transfer function)
+ * @outmax: maximum raw pressure in counts (based on transfer function)
+ * @function: transfer function
+ * @p_scale: pressure scale
+ * @p_scale_dec: pressure scale, decimal places
+ * @p_offset: pressure offset
+ * @p_offset_dec: pressure offset, decimal places
+ * @buffer: raw conversion data
+ */
+struct hsc_data {
+	struct device *dev;
+	const struct hsc_chip_data *chip;
+	hsc_recv_fn recv_cb;
+	bool is_valid;
+	s32 pmin;
+	s32 pmax;
+	u32 outmin;
+	u32 outmax;
+	u32 function;
+	s64 p_scale;
+	s32 p_scale_dec;
+	s64 p_offset;
+	s32 p_offset_dec;
+	u8 buffer[HSC_REG_MEASUREMENT_RD_SIZE] __aligned(IIO_DMA_MINALIGN);
+};
+
+struct hsc_chip_data {
+	bool (*valid)(struct hsc_data *data);
+	const struct iio_chan_spec *channels;
+	u8 num_channels;
+};
+
+enum hsc_func_id {
+	HSC_FUNCTION_A,
+	HSC_FUNCTION_B,
+	HSC_FUNCTION_C,
+	HSC_FUNCTION_F,
+};
+
+int hsc_common_probe(struct device *dev, hsc_recv_fn recv);
+
+#endif
diff --git a/drivers/iio/pressure/hsc030pa_i2c.c b/drivers/iio/pressure/hsc030pa_i2c.c
new file mode 100644
index 000000000000..e2b524b36417
--- /dev/null
+++ b/drivers/iio/pressure/hsc030pa_i2c.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Honeywell TruStability HSC Series pressure/temperature sensor
+ *
+ * Copyright (c) 2023 Petre Rodan <petre.rodan@subdimension.ro>
+ *
+ * Datasheet: https://prod-edam.honeywell.com/content/dam/honeywell-edam/sps/siot/en-us/products/sensors/pressure-sensors/board-mount-pressure-sensors/trustability-hsc-series/documents/sps-siot-trustability-hsc-series-high-accuracy-board-mount-pressure-sensors-50099148-a-en-ciid-151133.pdf [hsc]
+ * Datasheet: https://prod-edam.honeywell.com/content/dam/honeywell-edam/sps/siot/en-us/products/sensors/pressure-sensors/board-mount-pressure-sensors/common/documents/sps-siot-i2c-comms-digital-output-pressure-sensors-tn-008201-3-en-ciid-45841.pdf [i2c related]
+ */
+
+#include <linux/errno.h>
+#include <linux/i2c.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+
+#include <linux/iio/iio.h>
+
+#include "hsc030pa.h"
+
+static int hsc_i2c_recv(struct hsc_data *data)
+{
+	struct i2c_client *client = to_i2c_client(data->dev);
+	struct i2c_msg msg;
+	int ret;
+
+	msg.addr = client->addr;
+	msg.flags = client->flags | I2C_M_RD;
+	msg.len = HSC_REG_MEASUREMENT_RD_SIZE;
+	msg.buf = data->buffer;
+
+	ret = i2c_transfer(client->adapter, &msg, 1);
+
+	return (ret == 2) ? 0 : ret;
+}
+
+static int hsc_i2c_probe(struct i2c_client *client)
+{
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C))
+		return -EOPNOTSUPP;
+
+	return hsc_common_probe(&client->dev, hsc_i2c_recv);
+}
+
+static const struct of_device_id hsc_i2c_match[] = {
+	{ .compatible = "honeywell,hsc030pa" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, hsc_i2c_match);
+
+static const struct i2c_device_id hsc_i2c_id[] = {
+	{ "hsc030pa" },
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, hsc_i2c_id);
+
+static struct i2c_driver hsc_i2c_driver = {
+	.driver = {
+		.name = "hsc030pa",
+		.of_match_table = hsc_i2c_match,
+	},
+	.probe = hsc_i2c_probe,
+	.id_table = hsc_i2c_id,
+};
+module_i2c_driver(hsc_i2c_driver);
+
+MODULE_AUTHOR("Petre Rodan <petre.rodan@subdimension.ro>");
+MODULE_DESCRIPTION("Honeywell HSC and SSC pressure sensor i2c driver");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(IIO_HONEYWELL_HSC030PA);
diff --git a/drivers/iio/pressure/hsc030pa_spi.c b/drivers/iio/pressure/hsc030pa_spi.c
new file mode 100644
index 000000000000..a719bade8326
--- /dev/null
+++ b/drivers/iio/pressure/hsc030pa_spi.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Honeywell TruStability HSC Series pressure/temperature sensor
+ *
+ * Copyright (c) 2023 Petre Rodan <petre.rodan@subdimension.ro>
+ *
+ * Datasheet: https://prod-edam.honeywell.com/content/dam/honeywell-edam/sps/siot/en-us/products/sensors/pressure-sensors/board-mount-pressure-sensors/trustability-hsc-series/documents/sps-siot-trustability-hsc-series-high-accuracy-board-mount-pressure-sensors-50099148-a-en-ciid-151133.pdf
+ */
+
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/spi/spi.h>
+#include <linux/stddef.h>
+
+#include <linux/iio/iio.h>
+
+#include "hsc030pa.h"
+
+static int hsc_spi_recv(struct hsc_data *data)
+{
+	struct spi_device *spi = to_spi_device(data->dev);
+	struct spi_transfer xfer = {
+		.tx_buf = NULL,
+		.rx_buf = data->buffer,
+		.len = HSC_REG_MEASUREMENT_RD_SIZE,
+	};
+
+	return spi_sync_transfer(spi, &xfer, 1);
+}
+
+static int hsc_spi_probe(struct spi_device *spi)
+{
+	return hsc_common_probe(&spi->dev, hsc_spi_recv);
+}
+
+static const struct of_device_id hsc_spi_match[] = {
+	{ .compatible = "honeywell,hsc030pa" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, hsc_spi_match);
+
+static const struct spi_device_id hsc_spi_id[] = {
+	{ "hsc030pa" },
+	{}
+};
+MODULE_DEVICE_TABLE(spi, hsc_spi_id);
+
+static struct spi_driver hsc_spi_driver = {
+	.driver = {
+		.name = "hsc030pa",
+		.of_match_table = hsc_spi_match,
+	},
+	.probe = hsc_spi_probe,
+	.id_table = hsc_spi_id,
+};
+module_spi_driver(hsc_spi_driver);
+
+MODULE_AUTHOR("Petre Rodan <petre.rodan@subdimension.ro>");
+MODULE_DESCRIPTION("Honeywell HSC and SSC pressure sensor spi driver");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(IIO_HONEYWELL_HSC030PA);
diff --git a/drivers/iio/proximity/irsd200.c b/drivers/iio/proximity/irsd200.c
index bdff91f6b1a3..323ac6dac90e 100644
--- a/drivers/iio/proximity/irsd200.c
+++ b/drivers/iio/proximity/irsd200.c
@@ -7,7 +7,6 @@
 
 #include <asm/unaligned.h>
 #include <linux/bitfield.h>
-#include <linux/gpio.h>
 #include <linux/i2c.h>
 #include <linux/module.h>
 #include <linux/regmap.h>
diff --git a/drivers/iio/proximity/sx9324.c b/drivers/iio/proximity/sx9324.c
index 438f9c9aba6e..ac2ed2da21cc 100644
--- a/drivers/iio/proximity/sx9324.c
+++ b/drivers/iio/proximity/sx9324.c
@@ -888,7 +888,6 @@ sx9324_get_default_reg(struct device *dev, int idx,
 	char prop[] = SX9324_PROXRAW_DEF;
 	u32 start = 0, raw = 0, pos = 0;
 	int ret, count, ph, pin;
-	const char *res;
 
 	memcpy(reg_def, &sx9324_default_regs[idx], sizeof(*reg_def));
 
@@ -915,24 +914,21 @@ sx9324_get_default_reg(struct device *dev, int idx,
 		reg_def->def = raw;
 		break;
 	case SX9324_REG_AFE_CTRL0:
-		ret = device_property_read_string(dev,
-				"semtech,cs-idle-sleep", &res);
-		if (!ret)
-			ret = match_string(sx9324_csidle, ARRAY_SIZE(sx9324_csidle), res);
+		ret = device_property_match_property_string(dev, "semtech,cs-idle-sleep",
+							    sx9324_csidle,
+							    ARRAY_SIZE(sx9324_csidle));
 		if (ret >= 0) {
 			reg_def->def &= ~SX9324_REG_AFE_CTRL0_CSIDLE_MASK;
 			reg_def->def |= ret << SX9324_REG_AFE_CTRL0_CSIDLE_SHIFT;
 		}
 
-		ret = device_property_read_string(dev,
-				"semtech,int-comp-resistor", &res);
-		if (ret)
-			break;
-		ret = match_string(sx9324_rints, ARRAY_SIZE(sx9324_rints), res);
-		if (ret < 0)
-			break;
-		reg_def->def &= ~SX9324_REG_AFE_CTRL0_RINT_MASK;
-		reg_def->def |= ret << SX9324_REG_AFE_CTRL0_RINT_SHIFT;
+		ret = device_property_match_property_string(dev, "semtech,int-comp-resistor",
+							    sx9324_rints,
+							    ARRAY_SIZE(sx9324_rints));
+		if (ret >= 0) {
+			reg_def->def &= ~SX9324_REG_AFE_CTRL0_RINT_MASK;
+			reg_def->def |= ret << SX9324_REG_AFE_CTRL0_RINT_SHIFT;
+		}
 		break;
 	case SX9324_REG_AFE_CTRL4:
 	case SX9324_REG_AFE_CTRL7:
diff --git a/drivers/iio/resolver/ad2s1210.c b/drivers/iio/resolver/ad2s1210.c
index 1bd1b950e7cc..a414eef12e5e 100644
--- a/drivers/iio/resolver/ad2s1210.c
+++ b/drivers/iio/resolver/ad2s1210.c
@@ -141,7 +141,7 @@ struct ad2s1210_state {
 	struct spi_device *sdev;
 	/** GPIO pin connected to SAMPLE line. */
 	struct gpio_desc *sample_gpio;
-	/** GPIO pins connected to A0 and A1 lines. */
+	/** GPIO pins connected to A0 and A1 lines (optional). */
 	struct gpio_descs *mode_gpios;
 	/** Used to access config registers. */
 	struct regmap *regmap;
@@ -149,6 +149,8 @@ struct ad2s1210_state {
 	unsigned long clkin_hz;
 	/** Available raw hysteresis values based on resolution. */
 	int hysteresis_available[2];
+	/* adi,fixed-mode property - only valid when mode_gpios == NULL. */
+	enum ad2s1210_mode fixed_mode;
 	/** The selected resolution */
 	enum ad2s1210_resolution resolution;
 	/** Copy of fault register from the previous read. */
@@ -175,6 +177,9 @@ static int ad2s1210_set_mode(struct ad2s1210_state *st, enum ad2s1210_mode mode)
 	struct gpio_descs *gpios = st->mode_gpios;
 	DECLARE_BITMAP(bitmap, 2);
 
+	if (!gpios)
+		return mode == st->fixed_mode ? 0 : -EOPNOTSUPP;
+
 	bitmap[0] = mode;
 
 	return gpiod_set_array_value(gpios->ndescs, gpios->desc, gpios->info,
@@ -276,7 +281,8 @@ static int ad2s1210_regmap_reg_read(void *context, unsigned int reg,
 	 * parity error. The fault register is read-only and the D7 bit means
 	 * something else there.
 	 */
-	if (reg != AD2S1210_REG_FAULT && st->rx[1] & AD2S1210_ADDRESS_DATA)
+	if ((reg > AD2S1210_REG_VELOCITY_LSB && reg != AD2S1210_REG_FAULT)
+	     && st->rx[1] & AD2S1210_ADDRESS_DATA)
 		return -EBADMSG;
 
 	*val = st->rx[1];
@@ -450,21 +456,53 @@ static int ad2s1210_single_conversion(struct iio_dev *indio_dev,
 	ad2s1210_toggle_sample_line(st);
 	timestamp = iio_get_time_ns(indio_dev);
 
-	switch (chan->type) {
-	case IIO_ANGL:
-		ret = ad2s1210_set_mode(st, MOD_POS);
-		break;
-	case IIO_ANGL_VEL:
-		ret = ad2s1210_set_mode(st, MOD_VEL);
-		break;
-	default:
-		return -EINVAL;
+	if (st->fixed_mode == MOD_CONFIG) {
+		unsigned int reg_val;
+
+		switch (chan->type) {
+		case IIO_ANGL:
+			ret = regmap_bulk_read(st->regmap,
+					       AD2S1210_REG_POSITION_MSB,
+					       &st->sample.raw, 2);
+			if (ret < 0)
+				return ret;
+
+			break;
+		case IIO_ANGL_VEL:
+			ret = regmap_bulk_read(st->regmap,
+					       AD2S1210_REG_VELOCITY_MSB,
+					       &st->sample.raw, 2);
+			if (ret < 0)
+				return ret;
+
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		ret = regmap_read(st->regmap, AD2S1210_REG_FAULT, &reg_val);
+		if (ret < 0)
+			return ret;
+
+		st->sample.fault = reg_val;
+	} else {
+		switch (chan->type) {
+		case IIO_ANGL:
+			ret = ad2s1210_set_mode(st, MOD_POS);
+			break;
+		case IIO_ANGL_VEL:
+			ret = ad2s1210_set_mode(st, MOD_VEL);
+			break;
+		default:
+			return -EINVAL;
+		}
+		if (ret < 0)
+			return ret;
+
+		ret = spi_read(st->sdev, &st->sample, 3);
+		if (ret < 0)
+			return ret;
 	}
-	if (ret < 0)
-		return ret;
-	ret = spi_read(st->sdev, &st->sample, 3);
-	if (ret < 0)
-		return ret;
 
 	switch (chan->type) {
 	case IIO_ANGL:
@@ -1252,27 +1290,53 @@ static irqreturn_t ad2s1210_trigger_handler(int irq, void *p)
 	ad2s1210_toggle_sample_line(st);
 
 	if (test_bit(0, indio_dev->active_scan_mask)) {
-		ret = ad2s1210_set_mode(st, MOD_POS);
-		if (ret < 0)
-			goto error_ret;
-
-		ret = spi_read(st->sdev, &st->sample, 3);
-		if (ret < 0)
-			goto error_ret;
+		if (st->fixed_mode == MOD_CONFIG) {
+			ret = regmap_bulk_read(st->regmap,
+					       AD2S1210_REG_POSITION_MSB,
+					       &st->sample.raw, 2);
+			if (ret < 0)
+				goto error_ret;
+		} else {
+			ret = ad2s1210_set_mode(st, MOD_POS);
+			if (ret < 0)
+				goto error_ret;
+
+			ret = spi_read(st->sdev, &st->sample, 3);
+			if (ret < 0)
+				goto error_ret;
+		}
 
 		memcpy(&st->scan.chan[chan++], &st->sample.raw, 2);
 	}
 
 	if (test_bit(1, indio_dev->active_scan_mask)) {
-		ret = ad2s1210_set_mode(st, MOD_VEL);
-		if (ret < 0)
-			goto error_ret;
+		if (st->fixed_mode == MOD_CONFIG) {
+			ret = regmap_bulk_read(st->regmap,
+					       AD2S1210_REG_VELOCITY_MSB,
+					       &st->sample.raw, 2);
+			if (ret < 0)
+				goto error_ret;
+		} else {
+			ret = ad2s1210_set_mode(st, MOD_VEL);
+			if (ret < 0)
+				goto error_ret;
+
+			ret = spi_read(st->sdev, &st->sample, 3);
+			if (ret < 0)
+				goto error_ret;
+		}
 
-		ret = spi_read(st->sdev, &st->sample, 3);
+		memcpy(&st->scan.chan[chan++], &st->sample.raw, 2);
+	}
+
+	if (st->fixed_mode == MOD_CONFIG) {
+		unsigned int reg_val;
+
+		ret = regmap_read(st->regmap, AD2S1210_REG_FAULT, &reg_val);
 		if (ret < 0)
-			goto error_ret;
+			return ret;
 
-		memcpy(&st->scan.chan[chan++], &st->sample.raw, 2);
+		st->sample.fault = reg_val;
 	}
 
 	ad2s1210_push_events(indio_dev, st->sample.fault, pf->timestamp);
@@ -1299,9 +1363,24 @@ static const struct iio_info ad2s1210_info = {
 static int ad2s1210_setup_properties(struct ad2s1210_state *st)
 {
 	struct device *dev = &st->sdev->dev;
+	const char *str_val;
 	u32 val;
 	int ret;
 
+	ret = device_property_read_string(dev, "adi,fixed-mode", &str_val);
+	if (ret == -EINVAL)
+		st->fixed_mode = -1;
+	else if (ret < 0)
+		return dev_err_probe(dev, ret,
+			"failed to read adi,fixed-mode property\n");
+	else {
+		if (strcmp(str_val, "config"))
+			return dev_err_probe(dev, -EINVAL,
+				"only adi,fixed-mode=\"config\" is supported\n");
+
+		st->fixed_mode = MOD_CONFIG;
+	}
+
 	ret = device_property_read_u32(dev, "assigned-resolution-bits", &val);
 	if (ret < 0)
 		return dev_err_probe(dev, ret,
@@ -1347,6 +1426,7 @@ static int ad2s1210_setup_gpios(struct ad2s1210_state *st)
 {
 	struct device *dev = &st->sdev->dev;
 	struct gpio_descs *resolution_gpios;
+	struct gpio_desc *reset_gpio;
 	DECLARE_BITMAP(bitmap, 2);
 	int ret;
 
@@ -1357,12 +1437,21 @@ static int ad2s1210_setup_gpios(struct ad2s1210_state *st)
 				     "failed to request sample GPIO\n");
 
 	/* both pins high means that we start in config mode */
-	st->mode_gpios = devm_gpiod_get_array(dev, "mode", GPIOD_OUT_HIGH);
+	st->mode_gpios = devm_gpiod_get_array_optional(dev, "mode",
+						       GPIOD_OUT_HIGH);
 	if (IS_ERR(st->mode_gpios))
 		return dev_err_probe(dev, PTR_ERR(st->mode_gpios),
 				     "failed to request mode GPIOs\n");
 
-	if (st->mode_gpios->ndescs != 2)
+	if (!st->mode_gpios && st->fixed_mode == -1)
+		return dev_err_probe(dev, -EINVAL,
+			"must specify either adi,fixed-mode or mode-gpios\n");
+
+	if (st->mode_gpios && st->fixed_mode != -1)
+		return dev_err_probe(dev, -EINVAL,
+			"must specify only one of adi,fixed-mode or mode-gpios\n");
+
+	if (st->mode_gpios && st->mode_gpios->ndescs != 2)
 		return dev_err_probe(dev, -EINVAL,
 				     "requires exactly 2 mode-gpios\n");
 
@@ -1393,6 +1482,17 @@ static int ad2s1210_setup_gpios(struct ad2s1210_state *st)
 					     "failed to set resolution gpios\n");
 	}
 
+	/* If the optional reset GPIO is present, toggle it to do a hard reset. */
+	reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(reset_gpio))
+		return dev_err_probe(dev, PTR_ERR(reset_gpio),
+				     "failed to request reset GPIO\n");
+
+	if (reset_gpio) {
+		udelay(10);
+		gpiod_set_value(reset_gpio, 0);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/iio/temperature/Kconfig b/drivers/iio/temperature/Kconfig
index ed384f33e0c7..ed0e4963362f 100644
--- a/drivers/iio/temperature/Kconfig
+++ b/drivers/iio/temperature/Kconfig
@@ -76,6 +76,18 @@ config MLX90632
 	  This driver can also be built as a module. If so, the module will
 	  be called mlx90632.
 
+config MLX90635
+	tristate "MLX90635 contact-less infrared sensor with medical accuracy"
+	depends on I2C
+	select REGMAP_I2C
+	help
+	  If you say yes here you get support for the Melexis
+	  MLX90635 contact-less infrared sensor with medical accuracy
+	  connected with I2C.
+
+	  This driver can also be built as a module. If so, the module will
+	  be called mlx90635.
+
 config TMP006
 	tristate "TMP006 infrared thermopile sensor"
 	depends on I2C
@@ -158,4 +170,14 @@ config MAX31865
 	  This driver can also be build as a module. If so, the module
 	  will be called max31865.
 
+config MCP9600
+	tristate "MCP9600 thermocouple EMF converter"
+	depends on I2C
+	help
+	  If you say yes here you get support for MCP9600
+	  thermocouple EMF converter connected via I2C.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called mcp9600.
+
 endmenu
diff --git a/drivers/iio/temperature/Makefile b/drivers/iio/temperature/Makefile
index dfec8c6d3019..07d6e65709f7 100644
--- a/drivers/iio/temperature/Makefile
+++ b/drivers/iio/temperature/Makefile
@@ -10,8 +10,10 @@ obj-$(CONFIG_MAXIM_THERMOCOUPLE) += maxim_thermocouple.o
 obj-$(CONFIG_MAX30208) += max30208.o
 obj-$(CONFIG_MAX31856) += max31856.o
 obj-$(CONFIG_MAX31865) += max31865.o
+obj-$(CONFIG_MCP9600) += mcp9600.o
 obj-$(CONFIG_MLX90614) += mlx90614.o
 obj-$(CONFIG_MLX90632) += mlx90632.o
+obj-$(CONFIG_MLX90632) += mlx90635.o
 obj-$(CONFIG_TMP006) += tmp006.o
 obj-$(CONFIG_TMP007) += tmp007.o
 obj-$(CONFIG_TMP117) += tmp117.o
diff --git a/drivers/iio/temperature/mcp9600.c b/drivers/iio/temperature/mcp9600.c
new file mode 100644
index 000000000000..46845804292b
--- /dev/null
+++ b/drivers/iio/temperature/mcp9600.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * mcp9600.c - Support for Microchip MCP9600 thermocouple EMF converter
+ *
+ * Copyright (c) 2022 Andrew Hepp
+ * Author: <andrew.hepp@ahepp.dev>
+ */
+
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+
+#include <linux/iio/iio.h>
+
+/* MCP9600 registers */
+#define MCP9600_HOT_JUNCTION 0x0
+#define MCP9600_COLD_JUNCTION 0x2
+#define MCP9600_DEVICE_ID 0x20
+
+/* MCP9600 device id value */
+#define MCP9600_DEVICE_ID_MCP9600 0x40
+
+static const struct iio_chan_spec mcp9600_channels[] = {
+	{
+		.type = IIO_TEMP,
+		.address = MCP9600_HOT_JUNCTION,
+		.info_mask_separate =
+			BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE),
+	},
+	{
+		.type = IIO_TEMP,
+		.address = MCP9600_COLD_JUNCTION,
+		.channel2 = IIO_MOD_TEMP_AMBIENT,
+		.modified = 1,
+		.info_mask_separate =
+			BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE),
+	},
+};
+
+struct mcp9600_data {
+	struct i2c_client *client;
+};
+
+static int mcp9600_read(struct mcp9600_data *data,
+			struct iio_chan_spec const *chan, int *val)
+{
+	int ret;
+
+	ret = i2c_smbus_read_word_swapped(data->client, chan->address);
+
+	if (ret < 0)
+		return ret;
+	*val = ret;
+
+	return 0;
+}
+
+static int mcp9600_read_raw(struct iio_dev *indio_dev,
+			    struct iio_chan_spec const *chan, int *val,
+			    int *val2, long mask)
+{
+	struct mcp9600_data *data = iio_priv(indio_dev);
+	int ret;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		ret = mcp9600_read(data, chan, val);
+		if (ret)
+			return ret;
+		return IIO_VAL_INT;
+	case IIO_CHAN_INFO_SCALE:
+		*val = 62;
+		*val2 = 500000;
+		return IIO_VAL_INT_PLUS_MICRO;
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct iio_info mcp9600_info = {
+	.read_raw = mcp9600_read_raw,
+};
+
+static int mcp9600_probe(struct i2c_client *client)
+{
+	struct iio_dev *indio_dev;
+	struct mcp9600_data *data;
+	int ret;
+
+	ret = i2c_smbus_read_byte_data(client, MCP9600_DEVICE_ID);
+	if (ret < 0)
+		return dev_err_probe(&client->dev, ret, "Failed to read device ID\n");
+	if (ret != MCP9600_DEVICE_ID_MCP9600)
+		dev_warn(&client->dev, "Expected ID %x, got %x\n",
+				MCP9600_DEVICE_ID_MCP9600, ret);
+
+	indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*data));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	data = iio_priv(indio_dev);
+	data->client = client;
+
+	indio_dev->info = &mcp9600_info;
+	indio_dev->name = "mcp9600";
+	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->channels = mcp9600_channels;
+	indio_dev->num_channels = ARRAY_SIZE(mcp9600_channels);
+
+	return devm_iio_device_register(&client->dev, indio_dev);
+}
+
+static const struct i2c_device_id mcp9600_id[] = {
+	{ "mcp9600" },
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, mcp9600_id);
+
+static const struct of_device_id mcp9600_of_match[] = {
+	{ .compatible = "microchip,mcp9600" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, mcp9600_of_match);
+
+static struct i2c_driver mcp9600_driver = {
+	.driver = {
+		.name = "mcp9600",
+		.of_match_table = mcp9600_of_match,
+	},
+	.probe = mcp9600_probe,
+	.id_table = mcp9600_id
+};
+module_i2c_driver(mcp9600_driver);
+
+MODULE_AUTHOR("Andrew Hepp <andrew.hepp@ahepp.dev>");
+MODULE_DESCRIPTION("Microchip MCP9600 thermocouple EMF converter driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/iio/temperature/mlx90635.c b/drivers/iio/temperature/mlx90635.c
new file mode 100644
index 000000000000..1f5c962c1818
--- /dev/null
+++ b/drivers/iio/temperature/mlx90635.c
@@ -0,0 +1,1097 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * mlx90635.c - Melexis MLX90635 contactless IR temperature sensor
+ *
+ * Copyright (c) 2023 Melexis <cmo@melexis.com>
+ *
+ * Driver for the Melexis MLX90635 I2C 16-bit IR thermopile sensor
+ */
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/iopoll.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/limits.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/math64.h>
+#include <linux/pm_runtime.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+
+#include <linux/iio/iio.h>
+
+/* Memory sections addresses */
+#define MLX90635_ADDR_RAM	0x0000 /* Start address of ram */
+#define MLX90635_ADDR_EEPROM	0x0018 /* Start address of user eeprom */
+
+/* EEPROM addresses - used at startup */
+#define MLX90635_EE_I2C_CFG	0x0018 /* I2C address register initial value */
+#define MLX90635_EE_CTRL1	0x001A /* Control register1 initial value */
+#define MLX90635_EE_CTRL2	0x001C /* Control register2 initial value */
+
+#define MLX90635_EE_Ha		0x001E /* Ha customer calib value reg 16bit */
+#define MLX90635_EE_Hb		0x0020 /* Hb customer calib value reg 16bit */
+#define MLX90635_EE_Fa		0x0026 /* Fa calibration register 32bit */
+#define MLX90635_EE_FASCALE	0x002A /* Scaling coefficient for Fa register 16bit */
+#define MLX90635_EE_Ga		0x002C /* Ga calibration register 16bit */
+#define MLX90635_EE_Fb		0x002E /* Fb calibration register 16bit */
+#define MLX90635_EE_Ea		0x0030 /* Ea calibration register 32bit */
+#define MLX90635_EE_Eb		0x0034 /* Eb calibration register 32bit */
+#define MLX90635_EE_P_G		0x0038 /* P_G calibration register 16bit */
+#define MLX90635_EE_P_O		0x003A /* P_O calibration register 16bit */
+#define MLX90635_EE_Aa		0x003C /* Aa calibration register 16bit */
+#define MLX90635_EE_VERSION	0x003E /* Version bits 4:7 and 12:15 */
+#define MLX90635_EE_Gb		0x0040 /* Gb calibration register 16bit */
+
+/* Device status register - volatile */
+#define MLX90635_REG_STATUS	0x0000
+#define   MLX90635_STAT_BUSY BIT(6) /* Device busy indicator */
+#define   MLX90635_STAT_BRST BIT(5) /* Brown out reset indicator */
+#define   MLX90635_STAT_CYCLE_POS GENMASK(4, 2) /* Data position */
+#define   MLX90635_STAT_END_CONV BIT(1) /* End of conversion indicator */
+#define   MLX90635_STAT_DATA_RDY BIT(0) /* Data ready indicator */
+
+/* EEPROM control register address - volatile */
+#define MLX90635_REG_EE		0x000C
+#define   MLX90635_EE_ACTIVE BIT(4) /* Power-on EEPROM */
+#define   MLX90635_EE_BUSY_MASK	BIT(15)
+
+#define MLX90635_REG_CMD	0x0010 /* Command register address */
+
+/* Control register1 address - volatile */
+#define MLX90635_REG_CTRL1	0x0014
+#define   MLX90635_CTRL1_REFRESH_RATE_MASK GENMASK(2, 0)
+#define   MLX90635_CTRL1_RES_CTRL_MASK GENMASK(4, 3)
+#define   MLX90635_CTRL1_TABLE_MASK BIT(15) /* Table select */
+
+/* Control register2 address - volatile */
+#define   MLX90635_REG_CTRL2	0x0016
+#define   MLX90635_CTRL2_BURST_CNT_MASK GENMASK(10, 6) /* Burst count */
+#define   MLX90635_CTRL2_MODE_MASK GENMASK(12, 11) /* Power mode */
+#define   MLX90635_CTRL2_SOB_MASK BIT(15)
+
+/* PowerModes statuses */
+#define MLX90635_PWR_STATUS_HALT 0
+#define MLX90635_PWR_STATUS_SLEEP_STEP 1
+#define MLX90635_PWR_STATUS_STEP 2
+#define MLX90635_PWR_STATUS_CONTINUOUS 3
+
+/* Measurement data addresses */
+#define MLX90635_RESULT_1   0x0002
+#define MLX90635_RESULT_2   0x0004
+#define MLX90635_RESULT_3   0x0006
+#define MLX90635_RESULT_4   0x0008
+#define MLX90635_RESULT_5   0x000A
+
+/* Timings (ms) */
+#define MLX90635_TIMING_RST_MIN 200 /* Minimum time after addressed reset command */
+#define MLX90635_TIMING_RST_MAX 250 /* Maximum time after addressed reset command */
+#define MLX90635_TIMING_POLLING 10000 /* Time between bit polling*/
+#define MLX90635_TIMING_EE_ACTIVE_MIN 100 /* Minimum time after activating the EEPROM for read */
+#define MLX90635_TIMING_EE_ACTIVE_MAX 150 /* Maximum time after activating the EEPROM for read */
+
+/* Magic constants */
+#define MLX90635_ID_DSPv1 0x01 /* EEPROM DSP version */
+#define MLX90635_RESET_CMD  0x0006 /* Reset sensor (address or global) */
+#define MLX90635_MAX_MEAS_NUM   31 /* Maximum number of measurements in list */
+#define MLX90635_PTAT_DIV 12   /* Used to divide the PTAT value in pre-processing */
+#define MLX90635_IR_DIV 24   /* Used to divide the IR value in pre-processing */
+#define MLX90635_SLEEP_DELAY_MS 6000 /* Autosleep delay */
+#define MLX90635_MEAS_MAX_TIME 2000 /* Max measurement time in ms for the lowest refresh rate */
+#define MLX90635_READ_RETRIES 100 /* Number of read retries before quitting with timeout error */
+#define MLX90635_VERSION_MASK (GENMASK(15, 12) | GENMASK(7, 4))
+#define MLX90635_DSP_VERSION(reg) (((reg & GENMASK(14, 12)) >> 9) | ((reg & GENMASK(6, 4)) >> 4))
+#define MLX90635_DSP_FIXED BIT(15)
+
+
+/**
+ * struct mlx90635_data - private data for the MLX90635 device
+ * @client: I2C client of the device
+ * @lock: Internal mutex because multiple reads are needed for single triggered
+ *	  measurement to ensure data consistency
+ * @regmap: Regmap of the device registers
+ * @regmap_ee: Regmap of the device EEPROM which can be cached
+ * @emissivity: Object emissivity from 0 to 1000 where 1000 = 1
+ * @regulator: Regulator of the device
+ * @powerstatus: Current POWER status of the device
+ * @interaction_ts: Timestamp of the last temperature read that is used
+ *		    for power management in jiffies
+ */
+struct mlx90635_data {
+	struct i2c_client *client;
+	struct mutex lock;
+	struct regmap *regmap;
+	struct regmap *regmap_ee;
+	u16 emissivity;
+	struct regulator *regulator;
+	int powerstatus;
+	unsigned long interaction_ts;
+};
+
+static const struct regmap_range mlx90635_volatile_reg_range[] = {
+	regmap_reg_range(MLX90635_REG_STATUS, MLX90635_REG_STATUS),
+	regmap_reg_range(MLX90635_RESULT_1, MLX90635_RESULT_5),
+	regmap_reg_range(MLX90635_REG_EE, MLX90635_REG_EE),
+	regmap_reg_range(MLX90635_REG_CMD, MLX90635_REG_CMD),
+	regmap_reg_range(MLX90635_REG_CTRL1, MLX90635_REG_CTRL2),
+};
+
+static const struct regmap_access_table mlx90635_volatile_regs_tbl = {
+	.yes_ranges = mlx90635_volatile_reg_range,
+	.n_yes_ranges = ARRAY_SIZE(mlx90635_volatile_reg_range),
+};
+
+static const struct regmap_range mlx90635_read_reg_range[] = {
+	regmap_reg_range(MLX90635_REG_STATUS, MLX90635_REG_STATUS),
+	regmap_reg_range(MLX90635_RESULT_1, MLX90635_RESULT_5),
+	regmap_reg_range(MLX90635_REG_EE, MLX90635_REG_EE),
+	regmap_reg_range(MLX90635_REG_CMD, MLX90635_REG_CMD),
+	regmap_reg_range(MLX90635_REG_CTRL1, MLX90635_REG_CTRL2),
+};
+
+static const struct regmap_access_table mlx90635_readable_regs_tbl = {
+	.yes_ranges = mlx90635_read_reg_range,
+	.n_yes_ranges = ARRAY_SIZE(mlx90635_read_reg_range),
+};
+
+static const struct regmap_range mlx90635_no_write_reg_range[] = {
+	regmap_reg_range(MLX90635_RESULT_1, MLX90635_RESULT_5),
+};
+
+static const struct regmap_access_table mlx90635_writeable_regs_tbl = {
+	.no_ranges = mlx90635_no_write_reg_range,
+	.n_no_ranges = ARRAY_SIZE(mlx90635_no_write_reg_range),
+};
+
+static const struct regmap_config mlx90635_regmap = {
+	.name = "mlx90635-registers",
+	.reg_stride = 1,
+	.reg_bits = 16,
+	.val_bits = 16,
+
+	.volatile_table = &mlx90635_volatile_regs_tbl,
+	.rd_table = &mlx90635_readable_regs_tbl,
+	.wr_table = &mlx90635_writeable_regs_tbl,
+
+	.use_single_read = true,
+	.use_single_write = true,
+	.can_multi_write = false,
+	.reg_format_endian = REGMAP_ENDIAN_BIG,
+	.val_format_endian = REGMAP_ENDIAN_BIG,
+	.cache_type = REGCACHE_RBTREE,
+};
+
+static const struct regmap_range mlx90635_read_ee_range[] = {
+	regmap_reg_range(MLX90635_EE_I2C_CFG, MLX90635_EE_CTRL2),
+	regmap_reg_range(MLX90635_EE_Ha, MLX90635_EE_Gb),
+};
+
+static const struct regmap_access_table mlx90635_readable_ees_tbl = {
+	.yes_ranges = mlx90635_read_ee_range,
+	.n_yes_ranges = ARRAY_SIZE(mlx90635_read_ee_range),
+};
+
+static const struct regmap_range mlx90635_no_write_ee_range[] = {
+	regmap_reg_range(MLX90635_ADDR_EEPROM, MLX90635_EE_Gb),
+};
+
+static const struct regmap_access_table mlx90635_writeable_ees_tbl = {
+	.no_ranges = mlx90635_no_write_ee_range,
+	.n_no_ranges = ARRAY_SIZE(mlx90635_no_write_ee_range),
+};
+
+static const struct regmap_config mlx90635_regmap_ee = {
+	.name = "mlx90635-eeprom",
+	.reg_stride = 1,
+	.reg_bits = 16,
+	.val_bits = 16,
+
+	.volatile_table = NULL,
+	.rd_table = &mlx90635_readable_ees_tbl,
+	.wr_table = &mlx90635_writeable_ees_tbl,
+
+	.use_single_read = true,
+	.use_single_write = true,
+	.can_multi_write = false,
+	.reg_format_endian = REGMAP_ENDIAN_BIG,
+	.val_format_endian = REGMAP_ENDIAN_BIG,
+	.cache_type = REGCACHE_RBTREE,
+};
+
+/**
+ * mlx90635_reset_delay() - Give the mlx90635 some time to reset properly
+ * If this is not done, the following I2C command(s) will not be accepted.
+ */
+static void mlx90635_reset_delay(void)
+{
+	usleep_range(MLX90635_TIMING_RST_MIN, MLX90635_TIMING_RST_MAX);
+}
+
+static int mlx90635_pwr_sleep_step(struct mlx90635_data *data)
+{
+	int ret;
+
+	if (data->powerstatus == MLX90635_PWR_STATUS_SLEEP_STEP)
+		return 0;
+
+	ret = regmap_write_bits(data->regmap, MLX90635_REG_CTRL2, MLX90635_CTRL2_MODE_MASK,
+				FIELD_PREP(MLX90635_CTRL2_MODE_MASK, MLX90635_PWR_STATUS_SLEEP_STEP));
+	if (ret < 0)
+		return ret;
+
+	data->powerstatus = MLX90635_PWR_STATUS_SLEEP_STEP;
+	return 0;
+}
+
+static int mlx90635_pwr_continuous(struct mlx90635_data *data)
+{
+	int ret;
+
+	if (data->powerstatus == MLX90635_PWR_STATUS_CONTINUOUS)
+		return 0;
+
+	ret = regmap_write_bits(data->regmap, MLX90635_REG_CTRL2, MLX90635_CTRL2_MODE_MASK,
+				FIELD_PREP(MLX90635_CTRL2_MODE_MASK, MLX90635_PWR_STATUS_CONTINUOUS));
+	if (ret < 0)
+		return ret;
+
+	data->powerstatus = MLX90635_PWR_STATUS_CONTINUOUS;
+	return 0;
+}
+
+static int mlx90635_read_ee_register(struct regmap *regmap, u16 reg_lsb,
+				     s32 *reg_value)
+{
+	unsigned int read;
+	u32 value;
+	int ret;
+
+	ret = regmap_read(regmap, reg_lsb + 2, &read);
+	if (ret < 0)
+		return ret;
+
+	value = read;
+
+	ret = regmap_read(regmap, reg_lsb, &read);
+	if (ret < 0)
+		return ret;
+
+	*reg_value = (read << 16) | (value & 0xffff);
+
+	return 0;
+}
+
+static int mlx90635_read_ee_ambient(struct regmap *regmap, s16 *PG, s16 *PO, s16 *Gb)
+{
+	unsigned int read_tmp;
+	int ret;
+
+	ret = regmap_read(regmap, MLX90635_EE_P_O, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*PO = (s16)read_tmp;
+
+	ret = regmap_read(regmap, MLX90635_EE_P_G, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*PG = (s16)read_tmp;
+
+	ret = regmap_read(regmap, MLX90635_EE_Gb, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*Gb = (u16)read_tmp;
+
+	return 0;
+}
+
+static int mlx90635_read_ee_object(struct regmap *regmap, u32 *Ea, u32 *Eb, u32 *Fa, s16 *Fb,
+				   s16 *Ga, s16 *Gb, s16 *Ha, s16 *Hb, u16 *Fa_scale)
+{
+	unsigned int read_tmp;
+	int ret;
+
+	ret = mlx90635_read_ee_register(regmap, MLX90635_EE_Ea, Ea);
+	if (ret < 0)
+		return ret;
+
+	ret = mlx90635_read_ee_register(regmap, MLX90635_EE_Eb, Eb);
+	if (ret < 0)
+		return ret;
+
+	ret = mlx90635_read_ee_register(regmap, MLX90635_EE_Fa, Fa);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_read(regmap, MLX90635_EE_Ha, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*Ha = (s16)read_tmp;
+
+	ret = regmap_read(regmap, MLX90635_EE_Hb, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*Hb = (s16)read_tmp;
+
+	ret = regmap_read(regmap, MLX90635_EE_Ga, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*Ga = (s16)read_tmp;
+
+	ret = regmap_read(regmap, MLX90635_EE_Gb, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*Gb = (s16)read_tmp;
+
+	ret = regmap_read(regmap, MLX90635_EE_Fb, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*Fb = (s16)read_tmp;
+
+	ret = regmap_read(regmap, MLX90635_EE_FASCALE, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*Fa_scale = (u16)read_tmp;
+
+	return 0;
+}
+
+static int mlx90635_calculate_dataset_ready_time(struct mlx90635_data *data, int *refresh_time)
+{
+	unsigned int reg;
+	int ret;
+
+	ret = regmap_read(data->regmap, MLX90635_REG_CTRL1, &reg);
+	if (ret < 0)
+		return ret;
+
+	*refresh_time = 2 * (MLX90635_MEAS_MAX_TIME >> FIELD_GET(MLX90635_CTRL1_REFRESH_RATE_MASK, reg)) + 80;
+
+	return 0;
+}
+
+static int mlx90635_perform_measurement_burst(struct mlx90635_data *data)
+{
+	unsigned int reg_status;
+	int refresh_time;
+	int ret;
+
+	ret = regmap_write_bits(data->regmap, MLX90635_REG_STATUS,
+				MLX90635_STAT_END_CONV, MLX90635_STAT_END_CONV);
+	if (ret < 0)
+		return ret;
+
+	ret = mlx90635_calculate_dataset_ready_time(data, &refresh_time);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write_bits(data->regmap, MLX90635_REG_CTRL2,
+				FIELD_PREP(MLX90635_CTRL2_SOB_MASK, 1),
+				FIELD_PREP(MLX90635_CTRL2_SOB_MASK, 1));
+	if (ret < 0)
+		return ret;
+
+	msleep(refresh_time); /* Wait minimum time for dataset to be ready */
+
+	ret = regmap_read_poll_timeout(data->regmap, MLX90635_REG_STATUS, reg_status,
+				       (!(reg_status & MLX90635_STAT_END_CONV)) == 0,
+				       MLX90635_TIMING_POLLING, MLX90635_READ_RETRIES * 10000);
+	if (ret < 0) {
+		dev_err(&data->client->dev, "data not ready");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+static int mlx90635_read_ambient_raw(struct regmap *regmap,
+				     s16 *ambient_new_raw, s16 *ambient_old_raw)
+{
+	unsigned int read_tmp;
+	int ret;
+
+	ret = regmap_read(regmap, MLX90635_RESULT_2, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*ambient_new_raw = (s16)read_tmp;
+
+	ret = regmap_read(regmap, MLX90635_RESULT_3, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*ambient_old_raw = (s16)read_tmp;
+
+	return 0;
+}
+
+static int mlx90635_read_object_raw(struct regmap *regmap, s16 *object_raw)
+{
+	unsigned int read_tmp;
+	s16 read;
+	int ret;
+
+	ret = regmap_read(regmap, MLX90635_RESULT_1, &read_tmp);
+	if (ret < 0)
+		return ret;
+
+	read = (s16)read_tmp;
+
+	ret = regmap_read(regmap, MLX90635_RESULT_4, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*object_raw = (read - (s16)read_tmp) / 2;
+
+	return 0;
+}
+
+static int mlx90635_read_all_channel(struct mlx90635_data *data,
+				     s16 *ambient_new_raw, s16 *ambient_old_raw,
+				     s16 *object_raw)
+{
+	int ret;
+
+	mutex_lock(&data->lock);
+	if (data->powerstatus == MLX90635_PWR_STATUS_SLEEP_STEP) {
+		/* Trigger measurement in Sleep Step mode */
+		ret = mlx90635_perform_measurement_burst(data);
+		if (ret < 0)
+			goto read_unlock;
+	}
+
+	ret = mlx90635_read_ambient_raw(data->regmap, ambient_new_raw,
+					ambient_old_raw);
+	if (ret < 0)
+		goto read_unlock;
+
+	ret = mlx90635_read_object_raw(data->regmap, object_raw);
+read_unlock:
+	mutex_unlock(&data->lock);
+	return ret;
+}
+
+static s64 mlx90635_preprocess_temp_amb(s16 ambient_new_raw,
+					s16 ambient_old_raw, s16 Gb)
+{
+	s64 VR_Ta, kGb, tmp;
+
+	kGb = ((s64)Gb * 1000LL) >> 10ULL;
+	VR_Ta = (s64)ambient_old_raw * 1000000LL +
+		kGb * div64_s64(((s64)ambient_new_raw * 1000LL),
+			(MLX90635_PTAT_DIV));
+	tmp = div64_s64(
+			 div64_s64(((s64)ambient_new_raw * 1000000000000LL),
+				   (MLX90635_PTAT_DIV)), VR_Ta);
+	return div64_s64(tmp << 19ULL, 1000LL);
+}
+
+static s64 mlx90635_preprocess_temp_obj(s16 object_raw,
+					s16 ambient_new_raw,
+					s16 ambient_old_raw, s16 Gb)
+{
+	s64 VR_IR, kGb, tmp;
+
+	kGb = ((s64)Gb * 1000LL) >> 10ULL;
+	VR_IR = (s64)ambient_old_raw * 1000000LL +
+		kGb * (div64_s64((s64)ambient_new_raw * 1000LL,
+			MLX90635_PTAT_DIV));
+	tmp = div64_s64(
+			div64_s64((s64)(object_raw * 1000000LL),
+				   MLX90635_IR_DIV) * 1000000LL,
+			VR_IR);
+	return div64_s64((tmp << 19ULL), 1000LL);
+}
+
+static s32 mlx90635_calc_temp_ambient(s16 ambient_new_raw, s16 ambient_old_raw,
+				      u16 P_G, u16 P_O, s16 Gb)
+{
+	s64 kPG, kPO, AMB;
+
+	AMB = mlx90635_preprocess_temp_amb(ambient_new_raw, ambient_old_raw,
+					   Gb);
+	kPG = ((s64)P_G * 1000000LL) >> 9ULL;
+	kPO = AMB - (((s64)P_O * 1000LL) >> 1ULL);
+
+	return 30 * 1000LL + div64_s64(kPO * 1000000LL, kPG);
+}
+
+static s32 mlx90635_calc_temp_object_iteration(s32 prev_object_temp, s64 object,
+					       s64 TAdut, s64 TAdut4, s16 Ga,
+					       u32 Fa, u16 Fa_scale, s16 Fb,
+					       s16 Ha, s16 Hb, u16 emissivity)
+{
+	s64 calcedGa, calcedGb, calcedFa, Alpha_corr;
+	s64 Ha_customer, Hb_customer;
+
+	Ha_customer = ((s64)Ha * 1000000LL) >> 14ULL;
+	Hb_customer = ((s64)Hb * 100) >> 10ULL;
+
+	calcedGa = ((s64)((s64)Ga * (prev_object_temp - 35 * 1000LL)
+			     * 1000LL)) >> 24LL;
+	calcedGb = ((s64)(Fb * (TAdut - 30 * 1000000LL))) >> 24LL;
+
+	Alpha_corr = ((s64)((s64)Fa * Ha_customer * 10000LL) >> Fa_scale);
+	Alpha_corr *= ((s64)(1 * 1000000LL + calcedGa + calcedGb));
+
+	Alpha_corr = div64_s64(Alpha_corr, 1000LL);
+	Alpha_corr *= emissivity;
+	Alpha_corr = div64_s64(Alpha_corr, 100LL);
+	calcedFa = div64_s64((s64)object * 100000000000LL, Alpha_corr);
+
+	return (int_sqrt64(int_sqrt64(calcedFa * 100000000LL + TAdut4))
+		- 27315 - Hb_customer) * 10;
+}
+
+static s64 mlx90635_calc_ta4(s64 TAdut, s64 scale)
+{
+	return (div64_s64(TAdut, scale) + 27315) *
+		(div64_s64(TAdut, scale) + 27315) *
+		(div64_s64(TAdut, scale) + 27315) *
+		(div64_s64(TAdut, scale) + 27315);
+}
+
+static s32 mlx90635_calc_temp_object(s64 object, s64 ambient, u32 Ea, u32 Eb,
+				     s16 Ga, u32 Fa, u16 Fa_scale, s16 Fb, s16 Ha, s16 Hb,
+				     u16 tmp_emi)
+{
+	s64 kTA, kTA0, TAdut, TAdut4;
+	s64 temp = 35000;
+	s8 i;
+
+	kTA = (Ea * 1000LL) >> 16LL;
+	kTA0 = (Eb * 1000LL) >> 8LL;
+	TAdut = div64_s64(((ambient - kTA0) * 1000000LL), kTA) + 30 * 1000000LL;
+	TAdut4 = mlx90635_calc_ta4(TAdut, 10000LL);
+
+	/* Iterations of calculation as described in datasheet */
+	for (i = 0; i < 5; ++i) {
+		temp = mlx90635_calc_temp_object_iteration(temp, object, TAdut, TAdut4,
+							   Ga, Fa, Fa_scale, Fb, Ha, Hb,
+							   tmp_emi);
+	}
+	return temp;
+}
+
+static int mlx90635_calc_object(struct mlx90635_data *data, int *val)
+{
+	s16 ambient_new_raw, ambient_old_raw, object_raw;
+	s16 Fb, Ga, Gb, Ha, Hb;
+	s64 object, ambient;
+	u32 Ea, Eb, Fa;
+	u16 Fa_scale;
+	int ret;
+
+	ret = mlx90635_read_ee_object(data->regmap_ee, &Ea, &Eb, &Fa, &Fb, &Ga, &Gb, &Ha, &Hb, &Fa_scale);
+	if (ret < 0)
+		return ret;
+
+	ret = mlx90635_read_all_channel(data,
+					&ambient_new_raw, &ambient_old_raw,
+					&object_raw);
+	if (ret < 0)
+		return ret;
+
+	ambient = mlx90635_preprocess_temp_amb(ambient_new_raw,
+					       ambient_old_raw, Gb);
+	object = mlx90635_preprocess_temp_obj(object_raw,
+					      ambient_new_raw,
+					      ambient_old_raw, Gb);
+
+	*val = mlx90635_calc_temp_object(object, ambient, Ea, Eb, Ga, Fa, Fa_scale, Fb,
+					 Ha, Hb, data->emissivity);
+	return 0;
+}
+
+static int mlx90635_calc_ambient(struct mlx90635_data *data, int *val)
+{
+	s16 ambient_new_raw, ambient_old_raw;
+	s16 PG, PO, Gb;
+	int ret;
+
+	ret = mlx90635_read_ee_ambient(data->regmap_ee, &PG, &PO, &Gb);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&data->lock);
+	if (data->powerstatus == MLX90635_PWR_STATUS_SLEEP_STEP) {
+		ret = mlx90635_perform_measurement_burst(data);
+		if (ret < 0)
+			goto read_ambient_unlock;
+	}
+
+	ret = mlx90635_read_ambient_raw(data->regmap, &ambient_new_raw,
+					&ambient_old_raw);
+read_ambient_unlock:
+	mutex_unlock(&data->lock);
+	if (ret < 0)
+		return ret;
+
+	*val = mlx90635_calc_temp_ambient(ambient_new_raw, ambient_old_raw,
+					  PG, PO, Gb);
+	return ret;
+}
+
+static int mlx90635_get_refresh_rate(struct mlx90635_data *data,
+				     unsigned int *refresh_rate)
+{
+	unsigned int reg;
+	int ret;
+
+	ret = regmap_read(data->regmap, MLX90635_REG_CTRL1, &reg);
+	if (ret < 0)
+		return ret;
+
+	*refresh_rate = FIELD_GET(MLX90635_CTRL1_REFRESH_RATE_MASK, reg);
+
+	return 0;
+}
+
+static const struct {
+	int val;
+	int val2;
+} mlx90635_freqs[] = {
+	{ 0, 200000 },
+	{ 0, 500000 },
+	{ 0, 900000 },
+	{ 1, 700000 },
+	{ 3, 0 },
+	{ 4, 800000 },
+	{ 6, 900000 },
+	{ 8, 900000 }
+};
+
+/**
+ * mlx90635_pm_interaction_wakeup() - Measure time between user interactions to change powermode
+ * @data: pointer to mlx90635_data object containing interaction_ts information
+ *
+ * Switch to continuous mode when interaction is faster than MLX90635_MEAS_MAX_TIME. Update the
+ * interaction_ts for each function call with the jiffies to enable measurement between function
+ * calls. Initial value of the interaction_ts needs to be set before this function call.
+ */
+static int mlx90635_pm_interaction_wakeup(struct mlx90635_data *data)
+{
+	unsigned long now;
+	int ret;
+
+	now = jiffies;
+	if (time_in_range(now, data->interaction_ts,
+			  data->interaction_ts +
+			  msecs_to_jiffies(MLX90635_MEAS_MAX_TIME + 100))) {
+		ret = mlx90635_pwr_continuous(data);
+		if (ret < 0)
+			return ret;
+	}
+
+	data->interaction_ts = now;
+
+	return 0;
+}
+
+static int mlx90635_read_raw(struct iio_dev *indio_dev,
+			     struct iio_chan_spec const *channel, int *val,
+			     int *val2, long mask)
+{
+	struct mlx90635_data *data = iio_priv(indio_dev);
+	int ret;
+	int cr;
+
+	pm_runtime_get_sync(&data->client->dev);
+	ret = mlx90635_pm_interaction_wakeup(data);
+	if (ret < 0)
+		goto mlx90635_read_raw_pm;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_PROCESSED:
+		switch (channel->channel2) {
+		case IIO_MOD_TEMP_AMBIENT:
+			ret = mlx90635_calc_ambient(data, val);
+			if (ret < 0)
+				goto mlx90635_read_raw_pm;
+
+			ret = IIO_VAL_INT;
+			break;
+		case IIO_MOD_TEMP_OBJECT:
+			ret = mlx90635_calc_object(data, val);
+			if (ret < 0)
+				goto mlx90635_read_raw_pm;
+
+			ret = IIO_VAL_INT;
+			break;
+		default:
+			ret = -EINVAL;
+			break;
+		}
+		break;
+	case IIO_CHAN_INFO_CALIBEMISSIVITY:
+		if (data->emissivity == 1000) {
+			*val = 1;
+			*val2 = 0;
+		} else {
+			*val = 0;
+			*val2 = data->emissivity * 1000;
+		}
+		ret = IIO_VAL_INT_PLUS_MICRO;
+		break;
+	case IIO_CHAN_INFO_SAMP_FREQ:
+		ret = mlx90635_get_refresh_rate(data, &cr);
+		if (ret < 0)
+			goto mlx90635_read_raw_pm;
+
+		*val = mlx90635_freqs[cr].val;
+		*val2 = mlx90635_freqs[cr].val2;
+		ret = IIO_VAL_INT_PLUS_MICRO;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+mlx90635_read_raw_pm:
+	pm_runtime_mark_last_busy(&data->client->dev);
+	pm_runtime_put_autosuspend(&data->client->dev);
+	return ret;
+}
+
+static int mlx90635_write_raw(struct iio_dev *indio_dev,
+			      struct iio_chan_spec const *channel, int val,
+			      int val2, long mask)
+{
+	struct mlx90635_data *data = iio_priv(indio_dev);
+	int ret;
+	int i;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_CALIBEMISSIVITY:
+		/* Confirm we are within 0 and 1.0 */
+		if (val < 0 || val2 < 0 || val > 1 ||
+		    (val == 1 && val2 != 0))
+			return -EINVAL;
+		data->emissivity = val * 1000 + val2 / 1000;
+		return 0;
+	case IIO_CHAN_INFO_SAMP_FREQ:
+		for (i = 0; i < ARRAY_SIZE(mlx90635_freqs); i++) {
+			if (val == mlx90635_freqs[i].val &&
+			    val2 == mlx90635_freqs[i].val2)
+				break;
+		}
+		if (i == ARRAY_SIZE(mlx90635_freqs))
+			return -EINVAL;
+
+		ret = regmap_write_bits(data->regmap, MLX90635_REG_CTRL1,
+					MLX90635_CTRL1_REFRESH_RATE_MASK, i);
+
+		return ret;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int mlx90635_read_avail(struct iio_dev *indio_dev,
+			       struct iio_chan_spec const *chan,
+			       const int **vals, int *type, int *length,
+			       long mask)
+{
+	switch (mask) {
+	case IIO_CHAN_INFO_SAMP_FREQ:
+		*vals = (int *)mlx90635_freqs;
+		*type = IIO_VAL_INT_PLUS_MICRO;
+		*length = 2 * ARRAY_SIZE(mlx90635_freqs);
+		return IIO_AVAIL_LIST;
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct iio_chan_spec mlx90635_channels[] = {
+	{
+		.type = IIO_TEMP,
+		.modified = 1,
+		.channel2 = IIO_MOD_TEMP_AMBIENT,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED),
+		.info_mask_shared_by_all = BIT(IIO_CHAN_INFO_SAMP_FREQ),
+		.info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_SAMP_FREQ),
+	},
+	{
+		.type = IIO_TEMP,
+		.modified = 1,
+		.channel2 = IIO_MOD_TEMP_OBJECT,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED) |
+			BIT(IIO_CHAN_INFO_CALIBEMISSIVITY),
+		.info_mask_shared_by_all = BIT(IIO_CHAN_INFO_SAMP_FREQ),
+		.info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_SAMP_FREQ),
+	},
+};
+
+static const struct iio_info mlx90635_info = {
+	.read_raw = mlx90635_read_raw,
+	.write_raw = mlx90635_write_raw,
+	.read_avail = mlx90635_read_avail,
+};
+
+static void mlx90635_sleep(void *_data)
+{
+	struct mlx90635_data *data = _data;
+
+	mlx90635_pwr_sleep_step(data);
+}
+
+static int mlx90635_suspend(struct mlx90635_data *data)
+{
+	return mlx90635_pwr_sleep_step(data);
+}
+
+static int mlx90635_wakeup(struct mlx90635_data *data)
+{
+	s16 Fb, Ga, Gb, Ha, Hb, PG, PO;
+	unsigned int dsp_version;
+	u32 Ea, Eb, Fa;
+	u16 Fa_scale;
+	int ret;
+
+	regcache_cache_bypass(data->regmap_ee, false);
+	regcache_cache_only(data->regmap_ee, false);
+	regcache_cache_only(data->regmap, false);
+
+	ret = mlx90635_pwr_continuous(data);
+	if (ret < 0) {
+		dev_err(&data->client->dev, "Switch to continuous mode failed\n");
+		return ret;
+	}
+	ret = regmap_write_bits(data->regmap, MLX90635_REG_EE,
+				MLX90635_EE_ACTIVE, MLX90635_EE_ACTIVE);
+	if (ret < 0) {
+		dev_err(&data->client->dev, "Powering EEPROM failed\n");
+		return ret;
+	}
+	usleep_range(MLX90635_TIMING_EE_ACTIVE_MIN, MLX90635_TIMING_EE_ACTIVE_MAX);
+
+	regcache_mark_dirty(data->regmap_ee);
+
+	ret = regcache_sync(data->regmap_ee);
+	if (ret < 0) {
+		dev_err(&data->client->dev,
+			"Failed to sync cache: %d\n", ret);
+		return ret;
+	}
+
+	ret = mlx90635_read_ee_ambient(data->regmap_ee, &PG, &PO, &Gb);
+	if (ret < 0) {
+		dev_err(&data->client->dev,
+			"Failed to read to cache Ambient coefficients EEPROM region: %d\n", ret);
+		return ret;
+	}
+
+	ret = mlx90635_read_ee_object(data->regmap_ee, &Ea, &Eb, &Fa, &Fb, &Ga, &Gb, &Ha, &Hb, &Fa_scale);
+	if (ret < 0) {
+		dev_err(&data->client->dev,
+			"Failed to read to cache Object coefficients EEPROM region: %d\n", ret);
+		return ret;
+	}
+
+	ret = regmap_read(data->regmap_ee, MLX90635_EE_VERSION, &dsp_version);
+	if (ret < 0) {
+		dev_err(&data->client->dev,
+			"Failed to read to cache of EEPROM version: %d\n", ret);
+		return ret;
+	}
+
+	regcache_cache_only(data->regmap_ee, true);
+
+	return ret;
+}
+
+static void mlx90635_disable_regulator(void *_data)
+{
+	struct mlx90635_data *data = _data;
+	int ret;
+
+	ret = regulator_disable(data->regulator);
+	if (ret < 0)
+		dev_err(regmap_get_device(data->regmap),
+			"Failed to disable power regulator: %d\n", ret);
+}
+
+static int mlx90635_enable_regulator(struct mlx90635_data *data)
+{
+	int ret;
+
+	ret = regulator_enable(data->regulator);
+	if (ret < 0) {
+		dev_err(regmap_get_device(data->regmap), "Failed to enable power regulator!\n");
+		return ret;
+	}
+
+	mlx90635_reset_delay();
+
+	return ret;
+}
+
+static int mlx90635_probe(struct i2c_client *client)
+{
+	struct mlx90635_data *mlx90635;
+	struct iio_dev *indio_dev;
+	unsigned int dsp_version;
+	struct regmap *regmap;
+	struct regmap *regmap_ee;
+	int ret;
+
+	indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*mlx90635));
+	if (!indio_dev)
+		return dev_err_probe(&client->dev, -ENOMEM, "failed to allocate device\n");
+
+	regmap = devm_regmap_init_i2c(client, &mlx90635_regmap);
+	if (IS_ERR(regmap))
+		return dev_err_probe(&client->dev, PTR_ERR(regmap),
+				     "failed to allocate regmap\n");
+
+	regmap_ee = devm_regmap_init_i2c(client, &mlx90635_regmap_ee);
+	if (IS_ERR(regmap))
+		return dev_err_probe(&client->dev, PTR_ERR(regmap),
+				     "failed to allocate regmap\n");
+
+	mlx90635 = iio_priv(indio_dev);
+	i2c_set_clientdata(client, indio_dev);
+	mlx90635->client = client;
+	mlx90635->regmap = regmap;
+	mlx90635->regmap_ee = regmap_ee;
+	mlx90635->powerstatus = MLX90635_PWR_STATUS_SLEEP_STEP;
+
+	mutex_init(&mlx90635->lock);
+	indio_dev->name = "mlx90635";
+	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->info = &mlx90635_info;
+	indio_dev->channels = mlx90635_channels;
+	indio_dev->num_channels = ARRAY_SIZE(mlx90635_channels);
+
+	mlx90635->regulator = devm_regulator_get(&client->dev, "vdd");
+	if (IS_ERR(mlx90635->regulator))
+		return dev_err_probe(&client->dev, PTR_ERR(mlx90635->regulator),
+				     "failed to get vdd regulator");
+
+	ret = mlx90635_enable_regulator(mlx90635);
+	if (ret < 0)
+		return ret;
+
+	ret = devm_add_action_or_reset(&client->dev, mlx90635_disable_regulator,
+				       mlx90635);
+	if (ret < 0)
+		return dev_err_probe(&client->dev, ret,
+				     "failed to setup regulator cleanup action\n");
+
+	ret = mlx90635_wakeup(mlx90635);
+	if (ret < 0)
+		return dev_err_probe(&client->dev, ret, "wakeup failed\n");
+
+	ret = devm_add_action_or_reset(&client->dev, mlx90635_sleep, mlx90635);
+	if (ret < 0)
+		return dev_err_probe(&client->dev, ret,
+				     "failed to setup low power cleanup\n");
+
+	ret = regmap_read(mlx90635->regmap_ee, MLX90635_EE_VERSION, &dsp_version);
+	if (ret < 0)
+		return dev_err_probe(&client->dev, ret, "read of version failed\n");
+
+	dsp_version = dsp_version & MLX90635_VERSION_MASK;
+
+	if (FIELD_GET(MLX90635_DSP_FIXED, dsp_version)) {
+		if (MLX90635_DSP_VERSION(dsp_version) == MLX90635_ID_DSPv1) {
+			dev_dbg(&client->dev,
+				"Detected DSP v1 calibration %x\n", dsp_version);
+		} else {
+			dev_dbg(&client->dev,
+				"Detected Unknown EEPROM calibration %lx\n",
+				MLX90635_DSP_VERSION(dsp_version));
+		}
+	} else {
+		return dev_err_probe(&client->dev, -EPROTONOSUPPORT,
+			"Wrong fixed top bit %x (expected 0x8X0X)\n",
+			dsp_version);
+	}
+
+	mlx90635->emissivity = 1000;
+	mlx90635->interaction_ts = jiffies; /* Set initial value */
+
+	pm_runtime_get_noresume(&client->dev);
+	pm_runtime_set_active(&client->dev);
+
+	ret = devm_pm_runtime_enable(&client->dev);
+	if (ret)
+		return dev_err_probe(&client->dev, ret,
+				     "failed to enable powermanagement\n");
+
+	pm_runtime_set_autosuspend_delay(&client->dev, MLX90635_SLEEP_DELAY_MS);
+	pm_runtime_use_autosuspend(&client->dev);
+	pm_runtime_put_autosuspend(&client->dev);
+
+	return devm_iio_device_register(&client->dev, indio_dev);
+}
+
+static const struct i2c_device_id mlx90635_id[] = {
+	{ "mlx90635" },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, mlx90635_id);
+
+static const struct of_device_id mlx90635_of_match[] = {
+	{ .compatible = "melexis,mlx90635" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, mlx90635_of_match);
+
+static int mlx90635_pm_suspend(struct device *dev)
+{
+	struct mlx90635_data *data = iio_priv(dev_get_drvdata(dev));
+	int ret;
+
+	ret = mlx90635_suspend(data);
+	if (ret < 0)
+		return ret;
+
+	ret = regulator_disable(data->regulator);
+	if (ret < 0)
+		dev_err(regmap_get_device(data->regmap),
+			"Failed to disable power regulator: %d\n", ret);
+
+	return ret;
+}
+
+static int mlx90635_pm_resume(struct device *dev)
+{
+	struct mlx90635_data *data = iio_priv(dev_get_drvdata(dev));
+	int ret;
+
+	ret = mlx90635_enable_regulator(data);
+	if (ret < 0)
+		return ret;
+
+	return mlx90635_wakeup(data);
+}
+
+static int mlx90635_pm_runtime_suspend(struct device *dev)
+{
+	struct mlx90635_data *data = iio_priv(dev_get_drvdata(dev));
+
+	return mlx90635_pwr_sleep_step(data);
+}
+
+static const struct dev_pm_ops mlx90635_pm_ops = {
+	SYSTEM_SLEEP_PM_OPS(mlx90635_pm_suspend, mlx90635_pm_resume)
+	RUNTIME_PM_OPS(mlx90635_pm_runtime_suspend, NULL, NULL)
+};
+
+static struct i2c_driver mlx90635_driver = {
+	.driver = {
+		.name	= "mlx90635",
+		.of_match_table = mlx90635_of_match,
+		.pm	= pm_ptr(&mlx90635_pm_ops),
+	},
+	.probe = mlx90635_probe,
+	.id_table = mlx90635_id,
+};
+module_i2c_driver(mlx90635_driver);
+
+MODULE_AUTHOR("Crt Mori <cmo@melexis.com>");
+MODULE_DESCRIPTION("Melexis MLX90635 contactless Infra Red temperature sensor driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 824349659d69..ce9c5bae83bf 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -401,6 +401,10 @@ static void bnxt_re_create_fence_wqe(struct bnxt_re_pd *pd)
 	struct bnxt_re_fence_data *fence = &pd->fence;
 	struct ib_mr *ib_mr = &fence->mr->ib_mr;
 	struct bnxt_qplib_swqe *wqe = &fence->bind_wqe;
+	struct bnxt_re_dev *rdev = pd->rdev;
+
+	if (bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx))
+		return;
 
 	memset(wqe, 0, sizeof(*wqe));
 	wqe->type = BNXT_QPLIB_SWQE_TYPE_BIND_MW;
@@ -455,6 +459,9 @@ static void bnxt_re_destroy_fence_mr(struct bnxt_re_pd *pd)
 	struct device *dev = &rdev->en_dev->pdev->dev;
 	struct bnxt_re_mr *mr = fence->mr;
 
+	if (bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx))
+		return;
+
 	if (fence->mw) {
 		bnxt_re_dealloc_mw(fence->mw);
 		fence->mw = NULL;
@@ -486,6 +493,9 @@ static int bnxt_re_create_fence_mr(struct bnxt_re_pd *pd)
 	struct ib_mw *mw;
 	int rc;
 
+	if (bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx))
+		return 0;
+
 	dma_addr = dma_map_single(dev, fence->va, BNXT_RE_FENCE_BYTES,
 				  DMA_BIDIRECTIONAL);
 	rc = dma_mapping_error(dev, dma_addr);
@@ -1817,7 +1827,7 @@ int bnxt_re_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr,
 	switch (srq_attr_mask) {
 	case IB_SRQ_MAX_WR:
 		/* SRQ resize is not supported */
-		break;
+		return -EINVAL;
 	case IB_SRQ_LIMIT:
 		/* Change the SRQ threshold */
 		if (srq_attr->srq_limit > srq->qplib_srq.max_wqe)
@@ -1832,13 +1842,12 @@ int bnxt_re_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr,
 		/* On success, update the shadow */
 		srq->srq_limit = srq_attr->srq_limit;
 		/* No need to Build and send response back to udata */
-		break;
+		return 0;
 	default:
 		ibdev_err(&rdev->ibdev,
 			  "Unsupported srq_attr_mask 0x%x", srq_attr_mask);
 		return -EINVAL;
 	}
-	return 0;
 }
 
 int bnxt_re_query_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr)
@@ -2556,11 +2565,6 @@ static int bnxt_re_build_inv_wqe(const struct ib_send_wr *wr,
 	wqe->type = BNXT_QPLIB_SWQE_TYPE_LOCAL_INV;
 	wqe->local_inv.inv_l_key = wr->ex.invalidate_rkey;
 
-	/* Need unconditional fence for local invalidate
-	 * opcode to work as expected.
-	 */
-	wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE;
-
 	if (wr->send_flags & IB_SEND_SIGNALED)
 		wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP;
 	if (wr->send_flags & IB_SEND_SOLICITED)
@@ -2583,12 +2587,6 @@ static int bnxt_re_build_reg_wqe(const struct ib_reg_wr *wr,
 	wqe->frmr.levels = qplib_frpl->hwq.level;
 	wqe->type = BNXT_QPLIB_SWQE_TYPE_REG_MR;
 
-	/* Need unconditional fence for reg_mr
-	 * opcode to function as expected.
-	 */
-
-	wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE;
-
 	if (wr->wr.send_flags & IB_SEND_SIGNALED)
 		wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP;
 
@@ -2719,6 +2717,18 @@ bad:
 	return rc;
 }
 
+static void bnxt_re_legacy_set_uc_fence(struct bnxt_qplib_swqe *wqe)
+{
+	/* Need unconditional fence for non-wire memory opcode
+	 * to work as expected.
+	 */
+	if (wqe->type == BNXT_QPLIB_SWQE_TYPE_LOCAL_INV ||
+	    wqe->type == BNXT_QPLIB_SWQE_TYPE_FAST_REG_MR ||
+	    wqe->type == BNXT_QPLIB_SWQE_TYPE_REG_MR ||
+	    wqe->type == BNXT_QPLIB_SWQE_TYPE_BIND_MW)
+		wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE;
+}
+
 int bnxt_re_post_send(struct ib_qp *ib_qp, const struct ib_send_wr *wr,
 		      const struct ib_send_wr **bad_wr)
 {
@@ -2798,8 +2808,11 @@ int bnxt_re_post_send(struct ib_qp *ib_qp, const struct ib_send_wr *wr,
 			rc = -EINVAL;
 			goto bad;
 		}
-		if (!rc)
+		if (!rc) {
+			if (!bnxt_qplib_is_chip_gen_p5_p7(qp->rdev->chip_ctx))
+				bnxt_re_legacy_set_uc_fence(&wqe);
 			rc = bnxt_qplib_post_send(&qp->qplib_qp, &wqe);
+		}
 bad:
 		if (rc) {
 			ibdev_err(&qp->rdev->ibdev,
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index f022c922fae5..54b4d2f3a5d8 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -280,9 +280,6 @@ static void bnxt_re_set_resource_limits(struct bnxt_re_dev *rdev)
 
 static void bnxt_re_vf_res_config(struct bnxt_re_dev *rdev)
 {
-
-	if (test_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags))
-		return;
 	rdev->num_vfs = pci_sriov_get_totalvfs(rdev->en_dev->pdev);
 	if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) {
 		bnxt_re_set_resource_limits(rdev);
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index c98e04fe2ddd..439d0c7c5d0c 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -744,7 +744,8 @@ int bnxt_qplib_query_srq(struct bnxt_qplib_res *res,
 	bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, &sbuf, sizeof(req),
 				sizeof(resp), 0);
 	rc = bnxt_qplib_rcfw_send_message(rcfw, &msg);
-	srq->threshold = le16_to_cpu(sb->srq_limit);
+	if (!rc)
+		srq->threshold = le16_to_cpu(sb->srq_limit);
 	dma_free_coherent(&rcfw->pdev->dev, sbuf.size,
 			  sbuf.sb, sbuf.dma_addr);
 
diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c
index 68c621ff59d0..5a91cbda4aee 100644
--- a/drivers/infiniband/hw/hfi1/pio.c
+++ b/drivers/infiniband/hw/hfi1/pio.c
@@ -2086,7 +2086,7 @@ int init_credit_return(struct hfi1_devdata *dd)
 				   "Unable to allocate credit return DMA range for NUMA %d\n",
 				   i);
 			ret = -ENOMEM;
-			goto done;
+			goto free_cr_base;
 		}
 	}
 	set_dev_node(&dd->pcidev->dev, dd->node);
@@ -2094,6 +2094,10 @@ int init_credit_return(struct hfi1_devdata *dd)
 	ret = 0;
 done:
 	return ret;
+
+free_cr_base:
+	free_credit_return(dd);
+	goto done;
 }
 
 void free_credit_return(struct hfi1_devdata *dd)
diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c
index 6e5ac2023328..b67d23b1f286 100644
--- a/drivers/infiniband/hw/hfi1/sdma.c
+++ b/drivers/infiniband/hw/hfi1/sdma.c
@@ -3158,7 +3158,7 @@ int _pad_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx)
 {
 	int rval = 0;
 
-	if ((unlikely(tx->num_desc + 1 == tx->desc_limit))) {
+	if ((unlikely(tx->num_desc == tx->desc_limit))) {
 		rval = _extend_sdma_tx_descs(dd, tx);
 		if (rval) {
 			__sdma_txclean(dd, tx);
diff --git a/drivers/infiniband/hw/irdma/defs.h b/drivers/infiniband/hw/irdma/defs.h
index 8fb752f2eda2..2cb4b96db721 100644
--- a/drivers/infiniband/hw/irdma/defs.h
+++ b/drivers/infiniband/hw/irdma/defs.h
@@ -346,6 +346,7 @@ enum irdma_cqp_op_type {
 #define IRDMA_AE_LLP_TOO_MANY_KEEPALIVE_RETRIES				0x050b
 #define IRDMA_AE_LLP_DOUBT_REACHABILITY					0x050c
 #define IRDMA_AE_LLP_CONNECTION_ESTABLISHED				0x050e
+#define IRDMA_AE_LLP_TOO_MANY_RNRS					0x050f
 #define IRDMA_AE_RESOURCE_EXHAUSTION					0x0520
 #define IRDMA_AE_RESET_SENT						0x0601
 #define IRDMA_AE_TERMINATE_SENT						0x0602
diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c
index bd4b2b896444..ad50b77282f8 100644
--- a/drivers/infiniband/hw/irdma/hw.c
+++ b/drivers/infiniband/hw/irdma/hw.c
@@ -387,6 +387,7 @@ static void irdma_process_aeq(struct irdma_pci_f *rf)
 		case IRDMA_AE_LLP_TOO_MANY_RETRIES:
 		case IRDMA_AE_LCE_QP_CATASTROPHIC:
 		case IRDMA_AE_LCE_FUNCTION_CATASTROPHIC:
+		case IRDMA_AE_LLP_TOO_MANY_RNRS:
 		case IRDMA_AE_LCE_CQ_CATASTROPHIC:
 		case IRDMA_AE_UDA_XMIT_DGRAM_TOO_LONG:
 		default:
@@ -570,6 +571,13 @@ static void irdma_destroy_irq(struct irdma_pci_f *rf,
 	dev->irq_ops->irdma_dis_irq(dev, msix_vec->idx);
 	irq_update_affinity_hint(msix_vec->irq, NULL);
 	free_irq(msix_vec->irq, dev_id);
+	if (rf == dev_id) {
+		tasklet_kill(&rf->dpc_tasklet);
+	} else {
+		struct irdma_ceq *iwceq = (struct irdma_ceq *)dev_id;
+
+		tasklet_kill(&iwceq->dpc_tasklet);
+	}
 }
 
 /**
diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index b5eb8d421988..0b046c061742 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -839,7 +839,9 @@ static int irdma_validate_qp_attrs(struct ib_qp_init_attr *init_attr,
 
 	if (init_attr->cap.max_inline_data > uk_attrs->max_hw_inline ||
 	    init_attr->cap.max_send_sge > uk_attrs->max_hw_wq_frags ||
-	    init_attr->cap.max_recv_sge > uk_attrs->max_hw_wq_frags)
+	    init_attr->cap.max_recv_sge > uk_attrs->max_hw_wq_frags ||
+	    init_attr->cap.max_send_wr > uk_attrs->max_hw_wq_quanta ||
+	    init_attr->cap.max_recv_wr > uk_attrs->max_hw_rq_quanta)
 		return -EINVAL;
 
 	if (rdma_protocol_roce(&iwdev->ibdev, 1)) {
@@ -2184,9 +2186,8 @@ static int irdma_create_cq(struct ib_cq *ibcq,
 		info.cq_base_pa = iwcq->kmem.pa;
 	}
 
-	if (dev->hw_attrs.uk_attrs.hw_rev >= IRDMA_GEN_2)
-		info.shadow_read_threshold = min(info.cq_uk_init_info.cq_size / 2,
-						 (u32)IRDMA_MAX_CQ_READ_THRESH);
+	info.shadow_read_threshold = min(info.cq_uk_init_info.cq_size / 2,
+					 (u32)IRDMA_MAX_CQ_READ_THRESH);
 
 	if (irdma_sc_cq_init(cq, &info)) {
 		ibdev_dbg(&iwdev->ibdev, "VERBS: init cq fail\n");
diff --git a/drivers/infiniband/hw/mlx5/cong.c b/drivers/infiniband/hw/mlx5/cong.c
index f87531318feb..a78a067e3ce7 100644
--- a/drivers/infiniband/hw/mlx5/cong.c
+++ b/drivers/infiniband/hw/mlx5/cong.c
@@ -458,6 +458,12 @@ void mlx5_ib_init_cong_debugfs(struct mlx5_ib_dev *dev, u32 port_num)
 	dbg_cc_params->root = debugfs_create_dir("cc_params", mlx5_debugfs_get_dev_root(mdev));
 
 	for (i = 0; i < MLX5_IB_DBG_CC_MAX; i++) {
+		if ((i == MLX5_IB_DBG_CC_GENERAL_RTT_RESP_DSCP_VALID ||
+		     i == MLX5_IB_DBG_CC_GENERAL_RTT_RESP_DSCP))
+			if (!MLX5_CAP_GEN(mdev, roce) ||
+			    !MLX5_CAP_ROCE(mdev, roce_cc_general))
+				continue;
+
 		dbg_cc_params->params[i].offset = i;
 		dbg_cc_params->params[i].dev = dev;
 		dbg_cc_params->params[i].port_num = port_num;
diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index 869369cb5b5f..253fea374a72 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -2949,7 +2949,7 @@ DECLARE_UVERBS_NAMED_METHOD(
 	MLX5_IB_METHOD_DEVX_OBJ_MODIFY,
 	UVERBS_ATTR_IDR(MLX5_IB_ATTR_DEVX_OBJ_MODIFY_HANDLE,
 			UVERBS_IDR_ANY_OBJECT,
-			UVERBS_ACCESS_WRITE,
+			UVERBS_ACCESS_READ,
 			UA_MANDATORY),
 	UVERBS_ATTR_PTR_IN(
 		MLX5_IB_ATTR_DEVX_OBJ_MODIFY_CMD_IN,
diff --git a/drivers/infiniband/hw/mlx5/wr.c b/drivers/infiniband/hw/mlx5/wr.c
index df1d1b0a3ef7..9947feb7fb8a 100644
--- a/drivers/infiniband/hw/mlx5/wr.c
+++ b/drivers/infiniband/hw/mlx5/wr.c
@@ -78,7 +78,7 @@ static void set_eth_seg(const struct ib_send_wr *wr, struct mlx5_ib_qp *qp,
 		 */
 		copysz = min_t(u64, *cur_edge - (void *)eseg->inline_hdr.start,
 			       left);
-		memcpy(eseg->inline_hdr.start, pdata, copysz);
+		memcpy(eseg->inline_hdr.data, pdata, copysz);
 		stride = ALIGN(sizeof(struct mlx5_wqe_eth_seg) -
 			       sizeof(eseg->inline_hdr.start) + copysz, 16);
 		*size += stride / 16;
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 7887a6786ed4..f118ce0a9a61 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -1879,8 +1879,17 @@ static int qedr_create_user_qp(struct qedr_dev *dev,
 		/* RQ - read access only (0) */
 		rc = qedr_init_user_queue(udata, dev, &qp->urq, ureq.rq_addr,
 					  ureq.rq_len, true, 0, alloc_and_init);
-		if (rc)
+		if (rc) {
+			ib_umem_release(qp->usq.umem);
+			qp->usq.umem = NULL;
+			if (rdma_protocol_roce(&dev->ibdev, 1)) {
+				qedr_free_pbl(dev, &qp->usq.pbl_info,
+					      qp->usq.pbl_tbl);
+			} else {
+				kfree(qp->usq.pbl_tbl);
+			}
 			return rc;
+		}
 	}
 
 	memset(&in_params, 0, sizeof(in_params));
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 58f70cfec45a..040234c01be4 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -79,12 +79,16 @@ module_param(srpt_srq_size, int, 0444);
 MODULE_PARM_DESC(srpt_srq_size,
 		 "Shared receive queue (SRQ) size.");
 
+static int srpt_set_u64_x(const char *buffer, const struct kernel_param *kp)
+{
+	return kstrtou64(buffer, 16, (u64 *)kp->arg);
+}
 static int srpt_get_u64_x(char *buffer, const struct kernel_param *kp)
 {
 	return sprintf(buffer, "0x%016llx\n", *(u64 *)kp->arg);
 }
-module_param_call(srpt_service_guid, NULL, srpt_get_u64_x, &srpt_service_guid,
-		  0444);
+module_param_call(srpt_service_guid, srpt_set_u64_x, srpt_get_u64_x,
+		  &srpt_service_guid, 0444);
 MODULE_PARM_DESC(srpt_service_guid,
 		 "Using this value for ioc_guid, id_ext, and cm_listen_id instead of using the node_guid of the first HCA.");
 
@@ -210,10 +214,12 @@ static const char *get_ch_state_name(enum rdma_ch_state s)
 /**
  * srpt_qp_event - QP event callback function
  * @event: Description of the event that occurred.
- * @ch: SRPT RDMA channel.
+ * @ptr: SRPT RDMA channel.
  */
-static void srpt_qp_event(struct ib_event *event, struct srpt_rdma_ch *ch)
+static void srpt_qp_event(struct ib_event *event, void *ptr)
 {
+	struct srpt_rdma_ch *ch = ptr;
+
 	pr_debug("QP event %d on ch=%p sess_name=%s-%d state=%s\n",
 		 event->event, ch, ch->sess_name, ch->qp->qp_num,
 		 get_ch_state_name(ch->state));
@@ -1807,8 +1813,7 @@ retry:
 	ch->cq_size = ch->rq_size + sq_size;
 
 	qp_init->qp_context = (void *)ch;
-	qp_init->event_handler
-		= (void(*)(struct ib_event *, void*))srpt_qp_event;
+	qp_init->event_handler = srpt_qp_event;
 	qp_init->send_cq = ch->cq;
 	qp_init->recv_cq = ch->cq;
 	qp_init->sq_sig_type = IB_SIGNAL_REQ_WR;
diff --git a/drivers/input/input.c b/drivers/input/input.c
index 8c5fdb0f858a..f71ea4fb173f 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -1365,8 +1365,8 @@ static ssize_t input_dev_show_##name(struct device *dev,		\
 {									\
 	struct input_dev *input_dev = to_input_dev(dev);		\
 									\
-	return scnprintf(buf, PAGE_SIZE, "%s\n",			\
-			 input_dev->name ? input_dev->name : "");	\
+	return sysfs_emit(buf, "%s\n",					\
+			  input_dev->name ? input_dev->name : "");	\
 }									\
 static DEVICE_ATTR(name, S_IRUGO, input_dev_show_##name, NULL)
 
@@ -1458,7 +1458,7 @@ static ssize_t inhibited_show(struct device *dev,
 {
 	struct input_dev *input_dev = to_input_dev(dev);
 
-	return scnprintf(buf, PAGE_SIZE, "%d\n", input_dev->inhibited);
+	return sysfs_emit(buf, "%d\n", input_dev->inhibited);
 }
 
 static ssize_t inhibited_store(struct device *dev,
@@ -1505,7 +1505,7 @@ static ssize_t input_dev_show_id_##name(struct device *dev,		\
 					char *buf)			\
 {									\
 	struct input_dev *input_dev = to_input_dev(dev);		\
-	return scnprintf(buf, PAGE_SIZE, "%04x\n", input_dev->id.name);	\
+	return sysfs_emit(buf, "%04x\n", input_dev->id.name);		\
 }									\
 static DEVICE_ATTR(name, S_IRUGO, input_dev_show_id_##name, NULL)
 
diff --git a/drivers/input/joystick/Kconfig b/drivers/input/joystick/Kconfig
index ac6925ce8366..7755e5b454d2 100644
--- a/drivers/input/joystick/Kconfig
+++ b/drivers/input/joystick/Kconfig
@@ -412,4 +412,14 @@ config JOYSTICK_SENSEHAT
 	  To compile this driver as a module, choose M here: the
 	  module will be called sensehat_joystick.
 
+config JOYSTICK_SEESAW
+	tristate "Adafruit Mini I2C Gamepad with Seesaw"
+	depends on I2C
+	select INPUT_SPARSEKMAP
+	help
+	  Say Y here if you want to use the Adafruit Mini I2C Gamepad.
+
+	  To compile this driver as a module, choose M here: the module will be
+	  called adafruit-seesaw.
+
 endif
diff --git a/drivers/input/joystick/Makefile b/drivers/input/joystick/Makefile
index 3937535f0098..9976f596a920 100644
--- a/drivers/input/joystick/Makefile
+++ b/drivers/input/joystick/Makefile
@@ -28,6 +28,7 @@ obj-$(CONFIG_JOYSTICK_N64)		+= n64joy.o
 obj-$(CONFIG_JOYSTICK_PSXPAD_SPI)	+= psxpad-spi.o
 obj-$(CONFIG_JOYSTICK_PXRC)		+= pxrc.o
 obj-$(CONFIG_JOYSTICK_QWIIC)		+= qwiic-joystick.o
+obj-$(CONFIG_JOYSTICK_SEESAW)		+= adafruit-seesaw.o
 obj-$(CONFIG_JOYSTICK_SENSEHAT)	+= sensehat-joystick.o
 obj-$(CONFIG_JOYSTICK_SIDEWINDER)	+= sidewinder.o
 obj-$(CONFIG_JOYSTICK_SPACEBALL)	+= spaceball.o
diff --git a/drivers/input/joystick/adafruit-seesaw.c b/drivers/input/joystick/adafruit-seesaw.c
new file mode 100644
index 000000000000..1b9279f024cc
--- /dev/null
+++ b/drivers/input/joystick/adafruit-seesaw.c
@@ -0,0 +1,315 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2023 Anshul Dalal <anshulusr@gmail.com>
+ *
+ * Driver for Adafruit Mini I2C Gamepad
+ *
+ * Based on the work of:
+ *	Oleh Kravchenko (Sparkfun Qwiic Joystick driver)
+ *
+ * Datasheet: https://cdn-learn.adafruit.com/downloads/pdf/gamepad-qt.pdf
+ * Product page: https://www.adafruit.com/product/5743
+ * Firmware and hardware sources: https://github.com/adafruit/Adafruit_Seesaw
+ *
+ * TODO:
+ *	- Add interrupt support
+ */
+
+#include <asm/unaligned.h>
+#include <linux/bits.h>
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/input.h>
+#include <linux/input/sparse-keymap.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#define SEESAW_DEVICE_NAME		"seesaw-gamepad"
+
+#define SEESAW_ADC_BASE			0x0900
+
+#define SEESAW_GPIO_DIRCLR_BULK		0x0103
+#define SEESAW_GPIO_BULK		0x0104
+#define SEESAW_GPIO_BULK_SET		0x0105
+#define SEESAW_GPIO_PULLENSET		0x010b
+
+#define SEESAW_STATUS_HW_ID		0x0001
+#define SEESAW_STATUS_SWRST		0x007f
+
+#define SEESAW_ADC_OFFSET		0x07
+
+#define SEESAW_BUTTON_A			0x05
+#define SEESAW_BUTTON_B			0x01
+#define SEESAW_BUTTON_X			0x06
+#define SEESAW_BUTTON_Y			0x02
+#define SEESAW_BUTTON_START		0x10
+#define SEESAW_BUTTON_SELECT		0x00
+
+#define SEESAW_ANALOG_X			0x0e
+#define SEESAW_ANALOG_Y			0x0f
+
+#define SEESAW_JOYSTICK_MAX_AXIS	1023
+#define SEESAW_JOYSTICK_FUZZ		2
+#define SEESAW_JOYSTICK_FLAT		4
+
+#define SEESAW_GAMEPAD_POLL_INTERVAL_MS	16
+#define SEESAW_GAMEPAD_POLL_MIN		8
+#define SEESAW_GAMEPAD_POLL_MAX		32
+
+static const unsigned long SEESAW_BUTTON_MASK =
+	BIT(SEESAW_BUTTON_A) | BIT(SEESAW_BUTTON_B) | BIT(SEESAW_BUTTON_X) |
+	BIT(SEESAW_BUTTON_Y) | BIT(SEESAW_BUTTON_START) |
+	BIT(SEESAW_BUTTON_SELECT);
+
+struct seesaw_gamepad {
+	struct input_dev *input_dev;
+	struct i2c_client *i2c_client;
+};
+
+struct seesaw_data {
+	u16 x;
+	u16 y;
+	u32 button_state;
+};
+
+static const struct key_entry seesaw_buttons_new[] = {
+	{ KE_KEY, SEESAW_BUTTON_A, .keycode = BTN_SOUTH },
+	{ KE_KEY, SEESAW_BUTTON_B, .keycode = BTN_EAST },
+	{ KE_KEY, SEESAW_BUTTON_X, .keycode = BTN_NORTH },
+	{ KE_KEY, SEESAW_BUTTON_Y, .keycode = BTN_WEST },
+	{ KE_KEY, SEESAW_BUTTON_START, .keycode = BTN_START },
+	{ KE_KEY, SEESAW_BUTTON_SELECT, .keycode = BTN_SELECT },
+	{ KE_END, 0 }
+};
+
+static int seesaw_register_read(struct i2c_client *client, u16 reg, void *buf,
+				int count)
+{
+	__be16 register_buf = cpu_to_be16(reg);
+	struct i2c_msg message_buf[2] = {
+		{
+			.addr = client->addr,
+			.flags = client->flags,
+			.len = sizeof(register_buf),
+			.buf = (u8 *)&register_buf,
+		},
+		{
+			.addr = client->addr,
+			.flags = client->flags | I2C_M_RD,
+			.len = count,
+			.buf = (u8 *)buf,
+		},
+	};
+	int ret;
+
+	ret = i2c_transfer(client->adapter, message_buf,
+			   ARRAY_SIZE(message_buf));
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int seesaw_register_write_u8(struct i2c_client *client, u16 reg,
+				    u8 value)
+{
+	u8 write_buf[sizeof(reg) + sizeof(value)];
+	int ret;
+
+	put_unaligned_be16(reg, write_buf);
+	write_buf[sizeof(reg)] = value;
+
+	ret = i2c_master_send(client, write_buf, sizeof(write_buf));
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int seesaw_register_write_u32(struct i2c_client *client, u16 reg,
+				     u32 value)
+{
+	u8 write_buf[sizeof(reg) + sizeof(value)];
+	int ret;
+
+	put_unaligned_be16(reg, write_buf);
+	put_unaligned_be32(value, write_buf + sizeof(reg));
+	ret = i2c_master_send(client, write_buf, sizeof(write_buf));
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int seesaw_read_data(struct i2c_client *client, struct seesaw_data *data)
+{
+	__be16 adc_data;
+	__be32 read_buf;
+	int err;
+
+	err = seesaw_register_read(client, SEESAW_GPIO_BULK,
+				   &read_buf, sizeof(read_buf));
+	if (err)
+		return err;
+
+	data->button_state = ~be32_to_cpu(read_buf);
+
+	err = seesaw_register_read(client,
+				   SEESAW_ADC_BASE |
+					(SEESAW_ADC_OFFSET + SEESAW_ANALOG_X),
+				   &adc_data, sizeof(adc_data));
+	if (err)
+		return err;
+	/*
+	 * ADC reads left as max and right as 0, must be reversed since kernel
+	 * expects reports in opposite order.
+	 */
+	data->x = SEESAW_JOYSTICK_MAX_AXIS - be16_to_cpu(adc_data);
+
+	err = seesaw_register_read(client,
+				   SEESAW_ADC_BASE |
+					(SEESAW_ADC_OFFSET + SEESAW_ANALOG_Y),
+				   &adc_data, sizeof(adc_data));
+	if (err)
+		return err;
+
+	data->y = be16_to_cpu(adc_data);
+
+	return 0;
+}
+
+static void seesaw_poll(struct input_dev *input)
+{
+	struct seesaw_gamepad *private = input_get_drvdata(input);
+	struct seesaw_data data;
+	int err, i;
+
+	err = seesaw_read_data(private->i2c_client, &data);
+	if (err) {
+		dev_err_ratelimited(&input->dev,
+				    "failed to read joystick state: %d\n", err);
+		return;
+	}
+
+	input_report_abs(input, ABS_X, data.x);
+	input_report_abs(input, ABS_Y, data.y);
+
+	for_each_set_bit(i, &SEESAW_BUTTON_MASK,
+			 BITS_PER_TYPE(SEESAW_BUTTON_MASK)) {
+		if (!sparse_keymap_report_event(input, i,
+						data.button_state & BIT(i),
+						false))
+			dev_err_ratelimited(&input->dev,
+					    "failed to report keymap event");
+	}
+
+	input_sync(input);
+}
+
+static int seesaw_probe(struct i2c_client *client)
+{
+	struct seesaw_gamepad *seesaw;
+	u8 hardware_id;
+	int err;
+
+	err = seesaw_register_write_u8(client, SEESAW_STATUS_SWRST, 0xFF);
+	if (err)
+		return err;
+
+	/* Wait for the registers to reset before proceeding */
+	usleep_range(10000, 15000);
+
+	seesaw = devm_kzalloc(&client->dev, sizeof(*seesaw), GFP_KERNEL);
+	if (!seesaw)
+		return -ENOMEM;
+
+	err = seesaw_register_read(client, SEESAW_STATUS_HW_ID,
+				   &hardware_id, sizeof(hardware_id));
+	if (err)
+		return err;
+
+	dev_dbg(&client->dev, "Adafruit Seesaw Gamepad, Hardware ID: %02x\n",
+		hardware_id);
+
+	/* Set Pin Mode to input and enable pull-up resistors */
+	err = seesaw_register_write_u32(client, SEESAW_GPIO_DIRCLR_BULK,
+					SEESAW_BUTTON_MASK);
+	if (err)
+		return err;
+	err = seesaw_register_write_u32(client, SEESAW_GPIO_PULLENSET,
+					SEESAW_BUTTON_MASK);
+	if (err)
+		return err;
+	err = seesaw_register_write_u32(client, SEESAW_GPIO_BULK_SET,
+					SEESAW_BUTTON_MASK);
+	if (err)
+		return err;
+
+	seesaw->i2c_client = client;
+	seesaw->input_dev = devm_input_allocate_device(&client->dev);
+	if (!seesaw->input_dev)
+		return -ENOMEM;
+
+	seesaw->input_dev->id.bustype = BUS_I2C;
+	seesaw->input_dev->name = "Adafruit Seesaw Gamepad";
+	seesaw->input_dev->phys = "i2c/" SEESAW_DEVICE_NAME;
+	input_set_drvdata(seesaw->input_dev, seesaw);
+	input_set_abs_params(seesaw->input_dev, ABS_X,
+			     0, SEESAW_JOYSTICK_MAX_AXIS,
+			     SEESAW_JOYSTICK_FUZZ, SEESAW_JOYSTICK_FLAT);
+	input_set_abs_params(seesaw->input_dev, ABS_Y,
+			     0, SEESAW_JOYSTICK_MAX_AXIS,
+			     SEESAW_JOYSTICK_FUZZ, SEESAW_JOYSTICK_FLAT);
+
+	err = sparse_keymap_setup(seesaw->input_dev, seesaw_buttons_new, NULL);
+	if (err) {
+		dev_err(&client->dev,
+			"failed to set up input device keymap: %d\n", err);
+		return err;
+	}
+
+	err = input_setup_polling(seesaw->input_dev, seesaw_poll);
+	if (err) {
+		dev_err(&client->dev, "failed to set up polling: %d\n", err);
+		return err;
+	}
+
+	input_set_poll_interval(seesaw->input_dev,
+				SEESAW_GAMEPAD_POLL_INTERVAL_MS);
+	input_set_max_poll_interval(seesaw->input_dev, SEESAW_GAMEPAD_POLL_MAX);
+	input_set_min_poll_interval(seesaw->input_dev, SEESAW_GAMEPAD_POLL_MIN);
+
+	err = input_register_device(seesaw->input_dev);
+	if (err) {
+		dev_err(&client->dev, "failed to register joystick: %d\n", err);
+		return err;
+	}
+
+	return 0;
+}
+
+static const struct i2c_device_id seesaw_id_table[] = {
+	{ SEESAW_DEVICE_NAME },
+	{ /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(i2c, seesaw_id_table);
+
+static const struct of_device_id seesaw_of_table[] = {
+	{ .compatible = "adafruit,seesaw-gamepad"},
+	{ /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, seesaw_of_table);
+
+static struct i2c_driver seesaw_driver = {
+	.driver = {
+		.name = SEESAW_DEVICE_NAME,
+		.of_match_table = seesaw_of_table,
+	},
+	.id_table = seesaw_id_table,
+	.probe = seesaw_probe,
+};
+module_i2c_driver(seesaw_driver);
+
+MODULE_AUTHOR("Anshul Dalal <anshulusr@gmail.com>");
+MODULE_DESCRIPTION("Adafruit Mini I2C Gamepad driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/input/joystick/as5011.c b/drivers/input/joystick/as5011.c
index bf8b1cc0ea9c..f1822c19a289 100644
--- a/drivers/input/joystick/as5011.c
+++ b/drivers/input/joystick/as5011.c
@@ -13,7 +13,7 @@
 #include <linux/i2c.h>
 #include <linux/interrupt.h>
 #include <linux/input.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/delay.h>
 #include <linux/input/as5011.h>
 #include <linux/slab.h>
@@ -61,7 +61,7 @@ MODULE_LICENSE("GPL");
 struct as5011_device {
 	struct input_dev *input_dev;
 	struct i2c_client *i2c_client;
-	unsigned int button_gpio;
+	struct gpio_desc *button_gpiod;
 	unsigned int button_irq;
 	unsigned int axis_irq;
 };
@@ -114,7 +114,7 @@ static int as5011_i2c_read(struct i2c_client *client,
 static irqreturn_t as5011_button_interrupt(int irq, void *dev_id)
 {
 	struct as5011_device *as5011 = dev_id;
-	int val = gpio_get_value_cansleep(as5011->button_gpio);
+	int val = gpiod_get_value_cansleep(as5011->button_gpiod);
 
 	input_report_key(as5011->input_dev, BTN_JOYSTICK, !val);
 	input_sync(as5011->input_dev);
@@ -248,7 +248,6 @@ static int as5011_probe(struct i2c_client *client)
 
 	as5011->i2c_client = client;
 	as5011->input_dev = input_dev;
-	as5011->button_gpio = plat_data->button_gpio;
 	as5011->axis_irq = plat_data->axis_irq;
 
 	input_dev->name = "Austria Microsystem as5011 joystick";
@@ -262,18 +261,20 @@ static int as5011_probe(struct i2c_client *client)
 	input_set_abs_params(as5011->input_dev, ABS_Y,
 		AS5011_MIN_AXIS, AS5011_MAX_AXIS, AS5011_FUZZ, AS5011_FLAT);
 
-	error = gpio_request(as5011->button_gpio, "AS5011 button");
-	if (error < 0) {
-		dev_err(&client->dev, "Failed to request button gpio\n");
+	as5011->button_gpiod = devm_gpiod_get(&client->dev, NULL, GPIOD_IN);
+	if (IS_ERR(as5011->button_gpiod)) {
+		error = PTR_ERR(as5011->button_gpiod);
+		dev_err(&client->dev, "Failed to request button GPIO\n");
 		goto err_free_mem;
 	}
+	gpiod_set_consumer_name(as5011->button_gpiod, "AS5011 button");
 
-	irq = gpio_to_irq(as5011->button_gpio);
+	irq = gpiod_to_irq(as5011->button_gpiod);
 	if (irq < 0) {
 		dev_err(&client->dev,
 			"Failed to get irq number for button gpio\n");
 		error = irq;
-		goto err_free_button_gpio;
+		goto err_free_mem;
 	}
 
 	as5011->button_irq = irq;
@@ -286,7 +287,7 @@ static int as5011_probe(struct i2c_client *client)
 	if (error < 0) {
 		dev_err(&client->dev,
 			"Can't allocate button irq %d\n", as5011->button_irq);
-		goto err_free_button_gpio;
+		goto err_free_mem;
 	}
 
 	error = as5011_configure_chip(as5011, plat_data);
@@ -317,8 +318,6 @@ err_free_axis_irq:
 	free_irq(as5011->axis_irq, as5011);
 err_free_button_irq:
 	free_irq(as5011->button_irq, as5011);
-err_free_button_gpio:
-	gpio_free(as5011->button_gpio);
 err_free_mem:
 	input_free_device(input_dev);
 	kfree(as5011);
@@ -332,7 +331,6 @@ static void as5011_remove(struct i2c_client *client)
 
 	free_irq(as5011->axis_irq, as5011);
 	free_irq(as5011->button_irq, as5011);
-	gpio_free(as5011->button_gpio);
 
 	input_unregister_device(as5011->input_dev);
 	kfree(as5011);
diff --git a/drivers/input/joystick/pxrc.c b/drivers/input/joystick/pxrc.c
index ea2bf5951d67..52d9eab667b7 100644
--- a/drivers/input/joystick/pxrc.c
+++ b/drivers/input/joystick/pxrc.c
@@ -5,15 +5,17 @@
  * Copyright (C) 2018 Marcus Folkesson <marcus.folkesson@gmail.com>
  */
 
-#include <linux/kernel.h>
+#include <linux/cleanup.h>
 #include <linux/errno.h>
-#include <linux/slab.h>
+#include <linux/input.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
 #include <linux/uaccess.h>
+
 #include <linux/usb.h>
 #include <linux/usb/input.h>
-#include <linux/mutex.h>
-#include <linux/input.h>
 
 #define PXRC_VENDOR_ID		0x1781
 #define PXRC_PRODUCT_ID		0x0898
@@ -81,33 +83,28 @@ exit:
 static int pxrc_open(struct input_dev *input)
 {
 	struct pxrc *pxrc = input_get_drvdata(input);
-	int retval;
+	int error;
 
-	mutex_lock(&pxrc->pm_mutex);
-	retval = usb_submit_urb(pxrc->urb, GFP_KERNEL);
-	if (retval) {
+	guard(mutex)(&pxrc->pm_mutex);
+	error = usb_submit_urb(pxrc->urb, GFP_KERNEL);
+	if (error) {
 		dev_err(&pxrc->intf->dev,
 			"%s - usb_submit_urb failed, error: %d\n",
-			__func__, retval);
-		retval = -EIO;
-		goto out;
+			__func__, error);
+		return -EIO;
 	}
 
 	pxrc->is_open = true;
-
-out:
-	mutex_unlock(&pxrc->pm_mutex);
-	return retval;
+	return 0;
 }
 
 static void pxrc_close(struct input_dev *input)
 {
 	struct pxrc *pxrc = input_get_drvdata(input);
 
-	mutex_lock(&pxrc->pm_mutex);
+	guard(mutex)(&pxrc->pm_mutex);
 	usb_kill_urb(pxrc->urb);
 	pxrc->is_open = false;
-	mutex_unlock(&pxrc->pm_mutex);
 }
 
 static void pxrc_free_urb(void *_pxrc)
@@ -208,10 +205,9 @@ static int pxrc_suspend(struct usb_interface *intf, pm_message_t message)
 {
 	struct pxrc *pxrc = usb_get_intfdata(intf);
 
-	mutex_lock(&pxrc->pm_mutex);
+	guard(mutex)(&pxrc->pm_mutex);
 	if (pxrc->is_open)
 		usb_kill_urb(pxrc->urb);
-	mutex_unlock(&pxrc->pm_mutex);
 
 	return 0;
 }
@@ -219,14 +215,12 @@ static int pxrc_suspend(struct usb_interface *intf, pm_message_t message)
 static int pxrc_resume(struct usb_interface *intf)
 {
 	struct pxrc *pxrc = usb_get_intfdata(intf);
-	int retval = 0;
 
-	mutex_lock(&pxrc->pm_mutex);
+	guard(mutex)(&pxrc->pm_mutex);
 	if (pxrc->is_open && usb_submit_urb(pxrc->urb, GFP_KERNEL) < 0)
-		retval = -EIO;
+		return -EIO;
 
-	mutex_unlock(&pxrc->pm_mutex);
-	return retval;
+	return 0;
 }
 
 static int pxrc_pre_reset(struct usb_interface *intf)
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index e2c1848182de..14c828adebf7 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -130,7 +130,12 @@ static const struct xpad_device {
 	{ 0x0079, 0x18d4, "GPD Win 2 X-Box Controller", 0, XTYPE_XBOX360 },
 	{ 0x03eb, 0xff01, "Wooting One (Legacy)", 0, XTYPE_XBOX360 },
 	{ 0x03eb, 0xff02, "Wooting Two (Legacy)", 0, XTYPE_XBOX360 },
+	{ 0x03f0, 0x038D, "HyperX Clutch", 0, XTYPE_XBOX360 },			/* wired */
+	{ 0x03f0, 0x048D, "HyperX Clutch", 0, XTYPE_XBOX360 },			/* wireless */
 	{ 0x03f0, 0x0495, "HyperX Clutch Gladiate", 0, XTYPE_XBOXONE },
+	{ 0x03f0, 0x07A0, "HyperX Clutch Gladiate RGB", 0, XTYPE_XBOXONE },
+	{ 0x03f0, 0x08B6, "HyperX Clutch Gladiate", 0, XTYPE_XBOXONE },		/* v2 */
+	{ 0x03f0, 0x09B4, "HyperX Clutch Tanto", 0, XTYPE_XBOXONE },
 	{ 0x044f, 0x0f00, "Thrustmaster Wheel", 0, XTYPE_XBOX },
 	{ 0x044f, 0x0f03, "Thrustmaster Wheel", 0, XTYPE_XBOX },
 	{ 0x044f, 0x0f07, "Thrustmaster, Inc. Controller", 0, XTYPE_XBOX },
@@ -294,6 +299,7 @@ static const struct xpad_device {
 	{ 0x1689, 0xfd00, "Razer Onza Tournament Edition", 0, XTYPE_XBOX360 },
 	{ 0x1689, 0xfd01, "Razer Onza Classic Edition", 0, XTYPE_XBOX360 },
 	{ 0x1689, 0xfe00, "Razer Sabertooth", 0, XTYPE_XBOX360 },
+	{ 0x17ef, 0x6182, "Lenovo Legion Controller for Windows", 0, XTYPE_XBOX360 },
 	{ 0x1949, 0x041a, "Amazon Game Controller", 0, XTYPE_XBOX360 },
 	{ 0x1bad, 0x0002, "Harmonix Rock Band Guitar", 0, XTYPE_XBOX360 },
 	{ 0x1bad, 0x0003, "Harmonix Rock Band Drumkit", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
@@ -462,6 +468,7 @@ static const struct usb_device_id xpad_table[] = {
 	{ USB_INTERFACE_INFO('X', 'B', 0) },	/* Xbox USB-IF not-approved class */
 	XPAD_XBOX360_VENDOR(0x0079),		/* GPD Win 2 controller */
 	XPAD_XBOX360_VENDOR(0x03eb),		/* Wooting Keyboards (Legacy) */
+	XPAD_XBOX360_VENDOR(0x03f0),		/* HP HyperX Xbox 360 controllers */
 	XPAD_XBOXONE_VENDOR(0x03f0),		/* HP HyperX Xbox One controllers */
 	XPAD_XBOX360_VENDOR(0x044f),		/* Thrustmaster Xbox 360 controllers */
 	XPAD_XBOX360_VENDOR(0x045e),		/* Microsoft Xbox 360 controllers */
@@ -491,6 +498,7 @@ static const struct usb_device_id xpad_table[] = {
 	XPAD_XBOX360_VENDOR(0x15e4),		/* Numark Xbox 360 controllers */
 	XPAD_XBOX360_VENDOR(0x162e),		/* Joytech Xbox 360 controllers */
 	XPAD_XBOX360_VENDOR(0x1689),		/* Razer Onza */
+	XPAD_XBOX360_VENDOR(0x17ef),		/* Lenovo */
 	XPAD_XBOX360_VENDOR(0x1949),		/* Amazon controllers */
 	XPAD_XBOX360_VENDOR(0x1bad),		/* Harmonix Rock Band guitar and drums */
 	XPAD_XBOX360_VENDOR(0x20d6),		/* PowerA controllers */
@@ -1670,7 +1678,7 @@ static int xpad_led_probe(struct usb_xpad *xpad)
 	if (!led)
 		return -ENOMEM;
 
-	xpad->pad_nr = ida_simple_get(&xpad_pad_seq, 0, 0, GFP_KERNEL);
+	xpad->pad_nr = ida_alloc(&xpad_pad_seq, GFP_KERNEL);
 	if (xpad->pad_nr < 0) {
 		error = xpad->pad_nr;
 		goto err_free_mem;
@@ -1693,7 +1701,7 @@ static int xpad_led_probe(struct usb_xpad *xpad)
 	return 0;
 
 err_free_id:
-	ida_simple_remove(&xpad_pad_seq, xpad->pad_nr);
+	ida_free(&xpad_pad_seq, xpad->pad_nr);
 err_free_mem:
 	kfree(led);
 	xpad->led = NULL;
@@ -1706,7 +1714,7 @@ static void xpad_led_disconnect(struct usb_xpad *xpad)
 
 	if (xpad_led) {
 		led_classdev_unregister(&xpad_led->led_cdev);
-		ida_simple_remove(&xpad_pad_seq, xpad->pad_nr);
+		ida_free(&xpad_pad_seq, xpad->pad_nr);
 		kfree(xpad_led);
 	}
 }
diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c
index 786f00f6b7fd..7f67f9f2946b 100644
--- a/drivers/input/keyboard/atkbd.c
+++ b/drivers/input/keyboard/atkbd.c
@@ -791,9 +791,9 @@ static bool atkbd_is_portable_device(void)
  * not work. So in this case simply assume a keyboard is connected to avoid
  * confusing some laptop keyboards.
  *
- * Skipping ATKBD_CMD_GETID ends up using a fake keyboard id. Using a fake id is
- * ok in translated mode, only atkbd_select_set() checks atkbd->id and in
- * translated mode that is a no-op.
+ * Skipping ATKBD_CMD_GETID ends up using a fake keyboard id. Using the standard
+ * 0xab83 id is ok in translated mode, only atkbd_select_set() checks atkbd->id
+ * and in translated mode that is a no-op.
  */
 static bool atkbd_skip_getid(struct atkbd *atkbd)
 {
@@ -824,6 +824,11 @@ static int atkbd_probe(struct atkbd *atkbd)
 				 "keyboard reset failed on %s\n",
 				 ps2dev->serio->phys);
 
+	if (atkbd_skip_getid(atkbd)) {
+		atkbd->id = 0xab83;
+		goto deactivate_kbd;
+	}
+
 /*
  * Then we check the keyboard ID. We should get 0xab83 under normal conditions.
  * Some keyboards report different values, but the first byte is always 0xab or
@@ -832,10 +837,10 @@ static int atkbd_probe(struct atkbd *atkbd)
  */
 
 	param[0] = param[1] = 0xa5;	/* initialize with invalid values */
-	if (atkbd_skip_getid(atkbd) || ps2_command(ps2dev, param, ATKBD_CMD_GETID)) {
+	if (ps2_command(ps2dev, param, ATKBD_CMD_GETID)) {
 
 /*
- * If the get ID command was skipped or failed, we check if we can at least set
+ * If the get ID command failed, we check if we can at least set
  * the LEDs on the keyboard. This should work on every keyboard out there.
  * It also turns the LEDs off, which we want anyway.
  */
@@ -858,6 +863,7 @@ static int atkbd_probe(struct atkbd *atkbd)
 		return -1;
 	}
 
+deactivate_kbd:
 /*
  * Make sure nothing is coming from the keyboard and disturbs our
  * internal state.
diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c
index 1b4937dce672..52fba9ee7c1d 100644
--- a/drivers/input/keyboard/cap11xx.c
+++ b/drivers/input/keyboard/cap11xx.c
@@ -10,10 +10,11 @@
 #include <linux/interrupt.h>
 #include <linux/input.h>
 #include <linux/leds.h>
-#include <linux/of_irq.h>
+#include <linux/of.h>
 #include <linux/regmap.h>
 #include <linux/i2c.h>
 #include <linux/gpio/consumer.h>
+#include <linux/bitfield.h>
 
 #define CAP11XX_REG_MAIN_CONTROL	0x00
 #define CAP11XX_REG_MAIN_CONTROL_GAIN_SHIFT	(6)
@@ -24,6 +25,7 @@
 #define CAP11XX_REG_NOISE_FLAG_STATUS	0x0a
 #define CAP11XX_REG_SENOR_DELTA(X)	(0x10 + (X))
 #define CAP11XX_REG_SENSITIVITY_CONTROL	0x1f
+#define CAP11XX_REG_SENSITIVITY_CONTROL_DELTA_SENSE_MASK	0x70
 #define CAP11XX_REG_CONFIG		0x20
 #define CAP11XX_REG_SENSOR_ENABLE	0x21
 #define CAP11XX_REG_SENSOR_CONFIG	0x22
@@ -32,6 +34,7 @@
 #define CAP11XX_REG_CALIBRATION		0x26
 #define CAP11XX_REG_INT_ENABLE		0x27
 #define CAP11XX_REG_REPEAT_RATE		0x28
+#define CAP11XX_REG_SIGNAL_GUARD_ENABLE	0x29
 #define CAP11XX_REG_MT_CONFIG		0x2a
 #define CAP11XX_REG_MT_PATTERN_CONFIG	0x2b
 #define CAP11XX_REG_MT_PATTERN		0x2d
@@ -47,6 +50,8 @@
 #define CAP11XX_REG_SENSOR_BASE_CNT(X)	(0x50 + (X))
 #define CAP11XX_REG_LED_POLARITY	0x73
 #define CAP11XX_REG_LED_OUTPUT_CONTROL	0x74
+#define CAP11XX_REG_CALIB_SENSITIVITY_CONFIG	0x80
+#define CAP11XX_REG_CALIB_SENSITIVITY_CONFIG2	0x81
 
 #define CAP11XX_REG_LED_DUTY_CYCLE_1	0x90
 #define CAP11XX_REG_LED_DUTY_CYCLE_2	0x91
@@ -78,12 +83,20 @@ struct cap11xx_led {
 
 struct cap11xx_priv {
 	struct regmap *regmap;
+	struct device *dev;
 	struct input_dev *idev;
+	const struct cap11xx_hw_model *model;
+	u8 id;
 
 	struct cap11xx_led *leds;
 	int num_leds;
 
 	/* config */
+	u8 analog_gain;
+	u8 sensitivity_delta_sense;
+	u8 signal_guard_inputs_mask;
+	u32 thresholds[8];
+	u32 calib_sensitivities[8];
 	u32 keycodes[];
 };
 
@@ -160,9 +173,6 @@ static bool cap11xx_volatile_reg(struct device *dev, unsigned int reg)
 	case CAP11XX_REG_SENOR_DELTA(3):
 	case CAP11XX_REG_SENOR_DELTA(4):
 	case CAP11XX_REG_SENOR_DELTA(5):
-	case CAP11XX_REG_PRODUCT_ID:
-	case CAP11XX_REG_MANUFACTURER_ID:
-	case CAP11XX_REG_REVISION:
 		return true;
 	}
 
@@ -177,10 +187,179 @@ static const struct regmap_config cap11xx_regmap_config = {
 	.reg_defaults = cap11xx_reg_defaults,
 
 	.num_reg_defaults = ARRAY_SIZE(cap11xx_reg_defaults),
-	.cache_type = REGCACHE_RBTREE,
+	.cache_type = REGCACHE_MAPLE,
 	.volatile_reg = cap11xx_volatile_reg,
 };
 
+static int cap11xx_write_calib_sens_config_1(struct cap11xx_priv *priv)
+{
+	return regmap_write(priv->regmap,
+			    CAP11XX_REG_CALIB_SENSITIVITY_CONFIG,
+			    (priv->calib_sensitivities[3] << 6) |
+			    (priv->calib_sensitivities[2] << 4) |
+			    (priv->calib_sensitivities[1] << 2) |
+			    priv->calib_sensitivities[0]);
+}
+
+static int cap11xx_write_calib_sens_config_2(struct cap11xx_priv *priv)
+{
+	return regmap_write(priv->regmap,
+			    CAP11XX_REG_CALIB_SENSITIVITY_CONFIG2,
+			    (priv->calib_sensitivities[7] << 6) |
+			    (priv->calib_sensitivities[6] << 4) |
+			    (priv->calib_sensitivities[5] << 2) |
+			    priv->calib_sensitivities[4]);
+}
+
+static int cap11xx_init_keys(struct cap11xx_priv *priv)
+{
+	struct device_node *node = priv->dev->of_node;
+	struct device *dev = priv->dev;
+	int i, error;
+	u32 u32_val;
+
+	if (!node) {
+		dev_err(dev, "Corresponding DT entry is not available\n");
+		return -ENODEV;
+	}
+
+	if (!of_property_read_u32(node, "microchip,sensor-gain", &u32_val)) {
+		if (priv->model->no_gain) {
+			dev_warn(dev,
+				 "This model doesn't support 'sensor-gain'\n");
+		} else if (is_power_of_2(u32_val) && u32_val <= 8) {
+			priv->analog_gain = (u8)ilog2(u32_val);
+
+			error = regmap_update_bits(priv->regmap,
+				CAP11XX_REG_MAIN_CONTROL,
+				CAP11XX_REG_MAIN_CONTROL_GAIN_MASK,
+				priv->analog_gain << CAP11XX_REG_MAIN_CONTROL_GAIN_SHIFT);
+			if (error)
+				return error;
+		} else {
+			dev_err(dev, "Invalid sensor-gain value %u\n", u32_val);
+			return -EINVAL;
+		}
+	}
+
+	if (of_property_read_bool(node, "microchip,irq-active-high")) {
+		if (priv->id == CAP1106 ||
+		    priv->id == CAP1126 ||
+		    priv->id == CAP1188) {
+			error = regmap_update_bits(priv->regmap,
+						   CAP11XX_REG_CONFIG2,
+						   CAP11XX_REG_CONFIG2_ALT_POL,
+						   0);
+			if (error)
+				return error;
+		} else {
+			dev_warn(dev,
+				 "This model doesn't support 'irq-active-high'\n");
+		}
+	}
+
+	if (!of_property_read_u32(node, "microchip,sensitivity-delta-sense", &u32_val)) {
+		if (!is_power_of_2(u32_val) || u32_val > 128) {
+			dev_err(dev, "Invalid sensitivity-delta-sense value %u\n", u32_val);
+			return -EINVAL;
+		}
+
+		priv->sensitivity_delta_sense = (u8)ilog2(u32_val);
+		u32_val = ~(FIELD_PREP(CAP11XX_REG_SENSITIVITY_CONTROL_DELTA_SENSE_MASK,
+					priv->sensitivity_delta_sense));
+
+		error = regmap_update_bits(priv->regmap,
+					   CAP11XX_REG_SENSITIVITY_CONTROL,
+					   CAP11XX_REG_SENSITIVITY_CONTROL_DELTA_SENSE_MASK,
+					   u32_val);
+		if (error)
+			return error;
+	}
+
+	if (!of_property_read_u32_array(node, "microchip,input-threshold",
+					priv->thresholds, priv->model->num_channels)) {
+		for (i = 0; i < priv->model->num_channels; i++) {
+			if (priv->thresholds[i] > 127) {
+				dev_err(dev, "Invalid input-threshold value %u\n",
+					priv->thresholds[i]);
+				return -EINVAL;
+			}
+
+			error = regmap_write(priv->regmap,
+					     CAP11XX_REG_SENSOR_THRESH(i),
+					     priv->thresholds[i]);
+			if (error)
+				return error;
+		}
+	}
+
+	if (!of_property_read_u32_array(node, "microchip,calib-sensitivity",
+					priv->calib_sensitivities,
+					priv->model->num_channels)) {
+		if (priv->id == CAP1293 || priv->id == CAP1298) {
+			for (i = 0; i < priv->model->num_channels; i++) {
+				if (!is_power_of_2(priv->calib_sensitivities[i]) ||
+				    priv->calib_sensitivities[i] > 4) {
+					dev_err(dev, "Invalid calib-sensitivity value %u\n",
+						priv->calib_sensitivities[i]);
+					return -EINVAL;
+				}
+				priv->calib_sensitivities[i] = ilog2(priv->calib_sensitivities[i]);
+			}
+
+			error = cap11xx_write_calib_sens_config_1(priv);
+			if (error)
+				return error;
+
+			if (priv->id == CAP1298) {
+				error = cap11xx_write_calib_sens_config_2(priv);
+				if (error)
+					return error;
+			}
+		} else {
+			dev_warn(dev,
+				 "This model doesn't support 'calib-sensitivity'\n");
+		}
+	}
+
+	for (i = 0; i < priv->model->num_channels; i++) {
+		if (!of_property_read_u32_index(node, "microchip,signal-guard",
+						i, &u32_val)) {
+			if (u32_val > 1)
+				return -EINVAL;
+			if (u32_val)
+				priv->signal_guard_inputs_mask |= 0x01 << i;
+		}
+	}
+
+	if (priv->signal_guard_inputs_mask) {
+		if (priv->id == CAP1293 || priv->id == CAP1298) {
+			error = regmap_write(priv->regmap,
+					     CAP11XX_REG_SIGNAL_GUARD_ENABLE,
+					     priv->signal_guard_inputs_mask);
+			if (error)
+				return error;
+		} else {
+			dev_warn(dev,
+				 "This model doesn't support 'signal-guard'\n");
+		}
+	}
+
+	/* Provide some useful defaults */
+	for (i = 0; i < priv->model->num_channels; i++)
+		priv->keycodes[i] = KEY_A + i;
+
+	of_property_read_u32_array(node, "linux,keycodes",
+				   priv->keycodes, priv->model->num_channels);
+
+	/* Disable autorepeat. The Linux input system has its own handling. */
+	error = regmap_write(priv->regmap, CAP11XX_REG_REPEAT_RATE, 0);
+	if (error)
+		return error;
+
+	return 0;
+}
+
 static irqreturn_t cap11xx_thread_func(int irq_num, void *data)
 {
 	struct cap11xx_priv *priv = data;
@@ -332,11 +511,9 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client)
 	const struct i2c_device_id *id = i2c_client_get_device_id(i2c_client);
 	struct device *dev = &i2c_client->dev;
 	struct cap11xx_priv *priv;
-	struct device_node *node;
 	const struct cap11xx_hw_model *cap;
-	int i, error, irq, gain = 0;
+	int i, error;
 	unsigned int val, rev;
-	u32 gain32;
 
 	if (id->driver_data >= ARRAY_SIZE(cap11xx_devices)) {
 		dev_err(dev, "Invalid device ID %lu\n", id->driver_data);
@@ -355,6 +532,8 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client)
 	if (!priv)
 		return -ENOMEM;
 
+	priv->dev = dev;
+
 	priv->regmap = devm_regmap_init_i2c(i2c_client, &cap11xx_regmap_config);
 	if (IS_ERR(priv->regmap))
 		return PTR_ERR(priv->regmap);
@@ -384,50 +563,15 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client)
 		return error;
 
 	dev_info(dev, "CAP11XX detected, model %s, revision 0x%02x\n",
-		 id->name, rev);
-	node = dev->of_node;
-
-	if (!of_property_read_u32(node, "microchip,sensor-gain", &gain32)) {
-		if (cap->no_gain)
-			dev_warn(dev,
-				 "This version doesn't support sensor gain\n");
-		else if (is_power_of_2(gain32) && gain32 <= 8)
-			gain = ilog2(gain32);
-		else
-			dev_err(dev, "Invalid sensor-gain value %d\n", gain32);
-	}
+			 id->name, rev);
 
-	if (id->driver_data == CAP1106 ||
-	    id->driver_data == CAP1126 ||
-	    id->driver_data == CAP1188) {
-		if (of_property_read_bool(node, "microchip,irq-active-high")) {
-			error = regmap_update_bits(priv->regmap,
-						   CAP11XX_REG_CONFIG2,
-						   CAP11XX_REG_CONFIG2_ALT_POL,
-						   0);
-			if (error)
-				return error;
-		}
-	}
-
-	/* Provide some useful defaults */
-	for (i = 0; i < cap->num_channels; i++)
-		priv->keycodes[i] = KEY_A + i;
-
-	of_property_read_u32_array(node, "linux,keycodes",
-				   priv->keycodes, cap->num_channels);
+	priv->model = cap;
+	priv->id = id->driver_data;
 
-	if (!cap->no_gain) {
-		error = regmap_update_bits(priv->regmap,
-				CAP11XX_REG_MAIN_CONTROL,
-				CAP11XX_REG_MAIN_CONTROL_GAIN_MASK,
-				gain << CAP11XX_REG_MAIN_CONTROL_GAIN_SHIFT);
-		if (error)
-			return error;
-	}
+	dev_info(dev, "CAP11XX device detected, model %s, revision 0x%02x\n",
+		 id->name, rev);
 
-	/* Disable autorepeat. The Linux input system has its own handling. */
-	error = regmap_write(priv->regmap, CAP11XX_REG_REPEAT_RATE, 0);
+	error = cap11xx_init_keys(priv);
 	if (error)
 		return error;
 
@@ -439,7 +583,7 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client)
 	priv->idev->id.bustype = BUS_I2C;
 	priv->idev->evbit[0] = BIT_MASK(EV_KEY);
 
-	if (of_property_read_bool(node, "autorepeat"))
+	if (of_property_read_bool(dev->of_node, "autorepeat"))
 		__set_bit(EV_REP, priv->idev->evbit);
 
 	for (i = 0; i < cap->num_channels; i++)
@@ -474,13 +618,8 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client)
 	if (error)
 		return error;
 
-	irq = irq_of_parse_and_map(node, 0);
-	if (!irq) {
-		dev_err(dev, "Unable to parse or map IRQ\n");
-		return -ENXIO;
-	}
-
-	error = devm_request_threaded_irq(dev, irq, NULL, cap11xx_thread_func,
+	error = devm_request_threaded_irq(dev, i2c_client->irq,
+					  NULL, cap11xx_thread_func,
 					  IRQF_ONESHOT, dev_name(dev), priv);
 	if (error)
 		return error;
diff --git a/drivers/input/keyboard/gpio_keys.c b/drivers/input/keyboard/gpio_keys.c
index 2e7c2c046e67..9f3bcd41cf67 100644
--- a/drivers/input/keyboard/gpio_keys.c
+++ b/drivers/input/keyboard/gpio_keys.c
@@ -45,7 +45,9 @@ struct gpio_button_data {
 	unsigned int software_debounce;	/* in msecs, for GPIO-driven buttons */
 
 	unsigned int irq;
+	unsigned int wakeirq;
 	unsigned int wakeup_trigger_type;
+
 	spinlock_t lock;
 	bool disabled;
 	bool key_pressed;
@@ -511,6 +513,7 @@ static int gpio_keys_setup_key(struct platform_device *pdev,
 	struct gpio_button_data *bdata = &ddata->data[idx];
 	irq_handler_t isr;
 	unsigned long irqflags;
+	const char *wakedesc;
 	int irq;
 	int error;
 
@@ -575,15 +578,23 @@ static int gpio_keys_setup_key(struct platform_device *pdev,
 					!gpiod_cansleep(bdata->gpiod);
 		}
 
+		/*
+		 * If an interrupt was specified, use it instead of the gpio
+		 * interrupt and use the gpio for reading the state. A separate
+		 * interrupt may be used as the main button interrupt for
+		 * runtime PM to detect events also in deeper idle states. If a
+		 * dedicated wakeirq is used for system suspend only, see below
+		 * for bdata->wakeirq setup.
+		 */
 		if (button->irq) {
 			bdata->irq = button->irq;
 		} else {
 			irq = gpiod_to_irq(bdata->gpiod);
 			if (irq < 0) {
 				error = irq;
-				dev_err(dev,
-					"Unable to get irq number for GPIO %d, error %d\n",
-					button->gpio, error);
+				dev_err_probe(dev, error,
+					      "Unable to get irq number for GPIO %d\n",
+					      button->gpio);
 				return error;
 			}
 			bdata->irq = irq;
@@ -672,6 +683,36 @@ static int gpio_keys_setup_key(struct platform_device *pdev,
 		return error;
 	}
 
+	if (!button->wakeirq)
+		return 0;
+
+	/* Use :wakeup suffix like drivers/base/power/wakeirq.c does */
+	wakedesc = devm_kasprintf(dev, GFP_KERNEL, "%s:wakeup", desc);
+	if (!wakedesc)
+		return -ENOMEM;
+
+	bdata->wakeirq = button->wakeirq;
+	irqflags |= IRQF_NO_SUSPEND;
+
+	/*
+	 * Wakeirq shares the handler with the main interrupt, it's only
+	 * active during system suspend. See gpio_keys_button_enable_wakeup()
+	 * and gpio_keys_button_disable_wakeup().
+	 */
+	error = devm_request_any_context_irq(dev, bdata->wakeirq, isr,
+					     irqflags, wakedesc, bdata);
+	if (error < 0) {
+		dev_err(dev, "Unable to claim wakeirq %d; error %d\n",
+			bdata->irq, error);
+		return error;
+	}
+
+	/*
+	 * Disable wakeirq until suspend. IRQF_NO_AUTOEN won't work if
+	 * IRQF_SHARED was set based on !button->can_disable.
+	 */
+	disable_irq(bdata->wakeirq);
+
 	return 0;
 }
 
@@ -728,7 +769,7 @@ gpio_keys_get_devtree_pdata(struct device *dev)
 	struct gpio_keys_platform_data *pdata;
 	struct gpio_keys_button *button;
 	struct fwnode_handle *child;
-	int nbuttons;
+	int nbuttons, irq;
 
 	nbuttons = device_get_child_node_count(dev);
 	if (nbuttons == 0)
@@ -750,9 +791,19 @@ gpio_keys_get_devtree_pdata(struct device *dev)
 	device_property_read_string(dev, "label", &pdata->name);
 
 	device_for_each_child_node(dev, child) {
-		if (is_of_node(child))
-			button->irq =
-				irq_of_parse_and_map(to_of_node(child), 0);
+		if (is_of_node(child)) {
+			irq = of_irq_get_byname(to_of_node(child), "irq");
+			if (irq > 0)
+				button->irq = irq;
+
+			irq = of_irq_get_byname(to_of_node(child), "wakeup");
+			if (irq > 0)
+				button->wakeirq = irq;
+
+			if (!button->irq && !button->wakeirq)
+				button->irq =
+					irq_of_parse_and_map(to_of_node(child), 0);
+		}
 
 		if (fwnode_property_read_u32(child, "linux,code",
 					     &button->code)) {
@@ -921,6 +972,11 @@ gpio_keys_button_enable_wakeup(struct gpio_button_data *bdata)
 		}
 	}
 
+	if (bdata->wakeirq) {
+		enable_irq(bdata->wakeirq);
+		disable_irq(bdata->irq);
+	}
+
 	return 0;
 }
 
@@ -929,6 +985,11 @@ gpio_keys_button_disable_wakeup(struct gpio_button_data *bdata)
 {
 	int error;
 
+	if (bdata->wakeirq) {
+		enable_irq(bdata->irq);
+		disable_irq(bdata->wakeirq);
+	}
+
 	/*
 	 * The trigger type is always both edges for gpio-based keys and we do
 	 * not support changing wakeup trigger for interrupt-based keys.
diff --git a/drivers/input/keyboard/gpio_keys_polled.c b/drivers/input/keyboard/gpio_keys_polled.c
index ba00ecfbd343..b41fd1240f43 100644
--- a/drivers/input/keyboard/gpio_keys_polled.c
+++ b/drivers/input/keyboard/gpio_keys_polled.c
@@ -315,12 +315,10 @@ static int gpio_keys_polled_probe(struct platform_device *pdev)
 
 			error = devm_gpio_request_one(dev, button->gpio,
 					flags, button->desc ? : DRV_NAME);
-			if (error) {
-				dev_err(dev,
-					"unable to claim gpio %u, err=%d\n",
-					button->gpio, error);
-				return error;
-			}
+			if (error)
+				return dev_err_probe(dev, error,
+						     "unable to claim gpio %u\n",
+						     button->gpio);
 
 			bdata->gpiod = gpio_to_desc(button->gpio);
 			if (!bdata->gpiod) {
diff --git a/drivers/input/keyboard/omap-keypad.c b/drivers/input/keyboard/omap-keypad.c
index 454fb8675657..16f936db7305 100644
--- a/drivers/input/keyboard/omap-keypad.c
+++ b/drivers/input/keyboard/omap-keypad.c
@@ -21,7 +21,6 @@
 #include <linux/mutex.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
-#include <linux/gpio.h>
 #include <linux/platform_data/gpio-omap.h>
 #include <linux/platform_data/keypad-omap.h>
 #include <linux/soc/ti/omap1-io.h>
@@ -49,9 +48,6 @@ struct omap_kp {
 
 static DECLARE_TASKLET_DISABLED_OLD(kp_tasklet, omap_kp_tasklet);
 
-static unsigned int *row_gpios;
-static unsigned int *col_gpios;
-
 static irqreturn_t omap_kp_interrupt(int irq, void *dev_id)
 {
 	/* disable keyboard interrupt and schedule for handling */
@@ -180,7 +176,7 @@ static int omap_kp_probe(struct platform_device *pdev)
 	struct omap_kp *omap_kp;
 	struct input_dev *input_dev;
 	struct omap_kp_platform_data *pdata = dev_get_platdata(&pdev->dev);
-	int i, col_idx, row_idx, ret;
+	int ret;
 	unsigned int row_shift, keycodemax;
 
 	if (!pdata->rows || !pdata->cols || !pdata->keymap_data) {
@@ -209,17 +205,9 @@ static int omap_kp_probe(struct platform_device *pdev)
 	if (pdata->delay)
 		omap_kp->delay = pdata->delay;
 
-	if (pdata->row_gpios && pdata->col_gpios) {
-		row_gpios = pdata->row_gpios;
-		col_gpios = pdata->col_gpios;
-	}
-
 	omap_kp->rows = pdata->rows;
 	omap_kp->cols = pdata->cols;
 
-	col_idx = 0;
-	row_idx = 0;
-
 	timer_setup(&omap_kp->timer, omap_kp_timer, 0);
 
 	/* get the irq and init timer*/
@@ -276,11 +264,6 @@ err4:
 err3:
 	device_remove_file(&pdev->dev, &dev_attr_enable);
 err2:
-	for (i = row_idx - 1; i >= 0; i--)
-		gpio_free(row_gpios[i]);
-	for (i = col_idx - 1; i >= 0; i--)
-		gpio_free(col_gpios[i]);
-
 	kfree(omap_kp);
 	input_free_device(input_dev);
 
diff --git a/drivers/input/keyboard/omap4-keypad.c b/drivers/input/keyboard/omap4-keypad.c
index d3f8688fdd9c..040b340995d8 100644
--- a/drivers/input/keyboard/omap4-keypad.c
+++ b/drivers/input/keyboard/omap4-keypad.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
+#include <linux/clk.h>
 #include <linux/errno.h>
 #include <linux/io.h>
 #include <linux/of.h>
@@ -83,6 +84,7 @@ struct omap4_keypad {
 	bool no_autorepeat;
 	u64 keys;
 	unsigned short *keymap;
+	struct clk *fck;
 };
 
 static int kbd_readl(struct omap4_keypad *keypad_data, u32 offset)
@@ -209,6 +211,10 @@ static int omap4_keypad_open(struct input_dev *input)
 	if (error)
 		return error;
 
+	error = clk_prepare_enable(keypad_data->fck);
+	if (error)
+		goto out;
+
 	disable_irq(keypad_data->irq);
 
 	kbd_writel(keypad_data, OMAP4_KBD_CTRL,
@@ -226,10 +232,11 @@ static int omap4_keypad_open(struct input_dev *input)
 
 	enable_irq(keypad_data->irq);
 
+out:
 	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
-	return 0;
+	return error;
 }
 
 static void omap4_keypad_stop(struct omap4_keypad *keypad_data)
@@ -258,6 +265,7 @@ static void omap4_keypad_close(struct input_dev *input)
 	disable_irq(keypad_data->irq);
 	omap4_keypad_stop(keypad_data);
 	enable_irq(keypad_data->irq);
+	clk_disable_unprepare(keypad_data->fck);
 
 	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
@@ -356,6 +364,11 @@ static int omap4_keypad_probe(struct platform_device *pdev)
 	}
 
 	keypad_data->irq = irq;
+	keypad_data->fck = devm_clk_get(&pdev->dev, "fck");
+	if (IS_ERR(keypad_data->fck))
+		return dev_err_probe(&pdev->dev, PTR_ERR(keypad_data->fck),
+				     "unable to get fck");
+
 	mutex_init(&keypad_data->lock);
 	platform_set_drvdata(pdev, keypad_data);
 
diff --git a/drivers/input/keyboard/qt1050.c b/drivers/input/keyboard/qt1050.c
index 6953097db445..b51dfcd76038 100644
--- a/drivers/input/keyboard/qt1050.c
+++ b/drivers/input/keyboard/qt1050.c
@@ -213,7 +213,7 @@ static struct regmap_config qt1050_regmap_config = {
 	.val_bits = 8,
 	.max_register = QT1050_RES_CAL,
 
-	.cache_type = REGCACHE_RBTREE,
+	.cache_type = REGCACHE_MAPLE,
 
 	.wr_table = &qt1050_writeable_table,
 	.rd_table = &qt1050_readable_table,
diff --git a/drivers/input/keyboard/tca6416-keypad.c b/drivers/input/keyboard/tca6416-keypad.c
index 8af59ced1ec2..677bc4baa5d1 100644
--- a/drivers/input/keyboard/tca6416-keypad.c
+++ b/drivers/input/keyboard/tca6416-keypad.c
@@ -14,7 +14,6 @@
 #include <linux/slab.h>
 #include <linux/interrupt.h>
 #include <linux/workqueue.h>
-#include <linux/gpio.h>
 #include <linux/i2c.h>
 #include <linux/input.h>
 #include <linux/tca6416_keypad.h>
diff --git a/drivers/input/misc/da9063_onkey.c b/drivers/input/misc/da9063_onkey.c
index 74808bae326a..c338765e0ecd 100644
--- a/drivers/input/misc/da9063_onkey.c
+++ b/drivers/input/misc/da9063_onkey.c
@@ -9,11 +9,12 @@
 #include <linux/errno.h>
 #include <linux/input.h>
 #include <linux/interrupt.h>
+#include <linux/mod_devicetable.h>
 #include <linux/platform_device.h>
 #include <linux/pm_wakeirq.h>
+#include <linux/property.h>
 #include <linux/workqueue.h>
 #include <linux/regmap.h>
-#include <linux/of.h>
 #include <linux/mfd/da9063/core.h>
 #include <linux/mfd/da9063/registers.h>
 #include <linux/mfd/da9062/core.h>
@@ -74,13 +75,6 @@ static const struct da906x_chip_config da9062_regs = {
 	.name = "da9062-onkey",
 };
 
-static const struct of_device_id da9063_compatible_reg_id_table[] = {
-	{ .compatible = "dlg,da9063-onkey", .data = &da9063_regs },
-	{ .compatible = "dlg,da9062-onkey", .data = &da9062_regs },
-	{ },
-};
-MODULE_DEVICE_TABLE(of, da9063_compatible_reg_id_table);
-
 static void da9063_poll_on(struct work_struct *work)
 {
 	struct da9063_onkey *onkey = container_of(work,
@@ -187,56 +181,43 @@ static irqreturn_t da9063_onkey_irq_handler(int irq, void *data)
 static int da9063_onkey_probe(struct platform_device *pdev)
 {
 	struct da9063_onkey *onkey;
-	const struct of_device_id *match;
-	int irq;
 	int error;
-
-	match = of_match_node(da9063_compatible_reg_id_table,
-			      pdev->dev.of_node);
-	if (!match)
-		return -ENXIO;
+	int irq;
 
 	onkey = devm_kzalloc(&pdev->dev, sizeof(struct da9063_onkey),
 			     GFP_KERNEL);
-	if (!onkey) {
-		dev_err(&pdev->dev, "Failed to allocate memory.\n");
+	if (!onkey)
 		return -ENOMEM;
-	}
 
-	onkey->config = match->data;
+	onkey->config = device_get_match_data(&pdev->dev);
+	if (!onkey->config)
+		return -ENXIO;
+
 	onkey->dev = &pdev->dev;
 
 	onkey->regmap = dev_get_regmap(pdev->dev.parent, NULL);
-	if (!onkey->regmap) {
-		dev_err(&pdev->dev, "Parent regmap unavailable.\n");
-		return -ENXIO;
-	}
+	if (!onkey->regmap)
+		return dev_err_probe(&pdev->dev, -ENXIO,
+				     "Parent regmap unavailable.\n");
 
-	onkey->key_power = !of_property_read_bool(pdev->dev.of_node,
-						  "dlg,disable-key-power");
+	onkey->key_power = !device_property_read_bool(&pdev->dev,
+						      "dlg,disable-key-power");
 
 	onkey->input = devm_input_allocate_device(&pdev->dev);
-	if (!onkey->input) {
-		dev_err(&pdev->dev, "Failed to allocated input device.\n");
+	if (!onkey->input)
 		return -ENOMEM;
-	}
 
 	onkey->input->name = onkey->config->name;
 	snprintf(onkey->phys, sizeof(onkey->phys), "%s/input0",
 		 onkey->config->name);
 	onkey->input->phys = onkey->phys;
-	onkey->input->dev.parent = &pdev->dev;
 
 	input_set_capability(onkey->input, EV_KEY, KEY_POWER);
 
 	error = devm_delayed_work_autocancel(&pdev->dev, &onkey->work,
 					     da9063_poll_on);
-	if (error) {
-		dev_err(&pdev->dev,
-			"Failed to add cancel poll action: %d\n",
-			error);
+	if (error)
 		return error;
-	}
 
 	irq = platform_get_irq_byname(pdev, "ONKEY");
 	if (irq < 0)
@@ -246,11 +227,9 @@ static int da9063_onkey_probe(struct platform_device *pdev)
 					  NULL, da9063_onkey_irq_handler,
 					  IRQF_TRIGGER_LOW | IRQF_ONESHOT,
 					  "ONKEY", onkey);
-	if (error) {
-		dev_err(&pdev->dev,
-			"Failed to request IRQ %d: %d\n", irq, error);
-		return error;
-	}
+	if (error)
+		return dev_err_probe(&pdev->dev, error,
+				     "Failed to allocate onkey IRQ\n");
 
 	error = dev_pm_set_wake_irq(&pdev->dev, irq);
 	if (error)
@@ -261,15 +240,19 @@ static int da9063_onkey_probe(struct platform_device *pdev)
 		device_init_wakeup(&pdev->dev, true);
 
 	error = input_register_device(onkey->input);
-	if (error) {
-		dev_err(&pdev->dev,
-			"Failed to register input device: %d\n", error);
+	if (error)
 		return error;
-	}
 
 	return 0;
 }
 
+static const struct of_device_id da9063_compatible_reg_id_table[] = {
+	{ .compatible = "dlg,da9063-onkey", .data = &da9063_regs },
+	{ .compatible = "dlg,da9062-onkey", .data = &da9062_regs },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, da9063_compatible_reg_id_table);
+
 static struct platform_driver da9063_onkey_driver = {
 	.probe	= da9063_onkey_probe,
 	.driver	= {
diff --git a/drivers/input/misc/ims-pcu.c b/drivers/input/misc/ims-pcu.c
index b2f1292e27ef..6e8cc28debd9 100644
--- a/drivers/input/misc/ims-pcu.c
+++ b/drivers/input/misc/ims-pcu.c
@@ -1050,7 +1050,7 @@ static ssize_t ims_pcu_attribute_show(struct device *dev,
 			container_of(dattr, struct ims_pcu_attribute, dattr);
 	char *field = (char *)pcu + attr->field_offset;
 
-	return scnprintf(buf, PAGE_SIZE, "%.*s\n", attr->field_length, field);
+	return sysfs_emit(buf, "%.*s\n", attr->field_length, field);
 }
 
 static ssize_t ims_pcu_attribute_store(struct device *dev,
@@ -1206,7 +1206,7 @@ ims_pcu_update_firmware_status_show(struct device *dev,
 	struct usb_interface *intf = to_usb_interface(dev);
 	struct ims_pcu *pcu = usb_get_intfdata(intf);
 
-	return scnprintf(buf, PAGE_SIZE, "%d\n", pcu->update_firmware_status);
+	return sysfs_emit(buf, "%d\n", pcu->update_firmware_status);
 }
 
 static DEVICE_ATTR(update_firmware_status, S_IRUGO,
@@ -1309,7 +1309,7 @@ static ssize_t ims_pcu_ofn_reg_data_show(struct device *dev,
 	if (error)
 		return error;
 
-	return scnprintf(buf, PAGE_SIZE, "%x\n", data);
+	return sysfs_emit(buf, "%x\n", data);
 }
 
 static ssize_t ims_pcu_ofn_reg_data_store(struct device *dev,
@@ -1344,7 +1344,7 @@ static ssize_t ims_pcu_ofn_reg_addr_show(struct device *dev,
 	int error;
 
 	mutex_lock(&pcu->cmd_mutex);
-	error = scnprintf(buf, PAGE_SIZE, "%x\n", pcu->ofn_reg_addr);
+	error = sysfs_emit(buf, "%x\n", pcu->ofn_reg_addr);
 	mutex_unlock(&pcu->cmd_mutex);
 
 	return error;
@@ -1397,7 +1397,7 @@ static ssize_t ims_pcu_ofn_bit_show(struct device *dev,
 	if (error)
 		return error;
 
-	return scnprintf(buf, PAGE_SIZE, "%d\n", !!(data & (1 << attr->nr)));
+	return sysfs_emit(buf, "%d\n", !!(data & (1 << attr->nr)));
 }
 
 static ssize_t ims_pcu_ofn_bit_store(struct device *dev,
diff --git a/drivers/input/misc/iqs269a.c b/drivers/input/misc/iqs269a.c
index 3c636c75e8a1..cd14ff9f57cf 100644
--- a/drivers/input/misc/iqs269a.c
+++ b/drivers/input/misc/iqs269a.c
@@ -9,6 +9,7 @@
  * axial sliders presented by the device.
  */
 
+#include <linux/bits.h>
 #include <linux/completion.h>
 #include <linux/delay.h>
 #include <linux/device.h>
@@ -26,6 +27,8 @@
 
 #define IQS269_VER_INFO				0x00
 #define IQS269_VER_INFO_PROD_NUM		0x4F
+#define IQS269_VER_INFO_FW_NUM_2		0x03
+#define IQS269_VER_INFO_FW_NUM_3		0x10
 
 #define IQS269_SYS_FLAGS			0x02
 #define IQS269_SYS_FLAGS_SHOW_RESET		BIT(15)
@@ -53,6 +56,7 @@
 #define IQS269_SYS_SETTINGS_ULP_UPDATE_MASK	GENMASK(10, 8)
 #define IQS269_SYS_SETTINGS_ULP_UPDATE_SHIFT	8
 #define IQS269_SYS_SETTINGS_ULP_UPDATE_MAX	7
+#define IQS269_SYS_SETTINGS_SLIDER_SWIPE	BIT(7)
 #define IQS269_SYS_SETTINGS_RESEED_OFFSET	BIT(6)
 #define IQS269_SYS_SETTINGS_EVENT_MODE		BIT(5)
 #define IQS269_SYS_SETTINGS_EVENT_MODE_LP	BIT(4)
@@ -69,6 +73,7 @@
 #define IQS269_FILT_STR_MAX			3
 
 #define IQS269_EVENT_MASK_SYS			BIT(6)
+#define IQS269_EVENT_MASK_GESTURE		BIT(3)
 #define IQS269_EVENT_MASK_DEEP			BIT(2)
 #define IQS269_EVENT_MASK_TOUCH			BIT(1)
 #define IQS269_EVENT_MASK_PROX			BIT(0)
@@ -97,6 +102,15 @@
 #define IQS269_MISC_B_TRACKING_UI_ENABLE	BIT(4)
 #define IQS269_MISC_B_FILT_STR_SLIDER		GENMASK(1, 0)
 
+#define IQS269_TOUCH_HOLD_SLIDER_SEL		0x89
+#define IQS269_TOUCH_HOLD_DEFAULT		0x14
+#define IQS269_TOUCH_HOLD_MS_MIN		256
+#define IQS269_TOUCH_HOLD_MS_MAX		65280
+
+#define IQS269_TIMEOUT_TAP_MS_MAX		4080
+#define IQS269_TIMEOUT_SWIPE_MS_MAX		4080
+#define IQS269_THRESH_SWIPE_MAX			255
+
 #define IQS269_CHx_ENG_A_MEAS_CAP_SIZE		BIT(15)
 #define IQS269_CHx_ENG_A_RX_GND_INACTIVE	BIT(13)
 #define IQS269_CHx_ENG_A_LOCAL_CAP_SIZE		BIT(12)
@@ -142,6 +156,10 @@
 
 #define IQS269_MAX_REG				0xFF
 
+#define IQS269_OTP_OPTION_DEFAULT		0x00
+#define IQS269_OTP_OPTION_TWS			0xD0
+#define IQS269_OTP_OPTION_HOLD			BIT(7)
+
 #define IQS269_NUM_CH				8
 #define IQS269_NUM_SL				2
 
@@ -175,6 +193,20 @@ enum iqs269_event_id {
 	IQS269_EVENT_DEEP_UP,
 };
 
+enum iqs269_slider_id {
+	IQS269_SLIDER_NONE,
+	IQS269_SLIDER_KEY,
+	IQS269_SLIDER_RAW,
+};
+
+enum iqs269_gesture_id {
+	IQS269_GESTURE_TAP,
+	IQS269_GESTURE_HOLD,
+	IQS269_GESTURE_FLICK_POS,
+	IQS269_GESTURE_FLICK_NEG,
+	IQS269_NUM_GESTURES,
+};
+
 struct iqs269_switch_desc {
 	unsigned int code;
 	bool enabled;
@@ -234,7 +266,7 @@ struct iqs269_ver_info {
 	u8 prod_num;
 	u8 sw_num;
 	u8 hw_num;
-	u8 padding;
+	u8 fw_num;
 } __packed;
 
 struct iqs269_ch_reg {
@@ -285,16 +317,42 @@ struct iqs269_private {
 	struct regmap *regmap;
 	struct mutex lock;
 	struct iqs269_switch_desc switches[ARRAY_SIZE(iqs269_events)];
+	struct iqs269_ver_info ver_info;
 	struct iqs269_sys_reg sys_reg;
 	struct completion ati_done;
 	struct input_dev *keypad;
 	struct input_dev *slider[IQS269_NUM_SL];
 	unsigned int keycode[ARRAY_SIZE(iqs269_events) * IQS269_NUM_CH];
+	unsigned int sl_code[IQS269_NUM_SL][IQS269_NUM_GESTURES];
+	unsigned int otp_option;
 	unsigned int ch_num;
 	bool hall_enable;
 	bool ati_current;
 };
 
+static enum iqs269_slider_id iqs269_slider_type(struct iqs269_private *iqs269,
+						int slider_num)
+{
+	int i;
+
+	/*
+	 * Slider 1 is unavailable if the touch-and-hold option is enabled via
+	 * OTP. In that case, the channel selection register is repurposed for
+	 * the touch-and-hold timer ceiling.
+	 */
+	if (slider_num && (iqs269->otp_option & IQS269_OTP_OPTION_HOLD))
+		return IQS269_SLIDER_NONE;
+
+	if (!iqs269->sys_reg.slider_select[slider_num])
+		return IQS269_SLIDER_NONE;
+
+	for (i = 0; i < IQS269_NUM_GESTURES; i++)
+		if (iqs269->sl_code[slider_num][i] != KEY_RESERVED)
+			return IQS269_SLIDER_KEY;
+
+	return IQS269_SLIDER_RAW;
+}
+
 static int iqs269_ati_mode_set(struct iqs269_private *iqs269,
 			       unsigned int ch_num, unsigned int mode)
 {
@@ -525,7 +583,8 @@ static int iqs269_parse_chan(struct iqs269_private *iqs269,
 	if (fwnode_property_present(ch_node, "azoteq,slider0-select"))
 		iqs269->sys_reg.slider_select[0] |= BIT(reg);
 
-	if (fwnode_property_present(ch_node, "azoteq,slider1-select"))
+	if (fwnode_property_present(ch_node, "azoteq,slider1-select") &&
+	    !(iqs269->otp_option & IQS269_OTP_OPTION_HOLD))
 		iqs269->sys_reg.slider_select[1] |= BIT(reg);
 
 	ch_reg = &iqs269->sys_reg.ch_reg[reg];
@@ -950,7 +1009,43 @@ static int iqs269_parse_prop(struct iqs269_private *iqs269)
 	sys_reg->blocking = 0;
 
 	sys_reg->slider_select[0] = 0;
-	sys_reg->slider_select[1] = 0;
+
+	/*
+	 * If configured via OTP to do so, the device asserts a pulse on the
+	 * GPIO4 pin for approximately 60 ms once a selected channel is held
+	 * in a state of touch for a configurable length of time.
+	 *
+	 * In that case, the register used for slider 1 channel selection is
+	 * repurposed for the touch-and-hold timer ceiling.
+	 */
+	if (iqs269->otp_option & IQS269_OTP_OPTION_HOLD) {
+		if (!device_property_read_u32(&client->dev,
+					      "azoteq,touch-hold-ms", &val)) {
+			if (val < IQS269_TOUCH_HOLD_MS_MIN ||
+			    val > IQS269_TOUCH_HOLD_MS_MAX) {
+				dev_err(&client->dev,
+					"Invalid touch-and-hold ceiling: %u\n",
+					val);
+				return -EINVAL;
+			}
+
+			sys_reg->slider_select[1] = val / 256;
+		} else if (iqs269->ver_info.fw_num < IQS269_VER_INFO_FW_NUM_3) {
+			/*
+			 * The default touch-and-hold timer ceiling initially
+			 * read from early revisions of silicon is invalid if
+			 * the device experienced a soft reset between power-
+			 * on and the read operation.
+			 *
+			 * To protect against this case, explicitly cache the
+			 * default value so that it is restored each time the
+			 * device is re-initialized.
+			 */
+			sys_reg->slider_select[1] = IQS269_TOUCH_HOLD_DEFAULT;
+		}
+	} else {
+		sys_reg->slider_select[1] = 0;
+	}
 
 	sys_reg->event_mask = ~((u8)IQS269_EVENT_MASK_SYS);
 
@@ -1004,6 +1099,76 @@ static int iqs269_parse_prop(struct iqs269_private *iqs269)
 		general |= (val << IQS269_SYS_SETTINGS_ULP_UPDATE_SHIFT);
 	}
 
+	if (device_property_present(&client->dev, "linux,keycodes")) {
+		int scale = 1;
+		int count = device_property_count_u32(&client->dev,
+						      "linux,keycodes");
+		if (count > IQS269_NUM_GESTURES * IQS269_NUM_SL) {
+			dev_err(&client->dev, "Too many keycodes present\n");
+			return -EINVAL;
+		} else if (count < 0) {
+			dev_err(&client->dev, "Failed to count keycodes: %d\n",
+				count);
+			return count;
+		}
+
+		error = device_property_read_u32_array(&client->dev,
+						       "linux,keycodes",
+						       *iqs269->sl_code, count);
+		if (error) {
+			dev_err(&client->dev, "Failed to read keycodes: %d\n",
+				error);
+			return error;
+		}
+
+		if (device_property_present(&client->dev,
+					    "azoteq,gesture-swipe"))
+			general |= IQS269_SYS_SETTINGS_SLIDER_SWIPE;
+
+		/*
+		 * Early revisions of silicon use a more granular step size for
+		 * tap and swipe gesture timeouts; scale them appropriately.
+		 */
+		if (iqs269->ver_info.fw_num < IQS269_VER_INFO_FW_NUM_3)
+			scale = 4;
+
+		if (!device_property_read_u32(&client->dev,
+					      "azoteq,timeout-tap-ms", &val)) {
+			if (val > IQS269_TIMEOUT_TAP_MS_MAX / scale) {
+				dev_err(&client->dev, "Invalid timeout: %u\n",
+					val);
+				return -EINVAL;
+			}
+
+			sys_reg->timeout_tap = val / (16 / scale);
+		}
+
+		if (!device_property_read_u32(&client->dev,
+					      "azoteq,timeout-swipe-ms",
+					      &val)) {
+			if (val > IQS269_TIMEOUT_SWIPE_MS_MAX / scale) {
+				dev_err(&client->dev, "Invalid timeout: %u\n",
+					val);
+				return -EINVAL;
+			}
+
+			sys_reg->timeout_swipe = val / (16 / scale);
+		}
+
+		if (!device_property_read_u32(&client->dev,
+					      "azoteq,thresh-swipe", &val)) {
+			if (val > IQS269_THRESH_SWIPE_MAX) {
+				dev_err(&client->dev, "Invalid threshold: %u\n",
+					val);
+				return -EINVAL;
+			}
+
+			sys_reg->thresh_swipe = val;
+		}
+
+		sys_reg->event_mask &= ~IQS269_EVENT_MASK_GESTURE;
+	}
+
 	general &= ~IQS269_SYS_SETTINGS_RESEED_OFFSET;
 	if (device_property_present(&client->dev, "azoteq,reseed-offset"))
 		general |= IQS269_SYS_SETTINGS_RESEED_OFFSET;
@@ -1012,10 +1177,11 @@ static int iqs269_parse_prop(struct iqs269_private *iqs269)
 
 	/*
 	 * As per the datasheet, enable streaming during normal-power mode if
-	 * either slider is in use. In that case, the device returns to event
-	 * mode during low-power mode.
+	 * raw coordinates will be read from either slider. In that case, the
+	 * device returns to event mode during low-power mode.
 	 */
-	if (sys_reg->slider_select[0] || sys_reg->slider_select[1])
+	if (iqs269_slider_type(iqs269, 0) == IQS269_SLIDER_RAW ||
+	    iqs269_slider_type(iqs269, 1) == IQS269_SLIDER_RAW)
 		general |= IQS269_SYS_SETTINGS_EVENT_MODE_LP;
 
 	general |= IQS269_SYS_SETTINGS_REDO_ATI;
@@ -1026,12 +1192,30 @@ static int iqs269_parse_prop(struct iqs269_private *iqs269)
 	return 0;
 }
 
+static const struct reg_sequence iqs269_tws_init[] = {
+	{ IQS269_TOUCH_HOLD_SLIDER_SEL, IQS269_TOUCH_HOLD_DEFAULT },
+	{ 0xF0, 0x580F },
+	{ 0xF0, 0x59EF },
+};
+
 static int iqs269_dev_init(struct iqs269_private *iqs269)
 {
 	int error;
 
 	mutex_lock(&iqs269->lock);
 
+	/*
+	 * Early revisions of silicon require the following workaround in order
+	 * to restore any OTP-enabled functionality after a soft reset.
+	 */
+	if (iqs269->otp_option == IQS269_OTP_OPTION_TWS &&
+	    iqs269->ver_info.fw_num < IQS269_VER_INFO_FW_NUM_3) {
+		error = regmap_multi_reg_write(iqs269->regmap, iqs269_tws_init,
+					       ARRAY_SIZE(iqs269_tws_init));
+		if (error)
+			goto err_mutex;
+	}
+
 	error = regmap_update_bits(iqs269->regmap, IQS269_HALL_UI,
 				   IQS269_HALL_UI_ENABLE,
 				   iqs269->hall_enable ? ~0 : 0);
@@ -1106,19 +1290,37 @@ static int iqs269_input_init(struct iqs269_private *iqs269)
 	}
 
 	for (i = 0; i < IQS269_NUM_SL; i++) {
-		if (!iqs269->sys_reg.slider_select[i])
+		if (iqs269_slider_type(iqs269, i) == IQS269_SLIDER_NONE)
 			continue;
 
 		iqs269->slider[i] = devm_input_allocate_device(&client->dev);
 		if (!iqs269->slider[i])
 			return -ENOMEM;
 
+		iqs269->slider[i]->keycodemax = ARRAY_SIZE(iqs269->sl_code[i]);
+		iqs269->slider[i]->keycode = iqs269->sl_code[i];
+		iqs269->slider[i]->keycodesize = sizeof(**iqs269->sl_code);
+
 		iqs269->slider[i]->name = i ? "iqs269a_slider_1"
 					    : "iqs269a_slider_0";
 		iqs269->slider[i]->id.bustype = BUS_I2C;
 
-		input_set_capability(iqs269->slider[i], EV_KEY, BTN_TOUCH);
-		input_set_abs_params(iqs269->slider[i], ABS_X, 0, 255, 0, 0);
+		for (j = 0; j < IQS269_NUM_GESTURES; j++)
+			if (iqs269->sl_code[i][j] != KEY_RESERVED)
+				input_set_capability(iqs269->slider[i], EV_KEY,
+						     iqs269->sl_code[i][j]);
+
+		/*
+		 * Present the slider as a narrow trackpad if one or more chan-
+		 * nels have been selected to participate, but no gestures have
+		 * been mapped to a keycode.
+		 */
+		if (iqs269_slider_type(iqs269, i) == IQS269_SLIDER_RAW) {
+			input_set_capability(iqs269->slider[i],
+					     EV_KEY, BTN_TOUCH);
+			input_set_abs_params(iqs269->slider[i],
+					     ABS_X, 0, 255, 0, 0);
+		}
 
 		error = input_register_device(iqs269->slider[i]);
 		if (error) {
@@ -1167,28 +1369,62 @@ static int iqs269_report(struct iqs269_private *iqs269)
 	if (be16_to_cpu(flags.system) & IQS269_SYS_FLAGS_IN_ATI)
 		return 0;
 
-	error = regmap_raw_read(iqs269->regmap, IQS269_SLIDER_X, slider_x,
-				sizeof(slider_x));
-	if (error) {
-		dev_err(&client->dev, "Failed to read slider position: %d\n",
-			error);
-		return error;
+	if (iqs269_slider_type(iqs269, 0) == IQS269_SLIDER_RAW ||
+	    iqs269_slider_type(iqs269, 1) == IQS269_SLIDER_RAW) {
+		error = regmap_raw_read(iqs269->regmap, IQS269_SLIDER_X,
+					slider_x, sizeof(slider_x));
+		if (error) {
+			dev_err(&client->dev,
+				"Failed to read slider position: %d\n", error);
+			return error;
+		}
 	}
 
 	for (i = 0; i < IQS269_NUM_SL; i++) {
-		if (!iqs269->sys_reg.slider_select[i])
+		flags.gesture >>= (i * IQS269_NUM_GESTURES);
+
+		switch (iqs269_slider_type(iqs269, i)) {
+		case IQS269_SLIDER_NONE:
 			continue;
 
-		/*
-		 * Report BTN_TOUCH if any channel that participates in the
-		 * slider is in a state of touch.
-		 */
-		if (flags.states[IQS269_ST_OFFS_TOUCH] &
-		    iqs269->sys_reg.slider_select[i]) {
-			input_report_key(iqs269->slider[i], BTN_TOUCH, 1);
-			input_report_abs(iqs269->slider[i], ABS_X, slider_x[i]);
-		} else {
-			input_report_key(iqs269->slider[i], BTN_TOUCH, 0);
+		case IQS269_SLIDER_KEY:
+			for (j = 0; j < IQS269_NUM_GESTURES; j++)
+				input_report_key(iqs269->slider[i],
+						 iqs269->sl_code[i][j],
+						 flags.gesture & BIT(j));
+
+			if (!(flags.gesture & (BIT(IQS269_GESTURE_FLICK_NEG) |
+					       BIT(IQS269_GESTURE_FLICK_POS) |
+					       BIT(IQS269_GESTURE_TAP))))
+				break;
+
+			input_sync(iqs269->slider[i]);
+
+			/*
+			 * Momentary gestures are followed by a complementary
+			 * release cycle so as to emulate a full keystroke.
+			 */
+			for (j = 0; j < IQS269_NUM_GESTURES; j++)
+				if (j != IQS269_GESTURE_HOLD)
+					input_report_key(iqs269->slider[i],
+							 iqs269->sl_code[i][j],
+							 0);
+			break;
+
+		case IQS269_SLIDER_RAW:
+			/*
+			 * The slider is considered to be in a state of touch
+			 * if any selected channels are in a state of touch.
+			 */
+			state = flags.states[IQS269_ST_OFFS_TOUCH];
+			state &= iqs269->sys_reg.slider_select[i];
+
+			input_report_key(iqs269->slider[i], BTN_TOUCH, state);
+
+			if (state)
+				input_report_abs(iqs269->slider[i],
+						 ABS_X, slider_x[i]);
+			break;
 		}
 
 		input_sync(iqs269->slider[i]);
@@ -1286,7 +1522,7 @@ static ssize_t counts_show(struct device *dev,
 	if (error)
 		return error;
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n", le16_to_cpu(counts));
+	return sysfs_emit(buf, "%u\n", le16_to_cpu(counts));
 }
 
 static ssize_t hall_bin_show(struct device *dev,
@@ -1324,7 +1560,7 @@ static ssize_t hall_bin_show(struct device *dev,
 		return -EINVAL;
 	}
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n", val);
+	return sysfs_emit(buf, "%u\n", val);
 }
 
 static ssize_t hall_enable_show(struct device *dev,
@@ -1332,7 +1568,7 @@ static ssize_t hall_enable_show(struct device *dev,
 {
 	struct iqs269_private *iqs269 = dev_get_drvdata(dev);
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n", iqs269->hall_enable);
+	return sysfs_emit(buf, "%u\n", iqs269->hall_enable);
 }
 
 static ssize_t hall_enable_store(struct device *dev,
@@ -1362,7 +1598,7 @@ static ssize_t ch_number_show(struct device *dev,
 {
 	struct iqs269_private *iqs269 = dev_get_drvdata(dev);
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n", iqs269->ch_num);
+	return sysfs_emit(buf, "%u\n", iqs269->ch_num);
 }
 
 static ssize_t ch_number_store(struct device *dev,
@@ -1391,8 +1627,7 @@ static ssize_t rx_enable_show(struct device *dev,
 	struct iqs269_private *iqs269 = dev_get_drvdata(dev);
 	struct iqs269_ch_reg *ch_reg = iqs269->sys_reg.ch_reg;
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n",
-			 ch_reg[iqs269->ch_num].rx_enable);
+	return sysfs_emit(buf, "%u\n", ch_reg[iqs269->ch_num].rx_enable);
 }
 
 static ssize_t rx_enable_store(struct device *dev,
@@ -1432,7 +1667,7 @@ static ssize_t ati_mode_show(struct device *dev,
 	if (error)
 		return error;
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n", val);
+	return sysfs_emit(buf, "%u\n", val);
 }
 
 static ssize_t ati_mode_store(struct device *dev,
@@ -1465,7 +1700,7 @@ static ssize_t ati_base_show(struct device *dev,
 	if (error)
 		return error;
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n", val);
+	return sysfs_emit(buf, "%u\n", val);
 }
 
 static ssize_t ati_base_store(struct device *dev,
@@ -1498,7 +1733,7 @@ static ssize_t ati_target_show(struct device *dev,
 	if (error)
 		return error;
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n", val);
+	return sysfs_emit(buf, "%u\n", val);
 }
 
 static ssize_t ati_target_store(struct device *dev,
@@ -1525,9 +1760,9 @@ static ssize_t ati_trigger_show(struct device *dev,
 {
 	struct iqs269_private *iqs269 = dev_get_drvdata(dev);
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n",
-			 iqs269->ati_current &&
-			 completion_done(&iqs269->ati_done));
+	return sysfs_emit(buf, "%u\n",
+			  iqs269->ati_current &&
+			  completion_done(&iqs269->ati_done));
 }
 
 static ssize_t ati_trigger_store(struct device *dev,
@@ -1596,7 +1831,6 @@ static const struct regmap_config iqs269_regmap_config = {
 
 static int iqs269_probe(struct i2c_client *client)
 {
-	struct iqs269_ver_info ver_info;
 	struct iqs269_private *iqs269;
 	int error;
 
@@ -1618,14 +1852,16 @@ static int iqs269_probe(struct i2c_client *client)
 	mutex_init(&iqs269->lock);
 	init_completion(&iqs269->ati_done);
 
-	error = regmap_raw_read(iqs269->regmap, IQS269_VER_INFO, &ver_info,
-				sizeof(ver_info));
+	iqs269->otp_option = (uintptr_t)device_get_match_data(&client->dev);
+
+	error = regmap_raw_read(iqs269->regmap, IQS269_VER_INFO,
+				&iqs269->ver_info, sizeof(iqs269->ver_info));
 	if (error)
 		return error;
 
-	if (ver_info.prod_num != IQS269_VER_INFO_PROD_NUM) {
+	if (iqs269->ver_info.prod_num != IQS269_VER_INFO_PROD_NUM) {
 		dev_err(&client->dev, "Unrecognized product number: 0x%02X\n",
-			ver_info.prod_num);
+			iqs269->ver_info.prod_num);
 		return -EINVAL;
 	}
 
@@ -1728,7 +1964,18 @@ static int iqs269_resume(struct device *dev)
 static DEFINE_SIMPLE_DEV_PM_OPS(iqs269_pm, iqs269_suspend, iqs269_resume);
 
 static const struct of_device_id iqs269_of_match[] = {
-	{ .compatible = "azoteq,iqs269a" },
+	{
+		.compatible = "azoteq,iqs269a",
+		.data = (void *)IQS269_OTP_OPTION_DEFAULT,
+	},
+	{
+		.compatible = "azoteq,iqs269a-00",
+		.data = (void *)IQS269_OTP_OPTION_DEFAULT,
+	},
+	{
+		.compatible = "azoteq,iqs269a-d0",
+		.data = (void *)IQS269_OTP_OPTION_TWS,
+	},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, iqs269_of_match);
diff --git a/drivers/input/misc/max77693-haptic.c b/drivers/input/misc/max77693-haptic.c
index 80f4416ffe2f..0e646f1b257b 100644
--- a/drivers/input/misc/max77693-haptic.c
+++ b/drivers/input/misc/max77693-haptic.c
@@ -307,7 +307,7 @@ static int max77693_haptic_probe(struct platform_device *pdev)
 	haptic->suspend_state = false;
 
 	/* Variant-specific init */
-	haptic->dev_type = platform_get_device_id(pdev)->driver_data;
+	haptic->dev_type = max77693->type;
 	switch (haptic->dev_type) {
 	case TYPE_MAX77693:
 		haptic->regmap_haptic = max77693->regmap_haptic;
@@ -406,16 +406,24 @@ static DEFINE_SIMPLE_DEV_PM_OPS(max77693_haptic_pm_ops,
 				max77693_haptic_resume);
 
 static const struct platform_device_id max77693_haptic_id[] = {
-	{ "max77693-haptic", TYPE_MAX77693 },
-	{ "max77843-haptic", TYPE_MAX77843 },
+	{ "max77693-haptic", },
+	{ "max77843-haptic", },
 	{},
 };
 MODULE_DEVICE_TABLE(platform, max77693_haptic_id);
 
+static const struct of_device_id of_max77693_haptic_dt_match[] = {
+	{ .compatible = "maxim,max77693-haptic", },
+	{ .compatible = "maxim,max77843-haptic", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, of_max77693_haptic_dt_match);
+
 static struct platform_driver max77693_haptic_driver = {
 	.driver		= {
 		.name	= "max77693-haptic",
 		.pm	= pm_sleep_ptr(&max77693_haptic_pm_ops),
+		.of_match_table = of_max77693_haptic_dt_match,
 	},
 	.probe		= max77693_haptic_probe,
 	.id_table	= max77693_haptic_id,
diff --git a/drivers/input/mouse/cyapa.c b/drivers/input/mouse/cyapa.c
index a84098448f5b..5979deabe23d 100644
--- a/drivers/input/mouse/cyapa.c
+++ b/drivers/input/mouse/cyapa.c
@@ -756,16 +756,16 @@ static ssize_t cyapa_show_suspend_scanrate(struct device *dev,
 
 	switch (pwr_cmd) {
 	case PWR_MODE_BTN_ONLY:
-		len = scnprintf(buf, PAGE_SIZE, "%s\n", BTN_ONLY_MODE_NAME);
+		len = sysfs_emit(buf, "%s\n", BTN_ONLY_MODE_NAME);
 		break;
 
 	case PWR_MODE_OFF:
-		len = scnprintf(buf, PAGE_SIZE, "%s\n", OFF_MODE_NAME);
+		len = sysfs_emit(buf, "%s\n", OFF_MODE_NAME);
 		break;
 
 	default:
-		len = scnprintf(buf, PAGE_SIZE, "%u\n",
-				cyapa->gen == CYAPA_GEN3 ?
+		len = sysfs_emit(buf, "%u\n",
+				 cyapa->gen == CYAPA_GEN3 ?
 					cyapa_pwr_cmd_to_sleep_time(pwr_cmd) :
 					sleep_time);
 		break;
@@ -877,8 +877,8 @@ static ssize_t cyapa_show_rt_suspend_scanrate(struct device *dev,
 
 	mutex_unlock(&cyapa->state_sync_lock);
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n",
-			 cyapa->gen == CYAPA_GEN3 ?
+	return sysfs_emit(buf, "%u\n",
+			  cyapa->gen == CYAPA_GEN3 ?
 				cyapa_pwr_cmd_to_sleep_time(pwr_cmd) :
 				sleep_time);
 }
@@ -988,8 +988,8 @@ static ssize_t cyapa_show_fm_ver(struct device *dev,
 	error = mutex_lock_interruptible(&cyapa->state_sync_lock);
 	if (error)
 		return error;
-	error = scnprintf(buf, PAGE_SIZE, "%d.%d\n", cyapa->fw_maj_ver,
-			 cyapa->fw_min_ver);
+	error = sysfs_emit(buf, "%d.%d\n",
+			   cyapa->fw_maj_ver, cyapa->fw_min_ver);
 	mutex_unlock(&cyapa->state_sync_lock);
 	return error;
 }
@@ -1004,7 +1004,7 @@ static ssize_t cyapa_show_product_id(struct device *dev,
 	error = mutex_lock_interruptible(&cyapa->state_sync_lock);
 	if (error)
 		return error;
-	size = scnprintf(buf, PAGE_SIZE, "%s\n", cyapa->product_id);
+	size = sysfs_emit(buf, "%s\n", cyapa->product_id);
 	mutex_unlock(&cyapa->state_sync_lock);
 	return size;
 }
@@ -1209,8 +1209,8 @@ static ssize_t cyapa_show_mode(struct device *dev,
 	if (error)
 		return error;
 
-	size = scnprintf(buf, PAGE_SIZE, "gen%d %s\n",
-			cyapa->gen, cyapa_state_to_string(cyapa));
+	size = sysfs_emit(buf, "gen%d %s\n",
+			  cyapa->gen, cyapa_state_to_string(cyapa));
 
 	mutex_unlock(&cyapa->state_sync_lock);
 	return size;
diff --git a/drivers/input/mouse/cyapa_gen3.c b/drivers/input/mouse/cyapa_gen3.c
index a97f4acb6452..60c83bc71d84 100644
--- a/drivers/input/mouse/cyapa_gen3.c
+++ b/drivers/input/mouse/cyapa_gen3.c
@@ -860,7 +860,7 @@ static ssize_t cyapa_gen3_show_baseline(struct device *dev,
 
 	dev_dbg(dev, "Baseline report successful. Max: %d Min: %d\n",
 		max_baseline, min_baseline);
-	ret = scnprintf(buf, PAGE_SIZE, "%d %d\n", max_baseline, min_baseline);
+	ret = sysfs_emit(buf, "%d %d\n", max_baseline, min_baseline);
 
 out:
 	return ret;
diff --git a/drivers/input/mouse/cyapa_gen5.c b/drivers/input/mouse/cyapa_gen5.c
index abf42f77b4c5..2e6bcb07257e 100644
--- a/drivers/input/mouse/cyapa_gen5.c
+++ b/drivers/input/mouse/cyapa_gen5.c
@@ -2418,12 +2418,12 @@ resume_scanning:
 		return resume_error ? resume_error : error;
 
 	/* 12. Output data strings */
-	size = scnprintf(buf, PAGE_SIZE, "%d %d %d %d %d %d %d %d %d %d %d ",
+	size = sysfs_emit(buf, "%d %d %d %d %d %d %d %d %d %d %d ",
 		gidac_mutual_min, gidac_mutual_max, gidac_mutual_ave,
 		lidac_mutual_min, lidac_mutual_max, lidac_mutual_ave,
 		gidac_self_rx, gidac_self_tx,
 		lidac_self_min, lidac_self_max, lidac_self_ave);
-	size += scnprintf(buf + size, PAGE_SIZE - size,
+	size += sysfs_emit_at(buf, size,
 		"%d %d %d %d %d %d %d %d %d %d %d %d %d %d %d %d %d %d\n",
 		raw_cap_mutual_min, raw_cap_mutual_max, raw_cap_mutual_ave,
 		raw_cap_self_min, raw_cap_self_max, raw_cap_self_ave,
diff --git a/drivers/input/mouse/cyapa_gen6.c b/drivers/input/mouse/cyapa_gen6.c
index 0caaf3e64215..4ffe08fee10c 100644
--- a/drivers/input/mouse/cyapa_gen6.c
+++ b/drivers/input/mouse/cyapa_gen6.c
@@ -629,14 +629,14 @@ static ssize_t cyapa_gen6_show_baseline(struct device *dev,
 	if (error)
 		goto resume_scanning;
 
-	size = scnprintf(buf, PAGE_SIZE, "%d %d %d %d %d %d ",
-			data[0],  /* RX Attenuator Mutual */
-			data[1],  /* IDAC Mutual */
-			data[2],  /* RX Attenuator Self RX */
-			data[3],  /* IDAC Self RX */
-			data[4],  /* RX Attenuator Self TX */
-			data[5]	  /* IDAC Self TX */
-			);
+	size = sysfs_emit(buf, "%d %d %d %d %d %d ",
+			  data[0],  /* RX Attenuator Mutual */
+			  data[1],  /* IDAC Mutual */
+			  data[2],  /* RX Attenuator Self RX */
+			  data[3],  /* IDAC Self RX */
+			  data[4],  /* RX Attenuator Self TX */
+			  data[5]   /* IDAC Self TX */
+			 );
 
 	/* 3. Read Attenuator Trim. */
 	data_len = sizeof(data);
@@ -648,8 +648,8 @@ static ssize_t cyapa_gen6_show_baseline(struct device *dev,
 
 	/* set attenuator trim values. */
 	for (i = 0; i < data_len; i++)
-		size += scnprintf(buf + size, PAGE_SIZE - size,	"%d ", data[i]);
-	size += scnprintf(buf + size, PAGE_SIZE - size, "\n");
+		size += sysfs_emit_at(buf, size, "%d ", data[i]);
+	size += sysfs_emit_at(buf, size, "\n");
 
 resume_scanning:
 	/* 4. Resume Scanning*/
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index 148a601396f9..8a72c200ccb5 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -572,7 +572,7 @@ static ssize_t elan_sysfs_read_fw_checksum(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct elan_tp_data *data = i2c_get_clientdata(client);
 
-	return sprintf(buf, "0x%04x\n", data->fw_checksum);
+	return sysfs_emit(buf, "0x%04x\n", data->fw_checksum);
 }
 
 static ssize_t elan_sysfs_read_product_id(struct device *dev,
@@ -582,8 +582,8 @@ static ssize_t elan_sysfs_read_product_id(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct elan_tp_data *data = i2c_get_clientdata(client);
 
-	return sprintf(buf, ETP_PRODUCT_ID_FORMAT_STRING "\n",
-		       data->product_id);
+	return sysfs_emit(buf, ETP_PRODUCT_ID_FORMAT_STRING "\n",
+			  data->product_id);
 }
 
 static ssize_t elan_sysfs_read_fw_ver(struct device *dev,
@@ -593,7 +593,7 @@ static ssize_t elan_sysfs_read_fw_ver(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct elan_tp_data *data = i2c_get_clientdata(client);
 
-	return sprintf(buf, "%d.0\n", data->fw_version);
+	return sysfs_emit(buf, "%d.0\n", data->fw_version);
 }
 
 static ssize_t elan_sysfs_read_sm_ver(struct device *dev,
@@ -603,7 +603,7 @@ static ssize_t elan_sysfs_read_sm_ver(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct elan_tp_data *data = i2c_get_clientdata(client);
 
-	return sprintf(buf, "%d.0\n", data->sm_version);
+	return sysfs_emit(buf, "%d.0\n", data->sm_version);
 }
 
 static ssize_t elan_sysfs_read_iap_ver(struct device *dev,
@@ -613,7 +613,7 @@ static ssize_t elan_sysfs_read_iap_ver(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct elan_tp_data *data = i2c_get_clientdata(client);
 
-	return sprintf(buf, "%d.0\n", data->iap_version);
+	return sysfs_emit(buf, "%d.0\n", data->iap_version);
 }
 
 static ssize_t elan_sysfs_update_fw(struct device *dev,
@@ -754,7 +754,7 @@ static ssize_t elan_sysfs_read_mode(struct device *dev,
 	if (error)
 		return error;
 
-	return sprintf(buf, "%d\n", (int)mode);
+	return sysfs_emit(buf, "%d\n", (int)mode);
 }
 
 static DEVICE_ATTR(product_id, S_IRUGO, elan_sysfs_read_product_id, NULL);
@@ -858,7 +858,7 @@ static ssize_t min_show(struct device *dev,
 		goto out;
 	}
 
-	retval = snprintf(buf, PAGE_SIZE, "%d", data->min_baseline);
+	retval = sysfs_emit(buf, "%d", data->min_baseline);
 
 out:
 	mutex_unlock(&data->sysfs_mutex);
@@ -881,7 +881,7 @@ static ssize_t max_show(struct device *dev,
 		goto out;
 	}
 
-	retval = snprintf(buf, PAGE_SIZE, "%d", data->max_baseline);
+	retval = sysfs_emit(buf, "%d", data->max_baseline);
 
 out:
 	mutex_unlock(&data->sysfs_mutex);
diff --git a/drivers/input/mouse/navpoint.c b/drivers/input/mouse/navpoint.c
index c00dc1275da2..ba757783c258 100644
--- a/drivers/input/mouse/navpoint.c
+++ b/drivers/input/mouse/navpoint.c
@@ -10,7 +10,7 @@
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/input.h>
 #include <linux/input/navpoint.h>
 #include <linux/interrupt.h>
@@ -32,7 +32,7 @@ struct navpoint {
 	struct ssp_device	*ssp;
 	struct input_dev	*input;
 	struct device		*dev;
-	int			gpio;
+	struct gpio_desc	*gpiod;
 	int			index;
 	u8			data[1 + HEADER_LENGTH(0xff)];
 };
@@ -170,16 +170,14 @@ static void navpoint_up(struct navpoint *navpoint)
 		dev_err(navpoint->dev,
 			"timeout waiting for SSSR[CSS] to clear\n");
 
-	if (gpio_is_valid(navpoint->gpio))
-		gpio_set_value(navpoint->gpio, 1);
+	gpiod_set_value(navpoint->gpiod, 1);
 }
 
 static void navpoint_down(struct navpoint *navpoint)
 {
 	struct ssp_device *ssp = navpoint->ssp;
 
-	if (gpio_is_valid(navpoint->gpio))
-		gpio_set_value(navpoint->gpio, 0);
+	gpiod_set_value(navpoint->gpiod, 0);
 
 	pxa_ssp_write_reg(ssp, SSCR0, 0);
 
@@ -216,18 +214,9 @@ static int navpoint_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	if (gpio_is_valid(pdata->gpio)) {
-		error = gpio_request_one(pdata->gpio, GPIOF_OUT_INIT_LOW,
-					 "SYNAPTICS_ON");
-		if (error)
-			return error;
-	}
-
 	ssp = pxa_ssp_request(pdata->port, pdev->name);
-	if (!ssp) {
-		error = -ENODEV;
-		goto err_free_gpio;
-	}
+	if (!ssp)
+		return -ENODEV;
 
 	/* HaRET does not disable devices before jumping into Linux */
 	if (pxa_ssp_read_reg(ssp, SSCR0) & SSCR0_SSE) {
@@ -242,10 +231,18 @@ static int navpoint_probe(struct platform_device *pdev)
 		goto err_free_mem;
 	}
 
+	navpoint->gpiod = gpiod_get_optional(&pdev->dev,
+					     NULL, GPIOD_OUT_LOW);
+	if (IS_ERR(navpoint->gpiod)) {
+		error = PTR_ERR(navpoint->gpiod);
+		dev_err(&pdev->dev, "error getting GPIO\n");
+		goto err_free_mem;
+	}
+	gpiod_set_consumer_name(navpoint->gpiod, "SYNAPTICS_ON");
+
 	navpoint->ssp = ssp;
 	navpoint->input = input;
 	navpoint->dev = &pdev->dev;
-	navpoint->gpio = pdata->gpio;
 
 	input->name = pdev->name;
 	input->dev.parent = &pdev->dev;
@@ -288,17 +285,12 @@ err_free_mem:
 	input_free_device(input);
 	kfree(navpoint);
 	pxa_ssp_free(ssp);
-err_free_gpio:
-	if (gpio_is_valid(pdata->gpio))
-		gpio_free(pdata->gpio);
 
 	return error;
 }
 
 static void navpoint_remove(struct platform_device *pdev)
 {
-	const struct navpoint_platform_data *pdata =
-					dev_get_platdata(&pdev->dev);
 	struct navpoint *navpoint = platform_get_drvdata(pdev);
 	struct ssp_device *ssp = navpoint->ssp;
 
@@ -308,9 +300,6 @@ static void navpoint_remove(struct platform_device *pdev)
 	kfree(navpoint);
 
 	pxa_ssp_free(ssp);
-
-	if (gpio_is_valid(pdata->gpio))
-		gpio_free(pdata->gpio);
 }
 
 static int navpoint_suspend(struct device *dev)
diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c
index 258d5fe3d395..42eaebb3bf5c 100644
--- a/drivers/input/rmi4/rmi_driver.c
+++ b/drivers/input/rmi4/rmi_driver.c
@@ -978,12 +978,12 @@ static int rmi_driver_remove(struct device *dev)
 
 	rmi_disable_irq(rmi_dev, false);
 
-	irq_domain_remove(data->irqdomain);
-	data->irqdomain = NULL;
-
 	rmi_f34_remove_sysfs(rmi_dev);
 	rmi_free_function_list(rmi_dev);
 
+	irq_domain_remove(data->irqdomain);
+	data->irqdomain = NULL;
+
 	return 0;
 }
 
diff --git a/drivers/input/rmi4/rmi_f01.c b/drivers/input/rmi4/rmi_f01.c
index d7603c50f864..cc1d4b424640 100644
--- a/drivers/input/rmi4/rmi_f01.c
+++ b/drivers/input/rmi4/rmi_f01.c
@@ -267,8 +267,7 @@ static ssize_t rmi_driver_manufacturer_id_show(struct device *dev,
 	struct rmi_driver_data *data = dev_get_drvdata(dev);
 	struct f01_data *f01 = dev_get_drvdata(&data->f01_container->dev);
 
-	return scnprintf(buf, PAGE_SIZE, "%d\n",
-			 f01->properties.manufacturer_id);
+	return sysfs_emit(buf, "%d\n", f01->properties.manufacturer_id);
 }
 
 static DEVICE_ATTR(manufacturer_id, 0444,
@@ -280,7 +279,7 @@ static ssize_t rmi_driver_dom_show(struct device *dev,
 	struct rmi_driver_data *data = dev_get_drvdata(dev);
 	struct f01_data *f01 = dev_get_drvdata(&data->f01_container->dev);
 
-	return scnprintf(buf, PAGE_SIZE, "%s\n", f01->properties.dom);
+	return sysfs_emit(buf, "%s\n", f01->properties.dom);
 }
 
 static DEVICE_ATTR(date_of_manufacture, 0444, rmi_driver_dom_show, NULL);
@@ -292,7 +291,7 @@ static ssize_t rmi_driver_product_id_show(struct device *dev,
 	struct rmi_driver_data *data = dev_get_drvdata(dev);
 	struct f01_data *f01 = dev_get_drvdata(&data->f01_container->dev);
 
-	return scnprintf(buf, PAGE_SIZE, "%s\n", f01->properties.product_id);
+	return sysfs_emit(buf, "%s\n", f01->properties.product_id);
 }
 
 static DEVICE_ATTR(product_id, 0444, rmi_driver_product_id_show, NULL);
@@ -304,7 +303,7 @@ static ssize_t rmi_driver_firmware_id_show(struct device *dev,
 	struct rmi_driver_data *data = dev_get_drvdata(dev);
 	struct f01_data *f01 = dev_get_drvdata(&data->f01_container->dev);
 
-	return scnprintf(buf, PAGE_SIZE, "%d\n", f01->properties.firmware_id);
+	return sysfs_emit(buf, "%d\n", f01->properties.firmware_id);
 }
 
 static DEVICE_ATTR(firmware_id, 0444, rmi_driver_firmware_id_show, NULL);
@@ -318,8 +317,8 @@ static ssize_t rmi_driver_package_id_show(struct device *dev,
 
 	u32 package_id = f01->properties.package_id;
 
-	return scnprintf(buf, PAGE_SIZE, "%04x.%04x\n",
-			 package_id & 0xffff, (package_id >> 16) & 0xffff);
+	return sysfs_emit(buf, "%04x.%04x\n",
+			  package_id & 0xffff, (package_id >> 16) & 0xffff);
 }
 
 static DEVICE_ATTR(package_id, 0444, rmi_driver_package_id_show, NULL);
diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h
index b585b1dab870..dfc6c581873b 100644
--- a/drivers/input/serio/i8042-acpipnpio.h
+++ b/drivers/input/serio/i8042-acpipnpio.h
@@ -635,6 +635,14 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.driver_data = (void *)(SERIO_QUIRK_NOAUX)
 	},
 	{
+		/* Fujitsu Lifebook U728 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U728"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_NOAUX)
+	},
+	{
 		/* Gigabyte M912 */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
@@ -1210,6 +1218,12 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 	},
 	{
 		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "NS5x_7xPU"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_NOAUX)
+	},
+	{
+		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "NJ50_70CU"),
 		},
 		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c
index a2c4b3b87f93..542a31448c8f 100644
--- a/drivers/input/touchscreen/atmel_mxt_ts.c
+++ b/drivers/input/touchscreen/atmel_mxt_ts.c
@@ -2818,8 +2818,8 @@ static ssize_t mxt_fw_version_show(struct device *dev,
 {
 	struct mxt_data *data = dev_get_drvdata(dev);
 	struct mxt_info *info = data->info;
-	return scnprintf(buf, PAGE_SIZE, "%u.%u.%02X\n",
-			 info->version >> 4, info->version & 0xf, info->build);
+	return sysfs_emit(buf, "%u.%u.%02X\n",
+			  info->version >> 4, info->version & 0xf, info->build);
 }
 
 /* Hardware Version is returned as FamilyID.VariantID */
@@ -2828,8 +2828,7 @@ static ssize_t mxt_hw_version_show(struct device *dev,
 {
 	struct mxt_data *data = dev_get_drvdata(dev);
 	struct mxt_info *info = data->info;
-	return scnprintf(buf, PAGE_SIZE, "%u.%u\n",
-			 info->family_id, info->variant_id);
+	return sysfs_emit(buf, "%u.%u\n", info->family_id, info->variant_id);
 }
 
 static ssize_t mxt_show_instance(char *buf, int count,
@@ -2839,19 +2838,18 @@ static ssize_t mxt_show_instance(char *buf, int count,
 	int i;
 
 	if (mxt_obj_instances(object) > 1)
-		count += scnprintf(buf + count, PAGE_SIZE - count,
-				   "Instance %u\n", instance);
+		count += sysfs_emit_at(buf, count, "Instance %u\n", instance);
 
 	for (i = 0; i < mxt_obj_size(object); i++)
-		count += scnprintf(buf + count, PAGE_SIZE - count,
-				"\t[%2u]: %02x (%d)\n", i, val[i], val[i]);
-	count += scnprintf(buf + count, PAGE_SIZE - count, "\n");
+		count += sysfs_emit_at(buf, count, "\t[%2u]: %02x (%d)\n",
+				       i, val[i], val[i]);
+	count += sysfs_emit_at(buf, count, "\n");
 
 	return count;
 }
 
 static ssize_t mxt_object_show(struct device *dev,
-				    struct device_attribute *attr, char *buf)
+			       struct device_attribute *attr, char *buf)
 {
 	struct mxt_data *data = dev_get_drvdata(dev);
 	struct mxt_object *object;
@@ -2872,8 +2870,7 @@ static ssize_t mxt_object_show(struct device *dev,
 		if (!mxt_object_readable(object->type))
 			continue;
 
-		count += scnprintf(buf + count, PAGE_SIZE - count,
-				"T%u:\n", object->type);
+		count += sysfs_emit_at(buf, count, "T%u:\n", object->type);
 
 		for (j = 0; j < mxt_obj_instances(object); j++) {
 			u16 size = mxt_obj_size(object);
diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c
index 3e102bcc4a1c..2a1db1134476 100644
--- a/drivers/input/touchscreen/edt-ft5x06.c
+++ b/drivers/input/touchscreen/edt-ft5x06.c
@@ -431,7 +431,7 @@ static ssize_t edt_ft5x06_setting_show(struct device *dev,
 		*field = val;
 	}
 
-	count = scnprintf(buf, PAGE_SIZE, "%d\n", val);
+	count = sysfs_emit(buf, "%d\n", val);
 out:
 	mutex_unlock(&tsdata->mutex);
 	return error ?: count;
diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c
index af32fbe57b63..b068ff8afbc9 100644
--- a/drivers/input/touchscreen/goodix.c
+++ b/drivers/input/touchscreen/goodix.c
@@ -884,7 +884,8 @@ static int goodix_add_acpi_gpio_mappings(struct goodix_ts_data *ts)
 		}
 	}
 
-	if (ts->gpio_count == 2 && ts->gpio_int_idx == 0) {
+	/* Some devices with gpio_int_idx 0 list a third unused GPIO */
+	if ((ts->gpio_count == 2 || ts->gpio_count == 3) && ts->gpio_int_idx == 0) {
 		ts->irq_pin_access_method = IRQ_PIN_ACCESS_ACPI_GPIO;
 		gpio_mapping = acpi_goodix_int_first_gpios;
 	} else if (ts->gpio_count == 2 && ts->gpio_int_idx == 1) {
diff --git a/drivers/input/touchscreen/hideep.c b/drivers/input/touchscreen/hideep.c
index 0f58258306bf..eae90676f4e5 100644
--- a/drivers/input/touchscreen/hideep.c
+++ b/drivers/input/touchscreen/hideep.c
@@ -928,8 +928,7 @@ static ssize_t hideep_fw_version_show(struct device *dev,
 	ssize_t len;
 
 	mutex_lock(&ts->dev_mutex);
-	len = scnprintf(buf, PAGE_SIZE, "%04x\n",
-			be16_to_cpu(ts->dwz_info.release_ver));
+	len = sysfs_emit(buf, "%04x\n", be16_to_cpu(ts->dwz_info.release_ver));
 	mutex_unlock(&ts->dev_mutex);
 
 	return len;
@@ -943,8 +942,7 @@ static ssize_t hideep_product_id_show(struct device *dev,
 	ssize_t len;
 
 	mutex_lock(&ts->dev_mutex);
-	len = scnprintf(buf, PAGE_SIZE, "%04x\n",
-			be16_to_cpu(ts->dwz_info.product_id));
+	len = sysfs_emit(buf, "%04x\n", be16_to_cpu(ts->dwz_info.product_id));
 	mutex_unlock(&ts->dev_mutex);
 
 	return len;
diff --git a/drivers/input/touchscreen/hycon-hy46xx.c b/drivers/input/touchscreen/hycon-hy46xx.c
index d0f257989fd6..2e01d87977c1 100644
--- a/drivers/input/touchscreen/hycon-hy46xx.c
+++ b/drivers/input/touchscreen/hycon-hy46xx.c
@@ -202,7 +202,7 @@ static ssize_t hycon_hy46xx_setting_show(struct device *dev,
 		*field = val;
 	}
 
-	count = scnprintf(buf, PAGE_SIZE, "%d\n", val);
+	count = sysfs_emit(buf, "%d\n", val);
 
 out:
 	mutex_unlock(&tsdata->mutex);
diff --git a/drivers/input/touchscreen/ilitek_ts_i2c.c b/drivers/input/touchscreen/ilitek_ts_i2c.c
index 90c4934e750a..fc4e39b6651a 100644
--- a/drivers/input/touchscreen/ilitek_ts_i2c.c
+++ b/drivers/input/touchscreen/ilitek_ts_i2c.c
@@ -512,12 +512,12 @@ static ssize_t firmware_version_show(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct ilitek_ts_data *ts = i2c_get_clientdata(client);
 
-	return scnprintf(buf, PAGE_SIZE,
-			 "fw version: [%02X%02X.%02X%02X.%02X%02X.%02X%02X]\n",
-			 ts->firmware_ver[0], ts->firmware_ver[1],
-			 ts->firmware_ver[2], ts->firmware_ver[3],
-			 ts->firmware_ver[4], ts->firmware_ver[5],
-			 ts->firmware_ver[6], ts->firmware_ver[7]);
+	return sysfs_emit(buf,
+			  "fw version: [%02X%02X.%02X%02X.%02X%02X.%02X%02X]\n",
+			  ts->firmware_ver[0], ts->firmware_ver[1],
+			  ts->firmware_ver[2], ts->firmware_ver[3],
+			  ts->firmware_ver[4], ts->firmware_ver[5],
+			  ts->firmware_ver[6], ts->firmware_ver[7]);
 }
 static DEVICE_ATTR_RO(firmware_version);
 
@@ -527,8 +527,8 @@ static ssize_t product_id_show(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct ilitek_ts_data *ts = i2c_get_clientdata(client);
 
-	return scnprintf(buf, PAGE_SIZE, "product id: [%04X], module: [%s]\n",
-			 ts->mcu_ver, ts->product_id);
+	return sysfs_emit(buf, "product id: [%04X], module: [%s]\n",
+			  ts->mcu_ver, ts->product_id);
 }
 static DEVICE_ATTR_RO(product_id);
 
diff --git a/drivers/input/touchscreen/iqs5xx.c b/drivers/input/touchscreen/iqs5xx.c
index a3f4fb85bee5..4d226118f3cc 100644
--- a/drivers/input/touchscreen/iqs5xx.c
+++ b/drivers/input/touchscreen/iqs5xx.c
@@ -943,12 +943,12 @@ static ssize_t fw_info_show(struct device *dev,
 	if (!iqs5xx->dev_id_info.bl_status)
 		return -ENODATA;
 
-	return scnprintf(buf, PAGE_SIZE, "%u.%u.%u.%u:%u.%u\n",
-			 be16_to_cpu(iqs5xx->dev_id_info.prod_num),
-			 be16_to_cpu(iqs5xx->dev_id_info.proj_num),
-			 iqs5xx->dev_id_info.major_ver,
-			 iqs5xx->dev_id_info.minor_ver,
-			 iqs5xx->exp_file[0], iqs5xx->exp_file[1]);
+	return sysfs_emit(buf, "%u.%u.%u.%u:%u.%u\n",
+			  be16_to_cpu(iqs5xx->dev_id_info.prod_num),
+			  be16_to_cpu(iqs5xx->dev_id_info.proj_num),
+			  iqs5xx->dev_id_info.major_ver,
+			  iqs5xx->dev_id_info.minor_ver,
+			  iqs5xx->exp_file[0], iqs5xx->exp_file[1]);
 }
 
 static DEVICE_ATTR_WO(fw_file);
diff --git a/drivers/input/touchscreen/iqs7211.c b/drivers/input/touchscreen/iqs7211.c
index dc084f873762..f0a56cde899e 100644
--- a/drivers/input/touchscreen/iqs7211.c
+++ b/drivers/input/touchscreen/iqs7211.c
@@ -2401,12 +2401,12 @@ static ssize_t fw_info_show(struct device *dev,
 {
 	struct iqs7211_private *iqs7211 = dev_get_drvdata(dev);
 
-	return scnprintf(buf, PAGE_SIZE, "%u.%u.%u.%u:%u.%u\n",
-			 le16_to_cpu(iqs7211->ver_info.prod_num),
-			 le32_to_cpu(iqs7211->ver_info.patch),
-			 le16_to_cpu(iqs7211->ver_info.major),
-			 le16_to_cpu(iqs7211->ver_info.minor),
-			 iqs7211->exp_file[1], iqs7211->exp_file[0]);
+	return sysfs_emit(buf, "%u.%u.%u.%u:%u.%u\n",
+			  le16_to_cpu(iqs7211->ver_info.prod_num),
+			  le32_to_cpu(iqs7211->ver_info.patch),
+			  le16_to_cpu(iqs7211->ver_info.major),
+			  le16_to_cpu(iqs7211->ver_info.minor),
+			  iqs7211->exp_file[1], iqs7211->exp_file[0]);
 }
 
 static DEVICE_ATTR_RO(fw_info);
diff --git a/drivers/input/touchscreen/melfas_mip4.c b/drivers/input/touchscreen/melfas_mip4.c
index aa325486f618..78e1c63e530e 100644
--- a/drivers/input/touchscreen/melfas_mip4.c
+++ b/drivers/input/touchscreen/melfas_mip4.c
@@ -1336,9 +1336,9 @@ static ssize_t mip4_sysfs_read_fw_version(struct device *dev,
 	/* Take lock to prevent racing with firmware update */
 	mutex_lock(&ts->input->mutex);
 
-	count = snprintf(buf, PAGE_SIZE, "%04X %04X %04X %04X\n",
-			 ts->fw_version.boot, ts->fw_version.core,
-			 ts->fw_version.app, ts->fw_version.param);
+	count = sysfs_emit(buf, "%04X %04X %04X %04X\n",
+			   ts->fw_version.boot, ts->fw_version.core,
+			   ts->fw_version.app, ts->fw_version.param);
 
 	mutex_unlock(&ts->input->mutex);
 
@@ -1362,8 +1362,8 @@ static ssize_t mip4_sysfs_read_hw_version(struct device *dev,
 	 * product_name shows the name or version of the hardware
 	 * paired with current firmware in the chip.
 	 */
-	count = snprintf(buf, PAGE_SIZE, "%.*s\n",
-			 (int)sizeof(ts->product_name), ts->product_name);
+	count = sysfs_emit(buf, "%.*s\n",
+			   (int)sizeof(ts->product_name), ts->product_name);
 
 	mutex_unlock(&ts->input->mutex);
 
@@ -1382,7 +1382,7 @@ static ssize_t mip4_sysfs_read_product_id(struct device *dev,
 
 	mutex_lock(&ts->input->mutex);
 
-	count = snprintf(buf, PAGE_SIZE, "%04X\n", ts->product_id);
+	count = sysfs_emit(buf, "%04X\n", ts->product_id);
 
 	mutex_unlock(&ts->input->mutex);
 
@@ -1401,8 +1401,8 @@ static ssize_t mip4_sysfs_read_ic_name(struct device *dev,
 
 	mutex_lock(&ts->input->mutex);
 
-	count = snprintf(buf, PAGE_SIZE, "%.*s\n",
-			 (int)sizeof(ts->ic_name), ts->ic_name);
+	count = sysfs_emit(buf, "%.*s\n",
+			   (int)sizeof(ts->ic_name), ts->ic_name);
 
 	mutex_unlock(&ts->input->mutex);
 
diff --git a/drivers/input/touchscreen/usbtouchscreen.c b/drivers/input/touchscreen/usbtouchscreen.c
index d6d04b9f04fc..60354ebc7242 100644
--- a/drivers/input/touchscreen/usbtouchscreen.c
+++ b/drivers/input/touchscreen/usbtouchscreen.c
@@ -456,8 +456,8 @@ static ssize_t mtouch_firmware_rev_show(struct device *dev,
 	struct usbtouch_usb *usbtouch = usb_get_intfdata(intf);
 	struct mtouch_priv *priv = usbtouch->priv;
 
-	return scnprintf(output, PAGE_SIZE, "%1x.%1x\n",
-			 priv->fw_rev_major, priv->fw_rev_minor);
+	return sysfs_emit(output, "%1x.%1x\n",
+			  priv->fw_rev_major, priv->fw_rev_minor);
 }
 static DEVICE_ATTR(firmware_rev, 0444, mtouch_firmware_rev_show, NULL);
 
diff --git a/drivers/input/touchscreen/wdt87xx_i2c.c b/drivers/input/touchscreen/wdt87xx_i2c.c
index 128341a6696b..32c7be54434c 100644
--- a/drivers/input/touchscreen/wdt87xx_i2c.c
+++ b/drivers/input/touchscreen/wdt87xx_i2c.c
@@ -887,7 +887,7 @@ static ssize_t config_csum_show(struct device *dev,
 	cfg_csum = wdt->param.xmls_id1;
 	cfg_csum = (cfg_csum << 16) | wdt->param.xmls_id2;
 
-	return scnprintf(buf, PAGE_SIZE, "%x\n", cfg_csum);
+	return sysfs_emit(buf, "%x\n", cfg_csum);
 }
 
 static ssize_t fw_version_show(struct device *dev,
@@ -896,7 +896,7 @@ static ssize_t fw_version_show(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct wdt87xx_data *wdt = i2c_get_clientdata(client);
 
-	return scnprintf(buf, PAGE_SIZE, "%x\n", wdt->param.fw_id);
+	return sysfs_emit(buf, "%x\n", wdt->param.fw_id);
 }
 
 static ssize_t plat_id_show(struct device *dev,
@@ -905,7 +905,7 @@ static ssize_t plat_id_show(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct wdt87xx_data *wdt = i2c_get_clientdata(client);
 
-	return scnprintf(buf, PAGE_SIZE, "%x\n", wdt->param.plat_id);
+	return sysfs_emit(buf, "%x\n", wdt->param.plat_id);
 }
 
 static ssize_t update_config_store(struct device *dev,
diff --git a/drivers/input/touchscreen/zforce_ts.c b/drivers/input/touchscreen/zforce_ts.c
index 5be5112845e1..5680075f0bb8 100644
--- a/drivers/input/touchscreen/zforce_ts.c
+++ b/drivers/input/touchscreen/zforce_ts.c
@@ -20,6 +20,7 @@
 #include <linux/device.h>
 #include <linux/sysfs.h>
 #include <linux/input/mt.h>
+#include <linux/input/touchscreen.h>
 #include <linux/platform_data/zforce_ts.h>
 #include <linux/regulator/consumer.h>
 #include <linux/of.h>
@@ -106,6 +107,7 @@ struct zforce_point {
 struct zforce_ts {
 	struct i2c_client	*client;
 	struct input_dev	*input;
+	struct touchscreen_properties prop;
 	const struct zforce_ts_platdata *pdata;
 	char			phys[32];
 
@@ -266,7 +268,6 @@ static int zforce_setconfig(struct zforce_ts *ts, char b1)
 static int zforce_start(struct zforce_ts *ts)
 {
 	struct i2c_client *client = ts->client;
-	const struct zforce_ts_platdata *pdata = ts->pdata;
 	int ret;
 
 	dev_dbg(&client->dev, "starting device\n");
@@ -277,7 +278,7 @@ static int zforce_start(struct zforce_ts *ts)
 		return ret;
 	}
 
-	ret = zforce_resolution(ts, pdata->x_max, pdata->y_max);
+	ret = zforce_resolution(ts, ts->prop.max_x, ts->prop.max_y);
 	if (ret) {
 		dev_err(&client->dev, "Unable to set resolution, %d\n", ret);
 		goto error;
@@ -337,7 +338,6 @@ static int zforce_stop(struct zforce_ts *ts)
 static int zforce_touch_event(struct zforce_ts *ts, u8 *payload)
 {
 	struct i2c_client *client = ts->client;
-	const struct zforce_ts_platdata *pdata = ts->pdata;
 	struct zforce_point point;
 	int count, i, num = 0;
 
@@ -355,8 +355,8 @@ static int zforce_touch_event(struct zforce_ts *ts, u8 *payload)
 		point.coord_y =
 			payload[9 * i + 4] << 8 | payload[9 * i + 3];
 
-		if (point.coord_x > pdata->x_max ||
-		    point.coord_y > pdata->y_max) {
+		if (point.coord_x > ts->prop.max_x ||
+		    point.coord_y > ts->prop.max_y) {
 			dev_warn(&client->dev, "coordinates (%d,%d) invalid\n",
 				point.coord_x, point.coord_y);
 			point.coord_x = point.coord_y = 0;
@@ -390,10 +390,9 @@ static int zforce_touch_event(struct zforce_ts *ts, u8 *payload)
 						point.state != STATE_UP);
 
 		if (point.state != STATE_UP) {
-			input_report_abs(ts->input, ABS_MT_POSITION_X,
-					 point.coord_x);
-			input_report_abs(ts->input, ABS_MT_POSITION_Y,
-					 point.coord_y);
+			touchscreen_report_pos(ts->input, &ts->prop,
+					       point.coord_x, point.coord_y,
+					       true);
 			input_report_abs(ts->input, ABS_MT_TOUCH_MAJOR,
 					 point.area_major);
 			input_report_abs(ts->input, ABS_MT_TOUCH_MINOR,
@@ -719,15 +718,8 @@ static struct zforce_ts_platdata *zforce_parse_dt(struct device *dev)
 		return ERR_PTR(-ENOMEM);
 	}
 
-	if (of_property_read_u32(np, "x-size", &pdata->x_max)) {
-		dev_err(dev, "failed to get x-size property\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	if (of_property_read_u32(np, "y-size", &pdata->y_max)) {
-		dev_err(dev, "failed to get y-size property\n");
-		return ERR_PTR(-EINVAL);
-	}
+	of_property_read_u32(np, "x-size", &pdata->x_max);
+	of_property_read_u32(np, "y-size", &pdata->y_max);
 
 	return pdata;
 }
@@ -856,6 +848,12 @@ static int zforce_probe(struct i2c_client *client)
 	input_set_abs_params(input_dev, ABS_MT_POSITION_Y, 0,
 			     pdata->y_max, 0, 0);
 
+	touchscreen_parse_properties(input_dev, true, &ts->prop);
+	if (ts->prop.max_x == 0 || ts->prop.max_y == 0) {
+		dev_err(&client->dev, "no size specified\n");
+		return -EINVAL;
+	}
+
 	input_set_abs_params(input_dev, ABS_MT_TOUCH_MAJOR, 0,
 			     ZFORCE_MAX_AREA, 0, 0);
 	input_set_abs_params(input_dev, ABS_MT_TOUCH_MINOR, 0,
diff --git a/drivers/input/vivaldi-fmap.c b/drivers/input/vivaldi-fmap.c
index 6dae83d96806..0d29ec014e2f 100644
--- a/drivers/input/vivaldi-fmap.c
+++ b/drivers/input/vivaldi-fmap.c
@@ -27,10 +27,10 @@ ssize_t vivaldi_function_row_physmap_show(const struct vivaldi_data *data,
 		return 0;
 
 	for (i = 0; i < data->num_function_row_keys; i++)
-		size += scnprintf(buf + size, PAGE_SIZE - size,
-				  "%s%02X", size ? " " : "", physmap[i]);
+		size += sysfs_emit_at(buf, size,
+				      "%s%02X", size ? " " : "", physmap[i]);
 	if (size)
-		size += scnprintf(buf + size, PAGE_SIZE - size, "\n");
+		size += sysfs_emit_at(buf, size, "\n");
 
 	return size;
 }
diff --git a/drivers/interconnect/imx/imx8mm.c b/drivers/interconnect/imx/imx8mm.c
index b43325364aa3..8c40f4182263 100644
--- a/drivers/interconnect/imx/imx8mm.c
+++ b/drivers/interconnect/imx/imx8mm.c
@@ -86,16 +86,9 @@ static int imx8mm_icc_probe(struct platform_device *pdev)
 	return imx_icc_register(pdev, nodes, ARRAY_SIZE(nodes), NULL);
 }
 
-static int imx8mm_icc_remove(struct platform_device *pdev)
-{
-	imx_icc_unregister(pdev);
-
-	return 0;
-}
-
 static struct platform_driver imx8mm_icc_driver = {
 	.probe = imx8mm_icc_probe,
-	.remove = imx8mm_icc_remove,
+	.remove_new = imx_icc_unregister,
 	.driver = {
 		.name = "imx8mm-interconnect",
 	},
diff --git a/drivers/interconnect/imx/imx8mn.c b/drivers/interconnect/imx/imx8mn.c
index 8ce6d8e4bf5e..fa3d4f97dfa4 100644
--- a/drivers/interconnect/imx/imx8mn.c
+++ b/drivers/interconnect/imx/imx8mn.c
@@ -75,16 +75,9 @@ static int imx8mn_icc_probe(struct platform_device *pdev)
 	return imx_icc_register(pdev, nodes, ARRAY_SIZE(nodes), NULL);
 }
 
-static int imx8mn_icc_remove(struct platform_device *pdev)
-{
-	imx_icc_unregister(pdev);
-
-	return 0;
-}
-
 static struct platform_driver imx8mn_icc_driver = {
 	.probe = imx8mn_icc_probe,
-	.remove = imx8mn_icc_remove,
+	.remove_new = imx_icc_unregister,
 	.driver = {
 		.name = "imx8mn-interconnect",
 	},
diff --git a/drivers/interconnect/imx/imx8mp.c b/drivers/interconnect/imx/imx8mp.c
index a66ae3638b18..d218bb47757a 100644
--- a/drivers/interconnect/imx/imx8mp.c
+++ b/drivers/interconnect/imx/imx8mp.c
@@ -239,16 +239,9 @@ static int imx8mp_icc_probe(struct platform_device *pdev)
 	return imx_icc_register(pdev, nodes, ARRAY_SIZE(nodes), noc_setting_nodes);
 }
 
-static int imx8mp_icc_remove(struct platform_device *pdev)
-{
-	imx_icc_unregister(pdev);
-
-	return 0;
-}
-
 static struct platform_driver imx8mp_icc_driver = {
 	.probe = imx8mp_icc_probe,
-	.remove = imx8mp_icc_remove,
+	.remove_new = imx_icc_unregister,
 	.driver = {
 		.name = "imx8mp-interconnect",
 	},
diff --git a/drivers/interconnect/imx/imx8mq.c b/drivers/interconnect/imx/imx8mq.c
index b6fb71305c99..8bbd672b346e 100644
--- a/drivers/interconnect/imx/imx8mq.c
+++ b/drivers/interconnect/imx/imx8mq.c
@@ -85,16 +85,9 @@ static int imx8mq_icc_probe(struct platform_device *pdev)
 	return imx_icc_register(pdev, nodes, ARRAY_SIZE(nodes), NULL);
 }
 
-static int imx8mq_icc_remove(struct platform_device *pdev)
-{
-	imx_icc_unregister(pdev);
-
-	return 0;
-}
-
 static struct platform_driver imx8mq_icc_driver = {
 	.probe = imx8mq_icc_probe,
-	.remove = imx8mq_icc_remove,
+	.remove_new = imx_icc_unregister,
 	.driver = {
 		.name = "imx8mq-interconnect",
 		.sync_state = icc_sync_state,
diff --git a/drivers/interconnect/qcom/Kconfig b/drivers/interconnect/qcom/Kconfig
index 62b516d38d03..697f96c49f6f 100644
--- a/drivers/interconnect/qcom/Kconfig
+++ b/drivers/interconnect/qcom/Kconfig
@@ -191,6 +191,15 @@ config INTERCONNECT_QCOM_SDX75
 	  This is a driver for the Qualcomm Network-on-Chip on sdx75-based
 	  platforms.
 
+config INTERCONNECT_QCOM_SM6115
+	tristate "Qualcomm SM6115 interconnect driver"
+	depends on INTERCONNECT_QCOM
+	depends on QCOM_SMD_RPM
+	select INTERCONNECT_QCOM_SMD_RPM
+	help
+	  This is a driver for the Qualcomm Network-on-Chip on sm6115-based
+	  platforms.
+
 config INTERCONNECT_QCOM_SM6350
 	tristate "Qualcomm SM6350 interconnect driver"
 	depends on INTERCONNECT_QCOM_RPMH_POSSIBLE
@@ -245,5 +254,23 @@ config INTERCONNECT_QCOM_SM8550
 	  This is a driver for the Qualcomm Network-on-Chip on SM8550-based
 	  platforms.
 
+config INTERCONNECT_QCOM_SM8650
+	tristate "Qualcomm SM8650 interconnect driver"
+	depends on INTERCONNECT_QCOM_RPMH_POSSIBLE
+	select INTERCONNECT_QCOM_RPMH
+	select INTERCONNECT_QCOM_BCM_VOTER
+	help
+	  This is a driver for the Qualcomm Network-on-Chip on SM8650-based
+	  platforms.
+
+config INTERCONNECT_QCOM_X1E80100
+	tristate "Qualcomm X1E80100 interconnect driver"
+	depends on INTERCONNECT_QCOM_RPMH_POSSIBLE
+	select INTERCONNECT_QCOM_RPMH
+	select INTERCONNECT_QCOM_BCM_VOTER
+	help
+	  This is a driver for the Qualcomm Network-on-Chip on X1E80100-based
+	  platforms.
+
 config INTERCONNECT_QCOM_SMD_RPM
 	tristate
diff --git a/drivers/interconnect/qcom/Makefile b/drivers/interconnect/qcom/Makefile
index c5320e293960..704846165022 100644
--- a/drivers/interconnect/qcom/Makefile
+++ b/drivers/interconnect/qcom/Makefile
@@ -24,12 +24,15 @@ qnoc-sdm845-objs			:= sdm845.o
 qnoc-sdx55-objs				:= sdx55.o
 qnoc-sdx65-objs				:= sdx65.o
 qnoc-sdx75-objs				:= sdx75.o
+qnoc-sm6115-objs			:= sm6115.o
 qnoc-sm6350-objs			:= sm6350.o
 qnoc-sm8150-objs			:= sm8150.o
 qnoc-sm8250-objs			:= sm8250.o
 qnoc-sm8350-objs			:= sm8350.o
 qnoc-sm8450-objs			:= sm8450.o
 qnoc-sm8550-objs			:= sm8550.o
+qnoc-sm8650-objs			:= sm8650.o
+qnoc-x1e80100-objs			:= x1e80100.o
 icc-smd-rpm-objs			:= smd-rpm.o icc-rpm.o icc-rpm-clocks.o
 
 obj-$(CONFIG_INTERCONNECT_QCOM_BCM_VOTER) += icc-bcm-voter.o
@@ -53,10 +56,13 @@ obj-$(CONFIG_INTERCONNECT_QCOM_SDM845) += qnoc-sdm845.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SDX55) += qnoc-sdx55.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SDX65) += qnoc-sdx65.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SDX75) += qnoc-sdx75.o
+obj-$(CONFIG_INTERCONNECT_QCOM_SM6115) += qnoc-sm6115.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SM6350) += qnoc-sm6350.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SM8150) += qnoc-sm8150.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SM8250) += qnoc-sm8250.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SM8350) += qnoc-sm8350.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SM8450) += qnoc-sm8450.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SM8550) += qnoc-sm8550.o
+obj-$(CONFIG_INTERCONNECT_QCOM_SM8650) += qnoc-sm8650.o
+obj-$(CONFIG_INTERCONNECT_QCOM_X1E80100) += qnoc-x1e80100.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SMD_RPM) += icc-smd-rpm.o
diff --git a/drivers/interconnect/qcom/icc-rpm.c b/drivers/interconnect/qcom/icc-rpm.c
index dbacb2a7af50..a8ed435f696c 100644
--- a/drivers/interconnect/qcom/icc-rpm.c
+++ b/drivers/interconnect/qcom/icc-rpm.c
@@ -627,14 +627,12 @@ err_disable_unprepare_clk:
 }
 EXPORT_SYMBOL(qnoc_probe);
 
-int qnoc_remove(struct platform_device *pdev)
+void qnoc_remove(struct platform_device *pdev)
 {
 	struct qcom_icc_provider *qp = platform_get_drvdata(pdev);
 
 	icc_provider_deregister(&qp->provider);
 	icc_nodes_remove(&qp->provider);
 	clk_disable_unprepare(qp->bus_clk);
-
-	return 0;
 }
 EXPORT_SYMBOL(qnoc_remove);
diff --git a/drivers/interconnect/qcom/icc-rpm.h b/drivers/interconnect/qcom/icc-rpm.h
index a13768cfd231..f4883d43eae4 100644
--- a/drivers/interconnect/qcom/icc-rpm.h
+++ b/drivers/interconnect/qcom/icc-rpm.h
@@ -161,7 +161,7 @@ extern const struct rpm_clk_resource aggre1_branch_clk;
 extern const struct rpm_clk_resource aggre2_branch_clk;
 
 int qnoc_probe(struct platform_device *pdev);
-int qnoc_remove(struct platform_device *pdev);
+void qnoc_remove(struct platform_device *pdev);
 
 bool qcom_icc_rpm_smd_available(void);
 int qcom_icc_rpm_smd_send(int ctx, int rsc_type, int id, u32 val);
diff --git a/drivers/interconnect/qcom/msm8916.c b/drivers/interconnect/qcom/msm8916.c
index 35148880b3e8..499b1a9ac413 100644
--- a/drivers/interconnect/qcom/msm8916.c
+++ b/drivers/interconnect/qcom/msm8916.c
@@ -1344,7 +1344,7 @@ MODULE_DEVICE_TABLE(of, msm8916_noc_of_match);
 
 static struct platform_driver msm8916_noc_driver = {
 	.probe = qnoc_probe,
-	.remove = qnoc_remove,
+	.remove_new = qnoc_remove,
 	.driver = {
 		.name = "qnoc-msm8916",
 		.of_match_table = msm8916_noc_of_match,
diff --git a/drivers/interconnect/qcom/msm8939.c b/drivers/interconnect/qcom/msm8939.c
index b52c5ac1175c..8ff2c23b1ca0 100644
--- a/drivers/interconnect/qcom/msm8939.c
+++ b/drivers/interconnect/qcom/msm8939.c
@@ -1421,7 +1421,7 @@ MODULE_DEVICE_TABLE(of, msm8939_noc_of_match);
 
 static struct platform_driver msm8939_noc_driver = {
 	.probe = qnoc_probe,
-	.remove = qnoc_remove,
+	.remove_new = qnoc_remove,
 	.driver = {
 		.name = "qnoc-msm8939",
 		.of_match_table = msm8939_noc_of_match,
diff --git a/drivers/interconnect/qcom/msm8974.c b/drivers/interconnect/qcom/msm8974.c
index 21f6c852141e..241076b5f36b 100644
--- a/drivers/interconnect/qcom/msm8974.c
+++ b/drivers/interconnect/qcom/msm8974.c
@@ -740,15 +740,13 @@ err_remove_nodes:
 	return ret;
 }
 
-static int msm8974_icc_remove(struct platform_device *pdev)
+static void msm8974_icc_remove(struct platform_device *pdev)
 {
 	struct msm8974_icc_provider *qp = platform_get_drvdata(pdev);
 
 	icc_provider_deregister(&qp->provider);
 	icc_nodes_remove(&qp->provider);
 	clk_bulk_disable_unprepare(qp->num_clks, qp->bus_clks);
-
-	return 0;
 }
 
 static const struct of_device_id msm8974_noc_of_match[] = {
@@ -764,7 +762,7 @@ MODULE_DEVICE_TABLE(of, msm8974_noc_of_match);
 
 static struct platform_driver msm8974_noc_driver = {
 	.probe = msm8974_icc_probe,
-	.remove = msm8974_icc_remove,
+	.remove_new = msm8974_icc_remove,
 	.driver = {
 		.name = "qnoc-msm8974",
 		.of_match_table = msm8974_noc_of_match,
diff --git a/drivers/interconnect/qcom/msm8996.c b/drivers/interconnect/qcom/msm8996.c
index b73566c9b21f..788131400cd1 100644
--- a/drivers/interconnect/qcom/msm8996.c
+++ b/drivers/interconnect/qcom/msm8996.c
@@ -2108,7 +2108,7 @@ MODULE_DEVICE_TABLE(of, qnoc_of_match);
 
 static struct platform_driver qnoc_driver = {
 	.probe = qnoc_probe,
-	.remove = qnoc_remove,
+	.remove_new = qnoc_remove,
 	.driver = {
 		.name = "qnoc-msm8996",
 		.of_match_table = qnoc_of_match,
diff --git a/drivers/interconnect/qcom/osm-l3.c b/drivers/interconnect/qcom/osm-l3.c
index e97478bbc282..61a8695a9adc 100644
--- a/drivers/interconnect/qcom/osm-l3.c
+++ b/drivers/interconnect/qcom/osm-l3.c
@@ -148,14 +148,12 @@ static int qcom_osm_l3_set(struct icc_node *src, struct icc_node *dst)
 	return 0;
 }
 
-static int qcom_osm_l3_remove(struct platform_device *pdev)
+static void qcom_osm_l3_remove(struct platform_device *pdev)
 {
 	struct qcom_osm_l3_icc_provider *qp = platform_get_drvdata(pdev);
 
 	icc_provider_deregister(&qp->provider);
 	icc_nodes_remove(&qp->provider);
-
-	return 0;
 }
 
 static int qcom_osm_l3_probe(struct platform_device *pdev)
@@ -292,7 +290,7 @@ MODULE_DEVICE_TABLE(of, osm_l3_of_match);
 
 static struct platform_driver osm_l3_driver = {
 	.probe = qcom_osm_l3_probe,
-	.remove = qcom_osm_l3_remove,
+	.remove_new = qcom_osm_l3_remove,
 	.driver = {
 		.name = "osm-l3",
 		.of_match_table = osm_l3_of_match,
diff --git a/drivers/interconnect/qcom/qcm2290.c b/drivers/interconnect/qcom/qcm2290.c
index b88cf9a022e0..96735800b13c 100644
--- a/drivers/interconnect/qcom/qcm2290.c
+++ b/drivers/interconnect/qcom/qcm2290.c
@@ -1367,7 +1367,7 @@ MODULE_DEVICE_TABLE(of, qcm2290_noc_of_match);
 
 static struct platform_driver qcm2290_noc_driver = {
 	.probe = qnoc_probe,
-	.remove = qnoc_remove,
+	.remove_new = qnoc_remove,
 	.driver = {
 		.name = "qnoc-qcm2290",
 		.of_match_table = qcm2290_noc_of_match,
diff --git a/drivers/interconnect/qcom/qcs404.c b/drivers/interconnect/qcom/qcs404.c
index 9fa1da70c843..11b49a89c03d 100644
--- a/drivers/interconnect/qcom/qcs404.c
+++ b/drivers/interconnect/qcom/qcs404.c
@@ -1083,7 +1083,7 @@ MODULE_DEVICE_TABLE(of, qcs404_noc_of_match);
 
 static struct platform_driver qcs404_noc_driver = {
 	.probe = qnoc_probe,
-	.remove = qnoc_remove,
+	.remove_new = qnoc_remove,
 	.driver = {
 		.name = "qnoc-qcs404",
 		.of_match_table = qcs404_noc_of_match,
diff --git a/drivers/interconnect/qcom/sc8180x.c b/drivers/interconnect/qcom/sc8180x.c
index 20331e119beb..03d626776ba1 100644
--- a/drivers/interconnect/qcom/sc8180x.c
+++ b/drivers/interconnect/qcom/sc8180x.c
@@ -1372,6 +1372,7 @@ static struct qcom_icc_bcm bcm_mm0 = {
 
 static struct qcom_icc_bcm bcm_co0 = {
 	.name = "CO0",
+	.keepalive = true,
 	.num_nodes = 1,
 	.nodes = { &slv_qns_cdsp_mem_noc }
 };
diff --git a/drivers/interconnect/qcom/sdm660.c b/drivers/interconnect/qcom/sdm660.c
index 7392bebba334..ab91de446da8 100644
--- a/drivers/interconnect/qcom/sdm660.c
+++ b/drivers/interconnect/qcom/sdm660.c
@@ -1714,7 +1714,7 @@ MODULE_DEVICE_TABLE(of, sdm660_noc_of_match);
 
 static struct platform_driver sdm660_noc_driver = {
 	.probe = qnoc_probe,
-	.remove = qnoc_remove,
+	.remove_new = qnoc_remove,
 	.driver = {
 		.name = "qnoc-sdm660",
 		.of_match_table = sdm660_noc_of_match,
diff --git a/drivers/interconnect/qcom/sm6115.c b/drivers/interconnect/qcom/sm6115.c
new file mode 100644
index 000000000000..88b67634aa2f
--- /dev/null
+++ b/drivers/interconnect/qcom/sm6115.c
@@ -0,0 +1,1423 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#include <dt-bindings/interconnect/qcom,sm6115.h>
+#include <linux/device.h>
+#include <linux/interconnect-provider.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include "icc-rpm.h"
+
+static const char * const snoc_intf_clocks[] = {
+	"cpu_axi",
+	"ufs_axi",
+	"usb_axi",
+	"ipa", /* Required by qxm_ipa */
+};
+
+static const char * const cnoc_intf_clocks[] = {
+	"usb_axi",
+};
+
+enum {
+	SM6115_MASTER_AMPSS_M0,
+	SM6115_MASTER_ANOC_SNOC,
+	SM6115_MASTER_BIMC_SNOC,
+	SM6115_MASTER_CAMNOC_HF,
+	SM6115_MASTER_CAMNOC_SF,
+	SM6115_MASTER_CRYPTO_CORE0,
+	SM6115_MASTER_GRAPHICS_3D,
+	SM6115_MASTER_IPA,
+	SM6115_MASTER_MDP_PORT0,
+	SM6115_MASTER_PIMEM,
+	SM6115_MASTER_QDSS_BAM,
+	SM6115_MASTER_QDSS_DAP,
+	SM6115_MASTER_QDSS_ETR,
+	SM6115_MASTER_QPIC,
+	SM6115_MASTER_QUP_0,
+	SM6115_MASTER_QUP_CORE_0,
+	SM6115_MASTER_SDCC_1,
+	SM6115_MASTER_SDCC_2,
+	SM6115_MASTER_SNOC_BIMC_NRT,
+	SM6115_MASTER_SNOC_BIMC_RT,
+	SM6115_MASTER_SNOC_BIMC,
+	SM6115_MASTER_SNOC_CFG,
+	SM6115_MASTER_SNOC_CNOC,
+	SM6115_MASTER_TCU_0,
+	SM6115_MASTER_TIC,
+	SM6115_MASTER_USB3,
+	SM6115_MASTER_VIDEO_P0,
+	SM6115_MASTER_VIDEO_PROC,
+
+	SM6115_SLAVE_AHB2PHY_USB,
+	SM6115_SLAVE_ANOC_SNOC,
+	SM6115_SLAVE_APPSS,
+	SM6115_SLAVE_APSS_THROTTLE_CFG,
+	SM6115_SLAVE_BIMC_CFG,
+	SM6115_SLAVE_BIMC_SNOC,
+	SM6115_SLAVE_BOOT_ROM,
+	SM6115_SLAVE_CAMERA_CFG,
+	SM6115_SLAVE_CAMERA_NRT_THROTTLE_CFG,
+	SM6115_SLAVE_CAMERA_RT_THROTTLE_CFG,
+	SM6115_SLAVE_CLK_CTL,
+	SM6115_SLAVE_CNOC_MSS,
+	SM6115_SLAVE_CRYPTO_0_CFG,
+	SM6115_SLAVE_DCC_CFG,
+	SM6115_SLAVE_DDR_PHY_CFG,
+	SM6115_SLAVE_DDR_SS_CFG,
+	SM6115_SLAVE_DISPLAY_CFG,
+	SM6115_SLAVE_DISPLAY_THROTTLE_CFG,
+	SM6115_SLAVE_EBI_CH0,
+	SM6115_SLAVE_GPU_CFG,
+	SM6115_SLAVE_GPU_THROTTLE_CFG,
+	SM6115_SLAVE_HWKM_CORE,
+	SM6115_SLAVE_IMEM_CFG,
+	SM6115_SLAVE_IPA_CFG,
+	SM6115_SLAVE_LPASS,
+	SM6115_SLAVE_MAPSS,
+	SM6115_SLAVE_MDSP_MPU_CFG,
+	SM6115_SLAVE_MESSAGE_RAM,
+	SM6115_SLAVE_OCIMEM,
+	SM6115_SLAVE_PDM,
+	SM6115_SLAVE_PIMEM_CFG,
+	SM6115_SLAVE_PIMEM,
+	SM6115_SLAVE_PKA_CORE,
+	SM6115_SLAVE_PMIC_ARB,
+	SM6115_SLAVE_QDSS_CFG,
+	SM6115_SLAVE_QDSS_STM,
+	SM6115_SLAVE_QM_CFG,
+	SM6115_SLAVE_QM_MPU_CFG,
+	SM6115_SLAVE_QPIC,
+	SM6115_SLAVE_QUP_0,
+	SM6115_SLAVE_QUP_CORE_0,
+	SM6115_SLAVE_RBCPR_CX_CFG,
+	SM6115_SLAVE_RBCPR_MX_CFG,
+	SM6115_SLAVE_RPM,
+	SM6115_SLAVE_SDCC_1,
+	SM6115_SLAVE_SDCC_2,
+	SM6115_SLAVE_SECURITY,
+	SM6115_SLAVE_SERVICE_CNOC,
+	SM6115_SLAVE_SERVICE_SNOC,
+	SM6115_SLAVE_SNOC_BIMC_NRT,
+	SM6115_SLAVE_SNOC_BIMC_RT,
+	SM6115_SLAVE_SNOC_BIMC,
+	SM6115_SLAVE_SNOC_CFG,
+	SM6115_SLAVE_SNOC_CNOC,
+	SM6115_SLAVE_TCSR,
+	SM6115_SLAVE_TCU,
+	SM6115_SLAVE_TLMM,
+	SM6115_SLAVE_USB3,
+	SM6115_SLAVE_VENUS_CFG,
+	SM6115_SLAVE_VENUS_THROTTLE_CFG,
+	SM6115_SLAVE_VSENSE_CTRL_CFG,
+};
+
+static const u16 slv_ebi_slv_bimc_snoc_links[] = {
+	SM6115_SLAVE_EBI_CH0,
+	SM6115_SLAVE_BIMC_SNOC,
+};
+
+static struct qcom_icc_node apps_proc = {
+	.name = "apps_proc",
+	.id = SM6115_MASTER_AMPSS_M0,
+	.channels = 1,
+	.buswidth = 16,
+	.qos.qos_port = 0,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.prio_level = 0,
+	.qos.areq_prio = 0,
+	.mas_rpm_id = 0,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(slv_ebi_slv_bimc_snoc_links),
+	.links = slv_ebi_slv_bimc_snoc_links,
+};
+
+static const u16 link_slv_ebi[] = {
+	SM6115_SLAVE_EBI_CH0,
+};
+
+static struct qcom_icc_node mas_snoc_bimc_rt = {
+	.name = "mas_snoc_bimc_rt",
+	.id = SM6115_MASTER_SNOC_BIMC_RT,
+	.channels = 1,
+	.buswidth = 16,
+	.qos.qos_port = 2,
+	.qos.qos_mode = NOC_QOS_MODE_BYPASS,
+	.qos.areq_prio = 0,
+	.qos.prio_level = 0,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_ebi),
+	.links = link_slv_ebi,
+};
+
+static struct qcom_icc_node mas_snoc_bimc_nrt = {
+	.name = "mas_snoc_bimc_nrt",
+	.id = SM6115_MASTER_SNOC_BIMC_NRT,
+	.channels = 1,
+	.buswidth = 16,
+	.qos.qos_port = 3,
+	.qos.qos_mode = NOC_QOS_MODE_BYPASS,
+	.qos.areq_prio = 0,
+	.qos.prio_level = 0,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_ebi),
+	.links = link_slv_ebi,
+};
+
+static struct qcom_icc_node mas_snoc_bimc = {
+	.name = "mas_snoc_bimc",
+	.id = SM6115_MASTER_SNOC_BIMC,
+	.channels = 1,
+	.buswidth = 16,
+	.qos.qos_port = 6,
+	.qos.qos_mode = NOC_QOS_MODE_BYPASS,
+	.qos.areq_prio = 0,
+	.qos.prio_level = 0,
+	.mas_rpm_id = 3,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_ebi),
+	.links = link_slv_ebi,
+};
+
+static struct qcom_icc_node qnm_gpu = {
+	.name = "qnm_gpu",
+	.id = SM6115_MASTER_GRAPHICS_3D,
+	.channels = 1,
+	.buswidth = 32,
+	.qos.qos_port = 1,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.prio_level = 0,
+	.qos.areq_prio = 0,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(slv_ebi_slv_bimc_snoc_links),
+	.links = slv_ebi_slv_bimc_snoc_links,
+};
+
+static struct qcom_icc_node tcu_0 = {
+	.name = "tcu_0",
+	.id = SM6115_MASTER_TCU_0,
+	.channels = 1,
+	.buswidth = 8,
+	.qos.qos_port = 4,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.prio_level = 6,
+	.qos.areq_prio = 6,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(slv_ebi_slv_bimc_snoc_links),
+	.links = slv_ebi_slv_bimc_snoc_links,
+};
+
+static const u16 qup_core_0_links[] = {
+	SM6115_SLAVE_QUP_CORE_0,
+};
+
+static struct qcom_icc_node qup0_core_master = {
+	.name = "qup0_core_master",
+	.id = SM6115_MASTER_QUP_CORE_0,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = 170,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(qup_core_0_links),
+	.links = qup_core_0_links,
+};
+
+static const u16 link_slv_anoc_snoc[] = {
+	SM6115_SLAVE_ANOC_SNOC,
+};
+
+static struct qcom_icc_node crypto_c0 = {
+	.name = "crypto_c0",
+	.id = SM6115_MASTER_CRYPTO_CORE0,
+	.channels = 1,
+	.buswidth = 8,
+	.qos.qos_port = 43,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 2,
+	.mas_rpm_id = 23,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_anoc_snoc),
+	.links = link_slv_anoc_snoc,
+};
+
+static const u16 mas_snoc_cnoc_links[] = {
+	SM6115_SLAVE_AHB2PHY_USB,
+	SM6115_SLAVE_APSS_THROTTLE_CFG,
+	SM6115_SLAVE_BIMC_CFG,
+	SM6115_SLAVE_BOOT_ROM,
+	SM6115_SLAVE_CAMERA_CFG,
+	SM6115_SLAVE_CAMERA_NRT_THROTTLE_CFG,
+	SM6115_SLAVE_CAMERA_RT_THROTTLE_CFG,
+	SM6115_SLAVE_CLK_CTL,
+	SM6115_SLAVE_CNOC_MSS,
+	SM6115_SLAVE_CRYPTO_0_CFG,
+	SM6115_SLAVE_DCC_CFG,
+	SM6115_SLAVE_DDR_PHY_CFG,
+	SM6115_SLAVE_DDR_SS_CFG,
+	SM6115_SLAVE_DISPLAY_CFG,
+	SM6115_SLAVE_DISPLAY_THROTTLE_CFG,
+	SM6115_SLAVE_GPU_CFG,
+	SM6115_SLAVE_GPU_THROTTLE_CFG,
+	SM6115_SLAVE_HWKM_CORE,
+	SM6115_SLAVE_IMEM_CFG,
+	SM6115_SLAVE_IPA_CFG,
+	SM6115_SLAVE_LPASS,
+	SM6115_SLAVE_MAPSS,
+	SM6115_SLAVE_MDSP_MPU_CFG,
+	SM6115_SLAVE_MESSAGE_RAM,
+	SM6115_SLAVE_PDM,
+	SM6115_SLAVE_PIMEM_CFG,
+	SM6115_SLAVE_PKA_CORE,
+	SM6115_SLAVE_PMIC_ARB,
+	SM6115_SLAVE_QDSS_CFG,
+	SM6115_SLAVE_QM_CFG,
+	SM6115_SLAVE_QM_MPU_CFG,
+	SM6115_SLAVE_QPIC,
+	SM6115_SLAVE_QUP_0,
+	SM6115_SLAVE_RBCPR_CX_CFG,
+	SM6115_SLAVE_RBCPR_MX_CFG,
+	SM6115_SLAVE_RPM,
+	SM6115_SLAVE_SDCC_1,
+	SM6115_SLAVE_SDCC_2,
+	SM6115_SLAVE_SECURITY,
+	SM6115_SLAVE_SERVICE_CNOC,
+	SM6115_SLAVE_SNOC_CFG,
+	SM6115_SLAVE_TCSR,
+	SM6115_SLAVE_TLMM,
+	SM6115_SLAVE_USB3,
+	SM6115_SLAVE_VENUS_CFG,
+	SM6115_SLAVE_VENUS_THROTTLE_CFG,
+	SM6115_SLAVE_VSENSE_CTRL_CFG,
+};
+
+static struct qcom_icc_node mas_snoc_cnoc = {
+	.name = "mas_snoc_cnoc",
+	.id = SM6115_MASTER_SNOC_CNOC,
+	.channels = 1,
+	.buswidth = 8,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(mas_snoc_cnoc_links),
+	.links = mas_snoc_cnoc_links,
+};
+
+static struct qcom_icc_node xm_dap = {
+	.name = "xm_dap",
+	.id = SM6115_MASTER_QDSS_DAP,
+	.channels = 1,
+	.buswidth = 8,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(mas_snoc_cnoc_links),
+	.links = mas_snoc_cnoc_links,
+};
+
+static const u16 link_slv_snoc_bimc_nrt[] = {
+	SM6115_SLAVE_SNOC_BIMC_NRT,
+};
+
+static struct qcom_icc_node qnm_camera_nrt = {
+	.name = "qnm_camera_nrt",
+	.id = SM6115_MASTER_CAMNOC_SF,
+	.channels = 1,
+	.buswidth = 32,
+	.qos.qos_port = 25,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 3,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_snoc_bimc_nrt),
+	.links = link_slv_snoc_bimc_nrt,
+};
+
+static struct qcom_icc_node qxm_venus0 = {
+	.name = "qxm_venus0",
+	.id = SM6115_MASTER_VIDEO_P0,
+	.channels = 1,
+	.buswidth = 16,
+	.qos.qos_port = 30,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 3,
+	.qos.urg_fwd_en = true,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_snoc_bimc_nrt),
+	.links = link_slv_snoc_bimc_nrt,
+};
+
+static struct qcom_icc_node qxm_venus_cpu = {
+	.name = "qxm_venus_cpu",
+	.id = SM6115_MASTER_VIDEO_PROC,
+	.channels = 1,
+	.buswidth = 8,
+	.qos.qos_port = 34,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_snoc_bimc_nrt),
+	.links = link_slv_snoc_bimc_nrt,
+};
+
+static const u16 link_slv_snoc_bimc_rt[] = {
+	SM6115_SLAVE_SNOC_BIMC_RT,
+};
+
+static struct qcom_icc_node qnm_camera_rt = {
+	.name = "qnm_camera_rt",
+	.id = SM6115_MASTER_CAMNOC_HF,
+	.channels = 1,
+	.buswidth = 32,
+	.qos.qos_port = 31,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 3,
+	.qos.urg_fwd_en = true,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_snoc_bimc_rt),
+	.links = link_slv_snoc_bimc_rt,
+};
+
+static struct qcom_icc_node qxm_mdp0 = {
+	.name = "qxm_mdp0",
+	.id = SM6115_MASTER_MDP_PORT0,
+	.channels = 1,
+	.buswidth = 16,
+	.qos.qos_port = 26,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 3,
+	.qos.urg_fwd_en = true,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_snoc_bimc_rt),
+	.links = link_slv_snoc_bimc_rt,
+};
+
+static const u16 slv_service_snoc_links[] = {
+	SM6115_SLAVE_SERVICE_SNOC,
+};
+
+static struct qcom_icc_node qhm_snoc_cfg = {
+	.name = "qhm_snoc_cfg",
+	.id = SM6115_MASTER_SNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(slv_service_snoc_links),
+	.links = slv_service_snoc_links,
+};
+
+static const u16 mas_tic_links[] = {
+	SM6115_SLAVE_APPSS,
+	SM6115_SLAVE_OCIMEM,
+	SM6115_SLAVE_PIMEM,
+	SM6115_SLAVE_QDSS_STM,
+	SM6115_SLAVE_TCU,
+	SM6115_SLAVE_SNOC_BIMC,
+	SM6115_SLAVE_SNOC_CNOC,
+};
+
+static struct qcom_icc_node qhm_tic = {
+	.name = "qhm_tic",
+	.id = SM6115_MASTER_TIC,
+	.channels = 1,
+	.buswidth = 4,
+	.qos.qos_port = 29,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 2,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(mas_tic_links),
+	.links = mas_tic_links,
+};
+
+static struct qcom_icc_node mas_anoc_snoc = {
+	.name = "mas_anoc_snoc",
+	.id = SM6115_MASTER_ANOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(mas_tic_links),
+	.links = mas_tic_links,
+};
+
+static const u16 mas_bimc_snoc_links[] = {
+	SM6115_SLAVE_APPSS,
+	SM6115_SLAVE_SNOC_CNOC,
+	SM6115_SLAVE_OCIMEM,
+	SM6115_SLAVE_PIMEM,
+	SM6115_SLAVE_QDSS_STM,
+	SM6115_SLAVE_TCU,
+};
+
+static struct qcom_icc_node mas_bimc_snoc = {
+	.name = "mas_bimc_snoc",
+	.id = SM6115_MASTER_BIMC_SNOC,
+	.channels = 1,
+	.buswidth = 8,
+	.mas_rpm_id = 21,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(mas_bimc_snoc_links),
+	.links = mas_bimc_snoc_links,
+};
+
+static const u16 mas_pimem_links[] = {
+	SM6115_SLAVE_OCIMEM,
+	SM6115_SLAVE_SNOC_BIMC,
+};
+
+static struct qcom_icc_node qxm_pimem = {
+	.name = "qxm_pimem",
+	.id = SM6115_MASTER_PIMEM,
+	.channels = 1,
+	.buswidth = 8,
+	.qos.qos_port = 41,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 2,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(mas_pimem_links),
+	.links = mas_pimem_links,
+};
+
+static struct qcom_icc_node qhm_qdss_bam = {
+	.name = "qhm_qdss_bam",
+	.id = SM6115_MASTER_QDSS_BAM,
+	.channels = 1,
+	.buswidth = 4,
+	.qos.qos_port = 23,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 2,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_anoc_snoc),
+	.links = link_slv_anoc_snoc,
+};
+
+static struct qcom_icc_node qhm_qpic = {
+	.name = "qhm_qpic",
+	.id = SM6115_MASTER_QPIC,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_anoc_snoc),
+	.links = link_slv_anoc_snoc,
+};
+
+static struct qcom_icc_node qhm_qup0 = {
+	.name = "qhm_qup0",
+	.id = SM6115_MASTER_QUP_0,
+	.channels = 1,
+	.buswidth = 4,
+	.qos.qos_port = 21,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 2,
+	.mas_rpm_id = 166,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_anoc_snoc),
+	.links = link_slv_anoc_snoc,
+};
+
+static struct qcom_icc_node qxm_ipa = {
+	.name = "qxm_ipa",
+	.id = SM6115_MASTER_IPA,
+	.channels = 1,
+	.buswidth = 8,
+	.qos.qos_port = 24,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 2,
+	.mas_rpm_id = 59,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_anoc_snoc),
+	.links = link_slv_anoc_snoc,
+};
+
+static struct qcom_icc_node xm_qdss_etr = {
+	.name = "xm_qdss_etr",
+	.id = SM6115_MASTER_QDSS_ETR,
+	.channels = 1,
+	.buswidth = 8,
+	.qos.qos_port = 33,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 2,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_anoc_snoc),
+	.links = link_slv_anoc_snoc,
+};
+
+static struct qcom_icc_node xm_sdc1 = {
+	.name = "xm_sdc1",
+	.id = SM6115_MASTER_SDCC_1,
+	.channels = 1,
+	.buswidth = 8,
+	.qos.qos_port = 38,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 2,
+	.mas_rpm_id = 33,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_anoc_snoc),
+	.links = link_slv_anoc_snoc,
+};
+
+static struct qcom_icc_node xm_sdc2 = {
+	.name = "xm_sdc2",
+	.id = SM6115_MASTER_SDCC_2,
+	.channels = 1,
+	.buswidth = 8,
+	.qos.qos_port = 44,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 2,
+	.mas_rpm_id = 35,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_anoc_snoc),
+	.links = link_slv_anoc_snoc,
+};
+
+static struct qcom_icc_node xm_usb3_0 = {
+	.name = "xm_usb3_0",
+	.id = SM6115_MASTER_USB3,
+	.channels = 1,
+	.buswidth = 8,
+	.qos.qos_port = 45,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 2,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_anoc_snoc),
+	.links = link_slv_anoc_snoc,
+};
+
+static struct qcom_icc_node ebi = {
+	.name = "ebi",
+	.id = SM6115_SLAVE_EBI_CH0,
+	.channels = 2,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = 0,
+};
+
+static const u16 slv_bimc_snoc_links[] = {
+	SM6115_MASTER_BIMC_SNOC,
+};
+
+static struct qcom_icc_node slv_bimc_snoc = {
+	.name = "slv_bimc_snoc",
+	.id = SM6115_SLAVE_BIMC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = 2,
+	.num_links = ARRAY_SIZE(slv_bimc_snoc_links),
+	.links = slv_bimc_snoc_links,
+};
+
+static struct qcom_icc_node qup0_core_slave = {
+	.name = "qup0_core_slave",
+	.id = SM6115_SLAVE_QUP_CORE_0,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_ahb2phy_usb = {
+	.name = "qhs_ahb2phy_usb",
+	.id = SM6115_SLAVE_AHB2PHY_USB,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_apss_throttle_cfg = {
+	.name = "qhs_apss_throttle_cfg",
+	.id = SM6115_SLAVE_APSS_THROTTLE_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_bimc_cfg = {
+	.name = "qhs_bimc_cfg",
+	.id = SM6115_SLAVE_BIMC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_boot_rom = {
+	.name = "qhs_boot_rom",
+	.id = SM6115_SLAVE_BOOT_ROM,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_camera_nrt_throttle_cfg = {
+	.name = "qhs_camera_nrt_throttle_cfg",
+	.id = SM6115_SLAVE_CAMERA_NRT_THROTTLE_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_camera_rt_throttle_cfg = {
+	.name = "qhs_camera_rt_throttle_cfg",
+	.id = SM6115_SLAVE_CAMERA_RT_THROTTLE_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_camera_ss_cfg = {
+	.name = "qhs_camera_ss_cfg",
+	.id = SM6115_SLAVE_CAMERA_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_clk_ctl = {
+	.name = "qhs_clk_ctl",
+	.id = SM6115_SLAVE_CLK_CTL,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_cpr_cx = {
+	.name = "qhs_cpr_cx",
+	.id = SM6115_SLAVE_RBCPR_CX_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_cpr_mx = {
+	.name = "qhs_cpr_mx",
+	.id = SM6115_SLAVE_RBCPR_MX_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_crypto0_cfg = {
+	.name = "qhs_crypto0_cfg",
+	.id = SM6115_SLAVE_CRYPTO_0_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_dcc_cfg = {
+	.name = "qhs_dcc_cfg",
+	.id = SM6115_SLAVE_DCC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_ddr_phy_cfg = {
+	.name = "qhs_ddr_phy_cfg",
+	.id = SM6115_SLAVE_DDR_PHY_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_ddr_ss_cfg = {
+	.name = "qhs_ddr_ss_cfg",
+	.id = SM6115_SLAVE_DDR_SS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_disp_ss_cfg = {
+	.name = "qhs_disp_ss_cfg",
+	.id = SM6115_SLAVE_DISPLAY_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_display_throttle_cfg = {
+	.name = "qhs_display_throttle_cfg",
+	.id = SM6115_SLAVE_DISPLAY_THROTTLE_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_gpu_cfg = {
+	.name = "qhs_gpu_cfg",
+	.id = SM6115_SLAVE_GPU_CFG,
+	.channels = 1,
+	.buswidth = 8,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_gpu_throttle_cfg = {
+	.name = "qhs_gpu_throttle_cfg",
+	.id = SM6115_SLAVE_GPU_THROTTLE_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_hwkm = {
+	.name = "qhs_hwkm",
+	.id = SM6115_SLAVE_HWKM_CORE,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_imem_cfg = {
+	.name = "qhs_imem_cfg",
+	.id = SM6115_SLAVE_IMEM_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_ipa_cfg = {
+	.name = "qhs_ipa_cfg",
+	.id = SM6115_SLAVE_IPA_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_lpass = {
+	.name = "qhs_lpass",
+	.id = SM6115_SLAVE_LPASS,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_mapss = {
+	.name = "qhs_mapss",
+	.id = SM6115_SLAVE_MAPSS,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_mdsp_mpu_cfg = {
+	.name = "qhs_mdsp_mpu_cfg",
+	.id = SM6115_SLAVE_MDSP_MPU_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_mesg_ram = {
+	.name = "qhs_mesg_ram",
+	.id = SM6115_SLAVE_MESSAGE_RAM,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_mss = {
+	.name = "qhs_mss",
+	.id = SM6115_SLAVE_CNOC_MSS,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_pdm = {
+	.name = "qhs_pdm",
+	.id = SM6115_SLAVE_PDM,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_pimem_cfg = {
+	.name = "qhs_pimem_cfg",
+	.id = SM6115_SLAVE_PIMEM_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_pka_wrapper = {
+	.name = "qhs_pka_wrapper",
+	.id = SM6115_SLAVE_PKA_CORE,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_pmic_arb = {
+	.name = "qhs_pmic_arb",
+	.id = SM6115_SLAVE_PMIC_ARB,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_qdss_cfg = {
+	.name = "qhs_qdss_cfg",
+	.id = SM6115_SLAVE_QDSS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_qm_cfg = {
+	.name = "qhs_qm_cfg",
+	.id = SM6115_SLAVE_QM_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_qm_mpu_cfg = {
+	.name = "qhs_qm_mpu_cfg",
+	.id = SM6115_SLAVE_QM_MPU_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_qpic = {
+	.name = "qhs_qpic",
+	.id = SM6115_SLAVE_QPIC,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_qup0 = {
+	.name = "qhs_qup0",
+	.id = SM6115_SLAVE_QUP_0,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_rpm = {
+	.name = "qhs_rpm",
+	.id = SM6115_SLAVE_RPM,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_sdc1 = {
+	.name = "qhs_sdc1",
+	.id = SM6115_SLAVE_SDCC_1,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_sdc2 = {
+	.name = "qhs_sdc2",
+	.id = SM6115_SLAVE_SDCC_2,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_security = {
+	.name = "qhs_security",
+	.id = SM6115_SLAVE_SECURITY,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static const u16 slv_snoc_cfg_links[] = {
+	SM6115_MASTER_SNOC_CFG,
+};
+
+static struct qcom_icc_node qhs_snoc_cfg = {
+	.name = "qhs_snoc_cfg",
+	.id = SM6115_SLAVE_SNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(slv_snoc_cfg_links),
+	.links = slv_snoc_cfg_links,
+};
+
+static struct qcom_icc_node qhs_tcsr = {
+	.name = "qhs_tcsr",
+	.id = SM6115_SLAVE_TCSR,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_tlmm = {
+	.name = "qhs_tlmm",
+	.id = SM6115_SLAVE_TLMM,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_usb3 = {
+	.name = "qhs_usb3",
+	.id = SM6115_SLAVE_USB3,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_venus_cfg = {
+	.name = "qhs_venus_cfg",
+	.id = SM6115_SLAVE_VENUS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_venus_throttle_cfg = {
+	.name = "qhs_venus_throttle_cfg",
+	.id = SM6115_SLAVE_VENUS_THROTTLE_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_vsense_ctrl_cfg = {
+	.name = "qhs_vsense_ctrl_cfg",
+	.id = SM6115_SLAVE_VSENSE_CTRL_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node srvc_cnoc = {
+	.name = "srvc_cnoc",
+	.id = SM6115_SLAVE_SERVICE_CNOC,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static const u16 slv_snoc_bimc_nrt_links[] = {
+	SM6115_MASTER_SNOC_BIMC_NRT,
+};
+
+static struct qcom_icc_node slv_snoc_bimc_nrt = {
+	.name = "slv_snoc_bimc_nrt",
+	.id = SM6115_SLAVE_SNOC_BIMC_NRT,
+	.channels = 1,
+	.buswidth = 16,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(slv_snoc_bimc_nrt_links),
+	.links = slv_snoc_bimc_nrt_links,
+};
+
+static const u16 slv_snoc_bimc_rt_links[] = {
+	SM6115_MASTER_SNOC_BIMC_RT,
+};
+
+static struct qcom_icc_node slv_snoc_bimc_rt = {
+	.name = "slv_snoc_bimc_rt",
+	.id = SM6115_SLAVE_SNOC_BIMC_RT,
+	.channels = 1,
+	.buswidth = 16,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(slv_snoc_bimc_rt_links),
+	.links = slv_snoc_bimc_rt_links,
+};
+
+static struct qcom_icc_node qhs_apss = {
+	.name = "qhs_apss",
+	.id = SM6115_SLAVE_APPSS,
+	.channels = 1,
+	.buswidth = 8,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static const u16 slv_snoc_cnoc_links[] = {
+	SM6115_MASTER_SNOC_CNOC
+};
+
+static struct qcom_icc_node slv_snoc_cnoc = {
+	.name = "slv_snoc_cnoc",
+	.id = SM6115_SLAVE_SNOC_CNOC,
+	.channels = 1,
+	.buswidth = 8,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = 25,
+	.num_links = ARRAY_SIZE(slv_snoc_cnoc_links),
+	.links = slv_snoc_cnoc_links,
+};
+
+static struct qcom_icc_node qxs_imem = {
+	.name = "qxs_imem",
+	.id = SM6115_SLAVE_OCIMEM,
+	.channels = 1,
+	.buswidth = 8,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = 26,
+};
+
+static struct qcom_icc_node qxs_pimem = {
+	.name = "qxs_pimem",
+	.id = SM6115_SLAVE_PIMEM,
+	.channels = 1,
+	.buswidth = 8,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static const u16 slv_snoc_bimc_links[] = {
+	SM6115_MASTER_SNOC_BIMC,
+};
+
+static struct qcom_icc_node slv_snoc_bimc = {
+	.name = "slv_snoc_bimc",
+	.id = SM6115_SLAVE_SNOC_BIMC,
+	.channels = 1,
+	.buswidth = 16,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = 24,
+	.num_links = ARRAY_SIZE(slv_snoc_bimc_links),
+	.links = slv_snoc_bimc_links,
+};
+
+static struct qcom_icc_node srvc_snoc = {
+	.name = "srvc_snoc",
+	.id = SM6115_SLAVE_SERVICE_SNOC,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node xs_qdss_stm = {
+	.name = "xs_qdss_stm",
+	.id = SM6115_SLAVE_QDSS_STM,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = 30,
+};
+
+static struct qcom_icc_node xs_sys_tcu_cfg = {
+	.name = "xs_sys_tcu_cfg",
+	.id = SM6115_SLAVE_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static const u16 slv_anoc_snoc_links[] = {
+	SM6115_MASTER_ANOC_SNOC,
+};
+
+static struct qcom_icc_node slv_anoc_snoc = {
+	.name = "slv_anoc_snoc",
+	.id = SM6115_SLAVE_ANOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(slv_anoc_snoc_links),
+	.links = slv_anoc_snoc_links,
+};
+
+static struct qcom_icc_node *bimc_nodes[] = {
+	[MASTER_AMPSS_M0] = &apps_proc,
+	[MASTER_SNOC_BIMC_RT] = &mas_snoc_bimc_rt,
+	[MASTER_SNOC_BIMC_NRT] = &mas_snoc_bimc_nrt,
+	[SNOC_BIMC_MAS] = &mas_snoc_bimc,
+	[MASTER_GRAPHICS_3D] = &qnm_gpu,
+	[MASTER_TCU_0] = &tcu_0,
+	[SLAVE_EBI_CH0] = &ebi,
+	[BIMC_SNOC_SLV] = &slv_bimc_snoc,
+};
+
+static const struct regmap_config bimc_regmap_config = {
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.max_register	= 0x80000,
+	.fast_io	= true,
+};
+
+static const struct qcom_icc_desc sm6115_bimc = {
+	.type = QCOM_ICC_BIMC,
+	.nodes = bimc_nodes,
+	.num_nodes = ARRAY_SIZE(bimc_nodes),
+	.regmap_cfg = &bimc_regmap_config,
+	.bus_clk_desc = &bimc_clk,
+	.keep_alive = true,
+	.qos_offset = 0x8000,
+	.ab_coeff = 153,
+};
+
+static struct qcom_icc_node *config_noc_nodes[] = {
+	[SNOC_CNOC_MAS] = &mas_snoc_cnoc,
+	[MASTER_QDSS_DAP] = &xm_dap,
+	[SLAVE_AHB2PHY_USB] = &qhs_ahb2phy_usb,
+	[SLAVE_APSS_THROTTLE_CFG] = &qhs_apss_throttle_cfg,
+	[SLAVE_BIMC_CFG] = &qhs_bimc_cfg,
+	[SLAVE_BOOT_ROM] = &qhs_boot_rom,
+	[SLAVE_CAMERA_NRT_THROTTLE_CFG] = &qhs_camera_nrt_throttle_cfg,
+	[SLAVE_CAMERA_RT_THROTTLE_CFG] = &qhs_camera_rt_throttle_cfg,
+	[SLAVE_CAMERA_CFG] = &qhs_camera_ss_cfg,
+	[SLAVE_CLK_CTL] = &qhs_clk_ctl,
+	[SLAVE_RBCPR_CX_CFG] = &qhs_cpr_cx,
+	[SLAVE_RBCPR_MX_CFG] = &qhs_cpr_mx,
+	[SLAVE_CRYPTO_0_CFG] = &qhs_crypto0_cfg,
+	[SLAVE_DCC_CFG] = &qhs_dcc_cfg,
+	[SLAVE_DDR_PHY_CFG] = &qhs_ddr_phy_cfg,
+	[SLAVE_DDR_SS_CFG] = &qhs_ddr_ss_cfg,
+	[SLAVE_DISPLAY_CFG] = &qhs_disp_ss_cfg,
+	[SLAVE_DISPLAY_THROTTLE_CFG] = &qhs_display_throttle_cfg,
+	[SLAVE_GPU_CFG] = &qhs_gpu_cfg,
+	[SLAVE_GPU_THROTTLE_CFG] = &qhs_gpu_throttle_cfg,
+	[SLAVE_HWKM_CORE] = &qhs_hwkm,
+	[SLAVE_IMEM_CFG] = &qhs_imem_cfg,
+	[SLAVE_IPA_CFG] = &qhs_ipa_cfg,
+	[SLAVE_LPASS] = &qhs_lpass,
+	[SLAVE_MAPSS] = &qhs_mapss,
+	[SLAVE_MDSP_MPU_CFG] = &qhs_mdsp_mpu_cfg,
+	[SLAVE_MESSAGE_RAM] = &qhs_mesg_ram,
+	[SLAVE_CNOC_MSS] = &qhs_mss,
+	[SLAVE_PDM] = &qhs_pdm,
+	[SLAVE_PIMEM_CFG] = &qhs_pimem_cfg,
+	[SLAVE_PKA_CORE] = &qhs_pka_wrapper,
+	[SLAVE_PMIC_ARB] = &qhs_pmic_arb,
+	[SLAVE_QDSS_CFG] = &qhs_qdss_cfg,
+	[SLAVE_QM_CFG] = &qhs_qm_cfg,
+	[SLAVE_QM_MPU_CFG] = &qhs_qm_mpu_cfg,
+	[SLAVE_QPIC] = &qhs_qpic,
+	[SLAVE_QUP_0] = &qhs_qup0,
+	[SLAVE_RPM] = &qhs_rpm,
+	[SLAVE_SDCC_1] = &qhs_sdc1,
+	[SLAVE_SDCC_2] = &qhs_sdc2,
+	[SLAVE_SECURITY] = &qhs_security,
+	[SLAVE_SNOC_CFG] = &qhs_snoc_cfg,
+	[SLAVE_TCSR] = &qhs_tcsr,
+	[SLAVE_TLMM] = &qhs_tlmm,
+	[SLAVE_USB3] = &qhs_usb3,
+	[SLAVE_VENUS_CFG] = &qhs_venus_cfg,
+	[SLAVE_VENUS_THROTTLE_CFG] = &qhs_venus_throttle_cfg,
+	[SLAVE_VSENSE_CTRL_CFG] = &qhs_vsense_ctrl_cfg,
+	[SLAVE_SERVICE_CNOC] = &srvc_cnoc,
+};
+
+static const struct regmap_config cnoc_regmap_config = {
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.max_register	= 0x6200,
+	.fast_io	= true,
+};
+
+static const struct qcom_icc_desc sm6115_config_noc = {
+	.type = QCOM_ICC_QNOC,
+	.nodes = config_noc_nodes,
+	.num_nodes = ARRAY_SIZE(config_noc_nodes),
+	.regmap_cfg = &cnoc_regmap_config,
+	.intf_clocks = cnoc_intf_clocks,
+	.num_intf_clocks = ARRAY_SIZE(cnoc_intf_clocks),
+	.bus_clk_desc = &bus_1_clk,
+	.keep_alive = true,
+};
+
+static struct qcom_icc_node *sys_noc_nodes[] = {
+	[MASTER_CRYPTO_CORE0] = &crypto_c0,
+	[MASTER_SNOC_CFG] = &qhm_snoc_cfg,
+	[MASTER_TIC] = &qhm_tic,
+	[MASTER_ANOC_SNOC] = &mas_anoc_snoc,
+	[BIMC_SNOC_MAS] = &mas_bimc_snoc,
+	[MASTER_PIMEM] = &qxm_pimem,
+	[MASTER_QDSS_BAM] = &qhm_qdss_bam,
+	[MASTER_QPIC] = &qhm_qpic,
+	[MASTER_QUP_0] = &qhm_qup0,
+	[MASTER_IPA] = &qxm_ipa,
+	[MASTER_QDSS_ETR] = &xm_qdss_etr,
+	[MASTER_SDCC_1] = &xm_sdc1,
+	[MASTER_SDCC_2] = &xm_sdc2,
+	[MASTER_USB3] = &xm_usb3_0,
+	[SLAVE_APPSS] = &qhs_apss,
+	[SNOC_CNOC_SLV] = &slv_snoc_cnoc,
+	[SLAVE_OCIMEM] = &qxs_imem,
+	[SLAVE_PIMEM] = &qxs_pimem,
+	[SNOC_BIMC_SLV] = &slv_snoc_bimc,
+	[SLAVE_SERVICE_SNOC] = &srvc_snoc,
+	[SLAVE_QDSS_STM] = &xs_qdss_stm,
+	[SLAVE_TCU] = &xs_sys_tcu_cfg,
+	[SLAVE_ANOC_SNOC] = &slv_anoc_snoc,
+};
+
+static const struct regmap_config sys_noc_regmap_config = {
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.max_register	= 0x5f080,
+	.fast_io	= true,
+};
+
+static const struct qcom_icc_desc sm6115_sys_noc = {
+	.type = QCOM_ICC_QNOC,
+	.nodes = sys_noc_nodes,
+	.num_nodes = ARRAY_SIZE(sys_noc_nodes),
+	.regmap_cfg = &sys_noc_regmap_config,
+	.intf_clocks = snoc_intf_clocks,
+	.num_intf_clocks = ARRAY_SIZE(snoc_intf_clocks),
+	.bus_clk_desc = &bus_2_clk,
+	.keep_alive = true,
+};
+
+static struct qcom_icc_node *clk_virt_nodes[] = {
+	[MASTER_QUP_CORE_0] = &qup0_core_master,
+	[SLAVE_QUP_CORE_0] = &qup0_core_slave,
+};
+
+static const struct qcom_icc_desc sm6115_clk_virt = {
+	.type = QCOM_ICC_QNOC,
+	.nodes = clk_virt_nodes,
+	.num_nodes = ARRAY_SIZE(clk_virt_nodes),
+	.regmap_cfg = &sys_noc_regmap_config,
+	.bus_clk_desc = &qup_clk,
+	.keep_alive = true,
+};
+
+static struct qcom_icc_node *mmnrt_virt_nodes[] = {
+	[MASTER_CAMNOC_SF] = &qnm_camera_nrt,
+	[MASTER_VIDEO_P0] = &qxm_venus0,
+	[MASTER_VIDEO_PROC] = &qxm_venus_cpu,
+	[SLAVE_SNOC_BIMC_NRT] = &slv_snoc_bimc_nrt,
+};
+
+static const struct qcom_icc_desc sm6115_mmnrt_virt = {
+	.type = QCOM_ICC_QNOC,
+	.nodes = mmnrt_virt_nodes,
+	.num_nodes = ARRAY_SIZE(mmnrt_virt_nodes),
+	.regmap_cfg = &sys_noc_regmap_config,
+	.bus_clk_desc = &mmaxi_0_clk,
+	.keep_alive = true,
+	.ab_coeff = 142,
+};
+
+static struct qcom_icc_node *mmrt_virt_nodes[] = {
+	[MASTER_CAMNOC_HF] = &qnm_camera_rt,
+	[MASTER_MDP_PORT0] = &qxm_mdp0,
+	[SLAVE_SNOC_BIMC_RT] = &slv_snoc_bimc_rt,
+};
+
+static const struct qcom_icc_desc sm6115_mmrt_virt = {
+	.type = QCOM_ICC_QNOC,
+	.nodes = mmrt_virt_nodes,
+	.num_nodes = ARRAY_SIZE(mmrt_virt_nodes),
+	.regmap_cfg = &sys_noc_regmap_config,
+	.bus_clk_desc = &mmaxi_1_clk,
+	.keep_alive = true,
+	.ab_coeff = 139,
+};
+
+static const struct of_device_id qnoc_of_match[] = {
+	{ .compatible = "qcom,sm6115-bimc", .data = &sm6115_bimc },
+	{ .compatible = "qcom,sm6115-clk-virt", .data = &sm6115_clk_virt },
+	{ .compatible = "qcom,sm6115-cnoc", .data = &sm6115_config_noc },
+	{ .compatible = "qcom,sm6115-mmrt-virt", .data = &sm6115_mmrt_virt },
+	{ .compatible = "qcom,sm6115-mmnrt-virt", .data = &sm6115_mmnrt_virt },
+	{ .compatible = "qcom,sm6115-snoc", .data = &sm6115_sys_noc },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, qnoc_of_match);
+
+static struct platform_driver qnoc_driver = {
+	.probe = qnoc_probe,
+	.remove_new = qnoc_remove,
+	.driver = {
+		.name = "qnoc-sm6115",
+		.of_match_table = qnoc_of_match,
+		.sync_state = icc_sync_state,
+	},
+};
+
+static int __init qnoc_driver_init(void)
+{
+	return platform_driver_register(&qnoc_driver);
+}
+core_initcall(qnoc_driver_init);
+
+static void __exit qnoc_driver_exit(void)
+{
+	platform_driver_unregister(&qnoc_driver);
+}
+module_exit(qnoc_driver_exit);
+
+MODULE_DESCRIPTION("SM6115 NoC driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/interconnect/qcom/sm8550.c b/drivers/interconnect/qcom/sm8550.c
index 629faa4c9aae..fc22cecf650f 100644
--- a/drivers/interconnect/qcom/sm8550.c
+++ b/drivers/interconnect/qcom/sm8550.c
@@ -2223,6 +2223,7 @@ static struct platform_driver qnoc_driver = {
 	.driver = {
 		.name = "qnoc-sm8550",
 		.of_match_table = qnoc_of_match,
+		.sync_state = icc_sync_state,
 	},
 };
 
diff --git a/drivers/interconnect/qcom/sm8650.c b/drivers/interconnect/qcom/sm8650.c
new file mode 100644
index 000000000000..b962e6c233ef
--- /dev/null
+++ b/drivers/interconnect/qcom/sm8650.c
@@ -0,0 +1,1674 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#include <linux/device.h>
+#include <linux/interconnect.h>
+#include <linux/interconnect-provider.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <dt-bindings/interconnect/qcom,sm8650-rpmh.h>
+
+#include "bcm-voter.h"
+#include "icc-common.h"
+#include "icc-rpmh.h"
+#include "sm8650.h"
+
+static struct qcom_icc_node qhm_qspi = {
+	.name = "qhm_qspi",
+	.id = SM8650_MASTER_QSPI_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node qhm_qup1 = {
+	.name = "qhm_qup1",
+	.id = SM8650_MASTER_QUP_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node qxm_qup02 = {
+	.name = "qxm_qup02",
+	.id = SM8650_MASTER_QUP_3,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_sdc4 = {
+	.name = "xm_sdc4",
+	.id = SM8650_MASTER_SDCC_4,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_ufs_mem = {
+	.name = "xm_ufs_mem",
+	.id = SM8650_MASTER_UFS_MEM,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_usb3_0 = {
+	.name = "xm_usb3_0",
+	.id = SM8650_MASTER_USB3_0,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node qhm_qdss_bam = {
+	.name = "qhm_qdss_bam",
+	.id = SM8650_MASTER_QDSS_BAM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qhm_qup2 = {
+	.name = "qhm_qup2",
+	.id = SM8650_MASTER_QUP_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qxm_crypto = {
+	.name = "qxm_crypto",
+	.id = SM8650_MASTER_CRYPTO,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qxm_ipa = {
+	.name = "qxm_ipa",
+	.id = SM8650_MASTER_IPA,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qxm_sp = {
+	.name = "qxm_sp",
+	.id = SM8650_MASTER_SP,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_qdss_etr_0 = {
+	.name = "xm_qdss_etr_0",
+	.id = SM8650_MASTER_QDSS_ETR,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_qdss_etr_1 = {
+	.name = "xm_qdss_etr_1",
+	.id = SM8650_MASTER_QDSS_ETR_1,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_sdc2 = {
+	.name = "xm_sdc2",
+	.id = SM8650_MASTER_SDCC_2,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qup0_core_master = {
+	.name = "qup0_core_master",
+	.id = SM8650_MASTER_QUP_CORE_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_QUP_CORE_0 },
+};
+
+static struct qcom_icc_node qup1_core_master = {
+	.name = "qup1_core_master",
+	.id = SM8650_MASTER_QUP_CORE_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_QUP_CORE_1 },
+};
+
+static struct qcom_icc_node qup2_core_master = {
+	.name = "qup2_core_master",
+	.id = SM8650_MASTER_QUP_CORE_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_QUP_CORE_2 },
+};
+
+static struct qcom_icc_node qsm_cfg = {
+	.name = "qsm_cfg",
+	.id = SM8650_MASTER_CNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 46,
+	.links = { SM8650_SLAVE_AHB2PHY_SOUTH, SM8650_SLAVE_AHB2PHY_NORTH,
+		   SM8650_SLAVE_CAMERA_CFG, SM8650_SLAVE_CLK_CTL,
+		   SM8650_SLAVE_RBCPR_CX_CFG, SM8650_SLAVE_CPR_HMX,
+		   SM8650_SLAVE_RBCPR_MMCX_CFG, SM8650_SLAVE_RBCPR_MXA_CFG,
+		   SM8650_SLAVE_RBCPR_MXC_CFG, SM8650_SLAVE_CPR_NSPCX,
+		   SM8650_SLAVE_CRYPTO_0_CFG, SM8650_SLAVE_CX_RDPM,
+		   SM8650_SLAVE_DISPLAY_CFG, SM8650_SLAVE_GFX3D_CFG,
+		   SM8650_SLAVE_I2C, SM8650_SLAVE_I3C_IBI0_CFG,
+		   SM8650_SLAVE_I3C_IBI1_CFG, SM8650_SLAVE_IMEM_CFG,
+		   SM8650_SLAVE_CNOC_MSS, SM8650_SLAVE_MX_2_RDPM,
+		   SM8650_SLAVE_MX_RDPM, SM8650_SLAVE_PCIE_0_CFG,
+		   SM8650_SLAVE_PCIE_1_CFG, SM8650_SLAVE_PCIE_RSCC,
+		   SM8650_SLAVE_PDM, SM8650_SLAVE_PRNG,
+		   SM8650_SLAVE_QDSS_CFG, SM8650_SLAVE_QSPI_0,
+		   SM8650_SLAVE_QUP_3, SM8650_SLAVE_QUP_1,
+		   SM8650_SLAVE_QUP_2, SM8650_SLAVE_SDCC_2,
+		   SM8650_SLAVE_SDCC_4, SM8650_SLAVE_SPSS_CFG,
+		   SM8650_SLAVE_TCSR, SM8650_SLAVE_TLMM,
+		   SM8650_SLAVE_UFS_MEM_CFG, SM8650_SLAVE_USB3_0,
+		   SM8650_SLAVE_VENUS_CFG, SM8650_SLAVE_VSENSE_CTRL_CFG,
+		   SM8650_SLAVE_CNOC_MNOC_CFG, SM8650_SLAVE_NSP_QTB_CFG,
+		   SM8650_SLAVE_PCIE_ANOC_CFG, SM8650_SLAVE_SERVICE_CNOC_CFG,
+		   SM8650_SLAVE_QDSS_STM, SM8650_SLAVE_TCU },
+};
+
+static struct qcom_icc_node qnm_gemnoc_cnoc = {
+	.name = "qnm_gemnoc_cnoc",
+	.id = SM8650_MASTER_GEM_NOC_CNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 9,
+	.links = { SM8650_SLAVE_AOSS, SM8650_SLAVE_IPA_CFG,
+		   SM8650_SLAVE_IPC_ROUTER_CFG, SM8650_SLAVE_TME_CFG,
+		   SM8650_SLAVE_APPSS, SM8650_SLAVE_CNOC_CFG,
+		   SM8650_SLAVE_DDRSS_CFG, SM8650_SLAVE_IMEM,
+		   SM8650_SLAVE_SERVICE_CNOC },
+};
+
+static struct qcom_icc_node qnm_gemnoc_pcie = {
+	.name = "qnm_gemnoc_pcie",
+	.id = SM8650_MASTER_GEM_NOC_PCIE_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 2,
+	.links = { SM8650_SLAVE_PCIE_0, SM8650_SLAVE_PCIE_1 },
+};
+
+static struct qcom_icc_node alm_gpu_tcu = {
+	.name = "alm_gpu_tcu",
+	.id = SM8650_MASTER_GPU_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 2,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node alm_sys_tcu = {
+	.name = "alm_sys_tcu",
+	.id = SM8650_MASTER_SYS_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 2,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node alm_ubwc_p_tcu = {
+	.name = "alm_ubwc_p_tcu",
+	.id = SM8650_MASTER_UBWC_P_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 2,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node chm_apps = {
+	.name = "chm_apps",
+	.id = SM8650_MASTER_APPSS_PROC,
+	.channels = 3,
+	.buswidth = 32,
+	.num_links = 3,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC,
+		   SM8650_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_gpu = {
+	.name = "qnm_gpu",
+	.id = SM8650_MASTER_GFX3D,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 2,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_lpass_gemnoc = {
+	.name = "qnm_lpass_gemnoc",
+	.id = SM8650_MASTER_LPASS_GEM_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 3,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC,
+		   SM8650_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_mdsp = {
+	.name = "qnm_mdsp",
+	.id = SM8650_MASTER_MSS_PROC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 3,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC,
+		   SM8650_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_mnoc_hf = {
+	.name = "qnm_mnoc_hf",
+	.id = SM8650_MASTER_MNOC_HF_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 2,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_mnoc_sf = {
+	.name = "qnm_mnoc_sf",
+	.id = SM8650_MASTER_MNOC_SF_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 2,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_nsp_gemnoc = {
+	.name = "qnm_nsp_gemnoc",
+	.id = SM8650_MASTER_COMPUTE_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 3,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC,
+		   SM8650_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_pcie = {
+	.name = "qnm_pcie",
+	.id = SM8650_MASTER_ANOC_PCIE_GEM_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 2,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_snoc_sf = {
+	.name = "qnm_snoc_sf",
+	.id = SM8650_MASTER_SNOC_SF_MEM_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 3,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC,
+		   SM8650_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_ubwc_p = {
+	.name = "qnm_ubwc_p",
+	.id = SM8650_MASTER_UBWC_P,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node xm_gic = {
+	.name = "xm_gic",
+	.id = SM8650_MASTER_GIC,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_lpiaon_noc = {
+	.name = "qnm_lpiaon_noc",
+	.id = SM8650_MASTER_LPIAON_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_LPASS_GEM_NOC },
+};
+
+static struct qcom_icc_node qnm_lpass_lpinoc = {
+	.name = "qnm_lpass_lpinoc",
+	.id = SM8650_MASTER_LPASS_LPINOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_LPIAON_NOC_LPASS_AG_NOC },
+};
+
+static struct qcom_icc_node qxm_lpinoc_dsp_axim = {
+	.name = "qxm_lpinoc_dsp_axim",
+	.id = SM8650_MASTER_LPASS_PROC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_LPICX_NOC_LPIAON_NOC },
+};
+
+static struct qcom_icc_node llcc_mc = {
+	.name = "llcc_mc",
+	.id = SM8650_MASTER_LLCC,
+	.channels = 4,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_EBI1 },
+};
+
+static struct qcom_icc_node qnm_camnoc_hf = {
+	.name = "qnm_camnoc_hf",
+	.id = SM8650_MASTER_CAMNOC_HF,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_MNOC_HF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_camnoc_icp = {
+	.name = "qnm_camnoc_icp",
+	.id = SM8650_MASTER_CAMNOC_ICP,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_camnoc_sf = {
+	.name = "qnm_camnoc_sf",
+	.id = SM8650_MASTER_CAMNOC_SF,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_mdp = {
+	.name = "qnm_mdp",
+	.id = SM8650_MASTER_MDP,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_MNOC_HF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_vapss_hcp = {
+	.name = "qnm_vapss_hcp",
+	.id = SM8650_MASTER_CDSP_HCP,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_video = {
+	.name = "qnm_video",
+	.id = SM8650_MASTER_VIDEO,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_video_cv_cpu = {
+	.name = "qnm_video_cv_cpu",
+	.id = SM8650_MASTER_VIDEO_CV_PROC,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_video_cvp = {
+	.name = "qnm_video_cvp",
+	.id = SM8650_MASTER_VIDEO_PROC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_video_v_cpu = {
+	.name = "qnm_video_v_cpu",
+	.id = SM8650_MASTER_VIDEO_V_PROC,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qsm_mnoc_cfg = {
+	.name = "qsm_mnoc_cfg",
+	.id = SM8650_MASTER_CNOC_MNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_SERVICE_MNOC },
+};
+
+static struct qcom_icc_node qnm_nsp = {
+	.name = "qnm_nsp",
+	.id = SM8650_MASTER_CDSP_PROC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_CDSP_MEM_NOC },
+};
+
+static struct qcom_icc_node qsm_pcie_anoc_cfg = {
+	.name = "qsm_pcie_anoc_cfg",
+	.id = SM8650_MASTER_PCIE_ANOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_SERVICE_PCIE_ANOC },
+};
+
+static struct qcom_icc_node xm_pcie3_0 = {
+	.name = "xm_pcie3_0",
+	.id = SM8650_MASTER_PCIE_0,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_ANOC_PCIE_GEM_NOC },
+};
+
+static struct qcom_icc_node xm_pcie3_1 = {
+	.name = "xm_pcie3_1",
+	.id = SM8650_MASTER_PCIE_1,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_ANOC_PCIE_GEM_NOC },
+};
+
+static struct qcom_icc_node qnm_aggre1_noc = {
+	.name = "qnm_aggre1_noc",
+	.id = SM8650_MASTER_A1NOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_SNOC_GEM_NOC_SF },
+};
+
+static struct qcom_icc_node qnm_aggre2_noc = {
+	.name = "qnm_aggre2_noc",
+	.id = SM8650_MASTER_A2NOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_SNOC_GEM_NOC_SF },
+};
+
+static struct qcom_icc_node qns_a1noc_snoc = {
+	.name = "qns_a1noc_snoc",
+	.id = SM8650_SLAVE_A1NOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_MASTER_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node qns_a2noc_snoc = {
+	.name = "qns_a2noc_snoc",
+	.id = SM8650_SLAVE_A2NOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_MASTER_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qup0_core_slave = {
+	.name = "qup0_core_slave",
+	.id = SM8650_SLAVE_QUP_CORE_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qup1_core_slave = {
+	.name = "qup1_core_slave",
+	.id = SM8650_SLAVE_QUP_CORE_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qup2_core_slave = {
+	.name = "qup2_core_slave",
+	.id = SM8650_SLAVE_QUP_CORE_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ahb2phy0 = {
+	.name = "qhs_ahb2phy0",
+	.id = SM8650_SLAVE_AHB2PHY_SOUTH,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ahb2phy1 = {
+	.name = "qhs_ahb2phy1",
+	.id = SM8650_SLAVE_AHB2PHY_NORTH,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_camera_cfg = {
+	.name = "qhs_camera_cfg",
+	.id = SM8650_SLAVE_CAMERA_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_clk_ctl = {
+	.name = "qhs_clk_ctl",
+	.id = SM8650_SLAVE_CLK_CTL,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_cpr_cx = {
+	.name = "qhs_cpr_cx",
+	.id = SM8650_SLAVE_RBCPR_CX_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_cpr_hmx = {
+	.name = "qhs_cpr_hmx",
+	.id = SM8650_SLAVE_CPR_HMX,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_cpr_mmcx = {
+	.name = "qhs_cpr_mmcx",
+	.id = SM8650_SLAVE_RBCPR_MMCX_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_cpr_mxa = {
+	.name = "qhs_cpr_mxa",
+	.id = SM8650_SLAVE_RBCPR_MXA_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_cpr_mxc = {
+	.name = "qhs_cpr_mxc",
+	.id = SM8650_SLAVE_RBCPR_MXC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_cpr_nspcx = {
+	.name = "qhs_cpr_nspcx",
+	.id = SM8650_SLAVE_CPR_NSPCX,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_crypto0_cfg = {
+	.name = "qhs_crypto0_cfg",
+	.id = SM8650_SLAVE_CRYPTO_0_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_cx_rdpm = {
+	.name = "qhs_cx_rdpm",
+	.id = SM8650_SLAVE_CX_RDPM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_display_cfg = {
+	.name = "qhs_display_cfg",
+	.id = SM8650_SLAVE_DISPLAY_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_gpuss_cfg = {
+	.name = "qhs_gpuss_cfg",
+	.id = SM8650_SLAVE_GFX3D_CFG,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_i2c = {
+	.name = "qhs_i2c",
+	.id = SM8650_SLAVE_I2C,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_i3c_ibi0_cfg = {
+	.name = "qhs_i3c_ibi0_cfg",
+	.id = SM8650_SLAVE_I3C_IBI0_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_i3c_ibi1_cfg = {
+	.name = "qhs_i3c_ibi1_cfg",
+	.id = SM8650_SLAVE_I3C_IBI1_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_imem_cfg = {
+	.name = "qhs_imem_cfg",
+	.id = SM8650_SLAVE_IMEM_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_mss_cfg = {
+	.name = "qhs_mss_cfg",
+	.id = SM8650_SLAVE_CNOC_MSS,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_mx_2_rdpm = {
+	.name = "qhs_mx_2_rdpm",
+	.id = SM8650_SLAVE_MX_2_RDPM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_mx_rdpm = {
+	.name = "qhs_mx_rdpm",
+	.id = SM8650_SLAVE_MX_RDPM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie0_cfg = {
+	.name = "qhs_pcie0_cfg",
+	.id = SM8650_SLAVE_PCIE_0_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie1_cfg = {
+	.name = "qhs_pcie1_cfg",
+	.id = SM8650_SLAVE_PCIE_1_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie_rscc = {
+	.name = "qhs_pcie_rscc",
+	.id = SM8650_SLAVE_PCIE_RSCC,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pdm = {
+	.name = "qhs_pdm",
+	.id = SM8650_SLAVE_PDM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_prng = {
+	.name = "qhs_prng",
+	.id = SM8650_SLAVE_PRNG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qdss_cfg = {
+	.name = "qhs_qdss_cfg",
+	.id = SM8650_SLAVE_QDSS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qspi = {
+	.name = "qhs_qspi",
+	.id = SM8650_SLAVE_QSPI_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qup02 = {
+	.name = "qhs_qup02",
+	.id = SM8650_SLAVE_QUP_3,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qup1 = {
+	.name = "qhs_qup1",
+	.id = SM8650_SLAVE_QUP_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qup2 = {
+	.name = "qhs_qup2",
+	.id = SM8650_SLAVE_QUP_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_sdc2 = {
+	.name = "qhs_sdc2",
+	.id = SM8650_SLAVE_SDCC_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_sdc4 = {
+	.name = "qhs_sdc4",
+	.id = SM8650_SLAVE_SDCC_4,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_spss_cfg = {
+	.name = "qhs_spss_cfg",
+	.id = SM8650_SLAVE_SPSS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_tcsr = {
+	.name = "qhs_tcsr",
+	.id = SM8650_SLAVE_TCSR,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_tlmm = {
+	.name = "qhs_tlmm",
+	.id = SM8650_SLAVE_TLMM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ufs_mem_cfg = {
+	.name = "qhs_ufs_mem_cfg",
+	.id = SM8650_SLAVE_UFS_MEM_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_usb3_0 = {
+	.name = "qhs_usb3_0",
+	.id = SM8650_SLAVE_USB3_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_venus_cfg = {
+	.name = "qhs_venus_cfg",
+	.id = SM8650_SLAVE_VENUS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_vsense_ctrl_cfg = {
+	.name = "qhs_vsense_ctrl_cfg",
+	.id = SM8650_SLAVE_VSENSE_CTRL_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qss_mnoc_cfg = {
+	.name = "qss_mnoc_cfg",
+	.id = SM8650_SLAVE_CNOC_MNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_MASTER_CNOC_MNOC_CFG },
+};
+
+static struct qcom_icc_node qss_nsp_qtb_cfg = {
+	.name = "qss_nsp_qtb_cfg",
+	.id = SM8650_SLAVE_NSP_QTB_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qss_pcie_anoc_cfg = {
+	.name = "qss_pcie_anoc_cfg",
+	.id = SM8650_SLAVE_PCIE_ANOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_MASTER_PCIE_ANOC_CFG },
+};
+
+static struct qcom_icc_node srvc_cnoc_cfg = {
+	.name = "srvc_cnoc_cfg",
+	.id = SM8650_SLAVE_SERVICE_CNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_qdss_stm = {
+	.name = "xs_qdss_stm",
+	.id = SM8650_SLAVE_QDSS_STM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_sys_tcu_cfg = {
+	.name = "xs_sys_tcu_cfg",
+	.id = SM8650_SLAVE_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_aoss = {
+	.name = "qhs_aoss",
+	.id = SM8650_SLAVE_AOSS,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ipa = {
+	.name = "qhs_ipa",
+	.id = SM8650_SLAVE_IPA_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ipc_router = {
+	.name = "qhs_ipc_router",
+	.id = SM8650_SLAVE_IPC_ROUTER_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_tme_cfg = {
+	.name = "qhs_tme_cfg",
+	.id = SM8650_SLAVE_TME_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qss_apss = {
+	.name = "qss_apss",
+	.id = SM8650_SLAVE_APPSS,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qss_cfg = {
+	.name = "qss_cfg",
+	.id = SM8650_SLAVE_CNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_MASTER_CNOC_CFG },
+};
+
+static struct qcom_icc_node qss_ddrss_cfg = {
+	.name = "qss_ddrss_cfg",
+	.id = SM8650_SLAVE_DDRSS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qxs_imem = {
+	.name = "qxs_imem",
+	.id = SM8650_SLAVE_IMEM,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node srvc_cnoc_main = {
+	.name = "srvc_cnoc_main",
+	.id = SM8650_SLAVE_SERVICE_CNOC,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie_0 = {
+	.name = "xs_pcie_0",
+	.id = SM8650_SLAVE_PCIE_0,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie_1 = {
+	.name = "xs_pcie_1",
+	.id = SM8650_SLAVE_PCIE_1,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_gem_noc_cnoc = {
+	.name = "qns_gem_noc_cnoc",
+	.id = SM8650_SLAVE_GEM_NOC_CNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_MASTER_GEM_NOC_CNOC },
+};
+
+static struct qcom_icc_node qns_llcc = {
+	.name = "qns_llcc",
+	.id = SM8650_SLAVE_LLCC,
+	.channels = 4,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_MASTER_LLCC },
+};
+
+static struct qcom_icc_node qns_pcie = {
+	.name = "qns_pcie",
+	.id = SM8650_SLAVE_MEM_NOC_PCIE_SNOC,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_MASTER_GEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qns_lpass_ag_noc_gemnoc = {
+	.name = "qns_lpass_ag_noc_gemnoc",
+	.id = SM8650_SLAVE_LPASS_GEM_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_MASTER_LPASS_GEM_NOC },
+};
+
+static struct qcom_icc_node qns_lpass_aggnoc = {
+	.name = "qns_lpass_aggnoc",
+	.id = SM8650_SLAVE_LPIAON_NOC_LPASS_AG_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_MASTER_LPIAON_NOC },
+};
+
+static struct qcom_icc_node qns_lpi_aon_noc = {
+	.name = "qns_lpi_aon_noc",
+	.id = SM8650_SLAVE_LPICX_NOC_LPIAON_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_MASTER_LPASS_LPINOC },
+};
+
+static struct qcom_icc_node ebi = {
+	.name = "ebi",
+	.id = SM8650_SLAVE_EBI1,
+	.channels = 4,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_mem_noc_hf = {
+	.name = "qns_mem_noc_hf",
+	.id = SM8650_SLAVE_MNOC_HF_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_MASTER_MNOC_HF_MEM_NOC },
+};
+
+static struct qcom_icc_node qns_mem_noc_sf = {
+	.name = "qns_mem_noc_sf",
+	.id = SM8650_SLAVE_MNOC_SF_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_MASTER_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node srvc_mnoc = {
+	.name = "srvc_mnoc",
+	.id = SM8650_SLAVE_SERVICE_MNOC,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_nsp_gemnoc = {
+	.name = "qns_nsp_gemnoc",
+	.id = SM8650_SLAVE_CDSP_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_MASTER_COMPUTE_NOC },
+};
+
+static struct qcom_icc_node qns_pcie_mem_noc = {
+	.name = "qns_pcie_mem_noc",
+	.id = SM8650_SLAVE_ANOC_PCIE_GEM_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_MASTER_ANOC_PCIE_GEM_NOC },
+};
+
+static struct qcom_icc_node srvc_pcie_aggre_noc = {
+	.name = "srvc_pcie_aggre_noc",
+	.id = SM8650_SLAVE_SERVICE_PCIE_ANOC,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_gemnoc_sf = {
+	.name = "qns_gemnoc_sf",
+	.id = SM8650_SLAVE_SNOC_GEM_NOC_SF,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_MASTER_SNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_bcm bcm_acv = {
+	.name = "ACV",
+	.enable_mask = BIT(0),
+	.num_nodes = 1,
+	.nodes = { &ebi },
+};
+
+static struct qcom_icc_bcm bcm_ce0 = {
+	.name = "CE0",
+	.num_nodes = 1,
+	.nodes = { &qxm_crypto },
+};
+
+static struct qcom_icc_bcm bcm_cn0 = {
+	.name = "CN0",
+	.enable_mask = BIT(0),
+	.keepalive = true,
+	.num_nodes = 59,
+	.nodes = { &qsm_cfg, &qhs_ahb2phy0,
+		   &qhs_ahb2phy1, &qhs_camera_cfg,
+		   &qhs_clk_ctl, &qhs_cpr_cx,
+		   &qhs_cpr_hmx, &qhs_cpr_mmcx,
+		   &qhs_cpr_mxa, &qhs_cpr_mxc,
+		   &qhs_cpr_nspcx, &qhs_crypto0_cfg,
+		   &qhs_cx_rdpm, &qhs_display_cfg,
+		   &qhs_gpuss_cfg, &qhs_i2c,
+		   &qhs_i3c_ibi0_cfg, &qhs_i3c_ibi1_cfg,
+		   &qhs_imem_cfg, &qhs_mss_cfg,
+		   &qhs_mx_2_rdpm, &qhs_mx_rdpm,
+		   &qhs_pcie0_cfg, &qhs_pcie1_cfg,
+		   &qhs_pcie_rscc, &qhs_pdm,
+		   &qhs_prng, &qhs_qdss_cfg,
+		   &qhs_qspi, &qhs_qup02,
+		   &qhs_qup1, &qhs_qup2,
+		   &qhs_sdc2, &qhs_sdc4,
+		   &qhs_spss_cfg, &qhs_tcsr,
+		   &qhs_tlmm, &qhs_ufs_mem_cfg,
+		   &qhs_usb3_0, &qhs_venus_cfg,
+		   &qhs_vsense_ctrl_cfg, &qss_mnoc_cfg,
+		   &qss_nsp_qtb_cfg, &qss_pcie_anoc_cfg,
+		   &srvc_cnoc_cfg, &xs_qdss_stm,
+		   &xs_sys_tcu_cfg, &qnm_gemnoc_cnoc,
+		   &qnm_gemnoc_pcie, &qhs_aoss,
+		   &qhs_ipa, &qhs_ipc_router,
+		   &qhs_tme_cfg, &qss_apss,
+		   &qss_cfg, &qss_ddrss_cfg,
+		   &qxs_imem, &srvc_cnoc_main,
+		   &xs_pcie_0, &xs_pcie_1 },
+};
+
+static struct qcom_icc_bcm bcm_co0 = {
+	.name = "CO0",
+	.enable_mask = BIT(0),
+	.num_nodes = 2,
+	.nodes = { &qnm_nsp, &qns_nsp_gemnoc },
+};
+
+static struct qcom_icc_bcm bcm_lp0 = {
+	.name = "LP0",
+	.num_nodes = 2,
+	.nodes = { &qnm_lpass_lpinoc, &qns_lpass_aggnoc },
+};
+
+static struct qcom_icc_bcm bcm_mc0 = {
+	.name = "MC0",
+	.keepalive = true,
+	.num_nodes = 1,
+	.nodes = { &ebi },
+};
+
+static struct qcom_icc_bcm bcm_mm0 = {
+	.name = "MM0",
+	.num_nodes = 1,
+	.nodes = { &qns_mem_noc_hf },
+};
+
+static struct qcom_icc_bcm bcm_mm1 = {
+	.name = "MM1",
+	.enable_mask = BIT(0),
+	.num_nodes = 8,
+	.nodes = { &qnm_camnoc_hf, &qnm_camnoc_icp,
+		   &qnm_camnoc_sf, &qnm_vapss_hcp,
+		   &qnm_video_cv_cpu, &qnm_video_cvp,
+		   &qnm_video_v_cpu, &qns_mem_noc_sf },
+};
+
+static struct qcom_icc_bcm bcm_qup0 = {
+	.name = "QUP0",
+	.keepalive = true,
+	.vote_scale = 1,
+	.num_nodes = 1,
+	.nodes = { &qup0_core_slave },
+};
+
+static struct qcom_icc_bcm bcm_qup1 = {
+	.name = "QUP1",
+	.keepalive = true,
+	.vote_scale = 1,
+	.num_nodes = 1,
+	.nodes = { &qup1_core_slave },
+};
+
+static struct qcom_icc_bcm bcm_qup2 = {
+	.name = "QUP2",
+	.keepalive = true,
+	.vote_scale = 1,
+	.num_nodes = 1,
+	.nodes = { &qup2_core_slave },
+};
+
+static struct qcom_icc_bcm bcm_sh0 = {
+	.name = "SH0",
+	.keepalive = true,
+	.num_nodes = 1,
+	.nodes = { &qns_llcc },
+};
+
+static struct qcom_icc_bcm bcm_sh1 = {
+	.name = "SH1",
+	.enable_mask = BIT(0),
+	.num_nodes = 15,
+	.nodes = { &alm_gpu_tcu, &alm_sys_tcu,
+		   &alm_ubwc_p_tcu, &chm_apps,
+		   &qnm_gpu, &qnm_mdsp,
+		   &qnm_mnoc_hf, &qnm_mnoc_sf,
+		   &qnm_nsp_gemnoc, &qnm_pcie,
+		   &qnm_snoc_sf, &qnm_ubwc_p,
+		   &xm_gic, &qns_gem_noc_cnoc,
+		   &qns_pcie },
+};
+
+static struct qcom_icc_bcm bcm_sn0 = {
+	.name = "SN0",
+	.keepalive = true,
+	.num_nodes = 1,
+	.nodes = { &qns_gemnoc_sf },
+};
+
+static struct qcom_icc_bcm bcm_sn2 = {
+	.name = "SN2",
+	.num_nodes = 1,
+	.nodes = { &qnm_aggre1_noc },
+};
+
+static struct qcom_icc_bcm bcm_sn3 = {
+	.name = "SN3",
+	.num_nodes = 1,
+	.nodes = { &qnm_aggre2_noc },
+};
+
+static struct qcom_icc_bcm bcm_sn4 = {
+	.name = "SN4",
+	.num_nodes = 1,
+	.nodes = { &qns_pcie_mem_noc },
+};
+
+static struct qcom_icc_node * const aggre1_noc_nodes[] = {
+	[MASTER_QSPI_0] = &qhm_qspi,
+	[MASTER_QUP_1] = &qhm_qup1,
+	[MASTER_QUP_3] = &qxm_qup02,
+	[MASTER_SDCC_4] = &xm_sdc4,
+	[MASTER_UFS_MEM] = &xm_ufs_mem,
+	[MASTER_USB3_0] = &xm_usb3_0,
+	[SLAVE_A1NOC_SNOC] = &qns_a1noc_snoc,
+};
+
+static const struct qcom_icc_desc sm8650_aggre1_noc = {
+	.nodes = aggre1_noc_nodes,
+	.num_nodes = ARRAY_SIZE(aggre1_noc_nodes),
+};
+
+static struct qcom_icc_bcm * const aggre2_noc_bcms[] = {
+	&bcm_ce0,
+};
+
+static struct qcom_icc_node * const aggre2_noc_nodes[] = {
+	[MASTER_QDSS_BAM] = &qhm_qdss_bam,
+	[MASTER_QUP_2] = &qhm_qup2,
+	[MASTER_CRYPTO] = &qxm_crypto,
+	[MASTER_IPA] = &qxm_ipa,
+	[MASTER_SP] = &qxm_sp,
+	[MASTER_QDSS_ETR] = &xm_qdss_etr_0,
+	[MASTER_QDSS_ETR_1] = &xm_qdss_etr_1,
+	[MASTER_SDCC_2] = &xm_sdc2,
+	[SLAVE_A2NOC_SNOC] = &qns_a2noc_snoc,
+};
+
+static const struct qcom_icc_desc sm8650_aggre2_noc = {
+	.nodes = aggre2_noc_nodes,
+	.num_nodes = ARRAY_SIZE(aggre2_noc_nodes),
+	.bcms = aggre2_noc_bcms,
+	.num_bcms = ARRAY_SIZE(aggre2_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const clk_virt_bcms[] = {
+	&bcm_qup0,
+	&bcm_qup1,
+	&bcm_qup2,
+};
+
+static struct qcom_icc_node * const clk_virt_nodes[] = {
+	[MASTER_QUP_CORE_0] = &qup0_core_master,
+	[MASTER_QUP_CORE_1] = &qup1_core_master,
+	[MASTER_QUP_CORE_2] = &qup2_core_master,
+	[SLAVE_QUP_CORE_0] = &qup0_core_slave,
+	[SLAVE_QUP_CORE_1] = &qup1_core_slave,
+	[SLAVE_QUP_CORE_2] = &qup2_core_slave,
+};
+
+static const struct qcom_icc_desc sm8650_clk_virt = {
+	.nodes = clk_virt_nodes,
+	.num_nodes = ARRAY_SIZE(clk_virt_nodes),
+	.bcms = clk_virt_bcms,
+	.num_bcms = ARRAY_SIZE(clk_virt_bcms),
+};
+
+static struct qcom_icc_bcm * const config_noc_bcms[] = {
+	&bcm_cn0,
+};
+
+static struct qcom_icc_node * const config_noc_nodes[] = {
+	[MASTER_CNOC_CFG] = &qsm_cfg,
+	[SLAVE_AHB2PHY_SOUTH] = &qhs_ahb2phy0,
+	[SLAVE_AHB2PHY_NORTH] = &qhs_ahb2phy1,
+	[SLAVE_CAMERA_CFG] = &qhs_camera_cfg,
+	[SLAVE_CLK_CTL] = &qhs_clk_ctl,
+	[SLAVE_RBCPR_CX_CFG] = &qhs_cpr_cx,
+	[SLAVE_CPR_HMX] = &qhs_cpr_hmx,
+	[SLAVE_RBCPR_MMCX_CFG] = &qhs_cpr_mmcx,
+	[SLAVE_RBCPR_MXA_CFG] = &qhs_cpr_mxa,
+	[SLAVE_RBCPR_MXC_CFG] = &qhs_cpr_mxc,
+	[SLAVE_CPR_NSPCX] = &qhs_cpr_nspcx,
+	[SLAVE_CRYPTO_0_CFG] = &qhs_crypto0_cfg,
+	[SLAVE_CX_RDPM] = &qhs_cx_rdpm,
+	[SLAVE_DISPLAY_CFG] = &qhs_display_cfg,
+	[SLAVE_GFX3D_CFG] = &qhs_gpuss_cfg,
+	[SLAVE_I2C] = &qhs_i2c,
+	[SLAVE_I3C_IBI0_CFG] = &qhs_i3c_ibi0_cfg,
+	[SLAVE_I3C_IBI1_CFG] = &qhs_i3c_ibi1_cfg,
+	[SLAVE_IMEM_CFG] = &qhs_imem_cfg,
+	[SLAVE_CNOC_MSS] = &qhs_mss_cfg,
+	[SLAVE_MX_2_RDPM] = &qhs_mx_2_rdpm,
+	[SLAVE_MX_RDPM] = &qhs_mx_rdpm,
+	[SLAVE_PCIE_0_CFG] = &qhs_pcie0_cfg,
+	[SLAVE_PCIE_1_CFG] = &qhs_pcie1_cfg,
+	[SLAVE_PCIE_RSCC] = &qhs_pcie_rscc,
+	[SLAVE_PDM] = &qhs_pdm,
+	[SLAVE_PRNG] = &qhs_prng,
+	[SLAVE_QDSS_CFG] = &qhs_qdss_cfg,
+	[SLAVE_QSPI_0] = &qhs_qspi,
+	[SLAVE_QUP_3] = &qhs_qup02,
+	[SLAVE_QUP_1] = &qhs_qup1,
+	[SLAVE_QUP_2] = &qhs_qup2,
+	[SLAVE_SDCC_2] = &qhs_sdc2,
+	[SLAVE_SDCC_4] = &qhs_sdc4,
+	[SLAVE_SPSS_CFG] = &qhs_spss_cfg,
+	[SLAVE_TCSR] = &qhs_tcsr,
+	[SLAVE_TLMM] = &qhs_tlmm,
+	[SLAVE_UFS_MEM_CFG] = &qhs_ufs_mem_cfg,
+	[SLAVE_USB3_0] = &qhs_usb3_0,
+	[SLAVE_VENUS_CFG] = &qhs_venus_cfg,
+	[SLAVE_VSENSE_CTRL_CFG] = &qhs_vsense_ctrl_cfg,
+	[SLAVE_CNOC_MNOC_CFG] = &qss_mnoc_cfg,
+	[SLAVE_NSP_QTB_CFG] = &qss_nsp_qtb_cfg,
+	[SLAVE_PCIE_ANOC_CFG] = &qss_pcie_anoc_cfg,
+	[SLAVE_SERVICE_CNOC_CFG] = &srvc_cnoc_cfg,
+	[SLAVE_QDSS_STM] = &xs_qdss_stm,
+	[SLAVE_TCU] = &xs_sys_tcu_cfg,
+};
+
+static const struct qcom_icc_desc sm8650_config_noc = {
+	.nodes = config_noc_nodes,
+	.num_nodes = ARRAY_SIZE(config_noc_nodes),
+	.bcms = config_noc_bcms,
+	.num_bcms = ARRAY_SIZE(config_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const cnoc_main_bcms[] = {
+	&bcm_cn0,
+};
+
+static struct qcom_icc_node * const cnoc_main_nodes[] = {
+	[MASTER_GEM_NOC_CNOC] = &qnm_gemnoc_cnoc,
+	[MASTER_GEM_NOC_PCIE_SNOC] = &qnm_gemnoc_pcie,
+	[SLAVE_AOSS] = &qhs_aoss,
+	[SLAVE_IPA_CFG] = &qhs_ipa,
+	[SLAVE_IPC_ROUTER_CFG] = &qhs_ipc_router,
+	[SLAVE_TME_CFG] = &qhs_tme_cfg,
+	[SLAVE_APPSS] = &qss_apss,
+	[SLAVE_CNOC_CFG] = &qss_cfg,
+	[SLAVE_DDRSS_CFG] = &qss_ddrss_cfg,
+	[SLAVE_IMEM] = &qxs_imem,
+	[SLAVE_SERVICE_CNOC] = &srvc_cnoc_main,
+	[SLAVE_PCIE_0] = &xs_pcie_0,
+	[SLAVE_PCIE_1] = &xs_pcie_1,
+};
+
+static const struct qcom_icc_desc sm8650_cnoc_main = {
+	.nodes = cnoc_main_nodes,
+	.num_nodes = ARRAY_SIZE(cnoc_main_nodes),
+	.bcms = cnoc_main_bcms,
+	.num_bcms = ARRAY_SIZE(cnoc_main_bcms),
+};
+
+static struct qcom_icc_bcm * const gem_noc_bcms[] = {
+	&bcm_sh0,
+	&bcm_sh1,
+};
+
+static struct qcom_icc_node * const gem_noc_nodes[] = {
+	[MASTER_GPU_TCU] = &alm_gpu_tcu,
+	[MASTER_SYS_TCU] = &alm_sys_tcu,
+	[MASTER_UBWC_P_TCU] = &alm_ubwc_p_tcu,
+	[MASTER_APPSS_PROC] = &chm_apps,
+	[MASTER_GFX3D] = &qnm_gpu,
+	[MASTER_LPASS_GEM_NOC] = &qnm_lpass_gemnoc,
+	[MASTER_MSS_PROC] = &qnm_mdsp,
+	[MASTER_MNOC_HF_MEM_NOC] = &qnm_mnoc_hf,
+	[MASTER_MNOC_SF_MEM_NOC] = &qnm_mnoc_sf,
+	[MASTER_COMPUTE_NOC] = &qnm_nsp_gemnoc,
+	[MASTER_ANOC_PCIE_GEM_NOC] = &qnm_pcie,
+	[MASTER_SNOC_SF_MEM_NOC] = &qnm_snoc_sf,
+	[MASTER_UBWC_P] = &qnm_ubwc_p,
+	[MASTER_GIC] = &xm_gic,
+	[SLAVE_GEM_NOC_CNOC] = &qns_gem_noc_cnoc,
+	[SLAVE_LLCC] = &qns_llcc,
+	[SLAVE_MEM_NOC_PCIE_SNOC] = &qns_pcie,
+};
+
+static const struct qcom_icc_desc sm8650_gem_noc = {
+	.nodes = gem_noc_nodes,
+	.num_nodes = ARRAY_SIZE(gem_noc_nodes),
+	.bcms = gem_noc_bcms,
+	.num_bcms = ARRAY_SIZE(gem_noc_bcms),
+};
+
+static struct qcom_icc_node * const lpass_ag_noc_nodes[] = {
+	[MASTER_LPIAON_NOC] = &qnm_lpiaon_noc,
+	[SLAVE_LPASS_GEM_NOC] = &qns_lpass_ag_noc_gemnoc,
+};
+
+static const struct qcom_icc_desc sm8650_lpass_ag_noc = {
+	.nodes = lpass_ag_noc_nodes,
+	.num_nodes = ARRAY_SIZE(lpass_ag_noc_nodes),
+};
+
+static struct qcom_icc_bcm * const lpass_lpiaon_noc_bcms[] = {
+	&bcm_lp0,
+};
+
+static struct qcom_icc_node * const lpass_lpiaon_noc_nodes[] = {
+	[MASTER_LPASS_LPINOC] = &qnm_lpass_lpinoc,
+	[SLAVE_LPIAON_NOC_LPASS_AG_NOC] = &qns_lpass_aggnoc,
+};
+
+static const struct qcom_icc_desc sm8650_lpass_lpiaon_noc = {
+	.nodes = lpass_lpiaon_noc_nodes,
+	.num_nodes = ARRAY_SIZE(lpass_lpiaon_noc_nodes),
+	.bcms = lpass_lpiaon_noc_bcms,
+	.num_bcms = ARRAY_SIZE(lpass_lpiaon_noc_bcms),
+};
+
+static struct qcom_icc_node * const lpass_lpicx_noc_nodes[] = {
+	[MASTER_LPASS_PROC] = &qxm_lpinoc_dsp_axim,
+	[SLAVE_LPICX_NOC_LPIAON_NOC] = &qns_lpi_aon_noc,
+};
+
+static const struct qcom_icc_desc sm8650_lpass_lpicx_noc = {
+	.nodes = lpass_lpicx_noc_nodes,
+	.num_nodes = ARRAY_SIZE(lpass_lpicx_noc_nodes),
+};
+
+static struct qcom_icc_bcm * const mc_virt_bcms[] = {
+	&bcm_acv,
+	&bcm_mc0,
+};
+
+static struct qcom_icc_node * const mc_virt_nodes[] = {
+	[MASTER_LLCC] = &llcc_mc,
+	[SLAVE_EBI1] = &ebi,
+};
+
+static const struct qcom_icc_desc sm8650_mc_virt = {
+	.nodes = mc_virt_nodes,
+	.num_nodes = ARRAY_SIZE(mc_virt_nodes),
+	.bcms = mc_virt_bcms,
+	.num_bcms = ARRAY_SIZE(mc_virt_bcms),
+};
+
+static struct qcom_icc_bcm * const mmss_noc_bcms[] = {
+	&bcm_mm0,
+	&bcm_mm1,
+};
+
+static struct qcom_icc_node * const mmss_noc_nodes[] = {
+	[MASTER_CAMNOC_HF] = &qnm_camnoc_hf,
+	[MASTER_CAMNOC_ICP] = &qnm_camnoc_icp,
+	[MASTER_CAMNOC_SF] = &qnm_camnoc_sf,
+	[MASTER_MDP] = &qnm_mdp,
+	[MASTER_CDSP_HCP] = &qnm_vapss_hcp,
+	[MASTER_VIDEO] = &qnm_video,
+	[MASTER_VIDEO_CV_PROC] = &qnm_video_cv_cpu,
+	[MASTER_VIDEO_PROC] = &qnm_video_cvp,
+	[MASTER_VIDEO_V_PROC] = &qnm_video_v_cpu,
+	[MASTER_CNOC_MNOC_CFG] = &qsm_mnoc_cfg,
+	[SLAVE_MNOC_HF_MEM_NOC] = &qns_mem_noc_hf,
+	[SLAVE_MNOC_SF_MEM_NOC] = &qns_mem_noc_sf,
+	[SLAVE_SERVICE_MNOC] = &srvc_mnoc,
+};
+
+static const struct qcom_icc_desc sm8650_mmss_noc = {
+	.nodes = mmss_noc_nodes,
+	.num_nodes = ARRAY_SIZE(mmss_noc_nodes),
+	.bcms = mmss_noc_bcms,
+	.num_bcms = ARRAY_SIZE(mmss_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const nsp_noc_bcms[] = {
+	&bcm_co0,
+};
+
+static struct qcom_icc_node * const nsp_noc_nodes[] = {
+	[MASTER_CDSP_PROC] = &qnm_nsp,
+	[SLAVE_CDSP_MEM_NOC] = &qns_nsp_gemnoc,
+};
+
+static const struct qcom_icc_desc sm8650_nsp_noc = {
+	.nodes = nsp_noc_nodes,
+	.num_nodes = ARRAY_SIZE(nsp_noc_nodes),
+	.bcms = nsp_noc_bcms,
+	.num_bcms = ARRAY_SIZE(nsp_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const pcie_anoc_bcms[] = {
+	&bcm_sn4,
+};
+
+static struct qcom_icc_node * const pcie_anoc_nodes[] = {
+	[MASTER_PCIE_ANOC_CFG] = &qsm_pcie_anoc_cfg,
+	[MASTER_PCIE_0] = &xm_pcie3_0,
+	[MASTER_PCIE_1] = &xm_pcie3_1,
+	[SLAVE_ANOC_PCIE_GEM_NOC] = &qns_pcie_mem_noc,
+	[SLAVE_SERVICE_PCIE_ANOC] = &srvc_pcie_aggre_noc,
+};
+
+static const struct qcom_icc_desc sm8650_pcie_anoc = {
+	.nodes = pcie_anoc_nodes,
+	.num_nodes = ARRAY_SIZE(pcie_anoc_nodes),
+	.bcms = pcie_anoc_bcms,
+	.num_bcms = ARRAY_SIZE(pcie_anoc_bcms),
+};
+
+static struct qcom_icc_bcm * const system_noc_bcms[] = {
+	&bcm_sn0,
+	&bcm_sn2,
+	&bcm_sn3,
+};
+
+static struct qcom_icc_node * const system_noc_nodes[] = {
+	[MASTER_A1NOC_SNOC] = &qnm_aggre1_noc,
+	[MASTER_A2NOC_SNOC] = &qnm_aggre2_noc,
+	[SLAVE_SNOC_GEM_NOC_SF] = &qns_gemnoc_sf,
+};
+
+static const struct qcom_icc_desc sm8650_system_noc = {
+	.nodes = system_noc_nodes,
+	.num_nodes = ARRAY_SIZE(system_noc_nodes),
+	.bcms = system_noc_bcms,
+	.num_bcms = ARRAY_SIZE(system_noc_bcms),
+};
+
+static const struct of_device_id qnoc_of_match[] = {
+	{ .compatible = "qcom,sm8650-aggre1-noc", .data = &sm8650_aggre1_noc },
+	{ .compatible = "qcom,sm8650-aggre2-noc", .data = &sm8650_aggre2_noc },
+	{ .compatible = "qcom,sm8650-clk-virt", .data = &sm8650_clk_virt },
+	{ .compatible = "qcom,sm8650-config-noc", .data = &sm8650_config_noc },
+	{ .compatible = "qcom,sm8650-cnoc-main", .data = &sm8650_cnoc_main },
+	{ .compatible = "qcom,sm8650-gem-noc", .data = &sm8650_gem_noc },
+	{ .compatible = "qcom,sm8650-lpass-ag-noc", .data = &sm8650_lpass_ag_noc },
+	{ .compatible = "qcom,sm8650-lpass-lpiaon-noc", .data = &sm8650_lpass_lpiaon_noc },
+	{ .compatible = "qcom,sm8650-lpass-lpicx-noc", .data = &sm8650_lpass_lpicx_noc },
+	{ .compatible = "qcom,sm8650-mc-virt", .data = &sm8650_mc_virt },
+	{ .compatible = "qcom,sm8650-mmss-noc", .data = &sm8650_mmss_noc },
+	{ .compatible = "qcom,sm8650-nsp-noc", .data = &sm8650_nsp_noc },
+	{ .compatible = "qcom,sm8650-pcie-anoc", .data = &sm8650_pcie_anoc },
+	{ .compatible = "qcom,sm8650-system-noc", .data = &sm8650_system_noc },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, qnoc_of_match);
+
+static struct platform_driver qnoc_driver = {
+	.probe = qcom_icc_rpmh_probe,
+	.remove_new = qcom_icc_rpmh_remove,
+	.driver = {
+		.name = "qnoc-sm8650",
+		.of_match_table = qnoc_of_match,
+		.sync_state = icc_sync_state,
+	},
+};
+
+static int __init qnoc_driver_init(void)
+{
+	return platform_driver_register(&qnoc_driver);
+}
+core_initcall(qnoc_driver_init);
+
+static void __exit qnoc_driver_exit(void)
+{
+	platform_driver_unregister(&qnoc_driver);
+}
+module_exit(qnoc_driver_exit);
+
+MODULE_DESCRIPTION("sm8650 NoC driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/interconnect/qcom/sm8650.h b/drivers/interconnect/qcom/sm8650.h
new file mode 100644
index 000000000000..de35c956fe49
--- /dev/null
+++ b/drivers/interconnect/qcom/sm8650.h
@@ -0,0 +1,143 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * SM8650 interconnect IDs
+ *
+ * Copyright (c) 2020-2021, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef __DRIVERS_INTERCONNECT_QCOM_SM8650_H
+#define __DRIVERS_INTERCONNECT_QCOM_SM8650_H
+
+#define SM8650_MASTER_A1NOC_SNOC		0
+#define SM8650_MASTER_A2NOC_SNOC		1
+#define SM8650_MASTER_ANOC_PCIE_GEM_NOC		2
+#define SM8650_MASTER_APPSS_PROC		3
+#define SM8650_MASTER_CAMNOC_HF			4
+#define SM8650_MASTER_CAMNOC_ICP		5
+#define SM8650_MASTER_CAMNOC_SF			6
+#define SM8650_MASTER_CDSP_HCP			7
+#define SM8650_MASTER_CDSP_PROC			8
+#define SM8650_MASTER_CNOC_CFG			9
+#define SM8650_MASTER_CNOC_MNOC_CFG		10
+#define SM8650_MASTER_COMPUTE_NOC		11
+#define SM8650_MASTER_CRYPTO			12
+#define SM8650_MASTER_GEM_NOC_CNOC		13
+#define SM8650_MASTER_GEM_NOC_PCIE_SNOC		14
+#define SM8650_MASTER_GFX3D			15
+#define SM8650_MASTER_GIC			16
+#define SM8650_MASTER_GPU_TCU			17
+#define SM8650_MASTER_IPA			18
+#define SM8650_MASTER_LLCC			19
+#define SM8650_MASTER_LPASS_GEM_NOC		20
+#define SM8650_MASTER_LPASS_LPINOC		21
+#define SM8650_MASTER_LPASS_PROC		22
+#define SM8650_MASTER_LPIAON_NOC		23
+#define SM8650_MASTER_MDP			24
+#define SM8650_MASTER_MNOC_HF_MEM_NOC		25
+#define SM8650_MASTER_MNOC_SF_MEM_NOC		26
+#define SM8650_MASTER_MSS_PROC			27
+#define SM8650_MASTER_PCIE_0			28
+#define SM8650_MASTER_PCIE_1			29
+#define SM8650_MASTER_PCIE_ANOC_CFG		30
+#define SM8650_MASTER_QDSS_BAM			31
+#define SM8650_MASTER_QDSS_ETR			32
+#define SM8650_MASTER_QDSS_ETR_1		33
+#define SM8650_MASTER_QSPI_0			34
+#define SM8650_MASTER_QUP_1			35
+#define SM8650_MASTER_QUP_2			36
+#define SM8650_MASTER_QUP_3			37
+#define SM8650_MASTER_QUP_CORE_0		38
+#define SM8650_MASTER_QUP_CORE_1		39
+#define SM8650_MASTER_QUP_CORE_2		40
+#define SM8650_MASTER_SDCC_2			41
+#define SM8650_MASTER_SDCC_4			42
+#define SM8650_MASTER_SNOC_SF_MEM_NOC		43
+#define SM8650_MASTER_SP			44
+#define SM8650_MASTER_SYS_TCU			45
+#define SM8650_MASTER_UBWC_P			46
+#define SM8650_MASTER_UBWC_P_TCU		47
+#define SM8650_MASTER_UFS_MEM			48
+#define SM8650_MASTER_USB3_0			49
+#define SM8650_MASTER_VIDEO			50
+#define SM8650_MASTER_VIDEO_CV_PROC		51
+#define SM8650_MASTER_VIDEO_PROC		52
+#define SM8650_MASTER_VIDEO_V_PROC		53
+#define SM8650_SLAVE_A1NOC_SNOC			54
+#define SM8650_SLAVE_A2NOC_SNOC			55
+#define SM8650_SLAVE_AHB2PHY_NORTH		56
+#define SM8650_SLAVE_AHB2PHY_SOUTH		57
+#define SM8650_SLAVE_ANOC_PCIE_GEM_NOC		58
+#define SM8650_SLAVE_AOSS			59
+#define SM8650_SLAVE_APPSS			60
+#define SM8650_SLAVE_CAMERA_CFG			61
+#define SM8650_SLAVE_CDSP_MEM_NOC		62
+#define SM8650_SLAVE_CLK_CTL			63
+#define SM8650_SLAVE_CNOC_CFG			64
+#define SM8650_SLAVE_CNOC_MNOC_CFG		65
+#define SM8650_SLAVE_CNOC_MSS			66
+#define SM8650_SLAVE_CPR_HMX			67
+#define SM8650_SLAVE_CPR_NSPCX			68
+#define SM8650_SLAVE_CRYPTO_0_CFG		69
+#define SM8650_SLAVE_CX_RDPM			70
+#define SM8650_SLAVE_DDRSS_CFG			71
+#define SM8650_SLAVE_DISPLAY_CFG		72
+#define SM8650_SLAVE_EBI1			73
+#define SM8650_SLAVE_GEM_NOC_CNOC		74
+#define SM8650_SLAVE_GFX3D_CFG			75
+#define SM8650_SLAVE_I2C			76
+#define SM8650_SLAVE_I3C_IBI0_CFG		77
+#define SM8650_SLAVE_I3C_IBI1_CFG		78
+#define SM8650_SLAVE_IMEM			79
+#define SM8650_SLAVE_IMEM_CFG			80
+#define SM8650_SLAVE_IPA_CFG			81
+#define SM8650_SLAVE_IPC_ROUTER_CFG		82
+#define SM8650_SLAVE_LLCC			83
+#define SM8650_SLAVE_LPASS_GEM_NOC		84
+#define SM8650_SLAVE_LPIAON_NOC_LPASS_AG_NOC	85
+#define SM8650_SLAVE_LPICX_NOC_LPIAON_NOC	86
+#define SM8650_SLAVE_MEM_NOC_PCIE_SNOC		87
+#define SM8650_SLAVE_MNOC_HF_MEM_NOC		88
+#define SM8650_SLAVE_MNOC_SF_MEM_NOC		89
+#define SM8650_SLAVE_MX_2_RDPM			90
+#define SM8650_SLAVE_MX_RDPM			91
+#define SM8650_SLAVE_NSP_QTB_CFG		92
+#define SM8650_SLAVE_PCIE_0			93
+#define SM8650_SLAVE_PCIE_1			94
+#define SM8650_SLAVE_PCIE_0_CFG			95
+#define SM8650_SLAVE_PCIE_1_CFG			96
+#define SM8650_SLAVE_PCIE_ANOC_CFG		97
+#define SM8650_SLAVE_PCIE_RSCC			98
+#define SM8650_SLAVE_PDM			99
+#define SM8650_SLAVE_PRNG			100
+#define SM8650_SLAVE_QDSS_CFG			101
+#define SM8650_SLAVE_QDSS_STM			102
+#define SM8650_SLAVE_QSPI_0			103
+#define SM8650_SLAVE_QUP_1			104
+#define SM8650_SLAVE_QUP_2			105
+#define SM8650_SLAVE_QUP_3			106
+#define SM8650_SLAVE_QUP_CORE_0			107
+#define SM8650_SLAVE_QUP_CORE_1			108
+#define SM8650_SLAVE_QUP_CORE_2			109
+#define SM8650_SLAVE_RBCPR_CX_CFG		110
+#define SM8650_SLAVE_RBCPR_MMCX_CFG		111
+#define SM8650_SLAVE_RBCPR_MXA_CFG		112
+#define SM8650_SLAVE_RBCPR_MXC_CFG		113
+#define SM8650_SLAVE_SDCC_2			114
+#define SM8650_SLAVE_SDCC_4			115
+#define SM8650_SLAVE_SERVICE_CNOC		116
+#define SM8650_SLAVE_SERVICE_CNOC_CFG		117
+#define SM8650_SLAVE_SERVICE_MNOC		118
+#define SM8650_SLAVE_SERVICE_PCIE_ANOC		119
+#define SM8650_SLAVE_SNOC_GEM_NOC_SF		120
+#define SM8650_SLAVE_SPSS_CFG			121
+#define SM8650_SLAVE_TCSR			122
+#define SM8650_SLAVE_TCU			123
+#define SM8650_SLAVE_TLMM			124
+#define SM8650_SLAVE_TME_CFG			125
+#define SM8650_SLAVE_UFS_MEM_CFG		126
+#define SM8650_SLAVE_USB3_0			127
+#define SM8650_SLAVE_VENUS_CFG			128
+#define SM8650_SLAVE_VSENSE_CTRL_CFG		129
+
+#endif
diff --git a/drivers/interconnect/qcom/smd-rpm.c b/drivers/interconnect/qcom/smd-rpm.c
index 16a145a3c914..3816bfb4e2f3 100644
--- a/drivers/interconnect/qcom/smd-rpm.c
+++ b/drivers/interconnect/qcom/smd-rpm.c
@@ -63,11 +63,9 @@ int qcom_icc_rpm_set_bus_rate(const struct rpm_clk_resource *clk, int ctx, u32 r
 }
 EXPORT_SYMBOL_GPL(qcom_icc_rpm_set_bus_rate);
 
-static int qcom_icc_rpm_smd_remove(struct platform_device *pdev)
+static void qcom_icc_rpm_smd_remove(struct platform_device *pdev)
 {
 	icc_smd_rpm = NULL;
-
-	return 0;
 }
 
 static int qcom_icc_rpm_smd_probe(struct platform_device *pdev)
@@ -87,7 +85,7 @@ static struct platform_driver qcom_interconnect_rpm_smd_driver = {
 		.name		= "icc_smd_rpm",
 	},
 	.probe = qcom_icc_rpm_smd_probe,
-	.remove = qcom_icc_rpm_smd_remove,
+	.remove_new = qcom_icc_rpm_smd_remove,
 };
 module_platform_driver(qcom_interconnect_rpm_smd_driver);
 MODULE_AUTHOR("Georgi Djakov <georgi.djakov@linaro.org>");
diff --git a/drivers/interconnect/qcom/x1e80100.c b/drivers/interconnect/qcom/x1e80100.c
new file mode 100644
index 000000000000..cbaf4f9c41be
--- /dev/null
+++ b/drivers/interconnect/qcom/x1e80100.c
@@ -0,0 +1,2329 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ *
+ */
+
+#include <linux/device.h>
+#include <linux/interconnect.h>
+#include <linux/interconnect-provider.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <dt-bindings/interconnect/qcom,x1e80100-rpmh.h>
+
+#include "bcm-voter.h"
+#include "icc-common.h"
+#include "icc-rpmh.h"
+#include "x1e80100.h"
+
+static struct qcom_icc_node qhm_qspi = {
+	.name = "qhm_qspi",
+	.id = X1E80100_MASTER_QSPI_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node qhm_qup1 = {
+	.name = "qhm_qup1",
+	.id = X1E80100_MASTER_QUP_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_sdc4 = {
+	.name = "xm_sdc4",
+	.id = X1E80100_MASTER_SDCC_4,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_ufs_mem = {
+	.name = "xm_ufs_mem",
+	.id = X1E80100_MASTER_UFS_MEM,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node qhm_qup0 = {
+	.name = "qhm_qup0",
+	.id = X1E80100_MASTER_QUP_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qhm_qup2 = {
+	.name = "qhm_qup2",
+	.id = X1E80100_MASTER_QUP_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qxm_crypto = {
+	.name = "qxm_crypto",
+	.id = X1E80100_MASTER_CRYPTO,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qxm_sp = {
+	.name = "qxm_sp",
+	.id = X1E80100_MASTER_SP,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_qdss_etr_0 = {
+	.name = "xm_qdss_etr_0",
+	.id = X1E80100_MASTER_QDSS_ETR,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_qdss_etr_1 = {
+	.name = "xm_qdss_etr_1",
+	.id = X1E80100_MASTER_QDSS_ETR_1,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_sdc2 = {
+	.name = "xm_sdc2",
+	.id = X1E80100_MASTER_SDCC_2,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node ddr_perf_mode_master = {
+	.name = "ddr_perf_mode_master",
+	.id = X1E80100_MASTER_DDR_PERF_MODE,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_DDR_PERF_MODE },
+};
+
+static struct qcom_icc_node qup0_core_master = {
+	.name = "qup0_core_master",
+	.id = X1E80100_MASTER_QUP_CORE_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_QUP_CORE_0 },
+};
+
+static struct qcom_icc_node qup1_core_master = {
+	.name = "qup1_core_master",
+	.id = X1E80100_MASTER_QUP_CORE_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_QUP_CORE_1 },
+};
+
+static struct qcom_icc_node qup2_core_master = {
+	.name = "qup2_core_master",
+	.id = X1E80100_MASTER_QUP_CORE_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_QUP_CORE_2 },
+};
+
+static struct qcom_icc_node qsm_cfg = {
+	.name = "qsm_cfg",
+	.id = X1E80100_MASTER_CNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 47,
+	.links = { X1E80100_SLAVE_AHB2PHY_SOUTH, X1E80100_SLAVE_AHB2PHY_NORTH,
+		   X1E80100_SLAVE_AHB2PHY_2, X1E80100_SLAVE_AV1_ENC_CFG,
+		   X1E80100_SLAVE_CAMERA_CFG, X1E80100_SLAVE_CLK_CTL,
+		   X1E80100_SLAVE_CRYPTO_0_CFG, X1E80100_SLAVE_DISPLAY_CFG,
+		   X1E80100_SLAVE_GFX3D_CFG, X1E80100_SLAVE_IMEM_CFG,
+		   X1E80100_SLAVE_IPC_ROUTER_CFG, X1E80100_SLAVE_PCIE_0_CFG,
+		   X1E80100_SLAVE_PCIE_1_CFG, X1E80100_SLAVE_PCIE_2_CFG,
+		   X1E80100_SLAVE_PCIE_3_CFG, X1E80100_SLAVE_PCIE_4_CFG,
+		   X1E80100_SLAVE_PCIE_5_CFG, X1E80100_SLAVE_PCIE_6A_CFG,
+		   X1E80100_SLAVE_PCIE_6B_CFG, X1E80100_SLAVE_PCIE_RSC_CFG,
+		   X1E80100_SLAVE_PDM, X1E80100_SLAVE_PRNG,
+		   X1E80100_SLAVE_QDSS_CFG, X1E80100_SLAVE_QSPI_0,
+		   X1E80100_SLAVE_QUP_0, X1E80100_SLAVE_QUP_1,
+		   X1E80100_SLAVE_QUP_2, X1E80100_SLAVE_SDCC_2,
+		   X1E80100_SLAVE_SDCC_4, X1E80100_SLAVE_SMMUV3_CFG,
+		   X1E80100_SLAVE_TCSR, X1E80100_SLAVE_TLMM,
+		   X1E80100_SLAVE_UFS_MEM_CFG, X1E80100_SLAVE_USB2,
+		   X1E80100_SLAVE_USB3_0, X1E80100_SLAVE_USB3_1,
+		   X1E80100_SLAVE_USB3_2, X1E80100_SLAVE_USB3_MP,
+		   X1E80100_SLAVE_USB4_0, X1E80100_SLAVE_USB4_1,
+		   X1E80100_SLAVE_USB4_2, X1E80100_SLAVE_VENUS_CFG,
+		   X1E80100_SLAVE_LPASS_QTB_CFG, X1E80100_SLAVE_CNOC_MNOC_CFG,
+		   X1E80100_SLAVE_NSP_QTB_CFG, X1E80100_SLAVE_QDSS_STM,
+		   X1E80100_SLAVE_TCU },
+};
+
+static struct qcom_icc_node qnm_gemnoc_cnoc = {
+	.name = "qnm_gemnoc_cnoc",
+	.id = X1E80100_MASTER_GEM_NOC_CNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 6,
+	.links = { X1E80100_SLAVE_AOSS, X1E80100_SLAVE_TME_CFG,
+		   X1E80100_SLAVE_APPSS, X1E80100_SLAVE_CNOC_CFG,
+		   X1E80100_SLAVE_BOOT_IMEM, X1E80100_SLAVE_IMEM },
+};
+
+static struct qcom_icc_node qnm_gemnoc_pcie = {
+	.name = "qnm_gemnoc_pcie",
+	.id = X1E80100_MASTER_GEM_NOC_PCIE_SNOC,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 8,
+	.links = { X1E80100_SLAVE_PCIE_0, X1E80100_SLAVE_PCIE_1,
+		   X1E80100_SLAVE_PCIE_2, X1E80100_SLAVE_PCIE_3,
+		   X1E80100_SLAVE_PCIE_4, X1E80100_SLAVE_PCIE_5,
+		   X1E80100_SLAVE_PCIE_6A, X1E80100_SLAVE_PCIE_6B },
+};
+
+static struct qcom_icc_node alm_gpu_tcu = {
+	.name = "alm_gpu_tcu",
+	.id = X1E80100_MASTER_GPU_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 2,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node alm_pcie_tcu = {
+	.name = "alm_pcie_tcu",
+	.id = X1E80100_MASTER_PCIE_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 2,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node alm_sys_tcu = {
+	.name = "alm_sys_tcu",
+	.id = X1E80100_MASTER_SYS_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 2,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node chm_apps = {
+	.name = "chm_apps",
+	.id = X1E80100_MASTER_APPSS_PROC,
+	.channels = 6,
+	.buswidth = 32,
+	.num_links = 3,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC,
+		   X1E80100_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_gpu = {
+	.name = "qnm_gpu",
+	.id = X1E80100_MASTER_GFX3D,
+	.channels = 4,
+	.buswidth = 32,
+	.num_links = 2,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_lpass = {
+	.name = "qnm_lpass",
+	.id = X1E80100_MASTER_LPASS_GEM_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 3,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC,
+		   X1E80100_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_mnoc_hf = {
+	.name = "qnm_mnoc_hf",
+	.id = X1E80100_MASTER_MNOC_HF_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 2,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_mnoc_sf = {
+	.name = "qnm_mnoc_sf",
+	.id = X1E80100_MASTER_MNOC_SF_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 2,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_nsp_noc = {
+	.name = "qnm_nsp_noc",
+	.id = X1E80100_MASTER_COMPUTE_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 3,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC,
+		   X1E80100_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_pcie = {
+	.name = "qnm_pcie",
+	.id = X1E80100_MASTER_ANOC_PCIE_GEM_NOC,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 2,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_snoc_sf = {
+	.name = "qnm_snoc_sf",
+	.id = X1E80100_MASTER_SNOC_SF_MEM_NOC,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 3,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC,
+		   X1E80100_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node xm_gic = {
+	.name = "xm_gic",
+	.id = X1E80100_MASTER_GIC2,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_lpiaon_noc = {
+	.name = "qnm_lpiaon_noc",
+	.id = X1E80100_MASTER_LPIAON_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_LPASS_GEM_NOC },
+};
+
+static struct qcom_icc_node qnm_lpass_lpinoc = {
+	.name = "qnm_lpass_lpinoc",
+	.id = X1E80100_MASTER_LPASS_LPINOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_LPIAON_NOC_LPASS_AG_NOC },
+};
+
+static struct qcom_icc_node qxm_lpinoc_dsp_axim = {
+	.name = "qxm_lpinoc_dsp_axim",
+	.id = X1E80100_MASTER_LPASS_PROC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_LPICX_NOC_LPIAON_NOC },
+};
+
+static struct qcom_icc_node llcc_mc = {
+	.name = "llcc_mc",
+	.id = X1E80100_MASTER_LLCC,
+	.channels = 8,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_EBI1 },
+};
+
+static struct qcom_icc_node qnm_av1_enc = {
+	.name = "qnm_av1_enc",
+	.id = X1E80100_MASTER_AV1_ENC,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_camnoc_hf = {
+	.name = "qnm_camnoc_hf",
+	.id = X1E80100_MASTER_CAMNOC_HF,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_MNOC_HF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_camnoc_icp = {
+	.name = "qnm_camnoc_icp",
+	.id = X1E80100_MASTER_CAMNOC_ICP,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_camnoc_sf = {
+	.name = "qnm_camnoc_sf",
+	.id = X1E80100_MASTER_CAMNOC_SF,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_eva = {
+	.name = "qnm_eva",
+	.id = X1E80100_MASTER_EVA,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_mdp = {
+	.name = "qnm_mdp",
+	.id = X1E80100_MASTER_MDP,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_MNOC_HF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_video = {
+	.name = "qnm_video",
+	.id = X1E80100_MASTER_VIDEO,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_video_cv_cpu = {
+	.name = "qnm_video_cv_cpu",
+	.id = X1E80100_MASTER_VIDEO_CV_PROC,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_video_v_cpu = {
+	.name = "qnm_video_v_cpu",
+	.id = X1E80100_MASTER_VIDEO_V_PROC,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qsm_mnoc_cfg = {
+	.name = "qsm_mnoc_cfg",
+	.id = X1E80100_MASTER_CNOC_MNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_SERVICE_MNOC },
+};
+
+static struct qcom_icc_node qxm_nsp = {
+	.name = "qxm_nsp",
+	.id = X1E80100_MASTER_CDSP_PROC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_CDSP_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_pcie_north_gem_noc = {
+	.name = "qnm_pcie_north_gem_noc",
+	.id = X1E80100_MASTER_PCIE_NORTH,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_ANOC_PCIE_GEM_NOC },
+};
+
+static struct qcom_icc_node qnm_pcie_south_gem_noc = {
+	.name = "qnm_pcie_south_gem_noc",
+	.id = X1E80100_MASTER_PCIE_SOUTH,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_ANOC_PCIE_GEM_NOC },
+};
+
+static struct qcom_icc_node xm_pcie_3 = {
+	.name = "xm_pcie_3",
+	.id = X1E80100_MASTER_PCIE_3,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_NORTH },
+};
+
+static struct qcom_icc_node xm_pcie_4 = {
+	.name = "xm_pcie_4",
+	.id = X1E80100_MASTER_PCIE_4,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_NORTH },
+};
+
+static struct qcom_icc_node xm_pcie_5 = {
+	.name = "xm_pcie_5",
+	.id = X1E80100_MASTER_PCIE_5,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_NORTH },
+};
+
+static struct qcom_icc_node xm_pcie_0 = {
+	.name = "xm_pcie_0",
+	.id = X1E80100_MASTER_PCIE_0,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_SOUTH },
+};
+
+static struct qcom_icc_node xm_pcie_1 = {
+	.name = "xm_pcie_1",
+	.id = X1E80100_MASTER_PCIE_1,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_SOUTH },
+};
+
+static struct qcom_icc_node xm_pcie_2 = {
+	.name = "xm_pcie_2",
+	.id = X1E80100_MASTER_PCIE_2,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_SOUTH },
+};
+
+static struct qcom_icc_node xm_pcie_6a = {
+	.name = "xm_pcie_6a",
+	.id = X1E80100_MASTER_PCIE_6A,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_SOUTH },
+};
+
+static struct qcom_icc_node xm_pcie_6b = {
+	.name = "xm_pcie_6b",
+	.id = X1E80100_MASTER_PCIE_6B,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_SOUTH },
+};
+
+static struct qcom_icc_node qnm_aggre1_noc = {
+	.name = "qnm_aggre1_noc",
+	.id = X1E80100_MASTER_A1NOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_SNOC_GEM_NOC_SF },
+};
+
+static struct qcom_icc_node qnm_aggre2_noc = {
+	.name = "qnm_aggre2_noc",
+	.id = X1E80100_MASTER_A2NOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_SNOC_GEM_NOC_SF },
+};
+
+static struct qcom_icc_node qnm_gic = {
+	.name = "qnm_gic",
+	.id = X1E80100_MASTER_GIC1,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_SNOC_GEM_NOC_SF },
+};
+
+static struct qcom_icc_node qnm_usb_anoc = {
+	.name = "qnm_usb_anoc",
+	.id = X1E80100_MASTER_USB_NOC_SNOC,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_SNOC_GEM_NOC_SF },
+};
+
+static struct qcom_icc_node qnm_aggre_usb_north_snoc = {
+	.name = "qnm_aggre_usb_north_snoc",
+	.id = X1E80100_MASTER_AGGRE_USB_NORTH,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_USB_NOC_SNOC },
+};
+
+static struct qcom_icc_node qnm_aggre_usb_south_snoc = {
+	.name = "qnm_aggre_usb_south_snoc",
+	.id = X1E80100_MASTER_AGGRE_USB_SOUTH,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_USB_NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_usb2_0 = {
+	.name = "xm_usb2_0",
+	.id = X1E80100_MASTER_USB2,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_AGGRE_USB_NORTH },
+};
+
+static struct qcom_icc_node xm_usb3_mp = {
+	.name = "xm_usb3_mp",
+	.id = X1E80100_MASTER_USB3_MP,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_AGGRE_USB_NORTH },
+};
+
+static struct qcom_icc_node xm_usb3_0 = {
+	.name = "xm_usb3_0",
+	.id = X1E80100_MASTER_USB3_0,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_AGGRE_USB_SOUTH },
+};
+
+static struct qcom_icc_node xm_usb3_1 = {
+	.name = "xm_usb3_1",
+	.id = X1E80100_MASTER_USB3_1,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_AGGRE_USB_SOUTH },
+};
+
+static struct qcom_icc_node xm_usb3_2 = {
+	.name = "xm_usb3_2",
+	.id = X1E80100_MASTER_USB3_2,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_AGGRE_USB_SOUTH },
+};
+
+static struct qcom_icc_node xm_usb4_0 = {
+	.name = "xm_usb4_0",
+	.id = X1E80100_MASTER_USB4_0,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_AGGRE_USB_SOUTH },
+};
+
+static struct qcom_icc_node xm_usb4_1 = {
+	.name = "xm_usb4_1",
+	.id = X1E80100_MASTER_USB4_1,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_AGGRE_USB_SOUTH },
+};
+
+static struct qcom_icc_node xm_usb4_2 = {
+	.name = "xm_usb4_2",
+	.id = X1E80100_MASTER_USB4_2,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_AGGRE_USB_SOUTH },
+};
+
+static struct qcom_icc_node qnm_mnoc_hf_disp = {
+	.name = "qnm_mnoc_hf_disp",
+	.id = X1E80100_MASTER_MNOC_HF_MEM_NOC_DISP,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_LLCC_DISP },
+};
+
+static struct qcom_icc_node qnm_pcie_disp = {
+	.name = "qnm_pcie_disp",
+	.id = X1E80100_MASTER_ANOC_PCIE_GEM_NOC_DISP,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_LLCC_DISP },
+};
+
+static struct qcom_icc_node llcc_mc_disp = {
+	.name = "llcc_mc_disp",
+	.id = X1E80100_MASTER_LLCC_DISP,
+	.channels = 8,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_EBI1_DISP },
+};
+
+static struct qcom_icc_node qnm_mdp_disp = {
+	.name = "qnm_mdp_disp",
+	.id = X1E80100_MASTER_MDP_DISP,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_MNOC_HF_MEM_NOC_DISP },
+};
+
+static struct qcom_icc_node qnm_pcie_pcie = {
+	.name = "qnm_pcie_pcie",
+	.id = X1E80100_MASTER_ANOC_PCIE_GEM_NOC_PCIE,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_LLCC_PCIE },
+};
+
+static struct qcom_icc_node llcc_mc_pcie = {
+	.name = "llcc_mc_pcie",
+	.id = X1E80100_MASTER_LLCC_PCIE,
+	.channels = 8,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_EBI1_PCIE },
+};
+
+static struct qcom_icc_node qnm_pcie_north_gem_noc_pcie = {
+	.name = "qnm_pcie_north_gem_noc_pcie",
+	.id = X1E80100_MASTER_PCIE_NORTH_PCIE,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_ANOC_PCIE_GEM_NOC_PCIE },
+};
+
+static struct qcom_icc_node qnm_pcie_south_gem_noc_pcie = {
+	.name = "qnm_pcie_south_gem_noc_pcie",
+	.id = X1E80100_MASTER_PCIE_SOUTH_PCIE,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_ANOC_PCIE_GEM_NOC_PCIE },
+};
+
+static struct qcom_icc_node xm_pcie_3_pcie = {
+	.name = "xm_pcie_3_pcie",
+	.id = X1E80100_MASTER_PCIE_3_PCIE,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_NORTH_PCIE },
+};
+
+static struct qcom_icc_node xm_pcie_4_pcie = {
+	.name = "xm_pcie_4_pcie",
+	.id = X1E80100_MASTER_PCIE_4_PCIE,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_NORTH_PCIE },
+};
+
+static struct qcom_icc_node xm_pcie_5_pcie = {
+	.name = "xm_pcie_5_pcie",
+	.id = X1E80100_MASTER_PCIE_5_PCIE,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_NORTH_PCIE },
+};
+
+static struct qcom_icc_node xm_pcie_0_pcie = {
+	.name = "xm_pcie_0_pcie",
+	.id = X1E80100_MASTER_PCIE_0_PCIE,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_SOUTH_PCIE },
+};
+
+static struct qcom_icc_node xm_pcie_1_pcie = {
+	.name = "xm_pcie_1_pcie",
+	.id = X1E80100_MASTER_PCIE_1_PCIE,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_SOUTH_PCIE },
+};
+
+static struct qcom_icc_node xm_pcie_2_pcie = {
+	.name = "xm_pcie_2_pcie",
+	.id = X1E80100_MASTER_PCIE_2_PCIE,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_SOUTH_PCIE },
+};
+
+static struct qcom_icc_node xm_pcie_6a_pcie = {
+	.name = "xm_pcie_6a_pcie",
+	.id = X1E80100_MASTER_PCIE_6A_PCIE,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_SOUTH_PCIE },
+};
+
+static struct qcom_icc_node xm_pcie_6b_pcie = {
+	.name = "xm_pcie_6b_pcie",
+	.id = X1E80100_MASTER_PCIE_6B_PCIE,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_SOUTH_PCIE },
+};
+
+static struct qcom_icc_node qns_a1noc_snoc = {
+	.name = "qns_a1noc_snoc",
+	.id = X1E80100_SLAVE_A1NOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node qns_a2noc_snoc = {
+	.name = "qns_a2noc_snoc",
+	.id = X1E80100_SLAVE_A2NOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node ddr_perf_mode_slave = {
+	.name = "ddr_perf_mode_slave",
+	.id = X1E80100_SLAVE_DDR_PERF_MODE,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qup0_core_slave = {
+	.name = "qup0_core_slave",
+	.id = X1E80100_SLAVE_QUP_CORE_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qup1_core_slave = {
+	.name = "qup1_core_slave",
+	.id = X1E80100_SLAVE_QUP_CORE_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qup2_core_slave = {
+	.name = "qup2_core_slave",
+	.id = X1E80100_SLAVE_QUP_CORE_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ahb2phy0 = {
+	.name = "qhs_ahb2phy0",
+	.id = X1E80100_SLAVE_AHB2PHY_SOUTH,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ahb2phy1 = {
+	.name = "qhs_ahb2phy1",
+	.id = X1E80100_SLAVE_AHB2PHY_NORTH,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ahb2phy2 = {
+	.name = "qhs_ahb2phy2",
+	.id = X1E80100_SLAVE_AHB2PHY_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_av1_enc_cfg = {
+	.name = "qhs_av1_enc_cfg",
+	.id = X1E80100_SLAVE_AV1_ENC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_camera_cfg = {
+	.name = "qhs_camera_cfg",
+	.id = X1E80100_SLAVE_CAMERA_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_clk_ctl = {
+	.name = "qhs_clk_ctl",
+	.id = X1E80100_SLAVE_CLK_CTL,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_crypto0_cfg = {
+	.name = "qhs_crypto0_cfg",
+	.id = X1E80100_SLAVE_CRYPTO_0_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_display_cfg = {
+	.name = "qhs_display_cfg",
+	.id = X1E80100_SLAVE_DISPLAY_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_gpuss_cfg = {
+	.name = "qhs_gpuss_cfg",
+	.id = X1E80100_SLAVE_GFX3D_CFG,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_imem_cfg = {
+	.name = "qhs_imem_cfg",
+	.id = X1E80100_SLAVE_IMEM_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ipc_router = {
+	.name = "qhs_ipc_router",
+	.id = X1E80100_SLAVE_IPC_ROUTER_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie0_cfg = {
+	.name = "qhs_pcie0_cfg",
+	.id = X1E80100_SLAVE_PCIE_0_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie1_cfg = {
+	.name = "qhs_pcie1_cfg",
+	.id = X1E80100_SLAVE_PCIE_1_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie2_cfg = {
+	.name = "qhs_pcie2_cfg",
+	.id = X1E80100_SLAVE_PCIE_2_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie3_cfg = {
+	.name = "qhs_pcie3_cfg",
+	.id = X1E80100_SLAVE_PCIE_3_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie4_cfg = {
+	.name = "qhs_pcie4_cfg",
+	.id = X1E80100_SLAVE_PCIE_4_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie5_cfg = {
+	.name = "qhs_pcie5_cfg",
+	.id = X1E80100_SLAVE_PCIE_5_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie6a_cfg = {
+	.name = "qhs_pcie6a_cfg",
+	.id = X1E80100_SLAVE_PCIE_6A_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie6b_cfg = {
+	.name = "qhs_pcie6b_cfg",
+	.id = X1E80100_SLAVE_PCIE_6B_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie_rsc_cfg = {
+	.name = "qhs_pcie_rsc_cfg",
+	.id = X1E80100_SLAVE_PCIE_RSC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pdm = {
+	.name = "qhs_pdm",
+	.id = X1E80100_SLAVE_PDM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_prng = {
+	.name = "qhs_prng",
+	.id = X1E80100_SLAVE_PRNG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qdss_cfg = {
+	.name = "qhs_qdss_cfg",
+	.id = X1E80100_SLAVE_QDSS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qspi = {
+	.name = "qhs_qspi",
+	.id = X1E80100_SLAVE_QSPI_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qup0 = {
+	.name = "qhs_qup0",
+	.id = X1E80100_SLAVE_QUP_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qup1 = {
+	.name = "qhs_qup1",
+	.id = X1E80100_SLAVE_QUP_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qup2 = {
+	.name = "qhs_qup2",
+	.id = X1E80100_SLAVE_QUP_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_sdc2 = {
+	.name = "qhs_sdc2",
+	.id = X1E80100_SLAVE_SDCC_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_sdc4 = {
+	.name = "qhs_sdc4",
+	.id = X1E80100_SLAVE_SDCC_4,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_smmuv3_cfg = {
+	.name = "qhs_smmuv3_cfg",
+	.id = X1E80100_SLAVE_SMMUV3_CFG,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_tcsr = {
+	.name = "qhs_tcsr",
+	.id = X1E80100_SLAVE_TCSR,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_tlmm = {
+	.name = "qhs_tlmm",
+	.id = X1E80100_SLAVE_TLMM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ufs_mem_cfg = {
+	.name = "qhs_ufs_mem_cfg",
+	.id = X1E80100_SLAVE_UFS_MEM_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_usb2_0_cfg = {
+	.name = "qhs_usb2_0_cfg",
+	.id = X1E80100_SLAVE_USB2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_usb3_0_cfg = {
+	.name = "qhs_usb3_0_cfg",
+	.id = X1E80100_SLAVE_USB3_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_usb3_1_cfg = {
+	.name = "qhs_usb3_1_cfg",
+	.id = X1E80100_SLAVE_USB3_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_usb3_2_cfg = {
+	.name = "qhs_usb3_2_cfg",
+	.id = X1E80100_SLAVE_USB3_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_usb3_mp_cfg = {
+	.name = "qhs_usb3_mp_cfg",
+	.id = X1E80100_SLAVE_USB3_MP,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_usb4_0_cfg = {
+	.name = "qhs_usb4_0_cfg",
+	.id = X1E80100_SLAVE_USB4_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_usb4_1_cfg = {
+	.name = "qhs_usb4_1_cfg",
+	.id = X1E80100_SLAVE_USB4_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_usb4_2_cfg = {
+	.name = "qhs_usb4_2_cfg",
+	.id = X1E80100_SLAVE_USB4_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_venus_cfg = {
+	.name = "qhs_venus_cfg",
+	.id = X1E80100_SLAVE_VENUS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qss_lpass_qtb_cfg = {
+	.name = "qss_lpass_qtb_cfg",
+	.id = X1E80100_SLAVE_LPASS_QTB_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qss_mnoc_cfg = {
+	.name = "qss_mnoc_cfg",
+	.id = X1E80100_SLAVE_CNOC_MNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_CNOC_MNOC_CFG },
+};
+
+static struct qcom_icc_node qss_nsp_qtb_cfg = {
+	.name = "qss_nsp_qtb_cfg",
+	.id = X1E80100_SLAVE_NSP_QTB_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_qdss_stm = {
+	.name = "xs_qdss_stm",
+	.id = X1E80100_SLAVE_QDSS_STM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_sys_tcu_cfg = {
+	.name = "xs_sys_tcu_cfg",
+	.id = X1E80100_SLAVE_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_aoss = {
+	.name = "qhs_aoss",
+	.id = X1E80100_SLAVE_AOSS,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_tme_cfg = {
+	.name = "qhs_tme_cfg",
+	.id = X1E80100_SLAVE_TME_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_apss = {
+	.name = "qns_apss",
+	.id = X1E80100_SLAVE_APPSS,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qss_cfg = {
+	.name = "qss_cfg",
+	.id = X1E80100_SLAVE_CNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_CNOC_CFG },
+};
+
+static struct qcom_icc_node qxs_boot_imem = {
+	.name = "qxs_boot_imem",
+	.id = X1E80100_SLAVE_BOOT_IMEM,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qxs_imem = {
+	.name = "qxs_imem",
+	.id = X1E80100_SLAVE_IMEM,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie_0 = {
+	.name = "xs_pcie_0",
+	.id = X1E80100_SLAVE_PCIE_0,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie_1 = {
+	.name = "xs_pcie_1",
+	.id = X1E80100_SLAVE_PCIE_1,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie_2 = {
+	.name = "xs_pcie_2",
+	.id = X1E80100_SLAVE_PCIE_2,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie_3 = {
+	.name = "xs_pcie_3",
+	.id = X1E80100_SLAVE_PCIE_3,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie_4 = {
+	.name = "xs_pcie_4",
+	.id = X1E80100_SLAVE_PCIE_4,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie_5 = {
+	.name = "xs_pcie_5",
+	.id = X1E80100_SLAVE_PCIE_5,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie_6a = {
+	.name = "xs_pcie_6a",
+	.id = X1E80100_SLAVE_PCIE_6A,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie_6b = {
+	.name = "xs_pcie_6b",
+	.id = X1E80100_SLAVE_PCIE_6B,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_gem_noc_cnoc = {
+	.name = "qns_gem_noc_cnoc",
+	.id = X1E80100_SLAVE_GEM_NOC_CNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_GEM_NOC_CNOC },
+};
+
+static struct qcom_icc_node qns_llcc = {
+	.name = "qns_llcc",
+	.id = X1E80100_SLAVE_LLCC,
+	.channels = 8,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_LLCC },
+};
+
+static struct qcom_icc_node qns_pcie = {
+	.name = "qns_pcie",
+	.id = X1E80100_SLAVE_MEM_NOC_PCIE_SNOC,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_GEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qns_lpass_ag_noc_gemnoc = {
+	.name = "qns_lpass_ag_noc_gemnoc",
+	.id = X1E80100_SLAVE_LPASS_GEM_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_LPASS_GEM_NOC },
+};
+
+static struct qcom_icc_node qns_lpass_aggnoc = {
+	.name = "qns_lpass_aggnoc",
+	.id = X1E80100_SLAVE_LPIAON_NOC_LPASS_AG_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_LPIAON_NOC },
+};
+
+static struct qcom_icc_node qns_lpi_aon_noc = {
+	.name = "qns_lpi_aon_noc",
+	.id = X1E80100_SLAVE_LPICX_NOC_LPIAON_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_LPASS_LPINOC },
+};
+
+static struct qcom_icc_node ebi = {
+	.name = "ebi",
+	.id = X1E80100_SLAVE_EBI1,
+	.channels = 8,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_mem_noc_hf = {
+	.name = "qns_mem_noc_hf",
+	.id = X1E80100_SLAVE_MNOC_HF_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_MNOC_HF_MEM_NOC },
+};
+
+static struct qcom_icc_node qns_mem_noc_sf = {
+	.name = "qns_mem_noc_sf",
+	.id = X1E80100_SLAVE_MNOC_SF_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node srvc_mnoc = {
+	.name = "srvc_mnoc",
+	.id = X1E80100_SLAVE_SERVICE_MNOC,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_nsp_gemnoc = {
+	.name = "qns_nsp_gemnoc",
+	.id = X1E80100_SLAVE_CDSP_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_COMPUTE_NOC },
+};
+
+static struct qcom_icc_node qns_pcie_mem_noc = {
+	.name = "qns_pcie_mem_noc",
+	.id = X1E80100_SLAVE_ANOC_PCIE_GEM_NOC,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_ANOC_PCIE_GEM_NOC },
+};
+
+static struct qcom_icc_node qns_pcie_north_gem_noc = {
+	.name = "qns_pcie_north_gem_noc",
+	.id = X1E80100_SLAVE_PCIE_NORTH,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_PCIE_NORTH },
+};
+
+static struct qcom_icc_node qns_pcie_south_gem_noc = {
+	.name = "qns_pcie_south_gem_noc",
+	.id = X1E80100_SLAVE_PCIE_SOUTH,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_PCIE_SOUTH },
+};
+
+static struct qcom_icc_node qns_gemnoc_sf = {
+	.name = "qns_gemnoc_sf",
+	.id = X1E80100_SLAVE_SNOC_GEM_NOC_SF,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_SNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qns_aggre_usb_snoc = {
+	.name = "qns_aggre_usb_snoc",
+	.id = X1E80100_SLAVE_USB_NOC_SNOC,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_USB_NOC_SNOC },
+};
+
+static struct qcom_icc_node qns_aggre_usb_north_snoc = {
+	.name = "qns_aggre_usb_north_snoc",
+	.id = X1E80100_SLAVE_AGGRE_USB_NORTH,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_AGGRE_USB_NORTH },
+};
+
+static struct qcom_icc_node qns_aggre_usb_south_snoc = {
+	.name = "qns_aggre_usb_south_snoc",
+	.id = X1E80100_SLAVE_AGGRE_USB_SOUTH,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_AGGRE_USB_SOUTH },
+};
+
+static struct qcom_icc_node qns_llcc_disp = {
+	.name = "qns_llcc_disp",
+	.id = X1E80100_SLAVE_LLCC_DISP,
+	.channels = 8,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_LLCC_DISP },
+};
+
+static struct qcom_icc_node ebi_disp = {
+	.name = "ebi_disp",
+	.id = X1E80100_SLAVE_EBI1_DISP,
+	.channels = 8,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_mem_noc_hf_disp = {
+	.name = "qns_mem_noc_hf_disp",
+	.id = X1E80100_SLAVE_MNOC_HF_MEM_NOC_DISP,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_MNOC_HF_MEM_NOC_DISP },
+};
+
+static struct qcom_icc_node qns_llcc_pcie = {
+	.name = "qns_llcc_pcie",
+	.id = X1E80100_SLAVE_LLCC_PCIE,
+	.channels = 8,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_LLCC_PCIE },
+};
+
+static struct qcom_icc_node ebi_pcie = {
+	.name = "ebi_pcie",
+	.id = X1E80100_SLAVE_EBI1_PCIE,
+	.channels = 8,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_pcie_mem_noc_pcie = {
+	.name = "qns_pcie_mem_noc_pcie",
+	.id = X1E80100_SLAVE_ANOC_PCIE_GEM_NOC_PCIE,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_ANOC_PCIE_GEM_NOC_PCIE },
+};
+
+static struct qcom_icc_node qns_pcie_north_gem_noc_pcie = {
+	.name = "qns_pcie_north_gem_noc_pcie",
+	.id = X1E80100_SLAVE_PCIE_NORTH_PCIE,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_PCIE_NORTH_PCIE },
+};
+
+static struct qcom_icc_node qns_pcie_south_gem_noc_pcie = {
+	.name = "qns_pcie_south_gem_noc_pcie",
+	.id = X1E80100_SLAVE_PCIE_SOUTH_PCIE,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_PCIE_SOUTH_PCIE },
+};
+
+static struct qcom_icc_bcm bcm_acv = {
+	.name = "ACV",
+	.enable_mask = BIT(3),
+	.num_nodes = 1,
+	.nodes = { &ebi },
+};
+
+static struct qcom_icc_bcm bcm_acv_perf = {
+	.name = "ACV_PERF",
+	.num_nodes = 1,
+	.nodes = { &ddr_perf_mode_slave },
+};
+
+static struct qcom_icc_bcm bcm_ce0 = {
+	.name = "CE0",
+	.num_nodes = 1,
+	.nodes = { &qxm_crypto },
+};
+
+static struct qcom_icc_bcm bcm_cn0 = {
+	.name = "CN0",
+	.keepalive = true,
+	.num_nodes = 63,
+	.nodes = { &qsm_cfg, &qhs_ahb2phy0,
+		   &qhs_ahb2phy1, &qhs_ahb2phy2,
+		   &qhs_av1_enc_cfg, &qhs_camera_cfg,
+		   &qhs_clk_ctl, &qhs_crypto0_cfg,
+		   &qhs_gpuss_cfg, &qhs_imem_cfg,
+		   &qhs_ipc_router, &qhs_pcie0_cfg,
+		   &qhs_pcie1_cfg, &qhs_pcie2_cfg,
+		   &qhs_pcie3_cfg, &qhs_pcie4_cfg,
+		   &qhs_pcie5_cfg, &qhs_pcie6a_cfg,
+		   &qhs_pcie6b_cfg, &qhs_pcie_rsc_cfg,
+		   &qhs_pdm, &qhs_prng,
+		   &qhs_qdss_cfg, &qhs_qspi,
+		   &qhs_qup0, &qhs_qup1,
+		   &qhs_qup2, &qhs_sdc2,
+		   &qhs_sdc4, &qhs_smmuv3_cfg,
+		   &qhs_tcsr, &qhs_tlmm,
+		   &qhs_ufs_mem_cfg, &qhs_usb2_0_cfg,
+		   &qhs_usb3_0_cfg, &qhs_usb3_1_cfg,
+		   &qhs_usb3_2_cfg, &qhs_usb3_mp_cfg,
+		   &qhs_usb4_0_cfg, &qhs_usb4_1_cfg,
+		   &qhs_usb4_2_cfg, &qhs_venus_cfg,
+		   &qss_lpass_qtb_cfg, &qss_mnoc_cfg,
+		   &qss_nsp_qtb_cfg, &xs_qdss_stm,
+		   &xs_sys_tcu_cfg, &qnm_gemnoc_cnoc,
+		   &qnm_gemnoc_pcie, &qhs_aoss,
+		   &qhs_tme_cfg, &qns_apss,
+		   &qss_cfg, &qxs_boot_imem,
+		   &qxs_imem, &xs_pcie_0,
+		   &xs_pcie_1, &xs_pcie_2,
+		   &xs_pcie_3, &xs_pcie_4,
+		   &xs_pcie_5, &xs_pcie_6a,
+		   &xs_pcie_6b },
+};
+
+static struct qcom_icc_bcm bcm_cn1 = {
+	.name = "CN1",
+	.num_nodes = 1,
+	.nodes = { &qhs_display_cfg },
+};
+
+static struct qcom_icc_bcm bcm_co0 = {
+	.name = "CO0",
+	.num_nodes = 2,
+	.nodes = { &qxm_nsp, &qns_nsp_gemnoc },
+};
+
+static struct qcom_icc_bcm bcm_lp0 = {
+	.name = "LP0",
+	.num_nodes = 2,
+	.nodes = { &qnm_lpass_lpinoc, &qns_lpass_aggnoc },
+};
+
+static struct qcom_icc_bcm bcm_mc0 = {
+	.name = "MC0",
+	.keepalive = true,
+	.num_nodes = 1,
+	.nodes = { &ebi },
+};
+
+static struct qcom_icc_bcm bcm_mm0 = {
+	.name = "MM0",
+	.num_nodes = 1,
+	.nodes = { &qns_mem_noc_hf },
+};
+
+static struct qcom_icc_bcm bcm_mm1 = {
+	.name = "MM1",
+	.num_nodes = 10,
+	.nodes = { &qnm_av1_enc, &qnm_camnoc_hf,
+		   &qnm_camnoc_icp, &qnm_camnoc_sf,
+		   &qnm_eva, &qnm_mdp,
+		   &qnm_video, &qnm_video_cv_cpu,
+		   &qnm_video_v_cpu, &qns_mem_noc_sf },
+};
+
+static struct qcom_icc_bcm bcm_pc0 = {
+	.name = "PC0",
+	.num_nodes = 1,
+	.nodes = { &qns_pcie_mem_noc },
+};
+
+static struct qcom_icc_bcm bcm_qup0 = {
+	.name = "QUP0",
+	.keepalive = true,
+	.vote_scale = 1,
+	.num_nodes = 1,
+	.nodes = { &qup0_core_slave },
+};
+
+static struct qcom_icc_bcm bcm_qup1 = {
+	.name = "QUP1",
+	.keepalive = true,
+	.vote_scale = 1,
+	.num_nodes = 1,
+	.nodes = { &qup1_core_slave },
+};
+
+static struct qcom_icc_bcm bcm_qup2 = {
+	.name = "QUP2",
+	.keepalive = true,
+	.vote_scale = 1,
+	.num_nodes = 1,
+	.nodes = { &qup2_core_slave },
+};
+
+static struct qcom_icc_bcm bcm_sh0 = {
+	.name = "SH0",
+	.keepalive = true,
+	.num_nodes = 1,
+	.nodes = { &qns_llcc },
+};
+
+static struct qcom_icc_bcm bcm_sh1 = {
+	.name = "SH1",
+	.num_nodes = 13,
+	.nodes = { &alm_gpu_tcu, &alm_pcie_tcu,
+		   &alm_sys_tcu, &chm_apps,
+		   &qnm_gpu, &qnm_lpass,
+		   &qnm_mnoc_hf, &qnm_mnoc_sf,
+		   &qnm_nsp_noc, &qnm_pcie,
+		   &xm_gic, &qns_gem_noc_cnoc,
+		   &qns_pcie },
+};
+
+static struct qcom_icc_bcm bcm_sn0 = {
+	.name = "SN0",
+	.keepalive = true,
+	.num_nodes = 1,
+	.nodes = { &qns_gemnoc_sf },
+};
+
+static struct qcom_icc_bcm bcm_sn2 = {
+	.name = "SN2",
+	.num_nodes = 1,
+	.nodes = { &qnm_aggre1_noc },
+};
+
+static struct qcom_icc_bcm bcm_sn3 = {
+	.name = "SN3",
+	.num_nodes = 1,
+	.nodes = { &qnm_aggre2_noc },
+};
+
+static struct qcom_icc_bcm bcm_sn4 = {
+	.name = "SN4",
+	.num_nodes = 1,
+	.nodes = { &qnm_usb_anoc },
+};
+
+static struct qcom_icc_bcm bcm_acv_disp = {
+	.name = "ACV",
+	.num_nodes = 1,
+	.nodes = { &ebi_disp },
+};
+
+static struct qcom_icc_bcm bcm_mc0_disp = {
+	.name = "MC0",
+	.num_nodes = 1,
+	.nodes = { &ebi_disp },
+};
+
+static struct qcom_icc_bcm bcm_mm0_disp = {
+	.name = "MM0",
+	.num_nodes = 1,
+	.nodes = { &qns_mem_noc_hf_disp },
+};
+
+static struct qcom_icc_bcm bcm_mm1_disp = {
+	.name = "MM1",
+	.num_nodes = 1,
+	.nodes = { &qnm_mdp_disp },
+};
+
+static struct qcom_icc_bcm bcm_sh0_disp = {
+	.name = "SH0",
+	.num_nodes = 1,
+	.nodes = { &qns_llcc_disp },
+};
+
+static struct qcom_icc_bcm bcm_sh1_disp = {
+	.name = "SH1",
+	.num_nodes = 2,
+	.nodes = { &qnm_mnoc_hf_disp, &qnm_pcie_disp },
+};
+
+static struct qcom_icc_bcm bcm_acv_pcie = {
+	.name = "ACV",
+	.num_nodes = 1,
+	.nodes = { &ebi_pcie },
+};
+
+static struct qcom_icc_bcm bcm_mc0_pcie = {
+	.name = "MC0",
+	.num_nodes = 1,
+	.nodes = { &ebi_pcie },
+};
+
+static struct qcom_icc_bcm bcm_pc0_pcie = {
+	.name = "PC0",
+	.num_nodes = 1,
+	.nodes = { &qns_pcie_mem_noc_pcie },
+};
+
+static struct qcom_icc_bcm bcm_sh0_pcie = {
+	.name = "SH0",
+	.num_nodes = 1,
+	.nodes = { &qns_llcc_pcie },
+};
+
+static struct qcom_icc_bcm bcm_sh1_pcie = {
+	.name = "SH1",
+	.num_nodes = 1,
+	.nodes = { &qnm_pcie_pcie },
+};
+
+static struct qcom_icc_bcm *aggre1_noc_bcms[] = {
+};
+
+static struct qcom_icc_node * const aggre1_noc_nodes[] = {
+	[MASTER_QSPI_0] = &qhm_qspi,
+	[MASTER_QUP_1] = &qhm_qup1,
+	[MASTER_SDCC_4] = &xm_sdc4,
+	[MASTER_UFS_MEM] = &xm_ufs_mem,
+	[SLAVE_A1NOC_SNOC] = &qns_a1noc_snoc,
+};
+
+static const struct qcom_icc_desc x1e80100_aggre1_noc = {
+	.nodes = aggre1_noc_nodes,
+	.num_nodes = ARRAY_SIZE(aggre1_noc_nodes),
+	.bcms = aggre1_noc_bcms,
+	.num_bcms = ARRAY_SIZE(aggre1_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const aggre2_noc_bcms[] = {
+	&bcm_ce0,
+};
+
+static struct qcom_icc_node * const aggre2_noc_nodes[] = {
+	[MASTER_QUP_0] = &qhm_qup0,
+	[MASTER_QUP_2] = &qhm_qup2,
+	[MASTER_CRYPTO] = &qxm_crypto,
+	[MASTER_SP] = &qxm_sp,
+	[MASTER_QDSS_ETR] = &xm_qdss_etr_0,
+	[MASTER_QDSS_ETR_1] = &xm_qdss_etr_1,
+	[MASTER_SDCC_2] = &xm_sdc2,
+	[SLAVE_A2NOC_SNOC] = &qns_a2noc_snoc,
+};
+
+static const struct qcom_icc_desc x1e80100_aggre2_noc = {
+	.nodes = aggre2_noc_nodes,
+	.num_nodes = ARRAY_SIZE(aggre2_noc_nodes),
+	.bcms = aggre2_noc_bcms,
+	.num_bcms = ARRAY_SIZE(aggre2_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const clk_virt_bcms[] = {
+	&bcm_acv_perf,
+	&bcm_qup0,
+	&bcm_qup1,
+	&bcm_qup2,
+};
+
+static struct qcom_icc_node * const clk_virt_nodes[] = {
+	[MASTER_DDR_PERF_MODE] = &ddr_perf_mode_master,
+	[MASTER_QUP_CORE_0] = &qup0_core_master,
+	[MASTER_QUP_CORE_1] = &qup1_core_master,
+	[MASTER_QUP_CORE_2] = &qup2_core_master,
+	[SLAVE_DDR_PERF_MODE] = &ddr_perf_mode_slave,
+	[SLAVE_QUP_CORE_0] = &qup0_core_slave,
+	[SLAVE_QUP_CORE_1] = &qup1_core_slave,
+	[SLAVE_QUP_CORE_2] = &qup2_core_slave,
+};
+
+static const struct qcom_icc_desc x1e80100_clk_virt = {
+	.nodes = clk_virt_nodes,
+	.num_nodes = ARRAY_SIZE(clk_virt_nodes),
+	.bcms = clk_virt_bcms,
+	.num_bcms = ARRAY_SIZE(clk_virt_bcms),
+};
+
+static struct qcom_icc_bcm * const cnoc_cfg_bcms[] = {
+	&bcm_cn0,
+	&bcm_cn1,
+};
+
+static struct qcom_icc_node * const cnoc_cfg_nodes[] = {
+	[MASTER_CNOC_CFG] = &qsm_cfg,
+	[SLAVE_AHB2PHY_SOUTH] = &qhs_ahb2phy0,
+	[SLAVE_AHB2PHY_NORTH] = &qhs_ahb2phy1,
+	[SLAVE_AHB2PHY_2] = &qhs_ahb2phy2,
+	[SLAVE_AV1_ENC_CFG] = &qhs_av1_enc_cfg,
+	[SLAVE_CAMERA_CFG] = &qhs_camera_cfg,
+	[SLAVE_CLK_CTL] = &qhs_clk_ctl,
+	[SLAVE_CRYPTO_0_CFG] = &qhs_crypto0_cfg,
+	[SLAVE_DISPLAY_CFG] = &qhs_display_cfg,
+	[SLAVE_GFX3D_CFG] = &qhs_gpuss_cfg,
+	[SLAVE_IMEM_CFG] = &qhs_imem_cfg,
+	[SLAVE_IPC_ROUTER_CFG] = &qhs_ipc_router,
+	[SLAVE_PCIE_0_CFG] = &qhs_pcie0_cfg,
+	[SLAVE_PCIE_1_CFG] = &qhs_pcie1_cfg,
+	[SLAVE_PCIE_2_CFG] = &qhs_pcie2_cfg,
+	[SLAVE_PCIE_3_CFG] = &qhs_pcie3_cfg,
+	[SLAVE_PCIE_4_CFG] = &qhs_pcie4_cfg,
+	[SLAVE_PCIE_5_CFG] = &qhs_pcie5_cfg,
+	[SLAVE_PCIE_6A_CFG] = &qhs_pcie6a_cfg,
+	[SLAVE_PCIE_6B_CFG] = &qhs_pcie6b_cfg,
+	[SLAVE_PCIE_RSC_CFG] = &qhs_pcie_rsc_cfg,
+	[SLAVE_PDM] = &qhs_pdm,
+	[SLAVE_PRNG] = &qhs_prng,
+	[SLAVE_QDSS_CFG] = &qhs_qdss_cfg,
+	[SLAVE_QSPI_0] = &qhs_qspi,
+	[SLAVE_QUP_0] = &qhs_qup0,
+	[SLAVE_QUP_1] = &qhs_qup1,
+	[SLAVE_QUP_2] = &qhs_qup2,
+	[SLAVE_SDCC_2] = &qhs_sdc2,
+	[SLAVE_SDCC_4] = &qhs_sdc4,
+	[SLAVE_SMMUV3_CFG] = &qhs_smmuv3_cfg,
+	[SLAVE_TCSR] = &qhs_tcsr,
+	[SLAVE_TLMM] = &qhs_tlmm,
+	[SLAVE_UFS_MEM_CFG] = &qhs_ufs_mem_cfg,
+	[SLAVE_USB2] = &qhs_usb2_0_cfg,
+	[SLAVE_USB3_0] = &qhs_usb3_0_cfg,
+	[SLAVE_USB3_1] = &qhs_usb3_1_cfg,
+	[SLAVE_USB3_2] = &qhs_usb3_2_cfg,
+	[SLAVE_USB3_MP] = &qhs_usb3_mp_cfg,
+	[SLAVE_USB4_0] = &qhs_usb4_0_cfg,
+	[SLAVE_USB4_1] = &qhs_usb4_1_cfg,
+	[SLAVE_USB4_2] = &qhs_usb4_2_cfg,
+	[SLAVE_VENUS_CFG] = &qhs_venus_cfg,
+	[SLAVE_LPASS_QTB_CFG] = &qss_lpass_qtb_cfg,
+	[SLAVE_CNOC_MNOC_CFG] = &qss_mnoc_cfg,
+	[SLAVE_NSP_QTB_CFG] = &qss_nsp_qtb_cfg,
+	[SLAVE_QDSS_STM] = &xs_qdss_stm,
+	[SLAVE_TCU] = &xs_sys_tcu_cfg,
+};
+
+static const struct qcom_icc_desc x1e80100_cnoc_cfg = {
+	.nodes = cnoc_cfg_nodes,
+	.num_nodes = ARRAY_SIZE(cnoc_cfg_nodes),
+	.bcms = cnoc_cfg_bcms,
+	.num_bcms = ARRAY_SIZE(cnoc_cfg_bcms),
+};
+
+static struct qcom_icc_bcm * const cnoc_main_bcms[] = {
+	&bcm_cn0,
+};
+
+static struct qcom_icc_node * const cnoc_main_nodes[] = {
+	[MASTER_GEM_NOC_CNOC] = &qnm_gemnoc_cnoc,
+	[MASTER_GEM_NOC_PCIE_SNOC] = &qnm_gemnoc_pcie,
+	[SLAVE_AOSS] = &qhs_aoss,
+	[SLAVE_TME_CFG] = &qhs_tme_cfg,
+	[SLAVE_APPSS] = &qns_apss,
+	[SLAVE_CNOC_CFG] = &qss_cfg,
+	[SLAVE_BOOT_IMEM] = &qxs_boot_imem,
+	[SLAVE_IMEM] = &qxs_imem,
+	[SLAVE_PCIE_0] = &xs_pcie_0,
+	[SLAVE_PCIE_1] = &xs_pcie_1,
+	[SLAVE_PCIE_2] = &xs_pcie_2,
+	[SLAVE_PCIE_3] = &xs_pcie_3,
+	[SLAVE_PCIE_4] = &xs_pcie_4,
+	[SLAVE_PCIE_5] = &xs_pcie_5,
+	[SLAVE_PCIE_6A] = &xs_pcie_6a,
+	[SLAVE_PCIE_6B] = &xs_pcie_6b,
+};
+
+static const struct qcom_icc_desc x1e80100_cnoc_main = {
+	.nodes = cnoc_main_nodes,
+	.num_nodes = ARRAY_SIZE(cnoc_main_nodes),
+	.bcms = cnoc_main_bcms,
+	.num_bcms = ARRAY_SIZE(cnoc_main_bcms),
+};
+
+static struct qcom_icc_bcm * const gem_noc_bcms[] = {
+	&bcm_sh0,
+	&bcm_sh1,
+	&bcm_sh0_disp,
+	&bcm_sh1_disp,
+	&bcm_sh0_pcie,
+	&bcm_sh1_pcie,
+};
+
+static struct qcom_icc_node * const gem_noc_nodes[] = {
+	[MASTER_GPU_TCU] = &alm_gpu_tcu,
+	[MASTER_PCIE_TCU] = &alm_pcie_tcu,
+	[MASTER_SYS_TCU] = &alm_sys_tcu,
+	[MASTER_APPSS_PROC] = &chm_apps,
+	[MASTER_GFX3D] = &qnm_gpu,
+	[MASTER_LPASS_GEM_NOC] = &qnm_lpass,
+	[MASTER_MNOC_HF_MEM_NOC] = &qnm_mnoc_hf,
+	[MASTER_MNOC_SF_MEM_NOC] = &qnm_mnoc_sf,
+	[MASTER_COMPUTE_NOC] = &qnm_nsp_noc,
+	[MASTER_ANOC_PCIE_GEM_NOC] = &qnm_pcie,
+	[MASTER_SNOC_SF_MEM_NOC] = &qnm_snoc_sf,
+	[MASTER_GIC2] = &xm_gic,
+	[SLAVE_GEM_NOC_CNOC] = &qns_gem_noc_cnoc,
+	[SLAVE_LLCC] = &qns_llcc,
+	[SLAVE_MEM_NOC_PCIE_SNOC] = &qns_pcie,
+	[MASTER_MNOC_HF_MEM_NOC_DISP] = &qnm_mnoc_hf_disp,
+	[MASTER_ANOC_PCIE_GEM_NOC_DISP] = &qnm_pcie_disp,
+	[SLAVE_LLCC_DISP] = &qns_llcc_disp,
+	[MASTER_ANOC_PCIE_GEM_NOC_PCIE] = &qnm_pcie_pcie,
+	[SLAVE_LLCC_PCIE] = &qns_llcc_pcie,
+};
+
+static const struct qcom_icc_desc x1e80100_gem_noc = {
+	.nodes = gem_noc_nodes,
+	.num_nodes = ARRAY_SIZE(gem_noc_nodes),
+	.bcms = gem_noc_bcms,
+	.num_bcms = ARRAY_SIZE(gem_noc_bcms),
+};
+
+static struct qcom_icc_bcm *lpass_ag_noc_bcms[] = {
+};
+
+static struct qcom_icc_node * const lpass_ag_noc_nodes[] = {
+	[MASTER_LPIAON_NOC] = &qnm_lpiaon_noc,
+	[SLAVE_LPASS_GEM_NOC] = &qns_lpass_ag_noc_gemnoc,
+};
+
+static const struct qcom_icc_desc x1e80100_lpass_ag_noc = {
+	.nodes = lpass_ag_noc_nodes,
+	.num_nodes = ARRAY_SIZE(lpass_ag_noc_nodes),
+	.bcms = lpass_ag_noc_bcms,
+	.num_bcms = ARRAY_SIZE(lpass_ag_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const lpass_lpiaon_noc_bcms[] = {
+	&bcm_lp0,
+};
+
+static struct qcom_icc_node * const lpass_lpiaon_noc_nodes[] = {
+	[MASTER_LPASS_LPINOC] = &qnm_lpass_lpinoc,
+	[SLAVE_LPIAON_NOC_LPASS_AG_NOC] = &qns_lpass_aggnoc,
+};
+
+static const struct qcom_icc_desc x1e80100_lpass_lpiaon_noc = {
+	.nodes = lpass_lpiaon_noc_nodes,
+	.num_nodes = ARRAY_SIZE(lpass_lpiaon_noc_nodes),
+	.bcms = lpass_lpiaon_noc_bcms,
+	.num_bcms = ARRAY_SIZE(lpass_lpiaon_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const lpass_lpicx_noc_bcms[] = {
+};
+
+static struct qcom_icc_node * const lpass_lpicx_noc_nodes[] = {
+	[MASTER_LPASS_PROC] = &qxm_lpinoc_dsp_axim,
+	[SLAVE_LPICX_NOC_LPIAON_NOC] = &qns_lpi_aon_noc,
+};
+
+static const struct qcom_icc_desc x1e80100_lpass_lpicx_noc = {
+	.nodes = lpass_lpicx_noc_nodes,
+	.num_nodes = ARRAY_SIZE(lpass_lpicx_noc_nodes),
+	.bcms = lpass_lpicx_noc_bcms,
+	.num_bcms = ARRAY_SIZE(lpass_lpicx_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const mc_virt_bcms[] = {
+	&bcm_acv,
+	&bcm_mc0,
+	&bcm_acv_disp,
+	&bcm_mc0_disp,
+	&bcm_acv_pcie,
+	&bcm_mc0_pcie,
+};
+
+static struct qcom_icc_node * const mc_virt_nodes[] = {
+	[MASTER_LLCC] = &llcc_mc,
+	[SLAVE_EBI1] = &ebi,
+	[MASTER_LLCC_DISP] = &llcc_mc_disp,
+	[SLAVE_EBI1_DISP] = &ebi_disp,
+	[MASTER_LLCC_PCIE] = &llcc_mc_pcie,
+	[SLAVE_EBI1_PCIE] = &ebi_pcie,
+};
+
+static const struct qcom_icc_desc x1e80100_mc_virt = {
+	.nodes = mc_virt_nodes,
+	.num_nodes = ARRAY_SIZE(mc_virt_nodes),
+	.bcms = mc_virt_bcms,
+	.num_bcms = ARRAY_SIZE(mc_virt_bcms),
+};
+
+static struct qcom_icc_bcm * const mmss_noc_bcms[] = {
+	&bcm_mm0,
+	&bcm_mm1,
+	&bcm_mm0_disp,
+	&bcm_mm1_disp,
+};
+
+static struct qcom_icc_node * const mmss_noc_nodes[] = {
+	[MASTER_AV1_ENC] = &qnm_av1_enc,
+	[MASTER_CAMNOC_HF] = &qnm_camnoc_hf,
+	[MASTER_CAMNOC_ICP] = &qnm_camnoc_icp,
+	[MASTER_CAMNOC_SF] = &qnm_camnoc_sf,
+	[MASTER_EVA] = &qnm_eva,
+	[MASTER_MDP] = &qnm_mdp,
+	[MASTER_VIDEO] = &qnm_video,
+	[MASTER_VIDEO_CV_PROC] = &qnm_video_cv_cpu,
+	[MASTER_VIDEO_V_PROC] = &qnm_video_v_cpu,
+	[MASTER_CNOC_MNOC_CFG] = &qsm_mnoc_cfg,
+	[SLAVE_MNOC_HF_MEM_NOC] = &qns_mem_noc_hf,
+	[SLAVE_MNOC_SF_MEM_NOC] = &qns_mem_noc_sf,
+	[SLAVE_SERVICE_MNOC] = &srvc_mnoc,
+	[MASTER_MDP_DISP] = &qnm_mdp_disp,
+	[SLAVE_MNOC_HF_MEM_NOC_DISP] = &qns_mem_noc_hf_disp,
+};
+
+static const struct qcom_icc_desc x1e80100_mmss_noc = {
+	.nodes = mmss_noc_nodes,
+	.num_nodes = ARRAY_SIZE(mmss_noc_nodes),
+	.bcms = mmss_noc_bcms,
+	.num_bcms = ARRAY_SIZE(mmss_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const nsp_noc_bcms[] = {
+	&bcm_co0,
+};
+
+static struct qcom_icc_node * const nsp_noc_nodes[] = {
+	[MASTER_CDSP_PROC] = &qxm_nsp,
+	[SLAVE_CDSP_MEM_NOC] = &qns_nsp_gemnoc,
+};
+
+static const struct qcom_icc_desc x1e80100_nsp_noc = {
+	.nodes = nsp_noc_nodes,
+	.num_nodes = ARRAY_SIZE(nsp_noc_nodes),
+	.bcms = nsp_noc_bcms,
+	.num_bcms = ARRAY_SIZE(nsp_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const pcie_center_anoc_bcms[] = {
+	&bcm_pc0,
+	&bcm_pc0_pcie,
+};
+
+static struct qcom_icc_node * const pcie_center_anoc_nodes[] = {
+	[MASTER_PCIE_NORTH] = &qnm_pcie_north_gem_noc,
+	[MASTER_PCIE_SOUTH] = &qnm_pcie_south_gem_noc,
+	[SLAVE_ANOC_PCIE_GEM_NOC] = &qns_pcie_mem_noc,
+	[MASTER_PCIE_NORTH_PCIE] = &qnm_pcie_north_gem_noc_pcie,
+	[MASTER_PCIE_SOUTH_PCIE] = &qnm_pcie_south_gem_noc_pcie,
+	[SLAVE_ANOC_PCIE_GEM_NOC_PCIE] = &qns_pcie_mem_noc_pcie,
+};
+
+static const struct qcom_icc_desc x1e80100_pcie_center_anoc = {
+	.nodes = pcie_center_anoc_nodes,
+	.num_nodes = ARRAY_SIZE(pcie_center_anoc_nodes),
+	.bcms = pcie_center_anoc_bcms,
+	.num_bcms = ARRAY_SIZE(pcie_center_anoc_bcms),
+};
+
+static struct qcom_icc_bcm * const pcie_north_anoc_bcms[] = {
+};
+
+static struct qcom_icc_node * const pcie_north_anoc_nodes[] = {
+	[MASTER_PCIE_3] = &xm_pcie_3,
+	[MASTER_PCIE_4] = &xm_pcie_4,
+	[MASTER_PCIE_5] = &xm_pcie_5,
+	[SLAVE_PCIE_NORTH] = &qns_pcie_north_gem_noc,
+	[MASTER_PCIE_3_PCIE] = &xm_pcie_3_pcie,
+	[MASTER_PCIE_4_PCIE] = &xm_pcie_4_pcie,
+	[MASTER_PCIE_5_PCIE] = &xm_pcie_5_pcie,
+	[SLAVE_PCIE_NORTH_PCIE] = &qns_pcie_north_gem_noc_pcie,
+};
+
+static const struct qcom_icc_desc x1e80100_pcie_north_anoc = {
+	.nodes = pcie_north_anoc_nodes,
+	.num_nodes = ARRAY_SIZE(pcie_north_anoc_nodes),
+	.bcms = pcie_north_anoc_bcms,
+	.num_bcms = ARRAY_SIZE(pcie_north_anoc_bcms),
+};
+
+static struct qcom_icc_bcm *pcie_south_anoc_bcms[] = {
+};
+
+static struct qcom_icc_node * const pcie_south_anoc_nodes[] = {
+	[MASTER_PCIE_0] = &xm_pcie_0,
+	[MASTER_PCIE_1] = &xm_pcie_1,
+	[MASTER_PCIE_2] = &xm_pcie_2,
+	[MASTER_PCIE_6A] = &xm_pcie_6a,
+	[MASTER_PCIE_6B] = &xm_pcie_6b,
+	[SLAVE_PCIE_SOUTH] = &qns_pcie_south_gem_noc,
+	[MASTER_PCIE_0_PCIE] = &xm_pcie_0_pcie,
+	[MASTER_PCIE_1_PCIE] = &xm_pcie_1_pcie,
+	[MASTER_PCIE_2_PCIE] = &xm_pcie_2_pcie,
+	[MASTER_PCIE_6A_PCIE] = &xm_pcie_6a_pcie,
+	[MASTER_PCIE_6B_PCIE] = &xm_pcie_6b_pcie,
+	[SLAVE_PCIE_SOUTH_PCIE] = &qns_pcie_south_gem_noc_pcie,
+};
+
+static const struct qcom_icc_desc x1e80100_pcie_south_anoc = {
+	.nodes = pcie_south_anoc_nodes,
+	.num_nodes = ARRAY_SIZE(pcie_south_anoc_nodes),
+	.bcms = pcie_south_anoc_bcms,
+	.num_bcms = ARRAY_SIZE(pcie_south_anoc_bcms),
+};
+
+static struct qcom_icc_bcm *system_noc_bcms[] = {
+	&bcm_sn0,
+	&bcm_sn2,
+	&bcm_sn3,
+	&bcm_sn4,
+};
+
+static struct qcom_icc_node * const system_noc_nodes[] = {
+	[MASTER_A1NOC_SNOC] = &qnm_aggre1_noc,
+	[MASTER_A2NOC_SNOC] = &qnm_aggre2_noc,
+	[MASTER_GIC1] = &qnm_gic,
+	[MASTER_USB_NOC_SNOC] = &qnm_usb_anoc,
+	[SLAVE_SNOC_GEM_NOC_SF] = &qns_gemnoc_sf,
+};
+
+static const struct qcom_icc_desc x1e80100_system_noc = {
+	.nodes = system_noc_nodes,
+	.num_nodes = ARRAY_SIZE(system_noc_nodes),
+	.bcms = system_noc_bcms,
+	.num_bcms = ARRAY_SIZE(system_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const usb_center_anoc_bcms[] = {
+};
+
+static struct qcom_icc_node * const usb_center_anoc_nodes[] = {
+	[MASTER_AGGRE_USB_NORTH] = &qnm_aggre_usb_north_snoc,
+	[MASTER_AGGRE_USB_SOUTH] = &qnm_aggre_usb_south_snoc,
+	[SLAVE_USB_NOC_SNOC] = &qns_aggre_usb_snoc,
+};
+
+static const struct qcom_icc_desc x1e80100_usb_center_anoc = {
+	.nodes = usb_center_anoc_nodes,
+	.num_nodes = ARRAY_SIZE(usb_center_anoc_nodes),
+	.bcms = usb_center_anoc_bcms,
+	.num_bcms = ARRAY_SIZE(usb_center_anoc_bcms),
+};
+
+static struct qcom_icc_bcm *usb_north_anoc_bcms[] = {
+};
+
+static struct qcom_icc_node * const usb_north_anoc_nodes[] = {
+	[MASTER_USB2] = &xm_usb2_0,
+	[MASTER_USB3_MP] = &xm_usb3_mp,
+	[SLAVE_AGGRE_USB_NORTH] = &qns_aggre_usb_north_snoc,
+};
+
+static const struct qcom_icc_desc x1e80100_usb_north_anoc = {
+	.nodes = usb_north_anoc_nodes,
+	.num_nodes = ARRAY_SIZE(usb_north_anoc_nodes),
+	.bcms = usb_north_anoc_bcms,
+	.num_bcms = ARRAY_SIZE(usb_north_anoc_bcms),
+};
+
+static struct qcom_icc_bcm *usb_south_anoc_bcms[] = {
+};
+
+static struct qcom_icc_node * const usb_south_anoc_nodes[] = {
+	[MASTER_USB3_0] = &xm_usb3_0,
+	[MASTER_USB3_1] = &xm_usb3_1,
+	[MASTER_USB3_2] = &xm_usb3_2,
+	[MASTER_USB4_0] = &xm_usb4_0,
+	[MASTER_USB4_1] = &xm_usb4_1,
+	[MASTER_USB4_2] = &xm_usb4_2,
+	[SLAVE_AGGRE_USB_SOUTH] = &qns_aggre_usb_south_snoc,
+};
+
+static const struct qcom_icc_desc x1e80100_usb_south_anoc = {
+	.nodes = usb_south_anoc_nodes,
+	.num_nodes = ARRAY_SIZE(usb_south_anoc_nodes),
+	.bcms = usb_south_anoc_bcms,
+	.num_bcms = ARRAY_SIZE(usb_south_anoc_bcms),
+};
+
+static const struct of_device_id qnoc_of_match[] = {
+	{ .compatible = "qcom,x1e80100-aggre1-noc", .data = &x1e80100_aggre1_noc},
+	{ .compatible = "qcom,x1e80100-aggre2-noc", .data = &x1e80100_aggre2_noc},
+	{ .compatible = "qcom,x1e80100-clk-virt", .data = &x1e80100_clk_virt},
+	{ .compatible = "qcom,x1e80100-cnoc-cfg", .data = &x1e80100_cnoc_cfg},
+	{ .compatible = "qcom,x1e80100-cnoc-main", .data = &x1e80100_cnoc_main},
+	{ .compatible = "qcom,x1e80100-gem-noc", .data = &x1e80100_gem_noc},
+	{ .compatible = "qcom,x1e80100-lpass-ag-noc", .data = &x1e80100_lpass_ag_noc},
+	{ .compatible = "qcom,x1e80100-lpass-lpiaon-noc", .data = &x1e80100_lpass_lpiaon_noc},
+	{ .compatible = "qcom,x1e80100-lpass-lpicx-noc", .data = &x1e80100_lpass_lpicx_noc},
+	{ .compatible = "qcom,x1e80100-mc-virt", .data = &x1e80100_mc_virt},
+	{ .compatible = "qcom,x1e80100-mmss-noc", .data = &x1e80100_mmss_noc},
+	{ .compatible = "qcom,x1e80100-nsp-noc", .data = &x1e80100_nsp_noc},
+	{ .compatible = "qcom,x1e80100-pcie-center-anoc", .data = &x1e80100_pcie_center_anoc},
+	{ .compatible = "qcom,x1e80100-pcie-north-anoc", .data = &x1e80100_pcie_north_anoc},
+	{ .compatible = "qcom,x1e80100-pcie-south-anoc", .data = &x1e80100_pcie_south_anoc},
+	{ .compatible = "qcom,x1e80100-system-noc", .data = &x1e80100_system_noc},
+	{ .compatible = "qcom,x1e80100-usb-center-anoc", .data = &x1e80100_usb_center_anoc},
+	{ .compatible = "qcom,x1e80100-usb-north-anoc", .data = &x1e80100_usb_north_anoc},
+	{ .compatible = "qcom,x1e80100-usb-south-anoc", .data = &x1e80100_usb_south_anoc},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, qnoc_of_match);
+
+static struct platform_driver qnoc_driver = {
+	.probe = qcom_icc_rpmh_probe,
+	.remove_new = qcom_icc_rpmh_remove,
+	.driver = {
+		.name = "qnoc-x1e80100",
+		.of_match_table = qnoc_of_match,
+		.sync_state = icc_sync_state,
+	},
+};
+
+static int __init qnoc_driver_init(void)
+{
+	return platform_driver_register(&qnoc_driver);
+}
+core_initcall(qnoc_driver_init);
+
+static void __exit qnoc_driver_exit(void)
+{
+	platform_driver_unregister(&qnoc_driver);
+}
+module_exit(qnoc_driver_exit);
+
+MODULE_DESCRIPTION("x1e80100 NoC driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/interconnect/qcom/x1e80100.h b/drivers/interconnect/qcom/x1e80100.h
new file mode 100644
index 000000000000..2e14264f4c2b
--- /dev/null
+++ b/drivers/interconnect/qcom/x1e80100.h
@@ -0,0 +1,192 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * X1E80100 interconnect IDs
+ *
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef __DRIVERS_INTERCONNECT_QCOM_X1E80100_H
+#define __DRIVERS_INTERCONNECT_QCOM_X1E80100_H
+
+#define X1E80100_MASTER_A1NOC_SNOC			0
+#define X1E80100_MASTER_A2NOC_SNOC			1
+#define X1E80100_MASTER_ANOC_PCIE_GEM_NOC		2
+#define X1E80100_MASTER_ANOC_PCIE_GEM_NOC_DISP		3
+#define X1E80100_MASTER_APPSS_PROC			4
+#define X1E80100_MASTER_CAMNOC_HF			5
+#define X1E80100_MASTER_CAMNOC_ICP			6
+#define X1E80100_MASTER_CAMNOC_SF			7
+#define X1E80100_MASTER_CDSP_PROC			8
+#define X1E80100_MASTER_CNOC_CFG			9
+#define X1E80100_MASTER_CNOC_MNOC_CFG			10
+#define X1E80100_MASTER_COMPUTE_NOC			11
+#define X1E80100_MASTER_CRYPTO				12
+#define X1E80100_MASTER_GEM_NOC_CNOC			13
+#define X1E80100_MASTER_GEM_NOC_PCIE_SNOC		14
+#define X1E80100_MASTER_GFX3D				15
+#define X1E80100_MASTER_GPU_TCU				16
+#define X1E80100_MASTER_IPA				17
+#define X1E80100_MASTER_LLCC				18
+#define X1E80100_MASTER_LLCC_DISP			19
+#define X1E80100_MASTER_LPASS_GEM_NOC			20
+#define X1E80100_MASTER_LPASS_LPINOC			21
+#define X1E80100_MASTER_LPASS_PROC			22
+#define X1E80100_MASTER_LPIAON_NOC			23
+#define X1E80100_MASTER_MDP				24
+#define X1E80100_MASTER_MDP_DISP			25
+#define X1E80100_MASTER_MNOC_HF_MEM_NOC			26
+#define X1E80100_MASTER_MNOC_HF_MEM_NOC_DISP		27
+#define X1E80100_MASTER_MNOC_SF_MEM_NOC			28
+#define X1E80100_MASTER_PCIE_0				29
+#define X1E80100_MASTER_PCIE_1				30
+#define X1E80100_MASTER_QDSS_ETR			31
+#define X1E80100_MASTER_QDSS_ETR_1			32
+#define X1E80100_MASTER_QSPI_0				33
+#define X1E80100_MASTER_QUP_0				34
+#define X1E80100_MASTER_QUP_1				35
+#define X1E80100_MASTER_QUP_2				36
+#define X1E80100_MASTER_QUP_CORE_0			37
+#define X1E80100_MASTER_QUP_CORE_1			38
+#define X1E80100_MASTER_SDCC_2				39
+#define X1E80100_MASTER_SDCC_4				40
+#define X1E80100_MASTER_SNOC_SF_MEM_NOC			41
+#define X1E80100_MASTER_SP				42
+#define X1E80100_MASTER_SYS_TCU				43
+#define X1E80100_MASTER_UFS_MEM				44
+#define X1E80100_MASTER_USB3_0				45
+#define X1E80100_MASTER_VIDEO				46
+#define X1E80100_MASTER_VIDEO_CV_PROC			47
+#define X1E80100_MASTER_VIDEO_V_PROC			48
+#define X1E80100_SLAVE_A1NOC_SNOC			49
+#define X1E80100_SLAVE_A2NOC_SNOC			50
+#define X1E80100_SLAVE_AHB2PHY_NORTH			51
+#define X1E80100_SLAVE_AHB2PHY_SOUTH			52
+#define X1E80100_SLAVE_ANOC_PCIE_GEM_NOC		53
+#define X1E80100_SLAVE_AOSS				54
+#define X1E80100_SLAVE_APPSS				55
+#define X1E80100_SLAVE_BOOT_IMEM			56
+#define X1E80100_SLAVE_CAMERA_CFG			57
+#define X1E80100_SLAVE_CDSP_MEM_NOC			58
+#define X1E80100_SLAVE_CLK_CTL				59
+#define X1E80100_SLAVE_CNOC_CFG				60
+#define X1E80100_SLAVE_CNOC_MNOC_CFG			61
+#define X1E80100_SLAVE_CRYPTO_0_CFG			62
+#define X1E80100_SLAVE_DISPLAY_CFG			63
+#define X1E80100_SLAVE_EBI1				64
+#define X1E80100_SLAVE_EBI1_DISP			65
+#define X1E80100_SLAVE_GEM_NOC_CNOC			66
+#define X1E80100_SLAVE_GFX3D_CFG			67
+#define X1E80100_SLAVE_IMEM				68
+#define X1E80100_SLAVE_IMEM_CFG				69
+#define X1E80100_SLAVE_IPC_ROUTER_CFG			70
+#define X1E80100_SLAVE_LLCC				71
+#define X1E80100_SLAVE_LLCC_DISP			72
+#define X1E80100_SLAVE_LPASS_GEM_NOC			73
+#define X1E80100_SLAVE_LPASS_QTB_CFG			74
+#define X1E80100_SLAVE_LPIAON_NOC_LPASS_AG_NOC		75
+#define X1E80100_SLAVE_LPICX_NOC_LPIAON_NOC		76
+#define X1E80100_SLAVE_MEM_NOC_PCIE_SNOC		77
+#define X1E80100_SLAVE_MNOC_HF_MEM_NOC			78
+#define X1E80100_SLAVE_MNOC_HF_MEM_NOC_DISP		79
+#define X1E80100_SLAVE_MNOC_SF_MEM_NOC			80
+#define X1E80100_SLAVE_NSP_QTB_CFG			81
+#define X1E80100_SLAVE_PCIE_0				82
+#define X1E80100_SLAVE_PCIE_0_CFG			83
+#define X1E80100_SLAVE_PCIE_1				84
+#define X1E80100_SLAVE_PCIE_1_CFG			85
+#define X1E80100_SLAVE_PDM				86
+#define X1E80100_SLAVE_PRNG				87
+#define X1E80100_SLAVE_QDSS_CFG				88
+#define X1E80100_SLAVE_QDSS_STM				89
+#define X1E80100_SLAVE_QSPI_0				90
+#define X1E80100_SLAVE_QUP_1				91
+#define X1E80100_SLAVE_QUP_2				92
+#define X1E80100_SLAVE_QUP_CORE_0			93
+#define X1E80100_SLAVE_QUP_CORE_1			94
+#define X1E80100_SLAVE_QUP_CORE_2			95
+#define X1E80100_SLAVE_SDCC_2				96
+#define X1E80100_SLAVE_SDCC_4				97
+#define X1E80100_SLAVE_SERVICE_MNOC			98
+#define X1E80100_SLAVE_SNOC_GEM_NOC_SF			99
+#define X1E80100_SLAVE_TCSR				100
+#define X1E80100_SLAVE_TCU				101
+#define X1E80100_SLAVE_TLMM				102
+#define X1E80100_SLAVE_TME_CFG				103
+#define X1E80100_SLAVE_UFS_MEM_CFG			104
+#define X1E80100_SLAVE_USB3_0				105
+#define X1E80100_SLAVE_VENUS_CFG			106
+#define X1E80100_MASTER_DDR_PERF_MODE			107
+#define X1E80100_MASTER_QUP_CORE_2			108
+#define X1E80100_MASTER_PCIE_TCU			109
+#define X1E80100_MASTER_GIC2				110
+#define X1E80100_MASTER_AV1_ENC				111
+#define X1E80100_MASTER_EVA				112
+#define X1E80100_MASTER_PCIE_NORTH			113
+#define X1E80100_MASTER_PCIE_SOUTH			114
+#define X1E80100_MASTER_PCIE_3				115
+#define X1E80100_MASTER_PCIE_4				116
+#define X1E80100_MASTER_PCIE_5				117
+#define X1E80100_MASTER_PCIE_2				118
+#define X1E80100_MASTER_PCIE_6A				119
+#define X1E80100_MASTER_PCIE_6B				120
+#define X1E80100_MASTER_GIC1				121
+#define X1E80100_MASTER_USB_NOC_SNOC			122
+#define X1E80100_MASTER_AGGRE_USB_NORTH			123
+#define X1E80100_MASTER_AGGRE_USB_SOUTH			124
+#define X1E80100_MASTER_USB2				125
+#define X1E80100_MASTER_USB3_MP				126
+#define X1E80100_MASTER_USB3_1				127
+#define X1E80100_MASTER_USB3_2				128
+#define X1E80100_MASTER_USB4_0				129
+#define X1E80100_MASTER_USB4_1				130
+#define X1E80100_MASTER_USB4_2				131
+#define X1E80100_MASTER_ANOC_PCIE_GEM_NOC_PCIE		132
+#define X1E80100_MASTER_LLCC_PCIE			133
+#define X1E80100_MASTER_PCIE_NORTH_PCIE			134
+#define X1E80100_MASTER_PCIE_SOUTH_PCIE			135
+#define X1E80100_MASTER_PCIE_3_PCIE			136
+#define X1E80100_MASTER_PCIE_4_PCIE			137
+#define X1E80100_MASTER_PCIE_5_PCIE			138
+#define X1E80100_MASTER_PCIE_0_PCIE			139
+#define X1E80100_MASTER_PCIE_1_PCIE			140
+#define X1E80100_MASTER_PCIE_2_PCIE			141
+#define X1E80100_MASTER_PCIE_6A_PCIE			142
+#define X1E80100_MASTER_PCIE_6B_PCIE			143
+#define X1E80100_SLAVE_AHB2PHY_2			144
+#define X1E80100_SLAVE_AV1_ENC_CFG			145
+#define X1E80100_SLAVE_PCIE_2_CFG			146
+#define X1E80100_SLAVE_PCIE_3_CFG			147
+#define X1E80100_SLAVE_PCIE_4_CFG			148
+#define X1E80100_SLAVE_PCIE_5_CFG			149
+#define X1E80100_SLAVE_PCIE_6A_CFG			150
+#define X1E80100_SLAVE_PCIE_6B_CFG			151
+#define X1E80100_SLAVE_PCIE_RSC_CFG			152
+#define X1E80100_SLAVE_QUP_0				153
+#define X1E80100_SLAVE_SMMUV3_CFG			154
+#define X1E80100_SLAVE_USB2				155
+#define X1E80100_SLAVE_USB3_1				156
+#define X1E80100_SLAVE_USB3_2				157
+#define X1E80100_SLAVE_USB3_MP				158
+#define X1E80100_SLAVE_USB4_0				159
+#define X1E80100_SLAVE_USB4_1				160
+#define X1E80100_SLAVE_USB4_2				161
+#define X1E80100_SLAVE_PCIE_2				162
+#define X1E80100_SLAVE_PCIE_3				163
+#define X1E80100_SLAVE_PCIE_4				164
+#define X1E80100_SLAVE_PCIE_5				165
+#define X1E80100_SLAVE_PCIE_6A				166
+#define X1E80100_SLAVE_PCIE_6B				167
+#define X1E80100_SLAVE_DDR_PERF_MODE			168
+#define X1E80100_SLAVE_PCIE_NORTH			169
+#define X1E80100_SLAVE_PCIE_SOUTH			170
+#define X1E80100_SLAVE_USB_NOC_SNOC			171
+#define X1E80100_SLAVE_AGGRE_USB_NORTH			172
+#define X1E80100_SLAVE_AGGRE_USB_SOUTH			173
+#define X1E80100_SLAVE_LLCC_PCIE			174
+#define X1E80100_SLAVE_EBI1_PCIE			175
+#define X1E80100_SLAVE_ANOC_PCIE_GEM_NOC_PCIE		176
+#define X1E80100_SLAVE_PCIE_NORTH_PCIE			177
+#define X1E80100_SLAVE_PCIE_SOUTH_PCIE			178
+
+#endif
diff --git a/drivers/interconnect/samsung/exynos.c b/drivers/interconnect/samsung/exynos.c
index ebf09bbf725b..1ba14cb45d5a 100644
--- a/drivers/interconnect/samsung/exynos.c
+++ b/drivers/interconnect/samsung/exynos.c
@@ -93,14 +93,12 @@ static struct icc_node *exynos_generic_icc_xlate(struct of_phandle_args *spec,
 	return priv->node;
 }
 
-static int exynos_generic_icc_remove(struct platform_device *pdev)
+static void exynos_generic_icc_remove(struct platform_device *pdev)
 {
 	struct exynos_icc_priv *priv = platform_get_drvdata(pdev);
 
 	icc_provider_deregister(&priv->provider);
 	icc_nodes_remove(&priv->provider);
-
-	return 0;
 }
 
 static int exynos_generic_icc_probe(struct platform_device *pdev)
@@ -182,7 +180,7 @@ static struct platform_driver exynos_generic_icc_driver = {
 		.sync_state = icc_sync_state,
 	},
 	.probe = exynos_generic_icc_probe,
-	.remove = exynos_generic_icc_remove,
+	.remove_new = exynos_generic_icc_remove,
 };
 module_platform_driver(exynos_generic_icc_driver);
 
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 7673bb82945b..9a29d742617e 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -160,6 +160,7 @@ config IOMMU_DMA
 
 # Shared Virtual Addressing
 config IOMMU_SVA
+	select IOMMU_MM_DATA
 	bool
 
 config FSL_PAMU
diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index 86be1edd50ee..8b3601f285fd 100644
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -53,10 +53,16 @@ int amd_iommu_pdev_enable_cap_pri(struct pci_dev *pdev);
 void amd_iommu_pdev_disable_cap_pri(struct pci_dev *pdev);
 
 int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid, u64 address);
+/*
+ * This function flushes all internal caches of
+ * the IOMMU used by this driver.
+ */
+void amd_iommu_flush_all_caches(struct amd_iommu *iommu);
 void amd_iommu_update_and_flush_device_table(struct protection_domain *domain);
 void amd_iommu_domain_update(struct protection_domain *domain);
 void amd_iommu_domain_flush_complete(struct protection_domain *domain);
-void amd_iommu_domain_flush_tlb_pde(struct protection_domain *domain);
+void amd_iommu_domain_flush_pages(struct protection_domain *domain,
+				  u64 address, size_t size);
 int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid);
 int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, u32 pasid,
 			      unsigned long cr3);
diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 90b7d7950a9e..809d74faa1a5 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -902,12 +902,6 @@ extern int amd_iommu_max_glx_val;
 extern u64 amd_iommu_efr;
 extern u64 amd_iommu_efr2;
 
-/*
- * This function flushes all internal caches of
- * the IOMMU used by this driver.
- */
-void iommu_flush_all_caches(struct amd_iommu *iommu);
-
 static inline int get_ioapic_devid(int id)
 {
 	struct devid_map *entry;
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 64bcf3df37ee..c83bd0c2a1c9 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -2223,7 +2223,7 @@ static int __init amd_iommu_init_pci(void)
 		init_device_table_dma(pci_seg);
 
 	for_each_iommu(iommu)
-		iommu_flush_all_caches(iommu);
+		amd_iommu_flush_all_caches(iommu);
 
 	print_iommu_info();
 
@@ -2773,7 +2773,7 @@ static void early_enable_iommu(struct amd_iommu *iommu)
 	iommu_enable_xt(iommu);
 	iommu_enable_irtcachedis(iommu);
 	iommu_enable(iommu);
-	iommu_flush_all_caches(iommu);
+	amd_iommu_flush_all_caches(iommu);
 }
 
 /*
@@ -2829,7 +2829,7 @@ static void early_enable_iommus(void)
 			iommu_enable_xt(iommu);
 			iommu_enable_irtcachedis(iommu);
 			iommu_set_device_table(iommu);
-			iommu_flush_all_caches(iommu);
+			amd_iommu_flush_all_caches(iommu);
 		}
 	}
 }
@@ -3293,7 +3293,7 @@ static int __init state_next(void)
 				uninit_device_table_dma(pci_seg);
 
 			for_each_iommu(iommu)
-				iommu_flush_all_caches(iommu);
+				amd_iommu_flush_all_caches(iommu);
 		}
 	}
 	return ret;
diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c
index 6c0621f6f572..2a0d1e97e52f 100644
--- a/drivers/iommu/amd/io_pgtable.c
+++ b/drivers/iommu/amd/io_pgtable.c
@@ -369,6 +369,8 @@ static int iommu_v1_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
 	bool updated = false;
 	u64 __pte, *pte;
 	int ret, i, count;
+	size_t size = pgcount << __ffs(pgsize);
+	unsigned long o_iova = iova;
 
 	BUG_ON(!IS_ALIGNED(iova, pgsize));
 	BUG_ON(!IS_ALIGNED(paddr, pgsize));
@@ -424,8 +426,7 @@ out:
 		 * Updates and flushing already happened in
 		 * increase_address_space().
 		 */
-		amd_iommu_domain_flush_tlb_pde(dom);
-		amd_iommu_domain_flush_complete(dom);
+		amd_iommu_domain_flush_pages(dom, o_iova, size);
 		spin_unlock_irqrestore(&dom->lock, flags);
 	}
 
diff --git a/drivers/iommu/amd/io_pgtable_v2.c b/drivers/iommu/amd/io_pgtable_v2.c
index f818a7e254d4..6d69ba60744f 100644
--- a/drivers/iommu/amd/io_pgtable_v2.c
+++ b/drivers/iommu/amd/io_pgtable_v2.c
@@ -244,7 +244,6 @@ static int iommu_v2_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
 	unsigned long mapped_size = 0;
 	unsigned long o_iova = iova;
 	size_t size = pgcount << __ffs(pgsize);
-	int count = 0;
 	int ret = 0;
 	bool updated = false;
 
@@ -265,19 +264,14 @@ static int iommu_v2_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
 
 		*pte = set_pte_attr(paddr, map_size, prot);
 
-		count++;
 		iova += map_size;
 		paddr += map_size;
 		mapped_size += map_size;
 	}
 
 out:
-	if (updated) {
-		if (count > 1)
-			amd_iommu_flush_tlb(&pdom->domain, 0);
-		else
-			amd_iommu_flush_page(&pdom->domain, 0, o_iova);
-	}
+	if (updated)
+		amd_iommu_domain_flush_pages(pdom, o_iova, size);
 
 	if (mapped)
 		*mapped += mapped_size;
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index b9a0523cbb0a..4283dd8191f0 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -64,7 +64,7 @@ LIST_HEAD(hpet_map);
 LIST_HEAD(acpihid_map);
 
 const struct iommu_ops amd_iommu_ops;
-const struct iommu_dirty_ops amd_dirty_ops;
+static const struct iommu_dirty_ops amd_dirty_ops;
 
 int amd_iommu_max_glx_val = -1;
 
@@ -85,6 +85,11 @@ static void detach_device(struct device *dev);
  *
  ****************************************************************************/
 
+static inline bool pdom_is_v2_pgtbl_mode(struct protection_domain *pdom)
+{
+	return (pdom && (pdom->flags & PD_IOMMUV2_MASK));
+}
+
 static inline int get_acpihid_device_id(struct device *dev,
 					struct acpihid_map_entry **entry)
 {
@@ -551,8 +556,6 @@ static void amd_iommu_uninit_device(struct device *dev)
 	if (dev_data->domain)
 		detach_device(dev);
 
-	dev_iommu_priv_set(dev, NULL);
-
 	/*
 	 * We keep dev_data around for unplugged devices and reuse it when the
 	 * device is re-plugged - not doing so would introduce a ton of races.
@@ -1124,68 +1127,44 @@ static inline u64 build_inv_address(u64 address, size_t size)
 }
 
 static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address,
-				  size_t size, u16 domid, int pde)
+				  size_t size, u16 domid,
+				  ioasid_t pasid, bool gn)
 {
 	u64 inv_address = build_inv_address(address, size);
 
 	memset(cmd, 0, sizeof(*cmd));
+
 	cmd->data[1] |= domid;
 	cmd->data[2]  = lower_32_bits(inv_address);
 	cmd->data[3]  = upper_32_bits(inv_address);
+	/* PDE bit - we want to flush everything, not only the PTEs */
+	cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
+	if (gn) {
+		cmd->data[0] |= pasid;
+		cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
+	}
 	CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
-	if (pde) /* PDE bit - we want to flush everything, not only the PTEs */
-		cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
 }
 
 static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep,
-				  u64 address, size_t size)
+				  u64 address, size_t size,
+				  ioasid_t pasid, bool gn)
 {
 	u64 inv_address = build_inv_address(address, size);
 
 	memset(cmd, 0, sizeof(*cmd));
+
 	cmd->data[0]  = devid;
 	cmd->data[0] |= (qdep & 0xff) << 24;
 	cmd->data[1]  = devid;
 	cmd->data[2]  = lower_32_bits(inv_address);
 	cmd->data[3]  = upper_32_bits(inv_address);
-	CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
-}
-
-static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, u32 pasid,
-				  u64 address, bool size)
-{
-	memset(cmd, 0, sizeof(*cmd));
-
-	address &= ~(0xfffULL);
-
-	cmd->data[0]  = pasid;
-	cmd->data[1]  = domid;
-	cmd->data[2]  = lower_32_bits(address);
-	cmd->data[3]  = upper_32_bits(address);
-	cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
-	cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
-	if (size)
-		cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
-	CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
-}
-
-static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, u32 pasid,
-				  int qdep, u64 address, bool size)
-{
-	memset(cmd, 0, sizeof(*cmd));
-
-	address &= ~(0xfffULL);
+	if (gn) {
+		cmd->data[0] |= ((pasid >> 8) & 0xff) << 16;
+		cmd->data[1] |= (pasid & 0xff) << 16;
+		cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
+	}
 
-	cmd->data[0]  = devid;
-	cmd->data[0] |= ((pasid >> 8) & 0xff) << 16;
-	cmd->data[0] |= (qdep  & 0xff) << 24;
-	cmd->data[1]  = devid;
-	cmd->data[1] |= (pasid & 0xff) << 16;
-	cmd->data[2]  = lower_32_bits(address);
-	cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
-	cmd->data[3]  = upper_32_bits(address);
-	if (size)
-		cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
 	CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
 }
 
@@ -1341,7 +1320,7 @@ static void amd_iommu_flush_tlb_all(struct amd_iommu *iommu)
 	for (dom_id = 0; dom_id <= last_bdf; ++dom_id) {
 		struct iommu_cmd cmd;
 		build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
-				      dom_id, 1);
+				      dom_id, IOMMU_NO_PASID, false);
 		iommu_queue_command(iommu, &cmd);
 	}
 
@@ -1353,7 +1332,7 @@ static void amd_iommu_flush_tlb_domid(struct amd_iommu *iommu, u32 dom_id)
 	struct iommu_cmd cmd;
 
 	build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
-			      dom_id, 1);
+			      dom_id, IOMMU_NO_PASID, false);
 	iommu_queue_command(iommu, &cmd);
 
 	iommu_completion_wait(iommu);
@@ -1392,7 +1371,7 @@ static void amd_iommu_flush_irt_all(struct amd_iommu *iommu)
 	iommu_completion_wait(iommu);
 }
 
-void iommu_flush_all_caches(struct amd_iommu *iommu)
+void amd_iommu_flush_all_caches(struct amd_iommu *iommu)
 {
 	if (check_feature(FEATURE_IA)) {
 		amd_iommu_flush_all(iommu);
@@ -1406,8 +1385,8 @@ void iommu_flush_all_caches(struct amd_iommu *iommu)
 /*
  * Command send function for flushing on-device TLB
  */
-static int device_flush_iotlb(struct iommu_dev_data *dev_data,
-			      u64 address, size_t size)
+static int device_flush_iotlb(struct iommu_dev_data *dev_data, u64 address,
+			      size_t size, ioasid_t pasid, bool gn)
 {
 	struct amd_iommu *iommu;
 	struct iommu_cmd cmd;
@@ -1418,7 +1397,8 @@ static int device_flush_iotlb(struct iommu_dev_data *dev_data,
 	if (!iommu)
 		return -EINVAL;
 
-	build_inv_iotlb_pages(&cmd, dev_data->devid, qdep, address, size);
+	build_inv_iotlb_pages(&cmd, dev_data->devid, qdep, address,
+			      size, pasid, gn);
 
 	return iommu_queue_command(iommu, &cmd);
 }
@@ -1464,8 +1444,11 @@ static int device_flush_dte(struct iommu_dev_data *dev_data)
 			return ret;
 	}
 
-	if (dev_data->ats_enabled)
-		ret = device_flush_iotlb(dev_data, 0, ~0UL);
+	if (dev_data->ats_enabled) {
+		/* Invalidate the entire contents of an IOTLB */
+		ret = device_flush_iotlb(dev_data, 0, ~0UL,
+					 IOMMU_NO_PASID, false);
+	}
 
 	return ret;
 }
@@ -1476,13 +1459,18 @@ static int device_flush_dte(struct iommu_dev_data *dev_data)
  * page. Otherwise it flushes the whole TLB of the IOMMU.
  */
 static void __domain_flush_pages(struct protection_domain *domain,
-				 u64 address, size_t size, int pde)
+				 u64 address, size_t size)
 {
 	struct iommu_dev_data *dev_data;
 	struct iommu_cmd cmd;
 	int ret = 0, i;
+	ioasid_t pasid = IOMMU_NO_PASID;
+	bool gn = false;
+
+	if (pdom_is_v2_pgtbl_mode(domain))
+		gn = true;
 
-	build_inv_iommu_pages(&cmd, address, size, domain->id, pde);
+	build_inv_iommu_pages(&cmd, address, size, domain->id, pasid, gn);
 
 	for (i = 0; i < amd_iommu_get_num_iommus(); ++i) {
 		if (!domain->dev_iommu[i])
@@ -1500,17 +1488,21 @@ static void __domain_flush_pages(struct protection_domain *domain,
 		if (!dev_data->ats_enabled)
 			continue;
 
-		ret |= device_flush_iotlb(dev_data, address, size);
+		ret |= device_flush_iotlb(dev_data, address, size, pasid, gn);
 	}
 
 	WARN_ON(ret);
 }
 
-static void domain_flush_pages(struct protection_domain *domain,
-			       u64 address, size_t size, int pde)
+void amd_iommu_domain_flush_pages(struct protection_domain *domain,
+				  u64 address, size_t size)
 {
 	if (likely(!amd_iommu_np_cache)) {
-		__domain_flush_pages(domain, address, size, pde);
+		__domain_flush_pages(domain, address, size);
+
+		/* Wait until IOMMU TLB and all device IOTLB flushes are complete */
+		amd_iommu_domain_flush_complete(domain);
+
 		return;
 	}
 
@@ -1543,16 +1535,20 @@ static void domain_flush_pages(struct protection_domain *domain,
 
 		flush_size = 1ul << min_alignment;
 
-		__domain_flush_pages(domain, address, flush_size, pde);
+		__domain_flush_pages(domain, address, flush_size);
 		address += flush_size;
 		size -= flush_size;
 	}
+
+	/* Wait until IOMMU TLB and all device IOTLB flushes are complete */
+	amd_iommu_domain_flush_complete(domain);
 }
 
 /* Flush the whole IO/TLB for a given protection domain - including PDE */
-void amd_iommu_domain_flush_tlb_pde(struct protection_domain *domain)
+static void amd_iommu_domain_flush_all(struct protection_domain *domain)
 {
-	domain_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 1);
+	amd_iommu_domain_flush_pages(domain, 0,
+				     CMD_INV_IOMMU_ALL_PAGES_ADDRESS);
 }
 
 void amd_iommu_domain_flush_complete(struct protection_domain *domain)
@@ -1579,8 +1575,7 @@ static void domain_flush_np_cache(struct protection_domain *domain,
 		unsigned long flags;
 
 		spin_lock_irqsave(&domain->lock, flags);
-		domain_flush_pages(domain, iova, size, 1);
-		amd_iommu_domain_flush_complete(domain);
+		amd_iommu_domain_flush_pages(domain, iova, size);
 		spin_unlock_irqrestore(&domain->lock, flags);
 	}
 }
@@ -1858,11 +1853,8 @@ static void do_detach(struct iommu_dev_data *dev_data)
 	/* Flush the DTE entry */
 	device_flush_dte(dev_data);
 
-	/* Flush IOTLB */
-	amd_iommu_domain_flush_tlb_pde(domain);
-
-	/* Wait for the flushes to finish */
-	amd_iommu_domain_flush_complete(domain);
+	/* Flush IOTLB and wait for the flushes to finish */
+	amd_iommu_domain_flush_all(domain);
 
 	/* decrease reference counters - needs to happen after the flushes */
 	domain->dev_iommu[iommu->index] -= 1;
@@ -1896,15 +1888,6 @@ static int attach_device(struct device *dev,
 
 	do_attach(dev_data, domain);
 
-	/*
-	 * We might boot into a crash-kernel here. The crashed kernel
-	 * left the caches in the IOMMU dirty. So we have to flush
-	 * here to evict all dirty stuff.
-	 */
-	amd_iommu_domain_flush_tlb_pde(domain);
-
-	amd_iommu_domain_flush_complete(domain);
-
 out:
 	spin_unlock(&dev_data->lock);
 
@@ -2048,8 +2031,7 @@ void amd_iommu_domain_update(struct protection_domain *domain)
 	amd_iommu_update_and_flush_device_table(domain);
 
 	/* Flush domain TLB(s) and wait for completion */
-	amd_iommu_domain_flush_tlb_pde(domain);
-	amd_iommu_domain_flush_complete(domain);
+	amd_iommu_domain_flush_all(domain);
 }
 
 /*****************************************************************************
@@ -2482,10 +2464,9 @@ static int amd_iommu_set_dirty_tracking(struct iommu_domain *domain,
 	}
 
 	/* Flush IOTLB to mark IOPTE dirty on the next translation(s) */
-	if (domain_flush) {
-		amd_iommu_domain_flush_tlb_pde(pdomain);
-		amd_iommu_domain_flush_complete(pdomain);
-	}
+	if (domain_flush)
+		amd_iommu_domain_flush_all(pdomain);
+
 	pdomain->dirty_tracking = enable;
 	spin_unlock_irqrestore(&pdomain->lock, flags);
 
@@ -2588,8 +2569,7 @@ static void amd_iommu_flush_iotlb_all(struct iommu_domain *domain)
 	unsigned long flags;
 
 	spin_lock_irqsave(&dom->lock, flags);
-	amd_iommu_domain_flush_tlb_pde(dom);
-	amd_iommu_domain_flush_complete(dom);
+	amd_iommu_domain_flush_all(dom);
 	spin_unlock_irqrestore(&dom->lock, flags);
 }
 
@@ -2600,8 +2580,8 @@ static void amd_iommu_iotlb_sync(struct iommu_domain *domain,
 	unsigned long flags;
 
 	spin_lock_irqsave(&dom->lock, flags);
-	domain_flush_pages(dom, gather->start, gather->end - gather->start + 1, 1);
-	amd_iommu_domain_flush_complete(dom);
+	amd_iommu_domain_flush_pages(dom, gather->start,
+				     gather->end - gather->start + 1);
 	spin_unlock_irqrestore(&dom->lock, flags);
 }
 
@@ -2635,7 +2615,7 @@ static bool amd_iommu_enforce_cache_coherency(struct iommu_domain *domain)
 	return true;
 }
 
-const struct iommu_dirty_ops amd_dirty_ops = {
+static const struct iommu_dirty_ops amd_dirty_ops = {
 	.set_dirty_tracking = amd_iommu_set_dirty_tracking,
 	.read_and_clear_dirty = amd_iommu_read_and_clear_dirty,
 };
@@ -2666,7 +2646,7 @@ const struct iommu_ops amd_iommu_ops = {
 };
 
 static int __flush_pasid(struct protection_domain *domain, u32 pasid,
-			 u64 address, bool size)
+			 u64 address, size_t size)
 {
 	struct iommu_dev_data *dev_data;
 	struct iommu_cmd cmd;
@@ -2675,7 +2655,7 @@ static int __flush_pasid(struct protection_domain *domain, u32 pasid,
 	if (!(domain->flags & PD_IOMMUV2_MASK))
 		return -EINVAL;
 
-	build_inv_iommu_pasid(&cmd, domain->id, pasid, address, size);
+	build_inv_iommu_pages(&cmd, address, size, domain->id, pasid, true);
 
 	/*
 	 * IOMMU TLB needs to be flushed before Device TLB to
@@ -2709,8 +2689,8 @@ static int __flush_pasid(struct protection_domain *domain, u32 pasid,
 		iommu = rlookup_amd_iommu(dev_data->dev);
 		if (!iommu)
 			continue;
-		build_inv_iotlb_pasid(&cmd, dev_data->devid, pasid,
-				      qdep, address, size);
+		build_inv_iotlb_pages(&cmd, dev_data->devid, qdep,
+				      address, size, pasid, true);
 
 		ret = iommu_queue_command(iommu, &cmd);
 		if (ret != 0)
@@ -2730,7 +2710,7 @@ out:
 static int __amd_iommu_flush_page(struct protection_domain *domain, u32 pasid,
 				  u64 address)
 {
-	return __flush_pasid(domain, pasid, address, false);
+	return __flush_pasid(domain, pasid, address, PAGE_SIZE);
 }
 
 int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid,
@@ -2749,8 +2729,7 @@ int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid,
 
 static int __amd_iommu_flush_tlb(struct protection_domain *domain, u32 pasid)
 {
-	return __flush_pasid(domain, pasid, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
-			     true);
+	return __flush_pasid(domain, pasid, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS);
 }
 
 int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid)
@@ -3111,8 +3090,8 @@ out:
 	return index;
 }
 
-static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
-			  struct irte_ga *irte)
+static int __modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
+			    struct irte_ga *irte)
 {
 	struct irq_remap_table *table;
 	struct irte_ga *entry;
@@ -3139,6 +3118,18 @@ static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
 
 	raw_spin_unlock_irqrestore(&table->lock, flags);
 
+	return 0;
+}
+
+static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
+			  struct irte_ga *irte)
+{
+	bool ret;
+
+	ret = __modify_irte_ga(iommu, devid, index, irte);
+	if (ret)
+		return ret;
+
 	iommu_flush_irt_and_complete(iommu, devid);
 
 	return 0;
@@ -3822,8 +3813,8 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data)
 	}
 	entry->lo.fields_vapic.is_run = is_run;
 
-	return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
-			      ir_data->irq_2_irte.index, entry);
+	return __modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
+				ir_data->irq_2_irte.index, entry);
 }
 EXPORT_SYMBOL(amd_iommu_update_ga);
 #endif
diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c
index ee05f4824bfa..ef3ee95706da 100644
--- a/drivers/iommu/apple-dart.c
+++ b/drivers/iommu/apple-dart.c
@@ -81,6 +81,7 @@
 #define DART_T8020_TCR_BYPASS_DAPF      BIT(12)
 
 #define DART_T8020_TTBR       0x200
+#define DART_T8020_USB4_TTBR  0x400
 #define DART_T8020_TTBR_VALID BIT(31)
 #define DART_T8020_TTBR_ADDR_FIELD_SHIFT 0
 #define DART_T8020_TTBR_SHIFT 12
@@ -368,12 +369,14 @@ apple_dart_t8020_hw_stream_command(struct apple_dart_stream_map *stream_map,
 			     u32 command)
 {
 	unsigned long flags;
-	int ret;
+	int ret, i;
 	u32 command_reg;
 
 	spin_lock_irqsave(&stream_map->dart->lock, flags);
 
-	writel(stream_map->sidmap[0], stream_map->dart->regs + DART_T8020_STREAM_SELECT);
+	for (i = 0; i < BITS_TO_U32(stream_map->dart->num_streams); i++)
+		writel(stream_map->sidmap[i],
+		       stream_map->dart->regs + DART_T8020_STREAM_SELECT + 4 * i);
 	writel(command, stream_map->dart->regs + DART_T8020_STREAM_COMMAND);
 
 	ret = readl_poll_timeout_atomic(
@@ -740,7 +743,6 @@ static void apple_dart_release_device(struct device *dev)
 {
 	struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev);
 
-	dev_iommu_priv_set(dev, NULL);
 	kfree(cfg);
 }
 
@@ -908,7 +910,7 @@ static struct iommu_group *apple_dart_device_group(struct device *dev)
 
 		ret = apple_dart_merge_master_cfg(group_master_cfg, cfg);
 		if (ret) {
-			dev_err(dev, "Failed to merge DART IOMMU grups.\n");
+			dev_err(dev, "Failed to merge DART IOMMU groups.\n");
 			iommu_group_put(group);
 			res = ERR_PTR(ret);
 			goto out;
@@ -1215,6 +1217,33 @@ static const struct apple_dart_hw apple_dart_hw_t8103 = {
 	.ttbr_shift = DART_T8020_TTBR_SHIFT,
 	.ttbr_count = 4,
 };
+
+static const struct apple_dart_hw apple_dart_hw_t8103_usb4 = {
+	.type = DART_T8020,
+	.irq_handler = apple_dart_t8020_irq,
+	.invalidate_tlb = apple_dart_t8020_hw_invalidate_tlb,
+	.oas = 36,
+	.fmt = APPLE_DART,
+	.max_sid_count = 64,
+
+	.enable_streams = DART_T8020_STREAMS_ENABLE,
+	.lock = DART_T8020_CONFIG,
+	.lock_bit = DART_T8020_CONFIG_LOCK,
+
+	.error = DART_T8020_ERROR,
+
+	.tcr = DART_T8020_TCR,
+	.tcr_enabled = DART_T8020_TCR_TRANSLATE_ENABLE,
+	.tcr_disabled = 0,
+	.tcr_bypass = 0,
+
+	.ttbr = DART_T8020_USB4_TTBR,
+	.ttbr_valid = DART_T8020_TTBR_VALID,
+	.ttbr_addr_field_shift = DART_T8020_TTBR_ADDR_FIELD_SHIFT,
+	.ttbr_shift = DART_T8020_TTBR_SHIFT,
+	.ttbr_count = 4,
+};
+
 static const struct apple_dart_hw apple_dart_hw_t6000 = {
 	.type = DART_T6000,
 	.irq_handler = apple_dart_t8020_irq,
@@ -1272,7 +1301,7 @@ static __maybe_unused int apple_dart_suspend(struct device *dev)
 	unsigned int sid, idx;
 
 	for (sid = 0; sid < dart->num_streams; sid++) {
-		dart->save_tcr[sid] = readl_relaxed(dart->regs + DART_TCR(dart, sid));
+		dart->save_tcr[sid] = readl(dart->regs + DART_TCR(dart, sid));
 		for (idx = 0; idx < dart->hw->ttbr_count; idx++)
 			dart->save_ttbr[sid][idx] =
 				readl(dart->regs + DART_TTBR(dart, sid, idx));
@@ -1307,6 +1336,7 @@ static DEFINE_SIMPLE_DEV_PM_OPS(apple_dart_pm_ops, apple_dart_suspend, apple_dar
 
 static const struct of_device_id apple_dart_of_match[] = {
 	{ .compatible = "apple,t8103-dart", .data = &apple_dart_hw_t8103 },
+	{ .compatible = "apple,t8103-usb4-dart", .data = &apple_dart_hw_t8103_usb4 },
 	{ .compatible = "apple,t8110-dart", .data = &apple_dart_hw_t8110 },
 	{ .compatible = "apple,t6000-dart", .data = &apple_dart_hw_t6000 },
 	{},
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
index 353248ab18e7..4a27fbdb2d84 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
@@ -246,7 +246,8 @@ static void arm_smmu_mm_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn,
 						    smmu_domain);
 	}
 
-	arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, start, size);
+	arm_smmu_atc_inv_domain(smmu_domain, mm_get_enqcmd_pasid(mm), start,
+				size);
 }
 
 static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
@@ -264,10 +265,11 @@ static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 	 * DMA may still be running. Keep the cd valid to avoid C_BAD_CD events,
 	 * but disable translation.
 	 */
-	arm_smmu_update_ctx_desc_devices(smmu_domain, mm->pasid, &quiet_cd);
+	arm_smmu_update_ctx_desc_devices(smmu_domain, mm_get_enqcmd_pasid(mm),
+					 &quiet_cd);
 
 	arm_smmu_tlb_inv_asid(smmu_domain->smmu, smmu_mn->cd->asid);
-	arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, 0, 0);
+	arm_smmu_atc_inv_domain(smmu_domain, mm_get_enqcmd_pasid(mm), 0, 0);
 
 	smmu_mn->cleared = true;
 	mutex_unlock(&sva_lock);
@@ -290,10 +292,8 @@ arm_smmu_mmu_notifier_get(struct arm_smmu_domain *smmu_domain,
 			  struct mm_struct *mm)
 {
 	int ret;
-	unsigned long flags;
 	struct arm_smmu_ctx_desc *cd;
 	struct arm_smmu_mmu_notifier *smmu_mn;
-	struct arm_smmu_master *master;
 
 	list_for_each_entry(smmu_mn, &smmu_domain->mmu_notifiers, list) {
 		if (smmu_mn->mn.mm == mm) {
@@ -323,25 +323,9 @@ arm_smmu_mmu_notifier_get(struct arm_smmu_domain *smmu_domain,
 		goto err_free_cd;
 	}
 
-	spin_lock_irqsave(&smmu_domain->devices_lock, flags);
-	list_for_each_entry(master, &smmu_domain->devices, domain_head) {
-		ret = arm_smmu_write_ctx_desc(master, mm->pasid, cd);
-		if (ret) {
-			list_for_each_entry_from_reverse(master, &smmu_domain->devices, domain_head)
-				arm_smmu_write_ctx_desc(master, mm->pasid, NULL);
-			break;
-		}
-	}
-	spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
-	if (ret)
-		goto err_put_notifier;
-
 	list_add(&smmu_mn->list, &smmu_domain->mmu_notifiers);
 	return smmu_mn;
 
-err_put_notifier:
-	/* Frees smmu_mn */
-	mmu_notifier_put(&smmu_mn->mn);
 err_free_cd:
 	arm_smmu_free_shared_cd(cd);
 	return ERR_PTR(ret);
@@ -358,15 +342,14 @@ static void arm_smmu_mmu_notifier_put(struct arm_smmu_mmu_notifier *smmu_mn)
 
 	list_del(&smmu_mn->list);
 
-	arm_smmu_update_ctx_desc_devices(smmu_domain, mm->pasid, NULL);
-
 	/*
 	 * If we went through clear(), we've already invalidated, and no
 	 * new TLB entry can have been formed.
 	 */
 	if (!smmu_mn->cleared) {
 		arm_smmu_tlb_inv_asid(smmu_domain->smmu, cd->asid);
-		arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, 0, 0);
+		arm_smmu_atc_inv_domain(smmu_domain, mm_get_enqcmd_pasid(mm), 0,
+					0);
 	}
 
 	/* Frees smmu_mn */
@@ -374,7 +357,8 @@ static void arm_smmu_mmu_notifier_put(struct arm_smmu_mmu_notifier *smmu_mn)
 	arm_smmu_free_shared_cd(cd);
 }
 
-static int __arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm)
+static int __arm_smmu_sva_bind(struct device *dev, ioasid_t pasid,
+			       struct mm_struct *mm)
 {
 	int ret;
 	struct arm_smmu_bond *bond;
@@ -397,9 +381,15 @@ static int __arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm)
 		goto err_free_bond;
 	}
 
+	ret = arm_smmu_write_ctx_desc(master, pasid, bond->smmu_mn->cd);
+	if (ret)
+		goto err_put_notifier;
+
 	list_add(&bond->list, &master->bonds);
 	return 0;
 
+err_put_notifier:
+	arm_smmu_mmu_notifier_put(bond->smmu_mn);
 err_free_bond:
 	kfree(bond);
 	return ret;
@@ -561,6 +551,9 @@ void arm_smmu_sva_remove_dev_pasid(struct iommu_domain *domain,
 	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
 
 	mutex_lock(&sva_lock);
+
+	arm_smmu_write_ctx_desc(master, id, NULL);
+
 	list_for_each_entry(t, &master->bonds, list) {
 		if (t->mm == mm) {
 			bond = t;
@@ -583,7 +576,7 @@ static int arm_smmu_sva_set_dev_pasid(struct iommu_domain *domain,
 	struct mm_struct *mm = domain->mm;
 
 	mutex_lock(&sva_lock);
-	ret = __arm_smmu_sva_bind(dev, mm);
+	ret = __arm_smmu_sva_bind(dev, id, mm);
 	mutex_unlock(&sva_lock);
 
 	return ret;
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 7445454c2af2..0ffb1cf17e0b 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -1063,6 +1063,7 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid,
 	bool cd_live;
 	__le64 *cdptr;
 	struct arm_smmu_ctx_desc_cfg *cd_table = &master->cd_table;
+	struct arm_smmu_device *smmu = master->smmu;
 
 	if (WARN_ON(ssid >= (1 << cd_table->s1cdmax)))
 		return -E2BIG;
@@ -1077,6 +1078,8 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid,
 	if (!cd) { /* (5) */
 		val = 0;
 	} else if (cd == &quiet_cd) { /* (4) */
+		if (!(smmu->features & ARM_SMMU_FEAT_STALL_FORCE))
+			val &= ~(CTXDESC_CD_0_S | CTXDESC_CD_0_R);
 		val |= CTXDESC_CD_0_TCR_EPD0;
 	} else if (cd_live) { /* (3) */
 		val &= ~CTXDESC_CD_0_ASID;
@@ -1249,7 +1252,7 @@ static void arm_smmu_sync_ste_for_sid(struct arm_smmu_device *smmu, u32 sid)
 }
 
 static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
-				      __le64 *dst)
+				      struct arm_smmu_ste *dst)
 {
 	/*
 	 * This is hideously complicated, but we only really care about
@@ -1267,12 +1270,12 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 	 * 2. Write everything apart from dword 0, sync, write dword 0, sync
 	 * 3. Update Config, sync
 	 */
-	u64 val = le64_to_cpu(dst[0]);
+	u64 val = le64_to_cpu(dst->data[0]);
 	bool ste_live = false;
-	struct arm_smmu_device *smmu = NULL;
+	struct arm_smmu_device *smmu = master->smmu;
 	struct arm_smmu_ctx_desc_cfg *cd_table = NULL;
 	struct arm_smmu_s2_cfg *s2_cfg = NULL;
-	struct arm_smmu_domain *smmu_domain = NULL;
+	struct arm_smmu_domain *smmu_domain = master->domain;
 	struct arm_smmu_cmdq_ent prefetch_cmd = {
 		.opcode		= CMDQ_OP_PREFETCH_CFG,
 		.prefetch	= {
@@ -1280,18 +1283,12 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 		},
 	};
 
-	if (master) {
-		smmu_domain = master->domain;
-		smmu = master->smmu;
-	}
-
 	if (smmu_domain) {
 		switch (smmu_domain->stage) {
 		case ARM_SMMU_DOMAIN_S1:
 			cd_table = &master->cd_table;
 			break;
 		case ARM_SMMU_DOMAIN_S2:
-		case ARM_SMMU_DOMAIN_NESTED:
 			s2_cfg = &smmu_domain->s2_cfg;
 			break;
 		default:
@@ -1325,10 +1322,10 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 		else
 			val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS);
 
-		dst[0] = cpu_to_le64(val);
-		dst[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG,
+		dst->data[0] = cpu_to_le64(val);
+		dst->data[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG,
 						STRTAB_STE_1_SHCFG_INCOMING));
-		dst[2] = 0; /* Nuke the VMID */
+		dst->data[2] = 0; /* Nuke the VMID */
 		/*
 		 * The SMMU can perform negative caching, so we must sync
 		 * the STE regardless of whether the old value was live.
@@ -1343,7 +1340,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 			STRTAB_STE_1_STRW_EL2 : STRTAB_STE_1_STRW_NSEL1;
 
 		BUG_ON(ste_live);
-		dst[1] = cpu_to_le64(
+		dst->data[1] = cpu_to_le64(
 			 FIELD_PREP(STRTAB_STE_1_S1DSS, STRTAB_STE_1_S1DSS_SSID0) |
 			 FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) |
 			 FIELD_PREP(STRTAB_STE_1_S1COR, STRTAB_STE_1_S1C_CACHE_WBRA) |
@@ -1352,7 +1349,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 
 		if (smmu->features & ARM_SMMU_FEAT_STALLS &&
 		    !master->stall_enabled)
-			dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
+			dst->data[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
 
 		val |= (cd_table->cdtab_dma & STRTAB_STE_0_S1CTXPTR_MASK) |
 			FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S1_TRANS) |
@@ -1362,7 +1359,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 
 	if (s2_cfg) {
 		BUG_ON(ste_live);
-		dst[2] = cpu_to_le64(
+		dst->data[2] = cpu_to_le64(
 			 FIELD_PREP(STRTAB_STE_2_S2VMID, s2_cfg->vmid) |
 			 FIELD_PREP(STRTAB_STE_2_VTCR, s2_cfg->vtcr) |
 #ifdef __BIG_ENDIAN
@@ -1371,18 +1368,18 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 			 STRTAB_STE_2_S2PTW | STRTAB_STE_2_S2AA64 |
 			 STRTAB_STE_2_S2R);
 
-		dst[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK);
+		dst->data[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK);
 
 		val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S2_TRANS);
 	}
 
 	if (master->ats_enabled)
-		dst[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_EATS,
+		dst->data[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_EATS,
 						 STRTAB_STE_1_EATS_TRANS));
 
 	arm_smmu_sync_ste_for_sid(smmu, sid);
 	/* See comment in arm_smmu_write_ctx_desc() */
-	WRITE_ONCE(dst[0], cpu_to_le64(val));
+	WRITE_ONCE(dst->data[0], cpu_to_le64(val));
 	arm_smmu_sync_ste_for_sid(smmu, sid);
 
 	/* It's likely that we'll want to use the new STE soon */
@@ -1390,7 +1387,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 		arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd);
 }
 
-static void arm_smmu_init_bypass_stes(__le64 *strtab, unsigned int nent, bool force)
+static void arm_smmu_init_bypass_stes(struct arm_smmu_ste *strtab,
+				      unsigned int nent, bool force)
 {
 	unsigned int i;
 	u64 val = STRTAB_STE_0_V;
@@ -1401,11 +1399,11 @@ static void arm_smmu_init_bypass_stes(__le64 *strtab, unsigned int nent, bool fo
 		val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS);
 
 	for (i = 0; i < nent; ++i) {
-		strtab[0] = cpu_to_le64(val);
-		strtab[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG,
-						   STRTAB_STE_1_SHCFG_INCOMING));
-		strtab[2] = 0;
-		strtab += STRTAB_STE_DWORDS;
+		strtab->data[0] = cpu_to_le64(val);
+		strtab->data[1] = cpu_to_le64(FIELD_PREP(
+			STRTAB_STE_1_SHCFG, STRTAB_STE_1_SHCFG_INCOMING));
+		strtab->data[2] = 0;
+		strtab++;
 	}
 }
 
@@ -2171,7 +2169,6 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 		fmt = ARM_64_LPAE_S1;
 		finalise_stage_fn = arm_smmu_domain_finalise_s1;
 		break;
-	case ARM_SMMU_DOMAIN_NESTED:
 	case ARM_SMMU_DOMAIN_S2:
 		ias = smmu->ias;
 		oas = smmu->oas;
@@ -2209,26 +2206,23 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 	return 0;
 }
 
-static __le64 *arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid)
+static struct arm_smmu_ste *
+arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid)
 {
-	__le64 *step;
 	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
 
 	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
-		struct arm_smmu_strtab_l1_desc *l1_desc;
-		int idx;
+		unsigned int idx1, idx2;
 
 		/* Two-level walk */
-		idx = (sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS;
-		l1_desc = &cfg->l1_desc[idx];
-		idx = (sid & ((1 << STRTAB_SPLIT) - 1)) * STRTAB_STE_DWORDS;
-		step = &l1_desc->l2ptr[idx];
+		idx1 = (sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS;
+		idx2 = sid & ((1 << STRTAB_SPLIT) - 1);
+		return &cfg->l1_desc[idx1].l2ptr[idx2];
 	} else {
 		/* Simple linear lookup */
-		step = &cfg->strtab[sid * STRTAB_STE_DWORDS];
+		return (struct arm_smmu_ste *)&cfg
+			       ->strtab[sid * STRTAB_STE_DWORDS];
 	}
-
-	return step;
 }
 
 static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master)
@@ -2238,7 +2232,8 @@ static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master)
 
 	for (i = 0; i < master->num_streams; ++i) {
 		u32 sid = master->streams[i].id;
-		__le64 *step = arm_smmu_get_step_for_sid(smmu, sid);
+		struct arm_smmu_ste *step =
+			arm_smmu_get_step_for_sid(smmu, sid);
 
 		/* Bridged PCI devices may end up with duplicated IDs */
 		for (j = 0; j < i; j++)
@@ -2649,9 +2644,6 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 	struct arm_smmu_master *master;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 
-	if (!fwspec || fwspec->ops != &arm_smmu_ops)
-		return ERR_PTR(-ENODEV);
-
 	if (WARN_ON_ONCE(dev_iommu_priv_get(dev)))
 		return ERR_PTR(-EBUSY);
 
@@ -2698,7 +2690,6 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 
 err_free_master:
 	kfree(master);
-	dev_iommu_priv_set(dev, NULL);
 	return ERR_PTR(ret);
 }
 
@@ -2742,7 +2733,7 @@ static int arm_smmu_enable_nesting(struct iommu_domain *domain)
 	if (smmu_domain->smmu)
 		ret = -EPERM;
 	else
-		smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED;
+		smmu_domain->stage = ARM_SMMU_DOMAIN_S2;
 	mutex_unlock(&smmu_domain->init_mutex);
 
 	return ret;
@@ -3769,7 +3760,7 @@ static void arm_smmu_rmr_install_bypass_ste(struct arm_smmu_device *smmu)
 	iort_get_rmr_sids(dev_fwnode(smmu->dev), &rmr_list);
 
 	list_for_each_entry(e, &rmr_list, list) {
-		__le64 *step;
+		struct arm_smmu_ste *step;
 		struct iommu_iort_rmr_data *rmr;
 		int ret, i;
 
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index 925ac6a47bce..65fb388d5173 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -206,6 +206,11 @@
 #define STRTAB_L1_DESC_L2PTR_MASK	GENMASK_ULL(51, 6)
 
 #define STRTAB_STE_DWORDS		8
+
+struct arm_smmu_ste {
+	__le64 data[STRTAB_STE_DWORDS];
+};
+
 #define STRTAB_STE_0_V			(1UL << 0)
 #define STRTAB_STE_0_CFG		GENMASK_ULL(3, 1)
 #define STRTAB_STE_0_CFG_ABORT		0
@@ -571,7 +576,7 @@ struct arm_smmu_priq {
 struct arm_smmu_strtab_l1_desc {
 	u8				span;
 
-	__le64				*l2ptr;
+	struct arm_smmu_ste		*l2ptr;
 	dma_addr_t			l2ptr_dma;
 };
 
@@ -710,7 +715,6 @@ struct arm_smmu_master {
 enum arm_smmu_domain_stage {
 	ARM_SMMU_DOMAIN_S1 = 0,
 	ARM_SMMU_DOMAIN_S2,
-	ARM_SMMU_DOMAIN_NESTED,
 	ARM_SMMU_DOMAIN_BYPASS,
 };
 
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index 549ae4dba3a6..8b04ece00420 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -243,8 +243,10 @@ static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 
 static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = {
 	{ .compatible = "qcom,adreno" },
+	{ .compatible = "qcom,adreno-gmu" },
 	{ .compatible = "qcom,mdp4" },
 	{ .compatible = "qcom,mdss" },
+	{ .compatible = "qcom,qcm2290-mdss" },
 	{ .compatible = "qcom,sc7180-mdss" },
 	{ .compatible = "qcom,sc7180-mss-pil" },
 	{ .compatible = "qcom,sc7280-mdss" },
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index d6d1a2a55cc0..6317aaf7b3ab 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -82,6 +82,23 @@ static inline void arm_smmu_rpm_put(struct arm_smmu_device *smmu)
 		pm_runtime_put_autosuspend(smmu->dev);
 }
 
+static void arm_smmu_rpm_use_autosuspend(struct arm_smmu_device *smmu)
+{
+	/*
+	 * Setup an autosuspend delay to avoid bouncing runpm state.
+	 * Otherwise, if a driver for a suspended consumer device
+	 * unmaps buffers, it will runpm resume/suspend for each one.
+	 *
+	 * For example, when used by a GPU device, when an application
+	 * or game exits, it can trigger unmapping 100s or 1000s of
+	 * buffers.  With a runpm cycle for each buffer, that adds up
+	 * to 5-10sec worth of reprogramming the context bank, while
+	 * the system appears to be locked up to the user.
+	 */
+	pm_runtime_set_autosuspend_delay(smmu->dev, 20);
+	pm_runtime_use_autosuspend(smmu->dev);
+}
+
 static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
 {
 	return container_of(dom, struct arm_smmu_domain, domain);
@@ -392,8 +409,7 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
 {
 	u32 fsr, fsynr, cbfrsynra;
 	unsigned long iova;
-	struct iommu_domain *domain = dev;
-	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_domain *smmu_domain = dev;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	int idx = smmu_domain->cfg.cbndx;
 	int ret;
@@ -406,7 +422,7 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
 	iova = arm_smmu_cb_readq(smmu, idx, ARM_SMMU_CB_FAR);
 	cbfrsynra = arm_smmu_gr1_read(smmu, ARM_SMMU_GR1_CBFRSYNRA(idx));
 
-	ret = report_iommu_fault(domain, NULL, iova,
+	ret = report_iommu_fault(&smmu_domain->domain, NULL, iova,
 		fsynr & ARM_SMMU_FSYNR0_WNR ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ);
 
 	if (ret == -ENOSYS)
@@ -607,7 +623,7 @@ static int arm_smmu_alloc_context_bank(struct arm_smmu_domain *smmu_domain,
 	return __arm_smmu_alloc_bitmap(smmu->context_map, start, smmu->num_context_banks);
 }
 
-static int arm_smmu_init_domain_context(struct iommu_domain *domain,
+static int arm_smmu_init_domain_context(struct arm_smmu_domain *smmu_domain,
 					struct arm_smmu_device *smmu,
 					struct device *dev)
 {
@@ -616,7 +632,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	struct io_pgtable_ops *pgtbl_ops;
 	struct io_pgtable_cfg pgtbl_cfg;
 	enum io_pgtable_fmt fmt;
-	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct iommu_domain *domain = &smmu_domain->domain;
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
 	irqreturn_t (*context_fault)(int irq, void *dev);
 
@@ -624,12 +640,6 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	if (smmu_domain->smmu)
 		goto out_unlock;
 
-	if (domain->type == IOMMU_DOMAIN_IDENTITY) {
-		smmu_domain->stage = ARM_SMMU_DOMAIN_BYPASS;
-		smmu_domain->smmu = smmu;
-		goto out_unlock;
-	}
-
 	/*
 	 * Mapping the requested stage onto what we support is surprisingly
 	 * complicated, mainly because the spec allows S1+S2 SMMUs without
@@ -796,8 +806,8 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	else
 		context_fault = arm_smmu_context_fault;
 
-	ret = devm_request_irq(smmu->dev, irq, context_fault,
-			       IRQF_SHARED, "arm-smmu-context-fault", domain);
+	ret = devm_request_irq(smmu->dev, irq, context_fault, IRQF_SHARED,
+			       "arm-smmu-context-fault", smmu_domain);
 	if (ret < 0) {
 		dev_err(smmu->dev, "failed to request context IRQ %d (%u)\n",
 			cfg->irptndx, irq);
@@ -818,14 +828,13 @@ out_unlock:
 	return ret;
 }
 
-static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
+static void arm_smmu_destroy_domain_context(struct arm_smmu_domain *smmu_domain)
 {
-	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
 	int ret, irq;
 
-	if (!smmu || domain->type == IOMMU_DOMAIN_IDENTITY)
+	if (!smmu)
 		return;
 
 	ret = arm_smmu_rpm_get(smmu);
@@ -841,7 +850,7 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
 
 	if (cfg->irptndx != ARM_SMMU_INVALID_IRPTNDX) {
 		irq = smmu->irqs[cfg->irptndx];
-		devm_free_irq(smmu->dev, irq, domain);
+		devm_free_irq(smmu->dev, irq, smmu_domain);
 	}
 
 	free_io_pgtable_ops(smmu_domain->pgtbl_ops);
@@ -854,7 +863,7 @@ static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
 {
 	struct arm_smmu_domain *smmu_domain;
 
-	if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_IDENTITY) {
+	if (type != IOMMU_DOMAIN_UNMANAGED) {
 		if (using_legacy_binding || type != IOMMU_DOMAIN_DMA)
 			return NULL;
 	}
@@ -881,7 +890,7 @@ static void arm_smmu_domain_free(struct iommu_domain *domain)
 	 * Free the domain resources. We assume that all devices have
 	 * already been detached.
 	 */
-	arm_smmu_destroy_domain_context(domain);
+	arm_smmu_destroy_domain_context(smmu_domain);
 	kfree(smmu_domain);
 }
 
@@ -1081,21 +1090,14 @@ static void arm_smmu_master_free_smes(struct arm_smmu_master_cfg *cfg,
 	mutex_unlock(&smmu->stream_map_mutex);
 }
 
-static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
-				      struct arm_smmu_master_cfg *cfg,
-				      struct iommu_fwspec *fwspec)
+static void arm_smmu_master_install_s2crs(struct arm_smmu_master_cfg *cfg,
+					  enum arm_smmu_s2cr_type type,
+					  u8 cbndx, struct iommu_fwspec *fwspec)
 {
-	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_device *smmu = cfg->smmu;
 	struct arm_smmu_s2cr *s2cr = smmu->s2crs;
-	u8 cbndx = smmu_domain->cfg.cbndx;
-	enum arm_smmu_s2cr_type type;
 	int i, idx;
 
-	if (smmu_domain->stage == ARM_SMMU_DOMAIN_BYPASS)
-		type = S2CR_TYPE_BYPASS;
-	else
-		type = S2CR_TYPE_TRANS;
-
 	for_each_cfg_sme(cfg, fwspec, i, idx) {
 		if (type == s2cr[idx].type && cbndx == s2cr[idx].cbndx)
 			continue;
@@ -1105,7 +1107,6 @@ static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
 		s2cr[idx].cbndx = cbndx;
 		arm_smmu_write_s2cr(smmu, idx);
 	}
-	return 0;
 }
 
 static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
@@ -1116,11 +1117,6 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	struct arm_smmu_device *smmu;
 	int ret;
 
-	if (!fwspec || fwspec->ops != &arm_smmu_ops) {
-		dev_err(dev, "cannot attach to SMMU, is it on the same bus?\n");
-		return -ENXIO;
-	}
-
 	/*
 	 * FIXME: The arch/arm DMA API code tries to attach devices to its own
 	 * domains between of_xlate() and probe_device() - we have no way to cope
@@ -1139,7 +1135,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 		return ret;
 
 	/* Ensure that the domain is finalised */
-	ret = arm_smmu_init_domain_context(domain, smmu, dev);
+	ret = arm_smmu_init_domain_context(smmu_domain, smmu, dev);
 	if (ret < 0)
 		goto rpm_put;
 
@@ -1153,27 +1149,66 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	}
 
 	/* Looks ok, so add the device to the domain */
-	ret = arm_smmu_domain_add_master(smmu_domain, cfg, fwspec);
-
-	/*
-	 * Setup an autosuspend delay to avoid bouncing runpm state.
-	 * Otherwise, if a driver for a suspended consumer device
-	 * unmaps buffers, it will runpm resume/suspend for each one.
-	 *
-	 * For example, when used by a GPU device, when an application
-	 * or game exits, it can trigger unmapping 100s or 1000s of
-	 * buffers.  With a runpm cycle for each buffer, that adds up
-	 * to 5-10sec worth of reprogramming the context bank, while
-	 * the system appears to be locked up to the user.
-	 */
-	pm_runtime_set_autosuspend_delay(smmu->dev, 20);
-	pm_runtime_use_autosuspend(smmu->dev);
-
+	arm_smmu_master_install_s2crs(cfg, S2CR_TYPE_TRANS,
+				      smmu_domain->cfg.cbndx, fwspec);
+	arm_smmu_rpm_use_autosuspend(smmu);
 rpm_put:
 	arm_smmu_rpm_put(smmu);
 	return ret;
 }
 
+static int arm_smmu_attach_dev_type(struct device *dev,
+				    enum arm_smmu_s2cr_type type)
+{
+	struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct arm_smmu_device *smmu;
+	int ret;
+
+	if (!cfg)
+		return -ENODEV;
+	smmu = cfg->smmu;
+
+	ret = arm_smmu_rpm_get(smmu);
+	if (ret < 0)
+		return ret;
+
+	arm_smmu_master_install_s2crs(cfg, type, 0, fwspec);
+	arm_smmu_rpm_use_autosuspend(smmu);
+	arm_smmu_rpm_put(smmu);
+	return 0;
+}
+
+static int arm_smmu_attach_dev_identity(struct iommu_domain *domain,
+					struct device *dev)
+{
+	return arm_smmu_attach_dev_type(dev, S2CR_TYPE_BYPASS);
+}
+
+static const struct iommu_domain_ops arm_smmu_identity_ops = {
+	.attach_dev = arm_smmu_attach_dev_identity,
+};
+
+static struct iommu_domain arm_smmu_identity_domain = {
+	.type = IOMMU_DOMAIN_IDENTITY,
+	.ops = &arm_smmu_identity_ops,
+};
+
+static int arm_smmu_attach_dev_blocked(struct iommu_domain *domain,
+				       struct device *dev)
+{
+	return arm_smmu_attach_dev_type(dev, S2CR_TYPE_FAULT);
+}
+
+static const struct iommu_domain_ops arm_smmu_blocked_ops = {
+	.attach_dev = arm_smmu_attach_dev_blocked,
+};
+
+static struct iommu_domain arm_smmu_blocked_domain = {
+	.type = IOMMU_DOMAIN_BLOCKED,
+	.ops = &arm_smmu_blocked_ops,
+};
+
 static int arm_smmu_map_pages(struct iommu_domain *domain, unsigned long iova,
 			      phys_addr_t paddr, size_t pgsize, size_t pgcount,
 			      int prot, gfp_t gfp, size_t *mapped)
@@ -1357,10 +1392,8 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 		fwspec = dev_iommu_fwspec_get(dev);
 		if (ret)
 			goto out_free;
-	} else if (fwspec && fwspec->ops == &arm_smmu_ops) {
-		smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
 	} else {
-		return ERR_PTR(-ENODEV);
+		smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
 	}
 
 	ret = -EINVAL;
@@ -1427,7 +1460,6 @@ static void arm_smmu_release_device(struct device *dev)
 
 	arm_smmu_rpm_put(cfg->smmu);
 
-	dev_iommu_priv_set(dev, NULL);
 	kfree(cfg);
 }
 
@@ -1560,6 +1592,8 @@ static int arm_smmu_def_domain_type(struct device *dev)
 }
 
 static struct iommu_ops arm_smmu_ops = {
+	.identity_domain	= &arm_smmu_identity_domain,
+	.blocked_domain		= &arm_smmu_blocked_domain,
 	.capable		= arm_smmu_capable,
 	.domain_alloc		= arm_smmu_domain_alloc,
 	.probe_device		= arm_smmu_probe_device,
@@ -2161,7 +2195,8 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	err = iommu_device_register(&smmu->iommu, &arm_smmu_ops, dev);
+	err = iommu_device_register(&smmu->iommu, &arm_smmu_ops,
+				    using_legacy_binding ? NULL : dev);
 	if (err) {
 		dev_err(dev, "Failed to register iommu\n");
 		iommu_device_sysfs_remove(&smmu->iommu);
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h
index 703fd5817ec1..836ed6799a80 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.h
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h
@@ -361,7 +361,6 @@ enum arm_smmu_domain_stage {
 	ARM_SMMU_DOMAIN_S1 = 0,
 	ARM_SMMU_DOMAIN_S2,
 	ARM_SMMU_DOMAIN_NESTED,
-	ARM_SMMU_DOMAIN_BYPASS,
 };
 
 struct arm_smmu_domain {
diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
index 97b2122032b2..17a1c163fef6 100644
--- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c
+++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
@@ -79,16 +79,6 @@ static struct qcom_iommu_domain *to_qcom_iommu_domain(struct iommu_domain *dom)
 
 static const struct iommu_ops qcom_iommu_ops;
 
-static struct qcom_iommu_dev * to_iommu(struct device *dev)
-{
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-
-	if (!fwspec || fwspec->ops != &qcom_iommu_ops)
-		return NULL;
-
-	return dev_iommu_priv_get(dev);
-}
-
 static struct qcom_iommu_ctx * to_ctx(struct qcom_iommu_domain *d, unsigned asid)
 {
 	struct qcom_iommu_dev *qcom_iommu = d->iommu;
@@ -372,7 +362,7 @@ static void qcom_iommu_domain_free(struct iommu_domain *domain)
 
 static int qcom_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 {
-	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);
+	struct qcom_iommu_dev *qcom_iommu = dev_iommu_priv_get(dev);
 	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
 	int ret;
 
@@ -404,7 +394,7 @@ static int qcom_iommu_identity_attach(struct iommu_domain *identity_domain,
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 	struct qcom_iommu_domain *qcom_domain;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);
+	struct qcom_iommu_dev *qcom_iommu = dev_iommu_priv_get(dev);
 	unsigned int i;
 
 	if (domain == identity_domain || !domain)
@@ -535,7 +525,7 @@ static bool qcom_iommu_capable(struct device *dev, enum iommu_cap cap)
 
 static struct iommu_device *qcom_iommu_probe_device(struct device *dev)
 {
-	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);
+	struct qcom_iommu_dev *qcom_iommu = dev_iommu_priv_get(dev);
 	struct device_link *link;
 
 	if (!qcom_iommu)
@@ -900,8 +890,16 @@ static void qcom_iommu_device_remove(struct platform_device *pdev)
 static int __maybe_unused qcom_iommu_resume(struct device *dev)
 {
 	struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_bulk_prepare_enable(CLK_NUM, qcom_iommu->clks);
+	if (ret < 0)
+		return ret;
+
+	if (dev->pm_domain)
+		return qcom_scm_restore_sec_cfg(qcom_iommu->sec_id, 0);
 
-	return clk_bulk_prepare_enable(CLK_NUM, qcom_iommu->clks);
+	return ret;
 }
 
 static int __maybe_unused qcom_iommu_suspend(struct device *dev)
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index e59f50e11ea8..50ccc4f1ef81 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -29,6 +29,7 @@
 #include <linux/spinlock.h>
 #include <linux/swiotlb.h>
 #include <linux/vmalloc.h>
+#include <trace/events/swiotlb.h>
 
 #include "dma-iommu.h"
 
@@ -1156,6 +1157,8 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 			return DMA_MAPPING_ERROR;
 		}
 
+		trace_swiotlb_bounced(dev, phys, size);
+
 		aligned_size = iova_align(iovad, size);
 		phys = swiotlb_tbl_map_single(dev, phys, size, aligned_size,
 					      iova_mask(iovad), dir, attrs);
diff --git a/drivers/iommu/intel/debugfs.c b/drivers/iommu/intel/debugfs.c
index dee61e513be6..86b506af7daa 100644
--- a/drivers/iommu/intel/debugfs.c
+++ b/drivers/iommu/intel/debugfs.c
@@ -106,9 +106,6 @@ static const struct iommu_regset iommu_regs_64[] = {
 	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK8),
 	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE9),
 	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK9),
-	IOMMU_REGSET_ENTRY(VCCAP),
-	IOMMU_REGSET_ENTRY(VCMD),
-	IOMMU_REGSET_ENTRY(VCRSP),
 };
 
 static struct dentry *intel_iommu_debug;
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 897159dba47d..11652e0bcab3 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -46,9 +46,6 @@
 
 #define DEFAULT_DOMAIN_ADDRESS_WIDTH 57
 
-#define MAX_AGAW_WIDTH 64
-#define MAX_AGAW_PFN_WIDTH	(MAX_AGAW_WIDTH - VTD_PAGE_SHIFT)
-
 #define __DOMAIN_MAX_PFN(gaw)  ((((uint64_t)1) << ((gaw) - VTD_PAGE_SHIFT)) - 1)
 #define __DOMAIN_MAX_ADDR(gaw) ((((uint64_t)1) << (gaw)) - 1)
 
@@ -63,74 +60,6 @@
 
 #define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
 
-/* page table handling */
-#define LEVEL_STRIDE		(9)
-#define LEVEL_MASK		(((u64)1 << LEVEL_STRIDE) - 1)
-
-static inline int agaw_to_level(int agaw)
-{
-	return agaw + 2;
-}
-
-static inline int agaw_to_width(int agaw)
-{
-	return min_t(int, 30 + agaw * LEVEL_STRIDE, MAX_AGAW_WIDTH);
-}
-
-static inline int width_to_agaw(int width)
-{
-	return DIV_ROUND_UP(width - 30, LEVEL_STRIDE);
-}
-
-static inline unsigned int level_to_offset_bits(int level)
-{
-	return (level - 1) * LEVEL_STRIDE;
-}
-
-static inline int pfn_level_offset(u64 pfn, int level)
-{
-	return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK;
-}
-
-static inline u64 level_mask(int level)
-{
-	return -1ULL << level_to_offset_bits(level);
-}
-
-static inline u64 level_size(int level)
-{
-	return 1ULL << level_to_offset_bits(level);
-}
-
-static inline u64 align_to_level(u64 pfn, int level)
-{
-	return (pfn + level_size(level) - 1) & level_mask(level);
-}
-
-static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
-{
-	return 1UL << min_t(int, (lvl - 1) * LEVEL_STRIDE, MAX_AGAW_PFN_WIDTH);
-}
-
-/* VT-d pages must always be _smaller_ than MM pages. Otherwise things
-   are never going to work. */
-static inline unsigned long mm_to_dma_pfn_start(unsigned long mm_pfn)
-{
-	return mm_pfn << (PAGE_SHIFT - VTD_PAGE_SHIFT);
-}
-static inline unsigned long mm_to_dma_pfn_end(unsigned long mm_pfn)
-{
-	return ((mm_pfn + 1) << (PAGE_SHIFT - VTD_PAGE_SHIFT)) - 1;
-}
-static inline unsigned long page_to_dma_pfn(struct page *pg)
-{
-	return mm_to_dma_pfn_start(page_to_pfn(pg));
-}
-static inline unsigned long virt_to_dma_pfn(void *p)
-{
-	return page_to_dma_pfn(virt_to_page(p));
-}
-
 static void __init check_tylersburg_isoch(void);
 static int rwbf_quirk;
 
@@ -168,78 +97,6 @@ static phys_addr_t root_entry_uctp(struct root_entry *re)
 	return re->hi & VTD_PAGE_MASK;
 }
 
-static inline void context_set_present(struct context_entry *context)
-{
-	context->lo |= 1;
-}
-
-static inline void context_set_fault_enable(struct context_entry *context)
-{
-	context->lo &= (((u64)-1) << 2) | 1;
-}
-
-static inline void context_set_translation_type(struct context_entry *context,
-						unsigned long value)
-{
-	context->lo &= (((u64)-1) << 4) | 3;
-	context->lo |= (value & 3) << 2;
-}
-
-static inline void context_set_address_root(struct context_entry *context,
-					    unsigned long value)
-{
-	context->lo &= ~VTD_PAGE_MASK;
-	context->lo |= value & VTD_PAGE_MASK;
-}
-
-static inline void context_set_address_width(struct context_entry *context,
-					     unsigned long value)
-{
-	context->hi |= value & 7;
-}
-
-static inline void context_set_domain_id(struct context_entry *context,
-					 unsigned long value)
-{
-	context->hi |= (value & ((1 << 16) - 1)) << 8;
-}
-
-static inline void context_set_pasid(struct context_entry *context)
-{
-	context->lo |= CONTEXT_PASIDE;
-}
-
-static inline int context_domain_id(struct context_entry *c)
-{
-	return((c->hi >> 8) & 0xffff);
-}
-
-static inline void context_clear_entry(struct context_entry *context)
-{
-	context->lo = 0;
-	context->hi = 0;
-}
-
-static inline bool context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
-{
-	if (!iommu->copied_tables)
-		return false;
-
-	return test_bit(((long)bus << 8) | devfn, iommu->copied_tables);
-}
-
-static inline void
-set_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
-{
-	set_bit(((long)bus << 8) | devfn, iommu->copied_tables);
-}
-
-static inline void
-clear_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
-{
-	clear_bit(((long)bus << 8) | devfn, iommu->copied_tables);
-}
-
 /*
  * This domain is a statically identity mapping domain.
  *	1. This domain creats a static 1:1 mapping to all usable memory.
@@ -383,13 +240,12 @@ void free_pgtable_page(void *vaddr)
 	free_page((unsigned long)vaddr);
 }
 
-static inline int domain_type_is_si(struct dmar_domain *domain)
+static int domain_type_is_si(struct dmar_domain *domain)
 {
 	return domain->domain.type == IOMMU_DOMAIN_IDENTITY;
 }
 
-static inline int domain_pfn_supported(struct dmar_domain *domain,
-				       unsigned long pfn)
+static int domain_pfn_supported(struct dmar_domain *domain, unsigned long pfn)
 {
 	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
 
@@ -451,7 +307,7 @@ int iommu_calculate_agaw(struct intel_iommu *iommu)
 	return __iommu_calculate_agaw(iommu, DEFAULT_DOMAIN_ADDRESS_WIDTH);
 }
 
-static inline bool iommu_paging_structure_coherency(struct intel_iommu *iommu)
+static bool iommu_paging_structure_coherency(struct intel_iommu *iommu)
 {
 	return sm_supported(iommu) ?
 			ecap_smpwc(iommu->ecap) : ecap_coherent(iommu->ecap);
@@ -540,8 +396,6 @@ static int domain_update_device_node(struct dmar_domain *domain)
 	return nid;
 }
 
-static void domain_update_iotlb(struct dmar_domain *domain);
-
 /* Return the super pagesize bitmap if supported. */
 static unsigned long domain_super_pgsize_bitmap(struct dmar_domain *domain)
 {
@@ -703,7 +557,7 @@ static bool iommu_is_dummy(struct intel_iommu *iommu, struct device *dev)
 	return false;
 }
 
-struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
+static struct intel_iommu *device_lookup_iommu(struct device *dev, u8 *bus, u8 *devfn)
 {
 	struct dmar_drhd_unit *drhd = NULL;
 	struct pci_dev *pdev = NULL;
@@ -1362,7 +1216,7 @@ domain_lookup_dev_info(struct dmar_domain *domain,
 	return NULL;
 }
 
-static void domain_update_iotlb(struct dmar_domain *domain)
+void domain_update_iotlb(struct dmar_domain *domain)
 {
 	struct dev_pasid_info *dev_pasid;
 	struct device_domain_info *info;
@@ -1512,6 +1366,46 @@ static void domain_flush_pasid_iotlb(struct intel_iommu *iommu,
 	spin_unlock_irqrestore(&domain->lock, flags);
 }
 
+static void __iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
+				    unsigned long pfn, unsigned int pages,
+				    int ih)
+{
+	unsigned int aligned_pages = __roundup_pow_of_two(pages);
+	unsigned long bitmask = aligned_pages - 1;
+	unsigned int mask = ilog2(aligned_pages);
+	u64 addr = (u64)pfn << VTD_PAGE_SHIFT;
+
+	/*
+	 * PSI masks the low order bits of the base address. If the
+	 * address isn't aligned to the mask, then compute a mask value
+	 * needed to ensure the target range is flushed.
+	 */
+	if (unlikely(bitmask & pfn)) {
+		unsigned long end_pfn = pfn + pages - 1, shared_bits;
+
+		/*
+		 * Since end_pfn <= pfn + bitmask, the only way bits
+		 * higher than bitmask can differ in pfn and end_pfn is
+		 * by carrying. This means after masking out bitmask,
+		 * high bits starting with the first set bit in
+		 * shared_bits are all equal in both pfn and end_pfn.
+		 */
+		shared_bits = ~(pfn ^ end_pfn) & ~bitmask;
+		mask = shared_bits ? __ffs(shared_bits) : BITS_PER_LONG;
+	}
+
+	/*
+	 * Fallback to domain selective flush if no PSI support or
+	 * the size is too big.
+	 */
+	if (!cap_pgsel_inv(iommu->cap) || mask > cap_max_amask_val(iommu->cap))
+		iommu->flush.flush_iotlb(iommu, did, 0, 0,
+					 DMA_TLB_DSI_FLUSH);
+	else
+		iommu->flush.flush_iotlb(iommu, did, addr | ih, mask,
+					 DMA_TLB_PSI_FLUSH);
+}
+
 static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 				  struct dmar_domain *domain,
 				  unsigned long pfn, unsigned int pages,
@@ -1528,42 +1422,10 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 	if (ih)
 		ih = 1 << 6;
 
-	if (domain->use_first_level) {
+	if (domain->use_first_level)
 		domain_flush_pasid_iotlb(iommu, domain, addr, pages, ih);
-	} else {
-		unsigned long bitmask = aligned_pages - 1;
-
-		/*
-		 * PSI masks the low order bits of the base address. If the
-		 * address isn't aligned to the mask, then compute a mask value
-		 * needed to ensure the target range is flushed.
-		 */
-		if (unlikely(bitmask & pfn)) {
-			unsigned long end_pfn = pfn + pages - 1, shared_bits;
-
-			/*
-			 * Since end_pfn <= pfn + bitmask, the only way bits
-			 * higher than bitmask can differ in pfn and end_pfn is
-			 * by carrying. This means after masking out bitmask,
-			 * high bits starting with the first set bit in
-			 * shared_bits are all equal in both pfn and end_pfn.
-			 */
-			shared_bits = ~(pfn ^ end_pfn) & ~bitmask;
-			mask = shared_bits ? __ffs(shared_bits) : BITS_PER_LONG;
-		}
-
-		/*
-		 * Fallback to domain selective flush if no PSI support or
-		 * the size is too big.
-		 */
-		if (!cap_pgsel_inv(iommu->cap) ||
-		    mask > cap_max_amask_val(iommu->cap))
-			iommu->flush.flush_iotlb(iommu, did, 0, 0,
-							DMA_TLB_DSI_FLUSH);
-		else
-			iommu->flush.flush_iotlb(iommu, did, addr | ih, mask,
-							DMA_TLB_PSI_FLUSH);
-	}
+	else
+		__iommu_flush_iotlb_psi(iommu, did, pfn, pages, ih);
 
 	/*
 	 * In caching mode, changes of pages from non-present to present require
@@ -1574,9 +1436,8 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 }
 
 /* Notification for newly created mappings */
-static inline void __mapping_notify_one(struct intel_iommu *iommu,
-					struct dmar_domain *domain,
-					unsigned long pfn, unsigned int pages)
+static void __mapping_notify_one(struct intel_iommu *iommu, struct dmar_domain *domain,
+				 unsigned long pfn, unsigned int pages)
 {
 	/*
 	 * It's a non-present to present mapping. Only flush if caching mode
@@ -1588,6 +1449,46 @@ static inline void __mapping_notify_one(struct intel_iommu *iommu,
 		iommu_flush_write_buffer(iommu);
 }
 
+/*
+ * Flush the relevant caches in nested translation if the domain
+ * also serves as a parent
+ */
+static void parent_domain_flush(struct dmar_domain *domain,
+				unsigned long pfn,
+				unsigned long pages, int ih)
+{
+	struct dmar_domain *s1_domain;
+
+	spin_lock(&domain->s1_lock);
+	list_for_each_entry(s1_domain, &domain->s1_domains, s2_link) {
+		struct device_domain_info *device_info;
+		struct iommu_domain_info *info;
+		unsigned long flags;
+		unsigned long i;
+
+		xa_for_each(&s1_domain->iommu_array, i, info)
+			__iommu_flush_iotlb_psi(info->iommu, info->did,
+						pfn, pages, ih);
+
+		if (!s1_domain->has_iotlb_device)
+			continue;
+
+		spin_lock_irqsave(&s1_domain->lock, flags);
+		list_for_each_entry(device_info, &s1_domain->devices, link)
+			/*
+			 * Address translation cache in device side caches the
+			 * result of nested translation. There is no easy way
+			 * to identify the exact set of nested translations
+			 * affected by a change in S2. So just flush the entire
+			 * device cache.
+			 */
+			__iommu_flush_dev_iotlb(device_info, 0,
+						MAX_AGAW_PFN_WIDTH);
+		spin_unlock_irqrestore(&s1_domain->lock, flags);
+	}
+	spin_unlock(&domain->s1_lock);
+}
+
 static void intel_flush_iotlb_all(struct iommu_domain *domain)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
@@ -1607,6 +1508,9 @@ static void intel_flush_iotlb_all(struct iommu_domain *domain)
 		if (!cap_caching_mode(iommu->cap))
 			iommu_flush_dev_iotlb(dmar_domain, 0, MAX_AGAW_PFN_WIDTH);
 	}
+
+	if (dmar_domain->nested_parent)
+		parent_domain_flush(dmar_domain, 0, -1, 0);
 }
 
 static void iommu_disable_protect_mem_regions(struct intel_iommu *iommu)
@@ -1843,7 +1747,7 @@ void domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu)
 	spin_unlock(&iommu->lock);
 }
 
-static inline int guestwidth_to_adjustwidth(int gaw)
+static int guestwidth_to_adjustwidth(int gaw)
 {
 	int agaw;
 	int r = (gaw - 12) % 9;
@@ -1877,7 +1781,7 @@ static void domain_exit(struct dmar_domain *domain)
  * Value of X in the PDTS field of a scalable mode context entry
  * indicates PASID directory with 2^(X + 7) entries.
  */
-static inline unsigned long context_get_sm_pds(struct pasid_table *table)
+static unsigned long context_get_sm_pds(struct pasid_table *table)
 {
 	unsigned long pds, max_pde;
 
@@ -1889,38 +1793,6 @@ static inline unsigned long context_get_sm_pds(struct pasid_table *table)
 	return pds - 7;
 }
 
-/*
- * Set the RID_PASID field of a scalable mode context entry. The
- * IOMMU hardware will use the PASID value set in this field for
- * DMA translations of DMA requests without PASID.
- */
-static inline void
-context_set_sm_rid2pasid(struct context_entry *context, unsigned long pasid)
-{
-	context->hi |= pasid & ((1 << 20) - 1);
-}
-
-/*
- * Set the DTE(Device-TLB Enable) field of a scalable mode context
- * entry.
- */
-static inline void context_set_sm_dte(struct context_entry *context)
-{
-	context->lo |= BIT_ULL(2);
-}
-
-/*
- * Set the PRE(Page Request Enable) field of a scalable mode context
- * entry.
- */
-static inline void context_set_sm_pre(struct context_entry *context)
-{
-	context->lo |= BIT_ULL(4);
-}
-
-/* Convert value to context PASID directory size field coding. */
-#define context_pdts(pds)	(((pds) & 0x7) << 9)
-
 static int domain_context_mapping_one(struct dmar_domain *domain,
 				      struct intel_iommu *iommu,
 				      struct pasid_table *table,
@@ -2081,14 +1953,11 @@ static int domain_context_mapping_cb(struct pci_dev *pdev,
 static int
 domain_context_mapping(struct dmar_domain *domain, struct device *dev)
 {
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct domain_context_mapping_data data;
+	struct intel_iommu *iommu = info->iommu;
+	u8 bus = info->bus, devfn = info->devfn;
 	struct pasid_table *table;
-	struct intel_iommu *iommu;
-	u8 bus, devfn;
-
-	iommu = device_to_iommu(dev, &bus, &devfn);
-	if (!iommu)
-		return -ENODEV;
 
 	table = intel_pasid_get_table(dev);
 
@@ -2105,18 +1974,15 @@ domain_context_mapping(struct dmar_domain *domain, struct device *dev)
 }
 
 /* Returns a number of VTD pages, but aligned to MM page size */
-static inline unsigned long aligned_nrpages(unsigned long host_addr,
-					    size_t size)
+static unsigned long aligned_nrpages(unsigned long host_addr, size_t size)
 {
 	host_addr &= ~PAGE_MASK;
 	return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT;
 }
 
 /* Return largest possible superpage level for a given mapping */
-static inline int hardware_largepage_caps(struct dmar_domain *domain,
-					  unsigned long iov_pfn,
-					  unsigned long phy_pfn,
-					  unsigned long pages)
+static int hardware_largepage_caps(struct dmar_domain *domain, unsigned long iov_pfn,
+				   unsigned long phy_pfn, unsigned long pages)
 {
 	int support, level = 1;
 	unsigned long pfnmerge;
@@ -2168,6 +2034,9 @@ static void switch_to_super_page(struct dmar_domain *domain,
 				iommu_flush_iotlb_psi(info->iommu, domain,
 						      start_pfn, lvl_pages,
 						      0, 0);
+			if (domain->nested_parent)
+				parent_domain_flush(domain, start_pfn,
+						    lvl_pages, 0);
 		}
 
 		pte++;
@@ -2449,15 +2318,10 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 				     struct device *dev)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
-	struct intel_iommu *iommu;
+	struct intel_iommu *iommu = info->iommu;
 	unsigned long flags;
-	u8 bus, devfn;
 	int ret;
 
-	iommu = device_to_iommu(dev, &bus, &devfn);
-	if (!iommu)
-		return -ENODEV;
-
 	ret = domain_attach_iommu(domain, iommu);
 	if (ret)
 		return ret;
@@ -2470,7 +2334,7 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) {
 		/* Setup the PASID entry for requests without PASID: */
 		if (hw_pass_through && domain_type_is_si(domain))
-			ret = intel_pasid_setup_pass_through(iommu, domain,
+			ret = intel_pasid_setup_pass_through(iommu,
 					dev, IOMMU_NO_PASID);
 		else if (domain->use_first_level)
 			ret = domain_setup_first_level(iommu, domain, dev,
@@ -3615,7 +3479,7 @@ void intel_iommu_shutdown(void)
 	up_write(&dmar_global_lock);
 }
 
-static inline struct intel_iommu *dev_to_intel_iommu(struct device *dev)
+static struct intel_iommu *dev_to_intel_iommu(struct device *dev)
 {
 	struct iommu_device *iommu_dev = dev_to_iommu_device(dev);
 
@@ -3694,7 +3558,7 @@ const struct attribute_group *intel_iommu_groups[] = {
 	NULL,
 };
 
-static inline bool has_external_pci(void)
+static bool has_external_pci(void)
 {
 	struct pci_dev *pdev = NULL;
 
@@ -4071,6 +3935,7 @@ intel_iommu_domain_alloc_user(struct device *dev, u32 flags,
 	bool dirty_tracking = flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING;
 	bool nested_parent = flags & IOMMU_HWPT_ALLOC_NEST_PARENT;
 	struct intel_iommu *iommu = info->iommu;
+	struct dmar_domain *dmar_domain;
 	struct iommu_domain *domain;
 
 	/* Must be NESTING domain */
@@ -4096,11 +3961,16 @@ intel_iommu_domain_alloc_user(struct device *dev, u32 flags,
 	if (!domain)
 		return ERR_PTR(-ENOMEM);
 
-	if (nested_parent)
-		to_dmar_domain(domain)->nested_parent = true;
+	dmar_domain = to_dmar_domain(domain);
+
+	if (nested_parent) {
+		dmar_domain->nested_parent = true;
+		INIT_LIST_HEAD(&dmar_domain->s1_domains);
+		spin_lock_init(&dmar_domain->s1_lock);
+	}
 
 	if (dirty_tracking) {
-		if (to_dmar_domain(domain)->use_first_level) {
+		if (dmar_domain->use_first_level) {
 			iommu_domain_free(domain);
 			return ERR_PTR(-EOPNOTSUPP);
 		}
@@ -4112,21 +3982,22 @@ intel_iommu_domain_alloc_user(struct device *dev, u32 flags,
 
 static void intel_iommu_domain_free(struct iommu_domain *domain)
 {
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+
+	WARN_ON(dmar_domain->nested_parent &&
+		!list_empty(&dmar_domain->s1_domains));
 	if (domain != &si_domain->domain)
-		domain_exit(to_dmar_domain(domain));
+		domain_exit(dmar_domain);
 }
 
 int prepare_domain_attach_device(struct iommu_domain *domain,
 				 struct device *dev)
 {
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
-	struct intel_iommu *iommu;
+	struct intel_iommu *iommu = info->iommu;
 	int addr_width;
 
-	iommu = device_to_iommu(dev, NULL, NULL);
-	if (!iommu)
-		return -ENODEV;
-
 	if (dmar_domain->force_snooping && !ecap_sc_support(iommu->ecap))
 		return -EINVAL;
 
@@ -4298,6 +4169,9 @@ static void intel_iommu_tlb_sync(struct iommu_domain *domain,
 				      start_pfn, nrpages,
 				      list_empty(&gather->freelist), 0);
 
+	if (dmar_domain->nested_parent)
+		parent_domain_flush(dmar_domain, start_pfn, nrpages,
+				    list_empty(&gather->freelist));
 	put_pages_list(&gather->freelist);
 }
 
@@ -4403,7 +4277,7 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 	u8 bus, devfn;
 	int ret;
 
-	iommu = device_to_iommu(dev, &bus, &devfn);
+	iommu = device_lookup_iommu(dev, &bus, &devfn);
 	if (!iommu || !iommu->iommu.ops)
 		return ERR_PTR(-ENODEV);
 
@@ -4461,7 +4335,6 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 		ret = intel_pasid_alloc_table(dev);
 		if (ret) {
 			dev_err(dev, "PASID table allocation failed\n");
-			dev_iommu_priv_set(dev, NULL);
 			kfree(info);
 			return ERR_PTR(ret);
 		}
@@ -4479,7 +4352,6 @@ static void intel_iommu_release_device(struct device *dev)
 	dmar_remove_one_dev_info(dev);
 	intel_pasid_free_table(dev);
 	intel_iommu_debugfs_remove_dev(info);
-	dev_iommu_priv_set(dev, NULL);
 	kfree(info);
 	set_dma_ops(dev, NULL);
 }
@@ -4739,8 +4611,9 @@ static int intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
 
 static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)
 {
-	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct dev_pasid_info *curr, *dev_pasid = NULL;
+	struct intel_iommu *iommu = info->iommu;
 	struct dmar_domain *dmar_domain;
 	struct iommu_domain *domain;
 	unsigned long flags;
@@ -4811,8 +4684,7 @@ static int intel_iommu_set_dev_pasid(struct iommu_domain *domain,
 		goto out_free;
 
 	if (domain_type_is_si(dmar_domain))
-		ret = intel_pasid_setup_pass_through(iommu, dmar_domain,
-						     dev, pasid);
+		ret = intel_pasid_setup_pass_through(iommu, dev, pasid);
 	else if (dmar_domain->use_first_level)
 		ret = domain_setup_first_level(iommu, dmar_domain,
 					       dev, pasid);
@@ -4857,21 +4729,70 @@ static void *intel_iommu_hw_info(struct device *dev, u32 *length, u32 *type)
 	return vtd;
 }
 
+/*
+ * Set dirty tracking for the device list of a domain. The caller must
+ * hold the domain->lock when calling it.
+ */
+static int device_set_dirty_tracking(struct list_head *devices, bool enable)
+{
+	struct device_domain_info *info;
+	int ret = 0;
+
+	list_for_each_entry(info, devices, link) {
+		ret = intel_pasid_setup_dirty_tracking(info->iommu, info->dev,
+						       IOMMU_NO_PASID, enable);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static int parent_domain_set_dirty_tracking(struct dmar_domain *domain,
+					    bool enable)
+{
+	struct dmar_domain *s1_domain;
+	unsigned long flags;
+	int ret;
+
+	spin_lock(&domain->s1_lock);
+	list_for_each_entry(s1_domain, &domain->s1_domains, s2_link) {
+		spin_lock_irqsave(&s1_domain->lock, flags);
+		ret = device_set_dirty_tracking(&s1_domain->devices, enable);
+		spin_unlock_irqrestore(&s1_domain->lock, flags);
+		if (ret)
+			goto err_unwind;
+	}
+	spin_unlock(&domain->s1_lock);
+	return 0;
+
+err_unwind:
+	list_for_each_entry(s1_domain, &domain->s1_domains, s2_link) {
+		spin_lock_irqsave(&s1_domain->lock, flags);
+		device_set_dirty_tracking(&s1_domain->devices,
+					  domain->dirty_tracking);
+		spin_unlock_irqrestore(&s1_domain->lock, flags);
+	}
+	spin_unlock(&domain->s1_lock);
+	return ret;
+}
+
 static int intel_iommu_set_dirty_tracking(struct iommu_domain *domain,
 					  bool enable)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
-	struct device_domain_info *info;
 	int ret;
 
 	spin_lock(&dmar_domain->lock);
 	if (dmar_domain->dirty_tracking == enable)
 		goto out_unlock;
 
-	list_for_each_entry(info, &dmar_domain->devices, link) {
-		ret = intel_pasid_setup_dirty_tracking(info->iommu,
-						       info->domain, info->dev,
-						       IOMMU_NO_PASID, enable);
+	ret = device_set_dirty_tracking(&dmar_domain->devices, enable);
+	if (ret)
+		goto err_unwind;
+
+	if (dmar_domain->nested_parent) {
+		ret = parent_domain_set_dirty_tracking(dmar_domain, enable);
 		if (ret)
 			goto err_unwind;
 	}
@@ -4883,10 +4804,8 @@ out_unlock:
 	return 0;
 
 err_unwind:
-	list_for_each_entry(info, &dmar_domain->devices, link)
-		intel_pasid_setup_dirty_tracking(info->iommu, dmar_domain,
-						 info->dev, IOMMU_NO_PASID,
-						 dmar_domain->dirty_tracking);
+	device_set_dirty_tracking(&dmar_domain->devices,
+				  dmar_domain->dirty_tracking);
 	spin_unlock(&dmar_domain->lock);
 	return ret;
 }
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index ce030c5b5772..4145c04cb1c6 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -140,9 +140,6 @@
 #define DMAR_ECEO_REG		0x408
 #define DMAR_ECRSP_REG		0x410
 #define DMAR_ECCAP_REG		0x430
-#define DMAR_VCCAP_REG		0xe30 /* Virtual command capability register */
-#define DMAR_VCMD_REG		0xe00 /* Virtual command register */
-#define DMAR_VCRSP_REG		0xe10 /* Virtual command response register */
 
 #define DMAR_IQER_REG_IQEI(reg)		FIELD_GET(GENMASK_ULL(3, 0), reg)
 #define DMAR_IQER_REG_ITESID(reg)	FIELD_GET(GENMASK_ULL(47, 32), reg)
@@ -630,6 +627,10 @@ struct dmar_domain {
 			int		agaw;
 			/* maximum mapped address */
 			u64		max_addr;
+			/* Protect the s1_domains list */
+			spinlock_t	s1_lock;
+			/* Track s1_domains nested on this domain */
+			struct list_head s1_domains;
 		};
 
 		/* Nested user domain */
@@ -640,6 +641,8 @@ struct dmar_domain {
 			unsigned long s1_pgtbl;
 			/* page table attributes */
 			struct iommu_hwpt_vtd_s1 s1_cfg;
+			/* link to parent domain siblings */
+			struct list_head s2_link;
 		};
 	};
 
@@ -854,6 +857,181 @@ static inline bool context_present(struct context_entry *context)
 	return (context->lo & 1);
 }
 
+#define LEVEL_STRIDE		(9)
+#define LEVEL_MASK		(((u64)1 << LEVEL_STRIDE) - 1)
+#define MAX_AGAW_WIDTH		(64)
+#define MAX_AGAW_PFN_WIDTH	(MAX_AGAW_WIDTH - VTD_PAGE_SHIFT)
+
+static inline int agaw_to_level(int agaw)
+{
+	return agaw + 2;
+}
+
+static inline int agaw_to_width(int agaw)
+{
+	return min_t(int, 30 + agaw * LEVEL_STRIDE, MAX_AGAW_WIDTH);
+}
+
+static inline int width_to_agaw(int width)
+{
+	return DIV_ROUND_UP(width - 30, LEVEL_STRIDE);
+}
+
+static inline unsigned int level_to_offset_bits(int level)
+{
+	return (level - 1) * LEVEL_STRIDE;
+}
+
+static inline int pfn_level_offset(u64 pfn, int level)
+{
+	return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK;
+}
+
+static inline u64 level_mask(int level)
+{
+	return -1ULL << level_to_offset_bits(level);
+}
+
+static inline u64 level_size(int level)
+{
+	return 1ULL << level_to_offset_bits(level);
+}
+
+static inline u64 align_to_level(u64 pfn, int level)
+{
+	return (pfn + level_size(level) - 1) & level_mask(level);
+}
+
+static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
+{
+	return 1UL << min_t(int, (lvl - 1) * LEVEL_STRIDE, MAX_AGAW_PFN_WIDTH);
+}
+
+/* VT-d pages must always be _smaller_ than MM pages. Otherwise things
+   are never going to work. */
+static inline unsigned long mm_to_dma_pfn_start(unsigned long mm_pfn)
+{
+	return mm_pfn << (PAGE_SHIFT - VTD_PAGE_SHIFT);
+}
+static inline unsigned long mm_to_dma_pfn_end(unsigned long mm_pfn)
+{
+	return ((mm_pfn + 1) << (PAGE_SHIFT - VTD_PAGE_SHIFT)) - 1;
+}
+static inline unsigned long page_to_dma_pfn(struct page *pg)
+{
+	return mm_to_dma_pfn_start(page_to_pfn(pg));
+}
+static inline unsigned long virt_to_dma_pfn(void *p)
+{
+	return page_to_dma_pfn(virt_to_page(p));
+}
+
+static inline void context_set_present(struct context_entry *context)
+{
+	context->lo |= 1;
+}
+
+static inline void context_set_fault_enable(struct context_entry *context)
+{
+	context->lo &= (((u64)-1) << 2) | 1;
+}
+
+static inline void context_set_translation_type(struct context_entry *context,
+						unsigned long value)
+{
+	context->lo &= (((u64)-1) << 4) | 3;
+	context->lo |= (value & 3) << 2;
+}
+
+static inline void context_set_address_root(struct context_entry *context,
+					    unsigned long value)
+{
+	context->lo &= ~VTD_PAGE_MASK;
+	context->lo |= value & VTD_PAGE_MASK;
+}
+
+static inline void context_set_address_width(struct context_entry *context,
+					     unsigned long value)
+{
+	context->hi |= value & 7;
+}
+
+static inline void context_set_domain_id(struct context_entry *context,
+					 unsigned long value)
+{
+	context->hi |= (value & ((1 << 16) - 1)) << 8;
+}
+
+static inline void context_set_pasid(struct context_entry *context)
+{
+	context->lo |= CONTEXT_PASIDE;
+}
+
+static inline int context_domain_id(struct context_entry *c)
+{
+	return((c->hi >> 8) & 0xffff);
+}
+
+static inline void context_clear_entry(struct context_entry *context)
+{
+	context->lo = 0;
+	context->hi = 0;
+}
+
+#ifdef CONFIG_INTEL_IOMMU
+static inline bool context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	if (!iommu->copied_tables)
+		return false;
+
+	return test_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+
+static inline void
+set_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	set_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+
+static inline void
+clear_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	clear_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+#endif /* CONFIG_INTEL_IOMMU */
+
+/*
+ * Set the RID_PASID field of a scalable mode context entry. The
+ * IOMMU hardware will use the PASID value set in this field for
+ * DMA translations of DMA requests without PASID.
+ */
+static inline void
+context_set_sm_rid2pasid(struct context_entry *context, unsigned long pasid)
+{
+	context->hi |= pasid & ((1 << 20) - 1);
+}
+
+/*
+ * Set the DTE(Device-TLB Enable) field of a scalable mode context
+ * entry.
+ */
+static inline void context_set_sm_dte(struct context_entry *context)
+{
+	context->lo |= BIT_ULL(2);
+}
+
+/*
+ * Set the PRE(Page Request Enable) field of a scalable mode context
+ * entry.
+ */
+static inline void context_set_sm_pre(struct context_entry *context)
+{
+	context->lo |= BIT_ULL(4);
+}
+
+/* Convert value to context PASID directory size field coding. */
+#define context_pdts(pds)	(((pds) & 0x7) << 9)
+
 struct dmar_drhd_unit *dmar_find_matched_drhd_unit(struct pci_dev *dev);
 
 int dmar_enable_qi(struct intel_iommu *iommu);
@@ -888,6 +1066,7 @@ int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc,
  */
 #define QI_OPT_WAIT_DRAIN		BIT(0)
 
+void domain_update_iotlb(struct dmar_domain *domain);
 int domain_attach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu);
 void domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu);
 void device_block_translation(struct device *dev);
@@ -900,7 +1079,6 @@ int dmar_ir_support(void);
 void *alloc_pgtable_page(int node, gfp_t gfp);
 void free_pgtable_page(void *vaddr);
 void iommu_flush_write_buffer(struct intel_iommu *iommu);
-struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn);
 struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent,
 					       const struct iommu_user_data *user_data);
 
diff --git a/drivers/iommu/intel/nested.c b/drivers/iommu/intel/nested.c
index b5a5563ab32c..a7d68f3d518a 100644
--- a/drivers/iommu/intel/nested.c
+++ b/drivers/iommu/intel/nested.c
@@ -65,17 +65,113 @@ static int intel_nested_attach_dev(struct iommu_domain *domain,
 	list_add(&info->link, &dmar_domain->devices);
 	spin_unlock_irqrestore(&dmar_domain->lock, flags);
 
+	domain_update_iotlb(dmar_domain);
+
 	return 0;
 }
 
 static void intel_nested_domain_free(struct iommu_domain *domain)
 {
-	kfree(to_dmar_domain(domain));
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	struct dmar_domain *s2_domain = dmar_domain->s2_domain;
+
+	spin_lock(&s2_domain->s1_lock);
+	list_del(&dmar_domain->s2_link);
+	spin_unlock(&s2_domain->s1_lock);
+	kfree(dmar_domain);
+}
+
+static void nested_flush_dev_iotlb(struct dmar_domain *domain, u64 addr,
+				   unsigned int mask)
+{
+	struct device_domain_info *info;
+	unsigned long flags;
+	u16 sid, qdep;
+
+	spin_lock_irqsave(&domain->lock, flags);
+	list_for_each_entry(info, &domain->devices, link) {
+		if (!info->ats_enabled)
+			continue;
+		sid = info->bus << 8 | info->devfn;
+		qdep = info->ats_qdep;
+		qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
+				   qdep, addr, mask);
+		quirk_extra_dev_tlb_flush(info, addr, mask,
+					  IOMMU_NO_PASID, qdep);
+	}
+	spin_unlock_irqrestore(&domain->lock, flags);
+}
+
+static void intel_nested_flush_cache(struct dmar_domain *domain, u64 addr,
+				     u64 npages, bool ih)
+{
+	struct iommu_domain_info *info;
+	unsigned int mask;
+	unsigned long i;
+
+	xa_for_each(&domain->iommu_array, i, info)
+		qi_flush_piotlb(info->iommu,
+				domain_id_iommu(domain, info->iommu),
+				IOMMU_NO_PASID, addr, npages, ih);
+
+	if (!domain->has_iotlb_device)
+		return;
+
+	if (npages == U64_MAX)
+		mask = 64 - VTD_PAGE_SHIFT;
+	else
+		mask = ilog2(__roundup_pow_of_two(npages));
+
+	nested_flush_dev_iotlb(domain, addr, mask);
+}
+
+static int intel_nested_cache_invalidate_user(struct iommu_domain *domain,
+					      struct iommu_user_data_array *array)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	struct iommu_hwpt_vtd_s1_invalidate inv_entry;
+	u32 index, processed = 0;
+	int ret = 0;
+
+	if (array->type != IOMMU_HWPT_INVALIDATE_DATA_VTD_S1) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	for (index = 0; index < array->entry_num; index++) {
+		ret = iommu_copy_struct_from_user_array(&inv_entry, array,
+							IOMMU_HWPT_INVALIDATE_DATA_VTD_S1,
+							index, __reserved);
+		if (ret)
+			break;
+
+		if ((inv_entry.flags & ~IOMMU_VTD_INV_FLAGS_LEAF) ||
+		    inv_entry.__reserved) {
+			ret = -EOPNOTSUPP;
+			break;
+		}
+
+		if (!IS_ALIGNED(inv_entry.addr, VTD_PAGE_SIZE) ||
+		    ((inv_entry.npages == U64_MAX) && inv_entry.addr)) {
+			ret = -EINVAL;
+			break;
+		}
+
+		intel_nested_flush_cache(dmar_domain, inv_entry.addr,
+					 inv_entry.npages,
+					 inv_entry.flags & IOMMU_VTD_INV_FLAGS_LEAF);
+		processed++;
+	}
+
+out:
+	array->entry_num = processed;
+	return ret;
 }
 
 static const struct iommu_domain_ops intel_nested_domain_ops = {
 	.attach_dev		= intel_nested_attach_dev,
 	.free			= intel_nested_domain_free,
+	.cache_invalidate_user	= intel_nested_cache_invalidate_user,
 };
 
 struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent,
@@ -113,5 +209,9 @@ struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent,
 	spin_lock_init(&domain->lock);
 	xa_init(&domain->iommu_array);
 
+	spin_lock(&s2_domain->s1_lock);
+	list_add(&domain->s2_link, &s2_domain->s1_domains);
+	spin_unlock(&s2_domain->s1_lock);
+
 	return &domain->domain;
 }
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index 74e8e4c17e81..108158e2b907 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -26,63 +26,6 @@
  */
 u32 intel_pasid_max_id = PASID_MAX;
 
-int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid)
-{
-	unsigned long flags;
-	u8 status_code;
-	int ret = 0;
-	u64 res;
-
-	raw_spin_lock_irqsave(&iommu->register_lock, flags);
-	dmar_writeq(iommu->reg + DMAR_VCMD_REG, VCMD_CMD_ALLOC);
-	IOMMU_WAIT_OP(iommu, DMAR_VCRSP_REG, dmar_readq,
-		      !(res & VCMD_VRSP_IP), res);
-	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
-
-	status_code = VCMD_VRSP_SC(res);
-	switch (status_code) {
-	case VCMD_VRSP_SC_SUCCESS:
-		*pasid = VCMD_VRSP_RESULT_PASID(res);
-		break;
-	case VCMD_VRSP_SC_NO_PASID_AVAIL:
-		pr_info("IOMMU: %s: No PASID available\n", iommu->name);
-		ret = -ENOSPC;
-		break;
-	default:
-		ret = -ENODEV;
-		pr_warn("IOMMU: %s: Unexpected error code %d\n",
-			iommu->name, status_code);
-	}
-
-	return ret;
-}
-
-void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid)
-{
-	unsigned long flags;
-	u8 status_code;
-	u64 res;
-
-	raw_spin_lock_irqsave(&iommu->register_lock, flags);
-	dmar_writeq(iommu->reg + DMAR_VCMD_REG,
-		    VCMD_CMD_OPERAND(pasid) | VCMD_CMD_FREE);
-	IOMMU_WAIT_OP(iommu, DMAR_VCRSP_REG, dmar_readq,
-		      !(res & VCMD_VRSP_IP), res);
-	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
-
-	status_code = VCMD_VRSP_SC(res);
-	switch (status_code) {
-	case VCMD_VRSP_SC_SUCCESS:
-		break;
-	case VCMD_VRSP_SC_INVALID_PASID:
-		pr_info("IOMMU: %s: Invalid PASID\n", iommu->name);
-		break;
-	default:
-		pr_warn("IOMMU: %s: Unexpected error code %d\n",
-			iommu->name, status_code);
-	}
-}
-
 /*
  * Per device pasid table management:
  */
@@ -230,30 +173,6 @@ retry:
 /*
  * Interfaces for PASID table entry manipulation:
  */
-static inline void pasid_clear_entry(struct pasid_entry *pe)
-{
-	WRITE_ONCE(pe->val[0], 0);
-	WRITE_ONCE(pe->val[1], 0);
-	WRITE_ONCE(pe->val[2], 0);
-	WRITE_ONCE(pe->val[3], 0);
-	WRITE_ONCE(pe->val[4], 0);
-	WRITE_ONCE(pe->val[5], 0);
-	WRITE_ONCE(pe->val[6], 0);
-	WRITE_ONCE(pe->val[7], 0);
-}
-
-static inline void pasid_clear_entry_with_fpd(struct pasid_entry *pe)
-{
-	WRITE_ONCE(pe->val[0], PASID_PTE_FPD);
-	WRITE_ONCE(pe->val[1], 0);
-	WRITE_ONCE(pe->val[2], 0);
-	WRITE_ONCE(pe->val[3], 0);
-	WRITE_ONCE(pe->val[4], 0);
-	WRITE_ONCE(pe->val[5], 0);
-	WRITE_ONCE(pe->val[6], 0);
-	WRITE_ONCE(pe->val[7], 0);
-}
-
 static void
 intel_pasid_clear_entry(struct device *dev, u32 pasid, bool fault_ignore)
 {
@@ -269,192 +188,6 @@ intel_pasid_clear_entry(struct device *dev, u32 pasid, bool fault_ignore)
 		pasid_clear_entry(pe);
 }
 
-static inline void pasid_set_bits(u64 *ptr, u64 mask, u64 bits)
-{
-	u64 old;
-
-	old = READ_ONCE(*ptr);
-	WRITE_ONCE(*ptr, (old & ~mask) | bits);
-}
-
-static inline u64 pasid_get_bits(u64 *ptr)
-{
-	return READ_ONCE(*ptr);
-}
-
-/*
- * Setup the DID(Domain Identifier) field (Bit 64~79) of scalable mode
- * PASID entry.
- */
-static inline void
-pasid_set_domain_id(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[1], GENMASK_ULL(15, 0), value);
-}
-
-/*
- * Get domain ID value of a scalable mode PASID entry.
- */
-static inline u16
-pasid_get_domain_id(struct pasid_entry *pe)
-{
-	return (u16)(READ_ONCE(pe->val[1]) & GENMASK_ULL(15, 0));
-}
-
-/*
- * Setup the SLPTPTR(Second Level Page Table Pointer) field (Bit 12~63)
- * of a scalable mode PASID entry.
- */
-static inline void
-pasid_set_slptr(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[0], VTD_PAGE_MASK, value);
-}
-
-/*
- * Setup the AW(Address Width) field (Bit 2~4) of a scalable mode PASID
- * entry.
- */
-static inline void
-pasid_set_address_width(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[0], GENMASK_ULL(4, 2), value << 2);
-}
-
-/*
- * Setup the PGTT(PASID Granular Translation Type) field (Bit 6~8)
- * of a scalable mode PASID entry.
- */
-static inline void
-pasid_set_translation_type(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[0], GENMASK_ULL(8, 6), value << 6);
-}
-
-/*
- * Enable fault processing by clearing the FPD(Fault Processing
- * Disable) field (Bit 1) of a scalable mode PASID entry.
- */
-static inline void pasid_set_fault_enable(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[0], 1 << 1, 0);
-}
-
-/*
- * Enable second level A/D bits by setting the SLADE (Second Level
- * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
- * entry.
- */
-static inline void pasid_set_ssade(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[0], 1 << 9, 1 << 9);
-}
-
-/*
- * Disable second level A/D bits by clearing the SLADE (Second Level
- * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
- * entry.
- */
-static inline void pasid_clear_ssade(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[0], 1 << 9, 0);
-}
-
-/*
- * Checks if second level A/D bits specifically the SLADE (Second Level
- * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
- * entry is set.
- */
-static inline bool pasid_get_ssade(struct pasid_entry *pe)
-{
-	return pasid_get_bits(&pe->val[0]) & (1 << 9);
-}
-
-/*
- * Setup the SRE(Supervisor Request Enable) field (Bit 128) of a
- * scalable mode PASID entry.
- */
-static inline void pasid_set_sre(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[2], 1 << 0, 1);
-}
-
-/*
- * Setup the WPE(Write Protect Enable) field (Bit 132) of a
- * scalable mode PASID entry.
- */
-static inline void pasid_set_wpe(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[2], 1 << 4, 1 << 4);
-}
-
-/*
- * Setup the P(Present) field (Bit 0) of a scalable mode PASID
- * entry.
- */
-static inline void pasid_set_present(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[0], 1 << 0, 1);
-}
-
-/*
- * Setup Page Walk Snoop bit (Bit 87) of a scalable mode PASID
- * entry.
- */
-static inline void pasid_set_page_snoop(struct pasid_entry *pe, bool value)
-{
-	pasid_set_bits(&pe->val[1], 1 << 23, value << 23);
-}
-
-/*
- * Setup No Execute Enable bit (Bit 133) of a scalable mode PASID
- * entry. It is required when XD bit of the first level page table
- * entry is about to be set.
- */
-static inline void pasid_set_nxe(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[2], 1 << 5, 1 << 5);
-}
-
-/*
- * Setup the Page Snoop (PGSNP) field (Bit 88) of a scalable mode
- * PASID entry.
- */
-static inline void
-pasid_set_pgsnp(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[1], 1ULL << 24, 1ULL << 24);
-}
-
-/*
- * Setup the First Level Page table Pointer field (Bit 140~191)
- * of a scalable mode PASID entry.
- */
-static inline void
-pasid_set_flptr(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[2], VTD_PAGE_MASK, value);
-}
-
-/*
- * Setup the First Level Paging Mode field (Bit 130~131) of a
- * scalable mode PASID entry.
- */
-static inline void
-pasid_set_flpm(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[2], GENMASK_ULL(3, 2), value << 2);
-}
-
-/*
- * Setup the Extended Access Flag Enable (EAFE) field (Bit 135)
- * of a scalable mode PASID entry.
- */
-static inline void pasid_set_eafe(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[2], 1 << 7, 1 << 7);
-}
-
 static void
 pasid_cache_invalidation_with_pasid(struct intel_iommu *iommu,
 				    u16 did, u32 pasid)
@@ -613,9 +346,9 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu,
  * Skip top levels of page tables for iommu which has less agaw
  * than default. Unnecessary for PT mode.
  */
-static inline int iommu_skip_agaw(struct dmar_domain *domain,
-				  struct intel_iommu *iommu,
-				  struct dma_pte **pgd)
+static int iommu_skip_agaw(struct dmar_domain *domain,
+			   struct intel_iommu *iommu,
+			   struct dma_pte **pgd)
 {
 	int agaw;
 
@@ -695,7 +428,6 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
  * Set up dirty tracking on a second only or nested translation type.
  */
 int intel_pasid_setup_dirty_tracking(struct intel_iommu *iommu,
-				     struct dmar_domain *domain,
 				     struct device *dev, u32 pasid,
 				     bool enabled)
 {
@@ -712,7 +444,7 @@ int intel_pasid_setup_dirty_tracking(struct intel_iommu *iommu,
 		return -ENODEV;
 	}
 
-	did = domain_id_iommu(domain, iommu);
+	did = pasid_get_domain_id(pte);
 	pgtt = pasid_pte_get_pgtt(pte);
 	if (pgtt != PASID_ENTRY_PGTT_SL_ONLY &&
 	    pgtt != PASID_ENTRY_PGTT_NESTED) {
@@ -767,7 +499,6 @@ int intel_pasid_setup_dirty_tracking(struct intel_iommu *iommu,
  * Set up the scalable mode pasid entry for passthrough translation type.
  */
 int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
-				   struct dmar_domain *domain,
 				   struct device *dev, u32 pasid)
 {
 	u16 did = FLPT_DEFAULT_DID;
@@ -926,6 +657,8 @@ int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
 	pasid_set_domain_id(pte, did);
 	pasid_set_address_width(pte, s2_domain->agaw);
 	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
+	if (s2_domain->dirty_tracking)
+		pasid_set_ssade(pte);
 	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_NESTED);
 	pasid_set_present(pte);
 	spin_unlock(&iommu->lock);
diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h
index dd37611175cc..487ede039bdd 100644
--- a/drivers/iommu/intel/pasid.h
+++ b/drivers/iommu/intel/pasid.h
@@ -22,16 +22,6 @@
 #define is_pasid_enabled(entry)		(((entry)->lo >> 3) & 0x1)
 #define get_pasid_dir_size(entry)	(1 << ((((entry)->lo >> 9) & 0x7) + 7))
 
-/* Virtual command interface for enlightened pasid management. */
-#define VCMD_CMD_ALLOC			0x1
-#define VCMD_CMD_FREE			0x2
-#define VCMD_VRSP_IP			0x1
-#define VCMD_VRSP_SC(e)			(((e) & 0xff) >> 1)
-#define VCMD_VRSP_SC_SUCCESS		0
-#define VCMD_VRSP_SC_NO_PASID_AVAIL	16
-#define VCMD_VRSP_SC_INVALID_PASID	16
-#define VCMD_VRSP_RESULT_PASID(e)	(((e) >> 16) & 0xfffff)
-#define VCMD_CMD_OPERAND(e)		((e) << 16)
 /*
  * Domain ID reserved for pasid entries programmed for first-level
  * only and pass-through transfer modes.
@@ -96,6 +86,216 @@ static inline u16 pasid_pte_get_pgtt(struct pasid_entry *pte)
 	return (u16)((READ_ONCE(pte->val[0]) >> 6) & 0x7);
 }
 
+static inline void pasid_clear_entry(struct pasid_entry *pe)
+{
+	WRITE_ONCE(pe->val[0], 0);
+	WRITE_ONCE(pe->val[1], 0);
+	WRITE_ONCE(pe->val[2], 0);
+	WRITE_ONCE(pe->val[3], 0);
+	WRITE_ONCE(pe->val[4], 0);
+	WRITE_ONCE(pe->val[5], 0);
+	WRITE_ONCE(pe->val[6], 0);
+	WRITE_ONCE(pe->val[7], 0);
+}
+
+static inline void pasid_clear_entry_with_fpd(struct pasid_entry *pe)
+{
+	WRITE_ONCE(pe->val[0], PASID_PTE_FPD);
+	WRITE_ONCE(pe->val[1], 0);
+	WRITE_ONCE(pe->val[2], 0);
+	WRITE_ONCE(pe->val[3], 0);
+	WRITE_ONCE(pe->val[4], 0);
+	WRITE_ONCE(pe->val[5], 0);
+	WRITE_ONCE(pe->val[6], 0);
+	WRITE_ONCE(pe->val[7], 0);
+}
+
+static inline void pasid_set_bits(u64 *ptr, u64 mask, u64 bits)
+{
+	u64 old;
+
+	old = READ_ONCE(*ptr);
+	WRITE_ONCE(*ptr, (old & ~mask) | bits);
+}
+
+static inline u64 pasid_get_bits(u64 *ptr)
+{
+	return READ_ONCE(*ptr);
+}
+
+/*
+ * Setup the DID(Domain Identifier) field (Bit 64~79) of scalable mode
+ * PASID entry.
+ */
+static inline void
+pasid_set_domain_id(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[1], GENMASK_ULL(15, 0), value);
+}
+
+/*
+ * Get domain ID value of a scalable mode PASID entry.
+ */
+static inline u16
+pasid_get_domain_id(struct pasid_entry *pe)
+{
+	return (u16)(READ_ONCE(pe->val[1]) & GENMASK_ULL(15, 0));
+}
+
+/*
+ * Setup the SLPTPTR(Second Level Page Table Pointer) field (Bit 12~63)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_slptr(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[0], VTD_PAGE_MASK, value);
+}
+
+/*
+ * Setup the AW(Address Width) field (Bit 2~4) of a scalable mode PASID
+ * entry.
+ */
+static inline void
+pasid_set_address_width(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[0], GENMASK_ULL(4, 2), value << 2);
+}
+
+/*
+ * Setup the PGTT(PASID Granular Translation Type) field (Bit 6~8)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_translation_type(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[0], GENMASK_ULL(8, 6), value << 6);
+}
+
+/*
+ * Enable fault processing by clearing the FPD(Fault Processing
+ * Disable) field (Bit 1) of a scalable mode PASID entry.
+ */
+static inline void pasid_set_fault_enable(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[0], 1 << 1, 0);
+}
+
+/*
+ * Enable second level A/D bits by setting the SLADE (Second Level
+ * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
+ * entry.
+ */
+static inline void pasid_set_ssade(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[0], 1 << 9, 1 << 9);
+}
+
+/*
+ * Disable second level A/D bits by clearing the SLADE (Second Level
+ * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
+ * entry.
+ */
+static inline void pasid_clear_ssade(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[0], 1 << 9, 0);
+}
+
+/*
+ * Checks if second level A/D bits specifically the SLADE (Second Level
+ * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
+ * entry is set.
+ */
+static inline bool pasid_get_ssade(struct pasid_entry *pe)
+{
+	return pasid_get_bits(&pe->val[0]) & (1 << 9);
+}
+
+/*
+ * Setup the SRE(Supervisor Request Enable) field (Bit 128) of a
+ * scalable mode PASID entry.
+ */
+static inline void pasid_set_sre(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 0, 1);
+}
+
+/*
+ * Setup the WPE(Write Protect Enable) field (Bit 132) of a
+ * scalable mode PASID entry.
+ */
+static inline void pasid_set_wpe(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 4, 1 << 4);
+}
+
+/*
+ * Setup the P(Present) field (Bit 0) of a scalable mode PASID
+ * entry.
+ */
+static inline void pasid_set_present(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[0], 1 << 0, 1);
+}
+
+/*
+ * Setup Page Walk Snoop bit (Bit 87) of a scalable mode PASID
+ * entry.
+ */
+static inline void pasid_set_page_snoop(struct pasid_entry *pe, bool value)
+{
+	pasid_set_bits(&pe->val[1], 1 << 23, value << 23);
+}
+
+/*
+ * Setup No Execute Enable bit (Bit 133) of a scalable mode PASID
+ * entry. It is required when XD bit of the first level page table
+ * entry is about to be set.
+ */
+static inline void pasid_set_nxe(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 5, 1 << 5);
+}
+
+/*
+ * Setup the Page Snoop (PGSNP) field (Bit 88) of a scalable mode
+ * PASID entry.
+ */
+static inline void
+pasid_set_pgsnp(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[1], 1ULL << 24, 1ULL << 24);
+}
+
+/*
+ * Setup the First Level Page table Pointer field (Bit 140~191)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_flptr(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[2], VTD_PAGE_MASK, value);
+}
+
+/*
+ * Setup the First Level Paging Mode field (Bit 130~131) of a
+ * scalable mode PASID entry.
+ */
+static inline void
+pasid_set_flpm(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[2], GENMASK_ULL(3, 2), value << 2);
+}
+
+/*
+ * Setup the Extended Access Flag Enable (EAFE) field (Bit 135)
+ * of a scalable mode PASID entry.
+ */
+static inline void pasid_set_eafe(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 7, 1 << 7);
+}
+
 extern unsigned int intel_pasid_max_id;
 int intel_pasid_alloc_table(struct device *dev);
 void intel_pasid_free_table(struct device *dev);
@@ -107,19 +307,15 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 				   struct dmar_domain *domain,
 				   struct device *dev, u32 pasid);
 int intel_pasid_setup_dirty_tracking(struct intel_iommu *iommu,
-				     struct dmar_domain *domain,
 				     struct device *dev, u32 pasid,
 				     bool enabled);
 int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
-				   struct dmar_domain *domain,
 				   struct device *dev, u32 pasid);
 int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
 			     u32 pasid, struct dmar_domain *domain);
 void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
 				 struct device *dev, u32 pasid,
 				 bool fault_ignore);
-int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid);
-void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid);
 void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu,
 					  struct device *dev, u32 pasid);
 #endif /* __INTEL_PASID_H */
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index ac12f76c1212..40edd282903f 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -316,21 +316,22 @@ out:
 }
 
 static int intel_svm_bind_mm(struct intel_iommu *iommu, struct device *dev,
-			     struct mm_struct *mm)
+			     struct iommu_domain *domain, ioasid_t pasid)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct mm_struct *mm = domain->mm;
 	struct intel_svm_dev *sdev;
 	struct intel_svm *svm;
 	unsigned long sflags;
 	int ret = 0;
 
-	svm = pasid_private_find(mm->pasid);
+	svm = pasid_private_find(pasid);
 	if (!svm) {
 		svm = kzalloc(sizeof(*svm), GFP_KERNEL);
 		if (!svm)
 			return -ENOMEM;
 
-		svm->pasid = mm->pasid;
+		svm->pasid = pasid;
 		svm->mm = mm;
 		INIT_LIST_HEAD_RCU(&svm->devs);
 
@@ -368,7 +369,7 @@ static int intel_svm_bind_mm(struct intel_iommu *iommu, struct device *dev,
 
 	/* Setup the pasid table: */
 	sflags = cpu_feature_enabled(X86_FEATURE_LA57) ? PASID_FLAG_FL5LP : 0;
-	ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, mm->pasid,
+	ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, pasid,
 					    FLPT_DEFAULT_DID, sflags);
 	if (ret)
 		goto free_sdev;
@@ -382,7 +383,7 @@ free_sdev:
 free_svm:
 	if (list_empty(&svm->devs)) {
 		mmu_notifier_unregister(&svm->notifier, mm);
-		pasid_private_remove(mm->pasid);
+		pasid_private_remove(pasid);
 		kfree(svm);
 	}
 
@@ -392,14 +393,9 @@ free_svm:
 void intel_svm_remove_dev_pasid(struct device *dev, u32 pasid)
 {
 	struct intel_svm_dev *sdev;
-	struct intel_iommu *iommu;
 	struct intel_svm *svm;
 	struct mm_struct *mm;
 
-	iommu = device_to_iommu(dev, NULL, NULL);
-	if (!iommu)
-		return;
-
 	if (pasid_to_svm_sdev(dev, pasid, &svm, &sdev))
 		return;
 	mm = svm->mm;
@@ -750,25 +746,16 @@ int intel_svm_page_response(struct device *dev,
 			    struct iommu_fault_event *evt,
 			    struct iommu_page_response *msg)
 {
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
+	u8 bus = info->bus, devfn = info->devfn;
 	struct iommu_fault_page_request *prm;
-	struct intel_iommu *iommu;
 	bool private_present;
 	bool pasid_present;
 	bool last_page;
-	u8 bus, devfn;
 	int ret = 0;
 	u16 sid;
 
-	if (!dev || !dev_is_pci(dev))
-		return -ENODEV;
-
-	iommu = device_to_iommu(dev, &bus, &devfn);
-	if (!iommu)
-		return -ENODEV;
-
-	if (!msg || !evt)
-		return -EINVAL;
-
 	prm = &evt->fault.prm;
 	sid = PCI_DEVID(bus, devfn);
 	pasid_present = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
@@ -822,9 +809,8 @@ static int intel_svm_set_dev_pasid(struct iommu_domain *domain,
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_iommu *iommu = info->iommu;
-	struct mm_struct *mm = domain->mm;
 
-	return intel_svm_bind_mm(iommu, dev, mm);
+	return intel_svm_bind_mm(iommu, dev, domain, pasid);
 }
 
 static void intel_svm_domain_free(struct iommu_domain *domain)
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 72dcdd468cf3..f7828a7aad41 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -188,20 +188,28 @@ static dma_addr_t __arm_lpae_dma_addr(void *pages)
 }
 
 static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp,
-				    struct io_pgtable_cfg *cfg)
+				    struct io_pgtable_cfg *cfg,
+				    void *cookie)
 {
 	struct device *dev = cfg->iommu_dev;
 	int order = get_order(size);
-	struct page *p;
 	dma_addr_t dma;
 	void *pages;
 
 	VM_BUG_ON((gfp & __GFP_HIGHMEM));
-	p = alloc_pages_node(dev_to_node(dev), gfp | __GFP_ZERO, order);
-	if (!p)
+
+	if (cfg->alloc) {
+		pages = cfg->alloc(cookie, size, gfp);
+	} else {
+		struct page *p;
+
+		p = alloc_pages_node(dev_to_node(dev), gfp | __GFP_ZERO, order);
+		pages = p ? page_address(p) : NULL;
+	}
+
+	if (!pages)
 		return NULL;
 
-	pages = page_address(p);
 	if (!cfg->coherent_walk) {
 		dma = dma_map_single(dev, pages, size, DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, dma))
@@ -220,18 +228,28 @@ static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp,
 out_unmap:
 	dev_err(dev, "Cannot accommodate DMA translation for IOMMU page tables\n");
 	dma_unmap_single(dev, dma, size, DMA_TO_DEVICE);
+
 out_free:
-	__free_pages(p, order);
+	if (cfg->free)
+		cfg->free(cookie, pages, size);
+	else
+		free_pages((unsigned long)pages, order);
+
 	return NULL;
 }
 
 static void __arm_lpae_free_pages(void *pages, size_t size,
-				  struct io_pgtable_cfg *cfg)
+				  struct io_pgtable_cfg *cfg,
+				  void *cookie)
 {
 	if (!cfg->coherent_walk)
 		dma_unmap_single(cfg->iommu_dev, __arm_lpae_dma_addr(pages),
 				 size, DMA_TO_DEVICE);
-	free_pages((unsigned long)pages, get_order(size));
+
+	if (cfg->free)
+		cfg->free(cookie, pages, size);
+	else
+		free_pages((unsigned long)pages, get_order(size));
 }
 
 static void __arm_lpae_sync_pte(arm_lpae_iopte *ptep, int num_entries,
@@ -373,13 +391,13 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
 	/* Grab a pointer to the next level */
 	pte = READ_ONCE(*ptep);
 	if (!pte) {
-		cptep = __arm_lpae_alloc_pages(tblsz, gfp, cfg);
+		cptep = __arm_lpae_alloc_pages(tblsz, gfp, cfg, data->iop.cookie);
 		if (!cptep)
 			return -ENOMEM;
 
 		pte = arm_lpae_install_table(cptep, ptep, 0, data);
 		if (pte)
-			__arm_lpae_free_pages(cptep, tblsz, cfg);
+			__arm_lpae_free_pages(cptep, tblsz, cfg, data->iop.cookie);
 	} else if (!cfg->coherent_walk && !(pte & ARM_LPAE_PTE_SW_SYNC)) {
 		__arm_lpae_sync_pte(ptep, 1, cfg);
 	}
@@ -524,7 +542,7 @@ static void __arm_lpae_free_pgtable(struct arm_lpae_io_pgtable *data, int lvl,
 		__arm_lpae_free_pgtable(data, lvl + 1, iopte_deref(pte, data));
 	}
 
-	__arm_lpae_free_pages(start, table_size, &data->iop.cfg);
+	__arm_lpae_free_pages(start, table_size, &data->iop.cfg, data->iop.cookie);
 }
 
 static void arm_lpae_free_pgtable(struct io_pgtable *iop)
@@ -552,7 +570,7 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
 	if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS))
 		return 0;
 
-	tablep = __arm_lpae_alloc_pages(tablesz, GFP_ATOMIC, cfg);
+	tablep = __arm_lpae_alloc_pages(tablesz, GFP_ATOMIC, cfg, data->iop.cookie);
 	if (!tablep)
 		return 0; /* Bytes unmapped */
 
@@ -575,7 +593,7 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
 
 	pte = arm_lpae_install_table(tablep, ptep, blk_pte, data);
 	if (pte != blk_pte) {
-		__arm_lpae_free_pages(tablep, tablesz, cfg);
+		__arm_lpae_free_pages(tablep, tablesz, cfg, data->iop.cookie);
 		/*
 		 * We may race against someone unmapping another part of this
 		 * block, but anything else is invalid. We can't misinterpret
@@ -882,7 +900,7 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 
 	/* Looking good; allocate a pgd */
 	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data),
-					   GFP_KERNEL, cfg);
+					   GFP_KERNEL, cfg, cookie);
 	if (!data->pgd)
 		goto out_free_data;
 
@@ -984,7 +1002,7 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 
 	/* Allocate pgd pages */
 	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data),
-					   GFP_KERNEL, cfg);
+					   GFP_KERNEL, cfg, cookie);
 	if (!data->pgd)
 		goto out_free_data;
 
@@ -1059,7 +1077,7 @@ arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
 		 << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_DEV));
 
 	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data), GFP_KERNEL,
-					   cfg);
+					   cfg, cookie);
 	if (!data->pgd)
 		goto out_free_data;
 
@@ -1080,26 +1098,31 @@ out_free_data:
 }
 
 struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns = {
+	.caps	= IO_PGTABLE_CAP_CUSTOM_ALLOCATOR,
 	.alloc	= arm_64_lpae_alloc_pgtable_s1,
 	.free	= arm_lpae_free_pgtable,
 };
 
 struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s2_init_fns = {
+	.caps	= IO_PGTABLE_CAP_CUSTOM_ALLOCATOR,
 	.alloc	= arm_64_lpae_alloc_pgtable_s2,
 	.free	= arm_lpae_free_pgtable,
 };
 
 struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s1_init_fns = {
+	.caps	= IO_PGTABLE_CAP_CUSTOM_ALLOCATOR,
 	.alloc	= arm_32_lpae_alloc_pgtable_s1,
 	.free	= arm_lpae_free_pgtable,
 };
 
 struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s2_init_fns = {
+	.caps	= IO_PGTABLE_CAP_CUSTOM_ALLOCATOR,
 	.alloc	= arm_32_lpae_alloc_pgtable_s2,
 	.free	= arm_lpae_free_pgtable,
 };
 
 struct io_pgtable_init_fns io_pgtable_arm_mali_lpae_init_fns = {
+	.caps	= IO_PGTABLE_CAP_CUSTOM_ALLOCATOR,
 	.alloc	= arm_mali_lpae_alloc_pgtable,
 	.free	= arm_lpae_free_pgtable,
 };
diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c
index b843fcd365d2..8841c1487f00 100644
--- a/drivers/iommu/io-pgtable.c
+++ b/drivers/iommu/io-pgtable.c
@@ -34,6 +34,26 @@ io_pgtable_init_table[IO_PGTABLE_NUM_FMTS] = {
 #endif
 };
 
+static int check_custom_allocator(enum io_pgtable_fmt fmt,
+				  struct io_pgtable_cfg *cfg)
+{
+	/* No custom allocator, no need to check the format. */
+	if (!cfg->alloc && !cfg->free)
+		return 0;
+
+	/* When passing a custom allocator, both the alloc and free
+	 * functions should be provided.
+	 */
+	if (!cfg->alloc || !cfg->free)
+		return -EINVAL;
+
+	/* Make sure the format supports custom allocators. */
+	if (io_pgtable_init_table[fmt]->caps & IO_PGTABLE_CAP_CUSTOM_ALLOCATOR)
+		return 0;
+
+	return -EINVAL;
+}
+
 struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt,
 					    struct io_pgtable_cfg *cfg,
 					    void *cookie)
@@ -44,6 +64,9 @@ struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt,
 	if (fmt >= IO_PGTABLE_NUM_FMTS)
 		return NULL;
 
+	if (check_custom_allocator(fmt, cfg))
+		return NULL;
+
 	fns = io_pgtable_init_table[fmt];
 	if (!fns)
 		return NULL;
diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c
index b78671a8a914..65814cbc8402 100644
--- a/drivers/iommu/iommu-sva.c
+++ b/drivers/iommu/iommu-sva.c
@@ -12,32 +12,43 @@
 static DEFINE_MUTEX(iommu_sva_lock);
 
 /* Allocate a PASID for the mm within range (inclusive) */
-static int iommu_sva_alloc_pasid(struct mm_struct *mm, struct device *dev)
+static struct iommu_mm_data *iommu_alloc_mm_data(struct mm_struct *mm, struct device *dev)
 {
+	struct iommu_mm_data *iommu_mm;
 	ioasid_t pasid;
-	int ret = 0;
+
+	lockdep_assert_held(&iommu_sva_lock);
 
 	if (!arch_pgtable_dma_compat(mm))
-		return -EBUSY;
+		return ERR_PTR(-EBUSY);
 
-	mutex_lock(&iommu_sva_lock);
+	iommu_mm = mm->iommu_mm;
 	/* Is a PASID already associated with this mm? */
-	if (mm_valid_pasid(mm)) {
-		if (mm->pasid >= dev->iommu->max_pasids)
-			ret = -EOVERFLOW;
-		goto out;
+	if (iommu_mm) {
+		if (iommu_mm->pasid >= dev->iommu->max_pasids)
+			return ERR_PTR(-EOVERFLOW);
+		return iommu_mm;
 	}
 
+	iommu_mm = kzalloc(sizeof(struct iommu_mm_data), GFP_KERNEL);
+	if (!iommu_mm)
+		return ERR_PTR(-ENOMEM);
+
 	pasid = iommu_alloc_global_pasid(dev);
 	if (pasid == IOMMU_PASID_INVALID) {
-		ret = -ENOSPC;
-		goto out;
+		kfree(iommu_mm);
+		return ERR_PTR(-ENOSPC);
 	}
-	mm->pasid = pasid;
-	ret = 0;
-out:
-	mutex_unlock(&iommu_sva_lock);
-	return ret;
+	iommu_mm->pasid = pasid;
+	INIT_LIST_HEAD(&iommu_mm->sva_domains);
+	INIT_LIST_HEAD(&iommu_mm->sva_handles);
+	/*
+	 * Make sure the write to mm->iommu_mm is not reordered in front of
+	 * initialization to iommu_mm fields. If it does, readers may see a
+	 * valid iommu_mm with uninitialized values.
+	 */
+	smp_store_release(&mm->iommu_mm, iommu_mm);
+	return iommu_mm;
 }
 
 /**
@@ -58,57 +69,70 @@ out:
  */
 struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
 {
+	struct iommu_mm_data *iommu_mm;
 	struct iommu_domain *domain;
 	struct iommu_sva *handle;
 	int ret;
 
+	mutex_lock(&iommu_sva_lock);
+
 	/* Allocate mm->pasid if necessary. */
-	ret = iommu_sva_alloc_pasid(mm, dev);
-	if (ret)
-		return ERR_PTR(ret);
+	iommu_mm = iommu_alloc_mm_data(mm, dev);
+	if (IS_ERR(iommu_mm)) {
+		ret = PTR_ERR(iommu_mm);
+		goto out_unlock;
+	}
 
-	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
-	if (!handle)
-		return ERR_PTR(-ENOMEM);
+	list_for_each_entry(handle, &mm->iommu_mm->sva_handles, handle_item) {
+		if (handle->dev == dev) {
+			refcount_inc(&handle->users);
+			mutex_unlock(&iommu_sva_lock);
+			return handle;
+		}
+	}
 
-	mutex_lock(&iommu_sva_lock);
-	/* Search for an existing domain. */
-	domain = iommu_get_domain_for_dev_pasid(dev, mm->pasid,
-						IOMMU_DOMAIN_SVA);
-	if (IS_ERR(domain)) {
-		ret = PTR_ERR(domain);
+	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+	if (!handle) {
+		ret = -ENOMEM;
 		goto out_unlock;
 	}
 
-	if (domain) {
-		domain->users++;
-		goto out;
+	/* Search for an existing domain. */
+	list_for_each_entry(domain, &mm->iommu_mm->sva_domains, next) {
+		ret = iommu_attach_device_pasid(domain, dev, iommu_mm->pasid);
+		if (!ret) {
+			domain->users++;
+			goto out;
+		}
 	}
 
 	/* Allocate a new domain and set it on device pasid. */
 	domain = iommu_sva_domain_alloc(dev, mm);
 	if (!domain) {
 		ret = -ENOMEM;
-		goto out_unlock;
+		goto out_free_handle;
 	}
 
-	ret = iommu_attach_device_pasid(domain, dev, mm->pasid);
+	ret = iommu_attach_device_pasid(domain, dev, iommu_mm->pasid);
 	if (ret)
 		goto out_free_domain;
 	domain->users = 1;
+	list_add(&domain->next, &mm->iommu_mm->sva_domains);
+
 out:
+	refcount_set(&handle->users, 1);
+	list_add(&handle->handle_item, &mm->iommu_mm->sva_handles);
 	mutex_unlock(&iommu_sva_lock);
 	handle->dev = dev;
 	handle->domain = domain;
-
 	return handle;
 
 out_free_domain:
 	iommu_domain_free(domain);
+out_free_handle:
+	kfree(handle);
 out_unlock:
 	mutex_unlock(&iommu_sva_lock);
-	kfree(handle);
-
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(iommu_sva_bind_device);
@@ -124,12 +148,19 @@ EXPORT_SYMBOL_GPL(iommu_sva_bind_device);
 void iommu_sva_unbind_device(struct iommu_sva *handle)
 {
 	struct iommu_domain *domain = handle->domain;
-	ioasid_t pasid = domain->mm->pasid;
+	struct iommu_mm_data *iommu_mm = domain->mm->iommu_mm;
 	struct device *dev = handle->dev;
 
 	mutex_lock(&iommu_sva_lock);
+	if (!refcount_dec_and_test(&handle->users)) {
+		mutex_unlock(&iommu_sva_lock);
+		return;
+	}
+	list_del(&handle->handle_item);
+
+	iommu_detach_device_pasid(domain, dev, iommu_mm->pasid);
 	if (--domain->users == 0) {
-		iommu_detach_device_pasid(domain, dev, pasid);
+		list_del(&domain->next);
 		iommu_domain_free(domain);
 	}
 	mutex_unlock(&iommu_sva_lock);
@@ -141,7 +172,7 @@ u32 iommu_sva_get_pasid(struct iommu_sva *handle)
 {
 	struct iommu_domain *domain = handle->domain;
 
-	return domain->mm->pasid;
+	return mm_get_enqcmd_pasid(domain->mm);
 }
 EXPORT_SYMBOL_GPL(iommu_sva_get_pasid);
 
@@ -205,8 +236,11 @@ out_put_mm:
 
 void mm_pasid_drop(struct mm_struct *mm)
 {
-	if (likely(!mm_valid_pasid(mm)))
+	struct iommu_mm_data *iommu_mm = mm->iommu_mm;
+
+	if (!iommu_mm)
 		return;
 
-	iommu_free_global_pasid(mm->pasid);
+	iommu_free_global_pasid(iommu_mm->pasid);
+	kfree(iommu_mm);
 }
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 33e2a9b5d339..d14413916f93 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -148,7 +148,7 @@ struct iommu_group_attribute iommu_group_attr_##_name =		\
 static LIST_HEAD(iommu_device_list);
 static DEFINE_SPINLOCK(iommu_device_lock);
 
-static struct bus_type * const iommu_buses[] = {
+static const struct bus_type * const iommu_buses[] = {
 	&platform_bus_type,
 #ifdef CONFIG_PCI
 	&pci_bus_type,
@@ -257,13 +257,6 @@ int iommu_device_register(struct iommu_device *iommu,
 	/* We need to be able to take module references appropriately */
 	if (WARN_ON(is_module_address((unsigned long)ops) && !ops->owner))
 		return -EINVAL;
-	/*
-	 * Temporarily enforce global restriction to a single driver. This was
-	 * already the de-facto behaviour, since any possible combination of
-	 * existing drivers would compete for at least the PCI or platform bus.
-	 */
-	if (iommu_buses[0]->iommu_ops && iommu_buses[0]->iommu_ops != ops)
-		return -EBUSY;
 
 	iommu->ops = ops;
 	if (hwdev)
@@ -273,10 +266,8 @@ int iommu_device_register(struct iommu_device *iommu,
 	list_add_tail(&iommu->list, &iommu_device_list);
 	spin_unlock(&iommu_device_lock);
 
-	for (int i = 0; i < ARRAY_SIZE(iommu_buses) && !err; i++) {
-		iommu_buses[i]->iommu_ops = ops;
+	for (int i = 0; i < ARRAY_SIZE(iommu_buses) && !err; i++)
 		err = bus_iommu_probe(iommu_buses[i]);
-	}
 	if (err)
 		iommu_device_unregister(iommu);
 	return err;
@@ -329,7 +320,6 @@ int iommu_device_register_bus(struct iommu_device *iommu,
 	list_add_tail(&iommu->list, &iommu_device_list);
 	spin_unlock(&iommu_device_lock);
 
-	bus->iommu_ops = ops;
 	err = bus_iommu_probe(bus);
 	if (err) {
 		iommu_device_unregister_bus(iommu, bus, nb);
@@ -344,6 +334,8 @@ static struct dev_iommu *dev_iommu_get(struct device *dev)
 {
 	struct dev_iommu *param = dev->iommu;
 
+	lockdep_assert_held(&iommu_probe_device_lock);
+
 	if (param)
 		return param;
 
@@ -368,6 +360,15 @@ static void dev_iommu_free(struct device *dev)
 	kfree(param);
 }
 
+/*
+ * Internal equivalent of device_iommu_mapped() for when we care that a device
+ * actually has API ops, and don't want false positives from VFIO-only groups.
+ */
+static bool dev_has_iommu(struct device *dev)
+{
+	return dev->iommu && dev->iommu->iommu_dev;
+}
+
 static u32 dev_iommu_get_max_pasids(struct device *dev)
 {
 	u32 max_pasids = 0, bits = 0;
@@ -386,6 +387,15 @@ static u32 dev_iommu_get_max_pasids(struct device *dev)
 	return min_t(u32, max_pasids, dev->iommu->iommu_dev->max_pasids);
 }
 
+void dev_iommu_priv_set(struct device *dev, void *priv)
+{
+	/* FSL_PAMU does something weird */
+	if (!IS_ENABLED(CONFIG_FSL_PAMU))
+		lockdep_assert_held(&iommu_probe_device_lock);
+	dev->iommu->priv = priv;
+}
+EXPORT_SYMBOL_GPL(dev_iommu_priv_set);
+
 /*
  * Init the dev->iommu and dev->iommu_group in the struct device and get the
  * driver probed
@@ -489,11 +499,26 @@ DEFINE_MUTEX(iommu_probe_device_lock);
 
 static int __iommu_probe_device(struct device *dev, struct list_head *group_list)
 {
-	const struct iommu_ops *ops = dev->bus->iommu_ops;
+	const struct iommu_ops *ops;
+	struct iommu_fwspec *fwspec;
 	struct iommu_group *group;
 	struct group_device *gdev;
 	int ret;
 
+	/*
+	 * For FDT-based systems and ACPI IORT/VIOT, drivers register IOMMU
+	 * instances with non-NULL fwnodes, and client devices should have been
+	 * identified with a fwspec by this point. Otherwise, we can currently
+	 * assume that only one of Intel, AMD, s390, PAMU or legacy SMMUv2 can
+	 * be present, and that any of their registered instances has suitable
+	 * ops for probing, and thus cheekily co-opt the same mechanism.
+	 */
+	fwspec = dev_iommu_fwspec_get(dev);
+	if (fwspec && fwspec->ops)
+		ops = fwspec->ops;
+	else
+		ops = iommu_ops_from_fwnode(NULL);
+
 	if (!ops)
 		return -ENODEV;
 	/*
@@ -618,7 +643,7 @@ static void __iommu_group_remove_device(struct device *dev)
 
 		list_del(&device->list);
 		__iommu_group_free_device(group, device);
-		if (dev->iommu && dev->iommu->iommu_dev)
+		if (dev_has_iommu(dev))
 			iommu_deinit_device(dev);
 		else
 			dev->iommu_group = NULL;
@@ -817,7 +842,7 @@ int iommu_get_group_resv_regions(struct iommu_group *group,
 		 * Non-API groups still expose reserved_regions in sysfs,
 		 * so filter out calls that get here that way.
 		 */
-		if (!device->dev->iommu)
+		if (!dev_has_iommu(device->dev))
 			break;
 
 		INIT_LIST_HEAD(&dev_resv_regions);
@@ -1223,6 +1248,12 @@ void iommu_group_remove_device(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(iommu_group_remove_device);
 
+static struct device *iommu_group_first_dev(struct iommu_group *group)
+{
+	lockdep_assert_held(&group->mutex);
+	return list_first_entry(&group->devices, struct group_device, list)->dev;
+}
+
 /**
  * iommu_group_for_each_dev - iterate over each device in the group
  * @group: the group
@@ -1751,30 +1782,13 @@ __iommu_group_alloc_default_domain(struct iommu_group *group, int req_type)
 }
 
 /*
- * Returns the iommu_ops for the devices in an iommu group.
- *
- * It is assumed that all devices in an iommu group are managed by a single
- * IOMMU unit. Therefore, this returns the dev_iommu_ops of the first device
- * in the group.
- */
-static const struct iommu_ops *group_iommu_ops(struct iommu_group *group)
-{
-	struct group_device *device =
-		list_first_entry(&group->devices, struct group_device, list);
-
-	lockdep_assert_held(&group->mutex);
-
-	return dev_iommu_ops(device->dev);
-}
-
-/*
  * req_type of 0 means "auto" which means to select a domain based on
  * iommu_def_domain_type or what the driver actually supports.
  */
 static struct iommu_domain *
 iommu_group_alloc_default_domain(struct iommu_group *group, int req_type)
 {
-	const struct iommu_ops *ops = group_iommu_ops(group);
+	const struct iommu_ops *ops = dev_iommu_ops(iommu_group_first_dev(group));
 	struct iommu_domain *dom;
 
 	lockdep_assert_held(&group->mutex);
@@ -1785,7 +1799,7 @@ iommu_group_alloc_default_domain(struct iommu_group *group, int req_type)
 	 * domain. Do not use in new drivers.
 	 */
 	if (ops->default_domain) {
-		if (req_type)
+		if (req_type != ops->default_domain->type)
 			return ERR_PTR(-EINVAL);
 		return ops->default_domain;
 	}
@@ -1854,13 +1868,21 @@ static int iommu_bus_notifier(struct notifier_block *nb,
 static int iommu_get_def_domain_type(struct iommu_group *group,
 				     struct device *dev, int cur_type)
 {
-	const struct iommu_ops *ops = group_iommu_ops(group);
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
 	int type;
 
-	if (!ops->def_domain_type)
-		return cur_type;
-
-	type = ops->def_domain_type(dev);
+	if (ops->default_domain) {
+		/*
+		 * Drivers that declare a global static default_domain will
+		 * always choose that.
+		 */
+		type = ops->default_domain->type;
+	} else {
+		if (ops->def_domain_type)
+			type = ops->def_domain_type(dev);
+		else
+			return cur_type;
+	}
 	if (!type || cur_type == type)
 		return cur_type;
 	if (!cur_type)
@@ -2003,9 +2025,28 @@ int bus_iommu_probe(const struct bus_type *bus)
 	return 0;
 }
 
+/**
+ * iommu_present() - make platform-specific assumptions about an IOMMU
+ * @bus: bus to check
+ *
+ * Do not use this function. You want device_iommu_mapped() instead.
+ *
+ * Return: true if some IOMMU is present and aware of devices on the given bus;
+ * in general it may not be the only IOMMU, and it may not have anything to do
+ * with whatever device you are ultimately interested in.
+ */
 bool iommu_present(const struct bus_type *bus)
 {
-	return bus->iommu_ops != NULL;
+	bool ret = false;
+
+	for (int i = 0; i < ARRAY_SIZE(iommu_buses); i++) {
+		if (iommu_buses[i] == bus) {
+			spin_lock(&iommu_device_lock);
+			ret = !list_empty(&iommu_device_list);
+			spin_unlock(&iommu_device_lock);
+		}
+	}
+	return ret;
 }
 EXPORT_SYMBOL_GPL(iommu_present);
 
@@ -2021,7 +2062,7 @@ bool device_iommu_capable(struct device *dev, enum iommu_cap cap)
 {
 	const struct iommu_ops *ops;
 
-	if (!dev->iommu || !dev->iommu->iommu_dev)
+	if (!dev_has_iommu(dev))
 		return false;
 
 	ops = dev_iommu_ops(dev);
@@ -2107,6 +2148,7 @@ static struct iommu_domain *__iommu_domain_alloc(const struct iommu_ops *ops,
 		return ERR_PTR(-ENOMEM);
 
 	domain->type = type;
+	domain->owner = ops;
 	/*
 	 * If not already set, assume all sizes by default; the driver
 	 * may override this later
@@ -2132,21 +2174,37 @@ static struct iommu_domain *__iommu_domain_alloc(const struct iommu_ops *ops,
 static struct iommu_domain *
 __iommu_group_domain_alloc(struct iommu_group *group, unsigned int type)
 {
-	struct device *dev =
-		list_first_entry(&group->devices, struct group_device, list)
-			->dev;
+	struct device *dev = iommu_group_first_dev(group);
 
-	return __iommu_domain_alloc(group_iommu_ops(group), dev, type);
+	return __iommu_domain_alloc(dev_iommu_ops(dev), dev, type);
+}
+
+static int __iommu_domain_alloc_dev(struct device *dev, void *data)
+{
+	const struct iommu_ops **ops = data;
+
+	if (!dev_has_iommu(dev))
+		return 0;
+
+	if (WARN_ONCE(*ops && *ops != dev_iommu_ops(dev),
+		      "Multiple IOMMU drivers present for bus %s, which the public IOMMU API can't fully support yet. You will still need to disable one or more for this to work, sorry!\n",
+		      dev_bus_name(dev)))
+		return -EBUSY;
+
+	*ops = dev_iommu_ops(dev);
+	return 0;
 }
 
 struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus)
 {
+	const struct iommu_ops *ops = NULL;
+	int err = bus_for_each_dev(bus, NULL, &ops, __iommu_domain_alloc_dev);
 	struct iommu_domain *domain;
 
-	if (bus == NULL || bus->iommu_ops == NULL)
+	if (err || !ops)
 		return NULL;
-	domain = __iommu_domain_alloc(bus->iommu_ops, NULL,
-				    IOMMU_DOMAIN_UNMANAGED);
+
+	domain = __iommu_domain_alloc(ops, NULL, IOMMU_DOMAIN_UNMANAGED);
 	if (IS_ERR(domain))
 		return NULL;
 	return domain;
@@ -2284,10 +2342,16 @@ struct iommu_domain *iommu_get_dma_domain(struct device *dev)
 static int __iommu_attach_group(struct iommu_domain *domain,
 				struct iommu_group *group)
 {
+	struct device *dev;
+
 	if (group->domain && group->domain != group->default_domain &&
 	    group->domain != group->blocking_domain)
 		return -EBUSY;
 
+	dev = iommu_group_first_dev(group);
+	if (!dev_has_iommu(dev) || dev_iommu_ops(dev) != domain->owner)
+		return -EINVAL;
+
 	return __iommu_group_set_domain(group, domain);
 }
 
@@ -3004,8 +3068,8 @@ EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids);
  */
 int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat)
 {
-	if (dev->iommu && dev->iommu->iommu_dev) {
-		const struct iommu_ops *ops = dev->iommu->iommu_dev->ops;
+	if (dev_has_iommu(dev)) {
+		const struct iommu_ops *ops = dev_iommu_ops(dev);
 
 		if (ops->dev_enable_feat)
 			return ops->dev_enable_feat(dev, feat);
@@ -3020,8 +3084,8 @@ EXPORT_SYMBOL_GPL(iommu_dev_enable_feature);
  */
 int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat)
 {
-	if (dev->iommu && dev->iommu->iommu_dev) {
-		const struct iommu_ops *ops = dev->iommu->iommu_dev->ops;
+	if (dev_has_iommu(dev)) {
+		const struct iommu_ops *ops = dev_iommu_ops(dev);
 
 		if (ops->dev_disable_feat)
 			return ops->dev_disable_feat(dev, feat);
@@ -3481,6 +3545,9 @@ int iommu_attach_device_pasid(struct iommu_domain *domain,
 	if (!group)
 		return -ENODEV;
 
+	if (!dev_has_iommu(dev) || dev_iommu_ops(dev) != domain->owner)
+		return -EINVAL;
+
 	mutex_lock(&group->mutex);
 	curr = xa_cmpxchg(&group->pasid_array, pasid, NULL, domain, GFP_KERNEL);
 	if (curr) {
@@ -3569,6 +3636,7 @@ struct iommu_domain *iommu_sva_domain_alloc(struct device *dev,
 	domain->type = IOMMU_DOMAIN_SVA;
 	mmgrab(mm);
 	domain->mm = mm;
+	domain->owner = ops;
 	domain->iopf_handler = iommu_sva_handle_iopf;
 	domain->fault_data = mm;
 
diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index cbb5df0a6c32..33d142f8057d 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -135,6 +135,7 @@ iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
 			hwpt->domain = NULL;
 			goto out_abort;
 		}
+		hwpt->domain->owner = ops;
 	} else {
 		hwpt->domain = iommu_domain_alloc(idev->dev->bus);
 		if (!hwpt->domain) {
@@ -233,6 +234,7 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx,
 		hwpt->domain = NULL;
 		goto out_abort;
 	}
+	hwpt->domain->owner = ops;
 
 	if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED)) {
 		rc = -EINVAL;
@@ -261,7 +263,8 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd)
 
 	if (cmd->__reserved)
 		return -EOPNOTSUPP;
-	if (cmd->data_type == IOMMU_HWPT_DATA_NONE && cmd->data_len)
+	if ((cmd->data_type == IOMMU_HWPT_DATA_NONE && cmd->data_len) ||
+	    (cmd->data_type != IOMMU_HWPT_DATA_NONE && !cmd->data_len))
 		return -EINVAL;
 
 	idev = iommufd_get_device(ucmd, cmd->dev_id);
@@ -371,3 +374,44 @@ int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd)
 	iommufd_put_object(ucmd->ictx, &hwpt_paging->common.obj);
 	return rc;
 }
+
+int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd)
+{
+	struct iommu_hwpt_invalidate *cmd = ucmd->cmd;
+	struct iommu_user_data_array data_array = {
+		.type = cmd->data_type,
+		.uptr = u64_to_user_ptr(cmd->data_uptr),
+		.entry_len = cmd->entry_len,
+		.entry_num = cmd->entry_num,
+	};
+	struct iommufd_hw_pagetable *hwpt;
+	u32 done_num = 0;
+	int rc;
+
+	if (cmd->__reserved) {
+		rc = -EOPNOTSUPP;
+		goto out;
+	}
+
+	if (cmd->entry_num && (!cmd->data_uptr || !cmd->entry_len)) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	hwpt = iommufd_get_hwpt_nested(ucmd, cmd->hwpt_id);
+	if (IS_ERR(hwpt)) {
+		rc = PTR_ERR(hwpt);
+		goto out;
+	}
+
+	rc = hwpt->domain->ops->cache_invalidate_user(hwpt->domain,
+						      &data_array);
+	done_num = data_array.entry_num;
+
+	iommufd_put_object(ucmd->ictx, &hwpt->obj);
+out:
+	cmd->entry_num = done_num;
+	if (iommufd_ucmd_respond(ucmd, sizeof(*cmd)))
+		return -EFAULT;
+	return rc;
+}
diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c
index 504ac1b01b2d..05fd9d3abf1b 100644
--- a/drivers/iommu/iommufd/io_pagetable.c
+++ b/drivers/iommu/iommufd/io_pagetable.c
@@ -1330,20 +1330,23 @@ out_unlock:
 
 int iopt_add_access(struct io_pagetable *iopt, struct iommufd_access *access)
 {
+	u32 new_id;
 	int rc;
 
 	down_write(&iopt->domains_rwsem);
 	down_write(&iopt->iova_rwsem);
-	rc = xa_alloc(&iopt->access_list, &access->iopt_access_list_id, access,
-		      xa_limit_16b, GFP_KERNEL_ACCOUNT);
+	rc = xa_alloc(&iopt->access_list, &new_id, access, xa_limit_16b,
+		      GFP_KERNEL_ACCOUNT);
+
 	if (rc)
 		goto out_unlock;
 
 	rc = iopt_calculate_iova_alignment(iopt);
 	if (rc) {
-		xa_erase(&iopt->access_list, access->iopt_access_list_id);
+		xa_erase(&iopt->access_list, new_id);
 		goto out_unlock;
 	}
+	access->iopt_access_list_id = new_id;
 
 out_unlock:
 	up_write(&iopt->iova_rwsem);
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index abae041e256f..991f864d1f9b 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -328,6 +328,15 @@ iommufd_get_hwpt_paging(struct iommufd_ucmd *ucmd, u32 id)
 					       IOMMUFD_OBJ_HWPT_PAGING),
 			    struct iommufd_hwpt_paging, common.obj);
 }
+
+static inline struct iommufd_hw_pagetable *
+iommufd_get_hwpt_nested(struct iommufd_ucmd *ucmd, u32 id)
+{
+	return container_of(iommufd_get_object(ucmd->ictx, id,
+					       IOMMUFD_OBJ_HWPT_NESTED),
+			    struct iommufd_hw_pagetable, obj);
+}
+
 int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd);
 int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd);
 
@@ -345,6 +354,7 @@ void iommufd_hwpt_paging_abort(struct iommufd_object *obj);
 void iommufd_hwpt_nested_destroy(struct iommufd_object *obj);
 void iommufd_hwpt_nested_abort(struct iommufd_object *obj);
 int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd);
+int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd);
 
 static inline void iommufd_hw_pagetable_put(struct iommufd_ctx *ictx,
 					    struct iommufd_hw_pagetable *hwpt)
diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h
index 7910fbe1962d..e854d3f67205 100644
--- a/drivers/iommu/iommufd/iommufd_test.h
+++ b/drivers/iommu/iommufd/iommufd_test.h
@@ -21,6 +21,7 @@ enum {
 	IOMMU_TEST_OP_ACCESS_REPLACE_IOAS,
 	IOMMU_TEST_OP_MOCK_DOMAIN_FLAGS,
 	IOMMU_TEST_OP_DIRTY,
+	IOMMU_TEST_OP_MD_CHECK_IOTLB,
 };
 
 enum {
@@ -44,6 +45,7 @@ enum {
 
 enum {
 	MOCK_FLAGS_DEVICE_NO_DIRTY = 1 << 0,
+	MOCK_FLAGS_DEVICE_HUGE_IOVA = 1 << 1,
 };
 
 enum {
@@ -121,6 +123,10 @@ struct iommu_test_cmd {
 			__aligned_u64 uptr;
 			__aligned_u64 out_nr_dirty;
 		} dirty;
+		struct {
+			__u32 id;
+			__u32 iotlb;
+		} check_iotlb;
 	};
 	__u32 last;
 };
@@ -148,4 +154,22 @@ struct iommu_hwpt_selftest {
 	__u32 iotlb;
 };
 
+/* Should not be equal to any defined value in enum iommu_hwpt_invalidate_data_type */
+#define IOMMU_HWPT_INVALIDATE_DATA_SELFTEST 0xdeadbeef
+#define IOMMU_HWPT_INVALIDATE_DATA_SELFTEST_INVALID 0xdadbeef
+
+/**
+ * struct iommu_hwpt_invalidate_selftest - Invalidation data for Mock driver
+ *                                         (IOMMU_HWPT_INVALIDATE_DATA_SELFTEST)
+ * @flags: Invalidate flags
+ * @iotlb_id: Invalidate iotlb entry index
+ *
+ * If IOMMU_TEST_INVALIDATE_ALL is set in @flags, @iotlb_id will be ignored
+ */
+struct iommu_hwpt_invalidate_selftest {
+#define IOMMU_TEST_INVALIDATE_FLAG_ALL	(1 << 0)
+	__u32 flags;
+	__u32 iotlb_id;
+};
+
 #endif
diff --git a/drivers/iommu/iommufd/iova_bitmap.c b/drivers/iommu/iommufd/iova_bitmap.c
index 0a92c9eeaf7f..db8c46bee155 100644
--- a/drivers/iommu/iommufd/iova_bitmap.c
+++ b/drivers/iommu/iommufd/iova_bitmap.c
@@ -100,7 +100,7 @@ struct iova_bitmap {
 	struct iova_bitmap_map mapped;
 
 	/* userspace address of the bitmap */
-	u64 __user *bitmap;
+	u8 __user *bitmap;
 
 	/* u64 index that @mapped points to */
 	unsigned long mapped_base_index;
@@ -113,6 +113,9 @@ struct iova_bitmap {
 
 	/* length of the IOVA range for the whole bitmap */
 	size_t length;
+
+	/* length of the IOVA range set ahead the pinned pages */
+	unsigned long set_ahead_length;
 };
 
 /*
@@ -162,7 +165,7 @@ static int iova_bitmap_get(struct iova_bitmap *bitmap)
 {
 	struct iova_bitmap_map *mapped = &bitmap->mapped;
 	unsigned long npages;
-	u64 __user *addr;
+	u8 __user *addr;
 	long ret;
 
 	/*
@@ -176,17 +179,18 @@ static int iova_bitmap_get(struct iova_bitmap *bitmap)
 			       sizeof(*bitmap->bitmap), PAGE_SIZE);
 
 	/*
-	 * We always cap at max number of 'struct page' a base page can fit.
-	 * This is, for example, on x86 means 2M of bitmap data max.
-	 */
-	npages = min(npages,  PAGE_SIZE / sizeof(struct page *));
-
-	/*
 	 * Bitmap address to be pinned is calculated via pointer arithmetic
 	 * with bitmap u64 word index.
 	 */
 	addr = bitmap->bitmap + bitmap->mapped_base_index;
 
+	/*
+	 * We always cap at max number of 'struct page' a base page can fit.
+	 * This is, for example, on x86 means 2M of bitmap data max.
+	 */
+	npages = min(npages + !!offset_in_page(addr),
+		     PAGE_SIZE / sizeof(struct page *));
+
 	ret = pin_user_pages_fast((unsigned long)addr, npages,
 				  FOLL_WRITE, mapped->pages);
 	if (ret <= 0)
@@ -247,7 +251,7 @@ struct iova_bitmap *iova_bitmap_alloc(unsigned long iova, size_t length,
 
 	mapped = &bitmap->mapped;
 	mapped->pgshift = __ffs(page_size);
-	bitmap->bitmap = data;
+	bitmap->bitmap = (u8 __user *)data;
 	bitmap->mapped_total_index =
 		iova_bitmap_offset_to_index(bitmap, length - 1) + 1;
 	bitmap->iova = iova;
@@ -304,7 +308,7 @@ static unsigned long iova_bitmap_mapped_remaining(struct iova_bitmap *bitmap)
 
 	remaining = bitmap->mapped_total_index - bitmap->mapped_base_index;
 	remaining = min_t(unsigned long, remaining,
-			  bytes / sizeof(*bitmap->bitmap));
+			  DIV_ROUND_UP(bytes, sizeof(*bitmap->bitmap)));
 
 	return remaining;
 }
@@ -341,6 +345,32 @@ static bool iova_bitmap_done(struct iova_bitmap *bitmap)
 	return bitmap->mapped_base_index >= bitmap->mapped_total_index;
 }
 
+static int iova_bitmap_set_ahead(struct iova_bitmap *bitmap,
+				 size_t set_ahead_length)
+{
+	int ret = 0;
+
+	while (set_ahead_length > 0 && !iova_bitmap_done(bitmap)) {
+		unsigned long length = iova_bitmap_mapped_length(bitmap);
+		unsigned long iova = iova_bitmap_mapped_iova(bitmap);
+
+		ret = iova_bitmap_get(bitmap);
+		if (ret)
+			break;
+
+		length = min(length, set_ahead_length);
+		iova_bitmap_set(bitmap, iova, length);
+
+		set_ahead_length -= length;
+		bitmap->mapped_base_index +=
+			iova_bitmap_offset_to_index(bitmap, length - 1) + 1;
+		iova_bitmap_put(bitmap);
+	}
+
+	bitmap->set_ahead_length = 0;
+	return ret;
+}
+
 /*
  * Advances to the next range, releases the current pinned
  * pages and pins the next set of bitmap pages.
@@ -357,6 +387,15 @@ static int iova_bitmap_advance(struct iova_bitmap *bitmap)
 	if (iova_bitmap_done(bitmap))
 		return 0;
 
+	/* Iterate, set and skip any bits requested for next iteration */
+	if (bitmap->set_ahead_length) {
+		int ret;
+
+		ret = iova_bitmap_set_ahead(bitmap, bitmap->set_ahead_length);
+		if (ret)
+			return ret;
+	}
+
 	/* When advancing the index we pin the next set of bitmap pages */
 	return iova_bitmap_get(bitmap);
 }
@@ -409,6 +448,7 @@ void iova_bitmap_set(struct iova_bitmap *bitmap,
 			mapped->pgshift) + mapped->pgoff * BITS_PER_BYTE;
 	unsigned long last_bit = (((iova + length - 1) - mapped->iova) >>
 			mapped->pgshift) + mapped->pgoff * BITS_PER_BYTE;
+	unsigned long last_page_idx = mapped->npages - 1;
 
 	do {
 		unsigned int page_idx = cur_bit / BITS_PER_PAGE;
@@ -417,10 +457,18 @@ void iova_bitmap_set(struct iova_bitmap *bitmap,
 					 last_bit - cur_bit + 1);
 		void *kaddr;
 
+		if (unlikely(page_idx > last_page_idx))
+			break;
+
 		kaddr = kmap_local_page(mapped->pages[page_idx]);
 		bitmap_set(kaddr, offset, nbits);
 		kunmap_local(kaddr);
 		cur_bit += nbits;
 	} while (cur_bit <= last_bit);
+
+	if (unlikely(cur_bit <= last_bit)) {
+		bitmap->set_ahead_length =
+			((last_bit - cur_bit + 1) << bitmap->mapped.pgshift);
+	}
 }
 EXPORT_SYMBOL_NS_GPL(iova_bitmap_set, IOMMUFD);
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index c9091e46d208..39b32932c61e 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -322,6 +322,7 @@ union ucmd_buffer {
 	struct iommu_hw_info info;
 	struct iommu_hwpt_alloc hwpt;
 	struct iommu_hwpt_get_dirty_bitmap get_dirty_bitmap;
+	struct iommu_hwpt_invalidate cache;
 	struct iommu_hwpt_set_dirty_tracking set_dirty_tracking;
 	struct iommu_ioas_alloc alloc;
 	struct iommu_ioas_allow_iovas allow_iovas;
@@ -360,6 +361,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = {
 		 __reserved),
 	IOCTL_OP(IOMMU_HWPT_GET_DIRTY_BITMAP, iommufd_hwpt_get_dirty_bitmap,
 		 struct iommu_hwpt_get_dirty_bitmap, data),
+	IOCTL_OP(IOMMU_HWPT_INVALIDATE, iommufd_hwpt_invalidate,
+		 struct iommu_hwpt_invalidate, __reserved),
 	IOCTL_OP(IOMMU_HWPT_SET_DIRTY_TRACKING, iommufd_hwpt_set_dirty_tracking,
 		 struct iommu_hwpt_set_dirty_tracking, __reserved),
 	IOCTL_OP(IOMMU_IOAS_ALLOC, iommufd_ioas_alloc_ioctl,
diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
index 022ef8f55088..7a2199470f31 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -25,9 +25,23 @@ static struct iommu_domain_ops domain_nested_ops;
 
 size_t iommufd_test_memory_limit = 65536;
 
+struct mock_bus_type {
+	struct bus_type bus;
+	struct notifier_block nb;
+};
+
+static struct mock_bus_type iommufd_mock_bus_type = {
+	.bus = {
+		.name = "iommufd_mock",
+	},
+};
+
+static DEFINE_IDA(mock_dev_ida);
+
 enum {
 	MOCK_DIRTY_TRACK = 1,
 	MOCK_IO_PAGE_SIZE = PAGE_SIZE / 2,
+	MOCK_HUGE_PAGE_SIZE = 512 * MOCK_IO_PAGE_SIZE,
 
 	/*
 	 * Like a real page table alignment requires the low bits of the address
@@ -40,6 +54,7 @@ enum {
 	MOCK_PFN_START_IOVA = _MOCK_PFN_START,
 	MOCK_PFN_LAST_IOVA = _MOCK_PFN_START,
 	MOCK_PFN_DIRTY_IOVA = _MOCK_PFN_START << 1,
+	MOCK_PFN_HUGE_IOVA = _MOCK_PFN_START << 2,
 };
 
 /*
@@ -48,8 +63,8 @@ enum {
  * In syzkaller mode the 64 bit IOVA is converted into an nth area and offset
  * value. This has a much smaller randomization space and syzkaller can hit it.
  */
-static unsigned long iommufd_test_syz_conv_iova(struct io_pagetable *iopt,
-						u64 *iova)
+static unsigned long __iommufd_test_syz_conv_iova(struct io_pagetable *iopt,
+						  u64 *iova)
 {
 	struct syz_layout {
 		__u32 nth_area;
@@ -73,6 +88,21 @@ static unsigned long iommufd_test_syz_conv_iova(struct io_pagetable *iopt,
 	return 0;
 }
 
+static unsigned long iommufd_test_syz_conv_iova(struct iommufd_access *access,
+						u64 *iova)
+{
+	unsigned long ret;
+
+	mutex_lock(&access->ioas_lock);
+	if (!access->ioas) {
+		mutex_unlock(&access->ioas_lock);
+		return 0;
+	}
+	ret = __iommufd_test_syz_conv_iova(&access->ioas->iopt, iova);
+	mutex_unlock(&access->ioas_lock);
+	return ret;
+}
+
 void iommufd_test_syz_conv_iova_id(struct iommufd_ucmd *ucmd,
 				   unsigned int ioas_id, u64 *iova, u32 *flags)
 {
@@ -85,7 +115,7 @@ void iommufd_test_syz_conv_iova_id(struct iommufd_ucmd *ucmd,
 	ioas = iommufd_get_ioas(ucmd->ictx, ioas_id);
 	if (IS_ERR(ioas))
 		return;
-	*iova = iommufd_test_syz_conv_iova(&ioas->iopt, iova);
+	*iova = __iommufd_test_syz_conv_iova(&ioas->iopt, iova);
 	iommufd_put_object(ucmd->ictx, &ioas->obj);
 }
 
@@ -108,6 +138,7 @@ enum selftest_obj_type {
 struct mock_dev {
 	struct device dev;
 	unsigned long flags;
+	int id;
 };
 
 struct selftest_obj {
@@ -178,6 +209,34 @@ static int mock_domain_set_dirty_tracking(struct iommu_domain *domain,
 	return 0;
 }
 
+static bool mock_test_and_clear_dirty(struct mock_iommu_domain *mock,
+				      unsigned long iova, size_t page_size,
+				      unsigned long flags)
+{
+	unsigned long cur, end = iova + page_size - 1;
+	bool dirty = false;
+	void *ent, *old;
+
+	for (cur = iova; cur < end; cur += MOCK_IO_PAGE_SIZE) {
+		ent = xa_load(&mock->pfns, cur / MOCK_IO_PAGE_SIZE);
+		if (!ent || !(xa_to_value(ent) & MOCK_PFN_DIRTY_IOVA))
+			continue;
+
+		dirty = true;
+		/* Clear dirty */
+		if (!(flags & IOMMU_DIRTY_NO_CLEAR)) {
+			unsigned long val;
+
+			val = xa_to_value(ent) & ~MOCK_PFN_DIRTY_IOVA;
+			old = xa_store(&mock->pfns, cur / MOCK_IO_PAGE_SIZE,
+				       xa_mk_value(val), GFP_KERNEL);
+			WARN_ON_ONCE(ent != old);
+		}
+	}
+
+	return dirty;
+}
+
 static int mock_domain_read_and_clear_dirty(struct iommu_domain *domain,
 					    unsigned long iova, size_t size,
 					    unsigned long flags,
@@ -185,31 +244,31 @@ static int mock_domain_read_and_clear_dirty(struct iommu_domain *domain,
 {
 	struct mock_iommu_domain *mock =
 		container_of(domain, struct mock_iommu_domain, domain);
-	unsigned long i, max = size / MOCK_IO_PAGE_SIZE;
-	void *ent, *old;
+	unsigned long end = iova + size;
+	void *ent;
 
 	if (!(mock->flags & MOCK_DIRTY_TRACK) && dirty->bitmap)
 		return -EINVAL;
 
-	for (i = 0; i < max; i++) {
-		unsigned long cur = iova + i * MOCK_IO_PAGE_SIZE;
+	do {
+		unsigned long pgsize = MOCK_IO_PAGE_SIZE;
+		unsigned long head;
 
-		ent = xa_load(&mock->pfns, cur / MOCK_IO_PAGE_SIZE);
-		if (ent && (xa_to_value(ent) & MOCK_PFN_DIRTY_IOVA)) {
-			/* Clear dirty */
-			if (!(flags & IOMMU_DIRTY_NO_CLEAR)) {
-				unsigned long val;
-
-				val = xa_to_value(ent) & ~MOCK_PFN_DIRTY_IOVA;
-				old = xa_store(&mock->pfns,
-					       cur / MOCK_IO_PAGE_SIZE,
-					       xa_mk_value(val), GFP_KERNEL);
-				WARN_ON_ONCE(ent != old);
-			}
-			iommu_dirty_bitmap_record(dirty, cur,
-						  MOCK_IO_PAGE_SIZE);
+		ent = xa_load(&mock->pfns, iova / MOCK_IO_PAGE_SIZE);
+		if (!ent) {
+			iova += pgsize;
+			continue;
 		}
-	}
+
+		if (xa_to_value(ent) & MOCK_PFN_HUGE_IOVA)
+			pgsize = MOCK_HUGE_PAGE_SIZE;
+		head = iova & ~(pgsize - 1);
+
+		/* Clear dirty */
+		if (mock_test_and_clear_dirty(mock, head, pgsize, flags))
+			iommu_dirty_bitmap_record(dirty, head, pgsize);
+		iova = head + pgsize;
+	} while (iova < end);
 
 	return 0;
 }
@@ -221,6 +280,7 @@ const struct iommu_dirty_ops dirty_ops = {
 
 static struct iommu_domain *mock_domain_alloc_paging(struct device *dev)
 {
+	struct mock_dev *mdev = container_of(dev, struct mock_dev, dev);
 	struct mock_iommu_domain *mock;
 
 	mock = kzalloc(sizeof(*mock), GFP_KERNEL);
@@ -229,6 +289,8 @@ static struct iommu_domain *mock_domain_alloc_paging(struct device *dev)
 	mock->domain.geometry.aperture_start = MOCK_APERTURE_START;
 	mock->domain.geometry.aperture_end = MOCK_APERTURE_LAST;
 	mock->domain.pgsize_bitmap = MOCK_IO_PAGE_SIZE;
+	if (dev && mdev->flags & MOCK_FLAGS_DEVICE_HUGE_IOVA)
+		mock->domain.pgsize_bitmap |= MOCK_HUGE_PAGE_SIZE;
 	mock->domain.ops = mock_ops.default_domain_ops;
 	mock->domain.type = IOMMU_DOMAIN_UNMANAGED;
 	xa_init(&mock->pfns);
@@ -274,7 +336,7 @@ mock_domain_alloc_user(struct device *dev, u32 flags,
 			return ERR_PTR(-EOPNOTSUPP);
 		if (user_data || (has_dirty_flag && no_dirty_ops))
 			return ERR_PTR(-EOPNOTSUPP);
-		domain = mock_domain_alloc_paging(NULL);
+		domain = mock_domain_alloc_paging(dev);
 		if (!domain)
 			return ERR_PTR(-ENOMEM);
 		if (has_dirty_flag)
@@ -337,6 +399,9 @@ static int mock_domain_map_pages(struct iommu_domain *domain,
 
 			if (pgcount == 1 && cur + MOCK_IO_PAGE_SIZE == pgsize)
 				flags = MOCK_PFN_LAST_IOVA;
+			if (pgsize != MOCK_IO_PAGE_SIZE) {
+				flags |= MOCK_PFN_HUGE_IOVA;
+			}
 			old = xa_store(&mock->pfns, iova / MOCK_IO_PAGE_SIZE,
 				       xa_mk_value((paddr / MOCK_IO_PAGE_SIZE) |
 						   flags),
@@ -381,20 +446,27 @@ static size_t mock_domain_unmap_pages(struct iommu_domain *domain,
 
 			/*
 			 * iommufd generates unmaps that must be a strict
-			 * superset of the map's performend So every starting
-			 * IOVA should have been an iova passed to map, and the
+			 * superset of the map's performend So every
+			 * starting/ending IOVA should have been an iova passed
+			 * to map.
 			 *
-			 * First IOVA must be present and have been a first IOVA
-			 * passed to map_pages
+			 * This simple logic doesn't work when the HUGE_PAGE is
+			 * turned on since the core code will automatically
+			 * switch between the two page sizes creating a break in
+			 * the unmap calls. The break can land in the middle of
+			 * contiguous IOVA.
 			 */
-			if (first) {
-				WARN_ON(ent && !(xa_to_value(ent) &
-						 MOCK_PFN_START_IOVA));
-				first = false;
+			if (!(domain->pgsize_bitmap & MOCK_HUGE_PAGE_SIZE)) {
+				if (first) {
+					WARN_ON(ent && !(xa_to_value(ent) &
+							 MOCK_PFN_START_IOVA));
+					first = false;
+				}
+				if (pgcount == 1 &&
+				    cur + MOCK_IO_PAGE_SIZE == pgsize)
+					WARN_ON(ent && !(xa_to_value(ent) &
+							 MOCK_PFN_LAST_IOVA));
 			}
-			if (pgcount == 1 && cur + MOCK_IO_PAGE_SIZE == pgsize)
-				WARN_ON(ent && !(xa_to_value(ent) &
-						 MOCK_PFN_LAST_IOVA));
 
 			iova += MOCK_IO_PAGE_SIZE;
 			ret += MOCK_IO_PAGE_SIZE;
@@ -437,6 +509,8 @@ static struct iommu_device mock_iommu_device = {
 
 static struct iommu_device *mock_probe_device(struct device *dev)
 {
+	if (dev->bus != &iommufd_mock_bus_type.bus)
+		return ERR_PTR(-ENODEV);
 	return &mock_iommu_device;
 }
 
@@ -473,9 +547,59 @@ static void mock_domain_free_nested(struct iommu_domain *domain)
 	kfree(mock_nested);
 }
 
+static int
+mock_domain_cache_invalidate_user(struct iommu_domain *domain,
+				  struct iommu_user_data_array *array)
+{
+	struct mock_iommu_domain_nested *mock_nested =
+		container_of(domain, struct mock_iommu_domain_nested, domain);
+	struct iommu_hwpt_invalidate_selftest inv;
+	u32 processed = 0;
+	int i = 0, j;
+	int rc = 0;
+
+	if (array->type != IOMMU_HWPT_INVALIDATE_DATA_SELFTEST) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	for ( ; i < array->entry_num; i++) {
+		rc = iommu_copy_struct_from_user_array(&inv, array,
+						       IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+						       i, iotlb_id);
+		if (rc)
+			break;
+
+		if (inv.flags & ~IOMMU_TEST_INVALIDATE_FLAG_ALL) {
+			rc = -EOPNOTSUPP;
+			break;
+		}
+
+		if (inv.iotlb_id > MOCK_NESTED_DOMAIN_IOTLB_ID_MAX) {
+			rc = -EINVAL;
+			break;
+		}
+
+		if (inv.flags & IOMMU_TEST_INVALIDATE_FLAG_ALL) {
+			/* Invalidate all mock iotlb entries and ignore iotlb_id */
+			for (j = 0; j < MOCK_NESTED_DOMAIN_IOTLB_NUM; j++)
+				mock_nested->iotlb[j] = 0;
+		} else {
+			mock_nested->iotlb[inv.iotlb_id] = 0;
+		}
+
+		processed++;
+	}
+
+out:
+	array->entry_num = processed;
+	return rc;
+}
+
 static struct iommu_domain_ops domain_nested_ops = {
 	.free = mock_domain_free_nested,
 	.attach_dev = mock_domain_nop_attach,
+	.cache_invalidate_user = mock_domain_cache_invalidate_user,
 };
 
 static inline struct iommufd_hw_pagetable *
@@ -526,24 +650,11 @@ get_md_pagetable_nested(struct iommufd_ucmd *ucmd, u32 mockpt_id,
 	return hwpt;
 }
 
-struct mock_bus_type {
-	struct bus_type bus;
-	struct notifier_block nb;
-};
-
-static struct mock_bus_type iommufd_mock_bus_type = {
-	.bus = {
-		.name = "iommufd_mock",
-	},
-};
-
-static atomic_t mock_dev_num;
-
 static void mock_dev_release(struct device *dev)
 {
 	struct mock_dev *mdev = container_of(dev, struct mock_dev, dev);
 
-	atomic_dec(&mock_dev_num);
+	ida_free(&mock_dev_ida, mdev->id);
 	kfree(mdev);
 }
 
@@ -552,7 +663,8 @@ static struct mock_dev *mock_dev_create(unsigned long dev_flags)
 	struct mock_dev *mdev;
 	int rc;
 
-	if (dev_flags & ~(MOCK_FLAGS_DEVICE_NO_DIRTY))
+	if (dev_flags &
+	    ~(MOCK_FLAGS_DEVICE_NO_DIRTY | MOCK_FLAGS_DEVICE_HUGE_IOVA))
 		return ERR_PTR(-EINVAL);
 
 	mdev = kzalloc(sizeof(*mdev), GFP_KERNEL);
@@ -564,8 +676,12 @@ static struct mock_dev *mock_dev_create(unsigned long dev_flags)
 	mdev->dev.release = mock_dev_release;
 	mdev->dev.bus = &iommufd_mock_bus_type.bus;
 
-	rc = dev_set_name(&mdev->dev, "iommufd_mock%u",
-			  atomic_inc_return(&mock_dev_num));
+	rc = ida_alloc(&mock_dev_ida, GFP_KERNEL);
+	if (rc < 0)
+		goto err_put;
+	mdev->id = rc;
+
+	rc = dev_set_name(&mdev->dev, "iommufd_mock%u", mdev->id);
 	if (rc)
 		goto err_put;
 
@@ -793,6 +909,28 @@ static int iommufd_test_md_check_refs(struct iommufd_ucmd *ucmd,
 	return 0;
 }
 
+static int iommufd_test_md_check_iotlb(struct iommufd_ucmd *ucmd,
+				       u32 mockpt_id, unsigned int iotlb_id,
+				       u32 iotlb)
+{
+	struct mock_iommu_domain_nested *mock_nested;
+	struct iommufd_hw_pagetable *hwpt;
+	int rc = 0;
+
+	hwpt = get_md_pagetable_nested(ucmd, mockpt_id, &mock_nested);
+	if (IS_ERR(hwpt))
+		return PTR_ERR(hwpt);
+
+	mock_nested = container_of(hwpt->domain,
+				   struct mock_iommu_domain_nested, domain);
+
+	if (iotlb_id > MOCK_NESTED_DOMAIN_IOTLB_ID_MAX ||
+	    mock_nested->iotlb[iotlb_id] != iotlb)
+		rc = -EINVAL;
+	iommufd_put_object(ucmd->ictx, &hwpt->obj);
+	return rc;
+}
+
 struct selftest_access {
 	struct iommufd_access *access;
 	struct file *file;
@@ -1045,7 +1183,7 @@ static int iommufd_test_access_pages(struct iommufd_ucmd *ucmd,
 	}
 
 	if (flags & MOCK_FLAGS_ACCESS_SYZ)
-		iova = iommufd_test_syz_conv_iova(&staccess->access->ioas->iopt,
+		iova = iommufd_test_syz_conv_iova(staccess->access,
 					&cmd->access_pages.iova);
 
 	npages = (ALIGN(iova + length, PAGE_SIZE) -
@@ -1147,8 +1285,8 @@ static int iommufd_test_access_rw(struct iommufd_ucmd *ucmd,
 	}
 
 	if (flags & MOCK_FLAGS_ACCESS_SYZ)
-		iova = iommufd_test_syz_conv_iova(&staccess->access->ioas->iopt,
-					&cmd->access_rw.iova);
+		iova = iommufd_test_syz_conv_iova(staccess->access,
+				&cmd->access_rw.iova);
 
 	rc = iommufd_access_rw(staccess->access, iova, tmp, length, flags);
 	if (rc)
@@ -1274,6 +1412,10 @@ int iommufd_test(struct iommufd_ucmd *ucmd)
 		return iommufd_test_md_check_refs(
 			ucmd, u64_to_user_ptr(cmd->check_refs.uptr),
 			cmd->check_refs.length, cmd->check_refs.refs);
+	case IOMMU_TEST_OP_MD_CHECK_IOTLB:
+		return iommufd_test_md_check_iotlb(ucmd, cmd->id,
+						   cmd->check_iotlb.id,
+						   cmd->check_iotlb.iotlb);
 	case IOMMU_TEST_OP_CREATE_ACCESS:
 		return iommufd_test_create_access(ucmd, cmd->id,
 						  cmd->create_access.flags);
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 75279500a4a8..7abe9e85a570 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -863,16 +863,11 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
 static struct iommu_device *mtk_iommu_probe_device(struct device *dev)
 {
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-	struct mtk_iommu_data *data;
+	struct mtk_iommu_data *data = dev_iommu_priv_get(dev);
 	struct device_link *link;
 	struct device *larbdev;
 	unsigned int larbid, larbidx, i;
 
-	if (!fwspec || fwspec->ops != &mtk_iommu_ops)
-		return ERR_PTR(-ENODEV); /* Not a iommu client device */
-
-	data = dev_iommu_priv_get(dev);
-
 	if (!MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM))
 		return &data->iommu;
 
diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
index 67e044c1a7d9..25b41222abae 100644
--- a/drivers/iommu/mtk_iommu_v1.c
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -481,9 +481,6 @@ static struct iommu_device *mtk_iommu_v1_probe_device(struct device *dev)
 		idx++;
 	}
 
-	if (!fwspec || fwspec->ops != &mtk_iommu_v1_ops)
-		return ERR_PTR(-ENODEV); /* Not a iommu client device */
-
 	data = dev_iommu_priv_get(dev);
 
 	/* Link the consumer device with the smi-larb device(supplier) */
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 35ba090f3b5e..719652b60840 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -17,8 +17,6 @@
 #include <linux/slab.h>
 #include <linux/fsl/mc.h>
 
-#define NO_IOMMU	1
-
 static int of_iommu_xlate(struct device *dev,
 			  struct of_phandle_args *iommu_spec)
 {
@@ -29,7 +27,7 @@ static int of_iommu_xlate(struct device *dev,
 	ops = iommu_ops_from_fwnode(fwnode);
 	if ((ops && !ops->of_xlate) ||
 	    !of_device_is_available(iommu_spec->np))
-		return NO_IOMMU;
+		return -ENODEV;
 
 	ret = iommu_fwspec_init(dev, &iommu_spec->np->fwnode, ops);
 	if (ret)
@@ -61,7 +59,7 @@ static int of_iommu_configure_dev_id(struct device_node *master_np,
 			 "iommu-map-mask", &iommu_spec.np,
 			 iommu_spec.args);
 	if (err)
-		return err == -ENODEV ? NO_IOMMU : err;
+		return err;
 
 	err = of_iommu_xlate(dev, &iommu_spec);
 	of_node_put(iommu_spec.np);
@@ -72,7 +70,7 @@ static int of_iommu_configure_dev(struct device_node *master_np,
 				  struct device *dev)
 {
 	struct of_phandle_args iommu_spec;
-	int err = NO_IOMMU, idx = 0;
+	int err = -ENODEV, idx = 0;
 
 	while (!of_parse_phandle_with_args(master_np, "iommus",
 					   "#iommu-cells",
@@ -107,16 +105,21 @@ static int of_iommu_configure_device(struct device_node *master_np,
 		      of_iommu_configure_dev(master_np, dev);
 }
 
-const struct iommu_ops *of_iommu_configure(struct device *dev,
-					   struct device_node *master_np,
-					   const u32 *id)
+/*
+ * Returns:
+ *  0 on success, an iommu was configured
+ *  -ENODEV if the device does not have any IOMMU
+ *  -EPROBEDEFER if probing should be tried again
+ *  -errno fatal errors
+ */
+int of_iommu_configure(struct device *dev, struct device_node *master_np,
+		       const u32 *id)
 {
-	const struct iommu_ops *ops = NULL;
 	struct iommu_fwspec *fwspec;
-	int err = NO_IOMMU;
+	int err;
 
 	if (!master_np)
-		return NULL;
+		return -ENODEV;
 
 	/* Serialise to make dev->iommu stable under our potential fwspec */
 	mutex_lock(&iommu_probe_device_lock);
@@ -124,7 +127,7 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 	if (fwspec) {
 		if (fwspec->ops) {
 			mutex_unlock(&iommu_probe_device_lock);
-			return fwspec->ops;
+			return 0;
 		}
 		/* In the deferred case, start again from scratch */
 		iommu_fwspec_free(dev);
@@ -147,36 +150,21 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 	} else {
 		err = of_iommu_configure_device(master_np, dev, id);
 	}
-
-	/*
-	 * Two success conditions can be represented by non-negative err here:
-	 * >0 : there is no IOMMU, or one was unavailable for non-fatal reasons
-	 *  0 : we found an IOMMU, and dev->fwspec is initialised appropriately
-	 * <0 : any actual error
-	 */
-	if (!err) {
-		/* The fwspec pointer changed, read it again */
-		fwspec = dev_iommu_fwspec_get(dev);
-		ops    = fwspec->ops;
-	}
 	mutex_unlock(&iommu_probe_device_lock);
 
-	/*
-	 * If we have reason to believe the IOMMU driver missed the initial
-	 * probe for dev, replay it to get things in order.
-	 */
-	if (!err && dev->bus)
-		err = iommu_probe_device(dev);
-
-	/* Ignore all other errors apart from EPROBE_DEFER */
-	if (err == -EPROBE_DEFER) {
-		ops = ERR_PTR(err);
-	} else if (err < 0) {
-		dev_dbg(dev, "Adding to IOMMU failed: %d\n", err);
-		ops = NULL;
-	}
+	if (err == -ENODEV || err == -EPROBE_DEFER)
+		return err;
+	if (err)
+		goto err_log;
 
-	return ops;
+	err = iommu_probe_device(dev);
+	if (err)
+		goto err_log;
+	return 0;
+
+err_log:
+	dev_dbg(dev, "Adding to IOMMU failed: %pe\n", ERR_PTR(err));
+	return err;
 }
 
 static enum iommu_resv_type __maybe_unused
@@ -260,7 +248,14 @@ void of_iommu_get_resv_regions(struct device *dev, struct list_head *list)
 				phys_addr_t iova;
 				size_t length;
 
+				if (of_dma_is_coherent(dev->of_node))
+					prot |= IOMMU_CACHE;
+
 				maps = of_translate_dma_region(np, maps, &iova, &length);
+				if (length == 0) {
+					dev_warn(dev, "Cannot reserve IOVA region of 0 size\n");
+					continue;
+				}
 				type = iommu_resv_region_get_type(dev, &phys, iova, length);
 
 				region = iommu_alloc_resv_region(iova, length, prot, type,
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index c66b070841dd..c9528065a59a 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -1719,7 +1719,6 @@ static void omap_iommu_release_device(struct device *dev)
 	if (!dev->of_node || !arch_data)
 		return;
 
-	dev_iommu_priv_set(dev, NULL);
 	kfree(arch_data);
 
 }
diff --git a/drivers/iommu/sprd-iommu.c b/drivers/iommu/sprd-iommu.c
index 2eb9fb46703b..537359f10997 100644
--- a/drivers/iommu/sprd-iommu.c
+++ b/drivers/iommu/sprd-iommu.c
@@ -385,13 +385,7 @@ static phys_addr_t sprd_iommu_iova_to_phys(struct iommu_domain *domain,
 
 static struct iommu_device *sprd_iommu_probe_device(struct device *dev)
 {
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-	struct sprd_iommu_device *sdev;
-
-	if (!fwspec || fwspec->ops != &sprd_iommu_ops)
-		return ERR_PTR(-ENODEV);
-
-	sdev = dev_iommu_priv_get(dev);
+	struct sprd_iommu_device *sdev = dev_iommu_priv_get(dev);
 
 	return &sdev->iommu;
 }
diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
index 379ebe03efb6..34db37fd9675 100644
--- a/drivers/iommu/virtio-iommu.c
+++ b/drivers/iommu/virtio-iommu.c
@@ -843,7 +843,7 @@ static int viommu_map_pages(struct iommu_domain *domain, unsigned long iova,
 			.flags		= cpu_to_le32(flags),
 		};
 
-		ret = viommu_send_req_sync(vdomain->viommu, &map, sizeof(map));
+		ret = viommu_add_req(vdomain->viommu, &map, sizeof(map));
 		if (ret) {
 			viommu_del_mappings(vdomain, iova, end);
 			return ret;
@@ -912,6 +912,33 @@ static void viommu_iotlb_sync(struct iommu_domain *domain,
 	viommu_sync_req(vdomain->viommu);
 }
 
+static int viommu_iotlb_sync_map(struct iommu_domain *domain,
+				 unsigned long iova, size_t size)
+{
+	struct viommu_domain *vdomain = to_viommu_domain(domain);
+
+	/*
+	 * May be called before the viommu is initialized including
+	 * while creating direct mapping
+	 */
+	if (!vdomain->nr_endpoints)
+		return 0;
+	return viommu_sync_req(vdomain->viommu);
+}
+
+static void viommu_flush_iotlb_all(struct iommu_domain *domain)
+{
+	struct viommu_domain *vdomain = to_viommu_domain(domain);
+
+	/*
+	 * May be called before the viommu is initialized including
+	 * while creating direct mapping
+	 */
+	if (!vdomain->nr_endpoints)
+		return;
+	viommu_sync_req(vdomain->viommu);
+}
+
 static void viommu_get_resv_regions(struct device *dev, struct list_head *head)
 {
 	struct iommu_resv_region *entry, *new_entry, *msi = NULL;
@@ -969,9 +996,6 @@ static struct iommu_device *viommu_probe_device(struct device *dev)
 	struct viommu_dev *viommu = NULL;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 
-	if (!fwspec || fwspec->ops != &viommu_ops)
-		return ERR_PTR(-ENODEV);
-
 	viommu = viommu_get_by_fwnode(fwspec->iommu_fwnode);
 	if (!viommu)
 		return ERR_PTR(-ENODEV);
@@ -1037,6 +1061,8 @@ static bool viommu_capable(struct device *dev, enum iommu_cap cap)
 	switch (cap) {
 	case IOMMU_CAP_CACHE_COHERENCY:
 		return true;
+	case IOMMU_CAP_DEFERRED_FLUSH:
+		return true;
 	default:
 		return false;
 	}
@@ -1057,7 +1083,9 @@ static struct iommu_ops viommu_ops = {
 		.map_pages		= viommu_map_pages,
 		.unmap_pages		= viommu_unmap_pages,
 		.iova_to_phys		= viommu_iova_to_phys,
+		.flush_iotlb_all	= viommu_flush_iotlb_all,
 		.iotlb_sync		= viommu_iotlb_sync,
+		.iotlb_sync_map		= viommu_iotlb_sync_map,
 		.free			= viommu_domain_free,
 	}
 };
diff --git a/drivers/ipack/devices/ipoctal.c b/drivers/ipack/devices/ipoctal.c
index da308be6c487..ba2e9e52d72b 100644
--- a/drivers/ipack/devices/ipoctal.c
+++ b/drivers/ipack/devices/ipoctal.c
@@ -158,9 +158,7 @@ static int ipoctal_get_icount(struct tty_struct *tty,
 static void ipoctal_irq_rx(struct ipoctal_channel *channel, u8 sr)
 {
 	struct tty_port *port = &channel->tty_port;
-	unsigned char value;
-	unsigned char flag;
-	u8 isr;
+	u8 isr, value, flag;
 
 	do {
 		value = ioread8(&channel->regs->r.rhr);
@@ -202,8 +200,8 @@ static void ipoctal_irq_rx(struct ipoctal_channel *channel, u8 sr)
 
 static void ipoctal_irq_tx(struct ipoctal_channel *channel)
 {
-	unsigned char value;
 	unsigned int *pointer_write = &channel->pointer_write;
+	u8 value;
 
 	if (channel->nb_bytes == 0)
 		return;
@@ -436,11 +434,11 @@ err_put_driver:
 	return res;
 }
 
-static inline int ipoctal_copy_write_buffer(struct ipoctal_channel *channel,
-					    const u8 *buf, int count)
+static inline size_t ipoctal_copy_write_buffer(struct ipoctal_channel *channel,
+					       const u8 *buf, size_t count)
 {
 	unsigned long flags;
-	int i;
+	size_t i;
 	unsigned int *pointer_read = &channel->pointer_read;
 
 	/* Copy the bytes from the user buffer to the internal one */
@@ -462,7 +460,7 @@ static ssize_t ipoctal_write_tty(struct tty_struct *tty, const u8 *buf,
 				 size_t count)
 {
 	struct ipoctal_channel *channel = tty->driver_data;
-	unsigned int char_copied;
+	size_t char_copied;
 
 	char_copied = ipoctal_copy_write_buffer(channel, buf, count);
 
diff --git a/drivers/ipack/ipack.c b/drivers/ipack/ipack.c
index cc1ecfd49928..b1471ba016a5 100644
--- a/drivers/ipack/ipack.c
+++ b/drivers/ipack/ipack.c
@@ -207,7 +207,7 @@ struct ipack_bus_device *ipack_bus_register(struct device *parent, int slots,
 	if (!bus)
 		return NULL;
 
-	bus_nr = ida_simple_get(&ipack_ida, 0, 0, GFP_KERNEL);
+	bus_nr = ida_alloc(&ipack_ida, GFP_KERNEL);
 	if (bus_nr < 0) {
 		kfree(bus);
 		return NULL;
@@ -237,7 +237,7 @@ int ipack_bus_unregister(struct ipack_bus_device *bus)
 {
 	bus_for_each_dev(&ipack_bus_type, NULL, bus,
 		ipack_unregister_bus_member);
-	ida_simple_remove(&ipack_ida, bus->bus_nr);
+	ida_free(&ipack_ida, bus->bus_nr);
 	kfree(bus);
 	return 0;
 }
diff --git a/drivers/irqchip/irq-brcmstb-l2.c b/drivers/irqchip/irq-brcmstb-l2.c
index 5559c943f03f..2b0b3175cea0 100644
--- a/drivers/irqchip/irq-brcmstb-l2.c
+++ b/drivers/irqchip/irq-brcmstb-l2.c
@@ -2,7 +2,7 @@
 /*
  * Generic Broadcom Set Top Box Level 2 Interrupt controller driver
  *
- * Copyright (C) 2014-2017 Broadcom
+ * Copyright (C) 2014-2024 Broadcom
  */
 
 #define pr_fmt(fmt)	KBUILD_MODNAME	": " fmt
@@ -112,6 +112,9 @@ static void brcmstb_l2_intc_irq_handle(struct irq_desc *desc)
 		generic_handle_domain_irq(b->domain, irq);
 	} while (status);
 out:
+	/* Don't ack parent before all device writes are done */
+	wmb();
+
 	chained_irq_exit(chip, desc);
 }
 
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index d097001c1e3e..b822752c4261 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -207,6 +207,11 @@ static bool require_its_list_vmovp(struct its_vm *vm, struct its_node *its)
 	return (gic_rdists->has_rvpeid || vm->vlpi_count[its->list_nr]);
 }
 
+static bool rdists_support_shareable(void)
+{
+	return !(gic_rdists->flags & RDIST_FLAGS_FORCE_NON_SHAREABLE);
+}
+
 static u16 get_its_list(struct its_vm *vm)
 {
 	struct its_node *its;
@@ -2710,10 +2715,12 @@ static u64 inherit_vpe_l1_table_from_its(void)
 			break;
 		}
 		val |= FIELD_PREP(GICR_VPROPBASER_4_1_ADDR, addr >> 12);
-		val |= FIELD_PREP(GICR_VPROPBASER_SHAREABILITY_MASK,
-				  FIELD_GET(GITS_BASER_SHAREABILITY_MASK, baser));
-		val |= FIELD_PREP(GICR_VPROPBASER_INNER_CACHEABILITY_MASK,
-				  FIELD_GET(GITS_BASER_INNER_CACHEABILITY_MASK, baser));
+		if (rdists_support_shareable()) {
+			val |= FIELD_PREP(GICR_VPROPBASER_SHAREABILITY_MASK,
+					  FIELD_GET(GITS_BASER_SHAREABILITY_MASK, baser));
+			val |= FIELD_PREP(GICR_VPROPBASER_INNER_CACHEABILITY_MASK,
+					  FIELD_GET(GITS_BASER_INNER_CACHEABILITY_MASK, baser));
+		}
 		val |= FIELD_PREP(GICR_VPROPBASER_4_1_SIZE, GITS_BASER_NR_PAGES(baser) - 1);
 
 		return val;
@@ -2936,8 +2943,10 @@ static int allocate_vpe_l1_table(void)
 	WARN_ON(!IS_ALIGNED(pa, psz));
 
 	val |= FIELD_PREP(GICR_VPROPBASER_4_1_ADDR, pa >> 12);
-	val |= GICR_VPROPBASER_RaWb;
-	val |= GICR_VPROPBASER_InnerShareable;
+	if (rdists_support_shareable()) {
+		val |= GICR_VPROPBASER_RaWb;
+		val |= GICR_VPROPBASER_InnerShareable;
+	}
 	val |= GICR_VPROPBASER_4_1_Z;
 	val |= GICR_VPROPBASER_4_1_VALID;
 
@@ -3126,7 +3135,7 @@ static void its_cpu_init_lpis(void)
 	gicr_write_propbaser(val, rbase + GICR_PROPBASER);
 	tmp = gicr_read_propbaser(rbase + GICR_PROPBASER);
 
-	if (gic_rdists->flags & RDIST_FLAGS_FORCE_NON_SHAREABLE)
+	if (!rdists_support_shareable())
 		tmp &= ~GICR_PROPBASER_SHAREABILITY_MASK;
 
 	if ((tmp ^ val) & GICR_PROPBASER_SHAREABILITY_MASK) {
@@ -3153,7 +3162,7 @@ static void its_cpu_init_lpis(void)
 	gicr_write_pendbaser(val, rbase + GICR_PENDBASER);
 	tmp = gicr_read_pendbaser(rbase + GICR_PENDBASER);
 
-	if (gic_rdists->flags & RDIST_FLAGS_FORCE_NON_SHAREABLE)
+	if (!rdists_support_shareable())
 		tmp &= ~GICR_PENDBASER_SHAREABILITY_MASK;
 
 	if (!(tmp & GICR_PENDBASER_SHAREABILITY_MASK)) {
@@ -3172,6 +3181,7 @@ static void its_cpu_init_lpis(void)
 	val |= GICR_CTLR_ENABLE_LPIS;
 	writel_relaxed(val, rbase + GICR_CTLR);
 
+out:
 	if (gic_rdists->has_vlpis && !gic_rdists->has_rvpeid) {
 		void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
 
@@ -3207,7 +3217,6 @@ static void its_cpu_init_lpis(void)
 
 	/* Make sure the GIC has seen the above */
 	dsb(sy);
-out:
 	gic_data_rdist()->flags |= RD_LOCAL_LPI_ENABLED;
 	pr_info("GICv3: CPU%d: using %s LPI pending table @%pa\n",
 		smp_processor_id(),
@@ -3817,8 +3826,9 @@ static int its_vpe_set_affinity(struct irq_data *d,
 				bool force)
 {
 	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
-	int from, cpu = cpumask_first(mask_val);
+	struct cpumask common, *table_mask;
 	unsigned long flags;
+	int from, cpu;
 
 	/*
 	 * Changing affinity is mega expensive, so let's be as lazy as
@@ -3834,19 +3844,22 @@ static int its_vpe_set_affinity(struct irq_data *d,
 	 * taken on any vLPI handling path that evaluates vpe->col_idx.
 	 */
 	from = vpe_to_cpuid_lock(vpe, &flags);
-	if (from == cpu)
-		goto out;
-
-	vpe->col_idx = cpu;
+	table_mask = gic_data_rdist_cpu(from)->vpe_table_mask;
 
 	/*
-	 * GICv4.1 allows us to skip VMOVP if moving to a cpu whose RD
-	 * is sharing its VPE table with the current one.
+	 * If we are offered another CPU in the same GICv4.1 ITS
+	 * affinity, pick this one. Otherwise, any CPU will do.
 	 */
-	if (gic_data_rdist_cpu(cpu)->vpe_table_mask &&
-	    cpumask_test_cpu(from, gic_data_rdist_cpu(cpu)->vpe_table_mask))
+	if (table_mask && cpumask_and(&common, mask_val, table_mask))
+		cpu = cpumask_test_cpu(from, &common) ? from : cpumask_first(&common);
+	else
+		cpu = cpumask_first(mask_val);
+
+	if (from == cpu)
 		goto out;
 
+	vpe->col_idx = cpu;
+
 	its_send_vmovp(vpe);
 	its_vpe_db_proxy_move(vpe, from, cpu);
 
@@ -3880,14 +3893,18 @@ static void its_vpe_schedule(struct its_vpe *vpe)
 	val  = virt_to_phys(page_address(vpe->its_vm->vprop_page)) &
 		GENMASK_ULL(51, 12);
 	val |= (LPI_NRBITS - 1) & GICR_VPROPBASER_IDBITS_MASK;
-	val |= GICR_VPROPBASER_RaWb;
-	val |= GICR_VPROPBASER_InnerShareable;
+	if (rdists_support_shareable()) {
+		val |= GICR_VPROPBASER_RaWb;
+		val |= GICR_VPROPBASER_InnerShareable;
+	}
 	gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
 
 	val  = virt_to_phys(page_address(vpe->vpt_page)) &
 		GENMASK_ULL(51, 16);
-	val |= GICR_VPENDBASER_RaWaWb;
-	val |= GICR_VPENDBASER_InnerShareable;
+	if (rdists_support_shareable()) {
+		val |= GICR_VPENDBASER_RaWaWb;
+		val |= GICR_VPENDBASER_InnerShareable;
+	}
 	/*
 	 * There is no good way of finding out if the pending table is
 	 * empty as we can race against the doorbell interrupt very
@@ -5078,6 +5095,8 @@ static int __init its_probe_one(struct its_node *its)
 	u32 ctlr;
 	int err;
 
+	its_enable_quirks(its);
+
 	if (is_v4(its)) {
 		if (!(its->typer & GITS_TYPER_VMOVP)) {
 			err = its_compute_its_list_map(its);
@@ -5429,7 +5448,6 @@ static int __init its_of_probe(struct device_node *node)
 		if (!its)
 			return -ENOMEM;
 
-		its_enable_quirks(its);
 		err = its_probe_one(its);
 		if (err)  {
 			its_node_destroy(its);
diff --git a/drivers/irqchip/irq-loongson-eiointc.c b/drivers/irqchip/irq-loongson-eiointc.c
index 1623cd779175..b3736bdd4b9f 100644
--- a/drivers/irqchip/irq-loongson-eiointc.c
+++ b/drivers/irqchip/irq-loongson-eiointc.c
@@ -241,7 +241,7 @@ static int eiointc_domain_alloc(struct irq_domain *domain, unsigned int virq,
 	int ret;
 	unsigned int i, type;
 	unsigned long hwirq = 0;
-	struct eiointc *priv = domain->host_data;
+	struct eiointc_priv *priv = domain->host_data;
 
 	ret = irq_domain_translate_onecell(domain, arg, &hwirq, &type);
 	if (ret)
diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c
index 5101a3fb11df..58881d313979 100644
--- a/drivers/irqchip/irq-mbigen.c
+++ b/drivers/irqchip/irq-mbigen.c
@@ -235,22 +235,17 @@ static const struct irq_domain_ops mbigen_domain_ops = {
 static int mbigen_of_create_domain(struct platform_device *pdev,
 				   struct mbigen_device *mgn_chip)
 {
-	struct device *parent;
 	struct platform_device *child;
 	struct irq_domain *domain;
 	struct device_node *np;
 	u32 num_pins;
 	int ret = 0;
 
-	parent = bus_get_dev_root(&platform_bus_type);
-	if (!parent)
-		return -ENODEV;
-
 	for_each_child_of_node(pdev->dev.of_node, np) {
 		if (!of_property_read_bool(np, "interrupt-controller"))
 			continue;
 
-		child = of_platform_device_create(np, NULL, parent);
+		child = of_platform_device_create(np, NULL, NULL);
 		if (!child) {
 			ret = -ENOMEM;
 			break;
@@ -273,7 +268,6 @@ static int mbigen_of_create_domain(struct platform_device *pdev,
 		}
 	}
 
-	put_device(parent);
 	if (ret)
 		of_node_put(np);
 
diff --git a/drivers/irqchip/irq-qcom-mpm.c b/drivers/irqchip/irq-qcom-mpm.c
index cda5838d2232..7942d8eb3d00 100644
--- a/drivers/irqchip/irq-qcom-mpm.c
+++ b/drivers/irqchip/irq-qcom-mpm.c
@@ -389,8 +389,8 @@ static int qcom_mpm_init(struct device_node *np, struct device_node *parent)
 		/* Don't use devm_ioremap_resource, as we're accessing a shared region. */
 		priv->base = devm_ioremap(dev, res.start, resource_size(&res));
 		of_node_put(msgram_np);
-		if (IS_ERR(priv->base))
-			return PTR_ERR(priv->base);
+		if (!priv->base)
+			return -ENOMEM;
 	} else {
 		/* Otherwise, fall back to simple MMIO. */
 		priv->base = devm_platform_ioremap_resource(pdev, 0);
diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c
index 5b7bc4fd9517..bf0b40b0fad4 100644
--- a/drivers/irqchip/irq-sifive-plic.c
+++ b/drivers/irqchip/irq-sifive-plic.c
@@ -148,7 +148,13 @@ static void plic_irq_eoi(struct irq_data *d)
 {
 	struct plic_handler *handler = this_cpu_ptr(&plic_handlers);
 
-	writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM);
+	if (unlikely(irqd_irq_disabled(d))) {
+		plic_toggle(handler, d->hwirq, 1);
+		writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM);
+		plic_toggle(handler, d->hwirq, 0);
+	} else {
+		writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM);
+	}
 }
 
 #ifdef CONFIG_SMP
diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c
index 2f3789515445..6e80d7bd3c4d 100644
--- a/drivers/isdn/capi/capi.c
+++ b/drivers/isdn/capi/capi.c
@@ -1231,9 +1231,9 @@ static void capinc_tty_hangup(struct tty_struct *tty)
 	tty_port_hangup(&mp->port);
 }
 
-static void capinc_tty_send_xchar(struct tty_struct *tty, char ch)
+static void capinc_tty_send_xchar(struct tty_struct *tty, u8 ch)
 {
-	pr_debug("capinc_tty_send_xchar(%d)\n", ch);
+	pr_debug("capinc_tty_send_xchar(%u)\n", ch);
 }
 
 static const struct tty_operations capinc_ops = {
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 6292fddcc55c..d721b254e1e4 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -95,14 +95,18 @@ config LEDS_ARIEL
 	  Say Y to if your machine is a Dell Wyse 3020 thin client.
 
 config LEDS_AW200XX
-	tristate "LED support for Awinic AW20036/AW20054/AW20072"
+	tristate "LED support for Awinic AW20036/AW20054/AW20072/AW20108"
 	depends on LEDS_CLASS
 	depends on I2C
 	help
-	  This option enables support for the AW20036/AW20054/AW20072 LED driver.
-	  It is a 3x12/6x9/6x12 matrix LED driver programmed via
-	  an I2C interface, up to 36/54/72 LEDs or 12/18/24 RGBs,
-	  3 pattern controllers for auto breathing or group dimming control.
+	  This option enables support for the Awinic AW200XX LED controllers.
+	  It is a matrix LED driver programmed via an I2C interface. Devices have
+	  a set of individually controlled LEDs and support 3 pattern controllers
+	  for auto breathing or group dimming control. Supported devices:
+	    - AW20036 (3x12) 36 LEDs
+	    - AW20054 (6x9)  54 LEDs
+	    - AW20072 (6x12) 72 LEDs
+	    - AW20108 (9x12) 108 LEDs
 
 	  To compile this driver as a module, choose M here: the module
 	  will be called leds-aw200xx.
@@ -110,6 +114,7 @@ config LEDS_AW200XX
 config LEDS_AW2013
 	tristate "LED support for Awinic AW2013"
 	depends on LEDS_CLASS && I2C && OF
+	select REGMAP_I2C
 	help
 	  This option enables support for the AW2013 3-channel
 	  LED driver.
@@ -298,6 +303,15 @@ config LEDS_COBALT_RAQ
 	help
 	  This option enables support for the Cobalt Raq series LEDs.
 
+config LEDS_SUN50I_A100
+	tristate "LED support for Allwinner A100 RGB LED controller"
+	depends on LEDS_CLASS_MULTICOLOR
+	depends on ARCH_SUNXI || COMPILE_TEST
+	help
+	  This option enables support for the RGB LED controller found
+	  in some Allwinner sunxi SoCs, including A100, R329, and D1.
+	  It uses a one-wire interface to control up to 1024 LEDs.
+
 config LEDS_SUNFIRE
 	tristate "LED support for SunFire servers."
 	depends on LEDS_CLASS
@@ -638,6 +652,17 @@ config LEDS_ADP5520
 	  To compile this driver as a module, choose M here: the module will
 	  be called leds-adp5520.
 
+config LEDS_MAX5970
+	tristate "LED Support for Maxim 5970"
+	depends on LEDS_CLASS
+	depends on MFD_MAX5970
+	help
+	  This option enables support for the Maxim MAX5970 & MAX5978 smart
+	  switch indication LEDs via the I2C bus.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called leds-max5970.
+
 config LEDS_MC13783
 	tristate "LED Support for MC13XXX PMIC"
 	depends on LEDS_CLASS
diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile
index d7348e8bc019..ce07dc295ff0 100644
--- a/drivers/leds/Makefile
+++ b/drivers/leds/Makefile
@@ -56,6 +56,7 @@ obj-$(CONFIG_LEDS_LP8501)		+= leds-lp8501.o
 obj-$(CONFIG_LEDS_LP8788)		+= leds-lp8788.o
 obj-$(CONFIG_LEDS_LP8860)		+= leds-lp8860.o
 obj-$(CONFIG_LEDS_LT3593)		+= leds-lt3593.o
+obj-$(CONFIG_LEDS_MAX5970)		+= leds-max5970.o
 obj-$(CONFIG_LEDS_MAX77650)		+= leds-max77650.o
 obj-$(CONFIG_LEDS_MAX8997)		+= leds-max8997.o
 obj-$(CONFIG_LEDS_MC13783)		+= leds-mc13783.o
@@ -78,6 +79,7 @@ obj-$(CONFIG_LEDS_POWERNV)		+= leds-powernv.o
 obj-$(CONFIG_LEDS_PWM)			+= leds-pwm.o
 obj-$(CONFIG_LEDS_REGULATOR)		+= leds-regulator.o
 obj-$(CONFIG_LEDS_SC27XX_BLTC)		+= leds-sc27xx-bltc.o
+obj-$(CONFIG_LEDS_SUN50I_A100)		+= leds-sun50i-a100.o
 obj-$(CONFIG_LEDS_SUNFIRE)		+= leds-sunfire.o
 obj-$(CONFIG_LEDS_SYSCON)		+= leds-syscon.o
 obj-$(CONFIG_LEDS_TCA6507)		+= leds-tca6507.o
diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c
index 6a5e1f41f9a4..bd59a14a4a90 100644
--- a/drivers/leds/led-triggers.c
+++ b/drivers/leds/led-triggers.c
@@ -269,19 +269,6 @@ void led_trigger_set_default(struct led_classdev *led_cdev)
 }
 EXPORT_SYMBOL_GPL(led_trigger_set_default);
 
-void led_trigger_rename_static(const char *name, struct led_trigger *trig)
-{
-	/* new name must be on a temporary string to prevent races */
-	BUG_ON(name == trig->name);
-
-	down_write(&triggers_list_lock);
-	/* this assumes that trig->name was originaly allocated to
-	 * non constant storage */
-	strcpy((char *)trig->name, name);
-	up_write(&triggers_list_lock);
-}
-EXPORT_SYMBOL_GPL(led_trigger_rename_static);
-
 /* LED Trigger Interface */
 
 int led_trigger_register(struct led_trigger *trig)
diff --git a/drivers/leds/leds-aw200xx.c b/drivers/leds/leds-aw200xx.c
index 14ca236ce29e..f584a7f98fc5 100644
--- a/drivers/leds/leds-aw200xx.c
+++ b/drivers/leds/leds-aw200xx.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Awinic AW20036/AW20054/AW20072 LED driver
+ * Awinic AW20036/AW20054/AW20072/AW20108 LED driver
  *
  * Copyright (c) 2023, SberDevices. All Rights Reserved.
  *
@@ -10,6 +10,7 @@
 #include <linux/bitfield.h>
 #include <linux/bits.h>
 #include <linux/container_of.h>
+#include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
 #include <linux/leds.h>
 #include <linux/mod_devicetable.h>
@@ -74,6 +75,10 @@
 #define AW200XX_LED2REG(x, columns) \
 	((x) + (((x) / (columns)) * (AW200XX_DSIZE_COLUMNS_MAX - (columns))))
 
+/* DIM current configuration register on page 1 */
+#define AW200XX_REG_DIM_PAGE1(x, columns) \
+	AW200XX_REG(AW200XX_PAGE1, AW200XX_LED2REG(x, columns))
+
 /*
  * DIM current configuration register (page 4).
  * The even address for current DIM configuration.
@@ -82,6 +87,8 @@
 #define AW200XX_REG_DIM(x, columns) \
 	AW200XX_REG(AW200XX_PAGE4, AW200XX_LED2REG(x, columns) * 2)
 #define AW200XX_REG_DIM2FADE(x) ((x) + 1)
+#define AW200XX_REG_FADE2DIM(fade) \
+	DIV_ROUND_UP((fade) * AW200XX_DIM_MAX, AW200XX_FADE_MAX)
 
 /*
  * Duty ratio of display scan (see p.15 of datasheet for formula):
@@ -112,6 +119,7 @@ struct aw200xx {
 	struct mutex mutex;
 	u32 num_leds;
 	u32 display_rows;
+	struct gpio_desc *hwen;
 	struct aw200xx_led leds[] __counted_by(num_leds);
 };
 
@@ -153,7 +161,8 @@ static ssize_t dim_store(struct device *dev, struct device_attribute *devattr,
 
 	if (dim >= 0) {
 		ret = regmap_write(chip->regmap,
-				   AW200XX_REG_DIM(led->num, columns), dim);
+				   AW200XX_REG_DIM_PAGE1(led->num, columns),
+				   dim);
 		if (ret)
 			goto out_unlock;
 	}
@@ -188,9 +197,7 @@ static int aw200xx_brightness_set(struct led_classdev *cdev,
 
 	dim = led->dim;
 	if (dim < 0)
-		dim = max_t(int,
-			    brightness / (AW200XX_FADE_MAX / AW200XX_DIM_MAX),
-			    1);
+		dim = AW200XX_REG_FADE2DIM(brightness);
 
 	ret = regmap_write(chip->regmap, reg, dim);
 	if (ret)
@@ -314,6 +321,9 @@ static int aw200xx_chip_reset(const struct aw200xx *const chip)
 	if (ret)
 		return ret;
 
+	/* According to the datasheet software reset takes at least 1ms */
+	fsleep(1000);
+
 	regcache_mark_dirty(chip->regmap);
 	return regmap_write(chip->regmap, AW200XX_REG_FCD, AW200XX_FCD_CLEAR);
 }
@@ -353,6 +363,50 @@ static int aw200xx_chip_check(const struct aw200xx *const chip)
 	return 0;
 }
 
+static void aw200xx_enable(const struct aw200xx *const chip)
+{
+	gpiod_set_value_cansleep(chip->hwen, 1);
+
+	/*
+	 * After HWEN pin set high the chip begins to load the OTP information,
+	 * which takes 200us to complete. About 200us wait time is needed for
+	 * internal oscillator startup and display SRAM initialization. After
+	 * display SRAM initialization, the registers in page1 to page5 can be
+	 * configured via i2c interface.
+	 */
+	fsleep(400);
+}
+
+static void aw200xx_disable(const struct aw200xx *const chip)
+{
+	return gpiod_set_value_cansleep(chip->hwen, 0);
+}
+
+static int aw200xx_probe_get_display_rows(struct device *dev,
+					  struct aw200xx *chip)
+{
+	struct fwnode_handle *child;
+	u32 max_source = 0;
+
+	device_for_each_child_node(dev, child) {
+		u32 source;
+		int ret;
+
+		ret = fwnode_property_read_u32(child, "reg", &source);
+		if (ret || source >= chip->cdef->channels)
+			continue;
+
+		max_source = max(max_source, source);
+	}
+
+	if (max_source == 0)
+		return -EINVAL;
+
+	chip->display_rows = max_source / chip->cdef->display_size_columns + 1;
+
+	return 0;
+}
+
 static int aw200xx_probe_fw(struct device *dev, struct aw200xx *chip)
 {
 	struct fwnode_handle *child;
@@ -360,18 +414,10 @@ static int aw200xx_probe_fw(struct device *dev, struct aw200xx *chip)
 	int ret;
 	int i;
 
-	ret = device_property_read_u32(dev, "awinic,display-rows",
-				       &chip->display_rows);
+	ret = aw200xx_probe_get_display_rows(dev, chip);
 	if (ret)
 		return dev_err_probe(dev, ret,
-				     "Failed to read 'display-rows' property\n");
-
-	if (!chip->display_rows ||
-	    chip->display_rows > chip->cdef->display_size_rows_max) {
-		return dev_err_probe(dev, -EINVAL,
-				     "Invalid leds display size %u\n",
-				     chip->display_rows);
-	}
+				     "No valid led definitions found\n");
 
 	current_max = aw200xx_imax_from_global(chip, AW200XX_IMAX_MAX_uA);
 	current_min = aw200xx_imax_from_global(chip, AW200XX_IMAX_MIN_uA);
@@ -416,6 +462,7 @@ static int aw200xx_probe_fw(struct device *dev, struct aw200xx *chip)
 		led->num = source;
 		led->chip = chip;
 		led->cdev.brightness_set_blocking = aw200xx_brightness_set;
+		led->cdev.max_brightness = AW200XX_FADE_MAX;
 		led->cdev.groups = dim_groups;
 		init_data.fwnode = child;
 
@@ -480,6 +527,7 @@ static const struct regmap_config aw200xx_regmap_config = {
 	.rd_table = &aw200xx_readable_table,
 	.wr_table = &aw200xx_writeable_table,
 	.cache_type = REGCACHE_MAPLE,
+	.disable_locking = true,
 };
 
 static int aw200xx_probe(struct i2c_client *client)
@@ -512,6 +560,14 @@ static int aw200xx_probe(struct i2c_client *client)
 	if (IS_ERR(chip->regmap))
 		return PTR_ERR(chip->regmap);
 
+	chip->hwen = devm_gpiod_get_optional(&client->dev, "enable",
+					     GPIOD_OUT_HIGH);
+	if (IS_ERR(chip->hwen))
+		return dev_err_probe(&client->dev, PTR_ERR(chip->hwen),
+				     "Cannot get enable GPIO");
+
+	aw200xx_enable(chip);
+
 	ret = aw200xx_chip_check(chip);
 	if (ret)
 		return ret;
@@ -532,6 +588,9 @@ static int aw200xx_probe(struct i2c_client *client)
 	ret = aw200xx_chip_init(chip);
 
 out_unlock:
+	if (ret)
+		aw200xx_disable(chip);
+
 	mutex_unlock(&chip->mutex);
 	return ret;
 }
@@ -541,6 +600,7 @@ static void aw200xx_remove(struct i2c_client *client)
 	struct aw200xx *chip = i2c_get_clientdata(client);
 
 	aw200xx_chip_reset(chip);
+	aw200xx_disable(chip);
 	mutex_destroy(&chip->mutex);
 }
 
@@ -562,10 +622,17 @@ static const struct aw200xx_chipdef aw20072_cdef = {
 	.display_size_columns = 12,
 };
 
+static const struct aw200xx_chipdef aw20108_cdef = {
+	.channels = 108,
+	.display_size_rows_max = 9,
+	.display_size_columns = 12,
+};
+
 static const struct i2c_device_id aw200xx_id[] = {
 	{ "aw20036" },
 	{ "aw20054" },
 	{ "aw20072" },
+	{ "aw20108" },
 	{}
 };
 MODULE_DEVICE_TABLE(i2c, aw200xx_id);
@@ -574,6 +641,7 @@ static const struct of_device_id aw200xx_match_table[] = {
 	{ .compatible = "awinic,aw20036", .data = &aw20036_cdef, },
 	{ .compatible = "awinic,aw20054", .data = &aw20054_cdef, },
 	{ .compatible = "awinic,aw20072", .data = &aw20072_cdef, },
+	{ .compatible = "awinic,aw20108", .data = &aw20108_cdef, },
 	{}
 };
 MODULE_DEVICE_TABLE(of, aw200xx_match_table);
diff --git a/drivers/leds/leds-gpio.c b/drivers/leds/leds-gpio.c
index 710c319ad312..83fcd7b6afff 100644
--- a/drivers/leds/leds-gpio.c
+++ b/drivers/leds/leds-gpio.c
@@ -172,6 +172,8 @@ static struct gpio_leds_priv *gpio_leds_create(struct device *dev)
 		led.gpiod = devm_fwnode_gpiod_get(dev, child, NULL, GPIOD_ASIS,
 						  NULL);
 		if (IS_ERR(led.gpiod)) {
+			dev_err_probe(dev, PTR_ERR(led.gpiod), "Failed to get GPIO '%pfw'\n",
+				      child);
 			fwnode_handle_put(child);
 			return ERR_CAST(led.gpiod);
 		}
diff --git a/drivers/leds/leds-max5970.c b/drivers/leds/leds-max5970.c
new file mode 100644
index 000000000000..56a584311581
--- /dev/null
+++ b/drivers/leds/leds-max5970.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Device driver for leds in MAX5970 and MAX5978 IC
+ *
+ * Copyright (c) 2022 9elements GmbH
+ *
+ * Author: Patrick Rudolph <patrick.rudolph@9elements.com>
+ */
+
+#include <linux/bits.h>
+#include <linux/container_of.h>
+#include <linux/device.h>
+#include <linux/leds.h>
+#include <linux/mfd/max5970.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
+#include <linux/regmap.h>
+
+#define ldev_to_maxled(c)       container_of(c, struct max5970_led, cdev)
+
+struct max5970_led {
+	struct device *dev;
+	struct regmap *regmap;
+	struct led_classdev cdev;
+	unsigned int index;
+};
+
+static int max5970_led_set_brightness(struct led_classdev *cdev,
+				      enum led_brightness brightness)
+{
+	struct max5970_led *ddata = ldev_to_maxled(cdev);
+	int ret, val;
+
+	/* Set/clear corresponding bit for given led index */
+	val = !brightness ? BIT(ddata->index) : 0;
+
+	ret = regmap_update_bits(ddata->regmap, MAX5970_REG_LED_FLASH, BIT(ddata->index), val);
+	if (ret < 0)
+		dev_err(cdev->dev, "failed to set brightness %d", ret);
+
+	return ret;
+}
+
+static int max5970_led_probe(struct platform_device *pdev)
+{
+	struct fwnode_handle *led_node, *child;
+	struct device *dev = &pdev->dev;
+	struct regmap *regmap;
+	struct max5970_led *ddata;
+	int ret = -ENODEV;
+
+	regmap = dev_get_regmap(dev->parent, NULL);
+	if (!regmap)
+		return -ENODEV;
+
+	led_node = device_get_named_child_node(dev->parent, "leds");
+	if (!led_node)
+		return -ENODEV;
+
+	fwnode_for_each_available_child_node(led_node, child) {
+		u32 reg;
+
+		if (fwnode_property_read_u32(child, "reg", &reg))
+			continue;
+
+		if (reg >= MAX5970_NUM_LEDS) {
+			dev_err_probe(dev, -EINVAL, "invalid LED (%u >= %d)\n", reg, MAX5970_NUM_LEDS);
+			continue;
+		}
+
+		ddata = devm_kzalloc(dev, sizeof(*ddata), GFP_KERNEL);
+		if (!ddata) {
+			fwnode_handle_put(child);
+			return -ENOMEM;
+		}
+
+		ddata->index = reg;
+		ddata->regmap = regmap;
+		ddata->dev = dev;
+
+		if (fwnode_property_read_string(child, "label", &ddata->cdev.name))
+			ddata->cdev.name = fwnode_get_name(child);
+
+		ddata->cdev.max_brightness = 1;
+		ddata->cdev.brightness_set_blocking = max5970_led_set_brightness;
+		ddata->cdev.default_trigger = "none";
+
+		ret = devm_led_classdev_register(dev, &ddata->cdev);
+		if (ret < 0) {
+			fwnode_handle_put(child);
+			return dev_err_probe(dev, ret, "Failed to initialize LED %u\n", reg);
+		}
+	}
+
+	return ret;
+}
+
+static struct platform_driver max5970_led_driver = {
+	.driver = {
+		.name = "max5970-led",
+	},
+	.probe = max5970_led_probe,
+};
+module_platform_driver(max5970_led_driver);
+
+MODULE_AUTHOR("Patrick Rudolph <patrick.rudolph@9elements.com>");
+MODULE_AUTHOR("Naresh Solanki <Naresh.Solanki@9elements.com>");
+MODULE_DESCRIPTION("MAX5970_hot-swap controller LED driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/leds/leds-sun50i-a100.c b/drivers/leds/leds-sun50i-a100.c
new file mode 100644
index 000000000000..62d21c3a3575
--- /dev/null
+++ b/drivers/leds/leds-sun50i-a100.c
@@ -0,0 +1,584 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021-2023 Samuel Holland <samuel@sholland.org>
+ *
+ * Partly based on drivers/leds/leds-turris-omnia.c, which is:
+ *     Copyright (c) 2020 by Marek Behún <kabel@kernel.org>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/led-class-multicolor.h>
+#include <linux/leds.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/property.h>
+#include <linux/reset.h>
+#include <linux/spinlock.h>
+
+#define LEDC_CTRL_REG			0x0000
+#define LEDC_CTRL_REG_DATA_LENGTH		GENMASK(28, 16)
+#define LEDC_CTRL_REG_RGB_MODE			GENMASK(8, 6)
+#define LEDC_CTRL_REG_LEDC_EN			BIT(0)
+#define LEDC_T01_TIMING_CTRL_REG	0x0004
+#define LEDC_T01_TIMING_CTRL_REG_T1H		GENMASK(26, 21)
+#define LEDC_T01_TIMING_CTRL_REG_T1L		GENMASK(20, 16)
+#define LEDC_T01_TIMING_CTRL_REG_T0H		GENMASK(10, 6)
+#define LEDC_T01_TIMING_CTRL_REG_T0L		GENMASK(5, 0)
+#define LEDC_RESET_TIMING_CTRL_REG	0x000c
+#define LEDC_RESET_TIMING_CTRL_REG_TR		GENMASK(28, 16)
+#define LEDC_RESET_TIMING_CTRL_REG_LED_NUM	GENMASK(9, 0)
+#define LEDC_DATA_REG			0x0014
+#define LEDC_DMA_CTRL_REG		0x0018
+#define LEDC_DMA_CTRL_REG_DMA_EN		BIT(5)
+#define LEDC_DMA_CTRL_REG_FIFO_TRIG_LEVEL	GENMASK(4, 0)
+#define LEDC_INT_CTRL_REG		0x001c
+#define LEDC_INT_CTRL_REG_GLOBAL_INT_EN		BIT(5)
+#define LEDC_INT_CTRL_REG_FIFO_CPUREQ_INT_EN	BIT(1)
+#define LEDC_INT_CTRL_REG_TRANS_FINISH_INT_EN	BIT(0)
+#define LEDC_INT_STS_REG		0x0020
+#define LEDC_INT_STS_REG_FIFO_WLW		GENMASK(15, 10)
+#define LEDC_INT_STS_REG_FIFO_CPUREQ_INT	BIT(1)
+#define LEDC_INT_STS_REG_TRANS_FINISH_INT	BIT(0)
+
+#define LEDC_FIFO_DEPTH			32U
+#define LEDC_MAX_LEDS			1024
+#define LEDC_CHANNELS_PER_LED		3 /* RGB */
+
+#define LEDS_TO_BYTES(n)		((n) * sizeof(u32))
+
+struct sun50i_a100_ledc_led {
+	struct led_classdev_mc mc_cdev;
+	struct mc_subled subled_info[LEDC_CHANNELS_PER_LED];
+	u32 addr;
+};
+
+#define to_ledc_led(mc) container_of(mc, struct sun50i_a100_ledc_led, mc_cdev)
+
+struct sun50i_a100_ledc_timing {
+	u32 t0h_ns;
+	u32 t0l_ns;
+	u32 t1h_ns;
+	u32 t1l_ns;
+	u32 treset_ns;
+};
+
+struct sun50i_a100_ledc {
+	struct device *dev;
+	void __iomem *base;
+	struct clk *bus_clk;
+	struct clk *mod_clk;
+	struct reset_control *reset;
+
+	u32 *buffer;
+	struct dma_chan *dma_chan;
+	dma_addr_t dma_handle;
+	unsigned int pio_length;
+	unsigned int pio_offset;
+
+	spinlock_t lock;
+	unsigned int next_length;
+	bool xfer_active;
+
+	u32 format;
+	struct sun50i_a100_ledc_timing timing;
+
+	u32 max_addr;
+	u32 num_leds;
+	struct sun50i_a100_ledc_led leds[] __counted_by(num_leds);
+};
+
+static int sun50i_a100_ledc_dma_xfer(struct sun50i_a100_ledc *priv, unsigned int length)
+{
+	struct dma_async_tx_descriptor *desc;
+	dma_cookie_t cookie;
+
+	desc = dmaengine_prep_slave_single(priv->dma_chan, priv->dma_handle,
+					   LEDS_TO_BYTES(length), DMA_MEM_TO_DEV, 0);
+	if (!desc)
+		return -ENOMEM;
+
+	cookie = dmaengine_submit(desc);
+	if (dma_submit_error(cookie))
+		return -EIO;
+
+	dma_async_issue_pending(priv->dma_chan);
+
+	return 0;
+}
+
+static void sun50i_a100_ledc_pio_xfer(struct sun50i_a100_ledc *priv, unsigned int fifo_used)
+{
+	unsigned int burst, length, offset;
+	u32 control;
+
+	length = priv->pio_length;
+	offset = priv->pio_offset;
+	burst  = min(length, LEDC_FIFO_DEPTH - fifo_used);
+
+	iowrite32_rep(priv->base + LEDC_DATA_REG, priv->buffer + offset, burst);
+
+	if (burst < length) {
+		priv->pio_length = length - burst;
+		priv->pio_offset = offset + burst;
+
+		if (!offset) {
+			control = readl(priv->base + LEDC_INT_CTRL_REG);
+			control |= LEDC_INT_CTRL_REG_FIFO_CPUREQ_INT_EN;
+			writel(control, priv->base + LEDC_INT_CTRL_REG);
+		}
+	} else {
+		/* Disable the request IRQ once all data is written. */
+		control = readl(priv->base + LEDC_INT_CTRL_REG);
+		control &= ~LEDC_INT_CTRL_REG_FIFO_CPUREQ_INT_EN;
+		writel(control, priv->base + LEDC_INT_CTRL_REG);
+	}
+}
+
+static void sun50i_a100_ledc_start_xfer(struct sun50i_a100_ledc *priv, unsigned int length)
+{
+	bool use_dma = false;
+	u32 control;
+
+	if (priv->dma_chan && length > LEDC_FIFO_DEPTH) {
+		int ret;
+
+		ret = sun50i_a100_ledc_dma_xfer(priv, length);
+		if (ret)
+			dev_warn(priv->dev, "Failed to set up DMA (%d), using PIO\n", ret);
+		else
+			use_dma = true;
+	}
+
+	/* The DMA trigger level must be at least the burst length. */
+	control = FIELD_PREP(LEDC_DMA_CTRL_REG_DMA_EN, use_dma) |
+		  FIELD_PREP_CONST(LEDC_DMA_CTRL_REG_FIFO_TRIG_LEVEL, LEDC_FIFO_DEPTH / 2);
+	writel(control, priv->base + LEDC_DMA_CTRL_REG);
+
+	control = readl(priv->base + LEDC_CTRL_REG);
+	control &= ~LEDC_CTRL_REG_DATA_LENGTH;
+	control |= FIELD_PREP(LEDC_CTRL_REG_DATA_LENGTH, length) | LEDC_CTRL_REG_LEDC_EN;
+	writel(control, priv->base + LEDC_CTRL_REG);
+
+	if (!use_dma) {
+		/* The FIFO is empty when starting a new transfer. */
+		unsigned int fifo_used = 0;
+
+		priv->pio_length = length;
+		priv->pio_offset = 0;
+
+		sun50i_a100_ledc_pio_xfer(priv, fifo_used);
+	}
+}
+
+static irqreturn_t sun50i_a100_ledc_irq(int irq, void *data)
+{
+	struct sun50i_a100_ledc *priv = data;
+	u32 status;
+
+	status = readl(priv->base + LEDC_INT_STS_REG);
+
+	if (status & LEDC_INT_STS_REG_TRANS_FINISH_INT) {
+		unsigned int next_length;
+
+		spin_lock(&priv->lock);
+
+		/* If another transfer is queued, dequeue and start it. */
+		next_length = priv->next_length;
+		if (next_length)
+			priv->next_length = 0;
+		else
+			priv->xfer_active = false;
+
+		spin_unlock(&priv->lock);
+
+		if (next_length)
+			sun50i_a100_ledc_start_xfer(priv, next_length);
+	} else if (status & LEDC_INT_STS_REG_FIFO_CPUREQ_INT) {
+		/* Continue the current transfer. */
+		sun50i_a100_ledc_pio_xfer(priv, FIELD_GET(LEDC_INT_STS_REG_FIFO_WLW, status));
+	}
+
+	/* Clear the W1C status bits. */
+	writel(status, priv->base + LEDC_INT_STS_REG);
+
+	return IRQ_HANDLED;
+}
+
+static void sun50i_a100_ledc_brightness_set(struct led_classdev *cdev,
+					    enum led_brightness brightness)
+{
+	struct sun50i_a100_ledc *priv = dev_get_drvdata(cdev->dev->parent);
+	struct led_classdev_mc *mc_cdev = lcdev_to_mccdev(cdev);
+	struct sun50i_a100_ledc_led *led = to_ledc_led(mc_cdev);
+	unsigned int next_length;
+	unsigned long flags;
+	bool xfer_active;
+
+	led_mc_calc_color_components(mc_cdev, brightness);
+
+	priv->buffer[led->addr] = led->subled_info[0].brightness << 16 |
+				  led->subled_info[1].brightness <<  8 |
+				  led->subled_info[2].brightness;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	/* Start, enqueue, or extend an enqueued transfer, as appropriate. */
+	next_length = max(priv->next_length, led->addr + 1);
+	xfer_active = priv->xfer_active;
+	if (xfer_active)
+		priv->next_length = next_length;
+	else
+		priv->xfer_active = true;
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	if (!xfer_active)
+		sun50i_a100_ledc_start_xfer(priv, next_length);
+}
+
+static const char *const sun50i_a100_ledc_formats[] = {
+	"rgb", "rbg", "grb", "gbr", "brg", "bgr",
+};
+
+static int sun50i_a100_ledc_parse_format(struct device *dev,
+					 struct sun50i_a100_ledc *priv)
+{
+	const char *format = "grb";
+	u32 i;
+
+	device_property_read_string(dev, "allwinner,pixel-format", &format);
+
+	for (i = 0; i < ARRAY_SIZE(sun50i_a100_ledc_formats); i++) {
+		if (!strcmp(format, sun50i_a100_ledc_formats[i])) {
+			priv->format = i;
+			return 0;
+		}
+	}
+
+	return dev_err_probe(dev, -EINVAL, "Bad pixel format '%s'\n", format);
+}
+
+static void sun50i_a100_ledc_set_format(struct sun50i_a100_ledc *priv)
+{
+	u32 control;
+
+	control = readl(priv->base + LEDC_CTRL_REG);
+	control &= ~LEDC_CTRL_REG_RGB_MODE;
+	control |= FIELD_PREP(LEDC_CTRL_REG_RGB_MODE, priv->format);
+	writel(control, priv->base + LEDC_CTRL_REG);
+}
+
+static const struct sun50i_a100_ledc_timing sun50i_a100_ledc_default_timing = {
+	.t0h_ns = 336,
+	.t0l_ns = 840,
+	.t1h_ns = 882,
+	.t1l_ns = 294,
+	.treset_ns = 300000,
+};
+
+static int sun50i_a100_ledc_parse_timing(struct device *dev,
+					 struct sun50i_a100_ledc *priv)
+{
+	struct sun50i_a100_ledc_timing *timing = &priv->timing;
+
+	*timing = sun50i_a100_ledc_default_timing;
+
+	device_property_read_u32(dev, "allwinner,t0h-ns", &timing->t0h_ns);
+	device_property_read_u32(dev, "allwinner,t0l-ns", &timing->t0l_ns);
+	device_property_read_u32(dev, "allwinner,t1h-ns", &timing->t1h_ns);
+	device_property_read_u32(dev, "allwinner,t1l-ns", &timing->t1l_ns);
+	device_property_read_u32(dev, "allwinner,treset-ns", &timing->treset_ns);
+
+	return 0;
+}
+
+static void sun50i_a100_ledc_set_timing(struct sun50i_a100_ledc *priv)
+{
+	const struct sun50i_a100_ledc_timing *timing = &priv->timing;
+	unsigned long mod_freq = clk_get_rate(priv->mod_clk);
+	u32 cycle_ns;
+	u32 control;
+
+	if (!mod_freq)
+		return;
+
+	cycle_ns = NSEC_PER_SEC / mod_freq;
+	control = FIELD_PREP(LEDC_T01_TIMING_CTRL_REG_T1H, timing->t1h_ns / cycle_ns) |
+		  FIELD_PREP(LEDC_T01_TIMING_CTRL_REG_T1L, timing->t1l_ns / cycle_ns) |
+		  FIELD_PREP(LEDC_T01_TIMING_CTRL_REG_T0H, timing->t0h_ns / cycle_ns) |
+		  FIELD_PREP(LEDC_T01_TIMING_CTRL_REG_T0L, timing->t0l_ns / cycle_ns);
+	writel(control, priv->base + LEDC_T01_TIMING_CTRL_REG);
+
+	control = FIELD_PREP(LEDC_RESET_TIMING_CTRL_REG_TR, timing->treset_ns / cycle_ns) |
+		  FIELD_PREP(LEDC_RESET_TIMING_CTRL_REG_LED_NUM, priv->max_addr);
+	writel(control, priv->base + LEDC_RESET_TIMING_CTRL_REG);
+}
+
+static int sun50i_a100_ledc_resume(struct device *dev)
+{
+	struct sun50i_a100_ledc *priv = dev_get_drvdata(dev);
+	int ret;
+
+	ret = reset_control_deassert(priv->reset);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(priv->bus_clk);
+	if (ret)
+		goto err_assert_reset;
+
+	ret = clk_prepare_enable(priv->mod_clk);
+	if (ret)
+		goto err_disable_bus_clk;
+
+	sun50i_a100_ledc_set_format(priv);
+	sun50i_a100_ledc_set_timing(priv);
+
+	writel(LEDC_INT_CTRL_REG_GLOBAL_INT_EN | LEDC_INT_CTRL_REG_TRANS_FINISH_INT_EN,
+	       priv->base + LEDC_INT_CTRL_REG);
+
+	return 0;
+
+err_disable_bus_clk:
+	clk_disable_unprepare(priv->bus_clk);
+err_assert_reset:
+	reset_control_assert(priv->reset);
+
+	return ret;
+}
+
+static int sun50i_a100_ledc_suspend(struct device *dev)
+{
+	struct sun50i_a100_ledc *priv = dev_get_drvdata(dev);
+
+	/* Wait for all transfers to complete. */
+	for (;;) {
+		unsigned long flags;
+		bool xfer_active;
+
+		spin_lock_irqsave(&priv->lock, flags);
+		xfer_active = priv->xfer_active;
+		spin_unlock_irqrestore(&priv->lock, flags);
+		if (!xfer_active)
+			break;
+
+		msleep(1);
+	}
+
+	clk_disable_unprepare(priv->mod_clk);
+	clk_disable_unprepare(priv->bus_clk);
+	reset_control_assert(priv->reset);
+
+	return 0;
+}
+
+static void sun50i_a100_ledc_dma_cleanup(void *data)
+{
+	struct sun50i_a100_ledc *priv = data;
+
+	dma_release_channel(priv->dma_chan);
+}
+
+static int sun50i_a100_ledc_probe(struct platform_device *pdev)
+{
+	struct dma_slave_config dma_cfg = {};
+	struct led_init_data init_data = {};
+	struct sun50i_a100_ledc_led *led;
+	struct device *dev = &pdev->dev;
+	struct sun50i_a100_ledc *priv;
+	struct fwnode_handle *child;
+	struct resource *mem;
+	u32 max_addr = 0;
+	u32 num_leds = 0;
+	int irq, ret;
+
+	/*
+	 * The maximum LED address must be known in sun50i_a100_ledc_resume() before
+	 * class device registration, so parse and validate the subnodes up front.
+	 */
+	device_for_each_child_node(dev, child) {
+		u32 addr, color;
+
+		ret = fwnode_property_read_u32(child, "reg", &addr);
+		if (ret || addr >= LEDC_MAX_LEDS) {
+			fwnode_handle_put(child);
+			return dev_err_probe(dev, -EINVAL, "'reg' must be between 0 and %d\n",
+					     LEDC_MAX_LEDS - 1);
+		}
+
+		ret = fwnode_property_read_u32(child, "color", &color);
+		if (ret || color != LED_COLOR_ID_RGB) {
+			fwnode_handle_put(child);
+			return dev_err_probe(dev, -EINVAL, "'color' must be LED_COLOR_ID_RGB\n");
+		}
+
+		max_addr = max(max_addr, addr);
+		num_leds++;
+	}
+
+	if (!num_leds)
+		return -ENODEV;
+
+	priv = devm_kzalloc(dev, struct_size(priv, leds, num_leds), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->dev = dev;
+	priv->max_addr = max_addr;
+	priv->num_leds = num_leds;
+	spin_lock_init(&priv->lock);
+	dev_set_drvdata(dev, priv);
+
+	ret = sun50i_a100_ledc_parse_format(dev, priv);
+	if (ret)
+		return ret;
+
+	ret = sun50i_a100_ledc_parse_timing(dev, priv);
+	if (ret)
+		return ret;
+
+	priv->base = devm_platform_get_and_ioremap_resource(pdev, 0, &mem);
+	if (IS_ERR(priv->base))
+		return PTR_ERR(priv->base);
+
+	priv->bus_clk = devm_clk_get(dev, "bus");
+	if (IS_ERR(priv->bus_clk))
+		return PTR_ERR(priv->bus_clk);
+
+	priv->mod_clk = devm_clk_get(dev, "mod");
+	if (IS_ERR(priv->mod_clk))
+		return PTR_ERR(priv->mod_clk);
+
+	priv->reset = devm_reset_control_get_exclusive(dev, NULL);
+	if (IS_ERR(priv->reset))
+		return PTR_ERR(priv->reset);
+
+	priv->dma_chan = dma_request_chan(dev, "tx");
+	if (IS_ERR(priv->dma_chan)) {
+		if (PTR_ERR(priv->dma_chan) != -ENODEV)
+			return PTR_ERR(priv->dma_chan);
+
+		priv->dma_chan = NULL;
+
+		priv->buffer = devm_kzalloc(dev, LEDS_TO_BYTES(LEDC_MAX_LEDS), GFP_KERNEL);
+		if (!priv->buffer)
+			return -ENOMEM;
+	} else {
+		ret = devm_add_action_or_reset(dev, sun50i_a100_ledc_dma_cleanup, priv);
+		if (ret)
+			return ret;
+
+		dma_cfg.dst_addr	= mem->start + LEDC_DATA_REG;
+		dma_cfg.dst_addr_width	= DMA_SLAVE_BUSWIDTH_4_BYTES;
+		dma_cfg.dst_maxburst	= LEDC_FIFO_DEPTH / 2;
+
+		ret = dmaengine_slave_config(priv->dma_chan, &dma_cfg);
+		if (ret)
+			return ret;
+
+		priv->buffer = dmam_alloc_attrs(dmaengine_get_dma_device(priv->dma_chan),
+						LEDS_TO_BYTES(LEDC_MAX_LEDS), &priv->dma_handle,
+						GFP_KERNEL, DMA_ATTR_WRITE_COMBINE);
+		if (!priv->buffer)
+			return -ENOMEM;
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	ret = devm_request_irq(dev, irq, sun50i_a100_ledc_irq, 0, dev_name(dev), priv);
+	if (ret)
+		return ret;
+
+	ret = sun50i_a100_ledc_resume(dev);
+	if (ret)
+		return ret;
+
+	led = priv->leds;
+	device_for_each_child_node(dev, child) {
+		struct led_classdev *cdev;
+
+		/* The node was already validated above. */
+		fwnode_property_read_u32(child, "reg", &led->addr);
+
+		led->subled_info[0].color_index = LED_COLOR_ID_RED;
+		led->subled_info[0].channel = 0;
+		led->subled_info[1].color_index = LED_COLOR_ID_GREEN;
+		led->subled_info[1].channel = 1;
+		led->subled_info[2].color_index = LED_COLOR_ID_BLUE;
+		led->subled_info[2].channel = 2;
+
+		led->mc_cdev.num_colors = ARRAY_SIZE(led->subled_info);
+		led->mc_cdev.subled_info = led->subled_info;
+
+		cdev = &led->mc_cdev.led_cdev;
+		cdev->max_brightness = U8_MAX;
+		cdev->brightness_set = sun50i_a100_ledc_brightness_set;
+
+		init_data.fwnode = child;
+
+		ret = led_classdev_multicolor_register_ext(dev, &led->mc_cdev, &init_data);
+		if (ret) {
+			dev_err_probe(dev, ret, "Failed to register multicolor LED %u", led->addr);
+			goto err_put_child;
+		}
+
+		led++;
+	}
+
+	dev_info(dev, "Registered %u LEDs\n", num_leds);
+
+	return 0;
+
+err_put_child:
+	fwnode_handle_put(child);
+	while (led-- > priv->leds)
+		led_classdev_multicolor_unregister(&led->mc_cdev);
+	sun50i_a100_ledc_suspend(&pdev->dev);
+
+	return ret;
+}
+
+static void sun50i_a100_ledc_remove(struct platform_device *pdev)
+{
+	struct sun50i_a100_ledc *priv = platform_get_drvdata(pdev);
+
+	for (u32 i = 0; i < priv->num_leds; i++)
+		led_classdev_multicolor_unregister(&priv->leds[i].mc_cdev);
+	sun50i_a100_ledc_suspend(&pdev->dev);
+}
+
+static const struct of_device_id sun50i_a100_ledc_of_match[] = {
+	{ .compatible = "allwinner,sun50i-a100-ledc" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, sun50i_a100_ledc_of_match);
+
+static DEFINE_SIMPLE_DEV_PM_OPS(sun50i_a100_ledc_pm,
+				sun50i_a100_ledc_suspend,
+				sun50i_a100_ledc_resume);
+
+static struct platform_driver sun50i_a100_ledc_driver = {
+	.probe		= sun50i_a100_ledc_probe,
+	.remove_new	= sun50i_a100_ledc_remove,
+	.shutdown	= sun50i_a100_ledc_remove,
+	.driver		= {
+		.name		= "sun50i-a100-ledc",
+		.of_match_table	= sun50i_a100_ledc_of_match,
+		.pm		= pm_ptr(&sun50i_a100_ledc_pm),
+	},
+};
+module_platform_driver(sun50i_a100_ledc_driver);
+
+MODULE_AUTHOR("Samuel Holland <samuel@sholland.org>");
+MODULE_DESCRIPTION("Allwinner A100 LED controller driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/leds/leds-syscon.c b/drivers/leds/leds-syscon.c
index 360a376fa738..d633ad519d0c 100644
--- a/drivers/leds/leds-syscon.c
+++ b/drivers/leds/leds-syscon.c
@@ -81,7 +81,8 @@ static int syscon_led_probe(struct platform_device *pdev)
 
 	sled->map = map;
 
-	if (of_property_read_u32(np, "offset", &sled->offset))
+	if (of_property_read_u32(np, "reg", &sled->offset) &&
+	    of_property_read_u32(np, "offset", &sled->offset))
 		return -EINVAL;
 	if (of_property_read_u32(np, "mask", &sled->mask))
 		return -EINVAL;
diff --git a/drivers/leds/leds-tca6507.c b/drivers/leds/leds-tca6507.c
index e19074614095..4f22f4224946 100644
--- a/drivers/leds/leds-tca6507.c
+++ b/drivers/leds/leds-tca6507.c
@@ -638,19 +638,13 @@ static int tca6507_probe_gpios(struct device *dev,
 	tca->gpio.direction_output = tca6507_gpio_direction_output;
 	tca->gpio.set = tca6507_gpio_set_value;
 	tca->gpio.parent = dev;
-	err = gpiochip_add_data(&tca->gpio, tca);
+	err = devm_gpiochip_add_data(dev, &tca->gpio, tca);
 	if (err) {
 		tca->gpio.ngpio = 0;
 		return err;
 	}
 	return 0;
 }
-
-static void tca6507_remove_gpio(struct tca6507_chip *tca)
-{
-	if (tca->gpio.ngpio)
-		gpiochip_remove(&tca->gpio);
-}
 #else /* CONFIG_GPIOLIB */
 static int tca6507_probe_gpios(struct device *dev,
 			       struct tca6507_chip *tca,
@@ -658,9 +652,6 @@ static int tca6507_probe_gpios(struct device *dev,
 {
 	return 0;
 }
-static void tca6507_remove_gpio(struct tca6507_chip *tca)
-{
-}
 #endif /* CONFIG_GPIOLIB */
 
 static struct tca6507_platform_data *
@@ -762,38 +753,25 @@ static int tca6507_probe(struct i2c_client *client)
 			l->led_cdev.brightness_set = tca6507_brightness_set;
 			l->led_cdev.blink_set = tca6507_blink_set;
 			l->bank = -1;
-			err = led_classdev_register(dev, &l->led_cdev);
+			err = devm_led_classdev_register(dev, &l->led_cdev);
 			if (err < 0)
-				goto exit;
+				return err;
 		}
 	}
 	err = tca6507_probe_gpios(dev, tca, pdata);
 	if (err)
-		goto exit;
+		return err;
 	/* set all registers to known state - zero */
 	tca->reg_set = 0x7f;
 	schedule_work(&tca->work);
 
 	return 0;
-exit:
-	while (i--) {
-		if (tca->leds[i].led_cdev.name)
-			led_classdev_unregister(&tca->leds[i].led_cdev);
-	}
-	return err;
 }
 
 static void tca6507_remove(struct i2c_client *client)
 {
-	int i;
 	struct tca6507_chip *tca = i2c_get_clientdata(client);
-	struct tca6507_led *tca_leds = tca->leds;
 
-	for (i = 0; i < NUM_LEDS; i++) {
-		if (tca_leds[i].led_cdev.name)
-			led_classdev_unregister(&tca_leds[i].led_cdev);
-	}
-	tca6507_remove_gpio(tca);
 	cancel_work_sync(&tca->work);
 }
 
diff --git a/drivers/leds/rgb/Kconfig b/drivers/leds/rgb/Kconfig
index a6a21f564673..e66bd21b9852 100644
--- a/drivers/leds/rgb/Kconfig
+++ b/drivers/leds/rgb/Kconfig
@@ -4,7 +4,7 @@ if LEDS_CLASS_MULTICOLOR
 
 config LEDS_GROUP_MULTICOLOR
 	tristate "LEDs group multi-color support"
-	depends on OF || COMPILE_TEST
+	depends on OF
 	help
 	  This option enables support for monochrome LEDs that are grouped
 	  into multicolor LEDs which is useful in the case where LEDs of
diff --git a/drivers/leds/rgb/leds-qcom-lpg.c b/drivers/leds/rgb/leds-qcom-lpg.c
index 68d82a682bf6..156b73d1f4a2 100644
--- a/drivers/leds/rgb/leds-qcom-lpg.c
+++ b/drivers/leds/rgb/leds-qcom-lpg.c
@@ -552,9 +552,9 @@ static int lpg_parse_dtest(struct lpg *lpg)
 		ret = count;
 		goto err_malformed;
 	} else if (count != lpg->data->num_channels * 2) {
-		dev_err(lpg->dev, "qcom,dtest needs to be %d items\n",
-			lpg->data->num_channels * 2);
-		return -EINVAL;
+		return dev_err_probe(lpg->dev, -EINVAL,
+				     "qcom,dtest needs to be %d items\n",
+				     lpg->data->num_channels * 2);
 	}
 
 	for (i = 0; i < lpg->data->num_channels; i++) {
@@ -574,8 +574,7 @@ static int lpg_parse_dtest(struct lpg *lpg)
 	return 0;
 
 err_malformed:
-	dev_err(lpg->dev, "malformed qcom,dtest\n");
-	return ret;
+	return dev_err_probe(lpg->dev, ret, "malformed qcom,dtest\n");
 }
 
 static void lpg_apply_dtest(struct lpg_channel *chan)
@@ -977,9 +976,14 @@ static int lpg_pattern_mc_clear(struct led_classdev *cdev)
 	return lpg_pattern_clear(led);
 }
 
+static inline struct lpg *lpg_pwm_from_chip(struct pwm_chip *chip)
+{
+	return container_of(chip, struct lpg, pwm);
+}
+
 static int lpg_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm)
 {
-	struct lpg *lpg = container_of(chip, struct lpg, pwm);
+	struct lpg *lpg = lpg_pwm_from_chip(chip);
 	struct lpg_channel *chan = &lpg->channels[pwm->hwpwm];
 
 	return chan->in_use ? -EBUSY : 0;
@@ -995,7 +999,7 @@ static int lpg_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm)
 static int lpg_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 			 const struct pwm_state *state)
 {
-	struct lpg *lpg = container_of(chip, struct lpg, pwm);
+	struct lpg *lpg = lpg_pwm_from_chip(chip);
 	struct lpg_channel *chan = &lpg->channels[pwm->hwpwm];
 	int ret = 0;
 
@@ -1026,7 +1030,7 @@ out_unlock:
 static int lpg_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm,
 			     struct pwm_state *state)
 {
-	struct lpg *lpg = container_of(chip, struct lpg, pwm);
+	struct lpg *lpg = lpg_pwm_from_chip(chip);
 	struct lpg_channel *chan = &lpg->channels[pwm->hwpwm];
 	unsigned int resolution;
 	unsigned int pre_div;
@@ -1095,9 +1099,9 @@ static int lpg_add_pwm(struct lpg *lpg)
 	lpg->pwm.npwm = lpg->num_channels;
 	lpg->pwm.ops = &lpg_pwm_ops;
 
-	ret = pwmchip_add(&lpg->pwm);
+	ret = devm_pwmchip_add(lpg->dev, &lpg->pwm);
 	if (ret)
-		dev_err(lpg->dev, "failed to add PWM chip: ret %d\n", ret);
+		dev_err_probe(lpg->dev, ret, "failed to add PWM chip\n");
 
 	return ret;
 }
@@ -1111,19 +1115,16 @@ static int lpg_parse_channel(struct lpg *lpg, struct device_node *np,
 	int ret;
 
 	ret = of_property_read_u32(np, "reg", &reg);
-	if (ret || !reg || reg > lpg->num_channels) {
-		dev_err(lpg->dev, "invalid \"reg\" of %pOFn\n", np);
-		return -EINVAL;
-	}
+	if (ret || !reg || reg > lpg->num_channels)
+		return dev_err_probe(lpg->dev, -EINVAL, "invalid \"reg\" of %pOFn\n", np);
 
 	chan = &lpg->channels[reg - 1];
 	chan->in_use = true;
 
 	ret = of_property_read_u32(np, "color", &color);
-	if (ret < 0 && ret != -EINVAL) {
-		dev_err(lpg->dev, "failed to parse \"color\" of %pOF\n", np);
-		return ret;
-	}
+	if (ret < 0 && ret != -EINVAL)
+		return dev_err_probe(lpg->dev, ret,
+				     "failed to parse \"color\" of %pOF\n", np);
 
 	chan->color = color;
 
@@ -1146,10 +1147,9 @@ static int lpg_add_led(struct lpg *lpg, struct device_node *np)
 	int i;
 
 	ret = of_property_read_u32(np, "color", &color);
-	if (ret < 0 && ret != -EINVAL) {
-		dev_err(lpg->dev, "failed to parse \"color\" of %pOF\n", np);
-		return ret;
-	}
+	if (ret < 0 && ret != -EINVAL)
+		return dev_err_probe(lpg->dev, ret,
+			      "failed to parse \"color\" of %pOF\n", np);
 
 	if (color == LED_COLOR_ID_RGB)
 		num_channels = of_get_available_child_count(np);
@@ -1226,7 +1226,7 @@ static int lpg_add_led(struct lpg *lpg, struct device_node *np)
 	else
 		ret = devm_led_classdev_register_ext(lpg->dev, &led->cdev, &init_data);
 	if (ret)
-		dev_err(lpg->dev, "unable to register %s\n", cdev->name);
+		dev_err_probe(lpg->dev, ret, "unable to register %s\n", cdev->name);
 
 	return ret;
 }
@@ -1272,10 +1272,9 @@ static int lpg_init_triled(struct lpg *lpg)
 
 	if (lpg->triled_has_src_sel) {
 		ret = of_property_read_u32(np, "qcom,power-source", &lpg->triled_src);
-		if (ret || lpg->triled_src == 2 || lpg->triled_src > 3) {
-			dev_err(lpg->dev, "invalid power source\n");
-			return -EINVAL;
-		}
+		if (ret || lpg->triled_src == 2 || lpg->triled_src > 3)
+			return dev_err_probe(lpg->dev, -EINVAL,
+					     "invalid power source\n");
 	}
 
 	/* Disable automatic trickle charge LED */
@@ -1324,8 +1323,6 @@ static int lpg_probe(struct platform_device *pdev)
 	if (!lpg->data)
 		return -EINVAL;
 
-	platform_set_drvdata(pdev, lpg);
-
 	lpg->dev = &pdev->dev;
 	mutex_init(&lpg->lock);
 
@@ -1363,13 +1360,6 @@ static int lpg_probe(struct platform_device *pdev)
 	return lpg_add_pwm(lpg);
 }
 
-static void lpg_remove(struct platform_device *pdev)
-{
-	struct lpg *lpg = platform_get_drvdata(pdev);
-
-	pwmchip_remove(&lpg->pwm);
-}
-
 static const struct lpg_data pm8916_pwm_data = {
 	.num_channels = 1,
 	.channels = (const struct lpg_channel_data[]) {
@@ -1529,7 +1519,6 @@ MODULE_DEVICE_TABLE(of, lpg_of_table);
 
 static struct platform_driver lpg_driver = {
 	.probe = lpg_probe,
-	.remove_new = lpg_remove,
 	.driver = {
 		.name = "qcom-spmi-lpg",
 		.of_match_table = lpg_of_table,
diff --git a/drivers/leds/trigger/ledtrig-gpio.c b/drivers/leds/trigger/ledtrig-gpio.c
index 9b7fe5dd5208..7f6a2352b0ac 100644
--- a/drivers/leds/trigger/ledtrig-gpio.c
+++ b/drivers/leds/trigger/ledtrig-gpio.c
@@ -41,33 +41,30 @@ static irqreturn_t gpio_trig_irq(int irq, void *_led)
 	return IRQ_HANDLED;
 }
 
-static ssize_t gpio_trig_brightness_show(struct device *dev,
+static ssize_t desired_brightness_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
 
-	return sprintf(buf, "%u\n", gpio_data->desired_brightness);
+	return sysfs_emit(buf, "%u\n", gpio_data->desired_brightness);
 }
 
-static ssize_t gpio_trig_brightness_store(struct device *dev,
+static ssize_t desired_brightness_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t n)
 {
 	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
-	unsigned desired_brightness;
+	u8 desired_brightness;
 	int ret;
 
-	ret = sscanf(buf, "%u", &desired_brightness);
-	if (ret < 1 || desired_brightness > 255) {
-		dev_err(dev, "invalid value\n");
-		return -EINVAL;
-	}
+	ret = kstrtou8(buf, 10, &desired_brightness);
+	if (ret)
+		return ret;
 
 	gpio_data->desired_brightness = desired_brightness;
 
 	return n;
 }
-static DEVICE_ATTR(desired_brightness, 0644, gpio_trig_brightness_show,
-		gpio_trig_brightness_store);
+static DEVICE_ATTR_RW(desired_brightness);
 
 static struct attribute *gpio_trig_attrs[] = {
 	&dev_attr_desired_brightness.attr,
@@ -89,10 +86,7 @@ static int gpio_trig_activate(struct led_classdev *led)
 	 * The generic property "trigger-sources" is followed,
 	 * and we hope that this is a GPIO.
 	 */
-	gpio_data->gpiod = fwnode_gpiod_get_index(dev->fwnode,
-						  "trigger-sources",
-						  0, GPIOD_IN,
-						  "led-trigger");
+	gpio_data->gpiod = gpiod_get_optional(dev, "trigger-sources", GPIOD_IN);
 	if (IS_ERR(gpio_data->gpiod)) {
 		ret = PTR_ERR(gpio_data->gpiod);
 		kfree(gpio_data);
@@ -104,6 +98,8 @@ static int gpio_trig_activate(struct led_classdev *led)
 		return -EINVAL;
 	}
 
+	gpiod_set_consumer_name(gpio_data->gpiod, "led-trigger");
+
 	gpio_data->led = led;
 	led_set_trigger_data(led, gpio_data);
 
diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c
index d76214fa9ad8..8e5475819590 100644
--- a/drivers/leds/trigger/ledtrig-netdev.c
+++ b/drivers/leds/trigger/ledtrig-netdev.c
@@ -38,6 +38,16 @@
  * tx -  LED blinks on transmitted data
  * rx -  LED blinks on receive data
  *
+ * Note: If the user selects a mode that is not supported by hw, default
+ * behavior is to fall back to software control of the LED. However not every
+ * hw supports software control. LED callbacks brightness_set() and
+ * brightness_set_blocking() are NULL in this case. hw_control_is_supported()
+ * should use available means supported by hw to inform the user that selected
+ * mode isn't supported by hw. This could be switching off the LED or any
+ * hw blink mode. If software control fallback isn't possible, we return
+ * -EOPNOTSUPP to the user, but still store the selected mode. This is needed
+ * in case an intermediate unsupported mode is necessary to switch from one
+ * supported mode to another.
  */
 
 struct led_netdev_data {
@@ -99,6 +109,18 @@ static void set_baseline_state(struct led_netdev_data *trigger_data)
 		    trigger_data->link_speed == SPEED_1000)
 			blink_on = true;
 
+		if (test_bit(TRIGGER_NETDEV_LINK_2500, &trigger_data->mode) &&
+		    trigger_data->link_speed == SPEED_2500)
+			blink_on = true;
+
+		if (test_bit(TRIGGER_NETDEV_LINK_5000, &trigger_data->mode) &&
+		    trigger_data->link_speed == SPEED_5000)
+			blink_on = true;
+
+		if (test_bit(TRIGGER_NETDEV_LINK_10000, &trigger_data->mode) &&
+		    trigger_data->link_speed == SPEED_10000)
+			blink_on = true;
+
 		if (test_bit(TRIGGER_NETDEV_HALF_DUPLEX, &trigger_data->mode) &&
 		    trigger_data->duplex == DUPLEX_HALF)
 			blink_on = true;
@@ -289,6 +311,9 @@ static ssize_t netdev_led_attr_show(struct device *dev, char *buf,
 	case TRIGGER_NETDEV_LINK_10:
 	case TRIGGER_NETDEV_LINK_100:
 	case TRIGGER_NETDEV_LINK_1000:
+	case TRIGGER_NETDEV_LINK_2500:
+	case TRIGGER_NETDEV_LINK_5000:
+	case TRIGGER_NETDEV_LINK_10000:
 	case TRIGGER_NETDEV_HALF_DUPLEX:
 	case TRIGGER_NETDEV_FULL_DUPLEX:
 	case TRIGGER_NETDEV_TX:
@@ -306,6 +331,7 @@ static ssize_t netdev_led_attr_store(struct device *dev, const char *buf,
 				     size_t size, enum led_trigger_netdev_modes attr)
 {
 	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
+	struct led_classdev *led_cdev = trigger_data->led_cdev;
 	unsigned long state, mode = trigger_data->mode;
 	int ret;
 	int bit;
@@ -319,6 +345,9 @@ static ssize_t netdev_led_attr_store(struct device *dev, const char *buf,
 	case TRIGGER_NETDEV_LINK_10:
 	case TRIGGER_NETDEV_LINK_100:
 	case TRIGGER_NETDEV_LINK_1000:
+	case TRIGGER_NETDEV_LINK_2500:
+	case TRIGGER_NETDEV_LINK_5000:
+	case TRIGGER_NETDEV_LINK_10000:
 	case TRIGGER_NETDEV_HALF_DUPLEX:
 	case TRIGGER_NETDEV_FULL_DUPLEX:
 	case TRIGGER_NETDEV_TX:
@@ -337,7 +366,10 @@ static ssize_t netdev_led_attr_store(struct device *dev, const char *buf,
 	if (test_bit(TRIGGER_NETDEV_LINK, &mode) &&
 	    (test_bit(TRIGGER_NETDEV_LINK_10, &mode) ||
 	     test_bit(TRIGGER_NETDEV_LINK_100, &mode) ||
-	     test_bit(TRIGGER_NETDEV_LINK_1000, &mode)))
+	     test_bit(TRIGGER_NETDEV_LINK_1000, &mode) ||
+	     test_bit(TRIGGER_NETDEV_LINK_2500, &mode) ||
+	     test_bit(TRIGGER_NETDEV_LINK_5000, &mode) ||
+	     test_bit(TRIGGER_NETDEV_LINK_10000, &mode)))
 		return -EINVAL;
 
 	cancel_delayed_work_sync(&trigger_data->work);
@@ -345,6 +377,10 @@ static ssize_t netdev_led_attr_store(struct device *dev, const char *buf,
 	trigger_data->mode = mode;
 	trigger_data->hw_control = can_hw_control(trigger_data);
 
+	if (!led_cdev->brightness_set && !led_cdev->brightness_set_blocking &&
+	    !trigger_data->hw_control)
+		return -EOPNOTSUPP;
+
 	set_baseline_state(trigger_data);
 
 	return size;
@@ -367,6 +403,9 @@ DEFINE_NETDEV_TRIGGER(link, TRIGGER_NETDEV_LINK);
 DEFINE_NETDEV_TRIGGER(link_10, TRIGGER_NETDEV_LINK_10);
 DEFINE_NETDEV_TRIGGER(link_100, TRIGGER_NETDEV_LINK_100);
 DEFINE_NETDEV_TRIGGER(link_1000, TRIGGER_NETDEV_LINK_1000);
+DEFINE_NETDEV_TRIGGER(link_2500, TRIGGER_NETDEV_LINK_2500);
+DEFINE_NETDEV_TRIGGER(link_5000, TRIGGER_NETDEV_LINK_5000);
+DEFINE_NETDEV_TRIGGER(link_10000, TRIGGER_NETDEV_LINK_10000);
 DEFINE_NETDEV_TRIGGER(half_duplex, TRIGGER_NETDEV_HALF_DUPLEX);
 DEFINE_NETDEV_TRIGGER(full_duplex, TRIGGER_NETDEV_FULL_DUPLEX);
 DEFINE_NETDEV_TRIGGER(tx, TRIGGER_NETDEV_TX);
@@ -425,6 +464,9 @@ static struct attribute *netdev_trig_attrs[] = {
 	&dev_attr_link_10.attr,
 	&dev_attr_link_100.attr,
 	&dev_attr_link_1000.attr,
+	&dev_attr_link_2500.attr,
+	&dev_attr_link_5000.attr,
+	&dev_attr_link_10000.attr,
 	&dev_attr_full_duplex.attr,
 	&dev_attr_half_duplex.attr,
 	&dev_attr_rx.attr,
@@ -522,6 +564,9 @@ static void netdev_trig_work(struct work_struct *work)
 			 test_bit(TRIGGER_NETDEV_LINK_10, &trigger_data->mode) ||
 			 test_bit(TRIGGER_NETDEV_LINK_100, &trigger_data->mode) ||
 			 test_bit(TRIGGER_NETDEV_LINK_1000, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_LINK_2500, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_LINK_5000, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_LINK_10000, &trigger_data->mode) ||
 			 test_bit(TRIGGER_NETDEV_HALF_DUPLEX, &trigger_data->mode) ||
 			 test_bit(TRIGGER_NETDEV_FULL_DUPLEX, &trigger_data->mode);
 		interval = jiffies_to_msecs(
diff --git a/drivers/leds/trigger/ledtrig-panic.c b/drivers/leds/trigger/ledtrig-panic.c
index 64abf2e91608..5a6b21bfeb9a 100644
--- a/drivers/leds/trigger/ledtrig-panic.c
+++ b/drivers/leds/trigger/ledtrig-panic.c
@@ -64,10 +64,13 @@ static long led_panic_blink(int state)
 
 static int __init ledtrig_panic_init(void)
 {
+	led_trigger_register_simple("panic", &trigger);
+	if (!trigger)
+		return -ENOMEM;
+
 	atomic_notifier_chain_register(&panic_notifier_list,
 				       &led_trigger_panic_nb);
 
-	led_trigger_register_simple("panic", &trigger);
 	panic_blink = led_panic_blink;
 	return 0;
 }
diff --git a/drivers/leds/trigger/ledtrig-tty.c b/drivers/leds/trigger/ledtrig-tty.c
index 8ae0d2d284af..8cf1485e8165 100644
--- a/drivers/leds/trigger/ledtrig-tty.c
+++ b/drivers/leds/trigger/ledtrig-tty.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
+#include <linux/completion.h>
 #include <linux/delay.h>
 #include <linux/leds.h>
 #include <linux/module.h>
@@ -12,15 +13,45 @@
 struct ledtrig_tty_data {
 	struct led_classdev *led_cdev;
 	struct delayed_work dwork;
-	struct mutex mutex;
+	struct completion sysfs;
 	const char *ttyname;
 	struct tty_struct *tty;
 	int rx, tx;
+	bool mode_rx;
+	bool mode_tx;
+	bool mode_cts;
+	bool mode_dsr;
+	bool mode_dcd;
+	bool mode_rng;
 };
 
-static void ledtrig_tty_restart(struct ledtrig_tty_data *trigger_data)
+/* Indicates which state the LED should now display */
+enum led_trigger_tty_state {
+	TTY_LED_BLINK,
+	TTY_LED_ENABLE,
+	TTY_LED_DISABLE,
+};
+
+enum led_trigger_tty_modes {
+	TRIGGER_TTY_RX = 0,
+	TRIGGER_TTY_TX,
+	TRIGGER_TTY_CTS,
+	TRIGGER_TTY_DSR,
+	TRIGGER_TTY_DCD,
+	TRIGGER_TTY_RNG,
+};
+
+static int ledtrig_tty_wait_for_completion(struct device *dev)
 {
-	schedule_delayed_work(&trigger_data->dwork, 0);
+	struct ledtrig_tty_data *trigger_data = led_trigger_get_drvdata(dev);
+	int ret;
+
+	ret = wait_for_completion_timeout(&trigger_data->sysfs,
+					  msecs_to_jiffies(LEDTRIG_TTY_INTERVAL * 20));
+	if (ret == 0)
+		return -ETIMEDOUT;
+
+	return ret;
 }
 
 static ssize_t ttyname_show(struct device *dev,
@@ -28,14 +59,16 @@ static ssize_t ttyname_show(struct device *dev,
 {
 	struct ledtrig_tty_data *trigger_data = led_trigger_get_drvdata(dev);
 	ssize_t len = 0;
+	int completion;
 
-	mutex_lock(&trigger_data->mutex);
+	reinit_completion(&trigger_data->sysfs);
+	completion = ledtrig_tty_wait_for_completion(dev);
+	if (completion < 0)
+		return completion;
 
 	if (trigger_data->ttyname)
 		len = sprintf(buf, "%s\n", trigger_data->ttyname);
 
-	mutex_unlock(&trigger_data->mutex);
-
 	return len;
 }
 
@@ -46,7 +79,7 @@ static ssize_t ttyname_store(struct device *dev,
 	struct ledtrig_tty_data *trigger_data = led_trigger_get_drvdata(dev);
 	char *ttyname;
 	ssize_t ret = size;
-	bool running;
+	int completion;
 
 	if (size > 0 && buf[size - 1] == '\n')
 		size -= 1;
@@ -59,9 +92,10 @@ static ssize_t ttyname_store(struct device *dev,
 		ttyname = NULL;
 	}
 
-	mutex_lock(&trigger_data->mutex);
-
-	running = trigger_data->ttyname != NULL;
+	reinit_completion(&trigger_data->sysfs);
+	completion = ledtrig_tty_wait_for_completion(dev);
+	if (completion < 0)
+		return completion;
 
 	kfree(trigger_data->ttyname);
 	tty_kref_put(trigger_data->tty);
@@ -69,29 +103,107 @@ static ssize_t ttyname_store(struct device *dev,
 
 	trigger_data->ttyname = ttyname;
 
-	mutex_unlock(&trigger_data->mutex);
-
-	if (ttyname && !running)
-		ledtrig_tty_restart(trigger_data);
-
 	return ret;
 }
 static DEVICE_ATTR_RW(ttyname);
 
+static ssize_t ledtrig_tty_attr_show(struct device *dev, char *buf,
+				     enum led_trigger_tty_modes attr)
+{
+	struct ledtrig_tty_data *trigger_data = led_trigger_get_drvdata(dev);
+	bool state;
+
+	switch (attr) {
+	case TRIGGER_TTY_RX:
+		state = trigger_data->mode_rx;
+		break;
+	case TRIGGER_TTY_TX:
+		state = trigger_data->mode_tx;
+		break;
+	case TRIGGER_TTY_CTS:
+		state = trigger_data->mode_cts;
+		break;
+	case TRIGGER_TTY_DSR:
+		state = trigger_data->mode_dsr;
+		break;
+	case TRIGGER_TTY_DCD:
+		state = trigger_data->mode_dcd;
+		break;
+	case TRIGGER_TTY_RNG:
+		state = trigger_data->mode_rng;
+		break;
+	}
+
+	return sysfs_emit(buf, "%u\n", state);
+}
+
+static ssize_t ledtrig_tty_attr_store(struct device *dev, const char *buf,
+				      size_t size, enum led_trigger_tty_modes attr)
+{
+	struct ledtrig_tty_data *trigger_data = led_trigger_get_drvdata(dev);
+	bool state;
+	int ret;
+
+	ret = kstrtobool(buf, &state);
+	if (ret)
+		return ret;
+
+	switch (attr) {
+	case TRIGGER_TTY_RX:
+		trigger_data->mode_rx = state;
+		break;
+	case TRIGGER_TTY_TX:
+		trigger_data->mode_tx = state;
+		break;
+	case TRIGGER_TTY_CTS:
+		trigger_data->mode_cts = state;
+		break;
+	case TRIGGER_TTY_DSR:
+		trigger_data->mode_dsr = state;
+		break;
+	case TRIGGER_TTY_DCD:
+		trigger_data->mode_dcd = state;
+		break;
+	case TRIGGER_TTY_RNG:
+		trigger_data->mode_rng = state;
+		break;
+	}
+
+	return size;
+}
+
+#define DEFINE_TTY_TRIGGER(trigger_name, trigger) \
+	static ssize_t trigger_name##_show(struct device *dev, \
+		struct device_attribute *attr, char *buf) \
+	{ \
+		return ledtrig_tty_attr_show(dev, buf, trigger); \
+	} \
+	static ssize_t trigger_name##_store(struct device *dev, \
+		struct device_attribute *attr, const char *buf, size_t size) \
+	{ \
+		return ledtrig_tty_attr_store(dev, buf, size, trigger); \
+	} \
+	static DEVICE_ATTR_RW(trigger_name)
+
+DEFINE_TTY_TRIGGER(rx, TRIGGER_TTY_RX);
+DEFINE_TTY_TRIGGER(tx, TRIGGER_TTY_TX);
+DEFINE_TTY_TRIGGER(cts, TRIGGER_TTY_CTS);
+DEFINE_TTY_TRIGGER(dsr, TRIGGER_TTY_DSR);
+DEFINE_TTY_TRIGGER(dcd, TRIGGER_TTY_DCD);
+DEFINE_TTY_TRIGGER(rng, TRIGGER_TTY_RNG);
+
 static void ledtrig_tty_work(struct work_struct *work)
 {
 	struct ledtrig_tty_data *trigger_data =
 		container_of(work, struct ledtrig_tty_data, dwork.work);
-	struct serial_icounter_struct icount;
+	enum led_trigger_tty_state state = TTY_LED_DISABLE;
+	unsigned long interval = LEDTRIG_TTY_INTERVAL;
+	bool invert = false;
+	int status;
 	int ret;
 
-	mutex_lock(&trigger_data->mutex);
-
-	if (!trigger_data->ttyname) {
-		/* exit without rescheduling */
-		mutex_unlock(&trigger_data->mutex);
-		return;
-	}
+	if (!trigger_data->ttyname)
+		goto out;
 
 	/* try to get the tty corresponding to $ttyname */
 	if (!trigger_data->tty) {
@@ -115,32 +227,83 @@ static void ledtrig_tty_work(struct work_struct *work)
 		trigger_data->tty = tty;
 	}
 
-	ret = tty_get_icount(trigger_data->tty, &icount);
-	if (ret) {
-		dev_info(trigger_data->tty->dev, "Failed to get icount, stopped polling\n");
-		mutex_unlock(&trigger_data->mutex);
-		return;
+	status = tty_get_tiocm(trigger_data->tty);
+	if (status > 0) {
+		if (trigger_data->mode_cts) {
+			if (status & TIOCM_CTS)
+				state = TTY_LED_ENABLE;
+		}
+
+		if (trigger_data->mode_dsr) {
+			if (status & TIOCM_DSR)
+				state = TTY_LED_ENABLE;
+		}
+
+		if (trigger_data->mode_dcd) {
+			if (status & TIOCM_CAR)
+				state = TTY_LED_ENABLE;
+		}
+
+		if (trigger_data->mode_rng) {
+			if (status & TIOCM_RNG)
+				state = TTY_LED_ENABLE;
+		}
 	}
 
-	if (icount.rx != trigger_data->rx ||
-	    icount.tx != trigger_data->tx) {
-		unsigned long interval = LEDTRIG_TTY_INTERVAL;
+	/*
+	 * The evaluation of rx/tx must be done after the evaluation
+	 * of TIOCM_*, because rx/tx has priority.
+	 */
+	if (trigger_data->mode_rx || trigger_data->mode_tx) {
+		struct serial_icounter_struct icount;
 
-		led_blink_set_oneshot(trigger_data->led_cdev, &interval,
-				      &interval, 0);
+		ret = tty_get_icount(trigger_data->tty, &icount);
+		if (ret)
+			goto out;
 
-		trigger_data->rx = icount.rx;
-		trigger_data->tx = icount.tx;
+		if (trigger_data->mode_tx && (icount.tx != trigger_data->tx)) {
+			trigger_data->tx = icount.tx;
+			invert = state == TTY_LED_ENABLE;
+			state = TTY_LED_BLINK;
+		}
+
+		if (trigger_data->mode_rx && (icount.rx != trigger_data->rx)) {
+			trigger_data->rx = icount.rx;
+			invert = state == TTY_LED_ENABLE;
+			state = TTY_LED_BLINK;
+		}
 	}
 
 out:
-	mutex_unlock(&trigger_data->mutex);
+	switch (state) {
+	case TTY_LED_BLINK:
+		led_blink_set_oneshot(trigger_data->led_cdev, &interval,
+				&interval, invert);
+		break;
+	case TTY_LED_ENABLE:
+		led_set_brightness(trigger_data->led_cdev,
+				trigger_data->led_cdev->blink_brightness);
+		break;
+	case TTY_LED_DISABLE:
+		fallthrough;
+	default:
+		led_set_brightness(trigger_data->led_cdev, LED_OFF);
+		break;
+	}
+
+	complete_all(&trigger_data->sysfs);
 	schedule_delayed_work(&trigger_data->dwork,
 			      msecs_to_jiffies(LEDTRIG_TTY_INTERVAL * 2));
 }
 
 static struct attribute *ledtrig_tty_attrs[] = {
 	&dev_attr_ttyname.attr,
+	&dev_attr_rx.attr,
+	&dev_attr_tx.attr,
+	&dev_attr_cts.attr,
+	&dev_attr_dsr.attr,
+	&dev_attr_dcd.attr,
+	&dev_attr_rng.attr,
 	NULL
 };
 ATTRIBUTE_GROUPS(ledtrig_tty);
@@ -153,11 +316,17 @@ static int ledtrig_tty_activate(struct led_classdev *led_cdev)
 	if (!trigger_data)
 		return -ENOMEM;
 
+	/* Enable default rx/tx mode */
+	trigger_data->mode_rx = true;
+	trigger_data->mode_tx = true;
+
 	led_set_trigger_data(led_cdev, trigger_data);
 
 	INIT_DELAYED_WORK(&trigger_data->dwork, ledtrig_tty_work);
 	trigger_data->led_cdev = led_cdev;
-	mutex_init(&trigger_data->mutex);
+	init_completion(&trigger_data->sysfs);
+
+	schedule_delayed_work(&trigger_data->dwork, 0);
 
 	return 0;
 }
@@ -168,6 +337,10 @@ static void ledtrig_tty_deactivate(struct led_classdev *led_cdev)
 
 	cancel_delayed_work_sync(&trigger_data->dwork);
 
+	kfree(trigger_data->ttyname);
+	tty_kref_put(trigger_data->tty);
+	trigger_data->tty = NULL;
+
 	kfree(trigger_data);
 }
 
diff --git a/drivers/mailbox/arm_mhuv2.c b/drivers/mailbox/arm_mhuv2.c
index c6d4957c4da8..0ec21dcdbde7 100644
--- a/drivers/mailbox/arm_mhuv2.c
+++ b/drivers/mailbox/arm_mhuv2.c
@@ -553,7 +553,8 @@ static irqreturn_t mhuv2_sender_interrupt(int irq, void *data)
 	priv = chan->con_priv;
 
 	if (!IS_PROTOCOL_DOORBELL(priv)) {
-		writel_relaxed(1, &mhu->send->ch_wn[priv->ch_wn_idx + priv->windows - 1].int_clr);
+		for (i = 0; i < priv->windows; i++)
+			writel_relaxed(1, &mhu->send->ch_wn[priv->ch_wn_idx + i].int_clr);
 
 		if (chan->cl) {
 			mbox_chan_txdone(chan, 0);
diff --git a/drivers/mailbox/bcm-flexrm-mailbox.c b/drivers/mailbox/bcm-flexrm-mailbox.c
index a2b8839d4e7c..e3e28a4f7d01 100644
--- a/drivers/mailbox/bcm-flexrm-mailbox.c
+++ b/drivers/mailbox/bcm-flexrm-mailbox.c
@@ -1650,7 +1650,7 @@ fail:
 	return ret;
 }
 
-static int flexrm_mbox_remove(struct platform_device *pdev)
+static void flexrm_mbox_remove(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct flexrm_mbox *mbox = platform_get_drvdata(pdev);
@@ -1661,8 +1661,6 @@ static int flexrm_mbox_remove(struct platform_device *pdev)
 
 	dma_pool_destroy(mbox->cmpl_pool);
 	dma_pool_destroy(mbox->bd_pool);
-
-	return 0;
 }
 
 static const struct of_device_id flexrm_mbox_of_match[] = {
@@ -1677,7 +1675,7 @@ static struct platform_driver flexrm_mbox_driver = {
 		.of_match_table = flexrm_mbox_of_match,
 	},
 	.probe		= flexrm_mbox_probe,
-	.remove		= flexrm_mbox_remove,
+	.remove_new	= flexrm_mbox_remove,
 };
 module_platform_driver(flexrm_mbox_driver);
 
diff --git a/drivers/mailbox/bcm-pdc-mailbox.c b/drivers/mailbox/bcm-pdc-mailbox.c
index 778faeced81e..1768d3d5aaa0 100644
--- a/drivers/mailbox/bcm-pdc-mailbox.c
+++ b/drivers/mailbox/bcm-pdc-mailbox.c
@@ -1605,7 +1605,7 @@ cleanup:
 	return err;
 }
 
-static int pdc_remove(struct platform_device *pdev)
+static void pdc_remove(struct platform_device *pdev)
 {
 	struct pdc_state *pdcs = platform_get_drvdata(pdev);
 
@@ -1617,12 +1617,11 @@ static int pdc_remove(struct platform_device *pdev)
 
 	dma_pool_destroy(pdcs->rx_buf_pool);
 	dma_pool_destroy(pdcs->ring_pool);
-	return 0;
 }
 
 static struct platform_driver pdc_mbox_driver = {
 	.probe = pdc_probe,
-	.remove = pdc_remove,
+	.remove_new = pdc_remove,
 	.driver = {
 		   .name = "brcm-iproc-pdc-mbox",
 		   .of_match_table = pdc_mbox_of_match,
diff --git a/drivers/mailbox/imx-mailbox.c b/drivers/mailbox/imx-mailbox.c
index 0af739ab571c..656171362fe9 100644
--- a/drivers/mailbox/imx-mailbox.c
+++ b/drivers/mailbox/imx-mailbox.c
@@ -903,13 +903,11 @@ disable_runtime_pm:
 	return ret;
 }
 
-static int imx_mu_remove(struct platform_device *pdev)
+static void imx_mu_remove(struct platform_device *pdev)
 {
 	struct imx_mu_priv *priv = platform_get_drvdata(pdev);
 
 	pm_runtime_disable(priv->dev);
-
-	return 0;
 }
 
 static const struct imx_mu_dcfg imx_mu_cfg_imx6sx = {
@@ -1070,7 +1068,7 @@ static const struct dev_pm_ops imx_mu_pm_ops = {
 
 static struct platform_driver imx_mu_driver = {
 	.probe		= imx_mu_probe,
-	.remove		= imx_mu_remove,
+	.remove_new	= imx_mu_remove,
 	.driver = {
 		.name	= "imx_mu",
 		.of_match_table = imx_mu_dt_ids,
diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c
index 22d6018ceec3..3386b4e72551 100644
--- a/drivers/mailbox/mailbox-test.c
+++ b/drivers/mailbox/mailbox-test.c
@@ -418,7 +418,7 @@ static int mbox_test_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int mbox_test_remove(struct platform_device *pdev)
+static void mbox_test_remove(struct platform_device *pdev)
 {
 	struct mbox_test_device *tdev = platform_get_drvdata(pdev);
 
@@ -428,8 +428,6 @@ static int mbox_test_remove(struct platform_device *pdev)
 		mbox_free_channel(tdev->tx_channel);
 	if (tdev->rx_channel)
 		mbox_free_channel(tdev->rx_channel);
-
-	return 0;
 }
 
 static const struct of_device_id mbox_test_match[] = {
@@ -444,7 +442,7 @@ static struct platform_driver mbox_test_driver = {
 		.of_match_table = mbox_test_match,
 	},
 	.probe  = mbox_test_probe,
-	.remove = mbox_test_remove,
+	.remove_new = mbox_test_remove,
 };
 module_platform_driver(mbox_test_driver);
 
diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c
index de862e9137d5..ead2200f39ba 100644
--- a/drivers/mailbox/mtk-cmdq-mailbox.c
+++ b/drivers/mailbox/mtk-cmdq-mailbox.c
@@ -367,7 +367,7 @@ static int cmdq_resume(struct device *dev)
 	return 0;
 }
 
-static int cmdq_remove(struct platform_device *pdev)
+static void cmdq_remove(struct platform_device *pdev)
 {
 	struct cmdq *cmdq = platform_get_drvdata(pdev);
 
@@ -378,7 +378,6 @@ static int cmdq_remove(struct platform_device *pdev)
 		cmdq_runtime_suspend(&pdev->dev);
 
 	clk_bulk_unprepare(cmdq->pdata->gce_num, cmdq->clocks);
-	return 0;
 }
 
 static int cmdq_mbox_send_data(struct mbox_chan *chan, void *data)
@@ -706,62 +705,70 @@ static const struct dev_pm_ops cmdq_pm_ops = {
 			   cmdq_runtime_resume, NULL)
 };
 
-static const struct gce_plat gce_plat_v2 = {
-	.thread_nr = 16,
-	.shift = 0,
+static const struct gce_plat gce_plat_mt6779 = {
+	.thread_nr = 24,
+	.shift = 3,
 	.control_by_sw = false,
 	.gce_num = 1
 };
 
-static const struct gce_plat gce_plat_v3 = {
-	.thread_nr = 24,
+static const struct gce_plat gce_plat_mt8173 = {
+	.thread_nr = 16,
 	.shift = 0,
 	.control_by_sw = false,
 	.gce_num = 1
 };
 
-static const struct gce_plat gce_plat_v4 = {
+static const struct gce_plat gce_plat_mt8183 = {
 	.thread_nr = 24,
-	.shift = 3,
+	.shift = 0,
 	.control_by_sw = false,
 	.gce_num = 1
 };
 
-static const struct gce_plat gce_plat_v5 = {
+static const struct gce_plat gce_plat_mt8186 = {
 	.thread_nr = 24,
 	.shift = 3,
 	.control_by_sw = true,
+	.sw_ddr_en = true,
 	.gce_num = 1
 };
 
-static const struct gce_plat gce_plat_v6 = {
-	.thread_nr = 24,
+static const struct gce_plat gce_plat_mt8188 = {
+	.thread_nr = 32,
 	.shift = 3,
 	.control_by_sw = true,
 	.gce_num = 2
 };
 
-static const struct gce_plat gce_plat_v7 = {
+static const struct gce_plat gce_plat_mt8192 = {
 	.thread_nr = 24,
 	.shift = 3,
 	.control_by_sw = true,
-	.sw_ddr_en = true,
 	.gce_num = 1
 };
 
+static const struct gce_plat gce_plat_mt8195 = {
+	.thread_nr = 24,
+	.shift = 3,
+	.control_by_sw = true,
+	.gce_num = 2
+};
+
 static const struct of_device_id cmdq_of_ids[] = {
-	{.compatible = "mediatek,mt8173-gce", .data = (void *)&gce_plat_v2},
-	{.compatible = "mediatek,mt8183-gce", .data = (void *)&gce_plat_v3},
-	{.compatible = "mediatek,mt8186-gce", .data = (void *)&gce_plat_v7},
-	{.compatible = "mediatek,mt6779-gce", .data = (void *)&gce_plat_v4},
-	{.compatible = "mediatek,mt8192-gce", .data = (void *)&gce_plat_v5},
-	{.compatible = "mediatek,mt8195-gce", .data = (void *)&gce_plat_v6},
+	{.compatible = "mediatek,mt6779-gce", .data = (void *)&gce_plat_mt6779},
+	{.compatible = "mediatek,mt8173-gce", .data = (void *)&gce_plat_mt8173},
+	{.compatible = "mediatek,mt8183-gce", .data = (void *)&gce_plat_mt8183},
+	{.compatible = "mediatek,mt8186-gce", .data = (void *)&gce_plat_mt8186},
+	{.compatible = "mediatek,mt8188-gce", .data = (void *)&gce_plat_mt8188},
+	{.compatible = "mediatek,mt8192-gce", .data = (void *)&gce_plat_mt8192},
+	{.compatible = "mediatek,mt8195-gce", .data = (void *)&gce_plat_mt8195},
 	{}
 };
 
 static struct platform_driver cmdq_drv = {
 	.probe = cmdq_probe,
-	.remove = cmdq_remove,
+	.remove_new = cmdq_remove,
 	.driver = {
 		.name = "mtk_cmdq",
 		.pm = &cmdq_pm_ops,
diff --git a/drivers/mailbox/omap-mailbox.c b/drivers/mailbox/omap-mailbox.c
index 792bcaebbc9b..c961706fe61d 100644
--- a/drivers/mailbox/omap-mailbox.c
+++ b/drivers/mailbox/omap-mailbox.c
@@ -865,19 +865,17 @@ unregister:
 	return ret;
 }
 
-static int omap_mbox_remove(struct platform_device *pdev)
+static void omap_mbox_remove(struct platform_device *pdev)
 {
 	struct omap_mbox_device *mdev = platform_get_drvdata(pdev);
 
 	pm_runtime_disable(mdev->dev);
 	omap_mbox_unregister(mdev);
-
-	return 0;
 }
 
 static struct platform_driver omap_mbox_driver = {
 	.probe	= omap_mbox_probe,
-	.remove	= omap_mbox_remove,
+	.remove_new = omap_mbox_remove,
 	.driver	= {
 		.name = "omap-mailbox",
 		.pm = &omap_mbox_pm_ops,
diff --git a/drivers/mailbox/qcom-apcs-ipc-mailbox.c b/drivers/mailbox/qcom-apcs-ipc-mailbox.c
index 002a135ee868..7d91e7c016ba 100644
--- a/drivers/mailbox/qcom-apcs-ipc-mailbox.c
+++ b/drivers/mailbox/qcom-apcs-ipc-mailbox.c
@@ -129,14 +129,12 @@ static int qcom_apcs_ipc_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int qcom_apcs_ipc_remove(struct platform_device *pdev)
+static void qcom_apcs_ipc_remove(struct platform_device *pdev)
 {
 	struct qcom_apcs_ipc *apcs = platform_get_drvdata(pdev);
 	struct platform_device *clk = apcs->clk;
 
 	platform_device_unregister(clk);
-
-	return 0;
 }
 
 /* .data is the offset of the ipc register within the global block */
@@ -145,19 +143,19 @@ static const struct of_device_id qcom_apcs_ipc_of_match[] = {
 	{ .compatible = "qcom,msm8916-apcs-kpss-global", .data = &msm8916_apcs_data },
 	{ .compatible = "qcom,msm8939-apcs-kpss-global", .data = &msm8916_apcs_data },
 	{ .compatible = "qcom,msm8953-apcs-kpss-global", .data = &msm8994_apcs_data },
-	{ .compatible = "qcom,msm8976-apcs-kpss-global", .data = &msm8994_apcs_data },
 	{ .compatible = "qcom,msm8994-apcs-kpss-global", .data = &msm8994_apcs_data },
 	{ .compatible = "qcom,msm8996-apcs-hmss-global", .data = &msm8996_apcs_data },
-	{ .compatible = "qcom,msm8998-apcs-hmss-global", .data = &msm8994_apcs_data },
 	{ .compatible = "qcom,qcm2290-apcs-hmss-global", .data = &msm8994_apcs_data },
+	{ .compatible = "qcom,sdm845-apss-shared", .data = &apps_shared_apcs_data },
+	{ .compatible = "qcom,sdx55-apcs-gcc", .data = &sdx55_apcs_data },
+	/* Do not add any more entries using existing driver data */
+	{ .compatible = "qcom,msm8976-apcs-kpss-global", .data = &msm8994_apcs_data },
+	{ .compatible = "qcom,msm8998-apcs-hmss-global", .data = &msm8994_apcs_data },
 	{ .compatible = "qcom,qcs404-apcs-apps-global", .data = &msm8916_apcs_data },
 	{ .compatible = "qcom,sdm660-apcs-hmss-global", .data = &msm8994_apcs_data },
-	{ .compatible = "qcom,sdm845-apss-shared", .data = &apps_shared_apcs_data },
 	{ .compatible = "qcom,sm4250-apcs-hmss-global", .data = &msm8994_apcs_data },
 	{ .compatible = "qcom,sm6125-apcs-hmss-global", .data = &msm8994_apcs_data },
 	{ .compatible = "qcom,sm6115-apcs-hmss-global", .data = &msm8994_apcs_data },
-	{ .compatible = "qcom,sdx55-apcs-gcc", .data = &sdx55_apcs_data },
-	/* Do not add any more entries using existing driver data */
 	{ .compatible = "qcom,ipq5332-apcs-apps-global", .data = &ipq6018_apcs_data },
 	{ .compatible = "qcom,ipq8074-apcs-apps-global", .data = &ipq6018_apcs_data },
 	{ .compatible = "qcom,sc7180-apss-shared", .data = &apps_shared_apcs_data },
@@ -169,7 +167,7 @@ MODULE_DEVICE_TABLE(of, qcom_apcs_ipc_of_match);
 
 static struct platform_driver qcom_apcs_ipc_driver = {
 	.probe = qcom_apcs_ipc_probe,
-	.remove = qcom_apcs_ipc_remove,
+	.remove_new = qcom_apcs_ipc_remove,
 	.driver = {
 		.name = "qcom_apcs_ipc",
 		.of_match_table = qcom_apcs_ipc_of_match,
diff --git a/drivers/mailbox/qcom-ipcc.c b/drivers/mailbox/qcom-ipcc.c
index f597a1bd5684..d537cc9c4d4b 100644
--- a/drivers/mailbox/qcom-ipcc.c
+++ b/drivers/mailbox/qcom-ipcc.c
@@ -326,14 +326,12 @@ err_mbox:
 	return ret;
 }
 
-static int qcom_ipcc_remove(struct platform_device *pdev)
+static void qcom_ipcc_remove(struct platform_device *pdev)
 {
 	struct qcom_ipcc *ipcc = platform_get_drvdata(pdev);
 
 	disable_irq_wake(ipcc->irq);
 	irq_domain_remove(ipcc->irq_domain);
-
-	return 0;
 }
 
 static const struct of_device_id qcom_ipcc_of_match[] = {
@@ -348,7 +346,7 @@ static const struct dev_pm_ops qcom_ipcc_dev_pm_ops = {
 
 static struct platform_driver qcom_ipcc_driver = {
 	.probe = qcom_ipcc_probe,
-	.remove = qcom_ipcc_remove,
+	.remove_new = qcom_ipcc_remove,
 	.driver = {
 		.name = "qcom-ipcc",
 		.of_match_table = qcom_ipcc_of_match,
diff --git a/drivers/mailbox/stm32-ipcc.c b/drivers/mailbox/stm32-ipcc.c
index 4ad3653f3866..1442f275782b 100644
--- a/drivers/mailbox/stm32-ipcc.c
+++ b/drivers/mailbox/stm32-ipcc.c
@@ -331,7 +331,7 @@ err_clk:
 	return ret;
 }
 
-static int stm32_ipcc_remove(struct platform_device *pdev)
+static void stm32_ipcc_remove(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 
@@ -339,8 +339,6 @@ static int stm32_ipcc_remove(struct platform_device *pdev)
 		dev_pm_clear_wake_irq(&pdev->dev);
 
 	device_set_wakeup_capable(dev, false);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -381,7 +379,7 @@ static struct platform_driver stm32_ipcc_driver = {
 		.of_match_table = stm32_ipcc_of_match,
 	},
 	.probe		= stm32_ipcc_probe,
-	.remove		= stm32_ipcc_remove,
+	.remove_new	= stm32_ipcc_remove,
 };
 
 module_platform_driver(stm32_ipcc_driver);
diff --git a/drivers/mailbox/sun6i-msgbox.c b/drivers/mailbox/sun6i-msgbox.c
index 7f8d931042d3..3dcc54dc83b2 100644
--- a/drivers/mailbox/sun6i-msgbox.c
+++ b/drivers/mailbox/sun6i-msgbox.c
@@ -287,15 +287,13 @@ err_disable_unprepare:
 	return ret;
 }
 
-static int sun6i_msgbox_remove(struct platform_device *pdev)
+static void sun6i_msgbox_remove(struct platform_device *pdev)
 {
 	struct sun6i_msgbox *mbox = platform_get_drvdata(pdev);
 
 	mbox_controller_unregister(&mbox->controller);
 	/* See the comment in sun6i_msgbox_probe about the reset line. */
 	clk_disable_unprepare(mbox->clk);
-
-	return 0;
 }
 
 static const struct of_device_id sun6i_msgbox_of_match[] = {
@@ -310,7 +308,7 @@ static struct platform_driver sun6i_msgbox_driver = {
 		.of_match_table = sun6i_msgbox_of_match,
 	},
 	.probe  = sun6i_msgbox_probe,
-	.remove = sun6i_msgbox_remove,
+	.remove_new = sun6i_msgbox_remove,
 };
 module_platform_driver(sun6i_msgbox_driver);
 
diff --git a/drivers/mailbox/tegra-hsp.c b/drivers/mailbox/tegra-hsp.c
index fe29fc2ca526..19ef56cbcfd3 100644
--- a/drivers/mailbox/tegra-hsp.c
+++ b/drivers/mailbox/tegra-hsp.c
@@ -868,13 +868,11 @@ static int tegra_hsp_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int tegra_hsp_remove(struct platform_device *pdev)
+static void tegra_hsp_remove(struct platform_device *pdev)
 {
 	struct tegra_hsp *hsp = platform_get_drvdata(pdev);
 
 	lockdep_unregister_key(&hsp->lock_key);
-
-	return 0;
 }
 
 static int __maybe_unused tegra_hsp_resume(struct device *dev)
@@ -953,7 +951,7 @@ static struct platform_driver tegra_hsp_driver = {
 		.pm = &tegra_hsp_pm_ops,
 	},
 	.probe = tegra_hsp_probe,
-	.remove = tegra_hsp_remove,
+	.remove_new = tegra_hsp_remove,
 };
 
 static int __init tegra_hsp_init(void)
diff --git a/drivers/mailbox/zynqmp-ipi-mailbox.c b/drivers/mailbox/zynqmp-ipi-mailbox.c
index 7fa533e80dd9..25c65afc030a 100644
--- a/drivers/mailbox/zynqmp-ipi-mailbox.c
+++ b/drivers/mailbox/zynqmp-ipi-mailbox.c
@@ -81,7 +81,6 @@ struct zynqmp_ipi_mchan {
  * @remote_id:            remote IPI agent ID
  * @mbox:                 mailbox Controller
  * @mchans:               array for channels, tx channel and rx channel.
- * @irq:                  IPI agent interrupt ID
  */
 struct zynqmp_ipi_mbox {
 	struct zynqmp_ipi_pdata *pdata;
@@ -688,19 +687,17 @@ free_mbox_dev:
 	return ret;
 }
 
-static int zynqmp_ipi_remove(struct platform_device *pdev)
+static void zynqmp_ipi_remove(struct platform_device *pdev)
 {
 	struct zynqmp_ipi_pdata *pdata;
 
 	pdata = platform_get_drvdata(pdev);
 	zynqmp_ipi_free_mboxes(pdata);
-
-	return 0;
 }
 
 static struct platform_driver zynqmp_ipi_driver = {
 	.probe = zynqmp_ipi_probe,
-	.remove = zynqmp_ipi_remove,
+	.remove_new = zynqmp_ipi_remove,
 	.driver = {
 		   .name = "zynqmp-ipi",
 		   .of_match_table = of_match_ptr(zynqmp_ipi_of_match),
diff --git a/drivers/mcb/mcb-core.c b/drivers/mcb/mcb-core.c
index ba4530459de8..61994da7bad0 100644
--- a/drivers/mcb/mcb-core.c
+++ b/drivers/mcb/mcb-core.c
@@ -263,6 +263,7 @@ static void mcb_free_bus(struct device *dev)
 
 /**
  * mcb_alloc_bus() - Allocate a new @mcb_bus
+ * @carrier: generic &struct device for the carrier device
  *
  * Allocate a new @mcb_bus.
  */
@@ -327,7 +328,7 @@ void mcb_release_bus(struct mcb_bus *bus)
 EXPORT_SYMBOL_NS_GPL(mcb_release_bus, MCB);
 
 /**
- * mcb_bus_put() - Increment refcnt
+ * mcb_bus_get() - Increment refcnt
  * @bus: The @mcb_bus
  *
  * Get a @mcb_bus' ref
@@ -455,7 +456,7 @@ EXPORT_SYMBOL_NS_GPL(mcb_request_mem, MCB);
 
 /**
  * mcb_release_mem() - Release memory requested by device
- * @dev: The @mcb_device that requested the memory
+ * @mem: The memory resource to be released
  *
  * Release memory that was prior requested via @mcb_request_mem().
  */
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 6ae2329052c9..4e6afa89921f 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -300,7 +300,7 @@ struct cached_dev {
 	struct list_head	list;
 	struct bcache_device	disk;
 	struct block_device	*bdev;
-	struct bdev_handle	*bdev_handle;
+	struct file		*bdev_file;
 
 	struct cache_sb		sb;
 	struct cache_sb_disk	*sb_disk;
@@ -423,7 +423,7 @@ struct cache {
 
 	struct kobject		kobj;
 	struct block_device	*bdev;
-	struct bdev_handle	*bdev_handle;
+	struct file		*bdev_file;
 
 	struct task_struct	*alloc_thread;
 
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index dc3f50f69714..330bcd9ea4a9 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -900,9 +900,23 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 	struct request_queue *q;
 	const size_t max_stripes = min_t(size_t, INT_MAX,
 					 SIZE_MAX / sizeof(atomic_t));
+	struct queue_limits lim = {
+		.max_hw_sectors		= UINT_MAX,
+		.max_sectors		= UINT_MAX,
+		.max_segment_size	= UINT_MAX,
+		.max_segments		= BIO_MAX_VECS,
+		.max_hw_discard_sectors	= UINT_MAX,
+		.io_min			= block_size,
+		.logical_block_size	= block_size,
+		.physical_block_size	= block_size,
+	};
 	uint64_t n;
 	int idx;
 
+	if (cached_bdev) {
+		d->stripe_size = bdev_io_opt(cached_bdev) >> SECTOR_SHIFT;
+		lim.io_opt = umax(block_size, bdev_io_opt(cached_bdev));
+	}
 	if (!d->stripe_size)
 		d->stripe_size = 1 << 31;
 	else if (d->stripe_size < BCH_MIN_STRIPE_SZ)
@@ -935,8 +949,21 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 			BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER))
 		goto out_ida_remove;
 
-	d->disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!d->disk)
+	if (lim.logical_block_size > PAGE_SIZE && cached_bdev) {
+		/*
+		 * This should only happen with BCACHE_SB_VERSION_BDEV.
+		 * Block/page size is checked for BCACHE_SB_VERSION_CDEV.
+		 */
+		pr_info("bcache%i: sb/logical block size (%u) greater than page size (%lu) falling back to device logical block size (%u)\n",
+			idx, lim.logical_block_size,
+			PAGE_SIZE, bdev_logical_block_size(cached_bdev));
+
+		/* This also adjusts physical block size/min io size if needed */
+		lim.logical_block_size = bdev_logical_block_size(cached_bdev);
+	}
+
+	d->disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(d->disk))
 		goto out_bioset_exit;
 
 	set_capacity(d->disk, sectors);
@@ -949,27 +976,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 	d->disk->private_data	= d;
 
 	q = d->disk->queue;
-	q->limits.max_hw_sectors	= UINT_MAX;
-	q->limits.max_sectors		= UINT_MAX;
-	q->limits.max_segment_size	= UINT_MAX;
-	q->limits.max_segments		= BIO_MAX_VECS;
-	blk_queue_max_discard_sectors(q, UINT_MAX);
-	q->limits.io_min		= block_size;
-	q->limits.logical_block_size	= block_size;
-	q->limits.physical_block_size	= block_size;
-
-	if (q->limits.logical_block_size > PAGE_SIZE && cached_bdev) {
-		/*
-		 * This should only happen with BCACHE_SB_VERSION_BDEV.
-		 * Block/page size is checked for BCACHE_SB_VERSION_CDEV.
-		 */
-		pr_info("%s: sb/logical block size (%u) greater than page size (%lu) falling back to device logical block size (%u)\n",
-			d->disk->disk_name, q->limits.logical_block_size,
-			PAGE_SIZE, bdev_logical_block_size(cached_bdev));
-
-		/* This also adjusts physical block size/min io size if needed */
-		blk_queue_logical_block_size(q, bdev_logical_block_size(cached_bdev));
-	}
 
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, d->disk->queue);
 
@@ -1369,8 +1375,8 @@ static CLOSURE_CALLBACK(cached_dev_free)
 	if (dc->sb_disk)
 		put_page(virt_to_page(dc->sb_disk));
 
-	if (dc->bdev_handle)
-		bdev_release(dc->bdev_handle);
+	if (dc->bdev_file)
+		fput(dc->bdev_file);
 
 	wake_up(&unregister_wait);
 
@@ -1416,9 +1422,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 		hlist_add_head(&io->hash, dc->io_hash + RECENT_IO);
 	}
 
-	dc->disk.stripe_size = q->limits.io_opt >> 9;
-
-	if (dc->disk.stripe_size)
+	if (bdev_io_opt(dc->bdev))
 		dc->partial_stripes_expensive =
 			q->limits.raid_partial_stripes_expensive;
 
@@ -1428,9 +1432,6 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 	if (ret)
 		return ret;
 
-	blk_queue_io_opt(dc->disk.disk->queue,
-		max(queue_io_opt(dc->disk.disk->queue), queue_io_opt(q)));
-
 	atomic_set(&dc->io_errors, 0);
 	dc->io_disable = false;
 	dc->error_limit = DEFAULT_CACHED_DEV_ERROR_LIMIT;
@@ -1445,7 +1446,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 /* Cached device - bcache superblock */
 
 static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
-				 struct bdev_handle *bdev_handle,
+				 struct file *bdev_file,
 				 struct cached_dev *dc)
 {
 	const char *err = "cannot allocate memory";
@@ -1453,8 +1454,8 @@ static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
 	int ret = -ENOMEM;
 
 	memcpy(&dc->sb, sb, sizeof(struct cache_sb));
-	dc->bdev_handle = bdev_handle;
-	dc->bdev = bdev_handle->bdev;
+	dc->bdev_file = bdev_file;
+	dc->bdev = file_bdev(bdev_file);
 	dc->sb_disk = sb_disk;
 
 	if (cached_dev_init(dc, sb->block_size << 9))
@@ -2218,8 +2219,8 @@ void bch_cache_release(struct kobject *kobj)
 	if (ca->sb_disk)
 		put_page(virt_to_page(ca->sb_disk));
 
-	if (ca->bdev_handle)
-		bdev_release(ca->bdev_handle);
+	if (ca->bdev_file)
+		fput(ca->bdev_file);
 
 	kfree(ca);
 	module_put(THIS_MODULE);
@@ -2339,18 +2340,18 @@ err_free:
 }
 
 static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
-				struct bdev_handle *bdev_handle,
+				struct file *bdev_file,
 				struct cache *ca)
 {
 	const char *err = NULL; /* must be set for any error case */
 	int ret = 0;
 
 	memcpy(&ca->sb, sb, sizeof(struct cache_sb));
-	ca->bdev_handle = bdev_handle;
-	ca->bdev = bdev_handle->bdev;
+	ca->bdev_file = bdev_file;
+	ca->bdev = file_bdev(bdev_file);
 	ca->sb_disk = sb_disk;
 
-	if (bdev_max_discard_sectors((bdev_handle->bdev)))
+	if (bdev_max_discard_sectors(file_bdev(bdev_file)))
 		ca->discard = CACHE_DISCARD(&ca->sb);
 
 	ret = cache_alloc(ca);
@@ -2361,20 +2362,20 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
 			err = "cache_alloc(): cache device is too small";
 		else
 			err = "cache_alloc(): unknown error";
-		pr_notice("error %pg: %s\n", bdev_handle->bdev, err);
+		pr_notice("error %pg: %s\n", file_bdev(bdev_file), err);
 		/*
 		 * If we failed here, it means ca->kobj is not initialized yet,
 		 * kobject_put() won't be called and there is no chance to
-		 * call bdev_release() to bdev in bch_cache_release(). So
-		 * we explicitly call bdev_release() here.
+		 * call fput() to bdev in bch_cache_release(). So
+		 * we explicitly call fput() on the block device here.
 		 */
-		bdev_release(bdev_handle);
+		fput(bdev_file);
 		return ret;
 	}
 
-	if (kobject_add(&ca->kobj, bdev_kobj(bdev_handle->bdev), "bcache")) {
+	if (kobject_add(&ca->kobj, bdev_kobj(file_bdev(bdev_file)), "bcache")) {
 		pr_notice("error %pg: error calling kobject_add\n",
-			  bdev_handle->bdev);
+			  file_bdev(bdev_file));
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -2388,7 +2389,7 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
 		goto out;
 	}
 
-	pr_info("registered cache device %pg\n", ca->bdev_handle->bdev);
+	pr_info("registered cache device %pg\n", file_bdev(ca->bdev_file));
 
 out:
 	kobject_put(&ca->kobj);
@@ -2446,7 +2447,7 @@ struct async_reg_args {
 	char *path;
 	struct cache_sb *sb;
 	struct cache_sb_disk *sb_disk;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	void *holder;
 };
 
@@ -2457,7 +2458,7 @@ static void register_bdev_worker(struct work_struct *work)
 		container_of(work, struct async_reg_args, reg_work.work);
 
 	mutex_lock(&bch_register_lock);
-	if (register_bdev(args->sb, args->sb_disk, args->bdev_handle,
+	if (register_bdev(args->sb, args->sb_disk, args->bdev_file,
 			  args->holder) < 0)
 		fail = true;
 	mutex_unlock(&bch_register_lock);
@@ -2478,7 +2479,7 @@ static void register_cache_worker(struct work_struct *work)
 		container_of(work, struct async_reg_args, reg_work.work);
 
 	/* blkdev_put() will be called in bch_cache_release() */
-	if (register_cache(args->sb, args->sb_disk, args->bdev_handle,
+	if (register_cache(args->sb, args->sb_disk, args->bdev_file,
 			   args->holder))
 		fail = true;
 
@@ -2516,7 +2517,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 	char *path = NULL;
 	struct cache_sb *sb;
 	struct cache_sb_disk *sb_disk;
-	struct bdev_handle *bdev_handle, *bdev_handle2;
+	struct file *bdev_file, *bdev_file2;
 	void *holder = NULL;
 	ssize_t ret;
 	bool async_registration = false;
@@ -2549,15 +2550,15 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 
 	ret = -EINVAL;
 	err = "failed to open device";
-	bdev_handle = bdev_open_by_path(strim(path), BLK_OPEN_READ, NULL, NULL);
-	if (IS_ERR(bdev_handle))
+	bdev_file = bdev_file_open_by_path(strim(path), BLK_OPEN_READ, NULL, NULL);
+	if (IS_ERR(bdev_file))
 		goto out_free_sb;
 
 	err = "failed to set blocksize";
-	if (set_blocksize(bdev_handle->bdev, 4096))
+	if (set_blocksize(file_bdev(bdev_file), 4096))
 		goto out_blkdev_put;
 
-	err = read_super(sb, bdev_handle->bdev, &sb_disk);
+	err = read_super(sb, file_bdev(bdev_file), &sb_disk);
 	if (err)
 		goto out_blkdev_put;
 
@@ -2569,13 +2570,13 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 	}
 
 	/* Now reopen in exclusive mode with proper holder */
-	bdev_handle2 = bdev_open_by_dev(bdev_handle->bdev->bd_dev,
+	bdev_file2 = bdev_file_open_by_dev(file_bdev(bdev_file)->bd_dev,
 			BLK_OPEN_READ | BLK_OPEN_WRITE, holder, NULL);
-	bdev_release(bdev_handle);
-	bdev_handle = bdev_handle2;
-	if (IS_ERR(bdev_handle)) {
-		ret = PTR_ERR(bdev_handle);
-		bdev_handle = NULL;
+	fput(bdev_file);
+	bdev_file = bdev_file2;
+	if (IS_ERR(bdev_file)) {
+		ret = PTR_ERR(bdev_file);
+		bdev_file = NULL;
 		if (ret == -EBUSY) {
 			dev_t dev;
 
@@ -2610,7 +2611,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 		args->path	= path;
 		args->sb	= sb;
 		args->sb_disk	= sb_disk;
-		args->bdev_handle	= bdev_handle;
+		args->bdev_file	= bdev_file;
 		args->holder	= holder;
 		register_device_async(args);
 		/* No wait and returns to user space */
@@ -2619,14 +2620,14 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 
 	if (SB_IS_BDEV(sb)) {
 		mutex_lock(&bch_register_lock);
-		ret = register_bdev(sb, sb_disk, bdev_handle, holder);
+		ret = register_bdev(sb, sb_disk, bdev_file, holder);
 		mutex_unlock(&bch_register_lock);
 		/* blkdev_put() will be called in cached_dev_free() */
 		if (ret < 0)
 			goto out_free_sb;
 	} else {
 		/* blkdev_put() will be called in bch_cache_release() */
-		ret = register_cache(sb, sb_disk, bdev_handle, holder);
+		ret = register_cache(sb, sb_disk, bdev_file, holder);
 		if (ret)
 			goto out_free_sb;
 	}
@@ -2642,8 +2643,8 @@ out_free_holder:
 out_put_sb_page:
 	put_page(virt_to_page(sb_disk));
 out_blkdev_put:
-	if (bdev_handle)
-		bdev_release(bdev_handle);
+	if (bdev_file)
+		fput(bdev_file);
 out_free_sb:
 	kfree(sb);
 out_free_path:
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 095b9b49aa82..e6757a30dcca 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -22,6 +22,8 @@
 #include "dm-ima.h"
 
 #define DM_RESERVED_MAX_IOS		1024
+#define DM_MAX_TARGETS			1048576
+#define DM_MAX_TARGET_PARAMS		1024
 
 struct dm_io;
 
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 855b482cbff1..59445763e55a 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -53,15 +53,17 @@
 struct convert_context {
 	struct completion restart;
 	struct bio *bio_in;
-	struct bio *bio_out;
 	struct bvec_iter iter_in;
+	struct bio *bio_out;
 	struct bvec_iter iter_out;
-	u64 cc_sector;
 	atomic_t cc_pending;
+	u64 cc_sector;
 	union {
 		struct skcipher_request *req;
 		struct aead_request *req_aead;
 	} r;
+	bool aead_recheck;
+	bool aead_failed;
 
 };
 
@@ -73,10 +75,8 @@ struct dm_crypt_io {
 	struct bio *base_bio;
 	u8 *integrity_metadata;
 	bool integrity_metadata_from_pool:1;
-	bool in_tasklet:1;
 
 	struct work_struct work;
-	struct tasklet_struct tasklet;
 
 	struct convert_context ctx;
 
@@ -84,6 +84,8 @@ struct dm_crypt_io {
 	blk_status_t error;
 	sector_t sector;
 
+	struct bvec_iter saved_bi_iter;
+
 	struct rb_node rb_node;
 } CRYPTO_MINALIGN_ATTR;
 
@@ -1372,10 +1374,13 @@ static int crypt_convert_block_aead(struct crypt_config *cc,
 	if (r == -EBADMSG) {
 		sector_t s = le64_to_cpu(*sector);
 
-		DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu",
-			    ctx->bio_in->bi_bdev, s);
-		dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead",
-				 ctx->bio_in, s, 0);
+		ctx->aead_failed = true;
+		if (ctx->aead_recheck) {
+			DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu",
+				    ctx->bio_in->bi_bdev, s);
+			dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead",
+					 ctx->bio_in, s, 0);
+		}
 	}
 
 	if (!r && cc->iv_gen_ops && cc->iv_gen_ops->post)
@@ -1759,10 +1764,11 @@ static void crypt_io_init(struct dm_crypt_io *io, struct crypt_config *cc,
 	io->base_bio = bio;
 	io->sector = sector;
 	io->error = 0;
+	io->ctx.aead_recheck = false;
+	io->ctx.aead_failed = false;
 	io->ctx.r.req = NULL;
 	io->integrity_metadata = NULL;
 	io->integrity_metadata_from_pool = false;
-	io->in_tasklet = false;
 	atomic_set(&io->io_pending, 0);
 }
 
@@ -1771,12 +1777,7 @@ static void crypt_inc_pending(struct dm_crypt_io *io)
 	atomic_inc(&io->io_pending);
 }
 
-static void kcryptd_io_bio_endio(struct work_struct *work)
-{
-	struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
-
-	bio_endio(io->base_bio);
-}
+static void kcryptd_queue_read(struct dm_crypt_io *io);
 
 /*
  * One of the bios was finished. Check for completion of
@@ -1791,6 +1792,15 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
 	if (!atomic_dec_and_test(&io->io_pending))
 		return;
 
+	if (likely(!io->ctx.aead_recheck) && unlikely(io->ctx.aead_failed) &&
+	    cc->on_disk_tag_size && bio_data_dir(base_bio) == READ) {
+		io->ctx.aead_recheck = true;
+		io->ctx.aead_failed = false;
+		io->error = 0;
+		kcryptd_queue_read(io);
+		return;
+	}
+
 	if (io->ctx.r.req)
 		crypt_free_req(cc, io->ctx.r.req, base_bio);
 
@@ -1801,20 +1811,6 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
 
 	base_bio->bi_status = error;
 
-	/*
-	 * If we are running this function from our tasklet,
-	 * we can't call bio_endio() here, because it will call
-	 * clone_endio() from dm.c, which in turn will
-	 * free the current struct dm_crypt_io structure with
-	 * our tasklet. In this case we need to delay bio_endio()
-	 * execution to after the tasklet is done and dequeued.
-	 */
-	if (io->in_tasklet) {
-		INIT_WORK(&io->work, kcryptd_io_bio_endio);
-		queue_work(cc->io_queue, &io->work);
-		return;
-	}
-
 	bio_endio(base_bio);
 }
 
@@ -1840,15 +1836,19 @@ static void crypt_endio(struct bio *clone)
 	struct dm_crypt_io *io = clone->bi_private;
 	struct crypt_config *cc = io->cc;
 	unsigned int rw = bio_data_dir(clone);
-	blk_status_t error;
+	blk_status_t error = clone->bi_status;
+
+	if (io->ctx.aead_recheck && !error) {
+		kcryptd_queue_crypt(io);
+		return;
+	}
 
 	/*
 	 * free the processed pages
 	 */
-	if (rw == WRITE)
+	if (rw == WRITE || io->ctx.aead_recheck)
 		crypt_free_buffer_pages(cc, clone);
 
-	error = clone->bi_status;
 	bio_put(clone);
 
 	if (rw == READ && !error) {
@@ -1869,6 +1869,22 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
 	struct crypt_config *cc = io->cc;
 	struct bio *clone;
 
+	if (io->ctx.aead_recheck) {
+		if (!(gfp & __GFP_DIRECT_RECLAIM))
+			return 1;
+		crypt_inc_pending(io);
+		clone = crypt_alloc_buffer(io, io->base_bio->bi_iter.bi_size);
+		if (unlikely(!clone)) {
+			crypt_dec_pending(io);
+			return 1;
+		}
+		clone->bi_iter.bi_sector = cc->start + io->sector;
+		crypt_convert_init(cc, &io->ctx, clone, clone, io->sector);
+		io->saved_bi_iter = clone->bi_iter;
+		dm_submit_bio_remap(io->base_bio, clone);
+		return 0;
+	}
+
 	/*
 	 * We need the original biovec array in order to decrypt the whole bio
 	 * data *afterwards* -- thanks to immutable biovecs we don't need to
@@ -2095,6 +2111,12 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 	io->ctx.bio_out = clone;
 	io->ctx.iter_out = clone->bi_iter;
 
+	if (crypt_integrity_aead(cc)) {
+		bio_copy_data(clone, io->base_bio);
+		io->ctx.bio_in = clone;
+		io->ctx.iter_in = clone->bi_iter;
+	}
+
 	sector += bio_sectors(clone);
 
 	crypt_inc_pending(io);
@@ -2131,6 +2153,14 @@ dec:
 
 static void kcryptd_crypt_read_done(struct dm_crypt_io *io)
 {
+	if (io->ctx.aead_recheck) {
+		if (!io->error) {
+			io->ctx.bio_in->bi_iter = io->saved_bi_iter;
+			bio_copy_data(io->base_bio, io->ctx.bio_in);
+		}
+		crypt_free_buffer_pages(io->cc, io->ctx.bio_in);
+		bio_put(io->ctx.bio_in);
+	}
 	crypt_dec_pending(io);
 }
 
@@ -2160,11 +2190,17 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io)
 
 	crypt_inc_pending(io);
 
-	crypt_convert_init(cc, &io->ctx, io->base_bio, io->base_bio,
-			   io->sector);
+	if (io->ctx.aead_recheck) {
+		io->ctx.cc_sector = io->sector + cc->iv_offset;
+		r = crypt_convert(cc, &io->ctx,
+				  test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true);
+	} else {
+		crypt_convert_init(cc, &io->ctx, io->base_bio, io->base_bio,
+				   io->sector);
 
-	r = crypt_convert(cc, &io->ctx,
-			  test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true);
+		r = crypt_convert(cc, &io->ctx,
+				  test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true);
+	}
 	/*
 	 * Crypto API backlogged the request, because its queue was full
 	 * and we're in softirq context, so continue from a workqueue
@@ -2206,10 +2242,13 @@ static void kcryptd_async_done(void *data, int error)
 	if (error == -EBADMSG) {
 		sector_t s = le64_to_cpu(*org_sector_of_dmreq(cc, dmreq));
 
-		DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu",
-			    ctx->bio_in->bi_bdev, s);
-		dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead",
-				 ctx->bio_in, s, 0);
+		ctx->aead_failed = true;
+		if (ctx->aead_recheck) {
+			DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu",
+				    ctx->bio_in->bi_bdev, s);
+			dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead",
+					 ctx->bio_in, s, 0);
+		}
 		io->error = BLK_STS_PROTECTION;
 	} else if (error < 0)
 		io->error = BLK_STS_IOERR;
@@ -2246,11 +2285,6 @@ static void kcryptd_crypt(struct work_struct *work)
 		kcryptd_crypt_write_convert(io);
 }
 
-static void kcryptd_crypt_tasklet(unsigned long work)
-{
-	kcryptd_crypt((struct work_struct *)work);
-}
-
 static void kcryptd_queue_crypt(struct dm_crypt_io *io)
 {
 	struct crypt_config *cc = io->cc;
@@ -2262,15 +2296,10 @@ static void kcryptd_queue_crypt(struct dm_crypt_io *io)
 		 * irqs_disabled(): the kernel may run some IO completion from the idle thread, but
 		 * it is being executed with irqs disabled.
 		 */
-		if (in_hardirq() || irqs_disabled()) {
-			io->in_tasklet = true;
-			tasklet_init(&io->tasklet, kcryptd_crypt_tasklet, (unsigned long)&io->work);
-			tasklet_schedule(&io->tasklet);
+		if (!(in_hardirq() || irqs_disabled())) {
+			kcryptd_crypt(&io->work);
 			return;
 		}
-
-		kcryptd_crypt(&io->work);
-		return;
 	}
 
 	INIT_WORK(&io->work, kcryptd_crypt);
@@ -3144,7 +3173,7 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar
 			sval = strchr(opt_string + strlen("integrity:"), ':') + 1;
 			if (!strcasecmp(sval, "aead")) {
 				set_bit(CRYPT_MODE_INTEGRITY_AEAD, &cc->cipher_flags);
-			} else  if (strcasecmp(sval, "none")) {
+			} else if (strcasecmp(sval, "none")) {
 				ti->error = "Unknown integrity profile";
 				return -EINVAL;
 			}
@@ -3673,7 +3702,7 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type crypt_target = {
 	.name   = "crypt",
-	.version = {1, 24, 0},
+	.version = {1, 25, 0},
 	.module = THIS_MODULE,
 	.ctr    = crypt_ctr,
 	.dtr    = crypt_dtr,
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index c5f03aab4552..1fc901df84eb 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -278,6 +278,8 @@ struct dm_integrity_c {
 
 	atomic64_t number_of_mismatches;
 
+	mempool_t recheck_pool;
+
 	struct notifier_block reboot_notifier;
 };
 
@@ -1689,6 +1691,77 @@ failed:
 	get_random_bytes(result, ic->tag_size);
 }
 
+static noinline void integrity_recheck(struct dm_integrity_io *dio, char *checksum)
+{
+	struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io));
+	struct dm_integrity_c *ic = dio->ic;
+	struct bvec_iter iter;
+	struct bio_vec bv;
+	sector_t sector, logical_sector, area, offset;
+	struct page *page;
+	void *buffer;
+
+	get_area_and_offset(ic, dio->range.logical_sector, &area, &offset);
+	dio->metadata_block = get_metadata_sector_and_offset(ic, area, offset,
+							     &dio->metadata_offset);
+	sector = get_data_sector(ic, area, offset);
+	logical_sector = dio->range.logical_sector;
+
+	page = mempool_alloc(&ic->recheck_pool, GFP_NOIO);
+	buffer = page_to_virt(page);
+
+	__bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) {
+		unsigned pos = 0;
+
+		do {
+			char *mem;
+			int r;
+			struct dm_io_request io_req;
+			struct dm_io_region io_loc;
+			io_req.bi_opf = REQ_OP_READ;
+			io_req.mem.type = DM_IO_KMEM;
+			io_req.mem.ptr.addr = buffer;
+			io_req.notify.fn = NULL;
+			io_req.client = ic->io;
+			io_loc.bdev = ic->dev->bdev;
+			io_loc.sector = sector;
+			io_loc.count = ic->sectors_per_block;
+
+			r = dm_io(&io_req, 1, &io_loc, NULL);
+			if (unlikely(r)) {
+				dio->bi_status = errno_to_blk_status(r);
+				goto free_ret;
+			}
+
+			integrity_sector_checksum(ic, logical_sector, buffer, checksum);
+			r = dm_integrity_rw_tag(ic, checksum, &dio->metadata_block,
+						&dio->metadata_offset, ic->tag_size, TAG_CMP);
+			if (r) {
+				if (r > 0) {
+					DMERR_LIMIT("%pg: Checksum failed at sector 0x%llx",
+						    bio->bi_bdev, logical_sector);
+					atomic64_inc(&ic->number_of_mismatches);
+					dm_audit_log_bio(DM_MSG_PREFIX, "integrity-checksum",
+							 bio, logical_sector, 0);
+					r = -EILSEQ;
+				}
+				dio->bi_status = errno_to_blk_status(r);
+				goto free_ret;
+			}
+
+			mem = bvec_kmap_local(&bv);
+			memcpy(mem + pos, buffer, ic->sectors_per_block << SECTOR_SHIFT);
+			kunmap_local(mem);
+
+			pos += ic->sectors_per_block << SECTOR_SHIFT;
+			sector += ic->sectors_per_block;
+			logical_sector += ic->sectors_per_block;
+		} while (pos < bv.bv_len);
+	}
+free_ret:
+	mempool_free(page, &ic->recheck_pool);
+}
+
 static void integrity_metadata(struct work_struct *w)
 {
 	struct dm_integrity_io *dio = container_of(w, struct dm_integrity_io, work);
@@ -1776,15 +1849,8 @@ again:
 						checksums_ptr - checksums, dio->op == REQ_OP_READ ? TAG_CMP : TAG_WRITE);
 			if (unlikely(r)) {
 				if (r > 0) {
-					sector_t s;
-
-					s = sector - ((r + ic->tag_size - 1) / ic->tag_size);
-					DMERR_LIMIT("%pg: Checksum failed at sector 0x%llx",
-						    bio->bi_bdev, s);
-					r = -EILSEQ;
-					atomic64_inc(&ic->number_of_mismatches);
-					dm_audit_log_bio(DM_MSG_PREFIX, "integrity-checksum",
-							 bio, s, 0);
+					integrity_recheck(dio, checksums);
+					goto skip_io;
 				}
 				if (likely(checksums != checksums_onstack))
 					kfree(checksums);
@@ -4261,6 +4327,12 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv
 		goto bad;
 	}
 
+	r = mempool_init_page_pool(&ic->recheck_pool, 1, 0);
+	if (r) {
+		ti->error = "Cannot allocate mempool";
+		goto bad;
+	}
+
 	ic->metadata_wq = alloc_workqueue("dm-integrity-metadata",
 					  WQ_MEM_RECLAIM, METADATA_WORKQUEUE_MAX_ACTIVE);
 	if (!ic->metadata_wq) {
@@ -4609,6 +4681,7 @@ static void dm_integrity_dtr(struct dm_target *ti)
 	kvfree(ic->bbs);
 	if (ic->bufio)
 		dm_bufio_client_destroy(ic->bufio);
+	mempool_exit(&ic->recheck_pool);
 	mempool_exit(&ic->journal_io_mempool);
 	if (ic->io)
 		dm_io_client_destroy(ic->io);
@@ -4661,7 +4734,7 @@ static void dm_integrity_dtr(struct dm_target *ti)
 
 static struct target_type integrity_target = {
 	.name			= "integrity",
-	.version		= {1, 10, 0},
+	.version		= {1, 11, 0},
 	.module			= THIS_MODULE,
 	.features		= DM_TARGET_SINGLETON | DM_TARGET_INTEGRITY,
 	.ctr			= dm_integrity_ctr,
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index e65058e0ed06..3b1ad7127cb8 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1941,7 +1941,8 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern
 			   minimum_data_size - sizeof(param_kernel->version)))
 		return -EFAULT;
 
-	if (param_kernel->data_size < minimum_data_size) {
+	if (unlikely(param_kernel->data_size < minimum_data_size) ||
+	    unlikely(param_kernel->data_size > DM_MAX_TARGETS * DM_MAX_TARGET_PARAMS)) {
 		DMERR("Invalid data size in the ioctl structure: %u",
 		      param_kernel->data_size);
 		return -EINVAL;
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index eb009d6bb03a..17e9af60bbf7 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -213,6 +213,7 @@ struct raid_dev {
 #define RT_FLAG_RS_IN_SYNC		6
 #define RT_FLAG_RS_RESYNCING		7
 #define RT_FLAG_RS_GROW			8
+#define RT_FLAG_RS_FROZEN		9
 
 /* Array elements of 64 bit needed for rebuild/failed disk bits */
 #define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8)
@@ -3240,11 +3241,12 @@ size_check:
 	rs->md.ro = 1;
 	rs->md.in_sync = 1;
 
-	/* Keep array frozen until resume. */
-	set_bit(MD_RECOVERY_FROZEN, &rs->md.recovery);
-
 	/* Has to be held on running the array */
 	mddev_suspend_and_lock_nointr(&rs->md);
+
+	/* Keep array frozen until resume. */
+	md_frozen_sync_thread(&rs->md);
+
 	r = md_run(&rs->md);
 	rs->md.in_sync = 0; /* Assume already marked dirty */
 	if (r) {
@@ -3339,7 +3341,8 @@ static int raid_map(struct dm_target *ti, struct bio *bio)
 	if (unlikely(bio_end_sector(bio) > mddev->array_sectors))
 		return DM_MAPIO_REQUEUE;
 
-	md_handle_request(mddev, bio);
+	if (unlikely(!md_handle_request(mddev, bio)))
+		return DM_MAPIO_REQUEUE;
 
 	return DM_MAPIO_SUBMITTED;
 }
@@ -3718,21 +3721,33 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv,
 {
 	struct raid_set *rs = ti->private;
 	struct mddev *mddev = &rs->md;
+	int ret = 0;
 
 	if (!mddev->pers || !mddev->pers->sync_request)
 		return -EINVAL;
 
-	if (!strcasecmp(argv[0], "frozen"))
-		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	else
-		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	if (test_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags) ||
+	    test_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags))
+		return -EBUSY;
 
-	if (!strcasecmp(argv[0], "idle") || !strcasecmp(argv[0], "frozen")) {
-		if (mddev->sync_thread) {
-			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-			md_reap_sync_thread(mddev);
-		}
-	} else if (decipher_sync_action(mddev, mddev->recovery) != st_idle)
+	if (!strcasecmp(argv[0], "frozen")) {
+		ret = mddev_lock(mddev);
+		if (ret)
+			return ret;
+
+		md_frozen_sync_thread(mddev);
+		mddev_unlock(mddev);
+	} else if (!strcasecmp(argv[0], "idle")) {
+		ret = mddev_lock(mddev);
+		if (ret)
+			return ret;
+
+		md_idle_sync_thread(mddev);
+		mddev_unlock(mddev);
+	}
+
+	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	if (decipher_sync_action(mddev, mddev->recovery) != st_idle)
 		return -EBUSY;
 	else if (!strcasecmp(argv[0], "resync"))
 		; /* MD_RECOVERY_NEEDED set below */
@@ -3791,15 +3806,46 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits)
 	blk_limits_io_opt(limits, chunk_size_bytes * mddev_data_stripes(rs));
 }
 
+static void raid_presuspend(struct dm_target *ti)
+{
+	struct raid_set *rs = ti->private;
+	struct mddev *mddev = &rs->md;
+
+	/*
+	 * From now on, disallow raid_message() to change sync_thread until
+	 * resume, raid_postsuspend() is too late.
+	 */
+	set_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags);
+
+	if (!reshape_interrupted(mddev))
+		return;
+
+	/*
+	 * For raid456, if reshape is interrupted, IO across reshape position
+	 * will never make progress, while caller will wait for IO to be done.
+	 * Inform raid456 to handle those IO to prevent deadlock.
+	 */
+	if (mddev->pers && mddev->pers->prepare_suspend)
+		mddev->pers->prepare_suspend(mddev);
+}
+
+static void raid_presuspend_undo(struct dm_target *ti)
+{
+	struct raid_set *rs = ti->private;
+
+	clear_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags);
+}
+
 static void raid_postsuspend(struct dm_target *ti)
 {
 	struct raid_set *rs = ti->private;
 
 	if (!test_and_set_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) {
-		/* Writes have to be stopped before suspending to avoid deadlocks. */
-		if (!test_bit(MD_RECOVERY_FROZEN, &rs->md.recovery))
-			md_stop_writes(&rs->md);
-
+		/*
+		 * sync_thread must be stopped during suspend, and writes have
+		 * to be stopped before suspending to avoid deadlocks.
+		 */
+		md_stop_writes(&rs->md);
 		mddev_suspend(&rs->md, false);
 	}
 }
@@ -4012,8 +4058,6 @@ static int raid_preresume(struct dm_target *ti)
 	}
 
 	/* Check for any resize/reshape on @rs and adjust/initiate */
-	/* Be prepared for mddev_resume() in raid_resume() */
-	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 	if (mddev->recovery_cp && mddev->recovery_cp < MaxSector) {
 		set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
 		mddev->resync_min = mddev->recovery_cp;
@@ -4047,7 +4091,9 @@ static void raid_resume(struct dm_target *ti)
 		 * Take this opportunity to check whether any failed
 		 * devices are reachable again.
 		 */
+		mddev_lock_nointr(mddev);
 		attempt_restore_of_faulty_devices(rs);
+		mddev_unlock(mddev);
 	}
 
 	if (test_and_clear_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) {
@@ -4055,10 +4101,13 @@ static void raid_resume(struct dm_target *ti)
 		if (mddev->delta_disks < 0)
 			rs_set_capacity(rs);
 
+		WARN_ON_ONCE(!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery));
+		WARN_ON_ONCE(test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));
+		clear_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags);
 		mddev_lock_nointr(mddev);
-		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		mddev->ro = 0;
 		mddev->in_sync = 0;
+		md_unfrozen_sync_thread(mddev);
 		mddev_unlock_and_resume(mddev);
 	}
 }
@@ -4074,6 +4123,8 @@ static struct target_type raid_target = {
 	.message = raid_message,
 	.iterate_devices = raid_iterate_devices,
 	.io_hints = raid_io_hints,
+	.presuspend = raid_presuspend,
+	.presuspend_undo = raid_presuspend_undo,
 	.postsuspend = raid_postsuspend,
 	.preresume = raid_preresume,
 	.resume = raid_resume,
diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c
index bdc14ec99814..1e5d988f44da 100644
--- a/drivers/md/dm-stats.c
+++ b/drivers/md/dm-stats.c
@@ -66,6 +66,9 @@ struct dm_stats_last_position {
 	unsigned int last_rw;
 };
 
+#define DM_STAT_MAX_ENTRIES		8388608
+#define DM_STAT_MAX_HISTOGRAM_ENTRIES	134217728
+
 /*
  * A typo on the command line could possibly make the kernel run out of memory
  * and crash. To prevent the crash we account all used memory. We fail if we
@@ -285,6 +288,9 @@ static int dm_stats_create(struct dm_stats *stats, sector_t start, sector_t end,
 	if (n_entries != (size_t)n_entries || !(size_t)(n_entries + 1))
 		return -EOVERFLOW;
 
+	if (n_entries > DM_STAT_MAX_ENTRIES)
+		return -EOVERFLOW;
+
 	shared_alloc_size = struct_size(s, stat_shared, n_entries);
 	if ((shared_alloc_size - sizeof(struct dm_stat)) / sizeof(struct dm_stat_shared) != n_entries)
 		return -EOVERFLOW;
@@ -297,6 +303,9 @@ static int dm_stats_create(struct dm_stats *stats, sector_t start, sector_t end,
 	if (histogram_alloc_size / (n_histogram_entries + 1) != (size_t)n_entries * sizeof(unsigned long long))
 		return -EOVERFLOW;
 
+	if ((n_histogram_entries + 1) * (size_t)n_entries > DM_STAT_MAX_HISTOGRAM_ENTRIES)
+		return -EOVERFLOW;
+
 	if (!check_shared_memory(shared_alloc_size + histogram_alloc_size +
 				 num_possible_cpus() * (percpu_alloc_size + histogram_alloc_size)))
 		return -ENOMEM;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 260b5b8f2b0d..88114719fe18 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -129,7 +129,12 @@ static int alloc_targets(struct dm_table *t, unsigned int num)
 int dm_table_create(struct dm_table **result, blk_mode_t mode,
 		    unsigned int num_targets, struct mapped_device *md)
 {
-	struct dm_table *t = kzalloc(sizeof(*t), GFP_KERNEL);
+	struct dm_table *t;
+
+	if (num_targets > DM_MAX_TARGETS)
+		return -EOVERFLOW;
+
+	t = kzalloc(sizeof(*t), GFP_KERNEL);
 
 	if (!t)
 		return -ENOMEM;
@@ -144,7 +149,7 @@ int dm_table_create(struct dm_table **result, blk_mode_t mode,
 
 	if (!num_targets) {
 		kfree(t);
-		return -ENOMEM;
+		return -EOVERFLOW;
 	}
 
 	if (alloc_targets(t, num_targets)) {
@@ -1958,26 +1963,27 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	bool wc = false, fua = false;
 	int r;
 
-	/*
-	 * Copy table's limits to the DM device's request_queue
-	 */
-	q->limits = *limits;
-
 	if (dm_table_supports_nowait(t))
 		blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q);
 	else
 		blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, q);
 
 	if (!dm_table_supports_discards(t)) {
-		q->limits.max_discard_sectors = 0;
-		q->limits.max_hw_discard_sectors = 0;
-		q->limits.discard_granularity = 0;
-		q->limits.discard_alignment = 0;
-		q->limits.discard_misaligned = 0;
+		limits->max_hw_discard_sectors = 0;
+		limits->discard_granularity = 0;
+		limits->discard_alignment = 0;
+		limits->discard_misaligned = 0;
 	}
 
+	if (!dm_table_supports_write_zeroes(t))
+		limits->max_write_zeroes_sectors = 0;
+
 	if (!dm_table_supports_secure_erase(t))
-		q->limits.max_secure_erase_sectors = 0;
+		limits->max_secure_erase_sectors = 0;
+
+	r = queue_limits_set(q, limits);
+	if (r)
+		return r;
 
 	if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_WC))) {
 		wc = true;
@@ -2002,9 +2008,6 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	else
 		blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
 
-	if (!dm_table_supports_write_zeroes(t))
-		q->limits.max_write_zeroes_sectors = 0;
-
 	dm_table_verify_integrity(t);
 
 	/*
@@ -2042,7 +2045,6 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	}
 
 	dm_update_crypto_profile(q, t);
-	disk_update_readahead(t->md->disk);
 
 	/*
 	 * Check for request-based device is left to
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 14e58ae70521..1b591bfa90d5 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -482,6 +482,63 @@ int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io,
 	return 0;
 }
 
+static int verity_recheck_copy(struct dm_verity *v, struct dm_verity_io *io,
+			       u8 *data, size_t len)
+{
+	memcpy(data, io->recheck_buffer, len);
+	io->recheck_buffer += len;
+
+	return 0;
+}
+
+static noinline int verity_recheck(struct dm_verity *v, struct dm_verity_io *io,
+				   struct bvec_iter start, sector_t cur_block)
+{
+	struct page *page;
+	void *buffer;
+	int r;
+	struct dm_io_request io_req;
+	struct dm_io_region io_loc;
+
+	page = mempool_alloc(&v->recheck_pool, GFP_NOIO);
+	buffer = page_to_virt(page);
+
+	io_req.bi_opf = REQ_OP_READ;
+	io_req.mem.type = DM_IO_KMEM;
+	io_req.mem.ptr.addr = buffer;
+	io_req.notify.fn = NULL;
+	io_req.client = v->io;
+	io_loc.bdev = v->data_dev->bdev;
+	io_loc.sector = cur_block << (v->data_dev_block_bits - SECTOR_SHIFT);
+	io_loc.count = 1 << (v->data_dev_block_bits - SECTOR_SHIFT);
+	r = dm_io(&io_req, 1, &io_loc, NULL);
+	if (unlikely(r))
+		goto free_ret;
+
+	r = verity_hash(v, verity_io_hash_req(v, io), buffer,
+			1 << v->data_dev_block_bits,
+			verity_io_real_digest(v, io), true);
+	if (unlikely(r))
+		goto free_ret;
+
+	if (memcmp(verity_io_real_digest(v, io),
+		   verity_io_want_digest(v, io), v->digest_size)) {
+		r = -EIO;
+		goto free_ret;
+	}
+
+	io->recheck_buffer = buffer;
+	r = verity_for_bv_block(v, io, &start, verity_recheck_copy);
+	if (unlikely(r))
+		goto free_ret;
+
+	r = 0;
+free_ret:
+	mempool_free(page, &v->recheck_pool);
+
+	return r;
+}
+
 static int verity_bv_zero(struct dm_verity *v, struct dm_verity_io *io,
 			  u8 *data, size_t len)
 {
@@ -508,9 +565,7 @@ static int verity_verify_io(struct dm_verity_io *io)
 {
 	bool is_zero;
 	struct dm_verity *v = io->v;
-#if defined(CONFIG_DM_VERITY_FEC)
 	struct bvec_iter start;
-#endif
 	struct bvec_iter iter_copy;
 	struct bvec_iter *iter;
 	struct crypto_wait wait;
@@ -561,10 +616,7 @@ static int verity_verify_io(struct dm_verity_io *io)
 		if (unlikely(r < 0))
 			return r;
 
-#if defined(CONFIG_DM_VERITY_FEC)
-		if (verity_fec_is_enabled(v))
-			start = *iter;
-#endif
+		start = *iter;
 		r = verity_for_io_block(v, io, iter, &wait);
 		if (unlikely(r < 0))
 			return r;
@@ -586,6 +638,10 @@ static int verity_verify_io(struct dm_verity_io *io)
 			 * tasklet since it may sleep, so fallback to work-queue.
 			 */
 			return -EAGAIN;
+		} else if (verity_recheck(v, io, start, cur_block) == 0) {
+			if (v->validated_blocks)
+				set_bit(cur_block, v->validated_blocks);
+			continue;
 #if defined(CONFIG_DM_VERITY_FEC)
 		} else if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_DATA,
 					     cur_block, NULL, &start) == 0) {
@@ -645,23 +701,6 @@ static void verity_work(struct work_struct *w)
 	verity_finish_io(io, errno_to_blk_status(verity_verify_io(io)));
 }
 
-static void verity_tasklet(unsigned long data)
-{
-	struct dm_verity_io *io = (struct dm_verity_io *)data;
-	int err;
-
-	io->in_tasklet = true;
-	err = verity_verify_io(io);
-	if (err == -EAGAIN || err == -ENOMEM) {
-		/* fallback to retrying with work-queue */
-		INIT_WORK(&io->work, verity_work);
-		queue_work(io->v->verify_wq, &io->work);
-		return;
-	}
-
-	verity_finish_io(io, errno_to_blk_status(err));
-}
-
 static void verity_end_io(struct bio *bio)
 {
 	struct dm_verity_io *io = bio->bi_private;
@@ -674,13 +713,8 @@ static void verity_end_io(struct bio *bio)
 		return;
 	}
 
-	if (static_branch_unlikely(&use_tasklet_enabled) && io->v->use_tasklet) {
-		tasklet_init(&io->tasklet, verity_tasklet, (unsigned long)io);
-		tasklet_schedule(&io->tasklet);
-	} else {
-		INIT_WORK(&io->work, verity_work);
-		queue_work(io->v->verify_wq, &io->work);
-	}
+	INIT_WORK(&io->work, verity_work);
+	queue_work(io->v->verify_wq, &io->work);
 }
 
 /*
@@ -963,6 +997,10 @@ static void verity_dtr(struct dm_target *ti)
 	if (v->verify_wq)
 		destroy_workqueue(v->verify_wq);
 
+	mempool_exit(&v->recheck_pool);
+	if (v->io)
+		dm_io_client_destroy(v->io);
+
 	if (v->bufio)
 		dm_bufio_client_destroy(v->bufio);
 
@@ -1401,6 +1439,20 @@ static int verity_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	}
 	v->hash_blocks = hash_position;
 
+	r = mempool_init_page_pool(&v->recheck_pool, 1, 0);
+	if (unlikely(r)) {
+		ti->error = "Cannot allocate mempool";
+		goto bad;
+	}
+
+	v->io = dm_io_client_create();
+	if (IS_ERR(v->io)) {
+		r = PTR_ERR(v->io);
+		v->io = NULL;
+		ti->error = "Cannot allocate dm io";
+		goto bad;
+	}
+
 	v->bufio = dm_bufio_client_create(v->hash_dev->bdev,
 		1 << v->hash_dev_block_bits, 1, sizeof(struct buffer_aux),
 		dm_bufio_alloc_callback, NULL,
@@ -1508,7 +1560,7 @@ int dm_verity_get_root_digest(struct dm_target *ti, u8 **root_digest, unsigned i
 static struct target_type verity_target = {
 	.name		= "verity",
 	.features	= DM_TARGET_IMMUTABLE,
-	.version	= {1, 9, 0},
+	.version	= {1, 10, 0},
 	.module		= THIS_MODULE,
 	.ctr		= verity_ctr,
 	.dtr		= verity_dtr,
diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h
index f9d522c870e6..db93a91169d5 100644
--- a/drivers/md/dm-verity.h
+++ b/drivers/md/dm-verity.h
@@ -11,6 +11,7 @@
 #ifndef DM_VERITY_H
 #define DM_VERITY_H
 
+#include <linux/dm-io.h>
 #include <linux/dm-bufio.h>
 #include <linux/device-mapper.h>
 #include <linux/interrupt.h>
@@ -68,6 +69,9 @@ struct dm_verity {
 	unsigned long *validated_blocks; /* bitset blocks validated */
 
 	char *signature_key_desc; /* signature keyring reference */
+
+	struct dm_io_client *io;
+	mempool_t recheck_pool;
 };
 
 struct dm_verity_io {
@@ -76,14 +80,15 @@ struct dm_verity_io {
 	/* original value of bio->bi_end_io */
 	bio_end_io_t *orig_bi_end_io;
 
+	struct bvec_iter iter;
+
 	sector_t block;
 	unsigned int n_blocks;
 	bool in_tasklet;
 
-	struct bvec_iter iter;
-
 	struct work_struct work;
-	struct tasklet_struct tasklet;
+
+	char *recheck_buffer;
 
 	/*
 	 * Three variably-size fields follow this struct:
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 074cb785eafc..b463c28c39ad 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -299,7 +299,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 		long i;
 
 		wc->memory_map = NULL;
-		pages = kvmalloc_array(p, sizeof(struct page *), GFP_KERNEL);
+		pages = vmalloc_array(p, sizeof(struct page *));
 		if (!pages) {
 			r = -ENOMEM;
 			goto err2;
@@ -330,7 +330,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 			r = -ENOMEM;
 			goto err3;
 		}
-		kvfree(pages);
+		vfree(pages);
 		wc->memory_vmapped = true;
 	}
 
@@ -341,7 +341,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 
 	return 0;
 err3:
-	kvfree(pages);
+	vfree(pages);
 err2:
 	dax_read_unlock(id);
 err1:
@@ -962,7 +962,7 @@ static int writecache_alloc_entries(struct dm_writecache *wc)
 
 	if (wc->entries)
 		return 0;
-	wc->entries = vmalloc(array_size(sizeof(struct wc_entry), wc->n_blocks));
+	wc->entries = vmalloc_array(wc->n_blocks, sizeof(struct wc_entry));
 	if (!wc->entries)
 		return -ENOMEM;
 	for (b = 0; b < wc->n_blocks; b++) {
diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index fdfe30f7b697..8156881a31de 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -1655,10 +1655,13 @@ static int dmz_reset_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
 
 	if (!dmz_is_empty(zone) || dmz_seq_write_err(zone)) {
 		struct dmz_dev *dev = zone->dev;
+		unsigned int noio_flag;
 
+		noio_flag = memalloc_noio_save();
 		ret = blkdev_zone_mgmt(dev->bdev, REQ_OP_ZONE_RESET,
 				       dmz_start_sect(zmd, zone),
-				       zmd->zone_nr_sectors, GFP_NOIO);
+				       zmd->zone_nr_sectors);
+		memalloc_noio_restore(noio_flag);
 		if (ret) {
 			dmz_dev_err(dev, "Reset zone %u failed %d",
 				    zone->id, ret);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 8dcabf84d866..447e132d09b5 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -726,7 +726,8 @@ static struct table_device *open_table_device(struct mapped_device *md,
 		dev_t dev, blk_mode_t mode)
 {
 	struct table_device *td;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
+	struct block_device *bdev;
 	u64 part_off;
 	int r;
 
@@ -735,34 +736,36 @@ static struct table_device *open_table_device(struct mapped_device *md,
 		return ERR_PTR(-ENOMEM);
 	refcount_set(&td->count, 1);
 
-	bdev_handle = bdev_open_by_dev(dev, mode, _dm_claim_ptr, NULL);
-	if (IS_ERR(bdev_handle)) {
-		r = PTR_ERR(bdev_handle);
+	bdev_file = bdev_file_open_by_dev(dev, mode, _dm_claim_ptr, NULL);
+	if (IS_ERR(bdev_file)) {
+		r = PTR_ERR(bdev_file);
 		goto out_free_td;
 	}
 
+	bdev = file_bdev(bdev_file);
+
 	/*
 	 * We can be called before the dm disk is added.  In that case we can't
 	 * register the holder relation here.  It will be done once add_disk was
 	 * called.
 	 */
 	if (md->disk->slave_dir) {
-		r = bd_link_disk_holder(bdev_handle->bdev, md->disk);
+		r = bd_link_disk_holder(bdev, md->disk);
 		if (r)
 			goto out_blkdev_put;
 	}
 
 	td->dm_dev.mode = mode;
-	td->dm_dev.bdev = bdev_handle->bdev;
-	td->dm_dev.bdev_handle = bdev_handle;
-	td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev_handle->bdev, &part_off,
+	td->dm_dev.bdev = bdev;
+	td->dm_dev.bdev_file = bdev_file;
+	td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev, &part_off,
 						NULL, NULL);
 	format_dev_t(td->dm_dev.name, dev);
 	list_add(&td->list, &md->table_devices);
 	return td;
 
 out_blkdev_put:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 out_free_td:
 	kfree(td);
 	return ERR_PTR(r);
@@ -775,7 +778,7 @@ static void close_table_device(struct table_device *td, struct mapped_device *md
 {
 	if (md->disk->slave_dir)
 		bd_unlink_disk_holder(td->dm_dev.bdev, md->disk);
-	bdev_release(td->dm_dev.bdev_handle);
+	fput(td->dm_dev.bdev_file);
 	put_dax(td->dm_dev.dax_dev);
 	list_del(&td->list);
 	kfree(td);
@@ -2098,8 +2101,8 @@ static struct mapped_device *alloc_dev(int minor)
 	 * established. If request-based table is loaded: blk-mq will
 	 * override accordingly.
 	 */
-	md->disk = blk_alloc_disk(md->numa_node_id);
-	if (!md->disk)
+	md->disk = blk_alloc_disk(NULL, md->numa_node_id);
+	if (IS_ERR(md->disk))
 		goto bad;
 	md->queue = md->disk->queue;
 
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index 9672f75c3050..059afc24c08b 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -234,7 +234,8 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap,
 	sector_t doff;
 
 	bdev = (rdev->meta_bdev) ? rdev->meta_bdev : rdev->bdev;
-	if (pg_index == store->file_pages - 1) {
+	/* we compare length (page numbers), not page offset. */
+	if ((pg_index - store->sb_index) == store->file_pages - 1) {
 		unsigned int last_page_size = store->bytes & (PAGE_SIZE - 1);
 
 		if (last_page_size == 0)
@@ -438,8 +439,8 @@ static void filemap_write_page(struct bitmap *bitmap, unsigned long pg_index,
 	struct page *page = store->filemap[pg_index];
 
 	if (mddev_is_clustered(bitmap->mddev)) {
-		pg_index += bitmap->cluster_slot *
-			DIV_ROUND_UP(store->bytes, PAGE_SIZE);
+		/* go to node bitmap area starting point */
+		pg_index += store->sb_index;
 	}
 
 	if (store->file)
@@ -952,6 +953,7 @@ static void md_bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
 	unsigned long index = file_page_index(store, chunk);
 	unsigned long node_offset = 0;
 
+	index += store->sb_index;
 	if (mddev_is_clustered(bitmap->mddev))
 		node_offset = bitmap->cluster_slot * store->file_pages;
 
@@ -982,6 +984,7 @@ static void md_bitmap_file_clear_bit(struct bitmap *bitmap, sector_t block)
 	unsigned long index = file_page_index(store, chunk);
 	unsigned long node_offset = 0;
 
+	index += store->sb_index;
 	if (mddev_is_clustered(bitmap->mddev))
 		node_offset = bitmap->cluster_slot * store->file_pages;
 
@@ -1043,9 +1046,8 @@ void md_bitmap_unplug(struct bitmap *bitmap)
 		if (dirty || need_write) {
 			if (!writing) {
 				md_bitmap_wait_writes(bitmap);
-				if (bitmap->mddev->queue)
-					blk_add_trace_msg(bitmap->mddev->queue,
-							  "md bitmap_unplug");
+				mddev_add_trace_msg(bitmap->mddev,
+					"md bitmap_unplug");
 			}
 			clear_page_attr(bitmap, i, BITMAP_PAGE_PENDING);
 			filemap_write_page(bitmap, i, false);
@@ -1316,9 +1318,7 @@ void md_bitmap_daemon_work(struct mddev *mddev)
 	}
 	bitmap->allclean = 1;
 
-	if (bitmap->mddev->queue)
-		blk_add_trace_msg(bitmap->mddev->queue,
-				  "md bitmap_daemon_work");
+	mddev_add_trace_msg(bitmap->mddev, "md bitmap_daemon_work");
 
 	/* Any file-page which is PENDING now needs to be written.
 	 * So set NEEDWRITE now, then after we make any last-minute changes
diff --git a/drivers/md/md-linear.h b/drivers/md/md-linear.h
deleted file mode 100644
index 5587eeedb882..000000000000
--- a/drivers/md/md-linear.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINEAR_H
-#define _LINEAR_H
-
-struct dev_info {
-	struct md_rdev	*rdev;
-	sector_t	end_sector;
-};
-
-struct linear_conf
-{
-	struct rcu_head		rcu;
-	sector_t		array_sectors;
-	int			raid_disks; /* a copy of mddev->raid_disks */
-	struct dev_info		disks[] __counted_by(raid_disks);
-};
-#endif
diff --git a/drivers/md/md-multipath.h b/drivers/md/md-multipath.h
deleted file mode 100644
index b3099e5fc4d7..000000000000
--- a/drivers/md/md-multipath.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _MULTIPATH_H
-#define _MULTIPATH_H
-
-struct multipath_info {
-	struct md_rdev	*rdev;
-};
-
-struct mpconf {
-	struct mddev			*mddev;
-	struct multipath_info	*multipaths;
-	int			raid_disks;
-	spinlock_t		device_lock;
-	struct list_head	retry_list;
-
-	mempool_t		pool;
-};
-
-/*
- * this is our 'private' 'collective' MULTIPATH buffer head.
- * it contains information about what kind of IO operations were started
- * for this MULTIPATH operation, and about their status:
- */
-
-struct multipath_bh {
-	struct mddev			*mddev;
-	struct bio		*master_bio;
-	struct bio		bio;
-	int			path;
-	struct list_head	retry_list;
-};
-#endif
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 0a2bd72a6d76..e575e74aabf5 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -65,7 +65,6 @@
 #include <linux/percpu-refcount.h>
 #include <linux/part_stat.h>
 
-#include <trace/events/block.h>
 #include "md.h"
 #include "md-bitmap.h"
 #include "md-cluster.h"
@@ -99,18 +98,6 @@ static void mddev_detach(struct mddev *mddev);
 static void export_rdev(struct md_rdev *rdev, struct mddev *mddev);
 static void md_wakeup_thread_directly(struct md_thread __rcu *thread);
 
-enum md_ro_state {
-	MD_RDWR,
-	MD_RDONLY,
-	MD_AUTO_READ,
-	MD_MAX_STATE
-};
-
-static bool md_is_rdwr(struct mddev *mddev)
-{
-	return (mddev->ro == MD_RDWR);
-}
-
 /*
  * Default number of read corrections we'll attempt on an rdev
  * before ejecting it from the array. We divide the read error
@@ -378,7 +365,7 @@ static bool is_suspended(struct mddev *mddev, struct bio *bio)
 	return true;
 }
 
-void md_handle_request(struct mddev *mddev, struct bio *bio)
+bool md_handle_request(struct mddev *mddev, struct bio *bio)
 {
 check_suspended:
 	if (is_suspended(mddev, bio)) {
@@ -386,7 +373,7 @@ check_suspended:
 		/* Bail out if REQ_NOWAIT is set for the bio */
 		if (bio->bi_opf & REQ_NOWAIT) {
 			bio_wouldblock_error(bio);
-			return;
+			return true;
 		}
 		for (;;) {
 			prepare_to_wait(&mddev->sb_wait, &__wait,
@@ -402,10 +389,13 @@ check_suspended:
 
 	if (!mddev->pers->make_request(mddev, bio)) {
 		percpu_ref_put(&mddev->active_io);
+		if (!mddev->gendisk && mddev->pers->prepare_suspend)
+			return false;
 		goto check_suspended;
 	}
 
 	percpu_ref_put(&mddev->active_io);
+	return true;
 }
 EXPORT_SYMBOL(md_handle_request);
 
@@ -529,6 +519,24 @@ void mddev_resume(struct mddev *mddev)
 }
 EXPORT_SYMBOL_GPL(mddev_resume);
 
+/* sync bdev before setting device to readonly or stopping raid*/
+static int mddev_set_closing_and_sync_blockdev(struct mddev *mddev, int opener_num)
+{
+	mutex_lock(&mddev->open_mutex);
+	if (mddev->pers && atomic_read(&mddev->openers) > opener_num) {
+		mutex_unlock(&mddev->open_mutex);
+		return -EBUSY;
+	}
+	if (test_and_set_bit(MD_CLOSING, &mddev->flags)) {
+		mutex_unlock(&mddev->open_mutex);
+		return -EBUSY;
+	}
+	mutex_unlock(&mddev->open_mutex);
+
+	sync_blockdev(mddev->gendisk->part0);
+	return 0;
+}
+
 /*
  * Generic flush handling for md
  */
@@ -579,8 +587,12 @@ static void submit_flushes(struct work_struct *ws)
 			rcu_read_lock();
 		}
 	rcu_read_unlock();
-	if (atomic_dec_and_test(&mddev->flush_pending))
+	if (atomic_dec_and_test(&mddev->flush_pending)) {
+		/* The pair is percpu_ref_get() from md_flush_request() */
+		percpu_ref_put(&mddev->active_io);
+
 		queue_work(md_wq, &mddev->flush_work);
+	}
 }
 
 static void md_submit_flush_data(struct work_struct *ws)
@@ -2402,7 +2414,7 @@ int md_integrity_register(struct mddev *mddev)
 
 	if (list_empty(&mddev->disks))
 		return 0; /* nothing to do */
-	if (!mddev->gendisk || blk_get_integrity(mddev->gendisk))
+	if (mddev_is_dm(mddev) || blk_get_integrity(mddev->gendisk))
 		return 0; /* shouldn't register, or already is */
 	rdev_for_each(rdev, mddev) {
 		/* skip spares and non-functional disks */
@@ -2455,7 +2467,7 @@ int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev)
 {
 	struct blk_integrity *bi_mddev;
 
-	if (!mddev->gendisk)
+	if (mddev_is_dm(mddev))
 		return 0;
 
 	bi_mddev = blk_get_integrity(mddev->gendisk);
@@ -2562,6 +2574,7 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
  fail:
 	pr_warn("md: failed to register dev-%s for %s\n",
 		b, mdname(mddev));
+	mddev_destroy_serial_pool(mddev, rdev);
 	return err;
 }
 
@@ -2578,7 +2591,7 @@ static void export_rdev(struct md_rdev *rdev, struct mddev *mddev)
 	if (test_bit(AutoDetected, &rdev->flags))
 		md_autodetect_dev(rdev->bdev->bd_dev);
 #endif
-	bdev_release(rdev->bdev_handle);
+	fput(rdev->bdev_file);
 	rdev->bdev = NULL;
 	kobject_put(&rdev->kobj);
 }
@@ -2591,7 +2604,7 @@ static void md_kick_rdev_from_array(struct md_rdev *rdev)
 	list_del_rcu(&rdev->same_set);
 	pr_debug("md: unbind<%pg>\n", rdev->bdev);
 	mddev_destroy_serial_pool(rdev->mddev, rdev);
-	rdev->mddev = NULL;
+	WRITE_ONCE(rdev->mddev, NULL);
 	sysfs_remove_link(&rdev->kobj, "block");
 	sysfs_put(rdev->sysfs_state);
 	sysfs_put(rdev->sysfs_unack_badblocks);
@@ -2847,8 +2860,7 @@ repeat:
 	pr_debug("md: updating %s RAID superblock on device (in sync %d)\n",
 		 mdname(mddev), mddev->in_sync);
 
-	if (mddev->queue)
-		blk_add_trace_msg(mddev->queue, "md md_update_sb");
+	mddev_add_trace_msg(mddev, "md md_update_sb");
 rewrite:
 	md_bitmap_update_sb(mddev->bitmap);
 	rdev_for_each(rdev, mddev) {
@@ -2929,7 +2941,6 @@ static int add_bound_rdev(struct md_rdev *rdev)
 		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_new_event();
-	md_wakeup_thread(mddev->thread);
 	return 0;
 }
 
@@ -3044,10 +3055,8 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
 
 			if (err == 0) {
 				md_kick_rdev_from_array(rdev);
-				if (mddev->pers) {
+				if (mddev->pers)
 					set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
-					md_wakeup_thread(mddev->thread);
-				}
 				md_new_event();
 			}
 		}
@@ -3077,7 +3086,6 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
 		clear_bit(BlockedBadBlocks, &rdev->flags);
 		wake_up(&rdev->blocked_wait);
 		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
-		md_wakeup_thread(rdev->mddev->thread);
 
 		err = 0;
 	} else if (cmd_match(buf, "insync") && rdev->raid_disk == -1) {
@@ -3115,7 +3123,6 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
 		    !test_bit(Replacement, &rdev->flags))
 			set_bit(WantReplacement, &rdev->flags);
 		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
-		md_wakeup_thread(rdev->mddev->thread);
 		err = 0;
 	} else if (cmd_match(buf, "-want_replacement")) {
 		/* Clearing 'want_replacement' is always allowed.
@@ -3245,7 +3252,6 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len)
 		if (rdev->raid_disk >= 0)
 			return -EBUSY;
 		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
-		md_wakeup_thread(rdev->mddev->thread);
 	} else if (rdev->mddev->pers) {
 		/* Activating a spare .. or possibly reactivating
 		 * if we ever get bitmaps working here.
@@ -3339,8 +3345,7 @@ static ssize_t new_offset_store(struct md_rdev *rdev,
 	if (kstrtoull(buf, 10, &new_offset) < 0)
 		return -EINVAL;
 
-	if (mddev->sync_thread ||
-	    test_bit(MD_RECOVERY_RUNNING,&mddev->recovery))
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
 		return -EBUSY;
 	if (new_offset == rdev->data_offset)
 		/* reset is always permitted */
@@ -3671,7 +3676,7 @@ rdev_attr_store(struct kobject *kobj, struct attribute *attr,
 	struct kernfs_node *kn = NULL;
 	bool suspend = false;
 	ssize_t rv;
-	struct mddev *mddev = rdev->mddev;
+	struct mddev *mddev = READ_ONCE(rdev->mddev);
 
 	if (!entry->store)
 		return -EIO;
@@ -3773,16 +3778,16 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe
 	if (err)
 		goto out_clear_rdev;
 
-	rdev->bdev_handle = bdev_open_by_dev(newdev,
+	rdev->bdev_file = bdev_file_open_by_dev(newdev,
 			BLK_OPEN_READ | BLK_OPEN_WRITE,
 			super_format == -2 ? &claim_rdev : rdev, NULL);
-	if (IS_ERR(rdev->bdev_handle)) {
+	if (IS_ERR(rdev->bdev_file)) {
 		pr_warn("md: could not open device unknown-block(%u,%u).\n",
 			MAJOR(newdev), MINOR(newdev));
-		err = PTR_ERR(rdev->bdev_handle);
+		err = PTR_ERR(rdev->bdev_file);
 		goto out_clear_rdev;
 	}
-	rdev->bdev = rdev->bdev_handle->bdev;
+	rdev->bdev = file_bdev(rdev->bdev_file);
 
 	kobject_init(&rdev->kobj, &rdev_ktype);
 
@@ -3813,7 +3818,7 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe
 	return rdev;
 
 out_blkdev_put:
-	bdev_release(rdev->bdev_handle);
+	fput(rdev->bdev_file);
 out_clear_rdev:
 	md_rdev_clear(rdev);
 out_free_rdev:
@@ -4013,8 +4018,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 	 */
 
 	rv = -EBUSY;
-	if (mddev->sync_thread ||
-	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
 	    mddev->reshape_position != MaxSector ||
 	    mddev->sysfs_active)
 		goto out_unlock;
@@ -4164,7 +4168,6 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 		mddev->in_sync = 1;
 		del_timer_sync(&mddev->safemode_timer);
 	}
-	blk_set_stacking_limits(&mddev->queue->limits);
 	pers->run(mddev);
 	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 	if (!mddev->thread)
@@ -4471,8 +4474,8 @@ array_state_show(struct mddev *mddev, char *page)
 	return sprintf(page, "%s\n", array_states[st]);
 }
 
-static int do_md_stop(struct mddev *mddev, int ro, struct block_device *bdev);
-static int md_set_readonly(struct mddev *mddev, struct block_device *bdev);
+static int do_md_stop(struct mddev *mddev, int ro);
+static int md_set_readonly(struct mddev *mddev);
 static int restart_array(struct mddev *mddev);
 
 static ssize_t
@@ -4489,6 +4492,17 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 	case broken:		/* cannot be set */
 	case bad_word:
 		return -EINVAL;
+	case clear:
+	case readonly:
+	case inactive:
+	case read_auto:
+		if (!mddev->pers || !md_is_rdwr(mddev))
+			break;
+		/* write sysfs will not open mddev and opener should be 0 */
+		err = mddev_set_closing_and_sync_blockdev(mddev, 0);
+		if (err)
+			return err;
+		break;
 	default:
 		break;
 	}
@@ -4522,14 +4536,14 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 	case inactive:
 		/* stop an active array, return 0 otherwise */
 		if (mddev->pers)
-			err = do_md_stop(mddev, 2, NULL);
+			err = do_md_stop(mddev, 2);
 		break;
 	case clear:
-		err = do_md_stop(mddev, 0, NULL);
+		err = do_md_stop(mddev, 0);
 		break;
 	case readonly:
 		if (mddev->pers)
-			err = md_set_readonly(mddev, NULL);
+			err = md_set_readonly(mddev);
 		else {
 			mddev->ro = MD_RDONLY;
 			set_disk_ro(mddev->gendisk, 1);
@@ -4539,7 +4553,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 	case read_auto:
 		if (mddev->pers) {
 			if (md_is_rdwr(mddev))
-				err = md_set_readonly(mddev, NULL);
+				err = md_set_readonly(mddev);
 			else if (mddev->ro == MD_RDONLY)
 				err = restart_array(mddev);
 			if (err == 0) {
@@ -4588,6 +4602,11 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	}
 	mddev_unlock(mddev);
+
+	if (st == readonly || st == read_auto || st == inactive ||
+	    (err && st == clear))
+		clear_bit(MD_CLOSING, &mddev->flags);
+
 	return err ?: len;
 }
 static struct md_sysfs_entry md_array_state =
@@ -4915,6 +4934,35 @@ static void stop_sync_thread(struct mddev *mddev, bool locked, bool check_seq)
 		mddev_lock_nointr(mddev);
 }
 
+void md_idle_sync_thread(struct mddev *mddev)
+{
+	lockdep_assert_held(&mddev->reconfig_mutex);
+
+	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	stop_sync_thread(mddev, true, true);
+}
+EXPORT_SYMBOL_GPL(md_idle_sync_thread);
+
+void md_frozen_sync_thread(struct mddev *mddev)
+{
+	lockdep_assert_held(&mddev->reconfig_mutex);
+
+	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	stop_sync_thread(mddev, true, false);
+}
+EXPORT_SYMBOL_GPL(md_frozen_sync_thread);
+
+void md_unfrozen_sync_thread(struct mddev *mddev)
+{
+	lockdep_assert_held(&mddev->reconfig_mutex);
+
+	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	md_wakeup_thread(mddev->thread);
+	sysfs_notify_dirent_safe(mddev->sysfs_action);
+}
+EXPORT_SYMBOL_GPL(md_unfrozen_sync_thread);
+
 static void idle_sync_thread(struct mddev *mddev)
 {
 	mutex_lock(&mddev->sync_mutex);
@@ -5706,6 +5754,51 @@ static const struct kobj_type md_ktype = {
 
 int mdp_major = 0;
 
+/* stack the limit for all rdevs into lim */
+void mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim)
+{
+	struct md_rdev *rdev;
+
+	rdev_for_each(rdev, mddev) {
+		queue_limits_stack_bdev(lim, rdev->bdev, rdev->data_offset,
+					mddev->gendisk->disk_name);
+	}
+}
+EXPORT_SYMBOL_GPL(mddev_stack_rdev_limits);
+
+/* apply the extra stacking limits from a new rdev into mddev */
+int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev)
+{
+	struct queue_limits lim;
+
+	if (mddev_is_dm(mddev))
+		return 0;
+
+	lim = queue_limits_start_update(mddev->gendisk->queue);
+	queue_limits_stack_bdev(&lim, rdev->bdev, rdev->data_offset,
+				mddev->gendisk->disk_name);
+	return queue_limits_commit_update(mddev->gendisk->queue, &lim);
+}
+EXPORT_SYMBOL_GPL(mddev_stack_new_rdev);
+
+/* update the optimal I/O size after a reshape */
+void mddev_update_io_opt(struct mddev *mddev, unsigned int nr_stripes)
+{
+	struct queue_limits lim;
+
+	if (mddev_is_dm(mddev))
+		return;
+
+	/* don't bother updating io_opt if we can't suspend the array */
+	if (mddev_suspend(mddev, false) < 0)
+		return;
+	lim = queue_limits_start_update(mddev->gendisk->queue);
+	lim.io_opt = lim.io_min * nr_stripes;
+	queue_limits_commit_update(mddev->gendisk->queue, &lim);
+	mddev_resume(mddev);
+}
+EXPORT_SYMBOL_GPL(mddev_update_io_opt);
+
 static void mddev_delayed_delete(struct work_struct *ws)
 {
 	struct mddev *mddev = container_of(ws, struct mddev, del_work);
@@ -5770,10 +5863,11 @@ struct mddev *md_alloc(dev_t dev, char *name)
 		 */
 		mddev->hold_active = UNTIL_STOP;
 
-	error = -ENOMEM;
-	disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!disk)
+	disk = blk_alloc_disk(NULL, NUMA_NO_NODE);
+	if (IS_ERR(disk)) {
+		error = PTR_ERR(disk);
 		goto out_free_mddev;
+	}
 
 	disk->major = MAJOR(mddev->unit);
 	disk->first_minor = unit << shift;
@@ -5787,9 +5881,7 @@ struct mddev *md_alloc(dev_t dev, char *name)
 	disk->fops = &md_fops;
 	disk->private_data = mddev;
 
-	mddev->queue = disk->queue;
-	blk_set_stacking_limits(&mddev->queue->limits);
-	blk_queue_write_cache(mddev->queue, true, true);
+	blk_queue_write_cache(disk->queue, true, true);
 	disk->events |= DISK_EVENT_MEDIA_CHANGE;
 	mddev->gendisk = disk;
 	error = add_disk(disk);
@@ -5931,7 +6023,7 @@ int md_run(struct mddev *mddev)
 		invalidate_bdev(rdev->bdev);
 		if (mddev->ro != MD_RDONLY && rdev_read_only(rdev)) {
 			mddev->ro = MD_RDONLY;
-			if (mddev->gendisk)
+			if (!mddev_is_dm(mddev))
 				set_disk_ro(mddev->gendisk, 1);
 		}
 
@@ -6034,7 +6126,10 @@ int md_run(struct mddev *mddev)
 			pr_warn("True protection against single-disk failure might be compromised.\n");
 	}
 
-	mddev->recovery = 0;
+	/* dm-raid expect sync_thread to be frozen until resume */
+	if (mddev->gendisk)
+		mddev->recovery = 0;
+
 	/* may be over-ridden by personality */
 	mddev->resync_max_sectors = mddev->dev_sectors;
 
@@ -6090,7 +6185,8 @@ int md_run(struct mddev *mddev)
 		}
 	}
 
-	if (mddev->queue) {
+	if (!mddev_is_dm(mddev)) {
+		struct request_queue *q = mddev->gendisk->queue;
 		bool nonrot = true;
 
 		rdev_for_each(rdev, mddev) {
@@ -6102,14 +6198,14 @@ int md_run(struct mddev *mddev)
 		if (mddev->degraded)
 			nonrot = false;
 		if (nonrot)
-			blk_queue_flag_set(QUEUE_FLAG_NONROT, mddev->queue);
+			blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
 		else
-			blk_queue_flag_clear(QUEUE_FLAG_NONROT, mddev->queue);
-		blk_queue_flag_set(QUEUE_FLAG_IO_STAT, mddev->queue);
+			blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
+		blk_queue_flag_set(QUEUE_FLAG_IO_STAT, q);
 
 		/* Set the NOWAIT flags if all underlying devices support it */
 		if (nowait)
-			blk_queue_flag_set(QUEUE_FLAG_NOWAIT, mddev->queue);
+			blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q);
 	}
 	if (pers->sync_request) {
 		if (mddev->kobj.sd &&
@@ -6188,7 +6284,6 @@ int do_md_run(struct mddev *mddev)
 	/* run start up tasks that require md_thread */
 	md_start(mddev);
 
-	md_wakeup_thread(mddev->thread);
 	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 
 	set_capacity_and_notify(mddev->gendisk, mddev->array_sectors);
@@ -6209,7 +6304,6 @@ int md_start(struct mddev *mddev)
 
 	if (mddev->pers->start) {
 		set_bit(MD_RECOVERY_WAIT, &mddev->recovery);
-		md_wakeup_thread(mddev->thread);
 		ret = mddev->pers->start(mddev);
 		clear_bit(MD_RECOVERY_WAIT, &mddev->recovery);
 		md_wakeup_thread(mddev->sync_thread);
@@ -6254,7 +6348,6 @@ static int restart_array(struct mddev *mddev)
 	pr_debug("md: %s switched to read-write mode.\n", mdname(mddev));
 	/* Kick recovery or resync if necessary */
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-	md_wakeup_thread(mddev->thread);
 	md_wakeup_thread(mddev->sync_thread);
 	sysfs_notify_dirent_safe(mddev->sysfs_state);
 	return 0;
@@ -6274,7 +6367,15 @@ static void md_clean(struct mddev *mddev)
 	mddev->persistent = 0;
 	mddev->level = LEVEL_NONE;
 	mddev->clevel[0] = 0;
-	mddev->flags = 0;
+	/*
+	 * Don't clear MD_CLOSING, or mddev can be opened again.
+	 * 'hold_active != 0' means mddev is still in the creation
+	 * process and will be used later.
+	 */
+	if (mddev->hold_active)
+		mddev->flags = 0;
+	else
+		mddev->flags &= BIT_ULL_MASK(MD_CLOSING);
 	mddev->sb_flags = 0;
 	mddev->ro = MD_RDWR;
 	mddev->metadata_type[0] = 0;
@@ -6311,7 +6412,6 @@ static void md_clean(struct mddev *mddev)
 
 static void __md_stop_writes(struct mddev *mddev)
 {
-	stop_sync_thread(mddev, true, false);
 	del_timer_sync(&mddev->safemode_timer);
 
 	if (mddev->pers && mddev->pers->quiesce) {
@@ -6336,6 +6436,8 @@ static void __md_stop_writes(struct mddev *mddev)
 void md_stop_writes(struct mddev *mddev)
 {
 	mddev_lock_nointr(mddev);
+	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	stop_sync_thread(mddev, true, false);
 	__md_stop_writes(mddev);
 	mddev_unlock(mddev);
 }
@@ -6349,8 +6451,10 @@ static void mddev_detach(struct mddev *mddev)
 		mddev->pers->quiesce(mddev, 0);
 	}
 	md_unregister_thread(mddev, &mddev->thread);
-	if (mddev->queue)
-		blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
+
+	/* the unplug fn references 'conf' */
+	if (!mddev_is_dm(mddev))
+		blk_sync_queue(mddev->gendisk->queue);
 }
 
 static void __md_stop(struct mddev *mddev)
@@ -6387,7 +6491,8 @@ void md_stop(struct mddev *mddev)
 
 EXPORT_SYMBOL_GPL(md_stop);
 
-static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
+/* ensure 'mddev->pers' exist before calling md_set_readonly() */
+static int md_set_readonly(struct mddev *mddev)
 {
 	int err = 0;
 	int did_freeze = 0;
@@ -6398,7 +6503,6 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 	if (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) {
 		did_freeze = 1;
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-		md_wakeup_thread(mddev->thread);
 	}
 
 	stop_sync_thread(mddev, false, false);
@@ -6406,36 +6510,29 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
 	mddev_lock_nointr(mddev);
 
-	mutex_lock(&mddev->open_mutex);
-	if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) ||
-	    mddev->sync_thread ||
-	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
 		pr_warn("md: %s still in use.\n",mdname(mddev));
 		err = -EBUSY;
 		goto out;
 	}
 
-	if (mddev->pers) {
-		__md_stop_writes(mddev);
-
-		if (mddev->ro == MD_RDONLY) {
-			err  = -ENXIO;
-			goto out;
-		}
+	__md_stop_writes(mddev);
 
-		mddev->ro = MD_RDONLY;
-		set_disk_ro(mddev->gendisk, 1);
+	if (mddev->ro == MD_RDONLY) {
+		err  = -ENXIO;
+		goto out;
 	}
 
+	mddev->ro = MD_RDONLY;
+	set_disk_ro(mddev->gendisk, 1);
+
 out:
-	if ((mddev->pers && !err) || did_freeze) {
+	if (!err || did_freeze) {
 		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-		md_wakeup_thread(mddev->thread);
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	}
 
-	mutex_unlock(&mddev->open_mutex);
 	return err;
 }
 
@@ -6443,8 +6540,7 @@ out:
  *   0 - completely stop and dis-assemble array
  *   2 - stop but do not disassemble array
  */
-static int do_md_stop(struct mddev *mddev, int mode,
-		      struct block_device *bdev)
+static int do_md_stop(struct mddev *mddev, int mode)
 {
 	struct gendisk *disk = mddev->gendisk;
 	struct md_rdev *rdev;
@@ -6453,22 +6549,16 @@ static int do_md_stop(struct mddev *mddev, int mode,
 	if (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) {
 		did_freeze = 1;
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-		md_wakeup_thread(mddev->thread);
 	}
 
 	stop_sync_thread(mddev, true, false);
 
-	mutex_lock(&mddev->open_mutex);
-	if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) ||
-	    mddev->sysfs_active ||
-	    mddev->sync_thread ||
+	if (mddev->sysfs_active ||
 	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
 		pr_warn("md: %s still in use.\n",mdname(mddev));
-		mutex_unlock(&mddev->open_mutex);
 		if (did_freeze) {
 			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-			md_wakeup_thread(mddev->thread);
 		}
 		return -EBUSY;
 	}
@@ -6487,13 +6577,11 @@ static int do_md_stop(struct mddev *mddev, int mode,
 				sysfs_unlink_rdev(mddev, rdev);
 
 		set_capacity_and_notify(disk, 0);
-		mutex_unlock(&mddev->open_mutex);
 		mddev->changed = 1;
 
 		if (!md_is_rdwr(mddev))
 			mddev->ro = MD_RDWR;
-	} else
-		mutex_unlock(&mddev->open_mutex);
+	}
 	/*
 	 * Free resources if final stop
 	 */
@@ -6539,7 +6627,7 @@ static void autorun_array(struct mddev *mddev)
 	err = do_md_run(mddev);
 	if (err) {
 		pr_warn("md: do_md_run() returned %d\n", err);
-		do_md_stop(mddev, 0, NULL);
+		do_md_stop(mddev, 0);
 	}
 }
 
@@ -7009,9 +7097,7 @@ kick_rdev:
 
 	md_kick_rdev_from_array(rdev);
 	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
-	if (mddev->thread)
-		md_wakeup_thread(mddev->thread);
-	else
+	if (!mddev->thread)
 		md_update_sb(mddev, 1);
 	md_new_event();
 
@@ -7086,14 +7172,13 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev)
 	if (!bdev_nowait(rdev->bdev)) {
 		pr_info("%s: Disabling nowait because %pg does not support nowait\n",
 			mdname(mddev), rdev->bdev);
-		blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, mddev->queue);
+		blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, mddev->gendisk->queue);
 	}
 	/*
 	 * Kick recovery, maybe this spare has to be added to the
 	 * array immediately.
 	 */
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-	md_wakeup_thread(mddev->thread);
 	md_new_event();
 	return 0;
 
@@ -7307,8 +7392,7 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
 	 * of each device.  If num_sectors is zero, we find the largest size
 	 * that fits.
 	 */
-	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
-	    mddev->sync_thread)
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
 		return -EBUSY;
 	if (!md_is_rdwr(mddev))
 		return -EROFS;
@@ -7325,10 +7409,9 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
 	if (!rv) {
 		if (mddev_is_clustered(mddev))
 			md_cluster_ops->update_size(mddev, old_dev_sectors);
-		else if (mddev->queue) {
+		else if (!mddev_is_dm(mddev))
 			set_capacity_and_notify(mddev->gendisk,
 						mddev->array_sectors);
-		}
 	}
 	return rv;
 }
@@ -7345,8 +7428,7 @@ static int update_raid_disks(struct mddev *mddev, int raid_disks)
 	if (raid_disks <= 0 ||
 	    (mddev->max_disks && raid_disks >= mddev->max_disks))
 		return -EINVAL;
-	if (mddev->sync_thread ||
-	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
 	    test_bit(MD_RESYNCING_REMOTE, &mddev->recovery) ||
 	    mddev->reshape_position != MaxSector)
 		return -EBUSY;
@@ -7542,16 +7624,17 @@ static int md_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return 0;
 }
 
-static inline bool md_ioctl_valid(unsigned int cmd)
+static inline int md_ioctl_valid(unsigned int cmd)
 {
 	switch (cmd) {
-	case ADD_NEW_DISK:
 	case GET_ARRAY_INFO:
-	case GET_BITMAP_FILE:
 	case GET_DISK_INFO:
+	case RAID_VERSION:
+		return 0;
+	case ADD_NEW_DISK:
+	case GET_BITMAP_FILE:
 	case HOT_ADD_DISK:
 	case HOT_REMOVE_DISK:
-	case RAID_VERSION:
 	case RESTART_ARRAY_RW:
 	case RUN_ARRAY:
 	case SET_ARRAY_INFO:
@@ -7560,9 +7643,11 @@ static inline bool md_ioctl_valid(unsigned int cmd)
 	case STOP_ARRAY:
 	case STOP_ARRAY_RO:
 	case CLUSTERED_DISK_NACK:
-		return true;
+		if (!capable(CAP_SYS_ADMIN))
+			return -EACCES;
+		return 0;
 	default:
-		return false;
+		return -ENOTTY;
 	}
 }
 
@@ -7620,31 +7705,17 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
 	int err = 0;
 	void __user *argp = (void __user *)arg;
 	struct mddev *mddev = NULL;
-	bool did_set_md_closing = false;
-
-	if (!md_ioctl_valid(cmd))
-		return -ENOTTY;
 
-	switch (cmd) {
-	case RAID_VERSION:
-	case GET_ARRAY_INFO:
-	case GET_DISK_INFO:
-		break;
-	default:
-		if (!capable(CAP_SYS_ADMIN))
-			return -EACCES;
-	}
+	err = md_ioctl_valid(cmd);
+	if (err)
+		return err;
 
 	/*
 	 * Commands dealing with the RAID driver but not any
 	 * particular array:
 	 */
-	switch (cmd) {
-	case RAID_VERSION:
-		err = get_version(argp);
-		goto out;
-	default:;
-	}
+	if (cmd == RAID_VERSION)
+		return get_version(argp);
 
 	/*
 	 * Commands creating/starting a new array:
@@ -7652,35 +7723,23 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
 
 	mddev = bdev->bd_disk->private_data;
 
-	if (!mddev) {
-		BUG();
-		goto out;
-	}
-
 	/* Some actions do not requires the mutex */
 	switch (cmd) {
 	case GET_ARRAY_INFO:
 		if (!mddev->raid_disks && !mddev->external)
-			err = -ENODEV;
-		else
-			err = get_array_info(mddev, argp);
-		goto out;
+			return -ENODEV;
+		return get_array_info(mddev, argp);
 
 	case GET_DISK_INFO:
 		if (!mddev->raid_disks && !mddev->external)
-			err = -ENODEV;
-		else
-			err = get_disk_info(mddev, argp);
-		goto out;
+			return -ENODEV;
+		return get_disk_info(mddev, argp);
 
 	case SET_DISK_FAULTY:
-		err = set_disk_faulty(mddev, new_decode_dev(arg));
-		goto out;
+		return set_disk_faulty(mddev, new_decode_dev(arg));
 
 	case GET_BITMAP_FILE:
-		err = get_bitmap_file(mddev, argp);
-		goto out;
-
+		return get_bitmap_file(mddev, argp);
 	}
 
 	if (cmd == HOT_REMOVE_DISK)
@@ -7693,20 +7752,9 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
 		/* Need to flush page cache, and ensure no-one else opens
 		 * and writes
 		 */
-		mutex_lock(&mddev->open_mutex);
-		if (mddev->pers && atomic_read(&mddev->openers) > 1) {
-			mutex_unlock(&mddev->open_mutex);
-			err = -EBUSY;
-			goto out;
-		}
-		if (test_and_set_bit(MD_CLOSING, &mddev->flags)) {
-			mutex_unlock(&mddev->open_mutex);
-			err = -EBUSY;
-			goto out;
-		}
-		did_set_md_closing = true;
-		mutex_unlock(&mddev->open_mutex);
-		sync_blockdev(bdev);
+		err = mddev_set_closing_and_sync_blockdev(mddev, 1);
+		if (err)
+			return err;
 	}
 
 	if (!md_is_rdwr(mddev))
@@ -7747,11 +7795,12 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
 		goto unlock;
 
 	case STOP_ARRAY:
-		err = do_md_stop(mddev, 0, bdev);
+		err = do_md_stop(mddev, 0);
 		goto unlock;
 
 	case STOP_ARRAY_RO:
-		err = md_set_readonly(mddev, bdev);
+		if (mddev->pers)
+			err = md_set_readonly(mddev);
 		goto unlock;
 
 	case HOT_REMOVE_DISK:
@@ -7846,7 +7895,7 @@ unlock:
 				     mddev_unlock(mddev);
 
 out:
-	if(did_set_md_closing)
+	if (cmd == STOP_ARRAY_RO || (err && cmd == STOP_ARRAY))
 		clear_bit(MD_CLOSING, &mddev->flags);
 	return err;
 }
@@ -8132,6 +8181,19 @@ static void status_unused(struct seq_file *seq)
 	seq_printf(seq, "\n");
 }
 
+static void status_personalities(struct seq_file *seq)
+{
+	struct md_personality *pers;
+
+	seq_puts(seq, "Personalities : ");
+	spin_lock(&pers_lock);
+	list_for_each_entry(pers, &pers_list, list)
+		seq_printf(seq, "[%s] ", pers->name);
+
+	spin_unlock(&pers_lock);
+	seq_puts(seq, "\n");
+}
+
 static int status_resync(struct seq_file *seq, struct mddev *mddev)
 {
 	sector_t max_sectors, resync, res;
@@ -8273,20 +8335,10 @@ static int status_resync(struct seq_file *seq, struct mddev *mddev)
 static void *md_seq_start(struct seq_file *seq, loff_t *pos)
 	__acquires(&all_mddevs_lock)
 {
-	struct md_personality *pers;
-
-	seq_puts(seq, "Personalities : ");
-	spin_lock(&pers_lock);
-	list_for_each_entry(pers, &pers_list, list)
-		seq_printf(seq, "[%s] ", pers->name);
-
-	spin_unlock(&pers_lock);
-	seq_puts(seq, "\n");
 	seq->poll_event = atomic_read(&md_event_count);
-
 	spin_lock(&all_mddevs_lock);
 
-	return seq_list_start(&all_mddevs, *pos);
+	return seq_list_start_head(&all_mddevs, *pos);
 }
 
 static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos)
@@ -8297,16 +8349,23 @@ static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 static void md_seq_stop(struct seq_file *seq, void *v)
 	__releases(&all_mddevs_lock)
 {
-	status_unused(seq);
 	spin_unlock(&all_mddevs_lock);
 }
 
 static int md_seq_show(struct seq_file *seq, void *v)
 {
-	struct mddev *mddev = list_entry(v, struct mddev, all_mddevs);
+	struct mddev *mddev;
 	sector_t sectors;
 	struct md_rdev *rdev;
 
+	if (v == &all_mddevs) {
+		status_personalities(seq);
+		if (list_empty(&all_mddevs))
+			status_unused(seq);
+		return 0;
+	}
+
+	mddev = list_entry(v, struct mddev, all_mddevs);
 	if (!mddev_get(mddev))
 		return 0;
 
@@ -8382,6 +8441,10 @@ static int md_seq_show(struct seq_file *seq, void *v)
 	}
 	spin_unlock(&mddev->lock);
 	spin_lock(&all_mddevs_lock);
+
+	if (mddev == list_last_entry(&all_mddevs, struct mddev, all_mddevs))
+		status_unused(seq);
+
 	if (atomic_dec_and_test(&mddev->active))
 		__mddev_put(mddev);
 
@@ -8669,10 +8732,7 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 
 	bio_chain(discard_bio, bio);
 	bio_clone_blkg_association(discard_bio, bio);
-	if (mddev->gendisk)
-		trace_block_bio_remap(discard_bio,
-				disk_devt(mddev->gendisk),
-				bio->bi_iter.bi_sector);
+	mddev_trace_remap(mddev, discard_bio, bio->bi_iter.bi_sector);
 	submit_bio_noacct(discard_bio);
 }
 EXPORT_SYMBOL_GPL(md_submit_discard_bio);
@@ -8719,6 +8779,23 @@ void md_account_bio(struct mddev *mddev, struct bio **bio)
 }
 EXPORT_SYMBOL_GPL(md_account_bio);
 
+void md_free_cloned_bio(struct bio *bio)
+{
+	struct md_io_clone *md_io_clone = bio->bi_private;
+	struct bio *orig_bio = md_io_clone->orig_bio;
+	struct mddev *mddev = md_io_clone->mddev;
+
+	if (bio->bi_status && !orig_bio->bi_status)
+		orig_bio->bi_status = bio->bi_status;
+
+	if (md_io_clone->start_time)
+		bio_end_io_acct(orig_bio, md_io_clone->start_time);
+
+	bio_put(bio);
+	percpu_ref_put(&mddev->active_io);
+}
+EXPORT_SYMBOL_GPL(md_free_cloned_bio);
+
 /* md_allow_write(mddev)
  * Calling this ensures that the array is marked 'active' so that writes
  * may proceed without blocking.  It is important to call this before
@@ -8774,12 +8851,16 @@ void md_do_sync(struct md_thread *thread)
 	int ret;
 
 	/* just incase thread restarts... */
-	if (test_bit(MD_RECOVERY_DONE, &mddev->recovery) ||
-	    test_bit(MD_RECOVERY_WAIT, &mddev->recovery))
+	if (test_bit(MD_RECOVERY_DONE, &mddev->recovery))
 		return;
-	if (!md_is_rdwr(mddev)) {/* never try to sync a read-only array */
+
+	if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
+		goto skip;
+
+	if (test_bit(MD_RECOVERY_WAIT, &mddev->recovery) ||
+	    !md_is_rdwr(mddev)) {/* never try to sync a read-only array */
 		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-		return;
+		goto skip;
 	}
 
 	if (mddev_is_clustered(mddev)) {
@@ -9148,7 +9229,7 @@ void md_do_sync(struct md_thread *thread)
 			mddev->delta_disks > 0 &&
 			mddev->pers->finish_reshape &&
 			mddev->pers->size &&
-			mddev->queue) {
+			!mddev_is_dm(mddev)) {
 		mddev_lock_nointr(mddev);
 		md_set_array_sectors(mddev, mddev->pers->size(mddev, 0, 0));
 		mddev_unlock(mddev);
@@ -9248,9 +9329,14 @@ static bool md_spares_need_change(struct mddev *mddev)
 {
 	struct md_rdev *rdev;
 
-	rdev_for_each(rdev, mddev)
-		if (rdev_removeable(rdev) || rdev_addable(rdev))
+	rcu_read_lock();
+	rdev_for_each_rcu(rdev, mddev) {
+		if (rdev_removeable(rdev) || rdev_addable(rdev)) {
+			rcu_read_unlock();
 			return true;
+		}
+	}
+	rcu_read_unlock();
 	return false;
 }
 
@@ -9354,13 +9440,19 @@ static void md_start_sync(struct work_struct *ws)
 	struct mddev *mddev = container_of(ws, struct mddev, sync_work);
 	int spares = 0;
 	bool suspend = false;
+	char *name;
 
-	if (md_spares_need_change(mddev))
+	/*
+	 * If reshape is still in progress, spares won't be added or removed
+	 * from conf until reshape is done.
+	 */
+	if (mddev->reshape_position == MaxSector &&
+	    md_spares_need_change(mddev)) {
 		suspend = true;
+		mddev_suspend(mddev, false);
+	}
 
-	suspend ? mddev_suspend_and_lock_nointr(mddev) :
-		  mddev_lock_nointr(mddev);
-
+	mddev_lock_nointr(mddev);
 	if (!md_is_rdwr(mddev)) {
 		/*
 		 * On a read-only array we can:
@@ -9386,8 +9478,10 @@ static void md_start_sync(struct work_struct *ws)
 	if (spares)
 		md_bitmap_write_all(mddev->bitmap);
 
+	name = test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) ?
+			"reshape" : "resync";
 	rcu_assign_pointer(mddev->sync_thread,
-			   md_register_thread(md_do_sync, mddev, "resync"));
+			   md_register_thread(md_do_sync, mddev, name));
 	if (!mddev->sync_thread) {
 		pr_warn("%s: could not start resync thread...\n",
 			mdname(mddev));
@@ -9431,6 +9525,20 @@ not_running:
 		sysfs_notify_dirent_safe(mddev->sysfs_action);
 }
 
+static void unregister_sync_thread(struct mddev *mddev)
+{
+	if (!test_bit(MD_RECOVERY_DONE, &mddev->recovery)) {
+		/* resync/recovery still happening */
+		clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+		return;
+	}
+
+	if (WARN_ON_ONCE(!mddev->sync_thread))
+		return;
+
+	md_reap_sync_thread(mddev);
+}
+
 /*
  * This routine is regularly called by all per-raid-array threads to
  * deal with generic issues like resync and super-block update.
@@ -9455,9 +9563,6 @@ not_running:
  */
 void md_check_recovery(struct mddev *mddev)
 {
-	if (READ_ONCE(mddev->suspended))
-		return;
-
 	if (mddev->bitmap)
 		md_bitmap_daemon_work(mddev);
 
@@ -9471,7 +9576,8 @@ void md_check_recovery(struct mddev *mddev)
 	}
 
 	if (!md_is_rdwr(mddev) &&
-	    !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
+	    !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) &&
+	    !test_bit(MD_RECOVERY_DONE, &mddev->recovery))
 		return;
 	if ( ! (
 		(mddev->sb_flags & ~ (1<<MD_SB_CHANGE_PENDING)) ||
@@ -9493,8 +9599,7 @@ void md_check_recovery(struct mddev *mddev)
 			struct md_rdev *rdev;
 
 			if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
-				/* sync_work already queued. */
-				clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+				unregister_sync_thread(mddev);
 				goto unlock;
 			}
 
@@ -9557,16 +9662,7 @@ void md_check_recovery(struct mddev *mddev)
 		 * still set.
 		 */
 		if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
-			if (!test_bit(MD_RECOVERY_DONE, &mddev->recovery)) {
-				/* resync/recovery still happening */
-				clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-				goto unlock;
-			}
-
-			if (WARN_ON_ONCE(!mddev->sync_thread))
-				goto unlock;
-
-			md_reap_sync_thread(mddev);
+			unregister_sync_thread(mddev);
 			goto unlock;
 		}
 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 8d881cc59799..097d9dbd69b8 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -18,6 +18,7 @@
 #include <linux/timer.h>
 #include <linux/wait.h>
 #include <linux/workqueue.h>
+#include <trace/events/block.h>
 #include "md-cluster.h"
 
 #define MaxSector (~(sector_t)0)
@@ -59,7 +60,7 @@ struct md_rdev {
 	 */
 	struct block_device *meta_bdev;
 	struct block_device *bdev;	/* block device handle */
-	struct bdev_handle *bdev_handle;	/* Handle from open for bdev */
+	struct file *bdev_file;		/* Handle from open for bdev */
 
 	struct page	*sb_page, *bb_page;
 	int		sb_loaded;
@@ -207,6 +208,7 @@ enum flag_bits {
 				 * check if there is collision between raid1
 				 * serial bios.
 				 */
+	Nonrot,			/* non-rotational device (SSD) */
 };
 
 static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors,
@@ -222,6 +224,16 @@ static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors,
 	}
 	return 0;
 }
+
+static inline int rdev_has_badblock(struct md_rdev *rdev, sector_t s,
+				    int sectors)
+{
+	sector_t first_bad;
+	int bad_sectors;
+
+	return is_badblock(rdev, s, sectors, &first_bad, &bad_sectors);
+}
+
 extern int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 			      int is_new);
 extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
@@ -468,7 +480,6 @@ struct mddev {
 	struct timer_list		safemode_timer;
 	struct percpu_ref		writes_pending;
 	int				sync_checkers;	/* # of threads checking writes_pending */
-	struct request_queue		*queue;	/* for plugging ... */
 
 	struct bitmap			*bitmap; /* the bitmap for the device */
 	struct {
@@ -558,6 +569,37 @@ enum recovery_flags {
 	MD_RESYNCING_REMOTE,	/* remote node is running resync thread */
 };
 
+enum md_ro_state {
+	MD_RDWR,
+	MD_RDONLY,
+	MD_AUTO_READ,
+	MD_MAX_STATE
+};
+
+static inline bool md_is_rdwr(struct mddev *mddev)
+{
+	return (mddev->ro == MD_RDWR);
+}
+
+static inline bool reshape_interrupted(struct mddev *mddev)
+{
+	/* reshape never start */
+	if (mddev->reshape_position == MaxSector)
+		return false;
+
+	/* interrupted */
+	if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+		return true;
+
+	/* running reshape will be interrupted soon. */
+	if (test_bit(MD_RECOVERY_WAIT, &mddev->recovery) ||
+	    test_bit(MD_RECOVERY_INTR, &mddev->recovery) ||
+	    test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
+		return true;
+
+	return false;
+}
+
 static inline int __must_check mddev_lock(struct mddev *mddev)
 {
 	return mutex_lock_interruptible(&mddev->reconfig_mutex);
@@ -617,6 +659,7 @@ struct md_personality
 	int (*start_reshape) (struct mddev *mddev);
 	void (*finish_reshape) (struct mddev *mddev);
 	void (*update_reshape_pos) (struct mddev *mddev);
+	void (*prepare_suspend) (struct mddev *mddev);
 	/* quiesce suspends or resumes internal processing.
 	 * 1 - stop new actions and wait for action io to complete
 	 * 0 - return to normal behaviour
@@ -750,6 +793,7 @@ extern void md_finish_reshape(struct mddev *mddev);
 void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 			struct bio *bio, sector_t start, sector_t size);
 void md_account_bio(struct mddev *mddev, struct bio **bio);
+void md_free_cloned_bio(struct bio *bio);
 
 extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio);
 extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
@@ -778,9 +822,12 @@ extern void md_stop_writes(struct mddev *mddev);
 extern int md_rdev_init(struct md_rdev *rdev);
 extern void md_rdev_clear(struct md_rdev *rdev);
 
-extern void md_handle_request(struct mddev *mddev, struct bio *bio);
+extern bool md_handle_request(struct mddev *mddev, struct bio *bio);
 extern int mddev_suspend(struct mddev *mddev, bool interruptible);
 extern void mddev_resume(struct mddev *mddev);
+extern void md_idle_sync_thread(struct mddev *mddev);
+extern void md_frozen_sync_thread(struct mddev *mddev);
+extern void md_unfrozen_sync_thread(struct mddev *mddev);
 
 extern void md_reload_sb(struct mddev *mddev, int raid_disk);
 extern void md_update_sb(struct mddev *mddev, int force);
@@ -821,7 +868,7 @@ static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio
 {
 	if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
 	    !bio->bi_bdev->bd_disk->queue->limits.max_write_zeroes_sectors)
-		mddev->queue->limits.max_write_zeroes_sectors = 0;
+		mddev->gendisk->queue->limits.max_write_zeroes_sectors = 0;
 }
 
 static inline int mddev_suspend_and_lock(struct mddev *mddev)
@@ -860,7 +907,31 @@ void md_autostart_arrays(int part);
 int md_set_array_info(struct mddev *mddev, struct mdu_array_info_s *info);
 int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info);
 int do_md_run(struct mddev *mddev);
+void mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim);
+int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev);
+void mddev_update_io_opt(struct mddev *mddev, unsigned int nr_stripes);
 
 extern const struct block_device_operations md_fops;
 
+/*
+ * MD devices can be used undeneath by DM, in which case ->gendisk is NULL.
+ */
+static inline bool mddev_is_dm(struct mddev *mddev)
+{
+	return !mddev->gendisk;
+}
+
+static inline void mddev_trace_remap(struct mddev *mddev, struct bio *bio,
+		sector_t sector)
+{
+	if (!mddev_is_dm(mddev))
+		trace_block_bio_remap(bio, disk_devt(mddev->gendisk), sector);
+}
+
+#define mddev_add_trace_msg(mddev, fmt, args...)			\
+do {									\
+	if (!mddev_is_dm(mddev))					\
+		blk_add_trace_msg((mddev)->gendisk->queue, fmt, ##args); \
+} while (0)
+
 #endif /* _MD_MD_H */
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index c50a7abda744..c5d4aeb68404 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -379,6 +379,19 @@ static void raid0_free(struct mddev *mddev, void *priv)
 	free_conf(mddev, conf);
 }
 
+static int raid0_set_limits(struct mddev *mddev)
+{
+	struct queue_limits lim;
+
+	blk_set_stacking_limits(&lim);
+	lim.max_hw_sectors = mddev->chunk_sectors;
+	lim.max_write_zeroes_sectors = mddev->chunk_sectors;
+	lim.io_min = mddev->chunk_sectors << 9;
+	lim.io_opt = lim.io_min * mddev->raid_disks;
+	mddev_stack_rdev_limits(mddev, &lim);
+	return queue_limits_set(mddev->gendisk->queue, &lim);
+}
+
 static int raid0_run(struct mddev *mddev)
 {
 	struct r0conf *conf;
@@ -399,20 +412,10 @@ static int raid0_run(struct mddev *mddev)
 		mddev->private = conf;
 	}
 	conf = mddev->private;
-	if (mddev->queue) {
-		struct md_rdev *rdev;
-
-		blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
-		blk_queue_max_write_zeroes_sectors(mddev->queue, mddev->chunk_sectors);
-
-		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
-		blk_queue_io_opt(mddev->queue,
-				 (mddev->chunk_sectors << 9) * mddev->raid_disks);
-
-		rdev_for_each(rdev, mddev) {
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-		}
+	if (!mddev_is_dm(mddev)) {
+		ret = raid0_set_limits(mddev);
+		if (ret)
+			goto out_free_conf;
 	}
 
 	/* calculate array device size */
@@ -426,8 +429,10 @@ static int raid0_run(struct mddev *mddev)
 
 	ret = md_integrity_register(mddev);
 	if (ret)
-		free_conf(mddev, conf);
-
+		goto out_free_conf;
+	return 0;
+out_free_conf:
+	free_conf(mddev, conf);
 	return ret;
 }
 
@@ -578,10 +583,7 @@ static void raid0_map_submit_bio(struct mddev *mddev, struct bio *bio)
 	bio_set_dev(bio, tmp_dev->bdev);
 	bio->bi_iter.bi_sector = sector + zone->dev_start +
 		tmp_dev->data_offset;
-
-	if (mddev->gendisk)
-		trace_block_bio_remap(bio, disk_devt(mddev->gendisk),
-				      bio_sector);
+	mddev_trace_remap(mddev, bio, bio_sector);
 	mddev_check_write_zeroes(mddev, bio);
 	submit_bio_noacct(bio);
 }
diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c
index 512746551f36..2ea1710a3b70 100644
--- a/drivers/md/raid1-10.c
+++ b/drivers/md/raid1-10.c
@@ -227,3 +227,72 @@ static inline bool exceed_read_errors(struct mddev *mddev, struct md_rdev *rdev)
 
 	return false;
 }
+
+/**
+ * raid1_check_read_range() - check a given read range for bad blocks,
+ * available read length is returned;
+ * @rdev: the rdev to read;
+ * @this_sector: read position;
+ * @len: read length;
+ *
+ * helper function for read_balance()
+ *
+ * 1) If there are no bad blocks in the range, @len is returned;
+ * 2) If the range are all bad blocks, 0 is returned;
+ * 3) If there are partial bad blocks:
+ *  - If the bad block range starts after @this_sector, the length of first
+ *  good region is returned;
+ *  - If the bad block range starts before @this_sector, 0 is returned and
+ *  the @len is updated to the offset into the region before we get to the
+ *  good blocks;
+ */
+static inline int raid1_check_read_range(struct md_rdev *rdev,
+					 sector_t this_sector, int *len)
+{
+	sector_t first_bad;
+	int bad_sectors;
+
+	/* no bad block overlap */
+	if (!is_badblock(rdev, this_sector, *len, &first_bad, &bad_sectors))
+		return *len;
+
+	/*
+	 * bad block range starts offset into our range so we can return the
+	 * number of sectors before the bad blocks start.
+	 */
+	if (first_bad > this_sector)
+		return first_bad - this_sector;
+
+	/* read range is fully consumed by bad blocks. */
+	if (this_sector + *len <= first_bad + bad_sectors)
+		return 0;
+
+	/*
+	 * final case, bad block range starts before or at the start of our
+	 * range but does not cover our entire range so we still return 0 but
+	 * update the length with the number of sectors before we get to the
+	 * good ones.
+	 */
+	*len = first_bad + bad_sectors - this_sector;
+	return 0;
+}
+
+/*
+ * Check if read should choose the first rdev.
+ *
+ * Balance on the whole device if no resync is going on (recovery is ok) or
+ * below the resync window. Otherwise, take the first readable disk.
+ */
+static inline bool raid1_should_read_first(struct mddev *mddev,
+					   sector_t this_sector, int len)
+{
+	if ((mddev->recovery_cp < this_sector + len))
+		return true;
+
+	if (mddev_is_clustered(mddev) &&
+	    md_cluster_ops->area_resyncing(mddev, READ, this_sector,
+					   this_sector + len))
+		return true;
+
+	return false;
+}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index aaa434f0c175..be8ac24f50b6 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -46,9 +46,6 @@
 static void allow_barrier(struct r1conf *conf, sector_t sector_nr);
 static void lower_barrier(struct r1conf *conf, sector_t sector_nr);
 
-#define raid1_log(md, fmt, args...)				\
-	do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid1 " fmt, ##args); } while (0)
-
 #define RAID_1_10_NAME "raid1"
 #include "raid1-10.c"
 
@@ -498,9 +495,6 @@ static void raid1_end_write_request(struct bio *bio)
 		 * to user-side. So if something waits for IO, then it
 		 * will wait for the 'master' bio.
 		 */
-		sector_t first_bad;
-		int bad_sectors;
-
 		r1_bio->bios[mirror] = NULL;
 		to_put = bio;
 		/*
@@ -516,8 +510,8 @@ static void raid1_end_write_request(struct bio *bio)
 			set_bit(R1BIO_Uptodate, &r1_bio->state);
 
 		/* Maybe we can clear some bad blocks. */
-		if (is_badblock(rdev, r1_bio->sector, r1_bio->sectors,
-				&first_bad, &bad_sectors) && !discard_error) {
+		if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors) &&
+		    !discard_error) {
 			r1_bio->bios[mirror] = IO_MADE_GOOD;
 			set_bit(R1BIO_MadeGood, &r1_bio->state);
 		}
@@ -582,211 +576,312 @@ static sector_t align_to_barrier_unit_end(sector_t start_sector,
 	return len;
 }
 
-/*
- * This routine returns the disk from which the requested read should
- * be done. There is a per-array 'next expected sequential IO' sector
- * number - if this matches on the next IO then we use the last disk.
- * There is also a per-disk 'last know head position' sector that is
- * maintained from IRQ contexts, both the normal and the resync IO
- * completion handlers update this position correctly. If there is no
- * perfect sequential match then we pick the disk whose head is closest.
- *
- * If there are 2 mirrors in the same 2 devices, performance degrades
- * because position is mirror, not device based.
- *
- * The rdev for the device selected will have nr_pending incremented.
- */
-static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sectors)
+static void update_read_sectors(struct r1conf *conf, int disk,
+				sector_t this_sector, int len)
 {
-	const sector_t this_sector = r1_bio->sector;
-	int sectors;
-	int best_good_sectors;
-	int best_disk, best_dist_disk, best_pending_disk;
-	int has_nonrot_disk;
+	struct raid1_info *info = &conf->mirrors[disk];
+
+	atomic_inc(&info->rdev->nr_pending);
+	if (info->next_seq_sect != this_sector)
+		info->seq_start = this_sector;
+	info->next_seq_sect = this_sector + len;
+}
+
+static int choose_first_rdev(struct r1conf *conf, struct r1bio *r1_bio,
+			     int *max_sectors)
+{
+	sector_t this_sector = r1_bio->sector;
+	int len = r1_bio->sectors;
 	int disk;
-	sector_t best_dist;
-	unsigned int min_pending;
-	struct md_rdev *rdev;
-	int choose_first;
-	int choose_next_idle;
 
-	/*
-	 * Check if we can balance. We can balance on the whole
-	 * device if no resync is going on, or below the resync window.
-	 * We take the first readable disk when above the resync window.
-	 */
- retry:
-	sectors = r1_bio->sectors;
-	best_disk = -1;
-	best_dist_disk = -1;
-	best_dist = MaxSector;
-	best_pending_disk = -1;
-	min_pending = UINT_MAX;
-	best_good_sectors = 0;
-	has_nonrot_disk = 0;
-	choose_next_idle = 0;
-	clear_bit(R1BIO_FailFast, &r1_bio->state);
+	for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
+		struct md_rdev *rdev;
+		int read_len;
 
-	if ((conf->mddev->recovery_cp < this_sector + sectors) ||
-	    (mddev_is_clustered(conf->mddev) &&
-	    md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector,
-		    this_sector + sectors)))
-		choose_first = 1;
-	else
-		choose_first = 0;
+		if (r1_bio->bios[disk] == IO_BLOCKED)
+			continue;
+
+		rdev = conf->mirrors[disk].rdev;
+		if (!rdev || test_bit(Faulty, &rdev->flags))
+			continue;
+
+		/* choose the first disk even if it has some bad blocks. */
+		read_len = raid1_check_read_range(rdev, this_sector, &len);
+		if (read_len > 0) {
+			update_read_sectors(conf, disk, this_sector, read_len);
+			*max_sectors = read_len;
+			return disk;
+		}
+	}
+
+	return -1;
+}
+
+static int choose_bb_rdev(struct r1conf *conf, struct r1bio *r1_bio,
+			  int *max_sectors)
+{
+	sector_t this_sector = r1_bio->sector;
+	int best_disk = -1;
+	int best_len = 0;
+	int disk;
 
 	for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
-		sector_t dist;
-		sector_t first_bad;
-		int bad_sectors;
-		unsigned int pending;
-		bool nonrot;
+		struct md_rdev *rdev;
+		int len;
+		int read_len;
+
+		if (r1_bio->bios[disk] == IO_BLOCKED)
+			continue;
 
 		rdev = conf->mirrors[disk].rdev;
-		if (r1_bio->bios[disk] == IO_BLOCKED
-		    || rdev == NULL
-		    || test_bit(Faulty, &rdev->flags))
+		if (!rdev || test_bit(Faulty, &rdev->flags) ||
+		    test_bit(WriteMostly, &rdev->flags))
 			continue;
-		if (!test_bit(In_sync, &rdev->flags) &&
-		    rdev->recovery_offset < this_sector + sectors)
+
+		/* keep track of the disk with the most readable sectors. */
+		len = r1_bio->sectors;
+		read_len = raid1_check_read_range(rdev, this_sector, &len);
+		if (read_len > best_len) {
+			best_disk = disk;
+			best_len = read_len;
+		}
+	}
+
+	if (best_disk != -1) {
+		*max_sectors = best_len;
+		update_read_sectors(conf, best_disk, this_sector, best_len);
+	}
+
+	return best_disk;
+}
+
+static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio,
+			    int *max_sectors)
+{
+	sector_t this_sector = r1_bio->sector;
+	int bb_disk = -1;
+	int bb_read_len = 0;
+	int disk;
+
+	for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
+		struct md_rdev *rdev;
+		int len;
+		int read_len;
+
+		if (r1_bio->bios[disk] == IO_BLOCKED)
 			continue;
-		if (test_bit(WriteMostly, &rdev->flags)) {
-			/* Don't balance among write-mostly, just
-			 * use the first as a last resort */
-			if (best_dist_disk < 0) {
-				if (is_badblock(rdev, this_sector, sectors,
-						&first_bad, &bad_sectors)) {
-					if (first_bad <= this_sector)
-						/* Cannot use this */
-						continue;
-					best_good_sectors = first_bad - this_sector;
-				} else
-					best_good_sectors = sectors;
-				best_dist_disk = disk;
-				best_pending_disk = disk;
-			}
+
+		rdev = conf->mirrors[disk].rdev;
+		if (!rdev || test_bit(Faulty, &rdev->flags) ||
+		    !test_bit(WriteMostly, &rdev->flags))
 			continue;
+
+		/* there are no bad blocks, we can use this disk */
+		len = r1_bio->sectors;
+		read_len = raid1_check_read_range(rdev, this_sector, &len);
+		if (read_len == r1_bio->sectors) {
+			update_read_sectors(conf, disk, this_sector, read_len);
+			return disk;
 		}
-		/* This is a reasonable device to use.  It might
-		 * even be best.
+
+		/*
+		 * there are partial bad blocks, choose the rdev with largest
+		 * read length.
 		 */
-		if (is_badblock(rdev, this_sector, sectors,
-				&first_bad, &bad_sectors)) {
-			if (best_dist < MaxSector)
-				/* already have a better device */
-				continue;
-			if (first_bad <= this_sector) {
-				/* cannot read here. If this is the 'primary'
-				 * device, then we must not read beyond
-				 * bad_sectors from another device..
-				 */
-				bad_sectors -= (this_sector - first_bad);
-				if (choose_first && sectors > bad_sectors)
-					sectors = bad_sectors;
-				if (best_good_sectors > sectors)
-					best_good_sectors = sectors;
-
-			} else {
-				sector_t good_sectors = first_bad - this_sector;
-				if (good_sectors > best_good_sectors) {
-					best_good_sectors = good_sectors;
-					best_disk = disk;
-				}
-				if (choose_first)
-					break;
-			}
-			continue;
-		} else {
-			if ((sectors > best_good_sectors) && (best_disk >= 0))
-				best_disk = -1;
-			best_good_sectors = sectors;
+		if (read_len > bb_read_len) {
+			bb_disk = disk;
+			bb_read_len = read_len;
 		}
+	}
+
+	if (bb_disk != -1) {
+		*max_sectors = bb_read_len;
+		update_read_sectors(conf, bb_disk, this_sector, bb_read_len);
+	}
+
+	return bb_disk;
+}
+
+static bool is_sequential(struct r1conf *conf, int disk, struct r1bio *r1_bio)
+{
+	/* TODO: address issues with this check and concurrency. */
+	return conf->mirrors[disk].next_seq_sect == r1_bio->sector ||
+	       conf->mirrors[disk].head_position == r1_bio->sector;
+}
+
+/*
+ * If buffered sequential IO size exceeds optimal iosize, check if there is idle
+ * disk. If yes, choose the idle disk.
+ */
+static bool should_choose_next(struct r1conf *conf, int disk)
+{
+	struct raid1_info *mirror = &conf->mirrors[disk];
+	int opt_iosize;
+
+	if (!test_bit(Nonrot, &mirror->rdev->flags))
+		return false;
+
+	opt_iosize = bdev_io_opt(mirror->rdev->bdev) >> 9;
+	return opt_iosize > 0 && mirror->seq_start != MaxSector &&
+	       mirror->next_seq_sect > opt_iosize &&
+	       mirror->next_seq_sect - opt_iosize >= mirror->seq_start;
+}
+
+static bool rdev_readable(struct md_rdev *rdev, struct r1bio *r1_bio)
+{
+	if (!rdev || test_bit(Faulty, &rdev->flags))
+		return false;
+
+	/* still in recovery */
+	if (!test_bit(In_sync, &rdev->flags) &&
+	    rdev->recovery_offset < r1_bio->sector + r1_bio->sectors)
+		return false;
+
+	/* don't read from slow disk unless have to */
+	if (test_bit(WriteMostly, &rdev->flags))
+		return false;
+
+	/* don't split IO for bad blocks unless have to */
+	if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors))
+		return false;
+
+	return true;
+}
+
+struct read_balance_ctl {
+	sector_t closest_dist;
+	int closest_dist_disk;
+	int min_pending;
+	int min_pending_disk;
+	int sequential_disk;
+	int readable_disks;
+};
+
+static int choose_best_rdev(struct r1conf *conf, struct r1bio *r1_bio)
+{
+	int disk;
+	struct read_balance_ctl ctl = {
+		.closest_dist_disk      = -1,
+		.closest_dist           = MaxSector,
+		.min_pending_disk       = -1,
+		.min_pending            = UINT_MAX,
+		.sequential_disk	= -1,
+	};
+
+	for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
+		struct md_rdev *rdev;
+		sector_t dist;
+		unsigned int pending;
 
-		if (best_disk >= 0)
-			/* At least two disks to choose from so failfast is OK */
+		if (r1_bio->bios[disk] == IO_BLOCKED)
+			continue;
+
+		rdev = conf->mirrors[disk].rdev;
+		if (!rdev_readable(rdev, r1_bio))
+			continue;
+
+		/* At least two disks to choose from so failfast is OK */
+		if (ctl.readable_disks++ == 1)
 			set_bit(R1BIO_FailFast, &r1_bio->state);
 
-		nonrot = bdev_nonrot(rdev->bdev);
-		has_nonrot_disk |= nonrot;
 		pending = atomic_read(&rdev->nr_pending);
-		dist = abs(this_sector - conf->mirrors[disk].head_position);
-		if (choose_first) {
-			best_disk = disk;
-			break;
-		}
+		dist = abs(r1_bio->sector - conf->mirrors[disk].head_position);
+
 		/* Don't change to another disk for sequential reads */
-		if (conf->mirrors[disk].next_seq_sect == this_sector
-		    || dist == 0) {
-			int opt_iosize = bdev_io_opt(rdev->bdev) >> 9;
-			struct raid1_info *mirror = &conf->mirrors[disk];
+		if (is_sequential(conf, disk, r1_bio)) {
+			if (!should_choose_next(conf, disk))
+				return disk;
 
-			best_disk = disk;
 			/*
-			 * If buffered sequential IO size exceeds optimal
-			 * iosize, check if there is idle disk. If yes, choose
-			 * the idle disk. read_balance could already choose an
-			 * idle disk before noticing it's a sequential IO in
-			 * this disk. This doesn't matter because this disk
-			 * will idle, next time it will be utilized after the
-			 * first disk has IO size exceeds optimal iosize. In
-			 * this way, iosize of the first disk will be optimal
-			 * iosize at least. iosize of the second disk might be
-			 * small, but not a big deal since when the second disk
-			 * starts IO, the first disk is likely still busy.
+			 * Add 'pending' to avoid choosing this disk if
+			 * there is other idle disk.
 			 */
-			if (nonrot && opt_iosize > 0 &&
-			    mirror->seq_start != MaxSector &&
-			    mirror->next_seq_sect > opt_iosize &&
-			    mirror->next_seq_sect - opt_iosize >=
-			    mirror->seq_start) {
-				choose_next_idle = 1;
-				continue;
-			}
-			break;
+			pending++;
+			/*
+			 * If there is no other idle disk, this disk
+			 * will be chosen.
+			 */
+			ctl.sequential_disk = disk;
 		}
 
-		if (choose_next_idle)
-			continue;
-
-		if (min_pending > pending) {
-			min_pending = pending;
-			best_pending_disk = disk;
+		if (ctl.min_pending > pending) {
+			ctl.min_pending = pending;
+			ctl.min_pending_disk = disk;
 		}
 
-		if (dist < best_dist) {
-			best_dist = dist;
-			best_dist_disk = disk;
+		if (ctl.closest_dist > dist) {
+			ctl.closest_dist = dist;
+			ctl.closest_dist_disk = disk;
 		}
 	}
 
 	/*
+	 * sequential IO size exceeds optimal iosize, however, there is no other
+	 * idle disk, so choose the sequential disk.
+	 */
+	if (ctl.sequential_disk != -1 && ctl.min_pending != 0)
+		return ctl.sequential_disk;
+
+	/*
 	 * If all disks are rotational, choose the closest disk. If any disk is
 	 * non-rotational, choose the disk with less pending request even the
 	 * disk is rotational, which might/might not be optimal for raids with
 	 * mixed ratation/non-rotational disks depending on workload.
 	 */
-	if (best_disk == -1) {
-		if (has_nonrot_disk || min_pending == 0)
-			best_disk = best_pending_disk;
-		else
-			best_disk = best_dist_disk;
-	}
+	if (ctl.min_pending_disk != -1 &&
+	    (READ_ONCE(conf->nonrot_disks) || ctl.min_pending == 0))
+		return ctl.min_pending_disk;
+	else
+		return ctl.closest_dist_disk;
+}
 
-	if (best_disk >= 0) {
-		rdev = conf->mirrors[best_disk].rdev;
-		if (!rdev)
-			goto retry;
-		atomic_inc(&rdev->nr_pending);
-		sectors = best_good_sectors;
+/*
+ * This routine returns the disk from which the requested read should be done.
+ *
+ * 1) If resync is in progress, find the first usable disk and use it even if it
+ * has some bad blocks.
+ *
+ * 2) Now that there is no resync, loop through all disks and skipping slow
+ * disks and disks with bad blocks for now. Only pay attention to key disk
+ * choice.
+ *
+ * 3) If we've made it this far, now look for disks with bad blocks and choose
+ * the one with most number of sectors.
+ *
+ * 4) If we are all the way at the end, we have no choice but to use a disk even
+ * if it is write mostly.
+ *
+ * The rdev for the device selected will have nr_pending incremented.
+ */
+static int read_balance(struct r1conf *conf, struct r1bio *r1_bio,
+			int *max_sectors)
+{
+	int disk;
 
-		if (conf->mirrors[best_disk].next_seq_sect != this_sector)
-			conf->mirrors[best_disk].seq_start = this_sector;
+	clear_bit(R1BIO_FailFast, &r1_bio->state);
+
+	if (raid1_should_read_first(conf->mddev, r1_bio->sector,
+				    r1_bio->sectors))
+		return choose_first_rdev(conf, r1_bio, max_sectors);
 
-		conf->mirrors[best_disk].next_seq_sect = this_sector + sectors;
+	disk = choose_best_rdev(conf, r1_bio);
+	if (disk >= 0) {
+		*max_sectors = r1_bio->sectors;
+		update_read_sectors(conf, disk, r1_bio->sector,
+				    r1_bio->sectors);
+		return disk;
 	}
-	*max_sectors = sectors;
 
-	return best_disk;
+	/*
+	 * If we are here it means we didn't find a perfectly good disk so
+	 * now spend a bit more time trying to find one with the most good
+	 * sectors.
+	 */
+	disk = choose_bb_rdev(conf, r1_bio, max_sectors);
+	if (disk >= 0)
+		return disk;
+
+	return choose_slow_rdev(conf, r1_bio, max_sectors);
 }
 
 static void wake_up_barrier(struct r1conf *conf)
@@ -1098,7 +1193,7 @@ static void freeze_array(struct r1conf *conf, int extra)
 	 */
 	spin_lock_irq(&conf->resync_lock);
 	conf->array_frozen = 1;
-	raid1_log(conf->mddev, "wait freeze");
+	mddev_add_trace_msg(conf->mddev, "raid1 wait freeze");
 	wait_event_lock_irq_cmd(
 		conf->wait_barrier,
 		get_unqueued_pending(conf) == extra,
@@ -1287,7 +1382,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 		 * Reading from a write-mostly device must take care not to
 		 * over-take any writes that are 'behind'
 		 */
-		raid1_log(mddev, "wait behind writes");
+		mddev_add_trace_msg(mddev, "raid1 wait behind writes");
 		wait_event(bitmap->behind_wait,
 			   atomic_read(&bitmap->behind_writes) == 0);
 	}
@@ -1320,11 +1415,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	    test_bit(R1BIO_FailFast, &r1_bio->state))
 	        read_bio->bi_opf |= MD_FAILFAST;
 	read_bio->bi_private = r1_bio;
-
-	if (mddev->gendisk)
-	        trace_block_bio_remap(read_bio, disk_devt(mddev->gendisk),
-				      r1_bio->sector);
-
+	mddev_trace_remap(mddev, read_bio, r1_bio->sector);
 	submit_bio_noacct(read_bio);
 }
 
@@ -1474,7 +1565,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			bio_wouldblock_error(bio);
 			return;
 		}
-		raid1_log(mddev, "wait rdev %d blocked", blocked_rdev->raid_disk);
+		mddev_add_trace_msg(mddev, "raid1 wait rdev %d blocked",
+				blocked_rdev->raid_disk);
 		md_wait_for_blocked_rdev(blocked_rdev, mddev);
 		wait_barrier(conf, bio->bi_iter.bi_sector, false);
 		goto retry_write;
@@ -1557,10 +1649,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		mbio->bi_private = r1_bio;
 
 		atomic_inc(&r1_bio->remaining);
-
-		if (mddev->gendisk)
-			trace_block_bio_remap(mbio, disk_devt(mddev->gendisk),
-					      r1_bio->sector);
+		mddev_trace_remap(mddev, mbio, r1_bio->sector);
 		/* flush_pending_writes() needs access to the rdev so...*/
 		mbio->bi_bdev = (void *)rdev;
 		if (!raid1_add_bio_to_plug(mddev, mbio, raid1_unplug, disks)) {
@@ -1760,6 +1849,52 @@ static int raid1_spare_active(struct mddev *mddev)
 	return count;
 }
 
+static bool raid1_add_conf(struct r1conf *conf, struct md_rdev *rdev, int disk,
+			   bool replacement)
+{
+	struct raid1_info *info = conf->mirrors + disk;
+
+	if (replacement)
+		info += conf->raid_disks;
+
+	if (info->rdev)
+		return false;
+
+	if (bdev_nonrot(rdev->bdev)) {
+		set_bit(Nonrot, &rdev->flags);
+		WRITE_ONCE(conf->nonrot_disks, conf->nonrot_disks + 1);
+	}
+
+	rdev->raid_disk = disk;
+	info->head_position = 0;
+	info->seq_start = MaxSector;
+	WRITE_ONCE(info->rdev, rdev);
+
+	return true;
+}
+
+static bool raid1_remove_conf(struct r1conf *conf, int disk)
+{
+	struct raid1_info *info = conf->mirrors + disk;
+	struct md_rdev *rdev = info->rdev;
+
+	if (!rdev || test_bit(In_sync, &rdev->flags) ||
+	    atomic_read(&rdev->nr_pending))
+		return false;
+
+	/* Only remove non-faulty devices if recovery is not possible. */
+	if (!test_bit(Faulty, &rdev->flags) &&
+	    rdev->mddev->recovery_disabled != conf->recovery_disabled &&
+	    rdev->mddev->degraded < conf->raid_disks)
+		return false;
+
+	if (test_and_clear_bit(Nonrot, &rdev->flags))
+		WRITE_ONCE(conf->nonrot_disks, conf->nonrot_disks - 1);
+
+	WRITE_ONCE(info->rdev, NULL);
+	return true;
+}
+
 static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct r1conf *conf = mddev->private;
@@ -1791,19 +1926,16 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	for (mirror = first; mirror <= last; mirror++) {
 		p = conf->mirrors + mirror;
 		if (!p->rdev) {
-			if (mddev->gendisk)
-				disk_stack_limits(mddev->gendisk, rdev->bdev,
-						  rdev->data_offset << 9);
+			err = mddev_stack_new_rdev(mddev, rdev);
+			if (err)
+				return err;
 
-			p->head_position = 0;
-			rdev->raid_disk = mirror;
-			err = 0;
+			raid1_add_conf(conf, rdev, mirror, false);
 			/* As all devices are equivalent, we don't need a full recovery
 			 * if this was recently any drive of the array
 			 */
 			if (rdev->saved_raid_disk < 0)
 				conf->fullsync = 1;
-			WRITE_ONCE(p->rdev, rdev);
 			break;
 		}
 		if (test_bit(WantReplacement, &p->rdev->flags) &&
@@ -1813,13 +1945,11 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 
 	if (err && repl_slot >= 0) {
 		/* Add this device as a replacement */
-		p = conf->mirrors + repl_slot;
 		clear_bit(In_sync, &rdev->flags);
 		set_bit(Replacement, &rdev->flags);
-		rdev->raid_disk = repl_slot;
+		raid1_add_conf(conf, rdev, repl_slot, true);
 		err = 0;
 		conf->fullsync = 1;
-		WRITE_ONCE(p[conf->raid_disks].rdev, rdev);
 	}
 
 	print_conf(conf);
@@ -1836,27 +1966,20 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 	if (unlikely(number >= conf->raid_disks))
 		goto abort;
 
-	if (rdev != p->rdev)
-		p = conf->mirrors + conf->raid_disks + number;
+	if (rdev != p->rdev) {
+		number += conf->raid_disks;
+		p = conf->mirrors + number;
+	}
 
 	print_conf(conf);
 	if (rdev == p->rdev) {
-		if (test_bit(In_sync, &rdev->flags) ||
-		    atomic_read(&rdev->nr_pending)) {
+		if (!raid1_remove_conf(conf, number)) {
 			err = -EBUSY;
 			goto abort;
 		}
-		/* Only remove non-faulty devices if recovery
-		 * is not possible.
-		 */
-		if (!test_bit(Faulty, &rdev->flags) &&
-		    mddev->recovery_disabled != conf->recovery_disabled &&
-		    mddev->degraded < conf->raid_disks) {
-			err = -EBUSY;
-			goto abort;
-		}
-		WRITE_ONCE(p->rdev, NULL);
-		if (conf->mirrors[conf->raid_disks + number].rdev) {
+
+		if (number < conf->raid_disks &&
+		    conf->mirrors[conf->raid_disks + number].rdev) {
 			/* We just removed a device that is being replaced.
 			 * Move down the replacement.  We drain all IO before
 			 * doing this to avoid confusion.
@@ -1944,8 +2067,6 @@ static void end_sync_write(struct bio *bio)
 	struct r1bio *r1_bio = get_resync_r1bio(bio);
 	struct mddev *mddev = r1_bio->mddev;
 	struct r1conf *conf = mddev->private;
-	sector_t first_bad;
-	int bad_sectors;
 	struct md_rdev *rdev = conf->mirrors[find_bio_disk(r1_bio, bio)].rdev;
 
 	if (!uptodate) {
@@ -1955,25 +2076,22 @@ static void end_sync_write(struct bio *bio)
 			set_bit(MD_RECOVERY_NEEDED, &
 				mddev->recovery);
 		set_bit(R1BIO_WriteError, &r1_bio->state);
-	} else if (is_badblock(rdev, r1_bio->sector, r1_bio->sectors,
-			       &first_bad, &bad_sectors) &&
-		   !is_badblock(conf->mirrors[r1_bio->read_disk].rdev,
-				r1_bio->sector,
-				r1_bio->sectors,
-				&first_bad, &bad_sectors)
-		)
+	} else if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors) &&
+		   !rdev_has_badblock(conf->mirrors[r1_bio->read_disk].rdev,
+				      r1_bio->sector, r1_bio->sectors)) {
 		set_bit(R1BIO_MadeGood, &r1_bio->state);
+	}
 
 	put_sync_write_buf(r1_bio, uptodate);
 }
 
 static int r1_sync_page_io(struct md_rdev *rdev, sector_t sector,
-			   int sectors, struct page *page, int rw)
+			   int sectors, struct page *page, blk_opf_t rw)
 {
 	if (sync_page_io(rdev, sector, sectors << 9, page, rw, false))
 		/* success */
 		return 1;
-	if (rw == WRITE) {
+	if (rw == REQ_OP_WRITE) {
 		set_bit(WriteErrorSeen, &rdev->flags);
 		if (!test_and_set_bit(WantReplacement,
 				      &rdev->flags))
@@ -2090,7 +2208,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
 			rdev = conf->mirrors[d].rdev;
 			if (r1_sync_page_io(rdev, sect, s,
 					    pages[idx],
-					    WRITE) == 0) {
+					    REQ_OP_WRITE) == 0) {
 				r1_bio->bios[d]->bi_end_io = NULL;
 				rdev_dec_pending(rdev, mddev);
 			}
@@ -2105,7 +2223,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
 			rdev = conf->mirrors[d].rdev;
 			if (r1_sync_page_io(rdev, sect, s,
 					    pages[idx],
-					    READ) != 0)
+					    REQ_OP_READ) != 0)
 				atomic_add(s, &rdev->corrected_errors);
 		}
 		sectors -= s;
@@ -2262,7 +2380,7 @@ static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 	int sectors = r1_bio->sectors;
 	int read_disk = r1_bio->read_disk;
 	struct mddev *mddev = conf->mddev;
-	struct md_rdev *rdev = rcu_dereference(conf->mirrors[read_disk].rdev);
+	struct md_rdev *rdev = conf->mirrors[read_disk].rdev;
 
 	if (exceed_read_errors(mddev, rdev)) {
 		r1_bio->bios[r1_bio->read_disk] = IO_BLOCKED;
@@ -2279,16 +2397,12 @@ static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 			s = PAGE_SIZE >> 9;
 
 		do {
-			sector_t first_bad;
-			int bad_sectors;
-
 			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
 			    (test_bit(In_sync, &rdev->flags) ||
 			     (!test_bit(Faulty, &rdev->flags) &&
 			      rdev->recovery_offset >= sect + s)) &&
-			    is_badblock(rdev, sect, s,
-					&first_bad, &bad_sectors) == 0) {
+			    rdev_has_badblock(rdev, sect, s) == 0) {
 				atomic_inc(&rdev->nr_pending);
 				if (sync_page_io(rdev, sect, s<<9,
 					 conf->tmppage, REQ_OP_READ, false))
@@ -2321,7 +2435,7 @@ static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 			    !test_bit(Faulty, &rdev->flags)) {
 				atomic_inc(&rdev->nr_pending);
 				r1_sync_page_io(rdev, sect, s,
-						conf->tmppage, WRITE);
+						conf->tmppage, REQ_OP_WRITE);
 				rdev_dec_pending(rdev, mddev);
 			}
 		}
@@ -2335,7 +2449,7 @@ static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 			    !test_bit(Faulty, &rdev->flags)) {
 				atomic_inc(&rdev->nr_pending);
 				if (r1_sync_page_io(rdev, sect, s,
-						    conf->tmppage, READ)) {
+						conf->tmppage, REQ_OP_READ)) {
 					atomic_add(s, &rdev->corrected_errors);
 					pr_info("md/raid1:%s: read error corrected (%d sectors at %llu on %pg)\n",
 						mdname(mddev), s,
@@ -3006,23 +3120,17 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 
 	err = -EINVAL;
 	spin_lock_init(&conf->device_lock);
+	conf->raid_disks = mddev->raid_disks;
 	rdev_for_each(rdev, mddev) {
 		int disk_idx = rdev->raid_disk;
-		if (disk_idx >= mddev->raid_disks
-		    || disk_idx < 0)
+
+		if (disk_idx >= conf->raid_disks || disk_idx < 0)
 			continue;
-		if (test_bit(Replacement, &rdev->flags))
-			disk = conf->mirrors + mddev->raid_disks + disk_idx;
-		else
-			disk = conf->mirrors + disk_idx;
 
-		if (disk->rdev)
+		if (!raid1_add_conf(conf, rdev, disk_idx,
+				    test_bit(Replacement, &rdev->flags)))
 			goto abort;
-		disk->rdev = rdev;
-		disk->head_position = 0;
-		disk->seq_start = MaxSector;
 	}
-	conf->raid_disks = mddev->raid_disks;
 	conf->mddev = mddev;
 	INIT_LIST_HEAD(&conf->retry_list);
 	INIT_LIST_HEAD(&conf->bio_end_io_list);
@@ -3086,12 +3194,21 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 	return ERR_PTR(err);
 }
 
+static int raid1_set_limits(struct mddev *mddev)
+{
+	struct queue_limits lim;
+
+	blk_set_stacking_limits(&lim);
+	lim.max_write_zeroes_sectors = 0;
+	mddev_stack_rdev_limits(mddev, &lim);
+	return queue_limits_set(mddev->gendisk->queue, &lim);
+}
+
 static void raid1_free(struct mddev *mddev, void *priv);
 static int raid1_run(struct mddev *mddev)
 {
 	struct r1conf *conf;
 	int i;
-	struct md_rdev *rdev;
 	int ret;
 
 	if (mddev->level != 1) {
@@ -3118,14 +3235,10 @@ static int raid1_run(struct mddev *mddev)
 	if (IS_ERR(conf))
 		return PTR_ERR(conf);
 
-	if (mddev->queue)
-		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
-
-	rdev_for_each(rdev, mddev) {
-		if (!mddev->gendisk)
-			continue;
-		disk_stack_limits(mddev->gendisk, rdev->bdev,
-				  rdev->data_offset << 9);
+	if (!mddev_is_dm(mddev)) {
+		ret = raid1_set_limits(mddev);
+		if (ret)
+			goto abort;
 	}
 
 	mddev->degraded = 0;
diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h
index 14d4211a123a..5300cbaa58a4 100644
--- a/drivers/md/raid1.h
+++ b/drivers/md/raid1.h
@@ -71,6 +71,7 @@ struct r1conf {
 						 * allow for replacements.
 						 */
 	int			raid_disks;
+	int			nonrot_disks;
 
 	spinlock_t		device_lock;
 
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 7412066ea22c..a4556d2e46bf 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -76,9 +76,6 @@ static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio);
 static void end_reshape_write(struct bio *bio);
 static void end_reshape(struct r10conf *conf);
 
-#define raid10_log(md, fmt, args...)				\
-	do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid10 " fmt, ##args); } while (0)
-
 #include "raid1-10.c"
 
 #define NULL_CMD
@@ -518,11 +515,7 @@ static void raid10_end_write_request(struct bio *bio)
 		 * The 'master' represents the composite IO operation to
 		 * user-side. So if something waits for IO, then it will
 		 * wait for the 'master' bio.
-		 */
-		sector_t first_bad;
-		int bad_sectors;
-
-		/*
+		 *
 		 * Do not set R10BIO_Uptodate if the current device is
 		 * rebuilding or Faulty. This is because we cannot use
 		 * such device for properly reading the data back (we could
@@ -535,10 +528,9 @@ static void raid10_end_write_request(struct bio *bio)
 			set_bit(R10BIO_Uptodate, &r10_bio->state);
 
 		/* Maybe we can clear some bad blocks. */
-		if (is_badblock(rdev,
-				r10_bio->devs[slot].addr,
-				r10_bio->sectors,
-				&first_bad, &bad_sectors) && !discard_error) {
+		if (rdev_has_badblock(rdev, r10_bio->devs[slot].addr,
+				      r10_bio->sectors) &&
+		    !discard_error) {
 			bio_put(bio);
 			if (repl)
 				r10_bio->devs[slot].repl_bio = IO_MADE_GOOD;
@@ -753,17 +745,8 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 	best_good_sectors = 0;
 	do_balance = 1;
 	clear_bit(R10BIO_FailFast, &r10_bio->state);
-	/*
-	 * Check if we can balance. We can balance on the whole
-	 * device if no resync is going on (recovery is ok), or below
-	 * the resync window. We take the first readable disk when
-	 * above the resync window.
-	 */
-	if ((conf->mddev->recovery_cp < MaxSector
-	     && (this_sector + sectors >= conf->next_resync)) ||
-	    (mddev_is_clustered(conf->mddev) &&
-	     md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector,
-					    this_sector + sectors)))
+
+	if (raid1_should_read_first(conf->mddev, this_sector, sectors))
 		do_balance = 0;
 
 	for (slot = 0; slot < conf->copies ; slot++) {
@@ -1033,7 +1016,7 @@ static bool wait_barrier(struct r10conf *conf, bool nowait)
 			ret = false;
 		} else {
 			conf->nr_waiting++;
-			raid10_log(conf->mddev, "wait barrier");
+			mddev_add_trace_msg(conf->mddev, "raid10 wait barrier");
 			wait_event_barrier(conf, stop_waiting_barrier(conf));
 			conf->nr_waiting--;
 		}
@@ -1152,7 +1135,7 @@ static bool regular_request_wait(struct mddev *mddev, struct r10conf *conf,
 			bio_wouldblock_error(bio);
 			return false;
 		}
-		raid10_log(conf->mddev, "wait reshape");
+		mddev_add_trace_msg(conf->mddev, "raid10 wait reshape");
 		wait_event(conf->wait_barrier,
 			   conf->reshape_progress <= bio->bi_iter.bi_sector ||
 			   conf->reshape_progress >= bio->bi_iter.bi_sector +
@@ -1249,10 +1232,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	    test_bit(R10BIO_FailFast, &r10_bio->state))
 	        read_bio->bi_opf |= MD_FAILFAST;
 	read_bio->bi_private = r10_bio;
-
-	if (mddev->gendisk)
-	        trace_block_bio_remap(read_bio, disk_devt(mddev->gendisk),
-	                              r10_bio->sector);
+	mddev_trace_remap(mddev, read_bio, r10_bio->sector);
 	submit_bio_noacct(read_bio);
 	return;
 }
@@ -1288,10 +1268,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 			 && enough(conf, devnum))
 		mbio->bi_opf |= MD_FAILFAST;
 	mbio->bi_private = r10_bio;
-
-	if (conf->mddev->gendisk)
-		trace_block_bio_remap(mbio, disk_devt(conf->mddev->gendisk),
-				      r10_bio->sector);
+	mddev_trace_remap(mddev, mbio, r10_bio->sector);
 	/* flush_pending_writes() needs access to the rdev so...*/
 	mbio->bi_bdev = (void *)rdev;
 
@@ -1330,10 +1307,7 @@ retry_wait:
 		}
 
 		if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) {
-			sector_t first_bad;
 			sector_t dev_sector = r10_bio->devs[i].addr;
-			int bad_sectors;
-			int is_bad;
 
 			/*
 			 * Discard request doesn't care the write result
@@ -1342,9 +1316,8 @@ retry_wait:
 			if (!r10_bio->sectors)
 				continue;
 
-			is_bad = is_badblock(rdev, dev_sector, r10_bio->sectors,
-					     &first_bad, &bad_sectors);
-			if (is_bad < 0) {
+			if (rdev_has_badblock(rdev, dev_sector,
+					      r10_bio->sectors) < 0) {
 				/*
 				 * Mustn't write here until the bad block
 				 * is acknowledged
@@ -1360,8 +1333,9 @@ retry_wait:
 	if (unlikely(blocked_rdev)) {
 		/* Have to wait for this device to get unblocked, then retry */
 		allow_barrier(conf);
-		raid10_log(conf->mddev, "%s wait rdev %d blocked",
-				__func__, blocked_rdev->raid_disk);
+		mddev_add_trace_msg(conf->mddev,
+			"raid10 %s wait rdev %d blocked",
+			__func__, blocked_rdev->raid_disk);
 		md_wait_for_blocked_rdev(blocked_rdev, mddev);
 		wait_barrier(conf, false);
 		goto retry_wait;
@@ -1416,7 +1390,8 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 			bio_wouldblock_error(bio);
 			return;
 		}
-		raid10_log(conf->mddev, "wait reshape metadata");
+		mddev_add_trace_msg(conf->mddev,
+			"raid10 wait reshape metadata");
 		wait_event(mddev->sb_wait,
 			   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
 
@@ -2131,10 +2106,9 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			continue;
 		}
 
-		if (mddev->gendisk)
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-
+		err = mddev_stack_new_rdev(mddev, rdev);
+		if (err)
+			return err;
 		p->head_position = 0;
 		p->recovery_disabled = mddev->recovery_disabled - 1;
 		rdev->raid_disk = mirror;
@@ -2150,10 +2124,9 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		clear_bit(In_sync, &rdev->flags);
 		set_bit(Replacement, &rdev->flags);
 		rdev->raid_disk = repl_slot;
-		err = 0;
-		if (mddev->gendisk)
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
+		err = mddev_stack_new_rdev(mddev, rdev);
+		if (err)
+			return err;
 		conf->fullsync = 1;
 		WRITE_ONCE(p->replacement, rdev);
 	}
@@ -2290,8 +2263,6 @@ static void end_sync_write(struct bio *bio)
 	struct mddev *mddev = r10_bio->mddev;
 	struct r10conf *conf = mddev->private;
 	int d;
-	sector_t first_bad;
-	int bad_sectors;
 	int slot;
 	int repl;
 	struct md_rdev *rdev = NULL;
@@ -2312,11 +2283,10 @@ static void end_sync_write(struct bio *bio)
 					&rdev->mddev->recovery);
 			set_bit(R10BIO_WriteError, &r10_bio->state);
 		}
-	} else if (is_badblock(rdev,
-			     r10_bio->devs[slot].addr,
-			     r10_bio->sectors,
-			     &first_bad, &bad_sectors))
+	} else if (rdev_has_badblock(rdev, r10_bio->devs[slot].addr,
+				     r10_bio->sectors)) {
 		set_bit(R10BIO_MadeGood, &r10_bio->state);
+	}
 
 	rdev_dec_pending(rdev, mddev);
 
@@ -2597,11 +2567,8 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 static int r10_sync_page_io(struct md_rdev *rdev, sector_t sector,
 			    int sectors, struct page *page, enum req_op op)
 {
-	sector_t first_bad;
-	int bad_sectors;
-
-	if (is_badblock(rdev, sector, sectors, &first_bad, &bad_sectors)
-	    && (op == REQ_OP_READ || test_bit(WriteErrorSeen, &rdev->flags)))
+	if (rdev_has_badblock(rdev, sector, sectors) &&
+	    (op == REQ_OP_READ || test_bit(WriteErrorSeen, &rdev->flags)))
 		return -1;
 	if (sync_page_io(rdev, sector, sectors << 9, page, op, false))
 		/* success */
@@ -2658,16 +2625,14 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			s = PAGE_SIZE >> 9;
 
 		do {
-			sector_t first_bad;
-			int bad_sectors;
-
 			d = r10_bio->devs[sl].devnum;
 			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
 			    test_bit(In_sync, &rdev->flags) &&
 			    !test_bit(Faulty, &rdev->flags) &&
-			    is_badblock(rdev, r10_bio->devs[sl].addr + sect, s,
-					&first_bad, &bad_sectors) == 0) {
+			    rdev_has_badblock(rdev,
+					      r10_bio->devs[sl].addr + sect,
+					      s) == 0) {
 				atomic_inc(&rdev->nr_pending);
 				success = sync_page_io(rdev,
 						       r10_bio->devs[sl].addr +
@@ -4002,14 +3967,26 @@ static struct r10conf *setup_conf(struct mddev *mddev)
 	return ERR_PTR(err);
 }
 
-static void raid10_set_io_opt(struct r10conf *conf)
+static unsigned int raid10_nr_stripes(struct r10conf *conf)
 {
-	int raid_disks = conf->geo.raid_disks;
+	unsigned int raid_disks = conf->geo.raid_disks;
+
+	if (conf->geo.raid_disks % conf->geo.near_copies)
+		return raid_disks;
+	return raid_disks / conf->geo.near_copies;
+}
 
-	if (!(conf->geo.raid_disks % conf->geo.near_copies))
-		raid_disks /= conf->geo.near_copies;
-	blk_queue_io_opt(conf->mddev->queue, (conf->mddev->chunk_sectors << 9) *
-			 raid_disks);
+static int raid10_set_queue_limits(struct mddev *mddev)
+{
+	struct r10conf *conf = mddev->private;
+	struct queue_limits lim;
+
+	blk_set_stacking_limits(&lim);
+	lim.max_write_zeroes_sectors = 0;
+	lim.io_min = mddev->chunk_sectors << 9;
+	lim.io_opt = lim.io_min * raid10_nr_stripes(conf);
+	mddev_stack_rdev_limits(mddev, &lim);
+	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
 static int raid10_run(struct mddev *mddev)
@@ -4021,6 +3998,7 @@ static int raid10_run(struct mddev *mddev)
 	sector_t size;
 	sector_t min_offset_diff = 0;
 	int first = 1;
+	int ret = -EIO;
 
 	if (mddev->private == NULL) {
 		conf = setup_conf(mddev);
@@ -4047,12 +4025,6 @@ static int raid10_run(struct mddev *mddev)
 		}
 	}
 
-	if (mddev->queue) {
-		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
-		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
-		raid10_set_io_opt(conf);
-	}
-
 	rdev_for_each(rdev, mddev) {
 		long long diff;
 
@@ -4081,14 +4053,16 @@ static int raid10_run(struct mddev *mddev)
 		if (first || diff < min_offset_diff)
 			min_offset_diff = diff;
 
-		if (mddev->gendisk)
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-
 		disk->head_position = 0;
 		first = 0;
 	}
 
+	if (!mddev_is_dm(conf->mddev)) {
+		ret = raid10_set_queue_limits(mddev);
+		if (ret)
+			goto out_free_conf;
+	}
+
 	/* need to check that every block has at least one working mirror */
 	if (!enough(conf, -1)) {
 		pr_err("md/raid10:%s: not enough operational mirrors.\n",
@@ -4175,11 +4149,7 @@ static int raid10_run(struct mddev *mddev)
 		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 		clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 		set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-		set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-		rcu_assign_pointer(mddev->sync_thread,
-			md_register_thread(md_do_sync, mddev, "reshape"));
-		if (!mddev->sync_thread)
-			goto out_free_conf;
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	}
 
 	return 0;
@@ -4189,7 +4159,7 @@ out_free_conf:
 	raid10_free_conf(conf);
 	mddev->private = NULL;
 out:
-	return -EIO;
+	return ret;
 }
 
 static void raid10_free(struct mddev *mddev, void *priv)
@@ -4573,16 +4543,8 @@ out:
 	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 	clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 	set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-	set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-
-	rcu_assign_pointer(mddev->sync_thread,
-			   md_register_thread(md_do_sync, mddev, "reshape"));
-	if (!mddev->sync_thread) {
-		ret = -EAGAIN;
-		goto abort;
-	}
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	conf->reshape_checkpoint = jiffies;
-	md_wakeup_thread(mddev->sync_thread);
 	md_new_event();
 	return 0;
 
@@ -4966,8 +4928,7 @@ static void end_reshape(struct r10conf *conf)
 	conf->reshape_safe = MaxSector;
 	spin_unlock_irq(&conf->device_lock);
 
-	if (conf->mddev->queue)
-		raid10_set_io_opt(conf);
+	mddev_update_io_opt(conf->mddev, raid10_nr_stripes(conf));
 	conf->fullsync = 0;
 }
 
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index da4ba736c4f0..a70cbec12ed0 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -1393,7 +1393,8 @@ int ppl_init_log(struct r5conf *conf)
 		ppl_conf->signature = ~crc32c_le(~0, mddev->uuid, sizeof(mddev->uuid));
 		ppl_conf->block_size = 512;
 	} else {
-		ppl_conf->block_size = queue_logical_block_size(mddev->queue);
+		ppl_conf->block_size =
+			queue_logical_block_size(mddev->gendisk->queue);
 	}
 
 	for (i = 0; i < ppl_conf->count; i++) {
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 8497880135ee..d874abfc1836 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -36,6 +36,7 @@
  */
 
 #include <linux/blkdev.h>
+#include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/raid/pq.h>
 #include <linux/async_tx.h>
@@ -760,6 +761,7 @@ enum stripe_result {
 	STRIPE_RETRY,
 	STRIPE_SCHEDULE_AND_RETRY,
 	STRIPE_FAIL,
+	STRIPE_WAIT_RESHAPE,
 };
 
 struct stripe_request_ctx {
@@ -1210,10 +1212,8 @@ again:
 		 */
 		while (op_is_write(op) && rdev &&
 		       test_bit(WriteErrorSeen, &rdev->flags)) {
-			sector_t first_bad;
-			int bad_sectors;
-			int bad = is_badblock(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf),
-					      &first_bad, &bad_sectors);
+			int bad = rdev_has_badblock(rdev, sh->sector,
+						    RAID5_STRIPE_SECTORS(conf));
 			if (!bad)
 				break;
 
@@ -1295,10 +1295,7 @@ again:
 			if (rrdev)
 				set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags);
 
-			if (conf->mddev->gendisk)
-				trace_block_bio_remap(bi,
-						disk_devt(conf->mddev->gendisk),
-						sh->dev[i].sector);
+			mddev_trace_remap(conf->mddev, bi, sh->dev[i].sector);
 			if (should_defer && op_is_write(op))
 				bio_list_add(&pending_bios, bi);
 			else
@@ -1342,10 +1339,7 @@ again:
 			 */
 			if (op == REQ_OP_DISCARD)
 				rbi->bi_vcnt = 0;
-			if (conf->mddev->gendisk)
-				trace_block_bio_remap(rbi,
-						disk_devt(conf->mddev->gendisk),
-						sh->dev[i].sector);
+			mddev_trace_remap(conf->mddev, rbi, sh->dev[i].sector);
 			if (should_defer && op_is_write(op))
 				bio_list_add(&pending_bios, rbi);
 			else
@@ -2412,7 +2406,7 @@ static int grow_one_stripe(struct r5conf *conf, gfp_t gfp)
 	atomic_inc(&conf->active_stripes);
 
 	raid5_release_stripe(sh);
-	conf->max_nr_stripes++;
+	WRITE_ONCE(conf->max_nr_stripes, conf->max_nr_stripes + 1);
 	return 1;
 }
 
@@ -2422,12 +2416,12 @@ static int grow_stripes(struct r5conf *conf, int num)
 	size_t namelen = sizeof(conf->cache_name[0]);
 	int devs = max(conf->raid_disks, conf->previous_raid_disks);
 
-	if (conf->mddev->gendisk)
+	if (mddev_is_dm(conf->mddev))
 		snprintf(conf->cache_name[0], namelen,
-			"raid%d-%s", conf->level, mdname(conf->mddev));
+			"raid%d-%p", conf->level, conf->mddev);
 	else
 		snprintf(conf->cache_name[0], namelen,
-			"raid%d-%p", conf->level, conf->mddev);
+			"raid%d-%s", conf->level, mdname(conf->mddev));
 	snprintf(conf->cache_name[1], namelen, "%.27s-alt", conf->cache_name[0]);
 
 	conf->active_name = 0;
@@ -2707,7 +2701,7 @@ static int drop_one_stripe(struct r5conf *conf)
 	shrink_buffers(sh);
 	free_stripe(conf->slab_cache, sh);
 	atomic_dec(&conf->active_stripes);
-	conf->max_nr_stripes--;
+	WRITE_ONCE(conf->max_nr_stripes, conf->max_nr_stripes - 1);
 	return 1;
 }
 
@@ -2855,8 +2849,6 @@ static void raid5_end_write_request(struct bio *bi)
 	struct r5conf *conf = sh->raid_conf;
 	int disks = sh->disks, i;
 	struct md_rdev *rdev;
-	sector_t first_bad;
-	int bad_sectors;
 	int replacement = 0;
 
 	for (i = 0 ; i < disks; i++) {
@@ -2888,9 +2880,8 @@ static void raid5_end_write_request(struct bio *bi)
 	if (replacement) {
 		if (bi->bi_status)
 			md_error(conf->mddev, rdev);
-		else if (is_badblock(rdev, sh->sector,
-				     RAID5_STRIPE_SECTORS(conf),
-				     &first_bad, &bad_sectors))
+		else if (rdev_has_badblock(rdev, sh->sector,
+					   RAID5_STRIPE_SECTORS(conf)))
 			set_bit(R5_MadeGoodRepl, &sh->dev[i].flags);
 	} else {
 		if (bi->bi_status) {
@@ -2900,9 +2891,8 @@ static void raid5_end_write_request(struct bio *bi)
 			if (!test_and_set_bit(WantReplacement, &rdev->flags))
 				set_bit(MD_RECOVERY_NEEDED,
 					&rdev->mddev->recovery);
-		} else if (is_badblock(rdev, sh->sector,
-				       RAID5_STRIPE_SECTORS(conf),
-				       &first_bad, &bad_sectors)) {
+		} else if (rdev_has_badblock(rdev, sh->sector,
+					     RAID5_STRIPE_SECTORS(conf))) {
 			set_bit(R5_MadeGood, &sh->dev[i].flags);
 			if (test_bit(R5_ReadError, &sh->dev[i].flags))
 				/* That was a successful write so make
@@ -4205,10 +4195,9 @@ static int handle_stripe_dirtying(struct r5conf *conf,
 	set_bit(STRIPE_HANDLE, &sh->state);
 	if ((rmw < rcw || (rmw == rcw && conf->rmw_level == PARITY_PREFER_RMW)) && rmw > 0) {
 		/* prefer read-modify-write, but need to get some data */
-		if (conf->mddev->queue)
-			blk_add_trace_msg(conf->mddev->queue,
-					  "raid5 rmw %llu %d",
-					  (unsigned long long)sh->sector, rmw);
+		mddev_add_trace_msg(conf->mddev, "raid5 rmw %llu %d",
+				sh->sector, rmw);
+
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
 			if (test_bit(R5_InJournal, &dev->flags) &&
@@ -4285,10 +4274,11 @@ static int handle_stripe_dirtying(struct r5conf *conf,
 					set_bit(STRIPE_DELAYED, &sh->state);
 			}
 		}
-		if (rcw && conf->mddev->queue)
-			blk_add_trace_msg(conf->mddev->queue, "raid5 rcw %llu %d %d %d",
-					  (unsigned long long)sh->sector,
-					  rcw, qread, test_bit(STRIPE_DELAYED, &sh->state));
+		if (rcw && !mddev_is_dm(conf->mddev))
+			blk_add_trace_msg(conf->mddev->gendisk->queue,
+				"raid5 rcw %llu %d %d %d",
+				(unsigned long long)sh->sector, rcw, qread,
+				test_bit(STRIPE_DELAYED, &sh->state));
 	}
 
 	if (rcw > disks && rmw > disks &&
@@ -4674,8 +4664,6 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 	/* Now to look around and see what can be done */
 	for (i=disks; i--; ) {
 		struct md_rdev *rdev;
-		sector_t first_bad;
-		int bad_sectors;
 		int is_bad = 0;
 
 		dev = &sh->dev[i];
@@ -4719,8 +4707,8 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 		rdev = conf->disks[i].replacement;
 		if (rdev && !test_bit(Faulty, &rdev->flags) &&
 		    rdev->recovery_offset >= sh->sector + RAID5_STRIPE_SECTORS(conf) &&
-		    !is_badblock(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf),
-				 &first_bad, &bad_sectors))
+		    !rdev_has_badblock(rdev, sh->sector,
+				       RAID5_STRIPE_SECTORS(conf)))
 			set_bit(R5_ReadRepl, &dev->flags);
 		else {
 			if (rdev && !test_bit(Faulty, &rdev->flags))
@@ -4733,8 +4721,8 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 		if (rdev && test_bit(Faulty, &rdev->flags))
 			rdev = NULL;
 		if (rdev) {
-			is_bad = is_badblock(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf),
-					     &first_bad, &bad_sectors);
+			is_bad = rdev_has_badblock(rdev, sh->sector,
+						   RAID5_STRIPE_SECTORS(conf));
 			if (s->blocked_rdev == NULL
 			    && (test_bit(Blocked, &rdev->flags)
 				|| is_bad < 0)) {
@@ -5463,8 +5451,8 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 	struct r5conf *conf = mddev->private;
 	struct bio *align_bio;
 	struct md_rdev *rdev;
-	sector_t sector, end_sector, first_bad;
-	int bad_sectors, dd_idx;
+	sector_t sector, end_sector;
+	int dd_idx;
 	bool did_inc;
 
 	if (!in_chunk_boundary(mddev, raid_bio)) {
@@ -5493,8 +5481,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 
 	atomic_inc(&rdev->nr_pending);
 
-	if (is_badblock(rdev, sector, bio_sectors(raid_bio), &first_bad,
-			&bad_sectors)) {
+	if (rdev_has_badblock(rdev, sector, bio_sectors(raid_bio))) {
 		rdev_dec_pending(rdev, mddev);
 		return 0;
 	}
@@ -5530,9 +5517,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 		spin_unlock_irq(&conf->device_lock);
 	}
 
-	if (mddev->gendisk)
-		trace_block_bio_remap(align_bio, disk_devt(mddev->gendisk),
-				      raid_bio->bi_iter.bi_sector);
+	mddev_trace_remap(mddev, align_bio, raid_bio->bi_iter.bi_sector);
 	submit_bio_noacct(align_bio);
 	return 1;
 }
@@ -5701,8 +5686,8 @@ static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule)
 	}
 	release_inactive_stripe_list(conf, cb->temp_inactive_list,
 				     NR_STRIPE_HASH_LOCKS);
-	if (mddev->queue)
-		trace_block_unplug(mddev->queue, cnt, !from_schedule);
+	if (!mddev_is_dm(mddev))
+		trace_block_unplug(mddev->gendisk->queue, cnt, !from_schedule);
 	kfree(cb);
 }
 
@@ -5946,7 +5931,8 @@ static enum stripe_result make_stripe_request(struct mddev *mddev,
 			if (ahead_of_reshape(mddev, logical_sector,
 					     conf->reshape_safe)) {
 				spin_unlock_irq(&conf->device_lock);
-				return STRIPE_SCHEDULE_AND_RETRY;
+				ret = STRIPE_SCHEDULE_AND_RETRY;
+				goto out;
 			}
 		}
 		spin_unlock_irq(&conf->device_lock);
@@ -6025,6 +6011,12 @@ static enum stripe_result make_stripe_request(struct mddev *mddev,
 
 out_release:
 	raid5_release_stripe(sh);
+out:
+	if (ret == STRIPE_SCHEDULE_AND_RETRY && reshape_interrupted(mddev)) {
+		bi->bi_status = BLK_STS_RESOURCE;
+		ret = STRIPE_WAIT_RESHAPE;
+		pr_err_ratelimited("dm-raid456: io across reshape position while reshape can't make progress");
+	}
 	return ret;
 }
 
@@ -6146,7 +6138,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 	while (1) {
 		res = make_stripe_request(mddev, conf, &ctx, logical_sector,
 					  bi);
-		if (res == STRIPE_FAIL)
+		if (res == STRIPE_FAIL || res == STRIPE_WAIT_RESHAPE)
 			break;
 
 		if (res == STRIPE_RETRY)
@@ -6184,6 +6176,11 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 
 	if (rw == WRITE)
 		md_write_end(mddev);
+	if (res == STRIPE_WAIT_RESHAPE) {
+		md_free_cloned_bio(bi);
+		return false;
+	}
+
 	bio_endio(bi);
 	return true;
 }
@@ -6773,7 +6770,18 @@ static void raid5d(struct md_thread *thread)
 			spin_unlock_irq(&conf->device_lock);
 			md_check_recovery(mddev);
 			spin_lock_irq(&conf->device_lock);
+
+			/*
+			 * Waiting on MD_SB_CHANGE_PENDING below may deadlock
+			 * seeing md_check_recovery() is needed to clear
+			 * the flag when using mdmon.
+			 */
+			continue;
 		}
+
+		wait_event_lock_irq(mddev->sb_wait,
+			!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags),
+			conf->device_lock);
 	}
 	pr_debug("%d stripes handled\n", handled);
 
@@ -6820,7 +6828,7 @@ raid5_set_cache_size(struct mddev *mddev, int size)
 	if (size <= 16 || size > 32768)
 		return -EINVAL;
 
-	conf->min_nr_stripes = size;
+	WRITE_ONCE(conf->min_nr_stripes, size);
 	mutex_lock(&conf->cache_size_mutex);
 	while (size < conf->max_nr_stripes &&
 	       drop_one_stripe(conf))
@@ -6832,7 +6840,7 @@ raid5_set_cache_size(struct mddev *mddev, int size)
 	mutex_lock(&conf->cache_size_mutex);
 	while (size > conf->max_nr_stripes)
 		if (!grow_one_stripe(conf, GFP_KERNEL)) {
-			conf->min_nr_stripes = conf->max_nr_stripes;
+			WRITE_ONCE(conf->min_nr_stripes, conf->max_nr_stripes);
 			result = -ENOMEM;
 			break;
 		}
@@ -6967,10 +6975,8 @@ raid5_store_stripe_size(struct mddev  *mddev, const char *page, size_t len)
 	pr_debug("md/raid: change stripe_size from %lu to %lu\n",
 			conf->stripe_size, new);
 
-	if (mddev->sync_thread ||
-		test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
-		mddev->reshape_position != MaxSector ||
-		mddev->sysfs_active) {
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+	    mddev->reshape_position != MaxSector || mddev->sysfs_active) {
 		err = -EBUSY;
 		goto out_unlock;
 	}
@@ -7084,7 +7090,7 @@ raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
 	if (!conf)
 		err = -ENODEV;
 	else if (new != conf->skip_copy) {
-		struct request_queue *q = mddev->queue;
+		struct request_queue *q = mddev->gendisk->queue;
 
 		conf->skip_copy = new;
 		if (new)
@@ -7390,11 +7396,13 @@ static unsigned long raid5_cache_count(struct shrinker *shrink,
 				       struct shrink_control *sc)
 {
 	struct r5conf *conf = shrink->private_data;
+	int max_stripes = READ_ONCE(conf->max_nr_stripes);
+	int min_stripes = READ_ONCE(conf->min_nr_stripes);
 
-	if (conf->max_nr_stripes < conf->min_nr_stripes)
+	if (max_stripes < min_stripes)
 		/* unlikely, but not impossible */
 		return 0;
-	return conf->max_nr_stripes - conf->min_nr_stripes;
+	return max_stripes - min_stripes;
 }
 
 static struct r5conf *setup_conf(struct mddev *mddev)
@@ -7684,10 +7692,65 @@ static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded
 	return 0;
 }
 
-static void raid5_set_io_opt(struct r5conf *conf)
+static int raid5_set_limits(struct mddev *mddev)
 {
-	blk_queue_io_opt(conf->mddev->queue, (conf->chunk_sectors << 9) *
-			 (conf->raid_disks - conf->max_degraded));
+	struct r5conf *conf = mddev->private;
+	struct queue_limits lim;
+	int data_disks, stripe;
+	struct md_rdev *rdev;
+
+	/*
+	 * The read-ahead size must cover two whole stripes, which is
+	 * 2 * (datadisks) * chunksize where 'n' is the number of raid devices.
+	 */
+	data_disks = conf->previous_raid_disks - conf->max_degraded;
+
+	/*
+	 * We can only discard a whole stripe. It doesn't make sense to
+	 * discard data disk but write parity disk
+	 */
+	stripe = roundup_pow_of_two(data_disks * (mddev->chunk_sectors << 9));
+
+	blk_set_stacking_limits(&lim);
+	lim.io_min = mddev->chunk_sectors << 9;
+	lim.io_opt = lim.io_min * (conf->raid_disks - conf->max_degraded);
+	lim.raid_partial_stripes_expensive = 1;
+	lim.discard_granularity = stripe;
+	lim.max_write_zeroes_sectors = 0;
+	mddev_stack_rdev_limits(mddev, &lim);
+	rdev_for_each(rdev, mddev)
+		queue_limits_stack_bdev(&lim, rdev->bdev, rdev->new_data_offset,
+				mddev->gendisk->disk_name);
+
+	/*
+	 * Zeroing is required for discard, otherwise data could be lost.
+	 *
+	 * Consider a scenario: discard a stripe (the stripe could be
+	 * inconsistent if discard_zeroes_data is 0); write one disk of the
+	 * stripe (the stripe could be inconsistent again depending on which
+	 * disks are used to calculate parity); the disk is broken; The stripe
+	 * data of this disk is lost.
+	 *
+	 * We only allow DISCARD if the sysadmin has confirmed that only safe
+	 * devices are in use by setting a module parameter.  A better idea
+	 * might be to turn DISCARD into WRITE_ZEROES requests, as that is
+	 * required to be safe.
+	 */
+	if (!devices_handle_discard_safely ||
+	    lim.max_discard_sectors < (stripe >> 9) ||
+	    lim.discard_granularity < stripe)
+		lim.max_hw_discard_sectors = 0;
+
+	/*
+	 * Requests require having a bitmap for each stripe.
+	 * Limit the max sectors based on this.
+	 */
+	lim.max_hw_sectors = RAID5_MAX_REQ_STRIPES << RAID5_STRIPE_SHIFT(conf);
+
+	/* No restrictions on the number of segments in the request */
+	lim.max_segments = USHRT_MAX;
+
+	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
 static int raid5_run(struct mddev *mddev)
@@ -7700,6 +7763,7 @@ static int raid5_run(struct mddev *mddev)
 	int i;
 	long long min_offset_diff = 0;
 	int first = 1;
+	int ret = -EIO;
 
 	if (mddev->recovery_cp != MaxSector)
 		pr_notice("md/raid:%s: not clean -- starting background reconstruction\n",
@@ -7936,11 +8000,7 @@ static int raid5_run(struct mddev *mddev)
 		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 		clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 		set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-		set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-		rcu_assign_pointer(mddev->sync_thread,
-			md_register_thread(md_do_sync, mddev, "reshape"));
-		if (!mddev->sync_thread)
-			goto abort;
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	}
 
 	/* Ok, everything is just fine now */
@@ -7952,66 +8012,10 @@ static int raid5_run(struct mddev *mddev)
 			mdname(mddev));
 	md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
 
-	if (mddev->queue) {
-		int chunk_size;
-		/* read-ahead size must cover two whole stripes, which
-		 * is 2 * (datadisks) * chunksize where 'n' is the
-		 * number of raid devices
-		 */
-		int data_disks = conf->previous_raid_disks - conf->max_degraded;
-		int stripe = data_disks *
-			((mddev->chunk_sectors << 9) / PAGE_SIZE);
-
-		chunk_size = mddev->chunk_sectors << 9;
-		blk_queue_io_min(mddev->queue, chunk_size);
-		raid5_set_io_opt(conf);
-		mddev->queue->limits.raid_partial_stripes_expensive = 1;
-		/*
-		 * We can only discard a whole stripe. It doesn't make sense to
-		 * discard data disk but write parity disk
-		 */
-		stripe = stripe * PAGE_SIZE;
-		stripe = roundup_pow_of_two(stripe);
-		mddev->queue->limits.discard_granularity = stripe;
-
-		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
-
-		rdev_for_each(rdev, mddev) {
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->new_data_offset << 9);
-		}
-
-		/*
-		 * zeroing is required, otherwise data
-		 * could be lost. Consider a scenario: discard a stripe
-		 * (the stripe could be inconsistent if
-		 * discard_zeroes_data is 0); write one disk of the
-		 * stripe (the stripe could be inconsistent again
-		 * depending on which disks are used to calculate
-		 * parity); the disk is broken; The stripe data of this
-		 * disk is lost.
-		 *
-		 * We only allow DISCARD if the sysadmin has confirmed that
-		 * only safe devices are in use by setting a module parameter.
-		 * A better idea might be to turn DISCARD into WRITE_ZEROES
-		 * requests, as that is required to be safe.
-		 */
-		if (!devices_handle_discard_safely ||
-		    mddev->queue->limits.max_discard_sectors < (stripe >> 9) ||
-		    mddev->queue->limits.discard_granularity < stripe)
-			blk_queue_max_discard_sectors(mddev->queue, 0);
-
-		/*
-		 * Requests require having a bitmap for each stripe.
-		 * Limit the max sectors based on this.
-		 */
-		blk_queue_max_hw_sectors(mddev->queue,
-			RAID5_MAX_REQ_STRIPES << RAID5_STRIPE_SHIFT(conf));
-
-		/* No restrictions on the number of segments in the request */
-		blk_queue_max_segments(mddev->queue, USHRT_MAX);
+	if (!mddev_is_dm(mddev)) {
+		ret = raid5_set_limits(mddev);
+		if (ret)
+			goto abort;
 	}
 
 	if (log_init(conf, journal_dev, raid5_has_ppl(conf)))
@@ -8024,7 +8028,7 @@ abort:
 	free_conf(conf);
 	mddev->private = NULL;
 	pr_warn("md/raid:%s: failed to run raid set.\n", mdname(mddev));
-	return -EIO;
+	return ret;
 }
 
 static void raid5_free(struct mddev *mddev, void *priv)
@@ -8506,29 +8510,8 @@ static int raid5_start_reshape(struct mddev *mddev)
 	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 	clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 	set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-	set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-	rcu_assign_pointer(mddev->sync_thread,
-			   md_register_thread(md_do_sync, mddev, "reshape"));
-	if (!mddev->sync_thread) {
-		mddev->recovery = 0;
-		spin_lock_irq(&conf->device_lock);
-		write_seqcount_begin(&conf->gen_lock);
-		mddev->raid_disks = conf->raid_disks = conf->previous_raid_disks;
-		mddev->new_chunk_sectors =
-			conf->chunk_sectors = conf->prev_chunk_sectors;
-		mddev->new_layout = conf->algorithm = conf->prev_algo;
-		rdev_for_each(rdev, mddev)
-			rdev->new_data_offset = rdev->data_offset;
-		smp_wmb();
-		conf->generation --;
-		conf->reshape_progress = MaxSector;
-		mddev->reshape_position = MaxSector;
-		write_seqcount_end(&conf->gen_lock);
-		spin_unlock_irq(&conf->device_lock);
-		return -EAGAIN;
-	}
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	conf->reshape_checkpoint = jiffies;
-	md_wakeup_thread(mddev->sync_thread);
 	md_new_event();
 	return 0;
 }
@@ -8556,8 +8539,8 @@ static void end_reshape(struct r5conf *conf)
 		spin_unlock_irq(&conf->device_lock);
 		wake_up(&conf->wait_for_overlap);
 
-		if (conf->mddev->queue)
-			raid5_set_io_opt(conf);
+		mddev_update_io_opt(conf->mddev,
+			conf->raid_disks - conf->max_degraded);
 	}
 }
 
@@ -8934,6 +8917,18 @@ static int raid5_start(struct mddev *mddev)
 	return r5l_start(conf->log);
 }
 
+/*
+ * This is only used for dm-raid456, caller already frozen sync_thread, hence
+ * if rehsape is still in progress, io that is waiting for reshape can never be
+ * done now, hence wake up and handle those IO.
+ */
+static void raid5_prepare_suspend(struct mddev *mddev)
+{
+	struct r5conf *conf = mddev->private;
+
+	wake_up(&conf->wait_for_overlap);
+}
+
 static struct md_personality raid6_personality =
 {
 	.name		= "raid6",
@@ -8957,6 +8952,7 @@ static struct md_personality raid6_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid6_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
+	.prepare_suspend = raid5_prepare_suspend,
 };
 static struct md_personality raid5_personality =
 {
@@ -8981,6 +8977,7 @@ static struct md_personality raid5_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid5_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
+	.prepare_suspend = raid5_prepare_suspend,
 };
 
 static struct md_personality raid4_personality =
@@ -9006,6 +9003,7 @@ static struct md_personality raid4_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid4_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
+	.prepare_suspend = raid5_prepare_suspend,
 };
 
 static int __init raid5_init(void)
diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c
index 41a832dd1426..b6bf8f232f48 100644
--- a/drivers/media/common/videobuf2/videobuf2-core.c
+++ b/drivers/media/common/videobuf2/videobuf2-core.c
@@ -989,7 +989,7 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory,
 	bool no_previous_buffers = !q_num_bufs;
 	int ret = 0;
 
-	if (q->num_buffers == q->max_num_buffers) {
+	if (q_num_bufs == q->max_num_buffers) {
 		dprintk(q, 1, "maximum number of buffers already allocated\n");
 		return -ENOBUFS;
 	}
diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c
index 54d572c3b515..c575198e8354 100644
--- a/drivers/media/common/videobuf2/videobuf2-v4l2.c
+++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c
@@ -671,8 +671,20 @@ int vb2_querybuf(struct vb2_queue *q, struct v4l2_buffer *b)
 }
 EXPORT_SYMBOL(vb2_querybuf);
 
-static void fill_buf_caps(struct vb2_queue *q, u32 *caps)
+static void vb2_set_flags_and_caps(struct vb2_queue *q, u32 memory,
+				   u32 *flags, u32 *caps, u32 *max_num_bufs)
 {
+	if (!q->allow_cache_hints || memory != V4L2_MEMORY_MMAP) {
+		/*
+		 * This needs to clear V4L2_MEMORY_FLAG_NON_COHERENT only,
+		 * but in order to avoid bugs we zero out all bits.
+		 */
+		*flags = 0;
+	} else {
+		/* Clear all unknown flags. */
+		*flags &= V4L2_MEMORY_FLAG_NON_COHERENT;
+	}
+
 	*caps = V4L2_BUF_CAP_SUPPORTS_ORPHANED_BUFS;
 	if (q->io_modes & VB2_MMAP)
 		*caps |= V4L2_BUF_CAP_SUPPORTS_MMAP;
@@ -686,21 +698,9 @@ static void fill_buf_caps(struct vb2_queue *q, u32 *caps)
 		*caps |= V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS;
 	if (q->supports_requests)
 		*caps |= V4L2_BUF_CAP_SUPPORTS_REQUESTS;
-}
-
-static void validate_memory_flags(struct vb2_queue *q,
-				  int memory,
-				  u32 *flags)
-{
-	if (!q->allow_cache_hints || memory != V4L2_MEMORY_MMAP) {
-		/*
-		 * This needs to clear V4L2_MEMORY_FLAG_NON_COHERENT only,
-		 * but in order to avoid bugs we zero out all bits.
-		 */
-		*flags = 0;
-	} else {
-		/* Clear all unknown flags. */
-		*flags &= V4L2_MEMORY_FLAG_NON_COHERENT;
+	if (max_num_bufs) {
+		*max_num_bufs = q->max_num_buffers;
+		*caps |= V4L2_BUF_CAP_SUPPORTS_MAX_NUM_BUFFERS;
 	}
 }
 
@@ -709,8 +709,8 @@ int vb2_reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req)
 	int ret = vb2_verify_memory_type(q, req->memory, req->type);
 	u32 flags = req->flags;
 
-	fill_buf_caps(q, &req->capabilities);
-	validate_memory_flags(q, req->memory, &flags);
+	vb2_set_flags_and_caps(q, req->memory, &flags,
+			       &req->capabilities, NULL);
 	req->flags = flags;
 	return ret ? ret : vb2_core_reqbufs(q, req->memory,
 					    req->flags, &req->count);
@@ -751,11 +751,9 @@ int vb2_create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create)
 	int ret = vb2_verify_memory_type(q, create->memory, f->type);
 	unsigned i;
 
-	fill_buf_caps(q, &create->capabilities);
-	validate_memory_flags(q, create->memory, &create->flags);
 	create->index = vb2_get_num_buffers(q);
-	create->max_num_buffers = q->max_num_buffers;
-	create->capabilities |= V4L2_BUF_CAP_SUPPORTS_MAX_NUM_BUFFERS;
+	vb2_set_flags_and_caps(q, create->memory, &create->flags,
+			       &create->capabilities, &create->max_num_buffers);
 	if (create->count == 0)
 		return ret != -EBUSY ? ret : 0;
 
@@ -1006,8 +1004,8 @@ int vb2_ioctl_reqbufs(struct file *file, void *priv,
 	int res = vb2_verify_memory_type(vdev->queue, p->memory, p->type);
 	u32 flags = p->flags;
 
-	fill_buf_caps(vdev->queue, &p->capabilities);
-	validate_memory_flags(vdev->queue, p->memory, &flags);
+	vb2_set_flags_and_caps(vdev->queue, p->memory, &flags,
+			       &p->capabilities, NULL);
 	p->flags = flags;
 	if (res)
 		return res;
@@ -1026,12 +1024,11 @@ int vb2_ioctl_create_bufs(struct file *file, void *priv,
 			  struct v4l2_create_buffers *p)
 {
 	struct video_device *vdev = video_devdata(file);
-	int res = vb2_verify_memory_type(vdev->queue, p->memory,
-			p->format.type);
+	int res = vb2_verify_memory_type(vdev->queue, p->memory, p->format.type);
 
-	p->index = vdev->queue->num_buffers;
-	fill_buf_caps(vdev->queue, &p->capabilities);
-	validate_memory_flags(vdev->queue, p->memory, &p->flags);
+	p->index = vb2_get_num_buffers(vdev->queue);
+	vb2_set_flags_and_caps(vdev->queue, p->memory, &p->flags,
+			       &p->capabilities, &p->max_num_buffers);
 	/*
 	 * If count == 0, then just check if memory and type are valid.
 	 * Any -EBUSY result from vb2_verify_memory_type can be mapped to 0.
diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c b/drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c
index bd38ce444232..46676f2c89c7 100644
--- a/drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c
+++ b/drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c
@@ -289,7 +289,7 @@ static const struct i2c_algorithm netup_i2c_algorithm = {
 static const struct i2c_adapter netup_i2c_adapter = {
 	.owner		= THIS_MODULE,
 	.name		= NETUP_UNIDVB_NAME,
-	.class		= I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class		= I2C_CLASS_HWMON,
 	.algo		= &netup_i2c_algorithm,
 };
 
diff --git a/drivers/media/pci/solo6x10/solo6x10-offsets.h b/drivers/media/pci/solo6x10/solo6x10-offsets.h
index f414ee1316f2..fdbb817e6360 100644
--- a/drivers/media/pci/solo6x10/solo6x10-offsets.h
+++ b/drivers/media/pci/solo6x10/solo6x10-offsets.h
@@ -57,16 +57,16 @@
 #define SOLO_MP4E_EXT_ADDR(__solo) \
 	(SOLO_EREF_EXT_ADDR(__solo) + SOLO_EREF_EXT_AREA(__solo))
 #define SOLO_MP4E_EXT_SIZE(__solo) \
-	max((__solo->nr_chans * 0x00080000),				\
-	    min(((__solo->sdram_size - SOLO_MP4E_EXT_ADDR(__solo)) -	\
-		 __SOLO_JPEG_MIN_SIZE(__solo)), 0x00ff0000))
+	clamp(__solo->sdram_size - SOLO_MP4E_EXT_ADDR(__solo) -	\
+	      __SOLO_JPEG_MIN_SIZE(__solo),			\
+	      __solo->nr_chans * 0x00080000, 0x00ff0000)
 
 #define __SOLO_JPEG_MIN_SIZE(__solo)		(__solo->nr_chans * 0x00080000)
 #define SOLO_JPEG_EXT_ADDR(__solo) \
 		(SOLO_MP4E_EXT_ADDR(__solo) + SOLO_MP4E_EXT_SIZE(__solo))
 #define SOLO_JPEG_EXT_SIZE(__solo) \
-	max(__SOLO_JPEG_MIN_SIZE(__solo),				\
-	    min((__solo->sdram_size - SOLO_JPEG_EXT_ADDR(__solo)), 0x00ff0000))
+	clamp(__solo->sdram_size - SOLO_JPEG_EXT_ADDR(__solo),	\
+	      __SOLO_JPEG_MIN_SIZE(__solo), 0x00ff0000)
 
 #define SOLO_SDRAM_END(__solo) \
 	(SOLO_JPEG_EXT_ADDR(__solo) + SOLO_JPEG_EXT_SIZE(__solo))
diff --git a/drivers/media/platform/chips-media/wave5/wave5-vpu.c b/drivers/media/platform/chips-media/wave5/wave5-vpu.c
index bfe4caa79cc9..0d90b5820bef 100644
--- a/drivers/media/platform/chips-media/wave5/wave5-vpu.c
+++ b/drivers/media/platform/chips-media/wave5/wave5-vpu.c
@@ -272,7 +272,7 @@ static const struct wave5_match_data ti_wave521c_data = {
 };
 
 static const struct of_device_id wave5_dt_ids[] = {
-	{ .compatible = "ti,k3-j721s2-wave521c", .data = &ti_wave521c_data },
+	{ .compatible = "ti,j721s2-wave521c", .data = &ti_wave521c_data },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, wave5_dt_ids);
diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c
index aebd3c12020b..c381c22135a2 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c
@@ -725,6 +725,9 @@ irqreturn_t rkisp1_capture_isr(int irq, void *ctx)
 	unsigned int i;
 	u32 status;
 
+	if (!rkisp1->irqs_enabled)
+		return IRQ_NONE;
+
 	status = rkisp1_read(rkisp1, RKISP1_CIF_MI_MIS);
 	if (!status)
 		return IRQ_NONE;
diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-common.h b/drivers/media/platform/rockchip/rkisp1/rkisp1-common.h
index 4b6b28c05b89..b757f75edecf 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-common.h
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-common.h
@@ -450,6 +450,7 @@ struct rkisp1_debug {
  * @debug:	   debug params to be exposed on debugfs
  * @info:	   version-specific ISP information
  * @irqs:          IRQ line numbers
+ * @irqs_enabled:  the hardware is enabled and can cause interrupts
  */
 struct rkisp1_device {
 	void __iomem *base_addr;
@@ -471,6 +472,7 @@ struct rkisp1_device {
 	struct rkisp1_debug debug;
 	const struct rkisp1_info *info;
 	int irqs[RKISP1_NUM_IRQS];
+	bool irqs_enabled;
 };
 
 /*
diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c
index b6e47e2f1b94..4202642e0523 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c
@@ -196,6 +196,9 @@ irqreturn_t rkisp1_csi_isr(int irq, void *ctx)
 	struct rkisp1_device *rkisp1 = dev_get_drvdata(dev);
 	u32 val, status;
 
+	if (!rkisp1->irqs_enabled)
+		return IRQ_NONE;
+
 	status = rkisp1_read(rkisp1, RKISP1_CIF_MIPI_MIS);
 	if (!status)
 		return IRQ_NONE;
diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c
index f96f821a7b50..73cf08a74011 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c
@@ -305,6 +305,24 @@ static int __maybe_unused rkisp1_runtime_suspend(struct device *dev)
 {
 	struct rkisp1_device *rkisp1 = dev_get_drvdata(dev);
 
+	rkisp1->irqs_enabled = false;
+	/* Make sure the IRQ handler will see the above */
+	mb();
+
+	/*
+	 * Wait until any running IRQ handler has returned. The IRQ handler
+	 * may get called even after this (as it's a shared interrupt line)
+	 * but the 'irqs_enabled' flag will make the handler return immediately.
+	 */
+	for (unsigned int il = 0; il < ARRAY_SIZE(rkisp1->irqs); ++il) {
+		if (rkisp1->irqs[il] == -1)
+			continue;
+
+		/* Skip if the irq line is the same as previous */
+		if (il == 0 || rkisp1->irqs[il - 1] != rkisp1->irqs[il])
+			synchronize_irq(rkisp1->irqs[il]);
+	}
+
 	clk_bulk_disable_unprepare(rkisp1->clk_size, rkisp1->clks);
 	return pinctrl_pm_select_sleep_state(dev);
 }
@@ -321,6 +339,10 @@ static int __maybe_unused rkisp1_runtime_resume(struct device *dev)
 	if (ret)
 		return ret;
 
+	rkisp1->irqs_enabled = true;
+	/* Make sure the IRQ handler will see the above */
+	mb();
+
 	return 0;
 }
 
@@ -559,7 +581,7 @@ static int rkisp1_probe(struct platform_device *pdev)
 				rkisp1->irqs[il] = irq;
 		}
 
-		ret = devm_request_irq(dev, irq, info->isrs[i].isr, 0,
+		ret = devm_request_irq(dev, irq, info->isrs[i].isr, IRQF_SHARED,
 				       dev_driver_string(dev), dev);
 		if (ret) {
 			dev_err(dev, "request irq failed: %d\n", ret);
diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c
index f00873d31c42..78a1f7a1499b 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c
@@ -976,6 +976,9 @@ irqreturn_t rkisp1_isp_isr(int irq, void *ctx)
 	struct rkisp1_device *rkisp1 = dev_get_drvdata(dev);
 	u32 status, isp_err;
 
+	if (!rkisp1->irqs_enabled)
+		return IRQ_NONE;
+
 	status = rkisp1_read(rkisp1, RKISP1_CIF_ISP_MIS);
 	if (!status)
 		return IRQ_NONE;
diff --git a/drivers/media/rc/Kconfig b/drivers/media/rc/Kconfig
index 2afe67ffa285..74d69ce22a33 100644
--- a/drivers/media/rc/Kconfig
+++ b/drivers/media/rc/Kconfig
@@ -319,6 +319,7 @@ config IR_PWM_TX
 	tristate "PWM IR transmitter"
 	depends on LIRC
 	depends on PWM
+	depends on HIGH_RES_TIMERS
 	depends on OF
 	help
 	   Say Y if you want to use a PWM based IR transmitter. This is
diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c
index fe17c7f98e81..52d82cbe7685 100644
--- a/drivers/media/rc/bpf-lirc.c
+++ b/drivers/media/rc/bpf-lirc.c
@@ -253,7 +253,7 @@ int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 	if (attr->attach_flags)
 		return -EINVAL;
 
-	rcdev = rc_dev_get_from_fd(attr->target_fd);
+	rcdev = rc_dev_get_from_fd(attr->target_fd, true);
 	if (IS_ERR(rcdev))
 		return PTR_ERR(rcdev);
 
@@ -278,7 +278,7 @@ int lirc_prog_detach(const union bpf_attr *attr)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	rcdev = rc_dev_get_from_fd(attr->target_fd);
+	rcdev = rc_dev_get_from_fd(attr->target_fd, true);
 	if (IS_ERR(rcdev)) {
 		bpf_prog_put(prog);
 		return PTR_ERR(rcdev);
@@ -303,7 +303,7 @@ int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr)
 	if (attr->query.query_flags)
 		return -EINVAL;
 
-	rcdev = rc_dev_get_from_fd(attr->query.target_fd);
+	rcdev = rc_dev_get_from_fd(attr->query.target_fd, false);
 	if (IS_ERR(rcdev))
 		return PTR_ERR(rcdev);
 
diff --git a/drivers/media/rc/ir_toy.c b/drivers/media/rc/ir_toy.c
index 196806709259..69e630d85262 100644
--- a/drivers/media/rc/ir_toy.c
+++ b/drivers/media/rc/ir_toy.c
@@ -332,6 +332,7 @@ static int irtoy_tx(struct rc_dev *rc, uint *txbuf, uint count)
 			    sizeof(COMMAND_SMODE_EXIT), STATE_COMMAND_NO_RESP);
 	if (err) {
 		dev_err(irtoy->dev, "exit sample mode: %d\n", err);
+		kfree(buf);
 		return err;
 	}
 
@@ -339,6 +340,7 @@ static int irtoy_tx(struct rc_dev *rc, uint *txbuf, uint count)
 			    sizeof(COMMAND_SMODE_ENTER), STATE_COMMAND);
 	if (err) {
 		dev_err(irtoy->dev, "enter sample mode: %d\n", err);
+		kfree(buf);
 		return err;
 	}
 
diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c
index a537734832c5..caad59f76793 100644
--- a/drivers/media/rc/lirc_dev.c
+++ b/drivers/media/rc/lirc_dev.c
@@ -814,7 +814,7 @@ void __exit lirc_dev_exit(void)
 	unregister_chrdev_region(lirc_base_dev, RC_DEV_MAX);
 }
 
-struct rc_dev *rc_dev_get_from_fd(int fd)
+struct rc_dev *rc_dev_get_from_fd(int fd, bool write)
 {
 	struct fd f = fdget(fd);
 	struct lirc_fh *fh;
@@ -828,6 +828,9 @@ struct rc_dev *rc_dev_get_from_fd(int fd)
 		return ERR_PTR(-EINVAL);
 	}
 
+	if (write && !(f.file->f_mode & FMODE_WRITE))
+		return ERR_PTR(-EPERM);
+
 	fh = f.file->private_data;
 	dev = fh->rc;
 
diff --git a/drivers/media/rc/rc-core-priv.h b/drivers/media/rc/rc-core-priv.h
index ef1e95e1af7f..7df949fc65e2 100644
--- a/drivers/media/rc/rc-core-priv.h
+++ b/drivers/media/rc/rc-core-priv.h
@@ -325,7 +325,7 @@ void lirc_raw_event(struct rc_dev *dev, struct ir_raw_event ev);
 void lirc_scancode_event(struct rc_dev *dev, struct lirc_scancode *lsc);
 int lirc_register(struct rc_dev *dev);
 void lirc_unregister(struct rc_dev *dev);
-struct rc_dev *rc_dev_get_from_fd(int fd);
+struct rc_dev *rc_dev_get_from_fd(int fd, bool write);
 #else
 static inline int lirc_dev_init(void) { return 0; }
 static inline void lirc_dev_exit(void) {}
diff --git a/drivers/memory/tegra/tegra186.c b/drivers/memory/tegra/tegra186.c
index 0ff014a9d3cd..1b3183951bfe 100644
--- a/drivers/memory/tegra/tegra186.c
+++ b/drivers/memory/tegra/tegra186.c
@@ -114,9 +114,12 @@ static void tegra186_mc_client_sid_override(struct tegra_mc *mc,
 static int tegra186_mc_probe_device(struct tegra_mc *mc, struct device *dev)
 {
 #if IS_ENABLED(CONFIG_IOMMU_API)
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 	struct of_phandle_args args;
 	unsigned int i, index = 0;
+	u32 sid;
+
+	if (!tegra_dev_iommu_get_stream_id(dev, &sid))
+		return 0;
 
 	while (!of_parse_phandle_with_args(dev->of_node, "interconnects", "#interconnect-cells",
 					   index, &args)) {
@@ -124,11 +127,10 @@ static int tegra186_mc_probe_device(struct tegra_mc *mc, struct device *dev)
 			for (i = 0; i < mc->soc->num_clients; i++) {
 				const struct tegra_mc_client *client = &mc->soc->clients[i];
 
-				if (client->id == args.args[0]) {
-					u32 sid = fwspec->ids[0] & MC_SID_STREAMID_OVERRIDE_MASK;
-
-					tegra186_mc_client_sid_override(mc, client, sid);
-				}
+				if (client->id == args.args[0])
+					tegra186_mc_client_sid_override(
+						mc, client,
+						sid & MC_SID_STREAMID_OVERRIDE_MASK);
 			}
 		}
 
diff --git a/drivers/memstick/core/ms_block.c b/drivers/memstick/core/ms_block.c
index 04115cd92433..47a314a4eb6f 100644
--- a/drivers/memstick/core/ms_block.c
+++ b/drivers/memstick/core/ms_block.c
@@ -2078,6 +2078,12 @@ static const struct blk_mq_ops msb_mq_ops = {
 static int msb_init_disk(struct memstick_dev *card)
 {
 	struct msb_data *msb = memstick_get_drvdata(card);
+	struct queue_limits lim = {
+		.logical_block_size	= msb->page_size,
+		.max_hw_sectors		= MS_BLOCK_MAX_PAGES,
+		.max_segments		= MS_BLOCK_MAX_SEGS,
+		.max_segment_size	= MS_BLOCK_MAX_PAGES * msb->page_size,
+	};
 	int rc;
 	unsigned long capacity;
 
@@ -2093,19 +2099,13 @@ static int msb_init_disk(struct memstick_dev *card)
 	if (rc)
 		goto out_release_id;
 
-	msb->disk = blk_mq_alloc_disk(&msb->tag_set, card);
+	msb->disk = blk_mq_alloc_disk(&msb->tag_set, &lim, card);
 	if (IS_ERR(msb->disk)) {
 		rc = PTR_ERR(msb->disk);
 		goto out_free_tag_set;
 	}
 	msb->queue = msb->disk->queue;
 
-	blk_queue_max_hw_sectors(msb->queue, MS_BLOCK_MAX_PAGES);
-	blk_queue_max_segments(msb->queue, MS_BLOCK_MAX_SEGS);
-	blk_queue_max_segment_size(msb->queue,
-				   MS_BLOCK_MAX_PAGES * msb->page_size);
-	blk_queue_logical_block_size(msb->queue, msb->page_size);
-
 	sprintf(msb->disk->disk_name, "msblk%d", msb->disk_id);
 	msb->disk->fops = &msb_bdops;
 	msb->disk->private_data = msb;
diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c
index 5a69ed33999b..49accfdc89d6 100644
--- a/drivers/memstick/core/mspro_block.c
+++ b/drivers/memstick/core/mspro_block.c
@@ -1103,6 +1103,12 @@ static const struct blk_mq_ops mspro_mq_ops = {
 static int mspro_block_init_disk(struct memstick_dev *card)
 {
 	struct mspro_block_data *msb = memstick_get_drvdata(card);
+	struct queue_limits lim = {
+		.logical_block_size	= msb->page_size,
+		.max_hw_sectors		= MSPRO_BLOCK_MAX_PAGES,
+		.max_segments		= MSPRO_BLOCK_MAX_SEGS,
+		.max_segment_size	= MSPRO_BLOCK_MAX_PAGES * msb->page_size,
+	};
 	struct mspro_devinfo *dev_info = NULL;
 	struct mspro_sys_info *sys_info = NULL;
 	struct mspro_sys_attr *s_attr = NULL;
@@ -1138,18 +1144,13 @@ static int mspro_block_init_disk(struct memstick_dev *card)
 	if (rc)
 		goto out_release_id;
 
-	msb->disk = blk_mq_alloc_disk(&msb->tag_set, card);
+	msb->disk = blk_mq_alloc_disk(&msb->tag_set, &lim, card);
 	if (IS_ERR(msb->disk)) {
 		rc = PTR_ERR(msb->disk);
 		goto out_free_tag_set;
 	}
 	msb->queue = msb->disk->queue;
 
-	blk_queue_max_hw_sectors(msb->queue, MSPRO_BLOCK_MAX_PAGES);
-	blk_queue_max_segments(msb->queue, MSPRO_BLOCK_MAX_SEGS);
-	blk_queue_max_segment_size(msb->queue,
-				   MSPRO_BLOCK_MAX_PAGES * msb->page_size);
-
 	msb->disk->major = major;
 	msb->disk->first_minor = disk_id << MSPRO_BLOCK_PART_SHIFT;
 	msb->disk->minors = 1 << MSPRO_BLOCK_PART_SHIFT;
@@ -1158,8 +1159,6 @@ static int mspro_block_init_disk(struct memstick_dev *card)
 
 	sprintf(msb->disk->disk_name, "mspblk%d", disk_id);
 
-	blk_queue_logical_block_size(msb->queue, msb->page_size);
-
 	capacity = be16_to_cpu(sys_info->user_block_count);
 	capacity *= be16_to_cpu(sys_info->block_size);
 	capacity *= msb->page_size >> 9;
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 925c19ee513b..e7a6e45b9fac 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -1483,6 +1483,7 @@ config MFD_SYSCON
 
 config MFD_TI_AM335X_TSCADC
 	tristate "TI ADC / Touch Screen chip support"
+	depends on ARCH_OMAP2PLUS || ARCH_K3 || COMPILE_TEST
 	select MFD_CORE
 	select REGMAP
 	select REGMAP_MMIO
diff --git a/drivers/mfd/ab8500-sysctrl.c b/drivers/mfd/ab8500-sysctrl.c
index eeeb62415f53..8f3ebe651eea 100644
--- a/drivers/mfd/ab8500-sysctrl.c
+++ b/drivers/mfd/ab8500-sysctrl.c
@@ -30,7 +30,7 @@ static void ab8500_power_off(void)
 {
 	sigset_t old;
 	sigset_t all;
-	static const char * const pss[] = {"ab8500_ac", "pm2301", "ab8500_usb"};
+	static const char * const pss[] = {"ab8500_ac", "ab8500_usb"};
 	int i;
 	bool charger_present = false;
 	union power_supply_propval val;
@@ -140,14 +140,12 @@ static int ab8500_sysctrl_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int ab8500_sysctrl_remove(struct platform_device *pdev)
+static void ab8500_sysctrl_remove(struct platform_device *pdev)
 {
 	sysctrl_dev = NULL;
 
 	if (pm_power_off == ab8500_power_off)
 		pm_power_off = NULL;
-
-	return 0;
 }
 
 static const struct of_device_id ab8500_sysctrl_match[] = {
@@ -161,7 +159,7 @@ static struct platform_driver ab8500_sysctrl_driver = {
 		.of_match_table = ab8500_sysctrl_match,
 	},
 	.probe = ab8500_sysctrl_probe,
-	.remove = ab8500_sysctrl_remove,
+	.remove_new = ab8500_sysctrl_remove,
 };
 
 static int __init ab8500_sysctrl_init(void)
diff --git a/drivers/mfd/cros_ec_dev.c b/drivers/mfd/cros_ec_dev.c
index 79d393b602bf..603b1cd52785 100644
--- a/drivers/mfd/cros_ec_dev.c
+++ b/drivers/mfd/cros_ec_dev.c
@@ -288,13 +288,12 @@ failed:
 	return retval;
 }
 
-static int ec_device_remove(struct platform_device *pdev)
+static void ec_device_remove(struct platform_device *pdev)
 {
 	struct cros_ec_dev *ec = dev_get_drvdata(&pdev->dev);
 
 	mfd_remove_devices(ec->dev);
 	device_unregister(&ec->class_dev);
-	return 0;
 }
 
 static const struct platform_device_id cros_ec_id[] = {
@@ -309,7 +308,7 @@ static struct platform_driver cros_ec_dev_driver = {
 	},
 	.id_table = cros_ec_id,
 	.probe = ec_device_probe,
-	.remove = ec_device_remove,
+	.remove_new = ec_device_remove,
 };
 
 static int __init cros_ec_dev_init(void)
diff --git a/drivers/mfd/cs42l43-sdw.c b/drivers/mfd/cs42l43-sdw.c
index 7392b3d2e6b9..1d85bbf8cdd5 100644
--- a/drivers/mfd/cs42l43-sdw.c
+++ b/drivers/mfd/cs42l43-sdw.c
@@ -6,24 +6,23 @@
  *                         Cirrus Logic International Semiconductor Ltd.
  */
 
+#include <linux/device.h>
 #include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/mfd/cs42l43-regs.h>
 #include <linux/module.h>
-#include <linux/device.h>
 #include <linux/soundwire/sdw.h>
 #include <linux/soundwire/sdw_registers.h>
 #include <linux/soundwire/sdw_type.h>
 
 #include "cs42l43.h"
 
-enum cs42l43_sdw_ports {
-	CS42L43_DMIC_DEC_ASP_PORT = 1,
-	CS42L43_SPK_TX_PORT,
-	CS42L43_SPDIF_HP_PORT,
-	CS42L43_SPK_RX_PORT,
-	CS42L43_ASP_PORT,
-};
+#define CS42L43_SDW_PORT(port, chans) { \
+	.num = port, \
+	.max_ch = chans, \
+	.type = SDW_DPN_FULL, \
+	.max_word = 24, \
+}
 
 static const struct regmap_config cs42l43_sdw_regmap = {
 	.reg_bits		= 32,
@@ -42,65 +41,48 @@ static const struct regmap_config cs42l43_sdw_regmap = {
 	.num_reg_defaults	= ARRAY_SIZE(cs42l43_reg_default),
 };
 
+static const struct sdw_dpn_prop cs42l43_src_port_props[] = {
+	CS42L43_SDW_PORT(1, 4),
+	CS42L43_SDW_PORT(2, 2),
+	CS42L43_SDW_PORT(3, 2),
+	CS42L43_SDW_PORT(4, 2),
+};
+
+static const struct sdw_dpn_prop cs42l43_sink_port_props[] = {
+	CS42L43_SDW_PORT(5, 2),
+	CS42L43_SDW_PORT(6, 2),
+	CS42L43_SDW_PORT(7, 2),
+};
+
 static int cs42l43_read_prop(struct sdw_slave *sdw)
 {
 	struct sdw_slave_prop *prop = &sdw->prop;
 	struct device *dev = &sdw->dev;
-	struct sdw_dpn_prop *dpn;
-	unsigned long addr;
-	int nval;
 	int i;
-	u32 bit;
 
 	prop->use_domain_irq = true;
 	prop->paging_support = true;
 	prop->wake_capable = true;
-	prop->source_ports = BIT(CS42L43_DMIC_DEC_ASP_PORT) | BIT(CS42L43_SPK_TX_PORT);
-	prop->sink_ports = BIT(CS42L43_SPDIF_HP_PORT) |
-			   BIT(CS42L43_SPK_RX_PORT) | BIT(CS42L43_ASP_PORT);
 	prop->quirks = SDW_SLAVE_QUIRKS_INVALID_INITIAL_PARITY;
 	prop->scp_int1_mask = SDW_SCP_INT1_BUS_CLASH | SDW_SCP_INT1_PARITY |
 			      SDW_SCP_INT1_IMPL_DEF;
 
-	nval = hweight32(prop->source_ports);
-	prop->src_dpn_prop = devm_kcalloc(dev, nval, sizeof(*prop->src_dpn_prop),
-					  GFP_KERNEL);
+	for (i = 0; i < ARRAY_SIZE(cs42l43_src_port_props); i++)
+		prop->source_ports |= BIT(cs42l43_src_port_props[i].num);
+
+	prop->src_dpn_prop = devm_kmemdup(dev, cs42l43_src_port_props,
+					  sizeof(cs42l43_src_port_props), GFP_KERNEL);
 	if (!prop->src_dpn_prop)
 		return -ENOMEM;
 
-	i = 0;
-	dpn = prop->src_dpn_prop;
-	addr = prop->source_ports;
-	for_each_set_bit(bit, &addr, 32) {
-		dpn[i].num = bit;
-		dpn[i].max_ch = 2;
-		dpn[i].type = SDW_DPN_FULL;
-		dpn[i].max_word = 24;
-		i++;
-	}
-	/*
-	 * All ports are 2 channels max, except the first one,
-	 * CS42L43_DMIC_DEC_ASP_PORT.
-	 */
-	dpn[CS42L43_DMIC_DEC_ASP_PORT].max_ch = 4;
+	for (i = 0; i < ARRAY_SIZE(cs42l43_sink_port_props); i++)
+		prop->sink_ports |= BIT(cs42l43_sink_port_props[i].num);
 
-	nval = hweight32(prop->sink_ports);
-	prop->sink_dpn_prop = devm_kcalloc(dev, nval, sizeof(*prop->sink_dpn_prop),
-					   GFP_KERNEL);
+	prop->sink_dpn_prop = devm_kmemdup(dev, cs42l43_sink_port_props,
+					   sizeof(cs42l43_sink_port_props), GFP_KERNEL);
 	if (!prop->sink_dpn_prop)
 		return -ENOMEM;
 
-	i = 0;
-	dpn = prop->sink_dpn_prop;
-	addr = prop->sink_ports;
-	for_each_set_bit(bit, &addr, 32) {
-		dpn[i].num = bit;
-		dpn[i].max_ch = 2;
-		dpn[i].type = SDW_DPN_FULL;
-		dpn[i].max_word = 24;
-		i++;
-	}
-
 	return 0;
 }
 
diff --git a/drivers/mfd/da9062-core.c b/drivers/mfd/da9062-core.c
index 45da007d3e70..73a22107900c 100644
--- a/drivers/mfd/da9062-core.c
+++ b/drivers/mfd/da9062-core.c
@@ -588,16 +588,8 @@ static struct regmap_config da9062_regmap_config = {
 	.volatile_table = &da9062_aa_volatile_table,
 };
 
-static const struct of_device_id da9062_dt_ids[] = {
-	{ .compatible = "dlg,da9061", .data = (void *)COMPAT_TYPE_DA9061, },
-	{ .compatible = "dlg,da9062", .data = (void *)COMPAT_TYPE_DA9062, },
-	{ }
-};
-MODULE_DEVICE_TABLE(of, da9062_dt_ids);
-
 static int da9062_i2c_probe(struct i2c_client *i2c)
 {
-	const struct i2c_device_id *id = i2c_client_get_device_id(i2c);
 	struct da9062 *chip;
 	unsigned int irq_base = 0;
 	const struct mfd_cell *cell;
@@ -611,10 +603,7 @@ static int da9062_i2c_probe(struct i2c_client *i2c)
 	if (!chip)
 		return -ENOMEM;
 
-	if (i2c->dev.of_node)
-		chip->chip_type = (uintptr_t)of_device_get_match_data(&i2c->dev);
-	else
-		chip->chip_type = id->driver_data;
+	chip->chip_type = (uintptr_t)i2c_get_match_data(i2c);
 
 	i2c_set_clientdata(i2c, chip);
 	chip->dev = &i2c->dev;
@@ -714,10 +703,17 @@ static void da9062_i2c_remove(struct i2c_client *i2c)
 	regmap_del_irq_chip(i2c->irq, chip->regmap_irq);
 }
 
+static const struct of_device_id da9062_dt_ids[] = {
+	{ .compatible = "dlg,da9061", .data = (void *)COMPAT_TYPE_DA9061 },
+	{ .compatible = "dlg,da9062", .data = (void *)COMPAT_TYPE_DA9062 },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, da9062_dt_ids);
+
 static const struct i2c_device_id da9062_i2c_id[] = {
 	{ "da9061", COMPAT_TYPE_DA9061 },
 	{ "da9062", COMPAT_TYPE_DA9062 },
-	{ },
+	{ }
 };
 MODULE_DEVICE_TABLE(i2c, da9062_i2c_id);
 
diff --git a/drivers/mfd/exynos-lpass.c b/drivers/mfd/exynos-lpass.c
index 1506d8d352b1..e58990c85ed8 100644
--- a/drivers/mfd/exynos-lpass.c
+++ b/drivers/mfd/exynos-lpass.c
@@ -137,7 +137,7 @@ static int exynos_lpass_probe(struct platform_device *pdev)
 	return devm_of_platform_populate(dev);
 }
 
-static int exynos_lpass_remove(struct platform_device *pdev)
+static void exynos_lpass_remove(struct platform_device *pdev)
 {
 	struct exynos_lpass *lpass = platform_get_drvdata(pdev);
 
@@ -146,8 +146,6 @@ static int exynos_lpass_remove(struct platform_device *pdev)
 	if (!pm_runtime_status_suspended(&pdev->dev))
 		exynos_lpass_disable(lpass);
 	regmap_exit(lpass->top);
-
-	return 0;
 }
 
 static int __maybe_unused exynos_lpass_suspend(struct device *dev)
@@ -187,7 +185,7 @@ static struct platform_driver exynos_lpass_driver = {
 		.of_match_table	= exynos_lpass_of_match,
 	},
 	.probe	= exynos_lpass_probe,
-	.remove	= exynos_lpass_remove,
+	.remove_new = exynos_lpass_remove,
 };
 module_platform_driver(exynos_lpass_driver);
 
diff --git a/drivers/mfd/fsl-imx25-tsadc.c b/drivers/mfd/fsl-imx25-tsadc.c
index 089c2ce615b6..74f38bf3778f 100644
--- a/drivers/mfd/fsl-imx25-tsadc.c
+++ b/drivers/mfd/fsl-imx25-tsadc.c
@@ -194,11 +194,9 @@ err_irq:
 	return ret;
 }
 
-static int mx25_tsadc_remove(struct platform_device *pdev)
+static void mx25_tsadc_remove(struct platform_device *pdev)
 {
 	mx25_tsadc_unset_irq(pdev);
-
-	return 0;
 }
 
 static const struct of_device_id mx25_tsadc_ids[] = {
@@ -213,7 +211,7 @@ static struct platform_driver mx25_tsadc_driver = {
 		.of_match_table = mx25_tsadc_ids,
 	},
 	.probe = mx25_tsadc_probe,
-	.remove = mx25_tsadc_remove,
+	.remove_new = mx25_tsadc_remove,
 };
 module_platform_driver(mx25_tsadc_driver);
 
diff --git a/drivers/mfd/hi655x-pmic.c b/drivers/mfd/hi655x-pmic.c
index 8feae8d8fd9d..042109304db4 100644
--- a/drivers/mfd/hi655x-pmic.c
+++ b/drivers/mfd/hi655x-pmic.c
@@ -144,13 +144,12 @@ static int hi655x_pmic_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int hi655x_pmic_remove(struct platform_device *pdev)
+static void hi655x_pmic_remove(struct platform_device *pdev)
 {
 	struct hi655x_pmic *pmic = platform_get_drvdata(pdev);
 
 	regmap_del_irq_chip(gpiod_to_irq(pmic->gpio), pmic->irq_data);
 	mfd_remove_devices(&pdev->dev);
-	return 0;
 }
 
 static const struct of_device_id hi655x_pmic_match[] = {
@@ -165,7 +164,7 @@ static struct platform_driver hi655x_pmic_driver = {
 		.of_match_table = hi655x_pmic_match,
 	},
 	.probe  = hi655x_pmic_probe,
-	.remove = hi655x_pmic_remove,
+	.remove_new = hi655x_pmic_remove,
 };
 module_platform_driver(hi655x_pmic_driver);
 
diff --git a/drivers/mfd/intel-lpss-acpi.c b/drivers/mfd/intel-lpss-acpi.c
index 212818aef93e..2a83f8678f1d 100644
--- a/drivers/mfd/intel-lpss-acpi.c
+++ b/drivers/mfd/intel-lpss-acpi.c
@@ -8,15 +8,20 @@
  *          Mika Westerberg <mika.westerberg@linux.intel.com>
  */
 
-#include <linux/acpi.h>
+#include <linux/device.h>
+#include <linux/gfp_types.h>
 #include <linux/ioport.h>
-#include <linux/kernel.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
+#include <linux/pm.h>
 #include <linux/pm_runtime.h>
 #include <linux/platform_device.h>
 #include <linux/property.h>
+
 #include <linux/pxa2xx_ssp.h>
 
+#include <asm/errno.h>
+
 #include "intel-lpss.h"
 
 static const struct property_entry spt_spi_properties[] = {
@@ -169,23 +174,20 @@ MODULE_DEVICE_TABLE(acpi, intel_lpss_acpi_ids);
 
 static int intel_lpss_acpi_probe(struct platform_device *pdev)
 {
+	const struct intel_lpss_platform_info *data;
 	struct intel_lpss_platform_info *info;
-	const struct acpi_device_id *id;
 	int ret;
 
-	id = acpi_match_device(intel_lpss_acpi_ids, &pdev->dev);
-	if (!id)
+	data = device_get_match_data(&pdev->dev);
+	if (!data)
 		return -ENODEV;
 
-	info = devm_kmemdup(&pdev->dev, (void *)id->driver_data, sizeof(*info),
-			    GFP_KERNEL);
+	info = devm_kmemdup(&pdev->dev, data, sizeof(*info), GFP_KERNEL);
 	if (!info)
 		return -ENOMEM;
 
+	/* No need to check mem and irq here as intel_lpss_probe() does it for us */
 	info->mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!info->mem)
-		return -ENODEV;
-
 	info->irq = platform_get_irq(pdev, 0);
 
 	ret = intel_lpss_probe(&pdev->dev, info);
@@ -198,23 +200,19 @@ static int intel_lpss_acpi_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int intel_lpss_acpi_remove(struct platform_device *pdev)
+static void intel_lpss_acpi_remove(struct platform_device *pdev)
 {
 	intel_lpss_remove(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-
-	return 0;
 }
 
-static INTEL_LPSS_PM_OPS(intel_lpss_acpi_pm_ops);
-
 static struct platform_driver intel_lpss_acpi_driver = {
 	.probe = intel_lpss_acpi_probe,
-	.remove = intel_lpss_acpi_remove,
+	.remove_new = intel_lpss_acpi_remove,
 	.driver = {
 		.name = "intel-lpss",
 		.acpi_match_table = intel_lpss_acpi_ids,
-		.pm = &intel_lpss_acpi_pm_ops,
+		.pm = pm_ptr(&intel_lpss_pm_ops),
 	},
 };
 
@@ -224,3 +222,4 @@ MODULE_AUTHOR("Andy Shevchenko <andriy.shevchenko@linux.intel.com>");
 MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>");
 MODULE_DESCRIPTION("Intel LPSS ACPI driver");
 MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS(INTEL_LPSS);
diff --git a/drivers/mfd/intel-lpss-pci.c b/drivers/mfd/intel-lpss-pci.c
index ae5759200622..4621d3950b8f 100644
--- a/drivers/mfd/intel-lpss-pci.c
+++ b/drivers/mfd/intel-lpss-pci.c
@@ -8,14 +8,19 @@
  *          Mika Westerberg <mika.westerberg@linux.intel.com>
  */
 
-#include <linux/ioport.h>
-#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/gfp_types.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/pm.h>
 #include <linux/pm_runtime.h>
 #include <linux/property.h>
+
 #include <linux/pxa2xx_ssp.h>
 
+#include <asm/errno.h>
+
 #include "intel-lpss.h"
 
 /* Some DSDTs have an unused GEXP ACPI device conflicting with I2C4 resources */
@@ -30,6 +35,7 @@ static const struct pci_device_id ignore_resource_conflicts_ids[] = {
 static int intel_lpss_pci_probe(struct pci_dev *pdev,
 				const struct pci_device_id *id)
 {
+	const struct intel_lpss_platform_info *data = (void *)id->driver_data;
 	struct intel_lpss_platform_info *info;
 	int ret;
 
@@ -37,13 +43,17 @@ static int intel_lpss_pci_probe(struct pci_dev *pdev,
 	if (ret)
 		return ret;
 
-	info = devm_kmemdup(&pdev->dev, (void *)id->driver_data, sizeof(*info),
-			    GFP_KERNEL);
+	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_LEGACY);
+	if (ret < 0)
+		return ret;
+
+	info = devm_kmemdup(&pdev->dev, data, sizeof(*info), GFP_KERNEL);
 	if (!info)
 		return -ENOMEM;
 
-	info->mem = &pdev->resource[0];
-	info->irq = pdev->irq;
+	/* No need to check mem and irq here as intel_lpss_probe() does it for us */
+	info->mem = pci_resource_n(pdev, 0);
+	info->irq = pci_irq_vector(pdev, 0);
 
 	if (pci_match_id(ignore_resource_conflicts_ids, pdev))
 		info->ignore_resource_conflicts = true;
@@ -72,8 +82,6 @@ static void intel_lpss_pci_remove(struct pci_dev *pdev)
 	intel_lpss_remove(&pdev->dev);
 }
 
-static INTEL_LPSS_PM_OPS(intel_lpss_pci_pm_ops);
-
 static const struct property_entry spt_spi_properties[] = {
 	PROPERTY_ENTRY_U32("intel,spi-pxa2xx-type", LPSS_SPT_SSP),
 	{ }
@@ -584,7 +592,7 @@ static struct pci_driver intel_lpss_pci_driver = {
 	.probe = intel_lpss_pci_probe,
 	.remove = intel_lpss_pci_remove,
 	.driver = {
-		.pm = &intel_lpss_pci_pm_ops,
+		.pm = pm_ptr(&intel_lpss_pm_ops),
 	},
 };
 
@@ -594,3 +602,4 @@ MODULE_AUTHOR("Andy Shevchenko <andriy.shevchenko@linux.intel.com>");
 MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>");
 MODULE_DESCRIPTION("Intel LPSS PCI driver");
 MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS(INTEL_LPSS);
diff --git a/drivers/mfd/intel-lpss.c b/drivers/mfd/intel-lpss.c
index 9591b354072a..eff423f7dd28 100644
--- a/drivers/mfd/intel-lpss.c
+++ b/drivers/mfd/intel-lpss.c
@@ -10,26 +10,34 @@
  *          Jarkko Nikula <jarkko.nikula@linux.intel.com>
  */
 
-#include <linux/clk.h>
+#include <linux/array_size.h>
+#include <linux/bits.h>
 #include <linux/clkdev.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/gfp_types.h>
 #include <linux/idr.h>
 #include <linux/io.h>
 #include <linux/ioport.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/mfd/core.h>
+#include <linux/module.h>
+#include <linux/pm.h>
 #include <linux/pm_qos.h>
 #include <linux/pm_runtime.h>
-#include <linux/property.h>
-#include <linux/seq_file.h>
+#include <linux/sprintf.h>
+#include <linux/types.h>
+
 #include <linux/io-64-nonatomic-lo-hi.h>
 
 #include <linux/dma/idma64.h>
 
 #include "intel-lpss.h"
 
+struct dentry;
+
 #define LPSS_DEV_OFFSET		0x000
 #define LPSS_DEV_SIZE		0x200
 #define LPSS_PRIV_OFFSET	0x200
@@ -301,8 +309,8 @@ static int intel_lpss_register_clock_divider(struct intel_lpss *lpss,
 
 	snprintf(name, sizeof(name), "%s-div", devname);
 	tmp = clk_register_fractional_divider(NULL, name, __clk_get_name(tmp),
+					      0, lpss->priv, 1, 15, 16, 15,
 					      CLK_FRAC_DIVIDER_POWER_OF_TWO_PS,
-					      lpss->priv, 1, 15, 16, 15, 0,
 					      NULL);
 	if (IS_ERR(tmp))
 		return PTR_ERR(tmp);
@@ -378,9 +386,12 @@ int intel_lpss_probe(struct device *dev,
 	struct intel_lpss *lpss;
 	int ret;
 
-	if (!info || !info->mem || info->irq <= 0)
+	if (!info || !info->mem)
 		return -EINVAL;
 
+	if (info->irq < 0)
+		return info->irq;
+
 	lpss = devm_kzalloc(dev, sizeof(*lpss), GFP_KERNEL);
 	if (!lpss)
 		return -ENOMEM;
@@ -405,7 +416,7 @@ int intel_lpss_probe(struct device *dev,
 
 	intel_lpss_init_dev(lpss);
 
-	lpss->devid = ida_simple_get(&intel_lpss_devid_ida, 0, 0, GFP_KERNEL);
+	lpss->devid = ida_alloc(&intel_lpss_devid_ida, GFP_KERNEL);
 	if (lpss->devid < 0)
 		return lpss->devid;
 
@@ -442,11 +453,11 @@ err_remove_ltr:
 	intel_lpss_unregister_clock(lpss);
 
 err_clk_register:
-	ida_simple_remove(&intel_lpss_devid_ida, lpss->devid);
+	ida_free(&intel_lpss_devid_ida, lpss->devid);
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(intel_lpss_probe);
+EXPORT_SYMBOL_NS_GPL(intel_lpss_probe, INTEL_LPSS);
 
 void intel_lpss_remove(struct device *dev)
 {
@@ -456,11 +467,10 @@ void intel_lpss_remove(struct device *dev)
 	intel_lpss_debugfs_remove(lpss);
 	intel_lpss_ltr_hide(lpss);
 	intel_lpss_unregister_clock(lpss);
-	ida_simple_remove(&intel_lpss_devid_ida, lpss->devid);
+	ida_free(&intel_lpss_devid_ida, lpss->devid);
 }
-EXPORT_SYMBOL_GPL(intel_lpss_remove);
+EXPORT_SYMBOL_NS_GPL(intel_lpss_remove, INTEL_LPSS);
 
-#ifdef CONFIG_PM
 static int resume_lpss_device(struct device *dev, void *data)
 {
 	if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND))
@@ -469,7 +479,7 @@ static int resume_lpss_device(struct device *dev, void *data)
 	return 0;
 }
 
-int intel_lpss_prepare(struct device *dev)
+static int intel_lpss_prepare(struct device *dev)
 {
 	/*
 	 * Resume both child devices before entering system sleep. This
@@ -478,9 +488,8 @@ int intel_lpss_prepare(struct device *dev)
 	device_for_each_child_reverse(dev, NULL, resume_lpss_device);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(intel_lpss_prepare);
 
-int intel_lpss_suspend(struct device *dev)
+static int intel_lpss_suspend(struct device *dev)
 {
 	struct intel_lpss *lpss = dev_get_drvdata(dev);
 	unsigned int i;
@@ -499,9 +508,8 @@ int intel_lpss_suspend(struct device *dev)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(intel_lpss_suspend);
 
-int intel_lpss_resume(struct device *dev)
+static int intel_lpss_resume(struct device *dev)
 {
 	struct intel_lpss *lpss = dev_get_drvdata(dev);
 	unsigned int i;
@@ -514,8 +522,12 @@ int intel_lpss_resume(struct device *dev)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(intel_lpss_resume);
-#endif
+
+EXPORT_NS_GPL_DEV_PM_OPS(intel_lpss_pm_ops, INTEL_LPSS) = {
+	.prepare = pm_sleep_ptr(&intel_lpss_prepare),
+	LATE_SYSTEM_SLEEP_PM_OPS(intel_lpss_suspend, intel_lpss_resume)
+	RUNTIME_PM_OPS(intel_lpss_suspend, intel_lpss_resume, NULL)
+};
 
 static int __init intel_lpss_init(void)
 {
diff --git a/drivers/mfd/intel-lpss.h b/drivers/mfd/intel-lpss.h
index 062ce95b68b9..c1d72b117ed5 100644
--- a/drivers/mfd/intel-lpss.h
+++ b/drivers/mfd/intel-lpss.h
@@ -30,32 +30,6 @@ int intel_lpss_probe(struct device *dev,
 		     const struct intel_lpss_platform_info *info);
 void intel_lpss_remove(struct device *dev);
 
-#ifdef CONFIG_PM
-int intel_lpss_prepare(struct device *dev);
-int intel_lpss_suspend(struct device *dev);
-int intel_lpss_resume(struct device *dev);
-
-#ifdef CONFIG_PM_SLEEP
-#define INTEL_LPSS_SLEEP_PM_OPS			\
-	.prepare = intel_lpss_prepare,		\
-	SET_LATE_SYSTEM_SLEEP_PM_OPS(intel_lpss_suspend, intel_lpss_resume)
-#else
-#define INTEL_LPSS_SLEEP_PM_OPS
-#endif
-
-#define INTEL_LPSS_RUNTIME_PM_OPS		\
-	.runtime_suspend = intel_lpss_suspend,	\
-	.runtime_resume = intel_lpss_resume,
-
-#else /* !CONFIG_PM */
-#define INTEL_LPSS_SLEEP_PM_OPS
-#define INTEL_LPSS_RUNTIME_PM_OPS
-#endif /* CONFIG_PM */
-
-#define INTEL_LPSS_PM_OPS(name)			\
-const struct dev_pm_ops name = {		\
-	INTEL_LPSS_SLEEP_PM_OPS			\
-	INTEL_LPSS_RUNTIME_PM_OPS		\
-}
+extern const struct dev_pm_ops intel_lpss_pm_ops;
 
 #endif /* __MFD_INTEL_LPSS_H */
diff --git a/drivers/mfd/kempld-core.c b/drivers/mfd/kempld-core.c
index 33c6cfe9fe42..67af36a38913 100644
--- a/drivers/mfd/kempld-core.c
+++ b/drivers/mfd/kempld-core.c
@@ -535,7 +535,7 @@ static int kempld_probe(struct platform_device *pdev)
 	return kempld_detect_device(pld);
 }
 
-static int kempld_remove(struct platform_device *pdev)
+static void kempld_remove(struct platform_device *pdev)
 {
 	struct kempld_device_data *pld = platform_get_drvdata(pdev);
 	const struct kempld_platform_data *pdata = dev_get_platdata(pld->dev);
@@ -544,8 +544,6 @@ static int kempld_remove(struct platform_device *pdev)
 
 	mfd_remove_devices(&pdev->dev);
 	pdata->release_hardware_mutex(pld);
-
-	return 0;
 }
 
 #ifdef CONFIG_ACPI
@@ -563,7 +561,7 @@ static struct platform_driver kempld_driver = {
 		.acpi_match_table = ACPI_PTR(kempld_acpi_table),
 	},
 	.probe		= kempld_probe,
-	.remove		= kempld_remove,
+	.remove_new	= kempld_remove,
 };
 
 static const struct dmi_system_id kempld_dmi_table[] __initconst = {
diff --git a/drivers/mfd/mcp-sa11x0.c b/drivers/mfd/mcp-sa11x0.c
index 1c9831b78cf9..3883e472b739 100644
--- a/drivers/mfd/mcp-sa11x0.c
+++ b/drivers/mfd/mcp-sa11x0.c
@@ -232,7 +232,7 @@ static int mcp_sa11x0_probe(struct platform_device *dev)
 	return ret;
 }
 
-static int mcp_sa11x0_remove(struct platform_device *dev)
+static void mcp_sa11x0_remove(struct platform_device *dev)
 {
 	struct mcp *mcp = platform_get_drvdata(dev);
 	struct mcp_sa11x0 *m = priv(mcp);
@@ -251,8 +251,6 @@ static int mcp_sa11x0_remove(struct platform_device *dev)
 	mcp_host_free(mcp);
 	release_mem_region(mem1->start, resource_size(mem1));
 	release_mem_region(mem0->start, resource_size(mem0));
-
-	return 0;
 }
 
 static int mcp_sa11x0_suspend(struct device *dev)
@@ -288,7 +286,7 @@ static const struct dev_pm_ops mcp_sa11x0_pm_ops = {
 
 static struct platform_driver mcp_sa11x0_driver = {
 	.probe		= mcp_sa11x0_probe,
-	.remove		= mcp_sa11x0_remove,
+	.remove_new	= mcp_sa11x0_remove,
 	.driver		= {
 		.name	= DRIVER_NAME,
 		.pm	= pm_sleep_ptr(&mcp_sa11x0_pm_ops),
diff --git a/drivers/mfd/mxs-lradc.c b/drivers/mfd/mxs-lradc.c
index ec1b356562b9..73893890b50a 100644
--- a/drivers/mfd/mxs-lradc.c
+++ b/drivers/mfd/mxs-lradc.c
@@ -230,13 +230,11 @@ err_clk:
 	return ret;
 }
 
-static int mxs_lradc_remove(struct platform_device *pdev)
+static void mxs_lradc_remove(struct platform_device *pdev)
 {
 	struct mxs_lradc *lradc = platform_get_drvdata(pdev);
 
 	clk_disable_unprepare(lradc->clk);
-
-	return 0;
 }
 
 static struct platform_driver mxs_lradc_driver = {
@@ -245,7 +243,7 @@ static struct platform_driver mxs_lradc_driver = {
 		.of_match_table = mxs_lradc_dt_ids,
 	},
 	.probe = mxs_lradc_probe,
-	.remove = mxs_lradc_remove,
+	.remove_new = mxs_lradc_remove,
 };
 module_platform_driver(mxs_lradc_driver);
 
diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c
index 78f1bb55dbc0..ebc62033db16 100644
--- a/drivers/mfd/omap-usb-host.c
+++ b/drivers/mfd/omap-usb-host.c
@@ -816,13 +816,12 @@ static int usbhs_omap_remove_child(struct device *dev, void *data)
  *
  * Reverses the effect of usbhs_omap_probe().
  */
-static int usbhs_omap_remove(struct platform_device *pdev)
+static void usbhs_omap_remove(struct platform_device *pdev)
 {
 	pm_runtime_disable(&pdev->dev);
 
 	/* remove children */
 	device_for_each_child(&pdev->dev, NULL, usbhs_omap_remove_child);
-	return 0;
 }
 
 static const struct dev_pm_ops usbhsomap_dev_pm_ops = {
@@ -845,7 +844,7 @@ static struct platform_driver usbhs_omap_driver = {
 		.of_match_table = usbhs_omap_dt_ids,
 	},
 	.probe		= usbhs_omap_probe,
-	.remove		= usbhs_omap_remove,
+	.remove_new	= usbhs_omap_remove,
 };
 
 MODULE_AUTHOR("Keshava Munegowda <keshava_mgowda@ti.com>");
diff --git a/drivers/mfd/omap-usb-tll.c b/drivers/mfd/omap-usb-tll.c
index 906353735c78..b6303ddb013b 100644
--- a/drivers/mfd/omap-usb-tll.c
+++ b/drivers/mfd/omap-usb-tll.c
@@ -270,7 +270,7 @@ static int usbtll_omap_probe(struct platform_device *pdev)
  *
  * Reverses the effect of usbtll_omap_probe().
  */
-static int usbtll_omap_remove(struct platform_device *pdev)
+static void usbtll_omap_remove(struct platform_device *pdev)
 {
 	struct usbtll_omap *tll = platform_get_drvdata(pdev);
 	int i;
@@ -287,7 +287,6 @@ static int usbtll_omap_remove(struct platform_device *pdev)
 	}
 
 	pm_runtime_disable(&pdev->dev);
-	return 0;
 }
 
 static const struct of_device_id usbtll_omap_dt_ids[] = {
@@ -303,7 +302,7 @@ static struct platform_driver usbtll_omap_driver = {
 		.of_match_table = usbtll_omap_dt_ids,
 	},
 	.probe		= usbtll_omap_probe,
-	.remove		= usbtll_omap_remove,
+	.remove_new	= usbtll_omap_remove,
 };
 
 int omap_tll_init(struct usbhs_omap_platform_data *pdata)
diff --git a/drivers/mfd/pcf50633-adc.c b/drivers/mfd/pcf50633-adc.c
index 191b1bc6141c..ab55906f91f9 100644
--- a/drivers/mfd/pcf50633-adc.c
+++ b/drivers/mfd/pcf50633-adc.c
@@ -218,7 +218,7 @@ static int pcf50633_adc_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int pcf50633_adc_remove(struct platform_device *pdev)
+static void pcf50633_adc_remove(struct platform_device *pdev)
 {
 	struct pcf50633_adc *adc = platform_get_drvdata(pdev);
 	int i, head;
@@ -236,8 +236,6 @@ static int pcf50633_adc_remove(struct platform_device *pdev)
 		kfree(adc->queue[i]);
 
 	mutex_unlock(&adc->queue_mutex);
-
-	return 0;
 }
 
 static struct platform_driver pcf50633_adc_driver = {
@@ -245,7 +243,7 @@ static struct platform_driver pcf50633_adc_driver = {
 		.name = "pcf50633-adc",
 	},
 	.probe = pcf50633_adc_probe,
-	.remove = pcf50633_adc_remove,
+	.remove_new = pcf50633_adc_remove,
 };
 
 module_platform_driver(pcf50633_adc_driver);
diff --git a/drivers/mfd/qcom-pm8xxx.c b/drivers/mfd/qcom-pm8xxx.c
index 07c531bd1236..8b6285f687da 100644
--- a/drivers/mfd/qcom-pm8xxx.c
+++ b/drivers/mfd/qcom-pm8xxx.c
@@ -585,19 +585,17 @@ static int pm8xxx_remove_child(struct device *dev, void *unused)
 	return 0;
 }
 
-static int pm8xxx_remove(struct platform_device *pdev)
+static void pm8xxx_remove(struct platform_device *pdev)
 {
 	struct pm_irq_chip *chip = platform_get_drvdata(pdev);
 
 	device_for_each_child(&pdev->dev, NULL, pm8xxx_remove_child);
 	irq_domain_remove(chip->irqdomain);
-
-	return 0;
 }
 
 static struct platform_driver pm8xxx_driver = {
 	.probe		= pm8xxx_probe,
-	.remove		= pm8xxx_remove,
+	.remove_new	= pm8xxx_remove,
 	.driver		= {
 		.name	= "pm8xxx-core",
 		.of_match_table = pm8xxx_id_table,
diff --git a/drivers/mfd/qcom-spmi-pmic.c b/drivers/mfd/qcom-spmi-pmic.c
index 4549fa9f7d4b..eab5bf6cff10 100644
--- a/drivers/mfd/qcom-spmi-pmic.c
+++ b/drivers/mfd/qcom-spmi-pmic.c
@@ -53,6 +53,7 @@ static const struct of_device_id pmic_spmi_id_table[] = {
 	{ .compatible = "qcom,pm8901", .data = N_USIDS(2) },
 	{ .compatible = "qcom,pm8909", .data = N_USIDS(2) },
 	{ .compatible = "qcom,pm8916", .data = N_USIDS(2) },
+	{ .compatible = "qcom,pm8937", .data = N_USIDS(2) },
 	{ .compatible = "qcom,pm8941", .data = N_USIDS(2) },
 	{ .compatible = "qcom,pm8950", .data = N_USIDS(2) },
 	{ .compatible = "qcom,pm8994", .data = N_USIDS(2) },
diff --git a/drivers/mfd/rave-sp.c b/drivers/mfd/rave-sp.c
index f62422740de2..6ff84b2600c5 100644
--- a/drivers/mfd/rave-sp.c
+++ b/drivers/mfd/rave-sp.c
@@ -471,17 +471,17 @@ static void rave_sp_receive_frame(struct rave_sp *sp,
 		rave_sp_receive_reply(sp, data, length);
 }
 
-static int rave_sp_receive_buf(struct serdev_device *serdev,
-			       const unsigned char *buf, size_t size)
+static ssize_t rave_sp_receive_buf(struct serdev_device *serdev,
+				   const u8 *buf, size_t size)
 {
 	struct device *dev = &serdev->dev;
 	struct rave_sp *sp = dev_get_drvdata(dev);
 	struct rave_sp_deframer *deframer = &sp->deframer;
-	const unsigned char *src = buf;
-	const unsigned char *end = buf + size;
+	const u8 *src = buf;
+	const u8 *end = buf + size;
 
 	while (src < end) {
-		const unsigned char byte = *src++;
+		const u8 byte = *src++;
 
 		switch (deframer->state) {
 		case RAVE_SP_EXPECT_SOF:
diff --git a/drivers/mfd/rk8xx-core.c b/drivers/mfd/rk8xx-core.c
index c47164a3ec1d..b1ffc3b9e2be 100644
--- a/drivers/mfd/rk8xx-core.c
+++ b/drivers/mfd/rk8xx-core.c
@@ -53,76 +53,68 @@ static const struct resource rk817_charger_resources[] = {
 };
 
 static const struct mfd_cell rk805s[] = {
-	{ .name = "rk808-clkout", .id = PLATFORM_DEVID_NONE, },
-	{ .name = "rk808-regulator", .id = PLATFORM_DEVID_NONE, },
-	{ .name = "rk805-pinctrl", .id = PLATFORM_DEVID_NONE, },
+	{ .name = "rk808-clkout", },
+	{ .name = "rk808-regulator", },
+	{ .name = "rk805-pinctrl", },
 	{
 		.name = "rk808-rtc",
 		.num_resources = ARRAY_SIZE(rtc_resources),
 		.resources = &rtc_resources[0],
-		.id = PLATFORM_DEVID_NONE,
 	},
 	{	.name = "rk805-pwrkey",
 		.num_resources = ARRAY_SIZE(rk805_key_resources),
 		.resources = &rk805_key_resources[0],
-		.id = PLATFORM_DEVID_NONE,
 	},
 };
 
 static const struct mfd_cell rk806s[] = {
-	{ .name = "rk805-pinctrl", .id = PLATFORM_DEVID_AUTO, },
-	{ .name = "rk808-regulator", .id = PLATFORM_DEVID_AUTO, },
+	{ .name = "rk805-pinctrl", },
+	{ .name = "rk808-regulator", },
 	{
 		.name = "rk805-pwrkey",
 		.resources = rk806_pwrkey_resources,
 		.num_resources = ARRAY_SIZE(rk806_pwrkey_resources),
-		.id = PLATFORM_DEVID_AUTO,
 	},
 };
 
 static const struct mfd_cell rk808s[] = {
-	{ .name = "rk808-clkout", .id = PLATFORM_DEVID_NONE, },
-	{ .name = "rk808-regulator", .id = PLATFORM_DEVID_NONE, },
+	{ .name = "rk808-clkout", },
+	{ .name = "rk808-regulator", },
 	{
 		.name = "rk808-rtc",
 		.num_resources = ARRAY_SIZE(rtc_resources),
 		.resources = rtc_resources,
-		.id = PLATFORM_DEVID_NONE,
 	},
 };
 
 static const struct mfd_cell rk817s[] = {
-	{ .name = "rk808-clkout", .id = PLATFORM_DEVID_NONE, },
-	{ .name = "rk808-regulator", .id = PLATFORM_DEVID_NONE, },
+	{ .name = "rk808-clkout", },
+	{ .name = "rk808-regulator", },
 	{
 		.name = "rk805-pwrkey",
 		.num_resources = ARRAY_SIZE(rk817_pwrkey_resources),
 		.resources = &rk817_pwrkey_resources[0],
-		.id = PLATFORM_DEVID_NONE,
 	},
 	{
 		.name = "rk808-rtc",
 		.num_resources = ARRAY_SIZE(rk817_rtc_resources),
 		.resources = &rk817_rtc_resources[0],
-		.id = PLATFORM_DEVID_NONE,
 	},
-	{ .name = "rk817-codec", .id = PLATFORM_DEVID_NONE, },
+	{ .name = "rk817-codec", },
 	{
 		.name = "rk817-charger",
 		.num_resources = ARRAY_SIZE(rk817_charger_resources),
 		.resources = &rk817_charger_resources[0],
-		.id = PLATFORM_DEVID_NONE,
 	},
 };
 
 static const struct mfd_cell rk818s[] = {
-	{ .name = "rk808-clkout", .id = PLATFORM_DEVID_NONE, },
-	{ .name = "rk808-regulator", .id = PLATFORM_DEVID_NONE, },
+	{ .name = "rk808-clkout", },
+	{ .name = "rk808-regulator", },
 	{
 		.name = "rk808-rtc",
 		.num_resources = ARRAY_SIZE(rtc_resources),
 		.resources = rtc_resources,
-		.id = PLATFORM_DEVID_NONE,
 	},
 };
 
@@ -684,7 +676,7 @@ int rk8xx_probe(struct device *dev, int variant, unsigned int irq, struct regmap
 					     pre_init_reg[i].addr);
 	}
 
-	ret = devm_mfd_add_devices(dev, 0, cells, nr_cells, NULL, 0,
+	ret = devm_mfd_add_devices(dev, PLATFORM_DEVID_AUTO, cells, nr_cells, NULL, 0,
 			      regmap_irq_get_domain(rk808->irq_data));
 	if (ret)
 		return dev_err_probe(dev, ret, "failed to add MFD devices\n");
diff --git a/drivers/mfd/sm501.c b/drivers/mfd/sm501.c
index 28027982cf69..b3592982a83b 100644
--- a/drivers/mfd/sm501.c
+++ b/drivers/mfd/sm501.c
@@ -1667,7 +1667,7 @@ static void sm501_pci_remove(struct pci_dev *dev)
 	pci_disable_device(dev);
 }
 
-static int sm501_plat_remove(struct platform_device *dev)
+static void sm501_plat_remove(struct platform_device *dev)
 {
 	struct sm501_devdata *sm = platform_get_drvdata(dev);
 
@@ -1675,8 +1675,6 @@ static int sm501_plat_remove(struct platform_device *dev)
 	iounmap(sm->regs);
 
 	release_mem_region(sm->io_res->start, 0x100);
-
-	return 0;
 }
 
 static const struct pci_device_id sm501_pci_tbl[] = {
@@ -1707,7 +1705,7 @@ static struct platform_driver sm501_plat_driver = {
 		.of_match_table = of_sm501_match_tbl,
 	},
 	.probe		= sm501_plat_probe,
-	.remove		= sm501_plat_remove,
+	.remove_new	= sm501_plat_remove,
 	.suspend	= pm_sleep_ptr(sm501_plat_suspend),
 	.resume		= pm_sleep_ptr(sm501_plat_resume),
 };
diff --git a/drivers/mfd/stm32-timers.c b/drivers/mfd/stm32-timers.c
index a656a1c186a8..9fd13d88950c 100644
--- a/drivers/mfd/stm32-timers.c
+++ b/drivers/mfd/stm32-timers.c
@@ -306,7 +306,7 @@ static int stm32_timers_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int stm32_timers_remove(struct platform_device *pdev)
+static void stm32_timers_remove(struct platform_device *pdev)
 {
 	struct stm32_timers *ddata = platform_get_drvdata(pdev);
 
@@ -316,8 +316,6 @@ static int stm32_timers_remove(struct platform_device *pdev)
 	 */
 	of_platform_depopulate(&pdev->dev);
 	stm32_timers_dma_remove(&pdev->dev, ddata);
-
-	return 0;
 }
 
 static const struct of_device_id stm32_timers_of_match[] = {
@@ -328,7 +326,7 @@ MODULE_DEVICE_TABLE(of, stm32_timers_of_match);
 
 static struct platform_driver stm32_timers_driver = {
 	.probe = stm32_timers_probe,
-	.remove = stm32_timers_remove,
+	.remove_new = stm32_timers_remove,
 	.driver	= {
 		.name = "stm32-timers",
 		.of_match_table = stm32_timers_of_match,
diff --git a/drivers/mfd/syscon.c b/drivers/mfd/syscon.c
index 57b29c325131..c9550368d9ea 100644
--- a/drivers/mfd/syscon.c
+++ b/drivers/mfd/syscon.c
@@ -105,6 +105,10 @@ static struct syscon *of_syscon_register(struct device_node *np, bool check_res)
 	}
 
 	syscon_config.name = kasprintf(GFP_KERNEL, "%pOFn@%pa", np, &res.start);
+	if (!syscon_config.name) {
+		ret = -ENOMEM;
+		goto err_regmap;
+	}
 	syscon_config.reg_stride = reg_io_width;
 	syscon_config.val_bits = reg_io_width * 8;
 	syscon_config.max_register = resource_size(&res) - reg_io_width;
diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c
index b88eb70c17b3..4bbd542d753e 100644
--- a/drivers/mfd/ti_am335x_tscadc.c
+++ b/drivers/mfd/ti_am335x_tscadc.c
@@ -298,7 +298,7 @@ err_disable_clk:
 	return err;
 }
 
-static int ti_tscadc_remove(struct platform_device *pdev)
+static void ti_tscadc_remove(struct platform_device *pdev)
 {
 	struct ti_tscadc_dev *tscadc = platform_get_drvdata(pdev);
 
@@ -308,8 +308,6 @@ static int ti_tscadc_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 
 	mfd_remove_devices(tscadc->dev);
-
-	return 0;
 }
 
 static int __maybe_unused ti_tscadc_can_wakeup(struct device *dev, void *data)
@@ -381,7 +379,7 @@ static struct platform_driver ti_tscadc_driver = {
 		.of_match_table = ti_tscadc_dt_ids,
 	},
 	.probe	= ti_tscadc_probe,
-	.remove	= ti_tscadc_remove,
+	.remove_new = ti_tscadc_remove,
 
 };
 
diff --git a/drivers/mfd/tps65086.c b/drivers/mfd/tps65086.c
index 152179ee11ca..fdce81b33f60 100644
--- a/drivers/mfd/tps65086.c
+++ b/drivers/mfd/tps65086.c
@@ -36,6 +36,7 @@ static const struct regmap_config tps65086_regmap_config = {
 	.val_bits = 8,
 	.cache_type = REGCACHE_MAPLE,
 	.volatile_table = &tps65086_volatile_table,
+	.max_register = TPS65086_OC_STATUS,
 };
 
 static const struct regmap_irq tps65086_irqs[] = {
diff --git a/drivers/mfd/tps65911-comparator.c b/drivers/mfd/tps65911-comparator.c
index 8f4210075913..f206a9c50e9d 100644
--- a/drivers/mfd/tps65911-comparator.c
+++ b/drivers/mfd/tps65911-comparator.c
@@ -140,15 +140,13 @@ static int tps65911_comparator_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int tps65911_comparator_remove(struct platform_device *pdev)
+static void tps65911_comparator_remove(struct platform_device *pdev)
 {
 	struct tps65910 *tps65910;
 
 	tps65910 = dev_get_drvdata(pdev->dev.parent);
 	device_remove_file(&pdev->dev, &dev_attr_comp2_threshold);
 	device_remove_file(&pdev->dev, &dev_attr_comp1_threshold);
-
-	return 0;
 }
 
 static struct platform_driver tps65911_comparator_driver = {
@@ -156,7 +154,7 @@ static struct platform_driver tps65911_comparator_driver = {
 		.name = "tps65911-comparator",
 	},
 	.probe = tps65911_comparator_probe,
-	.remove = tps65911_comparator_remove,
+	.remove_new = tps65911_comparator_remove,
 };
 
 static int __init tps65911_comparator_init(void)
diff --git a/drivers/mfd/tps6594-core.c b/drivers/mfd/tps6594-core.c
index 0fb9c5cf213a..783ee59901e8 100644
--- a/drivers/mfd/tps6594-core.c
+++ b/drivers/mfd/tps6594-core.c
@@ -433,6 +433,9 @@ int tps6594_device_init(struct tps6594 *tps, bool enable_crc)
 	tps6594_irq_chip.name = devm_kasprintf(dev, GFP_KERNEL, "%s-%ld-0x%02x",
 					       dev->driver->name, tps->chip_id, tps->reg);
 
+	if (!tps6594_irq_chip.name)
+		return -ENOMEM;
+
 	ret = devm_regmap_add_irq_chip(dev, tps->regmap, tps->irq, IRQF_SHARED | IRQF_ONESHOT,
 				       0, &tps6594_irq_chip, &tps->irq_data);
 	if (ret)
diff --git a/drivers/mfd/twl4030-audio.c b/drivers/mfd/twl4030-audio.c
index 88002f8941e5..d436ddf661da 100644
--- a/drivers/mfd/twl4030-audio.c
+++ b/drivers/mfd/twl4030-audio.c
@@ -258,12 +258,10 @@ static int twl4030_audio_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int twl4030_audio_remove(struct platform_device *pdev)
+static void twl4030_audio_remove(struct platform_device *pdev)
 {
 	mfd_remove_devices(&pdev->dev);
 	twl4030_audio_dev = NULL;
-
-	return 0;
 }
 
 static const struct of_device_id twl4030_audio_of_match[] = {
@@ -278,7 +276,7 @@ static struct platform_driver twl4030_audio_driver = {
 		.of_match_table = twl4030_audio_of_match,
 	},
 	.probe		= twl4030_audio_probe,
-	.remove		= twl4030_audio_remove,
+	.remove_new	= twl4030_audio_remove,
 };
 
 module_platform_driver(twl4030_audio_driver);
diff --git a/drivers/mfd/twl6030-irq.c b/drivers/mfd/twl6030-irq.c
index f9fce8408c2c..3c03681c124c 100644
--- a/drivers/mfd/twl6030-irq.c
+++ b/drivers/mfd/twl6030-irq.c
@@ -24,10 +24,10 @@
 #include <linux/kthread.h>
 #include <linux/mfd/twl.h>
 #include <linux/platform_device.h>
-#include <linux/property.h>
 #include <linux/suspend.h>
 #include <linux/of.h>
 #include <linux/irqdomain.h>
+#include <linux/of_device.h>
 
 #include "twl-core.h"
 
@@ -368,10 +368,10 @@ int twl6030_init_irq(struct device *dev, int irq_num)
 	int			nr_irqs;
 	int			status;
 	u8			mask[3];
-	const int		*irq_tbl;
+	const struct of_device_id *of_id;
 
-	irq_tbl = device_get_match_data(dev);
-	if (!irq_tbl) {
+	of_id = of_match_device(twl6030_of_match, dev);
+	if (!of_id || !of_id->data) {
 		dev_err(dev, "Unknown TWL device model\n");
 		return -EINVAL;
 	}
@@ -409,7 +409,7 @@ int twl6030_init_irq(struct device *dev, int irq_num)
 
 	twl6030_irq->pm_nb.notifier_call = twl6030_irq_pm_notifier;
 	atomic_set(&twl6030_irq->wakeirqs, 0);
-	twl6030_irq->irq_mapping_tbl = irq_tbl;
+	twl6030_irq->irq_mapping_tbl = of_id->data;
 
 	twl6030_irq->irq_domain =
 		irq_domain_add_linear(node, nr_irqs,
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index f37c4b8380ae..4fb291f0bf7c 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -562,6 +562,18 @@ config TPS6594_PFSM
 	  This driver can also be built as a module.  If so, the module
 	  will be called tps6594-pfsm.
 
+config NSM
+	tristate "Nitro (Enclaves) Security Module support"
+	depends on VIRTIO
+	select HW_RANDOM
+	help
+	  This driver provides support for the Nitro Security Module
+	  in AWS EC2 Nitro based Enclaves. The driver exposes a /dev/nsm
+	  device user space can use to communicate with the hypervisor.
+
+	  To compile this driver as a module, choose M here.
+	  The module will be called nsm.
+
 source "drivers/misc/c2port/Kconfig"
 source "drivers/misc/eeprom/Kconfig"
 source "drivers/misc/cb710/Kconfig"
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index f2a4d1ff65d4..ea6ea5bbbc9c 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -67,3 +67,4 @@ obj-$(CONFIG_TMR_MANAGER)      += xilinx_tmr_manager.o
 obj-$(CONFIG_TMR_INJECT)	+= xilinx_tmr_inject.o
 obj-$(CONFIG_TPS6594_ESM)	+= tps6594-esm.o
 obj-$(CONFIG_TPS6594_PFSM)	+= tps6594-pfsm.o
+obj-$(CONFIG_NSM)		+= nsm.o
diff --git a/drivers/misc/bcm-vk/bcm_vk_tty.c b/drivers/misc/bcm-vk/bcm_vk_tty.c
index 2bce835ca43e..59bab76ff0a9 100644
--- a/drivers/misc/bcm-vk/bcm_vk_tty.c
+++ b/drivers/misc/bcm-vk/bcm_vk_tty.c
@@ -64,9 +64,9 @@ static void bcm_vk_tty_wq_handler(struct work_struct *work)
 	struct bcm_vk_tty *vktty;
 	int card_status;
 	int count;
-	unsigned char c;
 	int i;
 	int wr;
+	u8 c;
 
 	card_status = vkread32(vk, BAR_0, BAR_CARD_STATUS);
 	if (BCM_VK_INTF_IS_DOWN(card_status))
@@ -192,7 +192,7 @@ static ssize_t bcm_vk_tty_write(struct tty_struct *tty, const u8 *buffer,
 	int index;
 	struct bcm_vk *vk;
 	struct bcm_vk_tty *vktty;
-	int i;
+	size_t i;
 
 	index = tty->index;
 	vk = dev_get_drvdata(tty->dev);
diff --git a/drivers/misc/cardreader/Makefile b/drivers/misc/cardreader/Makefile
index 895128475d83..1e1bca6b0b22 100644
--- a/drivers/misc/cardreader/Makefile
+++ b/drivers/misc/cardreader/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_MISC_ALCOR_PCI)	+= alcor_pci.o
 obj-$(CONFIG_MISC_RTSX_PCI)	+= rtsx_pci.o
-rtsx_pci-objs := rtsx_pcr.o rts5209.o rts5229.o rtl8411.o rts5227.o rts5249.o rts5260.o rts5261.o rts5228.o
+rtsx_pci-objs := rtsx_pcr.o rts5209.o rts5229.o rtl8411.o rts5227.o rts5249.o rts5260.o rts5261.o rts5228.o rts5264.o
 obj-$(CONFIG_MISC_RTSX_USB)	+= rtsx_usb.o
diff --git a/drivers/misc/cardreader/rts5264.c b/drivers/misc/cardreader/rts5264.c
new file mode 100644
index 000000000000..8be4ed7d9d47
--- /dev/null
+++ b/drivers/misc/cardreader/rts5264.c
@@ -0,0 +1,886 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2009-2013 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * Author:
+ *   Ricky Wu <ricky_wu@realtek.com>
+ */
+
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/rtsx_pci.h>
+
+#include "rts5264.h"
+#include "rtsx_pcr.h"
+
+static u8 rts5264_get_ic_version(struct rtsx_pcr *pcr)
+{
+	u8 val;
+
+	rtsx_pci_read_register(pcr, DUMMY_REG_RESET_0, &val);
+	return val & 0x0F;
+}
+
+static void rts5264_fill_driving(struct rtsx_pcr *pcr, u8 voltage)
+{
+	u8 driving_3v3[4][3] = {
+		{0x88, 0x88, 0x88},
+		{0x77, 0x77, 0x77},
+		{0x99, 0x99, 0x99},
+		{0x66, 0x66, 0x66},
+	};
+	u8 driving_1v8[4][3] = {
+		{0x99, 0x99, 0x99},
+		{0x77, 0x77, 0x77},
+		{0xBB, 0xBB, 0xBB},
+		{0x65, 0x65, 0x65},
+	};
+	u8 (*driving)[3], drive_sel;
+
+	if (voltage == OUTPUT_3V3) {
+		driving = driving_3v3;
+		drive_sel = pcr->sd30_drive_sel_3v3;
+	} else {
+		driving = driving_1v8;
+		drive_sel = pcr->sd30_drive_sel_1v8;
+	}
+
+	rtsx_pci_write_register(pcr, SD30_CLK_DRIVE_SEL,
+			0xFF, driving[drive_sel][0]);
+	rtsx_pci_write_register(pcr, SD30_CMD_DRIVE_SEL,
+			0xFF, driving[drive_sel][1]);
+	rtsx_pci_write_register(pcr, SD30_DAT_DRIVE_SEL,
+			0xFF, driving[drive_sel][2]);
+}
+
+static void rts5264_force_power_down(struct rtsx_pcr *pcr, u8 pm_state, bool runtime)
+{
+	/* Set relink_time to 0 */
+	rtsx_pci_write_register(pcr, AUTOLOAD_CFG_BASE + 1, MASK_8_BIT_DEF, 0);
+	rtsx_pci_write_register(pcr, AUTOLOAD_CFG_BASE + 2, MASK_8_BIT_DEF, 0);
+	rtsx_pci_write_register(pcr, AUTOLOAD_CFG_BASE + 3,
+				RELINK_TIME_MASK, 0);
+
+	if (pm_state == HOST_ENTER_S3)
+		rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3,
+					D3_DELINK_MODE_EN, D3_DELINK_MODE_EN);
+
+	if (!runtime) {
+		rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG1,
+				CD_RESUME_EN_MASK, 0);
+		rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x01, 0x00);
+		rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+				FORCE_PM_CONTROL | FORCE_PM_VALUE, FORCE_PM_CONTROL);
+	} else {
+		rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+				FORCE_PM_CONTROL | FORCE_PM_VALUE, 0);
+		rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x01, 0x01);
+		rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3,
+					D3_DELINK_MODE_EN, 0);
+		rtsx_pci_write_register(pcr, RTS5264_FW_CTL,
+				RTS5264_INFORM_RTD3_COLD, RTS5264_INFORM_RTD3_COLD);
+		rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG4,
+				RTS5264_FORCE_PRSNT_LOW, RTS5264_FORCE_PRSNT_LOW);
+	}
+
+	rtsx_pci_write_register(pcr, RTS5264_REG_FPDCTL,
+		SSC_POWER_DOWN, SSC_POWER_DOWN);
+}
+
+static int rts5264_enable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, OLT_LED_CTL,
+		LED_SHINE_MASK, LED_SHINE_EN);
+}
+
+static int rts5264_disable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, OLT_LED_CTL,
+		LED_SHINE_MASK, LED_SHINE_DISABLE);
+}
+
+static int rts5264_turn_on_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, GPIO_CTL,
+		0x02, 0x02);
+}
+
+static int rts5264_turn_off_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, GPIO_CTL,
+		0x02, 0x00);
+}
+
+/* SD Pull Control Enable:
+ *     SD_DAT[3:0] ==> pull up
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull up
+ *     SD_CMD      ==> pull up
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rts5264_sd_pull_ctl_enable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0xAA),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xE9),
+	0,
+};
+
+/* SD Pull Control Disable:
+ *     SD_DAT[3:0] ==> pull down
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull down
+ *     SD_CMD      ==> pull down
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rts5264_sd_pull_ctl_disable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xD5),
+	0,
+};
+
+static int rts5264_sd_set_sample_push_timing_sd30(struct rtsx_pcr *pcr)
+{
+	rtsx_pci_write_register(pcr, SD_CFG1, SD_MODE_SELECT_MASK
+		| SD_ASYNC_FIFO_NOT_RST, SD_30_MODE | SD_ASYNC_FIFO_NOT_RST);
+	rtsx_pci_write_register(pcr, CLK_CTL, CLK_LOW_FREQ, CLK_LOW_FREQ);
+	rtsx_pci_write_register(pcr, CARD_CLK_SOURCE, 0xFF,
+			CRC_VAR_CLK0 | SD30_FIX_CLK | SAMPLE_VAR_CLK1);
+	rtsx_pci_write_register(pcr, CLK_CTL, CLK_LOW_FREQ, 0);
+
+	return 0;
+}
+
+static int rts5264_card_power_on(struct rtsx_pcr *pcr, int card)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+
+	if (option->ocp_en)
+		rtsx_pci_enable_ocp(pcr);
+
+	rtsx_pci_write_register(pcr, REG_CRC_DUMMY_0,
+		CFG_SD_POW_AUTO_PD, CFG_SD_POW_AUTO_PD);
+
+	rtsx_pci_write_register(pcr, RTS5264_LDO1_CFG1,
+			RTS5264_LDO1_TUNE_MASK, RTS5264_LDO1_33);
+	rtsx_pci_write_register(pcr, RTS5264_LDO1233318_POW_CTL,
+			RTS5264_LDO1_POWERON, RTS5264_LDO1_POWERON);
+	rtsx_pci_write_register(pcr, RTS5264_LDO1233318_POW_CTL,
+			RTS5264_LDO3318_POWERON, RTS5264_LDO3318_POWERON);
+
+	msleep(20);
+
+	rtsx_pci_write_register(pcr, CARD_OE, SD_OUTPUT_EN, SD_OUTPUT_EN);
+
+	/* Initialize SD_CFG1 register */
+	rtsx_pci_write_register(pcr, SD_CFG1, 0xFF,
+			SD_CLK_DIVIDE_128 | SD_20_MODE | SD_BUS_WIDTH_1BIT);
+	rtsx_pci_write_register(pcr, SD_SAMPLE_POINT_CTL,
+			0xFF, SD20_RX_POS_EDGE);
+	rtsx_pci_write_register(pcr, SD_PUSH_POINT_CTL, 0xFF, 0);
+	rtsx_pci_write_register(pcr, CARD_STOP, SD_STOP | SD_CLR_ERR,
+			SD_STOP | SD_CLR_ERR);
+
+	/* Reset SD_CFG3 register */
+	rtsx_pci_write_register(pcr, SD_CFG3, SD30_CLK_END_EN, 0);
+	rtsx_pci_write_register(pcr, REG_SD_STOP_SDCLK_CFG,
+			SD30_CLK_STOP_CFG_EN | SD30_CLK_STOP_CFG1 |
+			SD30_CLK_STOP_CFG0, 0);
+
+	if (pcr->extra_caps & EXTRA_CAPS_SD_SDR50 ||
+	    pcr->extra_caps & EXTRA_CAPS_SD_SDR104)
+		rts5264_sd_set_sample_push_timing_sd30(pcr);
+
+	return 0;
+}
+
+static int rts5264_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage)
+{
+	rtsx_pci_write_register(pcr, RTS5264_CARD_PWR_CTL,
+			RTS5264_PUPDC, RTS5264_PUPDC);
+
+	switch (voltage) {
+	case OUTPUT_3V3:
+		rtsx_pci_write_register(pcr, RTS5264_LDO1233318_POW_CTL,
+				RTS5264_TUNE_REF_LDO3318, RTS5264_TUNE_REF_LDO3318);
+		rtsx_pci_write_register(pcr, RTS5264_DV3318_CFG,
+				RTS5264_DV3318_TUNE_MASK, RTS5264_DV3318_33);
+		rtsx_pci_write_register(pcr, SD_PAD_CTL,
+				SD_IO_USING_1V8, 0);
+		break;
+	case OUTPUT_1V8:
+		rtsx_pci_write_register(pcr, RTS5264_LDO1233318_POW_CTL,
+				RTS5264_TUNE_REF_LDO3318, RTS5264_TUNE_REF_LDO3318_DFT);
+		rtsx_pci_write_register(pcr, RTS5264_DV3318_CFG,
+				RTS5264_DV3318_TUNE_MASK, RTS5264_DV3318_18);
+		rtsx_pci_write_register(pcr, SD_PAD_CTL,
+				SD_IO_USING_1V8, SD_IO_USING_1V8);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* set pad drive */
+	rts5264_fill_driving(pcr, voltage);
+
+	return 0;
+}
+
+static void rts5264_stop_cmd(struct rtsx_pcr *pcr)
+{
+	rtsx_pci_writel(pcr, RTSX_HCBCTLR, STOP_CMD);
+	rtsx_pci_writel(pcr, RTSX_HDBCTLR, STOP_DMA);
+	rtsx_pci_write_register(pcr, DMACTL, DMA_RST, DMA_RST);
+	rtsx_pci_write_register(pcr, RBCTL, RB_FLUSH, RB_FLUSH);
+}
+
+static void rts5264_card_before_power_off(struct rtsx_pcr *pcr)
+{
+	rts5264_stop_cmd(pcr);
+	rts5264_switch_output_voltage(pcr, OUTPUT_3V3);
+}
+
+static int rts5264_card_power_off(struct rtsx_pcr *pcr, int card)
+{
+	int err = 0;
+
+	rts5264_card_before_power_off(pcr);
+	err = rtsx_pci_write_register(pcr, RTS5264_LDO1233318_POW_CTL,
+				RTS5264_LDO_POWERON_MASK, 0);
+
+	rtsx_pci_write_register(pcr, REG_CRC_DUMMY_0,
+		CFG_SD_POW_AUTO_PD, 0);
+	if (pcr->option.ocp_en)
+		rtsx_pci_disable_ocp(pcr);
+
+	return err;
+}
+
+static void rts5264_enable_ocp(struct rtsx_pcr *pcr)
+{
+	u8 mask = 0;
+	u8 val = 0;
+
+	rtsx_pci_write_register(pcr, RTS5264_LDO1_CFG0,
+			RTS5264_LDO1_OCP_EN | RTS5264_LDO1_OCP_LMT_EN,
+			RTS5264_LDO1_OCP_EN | RTS5264_LDO1_OCP_LMT_EN);
+	rtsx_pci_write_register(pcr, RTS5264_LDO2_CFG0,
+			RTS5264_LDO2_OCP_EN | RTS5264_LDO2_OCP_LMT_EN,
+			RTS5264_LDO2_OCP_EN | RTS5264_LDO2_OCP_LMT_EN);
+	rtsx_pci_write_register(pcr, RTS5264_LDO3_CFG0,
+			RTS5264_LDO3_OCP_EN | RTS5264_LDO3_OCP_LMT_EN,
+			RTS5264_LDO3_OCP_EN | RTS5264_LDO3_OCP_LMT_EN);
+	rtsx_pci_write_register(pcr, RTS5264_OVP_DET,
+			RTS5264_POW_VDET, RTS5264_POW_VDET);
+
+	mask = SD_OCP_INT_EN | SD_DETECT_EN;
+	mask |= SDVIO_OCP_INT_EN | SDVIO_DETECT_EN;
+	val = mask;
+	rtsx_pci_write_register(pcr, REG_OCPCTL, mask, val);
+
+	mask = SD_VDD3_OCP_INT_EN | SD_VDD3_DETECT_EN;
+	val = mask;
+	rtsx_pci_write_register(pcr, RTS5264_OCP_VDD3_CTL, mask, val);
+
+	mask = RTS5264_OVP_INT_EN | RTS5264_OVP_DETECT_EN;
+	val = mask;
+	rtsx_pci_write_register(pcr, RTS5264_OVP_CTL, mask, val);
+}
+
+static void rts5264_disable_ocp(struct rtsx_pcr *pcr)
+{
+	u8 mask = 0;
+
+	mask = SD_OCP_INT_EN | SD_DETECT_EN;
+	mask |= SDVIO_OCP_INT_EN | SDVIO_DETECT_EN;
+	rtsx_pci_write_register(pcr, REG_OCPCTL, mask, 0);
+
+	mask = SD_VDD3_OCP_INT_EN | SD_VDD3_DETECT_EN;
+	rtsx_pci_write_register(pcr, RTS5264_OCP_VDD3_CTL, mask, 0);
+
+	mask = RTS5264_OVP_INT_EN | RTS5264_OVP_DETECT_EN;
+	rtsx_pci_write_register(pcr, RTS5264_OVP_CTL, mask, 0);
+
+	rtsx_pci_write_register(pcr, RTS5264_LDO1_CFG0,
+			RTS5264_LDO1_OCP_EN | RTS5264_LDO1_OCP_LMT_EN, 0);
+	rtsx_pci_write_register(pcr, RTS5264_LDO2_CFG0,
+			RTS5264_LDO2_OCP_EN | RTS5264_LDO2_OCP_LMT_EN, 0);
+	rtsx_pci_write_register(pcr, RTS5264_LDO3_CFG0,
+			RTS5264_LDO3_OCP_EN | RTS5264_LDO3_OCP_LMT_EN, 0);
+	rtsx_pci_write_register(pcr, RTS5264_OVP_DET, RTS5264_POW_VDET, 0);
+}
+
+static void rts5264_init_ocp(struct rtsx_pcr *pcr)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+
+	if (option->ocp_en) {
+		u8 mask, val;
+
+		rtsx_pci_write_register(pcr, RTS5264_LDO1_CFG0,
+			RTS5264_LDO1_OCP_THD_MASK, option->sd_800mA_ocp_thd);
+		rtsx_pci_write_register(pcr, RTS5264_LDO1_CFG0,
+			RTS5264_LDO1_OCP_LMT_THD_MASK,
+			RTS5264_LDO1_LMT_THD_2000);
+
+		rtsx_pci_write_register(pcr, RTS5264_LDO2_CFG0,
+			RTS5264_LDO2_OCP_THD_MASK, RTS5264_LDO2_OCP_THD_950);
+		rtsx_pci_write_register(pcr, RTS5264_LDO2_CFG0,
+			RTS5264_LDO2_OCP_LMT_THD_MASK,
+			RTS5264_LDO2_LMT_THD_2000);
+
+		rtsx_pci_write_register(pcr, RTS5264_LDO3_CFG0,
+			RTS5264_LDO3_OCP_THD_MASK, RTS5264_LDO3_OCP_THD_710);
+		rtsx_pci_write_register(pcr, RTS5264_LDO3_CFG0,
+			RTS5264_LDO3_OCP_LMT_THD_MASK,
+			RTS5264_LDO3_LMT_THD_1500);
+
+		rtsx_pci_write_register(pcr, RTS5264_OVP_DET,
+			RTS5264_TUNE_VROV_MASK, RTS5264_TUNE_VROV_1V6);
+
+		mask = SD_OCP_GLITCH_MASK | SDVIO_OCP_GLITCH_MASK;
+		val = pcr->hw_param.ocp_glitch;
+		rtsx_pci_write_register(pcr, REG_OCPGLITCH, mask, val);
+
+	} else {
+		rtsx_pci_write_register(pcr, RTS5264_LDO1_CFG0,
+			RTS5264_LDO1_OCP_EN | RTS5264_LDO1_OCP_LMT_EN, 0);
+		rtsx_pci_write_register(pcr, RTS5264_LDO2_CFG0,
+			RTS5264_LDO2_OCP_EN | RTS5264_LDO2_OCP_LMT_EN, 0);
+		rtsx_pci_write_register(pcr, RTS5264_LDO3_CFG0,
+			RTS5264_LDO3_OCP_EN | RTS5264_LDO3_OCP_LMT_EN, 0);
+		rtsx_pci_write_register(pcr, RTS5264_OVP_DET,
+			RTS5264_POW_VDET, 0);
+	}
+}
+
+static int rts5264_get_ocpstat2(struct rtsx_pcr *pcr, u8 *val)
+{
+	return rtsx_pci_read_register(pcr, RTS5264_OCP_VDD3_STS, val);
+}
+
+static int rts5264_get_ovpstat(struct rtsx_pcr *pcr, u8 *val)
+{
+	return rtsx_pci_read_register(pcr, RTS5264_OVP_STS, val);
+}
+
+static void rts5264_clear_ocpstat(struct rtsx_pcr *pcr)
+{
+	u8 mask = 0;
+	u8 val = 0;
+
+	mask = SD_OCP_INT_CLR | SD_OC_CLR;
+	mask |= SDVIO_OCP_INT_CLR | SDVIO_OC_CLR;
+	val = mask;
+	rtsx_pci_write_register(pcr, REG_OCPCTL, mask, val);
+	rtsx_pci_write_register(pcr, RTS5264_OCP_VDD3_CTL,
+		SD_VDD3_OCP_INT_CLR | SD_VDD3_OC_CLR,
+		SD_VDD3_OCP_INT_CLR | SD_VDD3_OC_CLR);
+	rtsx_pci_write_register(pcr, RTS5264_OVP_CTL,
+		RTS5264_OVP_INT_CLR | RTS5264_OVP_CLR,
+		RTS5264_OVP_INT_CLR | RTS5264_OVP_CLR);
+
+	udelay(1000);
+
+	rtsx_pci_write_register(pcr, REG_OCPCTL, mask, 0);
+	rtsx_pci_write_register(pcr, RTS5264_OCP_VDD3_CTL,
+		SD_VDD3_OCP_INT_CLR | SD_VDD3_OC_CLR, 0);
+	rtsx_pci_write_register(pcr, RTS5264_OVP_CTL,
+		RTS5264_OVP_INT_CLR | RTS5264_OVP_CLR, 0);
+}
+
+static void rts5264_process_ocp(struct rtsx_pcr *pcr)
+{
+	if (!pcr->option.ocp_en)
+		return;
+
+	rtsx_pci_get_ocpstat(pcr, &pcr->ocp_stat);
+	rts5264_get_ocpstat2(pcr, &pcr->ocp_stat2);
+	rts5264_get_ovpstat(pcr, &pcr->ovp_stat);
+
+	if ((pcr->ocp_stat & (SD_OC_NOW | SD_OC_EVER | SDVIO_OC_NOW | SDVIO_OC_EVER)) ||
+			(pcr->ocp_stat2 & (SD_VDD3_OC_NOW | SD_VDD3_OC_EVER)) ||
+			(pcr->ovp_stat & (RTS5264_OVP_NOW | RTS5264_OVP_EVER))) {
+		rts5264_clear_ocpstat(pcr);
+		rts5264_card_power_off(pcr, RTSX_SD_CARD);
+		rtsx_pci_write_register(pcr, CARD_OE, SD_OUTPUT_EN, 0);
+		pcr->ocp_stat = 0;
+		pcr->ocp_stat2 = 0;
+		pcr->ovp_stat = 0;
+	}
+}
+
+static void rts5264_init_from_hw(struct rtsx_pcr *pcr)
+{
+	struct pci_dev *pdev = pcr->pci;
+	u32 lval1, lval2, i;
+	u16 setting_reg1, setting_reg2;
+	u8 valid, efuse_valid, tmp;
+
+	rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+		REG_EFUSE_POR | REG_EFUSE_POWER_MASK,
+		REG_EFUSE_POR | REG_EFUSE_POWERON);
+	udelay(1);
+	rtsx_pci_write_register(pcr, RTS5264_EFUSE_ADDR,
+		RTS5264_EFUSE_ADDR_MASK, 0x00);
+	rtsx_pci_write_register(pcr, RTS5264_EFUSE_CTL,
+		RTS5264_EFUSE_ENABLE | RTS5264_EFUSE_MODE_MASK,
+		RTS5264_EFUSE_ENABLE);
+
+	/* Wait transfer end */
+	for (i = 0; i < MAX_RW_REG_CNT; i++) {
+		rtsx_pci_read_register(pcr, RTS5264_EFUSE_CTL, &tmp);
+		if ((tmp & 0x80) == 0)
+			break;
+	}
+	rtsx_pci_read_register(pcr, RTS5264_EFUSE_READ_DATA, &tmp);
+	efuse_valid = ((tmp & 0x0C) >> 2);
+	pcr_dbg(pcr, "Load efuse valid: 0x%x\n", efuse_valid);
+
+	pci_read_config_dword(pdev, PCR_SETTING_REG2, &lval2);
+	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG2, lval2);
+	/* 0x816 */
+	valid = (u8)((lval2 >> 16) & 0x03);
+
+	rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+		REG_EFUSE_POR, 0);
+	pcr_dbg(pcr, "Disable efuse por!\n");
+
+	if (efuse_valid == 2 || efuse_valid == 3) {
+		if (valid == 3) {
+			/* Bypass efuse */
+			setting_reg1 = PCR_SETTING_REG1;
+			setting_reg2 = PCR_SETTING_REG2;
+		} else {
+			/* Use efuse data */
+			setting_reg1 = PCR_SETTING_REG4;
+			setting_reg2 = PCR_SETTING_REG5;
+		}
+	} else if (efuse_valid == 0) {
+		// default
+		setting_reg1 = PCR_SETTING_REG1;
+		setting_reg2 = PCR_SETTING_REG2;
+	} else {
+		return;
+	}
+
+	pci_read_config_dword(pdev, setting_reg2, &lval2);
+	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", setting_reg2, lval2);
+
+	if (!rts5264_vendor_setting_valid(lval2)) {
+		pcr_dbg(pcr, "skip fetch vendor setting\n");
+		return;
+	}
+
+	pcr->rtd3_en = rts5264_reg_to_rtd3(lval2);
+
+	if (rts5264_reg_check_reverse_socket(lval2))
+		pcr->flags |= PCR_REVERSE_SOCKET;
+
+	pci_read_config_dword(pdev, setting_reg1, &lval1);
+	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", setting_reg1, lval1);
+
+	pcr->aspm_en = rts5264_reg_to_aspm(lval1);
+	pcr->sd30_drive_sel_1v8 = rts5264_reg_to_sd30_drive_sel_1v8(lval1);
+	pcr->sd30_drive_sel_3v3 = rts5264_reg_to_sd30_drive_sel_3v3(lval1);
+
+	if (setting_reg1 == PCR_SETTING_REG1) {
+		/* store setting */
+		rtsx_pci_write_register(pcr, 0xFF0C, 0xFF, (u8)(lval1 & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF0D, 0xFF, (u8)((lval1 >> 8) & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF0E, 0xFF, (u8)((lval1 >> 16) & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF0F, 0xFF, (u8)((lval1 >> 24) & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF10, 0xFF, (u8)(lval2 & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF11, 0xFF, (u8)((lval2 >> 8) & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF12, 0xFF, (u8)((lval2 >> 16) & 0xFF));
+
+		pci_write_config_dword(pdev, PCR_SETTING_REG4, lval1);
+		lval2 = lval2 & 0x00FFFFFF;
+		pci_write_config_dword(pdev, PCR_SETTING_REG5, lval2);
+	}
+}
+
+static void rts5264_init_from_cfg(struct rtsx_pcr *pcr)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+
+	if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN
+				| PM_L1_1_EN | PM_L1_2_EN))
+		rtsx_pci_disable_oobs_polling(pcr);
+	else
+		rtsx_pci_enable_oobs_polling(pcr);
+
+	rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0xFF, 0);
+
+	if (option->ltr_en) {
+		if (option->ltr_enabled)
+			rtsx_set_ltr_latency(pcr, option->ltr_active_latency);
+	}
+}
+
+static int rts5264_extra_init_hw(struct rtsx_pcr *pcr)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+
+	rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG1,
+			CD_RESUME_EN_MASK, CD_RESUME_EN_MASK);
+	rtsx_pci_write_register(pcr, REG_VREF, PWD_SUSPND_EN, PWD_SUSPND_EN);
+
+	rts5264_init_from_cfg(pcr);
+	rts5264_init_from_hw(pcr);
+
+	/* power off efuse */
+	rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+			REG_EFUSE_POWER_MASK, REG_EFUSE_POWEROFF);
+	rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG2,
+			RTS5264_CHIP_RST_N_SEL, 0);
+	rtsx_pci_write_register(pcr, RTS5264_REG_LDO12_CFG,
+			RTS5264_LDO12_SR_MASK, RTS5264_LDO12_SR_0_0_MS);
+	rtsx_pci_write_register(pcr, CDGW, 0xFF, 0x01);
+	rtsx_pci_write_register(pcr, RTS5264_CKMUX_MBIAS_PWR,
+			RTS5264_POW_CKMUX, RTS5264_POW_CKMUX);
+	rtsx_pci_write_register(pcr, RTS5264_CMD_OE_START_EARLY,
+			RTS5264_CMD_OE_EARLY_EN | RTS5264_CMD_OE_EARLY_CYCLE_MASK,
+			RTS5264_CMD_OE_EARLY_EN);
+	rtsx_pci_write_register(pcr, RTS5264_DAT_OE_START_EARLY,
+			RTS5264_DAT_OE_EARLY_EN | RTS5264_DAT_OE_EARLY_CYCLE_MASK,
+			RTS5264_DAT_OE_EARLY_EN);
+	rtsx_pci_write_register(pcr, SSC_DIV_N_0, 0xFF, 0x5D);
+
+	rtsx_pci_write_register(pcr, RTS5264_PWR_CUT,
+			RTS5264_CFG_MEM_PD, RTS5264_CFG_MEM_PD);
+	rtsx_pci_write_register(pcr, L1SUB_CONFIG1,
+			AUX_CLK_ACTIVE_SEL_MASK, MAC_CKSW_DONE);
+	rtsx_pci_write_register(pcr, L1SUB_CONFIG3, 0xFF, 0);
+	rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG4,
+			RTS5264_AUX_CLK_16M_EN, 0);
+
+	/* Release PRSNT# */
+	rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG4,
+			RTS5264_FORCE_PRSNT_LOW, 0);
+	rtsx_pci_write_register(pcr, PCLK_CTL,
+			PCLK_MODE_SEL, PCLK_MODE_SEL);
+
+	/* LED shine disabled, set initial shine cycle period */
+	rtsx_pci_write_register(pcr, OLT_LED_CTL, 0x0F, 0x02);
+
+	/* Configure driving */
+	rts5264_fill_driving(pcr, OUTPUT_3V3);
+
+	if (pcr->flags & PCR_REVERSE_SOCKET)
+		rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x30);
+	else
+		rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x00);
+
+	/*
+	 * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced
+	 * to drive low, and we forcibly request clock.
+	 */
+	if (option->force_clkreq_0)
+		rtsx_pci_write_register(pcr, PETXCFG,
+				 FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW);
+	else
+		rtsx_pci_write_register(pcr, PETXCFG,
+				 FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH);
+
+	rtsx_pci_write_register(pcr, PWD_SUSPEND_EN, 0xFF, 0xFF);
+	rtsx_pci_write_register(pcr, RBCTL, U_AUTO_DMA_EN_MASK, 0);
+	rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG4,
+			RTS5264_F_HIGH_RC_MASK, RTS5264_F_HIGH_RC_400K);
+
+	if (pcr->rtd3_en) {
+		rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x01, 0x00);
+		rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+				FORCE_PM_CONTROL | FORCE_PM_VALUE, 0);
+	} else {
+		rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x01, 0x00);
+		rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+				FORCE_PM_CONTROL | FORCE_PM_VALUE, FORCE_PM_CONTROL);
+	}
+	rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, D3_DELINK_MODE_EN, 0x00);
+
+	/* Clear Enter RTD3_cold Information*/
+	rtsx_pci_write_register(pcr, RTS5264_FW_CTL,
+		RTS5264_INFORM_RTD3_COLD, 0);
+
+	return 0;
+}
+
+static void rts5264_enable_aspm(struct rtsx_pcr *pcr, bool enable)
+{
+	u8 val = FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1;
+	u8 mask = FORCE_ASPM_VAL_MASK | FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1;
+
+	if (pcr->aspm_enabled == enable)
+		return;
+
+	val |= (pcr->aspm_en & 0x02);
+	rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, mask, val);
+	pcie_capability_clear_and_set_word(pcr->pci, PCI_EXP_LNKCTL,
+					   PCI_EXP_LNKCTL_ASPMC, pcr->aspm_en);
+	pcr->aspm_enabled = enable;
+}
+
+static void rts5264_disable_aspm(struct rtsx_pcr *pcr, bool enable)
+{
+	u8 val = FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1;
+	u8 mask = FORCE_ASPM_VAL_MASK | FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1;
+
+	if (pcr->aspm_enabled == enable)
+		return;
+
+	pcie_capability_clear_and_set_word(pcr->pci, PCI_EXP_LNKCTL,
+					   PCI_EXP_LNKCTL_ASPMC, 0);
+	rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, mask, val);
+	rtsx_pci_write_register(pcr, SD_CFG1, SD_ASYNC_FIFO_NOT_RST, 0);
+	udelay(10);
+	pcr->aspm_enabled = enable;
+}
+
+static void rts5264_set_aspm(struct rtsx_pcr *pcr, bool enable)
+{
+	if (enable)
+		rts5264_enable_aspm(pcr, true);
+	else
+		rts5264_disable_aspm(pcr, false);
+}
+
+static void rts5264_set_l1off_cfg_sub_d0(struct rtsx_pcr *pcr, int active)
+{
+	struct rtsx_cr_option *option = &(pcr->option);
+
+	u32 interrupt = rtsx_pci_readl(pcr, RTSX_BIPR);
+	int card_exist = (interrupt & SD_EXIST);
+	int aspm_L1_1, aspm_L1_2;
+	u8 val = 0;
+
+	aspm_L1_1 = rtsx_check_dev_flag(pcr, ASPM_L1_1_EN);
+	aspm_L1_2 = rtsx_check_dev_flag(pcr, ASPM_L1_2_EN);
+
+	if (active) {
+		/* Run, latency: 60us */
+		if (aspm_L1_1)
+			val = option->ltr_l1off_snooze_sspwrgate;
+	} else {
+		/* L1off, latency: 300us */
+		if (aspm_L1_2)
+			val = option->ltr_l1off_sspwrgate;
+	}
+
+	if (aspm_L1_1 || aspm_L1_2) {
+		if (rtsx_check_dev_flag(pcr,
+					LTR_L1SS_PWR_GATE_CHECK_CARD_EN)) {
+			if (card_exist)
+				val &= ~L1OFF_MBIAS2_EN_5250;
+			else
+				val |= L1OFF_MBIAS2_EN_5250;
+		}
+	}
+	rtsx_set_l1off_sub(pcr, val);
+}
+
+static const struct pcr_ops rts5264_pcr_ops = {
+	.turn_on_led = rts5264_turn_on_led,
+	.turn_off_led = rts5264_turn_off_led,
+	.extra_init_hw = rts5264_extra_init_hw,
+	.enable_auto_blink = rts5264_enable_auto_blink,
+	.disable_auto_blink = rts5264_disable_auto_blink,
+	.card_power_on = rts5264_card_power_on,
+	.card_power_off = rts5264_card_power_off,
+	.switch_output_voltage = rts5264_switch_output_voltage,
+	.force_power_down = rts5264_force_power_down,
+	.stop_cmd = rts5264_stop_cmd,
+	.set_aspm = rts5264_set_aspm,
+	.set_l1off_cfg_sub_d0 = rts5264_set_l1off_cfg_sub_d0,
+	.enable_ocp = rts5264_enable_ocp,
+	.disable_ocp = rts5264_disable_ocp,
+	.init_ocp = rts5264_init_ocp,
+	.process_ocp = rts5264_process_ocp,
+	.clear_ocpstat = rts5264_clear_ocpstat,
+};
+
+static inline u8 double_ssc_depth(u8 depth)
+{
+	return ((depth > 1) ? (depth - 1) : depth);
+}
+
+int rts5264_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
+		u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk)
+{
+	int err, clk;
+	u16 n;
+	u8 clk_divider, mcu_cnt, div;
+	static const u8 depth[] = {
+		[RTSX_SSC_DEPTH_4M] = RTS5264_SSC_DEPTH_4M,
+		[RTSX_SSC_DEPTH_2M] = RTS5264_SSC_DEPTH_2M,
+		[RTSX_SSC_DEPTH_1M] = RTS5264_SSC_DEPTH_1M,
+		[RTSX_SSC_DEPTH_500K] = RTS5264_SSC_DEPTH_512K,
+	};
+
+	if (initial_mode) {
+		/* We use 250k(around) here, in initial stage */
+		clk_divider = SD_CLK_DIVIDE_128;
+		card_clock = 30000000;
+	} else {
+		clk_divider = SD_CLK_DIVIDE_0;
+	}
+	err = rtsx_pci_write_register(pcr, SD_CFG1,
+			SD_CLK_DIVIDE_MASK, clk_divider);
+	if (err < 0)
+		return err;
+
+	card_clock /= 1000000;
+	pcr_dbg(pcr, "Switch card clock to %dMHz\n", card_clock);
+
+	clk = card_clock;
+	if (!initial_mode && double_clk)
+		clk = card_clock * 2;
+	pcr_dbg(pcr, "Internal SSC clock: %dMHz (cur_clock = %d)\n",
+		clk, pcr->cur_clock);
+
+	if (clk == pcr->cur_clock)
+		return 0;
+
+	if (pcr->ops->conv_clk_and_div_n)
+		n = pcr->ops->conv_clk_and_div_n(clk, CLK_TO_DIV_N);
+	else
+		n = clk - 4;
+	if ((clk <= 4) || (n > 396))
+		return -EINVAL;
+
+	mcu_cnt = 125/clk + 3;
+	if (mcu_cnt > 15)
+		mcu_cnt = 15;
+
+	div = CLK_DIV_1;
+	while ((n < MIN_DIV_N_PCR - 4) && (div < CLK_DIV_8)) {
+		if (pcr->ops->conv_clk_and_div_n) {
+			int dbl_clk = pcr->ops->conv_clk_and_div_n(n,
+					DIV_N_TO_CLK) * 2;
+			n = pcr->ops->conv_clk_and_div_n(dbl_clk,
+					CLK_TO_DIV_N);
+		} else {
+			n = (n + 4) * 2 - 4;
+		}
+		div++;
+	}
+
+	n = (n / 2) - 1;
+	pcr_dbg(pcr, "n = %d, div = %d\n", n, div);
+
+	ssc_depth = depth[ssc_depth];
+	if (double_clk)
+		ssc_depth = double_ssc_depth(ssc_depth);
+
+	if (ssc_depth) {
+		if (div == CLK_DIV_2) {
+			if (ssc_depth > 1)
+				ssc_depth -= 1;
+			else
+				ssc_depth = RTS5264_SSC_DEPTH_8M;
+		} else if (div == CLK_DIV_4) {
+			if (ssc_depth > 2)
+				ssc_depth -= 2;
+			else
+				ssc_depth = RTS5264_SSC_DEPTH_8M;
+		} else if (div == CLK_DIV_8) {
+			if (ssc_depth > 3)
+				ssc_depth -= 3;
+			else
+				ssc_depth = RTS5264_SSC_DEPTH_8M;
+		}
+	} else {
+		ssc_depth = 0;
+	}
+	pcr_dbg(pcr, "ssc_depth = %d\n", ssc_depth);
+
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_CTL,
+				CHANGE_CLK, CHANGE_CLK);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_DIV,
+			0xFF, (div << 4) | mcu_cnt);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, 0);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2,
+			SSC_DEPTH_MASK, ssc_depth);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_DIV_N_0, 0xFF, n);
+
+	if (is_version(pcr, 0x5264, IC_VER_A)) {
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, 0);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, RTS5264_CARD_CLK_SRC2,
+			RTS5264_REG_BIG_KVCO_A, 0);
+	} else {
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, SSC_RSTB);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, RTS5264_SYS_DUMMY_1,
+			RTS5264_REG_BIG_KVCO, 0);
+	}
+
+	if (vpclk) {
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK0_CTL,
+				PHASE_NOT_RESET, 0);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK1_CTL,
+				PHASE_NOT_RESET, 0);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK0_CTL,
+				PHASE_NOT_RESET, PHASE_NOT_RESET);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK1_CTL,
+				PHASE_NOT_RESET, PHASE_NOT_RESET);
+	}
+
+	err = rtsx_pci_send_cmd(pcr, 2000);
+	if (err < 0)
+		return err;
+
+	/* Wait SSC clock stable */
+	udelay(SSC_CLOCK_STABLE_WAIT);
+	err = rtsx_pci_write_register(pcr, CLK_CTL, CHANGE_CLK, 0);
+	if (err < 0)
+		return err;
+
+	pcr->cur_clock = clk;
+	return 0;
+}
+
+void rts5264_init_params(struct rtsx_pcr *pcr)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+	struct rtsx_hw_param *hw_param = &pcr->hw_param;
+	u8 val;
+
+	pcr->extra_caps = EXTRA_CAPS_SD_SDR50 | EXTRA_CAPS_SD_SDR104;
+	pcr->extra_caps |= EXTRA_CAPS_NO_MMC;
+	rtsx_pci_read_register(pcr, RTS5264_FW_STATUS, &val);
+	if (!(val & RTS5264_EXPRESS_LINK_FAIL_MASK))
+		pcr->extra_caps |= EXTRA_CAPS_SD_EXPRESS;
+	pcr->num_slots = 1;
+	pcr->ops = &rts5264_pcr_ops;
+
+	pcr->flags = 0;
+	pcr->card_drive_sel = RTSX_CARD_DRIVE_DEFAULT;
+	pcr->sd30_drive_sel_1v8 = 0x00;
+	pcr->sd30_drive_sel_3v3 = 0x00;
+	pcr->aspm_en = ASPM_L1_EN;
+	pcr->aspm_mode = ASPM_MODE_REG;
+	pcr->tx_initial_phase = SET_CLOCK_PHASE(24, 24, 11);
+	pcr->rx_initial_phase = SET_CLOCK_PHASE(24, 6, 5);
+
+	pcr->ic_version = rts5264_get_ic_version(pcr);
+	pcr->sd_pull_ctl_enable_tbl = rts5264_sd_pull_ctl_enable_tbl;
+	pcr->sd_pull_ctl_disable_tbl = rts5264_sd_pull_ctl_disable_tbl;
+
+	pcr->reg_pm_ctrl3 = RTS5264_AUTOLOAD_CFG3;
+
+	option->dev_flags = (LTR_L1SS_PWR_GATE_CHECK_CARD_EN
+				| LTR_L1SS_PWR_GATE_EN);
+	option->ltr_en = true;
+
+	/* init latency of active, idle, L1OFF to 60us, 300us, 3ms */
+	option->ltr_active_latency = LTR_ACTIVE_LATENCY_DEF;
+	option->ltr_idle_latency = LTR_IDLE_LATENCY_DEF;
+	option->ltr_l1off_latency = LTR_L1OFF_LATENCY_DEF;
+	option->l1_snooze_delay = L1_SNOOZE_DELAY_DEF;
+	option->ltr_l1off_sspwrgate = 0x7F;
+	option->ltr_l1off_snooze_sspwrgate = 0x78;
+
+	option->ocp_en = 1;
+	hw_param->interrupt_en |= (SD_OC_INT_EN | SD_OVP_INT_EN);
+	hw_param->ocp_glitch =  SD_OCP_GLITCH_800U | SDVIO_OCP_GLITCH_800U;
+	option->sd_800mA_ocp_thd =  RTS5264_LDO1_OCP_THD_1150;
+}
diff --git a/drivers/misc/cardreader/rts5264.h b/drivers/misc/cardreader/rts5264.h
new file mode 100644
index 000000000000..e3cbbf2fe1a4
--- /dev/null
+++ b/drivers/misc/cardreader/rts5264.h
@@ -0,0 +1,278 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2018-2019 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * Author:
+ *   Ricky Wu <ricky_wu@realtek.com>
+ */
+#ifndef RTS5264_H
+#define RTS5264_H
+
+/*New add*/
+#define rts5264_vendor_setting_valid(reg)	((reg) & 0x010000)
+#define rts5264_reg_to_aspm(reg) \
+	(((~(reg) >> 28) & 0x02) | (((reg) >> 28) & 0x01))
+#define rts5264_reg_check_reverse_socket(reg)	((reg) & 0x04)
+#define rts5264_reg_to_sd30_drive_sel_1v8(reg)	(((reg) >> 22) & 0x03)
+#define rts5264_reg_to_sd30_drive_sel_3v3(reg)	(((reg) >> 16) & 0x03)
+#define rts5264_reg_to_rtd3(reg)		((reg) & 0x08)
+
+#define RTS5264_AUTOLOAD_CFG0		0xFF7B
+#define RTS5264_AUTOLOAD_CFG1		0xFF7C
+#define RTS5264_AUTOLOAD_CFG3		0xFF7E
+#define RTS5264_AUTOLOAD_CFG4		0xFF7F
+#define RTS5264_FORCE_PRSNT_LOW		(1 << 6)
+#define RTS5264_AUX_CLK_16M_EN		(1 << 5)
+#define RTS5264_F_HIGH_RC_MASK		(1 << 4)
+#define RTS5264_F_HIGH_RC_1_6M		(1 << 4)
+#define RTS5264_F_HIGH_RC_400K		(0 << 4)
+
+/* SSC_CTL2 0xFC12 */
+#define RTS5264_SSC_DEPTH_MASK		0x07
+#define RTS5264_SSC_DEPTH_DISALBE	0x00
+#define RTS5264_SSC_DEPTH_8M		0x01
+#define RTS5264_SSC_DEPTH_4M		0x02
+#define RTS5264_SSC_DEPTH_2M		0x03
+#define RTS5264_SSC_DEPTH_1M		0x04
+#define RTS5264_SSC_DEPTH_512K		0x05
+#define RTS5264_SSC_DEPTH_256K		0x06
+#define RTS5264_SSC_DEPTH_128K		0x07
+
+#define RTS5264_CARD_CLK_SRC2		0xFC2F
+#define RTS5264_REG_BIG_KVCO_A		0x20
+
+/* efuse control register*/
+#define RTS5264_EFUSE_CTL		0xFC30
+#define RTS5264_EFUSE_ENABLE		0x80
+/* EFUSE_MODE: 0=READ 1=PROGRAM */
+#define RTS5264_EFUSE_MODE_MASK		0x40
+#define RTS5264_EFUSE_PROGRAM		0x40
+
+#define RTS5264_EFUSE_ADDR		0xFC31
+#define	RTS5264_EFUSE_ADDR_MASK		0x3F
+
+#define RTS5264_EFUSE_WRITE_DATA	0xFC32
+#define RTS5264_EFUSE_READ_DATA		0xFC34
+
+#define RTS5264_SYS_DUMMY_1		0xFC35
+#define RTS5264_REG_BIG_KVCO		0x04
+
+/* DMACTL 0xFE2C */
+#define RTS5264_DMA_PACK_SIZE_MASK	0x70
+
+#define RTS5264_FW_CFG1			0xFF55
+#define RTS5264_SYS_CLK_SEL_MCU_CLK	(0x01<<7)
+#define RTS5264_CRC_CLK_SEL_MCU_CLK	(0x01<<6)
+#define RTS5264_FAKE_MCU_CLOCK_GATING	(0x01<<5)
+#define RTS5264_MCU_BUS_SEL_MASK	(0x01<<4)
+
+/* FW status register */
+#define RTS5264_FW_STATUS		0xFF56
+#define RTS5264_EXPRESS_LINK_FAIL_MASK	(0x01<<7)
+
+/* FW control register */
+#define RTS5264_FW_CTL			0xFF5F
+#define RTS5264_INFORM_RTD3_COLD	(0x01<<5)
+
+#define RTS5264_REG_FPDCTL		0xFF60
+
+#define RTS5264_REG_LDO12_CFG		0xFF6E
+#define RTS5264_LDO12_SR_MASK		(0x03<<6)
+#define RTS5264_LDO12_SR_1_0_MS		(0x03<<6)
+#define RTS5264_LDO12_SR_0_5_MS		(0x02<<6)
+#define RTS5264_LDO12_SR_0_2_5_MS	(0x01<<6)
+#define RTS5264_LDO12_SR_0_0_MS		(0x00<<6)
+#define RTS5264_LDO12_VO_TUNE_MASK	(0x07<<1)
+#define RTS5264_LDO12_115		(0x03<<1)
+#define RTS5264_LDO12_120		(0x04<<1)
+#define RTS5264_LDO12_125		(0x05<<1)
+#define RTS5264_LDO12_130		(0x06<<1)
+#define RTS5264_LDO12_135		(0x07<<1)
+
+/* LDO control register */
+#define RTS5264_CARD_PWR_CTL		0xFD50
+#define RTS5264_SD_CLK_ISO		(0x01<<7)
+#define RTS5264_PAD_SD_DAT_FW_CTRL	(0x01<<6)
+#define RTS5264_PUPDC			(0x01<<5)
+#define RTS5264_SD_CMD_ISO		(0x01<<4)
+
+#define RTS5264_OCP_VDD3_CTL		0xFD89
+#define SD_VDD3_DETECT_EN		0x08
+#define SD_VDD3_OCP_INT_EN		0x04
+#define SD_VDD3_OCP_INT_CLR		0x02
+#define SD_VDD3_OC_CLR			0x01
+
+#define RTS5264_OCP_VDD3_STS		0xFD8A
+#define SD_VDD3_OCP_DETECT		0x08
+#define SD_VDD3_OC_NOW			0x04
+#define SD_VDD3_OC_EVER			0x02
+
+#define RTS5264_OVP_CTL			0xFD8D
+#define RTS5264_OVP_TIME_MASK		0xF0
+#define RTS5264_OVP_TIME_DFT		0x50
+#define RTS5264_OVP_DETECT_EN		0x08
+#define RTS5264_OVP_INT_EN		0x04
+#define RTS5264_OVP_INT_CLR		0x02
+#define RTS5264_OVP_CLR			0x01
+
+#define RTS5264_OVP_STS			0xFD8E
+#define RTS5264_OVP_GLTCH_TIME_MASK	0xF0
+#define RTS5264_OVP_GLTCH_TIME_DFT	0x50
+#define RTS5264_VOVER_DET		0x08
+#define RTS5264_OVP_NOW			0x04
+#define RTS5264_OVP_EVER		0x02
+
+#define RTS5264_CMD_OE_START_EARLY		0xFDCB
+#define RTS5264_CMD_OE_EARLY_LEAVE		0x08
+#define RTS5264_CMD_OE_EARLY_CYCLE_MASK		0x06
+#define RTS5264_CMD_OE_EARLY_4CYCLE		0x06
+#define RTS5264_CMD_OE_EARLY_3CYCLE		0x04
+#define RTS5264_CMD_OE_EARLY_2CYCLE		0x02
+#define RTS5264_CMD_OE_EARLY_1CYCLE		0x00
+#define RTS5264_CMD_OE_EARLY_EN			0x01
+
+#define RTS5264_DAT_OE_START_EARLY		0xFDCC
+#define RTS5264_DAT_OE_EARLY_LEAVE		0x08
+#define RTS5264_DAT_OE_EARLY_CYCLE_MASK		0x06
+#define RTS5264_DAT_OE_EARLY_4CYCLE		0x06
+#define RTS5264_DAT_OE_EARLY_3CYCLE		0x04
+#define RTS5264_DAT_OE_EARLY_2CYCLE		0x02
+#define RTS5264_DAT_OE_EARLY_1CYCLE		0x00
+#define RTS5264_DAT_OE_EARLY_EN			0x01
+
+#define RTS5264_LDO1233318_POW_CTL	0xFF70
+#define RTS5264_TUNE_REF_LDO3318	(0x03<<6)
+#define RTS5264_TUNE_REF_LDO3318_DFT	(0x02<<6)
+#define RTS5264_LDO3318_POWERON		(0x01<<3)
+#define RTS5264_LDO3_POWERON		(0x01<<2)
+#define RTS5264_LDO2_POWERON		(0x01<<1)
+#define RTS5264_LDO1_POWERON		(0x01<<0)
+#define RTS5264_LDO_POWERON_MASK	(0x0F<<0)
+
+#define RTS5264_DV3318_CFG		0xFF71
+#define RTS5264_DV3318_TUNE_MASK	(0x07<<4)
+#define RTS5264_DV3318_18		(0x02<<4)
+#define RTS5264_DV3318_19		(0x04<<4)
+#define RTS5264_DV3318_33		(0x07<<4)
+
+#define RTS5264_LDO1_CFG0		0xFF72
+#define RTS5264_LDO1_OCP_THD_MASK	(0x07 << 5)
+#define RTS5264_LDO1_OCP_EN		(0x01 << 4)
+#define RTS5264_LDO1_OCP_LMT_THD_MASK	(0x03 << 2)
+#define RTS5264_LDO1_OCP_LMT_EN		(0x01 << 1)
+
+#define RTS5264_LDO1_OCP_THD_850	(0x00<<5)
+#define RTS5264_LDO1_OCP_THD_950	(0x01<<5)
+#define RTS5264_LDO1_OCP_THD_1050	(0x02<<5)
+#define RTS5264_LDO1_OCP_THD_1100	(0x03<<5)
+#define RTS5264_LDO1_OCP_THD_1150	(0x04<<5)
+#define RTS5264_LDO1_OCP_THD_1200	(0x05<<5)
+#define RTS5264_LDO1_OCP_THD_1300	(0x06<<5)
+#define RTS5264_LDO1_OCP_THD_1350	(0x07<<5)
+
+#define RTS5264_LDO1_LMT_THD_1700	(0x00<<2)
+#define RTS5264_LDO1_LMT_THD_1800	(0x01<<2)
+#define RTS5264_LDO1_LMT_THD_1900	(0x02<<2)
+#define RTS5264_LDO1_LMT_THD_2000	(0x03<<2)
+
+#define RTS5264_LDO1_CFG1		0xFF73
+#define RTS5264_LDO1_TUNE_MASK		(0x07<<1)
+#define RTS5264_LDO1_18			(0x05<<1)
+#define RTS5264_LDO1_33			(0x07<<1)
+#define RTS5264_LDO1_PWD_MASK		(0x01<<0)
+
+#define RTS5264_LDO2_CFG0		0xFF74
+#define RTS5264_LDO2_OCP_THD_MASK	(0x07<<5)
+#define RTS5264_LDO2_OCP_EN		(0x01<<4)
+#define RTS5264_LDO2_OCP_LMT_THD_MASK	(0x03<<2)
+#define RTS5264_LDO2_OCP_LMT_EN		(0x01<<1)
+
+#define RTS5264_LDO2_OCP_THD_750	(0x00<<5)
+#define RTS5264_LDO2_OCP_THD_850	(0x01<<5)
+#define RTS5264_LDO2_OCP_THD_900	(0x02<<5)
+#define RTS5264_LDO2_OCP_THD_950	(0x03<<5)
+#define RTS5264_LDO2_OCP_THD_1050	(0x04<<5)
+#define RTS5264_LDO2_OCP_THD_1100	(0x05<<5)
+#define RTS5264_LDO2_OCP_THD_1150	(0x06<<5)
+#define RTS5264_LDO2_OCP_THD_1200	(0x07<<5)
+
+#define RTS5264_LDO2_LMT_THD_1700	(0x00<<2)
+#define RTS5264_LDO2_LMT_THD_1800	(0x01<<2)
+#define RTS5264_LDO2_LMT_THD_1900	(0x02<<2)
+#define RTS5264_LDO2_LMT_THD_2000	(0x03<<2)
+
+#define RTS5264_LDO2_CFG1		0xFF75
+#define RTS5264_LDO2_TUNE_MASK		(0x07<<1)
+#define RTS5264_LDO2_18			(0x02<<1)
+#define RTS5264_LDO2_185		(0x03<<1)
+#define RTS5264_LDO2_19			(0x04<<1)
+#define RTS5264_LDO2_195		(0x05<<1)
+#define RTS5264_LDO2_33			(0x07<<1)
+#define RTS5264_LDO2_PWD_MASK		(0x01<<0)
+
+#define RTS5264_LDO3_CFG0		0xFF76
+#define RTS5264_LDO3_OCP_THD_MASK	(0x07<<5)
+#define RTS5264_LDO3_OCP_EN		(0x01<<4)
+#define RTS5264_LDO3_OCP_LMT_THD_MASK	(0x03<<2)
+#define RTS5264_LDO3_OCP_LMT_EN		(0x01<<1)
+
+#define RTS5264_LDO3_OCP_THD_610	(0x00<<5)
+#define RTS5264_LDO3_OCP_THD_630	(0x01<<5)
+#define RTS5264_LDO3_OCP_THD_670	(0x02<<5)
+#define RTS5264_LDO3_OCP_THD_710	(0x03<<5)
+#define RTS5264_LDO3_OCP_THD_750	(0x04<<5)
+#define RTS5264_LDO3_OCP_THD_770	(0x05<<5)
+#define RTS5264_LDO3_OCP_THD_810	(0x06<<5)
+#define RTS5264_LDO3_OCP_THD_850	(0x07<<5)
+
+#define RTS5264_LDO3_LMT_THD_1200	(0x00<<2)
+#define RTS5264_LDO3_LMT_THD_1300	(0x01<<2)
+#define RTS5264_LDO3_LMT_THD_1400	(0x02<<2)
+#define RTS5264_LDO3_LMT_THD_1500	(0x03<<2)
+
+#define RTS5264_LDO3_CFG1		0xFF77
+#define RTS5264_LDO3_TUNE_MASK		(0x07<<1)
+#define RTS5264_LDO3_12			(0x02<<1)
+#define RTS5264_LDO3_125		(0x03<<1)
+#define RTS5264_LDO3_13			(0x04<<1)
+#define RTS5264_LDO3_135		(0x05<<1)
+#define RTS5264_LDO3_33			(0x07<<1)
+#define RTS5264_LDO3_PWD_MASK		(0x01<<0)
+
+#define RTS5264_REG_PME_FORCE_CTL	0xFF78
+#define FORCE_PM_CONTROL		0x20
+#define FORCE_PM_VALUE			0x10
+#define REG_EFUSE_BYPASS		0x08
+#define REG_EFUSE_POR			0x04
+#define REG_EFUSE_POWER_MASK		0x03
+#define REG_EFUSE_POWERON		0x03
+#define REG_EFUSE_POWEROFF		0x00
+
+#define RTS5264_PWR_CUT			0xFF81
+#define RTS5264_CFG_MEM_PD		0xF0
+
+#define RTS5264_OVP_DET			0xFF8A
+#define RTS5264_POW_VDET		0x04
+#define RTS5264_TUNE_VROV_MASK		0x03
+#define RTS5264_TUNE_VROV_2V		0x03
+#define RTS5264_TUNE_VROV_1V8		0x02
+#define RTS5264_TUNE_VROV_1V6		0x01
+#define RTS5264_TUNE_VROV_1V4		0x00
+
+#define RTS5264_CKMUX_MBIAS_PWR		0xFF8B
+#define RTS5264_NON_XTAL_SEL		0x80
+#define RTS5264_POW_CKMUX		0x40
+#define RTS5264_LVD_MASK		0x04
+#define RTS5264_POW_PSW_MASK		0x03
+#define RTS5264_POW_PSW_DFT		0x03
+
+/* Single LUN, support SD/SD EXPRESS */
+#define DEFAULT_SINGLE		0
+#define SD_LUN			1
+#define SD_EXPRESS_LUN		2
+
+int rts5264_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
+		u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk);
+
+#endif /* RTS5264_H */
diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c
index a30751ad3733..1a64364700eb 100644
--- a/drivers/misc/cardreader/rtsx_pcr.c
+++ b/drivers/misc/cardreader/rtsx_pcr.c
@@ -26,6 +26,7 @@
 #include "rtsx_pcr.h"
 #include "rts5261.h"
 #include "rts5228.h"
+#include "rts5264.h"
 
 static bool msi_en = true;
 module_param(msi_en, bool, S_IRUGO | S_IWUSR);
@@ -54,6 +55,7 @@ static const struct pci_device_id rtsx_pci_ids[] = {
 	{ PCI_DEVICE(0x10EC, 0x5260), PCI_CLASS_OTHERS << 16, 0xFF0000 },
 	{ PCI_DEVICE(0x10EC, 0x5261), PCI_CLASS_OTHERS << 16, 0xFF0000 },
 	{ PCI_DEVICE(0x10EC, 0x5228), PCI_CLASS_OTHERS << 16, 0xFF0000 },
+	{ PCI_DEVICE(0x10EC, 0x5264), PCI_CLASS_OTHERS << 16, 0xFF0000 },
 	{ 0, }
 };
 
@@ -714,6 +716,9 @@ int rtsx_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
 	if (PCI_PID(pcr) == PID_5228)
 		return rts5228_pci_switch_clock(pcr, card_clock,
 				ssc_depth, initial_mode, double_clk, vpclk);
+	if (PCI_PID(pcr) == PID_5264)
+		return rts5264_pci_switch_clock(pcr, card_clock,
+				ssc_depth, initial_mode, double_clk, vpclk);
 
 	if (initial_mode) {
 		/* We use 250k(around) here, in initial stage */
@@ -987,7 +992,8 @@ static irqreturn_t rtsx_pci_isr(int irq, void *dev_id)
 
 	int_reg &= (pcr->bier | 0x7FFFFF);
 
-	if (int_reg & SD_OC_INT)
+	if ((int_reg & SD_OC_INT) ||
+			((int_reg & SD_OVP_INT) && (PCI_PID(pcr) == PID_5264)))
 		rtsx_pci_process_ocp_interrupt(pcr);
 
 	if (int_reg & SD_INT) {
@@ -1159,7 +1165,9 @@ void rtsx_pci_enable_oobs_polling(struct rtsx_pcr *pcr)
 {
 	u16 val;
 
-	if ((PCI_PID(pcr) != PID_525A) && (PCI_PID(pcr) != PID_5260)) {
+	if ((PCI_PID(pcr) != PID_525A) &&
+		(PCI_PID(pcr) != PID_5260) &&
+		(PCI_PID(pcr) != PID_5264)) {
 		rtsx_pci_read_phy_register(pcr, 0x01, &val);
 		val |= 1<<9;
 		rtsx_pci_write_phy_register(pcr, 0x01, val);
@@ -1175,7 +1183,9 @@ void rtsx_pci_disable_oobs_polling(struct rtsx_pcr *pcr)
 {
 	u16 val;
 
-	if ((PCI_PID(pcr) != PID_525A) && (PCI_PID(pcr) != PID_5260)) {
+	if ((PCI_PID(pcr) != PID_525A) &&
+		(PCI_PID(pcr) != PID_5260) &&
+		(PCI_PID(pcr) != PID_5264)) {
 		rtsx_pci_read_phy_register(pcr, 0x01, &val);
 		val &= ~(1<<9);
 		rtsx_pci_write_phy_register(pcr, 0x01, val);
@@ -1226,7 +1236,7 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr)
 	rtsx_pci_enable_bus_int(pcr);
 
 	/* Power on SSC */
-	if (PCI_PID(pcr) == PID_5261) {
+	if ((PCI_PID(pcr) == PID_5261) || (PCI_PID(pcr) == PID_5264)) {
 		/* Gating real mcu clock */
 		err = rtsx_pci_write_register(pcr, RTS5261_FW_CFG1,
 			RTS5261_MCU_CLOCK_GATING, 0);
@@ -1270,6 +1280,11 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr)
 	else if (PCI_PID(pcr) == PID_5228)
 		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2, 0xFF,
 			RTS5228_SSC_DEPTH_2M);
+	else if (is_version(pcr, 0x5264, IC_VER_A))
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, 0);
+	else if (PCI_PID(pcr) == PID_5264)
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2, 0xFF,
+			RTS5264_SSC_DEPTH_2M);
 	else
 		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2, 0xFF, 0x12);
 
@@ -1305,6 +1320,7 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr)
 	case PID_5260:
 	case PID_5261:
 	case PID_5228:
+	case PID_5264:
 		rtsx_pci_write_register(pcr, PM_CLK_FORCE_CTL, 1, 1);
 		break;
 	default:
@@ -1404,6 +1420,10 @@ static int rtsx_pci_init_chip(struct rtsx_pcr *pcr)
 	case 0x5228:
 		rts5228_init_params(pcr);
 		break;
+
+	case 0x5264:
+		rts5264_init_params(pcr);
+		break;
 	}
 
 	pcr_dbg(pcr, "PID: 0x%04x, IC version: 0x%02x\n",
@@ -1544,7 +1564,7 @@ static int rtsx_pci_probe(struct pci_dev *pcidev,
 	pcr->pci = pcidev;
 	dev_set_drvdata(&pcidev->dev, handle);
 
-	if (CHK_PCI_PID(pcr, 0x525A))
+	if ((CHK_PCI_PID(pcr, 0x525A)) || (CHK_PCI_PID(pcr, 0x5264)))
 		bar = 1;
 	len = pci_resource_len(pcidev, bar);
 	base = pci_resource_start(pcidev, bar);
diff --git a/drivers/misc/cardreader/rtsx_pcr.h b/drivers/misc/cardreader/rtsx_pcr.h
index 37d1f316ae17..9215d66de00c 100644
--- a/drivers/misc/cardreader/rtsx_pcr.h
+++ b/drivers/misc/cardreader/rtsx_pcr.h
@@ -74,6 +74,7 @@ void rtl8411b_init_params(struct rtsx_pcr *pcr);
 void rts5260_init_params(struct rtsx_pcr *pcr);
 void rts5261_init_params(struct rtsx_pcr *pcr);
 void rts5228_init_params(struct rtsx_pcr *pcr);
+void rts5264_init_params(struct rtsx_pcr *pcr);
 
 static inline u8 map_sd_drive(int idx)
 {
diff --git a/drivers/misc/dw-xdata-pcie.c b/drivers/misc/dw-xdata-pcie.c
index 257c25da5199..efd0ca8cc925 100644
--- a/drivers/misc/dw-xdata-pcie.c
+++ b/drivers/misc/dw-xdata-pcie.c
@@ -333,7 +333,7 @@ static int dw_xdata_pcie_probe(struct pci_dev *pdev,
 
 	dw->pdev = pdev;
 
-	id = ida_simple_get(&xdata_ida, 0, 0, GFP_KERNEL);
+	id = ida_alloc(&xdata_ida, GFP_KERNEL);
 	if (id < 0) {
 		dev_err(dev, "xData: unable to get id\n");
 		return id;
@@ -377,7 +377,7 @@ err_kfree_name:
 	kfree(dw->misc_dev.name);
 
 err_ida_remove:
-	ida_simple_remove(&xdata_ida, id);
+	ida_free(&xdata_ida, id);
 
 	return err;
 }
@@ -396,7 +396,7 @@ static void dw_xdata_pcie_remove(struct pci_dev *pdev)
 	dw_xdata_stop(dw);
 	misc_deregister(&dw->misc_dev);
 	kfree(dw->misc_dev.name);
-	ida_simple_remove(&xdata_ida, id);
+	ida_free(&xdata_ida, id);
 }
 
 static const struct pci_device_id dw_xdata_pcie_id_table[] = {
diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c
index f61a80597a22..572333ead5fb 100644
--- a/drivers/misc/eeprom/at24.c
+++ b/drivers/misc/eeprom/at24.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/nvmem-provider.h>
+#include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/property.h>
@@ -242,7 +243,7 @@ static const struct i2c_device_id at24_ids[] = {
 };
 MODULE_DEVICE_TABLE(i2c, at24_ids);
 
-static const struct of_device_id at24_of_match[] = {
+static const struct of_device_id __maybe_unused at24_of_match[] = {
 	{ .compatible = "atmel,24c00",		.data = &at24_data_24c00 },
 	{ .compatible = "atmel,24c01",		.data = &at24_data_24c01 },
 	{ .compatible = "atmel,24cs01",		.data = &at24_data_24cs01 },
@@ -439,12 +440,9 @@ static int at24_read(void *priv, unsigned int off, void *val, size_t count)
 	if (off + count > at24->byte_len)
 		return -EINVAL;
 
-	ret = pm_runtime_get_sync(dev);
-	if (ret < 0) {
-		pm_runtime_put_noidle(dev);
+	ret = pm_runtime_resume_and_get(dev);
+	if (ret)
 		return ret;
-	}
-
 	/*
 	 * Read data from chip, protecting against concurrent updates
 	 * from this host, but not from other I2C masters.
@@ -486,12 +484,9 @@ static int at24_write(void *priv, unsigned int off, void *val, size_t count)
 	if (off + count > at24->byte_len)
 		return -EINVAL;
 
-	ret = pm_runtime_get_sync(dev);
-	if (ret < 0) {
-		pm_runtime_put_noidle(dev);
+	ret = pm_runtime_resume_and_get(dev);
+	if (ret)
 		return ret;
-	}
-
 	/*
 	 * Write data to chip, protecting against concurrent updates
 	 * from this host, but not from other I2C masters.
@@ -563,6 +558,31 @@ static unsigned int at24_get_offset_adj(u8 flags, unsigned int byte_len)
 	}
 }
 
+static void at24_probe_temp_sensor(struct i2c_client *client)
+{
+	struct at24_data *at24 = i2c_get_clientdata(client);
+	struct i2c_board_info info = { .type = "jc42" };
+	int ret;
+	u8 val;
+
+	/*
+	 * Byte 2 has value 11 for DDR3, earlier versions don't
+	 * support the thermal sensor present flag
+	 */
+	ret = at24_read(at24, 2, &val, 1);
+	if (ret || val != 11)
+		return;
+
+	/* Byte 32, bit 7 is set if temp sensor is present */
+	ret = at24_read(at24, 32, &val, 1);
+	if (ret || !(val & BIT(7)))
+		return;
+
+	info.addr = 0x18 | (client->addr & 7);
+
+	i2c_new_client_device(client->adapter, &info);
+}
+
 static int at24_probe(struct i2c_client *client)
 {
 	struct regmap_config regmap_config = { };
@@ -762,6 +782,10 @@ static int at24_probe(struct i2c_client *client)
 		}
 	}
 
+	/* If this a SPD EEPROM, probe for DDR3 thermal sensor */
+	if (cdata == &at24_data_spd)
+		at24_probe_temp_sensor(client);
+
 	pm_runtime_idle(dev);
 
 	if (writable)
@@ -812,7 +836,7 @@ static struct i2c_driver at24_driver = {
 	.driver = {
 		.name = "at24",
 		.pm = &at24_pm_ops,
-		.of_match_table = at24_of_match,
+		.of_match_table = of_match_ptr(at24_of_match),
 		.acpi_match_table = ACPI_PTR(at24_acpi_ids),
 	},
 	.probe = at24_probe,
diff --git a/drivers/misc/eeprom/ee1004.c b/drivers/misc/eeprom/ee1004.c
index a1acd77130f2..21feebc3044c 100644
--- a/drivers/misc/eeprom/ee1004.c
+++ b/drivers/misc/eeprom/ee1004.c
@@ -31,6 +31,7 @@
  * over performance.
  */
 
+#define EE1004_MAX_BUSSES		8
 #define EE1004_ADDR_SET_PAGE		0x36
 #define EE1004_NUM_PAGES		2
 #define EE1004_PAGE_SIZE		256
@@ -42,9 +43,13 @@
  * from page selection to end of read.
  */
 static DEFINE_MUTEX(ee1004_bus_lock);
-static struct i2c_client *ee1004_set_page[EE1004_NUM_PAGES];
-static unsigned int ee1004_dev_count;
-static int ee1004_current_page;
+
+static struct ee1004_bus_data {
+	struct i2c_adapter *adap;
+	struct i2c_client *set_page[EE1004_NUM_PAGES];
+	unsigned int dev_count;
+	int current_page;
+} ee1004_bus_data[EE1004_MAX_BUSSES];
 
 static const struct i2c_device_id ee1004_ids[] = {
 	{ "ee1004", 0 },
@@ -54,11 +59,29 @@ MODULE_DEVICE_TABLE(i2c, ee1004_ids);
 
 /*-------------------------------------------------------------------------*/
 
-static int ee1004_get_current_page(void)
+static struct ee1004_bus_data *ee1004_get_bus_data(struct i2c_adapter *adap)
+{
+	int i;
+
+	for (i = 0; i < EE1004_MAX_BUSSES; i++)
+		if (ee1004_bus_data[i].adap == adap)
+			return ee1004_bus_data + i;
+
+	/* If not existent yet, create new entry */
+	for (i = 0; i < EE1004_MAX_BUSSES; i++)
+		if (!ee1004_bus_data[i].adap) {
+			ee1004_bus_data[i].adap = adap;
+			return ee1004_bus_data + i;
+		}
+
+	return NULL;
+}
+
+static int ee1004_get_current_page(struct ee1004_bus_data *bd)
 {
 	int err;
 
-	err = i2c_smbus_read_byte(ee1004_set_page[0]);
+	err = i2c_smbus_read_byte(bd->set_page[0]);
 	if (err == -ENXIO) {
 		/* Nack means page 1 is selected */
 		return 1;
@@ -72,28 +95,29 @@ static int ee1004_get_current_page(void)
 	return 0;
 }
 
-static int ee1004_set_current_page(struct device *dev, int page)
+static int ee1004_set_current_page(struct i2c_client *client, int page)
 {
+	struct ee1004_bus_data *bd = i2c_get_clientdata(client);
 	int ret;
 
-	if (page == ee1004_current_page)
+	if (page == bd->current_page)
 		return 0;
 
 	/* Data is ignored */
-	ret = i2c_smbus_write_byte(ee1004_set_page[page], 0x00);
+	ret = i2c_smbus_write_byte(bd->set_page[page], 0x00);
 	/*
 	 * Don't give up just yet. Some memory modules will select the page
 	 * but not ack the command. Check which page is selected now.
 	 */
-	if (ret == -ENXIO && ee1004_get_current_page() == page)
+	if (ret == -ENXIO && ee1004_get_current_page(bd) == page)
 		ret = 0;
 	if (ret < 0) {
-		dev_err(dev, "Failed to select page %d (%d)\n", page, ret);
+		dev_err(&client->dev, "Failed to select page %d (%d)\n", page, ret);
 		return ret;
 	}
 
-	dev_dbg(dev, "Selected page %d\n", page);
-	ee1004_current_page = page;
+	dev_dbg(&client->dev, "Selected page %d\n", page);
+	bd->current_page = page;
 
 	return 0;
 }
@@ -106,7 +130,7 @@ static ssize_t ee1004_eeprom_read(struct i2c_client *client, char *buf,
 	page = offset >> EE1004_PAGE_SHIFT;
 	offset &= (1 << EE1004_PAGE_SHIFT) - 1;
 
-	status = ee1004_set_current_page(&client->dev, page);
+	status = ee1004_set_current_page(client, page);
 	if (status)
 		return status;
 
@@ -158,17 +182,34 @@ static struct bin_attribute *ee1004_attrs[] = {
 
 BIN_ATTRIBUTE_GROUPS(ee1004);
 
-static void ee1004_cleanup(int idx)
+static void ee1004_probe_temp_sensor(struct i2c_client *client)
 {
-	if (--ee1004_dev_count == 0)
-		while (--idx >= 0) {
-			i2c_unregister_device(ee1004_set_page[idx]);
-			ee1004_set_page[idx] = NULL;
-		}
+	struct i2c_board_info info = { .type = "jc42" };
+	u8 byte14;
+	int ret;
+
+	/* byte 14, bit 7 is set if temp sensor is present */
+	ret = ee1004_eeprom_read(client, &byte14, 14, 1);
+	if (ret != 1 || !(byte14 & BIT(7)))
+		return;
+
+	info.addr = 0x18 | (client->addr & 7);
+
+	i2c_new_client_device(client->adapter, &info);
+}
+
+static void ee1004_cleanup(int idx, struct ee1004_bus_data *bd)
+{
+	if (--bd->dev_count == 0) {
+		while (--idx >= 0)
+			i2c_unregister_device(bd->set_page[idx]);
+		memset(bd, 0, sizeof(struct ee1004_bus_data));
+	}
 }
 
 static int ee1004_probe(struct i2c_client *client)
 {
+	struct ee1004_bus_data *bd;
 	int err, cnr = 0;
 
 	/* Make sure we can operate on this adapter */
@@ -178,9 +219,19 @@ static int ee1004_probe(struct i2c_client *client)
 				     I2C_FUNC_SMBUS_BYTE | I2C_FUNC_SMBUS_READ_BYTE_DATA))
 		return -EPFNOSUPPORT;
 
-	/* Use 2 dummy devices for page select command */
 	mutex_lock(&ee1004_bus_lock);
-	if (++ee1004_dev_count == 1) {
+
+	bd = ee1004_get_bus_data(client->adapter);
+	if (!bd) {
+		mutex_unlock(&ee1004_bus_lock);
+		return dev_err_probe(&client->dev, -ENOSPC,
+				     "Only %d busses supported", EE1004_MAX_BUSSES);
+	}
+
+	i2c_set_clientdata(client, bd);
+
+	if (++bd->dev_count == 1) {
+		/* Use 2 dummy devices for page select command */
 		for (cnr = 0; cnr < EE1004_NUM_PAGES; cnr++) {
 			struct i2c_client *cl;
 
@@ -189,21 +240,19 @@ static int ee1004_probe(struct i2c_client *client)
 				err = PTR_ERR(cl);
 				goto err_clients;
 			}
-			ee1004_set_page[cnr] = cl;
+			bd->set_page[cnr] = cl;
 		}
 
 		/* Remember current page to avoid unneeded page select */
-		err = ee1004_get_current_page();
+		err = ee1004_get_current_page(bd);
 		if (err < 0)
 			goto err_clients;
 		dev_dbg(&client->dev, "Currently selected page: %d\n", err);
-		ee1004_current_page = err;
-	} else if (client->adapter != ee1004_set_page[0]->adapter) {
-		dev_err(&client->dev,
-			"Driver only supports devices on a single I2C bus\n");
-		err = -EOPNOTSUPP;
-		goto err_clients;
+		bd->current_page = err;
 	}
+
+	ee1004_probe_temp_sensor(client);
+
 	mutex_unlock(&ee1004_bus_lock);
 
 	dev_info(&client->dev,
@@ -213,7 +262,7 @@ static int ee1004_probe(struct i2c_client *client)
 	return 0;
 
  err_clients:
-	ee1004_cleanup(cnr);
+	ee1004_cleanup(cnr, bd);
 	mutex_unlock(&ee1004_bus_lock);
 
 	return err;
@@ -221,9 +270,11 @@ static int ee1004_probe(struct i2c_client *client)
 
 static void ee1004_remove(struct i2c_client *client)
 {
+	struct ee1004_bus_data *bd = i2c_get_clientdata(client);
+
 	/* Remove page select clients if this is the last device */
 	mutex_lock(&ee1004_bus_lock);
-	ee1004_cleanup(EE1004_NUM_PAGES);
+	ee1004_cleanup(EE1004_NUM_PAGES, bd);
 	mutex_unlock(&ee1004_bus_lock);
 }
 
diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 1c6c62a7f7f5..dbd26c3b245b 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -263,7 +263,6 @@ struct fastrpc_channel_ctx {
 	int domain_id;
 	int sesscount;
 	int vmcount;
-	u64 perms;
 	struct qcom_scm_vmperm vmperms[FASTRPC_MAX_VMIDS];
 	struct rpmsg_device *rpdev;
 	struct fastrpc_session_ctx session[FASTRPC_MAX_SESSIONS];
@@ -1279,9 +1278,11 @@ static int fastrpc_init_create_static_process(struct fastrpc_user *fl,
 
 		/* Map if we have any heap VMIDs associated with this ADSP Static Process. */
 		if (fl->cctx->vmcount) {
+			u64 src_perms = BIT(QCOM_SCM_VMID_HLOS);
+
 			err = qcom_scm_assign_mem(fl->cctx->remote_heap->phys,
 							(u64)fl->cctx->remote_heap->size,
-							&fl->cctx->perms,
+							&src_perms,
 							fl->cctx->vmperms, fl->cctx->vmcount);
 			if (err) {
 				dev_err(fl->sctx->dev, "Failed to assign memory with phys 0x%llx size 0x%llx err %d",
@@ -1915,8 +1916,10 @@ static int fastrpc_req_mmap(struct fastrpc_user *fl, char __user *argp)
 
 	/* Add memory to static PD pool, protection thru hypervisor */
 	if (req.flags == ADSP_MMAP_REMOTE_HEAP_ADDR && fl->cctx->vmcount) {
+		u64 src_perms = BIT(QCOM_SCM_VMID_HLOS);
+
 		err = qcom_scm_assign_mem(buf->phys, (u64)buf->size,
-			&fl->cctx->perms, fl->cctx->vmperms, fl->cctx->vmcount);
+			&src_perms, fl->cctx->vmperms, fl->cctx->vmcount);
 		if (err) {
 			dev_err(fl->sctx->dev, "Failed to assign memory phys 0x%llx size 0x%llx err %d",
 					buf->phys, buf->size, err);
@@ -2191,7 +2194,7 @@ static int fastrpc_cb_remove(struct platform_device *pdev)
 	int i;
 
 	spin_lock_irqsave(&cctx->lock, flags);
-	for (i = 1; i < FASTRPC_MAX_SESSIONS; i++) {
+	for (i = 0; i < FASTRPC_MAX_SESSIONS; i++) {
 		if (cctx->session[i].sid == sess->sid) {
 			cctx->session[i].valid = false;
 			cctx->sesscount--;
@@ -2290,7 +2293,6 @@ static int fastrpc_rpmsg_probe(struct rpmsg_device *rpdev)
 
 	if (vmcount) {
 		data->vmcount = vmcount;
-		data->perms = BIT(QCOM_SCM_VMID_HLOS);
 		for (i = 0; i < data->vmcount; i++) {
 			data->vmperms[i].vmid = vmids[i];
 			data->vmperms[i].perm = QCOM_SCM_PERM_RWX;
diff --git a/drivers/misc/lis3lv02d/lis3lv02d_i2c.c b/drivers/misc/lis3lv02d/lis3lv02d_i2c.c
index 3882e97e96a7..15119584473c 100644
--- a/drivers/misc/lis3lv02d/lis3lv02d_i2c.c
+++ b/drivers/misc/lis3lv02d/lis3lv02d_i2c.c
@@ -150,6 +150,7 @@ static int lis3lv02d_i2c_probe(struct i2c_client *client)
 	lis3_dev.init	  = lis3_i2c_init;
 	lis3_dev.read	  = lis3_i2c_read;
 	lis3_dev.write	  = lis3_i2c_write;
+	lis3_dev.reg_ctrl = lis3_reg_ctrl;
 	lis3_dev.irq	  = client->irq;
 	lis3_dev.ac	  = lis3lv02d_axis_map;
 	lis3_dev.pm_dev	  = &client->dev;
@@ -197,8 +198,14 @@ static int lis3lv02d_i2c_suspend(struct device *dev)
 	struct i2c_client *client = to_i2c_client(dev);
 	struct lis3lv02d *lis3 = i2c_get_clientdata(client);
 
-	if (!lis3->pdata || !lis3->pdata->wakeup_flags)
+	/* Turn on for wakeup if turned off by runtime suspend */
+	if (lis3->pdata && lis3->pdata->wakeup_flags) {
+		if (pm_runtime_suspended(dev))
+			lis3lv02d_poweron(lis3);
+	/* For non wakeup turn off if not already turned off by runtime suspend */
+	} else if (!pm_runtime_suspended(dev))
 		lis3lv02d_poweroff(lis3);
+
 	return 0;
 }
 
@@ -207,13 +214,12 @@ static int lis3lv02d_i2c_resume(struct device *dev)
 	struct i2c_client *client = to_i2c_client(dev);
 	struct lis3lv02d *lis3 = i2c_get_clientdata(client);
 
-	/*
-	 * pm_runtime documentation says that devices should always
-	 * be powered on at resume. Pm_runtime turns them off after system
-	 * wide resume is complete.
-	 */
-	if (!lis3->pdata || !lis3->pdata->wakeup_flags ||
-		pm_runtime_suspended(dev))
+	/* Turn back off if turned on for wakeup and runtime suspended*/
+	if (lis3->pdata && lis3->pdata->wakeup_flags) {
+		if (pm_runtime_suspended(dev))
+			lis3lv02d_poweroff(lis3);
+	/* For non wakeup turn back on if not runtime suspended */
+	} else if (!pm_runtime_suspended(dev))
 		lis3lv02d_poweron(lis3);
 
 	return 0;
diff --git a/drivers/misc/mei/Kconfig b/drivers/misc/mei/Kconfig
index 37db142de413..67d9391f1855 100644
--- a/drivers/misc/mei/Kconfig
+++ b/drivers/misc/mei/Kconfig
@@ -3,6 +3,7 @@
 config INTEL_MEI
 	tristate "Intel Management Engine Interface"
 	depends on X86 && PCI
+	default GENERIC_CPU || MCORE2 || MATOM || X86_GENERIC
 	help
 	  The Intel Management Engine (Intel ME) provides Manageability,
 	  Security and Media services for system containing Intel chipsets.
@@ -11,10 +12,11 @@ config INTEL_MEI
 	  For more information see
 	  <https://software.intel.com/en-us/manageability/>
 
+if INTEL_MEI
+
 config INTEL_MEI_ME
 	tristate "ME Enabled Intel Chipsets"
-	select INTEL_MEI
-	depends on X86 && PCI
+	default y
 	help
 	  MEI support for ME Enabled Intel chipsets.
 
@@ -38,8 +40,6 @@ config INTEL_MEI_ME
 
 config INTEL_MEI_TXE
 	tristate "Intel Trusted Execution Environment with ME Interface"
-	select INTEL_MEI
-	depends on X86 && PCI
 	help
 	  MEI Support for Trusted Execution Environment device on Intel SoCs
 
@@ -48,9 +48,7 @@ config INTEL_MEI_TXE
 
 config INTEL_MEI_GSC
 	tristate "Intel MEI GSC embedded device"
-	depends on INTEL_MEI
 	depends on INTEL_MEI_ME
-	depends on X86 && PCI
 	depends on DRM_I915
 	help
 	  Intel auxiliary driver for GSC devices embedded in Intel graphics devices.
@@ -60,6 +58,31 @@ config INTEL_MEI_GSC
 	  tasks such as graphics card firmware update and security
 	  tasks.
 
+config INTEL_MEI_VSC_HW
+	tristate "Intel visual sensing controller device transport driver"
+	depends on ACPI && SPI
+	depends on GPIOLIB || COMPILE_TEST
+	help
+	  Intel SPI transport driver between host and Intel visual sensing
+	  controller (IVSC) device.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called mei-vsc-hw.
+
+config INTEL_MEI_VSC
+	tristate "Intel visual sensing controller device with ME interface"
+	depends on INTEL_MEI_VSC_HW
+	help
+	  Intel MEI over SPI driver for Intel visual sensing controller
+	  (IVSC) device embedded in IA platform. It supports camera sharing
+	  between IVSC for context sensing and IPU for typical media usage.
+	  Select this config should enable transport layer for IVSC device.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called mei-vsc.
+
 source "drivers/misc/mei/hdcp/Kconfig"
 source "drivers/misc/mei/pxp/Kconfig"
 source "drivers/misc/mei/gsc_proxy/Kconfig"
+
+endif
diff --git a/drivers/misc/mei/Makefile b/drivers/misc/mei/Makefile
index 14aee253ae48..6f9fdbf1a495 100644
--- a/drivers/misc/mei/Makefile
+++ b/drivers/misc/mei/Makefile
@@ -31,3 +31,10 @@ CFLAGS_mei-trace.o = -I$(src)
 obj-$(CONFIG_INTEL_MEI_HDCP) += hdcp/
 obj-$(CONFIG_INTEL_MEI_PXP) += pxp/
 obj-$(CONFIG_INTEL_MEI_GSC_PROXY) += gsc_proxy/
+
+obj-$(CONFIG_INTEL_MEI_VSC_HW) += mei-vsc-hw.o
+mei-vsc-hw-y := vsc-tp.o
+mei-vsc-hw-y += vsc-fw-loader.o
+
+obj-$(CONFIG_INTEL_MEI_VSC) += mei-vsc.o
+mei-vsc-y := platform-vsc.o
diff --git a/drivers/misc/mei/gsc_proxy/Kconfig b/drivers/misc/mei/gsc_proxy/Kconfig
index 5f68d9f3d691..ac78b9d1eccd 100644
--- a/drivers/misc/mei/gsc_proxy/Kconfig
+++ b/drivers/misc/mei/gsc_proxy/Kconfig
@@ -3,7 +3,7 @@
 #
 config INTEL_MEI_GSC_PROXY
 	tristate "Intel GSC Proxy services of ME Interface"
-	select INTEL_MEI_ME
+	depends on INTEL_MEI_ME
 	depends on DRM_I915
 	help
          MEI Support for GSC Proxy Services on Intel platforms.
diff --git a/drivers/misc/mei/gsc_proxy/mei_gsc_proxy.c b/drivers/misc/mei/gsc_proxy/mei_gsc_proxy.c
index be52b113aea9..89364bdbb129 100644
--- a/drivers/misc/mei/gsc_proxy/mei_gsc_proxy.c
+++ b/drivers/misc/mei/gsc_proxy/mei_gsc_proxy.c
@@ -96,7 +96,8 @@ static const struct component_master_ops mei_component_master_ops = {
  *
  *    The function checks if the device is pci device and
  *    Intel VGA adapter, the subcomponent is SW Proxy
- *    and the parent of MEI PCI and the parent of VGA are the same PCH device.
+ *    and the VGA is on the bus 0 reserved for built-in devices
+ *    to reject discrete GFX.
  *
  * @dev: master device
  * @subcomponent: subcomponent to match (I915_COMPONENT_SWPROXY)
@@ -123,7 +124,8 @@ static int mei_gsc_proxy_component_match(struct device *dev, int subcomponent,
 	if (subcomponent != I915_COMPONENT_GSC_PROXY)
 		return 0;
 
-	return component_compare_dev(dev->parent, ((struct device *)data)->parent);
+	/* Only built-in GFX */
+	return (pdev->bus->number == 0);
 }
 
 static int mei_gsc_proxy_probe(struct mei_cl_device *cldev,
@@ -146,7 +148,7 @@ static int mei_gsc_proxy_probe(struct mei_cl_device *cldev,
 	}
 
 	component_match_add_typed(&cldev->dev, &master_match,
-				  mei_gsc_proxy_component_match, cldev->dev.parent);
+				  mei_gsc_proxy_component_match, NULL);
 	if (IS_ERR_OR_NULL(master_match)) {
 		ret = -ENOMEM;
 		goto err_exit;
diff --git a/drivers/misc/mei/hdcp/Kconfig b/drivers/misc/mei/hdcp/Kconfig
index 54e1c9526909..9be312ec798d 100644
--- a/drivers/misc/mei/hdcp/Kconfig
+++ b/drivers/misc/mei/hdcp/Kconfig
@@ -3,7 +3,7 @@
 #
 config INTEL_MEI_HDCP
 	tristate "Intel HDCP2.2 services of ME Interface"
-	select INTEL_MEI_ME
+	depends on INTEL_MEI_ME
 	depends on DRM_I915
 	help
 	  MEI Support for HDCP2.2 Services on Intel platforms.
diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h
index 961e5d53a27a..aac36750d2c5 100644
--- a/drivers/misc/mei/hw-me-regs.h
+++ b/drivers/misc/mei/hw-me-regs.h
@@ -112,6 +112,8 @@
 #define MEI_DEV_ID_RPL_S      0x7A68  /* Raptor Lake Point S */
 
 #define MEI_DEV_ID_MTL_M      0x7E70  /* Meteor Lake Point M */
+#define MEI_DEV_ID_ARL_S      0x7F68  /* Arrow Lake Point S */
+#define MEI_DEV_ID_ARL_H      0x7770  /* Arrow Lake Point H */
 
 /*
  * MEI HW Section
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index 676d566f38dd..8cf636c54032 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -119,6 +119,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = {
 	{MEI_PCI_DEVICE(MEI_DEV_ID_RPL_S, MEI_ME_PCH15_CFG)},
 
 	{MEI_PCI_DEVICE(MEI_DEV_ID_MTL_M, MEI_ME_PCH15_CFG)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_ARL_S, MEI_ME_PCH15_CFG)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_ARL_H, MEI_ME_PCH15_CFG)},
 
 	/* required last entry */
 	{0, }
diff --git a/drivers/misc/mei/platform-vsc.c b/drivers/misc/mei/platform-vsc.c
new file mode 100644
index 000000000000..8d303c6c0000
--- /dev/null
+++ b/drivers/misc/mei/platform-vsc.c
@@ -0,0 +1,450 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, Intel Corporation.
+ * Intel Visual Sensing Controller Interface Linux driver
+ */
+
+#include <linux/align.h>
+#include <linux/cache.h>
+#include <linux/cleanup.h>
+#include <linux/iopoll.h>
+#include <linux/list.h>
+#include <linux/mei.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/overflow.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/timekeeping.h>
+#include <linux/types.h>
+
+#include <asm-generic/bug.h>
+#include <asm-generic/unaligned.h>
+
+#include "mei_dev.h"
+#include "vsc-tp.h"
+
+#define MEI_VSC_DRV_NAME		"intel_vsc"
+
+#define MEI_VSC_MAX_MSG_SIZE		512
+
+#define MEI_VSC_POLL_DELAY_US		(50 * USEC_PER_MSEC)
+#define MEI_VSC_POLL_TIMEOUT_US		(200 * USEC_PER_MSEC)
+
+#define mei_dev_to_vsc_hw(dev)		((struct mei_vsc_hw *)((dev)->hw))
+
+struct mei_vsc_host_timestamp {
+	u64 realtime;
+	u64 boottime;
+};
+
+struct mei_vsc_hw {
+	struct vsc_tp *tp;
+
+	bool fw_ready;
+	bool host_ready;
+
+	atomic_t write_lock_cnt;
+
+	u32 rx_len;
+	u32 rx_hdr;
+
+	/* buffer for tx */
+	char tx_buf[MEI_VSC_MAX_MSG_SIZE + sizeof(struct mei_msg_hdr)] ____cacheline_aligned;
+	/* buffer for rx */
+	char rx_buf[MEI_VSC_MAX_MSG_SIZE + sizeof(struct mei_msg_hdr)] ____cacheline_aligned;
+};
+
+static int mei_vsc_read_helper(struct mei_vsc_hw *hw, u8 *buf,
+			       u32 max_len)
+{
+	struct mei_vsc_host_timestamp ts = {
+		.realtime = ktime_to_ns(ktime_get_real()),
+		.boottime = ktime_to_ns(ktime_get_boottime()),
+	};
+
+	return vsc_tp_xfer(hw->tp, VSC_TP_CMD_READ, &ts, sizeof(ts),
+			   buf, max_len);
+}
+
+static int mei_vsc_write_helper(struct mei_vsc_hw *hw, u8 *buf, u32 len)
+{
+	u8 status;
+
+	return vsc_tp_xfer(hw->tp, VSC_TP_CMD_WRITE, buf, len, &status,
+			   sizeof(status));
+}
+
+static int mei_vsc_fw_status(struct mei_device *mei_dev,
+			     struct mei_fw_status *fw_status)
+{
+	if (!fw_status)
+		return -EINVAL;
+
+	fw_status->count = 0;
+
+	return 0;
+}
+
+static inline enum mei_pg_state mei_vsc_pg_state(struct mei_device *mei_dev)
+{
+	return MEI_PG_OFF;
+}
+
+static void mei_vsc_intr_enable(struct mei_device *mei_dev)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+
+	vsc_tp_intr_enable(hw->tp);
+}
+
+static void mei_vsc_intr_disable(struct mei_device *mei_dev)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+
+	vsc_tp_intr_disable(hw->tp);
+}
+
+/* mei framework requires this ops */
+static void mei_vsc_intr_clear(struct mei_device *mei_dev)
+{
+}
+
+/* wait for pending irq handler */
+static void mei_vsc_synchronize_irq(struct mei_device *mei_dev)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+
+	vsc_tp_intr_synchronize(hw->tp);
+}
+
+static int mei_vsc_hw_config(struct mei_device *mei_dev)
+{
+	return 0;
+}
+
+static bool mei_vsc_host_is_ready(struct mei_device *mei_dev)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+
+	return hw->host_ready;
+}
+
+static bool mei_vsc_hw_is_ready(struct mei_device *mei_dev)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+
+	return hw->fw_ready;
+}
+
+static int mei_vsc_hw_start(struct mei_device *mei_dev)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+	int ret, rlen;
+	u8 buf;
+
+	hw->host_ready = true;
+
+	vsc_tp_intr_enable(hw->tp);
+
+	ret = read_poll_timeout(mei_vsc_read_helper, rlen,
+				rlen >= 0, MEI_VSC_POLL_DELAY_US,
+				MEI_VSC_POLL_TIMEOUT_US, true,
+				hw, &buf, sizeof(buf));
+	if (ret) {
+		dev_err(mei_dev->dev, "wait fw ready failed: %d\n", ret);
+		return ret;
+	}
+
+	hw->fw_ready = true;
+
+	return 0;
+}
+
+static bool mei_vsc_hbuf_is_ready(struct mei_device *mei_dev)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+
+	return atomic_read(&hw->write_lock_cnt) == 0;
+}
+
+static int mei_vsc_hbuf_empty_slots(struct mei_device *mei_dev)
+{
+	return MEI_VSC_MAX_MSG_SIZE / MEI_SLOT_SIZE;
+}
+
+static u32 mei_vsc_hbuf_depth(const struct mei_device *mei_dev)
+{
+	return MEI_VSC_MAX_MSG_SIZE / MEI_SLOT_SIZE;
+}
+
+static int mei_vsc_write(struct mei_device *mei_dev,
+			 const void *hdr, size_t hdr_len,
+			 const void *data, size_t data_len)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+	char *buf = hw->tx_buf;
+	int ret;
+
+	if (WARN_ON(!hdr || !IS_ALIGNED(hdr_len, 4)))
+		return -EINVAL;
+
+	if (!data || data_len > MEI_VSC_MAX_MSG_SIZE)
+		return -EINVAL;
+
+	atomic_inc(&hw->write_lock_cnt);
+
+	memcpy(buf, hdr, hdr_len);
+	memcpy(buf + hdr_len, data, data_len);
+
+	ret = mei_vsc_write_helper(hw, buf, hdr_len + data_len);
+
+	atomic_dec_if_positive(&hw->write_lock_cnt);
+
+	return ret < 0 ? ret : 0;
+}
+
+static inline u32 mei_vsc_read(const struct mei_device *mei_dev)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+	int ret;
+
+	ret = mei_vsc_read_helper(hw, hw->rx_buf, sizeof(hw->rx_buf));
+	if (ret < 0 || ret < sizeof(u32))
+		return 0;
+	hw->rx_len = ret;
+
+	hw->rx_hdr = get_unaligned_le32(hw->rx_buf);
+
+	return hw->rx_hdr;
+}
+
+static int mei_vsc_count_full_read_slots(struct mei_device *mei_dev)
+{
+	return MEI_VSC_MAX_MSG_SIZE / MEI_SLOT_SIZE;
+}
+
+static int mei_vsc_read_slots(struct mei_device *mei_dev, unsigned char *buf,
+			      unsigned long len)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+	struct mei_msg_hdr *hdr;
+
+	hdr = (struct mei_msg_hdr *)&hw->rx_hdr;
+	if (len != hdr->length || hdr->length + sizeof(*hdr) != hw->rx_len)
+		return -EINVAL;
+
+	memcpy(buf, hw->rx_buf + sizeof(*hdr), len);
+
+	return 0;
+}
+
+static bool mei_vsc_pg_in_transition(struct mei_device *mei_dev)
+{
+	return mei_dev->pg_event >= MEI_PG_EVENT_WAIT &&
+	       mei_dev->pg_event <= MEI_PG_EVENT_INTR_WAIT;
+}
+
+static bool mei_vsc_pg_is_enabled(struct mei_device *mei_dev)
+{
+	return false;
+}
+
+static int mei_vsc_hw_reset(struct mei_device *mei_dev, bool intr_enable)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+
+	vsc_tp_reset(hw->tp);
+
+	vsc_tp_intr_disable(hw->tp);
+
+	return vsc_tp_init(hw->tp, mei_dev->dev);
+}
+
+static const struct mei_hw_ops mei_vsc_hw_ops = {
+	.fw_status = mei_vsc_fw_status,
+	.pg_state = mei_vsc_pg_state,
+
+	.host_is_ready = mei_vsc_host_is_ready,
+	.hw_is_ready = mei_vsc_hw_is_ready,
+	.hw_reset = mei_vsc_hw_reset,
+	.hw_config = mei_vsc_hw_config,
+	.hw_start = mei_vsc_hw_start,
+
+	.pg_in_transition = mei_vsc_pg_in_transition,
+	.pg_is_enabled = mei_vsc_pg_is_enabled,
+
+	.intr_clear = mei_vsc_intr_clear,
+	.intr_enable = mei_vsc_intr_enable,
+	.intr_disable = mei_vsc_intr_disable,
+	.synchronize_irq = mei_vsc_synchronize_irq,
+
+	.hbuf_free_slots = mei_vsc_hbuf_empty_slots,
+	.hbuf_is_ready = mei_vsc_hbuf_is_ready,
+	.hbuf_depth = mei_vsc_hbuf_depth,
+	.write = mei_vsc_write,
+
+	.rdbuf_full_slots = mei_vsc_count_full_read_slots,
+	.read_hdr = mei_vsc_read,
+	.read = mei_vsc_read_slots,
+};
+
+static void mei_vsc_event_cb(void *context)
+{
+	struct mei_device *mei_dev = context;
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+	struct list_head cmpl_list;
+	s32 slots;
+	int ret;
+
+	if (mei_dev->dev_state == MEI_DEV_RESETTING ||
+	    mei_dev->dev_state == MEI_DEV_INITIALIZING)
+		return;
+
+	INIT_LIST_HEAD(&cmpl_list);
+
+	guard(mutex)(&mei_dev->device_lock);
+
+	while (vsc_tp_need_read(hw->tp)) {
+		/* check slots available for reading */
+		slots = mei_count_full_read_slots(mei_dev);
+
+		ret = mei_irq_read_handler(mei_dev, &cmpl_list, &slots);
+		if (ret) {
+			if (ret != -ENODATA) {
+				if (mei_dev->dev_state != MEI_DEV_RESETTING &&
+				    mei_dev->dev_state != MEI_DEV_POWER_DOWN)
+					schedule_work(&mei_dev->reset_work);
+			}
+
+			return;
+		}
+	}
+
+	mei_dev->hbuf_is_ready = mei_hbuf_is_ready(mei_dev);
+	ret = mei_irq_write_handler(mei_dev, &cmpl_list);
+	if (ret)
+		dev_err(mei_dev->dev, "dispatch write request failed: %d\n", ret);
+
+	mei_dev->hbuf_is_ready = mei_hbuf_is_ready(mei_dev);
+	mei_irq_compl_handler(mei_dev, &cmpl_list);
+}
+
+static int mei_vsc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct mei_device *mei_dev;
+	struct mei_vsc_hw *hw;
+	struct vsc_tp *tp;
+	int ret;
+
+	tp = *(struct vsc_tp **)dev_get_platdata(dev);
+	if (!tp)
+		return dev_err_probe(dev, -ENODEV, "no platform data\n");
+
+	mei_dev = devm_kzalloc(dev, size_add(sizeof(*mei_dev), sizeof(*hw)),
+			       GFP_KERNEL);
+	if (!mei_dev)
+		return -ENOMEM;
+
+	mei_device_init(mei_dev, dev, false, &mei_vsc_hw_ops);
+	mei_dev->fw_f_fw_ver_supported = 0;
+	mei_dev->kind = "ivsc";
+
+	hw = mei_dev_to_vsc_hw(mei_dev);
+	atomic_set(&hw->write_lock_cnt, 0);
+	hw->tp = tp;
+
+	platform_set_drvdata(pdev, mei_dev);
+
+	vsc_tp_register_event_cb(tp, mei_vsc_event_cb, mei_dev);
+
+	ret = mei_start(mei_dev);
+	if (ret) {
+		dev_err_probe(dev, ret, "init hw failed\n");
+		goto err_cancel;
+	}
+
+	ret = mei_register(mei_dev, dev);
+	if (ret)
+		goto err_stop;
+
+	pm_runtime_enable(mei_dev->dev);
+
+	return 0;
+
+err_stop:
+	mei_stop(mei_dev);
+
+err_cancel:
+	mei_cancel_work(mei_dev);
+
+	mei_disable_interrupts(mei_dev);
+
+	return ret;
+}
+
+static int mei_vsc_remove(struct platform_device *pdev)
+{
+	struct mei_device *mei_dev = platform_get_drvdata(pdev);
+
+	pm_runtime_disable(mei_dev->dev);
+
+	mei_stop(mei_dev);
+
+	mei_disable_interrupts(mei_dev);
+
+	mei_deregister(mei_dev);
+
+	return 0;
+}
+
+static int mei_vsc_suspend(struct device *dev)
+{
+	struct mei_device *mei_dev = dev_get_drvdata(dev);
+
+	mei_stop(mei_dev);
+
+	return 0;
+}
+
+static int mei_vsc_resume(struct device *dev)
+{
+	struct mei_device *mei_dev = dev_get_drvdata(dev);
+	int ret;
+
+	ret = mei_restart(mei_dev);
+	if (ret)
+		return ret;
+
+	/* start timer if stopped in suspend */
+	schedule_delayed_work(&mei_dev->timer_work, HZ);
+
+	return 0;
+}
+
+static DEFINE_SIMPLE_DEV_PM_OPS(mei_vsc_pm_ops, mei_vsc_suspend, mei_vsc_resume);
+
+static const struct platform_device_id mei_vsc_id_table[] = {
+	{ MEI_VSC_DRV_NAME },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(platform, mei_vsc_id_table);
+
+static struct platform_driver mei_vsc_drv = {
+	.probe = mei_vsc_probe,
+	.remove = mei_vsc_remove,
+	.id_table = mei_vsc_id_table,
+	.driver = {
+		.name = MEI_VSC_DRV_NAME,
+		.pm = &mei_vsc_pm_ops,
+		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
+	},
+};
+module_platform_driver(mei_vsc_drv);
+
+MODULE_AUTHOR("Wentong Wu <wentong.wu@intel.com>");
+MODULE_AUTHOR("Zhifeng Wang <zhifeng.wang@intel.com>");
+MODULE_DESCRIPTION("Intel Visual Sensing Controller Interface");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(VSC_TP);
diff --git a/drivers/misc/mei/pxp/Kconfig b/drivers/misc/mei/pxp/Kconfig
index 4029b96afc04..e9219b61cd92 100644
--- a/drivers/misc/mei/pxp/Kconfig
+++ b/drivers/misc/mei/pxp/Kconfig
@@ -1,10 +1,9 @@
-
 # SPDX-License-Identifier: GPL-2.0
 # Copyright (c) 2020, Intel Corporation. All rights reserved.
 #
 config INTEL_MEI_PXP
 	tristate "Intel PXP services of ME Interface"
-	select INTEL_MEI_ME
+	depends on INTEL_MEI_ME
 	depends on DRM_I915
 	help
 	  MEI Support for PXP Services on Intel platforms.
diff --git a/drivers/misc/mei/vsc-fw-loader.c b/drivers/misc/mei/vsc-fw-loader.c
new file mode 100644
index 000000000000..ffa4ccd96a10
--- /dev/null
+++ b/drivers/misc/mei/vsc-fw-loader.c
@@ -0,0 +1,770 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, Intel Corporation.
+ * Intel Visual Sensing Controller Transport Layer Linux driver
+ */
+
+#include <linux/acpi.h>
+#include <linux/align.h>
+#include <linux/bitfield.h>
+#include <linux/bits.h>
+#include <linux/cleanup.h>
+#include <linux/firmware.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/string_helpers.h>
+#include <linux/types.h>
+
+#include <asm-generic/unaligned.h>
+
+#include "vsc-tp.h"
+
+#define VSC_MAGIC_NUM			0x49505343 /* IPSC */
+#define VSC_MAGIC_FW			0x49574653 /* IWFS */
+#define VSC_MAGIC_FILE			0x46564353 /* FVCS */
+
+#define VSC_ADDR_BASE			0xE0030000
+#define VSC_EFUSE_ADDR			(VSC_ADDR_BASE + 0x038)
+#define VSC_STRAP_ADDR			(VSC_ADDR_BASE + 0x100)
+
+#define VSC_MAINSTEPPING_VERSION_MASK	GENMASK(7, 4)
+#define VSC_MAINSTEPPING_VERSION_A	0
+
+#define VSC_SUBSTEPPING_VERSION_MASK	GENMASK(3, 0)
+#define VSC_SUBSTEPPING_VERSION_0	0
+#define VSC_SUBSTEPPING_VERSION_1	2
+
+#define VSC_BOOT_IMG_OPTION_MASK	GENMASK(15, 0)
+
+#define VSC_SKU_CFG_LOCATION		0x5001A000
+#define VSC_SKU_MAX_SIZE		4100u
+
+#define VSC_ACE_IMG_CNT			2
+#define VSC_CSI_IMG_CNT			4
+#define VSC_IMG_CNT_MAX			6
+
+#define VSC_ROM_PKG_SIZE		256u
+#define VSC_FW_PKG_SIZE			512u
+
+#define VSC_IMAGE_DIR			"intel/vsc/"
+
+#define VSC_CSI_IMAGE_NAME		VSC_IMAGE_DIR "ivsc_fw.bin"
+#define VSC_ACE_IMAGE_NAME_FMT		VSC_IMAGE_DIR "ivsc_pkg_%s_0.bin"
+#define VSC_CFG_IMAGE_NAME_FMT		VSC_IMAGE_DIR "ivsc_skucfg_%s_0_1.bin"
+
+#define VSC_IMAGE_PATH_MAX_LEN		64
+
+#define VSC_SENSOR_NAME_MAX_LEN		16
+
+/* command id */
+enum {
+	VSC_CMD_QUERY = 0,
+	VSC_CMD_DL_SET = 1,
+	VSC_CMD_DL_START = 2,
+	VSC_CMD_DL_CONT = 3,
+	VSC_CMD_DUMP_MEM = 4,
+	VSC_CMD_GET_CONT = 8,
+	VSC_CMD_CAM_BOOT = 10,
+};
+
+/* command ack token */
+enum {
+	VSC_TOKEN_BOOTLOADER_REQ = 1,
+	VSC_TOKEN_DUMP_RESP = 4,
+	VSC_TOKEN_ERROR = 7,
+};
+
+/* image type */
+enum {
+	VSC_IMG_BOOTLOADER_TYPE = 1,
+	VSC_IMG_CSI_EM7D_TYPE,
+	VSC_IMG_CSI_SEM_TYPE,
+	VSC_IMG_CSI_RUNTIME_TYPE,
+	VSC_IMG_ACE_VISION_TYPE,
+	VSC_IMG_ACE_CFG_TYPE,
+	VSC_IMG_SKU_CFG_TYPE,
+};
+
+/* image fragments */
+enum {
+	VSC_IMG_BOOTLOADER_FRAG,
+	VSC_IMG_CSI_SEM_FRAG,
+	VSC_IMG_CSI_RUNTIME_FRAG,
+	VSC_IMG_ACE_VISION_FRAG,
+	VSC_IMG_ACE_CFG_FRAG,
+	VSC_IMG_CSI_EM7D_FRAG,
+	VSC_IMG_SKU_CFG_FRAG,
+	VSC_IMG_FRAG_MAX
+};
+
+struct vsc_rom_cmd {
+	__le32 magic;
+	__u8 cmd_id;
+	union {
+		/* download start */
+		struct {
+			__u8 img_type;
+			__le16 option;
+			__le32 img_len;
+			__le32 img_loc;
+			__le32 crc;
+			DECLARE_FLEX_ARRAY(__u8, res);
+		} __packed dl_start;
+		/* download set */
+		struct {
+			__u8 option;
+			__le16 img_cnt;
+			DECLARE_FLEX_ARRAY(__le32, payload);
+		} __packed dl_set;
+		/* download continue */
+		struct {
+			__u8 end_flag;
+			__le16 len;
+			/* 8 is the offset of payload */
+			__u8 payload[VSC_ROM_PKG_SIZE - 8];
+		} __packed dl_cont;
+		/* dump memory */
+		struct {
+			__u8 res;
+			__le16 len;
+			__le32 addr;
+			DECLARE_FLEX_ARRAY(__u8, payload);
+		} __packed dump_mem;
+		/* 5 is the offset of padding */
+		__u8 padding[VSC_ROM_PKG_SIZE - 5];
+	} data;
+};
+
+struct vsc_rom_cmd_ack {
+	__le32 magic;
+	__u8 token;
+	__u8 type;
+	__u8 res[2];
+	__u8 payload[];
+};
+
+struct vsc_fw_cmd {
+	__le32 magic;
+	__u8 cmd_id;
+	union {
+		struct {
+			__le16 option;
+			__u8 img_type;
+			__le32 img_len;
+			__le32 img_loc;
+			__le32 crc;
+			DECLARE_FLEX_ARRAY(__u8, res);
+		} __packed dl_start;
+		struct {
+			__le16 option;
+			__u8 img_cnt;
+			DECLARE_FLEX_ARRAY(__le32, payload);
+		} __packed dl_set;
+		struct {
+			__le32 addr;
+			__u8 len;
+			DECLARE_FLEX_ARRAY(__u8, payload);
+		} __packed dump_mem;
+		struct {
+			__u8 resv[3];
+			__le32 crc;
+			DECLARE_FLEX_ARRAY(__u8, payload);
+		} __packed boot;
+		/* 5 is the offset of padding */
+		__u8 padding[VSC_FW_PKG_SIZE - 5];
+	} data;
+};
+
+struct vsc_img {
+	__le32 magic;
+	__le32 option;
+	__le32 image_count;
+	__le32 image_location[VSC_IMG_CNT_MAX];
+};
+
+struct vsc_fw_sign {
+	__le32 magic;
+	__le32 image_size;
+	__u8 image[];
+};
+
+struct vsc_image_code_data {
+	/* fragment index */
+	u8 frag_index;
+	/* image type */
+	u8 image_type;
+};
+
+struct vsc_img_frag {
+	u8 type;
+	u32 location;
+	const u8 *data;
+	u32 size;
+};
+
+/**
+ * struct vsc_fw_loader - represent vsc firmware loader
+ * @dev: device used to request fimware
+ * @tp: transport layer used with the firmware loader
+ * @csi: CSI image
+ * @ace: ACE image
+ * @cfg: config image
+ * @tx_buf: tx buffer
+ * @rx_buf: rx buffer
+ * @option: command option
+ * @count: total image count
+ * @sensor_name: camera sensor name
+ * @frags: image fragments
+ */
+struct vsc_fw_loader {
+	struct device *dev;
+	struct vsc_tp *tp;
+
+	const struct firmware *csi;
+	const struct firmware *ace;
+	const struct firmware *cfg;
+
+	void *tx_buf;
+	void *rx_buf;
+
+	u16 option;
+	u16 count;
+
+	char sensor_name[VSC_SENSOR_NAME_MAX_LEN];
+
+	struct vsc_img_frag frags[VSC_IMG_FRAG_MAX];
+};
+
+static inline u32 vsc_sum_crc(void *data, size_t size)
+{
+	u32 crc = 0;
+	size_t i;
+
+	for (i = 0; i < size; i++)
+		crc += *((u8 *)data + i);
+
+	return crc;
+}
+
+/* get sensor name to construct image name */
+static int vsc_get_sensor_name(struct vsc_fw_loader *fw_loader,
+			       struct device *dev)
+{
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER };
+	union acpi_object obj = {
+		.type = ACPI_TYPE_INTEGER,
+		.integer.value = 1,
+	};
+	struct acpi_object_list arg_list = {
+		.count = 1,
+		.pointer = &obj,
+	};
+	union acpi_object *ret_obj;
+	acpi_handle handle;
+	acpi_status status;
+	int ret = 0;
+
+	handle = ACPI_HANDLE(dev);
+	if (!handle)
+		return -EINVAL;
+
+	status = acpi_evaluate_object(handle, "SID", &arg_list, &buffer);
+	if (ACPI_FAILURE(status)) {
+		dev_err(dev, "can't evaluate SID method: %d\n", status);
+		return -ENODEV;
+	}
+
+	ret_obj = buffer.pointer;
+	if (!ret_obj) {
+		dev_err(dev, "can't locate ACPI buffer\n");
+		return -ENODEV;
+	}
+
+	if (ret_obj->type != ACPI_TYPE_STRING) {
+		dev_err(dev, "found non-string entry\n");
+		ret = -ENODEV;
+		goto out_free_buff;
+	}
+
+	/* string length excludes trailing NUL */
+	if (ret_obj->string.length >= sizeof(fw_loader->sensor_name)) {
+		dev_err(dev, "sensor name buffer too small\n");
+		ret = -EINVAL;
+		goto out_free_buff;
+	}
+
+	memcpy(fw_loader->sensor_name, ret_obj->string.pointer,
+	       ret_obj->string.length);
+
+	string_lower(fw_loader->sensor_name, fw_loader->sensor_name);
+
+out_free_buff:
+	ACPI_FREE(buffer.pointer);
+
+	return ret;
+}
+
+static int vsc_identify_silicon(struct vsc_fw_loader *fw_loader)
+{
+	struct vsc_rom_cmd_ack *ack = fw_loader->rx_buf;
+	struct vsc_rom_cmd *cmd = fw_loader->tx_buf;
+	u8 version, sub_version;
+	int ret;
+
+	/* identify stepping information */
+	cmd->magic = cpu_to_le32(VSC_MAGIC_NUM);
+	cmd->cmd_id = VSC_CMD_DUMP_MEM;
+	cmd->data.dump_mem.addr = cpu_to_le32(VSC_EFUSE_ADDR);
+	cmd->data.dump_mem.len = cpu_to_le16(sizeof(__le32));
+	ret = vsc_tp_rom_xfer(fw_loader->tp, cmd, ack, VSC_ROM_PKG_SIZE);
+	if (ret)
+		return ret;
+	if (ack->token == VSC_TOKEN_ERROR)
+		return -EINVAL;
+
+	cmd->magic = cpu_to_le32(VSC_MAGIC_NUM);
+	cmd->cmd_id = VSC_CMD_GET_CONT;
+	ret = vsc_tp_rom_xfer(fw_loader->tp, cmd, ack, VSC_ROM_PKG_SIZE);
+	if (ret)
+		return ret;
+	if (ack->token != VSC_TOKEN_DUMP_RESP)
+		return -EINVAL;
+
+	version = FIELD_GET(VSC_MAINSTEPPING_VERSION_MASK, ack->payload[0]);
+	sub_version = FIELD_GET(VSC_SUBSTEPPING_VERSION_MASK, ack->payload[0]);
+
+	if (version != VSC_MAINSTEPPING_VERSION_A)
+		return -EINVAL;
+
+	if (sub_version != VSC_SUBSTEPPING_VERSION_0 &&
+	    sub_version != VSC_SUBSTEPPING_VERSION_1)
+		return -EINVAL;
+
+	dev_info(fw_loader->dev, "silicon stepping version is %u:%u\n",
+		 version, sub_version);
+
+	/* identify strap information */
+	cmd->magic = cpu_to_le32(VSC_MAGIC_NUM);
+	cmd->cmd_id = VSC_CMD_DUMP_MEM;
+	cmd->data.dump_mem.addr = cpu_to_le32(VSC_STRAP_ADDR);
+	cmd->data.dump_mem.len = cpu_to_le16(sizeof(__le32));
+	ret = vsc_tp_rom_xfer(fw_loader->tp, cmd, ack, VSC_ROM_PKG_SIZE);
+	if (ret)
+		return ret;
+	if (ack->token == VSC_TOKEN_ERROR)
+		return -EINVAL;
+
+	cmd->magic = cpu_to_le32(VSC_MAGIC_NUM);
+	cmd->cmd_id = VSC_CMD_GET_CONT;
+	ret = vsc_tp_rom_xfer(fw_loader->tp, cmd, ack, VSC_ROM_PKG_SIZE);
+	if (ret)
+		return ret;
+	if (ack->token != VSC_TOKEN_DUMP_RESP)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int vsc_identify_csi_image(struct vsc_fw_loader *fw_loader)
+{
+	const struct firmware *image;
+	struct vsc_fw_sign *sign;
+	struct vsc_img *img;
+	unsigned int i;
+	int ret;
+
+	ret = request_firmware(&image, VSC_CSI_IMAGE_NAME, fw_loader->dev);
+	if (ret)
+		return ret;
+
+	img = (struct vsc_img *)image->data;
+	if (!img) {
+		ret = -ENOENT;
+		goto err_release_image;
+	}
+
+	if (le32_to_cpu(img->magic) != VSC_MAGIC_FILE) {
+		ret = -EINVAL;
+		goto err_release_image;
+	}
+
+	if (le32_to_cpu(img->image_count) != VSC_CSI_IMG_CNT) {
+		ret = -EINVAL;
+		goto err_release_image;
+	}
+	fw_loader->count += le32_to_cpu(img->image_count) - 1;
+
+	fw_loader->option =
+		FIELD_GET(VSC_BOOT_IMG_OPTION_MASK, le32_to_cpu(img->option));
+
+	sign = (struct vsc_fw_sign *)
+		(img->image_location + le32_to_cpu(img->image_count));
+
+	for (i = 0; i < VSC_CSI_IMG_CNT; i++) {
+		/* mapping from CSI image index to image code data */
+		static const struct vsc_image_code_data csi_image_map[] = {
+			{ VSC_IMG_BOOTLOADER_FRAG, VSC_IMG_BOOTLOADER_TYPE },
+			{ VSC_IMG_CSI_SEM_FRAG, VSC_IMG_CSI_SEM_TYPE },
+			{ VSC_IMG_CSI_RUNTIME_FRAG, VSC_IMG_CSI_RUNTIME_TYPE },
+			{ VSC_IMG_CSI_EM7D_FRAG, VSC_IMG_CSI_EM7D_TYPE },
+		};
+		struct vsc_img_frag *frag;
+
+		if ((u8 *)sign + sizeof(*sign) > image->data + image->size) {
+			ret = -EINVAL;
+			goto err_release_image;
+		}
+
+		if (le32_to_cpu(sign->magic) != VSC_MAGIC_FW) {
+			ret = -EINVAL;
+			goto err_release_image;
+		}
+
+		if (!le32_to_cpu(img->image_location[i])) {
+			ret = -EINVAL;
+			goto err_release_image;
+		}
+
+		frag = &fw_loader->frags[csi_image_map[i].frag_index];
+
+		frag->data = sign->image;
+		frag->size = le32_to_cpu(sign->image_size);
+		frag->location = le32_to_cpu(img->image_location[i]);
+		frag->type = csi_image_map[i].image_type;
+
+		sign = (struct vsc_fw_sign *)
+			(sign->image + le32_to_cpu(sign->image_size));
+	}
+
+	fw_loader->csi = image;
+
+	return 0;
+
+err_release_image:
+	release_firmware(image);
+
+	return ret;
+}
+
+static int vsc_identify_ace_image(struct vsc_fw_loader *fw_loader)
+{
+	char path[VSC_IMAGE_PATH_MAX_LEN];
+	const struct firmware *image;
+	struct vsc_fw_sign *sign;
+	struct vsc_img *img;
+	unsigned int i;
+	int ret;
+
+	snprintf(path, sizeof(path), VSC_ACE_IMAGE_NAME_FMT,
+		 fw_loader->sensor_name);
+
+	ret = request_firmware(&image, path, fw_loader->dev);
+	if (ret)
+		return ret;
+
+	img = (struct vsc_img *)image->data;
+	if (!img) {
+		ret = -ENOENT;
+		goto err_release_image;
+	}
+
+	if (le32_to_cpu(img->magic) != VSC_MAGIC_FILE) {
+		ret = -EINVAL;
+		goto err_release_image;
+	}
+
+	if (le32_to_cpu(img->image_count) != VSC_ACE_IMG_CNT) {
+		ret = -EINVAL;
+		goto err_release_image;
+	}
+	fw_loader->count += le32_to_cpu(img->image_count);
+
+	sign = (struct vsc_fw_sign *)
+		(img->image_location + le32_to_cpu(img->image_count));
+
+	for (i = 0; i < VSC_ACE_IMG_CNT; i++) {
+		/* mapping from ACE image index to image code data */
+		static const struct vsc_image_code_data ace_image_map[] = {
+			{ VSC_IMG_ACE_VISION_FRAG, VSC_IMG_ACE_VISION_TYPE },
+			{ VSC_IMG_ACE_CFG_FRAG, VSC_IMG_ACE_CFG_TYPE },
+		};
+		struct vsc_img_frag *frag, *last_frag;
+		u8 frag_index;
+
+		if ((u8 *)sign + sizeof(*sign) > image->data + image->size) {
+			ret = -EINVAL;
+			goto err_release_image;
+		}
+
+		if (le32_to_cpu(sign->magic) != VSC_MAGIC_FW) {
+			ret = -EINVAL;
+			goto err_release_image;
+		}
+
+		frag_index = ace_image_map[i].frag_index;
+		frag = &fw_loader->frags[frag_index];
+
+		frag->data = sign->image;
+		frag->size = le32_to_cpu(sign->image_size);
+		frag->location = le32_to_cpu(img->image_location[i]);
+		frag->type = ace_image_map[i].image_type;
+
+		if (!frag->location) {
+			last_frag = &fw_loader->frags[frag_index - 1];
+			frag->location =
+				ALIGN(last_frag->location + last_frag->size, SZ_4K);
+		}
+
+		sign = (struct vsc_fw_sign *)
+			(sign->image + le32_to_cpu(sign->image_size));
+	}
+
+	fw_loader->ace = image;
+
+	return 0;
+
+err_release_image:
+	release_firmware(image);
+
+	return ret;
+}
+
+static int vsc_identify_cfg_image(struct vsc_fw_loader *fw_loader)
+{
+	struct vsc_img_frag *frag = &fw_loader->frags[VSC_IMG_SKU_CFG_FRAG];
+	char path[VSC_IMAGE_PATH_MAX_LEN];
+	const struct firmware *image;
+	u32 size;
+	int ret;
+
+	snprintf(path, sizeof(path), VSC_CFG_IMAGE_NAME_FMT,
+		 fw_loader->sensor_name);
+
+	ret = request_firmware(&image, path, fw_loader->dev);
+	if (ret)
+		return ret;
+
+	/* identify image size */
+	if (image->size <= sizeof(u32) || image->size > VSC_SKU_MAX_SIZE) {
+		ret = -EINVAL;
+		goto err_release_image;
+	}
+
+	size = le32_to_cpu(*((__le32 *)image->data)) + sizeof(u32);
+	if (image->size != size) {
+		ret = -EINVAL;
+		goto err_release_image;
+	}
+
+	frag->data = image->data;
+	frag->size = image->size;
+	frag->type = VSC_IMG_SKU_CFG_TYPE;
+	frag->location = VSC_SKU_CFG_LOCATION;
+
+	fw_loader->cfg = image;
+
+	return 0;
+
+err_release_image:
+	release_firmware(image);
+
+	return ret;
+}
+
+static int vsc_download_bootloader(struct vsc_fw_loader *fw_loader)
+{
+	struct vsc_img_frag *frag = &fw_loader->frags[VSC_IMG_BOOTLOADER_FRAG];
+	struct vsc_rom_cmd_ack *ack = fw_loader->rx_buf;
+	struct vsc_rom_cmd *cmd = fw_loader->tx_buf;
+	u32 len, c_len;
+	size_t remain;
+	const u8 *p;
+	int ret;
+
+	cmd->magic = cpu_to_le32(VSC_MAGIC_NUM);
+	cmd->cmd_id = VSC_CMD_QUERY;
+	ret = vsc_tp_rom_xfer(fw_loader->tp, cmd, ack, VSC_ROM_PKG_SIZE);
+	if (ret)
+		return ret;
+	if (ack->token != VSC_TOKEN_DUMP_RESP &&
+	    ack->token != VSC_TOKEN_BOOTLOADER_REQ)
+		return -EINVAL;
+
+	cmd->magic = cpu_to_le32(VSC_MAGIC_NUM);
+	cmd->cmd_id = VSC_CMD_DL_START;
+	cmd->data.dl_start.option = cpu_to_le16(fw_loader->option);
+	cmd->data.dl_start.img_type = frag->type;
+	cmd->data.dl_start.img_len = cpu_to_le32(frag->size);
+	cmd->data.dl_start.img_loc = cpu_to_le32(frag->location);
+
+	c_len = offsetof(struct vsc_rom_cmd, data.dl_start.crc);
+	cmd->data.dl_start.crc = cpu_to_le32(vsc_sum_crc(cmd, c_len));
+
+	ret = vsc_tp_rom_xfer(fw_loader->tp, cmd, NULL, VSC_ROM_PKG_SIZE);
+	if (ret)
+		return ret;
+
+	p = frag->data;
+	remain = frag->size;
+
+	/* download image data */
+	while (remain > 0) {
+		len = min(remain, sizeof(cmd->data.dl_cont.payload));
+
+		cmd->magic = cpu_to_le32(VSC_MAGIC_NUM);
+		cmd->cmd_id = VSC_CMD_DL_CONT;
+		cmd->data.dl_cont.len = cpu_to_le16(len);
+		cmd->data.dl_cont.end_flag = remain == len;
+		memcpy(cmd->data.dl_cont.payload, p, len);
+
+		ret = vsc_tp_rom_xfer(fw_loader->tp, cmd, NULL, VSC_ROM_PKG_SIZE);
+		if (ret)
+			return ret;
+
+		p += len;
+		remain -= len;
+	}
+
+	return 0;
+}
+
+static int vsc_download_firmware(struct vsc_fw_loader *fw_loader)
+{
+	struct vsc_fw_cmd *cmd = fw_loader->tx_buf;
+	unsigned int i, index = 0;
+	u32 c_len;
+	int ret;
+
+	cmd->magic = cpu_to_le32(VSC_MAGIC_NUM);
+	cmd->cmd_id = VSC_CMD_DL_SET;
+	cmd->data.dl_set.img_cnt = cpu_to_le16(fw_loader->count);
+	put_unaligned_le16(fw_loader->option, &cmd->data.dl_set.option);
+
+	for (i = VSC_IMG_CSI_SEM_FRAG; i <= VSC_IMG_CSI_EM7D_FRAG; i++) {
+		struct vsc_img_frag *frag = &fw_loader->frags[i];
+
+		cmd->data.dl_set.payload[index++] = cpu_to_le32(frag->location);
+		cmd->data.dl_set.payload[index++] = cpu_to_le32(frag->size);
+	}
+
+	c_len = offsetof(struct vsc_fw_cmd, data.dl_set.payload[index]);
+	cmd->data.dl_set.payload[index] = cpu_to_le32(vsc_sum_crc(cmd, c_len));
+
+	ret = vsc_tp_rom_xfer(fw_loader->tp, cmd, NULL, VSC_FW_PKG_SIZE);
+	if (ret)
+		return ret;
+
+	for (i = VSC_IMG_CSI_SEM_FRAG; i < VSC_IMG_FRAG_MAX; i++) {
+		struct vsc_img_frag *frag = &fw_loader->frags[i];
+		const u8 *p;
+		u32 remain;
+
+		cmd->magic = cpu_to_le32(VSC_MAGIC_NUM);
+		cmd->cmd_id = VSC_CMD_DL_START;
+		cmd->data.dl_start.img_type = frag->type;
+		cmd->data.dl_start.img_len = cpu_to_le32(frag->size);
+		cmd->data.dl_start.img_loc = cpu_to_le32(frag->location);
+		put_unaligned_le16(fw_loader->option, &cmd->data.dl_start.option);
+
+		c_len = offsetof(struct vsc_fw_cmd, data.dl_start.crc);
+		cmd->data.dl_start.crc = cpu_to_le32(vsc_sum_crc(cmd, c_len));
+
+		ret = vsc_tp_rom_xfer(fw_loader->tp, cmd, NULL, VSC_FW_PKG_SIZE);
+		if (ret)
+			return ret;
+
+		p = frag->data;
+		remain = frag->size;
+
+		/* download image data */
+		while (remain > 0) {
+			u32 len = min(remain, VSC_FW_PKG_SIZE);
+
+			memcpy(fw_loader->tx_buf, p, len);
+			memset(fw_loader->tx_buf + len, 0, VSC_FW_PKG_SIZE - len);
+
+			ret = vsc_tp_rom_xfer(fw_loader->tp, fw_loader->tx_buf,
+					      NULL, VSC_FW_PKG_SIZE);
+			if (ret)
+				break;
+
+			p += len;
+			remain -= len;
+		}
+	}
+
+	cmd->magic = cpu_to_le32(VSC_MAGIC_NUM);
+	cmd->cmd_id = VSC_CMD_CAM_BOOT;
+
+	c_len = offsetof(struct vsc_fw_cmd, data.dl_start.crc);
+	cmd->data.boot.crc = cpu_to_le32(vsc_sum_crc(cmd, c_len));
+
+	return vsc_tp_rom_xfer(fw_loader->tp, cmd, NULL, VSC_FW_PKG_SIZE);
+}
+
+/**
+ * vsc_tp_init - init vsc_tp
+ * @tp: vsc_tp device handle
+ * @dev: device node for mei vsc device
+ * Return: 0 in case of success, negative value in case of error
+ */
+int vsc_tp_init(struct vsc_tp *tp, struct device *dev)
+{
+	struct vsc_fw_loader *fw_loader __free(kfree) = NULL;
+	void *tx_buf __free(kfree) = NULL;
+	void *rx_buf __free(kfree) = NULL;
+	int ret;
+
+	fw_loader = kzalloc(sizeof(*fw_loader), GFP_KERNEL);
+	if (!fw_loader)
+		return -ENOMEM;
+
+	tx_buf = kzalloc(VSC_FW_PKG_SIZE, GFP_KERNEL);
+	if (!tx_buf)
+		return -ENOMEM;
+
+	rx_buf = kzalloc(VSC_FW_PKG_SIZE, GFP_KERNEL);
+	if (!rx_buf)
+		return -ENOMEM;
+
+	fw_loader->tx_buf = tx_buf;
+	fw_loader->rx_buf = rx_buf;
+
+	fw_loader->tp = tp;
+	fw_loader->dev = dev;
+
+	ret = vsc_get_sensor_name(fw_loader, dev);
+	if (ret)
+		return ret;
+
+	ret = vsc_identify_silicon(fw_loader);
+	if (ret)
+		return ret;
+
+	ret = vsc_identify_csi_image(fw_loader);
+	if (ret)
+		return ret;
+
+	ret = vsc_identify_ace_image(fw_loader);
+	if (ret)
+		goto err_release_csi;
+
+	ret = vsc_identify_cfg_image(fw_loader);
+	if (ret)
+		goto err_release_ace;
+
+	ret = vsc_download_bootloader(fw_loader);
+	if (!ret)
+		ret = vsc_download_firmware(fw_loader);
+
+	release_firmware(fw_loader->cfg);
+
+err_release_ace:
+	release_firmware(fw_loader->ace);
+
+err_release_csi:
+	release_firmware(fw_loader->csi);
+
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(vsc_tp_init, VSC_TP);
diff --git a/drivers/misc/mei/vsc-tp.c b/drivers/misc/mei/vsc-tp.c
new file mode 100644
index 000000000000..55f7db490d3b
--- /dev/null
+++ b/drivers/misc/mei/vsc-tp.c
@@ -0,0 +1,556 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, Intel Corporation.
+ * Intel Visual Sensing Controller Transport Layer Linux driver
+ */
+
+#include <linux/acpi.h>
+#include <linux/cleanup.h>
+#include <linux/crc32.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+#include <linux/irq.h>
+#include <linux/irqreturn.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+#include <linux/types.h>
+
+#include "vsc-tp.h"
+
+#define VSC_TP_RESET_PIN_TOGGLE_INTERVAL_MS	20
+#define VSC_TP_ROM_BOOTUP_DELAY_MS		10
+#define VSC_TP_ROM_XFER_POLL_TIMEOUT_US		(500 * USEC_PER_MSEC)
+#define VSC_TP_ROM_XFER_POLL_DELAY_US		(20 * USEC_PER_MSEC)
+#define VSC_TP_WAIT_FW_ASSERTED_TIMEOUT		(2 * HZ)
+#define VSC_TP_MAX_XFER_COUNT			5
+
+#define VSC_TP_PACKET_SYNC			0x31
+#define VSC_TP_CRC_SIZE				sizeof(u32)
+#define VSC_TP_MAX_MSG_SIZE			2048
+/* SPI xfer timeout size */
+#define VSC_TP_XFER_TIMEOUT_BYTES		700
+#define VSC_TP_PACKET_PADDING_SIZE		1
+#define VSC_TP_PACKET_SIZE(pkt) \
+	(sizeof(struct vsc_tp_packet) + le16_to_cpu((pkt)->len) + VSC_TP_CRC_SIZE)
+#define VSC_TP_MAX_PACKET_SIZE \
+	(sizeof(struct vsc_tp_packet) + VSC_TP_MAX_MSG_SIZE + VSC_TP_CRC_SIZE)
+#define VSC_TP_MAX_XFER_SIZE \
+	(VSC_TP_MAX_PACKET_SIZE + VSC_TP_XFER_TIMEOUT_BYTES)
+#define VSC_TP_NEXT_XFER_LEN(len, offset) \
+	(len + sizeof(struct vsc_tp_packet) + VSC_TP_CRC_SIZE - offset + VSC_TP_PACKET_PADDING_SIZE)
+
+struct vsc_tp_packet {
+	__u8 sync;
+	__u8 cmd;
+	__le16 len;
+	__le32 seq;
+	__u8 buf[] __counted_by(len);
+};
+
+struct vsc_tp {
+	/* do the actual data transfer */
+	struct spi_device *spi;
+
+	/* bind with mei framework */
+	struct platform_device *pdev;
+
+	struct gpio_desc *wakeuphost;
+	struct gpio_desc *resetfw;
+	struct gpio_desc *wakeupfw;
+
+	/* command sequence number */
+	u32 seq;
+
+	/* command buffer */
+	void *tx_buf;
+	void *rx_buf;
+
+	atomic_t assert_cnt;
+	wait_queue_head_t xfer_wait;
+
+	vsc_tp_event_cb_t event_notify;
+	void *event_notify_context;
+
+	/* used to protect command download */
+	struct mutex mutex;
+};
+
+/* GPIO resources */
+static const struct acpi_gpio_params wakeuphost_gpio = { 0, 0, false };
+static const struct acpi_gpio_params wakeuphostint_gpio = { 1, 0, false };
+static const struct acpi_gpio_params resetfw_gpio = { 2, 0, false };
+static const struct acpi_gpio_params wakeupfw = { 3, 0, false };
+
+static const struct acpi_gpio_mapping vsc_tp_acpi_gpios[] = {
+	{ "wakeuphost-gpios", &wakeuphost_gpio, 1 },
+	{ "wakeuphostint-gpios", &wakeuphostint_gpio, 1 },
+	{ "resetfw-gpios", &resetfw_gpio, 1 },
+	{ "wakeupfw-gpios", &wakeupfw, 1 },
+	{}
+};
+
+/* wakeup firmware and wait for response */
+static int vsc_tp_wakeup_request(struct vsc_tp *tp)
+{
+	int ret;
+
+	gpiod_set_value_cansleep(tp->wakeupfw, 0);
+
+	ret = wait_event_timeout(tp->xfer_wait,
+				 atomic_read(&tp->assert_cnt) &&
+				 gpiod_get_value_cansleep(tp->wakeuphost),
+				 VSC_TP_WAIT_FW_ASSERTED_TIMEOUT);
+	if (!ret)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static void vsc_tp_wakeup_release(struct vsc_tp *tp)
+{
+	atomic_dec_if_positive(&tp->assert_cnt);
+
+	gpiod_set_value_cansleep(tp->wakeupfw, 1);
+}
+
+static int vsc_tp_dev_xfer(struct vsc_tp *tp, void *obuf, void *ibuf, size_t len)
+{
+	struct spi_message msg = { 0 };
+	struct spi_transfer xfer = {
+		.tx_buf = obuf,
+		.rx_buf = ibuf,
+		.len = len,
+	};
+
+	spi_message_init_with_transfers(&msg, &xfer, 1);
+
+	return spi_sync_locked(tp->spi, &msg);
+}
+
+static int vsc_tp_xfer_helper(struct vsc_tp *tp, struct vsc_tp_packet *pkt,
+			      void *ibuf, u16 ilen)
+{
+	int ret, offset = 0, cpy_len, src_len, dst_len = sizeof(struct vsc_tp_packet);
+	int next_xfer_len = VSC_TP_PACKET_SIZE(pkt) + VSC_TP_XFER_TIMEOUT_BYTES;
+	u8 *src, *crc_src, *rx_buf = tp->rx_buf;
+	int count_down = VSC_TP_MAX_XFER_COUNT;
+	u32 recv_crc = 0, crc = ~0;
+	struct vsc_tp_packet ack;
+	u8 *dst = (u8 *)&ack;
+	bool synced = false;
+
+	do {
+		ret = vsc_tp_dev_xfer(tp, pkt, rx_buf, next_xfer_len);
+		if (ret)
+			return ret;
+		memset(pkt, 0, VSC_TP_MAX_XFER_SIZE);
+
+		if (synced) {
+			src = rx_buf;
+			src_len = next_xfer_len;
+		} else {
+			src = memchr(rx_buf, VSC_TP_PACKET_SYNC, next_xfer_len);
+			if (!src)
+				continue;
+			synced = true;
+			src_len = next_xfer_len - (src - rx_buf);
+		}
+
+		/* traverse received data */
+		while (src_len > 0) {
+			cpy_len = min(src_len, dst_len);
+			memcpy(dst, src, cpy_len);
+			crc_src = src;
+			src += cpy_len;
+			src_len -= cpy_len;
+			dst += cpy_len;
+			dst_len -= cpy_len;
+
+			if (offset < sizeof(ack)) {
+				offset += cpy_len;
+				crc = crc32(crc, crc_src, cpy_len);
+
+				if (!src_len)
+					continue;
+
+				if (le16_to_cpu(ack.len)) {
+					dst = ibuf;
+					dst_len = min(ilen, le16_to_cpu(ack.len));
+				} else {
+					dst = (u8 *)&recv_crc;
+					dst_len = sizeof(recv_crc);
+				}
+			} else if (offset < sizeof(ack) + le16_to_cpu(ack.len)) {
+				offset += cpy_len;
+				crc = crc32(crc, crc_src, cpy_len);
+
+				if (src_len) {
+					int remain = sizeof(ack) + le16_to_cpu(ack.len) - offset;
+
+					cpy_len = min(src_len, remain);
+					offset += cpy_len;
+					crc = crc32(crc, src, cpy_len);
+					src += cpy_len;
+					src_len -= cpy_len;
+					if (src_len) {
+						dst = (u8 *)&recv_crc;
+						dst_len = sizeof(recv_crc);
+						continue;
+					}
+				}
+				next_xfer_len = VSC_TP_NEXT_XFER_LEN(le16_to_cpu(ack.len), offset);
+			} else if (offset < sizeof(ack) + le16_to_cpu(ack.len) + VSC_TP_CRC_SIZE) {
+				offset += cpy_len;
+
+				if (src_len) {
+					/* terminate the traverse */
+					next_xfer_len = 0;
+					break;
+				}
+				next_xfer_len = VSC_TP_NEXT_XFER_LEN(le16_to_cpu(ack.len), offset);
+			}
+		}
+	} while (next_xfer_len > 0 && --count_down);
+
+	if (next_xfer_len > 0)
+		return -EAGAIN;
+
+	if (~recv_crc != crc || le32_to_cpu(ack.seq) != tp->seq) {
+		dev_err(&tp->spi->dev, "recv crc or seq error\n");
+		return -EINVAL;
+	}
+
+	if (ack.cmd == VSC_TP_CMD_ACK || ack.cmd == VSC_TP_CMD_NACK ||
+	    ack.cmd == VSC_TP_CMD_BUSY) {
+		dev_err(&tp->spi->dev, "recv cmd ack error\n");
+		return -EAGAIN;
+	}
+
+	return min(le16_to_cpu(ack.len), ilen);
+}
+
+/**
+ * vsc_tp_xfer - transfer data to firmware
+ * @tp: vsc_tp device handle
+ * @cmd: the command to be sent to the device
+ * @obuf: the tx buffer to be sent to the device
+ * @olen: the length of tx buffer
+ * @ibuf: the rx buffer to receive from the device
+ * @ilen: the length of rx buffer
+ * Return: the length of received data in case of success,
+ *	otherwise negative value
+ */
+int vsc_tp_xfer(struct vsc_tp *tp, u8 cmd, const void *obuf, size_t olen,
+		void *ibuf, size_t ilen)
+{
+	struct vsc_tp_packet *pkt = tp->tx_buf;
+	u32 crc;
+	int ret;
+
+	if (!obuf || !ibuf || olen > VSC_TP_MAX_MSG_SIZE)
+		return -EINVAL;
+
+	guard(mutex)(&tp->mutex);
+
+	pkt->sync = VSC_TP_PACKET_SYNC;
+	pkt->cmd = cmd;
+	pkt->len = cpu_to_le16(olen);
+	pkt->seq = cpu_to_le32(++tp->seq);
+	memcpy(pkt->buf, obuf, olen);
+
+	crc = ~crc32(~0, (u8 *)pkt, sizeof(pkt) + olen);
+	memcpy(pkt->buf + olen, &crc, sizeof(crc));
+
+	ret = vsc_tp_wakeup_request(tp);
+	if (unlikely(ret))
+		dev_err(&tp->spi->dev, "wakeup firmware failed ret: %d\n", ret);
+	else
+		ret = vsc_tp_xfer_helper(tp, pkt, ibuf, ilen);
+
+	vsc_tp_wakeup_release(tp);
+
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(vsc_tp_xfer, VSC_TP);
+
+/**
+ * vsc_tp_rom_xfer - transfer data to rom code
+ * @tp: vsc_tp device handle
+ * @obuf: the data buffer to be sent to the device
+ * @ibuf: the buffer to receive data from the device
+ * @len: the length of tx buffer and rx buffer
+ * Return: 0 in case of success, negative value in case of error
+ */
+int vsc_tp_rom_xfer(struct vsc_tp *tp, const void *obuf, void *ibuf, size_t len)
+{
+	size_t words = len / sizeof(__be32);
+	int ret;
+
+	if (len % sizeof(__be32) || len > VSC_TP_MAX_MSG_SIZE)
+		return -EINVAL;
+
+	guard(mutex)(&tp->mutex);
+
+	/* rom xfer is big endian */
+	cpu_to_be32_array(tp->tx_buf, obuf, words);
+
+	ret = read_poll_timeout(gpiod_get_value_cansleep, ret,
+				!ret, VSC_TP_ROM_XFER_POLL_DELAY_US,
+				VSC_TP_ROM_XFER_POLL_TIMEOUT_US, false,
+				tp->wakeuphost);
+	if (ret) {
+		dev_err(&tp->spi->dev, "wait rom failed ret: %d\n", ret);
+		return ret;
+	}
+
+	ret = vsc_tp_dev_xfer(tp, tp->tx_buf, tp->rx_buf, len);
+	if (ret)
+		return ret;
+
+	if (ibuf)
+		cpu_to_be32_array(ibuf, tp->rx_buf, words);
+
+	return ret;
+}
+
+/**
+ * vsc_tp_reset - reset vsc transport layer
+ * @tp: vsc_tp device handle
+ */
+void vsc_tp_reset(struct vsc_tp *tp)
+{
+	disable_irq(tp->spi->irq);
+
+	/* toggle reset pin */
+	gpiod_set_value_cansleep(tp->resetfw, 0);
+	msleep(VSC_TP_RESET_PIN_TOGGLE_INTERVAL_MS);
+	gpiod_set_value_cansleep(tp->resetfw, 1);
+
+	/* wait for ROM */
+	msleep(VSC_TP_ROM_BOOTUP_DELAY_MS);
+
+	/*
+	 * Set default host wakeup pin to non-active
+	 * to avoid unexpected host irq interrupt.
+	 */
+	gpiod_set_value_cansleep(tp->wakeupfw, 1);
+
+	atomic_set(&tp->assert_cnt, 0);
+
+	enable_irq(tp->spi->irq);
+}
+EXPORT_SYMBOL_NS_GPL(vsc_tp_reset, VSC_TP);
+
+/**
+ * vsc_tp_need_read - check if device has data to sent
+ * @tp: vsc_tp device handle
+ * Return: true if device has data to sent, otherwise false
+ */
+bool vsc_tp_need_read(struct vsc_tp *tp)
+{
+	if (!atomic_read(&tp->assert_cnt))
+		return false;
+	if (!gpiod_get_value_cansleep(tp->wakeuphost))
+		return false;
+	if (!gpiod_get_value_cansleep(tp->wakeupfw))
+		return false;
+
+	return true;
+}
+EXPORT_SYMBOL_NS_GPL(vsc_tp_need_read, VSC_TP);
+
+/**
+ * vsc_tp_register_event_cb - register a callback function to receive event
+ * @tp: vsc_tp device handle
+ * @event_cb: callback function
+ * @context: execution context of event callback
+ * Return: 0 in case of success, negative value in case of error
+ */
+int vsc_tp_register_event_cb(struct vsc_tp *tp, vsc_tp_event_cb_t event_cb,
+			    void *context)
+{
+	tp->event_notify = event_cb;
+	tp->event_notify_context = context;
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(vsc_tp_register_event_cb, VSC_TP);
+
+/**
+ * vsc_tp_intr_synchronize - synchronize vsc_tp interrupt
+ * @tp: vsc_tp device handle
+ */
+void vsc_tp_intr_synchronize(struct vsc_tp *tp)
+{
+	synchronize_irq(tp->spi->irq);
+}
+EXPORT_SYMBOL_NS_GPL(vsc_tp_intr_synchronize, VSC_TP);
+
+/**
+ * vsc_tp_intr_enable - enable vsc_tp interrupt
+ * @tp: vsc_tp device handle
+ */
+void vsc_tp_intr_enable(struct vsc_tp *tp)
+{
+	enable_irq(tp->spi->irq);
+}
+EXPORT_SYMBOL_NS_GPL(vsc_tp_intr_enable, VSC_TP);
+
+/**
+ * vsc_tp_intr_disable - disable vsc_tp interrupt
+ * @tp: vsc_tp device handle
+ */
+void vsc_tp_intr_disable(struct vsc_tp *tp)
+{
+	disable_irq(tp->spi->irq);
+}
+EXPORT_SYMBOL_NS_GPL(vsc_tp_intr_disable, VSC_TP);
+
+static irqreturn_t vsc_tp_isr(int irq, void *data)
+{
+	struct vsc_tp *tp = data;
+
+	atomic_inc(&tp->assert_cnt);
+
+	wake_up(&tp->xfer_wait);
+
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t vsc_tp_thread_isr(int irq, void *data)
+{
+	struct vsc_tp *tp = data;
+
+	if (tp->event_notify)
+		tp->event_notify(tp->event_notify_context);
+
+	return IRQ_HANDLED;
+}
+
+static int vsc_tp_match_any(struct acpi_device *adev, void *data)
+{
+	struct acpi_device **__adev = data;
+
+	*__adev = adev;
+
+	return 1;
+}
+
+static int vsc_tp_probe(struct spi_device *spi)
+{
+	struct platform_device_info pinfo = { 0 };
+	struct device *dev = &spi->dev;
+	struct platform_device *pdev;
+	struct acpi_device *adev;
+	struct vsc_tp *tp;
+	int ret;
+
+	tp = devm_kzalloc(dev, sizeof(*tp), GFP_KERNEL);
+	if (!tp)
+		return -ENOMEM;
+
+	tp->tx_buf = devm_kzalloc(dev, VSC_TP_MAX_XFER_SIZE, GFP_KERNEL);
+	if (!tp->tx_buf)
+		return -ENOMEM;
+
+	tp->rx_buf = devm_kzalloc(dev, VSC_TP_MAX_XFER_SIZE, GFP_KERNEL);
+	if (!tp->rx_buf)
+		return -ENOMEM;
+
+	ret = devm_acpi_dev_add_driver_gpios(dev, vsc_tp_acpi_gpios);
+	if (ret)
+		return ret;
+
+	tp->wakeuphost = devm_gpiod_get(dev, "wakeuphost", GPIOD_IN);
+	if (IS_ERR(tp->wakeuphost))
+		return PTR_ERR(tp->wakeuphost);
+
+	tp->resetfw = devm_gpiod_get(dev, "resetfw", GPIOD_OUT_HIGH);
+	if (IS_ERR(tp->resetfw))
+		return PTR_ERR(tp->resetfw);
+
+	tp->wakeupfw = devm_gpiod_get(dev, "wakeupfw", GPIOD_OUT_HIGH);
+	if (IS_ERR(tp->wakeupfw))
+		return PTR_ERR(tp->wakeupfw);
+
+	atomic_set(&tp->assert_cnt, 0);
+	init_waitqueue_head(&tp->xfer_wait);
+	tp->spi = spi;
+
+	irq_set_status_flags(spi->irq, IRQ_DISABLE_UNLAZY);
+	ret = devm_request_threaded_irq(dev, spi->irq, vsc_tp_isr,
+					vsc_tp_thread_isr,
+					IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+					dev_name(dev), tp);
+	if (ret)
+		return ret;
+
+	mutex_init(&tp->mutex);
+
+	/* only one child acpi device */
+	ret = acpi_dev_for_each_child(ACPI_COMPANION(dev),
+				      vsc_tp_match_any, &adev);
+	if (!ret) {
+		ret = -ENODEV;
+		goto err_destroy_lock;
+	}
+	pinfo.fwnode = acpi_fwnode_handle(adev);
+
+	pinfo.name = "intel_vsc";
+	pinfo.data = &tp;
+	pinfo.size_data = sizeof(tp);
+	pinfo.id = PLATFORM_DEVID_NONE;
+
+	pdev = platform_device_register_full(&pinfo);
+	if (IS_ERR(pdev)) {
+		ret = PTR_ERR(pdev);
+		goto err_destroy_lock;
+	}
+
+	tp->pdev = pdev;
+	spi_set_drvdata(spi, tp);
+
+	return 0;
+
+err_destroy_lock:
+	mutex_destroy(&tp->mutex);
+
+	return ret;
+}
+
+static void vsc_tp_remove(struct spi_device *spi)
+{
+	struct vsc_tp *tp = spi_get_drvdata(spi);
+
+	platform_device_unregister(tp->pdev);
+
+	mutex_destroy(&tp->mutex);
+}
+
+static const struct acpi_device_id vsc_tp_acpi_ids[] = {
+	{ "INTC1009" }, /* Raptor Lake */
+	{ "INTC1058" }, /* Tiger Lake */
+	{ "INTC1094" }, /* Alder Lake */
+	{ "INTC10D0" }, /* Meteor Lake */
+	{}
+};
+MODULE_DEVICE_TABLE(acpi, vsc_tp_acpi_ids);
+
+static struct spi_driver vsc_tp_driver = {
+	.probe = vsc_tp_probe,
+	.remove = vsc_tp_remove,
+	.driver = {
+		.name = "vsc-tp",
+		.acpi_match_table = vsc_tp_acpi_ids,
+	},
+};
+module_spi_driver(vsc_tp_driver);
+
+MODULE_AUTHOR("Wentong Wu <wentong.wu@intel.com>");
+MODULE_AUTHOR("Zhifeng Wang <zhifeng.wang@intel.com>");
+MODULE_DESCRIPTION("Intel Visual Sensing Controller Transport Layer");
+MODULE_LICENSE("GPL");
diff --git a/drivers/misc/mei/vsc-tp.h b/drivers/misc/mei/vsc-tp.h
new file mode 100644
index 000000000000..f9513ddc3e40
--- /dev/null
+++ b/drivers/misc/mei/vsc-tp.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2023, Intel Corporation.
+ * Intel Visual Sensing Controller Transport Layer Linux driver
+ */
+
+#ifndef _VSC_TP_H_
+#define _VSC_TP_H_
+
+#include <linux/types.h>
+
+#define VSC_TP_CMD_WRITE	0x01
+#define VSC_TP_CMD_READ		0x02
+
+#define VSC_TP_CMD_ACK		0x10
+#define VSC_TP_CMD_NACK		0x11
+#define VSC_TP_CMD_BUSY		0x12
+
+struct vsc_tp;
+
+/**
+ * typedef vsc_event_cb_t - event callback function signature
+ * @context: the execution context of who registered this callback
+ *
+ * The callback function is called in interrupt context and the data
+ * payload is only valid during the call. If the user needs access
+ * the data payload later, it must copy the payload.
+ */
+typedef void (*vsc_tp_event_cb_t)(void *context);
+
+int vsc_tp_rom_xfer(struct vsc_tp *tp, const void *obuf, void *ibuf,
+		    size_t len);
+
+int vsc_tp_xfer(struct vsc_tp *tp, u8 cmd, const void *obuf, size_t olen,
+		void *ibuf, size_t ilen);
+
+int vsc_tp_register_event_cb(struct vsc_tp *tp, vsc_tp_event_cb_t event_cb,
+			     void *context);
+
+void vsc_tp_intr_enable(struct vsc_tp *tp);
+void vsc_tp_intr_disable(struct vsc_tp *tp);
+void vsc_tp_intr_synchronize(struct vsc_tp *tp);
+
+void vsc_tp_reset(struct vsc_tp *tp);
+
+bool vsc_tp_need_read(struct vsc_tp *tp);
+
+int vsc_tp_init(struct vsc_tp *tp, struct device *dev);
+
+#endif
diff --git a/drivers/misc/nsm.c b/drivers/misc/nsm.c
new file mode 100644
index 000000000000..0eaa3b4484bd
--- /dev/null
+++ b/drivers/misc/nsm.c
@@ -0,0 +1,506 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Amazon Nitro Secure Module driver.
+ *
+ * Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ *
+ * The Nitro Secure Module implements commands via CBOR over virtio.
+ * This driver exposes a raw message ioctls on /dev/nsm that user
+ * space can use to issue these commands.
+ */
+
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/interrupt.h>
+#include <linux/hw_random.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <linux/uio.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ids.h>
+#include <linux/virtio.h>
+#include <linux/wait.h>
+#include <uapi/linux/nsm.h>
+
+/* Timeout for NSM virtqueue respose in milliseconds. */
+#define NSM_DEFAULT_TIMEOUT_MSECS (120000) /* 2 minutes */
+
+/* Maximum length input data */
+struct nsm_data_req {
+	u32 len;
+	u8  data[NSM_REQUEST_MAX_SIZE];
+};
+
+/* Maximum length output data */
+struct nsm_data_resp {
+	u32 len;
+	u8  data[NSM_RESPONSE_MAX_SIZE];
+};
+
+/* Full NSM request/response message */
+struct nsm_msg {
+	struct nsm_data_req req;
+	struct nsm_data_resp resp;
+};
+
+struct nsm {
+	struct virtio_device *vdev;
+	struct virtqueue     *vq;
+	struct mutex          lock;
+	struct completion     cmd_done;
+	struct miscdevice     misc;
+	struct hwrng          hwrng;
+	struct work_struct    misc_init;
+	struct nsm_msg        msg;
+};
+
+/* NSM device ID */
+static const struct virtio_device_id id_table[] = {
+	{ VIRTIO_ID_NITRO_SEC_MOD, VIRTIO_DEV_ANY_ID },
+	{ 0 },
+};
+
+static struct nsm *file_to_nsm(struct file *file)
+{
+	return container_of(file->private_data, struct nsm, misc);
+}
+
+static struct nsm *hwrng_to_nsm(struct hwrng *rng)
+{
+	return container_of(rng, struct nsm, hwrng);
+}
+
+#define CBOR_TYPE_MASK  0xE0
+#define CBOR_TYPE_MAP 0xA0
+#define CBOR_TYPE_TEXT 0x60
+#define CBOR_TYPE_ARRAY 0x40
+#define CBOR_HEADER_SIZE_SHORT 1
+
+#define CBOR_SHORT_SIZE_MAX_VALUE 23
+#define CBOR_LONG_SIZE_U8  24
+#define CBOR_LONG_SIZE_U16 25
+#define CBOR_LONG_SIZE_U32 26
+#define CBOR_LONG_SIZE_U64 27
+
+static bool cbor_object_is_array(const u8 *cbor_object, size_t cbor_object_size)
+{
+	if (cbor_object_size == 0 || cbor_object == NULL)
+		return false;
+
+	return (cbor_object[0] & CBOR_TYPE_MASK) == CBOR_TYPE_ARRAY;
+}
+
+static int cbor_object_get_array(u8 *cbor_object, size_t cbor_object_size, u8 **cbor_array)
+{
+	u8 cbor_short_size;
+	void *array_len_p;
+	u64 array_len;
+	u64 array_offset;
+
+	if (!cbor_object_is_array(cbor_object, cbor_object_size))
+		return -EFAULT;
+
+	cbor_short_size = (cbor_object[0] & 0x1F);
+
+	/* Decoding byte array length */
+	array_offset = CBOR_HEADER_SIZE_SHORT;
+	if (cbor_short_size >= CBOR_LONG_SIZE_U8)
+		array_offset += BIT(cbor_short_size - CBOR_LONG_SIZE_U8);
+
+	if (cbor_object_size < array_offset)
+		return -EFAULT;
+
+	array_len_p = &cbor_object[1];
+
+	switch (cbor_short_size) {
+	case CBOR_SHORT_SIZE_MAX_VALUE: /* short encoding */
+		array_len = cbor_short_size;
+		break;
+	case CBOR_LONG_SIZE_U8:
+		array_len = *(u8 *)array_len_p;
+		break;
+	case CBOR_LONG_SIZE_U16:
+		array_len = be16_to_cpup((__be16 *)array_len_p);
+		break;
+	case CBOR_LONG_SIZE_U32:
+		array_len = be32_to_cpup((__be32 *)array_len_p);
+		break;
+	case CBOR_LONG_SIZE_U64:
+		array_len = be64_to_cpup((__be64 *)array_len_p);
+		break;
+	}
+
+	if (cbor_object_size < array_offset)
+		return -EFAULT;
+
+	if (cbor_object_size - array_offset < array_len)
+		return -EFAULT;
+
+	if (array_len > INT_MAX)
+		return -EFAULT;
+
+	*cbor_array = cbor_object + array_offset;
+	return array_len;
+}
+
+/* Copy the request of a raw message to kernel space */
+static int fill_req_raw(struct nsm *nsm, struct nsm_data_req *req,
+			struct nsm_raw *raw)
+{
+	/* Verify the user input size. */
+	if (raw->request.len > sizeof(req->data))
+		return -EMSGSIZE;
+
+	/* Copy the request payload */
+	if (copy_from_user(req->data, u64_to_user_ptr(raw->request.addr),
+			   raw->request.len))
+		return -EFAULT;
+
+	req->len = raw->request.len;
+
+	return 0;
+}
+
+/* Copy the response of a raw message back to user-space */
+static int parse_resp_raw(struct nsm *nsm, struct nsm_data_resp *resp,
+			  struct nsm_raw *raw)
+{
+	/* Truncate any message that does not fit. */
+	raw->response.len = min_t(u64, raw->response.len, resp->len);
+
+	/* Copy the response content to user space */
+	if (copy_to_user(u64_to_user_ptr(raw->response.addr),
+			 resp->data, raw->response.len))
+		return -EFAULT;
+
+	return 0;
+}
+
+/* Virtqueue interrupt handler */
+static void nsm_vq_callback(struct virtqueue *vq)
+{
+	struct nsm *nsm = vq->vdev->priv;
+
+	complete(&nsm->cmd_done);
+}
+
+/* Forward a message to the NSM device and wait for the response from it */
+static int nsm_sendrecv_msg_locked(struct nsm *nsm)
+{
+	struct device *dev = &nsm->vdev->dev;
+	struct scatterlist sg_in, sg_out;
+	struct nsm_msg *msg = &nsm->msg;
+	struct virtqueue *vq = nsm->vq;
+	unsigned int len;
+	void *queue_buf;
+	bool kicked;
+	int rc;
+
+	/* Initialize scatter-gather lists with request and response buffers. */
+	sg_init_one(&sg_out, msg->req.data, msg->req.len);
+	sg_init_one(&sg_in, msg->resp.data, sizeof(msg->resp.data));
+
+	init_completion(&nsm->cmd_done);
+	/* Add the request buffer (read by the device). */
+	rc = virtqueue_add_outbuf(vq, &sg_out, 1, msg->req.data, GFP_KERNEL);
+	if (rc)
+		return rc;
+
+	/* Add the response buffer (written by the device). */
+	rc = virtqueue_add_inbuf(vq, &sg_in, 1, msg->resp.data, GFP_KERNEL);
+	if (rc)
+		goto cleanup;
+
+	kicked = virtqueue_kick(vq);
+	if (!kicked) {
+		/* Cannot kick the virtqueue. */
+		rc = -EIO;
+		goto cleanup;
+	}
+
+	/* If the kick succeeded, wait for the device's response. */
+	if (!wait_for_completion_io_timeout(&nsm->cmd_done,
+		msecs_to_jiffies(NSM_DEFAULT_TIMEOUT_MSECS))) {
+		rc = -ETIMEDOUT;
+		goto cleanup;
+	}
+
+	queue_buf = virtqueue_get_buf(vq, &len);
+	if (!queue_buf || (queue_buf != msg->req.data)) {
+		dev_err(dev, "wrong request buffer.");
+		rc = -ENODATA;
+		goto cleanup;
+	}
+
+	queue_buf = virtqueue_get_buf(vq, &len);
+	if (!queue_buf || (queue_buf != msg->resp.data)) {
+		dev_err(dev, "wrong response buffer.");
+		rc = -ENODATA;
+		goto cleanup;
+	}
+
+	msg->resp.len = len;
+
+	rc = 0;
+
+cleanup:
+	if (rc) {
+		/* Clean the virtqueue. */
+		while (virtqueue_get_buf(vq, &len) != NULL)
+			;
+	}
+
+	return rc;
+}
+
+static int fill_req_get_random(struct nsm *nsm, struct nsm_data_req *req)
+{
+	/*
+	 * 69                          # text(9)
+	 *     47657452616E646F6D      # "GetRandom"
+	 */
+	const u8 request[] = { CBOR_TYPE_TEXT + strlen("GetRandom"),
+			       'G', 'e', 't', 'R', 'a', 'n', 'd', 'o', 'm' };
+
+	memcpy(req->data, request, sizeof(request));
+	req->len = sizeof(request);
+
+	return 0;
+}
+
+static int parse_resp_get_random(struct nsm *nsm, struct nsm_data_resp *resp,
+				 void *out, size_t max)
+{
+	/*
+	 * A1                          # map(1)
+	 *     69                      # text(9) - Name of field
+	 *         47657452616E646F6D  # "GetRandom"
+	 * A1                          # map(1) - The field itself
+	 *     66                      # text(6)
+	 *         72616E646F6D        # "random"
+	 *	# The rest of the response is random data
+	 */
+	const u8 response[] = { CBOR_TYPE_MAP + 1,
+				CBOR_TYPE_TEXT + strlen("GetRandom"),
+				'G', 'e', 't', 'R', 'a', 'n', 'd', 'o', 'm',
+				CBOR_TYPE_MAP + 1,
+				CBOR_TYPE_TEXT + strlen("random"),
+				'r', 'a', 'n', 'd', 'o', 'm' };
+	struct device *dev = &nsm->vdev->dev;
+	u8 *rand_data = NULL;
+	u8 *resp_ptr = resp->data;
+	u64 resp_len = resp->len;
+	int rc;
+
+	if ((resp->len < sizeof(response) + 1) ||
+	    (memcmp(resp_ptr, response, sizeof(response)) != 0)) {
+		dev_err(dev, "Invalid response for GetRandom");
+		return -EFAULT;
+	}
+
+	resp_ptr += sizeof(response);
+	resp_len -= sizeof(response);
+
+	rc = cbor_object_get_array(resp_ptr, resp_len, &rand_data);
+	if (rc < 0) {
+		dev_err(dev, "GetRandom: Invalid CBOR encoding\n");
+		return rc;
+	}
+
+	rc = min_t(size_t, rc, max);
+	memcpy(out, rand_data, rc);
+
+	return rc;
+}
+
+/*
+ * HwRNG implementation
+ */
+static int nsm_rng_read(struct hwrng *rng, void *data, size_t max, bool wait)
+{
+	struct nsm *nsm = hwrng_to_nsm(rng);
+	struct device *dev = &nsm->vdev->dev;
+	int rc = 0;
+
+	/* NSM always needs to wait for a response */
+	if (!wait)
+		return 0;
+
+	mutex_lock(&nsm->lock);
+
+	rc = fill_req_get_random(nsm, &nsm->msg.req);
+	if (rc != 0)
+		goto out;
+
+	rc = nsm_sendrecv_msg_locked(nsm);
+	if (rc != 0)
+		goto out;
+
+	rc = parse_resp_get_random(nsm, &nsm->msg.resp, data, max);
+	if (rc < 0)
+		goto out;
+
+	dev_dbg(dev, "RNG: returning rand bytes = %d", rc);
+out:
+	mutex_unlock(&nsm->lock);
+	return rc;
+}
+
+static long nsm_dev_ioctl(struct file *file, unsigned int cmd,
+	unsigned long arg)
+{
+	void __user *argp = u64_to_user_ptr((u64)arg);
+	struct nsm *nsm = file_to_nsm(file);
+	struct nsm_raw raw;
+	int r = 0;
+
+	if (cmd != NSM_IOCTL_RAW)
+		return -EINVAL;
+
+	if (_IOC_SIZE(cmd) != sizeof(raw))
+		return -EINVAL;
+
+	/* Copy user argument struct to kernel argument struct */
+	r = -EFAULT;
+	if (copy_from_user(&raw, argp, _IOC_SIZE(cmd)))
+		goto out;
+
+	mutex_lock(&nsm->lock);
+
+	/* Convert kernel argument struct to device request */
+	r = fill_req_raw(nsm, &nsm->msg.req, &raw);
+	if (r)
+		goto out;
+
+	/* Send message to NSM and read reply */
+	r = nsm_sendrecv_msg_locked(nsm);
+	if (r)
+		goto out;
+
+	/* Parse device response into kernel argument struct */
+	r = parse_resp_raw(nsm, &nsm->msg.resp, &raw);
+	if (r)
+		goto out;
+
+	/* Copy kernel argument struct back to user argument struct */
+	r = -EFAULT;
+	if (copy_to_user(argp, &raw, sizeof(raw)))
+		goto out;
+
+	r = 0;
+
+out:
+	mutex_unlock(&nsm->lock);
+	return r;
+}
+
+static int nsm_device_init_vq(struct virtio_device *vdev)
+{
+	struct virtqueue *vq = virtio_find_single_vq(vdev,
+		nsm_vq_callback, "nsm.vq.0");
+	struct nsm *nsm = vdev->priv;
+
+	if (IS_ERR(vq))
+		return PTR_ERR(vq);
+
+	nsm->vq = vq;
+
+	return 0;
+}
+
+static const struct file_operations nsm_dev_fops = {
+	.unlocked_ioctl = nsm_dev_ioctl,
+	.compat_ioctl = compat_ptr_ioctl,
+};
+
+/* Handler for probing the NSM device */
+static int nsm_device_probe(struct virtio_device *vdev)
+{
+	struct device *dev = &vdev->dev;
+	struct nsm *nsm;
+	int rc;
+
+	nsm = devm_kzalloc(&vdev->dev, sizeof(*nsm), GFP_KERNEL);
+	if (!nsm)
+		return -ENOMEM;
+
+	vdev->priv = nsm;
+	nsm->vdev = vdev;
+
+	rc = nsm_device_init_vq(vdev);
+	if (rc) {
+		dev_err(dev, "queue failed to initialize: %d.\n", rc);
+		goto err_init_vq;
+	}
+
+	mutex_init(&nsm->lock);
+
+	/* Register as hwrng provider */
+	nsm->hwrng = (struct hwrng) {
+		.read = nsm_rng_read,
+		.name = "nsm-hwrng",
+		.quality = 1000,
+	};
+
+	rc = hwrng_register(&nsm->hwrng);
+	if (rc) {
+		dev_err(dev, "RNG initialization error: %d.\n", rc);
+		goto err_hwrng;
+	}
+
+	/* Register /dev/nsm device node */
+	nsm->misc = (struct miscdevice) {
+		.minor	= MISC_DYNAMIC_MINOR,
+		.name	= "nsm",
+		.fops	= &nsm_dev_fops,
+		.mode	= 0666,
+	};
+
+	rc = misc_register(&nsm->misc);
+	if (rc) {
+		dev_err(dev, "misc device registration error: %d.\n", rc);
+		goto err_misc;
+	}
+
+	return 0;
+
+err_misc:
+	hwrng_unregister(&nsm->hwrng);
+err_hwrng:
+	vdev->config->del_vqs(vdev);
+err_init_vq:
+	return rc;
+}
+
+/* Handler for removing the NSM device */
+static void nsm_device_remove(struct virtio_device *vdev)
+{
+	struct nsm *nsm = vdev->priv;
+
+	hwrng_unregister(&nsm->hwrng);
+
+	vdev->config->del_vqs(vdev);
+	misc_deregister(&nsm->misc);
+}
+
+/* NSM device configuration structure */
+static struct virtio_driver virtio_nsm_driver = {
+	.feature_table             = 0,
+	.feature_table_size        = 0,
+	.feature_table_legacy      = 0,
+	.feature_table_size_legacy = 0,
+	.driver.name               = KBUILD_MODNAME,
+	.driver.owner              = THIS_MODULE,
+	.id_table                  = id_table,
+	.probe                     = nsm_device_probe,
+	.remove                    = nsm_device_remove,
+};
+
+module_virtio_driver(virtio_nsm_driver);
+MODULE_DEVICE_TABLE(virtio, id_table);
+MODULE_DESCRIPTION("Virtio NSM driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/misc/open-dice.c b/drivers/misc/open-dice.c
index 8aea2d070a40..d279a4f195e2 100644
--- a/drivers/misc/open-dice.c
+++ b/drivers/misc/open-dice.c
@@ -140,7 +140,6 @@ static int __init open_dice_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	*drvdata = (struct open_dice_drvdata){
-		.lock = __MUTEX_INITIALIZER(drvdata->lock),
 		.rmem = rmem,
 		.misc = (struct miscdevice){
 			.parent	= dev,
@@ -150,6 +149,7 @@ static int __init open_dice_probe(struct platform_device *pdev)
 			.mode	= 0600,
 		},
 	};
+	mutex_init(&drvdata->lock);
 
 	/* Index overflow check not needed, misc_register() will fail. */
 	snprintf(drvdata->name, sizeof(drvdata->name), DRIVER_NAME"%u", dev_idx++);
diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c
index af519088732d..c38a6083f0a7 100644
--- a/drivers/misc/pci_endpoint_test.c
+++ b/drivers/misc/pci_endpoint_test.c
@@ -28,14 +28,14 @@
 #define DRV_MODULE_NAME				"pci-endpoint-test"
 
 #define IRQ_TYPE_UNDEFINED			-1
-#define IRQ_TYPE_LEGACY				0
+#define IRQ_TYPE_INTX				0
 #define IRQ_TYPE_MSI				1
 #define IRQ_TYPE_MSIX				2
 
 #define PCI_ENDPOINT_TEST_MAGIC			0x0
 
 #define PCI_ENDPOINT_TEST_COMMAND		0x4
-#define COMMAND_RAISE_LEGACY_IRQ		BIT(0)
+#define COMMAND_RAISE_INTX_IRQ			BIT(0)
 #define COMMAND_RAISE_MSI_IRQ			BIT(1)
 #define COMMAND_RAISE_MSIX_IRQ			BIT(2)
 #define COMMAND_READ				BIT(3)
@@ -183,8 +183,8 @@ static bool pci_endpoint_test_alloc_irq_vectors(struct pci_endpoint_test *test,
 	bool res = true;
 
 	switch (type) {
-	case IRQ_TYPE_LEGACY:
-		irq = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_LEGACY);
+	case IRQ_TYPE_INTX:
+		irq = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_INTX);
 		if (irq < 0)
 			dev_err(dev, "Failed to get Legacy interrupt\n");
 		break;
@@ -244,7 +244,7 @@ static bool pci_endpoint_test_request_irq(struct pci_endpoint_test *test)
 
 fail:
 	switch (irq_type) {
-	case IRQ_TYPE_LEGACY:
+	case IRQ_TYPE_INTX:
 		dev_err(dev, "Failed to request IRQ %d for Legacy\n",
 			pci_irq_vector(pdev, i));
 		break;
@@ -263,6 +263,15 @@ fail:
 	return false;
 }
 
+static const u32 bar_test_pattern[] = {
+	0xA0A0A0A0,
+	0xA1A1A1A1,
+	0xA2A2A2A2,
+	0xA3A3A3A3,
+	0xA4A4A4A4,
+	0xA5A5A5A5,
+};
+
 static bool pci_endpoint_test_bar(struct pci_endpoint_test *test,
 				  enum pci_barno barno)
 {
@@ -280,26 +289,27 @@ static bool pci_endpoint_test_bar(struct pci_endpoint_test *test,
 		size = 0x4;
 
 	for (j = 0; j < size; j += 4)
-		pci_endpoint_test_bar_writel(test, barno, j, 0xA0A0A0A0);
+		pci_endpoint_test_bar_writel(test, barno, j,
+					     bar_test_pattern[barno]);
 
 	for (j = 0; j < size; j += 4) {
 		val = pci_endpoint_test_bar_readl(test, barno, j);
-		if (val != 0xA0A0A0A0)
+		if (val != bar_test_pattern[barno])
 			return false;
 	}
 
 	return true;
 }
 
-static bool pci_endpoint_test_legacy_irq(struct pci_endpoint_test *test)
+static bool pci_endpoint_test_intx_irq(struct pci_endpoint_test *test)
 {
 	u32 val;
 
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE,
-				 IRQ_TYPE_LEGACY);
+				 IRQ_TYPE_INTX);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, 0);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND,
-				 COMMAND_RAISE_LEGACY_IRQ);
+				 COMMAND_RAISE_INTX_IRQ);
 	val = wait_for_completion_timeout(&test->irq_raised,
 					  msecs_to_jiffies(1000));
 	if (!val)
@@ -385,7 +395,7 @@ static bool pci_endpoint_test_copy(struct pci_endpoint_test *test,
 	if (use_dma)
 		flags |= FLAG_USE_DMA;
 
-	if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) {
+	if (irq_type < IRQ_TYPE_INTX || irq_type > IRQ_TYPE_MSIX) {
 		dev_err(dev, "Invalid IRQ type option\n");
 		goto err;
 	}
@@ -521,7 +531,7 @@ static bool pci_endpoint_test_write(struct pci_endpoint_test *test,
 	if (use_dma)
 		flags |= FLAG_USE_DMA;
 
-	if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) {
+	if (irq_type < IRQ_TYPE_INTX || irq_type > IRQ_TYPE_MSIX) {
 		dev_err(dev, "Invalid IRQ type option\n");
 		goto err;
 	}
@@ -621,7 +631,7 @@ static bool pci_endpoint_test_read(struct pci_endpoint_test *test,
 	if (use_dma)
 		flags |= FLAG_USE_DMA;
 
-	if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) {
+	if (irq_type < IRQ_TYPE_INTX || irq_type > IRQ_TYPE_MSIX) {
 		dev_err(dev, "Invalid IRQ type option\n");
 		goto err;
 	}
@@ -691,7 +701,7 @@ static bool pci_endpoint_test_set_irq(struct pci_endpoint_test *test,
 	struct pci_dev *pdev = test->pdev;
 	struct device *dev = &pdev->dev;
 
-	if (req_irq_type < IRQ_TYPE_LEGACY || req_irq_type > IRQ_TYPE_MSIX) {
+	if (req_irq_type < IRQ_TYPE_INTX || req_irq_type > IRQ_TYPE_MSIX) {
 		dev_err(dev, "Invalid IRQ type option\n");
 		return false;
 	}
@@ -737,8 +747,8 @@ static long pci_endpoint_test_ioctl(struct file *file, unsigned int cmd,
 			goto ret;
 		ret = pci_endpoint_test_bar(test, bar);
 		break;
-	case PCITEST_LEGACY_IRQ:
-		ret = pci_endpoint_test_legacy_irq(test);
+	case PCITEST_INTX_IRQ:
+		ret = pci_endpoint_test_intx_irq(test);
 		break;
 	case PCITEST_MSI:
 	case PCITEST_MSIX:
@@ -801,7 +811,7 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
 	test->irq_type = IRQ_TYPE_UNDEFINED;
 
 	if (no_msi)
-		irq_type = IRQ_TYPE_LEGACY;
+		irq_type = IRQ_TYPE_INTX;
 
 	data = (struct pci_endpoint_test_data *)ent->driver_data;
 	if (data) {
@@ -860,7 +870,7 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
 
 	pci_set_drvdata(pdev, test);
 
-	id = ida_simple_get(&pci_endpoint_test_ida, 0, 0, GFP_KERNEL);
+	id = ida_alloc(&pci_endpoint_test_ida, GFP_KERNEL);
 	if (id < 0) {
 		err = id;
 		dev_err(dev, "Unable to get id\n");
@@ -907,7 +917,7 @@ err_kfree_test_name:
 	kfree(test->name);
 
 err_ida_remove:
-	ida_simple_remove(&pci_endpoint_test_ida, id);
+	ida_free(&pci_endpoint_test_ida, id);
 
 err_iounmap:
 	for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) {
@@ -943,7 +953,7 @@ static void pci_endpoint_test_remove(struct pci_dev *pdev)
 	misc_deregister(&test->miscdev);
 	kfree(misc_device->name);
 	kfree(test->name);
-	ida_simple_remove(&pci_endpoint_test_ida, id);
+	ida_free(&pci_endpoint_test_ida, id);
 	for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) {
 		if (test->bar[bar])
 			pci_iounmap(pdev, test->bar[bar]);
diff --git a/drivers/misc/pvpanic/pvpanic-mmio.c b/drivers/misc/pvpanic/pvpanic-mmio.c
index 9715798acce3..f3f2113a54a7 100644
--- a/drivers/misc/pvpanic/pvpanic-mmio.c
+++ b/drivers/misc/pvpanic/pvpanic-mmio.c
@@ -7,16 +7,15 @@
  *  Copyright (C) 2021 Oracle.
  */
 
+#include <linux/device.h>
+#include <linux/err.h>
 #include <linux/io.h>
-#include <linux/kernel.h>
+#include <linux/ioport.h>
 #include <linux/kexec.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/types.h>
-#include <linux/slab.h>
-
-#include <uapi/misc/pvpanic.h>
 
 #include "pvpanic.h"
 
diff --git a/drivers/misc/pvpanic/pvpanic-pci.c b/drivers/misc/pvpanic/pvpanic-pci.c
index 689af4c28c2a..9ad20e82785b 100644
--- a/drivers/misc/pvpanic/pvpanic-pci.c
+++ b/drivers/misc/pvpanic/pvpanic-pci.c
@@ -5,17 +5,13 @@
  *  Copyright (C) 2021 Oracle.
  */
 
-#include <linux/kernel.h>
+#include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/types.h>
-#include <linux/slab.h>
-
-#include <uapi/misc/pvpanic.h>
 
 #include "pvpanic.h"
 
-#define PCI_VENDOR_ID_REDHAT             0x1b36
 #define PCI_DEVICE_ID_REDHAT_PVPANIC     0x0011
 
 MODULE_AUTHOR("Mihai Carabas <mihai.carabas@oracle.com>");
diff --git a/drivers/misc/pvpanic/pvpanic.c b/drivers/misc/pvpanic/pvpanic.c
index 305b367e0ce3..df3457ce1cb1 100644
--- a/drivers/misc/pvpanic/pvpanic.c
+++ b/drivers/misc/pvpanic/pvpanic.c
@@ -8,16 +8,20 @@
  */
 
 #include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/gfp_types.h>
 #include <linux/io.h>
-#include <linux/kernel.h>
 #include <linux/kexec.h>
+#include <linux/kstrtox.h>
+#include <linux/limits.h>
+#include <linux/list.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/platform_device.h>
 #include <linux/panic_notifier.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+#include <linux/sysfs.h>
 #include <linux/types.h>
-#include <linux/cdev.h>
-#include <linux/list.h>
 
 #include <uapi/misc/pvpanic.h>
 
diff --git a/drivers/misc/pvpanic/pvpanic.h b/drivers/misc/pvpanic/pvpanic.h
index 46ffb10438ad..a42fa760eed5 100644
--- a/drivers/misc/pvpanic/pvpanic.h
+++ b/drivers/misc/pvpanic/pvpanic.h
@@ -8,6 +8,11 @@
 #ifndef PVPANIC_H_
 #define PVPANIC_H_
 
+#include <linux/compiler_types.h>
+
+struct attribute_group;
+struct device;
+
 int devm_pvpanic_probe(struct device *dev, void __iomem *base);
 extern const struct attribute_group *pvpanic_dev_groups[];
 
diff --git a/drivers/misc/vmw_vmci/vmci_handle_array.c b/drivers/misc/vmw_vmci/vmci_handle_array.c
index de7fee7ead1b..681b3500125a 100644
--- a/drivers/misc/vmw_vmci/vmci_handle_array.c
+++ b/drivers/misc/vmw_vmci/vmci_handle_array.c
@@ -8,12 +8,6 @@
 #include <linux/slab.h>
 #include "vmci_handle_array.h"
 
-static size_t handle_arr_calc_size(u32 capacity)
-{
-	return VMCI_HANDLE_ARRAY_HEADER_SIZE +
-	    capacity * sizeof(struct vmci_handle);
-}
-
 struct vmci_handle_arr *vmci_handle_arr_create(u32 capacity, u32 max_capacity)
 {
 	struct vmci_handle_arr *array;
@@ -25,7 +19,7 @@ struct vmci_handle_arr *vmci_handle_arr_create(u32 capacity, u32 max_capacity)
 		capacity = min((u32)VMCI_HANDLE_ARRAY_DEFAULT_CAPACITY,
 			       max_capacity);
 
-	array = kmalloc(handle_arr_calc_size(capacity), GFP_ATOMIC);
+	array = kmalloc(struct_size(array, entries, capacity), GFP_ATOMIC);
 	if (!array)
 		return NULL;
 
@@ -51,8 +45,8 @@ int vmci_handle_arr_append_entry(struct vmci_handle_arr **array_ptr,
 		struct vmci_handle_arr *new_array;
 		u32 capacity_bump = min(array->max_capacity - array->capacity,
 					array->capacity);
-		size_t new_size = handle_arr_calc_size(array->capacity +
-						       capacity_bump);
+		size_t new_size = struct_size(array, entries,
+					      size_add(array->capacity, capacity_bump));
 
 		if (array->size >= array->max_capacity)
 			return VMCI_ERROR_NO_MEM;
diff --git a/drivers/misc/vmw_vmci/vmci_handle_array.h b/drivers/misc/vmw_vmci/vmci_handle_array.h
index b0e6b1956014..27a38b97e8a8 100644
--- a/drivers/misc/vmw_vmci/vmci_handle_array.h
+++ b/drivers/misc/vmw_vmci/vmci_handle_array.h
@@ -20,14 +20,8 @@ struct vmci_handle_arr {
 	struct vmci_handle entries[] __counted_by(capacity);
 };
 
-#define VMCI_HANDLE_ARRAY_HEADER_SIZE				\
-	offsetof(struct vmci_handle_arr, entries)
 /* Select a default capacity that results in a 64 byte sized array */
 #define VMCI_HANDLE_ARRAY_DEFAULT_CAPACITY			6
-/* Make sure that the max array size can be expressed by a u32 */
-#define VMCI_HANDLE_ARRAY_MAX_CAPACITY				\
-	((U32_MAX - VMCI_HANDLE_ARRAY_HEADER_SIZE - 1) /	\
-	sizeof(struct vmci_handle))
 
 struct vmci_handle_arr *vmci_handle_arr_create(u32 capacity, u32 max_capacity);
 void vmci_handle_arr_destroy(struct vmci_handle_arr *array);
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index f410bee50132..58ed7193a3ca 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1015,10 +1015,12 @@ static int mmc_select_bus_width(struct mmc_card *card)
 	static unsigned ext_csd_bits[] = {
 		EXT_CSD_BUS_WIDTH_8,
 		EXT_CSD_BUS_WIDTH_4,
+		EXT_CSD_BUS_WIDTH_1,
 	};
 	static unsigned bus_widths[] = {
 		MMC_BUS_WIDTH_8,
 		MMC_BUS_WIDTH_4,
+		MMC_BUS_WIDTH_1,
 	};
 	struct mmc_host *host = card->host;
 	unsigned idx, bus_width = 0;
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index a0a2412f62a7..2ae60d208cdf 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -174,8 +174,8 @@ static struct scatterlist *mmc_alloc_sg(unsigned short sg_len, gfp_t gfp)
 	return sg;
 }
 
-static void mmc_queue_setup_discard(struct request_queue *q,
-				    struct mmc_card *card)
+static void mmc_queue_setup_discard(struct mmc_card *card,
+		struct queue_limits *lim)
 {
 	unsigned max_discard;
 
@@ -183,15 +183,17 @@ static void mmc_queue_setup_discard(struct request_queue *q,
 	if (!max_discard)
 		return;
 
-	blk_queue_max_discard_sectors(q, max_discard);
-	q->limits.discard_granularity = card->pref_erase << 9;
-	/* granularity must not be greater than max. discard */
-	if (card->pref_erase > max_discard)
-		q->limits.discard_granularity = SECTOR_SIZE;
+	lim->max_hw_discard_sectors = max_discard;
 	if (mmc_can_secure_erase_trim(card))
-		blk_queue_max_secure_erase_sectors(q, max_discard);
+		lim->max_secure_erase_sectors = max_discard;
 	if (mmc_can_trim(card) && card->erased_byte == 0)
-		blk_queue_max_write_zeroes_sectors(q, max_discard);
+		lim->max_write_zeroes_sectors = max_discard;
+
+	/* granularity must not be greater than max. discard */
+	if (card->pref_erase > max_discard)
+		lim->discard_granularity = SECTOR_SIZE;
+	else
+		lim->discard_granularity = card->pref_erase << 9;
 }
 
 static unsigned short mmc_get_max_segments(struct mmc_host *host)
@@ -341,40 +343,53 @@ static const struct blk_mq_ops mmc_mq_ops = {
 	.timeout	= mmc_mq_timed_out,
 };
 
-static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card)
+static struct gendisk *mmc_alloc_disk(struct mmc_queue *mq,
+		struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
-	unsigned block_size = 512;
+	struct queue_limits lim = { };
+	struct gendisk *disk;
 
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, mq->queue);
-	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, mq->queue);
 	if (mmc_can_erase(card))
-		mmc_queue_setup_discard(mq->queue, card);
+		mmc_queue_setup_discard(card, &lim);
 
 	if (!mmc_dev(host)->dma_mask || !*mmc_dev(host)->dma_mask)
-		blk_queue_bounce_limit(mq->queue, BLK_BOUNCE_HIGH);
-	blk_queue_max_hw_sectors(mq->queue,
-		min(host->max_blk_count, host->max_req_size / 512));
-	if (host->can_dma_map_merge)
-		WARN(!blk_queue_can_use_dma_map_merging(mq->queue,
-							mmc_dev(host)),
-		     "merging was advertised but not possible");
-	blk_queue_max_segments(mq->queue, mmc_get_max_segments(host));
-
-	if (mmc_card_mmc(card) && card->ext_csd.data_sector_size) {
-		block_size = card->ext_csd.data_sector_size;
-		WARN_ON(block_size != 512 && block_size != 4096);
-	}
+		lim.bounce = BLK_BOUNCE_HIGH;
+
+	lim.max_hw_sectors = min(host->max_blk_count, host->max_req_size / 512);
+
+	if (mmc_card_mmc(card) && card->ext_csd.data_sector_size)
+		lim.logical_block_size = card->ext_csd.data_sector_size;
+	else
+		lim.logical_block_size = 512;
+
+	WARN_ON_ONCE(lim.logical_block_size != 512 &&
+		     lim.logical_block_size != 4096);
 
-	blk_queue_logical_block_size(mq->queue, block_size);
 	/*
-	 * After blk_queue_can_use_dma_map_merging() was called with succeed,
-	 * since it calls blk_queue_virt_boundary(), the mmc should not call
-	 * both blk_queue_max_segment_size().
+	 * Setting a virt_boundary implicity sets a max_segment_size, so try
+	 * to set the hardware one here.
 	 */
-	if (!host->can_dma_map_merge)
-		blk_queue_max_segment_size(mq->queue,
-			round_down(host->max_seg_size, block_size));
+	if (host->can_dma_map_merge) {
+		lim.virt_boundary_mask = dma_get_merge_boundary(mmc_dev(host));
+		lim.max_segments = MMC_DMA_MAP_MERGE_SEGMENTS;
+	} else {
+		lim.max_segment_size =
+			round_down(host->max_seg_size, lim.logical_block_size);
+		lim.max_segments = host->max_segs;
+	}
+
+	disk = blk_mq_alloc_disk(&mq->tag_set, &lim, mq);
+	if (IS_ERR(disk))
+		return disk;
+	mq->queue = disk->queue;
+
+	if (mmc_host_is_spi(host) && host->use_spi_crc)
+		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, mq->queue);
+	blk_queue_rq_timeout(mq->queue, 60 * HZ);
+
+	blk_queue_flag_set(QUEUE_FLAG_NONROT, mq->queue);
+	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, mq->queue);
 
 	dma_set_max_seg_size(mmc_dev(host), queue_max_segment_size(mq->queue));
 
@@ -386,6 +401,7 @@ static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card)
 	init_waitqueue_head(&mq->wait);
 
 	mmc_crypto_setup_queue(mq->queue, host);
+	return disk;
 }
 
 static inline bool mmc_merge_capable(struct mmc_host *host)
@@ -447,18 +463,9 @@ struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card)
 		return ERR_PTR(ret);
 		
 
-	disk = blk_mq_alloc_disk(&mq->tag_set, mq);
-	if (IS_ERR(disk)) {
+	disk = mmc_alloc_disk(mq, card);
+	if (IS_ERR(disk))
 		blk_mq_free_tag_set(&mq->tag_set);
-		return disk;
-	}
-	mq->queue = disk->queue;
-
-	if (mmc_host_is_spi(host) && host->use_spi_crc)
-		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, mq->queue);
-	blk_queue_rq_timeout(mq->queue, 60 * HZ);
-
-	mmc_setup_queue(mq, card);
 	return disk;
 }
 
diff --git a/drivers/mmc/core/sdio_uart.c b/drivers/mmc/core/sdio_uart.c
index ef38dcd3a887..575ebbce378e 100644
--- a/drivers/mmc/core/sdio_uart.c
+++ b/drivers/mmc/core/sdio_uart.c
@@ -178,11 +178,9 @@ static inline void sdio_uart_release_func(struct sdio_uart_port *port)
 		sdio_release_host(port->func);
 }
 
-static inline unsigned int sdio_in(struct sdio_uart_port *port, int offset)
+static inline u8 sdio_in(struct sdio_uart_port *port, int offset)
 {
-	unsigned char c;
-	c = sdio_readb(port->func, port->regs_offset + offset, NULL);
-	return c;
+	return sdio_readb(port->func, port->regs_offset + offset, NULL);
 }
 
 static inline void sdio_out(struct sdio_uart_port *port, int offset, int value)
@@ -192,8 +190,8 @@ static inline void sdio_out(struct sdio_uart_port *port, int offset, int value)
 
 static unsigned int sdio_uart_get_mctrl(struct sdio_uart_port *port)
 {
-	unsigned char status;
 	unsigned int ret;
+	u8 status;
 
 	/* FIXME: What stops this losing the delta bits and breaking
 	   sdio_uart_check_modem_status ? */
@@ -354,15 +352,13 @@ static void sdio_uart_stop_rx(struct sdio_uart_port *port)
 	sdio_out(port, UART_IER, port->ier);
 }
 
-static void sdio_uart_receive_chars(struct sdio_uart_port *port,
-				    unsigned int *status)
+static void sdio_uart_receive_chars(struct sdio_uart_port *port, u8 *status)
 {
-	unsigned int ch, flag;
 	int max_count = 256;
 
 	do {
-		ch = sdio_in(port, UART_RX);
-		flag = TTY_NORMAL;
+		u8 ch = sdio_in(port, UART_RX);
+		u8 flag = TTY_NORMAL;
 		port->icount.rx++;
 
 		if (unlikely(*status & (UART_LSR_BI | UART_LSR_PE |
@@ -449,8 +445,8 @@ static void sdio_uart_transmit_chars(struct sdio_uart_port *port)
 
 static void sdio_uart_check_modem_status(struct sdio_uart_port *port)
 {
-	int status;
 	struct tty_struct *tty;
+	u8 status;
 
 	status = sdio_in(port, UART_MSR);
 
@@ -499,7 +495,7 @@ static void sdio_uart_check_modem_status(struct sdio_uart_port *port)
 static void sdio_uart_irq(struct sdio_func *func)
 {
 	struct sdio_uart_port *port = sdio_get_drvdata(func);
-	unsigned int iir, lsr;
+	u8 iir, lsr;
 
 	/*
 	 * In a few places sdio_uart_irq() is called directly instead of
@@ -795,7 +791,7 @@ static unsigned int sdio_uart_chars_in_buffer(struct tty_struct *tty)
 	return kfifo_len(&port->xmit_fifo);
 }
 
-static void sdio_uart_send_xchar(struct tty_struct *tty, char ch)
+static void sdio_uart_send_xchar(struct tty_struct *tty, u8 ch)
 {
 	struct sdio_uart_port *port = tty->driver_data;
 
diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c
index 2a2d949a9344..39f45c2b6de8 100644
--- a/drivers/mmc/core/slot-gpio.c
+++ b/drivers/mmc/core/slot-gpio.c
@@ -75,11 +75,15 @@ EXPORT_SYMBOL(mmc_gpio_set_cd_irq);
 int mmc_gpio_get_ro(struct mmc_host *host)
 {
 	struct mmc_gpio *ctx = host->slot.handler_priv;
+	int cansleep;
 
 	if (!ctx || !ctx->ro_gpio)
 		return -ENOSYS;
 
-	return gpiod_get_value_cansleep(ctx->ro_gpio);
+	cansleep = gpiod_cansleep(ctx->ro_gpio);
+	return cansleep ?
+		gpiod_get_value_cansleep(ctx->ro_gpio) :
+		gpiod_get_value(ctx->ro_gpio);
 }
 EXPORT_SYMBOL(mmc_gpio_get_ro);
 
diff --git a/drivers/mmc/host/mmci_stm32_sdmmc.c b/drivers/mmc/host/mmci_stm32_sdmmc.c
index 35067e1e6cd8..f5da7f9baa52 100644
--- a/drivers/mmc/host/mmci_stm32_sdmmc.c
+++ b/drivers/mmc/host/mmci_stm32_sdmmc.c
@@ -225,6 +225,8 @@ static int sdmmc_idma_start(struct mmci_host *host, unsigned int *datactrl)
 	struct scatterlist *sg;
 	int i;
 
+	host->dma_in_progress = true;
+
 	if (!host->variant->dma_lli || data->sg_len == 1 ||
 	    idma->use_bounce_buffer) {
 		u32 dma_addr;
@@ -263,9 +265,30 @@ static int sdmmc_idma_start(struct mmci_host *host, unsigned int *datactrl)
 	return 0;
 }
 
+static void sdmmc_idma_error(struct mmci_host *host)
+{
+	struct mmc_data *data = host->data;
+	struct sdmmc_idma *idma = host->dma_priv;
+
+	if (!dma_inprogress(host))
+		return;
+
+	writel_relaxed(0, host->base + MMCI_STM32_IDMACTRLR);
+	host->dma_in_progress = false;
+	data->host_cookie = 0;
+
+	if (!idma->use_bounce_buffer)
+		dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
+			     mmc_get_dma_dir(data));
+}
+
 static void sdmmc_idma_finalize(struct mmci_host *host, struct mmc_data *data)
 {
+	if (!dma_inprogress(host))
+		return;
+
 	writel_relaxed(0, host->base + MMCI_STM32_IDMACTRLR);
+	host->dma_in_progress = false;
 
 	if (!data->host_cookie)
 		sdmmc_idma_unprep_data(host, data, 0);
@@ -676,6 +699,7 @@ static struct mmci_host_ops sdmmc_variant_ops = {
 	.dma_setup = sdmmc_idma_setup,
 	.dma_start = sdmmc_idma_start,
 	.dma_finalize = sdmmc_idma_finalize,
+	.dma_error = sdmmc_idma_error,
 	.set_clkreg = mmci_sdmmc_set_clkreg,
 	.set_pwrreg = mmci_sdmmc_set_pwrreg,
 	.busy_complete = sdmmc_busy_complete,
diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index 87d78432a1e0..7dfe7c4e0077 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -7,6 +7,7 @@
  *   Wei WANG <wei_wang@realsil.com.cn>
  */
 
+#include <linux/pci.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/highmem.h>
@@ -947,7 +948,7 @@ static int sd_power_on(struct realtek_pci_sdmmc *host, unsigned char power_mode)
 	/* send at least 74 clocks */
 	rtsx_pci_write_register(pcr, SD_BUS_STAT, SD_CLK_TOGGLE_EN, SD_CLK_TOGGLE_EN);
 
-	if (PCI_PID(pcr) == PID_5261) {
+	if ((PCI_PID(pcr) == PID_5261) || (PCI_PID(pcr) == PID_5264)) {
 		/*
 		 * If test mode is set switch to SD Express mandatorily,
 		 * this is only for factory testing.
@@ -1364,6 +1365,14 @@ static int sdmmc_init_sd_express(struct mmc_host *mmc, struct mmc_ios *ios)
 	struct realtek_pci_sdmmc *host = mmc_priv(mmc);
 	struct rtsx_pcr *pcr = host->pcr;
 
+	if (PCI_PID(pcr) == PID_5264) {
+		pcie_capability_clear_and_set_word(pcr->pci, PCI_EXP_LNKCTL2,
+				PCI_EXP_LNKCTL2_TLS, PCI_EXP_LNKCTL2_TLS_2_5GT);
+		pci_write_config_byte(pcr->pci, 0x80e, 0x02);
+		pcie_capability_clear_and_set_word(pcr->pci, PCI_EXP_LNKCTL2,
+				PCI_EXP_LNKCTL2_TLS, PCI_EXP_LNKCTL2_TLS_5_0GT);
+	}
+
 	/* Set relink_time for changing to PCIe card */
 	relink_time = 0x8FFF;
 
@@ -1379,6 +1388,12 @@ static int sdmmc_init_sd_express(struct mmc_host *mmc, struct mmc_ios *ios)
 	if (pcr->ops->disable_auto_blink)
 		pcr->ops->disable_auto_blink(pcr);
 
+	if (PCI_PID(pcr) == PID_5264) {
+		rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG2,
+			RTS5264_CHIP_RST_N_SEL, RTS5264_CHIP_RST_N_SEL);
+		rtsx_pci_write_register(pcr, GPIO_CTL, 0x02, 0x00);
+	}
+
 	/* For PCIe/NVMe mode can't enter delink issue */
 	pcr->hw_param.interrupt_en &= ~(SD_INT_EN);
 	rtsx_pci_writel(pcr, RTSX_BIER, pcr->hw_param.interrupt_en);
diff --git a/drivers/mmc/host/sdhci-pci-o2micro.c b/drivers/mmc/host/sdhci-pci-o2micro.c
index 7bfee28116af..d4a02184784a 100644
--- a/drivers/mmc/host/sdhci-pci-o2micro.c
+++ b/drivers/mmc/host/sdhci-pci-o2micro.c
@@ -693,6 +693,35 @@ static int sdhci_pci_o2_init_sd_express(struct mmc_host *mmc, struct mmc_ios *io
 	return 0;
 }
 
+static void sdhci_pci_o2_set_power(struct sdhci_host *host, unsigned char mode,  unsigned short vdd)
+{
+	struct sdhci_pci_chip *chip;
+	struct sdhci_pci_slot *slot = sdhci_priv(host);
+	u32 scratch_32 = 0;
+	u8 scratch_8 = 0;
+
+	chip = slot->chip;
+
+	if (mode == MMC_POWER_OFF) {
+		/* UnLock WP */
+		pci_read_config_byte(chip->pdev, O2_SD_LOCK_WP, &scratch_8);
+		scratch_8 &= 0x7f;
+		pci_write_config_byte(chip->pdev, O2_SD_LOCK_WP, scratch_8);
+
+		/* Set PCR 0x354[16] to switch Clock Source back to OPE Clock */
+		pci_read_config_dword(chip->pdev, O2_SD_OUTPUT_CLK_SOURCE_SWITCH, &scratch_32);
+		scratch_32 &= ~(O2_SD_SEL_DLL);
+		pci_write_config_dword(chip->pdev, O2_SD_OUTPUT_CLK_SOURCE_SWITCH, scratch_32);
+
+		/* Lock WP */
+		pci_read_config_byte(chip->pdev, O2_SD_LOCK_WP, &scratch_8);
+		scratch_8 |= 0x80;
+		pci_write_config_byte(chip->pdev, O2_SD_LOCK_WP, scratch_8);
+	}
+
+	sdhci_set_power(host, mode, vdd);
+}
+
 static int sdhci_pci_o2_probe_slot(struct sdhci_pci_slot *slot)
 {
 	struct sdhci_pci_chip *chip;
@@ -1051,6 +1080,7 @@ static const struct sdhci_ops sdhci_pci_o2_ops = {
 	.set_bus_width = sdhci_set_bus_width,
 	.reset = sdhci_reset,
 	.set_uhs_signaling = sdhci_set_uhs_signaling,
+	.set_power = sdhci_pci_o2_set_power,
 };
 
 const struct sdhci_pci_fixes sdhci_o2 = {
diff --git a/drivers/mmc/host/sdhci-xenon-phy.c b/drivers/mmc/host/sdhci-xenon-phy.c
index 8cf3a375de65..cc9d28b75eb9 100644
--- a/drivers/mmc/host/sdhci-xenon-phy.c
+++ b/drivers/mmc/host/sdhci-xenon-phy.c
@@ -11,6 +11,7 @@
 #include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/ktime.h>
+#include <linux/iopoll.h>
 #include <linux/of_address.h>
 
 #include "sdhci-pltfm.h"
@@ -109,6 +110,8 @@
 #define XENON_EMMC_PHY_LOGIC_TIMING_ADJUST	(XENON_EMMC_PHY_REG_BASE + 0x18)
 #define XENON_LOGIC_TIMING_VALUE		0x00AA8977
 
+#define XENON_MAX_PHY_TIMEOUT_LOOPS		100
+
 /*
  * List offset of PHY registers and some special register values
  * in eMMC PHY 5.0 or eMMC PHY 5.1
@@ -216,6 +219,19 @@ static int xenon_alloc_emmc_phy(struct sdhci_host *host)
 	return 0;
 }
 
+static int xenon_check_stability_internal_clk(struct sdhci_host *host)
+{
+	u32 reg;
+	int err;
+
+	err = read_poll_timeout(sdhci_readw, reg, reg & SDHCI_CLOCK_INT_STABLE,
+				1100, 20000, false, host, SDHCI_CLOCK_CONTROL);
+	if (err)
+		dev_err(mmc_dev(host->mmc), "phy_init: Internal clock never stabilized.\n");
+
+	return err;
+}
+
 /*
  * eMMC 5.0/5.1 PHY init/re-init.
  * eMMC PHY init should be executed after:
@@ -232,6 +248,11 @@ static int xenon_emmc_phy_init(struct sdhci_host *host)
 	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
 	struct xenon_emmc_phy_regs *phy_regs = priv->emmc_phy_regs;
 
+	int ret = xenon_check_stability_internal_clk(host);
+
+	if (ret)
+		return ret;
+
 	reg = sdhci_readl(host, phy_regs->timing_adj);
 	reg |= XENON_PHY_INITIALIZAION;
 	sdhci_writel(host, reg, phy_regs->timing_adj);
@@ -259,18 +280,27 @@ static int xenon_emmc_phy_init(struct sdhci_host *host)
 	/* get the wait time */
 	wait /= clock;
 	wait++;
-	/* wait for host eMMC PHY init completes */
-	udelay(wait);
 
-	reg = sdhci_readl(host, phy_regs->timing_adj);
-	reg &= XENON_PHY_INITIALIZAION;
-	if (reg) {
+	/*
+	 * AC5X spec says bit must be polled until zero.
+	 * We see cases in which timeout can take longer
+	 * than the standard calculation on AC5X, which is
+	 * expected following the spec comment above.
+	 * According to the spec, we must wait as long as
+	 * it takes for that bit to toggle on AC5X.
+	 * Cap that with 100 delay loops so we won't get
+	 * stuck here forever:
+	 */
+
+	ret = read_poll_timeout(sdhci_readl, reg,
+				!(reg & XENON_PHY_INITIALIZAION),
+				wait, XENON_MAX_PHY_TIMEOUT_LOOPS * wait,
+				false, host, phy_regs->timing_adj);
+	if (ret)
 		dev_err(mmc_dev(host->mmc), "eMMC PHY init cannot complete after %d us\n",
-			wait);
-		return -ETIMEDOUT;
-	}
+			wait * XENON_MAX_PHY_TIMEOUT_LOOPS);
 
-	return 0;
+	return ret;
 }
 
 #define ARMADA_3700_SOC_PAD_1_8V	0x1
diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c
index aa44a23ec045..97a00ec9a4d4 100644
--- a/drivers/mtd/devices/block2mtd.c
+++ b/drivers/mtd/devices/block2mtd.c
@@ -37,7 +37,7 @@
 /* Info for the block device */
 struct block2mtd_dev {
 	struct list_head list;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct mtd_info mtd;
 	struct mutex write_mutex;
 };
@@ -55,8 +55,7 @@ static struct page *page_read(struct address_space *mapping, pgoff_t index)
 /* erase a specified part of the device */
 static int _block2mtd_erase(struct block2mtd_dev *dev, loff_t to, size_t len)
 {
-	struct address_space *mapping =
-				dev->bdev_handle->bdev->bd_inode->i_mapping;
+	struct address_space *mapping = dev->bdev_file->f_mapping;
 	struct page *page;
 	pgoff_t index = to >> PAGE_SHIFT;	// page index
 	int pages = len >> PAGE_SHIFT;
@@ -106,8 +105,7 @@ static int block2mtd_read(struct mtd_info *mtd, loff_t from, size_t len,
 		size_t *retlen, u_char *buf)
 {
 	struct block2mtd_dev *dev = mtd->priv;
-	struct address_space *mapping =
-				dev->bdev_handle->bdev->bd_inode->i_mapping;
+	struct address_space *mapping = dev->bdev_file->f_mapping;
 	struct page *page;
 	pgoff_t index = from >> PAGE_SHIFT;
 	int offset = from & (PAGE_SIZE-1);
@@ -142,8 +140,7 @@ static int _block2mtd_write(struct block2mtd_dev *dev, const u_char *buf,
 		loff_t to, size_t len, size_t *retlen)
 {
 	struct page *page;
-	struct address_space *mapping =
-				dev->bdev_handle->bdev->bd_inode->i_mapping;
+	struct address_space *mapping = dev->bdev_file->f_mapping;
 	pgoff_t index = to >> PAGE_SHIFT;	// page index
 	int offset = to & ~PAGE_MASK;	// page offset
 	int cpylen;
@@ -198,7 +195,7 @@ static int block2mtd_write(struct mtd_info *mtd, loff_t to, size_t len,
 static void block2mtd_sync(struct mtd_info *mtd)
 {
 	struct block2mtd_dev *dev = mtd->priv;
-	sync_blockdev(dev->bdev_handle->bdev);
+	sync_blockdev(file_bdev(dev->bdev_file));
 	return;
 }
 
@@ -210,10 +207,9 @@ static void block2mtd_free_device(struct block2mtd_dev *dev)
 
 	kfree(dev->mtd.name);
 
-	if (dev->bdev_handle) {
-		invalidate_mapping_pages(
-			dev->bdev_handle->bdev->bd_inode->i_mapping, 0, -1);
-		bdev_release(dev->bdev_handle);
+	if (dev->bdev_file) {
+		invalidate_mapping_pages(dev->bdev_file->f_mapping, 0, -1);
+		fput(dev->bdev_file);
 	}
 
 	kfree(dev);
@@ -223,10 +219,10 @@ static void block2mtd_free_device(struct block2mtd_dev *dev)
  * This function is marked __ref because it calls the __init marked
  * early_lookup_bdev when called from the early boot code.
  */
-static struct bdev_handle __ref *mdtblock_early_get_bdev(const char *devname,
+static struct file __ref *mdtblock_early_get_bdev(const char *devname,
 		blk_mode_t mode, int timeout, struct block2mtd_dev *dev)
 {
-	struct bdev_handle *bdev_handle = ERR_PTR(-ENODEV);
+	struct file *bdev_file = ERR_PTR(-ENODEV);
 #ifndef MODULE
 	int i;
 
@@ -234,7 +230,7 @@ static struct bdev_handle __ref *mdtblock_early_get_bdev(const char *devname,
 	 * We can't use early_lookup_bdev from a running system.
 	 */
 	if (system_state >= SYSTEM_RUNNING)
-		return bdev_handle;
+		return bdev_file;
 
 	/*
 	 * We might not have the root device mounted at this point.
@@ -253,20 +249,20 @@ static struct bdev_handle __ref *mdtblock_early_get_bdev(const char *devname,
 		wait_for_device_probe();
 
 		if (!early_lookup_bdev(devname, &devt)) {
-			bdev_handle = bdev_open_by_dev(devt, mode, dev, NULL);
-			if (!IS_ERR(bdev_handle))
+			bdev_file = bdev_file_open_by_dev(devt, mode, dev, NULL);
+			if (!IS_ERR(bdev_file))
 				break;
 		}
 	}
 #endif
-	return bdev_handle;
+	return bdev_file;
 }
 
 static struct block2mtd_dev *add_device(char *devname, int erase_size,
 		char *label, int timeout)
 {
 	const blk_mode_t mode = BLK_OPEN_READ | BLK_OPEN_WRITE;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct block_device *bdev;
 	struct block2mtd_dev *dev;
 	char *name;
@@ -279,16 +275,16 @@ static struct block2mtd_dev *add_device(char *devname, int erase_size,
 		return NULL;
 
 	/* Get a handle on the device */
-	bdev_handle = bdev_open_by_path(devname, mode, dev, NULL);
-	if (IS_ERR(bdev_handle))
-		bdev_handle = mdtblock_early_get_bdev(devname, mode, timeout,
+	bdev_file = bdev_file_open_by_path(devname, mode, dev, NULL);
+	if (IS_ERR(bdev_file))
+		bdev_file = mdtblock_early_get_bdev(devname, mode, timeout,
 						      dev);
-	if (IS_ERR(bdev_handle)) {
+	if (IS_ERR(bdev_file)) {
 		pr_err("error: cannot open device %s\n", devname);
 		goto err_free_block2mtd;
 	}
-	dev->bdev_handle = bdev_handle;
-	bdev = bdev_handle->bdev;
+	dev->bdev_file = bdev_file;
+	bdev = file_bdev(bdev_file);
 
 	if (MAJOR(bdev->bd_dev) == MTD_BLOCK_MAJOR) {
 		pr_err("attempting to use an MTD device as a block device\n");
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index f0526dcc2162..3caa0717d46c 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -277,6 +277,7 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
 {
 	struct mtd_blktrans_ops *tr = new->tr;
 	struct mtd_blktrans_dev *d;
+	struct queue_limits lim = { };
 	int last_devnum = -1;
 	struct gendisk *gd;
 	int ret;
@@ -331,9 +332,13 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
 			BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING);
 	if (ret)
 		goto out_kfree_tag_set;
+	
+	lim.logical_block_size = tr->blksize;
+	if (tr->discard)
+		lim.max_hw_discard_sectors = UINT_MAX;
 
 	/* Create gendisk */
-	gd = blk_mq_alloc_disk(new->tag_set, new);
+	gd = blk_mq_alloc_disk(new->tag_set, &lim, new);
 	if (IS_ERR(gd)) {
 		ret = PTR_ERR(gd);
 		goto out_free_tag_set;
@@ -371,14 +376,9 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
 	if (tr->flush)
 		blk_queue_write_cache(new->rq, true, false);
 
-	blk_queue_logical_block_size(new->rq, tr->blksize);
-
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, new->rq);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, new->rq);
 
-	if (tr->discard)
-		blk_queue_max_discard_sectors(new->rq, UINT_MAX);
-
 	gd->queue = new->rq;
 
 	if (new->readonly)
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index bb0759ca12f1..5887feb347a4 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -30,6 +30,7 @@
 #include <linux/debugfs.h>
 #include <linux/nvmem-provider.h>
 #include <linux/root_dev.h>
+#include <linux/error-injection.h>
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
@@ -620,6 +621,7 @@ static void mtd_check_of_node(struct mtd_info *mtd)
 		if (plen == mtd_name_len &&
 		    !strncmp(mtd->name, pname + offset, plen)) {
 			mtd_set_of_node(mtd, mtd_dn);
+			of_node_put(mtd_dn);
 			break;
 		}
 	}
@@ -1412,6 +1414,7 @@ int mtd_erase(struct mtd_info *mtd, struct erase_info *instr)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(mtd_erase);
+ALLOW_ERROR_INJECTION(mtd_erase, ERRNO);
 
 /*
  * This stuff for eXecute-In-Place. phys is optional and may be set to NULL.
@@ -1511,6 +1514,7 @@ int mtd_read(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(mtd_read);
+ALLOW_ERROR_INJECTION(mtd_read, ERRNO);
 
 int mtd_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen,
 	      const u_char *buf)
@@ -1527,6 +1531,7 @@ int mtd_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(mtd_write);
+ALLOW_ERROR_INJECTION(mtd_write, ERRNO);
 
 /*
  * In blackbox flight recorder like scenarios we want to make successful writes
@@ -2347,6 +2352,7 @@ int mtd_block_markbad(struct mtd_info *mtd, loff_t ofs)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mtd_block_markbad);
+ALLOW_ERROR_INJECTION(mtd_block_markbad, ERRNO);
 
 /*
  * default_mtd_writev - the default writev method
diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index a46698744850..5b0f5a9cef81 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -290,16 +290,13 @@ static const struct marvell_hw_ecc_layout marvell_nfc_layouts[] = {
 	MARVELL_LAYOUT( 2048,   512,  4,  1,  1, 2048, 32, 30,  0,  0,  0),
 	MARVELL_LAYOUT( 2048,   512,  8,  2,  1, 1024,  0, 30,1024,32, 30),
 	MARVELL_LAYOUT( 2048,   512,  8,  2,  1, 1024,  0, 30,1024,64, 30),
-	MARVELL_LAYOUT( 2048,   512,  12, 3,  2, 704,   0, 30,640,  0, 30),
-	MARVELL_LAYOUT( 2048,   512,  16, 5,  4, 512,   0, 30,  0, 32, 30),
+	MARVELL_LAYOUT( 2048,   512,  16, 4,  4, 512,   0, 30,  0, 32, 30),
 	MARVELL_LAYOUT( 4096,   512,  4,  2,  2, 2048, 32, 30,  0,  0,  0),
-	MARVELL_LAYOUT( 4096,   512,  8,  5,  4, 1024,  0, 30,  0, 64, 30),
-	MARVELL_LAYOUT( 4096,   512,  12, 6,  5, 704,   0, 30,576, 32, 30),
-	MARVELL_LAYOUT( 4096,   512,  16, 9,  8, 512,   0, 30,  0, 32, 30),
+	MARVELL_LAYOUT( 4096,   512,  8,  4,  4, 1024,  0, 30,  0, 64, 30),
+	MARVELL_LAYOUT( 4096,   512,  16, 8,  8, 512,   0, 30,  0, 32, 30),
 	MARVELL_LAYOUT( 8192,   512,  4,  4,  4, 2048,  0, 30,  0,  0,  0),
-	MARVELL_LAYOUT( 8192,   512,  8,  9,  8, 1024,  0, 30,  0, 160, 30),
-	MARVELL_LAYOUT( 8192,   512,  12, 12, 11, 704,  0, 30,448,  64, 30),
-	MARVELL_LAYOUT( 8192,   512,  16, 17, 16, 512,  0, 30,  0,  32, 30),
+	MARVELL_LAYOUT( 8192,   512,  8,  8,  8, 1024,  0, 30,  0, 160, 30),
+	MARVELL_LAYOUT( 8192,   512,  16, 16, 16, 512,  0, 30,  0,  32, 30),
 };
 
 /**
diff --git a/drivers/mtd/nand/spi/gigadevice.c b/drivers/mtd/nand/spi/gigadevice.c
index 987710e09441..6023cba748bb 100644
--- a/drivers/mtd/nand/spi/gigadevice.c
+++ b/drivers/mtd/nand/spi/gigadevice.c
@@ -186,7 +186,7 @@ static int gd5fxgq4uexxg_ecc_get_status(struct spinand_device *spinand,
 {
 	u8 status2;
 	struct spi_mem_op op = SPINAND_GET_FEATURE_OP(GD5FXGQXXEXXG_REG_STATUS2,
-						      &status2);
+						      spinand->scratchbuf);
 	int ret;
 
 	switch (status & STATUS_ECC_MASK) {
@@ -207,6 +207,7 @@ static int gd5fxgq4uexxg_ecc_get_status(struct spinand_device *spinand,
 		 * report the maximum of 4 in this case
 		 */
 		/* bits sorted this way (3...0): ECCS1,ECCS0,ECCSE1,ECCSE0 */
+		status2 = *(spinand->scratchbuf);
 		return ((status & STATUS_ECC_MASK) >> 2) |
 			((status2 & STATUS_ECC_MASK) >> 4);
 
@@ -228,7 +229,7 @@ static int gd5fxgq5xexxg_ecc_get_status(struct spinand_device *spinand,
 {
 	u8 status2;
 	struct spi_mem_op op = SPINAND_GET_FEATURE_OP(GD5FXGQXXEXXG_REG_STATUS2,
-						      &status2);
+						      spinand->scratchbuf);
 	int ret;
 
 	switch (status & STATUS_ECC_MASK) {
@@ -248,6 +249,7 @@ static int gd5fxgq5xexxg_ecc_get_status(struct spinand_device *spinand,
 		 * 1 ... 4 bits are flipped (and corrected)
 		 */
 		/* bits sorted this way (1...0): ECCSE1, ECCSE0 */
+		status2 = *(spinand->scratchbuf);
 		return ((status2 & STATUS_ECC_MASK) >> 4) + 1;
 
 	case STATUS_ECC_UNCOR_ERROR:
diff --git a/drivers/mtd/ubi/Kconfig b/drivers/mtd/ubi/Kconfig
index 2ed77b7b3fcb..7499a540121e 100644
--- a/drivers/mtd/ubi/Kconfig
+++ b/drivers/mtd/ubi/Kconfig
@@ -104,4 +104,13 @@ config MTD_UBI_BLOCK
 
 	   If in doubt, say "N".
 
+config MTD_UBI_FAULT_INJECTION
+	bool "Fault injection capability of UBI device"
+	default n
+	depends on FAULT_INJECTION_DEBUG_FS
+	help
+	   This option enables fault-injection support for UBI devices for
+	   testing purposes.
+
+	   If in doubt, say "N".
 endif # MTD_UBI
diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c
index 309a42aeaa4c..5c8fdcc088a0 100644
--- a/drivers/mtd/ubi/block.c
+++ b/drivers/mtd/ubi/block.c
@@ -348,6 +348,9 @@ static int calc_disk_capacity(struct ubi_volume_info *vi, u64 *disk_capacity)
 
 int ubiblock_create(struct ubi_volume_info *vi)
 {
+	struct queue_limits lim = {
+		.max_segments		= UBI_MAX_SG_COUNT,
+	};
 	struct ubiblock *dev;
 	struct gendisk *gd;
 	u64 disk_capacity;
@@ -393,7 +396,7 @@ int ubiblock_create(struct ubi_volume_info *vi)
 
 
 	/* Initialize the gendisk of this ubiblock device */
-	gd = blk_mq_alloc_disk(&dev->tag_set, dev);
+	gd = blk_mq_alloc_disk(&dev->tag_set, &lim, dev);
 	if (IS_ERR(gd)) {
 		ret = PTR_ERR(gd);
 		goto out_free_tags;
@@ -416,7 +419,6 @@ int ubiblock_create(struct ubi_volume_info *vi)
 	dev->gd = gd;
 
 	dev->rq = gd->queue;
-	blk_queue_max_segments(dev->rq, UBI_MAX_SG_COUNT);
 
 	list_add_tail(&dev->list, &ubiblock_devices);
 
@@ -434,7 +436,7 @@ out_remove_minor:
 	list_del(&dev->list);
 	idr_remove(&ubiblock_minor_idr, gd->first_minor);
 out_cleanup_disk:
-	put_disk(dev->gd);
+	put_disk(gd);
 out_free_tags:
 	blk_mq_free_tag_set(&dev->tag_set);
 out_free_dev:
diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c
index 27168f511d6d..d57f52bd2ff3 100644
--- a/drivers/mtd/ubi/debug.c
+++ b/drivers/mtd/ubi/debug.c
@@ -10,7 +10,37 @@
 #include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/seq_file.h>
+#include <linux/fault-inject.h>
+
+#ifdef CONFIG_MTD_UBI_FAULT_INJECTION
+static DECLARE_FAULT_ATTR(fault_eccerr_attr);
+static DECLARE_FAULT_ATTR(fault_bitflips_attr);
+static DECLARE_FAULT_ATTR(fault_read_failure_attr);
+static DECLARE_FAULT_ATTR(fault_write_failure_attr);
+static DECLARE_FAULT_ATTR(fault_erase_failure_attr);
+static DECLARE_FAULT_ATTR(fault_power_cut_attr);
+static DECLARE_FAULT_ATTR(fault_io_ff_attr);
+static DECLARE_FAULT_ATTR(fault_io_ff_bitflips_attr);
+static DECLARE_FAULT_ATTR(fault_bad_hdr_attr);
+static DECLARE_FAULT_ATTR(fault_bad_hdr_ebadmsg_attr);
+
+#define FAIL_ACTION(name, fault_attr)			\
+bool should_fail_##name(void)				\
+{							\
+	return should_fail(&fault_attr, 1);		\
+}
 
+FAIL_ACTION(eccerr,		fault_eccerr_attr)
+FAIL_ACTION(bitflips,		fault_bitflips_attr)
+FAIL_ACTION(read_failure,	fault_read_failure_attr)
+FAIL_ACTION(write_failure,	fault_write_failure_attr)
+FAIL_ACTION(erase_failure,	fault_erase_failure_attr)
+FAIL_ACTION(power_cut,		fault_power_cut_attr)
+FAIL_ACTION(io_ff,		fault_io_ff_attr)
+FAIL_ACTION(io_ff_bitflips,	fault_io_ff_bitflips_attr)
+FAIL_ACTION(bad_hdr,		fault_bad_hdr_attr)
+FAIL_ACTION(bad_hdr_ebadmsg,	fault_bad_hdr_ebadmsg_attr)
+#endif
 
 /**
  * ubi_dump_flash - dump a region of flash.
@@ -212,6 +242,52 @@ void ubi_dump_mkvol_req(const struct ubi_mkvol_req *req)
  */
 static struct dentry *dfs_rootdir;
 
+#ifdef CONFIG_MTD_UBI_FAULT_INJECTION
+static void dfs_create_fault_entry(struct dentry *parent)
+{
+	struct dentry *dir;
+
+	dir = debugfs_create_dir("fault_inject", parent);
+	if (IS_ERR_OR_NULL(dir)) {
+		int err = dir ? PTR_ERR(dir) : -ENODEV;
+
+		pr_warn("UBI error: cannot create \"fault_inject\" debugfs directory, error %d\n",
+			 err);
+		return;
+	}
+
+	fault_create_debugfs_attr("emulate_eccerr", dir,
+				  &fault_eccerr_attr);
+
+	fault_create_debugfs_attr("emulate_read_failure", dir,
+				  &fault_read_failure_attr);
+
+	fault_create_debugfs_attr("emulate_bitflips", dir,
+				  &fault_bitflips_attr);
+
+	fault_create_debugfs_attr("emulate_write_failure", dir,
+				  &fault_write_failure_attr);
+
+	fault_create_debugfs_attr("emulate_erase_failure", dir,
+				  &fault_erase_failure_attr);
+
+	fault_create_debugfs_attr("emulate_power_cut", dir,
+				  &fault_power_cut_attr);
+
+	fault_create_debugfs_attr("emulate_io_ff", dir,
+				  &fault_io_ff_attr);
+
+	fault_create_debugfs_attr("emulate_io_ff_bitflips", dir,
+				  &fault_io_ff_bitflips_attr);
+
+	fault_create_debugfs_attr("emulate_bad_hdr", dir,
+				  &fault_bad_hdr_attr);
+
+	fault_create_debugfs_attr("emulate_bad_hdr_ebadmsg", dir,
+				  &fault_bad_hdr_ebadmsg_attr);
+}
+#endif
+
 /**
  * ubi_debugfs_init - create UBI debugfs directory.
  *
@@ -232,6 +308,10 @@ int ubi_debugfs_init(void)
 		return err;
 	}
 
+#ifdef CONFIG_MTD_UBI_FAULT_INJECTION
+	dfs_create_fault_entry(dfs_rootdir);
+#endif
+
 	return 0;
 }
 
@@ -252,7 +332,7 @@ static ssize_t dfs_file_read(struct file *file, char __user *user_buf,
 	struct dentry *dent = file->f_path.dentry;
 	struct ubi_device *ubi;
 	struct ubi_debug_info *d;
-	char buf[8];
+	char buf[16];
 	int val;
 
 	ubi = ubi_get_device(ubi_num);
@@ -272,7 +352,12 @@ static ssize_t dfs_file_read(struct file *file, char __user *user_buf,
 		val = d->emulate_bitflips;
 	else if (dent == d->dfs_emulate_io_failures)
 		val = d->emulate_io_failures;
-	else if (dent == d->dfs_emulate_power_cut) {
+	else if (dent == d->dfs_emulate_failures) {
+		snprintf(buf, sizeof(buf), "0x%04x\n", d->emulate_failures);
+		count = simple_read_from_buffer(user_buf, count, ppos,
+						buf, strlen(buf));
+		goto out;
+	} else if (dent == d->dfs_emulate_power_cut) {
 		snprintf(buf, sizeof(buf), "%u\n", d->emulate_power_cut);
 		count = simple_read_from_buffer(user_buf, count, ppos,
 						buf, strlen(buf));
@@ -287,8 +372,7 @@ static ssize_t dfs_file_read(struct file *file, char __user *user_buf,
 		count = simple_read_from_buffer(user_buf, count, ppos,
 						buf, strlen(buf));
 		goto out;
-	}
-	else {
+	} else {
 		count = -EINVAL;
 		goto out;
 	}
@@ -316,7 +400,7 @@ static ssize_t dfs_file_write(struct file *file, const char __user *user_buf,
 	struct ubi_device *ubi;
 	struct ubi_debug_info *d;
 	size_t buf_size;
-	char buf[8] = {0};
+	char buf[16] = {0};
 	int val;
 
 	ubi = ubi_get_device(ubi_num);
@@ -330,7 +414,11 @@ static ssize_t dfs_file_write(struct file *file, const char __user *user_buf,
 		goto out;
 	}
 
-	if (dent == d->dfs_power_cut_min) {
+	if (dent == d->dfs_emulate_failures) {
+		if (kstrtouint(buf, 0, &d->emulate_failures) != 0)
+			count = -EINVAL;
+		goto out;
+	} else if (dent == d->dfs_power_cut_min) {
 		if (kstrtouint(buf, 0, &d->power_cut_min) != 0)
 			count = -EINVAL;
 		goto out;
@@ -559,6 +647,12 @@ int ubi_debugfs_init_dev(struct ubi_device *ubi)
 	debugfs_create_file("detailed_erase_block_info", S_IRUSR, d->dfs_dir,
 			    (void *)ubi_num, &eraseblk_count_fops);
 
+#ifdef CONFIG_MTD_UBI_FAULT_INJECTION
+	d->dfs_emulate_failures = debugfs_create_file("emulate_failures",
+						       mode, d->dfs_dir,
+						       (void *)ubi_num,
+						       &dfs_fops);
+#endif
 	return 0;
 }
 
@@ -600,7 +694,5 @@ int ubi_dbg_power_cut(struct ubi_device *ubi, int caller)
 	if (ubi->dbg.power_cut_counter)
 		return 0;
 
-	ubi_msg(ubi, "XXXXXXXXXXXXXXX emulating a power cut XXXXXXXXXXXXXXXX");
-	ubi_ro_mode(ubi);
 	return 1;
 }
diff --git a/drivers/mtd/ubi/debug.h b/drivers/mtd/ubi/debug.h
index 23676f32b681..b2fd97548808 100644
--- a/drivers/mtd/ubi/debug.h
+++ b/drivers/mtd/ubi/debug.h
@@ -53,56 +53,315 @@ int ubi_debugfs_init_dev(struct ubi_device *ubi);
 void ubi_debugfs_exit_dev(struct ubi_device *ubi);
 
 /**
- * ubi_dbg_is_bgt_disabled - if the background thread is disabled.
+ * The following function is a legacy implementation of UBI fault-injection
+ * hook. When using more powerful fault injection capabilities, the legacy
+ * fault injection interface should be retained.
+ */
+int ubi_dbg_power_cut(struct ubi_device *ubi, int caller);
+
+static inline int ubi_dbg_bitflip(const struct ubi_device *ubi)
+{
+	if (ubi->dbg.emulate_bitflips)
+		return !get_random_u32_below(200);
+	return 0;
+}
+
+static inline int ubi_dbg_write_failure(const struct ubi_device *ubi)
+{
+	if (ubi->dbg.emulate_io_failures)
+		return !get_random_u32_below(500);
+	return 0;
+}
+
+static inline int ubi_dbg_erase_failure(const struct ubi_device *ubi)
+{
+	if (ubi->dbg.emulate_io_failures)
+		return !get_random_u32_below(400);
+	return 0;
+}
+
+/**
+ * MASK_XXX: Mask for emulate_failures in ubi_debug_info.The mask is used to
+ * precisely control the type and process of fault injection.
+ */
+/* Emulate a power cut when writing EC/VID header */
+#define MASK_POWER_CUT_EC			(1 << 0)
+#define MASK_POWER_CUT_VID			(1 << 1)
+/* Emulate a power cut when writing data*/
+#define MASK_POWER_CUT_DATA			(1 << 2)
+/* Emulate bit-flips */
+#define MASK_BITFLIPS				(1 << 3)
+/* Emulate ecc error */
+#define MASK_ECCERR				(1 << 4)
+/* Emulates -EIO during data read */
+#define MASK_READ_FAILURE			(1 << 5)
+#define MASK_READ_FAILURE_EC			(1 << 6)
+#define MASK_READ_FAILURE_VID			(1 << 7)
+/* Emulates -EIO during data write */
+#define MASK_WRITE_FAILURE			(1 << 8)
+/* Emulates -EIO during erase a PEB*/
+#define MASK_ERASE_FAILURE			(1 << 9)
+/* Return UBI_IO_FF when reading EC/VID header */
+#define MASK_IO_FF_EC				(1 << 10)
+#define MASK_IO_FF_VID				(1 << 11)
+/* Return UBI_IO_FF_BITFLIPS when reading EC/VID header */
+#define MASK_IO_FF_BITFLIPS_EC			(1 << 12)
+#define MASK_IO_FF_BITFLIPS_VID			(1 << 13)
+/* Return UBI_IO_BAD_HDR when reading EC/VID header */
+#define MASK_BAD_HDR_EC				(1 << 14)
+#define MASK_BAD_HDR_VID			(1 << 15)
+/* Return UBI_IO_BAD_HDR_EBADMSG when reading EC/VID header */
+#define MASK_BAD_HDR_EBADMSG_EC			(1 << 16)
+#define MASK_BAD_HDR_EBADMSG_VID		(1 << 17)
+
+#ifdef CONFIG_MTD_UBI_FAULT_INJECTION
+
+extern bool should_fail_eccerr(void);
+extern bool should_fail_bitflips(void);
+extern bool should_fail_read_failure(void);
+extern bool should_fail_write_failure(void);
+extern bool should_fail_erase_failure(void);
+extern bool should_fail_power_cut(void);
+extern bool should_fail_io_ff(void);
+extern bool should_fail_io_ff_bitflips(void);
+extern bool should_fail_bad_hdr(void);
+extern bool should_fail_bad_hdr_ebadmsg(void);
+
+static inline bool ubi_dbg_fail_bitflip(const struct ubi_device *ubi)
+{
+	if (ubi->dbg.emulate_failures & MASK_BITFLIPS)
+		return should_fail_bitflips();
+	return false;
+}
+
+static inline bool ubi_dbg_fail_write(const struct ubi_device *ubi)
+{
+	if (ubi->dbg.emulate_failures & MASK_WRITE_FAILURE)
+		return should_fail_write_failure();
+	return false;
+}
+
+static inline bool ubi_dbg_fail_erase(const struct ubi_device *ubi)
+{
+	if (ubi->dbg.emulate_failures & MASK_ERASE_FAILURE)
+		return should_fail_erase_failure();
+	return false;
+}
+
+static inline bool ubi_dbg_fail_power_cut(const struct ubi_device *ubi,
+					  unsigned int caller)
+{
+	if (ubi->dbg.emulate_failures & caller)
+		return should_fail_power_cut();
+	return false;
+}
+
+static inline bool ubi_dbg_fail_read(const struct ubi_device *ubi,
+				     unsigned int caller)
+{
+	if (ubi->dbg.emulate_failures & caller)
+		return should_fail_read_failure();
+	return false;
+}
+
+static inline bool ubi_dbg_fail_eccerr(const struct ubi_device *ubi)
+{
+	if (ubi->dbg.emulate_failures & MASK_ECCERR)
+		return should_fail_eccerr();
+	return false;
+}
+
+static inline bool ubi_dbg_fail_ff(const struct ubi_device *ubi,
+				   unsigned int caller)
+{
+	if (ubi->dbg.emulate_failures & caller)
+		return should_fail_io_ff();
+	return false;
+}
+
+static inline bool ubi_dbg_fail_ff_bitflips(const struct ubi_device *ubi,
+					    unsigned int caller)
+{
+	if (ubi->dbg.emulate_failures & caller)
+		return should_fail_io_ff_bitflips();
+	return false;
+}
+
+static inline bool ubi_dbg_fail_bad_hdr(const struct ubi_device *ubi,
+					 unsigned int caller)
+{
+	if (ubi->dbg.emulate_failures & caller)
+		return should_fail_bad_hdr();
+	return false;
+}
+
+static inline bool ubi_dbg_fail_bad_hdr_ebadmsg(const struct ubi_device *ubi,
+						 unsigned int caller)
+{
+	if (ubi->dbg.emulate_failures & caller)
+		return should_fail_bad_hdr_ebadmsg();
+	return false;
+}
+#else /* CONFIG_MTD_UBI_FAULT_INJECTION */
+
+#define ubi_dbg_fail_bitflip(u)             false
+#define ubi_dbg_fail_write(u)               false
+#define ubi_dbg_fail_erase(u)               false
+#define ubi_dbg_fail_power_cut(u, c)        false
+#define ubi_dbg_fail_read(u, c)             false
+#define ubi_dbg_fail_eccerr(u)              false
+#define ubi_dbg_fail_ff(u, c)               false
+#define ubi_dbg_fail_ff_bitflips(u, v)      false
+#define ubi_dbg_fail_bad_hdr(u, c)          false
+#define ubi_dbg_fail_bad_hdr_ebadmsg(u, c)  false
+
+#endif
+
+/**
+ * ubi_dbg_is_power_cut - if it is time to emulate power cut.
  * @ubi: UBI device description object
  *
- * Returns non-zero if the UBI background thread is disabled for testing
- * purposes.
+ * Returns true if power cut should be emulated, otherwise returns false.
  */
-static inline int ubi_dbg_is_bgt_disabled(const struct ubi_device *ubi)
+static inline bool ubi_dbg_is_power_cut(struct ubi_device *ubi,
+					unsigned int caller)
 {
-	return ubi->dbg.disable_bgt;
+	if (ubi_dbg_power_cut(ubi, caller))
+		return true;
+	return ubi_dbg_fail_power_cut(ubi, caller);
 }
 
 /**
  * ubi_dbg_is_bitflip - if it is time to emulate a bit-flip.
  * @ubi: UBI device description object
  *
- * Returns non-zero if a bit-flip should be emulated, otherwise returns zero.
+ * Returns true if a bit-flip should be emulated, otherwise returns false.
  */
-static inline int ubi_dbg_is_bitflip(const struct ubi_device *ubi)
+static inline bool ubi_dbg_is_bitflip(const struct ubi_device *ubi)
 {
-	if (ubi->dbg.emulate_bitflips)
-		return !get_random_u32_below(200);
-	return 0;
+	if (ubi_dbg_bitflip(ubi))
+		return true;
+	return ubi_dbg_fail_bitflip(ubi);
 }
 
 /**
  * ubi_dbg_is_write_failure - if it is time to emulate a write failure.
  * @ubi: UBI device description object
  *
- * Returns non-zero if a write failure should be emulated, otherwise returns
- * zero.
+ * Returns true if a write failure should be emulated, otherwise returns
+ * false.
  */
-static inline int ubi_dbg_is_write_failure(const struct ubi_device *ubi)
+static inline bool ubi_dbg_is_write_failure(const struct ubi_device *ubi)
 {
-	if (ubi->dbg.emulate_io_failures)
-		return !get_random_u32_below(500);
-	return 0;
+	if (ubi_dbg_write_failure(ubi))
+		return true;
+	return ubi_dbg_fail_write(ubi);
 }
 
 /**
  * ubi_dbg_is_erase_failure - if its time to emulate an erase failure.
  * @ubi: UBI device description object
  *
- * Returns non-zero if an erase failure should be emulated, otherwise returns
- * zero.
+ * Returns true if an erase failure should be emulated, otherwise returns
+ * false.
  */
-static inline int ubi_dbg_is_erase_failure(const struct ubi_device *ubi)
+static inline bool ubi_dbg_is_erase_failure(const struct ubi_device *ubi)
 {
-	if (ubi->dbg.emulate_io_failures)
-		return !get_random_u32_below(400);
-	return 0;
+	if (ubi_dbg_erase_failure(ubi))
+		return true;
+	return ubi_dbg_fail_erase(ubi);
+}
+
+/**
+ * ubi_dbg_is_eccerr - if it is time to emulate ECC error.
+ * @ubi: UBI device description object
+ *
+ * Returns true if a ECC error should be emulated, otherwise returns false.
+ */
+static inline bool ubi_dbg_is_eccerr(const struct ubi_device *ubi)
+{
+	return ubi_dbg_fail_eccerr(ubi);
+}
+
+/**
+ * ubi_dbg_is_read_failure - if it is time to emulate a read failure.
+ * @ubi: UBI device description object
+ *
+ * Returns true if a read failure should be emulated, otherwise returns
+ * false.
+ */
+static inline bool ubi_dbg_is_read_failure(const struct ubi_device *ubi,
+					   unsigned int caller)
+{
+	return ubi_dbg_fail_read(ubi, caller);
+}
+
+/**
+ * ubi_dbg_is_ff - if it is time to emulate that read region is only 0xFF.
+ * @ubi: UBI device description object
+ *
+ * Returns true if read region should be emulated 0xFF, otherwise
+ * returns false.
+ */
+static inline bool ubi_dbg_is_ff(const struct ubi_device *ubi,
+				 unsigned int caller)
+{
+	return ubi_dbg_fail_ff(ubi, caller);
+}
+
+/**
+ * ubi_dbg_is_ff_bitflips - if it is time to emulate that read region is only 0xFF
+ * with error reported by the MTD driver
+ *
+ * @ubi: UBI device description object
+ *
+ * Returns true if read region should be emulated 0xFF and error
+ * reported by the MTD driver, otherwise returns false.
+ */
+static inline bool ubi_dbg_is_ff_bitflips(const struct ubi_device *ubi,
+					  unsigned int caller)
+{
+	return ubi_dbg_fail_ff_bitflips(ubi, caller);
+}
+
+/**
+ * ubi_dbg_is_bad_hdr - if it is time to emulate a bad header
+ * @ubi: UBI device description object
+ *
+ * Returns true if a bad header error should be emulated, otherwise
+ * returns false.
+ */
+static inline bool ubi_dbg_is_bad_hdr(const struct ubi_device *ubi,
+				      unsigned int caller)
+{
+	return ubi_dbg_fail_bad_hdr(ubi, caller);
+}
+
+/**
+ * ubi_dbg_is_bad_hdr_ebadmsg - if it is time to emulate a bad header with
+ * ECC error.
+ *
+ * @ubi: UBI device description object
+ *
+ * Returns true if a bad header with ECC error should be emulated, otherwise
+ * returns false.
+ */
+static inline bool ubi_dbg_is_bad_hdr_ebadmsg(const struct ubi_device *ubi,
+					      unsigned int caller)
+{
+	return ubi_dbg_fail_bad_hdr_ebadmsg(ubi, caller);
+}
+
+/**
+ * ubi_dbg_is_bgt_disabled - if the background thread is disabled.
+ * @ubi: UBI device description object
+ *
+ * Returns non-zero if the UBI background thread is disabled for testing
+ * purposes.
+ */
+static inline int ubi_dbg_is_bgt_disabled(const struct ubi_device *ubi)
+{
+	return ubi->dbg.disable_bgt;
 }
 
 static inline int ubi_dbg_chk_io(const struct ubi_device *ubi)
@@ -125,5 +384,4 @@ static inline void ubi_enable_dbg_chk_fastmap(struct ubi_device *ubi)
 	ubi->dbg.chk_fastmap = 1;
 }
 
-int ubi_dbg_power_cut(struct ubi_device *ubi, int caller);
 #endif /* !__UBI_DEBUG_H__ */
diff --git a/drivers/mtd/ubi/io.c b/drivers/mtd/ubi/io.c
index 01b644861253..a4999bce435f 100644
--- a/drivers/mtd/ubi/io.c
+++ b/drivers/mtd/ubi/io.c
@@ -195,7 +195,19 @@ retry:
 
 		if (ubi_dbg_is_bitflip(ubi)) {
 			dbg_gen("bit-flip (emulated)");
-			err = UBI_IO_BITFLIPS;
+			return UBI_IO_BITFLIPS;
+		}
+
+		if (ubi_dbg_is_read_failure(ubi, MASK_READ_FAILURE)) {
+			ubi_warn(ubi, "cannot read %d bytes from PEB %d:%d (emulated)",
+				 len, pnum, offset);
+			return -EIO;
+		}
+
+		if (ubi_dbg_is_eccerr(ubi)) {
+			ubi_warn(ubi, "ECC error (emulated) while reading %d bytes from PEB %d:%d, read %zd bytes",
+				 len, pnum, offset, read);
+			return -EBADMSG;
 		}
 	}
 
@@ -782,7 +794,36 @@ int ubi_io_read_ec_hdr(struct ubi_device *ubi, int pnum,
 	 * If there was %-EBADMSG, but the header CRC is still OK, report about
 	 * a bit-flip to force scrubbing on this PEB.
 	 */
-	return read_err ? UBI_IO_BITFLIPS : 0;
+	if (read_err)
+		return UBI_IO_BITFLIPS;
+
+	if (ubi_dbg_is_read_failure(ubi, MASK_READ_FAILURE_EC)) {
+		ubi_warn(ubi, "cannot read EC header from PEB %d (emulated)",
+			 pnum);
+		return -EIO;
+	}
+
+	if (ubi_dbg_is_ff(ubi, MASK_IO_FF_EC)) {
+		ubi_warn(ubi, "bit-all-ff (emulated)");
+		return UBI_IO_FF;
+	}
+
+	if (ubi_dbg_is_ff_bitflips(ubi, MASK_IO_FF_BITFLIPS_EC)) {
+		ubi_warn(ubi, "bit-all-ff with error reported by MTD driver (emulated)");
+		return UBI_IO_FF_BITFLIPS;
+	}
+
+	if (ubi_dbg_is_bad_hdr(ubi, MASK_BAD_HDR_EC)) {
+		ubi_warn(ubi, "bad_hdr (emulated)");
+		return UBI_IO_BAD_HDR;
+	}
+
+	if (ubi_dbg_is_bad_hdr_ebadmsg(ubi, MASK_BAD_HDR_EBADMSG_EC)) {
+		ubi_warn(ubi, "bad_hdr with ECC error (emulated)");
+		return UBI_IO_BAD_HDR_EBADMSG;
+	}
+
+	return 0;
 }
 
 /**
@@ -821,8 +862,11 @@ int ubi_io_write_ec_hdr(struct ubi_device *ubi, int pnum,
 	if (err)
 		return err;
 
-	if (ubi_dbg_power_cut(ubi, POWER_CUT_EC_WRITE))
+	if (ubi_dbg_is_power_cut(ubi, MASK_POWER_CUT_EC)) {
+		ubi_warn(ubi, "emulating a power cut when writing EC header");
+		ubi_ro_mode(ubi);
 		return -EROFS;
+	}
 
 	err = ubi_io_write(ubi, ec_hdr, pnum, 0, ubi->ec_hdr_alsize);
 	return err;
@@ -1029,7 +1073,36 @@ int ubi_io_read_vid_hdr(struct ubi_device *ubi, int pnum,
 		return -EINVAL;
 	}
 
-	return read_err ? UBI_IO_BITFLIPS : 0;
+	if (read_err)
+		return UBI_IO_BITFLIPS;
+
+	if (ubi_dbg_is_read_failure(ubi, MASK_READ_FAILURE_VID)) {
+		ubi_warn(ubi, "cannot read VID header from PEB %d (emulated)",
+			 pnum);
+		return -EIO;
+	}
+
+	if (ubi_dbg_is_ff(ubi, MASK_IO_FF_VID)) {
+		ubi_warn(ubi, "bit-all-ff (emulated)");
+		return UBI_IO_FF;
+	}
+
+	if (ubi_dbg_is_ff_bitflips(ubi, MASK_IO_FF_BITFLIPS_VID)) {
+		ubi_warn(ubi, "bit-all-ff with error reported by MTD driver (emulated)");
+		return UBI_IO_FF_BITFLIPS;
+	}
+
+	if (ubi_dbg_is_bad_hdr(ubi, MASK_BAD_HDR_VID)) {
+		ubi_warn(ubi, "bad_hdr (emulated)");
+		return UBI_IO_BAD_HDR;
+	}
+
+	if (ubi_dbg_is_bad_hdr_ebadmsg(ubi, MASK_BAD_HDR_EBADMSG_VID)) {
+		ubi_warn(ubi, "bad_hdr with ECC error (emulated)");
+		return UBI_IO_BAD_HDR_EBADMSG;
+	}
+
+	return 0;
 }
 
 /**
@@ -1071,8 +1144,11 @@ int ubi_io_write_vid_hdr(struct ubi_device *ubi, int pnum,
 	if (err)
 		return err;
 
-	if (ubi_dbg_power_cut(ubi, POWER_CUT_VID_WRITE))
+	if (ubi_dbg_is_power_cut(ubi, MASK_POWER_CUT_VID)) {
+		ubi_warn(ubi, "emulating a power cut when writing VID header");
+		ubi_ro_mode(ubi);
 		return -EROFS;
+	}
 
 	err = ubi_io_write(ubi, p, pnum, ubi->vid_hdr_aloffset,
 			   ubi->vid_hdr_alsize);
diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h
index a5ec566df0d7..0b42bb45dd84 100644
--- a/drivers/mtd/ubi/ubi.h
+++ b/drivers/mtd/ubi/ubi.h
@@ -145,17 +145,6 @@ enum {
 	UBI_BAD_FASTMAP,
 };
 
-/*
- * Flags for emulate_power_cut in ubi_debug_info
- *
- * POWER_CUT_EC_WRITE: Emulate a power cut when writing an EC header
- * POWER_CUT_VID_WRITE: Emulate a power cut when writing a VID header
- */
-enum {
-	POWER_CUT_EC_WRITE = 0x01,
-	POWER_CUT_VID_WRITE = 0x02,
-};
-
 /**
  * struct ubi_vid_io_buf - VID buffer used to read/write VID info to/from the
  *			   flash.
@@ -404,6 +393,7 @@ struct ubi_volume_desc {
  * @power_cut_counter: count down for writes left until emulated power cut
  * @power_cut_min: minimum number of writes before emulating a power cut
  * @power_cut_max: maximum number of writes until emulating a power cut
+ * @emulate_failures: emulate failures for testing purposes
  * @dfs_dir_name: name of debugfs directory containing files of this UBI device
  * @dfs_dir: direntry object of the UBI device debugfs directory
  * @dfs_chk_gen: debugfs knob to enable UBI general extra checks
@@ -415,6 +405,7 @@ struct ubi_volume_desc {
  * @dfs_emulate_power_cut: debugfs knob to emulate power cuts
  * @dfs_power_cut_min: debugfs knob for minimum writes before power cut
  * @dfs_power_cut_max: debugfs knob for maximum writes until power cut
+ * @dfs_emulate_failures: debugfs entry to control the fault injection type
  */
 struct ubi_debug_info {
 	unsigned int chk_gen:1;
@@ -427,6 +418,7 @@ struct ubi_debug_info {
 	unsigned int power_cut_counter;
 	unsigned int power_cut_min;
 	unsigned int power_cut_max;
+	unsigned int emulate_failures;
 	char dfs_dir_name[UBI_DFS_DIR_LEN + 1];
 	struct dentry *dfs_dir;
 	struct dentry *dfs_chk_gen;
@@ -438,6 +430,7 @@ struct ubi_debug_info {
 	struct dentry *dfs_emulate_power_cut;
 	struct dentry *dfs_power_cut_min;
 	struct dentry *dfs_power_cut_max;
+	struct dentry *dfs_emulate_failures;
 };
 
 /**
@@ -1130,6 +1123,19 @@ static inline struct ubi_vid_hdr *ubi_get_vid_hdr(struct ubi_vid_io_buf *vidb)
 	return vidb->hdr;
 }
 
+/**
+ * ubi_ro_mode - switch to read-only mode.
+ * @ubi: UBI device description object
+ */
+static inline void ubi_ro_mode(struct ubi_device *ubi)
+{
+	if (!ubi->ro_mode) {
+		ubi->ro_mode = 1;
+		ubi_warn(ubi, "switch to read-only mode");
+		dump_stack();
+	}
+}
+
 /*
  * This function is equivalent to 'ubi_io_read()', but @offset is relative to
  * the beginning of the logical eraseblock, not to the beginning of the
@@ -1151,20 +1157,13 @@ static inline int ubi_io_write_data(struct ubi_device *ubi, const void *buf,
 				    int pnum, int offset, int len)
 {
 	ubi_assert(offset >= 0);
-	return ubi_io_write(ubi, buf, pnum, offset + ubi->leb_start, len);
-}
 
-/**
- * ubi_ro_mode - switch to read-only mode.
- * @ubi: UBI device description object
- */
-static inline void ubi_ro_mode(struct ubi_device *ubi)
-{
-	if (!ubi->ro_mode) {
-		ubi->ro_mode = 1;
-		ubi_warn(ubi, "switch to read-only mode");
-		dump_stack();
+	if (ubi_dbg_power_cut(ubi, MASK_POWER_CUT_DATA)) {
+		ubi_warn(ubi, "XXXXX emulating a power cut when writing data XXXXX");
+		ubi_ro_mode(ubi);
+		return -EROFS;
 	}
+	return ubi_io_write(ubi, buf, pnum, offset + ubi->leb_start, len);
 }
 
 /**
diff --git a/drivers/mux/mmio.c b/drivers/mux/mmio.c
index fd1d121a584b..30a952c34365 100644
--- a/drivers/mux/mmio.c
+++ b/drivers/mux/mmio.c
@@ -44,15 +44,20 @@ static int mux_mmio_probe(struct platform_device *pdev)
 	int ret;
 	int i;
 
-	if (of_device_is_compatible(np, "mmio-mux"))
+	if (of_device_is_compatible(np, "mmio-mux")) {
 		regmap = syscon_node_to_regmap(np->parent);
-	else
-		regmap = dev_get_regmap(dev->parent, NULL) ?: ERR_PTR(-ENODEV);
-	if (IS_ERR(regmap)) {
-		ret = PTR_ERR(regmap);
-		dev_err(dev, "failed to get regmap: %d\n", ret);
-		return ret;
+	} else {
+		regmap = device_node_to_regmap(np);
+		/* Fallback to checking the parent node on "real" errors. */
+		if (IS_ERR(regmap) && regmap != ERR_PTR(-EPROBE_DEFER)) {
+			regmap = dev_get_regmap(dev->parent, NULL);
+			if (!regmap)
+				regmap = ERR_PTR(-ENODEV);
+		}
 	}
+	if (IS_ERR(regmap))
+		return dev_err_probe(dev, PTR_ERR(regmap),
+				     "failed to get regmap\n");
 
 	ret = of_property_count_u32_elems(np, "mux-reg-masks");
 	if (ret == 0 || ret % 2)
diff --git a/drivers/net/amt.c b/drivers/net/amt.c
index 53415e83821c..68e79b1272f6 100644
--- a/drivers/net/amt.c
+++ b/drivers/net/amt.c
@@ -11,7 +11,7 @@
 #include <linux/net.h>
 #include <linux/igmp.h>
 #include <linux/workqueue.h>
-#include <net/sch_generic.h>
+#include <net/pkt_sched.h>
 #include <net/net_namespace.h>
 #include <net/ip.h>
 #include <net/udp.h>
@@ -80,11 +80,11 @@ static struct mld2_grec mldv2_zero_grec;
 
 static struct amt_skb_cb *amt_skb_cb(struct sk_buff *skb)
 {
-	BUILD_BUG_ON(sizeof(struct amt_skb_cb) + sizeof(struct qdisc_skb_cb) >
+	BUILD_BUG_ON(sizeof(struct amt_skb_cb) + sizeof(struct tc_skb_cb) >
 		     sizeof_field(struct sk_buff, cb));
 
 	return (struct amt_skb_cb *)((void *)skb->cb +
-		sizeof(struct qdisc_skb_cb));
+		sizeof(struct tc_skb_cb));
 }
 
 static void __amt_source_gc_work(void)
diff --git a/drivers/net/arcnet/arc-rawmode.c b/drivers/net/arcnet/arc-rawmode.c
index 8c651fdee039..57f1729066f2 100644
--- a/drivers/net/arcnet/arc-rawmode.c
+++ b/drivers/net/arcnet/arc-rawmode.c
@@ -186,4 +186,5 @@ static void __exit arcnet_raw_exit(void)
 module_init(arcnet_raw_init);
 module_exit(arcnet_raw_exit);
 
+MODULE_DESCRIPTION("ARCnet raw mode packet interface module");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c
index 8c3ccc7c83cd..53d10a04d1bd 100644
--- a/drivers/net/arcnet/arc-rimi.c
+++ b/drivers/net/arcnet/arc-rimi.c
@@ -312,6 +312,7 @@ module_param(node, int, 0);
 module_param(io, int, 0);
 module_param(irq, int, 0);
 module_param_string(device, device, sizeof(device), 0);
+MODULE_DESCRIPTION("ARCnet COM90xx RIM I chipset driver");
 MODULE_LICENSE("GPL");
 
 static struct net_device *my_dev;
diff --git a/drivers/net/arcnet/capmode.c b/drivers/net/arcnet/capmode.c
index c09b567845e1..7a0a79973769 100644
--- a/drivers/net/arcnet/capmode.c
+++ b/drivers/net/arcnet/capmode.c
@@ -265,4 +265,5 @@ static void __exit capmode_module_exit(void)
 module_init(capmode_module_init);
 module_exit(capmode_module_exit);
 
+MODULE_DESCRIPTION("ARCnet CAP mode packet interface module");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c
index 7b5c8bb02f11..c5e571ec94c9 100644
--- a/drivers/net/arcnet/com20020-pci.c
+++ b/drivers/net/arcnet/com20020-pci.c
@@ -61,6 +61,7 @@ module_param(timeout, int, 0);
 module_param(backplane, int, 0);
 module_param(clockp, int, 0);
 module_param(clockm, int, 0);
+MODULE_DESCRIPTION("ARCnet COM20020 chipset PCI driver");
 MODULE_LICENSE("GPL");
 
 static void led_tx_set(struct led_classdev *led_cdev,
diff --git a/drivers/net/arcnet/com20020.c b/drivers/net/arcnet/com20020.c
index 06e1651b594b..a0053e3992a3 100644
--- a/drivers/net/arcnet/com20020.c
+++ b/drivers/net/arcnet/com20020.c
@@ -399,6 +399,7 @@ EXPORT_SYMBOL(com20020_found);
 EXPORT_SYMBOL(com20020_netdev_ops);
 #endif
 
+MODULE_DESCRIPTION("ARCnet COM20020 chipset core driver");
 MODULE_LICENSE("GPL");
 
 #ifdef MODULE
diff --git a/drivers/net/arcnet/com20020_cs.c b/drivers/net/arcnet/com20020_cs.c
index dc3253b318da..75f08aa7528b 100644
--- a/drivers/net/arcnet/com20020_cs.c
+++ b/drivers/net/arcnet/com20020_cs.c
@@ -97,6 +97,7 @@ module_param(backplane, int, 0);
 module_param(clockp, int, 0);
 module_param(clockm, int, 0);
 
+MODULE_DESCRIPTION("ARCnet COM20020 chipset PCMCIA driver");
 MODULE_LICENSE("GPL");
 
 /*====================================================================*/
diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c
index 37b47749fc8b..3b463fbc6402 100644
--- a/drivers/net/arcnet/com90io.c
+++ b/drivers/net/arcnet/com90io.c
@@ -350,6 +350,7 @@ static char device[9];		/* use eg. device=arc1 to change name */
 module_param_hw(io, int, ioport, 0);
 module_param_hw(irq, int, irq, 0);
 module_param_string(device, device, sizeof(device), 0);
+MODULE_DESCRIPTION("ARCnet COM90xx IO mapped chipset driver");
 MODULE_LICENSE("GPL");
 
 #ifndef MODULE
diff --git a/drivers/net/arcnet/com90xx.c b/drivers/net/arcnet/com90xx.c
index f49dae194284..b3b287c16561 100644
--- a/drivers/net/arcnet/com90xx.c
+++ b/drivers/net/arcnet/com90xx.c
@@ -645,6 +645,7 @@ static void com90xx_copy_from_card(struct net_device *dev, int bufnum,
 	TIME(dev, "memcpy_fromio", count, memcpy_fromio(buf, memaddr, count));
 }
 
+MODULE_DESCRIPTION("ARCnet COM90xx normal chipset driver");
 MODULE_LICENSE("GPL");
 
 static int __init com90xx_init(void)
diff --git a/drivers/net/arcnet/rfc1051.c b/drivers/net/arcnet/rfc1051.c
index a7752a5b647f..46519ca63a0a 100644
--- a/drivers/net/arcnet/rfc1051.c
+++ b/drivers/net/arcnet/rfc1051.c
@@ -78,6 +78,7 @@ static void __exit arcnet_rfc1051_exit(void)
 module_init(arcnet_rfc1051_init);
 module_exit(arcnet_rfc1051_exit);
 
+MODULE_DESCRIPTION("ARCNet packet format (RFC 1051) module");
 MODULE_LICENSE("GPL");
 
 /* Determine a packet's protocol ID.
diff --git a/drivers/net/arcnet/rfc1201.c b/drivers/net/arcnet/rfc1201.c
index a4c856282674..0edf35d971c5 100644
--- a/drivers/net/arcnet/rfc1201.c
+++ b/drivers/net/arcnet/rfc1201.c
@@ -35,6 +35,7 @@
 
 #include "arcdevice.h"
 
+MODULE_DESCRIPTION("ARCNet packet format (RFC 1201) module");
 MODULE_LICENSE("GPL");
 
 static __be16 type_trans(struct sk_buff *skb, struct net_device *dev);
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 4e0600c7b050..cd0683bcca03 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1811,7 +1811,7 @@ void bond_xdp_set_features(struct net_device *bond_dev)
 
 	ASSERT_RTNL();
 
-	if (!bond_xdp_check(bond)) {
+	if (!bond_xdp_check(bond) || !bond_has_slaves(bond)) {
 		xdp_clear_features_flag(bond_dev);
 		return;
 	}
@@ -1819,6 +1819,8 @@ void bond_xdp_set_features(struct net_device *bond_dev)
 	bond_for_each_slave(bond, slave, iter)
 		val &= slave->dev->xdp_features;
 
+	val &= ~NETDEV_XDP_ACT_XSK_ZEROCOPY;
+
 	xdp_set_features_flag(bond_dev, val);
 }
 
@@ -5909,9 +5911,6 @@ void bond_setup(struct net_device *bond_dev)
 	if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
 		bond_dev->features |= BOND_XFRM_FEATURES;
 #endif /* CONFIG_XFRM_OFFLOAD */
-
-	if (bond_xdp_check(bond))
-		bond_dev->xdp_features = NETDEV_XDP_ACT_MASK;
 }
 
 /* Destroy a bonding device.
diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c
index f44ba2600415..e2ec69aa46e5 100644
--- a/drivers/net/can/c_can/c_can_platform.c
+++ b/drivers/net/can/c_can/c_can_platform.c
@@ -30,9 +30,9 @@
 #include <linux/io.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/property.h>
 #include <linux/clk.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/mfd/syscon.h>
 #include <linux/regmap.h>
 
@@ -259,22 +259,13 @@ static int c_can_plat_probe(struct platform_device *pdev)
 	void __iomem *addr;
 	struct net_device *dev;
 	struct c_can_priv *priv;
-	const struct of_device_id *match;
 	struct resource *mem;
 	int irq;
 	struct clk *clk;
 	const struct c_can_driver_data *drvdata;
 	struct device_node *np = pdev->dev.of_node;
 
-	match = of_match_device(c_can_of_table, &pdev->dev);
-	if (match) {
-		drvdata = match->data;
-	} else if (pdev->id_entry->driver_data) {
-		drvdata = (struct c_can_driver_data *)
-			platform_get_device_id(pdev)->driver_data;
-	} else {
-		return -ENODEV;
-	}
+	drvdata = device_get_match_data(&pdev->dev);
 
 	/* get the appropriate clk */
 	clk = devm_clk_get(&pdev->dev, NULL);
diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c
index 036d85ef07f5..dfdc039d92a6 100644
--- a/drivers/net/can/dev/netlink.c
+++ b/drivers/net/can/dev/netlink.c
@@ -346,7 +346,7 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 			/* Neither of TDC parameters nor TDC flags are
 			 * provided: do calculation
 			 */
-			can_calc_tdco(&priv->tdc, priv->tdc_const, &priv->data_bittiming,
+			can_calc_tdco(&priv->tdc, priv->tdc_const, &dbt,
 				      &priv->ctrlmode, priv->ctrlmode_supported);
 		} /* else: both CAN_CTRLMODE_TDC_{AUTO,MANUAL} are explicitly
 		   * turned off. TDC is disabled: do nothing
diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c
index d15f85a40c1e..8ea7f2795551 100644
--- a/drivers/net/can/flexcan/flexcan-core.c
+++ b/drivers/net/can/flexcan/flexcan-core.c
@@ -23,11 +23,11 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/can/platform/flexcan.h>
 #include <linux/pm_runtime.h>
+#include <linux/property.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
 
@@ -2034,7 +2034,6 @@ MODULE_DEVICE_TABLE(platform, flexcan_id_table);
 
 static int flexcan_probe(struct platform_device *pdev)
 {
-	const struct of_device_id *of_id;
 	const struct flexcan_devtype_data *devtype_data;
 	struct net_device *dev;
 	struct flexcan_priv *priv;
@@ -2090,14 +2089,7 @@ static int flexcan_probe(struct platform_device *pdev)
 	if (IS_ERR(regs))
 		return PTR_ERR(regs);
 
-	of_id = of_match_device(flexcan_of_match, &pdev->dev);
-	if (of_id)
-		devtype_data = of_id->data;
-	else if (platform_get_device_id(pdev)->driver_data)
-		devtype_data = (struct flexcan_devtype_data *)
-			platform_get_device_id(pdev)->driver_data;
-	else
-		return -ENODEV;
+	devtype_data = device_get_match_data(&pdev->dev);
 
 	if ((devtype_data->quirks & FLEXCAN_QUIRK_SUPPORT_FD) &&
 	    !((devtype_data->quirks &
diff --git a/drivers/net/can/mscan/mpc5xxx_can.c b/drivers/net/can/mscan/mpc5xxx_can.c
index 4837df6efa92..5b3d69c3b6b6 100644
--- a/drivers/net/can/mscan/mpc5xxx_can.c
+++ b/drivers/net/can/mscan/mpc5xxx_can.c
@@ -12,8 +12,10 @@
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/netdevice.h>
 #include <linux/can/dev.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
@@ -290,7 +292,7 @@ static int mpc5xxx_can_probe(struct platform_device *ofdev)
 	int irq, mscan_clksrc = 0;
 	int err = -ENOMEM;
 
-	data = of_device_get_match_data(&ofdev->dev);
+	data = device_get_match_data(&ofdev->dev);
 	if (!data)
 		return -EINVAL;
 
@@ -351,13 +353,11 @@ exit_unmap_mem:
 
 static void mpc5xxx_can_remove(struct platform_device *ofdev)
 {
-	const struct of_device_id *match;
 	const struct mpc5xxx_can_data *data;
 	struct net_device *dev = platform_get_drvdata(ofdev);
 	struct mscan_priv *priv = netdev_priv(dev);
 
-	match = of_match_device(mpc5xxx_can_table, &ofdev->dev);
-	data = match ? match->data : NULL;
+	data = device_get_match_data(&ofdev->dev);
 
 	unregister_mscandev(dev);
 	if (data && data->put_clock)
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index 24ad9f593a77..1efa39e134f4 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -1143,7 +1143,7 @@ static void __exit peak_usb_exit(void)
 	int err;
 
 	/* last chance do send any synchronous commands here */
-	err = driver_for_each_device(&peak_usb_driver.drvwrap.driver, NULL,
+	err = driver_for_each_device(&peak_usb_driver.driver, NULL,
 				     NULL, peak_usb_do_device_exit);
 	if (err)
 		pr_err("%s: failed to stop all can devices (err %d)\n",
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index abe58f103043..3722eaa84234 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -20,8 +20,8 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/skbuff.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
@@ -1726,8 +1726,7 @@ static int xcan_probe(struct platform_device *pdev)
 	struct net_device *ndev;
 	struct xcan_priv *priv;
 	struct phy *transceiver;
-	const struct of_device_id *of_id;
-	const struct xcan_devtype_data *devtype = &xcan_axi_data;
+	const struct xcan_devtype_data *devtype;
 	void __iomem *addr;
 	int ret;
 	int rx_max, tx_max;
@@ -1741,9 +1740,7 @@ static int xcan_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	of_id = of_match_device(xcan_of_match, &pdev->dev);
-	if (of_id && of_id->data)
-		devtype = of_id->data;
+	devtype = device_get_match_data(&pdev->dev);
 
 	hw_tx_max_property = devtype->flags & XCAN_FLAG_TX_MAILBOXES ?
 			     "tx-mailbox-count" : "tx-fifo-depth";
diff --git a/drivers/net/dsa/dsa_loop_bdinfo.c b/drivers/net/dsa/dsa_loop_bdinfo.c
index 237066d30704..14ca42491512 100644
--- a/drivers/net/dsa/dsa_loop_bdinfo.c
+++ b/drivers/net/dsa/dsa_loop_bdinfo.c
@@ -32,4 +32,5 @@ static int __init dsa_loop_bdinfo_init(void)
 }
 arch_initcall(dsa_loop_bdinfo_init)
 
+MODULE_DESCRIPTION("DSA mock-up switch driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c
index 61b71bcfe396..c3da97abce20 100644
--- a/drivers/net/dsa/microchip/ksz8795.c
+++ b/drivers/net/dsa/microchip/ksz8795.c
@@ -49,9 +49,9 @@ static int ksz8_ind_write8(struct ksz_device *dev, u8 table, u16 addr, u8 data)
 	mutex_lock(&dev->alu_mutex);
 
 	ctrl_addr = IND_ACC_TABLE(table) | addr;
-	ret = ksz_write8(dev, regs[REG_IND_BYTE], data);
+	ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
 	if (!ret)
-		ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
+		ret = ksz_write8(dev, regs[REG_IND_BYTE], data);
 
 	mutex_unlock(&dev->alu_mutex);
 
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 391c4dbdff42..3c1f657593a8 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -2838,8 +2838,7 @@ static void mt753x_phylink_mac_link_up(struct dsa_switch *ds, int port,
 	/* MT753x MAC works in 1G full duplex mode for all up-clocked
 	 * variants.
 	 */
-	if (interface == PHY_INTERFACE_MODE_INTERNAL ||
-	    interface == PHY_INTERFACE_MODE_TRGMII ||
+	if (interface == PHY_INTERFACE_MODE_TRGMII ||
 	    (phy_interface_mode_is_8023z(interface))) {
 		speed = SPEED_1000;
 		duplex = DUPLEX_FULL;
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 383b3c4d6f59..614cabb5c1b0 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -3659,7 +3659,7 @@ static int mv88e6xxx_mdio_read_c45(struct mii_bus *bus, int phy, int devad,
 	int err;
 
 	if (!chip->info->ops->phy_read_c45)
-		return -EOPNOTSUPP;
+		return 0xffff;
 
 	mv88e6xxx_reg_lock(chip);
 	err = chip->info->ops->phy_read_c45(chip, bus, phy, devad, reg, &val);
diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c
index c51f40960961..7a864329cb72 100644
--- a/drivers/net/dsa/qca/qca8k-8xxx.c
+++ b/drivers/net/dsa/qca/qca8k-8xxx.c
@@ -2051,12 +2051,11 @@ qca8k_sw_probe(struct mdio_device *mdiodev)
 	priv->info = of_device_get_match_data(priv->dev);
 
 	priv->reset_gpio = devm_gpiod_get_optional(priv->dev, "reset",
-						   GPIOD_ASIS);
+						   GPIOD_OUT_HIGH);
 	if (IS_ERR(priv->reset_gpio))
 		return PTR_ERR(priv->reset_gpio);
 
 	if (priv->reset_gpio) {
-		gpiod_set_value_cansleep(priv->reset_gpio, 1);
 		/* The active low duration must be greater than 10 ms
 		 * and checkpatch.pl wants 20 ms.
 		 */
diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c
index dd50502e2122..ae70eac3be28 100644
--- a/drivers/net/dsa/vitesse-vsc73xx-core.c
+++ b/drivers/net/dsa/vitesse-vsc73xx-core.c
@@ -1135,6 +1135,8 @@ static int vsc73xx_gpio_probe(struct vsc73xx *vsc)
 
 	vsc->gc.label = devm_kasprintf(vsc->dev, GFP_KERNEL, "VSC%04x",
 				       vsc->chipid);
+	if (!vsc->gc.label)
+		return -ENOMEM;
 	vsc->gc.ngpio = 4;
 	vsc->gc.owner = THIS_MODULE;
 	vsc->gc.parent = vsc->dev;
diff --git a/drivers/net/ethernet/8390/8390.c b/drivers/net/ethernet/8390/8390.c
index 0e0aa4016858..c5636245f1ca 100644
--- a/drivers/net/ethernet/8390/8390.c
+++ b/drivers/net/ethernet/8390/8390.c
@@ -100,4 +100,5 @@ static void __exit ns8390_module_exit(void)
 module_init(ns8390_module_init);
 module_exit(ns8390_module_exit);
 #endif /* MODULE */
+MODULE_DESCRIPTION("National Semiconductor 8390 core driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/8390/8390p.c b/drivers/net/ethernet/8390/8390p.c
index 6834742057b3..6d429b11e9c6 100644
--- a/drivers/net/ethernet/8390/8390p.c
+++ b/drivers/net/ethernet/8390/8390p.c
@@ -102,4 +102,5 @@ static void __exit NS8390p_cleanup_module(void)
 
 module_init(NS8390p_init_module);
 module_exit(NS8390p_cleanup_module);
+MODULE_DESCRIPTION("National Semiconductor 8390 core for ISA driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/8390/apne.c b/drivers/net/ethernet/8390/apne.c
index a09f383dd249..828edca8d30c 100644
--- a/drivers/net/ethernet/8390/apne.c
+++ b/drivers/net/ethernet/8390/apne.c
@@ -610,4 +610,5 @@ static int init_pcmcia(void)
 	return 1;
 }
 
+MODULE_DESCRIPTION("National Semiconductor 8390 Amiga PCMCIA ethernet driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/8390/hydra.c b/drivers/net/ethernet/8390/hydra.c
index 24f49a8ff903..fd9dcdc356e6 100644
--- a/drivers/net/ethernet/8390/hydra.c
+++ b/drivers/net/ethernet/8390/hydra.c
@@ -270,4 +270,5 @@ static void __exit hydra_cleanup_module(void)
 module_init(hydra_init_module);
 module_exit(hydra_cleanup_module);
 
+MODULE_DESCRIPTION("Zorro-II Hydra 8390 ethernet driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/8390/stnic.c b/drivers/net/ethernet/8390/stnic.c
index 265976e3b64a..6cc0e190aa79 100644
--- a/drivers/net/ethernet/8390/stnic.c
+++ b/drivers/net/ethernet/8390/stnic.c
@@ -296,4 +296,5 @@ static void __exit stnic_cleanup(void)
 
 module_init(stnic_probe);
 module_exit(stnic_cleanup);
+MODULE_DESCRIPTION("National Semiconductor DP83902AV ethernet driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/8390/zorro8390.c b/drivers/net/ethernet/8390/zorro8390.c
index d70390e9d03d..c24dd4fe7a10 100644
--- a/drivers/net/ethernet/8390/zorro8390.c
+++ b/drivers/net/ethernet/8390/zorro8390.c
@@ -443,4 +443,5 @@ static void __exit zorro8390_cleanup_module(void)
 module_init(zorro8390_init_module);
 module_exit(zorro8390_cleanup_module);
 
+MODULE_DESCRIPTION("Zorro NS8390-based ethernet driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/adi/Kconfig b/drivers/net/ethernet/adi/Kconfig
index da3bdd302502..760a9a60bc15 100644
--- a/drivers/net/ethernet/adi/Kconfig
+++ b/drivers/net/ethernet/adi/Kconfig
@@ -21,6 +21,7 @@ config ADIN1110
 	tristate "Analog Devices ADIN1110 MAC-PHY"
 	depends on SPI && NET_SWITCHDEV
 	select CRC8
+	select PHYLIB
 	help
 	  Say yes here to build support for Analog Devices ADIN1110
 	  Low Power 10BASE-T1L Ethernet MAC-PHY.
diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c
index 5beadabc2136..ea773cfa0af6 100644
--- a/drivers/net/ethernet/amd/pds_core/adminq.c
+++ b/drivers/net/ethernet/amd/pds_core/adminq.c
@@ -63,6 +63,15 @@ static int pdsc_process_notifyq(struct pdsc_qcq *qcq)
 	return nq_work;
 }
 
+static bool pdsc_adminq_inc_if_up(struct pdsc *pdsc)
+{
+	if (pdsc->state & BIT_ULL(PDSC_S_STOPPING_DRIVER) ||
+	    pdsc->state & BIT_ULL(PDSC_S_FW_DEAD))
+		return false;
+
+	return refcount_inc_not_zero(&pdsc->adminq_refcnt);
+}
+
 void pdsc_process_adminq(struct pdsc_qcq *qcq)
 {
 	union pds_core_adminq_comp *comp;
@@ -75,9 +84,9 @@ void pdsc_process_adminq(struct pdsc_qcq *qcq)
 	int aq_work = 0;
 	int credits;
 
-	/* Don't process AdminQ when shutting down */
-	if (pdsc->state & BIT_ULL(PDSC_S_STOPPING_DRIVER)) {
-		dev_err(pdsc->dev, "%s: called while PDSC_S_STOPPING_DRIVER\n",
+	/* Don't process AdminQ when it's not up */
+	if (!pdsc_adminq_inc_if_up(pdsc)) {
+		dev_err(pdsc->dev, "%s: called while adminq is unavailable\n",
 			__func__);
 		return;
 	}
@@ -124,6 +133,7 @@ credits:
 		pds_core_intr_credits(&pdsc->intr_ctrl[qcq->intx],
 				      credits,
 				      PDS_CORE_INTR_CRED_REARM);
+	refcount_dec(&pdsc->adminq_refcnt);
 }
 
 void pdsc_work_thread(struct work_struct *work)
@@ -135,18 +145,20 @@ void pdsc_work_thread(struct work_struct *work)
 
 irqreturn_t pdsc_adminq_isr(int irq, void *data)
 {
-	struct pdsc_qcq *qcq = data;
-	struct pdsc *pdsc = qcq->pdsc;
+	struct pdsc *pdsc = data;
+	struct pdsc_qcq *qcq;
 
-	/* Don't process AdminQ when shutting down */
-	if (pdsc->state & BIT_ULL(PDSC_S_STOPPING_DRIVER)) {
-		dev_err(pdsc->dev, "%s: called while PDSC_S_STOPPING_DRIVER\n",
+	/* Don't process AdminQ when it's not up */
+	if (!pdsc_adminq_inc_if_up(pdsc)) {
+		dev_err(pdsc->dev, "%s: called while adminq is unavailable\n",
 			__func__);
 		return IRQ_HANDLED;
 	}
 
+	qcq = &pdsc->adminqcq;
 	queue_work(pdsc->wq, &qcq->work);
 	pds_core_intr_mask(&pdsc->intr_ctrl[qcq->intx], PDS_CORE_INTR_MASK_CLEAR);
+	refcount_dec(&pdsc->adminq_refcnt);
 
 	return IRQ_HANDLED;
 }
@@ -179,10 +191,16 @@ static int __pdsc_adminq_post(struct pdsc *pdsc,
 
 	/* Check that the FW is running */
 	if (!pdsc_is_fw_running(pdsc)) {
-		u8 fw_status = ioread8(&pdsc->info_regs->fw_status);
-
-		dev_info(pdsc->dev, "%s: post failed - fw not running %#02x:\n",
-			 __func__, fw_status);
+		if (pdsc->info_regs) {
+			u8 fw_status =
+				ioread8(&pdsc->info_regs->fw_status);
+
+			dev_info(pdsc->dev, "%s: post failed - fw not running %#02x:\n",
+				 __func__, fw_status);
+		} else {
+			dev_info(pdsc->dev, "%s: post failed - BARs not setup\n",
+				 __func__);
+		}
 		ret = -ENXIO;
 
 		goto err_out_unlock;
@@ -230,6 +248,12 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 	int err = 0;
 	int index;
 
+	if (!pdsc_adminq_inc_if_up(pdsc)) {
+		dev_dbg(pdsc->dev, "%s: preventing adminq cmd %u\n",
+			__func__, cmd->opcode);
+		return -ENXIO;
+	}
+
 	wc.qcq = &pdsc->adminqcq;
 	index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp, &wc);
 	if (index < 0) {
@@ -248,10 +272,16 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 			break;
 
 		if (!pdsc_is_fw_running(pdsc)) {
-			u8 fw_status = ioread8(&pdsc->info_regs->fw_status);
-
-			dev_dbg(pdsc->dev, "%s: post wait failed - fw not running %#02x:\n",
-				__func__, fw_status);
+			if (pdsc->info_regs) {
+				u8 fw_status =
+					ioread8(&pdsc->info_regs->fw_status);
+
+				dev_dbg(pdsc->dev, "%s: post wait failed - fw not running %#02x:\n",
+					__func__, fw_status);
+			} else {
+				dev_dbg(pdsc->dev, "%s: post wait failed - BARs not setup\n",
+					__func__);
+			}
 			err = -ENXIO;
 			break;
 		}
@@ -285,6 +315,8 @@ err_out:
 			queue_work(pdsc->wq, &pdsc->health_work);
 	}
 
+	refcount_dec(&pdsc->adminq_refcnt);
+
 	return err;
 }
 EXPORT_SYMBOL_GPL(pdsc_adminq_post);
diff --git a/drivers/net/ethernet/amd/pds_core/auxbus.c b/drivers/net/ethernet/amd/pds_core/auxbus.c
index 11c23a7f3172..fd1a5149c003 100644
--- a/drivers/net/ethernet/amd/pds_core/auxbus.c
+++ b/drivers/net/ethernet/amd/pds_core/auxbus.c
@@ -160,23 +160,19 @@ static struct pds_auxiliary_dev *pdsc_auxbus_dev_register(struct pdsc *cf,
 	if (err < 0) {
 		dev_warn(cf->dev, "auxiliary_device_init of %s failed: %pe\n",
 			 name, ERR_PTR(err));
-		goto err_out;
+		kfree(padev);
+		return ERR_PTR(err);
 	}
 
 	err = auxiliary_device_add(aux_dev);
 	if (err) {
 		dev_warn(cf->dev, "auxiliary_device_add of %s failed: %pe\n",
 			 name, ERR_PTR(err));
-		goto err_out_uninit;
+		auxiliary_device_uninit(aux_dev);
+		return ERR_PTR(err);
 	}
 
 	return padev;
-
-err_out_uninit:
-	auxiliary_device_uninit(aux_dev);
-err_out:
-	kfree(padev);
-	return ERR_PTR(err);
 }
 
 int pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf)
diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c
index 0d2091e9eb28..7658a7286767 100644
--- a/drivers/net/ethernet/amd/pds_core/core.c
+++ b/drivers/net/ethernet/amd/pds_core/core.c
@@ -125,7 +125,7 @@ static int pdsc_qcq_intr_alloc(struct pdsc *pdsc, struct pdsc_qcq *qcq)
 
 	snprintf(name, sizeof(name), "%s-%d-%s",
 		 PDS_CORE_DRV_NAME, pdsc->pdev->bus->number, qcq->q.name);
-	index = pdsc_intr_alloc(pdsc, name, pdsc_adminq_isr, qcq);
+	index = pdsc_intr_alloc(pdsc, name, pdsc_adminq_isr, pdsc);
 	if (index < 0)
 		return index;
 	qcq->intx = index;
@@ -404,10 +404,7 @@ int pdsc_setup(struct pdsc *pdsc, bool init)
 	int numdescs;
 	int err;
 
-	if (init)
-		err = pdsc_dev_init(pdsc);
-	else
-		err = pdsc_dev_reinit(pdsc);
+	err = pdsc_dev_init(pdsc);
 	if (err)
 		return err;
 
@@ -450,6 +447,7 @@ int pdsc_setup(struct pdsc *pdsc, bool init)
 		pdsc_debugfs_add_viftype(pdsc);
 	}
 
+	refcount_set(&pdsc->adminq_refcnt, 1);
 	clear_bit(PDSC_S_FW_DEAD, &pdsc->state);
 	return 0;
 
@@ -464,6 +462,8 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing)
 
 	if (!pdsc->pdev->is_virtfn)
 		pdsc_devcmd_reset(pdsc);
+	if (pdsc->adminqcq.work.func)
+		cancel_work_sync(&pdsc->adminqcq.work);
 	pdsc_qcq_free(pdsc, &pdsc->notifyqcq);
 	pdsc_qcq_free(pdsc, &pdsc->adminqcq);
 
@@ -476,10 +476,9 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing)
 		for (i = 0; i < pdsc->nintrs; i++)
 			pdsc_intr_free(pdsc, i);
 
-		if (removing) {
-			kfree(pdsc->intr_info);
-			pdsc->intr_info = NULL;
-		}
+		kfree(pdsc->intr_info);
+		pdsc->intr_info = NULL;
+		pdsc->nintrs = 0;
 	}
 
 	if (pdsc->kern_dbpage) {
@@ -487,6 +486,7 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing)
 		pdsc->kern_dbpage = NULL;
 	}
 
+	pci_free_irq_vectors(pdsc->pdev);
 	set_bit(PDSC_S_FW_DEAD, &pdsc->state);
 }
 
@@ -512,6 +512,24 @@ void pdsc_stop(struct pdsc *pdsc)
 					   PDS_CORE_INTR_MASK_SET);
 }
 
+static void pdsc_adminq_wait_and_dec_once_unused(struct pdsc *pdsc)
+{
+	/* The driver initializes the adminq_refcnt to 1 when the adminq is
+	 * allocated and ready for use. Other users/requesters will increment
+	 * the refcnt while in use. If the refcnt is down to 1 then the adminq
+	 * is not in use and the refcnt can be cleared and adminq freed. Before
+	 * calling this function the driver will set PDSC_S_FW_DEAD, which
+	 * prevent subsequent attempts to use the adminq and increment the
+	 * refcnt to fail. This guarantees that this function will eventually
+	 * exit.
+	 */
+	while (!refcount_dec_if_one(&pdsc->adminq_refcnt)) {
+		dev_dbg_ratelimited(pdsc->dev, "%s: adminq in use\n",
+				    __func__);
+		cpu_relax();
+	}
+}
+
 void pdsc_fw_down(struct pdsc *pdsc)
 {
 	union pds_core_notifyq_comp reset_event = {
@@ -527,6 +545,8 @@ void pdsc_fw_down(struct pdsc *pdsc)
 	if (pdsc->pdev->is_virtfn)
 		return;
 
+	pdsc_adminq_wait_and_dec_once_unused(pdsc);
+
 	/* Notify clients of fw_down */
 	if (pdsc->fw_reporter)
 		devlink_health_report(pdsc->fw_reporter, "FW down reported", pdsc);
@@ -577,7 +597,13 @@ err_out:
 
 static void pdsc_check_pci_health(struct pdsc *pdsc)
 {
-	u8 fw_status = ioread8(&pdsc->info_regs->fw_status);
+	u8 fw_status;
+
+	/* some sort of teardown already in progress */
+	if (!pdsc->info_regs)
+		return;
+
+	fw_status = ioread8(&pdsc->info_regs->fw_status);
 
 	/* is PCI broken? */
 	if (fw_status != PDS_RC_BAD_PCI)
diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h
index e35d3e7006bf..110c4b826b22 100644
--- a/drivers/net/ethernet/amd/pds_core/core.h
+++ b/drivers/net/ethernet/amd/pds_core/core.h
@@ -184,6 +184,7 @@ struct pdsc {
 	struct mutex devcmd_lock;	/* lock for dev_cmd operations */
 	struct mutex config_lock;	/* lock for configuration operations */
 	spinlock_t adminq_lock;		/* lock for adminq operations */
+	refcount_t adminq_refcnt;
 	struct pds_core_dev_info_regs __iomem *info_regs;
 	struct pds_core_dev_cmd_regs __iomem *cmd_regs;
 	struct pds_core_intr __iomem *intr_ctrl;
@@ -280,7 +281,6 @@ int pdsc_devcmd_locked(struct pdsc *pdsc, union pds_core_dev_cmd *cmd,
 		       union pds_core_dev_comp *comp, int max_seconds);
 int pdsc_devcmd_init(struct pdsc *pdsc);
 int pdsc_devcmd_reset(struct pdsc *pdsc);
-int pdsc_dev_reinit(struct pdsc *pdsc);
 int pdsc_dev_init(struct pdsc *pdsc);
 
 void pdsc_reset_prepare(struct pci_dev *pdev);
diff --git a/drivers/net/ethernet/amd/pds_core/debugfs.c b/drivers/net/ethernet/amd/pds_core/debugfs.c
index 8ec392299b7d..4e8579ca1c8c 100644
--- a/drivers/net/ethernet/amd/pds_core/debugfs.c
+++ b/drivers/net/ethernet/amd/pds_core/debugfs.c
@@ -64,6 +64,10 @@ DEFINE_SHOW_ATTRIBUTE(identity);
 
 void pdsc_debugfs_add_ident(struct pdsc *pdsc)
 {
+	/* This file will already exist in the reset flow */
+	if (debugfs_lookup("identity", pdsc->dentry))
+		return;
+
 	debugfs_create_file("identity", 0400, pdsc->dentry,
 			    pdsc, &identity_fops);
 }
diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c
index 31940b857e0e..e65a1632df50 100644
--- a/drivers/net/ethernet/amd/pds_core/dev.c
+++ b/drivers/net/ethernet/amd/pds_core/dev.c
@@ -57,6 +57,9 @@ int pdsc_err_to_errno(enum pds_core_status_code code)
 
 bool pdsc_is_fw_running(struct pdsc *pdsc)
 {
+	if (!pdsc->info_regs)
+		return false;
+
 	pdsc->fw_status = ioread8(&pdsc->info_regs->fw_status);
 	pdsc->last_fw_time = jiffies;
 	pdsc->last_hb = ioread32(&pdsc->info_regs->fw_heartbeat);
@@ -182,13 +185,17 @@ int pdsc_devcmd_locked(struct pdsc *pdsc, union pds_core_dev_cmd *cmd,
 {
 	int err;
 
+	if (!pdsc->cmd_regs)
+		return -ENXIO;
+
 	memcpy_toio(&pdsc->cmd_regs->cmd, cmd, sizeof(*cmd));
 	pdsc_devcmd_dbell(pdsc);
 	err = pdsc_devcmd_wait(pdsc, cmd->opcode, max_seconds);
-	memcpy_fromio(comp, &pdsc->cmd_regs->comp, sizeof(*comp));
 
 	if ((err == -ENXIO || err == -ETIMEDOUT) && pdsc->wq)
 		queue_work(pdsc->wq, &pdsc->health_work);
+	else
+		memcpy_fromio(comp, &pdsc->cmd_regs->comp, sizeof(*comp));
 
 	return err;
 }
@@ -309,13 +316,6 @@ static int pdsc_identify(struct pdsc *pdsc)
 	return 0;
 }
 
-int pdsc_dev_reinit(struct pdsc *pdsc)
-{
-	pdsc_init_devinfo(pdsc);
-
-	return pdsc_identify(pdsc);
-}
-
 int pdsc_dev_init(struct pdsc *pdsc)
 {
 	unsigned int nintrs;
diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c
index e9948ea5bbcd..54864f27c87a 100644
--- a/drivers/net/ethernet/amd/pds_core/devlink.c
+++ b/drivers/net/ethernet/amd/pds_core/devlink.c
@@ -111,7 +111,8 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 
 	mutex_lock(&pdsc->devcmd_lock);
 	err = pdsc_devcmd_locked(pdsc, &cmd, &comp, pdsc->devcmd_timeout * 2);
-	memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list));
+	if (!err)
+		memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list));
 	mutex_unlock(&pdsc->devcmd_lock);
 	if (err && err != -EIO)
 		return err;
diff --git a/drivers/net/ethernet/amd/pds_core/fw.c b/drivers/net/ethernet/amd/pds_core/fw.c
index 90a811f3878a..fa626719e68d 100644
--- a/drivers/net/ethernet/amd/pds_core/fw.c
+++ b/drivers/net/ethernet/amd/pds_core/fw.c
@@ -107,6 +107,9 @@ int pdsc_firmware_update(struct pdsc *pdsc, const struct firmware *fw,
 
 	dev_info(pdsc->dev, "Installing firmware\n");
 
+	if (!pdsc->cmd_regs)
+		return -ENXIO;
+
 	dl = priv_to_devlink(pdsc);
 	devlink_flash_update_status_notify(dl, "Preparing to flash",
 					   NULL, 0, 0);
diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c
index 3080898d7b95..0050c5894563 100644
--- a/drivers/net/ethernet/amd/pds_core/main.c
+++ b/drivers/net/ethernet/amd/pds_core/main.c
@@ -37,6 +37,11 @@ static void pdsc_unmap_bars(struct pdsc *pdsc)
 	struct pdsc_dev_bar *bars = pdsc->bars;
 	unsigned int i;
 
+	pdsc->info_regs = NULL;
+	pdsc->cmd_regs = NULL;
+	pdsc->intr_status = NULL;
+	pdsc->intr_ctrl = NULL;
+
 	for (i = 0; i < PDS_CORE_BARS_MAX; i++) {
 		if (bars[i].vaddr)
 			pci_iounmap(pdsc->pdev, bars[i].vaddr);
@@ -293,7 +298,7 @@ err_out_stop:
 err_out_teardown:
 	pdsc_teardown(pdsc, PDSC_TEARDOWN_REMOVING);
 err_out_unmap_bars:
-	del_timer_sync(&pdsc->wdtimer);
+	timer_shutdown_sync(&pdsc->wdtimer);
 	if (pdsc->wq)
 		destroy_workqueue(pdsc->wq);
 	mutex_destroy(&pdsc->config_lock);
@@ -420,7 +425,7 @@ static void pdsc_remove(struct pci_dev *pdev)
 		 */
 		pdsc_sriov_configure(pdev, 0);
 
-		del_timer_sync(&pdsc->wdtimer);
+		timer_shutdown_sync(&pdsc->wdtimer);
 		if (pdsc->wq)
 			destroy_workqueue(pdsc->wq);
 
@@ -433,7 +438,6 @@ static void pdsc_remove(struct pci_dev *pdev)
 		mutex_destroy(&pdsc->config_lock);
 		mutex_destroy(&pdsc->devcmd_lock);
 
-		pci_free_irq_vectors(pdev);
 		pdsc_unmap_bars(pdsc);
 		pci_release_regions(pdev);
 	}
@@ -445,13 +449,32 @@ static void pdsc_remove(struct pci_dev *pdev)
 	devlink_free(dl);
 }
 
+static void pdsc_stop_health_thread(struct pdsc *pdsc)
+{
+	if (pdsc->pdev->is_virtfn)
+		return;
+
+	timer_shutdown_sync(&pdsc->wdtimer);
+	if (pdsc->health_work.func)
+		cancel_work_sync(&pdsc->health_work);
+}
+
+static void pdsc_restart_health_thread(struct pdsc *pdsc)
+{
+	if (pdsc->pdev->is_virtfn)
+		return;
+
+	timer_setup(&pdsc->wdtimer, pdsc_wdtimer_cb, 0);
+	mod_timer(&pdsc->wdtimer, jiffies + 1);
+}
+
 void pdsc_reset_prepare(struct pci_dev *pdev)
 {
 	struct pdsc *pdsc = pci_get_drvdata(pdev);
 
+	pdsc_stop_health_thread(pdsc);
 	pdsc_fw_down(pdsc);
 
-	pci_free_irq_vectors(pdev);
 	pdsc_unmap_bars(pdsc);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
@@ -486,6 +509,7 @@ void pdsc_reset_done(struct pci_dev *pdev)
 	}
 
 	pdsc_fw_up(pdsc);
+	pdsc_restart_health_thread(pdsc);
 }
 
 static const struct pci_error_handlers pdsc_err_handler = {
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
index abd4832e4ed2..5acb3e16b567 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
@@ -993,7 +993,7 @@ int aq_ptp_ring_alloc(struct aq_nic_s *aq_nic)
 	return 0;
 
 err_exit_hwts_rx:
-	aq_ring_free(&aq_ptp->hwts_rx);
+	aq_ring_hwts_rx_free(&aq_ptp->hwts_rx);
 err_exit_ptp_rx:
 	aq_ring_free(&aq_ptp->ptp_rx);
 err_exit_ptp_tx:
@@ -1011,7 +1011,7 @@ void aq_ptp_ring_free(struct aq_nic_s *aq_nic)
 
 	aq_ring_free(&aq_ptp->ptp_tx);
 	aq_ring_free(&aq_ptp->ptp_rx);
-	aq_ring_free(&aq_ptp->hwts_rx);
+	aq_ring_hwts_rx_free(&aq_ptp->hwts_rx);
 
 	aq_ptp_skb_ring_release(&aq_ptp->skb_ring);
 }
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index cda8597b4e14..f7433abd6591 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -919,6 +919,19 @@ void aq_ring_free(struct aq_ring_s *self)
 	}
 }
 
+void aq_ring_hwts_rx_free(struct aq_ring_s *self)
+{
+	if (!self)
+		return;
+
+	if (self->dx_ring) {
+		dma_free_coherent(aq_nic_get_dev(self->aq_nic),
+				  self->size * self->dx_size + AQ_CFG_RXDS_DEF,
+				  self->dx_ring, self->dx_ring_pa);
+		self->dx_ring = NULL;
+	}
+}
+
 unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data)
 {
 	unsigned int count;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
index 52847310740a..d627ace850ff 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
@@ -210,6 +210,7 @@ int aq_ring_rx_fill(struct aq_ring_s *self);
 int aq_ring_hwts_rx_alloc(struct aq_ring_s *self,
 			  struct aq_nic_s *aq_nic, unsigned int idx,
 			  unsigned int size, unsigned int dx_size);
+void aq_ring_hwts_rx_free(struct aq_ring_s *self);
 void aq_ring_hwts_rx_clean(struct aq_ring_s *self, struct aq_nic_s *aq_nic);
 
 unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data);
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
index 29b04a274d07..80245c65cc90 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
@@ -535,9 +535,6 @@ int bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs,
 	int j = 0, i;
 
 	for (i = 0; i < NUM_NET_FILTERS; i++) {
-		if (j == *rule_cnt)
-			return -EMSGSIZE;
-
 		if (!priv->net_filters[i].claimed ||
 		    priv->net_filters[i].port != intf->port)
 			continue;
@@ -547,6 +544,9 @@ int bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs,
 		    priv->net_filters[i - 1].wake_filter)
 			continue;
 
+		if (j == *rule_cnt)
+			return -EMSGSIZE;
+
 		rule_locs[j++] = priv->net_filters[i].fs.location;
 	}
 
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
index 53e542881255..6ad1366270f7 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
@@ -684,6 +684,8 @@ static int bcmasp_init_rx(struct bcmasp_intf *intf)
 
 	intf->rx_buf_order = get_order(RING_BUFFER_SIZE);
 	buffer_pg = alloc_pages(GFP_KERNEL, intf->rx_buf_order);
+	if (!buffer_pg)
+		return -ENOMEM;
 
 	dma = dma_map_page(kdev, buffer_pg, 0, RING_BUFFER_SIZE,
 			   DMA_FROM_DEVICE);
@@ -1048,6 +1050,9 @@ static int bcmasp_netif_init(struct net_device *dev, bool phy_connect)
 			netdev_err(dev, "could not attach to PHY\n");
 			goto err_phy_disable;
 		}
+
+		/* Indicate that the MAC is responsible for PHY PM */
+		phydev->mac_managed_pm = true;
 	} else if (!intf->wolopts) {
 		ret = phy_resume(dev->phydev);
 		if (ret)
@@ -1092,6 +1097,7 @@ static int bcmasp_netif_init(struct net_device *dev, bool phy_connect)
 	return 0;
 
 err_reclaim_tx:
+	netif_napi_del(&intf->tx_napi);
 	bcmasp_reclaim_free_all_tx(intf);
 err_phy_disconnect:
 	if (phydev)
diff --git a/drivers/net/ethernet/broadcom/bcm4908_enet.c b/drivers/net/ethernet/broadcom/bcm4908_enet.c
index 3e7c8671cd11..72df1bb10172 100644
--- a/drivers/net/ethernet/broadcom/bcm4908_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm4908_enet.c
@@ -793,5 +793,6 @@ static struct platform_driver bcm4908_enet_driver = {
 };
 module_platform_driver(bcm4908_enet_driver);
 
+MODULE_DESCRIPTION("Broadcom BCM4908 Gigabit Ethernet driver");
 MODULE_LICENSE("GPL v2");
 MODULE_DEVICE_TABLE(of, bcm4908_enet_of_match);
diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c b/drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c
index 9b83d5361699..50b8e97a811d 100644
--- a/drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c
+++ b/drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c
@@ -260,4 +260,5 @@ void bcma_mdio_mii_unregister(struct mii_bus *mii_bus)
 EXPORT_SYMBOL_GPL(bcma_mdio_mii_unregister);
 
 MODULE_AUTHOR("Rafał Miłecki");
+MODULE_DESCRIPTION("Broadcom iProc GBit BCMA MDIO helpers");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c
index 6e4f36aaf5db..36f9bad28e6a 100644
--- a/drivers/net/ethernet/broadcom/bgmac-bcma.c
+++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c
@@ -362,4 +362,5 @@ module_init(bgmac_init)
 module_exit(bgmac_exit)
 
 MODULE_AUTHOR("Rafał Miłecki");
+MODULE_DESCRIPTION("Broadcom iProc GBit BCMA interface driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c
index 0b21fd5bd457..77425c7a32db 100644
--- a/drivers/net/ethernet/broadcom/bgmac-platform.c
+++ b/drivers/net/ethernet/broadcom/bgmac-platform.c
@@ -298,4 +298,5 @@ static struct platform_driver bgmac_enet_driver = {
 };
 
 module_platform_driver(bgmac_enet_driver);
+MODULE_DESCRIPTION("Broadcom iProc GBit platform interface driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 448a1b90de5e..6ffdc4229407 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -1626,4 +1626,5 @@ int bgmac_enet_resume(struct bgmac *bgmac)
 EXPORT_SYMBOL_GPL(bgmac_enet_resume);
 
 MODULE_AUTHOR("Rafał Miłecki");
+MODULE_DESCRIPTION("Broadcom iProc GBit driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 0aacd3c6ed5c..39845d556baf 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3817,7 +3817,7 @@ static int bnxt_alloc_cp_rings(struct bnxt *bp)
 {
 	bool sh = !!(bp->flags & BNXT_FLAG_SHARED_RINGS);
 	int i, j, rc, ulp_base_vec, ulp_msix;
-	int tcs = netdev_get_num_tc(bp->dev);
+	int tcs = bp->num_tc;
 
 	if (!tcs)
 		tcs = 1;
@@ -5935,8 +5935,12 @@ static u16 bnxt_get_max_rss_ring(struct bnxt *bp)
 
 int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
-		return DIV_ROUND_UP(rx_rings, BNXT_RSS_TABLE_ENTRIES_P5);
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+		if (!rx_rings)
+			return 0;
+		return bnxt_calc_nr_ring_pages(rx_rings - 1,
+					       BNXT_RSS_TABLE_ENTRIES_P5);
+	}
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp))
 		return 2;
 	return 1;
@@ -6926,7 +6930,7 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp)
 			if (cp < (rx + tx)) {
 				rc = __bnxt_trim_rings(bp, &rx, &tx, cp, false);
 				if (rc)
-					return rc;
+					goto get_rings_exit;
 				if (bp->flags & BNXT_FLAG_AGG_RINGS)
 					rx <<= 1;
 				hw_resc->resv_rx_rings = rx;
@@ -6938,8 +6942,9 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp)
 		hw_resc->resv_cp_rings = cp;
 		hw_resc->resv_stat_ctxs = stats;
 	}
+get_rings_exit:
 	hwrm_req_drop(bp, req);
-	return 0;
+	return rc;
 }
 
 int __bnxt_hwrm_get_tx_rings(struct bnxt *bp, u16 fid, int *tx_rings)
@@ -7000,10 +7005,11 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 
 		req->num_rx_rings = cpu_to_le16(rx_rings);
 		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+			u16 rss_ctx = bnxt_get_nr_rss_ctxs(bp, ring_grps);
+
 			req->num_cmpl_rings = cpu_to_le16(tx_rings + ring_grps);
 			req->num_msix = cpu_to_le16(cp_rings);
-			req->num_rsscos_ctxs =
-				cpu_to_le16(DIV_ROUND_UP(ring_grps, 64));
+			req->num_rsscos_ctxs = cpu_to_le16(rss_ctx);
 		} else {
 			req->num_cmpl_rings = cpu_to_le16(cp_rings);
 			req->num_hw_ring_grps = cpu_to_le16(ring_grps);
@@ -7050,8 +7056,10 @@ __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 	req->num_tx_rings = cpu_to_le16(tx_rings);
 	req->num_rx_rings = cpu_to_le16(rx_rings);
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+		u16 rss_ctx = bnxt_get_nr_rss_ctxs(bp, ring_grps);
+
 		req->num_cmpl_rings = cpu_to_le16(tx_rings + ring_grps);
-		req->num_rsscos_ctxs = cpu_to_le16(DIV_ROUND_UP(ring_grps, 64));
+		req->num_rsscos_ctxs = cpu_to_le16(rss_ctx);
 	} else {
 		req->num_cmpl_rings = cpu_to_le16(cp_rings);
 		req->num_hw_ring_grps = cpu_to_le16(ring_grps);
@@ -9938,7 +9946,7 @@ static int __bnxt_num_tx_to_cp(struct bnxt *bp, int tx, int tx_sets, int tx_xdp)
 
 int bnxt_num_tx_to_cp(struct bnxt *bp, int tx)
 {
-	int tcs = netdev_get_num_tc(bp->dev);
+	int tcs = bp->num_tc;
 
 	if (!tcs)
 		tcs = 1;
@@ -9947,7 +9955,7 @@ int bnxt_num_tx_to_cp(struct bnxt *bp, int tx)
 
 static int bnxt_num_cp_to_tx(struct bnxt *bp, int tx_cp)
 {
-	int tcs = netdev_get_num_tc(bp->dev);
+	int tcs = bp->num_tc;
 
 	return (tx_cp - bp->tx_nr_rings_xdp) * tcs +
 	       bp->tx_nr_rings_xdp;
@@ -9977,7 +9985,7 @@ static void bnxt_setup_msix(struct bnxt *bp)
 	struct net_device *dev = bp->dev;
 	int tcs, i;
 
-	tcs = netdev_get_num_tc(dev);
+	tcs = bp->num_tc;
 	if (tcs) {
 		int i, off, count;
 
@@ -10009,8 +10017,10 @@ static void bnxt_setup_inta(struct bnxt *bp)
 {
 	const int len = sizeof(bp->irq_tbl[0].name);
 
-	if (netdev_get_num_tc(bp->dev))
+	if (bp->num_tc) {
 		netdev_reset_tc(bp->dev);
+		bp->num_tc = 0;
+	}
 
 	snprintf(bp->irq_tbl[0].name, len, "%s-%s-%d", bp->dev->name, "TxRx",
 		 0);
@@ -10236,8 +10246,8 @@ static void bnxt_clear_int_mode(struct bnxt *bp)
 
 int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init)
 {
-	int tcs = netdev_get_num_tc(bp->dev);
 	bool irq_cleared = false;
+	int tcs = bp->num_tc;
 	int rc;
 
 	if (!bnxt_need_reserve_rings(bp))
@@ -10263,6 +10273,7 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init)
 		    bp->tx_nr_rings - bp->tx_nr_rings_xdp)) {
 		netdev_err(bp->dev, "tx ring reservation failure\n");
 		netdev_reset_tc(bp->dev);
+		bp->num_tc = 0;
 		if (bp->tx_nr_rings_xdp)
 			bp->tx_nr_rings_per_tc = bp->tx_nr_rings_xdp;
 		else
@@ -11564,10 +11575,12 @@ int bnxt_half_open_nic(struct bnxt *bp)
 		netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc);
 		goto half_open_err;
 	}
+	bnxt_init_napi(bp);
 	set_bit(BNXT_STATE_HALF_OPEN, &bp->state);
 	rc = bnxt_init_nic(bp, true);
 	if (rc) {
 		clear_bit(BNXT_STATE_HALF_OPEN, &bp->state);
+		bnxt_del_napi(bp);
 		netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc);
 		goto half_open_err;
 	}
@@ -11586,6 +11599,7 @@ half_open_err:
 void bnxt_half_close_nic(struct bnxt *bp)
 {
 	bnxt_hwrm_resource_free(bp, false, true);
+	bnxt_del_napi(bp);
 	bnxt_free_skbs(bp);
 	bnxt_free_mem(bp, true);
 	clear_bit(BNXT_STATE_HALF_OPEN, &bp->state);
@@ -13232,6 +13246,11 @@ static int bnxt_fw_init_one_p1(struct bnxt *bp)
 
 	bp->fw_cap = 0;
 	rc = bnxt_hwrm_ver_get(bp);
+	/* FW may be unresponsive after FLR. FLR must complete within 100 msec
+	 * so wait before continuing with recovery.
+	 */
+	if (rc)
+		msleep(100);
 	bnxt_try_map_fw_health_reg(bp);
 	if (rc) {
 		rc = bnxt_try_recover_fw(bp);
@@ -13784,7 +13803,7 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 		return -EINVAL;
 	}
 
-	if (netdev_get_num_tc(dev) == tc)
+	if (bp->num_tc == tc)
 		return 0;
 
 	if (bp->flags & BNXT_FLAG_SHARED_RINGS)
@@ -13802,9 +13821,11 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 	if (tc) {
 		bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tc;
 		netdev_set_num_tc(dev, tc);
+		bp->num_tc = tc;
 	} else {
 		bp->tx_nr_rings = bp->tx_nr_rings_per_tc;
 		netdev_reset_tc(dev);
+		bp->num_tc = 0;
 	}
 	bp->tx_nr_rings += bp->tx_nr_rings_xdp;
 	tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index b8ef1717cb65..47338b48ca20 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2225,6 +2225,7 @@ struct bnxt {
 	u8			tc_to_qidx[BNXT_MAX_QUEUE];
 	u8			q_ids[BNXT_MAX_QUEUE];
 	u8			max_q;
+	u8			num_tc;
 
 	unsigned int		current_interval;
 #define BNXT_TIMER_INTERVAL	HZ
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index 63e067038385..0dbb880a7aa0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -228,7 +228,7 @@ static int bnxt_queue_remap(struct bnxt *bp, unsigned int lltc_mask)
 		}
 	}
 	if (bp->ieee_ets) {
-		int tc = netdev_get_num_tc(bp->dev);
+		int tc = bp->num_tc;
 
 		if (!tc)
 			tc = 1;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 27b983c0a8a9..dc4ca706b0e2 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -884,7 +884,7 @@ static void bnxt_get_channels(struct net_device *dev,
 	if (max_tx_sch_inputs)
 		max_tx_rings = min_t(int, max_tx_rings, max_tx_sch_inputs);
 
-	tcs = netdev_get_num_tc(dev);
+	tcs = bp->num_tc;
 	tx_grps = max(tcs, 1);
 	if (bp->tx_nr_rings_xdp)
 		tx_grps++;
@@ -944,7 +944,7 @@ static int bnxt_set_channels(struct net_device *dev,
 	if (channel->combined_count)
 		sh = true;
 
-	tcs = netdev_get_num_tc(dev);
+	tcs = bp->num_tc;
 
 	req_tx_rings = sh ? channel->combined_count : channel->tx_count;
 	req_rx_rings = sh ? channel->combined_count : channel->rx_count;
@@ -1574,7 +1574,8 @@ u32 bnxt_get_rxfh_indir_size(struct net_device *dev)
 	struct bnxt *bp = netdev_priv(dev);
 
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
-		return ALIGN(bp->rx_nr_rings, BNXT_RSS_TABLE_ENTRIES_P5);
+		return bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) *
+		       BNXT_RSS_TABLE_ENTRIES_P5;
 	return HW_HASH_INDEX_SIZE;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index adad188e38b8..cc07660330f5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -684,7 +684,7 @@ static void bnxt_stamp_tx_skb(struct bnxt *bp, struct sk_buff *skb)
 		timestamp.hwtstamp = ns_to_ktime(ns);
 		skb_tstamp_tx(ptp->tx_skb, &timestamp);
 	} else {
-		netdev_WARN_ONCE(bp->dev,
+		netdev_warn_once(bp->dev,
 				 "TS query for TX timer failed rc = %x\n", rc);
 	}
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index c2b25fc623ec..4079538bc310 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -407,7 +407,7 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 	if (prog)
 		tx_xdp = bp->rx_nr_rings;
 
-	tc = netdev_get_num_tc(dev);
+	tc = bp->num_tc;
 	if (!tc)
 		tc = 1;
 	rc = bnxt_check_rings(bp, bp->tx_nr_rings_per_tc, bp->rx_nr_rings,
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index 31191b520b58..c32174484a96 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -1091,10 +1091,10 @@ bnad_cb_tx_resume(struct bnad *bnad, struct bna_tx *tx)
  * Free all TxQs buffers and then notify TX_E_CLEANUP_DONE to Tx fsm.
  */
 static void
-bnad_tx_cleanup(struct delayed_work *work)
+bnad_tx_cleanup(struct work_struct *work)
 {
 	struct bnad_tx_info *tx_info =
-		container_of(work, struct bnad_tx_info, tx_cleanup_work);
+		container_of(work, struct bnad_tx_info, tx_cleanup_work.work);
 	struct bnad *bnad = NULL;
 	struct bna_tcb *tcb;
 	unsigned long flags;
@@ -1170,7 +1170,7 @@ bnad_cb_rx_stall(struct bnad *bnad, struct bna_rx *rx)
  * Free all RxQs buffers and then notify RX_E_CLEANUP_DONE to Rx fsm.
  */
 static void
-bnad_rx_cleanup(void *work)
+bnad_rx_cleanup(struct work_struct *work)
 {
 	struct bnad_rx_info *rx_info =
 		container_of(work, struct bnad_rx_info, rx_cleanup_work);
@@ -1991,8 +1991,7 @@ bnad_setup_tx(struct bnad *bnad, u32 tx_id)
 	}
 	tx_info->tx = tx;
 
-	INIT_DELAYED_WORK(&tx_info->tx_cleanup_work,
-			(work_func_t)bnad_tx_cleanup);
+	INIT_DELAYED_WORK(&tx_info->tx_cleanup_work, bnad_tx_cleanup);
 
 	/* Register ISR for the Tx object */
 	if (intr_info->intr_type == BNA_INTR_T_MSIX) {
@@ -2248,8 +2247,7 @@ bnad_setup_rx(struct bnad *bnad, u32 rx_id)
 	rx_info->rx = rx;
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
 
-	INIT_WORK(&rx_info->rx_cleanup_work,
-			(work_func_t)(bnad_rx_cleanup));
+	INIT_WORK(&rx_info->rx_cleanup_work, bnad_rx_cleanup);
 
 	/*
 	 * Init NAPI, so that state is set to NAPI_STATE_SCHED,
diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
index 068ed52b66c9..b3c81a2e9d46 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
@@ -1490,7 +1490,7 @@ int cn23xx_get_vf_stats(struct octeon_device *oct, int vfidx,
 	mbox_cmd.q_no = vfidx * oct->sriov_info.rings_per_vf;
 	mbox_cmd.recv_len = 0;
 	mbox_cmd.recv_status = 0;
-	mbox_cmd.fn = (octeon_mbox_callback_t)cn23xx_get_vf_stats_callback;
+	mbox_cmd.fn = cn23xx_get_vf_stats_callback;
 	ctx.stats = stats;
 	atomic_set(&ctx.status, 0);
 	mbox_cmd.fn_arg = (void *)&ctx;
diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c
index dd5d80fee24f..d2fcb3da484e 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c
@@ -429,7 +429,7 @@ int cn23xx_octeon_pfvf_handshake(struct octeon_device *oct)
 	mbox_cmd.q_no = 0;
 	mbox_cmd.recv_len = 0;
 	mbox_cmd.recv_status = 0;
-	mbox_cmd.fn = (octeon_mbox_callback_t)octeon_pfvf_hs_callback;
+	mbox_cmd.fn = octeon_pfvf_hs_callback;
 	mbox_cmd.fn_arg = &status;
 
 	octeon_mbox_write(oct, &mbox_cmd);
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c
index 9cc6303c82ff..f38d31bfab1b 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_core.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c
@@ -27,6 +27,7 @@
 #include "octeon_network.h"
 
 MODULE_AUTHOR("Cavium Networks, <support@cavium.com>");
+MODULE_DESCRIPTION("Cavium LiquidIO Intelligent Server Adapter Core");
 MODULE_LICENSE("GPL");
 
 /* OOM task polling interval */
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h
index d92bd7e16477..9ac85d22c615 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h
@@ -57,7 +57,10 @@ union octeon_mbox_message {
 	} s;
 };
 
-typedef void (*octeon_mbox_callback_t)(void *, void *, void *);
+struct octeon_mbox_cmd;
+
+typedef void (*octeon_mbox_callback_t)(struct octeon_device *,
+				       struct octeon_mbox_cmd *, void *);
 
 struct octeon_mbox_cmd {
 	union octeon_mbox_message msg;
diff --git a/drivers/net/ethernet/cirrus/ep93xx_eth.c b/drivers/net/ethernet/cirrus/ep93xx_eth.c
index 1c2a540db13d..1f495cfd7959 100644
--- a/drivers/net/ethernet/cirrus/ep93xx_eth.c
+++ b/drivers/net/ethernet/cirrus/ep93xx_eth.c
@@ -868,5 +868,6 @@ static struct platform_driver ep93xx_eth_driver = {
 
 module_platform_driver(ep93xx_eth_driver);
 
+MODULE_DESCRIPTION("Cirrus EP93xx Ethernet driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:ep93xx-eth");
diff --git a/drivers/net/ethernet/cisco/enic/vnic_vic.c b/drivers/net/ethernet/cisco/enic/vnic_vic.c
index 20fcb20b42ed..66b577835338 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_vic.c
+++ b/drivers/net/ethernet/cisco/enic/vnic_vic.c
@@ -49,7 +49,8 @@ int vic_provinfo_add_tlv(struct vic_provinfo *vp, u16 type, u16 length,
 
 	tlv->type = htons(type);
 	tlv->length = htons(length);
-	memcpy(tlv->value, value, length);
+	unsafe_memcpy(tlv->value, value, length,
+		      /* Flexible array of flexible arrays */);
 
 	vp->num_tlvs = htonl(ntohl(vp->num_tlvs) + 1);
 	vp->length = htonl(ntohl(vp->length) +
diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c
index df40c720e7b2..64eadd320798 100644
--- a/drivers/net/ethernet/engleder/tsnep_main.c
+++ b/drivers/net/ethernet/engleder/tsnep_main.c
@@ -719,17 +719,25 @@ static void tsnep_xdp_xmit_flush(struct tsnep_tx *tx)
 
 static bool tsnep_xdp_xmit_back(struct tsnep_adapter *adapter,
 				struct xdp_buff *xdp,
-				struct netdev_queue *tx_nq, struct tsnep_tx *tx)
+				struct netdev_queue *tx_nq, struct tsnep_tx *tx,
+				bool zc)
 {
 	struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp);
 	bool xmit;
+	u32 type;
 
 	if (unlikely(!xdpf))
 		return false;
 
+	/* no page pool for zero copy */
+	if (zc)
+		type = TSNEP_TX_TYPE_XDP_NDO;
+	else
+		type = TSNEP_TX_TYPE_XDP_TX;
+
 	__netif_tx_lock(tx_nq, smp_processor_id());
 
-	xmit = tsnep_xdp_xmit_frame_ring(xdpf, tx, TSNEP_TX_TYPE_XDP_TX);
+	xmit = tsnep_xdp_xmit_frame_ring(xdpf, tx, type);
 
 	/* Avoid transmit queue timeout since we share it with the slow path */
 	if (xmit)
@@ -1273,7 +1281,7 @@ static bool tsnep_xdp_run_prog(struct tsnep_rx *rx, struct bpf_prog *prog,
 	case XDP_PASS:
 		return false;
 	case XDP_TX:
-		if (!tsnep_xdp_xmit_back(rx->adapter, xdp, tx_nq, tx))
+		if (!tsnep_xdp_xmit_back(rx->adapter, xdp, tx_nq, tx, false))
 			goto out_failure;
 		*status |= TSNEP_XDP_TX;
 		return true;
@@ -1323,7 +1331,7 @@ static bool tsnep_xdp_run_prog_zc(struct tsnep_rx *rx, struct bpf_prog *prog,
 	case XDP_PASS:
 		return false;
 	case XDP_TX:
-		if (!tsnep_xdp_xmit_back(rx->adapter, xdp, tx_nq, tx))
+		if (!tsnep_xdp_xmit_back(rx->adapter, xdp, tx_nq, tx, true))
 			goto out_failure;
 		*status |= TSNEP_XDP_TX;
 		return true;
@@ -1485,7 +1493,7 @@ static int tsnep_rx_poll(struct tsnep_rx *rx, struct napi_struct *napi,
 
 			xdp_prepare_buff(&xdp, page_address(entry->page),
 					 XDP_PACKET_HEADROOM + TSNEP_RX_INLINE_METADATA_SIZE,
-					 length, false);
+					 length - ETH_FCS_LEN, false);
 
 			consume = tsnep_xdp_run_prog(rx, prog, &xdp,
 						     &xdp_status, tx_nq, tx);
@@ -1568,7 +1576,7 @@ static int tsnep_rx_poll_zc(struct tsnep_rx *rx, struct napi_struct *napi,
 		prefetch(entry->xdp->data);
 		length = __le32_to_cpu(entry->desc_wb->properties) &
 			 TSNEP_DESC_LENGTH_MASK;
-		xsk_buff_set_size(entry->xdp, length);
+		xsk_buff_set_size(entry->xdp, length - ETH_FCS_LEN);
 		xsk_buff_dma_sync_for_cpu(entry->xdp, rx->xsk_pool);
 
 		/* RX metadata with timestamps is in front of actual data,
@@ -1762,6 +1770,19 @@ static void tsnep_rx_reopen_xsk(struct tsnep_rx *rx)
 			allocated--;
 		}
 	}
+
+	/* set need wakeup flag immediately if ring is not filled completely,
+	 * first polling would be too late as need wakeup signalisation would
+	 * be delayed for an indefinite time
+	 */
+	if (xsk_uses_need_wakeup(rx->xsk_pool)) {
+		int desc_available = tsnep_rx_desc_available(rx);
+
+		if (desc_available)
+			xsk_set_rx_need_wakeup(rx->xsk_pool);
+		else
+			xsk_clear_rx_need_wakeup(rx->xsk_pool);
+	}
 }
 
 static bool tsnep_pending(struct tsnep_queue *queue)
diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c
index 07c2b701b5fa..9ebe751c1df0 100644
--- a/drivers/net/ethernet/ezchip/nps_enet.c
+++ b/drivers/net/ethernet/ezchip/nps_enet.c
@@ -661,4 +661,5 @@ static struct platform_driver nps_enet_driver = {
 module_platform_driver(nps_enet_driver);
 
 MODULE_AUTHOR("EZchip Semiconductor");
+MODULE_DESCRIPTION("EZchip NPS Ethernet driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index cffbf27c4656..bfdbdab443ae 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -3216,4 +3216,5 @@ void enetc_pci_remove(struct pci_dev *pdev)
 }
 EXPORT_SYMBOL_GPL(enetc_pci_remove);
 
+MODULE_DESCRIPTION("NXP ENETC Ethernet driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index d42594f32275..432523b2c789 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2036,6 +2036,7 @@ static void fec_enet_adjust_link(struct net_device *ndev)
 
 		/* if any of the above changed restart the FEC */
 		if (status_change) {
+			netif_stop_queue(ndev);
 			napi_disable(&fep->napi);
 			netif_tx_lock_bh(ndev);
 			fec_restart(ndev);
@@ -2045,6 +2046,7 @@ static void fec_enet_adjust_link(struct net_device *ndev)
 		}
 	} else {
 		if (fep->link) {
+			netif_stop_queue(ndev);
 			napi_disable(&fep->napi);
 			netif_tx_lock_bh(ndev);
 			fec_stop(ndev);
@@ -4769,4 +4771,5 @@ static struct platform_driver fec_driver = {
 
 module_platform_driver(fec_driver);
 
+MODULE_DESCRIPTION("NXP Fast Ethernet Controller (FEC) driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c
index 9ba15d3183d7..758535adc9ff 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.c
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.c
@@ -1073,6 +1073,14 @@ int memac_initialization(struct mac_device *mac_dev,
 	unsigned long		 capabilities;
 	unsigned long		*supported;
 
+	/* The internal connection to the serdes is XGMII, but this isn't
+	 * really correct for the phy mode (which is the external connection).
+	 * However, this is how all older device trees say that they want
+	 * 10GBASE-R (aka XFI), so just convert it for them.
+	 */
+	if (mac_dev->phy_if == PHY_INTERFACE_MODE_XGMII)
+		mac_dev->phy_if = PHY_INTERFACE_MODE_10GBASER;
+
 	mac_dev->phylink_ops		= &memac_mac_ops;
 	mac_dev->set_promisc		= memac_set_promiscuous;
 	mac_dev->change_addr		= memac_modify_mac_address;
@@ -1139,7 +1147,7 @@ int memac_initialization(struct mac_device *mac_dev,
 	 * (and therefore that xfi_pcs cannot be set). If we are defaulting to
 	 * XGMII, assume this is for XFI. Otherwise, assume it is for SGMII.
 	 */
-	if (err && mac_dev->phy_if == PHY_INTERFACE_MODE_XGMII)
+	if (err && mac_dev->phy_if == PHY_INTERFACE_MODE_10GBASER)
 		memac->xfi_pcs = pcs;
 	else
 		memac->sgmii_pcs = pcs;
@@ -1153,14 +1161,6 @@ int memac_initialization(struct mac_device *mac_dev,
 		goto _return_fm_mac_free;
 	}
 
-	/* The internal connection to the serdes is XGMII, but this isn't
-	 * really correct for the phy mode (which is the external connection).
-	 * However, this is how all older device trees say that they want
-	 * 10GBASE-R (aka XFI), so just convert it for them.
-	 */
-	if (mac_dev->phy_if == PHY_INTERFACE_MODE_XGMII)
-		mac_dev->phy_if = PHY_INTERFACE_MODE_10GBASER;
-
 	/* TODO: The following interface modes are supported by (some) hardware
 	 * but not by this driver:
 	 * - 1000BASE-KX
diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
index 70dd982a5edc..026f7270a54d 100644
--- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c
+++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
@@ -531,4 +531,5 @@ static struct platform_driver fsl_pq_mdio_driver = {
 
 module_platform_driver(fsl_pq_mdio_driver);
 
+MODULE_DESCRIPTION("Freescale PQ MDIO helpers");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c
index 7a8dc5386fff..76615d47e055 100644
--- a/drivers/net/ethernet/google/gve/gve_rx.c
+++ b/drivers/net/ethernet/google/gve/gve_rx.c
@@ -356,7 +356,7 @@ static enum pkt_hash_types gve_rss_type(__be16 pkt_flags)
 
 static struct sk_buff *gve_rx_add_frags(struct napi_struct *napi,
 					struct gve_rx_slot_page_info *page_info,
-					u16 packet_buffer_size, u16 len,
+					unsigned int truesize, u16 len,
 					struct gve_rx_ctx *ctx)
 {
 	u32 offset = page_info->page_offset + page_info->pad;
@@ -389,10 +389,10 @@ static struct sk_buff *gve_rx_add_frags(struct napi_struct *napi,
 	if (skb != ctx->skb_head) {
 		ctx->skb_head->len += len;
 		ctx->skb_head->data_len += len;
-		ctx->skb_head->truesize += packet_buffer_size;
+		ctx->skb_head->truesize += truesize;
 	}
 	skb_add_rx_frag(skb, num_frags, page_info->page,
-			offset, len, packet_buffer_size);
+			offset, len, truesize);
 
 	return ctx->skb_head;
 }
@@ -486,7 +486,7 @@ static struct sk_buff *gve_rx_copy_to_pool(struct gve_rx_ring *rx,
 
 		memcpy(alloc_page_info.page_address, src, page_info->pad + len);
 		skb = gve_rx_add_frags(napi, &alloc_page_info,
-				       rx->packet_buffer_size,
+				       PAGE_SIZE,
 				       len, ctx);
 
 		u64_stats_update_begin(&rx->statss);
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index a187582d2299..ba9c19e6994c 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -360,23 +360,43 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca);
  * As a result, a shift of INCVALUE_SHIFT_n is used to fit a value of
  * INCVALUE_n into the TIMINCA register allowing 32+8+(24-INCVALUE_SHIFT_n)
  * bits to count nanoseconds leaving the rest for fractional nonseconds.
+ *
+ * Any given INCVALUE also has an associated maximum adjustment value. This
+ * maximum adjustment value is the largest increase (or decrease) which can be
+ * safely applied without overflowing the INCVALUE. Since INCVALUE has
+ * a maximum range of 24 bits, its largest value is 0xFFFFFF.
+ *
+ * To understand where the maximum value comes from, consider the following
+ * equation:
+ *
+ *   new_incval = base_incval + (base_incval * adjustment) / 1billion
+ *
+ * To avoid overflow that means:
+ *   max_incval = base_incval + (base_incval * max_adj) / billion
+ *
+ * Re-arranging:
+ *   max_adj = floor(((max_incval - base_incval) * 1billion) / 1billion)
  */
 #define INCVALUE_96MHZ		125
 #define INCVALUE_SHIFT_96MHZ	17
 #define INCPERIOD_SHIFT_96MHZ	2
 #define INCPERIOD_96MHZ		(12 >> INCPERIOD_SHIFT_96MHZ)
+#define MAX_PPB_96MHZ		23999900 /* 23,999,900 ppb */
 
 #define INCVALUE_25MHZ		40
 #define INCVALUE_SHIFT_25MHZ	18
 #define INCPERIOD_25MHZ		1
+#define MAX_PPB_25MHZ		599999900 /* 599,999,900 ppb */
 
 #define INCVALUE_24MHZ		125
 #define INCVALUE_SHIFT_24MHZ	14
 #define INCPERIOD_24MHZ		3
+#define MAX_PPB_24MHZ		999999999 /* 999,999,999 ppb */
 
 #define INCVALUE_38400KHZ	26
 #define INCVALUE_SHIFT_38400KHZ	19
 #define INCPERIOD_38400KHZ	1
+#define MAX_PPB_38400KHZ	230769100 /* 230,769,100 ppb */
 
 /* Another drawback of scaling the incvalue by a large factor is the
  * 64-bit SYSTIM register overflows more quickly.  This is dealt with
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index a2788fd5f8bb..19e450a5bd31 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -2559,7 +2559,7 @@ void e1000_copy_rx_addrs_to_phy_ich8lan(struct e1000_hw *hw)
 		hw->phy.ops.write_reg_page(hw, BM_RAR_H(i),
 					   (u16)(mac_reg & 0xFFFF));
 		hw->phy.ops.write_reg_page(hw, BM_RAR_CTRL(i),
-					   FIELD_GET(E1000_RAH_AV, mac_reg));
+					   (u16)((mac_reg & E1000_RAH_AV) >> 16));
 	}
 
 	e1000_disable_phy_wakeup_reg_access_bm(hw, &phy_reg);
diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index 02d871bc112a..bbcfd529399b 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -280,8 +280,17 @@ void e1000e_ptp_init(struct e1000_adapter *adapter)
 
 	switch (hw->mac.type) {
 	case e1000_pch2lan:
+		adapter->ptp_clock_info.max_adj = MAX_PPB_96MHZ;
+		break;
 	case e1000_pch_lpt:
+		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)
+			adapter->ptp_clock_info.max_adj = MAX_PPB_96MHZ;
+		else
+			adapter->ptp_clock_info.max_adj = MAX_PPB_25MHZ;
+		break;
 	case e1000_pch_spt:
+		adapter->ptp_clock_info.max_adj = MAX_PPB_24MHZ;
+		break;
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
@@ -289,15 +298,14 @@ void e1000e_ptp_init(struct e1000_adapter *adapter)
 	case e1000_pch_lnp:
 	case e1000_pch_ptp:
 	case e1000_pch_nvp:
-		if ((hw->mac.type < e1000_pch_lpt) ||
-		    (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)) {
-			adapter->ptp_clock_info.max_adj = 24000000 - 1;
-			break;
-		}
-		fallthrough;
+		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)
+			adapter->ptp_clock_info.max_adj = MAX_PPB_24MHZ;
+		else
+			adapter->ptp_clock_info.max_adj = MAX_PPB_38400KHZ;
+		break;
 	case e1000_82574:
 	case e1000_82583:
-		adapter->ptp_clock_info.max_adj = 600000000 - 1;
+		adapter->ptp_clock_info.max_adj = MAX_PPB_25MHZ;
 		break;
 	default:
 		break;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 18a1c3b6d72c..c8f35d4de271 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -5,6 +5,7 @@
 #define _I40E_ADMINQ_CMD_H_
 
 #include <linux/bits.h>
+#include <linux/types.h>
 
 /* This header file defines the i40e Admin Queue commands and is shared between
  * i40e Firmware and Software.
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
index 9d88ed6105fd..8db1eb0c1768 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
@@ -1523,7 +1523,7 @@ void i40e_dcb_hw_rx_ets_bw_config(struct i40e_hw *hw, u8 *bw_share,
 		reg = rd32(hw, I40E_PRTDCB_RETSTCC(i));
 		reg &= ~(I40E_PRTDCB_RETSTCC_BWSHARE_MASK     |
 			 I40E_PRTDCB_RETSTCC_UPINTC_MODE_MASK |
-			 I40E_PRTDCB_RETSTCC_ETSTC_SHIFT);
+			 I40E_PRTDCB_RETSTCC_ETSTC_MASK);
 		reg |= FIELD_PREP(I40E_PRTDCB_RETSTCC_BWSHARE_MASK,
 				  bw_share[i]);
 		reg |= FIELD_PREP(I40E_PRTDCB_RETSTCC_UPINTC_MODE_MASK,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.h b/drivers/net/ethernet/intel/i40e/i40e_dcb.h
index 6b60dc9b7736..d76497566e40 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.h
@@ -43,7 +43,7 @@
 #define I40E_LLDP_TLV_SUBTYPE_SHIFT	0
 #define I40E_LLDP_TLV_SUBTYPE_MASK	(0xFF << I40E_LLDP_TLV_SUBTYPE_SHIFT)
 #define I40E_LLDP_TLV_OUI_SHIFT		8
-#define I40E_LLDP_TLV_OUI_MASK		(0xFFFFFF << I40E_LLDP_TLV_OUI_SHIFT)
+#define I40E_LLDP_TLV_OUI_MASK		(0xFFFFFFU << I40E_LLDP_TLV_OUI_SHIFT)
 
 /* Defines for IEEE ETS TLV */
 #define I40E_IEEE_ETS_MAXTC_SHIFT	0
diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.h b/drivers/net/ethernet/intel/i40e/i40e_diag.h
index ece3a6b9a5c6..ab20202a3da3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_diag.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_diag.h
@@ -4,6 +4,7 @@
 #ifndef _I40E_DIAG_H_
 #define _I40E_DIAG_H_
 
+#include <linux/types.h>
 #include "i40e_adminq_cmd.h"
 
 /* forward-declare the HW struct for the compiler */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index ae8f9f135725..89a3401d20ab 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3588,40 +3588,55 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	struct i40e_hmc_obj_rxq rx_ctx;
 	int err = 0;
 	bool ok;
-	int ret;
 
 	bitmap_zero(ring->state, __I40E_RING_STATE_NBITS);
 
 	/* clear the context structure first */
 	memset(&rx_ctx, 0, sizeof(rx_ctx));
 
-	if (ring->vsi->type == I40E_VSI_MAIN)
-		xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
+	ring->rx_buf_len = vsi->rx_buf_len;
+
+	/* XDP RX-queue info only needed for RX rings exposed to XDP */
+	if (ring->vsi->type != I40E_VSI_MAIN)
+		goto skip;
+
+	if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
+		err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+					 ring->queue_index,
+					 ring->q_vector->napi.napi_id,
+					 ring->rx_buf_len);
+		if (err)
+			return err;
+	}
 
 	ring->xsk_pool = i40e_xsk_pool(ring);
 	if (ring->xsk_pool) {
-		ring->rx_buf_len =
-		  xsk_pool_get_rx_frame_size(ring->xsk_pool);
-		ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+		xdp_rxq_info_unreg(&ring->xdp_rxq);
+		ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool);
+		err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+					 ring->queue_index,
+					 ring->q_vector->napi.napi_id,
+					 ring->rx_buf_len);
+		if (err)
+			return err;
+		err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 						 MEM_TYPE_XSK_BUFF_POOL,
 						 NULL);
-		if (ret)
-			return ret;
+		if (err)
+			return err;
 		dev_info(&vsi->back->pdev->dev,
 			 "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
 			 ring->queue_index);
 
 	} else {
-		ring->rx_buf_len = vsi->rx_buf_len;
-		if (ring->vsi->type == I40E_VSI_MAIN) {
-			ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
-							 MEM_TYPE_PAGE_SHARED,
-							 NULL);
-			if (ret)
-				return ret;
-		}
+		err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+						 MEM_TYPE_PAGE_SHARED,
+						 NULL);
+		if (err)
+			return err;
 	}
 
+skip:
 	xdp_init_buff(&ring->xdp, i40e_rx_pg_size(ring) / 2, &ring->xdp_rxq);
 
 	rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len,
@@ -4911,27 +4926,23 @@ int i40e_vsi_start_rings(struct i40e_vsi *vsi)
 void i40e_vsi_stop_rings(struct i40e_vsi *vsi)
 {
 	struct i40e_pf *pf = vsi->back;
-	int pf_q, err, q_end;
+	u32 pf_q, tx_q_end, rx_q_end;
 
 	/* When port TX is suspended, don't wait */
 	if (test_bit(__I40E_PORT_SUSPENDED, vsi->back->state))
 		return i40e_vsi_stop_rings_no_wait(vsi);
 
-	q_end = vsi->base_queue + vsi->num_queue_pairs;
-	for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++)
-		i40e_pre_tx_queue_cfg(&pf->hw, (u32)pf_q, false);
+	tx_q_end = vsi->base_queue +
+		vsi->alloc_queue_pairs * (i40e_enabled_xdp_vsi(vsi) ? 2 : 1);
+	for (pf_q = vsi->base_queue; pf_q < tx_q_end; pf_q++)
+		i40e_pre_tx_queue_cfg(&pf->hw, pf_q, false);
 
-	for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) {
-		err = i40e_control_wait_rx_q(pf, pf_q, false);
-		if (err)
-			dev_info(&pf->pdev->dev,
-				 "VSI seid %d Rx ring %d disable timeout\n",
-				 vsi->seid, pf_q);
-	}
+	rx_q_end = vsi->base_queue + vsi->num_queue_pairs;
+	for (pf_q = vsi->base_queue; pf_q < rx_q_end; pf_q++)
+		i40e_control_rx_q(pf, pf_q, false);
 
 	msleep(I40E_DISABLE_TX_GAP_MSEC);
-	pf_q = vsi->base_queue;
-	for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++)
+	for (pf_q = vsi->base_queue; pf_q < tx_q_end; pf_q++)
 		wr32(&pf->hw, I40E_QTX_ENA(pf_q), 0);
 
 	i40e_vsi_wait_queues_disabled(vsi);
@@ -5345,7 +5356,7 @@ static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf)
 {
 	int v, ret = 0;
 
-	for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+	for (v = 0; v < pf->num_alloc_vsi; v++) {
 		if (pf->vsi[v]) {
 			ret = i40e_vsi_wait_queues_disabled(pf->vsi[v]);
 			if (ret)
@@ -13549,9 +13560,9 @@ int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair)
 		return err;
 
 	i40e_queue_pair_disable_irq(vsi, queue_pair);
+	i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */);
 	err = i40e_queue_pair_toggle_rings(vsi, queue_pair, false /* off */);
 	i40e_clean_rx_ring(vsi->rx_rings[queue_pair]);
-	i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */);
 	i40e_queue_pair_clean_rings(vsi, queue_pair);
 	i40e_queue_pair_reset_stats(vsi, queue_pair);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index af4269330581..ce1f11b8ad65 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -567,8 +567,7 @@ static inline bool i40e_is_fw_ver_lt(struct i40e_hw *hw, u16 maj, u16 min)
  **/
 static inline bool i40e_is_fw_ver_eq(struct i40e_hw *hw, u16 maj, u16 min)
 {
-	return (hw->aq.fw_maj_ver > maj ||
-		(hw->aq.fw_maj_ver == maj && hw->aq.fw_min_ver == min));
+	return (hw->aq.fw_maj_ver == maj && hw->aq.fw_min_ver == min);
 }
 
 #endif /* _I40E_PROTOTYPE_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 971ba3322038..0d7177083708 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1548,7 +1548,6 @@ void i40e_free_rx_resources(struct i40e_ring *rx_ring)
 int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
 {
 	struct device *dev = rx_ring->dev;
-	int err;
 
 	u64_stats_init(&rx_ring->syncp);
 
@@ -1569,14 +1568,6 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
 	rx_ring->next_to_process = 0;
 	rx_ring->next_to_use = 0;
 
-	/* XDP RX-queue info only needed for RX rings exposed to XDP */
-	if (rx_ring->vsi->type == I40E_VSI_MAIN) {
-		err = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
-				       rx_ring->queue_index, rx_ring->q_vector->napi.napi_id);
-		if (err < 0)
-			return err;
-	}
-
 	rx_ring->xdp_prog = rx_ring->vsi->xdp_prog;
 
 	rx_ring->rx_bi =
@@ -2087,7 +2078,8 @@ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring,
 static void i40e_process_rx_buffs(struct i40e_ring *rx_ring, int xdp_res,
 				  struct xdp_buff *xdp)
 {
-	u32 next = rx_ring->next_to_clean;
+	u32 nr_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags;
+	u32 next = rx_ring->next_to_clean, i = 0;
 	struct i40e_rx_buffer *rx_buffer;
 
 	xdp->flags = 0;
@@ -2100,10 +2092,10 @@ static void i40e_process_rx_buffs(struct i40e_ring *rx_ring, int xdp_res,
 		if (!rx_buffer->page)
 			continue;
 
-		if (xdp_res == I40E_XDP_CONSUMED)
-			rx_buffer->pagecnt_bias++;
-		else
+		if (xdp_res != I40E_XDP_CONSUMED)
 			i40e_rx_buffer_flip(rx_buffer, xdp->frame_sz);
+		else if (i++ <= nr_frags)
+			rx_buffer->pagecnt_bias++;
 
 		/* EOP buffer will be put in i40e_clean_rx_irq() */
 		if (next == rx_ring->next_to_process)
@@ -2117,20 +2109,20 @@ static void i40e_process_rx_buffs(struct i40e_ring *rx_ring, int xdp_res,
  * i40e_construct_skb - Allocate skb and populate it
  * @rx_ring: rx descriptor ring to transact packets on
  * @xdp: xdp_buff pointing to the data
- * @nr_frags: number of buffers for the packet
  *
  * This function allocates an skb.  It then populates it with the page
  * data from the current receive descriptor, taking care to set up the
  * skb correctly.
  */
 static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
-					  struct xdp_buff *xdp,
-					  u32 nr_frags)
+					  struct xdp_buff *xdp)
 {
 	unsigned int size = xdp->data_end - xdp->data;
 	struct i40e_rx_buffer *rx_buffer;
+	struct skb_shared_info *sinfo;
 	unsigned int headlen;
 	struct sk_buff *skb;
+	u32 nr_frags = 0;
 
 	/* prefetch first cache line of first page */
 	net_prefetch(xdp->data);
@@ -2168,6 +2160,10 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
 	memcpy(__skb_put(skb, headlen), xdp->data,
 	       ALIGN(headlen, sizeof(long)));
 
+	if (unlikely(xdp_buff_has_frags(xdp))) {
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		nr_frags = sinfo->nr_frags;
+	}
 	rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
 	/* update all of the pointers */
 	size -= headlen;
@@ -2187,9 +2183,8 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
 	}
 
 	if (unlikely(xdp_buff_has_frags(xdp))) {
-		struct skb_shared_info *sinfo, *skinfo = skb_shinfo(skb);
+		struct skb_shared_info *skinfo = skb_shinfo(skb);
 
-		sinfo = xdp_get_shared_info_from_buff(xdp);
 		memcpy(&skinfo->frags[skinfo->nr_frags], &sinfo->frags[0],
 		       sizeof(skb_frag_t) * nr_frags);
 
@@ -2212,17 +2207,17 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
  * i40e_build_skb - Build skb around an existing buffer
  * @rx_ring: Rx descriptor ring to transact packets on
  * @xdp: xdp_buff pointing to the data
- * @nr_frags: number of buffers for the packet
  *
  * This function builds an skb around an existing Rx buffer, taking care
  * to set up the skb correctly and avoid any memcpy overhead.
  */
 static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
-				      struct xdp_buff *xdp,
-				      u32 nr_frags)
+				      struct xdp_buff *xdp)
 {
 	unsigned int metasize = xdp->data - xdp->data_meta;
+	struct skb_shared_info *sinfo;
 	struct sk_buff *skb;
+	u32 nr_frags;
 
 	/* Prefetch first cache line of first page. If xdp->data_meta
 	 * is unused, this points exactly as xdp->data, otherwise we
@@ -2231,6 +2226,11 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
 	 */
 	net_prefetch(xdp->data_meta);
 
+	if (unlikely(xdp_buff_has_frags(xdp))) {
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		nr_frags = sinfo->nr_frags;
+	}
+
 	/* build an skb around the page buffer */
 	skb = napi_build_skb(xdp->data_hard_start, xdp->frame_sz);
 	if (unlikely(!skb))
@@ -2243,9 +2243,6 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
 		skb_metadata_set(skb, metasize);
 
 	if (unlikely(xdp_buff_has_frags(xdp))) {
-		struct skb_shared_info *sinfo;
-
-		sinfo = xdp_get_shared_info_from_buff(xdp);
 		xdp_update_skb_shared_info(skb, nr_frags,
 					   sinfo->xdp_frags_size,
 					   nr_frags * xdp->frame_sz,
@@ -2589,9 +2586,9 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget,
 			total_rx_bytes += size;
 		} else {
 			if (ring_uses_build_skb(rx_ring))
-				skb = i40e_build_skb(rx_ring, xdp, nfrags);
+				skb = i40e_build_skb(rx_ring, xdp);
 			else
-				skb = i40e_construct_skb(rx_ring, xdp, nfrags);
+				skb = i40e_construct_skb(rx_ring, xdp);
 
 			/* drop if we failed to retrieve a buffer */
 			if (!skb) {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 908cdbd3ec5d..b34c71770887 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -2848,6 +2848,24 @@ error_param:
 				      (u8 *)&stats, sizeof(stats));
 }
 
+/**
+ * i40e_can_vf_change_mac
+ * @vf: pointer to the VF info
+ *
+ * Return true if the VF is allowed to change its MAC filters, false otherwise
+ */
+static bool i40e_can_vf_change_mac(struct i40e_vf *vf)
+{
+	/* If the VF MAC address has been set administratively (via the
+	 * ndo_set_vf_mac command), then deny permission to the VF to
+	 * add/delete unicast MAC addresses, unless the VF is trusted
+	 */
+	if (vf->pf_set_mac && !vf->trusted)
+		return false;
+
+	return true;
+}
+
 #define I40E_MAX_MACVLAN_PER_HW 3072
 #define I40E_MAX_MACVLAN_PER_PF(num_ports) (I40E_MAX_MACVLAN_PER_HW /	\
 	(num_ports))
@@ -2907,8 +2925,8 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf,
 		 * The VF may request to set the MAC address filter already
 		 * assigned to it so do not return an error in that case.
 		 */
-		if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps) &&
-		    !is_multicast_ether_addr(addr) && vf->pf_set_mac &&
+		if (!i40e_can_vf_change_mac(vf) &&
+		    !is_multicast_ether_addr(addr) &&
 		    !ether_addr_equal(addr, vf->default_lan_addr.addr)) {
 			dev_err(&pf->pdev->dev,
 				"VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n");
@@ -3114,19 +3132,29 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
 			ret = -EINVAL;
 			goto error_param;
 		}
-		if (ether_addr_equal(al->list[i].addr, vf->default_lan_addr.addr))
-			was_unimac_deleted = true;
 	}
 	vsi = pf->vsi[vf->lan_vsi_idx];
 
 	spin_lock_bh(&vsi->mac_filter_hash_lock);
 	/* delete addresses from the list */
-	for (i = 0; i < al->num_elements; i++)
+	for (i = 0; i < al->num_elements; i++) {
+		const u8 *addr = al->list[i].addr;
+
+		/* Allow to delete VF primary MAC only if it was not set
+		 * administratively by PF or if VF is trusted.
+		 */
+		if (ether_addr_equal(addr, vf->default_lan_addr.addr) &&
+		    i40e_can_vf_change_mac(vf))
+			was_unimac_deleted = true;
+		else
+			continue;
+
 		if (i40e_del_mac_filter(vsi, al->list[i].addr)) {
 			ret = -EINVAL;
 			spin_unlock_bh(&vsi->mac_filter_hash_lock);
 			goto error_param;
 		}
+	}
 
 	spin_unlock_bh(&vsi->mac_filter_hash_lock);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index af7d5fa6cdc1..11500003af0d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -414,7 +414,8 @@ i40e_add_xsk_frag(struct i40e_ring *rx_ring, struct xdp_buff *first,
 	}
 
 	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++,
-				   virt_to_page(xdp->data_hard_start), 0, size);
+				   virt_to_page(xdp->data_hard_start),
+				   XDP_PACKET_HEADROOM, size);
 	sinfo->xdp_frags_size += size;
 	xsk_buff_add_frag(xdp);
 
@@ -498,7 +499,6 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 		xdp_res = i40e_run_xdp_zc(rx_ring, first, xdp_prog);
 		i40e_handle_xdp_result_zc(rx_ring, first, rx_desc, &rx_packets,
 					  &rx_bytes, xdp_res, &failure);
-		first->flags = 0;
 		next_to_clean = next_to_process;
 		if (failure)
 			break;
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 533b923cae2d..c979192e44d1 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -190,15 +190,13 @@ static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx)
 	q_vector = vsi->q_vectors[v_idx];
 
 	ice_for_each_tx_ring(tx_ring, q_vector->tx) {
-		if (vsi->netdev)
-			netif_queue_set_napi(vsi->netdev, tx_ring->q_index,
-					     NETDEV_QUEUE_TYPE_TX, NULL);
+		ice_queue_set_napi(vsi, tx_ring->q_index, NETDEV_QUEUE_TYPE_TX,
+				   NULL);
 		tx_ring->q_vector = NULL;
 	}
 	ice_for_each_rx_ring(rx_ring, q_vector->rx) {
-		if (vsi->netdev)
-			netif_queue_set_napi(vsi->netdev, rx_ring->q_index,
-					     NETDEV_QUEUE_TYPE_RX, NULL);
+		ice_queue_set_napi(vsi, rx_ring->q_index, NETDEV_QUEUE_TYPE_RX,
+				   NULL);
 		rx_ring->q_vector = NULL;
 	}
 
@@ -547,19 +545,27 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 	ring->rx_buf_len = ring->vsi->rx_buf_len;
 
 	if (ring->vsi->type == ICE_VSI_PF) {
-		if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
-			/* coverity[check_return] */
-			__xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
-					   ring->q_index,
-					   ring->q_vector->napi.napi_id,
-					   ring->vsi->rx_buf_len);
+		if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
+			err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+						 ring->q_index,
+						 ring->q_vector->napi.napi_id,
+						 ring->rx_buf_len);
+			if (err)
+				return err;
+		}
 
 		ring->xsk_pool = ice_xsk_pool(ring);
 		if (ring->xsk_pool) {
-			xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
+			xdp_rxq_info_unreg(&ring->xdp_rxq);
 
 			ring->rx_buf_len =
 				xsk_pool_get_rx_frame_size(ring->xsk_pool);
+			err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+						 ring->q_index,
+						 ring->q_vector->napi.napi_id,
+						 ring->rx_buf_len);
+			if (err)
+				return err;
 			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 							 MEM_TYPE_XSK_BUFF_POOL,
 							 NULL);
@@ -571,13 +577,14 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
 				 ring->q_index);
 		} else {
-			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
-				/* coverity[check_return] */
-				__xdp_rxq_info_reg(&ring->xdp_rxq,
-						   ring->netdev,
-						   ring->q_index,
-						   ring->q_vector->napi.napi_id,
-						   ring->vsi->rx_buf_len);
+			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
+				err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+							 ring->q_index,
+							 ring->q_vector->napi.napi_id,
+							 ring->rx_buf_len);
+				if (err)
+					return err;
+			}
 
 			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 							 MEM_TYPE_PAGE_SHARED,
diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c
index b9c5eced6326..bd9b1fed74ab 100644
--- a/drivers/net/ethernet/intel/ice/ice_dpll.c
+++ b/drivers/net/ethernet/intel/ice/ice_dpll.c
@@ -31,6 +31,26 @@ static const char * const pin_type_name[] = {
 };
 
 /**
+ * ice_dpll_is_reset - check if reset is in progress
+ * @pf: private board structure
+ * @extack: error reporting
+ *
+ * If reset is in progress, fill extack with error.
+ *
+ * Return:
+ * * false - no reset in progress
+ * * true - reset in progress
+ */
+static bool ice_dpll_is_reset(struct ice_pf *pf, struct netlink_ext_ack *extack)
+{
+	if (ice_is_reset_in_progress(pf->state)) {
+		NL_SET_ERR_MSG(extack, "PF reset in progress");
+		return true;
+	}
+	return false;
+}
+
+/**
  * ice_dpll_pin_freq_set - set pin's frequency
  * @pf: private board structure
  * @pin: pointer to a pin
@@ -109,6 +129,9 @@ ice_dpll_frequency_set(const struct dpll_pin *pin, void *pin_priv,
 	struct ice_pf *pf = d->pf;
 	int ret;
 
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+
 	mutex_lock(&pf->dplls.lock);
 	ret = ice_dpll_pin_freq_set(pf, p, pin_type, frequency, extack);
 	mutex_unlock(&pf->dplls.lock);
@@ -254,6 +277,7 @@ ice_dpll_output_frequency_get(const struct dpll_pin *pin, void *pin_priv,
  * ice_dpll_pin_enable - enable a pin on dplls
  * @hw: board private hw structure
  * @pin: pointer to a pin
+ * @dpll_idx: dpll index to connect to output pin
  * @pin_type: type of pin being enabled
  * @extack: error reporting
  *
@@ -266,7 +290,7 @@ ice_dpll_output_frequency_get(const struct dpll_pin *pin, void *pin_priv,
  */
 static int
 ice_dpll_pin_enable(struct ice_hw *hw, struct ice_dpll_pin *pin,
-		    enum ice_dpll_pin_type pin_type,
+		    u8 dpll_idx, enum ice_dpll_pin_type pin_type,
 		    struct netlink_ext_ack *extack)
 {
 	u8 flags = 0;
@@ -280,10 +304,12 @@ ice_dpll_pin_enable(struct ice_hw *hw, struct ice_dpll_pin *pin,
 		ret = ice_aq_set_input_pin_cfg(hw, pin->idx, 0, flags, 0, 0);
 		break;
 	case ICE_DPLL_PIN_TYPE_OUTPUT:
+		flags = ICE_AQC_SET_CGU_OUT_CFG_UPDATE_SRC_SEL;
 		if (pin->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN)
 			flags |= ICE_AQC_SET_CGU_OUT_CFG_ESYNC_EN;
 		flags |= ICE_AQC_SET_CGU_OUT_CFG_OUT_EN;
-		ret = ice_aq_set_output_pin_cfg(hw, pin->idx, flags, 0, 0, 0);
+		ret = ice_aq_set_output_pin_cfg(hw, pin->idx, flags, dpll_idx,
+						0, 0);
 		break;
 	default:
 		return -EINVAL;
@@ -370,7 +396,7 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin,
 	case ICE_DPLL_PIN_TYPE_INPUT:
 		ret = ice_aq_get_input_pin_cfg(&pf->hw, pin->idx, NULL, NULL,
 					       NULL, &pin->flags[0],
-					       &pin->freq, NULL);
+					       &pin->freq, &pin->phase_adjust);
 		if (ret)
 			goto err;
 		if (ICE_AQC_GET_CGU_IN_CFG_FLG2_INPUT_EN & pin->flags[0]) {
@@ -398,14 +424,27 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin,
 		break;
 	case ICE_DPLL_PIN_TYPE_OUTPUT:
 		ret = ice_aq_get_output_pin_cfg(&pf->hw, pin->idx,
-						&pin->flags[0], NULL,
+						&pin->flags[0], &parent,
 						&pin->freq, NULL);
 		if (ret)
 			goto err;
-		if (ICE_AQC_SET_CGU_OUT_CFG_OUT_EN & pin->flags[0])
-			pin->state[0] = DPLL_PIN_STATE_CONNECTED;
-		else
-			pin->state[0] = DPLL_PIN_STATE_DISCONNECTED;
+
+		parent &= ICE_AQC_GET_CGU_OUT_CFG_DPLL_SRC_SEL;
+		if (ICE_AQC_SET_CGU_OUT_CFG_OUT_EN & pin->flags[0]) {
+			pin->state[pf->dplls.eec.dpll_idx] =
+				parent == pf->dplls.eec.dpll_idx ?
+				DPLL_PIN_STATE_CONNECTED :
+				DPLL_PIN_STATE_DISCONNECTED;
+			pin->state[pf->dplls.pps.dpll_idx] =
+				parent == pf->dplls.pps.dpll_idx ?
+				DPLL_PIN_STATE_CONNECTED :
+				DPLL_PIN_STATE_DISCONNECTED;
+		} else {
+			pin->state[pf->dplls.eec.dpll_idx] =
+				DPLL_PIN_STATE_DISCONNECTED;
+			pin->state[pf->dplls.pps.dpll_idx] =
+				DPLL_PIN_STATE_DISCONNECTED;
+		}
 		break;
 	case ICE_DPLL_PIN_TYPE_RCLK_INPUT:
 		for (parent = 0; parent < pf->dplls.rclk.num_parents;
@@ -568,9 +607,13 @@ ice_dpll_pin_state_set(const struct dpll_pin *pin, void *pin_priv,
 	struct ice_pf *pf = d->pf;
 	int ret;
 
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+
 	mutex_lock(&pf->dplls.lock);
 	if (enable)
-		ret = ice_dpll_pin_enable(&pf->hw, p, pin_type, extack);
+		ret = ice_dpll_pin_enable(&pf->hw, p, d->dpll_idx, pin_type,
+					  extack);
 	else
 		ret = ice_dpll_pin_disable(&pf->hw, p, pin_type, extack);
 	if (!ret)
@@ -603,6 +646,11 @@ ice_dpll_output_state_set(const struct dpll_pin *pin, void *pin_priv,
 			  struct netlink_ext_ack *extack)
 {
 	bool enable = state == DPLL_PIN_STATE_CONNECTED;
+	struct ice_dpll_pin *p = pin_priv;
+	struct ice_dpll *d = dpll_priv;
+
+	if (!enable && p->state[d->dpll_idx] == DPLL_PIN_STATE_DISCONNECTED)
+		return 0;
 
 	return ice_dpll_pin_state_set(pin, pin_priv, dpll, dpll_priv, enable,
 				      extack, ICE_DPLL_PIN_TYPE_OUTPUT);
@@ -665,14 +713,16 @@ ice_dpll_pin_state_get(const struct dpll_pin *pin, void *pin_priv,
 	struct ice_pf *pf = d->pf;
 	int ret;
 
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+
 	mutex_lock(&pf->dplls.lock);
 	ret = ice_dpll_pin_state_update(pf, p, pin_type, extack);
 	if (ret)
 		goto unlock;
-	if (pin_type == ICE_DPLL_PIN_TYPE_INPUT)
+	if (pin_type == ICE_DPLL_PIN_TYPE_INPUT ||
+	    pin_type == ICE_DPLL_PIN_TYPE_OUTPUT)
 		*state = p->state[d->dpll_idx];
-	else if (pin_type == ICE_DPLL_PIN_TYPE_OUTPUT)
-		*state = p->state[0];
 	ret = 0;
 unlock:
 	mutex_unlock(&pf->dplls.lock);
@@ -790,6 +840,9 @@ ice_dpll_input_prio_set(const struct dpll_pin *pin, void *pin_priv,
 	struct ice_pf *pf = d->pf;
 	int ret;
 
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+
 	mutex_lock(&pf->dplls.lock);
 	ret = ice_dpll_hw_input_prio_set(pf, d, p, prio, extack);
 	mutex_unlock(&pf->dplls.lock);
@@ -910,6 +963,9 @@ ice_dpll_pin_phase_adjust_set(const struct dpll_pin *pin, void *pin_priv,
 	u8 flag, flags_en = 0;
 	int ret;
 
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+
 	mutex_lock(&pf->dplls.lock);
 	switch (type) {
 	case ICE_DPLL_PIN_TYPE_INPUT:
@@ -1069,6 +1125,9 @@ ice_dpll_rclk_state_on_pin_set(const struct dpll_pin *pin, void *pin_priv,
 	int ret = -EINVAL;
 	u32 hw_idx;
 
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+
 	mutex_lock(&pf->dplls.lock);
 	hw_idx = parent->idx - pf->dplls.base_rclk_idx;
 	if (hw_idx >= pf->dplls.num_inputs)
@@ -1123,6 +1182,9 @@ ice_dpll_rclk_state_on_pin_get(const struct dpll_pin *pin, void *pin_priv,
 	int ret = -EINVAL;
 	u32 hw_idx;
 
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+
 	mutex_lock(&pf->dplls.lock);
 	hw_idx = parent->idx - pf->dplls.base_rclk_idx;
 	if (hw_idx >= pf->dplls.num_inputs)
@@ -1305,8 +1367,10 @@ static void ice_dpll_periodic_work(struct kthread_work *work)
 	struct ice_pf *pf = container_of(d, struct ice_pf, dplls);
 	struct ice_dpll *de = &pf->dplls.eec;
 	struct ice_dpll *dp = &pf->dplls.pps;
-	int ret;
+	int ret = 0;
 
+	if (ice_is_reset_in_progress(pf->state))
+		goto resched;
 	mutex_lock(&pf->dplls.lock);
 	ret = ice_dpll_update_state(pf, de, false);
 	if (!ret)
@@ -1326,6 +1390,7 @@ static void ice_dpll_periodic_work(struct kthread_work *work)
 	ice_dpll_notify_changes(de);
 	ice_dpll_notify_changes(dp);
 
+resched:
 	/* Run twice a second or reschedule if update failed */
 	kthread_queue_delayed_work(d->kworker, &d->work,
 				   ret ? msecs_to_jiffies(10) :
@@ -1532,7 +1597,7 @@ static void ice_dpll_deinit_rclk_pin(struct ice_pf *pf)
 	}
 	if (WARN_ON_ONCE(!vsi || !vsi->netdev))
 		return;
-	netdev_dpll_pin_clear(vsi->netdev);
+	dpll_netdev_pin_clear(vsi->netdev);
 	dpll_pin_put(rclk->pin);
 }
 
@@ -1576,7 +1641,7 @@ ice_dpll_init_rclk_pins(struct ice_pf *pf, struct ice_dpll_pin *pin,
 	}
 	if (WARN_ON((!vsi || !vsi->netdev)))
 		return -EINVAL;
-	netdev_dpll_pin_set(vsi->netdev, pf->dplls.rclk.pin);
+	dpll_netdev_pin_set(vsi->netdev, pf->dplls.rclk.pin);
 
 	return 0;
 
@@ -2055,6 +2120,7 @@ void ice_dpll_init(struct ice_pf *pf)
 	struct ice_dplls *d = &pf->dplls;
 	int err = 0;
 
+	mutex_init(&d->lock);
 	err = ice_dpll_init_info(pf, cgu);
 	if (err)
 		goto err_exit;
@@ -2067,7 +2133,6 @@ void ice_dpll_init(struct ice_pf *pf)
 	err = ice_dpll_init_pins(pf, cgu);
 	if (err)
 		goto deinit_pps;
-	mutex_init(&d->lock);
 	if (cgu) {
 		err = ice_dpll_init_worker(pf);
 		if (err)
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index 2a25323105e5..467372d541d2 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -152,6 +152,27 @@ ice_lag_find_hw_by_lport(struct ice_lag *lag, u8 lport)
 }
 
 /**
+ * ice_pkg_has_lport_extract - check if lport extraction supported
+ * @hw: HW struct
+ */
+static bool ice_pkg_has_lport_extract(struct ice_hw *hw)
+{
+	int i;
+
+	for (i = 0; i < hw->blk[ICE_BLK_SW].es.count; i++) {
+		u16 offset;
+		u8 fv_prot;
+
+		ice_find_prot_off(hw, ICE_BLK_SW, ICE_SW_DEFAULT_PROFILE, i,
+				  &fv_prot, &offset);
+		if (fv_prot == ICE_FV_PROT_MDID &&
+		    offset == ICE_LP_EXT_BUF_OFFSET)
+			return true;
+	}
+	return false;
+}
+
+/**
  * ice_lag_find_primary - returns pointer to primary interfaces lag struct
  * @lag: local interfaces lag struct
  */
@@ -1206,7 +1227,7 @@ static void ice_lag_del_prune_list(struct ice_lag *lag, struct ice_pf *event_pf)
 }
 
 /**
- * ice_lag_init_feature_support_flag - Check for NVM support for LAG
+ * ice_lag_init_feature_support_flag - Check for package and NVM support for LAG
  * @pf: PF struct
  */
 static void ice_lag_init_feature_support_flag(struct ice_pf *pf)
@@ -1219,7 +1240,7 @@ static void ice_lag_init_feature_support_flag(struct ice_pf *pf)
 	else
 		ice_clear_feature_support(pf, ICE_F_ROCE_LAG);
 
-	if (caps->sriov_lag)
+	if (caps->sriov_lag && ice_pkg_has_lport_extract(&pf->hw))
 		ice_set_feature_support(pf, ICE_F_SRIOV_LAG);
 	else
 		ice_clear_feature_support(pf, ICE_F_SRIOV_LAG);
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h
index ede833dfa658..183b38792ef2 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.h
+++ b/drivers/net/ethernet/intel/ice/ice_lag.h
@@ -17,6 +17,9 @@ enum ice_lag_role {
 #define ICE_LAG_INVALID_PORT 0xFF
 
 #define ICE_LAG_RESET_RETRIES		5
+#define ICE_SW_DEFAULT_PROFILE		0
+#define ICE_FV_PROT_MDID		255
+#define ICE_LP_EXT_BUF_OFFSET		32
 
 struct ice_pf;
 struct ice_vf;
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 9be724291ef8..fc23dbe302b4 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2426,7 +2426,7 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params)
 		ice_vsi_map_rings_to_vectors(vsi);
 
 		/* Associate q_vector rings to napi */
-		ice_vsi_set_napi_queues(vsi, true);
+		ice_vsi_set_napi_queues(vsi);
 
 		vsi->stat_offsets_loaded = false;
 
@@ -2904,19 +2904,19 @@ void ice_vsi_dis_irq(struct ice_vsi *vsi)
 }
 
 /**
- * ice_queue_set_napi - Set the napi instance for the queue
+ * __ice_queue_set_napi - Set the napi instance for the queue
  * @dev: device to which NAPI and queue belong
  * @queue_index: Index of queue
  * @type: queue type as RX or TX
  * @napi: NAPI context
  * @locked: is the rtnl_lock already held
  *
- * Set the napi instance for the queue
+ * Set the napi instance for the queue. Caller indicates the lock status.
  */
 static void
-ice_queue_set_napi(struct net_device *dev, unsigned int queue_index,
-		   enum netdev_queue_type type, struct napi_struct *napi,
-		   bool locked)
+__ice_queue_set_napi(struct net_device *dev, unsigned int queue_index,
+		     enum netdev_queue_type type, struct napi_struct *napi,
+		     bool locked)
 {
 	if (!locked)
 		rtnl_lock();
@@ -2926,26 +2926,79 @@ ice_queue_set_napi(struct net_device *dev, unsigned int queue_index,
 }
 
 /**
- * ice_q_vector_set_napi_queues - Map queue[s] associated with the napi
+ * ice_queue_set_napi - Set the napi instance for the queue
+ * @vsi: VSI being configured
+ * @queue_index: Index of queue
+ * @type: queue type as RX or TX
+ * @napi: NAPI context
+ *
+ * Set the napi instance for the queue. The rtnl lock state is derived from the
+ * execution path.
+ */
+void
+ice_queue_set_napi(struct ice_vsi *vsi, unsigned int queue_index,
+		   enum netdev_queue_type type, struct napi_struct *napi)
+{
+	struct ice_pf *pf = vsi->back;
+
+	if (!vsi->netdev)
+		return;
+
+	if (current_work() == &pf->serv_task ||
+	    test_bit(ICE_PREPARED_FOR_RESET, pf->state) ||
+	    test_bit(ICE_DOWN, pf->state) ||
+	    test_bit(ICE_SUSPENDED, pf->state))
+		__ice_queue_set_napi(vsi->netdev, queue_index, type, napi,
+				     false);
+	else
+		__ice_queue_set_napi(vsi->netdev, queue_index, type, napi,
+				     true);
+}
+
+/**
+ * __ice_q_vector_set_napi_queues - Map queue[s] associated with the napi
  * @q_vector: q_vector pointer
  * @locked: is the rtnl_lock already held
  *
+ * Associate the q_vector napi with all the queue[s] on the vector.
+ * Caller indicates the lock status.
+ */
+void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked)
+{
+	struct ice_rx_ring *rx_ring;
+	struct ice_tx_ring *tx_ring;
+
+	ice_for_each_rx_ring(rx_ring, q_vector->rx)
+		__ice_queue_set_napi(q_vector->vsi->netdev, rx_ring->q_index,
+				     NETDEV_QUEUE_TYPE_RX, &q_vector->napi,
+				     locked);
+
+	ice_for_each_tx_ring(tx_ring, q_vector->tx)
+		__ice_queue_set_napi(q_vector->vsi->netdev, tx_ring->q_index,
+				     NETDEV_QUEUE_TYPE_TX, &q_vector->napi,
+				     locked);
+	/* Also set the interrupt number for the NAPI */
+	netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq);
+}
+
+/**
+ * ice_q_vector_set_napi_queues - Map queue[s] associated with the napi
+ * @q_vector: q_vector pointer
+ *
  * Associate the q_vector napi with all the queue[s] on the vector
  */
-void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked)
+void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector)
 {
 	struct ice_rx_ring *rx_ring;
 	struct ice_tx_ring *tx_ring;
 
 	ice_for_each_rx_ring(rx_ring, q_vector->rx)
-		ice_queue_set_napi(q_vector->vsi->netdev, rx_ring->q_index,
-				   NETDEV_QUEUE_TYPE_RX, &q_vector->napi,
-				   locked);
+		ice_queue_set_napi(q_vector->vsi, rx_ring->q_index,
+				   NETDEV_QUEUE_TYPE_RX, &q_vector->napi);
 
 	ice_for_each_tx_ring(tx_ring, q_vector->tx)
-		ice_queue_set_napi(q_vector->vsi->netdev, tx_ring->q_index,
-				   NETDEV_QUEUE_TYPE_TX, &q_vector->napi,
-				   locked);
+		ice_queue_set_napi(q_vector->vsi, tx_ring->q_index,
+				   NETDEV_QUEUE_TYPE_TX, &q_vector->napi);
 	/* Also set the interrupt number for the NAPI */
 	netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq);
 }
@@ -2953,11 +3006,10 @@ void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked)
 /**
  * ice_vsi_set_napi_queues
  * @vsi: VSI pointer
- * @locked: is the rtnl_lock already held
  *
  * Associate queue[s] with napi for all vectors
  */
-void ice_vsi_set_napi_queues(struct ice_vsi *vsi, bool locked)
+void ice_vsi_set_napi_queues(struct ice_vsi *vsi)
 {
 	int i;
 
@@ -2965,7 +3017,7 @@ void ice_vsi_set_napi_queues(struct ice_vsi *vsi, bool locked)
 		return;
 
 	ice_for_each_q_vector(vsi, i)
-		ice_q_vector_set_napi_queues(vsi->q_vectors[i], locked);
+		ice_q_vector_set_napi_queues(vsi->q_vectors[i]);
 }
 
 /**
@@ -3140,7 +3192,7 @@ ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi)
 		}
 	}
 
-	tx_ring_stats = vsi_stat->rx_ring_stats;
+	tx_ring_stats = vsi_stat->tx_ring_stats;
 	vsi_stat->tx_ring_stats =
 		krealloc_array(vsi_stat->tx_ring_stats, req_txq,
 			       sizeof(*vsi_stat->tx_ring_stats),
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 71bd27244941..bfcfc582a4c0 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -91,9 +91,15 @@ void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc);
 struct ice_vsi *
 ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params);
 
-void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked);
+void
+ice_queue_set_napi(struct ice_vsi *vsi, unsigned int queue_index,
+		   enum netdev_queue_type type, struct napi_struct *napi);
+
+void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked);
+
+void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector);
 
-void ice_vsi_set_napi_queues(struct ice_vsi *vsi, bool locked);
+void ice_vsi_set_napi_queues(struct ice_vsi *vsi);
 
 int ice_vsi_release(struct ice_vsi *vsi);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index dd4a9bc0dfdc..df6a68ab747e 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3495,7 +3495,7 @@ static void ice_napi_add(struct ice_vsi *vsi)
 	ice_for_each_q_vector(vsi, v_idx) {
 		netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx]->napi,
 			       ice_napi_poll);
-		ice_q_vector_set_napi_queues(vsi->q_vectors[v_idx], false);
+		__ice_q_vector_set_napi_queues(vsi->q_vectors[v_idx], false);
 	}
 }
 
@@ -5447,6 +5447,7 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf)
 		if (ret)
 			goto err_reinit;
 		ice_vsi_map_rings_to_vectors(pf->vsi[v]);
+		ice_vsi_set_napi_queues(pf->vsi[v]);
 	}
 
 	ret = ice_req_irq_msix_misc(pf);
@@ -8012,6 +8013,8 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 	pf_sw = pf->first_sw;
 	/* find the attribute in the netlink message */
 	br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
+	if (!br_spec)
+		return -EINVAL;
 
 	nla_for_each_nested(attr, br_spec, rem) {
 		__u16 mode;
diff --git a/drivers/net/ethernet/intel/ice/ice_osdep.h b/drivers/net/ethernet/intel/ice/ice_osdep.h
index 82bc54fec7f3..a2562f04267f 100644
--- a/drivers/net/ethernet/intel/ice/ice_osdep.h
+++ b/drivers/net/ethernet/intel/ice/ice_osdep.h
@@ -24,7 +24,7 @@
 #define rd64(a, reg)		readq((a)->hw_addr + (reg))
 
 #define ice_flush(a)		rd32((a), GLGEN_STAT)
-#define ICE_M(m, s)		((m) << (s))
+#define ICE_M(m, s)		((m ## U) << (s))
 
 struct ice_dma_mem {
 	void *va;
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index a94a1c48c3de..b0f78c2f2790 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -1068,6 +1068,7 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count)
 	struct ice_pf *pf = pci_get_drvdata(pdev);
 	u16 prev_msix, prev_queues, queues;
 	bool needs_rebuild = false;
+	struct ice_vsi *vsi;
 	struct ice_vf *vf;
 	int id;
 
@@ -1102,6 +1103,10 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count)
 	if (!vf)
 		return -ENOENT;
 
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi)
+		return -ENOENT;
+
 	prev_msix = vf->num_msix;
 	prev_queues = vf->num_vf_qs;
 
@@ -1122,7 +1127,7 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count)
 	if (vf->first_vector_idx < 0)
 		goto unroll;
 
-	if (ice_vf_reconfig_vsi(vf)) {
+	if (ice_vf_reconfig_vsi(vf) || ice_vf_init_host_cfg(vf, vsi)) {
 		/* Try to rebuild with previous values */
 		needs_rebuild = true;
 		goto unroll;
@@ -1148,8 +1153,10 @@ unroll:
 	if (vf->first_vector_idx < 0)
 		return -EINVAL;
 
-	if (needs_rebuild)
+	if (needs_rebuild) {
 		ice_vf_reconfig_vsi(vf);
+		ice_vf_init_host_cfg(vf, vsi);
+	}
 
 	ice_ena_vf_mappings(vf);
 	ice_put_vf(vf);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 74d13cc5a3a7..97d41d6ebf1f 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -513,11 +513,6 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring)
 	if (ice_is_xdp_ena_vsi(rx_ring->vsi))
 		WRITE_ONCE(rx_ring->xdp_prog, rx_ring->vsi->xdp_prog);
 
-	if (rx_ring->vsi->type == ICE_VSI_PF &&
-	    !xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
-		if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
-				     rx_ring->q_index, rx_ring->q_vector->napi.napi_id))
-			goto err;
 	return 0;
 
 err:
@@ -603,9 +598,7 @@ out_failure:
 		ret = ICE_XDP_CONSUMED;
 	}
 exit:
-	rx_buf->act = ret;
-	if (unlikely(xdp_buff_has_frags(xdp)))
-		ice_set_rx_bufs_act(xdp, rx_ring, ret);
+	ice_set_rx_bufs_act(xdp, rx_ring, ret);
 }
 
 /**
@@ -893,14 +886,17 @@ ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	}
 
 	if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) {
-		if (unlikely(xdp_buff_has_frags(xdp)))
-			ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED);
+		ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED);
 		return -ENOMEM;
 	}
 
 	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page,
 				   rx_buf->page_offset, size);
 	sinfo->xdp_frags_size += size;
+	/* remember frag count before XDP prog execution; bpf_xdp_adjust_tail()
+	 * can pop off frags but driver has to handle it on its own
+	 */
+	rx_ring->nr_frags = sinfo->nr_frags;
 
 	if (page_is_pfmemalloc(rx_buf->page))
 		xdp_buff_set_frag_pfmemalloc(xdp);
@@ -1251,6 +1247,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 
 		xdp->data = NULL;
 		rx_ring->first_desc = ntc;
+		rx_ring->nr_frags = 0;
 		continue;
 construct_skb:
 		if (likely(ice_ring_uses_build_skb(rx_ring)))
@@ -1266,10 +1263,12 @@ construct_skb:
 						    ICE_XDP_CONSUMED);
 			xdp->data = NULL;
 			rx_ring->first_desc = ntc;
+			rx_ring->nr_frags = 0;
 			break;
 		}
 		xdp->data = NULL;
 		rx_ring->first_desc = ntc;
+		rx_ring->nr_frags = 0;
 
 		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S);
 		if (unlikely(ice_test_staterr(rx_desc->wb.status_error0,
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index b3379ff73674..af955b0e5dc5 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -358,6 +358,7 @@ struct ice_rx_ring {
 	struct ice_tx_ring *xdp_ring;
 	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
 	struct xsk_buff_pool *xsk_pool;
+	u32 nr_frags;
 	dma_addr_t dma;			/* physical address of ring */
 	u16 rx_buf_len;
 	u8 dcb_tc;			/* Traffic class of ring */
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
index 762047508619..afcead4baef4 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
@@ -12,26 +12,39 @@
  * act: action to store onto Rx buffers related to XDP buffer parts
  *
  * Set action that should be taken before putting Rx buffer from first frag
- * to one before last. Last one is handled by caller of this function as it
- * is the EOP frag that is currently being processed. This function is
- * supposed to be called only when XDP buffer contains frags.
+ * to the last.
  */
 static inline void
 ice_set_rx_bufs_act(struct xdp_buff *xdp, const struct ice_rx_ring *rx_ring,
 		    const unsigned int act)
 {
-	const struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
-	u32 first = rx_ring->first_desc;
-	u32 nr_frags = sinfo->nr_frags;
+	u32 sinfo_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags;
+	u32 nr_frags = rx_ring->nr_frags + 1;
+	u32 idx = rx_ring->first_desc;
 	u32 cnt = rx_ring->count;
 	struct ice_rx_buf *buf;
 
 	for (int i = 0; i < nr_frags; i++) {
-		buf = &rx_ring->rx_buf[first];
+		buf = &rx_ring->rx_buf[idx];
 		buf->act = act;
 
-		if (++first == cnt)
-			first = 0;
+		if (++idx == cnt)
+			idx = 0;
+	}
+
+	/* adjust pagecnt_bias on frags freed by XDP prog */
+	if (sinfo_frags < rx_ring->nr_frags && act == ICE_XDP_CONSUMED) {
+		u32 delta = rx_ring->nr_frags - sinfo_frags;
+
+		while (delta) {
+			if (idx == 0)
+				idx = cnt - 1;
+			else
+				idx--;
+			buf = &rx_ring->rx_buf[idx];
+			buf->pagecnt_bias--;
+			delta--;
+		}
 	}
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 41ab6d7bbd9e..a508e917ce5f 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -1072,7 +1072,7 @@ struct ice_aq_get_set_rss_lut_params {
 #define ICE_OROM_VER_BUILD_SHIFT	8
 #define ICE_OROM_VER_BUILD_MASK		(0xffff << ICE_OROM_VER_BUILD_SHIFT)
 #define ICE_OROM_VER_SHIFT		24
-#define ICE_OROM_VER_MASK		(0xff << ICE_OROM_VER_SHIFT)
+#define ICE_OROM_VER_MASK		(0xffU << ICE_OROM_VER_SHIFT)
 #define ICE_SR_PFA_PTR			0x40
 #define ICE_SR_1ST_NVM_BANK_PTR		0x42
 #define ICE_SR_NVM_BANK_SIZE		0x43
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index c925813ec9ca..6f2328a049bf 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -440,7 +440,6 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 		vf->driver_caps = *(u32 *)msg;
 	else
 		vf->driver_caps = VIRTCHNL_VF_OFFLOAD_L2 |
-				  VIRTCHNL_VF_OFFLOAD_RSS_REG |
 				  VIRTCHNL_VF_OFFLOAD_VLAN;
 
 	vfres->vf_cap_flags = VIRTCHNL_VF_OFFLOAD_L2;
@@ -453,14 +452,8 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 	vfres->vf_cap_flags |= ice_vc_get_vlan_caps(hw, vf, vsi,
 						    vf->driver_caps);
 
-	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) {
+	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF)
 		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PF;
-	} else {
-		if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_AQ)
-			vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_AQ;
-		else
-			vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_REG;
-	}
 
 	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC)
 		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC;
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
index 5e19d48a05b4..d796dbd2a440 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
@@ -13,8 +13,6 @@
  * - opcodes needed by VF when caps are activated
  *
  * Caps that don't use new opcodes (no opcodes should be allowed):
- * - VIRTCHNL_VF_OFFLOAD_RSS_AQ
- * - VIRTCHNL_VF_OFFLOAD_RSS_REG
  * - VIRTCHNL_VF_OFFLOAD_WB_ON_ITR
  * - VIRTCHNL_VF_OFFLOAD_CRC
  * - VIRTCHNL_VF_OFFLOAD_RX_POLLING
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 5d1ae8e4058a..2eecd0f39aa6 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -179,6 +179,10 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
 			return -EBUSY;
 		usleep_range(1000, 2000);
 	}
+
+	ice_qvec_dis_irq(vsi, rx_ring, q_vector);
+	ice_qvec_toggle_napi(vsi, q_vector, false);
+
 	netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
 
 	ice_fill_txq_meta(vsi, tx_ring, &txq_meta);
@@ -195,13 +199,10 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
 		if (err)
 			return err;
 	}
-	ice_qvec_dis_irq(vsi, rx_ring, q_vector);
-
 	err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true);
 	if (err)
 		return err;
 
-	ice_qvec_toggle_napi(vsi, q_vector, false);
 	ice_qp_clean_rings(vsi, q_idx);
 	ice_qp_reset_stats(vsi, q_idx);
 
@@ -259,11 +260,11 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
 	if (err)
 		return err;
 
-	clear_bit(ICE_CFG_BUSY, vsi->state);
 	ice_qvec_toggle_napi(vsi, q_vector, true);
 	ice_qvec_ena_irq(vsi, q_vector);
 
 	netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
+	clear_bit(ICE_CFG_BUSY, vsi->state);
 
 	return 0;
 }
@@ -825,7 +826,8 @@ ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first,
 	}
 
 	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++,
-				   virt_to_page(xdp->data_hard_start), 0, size);
+				   virt_to_page(xdp->data_hard_start),
+				   XDP_PACKET_HEADROOM, size);
 	sinfo->xdp_frags_size += size;
 	xsk_buff_add_frag(xdp);
 
@@ -895,7 +897,6 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 
 		if (!first) {
 			first = xdp;
-			xdp_buff_clear_frags_flag(first);
 		} else if (ice_add_xsk_frag(rx_ring, first, xdp, size)) {
 			break;
 		}
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index 5fea2fd957eb..58179bd733ff 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -783,6 +783,8 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 	/* setup watchdog timeout value to be 5 second */
 	netdev->watchdog_timeo = 5 * HZ;
 
+	netdev->dev_port = idx;
+
 	/* configure default MTU size */
 	netdev->min_mtu = ETH_MIN_MTU;
 	netdev->max_mtu = vport->max_mtu;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index d0cdd63b3d5b..390977a76de2 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -2087,8 +2087,10 @@ int idpf_send_disable_queues_msg(struct idpf_vport *vport)
 		set_bit(__IDPF_Q_POLL_MODE, vport->txqs[i]->flags);
 
 	/* schedule the napi to receive all the marker packets */
+	local_bh_disable();
 	for (i = 0; i < vport->num_q_vectors; i++)
 		napi_schedule(&vport->q_vectors[i].napi);
+	local_bh_enable();
 
 	return idpf_wait_for_marker_event(vport);
 }
diff --git a/drivers/net/ethernet/intel/idpf/virtchnl2.h b/drivers/net/ethernet/intel/idpf/virtchnl2.h
index 8dc837889723..4a3c4454d25a 100644
--- a/drivers/net/ethernet/intel/idpf/virtchnl2.h
+++ b/drivers/net/ethernet/intel/idpf/virtchnl2.h
@@ -978,7 +978,7 @@ struct virtchnl2_ptype {
 	u8 proto_id_count;
 	__le16 pad;
 	__le16 proto_id[];
-};
+} __packed __aligned(2);
 VIRTCHNL2_CHECK_STRUCT_LEN(6, virtchnl2_ptype);
 
 /**
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index a2b759531cb7..3c2dc7bdebb5 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -637,7 +637,7 @@ struct igb_adapter {
 		struct timespec64 period;
 	} perout[IGB_N_PEROUT];
 
-	char fw_version[32];
+	char fw_version[48];
 #ifdef CONFIG_IGB_HWMON
 	struct hwmon_buff *igb_hwmon_buff;
 	bool ets;
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 4df8d4153aa5..cebb44f51d5f 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -3069,7 +3069,6 @@ void igb_set_fw_version(struct igb_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
 	struct e1000_fw_version fw;
-	char *lbuf;
 
 	igb_get_fw_version(hw, &fw);
 
@@ -3077,34 +3076,36 @@ void igb_set_fw_version(struct igb_adapter *adapter)
 	case e1000_i210:
 	case e1000_i211:
 		if (!(igb_get_flash_presence_i210(hw))) {
-			lbuf = kasprintf(GFP_KERNEL, "%2d.%2d-%d",
-					 fw.invm_major, fw.invm_minor,
-					 fw.invm_img_type);
+			snprintf(adapter->fw_version,
+				 sizeof(adapter->fw_version),
+				 "%2d.%2d-%d",
+				 fw.invm_major, fw.invm_minor,
+				 fw.invm_img_type);
 			break;
 		}
 		fallthrough;
 	default:
 		/* if option rom is valid, display its version too */
 		if (fw.or_valid) {
-			lbuf = kasprintf(GFP_KERNEL, "%d.%d, 0x%08x, %d.%d.%d",
-					 fw.eep_major, fw.eep_minor,
-					 fw.etrack_id, fw.or_major, fw.or_build,
-					 fw.or_patch);
+			snprintf(adapter->fw_version,
+				 sizeof(adapter->fw_version),
+				 "%d.%d, 0x%08x, %d.%d.%d",
+				 fw.eep_major, fw.eep_minor, fw.etrack_id,
+				 fw.or_major, fw.or_build, fw.or_patch);
 		/* no option rom */
 		} else if (fw.etrack_id != 0X0000) {
-			lbuf = kasprintf(GFP_KERNEL, "%d.%d, 0x%08x",
-					 fw.eep_major, fw.eep_minor,
-					 fw.etrack_id);
+			snprintf(adapter->fw_version,
+				 sizeof(adapter->fw_version),
+				 "%d.%d, 0x%08x",
+				 fw.eep_major, fw.eep_minor, fw.etrack_id);
 		} else {
-			lbuf = kasprintf(GFP_KERNEL, "%d.%d.%d", fw.eep_major,
-					 fw.eep_minor, fw.eep_build);
+			snprintf(adapter->fw_version,
+				 sizeof(adapter->fw_version),
+				 "%d.%d.%d",
+				 fw.eep_major, fw.eep_minor, fw.eep_build);
 		}
 		break;
 	}
-
-	/* the truncate happens here if it doesn't fit */
-	strscpy(adapter->fw_version, lbuf, sizeof(adapter->fw_version));
-	kfree(lbuf);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index 319c544b9f04..f94570556120 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -957,7 +957,7 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter)
 
 	igb_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval);
 	/* adjust timestamp for the TX latency based on link speed */
-	if (adapter->hw.mac.type == e1000_i210) {
+	if (hw->mac.type == e1000_i210 || hw->mac.type == e1000_i211) {
 		switch (adapter->link_speed) {
 		case SPEED_10:
 			adjust = IGB_I210_TX_LATENCY_10;
@@ -1003,6 +1003,7 @@ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
 			ktime_t *timestamp)
 {
 	struct igb_adapter *adapter = q_vector->adapter;
+	struct e1000_hw *hw = &adapter->hw;
 	struct skb_shared_hwtstamps ts;
 	__le64 *regval = (__le64 *)va;
 	int adjust = 0;
@@ -1022,7 +1023,7 @@ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
 	igb_ptp_systim_to_hwtstamp(adapter, &ts, le64_to_cpu(regval[1]));
 
 	/* adjust timestamp for the RX latency based on link speed */
-	if (adapter->hw.mac.type == e1000_i210) {
+	if (hw->mac.type == e1000_i210 || hw->mac.type == e1000_i211) {
 		switch (adapter->link_speed) {
 		case SPEED_10:
 			adjust = IGB_I210_RX_LATENCY_10;
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index ba8d3fe186ae..81c21a893ede 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -6487,7 +6487,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames,
 	int cpu = smp_processor_id();
 	struct netdev_queue *nq;
 	struct igc_ring *ring;
-	int i, drops;
+	int i, nxmit;
 
 	if (unlikely(!netif_carrier_ok(dev)))
 		return -ENETDOWN;
@@ -6503,16 +6503,15 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames,
 	/* Avoid transmit queue timeout since we share it with the slow path */
 	txq_trans_cond_update(nq);
 
-	drops = 0;
+	nxmit = 0;
 	for (i = 0; i < num_frames; i++) {
 		int err;
 		struct xdp_frame *xdpf = frames[i];
 
 		err = igc_xdp_init_tx_descriptor(ring, xdpf);
-		if (err) {
-			xdp_return_frame_rx_napi(xdpf);
-			drops++;
-		}
+		if (err)
+			break;
+		nxmit++;
 	}
 
 	if (flags & XDP_XMIT_FLUSH)
@@ -6520,7 +6519,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames,
 
 	__netif_tx_unlock(nq);
 
-	return num_frames - drops;
+	return nxmit;
 }
 
 static void igc_trigger_rxtxq_interrupt(struct igc_adapter *adapter,
diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c
index 7cd8716d2ffa..861f37076861 100644
--- a/drivers/net/ethernet/intel/igc/igc_phy.c
+++ b/drivers/net/ethernet/intel/igc/igc_phy.c
@@ -130,11 +130,7 @@ void igc_power_down_phy_copper(struct igc_hw *hw)
 	/* The PHY will retain its settings across a power down/up cycle */
 	hw->phy.ops.read_reg(hw, PHY_CONTROL, &mii_reg);
 	mii_reg |= MII_CR_POWER_DOWN;
-
-	/* Temporary workaround - should be removed when PHY will implement
-	 * IEEE registers as properly
-	 */
-	/* hw->phy.ops.write_reg(hw, PHY_CONTROL, mii_reg);*/
+	hw->phy.ops.write_reg(hw, PHY_CONTROL, mii_reg);
 	usleep_range(1000, 2000);
 }
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index bd541527c8c7..99876b765b08 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2939,8 +2939,8 @@ static void ixgbe_check_lsc(struct ixgbe_adapter *adapter)
 static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter,
 					   u64 qmask)
 {
-	u32 mask;
 	struct ixgbe_hw *hw = &adapter->hw;
+	u32 mask;
 
 	switch (hw->mac.type) {
 	case ixgbe_mac_82598EB:
@@ -10525,6 +10525,44 @@ static void ixgbe_reset_rxr_stats(struct ixgbe_ring *rx_ring)
 }
 
 /**
+ * ixgbe_irq_disable_single - Disable single IRQ vector
+ * @adapter: adapter structure
+ * @ring: ring index
+ **/
+static void ixgbe_irq_disable_single(struct ixgbe_adapter *adapter, u32 ring)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u64 qmask = BIT_ULL(ring);
+	u32 mask;
+
+	switch (adapter->hw.mac.type) {
+	case ixgbe_mac_82598EB:
+		mask = qmask & IXGBE_EIMC_RTX_QUEUE;
+		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, mask);
+		break;
+	case ixgbe_mac_82599EB:
+	case ixgbe_mac_X540:
+	case ixgbe_mac_X550:
+	case ixgbe_mac_X550EM_x:
+	case ixgbe_mac_x550em_a:
+		mask = (qmask & 0xFFFFFFFF);
+		if (mask)
+			IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask);
+		mask = (qmask >> 32);
+		if (mask)
+			IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(1), mask);
+		break;
+	default:
+		break;
+	}
+	IXGBE_WRITE_FLUSH(&adapter->hw);
+	if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED)
+		synchronize_irq(adapter->msix_entries[ring].vector);
+	else
+		synchronize_irq(adapter->pdev->irq);
+}
+
+/**
  * ixgbe_txrx_ring_disable - Disable Rx/Tx/XDP Tx rings
  * @adapter: adapter structure
  * @ring: ring index
@@ -10540,6 +10578,11 @@ void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring)
 	tx_ring = adapter->tx_ring[ring];
 	xdp_ring = adapter->xdp_ring[ring];
 
+	ixgbe_irq_disable_single(adapter, ring);
+
+	/* Rx/Tx/XDP Tx share the same napi context. */
+	napi_disable(&rx_ring->q_vector->napi);
+
 	ixgbe_disable_txr(adapter, tx_ring);
 	if (xdp_ring)
 		ixgbe_disable_txr(adapter, xdp_ring);
@@ -10548,9 +10591,6 @@ void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring)
 	if (xdp_ring)
 		synchronize_rcu();
 
-	/* Rx/Tx/XDP Tx share the same napi context. */
-	napi_disable(&rx_ring->q_vector->napi);
-
 	ixgbe_clean_tx_ring(tx_ring);
 	if (xdp_ring)
 		ixgbe_clean_tx_ring(xdp_ring);
@@ -10578,9 +10618,6 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring)
 	tx_ring = adapter->tx_ring[ring];
 	xdp_ring = adapter->xdp_ring[ring];
 
-	/* Rx/Tx/XDP Tx share the same napi context. */
-	napi_enable(&rx_ring->q_vector->napi);
-
 	ixgbe_configure_tx_ring(adapter, tx_ring);
 	if (xdp_ring)
 		ixgbe_configure_tx_ring(adapter, xdp_ring);
@@ -10589,6 +10626,11 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring)
 	clear_bit(__IXGBE_TX_DISABLED, &tx_ring->state);
 	if (xdp_ring)
 		clear_bit(__IXGBE_TX_DISABLED, &xdp_ring->state);
+
+	/* Rx/Tx/XDP Tx share the same napi context. */
+	napi_enable(&rx_ring->q_vector->napi);
+	ixgbe_irq_enable_queues(adapter, BIT_ULL(ring));
+	IXGBE_WRITE_FLUSH(&adapter->hw);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
index 6208923e29a2..c1adc94a5a65 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
@@ -716,7 +716,8 @@ static s32 ixgbe_read_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr,
 	if ((command & IXGBE_SB_IOSF_CTRL_RESP_STAT_MASK) != 0) {
 		error = FIELD_GET(IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK, command);
 		hw_dbg(hw, "Failed to read, error %x\n", error);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 
 	if (!ret)
diff --git a/drivers/net/ethernet/litex/litex_liteeth.c b/drivers/net/ethernet/litex/litex_liteeth.c
index 5182fe737c37..ff54fbe41bcc 100644
--- a/drivers/net/ethernet/litex/litex_liteeth.c
+++ b/drivers/net/ethernet/litex/litex_liteeth.c
@@ -318,4 +318,5 @@ static struct platform_driver liteeth_driver = {
 module_platform_driver(liteeth_driver);
 
 MODULE_AUTHOR("Joel Stanley <joel@jms.id.au>");
+MODULE_DESCRIPTION("LiteX Liteeth Ethernet driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 820b1fabe297..23adf53c2aa1 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -614,12 +614,38 @@ static void mvpp23_bm_set_8pool_mode(struct mvpp2 *priv)
 	mvpp2_write(priv, MVPP22_BM_POOL_BASE_ADDR_HIGH_REG, val);
 }
 
+/* Cleanup pool before actual initialization in the OS */
+static void mvpp2_bm_pool_cleanup(struct mvpp2 *priv, int pool_id)
+{
+	unsigned int thread = mvpp2_cpu_to_thread(priv, get_cpu());
+	u32 val;
+	int i;
+
+	/* Drain the BM from all possible residues left by firmware */
+	for (i = 0; i < MVPP2_BM_POOL_SIZE_MAX; i++)
+		mvpp2_thread_read(priv, thread, MVPP2_BM_PHY_ALLOC_REG(pool_id));
+
+	put_cpu();
+
+	/* Stop the BM pool */
+	val = mvpp2_read(priv, MVPP2_BM_POOL_CTRL_REG(pool_id));
+	val |= MVPP2_BM_STOP_MASK;
+	mvpp2_write(priv, MVPP2_BM_POOL_CTRL_REG(pool_id), val);
+}
+
 static int mvpp2_bm_init(struct device *dev, struct mvpp2 *priv)
 {
 	enum dma_data_direction dma_dir = DMA_FROM_DEVICE;
 	int i, err, poolnum = MVPP2_BM_POOLS_NUM;
 	struct mvpp2_port *port;
 
+	if (priv->percpu_pools)
+		poolnum = mvpp2_get_nrxqs(priv) * 2;
+
+	/* Clean up the pool state in case it contains stale state */
+	for (i = 0; i < poolnum; i++)
+		mvpp2_bm_pool_cleanup(priv, i);
+
 	if (priv->percpu_pools) {
 		for (i = 0; i < priv->port_count; i++) {
 			port = priv->port_list[i];
@@ -629,7 +655,6 @@ static int mvpp2_bm_init(struct device *dev, struct mvpp2 *priv)
 			}
 		}
 
-		poolnum = mvpp2_get_nrxqs(priv) * 2;
 		for (i = 0; i < poolnum; i++) {
 			/* the pool in use */
 			int pn = i / (poolnum / 2);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
index 9690ac01f02c..b92264d0a77e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
@@ -413,4 +413,5 @@ const char *otx2_mbox_id2name(u16 id)
 EXPORT_SYMBOL(otx2_mbox_id2name);
 
 MODULE_AUTHOR("Marvell.");
+MODULE_DESCRIPTION("Marvell RVU NIC Mbox helpers");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
index 4728ba34b0e3..76218f1cb459 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
@@ -506,6 +506,7 @@ u32 rpm2_get_lmac_fifo_len(void *rpmd, int lmac_id)
 	rpm_t *rpm = rpmd;
 	u8 num_lmacs;
 	u32 fifo_len;
+	u16 max_lmac;
 
 	lmac_info = rpm_read(rpm, 0, RPM2_CMRX_RX_LMACS);
 	/* LMACs are divided into two groups and each group
@@ -513,7 +514,11 @@ u32 rpm2_get_lmac_fifo_len(void *rpmd, int lmac_id)
 	 * Group0 lmac_id range {0..3}
 	 * Group1 lmac_id range {4..7}
 	 */
-	fifo_len = rpm->mac_ops->fifo_len / 2;
+	max_lmac = (rpm_read(rpm, 0, CGX_CONST) >> 24) & 0xFF;
+	if (max_lmac > 4)
+		fifo_len = rpm->mac_ops->fifo_len / 2;
+	else
+		fifo_len = rpm->mac_ops->fifo_len;
 
 	if (lmac_id < 4) {
 		num_lmacs = hweight8(lmac_info & 0xF);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 167145bdcb75..516adb50f9f6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -61,28 +61,6 @@ int rvu_npc_get_tx_nibble_cfg(struct rvu *rvu, u64 nibble_ena)
 	return 0;
 }
 
-static int npc_mcam_verify_pf_func(struct rvu *rvu,
-				   struct mcam_entry *entry_data, u8 intf,
-				   u16 pcifunc)
-{
-	u16 pf_func, pf_func_mask;
-
-	if (is_npc_intf_rx(intf))
-		return 0;
-
-	pf_func_mask = (entry_data->kw_mask[0] >> 32) &
-		NPC_KEX_PF_FUNC_MASK;
-	pf_func = (entry_data->kw[0] >> 32) & NPC_KEX_PF_FUNC_MASK;
-
-	pf_func = be16_to_cpu((__force __be16)pf_func);
-	if (pf_func_mask != NPC_KEX_PF_FUNC_MASK ||
-	    ((pf_func & ~RVU_PFVF_FUNC_MASK) !=
-	     (pcifunc & ~RVU_PFVF_FUNC_MASK)))
-		return -EINVAL;
-
-	return 0;
-}
-
 void rvu_npc_set_pkind(struct rvu *rvu, int pkind, struct rvu_pfvf *pfvf)
 {
 	int blkaddr;
@@ -437,6 +415,10 @@ static void npc_fixup_vf_rule(struct rvu *rvu, struct npc_mcam *mcam,
 			return;
 	}
 
+	/* AF modifies given action iff PF/VF has requested for it */
+	if ((entry->action & 0xFULL) != NIX_RX_ACTION_DEFAULT)
+		return;
+
 	/* copy VF default entry action to the VF mcam entry */
 	rx_action = npc_get_default_entry_action(rvu, mcam, blkaddr,
 						 target_func);
@@ -1850,8 +1832,8 @@ void npc_mcam_rsrcs_deinit(struct rvu *rvu)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 
-	kfree(mcam->bmap);
-	kfree(mcam->bmap_reverse);
+	bitmap_free(mcam->bmap);
+	bitmap_free(mcam->bmap_reverse);
 	kfree(mcam->entry2pfvf_map);
 	kfree(mcam->cntr2pfvf_map);
 	kfree(mcam->entry2cntr_map);
@@ -1904,21 +1886,20 @@ int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 	mcam->pf_offset = mcam->nixlf_offset + nixlf_count;
 
 	/* Allocate bitmaps for managing MCAM entries */
-	mcam->bmap = kmalloc_array(BITS_TO_LONGS(mcam->bmap_entries),
-				   sizeof(long), GFP_KERNEL);
+	mcam->bmap = bitmap_zalloc(mcam->bmap_entries, GFP_KERNEL);
 	if (!mcam->bmap)
 		return -ENOMEM;
 
-	mcam->bmap_reverse = kmalloc_array(BITS_TO_LONGS(mcam->bmap_entries),
-					   sizeof(long), GFP_KERNEL);
+	mcam->bmap_reverse = bitmap_zalloc(mcam->bmap_entries, GFP_KERNEL);
 	if (!mcam->bmap_reverse)
 		goto free_bmap;
 
 	mcam->bmap_fcnt = mcam->bmap_entries;
 
 	/* Alloc memory for saving entry to RVU PFFUNC allocation mapping */
-	mcam->entry2pfvf_map = kmalloc_array(mcam->bmap_entries,
-					     sizeof(u16), GFP_KERNEL);
+	mcam->entry2pfvf_map = kcalloc(mcam->bmap_entries, sizeof(u16),
+				       GFP_KERNEL);
+
 	if (!mcam->entry2pfvf_map)
 		goto free_bmap_reverse;
 
@@ -1941,21 +1922,21 @@ int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 	if (err)
 		goto free_entry_map;
 
-	mcam->cntr2pfvf_map = kmalloc_array(mcam->counters.max,
-					    sizeof(u16), GFP_KERNEL);
+	mcam->cntr2pfvf_map = kcalloc(mcam->counters.max, sizeof(u16),
+				      GFP_KERNEL);
 	if (!mcam->cntr2pfvf_map)
 		goto free_cntr_bmap;
 
 	/* Alloc memory for MCAM entry to counter mapping and for tracking
 	 * counter's reference count.
 	 */
-	mcam->entry2cntr_map = kmalloc_array(mcam->bmap_entries,
-					     sizeof(u16), GFP_KERNEL);
+	mcam->entry2cntr_map = kcalloc(mcam->bmap_entries, sizeof(u16),
+				       GFP_KERNEL);
 	if (!mcam->entry2cntr_map)
 		goto free_cntr_map;
 
-	mcam->cntr_refcnt = kmalloc_array(mcam->counters.max,
-					  sizeof(u16), GFP_KERNEL);
+	mcam->cntr_refcnt = kcalloc(mcam->counters.max, sizeof(u16),
+				    GFP_KERNEL);
 	if (!mcam->cntr_refcnt)
 		goto free_entry_cntr_map;
 
@@ -1988,9 +1969,9 @@ free_cntr_bmap:
 free_entry_map:
 	kfree(mcam->entry2pfvf_map);
 free_bmap_reverse:
-	kfree(mcam->bmap_reverse);
+	bitmap_free(mcam->bmap_reverse);
 free_bmap:
-	kfree(mcam->bmap);
+	bitmap_free(mcam->bmap);
 
 	return -ENOMEM;
 }
@@ -2852,12 +2833,6 @@ int rvu_mbox_handler_npc_mcam_write_entry(struct rvu *rvu,
 	else
 		nix_intf = pfvf->nix_rx_intf;
 
-	if (!is_pffunc_af(pcifunc) &&
-	    npc_mcam_verify_pf_func(rvu, &req->entry_data, req->intf, pcifunc)) {
-		rc = NPC_MCAM_INVALID_REQ;
-		goto exit;
-	}
-
 	/* For AF installed rules, the nix_intf should be set to target NIX */
 	if (is_pffunc_af(req->hdr.pcifunc))
 		nix_intf = req->intf;
@@ -3209,10 +3184,6 @@ int rvu_mbox_handler_npc_mcam_alloc_and_write_entry(struct rvu *rvu,
 	if (!is_npc_interface_valid(rvu, req->intf))
 		return NPC_MCAM_INVALID_REQ;
 
-	if (npc_mcam_verify_pf_func(rvu, &req->entry_data, req->intf,
-				    req->hdr.pcifunc))
-		return NPC_MCAM_INVALID_REQ;
-
 	/* Try to allocate a MCAM entry */
 	entry_req.hdr.pcifunc = req->hdr.pcifunc;
 	entry_req.contig = true;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 7ca6941ea0b9..02d0b707aea5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -951,8 +951,11 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura)
 	if (pfvf->ptp && qidx < pfvf->hw.tx_queues) {
 		err = qmem_alloc(pfvf->dev, &sq->timestamps, qset->sqe_cnt,
 				 sizeof(*sq->timestamps));
-		if (err)
+		if (err) {
+			kfree(sq->sg);
+			sq->sg = NULL;
 			return err;
+		}
 	}
 
 	sq->head = 0;
@@ -968,7 +971,14 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura)
 	sq->stats.bytes = 0;
 	sq->stats.pkts = 0;
 
-	return pfvf->hw_ops->sq_aq_init(pfvf, qidx, sqb_aura);
+	err = pfvf->hw_ops->sq_aq_init(pfvf, qidx, sqb_aura);
+	if (err) {
+		kfree(sq->sg);
+		sq->sg = NULL;
+		return err;
+	}
+
+	return 0;
 
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
index 2928898c7f8d..7f786de61014 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
@@ -314,7 +314,6 @@ static int otx2_set_channels(struct net_device *dev,
 	pfvf->hw.tx_queues = channel->tx_count;
 	if (pfvf->xdp_prog)
 		pfvf->hw.xdp_queues = channel->rx_count;
-	pfvf->hw.non_qos_queues =  pfvf->hw.tx_queues + pfvf->hw.xdp_queues;
 
 	if (if_up)
 		err = dev->netdev_ops->ndo_open(dev);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index a57455aebff6..e5fe67e73865 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -1744,6 +1744,7 @@ int otx2_open(struct net_device *netdev)
 	/* RQ and SQs are mapped to different CQs,
 	 * so find out max CQ IRQs (i.e CINTs) needed.
 	 */
+	pf->hw.non_qos_queues =  pf->hw.tx_queues + pf->hw.xdp_queues;
 	pf->hw.cint_cnt = max3(pf->hw.rx_queues, pf->hw.tx_queues,
 			       pf->hw.tc_tx_queues);
 
@@ -2643,8 +2644,6 @@ static int otx2_xdp_setup(struct otx2_nic *pf, struct bpf_prog *prog)
 		xdp_features_clear_redirect_target(dev);
 	}
 
-	pf->hw.non_qos_queues += pf->hw.xdp_queues;
-
 	if (if_up)
 		otx2_open(pf->netdev);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index 4d519ea833b2..f828d32737af 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -1403,7 +1403,7 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 				     struct otx2_cq_queue *cq,
 				     bool *need_xdp_flush)
 {
-	unsigned char *hard_start, *data;
+	unsigned char *hard_start;
 	int qidx = cq->cq_idx;
 	struct xdp_buff xdp;
 	struct page *page;
@@ -1417,9 +1417,8 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 
 	xdp_init_buff(&xdp, pfvf->rbsize, &cq->xdp_rxq);
 
-	data = (unsigned char *)phys_to_virt(pa);
-	hard_start = page_address(page);
-	xdp_prepare_buff(&xdp, hard_start, data - hard_start,
+	hard_start = (unsigned char *)phys_to_virt(pa);
+	xdp_prepare_buff(&xdp, hard_start, OTX2_HEAD_ROOM,
 			 cqe->sg.seg_size, false);
 
 	act = bpf_prog_run_xdp(prog, &xdp);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index a6e91573f8da..de123350bd46 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -4761,7 +4761,10 @@ static int mtk_probe(struct platform_device *pdev)
 	}
 
 	if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA)) {
-		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(36));
+		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(36));
+		if (!err)
+			err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
+
 		if (err) {
 			dev_err(&pdev->dev, "Wrong DMA config\n");
 			return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index a7b1f9686c09..4957412ff1f6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1923,6 +1923,7 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status,
 {
 	const char *namep = mlx5_command_str(opcode);
 	struct mlx5_cmd_stats *stats;
+	unsigned long flags;
 
 	if (!err || !(strcmp(namep, "unknown command opcode")))
 		return;
@@ -1930,7 +1931,7 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status,
 	stats = xa_load(&dev->cmd.stats, opcode);
 	if (!stats)
 		return;
-	spin_lock_irq(&stats->lock);
+	spin_lock_irqsave(&stats->lock, flags);
 	stats->failed++;
 	if (err < 0)
 		stats->last_failed_errno = -err;
@@ -1939,7 +1940,7 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status,
 		stats->last_failed_mbox_status = status;
 		stats->last_failed_syndrome = syndrome;
 	}
-	spin_unlock_irq(&stats->lock);
+	spin_unlock_irqrestore(&stats->lock, flags);
 }
 
 /* preserve -EREMOTEIO for outbox.status != OK, otherwise return err as is */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 3e064234f6fe..98d4306929f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -157,6 +157,12 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change,
 		return -EOPNOTSUPP;
 	}
 
+	if (action == DEVLINK_RELOAD_ACTION_FW_ACTIVATE &&
+	    !dev->priv.fw_reset) {
+		NL_SET_ERR_MSG_MOD(extack, "FW activate is unsupported for this function");
+		return -EOPNOTSUPP;
+	}
+
 	if (mlx5_core_is_pf(dev) && pci_num_vf(pdev))
 		NL_SET_ERR_MSG_MOD(extack, "reload while VFs are present is unfavorable");
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
index 18fed2b34fb1..d74a5aaf4268 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
@@ -261,7 +261,7 @@ static void mlx5_dpll_netdev_dpll_pin_set(struct mlx5_dpll *mdpll,
 {
 	if (mdpll->tracking_netdev)
 		return;
-	netdev_dpll_pin_set(netdev, mdpll->dpll_pin);
+	dpll_netdev_pin_set(netdev, mdpll->dpll_pin);
 	mdpll->tracking_netdev = netdev;
 }
 
@@ -269,7 +269,7 @@ static void mlx5_dpll_netdev_dpll_pin_clear(struct mlx5_dpll *mdpll)
 {
 	if (!mdpll->tracking_netdev)
 		return;
-	netdev_dpll_pin_clear(mdpll->tracking_netdev);
+	dpll_netdev_pin_clear(mdpll->tracking_netdev);
 	mdpll->tracking_netdev = NULL;
 }
 
@@ -389,7 +389,7 @@ static void mlx5_dpll_remove(struct auxiliary_device *adev)
 	struct mlx5_dpll *mdpll = auxiliary_get_drvdata(adev);
 	struct mlx5_core_dev *mdev = mdpll->mdev;
 
-	cancel_delayed_work(&mdpll->work);
+	cancel_delayed_work_sync(&mdpll->work);
 	mlx5_dpll_mdev_netdev_untrack(mdpll, mdev);
 	destroy_workqueue(mdpll->wq);
 	dpll_pin_unregister(mdpll->dpll, mdpll->dpll_pin,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 0bfe1ca8a364..55c6ace0acd5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1124,7 +1124,7 @@ static inline bool mlx5_tx_swp_supported(struct mlx5_core_dev *mdev)
 extern const struct ethtool_ops mlx5e_ethtool_ops;
 
 int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey);
-int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev);
+int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises);
 void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev);
 int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb,
 		       bool enable_mc_lb);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c
index e1283531e0b8..671adbad0a40 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c
@@ -436,6 +436,7 @@ static int fs_any_create_groups(struct mlx5e_flow_table *ft)
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if  (!in || !ft->g) {
 		kfree(ft->g);
+		ft->g = NULL;
 		kvfree(in);
 		return -ENOMEM;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 284253b79266..5d213a9886f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -1064,8 +1064,8 @@ void mlx5e_build_sq_param(struct mlx5_core_dev *mdev,
 	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
 	bool allow_swp;
 
-	allow_swp =
-		mlx5_geneve_tx_allowed(mdev) || !!mlx5_ipsec_device_caps(mdev);
+	allow_swp = mlx5_geneve_tx_allowed(mdev) ||
+		    (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_CRYPTO);
 	mlx5e_build_sq_param_common(mdev, param);
 	MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
 	MLX5_SET(sqc, sqc, allow_swp, allow_swp);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index c206cc0a8483..ca05b3252a1b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -42,9 +42,9 @@ mlx5e_ptp_port_ts_cqe_list_add(struct mlx5e_ptp_port_ts_cqe_list *list, u8 metad
 
 	WARN_ON_ONCE(tracker->inuse);
 	tracker->inuse = true;
-	spin_lock(&list->tracker_list_lock);
+	spin_lock_bh(&list->tracker_list_lock);
 	list_add_tail(&tracker->entry, &list->tracker_list_head);
-	spin_unlock(&list->tracker_list_lock);
+	spin_unlock_bh(&list->tracker_list_lock);
 }
 
 static void
@@ -54,9 +54,9 @@ mlx5e_ptp_port_ts_cqe_list_remove(struct mlx5e_ptp_port_ts_cqe_list *list, u8 me
 
 	WARN_ON_ONCE(!tracker->inuse);
 	tracker->inuse = false;
-	spin_lock(&list->tracker_list_lock);
+	spin_lock_bh(&list->tracker_list_lock);
 	list_del(&tracker->entry);
-	spin_unlock(&list->tracker_list_lock);
+	spin_unlock_bh(&list->tracker_list_lock);
 }
 
 void mlx5e_ptpsq_track_metadata(struct mlx5e_ptpsq *ptpsq, u8 metadata)
@@ -155,7 +155,7 @@ static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq,
 	struct mlx5e_ptp_metadata_map *metadata_map = &ptpsq->metadata_map;
 	struct mlx5e_ptp_port_ts_cqe_tracker *pos, *n;
 
-	spin_lock(&cqe_list->tracker_list_lock);
+	spin_lock_bh(&cqe_list->tracker_list_lock);
 	list_for_each_entry_safe(pos, n, &cqe_list->tracker_list_head, entry) {
 		struct sk_buff *skb =
 			mlx5e_ptp_metadata_map_lookup(metadata_map, pos->metadata_id);
@@ -170,7 +170,7 @@ static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq,
 		pos->inuse = false;
 		list_del(&pos->entry);
 	}
-	spin_unlock(&cqe_list->tracker_list_lock);
+	spin_unlock_bh(&cqe_list->tracker_list_lock);
 }
 
 #define PTP_WQE_CTR2IDX(val) ((val) & ptpsq->ts_cqe_ctr_mask)
@@ -213,7 +213,7 @@ static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq,
 	mlx5e_ptpsq_mark_ts_cqes_undelivered(ptpsq, hwtstamp);
 out:
 	napi_consume_skb(skb, budget);
-	md_buff[*md_buff_sz++] = metadata_id;
+	md_buff[(*md_buff_sz)++] = metadata_id;
 	if (unlikely(mlx5e_ptp_metadata_map_unhealthy(&ptpsq->metadata_map)) &&
 	    !test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
 		queue_work(ptpsq->txqsq.priv->wq, &ptpsq->report_unhealthy_work);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c
index 86bf007fd05b..b500cc2c9689 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c
@@ -37,7 +37,7 @@ mlx5e_tc_post_act_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains,
 
 	if (!MLX5_CAP_FLOWTABLE_TYPE(priv->mdev, ignore_flow_level, table_type)) {
 		if (priv->mdev->coredev_type == MLX5_COREDEV_PF)
-			mlx5_core_warn(priv->mdev, "firmware level support is missing\n");
+			mlx5_core_dbg(priv->mdev, "firmware flow level support is missing\n");
 		err = -EOPNOTSUPP;
 		goto err_check;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 161c5190c236..05612d9c6080 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -336,12 +336,17 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry,
 	/* iv len */
 	aes_gcm->icv_len = x->aead->alg_icv_len;
 
+	attrs->dir = x->xso.dir;
+
 	/* esn */
 	if (x->props.flags & XFRM_STATE_ESN) {
 		attrs->replay_esn.trigger = true;
 		attrs->replay_esn.esn = sa_entry->esn_state.esn;
 		attrs->replay_esn.esn_msb = sa_entry->esn_state.esn_msb;
 		attrs->replay_esn.overlap = sa_entry->esn_state.overlap;
+		if (attrs->dir == XFRM_DEV_OFFLOAD_OUT)
+			goto skip_replay_window;
+
 		switch (x->replay_esn->replay_window) {
 		case 32:
 			attrs->replay_esn.replay_window =
@@ -365,7 +370,7 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry,
 		}
 	}
 
-	attrs->dir = x->xso.dir;
+skip_replay_window:
 	/* spi */
 	attrs->spi = be32_to_cpu(x->id.spi);
 
@@ -501,7 +506,8 @@ static int mlx5e_xfrm_validate_state(struct mlx5_core_dev *mdev,
 			return -EINVAL;
 		}
 
-		if (x->replay_esn && x->replay_esn->replay_window != 32 &&
+		if (x->replay_esn && x->xso.dir == XFRM_DEV_OFFLOAD_IN &&
+		    x->replay_esn->replay_window != 32 &&
 		    x->replay_esn->replay_window != 64 &&
 		    x->replay_esn->replay_window != 128 &&
 		    x->replay_esn->replay_window != 256) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
index d4ebd8743114..b2cabd6ab86c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
@@ -310,9 +310,9 @@ static void mlx5e_macsec_destroy_object(struct mlx5_core_dev *mdev, u32 macsec_o
 	mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
 }
 
-static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec,
-				    struct mlx5e_macsec_sa *sa,
-				    bool is_tx, struct net_device *netdev, u32 fs_id)
+static void mlx5e_macsec_cleanup_sa_fs(struct mlx5e_macsec *macsec,
+				       struct mlx5e_macsec_sa *sa, bool is_tx,
+				       struct net_device *netdev, u32 fs_id)
 {
 	int action =  (is_tx) ?  MLX5_ACCEL_MACSEC_ACTION_ENCRYPT :
 				 MLX5_ACCEL_MACSEC_ACTION_DECRYPT;
@@ -322,20 +322,49 @@ static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec,
 
 	mlx5_macsec_fs_del_rule(macsec->mdev->macsec_fs, sa->macsec_rule, action, netdev,
 				fs_id);
-	mlx5e_macsec_destroy_object(macsec->mdev, sa->macsec_obj_id);
 	sa->macsec_rule = NULL;
 }
 
+static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec,
+				    struct mlx5e_macsec_sa *sa, bool is_tx,
+				    struct net_device *netdev, u32 fs_id)
+{
+	mlx5e_macsec_cleanup_sa_fs(macsec, sa, is_tx, netdev, fs_id);
+	mlx5e_macsec_destroy_object(macsec->mdev, sa->macsec_obj_id);
+}
+
+static int mlx5e_macsec_init_sa_fs(struct macsec_context *ctx,
+				   struct mlx5e_macsec_sa *sa, bool encrypt,
+				   bool is_tx, u32 *fs_id)
+{
+	struct mlx5e_priv *priv = macsec_netdev_priv(ctx->netdev);
+	struct mlx5_macsec_fs *macsec_fs = priv->mdev->macsec_fs;
+	struct mlx5_macsec_rule_attrs rule_attrs;
+	union mlx5_macsec_rule *macsec_rule;
+
+	rule_attrs.macsec_obj_id = sa->macsec_obj_id;
+	rule_attrs.sci = sa->sci;
+	rule_attrs.assoc_num = sa->assoc_num;
+	rule_attrs.action = (is_tx) ? MLX5_ACCEL_MACSEC_ACTION_ENCRYPT :
+				      MLX5_ACCEL_MACSEC_ACTION_DECRYPT;
+
+	macsec_rule = mlx5_macsec_fs_add_rule(macsec_fs, ctx, &rule_attrs, fs_id);
+	if (!macsec_rule)
+		return -ENOMEM;
+
+	sa->macsec_rule = macsec_rule;
+
+	return 0;
+}
+
 static int mlx5e_macsec_init_sa(struct macsec_context *ctx,
 				struct mlx5e_macsec_sa *sa,
 				bool encrypt, bool is_tx, u32 *fs_id)
 {
 	struct mlx5e_priv *priv = macsec_netdev_priv(ctx->netdev);
 	struct mlx5e_macsec *macsec = priv->macsec;
-	struct mlx5_macsec_rule_attrs rule_attrs;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5_macsec_obj_attrs obj_attrs;
-	union mlx5_macsec_rule *macsec_rule;
 	int err;
 
 	obj_attrs.next_pn = sa->next_pn;
@@ -357,20 +386,12 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx,
 	if (err)
 		return err;
 
-	rule_attrs.macsec_obj_id = sa->macsec_obj_id;
-	rule_attrs.sci = sa->sci;
-	rule_attrs.assoc_num = sa->assoc_num;
-	rule_attrs.action = (is_tx) ? MLX5_ACCEL_MACSEC_ACTION_ENCRYPT :
-				      MLX5_ACCEL_MACSEC_ACTION_DECRYPT;
-
-	macsec_rule = mlx5_macsec_fs_add_rule(mdev->macsec_fs, ctx, &rule_attrs, fs_id);
-	if (!macsec_rule) {
-		err = -ENOMEM;
-		goto destroy_macsec_object;
+	if (sa->active) {
+		err = mlx5e_macsec_init_sa_fs(ctx, sa, encrypt, is_tx, fs_id);
+		if (err)
+			goto destroy_macsec_object;
 	}
 
-	sa->macsec_rule = macsec_rule;
-
 	return 0;
 
 destroy_macsec_object:
@@ -526,9 +547,7 @@ static int mlx5e_macsec_add_txsa(struct macsec_context *ctx)
 		goto destroy_sa;
 
 	macsec_device->tx_sa[assoc_num] = tx_sa;
-	if (!secy->operational ||
-	    assoc_num != tx_sc->encoding_sa ||
-	    !tx_sa->active)
+	if (!secy->operational)
 		goto out;
 
 	err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL);
@@ -595,7 +614,7 @@ static int mlx5e_macsec_upd_txsa(struct macsec_context *ctx)
 		goto out;
 
 	if (ctx_tx_sa->active) {
-		err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL);
+		err = mlx5e_macsec_init_sa_fs(ctx, tx_sa, tx_sc->encrypt, true, NULL);
 		if (err)
 			goto out;
 	} else {
@@ -604,7 +623,7 @@ static int mlx5e_macsec_upd_txsa(struct macsec_context *ctx)
 			goto out;
 		}
 
-		mlx5e_macsec_cleanup_sa(macsec, tx_sa, true, ctx->secy->netdev, 0);
+		mlx5e_macsec_cleanup_sa_fs(macsec, tx_sa, true, ctx->secy->netdev, 0);
 	}
 out:
 	mutex_unlock(&macsec->lock);
@@ -1030,8 +1049,9 @@ static int mlx5e_macsec_del_rxsa(struct macsec_context *ctx)
 		goto out;
 	}
 
-	mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev,
-				rx_sc->sc_xarray_element->fs_id);
+	if (rx_sa->active)
+		mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev,
+					rx_sc->sc_xarray_element->fs_id);
 	mlx5_destroy_encryption_key(macsec->mdev, rx_sa->enc_key_id);
 	kfree(rx_sa);
 	rx_sc->rx_sa[assoc_num] = NULL;
@@ -1112,8 +1132,8 @@ static int macsec_upd_secy_hw_address(struct macsec_context *ctx,
 			if (!rx_sa || !rx_sa->macsec_rule)
 				continue;
 
-			mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev,
-						rx_sc->sc_xarray_element->fs_id);
+			mlx5e_macsec_cleanup_sa_fs(macsec, rx_sa, false, ctx->secy->netdev,
+						   rx_sc->sc_xarray_element->fs_id);
 		}
 	}
 
@@ -1124,8 +1144,8 @@ static int macsec_upd_secy_hw_address(struct macsec_context *ctx,
 				continue;
 
 			if (rx_sa->active) {
-				err = mlx5e_macsec_init_sa(ctx, rx_sa, true, false,
-							   &rx_sc->sc_xarray_element->fs_id);
+				err = mlx5e_macsec_init_sa_fs(ctx, rx_sa, true, false,
+							      &rx_sc->sc_xarray_element->fs_id);
 				if (err)
 					goto out;
 			}
@@ -1178,7 +1198,7 @@ static int mlx5e_macsec_upd_secy(struct macsec_context *ctx)
 		if (!tx_sa)
 			continue;
 
-		mlx5e_macsec_cleanup_sa(macsec, tx_sa, true, ctx->secy->netdev, 0);
+		mlx5e_macsec_cleanup_sa_fs(macsec, tx_sa, true, ctx->secy->netdev, 0);
 	}
 
 	for (i = 0; i < MACSEC_NUM_AN; ++i) {
@@ -1187,7 +1207,7 @@ static int mlx5e_macsec_upd_secy(struct macsec_context *ctx)
 			continue;
 
 		if (tx_sa->assoc_num == tx_sc->encoding_sa && tx_sa->active) {
-			err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL);
+			err = mlx5e_macsec_init_sa_fs(ctx, tx_sa, tx_sc->encrypt, true, NULL);
 			if (err)
 				goto out;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index bb7f86c993e5..e66f486faafe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -254,11 +254,13 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft,
 
 	ft->g = kcalloc(MLX5E_ARFS_NUM_GROUPS,
 			sizeof(*ft->g), GFP_KERNEL);
-	in = kvzalloc(inlen, GFP_KERNEL);
-	if  (!in || !ft->g) {
-		kfree(ft->g);
-		kvfree(in);
+	if (!ft->g)
 		return -ENOMEM;
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in) {
+		err = -ENOMEM;
+		goto err_free_g;
 	}
 
 	mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
@@ -278,7 +280,7 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft,
 		break;
 	default:
 		err = -EINVAL;
-		goto out;
+		goto err_free_in;
 	}
 
 	switch (type) {
@@ -300,7 +302,7 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft,
 		break;
 	default:
 		err = -EINVAL;
-		goto out;
+		goto err_free_in;
 	}
 
 	MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
@@ -309,7 +311,7 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft,
 	MLX5_SET_CFG(in, end_flow_index, ix - 1);
 	ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in);
 	if (IS_ERR(ft->g[ft->num_groups]))
-		goto err;
+		goto err_clean_group;
 	ft->num_groups++;
 
 	memset(in, 0, inlen);
@@ -318,18 +320,20 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft,
 	MLX5_SET_CFG(in, end_flow_index, ix - 1);
 	ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in);
 	if (IS_ERR(ft->g[ft->num_groups]))
-		goto err;
+		goto err_clean_group;
 	ft->num_groups++;
 
 	kvfree(in);
 	return 0;
 
-err:
+err_clean_group:
 	err = PTR_ERR(ft->g[ft->num_groups]);
 	ft->g[ft->num_groups] = NULL;
-out:
+err_free_in:
 	kvfree(in);
-
+err_free_g:
+	kfree(ft->g);
+	ft->g = NULL;
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 67f546683e85..6ed3a32b7e22 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -95,7 +95,7 @@ static void mlx5e_destroy_tises(struct mlx5_core_dev *mdev, u32 tisn[MLX5_MAX_PO
 {
 	int tc, i;
 
-	for (i = 0; i < MLX5_MAX_PORTS; i++)
+	for (i = 0; i < mlx5e_get_num_lag_ports(mdev); i++)
 		for (tc = 0; tc < MLX5_MAX_NUM_TC; tc++)
 			mlx5e_destroy_tis(mdev, tisn[i][tc]);
 }
@@ -110,7 +110,7 @@ static int mlx5e_create_tises(struct mlx5_core_dev *mdev, u32 tisn[MLX5_MAX_PORT
 	int tc, i;
 	int err;
 
-	for (i = 0; i < MLX5_MAX_PORTS; i++) {
+	for (i = 0; i < mlx5e_get_num_lag_ports(mdev); i++) {
 		for (tc = 0; tc < MLX5_MAX_NUM_TC; tc++) {
 			u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {};
 			void *tisc;
@@ -140,7 +140,7 @@ err_close_tises:
 	return err;
 }
 
-int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
+int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises)
 {
 	struct mlx5e_hw_objs *res = &mdev->mlx5e_res.hw_objs;
 	int err;
@@ -169,11 +169,15 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
 		goto err_destroy_mkey;
 	}
 
-	err = mlx5e_create_tises(mdev, res->tisn);
-	if (err) {
-		mlx5_core_err(mdev, "alloc tises failed, %d\n", err);
-		goto err_destroy_bfreg;
+	if (create_tises) {
+		err = mlx5e_create_tises(mdev, res->tisn);
+		if (err) {
+			mlx5_core_err(mdev, "alloc tises failed, %d\n", err);
+			goto err_destroy_bfreg;
+		}
+		res->tisn_valid = true;
 	}
+
 	INIT_LIST_HEAD(&res->td.tirs_list);
 	mutex_init(&res->td.list_lock);
 
@@ -203,7 +207,8 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev)
 
 	mlx5_crypto_dek_cleanup(mdev->mlx5e_res.dek_priv);
 	mdev->mlx5e_res.dek_priv = NULL;
-	mlx5e_destroy_tises(mdev, res->tisn);
+	if (res->tisn_valid)
+		mlx5e_destroy_tises(mdev, res->tisn);
 	mlx5_free_bfreg(mdev, &res->bfreg);
 	mlx5_core_destroy_mkey(mdev, res->mkey);
 	mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index b5f1c4ca38ba..c8e8f512803e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5992,7 +5992,7 @@ static int mlx5e_resume(struct auxiliary_device *adev)
 	if (netif_device_present(netdev))
 		return 0;
 
-	err = mlx5e_create_mdev_resources(mdev);
+	err = mlx5e_create_mdev_resources(mdev, true);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 30932c9c9a8f..9fb2c057bd78 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -761,7 +761,7 @@ static int mlx5e_hairpin_create_indirect_rqt(struct mlx5e_hairpin *hp)
 
 	err = mlx5e_rss_params_indir_init(&indir, mdev,
 					  mlx5e_rqt_size(mdev, hp->num_channels),
-					  mlx5e_rqt_size(mdev, priv->max_nch));
+					  mlx5e_rqt_size(mdev, hp->num_channels));
 	if (err)
 		return err;
 
@@ -2014,9 +2014,10 @@ static void mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow,
 	list_for_each_entry_safe(peer_flow, tmp, &flow->peer_flows, peer_flows) {
 		if (peer_index != mlx5_get_dev_index(peer_flow->priv->mdev))
 			continue;
+
+		list_del(&peer_flow->peer_flows);
 		if (refcount_dec_and_test(&peer_flow->refcnt)) {
 			mlx5e_tc_del_fdb_flow(peer_flow->priv, peer_flow);
-			list_del(&peer_flow->peer_flows);
 			kfree(peer_flow);
 		}
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 5c166d9d2dca..2fa076b23fbe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -401,6 +401,8 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		mlx5e_skb_cb_hwtstamp_init(skb);
 		mlx5e_ptp_metadata_map_put(&sq->ptpsq->metadata_map, skb,
 					   metadata_index);
+		/* ensure skb is put on metadata_map before tracking the index */
+		wmb();
 		mlx5e_ptpsq_track_metadata(sq->ptpsq, metadata_index);
 		if (!netif_tx_queue_stopped(sq->txq) &&
 		    mlx5e_ptpsq_metadata_freelist_empty(sq->ptpsq)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c
index a7ed87e9d842..22dd30cf8033 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c
@@ -83,6 +83,7 @@ mlx5_esw_bridge_mdb_flow_create(u16 esw_owner_vhca_id, struct mlx5_esw_bridge_md
 		i++;
 	}
 
+	rule_spec->flow_context.flags |= FLOW_CONTEXT_UPLINK_HAIRPIN_EN;
 	rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
 	dmac_v = MLX5_ADDR_OF(fte_match_param, rule_spec->match_value, outer_headers.dmac_47_16);
 	ether_addr_copy(dmac_v, entry->key.addr);
@@ -587,6 +588,7 @@ mlx5_esw_bridge_mcast_vlan_flow_create(u16 vlan_proto, struct mlx5_esw_bridge_po
 	if (!rule_spec)
 		return ERR_PTR(-ENOMEM);
 
+	rule_spec->flow_context.flags |= FLOW_CONTEXT_UPLINK_HAIRPIN_EN;
 	rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
 
 	flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
@@ -662,6 +664,7 @@ mlx5_esw_bridge_mcast_fwd_flow_create(struct mlx5_esw_bridge_port *port)
 		dest.vport.flags = MLX5_FLOW_DEST_VPORT_VHCA_ID;
 		dest.vport.vhca_id = port->esw_owner_vhca_id;
 	}
+	rule_spec->flow_context.flags |= FLOW_CONTEXT_UPLINK_HAIRPIN_EN;
 	handle = mlx5_add_flow_rules(port->mcast.ft, rule_spec, &flow_act, &dest, 1);
 
 	kvfree(rule_spec);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
index 190f10aba170..5a0047bdcb51 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
@@ -152,7 +152,7 @@ void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev)
 
 	xa_for_each(&esw->offloads.vport_reps, i, rep) {
 		rpriv = rep->rep_data[REP_ETH].priv;
-		if (!rpriv || !rpriv->netdev || !atomic_read(&rpriv->tc_ht.nelems))
+		if (!rpriv || !rpriv->netdev)
 			continue;
 
 		rhashtable_walk_enter(&rpriv->tc_ht, &iter);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index b0455134c98e..baaae628b0a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -535,21 +535,26 @@ esw_src_port_rewrite_supported(struct mlx5_eswitch *esw)
 }
 
 static bool
-esw_dests_to_vf_pf_vports(struct mlx5_flow_destination *dests, int max_dest)
+esw_dests_to_int_external(struct mlx5_flow_destination *dests, int max_dest)
 {
-	bool vf_dest = false, pf_dest = false;
+	bool internal_dest = false, external_dest = false;
 	int i;
 
 	for (i = 0; i < max_dest; i++) {
-		if (dests[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT)
+		if (dests[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT &&
+		    dests[i].type != MLX5_FLOW_DESTINATION_TYPE_UPLINK)
 			continue;
 
-		if (dests[i].vport.num == MLX5_VPORT_UPLINK)
-			pf_dest = true;
+		/* Uplink dest is external, but considered as internal
+		 * if there is reformat because firmware uses LB+hairpin to support it.
+		 */
+		if (dests[i].vport.num == MLX5_VPORT_UPLINK &&
+		    !(dests[i].vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID))
+			external_dest = true;
 		else
-			vf_dest = true;
+			internal_dest = true;
 
-		if (vf_dest && pf_dest)
+		if (internal_dest && external_dest)
 			return true;
 	}
 
@@ -695,9 +700,9 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 
 		/* Header rewrite with combined wire+loopback in FDB is not allowed */
 		if ((flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) &&
-		    esw_dests_to_vf_pf_vports(dest, i)) {
+		    esw_dests_to_int_external(dest, i)) {
 			esw_warn(esw->dev,
-				 "FDB: Header rewrite with forwarding to both PF and VF is not allowed\n");
+				 "FDB: Header rewrite with forwarding to both internal and external dests is not allowed\n");
 			rule = ERR_PTR(-EINVAL);
 			goto err_esw_get;
 		}
@@ -3658,22 +3663,6 @@ static int esw_inline_mode_to_devlink(u8 mlx5_mode, u8 *mode)
 	return 0;
 }
 
-static bool esw_offloads_devlink_ns_eq_netdev_ns(struct devlink *devlink)
-{
-	struct mlx5_core_dev *dev = devlink_priv(devlink);
-	struct net *devl_net, *netdev_net;
-	bool ret = false;
-
-	mutex_lock(&dev->mlx5e_res.uplink_netdev_lock);
-	if (dev->mlx5e_res.uplink_netdev) {
-		netdev_net = dev_net(dev->mlx5e_res.uplink_netdev);
-		devl_net = devlink_net(devlink);
-		ret = net_eq(devl_net, netdev_net);
-	}
-	mutex_unlock(&dev->mlx5e_res.uplink_netdev_lock);
-	return ret;
-}
-
 int mlx5_eswitch_block_mode(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eswitch *esw = dev->priv.eswitch;
@@ -3718,13 +3707,6 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 	if (esw_mode_from_devlink(mode, &mlx5_mode))
 		return -EINVAL;
 
-	if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV &&
-	    !esw_offloads_devlink_ns_eq_netdev_ns(devlink)) {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "Can't change E-Switch mode to switchdev when netdev net namespace has diverged from the devlink's.");
-		return -EPERM;
-	}
-
 	mlx5_lag_disable_change(esw->dev);
 	err = mlx5_esw_try_lock(esw);
 	if (err < 0) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 1616a6144f7b..9b8599c200e2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -566,6 +566,8 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 		 fte->flow_context.flow_tag);
 	MLX5_SET(flow_context, in_flow_context, flow_source,
 		 fte->flow_context.flow_source);
+	MLX5_SET(flow_context, in_flow_context, uplink_hairpin_en,
+		 !!(fte->flow_context.flags & FLOW_CONTEXT_UPLINK_HAIRPIN_EN));
 
 	MLX5_SET(flow_context, in_flow_context, extended_destination,
 		 extended_dest);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index f27eab6e4929..2911aa34a5be 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -703,19 +703,30 @@ void mlx5_fw_reset_events_start(struct mlx5_core_dev *dev)
 {
 	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
 
+	if (!fw_reset)
+		return;
+
 	MLX5_NB_INIT(&fw_reset->nb, fw_reset_event_notifier, GENERAL_EVENT);
 	mlx5_eq_notifier_register(dev, &fw_reset->nb);
 }
 
 void mlx5_fw_reset_events_stop(struct mlx5_core_dev *dev)
 {
-	mlx5_eq_notifier_unregister(dev, &dev->priv.fw_reset->nb);
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	if (!fw_reset)
+		return;
+
+	mlx5_eq_notifier_unregister(dev, &fw_reset->nb);
 }
 
 void mlx5_drain_fw_reset(struct mlx5_core_dev *dev)
 {
 	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
 
+	if (!fw_reset)
+		return;
+
 	set_bit(MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, &fw_reset->reset_flags);
 	cancel_work_sync(&fw_reset->fw_live_patch_work);
 	cancel_work_sync(&fw_reset->reset_request_work);
@@ -733,9 +744,13 @@ static const struct devlink_param mlx5_fw_reset_devlink_params[] = {
 
 int mlx5_fw_reset_init(struct mlx5_core_dev *dev)
 {
-	struct mlx5_fw_reset *fw_reset = kzalloc(sizeof(*fw_reset), GFP_KERNEL);
+	struct mlx5_fw_reset *fw_reset;
 	int err;
 
+	if (!MLX5_CAP_MCAM_REG(dev, mfrl))
+		return 0;
+
+	fw_reset = kzalloc(sizeof(*fw_reset), GFP_KERNEL);
 	if (!fw_reset)
 		return -ENOMEM;
 	fw_reset->wq = create_singlethread_workqueue("mlx5_fw_reset_events");
@@ -771,6 +786,9 @@ void mlx5_fw_reset_cleanup(struct mlx5_core_dev *dev)
 {
 	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
 
+	if (!fw_reset)
+		return;
+
 	devl_params_unregister(priv_to_devlink(dev),
 			       mlx5_fw_reset_devlink_params,
 			       ARRAY_SIZE(mlx5_fw_reset_devlink_params));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 8ff6dc9bc803..b5c709bba155 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -452,10 +452,10 @@ mlx5_fw_reporter_diagnose(struct devlink_health_reporter *reporter,
 	struct health_buffer __iomem *h = health->health;
 	u8 synd = ioread8(&h->synd);
 
+	devlink_fmsg_u8_pair_put(fmsg, "Syndrome", synd);
 	if (!synd)
 		return 0;
 
-	devlink_fmsg_u8_pair_put(fmsg, "Syndrome", synd);
 	devlink_fmsg_string_pair_put(fmsg, "Description", hsynd_str(synd));
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 58845121954c..d77be1b4dd9c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -783,7 +783,7 @@ static int mlx5_rdma_setup_rn(struct ib_device *ibdev, u32 port_num,
 		}
 
 		/* This should only be called once per mdev */
-		err = mlx5e_create_mdev_resources(mdev);
+		err = mlx5e_create_mdev_resources(mdev, false);
 		if (err)
 			goto destroy_ht;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c
index 40c7be124041..58bd749b5e4d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c
@@ -98,7 +98,7 @@ static int create_aso_cq(struct mlx5_aso_cq *cq, void *cqc_data)
 	mlx5_fill_page_frag_array(&cq->wq_ctrl.buf,
 				  (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas));
 
-	MLX5_SET(cqc,   cqc, cq_period_mode, DIM_CQ_PERIOD_MODE_START_FROM_EQE);
+	MLX5_SET(cqc,   cqc, cq_period_mode, MLX5_CQ_PERIOD_MODE_START_FROM_EQE);
 	MLX5_SET(cqc,   cqc, c_eqn_or_apu_element, eqn);
 	MLX5_SET(cqc,   cqc, uar_page,      mdev->priv.uar->index);
 	MLX5_SET(cqc,   cqc, log_page_size, cq->wq_ctrl.buf.page_shift -
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
index 6f9790e97fed..2ebb61ef3ea9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
@@ -788,6 +788,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher,
 		switch (action_type) {
 		case DR_ACTION_TYP_DROP:
 			attr.final_icm_addr = nic_dmn->drop_icm_addr;
+			attr.hit_gvmi = nic_dmn->drop_icm_addr >> 48;
 			break;
 		case DR_ACTION_TYP_FT:
 			dest_action = action;
@@ -873,11 +874,17 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher,
 							action->sampler->tx_icm_addr;
 			break;
 		case DR_ACTION_TYP_VPORT:
-			attr.hit_gvmi = action->vport->caps->vhca_gvmi;
-			dest_action = action;
-			attr.final_icm_addr = rx_rule ?
-				action->vport->caps->icm_address_rx :
-				action->vport->caps->icm_address_tx;
+			if (unlikely(rx_rule && action->vport->caps->num == MLX5_VPORT_UPLINK)) {
+				/* can't go to uplink on RX rule - dropping instead */
+				attr.final_icm_addr = nic_dmn->drop_icm_addr;
+				attr.hit_gvmi = nic_dmn->drop_icm_addr >> 48;
+			} else {
+				attr.hit_gvmi = action->vport->caps->vhca_gvmi;
+				dest_action = action;
+				attr.final_icm_addr = rx_rule ?
+						      action->vport->caps->icm_address_rx :
+						      action->vport->caps->icm_address_tx;
+			}
 			break;
 		case DR_ACTION_TYP_POP_VLAN:
 			if (!rx_rule && !(dmn->ste_ctx->actions_caps &
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 21753f327868..1005bb6935b6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -440,6 +440,27 @@ out:
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_system_image_guid);
 
+int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group)
+{
+	int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out);
+	u32 *out;
+	int err;
+
+	out = kvzalloc(outlen, GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+
+	err = mlx5_query_nic_vport_context(mdev, 0, out);
+	if (err)
+		goto out;
+
+	*sd_group = MLX5_GET(query_nic_vport_context_out, out,
+			     nic_vport_context.sd_group);
+out:
+	kvfree(out);
+	return err;
+}
+
 int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid)
 {
 	u32 *out;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
index 4c98950380d5..d231f4d2888b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -301,6 +301,7 @@ mlxsw_sp_acl_erp_table_alloc(struct mlxsw_sp_acl_erp_core *erp_core,
 			     unsigned long *p_index)
 {
 	unsigned int num_rows, entry_size;
+	unsigned long index;
 
 	/* We only allow allocations of entire rows */
 	if (num_erps % erp_core->num_erp_banks != 0)
@@ -309,10 +310,11 @@ mlxsw_sp_acl_erp_table_alloc(struct mlxsw_sp_acl_erp_core *erp_core,
 	entry_size = erp_core->erpt_entries_size[region_type];
 	num_rows = num_erps / erp_core->num_erp_banks;
 
-	*p_index = gen_pool_alloc(erp_core->erp_tables, num_rows * entry_size);
-	if (*p_index == 0)
+	index = gen_pool_alloc(erp_core->erp_tables, num_rows * entry_size);
+	if (!index)
 		return -ENOBUFS;
-	*p_index -= MLXSW_SP_ACL_ERP_GENALLOC_OFFSET;
+
+	*p_index = index - MLXSW_SP_ACL_ERP_GENALLOC_OFFSET;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index d50786b0a6ce..50ea1eff02b2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -681,13 +681,13 @@ static void
 mlxsw_sp_acl_tcam_region_destroy(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_acl_tcam_region *region)
 {
+	struct mlxsw_sp_acl_tcam *tcam = mlxsw_sp_acl_to_tcam(mlxsw_sp->acl);
 	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 
 	ops->region_fini(mlxsw_sp, region->priv);
 	mlxsw_sp_acl_tcam_region_disable(mlxsw_sp, region);
 	mlxsw_sp_acl_tcam_region_free(mlxsw_sp, region);
-	mlxsw_sp_acl_tcam_region_id_put(region->group->tcam,
-					region->id);
+	mlxsw_sp_acl_tcam_region_id_put(tcam, region->id);
 	kfree(region);
 }
 
@@ -1564,6 +1564,8 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp,
 	tcam->max_groups = max_groups;
 	tcam->max_group_size = MLXSW_CORE_RES_GET(mlxsw_sp->core,
 						  ACL_MAX_GROUP_SIZE);
+	tcam->max_group_size = min_t(unsigned int, tcam->max_group_size,
+				     MLXSW_REG_PAGT_ACL_MAX_NUM);
 
 	err = ops->init(mlxsw_sp, tcam->priv, tcam);
 	if (err)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 2c255ed9b8a9..7164f9e6370f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -11472,6 +11472,13 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_register_netevent_notifier;
 
+	mlxsw_sp->router->netdevice_nb.notifier_call =
+		mlxsw_sp_router_netdevice_event;
+	err = register_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp),
+					      &mlxsw_sp->router->netdevice_nb);
+	if (err)
+		goto err_register_netdev_notifier;
+
 	mlxsw_sp->router->nexthop_nb.notifier_call =
 		mlxsw_sp_nexthop_obj_event;
 	err = register_nexthop_notifier(mlxsw_sp_net(mlxsw_sp),
@@ -11487,22 +11494,15 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_register_fib_notifier;
 
-	mlxsw_sp->router->netdevice_nb.notifier_call =
-		mlxsw_sp_router_netdevice_event;
-	err = register_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp),
-					      &mlxsw_sp->router->netdevice_nb);
-	if (err)
-		goto err_register_netdev_notifier;
-
 	return 0;
 
-err_register_netdev_notifier:
-	unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp),
-				&mlxsw_sp->router->fib_nb);
 err_register_fib_notifier:
 	unregister_nexthop_notifier(mlxsw_sp_net(mlxsw_sp),
 				    &mlxsw_sp->router->nexthop_nb);
 err_register_nexthop_notifier:
+	unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp),
+					  &router->netdevice_nb);
+err_register_netdev_notifier:
 	unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb);
 err_register_netevent_notifier:
 	unregister_inet6addr_validator_notifier(&router->inet6addr_valid_nb);
@@ -11550,11 +11550,11 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
 {
 	struct mlxsw_sp_router *router = mlxsw_sp->router;
 
-	unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp),
-					  &router->netdevice_nb);
 	unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp), &router->fib_nb);
 	unregister_nexthop_notifier(mlxsw_sp_net(mlxsw_sp),
 				    &router->nexthop_nb);
+	unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp),
+					  &router->netdevice_nb);
 	unregister_netevent_notifier(&router->netevent_nb);
 	unregister_inet6addr_validator_notifier(&router->inet6addr_valid_nb);
 	unregister_inetaddr_validator_notifier(&router->inetaddr_valid_nb);
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c b/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c
index 41fa2523d91d..5f2cd9a8cf8f 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c
@@ -37,19 +37,24 @@ static void lan966x_lag_set_aggr_pgids(struct lan966x *lan966x)
 
 	/* Now, set PGIDs for each active LAG */
 	for (lag = 0; lag < lan966x->num_phys_ports; ++lag) {
-		struct net_device *bond = lan966x->ports[lag]->bond;
+		struct lan966x_port *port = lan966x->ports[lag];
 		int num_active_ports = 0;
+		struct net_device *bond;
 		unsigned long bond_mask;
 		u8 aggr_idx[16];
 
-		if (!bond || (visited & BIT(lag)))
+		if (!port || !port->bond || (visited & BIT(lag)))
 			continue;
 
+		bond = port->bond;
 		bond_mask = lan966x_lag_get_mask(lan966x, bond);
 
 		for_each_set_bit(p, &bond_mask, lan966x->num_phys_ports) {
 			struct lan966x_port *port = lan966x->ports[p];
 
+			if (!port)
+				continue;
+
 			lan_wr(ANA_PGID_PGID_SET(bond_mask),
 			       lan966x, ANA_PGID(p));
 			if (port->lag_tx_active)
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c
index 92108d354051..2e83bbb9477e 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c
@@ -168,9 +168,10 @@ static void lan966x_port_link_up(struct lan966x_port *port)
 	lan966x_taprio_speed_set(port, config->speed);
 
 	/* Also the GIGA_MODE_ENA(1) needs to be set regardless of the
-	 * port speed for QSGMII ports.
+	 * port speed for QSGMII or SGMII ports.
 	 */
-	if (phy_interface_num_ports(config->portmode) == 4)
+	if (phy_interface_num_ports(config->portmode) == 4 ||
+	    config->portmode == PHY_INTERFACE_MODE_SGMII)
 		mode = DEV_MAC_MODE_CFG_GIGA_MODE_ENA_SET(1);
 
 	lan_wr(config->duplex | mode,
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c b/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c
index 4af285918ea2..75868b3f548e 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c
@@ -347,10 +347,10 @@ int sparx5_del_mact_entry(struct sparx5 *sparx5,
 				 list) {
 		if ((vid == 0 || mact_entry->vid == vid) &&
 		    ether_addr_equal(addr, mact_entry->mac)) {
+			sparx5_mact_forget(sparx5, addr, mact_entry->vid);
+
 			list_del(&mact_entry->list);
 			devm_kfree(sparx5->dev, mact_entry);
-
-			sparx5_mact_forget(sparx5, addr, mact_entry->vid);
 		}
 	}
 	mutex_unlock(&sparx5->mact_lock);
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
index d1f7fc8b1b71..3c066b62e689 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
@@ -757,6 +757,7 @@ static int mchp_sparx5_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, sparx5);
 	sparx5->pdev = pdev;
 	sparx5->dev = &pdev->dev;
+	spin_lock_init(&sparx5->tx_lock);
 
 	/* Do switch core reset if available */
 	reset = devm_reset_control_get_optional_shared(&pdev->dev, "switch");
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
index 6f565c0c0c3d..316fed5f2735 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
@@ -280,6 +280,7 @@ struct sparx5 {
 	int xtr_irq;
 	/* Frame DMA */
 	int fdma_irq;
+	spinlock_t tx_lock; /* lock for frame transmission */
 	struct sparx5_rx rx;
 	struct sparx5_tx tx;
 	/* PTP */
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
index 6db6ac6a3bbc..ac7e1cffbcec 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
@@ -244,10 +244,12 @@ netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	skb_tx_timestamp(skb);
+	spin_lock(&sparx5->tx_lock);
 	if (sparx5->fdma_irq > 0)
 		ret = sparx5_fdma_xmit(sparx5, ifh, skb);
 	else
 		ret = sparx5_inject(sparx5, ifh, skb, dev);
+	spin_unlock(&sparx5->tx_lock);
 
 	if (ret == -EBUSY)
 		goto busy;
diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index 61d8bfd12d5f..55408f16fbbc 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -414,6 +414,7 @@ static const u64 fix_mac[] = {
 	END_SIGN
 };
 
+MODULE_DESCRIPTION("Neterion 10GbE driver");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_VERSION);
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
index 2967bab72505..15180538b80a 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
@@ -1424,10 +1424,30 @@ static void nfp_nft_ct_translate_mangle_action(struct flow_action_entry *mangle_
 		mangle_action->mangle.mask = (__force u32)cpu_to_be32(mangle_action->mangle.mask);
 		return;
 
+	/* Both struct tcphdr and struct udphdr start with
+	 *	__be16 source;
+	 *	__be16 dest;
+	 * so we can use the same code for both.
+	 */
 	case FLOW_ACT_MANGLE_HDR_TYPE_TCP:
 	case FLOW_ACT_MANGLE_HDR_TYPE_UDP:
-		mangle_action->mangle.val = (__force u16)cpu_to_be16(mangle_action->mangle.val);
-		mangle_action->mangle.mask = (__force u16)cpu_to_be16(mangle_action->mangle.mask);
+		if (mangle_action->mangle.offset == offsetof(struct tcphdr, source)) {
+			mangle_action->mangle.val =
+				(__force u32)cpu_to_be32(mangle_action->mangle.val << 16);
+			/* The mask of mangle action is inverse mask,
+			 * so clear the dest tp port with 0xFFFF to
+			 * instead of rotate-left operation.
+			 */
+			mangle_action->mangle.mask =
+				(__force u32)cpu_to_be32(mangle_action->mangle.mask << 16 | 0xFFFF);
+		}
+		if (mangle_action->mangle.offset == offsetof(struct tcphdr, dest)) {
+			mangle_action->mangle.offset = 0;
+			mangle_action->mangle.val =
+				(__force u32)cpu_to_be32(mangle_action->mangle.val);
+			mangle_action->mangle.mask =
+				(__force u32)cpu_to_be32(mangle_action->mangle.mask);
+		}
 		return;
 
 	default:
@@ -1864,10 +1884,30 @@ int nfp_fl_ct_handle_post_ct(struct nfp_flower_priv *priv,
 {
 	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 	struct nfp_fl_ct_flow_entry *ct_entry;
+	struct flow_action_entry *ct_goto;
 	struct nfp_fl_ct_zone_entry *zt;
+	struct flow_action_entry *act;
 	bool wildcarded = false;
 	struct flow_match_ct ct;
-	struct flow_action_entry *ct_goto;
+	int i;
+
+	flow_action_for_each(i, act, &rule->action) {
+		switch (act->id) {
+		case FLOW_ACTION_REDIRECT:
+		case FLOW_ACTION_REDIRECT_INGRESS:
+		case FLOW_ACTION_MIRRED:
+		case FLOW_ACTION_MIRRED_INGRESS:
+			if (act->dev->rtnl_link_ops &&
+			    !strcmp(act->dev->rtnl_link_ops->kind, "openvswitch")) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "unsupported offload: out port is openvswitch internal port");
+				return -EOPNOTSUPP;
+			}
+			break;
+		default:
+			break;
+		}
+	}
 
 	flow_rule_match_ct(rule, &ct);
 	if (!ct.mask->ct_zone) {
diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index e522845c7c21..0d7d138d6e0d 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -1084,7 +1084,7 @@ nfp_tunnel_add_shared_mac(struct nfp_app *app, struct net_device *netdev,
 	u16 nfp_mac_idx = 0;
 
 	entry = nfp_tunnel_lookup_offloaded_macs(app, netdev->dev_addr);
-	if (entry && nfp_tunnel_is_mac_idx_global(entry->index)) {
+	if (entry && (nfp_tunnel_is_mac_idx_global(entry->index) || netif_is_lag_port(netdev))) {
 		if (entry->bridge_count ||
 		    !nfp_flower_is_supported_bridge(netdev)) {
 			nfp_tunnel_offloaded_macs_inc_ref_and_link(entry,
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 3b3210d823e8..f28e769e6fda 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -2776,6 +2776,7 @@ static void nfp_net_netdev_init(struct nfp_net *nn)
 	case NFP_NFD_VER_NFD3:
 		netdev->netdev_ops = &nfp_nfd3_netdev_ops;
 		netdev->xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY;
+		netdev->xdp_features |= NETDEV_XDP_ACT_REDIRECT;
 		break;
 	case NFP_NFD_VER_NFDK:
 		netdev->netdev_ops = &nfp_nfdk_netdev_ops;
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
index 33b4c2856316..3f10c5365c80 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
@@ -537,11 +537,13 @@ static int enable_bars(struct nfp6000_pcie *nfp, u16 interface)
 	const u32 barcfg_msix_general =
 		NFP_PCIE_BAR_PCIE2CPP_MapType(
 			NFP_PCIE_BAR_PCIE2CPP_MapType_GENERAL) |
-		NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT;
+		NFP_PCIE_BAR_PCIE2CPP_LengthSelect(
+			NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT);
 	const u32 barcfg_msix_xpb =
 		NFP_PCIE_BAR_PCIE2CPP_MapType(
 			NFP_PCIE_BAR_PCIE2CPP_MapType_BULK) |
-		NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT |
+		NFP_PCIE_BAR_PCIE2CPP_LengthSelect(
+			NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT) |
 		NFP_PCIE_BAR_PCIE2CPP_Target_BaseAddress(
 			NFP_CPP_TARGET_ISLAND_XPB);
 	const u32 barcfg_explicit[4] = {
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
index c49aa358e424..6ba8d4aca0a0 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
@@ -93,6 +93,7 @@ static void ionic_unmap_bars(struct ionic *ionic)
 			bars[i].len = 0;
 		}
 	}
+	ionic->num_bars = 0;
 }
 
 void __iomem *ionic_bus_map_dbpage(struct ionic *ionic, int page_num)
@@ -215,15 +216,17 @@ out:
 
 static void ionic_clear_pci(struct ionic *ionic)
 {
-	ionic->idev.dev_info_regs = NULL;
-	ionic->idev.dev_cmd_regs = NULL;
-	ionic->idev.intr_status = NULL;
-	ionic->idev.intr_ctrl = NULL;
-
-	ionic_unmap_bars(ionic);
-	pci_release_regions(ionic->pdev);
+	if (ionic->num_bars) {
+		ionic->idev.dev_info_regs = NULL;
+		ionic->idev.dev_cmd_regs = NULL;
+		ionic->idev.intr_status = NULL;
+		ionic->idev.intr_ctrl = NULL;
+
+		ionic_unmap_bars(ionic);
+		pci_release_regions(ionic->pdev);
+	}
 
-	if (atomic_read(&ionic->pdev->enable_cnt) > 0)
+	if (pci_is_enabled(ionic->pdev))
 		pci_disable_device(ionic->pdev);
 }
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
index 1e7c71f7f081..746072b4dbd0 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
@@ -319,22 +319,32 @@ do_check_time:
 
 u8 ionic_dev_cmd_status(struct ionic_dev *idev)
 {
+	if (!idev->dev_cmd_regs)
+		return (u8)PCI_ERROR_RESPONSE;
 	return ioread8(&idev->dev_cmd_regs->comp.comp.status);
 }
 
 bool ionic_dev_cmd_done(struct ionic_dev *idev)
 {
+	if (!idev->dev_cmd_regs)
+		return false;
 	return ioread32(&idev->dev_cmd_regs->done) & IONIC_DEV_CMD_DONE;
 }
 
 void ionic_dev_cmd_comp(struct ionic_dev *idev, union ionic_dev_cmd_comp *comp)
 {
+	if (!idev->dev_cmd_regs)
+		return;
 	memcpy_fromio(comp, &idev->dev_cmd_regs->comp, sizeof(*comp));
 }
 
 void ionic_dev_cmd_go(struct ionic_dev *idev, union ionic_dev_cmd *cmd)
 {
 	idev->opcode = cmd->cmd.opcode;
+
+	if (!idev->dev_cmd_regs)
+		return;
+
 	memcpy_toio(&idev->dev_cmd_regs->cmd, cmd, sizeof(*cmd));
 	iowrite32(0, &idev->dev_cmd_regs->done);
 	iowrite32(1, &idev->dev_cmd_regs->doorbell);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
index cd3c0b01402e..0ffc9c4904ac 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
@@ -90,18 +90,23 @@ static void ionic_get_regs(struct net_device *netdev, struct ethtool_regs *regs,
 			   void *p)
 {
 	struct ionic_lif *lif = netdev_priv(netdev);
+	struct ionic_dev *idev;
 	unsigned int offset;
 	unsigned int size;
 
 	regs->version = IONIC_DEV_CMD_REG_VERSION;
 
+	idev = &lif->ionic->idev;
+	if (!idev->dev_info_regs)
+		return;
+
 	offset = 0;
 	size = IONIC_DEV_INFO_REG_COUNT * sizeof(u32);
 	memcpy_fromio(p + offset, lif->ionic->idev.dev_info_regs->words, size);
 
 	offset += size;
 	size = IONIC_DEV_CMD_REG_COUNT * sizeof(u32);
-	memcpy_fromio(p + offset, lif->ionic->idev.dev_cmd_regs->words, size);
+	memcpy_fromio(p + offset, idev->dev_cmd_regs->words, size);
 }
 
 static void ionic_get_link_ext_stats(struct net_device *netdev,
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_fw.c b/drivers/net/ethernet/pensando/ionic/ionic_fw.c
index 5f40324cd243..3c209c1a2337 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_fw.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_fw.c
@@ -109,6 +109,11 @@ int ionic_firmware_update(struct ionic_lif *lif, const struct firmware *fw,
 	dl = priv_to_devlink(ionic);
 	devlink_flash_update_status_notify(dl, "Preparing to flash", NULL, 0, 0);
 
+	if (!idev->dev_cmd_regs) {
+		err = -ENXIO;
+		goto err_out;
+	}
+
 	buf_sz = sizeof(idev->dev_cmd_regs->data);
 
 	netdev_dbg(netdev,
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index cf2d5ad7b68c..fcb44ceeb6aa 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -3559,7 +3559,10 @@ int ionic_lif_init(struct ionic_lif *lif)
 			goto err_out_notifyq_deinit;
 	}
 
-	err = ionic_init_nic_features(lif);
+	if (test_bit(IONIC_LIF_F_FW_RESET, lif->state))
+		err = ionic_set_nic_features(lif, lif->netdev->features);
+	else
+		err = ionic_init_nic_features(lif);
 	if (err)
 		goto err_out_notifyq_deinit;
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index 165ab08ad2dd..2f479de329fe 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -416,6 +416,9 @@ static void ionic_dev_cmd_clean(struct ionic *ionic)
 {
 	struct ionic_dev *idev = &ionic->idev;
 
+	if (!idev->dev_cmd_regs)
+		return;
+
 	iowrite32(0, &idev->dev_cmd_regs->doorbell);
 	memset_io(&idev->dev_cmd_regs->cmd, 0, sizeof(idev->dev_cmd_regs->cmd));
 }
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 54cd96b035d6..6f4776759863 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -579,6 +579,9 @@ int ionic_tx_napi(struct napi_struct *napi, int budget)
 	work_done = ionic_cq_service(cq, budget,
 				     ionic_tx_service, NULL, NULL);
 
+	if (unlikely(!budget))
+		return budget;
+
 	if (work_done < budget && napi_complete_done(napi, work_done)) {
 		ionic_dim_update(qcq, IONIC_LIF_F_TX_DIM_INTR);
 		flags |= IONIC_INTR_CRED_UNMASK;
@@ -607,6 +610,9 @@ int ionic_rx_napi(struct napi_struct *napi, int budget)
 	u32 work_done = 0;
 	u32 flags = 0;
 
+	if (unlikely(!budget))
+		return budget;
+
 	lif = cq->bound_q->lif;
 	idev = &lif->ionic->idev;
 
@@ -656,6 +662,9 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget)
 	tx_work_done = ionic_cq_service(txcq, IONIC_TX_BUDGET_DEFAULT,
 					ionic_tx_service, NULL, NULL);
 
+	if (unlikely(!budget))
+		return budget;
+
 	rx_work_done = ionic_cq_service(rxcq, budget,
 					ionic_rx_service, NULL, NULL);
 
diff --git a/drivers/net/ethernet/qualcomm/qca_uart.c b/drivers/net/ethernet/qualcomm/qca_uart.c
index 9adec91f35e9..223321897b96 100644
--- a/drivers/net/ethernet/qualcomm/qca_uart.c
+++ b/drivers/net/ethernet/qualcomm/qca_uart.c
@@ -58,9 +58,8 @@ struct qcauart {
 	unsigned char *tx_buffer;
 };
 
-static int
-qca_tty_receive(struct serdev_device *serdev, const unsigned char *data,
-		size_t count)
+static ssize_t
+qca_tty_receive(struct serdev_device *serdev, const u8 *data, size_t count)
 {
 	struct qcauart *qca = serdev_device_get_drvdata(serdev);
 	struct net_device *netdev = qca->net_dev;
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index 39d24e07f306..5b69b9268c75 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -396,7 +396,7 @@ nla_put_failure:
 
 struct rtnl_link_ops rmnet_link_ops __read_mostly = {
 	.kind		= "rmnet",
-	.maxtype	= __IFLA_RMNET_MAX,
+	.maxtype	= IFLA_RMNET_MAX,
 	.priv_size	= sizeof(struct rmnet_priv),
 	.setup		= rmnet_vnd_setup,
 	.validate	= rmnet_rtnl_validate,
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 8649b3e90edb..f7566cfa45ca 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -772,29 +772,25 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q)
 	struct ravb_rx_desc *desc;
 	struct sk_buff *skb;
 	dma_addr_t dma_addr;
+	int rx_packets = 0;
 	u8  desc_status;
-	int boguscnt;
 	u16 pkt_len;
 	u8  die_dt;
 	int entry;
 	int limit;
+	int i;
 
 	entry = priv->cur_rx[q] % priv->num_rx_ring[q];
-	boguscnt = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q];
+	limit = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q];
 	stats = &priv->stats[q];
 
-	boguscnt = min(boguscnt, *quota);
-	limit = boguscnt;
 	desc = &priv->gbeth_rx_ring[entry];
-	while (desc->die_dt != DT_FEMPTY) {
+	for (i = 0; i < limit && rx_packets < *quota && desc->die_dt != DT_FEMPTY; i++) {
 		/* Descriptor type must be checked before all other reads */
 		dma_rmb();
 		desc_status = desc->msc;
 		pkt_len = le16_to_cpu(desc->ds_cc) & RX_DS;
 
-		if (--boguscnt < 0)
-			break;
-
 		/* We use 0-byte descriptors to mark the DMA mapping errors */
 		if (!pkt_len)
 			continue;
@@ -820,7 +816,7 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q)
 				skb_put(skb, pkt_len);
 				skb->protocol = eth_type_trans(skb, ndev);
 				napi_gro_receive(&priv->napi[q], skb);
-				stats->rx_packets++;
+				rx_packets++;
 				stats->rx_bytes += pkt_len;
 				break;
 			case DT_FSTART:
@@ -848,7 +844,7 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q)
 					eth_type_trans(priv->rx_1st_skb, ndev);
 				napi_gro_receive(&priv->napi[q],
 						 priv->rx_1st_skb);
-				stats->rx_packets++;
+				rx_packets++;
 				stats->rx_bytes += pkt_len;
 				break;
 			}
@@ -887,9 +883,9 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q)
 		desc->die_dt = DT_FEMPTY;
 	}
 
-	*quota -= limit - (++boguscnt);
-
-	return boguscnt <= 0;
+	stats->rx_packets += rx_packets;
+	*quota -= rx_packets;
+	return *quota == 0;
 }
 
 /* Packet receive function for Ethernet AVB */
@@ -1949,7 +1945,7 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	struct ravb_tstamp_skb *ts_skb;
 	struct ravb_tx_desc *desc;
 	unsigned long flags;
-	u32 dma_addr;
+	dma_addr_t dma_addr;
 	void *buffer;
 	u32 entry;
 	u32 len;
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 721c1f8e892f..5ba606a596e7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -59,28 +59,51 @@
 #undef FRAME_FILTER_DEBUG
 /* #define FRAME_FILTER_DEBUG */
 
+struct stmmac_q_tx_stats {
+	u64_stats_t tx_bytes;
+	u64_stats_t tx_set_ic_bit;
+	u64_stats_t tx_tso_frames;
+	u64_stats_t tx_tso_nfrags;
+};
+
+struct stmmac_napi_tx_stats {
+	u64_stats_t tx_packets;
+	u64_stats_t tx_pkt_n;
+	u64_stats_t poll;
+	u64_stats_t tx_clean;
+	u64_stats_t tx_set_ic_bit;
+};
+
 struct stmmac_txq_stats {
-	u64 tx_bytes;
-	u64 tx_packets;
-	u64 tx_pkt_n;
-	u64 tx_normal_irq_n;
-	u64 napi_poll;
-	u64 tx_clean;
-	u64 tx_set_ic_bit;
-	u64 tx_tso_frames;
-	u64 tx_tso_nfrags;
-	struct u64_stats_sync syncp;
+	/* Updates protected by tx queue lock. */
+	struct u64_stats_sync q_syncp;
+	struct stmmac_q_tx_stats q;
+
+	/* Updates protected by NAPI poll logic. */
+	struct u64_stats_sync napi_syncp;
+	struct stmmac_napi_tx_stats napi;
 } ____cacheline_aligned_in_smp;
 
+struct stmmac_napi_rx_stats {
+	u64_stats_t rx_bytes;
+	u64_stats_t rx_packets;
+	u64_stats_t rx_pkt_n;
+	u64_stats_t poll;
+};
+
 struct stmmac_rxq_stats {
-	u64 rx_bytes;
-	u64 rx_packets;
-	u64 rx_pkt_n;
-	u64 rx_normal_irq_n;
-	u64 napi_poll;
-	struct u64_stats_sync syncp;
+	/* Updates protected by NAPI poll logic. */
+	struct u64_stats_sync napi_syncp;
+	struct stmmac_napi_rx_stats napi;
 } ____cacheline_aligned_in_smp;
 
+/* Updates on each CPU protected by not allowing nested irqs. */
+struct stmmac_pcpu_stats {
+	struct u64_stats_sync syncp;
+	u64_stats_t rx_normal_irq_n[MTL_MAX_TX_QUEUES];
+	u64_stats_t tx_normal_irq_n[MTL_MAX_RX_QUEUES];
+};
+
 /* Extra statistic and debug information exposed by ethtool */
 struct stmmac_extra_stats {
 	/* Transmit errors */
@@ -205,6 +228,7 @@ struct stmmac_extra_stats {
 	/* per queue statistics */
 	struct stmmac_txq_stats txq_stats[MTL_MAX_TX_QUEUES];
 	struct stmmac_rxq_stats rxq_stats[MTL_MAX_RX_QUEUES];
+	struct stmmac_pcpu_stats __percpu *pcpu_stats;
 	unsigned long rx_dropped;
 	unsigned long rx_errors;
 	unsigned long tx_dropped;
@@ -216,6 +240,7 @@ struct stmmac_safety_stats {
 	unsigned long mac_errors[32];
 	unsigned long mtl_errors[32];
 	unsigned long dma_errors[32];
+	unsigned long dma_dpp_errors[32];
 };
 
 /* Number of fields in Safety Stats */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
index 8f730ada71f9..6b65420e11b5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
@@ -353,6 +353,10 @@ static int imx_dwmac_probe(struct platform_device *pdev)
 	if (data->flags & STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY)
 		plat_dat->flags |= STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY;
 
+	/* Default TX Q0 to use TSO and rest TXQ for TBS */
+	for (int i = 1; i < plat_dat->tx_queues_to_use; i++)
+		plat_dat->tx_queues_cfg[i].tbs_en = 1;
+
 	plat_dat->host_dma_width = dwmac->ops->addr_width;
 	plat_dat->init = imx_dwmac_init;
 	plat_dat->exit = imx_dwmac_exit;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 137741b94122..b21d99faa2d0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -441,8 +441,7 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv,
 				     struct stmmac_extra_stats *x, u32 chan,
 				     u32 dir)
 {
-	struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan];
-	struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan];
+	struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats);
 	int ret = 0;
 	u32 v;
 
@@ -455,9 +454,9 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv,
 
 	if (v & EMAC_TX_INT) {
 		ret |= handle_tx;
-		u64_stats_update_begin(&txq_stats->syncp);
-		txq_stats->tx_normal_irq_n++;
-		u64_stats_update_end(&txq_stats->syncp);
+		u64_stats_update_begin(&stats->syncp);
+		u64_stats_inc(&stats->tx_normal_irq_n[chan]);
+		u64_stats_update_end(&stats->syncp);
 	}
 
 	if (v & EMAC_TX_DMA_STOP_INT)
@@ -479,9 +478,9 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv,
 
 	if (v & EMAC_RX_INT) {
 		ret |= handle_rx;
-		u64_stats_update_begin(&rxq_stats->syncp);
-		rxq_stats->rx_normal_irq_n++;
-		u64_stats_update_end(&rxq_stats->syncp);
+		u64_stats_update_begin(&stats->syncp);
+		u64_stats_inc(&stats->rx_normal_irq_n[chan]);
+		u64_stats_update_end(&stats->syncp);
 	}
 
 	if (v & EMAC_RX_BUF_UA_INT)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
index 9470d3fd2ded..0d185e54eb7e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
@@ -171,8 +171,7 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
 	const struct dwmac4_addrs *dwmac4_addrs = priv->plat->dwmac4_addrs;
 	u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(dwmac4_addrs, chan));
 	u32 intr_en = readl(ioaddr + DMA_CHAN_INTR_ENA(dwmac4_addrs, chan));
-	struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan];
-	struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan];
+	struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats);
 	int ret = 0;
 
 	if (dir == DMA_DIR_RX)
@@ -201,15 +200,15 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
 	}
 	/* TX/RX NORMAL interrupts */
 	if (likely(intr_status & DMA_CHAN_STATUS_RI)) {
-		u64_stats_update_begin(&rxq_stats->syncp);
-		rxq_stats->rx_normal_irq_n++;
-		u64_stats_update_end(&rxq_stats->syncp);
+		u64_stats_update_begin(&stats->syncp);
+		u64_stats_inc(&stats->rx_normal_irq_n[chan]);
+		u64_stats_update_end(&stats->syncp);
 		ret |= handle_rx;
 	}
 	if (likely(intr_status & DMA_CHAN_STATUS_TI)) {
-		u64_stats_update_begin(&txq_stats->syncp);
-		txq_stats->tx_normal_irq_n++;
-		u64_stats_update_end(&txq_stats->syncp);
+		u64_stats_update_begin(&stats->syncp);
+		u64_stats_inc(&stats->tx_normal_irq_n[chan]);
+		u64_stats_update_end(&stats->syncp);
 		ret |= handle_tx;
 	}
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
index 7907d62d3437..85e18f9a22f9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
@@ -162,8 +162,7 @@ static void show_rx_process_state(unsigned int status)
 int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
 			struct stmmac_extra_stats *x, u32 chan, u32 dir)
 {
-	struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan];
-	struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan];
+	struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats);
 	int ret = 0;
 	/* read the status register (CSR5) */
 	u32 intr_status = readl(ioaddr + DMA_STATUS);
@@ -215,16 +214,16 @@ int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
 			u32 value = readl(ioaddr + DMA_INTR_ENA);
 			/* to schedule NAPI on real RIE event. */
 			if (likely(value & DMA_INTR_ENA_RIE)) {
-				u64_stats_update_begin(&rxq_stats->syncp);
-				rxq_stats->rx_normal_irq_n++;
-				u64_stats_update_end(&rxq_stats->syncp);
+				u64_stats_update_begin(&stats->syncp);
+				u64_stats_inc(&stats->rx_normal_irq_n[chan]);
+				u64_stats_update_end(&stats->syncp);
 				ret |= handle_rx;
 			}
 		}
 		if (likely(intr_status & DMA_STATUS_TI)) {
-			u64_stats_update_begin(&txq_stats->syncp);
-			txq_stats->tx_normal_irq_n++;
-			u64_stats_update_end(&txq_stats->syncp);
+			u64_stats_update_begin(&stats->syncp);
+			u64_stats_inc(&stats->tx_normal_irq_n[chan]);
+			u64_stats_update_end(&stats->syncp);
 			ret |= handle_tx;
 		}
 		if (unlikely(intr_status & DMA_STATUS_ERI))
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index 207ff1799f2c..6a2c7d22df1e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -303,6 +303,8 @@
 #define XGMAC_RXCEIE			BIT(4)
 #define XGMAC_TXCEIE			BIT(0)
 #define XGMAC_MTL_ECC_INT_STATUS	0x000010cc
+#define XGMAC_MTL_DPP_CONTROL		0x000010e0
+#define XGMAC_DPP_DISABLE		BIT(0)
 #define XGMAC_MTL_TXQ_OPMODE(x)		(0x00001100 + (0x80 * (x)))
 #define XGMAC_TQS			GENMASK(25, 16)
 #define XGMAC_TQS_SHIFT			16
@@ -385,6 +387,7 @@
 #define XGMAC_DCEIE			BIT(1)
 #define XGMAC_TCEIE			BIT(0)
 #define XGMAC_DMA_ECC_INT_STATUS	0x0000306c
+#define XGMAC_DMA_DPP_INT_STATUS	0x00003074
 #define XGMAC_DMA_CH_CONTROL(x)		(0x00003100 + (0x80 * (x)))
 #define XGMAC_SPH			BIT(24)
 #define XGMAC_PBLx8			BIT(16)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index eb48211d9b0e..1af2f89a0504 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -830,6 +830,44 @@ static const struct dwxgmac3_error_desc dwxgmac3_dma_errors[32]= {
 	{ false, "UNKNOWN", "Unknown Error" }, /* 31 */
 };
 
+#define DPP_RX_ERR "Read Rx Descriptor Parity checker Error"
+#define DPP_TX_ERR "Read Tx Descriptor Parity checker Error"
+
+static const struct dwxgmac3_error_desc dwxgmac3_dma_dpp_errors[32] = {
+	{ true, "TDPES0", DPP_TX_ERR },
+	{ true, "TDPES1", DPP_TX_ERR },
+	{ true, "TDPES2", DPP_TX_ERR },
+	{ true, "TDPES3", DPP_TX_ERR },
+	{ true, "TDPES4", DPP_TX_ERR },
+	{ true, "TDPES5", DPP_TX_ERR },
+	{ true, "TDPES6", DPP_TX_ERR },
+	{ true, "TDPES7", DPP_TX_ERR },
+	{ true, "TDPES8", DPP_TX_ERR },
+	{ true, "TDPES9", DPP_TX_ERR },
+	{ true, "TDPES10", DPP_TX_ERR },
+	{ true, "TDPES11", DPP_TX_ERR },
+	{ true, "TDPES12", DPP_TX_ERR },
+	{ true, "TDPES13", DPP_TX_ERR },
+	{ true, "TDPES14", DPP_TX_ERR },
+	{ true, "TDPES15", DPP_TX_ERR },
+	{ true, "RDPES0", DPP_RX_ERR },
+	{ true, "RDPES1", DPP_RX_ERR },
+	{ true, "RDPES2", DPP_RX_ERR },
+	{ true, "RDPES3", DPP_RX_ERR },
+	{ true, "RDPES4", DPP_RX_ERR },
+	{ true, "RDPES5", DPP_RX_ERR },
+	{ true, "RDPES6", DPP_RX_ERR },
+	{ true, "RDPES7", DPP_RX_ERR },
+	{ true, "RDPES8", DPP_RX_ERR },
+	{ true, "RDPES9", DPP_RX_ERR },
+	{ true, "RDPES10", DPP_RX_ERR },
+	{ true, "RDPES11", DPP_RX_ERR },
+	{ true, "RDPES12", DPP_RX_ERR },
+	{ true, "RDPES13", DPP_RX_ERR },
+	{ true, "RDPES14", DPP_RX_ERR },
+	{ true, "RDPES15", DPP_RX_ERR },
+};
+
 static void dwxgmac3_handle_dma_err(struct net_device *ndev,
 				    void __iomem *ioaddr, bool correctable,
 				    struct stmmac_safety_stats *stats)
@@ -841,6 +879,13 @@ static void dwxgmac3_handle_dma_err(struct net_device *ndev,
 
 	dwxgmac3_log_error(ndev, value, correctable, "DMA",
 			   dwxgmac3_dma_errors, STAT_OFF(dma_errors), stats);
+
+	value = readl(ioaddr + XGMAC_DMA_DPP_INT_STATUS);
+	writel(value, ioaddr + XGMAC_DMA_DPP_INT_STATUS);
+
+	dwxgmac3_log_error(ndev, value, false, "DMA_DPP",
+			   dwxgmac3_dma_dpp_errors,
+			   STAT_OFF(dma_dpp_errors), stats);
 }
 
 static int
@@ -881,6 +926,12 @@ dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp,
 	value |= XGMAC_TMOUTEN; /* FSM Timeout Feature */
 	writel(value, ioaddr + XGMAC_MAC_FSM_CONTROL);
 
+	/* 5. Enable Data Path Parity Protection */
+	value = readl(ioaddr + XGMAC_MTL_DPP_CONTROL);
+	/* already enabled by default, explicit enable it again */
+	value &= ~XGMAC_DPP_DISABLE;
+	writel(value, ioaddr + XGMAC_MTL_DPP_CONTROL);
+
 	return 0;
 }
 
@@ -914,7 +965,11 @@ static int dwxgmac3_safety_feat_irq_status(struct net_device *ndev,
 		ret |= !corr;
 	}
 
-	err = dma & (XGMAC_DEUIS | XGMAC_DECIS);
+	/* DMA_DPP_Interrupt_Status is indicated by MCSIS bit in
+	 * DMA_Safety_Interrupt_Status, so we handle DMA Data Path
+	 * Parity Errors here
+	 */
+	err = dma & (XGMAC_DEUIS | XGMAC_DECIS | XGMAC_MCSIS);
 	corr = dma & XGMAC_DECIS;
 	if (err) {
 		dwxgmac3_handle_dma_err(ndev, ioaddr, corr, stats);
@@ -930,6 +985,7 @@ static const struct dwxgmac3_error {
 	{ dwxgmac3_mac_errors },
 	{ dwxgmac3_mtl_errors },
 	{ dwxgmac3_dma_errors },
+	{ dwxgmac3_dma_dpp_errors },
 };
 
 static int dwxgmac3_safety_feat_dump(struct stmmac_safety_stats *stats,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 3cde695fec91..dd2ab6185c40 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -337,8 +337,7 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv,
 				  struct stmmac_extra_stats *x, u32 chan,
 				  u32 dir)
 {
-	struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan];
-	struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan];
+	struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats);
 	u32 intr_status = readl(ioaddr + XGMAC_DMA_CH_STATUS(chan));
 	u32 intr_en = readl(ioaddr + XGMAC_DMA_CH_INT_EN(chan));
 	int ret = 0;
@@ -367,15 +366,15 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv,
 	/* TX/RX NORMAL interrupts */
 	if (likely(intr_status & XGMAC_NIS)) {
 		if (likely(intr_status & XGMAC_RI)) {
-			u64_stats_update_begin(&rxq_stats->syncp);
-			rxq_stats->rx_normal_irq_n++;
-			u64_stats_update_end(&rxq_stats->syncp);
+			u64_stats_update_begin(&stats->syncp);
+			u64_stats_inc(&stats->rx_normal_irq_n[chan]);
+			u64_stats_update_end(&stats->syncp);
 			ret |= handle_rx;
 		}
 		if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) {
-			u64_stats_update_begin(&txq_stats->syncp);
-			txq_stats->tx_normal_irq_n++;
-			u64_stats_update_end(&txq_stats->syncp);
+			u64_stats_update_begin(&stats->syncp);
+			u64_stats_inc(&stats->tx_normal_irq_n[chan]);
+			u64_stats_update_end(&stats->syncp);
 			ret |= handle_tx;
 		}
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c
index 1bd34b2a47e8..29367105df54 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.c
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c
@@ -224,7 +224,7 @@ static const struct stmmac_hwif_entry {
 		.regs = {
 			.ptp_off = PTP_GMAC4_OFFSET,
 			.mmc_off = MMC_GMAC4_OFFSET,
-			.est_off = EST_XGMAC_OFFSET,
+			.est_off = EST_GMAC4_OFFSET,
 		},
 		.desc = &dwmac4_desc_ops,
 		.dma = &dwmac410_dma_ops,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 9f89acf31050..f155e4841c62 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -267,6 +267,7 @@ struct stmmac_priv {
 	u32 msg_enable;
 	int wolopts;
 	int wol_irq;
+	bool wol_irq_disabled;
 	int clk_csr;
 	struct timer_list eee_ctrl_timer;
 	int lpi_irq;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index dd05437b51f9..ec44becf0e2d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -321,8 +321,9 @@ static int stmmac_ethtool_get_link_ksettings(struct net_device *dev,
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 
-	if (priv->hw->pcs & STMMAC_PCS_RGMII ||
-	    priv->hw->pcs & STMMAC_PCS_SGMII) {
+	if (!(priv->plat->flags & STMMAC_FLAG_HAS_INTEGRATED_PCS) &&
+	    (priv->hw->pcs & STMMAC_PCS_RGMII ||
+	     priv->hw->pcs & STMMAC_PCS_SGMII)) {
 		struct rgmii_adv adv;
 		u32 supported, advertising, lp_advertising;
 
@@ -407,8 +408,9 @@ stmmac_ethtool_set_link_ksettings(struct net_device *dev,
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 
-	if (priv->hw->pcs & STMMAC_PCS_RGMII ||
-	    priv->hw->pcs & STMMAC_PCS_SGMII) {
+	if (!(priv->plat->flags & STMMAC_FLAG_HAS_INTEGRATED_PCS) &&
+	    (priv->hw->pcs & STMMAC_PCS_RGMII ||
+	     priv->hw->pcs & STMMAC_PCS_SGMII)) {
 		/* Only support ANE */
 		if (cmd->base.autoneg != AUTONEG_ENABLE)
 			return -EINVAL;
@@ -547,44 +549,79 @@ stmmac_set_pauseparam(struct net_device *netdev,
 	}
 }
 
+static u64 stmmac_get_rx_normal_irq_n(struct stmmac_priv *priv, int q)
+{
+	u64 total;
+	int cpu;
+
+	total = 0;
+	for_each_possible_cpu(cpu) {
+		struct stmmac_pcpu_stats *pcpu;
+		unsigned int start;
+		u64 irq_n;
+
+		pcpu = per_cpu_ptr(priv->xstats.pcpu_stats, cpu);
+		do {
+			start = u64_stats_fetch_begin(&pcpu->syncp);
+			irq_n = u64_stats_read(&pcpu->rx_normal_irq_n[q]);
+		} while (u64_stats_fetch_retry(&pcpu->syncp, start));
+		total += irq_n;
+	}
+	return total;
+}
+
+static u64 stmmac_get_tx_normal_irq_n(struct stmmac_priv *priv, int q)
+{
+	u64 total;
+	int cpu;
+
+	total = 0;
+	for_each_possible_cpu(cpu) {
+		struct stmmac_pcpu_stats *pcpu;
+		unsigned int start;
+		u64 irq_n;
+
+		pcpu = per_cpu_ptr(priv->xstats.pcpu_stats, cpu);
+		do {
+			start = u64_stats_fetch_begin(&pcpu->syncp);
+			irq_n = u64_stats_read(&pcpu->tx_normal_irq_n[q]);
+		} while (u64_stats_fetch_retry(&pcpu->syncp, start));
+		total += irq_n;
+	}
+	return total;
+}
+
 static void stmmac_get_per_qstats(struct stmmac_priv *priv, u64 *data)
 {
 	u32 tx_cnt = priv->plat->tx_queues_to_use;
 	u32 rx_cnt = priv->plat->rx_queues_to_use;
 	unsigned int start;
-	int q, stat;
-	char *p;
+	int q;
 
 	for (q = 0; q < tx_cnt; q++) {
 		struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[q];
-		struct stmmac_txq_stats snapshot;
+		u64 pkt_n;
 
 		do {
-			start = u64_stats_fetch_begin(&txq_stats->syncp);
-			snapshot = *txq_stats;
-		} while (u64_stats_fetch_retry(&txq_stats->syncp, start));
+			start = u64_stats_fetch_begin(&txq_stats->napi_syncp);
+			pkt_n = u64_stats_read(&txq_stats->napi.tx_pkt_n);
+		} while (u64_stats_fetch_retry(&txq_stats->napi_syncp, start));
 
-		p = (char *)&snapshot + offsetof(struct stmmac_txq_stats, tx_pkt_n);
-		for (stat = 0; stat < STMMAC_TXQ_STATS; stat++) {
-			*data++ = (*(u64 *)p);
-			p += sizeof(u64);
-		}
+		*data++ = pkt_n;
+		*data++ = stmmac_get_tx_normal_irq_n(priv, q);
 	}
 
 	for (q = 0; q < rx_cnt; q++) {
 		struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[q];
-		struct stmmac_rxq_stats snapshot;
+		u64 pkt_n;
 
 		do {
-			start = u64_stats_fetch_begin(&rxq_stats->syncp);
-			snapshot = *rxq_stats;
-		} while (u64_stats_fetch_retry(&rxq_stats->syncp, start));
+			start = u64_stats_fetch_begin(&rxq_stats->napi_syncp);
+			pkt_n = u64_stats_read(&rxq_stats->napi.rx_pkt_n);
+		} while (u64_stats_fetch_retry(&rxq_stats->napi_syncp, start));
 
-		p = (char *)&snapshot + offsetof(struct stmmac_rxq_stats, rx_pkt_n);
-		for (stat = 0; stat < STMMAC_RXQ_STATS; stat++) {
-			*data++ = (*(u64 *)p);
-			p += sizeof(u64);
-		}
+		*data++ = pkt_n;
+		*data++ = stmmac_get_rx_normal_irq_n(priv, q);
 	}
 }
 
@@ -643,39 +680,49 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
 	pos = j;
 	for (i = 0; i < rx_queues_count; i++) {
 		struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[i];
-		struct stmmac_rxq_stats snapshot;
+		struct stmmac_napi_rx_stats snapshot;
+		u64 n_irq;
 
 		j = pos;
 		do {
-			start = u64_stats_fetch_begin(&rxq_stats->syncp);
-			snapshot = *rxq_stats;
-		} while (u64_stats_fetch_retry(&rxq_stats->syncp, start));
-
-		data[j++] += snapshot.rx_pkt_n;
-		data[j++] += snapshot.rx_normal_irq_n;
-		normal_irq_n += snapshot.rx_normal_irq_n;
-		napi_poll += snapshot.napi_poll;
+			start = u64_stats_fetch_begin(&rxq_stats->napi_syncp);
+			snapshot = rxq_stats->napi;
+		} while (u64_stats_fetch_retry(&rxq_stats->napi_syncp, start));
+
+		data[j++] += u64_stats_read(&snapshot.rx_pkt_n);
+		n_irq = stmmac_get_rx_normal_irq_n(priv, i);
+		data[j++] += n_irq;
+		normal_irq_n += n_irq;
+		napi_poll += u64_stats_read(&snapshot.poll);
 	}
 
 	pos = j;
 	for (i = 0; i < tx_queues_count; i++) {
 		struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[i];
-		struct stmmac_txq_stats snapshot;
+		struct stmmac_napi_tx_stats napi_snapshot;
+		struct stmmac_q_tx_stats q_snapshot;
+		u64 n_irq;
 
 		j = pos;
 		do {
-			start = u64_stats_fetch_begin(&txq_stats->syncp);
-			snapshot = *txq_stats;
-		} while (u64_stats_fetch_retry(&txq_stats->syncp, start));
-
-		data[j++] += snapshot.tx_pkt_n;
-		data[j++] += snapshot.tx_normal_irq_n;
-		normal_irq_n += snapshot.tx_normal_irq_n;
-		data[j++] += snapshot.tx_clean;
-		data[j++] += snapshot.tx_set_ic_bit;
-		data[j++] += snapshot.tx_tso_frames;
-		data[j++] += snapshot.tx_tso_nfrags;
-		napi_poll += snapshot.napi_poll;
+			start = u64_stats_fetch_begin(&txq_stats->q_syncp);
+			q_snapshot = txq_stats->q;
+		} while (u64_stats_fetch_retry(&txq_stats->q_syncp, start));
+		do {
+			start = u64_stats_fetch_begin(&txq_stats->napi_syncp);
+			napi_snapshot = txq_stats->napi;
+		} while (u64_stats_fetch_retry(&txq_stats->napi_syncp, start));
+
+		data[j++] += u64_stats_read(&napi_snapshot.tx_pkt_n);
+		n_irq = stmmac_get_tx_normal_irq_n(priv, i);
+		data[j++] += n_irq;
+		normal_irq_n += n_irq;
+		data[j++] += u64_stats_read(&napi_snapshot.tx_clean);
+		data[j++] += u64_stats_read(&q_snapshot.tx_set_ic_bit) +
+			u64_stats_read(&napi_snapshot.tx_set_ic_bit);
+		data[j++] += u64_stats_read(&q_snapshot.tx_tso_frames);
+		data[j++] += u64_stats_read(&q_snapshot.tx_tso_nfrags);
+		napi_poll += u64_stats_read(&napi_snapshot.poll);
 	}
 	normal_irq_n += priv->xstats.rx_early_irq;
 	data[j++] = normal_irq_n;
@@ -830,10 +877,16 @@ static int stmmac_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 	if (wol->wolopts) {
 		pr_info("stmmac: wakeup enable\n");
 		device_set_wakeup_enable(priv->device, 1);
-		enable_irq_wake(priv->wol_irq);
+		/* Avoid unbalanced enable_irq_wake calls */
+		if (priv->wol_irq_disabled)
+			enable_irq_wake(priv->wol_irq);
+		priv->wol_irq_disabled = false;
 	} else {
 		device_set_wakeup_enable(priv->device, 0);
-		disable_irq_wake(priv->wol_irq);
+		/* Avoid unbalanced disable_irq_wake calls */
+		if (!priv->wol_irq_disabled)
+			disable_irq_wake(priv->wol_irq);
+		priv->wol_irq_disabled = true;
 	}
 
 	mutex_lock(&priv->lock);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 47de466e432c..7c6aef033a45 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2482,7 +2482,6 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 	struct xdp_desc xdp_desc;
 	bool work_done = true;
 	u32 tx_set_ic_bit = 0;
-	unsigned long flags;
 
 	/* Avoids TX time-out as we are sharing with slow path */
 	txq_trans_cond_update(nq);
@@ -2566,9 +2565,9 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 		tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, priv->dma_conf.dma_tx_size);
 		entry = tx_q->cur_tx;
 	}
-	flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-	txq_stats->tx_set_ic_bit += tx_set_ic_bit;
-	u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+	u64_stats_update_begin(&txq_stats->napi_syncp);
+	u64_stats_add(&txq_stats->napi.tx_set_ic_bit, tx_set_ic_bit);
+	u64_stats_update_end(&txq_stats->napi_syncp);
 
 	if (tx_desc) {
 		stmmac_flush_tx_descriptors(priv, queue);
@@ -2616,7 +2615,6 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue,
 	unsigned int bytes_compl = 0, pkts_compl = 0;
 	unsigned int entry, xmits = 0, count = 0;
 	u32 tx_packets = 0, tx_errors = 0;
-	unsigned long flags;
 
 	__netif_tx_lock_bh(netdev_get_tx_queue(priv->dev, queue));
 
@@ -2674,7 +2672,8 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue,
 			}
 			if (skb) {
 				stmmac_get_tx_hwtstamp(priv, p, skb);
-			} else {
+			} else if (tx_q->xsk_pool &&
+				   xp_tx_metadata_enabled(tx_q->xsk_pool)) {
 				struct stmmac_xsk_tx_complete tx_compl = {
 					.priv = priv,
 					.desc = p,
@@ -2782,11 +2781,11 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue,
 	if (tx_q->dirty_tx != tx_q->cur_tx)
 		*pending_packets = true;
 
-	flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-	txq_stats->tx_packets += tx_packets;
-	txq_stats->tx_pkt_n += tx_packets;
-	txq_stats->tx_clean++;
-	u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+	u64_stats_update_begin(&txq_stats->napi_syncp);
+	u64_stats_add(&txq_stats->napi.tx_packets, tx_packets);
+	u64_stats_add(&txq_stats->napi.tx_pkt_n, tx_packets);
+	u64_stats_inc(&txq_stats->napi.tx_clean);
+	u64_stats_update_end(&txq_stats->napi_syncp);
 
 	priv->xstats.tx_errors += tx_errors;
 
@@ -3628,6 +3627,7 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
 	/* Request the Wake IRQ in case of another line
 	 * is used for WoL
 	 */
+	priv->wol_irq_disabled = true;
 	if (priv->wol_irq > 0 && priv->wol_irq != dev->irq) {
 		int_name = priv->int_name_wol;
 		sprintf(int_name, "%s:%s", dev->name, "wol");
@@ -3931,6 +3931,9 @@ static int __stmmac_open(struct net_device *dev,
 	priv->rx_copybreak = STMMAC_RX_COPYBREAK;
 
 	buf_sz = dma_conf->dma_buf_sz;
+	for (int i = 0; i < MTL_MAX_TX_QUEUES; i++)
+		if (priv->dma_conf.tx_queue[i].tbs & STMMAC_TBS_EN)
+			dma_conf->tx_queue[i].tbs = priv->dma_conf.tx_queue[i].tbs;
 	memcpy(&priv->dma_conf, dma_conf, sizeof(*dma_conf));
 
 	stmmac_reset_queues_param(priv);
@@ -4003,8 +4006,10 @@ static void stmmac_fpe_stop_wq(struct stmmac_priv *priv)
 {
 	set_bit(__FPE_REMOVING, &priv->fpe_task_state);
 
-	if (priv->fpe_wq)
+	if (priv->fpe_wq) {
 		destroy_workqueue(priv->fpe_wq);
+		priv->fpe_wq = NULL;
+	}
 
 	netdev_info(priv->dev, "FPE workqueue stop");
 }
@@ -4209,7 +4214,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct stmmac_tx_queue *tx_q;
 	bool has_vlan, set_ic;
 	u8 proto_hdr_len, hdr;
-	unsigned long flags;
 	u32 pay_len, mss;
 	dma_addr_t des;
 	int i;
@@ -4374,13 +4378,13 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 		netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
 	}
 
-	flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-	txq_stats->tx_bytes += skb->len;
-	txq_stats->tx_tso_frames++;
-	txq_stats->tx_tso_nfrags += nfrags;
+	u64_stats_update_begin(&txq_stats->q_syncp);
+	u64_stats_add(&txq_stats->q.tx_bytes, skb->len);
+	u64_stats_inc(&txq_stats->q.tx_tso_frames);
+	u64_stats_add(&txq_stats->q.tx_tso_nfrags, nfrags);
 	if (set_ic)
-		txq_stats->tx_set_ic_bit++;
-	u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+		u64_stats_inc(&txq_stats->q.tx_set_ic_bit);
+	u64_stats_update_end(&txq_stats->q_syncp);
 
 	if (priv->sarc_type)
 		stmmac_set_desc_sarc(priv, first, priv->sarc_type);
@@ -4435,6 +4439,28 @@ dma_map_err:
 }
 
 /**
+ * stmmac_has_ip_ethertype() - Check if packet has IP ethertype
+ * @skb: socket buffer to check
+ *
+ * Check if a packet has an ethertype that will trigger the IP header checks
+ * and IP/TCP checksum engine of the stmmac core.
+ *
+ * Return: true if the ethertype can trigger the checksum engine, false
+ * otherwise
+ */
+static bool stmmac_has_ip_ethertype(struct sk_buff *skb)
+{
+	int depth = 0;
+	__be16 proto;
+
+	proto = __vlan_get_protocol(skb, eth_header_parse_protocol(skb),
+				    &depth);
+
+	return (depth <= ETH_HLEN) &&
+		(proto == htons(ETH_P_IP) || proto == htons(ETH_P_IPV6));
+}
+
+/**
  *  stmmac_xmit - Tx entry point of the driver
  *  @skb : the socket buffer
  *  @dev : device pointer
@@ -4457,7 +4483,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct stmmac_tx_queue *tx_q;
 	bool has_vlan, set_ic;
 	int entry, first_tx;
-	unsigned long flags;
 	dma_addr_t des;
 
 	tx_q = &priv->dma_conf.tx_queue[queue];
@@ -4498,9 +4523,13 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* DWMAC IPs can be synthesized to support tx coe only for a few tx
 	 * queues. In that case, checksum offloading for those queues that don't
 	 * support tx coe needs to fallback to software checksum calculation.
+	 *
+	 * Packets that won't trigger the COE e.g. most DSA-tagged packets will
+	 * also have to be checksummed in software.
 	 */
 	if (csum_insertion &&
-	    priv->plat->tx_queues_cfg[queue].coe_unsupported) {
+	    (priv->plat->tx_queues_cfg[queue].coe_unsupported ||
+	     !stmmac_has_ip_ethertype(skb))) {
 		if (unlikely(skb_checksum_help(skb)))
 			goto dma_map_err;
 		csum_insertion = !csum_insertion;
@@ -4623,11 +4652,11 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 		netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
 	}
 
-	flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-	txq_stats->tx_bytes += skb->len;
+	u64_stats_update_begin(&txq_stats->q_syncp);
+	u64_stats_add(&txq_stats->q.tx_bytes, skb->len);
 	if (set_ic)
-		txq_stats->tx_set_ic_bit++;
-	u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+		u64_stats_inc(&txq_stats->q.tx_set_ic_bit);
+	u64_stats_update_end(&txq_stats->q_syncp);
 
 	if (priv->sarc_type)
 		stmmac_set_desc_sarc(priv, first, priv->sarc_type);
@@ -4891,12 +4920,11 @@ static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue,
 		set_ic = false;
 
 	if (set_ic) {
-		unsigned long flags;
 		tx_q->tx_count_frames = 0;
 		stmmac_set_tx_ic(priv, tx_desc);
-		flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-		txq_stats->tx_set_ic_bit++;
-		u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+		u64_stats_update_begin(&txq_stats->q_syncp);
+		u64_stats_inc(&txq_stats->q.tx_set_ic_bit);
+		u64_stats_update_end(&txq_stats->q_syncp);
 	}
 
 	stmmac_enable_dma_transmission(priv, priv->ioaddr);
@@ -5046,7 +5074,6 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue,
 	unsigned int len = xdp->data_end - xdp->data;
 	enum pkt_hash_types hash_type;
 	int coe = priv->hw->rx_csum;
-	unsigned long flags;
 	struct sk_buff *skb;
 	u32 hash;
 
@@ -5065,7 +5092,7 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue,
 		stmmac_rx_vlan(priv->dev, skb);
 	skb->protocol = eth_type_trans(skb, priv->dev);
 
-	if (unlikely(!coe))
+	if (unlikely(!coe) || !stmmac_has_ip_ethertype(skb))
 		skb_checksum_none_assert(skb);
 	else
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -5076,10 +5103,10 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue,
 	skb_record_rx_queue(skb, queue);
 	napi_gro_receive(&ch->rxtx_napi, skb);
 
-	flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp);
-	rxq_stats->rx_pkt_n++;
-	rxq_stats->rx_bytes += len;
-	u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags);
+	u64_stats_update_begin(&rxq_stats->napi_syncp);
+	u64_stats_inc(&rxq_stats->napi.rx_pkt_n);
+	u64_stats_add(&rxq_stats->napi.rx_bytes, len);
+	u64_stats_update_end(&rxq_stats->napi_syncp);
 }
 
 static bool stmmac_rx_refill_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
@@ -5161,7 +5188,6 @@ static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue)
 	unsigned int desc_size;
 	struct bpf_prog *prog;
 	bool failure = false;
-	unsigned long flags;
 	int xdp_status = 0;
 	int status = 0;
 
@@ -5316,9 +5342,9 @@ read_again:
 
 	stmmac_finalize_xdp_rx(priv, xdp_status);
 
-	flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp);
-	rxq_stats->rx_pkt_n += count;
-	u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags);
+	u64_stats_update_begin(&rxq_stats->napi_syncp);
+	u64_stats_add(&rxq_stats->napi.rx_pkt_n, count);
+	u64_stats_update_end(&rxq_stats->napi_syncp);
 
 	priv->xstats.rx_dropped += rx_dropped;
 	priv->xstats.rx_errors += rx_errors;
@@ -5356,7 +5382,6 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 	unsigned int desc_size;
 	struct sk_buff *skb = NULL;
 	struct stmmac_xdp_buff ctx;
-	unsigned long flags;
 	int xdp_status = 0;
 	int buf_sz;
 
@@ -5588,7 +5613,7 @@ drain_data:
 
 		skb->protocol = eth_type_trans(skb, priv->dev);
 
-		if (unlikely(!coe))
+		if (unlikely(!coe) || !stmmac_has_ip_ethertype(skb))
 			skb_checksum_none_assert(skb);
 		else
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -5616,11 +5641,11 @@ drain_data:
 
 	stmmac_rx_refill(priv, queue);
 
-	flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp);
-	rxq_stats->rx_packets += rx_packets;
-	rxq_stats->rx_bytes += rx_bytes;
-	rxq_stats->rx_pkt_n += count;
-	u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags);
+	u64_stats_update_begin(&rxq_stats->napi_syncp);
+	u64_stats_add(&rxq_stats->napi.rx_packets, rx_packets);
+	u64_stats_add(&rxq_stats->napi.rx_bytes, rx_bytes);
+	u64_stats_add(&rxq_stats->napi.rx_pkt_n, count);
+	u64_stats_update_end(&rxq_stats->napi_syncp);
 
 	priv->xstats.rx_dropped += rx_dropped;
 	priv->xstats.rx_errors += rx_errors;
@@ -5635,13 +5660,12 @@ static int stmmac_napi_poll_rx(struct napi_struct *napi, int budget)
 	struct stmmac_priv *priv = ch->priv_data;
 	struct stmmac_rxq_stats *rxq_stats;
 	u32 chan = ch->index;
-	unsigned long flags;
 	int work_done;
 
 	rxq_stats = &priv->xstats.rxq_stats[chan];
-	flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp);
-	rxq_stats->napi_poll++;
-	u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags);
+	u64_stats_update_begin(&rxq_stats->napi_syncp);
+	u64_stats_inc(&rxq_stats->napi.poll);
+	u64_stats_update_end(&rxq_stats->napi_syncp);
 
 	work_done = stmmac_rx(priv, budget, chan);
 	if (work_done < budget && napi_complete_done(napi, work_done)) {
@@ -5663,13 +5687,12 @@ static int stmmac_napi_poll_tx(struct napi_struct *napi, int budget)
 	struct stmmac_txq_stats *txq_stats;
 	bool pending_packets = false;
 	u32 chan = ch->index;
-	unsigned long flags;
 	int work_done;
 
 	txq_stats = &priv->xstats.txq_stats[chan];
-	flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-	txq_stats->napi_poll++;
-	u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+	u64_stats_update_begin(&txq_stats->napi_syncp);
+	u64_stats_inc(&txq_stats->napi.poll);
+	u64_stats_update_end(&txq_stats->napi_syncp);
 
 	work_done = stmmac_tx_clean(priv, budget, chan, &pending_packets);
 	work_done = min(work_done, budget);
@@ -5699,17 +5722,16 @@ static int stmmac_napi_poll_rxtx(struct napi_struct *napi, int budget)
 	struct stmmac_rxq_stats *rxq_stats;
 	struct stmmac_txq_stats *txq_stats;
 	u32 chan = ch->index;
-	unsigned long flags;
 
 	rxq_stats = &priv->xstats.rxq_stats[chan];
-	flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp);
-	rxq_stats->napi_poll++;
-	u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags);
+	u64_stats_update_begin(&rxq_stats->napi_syncp);
+	u64_stats_inc(&rxq_stats->napi.poll);
+	u64_stats_update_end(&rxq_stats->napi_syncp);
 
 	txq_stats = &priv->xstats.txq_stats[chan];
-	flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-	txq_stats->napi_poll++;
-	u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+	u64_stats_update_begin(&txq_stats->napi_syncp);
+	u64_stats_inc(&txq_stats->napi.poll);
+	u64_stats_update_end(&txq_stats->napi_syncp);
 
 	tx_done = stmmac_tx_clean(priv, budget, chan, &tx_pending_packets);
 	tx_done = min(tx_done, budget);
@@ -6040,11 +6062,6 @@ static irqreturn_t stmmac_mac_interrupt(int irq, void *dev_id)
 	struct net_device *dev = (struct net_device *)dev_id;
 	struct stmmac_priv *priv = netdev_priv(dev);
 
-	if (unlikely(!dev)) {
-		netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__);
-		return IRQ_NONE;
-	}
-
 	/* Check if adapter is up */
 	if (test_bit(STMMAC_DOWN, &priv->state))
 		return IRQ_HANDLED;
@@ -6060,11 +6077,6 @@ static irqreturn_t stmmac_safety_interrupt(int irq, void *dev_id)
 	struct net_device *dev = (struct net_device *)dev_id;
 	struct stmmac_priv *priv = netdev_priv(dev);
 
-	if (unlikely(!dev)) {
-		netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__);
-		return IRQ_NONE;
-	}
-
 	/* Check if adapter is up */
 	if (test_bit(STMMAC_DOWN, &priv->state))
 		return IRQ_HANDLED;
@@ -6086,11 +6098,6 @@ static irqreturn_t stmmac_msi_intr_tx(int irq, void *data)
 	dma_conf = container_of(tx_q, struct stmmac_dma_conf, tx_queue[chan]);
 	priv = container_of(dma_conf, struct stmmac_priv, dma_conf);
 
-	if (unlikely(!data)) {
-		netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__);
-		return IRQ_NONE;
-	}
-
 	/* Check if adapter is up */
 	if (test_bit(STMMAC_DOWN, &priv->state))
 		return IRQ_HANDLED;
@@ -6117,11 +6124,6 @@ static irqreturn_t stmmac_msi_intr_rx(int irq, void *data)
 	dma_conf = container_of(rx_q, struct stmmac_dma_conf, rx_queue[chan]);
 	priv = container_of(dma_conf, struct stmmac_priv, dma_conf);
 
-	if (unlikely(!data)) {
-		netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__);
-		return IRQ_NONE;
-	}
-
 	/* Check if adapter is up */
 	if (test_bit(STMMAC_DOWN, &priv->state))
 		return IRQ_HANDLED;
@@ -7035,10 +7037,13 @@ static void stmmac_get_stats64(struct net_device *dev, struct rtnl_link_stats64
 		u64 tx_bytes;
 
 		do {
-			start = u64_stats_fetch_begin(&txq_stats->syncp);
-			tx_packets = txq_stats->tx_packets;
-			tx_bytes   = txq_stats->tx_bytes;
-		} while (u64_stats_fetch_retry(&txq_stats->syncp, start));
+			start = u64_stats_fetch_begin(&txq_stats->q_syncp);
+			tx_bytes   = u64_stats_read(&txq_stats->q.tx_bytes);
+		} while (u64_stats_fetch_retry(&txq_stats->q_syncp, start));
+		do {
+			start = u64_stats_fetch_begin(&txq_stats->napi_syncp);
+			tx_packets = u64_stats_read(&txq_stats->napi.tx_packets);
+		} while (u64_stats_fetch_retry(&txq_stats->napi_syncp, start));
 
 		stats->tx_packets += tx_packets;
 		stats->tx_bytes += tx_bytes;
@@ -7050,10 +7055,10 @@ static void stmmac_get_stats64(struct net_device *dev, struct rtnl_link_stats64
 		u64 rx_bytes;
 
 		do {
-			start = u64_stats_fetch_begin(&rxq_stats->syncp);
-			rx_packets = rxq_stats->rx_packets;
-			rx_bytes   = rxq_stats->rx_bytes;
-		} while (u64_stats_fetch_retry(&rxq_stats->syncp, start));
+			start = u64_stats_fetch_begin(&rxq_stats->napi_syncp);
+			rx_packets = u64_stats_read(&rxq_stats->napi.rx_packets);
+			rx_bytes   = u64_stats_read(&rxq_stats->napi.rx_bytes);
+		} while (u64_stats_fetch_retry(&rxq_stats->napi_syncp, start));
 
 		stats->rx_packets += rx_packets;
 		stats->rx_bytes += rx_bytes;
@@ -7447,9 +7452,16 @@ int stmmac_dvr_probe(struct device *device,
 	priv->dev = ndev;
 
 	for (i = 0; i < MTL_MAX_RX_QUEUES; i++)
-		u64_stats_init(&priv->xstats.rxq_stats[i].syncp);
-	for (i = 0; i < MTL_MAX_TX_QUEUES; i++)
-		u64_stats_init(&priv->xstats.txq_stats[i].syncp);
+		u64_stats_init(&priv->xstats.rxq_stats[i].napi_syncp);
+	for (i = 0; i < MTL_MAX_TX_QUEUES; i++) {
+		u64_stats_init(&priv->xstats.txq_stats[i].q_syncp);
+		u64_stats_init(&priv->xstats.txq_stats[i].napi_syncp);
+	}
+
+	priv->xstats.pcpu_stats =
+		devm_netdev_alloc_pcpu_stats(device, struct stmmac_pcpu_stats);
+	if (!priv->xstats.pcpu_stats)
+		return -ENOMEM;
 
 	stmmac_set_ethtool_ops(ndev);
 	priv->pause = pause;
@@ -7515,6 +7527,9 @@ int stmmac_dvr_probe(struct device *device,
 		dev_err(priv->device, "unable to bring out of ahb reset: %pe\n",
 			ERR_PTR(ret));
 
+	/* Wait a bit for the reset to take effect */
+	udelay(10);
+
 	/* Init MAC and get the capabilities */
 	ret = stmmac_hw_init(priv);
 	if (ret)
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index be01450c20dc..1530d13984d4 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -189,6 +189,7 @@ config TI_ICSSG_PRUETH
 	select TI_K3_CPPI_DESC_POOL
 	depends on PRU_REMOTEPROC
 	depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER
+	depends on PTP_1588_CLOCK_OPTIONAL
 	help
 	  Support dual Gigabit Ethernet ports over the ICSSG PRU Subsystem.
 	  This subsystem is available starting with the AM65 platform.
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index faa0561e988e..2939a21ca74f 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -56,7 +56,7 @@
 #define AM65_CPSW_MAX_PORTS	8
 
 #define AM65_CPSW_MIN_PACKET_SIZE	VLAN_ETH_ZLEN
-#define AM65_CPSW_MAX_PACKET_SIZE	(VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)
+#define AM65_CPSW_MAX_PACKET_SIZE	2024
 
 #define AM65_CPSW_REG_CTL		0x004
 #define AM65_CPSW_REG_STAT_PORT_EN	0x014
@@ -294,7 +294,7 @@ static void am65_cpsw_nuss_ndo_host_tx_timeout(struct net_device *ndev,
 		   txqueue,
 		   netif_tx_queue_stopped(netif_txq),
 		   jiffies_to_msecs(jiffies - trans_start),
-		   dql_avail(&netif_txq->dql),
+		   netdev_queue_dql_avail(netif_txq),
 		   k3_cppi_desc_pool_avail(tx_chn->desc_pool));
 
 	if (netif_tx_queue_stopped(netif_txq)) {
@@ -2244,7 +2244,8 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx)
 	eth_hw_addr_set(port->ndev, port->slave.mac_addr);
 
 	port->ndev->min_mtu = AM65_CPSW_MIN_PACKET_SIZE;
-	port->ndev->max_mtu = AM65_CPSW_MAX_PACKET_SIZE;
+	port->ndev->max_mtu = AM65_CPSW_MAX_PACKET_SIZE -
+			      (VLAN_ETH_HLEN + ETH_FCS_LEN);
 	port->ndev->hw_features = NETIF_F_SG |
 				  NETIF_F_RXCSUM |
 				  NETIF_F_HW_CSUM |
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index ea85c6dd5484..c0a5abd8d9a8 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -631,6 +631,8 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
 		}
 	}
 
+	phy->mac_managed_pm = true;
+
 	slave->phy = phy;
 
 	phy_attached_info(slave->phy);
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index 498c50c6d1a7..087dcb67505a 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -773,6 +773,9 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
 			slave->slave_num);
 		return;
 	}
+
+	phy->mac_managed_pm = true;
+
 	slave->phy = phy;
 
 	phy_attached_info(slave->phy);
diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index bcccf43d368b..dbbea9146040 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -638,6 +638,16 @@ static void cpts_calc_mult_shift(struct cpts *cpts)
 		 freq, cpts->cc.mult, cpts->cc.shift, (ns - NSEC_PER_SEC));
 }
 
+static void cpts_clk_unregister(void *clk)
+{
+	clk_hw_unregister_mux(clk);
+}
+
+static void cpts_clk_del_provider(void *np)
+{
+	of_clk_del_provider(np);
+}
+
 static int cpts_of_mux_clk_setup(struct cpts *cpts, struct device_node *node)
 {
 	struct device_node *refclk_np;
@@ -687,9 +697,7 @@ static int cpts_of_mux_clk_setup(struct cpts *cpts, struct device_node *node)
 		goto mux_fail;
 	}
 
-	ret = devm_add_action_or_reset(cpts->dev,
-				       (void(*)(void *))clk_hw_unregister_mux,
-				       clk_hw);
+	ret = devm_add_action_or_reset(cpts->dev, cpts_clk_unregister, clk_hw);
 	if (ret) {
 		dev_err(cpts->dev, "add clkmux unreg action %d", ret);
 		goto mux_fail;
@@ -699,8 +707,7 @@ static int cpts_of_mux_clk_setup(struct cpts *cpts, struct device_node *node)
 	if (ret)
 		goto mux_fail;
 
-	ret = devm_add_action_or_reset(cpts->dev,
-				       (void(*)(void *))of_clk_del_provider,
+	ret = devm_add_action_or_reset(cpts->dev, cpts_clk_del_provider,
 				       refclk_np);
 	if (ret) {
 		dev_err(cpts->dev, "add clkmux provider unreg action %d", ret);
diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
index d5b75af163d3..c1b0d35c8d05 100644
--- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c
+++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
@@ -384,18 +384,18 @@ static int gelic_descr_prepare_rx(struct gelic_card *card,
 	if (gelic_descr_get_status(descr) !=  GELIC_DESCR_DMA_NOT_IN_USE)
 		dev_info(ctodev(card), "%s: ERROR status\n", __func__);
 
-	descr->skb = netdev_alloc_skb(*card->netdev, rx_skb_size);
-	if (!descr->skb) {
-		descr->hw_regs.payload.dev_addr = 0; /* tell DMAC don't touch memory */
-		return -ENOMEM;
-	}
 	descr->hw_regs.dmac_cmd_status = 0;
 	descr->hw_regs.result_size = 0;
 	descr->hw_regs.valid_size = 0;
 	descr->hw_regs.data_error = 0;
 	descr->hw_regs.payload.dev_addr = 0;
 	descr->hw_regs.payload.size = 0;
-	descr->skb = NULL;
+
+	descr->skb = netdev_alloc_skb(*card->netdev, rx_skb_size);
+	if (!descr->skb) {
+		descr->hw_regs.payload.dev_addr = 0; /* tell DMAC don't touch memory */
+		return -ENOMEM;
+	}
 
 	offset = ((unsigned long)descr->skb->data) &
 		(GELIC_NET_RXBUF_ALIGN - 1);
diff --git a/drivers/net/ethernet/wangxun/Kconfig b/drivers/net/ethernet/wangxun/Kconfig
index 23cd610bd376..85cdbdd44fec 100644
--- a/drivers/net/ethernet/wangxun/Kconfig
+++ b/drivers/net/ethernet/wangxun/Kconfig
@@ -26,7 +26,7 @@ config NGBE
 	tristate "Wangxun(R) GbE PCI Express adapters support"
 	depends on PCI
 	select LIBWX
-	select PHYLIB
+	select PHYLINK
 	help
 	  This driver supports Wangxun(R) GbE PCI Express family of
 	  adapters.
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 23355cc408fd..8706223a6e5a 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -2769,4 +2769,5 @@ void wx_set_ring(struct wx *wx, u32 new_tx_count,
 }
 EXPORT_SYMBOL(wx_set_ring);
 
+MODULE_DESCRIPTION("Common library for Wangxun(R) Ethernet drivers.");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/fddi/skfp/skfddi.c b/drivers/net/fddi/skfp/skfddi.c
index 2b6a607ac0b7..a273362c9e70 100644
--- a/drivers/net/fddi/skfp/skfddi.c
+++ b/drivers/net/fddi/skfp/skfddi.c
@@ -153,6 +153,7 @@ static const struct pci_device_id skfddi_pci_tbl[] = {
 	{ }			/* Terminating entry */
 };
 MODULE_DEVICE_TABLE(pci, skfddi_pci_tbl);
+MODULE_DESCRIPTION("SysKonnect FDDI PCI driver");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Mirko Lindner <mlindner@syskonnect.de>");
 
diff --git a/drivers/net/fjes/fjes_hw.c b/drivers/net/fjes/fjes_hw.c
index 704e949484d0..b9b5554ea862 100644
--- a/drivers/net/fjes/fjes_hw.c
+++ b/drivers/net/fjes/fjes_hw.c
@@ -221,21 +221,25 @@ static int fjes_hw_setup(struct fjes_hw *hw)
 
 	mem_size = FJES_DEV_REQ_BUF_SIZE(hw->max_epid);
 	hw->hw_info.req_buf = kzalloc(mem_size, GFP_KERNEL);
-	if (!(hw->hw_info.req_buf))
-		return -ENOMEM;
+	if (!(hw->hw_info.req_buf)) {
+		result = -ENOMEM;
+		goto free_ep_info;
+	}
 
 	hw->hw_info.req_buf_size = mem_size;
 
 	mem_size = FJES_DEV_RES_BUF_SIZE(hw->max_epid);
 	hw->hw_info.res_buf = kzalloc(mem_size, GFP_KERNEL);
-	if (!(hw->hw_info.res_buf))
-		return -ENOMEM;
+	if (!(hw->hw_info.res_buf)) {
+		result = -ENOMEM;
+		goto free_req_buf;
+	}
 
 	hw->hw_info.res_buf_size = mem_size;
 
 	result = fjes_hw_alloc_shared_status_region(hw);
 	if (result)
-		return result;
+		goto free_res_buf;
 
 	hw->hw_info.buffer_share_bit = 0;
 	hw->hw_info.buffer_unshare_reserve_bit = 0;
@@ -246,11 +250,11 @@ static int fjes_hw_setup(struct fjes_hw *hw)
 
 			result = fjes_hw_alloc_epbuf(&buf_pair->tx);
 			if (result)
-				return result;
+				goto free_epbuf;
 
 			result = fjes_hw_alloc_epbuf(&buf_pair->rx);
 			if (result)
-				return result;
+				goto free_epbuf;
 
 			spin_lock_irqsave(&hw->rx_status_lock, flags);
 			fjes_hw_setup_epbuf(&buf_pair->tx, mac,
@@ -273,6 +277,25 @@ static int fjes_hw_setup(struct fjes_hw *hw)
 	fjes_hw_init_command_registers(hw, &param);
 
 	return 0;
+
+free_epbuf:
+	for (epidx = 0; epidx < hw->max_epid ; epidx++) {
+		if (epidx == hw->my_epid)
+			continue;
+		fjes_hw_free_epbuf(&hw->ep_shm_info[epidx].tx);
+		fjes_hw_free_epbuf(&hw->ep_shm_info[epidx].rx);
+	}
+	fjes_hw_free_shared_status_region(hw);
+free_res_buf:
+	kfree(hw->hw_info.res_buf);
+	hw->hw_info.res_buf = NULL;
+free_req_buf:
+	kfree(hw->hw_info.req_buf);
+	hw->hw_info.req_buf = NULL;
+free_ep_info:
+	kfree(hw->ep_shm_info);
+	hw->ep_shm_info = NULL;
+	return result;
 }
 
 static void fjes_hw_cleanup(struct fjes_hw *hw)
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 32c51c244153..c4ed36c71897 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -221,7 +221,7 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs,
 	struct genevehdr *gnvh = geneve_hdr(skb);
 	struct metadata_dst *tun_dst = NULL;
 	unsigned int len;
-	int err = 0;
+	int nh, err = 0;
 	void *oiph;
 
 	if (ip_tunnel_collect_metadata() || gs->collect_md) {
@@ -272,9 +272,23 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs,
 		skb->pkt_type = PACKET_HOST;
 	}
 
-	oiph = skb_network_header(skb);
+	/* Save offset of outer header relative to skb->head,
+	 * because we are going to reset the network header to the inner header
+	 * and might change skb->head.
+	 */
+	nh = skb_network_header(skb) - skb->head;
+
 	skb_reset_network_header(skb);
 
+	if (!pskb_inet_may_pull(skb)) {
+		DEV_STATS_INC(geneve->dev, rx_length_errors);
+		DEV_STATS_INC(geneve->dev, rx_errors);
+		goto drop;
+	}
+
+	/* Get the outer header. */
+	oiph = skb->head + nh;
+
 	if (geneve_get_sk_family(gs) == AF_INET)
 		err = IP_ECN_decapsulate(oiph, skb);
 #if IS_ENABLED(CONFIG_IPV6)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index b1919278e931..2b5357d94ff5 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -1903,26 +1903,26 @@ static int __init gtp_init(void)
 
 	get_random_bytes(&gtp_h_initval, sizeof(gtp_h_initval));
 
-	err = rtnl_link_register(&gtp_link_ops);
+	err = register_pernet_subsys(&gtp_net_ops);
 	if (err < 0)
 		goto error_out;
 
-	err = genl_register_family(&gtp_genl_family);
+	err = rtnl_link_register(&gtp_link_ops);
 	if (err < 0)
-		goto unreg_rtnl_link;
+		goto unreg_pernet_subsys;
 
-	err = register_pernet_subsys(&gtp_net_ops);
+	err = genl_register_family(&gtp_genl_family);
 	if (err < 0)
-		goto unreg_genl_family;
+		goto unreg_rtnl_link;
 
 	pr_info("GTP module loaded (pdp ctx size %zd bytes)\n",
 		sizeof(struct pdp_ctx));
 	return 0;
 
-unreg_genl_family:
-	genl_unregister_family(&gtp_genl_family);
 unreg_rtnl_link:
 	rtnl_link_unregister(&gtp_link_ops);
+unreg_pernet_subsys:
+	unregister_pernet_subsys(&gtp_net_ops);
 error_out:
 	pr_err("error loading GTP module loaded\n");
 	return err;
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 1dafa44155d0..a6fcbda64ecc 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -708,7 +708,10 @@ void netvsc_device_remove(struct hv_device *device)
 	/* Disable NAPI and disassociate its context from the device. */
 	for (i = 0; i < net_device->num_chn; i++) {
 		/* See also vmbus_reset_channel_cb(). */
-		napi_disable(&net_device->chan_table[i].napi);
+		/* only disable enabled NAPI channel */
+		if (i < ndev->real_num_rx_queues)
+			napi_disable(&net_device->chan_table[i].napi);
+
 		netif_napi_del(&net_device->chan_table[i].napi);
 	}
 
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 4406427d4617..11831a1c9762 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -42,9 +42,13 @@
 #define LINKCHANGE_INT (2 * HZ)
 #define VF_TAKEOVER_INT (HZ / 10)
 
+/* Macros to define the context of vf registration */
+#define VF_REG_IN_PROBE		1
+#define VF_REG_IN_NOTIFIER	2
+
 static unsigned int ring_size __ro_after_init = 128;
 module_param(ring_size, uint, 0444);
-MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)");
+MODULE_PARM_DESC(ring_size, "Ring buffer size (# of 4K pages)");
 unsigned int netvsc_ring_bytes __ro_after_init;
 
 static const u32 default_msg = NETIF_MSG_DRV | NETIF_MSG_PROBE |
@@ -2185,7 +2189,7 @@ static rx_handler_result_t netvsc_vf_handle_frame(struct sk_buff **pskb)
 }
 
 static int netvsc_vf_join(struct net_device *vf_netdev,
-			  struct net_device *ndev)
+			  struct net_device *ndev, int context)
 {
 	struct net_device_context *ndev_ctx = netdev_priv(ndev);
 	int ret;
@@ -2208,7 +2212,11 @@ static int netvsc_vf_join(struct net_device *vf_netdev,
 		goto upper_link_failed;
 	}
 
-	schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
+	/* If this registration is called from probe context vf_takeover
+	 * is taken care of later in probe itself.
+	 */
+	if (context == VF_REG_IN_NOTIFIER)
+		schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
 
 	call_netdevice_notifiers(NETDEV_JOIN, vf_netdev);
 
@@ -2346,7 +2354,7 @@ static int netvsc_prepare_bonding(struct net_device *vf_netdev)
 	return NOTIFY_DONE;
 }
 
-static int netvsc_register_vf(struct net_device *vf_netdev)
+static int netvsc_register_vf(struct net_device *vf_netdev, int context)
 {
 	struct net_device_context *net_device_ctx;
 	struct netvsc_device *netvsc_dev;
@@ -2386,7 +2394,7 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
 
 	netdev_info(ndev, "VF registering: %s\n", vf_netdev->name);
 
-	if (netvsc_vf_join(vf_netdev, ndev) != 0)
+	if (netvsc_vf_join(vf_netdev, ndev, context) != 0)
 		return NOTIFY_DONE;
 
 	dev_hold(vf_netdev);
@@ -2484,10 +2492,31 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev)
 	return NOTIFY_OK;
 }
 
+static int check_dev_is_matching_vf(struct net_device *event_ndev)
+{
+	/* Skip NetVSC interfaces */
+	if (event_ndev->netdev_ops == &device_ops)
+		return -ENODEV;
+
+	/* Avoid non-Ethernet type devices */
+	if (event_ndev->type != ARPHRD_ETHER)
+		return -ENODEV;
+
+	/* Avoid Vlan dev with same MAC registering as VF */
+	if (is_vlan_dev(event_ndev))
+		return -ENODEV;
+
+	/* Avoid Bonding master dev with same MAC registering as VF */
+	if (netif_is_bond_master(event_ndev))
+		return -ENODEV;
+
+	return 0;
+}
+
 static int netvsc_probe(struct hv_device *dev,
 			const struct hv_vmbus_device_id *dev_id)
 {
-	struct net_device *net = NULL;
+	struct net_device *net = NULL, *vf_netdev;
 	struct net_device_context *net_device_ctx;
 	struct netvsc_device_info *device_info = NULL;
 	struct netvsc_device *nvdev;
@@ -2599,6 +2628,30 @@ static int netvsc_probe(struct hv_device *dev,
 	}
 
 	list_add(&net_device_ctx->list, &netvsc_dev_list);
+
+	/* When the hv_netvsc driver is unloaded and reloaded, the
+	 * NET_DEVICE_REGISTER for the vf device is replayed before probe
+	 * is complete. This is because register_netdevice_notifier() gets
+	 * registered before vmbus_driver_register() so that callback func
+	 * is set before probe and we don't miss events like NETDEV_POST_INIT
+	 * So, in this section we try to register the matching vf device that
+	 * is present as a netdevice, knowing that its register call is not
+	 * processed in the netvsc_netdev_notifier(as probing is progress and
+	 * get_netvsc_byslot fails).
+	 */
+	for_each_netdev(dev_net(net), vf_netdev) {
+		ret = check_dev_is_matching_vf(vf_netdev);
+		if (ret != 0)
+			continue;
+
+		if (net != get_netvsc_byslot(vf_netdev))
+			continue;
+
+		netvsc_prepare_bonding(vf_netdev);
+		netvsc_register_vf(vf_netdev, VF_REG_IN_PROBE);
+		__netvsc_vf_setup(net, vf_netdev);
+		break;
+	}
 	rtnl_unlock();
 
 	netvsc_devinfo_put(device_info);
@@ -2754,28 +2807,17 @@ static int netvsc_netdev_event(struct notifier_block *this,
 			       unsigned long event, void *ptr)
 {
 	struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
+	int ret = 0;
 
-	/* Skip our own events */
-	if (event_dev->netdev_ops == &device_ops)
-		return NOTIFY_DONE;
-
-	/* Avoid non-Ethernet type devices */
-	if (event_dev->type != ARPHRD_ETHER)
-		return NOTIFY_DONE;
-
-	/* Avoid Vlan dev with same MAC registering as VF */
-	if (is_vlan_dev(event_dev))
-		return NOTIFY_DONE;
-
-	/* Avoid Bonding master dev with same MAC registering as VF */
-	if (netif_is_bond_master(event_dev))
+	ret = check_dev_is_matching_vf(event_dev);
+	if (ret != 0)
 		return NOTIFY_DONE;
 
 	switch (event) {
 	case NETDEV_POST_INIT:
 		return netvsc_prepare_bonding(event_dev);
 	case NETDEV_REGISTER:
-		return netvsc_register_vf(event_dev);
+		return netvsc_register_vf(event_dev, VF_REG_IN_NOTIFIER);
 	case NETDEV_UNREGISTER:
 		return netvsc_unregister_vf(event_dev);
 	case NETDEV_UP:
@@ -2807,7 +2849,7 @@ static int __init netvsc_drv_init(void)
 		pr_info("Increased ring_size to %u (min allowed)\n",
 			ring_size);
 	}
-	netvsc_ring_bytes = ring_size * PAGE_SIZE;
+	netvsc_ring_bytes = VMBUS_RING_SIZE(ring_size * 4096);
 
 	register_netdevice_notifier(&netvsc_netdev_notifier);
 
diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c
index 35e55f198e05..2930141d7dd2 100644
--- a/drivers/net/ieee802154/fakelb.c
+++ b/drivers/net/ieee802154/fakelb.c
@@ -259,4 +259,5 @@ static __exit void fake_remove_module(void)
 
 module_init(fakelb_init_module);
 module_exit(fake_remove_module);
+MODULE_DESCRIPTION("IEEE 802.15.4 loopback driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ipa/ipa_interrupt.c b/drivers/net/ipa/ipa_interrupt.c
index 4bc05948f772..a78c692f2d3c 100644
--- a/drivers/net/ipa/ipa_interrupt.c
+++ b/drivers/net/ipa/ipa_interrupt.c
@@ -212,7 +212,7 @@ void ipa_interrupt_suspend_clear_all(struct ipa_interrupt *interrupt)
 	u32 unit_count;
 	u32 unit;
 
-	unit_count = roundup(ipa->endpoint_count, 32);
+	unit_count = DIV_ROUND_UP(ipa->endpoint_count, 32);
 	for (unit = 0; unit < unit_count; unit++) {
 		const struct reg *reg;
 		u32 val;
diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c
index 60944a4beada..1afc4c47be73 100644
--- a/drivers/net/ipvlan/ipvtap.c
+++ b/drivers/net/ipvlan/ipvtap.c
@@ -237,4 +237,5 @@ static void __exit ipvtap_exit(void)
 module_exit(ipvtap_exit);
 MODULE_ALIAS_RTNL_LINK("ipvtap");
 MODULE_AUTHOR("Sainath Grandhi <sainath.grandhi@intel.com>");
+MODULE_DESCRIPTION("IP-VLAN based tap driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index e34816638569..7f5426285c61 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -607,11 +607,26 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 		return ERR_PTR(-EINVAL);
 	}
 
-	ret = skb_ensure_writable_head_tail(skb, dev);
-	if (unlikely(ret < 0)) {
-		macsec_txsa_put(tx_sa);
-		kfree_skb(skb);
-		return ERR_PTR(ret);
+	if (unlikely(skb_headroom(skb) < MACSEC_NEEDED_HEADROOM ||
+		     skb_tailroom(skb) < MACSEC_NEEDED_TAILROOM)) {
+		struct sk_buff *nskb = skb_copy_expand(skb,
+						       MACSEC_NEEDED_HEADROOM,
+						       MACSEC_NEEDED_TAILROOM,
+						       GFP_ATOMIC);
+		if (likely(nskb)) {
+			consume_skb(skb);
+			skb = nskb;
+		} else {
+			macsec_txsa_put(tx_sa);
+			kfree_skb(skb);
+			return ERR_PTR(-ENOMEM);
+		}
+	} else {
+		skb = skb_unshare(skb, GFP_ATOMIC);
+		if (!skb) {
+			macsec_txsa_put(tx_sa);
+			return ERR_PTR(-ENOMEM);
+		}
 	}
 
 	unprotected_len = skb->len;
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index b4d3b9cde8bd..92a7a36b93ac 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -835,14 +835,14 @@ static void nsim_dev_trap_report_work(struct work_struct *work)
 				      trap_report_dw.work);
 	nsim_dev = nsim_trap_data->nsim_dev;
 
-	/* For each running port and enabled packet trap, generate a UDP
-	 * packet with a random 5-tuple and report it.
-	 */
 	if (!devl_trylock(priv_to_devlink(nsim_dev))) {
-		schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, 0);
+		schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, 1);
 		return;
 	}
 
+	/* For each running port and enabled packet trap, generate a UDP
+	 * packet with a random 5-tuple and report it.
+	 */
 	list_for_each_entry(nsim_dev_port, &nsim_dev->port_list, list) {
 		if (!netif_running(nsim_dev_port->ns->netdev))
 			continue;
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index aecaf5f44374..77e8250282a5 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -369,6 +369,12 @@ static int nsim_init_netdevsim_vf(struct netdevsim *ns)
 	return err;
 }
 
+static void nsim_exit_netdevsim(struct netdevsim *ns)
+{
+	nsim_udp_tunnels_info_destroy(ns->netdev);
+	mock_phc_destroy(ns->phc);
+}
+
 struct netdevsim *
 nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port)
 {
@@ -417,8 +423,7 @@ void nsim_destroy(struct netdevsim *ns)
 	}
 	rtnl_unlock();
 	if (nsim_dev_port_is_pf(ns->nsim_dev_port))
-		nsim_udp_tunnels_info_destroy(dev);
-	mock_phc_destroy(ns->phc);
+		nsim_exit_netdevsim(ns);
 	free_netdev(dev);
 }
 
diff --git a/drivers/net/phy/mdio_devres.c b/drivers/net/phy/mdio_devres.c
index 69b829e6ab35..7fd3377dbd79 100644
--- a/drivers/net/phy/mdio_devres.c
+++ b/drivers/net/phy/mdio_devres.c
@@ -131,4 +131,5 @@ int __devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio,
 EXPORT_SYMBOL(__devm_of_mdiobus_register);
 #endif /* CONFIG_OF_MDIO */
 
+MODULE_DESCRIPTION("Network MDIO bus devres helpers");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/phy/mediatek-ge-soc.c b/drivers/net/phy/mediatek-ge-soc.c
index 8a20d9889f10..0f3a1538a8b8 100644
--- a/drivers/net/phy/mediatek-ge-soc.c
+++ b/drivers/net/phy/mediatek-ge-soc.c
@@ -489,7 +489,7 @@ static int tx_r50_fill_result(struct phy_device *phydev, u16 tx_r50_cal_val,
 	u16 reg, val;
 
 	if (phydev->drv->phy_id == MTK_GPHY_ID_MT7988)
-		bias = -2;
+		bias = -1;
 
 	val = clamp_val(bias + tx_r50_cal_val, 0, 63);
 
@@ -705,6 +705,11 @@ restore:
 static void mt798x_phy_common_finetune(struct phy_device *phydev)
 {
 	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
+	/* SlvDSPreadyTime = 24, MasDSPreadyTime = 24 */
+	__phy_write(phydev, 0x11, 0xc71);
+	__phy_write(phydev, 0x12, 0xc);
+	__phy_write(phydev, 0x10, 0x8fae);
+
 	/* EnabRandUpdTrig = 1 */
 	__phy_write(phydev, 0x11, 0x2f00);
 	__phy_write(phydev, 0x12, 0xe);
@@ -715,15 +720,56 @@ static void mt798x_phy_common_finetune(struct phy_device *phydev)
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x83aa);
 
-	/* TrFreeze = 0 */
+	/* FfeUpdGainForce = 1(Enable), FfeUpdGainForceVal = 4 */
+	__phy_write(phydev, 0x11, 0x240);
+	__phy_write(phydev, 0x12, 0x0);
+	__phy_write(phydev, 0x10, 0x9680);
+
+	/* TrFreeze = 0 (mt7988 default) */
 	__phy_write(phydev, 0x11, 0x0);
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x9686);
 
+	/* SSTrKp100 = 5 */
+	/* SSTrKf100 = 6 */
+	/* SSTrKp1000Mas = 5 */
+	/* SSTrKf1000Mas = 6 */
 	/* SSTrKp1000Slv = 5 */
+	/* SSTrKf1000Slv = 6 */
 	__phy_write(phydev, 0x11, 0xbaef);
 	__phy_write(phydev, 0x12, 0x2e);
 	__phy_write(phydev, 0x10, 0x968c);
+	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
+}
+
+static void mt7981_phy_finetune(struct phy_device *phydev)
+{
+	u16 val[8] = { 0x01ce, 0x01c1,
+		       0x020f, 0x0202,
+		       0x03d0, 0x03c0,
+		       0x0013, 0x0005 };
+	int i, k;
+
+	/* 100M eye finetune:
+	 * Keep middle level of TX MLT3 shapper as default.
+	 * Only change TX MLT3 overshoot level here.
+	 */
+	for (k = 0, i = 1; i < 12; i++) {
+		if (i % 3 == 0)
+			continue;
+		phy_write_mmd(phydev, MDIO_MMD_VEND1, i, val[k++]);
+	}
+
+	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
+	/* ResetSyncOffset = 6 */
+	__phy_write(phydev, 0x11, 0x600);
+	__phy_write(phydev, 0x12, 0x0);
+	__phy_write(phydev, 0x10, 0x8fc0);
+
+	/* VgaDecRate = 1 */
+	__phy_write(phydev, 0x11, 0x4c2a);
+	__phy_write(phydev, 0x12, 0x3e);
+	__phy_write(phydev, 0x10, 0x8fa4);
 
 	/* MrvlTrFix100Kp = 3, MrvlTrFix100Kf = 2,
 	 * MrvlTrFix1000Kp = 3, MrvlTrFix1000Kf = 2
@@ -738,7 +784,7 @@ static void mt798x_phy_common_finetune(struct phy_device *phydev)
 	__phy_write(phydev, 0x10, 0x8ec0);
 	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
 
-	/* TR_OPEN_LOOP_EN = 1, lpf_x_average = 9*/
+	/* TR_OPEN_LOOP_EN = 1, lpf_x_average = 9 */
 	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG234,
 		       MTK_PHY_TR_OPEN_LOOP_EN_MASK | MTK_PHY_LPF_X_AVERAGE_MASK,
 		       BIT(0) | FIELD_PREP(MTK_PHY_LPF_X_AVERAGE_MASK, 0x9));
@@ -771,48 +817,6 @@ static void mt798x_phy_common_finetune(struct phy_device *phydev)
 	phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_LDO_OUTPUT_V, 0x2222);
 }
 
-static void mt7981_phy_finetune(struct phy_device *phydev)
-{
-	u16 val[8] = { 0x01ce, 0x01c1,
-		       0x020f, 0x0202,
-		       0x03d0, 0x03c0,
-		       0x0013, 0x0005 };
-	int i, k;
-
-	/* 100M eye finetune:
-	 * Keep middle level of TX MLT3 shapper as default.
-	 * Only change TX MLT3 overshoot level here.
-	 */
-	for (k = 0, i = 1; i < 12; i++) {
-		if (i % 3 == 0)
-			continue;
-		phy_write_mmd(phydev, MDIO_MMD_VEND1, i, val[k++]);
-	}
-
-	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
-	/* SlvDSPreadyTime = 24, MasDSPreadyTime = 24 */
-	__phy_write(phydev, 0x11, 0xc71);
-	__phy_write(phydev, 0x12, 0xc);
-	__phy_write(phydev, 0x10, 0x8fae);
-
-	/* ResetSyncOffset = 6 */
-	__phy_write(phydev, 0x11, 0x600);
-	__phy_write(phydev, 0x12, 0x0);
-	__phy_write(phydev, 0x10, 0x8fc0);
-
-	/* VgaDecRate = 1 */
-	__phy_write(phydev, 0x11, 0x4c2a);
-	__phy_write(phydev, 0x12, 0x3e);
-	__phy_write(phydev, 0x10, 0x8fa4);
-
-	/* FfeUpdGainForce = 4 */
-	__phy_write(phydev, 0x11, 0x240);
-	__phy_write(phydev, 0x12, 0x0);
-	__phy_write(phydev, 0x10, 0x9680);
-
-	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
-}
-
 static void mt7988_phy_finetune(struct phy_device *phydev)
 {
 	u16 val[12] = { 0x0187, 0x01cd, 0x01c8, 0x0182,
@@ -827,17 +831,7 @@ static void mt7988_phy_finetune(struct phy_device *phydev)
 	/* TCT finetune */
 	phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_TX_FILTER, 0x5);
 
-	/* Disable TX power saving */
-	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RXADC_CTRL_RG7,
-		       MTK_PHY_DA_AD_BUF_BIAS_LP_MASK, 0x3 << 8);
-
 	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
-
-	/* SlvDSPreadyTime = 24, MasDSPreadyTime = 12 */
-	__phy_write(phydev, 0x11, 0x671);
-	__phy_write(phydev, 0x12, 0xc);
-	__phy_write(phydev, 0x10, 0x8fae);
-
 	/* ResetSyncOffset = 5 */
 	__phy_write(phydev, 0x11, 0x500);
 	__phy_write(phydev, 0x12, 0x0);
@@ -845,13 +839,27 @@ static void mt7988_phy_finetune(struct phy_device *phydev)
 
 	/* VgaDecRate is 1 at default on mt7988 */
 
-	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
+	/* MrvlTrFix100Kp = 6, MrvlTrFix100Kf = 7,
+	 * MrvlTrFix1000Kp = 6, MrvlTrFix1000Kf = 7
+	 */
+	__phy_write(phydev, 0x11, 0xb90a);
+	__phy_write(phydev, 0x12, 0x6f);
+	__phy_write(phydev, 0x10, 0x8f82);
+
+	/* RemAckCntLimitCtrl = 1 */
+	__phy_write(phydev, 0x11, 0xfbba);
+	__phy_write(phydev, 0x12, 0xc3);
+	__phy_write(phydev, 0x10, 0x87f8);
 
-	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_2A30);
-	/* TxClkOffset = 2 */
-	__phy_modify(phydev, MTK_PHY_ANARG_RG, MTK_PHY_TCLKOFFSET_MASK,
-		     FIELD_PREP(MTK_PHY_TCLKOFFSET_MASK, 0x2));
 	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
+
+	/* TR_OPEN_LOOP_EN = 1, lpf_x_average = 10 */
+	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG234,
+		       MTK_PHY_TR_OPEN_LOOP_EN_MASK | MTK_PHY_LPF_X_AVERAGE_MASK,
+		       BIT(0) | FIELD_PREP(MTK_PHY_LPF_X_AVERAGE_MASK, 0xa));
+
+	/* rg_tr_lpf_cnt_val = 1023 */
+	phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_LPF_CNT_VAL, 0x3ff);
 }
 
 static void mt798x_phy_eee(struct phy_device *phydev)
@@ -884,11 +892,11 @@ static void mt798x_phy_eee(struct phy_device *phydev)
 		       MTK_PHY_LPI_SLV_SEND_TX_EN,
 		       FIELD_PREP(MTK_PHY_LPI_SLV_SEND_TX_TIMER_MASK, 0x120));
 
-	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG239,
-		       MTK_PHY_LPI_SEND_LOC_TIMER_MASK |
-		       MTK_PHY_LPI_TXPCS_LOC_RCV,
-		       FIELD_PREP(MTK_PHY_LPI_SEND_LOC_TIMER_MASK, 0x117));
+	/* Keep MTK_PHY_LPI_SEND_LOC_TIMER as 375 */
+	phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG239,
+			   MTK_PHY_LPI_TXPCS_LOC_RCV);
 
+	/* This also fixes some IoT issues, such as CH340 */
 	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG2C7,
 		       MTK_PHY_MAX_GAIN_MASK | MTK_PHY_MIN_GAIN_MASK,
 		       FIELD_PREP(MTK_PHY_MAX_GAIN_MASK, 0x8) |
@@ -922,7 +930,7 @@ static void mt798x_phy_eee(struct phy_device *phydev)
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x9690);
 
-	/* REG_EEE_st2TrKf1000 = 3 */
+	/* REG_EEE_st2TrKf1000 = 2 */
 	__phy_write(phydev, 0x11, 0x114f);
 	__phy_write(phydev, 0x12, 0x2);
 	__phy_write(phydev, 0x10, 0x969a);
@@ -947,7 +955,7 @@ static void mt798x_phy_eee(struct phy_device *phydev)
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x96b8);
 
-	/* REGEEE_wake_slv_tr_wait_dfesigdet_en = 1 */
+	/* REGEEE_wake_slv_tr_wait_dfesigdet_en = 0 */
 	__phy_write(phydev, 0x11, 0x1463);
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x96ca);
@@ -1459,6 +1467,13 @@ static int mt7988_phy_probe(struct phy_device *phydev)
 	if (err)
 		return err;
 
+	/* Disable TX power saving at probing to:
+	 * 1. Meet common mode compliance test criteria
+	 * 2. Make sure that TX-VCM calibration works fine
+	 */
+	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RXADC_CTRL_RG7,
+		       MTK_PHY_DA_AD_BUF_BIAS_LP_MASK, 0x3 << 8);
+
 	return mt798x_phy_calibration(phydev);
 }
 
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index d2aa3d0695e3..dad720138baa 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -120,6 +120,11 @@
  */
 #define LAN8814_1PPM_FORMAT			17179
 
+#define PTP_RX_VERSION				0x0248
+#define PTP_TX_VERSION				0x0288
+#define PTP_MAX_VERSION(x)			(((x) & GENMASK(7, 0)) << 8)
+#define PTP_MIN_VERSION(x)			((x) & GENMASK(7, 0))
+
 #define PTP_RX_MOD				0x024F
 #define PTP_RX_MOD_BAD_UDPV4_CHKSUM_FORCE_FCS_DIS_ BIT(3)
 #define PTP_RX_TIMESTAMP_EN			0x024D
@@ -3150,6 +3155,12 @@ static void lan8814_ptp_init(struct phy_device *phydev)
 	lanphy_write_page_reg(phydev, 5, PTP_TX_PARSE_IP_ADDR_EN, 0);
 	lanphy_write_page_reg(phydev, 5, PTP_RX_PARSE_IP_ADDR_EN, 0);
 
+	/* Disable checking for minorVersionPTP field */
+	lanphy_write_page_reg(phydev, 5, PTP_RX_VERSION,
+			      PTP_MAX_VERSION(0xff) | PTP_MIN_VERSION(0x0));
+	lanphy_write_page_reg(phydev, 5, PTP_TX_VERSION,
+			      PTP_MAX_VERSION(0xff) | PTP_MIN_VERSION(0x0));
+
 	skb_queue_head_init(&ptp_priv->tx_queue);
 	skb_queue_head_init(&ptp_priv->rx_queue);
 	INIT_LIST_HEAD(&ptp_priv->rx_ts_list);
@@ -3338,8 +3349,10 @@ static int lan8814_probe(struct phy_device *phydev)
 #define LAN8841_ADC_CHANNEL_MASK		198
 #define LAN8841_PTP_RX_PARSE_L2_ADDR_EN		370
 #define LAN8841_PTP_RX_PARSE_IP_ADDR_EN		371
+#define LAN8841_PTP_RX_VERSION			374
 #define LAN8841_PTP_TX_PARSE_L2_ADDR_EN		434
 #define LAN8841_PTP_TX_PARSE_IP_ADDR_EN		435
+#define LAN8841_PTP_TX_VERSION			438
 #define LAN8841_PTP_CMD_CTL			256
 #define LAN8841_PTP_CMD_CTL_PTP_ENABLE		BIT(2)
 #define LAN8841_PTP_CMD_CTL_PTP_DISABLE		BIT(1)
@@ -3383,6 +3396,12 @@ static int lan8841_config_init(struct phy_device *phydev)
 	phy_write_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG,
 		      LAN8841_PTP_RX_PARSE_IP_ADDR_EN, 0);
 
+	/* Disable checking for minorVersionPTP field */
+	phy_write_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG,
+		      LAN8841_PTP_RX_VERSION, 0xff00);
+	phy_write_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG,
+		      LAN8841_PTP_TX_VERSION, 0xff00);
+
 	/* 100BT Clause 40 improvenent errata */
 	phy_write_mmd(phydev, LAN8841_MMD_ANALOG_REG,
 		      LAN8841_ANALOG_CONTROL_1,
@@ -4839,6 +4858,7 @@ static struct phy_driver ksphy_driver[] = {
 	.flags		= PHY_POLL_CABLE_TEST,
 	.driver_data	= &ksz9131_type,
 	.probe		= kszphy_probe,
+	.soft_reset	= genphy_soft_reset,
 	.config_init	= ksz9131_config_init,
 	.config_intr	= kszphy_config_intr,
 	.config_aneg	= ksz9131_config_aneg,
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 894172a3e15f..337899c69738 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -421,9 +421,11 @@ static int rtl8211f_config_init(struct phy_device *phydev)
 				ERR_PTR(ret));
 			return ret;
 		}
+
+		return genphy_soft_reset(phydev);
 	}
 
-	return genphy_soft_reset(phydev);
+	return 0;
 }
 
 static int rtl821x_suspend(struct phy_device *phydev)
diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index 6fa679b36290..db39dec7f247 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -151,10 +151,6 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id,
 	unsigned int br_min, br_nom, br_max;
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(modes) = { 0, };
 
-	phylink_set(modes, Autoneg);
-	phylink_set(modes, Pause);
-	phylink_set(modes, Asym_Pause);
-
 	/* Decode the bitrate information to MBd */
 	br_min = br_nom = br_max = 0;
 	if (id->base.br_nominal) {
@@ -339,6 +335,10 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id,
 		}
 	}
 
+	phylink_set(modes, Autoneg);
+	phylink_set(modes, Pause);
+	phylink_set(modes, Asym_Pause);
+
 	if (bus->sfp_quirk && bus->sfp_quirk->modes)
 		bus->sfp_quirk->modes(id, modes, interfaces);
 
diff --git a/drivers/net/plip/plip.c b/drivers/net/plip/plip.c
index 40ce8abe6999..cc7d1113ece0 100644
--- a/drivers/net/plip/plip.c
+++ b/drivers/net/plip/plip.c
@@ -1437,4 +1437,5 @@ static int __init plip_init (void)
 
 module_init(plip_init);
 module_exit(plip_cleanup_module);
+MODULE_DESCRIPTION("PLIP (parallel port) network module");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ppp/bsd_comp.c b/drivers/net/ppp/bsd_comp.c
index db0dc36d12e3..55954594e157 100644
--- a/drivers/net/ppp/bsd_comp.c
+++ b/drivers/net/ppp/bsd_comp.c
@@ -1166,5 +1166,6 @@ static void __exit bsdcomp_cleanup(void)
 
 module_init(bsdcomp_init);
 module_exit(bsdcomp_cleanup);
+MODULE_DESCRIPTION("PPP BSD-Compress compression module");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_ALIAS("ppp-compress-" __stringify(CI_BSD_COMPRESS));
diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c
index 840da924708b..c33c3db3cc08 100644
--- a/drivers/net/ppp/ppp_async.c
+++ b/drivers/net/ppp/ppp_async.c
@@ -87,6 +87,7 @@ struct asyncppp {
 static int flag_time = HZ;
 module_param(flag_time, int, 0);
 MODULE_PARM_DESC(flag_time, "ppp_async: interval between flagged packets (in clock ticks)");
+MODULE_DESCRIPTION("PPP async serial channel module");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_LDISC(N_PPP);
 
@@ -460,6 +461,10 @@ ppp_async_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg)
 	case PPPIOCSMRU:
 		if (get_user(val, p))
 			break;
+		if (val > U16_MAX) {
+			err = -EINVAL;
+			break;
+		}
 		if (val < PPP_MRU)
 			val = PPP_MRU;
 		ap->mru = val;
diff --git a/drivers/net/ppp/ppp_deflate.c b/drivers/net/ppp/ppp_deflate.c
index e6d48e5c65a3..4d2ff63f2ee2 100644
--- a/drivers/net/ppp/ppp_deflate.c
+++ b/drivers/net/ppp/ppp_deflate.c
@@ -630,6 +630,7 @@ static void __exit deflate_cleanup(void)
 
 module_init(deflate_init);
 module_exit(deflate_cleanup);
+MODULE_DESCRIPTION("PPP Deflate compression module");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_ALIAS("ppp-compress-" __stringify(CI_DEFLATE));
 MODULE_ALIAS("ppp-compress-" __stringify(CI_DEFLATE_DRAFT));
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 0193af2d31c9..3dd52bf28f15 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -3604,6 +3604,7 @@ EXPORT_SYMBOL(ppp_input_error);
 EXPORT_SYMBOL(ppp_output_wakeup);
 EXPORT_SYMBOL(ppp_register_compressor);
 EXPORT_SYMBOL(ppp_unregister_compressor);
+MODULE_DESCRIPTION("Generic PPP layer driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_CHARDEV(PPP_MAJOR, 0);
 MODULE_ALIAS_RTNL_LINK("ppp");
diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c
index 52d05ce4a281..45bf59ac8f57 100644
--- a/drivers/net/ppp/ppp_synctty.c
+++ b/drivers/net/ppp/ppp_synctty.c
@@ -724,5 +724,6 @@ ppp_sync_cleanup(void)
 
 module_init(ppp_sync_init);
 module_exit(ppp_sync_cleanup);
+MODULE_DESCRIPTION("PPP synchronous TTY channel module");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_LDISC(N_SYNC_PPP);
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 8e7238e97d0a..2ea4f4890d23 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -1007,26 +1007,21 @@ static int pppoe_recvmsg(struct socket *sock, struct msghdr *m,
 	struct sk_buff *skb;
 	int error = 0;
 
-	if (sk->sk_state & PPPOX_BOUND) {
-		error = -EIO;
-		goto end;
-	}
+	if (sk->sk_state & PPPOX_BOUND)
+		return -EIO;
 
 	skb = skb_recv_datagram(sk, flags, &error);
-	if (error < 0)
-		goto end;
+	if (!skb)
+		return error;
 
-	if (skb) {
-		total_len = min_t(size_t, total_len, skb->len);
-		error = skb_copy_datagram_msg(skb, 0, m, total_len);
-		if (error == 0) {
-			consume_skb(skb);
-			return total_len;
-		}
+	total_len = min_t(size_t, total_len, skb->len);
+	error = skb_copy_datagram_msg(skb, 0, m, total_len);
+	if (error == 0) {
+		consume_skb(skb);
+		return total_len;
 	}
 
 	kfree_skb(skb);
-end:
 	return error;
 }
 
diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c
index ba93bab948e0..18df7ca66198 100644
--- a/drivers/net/slip/slhc.c
+++ b/drivers/net/slip/slhc.c
@@ -752,4 +752,5 @@ EXPORT_SYMBOL(slhc_compress);
 EXPORT_SYMBOL(slhc_uncompress);
 EXPORT_SYMBOL(slhc_toss);
 
+MODULE_DESCRIPTION("Compression helpers for SLIP (serial line)");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index e4280e37fec9..0aba3569ccc0 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -1437,5 +1437,6 @@ out:
 }
 
 #endif
+MODULE_DESCRIPTION("SLIP (serial line) protocol module");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_LDISC(N_SLIP);
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index afa5497f7c35..8f95a562b8d0 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -653,6 +653,7 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 				   tun->tfiles[tun->numqueues - 1]);
 		ntfile = rtnl_dereference(tun->tfiles[index]);
 		ntfile->queue_index = index;
+		ntfile->xdp_rxq.queue_index = index;
 		rcu_assign_pointer(tun->tfiles[tun->numqueues - 1],
 				   NULL);
 
@@ -1630,13 +1631,19 @@ static int tun_xdp_act(struct tun_struct *tun, struct bpf_prog *xdp_prog,
 	switch (act) {
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(tun->dev, xdp, xdp_prog);
-		if (err)
+		if (err) {
+			dev_core_stats_rx_dropped_inc(tun->dev);
 			return err;
+		}
+		dev_sw_netstats_rx_add(tun->dev, xdp->data_end - xdp->data);
 		break;
 	case XDP_TX:
 		err = tun_xdp_tx(tun->dev, xdp);
-		if (err < 0)
+		if (err < 0) {
+			dev_core_stats_rx_dropped_inc(tun->dev);
 			return err;
+		}
+		dev_sw_netstats_rx_add(tun->dev, xdp->data_end - xdp->data);
 		break;
 	case XDP_PASS:
 		break;
diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c
index 99ec1d4a972d..8b6d6a1b3c2e 100644
--- a/drivers/net/usb/dm9601.c
+++ b/drivers/net/usb/dm9601.c
@@ -232,7 +232,7 @@ static int dm9601_mdio_read(struct net_device *netdev, int phy_id, int loc)
 	err = dm_read_shared_word(dev, 1, loc, &res);
 	if (err < 0) {
 		netdev_err(dev->net, "MDIO read error: %d\n", err);
-		return err;
+		return 0;
 	}
 
 	netdev_dbg(dev->net,
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index 83b8452220ec..f088ea2ba6f3 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -363,7 +363,6 @@ static int disable_net;
 /* driver info */
 static const char driver_name[] = "hso";
 static const char tty_filename[] = "ttyHS";
-static const char *version = __FILE__ ": " MOD_AUTHOR;
 /* the usb driver itself (registered in hso_init) */
 static struct usb_driver hso_driver;
 /* serial structures */
@@ -3228,16 +3227,8 @@ static struct usb_driver hso_driver = {
 
 static int __init hso_init(void)
 {
-	int i;
 	int result;
 
-	/* put it in the log */
-	pr_info("%s\n", version);
-
-	/* Initialise the serial table semaphore and table */
-	for (i = 0; i < HSO_SERIAL_TTY_MINORS; i++)
-		serial_table[i] = NULL;
-
 	/* allocate our driver using the proper amount of supported minors */
 	tty_drv = tty_alloc_driver(HSO_SERIAL_TTY_MINORS, TTY_DRIVER_REAL_RAW |
 			TTY_DRIVER_DYNAMIC_DEV);
@@ -3285,8 +3276,6 @@ err_free_tty:
 
 static void __exit hso_exit(void)
 {
-	pr_info("unloaded\n");
-
 	tty_unregister_driver(tty_drv);
 	/* deregister the usb driver */
 	usb_deregister(&hso_driver);
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index a6d653ff552a..d2aa2c5b1989 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1501,7 +1501,9 @@ static int lan78xx_link_reset(struct lan78xx_net *dev)
 
 		lan78xx_rx_urb_submit_all(dev);
 
+		local_bh_disable();
 		napi_schedule(&dev->napi);
+		local_bh_enable();
 	}
 
 	return 0;
@@ -3033,7 +3035,8 @@ static int lan78xx_reset(struct lan78xx_net *dev)
 	if (dev->chipid == ID_REV_CHIP_ID_7801_)
 		buf &= ~MAC_CR_GMII_EN_;
 
-	if (dev->chipid == ID_REV_CHIP_ID_7800_) {
+	if (dev->chipid == ID_REV_CHIP_ID_7800_ ||
+	    dev->chipid == ID_REV_CHIP_ID_7850_) {
 		ret = lan78xx_read_raw_eeprom(dev, 0, 1, &sig);
 		if (!ret && sig != EEPROM_INDICATOR) {
 			/* Implies there is no external eeprom. Set mac speed */
@@ -3132,7 +3135,8 @@ static int lan78xx_open(struct net_device *net)
 done:
 	mutex_unlock(&dev->dev_mutex);
 
-	usb_autopm_put_interface(dev->intf);
+	if (ret < 0)
+		usb_autopm_put_interface(dev->intf);
 
 	return ret;
 }
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 9bf2140fd0a1..0d0672d2a654 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -10069,7 +10069,7 @@ static struct usb_driver rtl8152_driver = {
 	.disable_hub_initiated_lpm = 1,
 };
 
-static int rtl8152_cfgselector_probe(struct usb_device *udev)
+static int rtl8152_cfgselector_choose_configuration(struct usb_device *udev)
 {
 	struct usb_host_config *c;
 	int i, num_configs;
@@ -10096,19 +10096,13 @@ static int rtl8152_cfgselector_probe(struct usb_device *udev)
 	if (i == num_configs)
 		return -ENODEV;
 
-	if (usb_set_configuration(udev, c->desc.bConfigurationValue)) {
-		dev_err(&udev->dev, "Failed to set configuration %d\n",
-			c->desc.bConfigurationValue);
-		return -ENODEV;
-	}
-
-	return 0;
+	return c->desc.bConfigurationValue;
 }
 
 static struct usb_device_driver rtl8152_cfgselector_driver = {
-	.name =		MODULENAME "-cfgselector",
-	.probe =	rtl8152_cfgselector_probe,
-	.id_table =	rtl8152_table,
+	.name =	MODULENAME "-cfgselector",
+	.choose_configuration = rtl8152_cfgselector_choose_configuration,
+	.id_table = rtl8152_table,
 	.generic_subclass = 1,
 	.supports_autosuspend = 1,
 };
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index a530f20ee257..2fa46baa589e 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -2105,6 +2105,11 @@ static const struct usb_device_id products[] = {
 		.driver_info = (unsigned long) &smsc95xx_info,
 	},
 	{
+		/* SYSTEC USB-SPEmodule1 10BASE-T1L Ethernet Device */
+		USB_DEVICE(0x0878, 0x1400),
+		.driver_info = (unsigned long)&smsc95xx_info,
+	},
+	{
 		/* Microchip's EVB-LAN8670-USB 10BASE-T1S Ethernet Device */
 		USB_DEVICE(0x184F, 0x0051),
 		.driver_info = (unsigned long)&smsc95xx_info,
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 578e36ea1589..cd4a6fe458f9 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1208,14 +1208,6 @@ static int veth_enable_xdp(struct net_device *dev)
 				veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, true);
 				return err;
 			}
-
-			if (!veth_gro_requested(dev)) {
-				/* user-space did not require GRO, but adding XDP
-				 * is supposed to get GRO working
-				 */
-				dev->features |= NETIF_F_GRO;
-				netdev_features_change(dev);
-			}
 		}
 	}
 
@@ -1235,18 +1227,9 @@ static void veth_disable_xdp(struct net_device *dev)
 	for (i = 0; i < dev->real_num_rx_queues; i++)
 		rcu_assign_pointer(priv->rq[i].xdp_prog, NULL);
 
-	if (!netif_running(dev) || !veth_gro_requested(dev)) {
+	if (!netif_running(dev) || !veth_gro_requested(dev))
 		veth_napi_del(dev);
 
-		/* if user-space did not require GRO, since adding XDP
-		 * enabled it, clear it now
-		 */
-		if (!veth_gro_requested(dev) && netif_running(dev)) {
-			dev->features &= ~NETIF_F_GRO;
-			netdev_features_change(dev);
-		}
-	}
-
 	veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, false);
 }
 
@@ -1478,7 +1461,8 @@ static int veth_alloc_queues(struct net_device *dev)
 	struct veth_priv *priv = netdev_priv(dev);
 	int i;
 
-	priv->rq = kcalloc(dev->num_rx_queues, sizeof(*priv->rq), GFP_KERNEL_ACCOUNT);
+	priv->rq = kvcalloc(dev->num_rx_queues, sizeof(*priv->rq),
+			    GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL);
 	if (!priv->rq)
 		return -ENOMEM;
 
@@ -1494,7 +1478,7 @@ static void veth_free_queues(struct net_device *dev)
 {
 	struct veth_priv *priv = netdev_priv(dev);
 
-	kfree(priv->rq);
+	kvfree(priv->rq);
 }
 
 static int veth_dev_init(struct net_device *dev)
@@ -1654,6 +1638,14 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		}
 
 		if (!old_prog) {
+			if (!veth_gro_requested(dev)) {
+				/* user-space did not require GRO, but adding
+				 * XDP is supposed to get GRO working
+				 */
+				dev->features |= NETIF_F_GRO;
+				netdev_features_change(dev);
+			}
+
 			peer->hw_features &= ~NETIF_F_GSO_SOFTWARE;
 			peer->max_mtu = max_mtu;
 		}
@@ -1669,6 +1661,14 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 			if (dev->flags & IFF_UP)
 				veth_disable_xdp(dev);
 
+			/* if user-space did not require GRO, since adding XDP
+			 * enabled it, clear it now
+			 */
+			if (!veth_gro_requested(dev)) {
+				dev->features &= ~NETIF_F_GRO;
+				netdev_features_change(dev);
+			}
+
 			if (peer) {
 				peer->hw_features |= NETIF_F_GSO_SOFTWARE;
 				peer->max_mtu = ETH_MAX_MTU;
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 3cb8aa193884..d7ce4a1011ea 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -4295,10 +4295,11 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 {
 	vq_callback_t **callbacks;
 	struct virtqueue **vqs;
-	int ret = -ENOMEM;
-	int i, total_vqs;
 	const char **names;
+	int ret = -ENOMEM;
+	int total_vqs;
 	bool *ctx;
+	u16 i;
 
 	/* We expect 1 RX virtqueue followed by 1 TX virtqueue, followed by
 	 * possible N-1 RX/TX queue pairs used in multiqueue mode, followed by
@@ -4335,8 +4336,8 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		callbacks[rxq2vq(i)] = skb_recv_done;
 		callbacks[txq2vq(i)] = skb_xmit_done;
-		sprintf(vi->rq[i].name, "input.%d", i);
-		sprintf(vi->sq[i].name, "output.%d", i);
+		sprintf(vi->rq[i].name, "input.%u", i);
+		sprintf(vi->sq[i].name, "output.%u", i);
 		names[rxq2vq(i)] = vi->rq[i].name;
 		names[txq2vq(i)] = vi->sq[i].name;
 		if (ctx)
diff --git a/drivers/net/wan/slic_ds26522.c b/drivers/net/wan/slic_ds26522.c
index 8a51cfcff99e..cbb99fc5ea9f 100644
--- a/drivers/net/wan/slic_ds26522.c
+++ b/drivers/net/wan/slic_ds26522.c
@@ -28,6 +28,7 @@
 
 static struct spi_device *g_spi;
 
+MODULE_DESCRIPTION("Slic Maxim DS26522 driver");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Zhao Qiang<B45475@freescale.com>");
 
diff --git a/drivers/net/wireless/ath/ar5523/ar5523.c b/drivers/net/wireless/ath/ar5523/ar5523.c
index 43e0db78d42b..a742cec44e3d 100644
--- a/drivers/net/wireless/ath/ar5523/ar5523.c
+++ b/drivers/net/wireless/ath/ar5523/ar5523.c
@@ -1803,5 +1803,6 @@ static struct usb_driver ar5523_driver = {
 
 module_usb_driver(ar5523_driver);
 
+MODULE_DESCRIPTION("Atheros AR5523 wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_FIRMWARE(AR5523_FIRMWARE_FILE);
diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index 7e3b6779f4e9..02e160d831be 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -368,10 +368,6 @@ struct ath11k_vif {
 	struct ieee80211_chanctx_conf chanctx;
 	struct ath11k_arp_ns_offload arp_ns_offload;
 	struct ath11k_rekey_data rekey_data;
-
-#ifdef CONFIG_ATH11K_DEBUGFS
-	struct dentry *debugfs_twt;
-#endif /* CONFIG_ATH11K_DEBUGFS */
 };
 
 struct ath11k_vif_iter {
diff --git a/drivers/net/wireless/ath/ath11k/debugfs.c b/drivers/net/wireless/ath/ath11k/debugfs.c
index a847bc0d50c0..a48e737ef35d 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs.c
+++ b/drivers/net/wireless/ath/ath11k/debugfs.c
@@ -1894,35 +1894,30 @@ static const struct file_operations ath11k_fops_twt_resume_dialog = {
 	.open = simple_open
 };
 
-void ath11k_debugfs_add_interface(struct ath11k_vif *arvif)
+void ath11k_debugfs_op_vif_add(struct ieee80211_hw *hw,
+			       struct ieee80211_vif *vif)
 {
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	struct ath11k_base *ab = arvif->ar->ab;
+	struct dentry *debugfs_twt;
 
 	if (arvif->vif->type != NL80211_IFTYPE_AP &&
 	    !(arvif->vif->type == NL80211_IFTYPE_STATION &&
 	      test_bit(WMI_TLV_SERVICE_STA_TWT, ab->wmi_ab.svc_map)))
 		return;
 
-	arvif->debugfs_twt = debugfs_create_dir("twt",
-						arvif->vif->debugfs_dir);
-	debugfs_create_file("add_dialog", 0200, arvif->debugfs_twt,
+	debugfs_twt = debugfs_create_dir("twt",
+					 arvif->vif->debugfs_dir);
+	debugfs_create_file("add_dialog", 0200, debugfs_twt,
 			    arvif, &ath11k_fops_twt_add_dialog);
 
-	debugfs_create_file("del_dialog", 0200, arvif->debugfs_twt,
+	debugfs_create_file("del_dialog", 0200, debugfs_twt,
 			    arvif, &ath11k_fops_twt_del_dialog);
 
-	debugfs_create_file("pause_dialog", 0200, arvif->debugfs_twt,
+	debugfs_create_file("pause_dialog", 0200, debugfs_twt,
 			    arvif, &ath11k_fops_twt_pause_dialog);
 
-	debugfs_create_file("resume_dialog", 0200, arvif->debugfs_twt,
+	debugfs_create_file("resume_dialog", 0200, debugfs_twt,
 			    arvif, &ath11k_fops_twt_resume_dialog);
 }
 
-void ath11k_debugfs_remove_interface(struct ath11k_vif *arvif)
-{
-	if (!arvif->debugfs_twt)
-		return;
-
-	debugfs_remove_recursive(arvif->debugfs_twt);
-	arvif->debugfs_twt = NULL;
-}
diff --git a/drivers/net/wireless/ath/ath11k/debugfs.h b/drivers/net/wireless/ath/ath11k/debugfs.h
index 44d15845f39a..a39e458637b0 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs.h
+++ b/drivers/net/wireless/ath/ath11k/debugfs.h
@@ -307,8 +307,8 @@ static inline int ath11k_debugfs_rx_filter(struct ath11k *ar)
 	return ar->debug.rx_filter;
 }
 
-void ath11k_debugfs_add_interface(struct ath11k_vif *arvif);
-void ath11k_debugfs_remove_interface(struct ath11k_vif *arvif);
+void ath11k_debugfs_op_vif_add(struct ieee80211_hw *hw,
+			       struct ieee80211_vif *vif);
 void ath11k_debugfs_add_dbring_entry(struct ath11k *ar,
 				     enum wmi_direct_buffer_module id,
 				     enum ath11k_dbg_dbr_event event,
@@ -387,14 +387,6 @@ static inline int ath11k_debugfs_get_fw_stats(struct ath11k *ar,
 	return 0;
 }
 
-static inline void ath11k_debugfs_add_interface(struct ath11k_vif *arvif)
-{
-}
-
-static inline void ath11k_debugfs_remove_interface(struct ath11k_vif *arvif)
-{
-}
-
 static inline void
 ath11k_debugfs_add_dbring_entry(struct ath11k *ar,
 				enum wmi_direct_buffer_module id,
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index db241589424d..b13525bbbb80 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -6756,13 +6756,6 @@ static int ath11k_mac_op_add_interface(struct ieee80211_hw *hw,
 		goto err;
 	}
 
-	/* In the case of hardware recovery, debugfs files are
-	 * not deleted since ieee80211_ops.remove_interface() is
-	 * not invoked. In such cases, try to delete the files.
-	 * These will be re-created later.
-	 */
-	ath11k_debugfs_remove_interface(arvif);
-
 	memset(arvif, 0, sizeof(*arvif));
 
 	arvif->ar = ar;
@@ -6939,8 +6932,6 @@ static int ath11k_mac_op_add_interface(struct ieee80211_hw *hw,
 
 	ath11k_dp_vdev_tx_attach(ar, arvif);
 
-	ath11k_debugfs_add_interface(arvif);
-
 	if (vif->type != NL80211_IFTYPE_MONITOR &&
 	    test_bit(ATH11K_FLAG_MONITOR_CONF_ENABLED, &ar->monitor_flags)) {
 		ret = ath11k_mac_monitor_vdev_create(ar);
@@ -7056,8 +7047,6 @@ err_vdev_del:
 	/* Recalc txpower for remaining vdev */
 	ath11k_mac_txpower_recalc(ar);
 
-	ath11k_debugfs_remove_interface(arvif);
-
 	/* TODO: recal traffic pause state based on the available vdevs */
 
 	mutex_unlock(&ar->conf_mutex);
@@ -9153,6 +9142,7 @@ static const struct ieee80211_ops ath11k_ops = {
 #endif
 
 #ifdef CONFIG_ATH11K_DEBUGFS
+	.vif_add_debugfs		= ath11k_debugfs_op_vif_add,
 	.sta_add_debugfs		= ath11k_debugfs_sta_op_add,
 #endif
 
diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index 41119fb177e3..4e6b4df8562f 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -1685,6 +1685,7 @@ static struct platform_driver wcn36xx_driver = {
 
 module_platform_driver(wcn36xx_driver);
 
+MODULE_DESCRIPTION("Qualcomm Atheros WCN3660/3680 wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Eugene Krasnikov k.eugene.e@gmail.com");
 MODULE_FIRMWARE(WLAN_NV_FILE);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/module.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/module.c
index d55f3271d619..4f0c1e1a8e60 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/module.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/module.c
@@ -20,6 +20,7 @@ static void __exit brcmf_bca_exit(void)
 	brcmf_fwvid_unregister_vendor(BRCMF_FWVENDOR_BCA, THIS_MODULE);
 }
 
+MODULE_DESCRIPTION("Broadcom FullMAC WLAN driver plugin for Broadcom AP chipsets");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_IMPORT_NS(BRCMFMAC);
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 133c5ea6429c..28d6a30cc010 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -3779,8 +3779,10 @@ static int brcmf_internal_escan_add_info(struct cfg80211_scan_request *req,
 		if (req->channels[i] == chan)
 			break;
 	}
-	if (i == req->n_channels)
-		req->channels[req->n_channels++] = chan;
+	if (i == req->n_channels) {
+		req->n_channels++;
+		req->channels[i] = chan;
+	}
 
 	for (i = 0; i < req->n_ssids; i++) {
 		if (req->ssids[i].ssid_len == ssid_len &&
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/module.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/module.c
index f82fbbe3ecef..90d06cda03a2 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/module.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/module.c
@@ -20,6 +20,7 @@ static void __exit brcmf_cyw_exit(void)
 	brcmf_fwvid_unregister_vendor(BRCMF_FWVENDOR_CYW, THIS_MODULE);
 }
 
+MODULE_DESCRIPTION("Broadcom FullMAC WLAN driver plugin for Cypress/Infineon chipsets");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_IMPORT_NS(BRCMFMAC);
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
index 80220685f5e4..d7fb88bb6ae1 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
@@ -2707,7 +2707,6 @@ MODULE_DEVICE_TABLE(pci, brcmf_pcie_devid_table);
 
 
 static struct pci_driver brcmf_pciedrvr = {
-	.node = {},
 	.name = KBUILD_MODNAME,
 	.id_table = brcmf_pcie_devid_table,
 	.probe = brcmf_pcie_probe,
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
index 2178675ae1a4..0ccf735316c2 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
@@ -1581,7 +1581,7 @@ static int brcmf_usb_reset_device(struct device *dev, void *notused)
 
 void brcmf_usb_exit(void)
 {
-	struct device_driver *drv = &brcmf_usbdrvr.drvwrap.driver;
+	struct device_driver *drv = &brcmf_usbdrvr.driver;
 	int ret;
 
 	brcmf_dbg(USB, "Enter\n");
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/module.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/module.c
index 02918d434556..b66135e3cff4 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/module.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/module.c
@@ -20,6 +20,7 @@ static void __exit brcmf_wcc_exit(void)
 	brcmf_fwvid_unregister_vendor(BRCMF_FWVENDOR_WCC, THIS_MODULE);
 }
 
+MODULE_DESCRIPTION("Broadcom FullMAC WLAN driver plugin for Broadcom mobility chipsets");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_IMPORT_NS(BRCMFMAC);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
index b96f30d11644..dcc4810cb324 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@@ -618,7 +618,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt)
 					 &tbl_rev);
 	if (!IS_ERR(wifi_pkg)) {
 		if (tbl_rev != 2) {
-			ret = PTR_ERR(wifi_pkg);
+			ret = -EINVAL;
 			goto out_free;
 		}
 
@@ -634,7 +634,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt)
 					 &tbl_rev);
 	if (!IS_ERR(wifi_pkg)) {
 		if (tbl_rev != 1) {
-			ret = PTR_ERR(wifi_pkg);
+			ret = -EINVAL;
 			goto out_free;
 		}
 
@@ -650,7 +650,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt)
 					 &tbl_rev);
 	if (!IS_ERR(wifi_pkg)) {
 		if (tbl_rev != 0) {
-			ret = PTR_ERR(wifi_pkg);
+			ret = -EINVAL;
 			goto out_free;
 		}
 
@@ -707,7 +707,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt)
 					 &tbl_rev);
 	if (!IS_ERR(wifi_pkg)) {
 		if (tbl_rev != 2) {
-			ret = PTR_ERR(wifi_pkg);
+			ret = -EINVAL;
 			goto out_free;
 		}
 
@@ -723,7 +723,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt)
 					 &tbl_rev);
 	if (!IS_ERR(wifi_pkg)) {
 		if (tbl_rev != 1) {
-			ret = PTR_ERR(wifi_pkg);
+			ret = -EINVAL;
 			goto out_free;
 		}
 
@@ -739,7 +739,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt)
 					 &tbl_rev);
 	if (!IS_ERR(wifi_pkg)) {
 		if (tbl_rev != 0) {
-			ret = PTR_ERR(wifi_pkg);
+			ret = -EINVAL;
 			goto out_free;
 		}
 
@@ -1116,6 +1116,9 @@ int iwl_acpi_get_ppag_table(struct iwl_fw_runtime *fwrt)
 		goto read_table;
 	}
 
+	ret = PTR_ERR(wifi_pkg);
+	goto out_free;
+
 read_table:
 	fwrt->ppag_ver = tbl_rev;
 	flags = &wifi_pkg->package.elements[1];
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
index 798731ecbefd..b740c65a7dca 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
@@ -537,7 +537,7 @@ enum iwl_fw_dbg_config_cmd_type {
 }; /* LDBG_CFG_CMD_TYPE_API_E_VER_1 */
 
 /* this token disables debug asserts in the firmware */
-#define IWL_FW_DBG_CONFIG_TOKEN 0x00011301
+#define IWL_FW_DBG_CONFIG_TOKEN 0x00010001
 
 /**
  * struct iwl_fw_dbg_config_cmd - configure FW debug
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/txq.h b/drivers/net/wireless/intel/iwlwifi/fw/api/txq.h
index 9c69d3674384..e6c0f928a6bb 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/txq.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/txq.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2005-2014, 2019-2021, 2023 Intel Corporation
+ * Copyright (C) 2005-2014, 2019-2021, 2023-2024 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -66,6 +66,16 @@ enum iwl_gen2_tx_fifo {
 	IWL_GEN2_TRIG_TX_FIFO_VO,
 };
 
+enum iwl_bz_tx_fifo {
+	IWL_BZ_EDCA_TX_FIFO_BK,
+	IWL_BZ_EDCA_TX_FIFO_BE,
+	IWL_BZ_EDCA_TX_FIFO_VI,
+	IWL_BZ_EDCA_TX_FIFO_VO,
+	IWL_BZ_TRIG_TX_FIFO_BK,
+	IWL_BZ_TRIG_TX_FIFO_BE,
+	IWL_BZ_TRIG_TX_FIFO_VI,
+	IWL_BZ_TRIG_TX_FIFO_VO,
+};
 /**
  * enum iwl_tx_queue_cfg_actions - TXQ config options
  * @TX_QUEUE_CFG_ENABLE_QUEUE: enable a queue
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index e27774e7ed74..80fda056e46a 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2005-2014, 2018-2023 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2024 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
  */
@@ -19,7 +19,6 @@
  * @fwrt_ptr: pointer to the buffer coming from fwrt
  * @trans_ptr: pointer to struct %iwl_trans_dump_data which contains the
  *	transport's data.
- * @trans_len: length of the valid data in trans_ptr
  * @fwrt_len: length of the valid data in fwrt_ptr
  */
 struct iwl_fw_dump_ptrs {
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
index 3b14f6476743..72075720969c 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2018-2023 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
  */
 #include <linux/firmware.h>
 #include "iwl-drv.h"
@@ -1096,7 +1096,7 @@ static int iwl_dbg_tlv_override_trig_node(struct iwl_fw_runtime *fwrt,
 		node_trig = (void *)node_tlv->data;
 	}
 
-	memcpy(node_trig->data + offset, trig->data, trig_data_len);
+	memcpy((u8 *)node_trig->data + offset, trig->data, trig_data_len);
 	node_tlv->length = cpu_to_le32(size);
 
 	if (policy & IWL_FW_INI_APPLY_POLICY_OVERRIDE_CFG) {
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index ffe2670720c9..abf8001bdac1 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -128,6 +128,7 @@ static void iwl_dealloc_ucode(struct iwl_drv *drv)
 	kfree(drv->fw.ucode_capa.cmd_versions);
 	kfree(drv->fw.phy_integration_ver);
 	kfree(drv->trans->dbg.pc_data);
+	drv->trans->dbg.pc_data = NULL;
 
 	for (i = 0; i < IWL_UCODE_TYPE_MAX; i++)
 		iwl_free_fw_img(drv, drv->fw.img + i);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 402896988686..2f6774ec37b2 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -668,7 +668,6 @@ static const struct ieee80211_sband_iftype_data iwl_he_eht_capa[] = {
 			.has_eht = true,
 			.eht_cap_elem = {
 				.mac_cap_info[0] =
-					IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS |
 					IEEE80211_EHT_MAC_CAP0_OM_CONTROL |
 					IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 |
 					IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2 |
@@ -793,7 +792,6 @@ static const struct ieee80211_sband_iftype_data iwl_he_eht_capa[] = {
 			.has_eht = true,
 			.eht_cap_elem = {
 				.mac_cap_info[0] =
-					IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS |
 					IEEE80211_EHT_MAC_CAP0_OM_CONTROL |
 					IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 |
 					IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2,
@@ -1020,8 +1018,7 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
 	if (CSR_HW_REV_TYPE(trans->hw_rev) == IWL_CFG_MAC_TYPE_GL &&
 	    iftype_data->eht_cap.has_eht) {
 		iftype_data->eht_cap.eht_cap_elem.mac_cap_info[0] &=
-			~(IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS |
-			  IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 |
+			~(IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 |
 			  IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2);
 		iftype_data->eht_cap.eht_cap_elem.phy_cap_info[3] &=
 			~(IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO |
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index 4582afb149d7..05b64176859e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -1279,7 +1279,9 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw,
 
 		mvm->net_detect = true;
 	} else {
-		struct iwl_wowlan_config_cmd wowlan_config_cmd = {};
+		struct iwl_wowlan_config_cmd wowlan_config_cmd = {
+			.offloading_tid = 0,
+		};
 
 		wowlan_config_cmd.sta_id = mvmvif->deflink.ap_sta_id;
 
@@ -1291,6 +1293,11 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw,
 			goto out_noreset;
 		}
 
+		ret = iwl_mvm_sta_ensure_queue(
+			mvm, ap_sta->txq[wowlan_config_cmd.offloading_tid]);
+		if (ret)
+			goto out_noreset;
+
 		ret = iwl_mvm_get_wowlan_config(mvm, wowlan, &wowlan_config_cmd,
 						vif, mvmvif, ap_sta);
 		if (ret)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index c4f96125cf33..25a5a31e63c2 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -31,6 +31,17 @@ const u8 iwl_mvm_ac_to_gen2_tx_fifo[] = {
 	IWL_GEN2_TRIG_TX_FIFO_BK,
 };
 
+const u8 iwl_mvm_ac_to_bz_tx_fifo[] = {
+	IWL_BZ_EDCA_TX_FIFO_VO,
+	IWL_BZ_EDCA_TX_FIFO_VI,
+	IWL_BZ_EDCA_TX_FIFO_BE,
+	IWL_BZ_EDCA_TX_FIFO_BK,
+	IWL_BZ_TRIG_TX_FIFO_VO,
+	IWL_BZ_TRIG_TX_FIFO_VI,
+	IWL_BZ_TRIG_TX_FIFO_BE,
+	IWL_BZ_TRIG_TX_FIFO_BK,
+};
+
 struct iwl_mvm_mac_iface_iterator_data {
 	struct iwl_mvm *mvm;
 	struct ieee80211_vif *vif;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 7f13dff04b26..53e26c3c3a9a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -1600,7 +1600,8 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw,
 	 */
 	if (vif->type == NL80211_IFTYPE_AP ||
 	    vif->type == NL80211_IFTYPE_ADHOC) {
-		iwl_mvm_vif_dbgfs_add_link(mvm, vif);
+		if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status))
+			iwl_mvm_vif_dbgfs_add_link(mvm, vif);
 		ret = 0;
 		goto out;
 	}
@@ -1640,7 +1641,8 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw,
 			iwl_mvm_chandef_get_primary_80(&vif->bss_conf.chandef);
 	}
 
-	iwl_mvm_vif_dbgfs_add_link(mvm, vif);
+	if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status))
+		iwl_mvm_vif_dbgfs_add_link(mvm, vif);
 
 	if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status) &&
 	    vif->type == NL80211_IFTYPE_STATION && !vif->p2p &&
@@ -3685,6 +3687,9 @@ iwl_mvm_sta_state_notexist_to_none(struct iwl_mvm *mvm,
 					   NL80211_TDLS_SETUP);
 	}
 
+	if (ret)
+		return ret;
+
 	for_each_sta_active_link(vif, sta, link_sta, i)
 		link_sta->agg.max_rc_amsdu_len = 1;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
index 61170173f917..893b69fc841b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
@@ -81,7 +81,8 @@ static int iwl_mvm_mld_mac_add_interface(struct ieee80211_hw *hw,
 		ieee80211_hw_set(mvm->hw, RX_INCLUDES_FCS);
 	}
 
-	iwl_mvm_vif_dbgfs_add_link(mvm, vif);
+	if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status))
+		iwl_mvm_vif_dbgfs_add_link(mvm, vif);
 
 	if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status) &&
 	    vif->type == NL80211_IFTYPE_STATION && !vif->p2p &&
@@ -437,6 +438,9 @@ __iwl_mvm_mld_unassign_vif_chanctx(struct iwl_mvm *mvm,
 		mvmvif->ap_ibss_active = false;
 	}
 
+	iwl_mvm_link_changed(mvm, vif, link_conf,
+			     LINK_CONTEXT_MODIFY_ACTIVE, false);
+
 	if (iwl_mvm_is_esr_supported(mvm->fwrt.trans) && n_active > 1) {
 		int ret = iwl_mvm_esr_mode_inactive(mvm, vif);
 
@@ -448,9 +452,6 @@ __iwl_mvm_mld_unassign_vif_chanctx(struct iwl_mvm *mvm,
 	if (vif->type == NL80211_IFTYPE_MONITOR)
 		iwl_mvm_mld_rm_snif_sta(mvm, vif);
 
-	iwl_mvm_link_changed(mvm, vif, link_conf,
-			     LINK_CONTEXT_MODIFY_ACTIVE, false);
-
 	if (switching_chanctx)
 		return;
 	mvmvif->link[link_id]->phy_ctxt = NULL;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 40627961b834..81dbef6947f5 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1581,12 +1581,16 @@ static inline int iwl_mvm_max_active_links(struct iwl_mvm *mvm,
 
 extern const u8 iwl_mvm_ac_to_tx_fifo[];
 extern const u8 iwl_mvm_ac_to_gen2_tx_fifo[];
+extern const u8 iwl_mvm_ac_to_bz_tx_fifo[];
 
 static inline u8 iwl_mvm_mac_ac_to_tx_fifo(struct iwl_mvm *mvm,
 					   enum ieee80211_ac_numbers ac)
 {
-	return iwl_mvm_has_new_tx_api(mvm) ?
-		iwl_mvm_ac_to_gen2_tx_fifo[ac] : iwl_mvm_ac_to_tx_fifo[ac];
+	if (mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
+		return iwl_mvm_ac_to_bz_tx_fifo[ac];
+	if (iwl_mvm_has_new_tx_api(mvm))
+		return iwl_mvm_ac_to_gen2_tx_fifo[ac];
+	return iwl_mvm_ac_to_tx_fifo[ac];
 }
 
 struct iwl_rate_info {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 886d00098528..af15d470c69b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -505,6 +505,10 @@ static bool iwl_mvm_is_dup(struct ieee80211_sta *sta, int queue,
 		return false;
 
 	mvm_sta = iwl_mvm_sta_from_mac80211(sta);
+
+	if (WARN_ON_ONCE(!mvm_sta->dup_data))
+		return false;
+
 	dup_data = &mvm_sta->dup_data[queue];
 
 	/*
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 2a3ca9785974..c2e0cff740e9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -1502,6 +1502,34 @@ out_err:
 	return ret;
 }
 
+int iwl_mvm_sta_ensure_queue(struct iwl_mvm *mvm,
+			     struct ieee80211_txq *txq)
+{
+	struct iwl_mvm_txq *mvmtxq = iwl_mvm_txq_from_mac80211(txq);
+	int ret = -EINVAL;
+
+	lockdep_assert_held(&mvm->mutex);
+
+	if (likely(test_bit(IWL_MVM_TXQ_STATE_READY, &mvmtxq->state)) ||
+	    !txq->sta) {
+		return 0;
+	}
+
+	if (!iwl_mvm_sta_alloc_queue(mvm, txq->sta, txq->ac, txq->tid)) {
+		set_bit(IWL_MVM_TXQ_STATE_READY, &mvmtxq->state);
+		ret = 0;
+	}
+
+	local_bh_disable();
+	spin_lock(&mvm->add_stream_lock);
+	if (!list_empty(&mvmtxq->list))
+		list_del_init(&mvmtxq->list);
+	spin_unlock(&mvm->add_stream_lock);
+	local_bh_enable();
+
+	return ret;
+}
+
 void iwl_mvm_add_new_dqa_stream_wk(struct work_struct *wk)
 {
 	struct iwl_mvm *mvm = container_of(wk, struct iwl_mvm,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
index b33a0ce096d4..3cf8a70274ce 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2018-2023 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
  * Copyright (C) 2013-2014 Intel Mobile Communications GmbH
  * Copyright (C) 2015-2016 Intel Deutschland GmbH
  */
@@ -571,6 +571,7 @@ void iwl_mvm_modify_all_sta_disable_tx(struct iwl_mvm *mvm,
 				       bool disable);
 
 void iwl_mvm_csa_client_absent(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
+int iwl_mvm_sta_ensure_queue(struct iwl_mvm *mvm, struct ieee80211_txq *txq);
 void iwl_mvm_add_new_dqa_stream_wk(struct work_struct *wk);
 int iwl_mvm_add_pasn_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			 struct iwl_mvm_int_sta *sta, u8 *addr, u32 cipher,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
index 218fdf1ed530..2e653a417d62 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2023 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2017 Intel Deutschland GmbH
  */
@@ -972,6 +972,7 @@ void iwl_mvm_rx_session_protect_notif(struct iwl_mvm *mvm,
 	if (!le32_to_cpu(notif->status) || !le32_to_cpu(notif->start)) {
 		/* End TE, notify mac80211 */
 		mvmvif->time_event_data.id = SESSION_PROTECT_CONF_MAX_ID;
+		mvmvif->time_event_data.link_id = -1;
 		iwl_mvm_p2p_roc_finished(mvm);
 		ieee80211_remain_on_channel_expired(mvm->hw);
 	} else if (le32_to_cpu(notif->start)) {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index db986bfc4dc3..461f26d9214e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -520,13 +520,24 @@ static void iwl_mvm_set_tx_cmd_crypto(struct iwl_mvm *mvm,
 	}
 }
 
+static void iwl_mvm_copy_hdr(void *cmd, const void *hdr, int hdrlen,
+			     const u8 *addr3_override)
+{
+	struct ieee80211_hdr *out_hdr = cmd;
+
+	memcpy(cmd, hdr, hdrlen);
+	if (addr3_override)
+		memcpy(out_hdr->addr3, addr3_override, ETH_ALEN);
+}
+
 /*
  * Allocates and sets the Tx cmd the driver data pointers in the skb
  */
 static struct iwl_device_tx_cmd *
 iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 		      struct ieee80211_tx_info *info, int hdrlen,
-		      struct ieee80211_sta *sta, u8 sta_id)
+		      struct ieee80211_sta *sta, u8 sta_id,
+		      const u8 *addr3_override)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	struct iwl_device_tx_cmd *dev_cmd;
@@ -584,7 +595,7 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 			cmd->len = cpu_to_le16((u16)skb->len);
 
 			/* Copy MAC header from skb into command buffer */
-			memcpy(cmd->hdr, hdr, hdrlen);
+			iwl_mvm_copy_hdr(cmd->hdr, hdr, hdrlen, addr3_override);
 
 			cmd->flags = cpu_to_le16(flags);
 			cmd->rate_n_flags = cpu_to_le32(rate_n_flags);
@@ -599,7 +610,7 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 			cmd->len = cpu_to_le16((u16)skb->len);
 
 			/* Copy MAC header from skb into command buffer */
-			memcpy(cmd->hdr, hdr, hdrlen);
+			iwl_mvm_copy_hdr(cmd->hdr, hdr, hdrlen, addr3_override);
 
 			cmd->flags = cpu_to_le32(flags);
 			cmd->rate_n_flags = cpu_to_le32(rate_n_flags);
@@ -617,7 +628,7 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 	iwl_mvm_set_tx_cmd_rate(mvm, tx_cmd, info, sta, hdr->frame_control);
 
 	/* Copy MAC header from skb into command buffer */
-	memcpy(tx_cmd->hdr, hdr, hdrlen);
+	iwl_mvm_copy_hdr(tx_cmd->hdr, hdr, hdrlen, addr3_override);
 
 out:
 	return dev_cmd;
@@ -820,7 +831,8 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb)
 
 	IWL_DEBUG_TX(mvm, "station Id %d, queue=%d\n", sta_id, queue);
 
-	dev_cmd = iwl_mvm_set_tx_params(mvm, skb, &info, hdrlen, NULL, sta_id);
+	dev_cmd = iwl_mvm_set_tx_params(mvm, skb, &info, hdrlen, NULL, sta_id,
+					NULL);
 	if (!dev_cmd)
 		return -1;
 
@@ -1140,7 +1152,8 @@ static int iwl_mvm_tx_pkt_queued(struct iwl_mvm *mvm,
  */
 static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
 			   struct ieee80211_tx_info *info,
-			   struct ieee80211_sta *sta)
+			   struct ieee80211_sta *sta,
+			   const u8 *addr3_override)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	struct iwl_mvm_sta *mvmsta;
@@ -1172,7 +1185,8 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
 		iwl_mvm_probe_resp_set_noa(mvm, skb);
 
 	dev_cmd = iwl_mvm_set_tx_params(mvm, skb, info, hdrlen,
-					sta, mvmsta->deflink.sta_id);
+					sta, mvmsta->deflink.sta_id,
+					addr3_override);
 	if (!dev_cmd)
 		goto drop;
 
@@ -1294,9 +1308,11 @@ int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb,
 	struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
 	struct ieee80211_tx_info info;
 	struct sk_buff_head mpdus_skbs;
+	struct ieee80211_vif *vif;
 	unsigned int payload_len;
 	int ret;
 	struct sk_buff *orig_skb = skb;
+	const u8 *addr3;
 
 	if (WARN_ON_ONCE(!mvmsta))
 		return -1;
@@ -1307,26 +1323,59 @@ int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb,
 	memcpy(&info, skb->cb, sizeof(info));
 
 	if (!skb_is_gso(skb))
-		return iwl_mvm_tx_mpdu(mvm, skb, &info, sta);
+		return iwl_mvm_tx_mpdu(mvm, skb, &info, sta, NULL);
 
 	payload_len = skb_tail_pointer(skb) - skb_transport_header(skb) -
 		tcp_hdrlen(skb) + skb->data_len;
 
 	if (payload_len <= skb_shinfo(skb)->gso_size)
-		return iwl_mvm_tx_mpdu(mvm, skb, &info, sta);
+		return iwl_mvm_tx_mpdu(mvm, skb, &info, sta, NULL);
 
 	__skb_queue_head_init(&mpdus_skbs);
 
+	vif = info.control.vif;
+	if (!vif)
+		return -1;
+
 	ret = iwl_mvm_tx_tso(mvm, skb, &info, sta, &mpdus_skbs);
 	if (ret)
 		return ret;
 
 	WARN_ON(skb_queue_empty(&mpdus_skbs));
 
+	/*
+	 * As described in IEEE sta 802.11-2020, table 9-30 (Address
+	 * field contents), A-MSDU address 3 should contain the BSSID
+	 * address.
+	 * Pass address 3 down to iwl_mvm_tx_mpdu() and further to set it
+	 * in the command header. We need to preserve the original
+	 * address 3 in the skb header to correctly create all the
+	 * A-MSDU subframe headers from it.
+	 */
+	switch (vif->type) {
+	case NL80211_IFTYPE_STATION:
+		addr3 = vif->cfg.ap_addr;
+		break;
+	case NL80211_IFTYPE_AP:
+		addr3 = vif->addr;
+		break;
+	default:
+		addr3 = NULL;
+		break;
+	}
+
 	while (!skb_queue_empty(&mpdus_skbs)) {
+		struct ieee80211_hdr *hdr;
+		bool amsdu;
+
 		skb = __skb_dequeue(&mpdus_skbs);
+		hdr = (void *)skb->data;
+		amsdu = ieee80211_is_data_qos(hdr->frame_control) &&
+			(*ieee80211_get_qos_ctl(hdr) &
+			 IEEE80211_QOS_CTL_A_MSDU_PRESENT);
 
-		ret = iwl_mvm_tx_mpdu(mvm, skb, &info, sta);
+		ret = iwl_mvm_tx_mpdu(mvm, skb, &info, sta,
+				      amsdu ? addr3 : NULL);
 		if (ret) {
 			/* Free skbs created as part of TSO logic that have not yet been dequeued */
 			__skb_queue_purge(&mpdus_skbs);
diff --git a/drivers/net/wireless/intersil/p54/fwio.c b/drivers/net/wireless/intersil/p54/fwio.c
index b52cce38115d..c4fe70e05b9b 100644
--- a/drivers/net/wireless/intersil/p54/fwio.c
+++ b/drivers/net/wireless/intersil/p54/fwio.c
@@ -125,7 +125,7 @@ int p54_parse_firmware(struct ieee80211_hw *dev, const struct firmware *fw)
 			   "FW rev %s - Softmac protocol %x.%x\n",
 			   fw_version, priv->fw_var >> 8, priv->fw_var & 0xff);
 		snprintf(dev->wiphy->fw_version, sizeof(dev->wiphy->fw_version),
-				"%s - %x.%x", fw_version,
+				"%.19s - %x.%x", fw_version,
 				priv->fw_var >> 8, priv->fw_var & 0xff);
 	}
 
diff --git a/drivers/net/wireless/intersil/p54/p54spi.c b/drivers/net/wireless/intersil/p54/p54spi.c
index ce0179b8ab36..0073b5e0f9c9 100644
--- a/drivers/net/wireless/intersil/p54/p54spi.c
+++ b/drivers/net/wireless/intersil/p54/p54spi.c
@@ -700,6 +700,7 @@ static struct spi_driver p54spi_driver = {
 
 module_spi_driver(p54spi_driver);
 
+MODULE_DESCRIPTION("Prism54 SPI wireless driver");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Christian Lamparter <chunkeey@web.de>");
 MODULE_ALIAS("spi:cx3110x");
diff --git a/drivers/net/wireless/marvell/mwifiex/usb.c b/drivers/net/wireless/marvell/mwifiex/usb.c
index d3ab9572e711..515e6db410f2 100644
--- a/drivers/net/wireless/marvell/mwifiex/usb.c
+++ b/drivers/net/wireless/marvell/mwifiex/usb.c
@@ -687,7 +687,7 @@ static struct usb_driver mwifiex_usb_driver = {
 	.suspend = mwifiex_usb_suspend,
 	.resume = mwifiex_usb_resume,
 	.soft_unbind = 1,
-	.drvwrap.driver = {
+	.driver = {
 		.coredump = mwifiex_usb_coredump,
 	},
 };
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/main.c b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
index 89d738deea62..e2146d30e553 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
@@ -728,6 +728,7 @@ const struct ieee80211_ops mt7603_ops = {
 	.set_sar_specs = mt7603_set_sar_specs,
 };
 
+MODULE_DESCRIPTION("MediaTek MT7603E and MT76x8 wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
 
 static int __init mt7603_init(void)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/main.c b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
index dab16b5fc386..0971c164b57e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
@@ -1375,4 +1375,5 @@ const struct ieee80211_ops mt7615_ops = {
 };
 EXPORT_SYMBOL_GPL(mt7615_ops);
 
+MODULE_DESCRIPTION("MediaTek MT7615E and MT7663E wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c
index ac036a072439..87a956ea3ad7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c
@@ -270,4 +270,5 @@ static void __exit mt7615_exit(void)
 
 module_init(mt7615_init);
 module_exit(mt7615_exit);
+MODULE_DESCRIPTION("MediaTek MT7615E MMIO helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
index 67cedd2555f9..9692890ba51b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
@@ -253,4 +253,5 @@ module_sdio_driver(mt7663s_driver);
 
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT7663S (SDIO) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb.c
index 04963b9f7498..df737e1ff27b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb.c
@@ -281,4 +281,5 @@ module_usb_driver(mt7663u_driver);
 
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT7663U (USB) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c
index 0052d103e276..820b39590027 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c
@@ -349,4 +349,5 @@ EXPORT_SYMBOL_GPL(mt7663_usb_sdio_register_device);
 
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
+MODULE_DESCRIPTION("MediaTek MT7663 SDIO/USB helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
index 96494ba2fdf7..3a20ba0d2492 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
@@ -3160,4 +3160,5 @@ exit:
 EXPORT_SYMBOL_GPL(mt76_connac2_mcu_fill_message);
 
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT76x connac layer helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
index c3a392a1a659..bcd24c9072ec 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
@@ -342,4 +342,5 @@ int mt76x0_eeprom_init(struct mt76x02_dev *dev)
 	return 0;
 }
 
+MODULE_DESCRIPTION("MediaTek MT76x EEPROM helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index 9277ff38b7a2..293e66fa83d5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -302,6 +302,7 @@ static const struct pci_device_id mt76x0e_device_table[] = {
 MODULE_DEVICE_TABLE(pci, mt76x0e_device_table);
 MODULE_FIRMWARE(MT7610E_FIRMWARE);
 MODULE_FIRMWARE(MT7650E_FIRMWARE);
+MODULE_DESCRIPTION("MediaTek MT76x0E (PCIe) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
 
 static struct pci_driver mt76x0e_driver = {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
index 0422c332354a..dd042949cf82 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -336,6 +336,7 @@ err:
 MODULE_DEVICE_TABLE(usb, mt76x0_device_table);
 MODULE_FIRMWARE(MT7610E_FIRMWARE);
 MODULE_FIRMWARE(MT7610U_FIRMWARE);
+MODULE_DESCRIPTION("MediaTek MT76x0U (USB) wireless driver");
 MODULE_LICENSE("GPL");
 
 static struct usb_driver mt76x0_driver = {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c
index 02da543dfc5c..b2cc44914294 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c
@@ -293,4 +293,5 @@ void mt76x02u_init_mcu(struct mt76_dev *dev)
 EXPORT_SYMBOL_GPL(mt76x02u_init_mcu);
 
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>");
+MODULE_DESCRIPTION("MediaTek MT76x02 MCU helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index 8a0e8124b894..8020446be37b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -696,4 +696,5 @@ void mt76x02_config_mac_addr_list(struct mt76x02_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt76x02_config_mac_addr_list);
 
+MODULE_DESCRIPTION("MediaTek MT76x02 helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c
index 8c01855885ce..1fe5f5a02f93 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c
@@ -506,4 +506,5 @@ int mt76x2_eeprom_init(struct mt76x02_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt76x2_eeprom_init);
 
+MODULE_DESCRIPTION("MediaTek MT76x2 EEPROM helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
index df85ebc6e1df..30959746e924 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
@@ -165,6 +165,7 @@ mt76x2e_resume(struct pci_dev *pdev)
 MODULE_DEVICE_TABLE(pci, mt76x2e_device_table);
 MODULE_FIRMWARE(MT7662_FIRMWARE);
 MODULE_FIRMWARE(MT7662_ROM_PATCH);
+MODULE_DESCRIPTION("MediaTek MT76x2E (PCIe) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
 
 static struct pci_driver mt76pci_driver = {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
index 55068f3252ef..ca78e14251c2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
@@ -147,4 +147,5 @@ static struct usb_driver mt76x2u_driver = {
 module_usb_driver(mt76x2u_driver);
 
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>");
+MODULE_DESCRIPTION("MediaTek MT76x2U (USB) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
index aff4f21e843d..3039f53e2245 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
@@ -958,4 +958,5 @@ static void __exit mt7915_exit(void)
 
 module_init(mt7915_init);
 module_exit(mt7915_exit);
+MODULE_DESCRIPTION("MediaTek MT7915E MMIO helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 0645417e0582..0d5adc5ddae3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -1418,5 +1418,6 @@ const struct ieee80211_ops mt7921_ops = {
 };
 EXPORT_SYMBOL_GPL(mt7921_ops);
 
+MODULE_DESCRIPTION("MediaTek MT7921 core driver");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index 57903c6e4f11..dde26f327478 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -544,4 +544,5 @@ MODULE_FIRMWARE(MT7922_FIRMWARE_WM);
 MODULE_FIRMWARE(MT7922_ROM_PATCH);
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT7921E (PCIe) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
index 7591e54d2897..a9ce1e746b95 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
@@ -323,5 +323,6 @@ static struct sdio_driver mt7921s_driver = {
 	.drv.pm		= pm_sleep_ptr(&mt7921s_pm_ops),
 };
 module_sdio_driver(mt7921s_driver);
+MODULE_DESCRIPTION("MediaTek MT7921S (SDIO) wireless driver");
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
index e5258c74fc07..8b7c03c47598 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
@@ -336,5 +336,6 @@ static struct usb_driver mt7921u_driver = {
 };
 module_usb_driver(mt7921u_driver);
 
+MODULE_DESCRIPTION("MediaTek MT7921U (USB) wireless driver");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index 8f1075da4903..125a1be3cb64 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -1450,4 +1450,5 @@ const struct ieee80211_ops mt7925_ops = {
 EXPORT_SYMBOL_GPL(mt7925_ops);
 
 MODULE_AUTHOR("Deren Wu <deren.wu@mediatek.com>");
+MODULE_DESCRIPTION("MediaTek MT7925 core driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
index 734f31ee40d3..1fd99a856541 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
@@ -583,4 +583,5 @@ MODULE_FIRMWARE(MT7925_FIRMWARE_WM);
 MODULE_FIRMWARE(MT7925_ROM_PATCH);
 MODULE_AUTHOR("Deren Wu <deren.wu@mediatek.com>");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT7925E (PCIe) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/usb.c b/drivers/net/wireless/mediatek/mt76/mt7925/usb.c
index 9b885c5b3ed5..1e0f094fc905 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/usb.c
@@ -329,4 +329,5 @@ static struct usb_driver mt7925u_driver = {
 module_usb_driver(mt7925u_driver);
 
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT7925U (USB) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
index 502be22dbe36..c42101aa9e45 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
@@ -862,5 +862,6 @@ int mt792x_load_firmware(struct mt792x_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt792x_load_firmware);
 
+MODULE_DESCRIPTION("MediaTek MT792x core driver");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_usb.c b/drivers/net/wireless/mediatek/mt76/mt792x_usb.c
index 2dd283caed36..589a3efb9f8c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_usb.c
@@ -314,5 +314,6 @@ void mt792xu_disconnect(struct usb_interface *usb_intf)
 }
 EXPORT_SYMBOL_GPL(mt792xu_disconnect);
 
+MODULE_DESCRIPTION("MediaTek MT792x USB helpers");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 3c729b563edc..699be57309c2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -4477,7 +4477,8 @@ int mt7996_mcu_set_txpower_sku(struct mt7996_phy *phy)
 
 	skb_put_data(skb, &req, sizeof(req));
 	/* cck and ofdm */
-	skb_put_data(skb, &la.cck, sizeof(la.cck) + sizeof(la.ofdm));
+	skb_put_data(skb, &la.cck, sizeof(la.cck));
+	skb_put_data(skb, &la.ofdm, sizeof(la.ofdm));
 	/* ht20 */
 	skb_put_data(skb, &la.mcs[0], 8);
 	/* ht40 */
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
index c50d89a445e9..9f2abfa273c9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
@@ -650,4 +650,5 @@ static void __exit mt7996_exit(void)
 
 module_init(mt7996_init);
 module_exit(mt7996_exit);
+MODULE_DESCRIPTION("MediaTek MT7996 MMIO helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/sdio.c b/drivers/net/wireless/mediatek/mt76/sdio.c
index c52d550f0c32..3e88798df017 100644
--- a/drivers/net/wireless/mediatek/mt76/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/sdio.c
@@ -672,4 +672,5 @@ EXPORT_SYMBOL_GPL(mt76s_init);
 
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT76x SDIO helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c
index 1584665fe3cb..5a0bcb5071bd 100644
--- a/drivers/net/wireless/mediatek/mt76/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/usb.c
@@ -1128,4 +1128,5 @@ int mt76u_init(struct mt76_dev *dev, struct usb_interface *intf)
 EXPORT_SYMBOL_GPL(mt76u_init);
 
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>");
+MODULE_DESCRIPTION("MediaTek MT76x USB helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/util.c b/drivers/net/wireless/mediatek/mt76/util.c
index fc76c66ff1a5..d6c01a2dd198 100644
--- a/drivers/net/wireless/mediatek/mt76/util.c
+++ b/drivers/net/wireless/mediatek/mt76/util.c
@@ -138,4 +138,5 @@ int __mt76_worker_fn(void *ptr)
 }
 EXPORT_SYMBOL_GPL(__mt76_worker_fn);
 
+MODULE_DESCRIPTION("MediaTek MT76x helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.c b/drivers/net/wireless/microchip/wilc1000/netdev.c
index 91d71e0f7ef2..81e8f25863f5 100644
--- a/drivers/net/wireless/microchip/wilc1000/netdev.c
+++ b/drivers/net/wireless/microchip/wilc1000/netdev.c
@@ -1018,5 +1018,6 @@ unregister_netdev:
 	return ERR_PTR(ret);
 }
 
+MODULE_DESCRIPTION("Atmel WILC1000 core wireless driver");
 MODULE_LICENSE("GPL");
 MODULE_FIRMWARE(WILC1000_FW(WILC1000_API_VER));
diff --git a/drivers/net/wireless/microchip/wilc1000/sdio.c b/drivers/net/wireless/microchip/wilc1000/sdio.c
index 0d13e3e46e98..d6d394693090 100644
--- a/drivers/net/wireless/microchip/wilc1000/sdio.c
+++ b/drivers/net/wireless/microchip/wilc1000/sdio.c
@@ -984,4 +984,5 @@ static struct sdio_driver wilc_sdio_driver = {
 module_driver(wilc_sdio_driver,
 	      sdio_register_driver,
 	      sdio_unregister_driver);
+MODULE_DESCRIPTION("Atmel WILC1000 SDIO wireless driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/wireless/microchip/wilc1000/spi.c b/drivers/net/wireless/microchip/wilc1000/spi.c
index 77b4cdff73c3..1d8b241ce43c 100644
--- a/drivers/net/wireless/microchip/wilc1000/spi.c
+++ b/drivers/net/wireless/microchip/wilc1000/spi.c
@@ -273,6 +273,7 @@ static struct spi_driver wilc_spi_driver = {
 	.remove = wilc_bus_remove,
 };
 module_spi_driver(wilc_spi_driver);
+MODULE_DESCRIPTION("Atmel WILC1000 SPI wireless driver");
 MODULE_LICENSE("GPL");
 
 static int wilc_spi_tx(struct wilc *wilc, u8 *b, u32 len)
diff --git a/drivers/net/wireless/ti/wl1251/sdio.c b/drivers/net/wireless/ti/wl1251/sdio.c
index 301bd0043a43..4e5b351f80f0 100644
--- a/drivers/net/wireless/ti/wl1251/sdio.c
+++ b/drivers/net/wireless/ti/wl1251/sdio.c
@@ -343,5 +343,6 @@ static void __exit wl1251_sdio_exit(void)
 module_init(wl1251_sdio_init);
 module_exit(wl1251_sdio_exit);
 
+MODULE_DESCRIPTION("TI WL1251 SDIO helpers");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Kalle Valo <kvalo@adurom.com>");
diff --git a/drivers/net/wireless/ti/wl1251/spi.c b/drivers/net/wireless/ti/wl1251/spi.c
index 29292f06bd3d..1936bb3af54a 100644
--- a/drivers/net/wireless/ti/wl1251/spi.c
+++ b/drivers/net/wireless/ti/wl1251/spi.c
@@ -342,6 +342,7 @@ static struct spi_driver wl1251_spi_driver = {
 
 module_spi_driver(wl1251_spi_driver);
 
+MODULE_DESCRIPTION("TI WL1251 SPI helpers");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Kalle Valo <kvalo@adurom.com>");
 MODULE_ALIAS("spi:wl1251");
diff --git a/drivers/net/wireless/ti/wl12xx/main.c b/drivers/net/wireless/ti/wl12xx/main.c
index de045fe4ca1e..b26d42b4e3cc 100644
--- a/drivers/net/wireless/ti/wl12xx/main.c
+++ b/drivers/net/wireless/ti/wl12xx/main.c
@@ -1955,6 +1955,7 @@ module_param_named(tcxo, tcxo_param, charp, 0);
 MODULE_PARM_DESC(tcxo,
 		 "TCXO clock: 19.2, 26, 38.4, 52, 16.368, 32.736, 16.8, 33.6");
 
+MODULE_DESCRIPTION("TI WL12xx wireless driver");
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>");
 MODULE_FIRMWARE(WL127X_FW_NAME_SINGLE);
diff --git a/drivers/net/wireless/ti/wl18xx/main.c b/drivers/net/wireless/ti/wl18xx/main.c
index 20d9181b3410..2ccac1cdec01 100644
--- a/drivers/net/wireless/ti/wl18xx/main.c
+++ b/drivers/net/wireless/ti/wl18xx/main.c
@@ -2086,6 +2086,7 @@ module_param_named(num_rx_desc, num_rx_desc_param, int, 0400);
 MODULE_PARM_DESC(num_rx_desc_param,
 		 "Number of Rx descriptors: u8 (default is 32)");
 
+MODULE_DESCRIPTION("TI WiLink 8 wireless driver");
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>");
 MODULE_FIRMWARE(WL18XX_FW_NAME);
diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index fb9ed97774c7..5736acb4d206 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -6793,6 +6793,7 @@ MODULE_PARM_DESC(bug_on_recovery, "BUG() on fw recovery");
 module_param(no_recovery, int, 0600);
 MODULE_PARM_DESC(no_recovery, "Prevent HW recovery. FW will remain stuck.");
 
+MODULE_DESCRIPTION("TI WLAN core driver");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>");
 MODULE_AUTHOR("Juuso Oikarinen <juuso.oikarinen@nokia.com>");
diff --git a/drivers/net/wireless/ti/wlcore/sdio.c b/drivers/net/wireless/ti/wlcore/sdio.c
index f0686635db46..eb5482ed76ae 100644
--- a/drivers/net/wireless/ti/wlcore/sdio.c
+++ b/drivers/net/wireless/ti/wlcore/sdio.c
@@ -447,6 +447,7 @@ module_sdio_driver(wl1271_sdio_driver);
 module_param(dump, bool, 0600);
 MODULE_PARM_DESC(dump, "Enable sdio read/write dumps.");
 
+MODULE_DESCRIPTION("TI WLAN SDIO helpers");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>");
 MODULE_AUTHOR("Juuso Oikarinen <juuso.oikarinen@nokia.com>");
diff --git a/drivers/net/wireless/ti/wlcore/spi.c b/drivers/net/wireless/ti/wlcore/spi.c
index 7d9a139db59e..0aa2b2f3c5c9 100644
--- a/drivers/net/wireless/ti/wlcore/spi.c
+++ b/drivers/net/wireless/ti/wlcore/spi.c
@@ -562,6 +562,7 @@ static struct spi_driver wl1271_spi_driver = {
 };
 
 module_spi_driver(wl1271_spi_driver);
+MODULE_DESCRIPTION("TI WLAN SPI helpers");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>");
 MODULE_AUTHOR("Juuso Oikarinen <juuso.oikarinen@nokia.com>");
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 88f760a7cbc3..ef76850d9bcd 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -104,13 +104,12 @@ bool provides_xdp_headroom = true;
 module_param(provides_xdp_headroom, bool, 0644);
 
 static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
-			       u8 status);
+			       s8 status);
 
 static void make_tx_response(struct xenvif_queue *queue,
-			     struct xen_netif_tx_request *txp,
+			     const struct xen_netif_tx_request *txp,
 			     unsigned int extra_count,
-			     s8       st);
-static void push_tx_responses(struct xenvif_queue *queue);
+			     s8 status);
 
 static void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx);
 
@@ -208,13 +207,9 @@ static void xenvif_tx_err(struct xenvif_queue *queue,
 			  unsigned int extra_count, RING_IDX end)
 {
 	RING_IDX cons = queue->tx.req_cons;
-	unsigned long flags;
 
 	do {
-		spin_lock_irqsave(&queue->response_lock, flags);
 		make_tx_response(queue, txp, extra_count, XEN_NETIF_RSP_ERROR);
-		push_tx_responses(queue);
-		spin_unlock_irqrestore(&queue->response_lock, flags);
 		if (cons == end)
 			break;
 		RING_COPY_REQUEST(&queue->tx, cons++, txp);
@@ -463,12 +458,20 @@ static void xenvif_get_requests(struct xenvif_queue *queue,
 	}
 
 	for (shinfo->nr_frags = 0; nr_slots > 0 && shinfo->nr_frags < MAX_SKB_FRAGS;
-	     shinfo->nr_frags++, gop++, nr_slots--) {
+	     nr_slots--) {
+		if (unlikely(!txp->size)) {
+			make_tx_response(queue, txp, 0, XEN_NETIF_RSP_OKAY);
+			++txp;
+			continue;
+		}
+
 		index = pending_index(queue->pending_cons++);
 		pending_idx = queue->pending_ring[index];
 		xenvif_tx_create_map_op(queue, pending_idx, txp,
 				        txp == first ? extra_count : 0, gop);
 		frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx);
+		++shinfo->nr_frags;
+		++gop;
 
 		if (txp == first)
 			txp = txfrags;
@@ -481,20 +484,33 @@ static void xenvif_get_requests(struct xenvif_queue *queue,
 		shinfo = skb_shinfo(nskb);
 		frags = shinfo->frags;
 
-		for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots;
-		     shinfo->nr_frags++, txp++, gop++) {
+		for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; ++txp) {
+			if (unlikely(!txp->size)) {
+				make_tx_response(queue, txp, 0,
+						 XEN_NETIF_RSP_OKAY);
+				continue;
+			}
+
 			index = pending_index(queue->pending_cons++);
 			pending_idx = queue->pending_ring[index];
 			xenvif_tx_create_map_op(queue, pending_idx, txp, 0,
 						gop);
 			frag_set_pending_idx(&frags[shinfo->nr_frags],
 					     pending_idx);
+			++shinfo->nr_frags;
+			++gop;
+		}
+
+		if (shinfo->nr_frags) {
+			skb_shinfo(skb)->frag_list = nskb;
+			nskb = NULL;
 		}
+	}
 
-		skb_shinfo(skb)->frag_list = nskb;
-	} else if (nskb) {
+	if (nskb) {
 		/* A frag_list skb was allocated but it is no longer needed
-		 * because enough slots were converted to copy ops above.
+		 * because enough slots were converted to copy ops above or some
+		 * were empty.
 		 */
 		kfree_skb(nskb);
 	}
@@ -963,7 +979,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 					 (ret == 0) ?
 					 XEN_NETIF_RSP_OKAY :
 					 XEN_NETIF_RSP_ERROR);
-			push_tx_responses(queue);
 			continue;
 		}
 
@@ -975,7 +990,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 
 			make_tx_response(queue, &txreq, extra_count,
 					 XEN_NETIF_RSP_OKAY);
-			push_tx_responses(queue);
 			continue;
 		}
 
@@ -1401,8 +1415,35 @@ int xenvif_tx_action(struct xenvif_queue *queue, int budget)
 	return work_done;
 }
 
+static void _make_tx_response(struct xenvif_queue *queue,
+			     const struct xen_netif_tx_request *txp,
+			     unsigned int extra_count,
+			     s8 status)
+{
+	RING_IDX i = queue->tx.rsp_prod_pvt;
+	struct xen_netif_tx_response *resp;
+
+	resp = RING_GET_RESPONSE(&queue->tx, i);
+	resp->id     = txp->id;
+	resp->status = status;
+
+	while (extra_count-- != 0)
+		RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL;
+
+	queue->tx.rsp_prod_pvt = ++i;
+}
+
+static void push_tx_responses(struct xenvif_queue *queue)
+{
+	int notify;
+
+	RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify);
+	if (notify)
+		notify_remote_via_irq(queue->tx_irq);
+}
+
 static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
-			       u8 status)
+			       s8 status)
 {
 	struct pending_tx_info *pending_tx_info;
 	pending_ring_idx_t index;
@@ -1412,8 +1453,8 @@ static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
 
 	spin_lock_irqsave(&queue->response_lock, flags);
 
-	make_tx_response(queue, &pending_tx_info->req,
-			 pending_tx_info->extra_count, status);
+	_make_tx_response(queue, &pending_tx_info->req,
+			  pending_tx_info->extra_count, status);
 
 	/* Release the pending index before pusing the Tx response so
 	 * its available before a new Tx request is pushed by the
@@ -1427,32 +1468,19 @@ static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
 	spin_unlock_irqrestore(&queue->response_lock, flags);
 }
 
-
 static void make_tx_response(struct xenvif_queue *queue,
-			     struct xen_netif_tx_request *txp,
+			     const struct xen_netif_tx_request *txp,
 			     unsigned int extra_count,
-			     s8       st)
+			     s8 status)
 {
-	RING_IDX i = queue->tx.rsp_prod_pvt;
-	struct xen_netif_tx_response *resp;
-
-	resp = RING_GET_RESPONSE(&queue->tx, i);
-	resp->id     = txp->id;
-	resp->status = st;
-
-	while (extra_count-- != 0)
-		RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL;
+	unsigned long flags;
 
-	queue->tx.rsp_prod_pvt = ++i;
-}
+	spin_lock_irqsave(&queue->response_lock, flags);
 
-static void push_tx_responses(struct xenvif_queue *queue)
-{
-	int notify;
+	_make_tx_response(queue, txp, extra_count, status);
+	push_tx_responses(queue);
 
-	RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify);
-	if (notify)
-		notify_remote_via_irq(queue->tx_irq);
+	spin_unlock_irqrestore(&queue->response_lock, flags);
 }
 
 static void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx)
@@ -1750,5 +1778,6 @@ static void __exit netback_fini(void)
 }
 module_exit(netback_fini);
 
+MODULE_DESCRIPTION("Xen backend network device module");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_ALIAS("xen-backend:vif");
diff --git a/drivers/nfc/pn533/uart.c b/drivers/nfc/pn533/uart.c
index a556acdb947b..2eb5978bd79e 100644
--- a/drivers/nfc/pn533/uart.c
+++ b/drivers/nfc/pn533/uart.c
@@ -203,8 +203,8 @@ static int pn532_uart_rx_is_frame(struct sk_buff *skb)
 	return 0;
 }
 
-static int pn532_receive_buf(struct serdev_device *serdev,
-		const unsigned char *data, size_t count)
+static ssize_t pn532_receive_buf(struct serdev_device *serdev,
+				 const u8 *data, size_t count)
 {
 	struct pn532_uart_phy *dev = serdev_device_get_drvdata(serdev);
 	size_t i;
diff --git a/drivers/nfc/s3fwrn5/uart.c b/drivers/nfc/s3fwrn5/uart.c
index 82ea35d748a5..456d3947116c 100644
--- a/drivers/nfc/s3fwrn5/uart.c
+++ b/drivers/nfc/s3fwrn5/uart.c
@@ -51,9 +51,8 @@ static const struct s3fwrn5_phy_ops uart_phy_ops = {
 	.write = s3fwrn82_uart_write,
 };
 
-static int s3fwrn82_uart_read(struct serdev_device *serdev,
-			      const unsigned char *data,
-			      size_t count)
+static ssize_t s3fwrn82_uart_read(struct serdev_device *serdev,
+				  const u8 *data, size_t count)
 {
 	struct s3fwrn82_uart_phy *phy = serdev_device_get_drvdata(serdev);
 	size_t i;
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index bb3726b622ad..4d0c527e8576 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1496,19 +1496,21 @@ static int btt_blk_init(struct btt *btt)
 {
 	struct nd_btt *nd_btt = btt->nd_btt;
 	struct nd_namespace_common *ndns = nd_btt->ndns;
-	int rc = -ENOMEM;
+	struct queue_limits lim = {
+		.logical_block_size	= btt->sector_size,
+		.max_hw_sectors		= UINT_MAX,
+	};
+	int rc;
 
-	btt->btt_disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!btt->btt_disk)
-		return -ENOMEM;
+	btt->btt_disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(btt->btt_disk))
+		return PTR_ERR(btt->btt_disk);
 
 	nvdimm_namespace_disk_name(ndns, btt->btt_disk->disk_name);
 	btt->btt_disk->first_minor = 0;
 	btt->btt_disk->fops = &btt_fops;
 	btt->btt_disk->private_data = btt;
 
-	blk_queue_logical_block_size(btt->btt_disk->queue, btt->sector_size);
-	blk_queue_max_hw_sectors(btt->btt_disk->queue, UINT_MAX);
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, btt->btt_disk->queue);
 	blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, btt->btt_disk->queue);
 
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 4e8fdcb3f1c8..8dcc10b6db5b 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -451,6 +451,11 @@ static int pmem_attach_disk(struct device *dev,
 {
 	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
 	struct nd_region *nd_region = to_nd_region(dev->parent);
+	struct queue_limits lim = {
+		.logical_block_size	= pmem_sector_size(ndns),
+		.physical_block_size	= PAGE_SIZE,
+		.max_hw_sectors		= UINT_MAX,
+	};
 	int nid = dev_to_node(dev), fua;
 	struct resource *res = &nsio->res;
 	struct range bb_range;
@@ -497,9 +502,9 @@ static int pmem_attach_disk(struct device *dev,
 		return -EBUSY;
 	}
 
-	disk = blk_alloc_disk(nid);
-	if (!disk)
-		return -ENOMEM;
+	disk = blk_alloc_disk(&lim, nid);
+	if (IS_ERR(disk))
+		return PTR_ERR(disk);
 	q = disk->queue;
 
 	pmem->disk = disk;
@@ -539,9 +544,6 @@ static int pmem_attach_disk(struct device *dev,
 	pmem->virt_addr = addr;
 
 	blk_queue_write_cache(q, true, fua);
-	blk_queue_physical_block_size(q, PAGE_SIZE);
-	blk_queue_logical_block_size(q, pmem_sector_size(ndns));
-	blk_queue_max_hw_sectors(q, UINT_MAX);
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
 	blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, q);
 	if (pmem->pfn_flags & PFN_MAP)
diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c
index a92eb172f0e7..4ceced5cefcf 100644
--- a/drivers/nvdimm/virtio_pmem.c
+++ b/drivers/nvdimm/virtio_pmem.c
@@ -29,12 +29,27 @@ static int init_vq(struct virtio_pmem *vpmem)
 	return 0;
 };
 
+static int virtio_pmem_validate(struct virtio_device *vdev)
+{
+	struct virtio_shm_region shm_reg;
+
+	if (virtio_has_feature(vdev, VIRTIO_PMEM_F_SHMEM_REGION) &&
+		!virtio_get_shm_region(vdev, &shm_reg, (u8)VIRTIO_PMEM_SHMEM_REGION_ID)
+	) {
+		dev_notice(&vdev->dev, "failed to get shared memory region %d\n",
+				VIRTIO_PMEM_SHMEM_REGION_ID);
+		__virtio_clear_bit(vdev, VIRTIO_PMEM_F_SHMEM_REGION);
+	}
+	return 0;
+}
+
 static int virtio_pmem_probe(struct virtio_device *vdev)
 {
 	struct nd_region_desc ndr_desc = {};
 	struct nd_region *nd_region;
 	struct virtio_pmem *vpmem;
 	struct resource res;
+	struct virtio_shm_region shm_reg;
 	int err = 0;
 
 	if (!vdev->config->get) {
@@ -57,10 +72,16 @@ static int virtio_pmem_probe(struct virtio_device *vdev)
 		goto out_err;
 	}
 
-	virtio_cread_le(vpmem->vdev, struct virtio_pmem_config,
-			start, &vpmem->start);
-	virtio_cread_le(vpmem->vdev, struct virtio_pmem_config,
-			size, &vpmem->size);
+	if (virtio_has_feature(vdev, VIRTIO_PMEM_F_SHMEM_REGION)) {
+		virtio_get_shm_region(vdev, &shm_reg, (u8)VIRTIO_PMEM_SHMEM_REGION_ID);
+		vpmem->start = shm_reg.addr;
+		vpmem->size = shm_reg.len;
+	} else {
+		virtio_cread_le(vpmem->vdev, struct virtio_pmem_config,
+				start, &vpmem->start);
+		virtio_cread_le(vpmem->vdev, struct virtio_pmem_config,
+				size, &vpmem->size);
+	}
 
 	res.start = vpmem->start;
 	res.end   = vpmem->start + vpmem->size - 1;
@@ -122,10 +143,17 @@ static void virtio_pmem_remove(struct virtio_device *vdev)
 	virtio_reset_device(vdev);
 }
 
+static unsigned int features[] = {
+	VIRTIO_PMEM_F_SHMEM_REGION,
+};
+
 static struct virtio_driver virtio_pmem_driver = {
+	.feature_table		= features,
+	.feature_table_size	= ARRAY_SIZE(features),
 	.driver.name		= KBUILD_MODNAME,
 	.driver.owner		= THIS_MODULE,
 	.id_table		= id_table,
+	.validate		= virtio_pmem_validate,
 	.probe			= virtio_pmem_probe,
 	.remove			= virtio_pmem_remove,
 };
diff --git a/drivers/nvme/common/auth.c b/drivers/nvme/common/auth.c
index a23ab5c968b9..a3455f1d67fa 100644
--- a/drivers/nvme/common/auth.c
+++ b/drivers/nvme/common/auth.c
@@ -471,4 +471,5 @@ int nvme_auth_generate_key(u8 *secret, struct nvme_dhchap_key **ret_key)
 }
 EXPORT_SYMBOL_GPL(nvme_auth_generate_key);
 
+MODULE_DESCRIPTION("NVMe Authentication framework");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/common/keyring.c b/drivers/nvme/common/keyring.c
index ee341b83eeba..6f7e7a8fa5ae 100644
--- a/drivers/nvme/common/keyring.c
+++ b/drivers/nvme/common/keyring.c
@@ -111,7 +111,7 @@ static struct key *nvme_tls_psk_lookup(struct key *keyring,
  * should be preferred to 'generated' PSKs,
  * and SHA-384 should be preferred to SHA-256.
  */
-struct nvme_tls_psk_priority_list {
+static struct nvme_tls_psk_priority_list {
 	bool generated;
 	enum nvme_tcp_tls_cipher cipher;
 } nvme_tls_psk_prio[] = {
@@ -181,5 +181,6 @@ static void __exit nvme_keyring_exit(void)
 
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Hannes Reinecke <hare@suse.de>");
+MODULE_DESCRIPTION("NVMe Keyring implementation");
 module_init(nvme_keyring_init);
 module_exit(nvme_keyring_exit);
diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
index 596bb11eeba5..a480cdeac288 100644
--- a/drivers/nvme/host/apple.c
+++ b/drivers/nvme/host/apple.c
@@ -797,6 +797,7 @@ static int apple_nvme_init_request(struct blk_mq_tag_set *set,
 
 static void apple_nvme_disable(struct apple_nvme *anv, bool shutdown)
 {
+	enum nvme_ctrl_state state = nvme_ctrl_state(&anv->ctrl);
 	u32 csts = readl(anv->mmio_nvme + NVME_REG_CSTS);
 	bool dead = false, freeze = false;
 	unsigned long flags;
@@ -808,8 +809,8 @@ static void apple_nvme_disable(struct apple_nvme *anv, bool shutdown)
 	if (csts & NVME_CSTS_CFS)
 		dead = true;
 
-	if (anv->ctrl.state == NVME_CTRL_LIVE ||
-	    anv->ctrl.state == NVME_CTRL_RESETTING) {
+	if (state == NVME_CTRL_LIVE ||
+	    state == NVME_CTRL_RESETTING) {
 		freeze = true;
 		nvme_start_freeze(&anv->ctrl);
 	}
@@ -881,7 +882,7 @@ static enum blk_eh_timer_return apple_nvme_timeout(struct request *req)
 	unsigned long flags;
 	u32 csts = readl(anv->mmio_nvme + NVME_REG_CSTS);
 
-	if (anv->ctrl.state != NVME_CTRL_LIVE) {
+	if (nvme_ctrl_state(&anv->ctrl) != NVME_CTRL_LIVE) {
 		/*
 		 * From rdma.c:
 		 * If we are resetting, connecting or deleting we should
@@ -985,10 +986,10 @@ static void apple_nvme_reset_work(struct work_struct *work)
 	u32 boot_status, aqa;
 	struct apple_nvme *anv =
 		container_of(work, struct apple_nvme, ctrl.reset_work);
+	enum nvme_ctrl_state state = nvme_ctrl_state(&anv->ctrl);
 
-	if (anv->ctrl.state != NVME_CTRL_RESETTING) {
-		dev_warn(anv->dev, "ctrl state %d is not RESETTING\n",
-			 anv->ctrl.state);
+	if (state != NVME_CTRL_RESETTING) {
+		dev_warn(anv->dev, "ctrl state %d is not RESETTING\n", state);
 		ret = -ENODEV;
 		goto out;
 	}
@@ -1515,7 +1516,7 @@ static int apple_nvme_probe(struct platform_device *pdev)
 		goto put_dev;
 	}
 
-	anv->ctrl.admin_q = blk_mq_init_queue(&anv->admin_tagset);
+	anv->ctrl.admin_q = blk_mq_alloc_queue(&anv->admin_tagset, NULL, NULL);
 	if (IS_ERR(anv->ctrl.admin_q)) {
 		ret = -ENOMEM;
 		goto put_dev;
diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c
index 72c0525c75f5..a264b3ae078b 100644
--- a/drivers/nvme/host/auth.c
+++ b/drivers/nvme/host/auth.c
@@ -48,11 +48,6 @@ struct nvme_dhchap_queue_context {
 
 static struct workqueue_struct *nvme_auth_wq;
 
-#define nvme_auth_flags_from_qid(qid) \
-	(qid == 0) ? 0 : BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_RESERVED
-#define nvme_auth_queue_from_qid(ctrl, qid) \
-	(qid == 0) ? (ctrl)->fabrics_q : (ctrl)->connect_q
-
 static inline int ctrl_max_dhchaps(struct nvme_ctrl *ctrl)
 {
 	return ctrl->opts->nr_io_queues + ctrl->opts->nr_write_queues +
@@ -63,10 +58,15 @@ static int nvme_auth_submit(struct nvme_ctrl *ctrl, int qid,
 			    void *data, size_t data_len, bool auth_send)
 {
 	struct nvme_command cmd = {};
-	blk_mq_req_flags_t flags = nvme_auth_flags_from_qid(qid);
-	struct request_queue *q = nvme_auth_queue_from_qid(ctrl, qid);
+	nvme_submit_flags_t flags = NVME_SUBMIT_RETRY;
+	struct request_queue *q = ctrl->fabrics_q;
 	int ret;
 
+	if (qid != 0) {
+		flags |= NVME_SUBMIT_NOWAIT | NVME_SUBMIT_RESERVED;
+		q = ctrl->connect_q;
+	}
+
 	cmd.auth_common.opcode = nvme_fabrics_command;
 	cmd.auth_common.secp = NVME_AUTH_DHCHAP_PROTOCOL_IDENTIFIER;
 	cmd.auth_common.spsp0 = 0x01;
@@ -80,8 +80,7 @@ static int nvme_auth_submit(struct nvme_ctrl *ctrl, int qid,
 	}
 
 	ret = __nvme_submit_sync_cmd(q, &cmd, NULL, data, data_len,
-				     qid == 0 ? NVME_QID_ANY : qid,
-				     0, flags);
+				     qid == 0 ? NVME_QID_ANY : qid, flags);
 	if (ret > 0)
 		dev_warn(ctrl->device,
 			"qid %d auth_send failed with status %d\n", qid, ret);
@@ -897,7 +896,7 @@ static void nvme_ctrl_auth_work(struct work_struct *work)
 	 * If the ctrl is no connected, bail as reconnect will handle
 	 * authentication.
 	 */
-	if (ctrl->state != NVME_CTRL_LIVE)
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE)
 		return;
 
 	/* Authenticate admin queue first */
diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c
index 20f46c230885..6f2ebb5fcdb0 100644
--- a/drivers/nvme/host/constants.c
+++ b/drivers/nvme/host/constants.c
@@ -171,15 +171,15 @@ static const char * const nvme_statuses[] = {
 	[NVME_SC_HOST_ABORTED_CMD] = "Host Aborted Command",
 };
 
-const unsigned char *nvme_get_error_status_str(u16 status)
+const char *nvme_get_error_status_str(u16 status)
 {
 	status &= 0x7ff;
 	if (status < ARRAY_SIZE(nvme_statuses) && nvme_statuses[status])
-		return nvme_statuses[status & 0x7ff];
+		return nvme_statuses[status];
 	return "Unknown";
 }
 
-const unsigned char *nvme_get_opcode_str(u8 opcode)
+const char *nvme_get_opcode_str(u8 opcode)
 {
 	if (opcode < ARRAY_SIZE(nvme_ops) && nvme_ops[opcode])
 		return nvme_ops[opcode];
@@ -187,7 +187,7 @@ const unsigned char *nvme_get_opcode_str(u8 opcode)
 }
 EXPORT_SYMBOL_GPL(nvme_get_opcode_str);
 
-const unsigned char *nvme_get_admin_opcode_str(u8 opcode)
+const char *nvme_get_admin_opcode_str(u8 opcode)
 {
 	if (opcode < ARRAY_SIZE(nvme_admin_ops) && nvme_admin_ops[opcode])
 		return nvme_admin_ops[opcode];
@@ -195,7 +195,7 @@ const unsigned char *nvme_get_admin_opcode_str(u8 opcode)
 }
 EXPORT_SYMBOL_GPL(nvme_get_admin_opcode_str);
 
-const unsigned char *nvme_get_fabrics_opcode_str(u8 opcode) {
+const char *nvme_get_fabrics_opcode_str(u8 opcode) {
 	if (opcode < ARRAY_SIZE(nvme_fabrics_ops) && nvme_fabrics_ops[opcode])
 		return nvme_fabrics_ops[opcode];
 	return "Unknown";
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 0af612387083..00864a634470 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -114,12 +114,21 @@ static DEFINE_MUTEX(nvme_subsystems_lock);
 
 static DEFINE_IDA(nvme_instance_ida);
 static dev_t nvme_ctrl_base_chr_devt;
-static struct class *nvme_class;
-static struct class *nvme_subsys_class;
+static int nvme_class_uevent(const struct device *dev, struct kobj_uevent_env *env);
+static const struct class nvme_class = {
+	.name = "nvme",
+	.dev_uevent = nvme_class_uevent,
+};
+
+static const struct class nvme_subsys_class = {
+	.name = "nvme-subsystem",
+};
 
 static DEFINE_IDA(nvme_ns_chr_minor_ida);
 static dev_t nvme_ns_chr_devt;
-static struct class *nvme_ns_chr_class;
+static const struct class nvme_ns_chr_class = {
+	.name = "nvme-generic",
+};
 
 static void nvme_put_subsystem(struct nvme_subsystem *subsys);
 static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
@@ -338,6 +347,30 @@ static void nvme_log_error(struct request *req)
 			   nr->status & NVME_SC_DNR  ? "DNR "  : "");
 }
 
+static void nvme_log_err_passthru(struct request *req)
+{
+	struct nvme_ns *ns = req->q->queuedata;
+	struct nvme_request *nr = nvme_req(req);
+
+	pr_err_ratelimited("%s: %s(0x%x), %s (sct 0x%x / sc 0x%x) %s%s"
+		"cdw10=0x%x cdw11=0x%x cdw12=0x%x cdw13=0x%x cdw14=0x%x cdw15=0x%x\n",
+		ns ? ns->disk->disk_name : dev_name(nr->ctrl->device),
+		ns ? nvme_get_opcode_str(nr->cmd->common.opcode) :
+		     nvme_get_admin_opcode_str(nr->cmd->common.opcode),
+		nr->cmd->common.opcode,
+		nvme_get_error_status_str(nr->status),
+		nr->status >> 8 & 7,	/* Status Code Type */
+		nr->status & 0xff,	/* Status Code */
+		nr->status & NVME_SC_MORE ? "MORE " : "",
+		nr->status & NVME_SC_DNR  ? "DNR "  : "",
+		nr->cmd->common.cdw10,
+		nr->cmd->common.cdw11,
+		nr->cmd->common.cdw12,
+		nr->cmd->common.cdw13,
+		nr->cmd->common.cdw14,
+		nr->cmd->common.cdw14);
+}
+
 enum nvme_disposition {
 	COMPLETE,
 	RETRY,
@@ -385,8 +418,12 @@ static inline void nvme_end_req(struct request *req)
 {
 	blk_status_t status = nvme_error_status(nvme_req(req)->status);
 
-	if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET)))
-		nvme_log_error(req);
+	if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET))) {
+		if (blk_rq_is_passthrough(req))
+			nvme_log_err_passthru(req);
+		else
+			nvme_log_error(req);
+	}
 	nvme_end_req_zoned(req);
 	nvme_trace_bio_complete(req);
 	if (req->cmd_flags & REQ_NVME_MPATH)
@@ -679,10 +716,21 @@ static inline void nvme_clear_nvme_request(struct request *req)
 /* initialize a passthrough request */
 void nvme_init_request(struct request *req, struct nvme_command *cmd)
 {
-	if (req->q->queuedata)
+	struct nvme_request *nr = nvme_req(req);
+	bool logging_enabled;
+
+	if (req->q->queuedata) {
+		struct nvme_ns *ns = req->q->disk->private_data;
+
+		logging_enabled = ns->head->passthru_err_log_enabled;
 		req->timeout = NVME_IO_TIMEOUT;
-	else /* no queuedata implies admin queue */
+	} else { /* no queuedata implies admin queue */
+		logging_enabled = nr->ctrl->passthru_err_log_enabled;
 		req->timeout = NVME_ADMIN_TIMEOUT;
+	}
+
+	if (!logging_enabled)
+		req->rq_flags |= RQF_QUIET;
 
 	/* passthru commands should let the driver set the SGL flags */
 	cmd->common.flags &= ~NVME_CMD_SGL_ALL;
@@ -691,8 +739,7 @@ void nvme_init_request(struct request *req, struct nvme_command *cmd)
 	if (req->mq_hctx->type == HCTX_TYPE_POLL)
 		req->cmd_flags |= REQ_POLLED;
 	nvme_clear_nvme_request(req);
-	req->rq_flags |= RQF_QUIET;
-	memcpy(nvme_req(req)->cmd, cmd, sizeof(*cmd));
+	memcpy(nr->cmd, cmd, sizeof(*cmd));
 }
 EXPORT_SYMBOL_GPL(nvme_init_request);
 
@@ -721,7 +768,7 @@ blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
 EXPORT_SYMBOL_GPL(nvme_fail_nonready_command);
 
 bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
-		bool queue_live)
+		bool queue_live, enum nvme_ctrl_state state)
 {
 	struct nvme_request *req = nvme_req(rq);
 
@@ -742,7 +789,7 @@ bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		 * command, which is require to set the queue live in the
 		 * appropinquate states.
 		 */
-		switch (nvme_ctrl_state(ctrl)) {
+		switch (state) {
 		case NVME_CTRL_CONNECTING:
 			if (blk_rq_is_passthrough(rq) && nvme_is_fabrics(req->cmd) &&
 			    (req->cmd->fabrics.fctype == nvme_fabrics_type_connect ||
@@ -1051,20 +1098,27 @@ EXPORT_SYMBOL_NS_GPL(nvme_execute_rq, NVME_TARGET_PASSTHRU);
  */
 int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		union nvme_result *result, void *buffer, unsigned bufflen,
-		int qid, int at_head, blk_mq_req_flags_t flags)
+		int qid, nvme_submit_flags_t flags)
 {
 	struct request *req;
 	int ret;
+	blk_mq_req_flags_t blk_flags = 0;
 
+	if (flags & NVME_SUBMIT_NOWAIT)
+		blk_flags |= BLK_MQ_REQ_NOWAIT;
+	if (flags & NVME_SUBMIT_RESERVED)
+		blk_flags |= BLK_MQ_REQ_RESERVED;
 	if (qid == NVME_QID_ANY)
-		req = blk_mq_alloc_request(q, nvme_req_op(cmd), flags);
+		req = blk_mq_alloc_request(q, nvme_req_op(cmd), blk_flags);
 	else
-		req = blk_mq_alloc_request_hctx(q, nvme_req_op(cmd), flags,
+		req = blk_mq_alloc_request_hctx(q, nvme_req_op(cmd), blk_flags,
 						qid - 1);
 
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 	nvme_init_request(req, cmd);
+	if (flags & NVME_SUBMIT_RETRY)
+		req->cmd_flags &= ~REQ_FAILFAST_DRIVER;
 
 	if (buffer && bufflen) {
 		ret = blk_rq_map_kern(q, req, buffer, bufflen, GFP_KERNEL);
@@ -1072,7 +1126,7 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 			goto out;
 	}
 
-	ret = nvme_execute_rq(req, at_head);
+	ret = nvme_execute_rq(req, flags & NVME_SUBMIT_AT_HEAD);
 	if (result && ret >= 0)
 		*result = nvme_req(req)->result;
  out:
@@ -1085,7 +1139,7 @@ int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		void *buffer, unsigned bufflen)
 {
 	return __nvme_submit_sync_cmd(q, cmd, NULL, buffer, bufflen,
-			NVME_QID_ANY, 0, 0);
+			NVME_QID_ANY, 0);
 }
 EXPORT_SYMBOL_GPL(nvme_submit_sync_cmd);
 
@@ -1108,6 +1162,10 @@ u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode)
 		effects &= ~NVME_CMD_EFFECTS_CSE_MASK;
 	} else {
 		effects = le32_to_cpu(ctrl->effects->acs[opcode]);
+
+		/* Ignore execution restrictions if any relaxation bits are set */
+		if (effects & NVME_CMD_EFFECTS_CSER_MASK)
+			effects &= ~NVME_CMD_EFFECTS_CSE_MASK;
 	}
 
 	return effects;
@@ -1349,8 +1407,10 @@ static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
 
 	error = nvme_submit_sync_cmd(dev->admin_q, &c, *id,
 			sizeof(struct nvme_id_ctrl));
-	if (error)
+	if (error) {
 		kfree(*id);
+		*id = NULL;
+	}
 	return error;
 }
 
@@ -1479,6 +1539,7 @@ int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid,
 	if (error) {
 		dev_warn(ctrl->device, "Identify namespace failed (%d)\n", error);
 		kfree(*id);
+		*id = NULL;
 	}
 	return error;
 }
@@ -1560,7 +1621,7 @@ static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid,
 	c.features.dword11 = cpu_to_le32(dword11);
 
 	ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &res,
-			buffer, buflen, NVME_QID_ANY, 0, 0);
+			buffer, buflen, NVME_QID_ANY, 0);
 	if (ret >= 0 && result)
 		*result = le32_to_cpu(res.u32);
 	return ret;
@@ -1678,12 +1739,23 @@ int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return 0;
 }
 
-#ifdef CONFIG_BLK_DEV_INTEGRITY
-static void nvme_init_integrity(struct gendisk *disk,
-		struct nvme_ns_head *head, u32 max_integrity_segments)
+static bool nvme_init_integrity(struct gendisk *disk, struct nvme_ns_head *head)
 {
 	struct blk_integrity integrity = { };
 
+	blk_integrity_unregister(disk);
+
+	if (!head->ms)
+		return true;
+
+	/*
+	 * PI can always be supported as we can ask the controller to simply
+	 * insert/strip it, which is not possible for other kinds of metadata.
+	 */
+	if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) ||
+	    !(head->features & NVME_NS_METADATA_SUPPORTED))
+		return nvme_ns_has_pi(head);
+
 	switch (head->pi_type) {
 	case NVME_NS_DPS_PI_TYPE3:
 		switch (head->guard_type) {
@@ -1726,45 +1798,32 @@ static void nvme_init_integrity(struct gendisk *disk,
 	}
 
 	integrity.tuple_size = head->ms;
+	integrity.pi_offset = head->pi_offset;
 	blk_integrity_register(disk, &integrity);
-	blk_queue_max_integrity_segments(disk->queue, max_integrity_segments);
-}
-#else
-static void nvme_init_integrity(struct gendisk *disk,
-		struct nvme_ns_head *head, u32 max_integrity_segments)
-{
+	return true;
 }
-#endif /* CONFIG_BLK_DEV_INTEGRITY */
 
-static void nvme_config_discard(struct nvme_ctrl *ctrl, struct gendisk *disk,
-		struct nvme_ns_head *head)
+static void nvme_config_discard(struct nvme_ns *ns, struct queue_limits *lim)
 {
-	struct request_queue *queue = disk->queue;
-	u32 size = queue_logical_block_size(queue);
-
-	if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(head, UINT_MAX))
-		ctrl->max_discard_sectors =
-			nvme_lba_to_sect(head, ctrl->dmrsl);
-
-	if (ctrl->max_discard_sectors == 0) {
-		blk_queue_max_discard_sectors(queue, 0);
-		return;
-	}
+	struct nvme_ctrl *ctrl = ns->ctrl;
 
 	BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
 			NVME_DSM_MAX_RANGES);
 
-	queue->limits.discard_granularity = size;
-
-	/* If discard is already enabled, don't reset queue limits */
-	if (queue->limits.max_discard_sectors)
-		return;
+	if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(ns->head, UINT_MAX))
+		lim->max_hw_discard_sectors =
+			nvme_lba_to_sect(ns->head, ctrl->dmrsl);
+	else if (ctrl->oncs & NVME_CTRL_ONCS_DSM)
+		lim->max_hw_discard_sectors = UINT_MAX;
+	else
+		lim->max_hw_discard_sectors = 0;
 
-	blk_queue_max_discard_sectors(queue, ctrl->max_discard_sectors);
-	blk_queue_max_discard_segments(queue, ctrl->max_discard_segments);
+	lim->discard_granularity = lim->logical_block_size;
 
-	if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
-		blk_queue_max_write_zeroes_sectors(queue, UINT_MAX);
+	if (ctrl->dmrl)
+		lim->max_discard_segments = ctrl->dmrl;
+	else
+		lim->max_discard_segments = NVME_DSM_MAX_RANGES;
 }
 
 static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
@@ -1775,42 +1834,38 @@ static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
 		a->csi == b->csi;
 }
 
-static int nvme_init_ms(struct nvme_ctrl *ctrl, struct nvme_ns_head *head,
-		struct nvme_id_ns *id)
+static int nvme_identify_ns_nvm(struct nvme_ctrl *ctrl, unsigned int nsid,
+		struct nvme_id_ns_nvm **nvmp)
 {
-	bool first = id->dps & NVME_NS_DPS_PI_FIRST;
-	unsigned lbaf = nvme_lbaf_index(id->flbas);
-	struct nvme_command c = { };
+	struct nvme_command c = {
+		.identify.opcode	= nvme_admin_identify,
+		.identify.nsid		= cpu_to_le32(nsid),
+		.identify.cns		= NVME_ID_CNS_CS_NS,
+		.identify.csi		= NVME_CSI_NVM,
+	};
 	struct nvme_id_ns_nvm *nvm;
-	int ret = 0;
-	u32 elbaf;
-
-	head->pi_size = 0;
-	head->ms = le16_to_cpu(id->lbaf[lbaf].ms);
-	if (!(ctrl->ctratt & NVME_CTRL_ATTR_ELBAS)) {
-		head->pi_size = sizeof(struct t10_pi_tuple);
-		head->guard_type = NVME_NVM_NS_16B_GUARD;
-		goto set_pi;
-	}
+	int ret;
 
 	nvm = kzalloc(sizeof(*nvm), GFP_KERNEL);
 	if (!nvm)
 		return -ENOMEM;
 
-	c.identify.opcode = nvme_admin_identify;
-	c.identify.nsid = cpu_to_le32(head->ns_id);
-	c.identify.cns = NVME_ID_CNS_CS_NS;
-	c.identify.csi = NVME_CSI_NVM;
-
 	ret = nvme_submit_sync_cmd(ctrl->admin_q, &c, nvm, sizeof(*nvm));
 	if (ret)
-		goto free_data;
+		kfree(nvm);
+	else
+		*nvmp = nvm;
+	return ret;
+}
 
-	elbaf = le32_to_cpu(nvm->elbaf[lbaf]);
+static void nvme_configure_pi_elbas(struct nvme_ns_head *head,
+		struct nvme_id_ns *id, struct nvme_id_ns_nvm *nvm)
+{
+	u32 elbaf = le32_to_cpu(nvm->elbaf[nvme_lbaf_index(id->flbas)]);
 
 	/* no support for storage tag formats right now */
 	if (nvme_elbaf_sts(elbaf))
-		goto free_data;
+		return;
 
 	head->guard_type = nvme_elbaf_guard_type(elbaf);
 	switch (head->guard_type) {
@@ -1823,30 +1878,31 @@ static int nvme_init_ms(struct nvme_ctrl *ctrl, struct nvme_ns_head *head,
 	default:
 		break;
 	}
-
-free_data:
-	kfree(nvm);
-set_pi:
-	if (head->pi_size && (first || head->ms == head->pi_size))
-		head->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
-	else
-		head->pi_type = 0;
-
-	return ret;
 }
 
-static int nvme_configure_metadata(struct nvme_ctrl *ctrl,
-		struct nvme_ns_head *head, struct nvme_id_ns *id)
+static void nvme_configure_metadata(struct nvme_ctrl *ctrl,
+		struct nvme_ns_head *head, struct nvme_id_ns *id,
+		struct nvme_id_ns_nvm *nvm)
 {
-	int ret;
-
-	ret = nvme_init_ms(ctrl, head, id);
-	if (ret)
-		return ret;
-
 	head->features &= ~(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
+	head->pi_type = 0;
+	head->pi_size = 0;
+	head->pi_offset = 0;
+	head->ms = le16_to_cpu(id->lbaf[nvme_lbaf_index(id->flbas)].ms);
 	if (!head->ms || !(ctrl->ops->flags & NVME_F_METADATA_SUPPORTED))
-		return 0;
+		return;
+
+	if (nvm && (ctrl->ctratt & NVME_CTRL_ATTR_ELBAS)) {
+		nvme_configure_pi_elbas(head, id, nvm);
+	} else {
+		head->pi_size = sizeof(struct t10_pi_tuple);
+		head->guard_type = NVME_NVM_NS_16B_GUARD;
+	}
+
+	if (head->pi_size && head->ms >= head->pi_size)
+		head->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
+	if (!(id->dps & NVME_NS_DPS_PI_FIRST))
+		head->pi_offset = head->ms - head->pi_size;
 
 	if (ctrl->ops->flags & NVME_F_FABRICS) {
 		/*
@@ -1855,7 +1911,7 @@ static int nvme_configure_metadata(struct nvme_ctrl *ctrl,
 		 * remap the separate metadata buffer from the block layer.
 		 */
 		if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT)))
-			return 0;
+			return;
 
 		head->features |= NVME_NS_EXT_LBAS;
 
@@ -1882,33 +1938,32 @@ static int nvme_configure_metadata(struct nvme_ctrl *ctrl,
 		else
 			head->features |= NVME_NS_METADATA_SUPPORTED;
 	}
-	return 0;
 }
 
-static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
-		struct request_queue *q)
+static u32 nvme_max_drv_segments(struct nvme_ctrl *ctrl)
 {
-	bool vwc = ctrl->vwc & NVME_CTRL_VWC_PRESENT;
-
-	if (ctrl->max_hw_sectors) {
-		u32 max_segments =
-			(ctrl->max_hw_sectors / (NVME_CTRL_PAGE_SIZE >> 9)) + 1;
+	return ctrl->max_hw_sectors / (NVME_CTRL_PAGE_SIZE >> SECTOR_SHIFT) + 1;
+}
 
-		max_segments = min_not_zero(max_segments, ctrl->max_segments);
-		blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors);
-		blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX));
-	}
-	blk_queue_virt_boundary(q, NVME_CTRL_PAGE_SIZE - 1);
-	blk_queue_dma_alignment(q, 3);
-	blk_queue_write_cache(q, vwc, vwc);
+static void nvme_set_ctrl_limits(struct nvme_ctrl *ctrl,
+		struct queue_limits *lim)
+{
+	lim->max_hw_sectors = ctrl->max_hw_sectors;
+	lim->max_segments = min_t(u32, USHRT_MAX,
+		min_not_zero(nvme_max_drv_segments(ctrl), ctrl->max_segments));
+	lim->max_integrity_segments = ctrl->max_integrity_segments;
+	lim->virt_boundary_mask = NVME_CTRL_PAGE_SIZE - 1;
+	lim->max_segment_size = UINT_MAX;
+	lim->dma_alignment = 3;
 }
 
-static void nvme_update_disk_info(struct nvme_ctrl *ctrl, struct gendisk *disk,
-		struct nvme_ns_head *head, struct nvme_id_ns *id)
+static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id,
+		struct queue_limits *lim)
 {
-	sector_t capacity = nvme_lba_to_sect(head, le64_to_cpu(id->nsze));
+	struct nvme_ns_head *head = ns->head;
 	u32 bs = 1U << head->lba_shift;
 	u32 atomic_bs, phys_bs, io_opt = 0;
+	bool valid = true;
 
 	/*
 	 * The block layer can't support LBA sizes larger than the page size
@@ -1916,12 +1971,10 @@ static void nvme_update_disk_info(struct nvme_ctrl *ctrl, struct gendisk *disk,
 	 * allow block I/O.
 	 */
 	if (head->lba_shift > PAGE_SHIFT || head->lba_shift < SECTOR_SHIFT) {
-		capacity = 0;
 		bs = (1 << 9);
+		valid = false;
 	}
 
-	blk_integrity_unregister(disk);
-
 	atomic_bs = phys_bs = bs;
 	if (id->nabo == 0) {
 		/*
@@ -1932,7 +1985,7 @@ static void nvme_update_disk_info(struct nvme_ctrl *ctrl, struct gendisk *disk,
 		if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf)
 			atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
 		else
-			atomic_bs = (1 + ctrl->subsys->awupf) * bs;
+			atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
 	}
 
 	if (id->nsfeat & NVME_NS_FEAT_IO_OPT) {
@@ -1942,36 +1995,20 @@ static void nvme_update_disk_info(struct nvme_ctrl *ctrl, struct gendisk *disk,
 		io_opt = bs * (1 + le16_to_cpu(id->nows));
 	}
 
-	blk_queue_logical_block_size(disk->queue, bs);
 	/*
 	 * Linux filesystems assume writing a single physical block is
 	 * an atomic operation. Hence limit the physical block size to the
 	 * value of the Atomic Write Unit Power Fail parameter.
 	 */
-	blk_queue_physical_block_size(disk->queue, min(phys_bs, atomic_bs));
-	blk_queue_io_min(disk->queue, phys_bs);
-	blk_queue_io_opt(disk->queue, io_opt);
-
-	/*
-	 * Register a metadata profile for PI, or the plain non-integrity NVMe
-	 * metadata masquerading as Type 0 if supported, otherwise reject block
-	 * I/O to namespaces with metadata except when the namespace supports
-	 * PI, as it can strip/insert in that case.
-	 */
-	if (head->ms) {
-		if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) &&
-		    (head->features & NVME_NS_METADATA_SUPPORTED))
-			nvme_init_integrity(disk, head,
-					    ctrl->max_integrity_segments);
-		else if (!nvme_ns_has_pi(head))
-			capacity = 0;
-	}
-
-	set_capacity_and_notify(disk, capacity);
-
-	nvme_config_discard(ctrl, disk, head);
-	blk_queue_max_write_zeroes_sectors(disk->queue,
-					   ctrl->max_zeroes_sectors);
+	lim->logical_block_size = bs;
+	lim->physical_block_size = min(phys_bs, atomic_bs);
+	lim->io_min = phys_bs;
+	lim->io_opt = io_opt;
+	if (ns->ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
+		lim->max_write_zeroes_sectors = UINT_MAX;
+	else
+		lim->max_write_zeroes_sectors = ns->ctrl->max_zeroes_sectors;
+	return valid;
 }
 
 static bool nvme_ns_is_readonly(struct nvme_ns *ns, struct nvme_ns_info *info)
@@ -1985,7 +2022,8 @@ static inline bool nvme_first_scan(struct gendisk *disk)
 	return !disk_live(disk);
 }
 
-static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id)
+static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id,
+		struct queue_limits *lim)
 {
 	struct nvme_ctrl *ctrl = ns->ctrl;
 	u32 iob;
@@ -2013,38 +2051,36 @@ static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id)
 		return;
 	}
 
-	blk_queue_chunk_sectors(ns->queue, iob);
+	lim->chunk_sectors = iob;
 }
 
 static int nvme_update_ns_info_generic(struct nvme_ns *ns,
 		struct nvme_ns_info *info)
 {
+	struct queue_limits lim;
+	int ret;
+
 	blk_mq_freeze_queue(ns->disk->queue);
-	nvme_set_queue_limits(ns->ctrl, ns->queue);
+	lim = queue_limits_start_update(ns->disk->queue);
+	nvme_set_ctrl_limits(ns->ctrl, &lim);
+	ret = queue_limits_commit_update(ns->disk->queue, &lim);
 	set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
 	blk_mq_unfreeze_queue(ns->disk->queue);
 
-	if (nvme_ns_head_multipath(ns->head)) {
-		blk_mq_freeze_queue(ns->head->disk->queue);
-		set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
-		nvme_mpath_revalidate_paths(ns);
-		blk_stack_limits(&ns->head->disk->queue->limits,
-				 &ns->queue->limits, 0);
-		ns->head->disk->flags |= GENHD_FL_HIDDEN;
-		blk_mq_unfreeze_queue(ns->head->disk->queue);
-	}
-
 	/* Hide the block-interface for these devices */
-	ns->disk->flags |= GENHD_FL_HIDDEN;
-	set_bit(NVME_NS_READY, &ns->flags);
-
-	return 0;
+	if (!ret)
+		ret = -ENODEV;
+	return ret;
 }
 
 static int nvme_update_ns_info_block(struct nvme_ns *ns,
 		struct nvme_ns_info *info)
 {
+	bool vwc = ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT;
+	struct queue_limits lim;
+	struct nvme_id_ns_nvm *nvm = NULL;
 	struct nvme_id_ns *id;
+	sector_t capacity;
 	unsigned lbaf;
 	int ret;
 
@@ -2056,30 +2092,52 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 		/* namespace not allocated or attached */
 		info->is_removed = true;
 		ret = -ENODEV;
-		goto error;
+		goto out;
+	}
+
+	if (ns->ctrl->ctratt & NVME_CTRL_ATTR_ELBAS) {
+		ret = nvme_identify_ns_nvm(ns->ctrl, info->nsid, &nvm);
+		if (ret < 0)
+			goto out;
 	}
 
 	blk_mq_freeze_queue(ns->disk->queue);
 	lbaf = nvme_lbaf_index(id->flbas);
 	ns->head->lba_shift = id->lbaf[lbaf].ds;
 	ns->head->nuse = le64_to_cpu(id->nuse);
-	nvme_set_queue_limits(ns->ctrl, ns->queue);
+	capacity = nvme_lba_to_sect(ns->head, le64_to_cpu(id->nsze));
 
-	ret = nvme_configure_metadata(ns->ctrl, ns->head, id);
-	if (ret < 0) {
-		blk_mq_unfreeze_queue(ns->disk->queue);
-		goto out;
-	}
-	nvme_set_chunk_sectors(ns, id);
-	nvme_update_disk_info(ns->ctrl, ns->disk, ns->head, id);
-
-	if (ns->head->ids.csi == NVME_CSI_ZNS) {
-		ret = nvme_update_zone_info(ns, lbaf);
+	lim = queue_limits_start_update(ns->disk->queue);
+	nvme_set_ctrl_limits(ns->ctrl, &lim);
+	nvme_configure_metadata(ns->ctrl, ns->head, id, nvm);
+	nvme_set_chunk_sectors(ns, id, &lim);
+	if (!nvme_update_disk_info(ns, id, &lim))
+		capacity = 0;
+	nvme_config_discard(ns, &lim);
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+	    ns->head->ids.csi == NVME_CSI_ZNS) {
+		ret = nvme_update_zone_info(ns, lbaf, &lim);
 		if (ret) {
 			blk_mq_unfreeze_queue(ns->disk->queue);
 			goto out;
 		}
 	}
+	ret = queue_limits_commit_update(ns->disk->queue, &lim);
+	if (ret) {
+		blk_mq_unfreeze_queue(ns->disk->queue);
+		goto out;
+	}
+
+	/*
+	 * Register a metadata profile for PI, or the plain non-integrity NVMe
+	 * metadata masquerading as Type 0 if supported, otherwise reject block
+	 * I/O to namespaces with metadata except when the namespace supports
+	 * PI, as it can strip/insert in that case.
+	 */
+	if (!nvme_init_integrity(ns->disk, ns->head))
+		capacity = 0;
+
+	set_capacity_and_notify(ns->disk, capacity);
 
 	/*
 	 * Only set the DEAC bit if the device guarantees that reads from
@@ -2090,62 +2148,81 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	if ((id->dlfeat & 0x7) == 0x1 && (id->dlfeat & (1 << 3)))
 		ns->head->features |= NVME_NS_DEAC;
 	set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
+	blk_queue_write_cache(ns->disk->queue, vwc, vwc);
 	set_bit(NVME_NS_READY, &ns->flags);
 	blk_mq_unfreeze_queue(ns->disk->queue);
 
 	if (blk_queue_is_zoned(ns->queue)) {
-		ret = nvme_revalidate_zones(ns);
+		ret = blk_revalidate_disk_zones(ns->disk, NULL);
 		if (ret && !nvme_first_scan(ns->disk))
 			goto out;
 	}
 
-	if (nvme_ns_head_multipath(ns->head)) {
-		blk_mq_freeze_queue(ns->head->disk->queue);
-		nvme_update_disk_info(ns->ctrl, ns->head->disk, ns->head, id);
-		set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
-		nvme_mpath_revalidate_paths(ns);
-		blk_stack_limits(&ns->head->disk->queue->limits,
-				 &ns->queue->limits, 0);
-		disk_update_readahead(ns->head->disk);
-		blk_mq_unfreeze_queue(ns->head->disk->queue);
-	}
-
 	ret = 0;
 out:
-	/*
-	 * If probing fails due an unsupported feature, hide the block device,
-	 * but still allow other access.
-	 */
-	if (ret == -ENODEV) {
-		ns->disk->flags |= GENHD_FL_HIDDEN;
-		set_bit(NVME_NS_READY, &ns->flags);
-		ret = 0;
-	}
-
-error:
+	kfree(nvm);
 	kfree(id);
 	return ret;
 }
 
 static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
 {
+	bool unsupported = false;
+	int ret;
+
 	switch (info->ids.csi) {
 	case NVME_CSI_ZNS:
 		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
 			dev_info(ns->ctrl->device,
 	"block device for nsid %u not supported without CONFIG_BLK_DEV_ZONED\n",
 				info->nsid);
-			return nvme_update_ns_info_generic(ns, info);
+			ret = nvme_update_ns_info_generic(ns, info);
+			break;
 		}
-		return nvme_update_ns_info_block(ns, info);
+		ret = nvme_update_ns_info_block(ns, info);
+		break;
 	case NVME_CSI_NVM:
-		return nvme_update_ns_info_block(ns, info);
+		ret = nvme_update_ns_info_block(ns, info);
+		break;
 	default:
 		dev_info(ns->ctrl->device,
 			"block device for nsid %u not supported (csi %u)\n",
 			info->nsid, info->ids.csi);
-		return nvme_update_ns_info_generic(ns, info);
+		ret = nvme_update_ns_info_generic(ns, info);
+		break;
+	}
+
+	/*
+	 * If probing fails due an unsupported feature, hide the block device,
+	 * but still allow other access.
+	 */
+	if (ret == -ENODEV) {
+		ns->disk->flags |= GENHD_FL_HIDDEN;
+		set_bit(NVME_NS_READY, &ns->flags);
+		unsupported = true;
+		ret = 0;
+	}
+
+	if (!ret && nvme_ns_head_multipath(ns->head)) {
+		struct queue_limits lim;
+
+		blk_mq_freeze_queue(ns->head->disk->queue);
+		if (unsupported)
+			ns->head->disk->flags |= GENHD_FL_HIDDEN;
+		else
+			nvme_init_integrity(ns->head->disk, ns->head);
+		set_capacity_and_notify(ns->head->disk, get_capacity(ns->disk));
+		set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
+		nvme_mpath_revalidate_paths(ns);
+
+		lim = queue_limits_start_update(ns->head->disk->queue);
+		queue_limits_stack_bdev(&lim, ns->disk->part0, 0,
+					ns->head->disk->disk_name);
+		ret = queue_limits_commit_update(ns->head->disk->queue, &lim);
+		blk_mq_unfreeze_queue(ns->head->disk->queue);
 	}
+
+	return ret;
 }
 
 #ifdef CONFIG_BLK_SED_OPAL
@@ -2164,7 +2241,7 @@ static int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t l
 	cmd.common.cdw11 = cpu_to_le32(len);
 
 	return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len,
-			NVME_QID_ANY, 1, 0);
+			NVME_QID_ANY, NVME_SUBMIT_AT_HEAD);
 }
 
 static void nvme_configure_opal(struct nvme_ctrl *ctrl, bool was_suspended)
@@ -2820,7 +2897,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	subsys->awupf = le16_to_cpu(id->awupf);
 	nvme_mpath_default_iopolicy(subsys);
 
-	subsys->dev.class = nvme_subsys_class;
+	subsys->dev.class = &nvme_subsys_class;
 	subsys->dev.release = nvme_release_subsystem;
 	subsys->dev.groups = nvme_subsys_attrs_groups;
 	dev_set_name(&subsys->dev, "nvme-subsys%d", ctrl->instance);
@@ -2930,14 +3007,6 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl)
 	struct nvme_id_ctrl_nvm *id;
 	int ret;
 
-	if (ctrl->oncs & NVME_CTRL_ONCS_DSM) {
-		ctrl->max_discard_sectors = UINT_MAX;
-		ctrl->max_discard_segments = NVME_DSM_MAX_RANGES;
-	} else {
-		ctrl->max_discard_sectors = 0;
-		ctrl->max_discard_segments = 0;
-	}
-
 	/*
 	 * Even though NVMe spec explicitly states that MDTS is not applicable
 	 * to the write-zeroes, we are cautious and limit the size to the
@@ -2967,8 +3036,7 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl)
 	if (ret)
 		goto free_data;
 
-	if (id->dmrl)
-		ctrl->max_discard_segments = id->dmrl;
+	ctrl->dmrl = id->dmrl;
 	ctrl->dmrsl = le32_to_cpu(id->dmrsl);
 	if (id->wzsl)
 		ctrl->max_zeroes_sectors = nvme_mps_to_sectors(ctrl, id->wzsl);
@@ -3069,11 +3137,17 @@ static int nvme_check_ctrl_fabric_info(struct nvme_ctrl *ctrl, struct nvme_id_ct
 		return -EINVAL;
 	}
 
+	if (!ctrl->maxcmd) {
+		dev_err(ctrl->device, "Maximum outstanding commands is 0\n");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
 static int nvme_init_identify(struct nvme_ctrl *ctrl)
 {
+	struct queue_limits lim;
 	struct nvme_id_ctrl *id;
 	u32 max_hw_sectors;
 	bool prev_apst_enabled;
@@ -3140,7 +3214,12 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl)
 	ctrl->max_hw_sectors =
 		min_not_zero(ctrl->max_hw_sectors, max_hw_sectors);
 
-	nvme_set_queue_limits(ctrl, ctrl->admin_q);
+	lim = queue_limits_start_update(ctrl->admin_q);
+	nvme_set_ctrl_limits(ctrl, &lim);
+	ret = queue_limits_commit_update(ctrl->admin_q, &lim);
+	if (ret)
+		goto out_free;
+
 	ctrl->sgls = le32_to_cpu(id->sgls);
 	ctrl->kas = le16_to_cpu(id->kas);
 	ctrl->max_namespaces = le32_to_cpu(id->mnan);
@@ -3372,7 +3451,7 @@ int nvme_cdev_add(struct cdev *cdev, struct device *cdev_device,
 	if (minor < 0)
 		return minor;
 	cdev_device->devt = MKDEV(MAJOR(nvme_ns_chr_devt), minor);
-	cdev_device->class = nvme_ns_chr_class;
+	cdev_device->class = &nvme_ns_chr_class;
 	cdev_device->release = nvme_cdev_rel;
 	device_initialize(cdev_device);
 	cdev_init(cdev, fops);
@@ -3644,7 +3723,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 	if (!ns)
 		return;
 
-	disk = blk_mq_alloc_disk(ctrl->tagset, ns);
+	disk = blk_mq_alloc_disk(ctrl->tagset, NULL, ns);
 	if (IS_ERR(disk))
 		goto out_free_ns;
 	disk->fops = &nvme_bdev_ops;
@@ -3715,6 +3794,13 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 	nvme_mpath_add_disk(ns, info->anagrpid);
 	nvme_fault_inject_init(&ns->fault_inject, ns->disk->disk_name);
 
+	/*
+	 * Set ns->disk->device->driver_data to ns so we can access
+	 * ns->head->passthru_err_log_enabled in
+	 * nvme_io_passthru_err_log_enabled_[store | show]().
+	 */
+	dev_set_drvdata(disk_to_dev(ns->disk), ns);
+
 	return;
 
  out_cleanup_ns_from_list:
@@ -4139,6 +4225,7 @@ static bool nvme_ctrl_pp_status(struct nvme_ctrl *ctrl)
 static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
 {
 	struct nvme_fw_slot_info_log *log;
+	u8 next_fw_slot, cur_fw_slot;
 
 	log = kmalloc(sizeof(*log), GFP_KERNEL);
 	if (!log)
@@ -4150,13 +4237,15 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
 		goto out_free_log;
 	}
 
-	if (log->afi & 0x70 || !(log->afi & 0x7)) {
+	cur_fw_slot = log->afi & 0x7;
+	next_fw_slot = (log->afi & 0x70) >> 4;
+	if (!cur_fw_slot || (next_fw_slot && (cur_fw_slot != next_fw_slot))) {
 		dev_info(ctrl->device,
 			 "Firmware is activated after next Controller Level Reset\n");
 		goto out_free_log;
 	}
 
-	memcpy(ctrl->subsys->firmware_rev, &log->frs[(log->afi & 0x7) - 1],
+	memcpy(ctrl->subsys->firmware_rev, &log->frs[cur_fw_slot - 1],
 		sizeof(ctrl->subsys->firmware_rev));
 
 out_free_log:
@@ -4295,6 +4384,7 @@ EXPORT_SYMBOL_GPL(nvme_complete_async_event);
 int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 		const struct blk_mq_ops *ops, unsigned int cmd_size)
 {
+	struct queue_limits lim = {};
 	int ret;
 
 	memset(set, 0, sizeof(*set));
@@ -4314,14 +4404,14 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 	if (ret)
 		return ret;
 
-	ctrl->admin_q = blk_mq_init_queue(set);
+	ctrl->admin_q = blk_mq_alloc_queue(set, &lim, NULL);
 	if (IS_ERR(ctrl->admin_q)) {
 		ret = PTR_ERR(ctrl->admin_q);
 		goto out_free_tagset;
 	}
 
 	if (ctrl->ops->flags & NVME_F_FABRICS) {
-		ctrl->fabrics_q = blk_mq_init_queue(set);
+		ctrl->fabrics_q = blk_mq_alloc_queue(set, NULL, NULL);
 		if (IS_ERR(ctrl->fabrics_q)) {
 			ret = PTR_ERR(ctrl->fabrics_q);
 			goto out_cleanup_admin_q;
@@ -4385,7 +4475,7 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 		return ret;
 
 	if (ctrl->ops->flags & NVME_F_FABRICS) {
-		ctrl->connect_q = blk_mq_init_queue(set);
+		ctrl->connect_q = blk_mq_alloc_queue(set, NULL, NULL);
         	if (IS_ERR(ctrl->connect_q)) {
 			ret = PTR_ERR(ctrl->connect_q);
 			goto out_free_tag_set;
@@ -4515,6 +4605,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	int ret;
 
 	WRITE_ONCE(ctrl->state, NVME_CTRL_NEW);
+	ctrl->passthru_err_log_enabled = false;
 	clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
 	spin_lock_init(&ctrl->lock);
 	mutex_init(&ctrl->scan_lock);
@@ -4554,7 +4645,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	ctrl->device = &ctrl->ctrl_device;
 	ctrl->device->devt = MKDEV(MAJOR(nvme_ctrl_base_chr_devt),
 			ctrl->instance);
-	ctrl->device->class = nvme_class;
+	ctrl->device->class = &nvme_class;
 	ctrl->device->parent = ctrl->dev;
 	if (ops->dev_attr_groups)
 		ctrl->device->groups = ops->dev_attr_groups;
@@ -4787,42 +4878,36 @@ static int __init nvme_core_init(void)
 	if (result < 0)
 		goto destroy_delete_wq;
 
-	nvme_class = class_create("nvme");
-	if (IS_ERR(nvme_class)) {
-		result = PTR_ERR(nvme_class);
+	result = class_register(&nvme_class);
+	if (result)
 		goto unregister_chrdev;
-	}
-	nvme_class->dev_uevent = nvme_class_uevent;
 
-	nvme_subsys_class = class_create("nvme-subsystem");
-	if (IS_ERR(nvme_subsys_class)) {
-		result = PTR_ERR(nvme_subsys_class);
+	result = class_register(&nvme_subsys_class);
+	if (result)
 		goto destroy_class;
-	}
 
 	result = alloc_chrdev_region(&nvme_ns_chr_devt, 0, NVME_MINORS,
 				     "nvme-generic");
 	if (result < 0)
 		goto destroy_subsys_class;
 
-	nvme_ns_chr_class = class_create("nvme-generic");
-	if (IS_ERR(nvme_ns_chr_class)) {
-		result = PTR_ERR(nvme_ns_chr_class);
+	result = class_register(&nvme_ns_chr_class);
+	if (result)
 		goto unregister_generic_ns;
-	}
+
 	result = nvme_init_auth();
 	if (result)
 		goto destroy_ns_chr;
 	return 0;
 
 destroy_ns_chr:
-	class_destroy(nvme_ns_chr_class);
+	class_unregister(&nvme_ns_chr_class);
 unregister_generic_ns:
 	unregister_chrdev_region(nvme_ns_chr_devt, NVME_MINORS);
 destroy_subsys_class:
-	class_destroy(nvme_subsys_class);
+	class_unregister(&nvme_subsys_class);
 destroy_class:
-	class_destroy(nvme_class);
+	class_unregister(&nvme_class);
 unregister_chrdev:
 	unregister_chrdev_region(nvme_ctrl_base_chr_devt, NVME_MINORS);
 destroy_delete_wq:
@@ -4838,9 +4923,9 @@ out:
 static void __exit nvme_core_exit(void)
 {
 	nvme_exit_auth();
-	class_destroy(nvme_ns_chr_class);
-	class_destroy(nvme_subsys_class);
-	class_destroy(nvme_class);
+	class_unregister(&nvme_ns_chr_class);
+	class_unregister(&nvme_subsys_class);
+	class_unregister(&nvme_class);
 	unregister_chrdev_region(nvme_ns_chr_devt, NVME_MINORS);
 	unregister_chrdev_region(nvme_ctrl_base_chr_devt, NVME_MINORS);
 	destroy_workqueue(nvme_delete_wq);
@@ -4852,5 +4937,6 @@ static void __exit nvme_core_exit(void)
 
 MODULE_LICENSE("GPL");
 MODULE_VERSION("1.0");
+MODULE_DESCRIPTION("NVMe host core framework");
 module_init(nvme_core_init);
 module_exit(nvme_core_exit);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index b5752a77ad98..1f0ea1f32d22 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -180,7 +180,7 @@ int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val)
 	cmd.prop_get.offset = cpu_to_le32(off);
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0,
-			NVME_QID_ANY, 0, 0);
+			NVME_QID_ANY, 0);
 
 	if (ret >= 0)
 		*val = le64_to_cpu(res.u64);
@@ -226,7 +226,7 @@ int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
 	cmd.prop_get.offset = cpu_to_le32(off);
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0,
-			NVME_QID_ANY, 0, 0);
+			NVME_QID_ANY, 0);
 
 	if (ret >= 0)
 		*val = le64_to_cpu(res.u64);
@@ -271,7 +271,7 @@ int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
 	cmd.prop_set.value = cpu_to_le64(val);
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, NULL, NULL, 0,
-			NVME_QID_ANY, 0, 0);
+			NVME_QID_ANY, 0);
 	if (unlikely(ret))
 		dev_err(ctrl->device,
 			"Property Set error: %d, offset %#x\n",
@@ -450,8 +450,10 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
 		return -ENOMEM;
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res,
-			data, sizeof(*data), NVME_QID_ANY, 1,
-			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
+			data, sizeof(*data), NVME_QID_ANY,
+			NVME_SUBMIT_AT_HEAD |
+			NVME_SUBMIT_NOWAIT |
+			NVME_SUBMIT_RESERVED);
 	if (ret) {
 		nvmf_log_connect_error(ctrl, ret, le32_to_cpu(res.u32),
 				       &cmd, data);
@@ -525,11 +527,14 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid)
 		return -ENOMEM;
 
 	ret = __nvme_submit_sync_cmd(ctrl->connect_q, &cmd, &res,
-			data, sizeof(*data), qid, 1,
-			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
+			data, sizeof(*data), qid,
+			NVME_SUBMIT_AT_HEAD |
+			NVME_SUBMIT_RESERVED |
+			NVME_SUBMIT_NOWAIT);
 	if (ret) {
 		nvmf_log_connect_error(ctrl, ret, le32_to_cpu(res.u32),
 				       &cmd, data);
+		goto out_free_data;
 	}
 	result = le32_to_cpu(res.u32);
 	if (result & (NVME_CONNECT_AUTHREQ_ATR | NVME_CONNECT_AUTHREQ_ASCR)) {
@@ -633,7 +638,7 @@ static struct key *nvmf_parse_key(int key_id)
 	}
 
 	key = key_lookup(key_id);
-	if (!IS_ERR(key))
+	if (IS_ERR(key))
 		pr_err("key id %08x not found\n", key_id);
 	else
 		pr_debug("Using key id %08x\n", key_id);
@@ -1314,7 +1319,10 @@ out_free_opts:
 	return ERR_PTR(ret);
 }
 
-static struct class *nvmf_class;
+static const struct class nvmf_class = {
+	.name = "nvme-fabrics",
+};
+
 static struct device *nvmf_device;
 static DEFINE_MUTEX(nvmf_dev_mutex);
 
@@ -1434,15 +1442,14 @@ static int __init nvmf_init(void)
 	if (!nvmf_default_host)
 		return -ENOMEM;
 
-	nvmf_class = class_create("nvme-fabrics");
-	if (IS_ERR(nvmf_class)) {
+	ret = class_register(&nvmf_class);
+	if (ret) {
 		pr_err("couldn't register class nvme-fabrics\n");
-		ret = PTR_ERR(nvmf_class);
 		goto out_free_host;
 	}
 
 	nvmf_device =
-		device_create(nvmf_class, NULL, MKDEV(0, 0), NULL, "ctl");
+		device_create(&nvmf_class, NULL, MKDEV(0, 0), NULL, "ctl");
 	if (IS_ERR(nvmf_device)) {
 		pr_err("couldn't create nvme-fabrics device!\n");
 		ret = PTR_ERR(nvmf_device);
@@ -1458,9 +1465,9 @@ static int __init nvmf_init(void)
 	return 0;
 
 out_destroy_device:
-	device_destroy(nvmf_class, MKDEV(0, 0));
+	device_destroy(&nvmf_class, MKDEV(0, 0));
 out_destroy_class:
-	class_destroy(nvmf_class);
+	class_unregister(&nvmf_class);
 out_free_host:
 	nvmf_host_put(nvmf_default_host);
 	return ret;
@@ -1469,8 +1476,8 @@ out_free_host:
 static void __exit nvmf_exit(void)
 {
 	misc_deregister(&nvmf_misc);
-	device_destroy(nvmf_class, MKDEV(0, 0));
-	class_destroy(nvmf_class);
+	device_destroy(&nvmf_class, MKDEV(0, 0));
+	class_unregister(&nvmf_class);
 	nvmf_host_put(nvmf_default_host);
 
 	BUILD_BUG_ON(sizeof(struct nvmf_common_command) != 64);
@@ -1488,6 +1495,7 @@ static void __exit nvmf_exit(void)
 }
 
 MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("NVMe host fabrics library");
 
 module_init(nvmf_init);
 module_exit(nvmf_exit);
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index fbaee5a7be19..06cc54851b1b 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -185,9 +185,11 @@ static inline bool
 nvmf_ctlr_matches_baseopts(struct nvme_ctrl *ctrl,
 			struct nvmf_ctrl_options *opts)
 {
-	if (ctrl->state == NVME_CTRL_DELETING ||
-	    ctrl->state == NVME_CTRL_DELETING_NOIO ||
-	    ctrl->state == NVME_CTRL_DEAD ||
+	enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
+
+	if (state == NVME_CTRL_DELETING ||
+	    state == NVME_CTRL_DELETING_NOIO ||
+	    state == NVME_CTRL_DEAD ||
 	    strcmp(opts->subsysnqn, ctrl->opts->subsysnqn) ||
 	    strcmp(opts->host->nqn, ctrl->opts->host->nqn) ||
 	    !uuid_equal(&opts->host->id, &ctrl->opts->host->id))
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 16847a316421..68a5d971657b 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -221,11 +221,6 @@ static LIST_HEAD(nvme_fc_lport_list);
 static DEFINE_IDA(nvme_fc_local_port_cnt);
 static DEFINE_IDA(nvme_fc_ctrl_cnt);
 
-static struct workqueue_struct *nvme_fc_wq;
-
-static bool nvme_fc_waiting_to_unload;
-static DECLARE_COMPLETION(nvme_fc_unload_proceed);
-
 /*
  * These items are short-term. They will eventually be moved into
  * a generic FC class. See comments in module init.
@@ -255,8 +250,6 @@ nvme_fc_free_lport(struct kref *ref)
 	/* remove from transport list */
 	spin_lock_irqsave(&nvme_fc_lock, flags);
 	list_del(&lport->port_list);
-	if (nvme_fc_waiting_to_unload && list_empty(&nvme_fc_lport_list))
-		complete(&nvme_fc_unload_proceed);
 	spin_unlock_irqrestore(&nvme_fc_lock, flags);
 
 	ida_free(&nvme_fc_local_port_cnt, lport->localport.port_num);
@@ -2574,6 +2567,7 @@ static enum blk_eh_timer_return nvme_fc_timeout(struct request *rq)
 {
 	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
 	struct nvme_fc_ctrl *ctrl = op->ctrl;
+	u16 qnum = op->queue->qnum;
 	struct nvme_fc_cmd_iu *cmdiu = &op->cmd_iu;
 	struct nvme_command *sqe = &cmdiu->sqe;
 
@@ -2582,10 +2576,11 @@ static enum blk_eh_timer_return nvme_fc_timeout(struct request *rq)
 	 * will detect the aborted io and will fail the connection.
 	 */
 	dev_info(ctrl->ctrl.device,
-		"NVME-FC{%d.%d}: io timeout: opcode %d fctype %d w10/11: "
+		"NVME-FC{%d.%d}: io timeout: opcode %d fctype %d (%s) w10/11: "
 		"x%08x/x%08x\n",
-		ctrl->cnum, op->queue->qnum, sqe->common.opcode,
-		sqe->connect.fctype, sqe->common.cdw10, sqe->common.cdw11);
+		ctrl->cnum, qnum, sqe->common.opcode, sqe->fabrics.fctype,
+		nvme_fabrics_opcode_str(qnum, sqe),
+		sqe->common.cdw10, sqe->common.cdw11);
 	if (__nvme_fc_abort_op(ctrl, op))
 		nvme_fc_error_recovery(ctrl, "io timeout abort failed");
 
@@ -3575,8 +3570,8 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	flush_delayed_work(&ctrl->connect_work);
 
 	dev_info(ctrl->ctrl.device,
-		"NVME-FC{%d}: new ctrl: NQN \"%s\"\n",
-		ctrl->cnum, nvmf_ctrl_subsysnqn(&ctrl->ctrl));
+		"NVME-FC{%d}: new ctrl: NQN \"%s\", hostnqn: %s\n",
+		ctrl->cnum, nvmf_ctrl_subsysnqn(&ctrl->ctrl), opts->host->nqn);
 
 	return &ctrl->ctrl;
 
@@ -3894,10 +3889,6 @@ static int __init nvme_fc_init_module(void)
 {
 	int ret;
 
-	nvme_fc_wq = alloc_workqueue("nvme_fc_wq", WQ_MEM_RECLAIM, 0);
-	if (!nvme_fc_wq)
-		return -ENOMEM;
-
 	/*
 	 * NOTE:
 	 * It is expected that in the future the kernel will combine
@@ -3915,7 +3906,7 @@ static int __init nvme_fc_init_module(void)
 	ret = class_register(&fc_class);
 	if (ret) {
 		pr_err("couldn't register class fc\n");
-		goto out_destroy_wq;
+		return ret;
 	}
 
 	/*
@@ -3939,8 +3930,6 @@ out_destroy_device:
 	device_destroy(&fc_class, MKDEV(0, 0));
 out_destroy_class:
 	class_unregister(&fc_class);
-out_destroy_wq:
-	destroy_workqueue(nvme_fc_wq);
 
 	return ret;
 }
@@ -3960,48 +3949,27 @@ nvme_fc_delete_controllers(struct nvme_fc_rport *rport)
 	spin_unlock(&rport->lock);
 }
 
-static void
-nvme_fc_cleanup_for_unload(void)
+static void __exit nvme_fc_exit_module(void)
 {
 	struct nvme_fc_lport *lport;
 	struct nvme_fc_rport *rport;
-
-	list_for_each_entry(lport, &nvme_fc_lport_list, port_list) {
-		list_for_each_entry(rport, &lport->endp_list, endp_list) {
-			nvme_fc_delete_controllers(rport);
-		}
-	}
-}
-
-static void __exit nvme_fc_exit_module(void)
-{
 	unsigned long flags;
-	bool need_cleanup = false;
 
 	spin_lock_irqsave(&nvme_fc_lock, flags);
-	nvme_fc_waiting_to_unload = true;
-	if (!list_empty(&nvme_fc_lport_list)) {
-		need_cleanup = true;
-		nvme_fc_cleanup_for_unload();
-	}
+	list_for_each_entry(lport, &nvme_fc_lport_list, port_list)
+		list_for_each_entry(rport, &lport->endp_list, endp_list)
+			nvme_fc_delete_controllers(rport);
 	spin_unlock_irqrestore(&nvme_fc_lock, flags);
-	if (need_cleanup) {
-		pr_info("%s: waiting for ctlr deletes\n", __func__);
-		wait_for_completion(&nvme_fc_unload_proceed);
-		pr_info("%s: ctrl deletes complete\n", __func__);
-	}
+	flush_workqueue(nvme_delete_wq);
 
 	nvmf_unregister_transport(&nvme_fc_transport);
 
-	ida_destroy(&nvme_fc_local_port_cnt);
-	ida_destroy(&nvme_fc_ctrl_cnt);
-
 	device_destroy(&fc_class, MKDEV(0, 0));
 	class_unregister(&fc_class);
-	destroy_workqueue(nvme_fc_wq);
 }
 
 module_init(nvme_fc_init_module);
 module_exit(nvme_fc_exit_module);
 
+MODULE_DESCRIPTION("NVMe host FC transport driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 18f5c1be5d67..3dfd5ae99ae0 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -228,7 +228,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	length = (io.nblocks + 1) << ns->head->lba_shift;
 
 	if ((io.control & NVME_RW_PRINFO_PRACT) &&
-	    ns->head->ms == sizeof(struct t10_pi_tuple)) {
+	    (ns->head->ms == ns->head->pi_size)) {
 		/*
 		 * Protection information is stripped/inserted by the
 		 * controller.
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 2dd4137a08b2..5397fb428b24 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -156,7 +156,7 @@ void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 		if (!ns->head->disk)
 			continue;
 		kblockd_schedule_work(&ns->head->requeue_work);
-		if (ctrl->state == NVME_CTRL_LIVE)
+		if (nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE)
 			disk_uevent(ns->head->disk, KOBJ_CHANGE);
 	}
 	up_read(&ctrl->namespaces_rwsem);
@@ -223,13 +223,14 @@ void nvme_mpath_revalidate_paths(struct nvme_ns *ns)
 
 static bool nvme_path_is_disabled(struct nvme_ns *ns)
 {
+	enum nvme_ctrl_state state = nvme_ctrl_state(ns->ctrl);
+
 	/*
 	 * We don't treat NVME_CTRL_DELETING as a disabled path as I/O should
 	 * still be able to complete assuming that the controller is connected.
 	 * Otherwise it will fail immediately and return to the requeue list.
 	 */
-	if (ns->ctrl->state != NVME_CTRL_LIVE &&
-	    ns->ctrl->state != NVME_CTRL_DELETING)
+	if (state != NVME_CTRL_LIVE && state != NVME_CTRL_DELETING)
 		return true;
 	if (test_bit(NVME_NS_ANA_PENDING, &ns->flags) ||
 	    !test_bit(NVME_NS_READY, &ns->flags))
@@ -331,7 +332,7 @@ out:
 
 static inline bool nvme_path_is_optimized(struct nvme_ns *ns)
 {
-	return ns->ctrl->state == NVME_CTRL_LIVE &&
+	return nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE &&
 		ns->ana_state == NVME_ANA_OPTIMIZED;
 }
 
@@ -358,7 +359,7 @@ static bool nvme_available_path(struct nvme_ns_head *head)
 	list_for_each_entry_rcu(ns, &head->list, siblings) {
 		if (test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ns->ctrl->flags))
 			continue;
-		switch (ns->ctrl->state) {
+		switch (nvme_ctrl_state(ns->ctrl)) {
 		case NVME_CTRL_LIVE:
 		case NVME_CTRL_RESETTING:
 		case NVME_CTRL_CONNECTING:
@@ -515,6 +516,7 @@ static void nvme_requeue_work(struct work_struct *work)
 
 int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 {
+	struct queue_limits lim;
 	bool vwc = false;
 
 	mutex_init(&head->lock);
@@ -531,9 +533,14 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	    !nvme_is_unique_nsid(ctrl, head) || !multipath)
 		return 0;
 
-	head->disk = blk_alloc_disk(ctrl->numa_node);
-	if (!head->disk)
-		return -ENOMEM;
+	blk_set_stacking_limits(&lim);
+	lim.dma_alignment = 3;
+	if (head->ids.csi != NVME_CSI_ZNS)
+		lim.max_zone_append_sectors = 0;
+
+	head->disk = blk_alloc_disk(&lim, ctrl->numa_node);
+	if (IS_ERR(head->disk))
+		return PTR_ERR(head->disk);
 	head->disk->fops = &nvme_ns_head_ops;
 	head->disk->private_data = head;
 	sprintf(head->disk->disk_name, "nvme%dn%d",
@@ -552,11 +559,6 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	    ctrl->tagset->map[HCTX_TYPE_POLL].nr_queues)
 		blk_queue_flag_set(QUEUE_FLAG_POLL, head->disk->queue);
 
-	/* set to a default value of 512 until the disk is validated */
-	blk_queue_logical_block_size(head->disk->queue, 512);
-	blk_set_stacking_limits(&head->disk->queue->limits);
-	blk_queue_dma_alignment(head->disk->queue, 3);
-
 	/* we need to propagate up the VMC settings */
 	if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
 		vwc = true;
@@ -667,7 +669,7 @@ static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
 	 * controller is ready.
 	 */
 	if (nvme_state_is_live(ns->ana_state) &&
-	    ns->ctrl->state == NVME_CTRL_LIVE)
+	    nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE)
 		nvme_mpath_set_live(ns);
 }
 
@@ -748,7 +750,7 @@ static void nvme_ana_work(struct work_struct *work)
 {
 	struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, ana_work);
 
-	if (ctrl->state != NVME_CTRL_LIVE)
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE)
 		return;
 
 	nvme_read_ana_log(ctrl);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 4be7f6822966..24193fcb8bd5 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -263,6 +263,7 @@ enum nvme_ctrl_flags {
 struct nvme_ctrl {
 	bool comp_seen;
 	bool identified;
+	bool passthru_err_log_enabled;
 	enum nvme_ctrl_state state;
 	spinlock_t lock;
 	struct mutex scan_lock;
@@ -303,14 +304,13 @@ struct nvme_ctrl {
 	u32 max_hw_sectors;
 	u32 max_segments;
 	u32 max_integrity_segments;
-	u32 max_discard_sectors;
-	u32 max_discard_segments;
 	u32 max_zeroes_sectors;
 #ifdef CONFIG_BLK_DEV_ZONED
 	u32 max_zone_append;
 #endif
 	u16 crdt[3];
 	u16 oncs;
+	u8 dmrl;
 	u32 dmrsl;
 	u16 oacs;
 	u16 sqsize;
@@ -455,6 +455,7 @@ struct nvme_ns_head {
 	struct list_head	entry;
 	struct kref		ref;
 	bool			shared;
+	bool			passthru_err_log_enabled;
 	int			instance;
 	struct nvme_effects_log *effects;
 	u64			nuse;
@@ -463,6 +464,7 @@ struct nvme_ns_head {
 	u16			ms;
 	u16			pi_size;
 	u8			pi_type;
+	u8			pi_offset;
 	u8			guard_type;
 	u16			sgs;
 	u32			sws;
@@ -523,7 +525,6 @@ struct nvme_ns {
 	struct device		cdev_device;
 
 	struct nvme_fault_inject fault_inject;
-
 };
 
 /* NVMe ns supports metadata actions by the controller (generate/strip) */
@@ -806,17 +807,18 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req);
 blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
 		struct request *req);
 bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
-		bool queue_live);
+		bool queue_live, enum nvme_ctrl_state state);
 
 static inline bool nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		bool queue_live)
 {
-	if (likely(ctrl->state == NVME_CTRL_LIVE))
+	enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
+
+	if (likely(state == NVME_CTRL_LIVE))
 		return true;
-	if (ctrl->ops->flags & NVME_F_FABRICS &&
-	    ctrl->state == NVME_CTRL_DELETING)
+	if (ctrl->ops->flags & NVME_F_FABRICS && state == NVME_CTRL_DELETING)
 		return queue_live;
-	return __nvme_check_ready(ctrl, rq, queue_live);
+	return __nvme_check_ready(ctrl, rq, queue_live, state);
 }
 
 /*
@@ -837,12 +839,27 @@ static inline bool nvme_is_unique_nsid(struct nvme_ctrl *ctrl,
 		(ctrl->ctratt & NVME_CTRL_CTRATT_NVM_SETS);
 }
 
+/*
+ * Flags for __nvme_submit_sync_cmd()
+ */
+typedef __u32 __bitwise nvme_submit_flags_t;
+
+enum {
+	/* Insert request at the head of the queue */
+	NVME_SUBMIT_AT_HEAD  = (__force nvme_submit_flags_t)(1 << 0),
+	/* Set BLK_MQ_REQ_NOWAIT when allocating request */
+	NVME_SUBMIT_NOWAIT = (__force nvme_submit_flags_t)(1 << 1),
+	/* Set BLK_MQ_REQ_RESERVED when allocating request */
+	NVME_SUBMIT_RESERVED = (__force nvme_submit_flags_t)(1 << 2),
+	/* Retry command when NVME_SC_DNR is not set in the result */
+	NVME_SUBMIT_RETRY = (__force nvme_submit_flags_t)(1 << 3),
+};
+
 int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		void *buf, unsigned bufflen);
 int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		union nvme_result *result, void *buffer, unsigned bufflen,
-		int qid, int at_head,
-		blk_mq_req_flags_t flags);
+		int qid, nvme_submit_flags_t flags);
 int nvme_set_features(struct nvme_ctrl *dev, unsigned int fid,
 		      unsigned int dword11, void *buffer, size_t buflen,
 		      u32 *result);
@@ -932,6 +949,10 @@ extern struct device_attribute dev_attr_ana_grpid;
 extern struct device_attribute dev_attr_ana_state;
 extern struct device_attribute subsys_attr_iopolicy;
 
+static inline bool nvme_disk_is_ns_head(struct gendisk *disk)
+{
+	return disk->fops == &nvme_ns_head_ops;
+}
 #else
 #define multipath false
 static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
@@ -1009,13 +1030,17 @@ static inline void nvme_mpath_start_request(struct request *rq)
 static inline void nvme_mpath_end_request(struct request *rq)
 {
 }
+static inline bool nvme_disk_is_ns_head(struct gendisk *disk)
+{
+	return false;
+}
 #endif /* CONFIG_NVME_MULTIPATH */
 
-int nvme_revalidate_zones(struct nvme_ns *ns);
 int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
 		unsigned int nr_zones, report_zones_cb cb, void *data);
+int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf,
+		struct queue_limits *lim);
 #ifdef CONFIG_BLK_DEV_ZONED
-int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf);
 blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
 				       struct nvme_command *cmnd,
 				       enum nvme_zone_mgmt_action action);
@@ -1026,18 +1051,14 @@ static inline blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns,
 {
 	return BLK_STS_NOTSUPP;
 }
-
-static inline int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
-{
-	dev_warn(ns->ctrl->device,
-		 "Please enable CONFIG_BLK_DEV_ZONED to support ZNS devices\n");
-	return -EPROTONOSUPPORT;
-}
 #endif
 
 static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
 {
-	return dev_to_disk(dev)->private_data;
+	struct gendisk *disk = dev_to_disk(dev);
+
+	WARN_ON(nvme_disk_is_ns_head(disk));
+	return disk->private_data;
 }
 
 #ifdef CONFIG_NVME_HWMON
@@ -1114,35 +1135,42 @@ static inline bool nvme_multi_css(struct nvme_ctrl *ctrl)
 }
 
 #ifdef CONFIG_NVME_VERBOSE_ERRORS
-const unsigned char *nvme_get_error_status_str(u16 status);
-const unsigned char *nvme_get_opcode_str(u8 opcode);
-const unsigned char *nvme_get_admin_opcode_str(u8 opcode);
-const unsigned char *nvme_get_fabrics_opcode_str(u8 opcode);
+const char *nvme_get_error_status_str(u16 status);
+const char *nvme_get_opcode_str(u8 opcode);
+const char *nvme_get_admin_opcode_str(u8 opcode);
+const char *nvme_get_fabrics_opcode_str(u8 opcode);
 #else /* CONFIG_NVME_VERBOSE_ERRORS */
-static inline const unsigned char *nvme_get_error_status_str(u16 status)
+static inline const char *nvme_get_error_status_str(u16 status)
 {
 	return "I/O Error";
 }
-static inline const unsigned char *nvme_get_opcode_str(u8 opcode)
+static inline const char *nvme_get_opcode_str(u8 opcode)
 {
 	return "I/O Cmd";
 }
-static inline const unsigned char *nvme_get_admin_opcode_str(u8 opcode)
+static inline const char *nvme_get_admin_opcode_str(u8 opcode)
 {
 	return "Admin Cmd";
 }
 
-static inline const unsigned char *nvme_get_fabrics_opcode_str(u8 opcode)
+static inline const char *nvme_get_fabrics_opcode_str(u8 opcode)
 {
 	return "Fabrics Cmd";
 }
 #endif /* CONFIG_NVME_VERBOSE_ERRORS */
 
-static inline const unsigned char *nvme_opcode_str(int qid, u8 opcode, u8 fctype)
+static inline const char *nvme_opcode_str(int qid, u8 opcode)
 {
-	if (opcode == nvme_fabrics_command)
-		return nvme_get_fabrics_opcode_str(fctype);
 	return qid ? nvme_get_opcode_str(opcode) :
 		nvme_get_admin_opcode_str(opcode);
 }
+
+static inline const char *nvme_fabrics_opcode_str(
+		int qid, const struct nvme_command *cmd)
+{
+	if (nvme_is_fabrics(cmd))
+		return nvme_get_fabrics_opcode_str(cmd->fabrics.fctype);
+
+	return nvme_opcode_str(qid, cmd->common.opcode);
+}
 #endif /* _NVME_H */
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 61af7ff1a9d6..e6267a6aa380 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1284,6 +1284,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	struct request *abort_req;
 	struct nvme_command cmd = { };
 	u32 csts = readl(dev->bar + NVME_REG_CSTS);
+	u8 opcode;
 
 	/* If PCI error recovery process is happening, we cannot reset or
 	 * the recovery mechanism will surely fail.
@@ -1310,8 +1311,8 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 
 	if (blk_mq_rq_state(req) != MQ_RQ_IN_FLIGHT) {
 		dev_warn(dev->ctrl.device,
-			 "I/O %d QID %d timeout, completion polled\n",
-			 req->tag, nvmeq->qid);
+			 "I/O tag %d (%04x) QID %d timeout, completion polled\n",
+			 req->tag, nvme_cid(req), nvmeq->qid);
 		return BLK_EH_DONE;
 	}
 
@@ -1327,8 +1328,8 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 		fallthrough;
 	case NVME_CTRL_DELETING:
 		dev_warn_ratelimited(dev->ctrl.device,
-			 "I/O %d QID %d timeout, disable controller\n",
-			 req->tag, nvmeq->qid);
+			 "I/O tag %d (%04x) QID %d timeout, disable controller\n",
+			 req->tag, nvme_cid(req), nvmeq->qid);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		nvme_dev_disable(dev, true);
 		return BLK_EH_DONE;
@@ -1343,10 +1344,12 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	 * command was already aborted once before and still hasn't been
 	 * returned to the driver, or if this is the admin queue.
 	 */
+	opcode = nvme_req(req)->cmd->common.opcode;
 	if (!nvmeq->qid || iod->aborted) {
 		dev_warn(dev->ctrl.device,
-			 "I/O %d QID %d timeout, reset controller\n",
-			 req->tag, nvmeq->qid);
+			 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout, reset controller\n",
+			 req->tag, nvme_cid(req), opcode,
+			 nvme_opcode_str(nvmeq->qid, opcode), nvmeq->qid);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		goto disable;
 	}
@@ -1362,10 +1365,10 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	cmd.abort.sqid = cpu_to_le16(nvmeq->qid);
 
 	dev_warn(nvmeq->dev->ctrl.device,
-		"I/O %d (%s) QID %d timeout, aborting\n",
-		 req->tag,
-		 nvme_get_opcode_str(nvme_req(req)->cmd->common.opcode),
-		 nvmeq->qid);
+		 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout, aborting req_op:%s(%u) size:%u\n",
+		 req->tag, nvme_cid(req), opcode, nvme_get_opcode_str(opcode),
+		 nvmeq->qid, blk_op_str(req_op(req)), req_op(req),
+		 blk_rq_bytes(req));
 
 	abort_req = blk_mq_alloc_request(dev->ctrl.admin_q, nvme_req_op(&cmd),
 					 BLK_MQ_REQ_NOWAIT);
@@ -2743,10 +2746,10 @@ static void nvme_reset_work(struct work_struct *work)
 	 * controller around but remove all namespaces.
 	 */
 	if (dev->online_queues > 1) {
+		nvme_dbbuf_set(dev);
 		nvme_unquiesce_io_queues(&dev->ctrl);
 		nvme_wait_freeze(&dev->ctrl);
 		nvme_pci_update_nr_queues(dev);
-		nvme_dbbuf_set(dev);
 		nvme_unfreeze(&dev->ctrl);
 	} else {
 		dev_warn(dev->ctrl.device, "IO queues lost\n");
@@ -3408,6 +3411,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x1c5c, 0x174a),   /* SK Hynix P31 SSD */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
+	{ PCI_DEVICE(0x1c5c, 0x1D59),   /* SK Hynix BC901 */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x15b7, 0x2001),   /*  Sandisk Skyhawk */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x1d97, 0x2263),   /* SPCC */
@@ -3538,5 +3543,6 @@ static void __exit nvme_exit(void)
 MODULE_AUTHOR("Matthew Wilcox <willy@linux.intel.com>");
 MODULE_LICENSE("GPL");
 MODULE_VERSION("1.0");
+MODULE_DESCRIPTION("NVMe host PCIe transport driver");
 module_init(nvme_init);
 module_exit(nvme_exit);
diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c
index 391b1465ebfd..fc3eed00f9ff 100644
--- a/drivers/nvme/host/pr.c
+++ b/drivers/nvme/host/pr.c
@@ -98,7 +98,7 @@ static int nvme_send_pr_command(struct block_device *bdev,
 		struct nvme_command *c, void *data, unsigned int data_len)
 {
 	if (IS_ENABLED(CONFIG_NVME_MULTIPATH) &&
-	    bdev->bd_disk->fops == &nvme_ns_head_ops)
+	    nvme_disk_is_ns_head(bdev->bd_disk))
 		return nvme_send_ns_head_pr_command(bdev, c, data, data_len);
 
 	return nvme_send_ns_pr_command(bdev->bd_disk->private_data, c, data,
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index c89503da24d7..366f0bb4ebfc 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1006,6 +1006,7 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
 {
 	int ret;
 	bool changed;
+	u16 max_queue_size;
 
 	ret = nvme_rdma_configure_admin_queue(ctrl, new);
 	if (ret)
@@ -1030,11 +1031,16 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
 			ctrl->ctrl.opts->queue_size, ctrl->ctrl.sqsize + 1);
 	}
 
-	if (ctrl->ctrl.sqsize + 1 > NVME_RDMA_MAX_QUEUE_SIZE) {
+	if (ctrl->ctrl.max_integrity_segments)
+		max_queue_size = NVME_RDMA_MAX_METADATA_QUEUE_SIZE;
+	else
+		max_queue_size = NVME_RDMA_MAX_QUEUE_SIZE;
+
+	if (ctrl->ctrl.sqsize + 1 > max_queue_size) {
 		dev_warn(ctrl->ctrl.device,
-			"ctrl sqsize %u > max queue size %u, clamping down\n",
-			ctrl->ctrl.sqsize + 1, NVME_RDMA_MAX_QUEUE_SIZE);
-		ctrl->ctrl.sqsize = NVME_RDMA_MAX_QUEUE_SIZE - 1;
+			 "ctrl sqsize %u > max queue size %u, clamping down\n",
+			 ctrl->ctrl.sqsize + 1, max_queue_size);
+		ctrl->ctrl.sqsize = max_queue_size - 1;
 	}
 
 	if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {
@@ -1410,6 +1416,8 @@ static int nvme_rdma_map_sg_pi(struct nvme_rdma_queue *queue,
 	struct nvme_ns *ns = rq->q->queuedata;
 	struct bio *bio = rq->bio;
 	struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl;
+	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
+	u32 xfer_len;
 	int nr;
 
 	req->mr = ib_mr_pool_get(queue->qp, &queue->qp->sig_mrs);
@@ -1422,8 +1430,7 @@ static int nvme_rdma_map_sg_pi(struct nvme_rdma_queue *queue,
 	if (unlikely(nr))
 		goto mr_put;
 
-	nvme_rdma_set_sig_attrs(blk_get_integrity(bio->bi_bdev->bd_disk), c,
-				req->mr->sig_attrs, ns->head->pi_type);
+	nvme_rdma_set_sig_attrs(bi, c, req->mr->sig_attrs, ns->head->pi_type);
 	nvme_rdma_set_prot_checks(c, &req->mr->sig_attrs->check_mask);
 
 	ib_update_fast_reg_key(req->mr, ib_inc_rkey(req->mr->rkey));
@@ -1441,7 +1448,11 @@ static int nvme_rdma_map_sg_pi(struct nvme_rdma_queue *queue,
 		     IB_ACCESS_REMOTE_WRITE;
 
 	sg->addr = cpu_to_le64(req->mr->iova);
-	put_unaligned_le24(req->mr->length, sg->length);
+	xfer_len = req->mr->length;
+	/* Check if PI is added by the HW */
+	if (!pi_count)
+		xfer_len += (xfer_len >> bi->interval_exp) * ns->head->pi_size;
+	put_unaligned_le24(xfer_len, sg->length);
 	put_unaligned_le32(req->mr->rkey, sg->key);
 	sg->type = NVME_KEY_SGL_FMT_DATA_DESC << 4;
 
@@ -1946,9 +1957,13 @@ static enum blk_eh_timer_return nvme_rdma_timeout(struct request *rq)
 	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_rdma_queue *queue = req->queue;
 	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
+	struct nvme_command *cmd = req->req.cmd;
+	int qid = nvme_rdma_queue_idx(queue);
 
-	dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n",
-		 rq->tag, nvme_rdma_queue_idx(queue));
+	dev_warn(ctrl->ctrl.device,
+		 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout\n",
+		 rq->tag, nvme_cid(rq), cmd->common.opcode,
+		 nvme_fabrics_opcode_str(qid, cmd), qid);
 
 	if (nvme_ctrl_state(&ctrl->ctrl) != NVME_CTRL_LIVE) {
 		/*
@@ -2291,8 +2306,8 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	if (ret)
 		goto out_uninit_ctrl;
 
-	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n",
-		nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr);
+	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs, hostnqn: %s\n",
+		nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr, opts->host->nqn);
 
 	mutex_lock(&nvme_rdma_ctrl_mutex);
 	list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list);
@@ -2395,4 +2410,5 @@ static void __exit nvme_rdma_cleanup_module(void)
 module_init(nvme_rdma_init_module);
 module_exit(nvme_rdma_cleanup_module);
 
+MODULE_DESCRIPTION("NVMe host RDMA transport driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index ac24ad102380..09fcaa519e5b 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -35,16 +35,71 @@ static ssize_t nvme_sysfs_rescan(struct device *dev,
 }
 static DEVICE_ATTR(rescan_controller, S_IWUSR, NULL, nvme_sysfs_rescan);
 
+static ssize_t nvme_adm_passthru_err_log_enabled_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf,
+			  ctrl->passthru_err_log_enabled ? "on\n" : "off\n");
+}
+
+static ssize_t nvme_adm_passthru_err_log_enabled_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	bool passthru_err_log_enabled;
+	int err;
+
+	err = kstrtobool(buf, &passthru_err_log_enabled);
+	if (err)
+		return -EINVAL;
+
+	ctrl->passthru_err_log_enabled = passthru_err_log_enabled;
+
+	return count;
+}
+
 static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev)
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
-	if (disk->fops == &nvme_bdev_ops)
-		return nvme_get_ns_from_dev(dev)->head;
-	else
+	if (nvme_disk_is_ns_head(disk))
 		return disk->private_data;
+	return nvme_get_ns_from_dev(dev)->head;
+}
+
+static ssize_t nvme_io_passthru_err_log_enabled_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvme_ns_head *head = dev_to_ns_head(dev);
+
+	return sysfs_emit(buf, head->passthru_err_log_enabled ? "on\n" : "off\n");
 }
 
+static ssize_t nvme_io_passthru_err_log_enabled_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct nvme_ns_head *head = dev_to_ns_head(dev);
+	bool passthru_err_log_enabled;
+	int err;
+
+	err = kstrtobool(buf, &passthru_err_log_enabled);
+	if (err)
+		return -EINVAL;
+	head->passthru_err_log_enabled = passthru_err_log_enabled;
+
+	return count;
+}
+
+static struct device_attribute dev_attr_adm_passthru_err_log_enabled = \
+	__ATTR(passthru_err_log_enabled, S_IRUGO | S_IWUSR, \
+	nvme_adm_passthru_err_log_enabled_show, nvme_adm_passthru_err_log_enabled_store);
+
+static struct device_attribute dev_attr_io_passthru_err_log_enabled = \
+	__ATTR(passthru_err_log_enabled, S_IRUGO | S_IWUSR, \
+	nvme_io_passthru_err_log_enabled_show, nvme_io_passthru_err_log_enabled_store);
+
 static ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
 {
@@ -166,14 +221,11 @@ static int ns_update_nuse(struct nvme_ns *ns)
 
 	ret = nvme_identify_ns(ns->ctrl, ns->head->ns_id, &id);
 	if (ret)
-		goto out_free_id;
+		return ret;
 
 	ns->head->nuse = le64_to_cpu(id->nuse);
-
-out_free_id:
 	kfree(id);
-
-	return ret;
+	return 0;
 }
 
 static ssize_t nuse_show(struct device *dev, struct device_attribute *attr,
@@ -209,6 +261,7 @@ static struct attribute *nvme_ns_attrs[] = {
 	&dev_attr_ana_grpid.attr,
 	&dev_attr_ana_state.attr,
 #endif
+	&dev_attr_io_passthru_err_log_enabled.attr,
 	NULL,
 };
 
@@ -233,7 +286,8 @@ static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj,
 	}
 #ifdef CONFIG_NVME_MULTIPATH
 	if (a == &dev_attr_ana_grpid.attr || a == &dev_attr_ana_state.attr) {
-		if (dev_to_disk(dev)->fops != &nvme_bdev_ops) /* per-path attr */
+		/* per-path attr */
+		if (nvme_disk_is_ns_head(dev_to_disk(dev)))
 			return 0;
 		if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl))
 			return 0;
@@ -311,6 +365,7 @@ static ssize_t nvme_sysfs_show_state(struct device *dev,
 				     char *buf)
 {
 	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	unsigned state = (unsigned)nvme_ctrl_state(ctrl);
 	static const char *const state_name[] = {
 		[NVME_CTRL_NEW]		= "new",
 		[NVME_CTRL_LIVE]	= "live",
@@ -321,9 +376,8 @@ static ssize_t nvme_sysfs_show_state(struct device *dev,
 		[NVME_CTRL_DEAD]	= "dead",
 	};
 
-	if ((unsigned)ctrl->state < ARRAY_SIZE(state_name) &&
-	    state_name[ctrl->state])
-		return sysfs_emit(buf, "%s\n", state_name[ctrl->state]);
+	if (state < ARRAY_SIZE(state_name) && state_name[state])
+		return sysfs_emit(buf, "%s\n", state_name[state]);
 
 	return sysfs_emit(buf, "unknown state\n");
 }
@@ -655,6 +709,7 @@ static struct attribute *nvme_dev_attrs[] = {
 #ifdef CONFIG_NVME_TCP_TLS
 	&dev_attr_tls_key.attr,
 #endif
+	&dev_attr_adm_passthru_err_log_enabled.attr,
 	NULL
 };
 
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 08805f027810..a6d596e05602 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1922,14 +1922,13 @@ static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl)
 						      ctrl->opts->subsysnqn);
 		if (!pskid) {
 			dev_err(ctrl->device, "no valid PSK found\n");
-			ret = -ENOKEY;
-			goto out_free_queue;
+			return -ENOKEY;
 		}
 	}
 
 	ret = nvme_tcp_alloc_queue(ctrl, 0, pskid);
 	if (ret)
-		goto out_free_queue;
+		return ret;
 
 	ret = nvme_tcp_alloc_async_req(to_tcp_ctrl(ctrl));
 	if (ret)
@@ -2429,13 +2428,13 @@ static enum blk_eh_timer_return nvme_tcp_timeout(struct request *rq)
 	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl;
 	struct nvme_tcp_cmd_pdu *pdu = nvme_tcp_req_cmd_pdu(req);
-	u8 opc = pdu->cmd.common.opcode, fctype = pdu->cmd.fabrics.fctype;
+	struct nvme_command *cmd = &pdu->cmd;
 	int qid = nvme_tcp_queue_id(req->queue);
 
 	dev_warn(ctrl->device,
-		"queue %d: timeout cid %#x type %d opcode %#x (%s)\n",
-		nvme_tcp_queue_id(req->queue), nvme_cid(rq), pdu->hdr.type,
-		opc, nvme_opcode_str(qid, opc, fctype));
+		 "I/O tag %d (%04x) type %d opcode %#x (%s) QID %d timeout\n",
+		 rq->tag, nvme_cid(rq), pdu->hdr.type, cmd->common.opcode,
+		 nvme_fabrics_opcode_str(qid, cmd), qid);
 
 	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE) {
 		/*
@@ -2754,8 +2753,8 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
 	if (ret)
 		goto out_uninit_ctrl;
 
-	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp\n",
-		nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr);
+	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp, hostnqn: %s\n",
+		nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr, opts->host->nqn);
 
 	mutex_lock(&nvme_tcp_ctrl_mutex);
 	list_add_tail(&ctrl->list, &nvme_tcp_ctrl_list);
@@ -2827,4 +2826,5 @@ static void __exit nvme_tcp_cleanup_module(void)
 module_init(nvme_tcp_init_module);
 module_exit(nvme_tcp_cleanup_module);
 
+MODULE_DESCRIPTION("NVMe host TCP transport driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index 499bbb0eee8d..722384bcc765 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -7,16 +7,6 @@
 #include <linux/vmalloc.h>
 #include "nvme.h"
 
-int nvme_revalidate_zones(struct nvme_ns *ns)
-{
-	struct request_queue *q = ns->queue;
-
-	blk_queue_chunk_sectors(q, ns->head->zsze);
-	blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append);
-
-	return blk_revalidate_disk_zones(ns->disk, NULL);
-}
-
 static int nvme_set_max_append(struct nvme_ctrl *ctrl)
 {
 	struct nvme_command c = { };
@@ -45,10 +35,10 @@ static int nvme_set_max_append(struct nvme_ctrl *ctrl)
 	return 0;
 }
 
-int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
+int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf,
+		struct queue_limits *lim)
 {
 	struct nvme_effects_log *log = ns->head->effects;
-	struct request_queue *q = ns->queue;
 	struct nvme_command c = { };
 	struct nvme_id_ns_zns *id;
 	int status;
@@ -109,10 +99,12 @@ int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
 		goto free_data;
 	}
 
-	disk_set_zoned(ns->disk);
-	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
-	disk_set_max_open_zones(ns->disk, le32_to_cpu(id->mor) + 1);
-	disk_set_max_active_zones(ns->disk, le32_to_cpu(id->mar) + 1);
+	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ns->queue);
+	lim->zoned = 1;
+	lim->max_open_zones = le32_to_cpu(id->mor) + 1;
+	lim->max_active_zones = le32_to_cpu(id->mar) + 1;
+	lim->chunk_sectors = ns->head->zsze;
+	lim->max_zone_append_sectors = ns->ctrl->max_zone_append;
 free_data:
 	kfree(id);
 	return status;
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 39cb570f833d..f5b7054a4a05 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -428,7 +428,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	id->cqes = (0x4 << 4) | 0x4;
 
 	/* no enforcement soft-limit for maxcmd - pick arbitrary high value */
-	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
+	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD(ctrl));
 
 	id->nn = cpu_to_le32(NVMET_MAX_NAMESPACES);
 	id->mnan = cpu_to_le32(NVMET_MAX_NAMESPACES);
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index 2482a0db2504..77a6e817b315 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -273,6 +273,32 @@ static ssize_t nvmet_param_inline_data_size_store(struct config_item *item,
 
 CONFIGFS_ATTR(nvmet_, param_inline_data_size);
 
+static ssize_t nvmet_param_max_queue_size_show(struct config_item *item,
+		char *page)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+
+	return snprintf(page, PAGE_SIZE, "%d\n", port->max_queue_size);
+}
+
+static ssize_t nvmet_param_max_queue_size_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+	int ret;
+
+	if (nvmet_is_port_enabled(port, __func__))
+		return -EACCES;
+	ret = kstrtoint(page, 0, &port->max_queue_size);
+	if (ret) {
+		pr_err("Invalid value '%s' for max_queue_size\n", page);
+		return -EINVAL;
+	}
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_, param_max_queue_size);
+
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 static ssize_t nvmet_param_pi_enable_show(struct config_item *item,
 		char *page)
@@ -1859,6 +1885,7 @@ static struct configfs_attribute *nvmet_port_attrs[] = {
 	&nvmet_attr_addr_trtype,
 	&nvmet_attr_addr_tsas,
 	&nvmet_attr_param_inline_data_size,
+	&nvmet_attr_param_max_queue_size,
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 	&nvmet_attr_param_pi_enable,
 #endif
@@ -1917,6 +1944,7 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 	INIT_LIST_HEAD(&port->subsystems);
 	INIT_LIST_HEAD(&port->referrals);
 	port->inline_data_size = -1;	/* < 0 == let the transport choose */
+	port->max_queue_size = -1;	/* < 0 == let the transport choose */
 
 	port->disc_addr.portid = cpu_to_le16(portid);
 	port->disc_addr.adrfam = NVMF_ADDR_FAMILY_MAX;
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index d26aa30f8702..6bbe4df0166c 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -248,7 +248,7 @@ void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
 		nvmet_add_to_changed_ns_log(ctrl, cpu_to_le32(nsid));
 		if (nvmet_aen_bit_disabled(ctrl, NVME_AEN_BIT_NS_ATTR))
 			continue;
-		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
+		nvmet_add_async_event(ctrl, NVME_AER_NOTICE,
 				NVME_AER_NOTICE_NS_CHANGED,
 				NVME_LOG_CHANGED_NS);
 	}
@@ -265,7 +265,7 @@ void nvmet_send_ana_event(struct nvmet_subsys *subsys,
 			continue;
 		if (nvmet_aen_bit_disabled(ctrl, NVME_AEN_BIT_ANA_CHANGE))
 			continue;
-		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
+		nvmet_add_async_event(ctrl, NVME_AER_NOTICE,
 				NVME_AER_NOTICE_ANA, NVME_LOG_ANA);
 	}
 	mutex_unlock(&subsys->lock);
@@ -358,6 +358,18 @@ int nvmet_enable_port(struct nvmet_port *port)
 	if (port->inline_data_size < 0)
 		port->inline_data_size = 0;
 
+	/*
+	 * If the transport didn't set the max_queue_size properly, then clamp
+	 * it to the target limits. Also set default values in case the
+	 * transport didn't set it at all.
+	 */
+	if (port->max_queue_size < 0)
+		port->max_queue_size = NVMET_MAX_QUEUE_SIZE;
+	else
+		port->max_queue_size = clamp_t(int, port->max_queue_size,
+					       NVMET_MIN_QUEUE_SIZE,
+					       NVMET_MAX_QUEUE_SIZE);
+
 	port->enabled = true;
 	port->tr_ops = ops;
 	return 0;
@@ -1223,9 +1235,10 @@ static void nvmet_init_cap(struct nvmet_ctrl *ctrl)
 	ctrl->cap |= (15ULL << 24);
 	/* maximum queue entries supported: */
 	if (ctrl->ops->get_max_queue_size)
-		ctrl->cap |= ctrl->ops->get_max_queue_size(ctrl) - 1;
+		ctrl->cap |= min_t(u16, ctrl->ops->get_max_queue_size(ctrl),
+				   ctrl->port->max_queue_size) - 1;
 	else
-		ctrl->cap |= NVMET_QUEUE_SIZE - 1;
+		ctrl->cap |= ctrl->port->max_queue_size - 1;
 
 	if (nvmet_is_passthru_subsys(ctrl->subsys))
 		nvmet_passthrough_override_cap(ctrl);
@@ -1411,6 +1424,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 
 	kref_init(&ctrl->ref);
 	ctrl->subsys = subsys;
+	ctrl->pi_support = ctrl->port->pi_enable && ctrl->subsys->pi_support;
 	nvmet_init_cap(ctrl);
 	WRITE_ONCE(ctrl->aen_enabled, NVMET_AEN_CFG_OPTIONAL);
 
@@ -1705,4 +1719,5 @@ static void __exit nvmet_exit(void)
 module_init(nvmet_init);
 module_exit(nvmet_exit);
 
+MODULE_DESCRIPTION("NVMe target core framework");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 668d257fa986..ce54da8c6b36 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -21,7 +21,7 @@ static void __nvmet_disc_changed(struct nvmet_port *port,
 	if (nvmet_aen_bit_disabled(ctrl, NVME_AEN_BIT_DISC_CHANGE))
 		return;
 
-	nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
+	nvmet_add_async_event(ctrl, NVME_AER_NOTICE,
 			      NVME_AER_NOTICE_DISC_CHANGED, NVME_LOG_DISC);
 }
 
@@ -282,7 +282,7 @@ static void nvmet_execute_disc_identify(struct nvmet_req *req)
 	id->lpa = (1 << 2);
 
 	/* no enforcement soft-limit for maxcmd - pick arbitrary high value */
-	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
+	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD(ctrl));
 
 	id->sgls = cpu_to_le32(1 << 0);	/* we always support SGLs */
 	if (ctrl->ops->flags & NVMF_KEYED_SGLS)
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index d8da840a1c0e..b23f4cf840bd 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -157,7 +157,8 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
 		return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
 	}
 
-	if (sqsize > mqes) {
+	/* for fabrics, this value applies to only the I/O Submission Queues */
+	if (qid && sqsize > mqes) {
 		pr_warn("sqsize %u is larger than MQES supported %u cntlid %d\n",
 				sqsize, mqes, ctrl->cntlid);
 		req->error_loc = offsetof(struct nvmf_connect_command, sqsize);
@@ -209,7 +210,7 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
 	struct nvmf_connect_command *c = &req->cmd->connect;
 	struct nvmf_connect_data *d;
 	struct nvmet_ctrl *ctrl = NULL;
-	u16 status = 0;
+	u16 status;
 	int ret;
 
 	if (!nvmet_check_transfer_len(req, sizeof(struct nvmf_connect_data)))
@@ -251,8 +252,6 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
 	if (status)
 		goto out;
 
-	ctrl->pi_support = ctrl->port->pi_enable && ctrl->subsys->pi_support;
-
 	uuid_copy(&ctrl->hostid, &d->hostid);
 
 	ret = nvmet_setup_auth(ctrl);
@@ -290,7 +289,7 @@ static void nvmet_execute_io_connect(struct nvmet_req *req)
 	struct nvmf_connect_data *d;
 	struct nvmet_ctrl *ctrl;
 	u16 qid = le16_to_cpu(c->qid);
-	u16 status = 0;
+	u16 status;
 
 	if (!nvmet_check_transfer_len(req, sizeof(struct nvmf_connect_data)))
 		return;
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index bd59990b5250..fd229f310c93 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -111,6 +111,8 @@ struct nvmet_fc_tgtport {
 	struct nvmet_fc_port_entry	*pe;
 	struct kref			ref;
 	u32				max_sg_cnt;
+
+	struct work_struct		put_work;
 };
 
 struct nvmet_fc_port_entry {
@@ -145,7 +147,6 @@ struct nvmet_fc_tgt_queue {
 	struct list_head		avail_defer_list;
 	struct workqueue_struct		*work_q;
 	struct kref			ref;
-	struct rcu_head			rcu;
 	/* array of fcp_iods */
 	struct nvmet_fc_fcp_iod		fod[] __counted_by(sqsize);
 } __aligned(sizeof(unsigned long long));
@@ -166,10 +167,9 @@ struct nvmet_fc_tgt_assoc {
 	struct nvmet_fc_hostport	*hostport;
 	struct nvmet_fc_ls_iod		*rcv_disconn;
 	struct list_head		a_list;
-	struct nvmet_fc_tgt_queue __rcu	*queues[NVMET_NR_QUEUES + 1];
+	struct nvmet_fc_tgt_queue 	*queues[NVMET_NR_QUEUES + 1];
 	struct kref			ref;
 	struct work_struct		del_work;
-	struct rcu_head			rcu;
 };
 
 
@@ -249,6 +249,13 @@ static int nvmet_fc_tgt_a_get(struct nvmet_fc_tgt_assoc *assoc);
 static void nvmet_fc_tgt_q_put(struct nvmet_fc_tgt_queue *queue);
 static int nvmet_fc_tgt_q_get(struct nvmet_fc_tgt_queue *queue);
 static void nvmet_fc_tgtport_put(struct nvmet_fc_tgtport *tgtport);
+static void nvmet_fc_put_tgtport_work(struct work_struct *work)
+{
+	struct nvmet_fc_tgtport *tgtport =
+		container_of(work, struct nvmet_fc_tgtport, put_work);
+
+	nvmet_fc_tgtport_put(tgtport);
+}
 static int nvmet_fc_tgtport_get(struct nvmet_fc_tgtport *tgtport);
 static void nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
 					struct nvmet_fc_fcp_iod *fod);
@@ -360,7 +367,7 @@ __nvmet_fc_finish_ls_req(struct nvmet_fc_ls_req_op *lsop)
 
 	if (!lsop->req_queued) {
 		spin_unlock_irqrestore(&tgtport->lock, flags);
-		return;
+		goto out_putwork;
 	}
 
 	list_del(&lsop->lsreq_list);
@@ -373,7 +380,8 @@ __nvmet_fc_finish_ls_req(struct nvmet_fc_ls_req_op *lsop)
 				  (lsreq->rqstlen + lsreq->rsplen),
 				  DMA_BIDIRECTIONAL);
 
-	nvmet_fc_tgtport_put(tgtport);
+out_putwork:
+	queue_work(nvmet_wq, &tgtport->put_work);
 }
 
 static int
@@ -489,8 +497,7 @@ nvmet_fc_xmt_disconnect_assoc(struct nvmet_fc_tgt_assoc *assoc)
 	 * message is normal. Otherwise, send unless the hostport has
 	 * already been invalidated by the lldd.
 	 */
-	if (!tgtport->ops->ls_req || !assoc->hostport ||
-	    assoc->hostport->invalid)
+	if (!tgtport->ops->ls_req || assoc->hostport->invalid)
 		return;
 
 	lsop = kzalloc((sizeof(*lsop) +
@@ -802,14 +809,11 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc,
 	if (!queue)
 		return NULL;
 
-	if (!nvmet_fc_tgt_a_get(assoc))
-		goto out_free_queue;
-
 	queue->work_q = alloc_workqueue("ntfc%d.%d.%d", 0, 0,
 				assoc->tgtport->fc_target_port.port_num,
 				assoc->a_id, qid);
 	if (!queue->work_q)
-		goto out_a_put;
+		goto out_free_queue;
 
 	queue->qid = qid;
 	queue->sqsize = sqsize;
@@ -831,15 +835,13 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc,
 		goto out_fail_iodlist;
 
 	WARN_ON(assoc->queues[qid]);
-	rcu_assign_pointer(assoc->queues[qid], queue);
+	assoc->queues[qid] = queue;
 
 	return queue;
 
 out_fail_iodlist:
 	nvmet_fc_destroy_fcp_iodlist(assoc->tgtport, queue);
 	destroy_workqueue(queue->work_q);
-out_a_put:
-	nvmet_fc_tgt_a_put(assoc);
 out_free_queue:
 	kfree(queue);
 	return NULL;
@@ -852,15 +854,11 @@ nvmet_fc_tgt_queue_free(struct kref *ref)
 	struct nvmet_fc_tgt_queue *queue =
 		container_of(ref, struct nvmet_fc_tgt_queue, ref);
 
-	rcu_assign_pointer(queue->assoc->queues[queue->qid], NULL);
-
 	nvmet_fc_destroy_fcp_iodlist(queue->assoc->tgtport, queue);
 
-	nvmet_fc_tgt_a_put(queue->assoc);
-
 	destroy_workqueue(queue->work_q);
 
-	kfree_rcu(queue, rcu);
+	kfree(queue);
 }
 
 static void
@@ -969,7 +967,7 @@ nvmet_fc_find_target_queue(struct nvmet_fc_tgtport *tgtport,
 	rcu_read_lock();
 	list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) {
 		if (association_id == assoc->association_id) {
-			queue = rcu_dereference(assoc->queues[qid]);
+			queue = assoc->queues[qid];
 			if (queue &&
 			    (!atomic_read(&queue->connected) ||
 			     !nvmet_fc_tgt_q_get(queue)))
@@ -1031,7 +1029,7 @@ nvmet_fc_match_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 	list_for_each_entry(host, &tgtport->host_list, host_list) {
 		if (host->hosthandle == hosthandle && !host->invalid) {
 			if (nvmet_fc_hostport_get(host))
-				return (host);
+				return host;
 		}
 	}
 
@@ -1078,8 +1076,6 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 		/* new allocation not needed */
 		kfree(newhost);
 		newhost = match;
-		/* no new allocation - release reference */
-		nvmet_fc_tgtport_put(tgtport);
 	} else {
 		newhost->tgtport = tgtport;
 		newhost->hosthandle = hosthandle;
@@ -1094,23 +1090,54 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 }
 
 static void
-nvmet_fc_delete_assoc(struct work_struct *work)
+nvmet_fc_delete_assoc(struct nvmet_fc_tgt_assoc *assoc)
+{
+	nvmet_fc_delete_target_assoc(assoc);
+	nvmet_fc_tgt_a_put(assoc);
+}
+
+static void
+nvmet_fc_delete_assoc_work(struct work_struct *work)
 {
 	struct nvmet_fc_tgt_assoc *assoc =
 		container_of(work, struct nvmet_fc_tgt_assoc, del_work);
+	struct nvmet_fc_tgtport *tgtport = assoc->tgtport;
 
-	nvmet_fc_delete_target_assoc(assoc);
-	nvmet_fc_tgt_a_put(assoc);
+	nvmet_fc_delete_assoc(assoc);
+	nvmet_fc_tgtport_put(tgtport);
+}
+
+static void
+nvmet_fc_schedule_delete_assoc(struct nvmet_fc_tgt_assoc *assoc)
+{
+	nvmet_fc_tgtport_get(assoc->tgtport);
+	queue_work(nvmet_wq, &assoc->del_work);
+}
+
+static bool
+nvmet_fc_assoc_exits(struct nvmet_fc_tgtport *tgtport, u64 association_id)
+{
+	struct nvmet_fc_tgt_assoc *a;
+
+	list_for_each_entry_rcu(a, &tgtport->assoc_list, a_list) {
+		if (association_id == a->association_id)
+			return true;
+	}
+
+	return false;
 }
 
 static struct nvmet_fc_tgt_assoc *
 nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 {
-	struct nvmet_fc_tgt_assoc *assoc, *tmpassoc;
+	struct nvmet_fc_tgt_assoc *assoc;
 	unsigned long flags;
+	bool done;
 	u64 ran;
 	int idx;
-	bool needrandom = true;
+
+	if (!tgtport->pe)
+		return NULL;
 
 	assoc = kzalloc(sizeof(*assoc), GFP_KERNEL);
 	if (!assoc)
@@ -1120,43 +1147,35 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 	if (idx < 0)
 		goto out_free_assoc;
 
-	if (!nvmet_fc_tgtport_get(tgtport))
-		goto out_ida;
-
 	assoc->hostport = nvmet_fc_alloc_hostport(tgtport, hosthandle);
 	if (IS_ERR(assoc->hostport))
-		goto out_put;
+		goto out_ida;
 
 	assoc->tgtport = tgtport;
 	assoc->a_id = idx;
 	INIT_LIST_HEAD(&assoc->a_list);
 	kref_init(&assoc->ref);
-	INIT_WORK(&assoc->del_work, nvmet_fc_delete_assoc);
+	INIT_WORK(&assoc->del_work, nvmet_fc_delete_assoc_work);
 	atomic_set(&assoc->terminating, 0);
 
-	while (needrandom) {
+	done = false;
+	do {
 		get_random_bytes(&ran, sizeof(ran) - BYTES_FOR_QID);
 		ran = ran << BYTES_FOR_QID_SHIFT;
 
 		spin_lock_irqsave(&tgtport->lock, flags);
-		needrandom = false;
-		list_for_each_entry(tmpassoc, &tgtport->assoc_list, a_list) {
-			if (ran == tmpassoc->association_id) {
-				needrandom = true;
-				break;
-			}
-		}
-		if (!needrandom) {
+		rcu_read_lock();
+		if (!nvmet_fc_assoc_exits(tgtport, ran)) {
 			assoc->association_id = ran;
 			list_add_tail_rcu(&assoc->a_list, &tgtport->assoc_list);
+			done = true;
 		}
+		rcu_read_unlock();
 		spin_unlock_irqrestore(&tgtport->lock, flags);
-	}
+	} while (!done);
 
 	return assoc;
 
-out_put:
-	nvmet_fc_tgtport_put(tgtport);
 out_ida:
 	ida_free(&tgtport->assoc_cnt, idx);
 out_free_assoc:
@@ -1172,13 +1191,18 @@ nvmet_fc_target_assoc_free(struct kref *ref)
 	struct nvmet_fc_tgtport *tgtport = assoc->tgtport;
 	struct nvmet_fc_ls_iod	*oldls;
 	unsigned long flags;
+	int i;
+
+	for (i = NVMET_NR_QUEUES; i >= 0; i--) {
+		if (assoc->queues[i])
+			nvmet_fc_delete_target_queue(assoc->queues[i]);
+	}
 
 	/* Send Disconnect now that all i/o has completed */
 	nvmet_fc_xmt_disconnect_assoc(assoc);
 
 	nvmet_fc_free_hostport(assoc->hostport);
 	spin_lock_irqsave(&tgtport->lock, flags);
-	list_del_rcu(&assoc->a_list);
 	oldls = assoc->rcv_disconn;
 	spin_unlock_irqrestore(&tgtport->lock, flags);
 	/* if pending Rcv Disconnect Association LS, send rsp now */
@@ -1188,8 +1212,7 @@ nvmet_fc_target_assoc_free(struct kref *ref)
 	dev_info(tgtport->dev,
 		"{%d:%d} Association freed\n",
 		tgtport->fc_target_port.port_num, assoc->a_id);
-	kfree_rcu(assoc, rcu);
-	nvmet_fc_tgtport_put(tgtport);
+	kfree(assoc);
 }
 
 static void
@@ -1208,7 +1231,7 @@ static void
 nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc)
 {
 	struct nvmet_fc_tgtport *tgtport = assoc->tgtport;
-	struct nvmet_fc_tgt_queue *queue;
+	unsigned long flags;
 	int i, terminating;
 
 	terminating = atomic_xchg(&assoc->terminating, 1);
@@ -1217,29 +1240,21 @@ nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc)
 	if (terminating)
 		return;
 
+	spin_lock_irqsave(&tgtport->lock, flags);
+	list_del_rcu(&assoc->a_list);
+	spin_unlock_irqrestore(&tgtport->lock, flags);
 
-	for (i = NVMET_NR_QUEUES; i >= 0; i--) {
-		rcu_read_lock();
-		queue = rcu_dereference(assoc->queues[i]);
-		if (!queue) {
-			rcu_read_unlock();
-			continue;
-		}
+	synchronize_rcu();
 
-		if (!nvmet_fc_tgt_q_get(queue)) {
-			rcu_read_unlock();
-			continue;
-		}
-		rcu_read_unlock();
-		nvmet_fc_delete_target_queue(queue);
-		nvmet_fc_tgt_q_put(queue);
+	/* ensure all in-flight I/Os have been processed */
+	for (i = NVMET_NR_QUEUES; i >= 0; i--) {
+		if (assoc->queues[i])
+			flush_workqueue(assoc->queues[i]->work_q);
 	}
 
 	dev_info(tgtport->dev,
 		"{%d:%d} Association deleted\n",
 		tgtport->fc_target_port.port_num, assoc->a_id);
-
-	nvmet_fc_tgt_a_put(assoc);
 }
 
 static struct nvmet_fc_tgt_assoc *
@@ -1415,6 +1430,7 @@ nvmet_fc_register_targetport(struct nvmet_fc_port_info *pinfo,
 	kref_init(&newrec->ref);
 	ida_init(&newrec->assoc_cnt);
 	newrec->max_sg_cnt = template->max_sgl_segments;
+	INIT_WORK(&newrec->put_work, nvmet_fc_put_tgtport_work);
 
 	ret = nvmet_fc_alloc_ls_iodlist(newrec);
 	if (ret) {
@@ -1492,9 +1508,8 @@ __nvmet_fc_free_assocs(struct nvmet_fc_tgtport *tgtport)
 	list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) {
 		if (!nvmet_fc_tgt_a_get(assoc))
 			continue;
-		if (!queue_work(nvmet_wq, &assoc->del_work))
-			/* already deleting - release local reference */
-			nvmet_fc_tgt_a_put(assoc);
+		nvmet_fc_schedule_delete_assoc(assoc);
+		nvmet_fc_tgt_a_put(assoc);
 	}
 	rcu_read_unlock();
 }
@@ -1540,16 +1555,14 @@ nvmet_fc_invalidate_host(struct nvmet_fc_target_port *target_port,
 	spin_lock_irqsave(&tgtport->lock, flags);
 	list_for_each_entry_safe(assoc, next,
 				&tgtport->assoc_list, a_list) {
-		if (!assoc->hostport ||
-		    assoc->hostport->hosthandle != hosthandle)
+		if (assoc->hostport->hosthandle != hosthandle)
 			continue;
 		if (!nvmet_fc_tgt_a_get(assoc))
 			continue;
 		assoc->hostport->invalid = 1;
 		noassoc = false;
-		if (!queue_work(nvmet_wq, &assoc->del_work))
-			/* already deleting - release local reference */
-			nvmet_fc_tgt_a_put(assoc);
+		nvmet_fc_schedule_delete_assoc(assoc);
+		nvmet_fc_tgt_a_put(assoc);
 	}
 	spin_unlock_irqrestore(&tgtport->lock, flags);
 
@@ -1581,7 +1594,7 @@ nvmet_fc_delete_ctrl(struct nvmet_ctrl *ctrl)
 
 		rcu_read_lock();
 		list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) {
-			queue = rcu_dereference(assoc->queues[0]);
+			queue = assoc->queues[0];
 			if (queue && queue->nvme_sq.ctrl == ctrl) {
 				if (nvmet_fc_tgt_a_get(assoc))
 					found_ctrl = true;
@@ -1593,9 +1606,8 @@ nvmet_fc_delete_ctrl(struct nvmet_ctrl *ctrl)
 		nvmet_fc_tgtport_put(tgtport);
 
 		if (found_ctrl) {
-			if (!queue_work(nvmet_wq, &assoc->del_work))
-				/* already deleting - release local reference */
-				nvmet_fc_tgt_a_put(assoc);
+			nvmet_fc_schedule_delete_assoc(assoc);
+			nvmet_fc_tgt_a_put(assoc);
 			return;
 		}
 
@@ -1625,6 +1637,8 @@ nvmet_fc_unregister_targetport(struct nvmet_fc_target_port *target_port)
 	/* terminate any outstanding associations */
 	__nvmet_fc_free_assocs(tgtport);
 
+	flush_workqueue(nvmet_wq);
+
 	/*
 	 * should terminate LS's as well. However, LS's will be generated
 	 * at the tail end of association termination, so they likely don't
@@ -1870,9 +1884,6 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
 				sizeof(struct fcnvme_ls_disconnect_assoc_acc)),
 			FCNVME_LS_DISCONNECT_ASSOC);
 
-	/* release get taken in nvmet_fc_find_target_assoc */
-	nvmet_fc_tgt_a_put(assoc);
-
 	/*
 	 * The rules for LS response says the response cannot
 	 * go back until ABTS's have been sent for all outstanding
@@ -1887,8 +1898,6 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
 	assoc->rcv_disconn = iod;
 	spin_unlock_irqrestore(&tgtport->lock, flags);
 
-	nvmet_fc_delete_target_assoc(assoc);
-
 	if (oldls) {
 		dev_info(tgtport->dev,
 			"{%d:%d} Multiple Disconnect Association LS's "
@@ -1904,6 +1913,9 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
 		nvmet_fc_xmt_ls_rsp(tgtport, oldls);
 	}
 
+	nvmet_fc_schedule_delete_assoc(assoc);
+	nvmet_fc_tgt_a_put(assoc);
+
 	return false;
 }
 
@@ -2540,8 +2552,9 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
 
 	fod->req.cmd = &fod->cmdiubuf.sqe;
 	fod->req.cqe = &fod->rspiubuf.cqe;
-	if (tgtport->pe)
-		fod->req.port = tgtport->pe->port;
+	if (!tgtport->pe)
+		goto transport_error;
+	fod->req.port = tgtport->pe->port;
 
 	/* clear any response payload */
 	memset(&fod->rspiubuf, 0, sizeof(fod->rspiubuf));
@@ -2902,6 +2915,9 @@ nvmet_fc_remove_port(struct nvmet_port *port)
 
 	nvmet_fc_portentry_unbind(pe);
 
+	/* terminate any outstanding associations */
+	__nvmet_fc_free_assocs(pe->tgtport);
+
 	kfree(pe);
 }
 
@@ -2933,6 +2949,9 @@ static int __init nvmet_fc_init_module(void)
 
 static void __exit nvmet_fc_exit_module(void)
 {
+	/* ensure any shutdown operation, e.g. delete ctrls have finished */
+	flush_workqueue(nvmet_wq);
+
 	/* sanity check - all lports should be removed */
 	if (!list_empty(&nvmet_fc_target_list))
 		pr_warn("%s: targetport list not empty\n", __func__);
@@ -2945,4 +2964,5 @@ static void __exit nvmet_fc_exit_module(void)
 module_init(nvmet_fc_init_module);
 module_exit(nvmet_fc_exit_module);
 
+MODULE_DESCRIPTION("NVMe target FC transport driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index c65a73433c05..913cd2ec7a6f 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -358,7 +358,7 @@ fcloop_h2t_ls_req(struct nvme_fc_local_port *localport,
 	if (!rport->targetport) {
 		tls_req->status = -ECONNREFUSED;
 		spin_lock(&rport->lock);
-		list_add_tail(&rport->ls_list, &tls_req->ls_list);
+		list_add_tail(&tls_req->ls_list, &rport->ls_list);
 		spin_unlock(&rport->lock);
 		queue_work(nvmet_wq, &rport->ls_work);
 		return ret;
@@ -391,7 +391,7 @@ fcloop_h2t_xmt_ls_rsp(struct nvmet_fc_target_port *targetport,
 	if (remoteport) {
 		rport = remoteport->private;
 		spin_lock(&rport->lock);
-		list_add_tail(&rport->ls_list, &tls_req->ls_list);
+		list_add_tail(&tls_req->ls_list, &rport->ls_list);
 		spin_unlock(&rport->lock);
 		queue_work(nvmet_wq, &rport->ls_work);
 	}
@@ -446,7 +446,7 @@ fcloop_t2h_ls_req(struct nvmet_fc_target_port *targetport, void *hosthandle,
 	if (!tport->remoteport) {
 		tls_req->status = -ECONNREFUSED;
 		spin_lock(&tport->lock);
-		list_add_tail(&tport->ls_list, &tls_req->ls_list);
+		list_add_tail(&tls_req->ls_list, &tport->ls_list);
 		spin_unlock(&tport->lock);
 		queue_work(nvmet_wq, &tport->ls_work);
 		return ret;
@@ -995,11 +995,6 @@ fcloop_nport_free(struct kref *ref)
 {
 	struct fcloop_nport *nport =
 		container_of(ref, struct fcloop_nport, ref);
-	unsigned long flags;
-
-	spin_lock_irqsave(&fcloop_lock, flags);
-	list_del(&nport->nport_list);
-	spin_unlock_irqrestore(&fcloop_lock, flags);
 
 	kfree(nport);
 }
@@ -1357,6 +1352,8 @@ __unlink_remote_port(struct fcloop_nport *nport)
 		nport->tport->remoteport = NULL;
 	nport->rport = NULL;
 
+	list_del(&nport->nport_list);
+
 	return rport;
 }
 
@@ -1559,7 +1556,9 @@ static const struct attribute_group *fcloop_dev_attr_groups[] = {
 	NULL,
 };
 
-static struct class *fcloop_class;
+static const struct class fcloop_class = {
+	.name = "fcloop",
+};
 static struct device *fcloop_device;
 
 
@@ -1567,15 +1566,14 @@ static int __init fcloop_init(void)
 {
 	int ret;
 
-	fcloop_class = class_create("fcloop");
-	if (IS_ERR(fcloop_class)) {
+	ret = class_register(&fcloop_class);
+	if (ret) {
 		pr_err("couldn't register class fcloop\n");
-		ret = PTR_ERR(fcloop_class);
 		return ret;
 	}
 
 	fcloop_device = device_create_with_groups(
-				fcloop_class, NULL, MKDEV(0, 0), NULL,
+				&fcloop_class, NULL, MKDEV(0, 0), NULL,
 				fcloop_dev_attr_groups, "ctl");
 	if (IS_ERR(fcloop_device)) {
 		pr_err("couldn't create ctl device!\n");
@@ -1588,7 +1586,7 @@ static int __init fcloop_init(void)
 	return 0;
 
 out_destroy_class:
-	class_destroy(fcloop_class);
+	class_unregister(&fcloop_class);
 	return ret;
 }
 
@@ -1646,11 +1644,12 @@ static void __exit fcloop_exit(void)
 
 	put_device(fcloop_device);
 
-	device_destroy(fcloop_class, MKDEV(0, 0));
-	class_destroy(fcloop_class);
+	device_destroy(&fcloop_class, MKDEV(0, 0));
+	class_unregister(&fcloop_class);
 }
 
 module_init(fcloop_init);
 module_exit(fcloop_exit);
 
+MODULE_DESCRIPTION("NVMe target FC loop transport driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index f11400a908f2..6426aac2634a 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -50,10 +50,10 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
 
 void nvmet_bdev_ns_disable(struct nvmet_ns *ns)
 {
-	if (ns->bdev_handle) {
-		bdev_release(ns->bdev_handle);
+	if (ns->bdev_file) {
+		fput(ns->bdev_file);
 		ns->bdev = NULL;
-		ns->bdev_handle = NULL;
+		ns->bdev_file = NULL;
 	}
 }
 
@@ -85,18 +85,18 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns)
 	if (ns->buffered_io)
 		return -ENOTBLK;
 
-	ns->bdev_handle = bdev_open_by_path(ns->device_path,
+	ns->bdev_file = bdev_file_open_by_path(ns->device_path,
 				BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, NULL);
-	if (IS_ERR(ns->bdev_handle)) {
-		ret = PTR_ERR(ns->bdev_handle);
+	if (IS_ERR(ns->bdev_file)) {
+		ret = PTR_ERR(ns->bdev_file);
 		if (ret != -ENOTBLK) {
 			pr_err("failed to open block device %s: (%d)\n",
 					ns->device_path, ret);
 		}
-		ns->bdev_handle = NULL;
+		ns->bdev_file = NULL;
 		return ret;
 	}
-	ns->bdev = ns->bdev_handle->bdev;
+	ns->bdev = file_bdev(ns->bdev_file);
 	ns->size = bdev_nr_bytes(ns->bdev);
 	ns->blksize_shift = blksize_bits(bdev_logical_block_size(ns->bdev));
 
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 9cb434c58075..e589915ddef8 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -400,7 +400,7 @@ static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl)
 	}
 
 	nvme_quiesce_admin_queue(&ctrl->ctrl);
-	if (ctrl->ctrl.state == NVME_CTRL_LIVE)
+	if (nvme_ctrl_state(&ctrl->ctrl) == NVME_CTRL_LIVE)
 		nvme_disable_ctrl(&ctrl->ctrl, true);
 
 	nvme_cancel_admin_tagset(&ctrl->ctrl);
@@ -434,8 +434,10 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work)
 	nvme_loop_shutdown_ctrl(ctrl);
 
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
-		if (ctrl->ctrl.state != NVME_CTRL_DELETING &&
-		    ctrl->ctrl.state != NVME_CTRL_DELETING_NOIO)
+		enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl);
+
+		if (state != NVME_CTRL_DELETING &&
+		    state != NVME_CTRL_DELETING_NOIO)
 			/* state change failure for non-deleted ctrl? */
 			WARN_ON_ONCE(1);
 		return;
@@ -688,5 +690,6 @@ static void __exit nvme_loop_cleanup_module(void)
 module_init(nvme_loop_init_module);
 module_exit(nvme_loop_cleanup_module);
 
+MODULE_DESCRIPTION("NVMe target loop transport driver");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("nvmet-transport-254"); /* 254 == NVMF_TRTYPE_LOOP */
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 6c8acebe1a1a..f460728e1df1 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -58,7 +58,7 @@
 
 struct nvmet_ns {
 	struct percpu_ref	ref;
-	struct bdev_handle	*bdev_handle;
+	struct file		*bdev_file;
 	struct block_device	*bdev;
 	struct file		*file;
 	bool			readonly;
@@ -163,6 +163,7 @@ struct nvmet_port {
 	void				*priv;
 	bool				enabled;
 	int				inline_data_size;
+	int				max_queue_size;
 	const struct nvmet_fabrics_ops	*tr_ops;
 	bool				pi_enable;
 };
@@ -543,9 +544,10 @@ void nvmet_subsys_disc_changed(struct nvmet_subsys *subsys,
 void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
 		u8 event_info, u8 log_page);
 
-#define NVMET_QUEUE_SIZE	1024
+#define NVMET_MIN_QUEUE_SIZE	16
+#define NVMET_MAX_QUEUE_SIZE	1024
 #define NVMET_NR_QUEUES		128
-#define NVMET_MAX_CMD		NVMET_QUEUE_SIZE
+#define NVMET_MAX_CMD(ctrl)	(NVME_CAP_MQES(ctrl->cap) + 1)
 
 /*
  * Nice round number that makes a list of nsids fit into a page.
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index f2d963e1fe94..bb4a69d538fd 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -132,7 +132,7 @@ static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req)
 
 	id->sqes = min_t(__u8, ((0x6 << 4) | 0x6), id->sqes);
 	id->cqes = min_t(__u8, ((0x4 << 4) | 0x4), id->cqes);
-	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
+	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD(ctrl));
 
 	/* don't support fuse commands */
 	id->fuses = 0;
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 4597bca43a6d..f2bb9d95ecf4 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -37,6 +37,8 @@
 #define NVMET_RDMA_MAX_MDTS			8
 #define NVMET_RDMA_MAX_METADATA_MDTS		5
 
+#define NVMET_RDMA_BACKLOG 128
+
 struct nvmet_rdma_srq;
 
 struct nvmet_rdma_cmd {
@@ -1583,8 +1585,19 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id,
 	}
 
 	if (queue->host_qid == 0) {
-		/* Let inflight controller teardown complete */
-		flush_workqueue(nvmet_wq);
+		struct nvmet_rdma_queue *q;
+		int pending = 0;
+
+		/* Check for pending controller teardown */
+		mutex_lock(&nvmet_rdma_queue_mutex);
+		list_for_each_entry(q, &nvmet_rdma_queue_list, queue_list) {
+			if (q->nvme_sq.ctrl == queue->nvme_sq.ctrl &&
+			    q->state == NVMET_RDMA_Q_DISCONNECTING)
+				pending++;
+		}
+		mutex_unlock(&nvmet_rdma_queue_mutex);
+		if (pending > NVMET_RDMA_BACKLOG)
+			return NVME_SC_CONNECT_CTRL_BUSY;
 	}
 
 	ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn);
@@ -1880,7 +1893,7 @@ static int nvmet_rdma_enable_port(struct nvmet_rdma_port *port)
 		goto out_destroy_id;
 	}
 
-	ret = rdma_listen(cm_id, 128);
+	ret = rdma_listen(cm_id, NVMET_RDMA_BACKLOG);
 	if (ret) {
 		pr_err("listening to %pISpcs failed (%d)\n", addr, ret);
 		goto out_destroy_id;
@@ -1943,6 +1956,14 @@ static int nvmet_rdma_add_port(struct nvmet_port *nport)
 		nport->inline_data_size = NVMET_RDMA_MAX_INLINE_DATA_SIZE;
 	}
 
+	if (nport->max_queue_size < 0) {
+		nport->max_queue_size = NVME_RDMA_DEFAULT_QUEUE_SIZE;
+	} else if (nport->max_queue_size > NVME_RDMA_MAX_QUEUE_SIZE) {
+		pr_warn("max_queue_size %u is too large, reducing to %u\n",
+			nport->max_queue_size, NVME_RDMA_MAX_QUEUE_SIZE);
+		nport->max_queue_size = NVME_RDMA_MAX_QUEUE_SIZE;
+	}
+
 	ret = inet_pton_with_scope(&init_net, af, nport->disc_addr.traddr,
 			nport->disc_addr.trsvcid, &port->addr);
 	if (ret) {
@@ -2002,6 +2023,8 @@ static u8 nvmet_rdma_get_mdts(const struct nvmet_ctrl *ctrl)
 
 static u16 nvmet_rdma_get_max_queue_size(const struct nvmet_ctrl *ctrl)
 {
+	if (ctrl->pi_support)
+		return NVME_RDMA_MAX_METADATA_QUEUE_SIZE;
 	return NVME_RDMA_MAX_QUEUE_SIZE;
 }
 
@@ -2091,5 +2114,6 @@ static void __exit nvmet_rdma_exit(void)
 module_init(nvmet_rdma_init);
 module_exit(nvmet_rdma_exit);
 
+MODULE_DESCRIPTION("NVMe target RDMA transport driver");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("nvmet-transport-1"); /* 1 == NVMF_TRTYPE_RDMA */
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 4cc27856aa8f..c8655fc5aa5b 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -24,6 +24,8 @@
 #include "nvmet.h"
 
 #define NVMET_TCP_DEF_INLINE_DATA_SIZE	(4 * PAGE_SIZE)
+#define NVMET_TCP_MAXH2CDATA		0x400000 /* 16M arbitrary limit */
+#define NVMET_TCP_BACKLOG 128
 
 static int param_store_val(const char *str, int *val, int min, int max)
 {
@@ -923,7 +925,7 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue)
 	icresp->hdr.pdo = 0;
 	icresp->hdr.plen = cpu_to_le32(icresp->hdr.hlen);
 	icresp->pfv = cpu_to_le16(NVME_TCP_PFV_1_0);
-	icresp->maxdata = cpu_to_le32(0x400000); /* 16M arbitrary limit */
+	icresp->maxdata = cpu_to_le32(NVMET_TCP_MAXH2CDATA);
 	icresp->cpda = 0;
 	if (queue->hdr_digest)
 		icresp->digest |= NVME_TCP_HDR_DIGEST_ENABLE;
@@ -978,13 +980,13 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue)
 {
 	struct nvme_tcp_data_pdu *data = &queue->pdu.data;
 	struct nvmet_tcp_cmd *cmd;
+	unsigned int exp_data_len;
 
 	if (likely(queue->nr_cmds)) {
 		if (unlikely(data->ttag >= queue->nr_cmds)) {
 			pr_err("queue %d: received out of bound ttag %u, nr_cmds %u\n",
 				queue->idx, data->ttag, queue->nr_cmds);
-			nvmet_tcp_fatal_error(queue);
-			return -EPROTO;
+			goto err_proto;
 		}
 		cmd = &queue->cmds[data->ttag];
 	} else {
@@ -995,19 +997,32 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue)
 		pr_err("ttag %u unexpected data offset %u (expected %u)\n",
 			data->ttag, le32_to_cpu(data->data_offset),
 			cmd->rbytes_done);
-		/* FIXME: use path and transport errors */
-		nvmet_req_complete(&cmd->req,
-			NVME_SC_INVALID_FIELD | NVME_SC_DNR);
-		return -EPROTO;
+		goto err_proto;
 	}
 
+	exp_data_len = le32_to_cpu(data->hdr.plen) -
+			nvmet_tcp_hdgst_len(queue) -
+			nvmet_tcp_ddgst_len(queue) -
+			sizeof(*data);
+
 	cmd->pdu_len = le32_to_cpu(data->data_length);
+	if (unlikely(cmd->pdu_len != exp_data_len ||
+		     cmd->pdu_len == 0 ||
+		     cmd->pdu_len > NVMET_TCP_MAXH2CDATA)) {
+		pr_err("H2CData PDU len %u is invalid\n", cmd->pdu_len);
+		goto err_proto;
+	}
 	cmd->pdu_recv = 0;
 	nvmet_tcp_build_pdu_iovec(cmd);
 	queue->cmd = cmd;
 	queue->rcv_state = NVMET_TCP_RECV_DATA;
 
 	return 0;
+
+err_proto:
+	/* FIXME: use proper transport errors */
+	nvmet_tcp_fatal_error(queue);
+	return -EPROTO;
 }
 
 static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue)
@@ -1768,7 +1783,7 @@ static int nvmet_tcp_try_peek_pdu(struct nvmet_tcp_queue *queue)
 		 (int)sizeof(struct nvme_tcp_icreq_pdu));
 	if (hdr->type == nvme_tcp_icreq &&
 	    hdr->hlen == sizeof(struct nvme_tcp_icreq_pdu) &&
-	    hdr->plen == (__le32)sizeof(struct nvme_tcp_icreq_pdu)) {
+	    hdr->plen == cpu_to_le32(sizeof(struct nvme_tcp_icreq_pdu))) {
 		pr_debug("queue %d: icreq detected\n",
 			 queue->idx);
 		return len;
@@ -2053,7 +2068,7 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport)
 		goto err_sock;
 	}
 
-	ret = kernel_listen(port->sock, 128);
+	ret = kernel_listen(port->sock, NVMET_TCP_BACKLOG);
 	if (ret) {
 		pr_err("failed to listen %d on port sock\n", ret);
 		goto err_sock;
@@ -2119,8 +2134,19 @@ static u16 nvmet_tcp_install_queue(struct nvmet_sq *sq)
 		container_of(sq, struct nvmet_tcp_queue, nvme_sq);
 
 	if (sq->qid == 0) {
-		/* Let inflight controller teardown complete */
-		flush_workqueue(nvmet_wq);
+		struct nvmet_tcp_queue *q;
+		int pending = 0;
+
+		/* Check for pending controller teardown */
+		mutex_lock(&nvmet_tcp_queue_mutex);
+		list_for_each_entry(q, &nvmet_tcp_queue_list, queue_list) {
+			if (q->nvme_sq.ctrl == sq->ctrl &&
+			    q->state == NVMET_TCP_Q_DISCONNECTING)
+				pending++;
+		}
+		mutex_unlock(&nvmet_tcp_queue_mutex);
+		if (pending > NVMET_TCP_BACKLOG)
+			return NVME_SC_CONNECT_CTRL_BUSY;
 	}
 
 	queue->nr_cmds = sq->size * 2;
@@ -2190,10 +2216,12 @@ static void __exit nvmet_tcp_exit(void)
 	flush_workqueue(nvmet_wq);
 
 	destroy_workqueue(nvmet_tcp_wq);
+	ida_destroy(&nvmet_tcp_queue_ida);
 }
 
 module_init(nvmet_tcp_init);
 module_exit(nvmet_tcp_exit);
 
+MODULE_DESCRIPTION("NVMe target TCP transport driver");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("nvmet-transport-3"); /* 3 == NVMF_TRTYPE_TCP */
diff --git a/drivers/nvme/target/trace.c b/drivers/nvme/target/trace.c
index bff454d46255..6ee1f3db81d0 100644
--- a/drivers/nvme/target/trace.c
+++ b/drivers/nvme/target/trace.c
@@ -211,7 +211,7 @@ const char *nvmet_trace_disk_name(struct trace_seq *p, char *name)
 	return ret;
 }
 
-const char *nvmet_trace_ctrl_name(struct trace_seq *p, struct nvmet_ctrl *ctrl)
+const char *nvmet_trace_ctrl_id(struct trace_seq *p, u16 ctrl_id)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
 
@@ -224,8 +224,8 @@ const char *nvmet_trace_ctrl_name(struct trace_seq *p, struct nvmet_ctrl *ctrl)
 	 * If we can know the extra data of the connect command in this stage,
 	 * we can update this print statement later.
 	 */
-	if (ctrl)
-		trace_seq_printf(p, "%d", ctrl->cntlid);
+	if (ctrl_id)
+		trace_seq_printf(p, "%d", ctrl_id);
 	else
 		trace_seq_printf(p, "_");
 	trace_seq_putc(p, 0);
diff --git a/drivers/nvme/target/trace.h b/drivers/nvme/target/trace.h
index 6109b3806b12..7f7ebf9558e5 100644
--- a/drivers/nvme/target/trace.h
+++ b/drivers/nvme/target/trace.h
@@ -32,18 +32,24 @@ const char *nvmet_trace_parse_fabrics_cmd(struct trace_seq *p, u8 fctype,
 	 nvmet_trace_parse_nvm_cmd(p, opcode, cdw10) :			\
 	 nvmet_trace_parse_admin_cmd(p, opcode, cdw10)))
 
-const char *nvmet_trace_ctrl_name(struct trace_seq *p, struct nvmet_ctrl *ctrl);
-#define __print_ctrl_name(ctrl)				\
-	nvmet_trace_ctrl_name(p, ctrl)
+const char *nvmet_trace_ctrl_id(struct trace_seq *p, u16 ctrl_id);
+#define __print_ctrl_id(ctrl_id)			\
+	nvmet_trace_ctrl_id(p, ctrl_id)
 
 const char *nvmet_trace_disk_name(struct trace_seq *p, char *name);
 #define __print_disk_name(name)				\
 	nvmet_trace_disk_name(p, name)
 
 #ifndef TRACE_HEADER_MULTI_READ
-static inline struct nvmet_ctrl *nvmet_req_to_ctrl(struct nvmet_req *req)
+static inline u16 nvmet_req_to_ctrl_id(struct nvmet_req *req)
 {
-	return req->sq->ctrl;
+	/*
+	 * The queue and controller pointers are not valid until an association
+	 * has been established.
+	 */
+	if (!req->sq || !req->sq->ctrl)
+		return 0;
+	return req->sq->ctrl->cntlid;
 }
 
 static inline void __assign_req_name(char *name, struct nvmet_req *req)
@@ -53,8 +59,7 @@ static inline void __assign_req_name(char *name, struct nvmet_req *req)
 		return;
 	}
 
-	strncpy(name, req->ns->device_path,
-		min_t(size_t, DISK_NAME_LEN, strlen(req->ns->device_path)));
+	strscpy_pad(name, req->ns->device_path, DISK_NAME_LEN);
 }
 #endif
 
@@ -63,7 +68,7 @@ TRACE_EVENT(nvmet_req_init,
 	TP_ARGS(req, cmd),
 	TP_STRUCT__entry(
 		__field(struct nvme_command *, cmd)
-		__field(struct nvmet_ctrl *, ctrl)
+		__field(u16, ctrl_id)
 		__array(char, disk, DISK_NAME_LEN)
 		__field(int, qid)
 		__field(u16, cid)
@@ -76,7 +81,7 @@ TRACE_EVENT(nvmet_req_init,
 	),
 	TP_fast_assign(
 		__entry->cmd = cmd;
-		__entry->ctrl = nvmet_req_to_ctrl(req);
+		__entry->ctrl_id = nvmet_req_to_ctrl_id(req);
 		__assign_req_name(__entry->disk, req);
 		__entry->qid = req->sq->qid;
 		__entry->cid = cmd->common.command_id;
@@ -85,12 +90,12 @@ TRACE_EVENT(nvmet_req_init,
 		__entry->flags = cmd->common.flags;
 		__entry->nsid = le32_to_cpu(cmd->common.nsid);
 		__entry->metadata = le64_to_cpu(cmd->common.metadata);
-		memcpy(__entry->cdw10, &cmd->common.cdw10,
+		memcpy(__entry->cdw10, &cmd->common.cdws,
 			sizeof(__entry->cdw10));
 	),
 	TP_printk("nvmet%s: %sqid=%d, cmdid=%u, nsid=%u, flags=%#x, "
 		  "meta=%#llx, cmd=(%s, %s)",
-		__print_ctrl_name(__entry->ctrl),
+		__print_ctrl_id(__entry->ctrl_id),
 		__print_disk_name(__entry->disk),
 		__entry->qid, __entry->cid, __entry->nsid,
 		__entry->flags, __entry->metadata,
@@ -104,7 +109,7 @@ TRACE_EVENT(nvmet_req_complete,
 	TP_PROTO(struct nvmet_req *req),
 	TP_ARGS(req),
 	TP_STRUCT__entry(
-		__field(struct nvmet_ctrl *, ctrl)
+		__field(u16, ctrl_id)
 		__array(char, disk, DISK_NAME_LEN)
 		__field(int, qid)
 		__field(int, cid)
@@ -112,7 +117,7 @@ TRACE_EVENT(nvmet_req_complete,
 		__field(u16, status)
 	),
 	TP_fast_assign(
-		__entry->ctrl = nvmet_req_to_ctrl(req);
+		__entry->ctrl_id = nvmet_req_to_ctrl_id(req);
 		__entry->qid = req->cq->qid;
 		__entry->cid = req->cqe->command_id;
 		__entry->result = le64_to_cpu(req->cqe->result.u64);
@@ -120,7 +125,7 @@ TRACE_EVENT(nvmet_req_complete,
 		__assign_req_name(__entry->disk, req);
 	),
 	TP_printk("nvmet%s: %sqid=%d, cmdid=%u, res=%#llx, status=%#x",
-		__print_ctrl_name(__entry->ctrl),
+		__print_ctrl_id(__entry->ctrl_id),
 		__print_disk_name(__entry->disk),
 		__entry->qid, __entry->cid, __entry->result, __entry->status)
 
diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c
index 5b5c1e481722..3148d9f1bde6 100644
--- a/drivers/nvme/target/zns.c
+++ b/drivers/nvme/target/zns.c
@@ -456,8 +456,7 @@ static u16 nvmet_bdev_execute_zmgmt_send_all(struct nvmet_req *req)
 	switch (zsa_req_op(req->cmd->zms.zsa)) {
 	case REQ_OP_ZONE_RESET:
 		ret = blkdev_zone_mgmt(req->ns->bdev, REQ_OP_ZONE_RESET, 0,
-				       get_capacity(req->ns->bdev->bd_disk),
-				       GFP_KERNEL);
+				       get_capacity(req->ns->bdev->bd_disk));
 		if (ret < 0)
 			return blkdev_zone_mgmt_errno_to_nvme_status(ret);
 		break;
@@ -508,7 +507,7 @@ static void nvmet_bdev_zmgmt_send_work(struct work_struct *w)
 		goto out;
 	}
 
-	ret = blkdev_zone_mgmt(bdev, op, sect, zone_sectors, GFP_KERNEL);
+	ret = blkdev_zone_mgmt(bdev, op, sect, zone_sectors);
 	if (ret < 0)
 		status = blkdev_zone_mgmt_errno_to_nvme_status(ret);
 
diff --git a/drivers/nvmem/Kconfig b/drivers/nvmem/Kconfig
index 5bc9c4874fe3..283134498fbc 100644
--- a/drivers/nvmem/Kconfig
+++ b/drivers/nvmem/Kconfig
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 menuconfig NVMEM
 	bool "NVMEM Support"
+	imply NVMEM_LAYOUTS
 	help
 	  Support for NVMEM(Non Volatile Memory) devices like EEPROM, EFUSES...
 
diff --git a/drivers/nvmem/Makefile b/drivers/nvmem/Makefile
index 423baf089515..cdd01fbf1313 100644
--- a/drivers/nvmem/Makefile
+++ b/drivers/nvmem/Makefile
@@ -5,6 +5,8 @@
 
 obj-$(CONFIG_NVMEM)		+= nvmem_core.o
 nvmem_core-y			:= core.o
+obj-$(CONFIG_NVMEM_LAYOUTS)	+= nvmem_layouts.o
+nvmem_layouts-y			:= layouts.o
 obj-y				+= layouts/
 
 # Devices
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index 608b352a7d91..eb357ac2e54a 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -19,29 +19,7 @@
 #include <linux/of.h>
 #include <linux/slab.h>
 
-struct nvmem_device {
-	struct module		*owner;
-	struct device		dev;
-	int			stride;
-	int			word_size;
-	int			id;
-	struct kref		refcnt;
-	size_t			size;
-	bool			read_only;
-	bool			root_only;
-	int			flags;
-	enum nvmem_type		type;
-	struct bin_attribute	eeprom;
-	struct device		*base_dev;
-	struct list_head	cells;
-	const struct nvmem_keepout *keepout;
-	unsigned int		nkeepout;
-	nvmem_reg_read_t	reg_read;
-	nvmem_reg_write_t	reg_write;
-	struct gpio_desc	*wp_gpio;
-	struct nvmem_layout	*layout;
-	void *priv;
-};
+#include "internals.h"
 
 #define to_nvmem_device(d) container_of(d, struct nvmem_device, dev)
 
@@ -77,9 +55,6 @@ static LIST_HEAD(nvmem_lookup_list);
 
 static BLOCKING_NOTIFIER_HEAD(nvmem_notifier);
 
-static DEFINE_SPINLOCK(nvmem_layout_lock);
-static LIST_HEAD(nvmem_layouts);
-
 static int __nvmem_reg_read(struct nvmem_device *nvmem, unsigned int offset,
 			    void *val, size_t bytes)
 {
@@ -324,6 +299,43 @@ static umode_t nvmem_bin_attr_is_visible(struct kobject *kobj,
 	return nvmem_bin_attr_get_umode(nvmem);
 }
 
+static struct nvmem_cell *nvmem_create_cell(struct nvmem_cell_entry *entry,
+					    const char *id, int index);
+
+static ssize_t nvmem_cell_attr_read(struct file *filp, struct kobject *kobj,
+				    struct bin_attribute *attr, char *buf,
+				    loff_t pos, size_t count)
+{
+	struct nvmem_cell_entry *entry;
+	struct nvmem_cell *cell = NULL;
+	size_t cell_sz, read_len;
+	void *content;
+
+	entry = attr->private;
+	cell = nvmem_create_cell(entry, entry->name, 0);
+	if (IS_ERR(cell))
+		return PTR_ERR(cell);
+
+	if (!cell)
+		return -EINVAL;
+
+	content = nvmem_cell_read(cell, &cell_sz);
+	if (IS_ERR(content)) {
+		read_len = PTR_ERR(content);
+		goto destroy_cell;
+	}
+
+	read_len = min_t(unsigned int, cell_sz - pos, count);
+	memcpy(buf, content + pos, read_len);
+	kfree(content);
+
+destroy_cell:
+	kfree_const(cell->id);
+	kfree(cell);
+
+	return read_len;
+}
+
 /* default read/write permissions */
 static struct bin_attribute bin_attr_rw_nvmem = {
 	.attr	= {
@@ -345,11 +357,21 @@ static const struct attribute_group nvmem_bin_group = {
 	.is_bin_visible = nvmem_bin_attr_is_visible,
 };
 
+/* Cell attributes will be dynamically allocated */
+static struct attribute_group nvmem_cells_group = {
+	.name		= "cells",
+};
+
 static const struct attribute_group *nvmem_dev_groups[] = {
 	&nvmem_bin_group,
 	NULL,
 };
 
+static const struct attribute_group *nvmem_cells_groups[] = {
+	&nvmem_cells_group,
+	NULL,
+};
+
 static struct bin_attribute bin_attr_nvmem_eeprom_compat = {
 	.attr	= {
 		.name	= "eeprom",
@@ -405,6 +427,69 @@ static void nvmem_sysfs_remove_compat(struct nvmem_device *nvmem,
 		device_remove_bin_file(nvmem->base_dev, &nvmem->eeprom);
 }
 
+static int nvmem_populate_sysfs_cells(struct nvmem_device *nvmem)
+{
+	struct bin_attribute **cells_attrs, *attrs;
+	struct nvmem_cell_entry *entry;
+	unsigned int ncells = 0, i = 0;
+	int ret = 0;
+
+	mutex_lock(&nvmem_mutex);
+
+	if (list_empty(&nvmem->cells) || nvmem->sysfs_cells_populated) {
+		nvmem_cells_group.bin_attrs = NULL;
+		goto unlock_mutex;
+	}
+
+	/* Allocate an array of attributes with a sentinel */
+	ncells = list_count_nodes(&nvmem->cells);
+	cells_attrs = devm_kcalloc(&nvmem->dev, ncells + 1,
+				   sizeof(struct bin_attribute *), GFP_KERNEL);
+	if (!cells_attrs) {
+		ret = -ENOMEM;
+		goto unlock_mutex;
+	}
+
+	attrs = devm_kcalloc(&nvmem->dev, ncells, sizeof(struct bin_attribute), GFP_KERNEL);
+	if (!attrs) {
+		ret = -ENOMEM;
+		goto unlock_mutex;
+	}
+
+	/* Initialize each attribute to take the name and size of the cell */
+	list_for_each_entry(entry, &nvmem->cells, node) {
+		sysfs_bin_attr_init(&attrs[i]);
+		attrs[i].attr.name = devm_kasprintf(&nvmem->dev, GFP_KERNEL,
+						    "%s@%x,%x", entry->name,
+						    entry->offset,
+						    entry->bit_offset);
+		attrs[i].attr.mode = 0444;
+		attrs[i].size = entry->bytes;
+		attrs[i].read = &nvmem_cell_attr_read;
+		attrs[i].private = entry;
+		if (!attrs[i].attr.name) {
+			ret = -ENOMEM;
+			goto unlock_mutex;
+		}
+
+		cells_attrs[i] = &attrs[i];
+		i++;
+	}
+
+	nvmem_cells_group.bin_attrs = cells_attrs;
+
+	ret = devm_device_add_groups(&nvmem->dev, nvmem_cells_groups);
+	if (ret)
+		goto unlock_mutex;
+
+	nvmem->sysfs_cells_populated = true;
+
+unlock_mutex:
+	mutex_unlock(&nvmem_mutex);
+
+	return ret;
+}
+
 #else /* CONFIG_NVMEM_SYSFS */
 
 static int nvmem_sysfs_setup_compat(struct nvmem_device *nvmem,
@@ -697,7 +782,6 @@ static int nvmem_validate_keepouts(struct nvmem_device *nvmem)
 
 static int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, struct device_node *np)
 {
-	struct nvmem_layout *layout = nvmem->layout;
 	struct device *dev = &nvmem->dev;
 	struct device_node *child;
 	const __be32 *addr;
@@ -727,8 +811,8 @@ static int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, struct device_nod
 
 		info.np = of_node_get(child);
 
-		if (layout && layout->fixup_cell_info)
-			layout->fixup_cell_info(nvmem, layout, &info);
+		if (nvmem->fixup_dt_cell_info)
+			nvmem->fixup_dt_cell_info(nvmem, &info);
 
 		ret = nvmem_add_one_cell(nvmem, &info);
 		kfree(info.name);
@@ -763,117 +847,35 @@ static int nvmem_add_cells_from_fixed_layout(struct nvmem_device *nvmem)
 	return err;
 }
 
-int __nvmem_layout_register(struct nvmem_layout *layout, struct module *owner)
-{
-	layout->owner = owner;
-
-	spin_lock(&nvmem_layout_lock);
-	list_add(&layout->node, &nvmem_layouts);
-	spin_unlock(&nvmem_layout_lock);
-
-	blocking_notifier_call_chain(&nvmem_notifier, NVMEM_LAYOUT_ADD, layout);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(__nvmem_layout_register);
-
-void nvmem_layout_unregister(struct nvmem_layout *layout)
-{
-	blocking_notifier_call_chain(&nvmem_notifier, NVMEM_LAYOUT_REMOVE, layout);
-
-	spin_lock(&nvmem_layout_lock);
-	list_del(&layout->node);
-	spin_unlock(&nvmem_layout_lock);
-}
-EXPORT_SYMBOL_GPL(nvmem_layout_unregister);
-
-static struct nvmem_layout *nvmem_layout_get(struct nvmem_device *nvmem)
+int nvmem_layout_register(struct nvmem_layout *layout)
 {
-	struct device_node *layout_np;
-	struct nvmem_layout *l, *layout = ERR_PTR(-EPROBE_DEFER);
-
-	layout_np = of_nvmem_layout_get_container(nvmem);
-	if (!layout_np)
-		return NULL;
-
-	/* Fixed layouts don't have a matching driver */
-	if (of_device_is_compatible(layout_np, "fixed-layout")) {
-		of_node_put(layout_np);
-		return NULL;
-	}
-
-	/*
-	 * In case the nvmem device was built-in while the layout was built as a
-	 * module, we shall manually request the layout driver loading otherwise
-	 * we'll never have any match.
-	 */
-	of_request_module(layout_np);
-
-	spin_lock(&nvmem_layout_lock);
-
-	list_for_each_entry(l, &nvmem_layouts, node) {
-		if (of_match_node(l->of_match_table, layout_np)) {
-			if (try_module_get(l->owner))
-				layout = l;
-
-			break;
-		}
-	}
-
-	spin_unlock(&nvmem_layout_lock);
-	of_node_put(layout_np);
-
-	return layout;
-}
+	int ret;
 
-static void nvmem_layout_put(struct nvmem_layout *layout)
-{
-	if (layout)
-		module_put(layout->owner);
-}
+	if (!layout->add_cells)
+		return -EINVAL;
 
-static int nvmem_add_cells_from_layout(struct nvmem_device *nvmem)
-{
-	struct nvmem_layout *layout = nvmem->layout;
-	int ret;
+	/* Populate the cells */
+	ret = layout->add_cells(layout);
+	if (ret)
+		return ret;
 
-	if (layout && layout->add_cells) {
-		ret = layout->add_cells(&nvmem->dev, nvmem, layout);
-		if (ret)
-			return ret;
+#ifdef CONFIG_NVMEM_SYSFS
+	ret = nvmem_populate_sysfs_cells(layout->nvmem);
+	if (ret) {
+		nvmem_device_remove_all_cells(layout->nvmem);
+		return ret;
 	}
+#endif
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nvmem_layout_register);
 
-#if IS_ENABLED(CONFIG_OF)
-/**
- * of_nvmem_layout_get_container() - Get OF node to layout container.
- *
- * @nvmem: nvmem device.
- *
- * Return: a node pointer with refcount incremented or NULL if no
- * container exists. Use of_node_put() on it when done.
- */
-struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem)
-{
-	return of_get_child_by_name(nvmem->dev.of_node, "nvmem-layout");
-}
-EXPORT_SYMBOL_GPL(of_nvmem_layout_get_container);
-#endif
-
-const void *nvmem_layout_get_match_data(struct nvmem_device *nvmem,
-					struct nvmem_layout *layout)
+void nvmem_layout_unregister(struct nvmem_layout *layout)
 {
-	struct device_node __maybe_unused *layout_np;
-	const struct of_device_id *match;
-
-	layout_np = of_nvmem_layout_get_container(nvmem);
-	match = of_match_node(layout->of_match_table, layout_np);
-
-	return match ? match->data : NULL;
+	/* Keep the API even with an empty stub in case we need it later */
 }
-EXPORT_SYMBOL_GPL(nvmem_layout_get_match_data);
+EXPORT_SYMBOL_GPL(nvmem_layout_unregister);
 
 /**
  * nvmem_register() - Register a nvmem device for given nvmem_config.
@@ -925,6 +927,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 
 	kref_init(&nvmem->refcnt);
 	INIT_LIST_HEAD(&nvmem->cells);
+	nvmem->fixup_dt_cell_info = config->fixup_dt_cell_info;
 
 	nvmem->owner = config->owner;
 	if (!nvmem->owner && config->dev->driver)
@@ -980,19 +983,6 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 			goto err_put_device;
 	}
 
-	/*
-	 * If the driver supplied a layout by config->layout, the module
-	 * pointer will be NULL and nvmem_layout_put() will be a noop.
-	 */
-	nvmem->layout = config->layout ?: nvmem_layout_get(nvmem);
-	if (IS_ERR(nvmem->layout)) {
-		rval = PTR_ERR(nvmem->layout);
-		nvmem->layout = NULL;
-
-		if (rval == -EPROBE_DEFER)
-			goto err_teardown_compat;
-	}
-
 	if (config->cells) {
 		rval = nvmem_add_cells(nvmem, config->cells, config->ncells);
 		if (rval)
@@ -1013,24 +1003,34 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 	if (rval)
 		goto err_remove_cells;
 
-	rval = nvmem_add_cells_from_layout(nvmem);
-	if (rval)
-		goto err_remove_cells;
-
 	dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name);
 
 	rval = device_add(&nvmem->dev);
 	if (rval)
 		goto err_remove_cells;
 
+	rval = nvmem_populate_layout(nvmem);
+	if (rval)
+		goto err_remove_dev;
+
+#ifdef CONFIG_NVMEM_SYSFS
+	rval = nvmem_populate_sysfs_cells(nvmem);
+	if (rval)
+		goto err_destroy_layout;
+#endif
+
 	blocking_notifier_call_chain(&nvmem_notifier, NVMEM_ADD, nvmem);
 
 	return nvmem;
 
+#ifdef CONFIG_NVMEM_SYSFS
+err_destroy_layout:
+	nvmem_destroy_layout(nvmem);
+#endif
+err_remove_dev:
+	device_del(&nvmem->dev);
 err_remove_cells:
 	nvmem_device_remove_all_cells(nvmem);
-	nvmem_layout_put(nvmem->layout);
-err_teardown_compat:
 	if (config->compat)
 		nvmem_sysfs_remove_compat(nvmem, config);
 err_put_device:
@@ -1052,7 +1052,7 @@ static void nvmem_device_release(struct kref *kref)
 		device_remove_bin_file(nvmem->base_dev, &nvmem->eeprom);
 
 	nvmem_device_remove_all_cells(nvmem);
-	nvmem_layout_put(nvmem->layout);
+	nvmem_destroy_layout(nvmem);
 	device_unregister(&nvmem->dev);
 }
 
@@ -1354,6 +1354,12 @@ nvmem_cell_get_from_lookup(struct device *dev, const char *con_id)
 	return cell;
 }
 
+static void nvmem_layout_module_put(struct nvmem_device *nvmem)
+{
+	if (nvmem->layout && nvmem->layout->dev.driver)
+		module_put(nvmem->layout->dev.driver->owner);
+}
+
 #if IS_ENABLED(CONFIG_OF)
 static struct nvmem_cell_entry *
 nvmem_find_cell_entry_by_node(struct nvmem_device *nvmem, struct device_node *np)
@@ -1372,6 +1378,18 @@ nvmem_find_cell_entry_by_node(struct nvmem_device *nvmem, struct device_node *np
 	return cell;
 }
 
+static int nvmem_layout_module_get_optional(struct nvmem_device *nvmem)
+{
+	if (!nvmem->layout)
+		return 0;
+
+	if (!nvmem->layout->dev.driver ||
+	    !try_module_get(nvmem->layout->dev.driver->owner))
+		return -EPROBE_DEFER;
+
+	return 0;
+}
+
 /**
  * of_nvmem_cell_get() - Get a nvmem cell from given device node and cell id
  *
@@ -1434,16 +1452,29 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id)
 		return ERR_CAST(nvmem);
 	}
 
+	ret = nvmem_layout_module_get_optional(nvmem);
+	if (ret) {
+		of_node_put(cell_np);
+		__nvmem_device_put(nvmem);
+		return ERR_PTR(ret);
+	}
+
 	cell_entry = nvmem_find_cell_entry_by_node(nvmem, cell_np);
 	of_node_put(cell_np);
 	if (!cell_entry) {
 		__nvmem_device_put(nvmem);
-		return ERR_PTR(-ENOENT);
+		nvmem_layout_module_put(nvmem);
+		if (nvmem->layout)
+			return ERR_PTR(-EPROBE_DEFER);
+		else
+			return ERR_PTR(-ENOENT);
 	}
 
 	cell = nvmem_create_cell(cell_entry, id, cell_index);
-	if (IS_ERR(cell))
+	if (IS_ERR(cell)) {
 		__nvmem_device_put(nvmem);
+		nvmem_layout_module_put(nvmem);
+	}
 
 	return cell;
 }
@@ -1557,6 +1588,7 @@ void nvmem_cell_put(struct nvmem_cell *cell)
 
 	kfree(cell);
 	__nvmem_device_put(nvmem);
+	nvmem_layout_module_put(nvmem);
 }
 EXPORT_SYMBOL_GPL(nvmem_cell_put);
 
@@ -2132,13 +2164,37 @@ const char *nvmem_dev_name(struct nvmem_device *nvmem)
 }
 EXPORT_SYMBOL_GPL(nvmem_dev_name);
 
+/**
+ * nvmem_dev_size() - Get the size of a given nvmem device.
+ *
+ * @nvmem: nvmem device.
+ *
+ * Return: size of the nvmem device.
+ */
+size_t nvmem_dev_size(struct nvmem_device *nvmem)
+{
+	return nvmem->size;
+}
+EXPORT_SYMBOL_GPL(nvmem_dev_size);
+
 static int __init nvmem_init(void)
 {
-	return bus_register(&nvmem_bus_type);
+	int ret;
+
+	ret = bus_register(&nvmem_bus_type);
+	if (ret)
+		return ret;
+
+	ret = nvmem_layout_bus_register();
+	if (ret)
+		bus_unregister(&nvmem_bus_type);
+
+	return ret;
 }
 
 static void __exit nvmem_exit(void)
 {
+	nvmem_layout_bus_unregister();
 	bus_unregister(&nvmem_bus_type);
 }
 
diff --git a/drivers/nvmem/imx-ocotp.c b/drivers/nvmem/imx-ocotp.c
index f1e202efaa49..79dd4fda0329 100644
--- a/drivers/nvmem/imx-ocotp.c
+++ b/drivers/nvmem/imx-ocotp.c
@@ -583,17 +583,12 @@ static const struct of_device_id imx_ocotp_dt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, imx_ocotp_dt_ids);
 
-static void imx_ocotp_fixup_cell_info(struct nvmem_device *nvmem,
-				      struct nvmem_layout *layout,
-				      struct nvmem_cell_info *cell)
+static void imx_ocotp_fixup_dt_cell_info(struct nvmem_device *nvmem,
+					 struct nvmem_cell_info *cell)
 {
 	cell->read_post_process = imx_ocotp_cell_pp;
 }
 
-static struct nvmem_layout imx_ocotp_layout = {
-	.fixup_cell_info = imx_ocotp_fixup_cell_info,
-};
-
 static int imx_ocotp_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -619,7 +614,7 @@ static int imx_ocotp_probe(struct platform_device *pdev)
 	imx_ocotp_nvmem_config.size = 4 * priv->params->nregs;
 	imx_ocotp_nvmem_config.dev = dev;
 	imx_ocotp_nvmem_config.priv = priv;
-	imx_ocotp_nvmem_config.layout = &imx_ocotp_layout;
+	imx_ocotp_nvmem_config.fixup_dt_cell_info = &imx_ocotp_fixup_dt_cell_info;
 
 	priv->config = &imx_ocotp_nvmem_config;
 
diff --git a/drivers/nvmem/internals.h b/drivers/nvmem/internals.h
new file mode 100644
index 000000000000..18fed57270e5
--- /dev/null
+++ b/drivers/nvmem/internals.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_NVMEM_INTERNALS_H
+#define _LINUX_NVMEM_INTERNALS_H
+
+#include <linux/device.h>
+#include <linux/nvmem-consumer.h>
+#include <linux/nvmem-provider.h>
+
+struct nvmem_device {
+	struct module		*owner;
+	struct device		dev;
+	struct list_head	node;
+	int			stride;
+	int			word_size;
+	int			id;
+	struct kref		refcnt;
+	size_t			size;
+	bool			read_only;
+	bool			root_only;
+	int			flags;
+	enum nvmem_type		type;
+	struct bin_attribute	eeprom;
+	struct device		*base_dev;
+	struct list_head	cells;
+	void (*fixup_dt_cell_info)(struct nvmem_device *nvmem,
+				   struct nvmem_cell_info *cell);
+	const struct nvmem_keepout *keepout;
+	unsigned int		nkeepout;
+	nvmem_reg_read_t	reg_read;
+	nvmem_reg_write_t	reg_write;
+	struct gpio_desc	*wp_gpio;
+	struct nvmem_layout	*layout;
+	void *priv;
+	bool			sysfs_cells_populated;
+};
+
+#if IS_ENABLED(CONFIG_OF)
+int nvmem_layout_bus_register(void);
+void nvmem_layout_bus_unregister(void);
+int nvmem_populate_layout(struct nvmem_device *nvmem);
+void nvmem_destroy_layout(struct nvmem_device *nvmem);
+#else /* CONFIG_OF */
+static inline int nvmem_layout_bus_register(void)
+{
+	return 0;
+}
+
+static inline void nvmem_layout_bus_unregister(void) {}
+
+static inline int nvmem_populate_layout(struct nvmem_device *nvmem)
+{
+	return 0;
+}
+
+static inline void nvmem_destroy_layout(struct nvmem_device *nvmem) { }
+#endif /* CONFIG_OF */
+
+#endif  /* ifndef _LINUX_NVMEM_INTERNALS_H */
diff --git a/drivers/nvmem/layouts.c b/drivers/nvmem/layouts.c
new file mode 100644
index 000000000000..6a6aa58369ff
--- /dev/null
+++ b/drivers/nvmem/layouts.c
@@ -0,0 +1,201 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NVMEM layout bus handling
+ *
+ * Copyright (C) 2023 Bootlin
+ * Author: Miquel Raynal <miquel.raynal@bootlin.com
+ */
+
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/nvmem-consumer.h>
+#include <linux/nvmem-provider.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+
+#include "internals.h"
+
+#define to_nvmem_layout_driver(drv) \
+	(container_of((drv), struct nvmem_layout_driver, driver))
+#define to_nvmem_layout_device(_dev) \
+	container_of((_dev), struct nvmem_layout, dev)
+
+static int nvmem_layout_bus_match(struct device *dev, struct device_driver *drv)
+{
+	return of_driver_match_device(dev, drv);
+}
+
+static int nvmem_layout_bus_probe(struct device *dev)
+{
+	struct nvmem_layout_driver *drv = to_nvmem_layout_driver(dev->driver);
+	struct nvmem_layout *layout = to_nvmem_layout_device(dev);
+
+	if (!drv->probe || !drv->remove)
+		return -EINVAL;
+
+	return drv->probe(layout);
+}
+
+static void nvmem_layout_bus_remove(struct device *dev)
+{
+	struct nvmem_layout_driver *drv = to_nvmem_layout_driver(dev->driver);
+	struct nvmem_layout *layout = to_nvmem_layout_device(dev);
+
+	return drv->remove(layout);
+}
+
+static struct bus_type nvmem_layout_bus_type = {
+	.name		= "nvmem-layout",
+	.match		= nvmem_layout_bus_match,
+	.probe		= nvmem_layout_bus_probe,
+	.remove		= nvmem_layout_bus_remove,
+};
+
+int nvmem_layout_driver_register(struct nvmem_layout_driver *drv)
+{
+	drv->driver.bus = &nvmem_layout_bus_type;
+
+	return driver_register(&drv->driver);
+}
+EXPORT_SYMBOL_GPL(nvmem_layout_driver_register);
+
+void nvmem_layout_driver_unregister(struct nvmem_layout_driver *drv)
+{
+	driver_unregister(&drv->driver);
+}
+EXPORT_SYMBOL_GPL(nvmem_layout_driver_unregister);
+
+static void nvmem_layout_release_device(struct device *dev)
+{
+	struct nvmem_layout *layout = to_nvmem_layout_device(dev);
+
+	of_node_put(layout->dev.of_node);
+	kfree(layout);
+}
+
+static int nvmem_layout_create_device(struct nvmem_device *nvmem,
+				      struct device_node *np)
+{
+	struct nvmem_layout *layout;
+	struct device *dev;
+	int ret;
+
+	layout = kzalloc(sizeof(*layout), GFP_KERNEL);
+	if (!layout)
+		return -ENOMEM;
+
+	/* Create a bidirectional link */
+	layout->nvmem = nvmem;
+	nvmem->layout = layout;
+
+	/* Device model registration */
+	dev = &layout->dev;
+	device_initialize(dev);
+	dev->parent = &nvmem->dev;
+	dev->bus = &nvmem_layout_bus_type;
+	dev->release = nvmem_layout_release_device;
+	dev->coherent_dma_mask = DMA_BIT_MASK(32);
+	dev->dma_mask = &dev->coherent_dma_mask;
+	device_set_node(dev, of_fwnode_handle(of_node_get(np)));
+	of_device_make_bus_id(dev);
+	of_msi_configure(dev, dev->of_node);
+
+	ret = device_add(dev);
+	if (ret) {
+		put_device(dev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct of_device_id of_nvmem_layout_skip_table[] = {
+	{ .compatible = "fixed-layout", },
+	{}
+};
+
+static int nvmem_layout_bus_populate(struct nvmem_device *nvmem,
+				     struct device_node *layout_dn)
+{
+	int ret;
+
+	/* Make sure it has a compatible property */
+	if (!of_get_property(layout_dn, "compatible", NULL)) {
+		pr_debug("%s() - skipping %pOF, no compatible prop\n",
+			 __func__, layout_dn);
+		return 0;
+	}
+
+	/* Fixed layouts are parsed manually somewhere else for now */
+	if (of_match_node(of_nvmem_layout_skip_table, layout_dn)) {
+		pr_debug("%s() - skipping %pOF node\n", __func__, layout_dn);
+		return 0;
+	}
+
+	if (of_node_check_flag(layout_dn, OF_POPULATED_BUS)) {
+		pr_debug("%s() - skipping %pOF, already populated\n",
+			 __func__, layout_dn);
+
+		return 0;
+	}
+
+	/* NVMEM layout buses expect only a single device representing the layout */
+	ret = nvmem_layout_create_device(nvmem, layout_dn);
+	if (ret)
+		return ret;
+
+	of_node_set_flag(layout_dn, OF_POPULATED_BUS);
+
+	return 0;
+}
+
+struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem)
+{
+	return of_get_child_by_name(nvmem->dev.of_node, "nvmem-layout");
+}
+EXPORT_SYMBOL_GPL(of_nvmem_layout_get_container);
+
+/*
+ * Returns the number of devices populated, 0 if the operation was not relevant
+ * for this nvmem device, an error code otherwise.
+ */
+int nvmem_populate_layout(struct nvmem_device *nvmem)
+{
+	struct device_node *layout_dn;
+	int ret;
+
+	layout_dn = of_nvmem_layout_get_container(nvmem);
+	if (!layout_dn)
+		return 0;
+
+	/* Populate the layout device */
+	device_links_supplier_sync_state_pause();
+	ret = nvmem_layout_bus_populate(nvmem, layout_dn);
+	device_links_supplier_sync_state_resume();
+
+	of_node_put(layout_dn);
+	return ret;
+}
+
+void nvmem_destroy_layout(struct nvmem_device *nvmem)
+{
+	struct device *dev;
+
+	if (!nvmem->layout)
+		return;
+
+	dev = &nvmem->layout->dev;
+	of_node_clear_flag(dev->of_node, OF_POPULATED_BUS);
+	device_unregister(dev);
+}
+
+int nvmem_layout_bus_register(void)
+{
+	return bus_register(&nvmem_layout_bus_type);
+}
+
+void nvmem_layout_bus_unregister(void)
+{
+	bus_unregister(&nvmem_layout_bus_type);
+}
diff --git a/drivers/nvmem/layouts/Kconfig b/drivers/nvmem/layouts/Kconfig
index 7ff1ee1c1f05..9c6e672fc350 100644
--- a/drivers/nvmem/layouts/Kconfig
+++ b/drivers/nvmem/layouts/Kconfig
@@ -1,5 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0
 
+config NVMEM_LAYOUTS
+	bool
+	depends on OF
+
+if NVMEM_LAYOUTS
+
 menu "Layout Types"
 
 config NVMEM_LAYOUT_SL28_VPD
@@ -21,3 +27,5 @@ config NVMEM_LAYOUT_ONIE_TLV
 	  If unsure, say N.
 
 endmenu
+
+endif
diff --git a/drivers/nvmem/layouts/onie-tlv.c b/drivers/nvmem/layouts/onie-tlv.c
index 59fc87ccfcff..9d2ad5f2dc10 100644
--- a/drivers/nvmem/layouts/onie-tlv.c
+++ b/drivers/nvmem/layouts/onie-tlv.c
@@ -182,9 +182,10 @@ static bool onie_tlv_crc_is_valid(struct device *dev, size_t table_len, u8 *tabl
 	return true;
 }
 
-static int onie_tlv_parse_table(struct device *dev, struct nvmem_device *nvmem,
-				struct nvmem_layout *layout)
+static int onie_tlv_parse_table(struct nvmem_layout *layout)
 {
+	struct nvmem_device *nvmem = layout->nvmem;
+	struct device *dev = &layout->dev;
 	struct onie_tlv_hdr hdr;
 	size_t table_len, data_len, hdr_len;
 	u8 *table, *data;
@@ -226,16 +227,32 @@ static int onie_tlv_parse_table(struct device *dev, struct nvmem_device *nvmem,
 	return 0;
 }
 
+static int onie_tlv_probe(struct nvmem_layout *layout)
+{
+	layout->add_cells = onie_tlv_parse_table;
+
+	return nvmem_layout_register(layout);
+}
+
+static void onie_tlv_remove(struct nvmem_layout *layout)
+{
+	nvmem_layout_unregister(layout);
+}
+
 static const struct of_device_id onie_tlv_of_match_table[] = {
 	{ .compatible = "onie,tlv-layout", },
 	{},
 };
 MODULE_DEVICE_TABLE(of, onie_tlv_of_match_table);
 
-static struct nvmem_layout onie_tlv_layout = {
-	.name = "ONIE tlv layout",
-	.of_match_table = onie_tlv_of_match_table,
-	.add_cells = onie_tlv_parse_table,
+static struct nvmem_layout_driver onie_tlv_layout = {
+	.driver = {
+		.owner = THIS_MODULE,
+		.name = "onie-tlv-layout",
+		.of_match_table = onie_tlv_of_match_table,
+	},
+	.probe = onie_tlv_probe,
+	.remove = onie_tlv_remove,
 };
 module_nvmem_layout_driver(onie_tlv_layout);
 
diff --git a/drivers/nvmem/layouts/sl28vpd.c b/drivers/nvmem/layouts/sl28vpd.c
index 05671371f631..53fa50f17dca 100644
--- a/drivers/nvmem/layouts/sl28vpd.c
+++ b/drivers/nvmem/layouts/sl28vpd.c
@@ -80,9 +80,10 @@ static int sl28vpd_v1_check_crc(struct device *dev, struct nvmem_device *nvmem)
 	return 0;
 }
 
-static int sl28vpd_add_cells(struct device *dev, struct nvmem_device *nvmem,
-			     struct nvmem_layout *layout)
+static int sl28vpd_add_cells(struct nvmem_layout *layout)
 {
+	struct nvmem_device *nvmem = layout->nvmem;
+	struct device *dev = &layout->dev;
 	const struct nvmem_cell_info *pinfo;
 	struct nvmem_cell_info info = {0};
 	struct device_node *layout_np;
@@ -135,16 +136,32 @@ static int sl28vpd_add_cells(struct device *dev, struct nvmem_device *nvmem,
 	return 0;
 }
 
+static int sl28vpd_probe(struct nvmem_layout *layout)
+{
+	layout->add_cells = sl28vpd_add_cells;
+
+	return nvmem_layout_register(layout);
+}
+
+static void sl28vpd_remove(struct nvmem_layout *layout)
+{
+	nvmem_layout_unregister(layout);
+}
+
 static const struct of_device_id sl28vpd_of_match_table[] = {
 	{ .compatible = "kontron,sl28-vpd" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, sl28vpd_of_match_table);
 
-static struct nvmem_layout sl28vpd_layout = {
-	.name = "sl28-vpd",
-	.of_match_table = sl28vpd_of_match_table,
-	.add_cells = sl28vpd_add_cells,
+static struct nvmem_layout_driver sl28vpd_layout = {
+	.driver = {
+		.owner = THIS_MODULE,
+		.name = "kontron-sl28vpd-layout",
+		.of_match_table = sl28vpd_of_match_table,
+	},
+	.probe = sl28vpd_probe,
+	.remove = sl28vpd_remove,
 };
 module_nvmem_layout_driver(sl28vpd_layout);
 
diff --git a/drivers/nvmem/mtk-efuse.c b/drivers/nvmem/mtk-efuse.c
index 87c94686cfd2..84f05b40a411 100644
--- a/drivers/nvmem/mtk-efuse.c
+++ b/drivers/nvmem/mtk-efuse.c
@@ -45,9 +45,8 @@ static int mtk_efuse_gpu_speedbin_pp(void *context, const char *id, int index,
 	return 0;
 }
 
-static void mtk_efuse_fixup_cell_info(struct nvmem_device *nvmem,
-				      struct nvmem_layout *layout,
-				      struct nvmem_cell_info *cell)
+static void mtk_efuse_fixup_dt_cell_info(struct nvmem_device *nvmem,
+					 struct nvmem_cell_info *cell)
 {
 	size_t sz = strlen(cell->name);
 
@@ -61,10 +60,6 @@ static void mtk_efuse_fixup_cell_info(struct nvmem_device *nvmem,
 		cell->read_post_process = mtk_efuse_gpu_speedbin_pp;
 }
 
-static struct nvmem_layout mtk_efuse_layout = {
-	.fixup_cell_info = mtk_efuse_fixup_cell_info,
-};
-
 static int mtk_efuse_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -91,7 +86,7 @@ static int mtk_efuse_probe(struct platform_device *pdev)
 	econfig.priv = priv;
 	econfig.dev = dev;
 	if (pdata->uses_post_processing)
-		econfig.layout = &mtk_efuse_layout;
+		econfig.fixup_dt_cell_info = &mtk_efuse_fixup_dt_cell_info;
 	nvmem = devm_nvmem_register(dev, &econfig);
 
 	return PTR_ERR_OR_ZERO(nvmem);
diff --git a/drivers/nvmem/stm32-romem.c b/drivers/nvmem/stm32-romem.c
index 8a553b1799a8..82879b1c9eb9 100644
--- a/drivers/nvmem/stm32-romem.c
+++ b/drivers/nvmem/stm32-romem.c
@@ -269,6 +269,19 @@ static const struct stm32_romem_cfg stm32mp13_bsec_cfg = {
 	.ta = true,
 };
 
+/*
+ * STM32MP25 BSEC OTP: 3 regions of 32-bits data words
+ *   lower OTP (OTP0 to OTP127), bitwise (1-bit) programmable
+ *   mid OTP (OTP128 to OTP255), bulk (32-bit) programmable
+ *   upper OTP (OTP256 to OTP383), bulk (32-bit) programmable
+ *              but no access to HWKEY and ECIES key: limited at OTP367
+ */
+static const struct stm32_romem_cfg stm32mp25_bsec_cfg = {
+	.size = 368 * 4,
+	.lower = 127,
+	.ta = true,
+};
+
 static const struct of_device_id stm32_romem_of_match[] __maybe_unused = {
 	{ .compatible = "st,stm32f4-otp", }, {
 		.compatible = "st,stm32mp15-bsec",
@@ -276,6 +289,9 @@ static const struct of_device_id stm32_romem_of_match[] __maybe_unused = {
 	}, {
 		.compatible = "st,stm32mp13-bsec",
 		.data = (void *)&stm32mp13_bsec_cfg,
+	}, {
+		.compatible = "st,stm32mp25-bsec",
+		.data = (void *)&stm32mp25_bsec_cfg,
 	},
 	{ /* sentinel */ },
 };
diff --git a/drivers/nvmem/u-boot-env.c b/drivers/nvmem/u-boot-env.c
index c4ae94af4af7..befbab156cda 100644
--- a/drivers/nvmem/u-boot-env.c
+++ b/drivers/nvmem/u-boot-env.c
@@ -23,13 +23,10 @@ enum u_boot_env_format {
 
 struct u_boot_env {
 	struct device *dev;
+	struct nvmem_device *nvmem;
 	enum u_boot_env_format format;
 
 	struct mtd_info *mtd;
-
-	/* Cells */
-	struct nvmem_cell_info *cells;
-	int ncells;
 };
 
 struct u_boot_env_image_single {
@@ -94,70 +91,71 @@ static int u_boot_env_read_post_process_ethaddr(void *context, const char *id, i
 static int u_boot_env_add_cells(struct u_boot_env *priv, uint8_t *buf,
 				size_t data_offset, size_t data_len)
 {
+	struct nvmem_device *nvmem = priv->nvmem;
 	struct device *dev = priv->dev;
 	char *data = buf + data_offset;
 	char *var, *value, *eq;
-	int idx;
-
-	priv->ncells = 0;
-	for (var = data; var < data + data_len && *var; var += strlen(var) + 1)
-		priv->ncells++;
-
-	priv->cells = devm_kcalloc(dev, priv->ncells, sizeof(*priv->cells), GFP_KERNEL);
-	if (!priv->cells)
-		return -ENOMEM;
 
-	for (var = data, idx = 0;
+	for (var = data;
 	     var < data + data_len && *var;
-	     var = value + strlen(value) + 1, idx++) {
+	     var = value + strlen(value) + 1) {
+		struct nvmem_cell_info info = {};
+
 		eq = strchr(var, '=');
 		if (!eq)
 			break;
 		*eq = '\0';
 		value = eq + 1;
 
-		priv->cells[idx].name = devm_kstrdup(dev, var, GFP_KERNEL);
-		if (!priv->cells[idx].name)
+		info.name = devm_kstrdup(dev, var, GFP_KERNEL);
+		if (!info.name)
 			return -ENOMEM;
-		priv->cells[idx].offset = data_offset + value - data;
-		priv->cells[idx].bytes = strlen(value);
-		priv->cells[idx].np = of_get_child_by_name(dev->of_node, priv->cells[idx].name);
+		info.offset = data_offset + value - data;
+		info.bytes = strlen(value);
+		info.np = of_get_child_by_name(dev->of_node, info.name);
 		if (!strcmp(var, "ethaddr")) {
-			priv->cells[idx].raw_len = strlen(value);
-			priv->cells[idx].bytes = ETH_ALEN;
-			priv->cells[idx].read_post_process = u_boot_env_read_post_process_ethaddr;
+			info.raw_len = strlen(value);
+			info.bytes = ETH_ALEN;
+			info.read_post_process = u_boot_env_read_post_process_ethaddr;
 		}
-	}
 
-	if (WARN_ON(idx != priv->ncells))
-		priv->ncells = idx;
+		nvmem_add_one_cell(nvmem, &info);
+	}
 
 	return 0;
 }
 
 static int u_boot_env_parse(struct u_boot_env *priv)
 {
+	struct nvmem_device *nvmem = priv->nvmem;
 	struct device *dev = priv->dev;
 	size_t crc32_data_offset;
 	size_t crc32_data_len;
 	size_t crc32_offset;
+	__le32 *crc32_addr;
 	size_t data_offset;
 	size_t data_len;
+	size_t dev_size;
 	uint32_t crc32;
 	uint32_t calc;
-	size_t bytes;
 	uint8_t *buf;
+	int bytes;
 	int err;
 
-	buf = kcalloc(1, priv->mtd->size, GFP_KERNEL);
+	dev_size = nvmem_dev_size(nvmem);
+
+	buf = kzalloc(dev_size, GFP_KERNEL);
 	if (!buf) {
 		err = -ENOMEM;
 		goto err_out;
 	}
 
-	err = mtd_read(priv->mtd, 0, priv->mtd->size, &bytes, buf);
-	if ((err && !mtd_is_bitflip(err)) || bytes != priv->mtd->size) {
-		dev_err(dev, "Failed to read from mtd: %d\n", err);
+	bytes = nvmem_device_read(nvmem, 0, dev_size, buf);
+	if (bytes < 0) {
+		err = bytes;
+		goto err_kfree;
+	} else if (bytes != dev_size) {
+		err = -EIO;
 		goto err_kfree;
 	}
 
@@ -178,9 +176,10 @@ static int u_boot_env_parse(struct u_boot_env *priv)
 		data_offset = offsetof(struct u_boot_env_image_broadcom, data);
 		break;
 	}
-	crc32 = le32_to_cpu(*(__le32 *)(buf + crc32_offset));
-	crc32_data_len = priv->mtd->size - crc32_data_offset;
-	data_len = priv->mtd->size - data_offset;
+	crc32_addr = (__le32 *)(buf + crc32_offset);
+	crc32 = le32_to_cpu(*crc32_addr);
+	crc32_data_len = dev_size - crc32_data_offset;
+	data_len = dev_size - data_offset;
 
 	calc = crc32(~0, buf + crc32_data_offset, crc32_data_len) ^ ~0L;
 	if (calc != crc32) {
@@ -189,10 +188,8 @@ static int u_boot_env_parse(struct u_boot_env *priv)
 		goto err_kfree;
 	}
 
-	buf[priv->mtd->size - 1] = '\0';
+	buf[dev_size - 1] = '\0';
 	err = u_boot_env_add_cells(priv, buf, data_offset, data_len);
-	if (err)
-		dev_err(dev, "Failed to add cells: %d\n", err);
 
 err_kfree:
 	kfree(buf);
@@ -209,7 +206,6 @@ static int u_boot_env_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
 	struct u_boot_env *priv;
-	int err;
 
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -224,17 +220,15 @@ static int u_boot_env_probe(struct platform_device *pdev)
 		return PTR_ERR(priv->mtd);
 	}
 
-	err = u_boot_env_parse(priv);
-	if (err)
-		return err;
-
 	config.dev = dev;
-	config.cells = priv->cells;
-	config.ncells = priv->ncells;
 	config.priv = priv;
 	config.size = priv->mtd->size;
 
-	return PTR_ERR_OR_ZERO(devm_nvmem_register(dev, &config));
+	priv->nvmem = devm_nvmem_register(dev, &config);
+	if (IS_ERR(priv->nvmem))
+		return PTR_ERR(priv->nvmem);
+
+	return u_boot_env_parse(priv);
 }
 
 static const struct of_device_id u_boot_env_of_match_table[] = {
diff --git a/drivers/of/device.c b/drivers/of/device.c
index 1ca42ad9dd15..de89f9906375 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -93,12 +93,12 @@ of_dma_set_restricted_buffer(struct device *dev, struct device_node *np)
 int of_dma_configure_id(struct device *dev, struct device_node *np,
 			bool force_dma, const u32 *id)
 {
-	const struct iommu_ops *iommu;
 	const struct bus_dma_region *map = NULL;
 	struct device_node *bus_np;
 	u64 dma_start = 0;
 	u64 mask, end, size = 0;
 	bool coherent;
+	int iommu_ret;
 	int ret;
 
 	if (np == dev->of_node)
@@ -181,21 +181,29 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 	dev_dbg(dev, "device is%sdma coherent\n",
 		coherent ? " " : " not ");
 
-	iommu = of_iommu_configure(dev, np, id);
-	if (PTR_ERR(iommu) == -EPROBE_DEFER) {
+	iommu_ret = of_iommu_configure(dev, np, id);
+	if (iommu_ret == -EPROBE_DEFER) {
 		/* Don't touch range map if it wasn't set from a valid dma-ranges */
 		if (!ret)
 			dev->dma_range_map = NULL;
 		kfree(map);
 		return -EPROBE_DEFER;
-	}
+	} else if (iommu_ret == -ENODEV) {
+		dev_dbg(dev, "device is not behind an iommu\n");
+	} else if (iommu_ret) {
+		dev_err(dev, "iommu configuration for device failed with %pe\n",
+			ERR_PTR(iommu_ret));
 
-	dev_dbg(dev, "device is%sbehind an iommu\n",
-		iommu ? " " : " not ");
+		/*
+		 * Historically this routine doesn't fail driver probing
+		 * due to errors in of_iommu_configure()
+		 */
+	} else
+		dev_dbg(dev, "device is behind an iommu\n");
 
-	arch_setup_dma_ops(dev, dma_start, size, iommu, coherent);
+	arch_setup_dma_ops(dev, dma_start, size, coherent);
 
-	if (!iommu)
+	if (iommu_ret)
 		of_dma_set_restricted_buffer(dev, np);
 
 	return 0;
@@ -304,3 +312,44 @@ int of_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *
 	return 0;
 }
 EXPORT_SYMBOL_GPL(of_device_uevent_modalias);
+
+/**
+ * of_device_make_bus_id - Use the device node data to assign a unique name
+ * @dev: pointer to device structure that is linked to a device tree node
+ *
+ * This routine will first try using the translated bus address to
+ * derive a unique name. If it cannot, then it will prepend names from
+ * parent nodes until a unique name can be derived.
+ */
+void of_device_make_bus_id(struct device *dev)
+{
+	struct device_node *node = dev->of_node;
+	const __be32 *reg;
+	u64 addr;
+	u32 mask;
+
+	/* Construct the name, using parent nodes if necessary to ensure uniqueness */
+	while (node->parent) {
+		/*
+		 * If the address can be translated, then that is as much
+		 * uniqueness as we need. Make it the first component and return
+		 */
+		reg = of_get_property(node, "reg", NULL);
+		if (reg && (addr = of_translate_address(node, reg)) != OF_BAD_ADDR) {
+			if (!of_property_read_u32(node, "mask", &mask))
+				dev_set_name(dev, dev_name(dev) ? "%llx.%x.%pOFn:%s" : "%llx.%x.%pOFn",
+					     addr, ffs(mask) - 1, node, dev_name(dev));
+
+			else
+				dev_set_name(dev, dev_name(dev) ? "%llx.%pOFn:%s" : "%llx.%pOFn",
+					     addr, node, dev_name(dev));
+			return;
+		}
+
+		/* format arguments only used if dev_name() resolves to NULL */
+		dev_set_name(dev, dev_name(dev) ? "%s:%s" : "%s",
+			     kbasename(node->full_name), dev_name(dev));
+		node = node->parent;
+	}
+}
+EXPORT_SYMBOL_GPL(of_device_make_bus_id);
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index af0e1fb2ab68..b7708a06dc78 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -99,46 +99,6 @@ static const struct of_device_id of_skipped_node_table[] = {
  */
 
 /**
- * of_device_make_bus_id - Use the device node data to assign a unique name
- * @dev: pointer to device structure that is linked to a device tree node
- *
- * This routine will first try using the translated bus address to
- * derive a unique name. If it cannot, then it will prepend names from
- * parent nodes until a unique name can be derived.
- */
-static void of_device_make_bus_id(struct device *dev)
-{
-	struct device_node *node = dev->of_node;
-	const __be32 *reg;
-	u64 addr;
-	u32 mask;
-
-	/* Construct the name, using parent nodes if necessary to ensure uniqueness */
-	while (node->parent) {
-		/*
-		 * If the address can be translated, then that is as much
-		 * uniqueness as we need. Make it the first component and return
-		 */
-		reg = of_get_property(node, "reg", NULL);
-		if (reg && (addr = of_translate_address(node, reg)) != OF_BAD_ADDR) {
-			if (!of_property_read_u32(node, "mask", &mask))
-				dev_set_name(dev, dev_name(dev) ? "%llx.%x.%pOFn:%s" : "%llx.%x.%pOFn",
-					     addr, ffs(mask) - 1, node, dev_name(dev));
-
-			else
-				dev_set_name(dev, dev_name(dev) ? "%llx.%pOFn:%s" : "%llx.%pOFn",
-					     addr, node, dev_name(dev));
-			return;
-		}
-
-		/* format arguments only used if dev_name() resolves to NULL */
-		dev_set_name(dev, dev_name(dev) ? "%s:%s" : "%s",
-			     kbasename(node->full_name), dev_name(dev));
-		node = node->parent;
-	}
-}
-
-/**
  * of_device_alloc - Allocate and initialize an of_device
  * @np: device node to assign to device
  * @bus_id: Name to assign to the device.  May be null to use default name.
diff --git a/drivers/of/property.c b/drivers/of/property.c
index 641a40cf5cf3..fa8cd33be131 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -763,7 +763,9 @@ struct device_node *of_graph_get_port_parent(struct device_node *node)
 	/* Walk 3 levels up only if there is 'ports' node. */
 	for (depth = 3; depth && node; depth--) {
 		node = of_get_next_parent(node);
-		if (depth == 2 && !of_node_name_eq(node, "ports"))
+		if (depth == 2 && !of_node_name_eq(node, "ports") &&
+		    !of_node_name_eq(node, "in-ports") &&
+		    !of_node_name_eq(node, "out-ports"))
 			break;
 	}
 	return node;
@@ -1063,36 +1065,6 @@ of_fwnode_device_get_match_data(const struct fwnode_handle *fwnode,
 	return of_device_get_match_data(dev);
 }
 
-static struct device_node *of_get_compat_node(struct device_node *np)
-{
-	of_node_get(np);
-
-	while (np) {
-		if (!of_device_is_available(np)) {
-			of_node_put(np);
-			np = NULL;
-		}
-
-		if (of_property_present(np, "compatible"))
-			break;
-
-		np = of_get_next_parent(np);
-	}
-
-	return np;
-}
-
-static struct device_node *of_get_compat_node_parent(struct device_node *np)
-{
-	struct device_node *parent, *node;
-
-	parent = of_get_parent(np);
-	node = of_get_compat_node(parent);
-	of_node_put(parent);
-
-	return node;
-}
-
 static void of_link_to_phandle(struct device_node *con_np,
 			      struct device_node *sup_np)
 {
@@ -1222,10 +1194,10 @@ static struct device_node *parse_##fname(struct device_node *np,	     \
  *  parse_prop.prop_name: Name of property holding a phandle value
  *  parse_prop.index: For properties holding a list of phandles, this is the
  *		      index into the list
+ * @get_con_dev: If the consumer node containing the property is never converted
+ *		 to a struct device, implement this ops so fw_devlink can use it
+ *		 to find the true consumer.
  * @optional: Describes whether a supplier is mandatory or not
- * @node_not_dev: The consumer node containing the property is never converted
- *		  to a struct device. Instead, parse ancestor nodes for the
- *		  compatible property to find a node corresponding to a device.
  *
  * Returns:
  * parse_prop() return values are
@@ -1236,15 +1208,15 @@ static struct device_node *parse_##fname(struct device_node *np,	     \
 struct supplier_bindings {
 	struct device_node *(*parse_prop)(struct device_node *np,
 					  const char *prop_name, int index);
+	struct device_node *(*get_con_dev)(struct device_node *np);
 	bool optional;
-	bool node_not_dev;
 };
 
 DEFINE_SIMPLE_PROP(clocks, "clocks", "#clock-cells")
 DEFINE_SIMPLE_PROP(interconnects, "interconnects", "#interconnect-cells")
 DEFINE_SIMPLE_PROP(iommus, "iommus", "#iommu-cells")
 DEFINE_SIMPLE_PROP(mboxes, "mboxes", "#mbox-cells")
-DEFINE_SIMPLE_PROP(io_channels, "io-channel", "#io-channel-cells")
+DEFINE_SIMPLE_PROP(io_channels, "io-channels", "#io-channel-cells")
 DEFINE_SIMPLE_PROP(interrupt_parent, "interrupt-parent", NULL)
 DEFINE_SIMPLE_PROP(dmas, "dmas", "#dma-cells")
 DEFINE_SIMPLE_PROP(power_domains, "power-domains", "#power-domain-cells")
@@ -1262,7 +1234,6 @@ DEFINE_SIMPLE_PROP(pinctrl5, "pinctrl-5", NULL)
 DEFINE_SIMPLE_PROP(pinctrl6, "pinctrl-6", NULL)
 DEFINE_SIMPLE_PROP(pinctrl7, "pinctrl-7", NULL)
 DEFINE_SIMPLE_PROP(pinctrl8, "pinctrl-8", NULL)
-DEFINE_SIMPLE_PROP(remote_endpoint, "remote-endpoint", NULL)
 DEFINE_SIMPLE_PROP(pwms, "pwms", "#pwm-cells")
 DEFINE_SIMPLE_PROP(resets, "resets", "#reset-cells")
 DEFINE_SIMPLE_PROP(leds, "leds", NULL)
@@ -1328,6 +1299,17 @@ static struct device_node *parse_interrupts(struct device_node *np,
 	return of_irq_parse_one(np, index, &sup_args) ? NULL : sup_args.np;
 }
 
+static struct device_node *parse_remote_endpoint(struct device_node *np,
+						 const char *prop_name,
+						 int index)
+{
+	/* Return NULL for index > 0 to signify end of remote-endpoints. */
+	if (index > 0 || strcmp(prop_name, "remote-endpoint"))
+		return NULL;
+
+	return of_graph_get_remote_port_parent(np);
+}
+
 static const struct supplier_bindings of_supplier_bindings[] = {
 	{ .parse_prop = parse_clocks, },
 	{ .parse_prop = parse_interconnects, },
@@ -1352,7 +1334,10 @@ static const struct supplier_bindings of_supplier_bindings[] = {
 	{ .parse_prop = parse_pinctrl6, },
 	{ .parse_prop = parse_pinctrl7, },
 	{ .parse_prop = parse_pinctrl8, },
-	{ .parse_prop = parse_remote_endpoint, .node_not_dev = true, },
+	{
+		.parse_prop = parse_remote_endpoint,
+		.get_con_dev = of_graph_get_port_parent,
+	},
 	{ .parse_prop = parse_pwms, },
 	{ .parse_prop = parse_resets, },
 	{ .parse_prop = parse_leds, },
@@ -1403,8 +1388,8 @@ static int of_link_property(struct device_node *con_np, const char *prop_name)
 		while ((phandle = s->parse_prop(con_np, prop_name, i))) {
 			struct device_node *con_dev_np;
 
-			con_dev_np = s->node_not_dev
-					? of_get_compat_node_parent(con_np)
+			con_dev_np = s->get_con_dev
+					? s->get_con_dev(con_np)
 					: of_node_get(con_np);
 			matched = true;
 			i++;
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index cfd60e35a899..d7593bde2d02 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -50,6 +50,12 @@ static struct unittest_results {
 	failed; \
 })
 
+#ifdef CONFIG_OF_KOBJ
+#define OF_KREF_READ(NODE) kref_read(&(NODE)->kobj.kref)
+#else
+#define OF_KREF_READ(NODE) 1
+#endif
+
 /*
  * Expected message may have a message level other than KERN_INFO.
  * Print the expected message only if the current loglevel will allow
@@ -570,7 +576,7 @@ static void __init of_unittest_parse_phandle_with_args_map(void)
 			pr_err("missing testcase data\n");
 			return;
 		}
-		prefs[i] = kref_read(&p[i]->kobj.kref);
+		prefs[i] = OF_KREF_READ(p[i]);
 	}
 
 	rc = of_count_phandle_with_args(np, "phandle-list", "#phandle-cells");
@@ -693,9 +699,9 @@ static void __init of_unittest_parse_phandle_with_args_map(void)
 	unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc);
 
 	for (i = 0; i < ARRAY_SIZE(p); ++i) {
-		unittest(prefs[i] == kref_read(&p[i]->kobj.kref),
+		unittest(prefs[i] == OF_KREF_READ(p[i]),
 			 "provider%d: expected:%d got:%d\n",
-			 i, prefs[i], kref_read(&p[i]->kobj.kref));
+			 i, prefs[i], OF_KREF_READ(p[i]));
 		of_node_put(p[i]);
 	}
 }
diff --git a/drivers/parisc/power.c b/drivers/parisc/power.c
index bb0d92461b08..7a6a3e7f2825 100644
--- a/drivers/parisc/power.c
+++ b/drivers/parisc/power.c
@@ -213,7 +213,7 @@ static int __init power_init(void)
 	if (running_on_qemu && soft_power_reg)
 		register_sys_off_handler(SYS_OFF_MODE_POWER_OFF, SYS_OFF_PRIO_DEFAULT,
 					qemu_power_off, (void *)soft_power_reg);
-	else
+	if (!running_on_qemu || soft_power_reg)
 		power_task = kthread_run(kpowerswd, (void*)soft_power_reg,
 					KTHREAD_NAME);
 	if (IS_ERR(power_task)) {
diff --git a/drivers/parport/parport_serial.c b/drivers/parport/parport_serial.c
index 9f5d784cd95d..3644997a8342 100644
--- a/drivers/parport/parport_serial.c
+++ b/drivers/parport/parport_serial.c
@@ -65,6 +65,10 @@ enum parport_pc_pci_cards {
 	sunix_5069a,
 	sunix_5079a,
 	sunix_5099a,
+	brainboxes_uc257,
+	brainboxes_is300,
+	brainboxes_uc414,
+	brainboxes_px263,
 };
 
 /* each element directly indexed from enum list, above */
@@ -158,6 +162,10 @@ static struct parport_pc_pci cards[] = {
 	/* sunix_5069a */		{ 1, { { 1, 2 }, } },
 	/* sunix_5079a */		{ 1, { { 1, 2 }, } },
 	/* sunix_5099a */		{ 1, { { 1, 2 }, } },
+	/* brainboxes_uc257 */	{ 1, { { 3, -1 }, } },
+	/* brainboxes_is300 */	{ 1, { { 3, -1 }, } },
+	/* brainboxes_uc414 */  { 1, { { 3, -1 }, } },
+	/* brainboxes_px263 */	{ 1, { { 3, -1 }, } },
 };
 
 static struct pci_device_id parport_serial_pci_tbl[] = {
@@ -277,6 +285,38 @@ static struct pci_device_id parport_serial_pci_tbl[] = {
 	{ PCI_VENDOR_ID_SUNIX, PCI_DEVICE_ID_SUNIX_1999, PCI_VENDOR_ID_SUNIX,
 	  0x0104, 0, 0, sunix_5099a },
 
+	/* Brainboxes UC-203 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0bc1,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 },
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0bc2,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 },
+
+	/* Brainboxes UC-257 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0861,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 },
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0862,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 },
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0863,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 },
+
+	/* Brainboxes UC-414 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0e61,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc414 },
+
+	/* Brainboxes UC-475 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0981,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 },
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0982,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 },
+
+	/* Brainboxes IS-300/IS-500 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0da0,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_is300 },
+
+	/* Brainboxes PX-263/PX-295 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x402c,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_px263 },
+
 	{ 0, } /* terminate list */
 };
 MODULE_DEVICE_TABLE(pci,parport_serial_pci_tbl);
@@ -542,6 +582,30 @@ static struct pciserial_board pci_parport_serial_boards[] = {
 		.base_baud      = 921600,
 		.uart_offset	= 0x8,
 	},
+	[brainboxes_uc257] = {
+		.flags		= FL_BASE2,
+		.num_ports	= 2,
+		.base_baud	= 115200,
+		.uart_offset	= 8,
+	},
+	[brainboxes_is300] = {
+		.flags		= FL_BASE2,
+		.num_ports	= 1,
+		.base_baud	= 115200,
+		.uart_offset	= 8,
+	},
+	[brainboxes_uc414] = {
+		.flags		= FL_BASE2,
+		.num_ports	= 4,
+		.base_baud	= 115200,
+		.uart_offset	= 8,
+	},
+	[brainboxes_px263] = {
+		.flags		= FL_BASE2,
+		.num_ports	= 4,
+		.base_baud	= 921600,
+		.uart_offset	= 8,
+	},
 };
 
 struct parport_serial_private {
diff --git a/drivers/parport/share.c b/drivers/parport/share.c
index e21831d93305..49c74ded8a53 100644
--- a/drivers/parport/share.c
+++ b/drivers/parport/share.c
@@ -611,7 +611,7 @@ static void free_pardevice(struct device *dev)
 {
 	struct pardevice *par_dev = to_pardevice(dev);
 
-	kfree(par_dev->name);
+	kfree_const(par_dev->name);
 	kfree(par_dev);
 }
 
@@ -682,8 +682,8 @@ parport_register_dev_model(struct parport *port, const char *name,
 			   const struct pardev_cb *par_dev_cb, int id)
 {
 	struct pardevice *par_dev;
+	const char *devname;
 	int ret;
-	char *devname;
 
 	if (port->physport->flags & PARPORT_FLAG_EXCL) {
 		/* An exclusive device is registered. */
@@ -726,7 +726,7 @@ parport_register_dev_model(struct parport *port, const char *name,
 	if (!par_dev->state)
 		goto err_put_par_dev;
 
-	devname = kstrdup(name, GFP_KERNEL);
+	devname = kstrdup_const(name, GFP_KERNEL);
 	if (!devname)
 		goto err_free_par_dev;
 
@@ -804,7 +804,7 @@ parport_register_dev_model(struct parport *port, const char *name,
 	return par_dev;
 
 err_free_devname:
-	kfree(devname);
+	kfree_const(devname);
 err_free_par_dev:
 	kfree(par_dev->state);
 err_put_par_dev:
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 9c2137dae429..826b5016a101 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -386,21 +386,8 @@ void pci_bus_add_devices(const struct pci_bus *bus)
 }
 EXPORT_SYMBOL(pci_bus_add_devices);
 
-/** pci_walk_bus - walk devices on/under bus, calling callback.
- *  @top      bus whose devices should be walked
- *  @cb       callback to be called for each device found
- *  @userdata arbitrary pointer to be passed to callback.
- *
- *  Walk the given bus, including any bridged devices
- *  on buses under this bus.  Call the provided callback
- *  on each device found.
- *
- *  We check the return of @cb each time. If it returns anything
- *  other than 0, we break out.
- *
- */
-void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
-		  void *userdata)
+static void __pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
+			   void *userdata, bool locked)
 {
 	struct pci_dev *dev;
 	struct pci_bus *bus;
@@ -408,7 +395,8 @@ void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
 	int retval;
 
 	bus = top;
-	down_read(&pci_bus_sem);
+	if (!locked)
+		down_read(&pci_bus_sem);
 	next = top->devices.next;
 	for (;;) {
 		if (next == &bus->devices) {
@@ -431,10 +419,37 @@ void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
 		if (retval)
 			break;
 	}
-	up_read(&pci_bus_sem);
+	if (!locked)
+		up_read(&pci_bus_sem);
+}
+
+/**
+ *  pci_walk_bus - walk devices on/under bus, calling callback.
+ *  @top: bus whose devices should be walked
+ *  @cb: callback to be called for each device found
+ *  @userdata: arbitrary pointer to be passed to callback
+ *
+ *  Walk the given bus, including any bridged devices
+ *  on buses under this bus.  Call the provided callback
+ *  on each device found.
+ *
+ *  We check the return of @cb each time. If it returns anything
+ *  other than 0, we break out.
+ */
+void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata)
+{
+	__pci_walk_bus(top, cb, userdata, false);
 }
 EXPORT_SYMBOL_GPL(pci_walk_bus);
 
+void pci_walk_bus_locked(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata)
+{
+	lockdep_assert_held(&pci_bus_sem);
+
+	__pci_walk_bus(top, cb, userdata, true);
+}
+EXPORT_SYMBOL_GPL(pci_walk_bus_locked);
+
 struct pci_bus *pci_bus_get(struct pci_bus *bus)
 {
 	if (bus)
diff --git a/drivers/pci/controller/cadence/Kconfig b/drivers/pci/controller/cadence/Kconfig
index 291d12711363..1d5a70c9055e 100644
--- a/drivers/pci/controller/cadence/Kconfig
+++ b/drivers/pci/controller/cadence/Kconfig
@@ -47,6 +47,7 @@ config PCI_J721E
 
 config PCI_J721E_HOST
 	bool "TI J721E PCIe controller (host mode)"
+	depends on ARCH_K3 || COMPILE_TEST
 	depends on OF
 	select PCIE_CADENCE_HOST
 	select PCI_J721E
@@ -57,6 +58,7 @@ config PCI_J721E_HOST
 
 config PCI_J721E_EP
 	bool "TI J721E PCIe controller (endpoint mode)"
+	depends on ARCH_K3 || COMPILE_TEST
 	depends on OF
 	depends on PCI_ENDPOINT
 	select PCIE_CADENCE_EP
diff --git a/drivers/pci/controller/cadence/pci-j721e.c b/drivers/pci/controller/cadence/pci-j721e.c
index 2c87e7728a65..85718246016b 100644
--- a/drivers/pci/controller/cadence/pci-j721e.c
+++ b/drivers/pci/controller/cadence/pci-j721e.c
@@ -42,18 +42,16 @@ enum link_status {
 };
 
 #define J721E_MODE_RC			BIT(7)
-#define LANE_COUNT_MASK			BIT(8)
 #define LANE_COUNT(n)			((n) << 8)
 
 #define GENERATION_SEL_MASK		GENMASK(1, 0)
 
-#define MAX_LANES			2
-
 struct j721e_pcie {
 	struct cdns_pcie	*cdns_pcie;
 	struct clk		*refclk;
 	u32			mode;
 	u32			num_lanes;
+	u32			max_lanes;
 	void __iomem		*user_cfg_base;
 	void __iomem		*intd_cfg_base;
 	u32			linkdown_irq_regfield;
@@ -71,6 +69,7 @@ struct j721e_pcie_data {
 	unsigned int		quirk_disable_flr:1;
 	u32			linkdown_irq_regfield;
 	unsigned int		byte_access_allowed:1;
+	unsigned int		max_lanes;
 };
 
 static inline u32 j721e_pcie_user_readl(struct j721e_pcie *pcie, u32 offset)
@@ -206,11 +205,15 @@ static int j721e_pcie_set_lane_count(struct j721e_pcie *pcie,
 {
 	struct device *dev = pcie->cdns_pcie->dev;
 	u32 lanes = pcie->num_lanes;
+	u32 mask = BIT(8);
 	u32 val = 0;
 	int ret;
 
+	if (pcie->max_lanes == 4)
+		mask = GENMASK(9, 8);
+
 	val = LANE_COUNT(lanes - 1);
-	ret = regmap_update_bits(syscon, offset, LANE_COUNT_MASK, val);
+	ret = regmap_update_bits(syscon, offset, mask, val);
 	if (ret)
 		dev_err(dev, "failed to set link count\n");
 
@@ -290,11 +293,13 @@ static const struct j721e_pcie_data j721e_pcie_rc_data = {
 	.quirk_retrain_flag = true,
 	.byte_access_allowed = false,
 	.linkdown_irq_regfield = LINK_DOWN,
+	.max_lanes = 2,
 };
 
 static const struct j721e_pcie_data j721e_pcie_ep_data = {
 	.mode = PCI_MODE_EP,
 	.linkdown_irq_regfield = LINK_DOWN,
+	.max_lanes = 2,
 };
 
 static const struct j721e_pcie_data j7200_pcie_rc_data = {
@@ -302,23 +307,41 @@ static const struct j721e_pcie_data j7200_pcie_rc_data = {
 	.quirk_detect_quiet_flag = true,
 	.linkdown_irq_regfield = J7200_LINK_DOWN,
 	.byte_access_allowed = true,
+	.max_lanes = 2,
 };
 
 static const struct j721e_pcie_data j7200_pcie_ep_data = {
 	.mode = PCI_MODE_EP,
 	.quirk_detect_quiet_flag = true,
 	.quirk_disable_flr = true,
+	.max_lanes = 2,
 };
 
 static const struct j721e_pcie_data am64_pcie_rc_data = {
 	.mode = PCI_MODE_RC,
 	.linkdown_irq_regfield = J7200_LINK_DOWN,
 	.byte_access_allowed = true,
+	.max_lanes = 1,
 };
 
 static const struct j721e_pcie_data am64_pcie_ep_data = {
 	.mode = PCI_MODE_EP,
 	.linkdown_irq_regfield = J7200_LINK_DOWN,
+	.max_lanes = 1,
+};
+
+static const struct j721e_pcie_data j784s4_pcie_rc_data = {
+	.mode = PCI_MODE_RC,
+	.quirk_retrain_flag = true,
+	.byte_access_allowed = false,
+	.linkdown_irq_regfield = LINK_DOWN,
+	.max_lanes = 4,
+};
+
+static const struct j721e_pcie_data j784s4_pcie_ep_data = {
+	.mode = PCI_MODE_EP,
+	.linkdown_irq_regfield = LINK_DOWN,
+	.max_lanes = 4,
 };
 
 static const struct of_device_id of_j721e_pcie_match[] = {
@@ -346,6 +369,14 @@ static const struct of_device_id of_j721e_pcie_match[] = {
 		.compatible = "ti,am64-pcie-ep",
 		.data = &am64_pcie_ep_data,
 	},
+	{
+		.compatible = "ti,j784s4-pcie-host",
+		.data = &j784s4_pcie_rc_data,
+	},
+	{
+		.compatible = "ti,j784s4-pcie-ep",
+		.data = &j784s4_pcie_ep_data,
+	},
 	{},
 };
 
@@ -432,9 +463,13 @@ static int j721e_pcie_probe(struct platform_device *pdev)
 	pcie->user_cfg_base = base;
 
 	ret = of_property_read_u32(node, "num-lanes", &num_lanes);
-	if (ret || num_lanes > MAX_LANES)
+	if (ret || num_lanes > data->max_lanes) {
+		dev_warn(dev, "num-lanes property not provided or invalid, setting num-lanes to 1\n");
 		num_lanes = 1;
+	}
+
 	pcie->num_lanes = num_lanes;
+	pcie->max_lanes = data->max_lanes;
 
 	if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48)))
 		return -EINVAL;
diff --git a/drivers/pci/controller/cadence/pcie-cadence-ep.c b/drivers/pci/controller/cadence/pcie-cadence-ep.c
index 3142feb8ac19..2d0a8d78bffb 100644
--- a/drivers/pci/controller/cadence/pcie-cadence-ep.c
+++ b/drivers/pci/controller/cadence/pcie-cadence-ep.c
@@ -360,8 +360,8 @@ static void cdns_pcie_ep_assert_intx(struct cdns_pcie_ep *ep, u8 fn, u8 intx,
 	writel(0, ep->irq_cpu_addr + offset);
 }
 
-static int cdns_pcie_ep_send_legacy_irq(struct cdns_pcie_ep *ep, u8 fn, u8 vfn,
-					u8 intx)
+static int cdns_pcie_ep_send_intx_irq(struct cdns_pcie_ep *ep, u8 fn, u8 vfn,
+				      u8 intx)
 {
 	u16 cmd;
 
@@ -371,7 +371,7 @@ static int cdns_pcie_ep_send_legacy_irq(struct cdns_pcie_ep *ep, u8 fn, u8 vfn,
 
 	cdns_pcie_ep_assert_intx(ep, fn, intx, true);
 	/*
-	 * The mdelay() value was taken from dra7xx_pcie_raise_legacy_irq()
+	 * The mdelay() value was taken from dra7xx_pcie_raise_intx_irq()
 	 */
 	mdelay(1);
 	cdns_pcie_ep_assert_intx(ep, fn, intx, false);
@@ -532,25 +532,24 @@ static int cdns_pcie_ep_send_msix_irq(struct cdns_pcie_ep *ep, u8 fn, u8 vfn,
 }
 
 static int cdns_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn,
-				  enum pci_epc_irq_type type,
-				  u16 interrupt_num)
+				  unsigned int type, u16 interrupt_num)
 {
 	struct cdns_pcie_ep *ep = epc_get_drvdata(epc);
 	struct cdns_pcie *pcie = &ep->pcie;
 	struct device *dev = pcie->dev;
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		if (vfn > 0) {
-			dev_err(dev, "Cannot raise legacy interrupts for VF\n");
+			dev_err(dev, "Cannot raise INTX interrupts for VF\n");
 			return -EINVAL;
 		}
-		return cdns_pcie_ep_send_legacy_irq(ep, fn, vfn, 0);
+		return cdns_pcie_ep_send_intx_irq(ep, fn, vfn, 0);
 
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return cdns_pcie_ep_send_msi_irq(ep, fn, vfn, interrupt_num);
 
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		return cdns_pcie_ep_send_msix_irq(ep, fn, vfn, interrupt_num);
 
 	default:
diff --git a/drivers/pci/controller/cadence/pcie-cadence.h b/drivers/pci/controller/cadence/pcie-cadence.h
index 373cb50fcd15..03b96798f858 100644
--- a/drivers/pci/controller/cadence/pcie-cadence.h
+++ b/drivers/pci/controller/cadence/pcie-cadence.h
@@ -347,16 +347,16 @@ struct cdns_pcie_epf {
  * @max_regions: maximum number of regions supported by hardware
  * @ob_region_map: bitmask of mapped outbound regions
  * @ob_addr: base addresses in the AXI bus where the outbound regions start
- * @irq_phys_addr: base address on the AXI bus where the MSI/legacy IRQ
+ * @irq_phys_addr: base address on the AXI bus where the MSI/INTX IRQ
  *		   dedicated outbound regions is mapped.
  * @irq_cpu_addr: base address in the CPU space where a write access triggers
- *		  the sending of a memory write (MSI) / normal message (legacy
+ *		  the sending of a memory write (MSI) / normal message (INTX
  *		  IRQ) TLP through the PCIe bus.
- * @irq_pci_addr: used to save the current mapping of the MSI/legacy IRQ
+ * @irq_pci_addr: used to save the current mapping of the MSI/INTX IRQ
  *		  dedicated outbound region.
  * @irq_pci_fn: the latest PCI function that has updated the mapping of
- *		the MSI/legacy IRQ dedicated outbound region.
- * @irq_pending: bitmask of asserted legacy IRQs.
+ *		the MSI/INTX IRQ dedicated outbound region.
+ * @irq_pending: bitmask of asserted INTX IRQs.
  * @lock: spin lock to disable interrupts while modifying PCIe controller
  *        registers fields (RMW) accessible by both remote RC and EP to
  *        minimize time between read and write
@@ -374,7 +374,7 @@ struct cdns_pcie_ep {
 	u64			irq_pci_addr;
 	u8			irq_pci_fn;
 	u8			irq_pending;
-	/* protect writing to PCI_STATUS while raising legacy interrupts */
+	/* protect writing to PCI_STATUS while raising INTX interrupts */
 	spinlock_t		lock;
 	struct cdns_pcie_epf	*epf;
 	unsigned int		quirk_detect_quiet_flag:1;
diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig
index 5ac021dbd46a..8afacc90c63b 100644
--- a/drivers/pci/controller/dwc/Kconfig
+++ b/drivers/pci/controller/dwc/Kconfig
@@ -336,7 +336,7 @@ config PCI_EXYNOS
 config PCIE_FU740
 	bool "SiFive FU740 PCIe controller"
 	depends on PCI_MSI
-	depends on SOC_SIFIVE || COMPILE_TEST
+	depends on ARCH_SIFIVE || COMPILE_TEST
 	select PCIE_DW_HOST
 	help
 	  Say Y here if you want PCIe controller support for the SiFive
diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c
index b445ffe95e3f..0e406677060d 100644
--- a/drivers/pci/controller/dwc/pci-dra7xx.c
+++ b/drivers/pci/controller/dwc/pci-dra7xx.c
@@ -371,7 +371,7 @@ static int dra7xx_pcie_init_irq_domain(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops dra7xx_pcie_host_ops = {
-	.host_init = dra7xx_pcie_host_init,
+	.init = dra7xx_pcie_host_init,
 };
 
 static void dra7xx_pcie_ep_init(struct dw_pcie_ep *ep)
@@ -386,7 +386,7 @@ static void dra7xx_pcie_ep_init(struct dw_pcie_ep *ep)
 	dra7xx_pcie_enable_wrapper_interrupts(dra7xx);
 }
 
-static void dra7xx_pcie_raise_legacy_irq(struct dra7xx_pcie *dra7xx)
+static void dra7xx_pcie_raise_intx_irq(struct dra7xx_pcie *dra7xx)
 {
 	dra7xx_pcie_writel(dra7xx, PCIECTRL_TI_CONF_INTX_ASSERT, 0x1);
 	mdelay(1);
@@ -404,16 +404,16 @@ static void dra7xx_pcie_raise_msi_irq(struct dra7xx_pcie *dra7xx,
 }
 
 static int dra7xx_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				 enum pci_epc_irq_type type, u16 interrupt_num)
+				 unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
-		dra7xx_pcie_raise_legacy_irq(dra7xx);
+	case PCI_IRQ_INTX:
+		dra7xx_pcie_raise_intx_irq(dra7xx);
 		break;
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		dra7xx_pcie_raise_msi_irq(dra7xx, interrupt_num);
 		break;
 	default:
@@ -436,7 +436,7 @@ dra7xx_pcie_get_features(struct dw_pcie_ep *ep)
 }
 
 static const struct dw_pcie_ep_ops pcie_ep_ops = {
-	.ep_init = dra7xx_pcie_ep_init,
+	.init = dra7xx_pcie_ep_init,
 	.raise_irq = dra7xx_pcie_raise_irq,
 	.get_features = dra7xx_pcie_get_features,
 };
diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c
index c6bede346932..a33fa98a252e 100644
--- a/drivers/pci/controller/dwc/pci-exynos.c
+++ b/drivers/pci/controller/dwc/pci-exynos.c
@@ -268,7 +268,7 @@ static int exynos_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops exynos_pcie_host_ops = {
-	.host_init = exynos_pcie_host_init,
+	.init = exynos_pcie_host_init,
 };
 
 static int exynos_add_pcie_port(struct exynos_pcie *ep,
@@ -375,7 +375,7 @@ fail_probe:
 	return ret;
 }
 
-static int exynos_pcie_remove(struct platform_device *pdev)
+static void exynos_pcie_remove(struct platform_device *pdev)
 {
 	struct exynos_pcie *ep = platform_get_drvdata(pdev);
 
@@ -385,8 +385,6 @@ static int exynos_pcie_remove(struct platform_device *pdev)
 	phy_exit(ep->phy);
 	exynos_pcie_deinit_clk_resources(ep);
 	regulator_bulk_disable(ARRAY_SIZE(ep->supplies), ep->supplies);
-
-	return 0;
 }
 
 static int exynos_pcie_suspend_noirq(struct device *dev)
@@ -431,7 +429,7 @@ static const struct of_device_id exynos_pcie_of_match[] = {
 
 static struct platform_driver exynos_pcie_driver = {
 	.probe		= exynos_pcie_probe,
-	.remove		= exynos_pcie_remove,
+	.remove_new	= exynos_pcie_remove,
 	.driver = {
 		.name	= "exynos-pcie",
 		.of_match_table = exynos_pcie_of_match,
diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index 74703362aeec..dc2c036ab28c 100644
--- a/drivers/pci/controller/dwc/pci-imx6.c
+++ b/drivers/pci/controller/dwc/pci-imx6.c
@@ -1039,8 +1039,8 @@ static void imx6_pcie_host_exit(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops imx6_pcie_host_ops = {
-	.host_init = imx6_pcie_host_init,
-	.host_deinit = imx6_pcie_host_exit,
+	.init = imx6_pcie_host_init,
+	.deinit = imx6_pcie_host_exit,
 };
 
 static const struct dw_pcie_ops dw_pcie_ops = {
@@ -1058,17 +1058,16 @@ static void imx6_pcie_ep_init(struct dw_pcie_ep *ep)
 }
 
 static int imx6_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				  enum pci_epc_irq_type type,
-				  u16 interrupt_num)
+				  unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
-		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_INTX:
+		return dw_pcie_ep_raise_intx_irq(ep, func_no);
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		return dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num);
 	default:
 		dev_err(pci->dev, "UNKNOWN IRQ type\n");
@@ -1093,7 +1092,7 @@ imx6_pcie_ep_get_features(struct dw_pcie_ep *ep)
 }
 
 static const struct dw_pcie_ep_ops pcie_ep_ops = {
-	.ep_init = imx6_pcie_ep_init,
+	.init = imx6_pcie_ep_init,
 	.raise_irq = imx6_pcie_ep_raise_irq,
 	.get_features = imx6_pcie_ep_get_features,
 };
diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index 0def919f89fa..c0c62533a3f1 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -115,8 +115,7 @@ struct keystone_pcie {
 	struct dw_pcie		*pci;
 	/* PCI Device ID */
 	u32			device_id;
-	int			legacy_host_irqs[PCI_NUM_INTX];
-	struct			device_node *legacy_intc_np;
+	int			intx_host_irqs[PCI_NUM_INTX];
 
 	int			msi_host_irq;
 	int			num_lanes;
@@ -124,7 +123,7 @@ struct keystone_pcie {
 	struct phy		**phy;
 	struct device_link	**link;
 	struct			device_node *msi_intc_np;
-	struct irq_domain	*legacy_irq_domain;
+	struct irq_domain	*intx_irq_domain;
 	struct device_node	*np;
 
 	/* Application register space */
@@ -252,8 +251,8 @@ static int ks_pcie_msi_host_init(struct dw_pcie_rp *pp)
 	return dw_pcie_allocate_domains(pp);
 }
 
-static void ks_pcie_handle_legacy_irq(struct keystone_pcie *ks_pcie,
-				      int offset)
+static void ks_pcie_handle_intx_irq(struct keystone_pcie *ks_pcie,
+				    int offset)
 {
 	struct dw_pcie *pci = ks_pcie->pci;
 	struct device *dev = pci->dev;
@@ -263,7 +262,7 @@ static void ks_pcie_handle_legacy_irq(struct keystone_pcie *ks_pcie,
 
 	if (BIT(0) & pending) {
 		dev_dbg(dev, ": irq: irq_offset %d", offset);
-		generic_handle_domain_irq(ks_pcie->legacy_irq_domain, offset);
+		generic_handle_domain_irq(ks_pcie->intx_irq_domain, offset);
 	}
 
 	/* EOI the INTx interrupt */
@@ -307,38 +306,37 @@ static irqreturn_t ks_pcie_handle_error_irq(struct keystone_pcie *ks_pcie)
 	return IRQ_HANDLED;
 }
 
-static void ks_pcie_ack_legacy_irq(struct irq_data *d)
+static void ks_pcie_ack_intx_irq(struct irq_data *d)
 {
 }
 
-static void ks_pcie_mask_legacy_irq(struct irq_data *d)
+static void ks_pcie_mask_intx_irq(struct irq_data *d)
 {
 }
 
-static void ks_pcie_unmask_legacy_irq(struct irq_data *d)
+static void ks_pcie_unmask_intx_irq(struct irq_data *d)
 {
 }
 
-static struct irq_chip ks_pcie_legacy_irq_chip = {
-	.name = "Keystone-PCI-Legacy-IRQ",
-	.irq_ack = ks_pcie_ack_legacy_irq,
-	.irq_mask = ks_pcie_mask_legacy_irq,
-	.irq_unmask = ks_pcie_unmask_legacy_irq,
+static struct irq_chip ks_pcie_intx_irq_chip = {
+	.name = "Keystone-PCI-INTX-IRQ",
+	.irq_ack = ks_pcie_ack_intx_irq,
+	.irq_mask = ks_pcie_mask_intx_irq,
+	.irq_unmask = ks_pcie_unmask_intx_irq,
 };
 
-static int ks_pcie_init_legacy_irq_map(struct irq_domain *d,
-				       unsigned int irq,
-				       irq_hw_number_t hw_irq)
+static int ks_pcie_init_intx_irq_map(struct irq_domain *d,
+				     unsigned int irq, irq_hw_number_t hw_irq)
 {
-	irq_set_chip_and_handler(irq, &ks_pcie_legacy_irq_chip,
+	irq_set_chip_and_handler(irq, &ks_pcie_intx_irq_chip,
 				 handle_level_irq);
 	irq_set_chip_data(irq, d->host_data);
 
 	return 0;
 }
 
-static const struct irq_domain_ops ks_pcie_legacy_irq_domain_ops = {
-	.map = ks_pcie_init_legacy_irq_map,
+static const struct irq_domain_ops ks_pcie_intx_irq_domain_ops = {
+	.map = ks_pcie_init_intx_irq_map,
 	.xlate = irq_domain_xlate_onetwocell,
 };
 
@@ -605,22 +603,22 @@ static void ks_pcie_msi_irq_handler(struct irq_desc *desc)
 }
 
 /**
- * ks_pcie_legacy_irq_handler() - Handle legacy interrupt
+ * ks_pcie_intx_irq_handler() - Handle INTX interrupt
  * @desc: Pointer to irq descriptor
  *
- * Traverse through pending legacy interrupts and invoke handler for each. Also
+ * Traverse through pending INTX interrupts and invoke handler for each. Also
  * takes care of interrupt controller level mask/ack operation.
  */
-static void ks_pcie_legacy_irq_handler(struct irq_desc *desc)
+static void ks_pcie_intx_irq_handler(struct irq_desc *desc)
 {
 	unsigned int irq = irq_desc_get_irq(desc);
 	struct keystone_pcie *ks_pcie = irq_desc_get_handler_data(desc);
 	struct dw_pcie *pci = ks_pcie->pci;
 	struct device *dev = pci->dev;
-	u32 irq_offset = irq - ks_pcie->legacy_host_irqs[0];
+	u32 irq_offset = irq - ks_pcie->intx_host_irqs[0];
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 
-	dev_dbg(dev, ": Handling legacy irq %d\n", irq);
+	dev_dbg(dev, ": Handling INTX irq %d\n", irq);
 
 	/*
 	 * The chained irq handler installation would have replaced normal
@@ -628,7 +626,7 @@ static void ks_pcie_legacy_irq_handler(struct irq_desc *desc)
 	 * ack operation.
 	 */
 	chained_irq_enter(chip, desc);
-	ks_pcie_handle_legacy_irq(ks_pcie, irq_offset);
+	ks_pcie_handle_intx_irq(ks_pcie, irq_offset);
 	chained_irq_exit(chip, desc);
 }
 
@@ -686,10 +684,10 @@ err:
 	return ret;
 }
 
-static int ks_pcie_config_legacy_irq(struct keystone_pcie *ks_pcie)
+static int ks_pcie_config_intx_irq(struct keystone_pcie *ks_pcie)
 {
 	struct device *dev = ks_pcie->pci->dev;
-	struct irq_domain *legacy_irq_domain;
+	struct irq_domain *intx_irq_domain;
 	struct device_node *np = ks_pcie->np;
 	struct device_node *intc_np;
 	int irq_count, irq, ret = 0, i;
@@ -697,7 +695,7 @@ static int ks_pcie_config_legacy_irq(struct keystone_pcie *ks_pcie)
 	intc_np = of_get_child_by_name(np, "legacy-interrupt-controller");
 	if (!intc_np) {
 		/*
-		 * Since legacy interrupts are modeled as edge-interrupts in
+		 * Since INTX interrupts are modeled as edge-interrupts in
 		 * AM6, keep it disabled for now.
 		 */
 		if (ks_pcie->is_am6)
@@ -719,22 +717,21 @@ static int ks_pcie_config_legacy_irq(struct keystone_pcie *ks_pcie)
 			ret = -EINVAL;
 			goto err;
 		}
-		ks_pcie->legacy_host_irqs[i] = irq;
+		ks_pcie->intx_host_irqs[i] = irq;
 
 		irq_set_chained_handler_and_data(irq,
-						 ks_pcie_legacy_irq_handler,
+						 ks_pcie_intx_irq_handler,
 						 ks_pcie);
 	}
 
-	legacy_irq_domain =
-		irq_domain_add_linear(intc_np, PCI_NUM_INTX,
-				      &ks_pcie_legacy_irq_domain_ops, NULL);
-	if (!legacy_irq_domain) {
-		dev_err(dev, "Failed to add irq domain for legacy irqs\n");
+	intx_irq_domain = irq_domain_add_linear(intc_np, PCI_NUM_INTX,
+					&ks_pcie_intx_irq_domain_ops, NULL);
+	if (!intx_irq_domain) {
+		dev_err(dev, "Failed to add irq domain for INTX irqs\n");
 		ret = -EINVAL;
 		goto err;
 	}
-	ks_pcie->legacy_irq_domain = legacy_irq_domain;
+	ks_pcie->intx_irq_domain = intx_irq_domain;
 
 	for (i = 0; i < PCI_NUM_INTX; i++)
 		ks_pcie_app_writel(ks_pcie, IRQ_ENABLE_SET(i), INTx_EN);
@@ -808,7 +805,7 @@ static int __init ks_pcie_host_init(struct dw_pcie_rp *pp)
 	if (!ks_pcie->is_am6)
 		pp->bridge->child_ops = &ks_child_pcie_ops;
 
-	ret = ks_pcie_config_legacy_irq(ks_pcie);
+	ret = ks_pcie_config_intx_irq(ks_pcie);
 	if (ret)
 		return ret;
 
@@ -838,12 +835,12 @@ static int __init ks_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops ks_pcie_host_ops = {
-	.host_init = ks_pcie_host_init,
-	.msi_host_init = ks_pcie_msi_host_init,
+	.init = ks_pcie_host_init,
+	.msi_init = ks_pcie_msi_host_init,
 };
 
 static const struct dw_pcie_host_ops ks_pcie_am654_host_ops = {
-	.host_init = ks_pcie_host_init,
+	.init = ks_pcie_host_init,
 };
 
 static irqreturn_t ks_pcie_err_irq_handler(int irq, void *priv)
@@ -881,7 +878,7 @@ static void ks_pcie_am654_ep_init(struct dw_pcie_ep *ep)
 	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, flags);
 }
 
-static void ks_pcie_am654_raise_legacy_irq(struct keystone_pcie *ks_pcie)
+static void ks_pcie_am654_raise_intx_irq(struct keystone_pcie *ks_pcie)
 {
 	struct dw_pcie *pci = ks_pcie->pci;
 	u8 int_pin;
@@ -900,20 +897,19 @@ static void ks_pcie_am654_raise_legacy_irq(struct keystone_pcie *ks_pcie)
 }
 
 static int ks_pcie_am654_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				   enum pci_epc_irq_type type,
-				   u16 interrupt_num)
+				   unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
-		ks_pcie_am654_raise_legacy_irq(ks_pcie);
+	case PCI_IRQ_INTX:
+		ks_pcie_am654_raise_intx_irq(ks_pcie);
 		break;
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
 		break;
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num);
 		break;
 	default:
@@ -944,7 +940,7 @@ ks_pcie_am654_get_features(struct dw_pcie_ep *ep)
 }
 
 static const struct dw_pcie_ep_ops ks_pcie_am654_ep_ops = {
-	.ep_init = ks_pcie_am654_ep_init,
+	.init = ks_pcie_am654_ep_init,
 	.raise_irq = ks_pcie_am654_raise_irq,
 	.get_features = &ks_pcie_am654_get_features,
 };
@@ -1218,7 +1214,16 @@ static int ks_pcie_probe(struct platform_device *pdev)
 		goto err_link;
 	}
 
+	/* Obtain references to the PHYs */
+	for (i = 0; i < num_lanes; i++)
+		phy_pm_runtime_get_sync(ks_pcie->phy[i]);
+
 	ret = ks_pcie_enable_phy(ks_pcie);
+
+	/* Release references to the PHYs */
+	for (i = 0; i < num_lanes; i++)
+		phy_pm_runtime_put_sync(ks_pcie->phy[i]);
+
 	if (ret) {
 		dev_err(dev, "failed to enable phy\n");
 		goto err_link;
@@ -1302,7 +1307,7 @@ err_link:
 	return ret;
 }
 
-static int ks_pcie_remove(struct platform_device *pdev)
+static void ks_pcie_remove(struct platform_device *pdev)
 {
 	struct keystone_pcie *ks_pcie = platform_get_drvdata(pdev);
 	struct device_link **link = ks_pcie->link;
@@ -1314,13 +1319,11 @@ static int ks_pcie_remove(struct platform_device *pdev)
 	ks_pcie_disable_phy(ks_pcie);
 	while (num_lanes--)
 		device_link_del(link[num_lanes]);
-
-	return 0;
 }
 
 static struct platform_driver ks_pcie_driver = {
 	.probe  = ks_pcie_probe,
-	.remove = ks_pcie_remove,
+	.remove_new = ks_pcie_remove,
 	.driver = {
 		.name	= "keystone-pcie",
 		.of_match_table = ks_pcie_of_match,
diff --git a/drivers/pci/controller/dwc/pci-layerscape-ep.c b/drivers/pci/controller/dwc/pci-layerscape-ep.c
index 3d3c50ef4b6f..2e398494e7c0 100644
--- a/drivers/pci/controller/dwc/pci-layerscape-ep.c
+++ b/drivers/pci/controller/dwc/pci-layerscape-ep.c
@@ -49,7 +49,7 @@ struct ls_pcie_ep {
 	bool				big_endian;
 };
 
-static u32 ls_lut_readl(struct ls_pcie_ep *pcie, u32 offset)
+static u32 ls_pcie_pf_lut_readl(struct ls_pcie_ep *pcie, u32 offset)
 {
 	struct dw_pcie *pci = pcie->pci;
 
@@ -59,7 +59,7 @@ static u32 ls_lut_readl(struct ls_pcie_ep *pcie, u32 offset)
 		return ioread32(pci->dbi_base + offset);
 }
 
-static void ls_lut_writel(struct ls_pcie_ep *pcie, u32 offset, u32 value)
+static void ls_pcie_pf_lut_writel(struct ls_pcie_ep *pcie, u32 offset, u32 value)
 {
 	struct dw_pcie *pci = pcie->pci;
 
@@ -76,8 +76,8 @@ static irqreturn_t ls_pcie_ep_event_handler(int irq, void *dev_id)
 	u32 val, cfg;
 	u8 offset;
 
-	val = ls_lut_readl(pcie, PEX_PF0_PME_MES_DR);
-	ls_lut_writel(pcie, PEX_PF0_PME_MES_DR, val);
+	val = ls_pcie_pf_lut_readl(pcie, PEX_PF0_PME_MES_DR);
+	ls_pcie_pf_lut_writel(pcie, PEX_PF0_PME_MES_DR, val);
 
 	if (!val)
 		return IRQ_NONE;
@@ -96,9 +96,9 @@ static irqreturn_t ls_pcie_ep_event_handler(int irq, void *dev_id)
 		dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCAP, pcie->lnkcap);
 		dw_pcie_dbi_ro_wr_dis(pci);
 
-		cfg = ls_lut_readl(pcie, PEX_PF0_CONFIG);
+		cfg = ls_pcie_pf_lut_readl(pcie, PEX_PF0_CONFIG);
 		cfg |= PEX_PF0_CFG_READY;
-		ls_lut_writel(pcie, PEX_PF0_CONFIG, cfg);
+		ls_pcie_pf_lut_writel(pcie, PEX_PF0_CONFIG, cfg);
 		dw_pcie_ep_linkup(&pci->ep);
 
 		dev_dbg(pci->dev, "Link up\n");
@@ -130,10 +130,10 @@ static int ls_pcie_ep_interrupt_init(struct ls_pcie_ep *pcie,
 	}
 
 	/* Enable interrupts */
-	val = ls_lut_readl(pcie, PEX_PF0_PME_MES_IER);
+	val = ls_pcie_pf_lut_readl(pcie, PEX_PF0_PME_MES_IER);
 	val |=  PEX_PF0_PME_MES_IER_LDDIE | PEX_PF0_PME_MES_IER_HRDIE |
 		PEX_PF0_PME_MES_IER_LUDIE;
-	ls_lut_writel(pcie, PEX_PF0_PME_MES_IER, val);
+	ls_pcie_pf_lut_writel(pcie, PEX_PF0_PME_MES_IER, val);
 
 	return 0;
 }
@@ -166,16 +166,16 @@ static void ls_pcie_ep_init(struct dw_pcie_ep *ep)
 }
 
 static int ls_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				enum pci_epc_irq_type type, u16 interrupt_num)
+				unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
-		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_INTX:
+		return dw_pcie_ep_raise_intx_irq(ep, func_no);
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		return dw_pcie_ep_raise_msix_irq_doorbell(ep, func_no,
 							  interrupt_num);
 	default:
@@ -184,8 +184,7 @@ static int ls_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
 	}
 }
 
-static unsigned int ls_pcie_ep_func_conf_select(struct dw_pcie_ep *ep,
-						u8 func_no)
+static unsigned int ls_pcie_ep_get_dbi_offset(struct dw_pcie_ep *ep, u8 func_no)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct ls_pcie_ep *pcie = to_ls_pcie_ep(pci);
@@ -195,10 +194,10 @@ static unsigned int ls_pcie_ep_func_conf_select(struct dw_pcie_ep *ep,
 }
 
 static const struct dw_pcie_ep_ops ls_pcie_ep_ops = {
-	.ep_init = ls_pcie_ep_init,
+	.init = ls_pcie_ep_init,
 	.raise_irq = ls_pcie_ep_raise_irq,
 	.get_features = ls_pcie_ep_get_features,
-	.func_conf_select = ls_pcie_ep_func_conf_select,
+	.get_dbi_offset = ls_pcie_ep_get_dbi_offset,
 };
 
 static const struct ls_pcie_ep_drvdata ls1_ep_drvdata = {
diff --git a/drivers/pci/controller/dwc/pci-layerscape.c b/drivers/pci/controller/dwc/pci-layerscape.c
index 37956e09c65b..ee6f52568133 100644
--- a/drivers/pci/controller/dwc/pci-layerscape.c
+++ b/drivers/pci/controller/dwc/pci-layerscape.c
@@ -35,21 +35,41 @@
 #define PF_MCR_PTOMR		BIT(0)
 #define PF_MCR_EXL2S		BIT(1)
 
+/* LS1021A PEXn PM Write Control Register */
+#define SCFG_PEXPMWRCR(idx)	(0x5c + (idx) * 0x64)
+#define PMXMTTURNOFF		BIT(31)
+#define SCFG_PEXSFTRSTCR	0x190
+#define PEXSR(idx)		BIT(idx)
+
+/* LS1043A PEX PME control register */
+#define SCFG_PEXPMECR		0x144
+#define PEXPME(idx)		BIT(31 - (idx) * 4)
+
+/* LS1043A PEX LUT debug register */
+#define LS_PCIE_LDBG	0x7fc
+#define LDBG_SR		BIT(30)
+#define LDBG_WE		BIT(31)
+
 #define PCIE_IATU_NUM		6
 
 struct ls_pcie_drvdata {
-	const u32 pf_off;
+	const u32 pf_lut_off;
+	const struct dw_pcie_host_ops *ops;
+	int (*exit_from_l2)(struct dw_pcie_rp *pp);
+	bool scfg_support;
 	bool pm_support;
 };
 
 struct ls_pcie {
 	struct dw_pcie *pci;
 	const struct ls_pcie_drvdata *drvdata;
-	void __iomem *pf_base;
+	void __iomem *pf_lut_base;
+	struct regmap *scfg;
+	int index;
 	bool big_endian;
 };
 
-#define ls_pcie_pf_readl_addr(addr)	ls_pcie_pf_readl(pcie, addr)
+#define ls_pcie_pf_lut_readl_addr(addr)	ls_pcie_pf_lut_readl(pcie, addr)
 #define to_ls_pcie(x)	dev_get_drvdata((x)->dev)
 
 static bool ls_pcie_is_bridge(struct ls_pcie *pcie)
@@ -90,20 +110,20 @@ static void ls_pcie_fix_error_response(struct ls_pcie *pcie)
 	iowrite32(PCIE_ABSERR_SETTING, pci->dbi_base + PCIE_ABSERR);
 }
 
-static u32 ls_pcie_pf_readl(struct ls_pcie *pcie, u32 off)
+static u32 ls_pcie_pf_lut_readl(struct ls_pcie *pcie, u32 off)
 {
 	if (pcie->big_endian)
-		return ioread32be(pcie->pf_base + off);
+		return ioread32be(pcie->pf_lut_base + off);
 
-	return ioread32(pcie->pf_base + off);
+	return ioread32(pcie->pf_lut_base + off);
 }
 
-static void ls_pcie_pf_writel(struct ls_pcie *pcie, u32 off, u32 val)
+static void ls_pcie_pf_lut_writel(struct ls_pcie *pcie, u32 off, u32 val)
 {
 	if (pcie->big_endian)
-		iowrite32be(val, pcie->pf_base + off);
+		iowrite32be(val, pcie->pf_lut_base + off);
 	else
-		iowrite32(val, pcie->pf_base + off);
+		iowrite32(val, pcie->pf_lut_base + off);
 }
 
 static void ls_pcie_send_turnoff_msg(struct dw_pcie_rp *pp)
@@ -113,11 +133,11 @@ static void ls_pcie_send_turnoff_msg(struct dw_pcie_rp *pp)
 	u32 val;
 	int ret;
 
-	val = ls_pcie_pf_readl(pcie, LS_PCIE_PF_MCR);
+	val = ls_pcie_pf_lut_readl(pcie, LS_PCIE_PF_MCR);
 	val |= PF_MCR_PTOMR;
-	ls_pcie_pf_writel(pcie, LS_PCIE_PF_MCR, val);
+	ls_pcie_pf_lut_writel(pcie, LS_PCIE_PF_MCR, val);
 
-	ret = readx_poll_timeout(ls_pcie_pf_readl_addr, LS_PCIE_PF_MCR,
+	ret = readx_poll_timeout(ls_pcie_pf_lut_readl_addr, LS_PCIE_PF_MCR,
 				 val, !(val & PF_MCR_PTOMR),
 				 PCIE_PME_TO_L2_TIMEOUT_US/10,
 				 PCIE_PME_TO_L2_TIMEOUT_US);
@@ -125,7 +145,7 @@ static void ls_pcie_send_turnoff_msg(struct dw_pcie_rp *pp)
 		dev_err(pcie->pci->dev, "PME_Turn_off timeout\n");
 }
 
-static void ls_pcie_exit_from_l2(struct dw_pcie_rp *pp)
+static int ls_pcie_exit_from_l2(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct ls_pcie *pcie = to_ls_pcie(pci);
@@ -136,20 +156,22 @@ static void ls_pcie_exit_from_l2(struct dw_pcie_rp *pp)
 	 * Set PF_MCR_EXL2S bit in LS_PCIE_PF_MCR register for the link
 	 * to exit L2 state.
 	 */
-	val = ls_pcie_pf_readl(pcie, LS_PCIE_PF_MCR);
+	val = ls_pcie_pf_lut_readl(pcie, LS_PCIE_PF_MCR);
 	val |= PF_MCR_EXL2S;
-	ls_pcie_pf_writel(pcie, LS_PCIE_PF_MCR, val);
+	ls_pcie_pf_lut_writel(pcie, LS_PCIE_PF_MCR, val);
 
 	/*
 	 * L2 exit timeout of 10ms is not defined in the specifications,
 	 * it was chosen based on empirical observations.
 	 */
-	ret = readx_poll_timeout(ls_pcie_pf_readl_addr, LS_PCIE_PF_MCR,
+	ret = readx_poll_timeout(ls_pcie_pf_lut_readl_addr, LS_PCIE_PF_MCR,
 				 val, !(val & PF_MCR_EXL2S),
 				 1000,
 				 10000);
 	if (ret)
 		dev_err(pcie->pci->dev, "L2 exit timeout\n");
+
+	return ret;
 }
 
 static int ls_pcie_host_init(struct dw_pcie_rp *pp)
@@ -168,25 +190,130 @@ static int ls_pcie_host_init(struct dw_pcie_rp *pp)
 	return 0;
 }
 
+static void scfg_pcie_send_turnoff_msg(struct regmap *scfg, u32 reg, u32 mask)
+{
+	/* Send PME_Turn_Off message */
+	regmap_write_bits(scfg, reg, mask, mask);
+
+	/*
+	 * There is no specific register to check for PME_To_Ack from endpoint.
+	 * So on the safe side, wait for PCIE_PME_TO_L2_TIMEOUT_US.
+	 */
+	mdelay(PCIE_PME_TO_L2_TIMEOUT_US/1000);
+
+	/*
+	 * Layerscape hardware reference manual recommends clearing the PMXMTTURNOFF bit
+	 * to complete the PME_Turn_Off handshake.
+	 */
+	regmap_write_bits(scfg, reg, mask, 0);
+}
+
+static void ls1021a_pcie_send_turnoff_msg(struct dw_pcie_rp *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct ls_pcie *pcie = to_ls_pcie(pci);
+
+	scfg_pcie_send_turnoff_msg(pcie->scfg, SCFG_PEXPMWRCR(pcie->index), PMXMTTURNOFF);
+}
+
+static int scfg_pcie_exit_from_l2(struct regmap *scfg, u32 reg, u32 mask)
+{
+	/* Reset the PEX wrapper to bring the link out of L2 */
+	regmap_write_bits(scfg, reg, mask, mask);
+	regmap_write_bits(scfg, reg, mask, 0);
+
+	return 0;
+}
+
+static int ls1021a_pcie_exit_from_l2(struct dw_pcie_rp *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct ls_pcie *pcie = to_ls_pcie(pci);
+
+	return scfg_pcie_exit_from_l2(pcie->scfg, SCFG_PEXSFTRSTCR, PEXSR(pcie->index));
+}
+
+static void ls1043a_pcie_send_turnoff_msg(struct dw_pcie_rp *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct ls_pcie *pcie = to_ls_pcie(pci);
+
+	scfg_pcie_send_turnoff_msg(pcie->scfg, SCFG_PEXPMECR, PEXPME(pcie->index));
+}
+
+static int ls1043a_pcie_exit_from_l2(struct dw_pcie_rp *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct ls_pcie *pcie = to_ls_pcie(pci);
+	u32 val;
+
+	/*
+	 * Reset the PEX wrapper to bring the link out of L2.
+	 * LDBG_WE: allows the user to have write access to the PEXDBG[SR] for both setting and
+	 *	    clearing the soft reset on the PEX module.
+	 * LDBG_SR: When SR is set to 1, the PEX module enters soft reset.
+	 */
+	val = ls_pcie_pf_lut_readl(pcie, LS_PCIE_LDBG);
+	val |= LDBG_WE;
+	ls_pcie_pf_lut_writel(pcie, LS_PCIE_LDBG, val);
+
+	val = ls_pcie_pf_lut_readl(pcie, LS_PCIE_LDBG);
+	val |= LDBG_SR;
+	ls_pcie_pf_lut_writel(pcie, LS_PCIE_LDBG, val);
+
+	val = ls_pcie_pf_lut_readl(pcie, LS_PCIE_LDBG);
+	val &= ~LDBG_SR;
+	ls_pcie_pf_lut_writel(pcie, LS_PCIE_LDBG, val);
+
+	val = ls_pcie_pf_lut_readl(pcie, LS_PCIE_LDBG);
+	val &= ~LDBG_WE;
+	ls_pcie_pf_lut_writel(pcie, LS_PCIE_LDBG, val);
+
+	return 0;
+}
+
 static const struct dw_pcie_host_ops ls_pcie_host_ops = {
-	.host_init = ls_pcie_host_init,
+	.init = ls_pcie_host_init,
 	.pme_turn_off = ls_pcie_send_turnoff_msg,
 };
 
+static const struct dw_pcie_host_ops ls1021a_pcie_host_ops = {
+	.init = ls_pcie_host_init,
+	.pme_turn_off = ls1021a_pcie_send_turnoff_msg,
+};
+
 static const struct ls_pcie_drvdata ls1021a_drvdata = {
-	.pm_support = false,
+	.pm_support = true,
+	.scfg_support = true,
+	.ops = &ls1021a_pcie_host_ops,
+	.exit_from_l2 = ls1021a_pcie_exit_from_l2,
+};
+
+static const struct dw_pcie_host_ops ls1043a_pcie_host_ops = {
+	.init = ls_pcie_host_init,
+	.pme_turn_off = ls1043a_pcie_send_turnoff_msg,
+};
+
+static const struct ls_pcie_drvdata ls1043a_drvdata = {
+	.pf_lut_off = 0x10000,
+	.pm_support = true,
+	.scfg_support = true,
+	.ops = &ls1043a_pcie_host_ops,
+	.exit_from_l2 = ls1043a_pcie_exit_from_l2,
 };
 
 static const struct ls_pcie_drvdata layerscape_drvdata = {
-	.pf_off = 0xc0000,
+	.pf_lut_off = 0xc0000,
 	.pm_support = true,
+	.ops = &ls_pcie_host_ops,
+	.exit_from_l2 = ls_pcie_exit_from_l2,
 };
 
 static const struct of_device_id ls_pcie_of_match[] = {
 	{ .compatible = "fsl,ls1012a-pcie", .data = &layerscape_drvdata },
 	{ .compatible = "fsl,ls1021a-pcie", .data = &ls1021a_drvdata },
 	{ .compatible = "fsl,ls1028a-pcie", .data = &layerscape_drvdata },
-	{ .compatible = "fsl,ls1043a-pcie", .data = &ls1021a_drvdata },
+	{ .compatible = "fsl,ls1043a-pcie", .data = &ls1043a_drvdata },
 	{ .compatible = "fsl,ls1046a-pcie", .data = &layerscape_drvdata },
 	{ .compatible = "fsl,ls2080a-pcie", .data = &layerscape_drvdata },
 	{ .compatible = "fsl,ls2085a-pcie", .data = &layerscape_drvdata },
@@ -201,6 +328,8 @@ static int ls_pcie_probe(struct platform_device *pdev)
 	struct dw_pcie *pci;
 	struct ls_pcie *pcie;
 	struct resource *dbi_base;
+	u32 index[2];
+	int ret;
 
 	pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL);
 	if (!pcie)
@@ -213,9 +342,8 @@ static int ls_pcie_probe(struct platform_device *pdev)
 	pcie->drvdata = of_device_get_match_data(dev);
 
 	pci->dev = dev;
-	pci->pp.ops = &ls_pcie_host_ops;
-
 	pcie->pci = pci;
+	pci->pp.ops = pcie->drvdata->ops;
 
 	dbi_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs");
 	pci->dbi_base = devm_pci_remap_cfg_resource(dev, dbi_base);
@@ -224,7 +352,21 @@ static int ls_pcie_probe(struct platform_device *pdev)
 
 	pcie->big_endian = of_property_read_bool(dev->of_node, "big-endian");
 
-	pcie->pf_base = pci->dbi_base + pcie->drvdata->pf_off;
+	pcie->pf_lut_base = pci->dbi_base + pcie->drvdata->pf_lut_off;
+
+	if (pcie->drvdata->scfg_support) {
+		pcie->scfg = syscon_regmap_lookup_by_phandle(dev->of_node, "fsl,pcie-scfg");
+		if (IS_ERR(pcie->scfg)) {
+			dev_err(dev, "No syscfg phandle specified\n");
+			return PTR_ERR(pcie->scfg);
+		}
+
+		ret = of_property_read_u32_array(dev->of_node, "fsl,pcie-scfg", index, 2);
+		if (ret)
+			return ret;
+
+		pcie->index = index[1];
+	}
 
 	if (!ls_pcie_is_bridge(pcie))
 		return -ENODEV;
@@ -247,11 +389,14 @@ static int ls_pcie_suspend_noirq(struct device *dev)
 static int ls_pcie_resume_noirq(struct device *dev)
 {
 	struct ls_pcie *pcie = dev_get_drvdata(dev);
+	int ret;
 
 	if (!pcie->drvdata->pm_support)
 		return 0;
 
-	ls_pcie_exit_from_l2(&pcie->pci->pp);
+	ret = pcie->drvdata->exit_from_l2(&pcie->pci->pp);
+	if (ret)
+		return ret;
 
 	return dw_pcie_resume_noirq(pcie->pci);
 }
diff --git a/drivers/pci/controller/dwc/pci-meson.c b/drivers/pci/controller/dwc/pci-meson.c
index 407558f5d74a..6477c83262c2 100644
--- a/drivers/pci/controller/dwc/pci-meson.c
+++ b/drivers/pci/controller/dwc/pci-meson.c
@@ -389,7 +389,7 @@ static int meson_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops meson_pcie_host_ops = {
-	.host_init = meson_pcie_host_init,
+	.init = meson_pcie_host_init,
 };
 
 static const struct dw_pcie_ops dw_pcie_ops = {
diff --git a/drivers/pci/controller/dwc/pcie-al.c b/drivers/pci/controller/dwc/pcie-al.c
index b8cb77c9c4bd..6dfdda59f328 100644
--- a/drivers/pci/controller/dwc/pcie-al.c
+++ b/drivers/pci/controller/dwc/pcie-al.c
@@ -311,7 +311,7 @@ static int al_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops al_pcie_host_ops = {
-	.host_init = al_pcie_host_init,
+	.init = al_pcie_host_init,
 };
 
 static int al_pcie_probe(struct platform_device *pdev)
diff --git a/drivers/pci/controller/dwc/pcie-armada8k.c b/drivers/pci/controller/dwc/pcie-armada8k.c
index 5c999e15c357..b5c599ccaacf 100644
--- a/drivers/pci/controller/dwc/pcie-armada8k.c
+++ b/drivers/pci/controller/dwc/pcie-armada8k.c
@@ -225,7 +225,7 @@ static irqreturn_t armada8k_pcie_irq_handler(int irq, void *arg)
 }
 
 static const struct dw_pcie_host_ops armada8k_pcie_host_ops = {
-	.host_init = armada8k_pcie_host_init,
+	.init = armada8k_pcie_host_init,
 };
 
 static int armada8k_add_pcie_port(struct armada8k_pcie *pcie,
diff --git a/drivers/pci/controller/dwc/pcie-artpec6.c b/drivers/pci/controller/dwc/pcie-artpec6.c
index 9b572a2b2c9a..9ed0a9ba7619 100644
--- a/drivers/pci/controller/dwc/pcie-artpec6.c
+++ b/drivers/pci/controller/dwc/pcie-artpec6.c
@@ -333,7 +333,7 @@ static int artpec6_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops artpec6_pcie_host_ops = {
-	.host_init = artpec6_pcie_host_init,
+	.init = artpec6_pcie_host_init,
 };
 
 static void artpec6_pcie_ep_init(struct dw_pcie_ep *ep)
@@ -352,15 +352,15 @@ static void artpec6_pcie_ep_init(struct dw_pcie_ep *ep)
 }
 
 static int artpec6_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				  enum pci_epc_irq_type type, u16 interrupt_num)
+				  unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
-		dev_err(pci->dev, "EP cannot trigger legacy IRQs\n");
+	case PCI_IRQ_INTX:
+		dev_err(pci->dev, "EP cannot trigger INTx IRQs\n");
 		return -EINVAL;
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
 	default:
 		dev_err(pci->dev, "UNKNOWN IRQ type\n");
@@ -370,7 +370,7 @@ static int artpec6_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
 }
 
 static const struct dw_pcie_ep_ops pcie_ep_ops = {
-	.ep_init = artpec6_pcie_ep_init,
+	.init = artpec6_pcie_ep_init,
 	.raise_irq = artpec6_pcie_raise_irq,
 };
 
diff --git a/drivers/pci/controller/dwc/pcie-bt1.c b/drivers/pci/controller/dwc/pcie-bt1.c
index 17e696797ff5..76d0ddea8007 100644
--- a/drivers/pci/controller/dwc/pcie-bt1.c
+++ b/drivers/pci/controller/dwc/pcie-bt1.c
@@ -559,8 +559,8 @@ static void bt1_pcie_host_deinit(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops bt1_pcie_host_ops = {
-	.host_init = bt1_pcie_host_init,
-	.host_deinit = bt1_pcie_host_deinit,
+	.init = bt1_pcie_host_init,
+	.deinit = bt1_pcie_host_deinit,
 };
 
 static struct bt1_pcie *bt1_pcie_create_data(struct platform_device *pdev)
diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index f6207989fc6a..9a437cfce073 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -6,6 +6,7 @@
  * Author: Kishon Vijay Abraham I <kishon@ti.com>
  */
 
+#include <linux/align.h>
 #include <linux/bitfield.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
@@ -43,46 +44,19 @@ dw_pcie_ep_get_func_from_ep(struct dw_pcie_ep *ep, u8 func_no)
 	return NULL;
 }
 
-static unsigned int dw_pcie_ep_func_select(struct dw_pcie_ep *ep, u8 func_no)
-{
-	unsigned int func_offset = 0;
-
-	if (ep->ops->func_conf_select)
-		func_offset = ep->ops->func_conf_select(ep, func_no);
-
-	return func_offset;
-}
-
-static unsigned int dw_pcie_ep_get_dbi2_offset(struct dw_pcie_ep *ep, u8 func_no)
-{
-	unsigned int dbi2_offset = 0;
-
-	if (ep->ops->get_dbi2_offset)
-		dbi2_offset = ep->ops->get_dbi2_offset(ep, func_no);
-	else if (ep->ops->func_conf_select)     /* for backward compatibility */
-		dbi2_offset = ep->ops->func_conf_select(ep, func_no);
-
-	return dbi2_offset;
-}
-
 static void __dw_pcie_ep_reset_bar(struct dw_pcie *pci, u8 func_no,
 				   enum pci_barno bar, int flags)
 {
-	unsigned int func_offset, dbi2_offset;
 	struct dw_pcie_ep *ep = &pci->ep;
-	u32 reg, reg_dbi2;
-
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
-	dbi2_offset = dw_pcie_ep_get_dbi2_offset(ep, func_no);
+	u32 reg;
 
-	reg = func_offset + PCI_BASE_ADDRESS_0 + (4 * bar);
-	reg_dbi2 = dbi2_offset + PCI_BASE_ADDRESS_0 + (4 * bar);
+	reg = PCI_BASE_ADDRESS_0 + (4 * bar);
 	dw_pcie_dbi_ro_wr_en(pci);
-	dw_pcie_writel_dbi2(pci, reg_dbi2, 0x0);
-	dw_pcie_writel_dbi(pci, reg, 0x0);
+	dw_pcie_ep_writel_dbi2(ep, func_no, reg, 0x0);
+	dw_pcie_ep_writel_dbi(ep, func_no, reg, 0x0);
 	if (flags & PCI_BASE_ADDRESS_MEM_TYPE_64) {
-		dw_pcie_writel_dbi2(pci, reg_dbi2 + 4, 0x0);
-		dw_pcie_writel_dbi(pci, reg + 4, 0x0);
+		dw_pcie_ep_writel_dbi2(ep, func_no, reg + 4, 0x0);
+		dw_pcie_ep_writel_dbi(ep, func_no, reg + 4, 0x0);
 	}
 	dw_pcie_dbi_ro_wr_dis(pci);
 }
@@ -99,19 +73,15 @@ void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar)
 EXPORT_SYMBOL_GPL(dw_pcie_ep_reset_bar);
 
 static u8 __dw_pcie_ep_find_next_cap(struct dw_pcie_ep *ep, u8 func_no,
-		u8 cap_ptr, u8 cap)
+				     u8 cap_ptr, u8 cap)
 {
-	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	unsigned int func_offset = 0;
 	u8 cap_id, next_cap_ptr;
 	u16 reg;
 
 	if (!cap_ptr)
 		return 0;
 
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
-
-	reg = dw_pcie_readw_dbi(pci, func_offset + cap_ptr);
+	reg = dw_pcie_ep_readw_dbi(ep, func_no, cap_ptr);
 	cap_id = (reg & 0x00ff);
 
 	if (cap_id > PCI_CAP_ID_MAX)
@@ -126,14 +96,10 @@ static u8 __dw_pcie_ep_find_next_cap(struct dw_pcie_ep *ep, u8 func_no,
 
 static u8 dw_pcie_ep_find_capability(struct dw_pcie_ep *ep, u8 func_no, u8 cap)
 {
-	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	unsigned int func_offset = 0;
 	u8 next_cap_ptr;
 	u16 reg;
 
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
-
-	reg = dw_pcie_readw_dbi(pci, func_offset + PCI_CAPABILITY_LIST);
+	reg = dw_pcie_ep_readw_dbi(ep, func_no, PCI_CAPABILITY_LIST);
 	next_cap_ptr = (reg & 0x00ff);
 
 	return __dw_pcie_ep_find_next_cap(ep, func_no, next_cap_ptr, cap);
@@ -144,24 +110,21 @@ static int dw_pcie_ep_write_header(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	unsigned int func_offset = 0;
-
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
 
 	dw_pcie_dbi_ro_wr_en(pci);
-	dw_pcie_writew_dbi(pci, func_offset + PCI_VENDOR_ID, hdr->vendorid);
-	dw_pcie_writew_dbi(pci, func_offset + PCI_DEVICE_ID, hdr->deviceid);
-	dw_pcie_writeb_dbi(pci, func_offset + PCI_REVISION_ID, hdr->revid);
-	dw_pcie_writeb_dbi(pci, func_offset + PCI_CLASS_PROG, hdr->progif_code);
-	dw_pcie_writew_dbi(pci, func_offset + PCI_CLASS_DEVICE,
-			   hdr->subclass_code | hdr->baseclass_code << 8);
-	dw_pcie_writeb_dbi(pci, func_offset + PCI_CACHE_LINE_SIZE,
-			   hdr->cache_line_size);
-	dw_pcie_writew_dbi(pci, func_offset + PCI_SUBSYSTEM_VENDOR_ID,
-			   hdr->subsys_vendor_id);
-	dw_pcie_writew_dbi(pci, func_offset + PCI_SUBSYSTEM_ID, hdr->subsys_id);
-	dw_pcie_writeb_dbi(pci, func_offset + PCI_INTERRUPT_PIN,
-			   hdr->interrupt_pin);
+	dw_pcie_ep_writew_dbi(ep, func_no, PCI_VENDOR_ID, hdr->vendorid);
+	dw_pcie_ep_writew_dbi(ep, func_no, PCI_DEVICE_ID, hdr->deviceid);
+	dw_pcie_ep_writeb_dbi(ep, func_no, PCI_REVISION_ID, hdr->revid);
+	dw_pcie_ep_writeb_dbi(ep, func_no, PCI_CLASS_PROG, hdr->progif_code);
+	dw_pcie_ep_writew_dbi(ep, func_no, PCI_CLASS_DEVICE,
+			      hdr->subclass_code | hdr->baseclass_code << 8);
+	dw_pcie_ep_writeb_dbi(ep, func_no, PCI_CACHE_LINE_SIZE,
+			      hdr->cache_line_size);
+	dw_pcie_ep_writew_dbi(ep, func_no, PCI_SUBSYSTEM_VENDOR_ID,
+			      hdr->subsys_vendor_id);
+	dw_pcie_ep_writew_dbi(ep, func_no, PCI_SUBSYSTEM_ID, hdr->subsys_id);
+	dw_pcie_ep_writeb_dbi(ep, func_no, PCI_INTERRUPT_PIN,
+			      hdr->interrupt_pin);
 	dw_pcie_dbi_ro_wr_dis(pci);
 
 	return 0;
@@ -243,18 +206,13 @@ static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	unsigned int func_offset, dbi2_offset;
 	enum pci_barno bar = epf_bar->barno;
 	size_t size = epf_bar->size;
 	int flags = epf_bar->flags;
-	u32 reg, reg_dbi2;
 	int ret, type;
+	u32 reg;
 
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
-	dbi2_offset = dw_pcie_ep_get_dbi2_offset(ep, func_no);
-
-	reg = PCI_BASE_ADDRESS_0 + (4 * bar) + func_offset;
-	reg_dbi2 = PCI_BASE_ADDRESS_0 + (4 * bar) + dbi2_offset;
+	reg = PCI_BASE_ADDRESS_0 + (4 * bar);
 
 	if (!(flags & PCI_BASE_ADDRESS_SPACE))
 		type = PCIE_ATU_TYPE_MEM;
@@ -270,12 +228,12 @@ static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 
 	dw_pcie_dbi_ro_wr_en(pci);
 
-	dw_pcie_writel_dbi2(pci, reg_dbi2, lower_32_bits(size - 1));
-	dw_pcie_writel_dbi(pci, reg, flags);
+	dw_pcie_ep_writel_dbi2(ep, func_no, reg, lower_32_bits(size - 1));
+	dw_pcie_ep_writel_dbi(ep, func_no, reg, flags);
 
 	if (flags & PCI_BASE_ADDRESS_MEM_TYPE_64) {
-		dw_pcie_writel_dbi2(pci, reg_dbi2 + 4, upper_32_bits(size - 1));
-		dw_pcie_writel_dbi(pci, reg + 4, 0);
+		dw_pcie_ep_writel_dbi2(ep, func_no, reg + 4, upper_32_bits(size - 1));
+		dw_pcie_ep_writel_dbi(ep, func_no, reg + 4, 0);
 	}
 
 	ep->epf_bar[bar] = epf_bar;
@@ -335,19 +293,15 @@ static int dw_pcie_ep_map_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 static int dw_pcie_ep_get_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
-	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	u32 val, reg;
-	unsigned int func_offset = 0;
 	struct dw_pcie_ep_func *ep_func;
+	u32 val, reg;
 
 	ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no);
 	if (!ep_func || !ep_func->msi_cap)
 		return -EINVAL;
 
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
-
-	reg = ep_func->msi_cap + func_offset + PCI_MSI_FLAGS;
-	val = dw_pcie_readw_dbi(pci, reg);
+	reg = ep_func->msi_cap + PCI_MSI_FLAGS;
+	val = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	if (!(val & PCI_MSI_FLAGS_ENABLE))
 		return -EINVAL;
 
@@ -361,22 +315,19 @@ static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	u32 val, reg;
-	unsigned int func_offset = 0;
 	struct dw_pcie_ep_func *ep_func;
+	u32 val, reg;
 
 	ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no);
 	if (!ep_func || !ep_func->msi_cap)
 		return -EINVAL;
 
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
-
-	reg = ep_func->msi_cap + func_offset + PCI_MSI_FLAGS;
-	val = dw_pcie_readw_dbi(pci, reg);
+	reg = ep_func->msi_cap + PCI_MSI_FLAGS;
+	val = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	val &= ~PCI_MSI_FLAGS_QMASK;
 	val |= FIELD_PREP(PCI_MSI_FLAGS_QMASK, interrupts);
 	dw_pcie_dbi_ro_wr_en(pci);
-	dw_pcie_writew_dbi(pci, reg, val);
+	dw_pcie_ep_writew_dbi(ep, func_no, reg, val);
 	dw_pcie_dbi_ro_wr_dis(pci);
 
 	return 0;
@@ -385,19 +336,15 @@ static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 static int dw_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
-	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	u32 val, reg;
-	unsigned int func_offset = 0;
 	struct dw_pcie_ep_func *ep_func;
+	u32 val, reg;
 
 	ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no);
 	if (!ep_func || !ep_func->msix_cap)
 		return -EINVAL;
 
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
-
-	reg = ep_func->msix_cap + func_offset + PCI_MSIX_FLAGS;
-	val = dw_pcie_readw_dbi(pci, reg);
+	reg = ep_func->msix_cap + PCI_MSIX_FLAGS;
+	val = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	if (!(val & PCI_MSIX_FLAGS_ENABLE))
 		return -EINVAL;
 
@@ -411,9 +358,8 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	u32 val, reg;
-	unsigned int func_offset = 0;
 	struct dw_pcie_ep_func *ep_func;
+	u32 val, reg;
 
 	ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no);
 	if (!ep_func || !ep_func->msix_cap)
@@ -421,21 +367,19 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 
 	dw_pcie_dbi_ro_wr_en(pci);
 
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
-
-	reg = ep_func->msix_cap + func_offset + PCI_MSIX_FLAGS;
-	val = dw_pcie_readw_dbi(pci, reg);
+	reg = ep_func->msix_cap + PCI_MSIX_FLAGS;
+	val = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	val &= ~PCI_MSIX_FLAGS_QSIZE;
 	val |= interrupts;
 	dw_pcie_writew_dbi(pci, reg, val);
 
-	reg = ep_func->msix_cap + func_offset + PCI_MSIX_TABLE;
+	reg = ep_func->msix_cap + PCI_MSIX_TABLE;
 	val = offset | bir;
-	dw_pcie_writel_dbi(pci, reg, val);
+	dw_pcie_ep_writel_dbi(ep, func_no, reg, val);
 
-	reg = ep_func->msix_cap + func_offset + PCI_MSIX_PBA;
+	reg = ep_func->msix_cap + PCI_MSIX_PBA;
 	val = (offset + (interrupts * PCI_MSIX_ENTRY_SIZE)) | bir;
-	dw_pcie_writel_dbi(pci, reg, val);
+	dw_pcie_ep_writel_dbi(ep, func_no, reg, val);
 
 	dw_pcie_dbi_ro_wr_dis(pci);
 
@@ -443,7 +387,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 }
 
 static int dw_pcie_ep_raise_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-				enum pci_epc_irq_type type, u16 interrupt_num)
+				unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 
@@ -496,56 +440,53 @@ static const struct pci_epc_ops epc_ops = {
 	.get_features		= dw_pcie_ep_get_features,
 };
 
-int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no)
+int dw_pcie_ep_raise_intx_irq(struct dw_pcie_ep *ep, u8 func_no)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct device *dev = pci->dev;
 
-	dev_err(dev, "EP cannot trigger legacy IRQs\n");
+	dev_err(dev, "EP cannot raise INTX IRQs\n");
 
 	return -EINVAL;
 }
-EXPORT_SYMBOL_GPL(dw_pcie_ep_raise_legacy_irq);
+EXPORT_SYMBOL_GPL(dw_pcie_ep_raise_intx_irq);
 
 int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 			     u8 interrupt_num)
 {
-	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	u32 msg_addr_lower, msg_addr_upper, reg;
 	struct dw_pcie_ep_func *ep_func;
 	struct pci_epc *epc = ep->epc;
 	unsigned int aligned_offset;
-	unsigned int func_offset = 0;
 	u16 msg_ctrl, msg_data;
-	u32 msg_addr_lower, msg_addr_upper, reg;
-	u64 msg_addr;
 	bool has_upper;
+	u64 msg_addr;
 	int ret;
 
 	ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no);
 	if (!ep_func || !ep_func->msi_cap)
 		return -EINVAL;
 
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
-
 	/* Raise MSI per the PCI Local Bus Specification Revision 3.0, 6.8.1. */
-	reg = ep_func->msi_cap + func_offset + PCI_MSI_FLAGS;
-	msg_ctrl = dw_pcie_readw_dbi(pci, reg);
+	reg = ep_func->msi_cap + PCI_MSI_FLAGS;
+	msg_ctrl = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	has_upper = !!(msg_ctrl & PCI_MSI_FLAGS_64BIT);
-	reg = ep_func->msi_cap + func_offset + PCI_MSI_ADDRESS_LO;
-	msg_addr_lower = dw_pcie_readl_dbi(pci, reg);
+	reg = ep_func->msi_cap + PCI_MSI_ADDRESS_LO;
+	msg_addr_lower = dw_pcie_ep_readl_dbi(ep, func_no, reg);
 	if (has_upper) {
-		reg = ep_func->msi_cap + func_offset + PCI_MSI_ADDRESS_HI;
-		msg_addr_upper = dw_pcie_readl_dbi(pci, reg);
-		reg = ep_func->msi_cap + func_offset + PCI_MSI_DATA_64;
-		msg_data = dw_pcie_readw_dbi(pci, reg);
+		reg = ep_func->msi_cap + PCI_MSI_ADDRESS_HI;
+		msg_addr_upper = dw_pcie_ep_readl_dbi(ep, func_no, reg);
+		reg = ep_func->msi_cap + PCI_MSI_DATA_64;
+		msg_data = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	} else {
 		msg_addr_upper = 0;
-		reg = ep_func->msi_cap + func_offset + PCI_MSI_DATA_32;
-		msg_data = dw_pcie_readw_dbi(pci, reg);
+		reg = ep_func->msi_cap + PCI_MSI_DATA_32;
+		msg_data = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	}
-	aligned_offset = msg_addr_lower & (epc->mem->window.page_size - 1);
-	msg_addr = ((u64)msg_addr_upper) << 32 |
-			(msg_addr_lower & ~aligned_offset);
+	msg_addr = ((u64)msg_addr_upper) << 32 | msg_addr_lower;
+
+	aligned_offset = msg_addr & (epc->mem->window.page_size - 1);
+	msg_addr = ALIGN_DOWN(msg_addr, epc->mem->window.page_size);
 	ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr,
 				  epc->mem->window.page_size);
 	if (ret)
@@ -582,10 +523,9 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
 			      u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	struct dw_pcie_ep_func *ep_func;
 	struct pci_epf_msix_tbl *msix_tbl;
+	struct dw_pcie_ep_func *ep_func;
 	struct pci_epc *epc = ep->epc;
-	unsigned int func_offset = 0;
 	u32 reg, msg_data, vec_ctrl;
 	unsigned int aligned_offset;
 	u32 tbl_offset;
@@ -597,10 +537,8 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
 	if (!ep_func || !ep_func->msix_cap)
 		return -EINVAL;
 
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
-
-	reg = ep_func->msix_cap + func_offset + PCI_MSIX_TABLE;
-	tbl_offset = dw_pcie_readl_dbi(pci, reg);
+	reg = ep_func->msix_cap + PCI_MSIX_TABLE;
+	tbl_offset = dw_pcie_ep_readl_dbi(ep, func_no, reg);
 	bir = FIELD_GET(PCI_MSIX_TABLE_BIR, tbl_offset);
 	tbl_offset &= PCI_MSIX_TABLE_OFFSET;
 
@@ -615,6 +553,7 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
 	}
 
 	aligned_offset = msg_addr & (epc->mem->window.page_size - 1);
+	msg_addr = ALIGN_DOWN(msg_addr, epc->mem->window.page_size);
 	ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr,
 				  epc->mem->window.page_size);
 	if (ret)
@@ -794,8 +733,8 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep)
 		list_add_tail(&ep_func->list, &ep->func_list);
 	}
 
-	if (ep->ops->ep_init)
-		ep->ops->ep_init(ep);
+	if (ep->ops->init)
+		ep->ops->init(ep);
 
 	ret = pci_epc_mem_init(epc, ep->phys_base, ep->addr_size,
 			       ep->page_size);
diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index 7991f0e179b2..d5fc31f8345f 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -441,14 +441,14 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp)
 	bridge->ops = &dw_pcie_ops;
 	bridge->child_ops = &dw_child_pcie_ops;
 
-	if (pp->ops->host_init) {
-		ret = pp->ops->host_init(pp);
+	if (pp->ops->init) {
+		ret = pp->ops->init(pp);
 		if (ret)
 			return ret;
 	}
 
 	if (pci_msi_enabled()) {
-		pp->has_msi_ctrl = !(pp->ops->msi_host_init ||
+		pp->has_msi_ctrl = !(pp->ops->msi_init ||
 				     of_property_read_bool(np, "msi-parent") ||
 				     of_property_read_bool(np, "msi-map"));
 
@@ -464,8 +464,8 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp)
 			goto err_deinit_host;
 		}
 
-		if (pp->ops->msi_host_init) {
-			ret = pp->ops->msi_host_init(pp);
+		if (pp->ops->msi_init) {
+			ret = pp->ops->msi_init(pp);
 			if (ret < 0)
 				goto err_deinit_host;
 		} else if (pp->has_msi_ctrl) {
@@ -502,8 +502,8 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp)
 	if (ret)
 		goto err_stop_link;
 
-	if (pp->ops->host_post_init)
-		pp->ops->host_post_init(pp);
+	if (pp->ops->post_init)
+		pp->ops->post_init(pp);
 
 	return 0;
 
@@ -518,8 +518,8 @@ err_free_msi:
 		dw_pcie_free_msi(pp);
 
 err_deinit_host:
-	if (pp->ops->host_deinit)
-		pp->ops->host_deinit(pp);
+	if (pp->ops->deinit)
+		pp->ops->deinit(pp);
 
 	return ret;
 }
@@ -539,8 +539,8 @@ void dw_pcie_host_deinit(struct dw_pcie_rp *pp)
 	if (pp->has_msi_ctrl)
 		dw_pcie_free_msi(pp);
 
-	if (pp->ops->host_deinit)
-		pp->ops->host_deinit(pp);
+	if (pp->ops->deinit)
+		pp->ops->deinit(pp);
 }
 EXPORT_SYMBOL_GPL(dw_pcie_host_deinit);
 
@@ -842,8 +842,8 @@ int dw_pcie_suspend_noirq(struct dw_pcie *pci)
 		return ret;
 	}
 
-	if (pci->pp.ops->host_deinit)
-		pci->pp.ops->host_deinit(&pci->pp);
+	if (pci->pp.ops->deinit)
+		pci->pp.ops->deinit(&pci->pp);
 
 	pci->suspended = true;
 
@@ -860,8 +860,8 @@ int dw_pcie_resume_noirq(struct dw_pcie *pci)
 
 	pci->suspended = false;
 
-	if (pci->pp.ops->host_init) {
-		ret = pci->pp.ops->host_init(&pci->pp);
+	if (pci->pp.ops->init) {
+		ret = pci->pp.ops->init(&pci->pp);
 		if (ret) {
 			dev_err(pci->dev, "Host init failed: %d\n", ret);
 			return ret;
diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c
index b625841e98aa..778588b4be70 100644
--- a/drivers/pci/controller/dwc/pcie-designware-plat.c
+++ b/drivers/pci/controller/dwc/pcie-designware-plat.c
@@ -42,17 +42,16 @@ static void dw_plat_pcie_ep_init(struct dw_pcie_ep *ep)
 }
 
 static int dw_plat_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				     enum pci_epc_irq_type type,
-				     u16 interrupt_num)
+				     unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
-		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_INTX:
+		return dw_pcie_ep_raise_intx_irq(ep, func_no);
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		return dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num);
 	default:
 		dev_err(pci->dev, "UNKNOWN IRQ type\n");
@@ -74,7 +73,7 @@ dw_plat_pcie_get_features(struct dw_pcie_ep *ep)
 }
 
 static const struct dw_pcie_ep_ops pcie_ep_ops = {
-	.ep_init = dw_plat_pcie_ep_init,
+	.init = dw_plat_pcie_ep_init,
 	.raise_irq = dw_plat_pcie_ep_raise_irq,
 	.get_features = dw_plat_pcie_get_features,
 };
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index 55ff76e3d384..26dae4837462 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -300,10 +300,10 @@ enum dw_pcie_ltssm {
 };
 
 struct dw_pcie_host_ops {
-	int (*host_init)(struct dw_pcie_rp *pp);
-	void (*host_deinit)(struct dw_pcie_rp *pp);
-	void (*host_post_init)(struct dw_pcie_rp *pp);
-	int (*msi_host_init)(struct dw_pcie_rp *pp);
+	int (*init)(struct dw_pcie_rp *pp);
+	void (*deinit)(struct dw_pcie_rp *pp);
+	void (*post_init)(struct dw_pcie_rp *pp);
+	int (*msi_init)(struct dw_pcie_rp *pp);
 	void (*pme_turn_off)(struct dw_pcie_rp *pp);
 };
 
@@ -332,10 +332,10 @@ struct dw_pcie_rp {
 
 struct dw_pcie_ep_ops {
 	void	(*pre_init)(struct dw_pcie_ep *ep);
-	void	(*ep_init)(struct dw_pcie_ep *ep);
+	void	(*init)(struct dw_pcie_ep *ep);
 	void	(*deinit)(struct dw_pcie_ep *ep);
 	int	(*raise_irq)(struct dw_pcie_ep *ep, u8 func_no,
-			     enum pci_epc_irq_type type, u16 interrupt_num);
+			     unsigned int type, u16 interrupt_num);
 	const struct pci_epc_features* (*get_features)(struct dw_pcie_ep *ep);
 	/*
 	 * Provide a method to implement the different func config space
@@ -344,7 +344,7 @@ struct dw_pcie_ep_ops {
 	 * return a 0, and implement code in callback function of platform
 	 * driver.
 	 */
-	unsigned int (*func_conf_select)(struct dw_pcie_ep *ep, u8 func_no);
+	unsigned int (*get_dbi_offset)(struct dw_pcie_ep *ep, u8 func_no);
 	unsigned int (*get_dbi2_offset)(struct dw_pcie_ep *ep, u8 func_no);
 };
 
@@ -486,6 +486,99 @@ static inline void dw_pcie_writel_dbi2(struct dw_pcie *pci, u32 reg, u32 val)
 	dw_pcie_write_dbi2(pci, reg, 0x4, val);
 }
 
+static inline unsigned int dw_pcie_ep_get_dbi_offset(struct dw_pcie_ep *ep,
+						     u8 func_no)
+{
+	unsigned int dbi_offset = 0;
+
+	if (ep->ops->get_dbi_offset)
+		dbi_offset = ep->ops->get_dbi_offset(ep, func_no);
+
+	return dbi_offset;
+}
+
+static inline u32 dw_pcie_ep_read_dbi(struct dw_pcie_ep *ep, u8 func_no,
+				      u32 reg, size_t size)
+{
+	unsigned int offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
+	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+
+	return dw_pcie_read_dbi(pci, offset + reg, size);
+}
+
+static inline void dw_pcie_ep_write_dbi(struct dw_pcie_ep *ep, u8 func_no,
+					u32 reg, size_t size, u32 val)
+{
+	unsigned int offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
+	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+
+	dw_pcie_write_dbi(pci, offset + reg, size, val);
+}
+
+static inline void dw_pcie_ep_writel_dbi(struct dw_pcie_ep *ep, u8 func_no,
+					 u32 reg, u32 val)
+{
+	dw_pcie_ep_write_dbi(ep, func_no, reg, 0x4, val);
+}
+
+static inline u32 dw_pcie_ep_readl_dbi(struct dw_pcie_ep *ep, u8 func_no,
+				       u32 reg)
+{
+	return dw_pcie_ep_read_dbi(ep, func_no, reg, 0x4);
+}
+
+static inline void dw_pcie_ep_writew_dbi(struct dw_pcie_ep *ep, u8 func_no,
+					 u32 reg, u16 val)
+{
+	dw_pcie_ep_write_dbi(ep, func_no, reg, 0x2, val);
+}
+
+static inline u16 dw_pcie_ep_readw_dbi(struct dw_pcie_ep *ep, u8 func_no,
+				       u32 reg)
+{
+	return dw_pcie_ep_read_dbi(ep, func_no, reg, 0x2);
+}
+
+static inline void dw_pcie_ep_writeb_dbi(struct dw_pcie_ep *ep, u8 func_no,
+					 u32 reg, u8 val)
+{
+	dw_pcie_ep_write_dbi(ep, func_no, reg, 0x1, val);
+}
+
+static inline u8 dw_pcie_ep_readb_dbi(struct dw_pcie_ep *ep, u8 func_no,
+				      u32 reg)
+{
+	return dw_pcie_ep_read_dbi(ep, func_no, reg, 0x1);
+}
+
+static inline unsigned int dw_pcie_ep_get_dbi2_offset(struct dw_pcie_ep *ep,
+						      u8 func_no)
+{
+	unsigned int dbi2_offset = 0;
+
+	if (ep->ops->get_dbi2_offset)
+		dbi2_offset = ep->ops->get_dbi2_offset(ep, func_no);
+	else if (ep->ops->get_dbi_offset)     /* for backward compatibility */
+		dbi2_offset = ep->ops->get_dbi_offset(ep, func_no);
+
+	return dbi2_offset;
+}
+
+static inline void dw_pcie_ep_write_dbi2(struct dw_pcie_ep *ep, u8 func_no,
+					 u32 reg, size_t size, u32 val)
+{
+	unsigned int offset = dw_pcie_ep_get_dbi2_offset(ep, func_no);
+	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+
+	dw_pcie_write_dbi2(pci, offset + reg, size, val);
+}
+
+static inline void dw_pcie_ep_writel_dbi2(struct dw_pcie_ep *ep, u8 func_no,
+					  u32 reg, u32 val)
+{
+	dw_pcie_ep_write_dbi2(ep, func_no, reg, 0x4, val);
+}
+
 static inline void dw_pcie_dbi_ro_wr_en(struct dw_pcie *pci)
 {
 	u32 reg;
@@ -580,7 +673,7 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep);
 int dw_pcie_ep_init_complete(struct dw_pcie_ep *ep);
 void dw_pcie_ep_init_notify(struct dw_pcie_ep *ep);
 void dw_pcie_ep_exit(struct dw_pcie_ep *ep);
-int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no);
+int dw_pcie_ep_raise_intx_irq(struct dw_pcie_ep *ep, u8 func_no);
 int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 			     u8 interrupt_num);
 int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
@@ -613,7 +706,7 @@ static inline void dw_pcie_ep_exit(struct dw_pcie_ep *ep)
 {
 }
 
-static inline int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no)
+static inline int dw_pcie_ep_raise_intx_irq(struct dw_pcie_ep *ep, u8 func_no)
 {
 	return 0;
 }
diff --git a/drivers/pci/controller/dwc/pcie-dw-rockchip.c b/drivers/pci/controller/dwc/pcie-dw-rockchip.c
index 2fe42c70097f..d6842141d384 100644
--- a/drivers/pci/controller/dwc/pcie-dw-rockchip.c
+++ b/drivers/pci/controller/dwc/pcie-dw-rockchip.c
@@ -72,7 +72,7 @@ static void rockchip_pcie_writel_apb(struct rockchip_pcie *rockchip,
 	writel_relaxed(val, rockchip->apb_base + reg);
 }
 
-static void rockchip_pcie_legacy_int_handler(struct irq_desc *desc)
+static void rockchip_pcie_intx_handler(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct rockchip_pcie *rockchip = irq_desc_get_handler_data(desc);
@@ -202,7 +202,7 @@ static int rockchip_pcie_host_init(struct dw_pcie_rp *pp)
 	if (ret < 0)
 		dev_err(dev, "failed to init irq domain\n");
 
-	irq_set_chained_handler_and_data(irq, rockchip_pcie_legacy_int_handler,
+	irq_set_chained_handler_and_data(irq, rockchip_pcie_intx_handler,
 					 rockchip);
 
 	/* LTSSM enable control mode */
@@ -215,7 +215,7 @@ static int rockchip_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops rockchip_pcie_host_ops = {
-	.host_init = rockchip_pcie_host_init,
+	.init = rockchip_pcie_host_init,
 };
 
 static int rockchip_pcie_clk_init(struct rockchip_pcie *rockchip)
diff --git a/drivers/pci/controller/dwc/pcie-fu740.c b/drivers/pci/controller/dwc/pcie-fu740.c
index 1e9b44b8bba4..66367252032b 100644
--- a/drivers/pci/controller/dwc/pcie-fu740.c
+++ b/drivers/pci/controller/dwc/pcie-fu740.c
@@ -279,7 +279,7 @@ static int fu740_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops fu740_pcie_host_ops = {
-	.host_init = fu740_pcie_host_init,
+	.init = fu740_pcie_host_init,
 };
 
 static const struct dw_pcie_ops dw_pcie_ops = {
diff --git a/drivers/pci/controller/dwc/pcie-histb.c b/drivers/pci/controller/dwc/pcie-histb.c
index fd484cc7c481..7a11c618b9d9 100644
--- a/drivers/pci/controller/dwc/pcie-histb.c
+++ b/drivers/pci/controller/dwc/pcie-histb.c
@@ -198,7 +198,7 @@ static int histb_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops histb_pcie_host_ops = {
-	.host_init = histb_pcie_host_init,
+	.init = histb_pcie_host_init,
 };
 
 static void histb_pcie_host_disable(struct histb_pcie *hipcie)
diff --git a/drivers/pci/controller/dwc/pcie-intel-gw.c b/drivers/pci/controller/dwc/pcie-intel-gw.c
index c9c93524e01d..acbe4f6d3291 100644
--- a/drivers/pci/controller/dwc/pcie-intel-gw.c
+++ b/drivers/pci/controller/dwc/pcie-intel-gw.c
@@ -391,7 +391,7 @@ static const struct dw_pcie_ops intel_pcie_ops = {
 };
 
 static const struct dw_pcie_host_ops intel_pcie_dw_ops = {
-	.host_init =		intel_pcie_rc_init,
+	.init = intel_pcie_rc_init,
 };
 
 static int intel_pcie_probe(struct platform_device *pdev)
diff --git a/drivers/pci/controller/dwc/pcie-keembay.c b/drivers/pci/controller/dwc/pcie-keembay.c
index 289bff99d762..208d3b0ba196 100644
--- a/drivers/pci/controller/dwc/pcie-keembay.c
+++ b/drivers/pci/controller/dwc/pcie-keembay.c
@@ -289,19 +289,18 @@ static void keembay_pcie_ep_init(struct dw_pcie_ep *ep)
 }
 
 static int keembay_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				     enum pci_epc_irq_type type,
-				     u16 interrupt_num)
+				     unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
-		/* Legacy interrupts are not supported in Keem Bay */
-		dev_err(pci->dev, "Legacy IRQ is not supported\n");
+	case PCI_IRQ_INTX:
+		/* INTx interrupts are not supported in Keem Bay */
+		dev_err(pci->dev, "INTx IRQ is not supported\n");
 		return -EINVAL;
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		return dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num);
 	default:
 		dev_err(pci->dev, "Unknown IRQ type %d\n", type);
@@ -325,7 +324,7 @@ keembay_pcie_get_features(struct dw_pcie_ep *ep)
 }
 
 static const struct dw_pcie_ep_ops keembay_pcie_ep_ops = {
-	.ep_init	= keembay_pcie_ep_init,
+	.init		= keembay_pcie_ep_init,
 	.raise_irq	= keembay_pcie_ep_raise_irq,
 	.get_features	= keembay_pcie_get_features,
 };
diff --git a/drivers/pci/controller/dwc/pcie-kirin.c b/drivers/pci/controller/dwc/pcie-kirin.c
index 2ee146767971..d5523f302102 100644
--- a/drivers/pci/controller/dwc/pcie-kirin.c
+++ b/drivers/pci/controller/dwc/pcie-kirin.c
@@ -366,7 +366,6 @@ static int kirin_pcie_get_gpio_enable(struct kirin_pcie *pcie,
 				      struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	char name[32];
 	int ret, i;
 
 	/* This is an optional property */
@@ -387,9 +386,8 @@ static int kirin_pcie_get_gpio_enable(struct kirin_pcie *pcie,
 		if (pcie->gpio_id_clkreq[i] < 0)
 			return pcie->gpio_id_clkreq[i];
 
-		sprintf(name, "pcie_clkreq_%d", i);
-		pcie->clkreq_names[i] = devm_kstrdup_const(dev, name,
-							    GFP_KERNEL);
+		pcie->clkreq_names[i] = devm_kasprintf(dev, GFP_KERNEL,
+						       "pcie_clkreq_%d", i);
 		if (!pcie->clkreq_names[i])
 			return -ENOMEM;
 	}
@@ -404,7 +402,6 @@ static int kirin_pcie_parse_port(struct kirin_pcie *pcie,
 	struct device *dev = &pdev->dev;
 	struct device_node *parent, *child;
 	int ret, slot, i;
-	char name[32];
 
 	for_each_available_child_of_node(node, parent) {
 		for_each_available_child_of_node(parent, child) {
@@ -430,9 +427,9 @@ static int kirin_pcie_parse_port(struct kirin_pcie *pcie,
 
 			slot = PCI_SLOT(ret);
 
-			sprintf(name, "pcie_perst_%d", slot);
-			pcie->reset_names[i] = devm_kstrdup_const(dev, name,
-								GFP_KERNEL);
+			pcie->reset_names[i] = devm_kasprintf(dev, GFP_KERNEL,
+							      "pcie_perst_%d",
+							      slot);
 			if (!pcie->reset_names[i]) {
 				ret = -ENOMEM;
 				goto put_node;
@@ -672,7 +669,7 @@ static const struct dw_pcie_ops kirin_dw_pcie_ops = {
 };
 
 static const struct dw_pcie_host_ops kirin_pcie_host_ops = {
-	.host_init = kirin_pcie_host_init,
+	.init = kirin_pcie_host_init,
 };
 
 static int kirin_pcie_power_off(struct kirin_pcie *kirin_pcie)
@@ -741,15 +738,13 @@ err:
 	return ret;
 }
 
-static int kirin_pcie_remove(struct platform_device *pdev)
+static void kirin_pcie_remove(struct platform_device *pdev)
 {
 	struct kirin_pcie *kirin_pcie = platform_get_drvdata(pdev);
 
 	dw_pcie_host_deinit(&kirin_pcie->pci->pp);
 
 	kirin_pcie_power_off(kirin_pcie);
-
-	return 0;
 }
 
 struct kirin_pcie_data {
@@ -818,7 +813,7 @@ static int kirin_pcie_probe(struct platform_device *pdev)
 
 static struct platform_driver kirin_pcie_driver = {
 	.probe			= kirin_pcie_probe,
-	.remove	        	= kirin_pcie_remove,
+	.remove_new		= kirin_pcie_remove,
 	.driver			= {
 		.name			= "kirin-pcie",
 		.of_match_table		= kirin_pcie_match,
diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c
index 9e58f055199a..36e5e80cd22f 100644
--- a/drivers/pci/controller/dwc/pcie-qcom-ep.c
+++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c
@@ -726,14 +726,14 @@ static int qcom_pcie_ep_enable_irq_resources(struct platform_device *pdev,
 }
 
 static int qcom_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				  enum pci_epc_irq_type type, u16 interrupt_num)
+				  unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
-		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_INTX:
+		return dw_pcie_ep_raise_intx_irq(ep, func_no);
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
 	default:
 		dev_err(pci->dev, "Unknown IRQ type\n");
@@ -796,7 +796,7 @@ static void qcom_pcie_ep_init(struct dw_pcie_ep *ep)
 }
 
 static const struct dw_pcie_ep_ops pci_ep_ops = {
-	.ep_init = qcom_pcie_ep_init,
+	.init = qcom_pcie_ep_init,
 	.raise_irq = qcom_pcie_ep_raise_irq,
 	.get_features = qcom_pcie_epc_get_features,
 };
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index 11c80555d975..2ce2a3bd932b 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -972,7 +972,7 @@ static int qcom_pcie_enable_aspm(struct pci_dev *pdev, void *userdata)
 	 * Downstream devices need to be in D0 state before enabling PCI PM
 	 * substates.
 	 */
-	pci_set_power_state(pdev, PCI_D0);
+	pci_set_power_state_locked(pdev, PCI_D0);
 	pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL);
 
 	return 0;
@@ -1247,9 +1247,9 @@ static void qcom_pcie_host_post_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops qcom_pcie_dw_ops = {
-	.host_init	= qcom_pcie_host_init,
-	.host_deinit	= qcom_pcie_host_deinit,
-	.host_post_init	= qcom_pcie_host_post_init,
+	.init		= qcom_pcie_host_init,
+	.deinit		= qcom_pcie_host_deinit,
+	.post_init	= qcom_pcie_host_post_init,
 };
 
 /* Qcom IP rev.: 2.1.0	Synopsys IP rev.: 4.01a */
diff --git a/drivers/pci/controller/dwc/pcie-rcar-gen4.c b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
index 3bc45e513b3d..e9166619b1f9 100644
--- a/drivers/pci/controller/dwc/pcie-rcar-gen4.c
+++ b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
@@ -8,7 +8,7 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
@@ -307,8 +307,8 @@ static void rcar_gen4_pcie_host_deinit(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops rcar_gen4_pcie_host_ops = {
-	.host_init = rcar_gen4_pcie_host_init,
-	.host_deinit = rcar_gen4_pcie_host_deinit,
+	.init = rcar_gen4_pcie_host_init,
+	.deinit = rcar_gen4_pcie_host_deinit,
 };
 
 static int rcar_gen4_add_dw_pcie_rp(struct rcar_gen4_pcie *rcar)
@@ -362,15 +362,14 @@ static void rcar_gen4_pcie_ep_deinit(struct dw_pcie_ep *ep)
 }
 
 static int rcar_gen4_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				       enum pci_epc_irq_type type,
-				       u16 interrupt_num)
+				       unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *dw = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
-		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_INTX:
+		return dw_pcie_ep_raise_intx_irq(ep, func_no);
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
 	default:
 		dev_err(dw->dev, "Unknown IRQ type\n");
@@ -394,7 +393,7 @@ rcar_gen4_pcie_ep_get_features(struct dw_pcie_ep *ep)
 	return &rcar_gen4_pcie_epc_features;
 }
 
-static unsigned int rcar_gen4_pcie_ep_func_conf_select(struct dw_pcie_ep *ep,
+static unsigned int rcar_gen4_pcie_ep_get_dbi_offset(struct dw_pcie_ep *ep,
 						       u8 func_no)
 {
 	return func_no * RCAR_GEN4_PCIE_EP_FUNC_DBI_OFFSET;
@@ -408,11 +407,11 @@ static unsigned int rcar_gen4_pcie_ep_get_dbi2_offset(struct dw_pcie_ep *ep,
 
 static const struct dw_pcie_ep_ops pcie_ep_ops = {
 	.pre_init = rcar_gen4_pcie_ep_pre_init,
-	.ep_init = rcar_gen4_pcie_ep_init,
+	.init = rcar_gen4_pcie_ep_init,
 	.deinit = rcar_gen4_pcie_ep_deinit,
 	.raise_irq = rcar_gen4_pcie_ep_raise_irq,
 	.get_features = rcar_gen4_pcie_ep_get_features,
-	.func_conf_select = rcar_gen4_pcie_ep_func_conf_select,
+	.get_dbi_offset = rcar_gen4_pcie_ep_get_dbi_offset,
 	.get_dbi2_offset = rcar_gen4_pcie_ep_get_dbi2_offset,
 };
 
@@ -436,7 +435,7 @@ static void rcar_gen4_remove_dw_pcie_ep(struct rcar_gen4_pcie *rcar)
 /* Common */
 static int rcar_gen4_add_dw_pcie(struct rcar_gen4_pcie *rcar)
 {
-	rcar->mode = (enum dw_pcie_device_mode)of_device_get_match_data(&rcar->pdev->dev);
+	rcar->mode = (uintptr_t)of_device_get_match_data(&rcar->pdev->dev);
 
 	switch (rcar->mode) {
 	case DW_PCIE_RC_TYPE:
diff --git a/drivers/pci/controller/dwc/pcie-spear13xx.c b/drivers/pci/controller/dwc/pcie-spear13xx.c
index 99d47ae80331..201dced209f0 100644
--- a/drivers/pci/controller/dwc/pcie-spear13xx.c
+++ b/drivers/pci/controller/dwc/pcie-spear13xx.c
@@ -148,7 +148,7 @@ static int spear13xx_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops spear13xx_pcie_host_ops = {
-	.host_init = spear13xx_pcie_host_init,
+	.init = spear13xx_pcie_host_init,
 };
 
 static int spear13xx_add_pcie_port(struct spear13xx_pcie *spear13xx_pcie,
diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c
index 0fe113598ebb..7afa9e9aabe2 100644
--- a/drivers/pci/controller/dwc/pcie-tegra194.c
+++ b/drivers/pci/controller/dwc/pcie-tegra194.c
@@ -773,13 +773,13 @@ static void tegra_pcie_enable_system_interrupts(struct dw_pcie_rp *pp)
 			   val_w);
 }
 
-static void tegra_pcie_enable_legacy_interrupts(struct dw_pcie_rp *pp)
+static void tegra_pcie_enable_intx_interrupts(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
 	u32 val;
 
-	/* Enable legacy interrupt generation */
+	/* Enable INTX interrupt generation */
 	val = appl_readl(pcie, APPL_INTR_EN_L0_0);
 	val |= APPL_INTR_EN_L0_0_SYS_INTR_EN;
 	val |= APPL_INTR_EN_L0_0_INT_INT_EN;
@@ -830,7 +830,7 @@ static void tegra_pcie_enable_interrupts(struct dw_pcie_rp *pp)
 	appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_17);
 
 	tegra_pcie_enable_system_interrupts(pp);
-	tegra_pcie_enable_legacy_interrupts(pp);
+	tegra_pcie_enable_intx_interrupts(pp);
 	if (IS_ENABLED(CONFIG_PCI_MSI))
 		tegra_pcie_enable_msi_interrupts(pp);
 }
@@ -1060,7 +1060,7 @@ static const struct dw_pcie_ops tegra_dw_pcie_ops = {
 };
 
 static const struct dw_pcie_host_ops tegra_pcie_dw_host_ops = {
-	.host_init = tegra_pcie_dw_host_init,
+	.init = tegra_pcie_dw_host_init,
 };
 
 static void tegra_pcie_disable_phy(struct tegra_pcie_dw *pcie)
@@ -1947,7 +1947,7 @@ static irqreturn_t tegra_pcie_ep_pex_rst_irq(int irq, void *arg)
 	return IRQ_HANDLED;
 }
 
-static int tegra_pcie_ep_raise_legacy_irq(struct tegra_pcie_dw *pcie, u16 irq)
+static int tegra_pcie_ep_raise_intx_irq(struct tegra_pcie_dw *pcie, u16 irq)
 {
 	/* Tegra194 supports only INTA */
 	if (irq > 1)
@@ -1979,20 +1979,19 @@ static int tegra_pcie_ep_raise_msix_irq(struct tegra_pcie_dw *pcie, u16 irq)
 }
 
 static int tegra_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				   enum pci_epc_irq_type type,
-				   u16 interrupt_num)
+				   unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
-		return tegra_pcie_ep_raise_legacy_irq(pcie, interrupt_num);
+	case PCI_IRQ_INTX:
+		return tegra_pcie_ep_raise_intx_irq(pcie, interrupt_num);
 
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return tegra_pcie_ep_raise_msi_irq(pcie, interrupt_num);
 
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		return tegra_pcie_ep_raise_msix_irq(pcie, interrupt_num);
 
 	default:
diff --git a/drivers/pci/controller/dwc/pcie-uniphier-ep.c b/drivers/pci/controller/dwc/pcie-uniphier-ep.c
index cba3c88fcf39..3fced0d3e851 100644
--- a/drivers/pci/controller/dwc/pcie-uniphier-ep.c
+++ b/drivers/pci/controller/dwc/pcie-uniphier-ep.c
@@ -212,7 +212,7 @@ static void uniphier_pcie_ep_init(struct dw_pcie_ep *ep)
 		dw_pcie_ep_reset_bar(pci, bar);
 }
 
-static int uniphier_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep)
+static int uniphier_pcie_ep_raise_intx_irq(struct dw_pcie_ep *ep)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct uniphier_pcie_ep_priv *priv = to_uniphier_pcie(pci);
@@ -256,15 +256,14 @@ static int uniphier_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep,
 }
 
 static int uniphier_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				      enum pci_epc_irq_type type,
-				      u16 interrupt_num)
+				      unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
-		return uniphier_pcie_ep_raise_legacy_irq(ep);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_INTX:
+		return uniphier_pcie_ep_raise_intx_irq(ep);
+	case PCI_IRQ_MSI:
 		return uniphier_pcie_ep_raise_msi_irq(ep, func_no,
 						      interrupt_num);
 	default:
@@ -284,7 +283,7 @@ uniphier_pcie_get_features(struct dw_pcie_ep *ep)
 }
 
 static const struct dw_pcie_ep_ops uniphier_pcie_ep_ops = {
-	.ep_init = uniphier_pcie_ep_init,
+	.init = uniphier_pcie_ep_init,
 	.raise_irq = uniphier_pcie_ep_raise_irq,
 	.get_features = uniphier_pcie_get_features,
 };
diff --git a/drivers/pci/controller/dwc/pcie-uniphier.c b/drivers/pci/controller/dwc/pcie-uniphier.c
index 48c3eba817b4..5757ca3803c9 100644
--- a/drivers/pci/controller/dwc/pcie-uniphier.c
+++ b/drivers/pci/controller/dwc/pcie-uniphier.c
@@ -67,7 +67,7 @@ struct uniphier_pcie {
 	struct clk *clk;
 	struct reset_control *rst;
 	struct phy *phy;
-	struct irq_domain *legacy_irq_domain;
+	struct irq_domain *intx_irq_domain;
 };
 
 #define to_uniphier_pcie(x)	dev_get_drvdata((x)->dev)
@@ -253,12 +253,12 @@ static void uniphier_pcie_irq_handler(struct irq_desc *desc)
 	reg = FIELD_GET(PCL_RCV_INTX_ALL_STATUS, val);
 
 	for_each_set_bit(bit, &reg, PCI_NUM_INTX)
-		generic_handle_domain_irq(pcie->legacy_irq_domain, bit);
+		generic_handle_domain_irq(pcie->intx_irq_domain, bit);
 
 	chained_irq_exit(chip, desc);
 }
 
-static int uniphier_pcie_config_legacy_irq(struct dw_pcie_rp *pp)
+static int uniphier_pcie_config_intx_irq(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct uniphier_pcie *pcie = to_uniphier_pcie(pci);
@@ -279,9 +279,9 @@ static int uniphier_pcie_config_legacy_irq(struct dw_pcie_rp *pp)
 		goto out_put_node;
 	}
 
-	pcie->legacy_irq_domain = irq_domain_add_linear(np_intc, PCI_NUM_INTX,
+	pcie->intx_irq_domain = irq_domain_add_linear(np_intc, PCI_NUM_INTX,
 						&uniphier_intx_domain_ops, pp);
-	if (!pcie->legacy_irq_domain) {
+	if (!pcie->intx_irq_domain) {
 		dev_err(pci->dev, "Failed to get INTx domain\n");
 		ret = -ENODEV;
 		goto out_put_node;
@@ -301,7 +301,7 @@ static int uniphier_pcie_host_init(struct dw_pcie_rp *pp)
 	struct uniphier_pcie *pcie = to_uniphier_pcie(pci);
 	int ret;
 
-	ret = uniphier_pcie_config_legacy_irq(pp);
+	ret = uniphier_pcie_config_intx_irq(pp);
 	if (ret)
 		return ret;
 
@@ -311,7 +311,7 @@ static int uniphier_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops uniphier_pcie_host_ops = {
-	.host_init = uniphier_pcie_host_init,
+	.init = uniphier_pcie_host_init,
 };
 
 static int uniphier_pcie_host_enable(struct uniphier_pcie *pcie)
diff --git a/drivers/pci/controller/dwc/pcie-visconti.c b/drivers/pci/controller/dwc/pcie-visconti.c
index 71026fefa366..318c278e65c8 100644
--- a/drivers/pci/controller/dwc/pcie-visconti.c
+++ b/drivers/pci/controller/dwc/pcie-visconti.c
@@ -236,7 +236,7 @@ static int visconti_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops visconti_pcie_host_ops = {
-	.host_init = visconti_pcie_host_init,
+	.init = visconti_pcie_host_init,
 };
 
 static int visconti_get_resources(struct platform_device *pdev,
diff --git a/drivers/pci/controller/pci-host-common.c b/drivers/pci/controller/pci-host-common.c
index 6be3266cd7b5..45b71806182d 100644
--- a/drivers/pci/controller/pci-host-common.c
+++ b/drivers/pci/controller/pci-host-common.c
@@ -85,7 +85,7 @@ int pci_host_common_probe(struct platform_device *pdev)
 }
 EXPORT_SYMBOL_GPL(pci_host_common_probe);
 
-int pci_host_common_remove(struct platform_device *pdev)
+void pci_host_common_remove(struct platform_device *pdev)
 {
 	struct pci_host_bridge *bridge = platform_get_drvdata(pdev);
 
@@ -93,8 +93,6 @@ int pci_host_common_remove(struct platform_device *pdev)
 	pci_stop_root_bus(bridge->bus);
 	pci_remove_root_bus(bridge->bus);
 	pci_unlock_rescan_remove();
-
-	return 0;
 }
 EXPORT_SYMBOL_GPL(pci_host_common_remove);
 
diff --git a/drivers/pci/controller/pci-host-generic.c b/drivers/pci/controller/pci-host-generic.c
index 63865aeb636b..41cb6a057f6e 100644
--- a/drivers/pci/controller/pci-host-generic.c
+++ b/drivers/pci/controller/pci-host-generic.c
@@ -82,7 +82,7 @@ static struct platform_driver gen_pci_driver = {
 		.of_match_table = gen_pci_of_match,
 	},
 	.probe = pci_host_common_probe,
-	.remove = pci_host_common_remove,
+	.remove_new = pci_host_common_remove,
 };
 module_platform_driver(gen_pci_driver);
 
diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c
index f9dd6622fe10..5b0730c3891b 100644
--- a/drivers/pci/controller/pcie-brcmstb.c
+++ b/drivers/pci/controller/pcie-brcmstb.c
@@ -48,6 +48,9 @@
 #define PCIE_RC_CFG_PRIV1_LINK_CAPABILITY			0x04dc
 #define  PCIE_RC_CFG_PRIV1_LINK_CAPABILITY_ASPM_SUPPORT_MASK	0xc00
 
+#define PCIE_RC_CFG_PRIV1_ROOT_CAP			0x4f8
+#define  PCIE_RC_CFG_PRIV1_ROOT_CAP_L1SS_MODE_MASK	0xf8
+
 #define PCIE_RC_DL_MDIO_ADDR				0x1100
 #define PCIE_RC_DL_MDIO_WR_DATA				0x1104
 #define PCIE_RC_DL_MDIO_RD_DATA				0x1108
@@ -121,9 +124,12 @@
 
 #define PCIE_MISC_HARD_PCIE_HARD_DEBUG					0x4204
 #define  PCIE_MISC_HARD_PCIE_HARD_DEBUG_CLKREQ_DEBUG_ENABLE_MASK	0x2
+#define  PCIE_MISC_HARD_PCIE_HARD_DEBUG_L1SS_ENABLE_MASK		0x200000
 #define  PCIE_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK		0x08000000
 #define  PCIE_BMIPS_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK		0x00800000
-
+#define  PCIE_CLKREQ_MASK \
+	  (PCIE_MISC_HARD_PCIE_HARD_DEBUG_CLKREQ_DEBUG_ENABLE_MASK | \
+	   PCIE_MISC_HARD_PCIE_HARD_DEBUG_L1SS_ENABLE_MASK)
 
 #define PCIE_INTR2_CPU_BASE		0x4300
 #define PCIE_MSI_INTR2_BASE		0x4500
@@ -1028,13 +1034,89 @@ static int brcm_pcie_setup(struct brcm_pcie *pcie)
 	return 0;
 }
 
+/*
+ * This extends the timeout period for an access to an internal bus.  This
+ * access timeout may occur during L1SS sleep periods, even without the
+ * presence of a PCIe access.
+ */
+static void brcm_extend_rbus_timeout(struct brcm_pcie *pcie)
+{
+	/* TIMEOUT register is two registers before RGR1_SW_INIT_1 */
+	const unsigned int REG_OFFSET = PCIE_RGR1_SW_INIT_1(pcie) - 8;
+	u32 timeout_us = 4000000; /* 4 seconds, our setting for L1SS */
+
+	/* Each unit in timeout register is 1/216,000,000 seconds */
+	writel(216 * timeout_us, pcie->base + REG_OFFSET);
+}
+
+static void brcm_config_clkreq(struct brcm_pcie *pcie)
+{
+	static const char err_msg[] = "invalid 'brcm,clkreq-mode' DT string\n";
+	const char *mode = "default";
+	u32 clkreq_cntl;
+	int ret, tmp;
+
+	ret = of_property_read_string(pcie->np, "brcm,clkreq-mode", &mode);
+	if (ret && ret != -EINVAL) {
+		dev_err(pcie->dev, err_msg);
+		mode = "safe";
+	}
+
+	/* Start out assuming safe mode (both mode bits cleared) */
+	clkreq_cntl = readl(pcie->base + PCIE_MISC_HARD_PCIE_HARD_DEBUG);
+	clkreq_cntl &= ~PCIE_CLKREQ_MASK;
+
+	if (strcmp(mode, "no-l1ss") == 0) {
+		/*
+		 * "no-l1ss" -- Provides Clock Power Management, L0s, and
+		 * L1, but cannot provide L1 substate (L1SS) power
+		 * savings. If the downstream device connected to the RC is
+		 * L1SS capable AND the OS enables L1SS, all PCIe traffic
+		 * may abruptly halt, potentially hanging the system.
+		 */
+		clkreq_cntl |= PCIE_MISC_HARD_PCIE_HARD_DEBUG_CLKREQ_DEBUG_ENABLE_MASK;
+		/*
+		 * We want to un-advertise L1 substates because if the OS
+		 * tries to configure the controller into using L1 substate
+		 * power savings it may fail or hang when the RC HW is in
+		 * "no-l1ss" mode.
+		 */
+		tmp = readl(pcie->base + PCIE_RC_CFG_PRIV1_ROOT_CAP);
+		u32p_replace_bits(&tmp, 2, PCIE_RC_CFG_PRIV1_ROOT_CAP_L1SS_MODE_MASK);
+		writel(tmp, pcie->base + PCIE_RC_CFG_PRIV1_ROOT_CAP);
+
+	} else if (strcmp(mode, "default") == 0) {
+		/*
+		 * "default" -- Provides L0s, L1, and L1SS, but not
+		 * compliant to provide Clock Power Management;
+		 * specifically, may not be able to meet the Tclron max
+		 * timing of 400ns as specified in "Dynamic Clock Control",
+		 * section 3.2.5.2.2 of the PCIe spec.  This situation is
+		 * atypical and should happen only with older devices.
+		 */
+		clkreq_cntl |= PCIE_MISC_HARD_PCIE_HARD_DEBUG_L1SS_ENABLE_MASK;
+		brcm_extend_rbus_timeout(pcie);
+
+	} else {
+		/*
+		 * "safe" -- No power savings; refclk is driven by RC
+		 * unconditionally.
+		 */
+		if (strcmp(mode, "safe") != 0)
+			dev_err(pcie->dev, err_msg);
+		mode = "safe";
+	}
+	writel(clkreq_cntl, pcie->base + PCIE_MISC_HARD_PCIE_HARD_DEBUG);
+
+	dev_info(pcie->dev, "clkreq-mode set to %s\n", mode);
+}
+
 static int brcm_pcie_start_link(struct brcm_pcie *pcie)
 {
 	struct device *dev = pcie->dev;
 	void __iomem *base = pcie->base;
 	u16 nlw, cls, lnksta;
 	bool ssc_good = false;
-	u32 tmp;
 	int ret, i;
 
 	/* Unassert the fundamental reset */
@@ -1059,6 +1141,8 @@ static int brcm_pcie_start_link(struct brcm_pcie *pcie)
 		return -ENODEV;
 	}
 
+	brcm_config_clkreq(pcie);
+
 	if (pcie->gen)
 		brcm_pcie_set_gen(pcie, pcie->gen);
 
@@ -1077,14 +1161,6 @@ static int brcm_pcie_start_link(struct brcm_pcie *pcie)
 		 pci_speed_string(pcie_link_speed[cls]), nlw,
 		 ssc_good ? "(SSC)" : "(!SSC)");
 
-	/*
-	 * Refclk from RC should be gated with CLKREQ# input when ASPM L0s,L1
-	 * is enabled => setting the CLKREQ_DEBUG_ENABLE field to 1.
-	 */
-	tmp = readl(base + PCIE_MISC_HARD_PCIE_HARD_DEBUG);
-	tmp |= PCIE_MISC_HARD_PCIE_HARD_DEBUG_CLKREQ_DEBUG_ENABLE_MASK;
-	writel(tmp, base + PCIE_MISC_HARD_PCIE_HARD_DEBUG);
-
 	return 0;
 }
 
diff --git a/drivers/pci/controller/pcie-iproc-platform.c b/drivers/pci/controller/pcie-iproc-platform.c
index acdc583d2980..4e6aa882a567 100644
--- a/drivers/pci/controller/pcie-iproc-platform.c
+++ b/drivers/pci/controller/pcie-iproc-platform.c
@@ -52,7 +52,7 @@ static int iproc_pltfm_pcie_probe(struct platform_device *pdev)
 	pcie = pci_host_bridge_priv(bridge);
 
 	pcie->dev = dev;
-	pcie->type = (enum iproc_pcie_type) of_device_get_match_data(dev);
+	pcie->type = (uintptr_t)of_device_get_match_data(dev);
 
 	ret = of_address_to_resource(np, 0, &reg);
 	if (ret < 0) {
diff --git a/drivers/pci/controller/pcie-mediatek-gen3.c b/drivers/pci/controller/pcie-mediatek-gen3.c
index e0e27645fdf4..975b3024fb08 100644
--- a/drivers/pci/controller/pcie-mediatek-gen3.c
+++ b/drivers/pci/controller/pcie-mediatek-gen3.c
@@ -245,35 +245,60 @@ static int mtk_pcie_set_trans_table(struct mtk_gen3_pcie *pcie,
 				    resource_size_t cpu_addr,
 				    resource_size_t pci_addr,
 				    resource_size_t size,
-				    unsigned long type, int num)
+				    unsigned long type, int *num)
 {
+	resource_size_t remaining = size;
+	resource_size_t table_size;
+	resource_size_t addr_align;
+	const char *range_type;
 	void __iomem *table;
 	u32 val;
 
-	if (num >= PCIE_MAX_TRANS_TABLES) {
-		dev_err(pcie->dev, "not enough translate table for addr: %#llx, limited to [%d]\n",
-			(unsigned long long)cpu_addr, PCIE_MAX_TRANS_TABLES);
-		return -ENODEV;
-	}
+	while (remaining && (*num < PCIE_MAX_TRANS_TABLES)) {
+		/* Table size needs to be a power of 2 */
+		table_size = BIT(fls(remaining) - 1);
+
+		if (cpu_addr > 0) {
+			addr_align = BIT(ffs(cpu_addr) - 1);
+			table_size = min(table_size, addr_align);
+		}
+
+		/* Minimum size of translate table is 4KiB */
+		if (table_size < 0x1000) {
+			dev_err(pcie->dev, "illegal table size %#llx\n",
+				(unsigned long long)table_size);
+			return -EINVAL;
+		}
 
-	table = pcie->base + PCIE_TRANS_TABLE_BASE_REG +
-		num * PCIE_ATR_TLB_SET_OFFSET;
+		table = pcie->base + PCIE_TRANS_TABLE_BASE_REG + *num * PCIE_ATR_TLB_SET_OFFSET;
+		writel_relaxed(lower_32_bits(cpu_addr) | PCIE_ATR_SIZE(fls(table_size) - 1), table);
+		writel_relaxed(upper_32_bits(cpu_addr), table + PCIE_ATR_SRC_ADDR_MSB_OFFSET);
+		writel_relaxed(lower_32_bits(pci_addr), table + PCIE_ATR_TRSL_ADDR_LSB_OFFSET);
+		writel_relaxed(upper_32_bits(pci_addr), table + PCIE_ATR_TRSL_ADDR_MSB_OFFSET);
 
-	writel_relaxed(lower_32_bits(cpu_addr) | PCIE_ATR_SIZE(fls(size) - 1),
-		       table);
-	writel_relaxed(upper_32_bits(cpu_addr),
-		       table + PCIE_ATR_SRC_ADDR_MSB_OFFSET);
-	writel_relaxed(lower_32_bits(pci_addr),
-		       table + PCIE_ATR_TRSL_ADDR_LSB_OFFSET);
-	writel_relaxed(upper_32_bits(pci_addr),
-		       table + PCIE_ATR_TRSL_ADDR_MSB_OFFSET);
+		if (type == IORESOURCE_IO) {
+			val = PCIE_ATR_TYPE_IO | PCIE_ATR_TLP_TYPE_IO;
+			range_type = "IO";
+		} else {
+			val = PCIE_ATR_TYPE_MEM | PCIE_ATR_TLP_TYPE_MEM;
+			range_type = "MEM";
+		}
 
-	if (type == IORESOURCE_IO)
-		val = PCIE_ATR_TYPE_IO | PCIE_ATR_TLP_TYPE_IO;
-	else
-		val = PCIE_ATR_TYPE_MEM | PCIE_ATR_TLP_TYPE_MEM;
+		writel_relaxed(val, table + PCIE_ATR_TRSL_PARAM_OFFSET);
 
-	writel_relaxed(val, table + PCIE_ATR_TRSL_PARAM_OFFSET);
+		dev_dbg(pcie->dev, "set %s trans window[%d]: cpu_addr = %#llx, pci_addr = %#llx, size = %#llx\n",
+			range_type, *num, (unsigned long long)cpu_addr,
+			(unsigned long long)pci_addr, (unsigned long long)table_size);
+
+		cpu_addr += table_size;
+		pci_addr += table_size;
+		remaining -= table_size;
+		(*num)++;
+	}
+
+	if (remaining)
+		dev_warn(pcie->dev, "not enough translate table for addr: %#llx, limited to [%d]\n",
+			 (unsigned long long)cpu_addr, PCIE_MAX_TRANS_TABLES);
 
 	return 0;
 }
@@ -380,30 +405,20 @@ static int mtk_pcie_startup_port(struct mtk_gen3_pcie *pcie)
 		resource_size_t cpu_addr;
 		resource_size_t pci_addr;
 		resource_size_t size;
-		const char *range_type;
 
-		if (type == IORESOURCE_IO) {
+		if (type == IORESOURCE_IO)
 			cpu_addr = pci_pio_to_address(res->start);
-			range_type = "IO";
-		} else if (type == IORESOURCE_MEM) {
+		else if (type == IORESOURCE_MEM)
 			cpu_addr = res->start;
-			range_type = "MEM";
-		} else {
+		else
 			continue;
-		}
 
 		pci_addr = res->start - entry->offset;
 		size = resource_size(res);
 		err = mtk_pcie_set_trans_table(pcie, cpu_addr, pci_addr, size,
-					       type, table_index);
+					       type, &table_index);
 		if (err)
 			return err;
-
-		dev_dbg(pcie->dev, "set %s trans window[%d]: cpu_addr = %#llx, pci_addr = %#llx, size = %#llx\n",
-			range_type, table_index, (unsigned long long)cpu_addr,
-			(unsigned long long)pci_addr, (unsigned long long)size);
-
-		table_index++;
 	}
 
 	return 0;
diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c
index 66a8f73296fc..48372013f26d 100644
--- a/drivers/pci/controller/pcie-mediatek.c
+++ b/drivers/pci/controller/pcie-mediatek.c
@@ -617,12 +617,18 @@ static void mtk_pcie_intr_handler(struct irq_desc *desc)
 		if (status & MSI_STATUS){
 			unsigned long imsi_status;
 
+			/*
+			 * The interrupt status can be cleared even if the
+			 * MSI status remains pending. As such, given the
+			 * edge-triggered interrupt type, its status should
+			 * be cleared before being dispatched to the
+			 * handler of the underlying device.
+			 */
+			writel(MSI_STATUS, port->base + PCIE_INT_STATUS);
 			while ((imsi_status = readl(port->base + PCIE_IMSI_STATUS))) {
 				for_each_set_bit(bit, &imsi_status, MTK_MSI_IRQS_NUM)
 					generic_handle_domain_irq(port->inner_domain, bit);
 			}
-			/* Clear MSI interrupt status */
-			writel(MSI_STATUS, port->base + PCIE_INT_STATUS);
 		}
 	}
 
diff --git a/drivers/pci/controller/pcie-rcar-ep.c b/drivers/pci/controller/pcie-rcar-ep.c
index 7034c0ff23d0..e6909271def7 100644
--- a/drivers/pci/controller/pcie-rcar-ep.c
+++ b/drivers/pci/controller/pcie-rcar-ep.c
@@ -402,16 +402,15 @@ static int rcar_pcie_ep_assert_msi(struct rcar_pcie *pcie,
 }
 
 static int rcar_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn,
-				  enum pci_epc_irq_type type,
-				  u16 interrupt_num)
+				  unsigned int type, u16 interrupt_num)
 {
 	struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		return rcar_pcie_ep_assert_intx(ep, fn, 0);
 
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return rcar_pcie_ep_assert_msi(&ep->pcie, fn, interrupt_num);
 
 	default:
diff --git a/drivers/pci/controller/pcie-rcar-host.c b/drivers/pci/controller/pcie-rcar-host.c
index bf7cc0b6a695..996077ab7cfd 100644
--- a/drivers/pci/controller/pcie-rcar-host.c
+++ b/drivers/pci/controller/pcie-rcar-host.c
@@ -29,6 +29,7 @@
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/regulator/consumer.h>
 
 #include "pcie-rcar.h"
 
@@ -953,14 +954,22 @@ static const struct of_device_id rcar_pcie_of_match[] = {
 	{},
 };
 
+/* Design note 346 from Linear Technology says order is not important. */
+static const char * const rcar_pcie_supplies[] = {
+	"vpcie1v5",
+	"vpcie3v3",
+	"vpcie12v",
+};
+
 static int rcar_pcie_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
+	struct pci_host_bridge *bridge;
 	struct rcar_pcie_host *host;
 	struct rcar_pcie *pcie;
+	unsigned int i;
 	u32 data;
 	int err;
-	struct pci_host_bridge *bridge;
 
 	bridge = devm_pci_alloc_host_bridge(dev, sizeof(*host));
 	if (!bridge)
@@ -971,6 +980,13 @@ static int rcar_pcie_probe(struct platform_device *pdev)
 	pcie->dev = dev;
 	platform_set_drvdata(pdev, host);
 
+	for (i = 0; i < ARRAY_SIZE(rcar_pcie_supplies); i++) {
+		err = devm_regulator_get_enable_optional(dev, rcar_pcie_supplies[i]);
+		if (err < 0 && err != -ENODEV)
+			return dev_err_probe(dev, err, "failed to enable regulator: %s\n",
+					     rcar_pcie_supplies[i]);
+	}
+
 	pm_runtime_enable(pcie->dev);
 	err = pm_runtime_get_sync(pcie->dev);
 	if (err < 0) {
diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index 0af0e965fb57..c9046e97a1d2 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -26,16 +26,16 @@
  * @max_regions: maximum number of regions supported by hardware
  * @ob_region_map: bitmask of mapped outbound regions
  * @ob_addr: base addresses in the AXI bus where the outbound regions start
- * @irq_phys_addr: base address on the AXI bus where the MSI/legacy IRQ
+ * @irq_phys_addr: base address on the AXI bus where the MSI/INTX IRQ
  *		   dedicated outbound regions is mapped.
  * @irq_cpu_addr: base address in the CPU space where a write access triggers
- *		  the sending of a memory write (MSI) / normal message (legacy
+ *		  the sending of a memory write (MSI) / normal message (INTX
  *		  IRQ) TLP through the PCIe bus.
- * @irq_pci_addr: used to save the current mapping of the MSI/legacy IRQ
+ * @irq_pci_addr: used to save the current mapping of the MSI/INTX IRQ
  *		  dedicated outbound region.
  * @irq_pci_fn: the latest PCI function that has updated the mapping of
- *		the MSI/legacy IRQ dedicated outbound region.
- * @irq_pending: bitmask of asserted legacy IRQs.
+ *		the MSI/INTX IRQ dedicated outbound region.
+ * @irq_pending: bitmask of asserted INTX IRQs.
  */
 struct rockchip_pcie_ep {
 	struct rockchip_pcie	rockchip;
@@ -325,8 +325,8 @@ static void rockchip_pcie_ep_assert_intx(struct rockchip_pcie_ep *ep, u8 fn,
 	}
 }
 
-static int rockchip_pcie_ep_send_legacy_irq(struct rockchip_pcie_ep *ep, u8 fn,
-					    u8 intx)
+static int rockchip_pcie_ep_send_intx_irq(struct rockchip_pcie_ep *ep, u8 fn,
+					  u8 intx)
 {
 	u16 cmd;
 
@@ -407,15 +407,14 @@ static int rockchip_pcie_ep_send_msi_irq(struct rockchip_pcie_ep *ep, u8 fn,
 }
 
 static int rockchip_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn,
-				      enum pci_epc_irq_type type,
-				      u16 interrupt_num)
+				      unsigned int type, u16 interrupt_num)
 {
 	struct rockchip_pcie_ep *ep = epc_get_drvdata(epc);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
-		return rockchip_pcie_ep_send_legacy_irq(ep, fn, 0);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_INTX:
+		return rockchip_pcie_ep_send_intx_irq(ep, fn, 0);
+	case PCI_IRQ_MSI:
 		return rockchip_pcie_ep_send_msi_irq(ep, fn, interrupt_num);
 	default:
 		return -EINVAL;
diff --git a/drivers/pci/controller/pcie-rockchip-host.c b/drivers/pci/controller/pcie-rockchip-host.c
index afbbdccd195d..300b9dc85ecc 100644
--- a/drivers/pci/controller/pcie-rockchip-host.c
+++ b/drivers/pci/controller/pcie-rockchip-host.c
@@ -505,7 +505,7 @@ static irqreturn_t rockchip_pcie_client_irq_handler(int irq, void *arg)
 	return IRQ_HANDLED;
 }
 
-static void rockchip_pcie_legacy_int_handler(struct irq_desc *desc)
+static void rockchip_pcie_intx_handler(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct rockchip_pcie *rockchip = irq_desc_get_handler_data(desc);
@@ -553,7 +553,7 @@ static int rockchip_pcie_setup_irq(struct rockchip_pcie *rockchip)
 		return irq;
 
 	irq_set_chained_handler_and_data(irq,
-					 rockchip_pcie_legacy_int_handler,
+					 rockchip_pcie_intx_handler,
 					 rockchip);
 
 	irq = platform_get_irq_byname(pdev, "client");
diff --git a/drivers/pci/controller/pcie-xilinx-dma-pl.c b/drivers/pci/controller/pcie-xilinx-dma-pl.c
index 2f7d676c683c..5be5dfd8398f 100644
--- a/drivers/pci/controller/pcie-xilinx-dma-pl.c
+++ b/drivers/pci/controller/pcie-xilinx-dma-pl.c
@@ -576,7 +576,7 @@ static int xilinx_pl_dma_pcie_init_irq_domain(struct pl_dma_pcie *port)
 						  &intx_domain_ops, port);
 	if (!port->intx_domain) {
 		dev_err(dev, "Failed to get a INTx IRQ domain\n");
-		return PTR_ERR(port->intx_domain);
+		return -ENOMEM;
 	}
 
 	irq_domain_update_bus_token(port->intx_domain, DOMAIN_BUS_WIRED);
@@ -635,14 +635,14 @@ static int xilinx_pl_dma_pcie_setup_irq(struct pl_dma_pcie *port)
 	err = devm_request_irq(dev, port->intx_irq, xilinx_pl_dma_pcie_intx_flow,
 			       IRQF_SHARED | IRQF_NO_THREAD, NULL, port);
 	if (err) {
-		dev_err(dev, "Failed to request INTx IRQ %d\n", irq);
+		dev_err(dev, "Failed to request INTx IRQ %d\n", port->intx_irq);
 		return err;
 	}
 
 	err = devm_request_irq(dev, port->irq, xilinx_pl_dma_pcie_event_flow,
 			       IRQF_SHARED | IRQF_NO_THREAD, NULL, port);
 	if (err) {
-		dev_err(dev, "Failed to request event IRQ %d\n", irq);
+		dev_err(dev, "Failed to request event IRQ %d\n", port->irq);
 		return err;
 	}
 
@@ -684,10 +684,8 @@ static int xilinx_request_msi_irq(struct pl_dma_pcie *port)
 	int ret;
 
 	port->msi.irq_msi0 = platform_get_irq_byname(pdev, "msi0");
-	if (port->msi.irq_msi0 <= 0) {
-		dev_err(dev, "Unable to find msi0 IRQ line\n");
+	if (port->msi.irq_msi0 <= 0)
 		return port->msi.irq_msi0;
-	}
 
 	ret = devm_request_irq(dev, port->msi.irq_msi0, xilinx_pl_dma_pcie_msi_handler_low,
 			       IRQF_SHARED | IRQF_NO_THREAD, "xlnx-pcie-dma-pl",
@@ -698,10 +696,8 @@ static int xilinx_request_msi_irq(struct pl_dma_pcie *port)
 	}
 
 	port->msi.irq_msi1 = platform_get_irq_byname(pdev, "msi1");
-	if (port->msi.irq_msi1 <= 0) {
-		dev_err(dev, "Unable to find msi1 IRQ line\n");
+	if (port->msi.irq_msi1 <= 0)
 		return port->msi.irq_msi1;
-	}
 
 	ret = devm_request_irq(dev, port->msi.irq_msi1, xilinx_pl_dma_pcie_msi_handler_high,
 			       IRQF_SHARED | IRQF_NO_THREAD, "xlnx-pcie-dma-pl",
diff --git a/drivers/pci/controller/pcie-xilinx-nwl.c b/drivers/pci/controller/pcie-xilinx-nwl.c
index e307aceba5c9..0408f4d612b5 100644
--- a/drivers/pci/controller/pcie-xilinx-nwl.c
+++ b/drivers/pci/controller/pcie-xilinx-nwl.c
@@ -166,7 +166,7 @@ struct nwl_pcie {
 	int irq_intx;
 	int irq_misc;
 	struct nwl_msi msi;
-	struct irq_domain *legacy_irq_domain;
+	struct irq_domain *intx_irq_domain;
 	struct clk *clk;
 	raw_spinlock_t leg_mask_lock;
 };
@@ -324,7 +324,7 @@ static void nwl_pcie_leg_handler(struct irq_desc *desc)
 	while ((status = nwl_bridge_readl(pcie, MSGF_LEG_STATUS) &
 				MSGF_LEG_SR_MASKALL) != 0) {
 		for_each_set_bit(bit, &status, PCI_NUM_INTX)
-			generic_handle_domain_irq(pcie->legacy_irq_domain, bit);
+			generic_handle_domain_irq(pcie->intx_irq_domain, bit);
 	}
 
 	chained_irq_exit(chip, desc);
@@ -364,7 +364,7 @@ static void nwl_pcie_msi_handler_low(struct irq_desc *desc)
 	chained_irq_exit(chip, desc);
 }
 
-static void nwl_mask_leg_irq(struct irq_data *data)
+static void nwl_mask_intx_irq(struct irq_data *data)
 {
 	struct nwl_pcie *pcie = irq_data_get_irq_chip_data(data);
 	unsigned long flags;
@@ -378,7 +378,7 @@ static void nwl_mask_leg_irq(struct irq_data *data)
 	raw_spin_unlock_irqrestore(&pcie->leg_mask_lock, flags);
 }
 
-static void nwl_unmask_leg_irq(struct irq_data *data)
+static void nwl_unmask_intx_irq(struct irq_data *data)
 {
 	struct nwl_pcie *pcie = irq_data_get_irq_chip_data(data);
 	unsigned long flags;
@@ -392,26 +392,26 @@ static void nwl_unmask_leg_irq(struct irq_data *data)
 	raw_spin_unlock_irqrestore(&pcie->leg_mask_lock, flags);
 }
 
-static struct irq_chip nwl_leg_irq_chip = {
+static struct irq_chip nwl_intx_irq_chip = {
 	.name = "nwl_pcie:legacy",
-	.irq_enable = nwl_unmask_leg_irq,
-	.irq_disable = nwl_mask_leg_irq,
-	.irq_mask = nwl_mask_leg_irq,
-	.irq_unmask = nwl_unmask_leg_irq,
+	.irq_enable = nwl_unmask_intx_irq,
+	.irq_disable = nwl_mask_intx_irq,
+	.irq_mask = nwl_mask_intx_irq,
+	.irq_unmask = nwl_unmask_intx_irq,
 };
 
-static int nwl_legacy_map(struct irq_domain *domain, unsigned int irq,
-			  irq_hw_number_t hwirq)
+static int nwl_intx_map(struct irq_domain *domain, unsigned int irq,
+			irq_hw_number_t hwirq)
 {
-	irq_set_chip_and_handler(irq, &nwl_leg_irq_chip, handle_level_irq);
+	irq_set_chip_and_handler(irq, &nwl_intx_irq_chip, handle_level_irq);
 	irq_set_chip_data(irq, domain->host_data);
 	irq_set_status_flags(irq, IRQ_LEVEL);
 
 	return 0;
 }
 
-static const struct irq_domain_ops legacy_domain_ops = {
-	.map = nwl_legacy_map,
+static const struct irq_domain_ops intx_domain_ops = {
+	.map = nwl_intx_map,
 	.xlate = pci_irqd_intx_xlate,
 };
 
@@ -525,20 +525,20 @@ static int nwl_pcie_init_irq_domain(struct nwl_pcie *pcie)
 {
 	struct device *dev = pcie->dev;
 	struct device_node *node = dev->of_node;
-	struct device_node *legacy_intc_node;
+	struct device_node *intc_node;
 
-	legacy_intc_node = of_get_next_child(node, NULL);
-	if (!legacy_intc_node) {
+	intc_node = of_get_next_child(node, NULL);
+	if (!intc_node) {
 		dev_err(dev, "No legacy intc node found\n");
 		return -EINVAL;
 	}
 
-	pcie->legacy_irq_domain = irq_domain_add_linear(legacy_intc_node,
-							PCI_NUM_INTX,
-							&legacy_domain_ops,
-							pcie);
-	of_node_put(legacy_intc_node);
-	if (!pcie->legacy_irq_domain) {
+	pcie->intx_irq_domain = irq_domain_add_linear(intc_node,
+						      PCI_NUM_INTX,
+						      &intx_domain_ops,
+						      pcie);
+	of_node_put(intc_node);
+	if (!pcie->intx_irq_domain) {
 		dev_err(dev, "failed to create IRQ domain\n");
 		return -ENOMEM;
 	}
@@ -710,14 +710,14 @@ static int nwl_pcie_bridge_init(struct nwl_pcie *pcie)
 	/* Enable all misc interrupts */
 	nwl_bridge_writel(pcie, MSGF_MISC_SR_MASKALL, MSGF_MISC_MASK);
 
-	/* Disable all legacy interrupts */
+	/* Disable all INTX interrupts */
 	nwl_bridge_writel(pcie, (u32)~MSGF_LEG_SR_MASKALL, MSGF_LEG_MASK);
 
-	/* Clear pending legacy interrupts */
+	/* Clear pending INTX interrupts */
 	nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, MSGF_LEG_STATUS) &
 			  MSGF_LEG_SR_MASKALL, MSGF_LEG_STATUS);
 
-	/* Enable all legacy interrupts */
+	/* Enable all INTX interrupts */
 	nwl_bridge_writel(pcie, MSGF_LEG_SR_MASKALL, MSGF_LEG_MASK);
 
 	/* Enable the bridge config interrupt */
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 0452cbc362ee..87b7856f375a 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -984,7 +984,7 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		return -ENOMEM;
 
 	vmd->dev = dev;
-	vmd->instance = ida_simple_get(&vmd_instance_ida, 0, 0, GFP_KERNEL);
+	vmd->instance = ida_alloc(&vmd_instance_ida, GFP_KERNEL);
 	if (vmd->instance < 0)
 		return vmd->instance;
 
@@ -1026,7 +1026,7 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	return 0;
 
  out_release_instance:
-	ida_simple_remove(&vmd_instance_ida, vmd->instance);
+	ida_free(&vmd_instance_ida, vmd->instance);
 	return err;
 }
 
@@ -1048,7 +1048,7 @@ static void vmd_remove(struct pci_dev *dev)
 	vmd_cleanup_srcu(vmd);
 	vmd_detach_resources(vmd);
 	vmd_remove_irq_domain(vmd);
-	ida_simple_remove(&vmd_instance_ida, vmd->instance);
+	ida_free(&vmd_instance_ida, vmd->instance);
 }
 
 static void vmd_shutdown(struct pci_dev *dev)
diff --git a/drivers/pci/endpoint/functions/pci-epf-mhi.c b/drivers/pci/endpoint/functions/pci-epf-mhi.c
index b7b9d3e21f97..1c3e4ea76bd2 100644
--- a/drivers/pci/endpoint/functions/pci-epf-mhi.c
+++ b/drivers/pci/endpoint/functions/pci-epf-mhi.c
@@ -21,6 +21,15 @@
 /* Platform specific flags */
 #define MHI_EPF_USE_DMA BIT(0)
 
+struct pci_epf_mhi_dma_transfer {
+	struct pci_epf_mhi *epf_mhi;
+	struct mhi_ep_buf_info buf_info;
+	struct list_head node;
+	dma_addr_t paddr;
+	enum dma_data_direction dir;
+	size_t size;
+};
+
 struct pci_epf_mhi_ep_info {
 	const struct mhi_ep_cntrl_config *config;
 	struct pci_epf_header *epf_header;
@@ -124,6 +133,10 @@ struct pci_epf_mhi {
 	resource_size_t mmio_phys;
 	struct dma_chan *dma_chan_tx;
 	struct dma_chan *dma_chan_rx;
+	struct workqueue_struct *dma_wq;
+	struct work_struct dma_work;
+	struct list_head dma_list;
+	spinlock_t list_lock;
 	u32 mmio_size;
 	int irq;
 };
@@ -205,63 +218,69 @@ static void pci_epf_mhi_raise_irq(struct mhi_ep_cntrl *mhi_cntrl, u32 vector)
 	 * MHI supplies 0 based MSI vectors but the API expects the vector
 	 * number to start from 1, so we need to increment the vector by 1.
 	 */
-	pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no, PCI_EPC_IRQ_MSI,
+	pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no, PCI_IRQ_MSI,
 			  vector + 1);
 }
 
-static int pci_epf_mhi_iatu_read(struct mhi_ep_cntrl *mhi_cntrl, u64 from,
-				 void *to, size_t size)
+static int pci_epf_mhi_iatu_read(struct mhi_ep_cntrl *mhi_cntrl,
+				 struct mhi_ep_buf_info *buf_info)
 {
 	struct pci_epf_mhi *epf_mhi = to_epf_mhi(mhi_cntrl);
-	size_t offset = get_align_offset(epf_mhi, from);
+	size_t offset = get_align_offset(epf_mhi, buf_info->host_addr);
 	void __iomem *tre_buf;
 	phys_addr_t tre_phys;
 	int ret;
 
 	mutex_lock(&epf_mhi->lock);
 
-	ret = __pci_epf_mhi_alloc_map(mhi_cntrl, from, &tre_phys, &tre_buf,
-				      offset, size);
+	ret = __pci_epf_mhi_alloc_map(mhi_cntrl, buf_info->host_addr, &tre_phys,
+				      &tre_buf, offset, buf_info->size);
 	if (ret) {
 		mutex_unlock(&epf_mhi->lock);
 		return ret;
 	}
 
-	memcpy_fromio(to, tre_buf, size);
+	memcpy_fromio(buf_info->dev_addr, tre_buf, buf_info->size);
 
-	__pci_epf_mhi_unmap_free(mhi_cntrl, from, tre_phys, tre_buf, offset,
-				 size);
+	__pci_epf_mhi_unmap_free(mhi_cntrl, buf_info->host_addr, tre_phys,
+				 tre_buf, offset, buf_info->size);
 
 	mutex_unlock(&epf_mhi->lock);
 
+	if (buf_info->cb)
+		buf_info->cb(buf_info);
+
 	return 0;
 }
 
 static int pci_epf_mhi_iatu_write(struct mhi_ep_cntrl *mhi_cntrl,
-				  void *from, u64 to, size_t size)
+				  struct mhi_ep_buf_info *buf_info)
 {
 	struct pci_epf_mhi *epf_mhi = to_epf_mhi(mhi_cntrl);
-	size_t offset = get_align_offset(epf_mhi, to);
+	size_t offset = get_align_offset(epf_mhi, buf_info->host_addr);
 	void __iomem *tre_buf;
 	phys_addr_t tre_phys;
 	int ret;
 
 	mutex_lock(&epf_mhi->lock);
 
-	ret = __pci_epf_mhi_alloc_map(mhi_cntrl, to, &tre_phys, &tre_buf,
-				      offset, size);
+	ret = __pci_epf_mhi_alloc_map(mhi_cntrl, buf_info->host_addr, &tre_phys,
+				      &tre_buf, offset, buf_info->size);
 	if (ret) {
 		mutex_unlock(&epf_mhi->lock);
 		return ret;
 	}
 
-	memcpy_toio(tre_buf, from, size);
+	memcpy_toio(tre_buf, buf_info->dev_addr, buf_info->size);
 
-	__pci_epf_mhi_unmap_free(mhi_cntrl, to, tre_phys, tre_buf, offset,
-				 size);
+	__pci_epf_mhi_unmap_free(mhi_cntrl, buf_info->host_addr, tre_phys,
+				 tre_buf, offset, buf_info->size);
 
 	mutex_unlock(&epf_mhi->lock);
 
+	if (buf_info->cb)
+		buf_info->cb(buf_info);
+
 	return 0;
 }
 
@@ -270,8 +289,8 @@ static void pci_epf_mhi_dma_callback(void *param)
 	complete(param);
 }
 
-static int pci_epf_mhi_edma_read(struct mhi_ep_cntrl *mhi_cntrl, u64 from,
-				 void *to, size_t size)
+static int pci_epf_mhi_edma_read(struct mhi_ep_cntrl *mhi_cntrl,
+				 struct mhi_ep_buf_info *buf_info)
 {
 	struct pci_epf_mhi *epf_mhi = to_epf_mhi(mhi_cntrl);
 	struct device *dma_dev = epf_mhi->epf->epc->dev.parent;
@@ -284,13 +303,13 @@ static int pci_epf_mhi_edma_read(struct mhi_ep_cntrl *mhi_cntrl, u64 from,
 	dma_addr_t dst_addr;
 	int ret;
 
-	if (size < SZ_4K)
-		return pci_epf_mhi_iatu_read(mhi_cntrl, from, to, size);
+	if (buf_info->size < SZ_4K)
+		return pci_epf_mhi_iatu_read(mhi_cntrl, buf_info);
 
 	mutex_lock(&epf_mhi->lock);
 
 	config.direction = DMA_DEV_TO_MEM;
-	config.src_addr = from;
+	config.src_addr = buf_info->host_addr;
 
 	ret = dmaengine_slave_config(chan, &config);
 	if (ret) {
@@ -298,14 +317,16 @@ static int pci_epf_mhi_edma_read(struct mhi_ep_cntrl *mhi_cntrl, u64 from,
 		goto err_unlock;
 	}
 
-	dst_addr = dma_map_single(dma_dev, to, size, DMA_FROM_DEVICE);
+	dst_addr = dma_map_single(dma_dev, buf_info->dev_addr, buf_info->size,
+				  DMA_FROM_DEVICE);
 	ret = dma_mapping_error(dma_dev, dst_addr);
 	if (ret) {
 		dev_err(dev, "Failed to map remote memory\n");
 		goto err_unlock;
 	}
 
-	desc = dmaengine_prep_slave_single(chan, dst_addr, size, DMA_DEV_TO_MEM,
+	desc = dmaengine_prep_slave_single(chan, dst_addr, buf_info->size,
+					   DMA_DEV_TO_MEM,
 					   DMA_CTRL_ACK | DMA_PREP_INTERRUPT);
 	if (!desc) {
 		dev_err(dev, "Failed to prepare DMA\n");
@@ -332,15 +353,15 @@ static int pci_epf_mhi_edma_read(struct mhi_ep_cntrl *mhi_cntrl, u64 from,
 	}
 
 err_unmap:
-	dma_unmap_single(dma_dev, dst_addr, size, DMA_FROM_DEVICE);
+	dma_unmap_single(dma_dev, dst_addr, buf_info->size, DMA_FROM_DEVICE);
 err_unlock:
 	mutex_unlock(&epf_mhi->lock);
 
 	return ret;
 }
 
-static int pci_epf_mhi_edma_write(struct mhi_ep_cntrl *mhi_cntrl, void *from,
-				  u64 to, size_t size)
+static int pci_epf_mhi_edma_write(struct mhi_ep_cntrl *mhi_cntrl,
+				  struct mhi_ep_buf_info *buf_info)
 {
 	struct pci_epf_mhi *epf_mhi = to_epf_mhi(mhi_cntrl);
 	struct device *dma_dev = epf_mhi->epf->epc->dev.parent;
@@ -353,13 +374,13 @@ static int pci_epf_mhi_edma_write(struct mhi_ep_cntrl *mhi_cntrl, void *from,
 	dma_addr_t src_addr;
 	int ret;
 
-	if (size < SZ_4K)
-		return pci_epf_mhi_iatu_write(mhi_cntrl, from, to, size);
+	if (buf_info->size < SZ_4K)
+		return pci_epf_mhi_iatu_write(mhi_cntrl, buf_info);
 
 	mutex_lock(&epf_mhi->lock);
 
 	config.direction = DMA_MEM_TO_DEV;
-	config.dst_addr = to;
+	config.dst_addr = buf_info->host_addr;
 
 	ret = dmaengine_slave_config(chan, &config);
 	if (ret) {
@@ -367,14 +388,16 @@ static int pci_epf_mhi_edma_write(struct mhi_ep_cntrl *mhi_cntrl, void *from,
 		goto err_unlock;
 	}
 
-	src_addr = dma_map_single(dma_dev, from, size, DMA_TO_DEVICE);
+	src_addr = dma_map_single(dma_dev, buf_info->dev_addr, buf_info->size,
+				  DMA_TO_DEVICE);
 	ret = dma_mapping_error(dma_dev, src_addr);
 	if (ret) {
 		dev_err(dev, "Failed to map remote memory\n");
 		goto err_unlock;
 	}
 
-	desc = dmaengine_prep_slave_single(chan, src_addr, size, DMA_MEM_TO_DEV,
+	desc = dmaengine_prep_slave_single(chan, src_addr, buf_info->size,
+					   DMA_MEM_TO_DEV,
 					   DMA_CTRL_ACK | DMA_PREP_INTERRUPT);
 	if (!desc) {
 		dev_err(dev, "Failed to prepare DMA\n");
@@ -401,7 +424,199 @@ static int pci_epf_mhi_edma_write(struct mhi_ep_cntrl *mhi_cntrl, void *from,
 	}
 
 err_unmap:
-	dma_unmap_single(dma_dev, src_addr, size, DMA_FROM_DEVICE);
+	dma_unmap_single(dma_dev, src_addr, buf_info->size, DMA_TO_DEVICE);
+err_unlock:
+	mutex_unlock(&epf_mhi->lock);
+
+	return ret;
+}
+
+static void pci_epf_mhi_dma_worker(struct work_struct *work)
+{
+	struct pci_epf_mhi *epf_mhi = container_of(work, struct pci_epf_mhi, dma_work);
+	struct device *dma_dev = epf_mhi->epf->epc->dev.parent;
+	struct pci_epf_mhi_dma_transfer *itr, *tmp;
+	struct mhi_ep_buf_info *buf_info;
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&epf_mhi->list_lock, flags);
+	list_splice_tail_init(&epf_mhi->dma_list, &head);
+	spin_unlock_irqrestore(&epf_mhi->list_lock, flags);
+
+	list_for_each_entry_safe(itr, tmp, &head, node) {
+		list_del(&itr->node);
+		dma_unmap_single(dma_dev, itr->paddr, itr->size, itr->dir);
+		buf_info = &itr->buf_info;
+		buf_info->cb(buf_info);
+		kfree(itr);
+	}
+}
+
+static void pci_epf_mhi_dma_async_callback(void *param)
+{
+	struct pci_epf_mhi_dma_transfer *transfer = param;
+	struct pci_epf_mhi *epf_mhi = transfer->epf_mhi;
+
+	spin_lock(&epf_mhi->list_lock);
+	list_add_tail(&transfer->node, &epf_mhi->dma_list);
+	spin_unlock(&epf_mhi->list_lock);
+
+	queue_work(epf_mhi->dma_wq, &epf_mhi->dma_work);
+}
+
+static int pci_epf_mhi_edma_read_async(struct mhi_ep_cntrl *mhi_cntrl,
+				       struct mhi_ep_buf_info *buf_info)
+{
+	struct pci_epf_mhi *epf_mhi = to_epf_mhi(mhi_cntrl);
+	struct device *dma_dev = epf_mhi->epf->epc->dev.parent;
+	struct pci_epf_mhi_dma_transfer *transfer = NULL;
+	struct dma_chan *chan = epf_mhi->dma_chan_rx;
+	struct device *dev = &epf_mhi->epf->dev;
+	DECLARE_COMPLETION_ONSTACK(complete);
+	struct dma_async_tx_descriptor *desc;
+	struct dma_slave_config config = {};
+	dma_cookie_t cookie;
+	dma_addr_t dst_addr;
+	int ret;
+
+	mutex_lock(&epf_mhi->lock);
+
+	config.direction = DMA_DEV_TO_MEM;
+	config.src_addr = buf_info->host_addr;
+
+	ret = dmaengine_slave_config(chan, &config);
+	if (ret) {
+		dev_err(dev, "Failed to configure DMA channel\n");
+		goto err_unlock;
+	}
+
+	dst_addr = dma_map_single(dma_dev, buf_info->dev_addr, buf_info->size,
+				  DMA_FROM_DEVICE);
+	ret = dma_mapping_error(dma_dev, dst_addr);
+	if (ret) {
+		dev_err(dev, "Failed to map remote memory\n");
+		goto err_unlock;
+	}
+
+	desc = dmaengine_prep_slave_single(chan, dst_addr, buf_info->size,
+					   DMA_DEV_TO_MEM,
+					   DMA_CTRL_ACK | DMA_PREP_INTERRUPT);
+	if (!desc) {
+		dev_err(dev, "Failed to prepare DMA\n");
+		ret = -EIO;
+		goto err_unmap;
+	}
+
+	transfer = kzalloc(sizeof(*transfer), GFP_KERNEL);
+	if (!transfer) {
+		ret = -ENOMEM;
+		goto err_unmap;
+	}
+
+	transfer->epf_mhi = epf_mhi;
+	transfer->paddr = dst_addr;
+	transfer->size = buf_info->size;
+	transfer->dir = DMA_FROM_DEVICE;
+	memcpy(&transfer->buf_info, buf_info, sizeof(*buf_info));
+
+	desc->callback = pci_epf_mhi_dma_async_callback;
+	desc->callback_param = transfer;
+
+	cookie = dmaengine_submit(desc);
+	ret = dma_submit_error(cookie);
+	if (ret) {
+		dev_err(dev, "Failed to do DMA submit\n");
+		goto err_free_transfer;
+	}
+
+	dma_async_issue_pending(chan);
+
+	goto err_unlock;
+
+err_free_transfer:
+	kfree(transfer);
+err_unmap:
+	dma_unmap_single(dma_dev, dst_addr, buf_info->size, DMA_FROM_DEVICE);
+err_unlock:
+	mutex_unlock(&epf_mhi->lock);
+
+	return ret;
+}
+
+static int pci_epf_mhi_edma_write_async(struct mhi_ep_cntrl *mhi_cntrl,
+					struct mhi_ep_buf_info *buf_info)
+{
+	struct pci_epf_mhi *epf_mhi = to_epf_mhi(mhi_cntrl);
+	struct device *dma_dev = epf_mhi->epf->epc->dev.parent;
+	struct pci_epf_mhi_dma_transfer *transfer = NULL;
+	struct dma_chan *chan = epf_mhi->dma_chan_tx;
+	struct device *dev = &epf_mhi->epf->dev;
+	DECLARE_COMPLETION_ONSTACK(complete);
+	struct dma_async_tx_descriptor *desc;
+	struct dma_slave_config config = {};
+	dma_cookie_t cookie;
+	dma_addr_t src_addr;
+	int ret;
+
+	mutex_lock(&epf_mhi->lock);
+
+	config.direction = DMA_MEM_TO_DEV;
+	config.dst_addr = buf_info->host_addr;
+
+	ret = dmaengine_slave_config(chan, &config);
+	if (ret) {
+		dev_err(dev, "Failed to configure DMA channel\n");
+		goto err_unlock;
+	}
+
+	src_addr = dma_map_single(dma_dev, buf_info->dev_addr, buf_info->size,
+				  DMA_TO_DEVICE);
+	ret = dma_mapping_error(dma_dev, src_addr);
+	if (ret) {
+		dev_err(dev, "Failed to map remote memory\n");
+		goto err_unlock;
+	}
+
+	desc = dmaengine_prep_slave_single(chan, src_addr, buf_info->size,
+					   DMA_MEM_TO_DEV,
+					   DMA_CTRL_ACK | DMA_PREP_INTERRUPT);
+	if (!desc) {
+		dev_err(dev, "Failed to prepare DMA\n");
+		ret = -EIO;
+		goto err_unmap;
+	}
+
+	transfer = kzalloc(sizeof(*transfer), GFP_KERNEL);
+	if (!transfer) {
+		ret = -ENOMEM;
+		goto err_unmap;
+	}
+
+	transfer->epf_mhi = epf_mhi;
+	transfer->paddr = src_addr;
+	transfer->size = buf_info->size;
+	transfer->dir = DMA_TO_DEVICE;
+	memcpy(&transfer->buf_info, buf_info, sizeof(*buf_info));
+
+	desc->callback = pci_epf_mhi_dma_async_callback;
+	desc->callback_param = transfer;
+
+	cookie = dmaengine_submit(desc);
+	ret = dma_submit_error(cookie);
+	if (ret) {
+		dev_err(dev, "Failed to do DMA submit\n");
+		goto err_free_transfer;
+	}
+
+	dma_async_issue_pending(chan);
+
+	goto err_unlock;
+
+err_free_transfer:
+	kfree(transfer);
+err_unmap:
+	dma_unmap_single(dma_dev, src_addr, buf_info->size, DMA_TO_DEVICE);
 err_unlock:
 	mutex_unlock(&epf_mhi->lock);
 
@@ -431,6 +646,7 @@ static int pci_epf_mhi_dma_init(struct pci_epf_mhi *epf_mhi)
 	struct device *dev = &epf_mhi->epf->dev;
 	struct epf_dma_filter filter;
 	dma_cap_mask_t mask;
+	int ret;
 
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);
@@ -449,16 +665,35 @@ static int pci_epf_mhi_dma_init(struct pci_epf_mhi *epf_mhi)
 						   &filter);
 	if (IS_ERR_OR_NULL(epf_mhi->dma_chan_rx)) {
 		dev_err(dev, "Failed to request rx channel\n");
-		dma_release_channel(epf_mhi->dma_chan_tx);
-		epf_mhi->dma_chan_tx = NULL;
-		return -ENODEV;
+		ret = -ENODEV;
+		goto err_release_tx;
+	}
+
+	epf_mhi->dma_wq = alloc_workqueue("pci_epf_mhi_dma_wq", 0, 0);
+	if (!epf_mhi->dma_wq) {
+		ret = -ENOMEM;
+		goto err_release_rx;
 	}
 
+	INIT_LIST_HEAD(&epf_mhi->dma_list);
+	INIT_WORK(&epf_mhi->dma_work, pci_epf_mhi_dma_worker);
+	spin_lock_init(&epf_mhi->list_lock);
+
 	return 0;
+
+err_release_rx:
+	dma_release_channel(epf_mhi->dma_chan_rx);
+	epf_mhi->dma_chan_rx = NULL;
+err_release_tx:
+	dma_release_channel(epf_mhi->dma_chan_tx);
+	epf_mhi->dma_chan_tx = NULL;
+
+	return ret;
 }
 
 static void pci_epf_mhi_dma_deinit(struct pci_epf_mhi *epf_mhi)
 {
+	destroy_workqueue(epf_mhi->dma_wq);
 	dma_release_channel(epf_mhi->dma_chan_tx);
 	dma_release_channel(epf_mhi->dma_chan_rx);
 	epf_mhi->dma_chan_tx = NULL;
@@ -531,12 +766,13 @@ static int pci_epf_mhi_link_up(struct pci_epf *epf)
 	mhi_cntrl->raise_irq = pci_epf_mhi_raise_irq;
 	mhi_cntrl->alloc_map = pci_epf_mhi_alloc_map;
 	mhi_cntrl->unmap_free = pci_epf_mhi_unmap_free;
+	mhi_cntrl->read_sync = mhi_cntrl->read_async = pci_epf_mhi_iatu_read;
+	mhi_cntrl->write_sync = mhi_cntrl->write_async = pci_epf_mhi_iatu_write;
 	if (info->flags & MHI_EPF_USE_DMA) {
-		mhi_cntrl->read_from_host = pci_epf_mhi_edma_read;
-		mhi_cntrl->write_to_host = pci_epf_mhi_edma_write;
-	} else {
-		mhi_cntrl->read_from_host = pci_epf_mhi_iatu_read;
-		mhi_cntrl->write_to_host = pci_epf_mhi_iatu_write;
+		mhi_cntrl->read_sync = pci_epf_mhi_edma_read;
+		mhi_cntrl->write_sync = pci_epf_mhi_edma_write;
+		mhi_cntrl->read_async = pci_epf_mhi_edma_read_async;
+		mhi_cntrl->write_async = pci_epf_mhi_edma_write_async;
 	}
 
 	/* Register the MHI EP controller */
@@ -644,7 +880,7 @@ static void pci_epf_mhi_unbind(struct pci_epf *epf)
 	pci_epc_clear_bar(epc, epf->func_no, epf->vfunc_no, epf_bar);
 }
 
-static struct pci_epc_event_ops pci_epf_mhi_event_ops = {
+static const struct pci_epc_event_ops pci_epf_mhi_event_ops = {
 	.core_init = pci_epf_mhi_core_init,
 	.link_up = pci_epf_mhi_link_up,
 	.link_down = pci_epf_mhi_link_down,
@@ -682,7 +918,7 @@ static const struct pci_epf_device_id pci_epf_mhi_ids[] = {
 	{},
 };
 
-static struct pci_epf_ops pci_epf_mhi_ops = {
+static const struct pci_epf_ops pci_epf_mhi_ops = {
 	.unbind	= pci_epf_mhi_unbind,
 	.bind	= pci_epf_mhi_bind,
 };
diff --git a/drivers/pci/endpoint/functions/pci-epf-ntb.c b/drivers/pci/endpoint/functions/pci-epf-ntb.c
index 9aac2c6f3bb9..0553946005c4 100644
--- a/drivers/pci/endpoint/functions/pci-epf-ntb.c
+++ b/drivers/pci/endpoint/functions/pci-epf-ntb.c
@@ -140,9 +140,9 @@ static struct pci_epf_header epf_ntb_header = {
 static int epf_ntb_link_up(struct epf_ntb *ntb, bool link_up)
 {
 	enum pci_epc_interface_type type;
-	enum pci_epc_irq_type irq_type;
 	struct epf_ntb_epc *ntb_epc;
 	struct epf_ntb_ctrl *ctrl;
+	unsigned int irq_type;
 	struct pci_epc *epc;
 	u8 func_no, vfunc_no;
 	bool is_msix;
@@ -159,7 +159,7 @@ static int epf_ntb_link_up(struct epf_ntb *ntb, bool link_up)
 			ctrl->link_status |= LINK_STATUS_UP;
 		else
 			ctrl->link_status &= ~LINK_STATUS_UP;
-		irq_type = is_msix ? PCI_EPC_IRQ_MSIX : PCI_EPC_IRQ_MSI;
+		irq_type = is_msix ? PCI_IRQ_MSIX : PCI_IRQ_MSI;
 		ret = pci_epc_raise_irq(epc, func_no, vfunc_no, irq_type, 1);
 		if (ret) {
 			dev_err(&epc->dev,
@@ -2099,7 +2099,7 @@ static int epf_ntb_probe(struct pci_epf *epf,
 	return 0;
 }
 
-static struct pci_epf_ops epf_ntb_ops = {
+static const struct pci_epf_ops epf_ntb_ops = {
 	.bind	= epf_ntb_bind,
 	.unbind	= epf_ntb_unbind,
 	.add_cfs = epf_ntb_add_cfs,
diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
index 1f0d2b84296a..18c80002d3bd 100644
--- a/drivers/pci/endpoint/functions/pci-epf-test.c
+++ b/drivers/pci/endpoint/functions/pci-epf-test.c
@@ -19,11 +19,11 @@
 #include <linux/pci-epf.h>
 #include <linux/pci_regs.h>
 
-#define IRQ_TYPE_LEGACY			0
+#define IRQ_TYPE_INTX			0
 #define IRQ_TYPE_MSI			1
 #define IRQ_TYPE_MSIX			2
 
-#define COMMAND_RAISE_LEGACY_IRQ	BIT(0)
+#define COMMAND_RAISE_INTX_IRQ		BIT(0)
 #define COMMAND_RAISE_MSI_IRQ		BIT(1)
 #define COMMAND_RAISE_MSIX_IRQ		BIT(2)
 #define COMMAND_READ			BIT(3)
@@ -600,9 +600,9 @@ static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test,
 	WRITE_ONCE(reg->status, status);
 
 	switch (reg->irq_type) {
-	case IRQ_TYPE_LEGACY:
+	case IRQ_TYPE_INTX:
 		pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no,
-				  PCI_EPC_IRQ_LEGACY, 0);
+				  PCI_IRQ_INTX, 0);
 		break;
 	case IRQ_TYPE_MSI:
 		count = pci_epc_get_msi(epc, epf->func_no, epf->vfunc_no);
@@ -612,7 +612,7 @@ static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test,
 			return;
 		}
 		pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no,
-				  PCI_EPC_IRQ_MSI, reg->irq_number);
+				  PCI_IRQ_MSI, reg->irq_number);
 		break;
 	case IRQ_TYPE_MSIX:
 		count = pci_epc_get_msix(epc, epf->func_no, epf->vfunc_no);
@@ -622,7 +622,7 @@ static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test,
 			return;
 		}
 		pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no,
-				  PCI_EPC_IRQ_MSIX, reg->irq_number);
+				  PCI_IRQ_MSIX, reg->irq_number);
 		break;
 	default:
 		dev_err(dev, "Failed to raise IRQ, unknown type\n");
@@ -659,7 +659,7 @@ static void pci_epf_test_cmd_handler(struct work_struct *work)
 	}
 
 	switch (command) {
-	case COMMAND_RAISE_LEGACY_IRQ:
+	case COMMAND_RAISE_INTX_IRQ:
 	case COMMAND_RAISE_MSI_IRQ:
 	case COMMAND_RAISE_MSIX_IRQ:
 		pci_epf_test_raise_irq(epf_test, reg);
@@ -973,7 +973,7 @@ static int pci_epf_test_probe(struct pci_epf *epf,
 	return 0;
 }
 
-static struct pci_epf_ops ops = {
+static const struct pci_epf_ops ops = {
 	.unbind	= pci_epf_test_unbind,
 	.bind	= pci_epf_test_bind,
 };
diff --git a/drivers/pci/endpoint/functions/pci-epf-vntb.c b/drivers/pci/endpoint/functions/pci-epf-vntb.c
index 3f60128560ed..e75a2af77328 100644
--- a/drivers/pci/endpoint/functions/pci-epf-vntb.c
+++ b/drivers/pci/endpoint/functions/pci-epf-vntb.c
@@ -1172,11 +1172,8 @@ static int vntb_epf_peer_db_set(struct ntb_dev *ndev, u64 db_bits)
 	func_no = ntb->epf->func_no;
 	vfunc_no = ntb->epf->vfunc_no;
 
-	ret = pci_epc_raise_irq(ntb->epf->epc,
-				func_no,
-				vfunc_no,
-				PCI_EPC_IRQ_MSI,
-				interrupt_num + 1);
+	ret = pci_epc_raise_irq(ntb->epf->epc, func_no, vfunc_no,
+				PCI_IRQ_MSI, interrupt_num + 1);
 	if (ret)
 		dev_err(&ntb->ntb.dev, "Failed to raise IRQ\n");
 
@@ -1387,7 +1384,7 @@ static void epf_ntb_unbind(struct pci_epf *epf)
 }
 
 // EPF driver probe
-static struct pci_epf_ops epf_ntb_ops = {
+static const struct pci_epf_ops epf_ntb_ops = {
 	.bind   = epf_ntb_bind,
 	.unbind = epf_ntb_unbind,
 	.add_cfs = epf_ntb_add_cfs,
diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c
index 56e1184bc6c2..dcd4e66430c1 100644
--- a/drivers/pci/endpoint/pci-epc-core.c
+++ b/drivers/pci/endpoint/pci-epc-core.c
@@ -211,13 +211,13 @@ EXPORT_SYMBOL_GPL(pci_epc_start);
  * @epc: the EPC device which has to interrupt the host
  * @func_no: the physical endpoint function number in the EPC device
  * @vfunc_no: the virtual endpoint function number in the physical function
- * @type: specify the type of interrupt; legacy, MSI or MSI-X
+ * @type: specify the type of interrupt; INTX, MSI or MSI-X
  * @interrupt_num: the MSI or MSI-X interrupt number with range (1-N)
  *
- * Invoke to raise an legacy, MSI or MSI-X interrupt
+ * Invoke to raise an INTX, MSI or MSI-X interrupt
  */
 int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-		      enum pci_epc_irq_type type, u16 interrupt_num)
+		      unsigned int type, u16 interrupt_num)
 {
 	int ret;
 
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 25dbe85c4217..aaa33e8dc4c9 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -745,6 +745,7 @@ static int sriov_init(struct pci_dev *dev, int pos)
 	u16 ctrl, total;
 	struct pci_sriov *iov;
 	struct resource *res;
+	const char *res_name;
 	struct pci_dev *pdev;
 
 	pci_read_config_word(dev, pos + PCI_SRIOV_CTRL, &ctrl);
@@ -785,6 +786,8 @@ found:
 	nres = 0;
 	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
 		res = &dev->resource[i + PCI_IOV_RESOURCES];
+		res_name = pci_resource_name(dev, i + PCI_IOV_RESOURCES);
+
 		/*
 		 * If it is already FIXED, don't change it, something
 		 * (perhaps EA or header fixups) wants it this way.
@@ -802,8 +805,8 @@ found:
 		}
 		iov->barsz[i] = resource_size(res);
 		res->end = res->start + resource_size(res) * total - 1;
-		pci_info(dev, "VF(n) BAR%d space: %pR (contains BAR%d for %d VFs)\n",
-			 i, res, i, total);
+		pci_info(dev, "%s %pR: contains BAR %d for %d VFs\n",
+			 res_name, res, i, total);
 		i += bar64;
 		nres++;
 	}
diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c
index c8be056c248d..cfd84a899c82 100644
--- a/drivers/pci/msi/irqdomain.c
+++ b/drivers/pci/msi/irqdomain.c
@@ -61,7 +61,7 @@ static irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc)
 
 	return (irq_hw_number_t)desc->msi_index |
 		pci_dev_id(dev) << 11 |
-		(pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 27;
+		((irq_hw_number_t)(pci_domain_nr(dev->bus) & 0xFFFFFFFF)) << 27;
 }
 
 static void pci_msi_domain_set_desc(msi_alloc_info_t *arg,
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index ae550d71b815..c3585229c12a 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -851,6 +851,66 @@ struct resource *pci_find_resource(struct pci_dev *dev, struct resource *res)
 EXPORT_SYMBOL(pci_find_resource);
 
 /**
+ * pci_resource_name - Return the name of the PCI resource
+ * @dev: PCI device to query
+ * @i: index of the resource
+ *
+ * Return the standard PCI resource (BAR) name according to their index.
+ */
+const char *pci_resource_name(struct pci_dev *dev, unsigned int i)
+{
+	static const char * const bar_name[] = {
+		"BAR 0",
+		"BAR 1",
+		"BAR 2",
+		"BAR 3",
+		"BAR 4",
+		"BAR 5",
+		"ROM",
+#ifdef CONFIG_PCI_IOV
+		"VF BAR 0",
+		"VF BAR 1",
+		"VF BAR 2",
+		"VF BAR 3",
+		"VF BAR 4",
+		"VF BAR 5",
+#endif
+		"bridge window",	/* "io" included in %pR */
+		"bridge window",	/* "mem" included in %pR */
+		"bridge window",	/* "mem pref" included in %pR */
+	};
+	static const char * const cardbus_name[] = {
+		"BAR 1",
+		"unknown",
+		"unknown",
+		"unknown",
+		"unknown",
+		"unknown",
+#ifdef CONFIG_PCI_IOV
+		"unknown",
+		"unknown",
+		"unknown",
+		"unknown",
+		"unknown",
+		"unknown",
+#endif
+		"CardBus bridge window 0",	/* I/O */
+		"CardBus bridge window 1",	/* I/O */
+		"CardBus bridge window 0",	/* mem */
+		"CardBus bridge window 1",	/* mem */
+	};
+
+	if (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS &&
+	    i < ARRAY_SIZE(cardbus_name))
+		return cardbus_name[i];
+
+	if (i < ARRAY_SIZE(bar_name))
+		return bar_name[i];
+
+	return "unknown";
+}
+
+/**
  * pci_wait_for_pending - wait for @mask bit(s) to clear in status word @pos
  * @dev: the PCI device to operate on
  * @pos: config space offset of status word
@@ -1294,6 +1354,7 @@ end:
 /**
  * pci_set_full_power_state - Put a PCI device into D0 and update its state
  * @dev: PCI device to power up
+ * @locked: whether pci_bus_sem is held
  *
  * Call pci_power_up() to put @dev into D0, read from its PCI_PM_CTRL register
  * to confirm the state change, restore its BARs if they might be lost and
@@ -1303,7 +1364,7 @@ end:
  * to D0, it is more efficient to use pci_power_up() directly instead of this
  * function.
  */
-static int pci_set_full_power_state(struct pci_dev *dev)
+static int pci_set_full_power_state(struct pci_dev *dev, bool locked)
 {
 	u16 pmcsr;
 	int ret;
@@ -1339,7 +1400,7 @@ static int pci_set_full_power_state(struct pci_dev *dev)
 	}
 
 	if (dev->bus->self)
-		pcie_aspm_pm_state_change(dev->bus->self);
+		pcie_aspm_pm_state_change(dev->bus->self, locked);
 
 	return 0;
 }
@@ -1368,10 +1429,22 @@ void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state)
 		pci_walk_bus(bus, __pci_dev_set_current_state, &state);
 }
 
+static void __pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state, bool locked)
+{
+	if (!bus)
+		return;
+
+	if (locked)
+		pci_walk_bus_locked(bus, __pci_dev_set_current_state, &state);
+	else
+		pci_walk_bus(bus, __pci_dev_set_current_state, &state);
+}
+
 /**
  * pci_set_low_power_state - Put a PCI device into a low-power state.
  * @dev: PCI device to handle.
  * @state: PCI power state (D1, D2, D3hot) to put the device into.
+ * @locked: whether pci_bus_sem is held
  *
  * Use the device's PCI_PM_CTRL register to put it into a low-power state.
  *
@@ -1382,7 +1455,7 @@ void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state)
  * 0 if device already is in the requested state.
  * 0 if device's power state has been successfully changed.
  */
-static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state)
+static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state, bool locked)
 {
 	u16 pmcsr;
 
@@ -1436,29 +1509,12 @@ static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state)
 				     pci_power_name(state));
 
 	if (dev->bus->self)
-		pcie_aspm_pm_state_change(dev->bus->self);
+		pcie_aspm_pm_state_change(dev->bus->self, locked);
 
 	return 0;
 }
 
-/**
- * pci_set_power_state - Set the power state of a PCI device
- * @dev: PCI device to handle.
- * @state: PCI power state (D0, D1, D2, D3hot) to put the device into.
- *
- * Transition a device to a new power state, using the platform firmware and/or
- * the device's PCI PM registers.
- *
- * RETURN VALUE:
- * -EINVAL if the requested state is invalid.
- * -EIO if device does not support PCI PM or its PM capabilities register has a
- * wrong version, or device doesn't support the requested state.
- * 0 if the transition is to D1 or D2 but D1 and D2 are not supported.
- * 0 if device already is in the requested state.
- * 0 if the transition is to D3 but D3 is not supported.
- * 0 if device's power state has been successfully changed.
- */
-int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
+static int __pci_set_power_state(struct pci_dev *dev, pci_power_t state, bool locked)
 {
 	int error;
 
@@ -1482,7 +1538,7 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 		return 0;
 
 	if (state == PCI_D0)
-		return pci_set_full_power_state(dev);
+		return pci_set_full_power_state(dev, locked);
 
 	/*
 	 * This device is quirked not to be put into D3, so don't put it in
@@ -1496,16 +1552,16 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 		 * To put the device in D3cold, put it into D3hot in the native
 		 * way, then put it into D3cold using platform ops.
 		 */
-		error = pci_set_low_power_state(dev, PCI_D3hot);
+		error = pci_set_low_power_state(dev, PCI_D3hot, locked);
 
 		if (pci_platform_power_transition(dev, PCI_D3cold))
 			return error;
 
 		/* Powering off a bridge may power off the whole hierarchy */
 		if (dev->current_state == PCI_D3cold)
-			pci_bus_set_current_state(dev->subordinate, PCI_D3cold);
+			__pci_bus_set_current_state(dev->subordinate, PCI_D3cold, locked);
 	} else {
-		error = pci_set_low_power_state(dev, state);
+		error = pci_set_low_power_state(dev, state, locked);
 
 		if (pci_platform_power_transition(dev, state))
 			return error;
@@ -1513,8 +1569,38 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 
 	return 0;
 }
+
+/**
+ * pci_set_power_state - Set the power state of a PCI device
+ * @dev: PCI device to handle.
+ * @state: PCI power state (D0, D1, D2, D3hot) to put the device into.
+ *
+ * Transition a device to a new power state, using the platform firmware and/or
+ * the device's PCI PM registers.
+ *
+ * RETURN VALUE:
+ * -EINVAL if the requested state is invalid.
+ * -EIO if device does not support PCI PM or its PM capabilities register has a
+ * wrong version, or device doesn't support the requested state.
+ * 0 if the transition is to D1 or D2 but D1 and D2 are not supported.
+ * 0 if device already is in the requested state.
+ * 0 if the transition is to D3 but D3 is not supported.
+ * 0 if device's power state has been successfully changed.
+ */
+int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
+{
+	return __pci_set_power_state(dev, state, false);
+}
 EXPORT_SYMBOL(pci_set_power_state);
 
+int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state)
+{
+	lockdep_assert_held(&pci_bus_sem);
+
+	return __pci_set_power_state(dev, state, true);
+}
+EXPORT_SYMBOL(pci_set_power_state_locked);
+
 #define PCI_EXP_SAVE_REGS	7
 
 static struct pci_cap_saved_state *_pci_find_saved_cap(struct pci_dev *pci_dev,
@@ -2436,29 +2522,36 @@ static void pci_pme_list_scan(struct work_struct *work)
 		if (pdev->pme_poll) {
 			struct pci_dev *bridge = pdev->bus->self;
 			struct device *dev = &pdev->dev;
-			int pm_status;
+			struct device *bdev = bridge ? &bridge->dev : NULL;
+			int bref = 0;
 
 			/*
-			 * If bridge is in low power state, the
-			 * configuration space of subordinate devices
-			 * may be not accessible
+			 * If we have a bridge, it should be in an active/D0
+			 * state or the configuration space of subordinate
+			 * devices may not be accessible or stable over the
+			 * course of the call.
 			 */
-			if (bridge && bridge->current_state != PCI_D0)
-				continue;
+			if (bdev) {
+				bref = pm_runtime_get_if_active(bdev, true);
+				if (!bref)
+					continue;
+
+				if (bridge->current_state != PCI_D0)
+					goto put_bridge;
+			}
 
 			/*
-			 * If the device is in a low power state it
-			 * should not be polled either.
+			 * The device itself should be suspended but config
+			 * space must be accessible, therefore it cannot be in
+			 * D3cold.
 			 */
-			pm_status = pm_runtime_get_if_active(dev, true);
-			if (!pm_status)
-				continue;
-
-			if (pdev->current_state != PCI_D3cold)
+			if (pm_runtime_suspended(dev) &&
+			    pdev->current_state != PCI_D3cold)
 				pci_pme_wakeup(pdev, NULL);
 
-			if (pm_status > 0)
-				pm_runtime_put(dev);
+put_bridge:
+			if (bref > 0)
+				pm_runtime_put(bdev);
 		} else {
 			list_del(&pme_dev->list);
 			kfree(pme_dev);
@@ -3299,6 +3392,7 @@ static struct resource *pci_ea_get_resource(struct pci_dev *dev, u8 bei,
 static int pci_ea_read(struct pci_dev *dev, int offset)
 {
 	struct resource *res;
+	const char *res_name;
 	int ent_size, ent_offset = offset;
 	resource_size_t start, end;
 	unsigned long flags;
@@ -3328,6 +3422,7 @@ static int pci_ea_read(struct pci_dev *dev, int offset)
 		goto out;
 
 	res = pci_ea_get_resource(dev, bei, prop);
+	res_name = pci_resource_name(dev, bei);
 	if (!res) {
 		pci_err(dev, "Unsupported EA entry BEI: %u\n", bei);
 		goto out;
@@ -3401,16 +3496,16 @@ static int pci_ea_read(struct pci_dev *dev, int offset)
 	res->flags = flags;
 
 	if (bei <= PCI_EA_BEI_BAR5)
-		pci_info(dev, "BAR %d: %pR (from Enhanced Allocation, properties %#02x)\n",
-			   bei, res, prop);
+		pci_info(dev, "%s %pR: from Enhanced Allocation, properties %#02x\n",
+			 res_name, res, prop);
 	else if (bei == PCI_EA_BEI_ROM)
-		pci_info(dev, "ROM: %pR (from Enhanced Allocation, properties %#02x)\n",
-			   res, prop);
+		pci_info(dev, "%s %pR: from Enhanced Allocation, properties %#02x\n",
+			 res_name, res, prop);
 	else if (bei >= PCI_EA_BEI_VF_BAR0 && bei <= PCI_EA_BEI_VF_BAR5)
-		pci_info(dev, "VF BAR %d: %pR (from Enhanced Allocation, properties %#02x)\n",
-			   bei - PCI_EA_BEI_VF_BAR0, res, prop);
+		pci_info(dev, "%s %pR: from Enhanced Allocation, properties %#02x\n",
+			 res_name, res, prop);
 	else
-		pci_info(dev, "BEI %d res: %pR (from Enhanced Allocation, properties %#02x)\n",
+		pci_info(dev, "BEI %d %pR: from Enhanced Allocation, properties %#02x\n",
 			   bei, res, prop);
 
 out:
@@ -6233,6 +6328,41 @@ int pcie_set_mps(struct pci_dev *dev, int mps)
 }
 EXPORT_SYMBOL(pcie_set_mps);
 
+static enum pci_bus_speed to_pcie_link_speed(u16 lnksta)
+{
+	return pcie_link_speed[FIELD_GET(PCI_EXP_LNKSTA_CLS, lnksta)];
+}
+
+int pcie_link_speed_mbps(struct pci_dev *pdev)
+{
+	u16 lnksta;
+	int err;
+
+	err = pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnksta);
+	if (err)
+		return err;
+
+	switch (to_pcie_link_speed(lnksta)) {
+	case PCIE_SPEED_2_5GT:
+		return 2500;
+	case PCIE_SPEED_5_0GT:
+		return 5000;
+	case PCIE_SPEED_8_0GT:
+		return 8000;
+	case PCIE_SPEED_16_0GT:
+		return 16000;
+	case PCIE_SPEED_32_0GT:
+		return 32000;
+	case PCIE_SPEED_64_0GT:
+		return 64000;
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL(pcie_link_speed_mbps);
+
 /**
  * pcie_bandwidth_available - determine minimum link settings of a PCIe
  *			      device and its bandwidth limitation
@@ -6266,8 +6396,7 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev,
 	while (dev) {
 		pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnksta);
 
-		next_speed = pcie_link_speed[FIELD_GET(PCI_EXP_LNKSTA_CLS,
-						       lnksta)];
+		next_speed = to_pcie_link_speed(lnksta);
 		next_width = FIELD_GET(PCI_EXP_LNKSTA_NLW, lnksta);
 
 		next_bw = next_width * PCIE_SPEED2MBS_ENC(next_speed);
@@ -6698,14 +6827,15 @@ static void pci_request_resource_alignment(struct pci_dev *dev, int bar,
 					   resource_size_t align, bool resize)
 {
 	struct resource *r = &dev->resource[bar];
+	const char *r_name = pci_resource_name(dev, bar);
 	resource_size_t size;
 
 	if (!(r->flags & IORESOURCE_MEM))
 		return;
 
 	if (r->flags & IORESOURCE_PCI_FIXED) {
-		pci_info(dev, "BAR%d %pR: ignoring requested alignment %#llx\n",
-			 bar, r, (unsigned long long)align);
+		pci_info(dev, "%s %pR: ignoring requested alignment %#llx\n",
+			 r_name, r, (unsigned long long)align);
 		return;
 	}
 
@@ -6741,8 +6871,8 @@ static void pci_request_resource_alignment(struct pci_dev *dev, int bar,
 	 * devices and we use the second.
 	 */
 
-	pci_info(dev, "BAR%d %pR: requesting alignment to %#llx\n",
-		 bar, r, (unsigned long long)align);
+	pci_info(dev, "%s %pR: requesting alignment to %#llx\n",
+		 r_name, r, (unsigned long long)align);
 
 	if (resize) {
 		r->start = 0;
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index f43873049d52..e9750b1b19ba 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -255,6 +255,8 @@ void __pci_bus_assign_resources(const struct pci_bus *bus,
 				struct list_head *fail_head);
 bool pci_bus_clip_resource(struct pci_dev *dev, int idx);
 
+const char *pci_resource_name(struct pci_dev *dev, unsigned int i);
+
 void pci_reassigndev_resource_alignment(struct pci_dev *dev);
 void pci_disable_bridge_window(struct pci_dev *dev);
 struct pci_bus *pci_bus_get(struct pci_bus *bus);
@@ -272,7 +274,7 @@ void pci_bus_put(struct pci_bus *bus);
 
 /* PCIe speed to Mb/s reduced by encoding overhead */
 #define PCIE_SPEED2MBS_ENC(speed) \
-	((speed) == PCIE_SPEED_64_0GT ? 64000*128/130 : \
+	((speed) == PCIE_SPEED_64_0GT ? 64000*1/1 : \
 	 (speed) == PCIE_SPEED_32_0GT ? 32000*128/130 : \
 	 (speed) == PCIE_SPEED_16_0GT ? 16000*128/130 : \
 	 (speed) == PCIE_SPEED_8_0GT  ?  8000*128/130 : \
@@ -569,12 +571,12 @@ int pcie_retrain_link(struct pci_dev *pdev, bool use_lt);
 #ifdef CONFIG_PCIEASPM
 void pcie_aspm_init_link_state(struct pci_dev *pdev);
 void pcie_aspm_exit_link_state(struct pci_dev *pdev);
-void pcie_aspm_pm_state_change(struct pci_dev *pdev);
+void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked);
 void pcie_aspm_powersave_config_link(struct pci_dev *pdev);
 #else
 static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { }
 static inline void pcie_aspm_exit_link_state(struct pci_dev *pdev) { }
-static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev) { }
+static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked) { }
 static inline void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { }
 #endif
 
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 42a3bd35a3e1..05fc30bb5134 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -41,8 +41,8 @@
 #define AER_MAX_TYPEOF_UNCOR_ERRS	27	/* as per PCI_ERR_UNCOR_STATUS*/
 
 struct aer_err_source {
-	unsigned int status;
-	unsigned int id;
+	u32 status;			/* PCI_ERR_ROOT_STATUS */
+	u32 id;				/* PCI_ERR_ROOT_ERR_SRC */
 };
 
 struct aer_rpc {
@@ -435,10 +435,10 @@ void pci_aer_exit(struct pci_dev *dev)
 /*
  * AER error strings
  */
-static const char *aer_error_severity_string[] = {
-	"Uncorrected (Non-Fatal)",
-	"Uncorrected (Fatal)",
-	"Corrected"
+static const char * const aer_error_severity_string[] = {
+	"Uncorrectable (Non-Fatal)",
+	"Uncorrectable (Fatal)",
+	"Correctable"
 };
 
 static const char *aer_error_layer[] = {
@@ -740,7 +740,7 @@ static void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info)
 	u8 bus = info->id >> 8;
 	u8 devfn = info->id & 0xff;
 
-	pci_info(dev, "%s%s error received: %04x:%02x:%02x.%d\n",
+	pci_info(dev, "%s%s error message received from %04x:%02x:%02x.%d\n",
 		 info->multi_error_valid ? "Multiple " : "",
 		 aer_error_severity_string[info->severity],
 		 pci_domain_nr(dev->bus), bus, PCI_SLOT(devfn),
@@ -929,7 +929,12 @@ static bool find_source_device(struct pci_dev *parent,
 		pci_walk_bus(parent->subordinate, find_device_iter, e_info);
 
 	if (!e_info->error_dev_num) {
-		pci_info(parent, "can't find device of ID%04x\n", e_info->id);
+		u8 bus = e_info->id >> 8;
+		u8 devfn = e_info->id & 0xff;
+
+		pci_info(parent, "found no error details for %04x:%02x:%02x.%d\n",
+			 pci_domain_nr(parent->bus), bus, PCI_SLOT(devfn),
+			 PCI_FUNC(devfn));
 		return false;
 	}
 	return true;
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 5a0066ecc3c5..bc0bd86695ec 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -1003,8 +1003,11 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev)
 	up_read(&pci_bus_sem);
 }
 
-/* @pdev: the root port or switch downstream port */
-void pcie_aspm_pm_state_change(struct pci_dev *pdev)
+/*
+ * @pdev: the root port or switch downstream port
+ * @locked: whether pci_bus_sem is held
+ */
+void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked)
 {
 	struct pcie_link_state *link = pdev->link_state;
 
@@ -1014,12 +1017,14 @@ void pcie_aspm_pm_state_change(struct pci_dev *pdev)
 	 * Devices changed PM state, we should recheck if latency
 	 * meets all functions' requirement
 	 */
-	down_read(&pci_bus_sem);
+	if (!locked)
+		down_read(&pci_bus_sem);
 	mutex_lock(&aspm_lock);
 	pcie_update_aspm_capable(link->root);
 	pcie_config_aspm_path(link);
 	mutex_unlock(&aspm_lock);
-	up_read(&pci_bus_sem);
+	if (!locked)
+		up_read(&pci_bus_sem);
 }
 
 void pcie_aspm_powersave_config_link(struct pci_dev *pdev)
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index ed6b7f48736a..b7335be56008 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -180,6 +180,7 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 	u64 l64, sz64, mask64;
 	u16 orig_cmd;
 	struct pci_bus_region region, inverted_region;
+	const char *res_name = pci_resource_name(dev, res - dev->resource);
 
 	mask = type ? PCI_ROM_ADDRESS_MASK : ~0;
 
@@ -254,8 +255,7 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 
 	sz64 = pci_size(l64, sz64, mask64);
 	if (!sz64) {
-		pci_info(dev, FW_BUG "reg 0x%x: invalid BAR (can't size)\n",
-			 pos);
+		pci_info(dev, FW_BUG "%s: invalid; can't size\n", res_name);
 		goto fail;
 	}
 
@@ -265,8 +265,8 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 			res->flags |= IORESOURCE_UNSET | IORESOURCE_DISABLED;
 			res->start = 0;
 			res->end = 0;
-			pci_err(dev, "reg 0x%x: can't handle BAR larger than 4GB (size %#010llx)\n",
-				pos, (unsigned long long)sz64);
+			pci_err(dev, "%s: can't handle BAR larger than 4GB (size %#010llx)\n",
+				res_name, (unsigned long long)sz64);
 			goto out;
 		}
 
@@ -275,8 +275,8 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 			res->flags |= IORESOURCE_UNSET;
 			res->start = 0;
 			res->end = sz64 - 1;
-			pci_info(dev, "reg 0x%x: can't handle BAR above 4GB (bus address %#010llx)\n",
-				 pos, (unsigned long long)l64);
+			pci_info(dev, "%s: can't handle BAR above 4GB (bus address %#010llx)\n",
+				 res_name, (unsigned long long)l64);
 			goto out;
 		}
 	}
@@ -302,8 +302,8 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 		res->flags |= IORESOURCE_UNSET;
 		res->start = 0;
 		res->end = region.end - region.start;
-		pci_info(dev, "reg 0x%x: initial BAR value %#010llx invalid\n",
-			 pos, (unsigned long long)region.start);
+		pci_info(dev, "%s: initial BAR value %#010llx invalid\n",
+			 res_name, (unsigned long long)region.start);
 	}
 
 	goto out;
@@ -313,7 +313,7 @@ fail:
 	res->flags = 0;
 out:
 	if (res->flags)
-		pci_info(dev, "reg 0x%x: %pR\n", pos, res);
+		pci_info(dev, "%s %pR\n", res_name, res);
 
 	return (res->flags & IORESOURCE_MEM_64) ? 1 : 0;
 }
@@ -344,64 +344,12 @@ static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom)
 	}
 }
 
-static void pci_read_bridge_windows(struct pci_dev *bridge)
+static void pci_read_bridge_io(struct pci_dev *dev, struct resource *res,
+			       bool log)
 {
-	u16 io;
-	u32 pmem, tmp;
-
-	pci_read_config_word(bridge, PCI_IO_BASE, &io);
-	if (!io) {
-		pci_write_config_word(bridge, PCI_IO_BASE, 0xe0f0);
-		pci_read_config_word(bridge, PCI_IO_BASE, &io);
-		pci_write_config_word(bridge, PCI_IO_BASE, 0x0);
-	}
-	if (io)
-		bridge->io_window = 1;
-
-	/*
-	 * DECchip 21050 pass 2 errata: the bridge may miss an address
-	 * disconnect boundary by one PCI data phase.  Workaround: do not
-	 * use prefetching on this device.
-	 */
-	if (bridge->vendor == PCI_VENDOR_ID_DEC && bridge->device == 0x0001)
-		return;
-
-	pci_read_config_dword(bridge, PCI_PREF_MEMORY_BASE, &pmem);
-	if (!pmem) {
-		pci_write_config_dword(bridge, PCI_PREF_MEMORY_BASE,
-					       0xffe0fff0);
-		pci_read_config_dword(bridge, PCI_PREF_MEMORY_BASE, &pmem);
-		pci_write_config_dword(bridge, PCI_PREF_MEMORY_BASE, 0x0);
-	}
-	if (!pmem)
-		return;
-
-	bridge->pref_window = 1;
-
-	if ((pmem & PCI_PREF_RANGE_TYPE_MASK) == PCI_PREF_RANGE_TYPE_64) {
-
-		/*
-		 * Bridge claims to have a 64-bit prefetchable memory
-		 * window; verify that the upper bits are actually
-		 * writable.
-		 */
-		pci_read_config_dword(bridge, PCI_PREF_BASE_UPPER32, &pmem);
-		pci_write_config_dword(bridge, PCI_PREF_BASE_UPPER32,
-				       0xffffffff);
-		pci_read_config_dword(bridge, PCI_PREF_BASE_UPPER32, &tmp);
-		pci_write_config_dword(bridge, PCI_PREF_BASE_UPPER32, pmem);
-		if (tmp)
-			bridge->pref_64_window = 1;
-	}
-}
-
-static void pci_read_bridge_io(struct pci_bus *child)
-{
-	struct pci_dev *dev = child->self;
 	u8 io_base_lo, io_limit_lo;
 	unsigned long io_mask, io_granularity, base, limit;
 	struct pci_bus_region region;
-	struct resource *res;
 
 	io_mask = PCI_IO_RANGE_MASK;
 	io_granularity = 0x1000;
@@ -411,7 +359,6 @@ static void pci_read_bridge_io(struct pci_bus *child)
 		io_granularity = 0x400;
 	}
 
-	res = child->resource[0];
 	pci_read_config_byte(dev, PCI_IO_BASE, &io_base_lo);
 	pci_read_config_byte(dev, PCI_IO_LIMIT, &io_limit_lo);
 	base = (io_base_lo & io_mask) << 8;
@@ -431,19 +378,18 @@ static void pci_read_bridge_io(struct pci_bus *child)
 		region.start = base;
 		region.end = limit + io_granularity - 1;
 		pcibios_bus_to_resource(dev->bus, res, &region);
-		pci_info(dev, "  bridge window %pR\n", res);
+		if (log)
+			pci_info(dev, "  bridge window %pR\n", res);
 	}
 }
 
-static void pci_read_bridge_mmio(struct pci_bus *child)
+static void pci_read_bridge_mmio(struct pci_dev *dev, struct resource *res,
+				 bool log)
 {
-	struct pci_dev *dev = child->self;
 	u16 mem_base_lo, mem_limit_lo;
 	unsigned long base, limit;
 	struct pci_bus_region region;
-	struct resource *res;
 
-	res = child->resource[1];
 	pci_read_config_word(dev, PCI_MEMORY_BASE, &mem_base_lo);
 	pci_read_config_word(dev, PCI_MEMORY_LIMIT, &mem_limit_lo);
 	base = ((unsigned long) mem_base_lo & PCI_MEMORY_RANGE_MASK) << 16;
@@ -453,20 +399,19 @@ static void pci_read_bridge_mmio(struct pci_bus *child)
 		region.start = base;
 		region.end = limit + 0xfffff;
 		pcibios_bus_to_resource(dev->bus, res, &region);
-		pci_info(dev, "  bridge window %pR\n", res);
+		if (log)
+			pci_info(dev, "  bridge window %pR\n", res);
 	}
 }
 
-static void pci_read_bridge_mmio_pref(struct pci_bus *child)
+static void pci_read_bridge_mmio_pref(struct pci_dev *dev, struct resource *res,
+				      bool log)
 {
-	struct pci_dev *dev = child->self;
 	u16 mem_base_lo, mem_limit_lo;
 	u64 base64, limit64;
 	pci_bus_addr_t base, limit;
 	struct pci_bus_region region;
-	struct resource *res;
 
-	res = child->resource[2];
 	pci_read_config_word(dev, PCI_PREF_MEMORY_BASE, &mem_base_lo);
 	pci_read_config_word(dev, PCI_PREF_MEMORY_LIMIT, &mem_limit_lo);
 	base64 = (mem_base_lo & PCI_PREF_RANGE_MASK) << 16;
@@ -506,10 +451,77 @@ static void pci_read_bridge_mmio_pref(struct pci_bus *child)
 		region.start = base;
 		region.end = limit + 0xfffff;
 		pcibios_bus_to_resource(dev->bus, res, &region);
-		pci_info(dev, "  bridge window %pR\n", res);
+		if (log)
+			pci_info(dev, "  bridge window %pR\n", res);
 	}
 }
 
+static void pci_read_bridge_windows(struct pci_dev *bridge)
+{
+	u32 buses;
+	u16 io;
+	u32 pmem, tmp;
+	struct resource res;
+
+	pci_read_config_dword(bridge, PCI_PRIMARY_BUS, &buses);
+	res.flags = IORESOURCE_BUS;
+	res.start = (buses >> 8) & 0xff;
+	res.end = (buses >> 16) & 0xff;
+	pci_info(bridge, "PCI bridge to %pR%s\n", &res,
+		 bridge->transparent ? " (subtractive decode)" : "");
+
+	pci_read_config_word(bridge, PCI_IO_BASE, &io);
+	if (!io) {
+		pci_write_config_word(bridge, PCI_IO_BASE, 0xe0f0);
+		pci_read_config_word(bridge, PCI_IO_BASE, &io);
+		pci_write_config_word(bridge, PCI_IO_BASE, 0x0);
+	}
+	if (io) {
+		bridge->io_window = 1;
+		pci_read_bridge_io(bridge, &res, true);
+	}
+
+	pci_read_bridge_mmio(bridge, &res, true);
+
+	/*
+	 * DECchip 21050 pass 2 errata: the bridge may miss an address
+	 * disconnect boundary by one PCI data phase.  Workaround: do not
+	 * use prefetching on this device.
+	 */
+	if (bridge->vendor == PCI_VENDOR_ID_DEC && bridge->device == 0x0001)
+		return;
+
+	pci_read_config_dword(bridge, PCI_PREF_MEMORY_BASE, &pmem);
+	if (!pmem) {
+		pci_write_config_dword(bridge, PCI_PREF_MEMORY_BASE,
+					       0xffe0fff0);
+		pci_read_config_dword(bridge, PCI_PREF_MEMORY_BASE, &pmem);
+		pci_write_config_dword(bridge, PCI_PREF_MEMORY_BASE, 0x0);
+	}
+	if (!pmem)
+		return;
+
+	bridge->pref_window = 1;
+
+	if ((pmem & PCI_PREF_RANGE_TYPE_MASK) == PCI_PREF_RANGE_TYPE_64) {
+
+		/*
+		 * Bridge claims to have a 64-bit prefetchable memory
+		 * window; verify that the upper bits are actually
+		 * writable.
+		 */
+		pci_read_config_dword(bridge, PCI_PREF_BASE_UPPER32, &pmem);
+		pci_write_config_dword(bridge, PCI_PREF_BASE_UPPER32,
+				       0xffffffff);
+		pci_read_config_dword(bridge, PCI_PREF_BASE_UPPER32, &tmp);
+		pci_write_config_dword(bridge, PCI_PREF_BASE_UPPER32, pmem);
+		if (tmp)
+			bridge->pref_64_window = 1;
+	}
+
+	pci_read_bridge_mmio_pref(bridge, &res, true);
+}
+
 void pci_read_bridge_bases(struct pci_bus *child)
 {
 	struct pci_dev *dev = child->self;
@@ -527,9 +539,9 @@ void pci_read_bridge_bases(struct pci_bus *child)
 	for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++)
 		child->resource[i] = &dev->resource[PCI_BRIDGE_RESOURCES+i];
 
-	pci_read_bridge_io(child);
-	pci_read_bridge_mmio(child);
-	pci_read_bridge_mmio_pref(child);
+	pci_read_bridge_io(child->self, child->resource[0], false);
+	pci_read_bridge_mmio(child->self, child->resource[1], false);
+	pci_read_bridge_mmio_pref(child->self, child->resource[2], false);
 
 	if (dev->transparent) {
 		pci_bus_for_each_resource(child->parent, res) {
@@ -1817,6 +1829,43 @@ static void early_dump_pci_device(struct pci_dev *pdev)
 		       value, 256, false);
 }
 
+static const char *pci_type_str(struct pci_dev *dev)
+{
+	static const char * const str[] = {
+		"PCIe Endpoint",
+		"PCIe Legacy Endpoint",
+		"PCIe unknown",
+		"PCIe unknown",
+		"PCIe Root Port",
+		"PCIe Switch Upstream Port",
+		"PCIe Switch Downstream Port",
+		"PCIe to PCI/PCI-X bridge",
+		"PCI/PCI-X to PCIe bridge",
+		"PCIe Root Complex Integrated Endpoint",
+		"PCIe Root Complex Event Collector",
+	};
+	int type;
+
+	if (pci_is_pcie(dev)) {
+		type = pci_pcie_type(dev);
+		if (type < ARRAY_SIZE(str))
+			return str[type];
+
+		return "PCIe unknown";
+	}
+
+	switch (dev->hdr_type) {
+	case PCI_HEADER_TYPE_NORMAL:
+		return "conventional PCI endpoint";
+	case PCI_HEADER_TYPE_BRIDGE:
+		return "conventional PCI bridge";
+	case PCI_HEADER_TYPE_CARDBUS:
+		return "CardBus bridge";
+	default:
+		return "conventional PCI";
+	}
+}
+
 /**
  * pci_setup_device - Fill in class and map information of a device
  * @dev: the device structure to fill
@@ -1887,8 +1936,9 @@ int pci_setup_device(struct pci_dev *dev)
 
 	pci_set_removable(dev);
 
-	pci_info(dev, "[%04x:%04x] type %02x class %#08x\n",
-		 dev->vendor, dev->device, dev->hdr_type, dev->class);
+	pci_info(dev, "[%04x:%04x] type %02x class %#08x %s\n",
+		 dev->vendor, dev->device, dev->hdr_type, dev->class,
+		 pci_type_str(dev));
 
 	/* Device class may be changed after fixup */
 	class = dev->class >> 8;
@@ -1929,14 +1979,14 @@ int pci_setup_device(struct pci_dev *dev)
 				res = &dev->resource[0];
 				res->flags = LEGACY_IO_RESOURCE;
 				pcibios_bus_to_resource(dev->bus, res, &region);
-				pci_info(dev, "legacy IDE quirk: reg 0x10: %pR\n",
+				pci_info(dev, "BAR 0 %pR: legacy IDE quirk\n",
 					 res);
 				region.start = 0x3F6;
 				region.end = 0x3F6;
 				res = &dev->resource[1];
 				res->flags = LEGACY_IO_RESOURCE;
 				pcibios_bus_to_resource(dev->bus, res, &region);
-				pci_info(dev, "legacy IDE quirk: reg 0x14: %pR\n",
+				pci_info(dev, "BAR 1 %pR: legacy IDE quirk\n",
 					 res);
 			}
 			if ((progif & 4) == 0) {
@@ -1945,14 +1995,14 @@ int pci_setup_device(struct pci_dev *dev)
 				res = &dev->resource[2];
 				res->flags = LEGACY_IO_RESOURCE;
 				pcibios_bus_to_resource(dev->bus, res, &region);
-				pci_info(dev, "legacy IDE quirk: reg 0x18: %pR\n",
+				pci_info(dev, "BAR 2 %pR: legacy IDE quirk\n",
 					 res);
 				region.start = 0x376;
 				region.end = 0x376;
 				res = &dev->resource[3];
 				res->flags = LEGACY_IO_RESOURCE;
 				pcibios_bus_to_resource(dev->bus, res, &region);
-				pci_info(dev, "legacy IDE quirk: reg 0x1c: %pR\n",
+				pci_info(dev, "BAR 3 %pR: legacy IDE quirk\n",
 					 res);
 			}
 		}
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index d208047d1b8f..d797df6e5f3e 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -570,13 +570,14 @@ static void quirk_extend_bar_to_page(struct pci_dev *dev)
 
 	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
 		struct resource *r = &dev->resource[i];
+		const char *r_name = pci_resource_name(dev, i);
 
 		if (r->flags & IORESOURCE_MEM && resource_size(r) < PAGE_SIZE) {
 			r->end = PAGE_SIZE - 1;
 			r->start = 0;
 			r->flags |= IORESOURCE_UNSET;
-			pci_info(dev, "expanded BAR %d to page size: %pR\n",
-				 i, r);
+			pci_info(dev, "%s %pR: expanded to page size\n",
+				 r_name, r);
 		}
 	}
 }
@@ -605,6 +606,7 @@ static void quirk_io(struct pci_dev *dev, int pos, unsigned int size,
 	u32 region;
 	struct pci_bus_region bus_region;
 	struct resource *res = dev->resource + pos;
+	const char *res_name = pci_resource_name(dev, pos);
 
 	pci_read_config_dword(dev, PCI_BASE_ADDRESS_0 + (pos << 2), &region);
 
@@ -622,8 +624,7 @@ static void quirk_io(struct pci_dev *dev, int pos, unsigned int size,
 	bus_region.end = region + size - 1;
 	pcibios_bus_to_resource(dev->bus, res, &bus_region);
 
-	pci_info(dev, FW_BUG "%s quirk: reg 0x%x: %pR\n",
-		 name, PCI_BASE_ADDRESS_0 + (pos << 2), res);
+	pci_info(dev, FW_BUG "%s %pR: %s quirk\n", res_name, res, name);
 }
 
 /*
@@ -670,6 +671,12 @@ static void quirk_io_region(struct pci_dev *dev, int port,
 	bus_region.end = region + size - 1;
 	pcibios_bus_to_resource(dev->bus, res, &bus_region);
 
+	/*
+	 * "res" is typically a bridge window resource that's not being
+	 * used for a bridge window, so it's just a place to stash this
+	 * non-standard resource.  Printing "nr" or pci_resource_name() of
+	 * it doesn't really make sense.
+	 */
 	if (!pci_claim_resource(dev, nr))
 		pci_info(dev, "quirk: %pR claimed by %s\n", res, name);
 }
@@ -702,10 +709,13 @@ static void quirk_amd_dwc_class(struct pci_dev *pdev)
 {
 	u32 class = pdev->class;
 
-	/* Use "USB Device (not host controller)" class */
-	pdev->class = PCI_CLASS_SERIAL_USB_DEVICE;
-	pci_info(pdev, "PCI class overridden (%#08x -> %#08x) so dwc3 driver can claim this instead of xhci\n",
-		 class, pdev->class);
+	if (class != PCI_CLASS_SERIAL_USB_DEVICE) {
+		/* Use "USB Device (not host controller)" class */
+		pdev->class = PCI_CLASS_SERIAL_USB_DEVICE;
+		pci_info(pdev,
+			"PCI class overridden (%#08x -> %#08x) so dwc3 driver can claim this instead of xhci\n",
+			class, pdev->class);
+	}
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_NL_USB,
 		quirk_amd_dwc_class);
@@ -4712,17 +4722,21 @@ static int pci_quirk_xgene_acs(struct pci_dev *dev, u16 acs_flags)
  * But the implementation could block peer-to-peer transactions between them
  * and provide ACS-like functionality.
  */
-static int  pci_quirk_zhaoxin_pcie_ports_acs(struct pci_dev *dev, u16 acs_flags)
+static int pci_quirk_zhaoxin_pcie_ports_acs(struct pci_dev *dev, u16 acs_flags)
 {
 	if (!pci_is_pcie(dev) ||
 	    ((pci_pcie_type(dev) != PCI_EXP_TYPE_ROOT_PORT) &&
 	     (pci_pcie_type(dev) != PCI_EXP_TYPE_DOWNSTREAM)))
 		return -ENOTTY;
 
+	/*
+	 * Future Zhaoxin Root Ports and Switch Downstream Ports will
+	 * implement ACS capability in accordance with the PCIe Spec.
+	 */
 	switch (dev->device) {
 	case 0x0710 ... 0x071e:
 	case 0x0721:
-	case 0x0723 ... 0x0732:
+	case 0x0723 ... 0x0752:
 		return pci_acs_ctrl_enabled(acs_flags,
 			PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
 	}
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index fd74f1c99dba..909e6a7c3cc3 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -213,6 +213,7 @@ static void reassign_resources_sorted(struct list_head *realloc_head,
 				      struct list_head *head)
 {
 	struct resource *res;
+	const char *res_name;
 	struct pci_dev_resource *add_res, *tmp;
 	struct pci_dev_resource *dev_res;
 	resource_size_t add_size, align;
@@ -222,6 +223,7 @@ static void reassign_resources_sorted(struct list_head *realloc_head,
 		bool found_match = false;
 
 		res = add_res->res;
+
 		/* Skip resource that has been reset */
 		if (!res->flags)
 			goto out;
@@ -237,6 +239,7 @@ static void reassign_resources_sorted(struct list_head *realloc_head,
 			continue;
 
 		idx = res - &add_res->dev->resource[0];
+		res_name = pci_resource_name(add_res->dev, idx);
 		add_size = add_res->add_size;
 		align = add_res->min_align;
 		if (!resource_size(res)) {
@@ -249,9 +252,9 @@ static void reassign_resources_sorted(struct list_head *realloc_head,
 				 (IORESOURCE_STARTALIGN|IORESOURCE_SIZEALIGN);
 			if (pci_reassign_resource(add_res->dev, idx,
 						  add_size, align))
-				pci_info(add_res->dev, "failed to add %llx res[%d]=%pR\n",
-					 (unsigned long long) add_size, idx,
-					 res);
+				pci_info(add_res->dev, "%s %pR: failed to add %llx\n",
+					 res_name, res,
+					 (unsigned long long) add_size);
 		}
 out:
 		list_del(&add_res->list);
@@ -571,6 +574,7 @@ EXPORT_SYMBOL(pci_setup_cardbus);
 static void pci_setup_bridge_io(struct pci_dev *bridge)
 {
 	struct resource *res;
+	const char *res_name;
 	struct pci_bus_region region;
 	unsigned long io_mask;
 	u8 io_base_lo, io_limit_lo;
@@ -583,6 +587,7 @@ static void pci_setup_bridge_io(struct pci_dev *bridge)
 
 	/* Set up the top and bottom of the PCI I/O segment for this bus */
 	res = &bridge->resource[PCI_BRIDGE_IO_WINDOW];
+	res_name = pci_resource_name(bridge, PCI_BRIDGE_IO_WINDOW);
 	pcibios_resource_to_bus(bridge->bus, &region, res);
 	if (res->flags & IORESOURCE_IO) {
 		pci_read_config_word(bridge, PCI_IO_BASE, &l);
@@ -591,7 +596,7 @@ static void pci_setup_bridge_io(struct pci_dev *bridge)
 		l = ((u16) io_limit_lo << 8) | io_base_lo;
 		/* Set up upper 16 bits of I/O base/limit */
 		io_upper16 = (region.end & 0xffff0000) | (region.start >> 16);
-		pci_info(bridge, "  bridge window %pR\n", res);
+		pci_info(bridge, "  %s %pR\n", res_name, res);
 	} else {
 		/* Clear upper 16 bits of I/O base/limit */
 		io_upper16 = 0;
@@ -608,16 +613,18 @@ static void pci_setup_bridge_io(struct pci_dev *bridge)
 static void pci_setup_bridge_mmio(struct pci_dev *bridge)
 {
 	struct resource *res;
+	const char *res_name;
 	struct pci_bus_region region;
 	u32 l;
 
 	/* Set up the top and bottom of the PCI Memory segment for this bus */
 	res = &bridge->resource[PCI_BRIDGE_MEM_WINDOW];
+	res_name = pci_resource_name(bridge, PCI_BRIDGE_MEM_WINDOW);
 	pcibios_resource_to_bus(bridge->bus, &region, res);
 	if (res->flags & IORESOURCE_MEM) {
 		l = (region.start >> 16) & 0xfff0;
 		l |= region.end & 0xfff00000;
-		pci_info(bridge, "  bridge window %pR\n", res);
+		pci_info(bridge, "  %s %pR\n", res_name, res);
 	} else {
 		l = 0x0000fff0;
 	}
@@ -627,6 +634,7 @@ static void pci_setup_bridge_mmio(struct pci_dev *bridge)
 static void pci_setup_bridge_mmio_pref(struct pci_dev *bridge)
 {
 	struct resource *res;
+	const char *res_name;
 	struct pci_bus_region region;
 	u32 l, bu, lu;
 
@@ -640,6 +648,7 @@ static void pci_setup_bridge_mmio_pref(struct pci_dev *bridge)
 	/* Set up PREF base/limit */
 	bu = lu = 0;
 	res = &bridge->resource[PCI_BRIDGE_PREF_MEM_WINDOW];
+	res_name = pci_resource_name(bridge, PCI_BRIDGE_PREF_MEM_WINDOW);
 	pcibios_resource_to_bus(bridge->bus, &region, res);
 	if (res->flags & IORESOURCE_PREFETCH) {
 		l = (region.start >> 16) & 0xfff0;
@@ -648,7 +657,7 @@ static void pci_setup_bridge_mmio_pref(struct pci_dev *bridge)
 			bu = upper_32_bits(region.start);
 			lu = upper_32_bits(region.end);
 		}
-		pci_info(bridge, "  bridge window %pR\n", res);
+		pci_info(bridge, "  %s %pR\n", res_name, res);
 	} else {
 		l = 0x0000fff0;
 	}
@@ -1013,6 +1022,7 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
 		int i;
 
 		pci_dev_for_each_resource(dev, r, i) {
+			const char *r_name = pci_resource_name(dev, i);
 			resource_size_t r_size;
 
 			if (r->parent || (r->flags & IORESOURCE_PCI_FIXED) ||
@@ -1043,8 +1053,8 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
 			if (order < 0)
 				order = 0;
 			if (order >= ARRAY_SIZE(aligns)) {
-				pci_warn(dev, "disabling BAR %d: %pR (bad alignment %#llx)\n",
-					 i, r, (unsigned long long) align);
+				pci_warn(dev, "%s %pR: disabling; bad alignment %#llx\n",
+					 r_name, r, (unsigned long long) align);
 				r->flags = 0;
 				continue;
 			}
@@ -2235,6 +2245,7 @@ int pci_reassign_bridge_resources(struct pci_dev *bridge, unsigned long type)
 		for (i = PCI_BRIDGE_RESOURCES; i < PCI_BRIDGE_RESOURCE_END;
 		     i++) {
 			struct resource *res = &bridge->resource[i];
+			const char *res_name = pci_resource_name(bridge, i);
 
 			if ((res->flags ^ type) & PCI_RES_TYPE_MASK)
 				continue;
@@ -2247,8 +2258,7 @@ int pci_reassign_bridge_resources(struct pci_dev *bridge, unsigned long type)
 			if (ret)
 				goto cleanup;
 
-			pci_info(bridge, "BAR %d: releasing %pR\n",
-				 i, res);
+			pci_info(bridge, "%s %pR: releasing\n", res_name, res);
 
 			if (res->parent)
 				release_resource(res);
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index ceaa69491f5e..c6d933ddfd46 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -30,6 +30,7 @@ static void pci_std_update_resource(struct pci_dev *dev, int resno)
 	u32 new, check, mask;
 	int reg;
 	struct resource *res = dev->resource + resno;
+	const char *res_name = pci_resource_name(dev, resno);
 
 	/* Per SR-IOV spec 3.4.1.11, VF BARs are RO zero */
 	if (dev->is_virtfn)
@@ -104,8 +105,8 @@ static void pci_std_update_resource(struct pci_dev *dev, int resno)
 	pci_read_config_dword(dev, reg, &check);
 
 	if ((new ^ check) & mask) {
-		pci_err(dev, "BAR %d: error updating (%#010x != %#010x)\n",
-			resno, new, check);
+		pci_err(dev, "%s: error updating (%#010x != %#010x)\n",
+			res_name, new, check);
 	}
 
 	if (res->flags & IORESOURCE_MEM_64) {
@@ -113,8 +114,8 @@ static void pci_std_update_resource(struct pci_dev *dev, int resno)
 		pci_write_config_dword(dev, reg + 4, new);
 		pci_read_config_dword(dev, reg + 4, &check);
 		if (check != new) {
-			pci_err(dev, "BAR %d: error updating (high %#010x != %#010x)\n",
-				resno, new, check);
+			pci_err(dev, "%s: error updating (high %#010x != %#010x)\n",
+				res_name, new, check);
 		}
 	}
 
@@ -135,11 +136,12 @@ void pci_update_resource(struct pci_dev *dev, int resno)
 int pci_claim_resource(struct pci_dev *dev, int resource)
 {
 	struct resource *res = &dev->resource[resource];
+	const char *res_name = pci_resource_name(dev, resource);
 	struct resource *root, *conflict;
 
 	if (res->flags & IORESOURCE_UNSET) {
-		pci_info(dev, "can't claim BAR %d %pR: no address assigned\n",
-			 resource, res);
+		pci_info(dev, "%s %pR: can't claim; no address assigned\n",
+			 res_name, res);
 		return -EINVAL;
 	}
 
@@ -153,16 +155,16 @@ int pci_claim_resource(struct pci_dev *dev, int resource)
 
 	root = pci_find_parent_resource(dev, res);
 	if (!root) {
-		pci_info(dev, "can't claim BAR %d %pR: no compatible bridge window\n",
-			 resource, res);
+		pci_info(dev, "%s %pR: can't claim; no compatible bridge window\n",
+			 res_name, res);
 		res->flags |= IORESOURCE_UNSET;
 		return -EINVAL;
 	}
 
 	conflict = request_resource_conflict(root, res);
 	if (conflict) {
-		pci_info(dev, "can't claim BAR %d %pR: address conflict with %s %pR\n",
-			 resource, res, conflict->name, conflict);
+		pci_info(dev, "%s %pR: can't claim; address conflict with %s %pR\n",
+			 res_name, res, conflict->name, conflict);
 		res->flags |= IORESOURCE_UNSET;
 		return -EBUSY;
 	}
@@ -201,6 +203,7 @@ static int pci_revert_fw_address(struct resource *res, struct pci_dev *dev,
 {
 	struct resource *root, *conflict;
 	resource_size_t fw_addr, start, end;
+	const char *res_name = pci_resource_name(dev, resno);
 
 	fw_addr = pcibios_retrieve_fw_addr(dev, resno);
 	if (!fw_addr)
@@ -231,12 +234,11 @@ static int pci_revert_fw_address(struct resource *res, struct pci_dev *dev,
 			root = &iomem_resource;
 	}
 
-	pci_info(dev, "BAR %d: trying firmware assignment %pR\n",
-		 resno, res);
+	pci_info(dev, "%s: trying firmware assignment %pR\n", res_name, res);
 	conflict = request_resource_conflict(root, res);
 	if (conflict) {
-		pci_info(dev, "BAR %d: %pR conflicts with %s %pR\n",
-			 resno, res, conflict->name, conflict);
+		pci_info(dev, "%s %pR: conflicts with %s %pR\n", res_name, res,
+			 conflict->name, conflict);
 		res->start = start;
 		res->end = end;
 		res->flags |= IORESOURCE_UNSET;
@@ -325,6 +327,7 @@ static int _pci_assign_resource(struct pci_dev *dev, int resno,
 int pci_assign_resource(struct pci_dev *dev, int resno)
 {
 	struct resource *res = dev->resource + resno;
+	const char *res_name = pci_resource_name(dev, resno);
 	resource_size_t align, size;
 	int ret;
 
@@ -334,8 +337,8 @@ int pci_assign_resource(struct pci_dev *dev, int resno)
 	res->flags |= IORESOURCE_UNSET;
 	align = pci_resource_alignment(dev, res);
 	if (!align) {
-		pci_info(dev, "BAR %d: can't assign %pR (bogus alignment)\n",
-			 resno, res);
+		pci_info(dev, "%s %pR: can't assign; bogus alignment\n",
+			 res_name, res);
 		return -EINVAL;
 	}
 
@@ -348,18 +351,18 @@ int pci_assign_resource(struct pci_dev *dev, int resno)
 	 * working, which is better than just leaving it disabled.
 	 */
 	if (ret < 0) {
-		pci_info(dev, "BAR %d: no space for %pR\n", resno, res);
+		pci_info(dev, "%s %pR: can't assign; no space\n", res_name, res);
 		ret = pci_revert_fw_address(res, dev, resno, size);
 	}
 
 	if (ret < 0) {
-		pci_info(dev, "BAR %d: failed to assign %pR\n", resno, res);
+		pci_info(dev, "%s %pR: failed to assign\n", res_name, res);
 		return ret;
 	}
 
 	res->flags &= ~IORESOURCE_UNSET;
 	res->flags &= ~IORESOURCE_STARTALIGN;
-	pci_info(dev, "BAR %d: assigned %pR\n", resno, res);
+	pci_info(dev, "%s %pR: assigned\n", res_name, res);
 	if (resno < PCI_BRIDGE_RESOURCES)
 		pci_update_resource(dev, resno);
 
@@ -367,10 +370,11 @@ int pci_assign_resource(struct pci_dev *dev, int resno)
 }
 EXPORT_SYMBOL(pci_assign_resource);
 
-int pci_reassign_resource(struct pci_dev *dev, int resno, resource_size_t addsize,
-			resource_size_t min_align)
+int pci_reassign_resource(struct pci_dev *dev, int resno,
+			  resource_size_t addsize, resource_size_t min_align)
 {
 	struct resource *res = dev->resource + resno;
+	const char *res_name = pci_resource_name(dev, resno);
 	unsigned long flags;
 	resource_size_t new_size;
 	int ret;
@@ -381,8 +385,8 @@ int pci_reassign_resource(struct pci_dev *dev, int resno, resource_size_t addsiz
 	flags = res->flags;
 	res->flags |= IORESOURCE_UNSET;
 	if (!res->parent) {
-		pci_info(dev, "BAR %d: can't reassign an unassigned resource %pR\n",
-			 resno, res);
+		pci_info(dev, "%s %pR: can't reassign; unassigned resource\n",
+			 res_name, res);
 		return -EINVAL;
 	}
 
@@ -391,15 +395,15 @@ int pci_reassign_resource(struct pci_dev *dev, int resno, resource_size_t addsiz
 	ret = _pci_assign_resource(dev, resno, new_size, min_align);
 	if (ret) {
 		res->flags = flags;
-		pci_info(dev, "BAR %d: %pR (failed to expand by %#llx)\n",
-			 resno, res, (unsigned long long) addsize);
+		pci_info(dev, "%s %pR: failed to expand by %#llx\n",
+			 res_name, res, (unsigned long long) addsize);
 		return ret;
 	}
 
 	res->flags &= ~IORESOURCE_UNSET;
 	res->flags &= ~IORESOURCE_STARTALIGN;
-	pci_info(dev, "BAR %d: reassigned %pR (expanded by %#llx)\n",
-		 resno, res, (unsigned long long) addsize);
+	pci_info(dev, "%s %pR: reassigned; expanded by %#llx\n",
+		 res_name, res, (unsigned long long) addsize);
 	if (resno < PCI_BRIDGE_RESOURCES)
 		pci_update_resource(dev, resno);
 
@@ -409,8 +413,9 @@ int pci_reassign_resource(struct pci_dev *dev, int resno, resource_size_t addsiz
 void pci_release_resource(struct pci_dev *dev, int resno)
 {
 	struct resource *res = dev->resource + resno;
+	const char *res_name = pci_resource_name(dev, resno);
 
-	pci_info(dev, "BAR %d: releasing %pR\n", resno, res);
+	pci_info(dev, "%s %pR: releasing\n", res_name, res);
 
 	if (!res->parent)
 		return;
@@ -480,6 +485,7 @@ int pci_enable_resources(struct pci_dev *dev, int mask)
 	u16 cmd, old_cmd;
 	int i;
 	struct resource *r;
+	const char *r_name;
 
 	pci_read_config_word(dev, PCI_COMMAND, &cmd);
 	old_cmd = cmd;
@@ -488,6 +494,8 @@ int pci_enable_resources(struct pci_dev *dev, int mask)
 		if (!(mask & (1 << i)))
 			continue;
 
+		r_name = pci_resource_name(dev, i);
+
 		if (!(r->flags & (IORESOURCE_IO | IORESOURCE_MEM)))
 			continue;
 		if ((i == PCI_ROM_RESOURCE) &&
@@ -495,14 +503,14 @@ int pci_enable_resources(struct pci_dev *dev, int mask)
 			continue;
 
 		if (r->flags & IORESOURCE_UNSET) {
-			pci_err(dev, "can't enable device: BAR %d %pR not assigned\n",
-				i, r);
+			pci_err(dev, "%s %pR: not assigned; can't enable device\n",
+				r_name, r);
 			return -EINVAL;
 		}
 
 		if (!r->parent) {
-			pci_err(dev, "can't enable device: BAR %d %pR not claimed\n",
-				i, r);
+			pci_err(dev, "%s %pR: not claimed; can't enable device\n",
+				r_name, r);
 			return -EINVAL;
 		}
 
diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c
index 5b921387eca6..1804794d0e68 100644
--- a/drivers/pci/switch/switchtec.c
+++ b/drivers/pci/switch/switchtec.c
@@ -1308,13 +1308,6 @@ static void stdev_release(struct device *dev)
 {
 	struct switchtec_dev *stdev = to_stdev(dev);
 
-	if (stdev->dma_mrpc) {
-		iowrite32(0, &stdev->mmio_mrpc->dma_en);
-		flush_wc_buf(stdev);
-		writeq(0, &stdev->mmio_mrpc->dma_addr);
-		dma_free_coherent(&stdev->pdev->dev, sizeof(*stdev->dma_mrpc),
-				stdev->dma_mrpc, stdev->dma_mrpc_dma_addr);
-	}
 	kfree(stdev);
 }
 
@@ -1358,7 +1351,7 @@ static struct switchtec_dev *stdev_create(struct pci_dev *pdev)
 		return ERR_PTR(-ENOMEM);
 
 	stdev->alive = true;
-	stdev->pdev = pdev;
+	stdev->pdev = pci_dev_get(pdev);
 	INIT_LIST_HEAD(&stdev->mrpc_queue);
 	mutex_init(&stdev->mrpc_mutex);
 	stdev->mrpc_busy = 0;
@@ -1391,6 +1384,7 @@ static struct switchtec_dev *stdev_create(struct pci_dev *pdev)
 	return stdev;
 
 err_put:
+	pci_dev_put(stdev->pdev);
 	put_device(&stdev->dev);
 	return ERR_PTR(rc);
 }
@@ -1644,6 +1638,18 @@ static int switchtec_init_pci(struct switchtec_dev *stdev,
 	return 0;
 }
 
+static void switchtec_exit_pci(struct switchtec_dev *stdev)
+{
+	if (stdev->dma_mrpc) {
+		iowrite32(0, &stdev->mmio_mrpc->dma_en);
+		flush_wc_buf(stdev);
+		writeq(0, &stdev->mmio_mrpc->dma_addr);
+		dma_free_coherent(&stdev->pdev->dev, sizeof(*stdev->dma_mrpc),
+				  stdev->dma_mrpc, stdev->dma_mrpc_dma_addr);
+		stdev->dma_mrpc = NULL;
+	}
+}
+
 static int switchtec_pci_probe(struct pci_dev *pdev,
 			       const struct pci_device_id *id)
 {
@@ -1703,6 +1709,9 @@ static void switchtec_pci_remove(struct pci_dev *pdev)
 	ida_free(&switchtec_minor_ida, MINOR(stdev->dev.devt));
 	dev_info(&stdev->dev, "unregistered.\n");
 	stdev_kill(stdev);
+	switchtec_exit_pci(stdev);
+	pci_dev_put(stdev->pdev);
+	stdev->pdev = NULL;
 	put_device(&stdev->dev);
 }
 
diff --git a/drivers/pcmcia/bcm63xx_pcmcia.c b/drivers/pcmcia/bcm63xx_pcmcia.c
index dd3c26099048..a5414441834a 100644
--- a/drivers/pcmcia/bcm63xx_pcmcia.c
+++ b/drivers/pcmcia/bcm63xx_pcmcia.c
@@ -437,7 +437,7 @@ err:
 	return ret;
 }
 
-static int bcm63xx_drv_pcmcia_remove(struct platform_device *pdev)
+static void bcm63xx_drv_pcmcia_remove(struct platform_device *pdev)
 {
 	struct bcm63xx_pcmcia_socket *skt;
 	struct resource *res;
@@ -449,12 +449,11 @@ static int bcm63xx_drv_pcmcia_remove(struct platform_device *pdev)
 	res = skt->reg_res;
 	release_mem_region(res->start, resource_size(res));
 	kfree(skt);
-	return 0;
 }
 
 struct platform_driver bcm63xx_pcmcia_driver = {
 	.probe	= bcm63xx_drv_pcmcia_probe,
-	.remove	= bcm63xx_drv_pcmcia_remove,
+	.remove_new = bcm63xx_drv_pcmcia_remove,
 	.driver	= {
 		.name	= "bcm63xx_pcmcia",
 		.owner  = THIS_MODULE,
diff --git a/drivers/pcmcia/db1xxx_ss.c b/drivers/pcmcia/db1xxx_ss.c
index 87a33ecc2cf1..509713b9a502 100644
--- a/drivers/pcmcia/db1xxx_ss.c
+++ b/drivers/pcmcia/db1xxx_ss.c
@@ -577,7 +577,7 @@ out0:
 	return ret;
 }
 
-static int db1x_pcmcia_socket_remove(struct platform_device *pdev)
+static void db1x_pcmcia_socket_remove(struct platform_device *pdev)
 {
 	struct db1x_pcmcia_sock *sock = platform_get_drvdata(pdev);
 
@@ -585,8 +585,6 @@ static int db1x_pcmcia_socket_remove(struct platform_device *pdev)
 	pcmcia_unregister_socket(&sock->socket);
 	iounmap((void *)(sock->virt_io + (u32)mips_io_port_base));
 	kfree(sock);
-
-	return 0;
 }
 
 static struct platform_driver db1x_pcmcia_socket_driver = {
@@ -594,7 +592,7 @@ static struct platform_driver db1x_pcmcia_socket_driver = {
 		.name	= "db1xxx_pcmcia",
 	},
 	.probe		= db1x_pcmcia_socket_probe,
-	.remove		= db1x_pcmcia_socket_remove,
+	.remove_new	= db1x_pcmcia_socket_remove,
 };
 
 module_platform_driver(db1x_pcmcia_socket_driver);
diff --git a/drivers/pcmcia/electra_cf.c b/drivers/pcmcia/electra_cf.c
index efc27bc15152..5ae826e54811 100644
--- a/drivers/pcmcia/electra_cf.c
+++ b/drivers/pcmcia/electra_cf.c
@@ -307,7 +307,7 @@ out_free_cf:
 
 }
 
-static int electra_cf_remove(struct platform_device *ofdev)
+static void electra_cf_remove(struct platform_device *ofdev)
 {
 	struct device *device = &ofdev->dev;
 	struct electra_cf_socket *cf;
@@ -326,8 +326,6 @@ static int electra_cf_remove(struct platform_device *ofdev)
 	release_region(cf->io_base, cf->io_size);
 
 	kfree(cf);
-
-	return 0;
 }
 
 static const struct of_device_id electra_cf_match[] = {
@@ -344,7 +342,7 @@ static struct platform_driver electra_cf_driver = {
 		.of_match_table = electra_cf_match,
 	},
 	.probe	  = electra_cf_probe,
-	.remove   = electra_cf_remove,
+	.remove_new = electra_cf_remove,
 };
 
 module_platform_driver(electra_cf_driver);
diff --git a/drivers/pcmcia/omap_cf.c b/drivers/pcmcia/omap_cf.c
index e613818dc0bc..80137c7afe0d 100644
--- a/drivers/pcmcia/omap_cf.c
+++ b/drivers/pcmcia/omap_cf.c
@@ -290,7 +290,7 @@ fail0:
 	return status;
 }
 
-static int __exit omap_cf_remove(struct platform_device *pdev)
+static void __exit omap_cf_remove(struct platform_device *pdev)
 {
 	struct omap_cf_socket *cf = platform_get_drvdata(pdev);
 
@@ -300,14 +300,13 @@ static int __exit omap_cf_remove(struct platform_device *pdev)
 	release_mem_region(cf->phys_cf, SZ_8K);
 	free_irq(cf->irq, cf);
 	kfree(cf);
-	return 0;
 }
 
 static struct platform_driver omap_cf_driver = {
 	.driver = {
 		.name	= driver_name,
 	},
-	.remove		= __exit_p(omap_cf_remove),
+	.remove_new	= __exit_p(omap_cf_remove),
 };
 
 static int __init omap_cf_init(void)
diff --git a/drivers/pcmcia/pxa2xx_base.c b/drivers/pcmcia/pxa2xx_base.c
index 5254028354f4..457fb81b497a 100644
--- a/drivers/pcmcia/pxa2xx_base.c
+++ b/drivers/pcmcia/pxa2xx_base.c
@@ -313,15 +313,13 @@ err0:
 	return ret;
 }
 
-static int pxa2xx_drv_pcmcia_remove(struct platform_device *dev)
+static void pxa2xx_drv_pcmcia_remove(struct platform_device *dev)
 {
 	struct skt_dev_info *sinfo = platform_get_drvdata(dev);
 	int i;
 
 	for (i = 0; i < sinfo->nskt; i++)
 		soc_pcmcia_remove_one(&sinfo->skt[i]);
-
-	return 0;
 }
 
 static int pxa2xx_drv_pcmcia_resume(struct device *dev)
@@ -338,7 +336,7 @@ static const struct dev_pm_ops pxa2xx_drv_pcmcia_pm_ops = {
 
 static struct platform_driver pxa2xx_pcmcia_driver = {
 	.probe		= pxa2xx_drv_pcmcia_probe,
-	.remove		= pxa2xx_drv_pcmcia_remove,
+	.remove_new	= pxa2xx_drv_pcmcia_remove,
 	.driver		= {
 		.name	= "pxa2xx-pcmcia",
 		.pm	= &pxa2xx_drv_pcmcia_pm_ops,
diff --git a/drivers/pcmcia/sa1100_generic.c b/drivers/pcmcia/sa1100_generic.c
index 89d4ba58c891..ccb219c38761 100644
--- a/drivers/pcmcia/sa1100_generic.c
+++ b/drivers/pcmcia/sa1100_generic.c
@@ -158,20 +158,18 @@ static int sa11x0_drv_pcmcia_probe(struct platform_device *pdev)
 	return sa11xx_drv_pcmcia_add_one(skt);
 }
 
-static int sa11x0_drv_pcmcia_remove(struct platform_device *dev)
+static void sa11x0_drv_pcmcia_remove(struct platform_device *dev)
 {
 	struct soc_pcmcia_socket *skt;
 
 	if (dev->id == -1) {
 		sa11x0_drv_pcmcia_legacy_remove(dev);
-		return 0;
+		return;
 	}
 
 	skt = platform_get_drvdata(dev);
 
 	soc_pcmcia_remove_one(skt);
-
-	return 0;
 }
 
 static struct platform_driver sa11x0_pcmcia_driver = {
@@ -179,7 +177,7 @@ static struct platform_driver sa11x0_pcmcia_driver = {
 		.name		= "sa11x0-pcmcia",
 	},
 	.probe		= sa11x0_drv_pcmcia_probe,
-	.remove		= sa11x0_drv_pcmcia_remove,
+	.remove_new	= sa11x0_drv_pcmcia_remove,
 };
 
 /* sa11x0_pcmcia_init()
diff --git a/drivers/pcmcia/xxs1500_ss.c b/drivers/pcmcia/xxs1500_ss.c
index b11c7abb1dc0..2a93fbbd128d 100644
--- a/drivers/pcmcia/xxs1500_ss.c
+++ b/drivers/pcmcia/xxs1500_ss.c
@@ -301,7 +301,7 @@ out0:
 	return ret;
 }
 
-static int xxs1500_pcmcia_remove(struct platform_device *pdev)
+static void xxs1500_pcmcia_remove(struct platform_device *pdev)
 {
 	struct xxs1500_pcmcia_sock *sock = platform_get_drvdata(pdev);
 
@@ -309,8 +309,6 @@ static int xxs1500_pcmcia_remove(struct platform_device *pdev)
 	free_irq(gpio_to_irq(GPIO_CDA), sock);
 	iounmap((void *)(sock->virt_io + (u32)mips_io_port_base));
 	kfree(sock);
-
-	return 0;
 }
 
 static struct platform_driver xxs1500_pcmcia_socket_driver = {
@@ -318,7 +316,7 @@ static struct platform_driver xxs1500_pcmcia_socket_driver = {
 		.name	= "xxs1500_pcmcia",
 	},
 	.probe		= xxs1500_pcmcia_probe,
-	.remove		= xxs1500_pcmcia_remove,
+	.remove_new	= xxs1500_pcmcia_remove,
 };
 
 module_platform_driver(xxs1500_pcmcia_socket_driver);
diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
index c584165b13ba..7e3aa7e2345f 100644
--- a/drivers/perf/arm-cmn.c
+++ b/drivers/perf/arm-cmn.c
@@ -2305,6 +2305,17 @@ static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset)
 				dev_dbg(cmn->dev, "ignoring external node %llx\n", reg);
 				continue;
 			}
+			/*
+			 * AmpereOneX erratum AC04_MESH_1 makes some XPs report a bogus
+			 * child count larger than the number of valid child pointers.
+			 * A child offset of 0 can only occur on CMN-600; otherwise it
+			 * would imply the root node being its own grandchild, which
+			 * we can safely dismiss in general.
+			 */
+			if (reg == 0 && cmn->part != PART_CMN600) {
+				dev_dbg(cmn->dev, "bogus child pointer?\n");
+				continue;
+			}
 
 			arm_cmn_init_node_info(cmn, reg & CMN_CHILD_NODE_ADDR, dn);
 
diff --git a/drivers/perf/cxl_pmu.c b/drivers/perf/cxl_pmu.c
index 365d964b0f6a..308c9969642e 100644
--- a/drivers/perf/cxl_pmu.c
+++ b/drivers/perf/cxl_pmu.c
@@ -59,7 +59,7 @@
 #define   CXL_PMU_COUNTER_CFG_EVENT_GRP_ID_IDX_MSK	GENMASK_ULL(63, 59)
 
 #define CXL_PMU_FILTER_CFG_REG(n, f)	(0x400 + 4 * ((f) + (n) * 8))
-#define   CXL_PMU_FILTER_CFG_VALUE_MSK			GENMASK(15, 0)
+#define   CXL_PMU_FILTER_CFG_VALUE_MSK			GENMASK(31, 0)
 
 #define CXL_PMU_COUNTER_REG(n)		(0xc00 + 8 * (n))
 
@@ -314,9 +314,9 @@ static bool cxl_pmu_config1_get_edge(struct perf_event *event)
 }
 
 /*
- * CPMU specification allows for 8 filters, each with a 16 bit value...
- * So we need to find 8x16bits to store it in.
- * As the value used for disable is 0xffff, a separate enable switch
+ * CPMU specification allows for 8 filters, each with a 32 bit value...
+ * So we need to find 8x32bits to store it in.
+ * As the value used for disable is 0xffff_ffff, a separate enable switch
  * is needed.
  */
 
@@ -419,7 +419,7 @@ static struct attribute *cxl_pmu_event_attrs[] = {
 	CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmp,			CXL_PMU_GID_S2M_NDR, BIT(0)),
 	CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmps,			CXL_PMU_GID_S2M_NDR, BIT(1)),
 	CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmpe,			CXL_PMU_GID_S2M_NDR, BIT(2)),
-	CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_biconflictack,		CXL_PMU_GID_S2M_NDR, BIT(3)),
+	CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_biconflictack,		CXL_PMU_GID_S2M_NDR, BIT(4)),
 	/* CXL rev 3.0 Table 3-46 S2M DRS opcodes */
 	CXL_PMU_EVENT_CXL_ATTR(s2m_drs_memdata,			CXL_PMU_GID_S2M_DRS, BIT(0)),
 	CXL_PMU_EVENT_CXL_ATTR(s2m_drs_memdatanxm,		CXL_PMU_GID_S2M_DRS, BIT(1)),
@@ -642,7 +642,7 @@ static void cxl_pmu_event_start(struct perf_event *event, int flags)
 		if (cxl_pmu_config1_hdm_filter_en(event))
 			cfg = cxl_pmu_config2_get_hdm_decoder(event);
 		else
-			cfg = GENMASK(15, 0); /* No filtering if 0xFFFF_FFFF */
+			cfg = GENMASK(31, 0); /* No filtering if 0xFFFF_FFFF */
 		writeq(cfg, base + CXL_PMU_FILTER_CFG_REG(hwc->idx, 0));
 	}
 
diff --git a/drivers/perf/riscv_pmu.c b/drivers/perf/riscv_pmu.c
index 0dda70e1ef90..c78a6fd6c57f 100644
--- a/drivers/perf/riscv_pmu.c
+++ b/drivers/perf/riscv_pmu.c
@@ -150,19 +150,11 @@ u64 riscv_pmu_ctr_get_width_mask(struct perf_event *event)
 	struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (!rvpmu->ctr_get_width)
-	/**
-	 * If the pmu driver doesn't support counter width, set it to default
-	 * maximum allowed by the specification.
-	 */
-		cwidth = 63;
-	else {
-		if (hwc->idx == -1)
-			/* Handle init case where idx is not initialized yet */
-			cwidth = rvpmu->ctr_get_width(0);
-		else
-			cwidth = rvpmu->ctr_get_width(hwc->idx);
-	}
+	if (hwc->idx == -1)
+		/* Handle init case where idx is not initialized yet */
+		cwidth = rvpmu->ctr_get_width(0);
+	else
+		cwidth = rvpmu->ctr_get_width(hwc->idx);
 
 	return GENMASK_ULL(cwidth, 0);
 }
diff --git a/drivers/perf/riscv_pmu_legacy.c b/drivers/perf/riscv_pmu_legacy.c
index 79fdd667922e..fa0bccf4edf2 100644
--- a/drivers/perf/riscv_pmu_legacy.c
+++ b/drivers/perf/riscv_pmu_legacy.c
@@ -37,6 +37,12 @@ static int pmu_legacy_event_map(struct perf_event *event, u64 *config)
 	return pmu_legacy_ctr_get_idx(event);
 }
 
+/* cycle & instret are always 64 bit, one bit less according to SBI spec */
+static int pmu_legacy_ctr_get_width(int idx)
+{
+	return 63;
+}
+
 static u64 pmu_legacy_read_ctr(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -111,12 +117,14 @@ static void pmu_legacy_init(struct riscv_pmu *pmu)
 	pmu->ctr_stop = NULL;
 	pmu->event_map = pmu_legacy_event_map;
 	pmu->ctr_get_idx = pmu_legacy_ctr_get_idx;
-	pmu->ctr_get_width = NULL;
+	pmu->ctr_get_width = pmu_legacy_ctr_get_width;
 	pmu->ctr_clear_idx = NULL;
 	pmu->ctr_read = pmu_legacy_read_ctr;
 	pmu->event_mapped = pmu_legacy_event_mapped;
 	pmu->event_unmapped = pmu_legacy_event_unmapped;
 	pmu->csr_index = pmu_legacy_csr_index;
+	pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+	pmu->pmu.capabilities |= PERF_PMU_CAP_NO_EXCLUDE;
 
 	perf_pmu_register(&pmu->pmu, "cpu", PERF_TYPE_RAW);
 }
diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
index 16acd4dcdb96..452aab49db1e 100644
--- a/drivers/perf/riscv_pmu_sbi.c
+++ b/drivers/perf/riscv_pmu_sbi.c
@@ -512,7 +512,7 @@ static void pmu_sbi_set_scounteren(void *arg)
 
 	if (event->hw.idx != -1)
 		csr_write(CSR_SCOUNTEREN,
-			  csr_read(CSR_SCOUNTEREN) | (1 << pmu_sbi_csr_index(event)));
+			  csr_read(CSR_SCOUNTEREN) | BIT(pmu_sbi_csr_index(event)));
 }
 
 static void pmu_sbi_reset_scounteren(void *arg)
@@ -521,7 +521,7 @@ static void pmu_sbi_reset_scounteren(void *arg)
 
 	if (event->hw.idx != -1)
 		csr_write(CSR_SCOUNTEREN,
-			  csr_read(CSR_SCOUNTEREN) & ~(1 << pmu_sbi_csr_index(event)));
+			  csr_read(CSR_SCOUNTEREN) & ~BIT(pmu_sbi_csr_index(event)));
 }
 
 static void pmu_sbi_ctr_start(struct perf_event *event, u64 ival)
@@ -731,14 +731,14 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 		/* compute hardware counter index */
 		hidx = info->csr - CSR_CYCLE;
 		/* check if the corresponding bit is set in sscountovf */
-		if (!(overflow & (1 << hidx)))
+		if (!(overflow & BIT(hidx)))
 			continue;
 
 		/*
 		 * Keep a track of overflowed counters so that they can be started
 		 * with updated initial value.
 		 */
-		overflowed_ctrs |= 1 << lidx;
+		overflowed_ctrs |= BIT(lidx);
 		hw_evt = &event->hw;
 		riscv_pmu_event_update(event);
 		perf_sample_data_init(&data, 0, hw_evt->last_period);
diff --git a/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c b/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c
index e625b32889bf..0928a526e2ab 100644
--- a/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c
+++ b/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c
@@ -706,7 +706,7 @@ static int mixel_dphy_probe(struct platform_device *pdev)
 			return ret;
 		}
 
-		priv->id = of_alias_get_id(np, "mipi_dphy");
+		priv->id = of_alias_get_id(np, "mipi-dphy");
 		if (priv->id < 0) {
 			dev_err(dev, "Failed to get phy node alias id: %d\n",
 				priv->id);
diff --git a/drivers/phy/mediatek/phy-mtk-tphy.c b/drivers/phy/mediatek/phy-mtk-tphy.c
index 05eab9014132..a4746f6cb8a1 100644
--- a/drivers/phy/mediatek/phy-mtk-tphy.c
+++ b/drivers/phy/mediatek/phy-mtk-tphy.c
@@ -185,6 +185,10 @@
 #define P3D_RG_CDR_BIR_LTD1		GENMASK(28, 24)
 #define P3D_RG_CDR_BIR_LTD0		GENMASK(12, 8)
 
+#define U3P_U3_PHYD_TOP1		0x100
+#define P3D_RG_PHY_MODE			GENMASK(2, 1)
+#define P3D_RG_FORCE_PHY_MODE		BIT(0)
+
 #define U3P_U3_PHYD_RXDET1		0x128
 #define P3D_RG_RXDET_STB2_SET		GENMASK(17, 9)
 
@@ -327,6 +331,7 @@ struct mtk_phy_instance {
 	int discth;
 	int pre_emphasis;
 	bool bc12_en;
+	bool type_force_mode;
 };
 
 struct mtk_tphy {
@@ -768,6 +773,23 @@ static void u3_phy_instance_init(struct mtk_tphy *tphy,
 	void __iomem *phya = u3_banks->phya;
 	void __iomem *phyd = u3_banks->phyd;
 
+	if (instance->type_force_mode) {
+		/* force phy as usb mode, default is pcie rc mode */
+		mtk_phy_update_field(phyd + U3P_U3_PHYD_TOP1, P3D_RG_PHY_MODE, 1);
+		mtk_phy_set_bits(phyd + U3P_U3_PHYD_TOP1, P3D_RG_FORCE_PHY_MODE);
+		/* power down phy by ip and pipe reset */
+		mtk_phy_set_bits(u3_banks->chip + U3P_U3_CHIP_GPIO_CTLD,
+				 P3C_FORCE_IP_SW_RST | P3C_MCU_BUS_CK_GATE_EN);
+		mtk_phy_set_bits(u3_banks->chip + U3P_U3_CHIP_GPIO_CTLE,
+				 P3C_RG_SWRST_U3_PHYD | P3C_RG_SWRST_U3_PHYD_FORCE_EN);
+		udelay(10);
+		/* power on phy again */
+		mtk_phy_clear_bits(u3_banks->chip + U3P_U3_CHIP_GPIO_CTLD,
+				   P3C_FORCE_IP_SW_RST | P3C_MCU_BUS_CK_GATE_EN);
+		mtk_phy_clear_bits(u3_banks->chip + U3P_U3_CHIP_GPIO_CTLE,
+				   P3C_RG_SWRST_U3_PHYD | P3C_RG_SWRST_U3_PHYD_FORCE_EN);
+	}
+
 	/* gating PCIe Analog XTAL clock */
 	mtk_phy_set_bits(u3_banks->spllc + U3P_SPLLC_XTALCTL3,
 			 XC3_RG_U3_XTAL_RX_PWD | XC3_RG_U3_FRC_XTAL_RX_PWD);
@@ -1120,6 +1142,9 @@ static void phy_parse_property(struct mtk_tphy *tphy,
 {
 	struct device *dev = &instance->phy->dev;
 
+	if (instance->type == PHY_TYPE_USB3)
+		instance->type_force_mode = device_property_read_bool(dev, "mediatek,force-mode");
+
 	if (instance->type != PHY_TYPE_USB2)
 		return;
 
diff --git a/drivers/phy/microchip/lan966x_serdes.c b/drivers/phy/microchip/lan966x_serdes.c
index c1a41b6cd29b..b5ac2b7995e7 100644
--- a/drivers/phy/microchip/lan966x_serdes.c
+++ b/drivers/phy/microchip/lan966x_serdes.c
@@ -96,6 +96,8 @@ static const struct serdes_mux lan966x_serdes_muxes[] = {
 	SERDES_MUX_SGMII(SERDES6G(1), 3, HSIO_HW_CFG_SD6G_1_CFG,
 			 HSIO_HW_CFG_SD6G_1_CFG_SET(1)),
 
+	SERDES_MUX_SGMII(SERDES6G(2), 4, 0, 0),
+
 	SERDES_MUX_RGMII(RGMII(0), 2, HSIO_HW_CFG_RGMII_0_CFG |
 			 HSIO_HW_CFG_RGMII_ENA |
 			 HSIO_HW_CFG_GMII_ENA,
diff --git a/drivers/phy/phy-can-transceiver.c b/drivers/phy/phy-can-transceiver.c
index 840b7f8a31c5..ee4ce4249698 100644
--- a/drivers/phy/phy-can-transceiver.c
+++ b/drivers/phy/phy-can-transceiver.c
@@ -6,11 +6,11 @@
  *
  */
 #include <linux/of.h>
-#include<linux/phy/phy.h>
-#include<linux/platform_device.h>
-#include<linux/module.h>
-#include<linux/gpio.h>
-#include<linux/gpio/consumer.h>
+#include <linux/phy/phy.h>
+#include <linux/platform_device.h>
+#include <linux/module.h>
+#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/mux/consumer.h>
 
 struct can_transceiver_data {
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index 96a0b1e111f3..d9be6a4d5383 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -959,7 +959,7 @@ struct phy *phy_create(struct device *dev, struct device_node *node,
 	if (!phy)
 		return ERR_PTR(-ENOMEM);
 
-	id = ida_simple_get(&phy_ida, 0, 0, GFP_KERNEL);
+	id = ida_alloc(&phy_ida, GFP_KERNEL);
 	if (id < 0) {
 		dev_err(dev, "unable to get id\n");
 		ret = id;
@@ -1232,7 +1232,7 @@ static void phy_release(struct device *dev)
 	dev_vdbg(dev, "releasing '%s'\n", dev_name(dev));
 	debugfs_remove_recursive(phy->debugfs);
 	regulator_put(phy->pwr);
-	ida_simple_remove(&phy_ida, phy->id);
+	ida_free(&phy_ida, phy->id);
 	kfree(phy);
 }
 
diff --git a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c
index a623f092b11f..a43e20abb10d 100644
--- a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c
+++ b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c
@@ -37,56 +37,28 @@
 #define EUSB2_TUNE_EUSB_EQU		0x5A
 #define EUSB2_TUNE_EUSB_HS_COMP_CUR	0x5B
 
-#define QCOM_EUSB2_REPEATER_INIT_CFG(r, v)	\
-	{					\
-		.reg = r,			\
-		.val = v,			\
-	}
-
-enum reg_fields {
-	F_TUNE_EUSB_HS_COMP_CUR,
-	F_TUNE_EUSB_EQU,
-	F_TUNE_EUSB_SLEW,
-	F_TUNE_USB2_HS_COMP_CUR,
-	F_TUNE_USB2_PREEM,
-	F_TUNE_USB2_EQU,
-	F_TUNE_USB2_SLEW,
-	F_TUNE_SQUELCH_U,
-	F_TUNE_HSDISC,
-	F_TUNE_RES_FSDIF,
-	F_TUNE_IUSB2,
-	F_TUNE_USB2_CROSSOVER,
-	F_NUM_TUNE_FIELDS,
-
-	F_FORCE_VAL_5 = F_NUM_TUNE_FIELDS,
-	F_FORCE_EN_5,
-
-	F_EN_CTL1,
-
-	F_RPTR_STATUS,
-	F_NUM_FIELDS,
-};
-
-static struct reg_field eusb2_repeater_tune_reg_fields[F_NUM_FIELDS] = {
-	[F_TUNE_EUSB_HS_COMP_CUR] = REG_FIELD(EUSB2_TUNE_EUSB_HS_COMP_CUR, 0, 1),
-	[F_TUNE_EUSB_EQU] = REG_FIELD(EUSB2_TUNE_EUSB_EQU, 0, 1),
-	[F_TUNE_EUSB_SLEW] = REG_FIELD(EUSB2_TUNE_EUSB_SLEW, 0, 1),
-	[F_TUNE_USB2_HS_COMP_CUR] = REG_FIELD(EUSB2_TUNE_USB2_HS_COMP_CUR, 0, 1),
-	[F_TUNE_USB2_PREEM] = REG_FIELD(EUSB2_TUNE_USB2_PREEM, 0, 2),
-	[F_TUNE_USB2_EQU] = REG_FIELD(EUSB2_TUNE_USB2_EQU, 0, 1),
-	[F_TUNE_USB2_SLEW] = REG_FIELD(EUSB2_TUNE_USB2_SLEW, 0, 1),
-	[F_TUNE_SQUELCH_U] = REG_FIELD(EUSB2_TUNE_SQUELCH_U, 0, 2),
-	[F_TUNE_HSDISC] = REG_FIELD(EUSB2_TUNE_HSDISC, 0, 2),
-	[F_TUNE_RES_FSDIF] = REG_FIELD(EUSB2_TUNE_RES_FSDIF, 0, 2),
-	[F_TUNE_IUSB2] = REG_FIELD(EUSB2_TUNE_IUSB2, 0, 3),
-	[F_TUNE_USB2_CROSSOVER] = REG_FIELD(EUSB2_TUNE_USB2_CROSSOVER, 0, 2),
-
-	[F_FORCE_VAL_5] = REG_FIELD(EUSB2_FORCE_VAL_5, 0, 7),
-	[F_FORCE_EN_5] = REG_FIELD(EUSB2_FORCE_EN_5, 0, 7),
-
-	[F_EN_CTL1] = REG_FIELD(EUSB2_EN_CTL1, 0, 7),
-
-	[F_RPTR_STATUS] = REG_FIELD(EUSB2_RPTR_STATUS, 0, 7),
+enum eusb2_reg_layout {
+	TUNE_EUSB_HS_COMP_CUR,
+	TUNE_EUSB_EQU,
+	TUNE_EUSB_SLEW,
+	TUNE_USB2_HS_COMP_CUR,
+	TUNE_USB2_PREEM,
+	TUNE_USB2_EQU,
+	TUNE_USB2_SLEW,
+	TUNE_SQUELCH_U,
+	TUNE_HSDISC,
+	TUNE_RES_FSDIF,
+	TUNE_IUSB2,
+	TUNE_USB2_CROSSOVER,
+	NUM_TUNE_FIELDS,
+
+	FORCE_VAL_5 = NUM_TUNE_FIELDS,
+	FORCE_EN_5,
+
+	EN_CTL1,
+
+	RPTR_STATUS,
+	LAYOUT_SIZE,
 };
 
 struct eusb2_repeater_cfg {
@@ -98,10 +70,11 @@ struct eusb2_repeater_cfg {
 
 struct eusb2_repeater {
 	struct device *dev;
-	struct regmap_field *regs[F_NUM_FIELDS];
+	struct regmap *regmap;
 	struct phy *phy;
 	struct regulator_bulk_data *vregs;
 	const struct eusb2_repeater_cfg *cfg;
+	u32 base;
 	enum phy_mode mode;
 };
 
@@ -109,10 +82,10 @@ static const char * const pm8550b_vreg_l[] = {
 	"vdd18", "vdd3",
 };
 
-static const u32 pm8550b_init_tbl[F_NUM_TUNE_FIELDS] = {
-	[F_TUNE_IUSB2] = 0x8,
-	[F_TUNE_SQUELCH_U] = 0x3,
-	[F_TUNE_USB2_PREEM] = 0x5,
+static const u32 pm8550b_init_tbl[NUM_TUNE_FIELDS] = {
+	[TUNE_IUSB2] = 0x8,
+	[TUNE_SQUELCH_U] = 0x3,
+	[TUNE_USB2_PREEM] = 0x5,
 };
 
 static const struct eusb2_repeater_cfg pm8550b_eusb2_cfg = {
@@ -140,47 +113,42 @@ static int eusb2_repeater_init_vregs(struct eusb2_repeater *rptr)
 
 static int eusb2_repeater_init(struct phy *phy)
 {
-	struct reg_field *regfields = eusb2_repeater_tune_reg_fields;
 	struct eusb2_repeater *rptr = phy_get_drvdata(phy);
 	struct device_node *np = rptr->dev->of_node;
-	u32 init_tbl[F_NUM_TUNE_FIELDS] = { 0 };
-	u8 override;
+	struct regmap *regmap = rptr->regmap;
+	const u32 *init_tbl = rptr->cfg->init_tbl;
+	u8 tune_usb2_preem = init_tbl[TUNE_USB2_PREEM];
+	u8 tune_hsdisc = init_tbl[TUNE_HSDISC];
+	u8 tune_iusb2 = init_tbl[TUNE_IUSB2];
+	u32 base = rptr->base;
 	u32 val;
 	int ret;
-	int i;
+
+	of_property_read_u8(np, "qcom,tune-usb2-amplitude", &tune_iusb2);
+	of_property_read_u8(np, "qcom,tune-usb2-disc-thres", &tune_hsdisc);
+	of_property_read_u8(np, "qcom,tune-usb2-preem", &tune_usb2_preem);
 
 	ret = regulator_bulk_enable(rptr->cfg->num_vregs, rptr->vregs);
 	if (ret)
 		return ret;
 
-	regmap_field_update_bits(rptr->regs[F_EN_CTL1], EUSB2_RPTR_EN, EUSB2_RPTR_EN);
+	regmap_write(regmap, base + EUSB2_EN_CTL1, EUSB2_RPTR_EN);
 
-	for (i = 0; i < F_NUM_TUNE_FIELDS; i++) {
-		if (init_tbl[i]) {
-			regmap_field_update_bits(rptr->regs[i], init_tbl[i], init_tbl[i]);
-		} else {
-			/* Write 0 if there's no value set */
-			u32 mask = GENMASK(regfields[i].msb, regfields[i].lsb);
-
-			regmap_field_update_bits(rptr->regs[i], mask, 0);
-		}
-	}
-	memcpy(init_tbl, rptr->cfg->init_tbl, sizeof(init_tbl));
+	regmap_write(regmap, base + EUSB2_TUNE_EUSB_HS_COMP_CUR, init_tbl[TUNE_EUSB_HS_COMP_CUR]);
+	regmap_write(regmap, base + EUSB2_TUNE_EUSB_EQU, init_tbl[TUNE_EUSB_EQU]);
+	regmap_write(regmap, base + EUSB2_TUNE_EUSB_SLEW, init_tbl[TUNE_EUSB_SLEW]);
+	regmap_write(regmap, base + EUSB2_TUNE_USB2_HS_COMP_CUR, init_tbl[TUNE_USB2_HS_COMP_CUR]);
+	regmap_write(regmap, base + EUSB2_TUNE_USB2_EQU, init_tbl[TUNE_USB2_EQU]);
+	regmap_write(regmap, base + EUSB2_TUNE_USB2_SLEW, init_tbl[TUNE_USB2_SLEW]);
+	regmap_write(regmap, base + EUSB2_TUNE_SQUELCH_U, init_tbl[TUNE_SQUELCH_U]);
+	regmap_write(regmap, base + EUSB2_TUNE_RES_FSDIF, init_tbl[TUNE_RES_FSDIF]);
+	regmap_write(regmap, base + EUSB2_TUNE_USB2_CROSSOVER, init_tbl[TUNE_USB2_CROSSOVER]);
 
-	if (!of_property_read_u8(np, "qcom,tune-usb2-amplitude", &override))
-		init_tbl[F_TUNE_IUSB2] = override;
+	regmap_write(regmap, base + EUSB2_TUNE_USB2_PREEM, tune_usb2_preem);
+	regmap_write(regmap, base + EUSB2_TUNE_HSDISC, tune_hsdisc);
+	regmap_write(regmap, base + EUSB2_TUNE_IUSB2, tune_iusb2);
 
-	if (!of_property_read_u8(np, "qcom,tune-usb2-disc-thres", &override))
-		init_tbl[F_TUNE_HSDISC] = override;
-
-	if (!of_property_read_u8(np, "qcom,tune-usb2-preem", &override))
-		init_tbl[F_TUNE_USB2_PREEM] = override;
-
-	for (i = 0; i < F_NUM_TUNE_FIELDS; i++)
-		regmap_field_update_bits(rptr->regs[i], init_tbl[i], init_tbl[i]);
-
-	ret = regmap_field_read_poll_timeout(rptr->regs[F_RPTR_STATUS],
-					     val, val & RPTR_OK, 10, 5);
+	ret = regmap_read_poll_timeout(regmap, base + EUSB2_RPTR_STATUS, val, val & RPTR_OK, 10, 5);
 	if (ret)
 		dev_err(rptr->dev, "initialization timed-out\n");
 
@@ -191,6 +159,8 @@ static int eusb2_repeater_set_mode(struct phy *phy,
 				   enum phy_mode mode, int submode)
 {
 	struct eusb2_repeater *rptr = phy_get_drvdata(phy);
+	struct regmap *regmap = rptr->regmap;
+	u32 base = rptr->base;
 
 	switch (mode) {
 	case PHY_MODE_USB_HOST:
@@ -199,10 +169,8 @@ static int eusb2_repeater_set_mode(struct phy *phy,
 		 * per eUSB 1.2 Spec. Below implement software workaround until
 		 * PHY and controller is fixing seen observation.
 		 */
-		regmap_field_update_bits(rptr->regs[F_FORCE_EN_5],
-					 F_CLK_19P2M_EN, F_CLK_19P2M_EN);
-		regmap_field_update_bits(rptr->regs[F_FORCE_VAL_5],
-					 V_CLK_19P2M_EN, V_CLK_19P2M_EN);
+		regmap_write(regmap, base + EUSB2_FORCE_EN_5, F_CLK_19P2M_EN);
+		regmap_write(regmap, base + EUSB2_FORCE_VAL_5, V_CLK_19P2M_EN);
 		break;
 	case PHY_MODE_USB_DEVICE:
 		/*
@@ -211,10 +179,8 @@ static int eusb2_repeater_set_mode(struct phy *phy,
 		 * repeater doesn't clear previous value due to shared
 		 * regulators (say host <-> device mode switch).
 		 */
-		regmap_field_update_bits(rptr->regs[F_FORCE_EN_5],
-					 F_CLK_19P2M_EN, 0);
-		regmap_field_update_bits(rptr->regs[F_FORCE_VAL_5],
-					 V_CLK_19P2M_EN, 0);
+		regmap_write(regmap, base + EUSB2_FORCE_EN_5, 0);
+		regmap_write(regmap, base + EUSB2_FORCE_VAL_5, 0);
 		break;
 	default:
 		return -EINVAL;
@@ -243,9 +209,8 @@ static int eusb2_repeater_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct phy_provider *phy_provider;
 	struct device_node *np = dev->of_node;
-	struct regmap *regmap;
-	int i, ret;
 	u32 res;
+	int ret;
 
 	rptr = devm_kzalloc(dev, sizeof(*rptr), GFP_KERNEL);
 	if (!rptr)
@@ -258,22 +223,15 @@ static int eusb2_repeater_probe(struct platform_device *pdev)
 	if (!rptr->cfg)
 		return -EINVAL;
 
-	regmap = dev_get_regmap(dev->parent, NULL);
-	if (!regmap)
+	rptr->regmap = dev_get_regmap(dev->parent, NULL);
+	if (!rptr->regmap)
 		return -ENODEV;
 
 	ret = of_property_read_u32(np, "reg", &res);
 	if (ret < 0)
 		return ret;
 
-	for (i = 0; i < F_NUM_FIELDS; i++)
-		eusb2_repeater_tune_reg_fields[i].reg += res;
-
-	ret = devm_regmap_field_bulk_alloc(dev, regmap, rptr->regs,
-					   eusb2_repeater_tune_reg_fields,
-					   F_NUM_FIELDS);
-	if (ret)
-		return ret;
+	rptr->base = res;
 
 	ret = eusb2_repeater_init_vregs(rptr);
 	if (ret < 0) {
diff --git a/drivers/phy/qualcomm/phy-qcom-m31.c b/drivers/phy/qualcomm/phy-qcom-m31.c
index c2590579190a..03fb0d4b75d7 100644
--- a/drivers/phy/qualcomm/phy-qcom-m31.c
+++ b/drivers/phy/qualcomm/phy-qcom-m31.c
@@ -299,7 +299,7 @@ static int m31usb_phy_probe(struct platform_device *pdev)
 
 	qphy->vreg = devm_regulator_get(dev, "vdda-phy");
 	if (IS_ERR(qphy->vreg))
-		return dev_err_probe(dev, PTR_ERR(qphy->phy),
+		return dev_err_probe(dev, PTR_ERR(qphy->vreg),
 				     "failed to get vreg\n");
 
 	phy_set_drvdata(qphy->phy, qphy);
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
index f6c727249104..17c4ad7553a5 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
@@ -1203,6 +1203,127 @@ static const struct qmp_phy_init_tbl sc8280xp_usb43dp_pcs_tbl[] = {
 	QMP_PHY_INIT_CFG(QPHY_V5_PCS_USB3_RXEQTRAINING_DFE_TIME_S2, 0x07),
 };
 
+static const struct qmp_phy_init_tbl x1e80100_usb43dp_serdes_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x62),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0xc2),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x03),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE1, 0xc2),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE1, 0x03),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_BUF_ENABLE, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0x1a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_CFG, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x1a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x41),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x82),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MSB_MODE0, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x82),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MSB_MODE1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE0, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE0, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x03),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE1, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE1, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE1, 0x03),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE1_MODE0, 0xba),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE2_MODE0, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE1_MODE1, 0xba),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE2_MODE1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x13),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_HS_SWITCH_SEL_1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CORE_CLK_DIV_MODE0, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORECLK_DIV_MODE1, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0xa0),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x76),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_IVCO, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_IVCO_MODE1, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN0_MODE0, 0x20),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN0_MODE1, 0x20),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_INITVAL2, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAXVAL2, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SVS_MODE_CLK_SEL, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_BG_TIMER, 0x0a),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_usb43dp_tx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_LANE_MODE_1, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_LANE_MODE_2, 0x50),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_LANE_MODE_3, 0x50),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_RES_CODE_LANE_OFFSET_TX, 0x1f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_RES_CODE_LANE_OFFSET_RX, 0x0a),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_usb43dp_rx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_SIGDET_CNTRL, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_SIGDET_DEGLITCH_CNTRL, 0x0e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_SIGDET_ENABLES, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B0, 0xc3),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B1, 0xc3),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B2, 0xd8),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B3, 0x9e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B4, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B5, 0xb6),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B6, 0x64),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B0, 0xd6),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B1, 0xee),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B2, 0x18),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B3, 0x9a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B4, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B5, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B6, 0xe3),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_IVCM_CAL_CODE_OVERRIDE, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_RX_IVCM_CAL_CTRL2, 0x80),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_RX_SUMMER_CAL_SPD_MODE, 0x2f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_DFE_CTLE_POST_CAL_OFFSET, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_UCDR_PI_CONTROLS, 0x15),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_UCDR_PI_CTRL1, 0xd0),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_UCDR_PI_CTRL2, 0x48),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_UCDR_SB2_GAIN2_RATE2, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_RX_IVCM_POSTCAL_OFFSET, 0x7c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_VGA_CAL_CNTRL1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_VGA_CAL_MAN_VAL, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_DFE_DAC_ENABLE1, 0x88),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_DFE_3, 0x45),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_GM_CAL, 0x0d),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_UCDR_FO_GAIN_RATE2, 0x09),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_UCDR_SO_GAIN_RATE2, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_Q_PI_INTRINSIC_BIAS_RATE32, 0x2f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_RX_BKUP_CTRL1, 0x14),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_usb43dp_pcs_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_L, 0xe7),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_H, 0x03),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG1, 0xc4),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG2, 0x89),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG3, 0x20),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG6, 0x13),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_REFGEN_REQ_CONFIG1, 0x21),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_RX_SIGDET_LVL, 0x55),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_CDR_RESET_TIME, 0x0a),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_ALIGN_DETECT_CONFIG1, 0xd4),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_ALIGN_DETECT_CONFIG2, 0x30),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_PCS_TX_RX_CONFIG, 0x0c),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_EQ_CONFIG1, 0x4b),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_EQ_CONFIG5, 0x10),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_usb43dp_pcs_usb_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_USB3_LFPS_DET_HIGH_COUNT_VAL, 0xf8),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_USB3_RXEQTRAINING_DFE_TIME_S2, 0x07),
+};
+
 /* list of regulators */
 struct qmp_regulator_data {
 	const char *name;
@@ -1682,6 +1803,51 @@ static const struct qmp_phy_cfg sc8280xp_usb43dpphy_cfg = {
 	.regs			= qmp_v5_5nm_usb3phy_regs_layout,
 };
 
+static const struct qmp_phy_cfg x1e80100_usb3dpphy_cfg = {
+	.offsets		= &qmp_combo_offsets_v5,
+
+	.serdes_tbl		= x1e80100_usb43dp_serdes_tbl,
+	.serdes_tbl_num		= ARRAY_SIZE(x1e80100_usb43dp_serdes_tbl),
+	.tx_tbl			= x1e80100_usb43dp_tx_tbl,
+	.tx_tbl_num		= ARRAY_SIZE(x1e80100_usb43dp_tx_tbl),
+	.rx_tbl			= x1e80100_usb43dp_rx_tbl,
+	.rx_tbl_num		= ARRAY_SIZE(x1e80100_usb43dp_rx_tbl),
+	.pcs_tbl		= x1e80100_usb43dp_pcs_tbl,
+	.pcs_tbl_num		= ARRAY_SIZE(x1e80100_usb43dp_pcs_tbl),
+	.pcs_usb_tbl		= x1e80100_usb43dp_pcs_usb_tbl,
+	.pcs_usb_tbl_num	= ARRAY_SIZE(x1e80100_usb43dp_pcs_usb_tbl),
+
+	.dp_serdes_tbl		= qmp_v6_dp_serdes_tbl,
+	.dp_serdes_tbl_num	= ARRAY_SIZE(qmp_v6_dp_serdes_tbl),
+	.dp_tx_tbl		= qmp_v6_dp_tx_tbl,
+	.dp_tx_tbl_num		= ARRAY_SIZE(qmp_v6_dp_tx_tbl),
+
+	.serdes_tbl_rbr		= qmp_v6_dp_serdes_tbl_rbr,
+	.serdes_tbl_rbr_num	= ARRAY_SIZE(qmp_v6_dp_serdes_tbl_rbr),
+	.serdes_tbl_hbr		= qmp_v6_dp_serdes_tbl_hbr,
+	.serdes_tbl_hbr_num	= ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr),
+	.serdes_tbl_hbr2	= qmp_v6_dp_serdes_tbl_hbr2,
+	.serdes_tbl_hbr2_num	= ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr2),
+	.serdes_tbl_hbr3	= qmp_v6_dp_serdes_tbl_hbr3,
+	.serdes_tbl_hbr3_num	= ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr3),
+
+	.swing_hbr_rbr		= &qmp_dp_v5_voltage_swing_hbr_rbr,
+	.pre_emphasis_hbr_rbr	= &qmp_dp_v5_pre_emphasis_hbr_rbr,
+	.swing_hbr3_hbr2	= &qmp_dp_v5_voltage_swing_hbr3_hbr2,
+	.pre_emphasis_hbr3_hbr2 = &qmp_dp_v5_pre_emphasis_hbr3_hbr2,
+
+	.dp_aux_init		= qmp_v4_dp_aux_init,
+	.configure_dp_tx	= qmp_v4_configure_dp_tx,
+	.configure_dp_phy	= qmp_v4_configure_dp_phy,
+	.calibrate_dp_phy	= qmp_v4_calibrate_dp_phy,
+
+	.reset_list		= msm8996_usb3phy_reset_l,
+	.num_resets		= ARRAY_SIZE(msm8996_usb3phy_reset_l),
+	.vreg_list		= qmp_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(qmp_phy_vreg_l),
+	.regs			= qmp_v45_usb3phy_regs_layout,
+};
+
 static const struct qmp_phy_cfg sm6350_usb3dpphy_cfg = {
 	.offsets		= &qmp_combo_offsets_v3,
 
@@ -3396,14 +3562,6 @@ static int qmp_combo_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = qmp_combo_typec_switch_register(qmp);
-	if (ret)
-		return ret;
-
-	ret = drm_aux_bridge_register(dev);
-	if (ret)
-		return ret;
-
 	/* Check for legacy binding with child nodes. */
 	usb_np = of_get_child_by_name(dev->of_node, "usb3-phy");
 	if (usb_np) {
@@ -3423,6 +3581,14 @@ static int qmp_combo_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_node_put;
 
+	ret = qmp_combo_typec_switch_register(qmp);
+	if (ret)
+		goto err_node_put;
+
+	ret = drm_aux_bridge_register(dev);
+	if (ret)
+		goto err_node_put;
+
 	pm_runtime_set_active(dev);
 	ret = devm_pm_runtime_enable(dev);
 	if (ret)
@@ -3518,6 +3684,14 @@ static const struct of_device_id qmp_combo_of_match_table[] = {
 		.compatible = "qcom,sm8550-qmp-usb3-dp-phy",
 		.data = &sm8550_usb3dpphy_cfg,
 	},
+	{
+		.compatible = "qcom,sm8650-qmp-usb3-dp-phy",
+		.data = &sm8550_usb3dpphy_cfg,
+	},
+	{
+		.compatible = "qcom,x1e80100-qmp-usb3-dp-phy",
+		.data = &x1e80100_usb3dpphy_cfg,
+	},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, qmp_combo_of_match_table);
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
index b64598ac59f4..2af7115ef968 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
@@ -1909,6 +1909,35 @@ static const struct qmp_phy_init_tbl sm8550_qmp_gen4x2_pcie_pcs_misc_tbl[] = {
 	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_G4_FOM_EQ_CONFIG5, 0xf2),
 };
 
+static const struct qmp_phy_init_tbl sm8650_qmp_gen4x2_pcie_rx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_UCDR_FO_GAIN_RATE_2, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_UCDR_FO_GAIN_RATE_3, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_UCDR_PI_CONTROLS, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_UCDR_SO_ACC_DEFAULT_VAL_RATE3, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_IVCM_CAL_CTRL2, 0x82),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_DFE_3, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_VGA_CAL_MAN_VAL, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_GM_CAL, 0x0d),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_EQU_ADAPTOR_CNTRL4, 0x0b),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_SIGDET_ENABLES, 0x1c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_PHPRE_CTRL, 0x20),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_DFE_CTLE_POST_CAL_OFFSET, 0x38),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B0, 0xd3),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B1, 0xd3),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B2, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B3, 0x9a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B4, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B5, 0xb6),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B6, 0xee),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B0, 0x23),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B1, 0x9b),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B2, 0x60),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B3, 0xdf),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B4, 0x43),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B5, 0x76),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B6, 0xff),
+};
+
 static const struct qmp_phy_init_tbl sa8775p_qmp_gen4x2_pcie_serdes_alt_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_V5_COM_BIAS_EN_CLKBUFLR_EN, 0x14),
 	QMP_PHY_INIT_CFG(QSERDES_V5_COM_PLL_IVCO, 0x0f),
@@ -3047,6 +3076,36 @@ static const struct qmp_phy_cfg sm8550_qmp_gen4x2_pciephy_cfg = {
 	.has_nocsr_reset	= true,
 };
 
+static const struct qmp_phy_cfg sm8650_qmp_gen4x2_pciephy_cfg = {
+	.lanes = 2,
+
+	.offsets		= &qmp_pcie_offsets_v6_20,
+
+	.tbls = {
+		.serdes			= sm8550_qmp_gen4x2_pcie_serdes_tbl,
+		.serdes_num		= ARRAY_SIZE(sm8550_qmp_gen4x2_pcie_serdes_tbl),
+		.tx			= sm8550_qmp_gen4x2_pcie_tx_tbl,
+		.tx_num			= ARRAY_SIZE(sm8550_qmp_gen4x2_pcie_tx_tbl),
+		.rx			= sm8650_qmp_gen4x2_pcie_rx_tbl,
+		.rx_num			= ARRAY_SIZE(sm8650_qmp_gen4x2_pcie_rx_tbl),
+		.pcs			= sm8550_qmp_gen4x2_pcie_pcs_tbl,
+		.pcs_num		= ARRAY_SIZE(sm8550_qmp_gen4x2_pcie_pcs_tbl),
+		.pcs_misc		= sm8550_qmp_gen4x2_pcie_pcs_misc_tbl,
+		.pcs_misc_num		= ARRAY_SIZE(sm8550_qmp_gen4x2_pcie_pcs_misc_tbl),
+		.ln_shrd		= sm8550_qmp_gen4x2_pcie_ln_shrd_tbl,
+		.ln_shrd_num		= ARRAY_SIZE(sm8550_qmp_gen4x2_pcie_ln_shrd_tbl),
+	},
+	.reset_list		= sdm845_pciephy_reset_l,
+	.num_resets		= ARRAY_SIZE(sdm845_pciephy_reset_l),
+	.vreg_list		= sm8550_qmp_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(sm8550_qmp_phy_vreg_l),
+	.regs			= pciephy_v5_regs_layout,
+
+	.pwrdn_ctrl		= SW_PWRDN | REFCLK_DRV_DSBL,
+	.phy_status		= PHYSTATUS_4_20,
+	.has_nocsr_reset	= true,
+};
+
 static const struct qmp_phy_cfg sa8775p_qmp_gen4x2_pciephy_cfg = {
 	.lanes			= 2,
 	.offsets		= &qmp_pcie_offsets_v5_20,
@@ -3820,6 +3879,12 @@ static const struct of_device_id qmp_pcie_of_match_table[] = {
 	}, {
 		.compatible = "qcom,sm8550-qmp-gen4x2-pcie-phy",
 		.data = &sm8550_qmp_gen4x2_pciephy_cfg,
+	}, {
+		.compatible = "qcom,sm8650-qmp-gen3x2-pcie-phy",
+		.data = &sm8550_qmp_gen3x2_pciephy_cfg,
+	}, {
+		.compatible = "qcom,sm8650-qmp-gen4x2-pcie-phy",
+		.data = &sm8650_qmp_gen4x2_pciephy_cfg,
 	},
 	{ },
 };
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-ufs-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-ufs-v6.h
index c23d5e41e25b..fe6c450f6123 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-ufs-v6.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-ufs-v6.h
@@ -12,6 +12,7 @@
 #define QPHY_V6_PCS_UFS_SW_RESET			0x008
 #define QPHY_V6_PCS_UFS_TIMER_20US_CORECLK_STEPS_MSB	0x00c
 #define QPHY_V6_PCS_UFS_TIMER_20US_CORECLK_STEPS_LSB	0x010
+#define QPHY_V6_PCS_UFS_PCS_CTRL1			0x020
 #define QPHY_V6_PCS_UFS_PLL_CNTL			0x02c
 #define QPHY_V6_PCS_UFS_TX_LARGE_AMP_DRV_LVL		0x030
 #define QPHY_V6_PCS_UFS_TX_SMALL_AMP_DRV_LVL		0x038
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-usb-v7.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-usb-v7.h
new file mode 100644
index 000000000000..24368d45ae76
--- /dev/null
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-usb-v7.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef QCOM_PHY_QMP_PCS_USB_V7_H_
+#define QCOM_PHY_QMP_PCS_USB_V7_H_
+
+#define QPHY_V7_PCS_USB3_POWER_STATE_CONFIG1		0x00
+#define QPHY_V7_PCS_USB3_AUTONOMOUS_MODE_CTRL		0x08
+#define QPHY_V7_PCS_USB3_LFPS_RXTERM_IRQ_CLEAR		0x14
+#define QPHY_V7_PCS_USB3_LFPS_DET_HIGH_COUNT_VAL	0x18
+#define QPHY_V7_PCS_USB3_RXEQTRAINING_DFE_TIME_S2	0x3c
+#define QPHY_V7_PCS_USB3_RCVR_DTCT_DLY_U3_L		0x40
+#define QPHY_V7_PCS_USB3_RCVR_DTCT_DLY_U3_H		0x44
+
+#endif
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v7.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v7.h
new file mode 100644
index 000000000000..c7759892ed2e
--- /dev/null
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v7.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef QCOM_PHY_QMP_PCS_V7_H_
+#define QCOM_PHY_QMP_PCS_V7_H_
+
+/* Only for QMP V7 PHY - USB/PCIe PCS registers */
+#define QPHY_V7_PCS_SW_RESET			0x000
+#define QPHY_V7_PCS_PCS_STATUS1			0x014
+#define QPHY_V7_PCS_POWER_DOWN_CONTROL		0x040
+#define QPHY_V7_PCS_START_CONTROL		0x044
+#define QPHY_V7_PCS_POWER_STATE_CONFIG1		0x090
+#define QPHY_V7_PCS_LOCK_DETECT_CONFIG1		0x0c4
+#define QPHY_V7_PCS_LOCK_DETECT_CONFIG2		0x0c8
+#define QPHY_V7_PCS_LOCK_DETECT_CONFIG3		0x0cc
+#define QPHY_V7_PCS_LOCK_DETECT_CONFIG6		0x0d8
+#define QPHY_V7_PCS_REFGEN_REQ_CONFIG1		0x0dc
+#define QPHY_V7_PCS_RX_SIGDET_LVL		0x188
+#define QPHY_V7_PCS_RCVR_DTCT_DLY_P1U2_L	0x190
+#define QPHY_V7_PCS_RCVR_DTCT_DLY_P1U2_H	0x194
+#define QPHY_V7_PCS_RATE_SLEW_CNTRL1		0x198
+#define QPHY_V7_PCS_CDR_RESET_TIME		0x1b0
+#define QPHY_V7_PCS_ALIGN_DETECT_CONFIG1	0x1c0
+#define QPHY_V7_PCS_ALIGN_DETECT_CONFIG2	0x1c4
+#define QPHY_V7_PCS_PCS_TX_RX_CONFIG		0x1d0
+#define QPHY_V7_PCS_EQ_CONFIG1			0x1dc
+#define QPHY_V7_PCS_EQ_CONFIG2			0x1e0
+#define QPHY_V7_PCS_EQ_CONFIG5			0x1ec
+
+#endif
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v6.h
index f420f8faf16a..ec7291424dd1 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v6.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v6.h
@@ -22,6 +22,8 @@
 #define QSERDES_V6_COM_DIV_FRAC_START2_MODE1			0x34
 #define QSERDES_V6_COM_DIV_FRAC_START3_MODE1			0x38
 #define QSERDES_V6_COM_HSCLK_SEL_1				0x3c
+#define QSERDES_V6_COM_INTEGLOOP_GAIN0_MODE1			0x40
+#define QSERDES_V6_COM_INTEGLOOP_GAIN1_MODE1			0x44
 #define QSERDES_V6_COM_VCO_TUNE1_MODE1				0x48
 #define QSERDES_V6_COM_VCO_TUNE2_MODE1				0x4c
 #define QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE1		0x50
@@ -48,6 +50,7 @@
 #define QSERDES_V6_COM_VCO_TUNE2_MODE0				0xac
 #define QSERDES_V6_COM_BG_TIMER					0xbc
 #define QSERDES_V6_COM_SSC_EN_CENTER				0xc0
+#define QSERDES_V6_COM_SSC_ADJ_PER1				0xc4
 #define QSERDES_V6_COM_SSC_PER1					0xcc
 #define QSERDES_V6_COM_SSC_PER2					0xd0
 #define QSERDES_V6_COM_PLL_POST_DIV_MUX				0xd8
@@ -56,6 +59,7 @@
 #define QSERDES_V6_COM_SYS_CLK_CTRL				0xe4
 #define QSERDES_V6_COM_SYSCLK_BUF_ENABLE			0xe8
 #define QSERDES_V6_COM_PLL_IVCO					0xf4
+#define QSERDES_V6_COM_PLL_IVCO_MODE1				0xf8
 #define QSERDES_V6_COM_SYSCLK_EN_SEL				0x110
 #define QSERDES_V6_COM_RESETSM_CNTRL				0x118
 #define QSERDES_V6_COM_LOCK_CMP_EN				0x120
@@ -63,6 +67,7 @@
 #define QSERDES_V6_COM_VCO_TUNE_CTRL				0x13c
 #define QSERDES_V6_COM_VCO_TUNE_MAP				0x140
 #define QSERDES_V6_COM_VCO_TUNE_INITVAL2			0x148
+#define QSERDES_V6_COM_VCO_TUNE_MAXVAL2				0x158
 #define QSERDES_V6_COM_CLK_SELECT				0x164
 #define QSERDES_V6_COM_CORE_CLK_EN				0x170
 #define QSERDES_V6_COM_CMN_CONFIG_1				0x174
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v7.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v7.h
new file mode 100644
index 000000000000..7430f4921477
--- /dev/null
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v7.h
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef QCOM_PHY_QMP_QSERDES_COM_V7_H_
+#define QCOM_PHY_QMP_QSERDES_COM_V7_H_
+
+/* Only for QMP V7 PHY - QSERDES COM registers */
+
+#define QSERDES_V7_COM_SSC_STEP_SIZE1_MODE1			0x00
+#define QSERDES_V7_COM_SSC_STEP_SIZE2_MODE1			0x04
+#define QSERDES_V7_COM_CP_CTRL_MODE1				0x10
+#define QSERDES_V7_COM_PLL_RCTRL_MODE1				0x14
+#define QSERDES_V7_COM_PLL_CCTRL_MODE1				0x18
+#define QSERDES_V7_COM_CORECLK_DIV_MODE1			0x1c
+#define QSERDES_V7_COM_LOCK_CMP1_MODE1				0x20
+#define QSERDES_V7_COM_LOCK_CMP2_MODE1				0x24
+#define QSERDES_V7_COM_DEC_START_MODE1				0x28
+#define QSERDES_V7_COM_DEC_START_MSB_MODE1			0x2c
+#define QSERDES_V7_COM_DIV_FRAC_START1_MODE1			0x30
+#define QSERDES_V7_COM_DIV_FRAC_START2_MODE1			0x34
+#define QSERDES_V7_COM_DIV_FRAC_START3_MODE1			0x38
+#define QSERDES_V7_COM_HSCLK_SEL_1				0x3c
+#define QSERDES_V7_COM_INTEGLOOP_GAIN0_MODE1			0x40
+#define QSERDES_V7_COM_INTEGLOOP_GAIN1_MODE1			0x44
+#define QSERDES_V7_COM_VCO_TUNE1_MODE1				0x48
+#define QSERDES_V7_COM_VCO_TUNE2_MODE1				0x4c
+#define QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE1_MODE1		0x50
+#define QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE2_MODE1		0x54
+#define QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE1_MODE0		0x58
+#define QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE2_MODE0		0x5c
+#define QSERDES_V7_COM_SSC_STEP_SIZE1_MODE0			0x60
+#define QSERDES_V7_COM_SSC_STEP_SIZE2_MODE0			0x64
+#define QSERDES_V7_COM_CP_CTRL_MODE0				0x70
+#define QSERDES_V7_COM_PLL_RCTRL_MODE0				0x74
+#define QSERDES_V7_COM_PLL_CCTRL_MODE0				0x78
+#define QSERDES_V7_COM_PLL_CORE_CLK_DIV_MODE0			0x7c
+#define QSERDES_V7_COM_LOCK_CMP1_MODE0				0x80
+#define QSERDES_V7_COM_LOCK_CMP2_MODE0				0x84
+#define QSERDES_V7_COM_DEC_START_MODE0				0x88
+#define QSERDES_V7_COM_DEC_START_MSB_MODE0			0x8c
+#define QSERDES_V7_COM_DIV_FRAC_START1_MODE0			0x90
+#define QSERDES_V7_COM_DIV_FRAC_START2_MODE0			0x94
+#define QSERDES_V7_COM_DIV_FRAC_START3_MODE0			0x98
+#define QSERDES_V7_COM_HSCLK_HS_SWITCH_SEL_1			0x9c
+#define QSERDES_V7_COM_INTEGLOOP_GAIN0_MODE0			0xa0
+#define QSERDES_V7_COM_INTEGLOOP_GAIN1_MODE0			0xa4
+#define QSERDES_V7_COM_VCO_TUNE1_MODE0				0xa8
+#define QSERDES_V7_COM_VCO_TUNE2_MODE0				0xac
+#define QSERDES_V7_COM_BG_TIMER					0xbc
+#define QSERDES_V7_COM_SSC_EN_CENTER				0xc0
+#define QSERDES_V7_COM_SSC_ADJ_PER1				0xc4
+#define QSERDES_V7_COM_SSC_PER1					0xcc
+#define QSERDES_V7_COM_SSC_PER2					0xd0
+#define QSERDES_V7_COM_PLL_POST_DIV_MUX				0xd8
+#define QSERDES_V7_COM_PLL_BIAS_EN_CLK_BUFLR_EN			0xdc
+#define QSERDES_V7_COM_CLK_ENABLE1				0xe0
+#define QSERDES_V7_COM_SYS_CLK_CTRL				0xe4
+#define QSERDES_V7_COM_SYSCLK_BUF_ENABLE			0xe8
+#define QSERDES_V7_COM_PLL_IVCO					0xf4
+#define QSERDES_V7_COM_PLL_IVCO_MODE1				0xf8
+#define QSERDES_V7_COM_SYSCLK_EN_SEL				0x110
+#define QSERDES_V7_COM_RESETSM_CNTRL				0x118
+#define QSERDES_V7_COM_LOCK_CMP_EN				0x120
+#define QSERDES_V7_COM_LOCK_CMP_CFG				0x124
+#define QSERDES_V7_COM_VCO_TUNE_CTRL				0x13c
+#define QSERDES_V7_COM_VCO_TUNE_MAP				0x140
+#define QSERDES_V7_COM_VCO_TUNE_INITVAL2			0x148
+#define QSERDES_V7_COM_VCO_TUNE_MAXVAL2				0x158
+#define QSERDES_V7_COM_CLK_SELECT				0x164
+#define QSERDES_V7_COM_CORE_CLK_EN				0x170
+#define QSERDES_V7_COM_CMN_CONFIG_1				0x174
+#define QSERDES_V7_COM_SVS_MODE_CLK_SEL				0x17c
+#define QSERDES_V7_COM_CMN_MISC_1				0x184
+#define QSERDES_V7_COM_CMN_MODE					0x188
+#define QSERDES_V7_COM_PLL_VCO_DC_LEVEL_CTRL			0x198
+#define QSERDES_V7_COM_AUTO_GAIN_ADJ_CTRL_1			0x1a4
+#define QSERDES_V7_COM_AUTO_GAIN_ADJ_CTRL_2			0x1a8
+#define QSERDES_V7_COM_AUTO_GAIN_ADJ_CTRL_3			0x1ac
+#define QSERDES_V7_COM_ADDITIONAL_MISC				0x1b4
+#define QSERDES_V7_COM_ADDITIONAL_MISC_2			0x1b8
+#define QSERDES_V7_COM_ADDITIONAL_MISC_3			0x1bc
+#define QSERDES_V7_COM_CMN_STATUS				0x1d0
+#define QSERDES_V7_COM_C_READY_STATUS				0x1f8
+
+#endif
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-ufs-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-ufs-v6.h
index 15bcb4ba9139..35d497fd9f9a 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-ufs-v6.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-ufs-v6.h
@@ -10,10 +10,18 @@
 #define QSERDES_UFS_V6_TX_RES_CODE_LANE_RX			0x2c
 #define QSERDES_UFS_V6_TX_RES_CODE_LANE_OFFSET_TX		0x30
 #define QSERDES_UFS_V6_TX_RES_CODE_LANE_OFFSET_RX		0x34
+#define QSERDES_UFS_V6_TX_LANE_MODE_1				0x7c
+#define QSERDES_UFS_V6_TX_FR_DCC_CTRL				0x108
 
 #define QSERDES_UFS_V6_RX_UCDR_FASTLOCK_FO_GAIN_RATE2		0x08
 #define QSERDES_UFS_V6_RX_UCDR_FASTLOCK_FO_GAIN_RATE4		0x10
+#define QSERDES_UFS_V6_RX_UCDR_SO_SATURATION			0x28
+#define QSERDES_UFS_V6_RX_UCDR_PI_CTRL1				0x58
+#define QSERDES_UFS_V6_RX_RX_TERM_BW_CTRL0			0xc4
+#define QSERDES_UFS_V6_RX_UCDR_FO_GAIN_RATE2			0xd4
+#define QSERDES_UFS_V6_RX_UCDR_FO_GAIN_RATE4			0xdc
 #define QSERDES_UFS_V6_RX_VGA_CAL_MAN_VAL			0x178
+#define QSERDES_UFS_V6_RX_INTERFACE_MODE			0x1e0
 #define QSERDES_UFS_V6_RX_MODE_RATE_0_1_B0			0x208
 #define QSERDES_UFS_V6_RX_MODE_RATE_0_1_B1			0x20c
 #define QSERDES_UFS_V6_RX_MODE_RATE_0_1_B3			0x214
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h
index 8883e1de730e..23ffcfae9efa 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h
@@ -23,6 +23,7 @@
 #define QSERDES_V6_TX_PARRATE_REC_DETECT_IDLE_EN		0x60
 #define QSERDES_V6_TX_BIST_PATTERN7				0x7c
 #define QSERDES_V6_TX_LANE_MODE_1				0x84
+#define QSERDES_V6_TX_LANE_MODE_2				0x88
 #define QSERDES_V6_TX_LANE_MODE_3				0x8c
 #define QSERDES_V6_TX_LANE_MODE_4				0x90
 #define QSERDES_V6_TX_LANE_MODE_5				0x94
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_20.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_20.h
index 5385a8b60970..6ed5339fd2ea 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_20.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_20.h
@@ -15,10 +15,13 @@
 
 #define QSERDES_V6_20_RX_UCDR_FO_GAIN_RATE_2			0x08
 #define QSERDES_V6_20_RX_UCDR_FO_GAIN_RATE_3			0x0c
+#define QSERDES_V6_20_RX_UCDR_SO_GAIN_RATE_2			0x18
 #define QSERDES_V6_20_RX_UCDR_PI_CONTROLS			0x20
 #define QSERDES_V6_20_RX_UCDR_SO_ACC_DEFAULT_VAL_RATE3		0x34
 #define QSERDES_V6_20_RX_IVCM_CAL_CTRL2				0x9c
 #define QSERDES_V6_20_RX_IVCM_POSTCAL_OFFSET			0xa0
+#define QSERDES_V6_20_RX_DFE_1					0xac
+#define QSERDES_V6_20_RX_DFE_2					0xb0
 #define QSERDES_V6_20_RX_DFE_3					0xb4
 #define QSERDES_V6_20_RX_VGA_CAL_MAN_VAL			0xe8
 #define QSERDES_V6_20_RX_GM_CAL					0x10c
@@ -41,5 +44,6 @@
 #define QSERDES_V6_20_RX_MODE_RATE3_B4				0x220
 #define QSERDES_V6_20_RX_MODE_RATE3_B5				0x224
 #define QSERDES_V6_20_RX_MODE_RATE3_B6				0x228
+#define QSERDES_V6_20_RX_BKUP_CTRL1				0x22c
 
 #endif
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_n4.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_n4.h
new file mode 100644
index 000000000000..a814ad11af07
--- /dev/null
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_n4.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef QCOM_PHY_QMP_QSERDES_TXRX_V6_N4_H_
+#define QCOM_PHY_QMP_QSERDES_TXRX_V6_N4_H_
+
+#define QSERDES_V6_N4_TX_RES_CODE_LANE_OFFSET_TX	0x30
+#define QSERDES_V6_N4_TX_RES_CODE_LANE_OFFSET_RX	0x34
+#define QSERDES_V6_N4_TX_LANE_MODE_1			0x78
+#define QSERDES_V6_N4_TX_LANE_MODE_2			0x7c
+#define QSERDES_V6_N4_TX_LANE_MODE_3			0x80
+
+#define QSERDES_V6_N4_RX_UCDR_FO_GAIN_RATE2		0x8
+#define QSERDES_V6_N4_RX_UCDR_SO_GAIN_RATE2		0x18
+#define QSERDES_V6_N4_RX_UCDR_PI_CONTROLS		0x20
+#define QSERDES_V6_N4_RX_IVCM_CAL_CODE_OVERRIDE		0x94
+#define QSERDES_V6_N4_RX_RX_IVCM_CAL_CTRL2		0x9c
+#define QSERDES_V6_N4_RX_RX_IVCM_POSTCAL_OFFSET		0xa0
+#define QSERDES_V6_N4_RX_DFE_3				0xb4
+#define QSERDES_V6_N4_RX_VGA_CAL_CNTRL1			0xe0
+#define QSERDES_V6_N4_RX_VGA_CAL_MAN_VAL		0xe8
+#define QSERDES_V6_N4_RX_GM_CAL				0x10c
+#define QSERDES_V6_N4_RX_SIGDET_ENABLES			0x148
+#define QSERDES_V6_N4_RX_SIGDET_CNTRL			0x14c
+#define QSERDES_V6_N4_RX_SIGDET_DEGLITCH_CNTRL		0x154
+#define QSERDES_V6_N4_RX_DFE_CTLE_POST_CAL_OFFSET	0x194
+#define QSERDES_V6_N4_RX_Q_PI_INTRINSIC_BIAS_RATE32	0x1dc
+#define QSERDES_V6_N4_RX_UCDR_PI_CTRL1			0x23c
+#define QSERDES_V6_N4_RX_UCDR_PI_CTRL2			0x240
+#define QSERDES_V6_N4_RX_UCDR_SB2_GAIN2_RATE2		0x27c
+#define QSERDES_V6_N4_RX_DFE_DAC_ENABLE1		0x298
+#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B0		0x2b8
+#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B1		0x2bc
+#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B2		0x2c0
+#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B3		0x2c4
+#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B4		0x2c8
+#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B5		0x2cc
+#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B6		0x2d0
+#define QSERDES_V6_N4_RX_MODE_RATE2_B0			0x2d4
+#define QSERDES_V6_N4_RX_MODE_RATE2_B1			0x2d8
+#define QSERDES_V6_N4_RX_MODE_RATE2_B2			0x2dc
+#define QSERDES_V6_N4_RX_MODE_RATE2_B3			0x2e0
+#define QSERDES_V6_N4_RX_MODE_RATE2_B4			0x2e4
+#define QSERDES_V6_N4_RX_MODE_RATE2_B5			0x2e8
+#define QSERDES_V6_N4_RX_MODE_RATE2_B6			0x2ec
+#define QSERDES_V6_N4_RX_RX_SUMMER_CAL_SPD_MODE		0x30c
+#define QSERDES_V6_N4_RX_RX_BKUP_CTRL1			0x310
+
+#endif
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v7.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v7.h
new file mode 100644
index 000000000000..91f865b11347
--- /dev/null
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v7.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef QCOM_PHY_QMP_QSERDES_TXRX_V7_H_
+#define QCOM_PHY_QMP_QSERDES_TXRX_V7_H_
+
+#define QSERDES_V7_TX_CLKBUF_ENABLE				0x08
+#define QSERDES_V7_TX_RESET_TSYNC_EN				0x1c
+#define QSERDES_V7_TX_PRE_STALL_LDO_BOOST_EN			0x20
+#define QSERDES_V7_TX_TX_BAND					0x24
+#define QSERDES_V7_TX_INTERFACE_SELECT				0x2c
+#define QSERDES_V7_TX_RES_CODE_LANE_TX				0x34
+#define QSERDES_V7_TX_RES_CODE_LANE_RX				0x38
+#define QSERDES_V7_TX_RES_CODE_LANE_OFFSET_TX			0x3c
+#define QSERDES_V7_TX_RES_CODE_LANE_OFFSET_RX			0x40
+#define QSERDES_V7_TX_PARRATE_REC_DETECT_IDLE_EN		0x60
+#define QSERDES_V7_TX_BIST_PATTERN7				0x7c
+#define QSERDES_V7_TX_LANE_MODE_1				0x84
+#define QSERDES_V7_TX_LANE_MODE_2				0x88
+#define QSERDES_V7_TX_LANE_MODE_3				0x8c
+#define QSERDES_V7_TX_LANE_MODE_4				0x90
+#define QSERDES_V7_TX_LANE_MODE_5				0x94
+#define QSERDES_V7_TX_RCV_DETECT_LVL_2				0xa4
+#define QSERDES_V7_TX_TRAN_DRVR_EMP_EN				0xc0
+#define QSERDES_V7_TX_TX_INTERFACE_MODE				0xc4
+#define QSERDES_V7_TX_VMODE_CTRL1				0xc8
+#define QSERDES_V7_TX_PI_QEC_CTRL				0xe4
+
+#define QSERDES_V7_RX_UCDR_FO_GAIN				0x08
+#define QSERDES_V7_RX_UCDR_SO_GAIN				0x14
+#define QSERDES_V7_RX_UCDR_FASTLOCK_FO_GAIN			0x30
+#define QSERDES_V7_RX_UCDR_SO_SATURATION_AND_ENABLE		0x34
+#define QSERDES_V7_RX_UCDR_FASTLOCK_COUNT_LOW			0x3c
+#define QSERDES_V7_RX_UCDR_FASTLOCK_COUNT_HIGH			0x40
+#define QSERDES_V7_RX_UCDR_PI_CONTROLS				0x44
+#define QSERDES_V7_RX_UCDR_SB2_THRESH1				0x4c
+#define QSERDES_V7_RX_UCDR_SB2_THRESH2				0x50
+#define QSERDES_V7_RX_UCDR_SB2_GAIN1				0x54
+#define QSERDES_V7_RX_UCDR_SB2_GAIN2				0x58
+#define QSERDES_V7_RX_AUX_DATA_TCOARSE_TFINE			0x60
+#define QSERDES_V7_RX_TX_ADAPT_POST_THRESH			0xcc
+#define QSERDES_V7_RX_VGA_CAL_CNTRL1				0xd4
+#define QSERDES_V7_RX_VGA_CAL_CNTRL2				0xd8
+#define QSERDES_V7_RX_GM_CAL					0xdc
+#define QSERDES_V7_RX_RX_EQU_ADAPTOR_CNTRL2			0xec
+#define QSERDES_V7_RX_RX_EQU_ADAPTOR_CNTRL3			0xf0
+#define QSERDES_V7_RX_RX_EQU_ADAPTOR_CNTRL4			0xf4
+#define QSERDES_V7_RX_RX_IDAC_TSETTLE_LOW			0xf8
+#define QSERDES_V7_RX_RX_IDAC_TSETTLE_HIGH			0xfc
+#define QSERDES_V7_RX_RX_EQ_OFFSET_ADAPTOR_CNTRL1		0x110
+#define QSERDES_V7_RX_SIDGET_ENABLES				0x118
+#define QSERDES_V7_RX_SIGDET_CNTRL				0x11c
+#define QSERDES_V7_RX_SIGDET_DEGLITCH_CNTRL			0x124
+#define QSERDES_V7_RX_RX_MODE_00_LOW				0x15c
+#define QSERDES_V7_RX_RX_MODE_00_HIGH				0x160
+#define QSERDES_V7_RX_RX_MODE_00_HIGH2				0x164
+#define QSERDES_V7_RX_RX_MODE_00_HIGH3				0x168
+#define QSERDES_V7_RX_RX_MODE_00_HIGH4				0x16c
+#define QSERDES_V7_RX_RX_MODE_01_LOW				0x170
+#define QSERDES_V7_RX_RX_MODE_01_HIGH				0x174
+#define QSERDES_V7_RX_RX_MODE_01_HIGH2				0x178
+#define QSERDES_V7_RX_RX_MODE_01_HIGH3				0x17c
+#define QSERDES_V7_RX_RX_MODE_01_HIGH4				0x180
+#define QSERDES_V7_RX_RX_MODE_10_LOW				0x184
+#define QSERDES_V7_RX_RX_MODE_10_HIGH				0x188
+#define QSERDES_V7_RX_RX_MODE_10_HIGH2				0x18c
+#define QSERDES_V7_RX_RX_MODE_10_HIGH3				0x190
+#define QSERDES_V7_RX_RX_MODE_10_HIGH4				0x194
+#define QSERDES_V7_RX_DFE_EN_TIMER				0x1a0
+#define QSERDES_V7_RX_DFE_CTLE_POST_CAL_OFFSET			0x1a4
+#define QSERDES_V7_RX_DCC_CTRL1					0x1a8
+#define QSERDES_V7_RX_VTH_CODE					0x1b0
+#define QSERDES_V7_RX_SIGDET_CAL_CTRL1				0x1e4
+#define QSERDES_V7_RX_SIGDET_CAL_TRIM				0x1f8
+
+#endif
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
index 514fa14df634..3c2e6255e26f 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
@@ -763,22 +763,26 @@ static const struct qmp_phy_init_tbl sm8550_ufsphy_serdes[] = {
 	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x14),
 	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x7f),
 	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x06),
-	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x4c),
-	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x0a),
-	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x18),
-	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x14),
-	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x99),
-	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x07),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x4c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x18),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0x99),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x07),
+};
+
+static const struct qmp_phy_init_tbl sm8550_ufsphy_hs_b_serdes[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x44),
 };
 
 static const struct qmp_phy_init_tbl sm8550_ufsphy_tx[] = {
-	QMP_PHY_INIT_CFG(QSERDES_V6_TX_LANE_MODE_1, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_TX_LANE_MODE_1, 0x05),
 	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_TX_RES_CODE_LANE_OFFSET_TX, 0x07),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_TX_FR_DCC_CTRL, 0x4c),
 };
 
 static const struct qmp_phy_init_tbl sm8550_ufsphy_rx[] = {
-	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_FASTLOCK_FO_GAIN_RATE2, 0x0c),
-	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_FASTLOCK_FO_GAIN_RATE4, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_FO_GAIN_RATE2, 0x0c),
 	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_VGA_CAL_MAN_VAL, 0x0e),
 
 	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE_0_1_B0, 0xc2),
@@ -801,6 +805,69 @@ static const struct qmp_phy_init_tbl sm8550_ufsphy_pcs[] = {
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_MID_TERM_CTRL1, 0x43),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PLL_CNTL, 0x2b),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_MULTI_LANE_CTRL1, 0x02),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_HSGEAR_CAPABILITY, 0x04),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_HSGEAR_CAPABILITY, 0x04),
+};
+
+static const struct qmp_phy_init_tbl sm8650_ufsphy_serdes[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0xd9),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x11),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_HS_SWITCH_SEL_1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_IVCO, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x44),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_INITVAL2, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x41),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x18),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x7f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x4c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x18),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0x99),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x07),
+};
+
+static const struct qmp_phy_init_tbl sm8650_ufsphy_tx[] = {
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_TX_LANE_MODE_1, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_TX_RES_CODE_LANE_OFFSET_TX, 0x07),
+};
+
+static const struct qmp_phy_init_tbl sm8650_ufsphy_rx[] = {
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_FO_GAIN_RATE2, 0x0c),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_FO_GAIN_RATE4, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_VGA_CAL_MAN_VAL, 0x0e),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE_0_1_B0, 0xc2),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE_0_1_B1, 0xc2),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE_0_1_B3, 0x1a),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE_0_1_B6, 0x60),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE2_B3, 0x9e),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE2_B6, 0x60),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE3_B3, 0x9e),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE3_B4, 0x0e),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE3_B5, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE3_B8, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE4_B3, 0xb9),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE4_B6, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_SO_SATURATION, 0x1f),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_PI_CTRL1, 0x94),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_RX_TERM_BW_CTRL0, 0xfa),
+};
+
+static const struct qmp_phy_init_tbl sm8650_ufsphy_pcs[] = {
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_MULTI_LANE_CTRL1, 0x00),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_MID_TERM_CTRL1, 0x43),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PCS_CTRL1, 0xc1),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PLL_CNTL, 0x33),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_HSGEAR_CAPABILITY, 0x04),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_HSGEAR_CAPABILITY, 0x04),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_LARGE_AMP_DRV_LVL, 0x0f),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_SIGDET_CTRL2, 0x69),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_MULTI_LANE_CTRL1, 0x02),
 };
 
 struct qmp_ufs_offsets {
@@ -1296,6 +1363,32 @@ static const struct qmp_phy_cfg sm8550_ufsphy_cfg = {
 		.pcs		= sm8550_ufsphy_pcs,
 		.pcs_num	= ARRAY_SIZE(sm8550_ufsphy_pcs),
 	},
+	.tbls_hs_b = {
+		.serdes		= sm8550_ufsphy_hs_b_serdes,
+		.serdes_num	= ARRAY_SIZE(sm8550_ufsphy_hs_b_serdes),
+	},
+	.clk_list		= sdm845_ufs_phy_clk_l,
+	.num_clks		= ARRAY_SIZE(sdm845_ufs_phy_clk_l),
+	.vreg_list		= qmp_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(qmp_phy_vreg_l),
+	.regs			= ufsphy_v6_regs_layout,
+};
+
+static const struct qmp_phy_cfg sm8650_ufsphy_cfg = {
+	.lanes			= 2,
+
+	.offsets		= &qmp_ufs_offsets_v6,
+
+	.tbls = {
+		.serdes		= sm8650_ufsphy_serdes,
+		.serdes_num	= ARRAY_SIZE(sm8650_ufsphy_serdes),
+		.tx		= sm8650_ufsphy_tx,
+		.tx_num		= ARRAY_SIZE(sm8650_ufsphy_tx),
+		.rx		= sm8650_ufsphy_rx,
+		.rx_num		= ARRAY_SIZE(sm8650_ufsphy_rx),
+		.pcs		= sm8650_ufsphy_pcs,
+		.pcs_num	= ARRAY_SIZE(sm8650_ufsphy_pcs),
+	},
 	.clk_list		= sdm845_ufs_phy_clk_l,
 	.num_clks		= ARRAY_SIZE(sdm845_ufs_phy_clk_l),
 	.vreg_list		= qmp_phy_vreg_l,
@@ -1826,6 +1919,9 @@ static const struct of_device_id qmp_ufs_of_match_table[] = {
 	}, {
 		.compatible = "qcom,sm8550-qmp-ufs-phy",
 		.data = &sm8550_ufsphy_cfg,
+	}, {
+		.compatible = "qcom,sm8650-qmp-ufs-phy",
+		.data = &sm8650_ufsphy_cfg,
 	},
 	{ },
 };
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
index 02f156298e77..5c003988c35d 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
@@ -24,6 +24,8 @@
 #include "phy-qcom-qmp-pcs-misc-v4.h"
 #include "phy-qcom-qmp-pcs-usb-v4.h"
 #include "phy-qcom-qmp-pcs-usb-v5.h"
+#include "phy-qcom-qmp-pcs-usb-v6.h"
+#include "phy-qcom-qmp-pcs-usb-v7.h"
 
 /* QPHY_SW_RESET bit */
 #define SW_RESET				BIT(0)
@@ -151,6 +153,28 @@ static const unsigned int qmp_v5_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = {
 	[QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR] = QPHY_V5_PCS_USB3_LFPS_RXTERM_IRQ_CLEAR,
 };
 
+static const unsigned int qmp_v6_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = {
+	[QPHY_SW_RESET]			= QPHY_V6_PCS_SW_RESET,
+	[QPHY_START_CTRL]		= QPHY_V6_PCS_START_CONTROL,
+	[QPHY_PCS_STATUS]		= QPHY_V6_PCS_PCS_STATUS1,
+	[QPHY_PCS_POWER_DOWN_CONTROL]	= QPHY_V6_PCS_POWER_DOWN_CONTROL,
+
+	/* In PCS_USB */
+	[QPHY_PCS_AUTONOMOUS_MODE_CTRL]	= QPHY_V6_PCS_USB3_AUTONOMOUS_MODE_CTRL,
+	[QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR] = QPHY_V6_PCS_USB3_LFPS_RXTERM_IRQ_CLEAR,
+};
+
+static const unsigned int qmp_v7_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = {
+	[QPHY_SW_RESET]			= QPHY_V7_PCS_SW_RESET,
+	[QPHY_START_CTRL]		= QPHY_V7_PCS_START_CONTROL,
+	[QPHY_PCS_STATUS]		= QPHY_V7_PCS_PCS_STATUS1,
+	[QPHY_PCS_POWER_DOWN_CONTROL]	= QPHY_V7_PCS_POWER_DOWN_CONTROL,
+
+	/* In PCS_USB */
+	[QPHY_PCS_AUTONOMOUS_MODE_CTRL]	= QPHY_V7_PCS_USB3_AUTONOMOUS_MODE_CTRL,
+	[QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR] = QPHY_V7_PCS_USB3_LFPS_RXTERM_IRQ_CLEAR,
+};
+
 static const struct qmp_phy_init_tbl ipq9574_usb3_serdes_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_COM_SYSCLK_EN_SEL, 0x1a),
 	QMP_PHY_INIT_CFG(QSERDES_COM_BIAS_EN_CLKBUFLR_EN, 0x08),
@@ -871,6 +895,134 @@ static const struct qmp_phy_init_tbl sdx65_usb3_uniphy_rx_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_V5_RX_SIGDET_ENABLES, 0x00),
 };
 
+static const struct qmp_phy_init_tbl sdx75_usb3_uniphy_serdes_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE1, 0x9e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE1, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORECLK_DIV_MODE1, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0x2e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x82),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x82),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE1, 0xab),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE1, 0xea),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE1, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE1_MODE1, 0x25),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE2_MODE1, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE1, 0xb7),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE1, 0x1e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE0, 0xb7),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x1e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0x9e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x12),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x34),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x82),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE0, 0xab),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE0, 0xea),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE1_MODE0, 0x25),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE2_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_BG_TIMER, 0x0e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x31),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_BUF_ENABLE, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0x1a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_CFG, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0x20),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_AUTO_GAIN_ADJ_CTRL_1, 0xb6),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_AUTO_GAIN_ADJ_CTRL_2, 0x4b),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_AUTO_GAIN_ADJ_CTRL_3, 0x37),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_ADDITIONAL_MISC, 0x0c),
+};
+
+static const struct qmp_phy_init_tbl sdx75_usb3_uniphy_tx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_TX_RES_CODE_LANE_TX, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_TX_RES_CODE_LANE_RX, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_TX_RES_CODE_LANE_OFFSET_TX, 0x1f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_TX_RES_CODE_LANE_OFFSET_RX, 0x09),
+	QMP_PHY_INIT_CFG(QSERDES_V6_TX_LANE_MODE_1, 0xf5),
+	QMP_PHY_INIT_CFG(QSERDES_V6_TX_LANE_MODE_3, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_TX_LANE_MODE_4, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_TX_LANE_MODE_5, 0x5f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_TX_RCV_DETECT_LVL_2, 0x12),
+	QMP_PHY_INIT_CFG(QSERDES_V6_TX_PI_QEC_CTRL, 0x21),
+};
+
+static const struct qmp_phy_init_tbl sdx75_usb3_uniphy_rx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_FO_GAIN, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SO_GAIN, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_FASTLOCK_FO_GAIN, 0x2f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x7f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_FASTLOCK_COUNT_LOW, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_FASTLOCK_COUNT_HIGH, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_PI_CONTROLS, 0x99),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SB2_THRESH1, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SB2_THRESH2, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SB2_GAIN1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SB2_GAIN2, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_AUX_DATA_TCOARSE_TFINE, 0xa0),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_VGA_CAL_CNTRL1, 0x54),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_VGA_CAL_CNTRL2, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_GM_CAL, 0x13),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_EQU_ADAPTOR_CNTRL2, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_EQU_ADAPTOR_CNTRL3, 0x4a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_EQU_ADAPTOR_CNTRL4, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_IDAC_TSETTLE_LOW, 0x07),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_IDAC_TSETTLE_HIGH, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_EQ_OFFSET_ADAPTOR_CNTRL1, 0x47),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_SIGDET_CNTRL, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_SIGDET_DEGLITCH_CNTRL, 0x0e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_00_LOW, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_00_HIGH, 0xbf),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_00_HIGH2, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_00_HIGH3, 0xdf),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_00_HIGH4, 0xed),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_01_LOW, 0xdc),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_01_HIGH, 0x5c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_01_HIGH2, 0x9c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_01_HIGH3, 0x1d),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_01_HIGH4, 0x09),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_DFE_EN_TIMER, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_DFE_CTLE_POST_CAL_OFFSET, 0x38),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_DCC_CTRL1, 0x0c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_VTH_CODE, 0x10),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_SIGDET_CAL_CTRL1, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_SIGDET_CAL_TRIM, 0x08),
+};
+
+static const struct qmp_phy_init_tbl sdx75_usb3_uniphy_pcs_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG1, 0xc4),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG2, 0x89),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG3, 0x20),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG6, 0x13),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_REFGEN_REQ_CONFIG1, 0x21),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_RX_SIGDET_LVL, 0xaa),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_L, 0xe7),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_H, 0x03),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_CDR_RESET_TIME, 0x0a),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_ALIGN_DETECT_CONFIG1, 0x88),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_ALIGN_DETECT_CONFIG2, 0x13),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_PCS_TX_RX_CONFIG, 0x0c),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_EQ_CONFIG1, 0x4b),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_EQ_CONFIG5, 0x10),
+};
+
+static const struct qmp_phy_init_tbl sdx75_usb3_uniphy_pcs_usb_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_USB3_LFPS_DET_HIGH_COUNT_VAL, 0xf8),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_USB3_RXEQTRAINING_DFE_TIME_S2, 0x07),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_USB3_RCVR_DTCT_DLY_U3_L, 0x40),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_USB3_RCVR_DTCT_DLY_U3_H, 0x00),
+};
+
 static const struct qmp_phy_init_tbl sm8350_usb3_uniphy_tx_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_V5_TX_LANE_MODE_1, 0xa5),
 	QMP_PHY_INIT_CFG(QSERDES_V5_TX_LANE_MODE_2, 0x82),
@@ -1161,6 +1313,134 @@ static const struct qmp_phy_init_tbl sa8775p_usb3_uniphy_pcs_usb_tbl[] = {
 	QMP_PHY_INIT_CFG(QPHY_V5_PCS_USB3_POWER_STATE_CONFIG1, 0x6f),
 };
 
+static const struct qmp_phy_init_tbl x1e80100_usb3_uniphy_serdes_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_STEP_SIZE1_MODE1, 0xc0),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_STEP_SIZE2_MODE1, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_CP_CTRL_MODE1, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_PLL_RCTRL_MODE1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_PLL_CCTRL_MODE1, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_CORECLK_DIV_MODE1, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_LOCK_CMP1_MODE1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_LOCK_CMP2_MODE1, 0x41),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_DEC_START_MODE1, 0x41),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_DIV_FRAC_START1_MODE1, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_DIV_FRAC_START2_MODE1, 0x75),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_DIV_FRAC_START3_MODE1, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_HSCLK_SEL_1, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_VCO_TUNE1_MODE1, 0x25),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_VCO_TUNE2_MODE1, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE1_MODE1, 0x5c),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE2_MODE1, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE1_MODE0, 0x5c),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_STEP_SIZE1_MODE0, 0xc0),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_STEP_SIZE2_MODE0, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_CP_CTRL_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_PLL_RCTRL_MODE0, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_PLL_CCTRL_MODE0, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_LOCK_CMP1_MODE0, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_LOCK_CMP2_MODE0, 0x1a),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_DEC_START_MODE0, 0x41),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_DIV_FRAC_START1_MODE0, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_DIV_FRAC_START2_MODE0, 0x75),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_DIV_FRAC_START3_MODE0, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_VCO_TUNE1_MODE0, 0x25),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_VCO_TUNE2_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_BG_TIMER, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_EN_CENTER, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_PER1, 0x62),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_PER2, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_SYSCLK_BUF_ENABLE, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_SYSCLK_EN_SEL, 0x1a),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_LOCK_CMP_CFG, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_VCO_TUNE_MAP, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_CORE_CLK_EN, 0x20),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_CMN_CONFIG_1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_AUTO_GAIN_ADJ_CTRL_1, 0xb6),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_AUTO_GAIN_ADJ_CTRL_2, 0x4b),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_AUTO_GAIN_ADJ_CTRL_3, 0x37),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_ADDITIONAL_MISC, 0x0c),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_usb3_uniphy_tx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V7_TX_RES_CODE_LANE_TX, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V7_TX_RES_CODE_LANE_RX, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V7_TX_RES_CODE_LANE_OFFSET_TX, 0x1f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_TX_RES_CODE_LANE_OFFSET_RX, 0x09),
+	QMP_PHY_INIT_CFG(QSERDES_V7_TX_LANE_MODE_1, 0xf5),
+	QMP_PHY_INIT_CFG(QSERDES_V7_TX_LANE_MODE_3, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_TX_LANE_MODE_4, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_TX_LANE_MODE_5, 0x5f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_TX_RCV_DETECT_LVL_2, 0x12),
+	QMP_PHY_INIT_CFG(QSERDES_V7_TX_PI_QEC_CTRL, 0x21),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_usb3_uniphy_rx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_FO_GAIN, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_SO_GAIN, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_FASTLOCK_FO_GAIN, 0x2f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x7f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_FASTLOCK_COUNT_LOW, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_FASTLOCK_COUNT_HIGH, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_PI_CONTROLS, 0x99),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_SB2_THRESH1, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_SB2_THRESH2, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_SB2_GAIN1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_SB2_GAIN2, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_AUX_DATA_TCOARSE_TFINE, 0xa0),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_VGA_CAL_CNTRL1, 0x54),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_VGA_CAL_CNTRL2, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_GM_CAL, 0x13),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_EQU_ADAPTOR_CNTRL2, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_EQU_ADAPTOR_CNTRL3, 0x4a),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_EQU_ADAPTOR_CNTRL4, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_IDAC_TSETTLE_LOW, 0x07),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_IDAC_TSETTLE_HIGH, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_EQ_OFFSET_ADAPTOR_CNTRL1, 0x47),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_SIGDET_CNTRL, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_SIGDET_DEGLITCH_CNTRL, 0x0e),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_00_LOW, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_00_HIGH, 0xbf),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_00_HIGH2, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_00_HIGH3, 0xdf),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_00_HIGH4, 0xed),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_01_LOW, 0xdc),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_01_HIGH, 0x5c),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_01_HIGH2, 0x9c),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_01_HIGH3, 0x1d),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_01_HIGH4, 0x09),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_DFE_EN_TIMER, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_DFE_CTLE_POST_CAL_OFFSET, 0x38),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_DCC_CTRL1, 0x0c),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_VTH_CODE, 0x10),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_SIGDET_CAL_CTRL1, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_SIGDET_CAL_TRIM, 0x08),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_usb3_uniphy_pcs_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_LOCK_DETECT_CONFIG1, 0xc4),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_LOCK_DETECT_CONFIG2, 0x89),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_LOCK_DETECT_CONFIG3, 0x20),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_LOCK_DETECT_CONFIG6, 0x13),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_REFGEN_REQ_CONFIG1, 0x21),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_RX_SIGDET_LVL, 0xaa),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_RCVR_DTCT_DLY_P1U2_L, 0xe7),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_RCVR_DTCT_DLY_P1U2_H, 0x03),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_CDR_RESET_TIME, 0x0a),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_ALIGN_DETECT_CONFIG1, 0x88),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_ALIGN_DETECT_CONFIG2, 0x13),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_PCS_TX_RX_CONFIG, 0x0c),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_EQ_CONFIG1, 0x4b),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_EQ_CONFIG5, 0x10),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_usb3_uniphy_pcs_usb_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_USB3_LFPS_DET_HIGH_COUNT_VAL, 0xf8),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_USB3_RXEQTRAINING_DFE_TIME_S2, 0x07),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_USB3_RCVR_DTCT_DLY_U3_L, 0x40),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_USB3_RCVR_DTCT_DLY_U3_H, 0x00),
+};
+
 struct qmp_usb_offsets {
 	u16 serdes;
 	u16 pcs;
@@ -1276,6 +1556,14 @@ static const char * const qmp_phy_vreg_l[] = {
 	"vdda-phy", "vdda-pll",
 };
 
+static const struct qmp_usb_offsets qmp_usb_offsets_v3 = {
+	.serdes		= 0,
+	.pcs		= 0x800,
+	.pcs_misc	= 0x600,
+	.tx		= 0x200,
+	.rx		= 0x400,
+};
+
 static const struct qmp_usb_offsets qmp_usb_offsets_ipq9574 = {
 	.serdes		= 0,
 	.pcs		= 0x800,
@@ -1284,7 +1572,7 @@ static const struct qmp_usb_offsets qmp_usb_offsets_ipq9574 = {
 	.rx		= 0x400,
 };
 
-static const struct qmp_usb_offsets qmp_usb_offsets_v3 = {
+static const struct qmp_usb_offsets qmp_usb_offsets_v3_msm8996 = {
 	.serdes		= 0,
 	.pcs		= 0x600,
 	.tx		= 0x200,
@@ -1317,6 +1605,40 @@ static const struct qmp_usb_offsets qmp_usb_offsets_v5 = {
 	.rx		= 0x1000,
 };
 
+static const struct qmp_usb_offsets qmp_usb_offsets_v6 = {
+	.serdes		= 0,
+	.pcs		= 0x0200,
+	.pcs_usb	= 0x1200,
+	.tx		= 0x0e00,
+	.rx		= 0x1000,
+};
+
+static const struct qmp_usb_offsets qmp_usb_offsets_v7 = {
+	.serdes		= 0,
+	.pcs		= 0x0200,
+	.pcs_usb	= 0x1200,
+	.tx		= 0x0e00,
+	.rx		= 0x1000,
+};
+
+static const struct qmp_phy_cfg ipq6018_usb3phy_cfg = {
+	.lanes			= 1,
+
+	.offsets		= &qmp_usb_offsets_v3,
+
+	.serdes_tbl		= ipq9574_usb3_serdes_tbl,
+	.serdes_tbl_num		= ARRAY_SIZE(ipq9574_usb3_serdes_tbl),
+	.tx_tbl			= msm8996_usb3_tx_tbl,
+	.tx_tbl_num		= ARRAY_SIZE(msm8996_usb3_tx_tbl),
+	.rx_tbl			= ipq8074_usb3_rx_tbl,
+	.rx_tbl_num		= ARRAY_SIZE(ipq8074_usb3_rx_tbl),
+	.pcs_tbl		= ipq8074_usb3_pcs_tbl,
+	.pcs_tbl_num		= ARRAY_SIZE(ipq8074_usb3_pcs_tbl),
+	.vreg_list		= qmp_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(qmp_phy_vreg_l),
+	.regs			= qmp_v3_usb3phy_regs_layout,
+};
+
 static const struct qmp_phy_cfg ipq8074_usb3phy_cfg = {
 	.lanes			= 1,
 
@@ -1356,7 +1678,7 @@ static const struct qmp_phy_cfg ipq9574_usb3phy_cfg = {
 static const struct qmp_phy_cfg msm8996_usb3phy_cfg = {
 	.lanes			= 1,
 
-	.offsets		= &qmp_usb_offsets_v3,
+	.offsets		= &qmp_usb_offsets_v3_msm8996,
 
 	.serdes_tbl		= msm8996_usb3_serdes_tbl,
 	.serdes_tbl_num		= ARRAY_SIZE(msm8996_usb3_serdes_tbl),
@@ -1541,6 +1863,28 @@ static const struct qmp_phy_cfg sdx65_usb3_uniphy_cfg = {
 	.has_pwrdn_delay	= true,
 };
 
+static const struct qmp_phy_cfg sdx75_usb3_uniphy_cfg = {
+	.lanes			= 1,
+	.offsets		= &qmp_usb_offsets_v6,
+
+	.serdes_tbl		= sdx75_usb3_uniphy_serdes_tbl,
+	.serdes_tbl_num		= ARRAY_SIZE(sdx75_usb3_uniphy_serdes_tbl),
+	.tx_tbl			= sdx75_usb3_uniphy_tx_tbl,
+	.tx_tbl_num		= ARRAY_SIZE(sdx75_usb3_uniphy_tx_tbl),
+	.rx_tbl			= sdx75_usb3_uniphy_rx_tbl,
+	.rx_tbl_num		= ARRAY_SIZE(sdx75_usb3_uniphy_rx_tbl),
+	.pcs_tbl		= sdx75_usb3_uniphy_pcs_tbl,
+	.pcs_tbl_num		= ARRAY_SIZE(sdx75_usb3_uniphy_pcs_tbl),
+	.pcs_usb_tbl		= sdx75_usb3_uniphy_pcs_usb_tbl,
+	.pcs_usb_tbl_num	= ARRAY_SIZE(sdx75_usb3_uniphy_pcs_usb_tbl),
+	.vreg_list		= qmp_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(qmp_phy_vreg_l),
+	.regs			= qmp_v6_usb3phy_regs_layout,
+	.pcs_usb_offset		= 0x1000,
+
+	.has_pwrdn_delay	= true,
+};
+
 static const struct qmp_phy_cfg sm8350_usb3_uniphy_cfg = {
 	.lanes			= 1,
 
@@ -1582,6 +1926,26 @@ static const struct qmp_phy_cfg qcm2290_usb3phy_cfg = {
 	.regs			= qmp_v3_usb3phy_regs_layout_qcm2290,
 };
 
+static const struct qmp_phy_cfg x1e80100_usb3_uniphy_cfg = {
+	.lanes			= 1,
+
+	.offsets		= &qmp_usb_offsets_v7,
+
+	.serdes_tbl		= x1e80100_usb3_uniphy_serdes_tbl,
+	.serdes_tbl_num		= ARRAY_SIZE(x1e80100_usb3_uniphy_serdes_tbl),
+	.tx_tbl			= x1e80100_usb3_uniphy_tx_tbl,
+	.tx_tbl_num		= ARRAY_SIZE(x1e80100_usb3_uniphy_tx_tbl),
+	.rx_tbl			= x1e80100_usb3_uniphy_rx_tbl,
+	.rx_tbl_num		= ARRAY_SIZE(x1e80100_usb3_uniphy_rx_tbl),
+	.pcs_tbl		= x1e80100_usb3_uniphy_pcs_tbl,
+	.pcs_tbl_num		= ARRAY_SIZE(x1e80100_usb3_uniphy_pcs_tbl),
+	.pcs_usb_tbl		= x1e80100_usb3_uniphy_pcs_usb_tbl,
+	.pcs_usb_tbl_num	= ARRAY_SIZE(x1e80100_usb3_uniphy_pcs_usb_tbl),
+	.vreg_list		= qmp_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(qmp_phy_vreg_l),
+	.regs			= qmp_v7_usb3phy_regs_layout,
+};
+
 static void qmp_usb_configure_lane(void __iomem *base,
 					const struct qmp_phy_init_tbl tbl[],
 					int num,
@@ -2225,7 +2589,7 @@ err_node_put:
 static const struct of_device_id qmp_usb_of_match_table[] = {
 	{
 		.compatible = "qcom,ipq6018-qmp-usb3-phy",
-		.data = &ipq8074_usb3phy_cfg,
+		.data = &ipq6018_usb3phy_cfg,
 	}, {
 		.compatible = "qcom,ipq8074-qmp-usb3-phy",
 		.data = &ipq8074_usb3phy_cfg,
@@ -2257,6 +2621,9 @@ static const struct of_device_id qmp_usb_of_match_table[] = {
 		.compatible = "qcom,sdx65-qmp-usb3-uni-phy",
 		.data = &sdx65_usb3_uniphy_cfg,
 	}, {
+		.compatible = "qcom,sdx75-qmp-usb3-uni-phy",
+		.data = &sdx75_usb3_uniphy_cfg,
+	}, {
 		.compatible = "qcom,sm6115-qmp-usb3-phy",
 		.data = &qcm2290_usb3phy_cfg,
 	}, {
@@ -2268,6 +2635,9 @@ static const struct of_device_id qmp_usb_of_match_table[] = {
 	}, {
 		.compatible = "qcom,sm8350-qmp-usb3-uni-phy",
 		.data = &sm8350_usb3_uniphy_cfg,
+	}, {
+		.compatible = "qcom,x1e80100-qmp-usb3-uni-phy",
+		.data = &x1e80100_usb3_uniphy_cfg,
 	},
 	{ },
 };
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.h b/drivers/phy/qualcomm/phy-qcom-qmp.h
index 71f063f4a56e..6923496cbfee 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp.h
@@ -24,8 +24,12 @@
 #include "phy-qcom-qmp-qserdes-com-v6.h"
 #include "phy-qcom-qmp-qserdes-txrx-v6.h"
 #include "phy-qcom-qmp-qserdes-txrx-v6_20.h"
+#include "phy-qcom-qmp-qserdes-txrx-v6_n4.h"
 #include "phy-qcom-qmp-qserdes-ln-shrd-v6.h"
 
+#include "phy-qcom-qmp-qserdes-com-v7.h"
+#include "phy-qcom-qmp-qserdes-txrx-v7.h"
+
 #include "phy-qcom-qmp-qserdes-pll.h"
 
 #include "phy-qcom-qmp-pcs-v2.h"
@@ -44,6 +48,8 @@
 
 #include "phy-qcom-qmp-pcs-v6_20.h"
 
+#include "phy-qcom-qmp-pcs-v7.h"
+
 /* Only for QMP V3 & V4 PHY - DP COM registers */
 #define QPHY_V3_DP_COM_PHY_MODE_CTRL			0x00
 #define QPHY_V3_DP_COM_SW_RESET				0x04
diff --git a/drivers/phy/renesas/Kconfig b/drivers/phy/renesas/Kconfig
index 36505fc5f386..e342eef0640b 100644
--- a/drivers/phy/renesas/Kconfig
+++ b/drivers/phy/renesas/Kconfig
@@ -13,7 +13,7 @@ config PHY_R8A779F0_ETHERNET_SERDES
 config PHY_RCAR_GEN2
 	tristate "Renesas R-Car generation 2 USB PHY driver"
 	depends on ARCH_RENESAS
-	depends on GENERIC_PHY
+	select GENERIC_PHY
 	help
 	  Support for USB PHY found on Renesas R-Car generation 2 SoCs.
 
diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
index e53eace7c91e..6387c0d34c55 100644
--- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c
+++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
@@ -673,8 +673,6 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
 	channel->irq = platform_get_irq_optional(pdev, 0);
 	channel->dr_mode = rcar_gen3_get_dr_mode(dev->of_node);
 	if (channel->dr_mode != USB_DR_MODE_UNKNOWN) {
-		int ret;
-
 		channel->is_otg_channel = true;
 		channel->uses_otg_pins = !of_property_read_bool(dev->of_node,
 							"renesas,no-otg-pins");
@@ -738,8 +736,6 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
 		ret = PTR_ERR(provider);
 		goto error;
 	} else if (channel->is_otg_channel) {
-		int ret;
-
 		ret = device_create_file(dev, &dev_attr_role);
 		if (ret < 0)
 			goto error;
diff --git a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
index a24d2af154df..4f71373ae6e1 100644
--- a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
+++ b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
@@ -123,9 +123,12 @@ struct rockchip_chg_det_reg {
  * @disrise_en: host disconnect rise edge detection enable.
  * @disrise_st: host disconnect rise edge detection state.
  * @disrise_clr: host disconnect rise edge detection clear.
- * @id_det_en: id detection enable register.
- * @id_det_st: id detection state register.
- * @id_det_clr: id detection clear register.
+ * @idfall_det_en: id detection enable register, falling edge
+ * @idfall_det_st: id detection state register, falling edge
+ * @idfall_det_clr: id detection clear register, falling edge
+ * @idrise_det_en: id detection enable register, rising edge
+ * @idrise_det_st: id detection state register, rising edge
+ * @idrise_det_clr: id detection clear register, rising edge
  * @ls_det_en: linestate detection enable register.
  * @ls_det_st: linestate detection state register.
  * @ls_det_clr: linestate detection clear register.
@@ -146,9 +149,12 @@ struct rockchip_usb2phy_port_cfg {
 	struct usb2phy_reg      disrise_en;
 	struct usb2phy_reg      disrise_st;
 	struct usb2phy_reg      disrise_clr;
-	struct usb2phy_reg	id_det_en;
-	struct usb2phy_reg	id_det_st;
-	struct usb2phy_reg	id_det_clr;
+	struct usb2phy_reg	idfall_det_en;
+	struct usb2phy_reg	idfall_det_st;
+	struct usb2phy_reg	idfall_det_clr;
+	struct usb2phy_reg	idrise_det_en;
+	struct usb2phy_reg	idrise_det_st;
+	struct usb2phy_reg	idrise_det_clr;
 	struct usb2phy_reg	ls_det_en;
 	struct usb2phy_reg	ls_det_st;
 	struct usb2phy_reg	ls_det_clr;
@@ -488,15 +494,27 @@ static int rockchip_usb2phy_init(struct phy *phy)
 			if (ret)
 				goto out;
 
-			/* clear id status and enable id detect irq */
+			/* clear id status and enable id detect irqs */
 			ret = property_enable(rphy->grf,
-					      &rport->port_cfg->id_det_clr,
+					      &rport->port_cfg->idfall_det_clr,
 					      true);
 			if (ret)
 				goto out;
 
 			ret = property_enable(rphy->grf,
-					      &rport->port_cfg->id_det_en,
+					      &rport->port_cfg->idrise_det_clr,
+					      true);
+			if (ret)
+				goto out;
+
+			ret = property_enable(rphy->grf,
+					      &rport->port_cfg->idfall_det_en,
+					      true);
+			if (ret)
+				goto out;
+
+			ret = property_enable(rphy->grf,
+					      &rport->port_cfg->idrise_det_en,
 					      true);
 			if (ret)
 				goto out;
@@ -1030,11 +1048,16 @@ static irqreturn_t rockchip_usb2phy_id_irq(int irq, void *data)
 	struct rockchip_usb2phy *rphy = dev_get_drvdata(rport->phy->dev.parent);
 	bool id;
 
-	if (!property_enabled(rphy->grf, &rport->port_cfg->id_det_st))
+	if (!property_enabled(rphy->grf, &rport->port_cfg->idfall_det_st) &&
+	    !property_enabled(rphy->grf, &rport->port_cfg->idrise_det_st))
 		return IRQ_NONE;
 
 	/* clear id detect irq pending status */
-	property_enable(rphy->grf, &rport->port_cfg->id_det_clr, true);
+	if (property_enabled(rphy->grf, &rport->port_cfg->idfall_det_st))
+		property_enable(rphy->grf, &rport->port_cfg->idfall_det_clr, true);
+
+	if (property_enabled(rphy->grf, &rport->port_cfg->idrise_det_st))
+		property_enable(rphy->grf, &rport->port_cfg->idrise_det_clr, true);
 
 	id = property_enabled(rphy->grf, &rport->port_cfg->utmi_id);
 	extcon_set_state_sync(rphy->edev, EXTCON_USB_HOST, !id);
@@ -1464,6 +1487,14 @@ put_child:
 	return ret;
 }
 
+static int rk3128_usb2phy_tuning(struct rockchip_usb2phy *rphy)
+{
+	/* Turn off differential receiver in suspend mode */
+	return regmap_write_bits(rphy->grf, 0x298,
+				BIT(2) << BIT_WRITEABLE_SHIFT | BIT(2),
+				BIT(2) << BIT_WRITEABLE_SHIFT | 0);
+}
+
 static int rk3588_usb2phy_tuning(struct rockchip_usb2phy *rphy)
 {
 	int ret;
@@ -1513,6 +1544,54 @@ static int rk3588_usb2phy_tuning(struct rockchip_usb2phy *rphy)
 	return ret;
 }
 
+static const struct rockchip_usb2phy_cfg rk3128_phy_cfgs[] = {
+	{
+		.reg = 0x17c,
+		.num_ports	= 2,
+		.phy_tuning	= rk3128_usb2phy_tuning,
+		.clkout_ctl	= { 0x0190, 15, 15, 1, 0 },
+		.port_cfgs	= {
+			[USB2PHY_PORT_OTG] = {
+				.phy_sus	= { 0x017c, 8, 0, 0, 0x1d1 },
+				.bvalid_det_en	= { 0x017c, 14, 14, 0, 1 },
+				.bvalid_det_st	= { 0x017c, 15, 15, 0, 1 },
+				.bvalid_det_clr	= { 0x017c, 15, 15, 0, 1 },
+				.idfall_det_en  = { 0x01a0, 2, 2, 0, 1 },
+				.idfall_det_st  = { 0x01a0, 3, 3, 0, 1 },
+				.idfall_det_clr = { 0x01a0, 3, 3, 0, 1 },
+				.idrise_det_en  = { 0x01a0, 0, 0, 0, 1 },
+				.idrise_det_st  = { 0x01a0, 1, 1, 0, 1 },
+				.idrise_det_clr = { 0x01a0, 1, 1, 0, 1 },
+				.ls_det_en	= { 0x017c, 12, 12, 0, 1 },
+				.ls_det_st	= { 0x017c, 13, 13, 0, 1 },
+				.ls_det_clr	= { 0x017c, 13, 13, 0, 1 },
+				.utmi_bvalid	= { 0x014c, 5, 5, 0, 1 },
+				.utmi_id	= { 0x014c, 8, 8, 0, 1 },
+				.utmi_ls	= { 0x014c, 7, 6, 0, 1 },
+			},
+			[USB2PHY_PORT_HOST] = {
+				.phy_sus	= { 0x0194, 8, 0, 0, 0x1d1 },
+				.ls_det_en	= { 0x0194, 14, 14, 0, 1 },
+				.ls_det_st	= { 0x0194, 15, 15, 0, 1 },
+				.ls_det_clr	= { 0x0194, 15, 15, 0, 1 }
+			}
+		},
+		.chg_det = {
+			.opmode		= { 0x017c, 3, 0, 5, 1 },
+			.cp_det		= { 0x02c0, 6, 6, 0, 1 },
+			.dcp_det	= { 0x02c0, 5, 5, 0, 1 },
+			.dp_det		= { 0x02c0, 7, 7, 0, 1 },
+			.idm_sink_en	= { 0x0184, 8, 8, 0, 1 },
+			.idp_sink_en	= { 0x0184, 7, 7, 0, 1 },
+			.idp_src_en	= { 0x0184, 9, 9, 0, 1 },
+			.rdm_pdwn_en	= { 0x0184, 10, 10, 0, 1 },
+			.vdm_src_en	= { 0x0184, 12, 12, 0, 1 },
+			.vdp_src_en	= { 0x0184, 11, 11, 0, 1 },
+		},
+	},
+	{ /* sentinel */ }
+};
+
 static const struct rockchip_usb2phy_cfg rk3228_phy_cfgs[] = {
 	{
 		.reg = 0x760,
@@ -1524,9 +1603,12 @@ static const struct rockchip_usb2phy_cfg rk3228_phy_cfgs[] = {
 				.bvalid_det_en	= { 0x0680, 3, 3, 0, 1 },
 				.bvalid_det_st	= { 0x0690, 3, 3, 0, 1 },
 				.bvalid_det_clr	= { 0x06a0, 3, 3, 0, 1 },
-				.id_det_en	= { 0x0680, 6, 5, 0, 3 },
-				.id_det_st	= { 0x0690, 6, 5, 0, 3 },
-				.id_det_clr	= { 0x06a0, 6, 5, 0, 3 },
+				.idfall_det_en	= { 0x0680, 6, 6, 0, 1 },
+				.idfall_det_st	= { 0x0690, 6, 6, 0, 1 },
+				.idfall_det_clr	= { 0x06a0, 6, 6, 0, 1 },
+				.idrise_det_en	= { 0x0680, 5, 5, 0, 1 },
+				.idrise_det_st	= { 0x0690, 5, 5, 0, 1 },
+				.idrise_det_clr	= { 0x06a0, 5, 5, 0, 1 },
 				.ls_det_en	= { 0x0680, 2, 2, 0, 1 },
 				.ls_det_st	= { 0x0690, 2, 2, 0, 1 },
 				.ls_det_clr	= { 0x06a0, 2, 2, 0, 1 },
@@ -1587,9 +1669,12 @@ static const struct rockchip_usb2phy_cfg rk3308_phy_cfgs[] = {
 				.bvalid_det_en	= { 0x3020, 3, 2, 0, 3 },
 				.bvalid_det_st	= { 0x3024, 3, 2, 0, 3 },
 				.bvalid_det_clr = { 0x3028, 3, 2, 0, 3 },
-				.id_det_en	= { 0x3020, 5, 4, 0, 3 },
-				.id_det_st	= { 0x3024, 5, 4, 0, 3 },
-				.id_det_clr	= { 0x3028, 5, 4, 0, 3 },
+				.idfall_det_en	= { 0x3020, 5, 5, 0, 1 },
+				.idfall_det_st	= { 0x3024, 5, 5, 0, 1 },
+				.idfall_det_clr = { 0x3028, 5, 5, 0, 1 },
+				.idrise_det_en	= { 0x3020, 4, 4, 0, 1 },
+				.idrise_det_st	= { 0x3024, 4, 4, 0, 1 },
+				.idrise_det_clr = { 0x3028, 4, 4, 0, 1 },
 				.ls_det_en	= { 0x3020, 0, 0, 0, 1 },
 				.ls_det_st	= { 0x3024, 0, 0, 0, 1 },
 				.ls_det_clr	= { 0x3028, 0, 0, 0, 1 },
@@ -1634,9 +1719,12 @@ static const struct rockchip_usb2phy_cfg rk3328_phy_cfgs[] = {
 				.bvalid_det_en	= { 0x0110, 3, 2, 0, 3 },
 				.bvalid_det_st	= { 0x0114, 3, 2, 0, 3 },
 				.bvalid_det_clr = { 0x0118, 3, 2, 0, 3 },
-				.id_det_en	= { 0x0110, 5, 4, 0, 3 },
-				.id_det_st	= { 0x0114, 5, 4, 0, 3 },
-				.id_det_clr	= { 0x0118, 5, 4, 0, 3 },
+				.idfall_det_en	= { 0x0110, 5, 5, 0, 1 },
+				.idfall_det_st	= { 0x0114, 5, 5, 0, 1 },
+				.idfall_det_clr = { 0x0118, 5, 5, 0, 1 },
+				.idrise_det_en	= { 0x0110, 4, 4, 0, 1 },
+				.idrise_det_st	= { 0x0114, 4, 4, 0, 1 },
+				.idrise_det_clr = { 0x0118, 4, 4, 0, 1 },
 				.ls_det_en	= { 0x0110, 0, 0, 0, 1 },
 				.ls_det_st	= { 0x0114, 0, 0, 0, 1 },
 				.ls_det_clr	= { 0x0118, 0, 0, 0, 1 },
@@ -1700,9 +1788,12 @@ static const struct rockchip_usb2phy_cfg rk3399_phy_cfgs[] = {
 				.bvalid_det_en	= { 0xe3c0, 3, 3, 0, 1 },
 				.bvalid_det_st	= { 0xe3e0, 3, 3, 0, 1 },
 				.bvalid_det_clr	= { 0xe3d0, 3, 3, 0, 1 },
-				.id_det_en	= { 0xe3c0, 5, 4, 0, 3 },
-				.id_det_st	= { 0xe3e0, 5, 4, 0, 3 },
-				.id_det_clr	= { 0xe3d0, 5, 4, 0, 3 },
+				.idfall_det_en	= { 0xe3c0, 5, 5, 0, 1 },
+				.idfall_det_st	= { 0xe3e0, 5, 5, 0, 1 },
+				.idfall_det_clr	= { 0xe3d0, 5, 5, 0, 1 },
+				.idrise_det_en	= { 0xe3c0, 4, 4, 0, 1 },
+				.idrise_det_st	= { 0xe3e0, 4, 4, 0, 1 },
+				.idrise_det_clr	= { 0xe3d0, 4, 4, 0, 1 },
 				.utmi_avalid	= { 0xe2ac, 7, 7, 0, 1 },
 				.utmi_bvalid	= { 0xe2ac, 12, 12, 0, 1 },
 				.utmi_id	= { 0xe2ac, 8, 8, 0, 1 },
@@ -1739,9 +1830,12 @@ static const struct rockchip_usb2phy_cfg rk3399_phy_cfgs[] = {
 				.bvalid_det_en  = { 0xe3c0, 8, 8, 0, 1 },
 				.bvalid_det_st  = { 0xe3e0, 8, 8, 0, 1 },
 				.bvalid_det_clr = { 0xe3d0, 8, 8, 0, 1 },
-				.id_det_en	= { 0xe3c0, 10, 9, 0, 3 },
-				.id_det_st	= { 0xe3e0, 10, 9, 0, 3 },
-				.id_det_clr	= { 0xe3d0, 10, 9, 0, 3 },
+				.idfall_det_en	= { 0xe3c0, 10, 10, 0, 1 },
+				.idfall_det_st	= { 0xe3e0, 10, 10, 0, 1 },
+				.idfall_det_clr	= { 0xe3d0, 10, 10, 0, 1 },
+				.idrise_det_en	= { 0xe3c0, 9, 9, 0, 1 },
+				.idrise_det_st	= { 0xe3e0, 9, 9, 0, 1 },
+				.idrise_det_clr	= { 0xe3d0, 9, 9, 0, 1 },
 				.utmi_avalid	= { 0xe2ac, 10, 10, 0, 1 },
 				.utmi_bvalid    = { 0xe2ac, 16, 16, 0, 1 },
 				.utmi_id	= { 0xe2ac, 11, 11, 0, 1 },
@@ -1770,9 +1864,12 @@ static const struct rockchip_usb2phy_cfg rk3568_phy_cfgs[] = {
 				.bvalid_det_en	= { 0x0080, 3, 2, 0, 3 },
 				.bvalid_det_st	= { 0x0084, 3, 2, 0, 3 },
 				.bvalid_det_clr = { 0x0088, 3, 2, 0, 3 },
-				.id_det_en	= { 0x0080, 5, 4, 0, 3 },
-				.id_det_st	= { 0x0084, 5, 4, 0, 3 },
-				.id_det_clr	= { 0x0088, 5, 4, 0, 3 },
+				.idfall_det_en	= { 0x0080, 5, 5, 0, 1 },
+				.idfall_det_st	= { 0x0084, 5, 5, 0, 1 },
+				.idfall_det_clr	= { 0x0088, 5, 5, 0, 1 },
+				.idrise_det_en	= { 0x0080, 4, 4, 0, 1 },
+				.idrise_det_st	= { 0x0084, 4, 4, 0, 1 },
+				.idrise_det_clr	= { 0x0088, 4, 4, 0, 1 },
 				.utmi_avalid	= { 0x00c0, 10, 10, 0, 1 },
 				.utmi_bvalid	= { 0x00c0, 9, 9, 0, 1 },
 				.utmi_id	= { 0x00c0, 6, 6, 0, 1 },
@@ -1990,6 +2087,7 @@ static const struct rockchip_usb2phy_cfg rv1108_phy_cfgs[] = {
 
 static const struct of_device_id rockchip_usb2phy_dt_match[] = {
 	{ .compatible = "rockchip,px30-usb2phy", .data = &rk3328_phy_cfgs },
+	{ .compatible = "rockchip,rk3128-usb2phy", .data = &rk3128_phy_cfgs },
 	{ .compatible = "rockchip,rk3228-usb2phy", .data = &rk3228_phy_cfgs },
 	{ .compatible = "rockchip,rk3308-usb2phy", .data = &rk3308_phy_cfgs },
 	{ .compatible = "rockchip,rk3328-usb2phy", .data = &rk3328_phy_cfgs },
diff --git a/drivers/phy/ti/phy-gmii-sel.c b/drivers/phy/ti/phy-gmii-sel.c
index bc847d3879f7..0f4818adb440 100644
--- a/drivers/phy/ti/phy-gmii-sel.c
+++ b/drivers/phy/ti/phy-gmii-sel.c
@@ -248,7 +248,7 @@ static const
 struct phy_gmii_sel_soc_data phy_gmii_sel_cpsw9g_soc_j784s4 = {
 	.use_of_data = true,
 	.regfields = phy_gmii_sel_fields_am654,
-	.extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) |
+	.extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) | BIT(PHY_INTERFACE_MODE_SGMII) |
 		       BIT(PHY_INTERFACE_MODE_USXGMII),
 	.num_ports = 8,
 	.num_qsgmii_main_ports = 2,
diff --git a/drivers/phy/ti/phy-j721e-wiz.c b/drivers/phy/ti/phy-j721e-wiz.c
index fc3cd98c60ff..00d7e6a6de03 100644
--- a/drivers/phy/ti/phy-j721e-wiz.c
+++ b/drivers/phy/ti/phy-j721e-wiz.c
@@ -1240,6 +1240,7 @@ static int wiz_phy_fullrt_div(struct wiz *wiz, int lane)
 	case J721E_WIZ_10G:
 	case J7200_WIZ_10G:
 	case J721S2_WIZ_10G:
+	case J784S4_WIZ_10G:
 		if (wiz->lane_phy_type[lane] == PHY_TYPE_SGMII)
 			return regmap_field_write(wiz->p0_fullrt_div[lane], 0x2);
 		break;
diff --git a/drivers/phy/ti/phy-omap-usb2.c b/drivers/phy/ti/phy-omap-usb2.c
index dd2913ac0fa2..78e19b128962 100644
--- a/drivers/phy/ti/phy-omap-usb2.c
+++ b/drivers/phy/ti/phy-omap-usb2.c
@@ -117,7 +117,7 @@ static int omap_usb_set_vbus(struct usb_otg *otg, bool enabled)
 {
 	struct omap_usb *phy = phy_to_omapusb(otg->usb_phy);
 
-	if (!phy->comparator)
+	if (!phy->comparator || !phy->comparator->set_vbus)
 		return -ENODEV;
 
 	return phy->comparator->set_vbus(phy->comparator, enabled);
@@ -127,7 +127,7 @@ static int omap_usb_start_srp(struct usb_otg *otg)
 {
 	struct omap_usb *phy = phy_to_omapusb(otg->usb_phy);
 
-	if (!phy->comparator)
+	if (!phy->comparator || !phy->comparator->start_srp)
 		return -ENODEV;
 
 	return phy->comparator->start_srp(phy->comparator);
diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index b11144bb448c..8163a5983166 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -484,6 +484,22 @@ config PINCTRL_TB10X
 	depends on OF && ARC_PLAT_TB10X
 	select GPIOLIB
 
+config PINCTRL_TPS6594
+	tristate "Pinctrl and GPIO driver for TI TPS6594 PMIC"
+	depends on OF && MFD_TPS6594
+	default MFD_TPS6594
+	select PINMUX
+	select GPIOLIB
+	select REGMAP
+	select GPIO_REGMAP
+	select GENERIC_PINCONF
+	help
+	  Say Y to select the pinmuxing and GPIOs driver for the TPS6594
+	  PMICs chip family.
+
+	  This driver can also be built as a module
+	  called tps6594-pinctrl.
+
 config PINCTRL_ZYNQ
 	bool "Pinctrl driver for Xilinx Zynq"
 	depends on ARCH_ZYNQ
diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile
index 7ac5d59c83e7..1071f301cc70 100644
--- a/drivers/pinctrl/Makefile
+++ b/drivers/pinctrl/Makefile
@@ -49,6 +49,7 @@ obj-$(CONFIG_PINCTRL_ST) 	+= pinctrl-st.o
 obj-$(CONFIG_PINCTRL_STMFX) 	+= pinctrl-stmfx.o
 obj-$(CONFIG_PINCTRL_SX150X)	+= pinctrl-sx150x.o
 obj-$(CONFIG_PINCTRL_TB10X)	+= pinctrl-tb10x.o
+obj-$(CONFIG_PINCTRL_TPS6594)	+= pinctrl-tps6594.o
 obj-$(CONFIG_PINCTRL_ZYNQMP)	+= pinctrl-zynqmp.o
 obj-$(CONFIG_PINCTRL_ZYNQ)	+= pinctrl-zynq.o
 
diff --git a/drivers/pinctrl/bcm/pinctrl-ns.c b/drivers/pinctrl/bcm/pinctrl-ns.c
index d099a7f25f64..6bb2b461950b 100644
--- a/drivers/pinctrl/bcm/pinctrl-ns.c
+++ b/drivers/pinctrl/bcm/pinctrl-ns.c
@@ -171,8 +171,8 @@ static int ns_pinctrl_set_mux(struct pinctrl_dev *pctrl_dev,
 	if (!group)
 		return -EINVAL;
 
-	for (i = 0; i < group->num_pins; i++)
-		unset |= BIT(group->pins[i]);
+	for (i = 0; i < group->grp.npins; i++)
+		unset |= BIT(group->grp.pins[i]);
 
 	tmp = readl(ns_pinctrl->base);
 	tmp &= ~unset;
diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index f2977eb65522..bbcdece83bf4 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -13,6 +13,7 @@
 #define pr_fmt(fmt) "pinctrl core: " fmt
 
 #include <linux/array_size.h>
+#include <linux/cleanup.h>
 #include <linux/debugfs.h>
 #include <linux/device.h>
 #include <linux/err.h>
@@ -23,6 +24,7 @@
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 
+#include <linux/gpio.h>
 #include <linux/gpio/driver.h>
 
 #include <linux/pinctrl/consumer.h>
@@ -30,10 +32,6 @@
 #include <linux/pinctrl/machine.h>
 #include <linux/pinctrl/pinctrl.h>
 
-#ifdef CONFIG_GPIOLIB
-#include "../gpio/gpiolib.h"
-#endif
-
 #include "core.h"
 #include "devicetree.h"
 #include "pinconf.h"
@@ -145,7 +143,7 @@ struct pinctrl_dev *get_pinctrl_dev_from_of_node(struct device_node *np)
  */
 int pin_get_from_name(struct pinctrl_dev *pctldev, const char *name)
 {
-	unsigned i, pin;
+	unsigned int i, pin;
 
 	/* The pin number can be retrived from the pin controller descriptor */
 	for (i = 0; i < pctldev->desc->npins; i++) {
@@ -166,7 +164,7 @@ int pin_get_from_name(struct pinctrl_dev *pctldev, const char *name)
  * @pctldev: the pin control device to lookup the pin on
  * @pin: pin number/id to look up
  */
-const char *pin_get_name(struct pinctrl_dev *pctldev, const unsigned pin)
+const char *pin_get_name(struct pinctrl_dev *pctldev, const unsigned int pin)
 {
 	const struct pin_desc *desc;
 
@@ -184,7 +182,7 @@ EXPORT_SYMBOL_GPL(pin_get_name);
 /* Deletes a range of pin descriptors */
 static void pinctrl_free_pindescs(struct pinctrl_dev *pctldev,
 				  const struct pinctrl_pin_desc *pins,
-				  unsigned num_pins)
+				  unsigned int num_pins)
 {
 	int i;
 
@@ -252,9 +250,9 @@ failed:
 
 static int pinctrl_register_pins(struct pinctrl_dev *pctldev,
 				 const struct pinctrl_pin_desc *pins,
-				 unsigned num_descs)
+				 unsigned int num_descs)
 {
-	unsigned i;
+	unsigned int i;
 	int ret = 0;
 
 	for (i = 0; i < num_descs; i++) {
@@ -428,7 +426,7 @@ EXPORT_SYMBOL_GPL(pinctrl_add_gpio_range);
 
 void pinctrl_add_gpio_ranges(struct pinctrl_dev *pctldev,
 			     struct pinctrl_gpio_range *ranges,
-			     unsigned nranges)
+			     unsigned int nranges)
 {
 	int i;
 
@@ -459,7 +457,7 @@ struct pinctrl_dev *pinctrl_find_and_add_gpio_range(const char *devname,
 EXPORT_SYMBOL_GPL(pinctrl_find_and_add_gpio_range);
 
 int pinctrl_get_group_pins(struct pinctrl_dev *pctldev, const char *pin_group,
-				const unsigned **pins, unsigned *num_pins)
+			   const unsigned int **pins, unsigned int *num_pins)
 {
 	const struct pinctrl_ops *pctlops = pctldev->desc->pctlops;
 	int gs;
@@ -559,7 +557,7 @@ const char *pinctrl_generic_get_group_name(struct pinctrl_dev *pctldev,
 	if (!group)
 		return NULL;
 
-	return group->name;
+	return group->grp.name;
 }
 EXPORT_SYMBOL_GPL(pinctrl_generic_get_group_name);
 
@@ -585,8 +583,8 @@ int pinctrl_generic_get_group_pins(struct pinctrl_dev *pctldev,
 		return -EINVAL;
 	}
 
-	*pins = group->pins;
-	*num_pins = group->num_pins;
+	*pins = group->grp.pins;
+	*num_pins = group->grp.npins;
 
 	return 0;
 }
@@ -642,7 +640,7 @@ static int pinctrl_generic_group_name_to_selector(struct pinctrl_dev *pctldev,
  * Note that the caller must take care of locking.
  */
 int pinctrl_generic_add_group(struct pinctrl_dev *pctldev, const char *name,
-			      int *pins, int num_pins, void *data)
+			      const unsigned int *pins, int num_pins, void *data)
 {
 	struct group_desc *group;
 	int selector, error;
@@ -660,10 +658,7 @@ int pinctrl_generic_add_group(struct pinctrl_dev *pctldev, const char *name,
 	if (!group)
 		return -ENOMEM;
 
-	group->name = name;
-	group->pins = pins;
-	group->num_pins = num_pins;
-	group->data = data;
+	*group = PINCTRL_GROUP_DESC(name, pins, num_pins, data);
 
 	error = radix_tree_insert(&pctldev->pin_group_tree, selector, group);
 	if (error)
@@ -734,8 +729,8 @@ int pinctrl_get_group_selector(struct pinctrl_dev *pctldev,
 			       const char *pin_group)
 {
 	const struct pinctrl_ops *pctlops = pctldev->desc->pctlops;
-	unsigned ngroups = pctlops->get_groups_count(pctldev);
-	unsigned group_selector = 0;
+	unsigned int ngroups = pctlops->get_groups_count(pctldev);
+	unsigned int group_selector = 0;
 
 	while (group_selector < ngroups) {
 		const char *gname = pctlops->get_group_name(pctldev,
@@ -1432,7 +1427,7 @@ EXPORT_SYMBOL_GPL(devm_pinctrl_put);
  * @num_maps: the number of maps in the mapping table
  */
 int pinctrl_register_mappings(const struct pinctrl_map *maps,
-			      unsigned num_maps)
+			      unsigned int num_maps)
 {
 	int i, ret;
 	struct pinctrl_maps *maps_node;
@@ -1647,10 +1642,10 @@ static int pinctrl_pins_show(struct seq_file *s, void *what)
 {
 	struct pinctrl_dev *pctldev = s->private;
 	const struct pinctrl_ops *ops = pctldev->desc->pctlops;
-	unsigned i, pin;
+	unsigned int i, pin;
 #ifdef CONFIG_GPIOLIB
+	struct gpio_device *gdev = NULL;
 	struct pinctrl_gpio_range *range;
-	struct gpio_chip *chip;
 	int gpio_num;
 #endif
 
@@ -1685,11 +1680,11 @@ static int pinctrl_pins_show(struct seq_file *s, void *what)
 			 * we need to get rid of the range->base eventually and
 			 * get the descriptor directly from the gpio_chip.
 			 */
-			chip = gpiod_to_chip(gpio_to_desc(gpio_num));
-		else
-			chip = NULL;
-		if (chip)
-			seq_printf(s, "%u:%s ", gpio_num - chip->gpiodev->base, chip->label);
+			gdev = gpiod_to_gpio_device(gpio_to_desc(gpio_num));
+		if (gdev)
+			seq_printf(s, "%u:%s ",
+				   gpio_num - gpio_device_get_base(gdev),
+				   gpio_device_get_label(gdev));
 		else
 			seq_puts(s, "0:? ");
 #endif
@@ -1711,7 +1706,7 @@ static int pinctrl_groups_show(struct seq_file *s, void *what)
 {
 	struct pinctrl_dev *pctldev = s->private;
 	const struct pinctrl_ops *ops = pctldev->desc->pctlops;
-	unsigned ngroups, selector = 0;
+	unsigned int ngroups, selector = 0;
 
 	mutex_lock(&pctldev->mutex);
 
@@ -1719,8 +1714,8 @@ static int pinctrl_groups_show(struct seq_file *s, void *what)
 
 	seq_puts(s, "registered pin groups:\n");
 	while (selector < ngroups) {
-		const unsigned *pins = NULL;
-		unsigned num_pins = 0;
+		const unsigned int *pins = NULL;
+		unsigned int num_pins = 0;
 		const char *gname = ops->get_group_name(pctldev, selector);
 		const char *pname;
 		int ret = 0;
diff --git a/drivers/pinctrl/core.h b/drivers/pinctrl/core.h
index 530370443c19..837fd5bd903d 100644
--- a/drivers/pinctrl/core.h
+++ b/drivers/pinctrl/core.h
@@ -111,8 +111,8 @@ struct pinctrl_state {
  * @func: the function selector to program
  */
 struct pinctrl_setting_mux {
-	unsigned group;
-	unsigned func;
+	unsigned int group;
+	unsigned int func;
 };
 
 /**
@@ -124,9 +124,9 @@ struct pinctrl_setting_mux {
  * @num_configs: the number of entries in array @configs
  */
 struct pinctrl_setting_configs {
-	unsigned group_or_pin;
+	unsigned int group_or_pin;
 	unsigned long *configs;
-	unsigned num_configs;
+	unsigned int num_configs;
 };
 
 /**
@@ -173,7 +173,7 @@ struct pin_desc {
 	void *drv_data;
 	/* These fields only added when supporting pinmux drivers */
 #ifdef CONFIG_PINMUX
-	unsigned mux_usecount;
+	unsigned int mux_usecount;
 	const char *mux_owner;
 	const struct pinctrl_setting_mux *mux_setting;
 	const char *gpio_owner;
@@ -189,25 +189,30 @@ struct pin_desc {
 struct pinctrl_maps {
 	struct list_head node;
 	const struct pinctrl_map *maps;
-	unsigned num_maps;
+	unsigned int num_maps;
 };
 
 #ifdef CONFIG_GENERIC_PINCTRL_GROUPS
 
+#include <linux/pinctrl/pinctrl.h>
+
 /**
  * struct group_desc - generic pin group descriptor
- * @name: name of the pin group
- * @pins: array of pins that belong to the group
- * @num_pins: number of pins in the group
+ * @grp: generic data of the pin group (name and pins)
  * @data: pin controller driver specific data
  */
 struct group_desc {
-	const char *name;
-	int *pins;
-	int num_pins;
+	struct pingroup grp;
 	void *data;
 };
 
+/* Convenience macro to define a generic pin group descriptor */
+#define PINCTRL_GROUP_DESC(_name, _pins, _num_pins, _data)	\
+(struct group_desc) {						\
+	.grp = PINCTRL_PINGROUP(_name, _pins, _num_pins),	\
+	.data = _data,						\
+}
+
 int pinctrl_generic_get_group_count(struct pinctrl_dev *pctldev);
 
 const char *pinctrl_generic_get_group_name(struct pinctrl_dev *pctldev,
@@ -222,7 +227,7 @@ struct group_desc *pinctrl_generic_get_group(struct pinctrl_dev *pctldev,
 					     unsigned int group_selector);
 
 int pinctrl_generic_add_group(struct pinctrl_dev *pctldev, const char *name,
-			      int *gpins, int ngpins, void *data);
+			      const unsigned int *pins, int num_pins, void *data);
 
 int pinctrl_generic_remove_group(struct pinctrl_dev *pctldev,
 				 unsigned int group_selector);
@@ -232,7 +237,7 @@ int pinctrl_generic_remove_group(struct pinctrl_dev *pctldev,
 struct pinctrl_dev *get_pinctrl_dev_from_devname(const char *dev_name);
 struct pinctrl_dev *get_pinctrl_dev_from_of_node(struct device_node *np);
 int pin_get_from_name(struct pinctrl_dev *pctldev, const char *name);
-const char *pin_get_name(struct pinctrl_dev *pctldev, const unsigned pin);
+const char *pin_get_name(struct pinctrl_dev *pctldev, const unsigned int pin);
 int pinctrl_get_group_selector(struct pinctrl_dev *pctldev,
 			       const char *pin_group);
 
diff --git a/drivers/pinctrl/devicetree.c b/drivers/pinctrl/devicetree.c
index 6e0a40962f38..df1efc2e5202 100644
--- a/drivers/pinctrl/devicetree.c
+++ b/drivers/pinctrl/devicetree.c
@@ -24,11 +24,11 @@ struct pinctrl_dt_map {
 	struct list_head node;
 	struct pinctrl_dev *pctldev;
 	struct pinctrl_map *map;
-	unsigned num_maps;
+	unsigned int num_maps;
 };
 
 static void dt_free_map(struct pinctrl_dev *pctldev,
-		     struct pinctrl_map *map, unsigned num_maps)
+			struct pinctrl_map *map, unsigned int num_maps)
 {
 	int i;
 
@@ -64,7 +64,7 @@ void pinctrl_dt_free_maps(struct pinctrl *p)
 
 static int dt_remember_or_free_map(struct pinctrl *p, const char *statename,
 				   struct pinctrl_dev *pctldev,
-				   struct pinctrl_map *map, unsigned num_maps)
+				   struct pinctrl_map *map, unsigned int num_maps)
 {
 	int i;
 	struct pinctrl_dt_map *dt_map;
@@ -116,7 +116,7 @@ static int dt_to_map_one_config(struct pinctrl *p,
 	const struct pinctrl_ops *ops;
 	int ret;
 	struct pinctrl_map *map;
-	unsigned num_maps;
+	unsigned int num_maps;
 	bool allow_default = false;
 
 	/* Find the pin controller containing np_config */
diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index 9bc16943014f..2d3d80921c0d 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -42,7 +42,7 @@ static inline const struct group_desc *imx_pinctrl_find_group_by_name(
 
 	for (i = 0; i < pctldev->num_groups; i++) {
 		grp = pinctrl_generic_get_group(pctldev, i);
-		if (grp && !strcmp(grp->name, name))
+		if (grp && !strcmp(grp->grp.name, name))
 			break;
 	}
 
@@ -79,9 +79,9 @@ static int imx_dt_node_to_map(struct pinctrl_dev *pctldev,
 	}
 
 	if (info->flags & IMX_USE_SCU) {
-		map_num += grp->num_pins;
+		map_num += grp->grp.npins;
 	} else {
-		for (i = 0; i < grp->num_pins; i++) {
+		for (i = 0; i < grp->grp.npins; i++) {
 			pin = &((struct imx_pin *)(grp->data))[i];
 			if (!(pin->conf.mmio.config & IMX_NO_PAD_CTL))
 				map_num++;
@@ -109,7 +109,7 @@ static int imx_dt_node_to_map(struct pinctrl_dev *pctldev,
 
 	/* create config map */
 	new_map++;
-	for (i = j = 0; i < grp->num_pins; i++) {
+	for (i = j = 0; i < grp->grp.npins; i++) {
 		pin = &((struct imx_pin *)(grp->data))[i];
 
 		/*
@@ -263,10 +263,10 @@ static int imx_pmx_set(struct pinctrl_dev *pctldev, unsigned selector,
 	if (!func)
 		return -EINVAL;
 
-	npins = grp->num_pins;
+	npins = grp->grp.npins;
 
 	dev_dbg(ipctl->dev, "enable function %s group %s\n",
-		func->name, grp->name);
+		func->name, grp->grp.name);
 
 	for (i = 0; i < npins; i++) {
 		/*
@@ -423,7 +423,7 @@ static void imx_pinconf_group_dbg_show(struct pinctrl_dev *pctldev,
 	if (!grp)
 		return;
 
-	for (i = 0; i < grp->num_pins; i++) {
+	for (i = 0; i < grp->grp.npins; i++) {
 		struct imx_pin *pin = &((struct imx_pin *)(grp->data))[i];
 
 		name = pin_get_name(pctldev, pin->pin);
@@ -511,6 +511,7 @@ static int imx_pinctrl_parse_groups(struct device_node *np,
 {
 	const struct imx_pinctrl_soc_info *info = ipctl->info;
 	struct imx_pin *pin;
+	unsigned int *pins;
 	int size, pin_size;
 	const __be32 *list;
 	int i;
@@ -525,7 +526,7 @@ static int imx_pinctrl_parse_groups(struct device_node *np,
 		pin_size = FSL_PIN_SIZE;
 
 	/* Initialise group */
-	grp->name = np->name;
+	grp->grp.name = np->name;
 
 	/*
 	 * the binding format is fsl,pins = <PIN_FUNC_ID CONFIG ...>,
@@ -553,24 +554,22 @@ static int imx_pinctrl_parse_groups(struct device_node *np,
 		return -EINVAL;
 	}
 
-	grp->num_pins = size / pin_size;
-	grp->data = devm_kcalloc(ipctl->dev,
-				 grp->num_pins, sizeof(struct imx_pin),
-				 GFP_KERNEL);
-	grp->pins = devm_kcalloc(ipctl->dev,
-				 grp->num_pins, sizeof(unsigned int),
-				 GFP_KERNEL);
-	if (!grp->pins || !grp->data)
+	grp->grp.npins = size / pin_size;
+	grp->data = devm_kcalloc(ipctl->dev, grp->grp.npins, sizeof(*pin), GFP_KERNEL);
+	if (!grp->data)
 		return -ENOMEM;
 
-	for (i = 0; i < grp->num_pins; i++) {
+	pins = devm_kcalloc(ipctl->dev, grp->grp.npins, sizeof(*pins), GFP_KERNEL);
+	if (!pins)
+		return -ENOMEM;
+	grp->grp.pins = pins;
+
+	for (i = 0; i < grp->grp.npins; i++) {
 		pin = &((struct imx_pin *)(grp->data))[i];
 		if (info->flags & IMX_USE_SCU)
-			info->imx_pinctrl_parse_pin(ipctl, &grp->pins[i],
-						  pin, &list);
+			info->imx_pinctrl_parse_pin(ipctl, &pins[i], pin, &list);
 		else
-			imx_pinctrl_parse_pin_mmio(ipctl, &grp->pins[i],
-						   pin, &list, np);
+			imx_pinctrl_parse_pin_mmio(ipctl, &pins[i], pin, &list, np);
 	}
 
 	return 0;
@@ -612,8 +611,7 @@ static int imx_pinctrl_parse_functions(struct device_node *np,
 
 	i = 0;
 	for_each_child_of_node(np, child) {
-		grp = devm_kzalloc(ipctl->dev, sizeof(struct group_desc),
-				   GFP_KERNEL);
+		grp = devm_kzalloc(ipctl->dev, sizeof(*grp), GFP_KERNEL);
 		if (!grp) {
 			of_node_put(child);
 			return -ENOMEM;
diff --git a/drivers/pinctrl/intel/Kconfig b/drivers/pinctrl/intel/Kconfig
index d66f4f6932d8..2101d30bd66c 100644
--- a/drivers/pinctrl/intel/Kconfig
+++ b/drivers/pinctrl/intel/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # Intel pin control drivers
 menu "Intel pinctrl drivers"
-	depends on ACPI && (X86 || COMPILE_TEST)
+	depends on (ACPI && X86) || COMPILE_TEST
 
 config PINCTRL_BAYTRAIL
 	bool "Intel Baytrail GPIO pin control"
@@ -37,6 +37,16 @@ config PINCTRL_INTEL
 	select GPIOLIB
 	select GPIOLIB_IRQCHIP
 
+config PINCTRL_INTEL_PLATFORM
+	tristate "Intel pinctrl and GPIO platform driver"
+	depends on ACPI
+	select PINCTRL_INTEL
+	help
+	  This pinctrl driver provides an interface that allows configuring
+	  of Intel PCH pins and using them as GPIOs. Currently the following
+	  Intel SoCs / platforms require this to be functional:
+	  - Lunar Lake
+
 config PINCTRL_ALDERLAKE
 	tristate "Intel Alder Lake pinctrl and GPIO driver"
 	select PINCTRL_INTEL
@@ -128,6 +138,15 @@ config PINCTRL_METEORLAKE
 	  This pinctrl driver provides an interface that allows configuring
 	  of Intel Meteor Lake pins and using them as GPIOs.
 
+config PINCTRL_METEORPOINT
+	tristate "Intel Meteor Point pinctrl and GPIO driver"
+	depends on ACPI
+	select PINCTRL_INTEL
+	help
+	  Meteor Point is the PCH of Intel Meteor Lake. This pinctrl driver
+	  provides an interface that allows configuring of PCH pins and
+	  using them as GPIOs.
+
 config PINCTRL_SUNRISEPOINT
 	tristate "Intel Sunrisepoint pinctrl and GPIO driver"
 	select PINCTRL_INTEL
diff --git a/drivers/pinctrl/intel/Makefile b/drivers/pinctrl/intel/Makefile
index f6d30f2d973a..d0d868c9a622 100644
--- a/drivers/pinctrl/intel/Makefile
+++ b/drivers/pinctrl/intel/Makefile
@@ -8,6 +8,7 @@ obj-$(CONFIG_PINCTRL_TANGIER)		+= pinctrl-tangier.o
 obj-$(CONFIG_PINCTRL_MERRIFIELD)	+= pinctrl-merrifield.o
 obj-$(CONFIG_PINCTRL_MOOREFIELD)	+= pinctrl-moorefield.o
 obj-$(CONFIG_PINCTRL_INTEL)		+= pinctrl-intel.o
+obj-$(CONFIG_PINCTRL_INTEL_PLATFORM)	+= pinctrl-intel-platform.o
 obj-$(CONFIG_PINCTRL_ALDERLAKE)		+= pinctrl-alderlake.o
 obj-$(CONFIG_PINCTRL_BROXTON)		+= pinctrl-broxton.o
 obj-$(CONFIG_PINCTRL_CANNONLAKE)	+= pinctrl-cannonlake.o
@@ -21,5 +22,6 @@ obj-$(CONFIG_PINCTRL_JASPERLAKE)	+= pinctrl-jasperlake.o
 obj-$(CONFIG_PINCTRL_LAKEFIELD)		+= pinctrl-lakefield.o
 obj-$(CONFIG_PINCTRL_LEWISBURG)		+= pinctrl-lewisburg.o
 obj-$(CONFIG_PINCTRL_METEORLAKE)	+= pinctrl-meteorlake.o
+obj-$(CONFIG_PINCTRL_METEORPOINT)	+= pinctrl-meteorpoint.o
 obj-$(CONFIG_PINCTRL_SUNRISEPOINT)	+= pinctrl-sunrisepoint.o
 obj-$(CONFIG_PINCTRL_TIGERLAKE)		+= pinctrl-tigerlake.o
diff --git a/drivers/pinctrl/intel/pinctrl-alderlake.c b/drivers/pinctrl/intel/pinctrl-alderlake.c
index 4a37dc273d63..7d9948e5f422 100644
--- a/drivers/pinctrl/intel/pinctrl-alderlake.c
+++ b/drivers/pinctrl/intel/pinctrl-alderlake.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -733,14 +734,12 @@ static const struct acpi_device_id adl_pinctrl_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, adl_pinctrl_acpi_match);
 
-static INTEL_PINCTRL_PM_OPS(adl_pinctrl_pm_ops);
-
 static struct platform_driver adl_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_hid,
 	.driver = {
 		.name = "alderlake-pinctrl",
 		.acpi_match_table = adl_pinctrl_acpi_match,
-		.pm = &adl_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 module_platform_driver(adl_pinctrl_driver);
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 3c8c02043481..ac97724c59ba 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -588,10 +588,9 @@ static void byt_set_group_simple_mux(struct intel_pinctrl *vg,
 				     const struct intel_pingroup group,
 				     unsigned int func)
 {
-	unsigned long flags;
 	int i;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
 
 	for (i = 0; i < group.grp.npins; i++) {
 		void __iomem *padcfg0;
@@ -609,18 +608,15 @@ static void byt_set_group_simple_mux(struct intel_pinctrl *vg,
 		value |= func;
 		writel(value, padcfg0);
 	}
-
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
 }
 
 static void byt_set_group_mixed_mux(struct intel_pinctrl *vg,
 				    const struct intel_pingroup group,
 				    const unsigned int *func)
 {
-	unsigned long flags;
 	int i;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
 
 	for (i = 0; i < group.grp.npins; i++) {
 		void __iomem *padcfg0;
@@ -638,8 +634,6 @@ static void byt_set_group_mixed_mux(struct intel_pinctrl *vg,
 		value |= func[i];
 		writel(value, padcfg0);
 	}
-
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
 }
 
 static int byt_set_mux(struct pinctrl_dev *pctldev, unsigned int func_selector,
@@ -677,10 +671,10 @@ static u32 byt_get_gpio_mux(struct intel_pinctrl *vg, unsigned int offset)
 static void byt_gpio_clear_triggering(struct intel_pinctrl *vg, unsigned int offset)
 {
 	void __iomem *reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
-	unsigned long flags;
 	u32 value;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
+
 	value = readl(reg);
 
 	/* Do not clear direct-irq enabled IRQs (from gpio_disable_free) */
@@ -688,7 +682,6 @@ static void byt_gpio_clear_triggering(struct intel_pinctrl *vg, unsigned int off
 		value &= ~(BYT_TRIG_POS | BYT_TRIG_NEG | BYT_TRIG_LVL);
 
 	writel(value, reg);
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
 }
 
 static int byt_gpio_request_enable(struct pinctrl_dev *pctl_dev,
@@ -698,9 +691,8 @@ static int byt_gpio_request_enable(struct pinctrl_dev *pctl_dev,
 	struct intel_pinctrl *vg = pinctrl_dev_get_drvdata(pctl_dev);
 	void __iomem *reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
 	u32 value, gpio_mux;
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
 
 	/*
 	 * In most cases, func pin mux 000 means GPIO function.
@@ -713,15 +705,14 @@ static int byt_gpio_request_enable(struct pinctrl_dev *pctl_dev,
 	 */
 	value = readl(reg) & BYT_PIN_MUX;
 	gpio_mux = byt_get_gpio_mux(vg, offset);
-	if (gpio_mux != value) {
-		value = readl(reg) & ~BYT_PIN_MUX;
-		value |= gpio_mux;
-		writel(value, reg);
+	if (gpio_mux == value)
+		return 0;
 
-		dev_warn(vg->dev, FW_BUG "Pin %i: forcibly re-configured as GPIO\n", offset);
-	}
+	value = readl(reg) & ~BYT_PIN_MUX;
+	value |= gpio_mux;
+	writel(value, reg);
 
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
+	dev_warn(vg->dev, FW_BUG "Pin %i: forcibly re-configured as GPIO\n", offset);
 
 	return 0;
 }
@@ -759,10 +750,9 @@ static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev,
 {
 	struct intel_pinctrl *vg = pinctrl_dev_get_drvdata(pctl_dev);
 	void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
-	unsigned long flags;
 	u32 value;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
 
 	value = readl(val_reg);
 	value &= ~BYT_DIR_MASK;
@@ -773,8 +763,6 @@ static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev,
 
 	writel(value, val_reg);
 
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
-
 	return 0;
 }
 
@@ -811,6 +799,7 @@ static int byt_set_pull_strength(u32 *reg, u16 strength)
 	*reg &= ~BYT_PULL_STR_MASK;
 
 	switch (strength) {
+	case 1: /* Set default strength value in case none is given */
 	case 2000:
 		*reg |= BYT_PULL_STR_2K;
 		break;
@@ -830,6 +819,24 @@ static int byt_set_pull_strength(u32 *reg, u16 strength)
 	return 0;
 }
 
+static void byt_gpio_force_input_mode(struct intel_pinctrl *vg, unsigned int offset)
+{
+	void __iomem *reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
+	u32 value;
+
+	value = readl(reg);
+	if (!(value & BYT_INPUT_EN))
+		return;
+
+	/*
+	 * Pull assignment is only applicable in input mode. If
+	 * chip is not in input mode, set it and warn about it.
+	 */
+	value &= ~BYT_INPUT_EN;
+	writel(value, reg);
+	dev_warn(vg->dev, "Pin %i: forcibly set to input mode\n", offset);
+}
+
 static int byt_pin_config_get(struct pinctrl_dev *pctl_dev, unsigned int offset,
 			      unsigned long *config)
 {
@@ -838,15 +845,15 @@ static int byt_pin_config_get(struct pinctrl_dev *pctl_dev, unsigned int offset,
 	void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
 	void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
 	void __iomem *db_reg = byt_gpio_reg(vg, offset, BYT_DEBOUNCE_REG);
-	unsigned long flags;
 	u32 conf, pull, val, debounce;
 	u16 arg = 0;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
-	conf = readl(conf_reg);
+	scoped_guard(raw_spinlock_irqsave, &byt_lock) {
+		conf = readl(conf_reg);
+		val = readl(val_reg);
+	}
+
 	pull = conf & BYT_PULL_ASSIGN_MASK;
-	val = readl(val_reg);
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
 
 	switch (param) {
 	case PIN_CONFIG_BIAS_DISABLE:
@@ -873,9 +880,8 @@ static int byt_pin_config_get(struct pinctrl_dev *pctl_dev, unsigned int offset,
 		if (!(conf & BYT_DEBOUNCE_EN))
 			return -EINVAL;
 
-		raw_spin_lock_irqsave(&byt_lock, flags);
-		debounce = readl(db_reg);
-		raw_spin_unlock_irqrestore(&byt_lock, flags);
+		scoped_guard(raw_spinlock_irqsave, &byt_lock)
+			debounce = readl(db_reg);
 
 		switch (debounce & BYT_DEBOUNCE_PULSE_MASK) {
 		case BYT_DEBOUNCE_PULSE_375US:
@@ -919,18 +925,16 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev,
 			      unsigned int num_configs)
 {
 	struct intel_pinctrl *vg = pinctrl_dev_get_drvdata(pctl_dev);
-	unsigned int param, arg;
 	void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
-	void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
 	void __iomem *db_reg = byt_gpio_reg(vg, offset, BYT_DEBOUNCE_REG);
-	u32 conf, val, db_pulse, debounce;
-	unsigned long flags;
-	int i, ret = 0;
+	u32 conf, db_pulse, debounce;
+	enum pin_config_param param;
+	int i, ret;
+	u32 arg;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
 
 	conf = readl(conf_reg);
-	val = readl(val_reg);
 
 	for (i = 0; i < num_configs; i++) {
 		param = pinconf_to_config_param(configs[i]);
@@ -941,59 +945,30 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev,
 			conf &= ~BYT_PULL_ASSIGN_MASK;
 			break;
 		case PIN_CONFIG_BIAS_PULL_DOWN:
-			/* Set default strength value in case none is given */
-			if (arg == 1)
-				arg = 2000;
-
-			/*
-			 * Pull assignment is only applicable in input mode. If
-			 * chip is not in input mode, set it and warn about it.
-			 */
-			if (val & BYT_INPUT_EN) {
-				val &= ~BYT_INPUT_EN;
-				writel(val, val_reg);
-				dev_warn(vg->dev, "Pin %i: forcibly set to input mode\n", offset);
-			}
+			byt_gpio_force_input_mode(vg, offset);
 
 			conf &= ~BYT_PULL_ASSIGN_MASK;
 			conf |= BYT_PULL_ASSIGN_DOWN;
 			ret = byt_set_pull_strength(&conf, arg);
+			if (ret)
+				return ret;
 
 			break;
 		case PIN_CONFIG_BIAS_PULL_UP:
-			/* Set default strength value in case none is given */
-			if (arg == 1)
-				arg = 2000;
-
-			/*
-			 * Pull assignment is only applicable in input mode. If
-			 * chip is not in input mode, set it and warn about it.
-			 */
-			if (val & BYT_INPUT_EN) {
-				val &= ~BYT_INPUT_EN;
-				writel(val, val_reg);
-				dev_warn(vg->dev, "Pin %i: forcibly set to input mode\n", offset);
-			}
+			byt_gpio_force_input_mode(vg, offset);
 
 			conf &= ~BYT_PULL_ASSIGN_MASK;
 			conf |= BYT_PULL_ASSIGN_UP;
 			ret = byt_set_pull_strength(&conf, arg);
+			if (ret)
+				return ret;
 
 			break;
 		case PIN_CONFIG_INPUT_DEBOUNCE:
-			if (arg) {
-				conf |= BYT_DEBOUNCE_EN;
-			} else {
-				conf &= ~BYT_DEBOUNCE_EN;
-
-				/*
-				 * No need to update the pulse value.
-				 * Debounce is going to be disabled.
-				 */
-				break;
-			}
-
 			switch (arg) {
+			case 0:
+				db_pulse = 0;
+				break;
 			case 375:
 				db_pulse = BYT_DEBOUNCE_PULSE_375US;
 				break;
@@ -1016,33 +991,28 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev,
 				db_pulse = BYT_DEBOUNCE_PULSE_24MS;
 				break;
 			default:
-				if (arg)
-					ret = -EINVAL;
-				break;
+				return -EINVAL;
 			}
 
-			if (ret)
-				break;
+			if (db_pulse) {
+				debounce = readl(db_reg);
+				debounce = (debounce & ~BYT_DEBOUNCE_PULSE_MASK) | db_pulse;
+				writel(debounce, db_reg);
 
-			debounce = readl(db_reg);
-			debounce = (debounce & ~BYT_DEBOUNCE_PULSE_MASK) | db_pulse;
-			writel(debounce, db_reg);
+				conf |= BYT_DEBOUNCE_EN;
+			} else {
+				conf &= ~BYT_DEBOUNCE_EN;
+			}
 
 			break;
 		default:
-			ret = -ENOTSUPP;
+			return -ENOTSUPP;
 		}
-
-		if (ret)
-			break;
 	}
 
-	if (!ret)
-		writel(conf, conf_reg);
-
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
+	writel(conf, conf_reg);
 
-	return ret;
+	return 0;
 }
 
 static const struct pinconf_ops byt_pinconf_ops = {
@@ -1062,12 +1032,10 @@ static int byt_gpio_get(struct gpio_chip *chip, unsigned int offset)
 {
 	struct intel_pinctrl *vg = gpiochip_get_data(chip);
 	void __iomem *reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
-	unsigned long flags;
 	u32 val;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
-	val = readl(reg);
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
+	scoped_guard(raw_spinlock_irqsave, &byt_lock)
+		val = readl(reg);
 
 	return !!(val & BYT_LEVEL);
 }
@@ -1075,35 +1043,34 @@ static int byt_gpio_get(struct gpio_chip *chip, unsigned int offset)
 static void byt_gpio_set(struct gpio_chip *chip, unsigned int offset, int value)
 {
 	struct intel_pinctrl *vg = gpiochip_get_data(chip);
-	void __iomem *reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
-	unsigned long flags;
+	void __iomem *reg;
 	u32 old_val;
 
+	reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
 	if (!reg)
 		return;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
+
 	old_val = readl(reg);
 	if (value)
 		writel(old_val | BYT_LEVEL, reg);
 	else
 		writel(old_val & ~BYT_LEVEL, reg);
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
 }
 
 static int byt_gpio_get_direction(struct gpio_chip *chip, unsigned int offset)
 {
 	struct intel_pinctrl *vg = gpiochip_get_data(chip);
-	void __iomem *reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
-	unsigned long flags;
+	void __iomem *reg;
 	u32 value;
 
+	reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
 	if (!reg)
 		return -EINVAL;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
-	value = readl(reg);
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
+	scoped_guard(raw_spinlock_irqsave, &byt_lock)
+		value = readl(reg);
 
 	if (!(value & BYT_OUTPUT_EN))
 		return GPIO_LINE_DIRECTION_OUT;
@@ -1117,17 +1084,15 @@ static int byt_gpio_direction_input(struct gpio_chip *chip, unsigned int offset)
 {
 	struct intel_pinctrl *vg = gpiochip_get_data(chip);
 	void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
-	unsigned long flags;
 	u32 reg;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
 
 	reg = readl(val_reg);
 	reg &= ~BYT_DIR_MASK;
 	reg |= BYT_OUTPUT_EN;
 	writel(reg, val_reg);
 
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
 	return 0;
 }
 
@@ -1142,10 +1107,9 @@ static int byt_gpio_direction_output(struct gpio_chip *chip,
 {
 	struct intel_pinctrl *vg = gpiochip_get_data(chip);
 	void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
-	unsigned long flags;
 	u32 reg;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
 
 	byt_gpio_direct_irq_check(vg, offset);
 
@@ -1158,7 +1122,6 @@ static int byt_gpio_direction_output(struct gpio_chip *chip,
 
 	writel(reg, val_reg);
 
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
 	return 0;
 }
 
@@ -1173,7 +1136,6 @@ static void byt_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip)
 		void __iomem *conf_reg, *val_reg;
 		const char *pull_str = NULL;
 		const char *pull = NULL;
-		unsigned long flags;
 		unsigned int pin;
 
 		pin = vg->soc->pins[i].number;
@@ -1190,10 +1152,10 @@ static void byt_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip)
 			continue;
 		}
 
-		raw_spin_lock_irqsave(&byt_lock, flags);
-		conf0 = readl(conf_reg);
-		val = readl(val_reg);
-		raw_spin_unlock_irqrestore(&byt_lock, flags);
+		scoped_guard(raw_spinlock_irqsave, &byt_lock) {
+			conf0 = readl(conf_reg);
+			val = readl(val_reg);
+		}
 
 		comm = intel_get_community(vg, pin);
 		if (!comm) {
@@ -1278,9 +1240,9 @@ static void byt_irq_ack(struct irq_data *d)
 	if (!reg)
 		return;
 
-	raw_spin_lock(&byt_lock);
+	guard(raw_spinlock)(&byt_lock);
+
 	writel(BIT(hwirq % 32), reg);
-	raw_spin_unlock(&byt_lock);
 }
 
 static void byt_irq_mask(struct irq_data *d)
@@ -1298,7 +1260,6 @@ static void byt_irq_unmask(struct irq_data *d)
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct intel_pinctrl *vg = gpiochip_get_data(gc);
 	irq_hw_number_t hwirq = irqd_to_hwirq(d);
-	unsigned long flags;
 	void __iomem *reg;
 	u32 value;
 
@@ -1308,7 +1269,8 @@ static void byt_irq_unmask(struct irq_data *d)
 	if (!reg)
 		return;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
+
 	value = readl(reg);
 
 	switch (irqd_get_trigger_type(d)) {
@@ -1330,23 +1292,21 @@ static void byt_irq_unmask(struct irq_data *d)
 	}
 
 	writel(value, reg);
-
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
 }
 
 static int byt_irq_type(struct irq_data *d, unsigned int type)
 {
 	struct intel_pinctrl *vg = gpiochip_get_data(irq_data_get_irq_chip_data(d));
 	irq_hw_number_t hwirq = irqd_to_hwirq(d);
-	u32 value;
-	unsigned long flags;
 	void __iomem *reg;
+	u32 value;
 
 	reg = byt_gpio_reg(vg, hwirq, BYT_CONF0_REG);
 	if (!reg)
 		return -EINVAL;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
+
 	value = readl(reg);
 
 	WARN(value & BYT_DIRECT_IRQ_EN,
@@ -1368,8 +1328,6 @@ static int byt_irq_type(struct irq_data *d, unsigned int type)
 	else if (type & IRQ_TYPE_LEVEL_MASK)
 		irq_set_handler_locked(d, handle_level_irq);
 
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
-
 	return 0;
 }
 
@@ -1401,9 +1359,8 @@ static void byt_gpio_irq_handler(struct irq_desc *desc)
 			continue;
 		}
 
-		raw_spin_lock(&byt_lock);
-		pending = readl(reg);
-		raw_spin_unlock(&byt_lock);
+		scoped_guard(raw_spinlock, &byt_lock)
+			pending = readl(reg);
 		for_each_set_bit(pin, &pending, 32)
 			generic_handle_domain_irq(vg->chip.irq.domain, base + pin);
 	}
@@ -1666,10 +1623,9 @@ static int byt_pinctrl_probe(struct platform_device *pdev)
 static int byt_gpio_suspend(struct device *dev)
 {
 	struct intel_pinctrl *vg = dev_get_drvdata(dev);
-	unsigned long flags;
 	int i;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
 
 	for (i = 0; i < vg->soc->npins; i++) {
 		void __iomem *reg;
@@ -1693,17 +1649,15 @@ static int byt_gpio_suspend(struct device *dev)
 		vg->context.pads[i].val = value;
 	}
 
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
 	return 0;
 }
 
 static int byt_gpio_resume(struct device *dev)
 {
 	struct intel_pinctrl *vg = dev_get_drvdata(dev);
-	unsigned long flags;
 	int i;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
 
 	for (i = 0; i < vg->soc->npins; i++) {
 		void __iomem *reg;
@@ -1743,7 +1697,6 @@ static int byt_gpio_resume(struct device *dev)
 		}
 	}
 
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
 	return 0;
 }
 
diff --git a/drivers/pinctrl/intel/pinctrl-broxton.c b/drivers/pinctrl/intel/pinctrl-broxton.c
index 3118c7c8842f..d99541676630 100644
--- a/drivers/pinctrl/intel/pinctrl-broxton.c
+++ b/drivers/pinctrl/intel/pinctrl-broxton.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -1000,14 +1001,12 @@ static const struct platform_device_id bxt_pinctrl_platform_ids[] = {
 };
 MODULE_DEVICE_TABLE(platform, bxt_pinctrl_platform_ids);
 
-static INTEL_PINCTRL_PM_OPS(bxt_pinctrl_pm_ops);
-
 static struct platform_driver bxt_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_uid,
 	.driver = {
 		.name = "broxton-pinctrl",
 		.acpi_match_table = bxt_pinctrl_acpi_match,
-		.pm = &bxt_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 	.id_table = bxt_pinctrl_platform_ids,
 };
diff --git a/drivers/pinctrl/intel/pinctrl-cannonlake.c b/drivers/pinctrl/intel/pinctrl-cannonlake.c
index 95976abfb785..1aa09f950be1 100644
--- a/drivers/pinctrl/intel/pinctrl-cannonlake.c
+++ b/drivers/pinctrl/intel/pinctrl-cannonlake.c
@@ -10,6 +10,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -824,14 +825,12 @@ static const struct acpi_device_id cnl_pinctrl_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, cnl_pinctrl_acpi_match);
 
-static INTEL_PINCTRL_PM_OPS(cnl_pinctrl_pm_ops);
-
 static struct platform_driver cnl_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_hid,
 	.driver = {
 		.name = "cannonlake-pinctrl",
 		.acpi_match_table = cnl_pinctrl_acpi_match,
-		.pm = &cnl_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 module_platform_driver(cnl_pinctrl_driver);
diff --git a/drivers/pinctrl/intel/pinctrl-cedarfork.c b/drivers/pinctrl/intel/pinctrl-cedarfork.c
index a20465eb2dc6..48af8930dd1f 100644
--- a/drivers/pinctrl/intel/pinctrl-cedarfork.c
+++ b/drivers/pinctrl/intel/pinctrl-cedarfork.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -319,8 +320,6 @@ static const struct intel_pinctrl_soc_data cdf_soc_data = {
 	.ncommunities = ARRAY_SIZE(cdf_communities),
 };
 
-static INTEL_PINCTRL_PM_OPS(cdf_pinctrl_pm_ops);
-
 static const struct acpi_device_id cdf_pinctrl_acpi_match[] = {
 	{ "INTC3001", (kernel_ulong_t)&cdf_soc_data },
 	{ }
@@ -332,7 +331,7 @@ static struct platform_driver cdf_pinctrl_driver = {
 	.driver = {
 		.name = "cedarfork-pinctrl",
 		.acpi_match_table = cdf_pinctrl_acpi_match,
-		.pm = &cdf_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 
diff --git a/drivers/pinctrl/intel/pinctrl-denverton.c b/drivers/pinctrl/intel/pinctrl-denverton.c
index 562a4f9188e4..666507f54f27 100644
--- a/drivers/pinctrl/intel/pinctrl-denverton.c
+++ b/drivers/pinctrl/intel/pinctrl-denverton.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -249,8 +250,6 @@ static const struct intel_pinctrl_soc_data dnv_soc_data = {
 	.ncommunities = ARRAY_SIZE(dnv_communities),
 };
 
-static INTEL_PINCTRL_PM_OPS(dnv_pinctrl_pm_ops);
-
 static const struct acpi_device_id dnv_pinctrl_acpi_match[] = {
 	{ "INTC3000", (kernel_ulong_t)&dnv_soc_data },
 	{ }
@@ -268,7 +267,7 @@ static struct platform_driver dnv_pinctrl_driver = {
 	.driver = {
 		.name = "denverton-pinctrl",
 		.acpi_match_table = dnv_pinctrl_acpi_match,
-		.pm = &dnv_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 	.id_table = dnv_pinctrl_platform_ids,
 };
diff --git a/drivers/pinctrl/intel/pinctrl-elkhartlake.c b/drivers/pinctrl/intel/pinctrl-elkhartlake.c
index 81581ab85316..1678634ebc06 100644
--- a/drivers/pinctrl/intel/pinctrl-elkhartlake.c
+++ b/drivers/pinctrl/intel/pinctrl-elkhartlake.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -485,14 +486,12 @@ static const struct acpi_device_id ehl_pinctrl_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, ehl_pinctrl_acpi_match);
 
-static INTEL_PINCTRL_PM_OPS(ehl_pinctrl_pm_ops);
-
 static struct platform_driver ehl_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_uid,
 	.driver = {
 		.name = "elkhartlake-pinctrl",
 		.acpi_match_table = ehl_pinctrl_acpi_match,
-		.pm = &ehl_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 module_platform_driver(ehl_pinctrl_driver);
diff --git a/drivers/pinctrl/intel/pinctrl-emmitsburg.c b/drivers/pinctrl/intel/pinctrl-emmitsburg.c
index 099ec8351d5f..e4798d32492c 100644
--- a/drivers/pinctrl/intel/pinctrl-emmitsburg.c
+++ b/drivers/pinctrl/intel/pinctrl-emmitsburg.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -358,14 +359,12 @@ static const struct acpi_device_id ebg_pinctrl_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, ebg_pinctrl_acpi_match);
 
-static INTEL_PINCTRL_PM_OPS(ebg_pinctrl_pm_ops);
-
 static struct platform_driver ebg_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_hid,
 	.driver = {
 		.name = "emmitsburg-pinctrl",
 		.acpi_match_table = ebg_pinctrl_acpi_match,
-		.pm = &ebg_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 module_platform_driver(ebg_pinctrl_driver);
diff --git a/drivers/pinctrl/intel/pinctrl-geminilake.c b/drivers/pinctrl/intel/pinctrl-geminilake.c
index 9effa06b61e9..6dcf0ac2059f 100644
--- a/drivers/pinctrl/intel/pinctrl-geminilake.c
+++ b/drivers/pinctrl/intel/pinctrl-geminilake.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -447,14 +448,12 @@ static const struct acpi_device_id glk_pinctrl_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, glk_pinctrl_acpi_match);
 
-static INTEL_PINCTRL_PM_OPS(glk_pinctrl_pm_ops);
-
 static struct platform_driver glk_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_uid,
 	.driver = {
 		.name = "geminilake-pinctrl",
 		.acpi_match_table = glk_pinctrl_acpi_match,
-		.pm = &glk_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 
diff --git a/drivers/pinctrl/intel/pinctrl-icelake.c b/drivers/pinctrl/intel/pinctrl-icelake.c
index 300e1538c8d0..fe3042de891a 100644
--- a/drivers/pinctrl/intel/pinctrl-icelake.c
+++ b/drivers/pinctrl/intel/pinctrl-icelake.c
@@ -10,6 +10,7 @@
 #include <linux/acpi.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -668,8 +669,6 @@ static const struct intel_pinctrl_soc_data icln_soc_data = {
 	.ncommunities = ARRAY_SIZE(icln_communities),
 };
 
-static INTEL_PINCTRL_PM_OPS(icl_pinctrl_pm_ops);
-
 static const struct acpi_device_id icl_pinctrl_acpi_match[] = {
 	{ "INT3455", (kernel_ulong_t)&icllp_soc_data },
 	{ "INT34C3", (kernel_ulong_t)&icln_soc_data },
@@ -682,7 +681,7 @@ static struct platform_driver icl_pinctrl_driver = {
 	.driver = {
 		.name = "icelake-pinctrl",
 		.acpi_match_table = icl_pinctrl_acpi_match,
-		.pm = &icl_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 module_platform_driver(icl_pinctrl_driver);
diff --git a/drivers/pinctrl/intel/pinctrl-intel-platform.c b/drivers/pinctrl/intel/pinctrl-intel-platform.c
new file mode 100644
index 000000000000..4a19ab3b4ba7
--- /dev/null
+++ b/drivers/pinctrl/intel/pinctrl-intel-platform.c
@@ -0,0 +1,225 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel PCH pinctrl/GPIO driver
+ *
+ * Copyright (C) 2021-2023, Intel Corporation
+ * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ */
+
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/property.h>
+#include <linux/string_helpers.h>
+
+#include <linux/pinctrl/pinctrl.h>
+
+#include "pinctrl-intel.h"
+
+struct intel_platform_pins {
+	struct pinctrl_pin_desc *pins;
+	size_t npins;
+};
+
+static int intel_platform_pinctrl_prepare_pins(struct device *dev, size_t base,
+					       const char *name, u32 size,
+					       struct intel_platform_pins *pins)
+{
+	struct pinctrl_pin_desc *descs;
+	char **pin_names;
+	unsigned int i;
+
+	pin_names = devm_kasprintf_strarray(dev, name, size);
+	if (IS_ERR(pin_names))
+		return PTR_ERR(pin_names);
+
+	descs = devm_krealloc_array(dev, pins->pins, base + size, sizeof(*descs), GFP_KERNEL);
+	if (!descs)
+		return -ENOMEM;
+
+	for (i = 0; i < size; i++) {
+		unsigned int pin_number = base + i;
+		char *pin_name = pin_names[i];
+		struct pinctrl_pin_desc *desc;
+
+		/* Unify delimiter for pin name */
+		strreplace(pin_name, '-', '_');
+
+		desc = &descs[pin_number];
+		desc->number = pin_number;
+		desc->name = pin_name;
+	}
+
+	pins->pins = descs;
+	pins->npins = base + size;
+
+	return 0;
+}
+
+static int intel_platform_pinctrl_prepare_group(struct device *dev,
+						struct fwnode_handle *child,
+						struct intel_padgroup *gpp,
+						struct intel_platform_pins *pins)
+{
+	size_t base = pins->npins;
+	const char *name;
+	u32 size;
+	int ret;
+
+	ret = fwnode_property_read_string(child, "intc-gpio-group-name", &name);
+	if (ret)
+		return ret;
+
+	ret = fwnode_property_read_u32(child, "intc-gpio-pad-count", &size);
+	if (ret)
+		return ret;
+
+	ret = intel_platform_pinctrl_prepare_pins(dev, base, name, size, pins);
+	if (ret)
+		return ret;
+
+	gpp->base = base;
+	gpp->size = size;
+	gpp->gpio_base = INTEL_GPIO_BASE_MATCH;
+
+	return 0;
+}
+
+static int intel_platform_pinctrl_prepare_community(struct device *dev,
+						    struct intel_community *community,
+						    struct intel_platform_pins *pins)
+{
+	struct fwnode_handle *child;
+	struct intel_padgroup *gpps;
+	unsigned int group;
+	size_t ngpps;
+	u32 offset;
+	int ret;
+
+	ret = device_property_read_u32(dev, "intc-gpio-pad-ownership-offset", &offset);
+	if (ret)
+		return ret;
+	community->padown_offset = offset;
+
+	ret = device_property_read_u32(dev, "intc-gpio-pad-configuration-lock-offset", &offset);
+	if (ret)
+		return ret;
+	community->padcfglock_offset = offset;
+
+	ret = device_property_read_u32(dev, "intc-gpio-host-software-pad-ownership-offset", &offset);
+	if (ret)
+		return ret;
+	community->hostown_offset = offset;
+
+	ret = device_property_read_u32(dev, "intc-gpio-gpi-interrupt-status-offset", &offset);
+	if (ret)
+		return ret;
+	community->is_offset = offset;
+
+	ret = device_property_read_u32(dev, "intc-gpio-gpi-interrupt-enable-offset", &offset);
+	if (ret)
+		return ret;
+	community->ie_offset = offset;
+
+	ngpps = device_get_child_node_count(dev);
+	if (!ngpps)
+		return -ENODEV;
+
+	gpps = devm_kcalloc(dev, ngpps, sizeof(*gpps), GFP_KERNEL);
+	if (!gpps)
+		return -ENOMEM;
+
+	group = 0;
+	device_for_each_child_node(dev, child) {
+		struct intel_padgroup *gpp = &gpps[group];
+
+		gpp->reg_num = group;
+
+		ret = intel_platform_pinctrl_prepare_group(dev, child, gpp, pins);
+		if (ret)
+			return ret;
+
+		group++;
+	}
+
+	community->ngpps = ngpps;
+	community->gpps = gpps;
+
+	return 0;
+}
+
+static int intel_platform_pinctrl_prepare_soc_data(struct device *dev,
+						   struct intel_pinctrl_soc_data *data)
+{
+	struct intel_platform_pins pins = {};
+	struct intel_community *communities;
+	size_t ncommunities;
+	unsigned int i;
+	int ret;
+
+	/* Version 1.0 of the specification assumes only a single community per device node */
+	ncommunities = 1,
+	communities = devm_kcalloc(dev, ncommunities, sizeof(*communities), GFP_KERNEL);
+	if (!communities)
+		return -ENOMEM;
+
+	for (i = 0; i < ncommunities; i++) {
+		struct intel_community *community = &communities[i];
+
+		community->barno = i;
+		community->pin_base = pins.npins;
+
+		ret = intel_platform_pinctrl_prepare_community(dev, community, &pins);
+		if (ret)
+			return ret;
+
+		community->npins = pins.npins - community->pin_base;
+	}
+
+	data->ncommunities = ncommunities;
+	data->communities = communities;
+
+	data->npins = pins.npins;
+	data->pins = pins.pins;
+
+	return 0;
+}
+
+static int intel_platform_pinctrl_probe(struct platform_device *pdev)
+{
+	struct intel_pinctrl_soc_data *data;
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	ret = intel_platform_pinctrl_prepare_soc_data(dev, data);
+	if (ret)
+		return ret;
+
+	return intel_pinctrl_probe(pdev, data);
+}
+
+static const struct acpi_device_id intel_platform_pinctrl_acpi_match[] = {
+	{ "INTC105F" },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, intel_platform_pinctrl_acpi_match);
+
+static struct platform_driver intel_platform_pinctrl_driver = {
+	.probe = intel_platform_pinctrl_probe,
+	.driver = {
+		.name = "intel-pinctrl",
+		.acpi_match_table = intel_platform_pinctrl_acpi_match,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
+	},
+};
+module_platform_driver(intel_platform_pinctrl_driver);
+
+MODULE_AUTHOR("Andy Shevchenko <andriy.shevchenko@linux.intel.com>");
+MODULE_DESCRIPTION("Intel PCH pinctrl/GPIO driver");
+MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS(PINCTRL_INTEL);
diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 652ba451f885..d6f29e6faab7 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -677,10 +677,6 @@ static int intel_config_set_pull(struct intel_pinctrl *pctrl, unsigned int pin,
 	u32 term = 0, up = 0, value;
 	void __iomem *padcfg1;
 
-	/* Set default strength value in case none is given */
-	if (arg == 1)
-		arg = 5000;
-
 	switch (param) {
 	case PIN_CONFIG_BIAS_DISABLE:
 		break;
@@ -690,6 +686,7 @@ static int intel_config_set_pull(struct intel_pinctrl *pctrl, unsigned int pin,
 		case 20000:
 			term = PADCFG1_TERM_20K;
 			break;
+		case 1: /* Set default strength value in case none is given */
 		case 5000:
 			term = PADCFG1_TERM_5K;
 			break;
@@ -716,6 +713,7 @@ static int intel_config_set_pull(struct intel_pinctrl *pctrl, unsigned int pin,
 		case 20000:
 			term = PADCFG1_TERM_20K;
 			break;
+		case 1: /* Set default strength value in case none is given */
 		case 5000:
 			term = PADCFG1_TERM_5K;
 			break;
@@ -899,7 +897,7 @@ static int intel_gpio_to_pin(struct intel_pinctrl *pctrl, unsigned int offset,
  *
  * Return: a GPIO offset, or negative error code if translation can't be done.
  */
-static __maybe_unused int intel_pin_to_gpio(struct intel_pinctrl *pctrl, int pin)
+static int intel_pin_to_gpio(struct intel_pinctrl *pctrl, int pin)
 {
 	const struct intel_community *community;
 	const struct intel_padgroup *padgrp;
@@ -1506,8 +1504,8 @@ static int intel_pinctrl_probe_pwm(struct intel_pinctrl *pctrl,
 	return PTR_ERR_OR_ZERO(pwm);
 }
 
-static int intel_pinctrl_probe(struct platform_device *pdev,
-			       const struct intel_pinctrl_soc_data *soc_data)
+int intel_pinctrl_probe(struct platform_device *pdev,
+			const struct intel_pinctrl_soc_data *soc_data)
 {
 	struct device *dev = &pdev->dev;
 	struct intel_pinctrl *pctrl;
@@ -1625,6 +1623,7 @@ static int intel_pinctrl_probe(struct platform_device *pdev,
 
 	return 0;
 }
+EXPORT_SYMBOL_NS_GPL(intel_pinctrl_probe, PINCTRL_INTEL);
 
 int intel_pinctrl_probe_by_hid(struct platform_device *pdev)
 {
@@ -1653,7 +1652,7 @@ EXPORT_SYMBOL_NS_GPL(intel_pinctrl_probe_by_uid, PINCTRL_INTEL);
 const struct intel_pinctrl_soc_data *intel_pinctrl_get_soc_data(struct platform_device *pdev)
 {
 	const struct intel_pinctrl_soc_data * const *table;
-	const struct intel_pinctrl_soc_data *data = NULL;
+	const struct intel_pinctrl_soc_data *data;
 	struct device *dev = &pdev->dev;
 
 	table = device_get_match_data(dev);
@@ -1662,11 +1661,10 @@ const struct intel_pinctrl_soc_data *intel_pinctrl_get_soc_data(struct platform_
 		unsigned int i;
 
 		for (i = 0; table[i]; i++) {
-			if (acpi_dev_uid_match(adev, table[i]->uid)) {
-				data = table[i];
+			if (acpi_dev_uid_match(adev, table[i]->uid))
 				break;
-			}
 		}
+		data = table[i];
 	} else {
 		const struct platform_device_id *id;
 
@@ -1682,7 +1680,6 @@ const struct intel_pinctrl_soc_data *intel_pinctrl_get_soc_data(struct platform_
 }
 EXPORT_SYMBOL_NS_GPL(intel_pinctrl_get_soc_data, PINCTRL_INTEL);
 
-#ifdef CONFIG_PM_SLEEP
 static bool __intel_gpio_is_direct_irq(u32 value)
 {
 	return (value & PADCFG0_GPIROUTIOXAPIC) && (value & PADCFG0_GPIOTXDIS) &&
@@ -1728,7 +1725,7 @@ static bool intel_pinctrl_should_save(struct intel_pinctrl *pctrl, unsigned int
 	return false;
 }
 
-int intel_pinctrl_suspend_noirq(struct device *dev)
+static int intel_pinctrl_suspend_noirq(struct device *dev)
 {
 	struct intel_pinctrl *pctrl = dev_get_drvdata(dev);
 	struct intel_community_context *communities;
@@ -1771,7 +1768,6 @@ int intel_pinctrl_suspend_noirq(struct device *dev)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(intel_pinctrl_suspend_noirq);
 
 static bool intel_gpio_update_reg(void __iomem *reg, u32 mask, u32 value)
 {
@@ -1838,7 +1834,7 @@ static void intel_restore_padcfg(struct intel_pinctrl *pctrl, unsigned int pin,
 	dev_dbg(dev, "restored pin %u padcfg%u %#08x\n", pin, n, readl(padcfg));
 }
 
-int intel_pinctrl_resume_noirq(struct device *dev)
+static int intel_pinctrl_resume_noirq(struct device *dev)
 {
 	struct intel_pinctrl *pctrl = dev_get_drvdata(dev);
 	const struct intel_community_context *communities;
@@ -1882,8 +1878,10 @@ int intel_pinctrl_resume_noirq(struct device *dev)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(intel_pinctrl_resume_noirq);
-#endif
+
+EXPORT_NS_GPL_DEV_SLEEP_PM_OPS(intel_pinctrl_pm_ops, PINCTRL_INTEL) = {
+	NOIRQ_SYSTEM_SLEEP_PM_OPS(intel_pinctrl_suspend_noirq, intel_pinctrl_resume_noirq)
+};
 
 MODULE_AUTHOR("Mathias Nyman <mathias.nyman@linux.intel.com>");
 MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>");
diff --git a/drivers/pinctrl/intel/pinctrl-intel.h b/drivers/pinctrl/intel/pinctrl-intel.h
index 2bb553598e8b..fde65e18cd14 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.h
+++ b/drivers/pinctrl/intel/pinctrl-intel.h
@@ -252,19 +252,13 @@ struct intel_pinctrl {
 	int irq;
 };
 
+int intel_pinctrl_probe(struct platform_device *pdev,
+			const struct intel_pinctrl_soc_data *soc_data);
+
 int intel_pinctrl_probe_by_hid(struct platform_device *pdev);
 int intel_pinctrl_probe_by_uid(struct platform_device *pdev);
 
-#ifdef CONFIG_PM_SLEEP
-int intel_pinctrl_suspend_noirq(struct device *dev);
-int intel_pinctrl_resume_noirq(struct device *dev);
-#endif
-
-#define INTEL_PINCTRL_PM_OPS(_name)					\
-const struct dev_pm_ops _name = {					\
-	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(intel_pinctrl_suspend_noirq,	\
-				      intel_pinctrl_resume_noirq)	\
-}
+extern const struct dev_pm_ops intel_pinctrl_pm_ops;
 
 struct intel_community *intel_get_community(struct intel_pinctrl *pctrl, unsigned int pin);
 
diff --git a/drivers/pinctrl/intel/pinctrl-jasperlake.c b/drivers/pinctrl/intel/pinctrl-jasperlake.c
index 50f137deed9c..3525480428ea 100644
--- a/drivers/pinctrl/intel/pinctrl-jasperlake.c
+++ b/drivers/pinctrl/intel/pinctrl-jasperlake.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -326,14 +327,12 @@ static const struct acpi_device_id jsl_pinctrl_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, jsl_pinctrl_acpi_match);
 
-static INTEL_PINCTRL_PM_OPS(jsl_pinctrl_pm_ops);
-
 static struct platform_driver jsl_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_hid,
 	.driver = {
 		.name = "jasperlake-pinctrl",
 		.acpi_match_table = jsl_pinctrl_acpi_match,
-		.pm = &jsl_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 module_platform_driver(jsl_pinctrl_driver);
diff --git a/drivers/pinctrl/intel/pinctrl-lakefield.c b/drivers/pinctrl/intel/pinctrl-lakefield.c
index 0b94e11b78ac..adef85db82ca 100644
--- a/drivers/pinctrl/intel/pinctrl-lakefield.c
+++ b/drivers/pinctrl/intel/pinctrl-lakefield.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -347,14 +348,12 @@ static const struct acpi_device_id lkf_pinctrl_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, lkf_pinctrl_acpi_match);
 
-static INTEL_PINCTRL_PM_OPS(lkf_pinctrl_pm_ops);
-
 static struct platform_driver lkf_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_hid,
 	.driver = {
 		.name = "lakefield-pinctrl",
 		.acpi_match_table = lkf_pinctrl_acpi_match,
-		.pm = &lkf_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 module_platform_driver(lkf_pinctrl_driver);
diff --git a/drivers/pinctrl/intel/pinctrl-lewisburg.c b/drivers/pinctrl/intel/pinctrl-lewisburg.c
index aa725a5d62b9..a304d30ea9ed 100644
--- a/drivers/pinctrl/intel/pinctrl-lewisburg.c
+++ b/drivers/pinctrl/intel/pinctrl-lewisburg.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -301,8 +302,6 @@ static const struct intel_pinctrl_soc_data lbg_soc_data = {
 	.ncommunities = ARRAY_SIZE(lbg_communities),
 };
 
-static INTEL_PINCTRL_PM_OPS(lbg_pinctrl_pm_ops);
-
 static const struct acpi_device_id lbg_pinctrl_acpi_match[] = {
 	{ "INT3536", (kernel_ulong_t)&lbg_soc_data },
 	{ }
@@ -314,7 +313,7 @@ static struct platform_driver lbg_pinctrl_driver = {
 	.driver = {
 		.name = "lewisburg-pinctrl",
 		.acpi_match_table = lbg_pinctrl_acpi_match,
-		.pm = &lbg_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 module_platform_driver(lbg_pinctrl_driver);
diff --git a/drivers/pinctrl/intel/pinctrl-lynxpoint.c b/drivers/pinctrl/intel/pinctrl-lynxpoint.c
index e6878e4cf20c..1fb0bba8b386 100644
--- a/drivers/pinctrl/intel/pinctrl-lynxpoint.c
+++ b/drivers/pinctrl/intel/pinctrl-lynxpoint.c
@@ -10,6 +10,7 @@
 #include <linux/acpi.h>
 #include <linux/array_size.h>
 #include <linux/bitops.h>
+#include <linux/cleanup.h>
 #include <linux/gpio/driver.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -291,10 +292,9 @@ static int lp_pinmux_set_mux(struct pinctrl_dev *pctldev,
 {
 	struct intel_pinctrl *lg = pinctrl_dev_get_drvdata(pctldev);
 	const struct intel_pingroup *grp = &lg->soc->groups[group];
-	unsigned long flags;
 	int i;
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
+	guard(raw_spinlock_irqsave)(&lg->lock);
 
 	/* Now enable the mux setting for each pin in the group */
 	for (i = 0; i < grp->grp.npins; i++) {
@@ -312,8 +312,6 @@ static int lp_pinmux_set_mux(struct pinctrl_dev *pctldev,
 		iowrite32(value, reg);
 	}
 
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
-
 	return 0;
 }
 
@@ -334,10 +332,9 @@ static int lp_gpio_request_enable(struct pinctrl_dev *pctldev,
 	struct intel_pinctrl *lg = pinctrl_dev_get_drvdata(pctldev);
 	void __iomem *reg = lp_gpio_reg(&lg->chip, pin, LP_CONFIG1);
 	void __iomem *conf2 = lp_gpio_reg(&lg->chip, pin, LP_CONFIG2);
-	unsigned long flags;
 	u32 value;
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
+	guard(raw_spinlock_irqsave)(&lg->lock);
 
 	/*
 	 * Reconfigure pin to GPIO mode if needed and issue a warning,
@@ -352,8 +349,6 @@ static int lp_gpio_request_enable(struct pinctrl_dev *pctldev,
 	/* Enable input sensing */
 	lp_gpio_enable_input(conf2);
 
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
-
 	return 0;
 }
 
@@ -363,14 +358,11 @@ static void lp_gpio_disable_free(struct pinctrl_dev *pctldev,
 {
 	struct intel_pinctrl *lg = pinctrl_dev_get_drvdata(pctldev);
 	void __iomem *conf2 = lp_gpio_reg(&lg->chip, pin, LP_CONFIG2);
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
+	guard(raw_spinlock_irqsave)(&lg->lock);
 
 	/* Disable input sensing */
 	lp_gpio_disable_input(conf2);
-
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
 }
 
 static int lp_gpio_set_direction(struct pinctrl_dev *pctldev,
@@ -379,10 +371,9 @@ static int lp_gpio_set_direction(struct pinctrl_dev *pctldev,
 {
 	struct intel_pinctrl *lg = pinctrl_dev_get_drvdata(pctldev);
 	void __iomem *reg = lp_gpio_reg(&lg->chip, pin, LP_CONFIG1);
-	unsigned long flags;
 	u32 value;
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
+	guard(raw_spinlock_irqsave)(&lg->lock);
 
 	value = ioread32(reg);
 	value &= ~DIR_BIT;
@@ -400,8 +391,6 @@ static int lp_gpio_set_direction(struct pinctrl_dev *pctldev,
 	}
 	iowrite32(value, reg);
 
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
-
 	return 0;
 }
 
@@ -421,13 +410,11 @@ static int lp_pin_config_get(struct pinctrl_dev *pctldev, unsigned int pin,
 	struct intel_pinctrl *lg = pinctrl_dev_get_drvdata(pctldev);
 	void __iomem *conf2 = lp_gpio_reg(&lg->chip, pin, LP_CONFIG2);
 	enum pin_config_param param = pinconf_to_config_param(*config);
-	unsigned long flags;
 	u32 value, pull;
 	u16 arg;
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
-	value = ioread32(conf2);
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
+	scoped_guard(raw_spinlock_irqsave, &lg->lock)
+		value = ioread32(conf2);
 
 	pull = value & GPIWP_MASK;
 
@@ -464,11 +451,10 @@ static int lp_pin_config_set(struct pinctrl_dev *pctldev, unsigned int pin,
 	struct intel_pinctrl *lg = pinctrl_dev_get_drvdata(pctldev);
 	void __iomem *conf2 = lp_gpio_reg(&lg->chip, pin, LP_CONFIG2);
 	enum pin_config_param param;
-	unsigned long flags;
-	int i, ret = 0;
+	unsigned int i;
 	u32 value;
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
+	guard(raw_spinlock_irqsave)(&lg->lock);
 
 	value = ioread32(conf2);
 
@@ -489,19 +475,13 @@ static int lp_pin_config_set(struct pinctrl_dev *pctldev, unsigned int pin,
 			value |= GPIWP_UP;
 			break;
 		default:
-			ret = -ENOTSUPP;
+			return -ENOTSUPP;
 		}
-
-		if (ret)
-			break;
 	}
 
-	if (!ret)
-		iowrite32(value, conf2);
+	iowrite32(value, conf2);
 
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
-
-	return ret;
+	return 0;
 }
 
 static const struct pinconf_ops lptlp_pinconf_ops = {
@@ -527,16 +507,13 @@ static void lp_gpio_set(struct gpio_chip *chip, unsigned int offset, int value)
 {
 	struct intel_pinctrl *lg = gpiochip_get_data(chip);
 	void __iomem *reg = lp_gpio_reg(chip, offset, LP_CONFIG1);
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
+	guard(raw_spinlock_irqsave)(&lg->lock);
 
 	if (value)
 		iowrite32(ioread32(reg) | OUT_LVL_BIT, reg);
 	else
 		iowrite32(ioread32(reg) & ~OUT_LVL_BIT, reg);
-
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
 }
 
 static int lp_gpio_direction_input(struct gpio_chip *chip, unsigned int offset)
@@ -592,11 +569,10 @@ static void lp_irq_ack(struct irq_data *d)
 	struct intel_pinctrl *lg = gpiochip_get_data(gc);
 	irq_hw_number_t hwirq = irqd_to_hwirq(d);
 	void __iomem *reg = lp_gpio_reg(&lg->chip, hwirq, LP_INT_STAT);
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
+	guard(raw_spinlock_irqsave)(&lg->lock);
+
 	iowrite32(BIT(hwirq % 32), reg);
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
 }
 
 static void lp_irq_unmask(struct irq_data *d)
@@ -613,13 +589,11 @@ static void lp_irq_enable(struct irq_data *d)
 	struct intel_pinctrl *lg = gpiochip_get_data(gc);
 	irq_hw_number_t hwirq = irqd_to_hwirq(d);
 	void __iomem *reg = lp_gpio_reg(&lg->chip, hwirq, LP_INT_ENABLE);
-	unsigned long flags;
 
 	gpiochip_enable_irq(gc, hwirq);
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
-	iowrite32(ioread32(reg) | BIT(hwirq % 32), reg);
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
+	scoped_guard(raw_spinlock_irqsave, &lg->lock)
+		iowrite32(ioread32(reg) | BIT(hwirq % 32), reg);
 }
 
 static void lp_irq_disable(struct irq_data *d)
@@ -628,11 +602,9 @@ static void lp_irq_disable(struct irq_data *d)
 	struct intel_pinctrl *lg = gpiochip_get_data(gc);
 	irq_hw_number_t hwirq = irqd_to_hwirq(d);
 	void __iomem *reg = lp_gpio_reg(&lg->chip, hwirq, LP_INT_ENABLE);
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
-	iowrite32(ioread32(reg) & ~BIT(hwirq % 32), reg);
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
+	scoped_guard(raw_spinlock_irqsave, &lg->lock)
+		iowrite32(ioread32(reg) & ~BIT(hwirq % 32), reg);
 
 	gpiochip_disable_irq(gc, hwirq);
 }
@@ -642,7 +614,6 @@ static int lp_irq_set_type(struct irq_data *d, unsigned int type)
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct intel_pinctrl *lg = gpiochip_get_data(gc);
 	irq_hw_number_t hwirq = irqd_to_hwirq(d);
-	unsigned long flags;
 	void __iomem *reg;
 	u32 value;
 
@@ -656,7 +627,8 @@ static int lp_irq_set_type(struct irq_data *d, unsigned int type)
 		return -EBUSY;
 	}
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
+	guard(raw_spinlock_irqsave)(&lg->lock);
+
 	value = ioread32(reg);
 
 	/* set both TRIG_SEL and INV bits to 0 for rising edge */
@@ -682,8 +654,6 @@ static int lp_irq_set_type(struct irq_data *d, unsigned int type)
 	else if (type & IRQ_TYPE_LEVEL_MASK)
 		irq_set_handler_locked(d, handle_level_irq);
 
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
-
 	return 0;
 }
 
diff --git a/drivers/pinctrl/intel/pinctrl-meteorlake.c b/drivers/pinctrl/intel/pinctrl-meteorlake.c
index 7ced2b402dce..cc44890c6699 100644
--- a/drivers/pinctrl/intel/pinctrl-meteorlake.c
+++ b/drivers/pinctrl/intel/pinctrl-meteorlake.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -589,14 +590,12 @@ static const struct acpi_device_id mtl_pinctrl_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, mtl_pinctrl_acpi_match);
 
-static INTEL_PINCTRL_PM_OPS(mtl_pinctrl_pm_ops);
-
 static struct platform_driver mtl_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_hid,
 	.driver = {
 		.name = "meteorlake-pinctrl",
 		.acpi_match_table = mtl_pinctrl_acpi_match,
-		.pm = &mtl_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 module_platform_driver(mtl_pinctrl_driver);
diff --git a/drivers/pinctrl/intel/pinctrl-meteorpoint.c b/drivers/pinctrl/intel/pinctrl-meteorpoint.c
new file mode 100644
index 000000000000..77e97775a60b
--- /dev/null
+++ b/drivers/pinctrl/intel/pinctrl-meteorpoint.c
@@ -0,0 +1,465 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel Meteor Point PCH pinctrl/GPIO driver
+ *
+ * Copyright (C) 2022-2023, Intel Corporation
+ * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ */
+
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+
+#include <linux/pinctrl/pinctrl.h>
+
+#include "pinctrl-intel.h"
+
+#define MTP_PAD_OWN	0x0b0
+#define MTP_PADCFGLOCK	0x110
+#define MTP_HOSTSW_OWN	0x150
+#define MTP_GPI_IS	0x200
+#define MTP_GPI_IE	0x220
+
+#define MTP_GPP(r, s, e, g)				\
+	{						\
+		.reg_num = (r),				\
+		.base = (s),				\
+		.size = ((e) - (s) + 1),		\
+		.gpio_base = (g),			\
+	}
+
+#define MTP_COMMUNITY(b, s, e, g)			\
+	INTEL_COMMUNITY_GPPS(b, s, e, g, MTP)
+
+/* Meteor Point-S */
+static const struct pinctrl_pin_desc mtps_pins[] = {
+	/* GPP_D */
+	PINCTRL_PIN(0, "GPP_D_0"),
+	PINCTRL_PIN(1, "GPP_D_1"),
+	PINCTRL_PIN(2, "GPP_D_2"),
+	PINCTRL_PIN(3, "GPP_D_3"),
+	PINCTRL_PIN(4, "GPP_D_4"),
+	PINCTRL_PIN(5, "CNV_RF_RESET_B"),
+	PINCTRL_PIN(6, "CRF_CLKREQ"),
+	PINCTRL_PIN(7, "GPP_D_7"),
+	PINCTRL_PIN(8, "GPP_D_8"),
+	PINCTRL_PIN(9, "SML0CLK"),
+	PINCTRL_PIN(10, "SML0DATA"),
+	PINCTRL_PIN(11, "GPP_D_11"),
+	PINCTRL_PIN(12, "GPP_D_12"),
+	PINCTRL_PIN(13, "GPP_D_13"),
+	PINCTRL_PIN(14, "GPP_D_14"),
+	PINCTRL_PIN(15, "GPP_D_15"),
+	PINCTRL_PIN(16, "GPP_D_16"),
+	PINCTRL_PIN(17, "GPP_D_17"),
+	PINCTRL_PIN(18, "GPP_D_18"),
+	PINCTRL_PIN(19, "GPP_D_19"),
+	PINCTRL_PIN(20, "GPP_D_20"),
+	PINCTRL_PIN(21, "GPP_D_21"),
+	PINCTRL_PIN(22, "GPP_D_22"),
+	PINCTRL_PIN(23, "GPP_D_23"),
+	PINCTRL_PIN(24, "GSPI3_CLK_LOOPBK"),
+	/* GPP_R */
+	PINCTRL_PIN(25, "HDA_BCLK"),
+	PINCTRL_PIN(26, "HDA_SYNC"),
+	PINCTRL_PIN(27, "HDA_SDO"),
+	PINCTRL_PIN(28, "HDA_SDI_0"),
+	PINCTRL_PIN(29, "HDA_RSTB"),
+	PINCTRL_PIN(30, "GPP_R_5"),
+	PINCTRL_PIN(31, "GPP_R_6"),
+	PINCTRL_PIN(32, "GPP_R_7"),
+	PINCTRL_PIN(33, "GPP_R_8"),
+	PINCTRL_PIN(34, "GPP_R_9"),
+	PINCTRL_PIN(35, "GPP_R_10"),
+	PINCTRL_PIN(36, "GPP_R_11"),
+	PINCTRL_PIN(37, "GPP_R_12"),
+	PINCTRL_PIN(38, "GSPI2_CLK_LOOPBK"),
+	/* GPP_J */
+	PINCTRL_PIN(39, "GPP_J_0"),
+	PINCTRL_PIN(40, "CNV_BRI_DT"),
+	PINCTRL_PIN(41, "CNV_BRI_RSP"),
+	PINCTRL_PIN(42, "CNV_RGI_DT"),
+	PINCTRL_PIN(43, "CNV_RGI_RSP"),
+	PINCTRL_PIN(44, "GPP_J_5"),
+	PINCTRL_PIN(45, "GPP_J_6"),
+	PINCTRL_PIN(46, "BOOTHALT_B"),
+	PINCTRL_PIN(47, "RTCCLKOUT"),
+	PINCTRL_PIN(48, "BPKI3C_SDA"),
+	PINCTRL_PIN(49, "BPKI3C_SCL"),
+	PINCTRL_PIN(50, "DAM"),
+	PINCTRL_PIN(51, "HDACPU_SDI"),
+	PINCTRL_PIN(52, "HDACPU_SDO"),
+	PINCTRL_PIN(53, "HDACPU_BCLK"),
+	PINCTRL_PIN(54, "AUX_PWRGD"),
+	PINCTRL_PIN(55, "GLB_RST_WARN_B"),
+	PINCTRL_PIN(56, "RESET_SYNCB"),
+	/* vGPIO */
+	PINCTRL_PIN(57, "CNV_BTEN"),
+	PINCTRL_PIN(58, "CNV_BT_HOST_WAKEB"),
+	PINCTRL_PIN(59, "CNV_BT_IF_SELECT"),
+	PINCTRL_PIN(60, "vCNV_BT_UART_TXD"),
+	PINCTRL_PIN(61, "vCNV_BT_UART_RXD"),
+	PINCTRL_PIN(62, "vCNV_BT_UART_CTS_B"),
+	PINCTRL_PIN(63, "vCNV_BT_UART_RTS_B"),
+	PINCTRL_PIN(64, "vCNV_MFUART1_TXD"),
+	PINCTRL_PIN(65, "vCNV_MFUART1_RXD"),
+	PINCTRL_PIN(66, "vCNV_MFUART1_CTS_B"),
+	PINCTRL_PIN(67, "vCNV_MFUART1_RTS_B"),
+	PINCTRL_PIN(68, "vUART0_TXD"),
+	PINCTRL_PIN(69, "vUART0_RXD"),
+	PINCTRL_PIN(70, "vUART0_CTS_B"),
+	PINCTRL_PIN(71, "vUART0_RTS_B"),
+	PINCTRL_PIN(72, "vISH_UART0_TXD"),
+	PINCTRL_PIN(73, "vISH_UART0_RXD"),
+	PINCTRL_PIN(74, "vISH_UART0_CTS_B"),
+	PINCTRL_PIN(75, "vISH_UART0_RTS_B"),
+	PINCTRL_PIN(76, "vCNV_BT_I2S_BCLK"),
+	PINCTRL_PIN(77, "vCNV_BT_I2S_WS_SYNC"),
+	PINCTRL_PIN(78, "vCNV_BT_I2S_SDO"),
+	PINCTRL_PIN(79, "vCNV_BT_I2S_SDI"),
+	PINCTRL_PIN(80, "vI2S2_SCLK"),
+	PINCTRL_PIN(81, "vI2S2_SFRM"),
+	PINCTRL_PIN(82, "vI2S2_TXD"),
+	PINCTRL_PIN(83, "vI2S2_RXD"),
+	PINCTRL_PIN(84, "THC0_WOT_INT"),
+	PINCTRL_PIN(85, "THC1_WOT_INT"),
+	PINCTRL_PIN(86, "THC0_WHC_INT"),
+	PINCTRL_PIN(87, "THC1_WHC_INT"),
+	/* GPP_A */
+	PINCTRL_PIN(88, "ESPI_IO_0"),
+	PINCTRL_PIN(89, "ESPI_IO_1"),
+	PINCTRL_PIN(90, "ESPI_IO_2"),
+	PINCTRL_PIN(91, "ESPI_IO_3"),
+	PINCTRL_PIN(92, "ESPI_CS0B"),
+	PINCTRL_PIN(93, "ESPI_CLK"),
+	PINCTRL_PIN(94, "ESPI_RESETB"),
+	PINCTRL_PIN(95, "ESPI_CS1B"),
+	PINCTRL_PIN(96, "ESPI_CS2B"),
+	PINCTRL_PIN(97, "ESPI_CS3B"),
+	PINCTRL_PIN(98, "ESPI_ALERT0B"),
+	PINCTRL_PIN(99, "ESPI_ALERT1B"),
+	PINCTRL_PIN(100, "ESPI_ALERT2B"),
+	PINCTRL_PIN(101, "ESPI_ALERT3B"),
+	PINCTRL_PIN(102, "ESPI_CLK_LOOPBK"),
+	/* DIR_ESPI */
+	PINCTRL_PIN(103, "PWRBTNB_OUT"),
+	PINCTRL_PIN(104, "DMI_PERSTB"),
+	PINCTRL_PIN(105, "DMI_CLKREQB"),
+	PINCTRL_PIN(106, "DIR_ESPI_IO_0"),
+	PINCTRL_PIN(107, "DIR_ESPI_IO_1"),
+	PINCTRL_PIN(108, "DIR_ESPI_IO_2"),
+	PINCTRL_PIN(109, "DIR_ESPI_IO_3"),
+	PINCTRL_PIN(110, "DIR_ESPI_CSB"),
+	PINCTRL_PIN(111, "DIR_ESPI_RESETB"),
+	PINCTRL_PIN(112, "DIR_ESPI_CLK"),
+	PINCTRL_PIN(113, "DIR_ESPI_RCLK"),
+	PINCTRL_PIN(114, "DIR_ESPI_ALERTB"),
+	/* GPP_B */
+	PINCTRL_PIN(115, "GPP_B_0"),
+	PINCTRL_PIN(116, "GPP_B_1"),
+	PINCTRL_PIN(117, "GPP_B_2"),
+	PINCTRL_PIN(118, "GPP_B_3"),
+	PINCTRL_PIN(119, "GPP_B_4"),
+	PINCTRL_PIN(120, "GPP_B_5"),
+	PINCTRL_PIN(121, "CLKOUT_48"),
+	PINCTRL_PIN(122, "GPP_B_7"),
+	PINCTRL_PIN(123, "GPP_B_8"),
+	PINCTRL_PIN(124, "GPP_B_9"),
+	PINCTRL_PIN(125, "GPP_B_10"),
+	PINCTRL_PIN(126, "GPP_B_11"),
+	PINCTRL_PIN(127, "SLP_S0B"),
+	PINCTRL_PIN(128, "PLTRSTB"),
+	PINCTRL_PIN(129, "GPP_B_14"),
+	PINCTRL_PIN(130, "GPP_B_15"),
+	PINCTRL_PIN(131, "GPP_B_16"),
+	PINCTRL_PIN(132, "GPP_B_17"),
+	PINCTRL_PIN(133, "GPP_B_18"),
+	PINCTRL_PIN(134, "FUSA_DIAGTEST_EN"),
+	PINCTRL_PIN(135, "FUSA_DIAGTEST_MODE"),
+	PINCTRL_PIN(136, "GPP_B_21"),
+	/* SPI0 */
+	PINCTRL_PIN(137, "SPI0_IO_2"),
+	PINCTRL_PIN(138, "SPI0_IO_3"),
+	PINCTRL_PIN(139, "SPI0_MOSI_IO_0"),
+	PINCTRL_PIN(140, "SPI0_MISO_IO_1"),
+	PINCTRL_PIN(141, "SPI0_TPM_CSB"),
+	PINCTRL_PIN(142, "SPI0_FLASH_0_CSB"),
+	PINCTRL_PIN(143, "SPI0_FLASH_1_CSB"),
+	PINCTRL_PIN(144, "SPI0_CLK"),
+	PINCTRL_PIN(145, "SPI0_CLK_LOOPBK"),
+	/* GPP_C */
+	PINCTRL_PIN(146, "SMBCLK"),
+	PINCTRL_PIN(147, "SMBDATA"),
+	PINCTRL_PIN(148, "SMBALERTB"),
+	PINCTRL_PIN(149, "GPP_C_3"),
+	PINCTRL_PIN(150, "GPP_C_4"),
+	PINCTRL_PIN(151, "GPP_C_5"),
+	PINCTRL_PIN(152, "GPP_C_6"),
+	PINCTRL_PIN(153, "GPP_C_7"),
+	PINCTRL_PIN(154, "GPP_C_8"),
+	PINCTRL_PIN(155, "GPP_C_9"),
+	PINCTRL_PIN(156, "GPP_C_10"),
+	PINCTRL_PIN(157, "GPP_C_11"),
+	PINCTRL_PIN(158, "GPP_C_12"),
+	PINCTRL_PIN(159, "GPP_C_13"),
+	PINCTRL_PIN(160, "GPP_C_14"),
+	PINCTRL_PIN(161, "GPP_C_15"),
+	PINCTRL_PIN(162, "GPP_C_16"),
+	PINCTRL_PIN(163, "GPP_C_17"),
+	PINCTRL_PIN(164, "GPP_C_18"),
+	PINCTRL_PIN(165, "GPP_C_19"),
+	PINCTRL_PIN(166, "GPP_C_20"),
+	PINCTRL_PIN(167, "GPP_C_21"),
+	PINCTRL_PIN(168, "GPP_C_22"),
+	PINCTRL_PIN(169, "GPP_C_23"),
+	/* GPP_H */
+	PINCTRL_PIN(170, "GPP_H_0"),
+	PINCTRL_PIN(171, "GPP_H_1"),
+	PINCTRL_PIN(172, "GPP_H_2"),
+	PINCTRL_PIN(173, "GPP_H_3"),
+	PINCTRL_PIN(174, "GPP_H_4"),
+	PINCTRL_PIN(175, "GPP_H_5"),
+	PINCTRL_PIN(176, "GPP_H_6"),
+	PINCTRL_PIN(177, "GPP_H_7"),
+	PINCTRL_PIN(178, "GPP_H_8"),
+	PINCTRL_PIN(179, "GPP_H_9"),
+	PINCTRL_PIN(180, "GPP_H_10"),
+	PINCTRL_PIN(181, "GPP_H_11"),
+	PINCTRL_PIN(182, "GPP_H_12"),
+	PINCTRL_PIN(183, "GPP_H_13"),
+	PINCTRL_PIN(184, "GPP_H_14"),
+	PINCTRL_PIN(185, "GPP_H_15"),
+	PINCTRL_PIN(186, "GPP_H_16"),
+	PINCTRL_PIN(187, "GPP_H_17"),
+	PINCTRL_PIN(188, "GPP_H_18"),
+	PINCTRL_PIN(189, "GPP_H_19"),
+	/* vGPIO_3 */
+	PINCTRL_PIN(190, "CPU_PCIE_LNK_DN_0"),
+	PINCTRL_PIN(191, "CPU_PCIE_LNK_DN_1"),
+	PINCTRL_PIN(192, "CPU_PCIE_LNK_DN_2"),
+	PINCTRL_PIN(193, "CPU_PCIE_LNK_DN_3"),
+	/* vGPIO_0 */
+	PINCTRL_PIN(194, "ESPI_USB_OCB_0"),
+	PINCTRL_PIN(195, "ESPI_USB_OCB_1"),
+	PINCTRL_PIN(196, "ESPI_USB_OCB_2"),
+	PINCTRL_PIN(197, "ESPI_USB_OCB_3"),
+	PINCTRL_PIN(198, "USB_CPU_OCB_0"),
+	PINCTRL_PIN(199, "USB_CPU_OCB_1"),
+	PINCTRL_PIN(200, "USB_CPU_OCB_2"),
+	PINCTRL_PIN(201, "USB_CPU_OCB_3"),
+	/* vGPIO_4 */
+	PINCTRL_PIN(202, "ESPI_ISCLK_XTAL_CLKREQ"),
+	PINCTRL_PIN(203, "ISCLK_ESPI_XTAL_CLKACK"),
+	PINCTRL_PIN(204, "ME_SLPC_FTPM_ENABLE"),
+	PINCTRL_PIN(205, "GP_SLPC_DTFUS_CORE_SPITPM_DIS"),
+	PINCTRL_PIN(206, "GP_SLPC_SPI_STRAP_TOS"),
+	PINCTRL_PIN(207, "GP_SLPC_DTFUS_CORE_SPITPM_DIS_L01"),
+	PINCTRL_PIN(208, "GP_SLPC_SPI_STRAP_TOS_L01"),
+	PINCTRL_PIN(209, "LPC_PRR_TS_OVR"),
+	PINCTRL_PIN(210, "ITSS_KU1_SHTDWN"),
+	PINCTRL_PIN(211, "vGPIO_SPARE_0"),
+	PINCTRL_PIN(212, "vGPIO_SPARE_1"),
+	PINCTRL_PIN(213, "vGPIO_SPARE_2"),
+	PINCTRL_PIN(214, "vGPIO_SPARE_3"),
+	PINCTRL_PIN(215, "vGPIO_SPARE_4"),
+	PINCTRL_PIN(216, "vGPIO_SPARE_5"),
+	PINCTRL_PIN(217, "vGPIO_SPARE_6"),
+	PINCTRL_PIN(218, "vGPIO_SPARE_7"),
+	PINCTRL_PIN(219, "vGPIO_SPARE_8"),
+	PINCTRL_PIN(220, "vGPIO_SPARE_9"),
+	PINCTRL_PIN(221, "vGPIO_SPARE_10"),
+	PINCTRL_PIN(222, "vGPIO_SPARE_11"),
+	PINCTRL_PIN(223, "vGPIO_SPARE_12"),
+	PINCTRL_PIN(224, "vGPIO_SPARE_13"),
+	PINCTRL_PIN(225, "vGPIO_SPARE_14"),
+	PINCTRL_PIN(226, "vGPIO_SPARE_15"),
+	PINCTRL_PIN(227, "vGPIO_SPARE_16"),
+	PINCTRL_PIN(228, "vGPIO_SPARE_17"),
+	PINCTRL_PIN(229, "vGPIO_SPARE_18"),
+	PINCTRL_PIN(230, "vGPIO_SPARE_19"),
+	PINCTRL_PIN(231, "vGPIO_SPARE_20"),
+	PINCTRL_PIN(232, "vGPIO_SPARE_21"),
+	/* GPP_S */
+	PINCTRL_PIN(233, "GPP_S_0"),
+	PINCTRL_PIN(234, "GPP_S_1"),
+	PINCTRL_PIN(235, "GPP_S_2"),
+	PINCTRL_PIN(236, "GPP_S_3"),
+	PINCTRL_PIN(237, "GPP_S_4"),
+	PINCTRL_PIN(238, "GPP_S_5"),
+	PINCTRL_PIN(239, "GPP_S_6"),
+	PINCTRL_PIN(240, "GPP_S_7"),
+	/* GPP_E */
+	PINCTRL_PIN(241, "GPP_E_0"),
+	PINCTRL_PIN(242, "GPP_E_1"),
+	PINCTRL_PIN(243, "GPP_E_2"),
+	PINCTRL_PIN(244, "GPP_E_3"),
+	PINCTRL_PIN(245, "GPP_E_4"),
+	PINCTRL_PIN(246, "GPP_E_5"),
+	PINCTRL_PIN(247, "GPP_E_6"),
+	PINCTRL_PIN(248, "GPP_E_7"),
+	PINCTRL_PIN(249, "GPP_E_8"),
+	PINCTRL_PIN(250, "GPP_E_9"),
+	PINCTRL_PIN(251, "GPP_E_10"),
+	PINCTRL_PIN(252, "GPP_E_11"),
+	PINCTRL_PIN(253, "GPP_E_12"),
+	PINCTRL_PIN(254, "GPP_E_13"),
+	PINCTRL_PIN(255, "GPP_E_14"),
+	PINCTRL_PIN(256, "GPP_E_15"),
+	PINCTRL_PIN(257, "GPP_E_16"),
+	PINCTRL_PIN(258, "GPP_E_17"),
+	PINCTRL_PIN(259, "GPP_E_18"),
+	PINCTRL_PIN(260, "GPP_E_19"),
+	PINCTRL_PIN(261, "GPP_E_20"),
+	PINCTRL_PIN(262, "GPP_E_21"),
+	PINCTRL_PIN(263, "SPI1_CLK_LOOPBK"),
+	/* GPP_K */
+	PINCTRL_PIN(264, "GPP_K_0"),
+	PINCTRL_PIN(265, "GPP_K_1"),
+	PINCTRL_PIN(266, "GPP_K_2"),
+	PINCTRL_PIN(267, "GPP_K_3"),
+	PINCTRL_PIN(268, "GPP_K_4"),
+	PINCTRL_PIN(269, "GPP_K_5"),
+	PINCTRL_PIN(270, "FUSE_SORT_BUMP_0"),
+	PINCTRL_PIN(271, "FUSE_SORT_BUMP_1"),
+	PINCTRL_PIN(272, "CORE_VID_0"),
+	PINCTRL_PIN(273, "CORE_VID_1"),
+	PINCTRL_PIN(274, "FUSE_SORT_BUMP_2"),
+	PINCTRL_PIN(275, "MISC_SPARE"),
+	PINCTRL_PIN(276, "SYS_RESETB"),
+	PINCTRL_PIN(277, "MLK_RSTB"),
+	/* GPP_F */
+	PINCTRL_PIN(278, "SATAXPCIE_3"),
+	PINCTRL_PIN(279, "SATAXPCIE_4"),
+	PINCTRL_PIN(280, "SATAXPCIE_5"),
+	PINCTRL_PIN(281, "SATAXPCIE_6"),
+	PINCTRL_PIN(282, "SATAXPCIE_7"),
+	PINCTRL_PIN(283, "SATA_DEVSLP_3"),
+	PINCTRL_PIN(284, "SATA_DEVSLP_4"),
+	PINCTRL_PIN(285, "SATA_DEVSLP_5"),
+	PINCTRL_PIN(286, "SATA_DEVSLP_6"),
+	PINCTRL_PIN(287, "GPP_F_9"),
+	PINCTRL_PIN(288, "GPP_F_10"),
+	PINCTRL_PIN(289, "GPP_F_11"),
+	PINCTRL_PIN(290, "GPP_F_12"),
+	PINCTRL_PIN(291, "GPP_F_13"),
+	PINCTRL_PIN(292, "GPP_F_14"),
+	PINCTRL_PIN(293, "GPP_F_15"),
+	PINCTRL_PIN(294, "GPP_F_16"),
+	PINCTRL_PIN(295, "GPP_F_17"),
+	PINCTRL_PIN(296, "GPP_F_18"),
+	PINCTRL_PIN(297, "DNX_FORCE_RELOAD"),
+	PINCTRL_PIN(298, "GPP_F_20"),
+	PINCTRL_PIN(299, "GPP_F_21"),
+	PINCTRL_PIN(300, "GPP_F_22"),
+	PINCTRL_PIN(301, "GPP_F_23"),
+	/* GPP_I */
+	PINCTRL_PIN(302, "GPP_I_0"),
+	PINCTRL_PIN(303, "GPP_I_1"),
+	PINCTRL_PIN(304, "GPP_I_2"),
+	PINCTRL_PIN(305, "GPP_I_3"),
+	PINCTRL_PIN(306, "GPP_I_4"),
+	PINCTRL_PIN(307, "GPP_I_5"),
+	PINCTRL_PIN(308, "GPP_I_6"),
+	PINCTRL_PIN(309, "GPP_I_7"),
+	PINCTRL_PIN(310, "GPP_I_8"),
+	PINCTRL_PIN(311, "GPP_I_9"),
+	PINCTRL_PIN(312, "GPP_I_10"),
+	PINCTRL_PIN(313, "GPP_I_11"),
+	PINCTRL_PIN(314, "GPP_I_12"),
+	PINCTRL_PIN(315, "GPP_I_13"),
+	PINCTRL_PIN(316, "GPP_I_14"),
+	PINCTRL_PIN(317, "GPP_I_15"),
+	PINCTRL_PIN(318, "GPP_I_16"),
+	PINCTRL_PIN(319, "GSPI0_CLK_LOOPBK"),
+	PINCTRL_PIN(320, "GSPI1_CLK_LOOPBK"),
+	PINCTRL_PIN(321, "ISH_I3C0_CLK_LOOPBK"),
+	PINCTRL_PIN(322, "I3C0_CLK_LOOPBK"),
+	/* JTAG_CPU */
+	PINCTRL_PIN(323, "JTAG_TDO"),
+	PINCTRL_PIN(324, "JTAGX"),
+	PINCTRL_PIN(325, "PRDYB"),
+	PINCTRL_PIN(326, "PREQB"),
+	PINCTRL_PIN(327, "JTAG_TDI"),
+	PINCTRL_PIN(328, "JTAG_TMS"),
+	PINCTRL_PIN(329, "JTAG_TCK"),
+	PINCTRL_PIN(330, "DBG_PMODE"),
+	PINCTRL_PIN(331, "CPU_TRSTB"),
+	PINCTRL_PIN(332, "CPUPWRGD"),
+	PINCTRL_PIN(333, "PM_SPARE0"),
+	PINCTRL_PIN(334, "PM_SPARE1"),
+	PINCTRL_PIN(335, "CRASHLOG_TRIG_N"),
+	PINCTRL_PIN(336, "TRIGGER_IN"),
+	PINCTRL_PIN(337, "TRIGGER_OUT"),
+	PINCTRL_PIN(338, "FBRK_OUT_N"),
+};
+
+static const struct intel_padgroup mtps_community0_gpps[] = {
+	MTP_GPP(0, 0, 24, 0),		/* GPP_D */
+	MTP_GPP(1, 25, 38, 32),		/* GPP_R */
+	MTP_GPP(2, 39, 56, 64),		/* GPP_J */
+	MTP_GPP(3, 57, 87, 96),		/* vGPIO */
+};
+
+static const struct intel_padgroup mtps_community1_gpps[] = {
+	MTP_GPP(0, 88, 102, 128),	/* GPP_A */
+	MTP_GPP(1, 103, 114, 160),	/* DIR_ESPI */
+	MTP_GPP(2, 115, 136, 192),	/* GPP_B */
+};
+
+static const struct intel_padgroup mtps_community3_gpps[] = {
+	MTP_GPP(0, 137, 145, 224),	/* SPI0 */
+	MTP_GPP(1, 146, 169, 256),	/* GPP_C */
+	MTP_GPP(2, 170, 189, 288),	/* GPP_H */
+	MTP_GPP(3, 190, 193, 320),	/* vGPIO_3 */
+	MTP_GPP(4, 194, 201, 352),	/* vGPIO_0 */
+	MTP_GPP(5, 202, 232, 384),	/* vGPIO_4 */
+};
+
+static const struct intel_padgroup mtps_community4_gpps[] = {
+	MTP_GPP(0, 233, 240, 416),	/* GPP_S */
+	MTP_GPP(1, 241, 263, 448),	/* GPP_E */
+	MTP_GPP(2, 264, 277, 480),	/* GPP_K */
+	MTP_GPP(3, 278, 301, 512),	/* GPP_F */
+};
+
+static const struct intel_padgroup mtps_community5_gpps[] = {
+	MTP_GPP(0, 302, 322, 544),	/* GPP_I */
+	MTP_GPP(1, 323, 338, 576),	/* JTAG_CPU */
+};
+
+static const struct intel_community mtps_communities[] = {
+	MTP_COMMUNITY(0, 0, 87, mtps_community0_gpps),
+	MTP_COMMUNITY(1, 88, 136, mtps_community1_gpps),
+	MTP_COMMUNITY(2, 137, 232, mtps_community3_gpps),
+	MTP_COMMUNITY(3, 233, 301, mtps_community4_gpps),
+	MTP_COMMUNITY(4, 302, 338, mtps_community5_gpps),
+};
+
+static const struct intel_pinctrl_soc_data mtps_soc_data = {
+	.pins = mtps_pins,
+	.npins = ARRAY_SIZE(mtps_pins),
+	.communities = mtps_communities,
+	.ncommunities = ARRAY_SIZE(mtps_communities),
+};
+
+static const struct acpi_device_id mtp_pinctrl_acpi_match[] = {
+	{ "INTC1084", (kernel_ulong_t)&mtps_soc_data },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, mtp_pinctrl_acpi_match);
+
+static struct platform_driver mtp_pinctrl_driver = {
+	.probe = intel_pinctrl_probe_by_hid,
+	.driver = {
+		.name = "meteorpoint-pinctrl",
+		.acpi_match_table = mtp_pinctrl_acpi_match,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
+	},
+};
+module_platform_driver(mtp_pinctrl_driver);
+
+MODULE_AUTHOR("Andy Shevchenko <andriy.shevchenko@linux.intel.com>");
+MODULE_DESCRIPTION("Intel Meteor Point PCH pinctrl/GPIO driver");
+MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS(PINCTRL_INTEL);
diff --git a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
index b7a40ab0bca8..55df9d2cfb1b 100644
--- a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
+++ b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
@@ -10,6 +10,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -579,14 +580,12 @@ static const struct acpi_device_id spt_pinctrl_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, spt_pinctrl_acpi_match);
 
-static INTEL_PINCTRL_PM_OPS(spt_pinctrl_pm_ops);
-
 static struct platform_driver spt_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_hid,
 	.driver = {
 		.name = "sunrisepoint-pinctrl",
 		.acpi_match_table = spt_pinctrl_acpi_match,
-		.pm = &spt_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 
diff --git a/drivers/pinctrl/intel/pinctrl-tangier.c b/drivers/pinctrl/intel/pinctrl-tangier.c
index 40dd60c9e526..2cb0b4758269 100644
--- a/drivers/pinctrl/intel/pinctrl-tangier.c
+++ b/drivers/pinctrl/intel/pinctrl-tangier.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/bits.h>
+#include <linux/cleanup.h>
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/errno.h>
@@ -220,7 +221,6 @@ static int tng_pinmux_set_mux(struct pinctrl_dev *pctldev,
 	const struct intel_pingroup *grp = &tp->groups[group];
 	u32 bits = grp->mode << BUFCFG_PINMODE_SHIFT;
 	u32 mask = BUFCFG_PINMODE_MASK;
-	unsigned long flags;
 	unsigned int i;
 
 	/*
@@ -232,11 +232,11 @@ static int tng_pinmux_set_mux(struct pinctrl_dev *pctldev,
 			return -EBUSY;
 	}
 
+	guard(raw_spinlock_irqsave)(&tp->lock);
+
 	/* Now enable the mux setting for each pin in the group */
-	raw_spin_lock_irqsave(&tp->lock, flags);
 	for (i = 0; i < grp->grp.npins; i++)
 		tng_update_bufcfg(tp, grp->grp.pins[i], bits, mask);
-	raw_spin_unlock_irqrestore(&tp->lock, flags);
 
 	return 0;
 }
@@ -248,14 +248,13 @@ static int tng_gpio_request_enable(struct pinctrl_dev *pctldev,
 	struct tng_pinctrl *tp = pinctrl_dev_get_drvdata(pctldev);
 	u32 bits = BUFCFG_PINMODE_GPIO << BUFCFG_PINMODE_SHIFT;
 	u32 mask = BUFCFG_PINMODE_MASK;
-	unsigned long flags;
 
 	if (!tng_buf_available(tp, pin))
 		return -EBUSY;
 
-	raw_spin_lock_irqsave(&tp->lock, flags);
+	guard(raw_spinlock_irqsave)(&tp->lock);
+
 	tng_update_bufcfg(tp, pin, bits, mask);
-	raw_spin_unlock_irqrestore(&tp->lock, flags);
 
 	return 0;
 }
@@ -360,7 +359,6 @@ static int tng_config_set_pin(struct tng_pinctrl *tp, unsigned int pin,
 	unsigned int param = pinconf_to_config_param(config);
 	unsigned int arg = pinconf_to_config_argument(config);
 	u32 mask, term, value = 0;
-	unsigned long flags;
 
 	switch (param) {
 	case PIN_CONFIG_BIAS_DISABLE:
@@ -368,20 +366,20 @@ static int tng_config_set_pin(struct tng_pinctrl *tp, unsigned int pin,
 		break;
 
 	case PIN_CONFIG_BIAS_PULL_UP:
-		/* Set default strength value in case none is given */
-		if (arg == 1)
-			arg = 20000;
-
 		switch (arg) {
 		case 50000:
 			term = BUFCFG_PUPD_VAL_50K;
 			break;
+		case 1: /* Set default strength value in case none is given */
 		case 20000:
 			term = BUFCFG_PUPD_VAL_20K;
 			break;
 		case 2000:
 			term = BUFCFG_PUPD_VAL_2K;
 			break;
+		case 910:
+			term = BUFCFG_PUPD_VAL_910;
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -391,20 +389,20 @@ static int tng_config_set_pin(struct tng_pinctrl *tp, unsigned int pin,
 		break;
 
 	case PIN_CONFIG_BIAS_PULL_DOWN:
-		/* Set default strength value in case none is given */
-		if (arg == 1)
-			arg = 20000;
-
 		switch (arg) {
 		case 50000:
 			term = BUFCFG_PUPD_VAL_50K;
 			break;
+		case 1: /* Set default strength value in case none is given */
 		case 20000:
 			term = BUFCFG_PUPD_VAL_20K;
 			break;
 		case 2000:
 			term = BUFCFG_PUPD_VAL_2K;
 			break;
+		case 910:
+			term = BUFCFG_PUPD_VAL_910;
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -432,9 +430,9 @@ static int tng_config_set_pin(struct tng_pinctrl *tp, unsigned int pin,
 		return -EINVAL;
 	}
 
-	raw_spin_lock_irqsave(&tp->lock, flags);
+	guard(raw_spinlock_irqsave)(&tp->lock);
+
 	tng_update_bufcfg(tp, pin, value, mask);
-	raw_spin_unlock_irqrestore(&tp->lock, flags);
 
 	return 0;
 }
diff --git a/drivers/pinctrl/intel/pinctrl-tigerlake.c b/drivers/pinctrl/intel/pinctrl-tigerlake.c
index 4768a69a9258..80cd7a06fe5a 100644
--- a/drivers/pinctrl/intel/pinctrl-tigerlake.c
+++ b/drivers/pinctrl/intel/pinctrl-tigerlake.c
@@ -10,6 +10,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -743,14 +744,12 @@ static const struct acpi_device_id tgl_pinctrl_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, tgl_pinctrl_acpi_match);
 
-static INTEL_PINCTRL_PM_OPS(tgl_pinctrl_pm_ops);
-
 static struct platform_driver tgl_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_hid,
 	.driver = {
 		.name = "tigerlake-pinctrl",
 		.acpi_match_table = tgl_pinctrl_acpi_match,
-		.pm = &tgl_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 module_platform_driver(tgl_pinctrl_driver);
diff --git a/drivers/pinctrl/mediatek/pinctrl-moore.c b/drivers/pinctrl/mediatek/pinctrl-moore.c
index c3d59eddd994..d972584c0519 100644
--- a/drivers/pinctrl/mediatek/pinctrl-moore.c
+++ b/drivers/pinctrl/mediatek/pinctrl-moore.c
@@ -56,12 +56,12 @@ static int mtk_pinmux_set_mux(struct pinctrl_dev *pctldev,
 		return -EINVAL;
 
 	dev_dbg(pctldev->dev, "enable function %s group %s\n",
-		func->name, grp->name);
+		func->name, grp->grp.name);
 
-	for (i = 0; i < grp->num_pins; i++) {
+	for (i = 0; i < grp->grp.npins; i++) {
 		const struct mtk_pin_desc *desc;
 		int *pin_modes = grp->data;
-		int pin = grp->pins[i];
+		int pin = grp->grp.pins[i];
 
 		desc = (const struct mtk_pin_desc *)&hw->soc->pins[pin];
 		if (!desc->name)
@@ -602,13 +602,12 @@ static int mtk_build_groups(struct mtk_pinctrl *hw)
 
 	for (i = 0; i < hw->soc->ngrps; i++) {
 		const struct group_desc *group = hw->soc->grps + i;
+		const struct pingroup *grp = &group->grp;
 
-		err = pinctrl_generic_add_group(hw->pctrl, group->name,
-						group->pins, group->num_pins,
+		err = pinctrl_generic_add_group(hw->pctrl, grp->name, grp->pins, grp->npins,
 						group->data);
 		if (err < 0) {
-			dev_err(hw->dev, "Failed to register group %s\n",
-				group->name);
+			dev_err(hw->dev, "Failed to register group %s\n", grp->name);
 			return err;
 		}
 	}
diff --git a/drivers/pinctrl/mediatek/pinctrl-moore.h b/drivers/pinctrl/mediatek/pinctrl-moore.h
index e1b4b82b9d3d..e0313e7a1fe0 100644
--- a/drivers/pinctrl/mediatek/pinctrl-moore.h
+++ b/drivers/pinctrl/mediatek/pinctrl-moore.h
@@ -37,12 +37,10 @@
 		.funcs = NULL,				\
 	}
 
-#define PINCTRL_PIN_GROUP(name, id)			\
-	{						\
-		name,					\
-		id##_pins,				\
-		ARRAY_SIZE(id##_pins),			\
-		id##_funcs,				\
+#define PINCTRL_PIN_GROUP(_name_, id)							\
+	{										\
+		.grp = PINCTRL_PINGROUP(_name_, id##_pins, ARRAY_SIZE(id##_pins)),	\
+		.data = id##_funcs,							\
 	}
 
 int mtk_moore_pinctrl_probe(struct platform_device *pdev,
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt2701.c b/drivers/pinctrl/mediatek/pinctrl-mt2701.c
index 5fb377c1668b..6b1c7122b0fb 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt2701.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt2701.c
@@ -533,7 +533,7 @@ static struct platform_driver mtk_pinctrl_driver = {
 	.driver = {
 		.name = "mediatek-mt2701-pinctrl",
 		.of_match_table = mt2701_pctrl_match,
-		.pm = &mtk_eint_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_eint_pm_ops),
 	},
 };
 
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt2712.c b/drivers/pinctrl/mediatek/pinctrl-mt2712.c
index 8a6daa0db54b..bb7394ae252b 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt2712.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt2712.c
@@ -581,7 +581,7 @@ static struct platform_driver mtk_pinctrl_driver = {
 	.driver = {
 		.name = "mediatek-mt2712-pinctrl",
 		.of_match_table = mt2712_pctrl_match,
-		.pm = &mtk_eint_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_eint_pm_ops),
 	},
 };
 
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt6795.c b/drivers/pinctrl/mediatek/pinctrl-mt6795.c
index 01e855ccd4dd..ee3ae3d2fa7e 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt6795.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt6795.c
@@ -612,7 +612,7 @@ static struct platform_driver mt6795_pinctrl_driver = {
 	.driver = {
 		.name = "mt6795-pinctrl",
 		.of_match_table = mt6795_pctrl_match,
-		.pm = &mtk_paris_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_paris_pinctrl_pm_ops),
 	},
 	.probe = mtk_paris_pinctrl_probe,
 };
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8167.c b/drivers/pinctrl/mediatek/pinctrl-mt8167.c
index ba7f30c3296f..143c26622272 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8167.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8167.c
@@ -334,7 +334,7 @@ static struct platform_driver mtk_pinctrl_driver = {
 	.driver = {
 		.name = "mediatek-mt8167-pinctrl",
 		.of_match_table = mt8167_pctrl_match,
-		.pm = &mtk_eint_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_eint_pm_ops),
 	},
 };
 
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8173.c b/drivers/pinctrl/mediatek/pinctrl-mt8173.c
index 455eec018f93..b214deeafbf1 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8173.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8173.c
@@ -347,7 +347,7 @@ static struct platform_driver mtk_pinctrl_driver = {
 	.driver = {
 		.name = "mediatek-mt8173-pinctrl",
 		.of_match_table = mt8173_pctrl_match,
-		.pm = &mtk_eint_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_eint_pm_ops),
 	},
 };
 
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8183.c b/drivers/pinctrl/mediatek/pinctrl-mt8183.c
index ddc48b725c22..93e482c6b5fd 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8183.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8183.c
@@ -576,7 +576,7 @@ static struct platform_driver mt8183_pinctrl_driver = {
 	.driver = {
 		.name = "mt8183-pinctrl",
 		.of_match_table = mt8183_pinctrl_of_match,
-		.pm = &mtk_paris_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_paris_pinctrl_pm_ops),
 	},
 	.probe = mtk_paris_pinctrl_probe,
 };
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8186.c b/drivers/pinctrl/mediatek/pinctrl-mt8186.c
index a02f7c326970..7be591591cce 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8186.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8186.c
@@ -1255,7 +1255,7 @@ static struct platform_driver mt8186_pinctrl_driver = {
 	.driver = {
 		.name = "mt8186-pinctrl",
 		.of_match_table = mt8186_pinctrl_of_match,
-		.pm = &mtk_paris_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_paris_pinctrl_pm_ops),
 	},
 	.probe = mtk_paris_pinctrl_probe,
 };
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8188.c b/drivers/pinctrl/mediatek/pinctrl-mt8188.c
index c067e043e619..3975e99d9cf4 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8188.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8188.c
@@ -1658,7 +1658,7 @@ static struct platform_driver mt8188_pinctrl_driver = {
 	.driver = {
 		.name = "mt8188-pinctrl",
 		.of_match_table = mt8188_pinctrl_of_match,
-		.pm = &mtk_paris_pinctrl_pm_ops
+		.pm = pm_sleep_ptr(&mtk_paris_pinctrl_pm_ops)
 	},
 	.probe = mtk_paris_pinctrl_probe,
 };
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8192.c b/drivers/pinctrl/mediatek/pinctrl-mt8192.c
index dee1b3aefd36..e3a76381f7f4 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8192.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8192.c
@@ -1420,7 +1420,7 @@ static struct platform_driver mt8192_pinctrl_driver = {
 	.driver = {
 		.name = "mt8192-pinctrl",
 		.of_match_table = mt8192_pinctrl_of_match,
-		.pm = &mtk_paris_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_paris_pinctrl_pm_ops),
 	},
 	.probe = mtk_paris_pinctrl_probe,
 };
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8195.c b/drivers/pinctrl/mediatek/pinctrl-mt8195.c
index 09c4dcef9338..83345c52b2fa 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8195.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8195.c
@@ -968,7 +968,7 @@ static struct platform_driver mt8195_pinctrl_driver = {
 	.driver = {
 		.name = "mt8195-pinctrl",
 		.of_match_table = mt8195_pinctrl_of_match,
-		.pm = &mtk_paris_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_paris_pinctrl_pm_ops),
 	},
 	.probe = mtk_paris_pinctrl_probe,
 };
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8365.c b/drivers/pinctrl/mediatek/pinctrl-mt8365.c
index 1db04bbdb423..e3e0d66cfbbf 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8365.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8365.c
@@ -484,7 +484,7 @@ static struct platform_driver mtk_pinctrl_driver = {
 	.driver = {
 		.name = "mediatek-mt8365-pinctrl",
 		.of_match_table = mt8365_pctrl_match,
-		.pm = &mtk_eint_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_eint_pm_ops),
 	},
 };
 
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8516.c b/drivers/pinctrl/mediatek/pinctrl-mt8516.c
index 950275c47122..abda75d4354e 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8516.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8516.c
@@ -334,7 +334,7 @@ static struct platform_driver mtk_pinctrl_driver = {
 	.driver = {
 		.name = "mediatek-mt8516-pinctrl",
 		.of_match_table = mt8516_pctrl_match,
-		.pm = &mtk_eint_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_eint_pm_ops),
 	},
 };
 
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
index e79d66a04194..d39afc122516 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
@@ -914,9 +914,8 @@ static int mtk_eint_resume(struct device *device)
 	return mtk_eint_do_resume(pctl->eint);
 }
 
-const struct dev_pm_ops mtk_eint_pm_ops = {
-	.suspend_noirq = mtk_eint_suspend,
-	.resume_noirq = mtk_eint_resume,
+EXPORT_GPL_DEV_SLEEP_PM_OPS(mtk_eint_pm_ops) = {
+	NOIRQ_SYSTEM_SLEEP_PM_OPS(mtk_eint_suspend, mtk_eint_resume)
 };
 
 static int mtk_pctrl_build_state(struct platform_device *pdev)
diff --git a/drivers/pinctrl/mediatek/pinctrl-paris.c b/drivers/pinctrl/mediatek/pinctrl-paris.c
index 6392f1e05d02..b6bc31abd2b0 100644
--- a/drivers/pinctrl/mediatek/pinctrl-paris.c
+++ b/drivers/pinctrl/mediatek/pinctrl-paris.c
@@ -1131,9 +1131,8 @@ static int mtk_paris_pinctrl_resume(struct device *device)
 	return mtk_eint_do_resume(pctl->eint);
 }
 
-const struct dev_pm_ops mtk_paris_pinctrl_pm_ops = {
-	.suspend_noirq = mtk_paris_pinctrl_suspend,
-	.resume_noirq = mtk_paris_pinctrl_resume,
+EXPORT_GPL_DEV_SLEEP_PM_OPS(mtk_paris_pinctrl_pm_ops) = {
+	NOIRQ_SYSTEM_SLEEP_PM_OPS(mtk_paris_pinctrl_suspend, mtk_paris_pinctrl_resume)
 };
 
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/pinctrl/mediatek/pinctrl-paris.h b/drivers/pinctrl/mediatek/pinctrl-paris.h
index 8762ac599329..948ce126aa0c 100644
--- a/drivers/pinctrl/mediatek/pinctrl-paris.h
+++ b/drivers/pinctrl/mediatek/pinctrl-paris.h
@@ -49,12 +49,10 @@
 			__VA_ARGS__, { } },				\
 	}
 
-#define PINCTRL_PIN_GROUP(name, id)			\
-	{						\
-		name,					\
-		id##_pins,				\
-		ARRAY_SIZE(id##_pins),			\
-		id##_funcs,				\
+#define PINCTRL_PIN_GROUP(_name_, id)							\
+	{										\
+		.grp = PINCTRL_PINGROUP(_name_,id##_pins, ARRAY_SIZE(id##_pins)),	\
+		.data = id##_funcs,							\
 	}
 
 int mtk_paris_pinctrl_probe(struct platform_device *pdev);
diff --git a/drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c b/drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c
index 1e658721aaba..62a46d824b46 100644
--- a/drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c
+++ b/drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c
@@ -1790,8 +1790,8 @@ static int npcm7xx_config_set_one(struct npcm7xx_pinctrl *npcm,
 		bank->direction_input(&bank->gc, pin % bank->gc.ngpio);
 		break;
 	case PIN_CONFIG_OUTPUT:
-		iowrite32(gpio, bank->base + NPCM7XX_GP_N_OES);
 		bank->direction_output(&bank->gc, pin % bank->gc.ngpio, arg);
+		iowrite32(gpio, bank->base + NPCM7XX_GP_N_OES);
 		break;
 	case PIN_CONFIG_DRIVE_PUSH_PULL:
 		npcm_gpio_clr(&bank->gc, bank->base + NPCM7XX_GP_N_OTYP, gpio);
diff --git a/drivers/pinctrl/nuvoton/pinctrl-wpcm450.c b/drivers/pinctrl/nuvoton/pinctrl-wpcm450.c
index 0cff44b07b29..4589900244c7 100644
--- a/drivers/pinctrl/nuvoton/pinctrl-wpcm450.c
+++ b/drivers/pinctrl/nuvoton/pinctrl-wpcm450.c
@@ -474,9 +474,8 @@ enum {
 #undef WPCM450_GRP
 };
 
-static struct group_desc wpcm450_groups[] = {
-#define WPCM450_GRP(x) { .name = #x, .pins = x ## _pins, \
-			.num_pins = ARRAY_SIZE(x ## _pins) }
+static struct pingroup wpcm450_groups[] = {
+#define WPCM450_GRP(x) PINCTRL_PINGROUP(#x, x ## _pins, ARRAY_SIZE(x ## _pins))
 	WPCM450_GRPS
 #undef WPCM450_GRP
 };
@@ -852,7 +851,7 @@ static int wpcm450_get_group_pins(struct pinctrl_dev *pctldev,
 				  const unsigned int **pins,
 				  unsigned int *npins)
 {
-	*npins = wpcm450_groups[selector].num_pins;
+	*npins = wpcm450_groups[selector].npins;
 	*pins  = wpcm450_groups[selector].pins;
 
 	return 0;
@@ -901,7 +900,7 @@ static int wpcm450_pinmux_set_mux(struct pinctrl_dev *pctldev,
 	struct wpcm450_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev);
 
 	wpcm450_setfunc(pctrl->gcr_regmap, wpcm450_groups[group].pins,
-			wpcm450_groups[group].num_pins, function);
+			wpcm450_groups[group].npins, function);
 
 	return 0;
 }
diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c
index 8313cb5f3b3c..cada5d18ffae 100644
--- a/drivers/pinctrl/pinconf-generic.c
+++ b/drivers/pinctrl/pinconf-generic.c
@@ -57,7 +57,7 @@ static const struct pin_config_item conf_items[] = {
 
 static void pinconf_generic_dump_one(struct pinctrl_dev *pctldev,
 				     struct seq_file *s, const char *gname,
-				     unsigned pin,
+				     unsigned int pin,
 				     const struct pin_config_item *items,
 				     int nitems, int *print_sep)
 {
@@ -110,7 +110,7 @@ static void pinconf_generic_dump_one(struct pinctrl_dev *pctldev,
  * to be specified the other can be NULL/0.
  */
 void pinconf_generic_dump_pins(struct pinctrl_dev *pctldev, struct seq_file *s,
-			       const char *gname, unsigned pin)
+			       const char *gname, unsigned int pin)
 {
 	const struct pinconf_ops *ops = pctldev->desc->confops;
 	int print_sep = 0;
@@ -295,15 +295,15 @@ EXPORT_SYMBOL_GPL(pinconf_generic_parse_dt_config);
 
 int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev,
 		struct device_node *np, struct pinctrl_map **map,
-		unsigned *reserved_maps, unsigned *num_maps,
+		unsigned int *reserved_maps, unsigned int *num_maps,
 		enum pinctrl_map_type type)
 {
 	int ret;
 	const char *function;
 	struct device *dev = pctldev->dev;
 	unsigned long *configs = NULL;
-	unsigned num_configs = 0;
-	unsigned reserve, strings_count;
+	unsigned int num_configs = 0;
+	unsigned int reserve, strings_count;
 	struct property *prop;
 	const char *group;
 	const char *subnode_target_type = "pins";
@@ -379,9 +379,9 @@ EXPORT_SYMBOL_GPL(pinconf_generic_dt_subnode_to_map);
 
 int pinconf_generic_dt_node_to_map(struct pinctrl_dev *pctldev,
 		struct device_node *np_config, struct pinctrl_map **map,
-		unsigned *num_maps, enum pinctrl_map_type type)
+		unsigned int *num_maps, enum pinctrl_map_type type)
 {
-	unsigned reserved_maps;
+	unsigned int reserved_maps;
 	struct device_node *np;
 	int ret;
 
@@ -412,7 +412,7 @@ EXPORT_SYMBOL_GPL(pinconf_generic_dt_node_to_map);
 
 void pinconf_generic_dt_free_map(struct pinctrl_dev *pctldev,
 				 struct pinctrl_map *map,
-				 unsigned num_maps)
+				 unsigned int num_maps)
 {
 	pinctrl_utils_free_map(pctldev, map, num_maps);
 }
diff --git a/drivers/pinctrl/pinconf.c b/drivers/pinctrl/pinconf.c
index 96d853a8f339..dca963633b5d 100644
--- a/drivers/pinctrl/pinconf.c
+++ b/drivers/pinctrl/pinconf.c
@@ -55,7 +55,7 @@ int pinconf_validate_map(const struct pinctrl_map *map, int i)
 	return 0;
 }
 
-int pin_config_get_for_pin(struct pinctrl_dev *pctldev, unsigned pin,
+int pin_config_get_for_pin(struct pinctrl_dev *pctldev, unsigned int pin,
 			   unsigned long *config)
 {
 	const struct pinconf_ops *ops = pctldev->desc->confops;
@@ -199,7 +199,7 @@ int pinconf_apply_setting(const struct pinctrl_setting *setting)
 	return 0;
 }
 
-int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned pin,
+int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned int pin,
 		       unsigned long *configs, size_t nconfigs)
 {
 	const struct pinconf_ops *ops;
@@ -214,7 +214,7 @@ int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned pin,
 #ifdef CONFIG_DEBUG_FS
 
 static void pinconf_show_config(struct seq_file *s, struct pinctrl_dev *pctldev,
-		      unsigned long *configs, unsigned num_configs)
+				unsigned long *configs, unsigned int num_configs)
 {
 	const struct pinconf_ops *confops;
 	int i;
@@ -304,7 +304,7 @@ static void pinconf_dump_pin(struct pinctrl_dev *pctldev,
 static int pinconf_pins_show(struct seq_file *s, void *what)
 {
 	struct pinctrl_dev *pctldev = s->private;
-	unsigned i, pin;
+	unsigned int i, pin;
 
 	seq_puts(s, "Pin config settings per pin\n");
 	seq_puts(s, "Format: pin (name): configs\n");
@@ -333,7 +333,7 @@ static int pinconf_pins_show(struct seq_file *s, void *what)
 }
 
 static void pinconf_dump_group(struct pinctrl_dev *pctldev,
-			       struct seq_file *s, unsigned selector,
+			       struct seq_file *s, unsigned int selector,
 			       const char *gname)
 {
 	const struct pinconf_ops *ops = pctldev->desc->confops;
@@ -348,8 +348,8 @@ static int pinconf_groups_show(struct seq_file *s, void *what)
 {
 	struct pinctrl_dev *pctldev = s->private;
 	const struct pinctrl_ops *pctlops = pctldev->desc->pctlops;
-	unsigned ngroups = pctlops->get_groups_count(pctldev);
-	unsigned selector = 0;
+	unsigned int ngroups = pctlops->get_groups_count(pctldev);
+	unsigned int selector = 0;
 
 	seq_puts(s, "Pin config settings per pin group\n");
 	seq_puts(s, "Format: group (name): configs\n");
diff --git a/drivers/pinctrl/pinconf.h b/drivers/pinctrl/pinconf.h
index 694bfc9961fa..a14c950bc700 100644
--- a/drivers/pinctrl/pinconf.h
+++ b/drivers/pinctrl/pinconf.h
@@ -29,14 +29,14 @@ int pinconf_map_to_setting(const struct pinctrl_map *map,
 void pinconf_free_setting(const struct pinctrl_setting *setting);
 int pinconf_apply_setting(const struct pinctrl_setting *setting);
 
-int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned pin,
+int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned int pin,
 		       unsigned long *configs, size_t nconfigs);
 
 /*
  * You will only be interested in these if you're using PINCONF
  * so don't supply any stubs for these.
  */
-int pin_config_get_for_pin(struct pinctrl_dev *pctldev, unsigned pin,
+int pin_config_get_for_pin(struct pinctrl_dev *pctldev, unsigned int pin,
 			   unsigned long *config);
 int pin_config_group_get(const char *dev_name, const char *pin_group,
 			 unsigned long *config);
@@ -68,7 +68,7 @@ static inline int pinconf_apply_setting(const struct pinctrl_setting *setting)
 	return 0;
 }
 
-static inline int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned pin,
+static inline int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned int pin,
 				     unsigned long *configs, size_t nconfigs)
 {
 	return -ENOTSUPP;
@@ -112,7 +112,7 @@ static inline void pinconf_init_device_debugfs(struct dentry *devroot,
 
 void pinconf_generic_dump_pins(struct pinctrl_dev *pctldev,
 			       struct seq_file *s, const char *gname,
-			       unsigned pin);
+			       unsigned int pin);
 
 void pinconf_generic_dump_config(struct pinctrl_dev *pctldev,
 				 struct seq_file *s, unsigned long config);
@@ -120,7 +120,7 @@ void pinconf_generic_dump_config(struct pinctrl_dev *pctldev,
 
 static inline void pinconf_generic_dump_pins(struct pinctrl_dev *pctldev,
 					     struct seq_file *s,
-					     const char *gname, unsigned pin)
+					     const char *gname, unsigned int pin)
 {
 	return;
 }
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index 03ecb3d1aaf6..49f89b70dcec 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -1159,7 +1159,7 @@ static int amd_gpio_probe(struct platform_device *pdev)
 	}
 
 	ret = devm_request_irq(&pdev->dev, gpio_dev->irq, amd_gpio_irq_handler,
-			       IRQF_SHARED, KBUILD_MODNAME, gpio_dev);
+			       IRQF_SHARED | IRQF_ONESHOT, KBUILD_MODNAME, gpio_dev);
 	if (ret)
 		goto out2;
 
diff --git a/drivers/pinctrl/pinctrl-as3722.c b/drivers/pinctrl/pinctrl-as3722.c
index 6a5f23cf7a2a..0d8c75ce20ed 100644
--- a/drivers/pinctrl/pinctrl-as3722.c
+++ b/drivers/pinctrl/pinctrl-as3722.c
@@ -542,7 +542,6 @@ static int as3722_pinctrl_probe(struct platform_device *pdev)
 
 	as_pci->dev = &pdev->dev;
 	as_pci->as3722 = dev_get_drvdata(pdev->dev.parent);
-	platform_set_drvdata(pdev, as_pci);
 
 	as_pci->pins = as3722_pins_desc;
 	as_pci->num_pins = ARRAY_SIZE(as3722_pins_desc);
@@ -562,7 +561,7 @@ static int as3722_pinctrl_probe(struct platform_device *pdev)
 
 	as_pci->gpio_chip = as3722_gpio_chip;
 	as_pci->gpio_chip.parent = &pdev->dev;
-	ret = gpiochip_add_data(&as_pci->gpio_chip, as_pci);
+	ret = devm_gpiochip_add_data(&pdev->dev, &as_pci->gpio_chip, as_pci);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Couldn't register gpiochip, %d\n", ret);
 		return ret;
@@ -572,21 +571,10 @@ static int as3722_pinctrl_probe(struct platform_device *pdev)
 				0, 0, AS3722_PIN_NUM);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Couldn't add pin range, %d\n", ret);
-		goto fail_range_add;
+		return ret;
 	}
 
 	return 0;
-
-fail_range_add:
-	gpiochip_remove(&as_pci->gpio_chip);
-	return ret;
-}
-
-static void as3722_pinctrl_remove(struct platform_device *pdev)
-{
-	struct as3722_pctrl_info *as_pci = platform_get_drvdata(pdev);
-
-	gpiochip_remove(&as_pci->gpio_chip);
 }
 
 static const struct of_device_id as3722_pinctrl_of_match[] = {
@@ -601,7 +589,6 @@ static struct platform_driver as3722_pinctrl_driver = {
 		.of_match_table = as3722_pinctrl_of_match,
 	},
 	.probe = as3722_pinctrl_probe,
-	.remove_new = as3722_pinctrl_remove,
 };
 module_platform_driver(as3722_pinctrl_driver);
 
diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c
index fe9545c630a2..67b5d160c027 100644
--- a/drivers/pinctrl/pinctrl-cy8c95x0.c
+++ b/drivers/pinctrl/pinctrl-cy8c95x0.c
@@ -58,6 +58,10 @@
 
 #define CY8C95X0_PIN_TO_OFFSET(x) (((x) >= 20) ? ((x) + 4) : (x))
 
+#define CY8C95X0_MUX_REGMAP_TO_PORT(x) ((x) / MUXED_STRIDE)
+#define CY8C95X0_MUX_REGMAP_TO_REG(x) (((x) % MUXED_STRIDE) + CY8C95X0_INTMASK)
+#define CY8C95X0_MUX_REGMAP_TO_OFFSET(x, p) ((x) - CY8C95X0_INTMASK + (p) * MUXED_STRIDE)
+
 static const struct i2c_device_id cy8c95x0_id[] = {
 	{ "cy8c9520", 20, },
 	{ "cy8c9540", 40, },
@@ -119,12 +123,13 @@ static const struct dmi_system_id cy8c95x0_dmi_acpi_irq_info[] = {
 #define MAX_BANK 8
 #define BANK_SZ 8
 #define MAX_LINE	(MAX_BANK * BANK_SZ)
-
+#define MUXED_STRIDE	16
 #define CY8C95X0_GPIO_MASK		GENMASK(7, 0)
 
 /**
  * struct cy8c95x0_pinctrl - driver data
- * @regmap:         Device's regmap
+ * @regmap:         Device's regmap. Only direct access registers.
+ * @muxed_regmap:   Regmap for all muxed registers.
  * @irq_lock:       IRQ bus lock
  * @i2c_lock:       Mutex for the device internal mux register
  * @irq_mask:       I/O bits affected by interrupts
@@ -147,6 +152,7 @@ static const struct dmi_system_id cy8c95x0_dmi_acpi_irq_info[] = {
  */
 struct cy8c95x0_pinctrl {
 	struct regmap *regmap;
+	struct regmap *muxed_regmap;
 	struct mutex irq_lock;
 	struct mutex i2c_lock;
 	DECLARE_BITMAP(irq_mask, MAX_LINE);
@@ -379,6 +385,54 @@ static bool cy8c95x0_precious_register(struct device *dev, unsigned int reg)
 	}
 }
 
+static bool cy8c95x0_muxed_register(unsigned int reg)
+{
+	switch (reg) {
+	case CY8C95X0_INTMASK:
+	case CY8C95X0_PWMSEL:
+	case CY8C95X0_INVERT:
+	case CY8C95X0_DIRECTION:
+	case CY8C95X0_DRV_PU:
+	case CY8C95X0_DRV_PD:
+	case CY8C95X0_DRV_ODH:
+	case CY8C95X0_DRV_ODL:
+	case CY8C95X0_DRV_PP_FAST:
+	case CY8C95X0_DRV_PP_SLOW:
+	case CY8C95X0_DRV_HIZ:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool cy8c95x0_wc_register(unsigned int reg)
+{
+	switch (reg) {
+	case CY8C95X0_DRV_PU:
+	case CY8C95X0_DRV_PD:
+	case CY8C95X0_DRV_ODH:
+	case CY8C95X0_DRV_ODL:
+	case CY8C95X0_DRV_PP_FAST:
+	case CY8C95X0_DRV_PP_SLOW:
+	case CY8C95X0_DRV_HIZ:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool cy8c95x0_quick_path_register(unsigned int reg)
+{
+	switch (reg) {
+	case CY8C95X0_INPUT_(0) ... CY8C95X0_INPUT_(7):
+	case CY8C95X0_INTSTATUS_(0) ... CY8C95X0_INTSTATUS_(7):
+	case CY8C95X0_OUTPUT_(0) ... CY8C95X0_OUTPUT_(7):
+		return true;
+	default:
+		return false;
+	}
+}
+
 static const struct reg_default cy8c95x0_reg_defaults[] = {
 	{ CY8C95X0_OUTPUT_(0), GENMASK(7, 0) },
 	{ CY8C95X0_OUTPUT_(1), GENMASK(7, 0) },
@@ -392,7 +446,89 @@ static const struct reg_default cy8c95x0_reg_defaults[] = {
 	{ CY8C95X0_PWMSEL, 0 },
 };
 
+static int
+cy8c95x0_mux_reg_read(void *context, unsigned int off, unsigned int *val)
+{
+	struct cy8c95x0_pinctrl *chip = context;
+	u8 port = CY8C95X0_MUX_REGMAP_TO_PORT(off);
+	int ret, reg = CY8C95X0_MUX_REGMAP_TO_REG(off);
+
+	mutex_lock(&chip->i2c_lock);
+	/* Select the correct bank */
+	ret = regmap_write(chip->regmap, CY8C95X0_PORTSEL, port);
+	if (ret < 0)
+		goto out;
+
+	/*
+	 * Read the register through direct access regmap. The target range
+	 * is marked volatile.
+	 */
+	ret = regmap_read(chip->regmap, reg, val);
+out:
+	mutex_unlock(&chip->i2c_lock);
+
+	return ret;
+}
+
+static int
+cy8c95x0_mux_reg_write(void *context, unsigned int off, unsigned int val)
+{
+	struct cy8c95x0_pinctrl *chip = context;
+	u8 port = CY8C95X0_MUX_REGMAP_TO_PORT(off);
+	int ret, reg = CY8C95X0_MUX_REGMAP_TO_REG(off);
+
+	mutex_lock(&chip->i2c_lock);
+	/* Select the correct bank */
+	ret = regmap_write(chip->regmap, CY8C95X0_PORTSEL, port);
+	if (ret < 0)
+		goto out;
+
+	/*
+	 * Write the register through direct access regmap. The target range
+	 * is marked volatile.
+	 */
+	ret = regmap_write(chip->regmap, reg, val);
+out:
+	mutex_unlock(&chip->i2c_lock);
+
+	return ret;
+}
+
+static bool cy8c95x0_mux_accessible_register(struct device *dev, unsigned int off)
+{
+	struct i2c_client *i2c = to_i2c_client(dev);
+	struct cy8c95x0_pinctrl *chip = i2c_get_clientdata(i2c);
+	u8 port = CY8C95X0_MUX_REGMAP_TO_PORT(off);
+	u8 reg = CY8C95X0_MUX_REGMAP_TO_REG(off);
+
+	if (port >= chip->nport)
+		return false;
+
+	return cy8c95x0_muxed_register(reg);
+}
+
+static struct regmap_bus cy8c95x0_regmap_bus = {
+	.reg_read = cy8c95x0_mux_reg_read,
+	.reg_write = cy8c95x0_mux_reg_write,
+};
+
+/* Regmap for muxed registers CY8C95X0_INTMASK - CY8C95X0_DRV_HIZ */
+static const struct regmap_config cy8c95x0_muxed_regmap = {
+	.name = "muxed",
+	.reg_bits = 8,
+	.val_bits = 8,
+	.cache_type = REGCACHE_FLAT,
+	.use_single_read = true,
+	.use_single_write = true,
+	.max_register = MUXED_STRIDE * BANK_SZ,
+	.num_reg_defaults_raw = MUXED_STRIDE * BANK_SZ,
+	.readable_reg = cy8c95x0_mux_accessible_register,
+	.writeable_reg = cy8c95x0_mux_accessible_register,
+};
+
+/* Direct access regmap */
 static const struct regmap_config cy8c95x0_i2c_regmap = {
+	.name = "direct",
 	.reg_bits = 8,
 	.val_bits = 8,
 
@@ -408,6 +544,147 @@ static const struct regmap_config cy8c95x0_i2c_regmap = {
 	.max_register = CY8C95X0_COMMAND,
 };
 
+static inline int cy8c95x0_regmap_update_bits_base(struct cy8c95x0_pinctrl *chip,
+						   unsigned int reg,
+						   unsigned int port,
+						   unsigned int mask,
+						   unsigned int val,
+						   bool *change, bool async,
+						   bool force)
+{
+	struct regmap *regmap;
+	int ret, off, i, read_val;
+
+	/* Caller should never modify PORTSEL directly */
+	if (reg == CY8C95X0_PORTSEL)
+		return -EINVAL;
+
+	/* Registers behind the PORTSEL mux have their own regmap */
+	if (cy8c95x0_muxed_register(reg)) {
+		regmap = chip->muxed_regmap;
+		off = CY8C95X0_MUX_REGMAP_TO_OFFSET(reg, port);
+	} else {
+		regmap = chip->regmap;
+		/* Quick path direct access registers honor the port argument */
+		if (cy8c95x0_quick_path_register(reg))
+			off = reg + port;
+		else
+			off = reg;
+	}
+
+	ret = regmap_update_bits_base(regmap, off, mask, val, change, async, force);
+	if (ret < 0)
+		return ret;
+
+	/* Update the cache when a WC bit is written */
+	if (cy8c95x0_wc_register(reg) && (mask & val)) {
+		for (i = CY8C95X0_DRV_PU; i <= CY8C95X0_DRV_HIZ; i++) {
+			if (i == reg)
+				continue;
+			off = CY8C95X0_MUX_REGMAP_TO_OFFSET(i, port);
+
+			ret = regmap_read(regmap, off, &read_val);
+			if (ret < 0)
+				continue;
+
+			if (!(read_val & mask & val))
+				continue;
+
+			regcache_cache_only(regmap, true);
+			regmap_update_bits(regmap, off, mask & val, 0);
+			regcache_cache_only(regmap, false);
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * cy8c95x0_regmap_write_bits() - writes a register using the regmap cache
+ * @chip: The pinctrl to work on
+ * @reg: The register to write to. Can be direct access or muxed register.
+ *       MUST NOT be the PORTSEL register.
+ * @port: The port to be used for muxed registers or quick path direct access
+ *        registers. Otherwise unused.
+ * @mask: Bitmask to change
+ * @val: New value for bitmask
+ *
+ * This function handles the register writes to the direct access registers and
+ * the muxed registers while caching all register accesses, internally handling
+ * the correct state of the PORTSEL register and protecting the access to muxed
+ * registers.
+ * The caller must only use this function to change registers behind the PORTSEL mux.
+ *
+ * Return: 0 for successful request, else a corresponding error value
+ */
+static int cy8c95x0_regmap_write_bits(struct cy8c95x0_pinctrl *chip, unsigned int reg,
+				      unsigned int port, unsigned int mask, unsigned int val)
+{
+	return cy8c95x0_regmap_update_bits_base(chip, reg, port, mask, val, NULL, false, true);
+}
+
+/**
+ * cy8c95x0_regmap_update_bits() - updates a register using the regmap cache
+ * @chip: The pinctrl to work on
+ * @reg: The register to write to. Can be direct access or muxed register.
+ *       MUST NOT be the PORTSEL register.
+ * @port: The port to be used for muxed registers or quick path direct access
+ *        registers. Otherwise unused.
+ * @mask: Bitmask to change
+ * @val: New value for bitmask
+ *
+ * This function handles the register updates to the direct access registers and
+ * the muxed registers while caching all register accesses, internally handling
+ * the correct state of the PORTSEL register and protecting the access to muxed
+ * registers.
+ * The caller must only use this function to change registers behind the PORTSEL mux.
+ *
+ * Return: 0 for successful request, else a corresponding error value
+ */
+static int cy8c95x0_regmap_update_bits(struct cy8c95x0_pinctrl *chip, unsigned int reg,
+				       unsigned int port, unsigned int mask, unsigned int val)
+{
+	return cy8c95x0_regmap_update_bits_base(chip, reg, port, mask, val, NULL, false, false);
+}
+
+/**
+ * cy8c95x0_regmap_read() - reads a register using the regmap cache
+ * @chip: The pinctrl to work on
+ * @reg: The register to read from. Can be direct access or muxed register.
+ * @port: The port to be used for muxed registers or quick path direct access
+ *        registers. Otherwise unused.
+ * @read_val: Value read from hardware or cache
+ *
+ * This function handles the register reads from the direct access registers and
+ * the muxed registers while caching all register accesses, internally handling
+ * the correct state of the PORTSEL register and protecting the access to muxed
+ * registers.
+ * The caller must only use this function to read registers behind the PORTSEL mux.
+ *
+ * Return: 0 for successful request, else a corresponding error value
+ */
+static int cy8c95x0_regmap_read(struct cy8c95x0_pinctrl *chip, unsigned int reg,
+				unsigned int port, unsigned int *read_val)
+{
+	struct regmap *regmap;
+	int off;
+
+	/* Registers behind the PORTSEL mux have their own regmap */
+	if (cy8c95x0_muxed_register(reg)) {
+		regmap = chip->muxed_regmap;
+		off = CY8C95X0_MUX_REGMAP_TO_OFFSET(reg, port);
+	} else {
+		regmap = chip->regmap;
+		/* Quick path direct access registers honor the port argument */
+		if (cy8c95x0_quick_path_register(reg))
+			off = reg + port;
+		else
+			off = reg;
+	}
+
+	return regmap_read(regmap, off, read_val);
+}
+
 static int cy8c95x0_write_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 				    unsigned long *val, unsigned long *mask)
 {
@@ -415,7 +692,7 @@ static int cy8c95x0_write_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	DECLARE_BITMAP(tval, MAX_LINE);
 	int write_val;
 	int ret = 0;
-	int i, off = 0;
+	int i;
 	u8 bits;
 
 	/* Add the 4 bit gap of Gport2 */
@@ -427,53 +704,22 @@ static int cy8c95x0_write_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	bitmap_shift_left(tval, tval, 4, MAX_LINE);
 	bitmap_replace(tval, tval, val, chip->shiftmask, BANK_SZ * 3);
 
-	mutex_lock(&chip->i2c_lock);
 	for (i = 0; i < chip->nport; i++) {
 		/* Skip over unused banks */
 		bits = bitmap_get_value8(tmask, i * BANK_SZ);
 		if (!bits)
 			continue;
 
-		switch (reg) {
-		/* Muxed registers */
-		case CY8C95X0_INTMASK:
-		case CY8C95X0_PWMSEL:
-		case CY8C95X0_INVERT:
-		case CY8C95X0_DIRECTION:
-		case CY8C95X0_DRV_PU:
-		case CY8C95X0_DRV_PD:
-		case CY8C95X0_DRV_ODH:
-		case CY8C95X0_DRV_ODL:
-		case CY8C95X0_DRV_PP_FAST:
-		case CY8C95X0_DRV_PP_SLOW:
-		case CY8C95X0_DRV_HIZ:
-			ret = regmap_write(chip->regmap, CY8C95X0_PORTSEL, i);
-			if (ret < 0)
-				goto out;
-			off = reg;
-			break;
-		/* Direct access registers */
-		case CY8C95X0_INPUT:
-		case CY8C95X0_OUTPUT:
-		case CY8C95X0_INTSTATUS:
-			off = reg + i;
-			break;
-		default:
-			ret = -EINVAL;
-			goto out;
-		}
-
 		write_val = bitmap_get_value8(tval, i * BANK_SZ);
 
-		ret = regmap_update_bits(chip->regmap, off, bits, write_val);
+		ret = cy8c95x0_regmap_update_bits(chip, reg, i, bits, write_val);
 		if (ret < 0)
 			goto out;
 	}
 out:
-	mutex_unlock(&chip->i2c_lock);
 
 	if (ret < 0)
-		dev_err(chip->dev, "failed writing register %d: err %d\n", off, ret);
+		dev_err(chip->dev, "failed writing register %d, port %d: err %d\n", reg, i, ret);
 
 	return ret;
 }
@@ -486,7 +732,7 @@ static int cy8c95x0_read_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	DECLARE_BITMAP(tmp, MAX_LINE);
 	int read_val;
 	int ret = 0;
-	int i, off = 0;
+	int i;
 	u8 bits;
 
 	/* Add the 4 bit gap of Gport2 */
@@ -498,43 +744,13 @@ static int cy8c95x0_read_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	bitmap_shift_left(tval, tval, 4, MAX_LINE);
 	bitmap_replace(tval, tval, val, chip->shiftmask, BANK_SZ * 3);
 
-	mutex_lock(&chip->i2c_lock);
 	for (i = 0; i < chip->nport; i++) {
 		/* Skip over unused banks */
 		bits = bitmap_get_value8(tmask, i * BANK_SZ);
 		if (!bits)
 			continue;
 
-		switch (reg) {
-		/* Muxed registers */
-		case CY8C95X0_INTMASK:
-		case CY8C95X0_PWMSEL:
-		case CY8C95X0_INVERT:
-		case CY8C95X0_DIRECTION:
-		case CY8C95X0_DRV_PU:
-		case CY8C95X0_DRV_PD:
-		case CY8C95X0_DRV_ODH:
-		case CY8C95X0_DRV_ODL:
-		case CY8C95X0_DRV_PP_FAST:
-		case CY8C95X0_DRV_PP_SLOW:
-		case CY8C95X0_DRV_HIZ:
-			ret = regmap_write(chip->regmap, CY8C95X0_PORTSEL, i);
-			if (ret < 0)
-				goto out;
-			off = reg;
-			break;
-		/* Direct access registers */
-		case CY8C95X0_INPUT:
-		case CY8C95X0_OUTPUT:
-		case CY8C95X0_INTSTATUS:
-			off = reg + i;
-			break;
-		default:
-			ret = -EINVAL;
-			goto out;
-		}
-
-		ret = regmap_read(chip->regmap, off, &read_val);
+		ret = cy8c95x0_regmap_read(chip, reg, i, &read_val);
 		if (ret < 0)
 			goto out;
 
@@ -548,10 +764,8 @@ static int cy8c95x0_read_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	bitmap_replace(val, tmp, tval, chip->shiftmask, MAX_LINE);
 
 out:
-	mutex_unlock(&chip->i2c_lock);
-
 	if (ret < 0)
-		dev_err(chip->dev, "failed reading register %d: err %d\n", off, ret);
+		dev_err(chip->dev, "failed reading register %d, port %d: err %d\n", reg, i, ret);
 
 	return ret;
 }
@@ -566,12 +780,11 @@ static int cy8c95x0_gpio_direction_output(struct gpio_chip *gc,
 {
 	struct cy8c95x0_pinctrl *chip = gpiochip_get_data(gc);
 	u8 port = cypress_get_port(chip, off);
-	u8 outreg = CY8C95X0_OUTPUT_(port);
 	u8 bit = cypress_get_pin_mask(chip, off);
 	int ret;
 
 	/* Set output level */
-	ret = regmap_write_bits(chip->regmap, outreg, bit, val ? bit : 0);
+	ret = cy8c95x0_regmap_write_bits(chip, CY8C95X0_OUTPUT, port, bit, val ? bit : 0);
 	if (ret)
 		return ret;
 
@@ -581,12 +794,12 @@ static int cy8c95x0_gpio_direction_output(struct gpio_chip *gc,
 static int cy8c95x0_gpio_get_value(struct gpio_chip *gc, unsigned int off)
 {
 	struct cy8c95x0_pinctrl *chip = gpiochip_get_data(gc);
-	u8 inreg = CY8C95X0_INPUT_(cypress_get_port(chip, off));
+	u8 port = cypress_get_port(chip, off);
 	u8 bit = cypress_get_pin_mask(chip, off);
 	u32 reg_val;
 	int ret;
 
-	ret = regmap_read(chip->regmap, inreg, &reg_val);
+	ret = cy8c95x0_regmap_read(chip, CY8C95X0_INPUT, port, &reg_val);
 	if (ret < 0) {
 		/*
 		 * NOTE:
@@ -604,10 +817,10 @@ static void cy8c95x0_gpio_set_value(struct gpio_chip *gc, unsigned int off,
 				    int val)
 {
 	struct cy8c95x0_pinctrl *chip = gpiochip_get_data(gc);
-	u8 outreg = CY8C95X0_OUTPUT_(cypress_get_port(chip, off));
+	u8 port = cypress_get_port(chip, off);
 	u8 bit = cypress_get_pin_mask(chip, off);
 
-	regmap_write_bits(chip->regmap, outreg, bit, val ? bit : 0);
+	cy8c95x0_regmap_write_bits(chip, CY8C95X0_OUTPUT, port, bit, val ? bit : 0);
 }
 
 static int cy8c95x0_gpio_get_direction(struct gpio_chip *gc, unsigned int off)
@@ -618,24 +831,15 @@ static int cy8c95x0_gpio_get_direction(struct gpio_chip *gc, unsigned int off)
 	u32 reg_val;
 	int ret;
 
-	mutex_lock(&chip->i2c_lock);
-
-	ret = regmap_write(chip->regmap, CY8C95X0_PORTSEL, port);
-	if (ret < 0)
-		goto out;
-
-	ret = regmap_read(chip->regmap, CY8C95X0_DIRECTION, &reg_val);
+	ret = cy8c95x0_regmap_read(chip, CY8C95X0_DIRECTION, port, &reg_val);
 	if (ret < 0)
 		goto out;
 
-	mutex_unlock(&chip->i2c_lock);
-
 	if (reg_val & bit)
 		return GPIO_LINE_DIRECTION_IN;
 
 	return GPIO_LINE_DIRECTION_OUT;
 out:
-	mutex_unlock(&chip->i2c_lock);
 	return ret;
 }
 
@@ -651,13 +855,6 @@ static int cy8c95x0_gpio_get_pincfg(struct cy8c95x0_pinctrl *chip,
 	u16 arg = 0;
 	int ret;
 
-	mutex_lock(&chip->i2c_lock);
-
-	/* Select port */
-	ret = regmap_write(chip->regmap, CY8C95X0_PORTSEL, port);
-	if (ret < 0)
-		goto out;
-
 	switch (param) {
 	case PIN_CONFIG_BIAS_PULL_UP:
 		reg = CY8C95X0_DRV_PU;
@@ -684,7 +881,7 @@ static int cy8c95x0_gpio_get_pincfg(struct cy8c95x0_pinctrl *chip,
 		reg = CY8C95X0_PWMSEL;
 		break;
 	case PIN_CONFIG_OUTPUT:
-		reg = CY8C95X0_OUTPUT_(port);
+		reg = CY8C95X0_OUTPUT;
 		break;
 	case PIN_CONFIG_OUTPUT_ENABLE:
 		reg = CY8C95X0_DIRECTION;
@@ -712,7 +909,10 @@ static int cy8c95x0_gpio_get_pincfg(struct cy8c95x0_pinctrl *chip,
 	 * Writing 1 to one of the drive mode registers will automatically
 	 * clear conflicting set bits in the other drive mode registers.
 	 */
-	ret = regmap_read(chip->regmap, reg, &reg_val);
+	ret = cy8c95x0_regmap_read(chip, reg, port, &reg_val);
+	if (ret < 0)
+		goto out;
+
 	if (reg_val & bit)
 		arg = 1;
 	if (param == PIN_CONFIG_OUTPUT_ENABLE)
@@ -720,8 +920,6 @@ static int cy8c95x0_gpio_get_pincfg(struct cy8c95x0_pinctrl *chip,
 
 	*config = pinconf_to_config_packed(param, (u16)arg);
 out:
-	mutex_unlock(&chip->i2c_lock);
-
 	return ret;
 }
 
@@ -736,13 +934,6 @@ static int cy8c95x0_gpio_set_pincfg(struct cy8c95x0_pinctrl *chip,
 	unsigned int reg;
 	int ret;
 
-	mutex_lock(&chip->i2c_lock);
-
-	/* Select port */
-	ret = regmap_write(chip->regmap, CY8C95X0_PORTSEL, port);
-	if (ret < 0)
-		goto out;
-
 	switch (param) {
 	case PIN_CONFIG_BIAS_PULL_UP:
 		__clear_bit(off, chip->push_pull);
@@ -785,10 +976,8 @@ static int cy8c95x0_gpio_set_pincfg(struct cy8c95x0_pinctrl *chip,
 	 * Writing 1 to one of the drive mode registers will automatically
 	 * clear conflicting set bits in the other drive mode registers.
 	 */
-	ret = regmap_write_bits(chip->regmap, reg, bit, bit);
-
+	ret = cy8c95x0_regmap_write_bits(chip, reg, port, bit, bit);
 out:
-	mutex_unlock(&chip->i2c_lock);
 	return ret;
 }
 
@@ -1105,14 +1294,8 @@ static int cy8c95x0_set_mode(struct cy8c95x0_pinctrl *chip, unsigned int off, bo
 {
 	u8 port = cypress_get_port(chip, off);
 	u8 bit = cypress_get_pin_mask(chip, off);
-	int ret;
 
-	/* Select port */
-	ret = regmap_write(chip->regmap, CY8C95X0_PORTSEL, port);
-	if (ret < 0)
-		return ret;
-
-	return regmap_write_bits(chip->regmap, CY8C95X0_PWMSEL, bit, mode ? bit : 0);
+	return cy8c95x0_regmap_write_bits(chip, CY8C95X0_PWMSEL, port, bit, mode ? bit : 0);
 }
 
 static int cy8c95x0_pinmux_mode(struct cy8c95x0_pinctrl *chip,
@@ -1130,24 +1313,19 @@ static int cy8c95x0_pinmux_mode(struct cy8c95x0_pinctrl *chip,
 		return 0;
 
 	/* Set direction to output & set output to 1 so that PWM can work */
-	ret = regmap_write_bits(chip->regmap, CY8C95X0_DIRECTION, bit, bit);
+	ret = cy8c95x0_regmap_write_bits(chip, CY8C95X0_DIRECTION, port, bit, bit);
 	if (ret < 0)
 		return ret;
 
-	return regmap_write_bits(chip->regmap, CY8C95X0_OUTPUT_(port), bit, bit);
+	return cy8c95x0_regmap_write_bits(chip, CY8C95X0_OUTPUT, port, bit, bit);
 }
 
 static int cy8c95x0_set_mux(struct pinctrl_dev *pctldev, unsigned int selector,
 			    unsigned int group)
 {
 	struct cy8c95x0_pinctrl *chip = pinctrl_dev_get_drvdata(pctldev);
-	int ret;
 
-	mutex_lock(&chip->i2c_lock);
-	ret = cy8c95x0_pinmux_mode(chip, selector, group);
-	mutex_unlock(&chip->i2c_lock);
-
-	return ret;
+	return cy8c95x0_pinmux_mode(chip, selector, group);
 }
 
 static int cy8c95x0_gpio_request_enable(struct pinctrl_dev *pctldev,
@@ -1155,13 +1333,8 @@ static int cy8c95x0_gpio_request_enable(struct pinctrl_dev *pctldev,
 					unsigned int pin)
 {
 	struct cy8c95x0_pinctrl *chip = pinctrl_dev_get_drvdata(pctldev);
-	int ret;
-
-	mutex_lock(&chip->i2c_lock);
-	ret = cy8c95x0_set_mode(chip, pin, false);
-	mutex_unlock(&chip->i2c_lock);
 
-	return ret;
+	return cy8c95x0_set_mode(chip, pin, false);
 }
 
 static int cy8c95x0_pinmux_direction(struct cy8c95x0_pinctrl *chip,
@@ -1171,13 +1344,7 @@ static int cy8c95x0_pinmux_direction(struct cy8c95x0_pinctrl *chip,
 	u8 bit = cypress_get_pin_mask(chip, pin);
 	int ret;
 
-	/* Select port... */
-	ret = regmap_write(chip->regmap, CY8C95X0_PORTSEL, port);
-	if (ret)
-		return ret;
-
-	/* ...then direction */
-	ret = regmap_write_bits(chip->regmap, CY8C95X0_DIRECTION, bit, input ? bit : 0);
+	ret = cy8c95x0_regmap_write_bits(chip, CY8C95X0_DIRECTION, port, bit, input ? bit : 0);
 	if (ret)
 		return ret;
 
@@ -1186,7 +1353,7 @@ static int cy8c95x0_pinmux_direction(struct cy8c95x0_pinctrl *chip,
 	 * the direction register isn't sufficient in Push-Pull mode.
 	 */
 	if (input && test_bit(pin, chip->push_pull)) {
-		ret = regmap_write_bits(chip->regmap, CY8C95X0_DRV_HIZ, bit, bit);
+		ret = cy8c95x0_regmap_write_bits(chip, CY8C95X0_DRV_HIZ, port, bit, bit);
 		if (ret)
 			return ret;
 
@@ -1201,13 +1368,8 @@ static int cy8c95x0_gpio_set_direction(struct pinctrl_dev *pctldev,
 				       unsigned int pin, bool input)
 {
 	struct cy8c95x0_pinctrl *chip = pinctrl_dev_get_drvdata(pctldev);
-	int ret;
 
-	mutex_lock(&chip->i2c_lock);
-	ret = cy8c95x0_pinmux_direction(chip, pin, input);
-	mutex_unlock(&chip->i2c_lock);
-
-	return ret;
+	return cy8c95x0_pinmux_direction(chip, pin, input);
 }
 
 static const struct pinmux_ops cy8c95x0_pmxops = {
@@ -1409,12 +1571,22 @@ static int cy8c95x0_probe(struct i2c_client *client)
 		gpiod_set_consumer_name(chip->gpio_reset, "CY8C95X0 RESET");
 	}
 
+	/* Generic regmap for direct access registers */
 	chip->regmap = devm_regmap_init_i2c(client, &cy8c95x0_i2c_regmap);
 	if (IS_ERR(chip->regmap)) {
 		ret = PTR_ERR(chip->regmap);
 		goto err_exit;
 	}
 
+	/* Port specific regmap behind PORTSEL mux */
+	chip->muxed_regmap = devm_regmap_init(&client->dev, &cy8c95x0_regmap_bus,
+					      chip, &cy8c95x0_muxed_regmap);
+	if (IS_ERR(chip->muxed_regmap)) {
+		ret = dev_err_probe(&client->dev, PTR_ERR(chip->muxed_regmap),
+				    "Failed to register muxed regmap\n");
+		goto err_exit;
+	}
+
 	bitmap_zero(chip->push_pull, MAX_LINE);
 	bitmap_zero(chip->shiftmask, MAX_LINE);
 	bitmap_set(chip->shiftmask, 0, 20);
diff --git a/drivers/pinctrl/pinctrl-equilibrium.c b/drivers/pinctrl/pinctrl-equilibrium.c
index 5b5ddf7e5d0e..6e1be38865c3 100644
--- a/drivers/pinctrl/pinctrl-equilibrium.c
+++ b/drivers/pinctrl/pinctrl-equilibrium.c
@@ -331,8 +331,8 @@ static int eqbr_pinmux_set_mux(struct pinctrl_dev *pctldev,
 		return -EINVAL;
 
 	pinmux = grp->data;
-	for (i = 0; i < grp->num_pins; i++)
-		eqbr_set_pin_mux(pctl, pinmux[i], grp->pins[i]);
+	for (i = 0; i < grp->grp.npins; i++)
+		eqbr_set_pin_mux(pctl, pinmux[i], grp->grp.pins[i]);
 
 	return 0;
 }
@@ -704,8 +704,8 @@ static int eqbr_build_groups(struct eqbr_pinctrl_drv_data *drvdata)
 {
 	struct device *dev = drvdata->dev;
 	struct device_node *node = dev->of_node;
-	unsigned int *pinmux, pin_id, pinmux_id;
-	struct group_desc group;
+	unsigned int *pins, *pinmux, pin_id, pinmux_id;
+	struct pingroup group, *grp = &group;
 	struct device_node *np;
 	struct property *prop;
 	int j, err;
@@ -715,55 +715,55 @@ static int eqbr_build_groups(struct eqbr_pinctrl_drv_data *drvdata)
 		if (!prop)
 			continue;
 
-		group.num_pins = of_property_count_u32_elems(np, "pins");
-		if (group.num_pins < 0) {
+		err = of_property_count_u32_elems(np, "pins");
+		if (err < 0) {
 			dev_err(dev, "No pins in the group: %s\n", prop->name);
 			of_node_put(np);
-			return -EINVAL;
+			return err;
 		}
-		group.name = prop->value;
-		group.pins = devm_kcalloc(dev, group.num_pins,
-					  sizeof(*(group.pins)), GFP_KERNEL);
-		if (!group.pins) {
+		grp->npins = err;
+		grp->name = prop->value;
+		pins = devm_kcalloc(dev, grp->npins, sizeof(*pins), GFP_KERNEL);
+		if (!pins) {
 			of_node_put(np);
 			return -ENOMEM;
 		}
+		grp->pins = pins;
 
-		pinmux = devm_kcalloc(dev, group.num_pins, sizeof(*pinmux),
-				      GFP_KERNEL);
+		pinmux = devm_kcalloc(dev, grp->npins, sizeof(*pinmux), GFP_KERNEL);
 		if (!pinmux) {
 			of_node_put(np);
 			return -ENOMEM;
 		}
 
-		for (j = 0; j < group.num_pins; j++) {
+		for (j = 0; j < grp->npins; j++) {
 			if (of_property_read_u32_index(np, "pins", j, &pin_id)) {
 				dev_err(dev, "Group %s: Read intel pins id failed\n",
-					group.name);
+					grp->name);
 				of_node_put(np);
 				return -EINVAL;
 			}
 			if (pin_id >= drvdata->pctl_desc.npins) {
 				dev_err(dev, "Group %s: Invalid pin ID, idx: %d, pin %u\n",
-					group.name, j, pin_id);
+					grp->name, j, pin_id);
 				of_node_put(np);
 				return -EINVAL;
 			}
-			group.pins[j] = pin_id;
+			pins[j] = pin_id;
 			if (of_property_read_u32_index(np, "pinmux", j, &pinmux_id)) {
 				dev_err(dev, "Group %s: Read intel pinmux id failed\n",
-					group.name);
+					grp->name);
 				of_node_put(np);
 				return -EINVAL;
 			}
 			pinmux[j] = pinmux_id;
 		}
 
-		err = pinctrl_generic_add_group(drvdata->pctl_dev, group.name,
-						group.pins, group.num_pins,
+		err = pinctrl_generic_add_group(drvdata->pctl_dev,
+						grp->name, grp->pins, grp->npins,
 						pinmux);
 		if (err < 0) {
-			dev_err(dev, "Failed to register group %s\n", group.name);
+			dev_err(dev, "Failed to register group %s\n", grp->name);
 			of_node_put(np);
 			return err;
 		}
diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c
index ee718f6e2556..bc6358a686fc 100644
--- a/drivers/pinctrl/pinctrl-ingenic.c
+++ b/drivers/pinctrl/pinctrl-ingenic.c
@@ -82,16 +82,17 @@
 #define PINS_PER_GPIO_CHIP			32
 #define JZ4730_PINS_PER_PAIRED_REG	16
 
-#define INGENIC_PIN_GROUP_FUNCS(name, id, funcs)		\
-	{						\
-		name,					\
-		id##_pins,				\
-		ARRAY_SIZE(id##_pins),			\
-		funcs,					\
+#define INGENIC_PIN_GROUP_FUNCS(_name_, id, funcs)					\
+	{										\
+		.grp = PINCTRL_PINGROUP(_name_, id##_pins, ARRAY_SIZE(id##_pins)),	\
+		.data = funcs,								\
 	}
 
-#define INGENIC_PIN_GROUP(name, id, func)		\
-	INGENIC_PIN_GROUP_FUNCS(name, id, (void *)(func))
+#define INGENIC_PIN_GROUP(_name_, id, func)						\
+	{										\
+		.grp = PINCTRL_PINGROUP(_name_, id##_pins, ARRAY_SIZE(id##_pins)),	\
+		.data = (void *)func,							\
+	}
 
 enum jz_version {
 	ID_JZ4730,
@@ -3761,17 +3762,17 @@ static int ingenic_pinmux_set_mux(struct pinctrl_dev *pctldev,
 		return -EINVAL;
 
 	dev_dbg(pctldev->dev, "enable function %s group %s\n",
-		func->name, grp->name);
+		func->name, grp->grp.name);
 
 	mode = (uintptr_t)grp->data;
 	if (mode <= 3) {
-		for (i = 0; i < grp->num_pins; i++)
-			ingenic_pinmux_set_pin_fn(jzpc, grp->pins[i], mode);
+		for (i = 0; i < grp->grp.npins; i++)
+			ingenic_pinmux_set_pin_fn(jzpc, grp->grp.pins[i], mode);
 	} else {
 		pin_modes = grp->data;
 
-		for (i = 0; i < grp->num_pins; i++)
-			ingenic_pinmux_set_pin_fn(jzpc, grp->pins[i], pin_modes[i]);
+		for (i = 0; i < grp->grp.npins; i++)
+			ingenic_pinmux_set_pin_fn(jzpc, grp->grp.pins[i], pin_modes[i]);
 	}
 
 	return 0;
@@ -4298,12 +4299,12 @@ static int __init ingenic_pinctrl_probe(struct platform_device *pdev)
 
 	for (i = 0; i < chip_info->num_groups; i++) {
 		const struct group_desc *group = &chip_info->groups[i];
+		const struct pingroup *grp = &group->grp;
 
-		err = pinctrl_generic_add_group(jzpc->pctl, group->name,
-				group->pins, group->num_pins, group->data);
+		err = pinctrl_generic_add_group(jzpc->pctl, grp->name, grp->pins, grp->npins,
+						group->data);
 		if (err < 0) {
-			dev_err(dev, "Failed to register group %s\n",
-					group->name);
+			dev_err(dev, "Failed to register group %s\n", grp->name);
 			return err;
 		}
 	}
diff --git a/drivers/pinctrl/pinctrl-keembay.c b/drivers/pinctrl/pinctrl-keembay.c
index 152c35bce8ec..b1349ee22799 100644
--- a/drivers/pinctrl/pinctrl-keembay.c
+++ b/drivers/pinctrl/pinctrl-keembay.c
@@ -945,7 +945,7 @@ static int keembay_set_mux(struct pinctrl_dev *pctldev, unsigned int fun_sel,
 		return -EINVAL;
 
 	/* Change modes for pins in the selected group */
-	pin = *grp->pins;
+	pin = *grp->grp.pins;
 	pin_mode = *(u8 *)(func->data);
 
 	val = keembay_read_reg(kpc->base1 + KEEMBAY_GPIO_MODE, pin);
@@ -1517,7 +1517,7 @@ static int keembay_gpiochip_probe(struct keembay_pinctrl *kpc,
 
 static int keembay_build_groups(struct keembay_pinctrl *kpc)
 {
-	struct group_desc *grp;
+	struct pingroup *grp;
 	unsigned int i;
 
 	kpc->ngroups = kpc->npins;
@@ -1528,7 +1528,7 @@ static int keembay_build_groups(struct keembay_pinctrl *kpc)
 	/* Each pin is categorised as one group */
 	for (i = 0; i < kpc->ngroups; i++) {
 		const struct pinctrl_pin_desc *pdesc = keembay_pins + i;
-		struct group_desc *kmb_grp = grp + i;
+		struct pingroup *kmb_grp = grp + i;
 
 		kmb_grp->name = pdesc->name;
 		kmb_grp->pins = (int *)&pdesc->number;
diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index 8267be769635..19cc0db771a5 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -1955,6 +1955,10 @@ static const struct pcs_soc_data pinctrl_single_am654 = {
 	.irq_status_mask = (1 << 30),   /* WKUP_EVT */
 };
 
+static const struct pcs_soc_data pinctrl_single_j7200 = {
+	.flags = PCS_CONTEXT_LOSS_OFF,
+};
+
 static const struct pcs_soc_data pinctrl_single = {
 };
 
@@ -1969,6 +1973,7 @@ static const struct of_device_id pcs_of_match[] = {
 	{ .compatible = "ti,omap3-padconf", .data = &pinctrl_single_omap_wkup },
 	{ .compatible = "ti,omap4-padconf", .data = &pinctrl_single_omap_wkup },
 	{ .compatible = "ti,omap5-padconf", .data = &pinctrl_single_omap_wkup },
+	{ .compatible = "ti,j7200-padconf", .data = &pinctrl_single_j7200 },
 	{ .compatible = "pinctrl-single", .data = &pinctrl_single },
 	{ .compatible = "pinconf-single", .data = &pinconf_single },
 	{ },
diff --git a/drivers/pinctrl/pinctrl-tps6594.c b/drivers/pinctrl/pinctrl-tps6594.c
new file mode 100644
index 000000000000..66985e54b74a
--- /dev/null
+++ b/drivers/pinctrl/pinctrl-tps6594.c
@@ -0,0 +1,373 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Pinmux and GPIO driver for tps6594 PMIC
+ *
+ * Copyright (C) 2023 BayLibre Incorporated - https://www.baylibre.com/
+ */
+
+#include <linux/gpio/driver.h>
+#include <linux/gpio/regmap.h>
+#include <linux/module.h>
+#include <linux/pinctrl/pinmux.h>
+#include <linux/platform_device.h>
+#include <linux/mod_devicetable.h>
+
+#include <linux/mfd/tps6594.h>
+
+#define TPS6594_PINCTRL_PINS_NB 11
+
+#define TPS6594_PINCTRL_GPIO_FUNCTION 0
+#define TPS6594_PINCTRL_SCL_I2C2_CS_SPI_FUNCTION 1
+#define TPS6594_PINCTRL_TRIG_WDOG_FUNCTION 1
+#define TPS6594_PINCTRL_CLK32KOUT_FUNCTION 1
+#define TPS6594_PINCTRL_SCLK_SPMI_FUNCTION 1
+#define TPS6594_PINCTRL_SDATA_SPMI_FUNCTION 1
+#define TPS6594_PINCTRL_NERR_MCU_FUNCTION 1
+#define TPS6594_PINCTRL_PDOG_FUNCTION 1
+#define TPS6594_PINCTRL_SYNCCLKIN_FUNCTION 1
+#define TPS6594_PINCTRL_NRSTOUT_SOC_FUNCTION 2
+#define TPS6594_PINCTRL_SYNCCLKOUT_FUNCTION 2
+#define TPS6594_PINCTRL_SDA_I2C2_SDO_SPI_FUNCTION 2
+#define TPS6594_PINCTRL_NERR_SOC_FUNCTION 2
+#define TPS6594_PINCTRL_DISABLE_WDOG_FUNCTION 3
+#define TPS6594_PINCTRL_NSLEEP1_FUNCTION 4
+#define TPS6594_PINCTRL_NSLEEP2_FUNCTION 5
+#define TPS6594_PINCTRL_WKUP1_FUNCTION 6
+#define TPS6594_PINCTRL_WKUP2_FUNCTION 7
+
+/* Special muxval for recalcitrant pins */
+#define TPS6594_PINCTRL_DISABLE_WDOG_FUNCTION_GPIO8 2
+#define TPS6594_PINCTRL_SYNCCLKOUT_FUNCTION_GPIO8 3
+#define TPS6594_PINCTRL_CLK32KOUT_FUNCTION_GPIO9 3
+
+#define TPS6594_OFFSET_GPIO_SEL 5
+
+#define FUNCTION(fname, v)									\
+{											\
+	.pinfunction = PINCTRL_PINFUNCTION(#fname,					\
+					tps6594_##fname##_func_group_names,		\
+					ARRAY_SIZE(tps6594_##fname##_func_group_names)),\
+	.muxval = v,									\
+}
+
+static const struct pinctrl_pin_desc tps6594_pins[TPS6594_PINCTRL_PINS_NB] = {
+	PINCTRL_PIN(0, "GPIO0"),   PINCTRL_PIN(1, "GPIO1"),
+	PINCTRL_PIN(2, "GPIO2"),   PINCTRL_PIN(3, "GPIO3"),
+	PINCTRL_PIN(4, "GPIO4"),   PINCTRL_PIN(5, "GPIO5"),
+	PINCTRL_PIN(6, "GPIO6"),   PINCTRL_PIN(7, "GPIO7"),
+	PINCTRL_PIN(8, "GPIO8"),   PINCTRL_PIN(9, "GPIO9"),
+	PINCTRL_PIN(10, "GPIO10"),
+};
+
+static const char *const tps6594_gpio_func_group_names[] = {
+	"GPIO0", "GPIO1", "GPIO2", "GPIO3", "GPIO4", "GPIO5",
+	"GPIO6", "GPIO7", "GPIO8", "GPIO9", "GPIO10",
+};
+
+static const char *const tps6594_nsleep1_func_group_names[] = {
+	"GPIO0", "GPIO1", "GPIO2", "GPIO3", "GPIO4", "GPIO5",
+	"GPIO6", "GPIO7", "GPIO8", "GPIO9", "GPIO10",
+};
+
+static const char *const tps6594_nsleep2_func_group_names[] = {
+	"GPIO0", "GPIO1", "GPIO2", "GPIO3", "GPIO4", "GPIO5",
+	"GPIO6", "GPIO7", "GPIO8", "GPIO9", "GPIO10",
+};
+
+static const char *const tps6594_wkup1_func_group_names[] = {
+	"GPIO0", "GPIO1", "GPIO2", "GPIO3", "GPIO4", "GPIO5",
+	"GPIO6", "GPIO7", "GPIO8", "GPIO9", "GPIO10",
+};
+
+static const char *const tps6594_wkup2_func_group_names[] = {
+	"GPIO0", "GPIO1", "GPIO2", "GPIO3", "GPIO4", "GPIO5",
+	"GPIO6", "GPIO7", "GPIO8", "GPIO9", "GPIO10",
+};
+
+static const char *const tps6594_scl_i2c2_cs_spi_func_group_names[] = {
+	"GPIO0",
+	"GPIO1",
+};
+
+static const char *const tps6594_nrstout_soc_func_group_names[] = {
+	"GPIO0",
+	"GPIO10",
+};
+
+static const char *const tps6594_trig_wdog_func_group_names[] = {
+	"GPIO1",
+	"GPIO10",
+};
+
+static const char *const tps6594_sda_i2c2_sdo_spi_func_group_names[] = {
+	"GPIO1",
+};
+
+static const char *const tps6594_clk32kout_func_group_names[] = {
+	"GPIO2",
+	"GPIO3",
+	"GPIO7",
+};
+
+static const char *const tps6594_nerr_soc_func_group_names[] = {
+	"GPIO2",
+};
+
+static const char *const tps6594_sclk_spmi_func_group_names[] = {
+	"GPIO4",
+};
+
+static const char *const tps6594_sdata_spmi_func_group_names[] = {
+	"GPIO5",
+};
+
+static const char *const tps6594_nerr_mcu_func_group_names[] = {
+	"GPIO6",
+};
+
+static const char *const tps6594_syncclkout_func_group_names[] = {
+	"GPIO7",
+	"GPIO9",
+};
+
+static const char *const tps6594_disable_wdog_func_group_names[] = {
+	"GPIO7",
+	"GPIO8",
+};
+
+static const char *const tps6594_pdog_func_group_names[] = {
+	"GPIO8",
+};
+
+static const char *const tps6594_syncclkin_func_group_names[] = {
+	"GPIO9",
+};
+
+struct tps6594_pinctrl_function {
+	struct pinfunction pinfunction;
+	u8 muxval;
+};
+
+static const struct tps6594_pinctrl_function pinctrl_functions[] = {
+	FUNCTION(gpio, TPS6594_PINCTRL_GPIO_FUNCTION),
+	FUNCTION(nsleep1, TPS6594_PINCTRL_NSLEEP1_FUNCTION),
+	FUNCTION(nsleep2, TPS6594_PINCTRL_NSLEEP2_FUNCTION),
+	FUNCTION(wkup1, TPS6594_PINCTRL_WKUP1_FUNCTION),
+	FUNCTION(wkup2, TPS6594_PINCTRL_WKUP2_FUNCTION),
+	FUNCTION(scl_i2c2_cs_spi, TPS6594_PINCTRL_SCL_I2C2_CS_SPI_FUNCTION),
+	FUNCTION(nrstout_soc, TPS6594_PINCTRL_NRSTOUT_SOC_FUNCTION),
+	FUNCTION(trig_wdog, TPS6594_PINCTRL_TRIG_WDOG_FUNCTION),
+	FUNCTION(sda_i2c2_sdo_spi, TPS6594_PINCTRL_SDA_I2C2_SDO_SPI_FUNCTION),
+	FUNCTION(clk32kout, TPS6594_PINCTRL_CLK32KOUT_FUNCTION),
+	FUNCTION(nerr_soc, TPS6594_PINCTRL_NERR_SOC_FUNCTION),
+	FUNCTION(sclk_spmi, TPS6594_PINCTRL_SCLK_SPMI_FUNCTION),
+	FUNCTION(sdata_spmi, TPS6594_PINCTRL_SDATA_SPMI_FUNCTION),
+	FUNCTION(nerr_mcu, TPS6594_PINCTRL_NERR_MCU_FUNCTION),
+	FUNCTION(syncclkout, TPS6594_PINCTRL_SYNCCLKOUT_FUNCTION),
+	FUNCTION(disable_wdog, TPS6594_PINCTRL_DISABLE_WDOG_FUNCTION),
+	FUNCTION(pdog, TPS6594_PINCTRL_PDOG_FUNCTION),
+	FUNCTION(syncclkin, TPS6594_PINCTRL_SYNCCLKIN_FUNCTION),
+};
+
+struct tps6594_pinctrl {
+	struct tps6594 *tps;
+	struct gpio_regmap *gpio_regmap;
+	struct pinctrl_dev *pctl_dev;
+	const struct tps6594_pinctrl_function *funcs;
+	const struct pinctrl_pin_desc *pins;
+};
+
+static int tps6594_gpio_regmap_xlate(struct gpio_regmap *gpio,
+				     unsigned int base, unsigned int offset,
+				     unsigned int *reg, unsigned int *mask)
+{
+	unsigned int line = offset % 8;
+	unsigned int stride = offset / 8;
+
+	switch (base) {
+	case TPS6594_REG_GPIOX_CONF(0):
+		*reg = TPS6594_REG_GPIOX_CONF(offset);
+		*mask = TPS6594_BIT_GPIO_DIR;
+		return 0;
+	case TPS6594_REG_GPIO_IN_1:
+	case TPS6594_REG_GPIO_OUT_1:
+		*reg = base + stride;
+		*mask = BIT(line);
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int tps6594_pmx_func_cnt(struct pinctrl_dev *pctldev)
+{
+	return ARRAY_SIZE(pinctrl_functions);
+}
+
+static const char *tps6594_pmx_func_name(struct pinctrl_dev *pctldev,
+					 unsigned int selector)
+{
+	struct tps6594_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
+
+	return pinctrl->funcs[selector].pinfunction.name;
+}
+
+static int tps6594_pmx_func_groups(struct pinctrl_dev *pctldev,
+				   unsigned int selector,
+				   const char *const **groups,
+				   unsigned int *num_groups)
+{
+	struct tps6594_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
+
+	*groups = pinctrl->funcs[selector].pinfunction.groups;
+	*num_groups = pinctrl->funcs[selector].pinfunction.ngroups;
+
+	return 0;
+}
+
+static int tps6594_pmx_set(struct tps6594_pinctrl *pinctrl, unsigned int pin,
+			   u8 muxval)
+{
+	u8 mux_sel_val = muxval << TPS6594_OFFSET_GPIO_SEL;
+
+	return regmap_update_bits(pinctrl->tps->regmap,
+				  TPS6594_REG_GPIOX_CONF(pin),
+				  TPS6594_MASK_GPIO_SEL, mux_sel_val);
+}
+
+static int tps6594_pmx_set_mux(struct pinctrl_dev *pctldev,
+			       unsigned int function, unsigned int group)
+{
+	struct tps6594_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
+	u8 muxval = pinctrl->funcs[function].muxval;
+
+	/* Some pins don't have the same muxval for the same function... */
+	if (group == 8) {
+		if (muxval == TPS6594_PINCTRL_DISABLE_WDOG_FUNCTION)
+			muxval = TPS6594_PINCTRL_DISABLE_WDOG_FUNCTION_GPIO8;
+		else if (muxval == TPS6594_PINCTRL_SYNCCLKOUT_FUNCTION)
+			muxval = TPS6594_PINCTRL_SYNCCLKOUT_FUNCTION_GPIO8;
+	} else if (group == 9) {
+		if (muxval == TPS6594_PINCTRL_CLK32KOUT_FUNCTION)
+			muxval = TPS6594_PINCTRL_CLK32KOUT_FUNCTION_GPIO9;
+	}
+
+	return tps6594_pmx_set(pinctrl, group, muxval);
+}
+
+static int tps6594_pmx_gpio_set_direction(struct pinctrl_dev *pctldev,
+					  struct pinctrl_gpio_range *range,
+					  unsigned int offset, bool input)
+{
+	struct tps6594_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
+	u8 muxval = pinctrl->funcs[TPS6594_PINCTRL_GPIO_FUNCTION].muxval;
+
+	return tps6594_pmx_set(pinctrl, offset, muxval);
+}
+
+static const struct pinmux_ops tps6594_pmx_ops = {
+	.get_functions_count = tps6594_pmx_func_cnt,
+	.get_function_name = tps6594_pmx_func_name,
+	.get_function_groups = tps6594_pmx_func_groups,
+	.set_mux = tps6594_pmx_set_mux,
+	.gpio_set_direction = tps6594_pmx_gpio_set_direction,
+	.strict = true,
+};
+
+static int tps6594_groups_cnt(struct pinctrl_dev *pctldev)
+{
+	return ARRAY_SIZE(tps6594_pins);
+}
+
+static int tps6594_group_pins(struct pinctrl_dev *pctldev,
+			      unsigned int selector, const unsigned int **pins,
+			      unsigned int *num_pins)
+{
+	struct tps6594_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
+
+	*pins = &pinctrl->pins[selector].number;
+	*num_pins = 1;
+
+	return 0;
+}
+
+static const char *tps6594_group_name(struct pinctrl_dev *pctldev,
+				      unsigned int selector)
+{
+	struct tps6594_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
+
+	return pinctrl->pins[selector].name;
+}
+
+static const struct pinctrl_ops tps6594_pctrl_ops = {
+	.dt_node_to_map = pinconf_generic_dt_node_to_map_group,
+	.dt_free_map = pinconf_generic_dt_free_map,
+	.get_groups_count = tps6594_groups_cnt,
+	.get_group_name = tps6594_group_name,
+	.get_group_pins = tps6594_group_pins,
+};
+
+static int tps6594_pinctrl_probe(struct platform_device *pdev)
+{
+	struct tps6594 *tps = dev_get_drvdata(pdev->dev.parent);
+	struct device *dev = &pdev->dev;
+	struct tps6594_pinctrl *pinctrl;
+	struct pinctrl_desc *pctrl_desc;
+	struct gpio_regmap_config config = {};
+
+	pctrl_desc = devm_kzalloc(dev, sizeof(*pctrl_desc), GFP_KERNEL);
+	if (!pctrl_desc)
+		return -ENOMEM;
+	pctrl_desc->name = dev_name(dev);
+	pctrl_desc->owner = THIS_MODULE;
+	pctrl_desc->pins = tps6594_pins;
+	pctrl_desc->npins = ARRAY_SIZE(tps6594_pins);
+	pctrl_desc->pctlops = &tps6594_pctrl_ops;
+	pctrl_desc->pmxops = &tps6594_pmx_ops;
+
+	pinctrl = devm_kzalloc(dev, sizeof(*pinctrl), GFP_KERNEL);
+	if (!pinctrl)
+		return -ENOMEM;
+	pinctrl->tps = dev_get_drvdata(dev->parent);
+	pinctrl->funcs = pinctrl_functions;
+	pinctrl->pins = tps6594_pins;
+	pinctrl->pctl_dev = devm_pinctrl_register(dev, pctrl_desc, pinctrl);
+	if (IS_ERR(pinctrl->pctl_dev))
+		return dev_err_probe(dev, PTR_ERR(pinctrl->pctl_dev),
+				     "Couldn't register pinctrl driver\n");
+
+	config.parent = tps->dev;
+	config.regmap = tps->regmap;
+	config.ngpio = TPS6594_PINCTRL_PINS_NB;
+	config.ngpio_per_reg = 8;
+	config.reg_dat_base = TPS6594_REG_GPIO_IN_1;
+	config.reg_set_base = TPS6594_REG_GPIO_OUT_1;
+	config.reg_dir_out_base = TPS6594_REG_GPIOX_CONF(0);
+	config.reg_mask_xlate = tps6594_gpio_regmap_xlate;
+
+	pinctrl->gpio_regmap = devm_gpio_regmap_register(dev, &config);
+	if (IS_ERR(pinctrl->gpio_regmap))
+		return dev_err_probe(dev, PTR_ERR(pinctrl->gpio_regmap),
+				     "Couldn't register gpio_regmap driver\n");
+
+	return 0;
+}
+
+static const struct platform_device_id tps6594_pinctrl_id_table[] = {
+	{ "tps6594-pinctrl", },
+	{}
+};
+MODULE_DEVICE_TABLE(platform, tps6594_pinctrl_id_table);
+
+static struct platform_driver tps6594_pinctrl_driver = {
+	.probe = tps6594_pinctrl_probe,
+	.driver = {
+		.name = "tps6594-pinctrl",
+	},
+	.id_table = tps6594_pinctrl_id_table,
+};
+module_platform_driver(tps6594_pinctrl_driver);
+
+MODULE_AUTHOR("Esteban Blanc <eblanc@baylibre.com>");
+MODULE_DESCRIPTION("TPS6594 pinctrl and GPIO driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/pinctrl/pinctrl-utils.c b/drivers/pinctrl/pinctrl-utils.c
index 40862f7bd6ca..d81d7b46116c 100644
--- a/drivers/pinctrl/pinctrl-utils.c
+++ b/drivers/pinctrl/pinctrl-utils.c
@@ -18,11 +18,11 @@
 #include "pinctrl-utils.h"
 
 int pinctrl_utils_reserve_map(struct pinctrl_dev *pctldev,
-		struct pinctrl_map **map, unsigned *reserved_maps,
-		unsigned *num_maps, unsigned reserve)
+		struct pinctrl_map **map, unsigned int *reserved_maps,
+		unsigned int *num_maps, unsigned int reserve)
 {
-	unsigned old_num = *reserved_maps;
-	unsigned new_num = *num_maps + reserve;
+	unsigned int old_num = *reserved_maps;
+	unsigned int new_num = *num_maps + reserve;
 	struct pinctrl_map *new_map;
 
 	if (old_num >= new_num)
@@ -43,8 +43,8 @@ int pinctrl_utils_reserve_map(struct pinctrl_dev *pctldev,
 EXPORT_SYMBOL_GPL(pinctrl_utils_reserve_map);
 
 int pinctrl_utils_add_map_mux(struct pinctrl_dev *pctldev,
-		struct pinctrl_map **map, unsigned *reserved_maps,
-		unsigned *num_maps, const char *group,
+		struct pinctrl_map **map, unsigned int *reserved_maps,
+		unsigned int *num_maps, const char *group,
 		const char *function)
 {
 	if (WARN_ON(*num_maps == *reserved_maps))
@@ -60,9 +60,9 @@ int pinctrl_utils_add_map_mux(struct pinctrl_dev *pctldev,
 EXPORT_SYMBOL_GPL(pinctrl_utils_add_map_mux);
 
 int pinctrl_utils_add_map_configs(struct pinctrl_dev *pctldev,
-		struct pinctrl_map **map, unsigned *reserved_maps,
-		unsigned *num_maps, const char *group,
-		unsigned long *configs, unsigned num_configs,
+		struct pinctrl_map **map, unsigned int *reserved_maps,
+		unsigned int *num_maps, const char *group,
+		unsigned long *configs, unsigned int num_configs,
 		enum pinctrl_map_type type)
 {
 	unsigned long *dup_configs;
@@ -86,11 +86,11 @@ int pinctrl_utils_add_map_configs(struct pinctrl_dev *pctldev,
 EXPORT_SYMBOL_GPL(pinctrl_utils_add_map_configs);
 
 int pinctrl_utils_add_config(struct pinctrl_dev *pctldev,
-		unsigned long **configs, unsigned *num_configs,
+		unsigned long **configs, unsigned int *num_configs,
 		unsigned long config)
 {
-	unsigned old_num = *num_configs;
-	unsigned new_num = old_num + 1;
+	unsigned int old_num = *num_configs;
+	unsigned int new_num = old_num + 1;
 	unsigned long *new_configs;
 
 	new_configs = krealloc(*configs, sizeof(*new_configs) * new_num,
@@ -110,7 +110,7 @@ int pinctrl_utils_add_config(struct pinctrl_dev *pctldev,
 EXPORT_SYMBOL_GPL(pinctrl_utils_add_config);
 
 void pinctrl_utils_free_map(struct pinctrl_dev *pctldev,
-	      struct pinctrl_map *map, unsigned num_maps)
+	      struct pinctrl_map *map, unsigned int num_maps)
 {
 	int i;
 
diff --git a/drivers/pinctrl/pinctrl-utils.h b/drivers/pinctrl/pinctrl-utils.h
index 4108ee2dd6d0..203fba257d71 100644
--- a/drivers/pinctrl/pinctrl-utils.h
+++ b/drivers/pinctrl/pinctrl-utils.h
@@ -15,21 +15,21 @@ struct pinctrl_dev;
 struct pinctrl_map;
 
 int pinctrl_utils_reserve_map(struct pinctrl_dev *pctldev,
-		struct pinctrl_map **map, unsigned *reserved_maps,
-		unsigned *num_maps, unsigned reserve);
+		struct pinctrl_map **map, unsigned int *reserved_maps,
+		unsigned int *num_maps, unsigned int reserve);
 int pinctrl_utils_add_map_mux(struct pinctrl_dev *pctldev,
-		struct pinctrl_map **map, unsigned *reserved_maps,
-		unsigned *num_maps, const char *group,
+		struct pinctrl_map **map, unsigned int *reserved_maps,
+		unsigned int *num_maps, const char *group,
 		const char *function);
 int pinctrl_utils_add_map_configs(struct pinctrl_dev *pctldev,
-		struct pinctrl_map **map, unsigned *reserved_maps,
-		unsigned *num_maps, const char *group,
-		unsigned long *configs, unsigned num_configs,
+		struct pinctrl_map **map, unsigned int *reserved_maps,
+		unsigned int *num_maps, const char *group,
+		unsigned long *configs, unsigned int num_configs,
 		enum pinctrl_map_type type);
 int pinctrl_utils_add_config(struct pinctrl_dev *pctldev,
-		unsigned long **configs, unsigned *num_configs,
+		unsigned long **configs, unsigned int *num_configs,
 		unsigned long config);
 void pinctrl_utils_free_map(struct pinctrl_dev *pctldev,
-		struct pinctrl_map *map, unsigned num_maps);
+		struct pinctrl_map *map, unsigned int num_maps);
 
 #endif /* __PINCTRL_UTILS_H__ */
diff --git a/drivers/pinctrl/pinmux.c b/drivers/pinctrl/pinmux.c
index 23d2da0b99b9..abbb044d6ace 100644
--- a/drivers/pinctrl/pinmux.c
+++ b/drivers/pinctrl/pinmux.c
@@ -35,8 +35,8 @@
 int pinmux_check_ops(struct pinctrl_dev *pctldev)
 {
 	const struct pinmux_ops *ops = pctldev->desc->pmxops;
-	unsigned nfuncs;
-	unsigned selector = 0;
+	unsigned int nfuncs;
+	unsigned int selector = 0;
 
 	/* Check that we implement required operations */
 	if (!ops ||
@@ -84,7 +84,7 @@ int pinmux_validate_map(const struct pinctrl_map *map, int i)
  * Controllers not defined as strict will always return true,
  * menaning that the gpio can be used.
  */
-bool pinmux_can_be_used_for_gpio(struct pinctrl_dev *pctldev, unsigned pin)
+bool pinmux_can_be_used_for_gpio(struct pinctrl_dev *pctldev, unsigned int pin)
 {
 	struct pin_desc *desc = pin_desc_get(pctldev, pin);
 	const struct pinmux_ops *ops = pctldev->desc->pmxops;
@@ -262,7 +262,7 @@ static const char *pin_free(struct pinctrl_dev *pctldev, int pin,
  */
 int pinmux_request_gpio(struct pinctrl_dev *pctldev,
 			struct pinctrl_gpio_range *range,
-			unsigned pin, unsigned gpio)
+			unsigned int pin, unsigned int gpio)
 {
 	const char *owner;
 	int ret;
@@ -285,7 +285,7 @@ int pinmux_request_gpio(struct pinctrl_dev *pctldev,
  * @pin: the affected currently GPIO-muxed in pin
  * @range: applicable GPIO range
  */
-void pinmux_free_gpio(struct pinctrl_dev *pctldev, unsigned pin,
+void pinmux_free_gpio(struct pinctrl_dev *pctldev, unsigned int pin,
 		      struct pinctrl_gpio_range *range)
 {
 	const char *owner;
@@ -303,7 +303,7 @@ void pinmux_free_gpio(struct pinctrl_dev *pctldev, unsigned pin,
  */
 int pinmux_gpio_direction(struct pinctrl_dev *pctldev,
 			  struct pinctrl_gpio_range *range,
-			  unsigned pin, bool input)
+			  unsigned int pin, bool input)
 {
 	const struct pinmux_ops *ops;
 	int ret;
@@ -322,8 +322,8 @@ static int pinmux_func_name_to_selector(struct pinctrl_dev *pctldev,
 					const char *function)
 {
 	const struct pinmux_ops *ops = pctldev->desc->pmxops;
-	unsigned nfuncs = ops->get_functions_count(pctldev);
-	unsigned selector = 0;
+	unsigned int nfuncs = ops->get_functions_count(pctldev);
+	unsigned int selector = 0;
 
 	/* See if this pctldev has this function */
 	while (selector < nfuncs) {
@@ -344,7 +344,7 @@ int pinmux_map_to_setting(const struct pinctrl_map *map,
 	struct pinctrl_dev *pctldev = setting->pctldev;
 	const struct pinmux_ops *pmxops = pctldev->desc->pmxops;
 	char const * const *groups;
-	unsigned num_groups;
+	unsigned int num_groups;
 	int ret;
 	const char *group;
 
@@ -409,8 +409,8 @@ int pinmux_enable_setting(const struct pinctrl_setting *setting)
 	const struct pinctrl_ops *pctlops = pctldev->desc->pctlops;
 	const struct pinmux_ops *ops = pctldev->desc->pmxops;
 	int ret = 0;
-	const unsigned *pins = NULL;
-	unsigned num_pins = 0;
+	const unsigned int *pins = NULL;
+	unsigned int num_pins = 0;
 	int i;
 	struct pin_desc *desc;
 
@@ -489,8 +489,8 @@ void pinmux_disable_setting(const struct pinctrl_setting *setting)
 	struct pinctrl_dev *pctldev = setting->pctldev;
 	const struct pinctrl_ops *pctlops = pctldev->desc->pctlops;
 	int ret = 0;
-	const unsigned *pins = NULL;
-	unsigned num_pins = 0;
+	const unsigned int *pins = NULL;
+	unsigned int num_pins = 0;
 	int i;
 	struct pin_desc *desc;
 
@@ -541,8 +541,8 @@ static int pinmux_functions_show(struct seq_file *s, void *what)
 {
 	struct pinctrl_dev *pctldev = s->private;
 	const struct pinmux_ops *pmxops = pctldev->desc->pmxops;
-	unsigned nfuncs;
-	unsigned func_selector = 0;
+	unsigned int nfuncs;
+	unsigned int func_selector = 0;
 
 	if (!pmxops)
 		return 0;
@@ -553,7 +553,7 @@ static int pinmux_functions_show(struct seq_file *s, void *what)
 		const char *func = pmxops->get_function_name(pctldev,
 							  func_selector);
 		const char * const *groups;
-		unsigned num_groups;
+		unsigned int num_groups;
 		int ret;
 		int i;
 
@@ -584,7 +584,7 @@ static int pinmux_pins_show(struct seq_file *s, void *what)
 	struct pinctrl_dev *pctldev = s->private;
 	const struct pinctrl_ops *pctlops = pctldev->desc->pctlops;
 	const struct pinmux_ops *pmxops = pctldev->desc->pmxops;
-	unsigned i, pin;
+	unsigned int i, pin;
 
 	if (!pmxops)
 		return 0;
@@ -818,7 +818,7 @@ EXPORT_SYMBOL_GPL(pinmux_generic_get_function_name);
 int pinmux_generic_get_function_groups(struct pinctrl_dev *pctldev,
 				       unsigned int selector,
 				       const char * const **groups,
-				       unsigned * const num_groups)
+				       unsigned int * const num_groups)
 {
 	struct function_desc *function;
 
diff --git a/drivers/pinctrl/pinmux.h b/drivers/pinctrl/pinmux.h
index ea6f99c24aa5..7c8aa25ccc80 100644
--- a/drivers/pinctrl/pinmux.h
+++ b/drivers/pinctrl/pinmux.h
@@ -26,16 +26,16 @@ int pinmux_check_ops(struct pinctrl_dev *pctldev);
 
 int pinmux_validate_map(const struct pinctrl_map *map, int i);
 
-bool pinmux_can_be_used_for_gpio(struct pinctrl_dev *pctldev, unsigned pin);
+bool pinmux_can_be_used_for_gpio(struct pinctrl_dev *pctldev, unsigned int pin);
 
 int pinmux_request_gpio(struct pinctrl_dev *pctldev,
 			struct pinctrl_gpio_range *range,
-			unsigned pin, unsigned gpio);
-void pinmux_free_gpio(struct pinctrl_dev *pctldev, unsigned pin,
+			unsigned int pin, unsigned int gpio);
+void pinmux_free_gpio(struct pinctrl_dev *pctldev, unsigned int pin,
 		      struct pinctrl_gpio_range *range);
 int pinmux_gpio_direction(struct pinctrl_dev *pctldev,
 			  struct pinctrl_gpio_range *range,
-			  unsigned pin, bool input);
+			  unsigned int pin, bool input);
 
 int pinmux_map_to_setting(const struct pinctrl_map *map,
 			  struct pinctrl_setting *setting);
@@ -56,27 +56,27 @@ static inline int pinmux_validate_map(const struct pinctrl_map *map, int i)
 }
 
 static inline bool pinmux_can_be_used_for_gpio(struct pinctrl_dev *pctldev,
-					       unsigned pin)
+					       unsigned int pin)
 {
 	return true;
 }
 
 static inline int pinmux_request_gpio(struct pinctrl_dev *pctldev,
 			struct pinctrl_gpio_range *range,
-			unsigned pin, unsigned gpio)
+			unsigned int pin, unsigned int gpio)
 {
 	return 0;
 }
 
 static inline void pinmux_free_gpio(struct pinctrl_dev *pctldev,
-				    unsigned pin,
+				    unsigned int pin,
 				    struct pinctrl_gpio_range *range)
 {
 }
 
 static inline int pinmux_gpio_direction(struct pinctrl_dev *pctldev,
 					struct pinctrl_gpio_range *range,
-					unsigned pin, bool input)
+					unsigned int pin, bool input)
 {
 	return 0;
 }
@@ -154,7 +154,7 @@ pinmux_generic_get_function_name(struct pinctrl_dev *pctldev,
 int pinmux_generic_get_function_groups(struct pinctrl_dev *pctldev,
 				       unsigned int selector,
 				       const char * const **groups,
-				       unsigned * const num_groups);
+				       unsigned int * const num_groups);
 
 struct function_desc *pinmux_generic_get_function(struct pinctrl_dev *pctldev,
 						  unsigned int selector);
@@ -162,7 +162,7 @@ struct function_desc *pinmux_generic_get_function(struct pinctrl_dev *pctldev,
 int pinmux_generic_add_function(struct pinctrl_dev *pctldev,
 				const char *name,
 				const char * const *groups,
-				unsigned const num_groups,
+				unsigned int const num_groups,
 				void *data);
 
 int pinmux_generic_remove_function(struct pinctrl_dev *pctldev,
diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig
index f84c0d3b7951..e0f2829c15d6 100644
--- a/drivers/pinctrl/qcom/Kconfig
+++ b/drivers/pinctrl/qcom/Kconfig
@@ -124,4 +124,14 @@ config PINCTRL_SM8550_LPASS_LPI
 	  (Low Power Island) found on the Qualcomm Technologies Inc SM8550
 	  platform.
 
+config PINCTRL_SM8650_LPASS_LPI
+	tristate "Qualcomm Technologies Inc SM8550 LPASS LPI pin controller driver"
+	depends on ARM64 || COMPILE_TEST
+	depends on PINCTRL_LPASS_LPI
+	help
+	  This is the pinctrl, pinmux, pinconf and gpiolib driver for the
+	  Qualcomm Technologies Inc LPASS (Low Power Audio SubSystem) LPI
+	  (Low Power Island) found on the Qualcomm Technologies Inc SM8650
+	  platform.
+
 endif
diff --git a/drivers/pinctrl/qcom/Kconfig.msm b/drivers/pinctrl/qcom/Kconfig.msm
index 01dd7b134354..8fe459d082ed 100644
--- a/drivers/pinctrl/qcom/Kconfig.msm
+++ b/drivers/pinctrl/qcom/Kconfig.msm
@@ -286,6 +286,14 @@ config PINCTRL_SDX75
          Qualcomm Technologies Inc TLMM block found on the Qualcomm
          Technologies Inc SDX75 platform.
 
+config PINCTRL_SM4450
+	tristate "Qualcomm Technologies Inc SM4450 pin controller driver"
+	depends on ARM64 || COMPILE_TEST
+	help
+	 This is the pinctrl, pinmux, pinconf and gpiolib driver for the
+	 Qualcomm Technologies Inc TLMM block found on the Qualcomm
+	 Technologies Inc SM4450 platform.
+
 config PINCTRL_SM6115
 	tristate "Qualcomm Technologies Inc SM6115,SM4250 pin controller driver"
 	depends on ARM64 || COMPILE_TEST
@@ -366,4 +374,22 @@ config PINCTRL_SM8550
 	  Qualcomm Technologies Inc TLMM block found on the Qualcomm
 	  Technologies Inc SM8550 platform.
 
+config PINCTRL_SM8650
+	tristate "Qualcomm Technologies Inc SM8650 pin controller driver"
+	depends on ARM64 || COMPILE_TEST
+	help
+	  This is the pinctrl, pinmux, pinconf and gpiolib driver for the
+	  Qualcomm Technologies Inc TLMM block found on the Qualcomm
+	  Technologies Inc SM8650 platform.
+
+config PINCTRL_X1E80100
+	tristate "Qualcomm Technologies Inc X1E80100 pin controller driver"
+	depends on ARM64 || COMPILE_TEST
+	help
+	  This is the pinctrl, pinmux, pinconf and gpiolib driver for the
+	  Qualcomm Technologies Inc Top Level Mode Multiplexer block (TLMM)
+	  block found on the Qualcomm Technologies Inc X1E80100 platform.
+	  Say Y here to compile statically, or M here to compile it as a module.
+	  If unsure, say N.
+
 endif
diff --git a/drivers/pinctrl/qcom/Makefile b/drivers/pinctrl/qcom/Makefile
index 5910e08c84ce..e2e76071d268 100644
--- a/drivers/pinctrl/qcom/Makefile
+++ b/drivers/pinctrl/qcom/Makefile
@@ -43,6 +43,7 @@ obj-$(CONFIG_PINCTRL_SDM845) += pinctrl-sdm845.o
 obj-$(CONFIG_PINCTRL_SDX55) += pinctrl-sdx55.o
 obj-$(CONFIG_PINCTRL_SDX65) += pinctrl-sdx65.o
 obj-$(CONFIG_PINCTRL_SDX75) += pinctrl-sdx75.o
+obj-$(CONFIG_PINCTRL_SM4450) += pinctrl-sm4450.o
 obj-$(CONFIG_PINCTRL_SM6115) += pinctrl-sm6115.o
 obj-$(CONFIG_PINCTRL_SM6115_LPASS_LPI) += pinctrl-sm6115-lpass-lpi.o
 obj-$(CONFIG_PINCTRL_SM6125) += pinctrl-sm6125.o
@@ -58,5 +59,8 @@ obj-$(CONFIG_PINCTRL_SM8450) += pinctrl-sm8450.o
 obj-$(CONFIG_PINCTRL_SM8450_LPASS_LPI) += pinctrl-sm8450-lpass-lpi.o
 obj-$(CONFIG_PINCTRL_SM8550) += pinctrl-sm8550.o
 obj-$(CONFIG_PINCTRL_SM8550_LPASS_LPI) += pinctrl-sm8550-lpass-lpi.o
+obj-$(CONFIG_PINCTRL_SM8650) += pinctrl-sm8650.o
+obj-$(CONFIG_PINCTRL_SM8650_LPASS_LPI) += pinctrl-sm8650-lpass-lpi.o
 obj-$(CONFIG_PINCTRL_SC8280XP_LPASS_LPI) += pinctrl-sc8280xp-lpass-lpi.o
 obj-$(CONFIG_PINCTRL_LPASS_LPI) += pinctrl-lpass-lpi.o
+obj-$(CONFIG_PINCTRL_X1E80100)	+= pinctrl-x1e80100.o
diff --git a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c
index 9651aed048cf..0d98008e33ee 100644
--- a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c
@@ -186,6 +186,41 @@ static int lpi_config_get(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
+static int lpi_config_set_slew_rate(struct lpi_pinctrl *pctrl,
+				    const struct lpi_pingroup *g,
+				    unsigned int group, unsigned int slew)
+{
+	unsigned long sval;
+	void __iomem *reg;
+	int slew_offset;
+
+	if (slew > LPI_SLEW_RATE_MAX) {
+		dev_err(pctrl->dev, "invalid slew rate %u for pin: %d\n",
+			slew, group);
+		return -EINVAL;
+	}
+
+	slew_offset = g->slew_offset;
+	if (slew_offset == LPI_NO_SLEW)
+		return 0;
+
+	if (pctrl->data->flags & LPI_FLAG_SLEW_RATE_SAME_REG)
+		reg = pctrl->tlmm_base + LPI_TLMM_REG_OFFSET * group + LPI_GPIO_CFG_REG;
+	else
+		reg = pctrl->slew_base + LPI_SLEW_RATE_CTL_REG;
+
+	mutex_lock(&pctrl->lock);
+
+	sval = ioread32(reg);
+	sval &= ~(LPI_SLEW_RATE_MASK << slew_offset);
+	sval |= slew << slew_offset;
+	iowrite32(sval, reg);
+
+	mutex_unlock(&pctrl->lock);
+
+	return 0;
+}
+
 static int lpi_config_set(struct pinctrl_dev *pctldev, unsigned int group,
 			  unsigned long *configs, unsigned int nconfs)
 {
@@ -193,8 +228,7 @@ static int lpi_config_set(struct pinctrl_dev *pctldev, unsigned int group,
 	unsigned int param, arg, pullup = LPI_GPIO_BIAS_DISABLE, strength = 2;
 	bool value, output_enabled = false;
 	const struct lpi_pingroup *g;
-	unsigned long sval;
-	int i, slew_offset;
+	int i, ret;
 	u32 val;
 
 	g = &pctrl->data->groups[group];
@@ -226,24 +260,9 @@ static int lpi_config_set(struct pinctrl_dev *pctldev, unsigned int group,
 			strength = arg;
 			break;
 		case PIN_CONFIG_SLEW_RATE:
-			if (arg > LPI_SLEW_RATE_MAX) {
-				dev_err(pctldev->dev, "invalid slew rate %u for pin: %d\n",
-					arg, group);
-				return -EINVAL;
-			}
-
-			slew_offset = g->slew_offset;
-			if (slew_offset == LPI_NO_SLEW)
-				break;
-
-			mutex_lock(&pctrl->lock);
-
-			sval = ioread32(pctrl->slew_base + LPI_SLEW_RATE_CTL_REG);
-			sval &= ~(LPI_SLEW_RATE_MASK << slew_offset);
-			sval |= arg << slew_offset;
-			iowrite32(sval, pctrl->slew_base + LPI_SLEW_RATE_CTL_REG);
-
-			mutex_unlock(&pctrl->lock);
+			ret = lpi_config_set_slew_rate(pctrl, g, group, arg);
+			if (ret)
+				return ret;
 			break;
 		default:
 			return -EINVAL;
@@ -319,7 +338,6 @@ static void lpi_gpio_set(struct gpio_chip *chip, unsigned int pin, int value)
 }
 
 #ifdef CONFIG_DEBUG_FS
-#include <linux/seq_file.h>
 
 static unsigned int lpi_regval_to_drive(u32 val)
 {
@@ -439,10 +457,12 @@ int lpi_pinctrl_probe(struct platform_device *pdev)
 		return dev_err_probe(dev, PTR_ERR(pctrl->tlmm_base),
 				     "TLMM resource not provided\n");
 
-	pctrl->slew_base = devm_platform_ioremap_resource(pdev, 1);
-	if (IS_ERR(pctrl->slew_base))
-		return dev_err_probe(dev, PTR_ERR(pctrl->slew_base),
-				     "Slew resource not provided\n");
+	if (!(data->flags & LPI_FLAG_SLEW_RATE_SAME_REG)) {
+		pctrl->slew_base = devm_platform_ioremap_resource(pdev, 1);
+		if (IS_ERR(pctrl->slew_base))
+			return dev_err_probe(dev, PTR_ERR(pctrl->slew_base),
+					     "Slew resource not provided\n");
+	}
 
 	ret = devm_clk_bulk_get_optional(dev, MAX_LPI_NUM_CLKS, pctrl->clks);
 	if (ret)
diff --git a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.h b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.h
index 387d83ee95b5..a9b2f65c1ebe 100644
--- a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.h
+++ b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.h
@@ -6,8 +6,8 @@
 #ifndef __PINCTRL_LPASS_LPI_H__
 #define __PINCTRL_LPASS_LPI_H__
 
+#include <linux/array_size.h>
 #include <linux/bits.h>
-#include <linux/kernel.h>
 
 #include "../core.h"
 
@@ -45,11 +45,8 @@ struct pinctrl_pin_desc;
 
 #define LPI_PINGROUP(id, soff, f1, f2, f3, f4)		\
 	{						\
-		.group.name = "gpio" #id,			\
-		.group.pins = gpio##id##_pins,		\
 		.pin = id,				\
 		.slew_offset = soff,			\
-		.group.num_pins = ARRAY_SIZE(gpio##id##_pins),	\
 		.funcs = (int[]){			\
 			LPI_MUX_gpio,			\
 			LPI_MUX_##f1,			\
@@ -60,8 +57,13 @@ struct pinctrl_pin_desc;
 		.nfuncs = 5,				\
 	}
 
+/*
+ * Slew rate control is done in the same register as rest of the
+ * pin configuration.
+ */
+#define LPI_FLAG_SLEW_RATE_SAME_REG			BIT(0)
+
 struct lpi_pingroup {
-	struct group_desc group;
 	unsigned int pin;
 	/* Bit offset in slew register for SoundWire pins only */
 	int slew_offset;
@@ -82,6 +84,7 @@ struct lpi_pinctrl_variant_data {
 	int ngroups;
 	const struct lpi_function *functions;
 	int nfunctions;
+	unsigned int flags;
 };
 
 int lpi_pinctrl_probe(struct platform_device *pdev);
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index 395040346d0f..aeaf0d1958f5 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -358,6 +358,10 @@ static int msm_config_group_get(struct pinctrl_dev *pctldev,
 	int ret;
 	u32 val;
 
+	/* Pin information can only be requested from valid pin groups */
+	if (!gpiochip_line_is_valid(&pctrl->chip, group))
+		return -EINVAL;
+
 	g = &pctrl->soc->groups[group];
 
 	ret = msm_config_reg(pctrl, g, param, &mask, &bit);
@@ -1196,6 +1200,8 @@ static int msm_gpio_irq_reqres(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct msm_pinctrl *pctrl = gpiochip_get_data(gc);
+	const struct msm_pingroup *g = &pctrl->soc->groups[d->hwirq];
+	unsigned long flags;
 	int ret;
 
 	if (!try_module_get(gc->owner))
@@ -1221,6 +1227,28 @@ static int msm_gpio_irq_reqres(struct irq_data *d)
 	 */
 	irq_set_status_flags(d->irq, IRQ_DISABLE_UNLAZY);
 
+	/*
+	 * If the wakeup_enable bit is present and marked as available for the
+	 * requested GPIO, it should be enabled when the GPIO is marked as
+	 * wake irq in order to allow the interrupt event to be transfered to
+	 * the PDC HW.
+	 * While the name implies only the wakeup event, it's also required for
+	 * the interrupt event.
+	 */
+	if (test_bit(d->hwirq, pctrl->skip_wake_irqs) && g->intr_wakeup_present_bit) {
+		u32 intr_cfg;
+
+		raw_spin_lock_irqsave(&pctrl->lock, flags);
+
+		intr_cfg = msm_readl_intr_cfg(pctrl, g);
+		if (intr_cfg & BIT(g->intr_wakeup_present_bit)) {
+			intr_cfg |= BIT(g->intr_wakeup_enable_bit);
+			msm_writel_intr_cfg(intr_cfg, pctrl, g);
+		}
+
+		raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+	}
+
 	return 0;
 out:
 	module_put(gc->owner);
@@ -1230,6 +1258,24 @@ out:
 static void msm_gpio_irq_relres(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct msm_pinctrl *pctrl = gpiochip_get_data(gc);
+	const struct msm_pingroup *g = &pctrl->soc->groups[d->hwirq];
+	unsigned long flags;
+
+	/* Disable the wakeup_enable bit if it has been set in msm_gpio_irq_reqres() */
+	if (test_bit(d->hwirq, pctrl->skip_wake_irqs) && g->intr_wakeup_present_bit) {
+		u32 intr_cfg;
+
+		raw_spin_lock_irqsave(&pctrl->lock, flags);
+
+		intr_cfg = msm_readl_intr_cfg(pctrl, g);
+		if (intr_cfg & BIT(g->intr_wakeup_present_bit)) {
+			intr_cfg &= ~BIT(g->intr_wakeup_enable_bit);
+			msm_writel_intr_cfg(intr_cfg, pctrl, g);
+		}
+
+		raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+	}
 
 	gpiochip_unlock_as_irq(gc, d->hwirq);
 	module_put(gc->owner);
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.h b/drivers/pinctrl/qcom/pinctrl-msm.h
index 4968d08a384d..63852ed70295 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.h
+++ b/drivers/pinctrl/qcom/pinctrl-msm.h
@@ -58,6 +58,9 @@ struct pinctrl_pin_desc;
  * @intr_enable_bit:      Offset in @intr_cfg_reg for enabling the interrupt for this group.
  * @intr_status_bit:      Offset in @intr_status_reg for reading and acking the interrupt
  *                        status.
+ * @intr_wakeup_present_bit: Offset in @intr_target_reg specifying the GPIO can generate
+ *			  wakeup events.
+ * @intr_wakeup_enable_bit: Offset in @intr_target_reg to enable wakeup events for the GPIO.
  * @intr_target_bit:      Offset in @intr_target_reg for configuring the interrupt routing.
  * @intr_target_width:    Number of bits used for specifying interrupt routing target.
  * @intr_target_kpss_val: Value in @intr_target_bit for specifying that the interrupt from
@@ -100,6 +103,8 @@ struct msm_pingroup {
 	unsigned intr_status_bit:5;
 	unsigned intr_ack_high:1;
 
+	unsigned intr_wakeup_present_bit:5;
+	unsigned intr_wakeup_enable_bit:5;
 	unsigned intr_target_bit:5;
 	unsigned intr_target_width:5;
 	unsigned intr_target_kpss_val:5;
diff --git a/drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c
index 99156217c6a5..6bb39812e1d8 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c
@@ -36,22 +36,6 @@ enum lpass_lpi_functions {
 	LPI_MUX__,
 };
 
-static int gpio0_pins[] = { 0 };
-static int gpio1_pins[] = { 1 };
-static int gpio2_pins[] = { 2 };
-static int gpio3_pins[] = { 3 };
-static int gpio4_pins[] = { 4 };
-static int gpio5_pins[] = { 5 };
-static int gpio6_pins[] = { 6 };
-static int gpio7_pins[] = { 7 };
-static int gpio8_pins[] = { 8 };
-static int gpio9_pins[] = { 9 };
-static int gpio10_pins[] = { 10 };
-static int gpio11_pins[] = { 11 };
-static int gpio12_pins[] = { 12 };
-static int gpio13_pins[] = { 13 };
-static int gpio14_pins[] = { 14 };
-
 static const struct pinctrl_pin_desc sc7280_lpi_pins[] = {
 	PINCTRL_PIN(0, "gpio0"),
 	PINCTRL_PIN(1, "gpio1"),
diff --git a/drivers/pinctrl/qcom/pinctrl-sc8280xp-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sc8280xp-lpass-lpi.c
index b33483056f42..c0369baf3398 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc8280xp-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc8280xp-lpass-lpi.c
@@ -45,26 +45,6 @@ enum lpass_lpi_functions {
 	LPI_MUX__,
 };
 
-static int gpio0_pins[] = { 0 };
-static int gpio1_pins[] = { 1 };
-static int gpio2_pins[] = { 2 };
-static int gpio3_pins[] = { 3 };
-static int gpio4_pins[] = { 4 };
-static int gpio5_pins[] = { 5 };
-static int gpio6_pins[] = { 6 };
-static int gpio7_pins[] = { 7 };
-static int gpio8_pins[] = { 8 };
-static int gpio9_pins[] = { 9 };
-static int gpio10_pins[] = { 10 };
-static int gpio11_pins[] = { 11 };
-static int gpio12_pins[] = { 12 };
-static int gpio13_pins[] = { 13 };
-static int gpio14_pins[] = { 14 };
-static int gpio15_pins[] = { 15 };
-static int gpio16_pins[] = { 16 };
-static int gpio17_pins[] = { 17 };
-static int gpio18_pins[] = { 18 };
-
 static const struct pinctrl_pin_desc sc8280xp_lpi_pins[] = {
 	PINCTRL_PIN(0, "gpio0"),
 	PINCTRL_PIN(1, "gpio1"),
diff --git a/drivers/pinctrl/qcom/pinctrl-sm4450.c b/drivers/pinctrl/qcom/pinctrl-sm4450.c
new file mode 100644
index 000000000000..27317b86d835
--- /dev/null
+++ b/drivers/pinctrl/qcom/pinctrl-sm4450.c
@@ -0,0 +1,1014 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include "pinctrl-msm.h"
+
+#define REG_SIZE 0x1000
+
+#define PINGROUP(id, f1, f2, f3, f4, f5, f6, f7, f8, f9)	\
+	{					        \
+		.grp = PINCTRL_PINGROUP("gpio" #id,     \
+			gpio##id##_pins,                \
+			ARRAY_SIZE(gpio##id##_pins)),   \
+		.funcs = (int[]){			\
+			msm_mux_gpio, /* gpio mode */	\
+			msm_mux_##f1,			\
+			msm_mux_##f2,			\
+			msm_mux_##f3,			\
+			msm_mux_##f4,			\
+			msm_mux_##f5,			\
+			msm_mux_##f6,			\
+			msm_mux_##f7,			\
+			msm_mux_##f8,			\
+			msm_mux_##f9			\
+		},				        \
+		.nfuncs = 10,				\
+		.ctl_reg = REG_SIZE * id,			\
+		.io_reg = 0x4 + REG_SIZE * id,		\
+		.intr_cfg_reg = 0x8 + REG_SIZE * id,		\
+		.intr_status_reg = 0xc + REG_SIZE * id,	\
+		.intr_target_reg = 0x8 + REG_SIZE * id,	\
+		.mux_bit = 2,			\
+		.pull_bit = 0,			\
+		.drv_bit = 6,			\
+		.egpio_enable = 12,		\
+		.egpio_present = 11,		\
+		.oe_bit = 9,			\
+		.in_bit = 0,			\
+		.out_bit = 1,			\
+		.intr_enable_bit = 0,		\
+		.intr_status_bit = 0,		\
+		.intr_target_bit = 5,		\
+		.intr_target_kpss_val = 3,	\
+		.intr_raw_status_bit = 4,	\
+		.intr_polarity_bit = 1,		\
+		.intr_detection_bit = 2,	\
+		.intr_detection_width = 2,	\
+	}
+
+#define SDC_QDSD_PINGROUP(pg_name, ctl, pull, drv)	\
+	{					        \
+		.grp = PINCTRL_PINGROUP(#pg_name,       \
+			pg_name##_pins,                 \
+			ARRAY_SIZE(pg_name##_pins)),    \
+		.ctl_reg = ctl,				\
+		.io_reg = 0,				\
+		.intr_cfg_reg = 0,			\
+		.intr_status_reg = 0,			\
+		.intr_target_reg = 0,			\
+		.mux_bit = -1,				\
+		.pull_bit = pull,			\
+		.drv_bit = drv,				\
+		.oe_bit = -1,				\
+		.in_bit = -1,				\
+		.out_bit = -1,				\
+		.intr_enable_bit = -1,			\
+		.intr_status_bit = -1,			\
+		.intr_target_bit = -1,			\
+		.intr_raw_status_bit = -1,		\
+		.intr_polarity_bit = -1,		\
+		.intr_detection_bit = -1,		\
+		.intr_detection_width = -1,		\
+	}
+
+#define UFS_RESET(pg_name, offset)				\
+	{					        \
+		.grp = PINCTRL_PINGROUP(#pg_name,       \
+			pg_name##_pins,                 \
+			ARRAY_SIZE(pg_name##_pins)),    \
+		.ctl_reg = offset,			\
+		.io_reg = offset + 0x4,			\
+		.intr_cfg_reg = 0,			\
+		.intr_status_reg = 0,			\
+		.intr_target_reg = 0,			\
+		.mux_bit = -1,				\
+		.pull_bit = 3,				\
+		.drv_bit = 0,				\
+		.oe_bit = -1,				\
+		.in_bit = -1,				\
+		.out_bit = 0,				\
+		.intr_enable_bit = -1,			\
+		.intr_status_bit = -1,			\
+		.intr_target_bit = -1,			\
+		.intr_raw_status_bit = -1,		\
+		.intr_polarity_bit = -1,		\
+		.intr_detection_bit = -1,		\
+		.intr_detection_width = -1,		\
+	}
+
+#define QUP_I3C(qup_mode, qup_offset)			\
+	{						\
+		.mode = qup_mode,			\
+		.offset = qup_offset,			\
+	}
+
+
+static const struct pinctrl_pin_desc sm4450_pins[] = {
+	PINCTRL_PIN(0, "GPIO_0"),
+	PINCTRL_PIN(1, "GPIO_1"),
+	PINCTRL_PIN(2, "GPIO_2"),
+	PINCTRL_PIN(3, "GPIO_3"),
+	PINCTRL_PIN(4, "GPIO_4"),
+	PINCTRL_PIN(5, "GPIO_5"),
+	PINCTRL_PIN(6, "GPIO_6"),
+	PINCTRL_PIN(7, "GPIO_7"),
+	PINCTRL_PIN(8, "GPIO_8"),
+	PINCTRL_PIN(9, "GPIO_9"),
+	PINCTRL_PIN(10, "GPIO_10"),
+	PINCTRL_PIN(11, "GPIO_11"),
+	PINCTRL_PIN(12, "GPIO_12"),
+	PINCTRL_PIN(13, "GPIO_13"),
+	PINCTRL_PIN(14, "GPIO_14"),
+	PINCTRL_PIN(15, "GPIO_15"),
+	PINCTRL_PIN(16, "GPIO_16"),
+	PINCTRL_PIN(17, "GPIO_17"),
+	PINCTRL_PIN(18, "GPIO_18"),
+	PINCTRL_PIN(19, "GPIO_19"),
+	PINCTRL_PIN(20, "GPIO_20"),
+	PINCTRL_PIN(21, "GPIO_21"),
+	PINCTRL_PIN(22, "GPIO_22"),
+	PINCTRL_PIN(23, "GPIO_23"),
+	PINCTRL_PIN(24, "GPIO_24"),
+	PINCTRL_PIN(25, "GPIO_25"),
+	PINCTRL_PIN(26, "GPIO_26"),
+	PINCTRL_PIN(27, "GPIO_27"),
+	PINCTRL_PIN(28, "GPIO_28"),
+	PINCTRL_PIN(29, "GPIO_29"),
+	PINCTRL_PIN(30, "GPIO_30"),
+	PINCTRL_PIN(31, "GPIO_31"),
+	PINCTRL_PIN(32, "GPIO_32"),
+	PINCTRL_PIN(33, "GPIO_33"),
+	PINCTRL_PIN(34, "GPIO_34"),
+	PINCTRL_PIN(35, "GPIO_35"),
+	PINCTRL_PIN(36, "GPIO_36"),
+	PINCTRL_PIN(37, "GPIO_37"),
+	PINCTRL_PIN(38, "GPIO_38"),
+	PINCTRL_PIN(39, "GPIO_39"),
+	PINCTRL_PIN(40, "GPIO_40"),
+	PINCTRL_PIN(41, "GPIO_41"),
+	PINCTRL_PIN(42, "GPIO_42"),
+	PINCTRL_PIN(43, "GPIO_43"),
+	PINCTRL_PIN(44, "GPIO_44"),
+	PINCTRL_PIN(45, "GPIO_45"),
+	PINCTRL_PIN(46, "GPIO_46"),
+	PINCTRL_PIN(47, "GPIO_47"),
+	PINCTRL_PIN(48, "GPIO_48"),
+	PINCTRL_PIN(49, "GPIO_49"),
+	PINCTRL_PIN(50, "GPIO_50"),
+	PINCTRL_PIN(51, "GPIO_51"),
+	PINCTRL_PIN(52, "GPIO_52"),
+	PINCTRL_PIN(53, "GPIO_53"),
+	PINCTRL_PIN(54, "GPIO_54"),
+	PINCTRL_PIN(55, "GPIO_55"),
+	PINCTRL_PIN(56, "GPIO_56"),
+	PINCTRL_PIN(57, "GPIO_57"),
+	PINCTRL_PIN(58, "GPIO_58"),
+	PINCTRL_PIN(59, "GPIO_59"),
+	PINCTRL_PIN(60, "GPIO_60"),
+	PINCTRL_PIN(61, "GPIO_61"),
+	PINCTRL_PIN(62, "GPIO_62"),
+	PINCTRL_PIN(63, "GPIO_63"),
+	PINCTRL_PIN(64, "GPIO_64"),
+	PINCTRL_PIN(65, "GPIO_65"),
+	PINCTRL_PIN(66, "GPIO_66"),
+	PINCTRL_PIN(67, "GPIO_67"),
+	PINCTRL_PIN(68, "GPIO_68"),
+	PINCTRL_PIN(69, "GPIO_69"),
+	PINCTRL_PIN(70, "GPIO_70"),
+	PINCTRL_PIN(71, "GPIO_71"),
+	PINCTRL_PIN(72, "GPIO_72"),
+	PINCTRL_PIN(73, "GPIO_73"),
+	PINCTRL_PIN(74, "GPIO_74"),
+	PINCTRL_PIN(75, "GPIO_75"),
+	PINCTRL_PIN(76, "GPIO_76"),
+	PINCTRL_PIN(77, "GPIO_77"),
+	PINCTRL_PIN(78, "GPIO_78"),
+	PINCTRL_PIN(79, "GPIO_79"),
+	PINCTRL_PIN(80, "GPIO_80"),
+	PINCTRL_PIN(81, "GPIO_81"),
+	PINCTRL_PIN(82, "GPIO_82"),
+	PINCTRL_PIN(83, "GPIO_83"),
+	PINCTRL_PIN(84, "GPIO_84"),
+	PINCTRL_PIN(85, "GPIO_85"),
+	PINCTRL_PIN(86, "GPIO_86"),
+	PINCTRL_PIN(87, "GPIO_87"),
+	PINCTRL_PIN(88, "GPIO_88"),
+	PINCTRL_PIN(89, "GPIO_89"),
+	PINCTRL_PIN(90, "GPIO_90"),
+	PINCTRL_PIN(91, "GPIO_91"),
+	PINCTRL_PIN(92, "GPIO_92"),
+	PINCTRL_PIN(93, "GPIO_93"),
+	PINCTRL_PIN(94, "GPIO_94"),
+	PINCTRL_PIN(95, "GPIO_95"),
+	PINCTRL_PIN(96, "GPIO_96"),
+	PINCTRL_PIN(97, "GPIO_97"),
+	PINCTRL_PIN(98, "GPIO_98"),
+	PINCTRL_PIN(99, "GPIO_99"),
+	PINCTRL_PIN(100, "GPIO_100"),
+	PINCTRL_PIN(101, "GPIO_101"),
+	PINCTRL_PIN(102, "GPIO_102"),
+	PINCTRL_PIN(103, "GPIO_103"),
+	PINCTRL_PIN(104, "GPIO_104"),
+	PINCTRL_PIN(105, "GPIO_105"),
+	PINCTRL_PIN(106, "GPIO_106"),
+	PINCTRL_PIN(107, "GPIO_107"),
+	PINCTRL_PIN(108, "GPIO_108"),
+	PINCTRL_PIN(109, "GPIO_109"),
+	PINCTRL_PIN(110, "GPIO_110"),
+	PINCTRL_PIN(111, "GPIO_111"),
+	PINCTRL_PIN(112, "GPIO_112"),
+	PINCTRL_PIN(113, "GPIO_113"),
+	PINCTRL_PIN(114, "GPIO_114"),
+	PINCTRL_PIN(115, "GPIO_115"),
+	PINCTRL_PIN(116, "GPIO_116"),
+	PINCTRL_PIN(117, "GPIO_117"),
+	PINCTRL_PIN(118, "GPIO_118"),
+	PINCTRL_PIN(119, "GPIO_119"),
+	PINCTRL_PIN(120, "GPIO_120"),
+	PINCTRL_PIN(121, "GPIO_121"),
+	PINCTRL_PIN(122, "GPIO_122"),
+	PINCTRL_PIN(123, "GPIO_123"),
+	PINCTRL_PIN(124, "GPIO_124"),
+	PINCTRL_PIN(125, "GPIO_125"),
+	PINCTRL_PIN(126, "GPIO_126"),
+	PINCTRL_PIN(127, "GPIO_127"),
+	PINCTRL_PIN(128, "GPIO_128"),
+	PINCTRL_PIN(129, "GPIO_129"),
+	PINCTRL_PIN(130, "GPIO_130"),
+	PINCTRL_PIN(131, "GPIO_131"),
+	PINCTRL_PIN(132, "GPIO_132"),
+	PINCTRL_PIN(133, "GPIO_133"),
+	PINCTRL_PIN(134, "GPIO_134"),
+	PINCTRL_PIN(135, "GPIO_135"),
+	PINCTRL_PIN(136, "UFS_RESET"),
+	PINCTRL_PIN(137, "SDC1_RCLK"),
+	PINCTRL_PIN(138, "SDC1_CLK"),
+	PINCTRL_PIN(139, "SDC1_CMD"),
+	PINCTRL_PIN(140, "SDC1_DATA"),
+	PINCTRL_PIN(141, "SDC2_CLK"),
+	PINCTRL_PIN(142, "SDC2_CMD"),
+	PINCTRL_PIN(143, "SDC2_DATA"),
+};
+
+#define DECLARE_MSM_GPIO_PINS(pin) \
+	static const unsigned int gpio##pin##_pins[] = { pin }
+DECLARE_MSM_GPIO_PINS(0);
+DECLARE_MSM_GPIO_PINS(1);
+DECLARE_MSM_GPIO_PINS(2);
+DECLARE_MSM_GPIO_PINS(3);
+DECLARE_MSM_GPIO_PINS(4);
+DECLARE_MSM_GPIO_PINS(5);
+DECLARE_MSM_GPIO_PINS(6);
+DECLARE_MSM_GPIO_PINS(7);
+DECLARE_MSM_GPIO_PINS(8);
+DECLARE_MSM_GPIO_PINS(9);
+DECLARE_MSM_GPIO_PINS(10);
+DECLARE_MSM_GPIO_PINS(11);
+DECLARE_MSM_GPIO_PINS(12);
+DECLARE_MSM_GPIO_PINS(13);
+DECLARE_MSM_GPIO_PINS(14);
+DECLARE_MSM_GPIO_PINS(15);
+DECLARE_MSM_GPIO_PINS(16);
+DECLARE_MSM_GPIO_PINS(17);
+DECLARE_MSM_GPIO_PINS(18);
+DECLARE_MSM_GPIO_PINS(19);
+DECLARE_MSM_GPIO_PINS(20);
+DECLARE_MSM_GPIO_PINS(21);
+DECLARE_MSM_GPIO_PINS(22);
+DECLARE_MSM_GPIO_PINS(23);
+DECLARE_MSM_GPIO_PINS(24);
+DECLARE_MSM_GPIO_PINS(25);
+DECLARE_MSM_GPIO_PINS(26);
+DECLARE_MSM_GPIO_PINS(27);
+DECLARE_MSM_GPIO_PINS(28);
+DECLARE_MSM_GPIO_PINS(29);
+DECLARE_MSM_GPIO_PINS(30);
+DECLARE_MSM_GPIO_PINS(31);
+DECLARE_MSM_GPIO_PINS(32);
+DECLARE_MSM_GPIO_PINS(33);
+DECLARE_MSM_GPIO_PINS(34);
+DECLARE_MSM_GPIO_PINS(35);
+DECLARE_MSM_GPIO_PINS(36);
+DECLARE_MSM_GPIO_PINS(37);
+DECLARE_MSM_GPIO_PINS(38);
+DECLARE_MSM_GPIO_PINS(39);
+DECLARE_MSM_GPIO_PINS(40);
+DECLARE_MSM_GPIO_PINS(41);
+DECLARE_MSM_GPIO_PINS(42);
+DECLARE_MSM_GPIO_PINS(43);
+DECLARE_MSM_GPIO_PINS(44);
+DECLARE_MSM_GPIO_PINS(45);
+DECLARE_MSM_GPIO_PINS(46);
+DECLARE_MSM_GPIO_PINS(47);
+DECLARE_MSM_GPIO_PINS(48);
+DECLARE_MSM_GPIO_PINS(49);
+DECLARE_MSM_GPIO_PINS(50);
+DECLARE_MSM_GPIO_PINS(51);
+DECLARE_MSM_GPIO_PINS(52);
+DECLARE_MSM_GPIO_PINS(53);
+DECLARE_MSM_GPIO_PINS(54);
+DECLARE_MSM_GPIO_PINS(55);
+DECLARE_MSM_GPIO_PINS(56);
+DECLARE_MSM_GPIO_PINS(57);
+DECLARE_MSM_GPIO_PINS(58);
+DECLARE_MSM_GPIO_PINS(59);
+DECLARE_MSM_GPIO_PINS(60);
+DECLARE_MSM_GPIO_PINS(61);
+DECLARE_MSM_GPIO_PINS(62);
+DECLARE_MSM_GPIO_PINS(63);
+DECLARE_MSM_GPIO_PINS(64);
+DECLARE_MSM_GPIO_PINS(65);
+DECLARE_MSM_GPIO_PINS(66);
+DECLARE_MSM_GPIO_PINS(67);
+DECLARE_MSM_GPIO_PINS(68);
+DECLARE_MSM_GPIO_PINS(69);
+DECLARE_MSM_GPIO_PINS(70);
+DECLARE_MSM_GPIO_PINS(71);
+DECLARE_MSM_GPIO_PINS(72);
+DECLARE_MSM_GPIO_PINS(73);
+DECLARE_MSM_GPIO_PINS(74);
+DECLARE_MSM_GPIO_PINS(75);
+DECLARE_MSM_GPIO_PINS(76);
+DECLARE_MSM_GPIO_PINS(77);
+DECLARE_MSM_GPIO_PINS(78);
+DECLARE_MSM_GPIO_PINS(79);
+DECLARE_MSM_GPIO_PINS(80);
+DECLARE_MSM_GPIO_PINS(81);
+DECLARE_MSM_GPIO_PINS(82);
+DECLARE_MSM_GPIO_PINS(83);
+DECLARE_MSM_GPIO_PINS(84);
+DECLARE_MSM_GPIO_PINS(85);
+DECLARE_MSM_GPIO_PINS(86);
+DECLARE_MSM_GPIO_PINS(87);
+DECLARE_MSM_GPIO_PINS(88);
+DECLARE_MSM_GPIO_PINS(89);
+DECLARE_MSM_GPIO_PINS(90);
+DECLARE_MSM_GPIO_PINS(91);
+DECLARE_MSM_GPIO_PINS(92);
+DECLARE_MSM_GPIO_PINS(93);
+DECLARE_MSM_GPIO_PINS(94);
+DECLARE_MSM_GPIO_PINS(95);
+DECLARE_MSM_GPIO_PINS(96);
+DECLARE_MSM_GPIO_PINS(97);
+DECLARE_MSM_GPIO_PINS(98);
+DECLARE_MSM_GPIO_PINS(99);
+DECLARE_MSM_GPIO_PINS(100);
+DECLARE_MSM_GPIO_PINS(101);
+DECLARE_MSM_GPIO_PINS(102);
+DECLARE_MSM_GPIO_PINS(103);
+DECLARE_MSM_GPIO_PINS(104);
+DECLARE_MSM_GPIO_PINS(105);
+DECLARE_MSM_GPIO_PINS(106);
+DECLARE_MSM_GPIO_PINS(107);
+DECLARE_MSM_GPIO_PINS(108);
+DECLARE_MSM_GPIO_PINS(109);
+DECLARE_MSM_GPIO_PINS(110);
+DECLARE_MSM_GPIO_PINS(111);
+DECLARE_MSM_GPIO_PINS(112);
+DECLARE_MSM_GPIO_PINS(113);
+DECLARE_MSM_GPIO_PINS(114);
+DECLARE_MSM_GPIO_PINS(115);
+DECLARE_MSM_GPIO_PINS(116);
+DECLARE_MSM_GPIO_PINS(117);
+DECLARE_MSM_GPIO_PINS(118);
+DECLARE_MSM_GPIO_PINS(119);
+DECLARE_MSM_GPIO_PINS(120);
+DECLARE_MSM_GPIO_PINS(121);
+DECLARE_MSM_GPIO_PINS(122);
+DECLARE_MSM_GPIO_PINS(123);
+DECLARE_MSM_GPIO_PINS(124);
+DECLARE_MSM_GPIO_PINS(125);
+DECLARE_MSM_GPIO_PINS(126);
+DECLARE_MSM_GPIO_PINS(127);
+DECLARE_MSM_GPIO_PINS(128);
+DECLARE_MSM_GPIO_PINS(129);
+DECLARE_MSM_GPIO_PINS(130);
+DECLARE_MSM_GPIO_PINS(131);
+DECLARE_MSM_GPIO_PINS(132);
+DECLARE_MSM_GPIO_PINS(133);
+DECLARE_MSM_GPIO_PINS(134);
+DECLARE_MSM_GPIO_PINS(135);
+
+static const unsigned int ufs_reset_pins[] = { 136 };
+static const unsigned int sdc1_rclk_pins[] = { 137 };
+static const unsigned int sdc1_clk_pins[] = { 138 };
+static const unsigned int sdc1_cmd_pins[] = { 139 };
+static const unsigned int sdc1_data_pins[] = { 140 };
+static const unsigned int sdc2_clk_pins[] = { 141 };
+static const unsigned int sdc2_cmd_pins[] = { 142 };
+static const unsigned int sdc2_data_pins[] = { 143 };
+
+enum sm4450_functions {
+	msm_mux_gpio,
+	msm_mux_atest_char,
+	msm_mux_atest_usb0,
+	msm_mux_audio_ref_clk,
+	msm_mux_cam_mclk,
+	msm_mux_cci_async_in0,
+	msm_mux_cci_i2c,
+	msm_mux_cci,
+	msm_mux_cmu_rng,
+	msm_mux_coex_uart1_rx,
+	msm_mux_coex_uart1_tx,
+	msm_mux_cri_trng,
+	msm_mux_dbg_out_clk,
+	msm_mux_ddr_bist,
+	msm_mux_ddr_pxi0_test,
+	msm_mux_ddr_pxi1_test,
+	msm_mux_gcc_gp1_clk,
+	msm_mux_gcc_gp2_clk,
+	msm_mux_gcc_gp3_clk,
+	msm_mux_host2wlan_sol,
+	msm_mux_ibi_i3c_qup0,
+	msm_mux_ibi_i3c_qup1,
+	msm_mux_jitter_bist_ref,
+	msm_mux_mdp_vsync0_out,
+	msm_mux_mdp_vsync1_out,
+	msm_mux_mdp_vsync2_out,
+	msm_mux_mdp_vsync3_out,
+	msm_mux_mdp_vsync,
+	msm_mux_nav,
+	msm_mux_pcie0_clk_req,
+	msm_mux_phase_flag,
+	msm_mux_pll_bist_sync,
+	msm_mux_pll_clk_aux,
+	msm_mux_prng_rosc,
+	msm_mux_qdss_cti_trig0,
+	msm_mux_qdss_cti_trig1,
+	msm_mux_qdss_gpio,
+	msm_mux_qlink0_enable,
+	msm_mux_qlink0_request,
+	msm_mux_qlink0_wmss_reset,
+	msm_mux_qup0_se0,
+	msm_mux_qup0_se1,
+	msm_mux_qup0_se2,
+	msm_mux_qup0_se3,
+	msm_mux_qup0_se4,
+	msm_mux_qup1_se0,
+	msm_mux_qup1_se1,
+	msm_mux_qup1_se2,
+	msm_mux_qup1_se3,
+	msm_mux_qup1_se4,
+	msm_mux_sd_write_protect,
+	msm_mux_tb_trig_sdc1,
+	msm_mux_tb_trig_sdc2,
+	msm_mux_tgu_ch0_trigout,
+	msm_mux_tgu_ch1_trigout,
+	msm_mux_tgu_ch2_trigout,
+	msm_mux_tgu_ch3_trigout,
+	msm_mux_tmess_prng,
+	msm_mux_tsense_pwm1_out,
+	msm_mux_tsense_pwm2_out,
+	msm_mux_uim0,
+	msm_mux_uim1,
+	msm_mux_usb0_hs_ac,
+	msm_mux_usb0_phy_ps,
+	msm_mux_vfr_0_mira,
+	msm_mux_vfr_0_mirb,
+	msm_mux_vfr_1,
+	msm_mux_vsense_trigger_mirnat,
+	msm_mux_wlan1_adc_dtest0,
+	msm_mux_wlan1_adc_dtest1,
+	msm_mux__,
+};
+
+static const char * const gpio_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7",
+	"gpio8", "gpio9", "gpio10", "gpio11", "gpio12", "gpio13", "gpio14",
+	"gpio15", "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21",
+	"gpio22", "gpio23", "gpio24", "gpio25", "gpio26", "gpio27", "gpio28",
+	"gpio29", "gpio30", "gpio31", "gpio32", "gpio33", "gpio34", "gpio35",
+	"gpio36", "gpio37", "gpio38", "gpio39", "gpio40", "gpio41", "gpio42",
+	"gpio43", "gpio44", "gpio45", "gpio46", "gpio47", "gpio48", "gpio49",
+	"gpio50", "gpio51", "gpio52", "gpio53", "gpio54", "gpio55", "gpio56",
+	"gpio57", "gpio58", "gpio59", "gpio60", "gpio61", "gpio62", "gpio63",
+	"gpio64", "gpio65", "gpio66", "gpio67", "gpio68", "gpio69", "gpio70",
+	"gpio71", "gpio72", "gpio73", "gpio74", "gpio75", "gpio76", "gpio77",
+	"gpio78", "gpio79", "gpio80", "gpio81", "gpio82", "gpio83", "gpio84",
+	"gpio85", "gpio86", "gpio87", "gpio88", "gpio89", "gpio90", "gpio91",
+	"gpio92", "gpio93", "gpio94", "gpio95", "gpio96", "gpio97", "gpio98",
+	"gpio99", "gpio100", "gpio101", "gpio102", "gpio103", "gpio104",
+	"gpio105", "gpio106", "gpio107", "gpio108", "gpio109", "gpio110",
+	"gpio111", "gpio112", "gpio113", "gpio114", "gpio115", "gpio116",
+	"gpio117", "gpio118", "gpio119", "gpio120", "gpio121", "gpio122",
+	"gpio123", "gpio124", "gpio125", "gpio126", "gpio127", "gpio128",
+	"gpio129", "gpio130", "gpio131", "gpio132", "gpio133", "gpio134",
+	"gpio135",
+};
+static const char * const atest_char_groups[] = {
+	"gpio95", "gpio97", "gpio98", "gpio99", "gpio100",
+};
+static const char * const atest_usb0_groups[] = {
+	"gpio75", "gpio10", "gpio78", "gpio79", "gpio80",
+};
+static const char * const audio_ref_clk_groups[] = {
+	"gpio71",
+};
+static const char * const cam_mclk_groups[] = {
+	"gpio36", "gpio37", "gpio38", "gpio39",
+};
+static const char * const cci_async_in0_groups[] = {
+	"gpio40",
+};
+static const char * const cci_i2c_groups[] = {
+	"gpio45", "gpio47", "gpio49", "gpio44",
+	"gpio46", "gpio48",
+};
+static const char * const cci_groups[] = {
+	"gpio40", "gpio41", "gpio42", "gpio43",
+};
+static const char * const cmu_rng_groups[] = {
+	"gpio28", "gpio3", "gpio1", "gpio0",
+};
+static const char * const coex_uart1_rx_groups[] = {
+	"gpio54",
+};
+static const char * const coex_uart1_tx_groups[] = {
+	"gpio55",
+};
+static const char * const cri_trng_groups[] = {
+	"gpio42", "gpio40", "gpio41",
+};
+static const char * const dbg_out_clk_groups[] = {
+	"gpio80",
+};
+static const char * const ddr_bist_groups[] = {
+	"gpio32", "gpio29", "gpio30", "gpio31",
+};
+static const char * const ddr_pxi0_test_groups[] = {
+	"gpio90", "gpio127",
+};
+static const char * const ddr_pxi1_test_groups[] = {
+	"gpio118", "gpio122",
+};
+static const char * const gcc_gp1_clk_groups[] = {
+	"gpio37", "gpio48",
+};
+static const char * const gcc_gp2_clk_groups[] = {
+	"gpio30", "gpio49",
+};
+static const char * const gcc_gp3_clk_groups[] = {
+	"gpio3", "gpio50",
+};
+static const char * const host2wlan_sol_groups[] = {
+	"gpio106",
+};
+static const char * const ibi_i3c_qup0_groups[] = {
+	"gpio4", "gpio5",
+};
+static const char * const ibi_i3c_qup1_groups[] = {
+	"gpio0", "gpio1",
+};
+static const char * const jitter_bist_ref_groups[] = {
+	"gpio90",
+};
+static const char * const mdp_vsync0_out_groups[] = {
+	"gpio93",
+};
+static const char * const mdp_vsync1_out_groups[] = {
+	"gpio93",
+};
+static const char * const mdp_vsync2_out_groups[] = {
+	"gpio22",
+};
+static const char * const mdp_vsync3_out_groups[] = {
+	"gpio22",
+};
+static const char * const mdp_vsync_groups[] = {
+	"gpio26", "gpio22", "gpio30", "gpio34", "gpio93", "gpio97",
+};
+static const char * const nav_groups[] = {
+	"gpio81", "gpio83", "gpio84",
+};
+static const char * const pcie0_clk_req_groups[] = {
+	"gpio107",
+};
+static const char * const phase_flag_groups[] = {
+	"gpio7", "gpio8", "gpio9", "gpio11", "gpio13", "gpio14", "gpio15",
+	"gpio17", "gpio18", "gpio19", "gpio21", "gpio24", "gpio25", "gpio31",
+	"gpio32", "gpio33", "gpio35", "gpio61", "gpio72", "gpio82", "gpio91",
+	"gpio95", "gpio97", "gpio98", "gpio99", "gpio100", "gpio105", "gpio115",
+	"gpio116", "gpio117", "gpio133", "gpio135",
+};
+static const char * const pll_bist_sync_groups[] = {
+	"gpio73",
+};
+static const char * const pll_clk_aux_groups[] = {
+	"gpio108",
+};
+static const char * const prng_rosc_groups[] = {
+	"gpio36", "gpio37", "gpio38", "gpio39",
+};
+static const char * const qdss_cti_trig0_groups[] = {
+	"gpio26", "gpio60", "gpio113", "gpio114",
+};
+static const char * const qdss_cti_trig1_groups[] = {
+	"gpio6", "gpio27", "gpio57", "gpio58",
+};
+static const char * const qdss_gpio_groups[] = {
+	"gpio0", "gpio1", "gpio3", "gpio4", "gpio5", "gpio7", "gpio8",
+	"gpio9", "gpio14", "gpio15", "gpio17", "gpio23", "gpio31", "gpio32",
+	"gpio33", "gpio35", "gpio36", "gpio37", "gpio38", "gpio39", "gpio40",
+	"gpio41", "gpio42", "gpio43", "gpio44", "gpio45", "gpio46", "gpio47",
+	"gpio49",  "gpio59", "gpio62", "gpio118", "gpio121", "gpio122", "gpio126",
+	"gpio127",
+};
+static const char * const qlink0_enable_groups[] = {
+	"gpio88",
+};
+static const char * const qlink0_request_groups[] = {
+	"gpio87",
+};
+static const char * const qlink0_wmss_reset_groups[] = {
+	"gpio89",
+};
+static const char * const qup0_se0_groups[] = {
+	"gpio4", "gpio5", "gpio34", "gpio35",
+};
+static const char * const qup0_se1_groups[] = {
+	"gpio10", "gpio11", "gpio12", "gpio13",
+};
+static const char * const qup0_se2_groups[] = {
+	"gpio14", "gpio15", "gpio16", "gpio17",
+};
+static const char * const qup0_se3_groups[] = {
+	"gpio18", "gpio19", "gpio20", "gpio21",
+};
+static const char * const qup0_se4_groups[] = {
+	"gpio6", "gpio7", "gpio8", "gpio9",
+	"gpio26", "gpio27", "gpio34",
+};
+static const char * const qup1_se0_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3",
+};
+static const char * const qup1_se1_groups[] = {
+	"gpio26", "gpio27", "gpio50", "gpio51",
+};
+static const char * const qup1_se2_groups[] = {
+	"gpio22", "gpio23", "gpio31", "gpio32",
+};
+static const char * const qup1_se3_groups[] = {
+	"gpio24", "gpio25", "gpio51", "gpio50",
+};
+static const char * const qup1_se4_groups[] = {
+	"gpio43", "gpio48", "gpio49", "gpio90",
+	"gpio91",
+};
+static const char * const sd_write_protect_groups[] = {
+	"gpio102",
+};
+static const char * const tb_trig_sdc1_groups[] = {
+	"gpio128",
+};
+static const char * const tb_trig_sdc2_groups[] = {
+	"gpio51",
+};
+static const char * const tgu_ch0_trigout_groups[] = {
+	"gpio20",
+};
+static const char * const tgu_ch1_trigout_groups[] = {
+	"gpio21",
+};
+static const char * const tgu_ch2_trigout_groups[] = {
+	"gpio22",
+};
+static const char * const tgu_ch3_trigout_groups[] = {
+	"gpio23",
+};
+static const char * const tmess_prng_groups[] = {
+	"gpio57", "gpio58", "gpio59", "gpio60",
+};
+static const char * const tsense_pwm1_out_groups[] = {
+	"gpio134",
+};
+static const char * const tsense_pwm2_out_groups[] = {
+	"gpio134",
+};
+static const char * const uim0_groups[] = {
+	"gpio64", "gpio63", "gpio66", "gpio65",
+};
+static const char * const uim1_groups[] = {
+	"gpio68", "gpio67", "gpio69", "gpio70",
+};
+static const char * const usb0_hs_ac_groups[] = {
+	"gpio99",
+};
+static const char * const usb0_phy_ps_groups[] = {
+	"gpio94",
+};
+static const char * const vfr_0_mira_groups[] = {
+	"gpio19",
+};
+static const char * const vfr_0_mirb_groups[] = {
+	"gpio100",
+};
+static const char * const vfr_1_groups[] = {
+	"gpio84",
+};
+static const char * const vsense_trigger_mirnat_groups[] = {
+	"gpio75",
+};
+static const char * const wlan1_adc_dtest0_groups[] = {
+	"gpio79",
+};
+static const char * const wlan1_adc_dtest1_groups[] = {
+	"gpio80",
+};
+
+static const struct pinfunction sm4450_functions[] = {
+	MSM_PIN_FUNCTION(gpio),
+	MSM_PIN_FUNCTION(atest_char),
+	MSM_PIN_FUNCTION(atest_usb0),
+	MSM_PIN_FUNCTION(audio_ref_clk),
+	MSM_PIN_FUNCTION(cam_mclk),
+	MSM_PIN_FUNCTION(cci_async_in0),
+	MSM_PIN_FUNCTION(cci_i2c),
+	MSM_PIN_FUNCTION(cci),
+	MSM_PIN_FUNCTION(cmu_rng),
+	MSM_PIN_FUNCTION(coex_uart1_rx),
+	MSM_PIN_FUNCTION(coex_uart1_tx),
+	MSM_PIN_FUNCTION(cri_trng),
+	MSM_PIN_FUNCTION(dbg_out_clk),
+	MSM_PIN_FUNCTION(ddr_bist),
+	MSM_PIN_FUNCTION(ddr_pxi0_test),
+	MSM_PIN_FUNCTION(ddr_pxi1_test),
+	MSM_PIN_FUNCTION(gcc_gp1_clk),
+	MSM_PIN_FUNCTION(gcc_gp2_clk),
+	MSM_PIN_FUNCTION(gcc_gp3_clk),
+	MSM_PIN_FUNCTION(host2wlan_sol),
+	MSM_PIN_FUNCTION(ibi_i3c_qup0),
+	MSM_PIN_FUNCTION(ibi_i3c_qup1),
+	MSM_PIN_FUNCTION(jitter_bist_ref),
+	MSM_PIN_FUNCTION(mdp_vsync0_out),
+	MSM_PIN_FUNCTION(mdp_vsync1_out),
+	MSM_PIN_FUNCTION(mdp_vsync2_out),
+	MSM_PIN_FUNCTION(mdp_vsync3_out),
+	MSM_PIN_FUNCTION(mdp_vsync),
+	MSM_PIN_FUNCTION(nav),
+	MSM_PIN_FUNCTION(pcie0_clk_req),
+	MSM_PIN_FUNCTION(phase_flag),
+	MSM_PIN_FUNCTION(pll_bist_sync),
+	MSM_PIN_FUNCTION(pll_clk_aux),
+	MSM_PIN_FUNCTION(prng_rosc),
+	MSM_PIN_FUNCTION(qdss_cti_trig0),
+	MSM_PIN_FUNCTION(qdss_cti_trig1),
+	MSM_PIN_FUNCTION(qdss_gpio),
+	MSM_PIN_FUNCTION(qlink0_enable),
+	MSM_PIN_FUNCTION(qlink0_request),
+	MSM_PIN_FUNCTION(qlink0_wmss_reset),
+	MSM_PIN_FUNCTION(qup0_se0),
+	MSM_PIN_FUNCTION(qup0_se1),
+	MSM_PIN_FUNCTION(qup0_se2),
+	MSM_PIN_FUNCTION(qup0_se3),
+	MSM_PIN_FUNCTION(qup0_se4),
+	MSM_PIN_FUNCTION(qup1_se0),
+	MSM_PIN_FUNCTION(qup1_se1),
+	MSM_PIN_FUNCTION(qup1_se2),
+	MSM_PIN_FUNCTION(qup1_se3),
+	MSM_PIN_FUNCTION(qup1_se4),
+	MSM_PIN_FUNCTION(sd_write_protect),
+	MSM_PIN_FUNCTION(tb_trig_sdc1),
+	MSM_PIN_FUNCTION(tb_trig_sdc2),
+	MSM_PIN_FUNCTION(tgu_ch0_trigout),
+	MSM_PIN_FUNCTION(tgu_ch1_trigout),
+	MSM_PIN_FUNCTION(tgu_ch2_trigout),
+	MSM_PIN_FUNCTION(tgu_ch3_trigout),
+	MSM_PIN_FUNCTION(tmess_prng),
+	MSM_PIN_FUNCTION(tsense_pwm1_out),
+	MSM_PIN_FUNCTION(tsense_pwm2_out),
+	MSM_PIN_FUNCTION(uim0),
+	MSM_PIN_FUNCTION(uim1),
+	MSM_PIN_FUNCTION(usb0_hs_ac),
+	MSM_PIN_FUNCTION(usb0_phy_ps),
+	MSM_PIN_FUNCTION(vfr_0_mira),
+	MSM_PIN_FUNCTION(vfr_0_mirb),
+	MSM_PIN_FUNCTION(vfr_1),
+	MSM_PIN_FUNCTION(vsense_trigger_mirnat),
+	MSM_PIN_FUNCTION(wlan1_adc_dtest0),
+	MSM_PIN_FUNCTION(wlan1_adc_dtest1),
+};
+
+/*
+ * Every pin is maintained as a single group, and missing or non-existing pin
+ * would be maintained as dummy group to synchronize pin group index with
+ * pin descriptor registered with pinctrl core.
+ * Clients would not be able to request these dummy pin groups.
+ */
+static const struct msm_pingroup sm4450_groups[] = {
+	[0] = PINGROUP(0, qup1_se0, ibi_i3c_qup1, cmu_rng, qdss_gpio, _, _, _, _, _),
+	[1] = PINGROUP(1, qup1_se0, ibi_i3c_qup1, cmu_rng, qdss_gpio, _, _, _, _, _),
+	[2] = PINGROUP(2, qup1_se0, _, _, _, _, _, _, _, _),
+	[3] = PINGROUP(3, qup1_se0, gcc_gp3_clk, cmu_rng, qdss_gpio, _, _, _, _, _),
+	[4] = PINGROUP(4, qup0_se0, ibi_i3c_qup0, qdss_gpio, _, _, _, _, _, _),
+	[5] = PINGROUP(5, qup0_se0, ibi_i3c_qup0, qdss_gpio, _, _, _, _, _, _),
+	[6] = PINGROUP(6, qup0_se4, qdss_cti_trig1, _, _, _, _, _, _, _),
+	[7] = PINGROUP(7, qup0_se4, _, phase_flag, qdss_gpio, _, _, _, _, _),
+	[8] = PINGROUP(8, qup0_se4, _, phase_flag, qdss_gpio, _, _, _, _, _),
+	[9] = PINGROUP(9, qup0_se4, _, phase_flag, qdss_gpio, _, _, _, _, _),
+	[10] = PINGROUP(10, qup0_se1, _, atest_usb0, _, _, _, _, _, _),
+	[11] = PINGROUP(11, qup0_se1, _, phase_flag, _, _, _, _, _, _),
+	[12] = PINGROUP(12, qup0_se1, _, _, _, _, _, _, _, _),
+	[13] = PINGROUP(13, qup0_se1, _, phase_flag, _, _, _, _, _, _),
+	[14] = PINGROUP(14, qup0_se2, _, phase_flag, _, qdss_gpio, _, _, _, _),
+	[15] = PINGROUP(15, qup0_se2, _, phase_flag, _, qdss_gpio, _, _, _, _),
+	[16] = PINGROUP(16, qup0_se2, _, _, _, _, _, _, _, _),
+	[17] = PINGROUP(17, qup0_se2, _, phase_flag, _, qdss_gpio, _, _, _, _),
+	[18] = PINGROUP(18, qup0_se3, _, phase_flag, _, _, _, _, _, _),
+	[19] = PINGROUP(19, qup0_se3, vfr_0_mira, _, phase_flag, _, _, _, _, _),
+	[20] = PINGROUP(20, qup0_se3, tgu_ch0_trigout, _, _, _, _, _, _, _),
+	[21] = PINGROUP(21, qup0_se3, _, phase_flag, tgu_ch1_trigout, _, _, _, _, _),
+	[22] = PINGROUP(22, qup1_se2, mdp_vsync, mdp_vsync2_out, mdp_vsync3_out, tgu_ch2_trigout, _, _, _, _),
+	[23] = PINGROUP(23, qup1_se2, tgu_ch3_trigout, qdss_gpio, _, _, _, _, _, _),
+	[24] = PINGROUP(24, qup1_se3, _, phase_flag, _, _, _, _, _, _),
+	[25] = PINGROUP(25, qup1_se3, _, phase_flag, _, _, _, _, _, _),
+	[26] = PINGROUP(26, qup1_se1, mdp_vsync, qup0_se4, qdss_cti_trig0, _, _, _, _, _),
+	[27] = PINGROUP(27, qup1_se1, qup0_se4, qdss_cti_trig1, _, _, _, _, _, _),
+	[28] = PINGROUP(28, cmu_rng, _, _, _, _, _, _, _, _),
+	[29] = PINGROUP(29, ddr_bist, _, _, _, _, _, _, _, _),
+	[30] = PINGROUP(30, mdp_vsync, gcc_gp2_clk, ddr_bist, _, _, _, _, _, _),
+	[31] = PINGROUP(31, qup1_se2, _, phase_flag, ddr_bist, qdss_gpio, _, _, _, _),
+	[32] = PINGROUP(32, qup1_se2, _, phase_flag, ddr_bist, qdss_gpio, _, _, _, _),
+	[33] = PINGROUP(33, _, phase_flag, qdss_gpio, _, _, _, _, _, _),
+	[34] = PINGROUP(34, qup0_se0, qup0_se4, mdp_vsync, _, _, _, _, _, _),
+	[35] = PINGROUP(35, qup0_se0, _, phase_flag, qdss_gpio, _, _, _, _, _),
+	[36] = PINGROUP(36, cam_mclk, prng_rosc, qdss_gpio, _, _, _, _, _, _),
+	[37] = PINGROUP(37, cam_mclk, gcc_gp1_clk, prng_rosc, qdss_gpio, _, _, _, _, _),
+	[38] = PINGROUP(38, cam_mclk, prng_rosc, qdss_gpio, _, _, _, _, _, _),
+	[39] = PINGROUP(39, cam_mclk, prng_rosc, qdss_gpio, _, _, _, _, _, _),
+	[40] = PINGROUP(40, cci, cci_async_in0, cri_trng, qdss_gpio, _, _, _, _, _),
+	[41] = PINGROUP(41, cci, cri_trng, qdss_gpio, _, _, _, _, _, _),
+	[42] = PINGROUP(42, cci, cri_trng, qdss_gpio, _, _, _, _, _, _),
+	[43] = PINGROUP(43, cci, qup1_se4, qdss_gpio, _, _, _, _, _, _),
+	[44] = PINGROUP(44, cci_i2c, qdss_gpio, _, _, _, _, _, _, _),
+	[45] = PINGROUP(45, cci_i2c, qdss_gpio, _, _, _, _, _, _, _),
+	[46] = PINGROUP(46, cci_i2c, qdss_gpio, _, _, _, _, _, _, _),
+	[47] = PINGROUP(47, cci_i2c, qdss_gpio, _, _, _, _, _, _, _),
+	[48] = PINGROUP(48, cci_i2c, qup1_se4, gcc_gp1_clk, _, _, _, _, _, _),
+	[49] = PINGROUP(49, cci_i2c, qup1_se4, gcc_gp2_clk, qdss_gpio, _, _, _, _, _),
+	[50] = PINGROUP(50, qup1_se1, qup1_se3, _, gcc_gp3_clk, _, _, _, _, _),
+	[51] = PINGROUP(51, qup1_se1, qup1_se3, _, tb_trig_sdc2, _, _, _, _, _),
+	[52] = PINGROUP(52, _, _, _, _, _, _, _, _, _),
+	[53] = PINGROUP(53, _, _, _, _, _, _, _, _, _),
+	[54] = PINGROUP(54, coex_uart1_rx, _, _, _, _, _, _, _, _),
+	[55] = PINGROUP(55, coex_uart1_tx, _, _, _, _, _, _, _, _),
+	[56] = PINGROUP(56, _, _, _, _, _, _, _, _, _),
+	[57] = PINGROUP(57, tmess_prng, qdss_cti_trig1, _, _, _, _, _, _, _),
+	[58] = PINGROUP(58, tmess_prng, qdss_cti_trig1, _, _, _, _, _, _, _),
+	[59] = PINGROUP(59, tmess_prng, qdss_gpio, _, _, _, _, _, _, _),
+	[60] = PINGROUP(60, tmess_prng, qdss_cti_trig0, _, _, _, _, _, _, _),
+	[61] = PINGROUP(61, _, phase_flag, _, _, _, _, _, _, _),
+	[62] = PINGROUP(62, qdss_gpio, _, _, _, _, _, _, _, _),
+	[63] = PINGROUP(63, uim0, _, _, _, _, _, _, _, _),
+	[64] = PINGROUP(64, uim0, _, _, _, _, _, _, _, _),
+	[65] = PINGROUP(65, uim0, _, _, _, _, _, _, _, _),
+	[66] = PINGROUP(66, uim0, _, _, _, _, _, _, _, _),
+	[67] = PINGROUP(67, uim1, _, _, _, _, _, _, _, _),
+	[68] = PINGROUP(68, uim1, _, _, _, _, _, _, _, _),
+	[69] = PINGROUP(69, uim1, _, _, _, _, _, _, _, _),
+	[70] = PINGROUP(70, uim1, _, _, _, _, _, _, _, _),
+	[71] = PINGROUP(71, _, _, _, audio_ref_clk, _, _, _, _, _),
+	[72] = PINGROUP(72, _, _, _, phase_flag, _, _, _, _, _),
+	[73] = PINGROUP(73, _, _, _, pll_bist_sync, _, _, _, _, _),
+	[74] = PINGROUP(74, _, _, _, _, _, _, _, _, _),
+	[75] = PINGROUP(75, _, _, _, vsense_trigger_mirnat, atest_usb0, _, _, _, _),
+	[76] = PINGROUP(76, _, _, _, _, _, _, _, _, _),
+	[77] = PINGROUP(77, _, _, _, _, _, _, _, _, _),
+	[78] = PINGROUP(78, _, _, _, atest_usb0, _, _, _, _, _),
+	[79] = PINGROUP(79, _, _, _, wlan1_adc_dtest0, atest_usb0, _, _, _, _),
+	[80] = PINGROUP(80, _, _, dbg_out_clk, wlan1_adc_dtest1, atest_usb0, _, _, _, _),
+	[81] = PINGROUP(81, _, nav, _, _, _, _, _, _, _),
+	[82] = PINGROUP(82, _, _, phase_flag, _, _, _, _, _, _),
+	[83] = PINGROUP(83, nav, _, _, _, _, _, _, _, _),
+	[84] = PINGROUP(84, nav, vfr_1, _, _, _, _, _, _, _),
+	[85] = PINGROUP(85, _, _, _, _, _, _, _, _, _),
+	[86] = PINGROUP(86, _, _, _, _, _, _, _, _, _),
+	[87] = PINGROUP(87, qlink0_request, _, _, _, _, _, _, _, _),
+	[88] = PINGROUP(88, qlink0_enable, _, _, _, _, _, _, _, _),
+	[89] = PINGROUP(89, qlink0_wmss_reset, _, _, _, _, _, _, _, _),
+	[90] = PINGROUP(90, qup1_se4, jitter_bist_ref, ddr_pxi0_test, _, _, _, _, _, _),
+	[91] = PINGROUP(91, qup1_se4, _, phase_flag, _, _, _, _, _, _),
+	[92] = PINGROUP(92, _, _, _, _, _, _, _, _, _),
+	[93] = PINGROUP(93, mdp_vsync, mdp_vsync0_out, mdp_vsync1_out, _, _, _, _, _, _),
+	[94] = PINGROUP(94, usb0_phy_ps, _, _, _, _, _, _, _, _),
+	[95] = PINGROUP(95, _, phase_flag, atest_char, _, _, _, _, _, _),
+	[96] = PINGROUP(96, _, _, _, _, _, _, _, _, _),
+	[97] = PINGROUP(97, mdp_vsync, _, phase_flag, atest_char, _, _, _, _, _),
+	[98] = PINGROUP(98, _, phase_flag, atest_char, _, _, _, _, _, _),
+	[99] = PINGROUP(99, usb0_hs_ac, _, phase_flag, atest_char, _, _, _, _, _),
+	[100] = PINGROUP(100, vfr_0_mirb, _, phase_flag, atest_char, _, _, _, _, _),
+	[101] = PINGROUP(101, _, _, _, _, _, _, _, _, _),
+	[102] = PINGROUP(102, sd_write_protect, _, _, _, _, _, _, _, _),
+	[103] = PINGROUP(103, _, _, _, _, _, _, _, _, _),
+	[104] = PINGROUP(104, _, _, _, _, _, _, _, _, _),
+	[105] = PINGROUP(105, _, phase_flag, _, _, _, _, _, _, _),
+	[106] = PINGROUP(106, host2wlan_sol, _, _, _, _, _, _, _, _),
+	[107] = PINGROUP(107, pcie0_clk_req, _, _, _, _, _, _, _, _),
+	[108] = PINGROUP(108, pll_clk_aux, _, _, _, _, _, _, _, _),
+	[109] = PINGROUP(109, _, _, _, _, _, _, _, _, _),
+	[110] = PINGROUP(110, _, _, _, _, _, _, _, _, _),
+	[111] = PINGROUP(111, _, _, _, _, _, _, _, _, _),
+	[112] = PINGROUP(112, _, _, _, _, _, _, _, _, _),
+	[113] = PINGROUP(113, qdss_cti_trig0, _, _, _, _, _, _, _, _),
+	[114] = PINGROUP(114, qdss_cti_trig0, _, _, _, _, _, _, _, _),
+	[115] = PINGROUP(115, _, phase_flag, _, _, _, _, _, _, _),
+	[116] = PINGROUP(116, _, phase_flag, _, _, _, _, _, _, _),
+	[117] = PINGROUP(117, _, phase_flag, _, _, _, _, _, _, _),
+	[118] = PINGROUP(118, qdss_gpio, _, ddr_pxi1_test, _, _, _, _, _, _),
+	[119] = PINGROUP(119, _, _, _, _, _, _, _, _, _),
+	[120] = PINGROUP(120, _, _, _, _, _, _, _, _, _),
+	[121] = PINGROUP(121, qdss_gpio, _, _, _, _, _, _, _, _),
+	[122] = PINGROUP(122, qdss_gpio, _, ddr_pxi1_test, _, _, _, _, _, _),
+	[123] = PINGROUP(123, _, _, _, _, _, _, _, _, _),
+	[124] = PINGROUP(124, _, _, _, _, _, _, _, _, _),
+	[125] = PINGROUP(125, _, _, _, _, _, _, _, _, _),
+	[126] = PINGROUP(126, qdss_gpio, _, _, _, _, _, _, _, _),
+	[127] = PINGROUP(127, qdss_gpio, ddr_pxi0_test, _, _, _, _, _, _, _),
+	[128] = PINGROUP(128, tb_trig_sdc1, _, _, _, _, _, _, _, _),
+	[129] = PINGROUP(129, _, _, _, _, _, _, _, _, _),
+	[130] = PINGROUP(130, _, _, _, _, _, _, _, _, _),
+	[131] = PINGROUP(131, _, _, _, _, _, _, _, _, _),
+	[132] = PINGROUP(132, _, _, _, _, _, _, _, _, _),
+	[133] = PINGROUP(133, _, phase_flag, _, _, _, _, _, _, _),
+	[134] = PINGROUP(134, tsense_pwm1_out, tsense_pwm2_out, _, _, _, _, _, _, _),
+	[135] = PINGROUP(135, _, phase_flag, _, _, _, _, _, _, _),
+	[136] = UFS_RESET(ufs_reset, 0x97000),
+	[137] = SDC_QDSD_PINGROUP(sdc1_rclk, 0x8c004, 0, 0),
+	[138] = SDC_QDSD_PINGROUP(sdc1_clk, 0x8c000, 13, 6),
+	[139] = SDC_QDSD_PINGROUP(sdc1_cmd, 0x8c000, 11, 3),
+	[140] = SDC_QDSD_PINGROUP(sdc1_data, 0x8c000, 9, 0),
+	[141] = SDC_QDSD_PINGROUP(sdc2_clk, 0x8f000, 14, 6),
+	[142] = SDC_QDSD_PINGROUP(sdc2_cmd, 0x8f000, 11, 3),
+	[143] = SDC_QDSD_PINGROUP(sdc2_data, 0x8f000, 9, 0),
+};
+
+static const struct msm_gpio_wakeirq_map sm4450_pdc_map[] = {
+	{ 0, 67 }, { 3, 82 }, { 4, 69 }, { 5, 70 }, { 6, 44 }, { 7, 43 },
+	{ 8, 71 }, { 9, 86 }, { 10, 48 }, { 11, 77 }, { 12, 90 },
+	{ 13, 54 }, { 14, 91 }, { 17, 97 }, { 18, 102 }, { 21, 103 },
+	{ 22, 104 }, { 23, 105 }, { 24, 53 }, { 25, 106 }, { 26, 65 },
+	{ 27, 55 }, { 28, 89 }, { 30, 80 }, { 31, 109 }, { 33, 87 },
+	{ 34, 81 }, { 35, 75 }, { 40, 88 }, { 41, 98 }, { 42, 110 },
+	{ 43, 95 }, { 47, 118 }, { 50, 111 }, { 52, 52 }, { 53, 114 },
+	{ 54, 115 }, { 55, 99 }, { 56, 45 }, { 57, 85 }, { 58, 56 },
+	{ 59, 84 }, { 60, 83 }, { 61, 96 }, { 62, 93 }, { 66, 116 },
+	{ 67, 113 }, { 70, 42 }, { 71, 122 }, { 73, 119 }, { 75, 121 },
+	{ 77, 120 }, { 79, 123 }, { 81, 124 }, { 83, 64 }, { 84, 128 },
+	{ 86, 129 }, { 87, 63 }, { 91, 92 }, { 92, 66 }, { 93, 125 },
+	{ 94, 76 }, { 95, 62 }, { 96, 132 }, { 97, 135 }, { 98, 73 },
+	{ 99, 133 }, { 101, 46 }, { 102, 134 }, { 103, 49 }, { 105, 58 },
+	{ 107, 94 }, { 110, 59 }, { 113, 57 }, { 114, 60 }, { 118, 107 },
+	{ 120, 61 }, { 121, 108 }, { 123, 68 }, { 125, 72 }, { 128, 112 },
+};
+
+static const struct msm_pinctrl_soc_data sm4450_tlmm = {
+	.pins = sm4450_pins,
+	.npins = ARRAY_SIZE(sm4450_pins),
+	.functions = sm4450_functions,
+	.nfunctions = ARRAY_SIZE(sm4450_functions),
+	.groups = sm4450_groups,
+	.ngroups = ARRAY_SIZE(sm4450_groups),
+	.ngpios = 137,
+	.wakeirq_map = sm4450_pdc_map,
+	.nwakeirq_map = ARRAY_SIZE(sm4450_pdc_map),
+};
+
+static int sm4450_tlmm_probe(struct platform_device *pdev)
+{
+	return msm_pinctrl_probe(pdev, &sm4450_tlmm);
+}
+
+static const struct of_device_id sm4450_tlmm_of_match[] = {
+	{ .compatible = "qcom,sm4450-tlmm", },
+	{ }
+};
+
+static struct platform_driver sm4450_tlmm_driver = {
+	.driver = {
+		.name = "sm4450-tlmm",
+		.of_match_table = sm4450_tlmm_of_match,
+	},
+	.probe = sm4450_tlmm_probe,
+	.remove_new = msm_pinctrl_remove,
+};
+MODULE_DEVICE_TABLE(of, sm4450_tlmm_of_match);
+
+static int __init sm4450_tlmm_init(void)
+{
+	return platform_driver_register(&sm4450_tlmm_driver);
+}
+arch_initcall(sm4450_tlmm_init);
+
+static void __exit sm4450_tlmm_exit(void)
+{
+	platform_driver_unregister(&sm4450_tlmm_driver);
+}
+module_exit(sm4450_tlmm_exit);
+
+MODULE_DESCRIPTION("QTI SM4450 TLMM driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/pinctrl/qcom/pinctrl-sm6115-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm6115-lpass-lpi.c
index e8a6f6f6af54..316d6fc69131 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm6115-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm6115-lpass-lpi.c
@@ -36,26 +36,6 @@ enum lpass_lpi_functions {
 	LPI_MUX__,
 };
 
-static int gpio0_pins[] = { 0 };
-static int gpio1_pins[] = { 1 };
-static int gpio2_pins[] = { 2 };
-static int gpio3_pins[] = { 3 };
-static int gpio4_pins[] = { 4 };
-static int gpio5_pins[] = { 5 };
-static int gpio6_pins[] = { 6 };
-static int gpio7_pins[] = { 7 };
-static int gpio8_pins[] = { 8 };
-static int gpio9_pins[] = { 9 };
-static int gpio10_pins[] = { 10 };
-static int gpio11_pins[] = { 11 };
-static int gpio12_pins[] = { 12 };
-static int gpio13_pins[] = { 13 };
-static int gpio14_pins[] = { 14 };
-static int gpio15_pins[] = { 15 };
-static int gpio16_pins[] = { 16 };
-static int gpio17_pins[] = { 17 };
-static int gpio18_pins[] = { 18 };
-
 static const struct pinctrl_pin_desc sm6115_lpi_pins[] = {
 	PINCTRL_PIN(0, "gpio0"),
 	PINCTRL_PIN(1, "gpio1"),
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8250-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm8250-lpass-lpi.c
index cb10ce8d5d28..9791d9ba5087 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8250-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8250-lpass-lpi.c
@@ -36,21 +36,6 @@ enum lpass_lpi_functions {
 	LPI_MUX__,
 };
 
-static int gpio0_pins[] = { 0 };
-static int gpio1_pins[] = { 1 };
-static int gpio2_pins[] = { 2 };
-static int gpio3_pins[] = { 3 };
-static int gpio4_pins[] = { 4 };
-static int gpio5_pins[] = { 5 };
-static int gpio6_pins[] = { 6 };
-static int gpio7_pins[] = { 7 };
-static int gpio8_pins[] = { 8 };
-static int gpio9_pins[] = { 9 };
-static int gpio10_pins[] = { 10 };
-static int gpio11_pins[] = { 11 };
-static int gpio12_pins[] = { 12 };
-static int gpio13_pins[] = { 13 };
-
 static const struct pinctrl_pin_desc sm8250_lpi_pins[] = {
 	PINCTRL_PIN(0, "gpio0"),
 	PINCTRL_PIN(1, "gpio1"),
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8350-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm8350-lpass-lpi.c
index 297cc95ac3c0..5b9a2cb216bd 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8350-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8350-lpass-lpi.c
@@ -36,22 +36,6 @@ enum lpass_lpi_functions {
 	LPI_MUX__,
 };
 
-static int gpio0_pins[] = { 0 };
-static int gpio1_pins[] = { 1 };
-static int gpio2_pins[] = { 2 };
-static int gpio3_pins[] = { 3 };
-static int gpio4_pins[] = { 4 };
-static int gpio5_pins[] = { 5 };
-static int gpio6_pins[] = { 6 };
-static int gpio7_pins[] = { 7 };
-static int gpio8_pins[] = { 8 };
-static int gpio9_pins[] = { 9 };
-static int gpio10_pins[] = { 10 };
-static int gpio11_pins[] = { 11 };
-static int gpio12_pins[] = { 12 };
-static int gpio13_pins[] = { 13 };
-static int gpio14_pins[] = { 14 };
-
 static const struct pinctrl_pin_desc sm8350_lpi_pins[] = {
 	PINCTRL_PIN(0, "gpio0"),
 	PINCTRL_PIN(1, "gpio1"),
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8450-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm8450-lpass-lpi.c
index 2e7896791fc0..a028cbb49947 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8450-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8450-lpass-lpi.c
@@ -52,30 +52,6 @@ enum lpass_lpi_functions {
 	LPI_MUX__,
 };
 
-static int gpio0_pins[] = { 0 };
-static int gpio1_pins[] = { 1 };
-static int gpio2_pins[] = { 2 };
-static int gpio3_pins[] = { 3 };
-static int gpio4_pins[] = { 4 };
-static int gpio5_pins[] = { 5 };
-static int gpio6_pins[] = { 6 };
-static int gpio7_pins[] = { 7 };
-static int gpio8_pins[] = { 8 };
-static int gpio9_pins[] = { 9 };
-static int gpio10_pins[] = { 10 };
-static int gpio11_pins[] = { 11 };
-static int gpio12_pins[] = { 12 };
-static int gpio13_pins[] = { 13 };
-static int gpio14_pins[] = { 14 };
-static int gpio15_pins[] = { 15 };
-static int gpio16_pins[] = { 16 };
-static int gpio17_pins[] = { 17 };
-static int gpio18_pins[] = { 18 };
-static int gpio19_pins[] = { 19 };
-static int gpio20_pins[] = { 20 };
-static int gpio21_pins[] = { 21 };
-static int gpio22_pins[] = { 22 };
-
 static const struct pinctrl_pin_desc sm8450_lpi_pins[] = {
 	PINCTRL_PIN(0, "gpio0"),
 	PINCTRL_PIN(1, "gpio1"),
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8550-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm8550-lpass-lpi.c
index 64458c3fbe5e..852192b044e1 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8550-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8550-lpass-lpi.c
@@ -52,30 +52,6 @@ enum lpass_lpi_functions {
 	LPI_MUX__,
 };
 
-static int gpio0_pins[] = { 0 };
-static int gpio1_pins[] = { 1 };
-static int gpio2_pins[] = { 2 };
-static int gpio3_pins[] = { 3 };
-static int gpio4_pins[] = { 4 };
-static int gpio5_pins[] = { 5 };
-static int gpio6_pins[] = { 6 };
-static int gpio7_pins[] = { 7 };
-static int gpio8_pins[] = { 8 };
-static int gpio9_pins[] = { 9 };
-static int gpio10_pins[] = { 10 };
-static int gpio11_pins[] = { 11 };
-static int gpio12_pins[] = { 12 };
-static int gpio13_pins[] = { 13 };
-static int gpio14_pins[] = { 14 };
-static int gpio15_pins[] = { 15 };
-static int gpio16_pins[] = { 16 };
-static int gpio17_pins[] = { 17 };
-static int gpio18_pins[] = { 18 };
-static int gpio19_pins[] = { 19 };
-static int gpio20_pins[] = { 20 };
-static int gpio21_pins[] = { 21 };
-static int gpio22_pins[] = { 22 };
-
 static const struct pinctrl_pin_desc sm8550_lpi_pins[] = {
 	PINCTRL_PIN(0, "gpio0"),
 	PINCTRL_PIN(1, "gpio1"),
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8650-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm8650-lpass-lpi.c
new file mode 100644
index 000000000000..04400c832327
--- /dev/null
+++ b/drivers/pinctrl/qcom/pinctrl-sm8650-lpass-lpi.c
@@ -0,0 +1,231 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2022-2023 Linaro Ltd.
+ */
+
+#include <linux/gpio/driver.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#include "pinctrl-lpass-lpi.h"
+
+enum lpass_lpi_functions {
+	LPI_MUX_dmic1_clk,
+	LPI_MUX_dmic1_data,
+	LPI_MUX_dmic2_clk,
+	LPI_MUX_dmic2_data,
+	LPI_MUX_dmic3_clk,
+	LPI_MUX_dmic3_data,
+	LPI_MUX_dmic4_clk,
+	LPI_MUX_dmic4_data,
+	LPI_MUX_i2s0_clk,
+	LPI_MUX_i2s0_data,
+	LPI_MUX_i2s0_ws,
+	LPI_MUX_i2s1_clk,
+	LPI_MUX_i2s1_data,
+	LPI_MUX_i2s1_ws,
+	LPI_MUX_i2s2_clk,
+	LPI_MUX_i2s2_data,
+	LPI_MUX_i2s2_ws,
+	LPI_MUX_i2s3_clk,
+	LPI_MUX_i2s3_data,
+	LPI_MUX_i2s3_ws,
+	LPI_MUX_i2s4_clk,
+	LPI_MUX_i2s4_data,
+	LPI_MUX_i2s4_ws,
+	LPI_MUX_qca_swr_clk,
+	LPI_MUX_qca_swr_data,
+	LPI_MUX_slimbus_clk,
+	LPI_MUX_slimbus_data,
+	LPI_MUX_swr_rx_clk,
+	LPI_MUX_swr_rx_data,
+	LPI_MUX_swr_tx_clk,
+	LPI_MUX_swr_tx_data,
+	LPI_MUX_wsa_swr_clk,
+	LPI_MUX_wsa_swr_data,
+	LPI_MUX_wsa2_swr_clk,
+	LPI_MUX_wsa2_swr_data,
+	LPI_MUX_ext_mclk1_a,
+	LPI_MUX_ext_mclk1_b,
+	LPI_MUX_ext_mclk1_c,
+	LPI_MUX_ext_mclk1_d,
+	LPI_MUX_ext_mclk1_e,
+	LPI_MUX_gpio,
+	LPI_MUX__,
+};
+
+static const struct pinctrl_pin_desc sm8650_lpi_pins[] = {
+	PINCTRL_PIN(0, "gpio0"),
+	PINCTRL_PIN(1, "gpio1"),
+	PINCTRL_PIN(2, "gpio2"),
+	PINCTRL_PIN(3, "gpio3"),
+	PINCTRL_PIN(4, "gpio4"),
+	PINCTRL_PIN(5, "gpio5"),
+	PINCTRL_PIN(6, "gpio6"),
+	PINCTRL_PIN(7, "gpio7"),
+	PINCTRL_PIN(8, "gpio8"),
+	PINCTRL_PIN(9, "gpio9"),
+	PINCTRL_PIN(10, "gpio10"),
+	PINCTRL_PIN(11, "gpio11"),
+	PINCTRL_PIN(12, "gpio12"),
+	PINCTRL_PIN(13, "gpio13"),
+	PINCTRL_PIN(14, "gpio14"),
+	PINCTRL_PIN(15, "gpio15"),
+	PINCTRL_PIN(16, "gpio16"),
+	PINCTRL_PIN(17, "gpio17"),
+	PINCTRL_PIN(18, "gpio18"),
+	PINCTRL_PIN(19, "gpio19"),
+	PINCTRL_PIN(20, "gpio20"),
+	PINCTRL_PIN(21, "gpio21"),
+	PINCTRL_PIN(22, "gpio22"),
+};
+
+static const char * const gpio_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7",
+	"gpio8", "gpio9", "gpio10", "gpio11", "gpio12", "gpio13", "gpio14",
+	"gpio15", "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21",
+	"gpio22",
+};
+
+static const char * const dmic1_clk_groups[] = { "gpio6" };
+static const char * const dmic1_data_groups[] = { "gpio7" };
+static const char * const dmic2_clk_groups[] = { "gpio8" };
+static const char * const dmic2_data_groups[] = { "gpio9" };
+static const char * const dmic3_clk_groups[] = { "gpio12" };
+static const char * const dmic3_data_groups[] = { "gpio13" };
+static const char * const dmic4_clk_groups[] = { "gpio17" };
+static const char * const dmic4_data_groups[] = { "gpio18" };
+static const char * const i2s0_clk_groups[] = { "gpio0" };
+static const char * const i2s0_ws_groups[] = { "gpio1" };
+static const char * const i2s0_data_groups[] = { "gpio2", "gpio3", "gpio4", "gpio5" };
+static const char * const i2s1_clk_groups[] = { "gpio6" };
+static const char * const i2s1_ws_groups[] = { "gpio7" };
+static const char * const i2s1_data_groups[] = { "gpio8", "gpio9" };
+static const char * const i2s2_clk_groups[] = { "gpio10" };
+static const char * const i2s2_ws_groups[] = { "gpio11" };
+static const char * const i2s2_data_groups[] = { "gpio15", "gpio16" };
+static const char * const i2s3_clk_groups[] = { "gpio12" };
+static const char * const i2s3_ws_groups[] = { "gpio13" };
+static const char * const i2s3_data_groups[] = { "gpio17", "gpio18" };
+static const char * const i2s4_clk_groups[] = { "gpio19"};
+static const char * const i2s4_ws_groups[] = { "gpio20"};
+static const char * const i2s4_data_groups[] = { "gpio21", "gpio22"};
+static const char * const qca_swr_clk_groups[] = { "gpio19" };
+static const char * const qca_swr_data_groups[] = { "gpio20" };
+static const char * const slimbus_clk_groups[] = { "gpio19"};
+static const char * const slimbus_data_groups[] = { "gpio20"};
+static const char * const swr_tx_clk_groups[] = { "gpio0" };
+static const char * const swr_tx_data_groups[] = { "gpio1", "gpio2", "gpio14" };
+static const char * const swr_rx_clk_groups[] = { "gpio3" };
+static const char * const swr_rx_data_groups[] = { "gpio4", "gpio5", "gpio15" };
+static const char * const wsa_swr_clk_groups[] = { "gpio10" };
+static const char * const wsa_swr_data_groups[] = { "gpio11" };
+static const char * const wsa2_swr_clk_groups[] = { "gpio15" };
+static const char * const wsa2_swr_data_groups[] = { "gpio16" };
+static const char * const ext_mclk1_c_groups[] = { "gpio5" };
+static const char * const ext_mclk1_b_groups[] = { "gpio9" };
+static const char * const ext_mclk1_a_groups[] = { "gpio13" };
+static const char * const ext_mclk1_d_groups[] = { "gpio14" };
+static const char * const ext_mclk1_e_groups[] = { "gpio22" };
+
+static const struct lpi_pingroup sm8650_groups[] = {
+	LPI_PINGROUP(0, 11, swr_tx_clk, i2s0_clk, _, _),
+	LPI_PINGROUP(1, 11, swr_tx_data, i2s0_ws, _, _),
+	LPI_PINGROUP(2, 11, swr_tx_data, i2s0_data, _, _),
+	LPI_PINGROUP(3, 11, swr_rx_clk, i2s0_data, _, _),
+	LPI_PINGROUP(4, 11, swr_rx_data, i2s0_data, _, _),
+	LPI_PINGROUP(5, 11, swr_rx_data, ext_mclk1_c, i2s0_data, _),
+	LPI_PINGROUP(6, LPI_NO_SLEW, dmic1_clk, i2s1_clk, _,  _),
+	LPI_PINGROUP(7, LPI_NO_SLEW, dmic1_data, i2s1_ws, _, _),
+	LPI_PINGROUP(8, LPI_NO_SLEW, dmic2_clk, i2s1_data, _, _),
+	LPI_PINGROUP(9, LPI_NO_SLEW, dmic2_data, i2s1_data, ext_mclk1_b, _),
+	LPI_PINGROUP(10, 11, i2s2_clk, wsa_swr_clk, _, _),
+	LPI_PINGROUP(11, 11, i2s2_ws, wsa_swr_data, _, _),
+	LPI_PINGROUP(12, LPI_NO_SLEW, dmic3_clk, i2s3_clk, _, _),
+	LPI_PINGROUP(13, LPI_NO_SLEW, dmic3_data, i2s3_ws, ext_mclk1_a, _),
+	LPI_PINGROUP(14, 11, swr_tx_data, ext_mclk1_d, _, _),
+	LPI_PINGROUP(15, 11, i2s2_data, wsa2_swr_clk, _, _),
+	LPI_PINGROUP(16, 11, i2s2_data, wsa2_swr_data, _, _),
+	LPI_PINGROUP(17, LPI_NO_SLEW, dmic4_clk, i2s3_data, _, _),
+	LPI_PINGROUP(18, LPI_NO_SLEW, dmic4_data, i2s3_data, _, _),
+	LPI_PINGROUP(19, 11, i2s4_clk, slimbus_clk, qca_swr_clk, _),
+	LPI_PINGROUP(20, 11, i2s4_ws, slimbus_data, qca_swr_data, _),
+	LPI_PINGROUP(21, LPI_NO_SLEW, i2s4_data, _, _, _),
+	LPI_PINGROUP(22, LPI_NO_SLEW, i2s4_data, ext_mclk1_e, _, _),
+};
+
+static const struct lpi_function sm8650_functions[] = {
+	LPI_FUNCTION(gpio),
+	LPI_FUNCTION(dmic1_clk),
+	LPI_FUNCTION(dmic1_data),
+	LPI_FUNCTION(dmic2_clk),
+	LPI_FUNCTION(dmic2_data),
+	LPI_FUNCTION(dmic3_clk),
+	LPI_FUNCTION(dmic3_data),
+	LPI_FUNCTION(dmic4_clk),
+	LPI_FUNCTION(dmic4_data),
+	LPI_FUNCTION(i2s0_clk),
+	LPI_FUNCTION(i2s0_data),
+	LPI_FUNCTION(i2s0_ws),
+	LPI_FUNCTION(i2s1_clk),
+	LPI_FUNCTION(i2s1_data),
+	LPI_FUNCTION(i2s1_ws),
+	LPI_FUNCTION(i2s2_clk),
+	LPI_FUNCTION(i2s2_data),
+	LPI_FUNCTION(i2s2_ws),
+	LPI_FUNCTION(i2s3_clk),
+	LPI_FUNCTION(i2s3_data),
+	LPI_FUNCTION(i2s3_ws),
+	LPI_FUNCTION(i2s4_clk),
+	LPI_FUNCTION(i2s4_data),
+	LPI_FUNCTION(i2s4_ws),
+	LPI_FUNCTION(qca_swr_clk),
+	LPI_FUNCTION(qca_swr_data),
+	LPI_FUNCTION(slimbus_clk),
+	LPI_FUNCTION(slimbus_data),
+	LPI_FUNCTION(swr_rx_clk),
+	LPI_FUNCTION(swr_rx_data),
+	LPI_FUNCTION(swr_tx_clk),
+	LPI_FUNCTION(swr_tx_data),
+	LPI_FUNCTION(wsa_swr_clk),
+	LPI_FUNCTION(wsa_swr_data),
+	LPI_FUNCTION(wsa2_swr_clk),
+	LPI_FUNCTION(wsa2_swr_data),
+	LPI_FUNCTION(ext_mclk1_a),
+	LPI_FUNCTION(ext_mclk1_b),
+	LPI_FUNCTION(ext_mclk1_c),
+	LPI_FUNCTION(ext_mclk1_d),
+	LPI_FUNCTION(ext_mclk1_e),
+};
+
+static const struct lpi_pinctrl_variant_data sm8650_lpi_data = {
+	.pins = sm8650_lpi_pins,
+	.npins = ARRAY_SIZE(sm8650_lpi_pins),
+	.groups = sm8650_groups,
+	.ngroups = ARRAY_SIZE(sm8650_groups),
+	.functions = sm8650_functions,
+	.nfunctions = ARRAY_SIZE(sm8650_functions),
+	.flags = LPI_FLAG_SLEW_RATE_SAME_REG,
+};
+
+static const struct of_device_id lpi_pinctrl_of_match[] = {
+	{
+	       .compatible = "qcom,sm8650-lpass-lpi-pinctrl",
+	       .data = &sm8650_lpi_data,
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, lpi_pinctrl_of_match);
+
+static struct platform_driver lpi_pinctrl_driver = {
+	.driver = {
+		   .name = "qcom-sm8650-lpass-lpi-pinctrl",
+		   .of_match_table = lpi_pinctrl_of_match,
+	},
+	.probe = lpi_pinctrl_probe,
+	.remove_new = lpi_pinctrl_remove,
+};
+
+module_platform_driver(lpi_pinctrl_driver);
+MODULE_DESCRIPTION("Qualcomm SM8650 LPI GPIO pin control driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8650.c b/drivers/pinctrl/qcom/pinctrl-sm8650.c
new file mode 100644
index 000000000000..adaddd728662
--- /dev/null
+++ b/drivers/pinctrl/qcom/pinctrl-sm8650.c
@@ -0,0 +1,1762 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include "pinctrl-msm.h"
+
+#define REG_SIZE 0x1000
+
+#define PINGROUP(id, f1, f2, f3, f4, f5, f6, f7, f8, f9, f10)	\
+	{					        \
+		.grp = PINCTRL_PINGROUP("gpio" #id,	\
+			gpio##id##_pins,		\
+			ARRAY_SIZE(gpio##id##_pins)),	\
+		.funcs = (int[]){			\
+			msm_mux_gpio, /* gpio mode */	\
+			msm_mux_##f1,			\
+			msm_mux_##f2,			\
+			msm_mux_##f3,			\
+			msm_mux_##f4,			\
+			msm_mux_##f5,			\
+			msm_mux_##f6,			\
+			msm_mux_##f7,			\
+			msm_mux_##f8,			\
+			msm_mux_##f9,			\
+			msm_mux_##f10			\
+		},				        \
+		.nfuncs = 11,				\
+		.ctl_reg = REG_SIZE * id,			\
+		.io_reg = 0x4 + REG_SIZE * id,		\
+		.intr_cfg_reg = 0x8 + REG_SIZE * id,		\
+		.intr_status_reg = 0xc + REG_SIZE * id,	\
+		.intr_target_reg = 0x8 + REG_SIZE * id,	\
+		.mux_bit = 2,			\
+		.pull_bit = 0,			\
+		.drv_bit = 6,			\
+		.i2c_pull_bit = 13,		\
+		.egpio_enable = 12,		\
+		.egpio_present = 11,		\
+		.oe_bit = 9,			\
+		.in_bit = 0,			\
+		.out_bit = 1,			\
+		.intr_enable_bit = 0,		\
+		.intr_status_bit = 0,		\
+		.intr_wakeup_present_bit = 6,   \
+		.intr_wakeup_enable_bit = 7,    \
+		.intr_target_bit = 8,		\
+		.intr_target_kpss_val = 3,	\
+		.intr_raw_status_bit = 4,	\
+		.intr_polarity_bit = 1,		\
+		.intr_detection_bit = 2,	\
+		.intr_detection_width = 2,	\
+	}
+
+#define SDC_QDSD_PINGROUP(pg_name, ctl, pull, drv)	\
+	{					        \
+		.grp = PINCTRL_PINGROUP(#pg_name,	\
+			pg_name##_pins,			\
+			ARRAY_SIZE(pg_name##_pins)),	\
+		.ctl_reg = ctl,				\
+		.io_reg = 0,				\
+		.intr_cfg_reg = 0,			\
+		.intr_status_reg = 0,			\
+		.intr_target_reg = 0,			\
+		.mux_bit = -1,				\
+		.pull_bit = pull,			\
+		.drv_bit = drv,				\
+		.oe_bit = -1,				\
+		.in_bit = -1,				\
+		.out_bit = -1,				\
+		.intr_enable_bit = -1,			\
+		.intr_status_bit = -1,			\
+		.intr_target_bit = -1,			\
+		.intr_raw_status_bit = -1,		\
+		.intr_polarity_bit = -1,		\
+		.intr_detection_bit = -1,		\
+		.intr_detection_width = -1,		\
+	}
+
+#define UFS_RESET(pg_name, ctl, io)			\
+	{					        \
+		.grp = PINCTRL_PINGROUP(#pg_name,	\
+			pg_name##_pins,			\
+			ARRAY_SIZE(pg_name##_pins)),	\
+		.ctl_reg = ctl,				\
+		.io_reg = io,				\
+		.intr_cfg_reg = 0,			\
+		.intr_status_reg = 0,			\
+		.intr_target_reg = 0,			\
+		.mux_bit = -1,				\
+		.pull_bit = 3,				\
+		.drv_bit = 0,				\
+		.oe_bit = -1,				\
+		.in_bit = -1,				\
+		.out_bit = 0,				\
+		.intr_enable_bit = -1,			\
+		.intr_status_bit = -1,			\
+		.intr_target_bit = -1,			\
+		.intr_raw_status_bit = -1,		\
+		.intr_polarity_bit = -1,		\
+		.intr_detection_bit = -1,		\
+		.intr_detection_width = -1,		\
+	}
+
+static const struct pinctrl_pin_desc sm8650_pins[] = {
+	PINCTRL_PIN(0, "GPIO_0"),
+	PINCTRL_PIN(1, "GPIO_1"),
+	PINCTRL_PIN(2, "GPIO_2"),
+	PINCTRL_PIN(3, "GPIO_3"),
+	PINCTRL_PIN(4, "GPIO_4"),
+	PINCTRL_PIN(5, "GPIO_5"),
+	PINCTRL_PIN(6, "GPIO_6"),
+	PINCTRL_PIN(7, "GPIO_7"),
+	PINCTRL_PIN(8, "GPIO_8"),
+	PINCTRL_PIN(9, "GPIO_9"),
+	PINCTRL_PIN(10, "GPIO_10"),
+	PINCTRL_PIN(11, "GPIO_11"),
+	PINCTRL_PIN(12, "GPIO_12"),
+	PINCTRL_PIN(13, "GPIO_13"),
+	PINCTRL_PIN(14, "GPIO_14"),
+	PINCTRL_PIN(15, "GPIO_15"),
+	PINCTRL_PIN(16, "GPIO_16"),
+	PINCTRL_PIN(17, "GPIO_17"),
+	PINCTRL_PIN(18, "GPIO_18"),
+	PINCTRL_PIN(19, "GPIO_19"),
+	PINCTRL_PIN(20, "GPIO_20"),
+	PINCTRL_PIN(21, "GPIO_21"),
+	PINCTRL_PIN(22, "GPIO_22"),
+	PINCTRL_PIN(23, "GPIO_23"),
+	PINCTRL_PIN(24, "GPIO_24"),
+	PINCTRL_PIN(25, "GPIO_25"),
+	PINCTRL_PIN(26, "GPIO_26"),
+	PINCTRL_PIN(27, "GPIO_27"),
+	PINCTRL_PIN(28, "GPIO_28"),
+	PINCTRL_PIN(29, "GPIO_29"),
+	PINCTRL_PIN(30, "GPIO_30"),
+	PINCTRL_PIN(31, "GPIO_31"),
+	PINCTRL_PIN(32, "GPIO_32"),
+	PINCTRL_PIN(33, "GPIO_33"),
+	PINCTRL_PIN(34, "GPIO_34"),
+	PINCTRL_PIN(35, "GPIO_35"),
+	PINCTRL_PIN(36, "GPIO_36"),
+	PINCTRL_PIN(37, "GPIO_37"),
+	PINCTRL_PIN(38, "GPIO_38"),
+	PINCTRL_PIN(39, "GPIO_39"),
+	PINCTRL_PIN(40, "GPIO_40"),
+	PINCTRL_PIN(41, "GPIO_41"),
+	PINCTRL_PIN(42, "GPIO_42"),
+	PINCTRL_PIN(43, "GPIO_43"),
+	PINCTRL_PIN(44, "GPIO_44"),
+	PINCTRL_PIN(45, "GPIO_45"),
+	PINCTRL_PIN(46, "GPIO_46"),
+	PINCTRL_PIN(47, "GPIO_47"),
+	PINCTRL_PIN(48, "GPIO_48"),
+	PINCTRL_PIN(49, "GPIO_49"),
+	PINCTRL_PIN(50, "GPIO_50"),
+	PINCTRL_PIN(51, "GPIO_51"),
+	PINCTRL_PIN(52, "GPIO_52"),
+	PINCTRL_PIN(53, "GPIO_53"),
+	PINCTRL_PIN(54, "GPIO_54"),
+	PINCTRL_PIN(55, "GPIO_55"),
+	PINCTRL_PIN(56, "GPIO_56"),
+	PINCTRL_PIN(57, "GPIO_57"),
+	PINCTRL_PIN(58, "GPIO_58"),
+	PINCTRL_PIN(59, "GPIO_59"),
+	PINCTRL_PIN(60, "GPIO_60"),
+	PINCTRL_PIN(61, "GPIO_61"),
+	PINCTRL_PIN(62, "GPIO_62"),
+	PINCTRL_PIN(63, "GPIO_63"),
+	PINCTRL_PIN(64, "GPIO_64"),
+	PINCTRL_PIN(65, "GPIO_65"),
+	PINCTRL_PIN(66, "GPIO_66"),
+	PINCTRL_PIN(67, "GPIO_67"),
+	PINCTRL_PIN(68, "GPIO_68"),
+	PINCTRL_PIN(69, "GPIO_69"),
+	PINCTRL_PIN(70, "GPIO_70"),
+	PINCTRL_PIN(71, "GPIO_71"),
+	PINCTRL_PIN(72, "GPIO_72"),
+	PINCTRL_PIN(73, "GPIO_73"),
+	PINCTRL_PIN(74, "GPIO_74"),
+	PINCTRL_PIN(75, "GPIO_75"),
+	PINCTRL_PIN(76, "GPIO_76"),
+	PINCTRL_PIN(77, "GPIO_77"),
+	PINCTRL_PIN(78, "GPIO_78"),
+	PINCTRL_PIN(79, "GPIO_79"),
+	PINCTRL_PIN(80, "GPIO_80"),
+	PINCTRL_PIN(81, "GPIO_81"),
+	PINCTRL_PIN(82, "GPIO_82"),
+	PINCTRL_PIN(83, "GPIO_83"),
+	PINCTRL_PIN(84, "GPIO_84"),
+	PINCTRL_PIN(85, "GPIO_85"),
+	PINCTRL_PIN(86, "GPIO_86"),
+	PINCTRL_PIN(87, "GPIO_87"),
+	PINCTRL_PIN(88, "GPIO_88"),
+	PINCTRL_PIN(89, "GPIO_89"),
+	PINCTRL_PIN(90, "GPIO_90"),
+	PINCTRL_PIN(91, "GPIO_91"),
+	PINCTRL_PIN(92, "GPIO_92"),
+	PINCTRL_PIN(93, "GPIO_93"),
+	PINCTRL_PIN(94, "GPIO_94"),
+	PINCTRL_PIN(95, "GPIO_95"),
+	PINCTRL_PIN(96, "GPIO_96"),
+	PINCTRL_PIN(97, "GPIO_97"),
+	PINCTRL_PIN(98, "GPIO_98"),
+	PINCTRL_PIN(99, "GPIO_99"),
+	PINCTRL_PIN(100, "GPIO_100"),
+	PINCTRL_PIN(101, "GPIO_101"),
+	PINCTRL_PIN(102, "GPIO_102"),
+	PINCTRL_PIN(103, "GPIO_103"),
+	PINCTRL_PIN(104, "GPIO_104"),
+	PINCTRL_PIN(105, "GPIO_105"),
+	PINCTRL_PIN(106, "GPIO_106"),
+	PINCTRL_PIN(107, "GPIO_107"),
+	PINCTRL_PIN(108, "GPIO_108"),
+	PINCTRL_PIN(109, "GPIO_109"),
+	PINCTRL_PIN(110, "GPIO_110"),
+	PINCTRL_PIN(111, "GPIO_111"),
+	PINCTRL_PIN(112, "GPIO_112"),
+	PINCTRL_PIN(113, "GPIO_113"),
+	PINCTRL_PIN(114, "GPIO_114"),
+	PINCTRL_PIN(115, "GPIO_115"),
+	PINCTRL_PIN(116, "GPIO_116"),
+	PINCTRL_PIN(117, "GPIO_117"),
+	PINCTRL_PIN(118, "GPIO_118"),
+	PINCTRL_PIN(119, "GPIO_119"),
+	PINCTRL_PIN(120, "GPIO_120"),
+	PINCTRL_PIN(121, "GPIO_121"),
+	PINCTRL_PIN(122, "GPIO_122"),
+	PINCTRL_PIN(123, "GPIO_123"),
+	PINCTRL_PIN(124, "GPIO_124"),
+	PINCTRL_PIN(125, "GPIO_125"),
+	PINCTRL_PIN(126, "GPIO_126"),
+	PINCTRL_PIN(127, "GPIO_127"),
+	PINCTRL_PIN(128, "GPIO_128"),
+	PINCTRL_PIN(129, "GPIO_129"),
+	PINCTRL_PIN(130, "GPIO_130"),
+	PINCTRL_PIN(131, "GPIO_131"),
+	PINCTRL_PIN(132, "GPIO_132"),
+	PINCTRL_PIN(133, "GPIO_133"),
+	PINCTRL_PIN(134, "GPIO_134"),
+	PINCTRL_PIN(135, "GPIO_135"),
+	PINCTRL_PIN(136, "GPIO_136"),
+	PINCTRL_PIN(137, "GPIO_137"),
+	PINCTRL_PIN(138, "GPIO_138"),
+	PINCTRL_PIN(139, "GPIO_139"),
+	PINCTRL_PIN(140, "GPIO_140"),
+	PINCTRL_PIN(141, "GPIO_141"),
+	PINCTRL_PIN(142, "GPIO_142"),
+	PINCTRL_PIN(143, "GPIO_143"),
+	PINCTRL_PIN(144, "GPIO_144"),
+	PINCTRL_PIN(145, "GPIO_145"),
+	PINCTRL_PIN(146, "GPIO_146"),
+	PINCTRL_PIN(147, "GPIO_147"),
+	PINCTRL_PIN(148, "GPIO_148"),
+	PINCTRL_PIN(149, "GPIO_149"),
+	PINCTRL_PIN(150, "GPIO_150"),
+	PINCTRL_PIN(151, "GPIO_151"),
+	PINCTRL_PIN(152, "GPIO_152"),
+	PINCTRL_PIN(153, "GPIO_153"),
+	PINCTRL_PIN(154, "GPIO_154"),
+	PINCTRL_PIN(155, "GPIO_155"),
+	PINCTRL_PIN(156, "GPIO_156"),
+	PINCTRL_PIN(157, "GPIO_157"),
+	PINCTRL_PIN(158, "GPIO_158"),
+	PINCTRL_PIN(159, "GPIO_159"),
+	PINCTRL_PIN(160, "GPIO_160"),
+	PINCTRL_PIN(161, "GPIO_161"),
+	PINCTRL_PIN(162, "GPIO_162"),
+	PINCTRL_PIN(163, "GPIO_163"),
+	PINCTRL_PIN(164, "GPIO_164"),
+	PINCTRL_PIN(165, "GPIO_165"),
+	PINCTRL_PIN(166, "GPIO_166"),
+	PINCTRL_PIN(167, "GPIO_167"),
+	PINCTRL_PIN(168, "GPIO_168"),
+	PINCTRL_PIN(169, "GPIO_169"),
+	PINCTRL_PIN(170, "GPIO_170"),
+	PINCTRL_PIN(171, "GPIO_171"),
+	PINCTRL_PIN(172, "GPIO_172"),
+	PINCTRL_PIN(173, "GPIO_173"),
+	PINCTRL_PIN(174, "GPIO_174"),
+	PINCTRL_PIN(175, "GPIO_175"),
+	PINCTRL_PIN(176, "GPIO_176"),
+	PINCTRL_PIN(177, "GPIO_177"),
+	PINCTRL_PIN(178, "GPIO_178"),
+	PINCTRL_PIN(179, "GPIO_179"),
+	PINCTRL_PIN(180, "GPIO_180"),
+	PINCTRL_PIN(181, "GPIO_181"),
+	PINCTRL_PIN(182, "GPIO_182"),
+	PINCTRL_PIN(183, "GPIO_183"),
+	PINCTRL_PIN(184, "GPIO_184"),
+	PINCTRL_PIN(185, "GPIO_185"),
+	PINCTRL_PIN(186, "GPIO_186"),
+	PINCTRL_PIN(187, "GPIO_187"),
+	PINCTRL_PIN(188, "GPIO_188"),
+	PINCTRL_PIN(189, "GPIO_189"),
+	PINCTRL_PIN(190, "GPIO_190"),
+	PINCTRL_PIN(191, "GPIO_191"),
+	PINCTRL_PIN(192, "GPIO_192"),
+	PINCTRL_PIN(193, "GPIO_193"),
+	PINCTRL_PIN(194, "GPIO_194"),
+	PINCTRL_PIN(195, "GPIO_195"),
+	PINCTRL_PIN(196, "GPIO_196"),
+	PINCTRL_PIN(197, "GPIO_197"),
+	PINCTRL_PIN(198, "GPIO_198"),
+	PINCTRL_PIN(199, "GPIO_199"),
+	PINCTRL_PIN(200, "GPIO_200"),
+	PINCTRL_PIN(201, "GPIO_201"),
+	PINCTRL_PIN(202, "GPIO_202"),
+	PINCTRL_PIN(203, "GPIO_203"),
+	PINCTRL_PIN(204, "GPIO_204"),
+	PINCTRL_PIN(205, "GPIO_205"),
+	PINCTRL_PIN(206, "GPIO_206"),
+	PINCTRL_PIN(207, "GPIO_207"),
+	PINCTRL_PIN(208, "GPIO_208"),
+	PINCTRL_PIN(209, "GPIO_209"),
+	PINCTRL_PIN(210, "UFS_RESET"),
+	PINCTRL_PIN(211, "SDC2_CLK"),
+	PINCTRL_PIN(212, "SDC2_CMD"),
+	PINCTRL_PIN(213, "SDC2_DATA"),
+};
+
+#define DECLARE_MSM_GPIO_PINS(pin) \
+	static const unsigned int gpio##pin##_pins[] = { pin }
+DECLARE_MSM_GPIO_PINS(0);
+DECLARE_MSM_GPIO_PINS(1);
+DECLARE_MSM_GPIO_PINS(2);
+DECLARE_MSM_GPIO_PINS(3);
+DECLARE_MSM_GPIO_PINS(4);
+DECLARE_MSM_GPIO_PINS(5);
+DECLARE_MSM_GPIO_PINS(6);
+DECLARE_MSM_GPIO_PINS(7);
+DECLARE_MSM_GPIO_PINS(8);
+DECLARE_MSM_GPIO_PINS(9);
+DECLARE_MSM_GPIO_PINS(10);
+DECLARE_MSM_GPIO_PINS(11);
+DECLARE_MSM_GPIO_PINS(12);
+DECLARE_MSM_GPIO_PINS(13);
+DECLARE_MSM_GPIO_PINS(14);
+DECLARE_MSM_GPIO_PINS(15);
+DECLARE_MSM_GPIO_PINS(16);
+DECLARE_MSM_GPIO_PINS(17);
+DECLARE_MSM_GPIO_PINS(18);
+DECLARE_MSM_GPIO_PINS(19);
+DECLARE_MSM_GPIO_PINS(20);
+DECLARE_MSM_GPIO_PINS(21);
+DECLARE_MSM_GPIO_PINS(22);
+DECLARE_MSM_GPIO_PINS(23);
+DECLARE_MSM_GPIO_PINS(24);
+DECLARE_MSM_GPIO_PINS(25);
+DECLARE_MSM_GPIO_PINS(26);
+DECLARE_MSM_GPIO_PINS(27);
+DECLARE_MSM_GPIO_PINS(28);
+DECLARE_MSM_GPIO_PINS(29);
+DECLARE_MSM_GPIO_PINS(30);
+DECLARE_MSM_GPIO_PINS(31);
+DECLARE_MSM_GPIO_PINS(32);
+DECLARE_MSM_GPIO_PINS(33);
+DECLARE_MSM_GPIO_PINS(34);
+DECLARE_MSM_GPIO_PINS(35);
+DECLARE_MSM_GPIO_PINS(36);
+DECLARE_MSM_GPIO_PINS(37);
+DECLARE_MSM_GPIO_PINS(38);
+DECLARE_MSM_GPIO_PINS(39);
+DECLARE_MSM_GPIO_PINS(40);
+DECLARE_MSM_GPIO_PINS(41);
+DECLARE_MSM_GPIO_PINS(42);
+DECLARE_MSM_GPIO_PINS(43);
+DECLARE_MSM_GPIO_PINS(44);
+DECLARE_MSM_GPIO_PINS(45);
+DECLARE_MSM_GPIO_PINS(46);
+DECLARE_MSM_GPIO_PINS(47);
+DECLARE_MSM_GPIO_PINS(48);
+DECLARE_MSM_GPIO_PINS(49);
+DECLARE_MSM_GPIO_PINS(50);
+DECLARE_MSM_GPIO_PINS(51);
+DECLARE_MSM_GPIO_PINS(52);
+DECLARE_MSM_GPIO_PINS(53);
+DECLARE_MSM_GPIO_PINS(54);
+DECLARE_MSM_GPIO_PINS(55);
+DECLARE_MSM_GPIO_PINS(56);
+DECLARE_MSM_GPIO_PINS(57);
+DECLARE_MSM_GPIO_PINS(58);
+DECLARE_MSM_GPIO_PINS(59);
+DECLARE_MSM_GPIO_PINS(60);
+DECLARE_MSM_GPIO_PINS(61);
+DECLARE_MSM_GPIO_PINS(62);
+DECLARE_MSM_GPIO_PINS(63);
+DECLARE_MSM_GPIO_PINS(64);
+DECLARE_MSM_GPIO_PINS(65);
+DECLARE_MSM_GPIO_PINS(66);
+DECLARE_MSM_GPIO_PINS(67);
+DECLARE_MSM_GPIO_PINS(68);
+DECLARE_MSM_GPIO_PINS(69);
+DECLARE_MSM_GPIO_PINS(70);
+DECLARE_MSM_GPIO_PINS(71);
+DECLARE_MSM_GPIO_PINS(72);
+DECLARE_MSM_GPIO_PINS(73);
+DECLARE_MSM_GPIO_PINS(74);
+DECLARE_MSM_GPIO_PINS(75);
+DECLARE_MSM_GPIO_PINS(76);
+DECLARE_MSM_GPIO_PINS(77);
+DECLARE_MSM_GPIO_PINS(78);
+DECLARE_MSM_GPIO_PINS(79);
+DECLARE_MSM_GPIO_PINS(80);
+DECLARE_MSM_GPIO_PINS(81);
+DECLARE_MSM_GPIO_PINS(82);
+DECLARE_MSM_GPIO_PINS(83);
+DECLARE_MSM_GPIO_PINS(84);
+DECLARE_MSM_GPIO_PINS(85);
+DECLARE_MSM_GPIO_PINS(86);
+DECLARE_MSM_GPIO_PINS(87);
+DECLARE_MSM_GPIO_PINS(88);
+DECLARE_MSM_GPIO_PINS(89);
+DECLARE_MSM_GPIO_PINS(90);
+DECLARE_MSM_GPIO_PINS(91);
+DECLARE_MSM_GPIO_PINS(92);
+DECLARE_MSM_GPIO_PINS(93);
+DECLARE_MSM_GPIO_PINS(94);
+DECLARE_MSM_GPIO_PINS(95);
+DECLARE_MSM_GPIO_PINS(96);
+DECLARE_MSM_GPIO_PINS(97);
+DECLARE_MSM_GPIO_PINS(98);
+DECLARE_MSM_GPIO_PINS(99);
+DECLARE_MSM_GPIO_PINS(100);
+DECLARE_MSM_GPIO_PINS(101);
+DECLARE_MSM_GPIO_PINS(102);
+DECLARE_MSM_GPIO_PINS(103);
+DECLARE_MSM_GPIO_PINS(104);
+DECLARE_MSM_GPIO_PINS(105);
+DECLARE_MSM_GPIO_PINS(106);
+DECLARE_MSM_GPIO_PINS(107);
+DECLARE_MSM_GPIO_PINS(108);
+DECLARE_MSM_GPIO_PINS(109);
+DECLARE_MSM_GPIO_PINS(110);
+DECLARE_MSM_GPIO_PINS(111);
+DECLARE_MSM_GPIO_PINS(112);
+DECLARE_MSM_GPIO_PINS(113);
+DECLARE_MSM_GPIO_PINS(114);
+DECLARE_MSM_GPIO_PINS(115);
+DECLARE_MSM_GPIO_PINS(116);
+DECLARE_MSM_GPIO_PINS(117);
+DECLARE_MSM_GPIO_PINS(118);
+DECLARE_MSM_GPIO_PINS(119);
+DECLARE_MSM_GPIO_PINS(120);
+DECLARE_MSM_GPIO_PINS(121);
+DECLARE_MSM_GPIO_PINS(122);
+DECLARE_MSM_GPIO_PINS(123);
+DECLARE_MSM_GPIO_PINS(124);
+DECLARE_MSM_GPIO_PINS(125);
+DECLARE_MSM_GPIO_PINS(126);
+DECLARE_MSM_GPIO_PINS(127);
+DECLARE_MSM_GPIO_PINS(128);
+DECLARE_MSM_GPIO_PINS(129);
+DECLARE_MSM_GPIO_PINS(130);
+DECLARE_MSM_GPIO_PINS(131);
+DECLARE_MSM_GPIO_PINS(132);
+DECLARE_MSM_GPIO_PINS(133);
+DECLARE_MSM_GPIO_PINS(134);
+DECLARE_MSM_GPIO_PINS(135);
+DECLARE_MSM_GPIO_PINS(136);
+DECLARE_MSM_GPIO_PINS(137);
+DECLARE_MSM_GPIO_PINS(138);
+DECLARE_MSM_GPIO_PINS(139);
+DECLARE_MSM_GPIO_PINS(140);
+DECLARE_MSM_GPIO_PINS(141);
+DECLARE_MSM_GPIO_PINS(142);
+DECLARE_MSM_GPIO_PINS(143);
+DECLARE_MSM_GPIO_PINS(144);
+DECLARE_MSM_GPIO_PINS(145);
+DECLARE_MSM_GPIO_PINS(146);
+DECLARE_MSM_GPIO_PINS(147);
+DECLARE_MSM_GPIO_PINS(148);
+DECLARE_MSM_GPIO_PINS(149);
+DECLARE_MSM_GPIO_PINS(150);
+DECLARE_MSM_GPIO_PINS(151);
+DECLARE_MSM_GPIO_PINS(152);
+DECLARE_MSM_GPIO_PINS(153);
+DECLARE_MSM_GPIO_PINS(154);
+DECLARE_MSM_GPIO_PINS(155);
+DECLARE_MSM_GPIO_PINS(156);
+DECLARE_MSM_GPIO_PINS(157);
+DECLARE_MSM_GPIO_PINS(158);
+DECLARE_MSM_GPIO_PINS(159);
+DECLARE_MSM_GPIO_PINS(160);
+DECLARE_MSM_GPIO_PINS(161);
+DECLARE_MSM_GPIO_PINS(162);
+DECLARE_MSM_GPIO_PINS(163);
+DECLARE_MSM_GPIO_PINS(164);
+DECLARE_MSM_GPIO_PINS(165);
+DECLARE_MSM_GPIO_PINS(166);
+DECLARE_MSM_GPIO_PINS(167);
+DECLARE_MSM_GPIO_PINS(168);
+DECLARE_MSM_GPIO_PINS(169);
+DECLARE_MSM_GPIO_PINS(170);
+DECLARE_MSM_GPIO_PINS(171);
+DECLARE_MSM_GPIO_PINS(172);
+DECLARE_MSM_GPIO_PINS(173);
+DECLARE_MSM_GPIO_PINS(174);
+DECLARE_MSM_GPIO_PINS(175);
+DECLARE_MSM_GPIO_PINS(176);
+DECLARE_MSM_GPIO_PINS(177);
+DECLARE_MSM_GPIO_PINS(178);
+DECLARE_MSM_GPIO_PINS(179);
+DECLARE_MSM_GPIO_PINS(180);
+DECLARE_MSM_GPIO_PINS(181);
+DECLARE_MSM_GPIO_PINS(182);
+DECLARE_MSM_GPIO_PINS(183);
+DECLARE_MSM_GPIO_PINS(184);
+DECLARE_MSM_GPIO_PINS(185);
+DECLARE_MSM_GPIO_PINS(186);
+DECLARE_MSM_GPIO_PINS(187);
+DECLARE_MSM_GPIO_PINS(188);
+DECLARE_MSM_GPIO_PINS(189);
+DECLARE_MSM_GPIO_PINS(190);
+DECLARE_MSM_GPIO_PINS(191);
+DECLARE_MSM_GPIO_PINS(192);
+DECLARE_MSM_GPIO_PINS(193);
+DECLARE_MSM_GPIO_PINS(194);
+DECLARE_MSM_GPIO_PINS(195);
+DECLARE_MSM_GPIO_PINS(196);
+DECLARE_MSM_GPIO_PINS(197);
+DECLARE_MSM_GPIO_PINS(198);
+DECLARE_MSM_GPIO_PINS(199);
+DECLARE_MSM_GPIO_PINS(200);
+DECLARE_MSM_GPIO_PINS(201);
+DECLARE_MSM_GPIO_PINS(202);
+DECLARE_MSM_GPIO_PINS(203);
+DECLARE_MSM_GPIO_PINS(204);
+DECLARE_MSM_GPIO_PINS(205);
+DECLARE_MSM_GPIO_PINS(206);
+DECLARE_MSM_GPIO_PINS(207);
+DECLARE_MSM_GPIO_PINS(208);
+DECLARE_MSM_GPIO_PINS(209);
+
+static const unsigned int ufs_reset_pins[] = { 210 };
+static const unsigned int sdc2_clk_pins[] = { 211 };
+static const unsigned int sdc2_cmd_pins[] = { 212 };
+static const unsigned int sdc2_data_pins[] = { 213 };
+
+enum sm8650_functions {
+	msm_mux_gpio,
+	msm_mux_aoss_cti,
+	msm_mux_atest_char,
+	msm_mux_atest_usb,
+	msm_mux_audio_ext_mclk0,
+	msm_mux_audio_ext_mclk1,
+	msm_mux_audio_ref_clk,
+	msm_mux_cam_aon_mclk2,
+	msm_mux_cam_aon_mclk4,
+	msm_mux_cam_mclk,
+	msm_mux_cci_async_in,
+	msm_mux_cci_i2c_scl,
+	msm_mux_cci_i2c_sda,
+	msm_mux_cci_timer,
+	msm_mux_cmu_rng,
+	msm_mux_coex_uart1_rx,
+	msm_mux_coex_uart1_tx,
+	msm_mux_coex_uart2_rx,
+	msm_mux_coex_uart2_tx,
+	msm_mux_cri_trng,
+	msm_mux_dbg_out_clk,
+	msm_mux_ddr_bist_complete,
+	msm_mux_ddr_bist_fail,
+	msm_mux_ddr_bist_start,
+	msm_mux_ddr_bist_stop,
+	msm_mux_ddr_pxi0,
+	msm_mux_ddr_pxi1,
+	msm_mux_ddr_pxi2,
+	msm_mux_ddr_pxi3,
+	msm_mux_do_not,
+	msm_mux_dp_hot,
+	msm_mux_egpio,
+	msm_mux_gcc_gp1,
+	msm_mux_gcc_gp2,
+	msm_mux_gcc_gp3,
+	msm_mux_gnss_adc0,
+	msm_mux_gnss_adc1,
+	msm_mux_i2chub0_se0,
+	msm_mux_i2chub0_se1,
+	msm_mux_i2chub0_se2,
+	msm_mux_i2chub0_se3,
+	msm_mux_i2chub0_se4,
+	msm_mux_i2chub0_se5,
+	msm_mux_i2chub0_se6,
+	msm_mux_i2chub0_se7,
+	msm_mux_i2chub0_se8,
+	msm_mux_i2chub0_se9,
+	msm_mux_i2s0_data0,
+	msm_mux_i2s0_data1,
+	msm_mux_i2s0_sck,
+	msm_mux_i2s0_ws,
+	msm_mux_i2s1_data0,
+	msm_mux_i2s1_data1,
+	msm_mux_i2s1_sck,
+	msm_mux_i2s1_ws,
+	msm_mux_ibi_i3c,
+	msm_mux_jitter_bist,
+	msm_mux_mdp_vsync,
+	msm_mux_mdp_vsync0_out,
+	msm_mux_mdp_vsync1_out,
+	msm_mux_mdp_vsync2_out,
+	msm_mux_mdp_vsync3_out,
+	msm_mux_mdp_vsync_e,
+	msm_mux_nav_gpio0,
+	msm_mux_nav_gpio1,
+	msm_mux_nav_gpio2,
+	msm_mux_nav_gpio3,
+	msm_mux_pcie0_clk_req_n,
+	msm_mux_pcie1_clk_req_n,
+	msm_mux_phase_flag,
+	msm_mux_pll_bist_sync,
+	msm_mux_pll_clk_aux,
+	msm_mux_prng_rosc0,
+	msm_mux_prng_rosc1,
+	msm_mux_prng_rosc2,
+	msm_mux_prng_rosc3,
+	msm_mux_qdss_cti,
+	msm_mux_qdss_gpio,
+	msm_mux_qlink_big_enable,
+	msm_mux_qlink_big_request,
+	msm_mux_qlink_little_enable,
+	msm_mux_qlink_little_request,
+	msm_mux_qlink_wmss,
+	msm_mux_qspi0,
+	msm_mux_qspi1,
+	msm_mux_qspi2,
+	msm_mux_qspi3,
+	msm_mux_qspi_clk,
+	msm_mux_qspi_cs,
+	msm_mux_qup1_se0,
+	msm_mux_qup1_se1,
+	msm_mux_qup1_se2,
+	msm_mux_qup1_se3,
+	msm_mux_qup1_se4,
+	msm_mux_qup1_se5,
+	msm_mux_qup1_se6,
+	msm_mux_qup1_se7,
+	msm_mux_qup2_se0,
+	msm_mux_qup2_se1,
+	msm_mux_qup2_se2,
+	msm_mux_qup2_se3,
+	msm_mux_qup2_se4,
+	msm_mux_qup2_se5,
+	msm_mux_qup2_se6,
+	msm_mux_qup2_se7,
+	msm_mux_sd_write_protect,
+	msm_mux_sdc40,
+	msm_mux_sdc41,
+	msm_mux_sdc42,
+	msm_mux_sdc43,
+	msm_mux_sdc4_clk,
+	msm_mux_sdc4_cmd,
+	msm_mux_tb_trig_sdc2,
+	msm_mux_tb_trig_sdc4,
+	msm_mux_tgu_ch0_trigout,
+	msm_mux_tgu_ch1_trigout,
+	msm_mux_tgu_ch2_trigout,
+	msm_mux_tgu_ch3_trigout,
+	msm_mux_tmess_prng0,
+	msm_mux_tmess_prng1,
+	msm_mux_tmess_prng2,
+	msm_mux_tmess_prng3,
+	msm_mux_tsense_pwm1,
+	msm_mux_tsense_pwm2,
+	msm_mux_tsense_pwm3,
+	msm_mux_uim0_clk,
+	msm_mux_uim0_data,
+	msm_mux_uim0_present,
+	msm_mux_uim0_reset,
+	msm_mux_uim1_clk,
+	msm_mux_uim1_data,
+	msm_mux_uim1_present,
+	msm_mux_uim1_reset,
+	msm_mux_usb1_hs,
+	msm_mux_usb_phy,
+	msm_mux_vfr_0,
+	msm_mux_vfr_1,
+	msm_mux_vsense_trigger_mirnat,
+	msm_mux__,
+};
+
+static const char *const gpio_groups[] = {
+	"gpio0",   "gpio1",   "gpio2",   "gpio3",
+	"gpio4",   "gpio5",   "gpio6",   "gpio7",
+	"gpio8",   "gpio9",   "gpio10",  "gpio11",
+	"gpio12",  "gpio13",  "gpio14",  "gpio15",
+	"gpio16",  "gpio17",  "gpio18",  "gpio19",
+	"gpio20",  "gpio21",  "gpio22",  "gpio23",
+	"gpio24",  "gpio25",  "gpio26",  "gpio27",
+	"gpio28",  "gpio29",  "gpio30",  "gpio31",
+	"gpio32",  "gpio33",  "gpio34",  "gpio35",
+	"gpio36",  "gpio37",  "gpio38",  "gpio39",
+	"gpio40",  "gpio41",  "gpio42",  "gpio43",
+	"gpio44",  "gpio45",  "gpio46",  "gpio47",
+	"gpio48",  "gpio49",  "gpio50",  "gpio51",
+	"gpio52",  "gpio53",  "gpio54",  "gpio55",
+	"gpio56",  "gpio57",  "gpio58",  "gpio59",
+	"gpio60",  "gpio61",  "gpio62",  "gpio63",
+	"gpio64",  "gpio65",  "gpio66",  "gpio67",
+	"gpio68",  "gpio69",  "gpio70",  "gpio71",
+	"gpio72",  "gpio73",  "gpio74",  "gpio75",
+	"gpio76",  "gpio77",  "gpio78",  "gpio79",
+	"gpio80",  "gpio81",  "gpio82",  "gpio83",
+	"gpio84",  "gpio85",  "gpio86",  "gpio87",
+	"gpio88",  "gpio89",  "gpio90",  "gpio91",
+	"gpio92",  "gpio93",  "gpio94",  "gpio95",
+	"gpio96",  "gpio97",  "gpio98",  "gpio99",
+	"gpio100", "gpio101", "gpio102", "gpio103",
+	"gpio104", "gpio105", "gpio106", "gpio107",
+	"gpio108", "gpio109", "gpio110", "gpio111",
+	"gpio112", "gpio113", "gpio114", "gpio115",
+	"gpio116", "gpio117", "gpio118", "gpio119",
+	"gpio120", "gpio121", "gpio122", "gpio123",
+	"gpio124", "gpio125", "gpio126", "gpio127",
+	"gpio128", "gpio129", "gpio130", "gpio131",
+	"gpio132", "gpio133", "gpio134", "gpio135",
+	"gpio136", "gpio137", "gpio138", "gpio139",
+	"gpio140", "gpio141", "gpio142", "gpio143",
+	"gpio144", "gpio145", "gpio146", "gpio147",
+	"gpio148", "gpio149", "gpio150", "gpio151",
+	"gpio152", "gpio153", "gpio154", "gpio155",
+	"gpio156", "gpio157", "gpio158", "gpio159",
+	"gpio160", "gpio161", "gpio162", "gpio163",
+	"gpio164", "gpio165", "gpio166", "gpio167",
+	"gpio168", "gpio169", "gpio170", "gpio171",
+	"gpio172", "gpio173", "gpio174", "gpio175",
+	"gpio176", "gpio177", "gpio178", "gpio179",
+	"gpio180", "gpio181", "gpio182", "gpio183",
+	"gpio184", "gpio185", "gpio186", "gpio187",
+	"gpio188", "gpio189", "gpio190", "gpio191",
+	"gpio192", "gpio193", "gpio194", "gpio195",
+	"gpio196", "gpio197", "gpio198", "gpio199",
+	"gpio200", "gpio201", "gpio202", "gpio203",
+	"gpio204", "gpio205", "gpio206", "gpio207",
+	"gpio208", "gpio209",
+};
+
+static const char * const egpio_groups[] = {
+	"gpio0",   "gpio1",   "gpio2",   "gpio3",   "gpio4",   "gpio5",
+	"gpio6",   "gpio7",   "gpio165", "gpio166", "gpio167", "gpio168",
+	"gpio169", "gpio170", "gpio171", "gpio172", "gpio173", "gpio174",
+	"gpio175", "gpio176", "gpio177", "gpio178", "gpio179", "gpio180",
+	"gpio181", "gpio182", "gpio183", "gpio184", "gpio185", "gpio186",
+	"gpio187", "gpio188", "gpio189", "gpio190", "gpio191", "gpio192",
+	"gpio193", "gpio194", "gpio195", "gpio196", "gpio197", "gpio198",
+	"gpio199", "gpio200", "gpio201", "gpio202", "gpio203", "gpio204",
+	"gpio205", "gpio206", "gpio207", "gpio208", "gpio209",
+};
+
+static const char * const aoss_cti_groups[] = {
+	"gpio50", "gpio51", "gpio60", "gpio61",
+};
+
+static const char *const atest_char_groups[] = {
+	"gpio130", "gpio131", "gpio132", "gpio133",
+	"gpio137",
+};
+
+static const char *const atest_usb_groups[] = {
+	"gpio71", "gpio72", "gpio74", "gpio130",
+	"gpio131",
+};
+
+static const char *const audio_ext_mclk0_groups[] = {
+	"gpio125",
+};
+
+static const char *const audio_ext_mclk1_groups[] = {
+	"gpio124",
+};
+
+static const char *const audio_ref_clk_groups[] = {
+	"gpio124",
+};
+
+static const char *const cam_aon_mclk2_groups[] = {
+	"gpio102",
+};
+
+static const char *const cam_aon_mclk4_groups[] = {
+	"gpio104",
+};
+
+static const char *const cam_mclk_groups[] = {
+	"gpio100", "gpio101", "gpio103", "gpio105",
+	"gpio106", "gpio108",
+};
+
+static const char *const cci_async_in_groups[] = {
+	"gpio15", "gpio163", "gpio164",
+};
+
+static const char *const cci_i2c_scl_groups[] = {
+	"gpio13",  "gpio114", "gpio116", "gpio118",
+	"gpio120", "gpio153",
+};
+
+static const char *const cci_i2c_sda_groups[] = {
+	"gpio12",  "gpio112", "gpio113", "gpio115",
+	"gpio117", "gpio119",
+};
+
+static const char *const cci_timer_groups[] = {
+	"gpio10", "gpio11", "gpio109", "gpio110",
+	"gpio111",
+};
+
+static const char *const cmu_rng_groups[] = {
+	"gpio95",  "gpio96", "gpio112", "gpio127",
+	"gpio122", "gpio128",
+};
+
+static const char *const coex_uart1_rx_groups[] = {
+	"gpio148",
+};
+
+static const char *const coex_uart1_tx_groups[] = {
+	"gpio149",
+};
+
+static const char *const coex_uart2_rx_groups[] = {
+	"gpio150",
+};
+
+static const char *const coex_uart2_tx_groups[] = {
+	"gpio151",
+};
+
+static const char *const cri_trng_groups[] = {
+	"gpio187",
+};
+
+static const char *const dbg_out_clk_groups[] = {
+	"gpio92",
+};
+
+static const char *const ddr_bist_complete_groups[] = {
+	"gpio44",
+};
+
+static const char *const ddr_bist_fail_groups[] = {
+	"gpio40",
+};
+
+static const char *const ddr_bist_start_groups[] = {
+	"gpio41",
+};
+
+static const char *const ddr_bist_stop_groups[] = {
+	"gpio45",
+};
+
+static const char *const ddr_pxi0_groups[] = {
+	"gpio75", "gpio76",
+};
+
+static const char *const ddr_pxi1_groups[] = {
+	"gpio44", "gpio45",
+};
+
+static const char *const ddr_pxi2_groups[] = {
+	"gpio51", "gpio62",
+};
+
+static const char *const ddr_pxi3_groups[] = {
+	"gpio46", "gpio47",
+};
+
+static const char *const do_not_groups[] = {
+	"gpio36", "gpio37", "gpio38", "gpio39",
+	"gpio134", "gpio135", "gpio136",
+};
+
+static const char *const dp_hot_groups[] = {
+	"gpio47",
+};
+
+static const char *const gcc_gp1_groups[] = {
+	"gpio86", "gpio134",
+};
+
+static const char *const gcc_gp2_groups[] = {
+	"gpio87", "gpio135",
+};
+
+static const char *const gcc_gp3_groups[] = {
+	"gpio88", "gpio136",
+};
+
+static const char *const gnss_adc0_groups[] = {
+	"gpio89", "gpio91",
+};
+
+static const char *const gnss_adc1_groups[] = {
+	"gpio90", "gpio92",
+};
+
+static const char *const i2chub0_se0_groups[] = {
+	"gpio64", "gpio65",
+};
+
+static const char *const i2chub0_se1_groups[] = {
+	"gpio66", "gpio67",
+};
+
+static const char *const i2chub0_se2_groups[] = {
+	"gpio68", "gpio69",
+};
+
+static const char *const i2chub0_se3_groups[] = {
+	"gpio70", "gpio71",
+};
+
+static const char *const i2chub0_se4_groups[] = {
+	"gpio72", "gpio73",
+};
+
+static const char *const i2chub0_se5_groups[] = {
+	"gpio74", "gpio75",
+};
+
+static const char *const i2chub0_se6_groups[] = {
+	"gpio76", "gpio77",
+};
+
+static const char *const i2chub0_se7_groups[] = {
+	"gpio78", "gpio79",
+};
+
+static const char *const i2chub0_se8_groups[] = {
+	"gpio206", "gpio207",
+};
+
+static const char *const i2chub0_se9_groups[] = {
+	"gpio80", "gpio81",
+};
+
+static const char *const i2s0_data0_groups[] = {
+	"gpio127",
+};
+
+static const char *const i2s0_data1_groups[] = {
+	"gpio128",
+};
+
+static const char *const i2s0_sck_groups[] = {
+	"gpio126",
+};
+
+static const char *const i2s0_ws_groups[] = {
+	"gpio129",
+};
+
+static const char *const i2s1_data0_groups[] = {
+	"gpio122",
+};
+
+static const char *const i2s1_data1_groups[] = {
+	"gpio124",
+};
+
+static const char *const i2s1_sck_groups[] = {
+	"gpio121",
+};
+
+static const char *const i2s1_ws_groups[] = {
+	"gpio123",
+};
+
+static const char *const ibi_i3c_groups[] = {
+	"gpio0",  "gpio1",  "gpio4",  "gpio5",
+	"gpio8",  "gpio9",  "gpio12", "gpio13",
+	"gpio32", "gpio33", "gpio36", "gpio37",
+	"gpio48", "gpio49", "gpio56", "gpio57",
+};
+
+static const char *const jitter_bist_groups[] = {
+	"gpio73",
+};
+
+static const char *const mdp_vsync_groups[] = {
+	"gpio86", "gpio87", "gpio133", "gpio137",
+};
+
+static const char *const mdp_vsync0_out_groups[] = {
+	"gpio86",
+};
+
+static const char *const mdp_vsync1_out_groups[] = {
+	"gpio86",
+};
+
+static const char *const mdp_vsync2_out_groups[] = {
+	"gpio87",
+};
+
+static const char *const mdp_vsync3_out_groups[] = {
+	"gpio87",
+};
+
+static const char *const mdp_vsync_e_groups[] = {
+	"gpio88",
+};
+
+static const char *const nav_gpio0_groups[] = {
+	"gpio154",
+};
+
+static const char *const nav_gpio1_groups[] = {
+	"gpio155",
+};
+
+static const char *const nav_gpio2_groups[] = {
+	"gpio152",
+};
+
+static const char *const nav_gpio3_groups[] = {
+	"gpio154",
+};
+
+static const char *const pcie0_clk_req_n_groups[] = {
+	"gpio95",
+};
+
+static const char *const pcie1_clk_req_n_groups[] = {
+	"gpio98",
+};
+
+static const char *const phase_flag_groups[] = {
+	"gpio0",   "gpio1",   "gpio3",   "gpio4",
+	"gpio5",   "gpio7",   "gpio8",   "gpio9",
+	"gpio11",  "gpio12",  "gpio13",  "gpio15",
+	"gpio16",  "gpio17",  "gpio19",  "gpio94",
+	"gpio95",  "gpio96",  "gpio109", "gpio111",
+	"gpio112", "gpio113", "gpio114", "gpio115",
+	"gpio116", "gpio117", "gpio118", "gpio119",
+	"gpio120", "gpio153", "gpio163", "gpio164",
+};
+
+static const char *const pll_bist_sync_groups[] = {
+	"gpio68",
+};
+
+static const char *const pll_clk_aux_groups[] = {
+	"gpio106",
+};
+
+static const char *const prng_rosc0_groups[] = {
+	"gpio186",
+};
+
+static const char *const prng_rosc1_groups[] = {
+	"gpio183",
+};
+
+static const char *const prng_rosc2_groups[] = {
+	"gpio182",
+};
+
+static const char *const prng_rosc3_groups[] = {
+	"gpio181",
+};
+
+static const char *const qdss_cti_groups[] = {
+	"gpio27", "gpio31", "gpio78",  "gpio79",
+	"gpio82", "gpio83", "gpio159", "gpio162",
+};
+
+static const char *const qdss_gpio_groups[] = {
+	"gpio3",   "gpio7",   "gpio8",   "gpio13",
+	"gpio15",  "gpio100", "gpio101", "gpio102",
+	"gpio103", "gpio104", "gpio105", "gpio113",
+	"gpio114", "gpio115", "gpio116", "gpio117",
+	"gpio118", "gpio140", "gpio141", "gpio142",
+	"gpio143", "gpio144", "gpio145", "gpio146",
+	"gpio147", "gpio148", "gpio149", "gpio150",
+	"gpio151", "gpio152", "gpio153", "gpio154",
+	"gpio155", "gpio156", "gpio157", "gpio158",
+};
+
+static const char *const qlink_big_enable_groups[] = {
+	"gpio160",
+};
+
+static const char *const qlink_big_request_groups[] = {
+	"gpio159",
+};
+
+static const char *const qlink_little_enable_groups[] = {
+	"gpio157",
+};
+
+static const char *const qlink_little_request_groups[] = {
+	"gpio156",
+};
+
+static const char *const qlink_wmss_groups[] = {
+	"gpio158",
+};
+
+static const char *const qspi0_groups[] = {
+	"gpio134",
+};
+
+static const char *const qspi1_groups[] = {
+	"gpio136",
+};
+
+static const char *const qspi2_groups[] = {
+	"gpio56",
+};
+
+static const char *const qspi3_groups[] = {
+	"gpio57",
+};
+
+static const char *const qspi_clk_groups[] = {
+	"gpio135",
+};
+
+static const char *const qspi_cs_groups[] = {
+	"gpio58", "gpio59",
+};
+
+static const char *const qup1_se0_groups[] = {
+	"gpio32", "gpio33", "gpio34", "gpio35",
+};
+
+static const char *const qup1_se1_groups[] = {
+	"gpio36", "gpio37", "gpio38", "gpio39",
+};
+
+static const char *const qup1_se2_groups[] = {
+	"gpio40", "gpio41", "gpio42", "gpio43",
+	"gpio44", "gpio45", "gpio46",
+};
+
+static const char *const qup1_se3_groups[] = {
+	"gpio44", "gpio45", "gpio46", "gpio47",
+};
+
+static const char *const qup1_se4_groups[] = {
+	"gpio48", "gpio49", "gpio50", "gpio51",
+};
+
+static const char *const qup1_se5_groups[] = {
+	"gpio52", "gpio53", "gpio54", "gpio55",
+};
+
+static const char *const qup1_se6_groups[] = {
+	"gpio56", "gpio57", "gpio58", "gpio59",
+};
+
+static const char *const qup1_se7_groups[] = {
+	"gpio60", "gpio61", "gpio62", "gpio63",
+};
+
+static const char *const qup2_se0_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3",
+};
+
+static const char *const qup2_se1_groups[] = {
+	"gpio4", "gpio5", "gpio6", "gpio7",
+};
+
+static const char *const qup2_se2_groups[] = {
+	"gpio8",  "gpio9",  "gpio10", "gpio11",
+	"gpio13", "gpio15", "gpio12",
+};
+
+static const char *const qup2_se3_groups[] = {
+	"gpio12", "gpio13", "gpio14", "gpio15",
+};
+
+static const char *const qup2_se4_groups[] = {
+	"gpio16", "gpio17", "gpio18", "gpio19",
+};
+
+static const char *const qup2_se5_groups[] = {
+	"gpio20", "gpio21", "gpio22", "gpio23",
+	"gpio23",
+};
+
+static const char *const qup2_se6_groups[] = {
+	"gpio24", "gpio25", "gpio26", "gpio27",
+};
+
+static const char *const qup2_se7_groups[] = {
+	"gpio28", "gpio29", "gpio30", "gpio31",
+};
+
+static const char *const sd_write_protect_groups[] = {
+	"gpio93",
+};
+
+static const char *const sdc40_groups[] = {
+	"gpio134",
+};
+
+static const char *const sdc41_groups[] = {
+	"gpio136",
+};
+
+static const char *const sdc42_groups[] = {
+	"gpio56",
+};
+
+static const char *const sdc43_groups[] = {
+	"gpio57",
+};
+
+static const char *const sdc4_clk_groups[] = {
+	"gpio135",
+};
+
+static const char *const sdc4_cmd_groups[] = {
+	"gpio59",
+};
+
+static const char *const tb_trig_sdc2_groups[] = {
+	"gpio8",
+};
+
+static const char *const tb_trig_sdc4_groups[] = {
+	"gpio58",
+};
+
+static const char *const tgu_ch0_trigout_groups[] = {
+	"gpio8",
+};
+
+static const char *const tgu_ch1_trigout_groups[] = {
+	"gpio9",
+};
+
+static const char *const tgu_ch2_trigout_groups[] = {
+	"gpio10",
+};
+
+static const char *const tgu_ch3_trigout_groups[] = {
+	"gpio11",
+};
+
+static const char *const tmess_prng0_groups[] = {
+	"gpio94",
+};
+
+static const char *const tmess_prng1_groups[] = {
+	"gpio95",
+};
+
+static const char *const tmess_prng2_groups[] = {
+	"gpio96",
+};
+
+static const char *const tmess_prng3_groups[] = {
+	"gpio109",
+};
+
+static const char *const tsense_pwm1_groups[] = {
+	"gpio58",
+};
+
+static const char *const tsense_pwm2_groups[] = {
+	"gpio58",
+};
+
+static const char *const tsense_pwm3_groups[] = {
+	"gpio58",
+};
+
+static const char *const uim0_clk_groups[] = {
+	"gpio131",
+};
+
+static const char *const uim0_data_groups[] = {
+	"gpio130",
+};
+
+static const char *const uim0_present_groups[] = {
+	"gpio47",
+};
+
+static const char *const uim0_reset_groups[] = {
+	"gpio132",
+};
+
+static const char *const uim1_clk_groups[] = {
+	"gpio135",
+};
+
+static const char *const uim1_data_groups[] = {
+	"gpio134",
+};
+
+static const char *const uim1_present_groups[] = {
+	"gpio76",
+};
+
+static const char *const uim1_reset_groups[] = {
+	"gpio136",
+};
+
+static const char *const usb1_hs_groups[] = {
+	"gpio89",
+};
+
+static const char *const usb_phy_groups[] = {
+	"gpio29", "gpio54",
+};
+
+static const char *const vfr_0_groups[] = {
+	"gpio150",
+};
+
+static const char *const vfr_1_groups[] = {
+	"gpio155",
+};
+
+static const char *const vsense_trigger_mirnat_groups[] = {
+	"gpio60",
+};
+
+static const struct pinfunction sm8650_functions[] = {
+	MSM_PIN_FUNCTION(gpio),
+	MSM_PIN_FUNCTION(aoss_cti),
+	MSM_PIN_FUNCTION(atest_char),
+	MSM_PIN_FUNCTION(atest_usb),
+	MSM_PIN_FUNCTION(audio_ext_mclk0),
+	MSM_PIN_FUNCTION(audio_ext_mclk1),
+	MSM_PIN_FUNCTION(audio_ref_clk),
+	MSM_PIN_FUNCTION(cam_aon_mclk2),
+	MSM_PIN_FUNCTION(cam_aon_mclk4),
+	MSM_PIN_FUNCTION(cam_mclk),
+	MSM_PIN_FUNCTION(cci_async_in),
+	MSM_PIN_FUNCTION(cci_i2c_scl),
+	MSM_PIN_FUNCTION(cci_i2c_sda),
+	MSM_PIN_FUNCTION(cci_timer),
+	MSM_PIN_FUNCTION(cmu_rng),
+	MSM_PIN_FUNCTION(coex_uart1_rx),
+	MSM_PIN_FUNCTION(coex_uart1_tx),
+	MSM_PIN_FUNCTION(coex_uart2_rx),
+	MSM_PIN_FUNCTION(coex_uart2_tx),
+	MSM_PIN_FUNCTION(cri_trng),
+	MSM_PIN_FUNCTION(dbg_out_clk),
+	MSM_PIN_FUNCTION(ddr_bist_complete),
+	MSM_PIN_FUNCTION(ddr_bist_fail),
+	MSM_PIN_FUNCTION(ddr_bist_start),
+	MSM_PIN_FUNCTION(ddr_bist_stop),
+	MSM_PIN_FUNCTION(ddr_pxi0),
+	MSM_PIN_FUNCTION(ddr_pxi1),
+	MSM_PIN_FUNCTION(ddr_pxi2),
+	MSM_PIN_FUNCTION(ddr_pxi3),
+	MSM_PIN_FUNCTION(do_not),
+	MSM_PIN_FUNCTION(dp_hot),
+	MSM_PIN_FUNCTION(egpio),
+	MSM_PIN_FUNCTION(gcc_gp1),
+	MSM_PIN_FUNCTION(gcc_gp2),
+	MSM_PIN_FUNCTION(gcc_gp3),
+	MSM_PIN_FUNCTION(gnss_adc0),
+	MSM_PIN_FUNCTION(gnss_adc1),
+	MSM_PIN_FUNCTION(i2chub0_se0),
+	MSM_PIN_FUNCTION(i2chub0_se1),
+	MSM_PIN_FUNCTION(i2chub0_se2),
+	MSM_PIN_FUNCTION(i2chub0_se3),
+	MSM_PIN_FUNCTION(i2chub0_se4),
+	MSM_PIN_FUNCTION(i2chub0_se5),
+	MSM_PIN_FUNCTION(i2chub0_se6),
+	MSM_PIN_FUNCTION(i2chub0_se7),
+	MSM_PIN_FUNCTION(i2chub0_se8),
+	MSM_PIN_FUNCTION(i2chub0_se9),
+	MSM_PIN_FUNCTION(i2s0_data0),
+	MSM_PIN_FUNCTION(i2s0_data1),
+	MSM_PIN_FUNCTION(i2s0_sck),
+	MSM_PIN_FUNCTION(i2s0_ws),
+	MSM_PIN_FUNCTION(i2s1_data0),
+	MSM_PIN_FUNCTION(i2s1_data1),
+	MSM_PIN_FUNCTION(i2s1_sck),
+	MSM_PIN_FUNCTION(i2s1_ws),
+	MSM_PIN_FUNCTION(ibi_i3c),
+	MSM_PIN_FUNCTION(jitter_bist),
+	MSM_PIN_FUNCTION(mdp_vsync),
+	MSM_PIN_FUNCTION(mdp_vsync0_out),
+	MSM_PIN_FUNCTION(mdp_vsync1_out),
+	MSM_PIN_FUNCTION(mdp_vsync2_out),
+	MSM_PIN_FUNCTION(mdp_vsync3_out),
+	MSM_PIN_FUNCTION(mdp_vsync_e),
+	MSM_PIN_FUNCTION(nav_gpio0),
+	MSM_PIN_FUNCTION(nav_gpio1),
+	MSM_PIN_FUNCTION(nav_gpio2),
+	MSM_PIN_FUNCTION(nav_gpio3),
+	MSM_PIN_FUNCTION(pcie0_clk_req_n),
+	MSM_PIN_FUNCTION(pcie1_clk_req_n),
+	MSM_PIN_FUNCTION(phase_flag),
+	MSM_PIN_FUNCTION(pll_bist_sync),
+	MSM_PIN_FUNCTION(pll_clk_aux),
+	MSM_PIN_FUNCTION(prng_rosc0),
+	MSM_PIN_FUNCTION(prng_rosc1),
+	MSM_PIN_FUNCTION(prng_rosc2),
+	MSM_PIN_FUNCTION(prng_rosc3),
+	MSM_PIN_FUNCTION(qdss_cti),
+	MSM_PIN_FUNCTION(qdss_gpio),
+	MSM_PIN_FUNCTION(qlink_big_enable),
+	MSM_PIN_FUNCTION(qlink_big_request),
+	MSM_PIN_FUNCTION(qlink_little_enable),
+	MSM_PIN_FUNCTION(qlink_little_request),
+	MSM_PIN_FUNCTION(qlink_wmss),
+	MSM_PIN_FUNCTION(qspi0),
+	MSM_PIN_FUNCTION(qspi1),
+	MSM_PIN_FUNCTION(qspi2),
+	MSM_PIN_FUNCTION(qspi3),
+	MSM_PIN_FUNCTION(qspi_clk),
+	MSM_PIN_FUNCTION(qspi_cs),
+	MSM_PIN_FUNCTION(qup1_se0),
+	MSM_PIN_FUNCTION(qup1_se1),
+	MSM_PIN_FUNCTION(qup1_se2),
+	MSM_PIN_FUNCTION(qup1_se3),
+	MSM_PIN_FUNCTION(qup1_se4),
+	MSM_PIN_FUNCTION(qup1_se5),
+	MSM_PIN_FUNCTION(qup1_se6),
+	MSM_PIN_FUNCTION(qup1_se7),
+	MSM_PIN_FUNCTION(qup2_se0),
+	MSM_PIN_FUNCTION(qup2_se1),
+	MSM_PIN_FUNCTION(qup2_se2),
+	MSM_PIN_FUNCTION(qup2_se3),
+	MSM_PIN_FUNCTION(qup2_se4),
+	MSM_PIN_FUNCTION(qup2_se5),
+	MSM_PIN_FUNCTION(qup2_se6),
+	MSM_PIN_FUNCTION(qup2_se7),
+	MSM_PIN_FUNCTION(sd_write_protect),
+	MSM_PIN_FUNCTION(sdc40),
+	MSM_PIN_FUNCTION(sdc41),
+	MSM_PIN_FUNCTION(sdc42),
+	MSM_PIN_FUNCTION(sdc43),
+	MSM_PIN_FUNCTION(sdc4_clk),
+	MSM_PIN_FUNCTION(sdc4_cmd),
+	MSM_PIN_FUNCTION(tb_trig_sdc2),
+	MSM_PIN_FUNCTION(tb_trig_sdc4),
+	MSM_PIN_FUNCTION(tgu_ch0_trigout),
+	MSM_PIN_FUNCTION(tgu_ch1_trigout),
+	MSM_PIN_FUNCTION(tgu_ch2_trigout),
+	MSM_PIN_FUNCTION(tgu_ch3_trigout),
+	MSM_PIN_FUNCTION(tmess_prng0),
+	MSM_PIN_FUNCTION(tmess_prng1),
+	MSM_PIN_FUNCTION(tmess_prng2),
+	MSM_PIN_FUNCTION(tmess_prng3),
+	MSM_PIN_FUNCTION(tsense_pwm1),
+	MSM_PIN_FUNCTION(tsense_pwm2),
+	MSM_PIN_FUNCTION(tsense_pwm3),
+	MSM_PIN_FUNCTION(uim0_clk),
+	MSM_PIN_FUNCTION(uim0_data),
+	MSM_PIN_FUNCTION(uim0_present),
+	MSM_PIN_FUNCTION(uim0_reset),
+	MSM_PIN_FUNCTION(uim1_clk),
+	MSM_PIN_FUNCTION(uim1_data),
+	MSM_PIN_FUNCTION(uim1_present),
+	MSM_PIN_FUNCTION(uim1_reset),
+	MSM_PIN_FUNCTION(usb1_hs),
+	MSM_PIN_FUNCTION(usb_phy),
+	MSM_PIN_FUNCTION(vfr_0),
+	MSM_PIN_FUNCTION(vfr_1),
+	MSM_PIN_FUNCTION(vsense_trigger_mirnat),
+};
+
+/*
+ * Every pin is maintained as a single group, and missing or non-existing pin
+ * would be maintained as dummy group to synchronize pin group index with
+ * pin descriptor registered with pinctrl core.
+ * Clients would not be able to request these dummy pin groups.
+ */
+static const struct msm_pingroup sm8650_groups[] = {
+	[0] = PINGROUP(0, qup2_se0, ibi_i3c, phase_flag, _, _, _, _, _, _, egpio),
+	[1] = PINGROUP(1, qup2_se0, ibi_i3c, phase_flag, _, _, _, _, _, _, egpio),
+	[2] = PINGROUP(2, qup2_se0, _, _, _, _, _, _, _, _, egpio),
+	[3] = PINGROUP(3, qup2_se0, phase_flag, _, qdss_gpio, _, _, _, _, _, egpio),
+	[4] = PINGROUP(4, qup2_se1, ibi_i3c, phase_flag, _, _, _, _, _, _, egpio),
+	[5] = PINGROUP(5, qup2_se1, ibi_i3c, phase_flag, _, _, _, _, _, _, egpio),
+	[6] = PINGROUP(6, qup2_se1, _, _, _, _, _, _, _, _, egpio),
+	[7] = PINGROUP(7, qup2_se1, phase_flag, _, qdss_gpio, _, _, _, _, _, egpio),
+	[8] = PINGROUP(8, qup2_se2, ibi_i3c, tb_trig_sdc2, phase_flag, tgu_ch0_trigout, _, qdss_gpio, _, _, _),
+	[9] = PINGROUP(9, qup2_se2, ibi_i3c, phase_flag, tgu_ch1_trigout, _, _, _, _, _, _),
+	[10] = PINGROUP(10, qup2_se2, cci_timer, tgu_ch2_trigout, _, _, _, _, _, _, _),
+	[11] = PINGROUP(11, qup2_se2, cci_timer, phase_flag, tgu_ch3_trigout, _, _, _, _, _, _),
+	[12] = PINGROUP(12, qup2_se3, cci_i2c_sda, ibi_i3c, qup2_se2, phase_flag, _, _, _, _, _),
+	[13] = PINGROUP(13, qup2_se3, cci_i2c_scl, ibi_i3c, qup2_se2, phase_flag, _, qdss_gpio, _, _, _),
+	[14] = PINGROUP(14, qup2_se3, _, _, _, _, _, _, _, _, _),
+	[15] = PINGROUP(15, qup2_se3, cci_async_in, qup2_se2, phase_flag, _, qdss_gpio, _, _, _, _),
+	[16] = PINGROUP(16, qup2_se4, phase_flag, _, _, _, _, _, _, _, _),
+	[17] = PINGROUP(17, qup2_se4, phase_flag, _, _, _, _, _, _, _, _),
+	[18] = PINGROUP(18, qup2_se4, _, _, _, _, _, _, _, _, _),
+	[19] = PINGROUP(19, qup2_se4, phase_flag, _, _, _, _, _, _, _, _),
+	[20] = PINGROUP(20, qup2_se5, _, _, _, _, _, _, _, _, _),
+	[21] = PINGROUP(21, qup2_se5, _, _, _, _, _, _, _, _, _),
+	[22] = PINGROUP(22, qup2_se5, _, _, _, _, _, _, _, _, _),
+	[23] = PINGROUP(23, qup2_se5, qup2_se5, _, _, _, _, _, _, _, _),
+	[24] = PINGROUP(24, qup2_se6, _, _, _, _, _, _, _, _, _),
+	[25] = PINGROUP(25, qup2_se6, _, _, _, _, _, _, _, _, _),
+	[26] = PINGROUP(26, qup2_se6, _, _, _, _, _, _, _, _, _),
+	[27] = PINGROUP(27, qup2_se6, qdss_cti, _, _, _, _, _, _, _, _),
+	[28] = PINGROUP(28, qup2_se7, _, _, _, _, _, _, _, _, _),
+	[29] = PINGROUP(29, qup2_se7, usb_phy, _, _, _, _, _, _, _, _),
+	[30] = PINGROUP(30, qup2_se7, _, _, _, _, _, _, _, _, _),
+	[31] = PINGROUP(31, qup2_se7, qdss_cti, _, _, _, _, _, _, _, _),
+	[32] = PINGROUP(32, qup1_se0, ibi_i3c, _, _, _, _, _, _, _, _),
+	[33] = PINGROUP(33, qup1_se0, ibi_i3c, _, _, _, _, _, _, _, _),
+	[34] = PINGROUP(34, qup1_se0, _, _, _, _, _, _, _, _, _),
+	[35] = PINGROUP(35, qup1_se0, _, _, _, _, _, _, _, _, _),
+	[36] = PINGROUP(36, qup1_se1, do_not, ibi_i3c, _, _, _, _, _, _, _),
+	[37] = PINGROUP(37, qup1_se1, do_not, ibi_i3c, _, _, _, _, _, _, _),
+	[38] = PINGROUP(38, qup1_se1, do_not, _, _, _, _, _, _, _, _),
+	[39] = PINGROUP(39, qup1_se1, do_not, _, _, _, _, _, _, _, _),
+	[40] = PINGROUP(40, qup1_se2, ddr_bist_fail, _, _, _, _, _, _, _, _),
+	[41] = PINGROUP(41, qup1_se2, ddr_bist_start, _, _, _, _, _, _, _, _),
+	[42] = PINGROUP(42, qup1_se2, _, _, _, _, _, _, _, _, _),
+	[43] = PINGROUP(43, qup1_se2, _, _, _, _, _, _, _, _, _),
+	[44] = PINGROUP(44, qup1_se3, qup1_se2, ddr_bist_complete, ddr_pxi1, _, _, _, _, _, _),
+	[45] = PINGROUP(45, qup1_se3, qup1_se2, ddr_bist_stop, ddr_pxi1, _, _, _, _, _, _),
+	[46] = PINGROUP(46, qup1_se3, qup1_se2, ddr_pxi3, _, _, _, _, _, _, _),
+	[47] = PINGROUP(47, qup1_se3, uim0_present, dp_hot, ddr_pxi3, _, _, _, _, _, _),
+	[48] = PINGROUP(48, qup1_se4, ibi_i3c, _, _, _, _, _, _, _, _),
+	[49] = PINGROUP(49, qup1_se4, ibi_i3c, _, _, _, _, _, _, _, _),
+	[50] = PINGROUP(50, qup1_se4, aoss_cti, _, _, _, _, _, _, _, _),
+	[51] = PINGROUP(51, qup1_se4, aoss_cti, ddr_pxi2, _, _, _, _, _, _, _),
+	[52] = PINGROUP(52, qup1_se5, _, _, _, _, _, _, _, _, _),
+	[53] = PINGROUP(53, qup1_se5, _, _, _, _, _, _, _, _, _),
+	[54] = PINGROUP(54, qup1_se5, usb_phy, _, _, _, _, _, _, _, _),
+	[55] = PINGROUP(55, qup1_se5, _, _, _, _, _, _, _, _, _),
+	[56] = PINGROUP(56, qup1_se6, ibi_i3c, qspi2, sdc42, _, _, _, _, _, _),
+	[57] = PINGROUP(57, qup1_se6, ibi_i3c, qspi3, sdc43, _, _, _, _, _, _),
+	[58] = PINGROUP(58, qup1_se6, qspi_cs, tb_trig_sdc4, tsense_pwm1, tsense_pwm2, tsense_pwm3, _, _, _, _),
+	[59] = PINGROUP(59, qup1_se6, _, qspi_cs, sdc4_cmd, _, _, _, _, _, _),
+	[60] = PINGROUP(60, qup1_se7, aoss_cti, vsense_trigger_mirnat, _, _, _, _, _, _, _),
+	[61] = PINGROUP(61, qup1_se7, aoss_cti, _, _, _, _, _, _, _, _),
+	[62] = PINGROUP(62, qup1_se7, ddr_pxi2, _, _, _, _, _, _, _, _),
+	[63] = PINGROUP(63, qup1_se7, _, _, _, _, _, _, _, _, _),
+	[64] = PINGROUP(64, i2chub0_se0, _, _, _, _, _, _, _, _, _),
+	[65] = PINGROUP(65, i2chub0_se0, _, _, _, _, _, _, _, _, _),
+	[66] = PINGROUP(66, i2chub0_se1, _, _, _, _, _, _, _, _, _),
+	[67] = PINGROUP(67, i2chub0_se1, _, _, _, _, _, _, _, _, _),
+	[68] = PINGROUP(68, i2chub0_se2, pll_bist_sync, _, _, _, _, _, _, _, _),
+	[69] = PINGROUP(69, i2chub0_se2, _, _, _, _, _, _, _, _, _),
+	[70] = PINGROUP(70, i2chub0_se3, _, _, _, _, _, _, _, _, _),
+	[71] = PINGROUP(71, i2chub0_se3, _, atest_usb, _, _, _, _, _, _, _),
+	[72] = PINGROUP(72, i2chub0_se4, _, atest_usb, _, _, _, _, _, _, _),
+	[73] = PINGROUP(73, i2chub0_se4, jitter_bist, _, _, _, _, _, _, _, _),
+	[74] = PINGROUP(74, i2chub0_se5, atest_usb, _, _, _, _, _, _, _, _),
+	[75] = PINGROUP(75, i2chub0_se5, ddr_pxi0, _, _, _, _, _, _, _, _),
+	[76] = PINGROUP(76, i2chub0_se6, ddr_pxi0, uim1_present, _, _, _, _, _, _, _),
+	[77] = PINGROUP(77, i2chub0_se6, _, _, _, _, _, _, _, _, _),
+	[78] = PINGROUP(78, i2chub0_se7, qdss_cti, _, _, _, _, _, _, _, _),
+	[79] = PINGROUP(79, i2chub0_se7, qdss_cti, _, _, _, _, _, _, _, _),
+	[80] = PINGROUP(80, i2chub0_se9, _, _, _, _, _, _, _, _, _),
+	[81] = PINGROUP(81, i2chub0_se9, _, _, _, _, _, _, _, _, _),
+	[82] = PINGROUP(82, qdss_cti, _, _, _, _, _, _, _, _, _),
+	[83] = PINGROUP(83, qdss_cti, _, _, _, _, _, _, _, _, _),
+	[84] = PINGROUP(84, _, _, _, _, _, _, _, _, _, _),
+	[85] = PINGROUP(85, _, _, _, _, _, _, _, _, _, _),
+	[86] = PINGROUP(86, mdp_vsync, mdp_vsync0_out, mdp_vsync1_out, gcc_gp1, _, _, _, _, _, _),
+	[87] = PINGROUP(87, mdp_vsync, mdp_vsync2_out, mdp_vsync3_out, gcc_gp2, _, _, _, _, _, _),
+	[88] = PINGROUP(88, mdp_vsync_e, gcc_gp3, _, _, _, _, _, _, _, _),
+	[89] = PINGROUP(89, usb1_hs, gnss_adc0, _, _, _, _, _, _, _, _),
+	[90] = PINGROUP(90, gnss_adc1, _, _, _, _, _, _, _, _, _),
+	[91] = PINGROUP(91, _, gnss_adc0, _, _, _, _, _, _, _, _),
+	[92] = PINGROUP(92, dbg_out_clk, gnss_adc1, _, _, _, _, _, _, _, _),
+	[93] = PINGROUP(93, sd_write_protect, _, _, _, _, _, _, _, _, _),
+	[94] = PINGROUP(94, cmu_rng, phase_flag, tmess_prng0, _, _, _, _, _, _, _),
+	[95] = PINGROUP(95, pcie0_clk_req_n, cmu_rng, phase_flag, tmess_prng1, _, _, _, _, _, _),
+	[96] = PINGROUP(96, cmu_rng, phase_flag, tmess_prng2, _, _, _, _, _, _, _),
+	[97] = PINGROUP(97, _, _, _, _, _, _, _, _, _, _),
+	[98] = PINGROUP(98, pcie1_clk_req_n, _, _, _, _, _, _, _, _, _),
+	[99] = PINGROUP(99, _, _, _, _, _, _, _, _, _, _),
+	[100] = PINGROUP(100, cam_mclk, qdss_gpio, _, _, _, _, _, _, _, _),
+	[101] = PINGROUP(101, cam_mclk, qdss_gpio, _, _, _, _, _, _, _, _),
+	[102] = PINGROUP(102, cam_aon_mclk2, qdss_gpio, _, _, _, _, _, _, _, _),
+	[103] = PINGROUP(103, cam_mclk, qdss_gpio, _, _, _, _, _, _, _, _),
+	[104] = PINGROUP(104, cam_aon_mclk4, qdss_gpio, _, _, _, _, _, _, _, _),
+	[105] = PINGROUP(105, cam_mclk, qdss_gpio, _, _, _, _, _, _, _, _),
+	[106] = PINGROUP(106, cam_mclk, pll_clk_aux, _, _, _, _, _, _, _, _),
+	[107] = PINGROUP(107, _, _, _, _, _, _, _, _, _, _),
+	[108] = PINGROUP(108, cam_mclk, _, _, _, _, _, _, _, _, _),
+	[109] = PINGROUP(109, cci_timer, phase_flag, tmess_prng3, _, _, _, _, _, _, _),
+	[110] = PINGROUP(110, cci_timer, _, _, _, _, _, _, _, _, _),
+	[111] = PINGROUP(111, cci_timer, phase_flag, _, _, _, _, _, _, _, _),
+	[112] = PINGROUP(112, cci_i2c_sda, cmu_rng, phase_flag, _, _, _, _, _, _, _),
+	[113] = PINGROUP(113, cci_i2c_sda, phase_flag, _, qdss_gpio, _, _, _, _, _, _),
+	[114] = PINGROUP(114, cci_i2c_scl, phase_flag, _, qdss_gpio, _, _, _, _, _, _),
+	[115] = PINGROUP(115, cci_i2c_sda, phase_flag, _, qdss_gpio, _, _, _, _, _, _),
+	[116] = PINGROUP(116, cci_i2c_scl, phase_flag, _, qdss_gpio, _, _, _, _, _, _),
+	[117] = PINGROUP(117, cci_i2c_sda, phase_flag, _, qdss_gpio, _, _, _, _, _, _),
+	[118] = PINGROUP(118, cci_i2c_scl, phase_flag, _, qdss_gpio, _, _, _, _, _, _),
+	[119] = PINGROUP(119, cci_i2c_sda, phase_flag, _, _, _, _, _, _, _, _),
+	[120] = PINGROUP(120, cci_i2c_scl, phase_flag, _, _, _, _, _, _, _, _),
+	[121] = PINGROUP(121, i2s1_sck, _, _, _, _, _, _, _, _, _),
+	[122] = PINGROUP(122, i2s1_data0, cmu_rng, _, _, _, _, _, _, _, _),
+	[123] = PINGROUP(123, i2s1_ws, _, _, _, _, _, _, _, _, _),
+	[124] = PINGROUP(124, i2s1_data1, audio_ext_mclk1, audio_ref_clk, _, _, _, _, _, _, _),
+	[125] = PINGROUP(125, audio_ext_mclk0, _, _, _, _, _, _, _, _, _),
+	[126] = PINGROUP(126, i2s0_sck, _, _, _, _, _, _, _, _, _),
+	[127] = PINGROUP(127, i2s0_data0, cmu_rng, _, _, _, _, _, _, _, _),
+	[128] = PINGROUP(128, i2s0_data1, cmu_rng, _, _, _, _, _, _, _, _),
+	[129] = PINGROUP(129, i2s0_ws, cmu_rng, _, _, _, _, _, _, _, _),
+	[130] = PINGROUP(130, uim0_data, atest_usb, atest_char, _, _, _, _, _, _, _),
+	[131] = PINGROUP(131, uim0_clk, atest_usb, atest_char, _, _, _, _, _, _, _),
+	[132] = PINGROUP(132, uim0_reset, atest_char, _, _, _, _, _, _, _, _),
+	[133] = PINGROUP(133, mdp_vsync, atest_char, _, _, _, _, _, _, _, _),
+	[134] = PINGROUP(134, uim1_data, do_not, qspi0, sdc40, gcc_gp1, _, _, _, _, _),
+	[135] = PINGROUP(135, uim1_clk, do_not, qspi_clk, sdc4_clk, gcc_gp2, _, _, _, _, _),
+	[136] = PINGROUP(136, uim1_reset, do_not, qspi1, sdc41, gcc_gp3, _, _, _, _, _),
+	[137] = PINGROUP(137, mdp_vsync, atest_char, _, _, _, _, _, _, _, _),
+	[138] = PINGROUP(138, _, _, _, _, _, _, _, _, _, _),
+	[139] = PINGROUP(139, _, _, _, _, _, _, _, _, _, _),
+	[140] = PINGROUP(140, _, _, qdss_gpio, _, _, _, _, _, _, _),
+	[141] = PINGROUP(141, _, _, qdss_gpio, _, _, _, _, _, _, _),
+	[142] = PINGROUP(142, _, _, qdss_gpio, _, _, _, _, _, _, _),
+	[143] = PINGROUP(143, _, _, qdss_gpio, _, _, _, _, _, _, _),
+	[144] = PINGROUP(144, _, qdss_gpio, _, _, _, _, _, _, _, _),
+	[145] = PINGROUP(145, _, qdss_gpio, _, _, _, _, _, _, _, _),
+	[146] = PINGROUP(146, _, qdss_gpio, _, _, _, _, _, _, _, _),
+	[147] = PINGROUP(147, _, qdss_gpio, _, _, _, _, _, _, _, _),
+	[148] = PINGROUP(148, coex_uart1_rx, qdss_gpio, _, _, _, _, _, _, _, _),
+	[149] = PINGROUP(149, coex_uart1_tx, qdss_gpio, _, _, _, _, _, _, _, _),
+	[150] = PINGROUP(150, _, vfr_0, coex_uart2_rx, qdss_gpio, _, _, _, _, _, _),
+	[151] = PINGROUP(151, _, coex_uart2_tx, qdss_gpio, _, _, _, _, _, _, _),
+	[152] = PINGROUP(152, nav_gpio2, _, qdss_gpio, _, _, _, _, _, _, _),
+	[153] = PINGROUP(153, cci_i2c_scl, phase_flag, _, qdss_gpio, _, _, _, _, _, _),
+	[154] = PINGROUP(154, nav_gpio0, nav_gpio3, qdss_gpio, _, _, _, _, _, _, _),
+	[155] = PINGROUP(155, nav_gpio1, vfr_1, qdss_gpio, _, _, _, _, _, _, _),
+	[156] = PINGROUP(156, qlink_little_request, qdss_gpio, _, _, _, _, _, _, _, _),
+	[157] = PINGROUP(157, qlink_little_enable, qdss_gpio, _, _, _, _, _, _, _, _),
+	[158] = PINGROUP(158, qlink_wmss, qdss_gpio, _, _, _, _, _, _, _, _),
+	[159] = PINGROUP(159, qlink_big_request, qdss_cti, _, _, _, _, _, _, _, _),
+	[160] = PINGROUP(160, qlink_big_enable, _, _, _, _, _, _, _, _, _),
+	[161] = PINGROUP(161, _, _, _, _, _, _, _, _, _, _),
+	[162] = PINGROUP(162, qdss_cti, _, _, _, _, _, _, _, _, _),
+	[163] = PINGROUP(163, cci_async_in, phase_flag, _, _, _, _, _, _, _, _),
+	[164] = PINGROUP(164, cci_async_in, phase_flag, _, _, _, _, _, _, _, _),
+	[165] = PINGROUP(165, _, _, _, _, _, _, _, _, _, egpio),
+	[166] = PINGROUP(166, _, _, _, _, _, _, _, _, _, egpio),
+	[167] = PINGROUP(167, _, _, _, _, _, _, _, _, _, egpio),
+	[168] = PINGROUP(168, _, _, _, _, _, _, _, _, _, egpio),
+	[169] = PINGROUP(169, _, _, _, _, _, _, _, _, _, egpio),
+	[170] = PINGROUP(170, _, _, _, _, _, _, _, _, _, egpio),
+	[171] = PINGROUP(171, _, _, _, _, _, _, _, _, _, egpio),
+	[172] = PINGROUP(172, _, _, _, _, _, _, _, _, _, egpio),
+	[173] = PINGROUP(173, _, _, _, _, _, _, _, _, _, egpio),
+	[174] = PINGROUP(174, _, _, _, _, _, _, _, _, _, egpio),
+	[175] = PINGROUP(175, _, _, _, _, _, _, _, _, _, egpio),
+	[176] = PINGROUP(176, _, _, _, _, _, _, _, _, _, egpio),
+	[177] = PINGROUP(177, _, _, _, _, _, _, _, _, _, egpio),
+	[178] = PINGROUP(178, _, _, _, _, _, _, _, _, _, egpio),
+	[179] = PINGROUP(179, _, _, _, _, _, _, _, _, _, egpio),
+	[180] = PINGROUP(180, _, _, _, _, _, _, _, _, _, egpio),
+	[181] = PINGROUP(181, prng_rosc3, _, _, _, _, _, _, _, _, egpio),
+	[182] = PINGROUP(182, prng_rosc2, _, _, _, _, _, _, _, _, egpio),
+	[183] = PINGROUP(183, prng_rosc1, _, _, _, _, _, _, _, _, egpio),
+	[184] = PINGROUP(184, _, _, _, _, _, _, _, _, _, egpio),
+	[185] = PINGROUP(185, _, _, _, _, _, _, _, _, _, egpio),
+	[186] = PINGROUP(186, prng_rosc0, _, _, _, _, _, _, _, _, egpio),
+	[187] = PINGROUP(187, cri_trng, _, _, _, _, _, _, _, _, egpio),
+	[188] = PINGROUP(188, _, _, _, _, _, _, _, _, _, egpio),
+	[189] = PINGROUP(189, _, _, _, _, _, _, _, _, _, egpio),
+	[190] = PINGROUP(190, _, _, _, _, _, _, _, _, _, egpio),
+	[191] = PINGROUP(191, _, _, _, _, _, _, _, _, _, egpio),
+	[192] = PINGROUP(192, _, _, _, _, _, _, _, _, _, egpio),
+	[193] = PINGROUP(193, _, _, _, _, _, _, _, _, _, egpio),
+	[194] = PINGROUP(194, _, _, _, _, _, _, _, _, _, egpio),
+	[195] = PINGROUP(195, _, _, _, _, _, _, _, _, _, egpio),
+	[196] = PINGROUP(196, _, _, _, _, _, _, _, _, _, egpio),
+	[197] = PINGROUP(197, _, _, _, _, _, _, _, _, _, egpio),
+	[198] = PINGROUP(198, _, _, _, _, _, _, _, _, _, egpio),
+	[199] = PINGROUP(199, _, _, _, _, _, _, _, _, _, egpio),
+	[200] = PINGROUP(200, _, _, _, _, _, _, _, _, _, egpio),
+	[201] = PINGROUP(201, _, _, _, _, _, _, _, _, _, egpio),
+	[202] = PINGROUP(202, _, _, _, _, _, _, _, _, _, egpio),
+	[203] = PINGROUP(203, _, _, _, _, _, _, _, _, _, egpio),
+	[204] = PINGROUP(204, _, _, _, _, _, _, _, _, _, egpio),
+	[205] = PINGROUP(205, _, _, _, _, _, _, _, _, _, egpio),
+	[206] = PINGROUP(206, i2chub0_se8, _, _, _, _, _, _, _, _, egpio),
+	[207] = PINGROUP(207, i2chub0_se8, _, _, _, _, _, _, _, _, egpio),
+	[208] = PINGROUP(208, _, _, _, _, _, _, _, _, _, egpio),
+	[209] = PINGROUP(209, _, _, _, _, _, _, _, _, _, egpio),
+	[210] = UFS_RESET(ufs_reset, 0xde004, 0xdf000),
+	[211] = SDC_QDSD_PINGROUP(sdc2_clk, 0xd6000, 14, 6),
+	[212] = SDC_QDSD_PINGROUP(sdc2_cmd, 0xd6000, 11, 3),
+	[213] = SDC_QDSD_PINGROUP(sdc2_data, 0xd6000, 9, 0),
+};
+
+static const struct msm_gpio_wakeirq_map sm8650_pdc_map[] = {
+	{ 0, 94 },    { 3, 105 },   { 4, 78 },    { 7, 67 },    { 8, 64 },
+	{ 11, 121 },  { 12, 71 },   { 15, 82 },   { 18, 75 },   { 19, 63 },
+	{ 20, 114 },  { 23, 84 },   { 27, 61 },   { 29, 112 },  { 31, 113 },
+	{ 32, 66 },   { 35, 52 },   { 36, 123 },  { 39, 56 },   { 43, 59 },
+	{ 46, 79 },   { 47, 124 },  { 48, 125 },  { 51, 93 },   { 54, 60 },
+	{ 55, 104 },  { 56, 72 },   { 57, 77 },   { 59, 51 },   { 63, 85 },
+	{ 64, 107 },  { 65, 108 },  { 66, 109 },  { 67, 83 },   { 68, 110 },
+	{ 69, 111 },  { 75, 96 },   { 76, 97 },   { 77, 98 },   { 80, 89 },
+	{ 81, 90 },   { 84, 106 },  { 85, 100 },  { 86, 87 },   { 87, 88 },
+	{ 88, 65 },   { 90, 92 },   { 92, 99 },   { 95, 118 },  { 96, 119 },
+	{ 98, 101 },  { 99, 62 },   { 112, 120 }, { 133, 80 },  { 136, 69 },
+	{ 137, 81 },  { 148, 57 },  { 150, 58 },  { 152, 127 }, { 153, 74 },
+	{ 154, 126 }, { 155, 73 },  { 156, 128 }, { 159, 129 }, { 162, 86 },
+	{ 163, 122 }, { 166, 139 }, { 169, 140 }, { 171, 141 }, { 172, 142 },
+	{ 174, 102 }, { 176, 143 }, { 177, 55 },  { 181, 144 }, { 182, 145 },
+	{ 185, 146 }, { 187, 95 },  { 188, 130 }, { 190, 131 }, { 191, 132 },
+	{ 192, 133 }, { 193, 134 }, { 195, 68 },  { 196, 135 }, { 197, 136 },
+	{ 198, 54 },  { 199, 103 }, { 200, 53 },  { 201, 137 }, { 202, 70 },
+	{ 203, 138 }, { 204, 76 },  { 205, 91 },
+};
+
+static const struct msm_pinctrl_soc_data sm8650_tlmm = {
+	.pins = sm8650_pins,
+	.npins = ARRAY_SIZE(sm8650_pins),
+	.functions = sm8650_functions,
+	.nfunctions = ARRAY_SIZE(sm8650_functions),
+	.groups = sm8650_groups,
+	.ngroups = ARRAY_SIZE(sm8650_groups),
+	.ngpios = 211,
+	.wakeirq_map = sm8650_pdc_map,
+	.nwakeirq_map = ARRAY_SIZE(sm8650_pdc_map),
+	.egpio_func = 10,
+};
+
+static int sm8650_tlmm_probe(struct platform_device *pdev)
+{
+	return msm_pinctrl_probe(pdev, &sm8650_tlmm);
+}
+
+static const struct of_device_id sm8650_tlmm_of_match[] = {
+	{ .compatible = "qcom,sm8650-tlmm", },
+	{},
+};
+
+static struct platform_driver sm8650_tlmm_driver = {
+	.driver = {
+		.name = "sm8650-tlmm",
+		.of_match_table = sm8650_tlmm_of_match,
+	},
+	.probe = sm8650_tlmm_probe,
+	.remove_new = msm_pinctrl_remove,
+};
+
+static int __init sm8650_tlmm_init(void)
+{
+	return platform_driver_register(&sm8650_tlmm_driver);
+}
+arch_initcall(sm8650_tlmm_init);
+
+static void __exit sm8650_tlmm_exit(void)
+{
+	platform_driver_unregister(&sm8650_tlmm_driver);
+}
+module_exit(sm8650_tlmm_exit);
+
+MODULE_DESCRIPTION("QTI SM8650 TLMM driver");
+MODULE_LICENSE("GPL");
+MODULE_DEVICE_TABLE(of, sm8650_tlmm_of_match);
diff --git a/drivers/pinctrl/qcom/pinctrl-x1e80100.c b/drivers/pinctrl/qcom/pinctrl-x1e80100.c
new file mode 100644
index 000000000000..e30e93840357
--- /dev/null
+++ b/drivers/pinctrl/qcom/pinctrl-x1e80100.c
@@ -0,0 +1,1876 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include "pinctrl-msm.h"
+
+#define REG_SIZE 0x1000
+
+#define PINGROUP(id, f1, f2, f3, f4, f5, f6, f7, f8, f9)	\
+	{					        \
+		.grp = PINCTRL_PINGROUP("gpio" #id,	\
+			gpio##id##_pins,		\
+			ARRAY_SIZE(gpio##id##_pins)),	\
+		.funcs = (int[]){			\
+			msm_mux_gpio, /* gpio mode */	\
+			msm_mux_##f1,			\
+			msm_mux_##f2,			\
+			msm_mux_##f3,			\
+			msm_mux_##f4,			\
+			msm_mux_##f5,			\
+			msm_mux_##f6,			\
+			msm_mux_##f7,			\
+			msm_mux_##f8,			\
+			msm_mux_##f9			\
+		},				        \
+		.nfuncs = 10,				\
+		.ctl_reg = REG_SIZE * id,			\
+		.io_reg = 0x4 + REG_SIZE * id,		\
+		.intr_cfg_reg = 0x8 + REG_SIZE * id,		\
+		.intr_status_reg = 0xc + REG_SIZE * id,	\
+		.intr_target_reg = 0x8 + REG_SIZE * id,	\
+		.mux_bit = 2,			\
+		.pull_bit = 0,			\
+		.drv_bit = 6,			\
+		.i2c_pull_bit = 13,		\
+		.egpio_enable = 12,		\
+		.egpio_present = 11,		\
+		.oe_bit = 9,			\
+		.in_bit = 0,			\
+		.out_bit = 1,			\
+		.intr_enable_bit = 0,		\
+		.intr_status_bit = 0,		\
+		.intr_target_bit = 5,		\
+		.intr_target_kpss_val = 3,	\
+		.intr_raw_status_bit = 4,	\
+		.intr_polarity_bit = 1,		\
+		.intr_detection_bit = 2,	\
+		.intr_detection_width = 2,	\
+	}
+
+#define SDC_QDSD_PINGROUP(pg_name, ctl, pull, drv)	\
+	{					        \
+		.grp = PINCTRL_PINGROUP(#pg_name,	\
+			pg_name##_pins,			\
+			ARRAY_SIZE(pg_name##_pins)),	\
+		.ctl_reg = ctl,				\
+		.io_reg = 0,				\
+		.intr_cfg_reg = 0,			\
+		.intr_status_reg = 0,			\
+		.intr_target_reg = 0,			\
+		.mux_bit = -1,				\
+		.pull_bit = pull,			\
+		.drv_bit = drv,				\
+		.oe_bit = -1,				\
+		.in_bit = -1,				\
+		.out_bit = -1,				\
+		.intr_enable_bit = -1,			\
+		.intr_status_bit = -1,			\
+		.intr_target_bit = -1,			\
+		.intr_raw_status_bit = -1,		\
+		.intr_polarity_bit = -1,		\
+		.intr_detection_bit = -1,		\
+		.intr_detection_width = -1,		\
+	}
+
+#define UFS_RESET(pg_name, offset)				\
+	{					        \
+		.grp = PINCTRL_PINGROUP(#pg_name,	\
+			pg_name##_pins,			\
+			ARRAY_SIZE(pg_name##_pins)),	\
+		.ctl_reg = offset,			\
+		.io_reg = offset + 0x4,			\
+		.intr_cfg_reg = 0,			\
+		.intr_status_reg = 0,			\
+		.intr_target_reg = 0,			\
+		.mux_bit = -1,				\
+		.pull_bit = 3,				\
+		.drv_bit = 0,				\
+		.oe_bit = -1,				\
+		.in_bit = -1,				\
+		.out_bit = 0,				\
+		.intr_enable_bit = -1,			\
+		.intr_status_bit = -1,			\
+		.intr_target_bit = -1,			\
+		.intr_raw_status_bit = -1,		\
+		.intr_polarity_bit = -1,		\
+		.intr_detection_bit = -1,		\
+		.intr_detection_width = -1,		\
+	}
+
+static const struct pinctrl_pin_desc x1e80100_pins[] = {
+	PINCTRL_PIN(0, "GPIO_0"),
+	PINCTRL_PIN(1, "GPIO_1"),
+	PINCTRL_PIN(2, "GPIO_2"),
+	PINCTRL_PIN(3, "GPIO_3"),
+	PINCTRL_PIN(4, "GPIO_4"),
+	PINCTRL_PIN(5, "GPIO_5"),
+	PINCTRL_PIN(6, "GPIO_6"),
+	PINCTRL_PIN(7, "GPIO_7"),
+	PINCTRL_PIN(8, "GPIO_8"),
+	PINCTRL_PIN(9, "GPIO_9"),
+	PINCTRL_PIN(10, "GPIO_10"),
+	PINCTRL_PIN(11, "GPIO_11"),
+	PINCTRL_PIN(12, "GPIO_12"),
+	PINCTRL_PIN(13, "GPIO_13"),
+	PINCTRL_PIN(14, "GPIO_14"),
+	PINCTRL_PIN(15, "GPIO_15"),
+	PINCTRL_PIN(16, "GPIO_16"),
+	PINCTRL_PIN(17, "GPIO_17"),
+	PINCTRL_PIN(18, "GPIO_18"),
+	PINCTRL_PIN(19, "GPIO_19"),
+	PINCTRL_PIN(20, "GPIO_20"),
+	PINCTRL_PIN(21, "GPIO_21"),
+	PINCTRL_PIN(22, "GPIO_22"),
+	PINCTRL_PIN(23, "GPIO_23"),
+	PINCTRL_PIN(24, "GPIO_24"),
+	PINCTRL_PIN(25, "GPIO_25"),
+	PINCTRL_PIN(26, "GPIO_26"),
+	PINCTRL_PIN(27, "GPIO_27"),
+	PINCTRL_PIN(28, "GPIO_28"),
+	PINCTRL_PIN(29, "GPIO_29"),
+	PINCTRL_PIN(30, "GPIO_30"),
+	PINCTRL_PIN(31, "GPIO_31"),
+	PINCTRL_PIN(32, "GPIO_32"),
+	PINCTRL_PIN(33, "GPIO_33"),
+	PINCTRL_PIN(34, "GPIO_34"),
+	PINCTRL_PIN(35, "GPIO_35"),
+	PINCTRL_PIN(36, "GPIO_36"),
+	PINCTRL_PIN(37, "GPIO_37"),
+	PINCTRL_PIN(38, "GPIO_38"),
+	PINCTRL_PIN(39, "GPIO_39"),
+	PINCTRL_PIN(40, "GPIO_40"),
+	PINCTRL_PIN(41, "GPIO_41"),
+	PINCTRL_PIN(42, "GPIO_42"),
+	PINCTRL_PIN(43, "GPIO_43"),
+	PINCTRL_PIN(44, "GPIO_44"),
+	PINCTRL_PIN(45, "GPIO_45"),
+	PINCTRL_PIN(46, "GPIO_46"),
+	PINCTRL_PIN(47, "GPIO_47"),
+	PINCTRL_PIN(48, "GPIO_48"),
+	PINCTRL_PIN(49, "GPIO_49"),
+	PINCTRL_PIN(50, "GPIO_50"),
+	PINCTRL_PIN(51, "GPIO_51"),
+	PINCTRL_PIN(52, "GPIO_52"),
+	PINCTRL_PIN(53, "GPIO_53"),
+	PINCTRL_PIN(54, "GPIO_54"),
+	PINCTRL_PIN(55, "GPIO_55"),
+	PINCTRL_PIN(56, "GPIO_56"),
+	PINCTRL_PIN(57, "GPIO_57"),
+	PINCTRL_PIN(58, "GPIO_58"),
+	PINCTRL_PIN(59, "GPIO_59"),
+	PINCTRL_PIN(60, "GPIO_60"),
+	PINCTRL_PIN(61, "GPIO_61"),
+	PINCTRL_PIN(62, "GPIO_62"),
+	PINCTRL_PIN(63, "GPIO_63"),
+	PINCTRL_PIN(64, "GPIO_64"),
+	PINCTRL_PIN(65, "GPIO_65"),
+	PINCTRL_PIN(66, "GPIO_66"),
+	PINCTRL_PIN(67, "GPIO_67"),
+	PINCTRL_PIN(68, "GPIO_68"),
+	PINCTRL_PIN(69, "GPIO_69"),
+	PINCTRL_PIN(70, "GPIO_70"),
+	PINCTRL_PIN(71, "GPIO_71"),
+	PINCTRL_PIN(72, "GPIO_72"),
+	PINCTRL_PIN(73, "GPIO_73"),
+	PINCTRL_PIN(74, "GPIO_74"),
+	PINCTRL_PIN(75, "GPIO_75"),
+	PINCTRL_PIN(76, "GPIO_76"),
+	PINCTRL_PIN(77, "GPIO_77"),
+	PINCTRL_PIN(78, "GPIO_78"),
+	PINCTRL_PIN(79, "GPIO_79"),
+	PINCTRL_PIN(80, "GPIO_80"),
+	PINCTRL_PIN(81, "GPIO_81"),
+	PINCTRL_PIN(82, "GPIO_82"),
+	PINCTRL_PIN(83, "GPIO_83"),
+	PINCTRL_PIN(84, "GPIO_84"),
+	PINCTRL_PIN(85, "GPIO_85"),
+	PINCTRL_PIN(86, "GPIO_86"),
+	PINCTRL_PIN(87, "GPIO_87"),
+	PINCTRL_PIN(88, "GPIO_88"),
+	PINCTRL_PIN(89, "GPIO_89"),
+	PINCTRL_PIN(90, "GPIO_90"),
+	PINCTRL_PIN(91, "GPIO_91"),
+	PINCTRL_PIN(92, "GPIO_92"),
+	PINCTRL_PIN(93, "GPIO_93"),
+	PINCTRL_PIN(94, "GPIO_94"),
+	PINCTRL_PIN(95, "GPIO_95"),
+	PINCTRL_PIN(96, "GPIO_96"),
+	PINCTRL_PIN(97, "GPIO_97"),
+	PINCTRL_PIN(98, "GPIO_98"),
+	PINCTRL_PIN(99, "GPIO_99"),
+	PINCTRL_PIN(100, "GPIO_100"),
+	PINCTRL_PIN(101, "GPIO_101"),
+	PINCTRL_PIN(102, "GPIO_102"),
+	PINCTRL_PIN(103, "GPIO_103"),
+	PINCTRL_PIN(104, "GPIO_104"),
+	PINCTRL_PIN(105, "GPIO_105"),
+	PINCTRL_PIN(106, "GPIO_106"),
+	PINCTRL_PIN(107, "GPIO_107"),
+	PINCTRL_PIN(108, "GPIO_108"),
+	PINCTRL_PIN(109, "GPIO_109"),
+	PINCTRL_PIN(110, "GPIO_110"),
+	PINCTRL_PIN(111, "GPIO_111"),
+	PINCTRL_PIN(112, "GPIO_112"),
+	PINCTRL_PIN(113, "GPIO_113"),
+	PINCTRL_PIN(114, "GPIO_114"),
+	PINCTRL_PIN(115, "GPIO_115"),
+	PINCTRL_PIN(116, "GPIO_116"),
+	PINCTRL_PIN(117, "GPIO_117"),
+	PINCTRL_PIN(118, "GPIO_118"),
+	PINCTRL_PIN(119, "GPIO_119"),
+	PINCTRL_PIN(120, "GPIO_120"),
+	PINCTRL_PIN(121, "GPIO_121"),
+	PINCTRL_PIN(122, "GPIO_122"),
+	PINCTRL_PIN(123, "GPIO_123"),
+	PINCTRL_PIN(124, "GPIO_124"),
+	PINCTRL_PIN(125, "GPIO_125"),
+	PINCTRL_PIN(126, "GPIO_126"),
+	PINCTRL_PIN(127, "GPIO_127"),
+	PINCTRL_PIN(128, "GPIO_128"),
+	PINCTRL_PIN(129, "GPIO_129"),
+	PINCTRL_PIN(130, "GPIO_130"),
+	PINCTRL_PIN(131, "GPIO_131"),
+	PINCTRL_PIN(132, "GPIO_132"),
+	PINCTRL_PIN(133, "GPIO_133"),
+	PINCTRL_PIN(134, "GPIO_134"),
+	PINCTRL_PIN(135, "GPIO_135"),
+	PINCTRL_PIN(136, "GPIO_136"),
+	PINCTRL_PIN(137, "GPIO_137"),
+	PINCTRL_PIN(138, "GPIO_138"),
+	PINCTRL_PIN(139, "GPIO_139"),
+	PINCTRL_PIN(140, "GPIO_140"),
+	PINCTRL_PIN(141, "GPIO_141"),
+	PINCTRL_PIN(142, "GPIO_142"),
+	PINCTRL_PIN(143, "GPIO_143"),
+	PINCTRL_PIN(144, "GPIO_144"),
+	PINCTRL_PIN(145, "GPIO_145"),
+	PINCTRL_PIN(146, "GPIO_146"),
+	PINCTRL_PIN(147, "GPIO_147"),
+	PINCTRL_PIN(148, "GPIO_148"),
+	PINCTRL_PIN(149, "GPIO_149"),
+	PINCTRL_PIN(150, "GPIO_150"),
+	PINCTRL_PIN(151, "GPIO_151"),
+	PINCTRL_PIN(152, "GPIO_152"),
+	PINCTRL_PIN(153, "GPIO_153"),
+	PINCTRL_PIN(154, "GPIO_154"),
+	PINCTRL_PIN(155, "GPIO_155"),
+	PINCTRL_PIN(156, "GPIO_156"),
+	PINCTRL_PIN(157, "GPIO_157"),
+	PINCTRL_PIN(158, "GPIO_158"),
+	PINCTRL_PIN(159, "GPIO_159"),
+	PINCTRL_PIN(160, "GPIO_160"),
+	PINCTRL_PIN(161, "GPIO_161"),
+	PINCTRL_PIN(162, "GPIO_162"),
+	PINCTRL_PIN(163, "GPIO_163"),
+	PINCTRL_PIN(164, "GPIO_164"),
+	PINCTRL_PIN(165, "GPIO_165"),
+	PINCTRL_PIN(166, "GPIO_166"),
+	PINCTRL_PIN(167, "GPIO_167"),
+	PINCTRL_PIN(168, "GPIO_168"),
+	PINCTRL_PIN(169, "GPIO_169"),
+	PINCTRL_PIN(170, "GPIO_170"),
+	PINCTRL_PIN(171, "GPIO_171"),
+	PINCTRL_PIN(172, "GPIO_172"),
+	PINCTRL_PIN(173, "GPIO_173"),
+	PINCTRL_PIN(174, "GPIO_174"),
+	PINCTRL_PIN(175, "GPIO_175"),
+	PINCTRL_PIN(176, "GPIO_176"),
+	PINCTRL_PIN(177, "GPIO_177"),
+	PINCTRL_PIN(178, "GPIO_178"),
+	PINCTRL_PIN(179, "GPIO_179"),
+	PINCTRL_PIN(180, "GPIO_180"),
+	PINCTRL_PIN(181, "GPIO_181"),
+	PINCTRL_PIN(182, "GPIO_182"),
+	PINCTRL_PIN(183, "GPIO_183"),
+	PINCTRL_PIN(184, "GPIO_184"),
+	PINCTRL_PIN(185, "GPIO_185"),
+	PINCTRL_PIN(186, "GPIO_186"),
+	PINCTRL_PIN(187, "GPIO_187"),
+	PINCTRL_PIN(188, "GPIO_188"),
+	PINCTRL_PIN(189, "GPIO_189"),
+	PINCTRL_PIN(190, "GPIO_190"),
+	PINCTRL_PIN(191, "GPIO_191"),
+	PINCTRL_PIN(192, "GPIO_192"),
+	PINCTRL_PIN(193, "GPIO_193"),
+	PINCTRL_PIN(194, "GPIO_194"),
+	PINCTRL_PIN(195, "GPIO_195"),
+	PINCTRL_PIN(196, "GPIO_196"),
+	PINCTRL_PIN(197, "GPIO_197"),
+	PINCTRL_PIN(198, "GPIO_198"),
+	PINCTRL_PIN(199, "GPIO_199"),
+	PINCTRL_PIN(200, "GPIO_200"),
+	PINCTRL_PIN(201, "GPIO_201"),
+	PINCTRL_PIN(202, "GPIO_202"),
+	PINCTRL_PIN(203, "GPIO_203"),
+	PINCTRL_PIN(204, "GPIO_204"),
+	PINCTRL_PIN(205, "GPIO_205"),
+	PINCTRL_PIN(206, "GPIO_206"),
+	PINCTRL_PIN(207, "GPIO_207"),
+	PINCTRL_PIN(208, "GPIO_208"),
+	PINCTRL_PIN(209, "GPIO_209"),
+	PINCTRL_PIN(210, "GPIO_210"),
+	PINCTRL_PIN(211, "GPIO_211"),
+	PINCTRL_PIN(212, "GPIO_212"),
+	PINCTRL_PIN(213, "GPIO_213"),
+	PINCTRL_PIN(214, "GPIO_214"),
+	PINCTRL_PIN(215, "GPIO_215"),
+	PINCTRL_PIN(216, "GPIO_216"),
+	PINCTRL_PIN(217, "GPIO_217"),
+	PINCTRL_PIN(218, "GPIO_218"),
+	PINCTRL_PIN(219, "GPIO_219"),
+	PINCTRL_PIN(220, "GPIO_220"),
+	PINCTRL_PIN(221, "GPIO_221"),
+	PINCTRL_PIN(222, "GPIO_222"),
+	PINCTRL_PIN(223, "GPIO_223"),
+	PINCTRL_PIN(224, "GPIO_224"),
+	PINCTRL_PIN(225, "GPIO_225"),
+	PINCTRL_PIN(226, "GPIO_226"),
+	PINCTRL_PIN(227, "GPIO_227"),
+	PINCTRL_PIN(228, "GPIO_228"),
+	PINCTRL_PIN(229, "GPIO_229"),
+	PINCTRL_PIN(230, "GPIO_230"),
+	PINCTRL_PIN(231, "GPIO_231"),
+	PINCTRL_PIN(232, "GPIO_232"),
+	PINCTRL_PIN(233, "GPIO_233"),
+	PINCTRL_PIN(234, "GPIO_234"),
+	PINCTRL_PIN(235, "GPIO_235"),
+	PINCTRL_PIN(236, "GPIO_236"),
+	PINCTRL_PIN(237, "GPIO_237"),
+	PINCTRL_PIN(238, "UFS_RESET"),
+	PINCTRL_PIN(239, "SDC2_CLK"),
+	PINCTRL_PIN(240, "SDC2_CMD"),
+	PINCTRL_PIN(241, "SDC2_DATA"),
+};
+
+#define DECLARE_MSM_GPIO_PINS(pin) \
+	static const unsigned int gpio##pin##_pins[] = { pin }
+DECLARE_MSM_GPIO_PINS(0);
+DECLARE_MSM_GPIO_PINS(1);
+DECLARE_MSM_GPIO_PINS(2);
+DECLARE_MSM_GPIO_PINS(3);
+DECLARE_MSM_GPIO_PINS(4);
+DECLARE_MSM_GPIO_PINS(5);
+DECLARE_MSM_GPIO_PINS(6);
+DECLARE_MSM_GPIO_PINS(7);
+DECLARE_MSM_GPIO_PINS(8);
+DECLARE_MSM_GPIO_PINS(9);
+DECLARE_MSM_GPIO_PINS(10);
+DECLARE_MSM_GPIO_PINS(11);
+DECLARE_MSM_GPIO_PINS(12);
+DECLARE_MSM_GPIO_PINS(13);
+DECLARE_MSM_GPIO_PINS(14);
+DECLARE_MSM_GPIO_PINS(15);
+DECLARE_MSM_GPIO_PINS(16);
+DECLARE_MSM_GPIO_PINS(17);
+DECLARE_MSM_GPIO_PINS(18);
+DECLARE_MSM_GPIO_PINS(19);
+DECLARE_MSM_GPIO_PINS(20);
+DECLARE_MSM_GPIO_PINS(21);
+DECLARE_MSM_GPIO_PINS(22);
+DECLARE_MSM_GPIO_PINS(23);
+DECLARE_MSM_GPIO_PINS(24);
+DECLARE_MSM_GPIO_PINS(25);
+DECLARE_MSM_GPIO_PINS(26);
+DECLARE_MSM_GPIO_PINS(27);
+DECLARE_MSM_GPIO_PINS(28);
+DECLARE_MSM_GPIO_PINS(29);
+DECLARE_MSM_GPIO_PINS(30);
+DECLARE_MSM_GPIO_PINS(31);
+DECLARE_MSM_GPIO_PINS(32);
+DECLARE_MSM_GPIO_PINS(33);
+DECLARE_MSM_GPIO_PINS(34);
+DECLARE_MSM_GPIO_PINS(35);
+DECLARE_MSM_GPIO_PINS(36);
+DECLARE_MSM_GPIO_PINS(37);
+DECLARE_MSM_GPIO_PINS(38);
+DECLARE_MSM_GPIO_PINS(39);
+DECLARE_MSM_GPIO_PINS(40);
+DECLARE_MSM_GPIO_PINS(41);
+DECLARE_MSM_GPIO_PINS(42);
+DECLARE_MSM_GPIO_PINS(43);
+DECLARE_MSM_GPIO_PINS(44);
+DECLARE_MSM_GPIO_PINS(45);
+DECLARE_MSM_GPIO_PINS(46);
+DECLARE_MSM_GPIO_PINS(47);
+DECLARE_MSM_GPIO_PINS(48);
+DECLARE_MSM_GPIO_PINS(49);
+DECLARE_MSM_GPIO_PINS(50);
+DECLARE_MSM_GPIO_PINS(51);
+DECLARE_MSM_GPIO_PINS(52);
+DECLARE_MSM_GPIO_PINS(53);
+DECLARE_MSM_GPIO_PINS(54);
+DECLARE_MSM_GPIO_PINS(55);
+DECLARE_MSM_GPIO_PINS(56);
+DECLARE_MSM_GPIO_PINS(57);
+DECLARE_MSM_GPIO_PINS(58);
+DECLARE_MSM_GPIO_PINS(59);
+DECLARE_MSM_GPIO_PINS(60);
+DECLARE_MSM_GPIO_PINS(61);
+DECLARE_MSM_GPIO_PINS(62);
+DECLARE_MSM_GPIO_PINS(63);
+DECLARE_MSM_GPIO_PINS(64);
+DECLARE_MSM_GPIO_PINS(65);
+DECLARE_MSM_GPIO_PINS(66);
+DECLARE_MSM_GPIO_PINS(67);
+DECLARE_MSM_GPIO_PINS(68);
+DECLARE_MSM_GPIO_PINS(69);
+DECLARE_MSM_GPIO_PINS(70);
+DECLARE_MSM_GPIO_PINS(71);
+DECLARE_MSM_GPIO_PINS(72);
+DECLARE_MSM_GPIO_PINS(73);
+DECLARE_MSM_GPIO_PINS(74);
+DECLARE_MSM_GPIO_PINS(75);
+DECLARE_MSM_GPIO_PINS(76);
+DECLARE_MSM_GPIO_PINS(77);
+DECLARE_MSM_GPIO_PINS(78);
+DECLARE_MSM_GPIO_PINS(79);
+DECLARE_MSM_GPIO_PINS(80);
+DECLARE_MSM_GPIO_PINS(81);
+DECLARE_MSM_GPIO_PINS(82);
+DECLARE_MSM_GPIO_PINS(83);
+DECLARE_MSM_GPIO_PINS(84);
+DECLARE_MSM_GPIO_PINS(85);
+DECLARE_MSM_GPIO_PINS(86);
+DECLARE_MSM_GPIO_PINS(87);
+DECLARE_MSM_GPIO_PINS(88);
+DECLARE_MSM_GPIO_PINS(89);
+DECLARE_MSM_GPIO_PINS(90);
+DECLARE_MSM_GPIO_PINS(91);
+DECLARE_MSM_GPIO_PINS(92);
+DECLARE_MSM_GPIO_PINS(93);
+DECLARE_MSM_GPIO_PINS(94);
+DECLARE_MSM_GPIO_PINS(95);
+DECLARE_MSM_GPIO_PINS(96);
+DECLARE_MSM_GPIO_PINS(97);
+DECLARE_MSM_GPIO_PINS(98);
+DECLARE_MSM_GPIO_PINS(99);
+DECLARE_MSM_GPIO_PINS(100);
+DECLARE_MSM_GPIO_PINS(101);
+DECLARE_MSM_GPIO_PINS(102);
+DECLARE_MSM_GPIO_PINS(103);
+DECLARE_MSM_GPIO_PINS(104);
+DECLARE_MSM_GPIO_PINS(105);
+DECLARE_MSM_GPIO_PINS(106);
+DECLARE_MSM_GPIO_PINS(107);
+DECLARE_MSM_GPIO_PINS(108);
+DECLARE_MSM_GPIO_PINS(109);
+DECLARE_MSM_GPIO_PINS(110);
+DECLARE_MSM_GPIO_PINS(111);
+DECLARE_MSM_GPIO_PINS(112);
+DECLARE_MSM_GPIO_PINS(113);
+DECLARE_MSM_GPIO_PINS(114);
+DECLARE_MSM_GPIO_PINS(115);
+DECLARE_MSM_GPIO_PINS(116);
+DECLARE_MSM_GPIO_PINS(117);
+DECLARE_MSM_GPIO_PINS(118);
+DECLARE_MSM_GPIO_PINS(119);
+DECLARE_MSM_GPIO_PINS(120);
+DECLARE_MSM_GPIO_PINS(121);
+DECLARE_MSM_GPIO_PINS(122);
+DECLARE_MSM_GPIO_PINS(123);
+DECLARE_MSM_GPIO_PINS(124);
+DECLARE_MSM_GPIO_PINS(125);
+DECLARE_MSM_GPIO_PINS(126);
+DECLARE_MSM_GPIO_PINS(127);
+DECLARE_MSM_GPIO_PINS(128);
+DECLARE_MSM_GPIO_PINS(129);
+DECLARE_MSM_GPIO_PINS(130);
+DECLARE_MSM_GPIO_PINS(131);
+DECLARE_MSM_GPIO_PINS(132);
+DECLARE_MSM_GPIO_PINS(133);
+DECLARE_MSM_GPIO_PINS(134);
+DECLARE_MSM_GPIO_PINS(135);
+DECLARE_MSM_GPIO_PINS(136);
+DECLARE_MSM_GPIO_PINS(137);
+DECLARE_MSM_GPIO_PINS(138);
+DECLARE_MSM_GPIO_PINS(139);
+DECLARE_MSM_GPIO_PINS(140);
+DECLARE_MSM_GPIO_PINS(141);
+DECLARE_MSM_GPIO_PINS(142);
+DECLARE_MSM_GPIO_PINS(143);
+DECLARE_MSM_GPIO_PINS(144);
+DECLARE_MSM_GPIO_PINS(145);
+DECLARE_MSM_GPIO_PINS(146);
+DECLARE_MSM_GPIO_PINS(147);
+DECLARE_MSM_GPIO_PINS(148);
+DECLARE_MSM_GPIO_PINS(149);
+DECLARE_MSM_GPIO_PINS(150);
+DECLARE_MSM_GPIO_PINS(151);
+DECLARE_MSM_GPIO_PINS(152);
+DECLARE_MSM_GPIO_PINS(153);
+DECLARE_MSM_GPIO_PINS(154);
+DECLARE_MSM_GPIO_PINS(155);
+DECLARE_MSM_GPIO_PINS(156);
+DECLARE_MSM_GPIO_PINS(157);
+DECLARE_MSM_GPIO_PINS(158);
+DECLARE_MSM_GPIO_PINS(159);
+DECLARE_MSM_GPIO_PINS(160);
+DECLARE_MSM_GPIO_PINS(161);
+DECLARE_MSM_GPIO_PINS(162);
+DECLARE_MSM_GPIO_PINS(163);
+DECLARE_MSM_GPIO_PINS(164);
+DECLARE_MSM_GPIO_PINS(165);
+DECLARE_MSM_GPIO_PINS(166);
+DECLARE_MSM_GPIO_PINS(167);
+DECLARE_MSM_GPIO_PINS(168);
+DECLARE_MSM_GPIO_PINS(169);
+DECLARE_MSM_GPIO_PINS(170);
+DECLARE_MSM_GPIO_PINS(171);
+DECLARE_MSM_GPIO_PINS(172);
+DECLARE_MSM_GPIO_PINS(173);
+DECLARE_MSM_GPIO_PINS(174);
+DECLARE_MSM_GPIO_PINS(175);
+DECLARE_MSM_GPIO_PINS(176);
+DECLARE_MSM_GPIO_PINS(177);
+DECLARE_MSM_GPIO_PINS(178);
+DECLARE_MSM_GPIO_PINS(179);
+DECLARE_MSM_GPIO_PINS(180);
+DECLARE_MSM_GPIO_PINS(181);
+DECLARE_MSM_GPIO_PINS(182);
+DECLARE_MSM_GPIO_PINS(183);
+DECLARE_MSM_GPIO_PINS(184);
+DECLARE_MSM_GPIO_PINS(185);
+DECLARE_MSM_GPIO_PINS(186);
+DECLARE_MSM_GPIO_PINS(187);
+DECLARE_MSM_GPIO_PINS(188);
+DECLARE_MSM_GPIO_PINS(189);
+DECLARE_MSM_GPIO_PINS(190);
+DECLARE_MSM_GPIO_PINS(191);
+DECLARE_MSM_GPIO_PINS(192);
+DECLARE_MSM_GPIO_PINS(193);
+DECLARE_MSM_GPIO_PINS(194);
+DECLARE_MSM_GPIO_PINS(195);
+DECLARE_MSM_GPIO_PINS(196);
+DECLARE_MSM_GPIO_PINS(197);
+DECLARE_MSM_GPIO_PINS(198);
+DECLARE_MSM_GPIO_PINS(199);
+DECLARE_MSM_GPIO_PINS(200);
+DECLARE_MSM_GPIO_PINS(201);
+DECLARE_MSM_GPIO_PINS(202);
+DECLARE_MSM_GPIO_PINS(203);
+DECLARE_MSM_GPIO_PINS(204);
+DECLARE_MSM_GPIO_PINS(205);
+DECLARE_MSM_GPIO_PINS(206);
+DECLARE_MSM_GPIO_PINS(207);
+DECLARE_MSM_GPIO_PINS(208);
+DECLARE_MSM_GPIO_PINS(209);
+DECLARE_MSM_GPIO_PINS(210);
+DECLARE_MSM_GPIO_PINS(211);
+DECLARE_MSM_GPIO_PINS(212);
+DECLARE_MSM_GPIO_PINS(213);
+DECLARE_MSM_GPIO_PINS(214);
+DECLARE_MSM_GPIO_PINS(215);
+DECLARE_MSM_GPIO_PINS(216);
+DECLARE_MSM_GPIO_PINS(217);
+DECLARE_MSM_GPIO_PINS(218);
+DECLARE_MSM_GPIO_PINS(219);
+DECLARE_MSM_GPIO_PINS(220);
+DECLARE_MSM_GPIO_PINS(221);
+DECLARE_MSM_GPIO_PINS(222);
+DECLARE_MSM_GPIO_PINS(223);
+DECLARE_MSM_GPIO_PINS(224);
+DECLARE_MSM_GPIO_PINS(225);
+DECLARE_MSM_GPIO_PINS(226);
+DECLARE_MSM_GPIO_PINS(227);
+DECLARE_MSM_GPIO_PINS(228);
+DECLARE_MSM_GPIO_PINS(229);
+DECLARE_MSM_GPIO_PINS(230);
+DECLARE_MSM_GPIO_PINS(231);
+DECLARE_MSM_GPIO_PINS(232);
+DECLARE_MSM_GPIO_PINS(233);
+DECLARE_MSM_GPIO_PINS(234);
+DECLARE_MSM_GPIO_PINS(235);
+DECLARE_MSM_GPIO_PINS(236);
+DECLARE_MSM_GPIO_PINS(237);
+
+static const unsigned int ufs_reset_pins[] = { 238 };
+static const unsigned int sdc2_clk_pins[] = { 239 };
+static const unsigned int sdc2_cmd_pins[] = { 240 };
+static const unsigned int sdc2_data_pins[] = { 241 };
+
+enum x1e80100_functions {
+	msm_mux_gpio,
+	msm_mux_RESOUT_GPIO,
+	msm_mux_aon_cci,
+	msm_mux_aoss_cti,
+	msm_mux_atest_char,
+	msm_mux_atest_char0,
+	msm_mux_atest_char1,
+	msm_mux_atest_char2,
+	msm_mux_atest_char3,
+	msm_mux_atest_usb,
+	msm_mux_audio_ext,
+	msm_mux_audio_ref,
+	msm_mux_cam_aon,
+	msm_mux_cam_mclk,
+	msm_mux_cci_async,
+	msm_mux_cci_i2c,
+	msm_mux_cci_timer0,
+	msm_mux_cci_timer1,
+	msm_mux_cci_timer2,
+	msm_mux_cci_timer3,
+	msm_mux_cci_timer4,
+	msm_mux_cmu_rng0,
+	msm_mux_cmu_rng1,
+	msm_mux_cmu_rng2,
+	msm_mux_cmu_rng3,
+	msm_mux_cri_trng,
+	msm_mux_dbg_out,
+	msm_mux_ddr_bist,
+	msm_mux_ddr_pxi0,
+	msm_mux_ddr_pxi1,
+	msm_mux_ddr_pxi2,
+	msm_mux_ddr_pxi3,
+	msm_mux_ddr_pxi4,
+	msm_mux_ddr_pxi5,
+	msm_mux_ddr_pxi6,
+	msm_mux_ddr_pxi7,
+	msm_mux_edp0_hot,
+	msm_mux_edp0_lcd,
+	msm_mux_edp1_hot,
+	msm_mux_edp1_lcd,
+	msm_mux_eusb0_ac,
+	msm_mux_eusb1_ac,
+	msm_mux_eusb2_ac,
+	msm_mux_eusb3_ac,
+	msm_mux_eusb5_ac,
+	msm_mux_eusb6_ac,
+	msm_mux_gcc_gp1,
+	msm_mux_gcc_gp2,
+	msm_mux_gcc_gp3,
+	msm_mux_i2s0_data0,
+	msm_mux_i2s0_data1,
+	msm_mux_i2s0_sck,
+	msm_mux_i2s0_ws,
+	msm_mux_i2s1_data0,
+	msm_mux_i2s1_data1,
+	msm_mux_i2s1_sck,
+	msm_mux_i2s1_ws,
+	msm_mux_ibi_i3c,
+	msm_mux_jitter_bist,
+	msm_mux_mdp_vsync0,
+	msm_mux_mdp_vsync1,
+	msm_mux_mdp_vsync2,
+	msm_mux_mdp_vsync3,
+	msm_mux_mdp_vsync4,
+	msm_mux_mdp_vsync5,
+	msm_mux_mdp_vsync6,
+	msm_mux_mdp_vsync7,
+	msm_mux_mdp_vsync8,
+	msm_mux_pcie3_clk,
+	msm_mux_pcie4_clk,
+	msm_mux_pcie5_clk,
+	msm_mux_pcie6a_clk,
+	msm_mux_pcie6b_clk,
+	msm_mux_phase_flag,
+	msm_mux_pll_bist,
+	msm_mux_pll_clk,
+	msm_mux_prng_rosc0,
+	msm_mux_prng_rosc1,
+	msm_mux_prng_rosc2,
+	msm_mux_prng_rosc3,
+	msm_mux_qdss_cti,
+	msm_mux_qdss_gpio,
+	msm_mux_qspi00,
+	msm_mux_qspi01,
+	msm_mux_qspi02,
+	msm_mux_qspi03,
+	msm_mux_qspi0_clk,
+	msm_mux_qspi0_cs0,
+	msm_mux_qspi0_cs1,
+	msm_mux_qup0_se0,
+	msm_mux_qup0_se1,
+	msm_mux_qup0_se2,
+	msm_mux_qup0_se3,
+	msm_mux_qup0_se4,
+	msm_mux_qup0_se5,
+	msm_mux_qup0_se6,
+	msm_mux_qup0_se7,
+	msm_mux_qup1_se0,
+	msm_mux_qup1_se1,
+	msm_mux_qup1_se2,
+	msm_mux_qup1_se3,
+	msm_mux_qup1_se4,
+	msm_mux_qup1_se5,
+	msm_mux_qup1_se6,
+	msm_mux_qup1_se7,
+	msm_mux_qup2_se0,
+	msm_mux_qup2_se1,
+	msm_mux_qup2_se2,
+	msm_mux_qup2_se3,
+	msm_mux_qup2_se4,
+	msm_mux_qup2_se5,
+	msm_mux_qup2_se6,
+	msm_mux_qup2_se7,
+	msm_mux_sd_write,
+	msm_mux_sdc4_clk,
+	msm_mux_sdc4_cmd,
+	msm_mux_sdc4_data0,
+	msm_mux_sdc4_data1,
+	msm_mux_sdc4_data2,
+	msm_mux_sdc4_data3,
+	msm_mux_sys_throttle,
+	msm_mux_tb_trig,
+	msm_mux_tgu_ch0,
+	msm_mux_tgu_ch1,
+	msm_mux_tgu_ch2,
+	msm_mux_tgu_ch3,
+	msm_mux_tgu_ch4,
+	msm_mux_tgu_ch5,
+	msm_mux_tgu_ch6,
+	msm_mux_tgu_ch7,
+	msm_mux_tmess_prng0,
+	msm_mux_tmess_prng1,
+	msm_mux_tmess_prng2,
+	msm_mux_tmess_prng3,
+	msm_mux_tsense_pwm1,
+	msm_mux_tsense_pwm2,
+	msm_mux_tsense_pwm3,
+	msm_mux_tsense_pwm4,
+	msm_mux_usb0_dp,
+	msm_mux_usb0_phy,
+	msm_mux_usb0_sbrx,
+	msm_mux_usb0_sbtx,
+	msm_mux_usb1_dp,
+	msm_mux_usb1_phy,
+	msm_mux_usb1_sbrx,
+	msm_mux_usb1_sbtx,
+	msm_mux_usb2_dp,
+	msm_mux_usb2_phy,
+	msm_mux_usb2_sbrx,
+	msm_mux_usb2_sbtx,
+	msm_mux_vsense_trigger,
+	msm_mux__,
+};
+
+static const char * const gpio_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7",
+	"gpio8", "gpio9", "gpio10", "gpio11", "gpio12", "gpio13", "gpio14",
+	"gpio15", "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21",
+	"gpio22", "gpio23", "gpio24", "gpio25", "gpio26", "gpio27", "gpio28",
+	"gpio29", "gpio30", "gpio31", "gpio32", "gpio33", "gpio34", "gpio35",
+	"gpio36", "gpio37", "gpio38", "gpio39", "gpio40", "gpio41", "gpio42",
+	"gpio43", "gpio44", "gpio45", "gpio46", "gpio47", "gpio48", "gpio49",
+	"gpio50", "gpio51", "gpio52", "gpio53", "gpio54", "gpio55", "gpio56",
+	"gpio57", "gpio58", "gpio59", "gpio60", "gpio61", "gpio62", "gpio63",
+	"gpio64", "gpio65", "gpio66", "gpio67", "gpio68", "gpio69", "gpio70",
+	"gpio71", "gpio72", "gpio73", "gpio74", "gpio75", "gpio76", "gpio77",
+	"gpio78", "gpio79", "gpio80", "gpio81", "gpio82", "gpio83", "gpio84",
+	"gpio85", "gpio86", "gpio87", "gpio88", "gpio89", "gpio90", "gpio91",
+	"gpio92", "gpio93", "gpio94", "gpio95", "gpio96", "gpio97", "gpio98",
+	"gpio99", "gpio100", "gpio101", "gpio102", "gpio103", "gpio104",
+	"gpio105", "gpio106", "gpio107", "gpio108", "gpio109", "gpio110",
+	"gpio111", "gpio112", "gpio113", "gpio114", "gpio115", "gpio116",
+	"gpio117", "gpio118", "gpio119", "gpio120", "gpio121", "gpio122",
+	"gpio123", "gpio124", "gpio125", "gpio126", "gpio127", "gpio128",
+	"gpio129", "gpio130", "gpio131", "gpio132", "gpio133", "gpio134",
+	"gpio135", "gpio136", "gpio137", "gpio138", "gpio139", "gpio140",
+	"gpio141", "gpio142", "gpio143", "gpio144", "gpio145", "gpio146",
+	"gpio147", "gpio148", "gpio149", "gpio150", "gpio151", "gpio152",
+	"gpio153", "gpio154", "gpio155", "gpio156", "gpio157", "gpio158",
+	"gpio159", "gpio160", "gpio161", "gpio162", "gpio163", "gpio164",
+	"gpio165", "gpio166", "gpio167", "gpio168", "gpio169", "gpio170",
+	"gpio171", "gpio172", "gpio173", "gpio174", "gpio175", "gpio176",
+	"gpio177", "gpio178", "gpio179", "gpio180", "gpio181", "gpio182",
+	"gpio183", "gpio184", "gpio185", "gpio186", "gpio187", "gpio188",
+	"gpio189", "gpio190", "gpio191", "gpio192", "gpio193", "gpio194",
+	"gpio195", "gpio196", "gpio197", "gpio198", "gpio199", "gpio200",
+	"gpio201", "gpio202", "gpio203", "gpio204", "gpio205", "gpio206",
+	"gpio207", "gpio208", "gpio209", "gpio210", "gpio211", "gpio212",
+	"gpio213", "gpio214", "gpio215", "gpio216", "gpio217", "gpio218",
+	"gpio219", "gpio220", "gpio221", "gpio222", "gpio223", "gpio224",
+	"gpio225", "gpio226", "gpio227", "gpio228", "gpio229", "gpio230",
+	"gpio231", "gpio232", "gpio233", "gpio234", "gpio235", "gpio236",
+	"gpio237",
+};
+
+static const char * const RESOUT_GPIO_groups[] = {
+	"gpio160",
+};
+
+static const char * const aon_cci_groups[] = {
+	"gpio235", "gpio236",
+};
+
+static const char * const aoss_cti_groups[] = {
+	"gpio60", "gpio61", "gpio62", "gpio63",
+};
+
+static const char * const atest_char_groups[] = {
+	"gpio181",
+};
+
+static const char * const atest_char0_groups[] = {
+	"gpio185",
+};
+
+static const char * const atest_char1_groups[] = {
+	"gpio184",
+};
+
+static const char * const atest_char2_groups[] = {
+	"gpio188",
+};
+
+static const char * const atest_char3_groups[] = {
+	"gpio182",
+};
+
+static const char * const atest_usb_groups[] = {
+	"gpio9", "gpio10", "gpio35", "gpio38", "gpio41", "gpio42",
+	"gpio43", "gpio44", "gpio45", "gpio46", "gpio47", "gpio48",
+	"gpio49", "gpio50", "gpio51", "gpio52", "gpio53", "gpio54",
+	"gpio58", "gpio59", "gpio65", "gpio66", "gpio67", "gpio72",
+	"gpio73", "gpio74", "gpio75", "gpio80", "gpio81", "gpio83",
+};
+
+static const char * const audio_ext_groups[] = {
+	"gpio134", "gpio142",
+};
+
+static const char * const audio_ref_groups[] = {
+	"gpio142",
+};
+
+static const char * const cam_aon_groups[] = {
+	"gpio100",
+};
+
+static const char * const cam_mclk_groups[] = {
+	"gpio96", "gpio97", "gpio98", "gpio99",
+};
+
+static const char * const cci_async_groups[] = {
+	"gpio111", "gpio112", "gpio113",
+};
+
+static const char * const cci_i2c_groups[] = {
+	"gpio101", "gpio102", "gpio103", "gpio104", "gpio105", "gpio106",
+};
+
+static const char * const cci_timer0_groups[] = {
+	"gpio109",
+};
+
+static const char * const cci_timer1_groups[] = {
+	"gpio110",
+};
+
+static const char * const cci_timer2_groups[] = {
+	"gpio111",
+};
+
+static const char * const cci_timer3_groups[] = {
+	"gpio112",
+};
+
+static const char * const cci_timer4_groups[] = {
+	"gpio113",
+};
+
+static const char * const cmu_rng0_groups[] = {
+	"gpio48",
+};
+
+static const char * const cmu_rng1_groups[] = {
+	"gpio47",
+};
+
+static const char * const cmu_rng2_groups[] = {
+	"gpio46",
+};
+
+static const char * const cmu_rng3_groups[] = {
+	"gpio45",
+};
+
+static const char * const cri_trng_groups[] = {
+	"gpio187",
+};
+
+static const char * const dbg_out_groups[] = {
+	"gpio51",
+};
+
+static const char * const ddr_bist_groups[] = {
+	"gpio54", "gpio55", "gpio56", "gpio57",
+};
+
+static const char * const ddr_pxi0_groups[] = {
+	"gpio9", "gpio38",
+};
+
+static const char * const ddr_pxi1_groups[] = {
+	"gpio10", "gpio41",
+};
+
+static const char * const ddr_pxi2_groups[] = {
+	"gpio42", "gpio43",
+};
+
+static const char * const ddr_pxi3_groups[] = {
+	"gpio44", "gpio45",
+};
+
+static const char * const ddr_pxi4_groups[] = {
+	"gpio46", "gpio47",
+};
+
+static const char * const ddr_pxi5_groups[] = {
+	"gpio48", "gpio49",
+};
+
+static const char * const ddr_pxi6_groups[] = {
+	"gpio50", "gpio51",
+};
+
+static const char * const ddr_pxi7_groups[] = {
+	"gpio52", "gpio53",
+};
+
+static const char * const edp0_hot_groups[] = {
+	"gpio119",
+};
+
+static const char * const edp0_lcd_groups[] = {
+	"gpio120",
+};
+
+static const char * const edp1_hot_groups[] = {
+	"gpio120",
+};
+
+static const char * const edp1_lcd_groups[] = {
+	"gpio115", "gpio119",
+};
+
+static const char * const eusb0_ac_groups[] = {
+	"gpio168",
+};
+
+static const char * const eusb1_ac_groups[] = {
+	"gpio177",
+};
+
+static const char * const eusb2_ac_groups[] = {
+	"gpio186",
+};
+
+static const char * const eusb3_ac_groups[] = {
+	"gpio169",
+};
+
+static const char * const eusb5_ac_groups[] = {
+	"gpio187",
+};
+
+static const char * const eusb6_ac_groups[] = {
+	"gpio178",
+};
+
+static const char * const gcc_gp1_groups[] = {
+	"gpio71", "gpio72",
+};
+
+static const char * const gcc_gp2_groups[] = {
+	"gpio64", "gpio73",
+};
+
+static const char * const gcc_gp3_groups[] = {
+	"gpio74", "gpio82",
+};
+
+static const char * const i2s0_data0_groups[] = {
+	"gpio136",
+};
+
+static const char * const i2s0_data1_groups[] = {
+	"gpio137",
+};
+
+static const char * const i2s0_sck_groups[] = {
+	"gpio135",
+};
+
+static const char * const i2s0_ws_groups[] = {
+	"gpio138",
+};
+
+static const char * const i2s1_data0_groups[] = {
+	"gpio140",
+};
+
+static const char * const i2s1_data1_groups[] = {
+	"gpio142",
+};
+
+static const char * const i2s1_sck_groups[] = {
+	"gpio139",
+};
+
+static const char * const i2s1_ws_groups[] = {
+	"gpio141",
+};
+
+static const char * const ibi_i3c_groups[] = {
+	"gpio0", "gpio1", "gpio32", "gpio33", "gpio36", "gpio37", "gpio68",
+	"gpio69",
+};
+
+static const char * const jitter_bist_groups[] = {
+	"gpio42",
+};
+
+static const char * const mdp_vsync0_groups[] = {
+	"gpio114",
+};
+
+static const char * const mdp_vsync1_groups[] = {
+	"gpio114",
+};
+
+static const char * const mdp_vsync2_groups[] = {
+	"gpio115",
+};
+
+static const char * const mdp_vsync3_groups[] = {
+	"gpio115",
+};
+
+static const char * const mdp_vsync4_groups[] = {
+	"gpio109",
+};
+
+static const char * const mdp_vsync5_groups[] = {
+	"gpio110",
+};
+
+static const char * const mdp_vsync6_groups[] = {
+	"gpio111",
+};
+
+static const char * const mdp_vsync7_groups[] = {
+	"gpio112",
+};
+
+static const char * const mdp_vsync8_groups[] = {
+	"gpio113",
+};
+
+static const char * const pcie3_clk_groups[] = {
+	"gpio144",
+};
+
+static const char * const pcie4_clk_groups[] = {
+	"gpio147",
+};
+
+static const char * const pcie5_clk_groups[] = {
+	"gpio150",
+};
+
+static const char * const pcie6a_clk_groups[] = {
+	"gpio153",
+};
+
+static const char * const pcie6b_clk_groups[] = {
+	"gpio156",
+};
+
+static const char * const phase_flag_groups[] = {
+	"gpio6", "gpio7", "gpio8", "gpio11", "gpio12", "gpio13",
+	"gpio14", "gpio15", "gpio16", "gpio17", "gpio18", "gpio19",
+	"gpio20", "gpio21", "gpio22", "gpio23", "gpio24", "gpio25",
+	"gpio26", "gpio27", "gpio39", "gpio40", "gpio76", "gpio77",
+	"gpio78", "gpio181", "gpio182", "gpio184", "gpio185",
+	"gpio186", "gpio187", "gpio188",
+};
+
+static const char * const pll_bist_groups[] = {
+	"gpio28",
+};
+
+static const char * const pll_clk_groups[] = {
+	"gpio35",
+};
+
+static const char * const prng_rosc0_groups[] = {
+	"gpio186",
+};
+
+static const char * const prng_rosc1_groups[] = {
+	"gpio188",
+};
+
+static const char * const prng_rosc2_groups[] = {
+	"gpio182",
+};
+
+static const char * const prng_rosc3_groups[] = {
+	"gpio181",
+};
+
+static const char * const qdss_cti_groups[] = {
+	"gpio18", "gpio19", "gpio23", "gpio27", "gpio161", "gpio162",
+	"gpio215", "gpio217",
+};
+
+static const char * const qdss_gpio_groups[] = {
+	"gpio96", "gpio97", "gpio98", "gpio99", "gpio100", "gpio101",
+	"gpio102", "gpio103", "gpio104", "gpio105", "gpio106", "gpio107",
+	"gpio108", "gpio109", "gpio110", "gpio111", "gpio112", "gpio113",
+	"gpio219", "gpio220", "gpio221", "gpio222", "gpio223", "gpio224",
+	"gpio225", "gpio226", "gpio227", "gpio228", "gpio229", "gpio230",
+	"gpio231", "gpio232", "gpio233", "gpio234", "gpio235", "gpio236",
+};
+
+static const char * const qspi00_groups[] = {
+	"gpio128",
+};
+
+static const char * const qspi01_groups[] = {
+	"gpio129",
+};
+
+static const char * const qspi02_groups[] = {
+	"gpio130",
+};
+
+static const char * const qspi03_groups[] = {
+	"gpio131",
+};
+
+static const char * const qspi0_clk_groups[] = {
+	"gpio127",
+};
+
+static const char * const qspi0_cs0_groups[] = {
+	"gpio132",
+};
+
+static const char * const qspi0_cs1_groups[] = {
+	"gpio133",
+};
+
+static const char * const qup0_se0_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3",
+};
+
+static const char * const qup0_se1_groups[] = {
+	"gpio4", "gpio5", "gpio6", "gpio7",
+};
+
+static const char * const qup0_se2_groups[] = {
+	"gpio8", "gpio9", "gpio10", "gpio11", "gpio17", "gpio18", "gpio19",
+};
+
+static const char * const qup0_se3_groups[] = {
+	"gpio12", "gpio13", "gpio14", "gpio15", "gpio21", "gpio22", "gpio23",
+};
+
+static const char * const qup0_se4_groups[] = {
+	"gpio16", "gpio17", "gpio18", "gpio19",
+};
+
+static const char * const qup0_se5_groups[] = {
+	"gpio20", "gpio21", "gpio22", "gpio23",
+};
+
+static const char * const qup0_se6_groups[] = {
+	"gpio24", "gpio25", "gpio26", "gpio27",
+};
+
+static const char * const qup0_se7_groups[] = {
+	"gpio12", "gpio13", "gpio14", "gpio15",
+};
+
+static const char * const qup1_se0_groups[] = {
+	"gpio32", "gpio33", "gpio34", "gpio35",
+};
+
+static const char * const qup1_se1_groups[] = {
+	"gpio36", "gpio37", "gpio38", "gpio39",
+};
+
+static const char * const qup1_se2_groups[] = {
+	"gpio40", "gpio41", "gpio42", "gpio43", "gpio49", "gpio50", "gpio51",
+};
+
+static const char * const qup1_se3_groups[] = {
+	"gpio33", "gpio34", "gpio35", "gpio44", "gpio45", "gpio46", "gpio47",
+};
+
+static const char * const qup1_se4_groups[] = {
+	"gpio48", "gpio49", "gpio50", "gpio51",
+};
+
+static const char * const qup1_se5_groups[] = {
+	"gpio52", "gpio53", "gpio54", "gpio55",
+};
+
+static const char * const qup1_se6_groups[] = {
+	"gpio56", "gpio57", "gpio58", "gpio59",
+};
+
+static const char * const qup1_se7_groups[] = {
+	"gpio52", "gpio53", "gpio54", "gpio55",
+};
+
+static const char * const qup2_se0_groups[] = {
+	"gpio64", "gpio65", "gpio66", "gpio67",
+};
+
+static const char * const qup2_se1_groups[] = {
+	"gpio68", "gpio69", "gpio70", "gpio71",
+};
+
+static const char * const qup2_se2_groups[] = {
+	"gpio72", "gpio73", "gpio74", "gpio75", "gpio81", "gpio82", "gpio83",
+};
+
+static const char * const qup2_se3_groups[] = {
+	"gpio65", "gpio66", "gpio67", "gpio76", "gpio77", "gpio78", "gpio79",
+};
+
+static const char * const qup2_se4_groups[] = {
+	"gpio80", "gpio81", "gpio82", "gpio83",
+};
+
+static const char * const qup2_se5_groups[] = {
+	"gpio84", "gpio85", "gpio86", "gpio87",
+};
+
+static const char * const qup2_se6_groups[] = {
+	"gpio88", "gpio89", "gpio90", "gpio91",
+};
+
+static const char * const qup2_se7_groups[] = {
+	"gpio84", "gpio85", "gpio86", "gpio87",
+};
+
+static const char * const sd_write_groups[] = {
+	"gpio162",
+};
+
+static const char * const sdc4_clk_groups[] = {
+	"gpio127",
+};
+
+static const char * const sdc4_cmd_groups[] = {
+	"gpio132",
+};
+
+static const char * const sdc4_data0_groups[] = {
+	"gpio128",
+};
+
+static const char * const sdc4_data1_groups[] = {
+	"gpio129",
+};
+
+static const char * const sdc4_data2_groups[] = {
+	"gpio130",
+};
+
+static const char * const sdc4_data3_groups[] = {
+	"gpio131",
+};
+
+static const char * const sys_throttle_groups[] = {
+	"gpio39", "gpio94",
+};
+
+static const char * const tb_trig_groups[] = {
+	"gpio133", "gpio137",
+};
+
+static const char * const tgu_ch0_groups[] = {
+	"gpio81",
+};
+
+static const char * const tgu_ch1_groups[] = {
+	"gpio65",
+};
+
+static const char * const tgu_ch2_groups[] = {
+	"gpio66",
+};
+
+static const char * const tgu_ch3_groups[] = {
+	"gpio67",
+};
+
+static const char * const tgu_ch4_groups[] = {
+	"gpio68",
+};
+
+static const char * const tgu_ch5_groups[] = {
+	"gpio69",
+};
+
+static const char * const tgu_ch6_groups[] = {
+	"gpio83",
+};
+
+static const char * const tgu_ch7_groups[] = {
+	"gpio80",
+};
+
+static const char * const tmess_prng0_groups[] = {
+	"gpio92",
+};
+
+static const char * const tmess_prng1_groups[] = {
+	"gpio93",
+};
+
+static const char * const tmess_prng2_groups[] = {
+	"gpio94",
+};
+
+static const char * const tmess_prng3_groups[] = {
+	"gpio95",
+};
+
+static const char * const tsense_pwm1_groups[] = {
+	"gpio34",
+};
+
+static const char * const tsense_pwm2_groups[] = {
+	"gpio34",
+};
+
+static const char * const tsense_pwm3_groups[] = {
+	"gpio34",
+};
+
+static const char * const tsense_pwm4_groups[] = {
+	"gpio34",
+};
+
+static const char * const usb0_dp_groups[] = {
+	"gpio122",
+};
+
+static const char * const usb0_phy_groups[] = {
+	"gpio121",
+};
+
+static const char * const usb0_sbrx_groups[] = {
+	"gpio163",
+};
+
+static const char * const usb0_sbtx_groups[] = {
+	"gpio164", "gpio165",
+};
+
+static const char * const usb1_dp_groups[] = {
+	"gpio124",
+};
+
+static const char * const usb1_phy_groups[] = {
+	"gpio123",
+};
+
+static const char * const usb1_sbrx_groups[] = {
+	"gpio172",
+};
+
+static const char * const usb1_sbtx_groups[] = {
+	"gpio173", "gpio174",
+};
+
+static const char * const usb2_dp_groups[] = {
+	"gpio126",
+};
+
+static const char * const usb2_phy_groups[] = {
+	"gpio125",
+};
+
+static const char * const usb2_sbrx_groups[] = {
+	"gpio181",
+};
+
+static const char * const usb2_sbtx_groups[] = {
+	"gpio182", "gpio183",
+};
+
+static const char * const vsense_trigger_groups[] = {
+	"gpio38",
+};
+
+static const struct pinfunction x1e80100_functions[] = {
+	MSM_PIN_FUNCTION(gpio),
+	MSM_PIN_FUNCTION(RESOUT_GPIO),
+	MSM_PIN_FUNCTION(aon_cci),
+	MSM_PIN_FUNCTION(aoss_cti),
+	MSM_PIN_FUNCTION(atest_char),
+	MSM_PIN_FUNCTION(atest_char0),
+	MSM_PIN_FUNCTION(atest_char1),
+	MSM_PIN_FUNCTION(atest_char2),
+	MSM_PIN_FUNCTION(atest_char3),
+	MSM_PIN_FUNCTION(atest_usb),
+	MSM_PIN_FUNCTION(audio_ext),
+	MSM_PIN_FUNCTION(audio_ref),
+	MSM_PIN_FUNCTION(cam_aon),
+	MSM_PIN_FUNCTION(cam_mclk),
+	MSM_PIN_FUNCTION(cci_async),
+	MSM_PIN_FUNCTION(cci_i2c),
+	MSM_PIN_FUNCTION(cci_timer0),
+	MSM_PIN_FUNCTION(cci_timer1),
+	MSM_PIN_FUNCTION(cci_timer2),
+	MSM_PIN_FUNCTION(cci_timer3),
+	MSM_PIN_FUNCTION(cci_timer4),
+	MSM_PIN_FUNCTION(cmu_rng0),
+	MSM_PIN_FUNCTION(cmu_rng1),
+	MSM_PIN_FUNCTION(cmu_rng2),
+	MSM_PIN_FUNCTION(cmu_rng3),
+	MSM_PIN_FUNCTION(cri_trng),
+	MSM_PIN_FUNCTION(dbg_out),
+	MSM_PIN_FUNCTION(ddr_bist),
+	MSM_PIN_FUNCTION(ddr_pxi0),
+	MSM_PIN_FUNCTION(ddr_pxi1),
+	MSM_PIN_FUNCTION(ddr_pxi2),
+	MSM_PIN_FUNCTION(ddr_pxi3),
+	MSM_PIN_FUNCTION(ddr_pxi4),
+	MSM_PIN_FUNCTION(ddr_pxi5),
+	MSM_PIN_FUNCTION(ddr_pxi6),
+	MSM_PIN_FUNCTION(ddr_pxi7),
+	MSM_PIN_FUNCTION(edp0_hot),
+	MSM_PIN_FUNCTION(edp0_lcd),
+	MSM_PIN_FUNCTION(edp1_hot),
+	MSM_PIN_FUNCTION(edp1_lcd),
+	MSM_PIN_FUNCTION(eusb0_ac),
+	MSM_PIN_FUNCTION(eusb1_ac),
+	MSM_PIN_FUNCTION(eusb2_ac),
+	MSM_PIN_FUNCTION(eusb3_ac),
+	MSM_PIN_FUNCTION(eusb5_ac),
+	MSM_PIN_FUNCTION(eusb6_ac),
+	MSM_PIN_FUNCTION(gcc_gp1),
+	MSM_PIN_FUNCTION(gcc_gp2),
+	MSM_PIN_FUNCTION(gcc_gp3),
+	MSM_PIN_FUNCTION(i2s0_data0),
+	MSM_PIN_FUNCTION(i2s0_data1),
+	MSM_PIN_FUNCTION(i2s0_sck),
+	MSM_PIN_FUNCTION(i2s0_ws),
+	MSM_PIN_FUNCTION(i2s1_data0),
+	MSM_PIN_FUNCTION(i2s1_data1),
+	MSM_PIN_FUNCTION(i2s1_sck),
+	MSM_PIN_FUNCTION(i2s1_ws),
+	MSM_PIN_FUNCTION(ibi_i3c),
+	MSM_PIN_FUNCTION(jitter_bist),
+	MSM_PIN_FUNCTION(mdp_vsync0),
+	MSM_PIN_FUNCTION(mdp_vsync1),
+	MSM_PIN_FUNCTION(mdp_vsync2),
+	MSM_PIN_FUNCTION(mdp_vsync3),
+	MSM_PIN_FUNCTION(mdp_vsync4),
+	MSM_PIN_FUNCTION(mdp_vsync5),
+	MSM_PIN_FUNCTION(mdp_vsync6),
+	MSM_PIN_FUNCTION(mdp_vsync7),
+	MSM_PIN_FUNCTION(mdp_vsync8),
+	MSM_PIN_FUNCTION(pcie3_clk),
+	MSM_PIN_FUNCTION(pcie4_clk),
+	MSM_PIN_FUNCTION(pcie5_clk),
+	MSM_PIN_FUNCTION(pcie6a_clk),
+	MSM_PIN_FUNCTION(pcie6b_clk),
+	MSM_PIN_FUNCTION(phase_flag),
+	MSM_PIN_FUNCTION(pll_bist),
+	MSM_PIN_FUNCTION(pll_clk),
+	MSM_PIN_FUNCTION(prng_rosc0),
+	MSM_PIN_FUNCTION(prng_rosc1),
+	MSM_PIN_FUNCTION(prng_rosc2),
+	MSM_PIN_FUNCTION(prng_rosc3),
+	MSM_PIN_FUNCTION(qdss_cti),
+	MSM_PIN_FUNCTION(qdss_gpio),
+	MSM_PIN_FUNCTION(qspi00),
+	MSM_PIN_FUNCTION(qspi01),
+	MSM_PIN_FUNCTION(qspi02),
+	MSM_PIN_FUNCTION(qspi03),
+	MSM_PIN_FUNCTION(qspi0_clk),
+	MSM_PIN_FUNCTION(qspi0_cs0),
+	MSM_PIN_FUNCTION(qspi0_cs1),
+	MSM_PIN_FUNCTION(qup0_se0),
+	MSM_PIN_FUNCTION(qup0_se1),
+	MSM_PIN_FUNCTION(qup0_se2),
+	MSM_PIN_FUNCTION(qup0_se3),
+	MSM_PIN_FUNCTION(qup0_se4),
+	MSM_PIN_FUNCTION(qup0_se5),
+	MSM_PIN_FUNCTION(qup0_se6),
+	MSM_PIN_FUNCTION(qup0_se7),
+	MSM_PIN_FUNCTION(qup1_se0),
+	MSM_PIN_FUNCTION(qup1_se1),
+	MSM_PIN_FUNCTION(qup1_se2),
+	MSM_PIN_FUNCTION(qup1_se3),
+	MSM_PIN_FUNCTION(qup1_se4),
+	MSM_PIN_FUNCTION(qup1_se5),
+	MSM_PIN_FUNCTION(qup1_se6),
+	MSM_PIN_FUNCTION(qup1_se7),
+	MSM_PIN_FUNCTION(qup2_se0),
+	MSM_PIN_FUNCTION(qup2_se1),
+	MSM_PIN_FUNCTION(qup2_se2),
+	MSM_PIN_FUNCTION(qup2_se3),
+	MSM_PIN_FUNCTION(qup2_se4),
+	MSM_PIN_FUNCTION(qup2_se5),
+	MSM_PIN_FUNCTION(qup2_se6),
+	MSM_PIN_FUNCTION(qup2_se7),
+	MSM_PIN_FUNCTION(sd_write),
+	MSM_PIN_FUNCTION(sdc4_clk),
+	MSM_PIN_FUNCTION(sdc4_cmd),
+	MSM_PIN_FUNCTION(sdc4_data0),
+	MSM_PIN_FUNCTION(sdc4_data1),
+	MSM_PIN_FUNCTION(sdc4_data2),
+	MSM_PIN_FUNCTION(sdc4_data3),
+	MSM_PIN_FUNCTION(sys_throttle),
+	MSM_PIN_FUNCTION(tb_trig),
+	MSM_PIN_FUNCTION(tgu_ch0),
+	MSM_PIN_FUNCTION(tgu_ch1),
+	MSM_PIN_FUNCTION(tgu_ch2),
+	MSM_PIN_FUNCTION(tgu_ch3),
+	MSM_PIN_FUNCTION(tgu_ch4),
+	MSM_PIN_FUNCTION(tgu_ch5),
+	MSM_PIN_FUNCTION(tgu_ch6),
+	MSM_PIN_FUNCTION(tgu_ch7),
+	MSM_PIN_FUNCTION(tmess_prng0),
+	MSM_PIN_FUNCTION(tmess_prng1),
+	MSM_PIN_FUNCTION(tmess_prng2),
+	MSM_PIN_FUNCTION(tmess_prng3),
+	MSM_PIN_FUNCTION(tsense_pwm1),
+	MSM_PIN_FUNCTION(tsense_pwm2),
+	MSM_PIN_FUNCTION(tsense_pwm3),
+	MSM_PIN_FUNCTION(tsense_pwm4),
+	MSM_PIN_FUNCTION(usb0_dp),
+	MSM_PIN_FUNCTION(usb0_phy),
+	MSM_PIN_FUNCTION(usb0_sbrx),
+	MSM_PIN_FUNCTION(usb0_sbtx),
+	MSM_PIN_FUNCTION(usb1_dp),
+	MSM_PIN_FUNCTION(usb1_phy),
+	MSM_PIN_FUNCTION(usb1_sbrx),
+	MSM_PIN_FUNCTION(usb1_sbtx),
+	MSM_PIN_FUNCTION(usb2_dp),
+	MSM_PIN_FUNCTION(usb2_phy),
+	MSM_PIN_FUNCTION(usb2_sbrx),
+	MSM_PIN_FUNCTION(usb2_sbtx),
+	MSM_PIN_FUNCTION(vsense_trigger),
+};
+
+/*
+ * Every pin is maintained as a single group, and missing or non-existing pin
+ * would be maintained as dummy group to synchronize pin group index with
+ * pin descriptor registered with pinctrl core.
+ * Clients would not be able to request these dummy pin groups.
+ */
+static const struct msm_pingroup x1e80100_groups[] = {
+	[0] = PINGROUP(0, qup0_se0, ibi_i3c, _, _, _, _, _, _, _),
+	[1] = PINGROUP(1, qup0_se0, ibi_i3c, _, _, _, _, _, _, _),
+	[2] = PINGROUP(2, qup0_se0, _, _, _, _, _, _, _, _),
+	[3] = PINGROUP(3, qup0_se0, _, _, _, _, _, _, _, _),
+	[4] = PINGROUP(4, qup0_se1, _, _, _, _, _, _, _, _),
+	[5] = PINGROUP(5, qup0_se1, _, _, _, _, _, _, _, _),
+	[6] = PINGROUP(6, qup0_se1, phase_flag, _, _, _, _, _, _, _),
+	[7] = PINGROUP(7, qup0_se1, phase_flag, _, _, _, _, _, _, _),
+	[8] = PINGROUP(8, qup0_se2, phase_flag, _, _, _, _, _, _, _),
+	[9] = PINGROUP(9, qup0_se2, _, atest_usb, ddr_pxi0, _, _, _, _, _),
+	[10] = PINGROUP(10, qup0_se2, _, atest_usb, ddr_pxi1, _, _, _, _, _),
+	[11] = PINGROUP(11, qup0_se2, phase_flag, _, _, _, _, _, _, _),
+	[12] = PINGROUP(12, qup0_se3, qup0_se7, phase_flag, _, _, _, _, _, _),
+	[13] = PINGROUP(13, qup0_se3, qup0_se7, phase_flag, _, _, _, _, _, _),
+	[14] = PINGROUP(14, qup0_se3, qup0_se7, phase_flag, _, _, _, _, _, _),
+	[15] = PINGROUP(15, qup0_se3, qup0_se7, phase_flag, _, _, _, _, _, _),
+	[16] = PINGROUP(16, qup0_se4, phase_flag, _, _, _, _, _, _, _),
+	[17] = PINGROUP(17, qup0_se4, qup0_se2, phase_flag, _, _, _, _, _, _),
+	[18] = PINGROUP(18, qup0_se4, qup0_se2, phase_flag, _, qdss_cti, _, _, _, _),
+	[19] = PINGROUP(19, qup0_se4, qup0_se2, phase_flag, _, qdss_cti, _, _, _, _),
+	[20] = PINGROUP(20, qup0_se5, _, phase_flag, _, _, _, _, _, _),
+	[21] = PINGROUP(21, qup0_se5, qup0_se3, _, phase_flag, _, _, _, _, _),
+	[22] = PINGROUP(22, qup0_se5, qup0_se3, _, phase_flag, _, _, _, _, _),
+	[23] = PINGROUP(23, qup0_se5, qup0_se3, phase_flag, _, qdss_cti, _, _, _, _),
+	[24] = PINGROUP(24, qup0_se6, phase_flag, _, _, _, _, _, _, _),
+	[25] = PINGROUP(25, qup0_se6, phase_flag, _, _, _, _, _, _, _),
+	[26] = PINGROUP(26, qup0_se6, phase_flag, _, _, _, _, _, _, _),
+	[27] = PINGROUP(27, qup0_se6, phase_flag, _, qdss_cti, _, _, _, _, _),
+	[28] = PINGROUP(28, pll_bist, _, _, _, _, _, _, _, _),
+	[29] = PINGROUP(29, _, _, _, _, _, _, _, _, _),
+	[30] = PINGROUP(30, _, _, _, _, _, _, _, _, _),
+	[31] = PINGROUP(31, _, _, _, _, _, _, _, _, _),
+	[32] = PINGROUP(32, qup1_se0, ibi_i3c, _, _, _, _, _, _, _),
+	[33] = PINGROUP(33, qup1_se0, ibi_i3c, qup1_se3, _, _, _, _, _, _),
+	[34] = PINGROUP(34, qup1_se0, qup1_se3, tsense_pwm1, tsense_pwm2, tsense_pwm3, tsense_pwm4, _, _, _),
+	[35] = PINGROUP(35, qup1_se0, qup1_se3, pll_clk, atest_usb, _, _, _, _, _),
+	[36] = PINGROUP(36, qup1_se1, ibi_i3c, _, _, _, _, _, _, _),
+	[37] = PINGROUP(37, qup1_se1, ibi_i3c, _, _, _, _, _, _, _),
+	[38] = PINGROUP(38, qup1_se1, vsense_trigger, atest_usb, ddr_pxi0, _, _, _, _, _),
+	[39] = PINGROUP(39, qup1_se1, sys_throttle, phase_flag, _, _, _, _, _, _),
+	[40] = PINGROUP(40, qup1_se2, phase_flag, _, _, _, _, _, _, _),
+	[41] = PINGROUP(41, qup1_se2, atest_usb, ddr_pxi1, _, _, _, _, _, _),
+	[42] = PINGROUP(42, qup1_se2, jitter_bist, atest_usb, ddr_pxi2, _, _, _, _, _),
+	[43] = PINGROUP(43, qup1_se2, _, atest_usb, ddr_pxi2, _, _, _, _, _),
+	[44] = PINGROUP(44, qup1_se3, _, atest_usb, ddr_pxi3, _, _, _, _, _),
+	[45] = PINGROUP(45, qup1_se3, cmu_rng3, _, atest_usb, ddr_pxi3, _, _, _, _),
+	[46] = PINGROUP(46, qup1_se3, cmu_rng2, _, atest_usb, ddr_pxi4, _, _, _, _),
+	[47] = PINGROUP(47, qup1_se3, cmu_rng1, _, atest_usb, ddr_pxi4, _, _, _, _),
+	[48] = PINGROUP(48, qup1_se4, cmu_rng0, _, atest_usb, ddr_pxi5, _, _, _, _),
+	[49] = PINGROUP(49, qup1_se4, qup1_se2, _, atest_usb, ddr_pxi5, _, _, _, _),
+	[50] = PINGROUP(50, qup1_se4, qup1_se2, _, atest_usb, ddr_pxi6, _, _, _, _),
+	[51] = PINGROUP(51, qup1_se4, qup1_se2, dbg_out, atest_usb, ddr_pxi6, _, _, _, _),
+	[52] = PINGROUP(52, qup1_se5, qup1_se7, atest_usb, ddr_pxi7, _, _, _, _, _),
+	[53] = PINGROUP(53, qup1_se5, qup1_se7, _, atest_usb, ddr_pxi7, _, _, _, _),
+	[54] = PINGROUP(54, qup1_se5, qup1_se7, ddr_bist, atest_usb, _, _, _, _, _),
+	[55] = PINGROUP(55, qup1_se5, qup1_se7, ddr_bist, _, _, _, _, _, _),
+	[56] = PINGROUP(56, qup1_se6, ddr_bist, _, _, _, _, _, _, _),
+	[57] = PINGROUP(57, qup1_se6, ddr_bist, _, _, _, _, _, _, _),
+	[58] = PINGROUP(58, qup1_se6, atest_usb, _, _, _, _, _, _, _),
+	[59] = PINGROUP(59, qup1_se6, atest_usb, _, _, _, _, _, _, _),
+	[60] = PINGROUP(60, aoss_cti, _, _, _, _, _, _, _, _),
+	[61] = PINGROUP(61, aoss_cti, _, _, _, _, _, _, _, _),
+	[62] = PINGROUP(62, aoss_cti, _, _, _, _, _, _, _, _),
+	[63] = PINGROUP(63, aoss_cti, _, _, _, _, _, _, _, _),
+	[64] = PINGROUP(64, qup2_se0, gcc_gp2, _, _, _, _, _, _, _),
+	[65] = PINGROUP(65, qup2_se0, qup2_se3, tgu_ch1, atest_usb, _, _, _, _, _),
+	[66] = PINGROUP(66, qup2_se0, qup2_se3, tgu_ch2, atest_usb, _, _, _, _, _),
+	[67] = PINGROUP(67, qup2_se0, qup2_se3, tgu_ch3, atest_usb, _, _, _, _, _),
+	[68] = PINGROUP(68, qup2_se1, ibi_i3c, tgu_ch4, _, _, _, _, _, _),
+	[69] = PINGROUP(69, qup2_se1, ibi_i3c, tgu_ch5, _, _, _, _, _, _),
+	[70] = PINGROUP(70, qup2_se1, _, _, _, _, _, _, _, _),
+	[71] = PINGROUP(71, qup2_se1, gcc_gp1, _, _, _, _, _, _, _),
+	[72] = PINGROUP(72, qup2_se2, gcc_gp1, atest_usb, _, _, _, _, _, _),
+	[73] = PINGROUP(73, qup2_se2, gcc_gp2, atest_usb, _, _, _, _, _, _),
+	[74] = PINGROUP(74, qup2_se2, gcc_gp3, atest_usb, _, _, _, _, _, _),
+	[75] = PINGROUP(75, qup2_se2, atest_usb, _, _, _, _, _, _, _),
+	[76] = PINGROUP(76, qup2_se3, phase_flag, _, _, _, _, _, _, _),
+	[77] = PINGROUP(77, qup2_se3, phase_flag, _, _, _, _, _, _, _),
+	[78] = PINGROUP(78, qup2_se3, phase_flag, _, _, _, _, _, _, _),
+	[79] = PINGROUP(79, qup2_se3, _, _, _, _, _, _, _, _),
+	[80] = PINGROUP(80, qup2_se4, tgu_ch7, atest_usb, _, _, _, _, _, _),
+	[81] = PINGROUP(81, qup2_se4, qup2_se2, tgu_ch0, atest_usb, _, _, _, _, _),
+	[82] = PINGROUP(82, qup2_se4, qup2_se2, gcc_gp3, _, _, _, _, _, _),
+	[83] = PINGROUP(83, qup2_se4, qup2_se2, tgu_ch6, atest_usb, _, _, _, _, _),
+	[84] = PINGROUP(84, qup2_se5, qup2_se7, _, _, _, _, _, _, _),
+	[85] = PINGROUP(85, qup2_se5, qup2_se7, _, _, _, _, _, _, _),
+	[86] = PINGROUP(86, qup2_se5, qup2_se7, _, _, _, _, _, _, _),
+	[87] = PINGROUP(87, qup2_se5, qup2_se7, _, _, _, _, _, _, _),
+	[88] = PINGROUP(88, qup2_se6, _, _, _, _, _, _, _, _),
+	[89] = PINGROUP(89, qup2_se6, _, _, _, _, _, _, _, _),
+	[90] = PINGROUP(90, qup2_se6, _, _, _, _, _, _, _, _),
+	[91] = PINGROUP(91, qup2_se6, _, _, _, _, _, _, _, _),
+	[92] = PINGROUP(92, tmess_prng0, _, _, _, _, _, _, _, _),
+	[93] = PINGROUP(93, tmess_prng1, _, _, _, _, _, _, _, _),
+	[94] = PINGROUP(94, sys_throttle, tmess_prng2, _, _, _, _, _, _, _),
+	[95] = PINGROUP(95, tmess_prng3, _, _, _, _, _, _, _, _),
+	[96] = PINGROUP(96, cam_mclk, qdss_gpio, _, _, _, _, _, _, _),
+	[97] = PINGROUP(97, cam_mclk, qdss_gpio, _, _, _, _, _, _, _),
+	[98] = PINGROUP(98, cam_mclk, qdss_gpio, _, _, _, _, _, _, _),
+	[99] = PINGROUP(99, cam_mclk, qdss_gpio, _, _, _, _, _, _, _),
+	[100] = PINGROUP(100, cam_aon, qdss_gpio, _, _, _, _, _, _, _),
+	[101] = PINGROUP(101, cci_i2c, qdss_gpio, _, _, _, _, _, _, _),
+	[102] = PINGROUP(102, cci_i2c, qdss_gpio, _, _, _, _, _, _, _),
+	[103] = PINGROUP(103, cci_i2c, qdss_gpio, _, _, _, _, _, _, _),
+	[104] = PINGROUP(104, cci_i2c, qdss_gpio, _, _, _, _, _, _, _),
+	[105] = PINGROUP(105, cci_i2c, qdss_gpio, _, _, _, _, _, _, _),
+	[106] = PINGROUP(106, cci_i2c, qdss_gpio, _, _, _, _, _, _, _),
+	[107] = PINGROUP(107, qdss_gpio, _, _, _, _, _, _, _, _),
+	[108] = PINGROUP(108, qdss_gpio, _, _, _, _, _, _, _, _),
+	[109] = PINGROUP(109, cci_timer0, mdp_vsync4, qdss_gpio, _, _, _, _, _, _),
+	[110] = PINGROUP(110, cci_timer1, mdp_vsync5, qdss_gpio, _, _, _, _, _, _),
+	[111] = PINGROUP(111, cci_timer2, cci_async, mdp_vsync6, qdss_gpio, _, _, _, _, _),
+	[112] = PINGROUP(112, cci_timer3, cci_async, mdp_vsync7, qdss_gpio, _, _, _, _, _),
+	[113] = PINGROUP(113, cci_timer4, cci_async, mdp_vsync8, qdss_gpio, _, _, _, _, _),
+	[114] = PINGROUP(114, mdp_vsync0, mdp_vsync1, _, _, _, _, _, _, _),
+	[115] = PINGROUP(115, mdp_vsync3, mdp_vsync2, edp1_lcd, _, _, _, _, _, _),
+	[116] = PINGROUP(116, _, _, _, _, _, _, _, _, _),
+	[117] = PINGROUP(117, _, _, _, _, _, _, _, _, _),
+	[118] = PINGROUP(118, _, _, _, _, _, _, _, _, _),
+	[119] = PINGROUP(119, edp0_hot, edp1_lcd, _, _, _, _, _, _, _),
+	[120] = PINGROUP(120, edp1_hot, edp0_lcd, _, _, _, _, _, _, _),
+	[121] = PINGROUP(121, usb0_phy, _, _, _, _, _, _, _, _),
+	[122] = PINGROUP(122, usb0_dp, _, _, _, _, _, _, _, _),
+	[123] = PINGROUP(123, usb1_phy, _, _, _, _, _, _, _, _),
+	[124] = PINGROUP(124, usb1_dp, _, _, _, _, _, _, _, _),
+	[125] = PINGROUP(125, usb2_phy, _, _, _, _, _, _, _, _),
+	[126] = PINGROUP(126, usb2_dp, _, _, _, _, _, _, _, _),
+	[127] = PINGROUP(127, qspi0_clk, sdc4_clk, _, _, _, _, _, _, _),
+	[128] = PINGROUP(128, qspi00, sdc4_data0, _, _, _, _, _, _, _),
+	[129] = PINGROUP(129, qspi01, sdc4_data1, _, _, _, _, _, _, _),
+	[130] = PINGROUP(130, qspi02, sdc4_data2, _, _, _, _, _, _, _),
+	[131] = PINGROUP(131, qspi03, sdc4_data3, _, _, _, _, _, _, _),
+	[132] = PINGROUP(132, qspi0_cs0, sdc4_cmd, _, _, _, _, _, _, _),
+	[133] = PINGROUP(133, qspi0_cs1, tb_trig, _, _, _, _, _, _, _),
+	[134] = PINGROUP(134, audio_ext, _, _, _, _, _, _, _, _),
+	[135] = PINGROUP(135, i2s0_sck, _, _, _, _, _, _, _, _),
+	[136] = PINGROUP(136, i2s0_data0, _, _, _, _, _, _, _, _),
+	[137] = PINGROUP(137, i2s0_data1, tb_trig, _, _, _, _, _, _, _),
+	[138] = PINGROUP(138, i2s0_ws, _, _, _, _, _, _, _, _),
+	[139] = PINGROUP(139, i2s1_sck, _, _, _, _, _, _, _, _),
+	[140] = PINGROUP(140, i2s1_data0, _, _, _, _, _, _, _, _),
+	[141] = PINGROUP(141, i2s1_ws, _, _, _, _, _, _, _, _),
+	[142] = PINGROUP(142, i2s1_data1, audio_ext, audio_ref, _, _, _, _, _, _),
+	[143] = PINGROUP(143, _, _, _, _, _, _, _, _, _),
+	[144] = PINGROUP(144, pcie3_clk, _, _, _, _, _, _, _, _),
+	[145] = PINGROUP(145, _, _, _, _, _, _, _, _, _),
+	[146] = PINGROUP(146, _, _, _, _, _, _, _, _, _),
+	[147] = PINGROUP(147, pcie4_clk, _, _, _, _, _, _, _, _),
+	[148] = PINGROUP(148, _, _, _, _, _, _, _, _, _),
+	[149] = PINGROUP(149, _, _, _, _, _, _, _, _, _),
+	[150] = PINGROUP(150, pcie5_clk, _, _, _, _, _, _, _, _),
+	[151] = PINGROUP(151, _, _, _, _, _, _, _, _, _),
+	[152] = PINGROUP(152, _, _, _, _, _, _, _, _, _),
+	[153] = PINGROUP(153, pcie6a_clk, _, _, _, _, _, _, _, _),
+	[154] = PINGROUP(154, _, _, _, _, _, _, _, _, _),
+	[155] = PINGROUP(155, _, _, _, _, _, _, _, _, _),
+	[156] = PINGROUP(156, pcie6b_clk, _, _, _, _, _, _, _, _),
+	[157] = PINGROUP(157, _, _, _, _, _, _, _, _, _),
+	[158] = PINGROUP(158, _, _, _, _, _, _, _, _, _),
+	[159] = PINGROUP(159, _, _, _, _, _, _, _, _, _),
+	[160] = PINGROUP(160, RESOUT_GPIO, _, _, _, _, _, _, _, _),
+	[161] = PINGROUP(161, qdss_cti, _, _, _, _, _, _, _, _),
+	[162] = PINGROUP(162, sd_write, qdss_cti, _, _, _, _, _, _, _),
+	[163] = PINGROUP(163, usb0_sbrx, _, _, _, _, _, _, _, _),
+	[164] = PINGROUP(164, usb0_sbtx, _, _, _, _, _, _, _, _),
+	[165] = PINGROUP(165, usb0_sbtx, _, _, _, _, _, _, _, _),
+	[166] = PINGROUP(166, _, _, _, _, _, _, _, _, _),
+	[167] = PINGROUP(167, _, _, _, _, _, _, _, _, _),
+	[168] = PINGROUP(168, eusb0_ac, _, _, _, _, _, _, _, _),
+	[169] = PINGROUP(169, eusb3_ac, _, _, _, _, _, _, _, _),
+	[170] = PINGROUP(170, _, _, _, _, _, _, _, _, _),
+	[171] = PINGROUP(171, _, _, _, _, _, _, _, _, _),
+	[172] = PINGROUP(172, usb1_sbrx, _, _, _, _, _, _, _, _),
+	[173] = PINGROUP(173, usb1_sbtx, _, _, _, _, _, _, _, _),
+	[174] = PINGROUP(174, usb1_sbtx, _, _, _, _, _, _, _, _),
+	[175] = PINGROUP(175, _, _, _, _, _, _, _, _, _),
+	[176] = PINGROUP(176, _, _, _, _, _, _, _, _, _),
+	[177] = PINGROUP(177, eusb1_ac, _, _, _, _, _, _, _, _),
+	[178] = PINGROUP(178, eusb6_ac, _, _, _, _, _, _, _, _),
+	[179] = PINGROUP(179, _, _, _, _, _, _, _, _, _),
+	[180] = PINGROUP(180, _, _, _, _, _, _, _, _, _),
+	[181] = PINGROUP(181, usb2_sbrx, prng_rosc3, phase_flag, _, atest_char, _, _, _, _),
+	[182] = PINGROUP(182, usb2_sbtx, prng_rosc2, phase_flag, _, atest_char3, _, _, _, _),
+	[183] = PINGROUP(183, usb2_sbtx, _, _, _, _, _, _, _, _),
+	[184] = PINGROUP(184, phase_flag, _, atest_char1, _, _, _, _, _, _),
+	[185] = PINGROUP(185, phase_flag, _, atest_char0, _, _, _, _, _, _),
+	[186] = PINGROUP(186, eusb2_ac, prng_rosc0, phase_flag, _, _, _, _, _, _),
+	[187] = PINGROUP(187, eusb5_ac, cri_trng, phase_flag, _, _, _, _, _, _),
+	[188] = PINGROUP(188, prng_rosc1, phase_flag, _, atest_char2, _, _, _, _, _),
+	[189] = PINGROUP(189, _, _, _, _, _, _, _, _, _),
+	[190] = PINGROUP(190, _, _, _, _, _, _, _, _, _),
+	[191] = PINGROUP(191, _, _, _, _, _, _, _, _, _),
+	[192] = PINGROUP(192, _, _, _, _, _, _, _, _, _),
+	[193] = PINGROUP(193, _, _, _, _, _, _, _, _, _),
+	[194] = PINGROUP(194, _, _, _, _, _, _, _, _, _),
+	[195] = PINGROUP(195, _, _, _, _, _, _, _, _, _),
+	[196] = PINGROUP(196, _, _, _, _, _, _, _, _, _),
+	[197] = PINGROUP(197, _, _, _, _, _, _, _, _, _),
+	[198] = PINGROUP(198, _, _, _, _, _, _, _, _, _),
+	[199] = PINGROUP(199, _, _, _, _, _, _, _, _, _),
+	[200] = PINGROUP(200, _, _, _, _, _, _, _, _, _),
+	[201] = PINGROUP(201, _, _, _, _, _, _, _, _, _),
+	[202] = PINGROUP(202, _, _, _, _, _, _, _, _, _),
+	[203] = PINGROUP(203, _, _, _, _, _, _, _, _, _),
+	[204] = PINGROUP(204, _, _, _, _, _, _, _, _, _),
+	[205] = PINGROUP(205, _, _, _, _, _, _, _, _, _),
+	[206] = PINGROUP(206, _, _, _, _, _, _, _, _, _),
+	[207] = PINGROUP(207, _, _, _, _, _, _, _, _, _),
+	[208] = PINGROUP(208, _, _, _, _, _, _, _, _, _),
+	[209] = PINGROUP(209, _, _, _, _, _, _, _, _, _),
+	[210] = PINGROUP(210, _, _, _, _, _, _, _, _, _),
+	[211] = PINGROUP(211, _, _, _, _, _, _, _, _, _),
+	[212] = PINGROUP(212, _, _, _, _, _, _, _, _, _),
+	[213] = PINGROUP(213, _, _, _, _, _, _, _, _, _),
+	[214] = PINGROUP(214, _, _, _, _, _, _, _, _, _),
+	[215] = PINGROUP(215, _, qdss_cti, _, _, _, _, _, _, _),
+	[216] = PINGROUP(216, _, _, _, _, _, _, _, _, _),
+	[217] = PINGROUP(217, _, qdss_cti, _, _, _, _, _, _, _),
+	[218] = PINGROUP(218, _, _, _, _, _, _, _, _, _),
+	[219] = PINGROUP(219, _, qdss_gpio, _, _, _, _, _, _, _),
+	[220] = PINGROUP(220, _, qdss_gpio, _, _, _, _, _, _, _),
+	[221] = PINGROUP(221, _, qdss_gpio, _, _, _, _, _, _, _),
+	[222] = PINGROUP(222, _, qdss_gpio, _, _, _, _, _, _, _),
+	[223] = PINGROUP(223, _, qdss_gpio, _, _, _, _, _, _, _),
+	[224] = PINGROUP(224, _, qdss_gpio, _, _, _, _, _, _, _),
+	[225] = PINGROUP(225, _, qdss_gpio, _, _, _, _, _, _, _),
+	[226] = PINGROUP(226, _, qdss_gpio, _, _, _, _, _, _, _),
+	[227] = PINGROUP(227, _, qdss_gpio, _, _, _, _, _, _, _),
+	[228] = PINGROUP(228, _, qdss_gpio, _, _, _, _, _, _, _),
+	[229] = PINGROUP(229, qdss_gpio, _, _, _, _, _, _, _, _),
+	[230] = PINGROUP(230, qdss_gpio, _, _, _, _, _, _, _, _),
+	[231] = PINGROUP(231, qdss_gpio, _, _, _, _, _, _, _, _),
+	[232] = PINGROUP(232, qdss_gpio, _, _, _, _, _, _, _, _),
+	[233] = PINGROUP(233, qdss_gpio, _, _, _, _, _, _, _, _),
+	[234] = PINGROUP(234, qdss_gpio, _, _, _, _, _, _, _, _),
+	[235] = PINGROUP(235, aon_cci, qdss_gpio, _, _, _, _, _, _, _),
+	[236] = PINGROUP(236, aon_cci, qdss_gpio, _, _, _, _, _, _, _),
+	[237] = PINGROUP(237, _, _, _, _, _, _, _, _, _),
+	[238] = UFS_RESET(ufs_reset, 0x1f9000),
+	[239] = SDC_QDSD_PINGROUP(sdc2_clk, 0x1f2000, 14, 6),
+	[240] = SDC_QDSD_PINGROUP(sdc2_cmd, 0x1f2000, 11, 3),
+	[241] = SDC_QDSD_PINGROUP(sdc2_data, 0x1f2000, 9, 0),
+};
+
+static const struct msm_gpio_wakeirq_map x1e80100_pdc_map[] = {
+	{ 0, 72 }, { 2, 70 }, { 3, 71 }, { 6, 123 }, { 7, 67 }, { 11, 85 },
+	{ 15, 68 }, { 18, 122 }, { 19, 69 }, { 21, 158 }, { 23, 143 }, { 26, 129 },
+	{ 27, 144 }, { 28, 77 }, { 29, 78 }, { 30, 92 }, { 32, 145 }, { 33, 115 },
+	{ 34, 130 }, { 35, 146 }, { 36, 147 }, { 39, 80 }, { 43, 148 }, { 47, 149 },
+	{ 51, 79 }, { 53, 89 }, { 59, 87 }, { 64, 90 }, { 65, 106 }, { 66, 142 },
+	{ 67, 88 }, { 71, 91 }, { 75, 152 }, { 79, 153 }, { 80, 125 }, { 81, 128 },
+	{ 84, 137 }, { 85, 155 }, { 87, 156 }, { 91, 157 }, { 92, 138 }, { 94, 140 },
+	{ 95, 141 }, { 113, 84 }, { 121, 73 }, { 123, 74 }, { 129, 76 }, { 131, 82 },
+	{ 134, 83 }, { 141, 93 }, { 144, 94 }, { 147, 96 }, { 148, 97 }, { 150, 102 },
+	{ 151, 103 }, { 153, 104 }, { 156, 105 }, { 157, 107 }, { 163, 98 }, { 166, 112 },
+	{ 172, 99 }, { 181, 101 }, { 184, 116 }, { 193, 40 }, { 193, 117 }, { 196, 108 },
+	{ 203, 133 }, { 212, 120 }, { 213, 150 }, { 214, 121 }, { 215, 118 }, { 217, 109 },
+	{ 220, 110 }, { 221, 111 }, { 222, 124 }, { 224, 131 }, { 225, 132 },
+};
+
+static const struct msm_pinctrl_soc_data x1e80100_pinctrl = {
+	.pins = x1e80100_pins,
+	.npins = ARRAY_SIZE(x1e80100_pins),
+	.functions = x1e80100_functions,
+	.nfunctions = ARRAY_SIZE(x1e80100_functions),
+	.groups = x1e80100_groups,
+	.ngroups = ARRAY_SIZE(x1e80100_groups),
+	.ngpios = 239,
+	.wakeirq_map = x1e80100_pdc_map,
+	.nwakeirq_map = ARRAY_SIZE(x1e80100_pdc_map),
+	.egpio_func = 9,
+};
+
+static int x1e80100_pinctrl_probe(struct platform_device *pdev)
+{
+	return msm_pinctrl_probe(pdev, &x1e80100_pinctrl);
+}
+
+static const struct of_device_id x1e80100_pinctrl_of_match[] = {
+	{ .compatible = "qcom,x1e80100-tlmm", },
+	{ },
+};
+
+static struct platform_driver x1e80100_pinctrl_driver = {
+	.driver = {
+		.name = "x1e80100-tlmm",
+		.of_match_table = x1e80100_pinctrl_of_match,
+	},
+	.probe = x1e80100_pinctrl_probe,
+	.remove_new = msm_pinctrl_remove,
+};
+
+static int __init x1e80100_pinctrl_init(void)
+{
+	return platform_driver_register(&x1e80100_pinctrl_driver);
+}
+arch_initcall(x1e80100_pinctrl_init);
+
+static void __exit x1e80100_pinctrl_exit(void)
+{
+	platform_driver_unregister(&x1e80100_pinctrl_driver);
+}
+module_exit(x1e80100_pinctrl_exit);
+
+MODULE_DESCRIPTION("QTI X1E80100 TLMM pinctrl driver");
+MODULE_LICENSE("GPL");
+MODULE_DEVICE_TABLE(of, x1e80100_pinctrl_of_match);
diff --git a/drivers/pinctrl/renesas/pinctrl-rza1.c b/drivers/pinctrl/renesas/pinctrl-rza1.c
index f43f1196fea8..edcbe7c9ad56 100644
--- a/drivers/pinctrl/renesas/pinctrl-rza1.c
+++ b/drivers/pinctrl/renesas/pinctrl-rza1.c
@@ -1131,7 +1131,7 @@ static int rza1_set_mux(struct pinctrl_dev *pctldev, unsigned int selector,
 		return -EINVAL;
 
 	mux_confs = (struct rza1_mux_conf *)func->data;
-	for (i = 0; i < grp->num_pins; ++i) {
+	for (i = 0; i < grp->grp.npins; ++i) {
 		int ret;
 
 		ret = rza1_pin_mux_single(rza1_pctl, &mux_confs[i]);
diff --git a/drivers/pinctrl/renesas/pinctrl-rza2.c b/drivers/pinctrl/renesas/pinctrl-rza2.c
index 990b96d45967..af689d7c117f 100644
--- a/drivers/pinctrl/renesas/pinctrl-rza2.c
+++ b/drivers/pinctrl/renesas/pinctrl-rza2.c
@@ -447,15 +447,15 @@ static int rza2_set_mux(struct pinctrl_dev *pctldev, unsigned int selector,
 
 	psel_val = func->data;
 
-	for (i = 0; i < grp->num_pins; ++i) {
+	for (i = 0; i < grp->grp.npins; ++i) {
 		dev_dbg(priv->dev, "Setting P%c_%d to PSEL=%d\n",
-			port_names[RZA2_PIN_ID_TO_PORT(grp->pins[i])],
-			RZA2_PIN_ID_TO_PIN(grp->pins[i]),
+			port_names[RZA2_PIN_ID_TO_PORT(grp->grp.pins[i])],
+			RZA2_PIN_ID_TO_PIN(grp->grp.pins[i]),
 			psel_val[i]);
 		rza2_set_pin_function(
 			priv->base,
-			RZA2_PIN_ID_TO_PORT(grp->pins[i]),
-			RZA2_PIN_ID_TO_PIN(grp->pins[i]),
+			RZA2_PIN_ID_TO_PORT(grp->grp.pins[i]),
+			RZA2_PIN_ID_TO_PIN(grp->grp.pins[i]),
 			psel_val[i]);
 	}
 
diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
index 9de350ad7e7d..80fb5011c7bb 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
@@ -57,6 +57,7 @@
 #define PIN_CFG_FILCLKSEL		BIT(12)
 #define PIN_CFG_IOLH_C			BIT(13)
 #define PIN_CFG_SOFT_PS			BIT(14)
+#define PIN_CFG_OEN			BIT(15)
 
 #define RZG2L_MPXED_COMMON_PIN_FUNCS(group) \
 					(PIN_CFG_IOLH_##group | \
@@ -107,8 +108,11 @@
 #define IEN(off)		(0x1800 + (off) * 8)
 #define ISEL(off)		(0x2C00 + (off) * 8)
 #define SD_CH(off, ch)		((off) + (ch) * 4)
+#define ETH_POC(off, ch)	((off) + (ch) * 4)
 #define QSPI			(0x3008)
+#define ETH_MODE		(0x3018)
 
+#define PVDD_2500		2	/* I/O domain voltage 2.5V */
 #define PVDD_1800		1	/* I/O domain voltage <= 1.8V */
 #define PVDD_3300		0	/* I/O domain voltage >= 3.3V */
 
@@ -116,7 +120,6 @@
 #define PWPR_PFCWE		BIT(6)	/* PFC Register Write Enable */
 
 #define PM_MASK			0x03
-#define PVDD_MASK		0x01
 #define PFC_MASK		0x07
 #define IEN_MASK		0x01
 #define IOLH_MASK		0x03
@@ -135,10 +138,12 @@
  * struct rzg2l_register_offsets - specific register offsets
  * @pwpr: PWPR register offset
  * @sd_ch: SD_CH register offset
+ * @eth_poc: ETH_POC register offset
  */
 struct rzg2l_register_offsets {
 	u16 pwpr;
 	u16 sd_ch;
+	u16 eth_poc;
 };
 
 /**
@@ -167,6 +172,8 @@ enum rzg2l_iolh_index {
  * @iolh_groupb_oi: IOLH group B output impedance specific values
  * @drive_strength_ua: drive strength in uA is supported (otherwise mA is supported)
  * @func_base: base number for port function (see register PFC)
+ * @oen_max_pin: the maximum pin number supporting output enable
+ * @oen_max_port: the maximum port number supporting output enable
  */
 struct rzg2l_hwcfg {
 	const struct rzg2l_register_offsets regs;
@@ -176,6 +183,8 @@ struct rzg2l_hwcfg {
 	u16 iolh_groupb_oi[4];
 	bool drive_strength_ua;
 	u8 func_base;
+	u8 oen_max_pin;
+	u8 oen_max_port;
 };
 
 struct rzg2l_dedicated_configs {
@@ -273,7 +282,7 @@ static int rzg2l_pinctrl_set_mux(struct pinctrl_dev *pctldev,
 	struct function_desc *func;
 	unsigned int i, *psel_val;
 	struct group_desc *group;
-	int *pins;
+	const unsigned int *pins;
 
 	func = pinmux_generic_get_function(pctldev, func_selector);
 	if (!func)
@@ -283,9 +292,9 @@ static int rzg2l_pinctrl_set_mux(struct pinctrl_dev *pctldev,
 		return -EINVAL;
 
 	psel_val = func->data;
-	pins = group->pins;
+	pins = group->grp.pins;
 
-	for (i = 0; i < group->num_pins; i++) {
+	for (i = 0; i < group->grp.npins; i++) {
 		unsigned int *pin_data = pctrl->desc.pins[pins[i]].drv_data;
 		u32 off = RZG2L_PIN_CFG_TO_PORT_OFFSET(*pin_data);
 		u32 pin = RZG2L_PIN_ID_TO_PIN(pins[i]);
@@ -376,8 +385,11 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev,
 		goto done;
 	}
 
-	if (num_pinmux)
+	if (num_pinmux) {
 		nmaps += 1;
+		if (num_configs)
+			nmaps += 1;
+	}
 
 	if (num_pins)
 		nmaps += num_pins;
@@ -462,6 +474,16 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev,
 	maps[idx].data.mux.function = name;
 	idx++;
 
+	if (num_configs) {
+		ret = rzg2l_map_add_config(&maps[idx], name,
+					   PIN_MAP_TYPE_CONFIGS_GROUP,
+					   configs, num_configs);
+		if (ret < 0)
+			goto remove_group;
+
+		idx++;
+	}
+
 	dev_dbg(pctrl->dev, "Parsed %pOF with %d pins\n", np, num_pinmux);
 	ret = 0;
 	goto done;
@@ -591,6 +613,10 @@ static int rzg2l_caps_to_pwr_reg(const struct rzg2l_register_offsets *regs, u32
 		return SD_CH(regs->sd_ch, 0);
 	if (caps & PIN_CFG_IO_VMC_SD1)
 		return SD_CH(regs->sd_ch, 1);
+	if (caps & PIN_CFG_IO_VMC_ETH0)
+		return ETH_POC(regs->eth_poc, 0);
+	if (caps & PIN_CFG_IO_VMC_ETH1)
+		return ETH_POC(regs->eth_poc, 1);
 	if (caps & PIN_CFG_IO_VMC_QSPI)
 		return QSPI;
 
@@ -602,6 +628,7 @@ static int rzg2l_get_power_source(struct rzg2l_pinctrl *pctrl, u32 pin, u32 caps
 	const struct rzg2l_hwcfg *hwcfg = pctrl->data->hwcfg;
 	const struct rzg2l_register_offsets *regs = &hwcfg->regs;
 	int pwr_reg;
+	u8 val;
 
 	if (caps & PIN_CFG_SOFT_PS)
 		return pctrl->settings[pin].power_source;
@@ -610,7 +637,18 @@ static int rzg2l_get_power_source(struct rzg2l_pinctrl *pctrl, u32 pin, u32 caps
 	if (pwr_reg < 0)
 		return pwr_reg;
 
-	return (readl(pctrl->base + pwr_reg) & PVDD_MASK) ? 1800 : 3300;
+	val = readb(pctrl->base + pwr_reg);
+	switch (val) {
+	case PVDD_1800:
+		return 1800;
+	case PVDD_2500:
+		return 2500;
+	case PVDD_3300:
+		return 3300;
+	default:
+		/* Should not happen. */
+		return -EINVAL;
+	}
 }
 
 static int rzg2l_set_power_source(struct rzg2l_pinctrl *pctrl, u32 pin, u32 caps, u32 ps)
@@ -618,17 +656,32 @@ static int rzg2l_set_power_source(struct rzg2l_pinctrl *pctrl, u32 pin, u32 caps
 	const struct rzg2l_hwcfg *hwcfg = pctrl->data->hwcfg;
 	const struct rzg2l_register_offsets *regs = &hwcfg->regs;
 	int pwr_reg;
+	u8 val;
 
 	if (caps & PIN_CFG_SOFT_PS) {
 		pctrl->settings[pin].power_source = ps;
 		return 0;
 	}
 
+	switch (ps) {
+	case 1800:
+		val = PVDD_1800;
+		break;
+	case 2500:
+		val = PVDD_2500;
+		break;
+	case 3300:
+		val = PVDD_3300;
+		break;
+	default:
+		return -EINVAL;
+	}
+
 	pwr_reg = rzg2l_caps_to_pwr_reg(regs, caps);
 	if (pwr_reg < 0)
 		return pwr_reg;
 
-	writel((ps == 1800) ? PVDD_1800 : PVDD_3300, pctrl->base + pwr_reg);
+	writeb(val, pctrl->base + pwr_reg);
 	pctrl->settings[pin].power_source = ps;
 
 	return 0;
@@ -735,6 +788,66 @@ static bool rzg2l_ds_is_supported(struct rzg2l_pinctrl *pctrl, u32 caps,
 	return false;
 }
 
+static bool rzg2l_oen_is_supported(u32 caps, u8 pin, u8 max_pin)
+{
+	if (!(caps & PIN_CFG_OEN))
+		return false;
+
+	if (pin > max_pin)
+		return false;
+
+	return true;
+}
+
+static u8 rzg2l_pin_to_oen_bit(u32 offset, u8 pin, u8 max_port)
+{
+	if (pin)
+		pin *= 2;
+
+	if (offset / RZG2L_PINS_PER_PORT == max_port)
+		pin += 1;
+
+	return pin;
+}
+
+static u32 rzg2l_read_oen(struct rzg2l_pinctrl *pctrl, u32 caps, u32 offset, u8 pin)
+{
+	u8 max_port = pctrl->data->hwcfg->oen_max_port;
+	u8 max_pin = pctrl->data->hwcfg->oen_max_pin;
+	u8 bit;
+
+	if (!rzg2l_oen_is_supported(caps, pin, max_pin))
+		return 0;
+
+	bit = rzg2l_pin_to_oen_bit(offset, pin, max_port);
+
+	return !(readb(pctrl->base + ETH_MODE) & BIT(bit));
+}
+
+static int rzg2l_write_oen(struct rzg2l_pinctrl *pctrl, u32 caps, u32 offset, u8 pin, u8 oen)
+{
+	u8 max_port = pctrl->data->hwcfg->oen_max_port;
+	u8 max_pin = pctrl->data->hwcfg->oen_max_pin;
+	unsigned long flags;
+	u8 val, bit;
+
+	if (!rzg2l_oen_is_supported(caps, pin, max_pin))
+		return -EINVAL;
+
+	bit = rzg2l_pin_to_oen_bit(offset, pin, max_port);
+
+	spin_lock_irqsave(&pctrl->lock, flags);
+	val = readb(pctrl->base + ETH_MODE);
+	if (oen)
+		val &= ~BIT(bit);
+	else
+		val |= BIT(bit);
+	writeb(val, pctrl->base + ETH_MODE);
+	spin_unlock_irqrestore(&pctrl->lock, flags);
+
+	return 0;
+}
+
 static int rzg2l_pinctrl_pinconf_get(struct pinctrl_dev *pctldev,
 				     unsigned int _pin,
 				     unsigned long *config)
@@ -772,6 +885,12 @@ static int rzg2l_pinctrl_pinconf_get(struct pinctrl_dev *pctldev,
 			return -EINVAL;
 		break;
 
+	case PIN_CONFIG_OUTPUT_ENABLE:
+		arg = rzg2l_read_oen(pctrl, cfg, _pin, bit);
+		if (!arg)
+			return -EINVAL;
+		break;
+
 	case PIN_CONFIG_POWER_SOURCE:
 		ret = rzg2l_get_power_source(pctrl, _pin, cfg);
 		if (ret < 0)
@@ -842,7 +961,7 @@ static int rzg2l_pinctrl_pinconf_set(struct pinctrl_dev *pctldev,
 	struct rzg2l_pinctrl_pin_settings settings = pctrl->settings[_pin];
 	unsigned int *pin_data = pin->drv_data;
 	enum pin_config_param param;
-	unsigned int i;
+	unsigned int i, arg, index;
 	u32 cfg, off;
 	int ret;
 	u8 bit;
@@ -864,24 +983,28 @@ static int rzg2l_pinctrl_pinconf_set(struct pinctrl_dev *pctldev,
 	for (i = 0; i < num_configs; i++) {
 		param = pinconf_to_config_param(_configs[i]);
 		switch (param) {
-		case PIN_CONFIG_INPUT_ENABLE: {
-			unsigned int arg =
-					pinconf_to_config_argument(_configs[i]);
+		case PIN_CONFIG_INPUT_ENABLE:
+			arg = pinconf_to_config_argument(_configs[i]);
 
 			if (!(cfg & PIN_CFG_IEN))
 				return -EINVAL;
 
 			rzg2l_rmw_pin_config(pctrl, IEN(off), bit, IEN_MASK, !!arg);
 			break;
-		}
+
+		case PIN_CONFIG_OUTPUT_ENABLE:
+			arg = pinconf_to_config_argument(_configs[i]);
+			ret = rzg2l_write_oen(pctrl, cfg, _pin, bit, !!arg);
+			if (ret)
+				return ret;
+			break;
 
 		case PIN_CONFIG_POWER_SOURCE:
 			settings.power_source = pinconf_to_config_argument(_configs[i]);
 			break;
 
-		case PIN_CONFIG_DRIVE_STRENGTH: {
-			unsigned int arg = pinconf_to_config_argument(_configs[i]);
-			unsigned int index;
+		case PIN_CONFIG_DRIVE_STRENGTH:
+			arg = pinconf_to_config_argument(_configs[i]);
 
 			if (!(cfg & PIN_CFG_IOLH_A) || hwcfg->drive_strength_ua)
 				return -EINVAL;
@@ -896,7 +1019,6 @@ static int rzg2l_pinctrl_pinconf_set(struct pinctrl_dev *pctldev,
 
 			rzg2l_rmw_pin_config(pctrl, IOLH(off), bit, IOLH_MASK, index);
 			break;
-		}
 
 		case PIN_CONFIG_DRIVE_STRENGTH_UA:
 			if (!(cfg & (PIN_CFG_IOLH_A | PIN_CFG_IOLH_B | PIN_CFG_IOLH_C)) ||
@@ -906,9 +1028,8 @@ static int rzg2l_pinctrl_pinconf_set(struct pinctrl_dev *pctldev,
 			settings.drive_strength_ua = pinconf_to_config_argument(_configs[i]);
 			break;
 
-		case PIN_CONFIG_OUTPUT_IMPEDANCE_OHMS: {
-			unsigned int arg = pinconf_to_config_argument(_configs[i]);
-			unsigned int index;
+		case PIN_CONFIG_OUTPUT_IMPEDANCE_OHMS:
+			arg = pinconf_to_config_argument(_configs[i]);
 
 			if (!(cfg & PIN_CFG_IOLH_B) || !hwcfg->iolh_groupb_oi[0])
 				return -EINVAL;
@@ -922,7 +1043,6 @@ static int rzg2l_pinctrl_pinconf_set(struct pinctrl_dev *pctldev,
 
 			rzg2l_rmw_pin_config(pctrl, IOLH(off), bit, IOLH_MASK, index);
 			break;
-		}
 
 		default:
 			return -EOPNOTSUPP;
@@ -1323,7 +1443,8 @@ static const u32 r9a07g043_gpio_configs[] = {
 static const u32 r9a08g045_gpio_configs[] = {
 	RZG2L_GPIO_PORT_PACK(4, 0x20, RZG3S_MPXED_PIN_FUNCS(A)),			/* P0  */
 	RZG2L_GPIO_PORT_PACK(5, 0x30, RZG2L_MPXED_ETH_PIN_FUNCS(PIN_CFG_IOLH_C |
-								PIN_CFG_IO_VMC_ETH0)),	/* P1 */
+								PIN_CFG_IO_VMC_ETH0)) |
+				      PIN_CFG_OEN | PIN_CFG_IEN,			/* P1 */
 	RZG2L_GPIO_PORT_PACK(4, 0x31, RZG2L_MPXED_ETH_PIN_FUNCS(PIN_CFG_IOLH_C |
 								PIN_CFG_IO_VMC_ETH0)),	/* P2 */
 	RZG2L_GPIO_PORT_PACK(4, 0x32, RZG2L_MPXED_ETH_PIN_FUNCS(PIN_CFG_IOLH_C |
@@ -1333,7 +1454,8 @@ static const u32 r9a08g045_gpio_configs[] = {
 	RZG2L_GPIO_PORT_PACK(5, 0x21, RZG3S_MPXED_PIN_FUNCS(A)),			/* P5  */
 	RZG2L_GPIO_PORT_PACK(5, 0x22, RZG3S_MPXED_PIN_FUNCS(A)),			/* P6  */
 	RZG2L_GPIO_PORT_PACK(5, 0x34, RZG2L_MPXED_ETH_PIN_FUNCS(PIN_CFG_IOLH_C |
-								PIN_CFG_IO_VMC_ETH1)),	/* P7 */
+								PIN_CFG_IO_VMC_ETH1)) |
+				      PIN_CFG_OEN | PIN_CFG_IEN,			/* P7 */
 	RZG2L_GPIO_PORT_PACK(5, 0x35, RZG2L_MPXED_ETH_PIN_FUNCS(PIN_CFG_IOLH_C |
 								PIN_CFG_IO_VMC_ETH1)),	/* P8 */
 	RZG2L_GPIO_PORT_PACK(4, 0x36, RZG2L_MPXED_ETH_PIN_FUNCS(PIN_CFG_IOLH_C |
@@ -1576,6 +1698,7 @@ static const struct irq_chip rzg2l_gpio_irqchip = {
 	.irq_set_type = rzg2l_gpio_irq_set_type,
 	.irq_eoi = rzg2l_gpio_irqc_eoi,
 	.irq_print_chip = rzg2l_gpio_irq_print_chip,
+	.irq_set_affinity = irq_chip_set_affinity_parent,
 	.flags = IRQCHIP_IMMUTABLE,
 	GPIOCHIP_IRQ_RESOURCE_HELPERS,
 };
@@ -1877,6 +2000,7 @@ static const struct rzg2l_hwcfg rzg2l_hwcfg = {
 	.regs = {
 		.pwpr = 0x3014,
 		.sd_ch = 0x3000,
+		.eth_poc = 0x300c,
 	},
 	.iolh_groupa_ua = {
 		/* 3v3 power source */
@@ -1889,6 +2013,7 @@ static const struct rzg2l_hwcfg rzg3s_hwcfg = {
 	.regs = {
 		.pwpr = 0x3000,
 		.sd_ch = 0x3004,
+		.eth_poc = 0x3010,
 	},
 	.iolh_groupa_ua = {
 		/* 1v8 power source */
@@ -1912,6 +2037,8 @@ static const struct rzg2l_hwcfg rzg3s_hwcfg = {
 	},
 	.drive_strength_ua = true,
 	.func_base = 1,
+	.oen_max_pin = 1, /* Pin 1 of P0 and P7 is the maximum OEN pin. */
+	.oen_max_port = 7, /* P7_1 is the maximum OEN port. */
 };
 
 static struct rzg2l_pinctrl_data r9a07g043_data = {
diff --git a/drivers/pinctrl/renesas/pinctrl-rzv2m.c b/drivers/pinctrl/renesas/pinctrl-rzv2m.c
index 21d7d5ac8c4a..0767a5ac23e0 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzv2m.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzv2m.c
@@ -165,7 +165,7 @@ static int rzv2m_pinctrl_set_mux(struct pinctrl_dev *pctldev,
 	struct function_desc *func;
 	unsigned int i, *psel_val;
 	struct group_desc *group;
-	int *pins;
+	const unsigned int *pins;
 
 	func = pinmux_generic_get_function(pctldev, func_selector);
 	if (!func)
@@ -175,9 +175,9 @@ static int rzv2m_pinctrl_set_mux(struct pinctrl_dev *pctldev,
 		return -EINVAL;
 
 	psel_val = func->data;
-	pins = group->pins;
+	pins = group->grp.pins;
 
-	for (i = 0; i < group->num_pins; i++) {
+	for (i = 0; i < group->grp.npins; i++) {
 		dev_dbg(pctrl->dev, "port:%u pin: %u PSEL:%u\n",
 			RZV2M_PIN_ID_TO_PORT(pins[i]), RZV2M_PIN_ID_TO_PIN(pins[i]),
 			psel_val[i]);
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
index cb965cf93705..5480e0884abe 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
@@ -726,6 +726,146 @@ const struct samsung_pinctrl_of_match_data exynosautov9_of_data __initconst = {
 	.num_ctrl	= ARRAY_SIZE(exynosautov9_pin_ctrl),
 };
 
+/* pin banks of exynosautov920 pin-controller 0 (ALIVE) */
+static const struct samsung_pin_bank_data exynosautov920_pin_banks0[] = {
+	EXYNOSV920_PIN_BANK_EINTW(8, 0x0000, "gpa0", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTW(2, 0x1000, "gpa1", 0x18, 0x20, 0x24),
+	EXYNOS850_PIN_BANK_EINTN(2, 0x2000, "gpq0"),
+};
+
+/* pin banks of exynosautov920 pin-controller 1 (AUD) */
+static const struct samsung_pin_bank_data exynosautov920_pin_banks1[] = {
+	EXYNOSV920_PIN_BANK_EINTG(7, 0x0000, "gpb0", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(6, 0x1000, "gpb1", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x2000, "gpb2", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x3000, "gpb3", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x4000, "gpb4", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(5, 0x5000, "gpb5", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(5, 0x6000, "gpb6", 0x18, 0x24, 0x28),
+};
+
+/* pin banks of exynosautov920 pin-controller 2 (HSI0) */
+static const struct samsung_pin_bank_data exynosautov920_pin_banks2[] = {
+	EXYNOSV920_PIN_BANK_EINTG(6, 0x0000, "gph0", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(2, 0x1000, "gph1", 0x18, 0x20, 0x24),
+};
+
+/* pin banks of exynosautov920 pin-controller 3 (HSI1) */
+static const struct samsung_pin_bank_data exynosautov920_pin_banks3[] = {
+	EXYNOSV920_PIN_BANK_EINTG(7, 0x000, "gph8", 0x18, 0x24, 0x28),
+};
+
+/* pin banks of exynosautov920 pin-controller 4 (HSI2) */
+static const struct samsung_pin_bank_data exynosautov920_pin_banks4[] = {
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x0000, "gph3", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(7, 0x1000, "gph4", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x2000, "gph5", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(7, 0x3000, "gph6", 0x18, 0x24, 0x28),
+};
+
+/* pin banks of exynosautov920 pin-controller 5 (HSI2UFS) */
+static const struct samsung_pin_bank_data exynosautov920_pin_banks5[] = {
+	EXYNOSV920_PIN_BANK_EINTG(4, 0x000, "gph2", 0x18, 0x20, 0x24),
+};
+
+/* pin banks of exynosautov920 pin-controller 6 (PERIC0) */
+static const struct samsung_pin_bank_data exynosautov920_pin_banks6[] = {
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x0000, "gpp0", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x1000, "gpp1", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x2000, "gpp2", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(5, 0x3000, "gpg0", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x4000, "gpp3", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(4, 0x5000, "gpp4", 0x18, 0x20, 0x24),
+	EXYNOSV920_PIN_BANK_EINTG(4, 0x6000, "gpg2", 0x18, 0x20, 0x24),
+	EXYNOSV920_PIN_BANK_EINTG(4, 0x7000, "gpg5", 0x18, 0x20, 0x24),
+	EXYNOSV920_PIN_BANK_EINTG(3, 0x8000, "gpg3", 0x18, 0x20, 0x24),
+	EXYNOSV920_PIN_BANK_EINTG(5, 0x9000, "gpg4", 0x18, 0x24, 0x28),
+};
+
+/* pin banks of exynosautov920 pin-controller 7 (PERIC1) */
+static const struct samsung_pin_bank_data exynosautov920_pin_banks7[] = {
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x0000, "gpp5",  0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(5, 0x1000, "gpp6",  0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(4, 0x2000, "gpp10", 0x18, 0x20, 0x24),
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x3000, "gpp7",  0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(4, 0x4000, "gpp8",  0x18, 0x20, 0x24),
+	EXYNOSV920_PIN_BANK_EINTG(4, 0x5000, "gpp11", 0x18, 0x20, 0x24),
+	EXYNOSV920_PIN_BANK_EINTG(4, 0x6000, "gpp9",  0x18, 0x20, 0x24),
+	EXYNOSV920_PIN_BANK_EINTG(4, 0x7000, "gpp12", 0x18, 0x20, 0x24),
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x8000, "gpg1",  0x18, 0x24, 0x28),
+};
+
+static const struct samsung_retention_data exynosautov920_retention_data __initconst = {
+	.regs	 = NULL,
+	.nr_regs = 0,
+	.value	 = 0,
+	.refcnt	 = &exynos_shared_retention_refcnt,
+	.init	 = exynos_retention_init,
+};
+
+static const struct samsung_pin_ctrl exynosautov920_pin_ctrl[] = {
+	{
+		/* pin-controller instance 0 ALIVE data */
+		.pin_banks	= exynosautov920_pin_banks0,
+		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks0),
+		.eint_wkup_init	= exynos_eint_wkup_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+		.retention_data	= &exynosautov920_retention_data,
+	}, {
+		/* pin-controller instance 1 AUD data */
+		.pin_banks	= exynosautov920_pin_banks1,
+		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks1),
+	}, {
+		/* pin-controller instance 2 HSI0 data */
+		.pin_banks	= exynosautov920_pin_banks2,
+		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks2),
+		.eint_gpio_init	= exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 3 HSI1 data */
+		.pin_banks	= exynosautov920_pin_banks3,
+		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks3),
+		.eint_gpio_init	= exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 4 HSI2 data */
+		.pin_banks	= exynosautov920_pin_banks4,
+		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks4),
+		.eint_gpio_init	= exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 5 HSI2UFS data */
+		.pin_banks	= exynosautov920_pin_banks5,
+		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks5),
+		.eint_gpio_init	= exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 6 PERIC0 data */
+		.pin_banks	= exynosautov920_pin_banks6,
+		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks6),
+		.eint_gpio_init	= exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 7 PERIC1 data */
+		.pin_banks	= exynosautov920_pin_banks7,
+		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks7),
+		.eint_gpio_init	= exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	},
+};
+
+const struct samsung_pinctrl_of_match_data exynosautov920_of_data __initconst = {
+	.ctrl		= exynosautov920_pin_ctrl,
+	.num_ctrl	= ARRAY_SIZE(exynosautov920_pin_ctrl),
+};
+
 /*
  * Pinctrl driver data for Tesla FSD SoC. FSD SoC includes three
  * gpio/pin-mux/pinconfig controllers.
@@ -796,3 +936,143 @@ const struct samsung_pinctrl_of_match_data fsd_of_data __initconst = {
 	.ctrl		= fsd_pin_ctrl,
 	.num_ctrl	= ARRAY_SIZE(fsd_pin_ctrl),
 };
+
+/* pin banks of gs101 pin-controller (ALIVE) */
+static const struct samsung_pin_bank_data gs101_pin_alive[] = {
+	EXYNOS850_PIN_BANK_EINTW(8, 0x0, "gpa0", 0x00),
+	EXYNOS850_PIN_BANK_EINTW(7, 0x20, "gpa1", 0x04),
+	EXYNOS850_PIN_BANK_EINTW(5, 0x40, "gpa2", 0x08),
+	EXYNOS850_PIN_BANK_EINTW(4, 0x60, "gpa3", 0x0c),
+	EXYNOS850_PIN_BANK_EINTW(4, 0x80, "gpa4", 0x10),
+	EXYNOS850_PIN_BANK_EINTW(7, 0xa0, "gpa5", 0x14),
+	EXYNOS850_PIN_BANK_EINTW(8, 0xc0, "gpa9", 0x18),
+	EXYNOS850_PIN_BANK_EINTW(2, 0xe0, "gpa10", 0x1c),
+};
+
+/* pin banks of gs101 pin-controller (FAR_ALIVE) */
+static const struct samsung_pin_bank_data gs101_pin_far_alive[] = {
+	EXYNOS850_PIN_BANK_EINTW(8, 0x0, "gpa6", 0x00),
+	EXYNOS850_PIN_BANK_EINTW(4, 0x20, "gpa7", 0x04),
+	EXYNOS850_PIN_BANK_EINTW(8, 0x40, "gpa8", 0x08),
+	EXYNOS850_PIN_BANK_EINTW(2, 0x60, "gpa11", 0x0c),
+};
+
+/* pin banks of gs101 pin-controller (GSACORE) */
+static const struct samsung_pin_bank_data gs101_pin_gsacore[] = {
+	EXYNOS850_PIN_BANK_EINTG(2, 0x0, "gps0", 0x00),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x20, "gps1", 0x04),
+	EXYNOS850_PIN_BANK_EINTG(3, 0x40, "gps2", 0x08),
+};
+
+/* pin banks of gs101 pin-controller (GSACTRL) */
+static const struct samsung_pin_bank_data gs101_pin_gsactrl[] = {
+	EXYNOS850_PIN_BANK_EINTW(6, 0x0, "gps3", 0x00),
+};
+
+/* pin banks of gs101 pin-controller (PERIC0) */
+static const struct samsung_pin_bank_data gs101_pin_peric0[] = {
+	EXYNOS850_PIN_BANK_EINTG(5, 0x0, "gpp0", 0x00),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x20, "gpp1", 0x04),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x40, "gpp2", 0x08),
+	EXYNOS850_PIN_BANK_EINTG(2, 0x60, "gpp3", 0x0c),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x80, "gpp4", 0x10),
+	EXYNOS850_PIN_BANK_EINTG(2, 0xa0, "gpp5", 0x14),
+	EXYNOS850_PIN_BANK_EINTG(4, 0xc0, "gpp6", 0x18),
+	EXYNOS850_PIN_BANK_EINTG(2, 0xe0, "gpp7", 0x1c),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x100, "gpp8", 0x20),
+	EXYNOS850_PIN_BANK_EINTG(2, 0x120, "gpp9", 0x24),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x140, "gpp10", 0x28),
+	EXYNOS850_PIN_BANK_EINTG(2, 0x160, "gpp11", 0x2c),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x180, "gpp12", 0x30),
+	EXYNOS850_PIN_BANK_EINTG(2, 0x1a0, "gpp13", 0x34),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x1c0, "gpp14", 0x38),
+	EXYNOS850_PIN_BANK_EINTG(2, 0x1e0, "gpp15", 0x3c),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x200, "gpp16", 0x40),
+	EXYNOS850_PIN_BANK_EINTG(2, 0x220, "gpp17", 0x44),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x240, "gpp18", 0x48),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x260, "gpp19", 0x4c),
+};
+
+/* pin banks of gs101 pin-controller (PERIC1) */
+static const struct samsung_pin_bank_data gs101_pin_peric1[] = {
+	EXYNOS850_PIN_BANK_EINTG(8, 0x0, "gpp20", 0x00),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x20, "gpp21", 0x04),
+	EXYNOS850_PIN_BANK_EINTG(2, 0x40, "gpp22", 0x08),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x60, "gpp23", 0x0c),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x80, "gpp24", 0x10),
+	EXYNOS850_PIN_BANK_EINTG(4, 0xa0, "gpp25", 0x14),
+	EXYNOS850_PIN_BANK_EINTG(5, 0xc0, "gpp26", 0x18),
+	EXYNOS850_PIN_BANK_EINTG(4, 0xe0, "gpp27", 0x1c),
+};
+
+/* pin banks of gs101 pin-controller (HSI1) */
+static const struct samsung_pin_bank_data gs101_pin_hsi1[] = {
+	EXYNOS850_PIN_BANK_EINTG(6, 0x0, "gph0", 0x00),
+	EXYNOS850_PIN_BANK_EINTG(7, 0x20, "gph1", 0x04),
+};
+
+/* pin banks of gs101 pin-controller (HSI2) */
+static const struct samsung_pin_bank_data gs101_pin_hsi2[] = {
+	EXYNOS850_PIN_BANK_EINTG(6, 0x0, "gph2", 0x00),
+	EXYNOS850_PIN_BANK_EINTG(2, 0x20, "gph3", 0x04),
+	EXYNOS850_PIN_BANK_EINTG(6, 0x40, "gph4", 0x08),
+};
+
+static const struct samsung_pin_ctrl gs101_pin_ctrl[] __initconst = {
+	{
+		/* pin banks of gs101 pin-controller (ALIVE) */
+		.pin_banks	= gs101_pin_alive,
+		.nr_banks	= ARRAY_SIZE(gs101_pin_alive),
+		.eint_wkup_init = exynos_eint_wkup_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin banks of gs101 pin-controller (FAR_ALIVE) */
+		.pin_banks	= gs101_pin_far_alive,
+		.nr_banks	= ARRAY_SIZE(gs101_pin_far_alive),
+		.eint_wkup_init = exynos_eint_wkup_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin banks of gs101 pin-controller (GSACORE) */
+		.pin_banks	= gs101_pin_gsacore,
+		.nr_banks	= ARRAY_SIZE(gs101_pin_gsacore),
+	}, {
+		/* pin banks of gs101 pin-controller (GSACTRL) */
+		.pin_banks	= gs101_pin_gsactrl,
+		.nr_banks	= ARRAY_SIZE(gs101_pin_gsactrl),
+	}, {
+		/* pin banks of gs101 pin-controller (PERIC0) */
+		.pin_banks	= gs101_pin_peric0,
+		.nr_banks	= ARRAY_SIZE(gs101_pin_peric0),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin banks of gs101 pin-controller (PERIC1) */
+		.pin_banks	= gs101_pin_peric1,
+		.nr_banks	= ARRAY_SIZE(gs101_pin_peric1),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume	= exynos_pinctrl_resume,
+	}, {
+		/* pin banks of gs101 pin-controller (HSI1) */
+		.pin_banks	= gs101_pin_hsi1,
+		.nr_banks	= ARRAY_SIZE(gs101_pin_hsi1),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin banks of gs101 pin-controller (HSI2) */
+		.pin_banks	= gs101_pin_hsi2,
+		.nr_banks	= ARRAY_SIZE(gs101_pin_hsi2),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	},
+};
+
+const struct samsung_pinctrl_of_match_data gs101_of_data __initconst = {
+	.ctrl		= gs101_pin_ctrl,
+	.num_ctrl	= ARRAY_SIZE(gs101_pin_ctrl),
+};
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index 6b58ec84e34b..871c1eb46ddf 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -52,10 +52,15 @@ static void exynos_irq_mask(struct irq_data *irqd)
 	struct irq_chip *chip = irq_data_get_irq_chip(irqd);
 	struct exynos_irq_chip *our_chip = to_exynos_irq_chip(chip);
 	struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd);
-	unsigned long reg_mask = our_chip->eint_mask + bank->eint_offset;
+	unsigned long reg_mask;
 	unsigned int mask;
 	unsigned long flags;
 
+	if (bank->eint_mask_offset)
+		reg_mask = bank->pctl_offset + bank->eint_mask_offset;
+	else
+		reg_mask = our_chip->eint_mask + bank->eint_offset;
+
 	raw_spin_lock_irqsave(&bank->slock, flags);
 
 	mask = readl(bank->eint_base + reg_mask);
@@ -70,7 +75,12 @@ static void exynos_irq_ack(struct irq_data *irqd)
 	struct irq_chip *chip = irq_data_get_irq_chip(irqd);
 	struct exynos_irq_chip *our_chip = to_exynos_irq_chip(chip);
 	struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd);
-	unsigned long reg_pend = our_chip->eint_pend + bank->eint_offset;
+	unsigned long reg_pend;
+
+	if (bank->eint_pend_offset)
+		reg_pend = bank->pctl_offset + bank->eint_pend_offset;
+	else
+		reg_pend = our_chip->eint_pend + bank->eint_offset;
 
 	writel(1 << irqd->hwirq, bank->eint_base + reg_pend);
 }
@@ -80,7 +90,7 @@ static void exynos_irq_unmask(struct irq_data *irqd)
 	struct irq_chip *chip = irq_data_get_irq_chip(irqd);
 	struct exynos_irq_chip *our_chip = to_exynos_irq_chip(chip);
 	struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd);
-	unsigned long reg_mask = our_chip->eint_mask + bank->eint_offset;
+	unsigned long reg_mask;
 	unsigned int mask;
 	unsigned long flags;
 
@@ -95,6 +105,11 @@ static void exynos_irq_unmask(struct irq_data *irqd)
 	if (irqd_get_trigger_type(irqd) & IRQ_TYPE_LEVEL_MASK)
 		exynos_irq_ack(irqd);
 
+	if (bank->eint_mask_offset)
+		reg_mask = bank->pctl_offset + bank->eint_mask_offset;
+	else
+		reg_mask = our_chip->eint_mask + bank->eint_offset;
+
 	raw_spin_lock_irqsave(&bank->slock, flags);
 
 	mask = readl(bank->eint_base + reg_mask);
@@ -111,7 +126,7 @@ static int exynos_irq_set_type(struct irq_data *irqd, unsigned int type)
 	struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd);
 	unsigned int shift = EXYNOS_EINT_CON_LEN * irqd->hwirq;
 	unsigned int con, trig_type;
-	unsigned long reg_con = our_chip->eint_con + bank->eint_offset;
+	unsigned long reg_con;
 
 	switch (type) {
 	case IRQ_TYPE_EDGE_RISING:
@@ -139,6 +154,11 @@ static int exynos_irq_set_type(struct irq_data *irqd, unsigned int type)
 	else
 		irq_set_handler_locked(irqd, handle_level_irq);
 
+	if (bank->eint_con_offset)
+		reg_con = bank->pctl_offset + bank->eint_con_offset;
+	else
+		reg_con = our_chip->eint_con + bank->eint_offset;
+
 	con = readl(bank->eint_base + reg_con);
 	con &= ~(EXYNOS_EINT_CON_MASK << shift);
 	con |= trig_type << shift;
@@ -147,6 +167,19 @@ static int exynos_irq_set_type(struct irq_data *irqd, unsigned int type)
 	return 0;
 }
 
+static int exynos_irq_set_affinity(struct irq_data *irqd,
+				   const struct cpumask *dest, bool force)
+{
+	struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd);
+	struct samsung_pinctrl_drv_data *d = bank->drvdata;
+	struct irq_data *parent = irq_get_irq_data(d->irq);
+
+	if (parent)
+		return parent->chip->irq_set_affinity(parent, dest, force);
+
+	return -EINVAL;
+}
+
 static int exynos_irq_request_resources(struct irq_data *irqd)
 {
 	struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd);
@@ -212,6 +245,7 @@ static const struct exynos_irq_chip exynos_gpio_irq_chip __initconst = {
 		.irq_mask = exynos_irq_mask,
 		.irq_ack = exynos_irq_ack,
 		.irq_set_type = exynos_irq_set_type,
+		.irq_set_affinity = exynos_irq_set_affinity,
 		.irq_request_resources = exynos_irq_request_resources,
 		.irq_release_resources = exynos_irq_release_resources,
 	},
@@ -247,7 +281,10 @@ static irqreturn_t exynos_eint_gpio_irq(int irq, void *data)
 	unsigned int svc, group, pin;
 	int ret;
 
-	svc = readl(bank->eint_base + EXYNOS_SVC_OFFSET);
+	if (bank->eint_con_offset)
+		svc = readl(bank->eint_base + EXYNOSAUTO_SVC_OFFSET);
+	else
+		svc = readl(bank->eint_base + EXYNOS_SVC_OFFSET);
 	group = EXYNOS_SVC_GROUP(svc);
 	pin = svc & EXYNOS_SVC_NUM_MASK;
 
@@ -456,6 +493,22 @@ static const struct exynos_irq_chip exynos7_wkup_irq_chip __initconst = {
 	.set_eint_wakeup_mask = exynos_pinctrl_set_eint_wakeup_mask,
 };
 
+static const struct exynos_irq_chip exynosautov920_wkup_irq_chip __initconst = {
+	.chip = {
+		.name = "exynosautov920_wkup_irq_chip",
+		.irq_unmask = exynos_irq_unmask,
+		.irq_mask = exynos_irq_mask,
+		.irq_ack = exynos_irq_ack,
+		.irq_set_type = exynos_irq_set_type,
+		.irq_set_wake = exynos_wkup_irq_set_wake,
+		.irq_request_resources = exynos_irq_request_resources,
+		.irq_release_resources = exynos_irq_release_resources,
+	},
+	.eint_wake_mask_value = &eint_wake_mask_value,
+	.eint_wake_mask_reg = EXYNOS5433_EINT_WAKEUP_MASK,
+	.set_eint_wakeup_mask = exynos_pinctrl_set_eint_wakeup_mask,
+};
+
 /* list of external wakeup controllers supported */
 static const struct of_device_id exynos_wkup_irq_ids[] = {
 	{ .compatible = "samsung,s5pv210-wakeup-eint",
@@ -468,6 +521,8 @@ static const struct of_device_id exynos_wkup_irq_ids[] = {
 			.data = &exynos7_wkup_irq_chip },
 	{ .compatible = "samsung,exynosautov9-wakeup-eint",
 			.data = &exynos7_wkup_irq_chip },
+	{ .compatible = "samsung,exynosautov920-wakeup-eint",
+			.data = &exynosautov920_wkup_irq_chip },
 	{ }
 };
 
@@ -638,7 +693,7 @@ static void exynos_pinctrl_suspend_bank(
 				struct samsung_pin_bank *bank)
 {
 	struct exynos_eint_gpio_save *save = bank->soc_priv;
-	void __iomem *regs = bank->eint_base;
+	const void __iomem *regs = bank->eint_base;
 
 	save->eint_con = readl(regs + EXYNOS_GPIO_ECON_OFFSET
 						+ bank->eint_offset);
@@ -655,6 +710,19 @@ static void exynos_pinctrl_suspend_bank(
 	pr_debug("%s: save    mask %#010x\n", bank->name, save->eint_mask);
 }
 
+static void exynosauto_pinctrl_suspend_bank(struct samsung_pinctrl_drv_data *drvdata,
+					    struct samsung_pin_bank *bank)
+{
+	struct exynos_eint_gpio_save *save = bank->soc_priv;
+	const void __iomem *regs = bank->eint_base;
+
+	save->eint_con = readl(regs + bank->pctl_offset + bank->eint_con_offset);
+	save->eint_mask = readl(regs + bank->pctl_offset + bank->eint_mask_offset);
+
+	pr_debug("%s: save     con %#010x\n", bank->name, save->eint_con);
+	pr_debug("%s: save    mask %#010x\n", bank->name, save->eint_mask);
+}
+
 void exynos_pinctrl_suspend(struct samsung_pinctrl_drv_data *drvdata)
 {
 	struct samsung_pin_bank *bank = drvdata->pin_banks;
@@ -662,8 +730,12 @@ void exynos_pinctrl_suspend(struct samsung_pinctrl_drv_data *drvdata)
 	int i;
 
 	for (i = 0; i < drvdata->nr_banks; ++i, ++bank) {
-		if (bank->eint_type == EINT_TYPE_GPIO)
-			exynos_pinctrl_suspend_bank(drvdata, bank);
+		if (bank->eint_type == EINT_TYPE_GPIO) {
+			if (bank->eint_con_offset)
+				exynosauto_pinctrl_suspend_bank(drvdata, bank);
+			else
+				exynos_pinctrl_suspend_bank(drvdata, bank);
+		}
 		else if (bank->eint_type == EINT_TYPE_WKUP) {
 			if (!irq_chip) {
 				irq_chip = bank->irq_chip;
@@ -704,14 +776,33 @@ static void exynos_pinctrl_resume_bank(
 						+ bank->eint_offset);
 }
 
+static void exynosauto_pinctrl_resume_bank(struct samsung_pinctrl_drv_data *drvdata,
+					   struct samsung_pin_bank *bank)
+{
+	struct exynos_eint_gpio_save *save = bank->soc_priv;
+	void __iomem *regs = bank->eint_base;
+
+	pr_debug("%s:     con %#010x => %#010x\n", bank->name,
+		 readl(regs + bank->pctl_offset + bank->eint_con_offset), save->eint_con);
+	pr_debug("%s:    mask %#010x => %#010x\n", bank->name,
+		 readl(regs + bank->pctl_offset + bank->eint_mask_offset), save->eint_mask);
+
+	writel(save->eint_con, regs + bank->pctl_offset + bank->eint_con_offset);
+	writel(save->eint_mask, regs + bank->pctl_offset + bank->eint_mask_offset);
+}
+
 void exynos_pinctrl_resume(struct samsung_pinctrl_drv_data *drvdata)
 {
 	struct samsung_pin_bank *bank = drvdata->pin_banks;
 	int i;
 
 	for (i = 0; i < drvdata->nr_banks; ++i, ++bank)
-		if (bank->eint_type == EINT_TYPE_GPIO)
-			exynos_pinctrl_resume_bank(drvdata, bank);
+		if (bank->eint_type == EINT_TYPE_GPIO) {
+			if (bank->eint_con_offset)
+				exynosauto_pinctrl_resume_bank(drvdata, bank);
+			else
+				exynos_pinctrl_resume_bank(drvdata, bank);
+		}
 }
 
 static void exynos_retention_enable(struct samsung_pinctrl_drv_data *drvdata)
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.h b/drivers/pinctrl/samsung/pinctrl-exynos.h
index 3ac52c2cf998..305cb1d31de4 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.h
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.h
@@ -31,6 +31,7 @@
 #define EXYNOS7_WKUP_EMASK_OFFSET	0x900
 #define EXYNOS7_WKUP_EPEND_OFFSET	0xA00
 #define EXYNOS_SVC_OFFSET		0xB08
+#define EXYNOSAUTO_SVC_OFFSET		0xF008
 
 /* helpers to access interrupt service register */
 #define EXYNOS_SVC_GROUP_SHIFT		3
@@ -140,6 +141,30 @@
 		.name		= id				\
 	}
 
+#define EXYNOSV920_PIN_BANK_EINTG(pins, reg, id, con_offs, mask_offs, pend_offs)	\
+	{							\
+		.type			= &exynos850_bank_type_off,	\
+		.pctl_offset		= reg,				\
+		.nr_pins		= pins,				\
+		.eint_type		= EINT_TYPE_GPIO,		\
+		.eint_con_offset	= con_offs,			\
+		.eint_mask_offset	= mask_offs,			\
+		.eint_pend_offset	= pend_offs,			\
+		.name			= id				\
+	}
+
+#define EXYNOSV920_PIN_BANK_EINTW(pins, reg, id, con_offs, mask_offs, pend_offs)	\
+	{							\
+		.type			= &exynos850_bank_type_alive,	\
+		.pctl_offset		= reg,				\
+		.nr_pins		= pins,				\
+		.eint_type		= EINT_TYPE_WKUP,		\
+		.eint_con_offset	= con_offs,			\
+		.eint_mask_offset	= mask_offs,			\
+		.eint_pend_offset	= pend_offs,			\
+		.name			= id				\
+	}
+
 /**
  * struct exynos_weint_data: irq specific data for all the wakeup interrupts
  * generated by the external wakeup interrupt controller.
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c
index 79babbb39ced..ed07e23e0912 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.c
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.c
@@ -565,7 +565,7 @@ static void samsung_gpio_set(struct gpio_chip *gc, unsigned offset, int value)
 /* gpiolib gpio_get callback function */
 static int samsung_gpio_get(struct gpio_chip *gc, unsigned offset)
 {
-	void __iomem *reg;
+	const void __iomem *reg;
 	u32 data;
 	struct samsung_pin_bank *bank = gpiochip_get_data(gc);
 	const struct samsung_pin_bank_type *type = bank->type;
@@ -1106,6 +1106,9 @@ samsung_pinctrl_get_soc_data(struct samsung_pinctrl_drv_data *d,
 		bank->eint_type = bdata->eint_type;
 		bank->eint_mask = bdata->eint_mask;
 		bank->eint_offset = bdata->eint_offset;
+		bank->eint_con_offset = bdata->eint_con_offset;
+		bank->eint_mask_offset = bdata->eint_mask_offset;
+		bank->eint_pend_offset = bdata->eint_pend_offset;
 		bank->name = bdata->name;
 
 		raw_spin_lock_init(&bank->slock);
@@ -1201,7 +1204,7 @@ static int __maybe_unused samsung_pinctrl_suspend(struct device *dev)
 
 	for (i = 0; i < drvdata->nr_banks; i++) {
 		struct samsung_pin_bank *bank = &drvdata->pin_banks[i];
-		void __iomem *reg = bank->pctl_base + bank->pctl_offset;
+		const void __iomem *reg = bank->pctl_base + bank->pctl_offset;
 		const u8 *offs = bank->type->reg_offset;
 		const u8 *widths = bank->type->fld_width;
 		enum pincfg_type type;
@@ -1309,6 +1312,8 @@ static const struct of_device_id samsung_pinctrl_dt_match[] = {
 		.data = &s5pv210_of_data },
 #endif
 #ifdef CONFIG_PINCTRL_EXYNOS_ARM64
+	{ .compatible = "google,gs101-pinctrl",
+		.data = &gs101_of_data },
 	{ .compatible = "samsung,exynos5433-pinctrl",
 		.data = &exynos5433_of_data },
 	{ .compatible = "samsung,exynos7-pinctrl",
@@ -1319,6 +1324,8 @@ static const struct of_device_id samsung_pinctrl_dt_match[] = {
 		.data = &exynos850_of_data },
 	{ .compatible = "samsung,exynosautov9-pinctrl",
 		.data = &exynosautov9_of_data },
+	{ .compatible = "samsung,exynosautov920-pinctrl",
+		.data = &exynosautov920_of_data },
 	{ .compatible = "tesla,fsd-pinctrl",
 		.data = &fsd_of_data },
 #endif
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.h b/drivers/pinctrl/samsung/pinctrl-samsung.h
index 9b3db50adef3..ab791afaabf5 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.h
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.h
@@ -122,6 +122,9 @@ struct samsung_pin_bank_type {
  * @eint_type: type of the external interrupt supported by the bank.
  * @eint_mask: bit mask of pins which support EINT function.
  * @eint_offset: SoC-specific EINT register or interrupt offset of bank.
+ * @eint_con_offset: ExynosAuto SoC-specific EINT control register offset of bank.
+ * @eint_mask_offset: ExynosAuto SoC-specific EINT mask register offset of bank.
+ * @eint_pend_offset: ExynosAuto SoC-specific EINT pend register offset of bank.
  * @name: name to be prefixed for each pin in this pin bank.
  */
 struct samsung_pin_bank_data {
@@ -133,6 +136,9 @@ struct samsung_pin_bank_data {
 	enum eint_type	eint_type;
 	u32		eint_mask;
 	u32		eint_offset;
+	u32		eint_con_offset;
+	u32		eint_mask_offset;
+	u32		eint_pend_offset;
 	const char	*name;
 };
 
@@ -147,6 +153,9 @@ struct samsung_pin_bank_data {
  * @eint_type: type of the external interrupt supported by the bank.
  * @eint_mask: bit mask of pins which support EINT function.
  * @eint_offset: SoC-specific EINT register or interrupt offset of bank.
+ * @eint_con_offset: ExynosAuto SoC-specific EINT register or interrupt offset of bank.
+ * @eint_mask_offset: ExynosAuto SoC-specific EINT mask register offset of bank.
+ * @eint_pend_offset: ExynosAuto SoC-specific EINT pend register offset of bank.
  * @name: name to be prefixed for each pin in this pin bank.
  * @id: id of the bank, propagated to the pin range.
  * @pin_base: starting pin number of the bank.
@@ -170,6 +179,9 @@ struct samsung_pin_bank {
 	enum eint_type	eint_type;
 	u32		eint_mask;
 	u32		eint_offset;
+	u32		eint_con_offset;
+	u32		eint_mask_offset;
+	u32		eint_pend_offset;
 	const char	*name;
 	u32		id;
 
@@ -350,7 +362,9 @@ extern const struct samsung_pinctrl_of_match_data exynos7_of_data;
 extern const struct samsung_pinctrl_of_match_data exynos7885_of_data;
 extern const struct samsung_pinctrl_of_match_data exynos850_of_data;
 extern const struct samsung_pinctrl_of_match_data exynosautov9_of_data;
+extern const struct samsung_pinctrl_of_match_data exynosautov920_of_data;
 extern const struct samsung_pinctrl_of_match_data fsd_of_data;
+extern const struct samsung_pinctrl_of_match_data gs101_of_data;
 extern const struct samsung_pinctrl_of_match_data s3c64xx_of_data;
 extern const struct samsung_pinctrl_of_match_data s3c2412_of_data;
 extern const struct samsung_pinctrl_of_match_data s3c2416_of_data;
diff --git a/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c b/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c
index b29b0ab9892b..6df7a310c7ed 100644
--- a/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c
+++ b/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c
@@ -654,7 +654,7 @@ static int starfive_set_mux(struct pinctrl_dev *pctldev,
 		return -EINVAL;
 
 	pinmux = group->data;
-	for (i = 0; i < group->num_pins; i++) {
+	for (i = 0; i < group->grp.npins; i++) {
 		u32 v = pinmux[i];
 		unsigned int gpio = starfive_pinmux_to_gpio(v);
 		u32 dout = starfive_pinmux_to_dout(v);
@@ -797,7 +797,7 @@ static int starfive_pinconf_group_get(struct pinctrl_dev *pctldev,
 	if (!group)
 		return -EINVAL;
 
-	return starfive_pinconf_get(pctldev, group->pins[0], config);
+	return starfive_pinconf_get(pctldev, group->grp.pins[0], config);
 }
 
 static int starfive_pinconf_group_set(struct pinctrl_dev *pctldev,
@@ -876,8 +876,8 @@ static int starfive_pinconf_group_set(struct pinctrl_dev *pctldev,
 		}
 	}
 
-	for (i = 0; i < group->num_pins; i++)
-		starfive_padctl_rmw(sfp, group->pins[i], mask, value);
+	for (i = 0; i < group->grp.npins; i++)
+		starfive_padctl_rmw(sfp, group->grp.pins[i], mask, value);
 
 	return 0;
 }
diff --git a/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c b/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
index 6de11a405734..9609eb1ecc3d 100644
--- a/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
+++ b/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
@@ -307,7 +307,7 @@ static int jh7110_set_mux(struct pinctrl_dev *pctldev,
 		return -EINVAL;
 
 	pinmux = group->data;
-	for (i = 0; i < group->num_pins; i++) {
+	for (i = 0; i < group->grp.npins; i++) {
 		u32 v = pinmux[i];
 
 		if (info->jh7110_set_one_pin_mux)
@@ -437,7 +437,7 @@ static int jh7110_pinconf_group_get(struct pinctrl_dev *pctldev,
 	if (!group)
 		return -EINVAL;
 
-	return jh7110_pinconf_get(pctldev, group->pins[0], config);
+	return jh7110_pinconf_get(pctldev, group->grp.pins[0], config);
 }
 
 static int jh7110_pinconf_group_set(struct pinctrl_dev *pctldev,
@@ -508,8 +508,8 @@ static int jh7110_pinconf_group_set(struct pinctrl_dev *pctldev,
 		}
 	}
 
-	for (i = 0; i < group->num_pins; i++)
-		jh7110_padcfg_rmw(sfp, group->pins[i], mask, value);
+	for (i = 0; i < group->grp.npins; i++)
+		jh7110_padcfg_rmw(sfp, group->grp.pins[i], mask, value);
 
 	return 0;
 }
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c
index 603f900e88c1..978ccdbaf3d3 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32.c
@@ -240,9 +240,8 @@ static int stm32_gpio_direction_output(struct gpio_chip *chip,
 	struct stm32_gpio_bank *bank = gpiochip_get_data(chip);
 
 	__stm32_gpio_set(bank, offset, value);
-	pinctrl_gpio_direction_output(chip, offset);
 
-	return 0;
+	return pinctrl_gpio_direction_output(chip, offset);
 }
 
 
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32mp257.c b/drivers/pinctrl/stm32/pinctrl-stm32mp257.c
index 73f091cd827e..23aebd4695e9 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32mp257.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32mp257.c
@@ -2562,7 +2562,7 @@ static const struct of_device_id stm32mp257_pctrl_match[] = {
 };
 
 static const struct dev_pm_ops stm32_pinctrl_dev_pm_ops = {
-	 SET_LATE_SYSTEM_SLEEP_PM_OPS(NULL, stm32_pinctrl_resume)
+	 SET_LATE_SYSTEM_SLEEP_PM_OPS(stm32_pinctrl_suspend, stm32_pinctrl_resume)
 };
 
 static struct platform_driver stm32mp257_pinctrl_driver = {
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra.c b/drivers/pinctrl/tegra/pinctrl-tegra.c
index 6bf8db424bec..ccfa3870a67d 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra.c
@@ -636,6 +636,14 @@ static void tegra_pinconf_group_dbg_show(struct pinctrl_dev *pctldev,
 		seq_printf(s, "\n\t%s=%u",
 			   strip_prefix(cfg_params[i].property), val);
 	}
+
+	if (g->mux_reg >= 0) {
+		/* read pinmux function and dump to seq_file */
+		val = pmx_readl(pmx, g->mux_bank, g->mux_reg);
+		val = g->funcs[(val >> g->mux_bit) & 0x3];
+
+		seq_printf(s, "\n\tfunction=%s", pmx->functions[val].name);
+	}
 }
 
 static void tegra_pinconf_config_dbg_show(struct pinctrl_dev *pctldev,
diff --git a/drivers/platform/chrome/cros_ec_uart.c b/drivers/platform/chrome/cros_ec_uart.c
index 788246559bbb..68d80559fddc 100644
--- a/drivers/platform/chrome/cros_ec_uart.c
+++ b/drivers/platform/chrome/cros_ec_uart.c
@@ -81,9 +81,8 @@ struct cros_ec_uart {
 	struct response_info response;
 };
 
-static int cros_ec_uart_rx_bytes(struct serdev_device *serdev,
-				 const u8 *data,
-				 size_t count)
+static ssize_t cros_ec_uart_rx_bytes(struct serdev_device *serdev,
+				     const u8 *data, size_t count)
 {
 	struct ec_host_response *host_response;
 	struct cros_ec_device *ec_dev = serdev_device_get_drvdata(serdev);
diff --git a/drivers/platform/goldfish/goldfish_pipe.c b/drivers/platform/goldfish/goldfish_pipe.c
index 7737d56191d7..061aa9647c19 100644
--- a/drivers/platform/goldfish/goldfish_pipe.c
+++ b/drivers/platform/goldfish/goldfish_pipe.c
@@ -915,12 +915,11 @@ static int goldfish_pipe_probe(struct platform_device *pdev)
 	return goldfish_pipe_device_init(pdev, dev);
 }
 
-static int goldfish_pipe_remove(struct platform_device *pdev)
+static void goldfish_pipe_remove(struct platform_device *pdev)
 {
 	struct goldfish_pipe_dev *dev = platform_get_drvdata(pdev);
 
 	goldfish_pipe_device_deinit(pdev, dev);
-	return 0;
 }
 
 static const struct acpi_device_id goldfish_pipe_acpi_match[] = {
@@ -937,7 +936,7 @@ MODULE_DEVICE_TABLE(of, goldfish_pipe_of_match);
 
 static struct platform_driver goldfish_pipe_driver = {
 	.probe = goldfish_pipe_probe,
-	.remove = goldfish_pipe_remove,
+	.remove_new = goldfish_pipe_remove,
 	.driver = {
 		.name = "goldfish_pipe",
 		.of_match_table = goldfish_pipe_of_match,
diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c
index 1dd84c7a79de..b1995ac268d7 100644
--- a/drivers/platform/mellanox/mlxbf-pmc.c
+++ b/drivers/platform/mellanox/mlxbf-pmc.c
@@ -1170,7 +1170,7 @@ static int mlxbf_pmc_program_crspace_counter(int blk_num, uint32_t cnt_num,
 	int ret;
 
 	addr = pmc->block[blk_num].mmio_base +
-		(rounddown(cnt_num, 2) * MLXBF_PMC_CRSPACE_PERFSEL_SZ);
+		((cnt_num / 2) * MLXBF_PMC_CRSPACE_PERFSEL_SZ);
 	ret = mlxbf_pmc_readl(addr, &word);
 	if (ret)
 		return ret;
@@ -1413,7 +1413,7 @@ static int mlxbf_pmc_read_crspace_event(int blk_num, uint32_t cnt_num,
 	int ret;
 
 	addr = pmc->block[blk_num].mmio_base +
-		(rounddown(cnt_num, 2) * MLXBF_PMC_CRSPACE_PERFSEL_SZ);
+		((cnt_num / 2) * MLXBF_PMC_CRSPACE_PERFSEL_SZ);
 	ret = mlxbf_pmc_readl(addr, &word);
 	if (ret)
 		return ret;
diff --git a/drivers/platform/mellanox/mlxbf-tmfifo.c b/drivers/platform/mellanox/mlxbf-tmfifo.c
index ed16ec422a7b..b8d1e32e97eb 100644
--- a/drivers/platform/mellanox/mlxbf-tmfifo.c
+++ b/drivers/platform/mellanox/mlxbf-tmfifo.c
@@ -47,6 +47,9 @@
 /* Message with data needs at least two words (for header & data). */
 #define MLXBF_TMFIFO_DATA_MIN_WORDS		2
 
+/* Tx timeout in milliseconds. */
+#define TMFIFO_TX_TIMEOUT			2000
+
 /* ACPI UID for BlueField-3. */
 #define TMFIFO_BF3_UID				1
 
@@ -62,12 +65,14 @@ struct mlxbf_tmfifo;
  * @drop_desc: dummy desc for packet dropping
  * @cur_len: processed length of the current descriptor
  * @rem_len: remaining length of the pending packet
+ * @rem_padding: remaining bytes to send as paddings
  * @pkt_len: total length of the pending packet
  * @next_avail: next avail descriptor id
  * @num: vring size (number of descriptors)
  * @align: vring alignment size
  * @index: vring index
  * @vdev_id: vring virtio id (VIRTIO_ID_xxx)
+ * @tx_timeout: expire time of last tx packet
  * @fifo: pointer to the tmfifo structure
  */
 struct mlxbf_tmfifo_vring {
@@ -79,12 +84,14 @@ struct mlxbf_tmfifo_vring {
 	struct vring_desc drop_desc;
 	int cur_len;
 	int rem_len;
+	int rem_padding;
 	u32 pkt_len;
 	u16 next_avail;
 	int num;
 	int align;
 	int index;
 	int vdev_id;
+	unsigned long tx_timeout;
 	struct mlxbf_tmfifo *fifo;
 };
 
@@ -819,6 +826,50 @@ mlxbf_tmfifo_desc_done:
 	return true;
 }
 
+static void mlxbf_tmfifo_check_tx_timeout(struct mlxbf_tmfifo_vring *vring)
+{
+	unsigned long flags;
+
+	/* Only handle Tx timeout for network vdev. */
+	if (vring->vdev_id != VIRTIO_ID_NET)
+		return;
+
+	/* Initialize the timeout or return if not expired. */
+	if (!vring->tx_timeout) {
+		/* Initialize the timeout. */
+		vring->tx_timeout = jiffies +
+			msecs_to_jiffies(TMFIFO_TX_TIMEOUT);
+		return;
+	} else if (time_before(jiffies, vring->tx_timeout)) {
+		/* Return if not timeout yet. */
+		return;
+	}
+
+	/*
+	 * Drop the packet after timeout. The outstanding packet is
+	 * released and the remaining bytes will be sent with padding byte 0x00
+	 * as a recovery. On the peer(host) side, the padding bytes 0x00 will be
+	 * either dropped directly, or appended into existing outstanding packet
+	 * thus dropped as corrupted network packet.
+	 */
+	vring->rem_padding = round_up(vring->rem_len, sizeof(u64));
+	mlxbf_tmfifo_release_pkt(vring);
+	vring->cur_len = 0;
+	vring->rem_len = 0;
+	vring->fifo->vring[0] = NULL;
+
+	/*
+	 * Make sure the load/store are in order before
+	 * returning back to virtio.
+	 */
+	virtio_mb(false);
+
+	/* Notify upper layer. */
+	spin_lock_irqsave(&vring->fifo->spin_lock[0], flags);
+	vring_interrupt(0, vring->vq);
+	spin_unlock_irqrestore(&vring->fifo->spin_lock[0], flags);
+}
+
 /* Rx & Tx processing of a queue. */
 static void mlxbf_tmfifo_rxtx(struct mlxbf_tmfifo_vring *vring, bool is_rx)
 {
@@ -841,6 +892,7 @@ static void mlxbf_tmfifo_rxtx(struct mlxbf_tmfifo_vring *vring, bool is_rx)
 		return;
 
 	do {
+retry:
 		/* Get available FIFO space. */
 		if (avail == 0) {
 			if (is_rx)
@@ -851,6 +903,17 @@ static void mlxbf_tmfifo_rxtx(struct mlxbf_tmfifo_vring *vring, bool is_rx)
 				break;
 		}
 
+		/* Insert paddings for discarded Tx packet. */
+		if (!is_rx) {
+			vring->tx_timeout = 0;
+			while (vring->rem_padding >= sizeof(u64)) {
+				writeq(0, vring->fifo->tx.data);
+				vring->rem_padding -= sizeof(u64);
+				if (--avail == 0)
+					goto retry;
+			}
+		}
+
 		/* Console output always comes from the Tx buffer. */
 		if (!is_rx && devid == VIRTIO_ID_CONSOLE) {
 			mlxbf_tmfifo_console_tx(fifo, avail);
@@ -860,6 +923,10 @@ static void mlxbf_tmfifo_rxtx(struct mlxbf_tmfifo_vring *vring, bool is_rx)
 		/* Handle one descriptor. */
 		more = mlxbf_tmfifo_rxtx_one_desc(vring, is_rx, &avail);
 	} while (more);
+
+	/* Check Tx timeout. */
+	if (avail <= 0 && !is_rx)
+		mlxbf_tmfifo_check_tx_timeout(vring);
 }
 
 /* Handle Rx or Tx queues. */
diff --git a/drivers/platform/surface/aggregator/bus.c b/drivers/platform/surface/aggregator/bus.c
index 42ccd7f1c9b9..118caa651bec 100644
--- a/drivers/platform/surface/aggregator/bus.c
+++ b/drivers/platform/surface/aggregator/bus.c
@@ -35,6 +35,8 @@ static struct attribute *ssam_device_attrs[] = {
 };
 ATTRIBUTE_GROUPS(ssam_device);
 
+static const struct bus_type ssam_bus_type;
+
 static int ssam_device_uevent(const struct device *dev, struct kobj_uevent_env *env)
 {
 	const struct ssam_device *sdev = to_ssam_device(dev);
@@ -329,13 +331,12 @@ static void ssam_bus_remove(struct device *dev)
 		sdrv->remove(to_ssam_device(dev));
 }
 
-struct bus_type ssam_bus_type = {
+static const struct bus_type ssam_bus_type = {
 	.name   = "surface_aggregator",
 	.match  = ssam_bus_match,
 	.probe  = ssam_bus_probe,
 	.remove = ssam_bus_remove,
 };
-EXPORT_SYMBOL_GPL(ssam_bus_type);
 
 /**
  * __ssam_device_driver_register() - Register a SSAM client device driver.
diff --git a/drivers/platform/surface/aggregator/controller.h b/drivers/platform/surface/aggregator/controller.h
index f0d987abc51e..f1638c2081e8 100644
--- a/drivers/platform/surface/aggregator/controller.h
+++ b/drivers/platform/surface/aggregator/controller.h
@@ -238,8 +238,8 @@ struct ssam_controller {
  * layer of the controller has been shut down, %-ESHUTDOWN.
  */
 static inline
-int ssam_controller_receive_buf(struct ssam_controller *ctrl,
-				const unsigned char *buf, size_t n)
+ssize_t ssam_controller_receive_buf(struct ssam_controller *ctrl, const u8 *buf,
+				    size_t n)
 {
 	return ssh_ptl_rx_rcvbuf(&ctrl->rtl.ptl, buf, n);
 }
diff --git a/drivers/platform/surface/aggregator/core.c b/drivers/platform/surface/aggregator/core.c
index 6152be38398c..9591a28bc38a 100644
--- a/drivers/platform/surface/aggregator/core.c
+++ b/drivers/platform/surface/aggregator/core.c
@@ -227,8 +227,8 @@ EXPORT_SYMBOL_GPL(ssam_client_bind);
 
 /* -- Glue layer (serdev_device -> ssam_controller). ------------------------ */
 
-static int ssam_receive_buf(struct serdev_device *dev, const unsigned char *buf,
-			    size_t n)
+static ssize_t ssam_receive_buf(struct serdev_device *dev, const u8 *buf,
+				size_t n)
 {
 	struct ssam_controller *ctrl;
 	int ret;
diff --git a/drivers/platform/surface/aggregator/ssh_packet_layer.c b/drivers/platform/surface/aggregator/ssh_packet_layer.c
index def8d7ac541f..d726b1a86319 100644
--- a/drivers/platform/surface/aggregator/ssh_packet_layer.c
+++ b/drivers/platform/surface/aggregator/ssh_packet_layer.c
@@ -1887,9 +1887,9 @@ int ssh_ptl_rx_stop(struct ssh_ptl *ptl)
  * Return: Returns the number of bytes transferred (positive or zero) on
  * success. Returns %-ESHUTDOWN if the packet layer has been shut down.
  */
-int ssh_ptl_rx_rcvbuf(struct ssh_ptl *ptl, const u8 *buf, size_t n)
+ssize_t ssh_ptl_rx_rcvbuf(struct ssh_ptl *ptl, const u8 *buf, size_t n)
 {
-	int used;
+	size_t used;
 
 	if (test_bit(SSH_PTL_SF_SHUTDOWN_BIT, &ptl->state))
 		return -ESHUTDOWN;
diff --git a/drivers/platform/surface/aggregator/ssh_packet_layer.h b/drivers/platform/surface/aggregator/ssh_packet_layer.h
index 64633522f971..c80e822070df 100644
--- a/drivers/platform/surface/aggregator/ssh_packet_layer.h
+++ b/drivers/platform/surface/aggregator/ssh_packet_layer.h
@@ -162,7 +162,7 @@ void ssh_ptl_shutdown(struct ssh_ptl *ptl);
 int ssh_ptl_submit(struct ssh_ptl *ptl, struct ssh_packet *p);
 void ssh_ptl_cancel(struct ssh_packet *p);
 
-int ssh_ptl_rx_rcvbuf(struct ssh_ptl *ptl, const u8 *buf, size_t n);
+ssize_t ssh_ptl_rx_rcvbuf(struct ssh_ptl *ptl, const u8 *buf, size_t n);
 
 /**
  * ssh_ptl_tx_wakeup_transfer() - Wake up packet transmitter thread for
diff --git a/drivers/platform/x86/amd/pmf/Kconfig b/drivers/platform/x86/amd/pmf/Kconfig
index f246252bddd8..f4fa8bd8bda8 100644
--- a/drivers/platform/x86/amd/pmf/Kconfig
+++ b/drivers/platform/x86/amd/pmf/Kconfig
@@ -10,6 +10,7 @@ config AMD_PMF
 	depends on AMD_NB
 	select ACPI_PLATFORM_PROFILE
 	depends on TEE && AMDTEE
+	depends on AMD_SFH_HID
 	help
 	  This driver provides support for the AMD Platform Management Framework.
 	  The goal is to enhance end user experience by making AMD PCs smarter,
diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c
index feaa09f5b35a..4f734e049f4a 100644
--- a/drivers/platform/x86/amd/pmf/core.c
+++ b/drivers/platform/x86/amd/pmf/core.c
@@ -296,7 +296,8 @@ static int amd_pmf_suspend_handler(struct device *dev)
 {
 	struct amd_pmf_dev *pdev = dev_get_drvdata(dev);
 
-	kfree(pdev->buf);
+	if (pdev->smart_pc_enabled)
+		cancel_delayed_work_sync(&pdev->pb_work);
 
 	return 0;
 }
@@ -312,6 +313,9 @@ static int amd_pmf_resume_handler(struct device *dev)
 			return ret;
 	}
 
+	if (pdev->smart_pc_enabled)
+		schedule_delayed_work(&pdev->pb_work, msecs_to_jiffies(2000));
+
 	return 0;
 }
 
@@ -330,9 +334,14 @@ static void amd_pmf_init_features(struct amd_pmf_dev *dev)
 		dev_dbg(dev->dev, "SPS enabled and Platform Profiles registered\n");
 	}
 
-	if (!amd_pmf_init_smart_pc(dev)) {
+	amd_pmf_init_smart_pc(dev);
+	if (dev->smart_pc_enabled) {
 		dev_dbg(dev->dev, "Smart PC Solution Enabled\n");
-	} else if (is_apmf_func_supported(dev, APMF_FUNC_AUTO_MODE)) {
+		/* If Smart PC is enabled, no need to check for other features */
+		return;
+	}
+
+	if (is_apmf_func_supported(dev, APMF_FUNC_AUTO_MODE)) {
 		amd_pmf_init_auto_mode(dev);
 		dev_dbg(dev->dev, "Auto Mode Init done\n");
 	} else if (is_apmf_func_supported(dev, APMF_FUNC_DYN_SLIDER_AC) ||
@@ -351,7 +360,7 @@ static void amd_pmf_deinit_features(struct amd_pmf_dev *dev)
 		amd_pmf_deinit_sps(dev);
 	}
 
-	if (!dev->smart_pc_enabled) {
+	if (dev->smart_pc_enabled) {
 		amd_pmf_deinit_smart_pc(dev);
 	} else if (is_apmf_func_supported(dev, APMF_FUNC_AUTO_MODE)) {
 		amd_pmf_deinit_auto_mode(dev);
diff --git a/drivers/platform/x86/amd/pmf/pmf.h b/drivers/platform/x86/amd/pmf/pmf.h
index 16999c5b334f..66cae1cca73c 100644
--- a/drivers/platform/x86/amd/pmf/pmf.h
+++ b/drivers/platform/x86/amd/pmf/pmf.h
@@ -441,11 +441,6 @@ struct apmf_dyn_slider_output {
 	struct apmf_cnqf_power_set ps[APMF_CNQF_MAX];
 } __packed;
 
-enum smart_pc_status {
-	PMF_SMART_PC_ENABLED,
-	PMF_SMART_PC_DISABLED,
-};
-
 /* Smart PC - TA internals */
 enum system_state {
 	SYSTEM_STATE_S0i3,
diff --git a/drivers/platform/x86/amd/pmf/spc.c b/drivers/platform/x86/amd/pmf/spc.c
index a0423942f771..a3dec14c3004 100644
--- a/drivers/platform/x86/amd/pmf/spc.c
+++ b/drivers/platform/x86/amd/pmf/spc.c
@@ -10,6 +10,7 @@
  */
 
 #include <acpi/button.h>
+#include <linux/amd-pmf-io.h>
 #include <linux/power_supply.h>
 #include <linux/units.h>
 #include "pmf.h"
@@ -44,6 +45,8 @@ void amd_pmf_dump_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *
 	dev_dbg(dev->dev, "Max C0 Residency: %u\n", in->ev_info.max_c0residency);
 	dev_dbg(dev->dev, "GFX Busy: %u\n", in->ev_info.gfx_busy);
 	dev_dbg(dev->dev, "LID State: %s\n", in->ev_info.lid_state ? "close" : "open");
+	dev_dbg(dev->dev, "User Presence: %s\n", in->ev_info.user_present ? "Present" : "Away");
+	dev_dbg(dev->dev, "Ambient Light: %d\n", in->ev_info.ambient_light);
 	dev_dbg(dev->dev, "==== TA inputs END ====\n");
 }
 #else
@@ -147,6 +150,38 @@ static int amd_pmf_get_slider_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_
 	return 0;
 }
 
+static int amd_pmf_get_sensor_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in)
+{
+	struct amd_sfh_info sfh_info;
+	int ret;
+
+	/* Get ALS data */
+	ret = amd_get_sfh_info(&sfh_info, MT_ALS);
+	if (!ret)
+		in->ev_info.ambient_light = sfh_info.ambient_light;
+	else
+		return ret;
+
+	/* get HPD data */
+	ret = amd_get_sfh_info(&sfh_info, MT_HPD);
+	if (ret)
+		return ret;
+
+	switch (sfh_info.user_present) {
+	case SFH_NOT_DETECTED:
+		in->ev_info.user_present = 0xff; /* assume no sensors connected */
+		break;
+	case SFH_USER_PRESENT:
+		in->ev_info.user_present = 1;
+		break;
+	case SFH_USER_AWAY:
+		in->ev_info.user_present = 0;
+		break;
+	}
+
+	return 0;
+}
+
 void amd_pmf_populate_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in)
 {
 	/* TA side lid open is 1 and close is 0, hence the ! here */
@@ -155,4 +190,5 @@ void amd_pmf_populate_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_tab
 	amd_pmf_get_smu_info(dev, in);
 	amd_pmf_get_battery_info(dev, in);
 	amd_pmf_get_slider_info(dev, in);
+	amd_pmf_get_sensor_info(dev, in);
 }
diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c
index 502ce93d5cdd..dcbe8f85e122 100644
--- a/drivers/platform/x86/amd/pmf/tee-if.c
+++ b/drivers/platform/x86/amd/pmf/tee-if.c
@@ -252,15 +252,17 @@ static int amd_pmf_start_policy_engine(struct amd_pmf_dev *dev)
 	cookie = readl(dev->policy_buf + POLICY_COOKIE_OFFSET);
 	length = readl(dev->policy_buf + POLICY_COOKIE_LEN);
 
-	if (cookie != POLICY_SIGN_COOKIE || !length)
+	if (cookie != POLICY_SIGN_COOKIE || !length) {
+		dev_dbg(dev->dev, "cookie doesn't match\n");
 		return -EINVAL;
+	}
 
 	/* Update the actual length */
 	dev->policy_sz = length + 512;
 	res = amd_pmf_invoke_cmd_init(dev);
 	if (res == TA_PMF_TYPE_SUCCESS) {
 		/* Now its safe to announce that smart pc is enabled */
-		dev->smart_pc_enabled = PMF_SMART_PC_ENABLED;
+		dev->smart_pc_enabled = true;
 		/*
 		 * Start collecting the data from TA FW after a small delay
 		 * or else, we might end up getting stale values.
@@ -268,7 +270,7 @@ static int amd_pmf_start_policy_engine(struct amd_pmf_dev *dev)
 		schedule_delayed_work(&dev->pb_work, msecs_to_jiffies(pb_actions_ms * 3));
 	} else {
 		dev_err(dev->dev, "ta invoke cmd init failed err: %x\n", res);
-		dev->smart_pc_enabled = PMF_SMART_PC_DISABLED;
+		dev->smart_pc_enabled = false;
 		return res;
 	}
 
@@ -298,8 +300,10 @@ static ssize_t amd_pmf_get_pb_data(struct file *filp, const char __user *buf,
 	if (!new_policy_buf)
 		return -ENOMEM;
 
-	if (copy_from_user(new_policy_buf, buf, length))
+	if (copy_from_user(new_policy_buf, buf, length)) {
+		kfree(new_policy_buf);
 		return -EFAULT;
+	}
 
 	kfree(dev->policy_buf);
 	dev->policy_buf = new_policy_buf;
@@ -334,25 +338,6 @@ static void amd_pmf_remove_pb(struct amd_pmf_dev *dev) {}
 static void amd_pmf_hex_dump_pb(struct amd_pmf_dev *dev) {}
 #endif
 
-static int amd_pmf_get_bios_buffer(struct amd_pmf_dev *dev)
-{
-	dev->policy_buf = kzalloc(dev->policy_sz, GFP_KERNEL);
-	if (!dev->policy_buf)
-		return -ENOMEM;
-
-	dev->policy_base = devm_ioremap(dev->dev, dev->policy_addr, dev->policy_sz);
-	if (!dev->policy_base)
-		return -ENOMEM;
-
-	memcpy(dev->policy_buf, dev->policy_base, dev->policy_sz);
-
-	amd_pmf_hex_dump_pb(dev);
-	if (pb_side_load)
-		amd_pmf_open_pb(dev, dev->dbgfs_dir);
-
-	return amd_pmf_start_policy_engine(dev);
-}
-
 static int amd_pmf_amdtee_ta_match(struct tee_ioctl_version_data *ver, const void *data)
 {
 	return ver->impl_id == TEE_IMPL_ID_AMDTEE;
@@ -451,22 +436,59 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
 		return ret;
 
 	INIT_DELAYED_WORK(&dev->pb_work, amd_pmf_invoke_cmd);
-	amd_pmf_set_dram_addr(dev, true);
-	amd_pmf_get_bios_buffer(dev);
+
+	ret = amd_pmf_set_dram_addr(dev, true);
+	if (ret)
+		goto error;
+
+	dev->policy_base = devm_ioremap(dev->dev, dev->policy_addr, dev->policy_sz);
+	if (!dev->policy_base) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	dev->policy_buf = kzalloc(dev->policy_sz, GFP_KERNEL);
+	if (!dev->policy_buf) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	memcpy(dev->policy_buf, dev->policy_base, dev->policy_sz);
+
+	amd_pmf_hex_dump_pb(dev);
+
 	dev->prev_data = kzalloc(sizeof(*dev->prev_data), GFP_KERNEL);
-	if (!dev->prev_data)
-		return -ENOMEM;
+	if (!dev->prev_data) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	ret = amd_pmf_start_policy_engine(dev);
+	if (ret)
+		goto error;
+
+	if (pb_side_load)
+		amd_pmf_open_pb(dev, dev->dbgfs_dir);
+
+	return 0;
 
-	return dev->smart_pc_enabled;
+error:
+	amd_pmf_deinit_smart_pc(dev);
+
+	return ret;
 }
 
 void amd_pmf_deinit_smart_pc(struct amd_pmf_dev *dev)
 {
-	if (pb_side_load)
+	if (pb_side_load && dev->esbin)
 		amd_pmf_remove_pb(dev);
 
+	cancel_delayed_work_sync(&dev->pb_work);
 	kfree(dev->prev_data);
+	dev->prev_data = NULL;
 	kfree(dev->policy_buf);
-	cancel_delayed_work_sync(&dev->pb_work);
+	dev->policy_buf = NULL;
+	kfree(dev->buf);
+	dev->buf = NULL;
 	amd_pmf_tee_deinit(dev);
 }
diff --git a/drivers/platform/x86/intel/chtwc_int33fe.c b/drivers/platform/x86/intel/chtwc_int33fe.c
index 848baecc1bb0..93f75ba1dafd 100644
--- a/drivers/platform/x86/intel/chtwc_int33fe.c
+++ b/drivers/platform/x86/intel/chtwc_int33fe.c
@@ -136,7 +136,7 @@ static const struct software_node altmodes_node = {
 };
 
 static const struct property_entry dp_altmode_properties[] = {
-	PROPERTY_ENTRY_U32("svid", 0xff01),
+	PROPERTY_ENTRY_U16("svid", 0xff01),
 	PROPERTY_ENTRY_U32("vdo", 0x0c0086),
 	{ }
 };
diff --git a/drivers/platform/x86/intel/ifs/load.c b/drivers/platform/x86/intel/ifs/load.c
index a1ee1a74fc3c..2cf3b4a8813f 100644
--- a/drivers/platform/x86/intel/ifs/load.c
+++ b/drivers/platform/x86/intel/ifs/load.c
@@ -399,7 +399,8 @@ int ifs_load_firmware(struct device *dev)
 	if (fw->size != expected_size) {
 		dev_err(dev, "File size mismatch (expected %u, actual %zu). Corrupted IFS image.\n",
 			expected_size, fw->size);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto release;
 	}
 
 	ret = image_sanity_check(dev, (struct microcode_header_intel *)fw->data);
diff --git a/drivers/platform/x86/intel/int0002_vgpio.c b/drivers/platform/x86/intel/int0002_vgpio.c
index b6708bab7c53..527d8fbc7cc1 100644
--- a/drivers/platform/x86/intel/int0002_vgpio.c
+++ b/drivers/platform/x86/intel/int0002_vgpio.c
@@ -196,7 +196,7 @@ static int int0002_probe(struct platform_device *pdev)
 	 * IRQs into gpiolib.
 	 */
 	ret = devm_request_irq(dev, irq, int0002_irq,
-			       IRQF_SHARED, "INT0002", chip);
+			       IRQF_ONESHOT | IRQF_SHARED, "INT0002", chip);
 	if (ret) {
 		dev_err(dev, "Error requesting IRQ %d: %d\n", irq, ret);
 		return ret;
diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c
index 33ab207493e3..33bb58dc3f78 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c
@@ -23,23 +23,23 @@ static int (*uncore_read)(struct uncore_data *data, unsigned int *min, unsigned
 static int (*uncore_write)(struct uncore_data *data, unsigned int input, unsigned int min_max);
 static int (*uncore_read_freq)(struct uncore_data *data, unsigned int *freq);
 
-static ssize_t show_domain_id(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t show_domain_id(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 {
-	struct uncore_data *data = container_of(attr, struct uncore_data, domain_id_dev_attr);
+	struct uncore_data *data = container_of(attr, struct uncore_data, domain_id_kobj_attr);
 
 	return sprintf(buf, "%u\n", data->domain_id);
 }
 
-static ssize_t show_fabric_cluster_id(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t show_fabric_cluster_id(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 {
-	struct uncore_data *data = container_of(attr, struct uncore_data, fabric_cluster_id_dev_attr);
+	struct uncore_data *data = container_of(attr, struct uncore_data, fabric_cluster_id_kobj_attr);
 
 	return sprintf(buf, "%u\n", data->cluster_id);
 }
 
-static ssize_t show_package_id(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t show_package_id(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 {
-	struct uncore_data *data = container_of(attr, struct uncore_data, package_id_dev_attr);
+	struct uncore_data *data = container_of(attr, struct uncore_data, package_id_kobj_attr);
 
 	return sprintf(buf, "%u\n", data->package_id);
 }
@@ -97,30 +97,30 @@ static ssize_t show_perf_status_freq_khz(struct uncore_data *data, char *buf)
 }
 
 #define store_uncore_min_max(name, min_max)				\
-	static ssize_t store_##name(struct device *dev,		\
-				     struct device_attribute *attr,	\
+	static ssize_t store_##name(struct kobject *kobj,		\
+				     struct kobj_attribute *attr,	\
 				     const char *buf, size_t count)	\
 	{								\
-		struct uncore_data *data = container_of(attr, struct uncore_data, name##_dev_attr);\
+		struct uncore_data *data = container_of(attr, struct uncore_data, name##_kobj_attr);\
 									\
 		return store_min_max_freq_khz(data, buf, count,	\
 					      min_max);		\
 	}
 
 #define show_uncore_min_max(name, min_max)				\
-	static ssize_t show_##name(struct device *dev,		\
-				    struct device_attribute *attr, char *buf)\
+	static ssize_t show_##name(struct kobject *kobj,		\
+				    struct kobj_attribute *attr, char *buf)\
 	{                                                               \
-		struct uncore_data *data = container_of(attr, struct uncore_data, name##_dev_attr);\
+		struct uncore_data *data = container_of(attr, struct uncore_data, name##_kobj_attr);\
 									\
 		return show_min_max_freq_khz(data, buf, min_max);	\
 	}
 
 #define show_uncore_perf_status(name)					\
-	static ssize_t show_##name(struct device *dev,		\
-				   struct device_attribute *attr, char *buf)\
+	static ssize_t show_##name(struct kobject *kobj,		\
+				   struct kobj_attribute *attr, char *buf)\
 	{                                                               \
-		struct uncore_data *data = container_of(attr, struct uncore_data, name##_dev_attr);\
+		struct uncore_data *data = container_of(attr, struct uncore_data, name##_kobj_attr);\
 									\
 		return show_perf_status_freq_khz(data, buf); \
 	}
@@ -134,11 +134,11 @@ show_uncore_min_max(max_freq_khz, 1);
 show_uncore_perf_status(current_freq_khz);
 
 #define show_uncore_data(member_name)					\
-	static ssize_t show_##member_name(struct device *dev,	\
-					   struct device_attribute *attr, char *buf)\
+	static ssize_t show_##member_name(struct kobject *kobj,	\
+					   struct kobj_attribute *attr, char *buf)\
 	{                                                               \
 		struct uncore_data *data = container_of(attr, struct uncore_data,\
-							  member_name##_dev_attr);\
+							  member_name##_kobj_attr);\
 									\
 		return sysfs_emit(buf, "%u\n",				\
 				 data->member_name);			\
@@ -149,29 +149,29 @@ show_uncore_data(initial_max_freq_khz);
 
 #define init_attribute_rw(_name)					\
 	do {								\
-		sysfs_attr_init(&data->_name##_dev_attr.attr);	\
-		data->_name##_dev_attr.show = show_##_name;		\
-		data->_name##_dev_attr.store = store_##_name;		\
-		data->_name##_dev_attr.attr.name = #_name;		\
-		data->_name##_dev_attr.attr.mode = 0644;		\
+		sysfs_attr_init(&data->_name##_kobj_attr.attr);	\
+		data->_name##_kobj_attr.show = show_##_name;		\
+		data->_name##_kobj_attr.store = store_##_name;		\
+		data->_name##_kobj_attr.attr.name = #_name;		\
+		data->_name##_kobj_attr.attr.mode = 0644;		\
 	} while (0)
 
 #define init_attribute_ro(_name)					\
 	do {								\
-		sysfs_attr_init(&data->_name##_dev_attr.attr);	\
-		data->_name##_dev_attr.show = show_##_name;		\
-		data->_name##_dev_attr.store = NULL;			\
-		data->_name##_dev_attr.attr.name = #_name;		\
-		data->_name##_dev_attr.attr.mode = 0444;		\
+		sysfs_attr_init(&data->_name##_kobj_attr.attr);	\
+		data->_name##_kobj_attr.show = show_##_name;		\
+		data->_name##_kobj_attr.store = NULL;			\
+		data->_name##_kobj_attr.attr.name = #_name;		\
+		data->_name##_kobj_attr.attr.mode = 0444;		\
 	} while (0)
 
 #define init_attribute_root_ro(_name)					\
 	do {								\
-		sysfs_attr_init(&data->_name##_dev_attr.attr);	\
-		data->_name##_dev_attr.show = show_##_name;		\
-		data->_name##_dev_attr.store = NULL;			\
-		data->_name##_dev_attr.attr.name = #_name;		\
-		data->_name##_dev_attr.attr.mode = 0400;		\
+		sysfs_attr_init(&data->_name##_kobj_attr.attr);	\
+		data->_name##_kobj_attr.show = show_##_name;		\
+		data->_name##_kobj_attr.store = NULL;			\
+		data->_name##_kobj_attr.attr.name = #_name;		\
+		data->_name##_kobj_attr.attr.mode = 0400;		\
 	} while (0)
 
 static int create_attr_group(struct uncore_data *data, char *name)
@@ -186,21 +186,21 @@ static int create_attr_group(struct uncore_data *data, char *name)
 
 	if (data->domain_id != UNCORE_DOMAIN_ID_INVALID) {
 		init_attribute_root_ro(domain_id);
-		data->uncore_attrs[index++] = &data->domain_id_dev_attr.attr;
+		data->uncore_attrs[index++] = &data->domain_id_kobj_attr.attr;
 		init_attribute_root_ro(fabric_cluster_id);
-		data->uncore_attrs[index++] = &data->fabric_cluster_id_dev_attr.attr;
+		data->uncore_attrs[index++] = &data->fabric_cluster_id_kobj_attr.attr;
 		init_attribute_root_ro(package_id);
-		data->uncore_attrs[index++] = &data->package_id_dev_attr.attr;
+		data->uncore_attrs[index++] = &data->package_id_kobj_attr.attr;
 	}
 
-	data->uncore_attrs[index++] = &data->max_freq_khz_dev_attr.attr;
-	data->uncore_attrs[index++] = &data->min_freq_khz_dev_attr.attr;
-	data->uncore_attrs[index++] = &data->initial_min_freq_khz_dev_attr.attr;
-	data->uncore_attrs[index++] = &data->initial_max_freq_khz_dev_attr.attr;
+	data->uncore_attrs[index++] = &data->max_freq_khz_kobj_attr.attr;
+	data->uncore_attrs[index++] = &data->min_freq_khz_kobj_attr.attr;
+	data->uncore_attrs[index++] = &data->initial_min_freq_khz_kobj_attr.attr;
+	data->uncore_attrs[index++] = &data->initial_max_freq_khz_kobj_attr.attr;
 
 	ret = uncore_read_freq(data, &freq);
 	if (!ret)
-		data->uncore_attrs[index++] = &data->current_freq_khz_dev_attr.attr;
+		data->uncore_attrs[index++] = &data->current_freq_khz_kobj_attr.attr;
 
 	data->uncore_attrs[index] = NULL;
 
diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.h b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.h
index 7afb69977c7e..0e5bf507e555 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.h
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.h
@@ -26,14 +26,14 @@
  * @instance_id:	Unique instance id to append to directory name
  * @name:		Sysfs entry name for this instance
  * @uncore_attr_group:	Attribute group storage
- * @max_freq_khz_dev_attr: Storage for device attribute max_freq_khz
- * @mix_freq_khz_dev_attr: Storage for device attribute min_freq_khz
- * @initial_max_freq_khz_dev_attr: Storage for device attribute initial_max_freq_khz
- * @initial_min_freq_khz_dev_attr: Storage for device attribute initial_min_freq_khz
- * @current_freq_khz_dev_attr: Storage for device attribute current_freq_khz
- * @domain_id_dev_attr: Storage for device attribute domain_id
- * @fabric_cluster_id_dev_attr: Storage for device attribute fabric_cluster_id
- * @package_id_dev_attr: Storage for device attribute package_id
+ * @max_freq_khz_kobj_attr: Storage for kobject attribute max_freq_khz
+ * @mix_freq_khz_kobj_attr: Storage for kobject attribute min_freq_khz
+ * @initial_max_freq_khz_kobj_attr: Storage for kobject attribute initial_max_freq_khz
+ * @initial_min_freq_khz_kobj_attr: Storage for kobject attribute initial_min_freq_khz
+ * @current_freq_khz_kobj_attr: Storage for kobject attribute current_freq_khz
+ * @domain_id_kobj_attr: Storage for kobject attribute domain_id
+ * @fabric_cluster_id_kobj_attr: Storage for kobject attribute fabric_cluster_id
+ * @package_id_kobj_attr: Storage for kobject attribute package_id
  * @uncore_attrs:	Attribute storage for group creation
  *
  * This structure is used to encapsulate all data related to uncore sysfs
@@ -53,14 +53,14 @@ struct uncore_data {
 	char name[32];
 
 	struct attribute_group uncore_attr_group;
-	struct device_attribute max_freq_khz_dev_attr;
-	struct device_attribute min_freq_khz_dev_attr;
-	struct device_attribute initial_max_freq_khz_dev_attr;
-	struct device_attribute initial_min_freq_khz_dev_attr;
-	struct device_attribute current_freq_khz_dev_attr;
-	struct device_attribute domain_id_dev_attr;
-	struct device_attribute fabric_cluster_id_dev_attr;
-	struct device_attribute package_id_dev_attr;
+	struct kobj_attribute max_freq_khz_kobj_attr;
+	struct kobj_attribute min_freq_khz_kobj_attr;
+	struct kobj_attribute initial_max_freq_khz_kobj_attr;
+	struct kobj_attribute initial_min_freq_khz_kobj_attr;
+	struct kobj_attribute current_freq_khz_kobj_attr;
+	struct kobj_attribute domain_id_kobj_attr;
+	struct kobj_attribute fabric_cluster_id_kobj_attr;
+	struct kobj_attribute package_id_kobj_attr;
 	struct attribute *uncore_attrs[9];
 };
 
diff --git a/drivers/platform/x86/intel/vbtn.c b/drivers/platform/x86/intel/vbtn.c
index 210b0a81b7ec..084c355c86f5 100644
--- a/drivers/platform/x86/intel/vbtn.c
+++ b/drivers/platform/x86/intel/vbtn.c
@@ -200,9 +200,6 @@ static void notify_handler(acpi_handle handle, u32 event, void *context)
 	autorelease = val && (!ke_rel || ke_rel->type == KE_IGNORE);
 
 	sparse_keymap_report_event(input_dev, event, val, autorelease);
-
-	/* Some devices need this to report further events */
-	acpi_evaluate_object(handle, "VBDL", NULL, NULL);
 }
 
 /*
diff --git a/drivers/platform/x86/intel/wmi/sbl-fw-update.c b/drivers/platform/x86/intel/wmi/sbl-fw-update.c
index 9cf5ed0f8dc2..040153ad67c1 100644
--- a/drivers/platform/x86/intel/wmi/sbl-fw-update.c
+++ b/drivers/platform/x86/intel/wmi/sbl-fw-update.c
@@ -32,7 +32,7 @@ static int get_fwu_request(struct device *dev, u32 *out)
 		return -ENODEV;
 
 	if (obj->type != ACPI_TYPE_INTEGER) {
-		dev_warn(dev, "wmi_query_block returned invalid value\n");
+		dev_warn(dev, "wmidev_block_query returned invalid value\n");
 		kfree(obj);
 		return -EINVAL;
 	}
@@ -55,7 +55,7 @@ static int set_fwu_request(struct device *dev, u32 in)
 
 	status = wmidev_block_set(to_wmi_device(dev), 0, &input);
 	if (ACPI_FAILURE(status)) {
-		dev_err(dev, "wmi_set_block failed\n");
+		dev_err(dev, "wmidev_block_set failed\n");
 		return -ENODEV;
 	}
 
diff --git a/drivers/platform/x86/p2sb.c b/drivers/platform/x86/p2sb.c
index 1cf2471d54dd..3d66e1d4eb1f 100644
--- a/drivers/platform/x86/p2sb.c
+++ b/drivers/platform/x86/p2sb.c
@@ -20,12 +20,29 @@
 #define P2SBC_HIDE		BIT(8)
 
 #define P2SB_DEVFN_DEFAULT	PCI_DEVFN(31, 1)
+#define P2SB_DEVFN_GOLDMONT	PCI_DEVFN(13, 0)
+#define SPI_DEVFN_GOLDMONT	PCI_DEVFN(13, 2)
 
 static const struct x86_cpu_id p2sb_cpu_ids[] = {
-	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT,	PCI_DEVFN(13, 0)),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, P2SB_DEVFN_GOLDMONT),
 	{}
 };
 
+/*
+ * Cache BAR0 of P2SB device functions 0 to 7.
+ * TODO: The constant 8 is the number of functions that PCI specification
+ *       defines. Same definitions exist tree-wide. Unify this definition and
+ *       the other definitions then move to include/uapi/linux/pci.h.
+ */
+#define NR_P2SB_RES_CACHE 8
+
+struct p2sb_res_cache {
+	u32 bus_dev_id;
+	struct resource res;
+};
+
+static struct p2sb_res_cache p2sb_resources[NR_P2SB_RES_CACHE];
+
 static int p2sb_get_devfn(unsigned int *devfn)
 {
 	unsigned int fn = P2SB_DEVFN_DEFAULT;
@@ -39,10 +56,18 @@ static int p2sb_get_devfn(unsigned int *devfn)
 	return 0;
 }
 
+static bool p2sb_valid_resource(struct resource *res)
+{
+	if (res->flags)
+		return true;
+
+	return false;
+}
+
 /* Copy resource from the first BAR of the device in question */
-static int p2sb_read_bar0(struct pci_dev *pdev, struct resource *mem)
+static void p2sb_read_bar0(struct pci_dev *pdev, struct resource *mem)
 {
-	struct resource *bar0 = &pdev->resource[0];
+	struct resource *bar0 = pci_resource_n(pdev, 0);
 
 	/* Make sure we have no dangling pointers in the output */
 	memset(mem, 0, sizeof(*mem));
@@ -56,49 +81,57 @@ static int p2sb_read_bar0(struct pci_dev *pdev, struct resource *mem)
 	mem->end = bar0->end;
 	mem->flags = bar0->flags;
 	mem->desc = bar0->desc;
-
-	return 0;
 }
 
-static int p2sb_scan_and_read(struct pci_bus *bus, unsigned int devfn, struct resource *mem)
+static void p2sb_scan_and_cache_devfn(struct pci_bus *bus, unsigned int devfn)
 {
+	struct p2sb_res_cache *cache = &p2sb_resources[PCI_FUNC(devfn)];
 	struct pci_dev *pdev;
-	int ret;
 
 	pdev = pci_scan_single_device(bus, devfn);
 	if (!pdev)
-		return -ENODEV;
+		return;
 
-	ret = p2sb_read_bar0(pdev, mem);
+	p2sb_read_bar0(pdev, &cache->res);
+	cache->bus_dev_id = bus->dev.id;
 
 	pci_stop_and_remove_bus_device(pdev);
-	return ret;
 }
 
-/**
- * p2sb_bar - Get Primary to Sideband (P2SB) bridge device BAR
- * @bus: PCI bus to communicate with
- * @devfn: PCI slot and function to communicate with
- * @mem: memory resource to be filled in
- *
- * The BIOS prevents the P2SB device from being enumerated by the PCI
- * subsystem, so we need to unhide and hide it back to lookup the BAR.
- *
- * if @bus is NULL, the bus 0 in domain 0 will be used.
- * If @devfn is 0, it will be replaced by devfn of the P2SB device.
- *
- * Caller must provide a valid pointer to @mem.
- *
- * Locking is handled by pci_rescan_remove_lock mutex.
- *
- * Return:
- * 0 on success or appropriate errno value on error.
- */
-int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem)
+static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn)
+{
+	/* Scan the P2SB device and cache its BAR0 */
+	p2sb_scan_and_cache_devfn(bus, devfn);
+
+	/* On Goldmont p2sb_bar() also gets called for the SPI controller */
+	if (devfn == P2SB_DEVFN_GOLDMONT)
+		p2sb_scan_and_cache_devfn(bus, SPI_DEVFN_GOLDMONT);
+
+	if (!p2sb_valid_resource(&p2sb_resources[PCI_FUNC(devfn)].res))
+		return -ENOENT;
+
+	return 0;
+}
+
+static struct pci_bus *p2sb_get_bus(struct pci_bus *bus)
+{
+	static struct pci_bus *p2sb_bus;
+
+	bus = bus ?: p2sb_bus;
+	if (bus)
+		return bus;
+
+	/* Assume P2SB is on the bus 0 in domain 0 */
+	p2sb_bus = pci_find_bus(0, 0);
+	return p2sb_bus;
+}
+
+static int p2sb_cache_resources(void)
 {
-	struct pci_dev *pdev_p2sb;
 	unsigned int devfn_p2sb;
 	u32 value = P2SBC_HIDE;
+	struct pci_bus *bus;
+	u16 class;
 	int ret;
 
 	/* Get devfn for P2SB device itself */
@@ -106,8 +139,17 @@ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem)
 	if (ret)
 		return ret;
 
-	/* if @bus is NULL, use bus 0 in domain 0 */
-	bus = bus ?: pci_find_bus(0, 0);
+	bus = p2sb_get_bus(NULL);
+	if (!bus)
+		return -ENODEV;
+
+	/*
+	 * When a device with same devfn exists and its device class is not
+	 * PCI_CLASS_MEMORY_OTHER for P2SB, do not touch it.
+	 */
+	pci_bus_read_config_word(bus, devfn_p2sb, PCI_CLASS_DEVICE, &class);
+	if (!PCI_POSSIBLE_ERROR(class) && class != PCI_CLASS_MEMORY_OTHER)
+		return -ENODEV;
 
 	/*
 	 * Prevent concurrent PCI bus scan from seeing the P2SB device and
@@ -115,17 +157,16 @@ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem)
 	 */
 	pci_lock_rescan_remove();
 
-	/* Unhide the P2SB device, if needed */
+	/*
+	 * The BIOS prevents the P2SB device from being enumerated by the PCI
+	 * subsystem, so we need to unhide and hide it back to lookup the BAR.
+	 * Unhide the P2SB device here, if needed.
+	 */
 	pci_bus_read_config_dword(bus, devfn_p2sb, P2SBC, &value);
 	if (value & P2SBC_HIDE)
 		pci_bus_write_config_dword(bus, devfn_p2sb, P2SBC, 0);
 
-	pdev_p2sb = pci_scan_single_device(bus, devfn_p2sb);
-	if (devfn)
-		ret = p2sb_scan_and_read(bus, devfn, mem);
-	else
-		ret = p2sb_read_bar0(pdev_p2sb, mem);
-	pci_stop_and_remove_bus_device(pdev_p2sb);
+	ret = p2sb_scan_and_cache(bus, devfn_p2sb);
 
 	/* Hide the P2SB device, if it was hidden */
 	if (value & P2SBC_HIDE)
@@ -133,12 +174,62 @@ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem)
 
 	pci_unlock_rescan_remove();
 
-	if (ret)
-		return ret;
+	return ret;
+}
 
-	if (mem->flags == 0)
+/**
+ * p2sb_bar - Get Primary to Sideband (P2SB) bridge device BAR
+ * @bus: PCI bus to communicate with
+ * @devfn: PCI slot and function to communicate with
+ * @mem: memory resource to be filled in
+ *
+ * If @bus is NULL, the bus 0 in domain 0 will be used.
+ * If @devfn is 0, it will be replaced by devfn of the P2SB device.
+ *
+ * Caller must provide a valid pointer to @mem.
+ *
+ * Return:
+ * 0 on success or appropriate errno value on error.
+ */
+int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem)
+{
+	struct p2sb_res_cache *cache;
+	int ret;
+
+	bus = p2sb_get_bus(bus);
+	if (!bus)
+		return -ENODEV;
+
+	if (!devfn) {
+		ret = p2sb_get_devfn(&devfn);
+		if (ret)
+			return ret;
+	}
+
+	cache = &p2sb_resources[PCI_FUNC(devfn)];
+	if (cache->bus_dev_id != bus->dev.id)
 		return -ENODEV;
 
+	if (!p2sb_valid_resource(&cache->res))
+		return -ENOENT;
+
+	memcpy(mem, &cache->res, sizeof(*mem));
 	return 0;
 }
 EXPORT_SYMBOL_GPL(p2sb_bar);
+
+static int __init p2sb_fs_init(void)
+{
+	p2sb_cache_resources();
+	return 0;
+}
+
+/*
+ * pci_rescan_remove_lock to avoid access to unhidden P2SB devices can
+ * not be locked in sysfs pci bus rescan path because of deadlock. To
+ * avoid the deadlock, access to P2SB devices with the lock at an early
+ * step in kernel initialization and cache required resources. This
+ * should happen after subsys_initcall which initializes PCI subsystem
+ * and before device_initcall which requires P2SB resources.
+ */
+fs_initcall(p2sb_fs_init);
diff --git a/drivers/platform/x86/serdev_helpers.h b/drivers/platform/x86/serdev_helpers.h
new file mode 100644
index 000000000000..bcf3a0c356ea
--- /dev/null
+++ b/drivers/platform/x86/serdev_helpers.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * In some cases UART attached devices which require an in kernel driver,
+ * e.g. UART attached Bluetooth HCIs are described in the ACPI tables
+ * by an ACPI device with a broken or missing UartSerialBusV2() resource.
+ *
+ * This causes the kernel to create a /dev/ttyS# char-device for the UART
+ * instead of creating an in kernel serdev-controller + serdev-device pair
+ * for the in kernel driver.
+ *
+ * The quirk handling in acpi_quirk_skip_serdev_enumeration() makes the kernel
+ * create a serdev-controller device for these UARTs instead of a /dev/ttyS#.
+ *
+ * Instantiating the actual serdev-device to bind to is up to pdx86 code,
+ * this header provides a helper for getting the serdev-controller device.
+ */
+#include <linux/acpi.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/printk.h>
+#include <linux/sprintf.h>
+#include <linux/string.h>
+
+static inline struct device *
+get_serdev_controller(const char *serial_ctrl_hid,
+		      const char *serial_ctrl_uid,
+		      int serial_ctrl_port,
+		      const char *serdev_ctrl_name)
+{
+	struct device *ctrl_dev, *child;
+	struct acpi_device *ctrl_adev;
+	char name[32];
+	int i;
+
+	ctrl_adev = acpi_dev_get_first_match_dev(serial_ctrl_hid, serial_ctrl_uid, -1);
+	if (!ctrl_adev) {
+		pr_err("error could not get %s/%s serial-ctrl adev\n",
+		       serial_ctrl_hid, serial_ctrl_uid);
+		return ERR_PTR(-ENODEV);
+	}
+
+	/* get_first_physical_node() returns a weak ref */
+	ctrl_dev = get_device(acpi_get_first_physical_node(ctrl_adev));
+	if (!ctrl_dev) {
+		pr_err("error could not get %s/%s serial-ctrl physical node\n",
+		       serial_ctrl_hid, serial_ctrl_uid);
+		ctrl_dev = ERR_PTR(-ENODEV);
+		goto put_ctrl_adev;
+	}
+
+	/* Walk host -> uart-ctrl -> port -> serdev-ctrl */
+	for (i = 0; i < 3; i++) {
+		switch (i) {
+		case 0:
+			snprintf(name, sizeof(name), "%s:0", dev_name(ctrl_dev));
+			break;
+		case 1:
+			snprintf(name, sizeof(name), "%s.%d",
+				 dev_name(ctrl_dev), serial_ctrl_port);
+			break;
+		case 2:
+			strscpy(name, serdev_ctrl_name, sizeof(name));
+			break;
+		}
+
+		child = device_find_child_by_name(ctrl_dev, name);
+		put_device(ctrl_dev);
+		if (!child) {
+			pr_err("error could not find '%s' device\n", name);
+			ctrl_dev = ERR_PTR(-ENODEV);
+			goto put_ctrl_adev;
+		}
+
+		ctrl_dev = child;
+	}
+
+put_ctrl_adev:
+	acpi_dev_put(ctrl_adev);
+	return ctrl_dev;
+}
diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c
index 3a396b763c49..ce3e08815a8e 100644
--- a/drivers/platform/x86/think-lmi.c
+++ b/drivers/platform/x86/think-lmi.c
@@ -1009,7 +1009,16 @@ static ssize_t current_value_store(struct kobject *kobj,
 		 * Note - this sets the variable and then the password as separate
 		 * WMI calls. Function tlmi_save_bios_settings will error if the
 		 * password is incorrect.
+		 * Workstation's require the opcode to be set before changing the
+		 * attribute.
 		 */
+		if (tlmi_priv.pwd_admin->valid && tlmi_priv.pwd_admin->password[0]) {
+			ret = tlmi_opcode_setting("WmiOpcodePasswordAdmin",
+						  tlmi_priv.pwd_admin->password);
+			if (ret)
+				goto out;
+		}
+
 		set_str = kasprintf(GFP_KERNEL, "%s,%s;", setting->display_name,
 				    new_setting);
 		if (!set_str) {
@@ -1021,17 +1030,10 @@ static ssize_t current_value_store(struct kobject *kobj,
 		if (ret)
 			goto out;
 
-		if (tlmi_priv.save_mode == TLMI_SAVE_BULK) {
+		if (tlmi_priv.save_mode == TLMI_SAVE_BULK)
 			tlmi_priv.save_required = true;
-		} else {
-			if (tlmi_priv.pwd_admin->valid && tlmi_priv.pwd_admin->password[0]) {
-				ret = tlmi_opcode_setting("WmiOpcodePasswordAdmin",
-							  tlmi_priv.pwd_admin->password);
-				if (ret)
-					goto out;
-			}
+		else
 			ret = tlmi_save_bios_settings("");
-		}
 	} else { /* old non-opcode based authentication method (deprecated) */
 		if (tlmi_priv.pwd_admin->valid && tlmi_priv.pwd_admin->password[0]) {
 			auth_str = kasprintf(GFP_KERNEL, "%s,%s,%s;",
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index c4895e9bc714..5ecd9d33250d 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -10308,6 +10308,7 @@ static int convert_dytc_to_profile(int funcmode, int dytcmode,
 		return 0;
 	default:
 		/* Unknown function */
+		pr_debug("unknown function 0x%x\n", funcmode);
 		return -EOPNOTSUPP;
 	}
 	return 0;
@@ -10493,8 +10494,8 @@ static void dytc_profile_refresh(void)
 		return;
 
 	perfmode = (output >> DYTC_GET_MODE_BIT) & 0xF;
-	convert_dytc_to_profile(funcmode, perfmode, &profile);
-	if (profile != dytc_current_profile) {
+	err = convert_dytc_to_profile(funcmode, perfmode, &profile);
+	if (!err && profile != dytc_current_profile) {
 		dytc_current_profile = profile;
 		platform_profile_notify();
 	}
diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c
index 0c6733772698..975cf24ae359 100644
--- a/drivers/platform/x86/touchscreen_dmi.c
+++ b/drivers/platform/x86/touchscreen_dmi.c
@@ -81,7 +81,7 @@ static const struct property_entry chuwi_hi8_air_props[] = {
 };
 
 static const struct ts_dmi_data chuwi_hi8_air_data = {
-	.acpi_name	= "MSSL1680:00",
+	.acpi_name	= "MSSL1680",
 	.properties	= chuwi_hi8_air_props,
 };
 
@@ -415,18 +415,13 @@ static const struct property_entry gdix1001_upside_down_props[] = {
 	{ }
 };
 
-static const struct ts_dmi_data gdix1001_00_upside_down_data = {
-	.acpi_name	= "GDIX1001:00",
-	.properties	= gdix1001_upside_down_props,
-};
-
-static const struct ts_dmi_data gdix1001_01_upside_down_data = {
-	.acpi_name	= "GDIX1001:01",
+static const struct ts_dmi_data gdix1001_upside_down_data = {
+	.acpi_name	= "GDIX1001",
 	.properties	= gdix1001_upside_down_props,
 };
 
-static const struct ts_dmi_data gdix1002_00_upside_down_data = {
-	.acpi_name	= "GDIX1002:00",
+static const struct ts_dmi_data gdix1002_upside_down_data = {
+	.acpi_name	= "GDIX1002",
 	.properties	= gdix1001_upside_down_props,
 };
 
@@ -944,6 +939,32 @@ static const struct ts_dmi_data teclast_tbook11_data = {
 	.properties	= teclast_tbook11_props,
 };
 
+static const struct property_entry teclast_x16_plus_props[] = {
+	PROPERTY_ENTRY_U32("touchscreen-min-x", 8),
+	PROPERTY_ENTRY_U32("touchscreen-min-y", 14),
+	PROPERTY_ENTRY_U32("touchscreen-size-x", 1916),
+	PROPERTY_ENTRY_U32("touchscreen-size-y", 1264),
+	PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"),
+	PROPERTY_ENTRY_STRING("firmware-name", "gsl3692-teclast-x16-plus.fw"),
+	PROPERTY_ENTRY_U32("silead,max-fingers", 10),
+	PROPERTY_ENTRY_BOOL("silead,home-button"),
+	{ }
+};
+
+static const struct ts_dmi_data teclast_x16_plus_data = {
+	.embedded_fw = {
+		.name	= "silead/gsl3692-teclast-x16-plus.fw",
+		.prefix = { 0xf0, 0x00, 0x00, 0x00, 0x02, 0x00, 0x00, 0x00 },
+		.length	= 43560,
+		.sha256	= { 0x9d, 0xb0, 0x3d, 0xf1, 0x00, 0x3c, 0xb5, 0x25,
+			    0x62, 0x8a, 0xa0, 0x93, 0x4b, 0xe0, 0x4e, 0x75,
+			    0xd1, 0x27, 0xb1, 0x65, 0x3c, 0xba, 0xa5, 0x0f,
+			    0xcd, 0xb4, 0xbe, 0x00, 0xbb, 0xf6, 0x43, 0x29 },
+	},
+	.acpi_name	= "MSSL1680:00",
+	.properties	= teclast_x16_plus_props,
+};
+
 static const struct property_entry teclast_x3_plus_props[] = {
 	PROPERTY_ENTRY_U32("touchscreen-size-x", 1980),
 	PROPERTY_ENTRY_U32("touchscreen-size-y", 1500),
@@ -1386,7 +1407,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 	},
 	{
 		/* Juno Tablet */
-		.driver_data = (void *)&gdix1002_00_upside_down_data,
+		.driver_data = (void *)&gdix1002_upside_down_data,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Default string"),
 			/* Both product- and board-name being "Default string" is somewhat rare */
@@ -1613,6 +1634,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 		},
 	},
 	{
+		/* Teclast X16 Plus */
+		.driver_data = (void *)&teclast_x16_plus_data,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "TECLAST"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Default string"),
+			DMI_MATCH(DMI_PRODUCT_SKU, "D3A5_A1"),
+		},
+	},
+	{
 		/* Teclast X3 Plus */
 		.driver_data = (void *)&teclast_x3_plus_data,
 		.matches = {
@@ -1623,7 +1653,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 	},
 	{
 		/* Teclast X89 (Android version / BIOS) */
-		.driver_data = (void *)&gdix1001_00_upside_down_data,
+		.driver_data = (void *)&gdix1001_upside_down_data,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "WISKY"),
 			DMI_MATCH(DMI_BOARD_NAME, "3G062i"),
@@ -1631,7 +1661,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 	},
 	{
 		/* Teclast X89 (Windows version / BIOS) */
-		.driver_data = (void *)&gdix1001_01_upside_down_data,
+		.driver_data = (void *)&gdix1001_upside_down_data,
 		.matches = {
 			/* tPAD is too generic, also match on bios date */
 			DMI_MATCH(DMI_BOARD_VENDOR, "TECLAST"),
@@ -1649,7 +1679,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 	},
 	{
 		/* Teclast X98 Pro */
-		.driver_data = (void *)&gdix1001_00_upside_down_data,
+		.driver_data = (void *)&gdix1001_upside_down_data,
 		.matches = {
 			/*
 			 * Only match BIOS date, because the manufacturers
@@ -1753,7 +1783,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 	},
 	{
 		/* "WinBook TW100" */
-		.driver_data = (void *)&gdix1001_00_upside_down_data,
+		.driver_data = (void *)&gdix1001_upside_down_data,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "WinBook"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "TW100")
@@ -1761,7 +1791,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 	},
 	{
 		/* WinBook TW700 */
-		.driver_data = (void *)&gdix1001_00_upside_down_data,
+		.driver_data = (void *)&gdix1001_upside_down_data,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "WinBook"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "TW700")
@@ -1786,7 +1816,7 @@ static void ts_dmi_add_props(struct i2c_client *client)
 	int error;
 
 	if (has_acpi_companion(dev) &&
-	    !strncmp(ts_data->acpi_name, client->name, I2C_NAME_SIZE)) {
+	    strstarts(client->name, ts_data->acpi_name)) {
 		error = device_create_managed_software_node(dev, ts_data->properties, NULL);
 		if (error)
 			dev_err(dev, "failed to add properties: %d\n", error);
diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c
index bd271a5730aa..3c288e8f404b 100644
--- a/drivers/platform/x86/wmi.c
+++ b/drivers/platform/x86/wmi.c
@@ -25,6 +25,7 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/rwsem.h>
 #include <linux/slab.h>
 #include <linux/sysfs.h>
 #include <linux/types.h>
@@ -56,7 +57,6 @@ static_assert(__alignof__(struct guid_block) == 1);
 
 enum {	/* wmi_block flags */
 	WMI_READ_TAKES_NO_ARGS,
-	WMI_PROBED,
 };
 
 struct wmi_block {
@@ -64,8 +64,10 @@ struct wmi_block {
 	struct list_head list;
 	struct guid_block gblock;
 	struct acpi_device *acpi_device;
+	struct rw_semaphore notify_lock;	/* Protects notify callback add/remove */
 	wmi_notify_handler handler;
 	void *handler_data;
+	bool driver_ready;
 	unsigned long flags;
 };
 
@@ -219,6 +221,17 @@ static int wmidev_match_guid(struct device *dev, const void *data)
 	return 0;
 }
 
+static int wmidev_match_notify_id(struct device *dev, const void *data)
+{
+	struct wmi_block *wblock = dev_to_wblock(dev);
+	const u32 *notify_id = data;
+
+	if (wblock->gblock.flags & ACPI_WMI_EVENT && wblock->gblock.notify_id == *notify_id)
+		return 1;
+
+	return 0;
+}
+
 static struct bus_type wmi_bus_type;
 
 static struct wmi_device *wmi_find_device_by_guid(const char *guid_string)
@@ -238,6 +251,17 @@ static struct wmi_device *wmi_find_device_by_guid(const char *guid_string)
 	return dev_to_wdev(dev);
 }
 
+static struct wmi_device *wmi_find_event_by_notify_id(const u32 notify_id)
+{
+	struct device *dev;
+
+	dev = bus_find_device(&wmi_bus_type, NULL, &notify_id, wmidev_match_notify_id);
+	if (!dev)
+		return ERR_PTR(-ENODEV);
+
+	return to_wmi_device(dev);
+}
+
 static void wmi_device_put(struct wmi_device *wdev)
 {
 	put_device(&wdev->dev);
@@ -572,32 +596,31 @@ acpi_status wmi_install_notify_handler(const char *guid,
 				       wmi_notify_handler handler,
 				       void *data)
 {
-	struct wmi_block *block;
-	acpi_status status = AE_NOT_EXIST;
-	guid_t guid_input;
-
-	if (!guid || !handler)
-		return AE_BAD_PARAMETER;
+	struct wmi_block *wblock;
+	struct wmi_device *wdev;
+	acpi_status status;
 
-	if (guid_parse(guid, &guid_input))
-		return AE_BAD_PARAMETER;
+	wdev = wmi_find_device_by_guid(guid);
+	if (IS_ERR(wdev))
+		return AE_ERROR;
 
-	list_for_each_entry(block, &wmi_block_list, list) {
-		acpi_status wmi_status;
+	wblock = container_of(wdev, struct wmi_block, dev);
 
-		if (guid_equal(&block->gblock.guid, &guid_input)) {
-			if (block->handler)
-				return AE_ALREADY_ACQUIRED;
+	down_write(&wblock->notify_lock);
+	if (wblock->handler) {
+		status = AE_ALREADY_ACQUIRED;
+	} else {
+		wblock->handler = handler;
+		wblock->handler_data = data;
 
-			block->handler = handler;
-			block->handler_data = data;
+		if (ACPI_FAILURE(wmi_method_enable(wblock, true)))
+			dev_warn(&wblock->dev.dev, "Failed to enable device\n");
 
-			wmi_status = wmi_method_enable(block, true);
-			if ((wmi_status != AE_OK) ||
-			    ((wmi_status == AE_OK) && (status == AE_NOT_EXIST)))
-				status = wmi_status;
-		}
+		status = AE_OK;
 	}
+	up_write(&wblock->notify_lock);
+
+	wmi_device_put(wdev);
 
 	return status;
 }
@@ -613,30 +636,31 @@ EXPORT_SYMBOL_GPL(wmi_install_notify_handler);
  */
 acpi_status wmi_remove_notify_handler(const char *guid)
 {
-	struct wmi_block *block;
-	acpi_status status = AE_NOT_EXIST;
-	guid_t guid_input;
+	struct wmi_block *wblock;
+	struct wmi_device *wdev;
+	acpi_status status;
 
-	if (!guid)
-		return AE_BAD_PARAMETER;
+	wdev = wmi_find_device_by_guid(guid);
+	if (IS_ERR(wdev))
+		return AE_ERROR;
 
-	if (guid_parse(guid, &guid_input))
-		return AE_BAD_PARAMETER;
+	wblock = container_of(wdev, struct wmi_block, dev);
 
-	list_for_each_entry(block, &wmi_block_list, list) {
-		acpi_status wmi_status;
+	down_write(&wblock->notify_lock);
+	if (!wblock->handler) {
+		status = AE_NULL_ENTRY;
+	} else {
+		if (ACPI_FAILURE(wmi_method_enable(wblock, false)))
+			dev_warn(&wblock->dev.dev, "Failed to disable device\n");
 
-		if (guid_equal(&block->gblock.guid, &guid_input)) {
-			if (!block->handler)
-				return AE_NULL_ENTRY;
+		wblock->handler = NULL;
+		wblock->handler_data = NULL;
 
-			wmi_status = wmi_method_enable(block, false);
-			block->handler = NULL;
-			block->handler_data = NULL;
-			if (wmi_status != AE_OK || (wmi_status == AE_OK && status == AE_NOT_EXIST))
-				status = wmi_status;
-		}
+		status = AE_OK;
 	}
+	up_write(&wblock->notify_lock);
+
+	wmi_device_put(wdev);
 
 	return status;
 }
@@ -655,15 +679,19 @@ EXPORT_SYMBOL_GPL(wmi_remove_notify_handler);
 acpi_status wmi_get_event_data(u32 event, struct acpi_buffer *out)
 {
 	struct wmi_block *wblock;
+	struct wmi_device *wdev;
+	acpi_status status;
 
-	list_for_each_entry(wblock, &wmi_block_list, list) {
-		struct guid_block *gblock = &wblock->gblock;
+	wdev = wmi_find_event_by_notify_id(event);
+	if (IS_ERR(wdev))
+		return AE_NOT_FOUND;
 
-		if ((gblock->flags & ACPI_WMI_EVENT) && gblock->notify_id == event)
-			return get_event_data(wblock, out);
-	}
+	wblock = container_of(wdev, struct wmi_block, dev);
+	status = get_event_data(wblock, out);
 
-	return AE_NOT_FOUND;
+	wmi_device_put(wdev);
+
+	return status;
 }
 EXPORT_SYMBOL_GPL(wmi_get_event_data);
 
@@ -868,7 +896,7 @@ static int wmi_dev_probe(struct device *dev)
 	if (wdriver->probe) {
 		ret = wdriver->probe(dev_to_wdev(dev),
 				find_guid_context(wblock, wdriver));
-		if (!ret) {
+		if (ret) {
 			if (ACPI_FAILURE(wmi_method_enable(wblock, false)))
 				dev_warn(dev, "Failed to disable device\n");
 
@@ -876,7 +904,9 @@ static int wmi_dev_probe(struct device *dev)
 		}
 	}
 
-	set_bit(WMI_PROBED, &wblock->flags);
+	down_write(&wblock->notify_lock);
+	wblock->driver_ready = true;
+	up_write(&wblock->notify_lock);
 
 	return 0;
 }
@@ -886,7 +916,9 @@ static void wmi_dev_remove(struct device *dev)
 	struct wmi_block *wblock = dev_to_wblock(dev);
 	struct wmi_driver *wdriver = drv_to_wdrv(dev->driver);
 
-	clear_bit(WMI_PROBED, &wblock->flags);
+	down_write(&wblock->notify_lock);
+	wblock->driver_ready = false;
+	up_write(&wblock->notify_lock);
 
 	if (wdriver->remove)
 		wdriver->remove(dev_to_wdev(dev));
@@ -999,6 +1031,8 @@ static int wmi_create_device(struct device *wmi_bus_dev,
 		wblock->dev.setable = true;
 
  out_init:
+	init_rwsem(&wblock->notify_lock);
+	wblock->driver_ready = false;
 	wblock->dev.dev.bus = &wmi_bus_type;
 	wblock->dev.dev.parent = wmi_bus_dev;
 
@@ -1171,6 +1205,26 @@ acpi_wmi_ec_space_handler(u32 function, acpi_physical_address address,
 	}
 }
 
+static void wmi_notify_driver(struct wmi_block *wblock)
+{
+	struct wmi_driver *driver = drv_to_wdrv(wblock->dev.dev.driver);
+	struct acpi_buffer data = { ACPI_ALLOCATE_BUFFER, NULL };
+	acpi_status status;
+
+	if (!driver->no_notify_data) {
+		status = get_event_data(wblock, &data);
+		if (ACPI_FAILURE(status)) {
+			dev_warn(&wblock->dev.dev, "Failed to get event data\n");
+			return;
+		}
+	}
+
+	if (driver->notify)
+		driver->notify(&wblock->dev, data.pointer);
+
+	kfree(data.pointer);
+}
+
 static int wmi_notify_device(struct device *dev, void *data)
 {
 	struct wmi_block *wblock = dev_to_wblock(dev);
@@ -1179,28 +1233,17 @@ static int wmi_notify_device(struct device *dev, void *data)
 	if (!(wblock->gblock.flags & ACPI_WMI_EVENT && wblock->gblock.notify_id == *event))
 		return 0;
 
-	/* If a driver is bound, then notify the driver. */
-	if (test_bit(WMI_PROBED, &wblock->flags) && wblock->dev.dev.driver) {
-		struct wmi_driver *driver = drv_to_wdrv(wblock->dev.dev.driver);
-		struct acpi_buffer evdata = { ACPI_ALLOCATE_BUFFER, NULL };
-		acpi_status status;
-
-		if (!driver->no_notify_data) {
-			status = get_event_data(wblock, &evdata);
-			if (ACPI_FAILURE(status)) {
-				dev_warn(&wblock->dev.dev, "failed to get event data\n");
-				return -EIO;
-			}
-		}
-
-		if (driver->notify)
-			driver->notify(&wblock->dev, evdata.pointer);
-
-		kfree(evdata.pointer);
-	} else if (wblock->handler) {
-		/* Legacy handler */
-		wblock->handler(*event, wblock->handler_data);
+	down_read(&wblock->notify_lock);
+	/* The WMI driver notify handler conflicts with the legacy WMI handler.
+	 * Because of this the WMI driver notify handler takes precedence.
+	 */
+	if (wblock->dev.dev.driver && wblock->driver_ready) {
+		wmi_notify_driver(wblock);
+	} else {
+		if (wblock->handler)
+			wblock->handler(*event, wblock->handler_data);
 	}
+	up_read(&wblock->notify_lock);
 
 	acpi_bus_generate_netlink_event(wblock->acpi_device->pnp.device_class,
 					dev_name(&wblock->dev.dev), *event, 0);
diff --git a/drivers/platform/x86/x86-android-tablets/core.c b/drivers/platform/x86/x86-android-tablets/core.c
index f8221a15575b..a3415f1c0b5f 100644
--- a/drivers/platform/x86/x86-android-tablets/core.c
+++ b/drivers/platform/x86/x86-android-tablets/core.c
@@ -21,6 +21,7 @@
 #include <linux/string.h>
 
 #include "x86-android-tablets.h"
+#include "../serdev_helpers.h"
 
 static struct platform_device *x86_android_tablet_device;
 
@@ -113,6 +114,9 @@ int x86_acpi_irq_helper_get(const struct x86_acpi_irq_data *data)
 		if (irq_type != IRQ_TYPE_NONE && irq_type != irq_get_trigger_type(irq))
 			irq_set_irq_type(irq, irq_type);
 
+		if (data->free_gpio)
+			devm_gpiod_put(&x86_android_tablet_device->dev, gpiod);
+
 		return irq;
 	case X86_ACPI_IRQ_TYPE_PMIC:
 		status = acpi_get_handle(NULL, data->chip, &handle);
@@ -229,38 +233,20 @@ static __init int x86_instantiate_spi_dev(const struct x86_dev_info *dev_info, i
 
 static __init int x86_instantiate_serdev(const struct x86_serdev_info *info, int idx)
 {
-	struct acpi_device *ctrl_adev, *serdev_adev;
+	struct acpi_device *serdev_adev;
 	struct serdev_device *serdev;
 	struct device *ctrl_dev;
 	int ret = -ENODEV;
 
-	ctrl_adev = acpi_dev_get_first_match_dev(info->ctrl_hid, info->ctrl_uid, -1);
-	if (!ctrl_adev) {
-		pr_err("error could not get %s/%s ctrl adev\n",
-		       info->ctrl_hid, info->ctrl_uid);
-		return -ENODEV;
-	}
+	ctrl_dev = get_serdev_controller(info->ctrl_hid, info->ctrl_uid, 0,
+					 info->ctrl_devname);
+	if (IS_ERR(ctrl_dev))
+		return PTR_ERR(ctrl_dev);
 
 	serdev_adev = acpi_dev_get_first_match_dev(info->serdev_hid, NULL, -1);
 	if (!serdev_adev) {
 		pr_err("error could not get %s serdev adev\n", info->serdev_hid);
-		goto put_ctrl_adev;
-	}
-
-	/* get_first_physical_node() returns a weak ref, no need to put() it */
-	ctrl_dev = acpi_get_first_physical_node(ctrl_adev);
-	if (!ctrl_dev)	{
-		pr_err("error could not get %s/%s ctrl physical dev\n",
-		       info->ctrl_hid, info->ctrl_uid);
-		goto put_serdev_adev;
-	}
-
-	/* ctrl_dev now points to the controller's parent, get the controller */
-	ctrl_dev = device_find_child_by_name(ctrl_dev, info->ctrl_devname);
-	if (!ctrl_dev) {
-		pr_err("error could not get %s/%s %s ctrl dev\n",
-		       info->ctrl_hid, info->ctrl_uid, info->ctrl_devname);
-		goto put_serdev_adev;
+		goto put_ctrl_dev;
 	}
 
 	serdev = serdev_device_alloc(to_serdev_controller(ctrl_dev));
@@ -283,8 +269,8 @@ static __init int x86_instantiate_serdev(const struct x86_serdev_info *info, int
 
 put_serdev_adev:
 	acpi_dev_put(serdev_adev);
-put_ctrl_adev:
-	acpi_dev_put(ctrl_adev);
+put_ctrl_dev:
+	put_device(ctrl_dev);
 	return ret;
 }
 
diff --git a/drivers/platform/x86/x86-android-tablets/lenovo.c b/drivers/platform/x86/x86-android-tablets/lenovo.c
index f1c66a61bfc5..c297391955ad 100644
--- a/drivers/platform/x86/x86-android-tablets/lenovo.c
+++ b/drivers/platform/x86/x86-android-tablets/lenovo.c
@@ -116,6 +116,7 @@ static const struct x86_i2c_client_info lenovo_yb1_x90_i2c_clients[] __initconst
 			.trigger = ACPI_EDGE_SENSITIVE,
 			.polarity = ACPI_ACTIVE_LOW,
 			.con_id = "goodix_ts_irq",
+			.free_gpio = true,
 		},
 	}, {
 		/* Wacom Digitizer in keyboard half */
diff --git a/drivers/platform/x86/x86-android-tablets/other.c b/drivers/platform/x86/x86-android-tablets/other.c
index bc6bbf7ec6ea..278402dcb808 100644
--- a/drivers/platform/x86/x86-android-tablets/other.c
+++ b/drivers/platform/x86/x86-android-tablets/other.c
@@ -68,7 +68,7 @@ static const struct x86_i2c_client_info acer_b1_750_i2c_clients[] __initconst =
 	},
 };
 
-static struct gpiod_lookup_table acer_b1_750_goodix_gpios = {
+static struct gpiod_lookup_table acer_b1_750_nvt_ts_gpios = {
 	.dev_id = "i2c-NVT-ts",
 	.table = {
 		GPIO_LOOKUP("INT33FC:01", 26, "reset", GPIO_ACTIVE_LOW),
@@ -77,7 +77,7 @@ static struct gpiod_lookup_table acer_b1_750_goodix_gpios = {
 };
 
 static struct gpiod_lookup_table * const acer_b1_750_gpios[] = {
-	&acer_b1_750_goodix_gpios,
+	&acer_b1_750_nvt_ts_gpios,
 	&int3496_reference_gpios,
 	NULL
 };
diff --git a/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h b/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h
index 49fed9410adb..468993edfeee 100644
--- a/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h
+++ b/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h
@@ -39,6 +39,7 @@ struct x86_acpi_irq_data {
 	int index;
 	int trigger;  /* ACPI_EDGE_SENSITIVE / ACPI_LEVEL_SENSITIVE */
 	int polarity; /* ACPI_ACTIVE_HIGH / ACPI_ACTIVE_LOW / ACPI_ACTIVE_BOTH */
+	bool free_gpio; /* Release GPIO after getting IRQ (for TYPE_GPIOINT) */
 	const char *con_id;
 };
 
diff --git a/drivers/pmdomain/arm/scmi_perf_domain.c b/drivers/pmdomain/arm/scmi_perf_domain.c
index 709bbc448fad..d7ef46ccd9b8 100644
--- a/drivers/pmdomain/arm/scmi_perf_domain.c
+++ b/drivers/pmdomain/arm/scmi_perf_domain.c
@@ -159,6 +159,9 @@ static void scmi_perf_domain_remove(struct scmi_device *sdev)
 	struct genpd_onecell_data *scmi_pd_data = dev_get_drvdata(dev);
 	int i;
 
+	if (!scmi_pd_data)
+		return;
+
 	of_genpd_del_provider(dev->of_node);
 
 	for (i = 0; i < scmi_pd_data->num_domains; i++)
diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c
index 9ee1bf2ece10..18e232b5ed53 100644
--- a/drivers/pmdomain/core.c
+++ b/drivers/pmdomain/core.c
@@ -1109,7 +1109,7 @@ static int __init genpd_power_off_unused(void)
 
 	return 0;
 }
-late_initcall(genpd_power_off_unused);
+late_initcall_sync(genpd_power_off_unused);
 
 #ifdef CONFIG_PM_SLEEP
 
@@ -2668,7 +2668,7 @@ static void genpd_release_dev(struct device *dev)
 	kfree(dev);
 }
 
-static struct bus_type genpd_bus_type = {
+static const struct bus_type genpd_bus_type = {
 	.name		= "genpd",
 };
 
diff --git a/drivers/pmdomain/mediatek/mtk-pm-domains.c b/drivers/pmdomain/mediatek/mtk-pm-domains.c
index e26dc17d07ad..e274e3315fe7 100644
--- a/drivers/pmdomain/mediatek/mtk-pm-domains.c
+++ b/drivers/pmdomain/mediatek/mtk-pm-domains.c
@@ -561,6 +561,11 @@ static int scpsys_add_subdomain(struct scpsys *scpsys, struct device_node *paren
 			goto err_put_node;
 		}
 
+		/* recursive call to add all subdomains */
+		ret = scpsys_add_subdomain(scpsys, child);
+		if (ret)
+			goto err_put_node;
+
 		ret = pm_genpd_add_subdomain(parent_pd, child_pd);
 		if (ret) {
 			dev_err(scpsys->dev, "failed to add %s subdomain to parent %s\n",
@@ -570,11 +575,6 @@ static int scpsys_add_subdomain(struct scpsys *scpsys, struct device_node *paren
 			dev_dbg(scpsys->dev, "%s add subdomain: %s\n", parent_pd->name,
 				child_pd->name);
 		}
-
-		/* recursive call to add all subdomains */
-		ret = scpsys_add_subdomain(scpsys, child);
-		if (ret)
-			goto err_put_node;
 	}
 
 	return 0;
@@ -588,9 +588,6 @@ static void scpsys_remove_one_domain(struct scpsys_domain *pd)
 {
 	int ret;
 
-	if (scpsys_domain_is_on(pd))
-		scpsys_power_off(&pd->genpd);
-
 	/*
 	 * We're in the error cleanup already, so we only complain,
 	 * but won't emit another error on top of the original one.
@@ -600,6 +597,8 @@ static void scpsys_remove_one_domain(struct scpsys_domain *pd)
 		dev_err(pd->scpsys->dev,
 			"failed to remove domain '%s' : %d - state may be inconsistent\n",
 			pd->genpd.name, ret);
+	if (scpsys_domain_is_on(pd))
+		scpsys_power_off(&pd->genpd);
 
 	clk_bulk_put(pd->num_clks, pd->clks);
 	clk_bulk_put(pd->num_subsys_clks, pd->subsys_clks);
diff --git a/drivers/pmdomain/qcom/rpmhpd.c b/drivers/pmdomain/qcom/rpmhpd.c
index 3078896b1300..47df910645f6 100644
--- a/drivers/pmdomain/qcom/rpmhpd.c
+++ b/drivers/pmdomain/qcom/rpmhpd.c
@@ -692,6 +692,7 @@ static int rpmhpd_aggregate_corner(struct rpmhpd *pd, unsigned int corner)
 	unsigned int active_corner, sleep_corner;
 	unsigned int this_active_corner = 0, this_sleep_corner = 0;
 	unsigned int peer_active_corner = 0, peer_sleep_corner = 0;
+	unsigned int peer_enabled_corner;
 
 	if (pd->state_synced) {
 		to_active_sleep(pd, corner, &this_active_corner, &this_sleep_corner);
@@ -701,9 +702,11 @@ static int rpmhpd_aggregate_corner(struct rpmhpd *pd, unsigned int corner)
 		this_sleep_corner = pd->level_count - 1;
 	}
 
-	if (peer && peer->enabled)
-		to_active_sleep(peer, peer->corner, &peer_active_corner,
+	if (peer && peer->enabled) {
+		peer_enabled_corner = max(peer->corner, peer->enable_corner);
+		to_active_sleep(peer, peer_enabled_corner, &peer_active_corner,
 				&peer_sleep_corner);
+	}
 
 	active_corner = max(this_active_corner, peer_active_corner);
 
diff --git a/drivers/pmdomain/renesas/r8a77980-sysc.c b/drivers/pmdomain/renesas/r8a77980-sysc.c
index 39ca84a67daa..621e411fc999 100644
--- a/drivers/pmdomain/renesas/r8a77980-sysc.c
+++ b/drivers/pmdomain/renesas/r8a77980-sysc.c
@@ -25,7 +25,8 @@ static const struct rcar_sysc_area r8a77980_areas[] __initconst = {
 	  PD_CPU_NOCR },
 	{ "ca53-cpu3",	0x200, 3, R8A77980_PD_CA53_CPU3, R8A77980_PD_CA53_SCU,
 	  PD_CPU_NOCR },
-	{ "cr7",	0x240, 0, R8A77980_PD_CR7,	R8A77980_PD_ALWAYS_ON },
+	{ "cr7",	0x240, 0, R8A77980_PD_CR7,	R8A77980_PD_ALWAYS_ON,
+	  PD_CPU_NOCR },
 	{ "a3ir",	0x180, 0, R8A77980_PD_A3IR,	R8A77980_PD_ALWAYS_ON },
 	{ "a2ir0",	0x400, 0, R8A77980_PD_A2IR0,	R8A77980_PD_A3IR },
 	{ "a2ir1",	0x400, 1, R8A77980_PD_A2IR1,	R8A77980_PD_A3IR },
diff --git a/drivers/pnp/driver.c b/drivers/pnp/driver.c
index 46c534f6b1c9..0a5d0d8befa8 100644
--- a/drivers/pnp/driver.c
+++ b/drivers/pnp/driver.c
@@ -256,7 +256,7 @@ static const struct dev_pm_ops pnp_bus_dev_pm_ops = {
 	.restore = pnp_bus_resume,
 };
 
-struct bus_type pnp_bus_type = {
+const struct bus_type pnp_bus_type = {
 	.name    = "pnp",
 	.match   = pnp_bus_match,
 	.probe   = pnp_device_probe,
diff --git a/drivers/power/reset/as3722-poweroff.c b/drivers/power/reset/as3722-poweroff.c
index 829e0dba2fda..ab3350ce2d62 100644
--- a/drivers/power/reset/as3722-poweroff.c
+++ b/drivers/power/reset/as3722-poweroff.c
@@ -61,13 +61,11 @@ static int as3722_poweroff_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int as3722_poweroff_remove(struct platform_device *pdev)
+static void as3722_poweroff_remove(struct platform_device *pdev)
 {
 	if (pm_power_off == as3722_pm_power_off)
 		pm_power_off = NULL;
 	as3722_pm_poweroff = NULL;
-
-	return 0;
 }
 
 static struct platform_driver as3722_poweroff_driver = {
@@ -75,7 +73,7 @@ static struct platform_driver as3722_poweroff_driver = {
 		.name = "as3722-power-off",
 	},
 	.probe = as3722_poweroff_probe,
-	.remove = as3722_poweroff_remove,
+	.remove_new = as3722_poweroff_remove,
 };
 
 module_platform_driver(as3722_poweroff_driver);
diff --git a/drivers/power/reset/at91-poweroff.c b/drivers/power/reset/at91-poweroff.c
index dd5399785b69..93eece027865 100644
--- a/drivers/power/reset/at91-poweroff.c
+++ b/drivers/power/reset/at91-poweroff.c
@@ -57,7 +57,7 @@ static struct shdwc {
 	void __iomem *mpddrc_base;
 } at91_shdwc;
 
-static void __init at91_wakeup_status(struct platform_device *pdev)
+static void at91_wakeup_status(struct platform_device *pdev)
 {
 	const char *reason;
 	u32 reg = readl(at91_shdwc.shdwc_base + AT91_SHDW_SR);
@@ -149,7 +149,7 @@ static void at91_poweroff_dt_set_wakeup_mode(struct platform_device *pdev)
 	writel(wakeup_mode | mode, at91_shdwc.shdwc_base + AT91_SHDW_MR);
 }
 
-static int __init at91_poweroff_probe(struct platform_device *pdev)
+static int at91_poweroff_probe(struct platform_device *pdev)
 {
 	struct device_node *np;
 	u32 ddr_type;
@@ -202,7 +202,7 @@ clk_disable:
 	return ret;
 }
 
-static int __exit at91_poweroff_remove(struct platform_device *pdev)
+static void at91_poweroff_remove(struct platform_device *pdev)
 {
 	if (pm_power_off == at91_poweroff)
 		pm_power_off = NULL;
@@ -211,8 +211,6 @@ static int __exit at91_poweroff_remove(struct platform_device *pdev)
 		iounmap(at91_shdwc.mpddrc_base);
 
 	clk_disable_unprepare(at91_shdwc.sclk);
-
-	return 0;
 }
 
 static const struct of_device_id at91_poweroff_of_match[] = {
@@ -224,13 +222,14 @@ static const struct of_device_id at91_poweroff_of_match[] = {
 MODULE_DEVICE_TABLE(of, at91_poweroff_of_match);
 
 static struct platform_driver at91_poweroff_driver = {
-	.remove = __exit_p(at91_poweroff_remove),
+	.probe = at91_poweroff_probe,
+	.remove_new = at91_poweroff_remove,
 	.driver = {
 		.name = "at91-poweroff",
 		.of_match_table = at91_poweroff_of_match,
 	},
 };
-module_platform_driver_probe(at91_poweroff_driver, at91_poweroff_probe);
+module_platform_driver(at91_poweroff_driver);
 
 MODULE_AUTHOR("Atmel Corporation");
 MODULE_DESCRIPTION("Shutdown driver for Atmel SoCs");
diff --git a/drivers/power/reset/at91-reset.c b/drivers/power/reset/at91-reset.c
index aa9b012d3d00..16512654295f 100644
--- a/drivers/power/reset/at91-reset.c
+++ b/drivers/power/reset/at91-reset.c
@@ -337,7 +337,7 @@ static int at91_rcdev_init(struct at91_reset *reset,
 	return devm_reset_controller_register(&pdev->dev, &reset->rcdev);
 }
 
-static int __init at91_reset_probe(struct platform_device *pdev)
+static int at91_reset_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *match;
 	struct at91_reset *reset;
@@ -417,24 +417,23 @@ disable_clk:
 	return ret;
 }
 
-static int __exit at91_reset_remove(struct platform_device *pdev)
+static void at91_reset_remove(struct platform_device *pdev)
 {
 	struct at91_reset *reset = platform_get_drvdata(pdev);
 
 	unregister_restart_handler(&reset->nb);
 	clk_disable_unprepare(reset->sclk);
-
-	return 0;
 }
 
 static struct platform_driver at91_reset_driver = {
-	.remove = __exit_p(at91_reset_remove),
+	.probe = at91_reset_probe,
+	.remove_new = at91_reset_remove,
 	.driver = {
 		.name = "at91-reset",
 		.of_match_table = at91_reset_of_match,
 	},
 };
-module_platform_driver_probe(at91_reset_driver, at91_reset_probe);
+module_platform_driver(at91_reset_driver);
 
 MODULE_AUTHOR("Atmel Corporation");
 MODULE_DESCRIPTION("Reset driver for Atmel SoCs");
diff --git a/drivers/power/reset/at91-sama5d2_shdwc.c b/drivers/power/reset/at91-sama5d2_shdwc.c
index e76b102b57b1..959ce0dbe91d 100644
--- a/drivers/power/reset/at91-sama5d2_shdwc.c
+++ b/drivers/power/reset/at91-sama5d2_shdwc.c
@@ -107,7 +107,7 @@ static const unsigned long long sdwc_dbc_period[] = {
 	0, 3, 32, 512, 4096, 32768,
 };
 
-static void __init at91_wakeup_status(struct platform_device *pdev)
+static void at91_wakeup_status(struct platform_device *pdev)
 {
 	struct shdwc *shdw = platform_get_drvdata(pdev);
 	const struct reg_config *rcfg = shdw->rcfg;
@@ -329,7 +329,7 @@ static const struct of_device_id at91_pmc_ids[] = {
 	{ /* Sentinel. */ }
 };
 
-static int __init at91_shdwc_probe(struct platform_device *pdev)
+static int at91_shdwc_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *match;
 	struct device_node *np;
@@ -421,7 +421,7 @@ clk_disable:
 	return ret;
 }
 
-static int __exit at91_shdwc_remove(struct platform_device *pdev)
+static void at91_shdwc_remove(struct platform_device *pdev)
 {
 	struct shdwc *shdw = platform_get_drvdata(pdev);
 
@@ -437,18 +437,17 @@ static int __exit at91_shdwc_remove(struct platform_device *pdev)
 	iounmap(shdw->pmc_base);
 
 	clk_disable_unprepare(shdw->sclk);
-
-	return 0;
 }
 
 static struct platform_driver at91_shdwc_driver = {
-	.remove = __exit_p(at91_shdwc_remove),
+	.probe = at91_shdwc_probe,
+	.remove_new = at91_shdwc_remove,
 	.driver = {
 		.name = "at91-shdwc",
 		.of_match_table = at91_shdwc_of_match,
 	},
 };
-module_platform_driver_probe(at91_shdwc_driver, at91_shdwc_probe);
+module_platform_driver(at91_shdwc_driver);
 
 MODULE_AUTHOR("Nicolas Ferre <nicolas.ferre@atmel.com>");
 MODULE_DESCRIPTION("Atmel shutdown controller driver");
diff --git a/drivers/power/reset/atc260x-poweroff.c b/drivers/power/reset/atc260x-poweroff.c
index 98f20251a6d1..b4aa50e9685e 100644
--- a/drivers/power/reset/atc260x-poweroff.c
+++ b/drivers/power/reset/atc260x-poweroff.c
@@ -233,7 +233,7 @@ static int atc260x_pwrc_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int atc260x_pwrc_remove(struct platform_device *pdev)
+static void atc260x_pwrc_remove(struct platform_device *pdev)
 {
 	struct atc260x_pwrc *priv = platform_get_drvdata(pdev);
 
@@ -243,13 +243,11 @@ static int atc260x_pwrc_remove(struct platform_device *pdev)
 	}
 
 	unregister_restart_handler(&priv->restart_nb);
-
-	return 0;
 }
 
 static struct platform_driver atc260x_pwrc_driver = {
 	.probe = atc260x_pwrc_probe,
-	.remove = atc260x_pwrc_remove,
+	.remove_new = atc260x_pwrc_remove,
 	.driver = {
 		.name = "atc260x-pwrc",
 	},
diff --git a/drivers/power/reset/gpio-restart.c b/drivers/power/reset/gpio-restart.c
index 3aa19765772d..d1e177176fa1 100644
--- a/drivers/power/reset/gpio-restart.c
+++ b/drivers/power/reset/gpio-restart.c
@@ -17,17 +17,14 @@
 
 struct gpio_restart {
 	struct gpio_desc *reset_gpio;
-	struct notifier_block restart_handler;
 	u32 active_delay_ms;
 	u32 inactive_delay_ms;
 	u32 wait_delay_ms;
 };
 
-static int gpio_restart_notify(struct notifier_block *this,
-				unsigned long mode, void *cmd)
+static int gpio_restart_notify(struct sys_off_data *data)
 {
-	struct gpio_restart *gpio_restart =
-		container_of(this, struct gpio_restart, restart_handler);
+	struct gpio_restart *gpio_restart = data->cb_data;
 
 	/* drive it active, also inactive->active edge */
 	gpiod_direction_output(gpio_restart->reset_gpio, 1);
@@ -52,6 +49,7 @@ static int gpio_restart_probe(struct platform_device *pdev)
 {
 	struct gpio_restart *gpio_restart;
 	bool open_source = false;
+	int priority = 129;
 	u32 property;
 	int ret;
 
@@ -71,8 +69,6 @@ static int gpio_restart_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	gpio_restart->restart_handler.notifier_call = gpio_restart_notify;
-	gpio_restart->restart_handler.priority = 129;
 	gpio_restart->active_delay_ms = 100;
 	gpio_restart->inactive_delay_ms = 100;
 	gpio_restart->wait_delay_ms = 3000;
@@ -83,7 +79,7 @@ static int gpio_restart_probe(struct platform_device *pdev)
 			dev_err(&pdev->dev, "Invalid priority property: %u\n",
 					property);
 		else
-			gpio_restart->restart_handler.priority = property;
+			priority = property;
 	}
 
 	of_property_read_u32(pdev->dev.of_node, "active-delay",
@@ -93,9 +89,11 @@ static int gpio_restart_probe(struct platform_device *pdev)
 	of_property_read_u32(pdev->dev.of_node, "wait-delay",
 			&gpio_restart->wait_delay_ms);
 
-	platform_set_drvdata(pdev, gpio_restart);
-
-	ret = register_restart_handler(&gpio_restart->restart_handler);
+	ret = devm_register_sys_off_handler(&pdev->dev,
+					    SYS_OFF_MODE_RESTART,
+					    priority,
+					    gpio_restart_notify,
+					    gpio_restart);
 	if (ret) {
 		dev_err(&pdev->dev, "%s: cannot register restart handler, %d\n",
 				__func__, ret);
@@ -105,19 +103,6 @@ static int gpio_restart_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static void gpio_restart_remove(struct platform_device *pdev)
-{
-	struct gpio_restart *gpio_restart = platform_get_drvdata(pdev);
-	int ret;
-
-	ret = unregister_restart_handler(&gpio_restart->restart_handler);
-	if (ret) {
-		dev_err(&pdev->dev,
-				"%s: cannot unregister restart handler, %d\n",
-				__func__, ret);
-	}
-}
-
 static const struct of_device_id of_gpio_restart_match[] = {
 	{ .compatible = "gpio-restart", },
 	{},
@@ -125,7 +110,6 @@ static const struct of_device_id of_gpio_restart_match[] = {
 
 static struct platform_driver gpio_restart_driver = {
 	.probe = gpio_restart_probe,
-	.remove_new = gpio_restart_remove,
 	.driver = {
 		.name = "restart-gpio",
 		.of_match_table = of_gpio_restart_match,
diff --git a/drivers/power/reset/ltc2952-poweroff.c b/drivers/power/reset/ltc2952-poweroff.c
index eea05921a054..fa25fbd53934 100644
--- a/drivers/power/reset/ltc2952-poweroff.c
+++ b/drivers/power/reset/ltc2952-poweroff.c
@@ -286,7 +286,7 @@ static int ltc2952_poweroff_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int ltc2952_poweroff_remove(struct platform_device *pdev)
+static void ltc2952_poweroff_remove(struct platform_device *pdev)
 {
 	struct ltc2952_poweroff *data = platform_get_drvdata(pdev);
 
@@ -295,7 +295,6 @@ static int ltc2952_poweroff_remove(struct platform_device *pdev)
 	hrtimer_cancel(&data->timer_wde);
 	atomic_notifier_chain_unregister(&panic_notifier_list,
 					 &data->panic_notifier);
-	return 0;
 }
 
 static const struct of_device_id of_ltc2952_poweroff_match[] = {
@@ -306,7 +305,7 @@ MODULE_DEVICE_TABLE(of, of_ltc2952_poweroff_match);
 
 static struct platform_driver ltc2952_poweroff_driver = {
 	.probe = ltc2952_poweroff_probe,
-	.remove = ltc2952_poweroff_remove,
+	.remove_new = ltc2952_poweroff_remove,
 	.driver = {
 		.name = "ltc2952-poweroff",
 		.of_match_table = of_ltc2952_poweroff_match,
diff --git a/drivers/power/reset/mt6323-poweroff.c b/drivers/power/reset/mt6323-poweroff.c
index 108167f7738b..57a63c0ab7fb 100644
--- a/drivers/power/reset/mt6323-poweroff.c
+++ b/drivers/power/reset/mt6323-poweroff.c
@@ -70,12 +70,10 @@ static int mt6323_pwrc_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int mt6323_pwrc_remove(struct platform_device *pdev)
+static void mt6323_pwrc_remove(struct platform_device *pdev)
 {
 	if (pm_power_off == &mt6323_do_pwroff)
 		pm_power_off = NULL;
-
-	return 0;
 }
 
 static const struct of_device_id mt6323_pwrc_dt_match[] = {
@@ -86,7 +84,7 @@ MODULE_DEVICE_TABLE(of, mt6323_pwrc_dt_match);
 
 static struct platform_driver mt6323_pwrc_driver = {
 	.probe          = mt6323_pwrc_probe,
-	.remove         = mt6323_pwrc_remove,
+	.remove_new     = mt6323_pwrc_remove,
 	.driver         = {
 		.name   = "mt6323-pwrc",
 		.of_match_table = mt6323_pwrc_dt_match,
diff --git a/drivers/power/reset/pwr-mlxbf.c b/drivers/power/reset/pwr-mlxbf.c
index de35d24bb7ef..1775b318d0ef 100644
--- a/drivers/power/reset/pwr-mlxbf.c
+++ b/drivers/power/reset/pwr-mlxbf.c
@@ -17,11 +17,17 @@
 #include <linux/types.h>
 
 struct pwr_mlxbf {
-	struct work_struct send_work;
+	struct work_struct reboot_work;
+	struct work_struct shutdown_work;
 	const char *hid;
 };
 
-static void pwr_mlxbf_send_work(struct work_struct *work)
+static void pwr_mlxbf_reboot_work(struct work_struct *work)
+{
+	acpi_bus_generate_netlink_event("button/reboot.*", "Reboot Button", 0x80, 1);
+}
+
+static void pwr_mlxbf_shutdown_work(struct work_struct *work)
 {
 	acpi_bus_generate_netlink_event("button/power.*", "Power Button", 0x80, 1);
 }
@@ -33,10 +39,10 @@ static irqreturn_t pwr_mlxbf_irq(int irq, void *ptr)
 	struct pwr_mlxbf *priv = ptr;
 
 	if (!strncmp(priv->hid, rst_pwr_hid, 8))
-		emergency_restart();
+		schedule_work(&priv->reboot_work);
 
 	if (!strncmp(priv->hid, low_pwr_hid, 8))
-		schedule_work(&priv->send_work);
+		schedule_work(&priv->shutdown_work);
 
 	return IRQ_HANDLED;
 }
@@ -64,7 +70,11 @@ static int pwr_mlxbf_probe(struct platform_device *pdev)
 	if (irq < 0)
 		return dev_err_probe(dev, irq, "Error getting %s irq.\n", priv->hid);
 
-	err = devm_work_autocancel(dev, &priv->send_work, pwr_mlxbf_send_work);
+	err = devm_work_autocancel(dev, &priv->shutdown_work, pwr_mlxbf_shutdown_work);
+	if (err)
+		return err;
+
+	err = devm_work_autocancel(dev, &priv->reboot_work, pwr_mlxbf_reboot_work);
 	if (err)
 		return err;
 
diff --git a/drivers/power/reset/qnap-poweroff.c b/drivers/power/reset/qnap-poweroff.c
index 0ddf7f25f7b8..e0f2ff6b147c 100644
--- a/drivers/power/reset/qnap-poweroff.c
+++ b/drivers/power/reset/qnap-poweroff.c
@@ -111,15 +111,14 @@ static int qnap_power_off_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int qnap_power_off_remove(struct platform_device *pdev)
+static void qnap_power_off_remove(struct platform_device *pdev)
 {
 	pm_power_off = NULL;
-	return 0;
 }
 
 static struct platform_driver qnap_power_off_driver = {
 	.probe	= qnap_power_off_probe,
-	.remove	= qnap_power_off_remove,
+	.remove_new = qnap_power_off_remove,
 	.driver	= {
 		.name	= "qnap_power_off",
 		.of_match_table = of_match_ptr(qnap_power_off_of_match_table),
diff --git a/drivers/power/reset/regulator-poweroff.c b/drivers/power/reset/regulator-poweroff.c
index 7f87fbb8b051..15160809c423 100644
--- a/drivers/power/reset/regulator-poweroff.c
+++ b/drivers/power/reset/regulator-poweroff.c
@@ -52,12 +52,10 @@ static int regulator_poweroff_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int regulator_poweroff_remove(__maybe_unused struct platform_device *pdev)
+static void regulator_poweroff_remove(struct platform_device *pdev)
 {
 	if (pm_power_off == &regulator_poweroff_do_poweroff)
 		pm_power_off = NULL;
-
-	return 0;
 }
 
 static const struct of_device_id of_regulator_poweroff_match[] = {
@@ -68,7 +66,7 @@ MODULE_DEVICE_TABLE(of, of_regulator_poweroff_match);
 
 static struct platform_driver regulator_poweroff_driver = {
 	.probe = regulator_poweroff_probe,
-	.remove = regulator_poweroff_remove,
+	.remove_new = regulator_poweroff_remove,
 	.driver = {
 		.name = "poweroff-regulator",
 		.of_match_table = of_regulator_poweroff_match,
diff --git a/drivers/power/reset/restart-poweroff.c b/drivers/power/reset/restart-poweroff.c
index 28f1822db162..f4d6004793d3 100644
--- a/drivers/power/reset/restart-poweroff.c
+++ b/drivers/power/reset/restart-poweroff.c
@@ -33,12 +33,10 @@ static int restart_poweroff_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int restart_poweroff_remove(struct platform_device *pdev)
+static void restart_poweroff_remove(struct platform_device *pdev)
 {
 	if (pm_power_off == &restart_poweroff_do_poweroff)
 		pm_power_off = NULL;
-
-	return 0;
 }
 
 static const struct of_device_id of_restart_poweroff_match[] = {
@@ -49,7 +47,7 @@ MODULE_DEVICE_TABLE(of, of_restart_poweroff_match);
 
 static struct platform_driver restart_poweroff_driver = {
 	.probe = restart_poweroff_probe,
-	.remove = restart_poweroff_remove,
+	.remove_new = restart_poweroff_remove,
 	.driver = {
 		.name = "poweroff-restart",
 		.of_match_table = of_restart_poweroff_match,
diff --git a/drivers/power/reset/rmobile-reset.c b/drivers/power/reset/rmobile-reset.c
index bd3b396558e0..5df9b41c68c7 100644
--- a/drivers/power/reset/rmobile-reset.c
+++ b/drivers/power/reset/rmobile-reset.c
@@ -59,11 +59,10 @@ fail_unmap:
 	return error;
 }
 
-static int rmobile_reset_remove(struct platform_device *pdev)
+static void rmobile_reset_remove(struct platform_device *pdev)
 {
 	unregister_restart_handler(&rmobile_reset_nb);
 	iounmap(sysc_base2);
-	return 0;
 }
 
 static const struct of_device_id rmobile_reset_of_match[] = {
@@ -74,7 +73,7 @@ MODULE_DEVICE_TABLE(of, rmobile_reset_of_match);
 
 static struct platform_driver rmobile_reset_driver = {
 	.probe = rmobile_reset_probe,
-	.remove = rmobile_reset_remove,
+	.remove_new = rmobile_reset_remove,
 	.driver = {
 		.name = "rmobile_reset",
 		.of_match_table = rmobile_reset_of_match,
diff --git a/drivers/power/reset/syscon-poweroff.c b/drivers/power/reset/syscon-poweroff.c
index c3aab7f59345..1b2ce7734260 100644
--- a/drivers/power/reset/syscon-poweroff.c
+++ b/drivers/power/reset/syscon-poweroff.c
@@ -76,12 +76,10 @@ static int syscon_poweroff_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int syscon_poweroff_remove(struct platform_device *pdev)
+static void syscon_poweroff_remove(struct platform_device *pdev)
 {
 	if (pm_power_off == syscon_poweroff)
 		pm_power_off = NULL;
-
-	return 0;
 }
 
 static const struct of_device_id syscon_poweroff_of_match[] = {
@@ -91,7 +89,7 @@ static const struct of_device_id syscon_poweroff_of_match[] = {
 
 static struct platform_driver syscon_poweroff_driver = {
 	.probe = syscon_poweroff_probe,
-	.remove = syscon_poweroff_remove,
+	.remove_new = syscon_poweroff_remove,
 	.driver = {
 		.name = "syscon-poweroff",
 		.of_match_table = syscon_poweroff_of_match,
diff --git a/drivers/power/reset/tps65086-restart.c b/drivers/power/reset/tps65086-restart.c
index 5ec819eac7da..ee8e9f4b837e 100644
--- a/drivers/power/reset/tps65086-restart.c
+++ b/drivers/power/reset/tps65086-restart.c
@@ -62,19 +62,21 @@ static int tps65086_restart_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int tps65086_restart_remove(struct platform_device *pdev)
+static void tps65086_restart_remove(struct platform_device *pdev)
 {
 	struct tps65086_restart *tps65086_restart = platform_get_drvdata(pdev);
 	int ret;
 
 	ret = unregister_restart_handler(&tps65086_restart->handler);
 	if (ret) {
+		/*
+		 * tps65086_restart_probe() registered the restart handler. So
+		 * unregistering should work fine. Checking the error code
+		 * shouldn't be needed, still doing it for completeness.
+		 */
 		dev_err(&pdev->dev, "%s: cannot unregister restart handler: %d\n",
 			__func__, ret);
-		return -ENODEV;
 	}
-
-	return 0;
 }
 
 static const struct platform_device_id tps65086_restart_id_table[] = {
@@ -88,7 +90,7 @@ static struct platform_driver tps65086_restart_driver = {
 		.name = "tps65086-restart",
 	},
 	.probe = tps65086_restart_probe,
-	.remove = tps65086_restart_remove,
+	.remove_new = tps65086_restart_remove,
 	.id_table = tps65086_restart_id_table,
 };
 module_platform_driver(tps65086_restart_driver);
diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig
index f21cb05815ec..3e31375491d5 100644
--- a/drivers/power/supply/Kconfig
+++ b/drivers/power/supply/Kconfig
@@ -978,6 +978,7 @@ config CHARGER_QCOM_SMB2
 config FUEL_GAUGE_MM8013
 	tristate "Mitsumi MM8013 fuel gauge driver"
 	depends on I2C
+	select REGMAP_I2C
 	help
 	  Say Y here to enable the Mitsumi MM8013 fuel gauge driver.
 	  It enables the monitoring of many battery parameters, including
diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c
index 1db290ee2591..2b393eb5c282 100644
--- a/drivers/power/supply/bq24190_charger.c
+++ b/drivers/power/supply/bq24190_charger.c
@@ -36,10 +36,16 @@
 #define BQ24190_REG_POC_WDT_RESET_SHIFT		6
 #define BQ24190_REG_POC_CHG_CONFIG_MASK		(BIT(5) | BIT(4))
 #define BQ24190_REG_POC_CHG_CONFIG_SHIFT	4
-#define BQ24190_REG_POC_CHG_CONFIG_DISABLE		0x0
-#define BQ24190_REG_POC_CHG_CONFIG_CHARGE		0x1
-#define BQ24190_REG_POC_CHG_CONFIG_OTG			0x2
-#define BQ24190_REG_POC_CHG_CONFIG_OTG_ALT		0x3
+#define BQ24190_REG_POC_CHG_CONFIG_DISABLE	0x0
+#define BQ24190_REG_POC_CHG_CONFIG_CHARGE	0x1
+#define BQ24190_REG_POC_CHG_CONFIG_OTG		0x2
+#define BQ24190_REG_POC_CHG_CONFIG_OTG_ALT	0x3
+#define BQ24296_REG_POC_OTG_CONFIG_MASK		BIT(5)
+#define BQ24296_REG_POC_OTG_CONFIG_SHIFT	5
+#define BQ24296_REG_POC_CHG_CONFIG_MASK		BIT(4)
+#define BQ24296_REG_POC_CHG_CONFIG_SHIFT	4
+#define BQ24296_REG_POC_OTG_CONFIG_DISABLE	0x0
+#define BQ24296_REG_POC_OTG_CONFIG_OTG		0x1
 #define BQ24190_REG_POC_SYS_MIN_MASK		(BIT(3) | BIT(2) | BIT(1))
 #define BQ24190_REG_POC_SYS_MIN_SHIFT		1
 #define BQ24190_REG_POC_SYS_MIN_MIN			3000
@@ -134,59 +140,24 @@
 #define BQ24190_REG_F_BAT_FAULT_SHIFT		3
 #define BQ24190_REG_F_NTC_FAULT_MASK		(BIT(2) | BIT(1) | BIT(0))
 #define BQ24190_REG_F_NTC_FAULT_SHIFT		0
+#define BQ24296_REG_F_NTC_FAULT_MASK		(BIT(1) | BIT(0))
+#define BQ24296_REG_F_NTC_FAULT_SHIFT		0
 
 #define BQ24190_REG_VPRS	0x0A /* Vendor/Part/Revision Status */
 #define BQ24190_REG_VPRS_PN_MASK		(BIT(5) | BIT(4) | BIT(3))
 #define BQ24190_REG_VPRS_PN_SHIFT		3
-#define BQ24190_REG_VPRS_PN_24190			0x4
-#define BQ24190_REG_VPRS_PN_24192			0x5 /* Also 24193, 24196 */
-#define BQ24190_REG_VPRS_PN_24192I			0x3
+#define BQ24190_REG_VPRS_PN_24190		0x4
+#define BQ24190_REG_VPRS_PN_24192		0x5 /* Also 24193, 24196 */
+#define BQ24190_REG_VPRS_PN_24192I		0x3
+#define BQ24296_REG_VPRS_PN_MASK		(BIT(7) | BIT(6) | BIT(5))
+#define BQ24296_REG_VPRS_PN_SHIFT		5
+#define BQ24296_REG_VPRS_PN_24296		0x1
 #define BQ24190_REG_VPRS_TS_PROFILE_MASK	BIT(2)
 #define BQ24190_REG_VPRS_TS_PROFILE_SHIFT	2
 #define BQ24190_REG_VPRS_DEV_REG_MASK		(BIT(1) | BIT(0))
 #define BQ24190_REG_VPRS_DEV_REG_SHIFT		0
 
 /*
- * The FAULT register is latched by the bq24190 (except for NTC_FAULT)
- * so the first read after a fault returns the latched value and subsequent
- * reads return the current value.  In order to return the fault status
- * to the user, have the interrupt handler save the reg's value and retrieve
- * it in the appropriate health/status routine.
- */
-struct bq24190_dev_info {
-	struct i2c_client		*client;
-	struct device			*dev;
-	struct extcon_dev		*edev;
-	struct power_supply		*charger;
-	struct power_supply		*battery;
-	struct delayed_work		input_current_limit_work;
-	char				model_name[I2C_NAME_SIZE];
-	bool				initialized;
-	bool				irq_event;
-	bool				otg_vbus_enabled;
-	int				charge_type;
-	u16				sys_min;
-	u16				iprechg;
-	u16				iterm;
-	u32				ichg;
-	u32				ichg_max;
-	u32				vreg;
-	u32				vreg_max;
-	struct mutex			f_reg_lock;
-	u8				f_reg;
-	u8				ss_reg;
-	u8				watchdog;
-};
-
-static int bq24190_charger_set_charge_type(struct bq24190_dev_info *bdi,
-					   const union power_supply_propval *val);
-
-static const unsigned int bq24190_usb_extcon_cable[] = {
-	EXTCON_USB,
-	EXTCON_NONE,
-};
-
-/*
  * The tables below provide a 2-way mapping for the value that goes in
  * the register field and the real-world value that it represents.
  * The index of the array is the value that goes in the register; the
@@ -211,6 +182,9 @@ static const int bq24190_ccc_ichg_values[] = {
 	4096000, 4160000, 4224000, 4288000, 4352000, 4416000, 4480000, 4544000
 };
 
+/* ICHG higher than 3008mA is not supported in BQ24296 */
+#define BQ24296_CCC_ICHG_VALUES_LEN	40
+
 /* REG04[7:2] (VREG) in uV */
 static const int bq24190_cvc_vreg_values[] = {
 	3504000, 3520000, 3536000, 3552000, 3568000, 3584000, 3600000, 3616000,
@@ -228,6 +202,68 @@ static const int bq24190_ictrc_treg_values[] = {
 	600, 800, 1000, 1200
 };
 
+enum bq24190_chip {
+	BQ24190,
+	BQ24192,
+	BQ24192i,
+	BQ24196,
+	BQ24296,
+};
+
+/*
+ * The FAULT register is latched by the bq24190 (except for NTC_FAULT)
+ * so the first read after a fault returns the latched value and subsequent
+ * reads return the current value.  In order to return the fault status
+ * to the user, have the interrupt handler save the reg's value and retrieve
+ * it in the appropriate health/status routine.
+ */
+struct bq24190_dev_info {
+	struct i2c_client		*client;
+	struct device			*dev;
+	struct extcon_dev		*edev;
+	struct power_supply		*charger;
+	struct power_supply		*battery;
+	struct delayed_work		input_current_limit_work;
+	char				model_name[I2C_NAME_SIZE];
+	bool				initialized;
+	bool				irq_event;
+	bool				otg_vbus_enabled;
+	int				charge_type;
+	u16				sys_min;
+	u16				iprechg;
+	u16				iterm;
+	u32				ichg;
+	u32				ichg_max;
+	u32				vreg;
+	u32				vreg_max;
+	struct mutex			f_reg_lock;
+	u8				f_reg;
+	u8				ss_reg;
+	u8				watchdog;
+	const struct bq24190_chip_info	*info;
+};
+
+struct bq24190_chip_info {
+	int ichg_array_size;
+#ifdef CONFIG_REGULATOR
+	const struct regulator_desc *vbus_desc;
+#endif
+	int (*check_chip)(struct bq24190_dev_info *bdi);
+	int (*set_chg_config)(struct bq24190_dev_info *bdi, const u8 chg_config);
+	int (*set_otg_vbus)(struct bq24190_dev_info *bdi, bool enable);
+	u8 ntc_fault_mask;
+	int (*get_ntc_status)(const u8 value);
+};
+
+static int bq24190_charger_set_charge_type(struct bq24190_dev_info *bdi,
+					   const union power_supply_propval *val);
+
+static const unsigned int bq24190_usb_extcon_cable[] = {
+	EXTCON_USB,
+	EXTCON_NONE,
+};
+
+
 /*
  * Return the index in 'tbl' of greatest value that is less than or equal to
  * 'val'.  The index range returned is 0 to 'tbl_size' - 1.  Assumes that
@@ -529,6 +565,43 @@ static int bq24190_set_otg_vbus(struct bq24190_dev_info *bdi, bool enable)
 	return ret;
 }
 
+static int bq24296_set_otg_vbus(struct bq24190_dev_info *bdi, bool enable)
+{
+	int ret;
+
+	ret = pm_runtime_resume_and_get(bdi->dev);
+	if (ret < 0) {
+		dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", ret);
+		return ret;
+	}
+
+	bdi->otg_vbus_enabled = enable;
+	if (enable) {
+		ret = bq24190_write_mask(bdi, BQ24190_REG_POC,
+					 BQ24296_REG_POC_CHG_CONFIG_MASK,
+					 BQ24296_REG_POC_CHG_CONFIG_SHIFT,
+					 BQ24190_REG_POC_CHG_CONFIG_DISABLE);
+
+		if (ret < 0)
+			goto out;
+
+		ret = bq24190_write_mask(bdi, BQ24190_REG_POC,
+					 BQ24296_REG_POC_OTG_CONFIG_MASK,
+					 BQ24296_REG_POC_CHG_CONFIG_SHIFT,
+					 BQ24296_REG_POC_OTG_CONFIG_OTG);
+	} else
+		ret = bq24190_write_mask(bdi, BQ24190_REG_POC,
+					 BQ24296_REG_POC_OTG_CONFIG_MASK,
+					 BQ24296_REG_POC_CHG_CONFIG_SHIFT,
+					 BQ24296_REG_POC_OTG_CONFIG_DISABLE);
+
+out:
+	pm_runtime_mark_last_busy(bdi->dev);
+	pm_runtime_put_autosuspend(bdi->dev);
+
+	return ret;
+}
+
 #ifdef CONFIG_REGULATOR
 static int bq24190_vbus_enable(struct regulator_dev *dev)
 {
@@ -567,6 +640,43 @@ static int bq24190_vbus_is_enabled(struct regulator_dev *dev)
 	return bdi->otg_vbus_enabled;
 }
 
+static int bq24296_vbus_enable(struct regulator_dev *dev)
+{
+	return bq24296_set_otg_vbus(rdev_get_drvdata(dev), true);
+}
+
+static int bq24296_vbus_disable(struct regulator_dev *dev)
+{
+	return bq24296_set_otg_vbus(rdev_get_drvdata(dev), false);
+}
+
+static int bq24296_vbus_is_enabled(struct regulator_dev *dev)
+{
+	struct bq24190_dev_info *bdi = rdev_get_drvdata(dev);
+	int ret;
+	u8 val;
+
+	ret = pm_runtime_resume_and_get(bdi->dev);
+	if (ret < 0) {
+		dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", ret);
+		return ret;
+	}
+
+	ret = bq24190_read_mask(bdi, BQ24190_REG_POC,
+				BQ24296_REG_POC_OTG_CONFIG_MASK,
+				BQ24296_REG_POC_OTG_CONFIG_SHIFT, &val);
+
+	pm_runtime_mark_last_busy(bdi->dev);
+	pm_runtime_put_autosuspend(bdi->dev);
+
+	if (ret)
+		return ret;
+
+	bdi->otg_vbus_enabled = (val == BQ24296_REG_POC_OTG_CONFIG_OTG);
+
+	return bdi->otg_vbus_enabled;
+}
+
 static const struct regulator_ops bq24190_vbus_ops = {
 	.enable = bq24190_vbus_enable,
 	.disable = bq24190_vbus_disable,
@@ -583,6 +693,22 @@ static const struct regulator_desc bq24190_vbus_desc = {
 	.n_voltages = 1,
 };
 
+static const struct regulator_ops bq24296_vbus_ops = {
+	.enable = bq24296_vbus_enable,
+	.disable = bq24296_vbus_disable,
+	.is_enabled = bq24296_vbus_is_enabled,
+};
+
+static const struct regulator_desc bq24296_vbus_desc = {
+	.name = "usb_otg_vbus",
+	.of_match = "usb-otg-vbus",
+	.type = REGULATOR_VOLTAGE,
+	.owner = THIS_MODULE,
+	.ops = &bq24296_vbus_ops,
+	.fixed_uV = 5000000,
+	.n_voltages = 1,
+};
+
 static const struct regulator_init_data bq24190_vbus_init_data = {
 	.constraints = {
 		.valid_ops_mask = REGULATOR_CHANGE_STATUS,
@@ -602,7 +728,7 @@ static int bq24190_register_vbus_regulator(struct bq24190_dev_info *bdi)
 	else
 		cfg.init_data = &bq24190_vbus_init_data;
 	cfg.driver_data = bdi;
-	reg = devm_regulator_register(bdi->dev, &bq24190_vbus_desc, &cfg);
+	reg = devm_regulator_register(bdi->dev, bdi->info->vbus_desc, &cfg);
 	if (IS_ERR(reg)) {
 		ret = PTR_ERR(reg);
 		dev_err(bdi->dev, "Can't register regulator: %d\n", ret);
@@ -678,7 +804,7 @@ static int bq24190_set_config(struct bq24190_dev_info *bdi)
 					    BQ24190_REG_CCC_ICHG_MASK,
 					    BQ24190_REG_CCC_ICHG_SHIFT,
 					    bq24190_ccc_ichg_values,
-					    ARRAY_SIZE(bq24190_ccc_ichg_values),
+					    bdi->info->ichg_array_size,
 					    bdi->ichg);
 		if (ret < 0)
 			return ret;
@@ -777,6 +903,24 @@ static int bq24190_charger_get_charge_type(struct bq24190_dev_info *bdi,
 	return 0;
 }
 
+static int bq24190_battery_set_chg_config(struct bq24190_dev_info *bdi,
+		const u8 chg_config)
+{
+	return bq24190_write_mask(bdi, BQ24190_REG_POC,
+			BQ24190_REG_POC_CHG_CONFIG_MASK,
+			BQ24190_REG_POC_CHG_CONFIG_SHIFT,
+			chg_config);
+}
+
+static int bq24296_battery_set_chg_config(struct bq24190_dev_info *bdi,
+		const u8 chg_config)
+{
+	return bq24190_write_mask(bdi, BQ24190_REG_POC,
+			BQ24296_REG_POC_CHG_CONFIG_MASK,
+			BQ24296_REG_POC_CHG_CONFIG_SHIFT,
+			chg_config);
+}
+
 static int bq24190_charger_set_charge_type(struct bq24190_dev_info *bdi,
 		const union power_supply_propval *val)
 {
@@ -835,9 +979,50 @@ static int bq24190_charger_set_charge_type(struct bq24190_dev_info *bdi,
 			return ret;
 	}
 
-	return bq24190_write_mask(bdi, BQ24190_REG_POC,
-			BQ24190_REG_POC_CHG_CONFIG_MASK,
-			BQ24190_REG_POC_CHG_CONFIG_SHIFT, chg_config);
+	return bdi->info->set_chg_config(bdi, chg_config);
+}
+
+static int bq24190_charger_get_ntc_status(u8 value)
+{
+	int health;
+
+	switch (value >> BQ24190_REG_F_NTC_FAULT_SHIFT & 0x7) {
+	case 0x1: /* TS1  Cold */
+	case 0x3: /* TS2  Cold */
+	case 0x5: /* Both Cold */
+		health = POWER_SUPPLY_HEALTH_COLD;
+		break;
+	case 0x2: /* TS1  Hot */
+	case 0x4: /* TS2  Hot */
+	case 0x6: /* Both Hot */
+		health = POWER_SUPPLY_HEALTH_OVERHEAT;
+		break;
+	default:
+		health = POWER_SUPPLY_HEALTH_UNKNOWN;
+	}
+
+	return health;
+}
+
+static int bq24296_charger_get_ntc_status(u8 value)
+{
+	int health;
+
+	switch (value >> BQ24296_REG_F_NTC_FAULT_SHIFT & 0x3) {
+	case 0x0: /* Normal */
+		health = POWER_SUPPLY_HEALTH_GOOD;
+		break;
+	case 0x1: /* Hot */
+		health = POWER_SUPPLY_HEALTH_OVERHEAT;
+		break;
+	case 0x2: /* Cold */
+		health = POWER_SUPPLY_HEALTH_COLD;
+		break;
+	default:
+		health = POWER_SUPPLY_HEALTH_UNKNOWN;
+	}
+
+	return health;
 }
 
 static int bq24190_charger_get_health(struct bq24190_dev_info *bdi,
@@ -850,21 +1035,8 @@ static int bq24190_charger_get_health(struct bq24190_dev_info *bdi,
 	v = bdi->f_reg;
 	mutex_unlock(&bdi->f_reg_lock);
 
-	if (v & BQ24190_REG_F_NTC_FAULT_MASK) {
-		switch (v >> BQ24190_REG_F_NTC_FAULT_SHIFT & 0x7) {
-		case 0x1: /* TS1  Cold */
-		case 0x3: /* TS2  Cold */
-		case 0x5: /* Both Cold */
-			health = POWER_SUPPLY_HEALTH_COLD;
-			break;
-		case 0x2: /* TS1  Hot */
-		case 0x4: /* TS2  Hot */
-		case 0x6: /* Both Hot */
-			health = POWER_SUPPLY_HEALTH_OVERHEAT;
-			break;
-		default:
-			health = POWER_SUPPLY_HEALTH_UNKNOWN;
-		}
+	if (v & bdi->info->ntc_fault_mask) {
+		health = bdi->info->get_ntc_status(v);
 	} else if (v & BQ24190_REG_F_BAT_FAULT_MASK) {
 		health = POWER_SUPPLY_HEALTH_OVERVOLTAGE;
 	} else if (v & BQ24190_REG_F_CHRG_FAULT_MASK) {
@@ -1015,7 +1187,7 @@ static int bq24190_charger_get_current(struct bq24190_dev_info *bdi,
 	ret = bq24190_get_field_val(bdi, BQ24190_REG_CCC,
 			BQ24190_REG_CCC_ICHG_MASK, BQ24190_REG_CCC_ICHG_SHIFT,
 			bq24190_ccc_ichg_values,
-			ARRAY_SIZE(bq24190_ccc_ichg_values), &curr);
+			bdi->info->ichg_array_size, &curr);
 	if (ret < 0)
 		return ret;
 
@@ -1055,7 +1227,7 @@ static int bq24190_charger_set_current(struct bq24190_dev_info *bdi,
 	ret = bq24190_set_field_val(bdi, BQ24190_REG_CCC,
 			BQ24190_REG_CCC_ICHG_MASK, BQ24190_REG_CCC_ICHG_SHIFT,
 			bq24190_ccc_ichg_values,
-			ARRAY_SIZE(bq24190_ccc_ichg_values), curr);
+			bdi->info->ichg_array_size, curr);
 	if (ret < 0)
 		return ret;
 
@@ -1395,26 +1567,9 @@ static int bq24190_battery_get_health(struct bq24190_dev_info *bdi,
 	if (v & BQ24190_REG_F_BAT_FAULT_MASK) {
 		health = POWER_SUPPLY_HEALTH_OVERVOLTAGE;
 	} else {
-		v &= BQ24190_REG_F_NTC_FAULT_MASK;
-		v >>= BQ24190_REG_F_NTC_FAULT_SHIFT;
+		v &= bdi->info->ntc_fault_mask;
 
-		switch (v) {
-		case 0x0: /* Normal */
-			health = POWER_SUPPLY_HEALTH_GOOD;
-			break;
-		case 0x1: /* TS1 Cold */
-		case 0x3: /* TS2 Cold */
-		case 0x5: /* Both Cold */
-			health = POWER_SUPPLY_HEALTH_COLD;
-			break;
-		case 0x2: /* TS1 Hot */
-		case 0x4: /* TS2 Hot */
-		case 0x6: /* Both Hot */
-			health = POWER_SUPPLY_HEALTH_OVERHEAT;
-			break;
-		default:
-			health = POWER_SUPPLY_HEALTH_UNKNOWN;
-		}
+		health = v ? bdi->info->get_ntc_status(v) : POWER_SUPPLY_HEALTH_GOOD;
 	}
 
 	val->intval = health;
@@ -1601,12 +1756,13 @@ static int bq24190_configure_usb_otg(struct bq24190_dev_info *bdi, u8 ss_reg)
 static void bq24190_check_status(struct bq24190_dev_info *bdi)
 {
 	const u8 battery_mask_ss = BQ24190_REG_SS_CHRG_STAT_MASK;
-	const u8 battery_mask_f = BQ24190_REG_F_BAT_FAULT_MASK
-				| BQ24190_REG_F_NTC_FAULT_MASK;
+	u8 battery_mask_f = BQ24190_REG_F_BAT_FAULT_MASK;
 	bool alert_charger = false, alert_battery = false;
 	u8 ss_reg = 0, f_reg = 0;
 	int i, ret;
 
+	battery_mask_f |= bdi->info->ntc_fault_mask;
+
 	ret = bq24190_read(bdi, BQ24190_REG_SS, &ss_reg);
 	if (ret < 0) {
 		dev_err(bdi->dev, "Can't read SS reg: %d\n", ret);
@@ -1633,7 +1789,7 @@ static void bq24190_check_status(struct bq24190_dev_info *bdi)
 			!!(f_reg & BQ24190_REG_F_BOOST_FAULT_MASK),
 			!!(f_reg & BQ24190_REG_F_CHRG_FAULT_MASK),
 			!!(f_reg & BQ24190_REG_F_BAT_FAULT_MASK),
-			!!(f_reg & BQ24190_REG_F_NTC_FAULT_MASK));
+			!!(f_reg & bdi->info->ntc_fault_mask));
 
 		mutex_lock(&bdi->f_reg_lock);
 		if ((bdi->f_reg & battery_mask_f) != (f_reg & battery_mask_f))
@@ -1696,12 +1852,11 @@ static irqreturn_t bq24190_irq_handler_thread(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int bq24190_hw_init(struct bq24190_dev_info *bdi)
+static int bq24190_check_chip(struct bq24190_dev_info *bdi)
 {
 	u8 v;
 	int ret;
 
-	/* First check that the device really is what its supposed to be */
 	ret = bq24190_read_mask(bdi, BQ24190_REG_VPRS,
 			BQ24190_REG_VPRS_PN_MASK,
 			BQ24190_REG_VPRS_PN_SHIFT,
@@ -1719,6 +1874,40 @@ static int bq24190_hw_init(struct bq24190_dev_info *bdi)
 		return -ENODEV;
 	}
 
+	return 0;
+}
+
+static int bq24296_check_chip(struct bq24190_dev_info *bdi)
+{
+	u8 v;
+	int ret;
+
+	ret = bq24190_read_mask(bdi, BQ24190_REG_VPRS,
+			BQ24296_REG_VPRS_PN_MASK,
+			BQ24296_REG_VPRS_PN_SHIFT,
+			&v);
+	if (ret < 0)
+		return ret;
+
+	switch (v) {
+	case BQ24296_REG_VPRS_PN_24296:
+		break;
+	default:
+		dev_err(bdi->dev, "Error unknown model: 0x%02x\n", v);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int bq24190_hw_init(struct bq24190_dev_info *bdi)
+{
+	int ret;
+
+	ret = bdi->info->check_chip(bdi);
+	if (ret < 0)
+		return ret;
+
 	ret = bq24190_register_reset(bdi);
 	if (ret < 0)
 		return ret;
@@ -1736,7 +1925,8 @@ static int bq24190_get_config(struct bq24190_dev_info *bdi)
 	struct power_supply_battery_info *info;
 	int v, idx;
 
-	idx = ARRAY_SIZE(bq24190_ccc_ichg_values) - 1;
+	idx = bdi->info->ichg_array_size - 1;
+
 	bdi->ichg_max = bq24190_ccc_ichg_values[idx];
 
 	idx = ARRAY_SIZE(bq24190_cvc_vreg_values) - 1;
@@ -1781,6 +1971,64 @@ static int bq24190_get_config(struct bq24190_dev_info *bdi)
 	return 0;
 }
 
+static const struct bq24190_chip_info bq24190_chip_info_tbl[] = {
+	[BQ24190] = {
+		.ichg_array_size = ARRAY_SIZE(bq24190_ccc_ichg_values),
+#ifdef CONFIG_REGULATOR
+		.vbus_desc = &bq24190_vbus_desc,
+#endif
+		.check_chip = bq24190_check_chip,
+		.set_chg_config = bq24190_battery_set_chg_config,
+		.ntc_fault_mask = BQ24190_REG_F_NTC_FAULT_MASK,
+		.get_ntc_status = bq24190_charger_get_ntc_status,
+		.set_otg_vbus = bq24190_set_otg_vbus,
+	},
+	[BQ24192] = {
+		.ichg_array_size = ARRAY_SIZE(bq24190_ccc_ichg_values),
+#ifdef CONFIG_REGULATOR
+		.vbus_desc = &bq24190_vbus_desc,
+#endif
+		.check_chip = bq24190_check_chip,
+		.set_chg_config = bq24190_battery_set_chg_config,
+		.ntc_fault_mask = BQ24190_REG_F_NTC_FAULT_MASK,
+		.get_ntc_status = bq24190_charger_get_ntc_status,
+		.set_otg_vbus = bq24190_set_otg_vbus,
+	},
+	[BQ24192i] = {
+		.ichg_array_size = ARRAY_SIZE(bq24190_ccc_ichg_values),
+#ifdef CONFIG_REGULATOR
+		.vbus_desc = &bq24190_vbus_desc,
+#endif
+		.check_chip = bq24190_check_chip,
+		.set_chg_config = bq24190_battery_set_chg_config,
+		.ntc_fault_mask = BQ24190_REG_F_NTC_FAULT_MASK,
+		.get_ntc_status = bq24190_charger_get_ntc_status,
+		.set_otg_vbus = bq24190_set_otg_vbus,
+	},
+	[BQ24196] = {
+		.ichg_array_size = ARRAY_SIZE(bq24190_ccc_ichg_values),
+#ifdef CONFIG_REGULATOR
+		.vbus_desc = &bq24190_vbus_desc,
+#endif
+		.check_chip = bq24190_check_chip,
+		.set_chg_config = bq24190_battery_set_chg_config,
+		.ntc_fault_mask = BQ24190_REG_F_NTC_FAULT_MASK,
+		.get_ntc_status = bq24190_charger_get_ntc_status,
+		.set_otg_vbus = bq24190_set_otg_vbus,
+	},
+	[BQ24296] = {
+		.ichg_array_size = BQ24296_CCC_ICHG_VALUES_LEN,
+#ifdef CONFIG_REGULATOR
+		.vbus_desc = &bq24296_vbus_desc,
+#endif
+		.check_chip = bq24296_check_chip,
+		.set_chg_config = bq24296_battery_set_chg_config,
+		.ntc_fault_mask = BQ24296_REG_F_NTC_FAULT_MASK,
+		.get_ntc_status = bq24296_charger_get_ntc_status,
+		.set_otg_vbus = bq24296_set_otg_vbus,
+	},
+};
+
 static int bq24190_probe(struct i2c_client *client)
 {
 	const struct i2c_device_id *id = i2c_client_get_device_id(client);
@@ -1804,6 +2052,7 @@ static int bq24190_probe(struct i2c_client *client)
 	bdi->client = client;
 	bdi->dev = dev;
 	strscpy(bdi->model_name, id->name, sizeof(bdi->model_name));
+	bdi->info = i2c_get_match_data(client);
 	mutex_init(&bdi->f_reg_lock);
 	bdi->charge_type = POWER_SUPPLY_CHARGE_TYPE_FAST;
 	bdi->f_reg = 0;
@@ -1940,7 +2189,7 @@ static void bq24190_shutdown(struct i2c_client *client)
 	struct bq24190_dev_info *bdi = i2c_get_clientdata(client);
 
 	/* Turn off 5V boost regulator on shutdown */
-	bq24190_set_otg_vbus(bdi, false);
+	bdi->info->set_otg_vbus(bdi, false);
 }
 
 static __maybe_unused int bq24190_runtime_suspend(struct device *dev)
@@ -2029,19 +2278,21 @@ static const struct dev_pm_ops bq24190_pm_ops = {
 };
 
 static const struct i2c_device_id bq24190_i2c_ids[] = {
-	{ "bq24190" },
-	{ "bq24192" },
-	{ "bq24192i" },
-	{ "bq24196" },
+	{ "bq24190", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24190] },
+	{ "bq24192", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24192] },
+	{ "bq24192i", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24192i] },
+	{ "bq24196", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24196] },
+	{ "bq24296", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24296] },
 	{ },
 };
 MODULE_DEVICE_TABLE(i2c, bq24190_i2c_ids);
 
 static const struct of_device_id bq24190_of_match[] = {
-	{ .compatible = "ti,bq24190", },
-	{ .compatible = "ti,bq24192", },
-	{ .compatible = "ti,bq24192i", },
-	{ .compatible = "ti,bq24196", },
+	{ .compatible = "ti,bq24190", .data = &bq24190_chip_info_tbl[BQ24190] },
+	{ .compatible = "ti,bq24192", .data = &bq24190_chip_info_tbl[BQ24192] },
+	{ .compatible = "ti,bq24192i", .data = &bq24190_chip_info_tbl[BQ24192i] },
+	{ .compatible = "ti,bq24196", .data = &bq24190_chip_info_tbl[BQ24196] },
+	{ .compatible = "ti,bq24296", .data = &bq24190_chip_info_tbl[BQ24296] },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, bq24190_of_match);
diff --git a/drivers/power/supply/bq256xx_charger.c b/drivers/power/supply/bq256xx_charger.c
index 789a31bd70c3..1a935bc88510 100644
--- a/drivers/power/supply/bq256xx_charger.c
+++ b/drivers/power/supply/bq256xx_charger.c
@@ -1574,13 +1574,16 @@ static int bq256xx_hw_init(struct bq256xx_device *bq)
 			wd_reg_val = i;
 			break;
 		}
-		if (bq->watchdog_timer > bq256xx_watchdog_time[i] &&
+		if (i + 1 < BQ256XX_NUM_WD_VAL &&
+		    bq->watchdog_timer > bq256xx_watchdog_time[i] &&
 		    bq->watchdog_timer < bq256xx_watchdog_time[i + 1])
 			wd_reg_val = i;
 	}
 	ret = regmap_update_bits(bq->regmap, BQ256XX_CHARGER_CONTROL_1,
 				 BQ256XX_WATCHDOG_MASK, wd_reg_val <<
 						BQ256XX_WDT_BIT_SHIFT);
+	if (ret)
+		return ret;
 
 	ret = power_supply_get_battery_info(bq->charger, &bat_info);
 	if (ret == -ENOMEM)
diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c
index 4296600e8912..1c4a9d137744 100644
--- a/drivers/power/supply/bq27xxx_battery.c
+++ b/drivers/power/supply/bq27xxx_battery.c
@@ -2162,6 +2162,28 @@ void bq27xxx_battery_teardown(struct bq27xxx_device_info *di)
 }
 EXPORT_SYMBOL_GPL(bq27xxx_battery_teardown);
 
+#ifdef CONFIG_PM_SLEEP
+static int bq27xxx_battery_suspend(struct device *dev)
+{
+	struct bq27xxx_device_info *di = dev_get_drvdata(dev);
+
+	cancel_delayed_work(&di->work);
+	return 0;
+}
+
+static int bq27xxx_battery_resume(struct device *dev)
+{
+	struct bq27xxx_device_info *di = dev_get_drvdata(dev);
+
+	schedule_delayed_work(&di->work, 0);
+	return 0;
+}
+#endif /* CONFIG_PM_SLEEP */
+
+SIMPLE_DEV_PM_OPS(bq27xxx_battery_battery_pm_ops,
+		  bq27xxx_battery_suspend, bq27xxx_battery_resume);
+EXPORT_SYMBOL_GPL(bq27xxx_battery_battery_pm_ops);
+
 MODULE_AUTHOR("Rodolfo Giometti <giometti@linux.it>");
 MODULE_DESCRIPTION("BQ27xxx battery monitor driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c
index 9b5475590518..9910c600743e 100644
--- a/drivers/power/supply/bq27xxx_battery_i2c.c
+++ b/drivers/power/supply/bq27xxx_battery_i2c.c
@@ -209,7 +209,9 @@ static void bq27xxx_battery_i2c_remove(struct i2c_client *client)
 {
 	struct bq27xxx_device_info *di = i2c_get_clientdata(client);
 
-	free_irq(client->irq, di);
+	if (client->irq)
+		free_irq(client->irq, di);
+
 	bq27xxx_battery_teardown(di);
 
 	mutex_lock(&battery_mutex);
@@ -295,6 +297,7 @@ static struct i2c_driver bq27xxx_battery_i2c_driver = {
 	.driver = {
 		.name = "bq27xxx-battery",
 		.of_match_table = of_match_ptr(bq27xxx_battery_i2c_of_match_table),
+		.pm = &bq27xxx_battery_battery_pm_ops,
 	},
 	.probe = bq27xxx_battery_i2c_probe,
 	.remove = bq27xxx_battery_i2c_remove,
diff --git a/drivers/power/supply/cw2015_battery.c b/drivers/power/supply/cw2015_battery.c
index bb29e9ebd24a..99f3ccdc30a6 100644
--- a/drivers/power/supply/cw2015_battery.c
+++ b/drivers/power/supply/cw2015_battery.c
@@ -491,7 +491,7 @@ static int cw_battery_get_property(struct power_supply *psy,
 
 	case POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW:
 		if (cw_battery_valid_time_to_empty(cw_bat))
-			val->intval = cw_bat->time_to_empty;
+			val->intval = cw_bat->time_to_empty * 60;
 		else
 			val->intval = 0;
 		break;
diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index 73265001dd4b..ecef35ac3b7e 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -861,44 +861,44 @@ const size_t power_supply_battery_info_properties_size = ARRAY_SIZE(power_supply
 EXPORT_SYMBOL_GPL(power_supply_battery_info_properties_size);
 
 bool power_supply_battery_info_has_prop(struct power_supply_battery_info *info,
-				        enum power_supply_property psp)
+					enum power_supply_property psp)
 {
 	if (!info)
 		return false;
 
 	switch (psp) {
-		case POWER_SUPPLY_PROP_TECHNOLOGY:
-			return info->technology != POWER_SUPPLY_TECHNOLOGY_UNKNOWN;
-		case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN:
-			return info->energy_full_design_uwh >= 0;
-		case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN:
-			return info->charge_full_design_uah >= 0;
-		case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
-			return info->voltage_min_design_uv >= 0;
-		case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN:
-			return info->voltage_max_design_uv >= 0;
-		case POWER_SUPPLY_PROP_PRECHARGE_CURRENT:
-			return info->precharge_current_ua >= 0;
-		case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT:
-			return info->charge_term_current_ua >= 0;
-		case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX:
-			return info->constant_charge_current_max_ua >= 0;
-		case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX:
-			return info->constant_charge_voltage_max_uv >= 0;
-		case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MIN:
-			return info->temp_ambient_alert_min > INT_MIN;
-		case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MAX:
-			return info->temp_ambient_alert_max < INT_MAX;
-		case POWER_SUPPLY_PROP_TEMP_ALERT_MIN:
-			return info->temp_alert_min > INT_MIN;
-		case POWER_SUPPLY_PROP_TEMP_ALERT_MAX:
-			return info->temp_alert_max < INT_MAX;
-		case POWER_SUPPLY_PROP_TEMP_MIN:
-			return info->temp_min > INT_MIN;
-		case POWER_SUPPLY_PROP_TEMP_MAX:
-			return info->temp_max < INT_MAX;
-		default:
-			return false;
+	case POWER_SUPPLY_PROP_TECHNOLOGY:
+		return info->technology != POWER_SUPPLY_TECHNOLOGY_UNKNOWN;
+	case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN:
+		return info->energy_full_design_uwh >= 0;
+	case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN:
+		return info->charge_full_design_uah >= 0;
+	case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
+		return info->voltage_min_design_uv >= 0;
+	case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN:
+		return info->voltage_max_design_uv >= 0;
+	case POWER_SUPPLY_PROP_PRECHARGE_CURRENT:
+		return info->precharge_current_ua >= 0;
+	case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT:
+		return info->charge_term_current_ua >= 0;
+	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX:
+		return info->constant_charge_current_max_ua >= 0;
+	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX:
+		return info->constant_charge_voltage_max_uv >= 0;
+	case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MIN:
+		return info->temp_ambient_alert_min > INT_MIN;
+	case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MAX:
+		return info->temp_ambient_alert_max < INT_MAX;
+	case POWER_SUPPLY_PROP_TEMP_ALERT_MIN:
+		return info->temp_alert_min > INT_MIN;
+	case POWER_SUPPLY_PROP_TEMP_ALERT_MAX:
+		return info->temp_alert_max < INT_MAX;
+	case POWER_SUPPLY_PROP_TEMP_MIN:
+		return info->temp_min > INT_MIN;
+	case POWER_SUPPLY_PROP_TEMP_MAX:
+		return info->temp_max < INT_MAX;
+	default:
+		return false;
 	}
 }
 EXPORT_SYMBOL_GPL(power_supply_battery_info_has_prop);
@@ -914,53 +914,53 @@ int power_supply_battery_info_get_prop(struct power_supply_battery_info *info,
 		return -EINVAL;
 
 	switch (psp) {
-		case POWER_SUPPLY_PROP_TECHNOLOGY:
-			val->intval = info->technology;
-			return 0;
-		case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN:
-			val->intval = info->energy_full_design_uwh;
-			return 0;
-		case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN:
-			val->intval = info->charge_full_design_uah;
-			return 0;
-		case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
-			val->intval = info->voltage_min_design_uv;
-			return 0;
-		case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN:
-			val->intval = info->voltage_max_design_uv;
-			return 0;
-		case POWER_SUPPLY_PROP_PRECHARGE_CURRENT:
-			val->intval = info->precharge_current_ua;
-			return 0;
-		case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT:
-			val->intval = info->charge_term_current_ua;
-			return 0;
-		case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX:
-			val->intval = info->constant_charge_current_max_ua;
-			return 0;
-		case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX:
-			val->intval = info->constant_charge_voltage_max_uv;
-			return 0;
-		case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MIN:
-			val->intval = info->temp_ambient_alert_min;
-			return 0;
-		case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MAX:
-			val->intval = info->temp_ambient_alert_max;
-			return 0;
-		case POWER_SUPPLY_PROP_TEMP_ALERT_MIN:
-			val->intval = info->temp_alert_min;
-			return 0;
-		case POWER_SUPPLY_PROP_TEMP_ALERT_MAX:
-			val->intval = info->temp_alert_max;
-			return 0;
-		case POWER_SUPPLY_PROP_TEMP_MIN:
-			val->intval = info->temp_min;
-			return 0;
-		case POWER_SUPPLY_PROP_TEMP_MAX:
-			val->intval = info->temp_max;
-			return 0;
-		default:
-			return -EINVAL;
+	case POWER_SUPPLY_PROP_TECHNOLOGY:
+		val->intval = info->technology;
+		return 0;
+	case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN:
+		val->intval = info->energy_full_design_uwh;
+		return 0;
+	case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN:
+		val->intval = info->charge_full_design_uah;
+		return 0;
+	case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
+		val->intval = info->voltage_min_design_uv;
+		return 0;
+	case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN:
+		val->intval = info->voltage_max_design_uv;
+		return 0;
+	case POWER_SUPPLY_PROP_PRECHARGE_CURRENT:
+		val->intval = info->precharge_current_ua;
+		return 0;
+	case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT:
+		val->intval = info->charge_term_current_ua;
+		return 0;
+	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX:
+		val->intval = info->constant_charge_current_max_ua;
+		return 0;
+	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX:
+		val->intval = info->constant_charge_voltage_max_uv;
+		return 0;
+	case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MIN:
+		val->intval = info->temp_ambient_alert_min;
+		return 0;
+	case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MAX:
+		val->intval = info->temp_ambient_alert_max;
+		return 0;
+	case POWER_SUPPLY_PROP_TEMP_ALERT_MIN:
+		val->intval = info->temp_alert_min;
+		return 0;
+	case POWER_SUPPLY_PROP_TEMP_ALERT_MAX:
+		val->intval = info->temp_alert_max;
+		return 0;
+	case POWER_SUPPLY_PROP_TEMP_MIN:
+		val->intval = info->temp_min;
+		return 0;
+	case POWER_SUPPLY_PROP_TEMP_MAX:
+		val->intval = info->temp_max;
+		return 0;
+	default:
+		return -EINVAL;
 	}
 }
 EXPORT_SYMBOL_GPL(power_supply_battery_info_get_prop);
@@ -1255,6 +1255,7 @@ EXPORT_SYMBOL_GPL(power_supply_powers);
 static void power_supply_dev_release(struct device *dev)
 {
 	struct power_supply *psy = to_power_supply(dev);
+
 	dev_dbg(dev, "%s\n", __func__);
 	kfree(psy);
 }
@@ -1636,6 +1637,6 @@ subsys_initcall(power_supply_class_init);
 module_exit(power_supply_class_exit);
 
 MODULE_DESCRIPTION("Universal power supply monitor class");
-MODULE_AUTHOR("Ian Molton <spyro@f2s.com>, "
-	      "Szabolcs Gyurko, "
-	      "Anton Vorontsov <cbou@mail.ru>");
+MODULE_AUTHOR("Ian Molton <spyro@f2s.com>");
+MODULE_AUTHOR("Szabolcs Gyurko");
+MODULE_AUTHOR("Anton Vorontsov <cbou@mail.ru>");
diff --git a/drivers/power/supply/qcom_pmi8998_charger.c b/drivers/power/supply/qcom_pmi8998_charger.c
index 8acf63ee6897..9bb777406013 100644
--- a/drivers/power/supply/qcom_pmi8998_charger.c
+++ b/drivers/power/supply/qcom_pmi8998_charger.c
@@ -972,10 +972,14 @@ static int smb2_probe(struct platform_device *pdev)
 	supply_config.of_node = pdev->dev.of_node;
 
 	desc = devm_kzalloc(chip->dev, sizeof(smb2_psy_desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
 	memcpy(desc, &smb2_psy_desc, sizeof(smb2_psy_desc));
 	desc->name =
 		devm_kasprintf(chip->dev, GFP_KERNEL, "%s-charger",
 			       (const char *)device_get_match_data(chip->dev));
+	if (!desc->name)
+		return -ENOMEM;
 
 	chip->chg_psy =
 		devm_power_supply_register(chip->dev, desc, &supply_config);
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index 9a4c720c88aa..f2728ee787d7 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -152,7 +152,7 @@ of_pwm_single_xlate(struct pwm_chip *chip, const struct of_phandle_args *args)
 	pwm->args.period = args->args[0];
 	pwm->args.polarity = PWM_POLARITY_NORMAL;
 
-	if (args->args_count == 2 && args->args[2] & PWM_POLARITY_INVERTED)
+	if (args->args_count == 2 && args->args[1] & PWM_POLARITY_INVERTED)
 		pwm->args.polarity = PWM_POLARITY_INVERSED;
 
 	return pwm;
diff --git a/drivers/pwm/pwm-bcm2835.c b/drivers/pwm/pwm-bcm2835.c
index 307c0bd5f885..283cf27f25ba 100644
--- a/drivers/pwm/pwm-bcm2835.c
+++ b/drivers/pwm/pwm-bcm2835.c
@@ -160,10 +160,8 @@ static int bcm2835_pwm_probe(struct platform_device *pdev)
 
 	ret = devm_add_action_or_reset(&pdev->dev, devm_clk_rate_exclusive_put,
 				       pc->clk);
-	if (ret) {
-		clk_rate_exclusive_put(pc->clk);
+	if (ret)
 		return ret;
-	}
 
 	pc->rate = clk_get_rate(pc->clk);
 	if (!pc->rate)
diff --git a/drivers/pwm/pwm-jz4740.c b/drivers/pwm/pwm-jz4740.c
index 80dcff237a15..3933418e551b 100644
--- a/drivers/pwm/pwm-jz4740.c
+++ b/drivers/pwm/pwm-jz4740.c
@@ -61,9 +61,10 @@ static int jz4740_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm)
 	snprintf(name, sizeof(name), "timer%u", pwm->hwpwm);
 
 	clk = clk_get(chip->dev, name);
-	if (IS_ERR(clk))
-		return dev_err_probe(chip->dev, PTR_ERR(clk),
-				     "Failed to get clock\n");
+	if (IS_ERR(clk)) {
+		dev_err(chip->dev, "error %pe: Failed to get clock\n", clk);
+		return PTR_ERR(clk);
+	}
 
 	err = clk_prepare_enable(clk);
 	if (err < 0) {
diff --git a/drivers/regulator/max5970-regulator.c b/drivers/regulator/max5970-regulator.c
index bc88a40a88d4..8bbcd983a74a 100644
--- a/drivers/regulator/max5970-regulator.c
+++ b/drivers/regulator/max5970-regulator.c
@@ -29,8 +29,8 @@ struct max5970_regulator {
 };
 
 enum max597x_regulator_id {
-	MAX597X_SW0,
-	MAX597X_SW1,
+	MAX597X_sw0,
+	MAX597X_sw1,
 };
 
 static int max5970_read_adc(struct regmap *regmap, int reg, long *val)
@@ -378,8 +378,8 @@ static int max597x_dt_parse(struct device_node *np,
 }
 
 static const struct regulator_desc regulators[] = {
-	MAX597X_SWITCH(SW0, MAX5970_REG_CHXEN, 0, "vss1"),
-	MAX597X_SWITCH(SW1, MAX5970_REG_CHXEN, 1, "vss2"),
+	MAX597X_SWITCH(sw0, MAX5970_REG_CHXEN, 0, "vss1"),
+	MAX597X_SWITCH(sw1, MAX5970_REG_CHXEN, 1, "vss2"),
 };
 
 static int max597x_regmap_read_clear(struct regmap *map, unsigned int reg,
@@ -392,7 +392,7 @@ static int max597x_regmap_read_clear(struct regmap *map, unsigned int reg,
 		return ret;
 
 	if (*val)
-		return regmap_write(map, reg, *val);
+		return regmap_write(map, reg, 0);
 
 	return 0;
 }
diff --git a/drivers/regulator/pwm-regulator.c b/drivers/regulator/pwm-regulator.c
index 698c420e0869..60cfcd741c2a 100644
--- a/drivers/regulator/pwm-regulator.c
+++ b/drivers/regulator/pwm-regulator.c
@@ -157,7 +157,17 @@ static int pwm_regulator_get_voltage(struct regulator_dev *rdev)
 
 	pwm_get_state(drvdata->pwm, &pstate);
 
+	if (!pstate.enabled) {
+		if (pstate.polarity == PWM_POLARITY_INVERSED)
+			pstate.duty_cycle = pstate.period;
+		else
+			pstate.duty_cycle = 0;
+	}
+
 	voltage = pwm_get_relative_duty_cycle(&pstate, duty_unit);
+	if (voltage < min(max_uV_duty, min_uV_duty) ||
+	    voltage > max(max_uV_duty, min_uV_duty))
+		return -ENOTRECOVERABLE;
 
 	/*
 	 * The dutycycle for min_uV might be greater than the one for max_uV.
@@ -313,6 +323,32 @@ static int pwm_regulator_init_continuous(struct platform_device *pdev,
 	return 0;
 }
 
+static int pwm_regulator_init_boot_on(struct platform_device *pdev,
+				      struct pwm_regulator_data *drvdata,
+				      const struct regulator_init_data *init_data)
+{
+	struct pwm_state pstate;
+
+	if (!init_data->constraints.boot_on || drvdata->enb_gpio)
+		return 0;
+
+	pwm_get_state(drvdata->pwm, &pstate);
+	if (pstate.enabled)
+		return 0;
+
+	/*
+	 * Update the duty cycle so the output does not change
+	 * when the regulator core enables the regulator (and
+	 * thus the PWM channel).
+	 */
+	if (pstate.polarity == PWM_POLARITY_INVERSED)
+		pstate.duty_cycle = pstate.period;
+	else
+		pstate.duty_cycle = 0;
+
+	return pwm_apply_might_sleep(drvdata->pwm, &pstate);
+}
+
 static int pwm_regulator_probe(struct platform_device *pdev)
 {
 	const struct regulator_init_data *init_data;
@@ -372,6 +408,13 @@ static int pwm_regulator_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	ret = pwm_regulator_init_boot_on(pdev, drvdata, init_data);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to apply boot_on settings: %d\n",
+			ret);
+		return ret;
+	}
+
 	regulator = devm_regulator_register(&pdev->dev,
 					    &drvdata->desc, &config);
 	if (IS_ERR(regulator)) {
diff --git a/drivers/regulator/rk808-regulator.c b/drivers/regulator/rk808-regulator.c
index e374fa6e5f28..d89ae7f16d7a 100644
--- a/drivers/regulator/rk808-regulator.c
+++ b/drivers/regulator/rk808-regulator.c
@@ -1017,14 +1017,14 @@ static const struct regulator_desc rk805_reg[] = {
 };
 
 static const struct linear_range rk806_buck_voltage_ranges[] = {
-	REGULATOR_LINEAR_RANGE(500000, 0, 160, 6250), /* 500mV ~ 1500mV */
-	REGULATOR_LINEAR_RANGE(1500000, 161, 237, 25000), /* 1500mV ~ 3400mV */
-	REGULATOR_LINEAR_RANGE(3400000, 238, 255, 0),
+	REGULATOR_LINEAR_RANGE(500000, 0, 159, 6250), /* 500mV ~ 1500mV */
+	REGULATOR_LINEAR_RANGE(1500000, 160, 235, 25000), /* 1500mV ~ 3400mV */
+	REGULATOR_LINEAR_RANGE(3400000, 236, 255, 0),
 };
 
 static const struct linear_range rk806_ldo_voltage_ranges[] = {
-	REGULATOR_LINEAR_RANGE(500000, 0, 232, 12500), /* 500mV ~ 3400mV */
-	REGULATOR_LINEAR_RANGE(3400000, 233, 255, 0), /* 500mV ~ 3400mV */
+	REGULATOR_LINEAR_RANGE(500000, 0, 231, 12500), /* 500mV ~ 3400mV */
+	REGULATOR_LINEAR_RANGE(3400000, 232, 255, 0),
 };
 
 static const struct regulator_desc rk806_reg[] = {
diff --git a/drivers/regulator/ti-abb-regulator.c b/drivers/regulator/ti-abb-regulator.c
index f48214e2c3b4..04133510e5af 100644
--- a/drivers/regulator/ti-abb-regulator.c
+++ b/drivers/regulator/ti-abb-regulator.c
@@ -726,9 +726,25 @@ static int ti_abb_probe(struct platform_device *pdev)
 			return PTR_ERR(abb->setup_reg);
 	}
 
-	abb->int_base = devm_platform_ioremap_resource_byname(pdev, "int-address");
-	if (IS_ERR(abb->int_base))
-		return PTR_ERR(abb->int_base);
+	pname = "int-address";
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, pname);
+	if (!res) {
+		dev_err(dev, "Missing '%s' IO resource\n", pname);
+		return -ENODEV;
+	}
+	/*
+	 * The MPU interrupt status register (PRM_IRQSTATUS_MPU) is
+	 * shared between regulator-abb-{ivahd,dspeve,gpu} driver
+	 * instances. Therefore use devm_ioremap() rather than
+	 * devm_platform_ioremap_resource_byname() to avoid busy
+	 * resource region conflicts.
+	 */
+	abb->int_base = devm_ioremap(dev, res->start,
+					     resource_size(res));
+	if (!abb->int_base) {
+		dev_err(dev, "Unable to map '%s'\n", pname);
+		return -ENOMEM;
+	}
 
 	/* Map Optional resources */
 	pname = "efuse-address";
diff --git a/drivers/remoteproc/imx_dsp_rproc.c b/drivers/remoteproc/imx_dsp_rproc.c
index 8fcda9b74545..a1c62d15f16c 100644
--- a/drivers/remoteproc/imx_dsp_rproc.c
+++ b/drivers/remoteproc/imx_dsp_rproc.c
@@ -940,6 +940,7 @@ static const struct rproc_ops imx_dsp_rproc_ops = {
 	.kick		= imx_dsp_rproc_kick,
 	.load		= imx_dsp_rproc_elf_load_segments,
 	.parse_fw	= imx_dsp_rproc_parse_fw,
+	.find_loaded_rsc_table = rproc_elf_find_loaded_rsc_table,
 	.sanity_check	= rproc_elf_sanity_check,
 	.get_boot_addr	= rproc_elf_get_boot_addr,
 };
diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c
index 913a5d2068e8..a9dd58608052 100644
--- a/drivers/remoteproc/qcom_q6v5_pas.c
+++ b/drivers/remoteproc/qcom_q6v5_pas.c
@@ -1165,6 +1165,22 @@ static const struct adsp_data sm8550_mpss_resource = {
 	.region_assign_idx = 2,
 };
 
+static const struct adsp_data sc7280_wpss_resource = {
+	.crash_reason_smem = 626,
+	.firmware_name = "wpss.mdt",
+	.pas_id = 6,
+	.auto_boot = true,
+	.proxy_pd_names = (char*[]){
+		"cx",
+		"mx",
+		NULL
+	},
+	.load_state = "wpss",
+	.ssr_name = "wpss",
+	.sysmon_name = "wpss",
+	.ssctl_id = 0x19,
+};
+
 static const struct of_device_id adsp_of_match[] = {
 	{ .compatible = "qcom,msm8226-adsp-pil", .data = &adsp_resource_init},
 	{ .compatible = "qcom,msm8953-adsp-pil", .data = &msm8996_adsp_resource},
@@ -1178,7 +1194,10 @@ static const struct of_device_id adsp_of_match[] = {
 	{ .compatible = "qcom,qcs404-wcss-pas", .data = &wcss_resource_init },
 	{ .compatible = "qcom,sc7180-adsp-pas", .data = &sm8250_adsp_resource},
 	{ .compatible = "qcom,sc7180-mpss-pas", .data = &mpss_resource_init},
+	{ .compatible = "qcom,sc7280-adsp-pas", .data = &sm8350_adsp_resource},
+	{ .compatible = "qcom,sc7280-cdsp-pas", .data = &sm6350_cdsp_resource},
 	{ .compatible = "qcom,sc7280-mpss-pas", .data = &mpss_resource_init},
+	{ .compatible = "qcom,sc7280-wpss-pas", .data = &sc7280_wpss_resource},
 	{ .compatible = "qcom,sc8180x-adsp-pas", .data = &sm8150_adsp_resource},
 	{ .compatible = "qcom,sc8180x-cdsp-pas", .data = &sm8150_cdsp_resource},
 	{ .compatible = "qcom,sc8180x-mpss-pas", .data = &sc8180x_mpss_resource},
diff --git a/drivers/remoteproc/ti_k3_dsp_remoteproc.c b/drivers/remoteproc/ti_k3_dsp_remoteproc.c
index ef8415a7cd54..ab882e3b7130 100644
--- a/drivers/remoteproc/ti_k3_dsp_remoteproc.c
+++ b/drivers/remoteproc/ti_k3_dsp_remoteproc.c
@@ -158,8 +158,8 @@ static void k3_dsp_rproc_kick(struct rproc *rproc, int vqid)
 	/* send the index of the triggered virtqueue in the mailbox payload */
 	ret = mbox_send_message(kproc->mbox, (void *)msg);
 	if (ret < 0)
-		dev_err(dev, "failed to send mailbox message, status = %d\n",
-			ret);
+		dev_err(dev, "failed to send mailbox message (%pe)\n",
+			ERR_PTR(ret));
 }
 
 /* Put the DSP processor into reset */
@@ -170,7 +170,7 @@ static int k3_dsp_rproc_reset(struct k3_dsp_rproc *kproc)
 
 	ret = reset_control_assert(kproc->reset);
 	if (ret) {
-		dev_err(dev, "local-reset assert failed, ret = %d\n", ret);
+		dev_err(dev, "local-reset assert failed (%pe)\n", ERR_PTR(ret));
 		return ret;
 	}
 
@@ -180,7 +180,7 @@ static int k3_dsp_rproc_reset(struct k3_dsp_rproc *kproc)
 	ret = kproc->ti_sci->ops.dev_ops.put_device(kproc->ti_sci,
 						    kproc->ti_sci_id);
 	if (ret) {
-		dev_err(dev, "module-reset assert failed, ret = %d\n", ret);
+		dev_err(dev, "module-reset assert failed (%pe)\n", ERR_PTR(ret));
 		if (reset_control_deassert(kproc->reset))
 			dev_warn(dev, "local-reset deassert back failed\n");
 	}
@@ -200,14 +200,14 @@ static int k3_dsp_rproc_release(struct k3_dsp_rproc *kproc)
 	ret = kproc->ti_sci->ops.dev_ops.get_device(kproc->ti_sci,
 						    kproc->ti_sci_id);
 	if (ret) {
-		dev_err(dev, "module-reset deassert failed, ret = %d\n", ret);
+		dev_err(dev, "module-reset deassert failed (%pe)\n", ERR_PTR(ret));
 		return ret;
 	}
 
 lreset:
 	ret = reset_control_deassert(kproc->reset);
 	if (ret) {
-		dev_err(dev, "local-reset deassert failed, ret = %d\n", ret);
+		dev_err(dev, "local-reset deassert failed, (%pe)\n", ERR_PTR(ret));
 		if (kproc->ti_sci->ops.dev_ops.put_device(kproc->ti_sci,
 							  kproc->ti_sci_id))
 			dev_warn(dev, "module-reset assert back failed\n");
@@ -246,7 +246,7 @@ static int k3_dsp_rproc_request_mbox(struct rproc *rproc)
 	 */
 	ret = mbox_send_message(kproc->mbox, (void *)RP_MBOX_ECHO_REQUEST);
 	if (ret < 0) {
-		dev_err(dev, "mbox_send_message failed: %d\n", ret);
+		dev_err(dev, "mbox_send_message failed (%pe)\n", ERR_PTR(ret));
 		mbox_free_channel(kproc->mbox);
 		return ret;
 	}
@@ -272,8 +272,8 @@ static int k3_dsp_rproc_prepare(struct rproc *rproc)
 	ret = kproc->ti_sci->ops.dev_ops.get_device(kproc->ti_sci,
 						    kproc->ti_sci_id);
 	if (ret)
-		dev_err(dev, "module-reset deassert failed, cannot enable internal RAM loading, ret = %d\n",
-			ret);
+		dev_err(dev, "module-reset deassert failed, cannot enable internal RAM loading (%pe)\n",
+			ERR_PTR(ret));
 
 	return ret;
 }
@@ -296,7 +296,7 @@ static int k3_dsp_rproc_unprepare(struct rproc *rproc)
 	ret = kproc->ti_sci->ops.dev_ops.put_device(kproc->ti_sci,
 						    kproc->ti_sci_id);
 	if (ret)
-		dev_err(dev, "module-reset assert failed, ret = %d\n", ret);
+		dev_err(dev, "module-reset assert failed (%pe)\n", ERR_PTR(ret));
 
 	return ret;
 }
@@ -561,9 +561,9 @@ static int k3_dsp_reserved_mem_init(struct k3_dsp_rproc *kproc)
 
 	num_rmems = of_property_count_elems_of_size(np, "memory-region",
 						    sizeof(phandle));
-	if (num_rmems <= 0) {
-		dev_err(dev, "device does not reserved memory regions, ret = %d\n",
-			num_rmems);
+	if (num_rmems < 0) {
+		dev_err(dev, "device does not reserved memory regions (%pe)\n",
+			ERR_PTR(num_rmems));
 		return -EINVAL;
 	}
 	if (num_rmems < 2) {
@@ -575,8 +575,8 @@ static int k3_dsp_reserved_mem_init(struct k3_dsp_rproc *kproc)
 	/* use reserved memory region 0 for vring DMA allocations */
 	ret = of_reserved_mem_device_init_by_idx(dev, np, 0);
 	if (ret) {
-		dev_err(dev, "device cannot initialize DMA pool, ret = %d\n",
-			ret);
+		dev_err(dev, "device cannot initialize DMA pool (%pe)\n",
+			ERR_PTR(ret));
 		return ret;
 	}
 
@@ -687,11 +687,8 @@ static int k3_dsp_rproc_probe(struct platform_device *pdev)
 		return -ENODEV;
 
 	ret = rproc_of_parse_firmware(dev, 0, &fw_name);
-	if (ret) {
-		dev_err(dev, "failed to parse firmware-name property, ret = %d\n",
-			ret);
-		return ret;
-	}
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to parse firmware-name property\n");
 
 	rproc = rproc_alloc(dev, dev_name(dev), &k3_dsp_rproc_ops, fw_name,
 			    sizeof(*kproc));
@@ -711,39 +708,35 @@ static int k3_dsp_rproc_probe(struct platform_device *pdev)
 
 	kproc->ti_sci = ti_sci_get_by_phandle(np, "ti,sci");
 	if (IS_ERR(kproc->ti_sci)) {
-		ret = PTR_ERR(kproc->ti_sci);
-		if (ret != -EPROBE_DEFER) {
-			dev_err(dev, "failed to get ti-sci handle, ret = %d\n",
-				ret);
-		}
+		ret = dev_err_probe(dev, PTR_ERR(kproc->ti_sci),
+				    "failed to get ti-sci handle\n");
 		kproc->ti_sci = NULL;
 		goto free_rproc;
 	}
 
 	ret = of_property_read_u32(np, "ti,sci-dev-id", &kproc->ti_sci_id);
 	if (ret) {
-		dev_err(dev, "missing 'ti,sci-dev-id' property\n");
+		dev_err_probe(dev, ret, "missing 'ti,sci-dev-id' property\n");
 		goto put_sci;
 	}
 
 	kproc->reset = devm_reset_control_get_exclusive(dev, NULL);
 	if (IS_ERR(kproc->reset)) {
-		ret = PTR_ERR(kproc->reset);
-		dev_err(dev, "failed to get reset, status = %d\n", ret);
+		ret = dev_err_probe(dev, PTR_ERR(kproc->reset),
+				    "failed to get reset\n");
 		goto put_sci;
 	}
 
 	kproc->tsp = k3_dsp_rproc_of_get_tsp(dev, kproc->ti_sci);
 	if (IS_ERR(kproc->tsp)) {
-		dev_err(dev, "failed to construct ti-sci proc control, ret = %d\n",
-			ret);
-		ret = PTR_ERR(kproc->tsp);
+		ret = dev_err_probe(dev, PTR_ERR(kproc->tsp),
+				    "failed to construct ti-sci proc control\n");
 		goto put_sci;
 	}
 
 	ret = ti_sci_proc_request(kproc->tsp);
 	if (ret < 0) {
-		dev_err(dev, "ti_sci_proc_request failed, ret = %d\n", ret);
+		dev_err_probe(dev, ret, "ti_sci_proc_request failed\n");
 		goto free_tsp;
 	}
 
@@ -753,15 +746,14 @@ static int k3_dsp_rproc_probe(struct platform_device *pdev)
 
 	ret = k3_dsp_reserved_mem_init(kproc);
 	if (ret) {
-		dev_err(dev, "reserved memory init failed, ret = %d\n", ret);
+		dev_err_probe(dev, ret, "reserved memory init failed\n");
 		goto release_tsp;
 	}
 
 	ret = kproc->ti_sci->ops.dev_ops.is_on(kproc->ti_sci, kproc->ti_sci_id,
 					       NULL, &p_state);
 	if (ret) {
-		dev_err(dev, "failed to get initial state, mode cannot be determined, ret = %d\n",
-			ret);
+		dev_err_probe(dev, ret, "failed to get initial state, mode cannot be determined\n");
 		goto release_mem;
 	}
 
@@ -787,8 +779,7 @@ static int k3_dsp_rproc_probe(struct platform_device *pdev)
 		if (data->uses_lreset) {
 			ret = reset_control_status(kproc->reset);
 			if (ret < 0) {
-				dev_err(dev, "failed to get reset status, status = %d\n",
-					ret);
+				dev_err_probe(dev, ret, "failed to get reset status\n");
 				goto release_mem;
 			} else if (ret == 0) {
 				dev_warn(dev, "local reset is deasserted for device\n");
@@ -799,8 +790,7 @@ static int k3_dsp_rproc_probe(struct platform_device *pdev)
 
 	ret = rproc_add(rproc);
 	if (ret) {
-		dev_err(dev, "failed to add register device with remoteproc core, status = %d\n",
-			ret);
+		dev_err_probe(dev, ret, "failed to add register device with remoteproc core\n");
 		goto release_mem;
 	}
 
@@ -813,19 +803,19 @@ release_mem:
 release_tsp:
 	ret1 = ti_sci_proc_release(kproc->tsp);
 	if (ret1)
-		dev_err(dev, "failed to release proc, ret = %d\n", ret1);
+		dev_err(dev, "failed to release proc (%pe)\n", ERR_PTR(ret1));
 free_tsp:
 	kfree(kproc->tsp);
 put_sci:
 	ret1 = ti_sci_put_handle(kproc->ti_sci);
 	if (ret1)
-		dev_err(dev, "failed to put ti_sci handle, ret = %d\n", ret1);
+		dev_err(dev, "failed to put ti_sci handle (%pe)\n", ERR_PTR(ret1));
 free_rproc:
 	rproc_free(rproc);
 	return ret;
 }
 
-static int k3_dsp_rproc_remove(struct platform_device *pdev)
+static void k3_dsp_rproc_remove(struct platform_device *pdev)
 {
 	struct k3_dsp_rproc *kproc = platform_get_drvdata(pdev);
 	struct rproc *rproc = kproc->rproc;
@@ -835,8 +825,9 @@ static int k3_dsp_rproc_remove(struct platform_device *pdev)
 	if (rproc->state == RPROC_ATTACHED) {
 		ret = rproc_detach(rproc);
 		if (ret) {
-			dev_err(dev, "failed to detach proc, ret = %d\n", ret);
-			return ret;
+			/* Note this error path leaks resources */
+			dev_err(dev, "failed to detach proc (%pe)\n", ERR_PTR(ret));
+			return;
 		}
 	}
 
@@ -844,18 +835,16 @@ static int k3_dsp_rproc_remove(struct platform_device *pdev)
 
 	ret = ti_sci_proc_release(kproc->tsp);
 	if (ret)
-		dev_err(dev, "failed to release proc, ret = %d\n", ret);
+		dev_err(dev, "failed to release proc (%pe)\n", ERR_PTR(ret));
 
 	kfree(kproc->tsp);
 
 	ret = ti_sci_put_handle(kproc->ti_sci);
 	if (ret)
-		dev_err(dev, "failed to put ti_sci handle, ret = %d\n", ret);
+		dev_err(dev, "failed to put ti_sci handle (%pe)\n", ERR_PTR(ret));
 
 	k3_dsp_reserved_mem_exit(kproc);
 	rproc_free(kproc->rproc);
-
-	return 0;
 }
 
 static const struct k3_dsp_mem_data c66_mems[] = {
@@ -906,7 +895,7 @@ MODULE_DEVICE_TABLE(of, k3_dsp_of_match);
 
 static struct platform_driver k3_dsp_rproc_driver = {
 	.probe	= k3_dsp_rproc_probe,
-	.remove	= k3_dsp_rproc_remove,
+	.remove_new = k3_dsp_rproc_remove,
 	.driver	= {
 		.name = "k3-dsp-rproc",
 		.of_match_table = k3_dsp_of_match,
diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c
index dc87965f8164..1062939c3264 100644
--- a/drivers/rpmsg/virtio_rpmsg_bus.c
+++ b/drivers/rpmsg/virtio_rpmsg_bus.c
@@ -378,6 +378,7 @@ static void virtio_rpmsg_release_device(struct device *dev)
 	struct rpmsg_device *rpdev = to_rpmsg_device(dev);
 	struct virtio_rpmsg_channel *vch = to_virtio_rpmsg_channel(rpdev);
 
+	kfree(rpdev->driver_override);
 	kfree(vch);
 }
 
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 3814e0845e77..e37a4341f442 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -373,6 +373,19 @@ config RTC_DRV_MAX8997
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-max8997.
 
+config RTC_DRV_MAX31335
+	tristate "Analog Devices MAX31335"
+	depends on I2C
+	depends on COMMON_CLK
+	depends on HWMON || HWMON=n
+	select REGMAP_I2C
+	help
+	  If you say yes here you get support for the Analog Devices
+	  MAX31335.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called rtc-max31335.
+
 config RTC_DRV_MAX77686
 	tristate "Maxim MAX77686"
 	depends on MFD_MAX77686 || MFD_MAX77620 || MFD_MAX77714 || COMPILE_TEST
@@ -578,6 +591,18 @@ config RTC_DRV_TPS6586X
 	  along with alarm. This driver supports the RTC driver for
 	  the TPS6586X RTC module.
 
+config RTC_DRV_TPS6594
+	tristate "TI TPS6594 RTC driver"
+	depends on MFD_TPS6594
+	default MFD_TPS6594
+	help
+	  TI Power Management IC TPS6594 supports RTC functionality
+	  along with alarm. This driver supports the RTC driver for
+	  the TPS6594 RTC module.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called rtc-tps6594.
+
 config RTC_DRV_TPS65910
 	tristate "TI TPS65910 RTC driver"
 	depends on MFD_TPS65910
@@ -1705,6 +1730,7 @@ config RTC_DRV_LPC24XX
 	tristate "NXP RTC for LPC178x/18xx/408x/43xx"
 	depends on ARCH_LPC18XX || COMPILE_TEST
 	depends on OF && HAS_IOMEM
+	depends on COMMON_CLK
 	help
 	  This enables support for the NXP RTC found which can be found on
 	  NXP LPC178x/18xx/408x/43xx devices.
@@ -1930,6 +1956,17 @@ config RTC_DRV_TI_K3
 	  This driver can also be built as a module, if so, the module
 	  will be called "rtc-ti-k3".
 
+config RTC_DRV_MA35D1
+	tristate "Nuvoton MA35D1 RTC"
+	depends on ARCH_MA35 || COMPILE_TEST
+	select REGMAP_MMIO
+	help
+	   If you say yes here you get support for the Nuvoton MA35D1
+	   On-Chip Real Time Clock.
+
+	   This driver can also be built as a module, if so, the module
+	   will be called "rtc-ma35d1".
+
 comment "HID Sensor RTC drivers"
 
 config RTC_DRV_HID_SENSOR_TIME
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index 7b03c3abfd78..6efff381c484 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -88,6 +88,8 @@ obj-$(CONFIG_RTC_DRV_M41T94)	+= rtc-m41t94.o
 obj-$(CONFIG_RTC_DRV_M48T35)	+= rtc-m48t35.o
 obj-$(CONFIG_RTC_DRV_M48T59)	+= rtc-m48t59.o
 obj-$(CONFIG_RTC_DRV_M48T86)	+= rtc-m48t86.o
+obj-$(CONFIG_RTC_DRV_MA35D1)	+= rtc-ma35d1.o
+obj-$(CONFIG_RTC_DRV_MAX31335)	+= rtc-max31335.o
 obj-$(CONFIG_RTC_DRV_MAX6900)	+= rtc-max6900.o
 obj-$(CONFIG_RTC_DRV_MAX6902)	+= rtc-max6902.o
 obj-$(CONFIG_RTC_DRV_MAX6916)	+= rtc-max6916.o
@@ -176,6 +178,7 @@ obj-$(CONFIG_RTC_DRV_TEGRA)	+= rtc-tegra.o
 obj-$(CONFIG_RTC_DRV_TEST)	+= rtc-test.o
 obj-$(CONFIG_RTC_DRV_TI_K3)	+= rtc-ti-k3.o
 obj-$(CONFIG_RTC_DRV_TPS6586X)	+= rtc-tps6586x.o
+obj-$(CONFIG_RTC_DRV_TPS6594)	+= rtc-tps6594.o
 obj-$(CONFIG_RTC_DRV_TPS65910)	+= rtc-tps65910.o
 obj-$(CONFIG_RTC_DRV_TWL4030)	+= rtc-twl.o
 obj-$(CONFIG_RTC_DRV_VT8500)	+= rtc-vt8500.o
diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c
index edfd942f8c54..921ee1827974 100644
--- a/drivers/rtc/class.c
+++ b/drivers/rtc/class.c
@@ -256,7 +256,7 @@ static int rtc_device_get_id(struct device *dev)
 		of_id = of_alias_get_id(dev->parent->of_node, "rtc");
 
 	if (of_id >= 0) {
-		id = ida_simple_get(&rtc_ida, of_id, of_id + 1, GFP_KERNEL);
+		id = ida_alloc_range(&rtc_ida, of_id, of_id, GFP_KERNEL);
 		if (id < 0)
 			dev_warn(dev, "/aliases ID %d not available\n", of_id);
 	}
diff --git a/drivers/rtc/lib_test.c b/drivers/rtc/lib_test.c
index d5caf36c56cd..225c859d6da5 100644
--- a/drivers/rtc/lib_test.c
+++ b/drivers/rtc/lib_test.c
@@ -54,7 +54,7 @@ static void rtc_time64_to_tm_test_date_range(struct kunit *test)
 
 		days = div_s64(secs, 86400);
 
-		#define FAIL_MSG "%d/%02d/%02d (%2d) : %ld", \
+		#define FAIL_MSG "%d/%02d/%02d (%2d) : %lld", \
 			year, month, mday, yday, days
 
 		KUNIT_ASSERT_EQ_MSG(test, year - 1900, result.tm_year, FAIL_MSG);
diff --git a/drivers/rtc/rtc-ac100.c b/drivers/rtc/rtc-ac100.c
index eaf2c9ab9661..fa642bba3cee 100644
--- a/drivers/rtc/rtc-ac100.c
+++ b/drivers/rtc/rtc-ac100.c
@@ -99,7 +99,7 @@ struct ac100_rtc_dev {
 	struct clk_hw_onecell_data *clk_data;
 };
 
-/**
+/*
  * Clock controls for 3 clock output pins
  */
 
@@ -378,7 +378,7 @@ static void ac100_rtc_unregister_clks(struct ac100_rtc_dev *chip)
 	clk_unregister_fixed_rate(chip->rtc_32k_clk->clk);
 }
 
-/**
+/*
  * RTC related bits
  */
 static int ac100_rtc_get_time(struct device *dev, struct rtc_time *rtc_tm)
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index 228fb2d11c70..7d99cd2c37a0 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -231,7 +231,7 @@ static int cmos_read_time(struct device *dev, struct rtc_time *t)
 	if (!pm_trace_rtc_valid())
 		return -EIO;
 
-	ret = mc146818_get_time(t);
+	ret = mc146818_get_time(t, 1000);
 	if (ret < 0) {
 		dev_err_ratelimited(dev, "unable to read current time\n");
 		return ret;
@@ -292,7 +292,7 @@ static int cmos_read_alarm(struct device *dev, struct rtc_wkalrm *t)
 
 	/* This not only a rtc_op, but also called directly */
 	if (!is_valid_irq(cmos->irq))
-		return -EIO;
+		return -ETIMEDOUT;
 
 	/* Basic alarms only support hour, minute, and seconds fields.
 	 * Some also support day and month, for alarms up to a year in
@@ -307,7 +307,7 @@ static int cmos_read_alarm(struct device *dev, struct rtc_wkalrm *t)
 	 *
 	 * Use the mc146818_avoid_UIP() function to avoid this.
 	 */
-	if (!mc146818_avoid_UIP(cmos_read_alarm_callback, &p))
+	if (!mc146818_avoid_UIP(cmos_read_alarm_callback, 10, &p))
 		return -EIO;
 
 	if (!(p.rtc_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
@@ -556,8 +556,8 @@ static int cmos_set_alarm(struct device *dev, struct rtc_wkalrm *t)
 	 *
 	 * Use mc146818_avoid_UIP() to avoid this.
 	 */
-	if (!mc146818_avoid_UIP(cmos_set_alarm_callback, &p))
-		return -EIO;
+	if (!mc146818_avoid_UIP(cmos_set_alarm_callback, 10, &p))
+		return -ETIMEDOUT;
 
 	cmos->alarm_expires = rtc_tm_to_time64(&t->time);
 
@@ -818,18 +818,24 @@ static void rtc_wake_off(struct device *dev)
 }
 
 #ifdef CONFIG_X86
-/* Enable use_acpi_alarm mode for Intel platforms no earlier than 2015 */
 static void use_acpi_alarm_quirks(void)
 {
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_INTEL:
+		if (dmi_get_bios_year() < 2015)
+			return;
+		break;
+	case X86_VENDOR_AMD:
+	case X86_VENDOR_HYGON:
+		if (dmi_get_bios_year() < 2021)
+			return;
+		break;
+	default:
 		return;
-
+	}
 	if (!is_hpet_enabled())
 		return;
 
-	if (dmi_get_bios_year() < 2015)
-		return;
-
 	use_acpi_alarm = true;
 }
 #else
diff --git a/drivers/rtc/rtc-da9063.c b/drivers/rtc/rtc-da9063.c
index 2f5d60622564..859397541f29 100644
--- a/drivers/rtc/rtc-da9063.c
+++ b/drivers/rtc/rtc-da9063.c
@@ -377,7 +377,6 @@ static int da9063_rtc_probe(struct platform_device *pdev)
 {
 	struct da9063_compatible_rtc *rtc;
 	const struct da9063_compatible_rtc_regmap *config;
-	const struct of_device_id *match;
 	int irq_alarm;
 	u8 data[RTC_DATA_LEN];
 	int ret;
@@ -385,14 +384,11 @@ static int da9063_rtc_probe(struct platform_device *pdev)
 	if (!pdev->dev.of_node)
 		return -ENXIO;
 
-	match = of_match_node(da9063_compatible_reg_id_table,
-			      pdev->dev.of_node);
-
 	rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL);
 	if (!rtc)
 		return -ENOMEM;
 
-	rtc->config = match->data;
+	rtc->config = device_get_match_data(&pdev->dev);
 	if (of_device_is_compatible(pdev->dev.of_node, "dlg,da9063-rtc")) {
 		struct da9063 *chip = dev_get_drvdata(pdev->dev.parent);
 
@@ -411,57 +407,49 @@ static int da9063_rtc_probe(struct platform_device *pdev)
 				 config->rtc_enable_reg,
 				 config->rtc_enable_mask,
 				 config->rtc_enable_mask);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to enable RTC\n");
-		return ret;
-	}
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret, "Failed to enable RTC\n");
 
 	ret = regmap_update_bits(rtc->regmap,
 				 config->rtc_enable_32k_crystal_reg,
 				 config->rtc_crystal_mask,
 				 config->rtc_crystal_mask);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to run 32kHz oscillator\n");
-		return ret;
-	}
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret,
+				     "Failed to run 32kHz oscillator\n");
 
 	ret = regmap_update_bits(rtc->regmap,
 				 config->rtc_alarm_secs_reg,
 				 config->rtc_alarm_status_mask,
 				 0);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to access RTC alarm register\n");
-		return ret;
-	}
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret,
+				     "Failed to access RTC alarm register\n");
 
 	ret = regmap_update_bits(rtc->regmap,
 				 config->rtc_alarm_secs_reg,
 				 DA9063_ALARM_STATUS_ALARM,
 				 DA9063_ALARM_STATUS_ALARM);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to access RTC alarm register\n");
-		return ret;
-	}
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret,
+				     "Failed to access RTC alarm register\n");
 
 	ret = regmap_update_bits(rtc->regmap,
 				 config->rtc_alarm_year_reg,
 				 config->rtc_tick_on_mask,
 				 0);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to disable TICKs\n");
-		return ret;
-	}
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret,
+				     "Failed to disable TICKs\n");
 
 	data[RTC_SEC] = 0;
 	ret = regmap_bulk_read(rtc->regmap,
 			       config->rtc_alarm_secs_reg,
 			       &data[config->rtc_data_start],
 			       config->rtc_alarm_len);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to read initial alarm data: %d\n",
-			ret);
-		return ret;
-	}
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret,
+				     "Failed to read initial alarm data\n");
 
 	platform_set_drvdata(pdev, rtc);
 
@@ -485,25 +473,29 @@ static int da9063_rtc_probe(struct platform_device *pdev)
 		clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->rtc_dev->features);
 	}
 
-	irq_alarm = platform_get_irq_byname(pdev, "ALARM");
-	if (irq_alarm < 0)
+	irq_alarm = platform_get_irq_byname_optional(pdev, "ALARM");
+	if (irq_alarm >= 0) {
+		ret = devm_request_threaded_irq(&pdev->dev, irq_alarm, NULL,
+						da9063_alarm_event,
+						IRQF_TRIGGER_LOW | IRQF_ONESHOT,
+						"ALARM", rtc);
+		if (ret)
+			dev_err(&pdev->dev,
+				"Failed to request ALARM IRQ %d: %d\n",
+				irq_alarm, ret);
+
+		ret = dev_pm_set_wake_irq(&pdev->dev, irq_alarm);
+		if (ret)
+			dev_warn(&pdev->dev,
+				 "Failed to set IRQ %d as a wake IRQ: %d\n",
+				 irq_alarm, ret);
+
+		device_init_wakeup(&pdev->dev, true);
+	}  else if (irq_alarm != -ENXIO) {
 		return irq_alarm;
-
-	ret = devm_request_threaded_irq(&pdev->dev, irq_alarm, NULL,
-					da9063_alarm_event,
-					IRQF_TRIGGER_LOW | IRQF_ONESHOT,
-					"ALARM", rtc);
-	if (ret)
-		dev_err(&pdev->dev, "Failed to request ALARM IRQ %d: %d\n",
-			irq_alarm, ret);
-
-	ret = dev_pm_set_wake_irq(&pdev->dev, irq_alarm);
-	if (ret)
-		dev_warn(&pdev->dev,
-			 "Failed to set IRQ %d as a wake IRQ: %d\n",
-			 irq_alarm, ret);
-
-	device_init_wakeup(&pdev->dev, true);
+	} else {
+		clear_bit(RTC_FEATURE_ALARM, rtc->rtc_dev->features);
+	}
 
 	return devm_rtc_register_device(rtc->rtc_dev);
 }
diff --git a/drivers/rtc/rtc-ds3232.c b/drivers/rtc/rtc-ds3232.c
index 89d7b085f721..1485a6ae51e6 100644
--- a/drivers/rtc/rtc-ds3232.c
+++ b/drivers/rtc/rtc-ds3232.c
@@ -536,6 +536,8 @@ static int ds3232_probe(struct device *dev, struct regmap *regmap, int irq,
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_I2C)
+
 #ifdef CONFIG_PM_SLEEP
 static int ds3232_suspend(struct device *dev)
 {
@@ -564,8 +566,6 @@ static const struct dev_pm_ops ds3232_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(ds3232_suspend, ds3232_resume)
 };
 
-#if IS_ENABLED(CONFIG_I2C)
-
 static int ds3232_i2c_probe(struct i2c_client *client)
 {
 	struct regmap *regmap;
diff --git a/drivers/rtc/rtc-ma35d1.c b/drivers/rtc/rtc-ma35d1.c
new file mode 100644
index 000000000000..cfcfc28060f6
--- /dev/null
+++ b/drivers/rtc/rtc-ma35d1.c
@@ -0,0 +1,304 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * RTC driver for Nuvoton MA35D1
+ *
+ * Copyright (C) 2023 Nuvoton Technology Corp.
+ */
+
+#include <linux/bcd.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/rtc.h>
+
+/* MA35D1 RTC Control Registers */
+#define MA35_REG_RTC_INIT	0x00
+#define MA35_REG_RTC_SINFASTS	0x04
+#define MA35_REG_RTC_FREQADJ	0x08
+#define MA35_REG_RTC_TIME	0x0c
+#define MA35_REG_RTC_CAL	0x10
+#define MA35_REG_RTC_CLKFMT	0x14
+#define MA35_REG_RTC_WEEKDAY	0x18
+#define MA35_REG_RTC_TALM	0x1c
+#define MA35_REG_RTC_CALM	0x20
+#define MA35_REG_RTC_LEAPYEAR	0x24
+#define MA35_REG_RTC_INTEN	0x28
+#define MA35_REG_RTC_INTSTS	0x2c
+
+/* register MA35_REG_RTC_INIT */
+#define RTC_INIT_ACTIVE		BIT(0)
+#define RTC_INIT_MAGIC_CODE	0xa5eb1357
+
+/* register MA35_REG_RTC_CLKFMT */
+#define RTC_CLKFMT_24HEN	BIT(0)
+#define RTC_CLKFMT_DCOMPEN	BIT(16)
+
+/* register MA35_REG_RTC_INTEN */
+#define RTC_INTEN_ALMIEN	BIT(0)
+#define RTC_INTEN_UIEN		BIT(1)
+#define RTC_INTEN_CLKFIEN	BIT(24)
+#define RTC_INTEN_CLKSTIEN	BIT(25)
+
+/* register MA35_REG_RTC_INTSTS */
+#define RTC_INTSTS_ALMIF	BIT(0)
+#define RTC_INTSTS_UIF		BIT(1)
+#define RTC_INTSTS_CLKFIF	BIT(24)
+#define RTC_INTSTS_CLKSTIF	BIT(25)
+
+#define RTC_INIT_TIMEOUT	250
+
+struct ma35_rtc {
+	int irq_num;
+	void __iomem *rtc_reg;
+	struct rtc_device *rtcdev;
+};
+
+static u32 rtc_reg_read(struct ma35_rtc *p, u32 offset)
+{
+	return __raw_readl(p->rtc_reg + offset);
+}
+
+static inline void rtc_reg_write(struct ma35_rtc *p, u32 offset, u32 value)
+{
+	__raw_writel(value, p->rtc_reg + offset);
+}
+
+static irqreturn_t ma35d1_rtc_interrupt(int irq, void *data)
+{
+	struct ma35_rtc *rtc = (struct ma35_rtc *)data;
+	unsigned long events = 0, rtc_irq;
+
+	rtc_irq = rtc_reg_read(rtc, MA35_REG_RTC_INTSTS);
+
+	if (rtc_irq & RTC_INTSTS_ALMIF) {
+		rtc_reg_write(rtc, MA35_REG_RTC_INTSTS, RTC_INTSTS_ALMIF);
+		events |= RTC_AF | RTC_IRQF;
+	}
+
+	rtc_update_irq(rtc->rtcdev, 1, events);
+
+	return IRQ_HANDLED;
+}
+
+static int ma35d1_rtc_init(struct ma35_rtc *rtc, u32 ms_timeout)
+{
+	const unsigned long timeout = jiffies + msecs_to_jiffies(ms_timeout);
+
+	do {
+		if (rtc_reg_read(rtc, MA35_REG_RTC_INIT) & RTC_INIT_ACTIVE)
+			return 0;
+
+		rtc_reg_write(rtc, MA35_REG_RTC_INIT, RTC_INIT_MAGIC_CODE);
+
+		mdelay(1);
+
+	} while (time_before(jiffies, timeout));
+
+	return -ETIMEDOUT;
+}
+
+static int ma35d1_alarm_irq_enable(struct device *dev, u32 enabled)
+{
+	struct ma35_rtc *rtc = dev_get_drvdata(dev);
+	u32 reg_ien;
+
+	reg_ien = rtc_reg_read(rtc, MA35_REG_RTC_INTEN);
+
+	if (enabled)
+		rtc_reg_write(rtc, MA35_REG_RTC_INTEN, reg_ien | RTC_INTEN_ALMIEN);
+	else
+		rtc_reg_write(rtc, MA35_REG_RTC_INTEN, reg_ien & ~RTC_INTEN_ALMIEN);
+
+	return 0;
+}
+
+static int ma35d1_rtc_read_time(struct device *dev, struct rtc_time *tm)
+{
+	struct ma35_rtc *rtc = dev_get_drvdata(dev);
+	u32 time, cal, wday;
+
+	do {
+		time = rtc_reg_read(rtc, MA35_REG_RTC_TIME);
+		cal  = rtc_reg_read(rtc, MA35_REG_RTC_CAL);
+		wday = rtc_reg_read(rtc, MA35_REG_RTC_WEEKDAY);
+	} while (time != rtc_reg_read(rtc, MA35_REG_RTC_TIME) ||
+		 cal != rtc_reg_read(rtc, MA35_REG_RTC_CAL));
+
+	tm->tm_mday = bcd2bin(cal >> 0);
+	tm->tm_wday = wday;
+	tm->tm_mon = bcd2bin(cal >> 8);
+	tm->tm_mon = tm->tm_mon - 1;
+	tm->tm_year = bcd2bin(cal >> 16) + 100;
+
+	tm->tm_sec = bcd2bin(time >> 0);
+	tm->tm_min = bcd2bin(time >> 8);
+	tm->tm_hour = bcd2bin(time >> 16);
+
+	return rtc_valid_tm(tm);
+}
+
+static int ma35d1_rtc_set_time(struct device *dev, struct rtc_time *tm)
+{
+	struct ma35_rtc *rtc = dev_get_drvdata(dev);
+	u32 val;
+
+	val = bin2bcd(tm->tm_mday) << 0 | bin2bcd(tm->tm_mon + 1) << 8 |
+	      bin2bcd(tm->tm_year - 100) << 16;
+	rtc_reg_write(rtc, MA35_REG_RTC_CAL, val);
+
+	val = bin2bcd(tm->tm_sec) << 0 | bin2bcd(tm->tm_min) << 8 |
+	      bin2bcd(tm->tm_hour) << 16;
+	rtc_reg_write(rtc, MA35_REG_RTC_TIME, val);
+
+	val = tm->tm_wday;
+	rtc_reg_write(rtc, MA35_REG_RTC_WEEKDAY, val);
+
+	return 0;
+}
+
+static int ma35d1_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct ma35_rtc *rtc = dev_get_drvdata(dev);
+	u32 talm, calm;
+
+	talm = rtc_reg_read(rtc, MA35_REG_RTC_TALM);
+	calm = rtc_reg_read(rtc, MA35_REG_RTC_CALM);
+
+	alrm->time.tm_mday = bcd2bin(calm >> 0);
+	alrm->time.tm_mon = bcd2bin(calm >> 8);
+	alrm->time.tm_mon = alrm->time.tm_mon - 1;
+
+	alrm->time.tm_year = bcd2bin(calm >> 16) + 100;
+
+	alrm->time.tm_sec = bcd2bin(talm >> 0);
+	alrm->time.tm_min = bcd2bin(talm >> 8);
+	alrm->time.tm_hour = bcd2bin(talm >> 16);
+
+	return rtc_valid_tm(&alrm->time);
+}
+
+static int ma35d1_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct ma35_rtc *rtc = dev_get_drvdata(dev);
+	unsigned long val;
+
+	val = bin2bcd(alrm->time.tm_mday) << 0 | bin2bcd(alrm->time.tm_mon + 1) << 8 |
+	      bin2bcd(alrm->time.tm_year - 100) << 16;
+	rtc_reg_write(rtc, MA35_REG_RTC_CALM, val);
+
+	val = bin2bcd(alrm->time.tm_sec) << 0 | bin2bcd(alrm->time.tm_min) << 8 |
+	      bin2bcd(alrm->time.tm_hour) << 16;
+	rtc_reg_write(rtc, MA35_REG_RTC_TALM, val);
+
+	ma35d1_alarm_irq_enable(dev, alrm->enabled);
+
+	return 0;
+}
+
+static const struct rtc_class_ops ma35d1_rtc_ops = {
+	.read_time = ma35d1_rtc_read_time,
+	.set_time = ma35d1_rtc_set_time,
+	.read_alarm = ma35d1_rtc_read_alarm,
+	.set_alarm = ma35d1_rtc_set_alarm,
+	.alarm_irq_enable = ma35d1_alarm_irq_enable,
+};
+
+static int ma35d1_rtc_probe(struct platform_device *pdev)
+{
+	struct ma35_rtc *rtc;
+	struct clk *clk;
+	int ret;
+
+	rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL);
+	if (!rtc)
+		return -ENOMEM;
+
+	rtc->rtc_reg = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(rtc->rtc_reg))
+		return PTR_ERR(rtc->rtc_reg);
+
+	clk = of_clk_get(pdev->dev.of_node, 0);
+	if (IS_ERR(clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(clk), "failed to find rtc clock\n");
+
+	ret = clk_prepare_enable(clk);
+	if (ret)
+		return ret;
+
+	if (!(rtc_reg_read(rtc, MA35_REG_RTC_INIT) & RTC_INIT_ACTIVE)) {
+		ret = ma35d1_rtc_init(rtc, RTC_INIT_TIMEOUT);
+		if (ret)
+			return dev_err_probe(&pdev->dev, ret, "rtc init failed\n");
+	}
+
+	rtc->irq_num = platform_get_irq(pdev, 0);
+
+	ret = devm_request_irq(&pdev->dev, rtc->irq_num, ma35d1_rtc_interrupt,
+			       IRQF_NO_SUSPEND, "ma35d1rtc", rtc);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "Failed to request rtc irq\n");
+
+	platform_set_drvdata(pdev, rtc);
+
+	device_init_wakeup(&pdev->dev, true);
+
+	rtc->rtcdev = devm_rtc_allocate_device(&pdev->dev);
+	if (IS_ERR(rtc->rtcdev))
+		return PTR_ERR(rtc->rtcdev);
+
+	rtc->rtcdev->ops = &ma35d1_rtc_ops;
+	rtc->rtcdev->range_min = RTC_TIMESTAMP_BEGIN_2000;
+	rtc->rtcdev->range_max = RTC_TIMESTAMP_END_2099;
+
+	ret = devm_rtc_register_device(rtc->rtcdev);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "Failed to register rtc device\n");
+
+	return 0;
+}
+
+static int ma35d1_rtc_suspend(struct platform_device *pdev, pm_message_t state)
+{
+	struct ma35_rtc *rtc = platform_get_drvdata(pdev);
+
+	if (device_may_wakeup(&pdev->dev))
+		enable_irq_wake(rtc->irq_num);
+
+	return 0;
+}
+
+static int ma35d1_rtc_resume(struct platform_device *pdev)
+{
+	struct ma35_rtc *rtc = platform_get_drvdata(pdev);
+
+	if (device_may_wakeup(&pdev->dev))
+		disable_irq_wake(rtc->irq_num);
+
+	return 0;
+}
+
+static const struct of_device_id ma35d1_rtc_of_match[] = {
+	{ .compatible = "nuvoton,ma35d1-rtc", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, ma35d1_rtc_of_match);
+
+static struct platform_driver ma35d1_rtc_driver = {
+	.suspend    = ma35d1_rtc_suspend,
+	.resume     = ma35d1_rtc_resume,
+	.probe      = ma35d1_rtc_probe,
+	.driver		= {
+		.name	= "rtc-ma35d1",
+		.of_match_table = ma35d1_rtc_of_match,
+	},
+};
+
+module_platform_driver(ma35d1_rtc_driver);
+
+MODULE_AUTHOR("Ming-Jen Chen <mjchen@nuvoton.com>");
+MODULE_DESCRIPTION("MA35D1 RTC driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/rtc/rtc-max31335.c b/drivers/rtc/rtc-max31335.c
new file mode 100644
index 000000000000..402fda8fd548
--- /dev/null
+++ b/drivers/rtc/rtc-max31335.c
@@ -0,0 +1,697 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * RTC driver for the MAX31335
+ *
+ * Copyright (C) 2023 Analog Devices
+ *
+ * Antoniu Miclaus <antoniu.miclaus@analog.com>
+ *
+ */
+
+#include <asm-generic/unaligned.h>
+#include <linux/bcd.h>
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/hwmon.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/regmap.h>
+#include <linux/rtc.h>
+#include <linux/util_macros.h>
+
+/* MAX31335 Register Map */
+#define MAX31335_STATUS1			0x00
+#define MAX31335_INT_EN1			0x01
+#define MAX31335_STATUS2			0x02
+#define MAX31335_INT_EN2			0x03
+#define MAX31335_RTC_RESET			0x04
+#define MAX31335_RTC_CONFIG			0x05
+#define MAX31335_RTC_CONFIG2			0x06
+#define MAX31335_TIMESTAMP_CONFIG		0x07
+#define MAX31335_TIMER_CONFIG			0x08
+#define MAX31335_SECONDS_1_128			0x09
+#define MAX31335_SECONDS			0x0A
+#define MAX31335_MINUTES			0x0B
+#define MAX31335_HOURS				0x0C
+#define MAX31335_DAY				0x0D
+#define MAX31335_DATE				0x0E
+#define MAX31335_MONTH				0x0F
+#define MAX31335_YEAR				0x0F
+#define MAX31335_ALM1_SEC			0x11
+#define MAX31335_ALM1_MIN			0x12
+#define MAX31335_ALM1_HRS			0x13
+#define MAX31335_ALM1_DAY_DATE			0x14
+#define MAX31335_ALM1_MON			0x15
+#define MAX31335_ALM1_YEAR			0x16
+#define MAX31335_ALM2_MIN			0x17
+#define MAX31335_ALM2_HRS			0x18
+#define MAX31335_ALM2_DAY_DATE			0x19
+#define MAX31335_TIMER_COUNT			0x1A
+#define MAX31335_TIMER_INIT			0x1B
+#define MAX31335_PWR_MGMT			0x1C
+#define MAX31335_TRICKLE_REG			0x1D
+#define MAX31335_AGING_OFFSET			0x1E
+#define MAX31335_TS_CONFIG			0x30
+#define MAX31335_TEMP_ALARM_HIGH_MSB		0x31
+#define MAX31335_TEMP_ALARM_HIGH_LSB		0x32
+#define MAX31335_TEMP_ALARM_LOW_MSB		0x33
+#define MAX31335_TEMP_ALARM_LOW_LSB		0x34
+#define MAX31335_TEMP_DATA_MSB			0x35
+#define MAX31335_TEMP_DATA_LSB			0x36
+#define MAX31335_TS0_SEC_1_128			0x40
+#define MAX31335_TS0_SEC			0x41
+#define MAX31335_TS0_MIN			0x42
+#define MAX31335_TS0_HOUR			0x43
+#define MAX31335_TS0_DATE			0x44
+#define MAX31335_TS0_MONTH			0x45
+#define MAX31335_TS0_YEAR			0x46
+#define MAX31335_TS0_FLAGS			0x47
+#define MAX31335_TS1_SEC_1_128			0x48
+#define MAX31335_TS1_SEC			0x49
+#define MAX31335_TS1_MIN			0x4A
+#define MAX31335_TS1_HOUR			0x4B
+#define MAX31335_TS1_DATE			0x4C
+#define MAX31335_TS1_MONTH			0x4D
+#define MAX31335_TS1_YEAR			0x4E
+#define MAX31335_TS1_FLAGS			0x4F
+#define MAX31335_TS2_SEC_1_128			0x50
+#define MAX31335_TS2_SEC			0x51
+#define MAX31335_TS2_MIN			0x52
+#define MAX31335_TS2_HOUR			0x53
+#define MAX31335_TS2_DATE			0x54
+#define MAX31335_TS2_MONTH			0x55
+#define MAX31335_TS2_YEAR			0x56
+#define MAX31335_TS2_FLAGS			0x57
+#define MAX31335_TS3_SEC_1_128			0x58
+#define MAX31335_TS3_SEC			0x59
+#define MAX31335_TS3_MIN			0x5A
+#define MAX31335_TS3_HOUR			0x5B
+#define MAX31335_TS3_DATE			0x5C
+#define MAX31335_TS3_MONTH			0x5D
+#define MAX31335_TS3_YEAR			0x5E
+#define MAX31335_TS3_FLAGS			0x5F
+
+/* MAX31335_STATUS1 Bit Definitions */
+#define MAX31335_STATUS1_PSDECT			BIT(7)
+#define MAX31335_STATUS1_OSF			BIT(6)
+#define MAX31335_STATUS1_PFAIL			BIT(5)
+#define MAX31335_STATUS1_VBATLOW		BIT(4)
+#define MAX31335_STATUS1_DIF			BIT(3)
+#define MAX31335_STATUS1_TIF			BIT(2)
+#define MAX31335_STATUS1_A2F			BIT(1)
+#define MAX31335_STATUS1_A1F			BIT(0)
+
+/* MAX31335_INT_EN1 Bit Definitions */
+#define MAX31335_INT_EN1_DOSF			BIT(6)
+#define MAX31335_INT_EN1_PFAILE			BIT(5)
+#define MAX31335_INT_EN1_VBATLOWE		BIT(4)
+#define MAX31335_INT_EN1_DIE			BIT(3)
+#define MAX31335_INT_EN1_TIE			BIT(2)
+#define MAX31335_INT_EN1_A2IE			BIT(1)
+#define MAX31335_INT_EN1_A1IE			BIT(0)
+
+/* MAX31335_STATUS2 Bit Definitions */
+#define MAX31335_STATUS2_TEMP_RDY		BIT(2)
+#define MAX31335_STATUS2_OTF			BIT(1)
+#define MAX31335_STATUS2_UTF			BIT(0)
+
+/* MAX31335_INT_EN2 Bit Definitions */
+#define MAX31335_INT_EN2_TEMP_RDY_EN		BIT(2)
+#define MAX31335_INT_EN2_OTIE			BIT(1)
+#define MAX31335_INT_EN2_UTIE			BIT(0)
+
+/* MAX31335_RTC_RESET Bit Definitions */
+#define MAX31335_RTC_RESET_SWRST		BIT(0)
+
+/* MAX31335_RTC_CONFIG1 Bit Definitions */
+#define MAX31335_RTC_CONFIG1_EN_IO		BIT(6)
+#define MAX31335_RTC_CONFIG1_A1AC		GENMASK(5, 4)
+#define MAX31335_RTC_CONFIG1_DIP		BIT(3)
+#define MAX31335_RTC_CONFIG1_I2C_TIMEOUT	BIT(1)
+#define MAX31335_RTC_CONFIG1_EN_OSC		BIT(0)
+
+/* MAX31335_RTC_CONFIG2 Bit Definitions */
+#define MAX31335_RTC_CONFIG2_ENCLKO		BIT(2)
+#define MAX31335_RTC_CONFIG2_CLKO_HZ		GENMASK(1, 0)
+
+/* MAX31335_TIMESTAMP_CONFIG Bit Definitions */
+#define MAX31335_TIMESTAMP_CONFIG_TSVLOW	BIT(5)
+#define MAX31335_TIMESTAMP_CONFIG_TSPWM		BIT(4)
+#define MAX31335_TIMESTAMP_CONFIG_TSDIN		BIT(3)
+#define MAX31335_TIMESTAMP_CONFIG_TSOW		BIT(2)
+#define MAX31335_TIMESTAMP_CONFIG_TSR		BIT(1)
+#define MAX31335_TIMESTAMP_CONFIG_TSE		BIT(0)
+
+/* MAX31335_TIMER_CONFIG Bit Definitions */
+#define MAX31335_TIMER_CONFIG_TE		BIT(4)
+#define MAX31335_TIMER_CONFIG_TPAUSE		BIT(3)
+#define MAX31335_TIMER_CONFIG_TRPT		BIT(2)
+#define MAX31335_TIMER_CONFIG_TFS		GENMASK(1, 0)
+
+/* MAX31335_HOURS Bit Definitions */
+#define MAX31335_HOURS_F_24_12			BIT(6)
+#define MAX31335_HOURS_HR_20_AM_PM		BIT(5)
+
+/* MAX31335_MONTH Bit Definitions */
+#define MAX31335_MONTH_CENTURY			BIT(7)
+
+/* MAX31335_PWR_MGMT Bit Definitions */
+#define MAX31335_PWR_MGMT_PFVT			BIT(0)
+
+/* MAX31335_TRICKLE_REG Bit Definitions */
+#define MAX31335_TRICKLE_REG_TRICKLE		GENMASK(3, 1)
+#define MAX31335_TRICKLE_REG_EN_TRICKLE		BIT(0)
+
+/* MAX31335_TS_CONFIG Bit Definitions */
+#define MAX31335_TS_CONFIG_AUTO			BIT(4)
+#define MAX31335_TS_CONFIG_CONVERT_T		BIT(3)
+#define MAX31335_TS_CONFIG_TSINT		GENMASK(2, 0)
+
+/* MAX31335_TS_FLAGS Bit Definitions */
+#define MAX31335_TS_FLAGS_VLOWF			BIT(3)
+#define MAX31335_TS_FLAGS_VBATF			BIT(2)
+#define MAX31335_TS_FLAGS_VCCF			BIT(1)
+#define MAX31335_TS_FLAGS_DINF			BIT(0)
+
+/* MAX31335 Miscellaneous Definitions */
+#define MAX31335_TRICKLE_SCHOTTKY_DIODE		1
+#define MAX31335_TRICKLE_STANDARD_DIODE		4
+#define MAX31335_RAM_SIZE			32
+#define MAX31335_TIME_SIZE			0x07
+
+#define clk_hw_to_max31335(_hw) container_of(_hw, struct max31335_data, clkout)
+
+struct max31335_data {
+	struct regmap *regmap;
+	struct rtc_device *rtc;
+	struct clk_hw clkout;
+};
+
+static const int max31335_clkout_freq[] = { 1, 64, 1024, 32768 };
+
+static const u16 max31335_trickle_resistors[] = {3000, 6000, 11000};
+
+static bool max31335_volatile_reg(struct device *dev, unsigned int reg)
+{
+	/* time keeping registers */
+	if (reg >= MAX31335_SECONDS &&
+	    reg < MAX31335_SECONDS + MAX31335_TIME_SIZE)
+		return true;
+
+	/* interrupt status register */
+	if (reg == MAX31335_INT_EN1_A1IE)
+		return true;
+
+	/* temperature registers */
+	if (reg == MAX31335_TEMP_DATA_MSB || reg == MAX31335_TEMP_DATA_LSB)
+		return true;
+
+	return false;
+}
+
+static const struct regmap_config regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = 0x5F,
+	.volatile_reg = max31335_volatile_reg,
+};
+
+static int max31335_read_time(struct device *dev, struct rtc_time *tm)
+{
+	struct max31335_data *max31335 = dev_get_drvdata(dev);
+	u8 date[7];
+	int ret;
+
+	ret = regmap_bulk_read(max31335->regmap, MAX31335_SECONDS, date,
+			       sizeof(date));
+	if (ret)
+		return ret;
+
+	tm->tm_sec  = bcd2bin(date[0] & 0x7f);
+	tm->tm_min  = bcd2bin(date[1] & 0x7f);
+	tm->tm_hour = bcd2bin(date[2] & 0x3f);
+	tm->tm_wday = bcd2bin(date[3] & 0x7) - 1;
+	tm->tm_mday = bcd2bin(date[4] & 0x3f);
+	tm->tm_mon  = bcd2bin(date[5] & 0x1f) - 1;
+	tm->tm_year = bcd2bin(date[6]) + 100;
+
+	if (FIELD_GET(MAX31335_MONTH_CENTURY, date[5]))
+		tm->tm_year += 100;
+
+	return 0;
+}
+
+static int max31335_set_time(struct device *dev, struct rtc_time *tm)
+{
+	struct max31335_data *max31335 = dev_get_drvdata(dev);
+	u8 date[7];
+
+	date[0] = bin2bcd(tm->tm_sec);
+	date[1] = bin2bcd(tm->tm_min);
+	date[2] = bin2bcd(tm->tm_hour);
+	date[3] = bin2bcd(tm->tm_wday + 1);
+	date[4] = bin2bcd(tm->tm_mday);
+	date[5] = bin2bcd(tm->tm_mon + 1);
+	date[6] = bin2bcd(tm->tm_year % 100);
+
+	if (tm->tm_year >= 200)
+		date[5] |= FIELD_PREP(MAX31335_MONTH_CENTURY, 1);
+
+	return regmap_bulk_write(max31335->regmap, MAX31335_SECONDS, date,
+				 sizeof(date));
+}
+
+static int max31335_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct max31335_data *max31335 = dev_get_drvdata(dev);
+	int ret, ctrl, status;
+	struct rtc_time time;
+	u8 regs[6];
+
+	ret = regmap_bulk_read(max31335->regmap, MAX31335_ALM1_SEC, regs,
+			       sizeof(regs));
+	if (ret)
+		return ret;
+
+	alrm->time.tm_sec  = bcd2bin(regs[0] & 0x7f);
+	alrm->time.tm_min  = bcd2bin(regs[1] & 0x7f);
+	alrm->time.tm_hour = bcd2bin(regs[2] & 0x3f);
+	alrm->time.tm_mday = bcd2bin(regs[3] & 0x3f);
+	alrm->time.tm_mon  = bcd2bin(regs[4] & 0x1f) - 1;
+	alrm->time.tm_year = bcd2bin(regs[5]) + 100;
+
+	ret = max31335_read_time(dev, &time);
+	if (ret)
+		return ret;
+
+	if (time.tm_year >= 200)
+		alrm->time.tm_year += 100;
+
+	ret = regmap_read(max31335->regmap, MAX31335_INT_EN1, &ctrl);
+	if (ret)
+		return ret;
+
+	ret = regmap_read(max31335->regmap, MAX31335_STATUS1, &status);
+	if (ret)
+		return ret;
+
+	alrm->enabled = FIELD_GET(MAX31335_INT_EN1_A1IE, ctrl);
+	alrm->pending = FIELD_GET(MAX31335_STATUS1_A1F, status);
+
+	return 0;
+}
+
+static int max31335_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct max31335_data *max31335 = dev_get_drvdata(dev);
+	unsigned int reg;
+	u8 regs[6];
+	int ret;
+
+	regs[0] = bin2bcd(alrm->time.tm_sec);
+	regs[1] = bin2bcd(alrm->time.tm_min);
+	regs[2] = bin2bcd(alrm->time.tm_hour);
+	regs[3] = bin2bcd(alrm->time.tm_mday);
+	regs[4] = bin2bcd(alrm->time.tm_mon + 1);
+	regs[5] = bin2bcd(alrm->time.tm_year % 100);
+
+	ret = regmap_bulk_write(max31335->regmap, MAX31335_ALM1_SEC,
+				regs, sizeof(regs));
+	if (ret)
+		return ret;
+
+	reg = FIELD_PREP(MAX31335_INT_EN1_A1IE, alrm->enabled);
+	ret = regmap_update_bits(max31335->regmap, MAX31335_INT_EN1,
+				 MAX31335_INT_EN1_A1IE, reg);
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(max31335->regmap, MAX31335_STATUS1,
+				 MAX31335_STATUS1_A1F, 0);
+
+	return 0;
+}
+
+static int max31335_alarm_irq_enable(struct device *dev, unsigned int enabled)
+{
+	struct max31335_data *max31335 = dev_get_drvdata(dev);
+
+	return regmap_update_bits(max31335->regmap, MAX31335_INT_EN1,
+				  MAX31335_INT_EN1_A1IE, enabled);
+}
+
+static irqreturn_t max31335_handle_irq(int irq, void *dev_id)
+{
+	struct max31335_data *max31335 = dev_id;
+	bool status;
+	int ret;
+
+	ret = regmap_update_bits_check(max31335->regmap, MAX31335_STATUS1,
+				       MAX31335_STATUS1_A1F, 0, &status);
+	if (ret)
+		return IRQ_HANDLED;
+
+	if (status)
+		rtc_update_irq(max31335->rtc, 1, RTC_AF | RTC_IRQF);
+
+	return IRQ_HANDLED;
+}
+
+static const struct rtc_class_ops max31335_rtc_ops = {
+	.read_time = max31335_read_time,
+	.set_time = max31335_set_time,
+	.read_alarm = max31335_read_alarm,
+	.set_alarm = max31335_set_alarm,
+	.alarm_irq_enable = max31335_alarm_irq_enable,
+};
+
+static int max31335_trickle_charger_setup(struct device *dev,
+					  struct max31335_data *max31335)
+{
+	u32 ohms, chargeable;
+	int i, trickle_cfg;
+	const char *diode;
+
+	if (device_property_read_u32(dev, "aux-voltage-chargeable",
+				     &chargeable))
+		return 0;
+
+	if (device_property_read_u32(dev, "trickle-resistor-ohms", &ohms))
+		return 0;
+
+	if (device_property_read_string(dev, "adi,tc-diode", &diode))
+		return 0;
+
+	if (!strcmp(diode, "schottky"))
+		trickle_cfg = MAX31335_TRICKLE_SCHOTTKY_DIODE;
+	else if (!strcmp(diode, "standard+schottky"))
+		trickle_cfg = MAX31335_TRICKLE_STANDARD_DIODE;
+	else
+		return dev_err_probe(dev, -EINVAL,
+				     "Invalid tc-diode value: %s\n", diode);
+
+	for (i = 0; i < ARRAY_SIZE(max31335_trickle_resistors); i++)
+		if (ohms == max31335_trickle_resistors[i])
+			break;
+
+	if (i >= ARRAY_SIZE(max31335_trickle_resistors))
+		return 0;
+
+	i = i + trickle_cfg;
+
+	return regmap_write(max31335->regmap, MAX31335_TRICKLE_REG,
+			    FIELD_PREP(MAX31335_TRICKLE_REG_TRICKLE, i) |
+			    FIELD_PREP(MAX31335_TRICKLE_REG_EN_TRICKLE,
+				       chargeable));
+}
+
+static unsigned long max31335_clkout_recalc_rate(struct clk_hw *hw,
+						 unsigned long parent_rate)
+{
+	struct max31335_data *max31335 = clk_hw_to_max31335(hw);
+	unsigned int freq_mask;
+	unsigned int reg;
+	int ret;
+
+	ret = regmap_read(max31335->regmap, MAX31335_RTC_CONFIG2, &reg);
+	if (ret)
+		return 0;
+
+	freq_mask = __roundup_pow_of_two(ARRAY_SIZE(max31335_clkout_freq)) - 1;
+
+	return max31335_clkout_freq[reg & freq_mask];
+}
+
+static long max31335_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
+				       unsigned long *prate)
+{
+	int index;
+
+	index = find_closest(rate, max31335_clkout_freq,
+			     ARRAY_SIZE(max31335_clkout_freq));
+
+	return max31335_clkout_freq[index];
+}
+
+static int max31335_clkout_set_rate(struct clk_hw *hw, unsigned long rate,
+				    unsigned long parent_rate)
+{
+	struct max31335_data *max31335 = clk_hw_to_max31335(hw);
+	unsigned int freq_mask;
+	int index;
+
+	index = find_closest(rate, max31335_clkout_freq,
+			     ARRAY_SIZE(max31335_clkout_freq));
+	freq_mask = __roundup_pow_of_two(ARRAY_SIZE(max31335_clkout_freq)) - 1;
+
+	return regmap_update_bits(max31335->regmap, MAX31335_RTC_CONFIG2,
+				  freq_mask, index);
+}
+
+static int max31335_clkout_enable(struct clk_hw *hw)
+{
+	struct max31335_data *max31335 = clk_hw_to_max31335(hw);
+
+	return regmap_set_bits(max31335->regmap, MAX31335_RTC_CONFIG2,
+			       MAX31335_RTC_CONFIG2_ENCLKO);
+}
+
+static void max31335_clkout_disable(struct clk_hw *hw)
+{
+	struct max31335_data *max31335 = clk_hw_to_max31335(hw);
+
+	regmap_clear_bits(max31335->regmap, MAX31335_RTC_CONFIG2,
+			  MAX31335_RTC_CONFIG2_ENCLKO);
+}
+
+static int max31335_clkout_is_enabled(struct clk_hw *hw)
+{
+	struct max31335_data *max31335 = clk_hw_to_max31335(hw);
+	unsigned int reg;
+	int ret;
+
+	ret = regmap_read(max31335->regmap, MAX31335_RTC_CONFIG2, &reg);
+	if (ret)
+		return ret;
+
+	return !!(reg & MAX31335_RTC_CONFIG2_ENCLKO);
+}
+
+static const struct clk_ops max31335_clkout_ops = {
+	.recalc_rate = max31335_clkout_recalc_rate,
+	.round_rate = max31335_clkout_round_rate,
+	.set_rate = max31335_clkout_set_rate,
+	.enable = max31335_clkout_enable,
+	.disable = max31335_clkout_disable,
+	.is_enabled = max31335_clkout_is_enabled,
+};
+
+static struct clk_init_data max31335_clk_init = {
+	.name = "max31335-clkout",
+	.ops = &max31335_clkout_ops,
+};
+
+static int max31335_nvmem_reg_read(void *priv, unsigned int offset,
+				   void *val, size_t bytes)
+{
+	struct max31335_data *max31335 = priv;
+	unsigned int reg = MAX31335_TS0_SEC_1_128 + offset;
+
+	return regmap_bulk_read(max31335->regmap, reg, val, bytes);
+}
+
+static int max31335_nvmem_reg_write(void *priv, unsigned int offset,
+				    void *val, size_t bytes)
+{
+	struct max31335_data *max31335 = priv;
+	unsigned int reg = MAX31335_TS0_SEC_1_128 + offset;
+
+	return regmap_bulk_write(max31335->regmap, reg, val, bytes);
+}
+
+static struct nvmem_config max31335_nvmem_cfg = {
+	.reg_read = max31335_nvmem_reg_read,
+	.reg_write = max31335_nvmem_reg_write,
+	.word_size = 8,
+	.size = MAX31335_RAM_SIZE,
+};
+
+#if IS_REACHABLE(HWMON)
+static int max31335_read_temp(struct device *dev, enum hwmon_sensor_types type,
+			      u32 attr, int channel, long *val)
+{
+	struct max31335_data *max31335 = dev_get_drvdata(dev);
+	u8 reg[2];
+	s16 temp;
+	int ret;
+
+	if (type != hwmon_temp || attr != hwmon_temp_input)
+		return -EOPNOTSUPP;
+
+	ret = regmap_bulk_read(max31335->regmap, MAX31335_TEMP_DATA_MSB,
+			       reg, 2);
+	if (ret)
+		return ret;
+
+	temp = get_unaligned_be16(reg);
+
+	*val = (temp / 64) * 250;
+
+	return 0;
+}
+
+static umode_t max31335_is_visible(const void *data,
+				   enum hwmon_sensor_types type,
+				   u32 attr, int channel)
+{
+	if (type == hwmon_temp && attr == hwmon_temp_input)
+		return 0444;
+
+	return 0;
+}
+
+static const struct hwmon_channel_info *max31335_info[] = {
+	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT),
+	NULL
+};
+
+static const struct hwmon_ops max31335_hwmon_ops = {
+	.is_visible = max31335_is_visible,
+	.read = max31335_read_temp,
+};
+
+static const struct hwmon_chip_info max31335_chip_info = {
+	.ops = &max31335_hwmon_ops,
+	.info = max31335_info,
+};
+#endif
+
+static int max31335_clkout_register(struct device *dev)
+{
+	struct max31335_data *max31335 = dev_get_drvdata(dev);
+	int ret;
+
+	if (!device_property_present(dev, "#clock-cells"))
+		return regmap_clear_bits(max31335->regmap, MAX31335_RTC_CONFIG2,
+					 MAX31335_RTC_CONFIG2_ENCLKO);
+
+	max31335->clkout.init = &max31335_clk_init;
+
+	ret = devm_clk_hw_register(dev, &max31335->clkout);
+	if (ret)
+		return dev_err_probe(dev, ret, "cannot register clock\n");
+
+	ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get,
+					  &max31335->clkout);
+	if (ret)
+		return dev_err_probe(dev, ret, "cannot add hw provider\n");
+
+	max31335->clkout.clk = devm_clk_get_enabled(dev, NULL);
+	if (IS_ERR(max31335->clkout.clk))
+		return dev_err_probe(dev, PTR_ERR(max31335->clkout.clk),
+				     "cannot enable clkout\n");
+
+	return 0;
+}
+
+static int max31335_probe(struct i2c_client *client)
+{
+	struct max31335_data *max31335;
+#if IS_REACHABLE(HWMON)
+	struct device *hwmon;
+#endif
+	int ret;
+
+	max31335 = devm_kzalloc(&client->dev, sizeof(*max31335), GFP_KERNEL);
+	if (!max31335)
+		return -ENOMEM;
+
+	max31335->regmap = devm_regmap_init_i2c(client, &regmap_config);
+	if (IS_ERR(max31335->regmap))
+		return PTR_ERR(max31335->regmap);
+
+	i2c_set_clientdata(client, max31335);
+
+	max31335->rtc = devm_rtc_allocate_device(&client->dev);
+	if (IS_ERR(max31335->rtc))
+		return PTR_ERR(max31335->rtc);
+
+	max31335->rtc->ops = &max31335_rtc_ops;
+	max31335->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
+	max31335->rtc->range_max = RTC_TIMESTAMP_END_2199;
+	max31335->rtc->alarm_offset_max = 24 * 60 * 60;
+
+	ret = max31335_clkout_register(&client->dev);
+	if (ret)
+		return ret;
+
+	if (client->irq > 0) {
+		ret = devm_request_threaded_irq(&client->dev, client->irq,
+						NULL, max31335_handle_irq,
+						IRQF_ONESHOT,
+						"max31335", max31335);
+		if (ret) {
+			dev_warn(&client->dev,
+				 "unable to request IRQ, alarm max31335 disabled\n");
+			client->irq = 0;
+		}
+	}
+
+	if (!client->irq)
+		clear_bit(RTC_FEATURE_ALARM, max31335->rtc->features);
+
+	max31335_nvmem_cfg.priv = max31335;
+	ret = devm_rtc_nvmem_register(max31335->rtc, &max31335_nvmem_cfg);
+	if (ret)
+		return dev_err_probe(&client->dev, ret,
+				     "cannot register rtc nvmem\n");
+
+#if IS_REACHABLE(HWMON)
+	hwmon = devm_hwmon_device_register_with_info(&client->dev, client->name,
+						     max31335,
+						     &max31335_chip_info,
+						     NULL);
+	if (IS_ERR(hwmon))
+		return dev_err_probe(&client->dev, PTR_ERR(hwmon),
+				     "cannot register hwmon device\n");
+#endif
+
+	ret = max31335_trickle_charger_setup(&client->dev, max31335);
+	if (ret)
+		return ret;
+
+	return devm_rtc_register_device(max31335->rtc);
+}
+
+static const struct i2c_device_id max31335_id[] = {
+	{ "max31335", 0 },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(i2c, max31335_id);
+
+static const struct of_device_id max31335_of_match[] = {
+	{ .compatible = "adi,max31335" },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(of, max31335_of_match);
+
+static struct i2c_driver max31335_driver = {
+	.driver = {
+		.name = "rtc-max31335",
+		.of_match_table = max31335_of_match,
+	},
+	.probe = max31335_probe,
+	.id_table = max31335_id,
+};
+module_i2c_driver(max31335_driver);
+
+MODULE_AUTHOR("Antoniu Miclaus <antoniu.miclaus@analog.com>");
+MODULE_DESCRIPTION("MAX31335 RTC driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/rtc/rtc-mc146818-lib.c b/drivers/rtc/rtc-mc146818-lib.c
index f1c09f1db044..651bf3c279c7 100644
--- a/drivers/rtc/rtc-mc146818-lib.c
+++ b/drivers/rtc/rtc-mc146818-lib.c
@@ -8,26 +8,31 @@
 #include <linux/acpi.h>
 #endif
 
+#define UIP_RECHECK_DELAY		100	/* usec */
+#define UIP_RECHECK_DELAY_MS		(USEC_PER_MSEC / UIP_RECHECK_DELAY)
+#define UIP_RECHECK_LOOPS_MS(x)		(x / UIP_RECHECK_DELAY_MS)
+
 /*
  * Execute a function while the UIP (Update-in-progress) bit of the RTC is
- * unset.
+ * unset. The timeout is configurable by the caller in ms.
  *
  * Warning: callback may be executed more then once.
  */
 bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param),
+			int timeout,
 			void *param)
 {
 	int i;
 	unsigned long flags;
 	unsigned char seconds;
 
-	for (i = 0; i < 100; i++) {
+	for (i = 0; UIP_RECHECK_LOOPS_MS(i) < timeout; i++) {
 		spin_lock_irqsave(&rtc_lock, flags);
 
 		/*
 		 * Check whether there is an update in progress during which the
 		 * readout is unspecified. The maximum update time is ~2ms. Poll
-		 * every 100 usec for completion.
+		 * for completion.
 		 *
 		 * Store the second value before checking UIP so a long lasting
 		 * NMI which happens to hit after the UIP check cannot make
@@ -37,7 +42,7 @@ bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param),
 
 		if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) {
 			spin_unlock_irqrestore(&rtc_lock, flags);
-			udelay(100);
+			udelay(UIP_RECHECK_DELAY);
 			continue;
 		}
 
@@ -56,7 +61,7 @@ bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param),
 		 */
 		if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) {
 			spin_unlock_irqrestore(&rtc_lock, flags);
-			udelay(100);
+			udelay(UIP_RECHECK_DELAY);
 			continue;
 		}
 
@@ -72,6 +77,10 @@ bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param),
 		}
 		spin_unlock_irqrestore(&rtc_lock, flags);
 
+		if (UIP_RECHECK_LOOPS_MS(i) >= 100)
+			pr_warn("Reading current time from RTC took around %li ms\n",
+				UIP_RECHECK_LOOPS_MS(i));
+
 		return true;
 	}
 	return false;
@@ -84,7 +93,7 @@ EXPORT_SYMBOL_GPL(mc146818_avoid_UIP);
  */
 bool mc146818_does_rtc_work(void)
 {
-	return mc146818_avoid_UIP(NULL, NULL);
+	return mc146818_avoid_UIP(NULL, 1000, NULL);
 }
 EXPORT_SYMBOL_GPL(mc146818_does_rtc_work);
 
@@ -130,15 +139,27 @@ static void mc146818_get_time_callback(unsigned char seconds, void *param_in)
 	p->ctrl = CMOS_READ(RTC_CONTROL);
 }
 
-int mc146818_get_time(struct rtc_time *time)
+/**
+ * mc146818_get_time - Get the current time from the RTC
+ * @time: pointer to struct rtc_time to store the current time
+ * @timeout: timeout value in ms
+ *
+ * This function reads the current time from the RTC and stores it in the
+ * provided struct rtc_time. The timeout parameter specifies the maximum
+ * time to wait for the RTC to become ready.
+ *
+ * Return: 0 on success, -ETIMEDOUT if the RTC did not become ready within
+ * the specified timeout, or another error code if an error occurred.
+ */
+int mc146818_get_time(struct rtc_time *time, int timeout)
 {
 	struct mc146818_get_time_callback_param p = {
 		.time = time
 	};
 
-	if (!mc146818_avoid_UIP(mc146818_get_time_callback, &p)) {
+	if (!mc146818_avoid_UIP(mc146818_get_time_callback, timeout, &p)) {
 		memset(time, 0, sizeof(*time));
-		return -EIO;
+		return -ETIMEDOUT;
 	}
 
 	if (!(p.ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
diff --git a/drivers/rtc/rtc-nct3018y.c b/drivers/rtc/rtc-nct3018y.c
index ed4e606be8e5..f488a189a465 100644
--- a/drivers/rtc/rtc-nct3018y.c
+++ b/drivers/rtc/rtc-nct3018y.c
@@ -23,6 +23,7 @@
 #define NCT3018Y_REG_CTRL	0x0A /* timer control */
 #define NCT3018Y_REG_ST		0x0B /* status */
 #define NCT3018Y_REG_CLKO	0x0C /* clock out */
+#define NCT3018Y_REG_PART	0x21 /* part info */
 
 #define NCT3018Y_BIT_AF		BIT(7)
 #define NCT3018Y_BIT_ST		BIT(7)
@@ -37,10 +38,12 @@
 #define NCT3018Y_REG_BAT_MASK		0x07
 #define NCT3018Y_REG_CLKO_F_MASK	0x03 /* frequenc mask */
 #define NCT3018Y_REG_CLKO_CKE		0x80 /* clock out enabled */
+#define NCT3018Y_REG_PART_NCT3018Y	0x02
 
 struct nct3018y {
 	struct rtc_device *rtc;
 	struct i2c_client *client;
+	int part_num;
 #ifdef CONFIG_COMMON_CLK
 	struct clk_hw clkout_hw;
 #endif
@@ -177,8 +180,27 @@ static int nct3018y_rtc_read_time(struct device *dev, struct rtc_time *tm)
 static int nct3018y_rtc_set_time(struct device *dev, struct rtc_time *tm)
 {
 	struct i2c_client *client = to_i2c_client(dev);
+	struct nct3018y *nct3018y = dev_get_drvdata(dev);
 	unsigned char buf[4] = {0};
-	int err;
+	int err, flags;
+	int restore_flags = 0;
+
+	flags = i2c_smbus_read_byte_data(client, NCT3018Y_REG_CTRL);
+	if (flags < 0) {
+		dev_dbg(&client->dev, "Failed to read NCT3018Y_REG_CTRL.\n");
+		return flags;
+	}
+
+	/* Check and set TWO bit */
+	if (nct3018y->part_num == NCT3018Y_REG_PART_NCT3018Y && !(flags & NCT3018Y_BIT_TWO)) {
+		restore_flags = 1;
+		flags |= NCT3018Y_BIT_TWO;
+		err = i2c_smbus_write_byte_data(client, NCT3018Y_REG_CTRL, flags);
+		if (err < 0) {
+			dev_dbg(&client->dev, "Unable to write NCT3018Y_REG_CTRL.\n");
+			return err;
+		}
+	}
 
 	buf[0] = bin2bcd(tm->tm_sec);
 	err = i2c_smbus_write_byte_data(client, NCT3018Y_REG_SC, buf[0]);
@@ -212,6 +234,18 @@ static int nct3018y_rtc_set_time(struct device *dev, struct rtc_time *tm)
 		return -EIO;
 	}
 
+	/* Restore TWO bit */
+	if (restore_flags) {
+		if (nct3018y->part_num == NCT3018Y_REG_PART_NCT3018Y)
+			flags &= ~NCT3018Y_BIT_TWO;
+
+		err = i2c_smbus_write_byte_data(client, NCT3018Y_REG_CTRL, flags);
+		if (err < 0) {
+			dev_dbg(&client->dev, "Unable to write NCT3018Y_REG_CTRL.\n");
+			return err;
+		}
+	}
+
 	return err;
 }
 
@@ -479,11 +513,17 @@ static int nct3018y_probe(struct i2c_client *client)
 		dev_dbg(&client->dev, "%s: NCT3018Y_BIT_TWO is set\n", __func__);
 	}
 
-	flags = NCT3018Y_BIT_TWO;
-	err = i2c_smbus_write_byte_data(client, NCT3018Y_REG_CTRL, flags);
-	if (err < 0) {
-		dev_dbg(&client->dev, "Unable to write NCT3018Y_REG_CTRL\n");
-		return err;
+	nct3018y->part_num = i2c_smbus_read_byte_data(client, NCT3018Y_REG_PART);
+	if (nct3018y->part_num < 0) {
+		dev_dbg(&client->dev, "Failed to read NCT3018Y_REG_PART.\n");
+		return nct3018y->part_num;
+	} else if (nct3018y->part_num == NCT3018Y_REG_PART_NCT3018Y) {
+		flags = NCT3018Y_BIT_HF;
+		err = i2c_smbus_write_byte_data(client, NCT3018Y_REG_CTRL, flags);
+		if (err < 0) {
+			dev_dbg(&client->dev, "Unable to write NCT3018Y_REG_CTRL.\n");
+			return err;
+		}
 	}
 
 	flags = 0;
diff --git a/drivers/rtc/rtc-rv8803.c b/drivers/rtc/rtc-rv8803.c
index 1a3ec1bb5b81..1327251e527c 100644
--- a/drivers/rtc/rtc-rv8803.c
+++ b/drivers/rtc/rtc-rv8803.c
@@ -17,6 +17,7 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/rtc.h>
+#include <linux/pm_wakeirq.h>
 
 #define RV8803_I2C_TRY_COUNT		4
 
@@ -607,6 +608,28 @@ static int rv8803_regs_configure(struct rv8803_data *rv8803)
 	return 0;
 }
 
+static int rv8803_resume(struct device *dev)
+{
+	struct rv8803_data *rv8803 = dev_get_drvdata(dev);
+
+	if (rv8803->client->irq > 0 && device_may_wakeup(dev))
+		disable_irq_wake(rv8803->client->irq);
+
+	return 0;
+}
+
+static int rv8803_suspend(struct device *dev)
+{
+	struct rv8803_data *rv8803 = dev_get_drvdata(dev);
+
+	if (rv8803->client->irq > 0 && device_may_wakeup(dev))
+		enable_irq_wake(rv8803->client->irq);
+
+	return 0;
+}
+
+static DEFINE_SIMPLE_DEV_PM_OPS(rv8803_pm_ops, rv8803_suspend, rv8803_resume);
+
 static const struct i2c_device_id rv8803_id[] = {
 	{ "rv8803", rv_8803 },
 	{ "rv8804", rx_8804 },
@@ -683,10 +706,18 @@ static int rv8803_probe(struct i2c_client *client)
 		if (err) {
 			dev_warn(&client->dev, "unable to request IRQ, alarms disabled\n");
 			client->irq = 0;
+		} else {
+			device_init_wakeup(&client->dev, true);
+			err = dev_pm_set_wake_irq(&client->dev, client->irq);
+			if (err)
+				dev_err(&client->dev, "failed to set wake IRQ\n");
 		}
+	} else {
+		if (device_property_read_bool(&client->dev, "wakeup-source"))
+			device_init_wakeup(&client->dev, true);
+		else
+			clear_bit(RTC_FEATURE_ALARM, rv8803->rtc->features);
 	}
-	if (!client->irq)
-		clear_bit(RTC_FEATURE_ALARM, rv8803->rtc->features);
 
 	if (of_property_read_bool(client->dev.of_node, "epson,vdet-disable"))
 		rv8803->backup |= RX8900_FLAG_VDETOFF;
@@ -737,6 +768,7 @@ static struct i2c_driver rv8803_driver = {
 	.driver = {
 		.name = "rtc-rv8803",
 		.of_match_table = of_match_ptr(rv8803_of_match),
+		.pm = &rv8803_pm_ops,
 	},
 	.probe		= rv8803_probe,
 	.id_table	= rv8803_id,
diff --git a/drivers/rtc/rtc-tps6594.c b/drivers/rtc/rtc-tps6594.c
new file mode 100644
index 000000000000..838ae8562a35
--- /dev/null
+++ b/drivers/rtc/rtc-tps6594.c
@@ -0,0 +1,454 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * RTC driver for tps6594 PMIC
+ *
+ * Copyright (C) 2023 BayLibre Incorporated - https://www.baylibre.com/
+ */
+
+#include <linux/bcd.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/limits.h>
+#include <linux/math64.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/mod_devicetable.h>
+#include <linux/property.h>
+#include <linux/rtc.h>
+#include <linux/types.h>
+#include <linux/units.h>
+
+#include <linux/mfd/tps6594.h>
+
+// Total number of RTC registers needed to set time
+#define NUM_TIME_REGS (TPS6594_REG_RTC_WEEKS - TPS6594_REG_RTC_SECONDS + 1)
+
+// Total number of RTC alarm registers
+#define NUM_TIME_ALARM_REGS (NUM_TIME_REGS - 1)
+
+/*
+ * Min and max values supported by 'offset' interface (swapped sign).
+ * After conversion, the values do not exceed the range [-32767, 33767]
+ * which COMP_REG must conform to.
+ */
+#define MIN_OFFSET (-277774)
+#define MAX_OFFSET (277774)
+
+// Number of ticks per hour
+#define TICKS_PER_HOUR (32768 * 3600)
+
+// Multiplier for ppb conversions
+#define PPB_MULT NANO
+
+static int tps6594_rtc_alarm_irq_enable(struct device *dev,
+					unsigned int enabled)
+{
+	struct tps6594 *tps = dev_get_drvdata(dev->parent);
+	u8 val;
+
+	val = enabled ? TPS6594_BIT_IT_ALARM : 0;
+
+	return regmap_update_bits(tps->regmap, TPS6594_REG_RTC_INTERRUPTS,
+				  TPS6594_BIT_IT_ALARM, val);
+}
+
+/* Pulse GET_TIME field of RTC_CTRL_1 to store a timestamp in shadow registers. */
+static int tps6594_rtc_shadow_timestamp(struct device *dev, struct tps6594 *tps)
+{
+	int ret;
+
+	/*
+	 * Set GET_TIME to 0. Next time we set GET_TIME to 1 we will be sure to store
+	 * an up-to-date timestamp.
+	 */
+	ret = regmap_clear_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1,
+				TPS6594_BIT_GET_TIME);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Copy content of RTC registers to shadow registers or latches to read
+	 * a coherent timestamp.
+	 */
+	return regmap_set_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1,
+			       TPS6594_BIT_GET_TIME);
+}
+
+static int tps6594_rtc_read_time(struct device *dev, struct rtc_time *tm)
+{
+	unsigned char rtc_data[NUM_TIME_REGS];
+	struct tps6594 *tps = dev_get_drvdata(dev->parent);
+	int ret;
+
+	// Check if RTC is running.
+	ret = regmap_test_bits(tps->regmap, TPS6594_REG_RTC_STATUS,
+			       TPS6594_BIT_RUN);
+	if (ret < 0)
+		return ret;
+	if (ret == 0)
+		return -EINVAL;
+
+	ret = tps6594_rtc_shadow_timestamp(dev, tps);
+	if (ret < 0)
+		return ret;
+
+	// Read shadowed RTC registers.
+	ret = regmap_bulk_read(tps->regmap, TPS6594_REG_RTC_SECONDS, rtc_data,
+			       NUM_TIME_REGS);
+	if (ret < 0)
+		return ret;
+
+	tm->tm_sec = bcd2bin(rtc_data[0]);
+	tm->tm_min = bcd2bin(rtc_data[1]);
+	tm->tm_hour = bcd2bin(rtc_data[2]);
+	tm->tm_mday = bcd2bin(rtc_data[3]);
+	tm->tm_mon = bcd2bin(rtc_data[4]) - 1;
+	tm->tm_year = bcd2bin(rtc_data[5]) + 100;
+	tm->tm_wday = bcd2bin(rtc_data[6]);
+
+	return 0;
+}
+
+static int tps6594_rtc_set_time(struct device *dev, struct rtc_time *tm)
+{
+	unsigned char rtc_data[NUM_TIME_REGS];
+	struct tps6594 *tps = dev_get_drvdata(dev->parent);
+	int ret;
+
+	rtc_data[0] = bin2bcd(tm->tm_sec);
+	rtc_data[1] = bin2bcd(tm->tm_min);
+	rtc_data[2] = bin2bcd(tm->tm_hour);
+	rtc_data[3] = bin2bcd(tm->tm_mday);
+	rtc_data[4] = bin2bcd(tm->tm_mon + 1);
+	rtc_data[5] = bin2bcd(tm->tm_year - 100);
+	rtc_data[6] = bin2bcd(tm->tm_wday);
+
+	// Stop RTC while updating the RTC time registers.
+	ret = regmap_clear_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1,
+				TPS6594_BIT_STOP_RTC);
+	if (ret < 0)
+		return ret;
+
+	// Update all the time registers in one shot.
+	ret = regmap_bulk_write(tps->regmap, TPS6594_REG_RTC_SECONDS, rtc_data,
+				NUM_TIME_REGS);
+	if (ret < 0)
+		return ret;
+
+	// Start back RTC.
+	return regmap_set_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1,
+			       TPS6594_BIT_STOP_RTC);
+}
+
+static int tps6594_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alm)
+{
+	unsigned char alarm_data[NUM_TIME_ALARM_REGS];
+	u32 int_val;
+	struct tps6594 *tps = dev_get_drvdata(dev->parent);
+	int ret;
+
+	ret = regmap_bulk_read(tps->regmap, TPS6594_REG_ALARM_SECONDS,
+			       alarm_data, NUM_TIME_ALARM_REGS);
+	if (ret < 0)
+		return ret;
+
+	alm->time.tm_sec = bcd2bin(alarm_data[0]);
+	alm->time.tm_min = bcd2bin(alarm_data[1]);
+	alm->time.tm_hour = bcd2bin(alarm_data[2]);
+	alm->time.tm_mday = bcd2bin(alarm_data[3]);
+	alm->time.tm_mon = bcd2bin(alarm_data[4]) - 1;
+	alm->time.tm_year = bcd2bin(alarm_data[5]) + 100;
+
+	ret = regmap_read(tps->regmap, TPS6594_REG_RTC_INTERRUPTS, &int_val);
+	if (ret < 0)
+		return ret;
+
+	alm->enabled = int_val & TPS6594_BIT_IT_ALARM;
+
+	return 0;
+}
+
+static int tps6594_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm)
+{
+	unsigned char alarm_data[NUM_TIME_ALARM_REGS];
+	struct tps6594 *tps = dev_get_drvdata(dev->parent);
+	int ret;
+
+	// Disable alarm irq before changing the alarm timestamp.
+	ret = tps6594_rtc_alarm_irq_enable(dev, 0);
+	if (ret)
+		return ret;
+
+	alarm_data[0] = bin2bcd(alm->time.tm_sec);
+	alarm_data[1] = bin2bcd(alm->time.tm_min);
+	alarm_data[2] = bin2bcd(alm->time.tm_hour);
+	alarm_data[3] = bin2bcd(alm->time.tm_mday);
+	alarm_data[4] = bin2bcd(alm->time.tm_mon + 1);
+	alarm_data[5] = bin2bcd(alm->time.tm_year - 100);
+
+	// Update all the alarm registers in one shot.
+	ret = regmap_bulk_write(tps->regmap, TPS6594_REG_ALARM_SECONDS,
+				alarm_data, NUM_TIME_ALARM_REGS);
+	if (ret < 0)
+		return ret;
+
+	if (alm->enabled)
+		ret = tps6594_rtc_alarm_irq_enable(dev, 1);
+
+	return ret;
+}
+
+static int tps6594_rtc_set_calibration(struct device *dev, int calibration)
+{
+	struct tps6594 *tps = dev_get_drvdata(dev->parent);
+	__le16 value;
+	int ret;
+
+	/*
+	 * TPS6594 uses two's complement 16 bit value for compensation of RTC
+	 * crystal inaccuracies. One time every hour when seconds counter
+	 * increments from 0 to 1 compensation value will be added to internal
+	 * RTC counter value.
+	 *
+	 * Valid range for compensation value: [-32767 .. 32767].
+	 */
+	if (calibration < S16_MIN + 1 || calibration > S16_MAX)
+		return -ERANGE;
+
+	value = cpu_to_le16(calibration);
+
+	// Update all the compensation registers in one shot.
+	ret = regmap_bulk_write(tps->regmap, TPS6594_REG_RTC_COMP_LSB, &value,
+				sizeof(value));
+	if (ret < 0)
+		return ret;
+
+	// Enable automatic compensation.
+	return regmap_set_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1,
+			       TPS6594_BIT_AUTO_COMP);
+}
+
+static int tps6594_rtc_get_calibration(struct device *dev, int *calibration)
+{
+	struct tps6594 *tps = dev_get_drvdata(dev->parent);
+	unsigned int ctrl;
+	__le16 value;
+	int ret;
+
+	ret = regmap_read(tps->regmap, TPS6594_REG_RTC_CTRL_1, &ctrl);
+	if (ret < 0)
+		return ret;
+
+	// If automatic compensation is not enabled report back zero.
+	if (!(ctrl & TPS6594_BIT_AUTO_COMP)) {
+		*calibration = 0;
+		return 0;
+	}
+
+	ret = regmap_bulk_read(tps->regmap, TPS6594_REG_RTC_COMP_LSB, &value,
+			       sizeof(value));
+	if (ret < 0)
+		return ret;
+
+	*calibration = le16_to_cpu(value);
+
+	return 0;
+}
+
+static int tps6594_rtc_read_offset(struct device *dev, long *offset)
+{
+	int calibration;
+	s64 tmp;
+	int ret;
+
+	ret = tps6594_rtc_get_calibration(dev, &calibration);
+	if (ret < 0)
+		return ret;
+
+	// Convert from RTC calibration register format to ppb format.
+	tmp = calibration * PPB_MULT;
+
+	if (tmp < 0)
+		tmp -= TICKS_PER_HOUR / 2LL;
+	else
+		tmp += TICKS_PER_HOUR / 2LL;
+	tmp = div_s64(tmp, TICKS_PER_HOUR);
+
+	/*
+	 * SAFETY:
+	 * Computatiion is the reverse operation of the one done in
+	 * `tps6594_rtc_set_offset`. The safety remarks applie here too.
+	 */
+
+	/*
+	 * Offset value operates in negative way, so swap sign.
+	 * See 8.3.10.5, (32768 - COMP_REG).
+	 */
+	*offset = (long)-tmp;
+
+	return 0;
+}
+
+static int tps6594_rtc_set_offset(struct device *dev, long offset)
+{
+	int calibration;
+	s64 tmp;
+
+	// Make sure offset value is within supported range.
+	if (offset < MIN_OFFSET || offset > MAX_OFFSET)
+		return -ERANGE;
+
+	// Convert from ppb format to RTC calibration register format.
+
+	tmp = offset * TICKS_PER_HOUR;
+	if (tmp < 0)
+		tmp -= PPB_MULT / 2LL;
+	else
+		tmp += PPB_MULT / 2LL;
+	tmp = div_s64(tmp, PPB_MULT);
+
+	/*
+	 * SAFETY:
+	 * - tmp = offset * TICK_PER_HOUR :
+	 *	`offset` can't be more than 277774, so `tmp` can't exceed 277774000000000
+	 *	which is lower than the maximum value in an `s64` (2^63-1). No overflow here.
+	 *
+	 * - tmp += TICK_PER_HOUR / 2LL :
+	 *	tmp will have a maximum value of 277774117964800 which is still inferior to 2^63-1.
+	 */
+
+	// Offset value operates in negative way, so swap sign.
+	calibration = (int)-tmp;
+
+	return tps6594_rtc_set_calibration(dev, calibration);
+}
+
+static irqreturn_t tps6594_rtc_interrupt(int irq, void *rtc)
+{
+	struct device *dev = rtc;
+	struct tps6594 *tps = dev_get_drvdata(dev->parent);
+	struct rtc_device *rtc_dev = dev_get_drvdata(dev);
+	int ret;
+	u32 rtc_reg;
+
+	ret = regmap_read(tps->regmap, TPS6594_REG_RTC_STATUS, &rtc_reg);
+	if (ret)
+		return IRQ_NONE;
+
+	rtc_update_irq(rtc_dev, 1, RTC_IRQF | RTC_AF);
+
+	return IRQ_HANDLED;
+}
+
+static const struct rtc_class_ops tps6594_rtc_ops = {
+	.read_time = tps6594_rtc_read_time,
+	.set_time = tps6594_rtc_set_time,
+	.read_alarm = tps6594_rtc_read_alarm,
+	.set_alarm = tps6594_rtc_set_alarm,
+	.alarm_irq_enable = tps6594_rtc_alarm_irq_enable,
+	.read_offset = tps6594_rtc_read_offset,
+	.set_offset = tps6594_rtc_set_offset,
+};
+
+static int tps6594_rtc_probe(struct platform_device *pdev)
+{
+	struct tps6594 *tps = dev_get_drvdata(pdev->dev.parent);
+	struct device *dev = &pdev->dev;
+	struct rtc_device *rtc;
+	int irq;
+	int ret;
+
+	rtc = devm_kzalloc(dev, sizeof(*rtc), GFP_KERNEL);
+	if (!rtc)
+		return -ENOMEM;
+
+	rtc = devm_rtc_allocate_device(dev);
+	if (IS_ERR(rtc))
+		return PTR_ERR(rtc);
+
+	// Enable crystal oscillator.
+	ret = regmap_set_bits(tps->regmap, TPS6594_REG_RTC_CTRL_2,
+			      TPS6594_BIT_XTAL_EN);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_test_bits(tps->regmap, TPS6594_REG_RTC_STATUS,
+			       TPS6594_BIT_RUN);
+	if (ret < 0)
+		return ret;
+	// RTC not running.
+	if (ret == 0) {
+		ret = regmap_set_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1,
+				      TPS6594_BIT_STOP_RTC);
+		if (ret < 0)
+			return ret;
+
+		/*
+		 * On some boards, a 40 ms delay is needed before BIT_RUN is set.
+		 * 80 ms should provide sufficient margin.
+		 */
+		mdelay(80);
+
+		/*
+		 * RTC should be running now. Check if this is the case.
+		 * If not it might be a missing oscillator.
+		 */
+		ret = regmap_test_bits(tps->regmap, TPS6594_REG_RTC_STATUS,
+				       TPS6594_BIT_RUN);
+		if (ret < 0)
+			return ret;
+		if (ret == 0)
+			return -ENODEV;
+
+		// Stop RTC until first call to `tps6594_rtc_set_time`.
+		ret = regmap_clear_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1,
+					TPS6594_BIT_STOP_RTC);
+		if (ret < 0)
+			return ret;
+	}
+
+	platform_set_drvdata(pdev, rtc);
+
+	irq = platform_get_irq_byname(pdev, TPS6594_IRQ_NAME_ALARM);
+	if (irq < 0)
+		return dev_err_probe(dev, irq, "Failed to get irq\n");
+
+	ret = devm_request_threaded_irq(dev, irq, NULL, tps6594_rtc_interrupt,
+					IRQF_ONESHOT, TPS6594_IRQ_NAME_ALARM,
+					dev);
+	if (ret < 0)
+		return dev_err_probe(dev, ret,
+				     "Failed to request_threaded_irq\n");
+
+	ret = device_init_wakeup(dev, true);
+	if (ret < 0)
+		return dev_err_probe(dev, ret,
+				     "Failed to init rtc as wakeup source\n");
+
+	rtc->ops = &tps6594_rtc_ops;
+	rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
+	rtc->range_max = RTC_TIMESTAMP_END_2099;
+
+	return devm_rtc_register_device(rtc);
+}
+
+static const struct platform_device_id tps6594_rtc_id_table[] = {
+	{ "tps6594-rtc", },
+	{}
+};
+MODULE_DEVICE_TABLE(platform, tps6594_rtc_id_table);
+
+static struct platform_driver tps6594_rtc_driver = {
+	.probe		= tps6594_rtc_probe,
+	.driver		= {
+		.name	= "tps6594-rtc",
+	},
+	.id_table = tps6594_rtc_id_table,
+};
+
+module_platform_driver(tps6594_rtc_driver);
+MODULE_AUTHOR("Esteban Blanc <eblanc@baylibre.com>");
+MODULE_DESCRIPTION("TPS6594 RTC driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 7327e81352e9..cead018c3f06 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -8,9 +8,6 @@
  * Copyright IBM Corp. 1999, 2009
  */
 
-#define KMSG_COMPONENT "dasd"
-#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
-
 #include <linux/kmod.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
@@ -30,9 +27,6 @@
 #include <asm/itcw.h>
 #include <asm/diag.h>
 
-/* This is ugly... */
-#define PRINTK_HEADER "dasd:"
-
 #include "dasd_int.h"
 /*
  * SECTION: Constant definitions to be used within this file
@@ -313,39 +307,57 @@ static int dasd_state_basic_to_known(struct dasd_device *device)
  */
 static int dasd_state_basic_to_ready(struct dasd_device *device)
 {
-	int rc;
-	struct dasd_block *block;
-	struct gendisk *disk;
+	struct dasd_block *block = device->block;
+	struct queue_limits lim;
+	int rc = 0;
 
-	rc = 0;
-	block = device->block;
 	/* make disk known with correct capacity */
-	if (block) {
-		if (block->base->discipline->do_analysis != NULL)
-			rc = block->base->discipline->do_analysis(block);
-		if (rc) {
-			if (rc != -EAGAIN) {
-				device->state = DASD_STATE_UNFMT;
-				disk = device->block->gdp;
-				kobject_uevent(&disk_to_dev(disk)->kobj,
-					       KOBJ_CHANGE);
-				goto out;
-			}
-			return rc;
-		}
-		if (device->discipline->setup_blk_queue)
-			device->discipline->setup_blk_queue(block);
-		set_capacity(block->gdp,
-			     block->blocks << block->s2b_shift);
+	if (!block) {
 		device->state = DASD_STATE_READY;
-		rc = dasd_scan_partitions(block);
-		if (rc) {
-			device->state = DASD_STATE_BASIC;
+		goto out;
+	}
+
+	if (block->base->discipline->do_analysis != NULL)
+		rc = block->base->discipline->do_analysis(block);
+	if (rc) {
+		if (rc == -EAGAIN)
 			return rc;
-		}
-	} else {
-		device->state = DASD_STATE_READY;
+		device->state = DASD_STATE_UNFMT;
+		kobject_uevent(&disk_to_dev(device->block->gdp)->kobj,
+			       KOBJ_CHANGE);
+		goto out;
+	}
+
+	lim = queue_limits_start_update(block->gdp->queue);
+	lim.max_dev_sectors = device->discipline->max_sectors(block);
+	lim.max_hw_sectors = lim.max_dev_sectors;
+	lim.logical_block_size = block->bp_block;
+
+	if (device->discipline->has_discard) {
+		unsigned int max_bytes;
+
+		lim.discard_granularity = block->bp_block;
+
+		/* Calculate max_discard_sectors and make it PAGE aligned */
+		max_bytes = USHRT_MAX * block->bp_block;
+		max_bytes = ALIGN_DOWN(max_bytes, PAGE_SIZE);
+
+		lim.max_hw_discard_sectors = max_bytes / block->bp_block;
+		lim.max_write_zeroes_sectors = lim.max_hw_discard_sectors;
 	}
+	rc = queue_limits_commit_update(block->gdp->queue, &lim);
+	if (rc)
+		return rc;
+
+	set_capacity(block->gdp, block->blocks << block->s2b_shift);
+	device->state = DASD_STATE_READY;
+
+	rc = dasd_scan_partitions(block);
+	if (rc) {
+		device->state = DASD_STATE_BASIC;
+		return rc;
+	}
+
 out:
 	if (device->discipline->basic_to_ready)
 		rc = device->discipline->basic_to_ready(device);
@@ -412,7 +424,7 @@ dasd_state_ready_to_online(struct dasd_device * device)
 					KOBJ_CHANGE);
 			return 0;
 		}
-		disk_uevent(device->block->bdev_handle->bdev->bd_disk,
+		disk_uevent(file_bdev(device->block->bdev_file)->bd_disk,
 			    KOBJ_CHANGE);
 	}
 	return 0;
@@ -433,7 +445,7 @@ static int dasd_state_online_to_ready(struct dasd_device *device)
 
 	device->state = DASD_STATE_READY;
 	if (device->block && !(device->features & DASD_FEATURE_USERAW))
-		disk_uevent(device->block->bdev_handle->bdev->bd_disk,
+		disk_uevent(file_bdev(device->block->bdev_file)->bd_disk,
 			    KOBJ_CHANGE);
 	return 0;
 }
@@ -1301,7 +1313,6 @@ int dasd_term_IO(struct dasd_ccw_req *cqr)
 {
 	struct dasd_device *device;
 	int retries, rc;
-	char errorstring[ERRORLENGTH];
 
 	/* Check the cqr */
 	rc = dasd_check_cqr(cqr);
@@ -1340,10 +1351,8 @@ int dasd_term_IO(struct dasd_ccw_req *cqr)
 			rc = 0;
 			break;
 		default:
-			/* internal error 10 - unknown rc*/
-			snprintf(errorstring, ERRORLENGTH, "10 %d", rc);
-			dev_err(&device->cdev->dev, "An error occurred in the "
-				"DASD device driver, reason=%s\n", errorstring);
+			dev_err(&device->cdev->dev,
+				"Unexpected error during request termination %d\n", rc);
 			BUG();
 			break;
 		}
@@ -1362,7 +1371,6 @@ int dasd_start_IO(struct dasd_ccw_req *cqr)
 {
 	struct dasd_device *device;
 	int rc;
-	char errorstring[ERRORLENGTH];
 
 	/* Check the cqr */
 	rc = dasd_check_cqr(cqr);
@@ -1382,10 +1390,8 @@ int dasd_start_IO(struct dasd_ccw_req *cqr)
 		return -EPERM;
 	}
 	if (cqr->retries < 0) {
-		/* internal error 14 - start_IO run out of retries */
-		sprintf(errorstring, "14 %p", cqr);
-		dev_err(&device->cdev->dev, "An error occurred in the DASD "
-			"device driver, reason=%s\n", errorstring);
+		dev_err(&device->cdev->dev,
+			"Start I/O ran out of retries\n");
 		cqr->status = DASD_CQR_ERROR;
 		return -EIO;
 	}
@@ -1463,11 +1469,8 @@ int dasd_start_IO(struct dasd_ccw_req *cqr)
 			      "not accessible");
 		break;
 	default:
-		/* internal error 11 - unknown rc */
-		snprintf(errorstring, ERRORLENGTH, "11 %d", rc);
 		dev_err(&device->cdev->dev,
-			"An error occurred in the DASD device driver, "
-			"reason=%s\n", errorstring);
+			"Unexpected error during request start %d", rc);
 		BUG();
 		break;
 	}
@@ -1904,8 +1907,6 @@ static void __dasd_device_process_ccw_queue(struct dasd_device *device,
 static void __dasd_process_cqr(struct dasd_device *device,
 			       struct dasd_ccw_req *cqr)
 {
-	char errorstring[ERRORLENGTH];
-
 	switch (cqr->status) {
 	case DASD_CQR_SUCCESS:
 		cqr->status = DASD_CQR_DONE;
@@ -1917,11 +1918,8 @@ static void __dasd_process_cqr(struct dasd_device *device,
 		cqr->status = DASD_CQR_TERMINATED;
 		break;
 	default:
-		/* internal error 12 - wrong cqr status*/
-		snprintf(errorstring, ERRORLENGTH, "12 %p %x02", cqr, cqr->status);
 		dev_err(&device->cdev->dev,
-			"An error occurred in the DASD device driver, "
-			"reason=%s\n", errorstring);
+			"Unexpected CQR status %02x", cqr->status);
 		BUG();
 	}
 	if (cqr->callback)
@@ -1986,16 +1984,14 @@ static void __dasd_device_check_expire(struct dasd_device *device)
 		if (device->discipline->term_IO(cqr) != 0) {
 			/* Hmpf, try again in 5 sec */
 			dev_err(&device->cdev->dev,
-				"cqr %p timed out (%lus) but cannot be "
-				"ended, retrying in 5 s\n",
-				cqr, (cqr->expires/HZ));
+				"CQR timed out (%lus) but cannot be ended, retrying in 5s\n",
+				(cqr->expires / HZ));
 			cqr->expires += 5*HZ;
 			dasd_device_set_timer(device, 5*HZ);
 		} else {
 			dev_err(&device->cdev->dev,
-				"cqr %p timed out (%lus), %i retries "
-				"remaining\n", cqr, (cqr->expires/HZ),
-				cqr->retries);
+				"CQR timed out (%lus), %i retries remaining\n",
+				(cqr->expires / HZ), cqr->retries);
 		}
 		__dasd_device_check_autoquiesce_timeout(device, cqr);
 	}
@@ -2116,8 +2112,7 @@ int dasd_flush_device_queue(struct dasd_device *device)
 			if (rc) {
 				/* unable to terminate requeust */
 				dev_err(&device->cdev->dev,
-					"Flushing the DASD request queue "
-					"failed for request %p\n", cqr);
+					"Flushing the DASD request queue failed\n");
 				/* stop flush processing */
 				goto finished;
 			}
@@ -2633,8 +2628,7 @@ static int __dasd_cancel_req(struct dasd_ccw_req *cqr)
 		rc = device->discipline->term_IO(cqr);
 		if (rc) {
 			dev_err(&device->cdev->dev,
-				"Cancelling request %p failed with rc=%d\n",
-				cqr, rc);
+				"Cancelling request failed with rc=%d\n", rc);
 		} else {
 			cqr->stopclk = get_tod_clock();
 		}
@@ -3402,8 +3396,7 @@ static void dasd_generic_auto_online(void *data, async_cookie_t cookie)
 
 	ret = ccw_device_set_online(cdev);
 	if (ret)
-		pr_warn("%s: Setting the DASD online failed with rc=%d\n",
-			dev_name(&cdev->dev), ret);
+		dev_warn(&cdev->dev, "Setting the DASD online failed with rc=%d\n", ret);
 }
 
 /*
@@ -3490,8 +3483,11 @@ int dasd_generic_set_online(struct ccw_device *cdev,
 {
 	struct dasd_discipline *discipline;
 	struct dasd_device *device;
+	struct device *dev;
 	int rc;
 
+	dev = &cdev->dev;
+
 	/* first online clears initial online feature flag */
 	dasd_set_feature(cdev, DASD_FEATURE_INITIAL_ONLINE, 0);
 	device = dasd_create_device(cdev);
@@ -3504,11 +3500,10 @@ int dasd_generic_set_online(struct ccw_device *cdev,
 			/* Try to load the required module. */
 			rc = request_module(DASD_DIAG_MOD);
 			if (rc) {
-				pr_warn("%s Setting the DASD online failed "
-					"because the required module %s "
-					"could not be loaded (rc=%d)\n",
-					dev_name(&cdev->dev), DASD_DIAG_MOD,
-					rc);
+				dev_warn(dev, "Setting the DASD online failed "
+					 "because the required module %s "
+					 "could not be loaded (rc=%d)\n",
+					 DASD_DIAG_MOD, rc);
 				dasd_delete_device(device);
 				return -ENODEV;
 			}
@@ -3516,8 +3511,7 @@ int dasd_generic_set_online(struct ccw_device *cdev,
 		/* Module init could have failed, so check again here after
 		 * request_module(). */
 		if (!dasd_diag_discipline_pointer) {
-			pr_warn("%s Setting the DASD online failed because of missing DIAG discipline\n",
-				dev_name(&cdev->dev));
+			dev_warn(dev, "Setting the DASD online failed because of missing DIAG discipline\n");
 			dasd_delete_device(device);
 			return -ENODEV;
 		}
@@ -3527,37 +3521,33 @@ int dasd_generic_set_online(struct ccw_device *cdev,
 		dasd_delete_device(device);
 		return -EINVAL;
 	}
+	device->base_discipline = base_discipline;
 	if (!try_module_get(discipline->owner)) {
-		module_put(base_discipline->owner);
 		dasd_delete_device(device);
 		return -EINVAL;
 	}
-	device->base_discipline = base_discipline;
 	device->discipline = discipline;
 
 	/* check_device will allocate block device if necessary */
 	rc = discipline->check_device(device);
 	if (rc) {
-		pr_warn("%s Setting the DASD online with discipline %s failed with rc=%i\n",
-			dev_name(&cdev->dev), discipline->name, rc);
-		module_put(discipline->owner);
-		module_put(base_discipline->owner);
+		dev_warn(dev, "Setting the DASD online with discipline %s failed with rc=%i\n",
+			 discipline->name, rc);
 		dasd_delete_device(device);
 		return rc;
 	}
 
 	dasd_set_target_state(device, DASD_STATE_ONLINE);
 	if (device->state <= DASD_STATE_KNOWN) {
-		pr_warn("%s Setting the DASD online failed because of a missing discipline\n",
-			dev_name(&cdev->dev));
+		dev_warn(dev, "Setting the DASD online failed because of a missing discipline\n");
 		rc = -ENODEV;
 		dasd_set_target_state(device, DASD_STATE_NEW);
 		if (device->block)
 			dasd_free_block(device->block);
 		dasd_delete_device(device);
-	} else
-		pr_debug("dasd_generic device %s found\n",
-				dev_name(&cdev->dev));
+	} else {
+		dev_dbg(dev, "dasd_generic device found\n");
+	}
 
 	wait_event(dasd_init_waitq, _wait_for_device(device));
 
@@ -3568,10 +3558,13 @@ EXPORT_SYMBOL_GPL(dasd_generic_set_online);
 
 int dasd_generic_set_offline(struct ccw_device *cdev)
 {
+	int max_count, open_count, rc;
 	struct dasd_device *device;
 	struct dasd_block *block;
-	int max_count, open_count, rc;
 	unsigned long flags;
+	struct device *dev;
+
+	dev = &cdev->dev;
 
 	rc = 0;
 	spin_lock_irqsave(get_ccwdev_lock(cdev), flags);
@@ -3588,15 +3581,14 @@ int dasd_generic_set_offline(struct ccw_device *cdev)
 	 * in the other openers.
 	 */
 	if (device->block) {
-		max_count = device->block->bdev_handle ? 0 : -1;
+		max_count = device->block->bdev_file ? 0 : -1;
 		open_count = atomic_read(&device->block->open_count);
 		if (open_count > max_count) {
 			if (open_count > 0)
-				pr_warn("%s: The DASD cannot be set offline with open count %i\n",
-					dev_name(&cdev->dev), open_count);
+				dev_warn(dev, "The DASD cannot be set offline with open count %i\n",
+					 open_count);
 			else
-				pr_warn("%s: The DASD cannot be set offline while it is in use\n",
-					dev_name(&cdev->dev));
+				dev_warn(dev, "The DASD cannot be set offline while it is in use\n");
 			rc = -EBUSY;
 			goto out_err;
 		}
@@ -3634,8 +3626,8 @@ int dasd_generic_set_offline(struct ccw_device *cdev)
 		 * so sync bdev first and then wait for our queues to become
 		 * empty
 		 */
-		if (device->block && device->block->bdev_handle)
-			bdev_mark_dead(device->block->bdev_handle->bdev, false);
+		if (device->block && device->block->bdev_file)
+			bdev_mark_dead(file_bdev(device->block->bdev_file), false);
 		dasd_schedule_device_bh(device);
 		rc = wait_event_interruptible(shutdown_waitq,
 					      _wait_for_empty_queues(device));
@@ -3956,8 +3948,8 @@ static int dasd_handle_autoquiesce(struct dasd_device *device,
 	if (dasd_eer_enabled(device))
 		dasd_eer_write(device, NULL, DASD_EER_AUTOQUIESCE);
 
-	pr_info("%s: The DASD has been put in the quiesce state\n",
-		dev_name(&device->cdev->dev));
+	dev_info(&device->cdev->dev,
+		 "The DASD has been put in the quiesce state\n");
 	dasd_device_set_stop_bits(device, DASD_STOPPED_QUIESCE);
 
 	if (device->features & DASD_FEATURE_REQUEUEQUIESCE)
@@ -3977,10 +3969,8 @@ static struct dasd_ccw_req *dasd_generic_build_rdc(struct dasd_device *device,
 				   NULL);
 
 	if (IS_ERR(cqr)) {
-		/* internal error 13 - Allocating the RDC request failed*/
-		dev_err(&device->cdev->dev,
-			 "An error occurred in the DASD device driver, "
-			 "reason=%s\n", "13");
+		DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "%s",
+				"Could not allocate RDC request");
 		return cqr;
 	}
 
diff --git a/drivers/s390/block/dasd_3990_erp.c b/drivers/s390/block/dasd_3990_erp.c
index 89957bb7244d..459b7f8ac883 100644
--- a/drivers/s390/block/dasd_3990_erp.c
+++ b/drivers/s390/block/dasd_3990_erp.c
@@ -7,13 +7,9 @@
  *
  */
 
-#define KMSG_COMPONENT "dasd-eckd"
-
 #include <linux/timer.h>
 #include <asm/idals.h>
 
-#define PRINTK_HEADER "dasd_erp(3990): "
-
 #include "dasd_int.h"
 #include "dasd_eckd.h"
 
@@ -398,7 +394,6 @@ dasd_3990_handle_env_data(struct dasd_ccw_req * erp, char *sense)
 	struct dasd_device *device = erp->startdev;
 	char msg_format = (sense[7] & 0xF0);
 	char msg_no = (sense[7] & 0x0F);
-	char errorstring[ERRORLENGTH];
 
 	switch (msg_format) {
 	case 0x00:		/* Format 0 - Program or System Checks */
@@ -1004,12 +999,9 @@ dasd_3990_handle_env_data(struct dasd_ccw_req * erp, char *sense)
 		}
 		break;
 
-	default:	/* unknown message format - should not happen
-			   internal error 03 - unknown message format */
-		snprintf(errorstring, ERRORLENGTH, "03 %x02", msg_format);
+	default:
 		dev_err(&device->cdev->dev,
-			 "An error occurred in the DASD device driver, "
-			 "reason=%s\n", errorstring);
+			"Unknown message format %02x", msg_format);
 		break;
 	}			/* end switch message format */
 
@@ -1056,11 +1048,9 @@ dasd_3990_erp_com_rej(struct dasd_ccw_req * erp, char *sense)
 		set_bit(DASD_CQR_SUPPRESS_CR, &erp->refers->flags);
 		erp = dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED);
 	} else {
-		/* fatal error -  set status to FAILED
-		   internal error 09 - Command Reject */
 		if (!test_bit(DASD_CQR_SUPPRESS_CR, &erp->flags))
 			dev_err(&device->cdev->dev,
-				"An error occurred in the DASD device driver, reason=09\n");
+				"An I/O command request was rejected\n");
 
 		erp = dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED);
 	}
@@ -1128,13 +1118,7 @@ dasd_3990_erp_equip_check(struct dasd_ccw_req * erp, char *sense)
 	erp->function = dasd_3990_erp_equip_check;
 
 	if (sense[1] & SNS1_WRITE_INHIBITED) {
-		dev_info(&device->cdev->dev,
-			    "Write inhibited path encountered\n");
-
-		/* vary path offline
-		   internal error 04 - Path should be varied off-line.*/
-		dev_err(&device->cdev->dev, "An error occurred in the DASD "
-			"device driver, reason=%s\n", "04");
+		dev_err(&device->cdev->dev, "Write inhibited path encountered\n");
 
 		erp = dasd_3990_erp_action_1(erp);
 
@@ -1285,11 +1269,7 @@ dasd_3990_erp_inv_format(struct dasd_ccw_req * erp, char *sense)
 		erp = dasd_3990_erp_action_4(erp, sense);
 
 	} else {
-		/* internal error 06 - The track format is not valid*/
-		dev_err(&device->cdev->dev,
-			"An error occurred in the DASD device driver, "
-			"reason=%s\n", "06");
-
+		dev_err(&device->cdev->dev, "Track format is not valid\n");
 		erp = dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED);
 	}
 
@@ -1663,9 +1643,8 @@ dasd_3990_erp_action_1B_32(struct dasd_ccw_req * default_erp, char *sense)
 				     sizeof(struct LO_eckd_data), device);
 
 	if (IS_ERR(erp)) {
-		/* internal error 01 - Unable to allocate ERP */
-		dev_err(&device->cdev->dev, "An error occurred in the DASD "
-			"device driver, reason=%s\n", "01");
+		DBF_DEV_EVENT(DBF_ERR, device, "%s",
+			      "Unable to allocate ERP request (1B 32)");
 		return dasd_3990_erp_cleanup(default_erp, DASD_CQR_FAILED);
 	}
 
@@ -1807,10 +1786,8 @@ dasd_3990_update_1B(struct dasd_ccw_req * previous_erp, char *sense)
 	cpa = previous_erp->irb.scsw.cmd.cpa;
 
 	if (cpa == 0) {
-		/* internal error 02 -
-		   Unable to determine address of the CCW to be restarted */
-		dev_err(&device->cdev->dev, "An error occurred in the DASD "
-			"device driver, reason=%s\n", "02");
+		dev_err(&device->cdev->dev,
+			"Unable to determine address of to be restarted CCW\n");
 
 		previous_erp->status = DASD_CQR_FAILED;
 
@@ -2009,15 +1986,9 @@ dasd_3990_erp_compound_config(struct dasd_ccw_req * erp, char *sense)
 {
 
 	if ((sense[25] & DASD_SENSE_BIT_1) && (sense[26] & DASD_SENSE_BIT_2)) {
-
-		/* set to suspended duplex state then restart
-		   internal error 05 - Set device to suspended duplex state
-		   should be done */
 		struct dasd_device *device = erp->startdev;
 		dev_err(&device->cdev->dev,
-			"An error occurred in the DASD device driver, "
-			"reason=%s\n", "05");
-
+			"Compound configuration error occurred\n");
 	}
 
 	erp->function = dasd_3990_erp_compound_config;
@@ -2153,10 +2124,9 @@ dasd_3990_erp_inspect_32(struct dasd_ccw_req * erp, char *sense)
 			erp = dasd_3990_erp_int_req(erp);
 			break;
 
-		case 0x0F:  /* length mismatch during update write command
-			       internal error 08 - update write command error*/
-			dev_err(&device->cdev->dev, "An error occurred in the "
-				"DASD device driver, reason=%s\n", "08");
+		case 0x0F:
+			dev_err(&device->cdev->dev,
+				"Update write command error occurred\n");
 
 			erp = dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED);
 			break;
@@ -2165,12 +2135,9 @@ dasd_3990_erp_inspect_32(struct dasd_ccw_req * erp, char *sense)
 			erp = dasd_3990_erp_action_10_32(erp, sense);
 			break;
 
-		case 0x15:	/* next track outside defined extend
-				   internal error 07 - The next track is not
-				   within the defined storage extent */
+		case 0x15:
 			dev_err(&device->cdev->dev,
-				"An error occurred in the DASD device driver, "
-				"reason=%s\n", "07");
+				"Track outside defined extent error occurred\n");
 
 			erp = dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED);
 			break;
@@ -2663,7 +2630,7 @@ dasd_3990_erp_further_erp(struct dasd_ccw_req *erp)
 		 * necessary
 		 */
 		dev_err(&device->cdev->dev,
-			"ERP %p has run out of retries and failed\n", erp);
+			"ERP %px has run out of retries and failed\n", erp);
 
 		erp->status = DASD_CQR_FAILED;
 	}
@@ -2704,8 +2671,7 @@ dasd_3990_erp_handle_match_erp(struct dasd_ccw_req *erp_head,
 	while (erp_done != erp) {
 
 		if (erp_done == NULL)	/* end of chain reached */
-			panic(PRINTK_HEADER "Programming error in ERP! The "
-			      "original request was lost\n");
+			panic("Programming error in ERP! The original request was lost\n");
 
 		/* remove the request from the device queue */
 		list_del(&erp_done->blocklist);
@@ -2786,11 +2752,9 @@ dasd_3990_erp_action(struct dasd_ccw_req * cqr)
 			    "ERP chain at BEGINNING of ERP-ACTION\n");
 		for (temp_erp = cqr;
 		     temp_erp != NULL; temp_erp = temp_erp->refers) {
-
 			dev_err(&device->cdev->dev,
-				    "ERP %p (%02x) refers to %p\n",
-				    temp_erp, temp_erp->status,
-				    temp_erp->refers);
+				"ERP %px (%02x) refers to %px\n",
+				temp_erp, temp_erp->status, temp_erp->refers);
 		}
 	}
 
@@ -2837,11 +2801,9 @@ dasd_3990_erp_action(struct dasd_ccw_req * cqr)
 			    "ERP chain at END of ERP-ACTION\n");
 		for (temp_erp = erp;
 		     temp_erp != NULL; temp_erp = temp_erp->refers) {
-
 			dev_err(&device->cdev->dev,
-				    "ERP %p (%02x) refers to %p\n",
-				    temp_erp, temp_erp->status,
-				    temp_erp->refers);
+				"ERP %px (%02x) refers to %px\n",
+				temp_erp, temp_erp->status, temp_erp->refers);
 		}
 	}
 
diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c
index c9740ae88d1a..e84cd5436556 100644
--- a/drivers/s390/block/dasd_alias.c
+++ b/drivers/s390/block/dasd_alias.c
@@ -6,20 +6,12 @@
  * Author(s): Stefan Weinhuber <wein@de.ibm.com>
  */
 
-#define KMSG_COMPONENT "dasd-eckd"
-
 #include <linux/list.h>
 #include <linux/slab.h>
 #include <asm/ebcdic.h>
 #include "dasd_int.h"
 #include "dasd_eckd.h"
 
-#ifdef PRINTK_HEADER
-#undef PRINTK_HEADER
-#endif				/* PRINTK_HEADER */
-#define PRINTK_HEADER "dasd(eckd):"
-
-
 /*
  * General concept of alias management:
  * - PAV and DASD alias management is specific to the eckd discipline.
diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c
index c4e36650c426..0316c20823ee 100644
--- a/drivers/s390/block/dasd_devmap.c
+++ b/drivers/s390/block/dasd_devmap.c
@@ -13,8 +13,6 @@
  *
  */
 
-#define KMSG_COMPONENT "dasd"
-
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -24,8 +22,6 @@
 #include <linux/uaccess.h>
 #include <asm/ipl.h>
 
-/* This is ugly... */
-#define PRINTK_HEADER "dasd_devmap:"
 #define DASD_MAX_PARAMS 256
 
 #include "dasd_int.h"
@@ -1114,7 +1110,7 @@ dasd_use_diag_show(struct device *dev, struct device_attribute *attr, char *buf)
 		use_diag = (devmap->features & DASD_FEATURE_USEDIAG) != 0;
 	else
 		use_diag = (DASD_FEATURE_DEFAULT & DASD_FEATURE_USEDIAG) != 0;
-	return sprintf(buf, use_diag ? "1\n" : "0\n");
+	return sysfs_emit(buf, use_diag ? "1\n" : "0\n");
 }
 
 static ssize_t
@@ -1163,7 +1159,7 @@ dasd_use_raw_show(struct device *dev, struct device_attribute *attr, char *buf)
 		use_raw = (devmap->features & DASD_FEATURE_USERAW) != 0;
 	else
 		use_raw = (DASD_FEATURE_DEFAULT & DASD_FEATURE_USERAW) != 0;
-	return sprintf(buf, use_raw ? "1\n" : "0\n");
+	return sysfs_emit(buf, use_raw ? "1\n" : "0\n");
 }
 
 static ssize_t
@@ -1259,7 +1255,7 @@ dasd_access_show(struct device *dev, struct device_attribute *attr,
 	if (count < 0)
 		return count;
 
-	return sprintf(buf, "%d\n", count);
+	return sysfs_emit(buf, "%d\n", count);
 }
 
 static DEVICE_ATTR(host_access_count, 0444, dasd_access_show, NULL);
@@ -1338,19 +1334,19 @@ static ssize_t dasd_alias_show(struct device *dev,
 
 	device = dasd_device_from_cdev(to_ccwdev(dev));
 	if (IS_ERR(device))
-		return sprintf(buf, "0\n");
+		return sysfs_emit(buf, "0\n");
 
 	if (device->discipline && device->discipline->get_uid &&
 	    !device->discipline->get_uid(device, &uid)) {
 		if (uid.type == UA_BASE_PAV_ALIAS ||
 		    uid.type == UA_HYPER_PAV_ALIAS) {
 			dasd_put_device(device);
-			return sprintf(buf, "1\n");
+			return sysfs_emit(buf, "1\n");
 		}
 	}
 	dasd_put_device(device);
 
-	return sprintf(buf, "0\n");
+	return sysfs_emit(buf, "0\n");
 }
 
 static DEVICE_ATTR(alias, 0444, dasd_alias_show, NULL);
@@ -1412,15 +1408,9 @@ dasd_uid_show(struct device *dev, struct device_attribute *attr, char *buf)
 			break;
 		}
 
-		if (strlen(uid.vduit) > 0)
-			snprintf(uid_string, sizeof(uid_string),
-				 "%s.%s.%04x.%s.%s",
-				 uid.vendor, uid.serial, uid.ssid, ua_string,
-				 uid.vduit);
-		else
-			snprintf(uid_string, sizeof(uid_string),
-				 "%s.%s.%04x.%s",
-				 uid.vendor, uid.serial, uid.ssid, ua_string);
+		snprintf(uid_string, sizeof(uid_string), "%s.%s.%04x.%s%s%s",
+			 uid.vendor, uid.serial, uid.ssid, ua_string,
+			 uid.vduit[0] ? "." : "", uid.vduit);
 	}
 	dasd_put_device(device);
 
@@ -1862,7 +1852,7 @@ static ssize_t dasd_pm_show(struct device *dev,
 
 	device = dasd_device_from_cdev(to_ccwdev(dev));
 	if (IS_ERR(device))
-		return sprintf(buf, "0\n");
+		return sysfs_emit(buf, "0\n");
 
 	opm = dasd_path_get_opm(device);
 	nppm = dasd_path_get_nppm(device);
@@ -1872,8 +1862,8 @@ static ssize_t dasd_pm_show(struct device *dev,
 	ifccpm = dasd_path_get_ifccpm(device);
 	dasd_put_device(device);
 
-	return sprintf(buf, "%02x %02x %02x %02x %02x %02x\n", opm, nppm,
-		       cablepm, cuirpm, hpfpm, ifccpm);
+	return sysfs_emit(buf, "%02x %02x %02x %02x %02x %02x\n", opm, nppm,
+			  cablepm, cuirpm, hpfpm, ifccpm);
 }
 
 static DEVICE_ATTR(path_masks, 0444, dasd_pm_show, NULL);
diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c
index 2e4e555b37c3..ea4b1d01bb76 100644
--- a/drivers/s390/block/dasd_diag.c
+++ b/drivers/s390/block/dasd_diag.c
@@ -8,8 +8,6 @@
  *
  */
 
-#define KMSG_COMPONENT "dasd"
-
 #include <linux/kernel_stat.h>
 #include <linux/stddef.h>
 #include <linux/kernel.h>
@@ -31,8 +29,6 @@
 #include "dasd_int.h"
 #include "dasd_diag.h"
 
-#define PRINTK_HEADER "dasd(diag):"
-
 MODULE_LICENSE("GPL");
 
 /* The maximum number of blocks per request (max_blocks) is dependent on the
@@ -621,25 +617,9 @@ dasd_diag_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req,
 		    "dump sense not available for DIAG data");
 }
 
-/*
- * Initialize block layer request queue.
- */
-static void dasd_diag_setup_blk_queue(struct dasd_block *block)
+static unsigned int dasd_diag_max_sectors(struct dasd_block *block)
 {
-	unsigned int logical_block_size = block->bp_block;
-	struct request_queue *q = block->gdp->queue;
-	int max;
-
-	max = DIAG_MAX_BLOCKS << block->s2b_shift;
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
-	q->limits.max_dev_sectors = max;
-	blk_queue_logical_block_size(q, logical_block_size);
-	blk_queue_max_hw_sectors(q, max);
-	blk_queue_max_segments(q, USHRT_MAX);
-	/* With page sized segments each segment can be translated into one idaw/tidaw */
-	blk_queue_max_segment_size(q, PAGE_SIZE);
-	blk_queue_segment_boundary(q, PAGE_SIZE - 1);
-	blk_queue_dma_alignment(q, PAGE_SIZE - 1);
+	return DIAG_MAX_BLOCKS << block->s2b_shift;
 }
 
 static int dasd_diag_pe_handler(struct dasd_device *device,
@@ -652,10 +632,10 @@ static struct dasd_discipline dasd_diag_discipline = {
 	.owner = THIS_MODULE,
 	.name = "DIAG",
 	.ebcname = "DIAG",
+	.max_sectors = dasd_diag_max_sectors,
 	.check_device = dasd_diag_check_device,
 	.pe_handler = dasd_diag_pe_handler,
 	.fill_geometry = dasd_diag_fill_geometry,
-	.setup_blk_queue = dasd_diag_setup_blk_queue,
 	.start_IO = dasd_start_diag,
 	.term_IO = dasd_diag_term_IO,
 	.handle_terminated_request = dasd_diag_handle_terminated_request,
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index bd89b032968a..373c1a86c33e 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -10,8 +10,6 @@
  * Author.........: Nigel Hislop <hislop_nigel@emc.com>
  */
 
-#define KMSG_COMPONENT "dasd-eckd"
-
 #include <linux/stddef.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -37,11 +35,6 @@
 #include "dasd_int.h"
 #include "dasd_eckd.h"
 
-#ifdef PRINTK_HEADER
-#undef PRINTK_HEADER
-#endif				/* PRINTK_HEADER */
-#define PRINTK_HEADER "dasd(eckd):"
-
 /*
  * raw track access always map to 64k in memory
  * so it maps to 16 blocks of 4k per track
@@ -1072,22 +1065,14 @@ static void dasd_eckd_read_fc_security(struct dasd_device *device)
 	}
 }
 
-static void dasd_eckd_get_uid_string(struct dasd_conf *conf,
-				     char *print_uid)
+static void dasd_eckd_get_uid_string(struct dasd_conf *conf, char *print_uid)
 {
 	struct dasd_uid uid;
 
 	create_uid(conf, &uid);
-	if (strlen(uid.vduit) > 0)
-		snprintf(print_uid, DASD_UID_STRLEN,
-			 "%s.%s.%04x.%02x.%s",
-			 uid.vendor, uid.serial, uid.ssid,
-			 uid.real_unit_addr, uid.vduit);
-	else
-		snprintf(print_uid, DASD_UID_STRLEN,
-			 "%s.%s.%04x.%02x",
-			 uid.vendor, uid.serial, uid.ssid,
-			 uid.real_unit_addr);
+	snprintf(print_uid, DASD_UID_STRLEN, "%s.%s.%04x.%02x%s%s",
+		 uid.vendor, uid.serial, uid.ssid, uid.real_unit_addr,
+		 uid.vduit[0] ? "." : "", uid.vduit);
 }
 
 static int dasd_eckd_check_cabling(struct dasd_device *device,
@@ -5529,15 +5514,15 @@ dasd_eckd_ioctl(struct dasd_block *block, unsigned int cmd, void __user *argp)
  * and return number of printed chars.
  */
 static void
-dasd_eckd_dump_ccw_range(struct ccw1 *from, struct ccw1 *to, char *page)
+dasd_eckd_dump_ccw_range(struct dasd_device *device, struct ccw1 *from,
+			 struct ccw1 *to, char *page)
 {
 	int len, count;
 	char *datap;
 
 	len = 0;
 	while (from <= to) {
-		len += sprintf(page + len, PRINTK_HEADER
-			       " CCW %p: %08X %08X DAT:",
+		len += sprintf(page + len, "CCW %px: %08X %08X DAT:",
 			       from, ((int *) from)[0], ((int *) from)[1]);
 
 		/* get pointer to data (consider IDALs) */
@@ -5560,7 +5545,7 @@ dasd_eckd_dump_ccw_range(struct ccw1 *from, struct ccw1 *to, char *page)
 		from++;
 	}
 	if (len > 0)
-		printk(KERN_ERR "%s", page);
+		dev_err(&device->cdev->dev, "%s", page);
 }
 
 static void
@@ -5591,9 +5576,12 @@ dasd_eckd_dump_sense_dbf(struct dasd_device *device, struct irb *irb,
 static void dasd_eckd_dump_sense_ccw(struct dasd_device *device,
 				 struct dasd_ccw_req *req, struct irb *irb)
 {
-	char *page;
 	struct ccw1 *first, *last, *fail, *from, *to;
+	struct device *dev;
 	int len, sl, sct;
+	char *page;
+
+	dev = &device->cdev->dev;
 
 	page = (char *) get_zeroed_page(GFP_ATOMIC);
 	if (page == NULL) {
@@ -5602,24 +5590,18 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device,
 		return;
 	}
 	/* dump the sense data */
-	len = sprintf(page, PRINTK_HEADER
-		      " I/O status report for device %s:\n",
-		      dev_name(&device->cdev->dev));
-	len += sprintf(page + len, PRINTK_HEADER
-		       " in req: %p CC:%02X FC:%02X AC:%02X SC:%02X DS:%02X "
-		       "CS:%02X RC:%d\n",
+	len = sprintf(page, "I/O status report:\n");
+	len += sprintf(page + len,
+		       "in req: %px CC:%02X FC:%02X AC:%02X SC:%02X DS:%02X CS:%02X RC:%d\n",
 		       req, scsw_cc(&irb->scsw), scsw_fctl(&irb->scsw),
 		       scsw_actl(&irb->scsw), scsw_stctl(&irb->scsw),
 		       scsw_dstat(&irb->scsw), scsw_cstat(&irb->scsw),
 		       req ? req->intrc : 0);
-	len += sprintf(page + len, PRINTK_HEADER
-		       " device %s: Failing CCW: %p\n",
-		       dev_name(&device->cdev->dev),
+	len += sprintf(page + len, "Failing CCW: %px\n",
 		       phys_to_virt(irb->scsw.cmd.cpa));
 	if (irb->esw.esw0.erw.cons) {
 		for (sl = 0; sl < 4; sl++) {
-			len += sprintf(page + len, PRINTK_HEADER
-				       " Sense(hex) %2d-%2d:",
+			len += sprintf(page + len, "Sense(hex) %2d-%2d:",
 				       (8 * sl), ((8 * sl) + 7));
 
 			for (sct = 0; sct < 8; sct++) {
@@ -5631,23 +5613,20 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device,
 
 		if (irb->ecw[27] & DASD_SENSE_BIT_0) {
 			/* 24 Byte Sense Data */
-			sprintf(page + len, PRINTK_HEADER
-				" 24 Byte: %x MSG %x, "
-				"%s MSGb to SYSOP\n",
+			sprintf(page + len,
+				"24 Byte: %x MSG %x, %s MSGb to SYSOP\n",
 				irb->ecw[7] >> 4, irb->ecw[7] & 0x0f,
 				irb->ecw[1] & 0x10 ? "" : "no");
 		} else {
 			/* 32 Byte Sense Data */
-			sprintf(page + len, PRINTK_HEADER
-				" 32 Byte: Format: %x "
-				"Exception class %x\n",
+			sprintf(page + len,
+				"32 Byte: Format: %x Exception class %x\n",
 				irb->ecw[6] & 0x0f, irb->ecw[22] >> 4);
 		}
 	} else {
-		sprintf(page + len, PRINTK_HEADER
-			" SORRY - NO VALID SENSE AVAILABLE\n");
+		sprintf(page + len, "SORRY - NO VALID SENSE AVAILABLE\n");
 	}
-	printk(KERN_ERR "%s", page);
+	dev_err(dev, "%s", page);
 
 	if (req) {
 		/* req == NULL for unsolicited interrupts */
@@ -5656,8 +5635,8 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device,
 		first = req->cpaddr;
 		for (last = first; last->flags & (CCW_FLAG_CC | CCW_FLAG_DC); last++);
 		to = min(first + 6, last);
-		printk(KERN_ERR PRINTK_HEADER " Related CP in req: %p\n", req);
-		dasd_eckd_dump_ccw_range(first, to, page);
+		dev_err(dev, "Related CP in req: %px\n", req);
+		dasd_eckd_dump_ccw_range(device, first, to, page);
 
 		/* print failing CCW area (maximum 4) */
 		/* scsw->cda is either valid or zero  */
@@ -5665,19 +5644,19 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device,
 		fail = phys_to_virt(irb->scsw.cmd.cpa); /* failing CCW */
 		if (from <  fail - 2) {
 			from = fail - 2;     /* there is a gap - print header */
-			printk(KERN_ERR PRINTK_HEADER "......\n");
+			dev_err(dev, "......\n");
 		}
 		to = min(fail + 1, last);
-		dasd_eckd_dump_ccw_range(from, to, page + len);
+		dasd_eckd_dump_ccw_range(device, from, to, page + len);
 
 		/* print last CCWs (maximum 2) */
 		len = 0;
 		from = max(from, ++to);
 		if (from < last - 1) {
 			from = last - 1;     /* there is a gap - print header */
-			printk(KERN_ERR PRINTK_HEADER "......\n");
+			dev_err(dev, "......\n");
 		}
-		dasd_eckd_dump_ccw_range(from, last, page + len);
+		dasd_eckd_dump_ccw_range(device, from, last, page + len);
 	}
 	free_page((unsigned long) page);
 }
@@ -5701,11 +5680,9 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device,
 		return;
 	}
 	/* dump the sense data */
-	len = sprintf(page, PRINTK_HEADER
-		      " I/O status report for device %s:\n",
-		      dev_name(&device->cdev->dev));
-	len += sprintf(page + len, PRINTK_HEADER
-		       " in req: %p CC:%02X FC:%02X AC:%02X SC:%02X DS:%02X "
+	len = sprintf(page, "I/O status report:\n");
+	len += sprintf(page + len,
+		       "in req: %px CC:%02X FC:%02X AC:%02X SC:%02X DS:%02X "
 		       "CS:%02X fcxs:%02X schxs:%02X RC:%d\n",
 		       req, scsw_cc(&irb->scsw), scsw_fctl(&irb->scsw),
 		       scsw_actl(&irb->scsw), scsw_stctl(&irb->scsw),
@@ -5713,9 +5690,7 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device,
 		       irb->scsw.tm.fcxs,
 		       (irb->scsw.tm.ifob << 7) | irb->scsw.tm.sesq,
 		       req ? req->intrc : 0);
-	len += sprintf(page + len, PRINTK_HEADER
-		       " device %s: Failing TCW: %p\n",
-		       dev_name(&device->cdev->dev),
+	len += sprintf(page + len, "Failing TCW: %px\n",
 		       phys_to_virt(irb->scsw.tm.tcw));
 
 	tsb = NULL;
@@ -5724,47 +5699,37 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device,
 		tsb = tcw_get_tsb(phys_to_virt(irb->scsw.tm.tcw));
 
 	if (tsb) {
-		len += sprintf(page + len, PRINTK_HEADER
-			       " tsb->length %d\n", tsb->length);
-		len += sprintf(page + len, PRINTK_HEADER
-			       " tsb->flags %x\n", tsb->flags);
-		len += sprintf(page + len, PRINTK_HEADER
-			       " tsb->dcw_offset %d\n", tsb->dcw_offset);
-		len += sprintf(page + len, PRINTK_HEADER
-			       " tsb->count %d\n", tsb->count);
+		len += sprintf(page + len, "tsb->length %d\n", tsb->length);
+		len += sprintf(page + len, "tsb->flags %x\n", tsb->flags);
+		len += sprintf(page + len, "tsb->dcw_offset %d\n", tsb->dcw_offset);
+		len += sprintf(page + len, "tsb->count %d\n", tsb->count);
 		residual = tsb->count - 28;
-		len += sprintf(page + len, PRINTK_HEADER
-			       " residual %d\n", residual);
+		len += sprintf(page + len, "residual %d\n", residual);
 
 		switch (tsb->flags & 0x07) {
 		case 1:	/* tsa_iostat */
-			len += sprintf(page + len, PRINTK_HEADER
-			       " tsb->tsa.iostat.dev_time %d\n",
+			len += sprintf(page + len, "tsb->tsa.iostat.dev_time %d\n",
 				       tsb->tsa.iostat.dev_time);
-			len += sprintf(page + len, PRINTK_HEADER
-			       " tsb->tsa.iostat.def_time %d\n",
+			len += sprintf(page + len, "tsb->tsa.iostat.def_time %d\n",
 				       tsb->tsa.iostat.def_time);
-			len += sprintf(page + len, PRINTK_HEADER
-			       " tsb->tsa.iostat.queue_time %d\n",
+			len += sprintf(page + len, "tsb->tsa.iostat.queue_time %d\n",
 				       tsb->tsa.iostat.queue_time);
-			len += sprintf(page + len, PRINTK_HEADER
-			       " tsb->tsa.iostat.dev_busy_time %d\n",
+			len += sprintf(page + len, "tsb->tsa.iostat.dev_busy_time %d\n",
 				       tsb->tsa.iostat.dev_busy_time);
-			len += sprintf(page + len, PRINTK_HEADER
-			       " tsb->tsa.iostat.dev_act_time %d\n",
+			len += sprintf(page + len, "tsb->tsa.iostat.dev_act_time %d\n",
 				       tsb->tsa.iostat.dev_act_time);
 			sense = tsb->tsa.iostat.sense;
 			break;
 		case 2: /* ts_ddpc */
-			len += sprintf(page + len, PRINTK_HEADER
-			       " tsb->tsa.ddpc.rc %d\n", tsb->tsa.ddpc.rc);
+			len += sprintf(page + len, "tsb->tsa.ddpc.rc %d\n",
+				       tsb->tsa.ddpc.rc);
 			for (sl = 0; sl < 2; sl++) {
-				len += sprintf(page + len, PRINTK_HEADER
-					       " tsb->tsa.ddpc.rcq %2d-%2d: ",
+				len += sprintf(page + len,
+					       "tsb->tsa.ddpc.rcq %2d-%2d: ",
 					       (8 * sl), ((8 * sl) + 7));
 				rcq = tsb->tsa.ddpc.rcq;
 				for (sct = 0; sct < 8; sct++) {
-					len += sprintf(page + len, " %02x",
+					len += sprintf(page + len, "%02x",
 						       rcq[8 * sl + sct]);
 				}
 				len += sprintf(page + len, "\n");
@@ -5772,15 +5737,15 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device,
 			sense = tsb->tsa.ddpc.sense;
 			break;
 		case 3: /* tsa_intrg */
-			len += sprintf(page + len, PRINTK_HEADER
-				      " tsb->tsa.intrg.: not supported yet\n");
+			len += sprintf(page + len,
+				      "tsb->tsa.intrg.: not supported yet\n");
 			break;
 		}
 
 		if (sense) {
 			for (sl = 0; sl < 4; sl++) {
-				len += sprintf(page + len, PRINTK_HEADER
-					       " Sense(hex) %2d-%2d:",
+				len += sprintf(page + len,
+					       "Sense(hex) %2d-%2d:",
 					       (8 * sl), ((8 * sl) + 7));
 				for (sct = 0; sct < 8; sct++) {
 					len += sprintf(page + len, " %02x",
@@ -5791,27 +5756,23 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device,
 
 			if (sense[27] & DASD_SENSE_BIT_0) {
 				/* 24 Byte Sense Data */
-				sprintf(page + len, PRINTK_HEADER
-					" 24 Byte: %x MSG %x, "
-					"%s MSGb to SYSOP\n",
+				sprintf(page + len,
+					"24 Byte: %x MSG %x, %s MSGb to SYSOP\n",
 					sense[7] >> 4, sense[7] & 0x0f,
 					sense[1] & 0x10 ? "" : "no");
 			} else {
 				/* 32 Byte Sense Data */
-				sprintf(page + len, PRINTK_HEADER
-					" 32 Byte: Format: %x "
-					"Exception class %x\n",
+				sprintf(page + len,
+					"32 Byte: Format: %x Exception class %x\n",
 					sense[6] & 0x0f, sense[22] >> 4);
 			}
 		} else {
-			sprintf(page + len, PRINTK_HEADER
-				" SORRY - NO VALID SENSE AVAILABLE\n");
+			sprintf(page + len, "SORRY - NO VALID SENSE AVAILABLE\n");
 		}
 	} else {
-		sprintf(page + len, PRINTK_HEADER
-			" SORRY - NO TSB DATA AVAILABLE\n");
+		sprintf(page + len, "SORRY - NO TSB DATA AVAILABLE\n");
 	}
-	printk(KERN_ERR "%s", page);
+	dev_err(&device->cdev->dev, "%s", page);
 	free_page((unsigned long) page);
 }
 
@@ -6865,17 +6826,9 @@ static void dasd_eckd_handle_hpf_error(struct dasd_device *device,
 	dasd_schedule_requeue(device);
 }
 
-/*
- * Initialize block layer request queue.
- */
-static void dasd_eckd_setup_blk_queue(struct dasd_block *block)
+static unsigned int dasd_eckd_max_sectors(struct dasd_block *block)
 {
-	unsigned int logical_block_size = block->bp_block;
-	struct request_queue *q = block->gdp->queue;
-	struct dasd_device *device = block->base;
-	int max;
-
-	if (device->features & DASD_FEATURE_USERAW) {
+	if (block->base->features & DASD_FEATURE_USERAW) {
 		/*
 		 * the max_blocks value for raw_track access is 256
 		 * it is higher than the native ECKD value because we
@@ -6883,19 +6836,10 @@ static void dasd_eckd_setup_blk_queue(struct dasd_block *block)
 		 * so the max_hw_sectors are
 		 * 2048 x 512B = 1024kB = 16 tracks
 		 */
-		max = DASD_ECKD_MAX_BLOCKS_RAW << block->s2b_shift;
-	} else {
-		max = DASD_ECKD_MAX_BLOCKS << block->s2b_shift;
+		return DASD_ECKD_MAX_BLOCKS_RAW << block->s2b_shift;
 	}
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
-	q->limits.max_dev_sectors = max;
-	blk_queue_logical_block_size(q, logical_block_size);
-	blk_queue_max_hw_sectors(q, max);
-	blk_queue_max_segments(q, USHRT_MAX);
-	/* With page sized segments each segment can be translated into one idaw/tidaw */
-	blk_queue_max_segment_size(q, PAGE_SIZE);
-	blk_queue_segment_boundary(q, PAGE_SIZE - 1);
-	blk_queue_dma_alignment(q, PAGE_SIZE - 1);
+
+	return DASD_ECKD_MAX_BLOCKS << block->s2b_shift;
 }
 
 static struct ccw_driver dasd_eckd_driver = {
@@ -6927,7 +6871,7 @@ static struct dasd_discipline dasd_eckd_discipline = {
 	.basic_to_ready = dasd_eckd_basic_to_ready,
 	.online_to_ready = dasd_eckd_online_to_ready,
 	.basic_to_known = dasd_eckd_basic_to_known,
-	.setup_blk_queue = dasd_eckd_setup_blk_queue,
+	.max_sectors = dasd_eckd_max_sectors,
 	.fill_geometry = dasd_eckd_fill_geometry,
 	.start_IO = dasd_start_IO,
 	.term_IO = dasd_term_IO,
diff --git a/drivers/s390/block/dasd_eer.c b/drivers/s390/block/dasd_eer.c
index c956de711cf7..5064a616e041 100644
--- a/drivers/s390/block/dasd_eer.c
+++ b/drivers/s390/block/dasd_eer.c
@@ -7,8 +7,6 @@
  *  Author(s): Stefan Weinhuber <wein@de.ibm.com>
  */
 
-#define KMSG_COMPONENT "dasd-eckd"
-
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/kernel.h>
@@ -28,11 +26,6 @@
 #include "dasd_int.h"
 #include "dasd_eckd.h"
 
-#ifdef PRINTK_HEADER
-#undef PRINTK_HEADER
-#endif				/* PRINTK_HEADER */
-#define PRINTK_HEADER "dasd(eer):"
-
 /*
  * SECTION: the internal buffer
  */
diff --git a/drivers/s390/block/dasd_erp.c b/drivers/s390/block/dasd_erp.c
index c07e6e713518..4c0d3a704513 100644
--- a/drivers/s390/block/dasd_erp.c
+++ b/drivers/s390/block/dasd_erp.c
@@ -9,8 +9,6 @@
  *
  */
 
-#define KMSG_COMPONENT "dasd"
-
 #include <linux/ctype.h>
 #include <linux/init.h>
 
@@ -18,9 +16,6 @@
 #include <asm/ebcdic.h>
 #include <linux/uaccess.h>
 
-/* This is ugly... */
-#define PRINTK_HEADER "dasd_erp:"
-
 #include "dasd_int.h"
 
 struct dasd_ccw_req *
@@ -170,12 +165,12 @@ dasd_log_sense(struct dasd_ccw_req *cqr, struct irb *irb)
 	device = cqr->startdev;
 	if (cqr->intrc == -ETIMEDOUT) {
 		dev_err(&device->cdev->dev,
-			"A timeout error occurred for cqr %p\n", cqr);
+			"A timeout error occurred for cqr %px\n", cqr);
 		return;
 	}
 	if (cqr->intrc == -ENOLINK) {
 		dev_err(&device->cdev->dev,
-			"A transport error occurred for cqr %p\n", cqr);
+			"A transport error occurred for cqr %px\n", cqr);
 		return;
 	}
 	/* dump sense data */
diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c
index c06fa2b27120..bcbb2f8e91fe 100644
--- a/drivers/s390/block/dasd_fba.c
+++ b/drivers/s390/block/dasd_fba.c
@@ -25,11 +25,6 @@
 #include "dasd_int.h"
 #include "dasd_fba.h"
 
-#ifdef PRINTK_HEADER
-#undef PRINTK_HEADER
-#endif				/* PRINTK_HEADER */
-#define PRINTK_HEADER "dasd(fba):"
-
 #define FBA_DEFAULT_RETRIES 32
 
 #define DASD_FBA_CCW_WRITE 0x41
@@ -660,30 +655,27 @@ static void
 dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req,
 		    struct irb *irb)
 {
-	char *page;
 	struct ccw1 *act, *end, *last;
 	int len, sl, sct, count;
+	struct device *dev;
+	char *page;
+
+	dev = &device->cdev->dev;
 
 	page = (char *) get_zeroed_page(GFP_ATOMIC);
 	if (page == NULL) {
 		DBF_DEV_EVENT(DBF_WARNING, device, "%s",
-			    "No memory to dump sense data");
+			      "No memory to dump sense data");
 		return;
 	}
-	len = sprintf(page, PRINTK_HEADER
-		      " I/O status report for device %s:\n",
-		      dev_name(&device->cdev->dev));
-	len += sprintf(page + len, PRINTK_HEADER
-		       " in req: %p CS: 0x%02X DS: 0x%02X\n", req,
-		       irb->scsw.cmd.cstat, irb->scsw.cmd.dstat);
-	len += sprintf(page + len, PRINTK_HEADER
-		       " device %s: Failing CCW: %p\n",
-		       dev_name(&device->cdev->dev),
+	len = sprintf(page, "I/O status report:\n");
+	len += sprintf(page + len, "in req: %px CS: 0x%02X DS: 0x%02X\n",
+		       req, irb->scsw.cmd.cstat, irb->scsw.cmd.dstat);
+	len += sprintf(page + len, "Failing CCW: %px\n",
 		       (void *) (addr_t) irb->scsw.cmd.cpa);
 	if (irb->esw.esw0.erw.cons) {
 		for (sl = 0; sl < 4; sl++) {
-			len += sprintf(page + len, PRINTK_HEADER
-				       " Sense(hex) %2d-%2d:",
+			len += sprintf(page + len, "Sense(hex) %2d-%2d:",
 				       (8 * sl), ((8 * sl) + 7));
 
 			for (sct = 0; sct < 8; sct++) {
@@ -693,20 +685,18 @@ dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req,
 			len += sprintf(page + len, "\n");
 		}
 	} else {
-		len += sprintf(page + len, PRINTK_HEADER
-			       " SORRY - NO VALID SENSE AVAILABLE\n");
+		len += sprintf(page + len, "SORRY - NO VALID SENSE AVAILABLE\n");
 	}
-	printk(KERN_ERR "%s", page);
+	dev_err(dev, "%s", page);
 
 	/* dump the Channel Program */
 	/* print first CCWs (maximum 8) */
 	act = req->cpaddr;
-        for (last = act; last->flags & (CCW_FLAG_CC | CCW_FLAG_DC); last++);
+	for (last = act; last->flags & (CCW_FLAG_CC | CCW_FLAG_DC); last++);
 	end = min(act + 8, last);
-	len = sprintf(page, PRINTK_HEADER " Related CP in req: %p\n", req);
+	len = sprintf(page, "Related CP in req: %px\n", req);
 	while (act <= end) {
-		len += sprintf(page + len, PRINTK_HEADER
-			       " CCW %p: %08X %08X DAT:",
+		len += sprintf(page + len, "CCW %px: %08X %08X DAT:",
 			       act, ((int *) act)[0], ((int *) act)[1]);
 		for (count = 0; count < 32 && count < act->count;
 		     count += sizeof(int))
@@ -716,19 +706,17 @@ dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req,
 		len += sprintf(page + len, "\n");
 		act++;
 	}
-	printk(KERN_ERR "%s", page);
-
+	dev_err(dev, "%s", page);
 
 	/* print failing CCW area */
 	len = 0;
 	if (act <  ((struct ccw1 *)(addr_t) irb->scsw.cmd.cpa) - 2) {
 		act = ((struct ccw1 *)(addr_t) irb->scsw.cmd.cpa) - 2;
-		len += sprintf(page + len, PRINTK_HEADER "......\n");
+		len += sprintf(page + len, "......\n");
 	}
 	end = min((struct ccw1 *)(addr_t) irb->scsw.cmd.cpa + 2, last);
 	while (act <= end) {
-		len += sprintf(page + len, PRINTK_HEADER
-			       " CCW %p: %08X %08X DAT:",
+		len += sprintf(page + len, "CCW %px: %08X %08X DAT:",
 			       act, ((int *) act)[0], ((int *) act)[1]);
 		for (count = 0; count < 32 && count < act->count;
 		     count += sizeof(int))
@@ -742,11 +730,10 @@ dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req,
 	/* print last CCWs */
 	if (act <  last - 2) {
 		act = last - 2;
-		len += sprintf(page + len, PRINTK_HEADER "......\n");
+		len += sprintf(page + len, "......\n");
 	}
 	while (act <= last) {
-		len += sprintf(page + len, PRINTK_HEADER
-			       " CCW %p: %08X %08X DAT:",
+		len += sprintf(page + len, "CCW %px: %08X %08X DAT:",
 			       act, ((int *) act)[0], ((int *) act)[1]);
 		for (count = 0; count < 32 && count < act->count;
 		     count += sizeof(int))
@@ -757,39 +744,13 @@ dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req,
 		act++;
 	}
 	if (len > 0)
-		printk(KERN_ERR "%s", page);
+		dev_err(dev, "%s", page);
 	free_page((unsigned long) page);
 }
 
-/*
- * Initialize block layer request queue.
- */
-static void dasd_fba_setup_blk_queue(struct dasd_block *block)
+static unsigned int dasd_fba_max_sectors(struct dasd_block *block)
 {
-	unsigned int logical_block_size = block->bp_block;
-	struct request_queue *q = block->gdp->queue;
-	unsigned int max_bytes, max_discard_sectors;
-	int max;
-
-	max = DASD_FBA_MAX_BLOCKS << block->s2b_shift;
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
-	q->limits.max_dev_sectors = max;
-	blk_queue_logical_block_size(q, logical_block_size);
-	blk_queue_max_hw_sectors(q, max);
-	blk_queue_max_segments(q, USHRT_MAX);
-	/* With page sized segments each segment can be translated into one idaw/tidaw */
-	blk_queue_max_segment_size(q, PAGE_SIZE);
-	blk_queue_segment_boundary(q, PAGE_SIZE - 1);
-
-	q->limits.discard_granularity = logical_block_size;
-
-	/* Calculate max_discard_sectors and make it PAGE aligned */
-	max_bytes = USHRT_MAX * logical_block_size;
-	max_bytes = ALIGN_DOWN(max_bytes, PAGE_SIZE);
-	max_discard_sectors = max_bytes / logical_block_size;
-
-	blk_queue_max_discard_sectors(q, max_discard_sectors);
-	blk_queue_max_write_zeroes_sectors(q, max_discard_sectors);
+	return DASD_FBA_MAX_BLOCKS << block->s2b_shift;
 }
 
 static int dasd_fba_pe_handler(struct dasd_device *device,
@@ -802,10 +763,11 @@ static struct dasd_discipline dasd_fba_discipline = {
 	.owner = THIS_MODULE,
 	.name = "FBA ",
 	.ebcname = "FBA ",
+	.has_discard = true,
 	.check_device = dasd_fba_check_characteristics,
 	.do_analysis = dasd_fba_do_analysis,
 	.pe_handler = dasd_fba_pe_handler,
-	.setup_blk_queue = dasd_fba_setup_blk_queue,
+	.max_sectors = dasd_fba_max_sectors,
 	.fill_geometry = dasd_fba_fill_geometry,
 	.start_IO = dasd_start_IO,
 	.term_IO = dasd_term_IO,
diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c
index 55e3abe94cde..4533dd055ca8 100644
--- a/drivers/s390/block/dasd_genhd.c
+++ b/drivers/s390/block/dasd_genhd.c
@@ -11,8 +11,6 @@
  *
  */
 
-#define KMSG_COMPONENT "dasd"
-
 #include <linux/interrupt.h>
 #include <linux/major.h>
 #include <linux/fs.h>
@@ -20,9 +18,6 @@
 
 #include <linux/uaccess.h>
 
-/* This is ugly... */
-#define PRINTK_HEADER "dasd_gendisk:"
-
 #include "dasd_int.h"
 
 static unsigned int queue_depth = 32;
@@ -39,6 +34,16 @@ MODULE_PARM_DESC(nr_hw_queues, "Default number of hardware queues for new DASD d
  */
 int dasd_gendisk_alloc(struct dasd_block *block)
 {
+	struct queue_limits lim = {
+		/*
+		 * With page sized segments, each segment can be translated into
+		 * one idaw/tidaw.
+		 */
+		.max_segment_size = PAGE_SIZE,
+		.seg_boundary_mask = PAGE_SIZE - 1,
+		.dma_alignment = PAGE_SIZE - 1,
+		.max_segments = USHRT_MAX,
+	};
 	struct gendisk *gdp;
 	struct dasd_device *base;
 	int len, rc;
@@ -58,11 +63,12 @@ int dasd_gendisk_alloc(struct dasd_block *block)
 	if (rc)
 		return rc;
 
-	gdp = blk_mq_alloc_disk(&block->tag_set, block);
+	gdp = blk_mq_alloc_disk(&block->tag_set, &lim, block);
 	if (IS_ERR(gdp)) {
 		blk_mq_free_tag_set(&block->tag_set);
 		return PTR_ERR(gdp);
 	}
+	blk_queue_flag_set(QUEUE_FLAG_NONROT, gdp->queue);
 
 	/* Initialize gendisk structure. */
 	gdp->major = DASD_MAJOR;
@@ -127,15 +133,15 @@ void dasd_gendisk_free(struct dasd_block *block)
  */
 int dasd_scan_partitions(struct dasd_block *block)
 {
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	int rc;
 
-	bdev_handle = bdev_open_by_dev(disk_devt(block->gdp), BLK_OPEN_READ,
+	bdev_file = bdev_file_open_by_dev(disk_devt(block->gdp), BLK_OPEN_READ,
 				       NULL, NULL);
-	if (IS_ERR(bdev_handle)) {
+	if (IS_ERR(bdev_file)) {
 		DBF_DEV_EVENT(DBF_ERR, block->base,
 			      "scan partitions error, blkdev_get returned %ld",
-			      PTR_ERR(bdev_handle));
+			      PTR_ERR(bdev_file));
 		return -ENODEV;
 	}
 
@@ -147,15 +153,15 @@ int dasd_scan_partitions(struct dasd_block *block)
 				"scan partitions error, rc %d", rc);
 
 	/*
-	 * Since the matching bdev_release() call to the
-	 * bdev_open_by_path() in this function is not called before
+	 * Since the matching fput() call to the
+	 * bdev_file_open_by_path() in this function is not called before
 	 * dasd_destroy_partitions the offline open_count limit needs to be
-	 * increased from 0 to 1. This is done by setting device->bdev_handle
+	 * increased from 0 to 1. This is done by setting device->bdev_file
 	 * (see dasd_generic_set_offline). As long as the partition detection
 	 * is running no offline should be allowed. That is why the assignment
-	 * to block->bdev_handle is done AFTER the BLKRRPART ioctl.
+	 * to block->bdev_file is done AFTER the BLKRRPART ioctl.
 	 */
-	block->bdev_handle = bdev_handle;
+	block->bdev_file = bdev_file;
 	return 0;
 }
 
@@ -165,21 +171,21 @@ int dasd_scan_partitions(struct dasd_block *block)
  */
 void dasd_destroy_partitions(struct dasd_block *block)
 {
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 
 	/*
-	 * Get the bdev_handle pointer from the device structure and clear
-	 * device->bdev_handle to lower the offline open_count limit again.
+	 * Get the bdev_file pointer from the device structure and clear
+	 * device->bdev_file to lower the offline open_count limit again.
 	 */
-	bdev_handle = block->bdev_handle;
-	block->bdev_handle = NULL;
+	bdev_file = block->bdev_file;
+	block->bdev_file = NULL;
 
-	mutex_lock(&bdev_handle->bdev->bd_disk->open_mutex);
-	bdev_disk_changed(bdev_handle->bdev->bd_disk, true);
-	mutex_unlock(&bdev_handle->bdev->bd_disk->open_mutex);
+	mutex_lock(&file_bdev(bdev_file)->bd_disk->open_mutex);
+	bdev_disk_changed(file_bdev(bdev_file)->bd_disk, true);
+	mutex_unlock(&file_bdev(bdev_file)->bd_disk->open_mutex);
 
 	/* Matching blkdev_put to the blkdev_get in dasd_scan_partitions. */
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 }
 
 int dasd_gendisk_init(void)
diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h
index 1b1b8a41c4d4..e5f40536b425 100644
--- a/drivers/s390/block/dasd_int.h
+++ b/drivers/s390/block/dasd_int.h
@@ -113,9 +113,6 @@ do { \
 			    __dev_id.ssid, __dev_id.devno, d_data);	\
 } while (0)
 
-/* limit size for an errorstring */
-#define ERRORLENGTH 30
-
 /* definition of dbf debug levels */
 #define	DBF_EMERG	0	/* system is unusable			*/
 #define	DBF_ALERT	1	/* action must be taken immediately	*/
@@ -126,32 +123,6 @@ do { \
 #define	DBF_INFO	6	/* informational			*/
 #define	DBF_DEBUG	6	/* debug-level messages			*/
 
-/* messages to be written via klogd and dbf */
-#define DEV_MESSAGE(d_loglevel,d_device,d_string,d_args...)\
-do { \
-	printk(d_loglevel PRINTK_HEADER " %s: " d_string "\n", \
-	       dev_name(&d_device->cdev->dev), d_args); \
-	DBF_DEV_EVENT(DBF_ALERT, d_device, d_string, d_args); \
-} while(0)
-
-#define MESSAGE(d_loglevel,d_string,d_args...)\
-do { \
-	printk(d_loglevel PRINTK_HEADER " " d_string "\n", d_args); \
-	DBF_EVENT(DBF_ALERT, d_string, d_args); \
-} while(0)
-
-/* messages to be written via klogd only */
-#define DEV_MESSAGE_LOG(d_loglevel,d_device,d_string,d_args...)\
-do { \
-	printk(d_loglevel PRINTK_HEADER " %s: " d_string "\n", \
-	       dev_name(&d_device->cdev->dev), d_args); \
-} while(0)
-
-#define MESSAGE_LOG(d_loglevel,d_string,d_args...)\
-do { \
-	printk(d_loglevel PRINTK_HEADER " " d_string "\n", d_args); \
-} while(0)
-
 /* Macro to calculate number of blocks per page */
 #define BLOCKS_PER_PAGE(blksize) (PAGE_SIZE / blksize)
 
@@ -322,6 +293,7 @@ struct dasd_discipline {
 	struct module *owner;
 	char ebcname[8];	/* a name used for tagging and printks */
 	char name[8];		/* a name used for tagging and printks */
+	bool has_discard;
 
 	struct list_head list;	/* used for list of disciplines */
 
@@ -360,10 +332,7 @@ struct dasd_discipline {
 	int (*online_to_ready) (struct dasd_device *);
 	int (*basic_to_known)(struct dasd_device *);
 
-	/*
-	 * Initialize block layer request queue.
-	 */
-	void (*setup_blk_queue)(struct dasd_block *);
+	unsigned int (*max_sectors)(struct dasd_block *);
 	/* (struct dasd_device *);
 	 * Device operation functions. build_cp creates a ccw chain for
 	 * a block device request, start_io starts the request and
@@ -650,7 +619,7 @@ struct dasd_block {
 	struct gendisk *gdp;
 	spinlock_t request_queue_lock;
 	struct blk_mq_tag_set tag_set;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	atomic_t open_count;
 
 	unsigned long blocks;	   /* size of volume in blocks */
diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c
index 61b9675e2a67..7e0ed7032f76 100644
--- a/drivers/s390/block/dasd_ioctl.c
+++ b/drivers/s390/block/dasd_ioctl.c
@@ -10,8 +10,6 @@
  * i/o controls for the dasd driver.
  */
 
-#define KMSG_COMPONENT "dasd"
-
 #include <linux/interrupt.h>
 #include <linux/compat.h>
 #include <linux/major.h>
@@ -24,12 +22,8 @@
 #include <linux/uaccess.h>
 #include <linux/dasd_mod.h>
 
-/* This is ugly... */
-#define PRINTK_HEADER "dasd_ioctl:"
-
 #include "dasd_int.h"
 
-
 static int
 dasd_ioctl_api_version(void __user *argp)
 {
@@ -537,7 +531,7 @@ static int __dasd_ioctl_information(struct dasd_block *block,
 	 * This must be hidden from user-space.
 	 */
 	dasd_info->open_count = atomic_read(&block->open_count);
-	if (!block->bdev_handle)
+	if (!block->bdev_file)
 		dasd_info->open_count++;
 
 	/*
diff --git a/drivers/s390/block/dasd_proc.c b/drivers/s390/block/dasd_proc.c
index 62a859ea67f8..0faaa437d9be 100644
--- a/drivers/s390/block/dasd_proc.c
+++ b/drivers/s390/block/dasd_proc.c
@@ -11,8 +11,6 @@
  *
  */
 
-#define KMSG_COMPONENT "dasd"
-
 #include <linux/ctype.h>
 #include <linux/slab.h>
 #include <linux/string.h>
@@ -23,9 +21,6 @@
 #include <asm/debug.h>
 #include <linux/uaccess.h>
 
-/* This is ugly... */
-#define PRINTK_HEADER "dasd_proc:"
-
 #include "dasd_int.h"
 
 static struct proc_dir_entry *dasd_proc_root_entry = NULL;
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 4b7ecd4fd431..9c8f529b827c 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -546,6 +546,9 @@ static const struct attribute_group *dcssblk_dev_attr_groups[] = {
 static ssize_t
 dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count)
 {
+	struct queue_limits lim = {
+		.logical_block_size	= 4096,
+	};
 	int rc, i, j, num_of_segments;
 	struct dcssblk_dev_info *dev_info;
 	struct segment_info *seg_info, *temp;
@@ -629,9 +632,9 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
 	dev_info->dev.release = dcssblk_release_segment;
 	dev_info->dev.groups = dcssblk_dev_attr_groups;
 	INIT_LIST_HEAD(&dev_info->lh);
-	dev_info->gd = blk_alloc_disk(NUMA_NO_NODE);
-	if (dev_info->gd == NULL) {
-		rc = -ENOMEM;
+	dev_info->gd = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(dev_info->gd)) {
+		rc = PTR_ERR(dev_info->gd);
 		goto seg_list_del;
 	}
 	dev_info->gd->major = dcssblk_major;
@@ -639,7 +642,6 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
 	dev_info->gd->fops = &dcssblk_devops;
 	dev_info->gd->private_data = dev_info;
 	dev_info->gd->flags |= GENHD_FL_NO_PART;
-	blk_queue_logical_block_size(dev_info->gd->queue, 4096);
 	blk_queue_flag_set(QUEUE_FLAG_DAX, dev_info->gd->queue);
 
 	seg_byte_size = (dev_info->end - dev_info->start + 1);
diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c
index ade95e91b3c8..9f6fdd0daa74 100644
--- a/drivers/s390/block/scm_blk.c
+++ b/drivers/s390/block/scm_blk.c
@@ -435,10 +435,17 @@ static const struct blk_mq_ops scm_mq_ops = {
 
 int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev)
 {
-	unsigned int devindex, nr_max_blk;
+	struct queue_limits lim = {
+		.logical_block_size	= 1 << 12,
+	};
+	unsigned int devindex;
 	struct request_queue *rq;
 	int len, ret;
 
+	lim.max_segments = min(scmdev->nr_max_block,
+		(unsigned int) (PAGE_SIZE / sizeof(struct aidaw)));
+	lim.max_hw_sectors = lim.max_segments << 3; /* 8 * 512 = blk_size */
+
 	devindex = atomic_inc_return(&nr_devices) - 1;
 	/* scma..scmz + scmaa..scmzz */
 	if (devindex > 701) {
@@ -462,18 +469,12 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev)
 	if (ret)
 		goto out;
 
-	bdev->gendisk = blk_mq_alloc_disk(&bdev->tag_set, scmdev);
+	bdev->gendisk = blk_mq_alloc_disk(&bdev->tag_set, &lim, scmdev);
 	if (IS_ERR(bdev->gendisk)) {
 		ret = PTR_ERR(bdev->gendisk);
 		goto out_tag;
 	}
 	rq = bdev->rq = bdev->gendisk->queue;
-	nr_max_blk = min(scmdev->nr_max_block,
-			 (unsigned int) (PAGE_SIZE / sizeof(struct aidaw)));
-
-	blk_queue_logical_block_size(rq, 1 << 12);
-	blk_queue_max_hw_sectors(rq, nr_max_blk << 3); /* 8 * 512 = blk_size */
-	blk_queue_max_segments(rq, nr_max_blk);
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, rq);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, rq);
 
diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c
index 99361618c31f..0b0324fe4aff 100644
--- a/drivers/s390/char/con3215.c
+++ b/drivers/s390/char/con3215.c
@@ -79,8 +79,8 @@ struct raw3215_info {
 	struct ccw_device *cdev;      /* device for tty driver */
 	spinlock_t *lock;	      /* pointer to irq lock */
 	int flags;		      /* state flags */
-	char *buffer;		      /* pointer to output buffer */
-	char *inbuf;		      /* pointer to input buffer */
+	u8 *buffer;		      /* pointer to output buffer */
+	u8 *inbuf;		      /* pointer to input buffer */
 	int head;		      /* first free byte in output buffer */
 	int count;		      /* number of bytes in output buffer */
 	int written;		      /* number of bytes in write requests */
@@ -89,7 +89,6 @@ struct raw3215_info {
 	wait_queue_head_t empty_wait; /* wait queue for flushing */
 	struct timer_list timer;      /* timer for delayed output */
 	int line_pos;		      /* position on the line (for tabs) */
-	char ubuffer[80];	      /* copy_from_user buffer */
 };
 
 /* array of 3215 devices structures */
@@ -523,12 +522,14 @@ static unsigned int raw3215_make_room(struct raw3215_info *raw,
  *	string	without blocking.
  *	Return value is the number of bytes copied.
  */
-static unsigned int raw3215_addtext(const char *str, unsigned int length,
+static unsigned int raw3215_addtext(const u8 *str, size_t length,
 				    struct raw3215_info *raw, int opmode,
 				    unsigned int todrop)
 {
-	unsigned int c, ch, i, blanks, expanded_size = 0;
+	unsigned int i, blanks, expanded_size = 0;
 	unsigned int column = raw->line_pos;
+	size_t c;
+	u8 ch;
 
 	if (opmode == RAW3215_COUNT)
 		todrop = 0;
@@ -559,7 +560,7 @@ static unsigned int raw3215_addtext(const char *str, unsigned int length,
 		if (todrop && expanded_size < todrop)	/* Drop head data */
 			continue;
 		for (i = 0; i < blanks; i++) {
-			raw->buffer[raw->head] = (char)_ascebc[(int)ch];
+			raw->buffer[raw->head] = _ascebc[ch];
 			raw->head = (raw->head + 1) & (RAW3215_BUFFER_SIZE - 1);
 			raw->count++;
 		}
@@ -571,8 +572,8 @@ static unsigned int raw3215_addtext(const char *str, unsigned int length,
 /*
  * String write routine for 3215 devices
  */
-static void raw3215_write(struct raw3215_info *raw, const char *str,
-			  unsigned int length)
+static void raw3215_write(struct raw3215_info *raw, const u8 *str,
+			  size_t length)
 {
 	unsigned int count, avail;
 	unsigned long flags;
@@ -597,7 +598,7 @@ static void raw3215_write(struct raw3215_info *raw, const char *str,
 /*
  * Put character routine for 3215 devices
  */
-static void raw3215_putchar(struct raw3215_info *raw, unsigned char ch)
+static void raw3215_putchar(struct raw3215_info *raw, u8 ch)
 {
 	raw3215_write(raw, &ch, 1);
 }
@@ -824,12 +825,10 @@ static struct ccw_driver raw3215_ccw_driver = {
 	.int_class	= IRQIO_C15,
 };
 
-static void handle_write(struct raw3215_info *raw, const char *str, int count)
+static void handle_write(struct raw3215_info *raw, const u8 *str, size_t count)
 {
-	int i;
-
 	while (count > 0) {
-		i = min_t(int, count, RAW3215_BUFFER_SIZE - 1);
+		size_t i = min_t(size_t, count, RAW3215_BUFFER_SIZE - 1);
 		raw3215_write(raw, str, i);
 		count -= i;
 		str += i;
diff --git a/drivers/s390/char/con3270.c b/drivers/s390/char/con3270.c
index 363315fa1666..251d2a1c3eef 100644
--- a/drivers/s390/char/con3270.c
+++ b/drivers/s390/char/con3270.c
@@ -54,7 +54,7 @@ struct tty3270_attribute {
 };
 
 struct tty3270_cell {
-	unsigned char character;
+	u8 character;
 	struct tty3270_attribute attributes;
 };
 
@@ -123,7 +123,7 @@ struct tty3270 {
 
 	/* Character array for put_char/flush_chars. */
 	unsigned int char_count;
-	char char_buf[TTY3270_CHAR_BUF_SIZE];
+	u8 char_buf[TTY3270_CHAR_BUF_SIZE];
 };
 
 /* tty3270->update_flags. See tty3270_update for details. */
@@ -1255,7 +1255,7 @@ static unsigned int tty3270_write_room(struct tty_struct *tty)
  * Insert character into the screen at the current position with the
  * current color and highlight. This function does NOT do cursor movement.
  */
-static void tty3270_put_character(struct tty3270 *tp, char ch)
+static void tty3270_put_character(struct tty3270 *tp, u8 ch)
 {
 	struct tty3270_line *line;
 	struct tty3270_cell *cell;
@@ -1561,7 +1561,7 @@ static void tty3270_goto_xy(struct tty3270 *tp, int cx, int cy)
  *  Pn is a numeric parameter, a string of zero or more decimal digits.
  *  Ps is a selective parameter.
  */
-static void tty3270_escape_sequence(struct tty3270 *tp, char ch)
+static void tty3270_escape_sequence(struct tty3270 *tp, u8 ch)
 {
 	enum { ES_NORMAL, ES_ESC, ES_SQUARE, ES_PAREN, ES_GETPARS };
 
@@ -1726,7 +1726,7 @@ static void tty3270_escape_sequence(struct tty3270 *tp, char ch)
  * String write routine for 3270 ttys
  */
 static void tty3270_do_write(struct tty3270 *tp, struct tty_struct *tty,
-			     const unsigned char *buf, int count)
+			     const u8 *buf, size_t count)
 {
 	int i_msg, i;
 
@@ -2052,7 +2052,7 @@ con3270_write(struct console *co, const char *str, unsigned int count)
 {
 	struct tty3270 *tp = co->data;
 	unsigned long flags;
-	char c;
+	u8 c;
 
 	spin_lock_irqsave(&tp->view.lock, flags);
 	while (count--) {
diff --git a/drivers/s390/char/uvdevice.c b/drivers/s390/char/uvdevice.c
index 144cd2e03590..42c9f77f8da0 100644
--- a/drivers/s390/char/uvdevice.c
+++ b/drivers/s390/char/uvdevice.c
@@ -109,6 +109,7 @@ static int uvio_copy_attest_result_to_user(struct uv_cb_attest *uvcb_attest,
 					   struct uvio_attest *uvio_attest)
 {
 	struct uvio_attest __user *user_uvio_attest = (void __user *)uv_ioctl->argument_addr;
+	u32 __user *user_buf_add_len = (u32 __user *)&user_uvio_attest->add_data_len;
 	void __user *user_buf_add = (void __user *)uvio_attest->add_data_addr;
 	void __user *user_buf_meas = (void __user *)uvio_attest->meas_addr;
 	void __user *user_buf_uid = &user_uvio_attest->config_uid;
@@ -117,6 +118,8 @@ static int uvio_copy_attest_result_to_user(struct uv_cb_attest *uvcb_attest,
 		return -EFAULT;
 	if (add_data && copy_to_user(user_buf_add, add_data, uvio_attest->add_data_len))
 		return -EFAULT;
+	if (put_user(uvio_attest->add_data_len, user_buf_add_len))
+		return -EFAULT;
 	if (copy_to_user(user_buf_uid, uvcb_attest->config_uid, sizeof(uvcb_attest->config_uid)))
 		return -EFAULT;
 	return 0;
diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c
index c533d1dadc6b..a5dba3829769 100644
--- a/drivers/s390/cio/device_ops.c
+++ b/drivers/s390/cio/device_ops.c
@@ -202,7 +202,8 @@ int ccw_device_start_timeout_key(struct ccw_device *cdev, struct ccw1 *cpa,
 		return -EINVAL;
 	if (cdev->private->state == DEV_STATE_NOT_OPER)
 		return -ENODEV;
-	if (cdev->private->state == DEV_STATE_VERIFY) {
+	if (cdev->private->state == DEV_STATE_VERIFY ||
+	    cdev->private->flags.doverify) {
 		/* Remember to fake irb when finished. */
 		if (!cdev->private->flags.fake_irb) {
 			cdev->private->flags.fake_irb = FAKE_CMD_IRB;
@@ -214,8 +215,7 @@ int ccw_device_start_timeout_key(struct ccw_device *cdev, struct ccw1 *cpa,
 	}
 	if (cdev->private->state != DEV_STATE_ONLINE ||
 	    ((sch->schib.scsw.cmd.stctl & SCSW_STCTL_PRIM_STATUS) &&
-	     !(sch->schib.scsw.cmd.stctl & SCSW_STCTL_SEC_STATUS)) ||
-	    cdev->private->flags.doverify)
+	     !(sch->schib.scsw.cmd.stctl & SCSW_STCTL_SEC_STATUS)))
 		return -EBUSY;
 	ret = cio_set_options (sch, flags);
 	if (ret)
diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index acb710d3d7bc..983b3b16196c 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -32,7 +32,8 @@
 
 #define AP_RESET_INTERVAL		20	/* Reset sleep interval (20ms)		*/
 
-static int vfio_ap_mdev_reset_queues(struct ap_queue_table *qtable);
+static int vfio_ap_mdev_reset_queues(struct ap_matrix_mdev *matrix_mdev);
+static int vfio_ap_mdev_reset_qlist(struct list_head *qlist);
 static struct vfio_ap_queue *vfio_ap_find_queue(int apqn);
 static const struct vfio_device_ops vfio_ap_matrix_dev_ops;
 static void vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q);
@@ -665,17 +666,23 @@ static bool vfio_ap_mdev_filter_cdoms(struct ap_matrix_mdev *matrix_mdev)
  *				device driver.
  *
  * @matrix_mdev: the matrix mdev whose matrix is to be filtered.
+ * @apm_filtered: a 256-bit bitmap for storing the APIDs filtered from the
+ *		  guest's AP configuration that are still in the host's AP
+ *		  configuration.
  *
  * Note: If an APQN referencing a queue device that is not bound to the vfio_ap
  *	 driver, its APID will be filtered from the guest's APCB. The matrix
  *	 structure precludes filtering an individual APQN, so its APID will be
- *	 filtered.
+ *	 filtered. Consequently, all queues associated with the adapter that
+ *	 are in the host's AP configuration must be reset. If queues are
+ *	 subsequently made available again to the guest, they should re-appear
+ *	 in a reset state
  *
  * Return: a boolean value indicating whether the KVM guest's APCB was changed
  *	   by the filtering or not.
  */
-static bool vfio_ap_mdev_filter_matrix(unsigned long *apm, unsigned long *aqm,
-				       struct ap_matrix_mdev *matrix_mdev)
+static bool vfio_ap_mdev_filter_matrix(struct ap_matrix_mdev *matrix_mdev,
+				       unsigned long *apm_filtered)
 {
 	unsigned long apid, apqi, apqn;
 	DECLARE_BITMAP(prev_shadow_apm, AP_DEVICES);
@@ -685,6 +692,7 @@ static bool vfio_ap_mdev_filter_matrix(unsigned long *apm, unsigned long *aqm,
 	bitmap_copy(prev_shadow_apm, matrix_mdev->shadow_apcb.apm, AP_DEVICES);
 	bitmap_copy(prev_shadow_aqm, matrix_mdev->shadow_apcb.aqm, AP_DOMAINS);
 	vfio_ap_matrix_init(&matrix_dev->info, &matrix_mdev->shadow_apcb);
+	bitmap_clear(apm_filtered, 0, AP_DEVICES);
 
 	/*
 	 * Copy the adapters, domains and control domains to the shadow_apcb
@@ -696,8 +704,9 @@ static bool vfio_ap_mdev_filter_matrix(unsigned long *apm, unsigned long *aqm,
 	bitmap_and(matrix_mdev->shadow_apcb.aqm, matrix_mdev->matrix.aqm,
 		   (unsigned long *)matrix_dev->info.aqm, AP_DOMAINS);
 
-	for_each_set_bit_inv(apid, apm, AP_DEVICES) {
-		for_each_set_bit_inv(apqi, aqm, AP_DOMAINS) {
+	for_each_set_bit_inv(apid, matrix_mdev->shadow_apcb.apm, AP_DEVICES) {
+		for_each_set_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm,
+				     AP_DOMAINS) {
 			/*
 			 * If the APQN is not bound to the vfio_ap device
 			 * driver, then we can't assign it to the guest's
@@ -709,8 +718,16 @@ static bool vfio_ap_mdev_filter_matrix(unsigned long *apm, unsigned long *aqm,
 			apqn = AP_MKQID(apid, apqi);
 			q = vfio_ap_mdev_get_queue(matrix_mdev, apqn);
 			if (!q || q->reset_status.response_code) {
-				clear_bit_inv(apid,
-					      matrix_mdev->shadow_apcb.apm);
+				clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm);
+
+				/*
+				 * If the adapter was previously plugged into
+				 * the guest, let's let the caller know that
+				 * the APID was filtered.
+				 */
+				if (test_bit_inv(apid, prev_shadow_apm))
+					set_bit_inv(apid, apm_filtered);
+
 				break;
 			}
 		}
@@ -812,7 +829,7 @@ static void vfio_ap_mdev_remove(struct mdev_device *mdev)
 
 	mutex_lock(&matrix_dev->guests_lock);
 	mutex_lock(&matrix_dev->mdevs_lock);
-	vfio_ap_mdev_reset_queues(&matrix_mdev->qtable);
+	vfio_ap_mdev_reset_queues(matrix_mdev);
 	vfio_ap_mdev_unlink_fr_queues(matrix_mdev);
 	list_del(&matrix_mdev->node);
 	mutex_unlock(&matrix_dev->mdevs_lock);
@@ -922,6 +939,47 @@ static void vfio_ap_mdev_link_adapter(struct ap_matrix_mdev *matrix_mdev,
 				       AP_MKQID(apid, apqi));
 }
 
+static void collect_queues_to_reset(struct ap_matrix_mdev *matrix_mdev,
+				    unsigned long apid,
+				    struct list_head *qlist)
+{
+	struct vfio_ap_queue *q;
+	unsigned long  apqi;
+
+	for_each_set_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm, AP_DOMAINS) {
+		q = vfio_ap_mdev_get_queue(matrix_mdev, AP_MKQID(apid, apqi));
+		if (q)
+			list_add_tail(&q->reset_qnode, qlist);
+	}
+}
+
+static void reset_queues_for_apid(struct ap_matrix_mdev *matrix_mdev,
+				  unsigned long apid)
+{
+	struct list_head qlist;
+
+	INIT_LIST_HEAD(&qlist);
+	collect_queues_to_reset(matrix_mdev, apid, &qlist);
+	vfio_ap_mdev_reset_qlist(&qlist);
+}
+
+static int reset_queues_for_apids(struct ap_matrix_mdev *matrix_mdev,
+				  unsigned long *apm_reset)
+{
+	struct list_head qlist;
+	unsigned long apid;
+
+	if (bitmap_empty(apm_reset, AP_DEVICES))
+		return 0;
+
+	INIT_LIST_HEAD(&qlist);
+
+	for_each_set_bit_inv(apid, apm_reset, AP_DEVICES)
+		collect_queues_to_reset(matrix_mdev, apid, &qlist);
+
+	return vfio_ap_mdev_reset_qlist(&qlist);
+}
+
 /**
  * assign_adapter_store - parses the APID from @buf and sets the
  * corresponding bit in the mediated matrix device's APM
@@ -962,7 +1020,7 @@ static ssize_t assign_adapter_store(struct device *dev,
 {
 	int ret;
 	unsigned long apid;
-	DECLARE_BITMAP(apm_delta, AP_DEVICES);
+	DECLARE_BITMAP(apm_filtered, AP_DEVICES);
 	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev);
 
 	mutex_lock(&ap_perms_mutex);
@@ -991,12 +1049,11 @@ static ssize_t assign_adapter_store(struct device *dev,
 	}
 
 	vfio_ap_mdev_link_adapter(matrix_mdev, apid);
-	memset(apm_delta, 0, sizeof(apm_delta));
-	set_bit_inv(apid, apm_delta);
 
-	if (vfio_ap_mdev_filter_matrix(apm_delta,
-				       matrix_mdev->matrix.aqm, matrix_mdev))
+	if (vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered)) {
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
+		reset_queues_for_apids(matrix_mdev, apm_filtered);
+	}
 
 	ret = count;
 done:
@@ -1027,11 +1084,12 @@ static struct vfio_ap_queue
  *				 adapter was assigned.
  * @matrix_mdev: the matrix mediated device to which the adapter was assigned.
  * @apid: the APID of the unassigned adapter.
- * @qtable: table for storing queues associated with unassigned adapter.
+ * @qlist: list for storing queues associated with unassigned adapter that
+ *	   need to be reset.
  */
 static void vfio_ap_mdev_unlink_adapter(struct ap_matrix_mdev *matrix_mdev,
 					unsigned long apid,
-					struct ap_queue_table *qtable)
+					struct list_head *qlist)
 {
 	unsigned long apqi;
 	struct vfio_ap_queue *q;
@@ -1039,11 +1097,10 @@ static void vfio_ap_mdev_unlink_adapter(struct ap_matrix_mdev *matrix_mdev,
 	for_each_set_bit_inv(apqi, matrix_mdev->matrix.aqm, AP_DOMAINS) {
 		q = vfio_ap_unlink_apqn_fr_mdev(matrix_mdev, apid, apqi);
 
-		if (q && qtable) {
+		if (q && qlist) {
 			if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm) &&
 			    test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm))
-				hash_add(qtable->queues, &q->mdev_qnode,
-					 q->apqn);
+				list_add_tail(&q->reset_qnode, qlist);
 		}
 	}
 }
@@ -1051,26 +1108,23 @@ static void vfio_ap_mdev_unlink_adapter(struct ap_matrix_mdev *matrix_mdev,
 static void vfio_ap_mdev_hot_unplug_adapter(struct ap_matrix_mdev *matrix_mdev,
 					    unsigned long apid)
 {
-	int loop_cursor;
-	struct vfio_ap_queue *q;
-	struct ap_queue_table *qtable = kzalloc(sizeof(*qtable), GFP_KERNEL);
+	struct vfio_ap_queue *q, *tmpq;
+	struct list_head qlist;
 
-	hash_init(qtable->queues);
-	vfio_ap_mdev_unlink_adapter(matrix_mdev, apid, qtable);
+	INIT_LIST_HEAD(&qlist);
+	vfio_ap_mdev_unlink_adapter(matrix_mdev, apid, &qlist);
 
 	if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm)) {
 		clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm);
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
 	}
 
-	vfio_ap_mdev_reset_queues(qtable);
+	vfio_ap_mdev_reset_qlist(&qlist);
 
-	hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode) {
+	list_for_each_entry_safe(q, tmpq, &qlist, reset_qnode) {
 		vfio_ap_unlink_mdev_fr_queue(q);
-		hash_del(&q->mdev_qnode);
+		list_del(&q->reset_qnode);
 	}
-
-	kfree(qtable);
 }
 
 /**
@@ -1171,7 +1225,7 @@ static ssize_t assign_domain_store(struct device *dev,
 {
 	int ret;
 	unsigned long apqi;
-	DECLARE_BITMAP(aqm_delta, AP_DOMAINS);
+	DECLARE_BITMAP(apm_filtered, AP_DEVICES);
 	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev);
 
 	mutex_lock(&ap_perms_mutex);
@@ -1200,12 +1254,11 @@ static ssize_t assign_domain_store(struct device *dev,
 	}
 
 	vfio_ap_mdev_link_domain(matrix_mdev, apqi);
-	memset(aqm_delta, 0, sizeof(aqm_delta));
-	set_bit_inv(apqi, aqm_delta);
 
-	if (vfio_ap_mdev_filter_matrix(matrix_mdev->matrix.apm, aqm_delta,
-				       matrix_mdev))
+	if (vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered)) {
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
+		reset_queues_for_apids(matrix_mdev, apm_filtered);
+	}
 
 	ret = count;
 done:
@@ -1218,7 +1271,7 @@ static DEVICE_ATTR_WO(assign_domain);
 
 static void vfio_ap_mdev_unlink_domain(struct ap_matrix_mdev *matrix_mdev,
 				       unsigned long apqi,
-				       struct ap_queue_table *qtable)
+				       struct list_head *qlist)
 {
 	unsigned long apid;
 	struct vfio_ap_queue *q;
@@ -1226,11 +1279,10 @@ static void vfio_ap_mdev_unlink_domain(struct ap_matrix_mdev *matrix_mdev,
 	for_each_set_bit_inv(apid, matrix_mdev->matrix.apm, AP_DEVICES) {
 		q = vfio_ap_unlink_apqn_fr_mdev(matrix_mdev, apid, apqi);
 
-		if (q && qtable) {
+		if (q && qlist) {
 			if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm) &&
 			    test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm))
-				hash_add(qtable->queues, &q->mdev_qnode,
-					 q->apqn);
+				list_add_tail(&q->reset_qnode, qlist);
 		}
 	}
 }
@@ -1238,26 +1290,23 @@ static void vfio_ap_mdev_unlink_domain(struct ap_matrix_mdev *matrix_mdev,
 static void vfio_ap_mdev_hot_unplug_domain(struct ap_matrix_mdev *matrix_mdev,
 					   unsigned long apqi)
 {
-	int loop_cursor;
-	struct vfio_ap_queue *q;
-	struct ap_queue_table *qtable = kzalloc(sizeof(*qtable), GFP_KERNEL);
+	struct vfio_ap_queue *q, *tmpq;
+	struct list_head qlist;
 
-	hash_init(qtable->queues);
-	vfio_ap_mdev_unlink_domain(matrix_mdev, apqi, qtable);
+	INIT_LIST_HEAD(&qlist);
+	vfio_ap_mdev_unlink_domain(matrix_mdev, apqi, &qlist);
 
 	if (test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm)) {
 		clear_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm);
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
 	}
 
-	vfio_ap_mdev_reset_queues(qtable);
+	vfio_ap_mdev_reset_qlist(&qlist);
 
-	hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode) {
+	list_for_each_entry_safe(q, tmpq, &qlist, reset_qnode) {
 		vfio_ap_unlink_mdev_fr_queue(q);
-		hash_del(&q->mdev_qnode);
+		list_del(&q->reset_qnode);
 	}
-
-	kfree(qtable);
 }
 
 /**
@@ -1612,7 +1661,7 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev)
 		get_update_locks_for_kvm(kvm);
 
 		kvm_arch_crypto_clear_masks(kvm);
-		vfio_ap_mdev_reset_queues(&matrix_mdev->qtable);
+		vfio_ap_mdev_reset_queues(matrix_mdev);
 		kvm_put_kvm(kvm);
 		matrix_mdev->kvm = NULL;
 
@@ -1748,15 +1797,33 @@ static void vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q)
 	}
 }
 
-static int vfio_ap_mdev_reset_queues(struct ap_queue_table *qtable)
+static int vfio_ap_mdev_reset_queues(struct ap_matrix_mdev *matrix_mdev)
 {
 	int ret = 0, loop_cursor;
 	struct vfio_ap_queue *q;
 
-	hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode)
+	hash_for_each(matrix_mdev->qtable.queues, loop_cursor, q, mdev_qnode)
 		vfio_ap_mdev_reset_queue(q);
 
-	hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode) {
+	hash_for_each(matrix_mdev->qtable.queues, loop_cursor, q, mdev_qnode) {
+		flush_work(&q->reset_work);
+
+		if (q->reset_status.response_code)
+			ret = -EIO;
+	}
+
+	return ret;
+}
+
+static int vfio_ap_mdev_reset_qlist(struct list_head *qlist)
+{
+	int ret = 0;
+	struct vfio_ap_queue *q;
+
+	list_for_each_entry(q, qlist, reset_qnode)
+		vfio_ap_mdev_reset_queue(q);
+
+	list_for_each_entry(q, qlist, reset_qnode) {
 		flush_work(&q->reset_work);
 
 		if (q->reset_status.response_code)
@@ -1942,7 +2009,7 @@ static ssize_t vfio_ap_mdev_ioctl(struct vfio_device *vdev,
 		ret = vfio_ap_mdev_get_device_info(arg);
 		break;
 	case VFIO_DEVICE_RESET:
-		ret = vfio_ap_mdev_reset_queues(&matrix_mdev->qtable);
+		ret = vfio_ap_mdev_reset_queues(matrix_mdev);
 		break;
 	case VFIO_DEVICE_GET_IRQ_INFO:
 			ret = vfio_ap_get_irq_info(arg);
@@ -2088,6 +2155,7 @@ int vfio_ap_mdev_probe_queue(struct ap_device *apdev)
 {
 	int ret;
 	struct vfio_ap_queue *q;
+	DECLARE_BITMAP(apm_filtered, AP_DEVICES);
 	struct ap_matrix_mdev *matrix_mdev;
 
 	ret = sysfs_create_group(&apdev->device.kobj, &vfio_queue_attr_group);
@@ -2109,15 +2177,28 @@ int vfio_ap_mdev_probe_queue(struct ap_device *apdev)
 	if (matrix_mdev) {
 		vfio_ap_mdev_link_queue(matrix_mdev, q);
 
-		if (vfio_ap_mdev_filter_matrix(matrix_mdev->matrix.apm,
-					       matrix_mdev->matrix.aqm,
-					       matrix_mdev))
+		/*
+		 * If we're in the process of handling the adding of adapters or
+		 * domains to the host's AP configuration, then let the
+		 * vfio_ap device driver's on_scan_complete callback filter the
+		 * matrix and update the guest's AP configuration after all of
+		 * the new queue devices are probed.
+		 */
+		if (!bitmap_empty(matrix_mdev->apm_add, AP_DEVICES) ||
+		    !bitmap_empty(matrix_mdev->aqm_add, AP_DOMAINS))
+			goto done;
+
+		if (vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered)) {
 			vfio_ap_mdev_update_guest_apcb(matrix_mdev);
+			reset_queues_for_apids(matrix_mdev, apm_filtered);
+		}
 	}
+
+done:
 	dev_set_drvdata(&apdev->device, q);
 	release_update_locks_for_mdev(matrix_mdev);
 
-	return 0;
+	return ret;
 
 err_remove_group:
 	sysfs_remove_group(&apdev->device.kobj, &vfio_queue_attr_group);
@@ -2134,26 +2215,40 @@ void vfio_ap_mdev_remove_queue(struct ap_device *apdev)
 	q = dev_get_drvdata(&apdev->device);
 	get_update_locks_for_queue(q);
 	matrix_mdev = q->matrix_mdev;
+	apid = AP_QID_CARD(q->apqn);
+	apqi = AP_QID_QUEUE(q->apqn);
 
 	if (matrix_mdev) {
-		vfio_ap_unlink_queue_fr_mdev(q);
-
-		apid = AP_QID_CARD(q->apqn);
-		apqi = AP_QID_QUEUE(q->apqn);
-
-		/*
-		 * If the queue is assigned to the guest's APCB, then remove
-		 * the adapter's APID from the APCB and hot it into the guest.
-		 */
+		/* If the queue is assigned to the guest's AP configuration */
 		if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm) &&
 		    test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm)) {
+			/*
+			 * Since the queues are defined via a matrix of adapters
+			 * and domains, it is not possible to hot unplug a
+			 * single queue; so, let's unplug the adapter.
+			 */
 			clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm);
 			vfio_ap_mdev_update_guest_apcb(matrix_mdev);
+			reset_queues_for_apid(matrix_mdev, apid);
+			goto done;
 		}
 	}
 
-	vfio_ap_mdev_reset_queue(q);
-	flush_work(&q->reset_work);
+	/*
+	 * If the queue is not in the host's AP configuration, then resetting
+	 * it will fail with response code 01, (APQN not valid); so, let's make
+	 * sure it is in the host's config.
+	 */
+	if (test_bit_inv(apid, (unsigned long *)matrix_dev->info.apm) &&
+	    test_bit_inv(apqi, (unsigned long *)matrix_dev->info.aqm)) {
+		vfio_ap_mdev_reset_queue(q);
+		flush_work(&q->reset_work);
+	}
+
+done:
+	if (matrix_mdev)
+		vfio_ap_unlink_queue_fr_mdev(q);
+
 	dev_set_drvdata(&apdev->device, NULL);
 	kfree(q);
 	release_update_locks_for_mdev(matrix_mdev);
@@ -2461,39 +2556,30 @@ void vfio_ap_on_cfg_changed(struct ap_config_info *cur_cfg_info,
 
 static void vfio_ap_mdev_hot_plug_cfg(struct ap_matrix_mdev *matrix_mdev)
 {
-	bool do_hotplug = false;
-	int filter_domains = 0;
-	int filter_adapters = 0;
-	DECLARE_BITMAP(apm, AP_DEVICES);
-	DECLARE_BITMAP(aqm, AP_DOMAINS);
+	DECLARE_BITMAP(apm_filtered, AP_DEVICES);
+	bool filter_domains, filter_adapters, filter_cdoms, do_hotplug = false;
 
 	mutex_lock(&matrix_mdev->kvm->lock);
 	mutex_lock(&matrix_dev->mdevs_lock);
 
-	filter_adapters = bitmap_and(apm, matrix_mdev->matrix.apm,
-				     matrix_mdev->apm_add, AP_DEVICES);
-	filter_domains = bitmap_and(aqm, matrix_mdev->matrix.aqm,
-				    matrix_mdev->aqm_add, AP_DOMAINS);
-
-	if (filter_adapters && filter_domains)
-		do_hotplug |= vfio_ap_mdev_filter_matrix(apm, aqm, matrix_mdev);
-	else if (filter_adapters)
-		do_hotplug |=
-			vfio_ap_mdev_filter_matrix(apm,
-						   matrix_mdev->shadow_apcb.aqm,
-						   matrix_mdev);
-	else
-		do_hotplug |=
-			vfio_ap_mdev_filter_matrix(matrix_mdev->shadow_apcb.apm,
-						   aqm, matrix_mdev);
+	filter_adapters = bitmap_intersects(matrix_mdev->matrix.apm,
+					    matrix_mdev->apm_add, AP_DEVICES);
+	filter_domains = bitmap_intersects(matrix_mdev->matrix.aqm,
+					   matrix_mdev->aqm_add, AP_DOMAINS);
+	filter_cdoms = bitmap_intersects(matrix_mdev->matrix.adm,
+					 matrix_mdev->adm_add, AP_DOMAINS);
 
-	if (bitmap_intersects(matrix_mdev->matrix.adm, matrix_mdev->adm_add,
-			      AP_DOMAINS))
+	if (filter_adapters || filter_domains)
+		do_hotplug = vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered);
+
+	if (filter_cdoms)
 		do_hotplug |= vfio_ap_mdev_filter_cdoms(matrix_mdev);
 
 	if (do_hotplug)
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
 
+	reset_queues_for_apids(matrix_mdev, apm_filtered);
+
 	mutex_unlock(&matrix_dev->mdevs_lock);
 	mutex_unlock(&matrix_mdev->kvm->lock);
 }
diff --git a/drivers/s390/crypto/vfio_ap_private.h b/drivers/s390/crypto/vfio_ap_private.h
index 88aff8b81f2f..98d37aa27044 100644
--- a/drivers/s390/crypto/vfio_ap_private.h
+++ b/drivers/s390/crypto/vfio_ap_private.h
@@ -133,6 +133,8 @@ struct ap_matrix_mdev {
  * @apqn: the APQN of the AP queue device
  * @saved_isc: the guest ISC registered with the GIB interface
  * @mdev_qnode: allows the vfio_ap_queue struct to be added to a hashtable
+ * @reset_qnode: allows the vfio_ap_queue struct to be added to a list of queues
+ *		 that need to be reset
  * @reset_status: the status from the last reset of the queue
  * @reset_work: work to wait for queue reset to complete
  */
@@ -143,6 +145,7 @@ struct vfio_ap_queue {
 #define VFIO_AP_ISC_INVALID 0xff
 	unsigned char saved_isc;
 	struct hlist_node mdev_qnode;
+	struct list_head reset_qnode;
 	struct ap_queue_status reset_status;
 	struct work_struct reset_work;
 };
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index b92a32b4b114..04c64ce0a1ca 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -255,9 +255,10 @@ static void qeth_l3_clear_ip_htable(struct qeth_card *card, int recover)
 		if (!recover) {
 			hash_del(&addr->hnode);
 			kfree(addr);
-			continue;
+		} else {
+			/* prepare for recovery */
+			addr->disp_flag = QETH_DISP_ADDR_ADD;
 		}
-		addr->disp_flag = QETH_DISP_ADDR_ADD;
 	}
 
 	mutex_unlock(&card->ip_lock);
@@ -278,9 +279,11 @@ static void qeth_l3_recover_ip(struct qeth_card *card)
 		if (addr->disp_flag == QETH_DISP_ADDR_ADD) {
 			rc = qeth_l3_register_addr_entry(card, addr);
 
-			if (!rc) {
+			if (!rc || rc == -EADDRINUSE || rc == -ENETDOWN) {
+				/* keep it in the records */
 				addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
 			} else {
+				/* bad address */
 				hash_del(&addr->hnode);
 				kfree(addr);
 			}
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index addac7fbe37b..9ce27092729c 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -1270,7 +1270,7 @@ source "drivers/scsi/arm/Kconfig"
 
 config JAZZ_ESP
 	bool "MIPS JAZZ FAS216 SCSI support"
-	depends on MACH_JAZZ && SCSI
+	depends on MACH_JAZZ && SCSI=y
 	select SCSI_SPI_ATTRS
 	help
 	  This is the driver for the onboard SCSI host adapter of MIPS Magnum
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index 19eee108db02..5c8d1ba3f8f3 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -319,17 +319,16 @@ static void fcoe_ctlr_announce(struct fcoe_ctlr *fip)
 {
 	struct fcoe_fcf *sel;
 	struct fcoe_fcf *fcf;
-	unsigned long flags;
 
 	mutex_lock(&fip->ctlr_mutex);
-	spin_lock_irqsave(&fip->ctlr_lock, flags);
+	spin_lock_bh(&fip->ctlr_lock);
 
 	kfree_skb(fip->flogi_req);
 	fip->flogi_req = NULL;
 	list_for_each_entry(fcf, &fip->fcfs, list)
 		fcf->flogi_sent = 0;
 
-	spin_unlock_irqrestore(&fip->ctlr_lock, flags);
+	spin_unlock_bh(&fip->ctlr_lock);
 	sel = fip->sel_fcf;
 
 	if (sel && ether_addr_equal(sel->fcf_mac, fip->dest_addr))
@@ -700,7 +699,6 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport,
 {
 	struct fc_frame *fp;
 	struct fc_frame_header *fh;
-	unsigned long flags;
 	u16 old_xid;
 	u8 op;
 	u8 mac[ETH_ALEN];
@@ -734,11 +732,11 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport,
 		op = FIP_DT_FLOGI;
 		if (fip->mode == FIP_MODE_VN2VN)
 			break;
-		spin_lock_irqsave(&fip->ctlr_lock, flags);
+		spin_lock_bh(&fip->ctlr_lock);
 		kfree_skb(fip->flogi_req);
 		fip->flogi_req = skb;
 		fip->flogi_req_send = 1;
-		spin_unlock_irqrestore(&fip->ctlr_lock, flags);
+		spin_unlock_bh(&fip->ctlr_lock);
 		schedule_work(&fip->timer_work);
 		return -EINPROGRESS;
 	case ELS_FDISC:
@@ -1707,11 +1705,10 @@ static int fcoe_ctlr_flogi_send_locked(struct fcoe_ctlr *fip)
 static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip)
 {
 	struct fcoe_fcf *fcf;
-	unsigned long flags;
 	int error;
 
 	mutex_lock(&fip->ctlr_mutex);
-	spin_lock_irqsave(&fip->ctlr_lock, flags);
+	spin_lock_bh(&fip->ctlr_lock);
 	LIBFCOE_FIP_DBG(fip, "re-sending FLOGI - reselect\n");
 	fcf = fcoe_ctlr_select(fip);
 	if (!fcf || fcf->flogi_sent) {
@@ -1722,7 +1719,7 @@ static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip)
 		fcoe_ctlr_solicit(fip, NULL);
 		error = fcoe_ctlr_flogi_send_locked(fip);
 	}
-	spin_unlock_irqrestore(&fip->ctlr_lock, flags);
+	spin_unlock_bh(&fip->ctlr_lock);
 	mutex_unlock(&fip->ctlr_mutex);
 	return error;
 }
@@ -1739,9 +1736,8 @@ static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip)
 static void fcoe_ctlr_flogi_send(struct fcoe_ctlr *fip)
 {
 	struct fcoe_fcf *fcf;
-	unsigned long flags;
 
-	spin_lock_irqsave(&fip->ctlr_lock, flags);
+	spin_lock_bh(&fip->ctlr_lock);
 	fcf = fip->sel_fcf;
 	if (!fcf || !fip->flogi_req_send)
 		goto unlock;
@@ -1768,7 +1764,7 @@ static void fcoe_ctlr_flogi_send(struct fcoe_ctlr *fip)
 	} else /* XXX */
 		LIBFCOE_FIP_DBG(fip, "No FCF selected - defer send\n");
 unlock:
-	spin_unlock_irqrestore(&fip->ctlr_lock, flags);
+	spin_unlock_bh(&fip->ctlr_lock);
 }
 
 /**
diff --git a/drivers/scsi/fcoe/fcoe_sysfs.c b/drivers/scsi/fcoe/fcoe_sysfs.c
index 408a806bf4c2..c64a085a7ee2 100644
--- a/drivers/scsi/fcoe/fcoe_sysfs.c
+++ b/drivers/scsi/fcoe/fcoe_sysfs.c
@@ -263,6 +263,7 @@ static ssize_t store_ctlr_mode(struct device *dev,
 			       const char *buf, size_t count)
 {
 	struct fcoe_ctlr_device *ctlr = dev_to_ctlr(dev);
+	int res;
 
 	if (count > FCOE_MAX_MODENAME_LEN)
 		return -EINVAL;
@@ -279,12 +280,13 @@ static ssize_t store_ctlr_mode(struct device *dev,
 			return -ENOTSUPP;
 		}
 
-		ctlr->mode = sysfs_match_string(fip_conn_type_names, buf);
-		if (ctlr->mode < 0 || ctlr->mode == FIP_CONN_TYPE_UNKNOWN) {
+		res = sysfs_match_string(fip_conn_type_names, buf);
+		if (res < 0 || res == FIP_CONN_TYPE_UNKNOWN) {
 			LIBFCOE_SYSFS_DBG(ctlr, "Unknown mode %s provided.\n",
 					  buf);
 			return -EINVAL;
 		}
+		ctlr->mode = res;
 
 		ctlr->f->set_fcoe_ctlr_mode(ctlr);
 		LIBFCOE_SYSFS_DBG(ctlr, "Mode changed to %s.\n", buf);
diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h
index 2074937c05bc..ce73f08ee889 100644
--- a/drivers/scsi/fnic/fnic.h
+++ b/drivers/scsi/fnic/fnic.h
@@ -305,6 +305,7 @@ struct fnic {
 	unsigned int copy_wq_base;
 	struct work_struct link_work;
 	struct work_struct frame_work;
+	struct work_struct flush_work;
 	struct sk_buff_head frame_queue;
 	struct sk_buff_head tx_queue;
 
@@ -363,7 +364,7 @@ void fnic_handle_event(struct work_struct *work);
 int fnic_rq_cmpl_handler(struct fnic *fnic, int);
 int fnic_alloc_rq_frame(struct vnic_rq *rq);
 void fnic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf);
-void fnic_flush_tx(struct fnic *);
+void fnic_flush_tx(struct work_struct *work);
 void fnic_eth_send(struct fcoe_ctlr *, struct sk_buff *skb);
 void fnic_set_port_id(struct fc_lport *, u32, struct fc_frame *);
 void fnic_update_mac(struct fc_lport *, u8 *new);
diff --git a/drivers/scsi/fnic/fnic_fcs.c b/drivers/scsi/fnic/fnic_fcs.c
index 5e312a55cc7d..a08293b2ad9f 100644
--- a/drivers/scsi/fnic/fnic_fcs.c
+++ b/drivers/scsi/fnic/fnic_fcs.c
@@ -1182,7 +1182,7 @@ int fnic_send(struct fc_lport *lp, struct fc_frame *fp)
 
 /**
  * fnic_flush_tx() - send queued frames.
- * @fnic: fnic device
+ * @work: pointer to work element
  *
  * Send frames that were waiting to go out in FC or Ethernet mode.
  * Whenever changing modes we purge queued frames, so these frames should
@@ -1190,8 +1190,9 @@ int fnic_send(struct fc_lport *lp, struct fc_frame *fp)
  *
  * Called without fnic_lock held.
  */
-void fnic_flush_tx(struct fnic *fnic)
+void fnic_flush_tx(struct work_struct *work)
 {
+	struct fnic *fnic = container_of(work, struct fnic, flush_work);
 	struct sk_buff *skb;
 	struct fc_frame *fp;
 
diff --git a/drivers/scsi/fnic/fnic_main.c b/drivers/scsi/fnic/fnic_main.c
index 5ed1d897311a..29eead383eb9 100644
--- a/drivers/scsi/fnic/fnic_main.c
+++ b/drivers/scsi/fnic/fnic_main.c
@@ -830,6 +830,7 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		spin_lock_init(&fnic->vlans_lock);
 		INIT_WORK(&fnic->fip_frame_work, fnic_handle_fip_frame);
 		INIT_WORK(&fnic->event_work, fnic_handle_event);
+		INIT_WORK(&fnic->flush_work, fnic_flush_tx);
 		skb_queue_head_init(&fnic->fip_frame_queue);
 		INIT_LIST_HEAD(&fnic->evlist);
 		INIT_LIST_HEAD(&fnic->vlans);
diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c
index 4d6db4509e75..fc4cee91b175 100644
--- a/drivers/scsi/fnic/fnic_scsi.c
+++ b/drivers/scsi/fnic/fnic_scsi.c
@@ -546,6 +546,7 @@ int fnic_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *sc)
 	if (fnic->sw_copy_wq[hwq].io_req_table[blk_mq_unique_tag_to_tag(mqtag)] != NULL) {
 		WARN(1, "fnic<%d>: %s: hwq: %d tag 0x%x already exists\n",
 				fnic->fnic_num, __func__, hwq, blk_mq_unique_tag_to_tag(mqtag));
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		return SCSI_MLQUEUE_HOST_BUSY;
 	}
 
@@ -679,7 +680,7 @@ static int fnic_fcpio_fw_reset_cmpl_handler(struct fnic *fnic,
 
 	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 
-	fnic_flush_tx(fnic);
+	queue_work(fnic_event_queue, &fnic->flush_work);
 
  reset_cmpl_handler_end:
 	fnic_clear_state_flags(fnic, FNIC_FLAGS_FWRESET);
@@ -735,7 +736,7 @@ static int fnic_fcpio_flogi_reg_cmpl_handler(struct fnic *fnic,
 		}
 		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 
-		fnic_flush_tx(fnic);
+		queue_work(fnic_event_queue, &fnic->flush_work);
 		queue_work(fnic_event_queue, &fnic->frame_work);
 	} else {
 		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
diff --git a/drivers/scsi/initio.c b/drivers/scsi/initio.c
index 2a50fda3a628..625fd547ee60 100644
--- a/drivers/scsi/initio.c
+++ b/drivers/scsi/initio.c
@@ -371,7 +371,6 @@ static u16 initio_se2_rd(unsigned long base, u8 addr)
  */
 static void initio_se2_wr(unsigned long base, u8 addr, u16 val)
 {
-	u8 rb;
 	u8 instr;
 	int i;
 
@@ -400,7 +399,7 @@ static void initio_se2_wr(unsigned long base, u8 addr, u16 val)
 		udelay(30);
 		outb(SE2CS, base + TUL_NVRAM);			/* -CLK */
 		udelay(30);
-		if ((rb = inb(base + TUL_NVRAM)) & SE2DI)
+		if (inb(base + TUL_NVRAM) & SE2DI)
 			break;	/* write complete */
 	}
 	outb(0, base + TUL_NVRAM);				/* -CS */
diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c
index 71f711cb0628..355a0bc0828e 100644
--- a/drivers/scsi/isci/request.c
+++ b/drivers/scsi/isci/request.c
@@ -3387,7 +3387,7 @@ static enum sci_status isci_io_request_build(struct isci_host *ihost,
 		return SCI_FAILURE;
 	}
 
-	return SCI_SUCCESS;
+	return status;
 }
 
 static struct isci_request *isci_request_from_tag(struct isci_host *ihost, u16 tag)
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index d26941b131fd..bf879d81846b 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -1918,7 +1918,7 @@ out:
  *
  * Returns the number of SGEs added to the SGL.
  **/
-static int
+static uint32_t
 lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 		struct sli4_sge *sgl, int datasegcnt,
 		struct lpfc_io_buf *lpfc_cmd)
@@ -1926,8 +1926,8 @@ lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 	struct scatterlist *sgde = NULL; /* s/g data entry */
 	struct sli4_sge_diseed *diseed = NULL;
 	dma_addr_t physaddr;
-	int i = 0, num_sge = 0, status;
-	uint32_t reftag;
+	int i = 0, status;
+	uint32_t reftag, num_sge = 0;
 	uint8_t txop, rxop;
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 	uint32_t rc;
@@ -2099,7 +2099,7 @@ out:
  *
  * Returns the number of SGEs added to the SGL.
  **/
-static int
+static uint32_t
 lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 		struct sli4_sge *sgl, int datacnt, int protcnt,
 		struct lpfc_io_buf *lpfc_cmd)
@@ -2123,8 +2123,8 @@ lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 	uint32_t rc;
 #endif
 	uint32_t checking = 1;
-	uint32_t dma_offset = 0;
-	int num_sge = 0, j = 2;
+	uint32_t dma_offset = 0, num_sge = 0;
+	int j = 2;
 	struct sli4_hybrid_sgl *sgl_xtra = NULL;
 
 	sgpe = scsi_prot_sglist(sc);
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 46e6f807d1ca..706985358c6a 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -4880,7 +4880,7 @@ void lpfc_reset_barrier(struct lpfc_hba *phba)
 	lockdep_assert_held(&phba->hbalock);
 
 	pci_read_config_byte(phba->pcidev, PCI_HEADER_TYPE, &hdrtype);
-	if (hdrtype != 0x80 ||
+	if (hdrtype != PCI_HEADER_TYPE_MFD ||
 	    (FC_JEDEC_ID(phba->vpd.rev.biuRev) != HELIOS_JEDEC_ID &&
 	     FC_JEDEC_ID(phba->vpd.rev.biuRev) != THOR_JEDEC_ID))
 		return;
diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c
index d8c57a0a518f..528f19f782f2 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_fw.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c
@@ -475,7 +475,7 @@ int mpi3mr_process_admin_reply_q(struct mpi3mr_ioc *mrioc)
  * @op_reply_q: op_reply_qinfo object
  * @reply_ci: operational reply descriptor's queue consumer index
  *
- * Returns reply descriptor frame address
+ * Returns: reply descriptor frame address
  */
 static inline struct mpi3_default_reply_descriptor *
 mpi3mr_get_reply_desc(struct op_reply_qinfo *op_reply_q, u32 reply_ci)
@@ -1063,7 +1063,6 @@ enum mpi3mr_iocstate mpi3mr_get_iocstate(struct mpi3mr_ioc *mrioc)
  * @mrioc: Adapter instance reference
  *
  * Free the DMA memory allocated for IOCTL handling purpose.
-
  *
  * Return: None
  */
@@ -1106,7 +1105,6 @@ static void mpi3mr_free_ioctl_dma_memory(struct mpi3mr_ioc *mrioc)
 /**
  * mpi3mr_alloc_ioctl_dma_memory - Alloc memory for ioctl dma
  * @mrioc: Adapter instance reference
-
  *
  * This function allocates dmaable memory required to handle the
  * application issued MPI3 IOCTL requests.
@@ -1241,7 +1239,7 @@ static int mpi3mr_issue_and_process_mur(struct mpi3mr_ioc *mrioc,
  * during reset/resume
  * @mrioc: Adapter instance reference
  *
- * Return zero if the new IOCFacts parameters value is compatible with
+ * Return: zero if the new IOCFacts parameters value is compatible with
  * older values else return -EPERM
  */
 static int
diff --git a/drivers/scsi/mpi3mr/mpi3mr_transport.c b/drivers/scsi/mpi3mr/mpi3mr_transport.c
index c0c8ab586957..d32ad46318cb 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_transport.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_transport.c
@@ -1671,7 +1671,7 @@ mpi3mr_update_mr_sas_port(struct mpi3mr_ioc *mrioc, struct host_port *h_port,
 void
 mpi3mr_refresh_sas_ports(struct mpi3mr_ioc *mrioc)
 {
-	struct host_port h_port[64];
+	struct host_port *h_port = NULL;
 	int i, j, found, host_port_count = 0, port_idx;
 	u16 sz, attached_handle, ioc_status;
 	struct mpi3_sas_io_unit_page0 *sas_io_unit_pg0 = NULL;
@@ -1685,6 +1685,10 @@ mpi3mr_refresh_sas_ports(struct mpi3mr_ioc *mrioc)
 	sas_io_unit_pg0 = kzalloc(sz, GFP_KERNEL);
 	if (!sas_io_unit_pg0)
 		return;
+	h_port = kcalloc(64, sizeof(struct host_port), GFP_KERNEL);
+	if (!h_port)
+		goto out;
+
 	if (mpi3mr_cfg_get_sas_io_unit_pg0(mrioc, sas_io_unit_pg0, sz)) {
 		ioc_err(mrioc, "failure at %s:%d/%s()!\n",
 		    __FILE__, __LINE__, __func__);
@@ -1814,6 +1818,7 @@ mpi3mr_refresh_sas_ports(struct mpi3mr_ioc *mrioc)
 		}
 	}
 out:
+	kfree(h_port);
 	kfree(sas_io_unit_pg0);
 }
 
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 8761bc58d965..b8120ca93c79 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -7378,7 +7378,9 @@ _base_wait_for_iocstate(struct MPT3SAS_ADAPTER *ioc, int timeout)
 		return -EFAULT;
 	}
 
- issue_diag_reset:
+	return 0;
+
+issue_diag_reset:
 	rc = _base_diag_reset(ioc);
 	return rc;
 }
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 03348f605c2e..dd674378f2f3 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -2889,7 +2889,7 @@ static void qla2x00_iocb_work_fn(struct work_struct *work)
 static void
 qla_trace_init(void)
 {
-	qla_trc_array = trace_array_get_by_name("qla2xxx");
+	qla_trc_array = trace_array_get_by_name("qla2xxx", NULL);
 	if (!qla_trc_array) {
 		ql_log(ql_log_fatal, NULL, 0x0001,
 		       "Unable to create qla2xxx trace instance, instance logging will be disabled.\n");
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 76d369343c7a..8cad9792a562 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -328,21 +328,39 @@ static int scsi_vpd_inquiry(struct scsi_device *sdev, unsigned char *buffer,
 	return result + 4;
 }
 
+enum scsi_vpd_parameters {
+	SCSI_VPD_HEADER_SIZE = 4,
+	SCSI_VPD_LIST_SIZE = 36,
+};
+
 static int scsi_get_vpd_size(struct scsi_device *sdev, u8 page)
 {
-	unsigned char vpd_header[SCSI_VPD_HEADER_SIZE] __aligned(4);
+	unsigned char vpd[SCSI_VPD_LIST_SIZE] __aligned(4);
 	int result;
 
 	if (sdev->no_vpd_size)
 		return SCSI_DEFAULT_VPD_LEN;
 
 	/*
+	 * Fetch the supported pages VPD and validate that the requested page
+	 * number is present.
+	 */
+	if (page != 0) {
+		result = scsi_vpd_inquiry(sdev, vpd, 0, sizeof(vpd));
+		if (result < SCSI_VPD_HEADER_SIZE)
+			return 0;
+
+		result -= SCSI_VPD_HEADER_SIZE;
+		if (!memchr(&vpd[SCSI_VPD_HEADER_SIZE], page, result))
+			return 0;
+	}
+	/*
 	 * Fetch the VPD page header to find out how big the page
 	 * is. This is done to prevent problems on legacy devices
 	 * which can not handle allocation lengths as large as
 	 * potentially requested by the caller.
 	 */
-	result = scsi_vpd_inquiry(sdev, vpd_header, page, sizeof(vpd_header));
+	result = scsi_vpd_inquiry(sdev, vpd, page, SCSI_VPD_HEADER_SIZE);
 	if (result < 0)
 		return 0;
 
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 885a7d5df3b9..612489afe8d2 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -61,11 +61,11 @@ static int scsi_eh_try_stu(struct scsi_cmnd *scmd);
 static enum scsi_disposition scsi_try_to_abort_cmd(const struct scsi_host_template *,
 						   struct scsi_cmnd *);
 
-void scsi_eh_wakeup(struct Scsi_Host *shost)
+void scsi_eh_wakeup(struct Scsi_Host *shost, unsigned int busy)
 {
 	lockdep_assert_held(shost->host_lock);
 
-	if (scsi_host_busy(shost) == shost->host_failed) {
+	if (busy == shost->host_failed) {
 		trace_scsi_eh_wakeup(shost);
 		wake_up_process(shost->ehandler);
 		SCSI_LOG_ERROR_RECOVERY(5, shost_printk(KERN_INFO, shost,
@@ -88,7 +88,7 @@ void scsi_schedule_eh(struct Scsi_Host *shost)
 	if (scsi_host_set_state(shost, SHOST_RECOVERY) == 0 ||
 	    scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY) == 0) {
 		shost->host_eh_scheduled++;
-		scsi_eh_wakeup(shost);
+		scsi_eh_wakeup(shost, scsi_host_busy(shost));
 	}
 
 	spin_unlock_irqrestore(shost->host_lock, flags);
@@ -282,11 +282,12 @@ static void scsi_eh_inc_host_failed(struct rcu_head *head)
 {
 	struct scsi_cmnd *scmd = container_of(head, typeof(*scmd), rcu);
 	struct Scsi_Host *shost = scmd->device->host;
+	unsigned int busy = scsi_host_busy(shost);
 	unsigned long flags;
 
 	spin_lock_irqsave(shost->host_lock, flags);
 	shost->host_failed++;
-	scsi_eh_wakeup(shost);
+	scsi_eh_wakeup(shost, busy);
 	spin_unlock_irqrestore(shost->host_lock, flags);
 }
 
@@ -2197,15 +2198,18 @@ void scsi_eh_flush_done_q(struct list_head *done_q)
 	struct scsi_cmnd *scmd, *next;
 
 	list_for_each_entry_safe(scmd, next, done_q, eh_entry) {
+		struct scsi_device *sdev = scmd->device;
+
 		list_del_init(&scmd->eh_entry);
-		if (scsi_device_online(scmd->device) &&
-		    !scsi_noretry_cmd(scmd) && scsi_cmd_retry_allowed(scmd) &&
-			scsi_eh_should_retry_cmd(scmd)) {
+		if (scsi_device_online(sdev) && !scsi_noretry_cmd(scmd) &&
+		    scsi_cmd_retry_allowed(scmd) &&
+		    scsi_eh_should_retry_cmd(scmd)) {
 			SCSI_LOG_ERROR_RECOVERY(3,
 				scmd_printk(KERN_INFO, scmd,
 					     "%s: flush retry cmd\n",
 					     current->comm));
 				scsi_queue_insert(scmd, SCSI_MLQUEUE_EH_RETRY);
+				blk_mq_kick_requeue_list(sdev->request_queue);
 		} else {
 			/*
 			 * If just we got sense for the device (called
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index cf3864f72093..df5ac03d5d6c 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -278,9 +278,11 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost, struct scsi_cmnd *cmd)
 	rcu_read_lock();
 	__clear_bit(SCMD_STATE_INFLIGHT, &cmd->state);
 	if (unlikely(scsi_host_in_recovery(shost))) {
+		unsigned int busy = scsi_host_busy(shost);
+
 		spin_lock_irqsave(shost->host_lock, flags);
 		if (shost->host_failed || shost->host_eh_scheduled)
-			scsi_eh_wakeup(shost);
+			scsi_eh_wakeup(shost, busy);
 		spin_unlock_irqrestore(shost->host_lock, flags);
 	}
 	rcu_read_unlock();
diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h
index 3f0dfb97db6b..1fbfe1b52c9f 100644
--- a/drivers/scsi/scsi_priv.h
+++ b/drivers/scsi/scsi_priv.h
@@ -92,7 +92,7 @@ extern void scmd_eh_abort_handler(struct work_struct *work);
 extern enum blk_eh_timer_return scsi_timeout(struct request *req);
 extern int scsi_error_handler(void *host);
 extern enum scsi_disposition scsi_decide_disposition(struct scsi_cmnd *cmd);
-extern void scsi_eh_wakeup(struct Scsi_Host *shost);
+extern void scsi_eh_wakeup(struct Scsi_Host *shost, unsigned int busy);
 extern void scsi_eh_scmd_add(struct scsi_cmnd *);
 void scsi_eh_ready_devs(struct Scsi_Host *shost,
 			struct list_head *work_q,
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 44680f65ea14..9969f4e2f1c3 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -332,7 +332,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 
 	sdev->sg_reserved_size = INT_MAX;
 
-	q = blk_mq_init_queue(&sdev->host->tag_set);
+	q = blk_mq_alloc_queue(&sdev->host->tag_set, NULL, NULL);
 	if (IS_ERR(q)) {
 		/* release fn is set up in scsi_sysfs_device_initialise, so
 		 * have to free and put manually here */
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 0833b3e6aa6e..bdd0acf7fa3c 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3407,6 +3407,24 @@ static bool sd_validate_opt_xfer_size(struct scsi_disk *sdkp,
 	return true;
 }
 
+static void sd_read_block_zero(struct scsi_disk *sdkp)
+{
+	unsigned int buf_len = sdkp->device->sector_size;
+	char *buffer, cmd[10] = { };
+
+	buffer = kmalloc(buf_len, GFP_KERNEL);
+	if (!buffer)
+		return;
+
+	cmd[0] = READ_10;
+	put_unaligned_be32(0, &cmd[2]); /* Logical block address 0 */
+	put_unaligned_be16(1, &cmd[7]);	/* Transfer 1 logical block */
+
+	scsi_execute_cmd(sdkp->device, cmd, REQ_OP_DRV_IN, buffer, buf_len,
+			 SD_TIMEOUT, sdkp->max_retries, NULL);
+	kfree(buffer);
+}
+
 /**
  *	sd_revalidate_disk - called the first time a new disk is seen,
  *	performs disk spin up, read_capacity, etc.
@@ -3446,7 +3464,13 @@ static int sd_revalidate_disk(struct gendisk *disk)
 	 */
 	if (sdkp->media_present) {
 		sd_read_capacity(sdkp, buffer);
-
+		/*
+		 * Some USB/UAS devices return generic values for mode pages
+		 * until the media has been accessed. Trigger a READ operation
+		 * to force the device to populate mode pages.
+		 */
+		if (sdp->read_before_ms)
+			sd_read_block_zero(sdkp);
 		/*
 		 * set the default to rotational.  All non-rotational devices
 		 * support the block characteristics VPD page, which will
diff --git a/drivers/scsi/smartpqi/smartpqi.h b/drivers/scsi/smartpqi/smartpqi.h
index 041940183516..cdedc271857a 100644
--- a/drivers/scsi/smartpqi/smartpqi.h
+++ b/drivers/scsi/smartpqi/smartpqi.h
@@ -1347,7 +1347,6 @@ struct pqi_ctrl_info {
 	bool		controller_online;
 	bool		block_requests;
 	bool		scan_blocked;
-	u8		logical_volume_rescan_needed : 1;
 	u8		inbound_spanning_supported : 1;
 	u8		outbound_spanning_supported : 1;
 	u8		pqi_mode_enabled : 1;
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 9a58df9312fa..385180c98be4 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -33,11 +33,11 @@
 #define BUILD_TIMESTAMP
 #endif
 
-#define DRIVER_VERSION		"2.1.24-046"
+#define DRIVER_VERSION		"2.1.26-030"
 #define DRIVER_MAJOR		2
 #define DRIVER_MINOR		1
-#define DRIVER_RELEASE		24
-#define DRIVER_REVISION		46
+#define DRIVER_RELEASE		26
+#define DRIVER_REVISION		30
 
 #define DRIVER_NAME		"Microchip SmartPQI Driver (v" \
 				DRIVER_VERSION BUILD_TIMESTAMP ")"
@@ -2093,8 +2093,6 @@ static void pqi_scsi_update_device(struct pqi_ctrl_info *ctrl_info,
 		if (existing_device->devtype == TYPE_DISK) {
 			existing_device->raid_level = new_device->raid_level;
 			existing_device->volume_status = new_device->volume_status;
-			if (ctrl_info->logical_volume_rescan_needed)
-				existing_device->rescan = true;
 			memset(existing_device->next_bypass_group, 0, sizeof(existing_device->next_bypass_group));
 			if (!pqi_raid_maps_equal(existing_device->raid_map, new_device->raid_map)) {
 				kfree(existing_device->raid_map);
@@ -2164,6 +2162,20 @@ static inline void pqi_init_device_tmf_work(struct pqi_scsi_dev *device)
 		INIT_WORK(&tmf_work->work_struct, pqi_tmf_worker);
 }
 
+static inline bool pqi_volume_rescan_needed(struct pqi_scsi_dev *device)
+{
+	if (pqi_device_in_remove(device))
+		return false;
+
+	if (device->sdev == NULL)
+		return false;
+
+	if (!scsi_device_online(device->sdev))
+		return false;
+
+	return device->rescan;
+}
+
 static void pqi_update_device_list(struct pqi_ctrl_info *ctrl_info,
 	struct pqi_scsi_dev *new_device_list[], unsigned int num_new_devices)
 {
@@ -2284,9 +2296,13 @@ static void pqi_update_device_list(struct pqi_ctrl_info *ctrl_info,
 		if (device->sdev && device->queue_depth != device->advertised_queue_depth) {
 			device->advertised_queue_depth = device->queue_depth;
 			scsi_change_queue_depth(device->sdev, device->advertised_queue_depth);
-			if (device->rescan) {
-				scsi_rescan_device(device->sdev);
+			spin_lock_irqsave(&ctrl_info->scsi_device_list_lock, flags);
+			if (pqi_volume_rescan_needed(device)) {
 				device->rescan = false;
+				spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
+				scsi_rescan_device(device->sdev);
+			} else {
+				spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
 			}
 		}
 	}
@@ -2308,8 +2324,6 @@ static void pqi_update_device_list(struct pqi_ctrl_info *ctrl_info,
 		}
 	}
 
-	ctrl_info->logical_volume_rescan_needed = false;
-
 }
 
 static inline bool pqi_is_supported_device(struct pqi_scsi_dev *device)
@@ -3702,6 +3716,21 @@ static bool pqi_ofa_process_event(struct pqi_ctrl_info *ctrl_info,
 	return ack_event;
 }
 
+static void pqi_mark_volumes_for_rescan(struct pqi_ctrl_info *ctrl_info)
+{
+	unsigned long flags;
+	struct pqi_scsi_dev *device;
+
+	spin_lock_irqsave(&ctrl_info->scsi_device_list_lock, flags);
+
+	list_for_each_entry(device, &ctrl_info->scsi_device_list, scsi_device_list_entry) {
+		if (pqi_is_logical_device(device) && device->devtype == TYPE_DISK)
+			device->rescan = true;
+	}
+
+	spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
+}
+
 static void pqi_disable_raid_bypass(struct pqi_ctrl_info *ctrl_info)
 {
 	unsigned long flags;
@@ -3742,7 +3771,7 @@ static void pqi_event_worker(struct work_struct *work)
 				ack_event = true;
 				rescan_needed = true;
 				if (event->event_type == PQI_EVENT_TYPE_LOGICAL_DEVICE)
-					ctrl_info->logical_volume_rescan_needed = true;
+					pqi_mark_volumes_for_rescan(ctrl_info);
 				else if (event->event_type == PQI_EVENT_TYPE_AIO_STATE_CHANGE)
 					pqi_disable_raid_bypass(ctrl_info);
 			}
@@ -6504,8 +6533,11 @@ static void pqi_map_queues(struct Scsi_Host *shost)
 {
 	struct pqi_ctrl_info *ctrl_info = shost_to_hba(shost);
 
-	blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT],
+	if (!ctrl_info->disable_managed_interrupts)
+		return blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT],
 			      ctrl_info->pci_dev, 0);
+	else
+		return blk_mq_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT]);
 }
 
 static inline bool pqi_is_tape_changer_device(struct pqi_scsi_dev *device)
@@ -10144,6 +10176,18 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1137, 0x02f8)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1137, 0x02f9)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1137, 0x02fa)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 				0x1e93, 0x1000)
 	},
 	{
@@ -10200,6 +10244,34 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1f51, 0x100e)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1f51, 0x100f)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1f51, 0x1010)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1f51, 0x1011)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1f51, 0x1043)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1f51, 0x1044)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1f51, 0x1045)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       PCI_ANY_ID, PCI_ANY_ID)
 	},
 	{ 0 }
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index a95936b18f69..7ceb982040a5 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -330,6 +330,7 @@ enum storvsc_request_type {
  */
 
 static int storvsc_ringbuffer_size = (128 * 1024);
+static int aligned_ringbuffer_size;
 static u32 max_outstanding_req_per_channel;
 static int storvsc_change_queue_depth(struct scsi_device *sdev, int queue_depth);
 
@@ -687,8 +688,8 @@ static void handle_sc_creation(struct vmbus_channel *new_sc)
 	new_sc->next_request_id_callback = storvsc_next_request_id;
 
 	ret = vmbus_open(new_sc,
-			 storvsc_ringbuffer_size,
-			 storvsc_ringbuffer_size,
+			 aligned_ringbuffer_size,
+			 aligned_ringbuffer_size,
 			 (void *)&props,
 			 sizeof(struct vmstorage_channel_properties),
 			 storvsc_on_channel_callback, new_sc);
@@ -1973,7 +1974,7 @@ static int storvsc_probe(struct hv_device *device,
 	dma_set_min_align_mask(&device->device, HV_HYP_PAGE_SIZE - 1);
 
 	stor_device->port_number = host->host_no;
-	ret = storvsc_connect_to_vsp(device, storvsc_ringbuffer_size, is_fc);
+	ret = storvsc_connect_to_vsp(device, aligned_ringbuffer_size, is_fc);
 	if (ret)
 		goto err_out1;
 
@@ -2164,7 +2165,7 @@ static int storvsc_resume(struct hv_device *hv_dev)
 {
 	int ret;
 
-	ret = storvsc_connect_to_vsp(hv_dev, storvsc_ringbuffer_size,
+	ret = storvsc_connect_to_vsp(hv_dev, aligned_ringbuffer_size,
 				     hv_dev_is_fc(hv_dev));
 	return ret;
 }
@@ -2198,8 +2199,9 @@ static int __init storvsc_drv_init(void)
 	 * the ring buffer indices) by the max request size (which is
 	 * vmbus_channel_packet_multipage_buffer + struct vstor_packet + u64)
 	 */
+	aligned_ringbuffer_size = VMBUS_RING_SIZE(storvsc_ringbuffer_size);
 	max_outstanding_req_per_channel =
-		((storvsc_ringbuffer_size - PAGE_SIZE) /
+		((aligned_ringbuffer_size - PAGE_SIZE) /
 		ALIGN(MAX_MULTIPAGE_BUFFER_PACKET +
 		sizeof(struct vstor_packet) + sizeof(u64),
 		sizeof(u64)));
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 9d1bdcdc1331..617eb892f4ad 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -37,6 +37,11 @@
 #define VIRTIO_SCSI_EVENT_LEN 8
 #define VIRTIO_SCSI_VQ_BASE 2
 
+static unsigned int virtscsi_poll_queues;
+module_param(virtscsi_poll_queues, uint, 0644);
+MODULE_PARM_DESC(virtscsi_poll_queues,
+		 "The number of dedicated virtqueues for polling I/O");
+
 /* Command queue element */
 struct virtio_scsi_cmd {
 	struct scsi_cmnd *sc;
@@ -76,6 +81,7 @@ struct virtio_scsi {
 	struct virtio_scsi_event_node event_list[VIRTIO_SCSI_EVENT_LEN];
 
 	u32 num_queues;
+	int io_queues[HCTX_MAX_TYPES];
 
 	struct hlist_node node;
 
@@ -182,8 +188,6 @@ static void virtscsi_vq_done(struct virtio_scsi *vscsi,
 		while ((buf = virtqueue_get_buf(vq, &len)) != NULL)
 			fn(vscsi, buf);
 
-		if (unlikely(virtqueue_is_broken(vq)))
-			break;
 	} while (!virtqueue_enable_cb(vq));
 	spin_unlock_irqrestore(&virtscsi_vq->vq_lock, flags);
 }
@@ -722,9 +726,49 @@ static int virtscsi_abort(struct scsi_cmnd *sc)
 static void virtscsi_map_queues(struct Scsi_Host *shost)
 {
 	struct virtio_scsi *vscsi = shost_priv(shost);
-	struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT];
+	int i, qoff;
+
+	for (i = 0, qoff = 0; i < shost->nr_maps; i++) {
+		struct blk_mq_queue_map *map = &shost->tag_set.map[i];
+
+		map->nr_queues = vscsi->io_queues[i];
+		map->queue_offset = qoff;
+		qoff += map->nr_queues;
+
+		if (map->nr_queues == 0)
+			continue;
+
+		/*
+		 * Regular queues have interrupts and hence CPU affinity is
+		 * defined by the core virtio code, but polling queues have
+		 * no interrupts so we let the block layer assign CPU affinity.
+		 */
+		if (i == HCTX_TYPE_POLL)
+			blk_mq_map_queues(map);
+		else
+			blk_mq_virtio_map_queues(map, vscsi->vdev, 2);
+	}
+}
+
+static int virtscsi_mq_poll(struct Scsi_Host *shost, unsigned int queue_num)
+{
+	struct virtio_scsi *vscsi = shost_priv(shost);
+	struct virtio_scsi_vq *virtscsi_vq = &vscsi->req_vqs[queue_num];
+	unsigned long flags;
+	unsigned int len;
+	int found = 0;
+	void *buf;
+
+	spin_lock_irqsave(&virtscsi_vq->vq_lock, flags);
+
+	while ((buf = virtqueue_get_buf(virtscsi_vq->vq, &len)) != NULL) {
+		virtscsi_complete_cmd(vscsi, buf);
+		found++;
+	}
+
+	spin_unlock_irqrestore(&virtscsi_vq->vq_lock, flags);
 
-	blk_mq_virtio_map_queues(qmap, vscsi->vdev, 2);
+	return found;
 }
 
 static void virtscsi_commit_rqs(struct Scsi_Host *shost, u16 hwq)
@@ -751,6 +795,7 @@ static const struct scsi_host_template virtscsi_host_template = {
 	.this_id = -1,
 	.cmd_size = sizeof(struct virtio_scsi_cmd),
 	.queuecommand = virtscsi_queuecommand,
+	.mq_poll = virtscsi_mq_poll,
 	.commit_rqs = virtscsi_commit_rqs,
 	.change_queue_depth = virtscsi_change_queue_depth,
 	.eh_abort_handler = virtscsi_abort,
@@ -795,13 +840,14 @@ static int virtscsi_init(struct virtio_device *vdev,
 {
 	int err;
 	u32 i;
-	u32 num_vqs;
+	u32 num_vqs, num_poll_vqs, num_req_vqs;
 	vq_callback_t **callbacks;
 	const char **names;
 	struct virtqueue **vqs;
 	struct irq_affinity desc = { .pre_vectors = 2 };
 
-	num_vqs = vscsi->num_queues + VIRTIO_SCSI_VQ_BASE;
+	num_req_vqs = vscsi->num_queues;
+	num_vqs = num_req_vqs + VIRTIO_SCSI_VQ_BASE;
 	vqs = kmalloc_array(num_vqs, sizeof(struct virtqueue *), GFP_KERNEL);
 	callbacks = kmalloc_array(num_vqs, sizeof(vq_callback_t *),
 				  GFP_KERNEL);
@@ -812,15 +858,31 @@ static int virtscsi_init(struct virtio_device *vdev,
 		goto out;
 	}
 
+	num_poll_vqs = min_t(unsigned int, virtscsi_poll_queues,
+			     num_req_vqs - 1);
+	vscsi->io_queues[HCTX_TYPE_DEFAULT] = num_req_vqs - num_poll_vqs;
+	vscsi->io_queues[HCTX_TYPE_READ] = 0;
+	vscsi->io_queues[HCTX_TYPE_POLL] = num_poll_vqs;
+
+	dev_info(&vdev->dev, "%d/%d/%d default/read/poll queues\n",
+		 vscsi->io_queues[HCTX_TYPE_DEFAULT],
+		 vscsi->io_queues[HCTX_TYPE_READ],
+		 vscsi->io_queues[HCTX_TYPE_POLL]);
+
 	callbacks[0] = virtscsi_ctrl_done;
 	callbacks[1] = virtscsi_event_done;
 	names[0] = "control";
 	names[1] = "event";
-	for (i = VIRTIO_SCSI_VQ_BASE; i < num_vqs; i++) {
+	for (i = VIRTIO_SCSI_VQ_BASE; i < num_vqs - num_poll_vqs; i++) {
 		callbacks[i] = virtscsi_req_done;
 		names[i] = "request";
 	}
 
+	for (; i < num_vqs; i++) {
+		callbacks[i] = NULL;
+		names[i] = "request_poll";
+	}
+
 	/* Discover virtqueues and write information to configuration.  */
 	err = virtio_find_vqs(vdev, num_vqs, vqs, callbacks, names, &desc);
 	if (err)
@@ -874,6 +936,7 @@ static int virtscsi_probe(struct virtio_device *vdev)
 
 	sg_elems = virtscsi_config_get(vdev, seg_max) ?: 1;
 	shost->sg_tablesize = sg_elems;
+	shost->nr_maps = 1;
 	vscsi = shost_priv(shost);
 	vscsi->vdev = vdev;
 	vscsi->num_queues = num_queues;
@@ -883,6 +946,9 @@ static int virtscsi_probe(struct virtio_device *vdev)
 	if (err)
 		goto virtscsi_init_failed;
 
+	if (vscsi->io_queues[HCTX_TYPE_POLL])
+		shost->nr_maps = HCTX_TYPE_POLL + 1;
+
 	shost->can_queue = virtqueue_get_vring_size(vscsi->req_vqs[0].vq);
 
 	cmd_per_lun = virtscsi_config_get(vdev, cmd_per_lun) ?: 1;
diff --git a/drivers/sh/maple/maple.c b/drivers/sh/maple/maple.c
index e05473c5c267..16018009a5a6 100644
--- a/drivers/sh/maple/maple.c
+++ b/drivers/sh/maple/maple.c
@@ -59,6 +59,7 @@ struct maple_device_specify {
 static bool checked[MAPLE_PORTS];
 static bool empty[MAPLE_PORTS];
 static struct maple_device *baseunits[MAPLE_PORTS];
+static const struct bus_type maple_bus_type;
 
 /**
  * maple_driver_register - register a maple driver
@@ -773,11 +774,10 @@ static struct maple_driver maple_unsupported_device = {
 /*
  * maple_bus_type - core maple bus structure
  */
-struct bus_type maple_bus_type = {
+static const struct bus_type maple_bus_type = {
 	.name = "maple",
 	.match = maple_match_bus_driver,
 };
-EXPORT_SYMBOL_GPL(maple_bus_type);
 
 static struct device maple_bus = {
 	.init_name = "maple",
diff --git a/drivers/soc/apple/mailbox.c b/drivers/soc/apple/mailbox.c
index 780199bf351e..49a0955e82d6 100644
--- a/drivers/soc/apple/mailbox.c
+++ b/drivers/soc/apple/mailbox.c
@@ -296,14 +296,14 @@ struct apple_mbox *apple_mbox_get(struct device *dev, int index)
 	of_node_put(args.np);
 
 	if (!pdev)
-		return ERR_PTR(EPROBE_DEFER);
+		return ERR_PTR(-EPROBE_DEFER);
 
 	mbox = platform_get_drvdata(pdev);
 	if (!mbox)
-		return ERR_PTR(EPROBE_DEFER);
+		return ERR_PTR(-EPROBE_DEFER);
 
 	if (!device_link_add(dev, &pdev->dev, DL_FLAG_AUTOREMOVE_CONSUMER))
-		return ERR_PTR(ENODEV);
+		return ERR_PTR(-ENODEV);
 
 	return mbox;
 }
diff --git a/drivers/soc/microchip/Kconfig b/drivers/soc/microchip/Kconfig
index 9b0fdd95276e..19f4b576f822 100644
--- a/drivers/soc/microchip/Kconfig
+++ b/drivers/soc/microchip/Kconfig
@@ -1,5 +1,5 @@
 config POLARFIRE_SOC_SYS_CTRL
-	tristate "POLARFIRE_SOC_SYS_CTRL"
+	tristate "Microchip PolarFire SoC (MPFS) system controller support"
 	depends on POLARFIRE_SOC_MAILBOX
 	depends on MTD
 	help
diff --git a/drivers/soc/qcom/pmic_glink.c b/drivers/soc/qcom/pmic_glink.c
index f4bfd24386f1..f913e9bd57ed 100644
--- a/drivers/soc/qcom/pmic_glink.c
+++ b/drivers/soc/qcom/pmic_glink.c
@@ -265,10 +265,17 @@ static int pmic_glink_probe(struct platform_device *pdev)
 
 	pg->client_mask = *match_data;
 
+	pg->pdr = pdr_handle_alloc(pmic_glink_pdr_callback, pg);
+	if (IS_ERR(pg->pdr)) {
+		ret = dev_err_probe(&pdev->dev, PTR_ERR(pg->pdr),
+				    "failed to initialize pdr\n");
+		return ret;
+	}
+
 	if (pg->client_mask & BIT(PMIC_GLINK_CLIENT_UCSI)) {
 		ret = pmic_glink_add_aux_device(pg, &pg->ucsi_aux, "ucsi");
 		if (ret)
-			return ret;
+			goto out_release_pdr_handle;
 	}
 	if (pg->client_mask & BIT(PMIC_GLINK_CLIENT_ALTMODE)) {
 		ret = pmic_glink_add_aux_device(pg, &pg->altmode_aux, "altmode");
@@ -281,17 +288,11 @@ static int pmic_glink_probe(struct platform_device *pdev)
 			goto out_release_altmode_aux;
 	}
 
-	pg->pdr = pdr_handle_alloc(pmic_glink_pdr_callback, pg);
-	if (IS_ERR(pg->pdr)) {
-		ret = dev_err_probe(&pdev->dev, PTR_ERR(pg->pdr), "failed to initialize pdr\n");
-		goto out_release_aux_devices;
-	}
-
 	service = pdr_add_lookup(pg->pdr, "tms/servreg", "msm/adsp/charger_pd");
 	if (IS_ERR(service)) {
 		ret = dev_err_probe(&pdev->dev, PTR_ERR(service),
 				    "failed adding pdr lookup for charger_pd\n");
-		goto out_release_pdr_handle;
+		goto out_release_aux_devices;
 	}
 
 	mutex_lock(&__pmic_glink_lock);
@@ -300,8 +301,6 @@ static int pmic_glink_probe(struct platform_device *pdev)
 
 	return 0;
 
-out_release_pdr_handle:
-	pdr_handle_release(pg->pdr);
 out_release_aux_devices:
 	if (pg->client_mask & BIT(PMIC_GLINK_CLIENT_BATT))
 		pmic_glink_del_aux_device(pg, &pg->ps_aux);
@@ -311,6 +310,8 @@ out_release_altmode_aux:
 out_release_ucsi_aux:
 	if (pg->client_mask & BIT(PMIC_GLINK_CLIENT_UCSI))
 		pmic_glink_del_aux_device(pg, &pg->ucsi_aux);
+out_release_pdr_handle:
+	pdr_handle_release(pg->pdr);
 
 	return ret;
 }
diff --git a/drivers/soc/qcom/pmic_glink_altmode.c b/drivers/soc/qcom/pmic_glink_altmode.c
index 5fcd0fdd2faa..b3808fc24c69 100644
--- a/drivers/soc/qcom/pmic_glink_altmode.c
+++ b/drivers/soc/qcom/pmic_glink_altmode.c
@@ -76,7 +76,7 @@ struct pmic_glink_altmode_port {
 
 	struct work_struct work;
 
-	struct device *bridge;
+	struct auxiliary_device *bridge;
 
 	enum typec_orientation orientation;
 	u16 svid;
@@ -230,7 +230,7 @@ static void pmic_glink_altmode_worker(struct work_struct *work)
 	else
 		pmic_glink_altmode_enable_usb(altmode, alt_port);
 
-	drm_aux_hpd_bridge_notify(alt_port->bridge,
+	drm_aux_hpd_bridge_notify(&alt_port->bridge->dev,
 				  alt_port->hpd_state ?
 				  connector_status_connected :
 				  connector_status_disconnected);
@@ -454,7 +454,7 @@ static int pmic_glink_altmode_probe(struct auxiliary_device *adev,
 		alt_port->index = port;
 		INIT_WORK(&alt_port->work, pmic_glink_altmode_worker);
 
-		alt_port->bridge = drm_dp_hpd_bridge_register(dev, to_of_node(fwnode));
+		alt_port->bridge = devm_drm_dp_hpd_bridge_alloc(dev, to_of_node(fwnode));
 		if (IS_ERR(alt_port->bridge)) {
 			fwnode_handle_put(fwnode);
 			return PTR_ERR(alt_port->bridge);
@@ -510,6 +510,16 @@ static int pmic_glink_altmode_probe(struct auxiliary_device *adev,
 		}
 	}
 
+	for (port = 0; port < ARRAY_SIZE(altmode->ports); port++) {
+		alt_port = &altmode->ports[port];
+		if (!alt_port->bridge)
+			continue;
+
+		ret = devm_drm_dp_hpd_bridge_add(dev, alt_port->bridge);
+		if (ret)
+			return ret;
+	}
+
 	altmode->client = devm_pmic_glink_register_client(dev,
 							  altmode->owner_id,
 							  pmic_glink_altmode_callback,
diff --git a/drivers/soc/xilinx/xlnx_event_manager.c b/drivers/soc/xilinx/xlnx_event_manager.c
index 042553abe1bf..253299e4214d 100644
--- a/drivers/soc/xilinx/xlnx_event_manager.c
+++ b/drivers/soc/xilinx/xlnx_event_manager.c
@@ -77,11 +77,26 @@ struct registered_event_data {
 
 static bool xlnx_is_error_event(const u32 node_id)
 {
-	if (node_id == EVENT_ERROR_PMC_ERR1 ||
-	    node_id == EVENT_ERROR_PMC_ERR2 ||
-	    node_id == EVENT_ERROR_PSM_ERR1 ||
-	    node_id == EVENT_ERROR_PSM_ERR2)
-		return true;
+	u32 pm_family_code, pm_sub_family_code;
+
+	zynqmp_pm_get_family_info(&pm_family_code, &pm_sub_family_code);
+
+	if (pm_sub_family_code == VERSAL_SUB_FAMILY_CODE) {
+		if (node_id == VERSAL_EVENT_ERROR_PMC_ERR1 ||
+		    node_id == VERSAL_EVENT_ERROR_PMC_ERR2 ||
+		    node_id == VERSAL_EVENT_ERROR_PSM_ERR1 ||
+		    node_id == VERSAL_EVENT_ERROR_PSM_ERR2)
+			return true;
+	} else {
+		if (node_id == VERSAL_NET_EVENT_ERROR_PMC_ERR1 ||
+		    node_id == VERSAL_NET_EVENT_ERROR_PMC_ERR2 ||
+		    node_id == VERSAL_NET_EVENT_ERROR_PMC_ERR3 ||
+		    node_id == VERSAL_NET_EVENT_ERROR_PSM_ERR1 ||
+		    node_id == VERSAL_NET_EVENT_ERROR_PSM_ERR2 ||
+		    node_id == VERSAL_NET_EVENT_ERROR_PSM_ERR3 ||
+		    node_id == VERSAL_NET_EVENT_ERROR_PSM_ERR4)
+			return true;
+	}
 
 	return false;
 }
@@ -483,7 +498,7 @@ static void xlnx_call_notify_cb_handler(const u32 *payload)
 
 static void xlnx_get_event_callback_data(u32 *buf)
 {
-	zynqmp_pm_invoke_fn(GET_CALLBACK_DATA, 0, 0, 0, 0, buf);
+	zynqmp_pm_invoke_fn(GET_CALLBACK_DATA, buf, 0);
 }
 
 static irqreturn_t xlnx_event_handler(int irq, void *dev_id)
@@ -656,7 +671,11 @@ static int xlnx_event_manager_probe(struct platform_device *pdev)
 
 	ret = zynqmp_pm_register_sgi(sgi_num, 0);
 	if (ret) {
-		dev_err(&pdev->dev, "SGI %d Registration over TF-A failed with %d\n", sgi_num, ret);
+		if (ret == -EOPNOTSUPP)
+			dev_err(&pdev->dev, "SGI registration not supported by TF-A or Xen\n");
+		else
+			dev_err(&pdev->dev, "SGI %d registration failed, err %d\n", sgi_num, ret);
+
 		xlnx_event_cleanup_sgi(pdev);
 		return ret;
 	}
diff --git a/drivers/soc/xilinx/zynqmp_power.c b/drivers/soc/xilinx/zynqmp_power.c
index 07d735b38b49..965b1143936a 100644
--- a/drivers/soc/xilinx/zynqmp_power.c
+++ b/drivers/soc/xilinx/zynqmp_power.c
@@ -51,7 +51,7 @@ static enum pm_suspend_mode suspend_mode = PM_SUSPEND_MODE_STD;
 
 static void zynqmp_pm_get_callback_data(u32 *buf)
 {
-	zynqmp_pm_invoke_fn(GET_CALLBACK_DATA, 0, 0, 0, 0, buf);
+	zynqmp_pm_invoke_fn(GET_CALLBACK_DATA, buf, 0);
 }
 
 static void suspend_event_callback(const u32 *payload, void *data)
diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c
index 3a99f6dcdfaf..f54bb4dd2d10 100644
--- a/drivers/soundwire/amd_manager.c
+++ b/drivers/soundwire/amd_manager.c
@@ -927,6 +927,14 @@ static int amd_sdw_manager_probe(struct platform_device *pdev)
 	amd_manager->bus.clk_stop_timeout = 200;
 	amd_manager->bus.link_id = amd_manager->instance;
 
+	/*
+	 * Due to BIOS compatibility, the two links are exposed within
+	 * the scope of a single controller. If this changes, the
+	 * controller_id will have to be updated with drv_data
+	 * information.
+	 */
+	amd_manager->bus.controller_id = 0;
+
 	switch (amd_manager->instance) {
 	case ACP_SDW0:
 		amd_manager->num_dout_ports = AMD_SDW0_MAX_TX_PORTS;
@@ -942,13 +950,13 @@ static int amd_sdw_manager_probe(struct platform_device *pdev)
 
 	amd_manager->reg_mask = &sdw_manager_reg_mask_array[amd_manager->instance];
 	params = &amd_manager->bus.params;
-	params->max_dr_freq = AMD_SDW_DEFAULT_CLK_FREQ * 2;
-	params->curr_dr_freq = AMD_SDW_DEFAULT_CLK_FREQ * 2;
+
 	params->col = AMD_SDW_DEFAULT_COLUMNS;
 	params->row = AMD_SDW_DEFAULT_ROWS;
 	prop = &amd_manager->bus.prop;
 	prop->clk_freq = &amd_sdw_freq_tbl[0];
 	prop->mclk_freq = AMD_SDW_BUS_BASE_FREQ;
+	prop->max_clk_freq = AMD_SDW_DEFAULT_CLK_FREQ;
 
 	ret = sdw_bus_master_add(&amd_manager->bus, dev, dev->fwnode);
 	if (ret) {
diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index 41b0d9adf68e..f3fec15c3112 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -22,6 +22,10 @@ static int sdw_get_id(struct sdw_bus *bus)
 		return rc;
 
 	bus->id = rc;
+
+	if (bus->controller_id == -1)
+		bus->controller_id = rc;
+
 	return 0;
 }
 
diff --git a/drivers/soundwire/debugfs.c b/drivers/soundwire/debugfs.c
index d1553cb77187..67abd7e52f09 100644
--- a/drivers/soundwire/debugfs.c
+++ b/drivers/soundwire/debugfs.c
@@ -20,7 +20,7 @@ void sdw_bus_debugfs_init(struct sdw_bus *bus)
 		return;
 
 	/* create the debugfs master-N */
-	snprintf(name, sizeof(name), "master-%d-%d", bus->id, bus->link_id);
+	snprintf(name, sizeof(name), "master-%d-%d", bus->controller_id, bus->link_id);
 	bus->debugfs = debugfs_create_dir(name, sdw_debugfs_root);
 }
 
diff --git a/drivers/soundwire/generic_bandwidth_allocation.c b/drivers/soundwire/generic_bandwidth_allocation.c
index 31162f2b5638..c70a63d009ae 100644
--- a/drivers/soundwire/generic_bandwidth_allocation.c
+++ b/drivers/soundwire/generic_bandwidth_allocation.c
@@ -333,7 +333,7 @@ static int sdw_select_row_col(struct sdw_bus *bus, int clk_freq)
  */
 static int sdw_compute_bus_params(struct sdw_bus *bus)
 {
-	unsigned int max_dr_freq, curr_dr_freq = 0;
+	unsigned int curr_dr_freq = 0;
 	struct sdw_master_prop *mstr_prop = &bus->prop;
 	int i, clk_values, ret;
 	bool is_gear = false;
@@ -351,14 +351,12 @@ static int sdw_compute_bus_params(struct sdw_bus *bus)
 		clk_buf = NULL;
 	}
 
-	max_dr_freq = mstr_prop->max_clk_freq * SDW_DOUBLE_RATE_FACTOR;
-
 	for (i = 0; i < clk_values; i++) {
 		if (!clk_buf)
-			curr_dr_freq = max_dr_freq;
+			curr_dr_freq = bus->params.max_dr_freq;
 		else
 			curr_dr_freq = (is_gear) ?
-				(max_dr_freq >>  clk_buf[i]) :
+				(bus->params.max_dr_freq >>  clk_buf[i]) :
 				clk_buf[i] * SDW_DOUBLE_RATE_FACTOR;
 
 		if (curr_dr_freq <= bus->params.bandwidth)
diff --git a/drivers/soundwire/intel_auxdevice.c b/drivers/soundwire/intel_auxdevice.c
index 7f15e3549e53..93698532deac 100644
--- a/drivers/soundwire/intel_auxdevice.c
+++ b/drivers/soundwire/intel_auxdevice.c
@@ -234,6 +234,9 @@ static int intel_link_probe(struct auxiliary_device *auxdev,
 	cdns->instance = sdw->instance;
 	cdns->msg_count = 0;
 
+	/* single controller for all SoundWire links */
+	bus->controller_id = 0;
+
 	bus->link_id = auxdev->id;
 	bus->clk_stop_timeout = 1;
 
diff --git a/drivers/soundwire/master.c b/drivers/soundwire/master.c
index 9b05c9e25ebe..51abedbbaa66 100644
--- a/drivers/soundwire/master.c
+++ b/drivers/soundwire/master.c
@@ -145,7 +145,7 @@ int sdw_master_device_add(struct sdw_bus *bus, struct device *parent,
 	md->dev.fwnode = fwnode;
 	md->dev.dma_mask = parent->dma_mask;
 
-	dev_set_name(&md->dev, "sdw-master-%d", bus->id);
+	dev_set_name(&md->dev, "sdw-master-%d-%d", bus->controller_id, bus->link_id);
 
 	ret = device_register(&md->dev);
 	if (ret) {
diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c
index 8076d40407d4..3c4d6debab1f 100644
--- a/drivers/soundwire/qcom.c
+++ b/drivers/soundwire/qcom.c
@@ -1157,9 +1157,20 @@ static int qcom_swrm_stream_alloc_ports(struct qcom_swrm_ctrl *ctrl,
 	struct sdw_port_runtime *p_rt;
 	struct sdw_slave *slave;
 	unsigned long *port_mask;
-	int i, maxport, pn, nports = 0, ret = 0;
+	int maxport, pn, nports = 0, ret = 0;
 	unsigned int m_port;
 
+	if (direction == SNDRV_PCM_STREAM_CAPTURE)
+		sconfig.direction = SDW_DATA_DIR_TX;
+	else
+		sconfig.direction = SDW_DATA_DIR_RX;
+
+	/* hw parameters wil be ignored as we only support PDM */
+	sconfig.ch_count = 1;
+	sconfig.frame_rate = params_rate(params);
+	sconfig.type = stream->type;
+	sconfig.bps = 1;
+
 	mutex_lock(&ctrl->port_lock);
 	list_for_each_entry(m_rt, &stream->master_list, stream_node) {
 		if (m_rt->direction == SDW_DATA_DIR_RX) {
@@ -1183,7 +1194,7 @@ static int qcom_swrm_stream_alloc_ports(struct qcom_swrm_ctrl *ctrl,
 				if (pn > maxport) {
 					dev_err(ctrl->dev, "All ports busy\n");
 					ret = -EBUSY;
-					goto err;
+					goto out;
 				}
 				set_bit(pn, port_mask);
 				pconfig[nports].num = pn;
@@ -1193,24 +1204,9 @@ static int qcom_swrm_stream_alloc_ports(struct qcom_swrm_ctrl *ctrl,
 		}
 	}
 
-	if (direction == SNDRV_PCM_STREAM_CAPTURE)
-		sconfig.direction = SDW_DATA_DIR_TX;
-	else
-		sconfig.direction = SDW_DATA_DIR_RX;
-
-	/* hw parameters wil be ignored as we only support PDM */
-	sconfig.ch_count = 1;
-	sconfig.frame_rate = params_rate(params);
-	sconfig.type = stream->type;
-	sconfig.bps = 1;
 	sdw_stream_add_master(&ctrl->bus, &sconfig, pconfig,
 			      nports, stream);
-err:
-	if (ret) {
-		for (i = 0; i < nports; i++)
-			clear_bit(pconfig[i].num, port_mask);
-	}
-
+out:
 	mutex_unlock(&ctrl->port_lock);
 
 	return ret;
@@ -1593,6 +1589,13 @@ static int qcom_swrm_probe(struct platform_device *pdev)
 		}
 	}
 
+	ctrl->bus.controller_id = -1;
+
+	if (ctrl->version > SWRM_VERSION_1_3_0) {
+		ctrl->reg_read(ctrl, SWRM_COMP_MASTER_ID, &val);
+		ctrl->bus.controller_id = val;
+	}
+
 	ret = sdw_bus_master_add(&ctrl->bus, dev, dev->fwnode);
 	if (ret) {
 		dev_err(dev, "Failed to register Soundwire controller (%d)\n",
diff --git a/drivers/soundwire/slave.c b/drivers/soundwire/slave.c
index c1c1a2ac293a..060c2982e26b 100644
--- a/drivers/soundwire/slave.c
+++ b/drivers/soundwire/slave.c
@@ -39,14 +39,14 @@ int sdw_slave_add(struct sdw_bus *bus,
 	slave->dev.fwnode = fwnode;
 
 	if (id->unique_id == SDW_IGNORED_UNIQUE_ID) {
-		/* name shall be sdw:link:mfg:part:class */
-		dev_set_name(&slave->dev, "sdw:%01x:%04x:%04x:%02x",
-			     bus->link_id, id->mfg_id, id->part_id,
+		/* name shall be sdw:ctrl:link:mfg:part:class */
+		dev_set_name(&slave->dev, "sdw:%01x:%01x:%04x:%04x:%02x",
+			     bus->controller_id, bus->link_id, id->mfg_id, id->part_id,
 			     id->class_id);
 	} else {
-		/* name shall be sdw:link:mfg:part:class:unique */
-		dev_set_name(&slave->dev, "sdw:%01x:%04x:%04x:%02x:%01x",
-			     bus->link_id, id->mfg_id, id->part_id,
+		/* name shall be sdw:ctrl:link:mfg:part:class:unique */
+		dev_set_name(&slave->dev, "sdw:%01x:%01x:%04x:%04x:%02x:%01x",
+			     bus->controller_id, bus->link_id, id->mfg_id, id->part_id,
 			     id->class_id, id->unique_id);
 	}
 
diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
index f048b3d55b2e..f9c0adc0738d 100644
--- a/drivers/soundwire/stream.c
+++ b/drivers/soundwire/stream.c
@@ -898,7 +898,7 @@ static struct sdw_port_runtime *sdw_port_alloc(struct list_head *port_list)
 }
 
 static int sdw_port_config(struct sdw_port_runtime *p_rt,
-			   struct sdw_port_config *port_config,
+			   const struct sdw_port_config *port_config,
 			   int port_index)
 {
 	p_rt->ch_mask = port_config[port_index].ch_mask;
@@ -971,7 +971,7 @@ static int sdw_slave_port_is_valid_range(struct device *dev, int num)
 
 static int sdw_slave_port_config(struct sdw_slave *slave,
 				 struct sdw_slave_runtime *s_rt,
-				 struct sdw_port_config *port_config)
+				 const struct sdw_port_config *port_config)
 {
 	struct sdw_port_runtime *p_rt;
 	int ret;
@@ -1027,7 +1027,7 @@ static int sdw_master_port_alloc(struct sdw_master_runtime *m_rt,
 }
 
 static int sdw_master_port_config(struct sdw_master_runtime *m_rt,
-				  struct sdw_port_config *port_config)
+				  const struct sdw_port_config *port_config)
 {
 	struct sdw_port_runtime *p_rt;
 	int ret;
@@ -1862,7 +1862,7 @@ EXPORT_SYMBOL(sdw_release_stream);
  */
 int sdw_stream_add_master(struct sdw_bus *bus,
 			  struct sdw_stream_config *stream_config,
-			  struct sdw_port_config *port_config,
+			  const struct sdw_port_config *port_config,
 			  unsigned int num_ports,
 			  struct sdw_stream_runtime *stream)
 {
@@ -1982,7 +1982,7 @@ EXPORT_SYMBOL(sdw_stream_remove_master);
  */
 int sdw_stream_add_slave(struct sdw_slave *slave,
 			 struct sdw_stream_config *stream_config,
-			 struct sdw_port_config *port_config,
+			 const struct sdw_port_config *port_config,
 			 unsigned int num_ports,
 			 struct sdw_stream_runtime *stream)
 {
diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c
index d96222e6d7d2..cfdaa5eaec76 100644
--- a/drivers/spi/spi-bcm-qspi.c
+++ b/drivers/spi/spi-bcm-qspi.c
@@ -19,7 +19,7 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/spi/spi.h>
-#include <linux/spi/spi-mem.h>
+#include <linux/mtd/spi-nor.h>
 #include <linux/sysfs.h>
 #include <linux/types.h>
 #include "spi-bcm-qspi.h"
@@ -1221,7 +1221,7 @@ static int bcm_qspi_exec_mem_op(struct spi_mem *mem,
 
 	/* non-aligned and very short transfers are handled by MSPI */
 	if (!IS_ALIGNED((uintptr_t)addr, 4) || !IS_ALIGNED((uintptr_t)buf, 4) ||
-	    len < 4)
+	    len < 4 || op->cmd.opcode == SPINOR_OP_RDSFDP)
 		mspi_read = true;
 
 	if (!has_bspi(qspi) || mspi_read)
diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index f94e0d370d46..1a8d03958dff 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -1927,24 +1927,18 @@ static void cqspi_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 }
 
-static int cqspi_suspend(struct device *dev)
+static int cqspi_runtime_suspend(struct device *dev)
 {
 	struct cqspi_st *cqspi = dev_get_drvdata(dev);
-	struct spi_controller *host = dev_get_drvdata(dev);
-	int ret;
 
-	ret = spi_controller_suspend(host);
 	cqspi_controller_enable(cqspi, 0);
-
 	clk_disable_unprepare(cqspi->clk);
-
-	return ret;
+	return 0;
 }
 
-static int cqspi_resume(struct device *dev)
+static int cqspi_runtime_resume(struct device *dev)
 {
 	struct cqspi_st *cqspi = dev_get_drvdata(dev);
-	struct spi_controller *host = dev_get_drvdata(dev);
 
 	clk_prepare_enable(cqspi->clk);
 	cqspi_wait_idle(cqspi);
@@ -1952,12 +1946,27 @@ static int cqspi_resume(struct device *dev)
 
 	cqspi->current_cs = -1;
 	cqspi->sclk = 0;
+	return 0;
+}
+
+static int cqspi_suspend(struct device *dev)
+{
+	struct cqspi_st *cqspi = dev_get_drvdata(dev);
+
+	return spi_controller_suspend(cqspi->host);
+}
 
-	return spi_controller_resume(host);
+static int cqspi_resume(struct device *dev)
+{
+	struct cqspi_st *cqspi = dev_get_drvdata(dev);
+
+	return spi_controller_resume(cqspi->host);
 }
 
-static DEFINE_RUNTIME_DEV_PM_OPS(cqspi_dev_pm_ops, cqspi_suspend,
-				 cqspi_resume, NULL);
+static const struct dev_pm_ops cqspi_dev_pm_ops = {
+	RUNTIME_PM_OPS(cqspi_runtime_suspend, cqspi_runtime_resume, NULL)
+	SYSTEM_SLEEP_PM_OPS(cqspi_suspend, cqspi_resume)
+};
 
 static const struct cqspi_driver_platdata cdns_qspi = {
 	.quirks = CQSPI_DISABLE_DAC_MODE,
diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c
index a50eb4db79de..e5140532071d 100644
--- a/drivers/spi/spi-cadence.c
+++ b/drivers/spi/spi-cadence.c
@@ -317,6 +317,15 @@ static void cdns_spi_process_fifo(struct cdns_spi *xspi, int ntx, int nrx)
 	xspi->rx_bytes -= nrx;
 
 	while (ntx || nrx) {
+		if (nrx) {
+			u8 data = cdns_spi_read(xspi, CDNS_SPI_RXD);
+
+			if (xspi->rxbuf)
+				*xspi->rxbuf++ = data;
+
+			nrx--;
+		}
+
 		if (ntx) {
 			if (xspi->txbuf)
 				cdns_spi_write(xspi, CDNS_SPI_TXD, *xspi->txbuf++);
@@ -326,14 +335,6 @@ static void cdns_spi_process_fifo(struct cdns_spi *xspi, int ntx, int nrx)
 			ntx--;
 		}
 
-		if (nrx) {
-			u8 data = cdns_spi_read(xspi, CDNS_SPI_RXD);
-
-			if (xspi->rxbuf)
-				*xspi->rxbuf++ = data;
-
-			nrx--;
-		}
 	}
 }
 
diff --git a/drivers/spi/spi-coldfire-qspi.c b/drivers/spi/spi-coldfire-qspi.c
index f0b630fe16c3..b341b6908df0 100644
--- a/drivers/spi/spi-coldfire-qspi.c
+++ b/drivers/spi/spi-coldfire-qspi.c
@@ -441,7 +441,6 @@ static void mcfqspi_remove(struct platform_device *pdev)
 	mcfqspi_wr_qmr(mcfqspi, MCFQSPI_QMR_MSTR);
 
 	mcfqspi_cs_teardown(mcfqspi);
-	clk_disable_unprepare(mcfqspi->clk);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/spi/spi-cs42l43.c b/drivers/spi/spi-cs42l43.c
index f13073e12593..adf19e8c4c8a 100644
--- a/drivers/spi/spi-cs42l43.c
+++ b/drivers/spi/spi-cs42l43.c
@@ -148,8 +148,7 @@ static void cs42l43_set_cs(struct spi_device *spi, bool is_high)
 {
 	struct cs42l43_spi *priv = spi_controller_get_devdata(spi->controller);
 
-	if (spi_get_chipselect(spi, 0) == 0)
-		regmap_write(priv->regmap, CS42L43_SPI_CONFIG2, !is_high);
+	regmap_write(priv->regmap, CS42L43_SPI_CONFIG2, !is_high);
 }
 
 static int cs42l43_prepare_message(struct spi_controller *ctlr, struct spi_message *msg)
@@ -244,7 +243,10 @@ static int cs42l43_spi_probe(struct platform_device *pdev)
 	priv->ctlr->use_gpio_descriptors = true;
 	priv->ctlr->auto_runtime_pm = true;
 
-	devm_pm_runtime_enable(priv->dev);
+	ret = devm_pm_runtime_enable(priv->dev);
+	if (ret)
+		return ret;
+
 	pm_runtime_idle(priv->dev);
 
 	regmap_write(priv->regmap, CS42L43_TRAN_CONFIG6, CS42L43_FIFO_SIZE - 1);
diff --git a/drivers/spi/spi-hisi-sfc-v3xx.c b/drivers/spi/spi-hisi-sfc-v3xx.c
index 9d22018f7985..1301d14483d4 100644
--- a/drivers/spi/spi-hisi-sfc-v3xx.c
+++ b/drivers/spi/spi-hisi-sfc-v3xx.c
@@ -377,6 +377,11 @@ static const struct spi_controller_mem_ops hisi_sfc_v3xx_mem_ops = {
 static irqreturn_t hisi_sfc_v3xx_isr(int irq, void *data)
 {
 	struct hisi_sfc_v3xx_host *host = data;
+	u32 reg;
+
+	reg = readl(host->regbase + HISI_SFC_V3XX_INT_STAT);
+	if (!reg)
+		return IRQ_NONE;
 
 	hisi_sfc_v3xx_disable_int(host);
 
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 272bc871a848..833a1bb7a914 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -2,6 +2,7 @@
 // Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved.
 // Copyright (C) 2008 Juergen Beisert
 
+#include <linux/bits.h>
 #include <linux/clk.h>
 #include <linux/completion.h>
 #include <linux/delay.h>
@@ -660,15 +661,15 @@ static int mx51_ecspi_prepare_transfer(struct spi_imx_data *spi_imx,
 			<< MX51_ECSPI_CTRL_BL_OFFSET;
 	else {
 		if (spi_imx->usedma) {
-			ctrl |= (spi_imx->bits_per_word *
-				spi_imx_bytes_per_word(spi_imx->bits_per_word) - 1)
+			ctrl |= (spi_imx->bits_per_word - 1)
 				<< MX51_ECSPI_CTRL_BL_OFFSET;
 		} else {
 			if (spi_imx->count >= MX51_ECSPI_CTRL_MAX_BURST)
-				ctrl |= (MX51_ECSPI_CTRL_MAX_BURST - 1)
+				ctrl |= (MX51_ECSPI_CTRL_MAX_BURST * BITS_PER_BYTE - 1)
 						<< MX51_ECSPI_CTRL_BL_OFFSET;
 			else
-				ctrl |= (spi_imx->count * spi_imx->bits_per_word - 1)
+				ctrl |= spi_imx->count / DIV_ROUND_UP(spi_imx->bits_per_word,
+						BITS_PER_BYTE) * spi_imx->bits_per_word
 						<< MX51_ECSPI_CTRL_BL_OFFSET;
 		}
 	}
@@ -1344,7 +1345,7 @@ static int spi_imx_sdma_init(struct device *dev, struct spi_imx_data *spi_imx,
 	controller->dma_tx = dma_request_chan(dev, "tx");
 	if (IS_ERR(controller->dma_tx)) {
 		ret = PTR_ERR(controller->dma_tx);
-		dev_dbg(dev, "can't get the TX DMA channel, error %d!\n", ret);
+		dev_err_probe(dev, ret, "can't get the TX DMA channel!\n");
 		controller->dma_tx = NULL;
 		goto err;
 	}
@@ -1353,7 +1354,7 @@ static int spi_imx_sdma_init(struct device *dev, struct spi_imx_data *spi_imx,
 	controller->dma_rx = dma_request_chan(dev, "rx");
 	if (IS_ERR(controller->dma_rx)) {
 		ret = PTR_ERR(controller->dma_rx);
-		dev_dbg(dev, "can't get the RX DMA channel, error %d\n", ret);
+		dev_err_probe(dev, ret, "can't get the RX DMA channel!\n");
 		controller->dma_rx = NULL;
 		goto err;
 	}
diff --git a/drivers/spi/spi-intel-pci.c b/drivers/spi/spi-intel-pci.c
index 57d767a68e7b..4337ca51d7aa 100644
--- a/drivers/spi/spi-intel-pci.c
+++ b/drivers/spi/spi-intel-pci.c
@@ -76,6 +76,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0x7a24), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0x7aa4), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0x7e23), (unsigned long)&cnl_info },
+	{ PCI_VDEVICE(INTEL, 0x7f24), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0x9d24), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0x9da4), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0xa0a4), (unsigned long)&cnl_info },
@@ -84,7 +85,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0xa2a4), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0xa324), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0xa3a4), (unsigned long)&cnl_info },
-	{ PCI_VDEVICE(INTEL, 0xae23), (unsigned long)&cnl_info },
+	{ PCI_VDEVICE(INTEL, 0xa823), (unsigned long)&cnl_info },
 	{ },
 };
 MODULE_DEVICE_TABLE(pci, intel_spi_pci_ids);
diff --git a/drivers/spi/spi-mxs.c b/drivers/spi/spi-mxs.c
index 1bf080339b5a..88cbe4f00cc3 100644
--- a/drivers/spi/spi-mxs.c
+++ b/drivers/spi/spi-mxs.c
@@ -39,6 +39,7 @@
 #include <linux/spi/spi.h>
 #include <linux/spi/mxs-spi.h>
 #include <trace/events/spi.h>
+#include <linux/dma/mxs-dma.h>
 
 #define DRIVER_NAME		"mxs-spi"
 
@@ -252,7 +253,7 @@ static int mxs_spi_txrx_dma(struct mxs_spi *spi,
 		desc = dmaengine_prep_slave_sg(ssp->dmach,
 				&dma_xfer[sg_count].sg, 1,
 				(flags & TXRX_WRITE) ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM,
-				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+				DMA_PREP_INTERRUPT | MXS_DMA_CTRL_WAIT4END);
 
 		if (!desc) {
 			dev_err(ssp->dev,
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index a0c9fea908f5..ddf1c684bcc7 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -53,8 +53,6 @@
 
 /* per-register bitmasks: */
 #define OMAP2_MCSPI_IRQSTATUS_EOW	BIT(17)
-#define OMAP2_MCSPI_IRQSTATUS_TX0_EMPTY    BIT(0)
-#define OMAP2_MCSPI_IRQSTATUS_RX0_FULL    BIT(2)
 
 #define OMAP2_MCSPI_MODULCTRL_SINGLE	BIT(0)
 #define OMAP2_MCSPI_MODULCTRL_MS	BIT(2)
@@ -293,7 +291,7 @@ static void omap2_mcspi_set_mode(struct spi_controller *ctlr)
 }
 
 static void omap2_mcspi_set_fifo(const struct spi_device *spi,
-				struct spi_transfer *t, int enable, int dma_enabled)
+				struct spi_transfer *t, int enable)
 {
 	struct spi_controller *ctlr = spi->controller;
 	struct omap2_mcspi_cs *cs = spi->controller_state;
@@ -314,28 +312,20 @@ static void omap2_mcspi_set_fifo(const struct spi_device *spi,
 			max_fifo_depth = OMAP2_MCSPI_MAX_FIFODEPTH / 2;
 		else
 			max_fifo_depth = OMAP2_MCSPI_MAX_FIFODEPTH;
-		if (dma_enabled)
-			wcnt = t->len / bytes_per_word;
-		else
-			wcnt = 0;
+
+		wcnt = t->len / bytes_per_word;
 		if (wcnt > OMAP2_MCSPI_MAX_FIFOWCNT)
 			goto disable_fifo;
 
 		xferlevel = wcnt << 16;
 		if (t->rx_buf != NULL) {
 			chconf |= OMAP2_MCSPI_CHCONF_FFER;
-			if (dma_enabled)
-				xferlevel |= (bytes_per_word - 1) << 8;
-			else
-				xferlevel |= (max_fifo_depth - 1) << 8;
+			xferlevel |= (bytes_per_word - 1) << 8;
 		}
 
 		if (t->tx_buf != NULL) {
 			chconf |= OMAP2_MCSPI_CHCONF_FFET;
-			if (dma_enabled)
-				xferlevel |= bytes_per_word - 1;
-			else
-				xferlevel |= (max_fifo_depth - 1);
+			xferlevel |= bytes_per_word - 1;
 		}
 
 		mcspi_write_reg(ctlr, OMAP2_MCSPI_XFERLEVEL, xferlevel);
@@ -892,113 +882,6 @@ out:
 	return count - c;
 }
 
-static unsigned
-omap2_mcspi_txrx_piofifo(struct spi_device *spi, struct spi_transfer *xfer)
-{
-	struct omap2_mcspi_cs	*cs = spi->controller_state;
-	struct omap2_mcspi    *mcspi;
-	unsigned int		count, c;
-	unsigned int		iter, cwc;
-	int last_request;
-	void __iomem		*base = cs->base;
-	void __iomem		*tx_reg;
-	void __iomem		*rx_reg;
-	void __iomem		*chstat_reg;
-	void __iomem        *irqstat_reg;
-	int			word_len, bytes_per_word;
-	u8		*rx;
-	const u8	*tx;
-
-	mcspi = spi_controller_get_devdata(spi->controller);
-	count = xfer->len;
-	c = count;
-	word_len = cs->word_len;
-	bytes_per_word = mcspi_bytes_per_word(word_len);
-
-	/*
-	 * We store the pre-calculated register addresses on stack to speed
-	 * up the transfer loop.
-	 */
-	tx_reg		= base + OMAP2_MCSPI_TX0;
-	rx_reg		= base + OMAP2_MCSPI_RX0;
-	chstat_reg	= base + OMAP2_MCSPI_CHSTAT0;
-	irqstat_reg    = base + OMAP2_MCSPI_IRQSTATUS;
-
-	if (c < (word_len >> 3))
-		return 0;
-
-	rx = xfer->rx_buf;
-	tx = xfer->tx_buf;
-
-	do {
-		/* calculate number of words in current iteration */
-		cwc = min((unsigned int)mcspi->fifo_depth / bytes_per_word,
-			  c / bytes_per_word);
-		last_request = cwc != (mcspi->fifo_depth / bytes_per_word);
-		if (tx) {
-			if (mcspi_wait_for_reg_bit(irqstat_reg,
-						   OMAP2_MCSPI_IRQSTATUS_TX0_EMPTY) < 0) {
-				dev_err(&spi->dev, "TX Empty timed out\n");
-				goto out;
-			}
-			writel_relaxed(OMAP2_MCSPI_IRQSTATUS_TX0_EMPTY, irqstat_reg);
-
-			for (iter = 0; iter < cwc; iter++, tx += bytes_per_word) {
-				if (bytes_per_word == 1)
-					writel_relaxed(*tx, tx_reg);
-				else if (bytes_per_word == 2)
-					writel_relaxed(*((u16 *)tx), tx_reg);
-				else if (bytes_per_word == 4)
-					writel_relaxed(*((u32 *)tx), tx_reg);
-			}
-		}
-
-		if (rx) {
-			if (!last_request &&
-			    mcspi_wait_for_reg_bit(irqstat_reg,
-						   OMAP2_MCSPI_IRQSTATUS_RX0_FULL) < 0) {
-				dev_err(&spi->dev, "RX_FULL timed out\n");
-				goto out;
-			}
-			writel_relaxed(OMAP2_MCSPI_IRQSTATUS_RX0_FULL, irqstat_reg);
-
-			for (iter = 0; iter < cwc; iter++, rx += bytes_per_word) {
-				if (last_request &&
-				    mcspi_wait_for_reg_bit(chstat_reg,
-							   OMAP2_MCSPI_CHSTAT_RXS) < 0) {
-					dev_err(&spi->dev, "RXS timed out\n");
-					goto out;
-				}
-				if (bytes_per_word == 1)
-					*rx = readl_relaxed(rx_reg);
-				else if (bytes_per_word == 2)
-					*((u16 *)rx) = readl_relaxed(rx_reg);
-				else if (bytes_per_word == 4)
-					*((u32 *)rx) = readl_relaxed(rx_reg);
-			}
-		}
-
-		if (last_request) {
-			if (mcspi_wait_for_reg_bit(chstat_reg,
-						   OMAP2_MCSPI_CHSTAT_EOT) < 0) {
-				dev_err(&spi->dev, "EOT timed out\n");
-				goto out;
-			}
-			if (mcspi_wait_for_reg_bit(chstat_reg,
-						   OMAP2_MCSPI_CHSTAT_TXFFE) < 0) {
-				dev_err(&spi->dev, "TXFFE timed out\n");
-				goto out;
-			}
-			omap2_mcspi_set_enable(spi, 0);
-		}
-		c -= cwc * bytes_per_word;
-	} while (c >= bytes_per_word);
-
-out:
-	omap2_mcspi_set_enable(spi, 1);
-	return count - c;
-}
-
 static u32 omap2_mcspi_calc_divisor(u32 speed_hz, u32 ref_clk_hz)
 {
 	u32 div;
@@ -1323,9 +1206,7 @@ static int omap2_mcspi_transfer_one(struct spi_controller *ctlr,
 		if ((mcspi_dma->dma_rx && mcspi_dma->dma_tx) &&
 		    ctlr->cur_msg_mapped &&
 		    ctlr->can_dma(ctlr, spi, t))
-			omap2_mcspi_set_fifo(spi, t, 1, 1);
-		else if (t->len > OMAP2_MCSPI_MAX_FIFODEPTH)
-			omap2_mcspi_set_fifo(spi, t, 1, 0);
+			omap2_mcspi_set_fifo(spi, t, 1);
 
 		omap2_mcspi_set_enable(spi, 1);
 
@@ -1338,8 +1219,6 @@ static int omap2_mcspi_transfer_one(struct spi_controller *ctlr,
 		    ctlr->cur_msg_mapped &&
 		    ctlr->can_dma(ctlr, spi, t))
 			count = omap2_mcspi_txrx_dma(spi, t);
-		else if (mcspi->fifo_depth > 0)
-			count = omap2_mcspi_txrx_piofifo(spi, t);
 		else
 			count = omap2_mcspi_txrx_pio(spi, t);
 
@@ -1352,7 +1231,7 @@ static int omap2_mcspi_transfer_one(struct spi_controller *ctlr,
 	omap2_mcspi_set_enable(spi, 0);
 
 	if (mcspi->fifo_depth > 0)
-		omap2_mcspi_set_fifo(spi, t, 0, 0);
+		omap2_mcspi_set_fifo(spi, t, 0);
 
 out:
 	/* Restore defaults if they were overriden */
@@ -1375,7 +1254,7 @@ out:
 		omap2_mcspi_set_cs(spi, !(spi->mode & SPI_CS_HIGH));
 
 	if (mcspi->fifo_depth > 0 && t)
-		omap2_mcspi_set_fifo(spi, t, 0, 0);
+		omap2_mcspi_set_fifo(spi, t, 0);
 
 	return status;
 }
diff --git a/drivers/spi/spi-ppc4xx.c b/drivers/spi/spi-ppc4xx.c
index 03aab661be9d..82d6264841fc 100644
--- a/drivers/spi/spi-ppc4xx.c
+++ b/drivers/spi/spi-ppc4xx.c
@@ -25,11 +25,13 @@
 #include <linux/slab.h>
 #include <linux/errno.h>
 #include <linux/wait.h>
+#include <linux/platform_device.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
+#include <linux/platform_device.h>
 
 #include <linux/spi/spi.h>
 #include <linux/spi/spi_bitbang.h>
@@ -166,10 +168,8 @@ static int spi_ppc4xx_setupxfer(struct spi_device *spi, struct spi_transfer *t)
 	int scr;
 	u8 cdm = 0;
 	u32 speed;
-	u8 bits_per_word;
 
 	/* Start with the generic configuration for this device. */
-	bits_per_word = spi->bits_per_word;
 	speed = spi->max_speed_hz;
 
 	/*
@@ -177,9 +177,6 @@ static int spi_ppc4xx_setupxfer(struct spi_device *spi, struct spi_transfer *t)
 	 * the transfer to overwrite the generic configuration with zeros.
 	 */
 	if (t) {
-		if (t->bits_per_word)
-			bits_per_word = t->bits_per_word;
-
 		if (t->speed_hz)
 			speed = min(t->speed_hz, spi->max_speed_hz);
 	}
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index cfc3b1ddbd22..6f12e4fb2e2e 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -136,14 +136,14 @@ struct sh_msiof_spi_priv {
 
 /* SIFCTR */
 #define SIFCTR_TFWM_MASK	GENMASK(31, 29)	/* Transmit FIFO Watermark */
-#define SIFCTR_TFWM_64		(0 << 29)	/*  Transfer Request when 64 empty stages */
-#define SIFCTR_TFWM_32		(1 << 29)	/*  Transfer Request when 32 empty stages */
-#define SIFCTR_TFWM_24		(2 << 29)	/*  Transfer Request when 24 empty stages */
-#define SIFCTR_TFWM_16		(3 << 29)	/*  Transfer Request when 16 empty stages */
-#define SIFCTR_TFWM_12		(4 << 29)	/*  Transfer Request when 12 empty stages */
-#define SIFCTR_TFWM_8		(5 << 29)	/*  Transfer Request when 8 empty stages */
-#define SIFCTR_TFWM_4		(6 << 29)	/*  Transfer Request when 4 empty stages */
-#define SIFCTR_TFWM_1		(7 << 29)	/*  Transfer Request when 1 empty stage */
+#define SIFCTR_TFWM_64		(0UL << 29)	/*  Transfer Request when 64 empty stages */
+#define SIFCTR_TFWM_32		(1UL << 29)	/*  Transfer Request when 32 empty stages */
+#define SIFCTR_TFWM_24		(2UL << 29)	/*  Transfer Request when 24 empty stages */
+#define SIFCTR_TFWM_16		(3UL << 29)	/*  Transfer Request when 16 empty stages */
+#define SIFCTR_TFWM_12		(4UL << 29)	/*  Transfer Request when 12 empty stages */
+#define SIFCTR_TFWM_8		(5UL << 29)	/*  Transfer Request when 8 empty stages */
+#define SIFCTR_TFWM_4		(6UL << 29)	/*  Transfer Request when 4 empty stages */
+#define SIFCTR_TFWM_1		(7UL << 29)	/*  Transfer Request when 1 empty stage */
 #define SIFCTR_TFUA_MASK	GENMASK(26, 20) /* Transmit FIFO Usable Area */
 #define SIFCTR_TFUA_SHIFT	20
 #define SIFCTR_TFUA(i)		((i) << SIFCTR_TFUA_SHIFT)
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 7477a11e12be..f2170f4b5077 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1717,6 +1717,10 @@ static int __spi_pump_transfer_message(struct spi_controller *ctlr,
 			pm_runtime_put_noidle(ctlr->dev.parent);
 			dev_err(&ctlr->dev, "Failed to power device: %d\n",
 				ret);
+
+			msg->status = ret;
+			spi_finalize_current_message(ctlr);
+
 			return ret;
 		}
 	}
diff --git a/drivers/spmi/Makefile b/drivers/spmi/Makefile
index 9d974424c8c1..7f152167bb05 100644
--- a/drivers/spmi/Makefile
+++ b/drivers/spmi/Makefile
@@ -2,7 +2,7 @@
 #
 # Makefile for kernel SPMI framework.
 #
-obj-$(CONFIG_SPMI)	+= spmi.o
+obj-$(CONFIG_SPMI)	+= spmi.o spmi-devres.o
 
 obj-$(CONFIG_SPMI_HISI3670)	+= hisi-spmi-controller.o
 obj-$(CONFIG_SPMI_MSM_PMIC_ARB)	+= spmi-pmic-arb.o
diff --git a/drivers/spmi/hisi-spmi-controller.c b/drivers/spmi/hisi-spmi-controller.c
index 9cbd473487cb..674a350cc676 100644
--- a/drivers/spmi/hisi-spmi-controller.c
+++ b/drivers/spmi/hisi-spmi-controller.c
@@ -267,10 +267,10 @@ static int spmi_controller_probe(struct platform_device *pdev)
 	struct resource *iores;
 	int ret;
 
-	ctrl = spmi_controller_alloc(&pdev->dev, sizeof(*spmi_controller));
-	if (!ctrl) {
+	ctrl = devm_spmi_controller_alloc(&pdev->dev, sizeof(*spmi_controller));
+	if (IS_ERR(ctrl)) {
 		dev_err(&pdev->dev, "can not allocate spmi_controller data\n");
-		return -ENOMEM;
+		return PTR_ERR(ctrl);
 	}
 	spmi_controller = spmi_controller_get_drvdata(ctrl);
 	spmi_controller->controller = ctrl;
@@ -278,24 +278,21 @@ static int spmi_controller_probe(struct platform_device *pdev)
 	iores = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!iores) {
 		dev_err(&pdev->dev, "can not get resource!\n");
-		ret = -EINVAL;
-		goto err_put_controller;
+		return -EINVAL;
 	}
 
 	spmi_controller->base = devm_ioremap(&pdev->dev, iores->start,
 					     resource_size(iores));
 	if (!spmi_controller->base) {
 		dev_err(&pdev->dev, "can not remap base addr!\n");
-		ret = -EADDRNOTAVAIL;
-		goto err_put_controller;
+		return -EADDRNOTAVAIL;
 	}
 
 	ret = of_property_read_u32(pdev->dev.of_node, "hisilicon,spmi-channel",
 				   &spmi_controller->channel);
 	if (ret) {
 		dev_err(&pdev->dev, "can not get channel\n");
-		ret = -ENODEV;
-		goto err_put_controller;
+		return -ENODEV;
 	}
 
 	platform_set_drvdata(pdev, spmi_controller);
@@ -311,25 +308,13 @@ static int spmi_controller_probe(struct platform_device *pdev)
 	ctrl->read_cmd = spmi_read_cmd;
 	ctrl->write_cmd = spmi_write_cmd;
 
-	ret = spmi_controller_add(ctrl);
+	ret = devm_spmi_controller_add(&pdev->dev, ctrl);
 	if (ret) {
 		dev_err(&pdev->dev, "spmi_controller_add failed with error %d!\n", ret);
-		goto err_put_controller;
+		return ret;
 	}
 
 	return 0;
-
-err_put_controller:
-	spmi_controller_put(ctrl);
-	return ret;
-}
-
-static void spmi_del_controller(struct platform_device *pdev)
-{
-	struct spmi_controller *ctrl = platform_get_drvdata(pdev);
-
-	spmi_controller_remove(ctrl);
-	spmi_controller_put(ctrl);
 }
 
 static const struct of_device_id spmi_controller_match_table[] = {
@@ -342,7 +327,6 @@ MODULE_DEVICE_TABLE(of, spmi_controller_match_table);
 
 static struct platform_driver spmi_controller_driver = {
 	.probe		= spmi_controller_probe,
-	.remove_new	= spmi_del_controller,
 	.driver		= {
 		.name	= "hisi_spmi_controller",
 		.of_match_table = spmi_controller_match_table,
diff --git a/drivers/spmi/spmi-devres.c b/drivers/spmi/spmi-devres.c
new file mode 100644
index 000000000000..62c4b3f24d06
--- /dev/null
+++ b/drivers/spmi/spmi-devres.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2023 Google LLC.
+ */
+
+#include <linux/device.h>
+#include <linux/spmi.h>
+
+static void devm_spmi_controller_release(struct device *parent, void *res)
+{
+	spmi_controller_put(*(struct spmi_controller **)res);
+}
+
+struct spmi_controller *devm_spmi_controller_alloc(struct device *parent, size_t size)
+{
+	struct spmi_controller **ptr, *ctrl;
+
+	ptr = devres_alloc(devm_spmi_controller_release, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	ctrl = spmi_controller_alloc(parent, size);
+	if (IS_ERR(ctrl)) {
+		devres_free(ptr);
+		return ctrl;
+	}
+
+	*ptr = ctrl;
+	devres_add(parent, ptr);
+
+	return ctrl;
+}
+EXPORT_SYMBOL_GPL(devm_spmi_controller_alloc);
+
+static void devm_spmi_controller_remove(struct device *parent, void *res)
+{
+	spmi_controller_remove(*(struct spmi_controller **)res);
+}
+
+int devm_spmi_controller_add(struct device *parent, struct spmi_controller *ctrl)
+{
+	struct spmi_controller **ptr;
+	int ret;
+
+	ptr = devres_alloc(devm_spmi_controller_remove, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	ret = spmi_controller_add(ctrl);
+	if (ret) {
+		devres_free(ptr);
+		return ret;
+	}
+
+	*ptr = ctrl;
+	devres_add(parent, ptr);
+
+	return 0;
+
+}
+EXPORT_SYMBOL_GPL(devm_spmi_controller_add);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SPMI devres helpers");
diff --git a/drivers/spmi/spmi-mtk-pmif.c b/drivers/spmi/spmi-mtk-pmif.c
index b3c991e1ea40..5079442f8ea1 100644
--- a/drivers/spmi/spmi-mtk-pmif.c
+++ b/drivers/spmi/spmi-mtk-pmif.c
@@ -50,6 +50,7 @@ struct pmif {
 	struct clk_bulk_data clks[PMIF_MAX_CLKS];
 	size_t nclks;
 	const struct pmif_data *data;
+	raw_spinlock_t lock;
 };
 
 static const char * const pmif_clock_names[] = {
@@ -314,6 +315,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 	struct ch_reg *inf_reg;
 	int ret;
 	u32 data, cmd;
+	unsigned long flags;
 
 	/* Check for argument validation. */
 	if (sid & ~0xf) {
@@ -334,6 +336,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 	else
 		return -EINVAL;
 
+	raw_spin_lock_irqsave(&arb->lock, flags);
 	/* Wait for Software Interface FSM state to be IDLE. */
 	inf_reg = &arb->chan;
 	ret = readl_poll_timeout_atomic(arb->base + arb->data->regs[inf_reg->ch_sta],
@@ -343,6 +346,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 		/* set channel ready if the data has transferred */
 		if (pmif_is_fsm_vldclr(arb))
 			pmif_writel(arb, 1, inf_reg->ch_rdy);
+		raw_spin_unlock_irqrestore(&arb->lock, flags);
 		dev_err(&ctrl->dev, "failed to wait for SWINF_IDLE\n");
 		return ret;
 	}
@@ -350,6 +354,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 	/* Send the command. */
 	cmd = (opc << 30) | (sid << 24) | ((len - 1) << 16) | addr;
 	pmif_writel(arb, cmd, inf_reg->ch_send);
+	raw_spin_unlock_irqrestore(&arb->lock, flags);
 
 	/*
 	 * Wait for Software Interface FSM state to be WFVLDCLR,
@@ -376,7 +381,14 @@ static int pmif_spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 	struct pmif *arb = spmi_controller_get_drvdata(ctrl);
 	struct ch_reg *inf_reg;
 	int ret;
-	u32 data, cmd;
+	u32 data, wdata, cmd;
+	unsigned long flags;
+
+	/* Check for argument validation. */
+	if (unlikely(sid & ~0xf)) {
+		dev_err(&ctrl->dev, "exceed the max slv id\n");
+		return -EINVAL;
+	}
 
 	if (len > 4) {
 		dev_err(&ctrl->dev, "pmif supports 1..4 bytes per trans, but:%zu requested", len);
@@ -394,6 +406,10 @@ static int pmif_spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 	else
 		return -EINVAL;
 
+	/* Set the write data. */
+	memcpy(&wdata, buf, len);
+
+	raw_spin_lock_irqsave(&arb->lock, flags);
 	/* Wait for Software Interface FSM state to be IDLE. */
 	inf_reg = &arb->chan;
 	ret = readl_poll_timeout_atomic(arb->base + arb->data->regs[inf_reg->ch_sta],
@@ -403,17 +419,17 @@ static int pmif_spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 		/* set channel ready if the data has transferred */
 		if (pmif_is_fsm_vldclr(arb))
 			pmif_writel(arb, 1, inf_reg->ch_rdy);
+		raw_spin_unlock_irqrestore(&arb->lock, flags);
 		dev_err(&ctrl->dev, "failed to wait for SWINF_IDLE\n");
 		return ret;
 	}
 
-	/* Set the write data. */
-	memcpy(&data, buf, len);
-	pmif_writel(arb, data, inf_reg->wdata);
+	pmif_writel(arb, wdata, inf_reg->wdata);
 
 	/* Send the command. */
 	cmd = (opc << 30) | BIT(29) | (sid << 24) | ((len - 1) << 16) | addr;
 	pmif_writel(arb, cmd, inf_reg->ch_send);
+	raw_spin_unlock_irqrestore(&arb->lock, flags);
 
 	return 0;
 }
@@ -437,44 +453,39 @@ static int mtk_spmi_probe(struct platform_device *pdev)
 	int err, i;
 	u32 chan_offset;
 
-	ctrl = spmi_controller_alloc(&pdev->dev, sizeof(*arb));
-	if (!ctrl)
-		return -ENOMEM;
+	ctrl = devm_spmi_controller_alloc(&pdev->dev, sizeof(*arb));
+	if (IS_ERR(ctrl))
+		return PTR_ERR(ctrl);
 
 	arb = spmi_controller_get_drvdata(ctrl);
 	arb->data = device_get_match_data(&pdev->dev);
 	if (!arb->data) {
-		err = -EINVAL;
 		dev_err(&pdev->dev, "Cannot get drv_data\n");
-		goto err_put_ctrl;
+		return -EINVAL;
 	}
 
 	arb->base = devm_platform_ioremap_resource_byname(pdev, "pmif");
-	if (IS_ERR(arb->base)) {
-		err = PTR_ERR(arb->base);
-		goto err_put_ctrl;
-	}
+	if (IS_ERR(arb->base))
+		return PTR_ERR(arb->base);
 
 	arb->spmimst_base = devm_platform_ioremap_resource_byname(pdev, "spmimst");
-	if (IS_ERR(arb->spmimst_base)) {
-		err = PTR_ERR(arb->spmimst_base);
-		goto err_put_ctrl;
-	}
+	if (IS_ERR(arb->spmimst_base))
+		return PTR_ERR(arb->spmimst_base);
 
 	arb->nclks = ARRAY_SIZE(pmif_clock_names);
 	for (i = 0; i < arb->nclks; i++)
 		arb->clks[i].id = pmif_clock_names[i];
 
-	err = devm_clk_bulk_get(&pdev->dev, arb->nclks, arb->clks);
+	err = clk_bulk_get(&pdev->dev, arb->nclks, arb->clks);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to get clocks: %d\n", err);
-		goto err_put_ctrl;
+		return err;
 	}
 
 	err = clk_bulk_prepare_enable(arb->nclks, arb->clks);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to enable clocks: %d\n", err);
-		goto err_put_ctrl;
+		goto err_put_clks;
 	}
 
 	ctrl->cmd = pmif_arb_cmd;
@@ -488,6 +499,8 @@ static int mtk_spmi_probe(struct platform_device *pdev)
 	arb->chan.ch_send = PMIF_SWINF_0_ACC + chan_offset;
 	arb->chan.ch_rdy = PMIF_SWINF_0_VLD_CLR + chan_offset;
 
+	raw_spin_lock_init(&arb->lock);
+
 	platform_set_drvdata(pdev, ctrl);
 
 	err = spmi_controller_add(ctrl);
@@ -498,8 +511,8 @@ static int mtk_spmi_probe(struct platform_device *pdev)
 
 err_domain_remove:
 	clk_bulk_disable_unprepare(arb->nclks, arb->clks);
-err_put_ctrl:
-	spmi_controller_put(ctrl);
+err_put_clks:
+	clk_bulk_put(arb->nclks, arb->clks);
 	return err;
 }
 
@@ -508,9 +521,9 @@ static void mtk_spmi_remove(struct platform_device *pdev)
 	struct spmi_controller *ctrl = platform_get_drvdata(pdev);
 	struct pmif *arb = spmi_controller_get_drvdata(ctrl);
 
-	clk_bulk_disable_unprepare(arb->nclks, arb->clks);
 	spmi_controller_remove(ctrl);
-	spmi_controller_put(ctrl);
+	clk_bulk_disable_unprepare(arb->nclks, arb->clks);
+	clk_bulk_put(arb->nclks, arb->clks);
 }
 
 static const struct of_device_id mtk_spmi_match_table[] = {
diff --git a/drivers/spmi/spmi-pmic-arb.c b/drivers/spmi/spmi-pmic-arb.c
index dcb675d980d4..9ed1180fe31f 100644
--- a/drivers/spmi/spmi-pmic-arb.c
+++ b/drivers/spmi/spmi-pmic-arb.c
@@ -1443,9 +1443,9 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev)
 	u32 channel, ee, hw_ver;
 	int err;
 
-	ctrl = spmi_controller_alloc(&pdev->dev, sizeof(*pmic_arb));
-	if (!ctrl)
-		return -ENOMEM;
+	ctrl = devm_spmi_controller_alloc(&pdev->dev, sizeof(*pmic_arb));
+	if (IS_ERR(ctrl))
+		return PTR_ERR(ctrl);
 
 	pmic_arb = spmi_controller_get_drvdata(ctrl);
 	pmic_arb->spmic = ctrl;
@@ -1462,20 +1462,16 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev)
 	 */
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "core");
 	core = devm_ioremap(&ctrl->dev, res->start, resource_size(res));
-	if (IS_ERR(core)) {
-		err = PTR_ERR(core);
-		goto err_put_ctrl;
-	}
+	if (IS_ERR(core))
+		return PTR_ERR(core);
 
 	pmic_arb->core_size = resource_size(res);
 
 	pmic_arb->ppid_to_apid = devm_kcalloc(&ctrl->dev, PMIC_ARB_MAX_PPID,
 					      sizeof(*pmic_arb->ppid_to_apid),
 					      GFP_KERNEL);
-	if (!pmic_arb->ppid_to_apid) {
-		err = -ENOMEM;
-		goto err_put_ctrl;
-	}
+	if (!pmic_arb->ppid_to_apid)
+		return -ENOMEM;
 
 	hw_ver = readl_relaxed(core + PMIC_ARB_VERSION);
 
@@ -1499,19 +1495,15 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev)
 						   "obsrvr");
 		pmic_arb->rd_base = devm_ioremap(&ctrl->dev, res->start,
 						 resource_size(res));
-		if (IS_ERR(pmic_arb->rd_base)) {
-			err = PTR_ERR(pmic_arb->rd_base);
-			goto err_put_ctrl;
-		}
+		if (IS_ERR(pmic_arb->rd_base))
+			return PTR_ERR(pmic_arb->rd_base);
 
 		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
 						   "chnls");
 		pmic_arb->wr_base = devm_ioremap(&ctrl->dev, res->start,
 						 resource_size(res));
-		if (IS_ERR(pmic_arb->wr_base)) {
-			err = PTR_ERR(pmic_arb->wr_base);
-			goto err_put_ctrl;
-		}
+		if (IS_ERR(pmic_arb->wr_base))
+			return PTR_ERR(pmic_arb->wr_base);
 	}
 
 	pmic_arb->max_periphs = PMIC_ARB_MAX_PERIPHS;
@@ -1522,10 +1514,9 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev)
 		of_property_read_u32(pdev->dev.of_node, "qcom,bus-id",
 					&pmic_arb->bus_instance);
 		if (pmic_arb->bus_instance > 1) {
-			err = -EINVAL;
 			dev_err(&pdev->dev, "invalid bus instance (%u) specified\n",
 				pmic_arb->bus_instance);
-			goto err_put_ctrl;
+			return -EINVAL;
 		}
 
 		if (pmic_arb->bus_instance == 0) {
@@ -1543,10 +1534,9 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev)
 		}
 
 		if (pmic_arb->base_apid + pmic_arb->apid_count > pmic_arb->max_periphs) {
-			err = -EINVAL;
 			dev_err(&pdev->dev, "Unsupported APID count %d detected\n",
 				pmic_arb->base_apid + pmic_arb->apid_count);
-			goto err_put_ctrl;
+			return -EINVAL;
 		}
 	} else if (hw_ver >= PMIC_ARB_VERSION_V5_MIN) {
 		pmic_arb->base_apid = 0;
@@ -1554,55 +1544,45 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev)
 					PMIC_ARB_FEATURES_PERIPH_MASK;
 
 		if (pmic_arb->apid_count > pmic_arb->max_periphs) {
-			err = -EINVAL;
 			dev_err(&pdev->dev, "Unsupported APID count %d detected\n",
 				pmic_arb->apid_count);
-			goto err_put_ctrl;
+			return -EINVAL;
 		}
 	}
 
 	pmic_arb->apid_data = devm_kcalloc(&ctrl->dev, pmic_arb->max_periphs,
 					   sizeof(*pmic_arb->apid_data),
 					   GFP_KERNEL);
-	if (!pmic_arb->apid_data) {
-		err = -ENOMEM;
-		goto err_put_ctrl;
-	}
+	if (!pmic_arb->apid_data)
+		return -ENOMEM;
 
 	dev_info(&ctrl->dev, "PMIC arbiter version %s (0x%x)\n",
 		 pmic_arb->ver_ops->ver_str, hw_ver);
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "intr");
 	pmic_arb->intr = devm_ioremap_resource(&ctrl->dev, res);
-	if (IS_ERR(pmic_arb->intr)) {
-		err = PTR_ERR(pmic_arb->intr);
-		goto err_put_ctrl;
-	}
+	if (IS_ERR(pmic_arb->intr))
+		return PTR_ERR(pmic_arb->intr);
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cnfg");
 	pmic_arb->cnfg = devm_ioremap_resource(&ctrl->dev, res);
-	if (IS_ERR(pmic_arb->cnfg)) {
-		err = PTR_ERR(pmic_arb->cnfg);
-		goto err_put_ctrl;
-	}
+	if (IS_ERR(pmic_arb->cnfg))
+		return PTR_ERR(pmic_arb->cnfg);
 
 	pmic_arb->irq = platform_get_irq_byname(pdev, "periph_irq");
-	if (pmic_arb->irq < 0) {
-		err = pmic_arb->irq;
-		goto err_put_ctrl;
-	}
+	if (pmic_arb->irq < 0)
+		return pmic_arb->irq;
 
 	err = of_property_read_u32(pdev->dev.of_node, "qcom,channel", &channel);
 	if (err) {
 		dev_err(&pdev->dev, "channel unspecified.\n");
-		goto err_put_ctrl;
+		return err;
 	}
 
 	if (channel > 5) {
 		dev_err(&pdev->dev, "invalid channel (%u) specified.\n",
 			channel);
-		err = -EINVAL;
-		goto err_put_ctrl;
+		return -EINVAL;
 	}
 
 	pmic_arb->channel = channel;
@@ -1610,22 +1590,19 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev)
 	err = of_property_read_u32(pdev->dev.of_node, "qcom,ee", &ee);
 	if (err) {
 		dev_err(&pdev->dev, "EE unspecified.\n");
-		goto err_put_ctrl;
+		return err;
 	}
 
 	if (ee > 5) {
 		dev_err(&pdev->dev, "invalid EE (%u) specified\n", ee);
-		err = -EINVAL;
-		goto err_put_ctrl;
+		return -EINVAL;
 	}
 
 	pmic_arb->ee = ee;
 	mapping_table = devm_kcalloc(&ctrl->dev, pmic_arb->max_periphs,
 					sizeof(*mapping_table), GFP_KERNEL);
-	if (!mapping_table) {
-		err = -ENOMEM;
-		goto err_put_ctrl;
-	}
+	if (!mapping_table)
+		return -ENOMEM;
 
 	pmic_arb->mapping_table = mapping_table;
 	/* Initialize max_apid/min_apid to the opposite bounds, during
@@ -1645,7 +1622,7 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev)
 		if (err) {
 			dev_err(&pdev->dev, "could not read APID->PPID mapping table, rc= %d\n",
 				err);
-			goto err_put_ctrl;
+			return err;
 		}
 	}
 
@@ -1654,8 +1631,7 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev)
 					 &pmic_arb_irq_domain_ops, pmic_arb);
 	if (!pmic_arb->domain) {
 		dev_err(&pdev->dev, "unable to create irq_domain\n");
-		err = -ENOMEM;
-		goto err_put_ctrl;
+		return -ENOMEM;
 	}
 
 	irq_set_chained_handler_and_data(pmic_arb->irq, pmic_arb_chained_irq,
@@ -1669,8 +1645,6 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev)
 err_domain_remove:
 	irq_set_chained_handler_and_data(pmic_arb->irq, NULL, NULL);
 	irq_domain_remove(pmic_arb->domain);
-err_put_ctrl:
-	spmi_controller_put(ctrl);
 	return err;
 }
 
@@ -1681,7 +1655,6 @@ static void spmi_pmic_arb_remove(struct platform_device *pdev)
 	spmi_controller_remove(ctrl);
 	irq_set_chained_handler_and_data(pmic_arb->irq, NULL, NULL);
 	irq_domain_remove(pmic_arb->domain);
-	spmi_controller_put(ctrl);
 }
 
 static const struct of_device_id spmi_pmic_arb_match_table[] = {
diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c
index 93cd4a34debc..3a60fd2e09e1 100644
--- a/drivers/spmi/spmi.c
+++ b/drivers/spmi/spmi.c
@@ -448,11 +448,11 @@ struct spmi_controller *spmi_controller_alloc(struct device *parent,
 	int id;
 
 	if (WARN_ON(!parent))
-		return NULL;
+		return ERR_PTR(-EINVAL);
 
 	ctrl = kzalloc(sizeof(*ctrl) + size, GFP_KERNEL);
 	if (!ctrl)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	device_initialize(&ctrl->dev);
 	ctrl->dev.type = &spmi_ctrl_type;
@@ -466,7 +466,7 @@ struct spmi_controller *spmi_controller_alloc(struct device *parent,
 		dev_err(parent,
 			"unable to allocate SPMI controller identifier.\n");
 		spmi_controller_put(ctrl);
-		return NULL;
+		return ERR_PTR(id);
 	}
 
 	ctrl->nr = id;
diff --git a/drivers/staging/greybus/i2c.c b/drivers/staging/greybus/i2c.c
index de2f6516da09..22325ab9d652 100644
--- a/drivers/staging/greybus/i2c.c
+++ b/drivers/staging/greybus/i2c.c
@@ -264,7 +264,7 @@ static int gb_i2c_probe(struct gbphy_device *gbphy_dev,
 	/* Looks good; up our i2c adapter */
 	adapter = &gb_i2c_dev->adapter;
 	adapter->owner = THIS_MODULE;
-	adapter->class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	adapter->class = I2C_CLASS_HWMON;
 	adapter->algo = &gb_i2c_algorithm;
 
 	adapter->dev.parent = &gbphy_dev->dev;
diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c
index e748a5d04e97..9149d41fe65b 100644
--- a/drivers/staging/iio/impedance-analyzer/ad5933.c
+++ b/drivers/staging/iio/impedance-analyzer/ad5933.c
@@ -608,7 +608,7 @@ static void ad5933_work(struct work_struct *work)
 		struct ad5933_state, work.work);
 	struct iio_dev *indio_dev = i2c_get_clientdata(st->client);
 	__be16 buf[2];
-	int val[2];
+	u16 val[2];
 	unsigned char status;
 	int ret;
 
diff --git a/drivers/staging/media/atomisp/pci/atomisp_cmd.c b/drivers/staging/media/atomisp/pci/atomisp_cmd.c
index f44e6412f4e3..d0db2efe0045 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_cmd.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_cmd.c
@@ -3723,12 +3723,10 @@ apply_min_padding:
 
 static int atomisp_set_crop(struct atomisp_device *isp,
 			    const struct v4l2_mbus_framefmt *format,
+			    struct v4l2_subdev_state *sd_state,
 			    int which)
 {
 	struct atomisp_input_subdev *input = &isp->inputs[isp->asd.input_curr];
-	struct v4l2_subdev_state pad_state = {
-		.pads = &input->pad_cfg,
-	};
 	struct v4l2_subdev_selection sel = {
 		.which = which,
 		.target = V4L2_SEL_TGT_CROP,
@@ -3754,7 +3752,7 @@ static int atomisp_set_crop(struct atomisp_device *isp,
 	sel.r.left = ((input->native_rect.width - sel.r.width) / 2) & ~1;
 	sel.r.top = ((input->native_rect.height - sel.r.height) / 2) & ~1;
 
-	ret = v4l2_subdev_call(input->camera, pad, set_selection, &pad_state, &sel);
+	ret = v4l2_subdev_call(input->camera, pad, set_selection, sd_state, &sel);
 	if (ret)
 		dev_err(isp->dev, "Error setting crop to %ux%u @%ux%u: %d\n",
 			sel.r.width, sel.r.height, sel.r.left, sel.r.top, ret);
@@ -3770,9 +3768,6 @@ int atomisp_try_fmt(struct atomisp_device *isp, struct v4l2_pix_format *f,
 	const struct atomisp_format_bridge *fmt, *snr_fmt;
 	struct atomisp_sub_device *asd = &isp->asd;
 	struct atomisp_input_subdev *input = &isp->inputs[asd->input_curr];
-	struct v4l2_subdev_state pad_state = {
-		.pads = &input->pad_cfg,
-	};
 	struct v4l2_subdev_format format = {
 		.which = V4L2_SUBDEV_FORMAT_TRY,
 	};
@@ -3809,11 +3804,16 @@ int atomisp_try_fmt(struct atomisp_device *isp, struct v4l2_pix_format *f,
 	dev_dbg(isp->dev, "try_mbus_fmt: asking for %ux%u\n",
 		format.format.width, format.format.height);
 
-	ret = atomisp_set_crop(isp, &format.format, V4L2_SUBDEV_FORMAT_TRY);
-	if (ret)
-		return ret;
+	v4l2_subdev_lock_state(input->try_sd_state);
+
+	ret = atomisp_set_crop(isp, &format.format, input->try_sd_state,
+			       V4L2_SUBDEV_FORMAT_TRY);
+	if (ret == 0)
+		ret = v4l2_subdev_call(input->camera, pad, set_fmt,
+				       input->try_sd_state, &format);
+
+	v4l2_subdev_unlock_state(input->try_sd_state);
 
-	ret = v4l2_subdev_call(input->camera, pad, set_fmt, &pad_state, &format);
 	if (ret)
 		return ret;
 
@@ -4238,9 +4238,7 @@ static int atomisp_set_fmt_to_snr(struct video_device *vdev, const struct v4l2_p
 	struct atomisp_device *isp = asd->isp;
 	struct atomisp_input_subdev *input = &isp->inputs[asd->input_curr];
 	const struct atomisp_format_bridge *format;
-	struct v4l2_subdev_state pad_state = {
-		.pads = &input->pad_cfg,
-	};
+	struct v4l2_subdev_state *act_sd_state;
 	struct v4l2_subdev_format vformat = {
 		.which = V4L2_SUBDEV_FORMAT_TRY,
 	};
@@ -4268,12 +4266,18 @@ static int atomisp_set_fmt_to_snr(struct video_device *vdev, const struct v4l2_p
 
 	/* Disable dvs if resolution can't be supported by sensor */
 	if (asd->params.video_dis_en && asd->run_mode->val == ATOMISP_RUN_MODE_VIDEO) {
-		ret = atomisp_set_crop(isp, &vformat.format, V4L2_SUBDEV_FORMAT_TRY);
-		if (ret)
-			return ret;
+		v4l2_subdev_lock_state(input->try_sd_state);
+
+		ret = atomisp_set_crop(isp, &vformat.format, input->try_sd_state,
+				       V4L2_SUBDEV_FORMAT_TRY);
+		if (ret == 0) {
+			vformat.which = V4L2_SUBDEV_FORMAT_TRY;
+			ret = v4l2_subdev_call(input->camera, pad, set_fmt,
+					       input->try_sd_state, &vformat);
+		}
+
+		v4l2_subdev_unlock_state(input->try_sd_state);
 
-		vformat.which = V4L2_SUBDEV_FORMAT_TRY;
-		ret = v4l2_subdev_call(input->camera, pad, set_fmt, &pad_state, &vformat);
 		if (ret)
 			return ret;
 
@@ -4291,12 +4295,18 @@ static int atomisp_set_fmt_to_snr(struct video_device *vdev, const struct v4l2_p
 		}
 	}
 
-	ret = atomisp_set_crop(isp, &vformat.format, V4L2_SUBDEV_FORMAT_ACTIVE);
-	if (ret)
-		return ret;
+	act_sd_state = v4l2_subdev_lock_and_get_active_state(input->camera);
+
+	ret = atomisp_set_crop(isp, &vformat.format, act_sd_state,
+			       V4L2_SUBDEV_FORMAT_ACTIVE);
+	if (ret == 0) {
+		vformat.which = V4L2_SUBDEV_FORMAT_ACTIVE;
+		ret = v4l2_subdev_call(input->camera, pad, set_fmt, act_sd_state, &vformat);
+	}
+
+	if (act_sd_state)
+		v4l2_subdev_unlock_state(act_sd_state);
 
-	vformat.which = V4L2_SUBDEV_FORMAT_ACTIVE;
-	ret = v4l2_subdev_call(input->camera, pad, set_fmt, NULL, &vformat);
 	if (ret)
 		return ret;
 
diff --git a/drivers/staging/media/atomisp/pci/atomisp_internal.h b/drivers/staging/media/atomisp/pci/atomisp_internal.h
index f7b4bee9574b..d5b077e602ca 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_internal.h
+++ b/drivers/staging/media/atomisp/pci/atomisp_internal.h
@@ -132,8 +132,8 @@ struct atomisp_input_subdev {
 	/* Sensor rects for sensors which support crop */
 	struct v4l2_rect native_rect;
 	struct v4l2_rect active_rect;
-	/* Sensor pad_cfg for which == V4L2_SUBDEV_FORMAT_TRY calls */
-	struct v4l2_subdev_pad_config pad_cfg;
+	/* Sensor state for which == V4L2_SUBDEV_FORMAT_TRY calls */
+	struct v4l2_subdev_state *try_sd_state;
 
 	struct v4l2_subdev *motor;
 
diff --git a/drivers/staging/media/atomisp/pci/atomisp_ioctl.c b/drivers/staging/media/atomisp/pci/atomisp_ioctl.c
index 01b7fa9b56a2..5b2d88c02d36 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_ioctl.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_ioctl.c
@@ -781,12 +781,20 @@ static int atomisp_enum_framesizes(struct file *file, void *priv,
 		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
 		.code = input->code,
 	};
+	struct v4l2_subdev_state *act_sd_state;
 	int ret;
 
+	if (!input->camera)
+		return -EINVAL;
+
 	if (input->crop_support)
 		return atomisp_enum_framesizes_crop(isp, fsize);
 
-	ret = v4l2_subdev_call(input->camera, pad, enum_frame_size, NULL, &fse);
+	act_sd_state = v4l2_subdev_lock_and_get_active_state(input->camera);
+	ret = v4l2_subdev_call(input->camera, pad, enum_frame_size,
+			       act_sd_state, &fse);
+	if (act_sd_state)
+		v4l2_subdev_unlock_state(act_sd_state);
 	if (ret)
 		return ret;
 
@@ -803,18 +811,25 @@ static int atomisp_enum_frameintervals(struct file *file, void *priv,
 	struct video_device *vdev = video_devdata(file);
 	struct atomisp_device *isp = video_get_drvdata(vdev);
 	struct atomisp_sub_device *asd = atomisp_to_video_pipe(vdev)->asd;
+	struct atomisp_input_subdev *input = &isp->inputs[asd->input_curr];
 	struct v4l2_subdev_frame_interval_enum fie = {
-		.code	= atomisp_in_fmt_conv[0].code,
+		.code = atomisp_in_fmt_conv[0].code,
 		.index = fival->index,
 		.width = fival->width,
 		.height = fival->height,
 		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
 	};
+	struct v4l2_subdev_state *act_sd_state;
 	int ret;
 
-	ret = v4l2_subdev_call(isp->inputs[asd->input_curr].camera,
-			       pad, enum_frame_interval, NULL,
-			       &fie);
+	if (!input->camera)
+		return -EINVAL;
+
+	act_sd_state = v4l2_subdev_lock_and_get_active_state(input->camera);
+	ret = v4l2_subdev_call(input->camera, pad, enum_frame_interval,
+			       act_sd_state, &fie);
+	if (act_sd_state)
+		v4l2_subdev_unlock_state(act_sd_state);
 	if (ret)
 		return ret;
 
@@ -830,30 +845,25 @@ static int atomisp_enum_fmt_cap(struct file *file, void *fh,
 	struct video_device *vdev = video_devdata(file);
 	struct atomisp_device *isp = video_get_drvdata(vdev);
 	struct atomisp_sub_device *asd = atomisp_to_video_pipe(vdev)->asd;
+	struct atomisp_input_subdev *input = &isp->inputs[asd->input_curr];
 	struct v4l2_subdev_mbus_code_enum code = {
 		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
 	};
 	const struct atomisp_format_bridge *format;
-	struct v4l2_subdev *camera;
+	struct v4l2_subdev_state *act_sd_state;
 	unsigned int i, fi = 0;
-	int rval;
+	int ret;
 
-	camera = isp->inputs[asd->input_curr].camera;
-	if(!camera) {
-		dev_err(isp->dev, "%s(): camera is NULL, device is %s\n",
-			__func__, vdev->name);
+	if (!input->camera)
 		return -EINVAL;
-	}
 
-	rval = v4l2_subdev_call(camera, pad, enum_mbus_code, NULL, &code);
-	if (rval == -ENOIOCTLCMD) {
-		dev_warn(isp->dev,
-			 "enum_mbus_code pad op not supported by %s. Please fix your sensor driver!\n",
-			 camera->name);
-	}
-
-	if (rval)
-		return rval;
+	act_sd_state = v4l2_subdev_lock_and_get_active_state(input->camera);
+	ret = v4l2_subdev_call(input->camera, pad, enum_mbus_code,
+			       act_sd_state, &code);
+	if (act_sd_state)
+		v4l2_subdev_unlock_state(act_sd_state);
+	if (ret)
+		return ret;
 
 	for (i = 0; i < ARRAY_SIZE(atomisp_output_fmts); i++) {
 		format = &atomisp_output_fmts[i];
diff --git a/drivers/staging/media/atomisp/pci/atomisp_v4l2.c b/drivers/staging/media/atomisp/pci/atomisp_v4l2.c
index c1c8501ec61f..547e1444ad97 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_v4l2.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_v4l2.c
@@ -862,6 +862,9 @@ static void atomisp_unregister_entities(struct atomisp_device *isp)
 	v4l2_device_unregister(&isp->v4l2_dev);
 	media_device_unregister(&isp->media_dev);
 	media_device_cleanup(&isp->media_dev);
+
+	for (i = 0; i < isp->input_cnt; i++)
+		__v4l2_subdev_state_free(isp->inputs[i].try_sd_state);
 }
 
 static int atomisp_register_entities(struct atomisp_device *isp)
@@ -933,32 +936,49 @@ v4l2_device_failed:
 
 static void atomisp_init_sensor(struct atomisp_input_subdev *input)
 {
+	static struct lock_class_key try_sd_state_key;
 	struct v4l2_subdev_mbus_code_enum mbus_code_enum = { };
 	struct v4l2_subdev_frame_size_enum fse = { };
-	struct v4l2_subdev_state sd_state = {
-		.pads = &input->pad_cfg,
-	};
 	struct v4l2_subdev_selection sel = { };
+	struct v4l2_subdev_state *try_sd_state, *act_sd_state;
 	int i, err;
 
+	/*
+	 * FIXME: Drivers are not supposed to use __v4l2_subdev_state_alloc()
+	 * but atomisp needs this for try_fmt on its /dev/video# node since
+	 * it emulates a normal v4l2 device there, passing through try_fmt /
+	 * set_fmt to the sensor.
+	 */
+	try_sd_state = __v4l2_subdev_state_alloc(input->camera,
+				"atomisp:try_sd_state->lock", &try_sd_state_key);
+	if (IS_ERR(try_sd_state))
+		return;
+
+	input->try_sd_state = try_sd_state;
+
+	act_sd_state = v4l2_subdev_lock_and_get_active_state(input->camera);
+
 	mbus_code_enum.which = V4L2_SUBDEV_FORMAT_ACTIVE;
-	err = v4l2_subdev_call(input->camera, pad, enum_mbus_code, NULL, &mbus_code_enum);
+	err = v4l2_subdev_call(input->camera, pad, enum_mbus_code,
+			       act_sd_state, &mbus_code_enum);
 	if (!err)
 		input->code = mbus_code_enum.code;
 
 	sel.which = V4L2_SUBDEV_FORMAT_ACTIVE;
 	sel.target = V4L2_SEL_TGT_NATIVE_SIZE;
-	err = v4l2_subdev_call(input->camera, pad, get_selection, NULL, &sel);
+	err = v4l2_subdev_call(input->camera, pad, get_selection,
+			       act_sd_state, &sel);
 	if (err)
-		return;
+		goto unlock_act_sd_state;
 
 	input->native_rect = sel.r;
 
 	sel.which = V4L2_SUBDEV_FORMAT_ACTIVE;
 	sel.target = V4L2_SEL_TGT_CROP_DEFAULT;
-	err = v4l2_subdev_call(input->camera, pad, get_selection, NULL, &sel);
+	err = v4l2_subdev_call(input->camera, pad, get_selection,
+			       act_sd_state, &sel);
 	if (err)
-		return;
+		goto unlock_act_sd_state;
 
 	input->active_rect = sel.r;
 
@@ -973,7 +993,8 @@ static void atomisp_init_sensor(struct atomisp_input_subdev *input)
 		fse.code = input->code;
 		fse.which = V4L2_SUBDEV_FORMAT_ACTIVE;
 
-		err = v4l2_subdev_call(input->camera, pad, enum_frame_size, NULL, &fse);
+		err = v4l2_subdev_call(input->camera, pad, enum_frame_size,
+				       act_sd_state, &fse);
 		if (err)
 			break;
 
@@ -989,22 +1010,26 @@ static void atomisp_init_sensor(struct atomisp_input_subdev *input)
 	 * for padding, set the crop rect to cover the entire sensor instead
 	 * of only the default active area.
 	 *
-	 * Do this for both try and active formats since the try_crop rect in
-	 * pad_cfg may influence (clamp) future try_fmt calls with which == try.
+	 * Do this for both try and active formats since the crop rect in
+	 * try_sd_state may influence (clamp size) in calls with which == try.
 	 */
 	sel.which = V4L2_SUBDEV_FORMAT_TRY;
 	sel.target = V4L2_SEL_TGT_CROP;
 	sel.r = input->native_rect;
-	err = v4l2_subdev_call(input->camera, pad, set_selection, &sd_state, &sel);
+	v4l2_subdev_lock_state(input->try_sd_state);
+	err = v4l2_subdev_call(input->camera, pad, set_selection,
+			       input->try_sd_state, &sel);
+	v4l2_subdev_unlock_state(input->try_sd_state);
 	if (err)
-		return;
+		goto unlock_act_sd_state;
 
 	sel.which = V4L2_SUBDEV_FORMAT_ACTIVE;
 	sel.target = V4L2_SEL_TGT_CROP;
 	sel.r = input->native_rect;
-	err = v4l2_subdev_call(input->camera, pad, set_selection, NULL, &sel);
+	err = v4l2_subdev_call(input->camera, pad, set_selection,
+			       act_sd_state, &sel);
 	if (err)
-		return;
+		goto unlock_act_sd_state;
 
 	dev_info(input->camera->dev, "Supports crop native %dx%d active %dx%d binning %d\n",
 		 input->native_rect.width, input->native_rect.height,
@@ -1012,6 +1037,10 @@ static void atomisp_init_sensor(struct atomisp_input_subdev *input)
 		 input->binning_support);
 
 	input->crop_support = true;
+
+unlock_act_sd_state:
+	if (act_sd_state)
+		v4l2_subdev_unlock_state(act_sd_state);
 }
 
 int atomisp_register_device_nodes(struct atomisp_device *isp)
diff --git a/drivers/staging/rtl8192e/Makefile b/drivers/staging/rtl8192e/Makefile
index 6af519938868..a1492215dab1 100644
--- a/drivers/staging/rtl8192e/Makefile
+++ b/drivers/staging/rtl8192e/Makefile
@@ -1,6 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
 rtllib-objs :=			\
-	dot11d.o		\
 	rtllib_module.o		\
 	rtllib_rx.o		\
 	rtllib_tx.o		\
diff --git a/drivers/staging/rtl8192e/dot11d.c b/drivers/staging/rtl8192e/dot11d.c
deleted file mode 100644
index d0b7332645be..000000000000
--- a/drivers/staging/rtl8192e/dot11d.c
+++ /dev/null
@@ -1,165 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/******************************************************************************
- * Copyright(c) 2008 - 2010 Realtek Corporation. All rights reserved.
- *
- * Contact Information:
- * wlanfae <wlanfae@realtek.com>
- ******************************************************************************/
-#include "dot11d.h"
-
-struct channel_list {
-	u8      channel[32];
-	u8      len;
-};
-
-static struct channel_list channel_array[] = {
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 36, 40, 44, 48, 52, 56, 60, 64,
-	  149, 153, 157, 161, 165}, 24},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11}, 11},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 36, 40, 44, 48, 52, 56,
-	  60, 64}, 21},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13}, 13},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13}, 13},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 36, 40, 44, 48, 52,
-	  56, 60, 64}, 22},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 36, 40, 44, 48, 52,
-	  56, 60, 64}, 22},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13}, 13},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 36, 40, 44, 48, 52,
-	  56, 60, 64}, 22},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 36, 40, 44, 48, 52,
-	 56, 60, 64}, 22},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14}, 14},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13}, 13},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 36, 40, 44, 48, 52,
-	  56, 60, 64}, 21}
-};
-
-void dot11d_init(struct rtllib_device *ieee)
-{
-	struct rt_dot11d_info *dot11d_info = GET_DOT11D_INFO(ieee);
-
-	dot11d_info->enabled = false;
-
-	dot11d_info->state = DOT11D_STATE_NONE;
-	dot11d_info->country_len = 0;
-	memset(dot11d_info->channel_map, 0, MAX_CHANNEL_NUMBER + 1);
-	memset(dot11d_info->max_tx_power_list, 0xFF, MAX_CHANNEL_NUMBER + 1);
-	RESET_CIE_WATCHDOG(ieee);
-}
-EXPORT_SYMBOL(dot11d_init);
-
-void dot11d_channel_map(u8 channel_plan, struct rtllib_device *ieee)
-{
-	int i, max_chan = 14, min_chan = 1;
-
-	ieee->global_domain = false;
-
-	if (channel_array[channel_plan].len != 0) {
-		memset(GET_DOT11D_INFO(ieee)->channel_map, 0,
-		       sizeof(GET_DOT11D_INFO(ieee)->channel_map));
-		for (i = 0; i < channel_array[channel_plan].len; i++) {
-			if (channel_array[channel_plan].channel[i] < min_chan ||
-			    channel_array[channel_plan].channel[i] > max_chan)
-				break;
-			GET_DOT11D_INFO(ieee)->channel_map[channel_array
-					[channel_plan].channel[i]] = 1;
-		}
-	}
-
-	switch (channel_plan) {
-	case COUNTRY_CODE_GLOBAL_DOMAIN:
-		ieee->global_domain = true;
-		for (i = 12; i <= 14; i++)
-			GET_DOT11D_INFO(ieee)->channel_map[i] = 2;
-		ieee->bss_start_channel = 10;
-		break;
-
-	case COUNTRY_CODE_WORLD_WIDE_13:
-		for (i = 12; i <= 13; i++)
-			GET_DOT11D_INFO(ieee)->channel_map[i] = 2;
-		ieee->bss_start_channel = 10;
-		break;
-
-	default:
-		ieee->bss_start_channel = 1;
-		break;
-	}
-}
-EXPORT_SYMBOL(dot11d_channel_map);
-
-void dot11d_reset(struct rtllib_device *ieee)
-{
-	struct rt_dot11d_info *dot11d_info = GET_DOT11D_INFO(ieee);
-	u32 i;
-
-	memset(dot11d_info->channel_map, 0, MAX_CHANNEL_NUMBER + 1);
-	memset(dot11d_info->max_tx_power_list, 0xFF, MAX_CHANNEL_NUMBER + 1);
-	for (i = 1; i <= 11; i++)
-		(dot11d_info->channel_map)[i] = 1;
-	for (i = 12; i <= 14; i++)
-		(dot11d_info->channel_map)[i] = 2;
-	dot11d_info->state = DOT11D_STATE_NONE;
-	dot11d_info->country_len = 0;
-	RESET_CIE_WATCHDOG(ieee);
-}
-
-void dot11d_update_country(struct rtllib_device *dev, u8 *address,
-			   u16 country_len, u8 *country)
-{
-	struct rt_dot11d_info *dot11d_info = GET_DOT11D_INFO(dev);
-	u8 i, j, number_of_triples, max_channel_number;
-	struct chnl_txpow_triple *triple;
-
-	memset(dot11d_info->channel_map, 0, MAX_CHANNEL_NUMBER + 1);
-	memset(dot11d_info->max_tx_power_list, 0xFF, MAX_CHANNEL_NUMBER + 1);
-	max_channel_number = 0;
-	number_of_triples = (country_len - 3) / 3;
-	triple = (struct chnl_txpow_triple *)(country + 3);
-	for (i = 0; i < number_of_triples; i++) {
-		if (max_channel_number >= triple->first_channel) {
-			netdev_info(dev->dev,
-				    "%s: Invalid country IE, skip it......1\n",
-				    __func__);
-			return;
-		}
-		if (MAX_CHANNEL_NUMBER < (triple->first_channel +
-		    triple->num_channels)) {
-			netdev_info(dev->dev,
-				    "%s: Invalid country IE, skip it......2\n",
-				    __func__);
-			return;
-		}
-
-		for (j = 0; j < triple->num_channels; j++) {
-			dot11d_info->channel_map[triple->first_channel + j] = 1;
-			dot11d_info->max_tx_power_list[triple->first_channel + j] =
-						 triple->max_tx_power;
-			max_channel_number = triple->first_channel + j;
-		}
-
-		triple = (struct chnl_txpow_triple *)((u8 *)triple + 3);
-	}
-
-	UPDATE_CIE_SRC(dev, address);
-
-	dot11d_info->country_len = country_len;
-	memcpy(dot11d_info->country_buffer, country, country_len);
-	dot11d_info->state = DOT11D_STATE_LEARNED;
-}
-
-void dot11d_scan_complete(struct rtllib_device *dev)
-{
-	struct rt_dot11d_info *dot11d_info = GET_DOT11D_INFO(dev);
-
-	switch (dot11d_info->state) {
-	case DOT11D_STATE_LEARNED:
-		dot11d_info->state = DOT11D_STATE_DONE;
-		break;
-	case DOT11D_STATE_DONE:
-		dot11d_reset(dev);
-		break;
-	case DOT11D_STATE_NONE:
-		break;
-	}
-}
diff --git a/drivers/staging/rtl8192e/dot11d.h b/drivers/staging/rtl8192e/dot11d.h
deleted file mode 100644
index 6d2b93acfa43..000000000000
--- a/drivers/staging/rtl8192e/dot11d.h
+++ /dev/null
@@ -1,84 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/******************************************************************************
- * Copyright(c) 2008 - 2010 Realtek Corporation. All rights reserved.
- *
- * Contact Information:
- * wlanfae <wlanfae@realtek.com>
- ******************************************************************************/
-#ifndef __INC_DOT11D_H
-#define __INC_DOT11D_H
-
-#include "rtllib.h"
-
-struct chnl_txpow_triple {
-	u8 first_channel;
-	u8  num_channels;
-	u8  max_tx_power;
-};
-
-enum dot11d_state {
-	DOT11D_STATE_NONE = 0,
-	DOT11D_STATE_LEARNED,
-	DOT11D_STATE_DONE,
-};
-
-/**
- * struct rt_dot11d_info * @country_len: value greater than 0 if
- *		  @country_buffer contains valid country information element.
- * @channel_map: holds channel values
- *		0 - invalid,
- *		1 - valid (active scan),
- *		2 - valid (passive scan)
- * @country_src_addr - Source AP of the country IE
- */
-
-struct rt_dot11d_info {
-	bool enabled;
-
-	u16 country_len;
-	u8  country_buffer[MAX_IE_LEN];
-	u8  country_src_addr[6];
-	u8  country_watchdog;
-
-	u8  channel_map[MAX_CHANNEL_NUMBER + 1];
-	u8  max_tx_power_list[MAX_CHANNEL_NUMBER + 1];
-
-	enum dot11d_state state;
-};
-
-static inline void copy_mac_addr(unsigned char *des, unsigned char *src)
-{
-	memcpy(des, src, 6);
-}
-
-#define GET_DOT11D_INFO(__ieee_dev)			\
-	 ((struct rt_dot11d_info *)((__ieee_dev)->dot11d_info))
-
-#define IS_DOT11D_ENABLE(__ieee_dev)			\
-	 (GET_DOT11D_INFO(__ieee_dev)->enabled)
-#define IS_COUNTRY_IE_VALID(__ieee_dev)			\
-	(GET_DOT11D_INFO(__ieee_dev)->country_len > 0)
-
-#define IS_EQUAL_CIE_SRC(__ieee_dev, __address)		\
-	 ether_addr_equal_unaligned( \
-		GET_DOT11D_INFO(__ieee_dev)->country_src_addr, __address)
-#define UPDATE_CIE_SRC(__ieee_dev, __address)		\
-	copy_mac_addr(GET_DOT11D_INFO(__ieee_dev)->country_src_addr, __address)
-
-#define GET_CIE_WATCHDOG(__ieee_dev)				\
-	 (GET_DOT11D_INFO(__ieee_dev)->country_watchdog)
-static inline void RESET_CIE_WATCHDOG(struct rtllib_device *__ieee_dev)
-{
-	GET_CIE_WATCHDOG(__ieee_dev) = 0;
-}
-
-#define UPDATE_CIE_WATCHDOG(__ieee_dev) (++GET_CIE_WATCHDOG(__ieee_dev))
-
-void dot11d_init(struct rtllib_device *dev);
-void dot11d_channel_map(u8 channel_plan, struct rtllib_device *ieee);
-void dot11d_reset(struct rtllib_device *dev);
-void dot11d_update_country(struct rtllib_device *dev, u8 *address,
-			   u16 country_len, u8 *country);
-void dot11d_scan_complete(struct rtllib_device *dev);
-
-#endif
diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_cmdpkt.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_cmdpkt.c
index eba8364d0ff2..7f0c160bc741 100644
--- a/drivers/staging/rtl8192e/rtl8192e/r8192E_cmdpkt.c
+++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_cmdpkt.c
@@ -63,9 +63,9 @@ bool rtl92e_send_cmd_pkt(struct net_device *dev, u32 type, const void *data,
 
 		if (type == DESC_PACKET_TYPE_INIT &&
 		    (!priv->rtllib->check_nic_enough_desc(dev, TXCMD_QUEUE) ||
-		     (!skb_queue_empty(&priv->rtllib->skb_waitQ[TXCMD_QUEUE])) ||
+		     (!skb_queue_empty(&priv->rtllib->skb_waitq[TXCMD_QUEUE])) ||
 		     (priv->rtllib->queue_stop))) {
-			skb_queue_tail(&priv->rtllib->skb_waitQ[TXCMD_QUEUE],
+			skb_queue_tail(&priv->rtllib->skb_waitq[TXCMD_QUEUE],
 				       skb);
 		} else {
 			priv->rtllib->softmac_hard_start_xmit(skb, dev);
diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
index e93394c51264..c7a2eae2fdb9 100644
--- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
+++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
@@ -51,12 +51,12 @@ void rtl92e_set_reg(struct net_device *dev, u8 variable, u8 *val)
 
 	case HW_VAR_MEDIA_STATUS:
 	{
-		enum rt_op_mode OpMode = *((enum rt_op_mode *)(val));
+		enum rt_op_mode op_mode = *((enum rt_op_mode *)(val));
 		u8 btMsr = rtl92e_readb(dev, MSR);
 
 		btMsr &= 0xfc;
 
-		switch (OpMode) {
+		switch (op_mode) {
 		case RT_OP_MODE_INFRASTRUCTURE:
 			btMsr |= MSR_INFRA;
 			break;
@@ -261,7 +261,6 @@ static void _rtl92e_read_eeprom_info(struct net_device *dev)
 		priv->eeprom_customer_id = usValue & 0xff;
 		usValue = rtl92e_eeprom_read(dev,
 					     EEPROM_ICVersion_ChannelPlan >> 1);
-		priv->eeprom_chnl_plan = usValue & 0xff;
 		IC_Version = (usValue & 0xff00) >> 8;
 
 		ICVer8192 = IC_Version & 0xf;
@@ -283,7 +282,6 @@ static void _rtl92e_read_eeprom_info(struct net_device *dev)
 		priv->eeprom_vid = 0;
 		priv->eeprom_did = 0;
 		priv->eeprom_customer_id = 0;
-		priv->eeprom_chnl_plan = 0;
 	}
 
 	if (!priv->autoload_fail_flag) {
@@ -387,25 +385,15 @@ static void _rtl92e_read_eeprom_info(struct net_device *dev)
 
 	rtl92e_init_adaptive_rate(dev);
 
-	priv->chnl_plan = priv->eeprom_chnl_plan;
-
 	switch (priv->eeprom_customer_id) {
 	case EEPROM_CID_NetCore:
 		priv->customer_id = RT_CID_819X_NETCORE;
 		break;
 	case EEPROM_CID_TOSHIBA:
 		priv->customer_id = RT_CID_TOSHIBA;
-		if (priv->eeprom_chnl_plan & 0x80)
-			priv->chnl_plan = priv->eeprom_chnl_plan & 0x7f;
-		else
-			priv->chnl_plan = 0x0;
 		break;
 	}
 
-	if (priv->chnl_plan > CHANNEL_PLAN_LEN - 1)
-		priv->chnl_plan = 0;
-	priv->chnl_plan = COUNTRY_CODE_WORLD_WIDE_13;
-
 	if (priv->eeprom_vid == 0x1186 &&  priv->eeprom_did == 0x3304)
 		priv->rtllib->bSupportRemoteWakeUp = true;
 	else
@@ -891,11 +879,11 @@ void  rtl92e_fill_tx_desc(struct net_device *dev, struct tx_desc *pdesc,
 	memset(pTxFwInfo, 0, sizeof(struct tx_fwinfo_8190pci));
 	pTxFwInfo->TxHT = (cb_desc->data_rate & 0x80) ? 1 : 0;
 	pTxFwInfo->TxRate = _rtl92e_rate_mgn_to_hw(cb_desc->data_rate);
-	pTxFwInfo->EnableCPUDur = cb_desc->bTxEnableFwCalcDur;
+	pTxFwInfo->EnableCPUDur = cb_desc->tx_enable_fw_calc_dur;
 	pTxFwInfo->Short = _rtl92e_query_is_short(pTxFwInfo->TxHT,
 						  pTxFwInfo->TxRate, cb_desc);
 
-	if (cb_desc->bAMPDUEnable) {
+	if (cb_desc->ampdu_enable) {
 		pTxFwInfo->AllowAggregation = 1;
 		pTxFwInfo->RxMF = cb_desc->ampdu_factor;
 		pTxFwInfo->RxAMD = cb_desc->ampdu_density;
@@ -1685,8 +1673,6 @@ bool rtl92e_get_rx_stats(struct net_device *dev, struct rtllib_rx_stats *stats,
 	stats->TimeStampLow = pDrvInfo->TSFL;
 	stats->TimeStampHigh = rtl92e_readl(dev, TSFR + 4);
 
-	rtl92e_update_rx_pkt_timestamp(dev, stats);
-
 	if ((stats->RxBufShift + stats->RxDrvInfoSize) > 0)
 		stats->bShift = 1;
 
@@ -1707,12 +1693,12 @@ void rtl92e_stop_adapter(struct net_device *dev, bool reset)
 {
 	struct r8192_priv *priv = rtllib_priv(dev);
 	int i;
-	u8	OpMode;
+	u8	op_mode;
 	u8	u1bTmp;
 	u32	ulRegRead;
 
-	OpMode = RT_OP_MODE_NO_LINK;
-	priv->rtllib->SetHwRegHandler(dev, HW_VAR_MEDIA_STATUS, &OpMode);
+	op_mode = RT_OP_MODE_NO_LINK;
+	priv->rtllib->SetHwRegHandler(dev, HW_VAR_MEDIA_STATUS, &op_mode);
 
 	if (!priv->rtllib->bSupportRemoteWakeUp) {
 		u1bTmp = 0x0;
@@ -1742,7 +1728,7 @@ void rtl92e_stop_adapter(struct net_device *dev, bool reset)
 	}
 
 	for (i = 0; i < MAX_QUEUE_SIZE; i++)
-		skb_queue_purge(&priv->rtllib->skb_waitQ[i]);
+		skb_queue_purge(&priv->rtllib->skb_waitq[i]);
 
 	skb_queue_purge(&priv->skb_queue);
 }
@@ -1767,20 +1753,17 @@ void rtl92e_update_ratr_table(struct net_device *dev)
 		ratr_value &= 0x00000FF7;
 		break;
 	case WIRELESS_MODE_N_24G:
-		if (ieee->ht_info->peer_mimo_ps == 0)
-			ratr_value &= 0x0007F007;
-		else
-			ratr_value &= 0x000FF007;
+		ratr_value &= 0x000FF007;
 		break;
 	default:
 		break;
 	}
 	ratr_value &= 0x0FFFFFFF;
 	if (ieee->ht_info->cur_tx_bw40mhz &&
-	    ieee->ht_info->bCurShortGI40MHz)
+	    ieee->ht_info->cur_short_gi_40mhz)
 		ratr_value |= 0x80000000;
 	else if (!ieee->ht_info->cur_tx_bw40mhz &&
-		  ieee->ht_info->bCurShortGI20MHz)
+		  ieee->ht_info->cur_short_gi_20mhz)
 		ratr_value |= 0x80000000;
 	rtl92e_writel(dev, RATR0 + rate_index * 4, ratr_value);
 	rtl92e_writeb(dev, UFWP, 1);
@@ -1814,7 +1797,7 @@ rtl92e_init_variables(struct net_device  *dev)
 			    IMR_MGNTDOK | IMR_COMDOK | IMR_HIGHDOK |
 			    IMR_BDOK | IMR_RXCMDOK | IMR_TIMEOUT0 |
 			    IMR_RDU | IMR_RXFOVW | IMR_TXFOVW |
-			    IMR_BcnInt | IMR_TBDOK | IMR_TBDER);
+			    IMR_TBDOK | IMR_TBDER);
 
 	priv->bfirst_after_down = false;
 }
diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c
index 4d12d7385041..e1bd4d67e862 100644
--- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c
+++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c
@@ -671,16 +671,16 @@ static void _rtl92e_phy_switch_channel_work_item(struct net_device *dev)
 	_rtl92e_phy_switch_channel(dev, priv->chan);
 }
 
-u8 rtl92e_set_channel(struct net_device *dev, u8 channel)
+void rtl92e_set_channel(struct net_device *dev, u8 channel)
 {
 	struct r8192_priv *priv = rtllib_priv(dev);
 
 	if (!priv->up) {
 		netdev_err(dev, "%s(): Driver is not initialized\n", __func__);
-		return false;
+		return;
 	}
 	if (priv->sw_chnl_in_progress)
-		return false;
+		return;
 
 	switch (priv->rtllib->mode) {
 	case WIRELESS_MODE_B:
@@ -688,7 +688,7 @@ u8 rtl92e_set_channel(struct net_device *dev, u8 channel)
 			netdev_warn(dev,
 				    "Channel %d not available in 802.11b.\n",
 				    channel);
-			return false;
+			return;
 		}
 		break;
 	case WIRELESS_MODE_G:
@@ -697,7 +697,7 @@ u8 rtl92e_set_channel(struct net_device *dev, u8 channel)
 			netdev_warn(dev,
 				    "Channel %d not available in 802.11g.\n",
 				    channel);
-			return false;
+			return;
 		}
 		break;
 	}
@@ -714,7 +714,7 @@ u8 rtl92e_set_channel(struct net_device *dev, u8 channel)
 	if (priv->up)
 		_rtl92e_phy_switch_channel_work_item(dev);
 	priv->sw_chnl_in_progress = false;
-	return true;
+	return;
 }
 
 static void _rtl92e_cck_tx_power_track_bw_switch_tssi(struct net_device *dev)
diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h
index 6c4c33ded6a9..ff4b4004b0d0 100644
--- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h
+++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h
@@ -41,7 +41,7 @@ void rtl92e_get_tx_power(struct net_device *dev);
 void rtl92e_set_tx_power(struct net_device *dev, u8 channel);
 u8 rtl92e_config_rf_path(struct net_device *dev, enum rf90_radio_path eRFPath);
 
-u8 rtl92e_set_channel(struct net_device *dev, u8 channel);
+void rtl92e_set_channel(struct net_device *dev, u8 channel);
 void rtl92e_set_bw_mode(struct net_device *dev,
 			enum ht_channel_width bandwidth,
 			enum ht_extchnl_offset Offset);
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
index 995daab906c9..6815d18a7919 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
@@ -226,16 +226,6 @@ static void _rtl92e_tx_timeout(struct net_device *dev, unsigned int txqueue)
 	netdev_info(dev, "TXTIMEOUT");
 }
 
-static void _rtl92e_set_chan(struct net_device *dev, short ch)
-{
-	struct r8192_priv *priv = rtllib_priv(dev);
-
-	priv->chan = ch;
-
-	if (priv->rf_set_chan)
-		priv->rf_set_chan(dev, priv->chan);
-}
-
 static void _rtl92e_update_cap(struct net_device *dev, u16 cap)
 {
 	struct r8192_priv *priv = rtllib_priv(dev);
@@ -297,7 +287,6 @@ static void _rtl92e_update_beacon(void *data)
 	if (ieee->ht_info->current_ht_support)
 		HT_update_self_and_peer_setting(ieee, net);
 	ieee->ht_info->current_rt2rt_long_slot_time = net->bssht.bd_rt2rt_long_slot_time;
-	ieee->ht_info->RT2RT_HT_Mode = net->bssht.rt2rt_ht_mode;
 	_rtl92e_update_cap(dev, net->capability);
 }
 
@@ -426,38 +415,6 @@ static int _rtl92e_handle_assoc_response(struct net_device *dev,
 	return 0;
 }
 
-static void _rtl92e_prepare_beacon(struct tasklet_struct *t)
-{
-	struct r8192_priv *priv = from_tasklet(priv, t,
-					       irq_prepare_beacon_tasklet);
-	struct net_device *dev = priv->rtllib->dev;
-	struct sk_buff *pskb = NULL, *pnewskb = NULL;
-	struct cb_desc *tcb_desc = NULL;
-	struct rtl8192_tx_ring *ring = NULL;
-	struct tx_desc *pdesc = NULL;
-
-	ring = &priv->tx_ring[BEACON_QUEUE];
-	pskb = __skb_dequeue(&ring->queue);
-	kfree_skb(pskb);
-
-	pnewskb = rtllib_get_beacon(priv->rtllib);
-	if (!pnewskb)
-		return;
-
-	tcb_desc = (struct cb_desc *)(pnewskb->cb + 8);
-	tcb_desc->queue_index = BEACON_QUEUE;
-	tcb_desc->data_rate = 2;
-	tcb_desc->ratr_index = 7;
-	tcb_desc->tx_dis_rate_fallback = 1;
-	tcb_desc->tx_use_drv_assinged_rate = 1;
-	skb_push(pnewskb, priv->rtllib->tx_headroom);
-
-	pdesc = &ring->desc[0];
-	rtl92e_fill_tx_desc(dev, pdesc, tcb_desc, pnewskb);
-	__skb_queue_tail(&ring->queue, pnewskb);
-	pdesc->OWN = 1;
-}
-
 void rtl92e_config_rate(struct net_device *dev, u16 *rate_config)
 {
 	struct r8192_priv *priv = rtllib_priv(dev);
@@ -685,7 +642,7 @@ static void _rtl92e_init_priv_handler(struct net_device *dev)
 	struct r8192_priv *priv = rtllib_priv(dev);
 
 	priv->rtllib->softmac_hard_start_xmit	= _rtl92e_hard_start_xmit;
-	priv->rtllib->set_chan			= _rtl92e_set_chan;
+	priv->rtllib->set_chan			= rtl92e_set_channel;
 	priv->rtllib->link_change		= rtl92e_link_change;
 	priv->rtllib->softmac_data_hard_start_xmit = _rtl92e_hard_data_xmit;
 	priv->rtllib->check_nic_enough_desc	= _rtl92e_check_nic_enough_desc;
@@ -694,7 +651,6 @@ static void _rtl92e_init_priv_handler(struct net_device *dev)
 	priv->rtllib->set_wireless_mode		= rtl92e_set_wireless_mode;
 	priv->rtllib->leisure_ps_leave		= rtl92e_leisure_ps_leave;
 	priv->rtllib->set_bw_mode_handler	= rtl92e_set_bw_mode;
-	priv->rf_set_chan			= rtl92e_set_channel;
 
 	priv->rtllib->sta_wake_up = rtl92e_hw_wakeup;
 	priv->rtllib->enter_sleep_state = rtl92e_enter_sleep;
@@ -767,7 +723,7 @@ static void _rtl92e_init_priv_variable(struct net_device *dev)
 	skb_queue_head_init(&priv->skb_queue);
 
 	for (i = 0; i < MAX_QUEUE_SIZE; i++)
-		skb_queue_head_init(&priv->rtllib->skb_waitQ[i]);
+		skb_queue_head_init(&priv->rtllib->skb_waitq[i]);
 }
 
 static void _rtl92e_init_priv_lock(struct r8192_priv *priv)
@@ -796,8 +752,6 @@ static void _rtl92e_init_priv_task(struct net_device *dev)
 	INIT_DELAYED_WORK(&priv->rtllib->hw_sleep_wq, (void *)rtl92e_hw_sleep_wq);
 	tasklet_setup(&priv->irq_rx_tasklet, _rtl92e_irq_rx_tasklet);
 	tasklet_setup(&priv->irq_tx_tasklet, _rtl92e_irq_tx_tasklet);
-	tasklet_setup(&priv->irq_prepare_beacon_tasklet,
-		      _rtl92e_prepare_beacon);
 }
 
 static short _rtl92e_get_channel_map(struct net_device *dev)
@@ -806,13 +760,6 @@ static short _rtl92e_get_channel_map(struct net_device *dev)
 
 	struct r8192_priv *priv = rtllib_priv(dev);
 
-	if (priv->chnl_plan >= COUNTRY_CODE_MAX) {
-		netdev_info(dev,
-			    "rtl819x_init:Error channel plan! Set to default.\n");
-		priv->chnl_plan = COUNTRY_CODE_FCC;
-	}
-	dot11d_init(priv->rtllib);
-	dot11d_channel_map(priv->chnl_plan, priv->rtllib);
 	for (i = 1; i <= 11; i++)
 		(priv->rtllib->active_channel_map)[i] = 1;
 	(priv->rtllib->active_channel_map)[12] = 2;
@@ -1024,21 +971,21 @@ static void _rtl92e_watchdog_wq_cb(void *data)
 		}
 	}
 	if ((ieee->link_state == MAC80211_LINKED) && (ieee->iw_mode == IW_MODE_INFRA)) {
-		if (ieee->link_detect_info.NumRxOkInPeriod > 100 ||
-		ieee->link_detect_info.NumTxOkInPeriod > 100)
+		if (ieee->link_detect_info.num_rx_ok_in_period > 100 ||
+		ieee->link_detect_info.num_tx_ok_in_period > 100)
 			bBusyTraffic = true;
 
-		if (ieee->link_detect_info.NumRxOkInPeriod > 4000 ||
-		    ieee->link_detect_info.NumTxOkInPeriod > 4000) {
+		if (ieee->link_detect_info.num_rx_ok_in_period > 4000 ||
+		    ieee->link_detect_info.num_tx_ok_in_period > 4000) {
 			bHigherBusyTraffic = true;
-			if (ieee->link_detect_info.NumRxOkInPeriod > 5000)
+			if (ieee->link_detect_info.num_rx_ok_in_period > 5000)
 				bHigherBusyRxTraffic = true;
 			else
 				bHigherBusyRxTraffic = false;
 		}
 
 		if (((ieee->link_detect_info.NumRxUnicastOkInPeriod +
-		    ieee->link_detect_info.NumTxOkInPeriod) > 8) ||
+		    ieee->link_detect_info.num_tx_ok_in_period) > 8) ||
 		    (ieee->link_detect_info.NumRxUnicastOkInPeriod > 2))
 			bEnterPS = false;
 		else
@@ -1056,8 +1003,8 @@ static void _rtl92e_watchdog_wq_cb(void *data)
 		rtl92e_leisure_ps_leave(dev);
 	}
 
-	ieee->link_detect_info.NumRxOkInPeriod = 0;
-	ieee->link_detect_info.NumTxOkInPeriod = 0;
+	ieee->link_detect_info.num_rx_ok_in_period = 0;
+	ieee->link_detect_info.num_tx_ok_in_period = 0;
 	ieee->link_detect_info.NumRxUnicastOkInPeriod = 0;
 	ieee->link_detect_info.bBusyTraffic = bBusyTraffic;
 
@@ -1240,7 +1187,7 @@ static int _rtl92e_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	tcb_desc->ratr_index = 7;
 	tcb_desc->tx_dis_rate_fallback = 1;
 	tcb_desc->tx_use_drv_assinged_rate = 1;
-	tcb_desc->bTxEnableFwCalcDur = 1;
+	tcb_desc->tx_enable_fw_calc_dur = 1;
 	skb_push(skb, priv->rtllib->tx_headroom);
 	ret = _rtl92e_tx(dev, skb);
 	if (ret != 0)
@@ -1484,17 +1431,6 @@ void rtl92e_reset_desc_ring(struct net_device *dev)
 	spin_unlock_irqrestore(&priv->irq_th_lock, flags);
 }
 
-void rtl92e_update_rx_pkt_timestamp(struct net_device *dev,
-				    struct rtllib_rx_stats *stats)
-{
-	struct r8192_priv *priv = rtllib_priv(dev);
-
-	if (stats->bIsAMPDU && !stats->bFirstMPDU)
-		stats->mac_time = priv->last_rx_desc_tsf;
-	else
-		priv->last_rx_desc_tsf = stats->mac_time;
-}
-
 long rtl92e_translate_to_dbm(struct r8192_priv *priv, u8 signal_strength_index)
 {
 	long	signal_power;
@@ -1638,9 +1574,9 @@ static void _rtl92e_tx_resume(struct net_device *dev)
 
 	for (queue_index = BK_QUEUE;
 	     queue_index < MAX_QUEUE_SIZE; queue_index++) {
-		while ((!skb_queue_empty(&ieee->skb_waitQ[queue_index])) &&
+		while ((!skb_queue_empty(&ieee->skb_waitq[queue_index])) &&
 		(priv->rtllib->check_nic_enough_desc(dev, queue_index) > 0)) {
-			skb = skb_dequeue(&ieee->skb_waitQ[queue_index]);
+			skb = skb_dequeue(&ieee->skb_waitq[queue_index]);
 			ieee->softmac_data_hard_start_xmit(skb, dev, 0);
 		}
 	}
@@ -1827,9 +1763,6 @@ static irqreturn_t _rtl92e_irq(int irq, void *netdev)
 	if (inta & IMR_ROK)
 		tasklet_schedule(&priv->irq_rx_tasklet);
 
-	if (inta & IMR_BcnInt)
-		tasklet_schedule(&priv->irq_prepare_beacon_tasklet);
-
 	if (inta & IMR_RDU) {
 		rtl92e_writel(dev, INTA_MASK,
 			      rtl92e_readl(dev, INTA_MASK) & ~IMR_RDU);
@@ -1840,22 +1773,22 @@ static irqreturn_t _rtl92e_irq(int irq, void *netdev)
 		tasklet_schedule(&priv->irq_rx_tasklet);
 
 	if (inta & IMR_BKDOK) {
-		priv->rtllib->link_detect_info.NumTxOkInPeriod++;
+		priv->rtllib->link_detect_info.num_tx_ok_in_period++;
 		_rtl92e_tx_isr(dev, BK_QUEUE);
 	}
 
 	if (inta & IMR_BEDOK) {
-		priv->rtllib->link_detect_info.NumTxOkInPeriod++;
+		priv->rtllib->link_detect_info.num_tx_ok_in_period++;
 		_rtl92e_tx_isr(dev, BE_QUEUE);
 	}
 
 	if (inta & IMR_VIDOK) {
-		priv->rtllib->link_detect_info.NumTxOkInPeriod++;
+		priv->rtllib->link_detect_info.num_tx_ok_in_period++;
 		_rtl92e_tx_isr(dev, VI_QUEUE);
 	}
 
 	if (inta & IMR_VODOK) {
-		priv->rtllib->link_detect_info.NumTxOkInPeriod++;
+		priv->rtllib->link_detect_info.num_tx_ok_in_period++;
 		_rtl92e_tx_isr(dev, VO_QUEUE);
 	}
 
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
index a4afbf3e934d..1d6d31292f41 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
@@ -34,8 +34,6 @@
 
 #include "../rtllib.h"
 
-#include "../dot11d.h"
-
 #include "r8192E_firmware.h"
 #include "r8192E_hw.h"
 
@@ -219,7 +217,6 @@ struct r8192_priv {
 
 	struct tasklet_struct		irq_rx_tasklet;
 	struct tasklet_struct		irq_tx_tasklet;
-	struct tasklet_struct		irq_prepare_beacon_tasklet;
 
 	struct mutex				wx_mutex;
 	struct mutex				rf_mutex;
@@ -228,8 +225,6 @@ struct r8192_priv {
 	struct rt_stats stats;
 	struct iw_statistics			wstats;
 
-	u8 (*rf_set_chan)(struct net_device *dev, u8 ch);
-
 	struct rx_desc *rx_ring;
 	struct sk_buff	*rx_buf[MAX_RX_COUNT];
 	dma_addr_t	rx_ring_dma;
@@ -237,8 +232,6 @@ struct r8192_priv {
 	int		rxringcount;
 	u16		rxbuffersize;
 
-	u64 last_rx_desc_tsf;
-
 	u32 receive_config;
 	u8		retry_data;
 	u8		retry_rts;
@@ -286,7 +279,6 @@ struct r8192_priv {
 	u16 eeprom_vid;
 	u16 eeprom_did;
 	u8 eeprom_customer_id;
-	u16 eeprom_chnl_plan;
 
 	u8 eeprom_tx_pwr_level_cck[14];
 	u8 eeprom_tx_pwr_level_ofdm24g[14];
@@ -312,7 +304,6 @@ struct r8192_priv {
 
 	bool tx_pwr_data_read_from_eeprom;
 
-	u16 chnl_plan;
 	u8 hw_rf_off_action;
 
 	bool rf_change_in_progress;
@@ -396,8 +387,6 @@ void rtl92e_irq_enable(struct net_device *dev);
 void rtl92e_config_rate(struct net_device *dev, u16 *rate_config);
 void rtl92e_irq_disable(struct net_device *dev);
 
-void rtl92e_update_rx_pkt_timestamp(struct net_device *dev,
-				    struct rtllib_rx_stats *stats);
 long rtl92e_translate_to_dbm(struct r8192_priv *priv, u8 signal_strength_index);
 void rtl92e_update_rx_statistics(struct r8192_priv *priv,
 				 struct rtllib_rx_stats *pprevious_stats);
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c
index 330dafd62656..92143c50c149 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c
@@ -287,9 +287,9 @@ static void _rtl92e_dm_check_rate_adaptive(struct net_device *dev)
 
 	if (priv->rtllib->link_state == MAC80211_LINKED) {
 		bshort_gi_enabled = (ht_info->cur_tx_bw40mhz &&
-				     ht_info->bCurShortGI40MHz) ||
+				     ht_info->cur_short_gi_40mhz) ||
 				    (!ht_info->cur_tx_bw40mhz &&
-				     ht_info->bCurShortGI20MHz);
+				     ht_info->cur_short_gi_20mhz);
 
 		pra->upper_rssi_threshold_ratr =
 				(pra->upper_rssi_threshold_ratr & (~BIT(31))) |
@@ -1142,7 +1142,7 @@ static void _rtl92e_dm_check_edca_turbo(struct net_device *dev)
 				if (priv->bis_cur_rdlstate ||
 				    !priv->bcurrent_turbo_EDCA) {
 					rtl92e_writel(dev, EDCAPARA_BE,
-						      edca_setting_UL[ht_info->IOTPeer]);
+						      edca_setting_UL[ht_info->iot_peer]);
 					priv->bis_cur_rdlstate = false;
 				}
 			} else {
@@ -1150,10 +1150,10 @@ static void _rtl92e_dm_check_edca_turbo(struct net_device *dev)
 				    !priv->bcurrent_turbo_EDCA) {
 					if (priv->rtllib->mode == WIRELESS_MODE_G)
 						rtl92e_writel(dev, EDCAPARA_BE,
-							      edca_setting_DL_GMode[ht_info->IOTPeer]);
+							      edca_setting_DL_GMode[ht_info->iot_peer]);
 					else
 						rtl92e_writel(dev, EDCAPARA_BE,
-							      edca_setting_DL[ht_info->IOTPeer]);
+							      edca_setting_DL[ht_info->iot_peer]);
 					priv->bis_cur_rdlstate = true;
 				}
 			}
@@ -1164,17 +1164,17 @@ static void _rtl92e_dm_check_edca_turbo(struct net_device *dev)
 				    !priv->bcurrent_turbo_EDCA) {
 					if (priv->rtllib->mode == WIRELESS_MODE_G)
 						rtl92e_writel(dev, EDCAPARA_BE,
-							      edca_setting_DL_GMode[ht_info->IOTPeer]);
+							      edca_setting_DL_GMode[ht_info->iot_peer]);
 					else
 						rtl92e_writel(dev, EDCAPARA_BE,
-							      edca_setting_DL[ht_info->IOTPeer]);
+							      edca_setting_DL[ht_info->iot_peer]);
 					priv->bis_cur_rdlstate = true;
 				}
 			} else {
 				if (priv->bis_cur_rdlstate ||
 				    !priv->bcurrent_turbo_EDCA) {
 					rtl92e_writel(dev, EDCAPARA_BE,
-						      edca_setting_UL[ht_info->IOTPeer]);
+						      edca_setting_UL[ht_info->iot_peer]);
 					priv->bis_cur_rdlstate = false;
 				}
 			}
@@ -1217,7 +1217,7 @@ static void _rtl92e_dm_cts_to_self(struct net_device *dev)
 		ht_info->iot_action &= ~HT_IOT_ACT_FORCED_CTS2SELF;
 		return;
 	}
-	if (ht_info->IOTPeer == HT_IOT_PEER_BROADCOM) {
+	if (ht_info->iot_peer == HT_IOT_PEER_BROADCOM) {
 		curTxOkCnt = priv->stats.txbytesunicast - lastTxOkCnt;
 		curRxOkCnt = priv->stats.rxbytesunicast - lastRxOkCnt;
 		if (curRxOkCnt > 4 * curTxOkCnt)
@@ -1713,7 +1713,7 @@ static void _rtl92e_dm_check_fsync(struct net_device *dev)
 	static u8 reg_c38_State = RegC38_Default;
 
 	if (priv->rtllib->link_state == MAC80211_LINKED &&
-	    priv->rtllib->ht_info->IOTPeer == HT_IOT_PEER_BROADCOM) {
+	    priv->rtllib->ht_info->iot_peer == HT_IOT_PEER_BROADCOM) {
 		if (priv->rtllib->bfsync_enable == 0) {
 			switch (priv->rtllib->fsync_state) {
 			case Default_Fsync:
@@ -1819,7 +1819,7 @@ static void _rtl92e_dm_dynamic_tx_power(struct net_device *dev)
 		priv->dynamic_tx_low_pwr = false;
 		return;
 	}
-	if ((priv->rtllib->ht_info->IOTPeer == HT_IOT_PEER_ATHEROS) &&
+	if ((priv->rtllib->ht_info->iot_peer == HT_IOT_PEER_ATHEROS) &&
 	    (priv->rtllib->mode == WIRELESS_MODE_G)) {
 		txhipower_threshold = TX_POWER_ATHEROAP_THRESH_HIGH;
 		txlowpower_threshold = TX_POWER_ATHEROAP_THRESH_LOW;
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_wx.c b/drivers/staging/rtl8192e/rtl8192e/rtl_wx.c
index 4371ab1239ee..4c884c5277f9 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_wx.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_wx.c
@@ -158,28 +158,6 @@ static int _rtl92e_wx_set_mode(struct net_device *dev,
 	return ret;
 }
 
-struct  iw_range_with_scan_capa {
-	/* Informative stuff (to choose between different interface) */
-	__u32	   throughput;     /* To give an idea... */
-	/* In theory this value should be the maximum benchmarked
-	 * TCP/IP throughput, because with most of these devices the
-	 * bit rate is meaningless (overhead an co) to estimate how
-	 * fast the connection will go and pick the fastest one.
-	 * I suggest people to play with Netperf or any benchmark...
-	 */
-
-	/* NWID (or domain id) */
-	__u32	   min_nwid;	/* Minimal NWID we are able to set */
-	__u32	   max_nwid;	/* Maximal NWID we are able to set */
-
-	/* Old Frequency (backward compat - moved lower ) */
-	__u16	   old_num_channels;
-	__u8	    old_num_frequency;
-
-	/* Scan capabilities */
-	__u8	    scan_capa;
-};
-
 static int _rtl92e_wx_get_range(struct net_device *dev,
 				struct iw_request_info *info,
 				union iwreq_data *wrqu, char *extra)
diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index 4af8055d2489..ee9ce392155c 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -23,35 +23,35 @@ static void deactivate_ba_entry(struct rtllib_device *ieee, struct ba_record *ba
 	del_timer_sync(&ba->timer);
 }
 
-static u8 tx_ts_delete_ba(struct rtllib_device *ieee, struct tx_ts_record *pTxTs)
+static u8 tx_ts_delete_ba(struct rtllib_device *ieee, struct tx_ts_record *ts)
 {
-	struct ba_record *admitted_ba = &pTxTs->TxAdmittedBARecord;
-	struct ba_record *pending_ba = &pTxTs->TxPendingBARecord;
-	u8 bSendDELBA = false;
+	struct ba_record *admitted_ba = &ts->tx_admitted_ba_record;
+	struct ba_record *pending_ba = &ts->tx_pending_ba_record;
+	u8 send_del_ba = false;
 
 	if (pending_ba->b_valid) {
 		deactivate_ba_entry(ieee, pending_ba);
-		bSendDELBA = true;
+		send_del_ba = true;
 	}
 
 	if (admitted_ba->b_valid) {
 		deactivate_ba_entry(ieee, admitted_ba);
-		bSendDELBA = true;
+		send_del_ba = true;
 	}
-	return bSendDELBA;
+	return send_del_ba;
 }
 
 static u8 rx_ts_delete_ba(struct rtllib_device *ieee, struct rx_ts_record *ts)
 {
 	struct ba_record *ba = &ts->rx_admitted_ba_record;
-	u8			bSendDELBA = false;
+	u8			send_del_ba = false;
 
 	if (ba->b_valid) {
 		deactivate_ba_entry(ieee, ba);
-		bSendDELBA = true;
+		send_del_ba = true;
 	}
 
-	return bSendDELBA;
+	return send_del_ba;
 }
 
 void rtllib_reset_ba_entry(struct ba_record *ba)
@@ -68,7 +68,7 @@ static struct sk_buff *rtllib_ADDBA(struct rtllib_device *ieee, u8 *dst,
 				    u16 status_code, u8 type)
 {
 	struct sk_buff *skb = NULL;
-	struct ieee80211_hdr_3addr *BAReq = NULL;
+	struct ieee80211_hdr_3addr *ba_req = NULL;
 	u8 *tag = NULL;
 	u16 len = ieee->tx_headroom + 9;
 
@@ -87,13 +87,13 @@ static struct sk_buff *rtllib_ADDBA(struct rtllib_device *ieee, u8 *dst,
 
 	skb_reserve(skb, ieee->tx_headroom);
 
-	BAReq = skb_put(skb, sizeof(struct ieee80211_hdr_3addr));
+	ba_req = skb_put(skb, sizeof(struct ieee80211_hdr_3addr));
 
-	ether_addr_copy(BAReq->addr1, dst);
-	ether_addr_copy(BAReq->addr2, ieee->dev->dev_addr);
+	ether_addr_copy(ba_req->addr1, dst);
+	ether_addr_copy(ba_req->addr2, ieee->dev->dev_addr);
 
-	ether_addr_copy(BAReq->addr3, ieee->current_network.bssid);
-	BAReq->frame_control = cpu_to_le16(IEEE80211_STYPE_ACTION);
+	ether_addr_copy(ba_req->addr3, ieee->current_network.bssid);
+	ba_req->frame_control = cpu_to_le16(IEEE80211_STYPE_ACTION);
 
 	tag = skb_put(skb, 9);
 	*tag++ = ACT_CAT_BA;
@@ -127,9 +127,9 @@ static struct sk_buff *rtllib_DELBA(struct rtllib_device *ieee, u8 *dst,
 				    struct ba_record *ba,
 				    enum tr_select TxRxSelect, u16 reason_code)
 {
-	union delba_param_set DelbaParamSet;
+	union delba_param_set del_ba_param_set;
 	struct sk_buff *skb = NULL;
-	struct ieee80211_hdr_3addr *Delba = NULL;
+	struct ieee80211_hdr_3addr *del_ba = NULL;
 	u8 *tag = NULL;
 	u16 len = 6 + ieee->tx_headroom;
 
@@ -137,10 +137,10 @@ static struct sk_buff *rtllib_DELBA(struct rtllib_device *ieee, u8 *dst,
 		netdev_dbg(ieee->dev, "%s(): reason_code(%d) sentd to: %pM\n",
 			   __func__, reason_code, dst);
 
-	memset(&DelbaParamSet, 0, 2);
+	memset(&del_ba_param_set, 0, 2);
 
-	DelbaParamSet.field.initiator = (TxRxSelect == TX_DIR) ? 1 : 0;
-	DelbaParamSet.field.tid	= ba->ba_param_set.field.tid;
+	del_ba_param_set.field.initiator = (TxRxSelect == TX_DIR) ? 1 : 0;
+	del_ba_param_set.field.tid	= ba->ba_param_set.field.tid;
 
 	skb = dev_alloc_skb(len + sizeof(struct ieee80211_hdr_3addr));
 	if (!skb)
@@ -148,19 +148,19 @@ static struct sk_buff *rtllib_DELBA(struct rtllib_device *ieee, u8 *dst,
 
 	skb_reserve(skb, ieee->tx_headroom);
 
-	Delba = skb_put(skb, sizeof(struct ieee80211_hdr_3addr));
+	del_ba = skb_put(skb, sizeof(struct ieee80211_hdr_3addr));
 
-	ether_addr_copy(Delba->addr1, dst);
-	ether_addr_copy(Delba->addr2, ieee->dev->dev_addr);
-	ether_addr_copy(Delba->addr3, ieee->current_network.bssid);
-	Delba->frame_control = cpu_to_le16(IEEE80211_STYPE_ACTION);
+	ether_addr_copy(del_ba->addr1, dst);
+	ether_addr_copy(del_ba->addr2, ieee->dev->dev_addr);
+	ether_addr_copy(del_ba->addr3, ieee->current_network.bssid);
+	del_ba->frame_control = cpu_to_le16(IEEE80211_STYPE_ACTION);
 
 	tag = skb_put(skb, 6);
 
 	*tag++ = ACT_CAT_BA;
 	*tag++ = ACT_DELBA;
 
-	put_unaligned_le16(DelbaParamSet.short_data, tag);
+	put_unaligned_le16(del_ba_param_set.short_data, tag);
 	tag += 2;
 
 	put_unaligned_le16(reason_code, tag);
@@ -215,11 +215,11 @@ int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb)
 {
 	struct ieee80211_hdr_3addr *req = NULL;
 	u16 rc = 0;
-	u8 *dst = NULL, *pDialogToken = NULL, *tag = NULL;
+	u8 *dst = NULL, *dialog_token = NULL, *tag = NULL;
 	struct ba_record *ba = NULL;
-	union ba_param_set *pBaParamSet = NULL;
-	u16 *pBaTimeoutVal = NULL;
-	union sequence_control *pBaStartSeqCtrl = NULL;
+	union ba_param_set *ba_param_set = NULL;
+	u16 *ba_timeout_value = NULL;
+	union sequence_control *ba_start_seq_ctrl = NULL;
 	struct rx_ts_record *ts = NULL;
 
 	if (skb->len < sizeof(struct ieee80211_hdr_3addr) + 9) {
@@ -238,10 +238,10 @@ int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb)
 	tag = (u8 *)req;
 	dst = (u8 *)(&req->addr2[0]);
 	tag += sizeof(struct ieee80211_hdr_3addr);
-	pDialogToken = tag + 2;
-	pBaParamSet = (union ba_param_set *)(tag + 3);
-	pBaTimeoutVal = (u16 *)(tag + 5);
-	pBaStartSeqCtrl = (union sequence_control *)(req + 7);
+	dialog_token = tag + 2;
+	ba_param_set = (union ba_param_set *)(tag + 3);
+	ba_timeout_value = (u16 *)(tag + 5);
+	ba_start_seq_ctrl = (union sequence_control *)(req + 7);
 
 	if (!ieee->current_network.qos_data.active ||
 	    !ieee->ht_info->current_ht_support ||
@@ -254,14 +254,14 @@ int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb)
 		goto OnADDBAReq_Fail;
 	}
 	if (!rtllib_get_ts(ieee, (struct ts_common_info **)&ts, dst,
-		   (u8)(pBaParamSet->field.tid), RX_DIR, true)) {
+		   (u8)(ba_param_set->field.tid), RX_DIR, true)) {
 		rc = ADDBA_STATUS_REFUSED;
 		netdev_warn(ieee->dev, "%s(): can't get TS\n", __func__);
 		goto OnADDBAReq_Fail;
 	}
 	ba = &ts->rx_admitted_ba_record;
 
-	if (pBaParamSet->field.ba_policy == BA_POLICY_DELAYED) {
+	if (ba_param_set->field.ba_policy == BA_POLICY_DELAYED) {
 		rc = ADDBA_STATUS_INVALID_PARAM;
 		netdev_warn(ieee->dev, "%s(): BA Policy is not correct\n",
 			    __func__);
@@ -271,10 +271,10 @@ int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb)
 	rtllib_FlushRxTsPendingPkts(ieee, ts);
 
 	deactivate_ba_entry(ieee, ba);
-	ba->dialog_token = *pDialogToken;
-	ba->ba_param_set = *pBaParamSet;
-	ba->ba_timeout_value = *pBaTimeoutVal;
-	ba->ba_start_seq_ctrl = *pBaStartSeqCtrl;
+	ba->dialog_token = *dialog_token;
+	ba->ba_param_set = *ba_param_set;
+	ba->ba_timeout_value = *ba_timeout_value;
+	ba->ba_start_seq_ctrl = *ba_start_seq_ctrl;
 
 	if (ieee->GetHalfNmodeSupportByAPsHandler(ieee->dev) ||
 	   (ieee->ht_info->iot_action & HT_IOT_ACT_ALLOW_PEER_AGG_ONE_PKT))
@@ -291,9 +291,9 @@ OnADDBAReq_Fail:
 	{
 		struct ba_record BA;
 
-		BA.ba_param_set = *pBaParamSet;
-		BA.ba_timeout_value = *pBaTimeoutVal;
-		BA.dialog_token = *pDialogToken;
+		BA.ba_param_set = *ba_param_set;
+		BA.ba_timeout_value = *ba_timeout_value;
+		BA.dialog_token = *dialog_token;
 		BA.ba_param_set.field.ba_policy = BA_POLICY_IMMEDIATE;
 		rtllib_send_ADDBARsp(ieee, dst, &BA, rc);
 		return 0;
@@ -303,11 +303,11 @@ OnADDBAReq_Fail:
 int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 {
 	struct ieee80211_hdr_3addr *rsp = NULL;
-	struct ba_record *pending_ba, *pAdmittedBA;
+	struct ba_record *pending_ba, *admitted_ba;
 	struct tx_ts_record *ts = NULL;
-	u8 *dst = NULL, *pDialogToken = NULL, *tag = NULL;
-	u16 *status_code = NULL, *pBaTimeoutVal = NULL;
-	union ba_param_set *pBaParamSet = NULL;
+	u8 *dst = NULL, *dialog_token = NULL, *tag = NULL;
+	u16 *status_code = NULL, *ba_timeout_value = NULL;
+	union ba_param_set *ba_param_set = NULL;
 	u16			reason_code;
 
 	if (skb->len < sizeof(struct ieee80211_hdr_3addr) + 9) {
@@ -320,40 +320,40 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 	tag = (u8 *)rsp;
 	dst = (u8 *)(&rsp->addr2[0]);
 	tag += sizeof(struct ieee80211_hdr_3addr);
-	pDialogToken = tag + 2;
+	dialog_token = tag + 2;
 	status_code = (u16 *)(tag + 3);
-	pBaParamSet = (union ba_param_set *)(tag + 5);
-	pBaTimeoutVal = (u16 *)(tag + 7);
+	ba_param_set = (union ba_param_set *)(tag + 5);
+	ba_timeout_value = (u16 *)(tag + 7);
 
 	if (!ieee->current_network.qos_data.active ||
 	    !ieee->ht_info->current_ht_support ||
-	    !ieee->ht_info->bCurrentAMPDUEnable) {
+	    !ieee->ht_info->current_ampdu_enable) {
 		netdev_warn(ieee->dev,
 			    "reject to ADDBA_RSP as some capability is not ready(%d, %d, %d)\n",
 			    ieee->current_network.qos_data.active,
 			    ieee->ht_info->current_ht_support,
-			    ieee->ht_info->bCurrentAMPDUEnable);
+			    ieee->ht_info->current_ampdu_enable);
 		reason_code = DELBA_REASON_UNKNOWN_BA;
 		goto OnADDBARsp_Reject;
 	}
 
 	if (!rtllib_get_ts(ieee, (struct ts_common_info **)&ts, dst,
-		   (u8)(pBaParamSet->field.tid), TX_DIR, false)) {
+		   (u8)(ba_param_set->field.tid), TX_DIR, false)) {
 		netdev_warn(ieee->dev, "%s(): can't get TS\n", __func__);
 		reason_code = DELBA_REASON_UNKNOWN_BA;
 		goto OnADDBARsp_Reject;
 	}
 
-	ts->bAddBaReqInProgress = false;
-	pending_ba = &ts->TxPendingBARecord;
-	pAdmittedBA = &ts->TxAdmittedBARecord;
+	ts->add_ba_req_in_progress = false;
+	pending_ba = &ts->tx_pending_ba_record;
+	admitted_ba = &ts->tx_admitted_ba_record;
 
-	if (pAdmittedBA->b_valid) {
+	if (admitted_ba->b_valid) {
 		netdev_dbg(ieee->dev, "%s(): ADDBA response already admitted\n",
 			   __func__);
 		return -1;
 	} else if (!pending_ba->b_valid ||
-		   (*pDialogToken != pending_ba->dialog_token)) {
+		   (*dialog_token != pending_ba->dialog_token)) {
 		netdev_warn(ieee->dev,
 			    "%s(): ADDBA Rsp. BA invalid, DELBA!\n",
 			    __func__);
@@ -367,22 +367,22 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 	}
 
 	if (*status_code == ADDBA_STATUS_SUCCESS) {
-		if (pBaParamSet->field.ba_policy == BA_POLICY_DELAYED) {
-			ts->bAddBaReqDelayed = true;
-			deactivate_ba_entry(ieee, pAdmittedBA);
+		if (ba_param_set->field.ba_policy == BA_POLICY_DELAYED) {
+			ts->add_ba_req_delayed = true;
+			deactivate_ba_entry(ieee, admitted_ba);
 			reason_code = DELBA_REASON_END_BA;
 			goto OnADDBARsp_Reject;
 		}
 
-		pAdmittedBA->dialog_token = *pDialogToken;
-		pAdmittedBA->ba_timeout_value = *pBaTimeoutVal;
-		pAdmittedBA->ba_start_seq_ctrl = pending_ba->ba_start_seq_ctrl;
-		pAdmittedBA->ba_param_set = *pBaParamSet;
-		deactivate_ba_entry(ieee, pAdmittedBA);
-		activate_ba_entry(pAdmittedBA, *pBaTimeoutVal);
+		admitted_ba->dialog_token = *dialog_token;
+		admitted_ba->ba_timeout_value = *ba_timeout_value;
+		admitted_ba->ba_start_seq_ctrl = pending_ba->ba_start_seq_ctrl;
+		admitted_ba->ba_param_set = *ba_param_set;
+		deactivate_ba_entry(ieee, admitted_ba);
+		activate_ba_entry(admitted_ba, *ba_timeout_value);
 	} else {
-		ts->bAddBaReqDelayed = true;
-		ts->bDisable_AddBa = true;
+		ts->add_ba_req_delayed = true;
+		ts->disable_add_ba = true;
 		reason_code = DELBA_REASON_END_BA;
 		goto OnADDBARsp_Reject;
 	}
@@ -393,7 +393,7 @@ OnADDBARsp_Reject:
 	{
 		struct ba_record BA;
 
-		BA.ba_param_set = *pBaParamSet;
+		BA.ba_param_set = *ba_param_set;
 		rtllib_send_DELBA(ieee, dst, &BA, TX_DIR, reason_code);
 		return 0;
 	}
@@ -402,7 +402,7 @@ OnADDBARsp_Reject:
 int rtllib_rx_DELBA(struct rtllib_device *ieee, struct sk_buff *skb)
 {
 	struct ieee80211_hdr_3addr *delba = NULL;
-	union delba_param_set *pDelBaParamSet = NULL;
+	union delba_param_set *del_ba_param_set = NULL;
 	u8 *dst = NULL;
 
 	if (skb->len < sizeof(struct ieee80211_hdr_3addr) + 6) {
@@ -427,46 +427,46 @@ int rtllib_rx_DELBA(struct rtllib_device *ieee, struct sk_buff *skb)
 #endif
 	delba = (struct ieee80211_hdr_3addr *)skb->data;
 	dst = (u8 *)(&delba->addr2[0]);
-	pDelBaParamSet = (union delba_param_set *)&delba->seq_ctrl + 2;
+	del_ba_param_set = (union delba_param_set *)&delba->seq_ctrl + 2;
 
-	if (pDelBaParamSet->field.initiator == 1) {
+	if (del_ba_param_set->field.initiator == 1) {
 		struct rx_ts_record *ts;
 
 		if (!rtllib_get_ts(ieee, (struct ts_common_info **)&ts, dst,
-			   (u8)pDelBaParamSet->field.tid, RX_DIR, false)) {
+			   (u8)del_ba_param_set->field.tid, RX_DIR, false)) {
 			netdev_warn(ieee->dev,
 				    "%s(): can't get TS for RXTS. dst:%pM TID:%d\n",
 				    __func__, dst,
-				    (u8)pDelBaParamSet->field.tid);
+				    (u8)del_ba_param_set->field.tid);
 			return -1;
 		}
 
 		rx_ts_delete_ba(ieee, ts);
 	} else {
-		struct tx_ts_record *pTxTs;
+		struct tx_ts_record *ts;
 
-		if (!rtllib_get_ts(ieee, (struct ts_common_info **)&pTxTs, dst,
-			   (u8)pDelBaParamSet->field.tid, TX_DIR, false)) {
+		if (!rtllib_get_ts(ieee, (struct ts_common_info **)&ts, dst,
+			   (u8)del_ba_param_set->field.tid, TX_DIR, false)) {
 			netdev_warn(ieee->dev, "%s(): can't get TS for TXTS\n",
 				    __func__);
 			return -1;
 		}
 
-		pTxTs->bUsingBa = false;
-		pTxTs->bAddBaReqInProgress = false;
-		pTxTs->bAddBaReqDelayed = false;
-		del_timer_sync(&pTxTs->TsAddBaTimer);
-		tx_ts_delete_ba(ieee, pTxTs);
+		ts->using_ba = false;
+		ts->add_ba_req_in_progress = false;
+		ts->add_ba_req_delayed = false;
+		del_timer_sync(&ts->ts_add_ba_timer);
+		tx_ts_delete_ba(ieee, ts);
 	}
 	return 0;
 }
 
 void rtllib_ts_init_add_ba(struct rtllib_device *ieee, struct tx_ts_record *ts,
-			   u8 policy, u8	bOverwritePending)
+			   u8 policy, u8	overwrite_pending)
 {
-	struct ba_record *ba = &ts->TxPendingBARecord;
+	struct ba_record *ba = &ts->tx_pending_ba_record;
 
-	if (ba->b_valid && !bOverwritePending)
+	if (ba->b_valid && !overwrite_pending)
 		return;
 
 	deactivate_ba_entry(ieee, ba);
@@ -474,35 +474,35 @@ void rtllib_ts_init_add_ba(struct rtllib_device *ieee, struct tx_ts_record *ts,
 	ba->dialog_token++;
 	ba->ba_param_set.field.amsdu_support = 0;
 	ba->ba_param_set.field.ba_policy = policy;
-	ba->ba_param_set.field.tid = ts->TsCommonInfo.TSpec.ucTSID;
+	ba->ba_param_set.field.tid = ts->ts_common_info.tspec.ts_id;
 	ba->ba_param_set.field.buffer_size = 32;
 	ba->ba_timeout_value = 0;
-	ba->ba_start_seq_ctrl.field.seq_num = (ts->TxCurSeq + 3) % 4096;
+	ba->ba_start_seq_ctrl.field.seq_num = (ts->tx_cur_seq + 3) % 4096;
 
 	activate_ba_entry(ba, BA_SETUP_TIMEOUT);
 
-	rtllib_send_ADDBAReq(ieee, ts->TsCommonInfo.addr, ba);
+	rtllib_send_ADDBAReq(ieee, ts->ts_common_info.addr, ba);
 }
 
 void rtllib_ts_init_del_ba(struct rtllib_device *ieee,
-			   struct ts_common_info *pTsCommonInfo,
+			   struct ts_common_info *ts_common_info,
 			   enum tr_select TxRxSelect)
 {
 	if (TxRxSelect == TX_DIR) {
-		struct tx_ts_record *pTxTs =
-			 (struct tx_ts_record *)pTsCommonInfo;
-
-		if (tx_ts_delete_ba(ieee, pTxTs))
-			rtllib_send_DELBA(ieee, pTsCommonInfo->addr,
-					  (pTxTs->TxAdmittedBARecord.b_valid) ?
-					 (&pTxTs->TxAdmittedBARecord) :
-					(&pTxTs->TxPendingBARecord),
+		struct tx_ts_record *ts =
+			 (struct tx_ts_record *)ts_common_info;
+
+		if (tx_ts_delete_ba(ieee, ts))
+			rtllib_send_DELBA(ieee, ts_common_info->addr,
+					  (ts->tx_admitted_ba_record.b_valid) ?
+					 (&ts->tx_admitted_ba_record) :
+					(&ts->tx_pending_ba_record),
 					 TxRxSelect, DELBA_REASON_END_BA);
 	} else if (TxRxSelect == RX_DIR) {
 		struct rx_ts_record *ts =
-				 (struct rx_ts_record *)pTsCommonInfo;
+				 (struct rx_ts_record *)ts_common_info;
 		if (rx_ts_delete_ba(ieee, ts))
-			rtllib_send_DELBA(ieee, pTsCommonInfo->addr,
+			rtllib_send_DELBA(ieee, ts_common_info->addr,
 					  &ts->rx_admitted_ba_record,
 					  TxRxSelect, DELBA_REASON_END_BA);
 	}
@@ -510,23 +510,23 @@ void rtllib_ts_init_del_ba(struct rtllib_device *ieee,
 
 void rtllib_ba_setup_timeout(struct timer_list *t)
 {
-	struct tx_ts_record *pTxTs = from_timer(pTxTs, t,
-					      TxPendingBARecord.timer);
+	struct tx_ts_record *ts = from_timer(ts, t,
+					      tx_pending_ba_record.timer);
 
-	pTxTs->bAddBaReqInProgress = false;
-	pTxTs->bAddBaReqDelayed = true;
-	pTxTs->TxPendingBARecord.b_valid = false;
+	ts->add_ba_req_in_progress = false;
+	ts->add_ba_req_delayed = true;
+	ts->tx_pending_ba_record.b_valid = false;
 }
 
 void rtllib_tx_ba_inact_timeout(struct timer_list *t)
 {
-	struct tx_ts_record *pTxTs = from_timer(pTxTs, t,
-					      TxAdmittedBARecord.timer);
-	struct rtllib_device *ieee = container_of(pTxTs, struct rtllib_device,
-				     TxTsRecord[pTxTs->num]);
-	tx_ts_delete_ba(ieee, pTxTs);
-	rtllib_send_DELBA(ieee, pTxTs->TsCommonInfo.addr,
-			  &pTxTs->TxAdmittedBARecord, TX_DIR,
+	struct tx_ts_record *ts = from_timer(ts, t,
+					      tx_admitted_ba_record.timer);
+	struct rtllib_device *ieee = container_of(ts, struct rtllib_device,
+				     tx_ts_records[ts->num]);
+	tx_ts_delete_ba(ieee, ts);
+	rtllib_send_DELBA(ieee, ts->ts_common_info.addr,
+			  &ts->tx_admitted_ba_record, TX_DIR,
 			  DELBA_REASON_TIMEOUT);
 }
 
@@ -535,7 +535,7 @@ void rtllib_rx_ba_inact_timeout(struct timer_list *t)
 	struct rx_ts_record *ts = from_timer(ts, t,
 					      rx_admitted_ba_record.timer);
 	struct rtllib_device *ieee = container_of(ts, struct rtllib_device,
-				     RxTsRecord[ts->num]);
+				     rx_ts_records[ts->num]);
 
 	rx_ts_delete_ba(ieee, ts);
 	rtllib_send_DELBA(ieee, ts->ts_common_info.addr,
diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index f8eb4d553fe0..68577bffb936 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -94,51 +94,32 @@ enum ht_aggre_mode {
 struct rt_hi_throughput {
 	u8 enable_ht;
 	u8 current_ht_support;
-	u8 bRegBW40MHz;
-	u8 bCurBW40MHz;
-	u8 bRegShortGI40MHz;
-	u8 bCurShortGI40MHz;
-	u8 bRegShortGI20MHz;
-	u8 bCurShortGI20MHz;
-	u8 bRegSuppCCK;
-	u8 bCurSuppCCK;
-	enum ht_spec_ver ePeerHTSpecVer;
+	u8 cur_bw_40mhz;
+	u8 cur_short_gi_40mhz;
+	u8 cur_short_gi_20mhz;
+	enum ht_spec_ver peer_ht_spec_ver;
 	struct ht_capab_ele SelfHTCap;
-	struct ht_info_ele SelfHTInfo;
 	u8 PeerHTCapBuf[32];
 	u8 PeerHTInfoBuf[32];
-	u8 bAMSDU_Support;
-	u16 nAMSDU_MaxSize;
-	u8 bCurrent_AMSDU_Support;
-	u16 nCurrent_AMSDU_MaxSize;
-	u8 bAMPDUEnable;
-	u8 bCurrentAMPDUEnable;
-	u8 AMPDU_Factor;
+	u8 ampdu_enable;
+	u8 current_ampdu_enable;
+	u8 ampdu_factor;
 	u8 CurrentAMPDUFactor;
-	u8 MPDU_Density;
 	u8 current_mpdu_density;
-	enum ht_aggre_mode ForcedAMPDUMode;
 	u8 forced_ampdu_factor;
 	u8 forced_mpdu_density;
-	enum ht_aggre_mode ForcedAMSDUMode;
-	u8 forced_short_gi;
 	u8 current_op_mode;
-	u8 self_mimo_ps;
-	u8 peer_mimo_ps;
 	enum ht_extchnl_offset CurSTAExtChnlOffset;
 	u8 cur_tx_bw40mhz;
 	u8 sw_bw_in_progress;
-	u8 reg_rt2rt_aggregation;
-	u8 RT2RT_HT_Mode;
 	u8 current_rt2rt_aggregation;
 	u8 current_rt2rt_long_slot_time;
 	u8 sz_rt2rt_agg_buf[10];
-	u8 reg_rx_reorder_enable;
 	u8 cur_rx_reorder_enable;
 	u8 rx_reorder_win_size;
 	u8 rx_reorder_pending_time;
 	u16 rx_reorder_drop_counter;
-	u8 IOTPeer;
+	u8 iot_peer;
 	u32 iot_action;
 	u8 iot_ra_func;
 } __packed;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index e607bccc079a..6d0912f90198 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -71,75 +71,55 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
-	ht_info->bRegShortGI20MHz = 1;
-	ht_info->bRegShortGI40MHz = 1;
+	ht_info->ampdu_enable = 1;
+	ht_info->ampdu_factor = 2;
 
-	ht_info->bRegBW40MHz = 1;
-
-	if (ht_info->bRegBW40MHz)
-		ht_info->bRegSuppCCK = 1;
-	else
-		ht_info->bRegSuppCCK = true;
-
-	ht_info->nAMSDU_MaxSize = 7935UL;
-	ht_info->bAMSDU_Support = 0;
-
-	ht_info->bAMPDUEnable = 1;
-	ht_info->AMPDU_Factor = 2;
-	ht_info->MPDU_Density = 0;
-
-	ht_info->self_mimo_ps = 3;
-	if (ht_info->self_mimo_ps == 2)
-		ht_info->self_mimo_ps = 3;
 	ieee->tx_dis_rate_fallback = 0;
 	ieee->tx_use_drv_assinged_rate = 0;
 
-	ieee->bTxEnableFwCalcDur = 1;
-
-	ht_info->reg_rt2rt_aggregation = 1;
+	ieee->tx_enable_fw_calc_dur = 1;
 
-	ht_info->reg_rx_reorder_enable = 1;
 	ht_info->rx_reorder_win_size = 64;
 	ht_info->rx_reorder_pending_time = 30;
 }
 
-static u16 HTMcsToDataRate(struct rtllib_device *ieee, u8 nMcsRate)
+static u16 ht_mcs_to_data_rate(struct rtllib_device *ieee, u8 mcs_rate)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
-	u8	is40MHz = (ht_info->bCurBW40MHz) ? 1 : 0;
-	u8	isShortGI = (ht_info->bCurBW40MHz) ?
-			    ((ht_info->bCurShortGI40MHz) ? 1 : 0) :
-			    ((ht_info->bCurShortGI20MHz) ? 1 : 0);
-	return MCS_DATA_RATE[is40MHz][isShortGI][(nMcsRate & 0x7f)];
+	u8	is40MHz = (ht_info->cur_bw_40mhz) ? 1 : 0;
+	u8	isShortGI = (ht_info->cur_bw_40mhz) ?
+			    ((ht_info->cur_short_gi_40mhz) ? 1 : 0) :
+			    ((ht_info->cur_short_gi_20mhz) ? 1 : 0);
+	return MCS_DATA_RATE[is40MHz][isShortGI][(mcs_rate & 0x7f)];
 }
 
-u16  TxCountToDataRate(struct rtllib_device *ieee, u8 nDataRate)
+u16  tx_count_to_data_rate(struct rtllib_device *ieee, u8 data_rate)
 {
-	u16	CCKOFDMRate[12] = {0x02, 0x04, 0x0b, 0x16, 0x0c, 0x12, 0x18,
+	u16	cck_of_dm_rate[12] = {0x02, 0x04, 0x0b, 0x16, 0x0c, 0x12, 0x18,
 				   0x24, 0x30, 0x48, 0x60, 0x6c};
 	u8	is40MHz = 0;
 	u8	isShortGI = 0;
 
-	if (nDataRate < 12)
-		return CCKOFDMRate[nDataRate];
-	if (nDataRate >= 0x10 && nDataRate <= 0x1f) {
+	if (data_rate < 12)
+		return cck_of_dm_rate[data_rate];
+	if (data_rate >= 0x10 && data_rate <= 0x1f) {
 		is40MHz = 0;
 		isShortGI = 0;
-	} else if (nDataRate >= 0x20  && nDataRate <= 0x2f) {
+	} else if (data_rate >= 0x20  && data_rate <= 0x2f) {
 		is40MHz = 1;
 		isShortGI = 0;
-	} else if (nDataRate >= 0x30  && nDataRate <= 0x3f) {
+	} else if (data_rate >= 0x30  && data_rate <= 0x3f) {
 		is40MHz = 0;
 		isShortGI = 1;
-	} else if (nDataRate >= 0x40  && nDataRate <= 0x4f) {
+	} else if (data_rate >= 0x40  && data_rate <= 0x4f) {
 		is40MHz = 1;
 		isShortGI = 1;
 	}
-	return MCS_DATA_RATE[is40MHz][isShortGI][nDataRate & 0xf];
+	return MCS_DATA_RATE[is40MHz][isShortGI][data_rate & 0xf];
 }
 
-bool IsHTHalfNmodeAPs(struct rtllib_device *ieee)
+bool is_ht_half_nmode_aps(struct rtllib_device *ieee)
 {
 	bool			retValue = false;
 	struct rtllib_network *net = &ieee->current_network;
@@ -164,187 +144,171 @@ bool IsHTHalfNmodeAPs(struct rtllib_device *ieee)
 	return retValue;
 }
 
-static void HTIOTPeerDetermine(struct rtllib_device *ieee)
+static void ht_iot_peer_determine(struct rtllib_device *ieee)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 	struct rtllib_network *net = &ieee->current_network;
 
 	if (net->bssht.bd_rt2rt_aggregation) {
-		ht_info->IOTPeer = HT_IOT_PEER_REALTEK;
+		ht_info->iot_peer = HT_IOT_PEER_REALTEK;
 		if (net->bssht.rt2rt_ht_mode & RT_HT_CAP_USE_92SE)
-			ht_info->IOTPeer = HT_IOT_PEER_REALTEK_92SE;
+			ht_info->iot_peer = HT_IOT_PEER_REALTEK_92SE;
 		if (net->bssht.rt2rt_ht_mode & RT_HT_CAP_USE_SOFTAP)
-			ht_info->IOTPeer = HT_IOT_PEER_92U_SOFTAP;
+			ht_info->iot_peer = HT_IOT_PEER_92U_SOFTAP;
 	} else if (net->broadcom_cap_exist) {
-		ht_info->IOTPeer = HT_IOT_PEER_BROADCOM;
+		ht_info->iot_peer = HT_IOT_PEER_BROADCOM;
 	} else if (!memcmp(net->bssid, UNKNOWN_BORADCOM, 3) ||
 		 !memcmp(net->bssid, LINKSYSWRT330_LINKSYSWRT300_BROADCOM, 3) ||
 		 !memcmp(net->bssid, LINKSYSWRT350_LINKSYSWRT150_BROADCOM, 3)) {
-		ht_info->IOTPeer = HT_IOT_PEER_BROADCOM;
+		ht_info->iot_peer = HT_IOT_PEER_BROADCOM;
 	} else if ((memcmp(net->bssid, BELKINF5D8233V1_RALINK, 3) == 0) ||
 		 (memcmp(net->bssid, BELKINF5D82334V3_RALINK, 3) == 0) ||
 		 (memcmp(net->bssid, PCI_RALINK, 3) == 0) ||
 		 (memcmp(net->bssid, EDIMAX_RALINK, 3) == 0) ||
 		 (memcmp(net->bssid, AIRLINK_RALINK, 3) == 0) ||
 		  net->ralink_cap_exist) {
-		ht_info->IOTPeer = HT_IOT_PEER_RALINK;
+		ht_info->iot_peer = HT_IOT_PEER_RALINK;
 	} else if ((net->atheros_cap_exist) ||
 		(memcmp(net->bssid, DLINK_ATHEROS_1, 3) == 0) ||
 		(memcmp(net->bssid, DLINK_ATHEROS_2, 3) == 0)) {
-		ht_info->IOTPeer = HT_IOT_PEER_ATHEROS;
+		ht_info->iot_peer = HT_IOT_PEER_ATHEROS;
 	} else if ((memcmp(net->bssid, CISCO_BROADCOM, 3) == 0) ||
 		  net->cisco_cap_exist) {
-		ht_info->IOTPeer = HT_IOT_PEER_CISCO;
+		ht_info->iot_peer = HT_IOT_PEER_CISCO;
 	} else if ((memcmp(net->bssid, LINKSYS_MARVELL_4400N, 3) == 0) ||
 		  net->marvell_cap_exist) {
-		ht_info->IOTPeer = HT_IOT_PEER_MARVELL;
+		ht_info->iot_peer = HT_IOT_PEER_MARVELL;
 	} else if (net->airgo_cap_exist) {
-		ht_info->IOTPeer = HT_IOT_PEER_AIRGO;
+		ht_info->iot_peer = HT_IOT_PEER_AIRGO;
 	} else {
-		ht_info->IOTPeer = HT_IOT_PEER_UNKNOWN;
+		ht_info->iot_peer = HT_IOT_PEER_UNKNOWN;
 	}
 
-	netdev_dbg(ieee->dev, "IOTPEER: %x\n", ht_info->IOTPeer);
+	netdev_dbg(ieee->dev, "IOTPEER: %x\n", ht_info->iot_peer);
 }
 
-static u8 HTIOTActIsMgntUseCCK6M(struct rtllib_device *ieee,
+static u8 ht_iot_act_is_mgnt_use_cck_6m(struct rtllib_device *ieee,
 				 struct rtllib_network *network)
 {
 	u8	retValue = 0;
 
-	if (ieee->ht_info->IOTPeer == HT_IOT_PEER_BROADCOM)
+	if (ieee->ht_info->iot_peer == HT_IOT_PEER_BROADCOM)
 		retValue = 1;
 
 	return retValue;
 }
 
-static u8 HTIOTActIsCCDFsync(struct rtllib_device *ieee)
+static u8 ht_iot_act_is_ccd_fsync(struct rtllib_device *ieee)
 {
 	u8	retValue = 0;
 
-	if (ieee->ht_info->IOTPeer == HT_IOT_PEER_BROADCOM)
+	if (ieee->ht_info->iot_peer == HT_IOT_PEER_BROADCOM)
 		retValue = 1;
 	return retValue;
 }
 
-static void HTIOTActDetermineRaFunc(struct rtllib_device *ieee, bool bPeerRx2ss)
+static void ht_iot_act_determine_ra_func(struct rtllib_device *ieee, bool bPeerRx2ss)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
 	ht_info->iot_ra_func &= HT_IOT_RAFUNC_DISABLE_ALL;
 
-	if (ht_info->IOTPeer == HT_IOT_PEER_RALINK && !bPeerRx2ss)
+	if (ht_info->iot_peer == HT_IOT_PEER_RALINK && !bPeerRx2ss)
 		ht_info->iot_ra_func |= HT_IOT_RAFUNC_PEER_1R;
 
 	if (ht_info->iot_action & HT_IOT_ACT_AMSDU_ENABLE)
 		ht_info->iot_ra_func |= HT_IOT_RAFUNC_TX_AMSDU;
 }
 
-void HTResetIOTSetting(struct rt_hi_throughput *ht_info)
+void ht_reset_iot_setting(struct rt_hi_throughput *ht_info)
 {
 	ht_info->iot_action = 0;
-	ht_info->IOTPeer = HT_IOT_PEER_UNKNOWN;
+	ht_info->iot_peer = HT_IOT_PEER_UNKNOWN;
 	ht_info->iot_ra_func = 0;
 }
 
-void HTConstructCapabilityElement(struct rtllib_device *ieee, u8 *posHTCap,
-				  u8 *len, u8 IsEncrypt, bool bAssoc)
+void ht_construct_capability_element(struct rtllib_device *ieee, u8 *pos_ht_cap,
+				  u8 *len, u8 is_encrypt, bool assoc)
 {
-	struct rt_hi_throughput *pHT = ieee->ht_info;
-	struct ht_capab_ele *pCapELE = NULL;
+	struct rt_hi_throughput *ht = ieee->ht_info;
+	struct ht_capab_ele *cap_ele = NULL;
 
-	if (!posHTCap || !pHT) {
+	if (!pos_ht_cap || !ht) {
 		netdev_warn(ieee->dev,
 			    "%s(): posHTCap and ht_info are null\n", __func__);
 		return;
 	}
-	memset(posHTCap, 0, *len);
+	memset(pos_ht_cap, 0, *len);
 
-	if ((bAssoc) && (pHT->ePeerHTSpecVer == HT_SPEC_VER_EWC)) {
+	if ((assoc) && (ht->peer_ht_spec_ver == HT_SPEC_VER_EWC)) {
 		static const u8	EWC11NHTCap[] = { 0x00, 0x90, 0x4c, 0x33 };
 
-		memcpy(posHTCap, EWC11NHTCap, sizeof(EWC11NHTCap));
-		pCapELE = (struct ht_capab_ele *)&posHTCap[4];
+		memcpy(pos_ht_cap, EWC11NHTCap, sizeof(EWC11NHTCap));
+		cap_ele = (struct ht_capab_ele *)&pos_ht_cap[4];
 		*len = 30 + 2;
 	} else {
-		pCapELE = (struct ht_capab_ele *)posHTCap;
+		cap_ele = (struct ht_capab_ele *)pos_ht_cap;
 		*len = 26 + 2;
 	}
 
-	pCapELE->AdvCoding		= 0;
+	cap_ele->AdvCoding		= 0;
 	if (ieee->GetHalfNmodeSupportByAPsHandler(ieee->dev))
-		pCapELE->ChlWidth = 0;
+		cap_ele->ChlWidth = 0;
 	else
-		pCapELE->ChlWidth = (pHT->bRegBW40MHz ? 1 : 0);
+		cap_ele->ChlWidth = 1;
 
-	pCapELE->MimoPwrSave		= pHT->self_mimo_ps;
-	pCapELE->GreenField		= 0;
-	pCapELE->ShortGI20Mhz		= 1;
-	pCapELE->ShortGI40Mhz		= 1;
+	cap_ele->MimoPwrSave		= 3;
+	cap_ele->GreenField		= 0;
+	cap_ele->ShortGI20Mhz		= 1;
+	cap_ele->ShortGI40Mhz		= 1;
 
-	pCapELE->TxSTBC			= 1;
-	pCapELE->RxSTBC			= 0;
-	pCapELE->DelayBA		= 0;
-	pCapELE->MaxAMSDUSize = (MAX_RECEIVE_BUFFER_SIZE >= 7935) ? 1 : 0;
-	pCapELE->DssCCk = ((pHT->bRegBW40MHz) ? (pHT->bRegSuppCCK ? 1 : 0) : 0);
-	pCapELE->PSMP = 0;
-	pCapELE->LSigTxopProtect = 0;
+	cap_ele->TxSTBC			= 1;
+	cap_ele->RxSTBC			= 0;
+	cap_ele->DelayBA		= 0;
+	cap_ele->MaxAMSDUSize = (MAX_RECEIVE_BUFFER_SIZE >= 7935) ? 1 : 0;
+	cap_ele->DssCCk = 1;
+	cap_ele->PSMP = 0;
+	cap_ele->LSigTxopProtect = 0;
 
 	netdev_dbg(ieee->dev,
 		   "TX HT cap/info ele BW=%d MaxAMSDUSize:%d DssCCk:%d\n",
-		   pCapELE->ChlWidth, pCapELE->MaxAMSDUSize, pCapELE->DssCCk);
+		   cap_ele->ChlWidth, cap_ele->MaxAMSDUSize, cap_ele->DssCCk);
 
-	if (IsEncrypt) {
-		pCapELE->MPDUDensity	= 7;
-		pCapELE->MaxRxAMPDUFactor	= 2;
+	if (is_encrypt) {
+		cap_ele->MPDUDensity	= 7;
+		cap_ele->MaxRxAMPDUFactor	= 2;
 	} else {
-		pCapELE->MaxRxAMPDUFactor	= 3;
-		pCapELE->MPDUDensity	= 0;
+		cap_ele->MaxRxAMPDUFactor	= 3;
+		cap_ele->MPDUDensity	= 0;
 	}
 
-	memcpy(pCapELE->MCS, ieee->reg_dot11ht_oper_rate_set, 16);
-	memset(&pCapELE->ExtHTCapInfo, 0, 2);
-	memset(pCapELE->TxBFCap, 0, 4);
+	memcpy(cap_ele->MCS, ieee->reg_dot11ht_oper_rate_set, 16);
+	memset(&cap_ele->ExtHTCapInfo, 0, 2);
+	memset(cap_ele->TxBFCap, 0, 4);
 
-	pCapELE->ASCap = 0;
+	cap_ele->ASCap = 0;
 
-	if (bAssoc) {
-		if (pHT->iot_action & HT_IOT_ACT_DISABLE_MCS15)
-			pCapELE->MCS[1] &= 0x7f;
+	if (assoc) {
+		if (ht->iot_action & HT_IOT_ACT_DISABLE_MCS15)
+			cap_ele->MCS[1] &= 0x7f;
 
-		if (pHT->iot_action & HT_IOT_ACT_DISABLE_MCS14)
-			pCapELE->MCS[1] &= 0xbf;
+		if (ht->iot_action & HT_IOT_ACT_DISABLE_MCS14)
+			cap_ele->MCS[1] &= 0xbf;
 
-		if (pHT->iot_action & HT_IOT_ACT_DISABLE_ALL_2SS)
-			pCapELE->MCS[1] &= 0x00;
+		if (ht->iot_action & HT_IOT_ACT_DISABLE_ALL_2SS)
+			cap_ele->MCS[1] &= 0x00;
 
-		if (pHT->iot_action & HT_IOT_ACT_DISABLE_RX_40MHZ_SHORT_GI)
-			pCapELE->ShortGI40Mhz		= 0;
+		if (ht->iot_action & HT_IOT_ACT_DISABLE_RX_40MHZ_SHORT_GI)
+			cap_ele->ShortGI40Mhz		= 0;
 
 		if (ieee->GetHalfNmodeSupportByAPsHandler(ieee->dev)) {
-			pCapELE->ChlWidth = 0;
-			pCapELE->MCS[1] = 0;
+			cap_ele->ChlWidth = 0;
+			cap_ele->MCS[1] = 0;
 		}
 	}
 }
 
-void HTConstructInfoElement(struct rtllib_device *ieee, u8 *posHTInfo,
-			    u8 *len, u8 IsEncrypt)
-{
-	struct ht_info_ele *pHTInfoEle = (struct ht_info_ele *)posHTInfo;
-
-	if (!posHTInfo || !pHTInfoEle) {
-		netdev_warn(ieee->dev,
-			    "%s(): posHTInfo and pHTInfoEle are null\n",
-			    __func__);
-		return;
-	}
-
-	memset(posHTInfo, 0, *len);
-	*len = 0;
-}
-
-void HTConstructRT2RTAggElement(struct rtllib_device *ieee, u8 *posRT2RTAgg,
+void ht_construct_rt2rt_agg_element(struct rtllib_device *ieee, u8 *posRT2RTAgg,
 				u8 *len)
 {
 	if (!posRT2RTAgg) {
@@ -366,7 +330,7 @@ void HTConstructRT2RTAggElement(struct rtllib_device *ieee, u8 *posRT2RTAgg,
 	*len = 6 + 2;
 }
 
-static u8 HT_PickMCSRate(struct rtllib_device *ieee, u8 *pOperateMCS)
+static u8 ht_pick_mcs_rate(struct rtllib_device *ieee, u8 *pOperateMCS)
 {
 	u8 i;
 
@@ -393,7 +357,7 @@ static u8 HT_PickMCSRate(struct rtllib_device *ieee, u8 *pOperateMCS)
 	return true;
 }
 
-u8 HTGetHighestMCSRate(struct rtllib_device *ieee, u8 *pMCSRateSet,
+u8 ht_get_highest_mcs_rate(struct rtllib_device *ieee, u8 *pMCSRateSet,
 		       u8 *pMCSFilter)
 {
 	u8		i, j;
@@ -422,8 +386,8 @@ u8 HTGetHighestMCSRate(struct rtllib_device *ieee, u8 *pMCSRateSet,
 			bitMap = availableMcsRate[i];
 			for (j = 0; j < 8; j++) {
 				if ((bitMap % 2) != 0) {
-					if (HTMcsToDataRate(ieee, (8 * i + j)) >
-					    HTMcsToDataRate(ieee, mcsRate))
+					if (ht_mcs_to_data_rate(ieee, (8 * i + j)) >
+					    ht_mcs_to_data_rate(ieee, mcsRate))
 						mcsRate = 8 * i + j;
 				}
 				bitMap >>= 1;
@@ -433,7 +397,7 @@ u8 HTGetHighestMCSRate(struct rtllib_device *ieee, u8 *pMCSRateSet,
 	return mcsRate | 0x80;
 }
 
-static u8 HTFilterMCSRate(struct rtllib_device *ieee, u8 *pSupportMCS,
+static u8 ht_filter_mcs_rate(struct rtllib_device *ieee, u8 *pSupportMCS,
 			  u8 *pOperateMCS)
 {
 	u8 i;
@@ -442,7 +406,7 @@ static u8 HTFilterMCSRate(struct rtllib_device *ieee, u8 *pSupportMCS,
 		pOperateMCS[i] = ieee->reg_dot11tx_ht_oper_rate_set[i] &
 				 pSupportMCS[i];
 
-	HT_PickMCSRate(ieee, pOperateMCS);
+	ht_pick_mcs_rate(ieee, pOperateMCS);
 
 	if (ieee->GetHalfNmodeSupportByAPsHandler(ieee->dev))
 		pOperateMCS[1] = 0;
@@ -453,16 +417,15 @@ static u8 HTFilterMCSRate(struct rtllib_device *ieee, u8 *pSupportMCS,
 	return true;
 }
 
-void HTSetConnectBwMode(struct rtllib_device *ieee,
+void ht_set_connect_bw_mode(struct rtllib_device *ieee,
 			enum ht_channel_width bandwidth,
 			enum ht_extchnl_offset Offset);
 
-void HTOnAssocRsp(struct rtllib_device *ieee)
+void ht_on_assoc_rsp(struct rtllib_device *ieee)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 	struct ht_capab_ele *pPeerHTCap = NULL;
 	struct ht_info_ele *pPeerHTInfo = NULL;
-	u16 nMaxAMSDUSize = 0;
 	u8 *pMcsFilter = NULL;
 
 	static const u8 EWC11NHTCap[] = { 0x00, 0x90, 0x4c, 0x33 };
@@ -489,79 +452,48 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 	print_hex_dump_bytes("%s: ", __func__, DUMP_PREFIX_NONE,
 			     pPeerHTCap, sizeof(struct ht_capab_ele));
 #endif
-	HTSetConnectBwMode(ieee, (enum ht_channel_width)(pPeerHTCap->ChlWidth),
+	ht_set_connect_bw_mode(ieee, (enum ht_channel_width)(pPeerHTCap->ChlWidth),
 			   (enum ht_extchnl_offset)(pPeerHTInfo->ExtChlOffset));
 	ht_info->cur_tx_bw40mhz = ((pPeerHTInfo->RecommemdedTxWidth == 1) ?
 				 true : false);
 
-	ht_info->bCurShortGI20MHz = ((ht_info->bRegShortGI20MHz) ?
-				    ((pPeerHTCap->ShortGI20Mhz == 1) ?
-				    true : false) : false);
-	ht_info->bCurShortGI40MHz = ((ht_info->bRegShortGI40MHz) ?
-				     ((pPeerHTCap->ShortGI40Mhz == 1) ?
-				     true : false) : false);
+	ht_info->cur_short_gi_20mhz = ((pPeerHTCap->ShortGI20Mhz == 1) ? true : false);
+	ht_info->cur_short_gi_40mhz = ((pPeerHTCap->ShortGI40Mhz == 1) ? true : false);
 
-	ht_info->bCurSuppCCK = ((ht_info->bRegSuppCCK) ?
-			       ((pPeerHTCap->DssCCk == 1) ? true :
-			       false) : false);
-
-	ht_info->bCurrent_AMSDU_Support = ht_info->bAMSDU_Support;
-
-	nMaxAMSDUSize = (pPeerHTCap->MaxAMSDUSize == 0) ? 3839 : 7935;
-
-	if (ht_info->nAMSDU_MaxSize > nMaxAMSDUSize)
-		ht_info->nCurrent_AMSDU_MaxSize = nMaxAMSDUSize;
-	else
-		ht_info->nCurrent_AMSDU_MaxSize = ht_info->nAMSDU_MaxSize;
-
-	ht_info->bCurrentAMPDUEnable = ht_info->bAMPDUEnable;
+	ht_info->current_ampdu_enable = ht_info->ampdu_enable;
 	if (ieee->rtllib_ap_sec_type &&
 	    (ieee->rtllib_ap_sec_type(ieee) & (SEC_ALG_WEP | SEC_ALG_TKIP))) {
-		if ((ht_info->IOTPeer == HT_IOT_PEER_ATHEROS) ||
-		    (ht_info->IOTPeer == HT_IOT_PEER_UNKNOWN))
-			ht_info->bCurrentAMPDUEnable = false;
+		if ((ht_info->iot_peer == HT_IOT_PEER_ATHEROS) ||
+		    (ht_info->iot_peer == HT_IOT_PEER_UNKNOWN))
+			ht_info->current_ampdu_enable = false;
 	}
 
-	if (!ht_info->reg_rt2rt_aggregation) {
-		if (ht_info->AMPDU_Factor > pPeerHTCap->MaxRxAMPDUFactor)
+	if (ieee->current_network.bssht.bd_rt2rt_aggregation) {
+		if (ieee->pairwise_key_type != KEY_TYPE_NA)
 			ht_info->CurrentAMPDUFactor =
-						 pPeerHTCap->MaxRxAMPDUFactor;
+					 pPeerHTCap->MaxRxAMPDUFactor;
 		else
-			ht_info->CurrentAMPDUFactor = ht_info->AMPDU_Factor;
-
+			ht_info->CurrentAMPDUFactor = HT_AGG_SIZE_64K;
 	} else {
-		if (ieee->current_network.bssht.bd_rt2rt_aggregation) {
-			if (ieee->pairwise_key_type != KEY_TYPE_NA)
-				ht_info->CurrentAMPDUFactor =
-						 pPeerHTCap->MaxRxAMPDUFactor;
-			else
-				ht_info->CurrentAMPDUFactor = HT_AGG_SIZE_64K;
-		} else {
-			ht_info->CurrentAMPDUFactor = min_t(u32, pPeerHTCap->MaxRxAMPDUFactor,
-							    HT_AGG_SIZE_32K);
-		}
+		ht_info->CurrentAMPDUFactor = min_t(u32, pPeerHTCap->MaxRxAMPDUFactor,
+						    HT_AGG_SIZE_32K);
 	}
-	ht_info->current_mpdu_density = max_t(u8, ht_info->MPDU_Density,
-					      pPeerHTCap->MPDUDensity);
+
+	ht_info->current_mpdu_density = pPeerHTCap->MPDUDensity;
 	if (ht_info->iot_action & HT_IOT_ACT_TX_USE_AMSDU_8K) {
-		ht_info->bCurrentAMPDUEnable = false;
-		ht_info->ForcedAMSDUMode = HT_AGG_FORCE_ENABLE;
+		ht_info->current_ampdu_enable = false;
 	}
-	ht_info->cur_rx_reorder_enable = ht_info->reg_rx_reorder_enable;
+	ht_info->cur_rx_reorder_enable = 1;
 
 	if (pPeerHTCap->MCS[0] == 0)
 		pPeerHTCap->MCS[0] = 0xff;
 
-	HTIOTActDetermineRaFunc(ieee, ((pPeerHTCap->MCS[1]) != 0));
+	ht_iot_act_determine_ra_func(ieee, ((pPeerHTCap->MCS[1]) != 0));
 
-	HTFilterMCSRate(ieee, pPeerHTCap->MCS, ieee->dot11ht_oper_rate_set);
+	ht_filter_mcs_rate(ieee, pPeerHTCap->MCS, ieee->dot11ht_oper_rate_set);
 
-	ht_info->peer_mimo_ps = pPeerHTCap->MimoPwrSave;
-	if (ht_info->peer_mimo_ps == MIMO_PS_STATIC)
-		pMcsFilter = MCS_FILTER_1SS;
-	else
-		pMcsFilter = MCS_FILTER_ALL;
-	ieee->HTHighestOperaRate = HTGetHighestMCSRate(ieee,
+	pMcsFilter = MCS_FILTER_ALL;
+	ieee->HTHighestOperaRate = ht_get_highest_mcs_rate(ieee,
 						       ieee->dot11ht_oper_rate_set,
 						       pMcsFilter);
 	ieee->HTCurrentOperaRate = ieee->HTHighestOperaRate;
@@ -569,30 +501,23 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 	ht_info->current_op_mode = pPeerHTInfo->OptMode;
 }
 
-void HTInitializeHTInfo(struct rtllib_device *ieee)
+void ht_initialize_ht_info(struct rtllib_device *ieee)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
 	ht_info->current_ht_support = false;
 
-	ht_info->bCurBW40MHz = false;
+	ht_info->cur_bw_40mhz = false;
 	ht_info->cur_tx_bw40mhz = false;
 
-	ht_info->bCurShortGI20MHz = false;
-	ht_info->bCurShortGI40MHz = false;
-	ht_info->forced_short_gi = false;
+	ht_info->cur_short_gi_20mhz = false;
+	ht_info->cur_short_gi_40mhz = false;
 
-	ht_info->bCurSuppCCK = true;
-
-	ht_info->bCurrent_AMSDU_Support = false;
-	ht_info->nCurrent_AMSDU_MaxSize = ht_info->nAMSDU_MaxSize;
-	ht_info->current_mpdu_density = ht_info->MPDU_Density;
-	ht_info->CurrentAMPDUFactor = ht_info->AMPDU_Factor;
+	ht_info->current_mpdu_density = 0;
+	ht_info->CurrentAMPDUFactor = ht_info->ampdu_factor;
 
 	memset((void *)(&ht_info->SelfHTCap), 0,
 	       sizeof(ht_info->SelfHTCap));
-	memset((void *)(&ht_info->SelfHTInfo), 0,
-	       sizeof(ht_info->SelfHTInfo));
 	memset((void *)(&ht_info->PeerHTCapBuf), 0,
 	       sizeof(ht_info->PeerHTCapBuf));
 	memset((void *)(&ht_info->PeerHTInfoBuf), 0,
@@ -600,13 +525,12 @@ void HTInitializeHTInfo(struct rtllib_device *ieee)
 
 	ht_info->sw_bw_in_progress = false;
 
-	ht_info->ePeerHTSpecVer = HT_SPEC_VER_IEEE;
+	ht_info->peer_ht_spec_ver = HT_SPEC_VER_IEEE;
 
 	ht_info->current_rt2rt_aggregation = false;
 	ht_info->current_rt2rt_long_slot_time = false;
-	ht_info->RT2RT_HT_Mode = (enum rt_ht_capability)0;
 
-	ht_info->IOTPeer = 0;
+	ht_info->iot_peer = 0;
 	ht_info->iot_action = 0;
 	ht_info->iot_ra_func = 0;
 
@@ -619,7 +543,7 @@ void HTInitializeHTInfo(struct rtllib_device *ieee)
 	}
 }
 
-void HTInitializeBssDesc(struct bss_ht *pBssHT)
+void ht_initialize_bss_desc(struct bss_ht *pBssHT)
 {
 	pBssHT->bd_support_ht = false;
 	memset(pBssHT->bd_ht_cap_buf, 0, sizeof(pBssHT->bd_ht_cap_buf));
@@ -634,7 +558,7 @@ void HTInitializeBssDesc(struct bss_ht *pBssHT)
 	pBssHT->rt2rt_ht_mode = (enum rt_ht_capability)0;
 }
 
-void HTResetSelfAndSavePeerSetting(struct rtllib_device *ieee,
+void ht_reset_self_and_save_peer_setting(struct rtllib_device *ieee,
 				   struct rtllib_network *pNetwork)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
@@ -645,7 +569,7 @@ void HTResetSelfAndSavePeerSetting(struct rtllib_device *ieee,
 	 */
 	if (pNetwork->bssht.bd_support_ht) {
 		ht_info->current_ht_support = true;
-		ht_info->ePeerHTSpecVer = pNetwork->bssht.bd_ht_spec_ver;
+		ht_info->peer_ht_spec_ver = pNetwork->bssht.bd_ht_spec_ver;
 
 		if (pNetwork->bssht.bd_ht_cap_len > 0 &&
 		    pNetwork->bssht.bd_ht_cap_len <= sizeof(ht_info->PeerHTCapBuf))
@@ -660,32 +584,24 @@ void HTResetSelfAndSavePeerSetting(struct rtllib_device *ieee,
 			       pNetwork->bssht.bd_ht_info_buf,
 			       pNetwork->bssht.bd_ht_info_len);
 
-		if (ht_info->reg_rt2rt_aggregation) {
-			ht_info->current_rt2rt_aggregation =
-				 pNetwork->bssht.bd_rt2rt_aggregation;
-			ht_info->current_rt2rt_long_slot_time =
-				 pNetwork->bssht.bd_rt2rt_long_slot_time;
-			ht_info->RT2RT_HT_Mode = pNetwork->bssht.rt2rt_ht_mode;
-		} else {
-			ht_info->current_rt2rt_aggregation = false;
-			ht_info->current_rt2rt_long_slot_time = false;
-			ht_info->RT2RT_HT_Mode = (enum rt_ht_capability)0;
-		}
+		ht_info->current_rt2rt_aggregation =
+			 pNetwork->bssht.bd_rt2rt_aggregation;
+		ht_info->current_rt2rt_long_slot_time =
+			 pNetwork->bssht.bd_rt2rt_long_slot_time;
 
-		HTIOTPeerDetermine(ieee);
+		ht_iot_peer_determine(ieee);
 
 		ht_info->iot_action = 0;
-		bIOTAction = HTIOTActIsMgntUseCCK6M(ieee, pNetwork);
+		bIOTAction = ht_iot_act_is_mgnt_use_cck_6m(ieee, pNetwork);
 		if (bIOTAction)
 			ht_info->iot_action |= HT_IOT_ACT_MGNT_USE_CCK_6M;
-		bIOTAction = HTIOTActIsCCDFsync(ieee);
+		bIOTAction = ht_iot_act_is_ccd_fsync(ieee);
 		if (bIOTAction)
 			ht_info->iot_action |= HT_IOT_ACT_CDD_FSYNC;
 	} else {
 		ht_info->current_ht_support = false;
 		ht_info->current_rt2rt_aggregation = false;
 		ht_info->current_rt2rt_long_slot_time = false;
-		ht_info->RT2RT_HT_Mode = (enum rt_ht_capability)0;
 
 		ht_info->iot_action = 0;
 		ht_info->iot_ra_func = 0;
@@ -706,7 +622,7 @@ void HT_update_self_and_peer_setting(struct rtllib_device *ieee,
 }
 EXPORT_SYMBOL(HT_update_self_and_peer_setting);
 
-u8 HTCCheck(struct rtllib_device *ieee, u8 *pFrame)
+u8 ht_c_check(struct rtllib_device *ieee, u8 *pFrame)
 {
 	if (ieee->ht_info->current_ht_support) {
 		if ((IsQoSDataFrame(pFrame) && Frame_Order(pFrame)) == 1) {
@@ -717,11 +633,11 @@ u8 HTCCheck(struct rtllib_device *ieee, u8 *pFrame)
 	return false;
 }
 
-static void HTSetConnectBwModeCallback(struct rtllib_device *ieee)
+static void ht_set_connect_bw_mode_callback(struct rtllib_device *ieee)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
-	if (ht_info->bCurBW40MHz) {
+	if (ht_info->cur_bw_40mhz) {
 		if (ht_info->CurSTAExtChnlOffset == HT_EXTCHNL_OFFSET_UPPER)
 			ieee->set_chan(ieee->dev,
 				       ieee->current_network.channel + 2);
@@ -744,15 +660,12 @@ static void HTSetConnectBwModeCallback(struct rtllib_device *ieee)
 	ht_info->sw_bw_in_progress = false;
 }
 
-void HTSetConnectBwMode(struct rtllib_device *ieee,
+void ht_set_connect_bw_mode(struct rtllib_device *ieee,
 			enum ht_channel_width bandwidth,
 			enum ht_extchnl_offset Offset)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
-	if (!ht_info->bRegBW40MHz)
-		return;
-
 	if (ieee->GetHalfNmodeSupportByAPsHandler(ieee->dev))
 		bandwidth = HT_CHANNEL_WIDTH_20;
 
@@ -766,21 +679,21 @@ void HTSetConnectBwMode(struct rtllib_device *ieee,
 			Offset = HT_EXTCHNL_OFFSET_NO_EXT;
 		if (Offset == HT_EXTCHNL_OFFSET_UPPER ||
 		    Offset == HT_EXTCHNL_OFFSET_LOWER) {
-			ht_info->bCurBW40MHz = true;
+			ht_info->cur_bw_40mhz = true;
 			ht_info->CurSTAExtChnlOffset = Offset;
 		} else {
-			ht_info->bCurBW40MHz = false;
+			ht_info->cur_bw_40mhz = false;
 			ht_info->CurSTAExtChnlOffset = HT_EXTCHNL_OFFSET_NO_EXT;
 		}
 	} else {
-		ht_info->bCurBW40MHz = false;
+		ht_info->cur_bw_40mhz = false;
 		ht_info->CurSTAExtChnlOffset = HT_EXTCHNL_OFFSET_NO_EXT;
 	}
 
 	netdev_dbg(ieee->dev, "%s():ht_info->bCurBW40MHz:%x\n", __func__,
-		   ht_info->bCurBW40MHz);
+		   ht_info->cur_bw_40mhz);
 
 	ht_info->sw_bw_in_progress = true;
 
-	HTSetConnectBwModeCallback(ieee);
+	ht_set_connect_bw_mode_callback(ieee);
 }
diff --git a/drivers/staging/rtl8192e/rtl819x_Qos.h b/drivers/staging/rtl8192e/rtl819x_Qos.h
index 1c00092ea3a5..50e01ca49a4c 100644
--- a/drivers/staging/rtl8192e/rtl819x_Qos.h
+++ b/drivers/staging/rtl8192e/rtl819x_Qos.h
@@ -8,7 +8,7 @@
 #define __INC_QOS_TYPE_H
 
 struct qos_tsinfo {
-	u8		ucTSID:4;
+	u8		ts_id:4;
 	u8		ucDirection:2;
 };
 
diff --git a/drivers/staging/rtl8192e/rtl819x_TS.h b/drivers/staging/rtl8192e/rtl819x_TS.h
index fff36315f174..5b0e4cb572d2 100644
--- a/drivers/staging/rtl8192e/rtl819x_TS.h
+++ b/drivers/staging/rtl8192e/rtl819x_TS.h
@@ -17,21 +17,21 @@ enum tr_select {
 };
 
 struct ts_common_info {
-	struct list_head		List;
+	struct list_head		list;
 	u8				addr[ETH_ALEN];
-	struct qos_tsinfo TSpec;
+	struct qos_tsinfo tspec;
 };
 
 struct tx_ts_record {
-	struct ts_common_info TsCommonInfo;
-	u16				TxCurSeq;
-	struct ba_record TxPendingBARecord;
-	struct ba_record TxAdmittedBARecord;
-	u8				bAddBaReqInProgress;
-	u8				bAddBaReqDelayed;
-	u8				bUsingBa;
-	u8				bDisable_AddBa;
-	struct timer_list		TsAddBaTimer;
+	struct ts_common_info ts_common_info;
+	u16				tx_cur_seq;
+	struct ba_record tx_pending_ba_record;
+	struct ba_record tx_admitted_ba_record;
+	u8				add_ba_req_in_progress;
+	u8				add_ba_req_delayed;
+	u8				using_ba;
+	u8				disable_add_ba;
+	struct timer_list		ts_add_ba_timer;
 	u8				num;
 };
 
diff --git a/drivers/staging/rtl8192e/rtl819x_TSProc.c b/drivers/staging/rtl8192e/rtl819x_TSProc.c
index 3206fdb3e65a..7e73d31dcccf 100644
--- a/drivers/staging/rtl8192e/rtl819x_TSProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_TSProc.c
@@ -12,7 +12,7 @@ static void RxPktPendingTimeout(struct timer_list *t)
 {
 	struct rx_ts_record *ts = from_timer(ts, t, rx_pkt_pending_timer);
 	struct rtllib_device *ieee = container_of(ts, struct rtllib_device,
-						  RxTsRecord[ts->num]);
+						  rx_ts_records[ts->num]);
 
 	struct rx_reorder_entry *pReorderEntry = NULL;
 
@@ -25,7 +25,7 @@ static void RxPktPendingTimeout(struct timer_list *t)
 		while (!list_empty(&ts->rx_pending_pkt_list)) {
 			pReorderEntry = (struct rx_reorder_entry *)
 					list_entry(ts->rx_pending_pkt_list.prev,
-					struct rx_reorder_entry, List);
+					struct rx_reorder_entry, list);
 			if (index == 0)
 				ts->rx_indicate_seq = pReorderEntry->SeqNum;
 
@@ -33,7 +33,7 @@ static void RxPktPendingTimeout(struct timer_list *t)
 				    ts->rx_indicate_seq) ||
 			    SN_EQUAL(pReorderEntry->SeqNum,
 				     ts->rx_indicate_seq)) {
-				list_del_init(&pReorderEntry->List);
+				list_del_init(&pReorderEntry->list);
 
 				if (SN_EQUAL(pReorderEntry->SeqNum,
 				    ts->rx_indicate_seq))
@@ -47,7 +47,7 @@ static void RxPktPendingTimeout(struct timer_list *t)
 							 pReorderEntry->prxb;
 				index++;
 
-				list_add_tail(&pReorderEntry->List,
+				list_add_tail(&pReorderEntry->list,
 					      &ieee->RxReorder_Unused_List);
 			} else {
 				bPktInBuf = true;
@@ -82,31 +82,31 @@ static void RxPktPendingTimeout(struct timer_list *t)
 
 static void TsAddBaProcess(struct timer_list *t)
 {
-	struct tx_ts_record *pTxTs = from_timer(pTxTs, t, TsAddBaTimer);
-	u8 num = pTxTs->num;
-	struct rtllib_device *ieee = container_of(pTxTs, struct rtllib_device,
-				     TxTsRecord[num]);
+	struct tx_ts_record *ts = from_timer(ts, t, ts_add_ba_timer);
+	u8 num = ts->num;
+	struct rtllib_device *ieee = container_of(ts, struct rtllib_device,
+				     tx_ts_records[num]);
 
-	rtllib_ts_init_add_ba(ieee, pTxTs, BA_POLICY_IMMEDIATE, false);
+	rtllib_ts_init_add_ba(ieee, ts, BA_POLICY_IMMEDIATE, false);
 	netdev_dbg(ieee->dev, "%s(): ADDBA Req is started\n", __func__);
 }
 
-static void ResetTsCommonInfo(struct ts_common_info *pTsCommonInfo)
+static void ResetTsCommonInfo(struct ts_common_info *ts_common_info)
 {
-	eth_zero_addr(pTsCommonInfo->addr);
-	memset(&pTsCommonInfo->TSpec, 0, sizeof(struct qos_tsinfo));
+	eth_zero_addr(ts_common_info->addr);
+	memset(&ts_common_info->tspec, 0, sizeof(struct qos_tsinfo));
 }
 
 static void ResetTxTsEntry(struct tx_ts_record *ts)
 {
-	ResetTsCommonInfo(&ts->TsCommonInfo);
-	ts->TxCurSeq = 0;
-	ts->bAddBaReqInProgress = false;
-	ts->bAddBaReqDelayed = false;
-	ts->bUsingBa = false;
-	ts->bDisable_AddBa = false;
-	rtllib_reset_ba_entry(&ts->TxAdmittedBARecord);
-	rtllib_reset_ba_entry(&ts->TxPendingBARecord);
+	ResetTsCommonInfo(&ts->ts_common_info);
+	ts->tx_cur_seq = 0;
+	ts->add_ba_req_in_progress = false;
+	ts->add_ba_req_delayed = false;
+	ts->using_ba = false;
+	ts->disable_add_ba = false;
+	rtllib_reset_ba_entry(&ts->tx_admitted_ba_record);
+	rtllib_reset_ba_entry(&ts->tx_pending_ba_record);
 }
 
 static void ResetRxTsEntry(struct rx_ts_record *ts)
@@ -119,8 +119,8 @@ static void ResetRxTsEntry(struct rx_ts_record *ts)
 
 void rtllib_ts_init(struct rtllib_device *ieee)
 {
-	struct tx_ts_record *pTxTS  = ieee->TxTsRecord;
-	struct rx_ts_record *rxts  = ieee->RxTsRecord;
+	struct tx_ts_record *pTxTS  = ieee->tx_ts_records;
+	struct rx_ts_record *rxts  = ieee->rx_ts_records;
 	struct rx_reorder_entry *pRxReorderEntry = ieee->RxReorderEntry;
 	u8				count = 0;
 
@@ -130,15 +130,15 @@ void rtllib_ts_init(struct rtllib_device *ieee)
 
 	for (count = 0; count < TOTAL_TS_NUM; count++) {
 		pTxTS->num = count;
-		timer_setup(&pTxTS->TsAddBaTimer, TsAddBaProcess, 0);
+		timer_setup(&pTxTS->ts_add_ba_timer, TsAddBaProcess, 0);
 
-		timer_setup(&pTxTS->TxPendingBARecord.timer, rtllib_ba_setup_timeout,
+		timer_setup(&pTxTS->tx_pending_ba_record.timer, rtllib_ba_setup_timeout,
 			    0);
-		timer_setup(&pTxTS->TxAdmittedBARecord.timer,
+		timer_setup(&pTxTS->tx_admitted_ba_record.timer,
 			    rtllib_tx_ba_inact_timeout, 0);
 
 		ResetTxTsEntry(pTxTS);
-		list_add_tail(&pTxTS->TsCommonInfo.List,
+		list_add_tail(&pTxTS->ts_common_info.list,
 				&ieee->Tx_TS_Unused_List);
 		pTxTS++;
 	}
@@ -155,13 +155,13 @@ void rtllib_ts_init(struct rtllib_device *ieee)
 		timer_setup(&rxts->rx_pkt_pending_timer, RxPktPendingTimeout, 0);
 
 		ResetRxTsEntry(rxts);
-		list_add_tail(&rxts->ts_common_info.List,
+		list_add_tail(&rxts->ts_common_info.list,
 			      &ieee->Rx_TS_Unused_List);
 		rxts++;
 	}
 	INIT_LIST_HEAD(&ieee->RxReorder_Unused_List);
 	for (count = 0; count < REORDER_ENTRY_NUM; count++) {
-		list_add_tail(&pRxReorderEntry->List,
+		list_add_tail(&pRxReorderEntry->list,
 			      &ieee->RxReorder_Unused_List);
 		if (count == (REORDER_ENTRY_NUM - 1))
 			break;
@@ -196,31 +196,31 @@ static struct ts_common_info *SearchAdmitTRStream(struct rtllib_device *ieee,
 	for (dir = 0; dir <= DIR_BI_DIR; dir++) {
 		if (!search_dir[dir])
 			continue;
-		list_for_each_entry(pRet, psearch_list, List) {
+		list_for_each_entry(pRet, psearch_list, list) {
 			if (memcmp(pRet->addr, addr, 6) == 0 &&
-			    pRet->TSpec.ucTSID == TID &&
-			    pRet->TSpec.ucDirection == dir)
+			    pRet->tspec.ts_id == TID &&
+			    pRet->tspec.ucDirection == dir)
 				break;
 		}
-		if (&pRet->List  != psearch_list)
+		if (&pRet->list  != psearch_list)
 			break;
 	}
 
-	if (pRet && &pRet->List  != psearch_list)
+	if (pRet && &pRet->list  != psearch_list)
 		return pRet;
 	return NULL;
 }
 
-static void MakeTSEntry(struct ts_common_info *pTsCommonInfo, u8 *addr,
+static void MakeTSEntry(struct ts_common_info *ts_common_info, u8 *addr,
 			struct qos_tsinfo *pTSPEC)
 {
-	if (!pTsCommonInfo)
+	if (!ts_common_info)
 		return;
 
-	memcpy(pTsCommonInfo->addr, addr, 6);
+	memcpy(ts_common_info->addr, addr, 6);
 
 	if (pTSPEC)
-		memcpy((u8 *)(&(pTsCommonInfo->TSpec)), (u8 *)pTSPEC,
+		memcpy((u8 *)(&(ts_common_info->tspec)), (u8 *)pTSPEC,
 			sizeof(struct qos_tsinfo));
 }
 
@@ -228,8 +228,8 @@ bool rtllib_get_ts(struct rtllib_device *ieee, struct ts_common_info **ppTS,
 	   u8 *addr, u8 TID, enum tr_select TxRxSelect, bool bAddNewTs)
 {
 	u8	UP = 0;
-	struct qos_tsinfo TSpec;
-	struct qos_tsinfo *ts_info = &TSpec;
+	struct qos_tsinfo tspec;
+	struct qos_tsinfo *ts_info = &tspec;
 	struct list_head *pUnusedList;
 	struct list_head *pAddmitList;
 	enum direction_value Dir;
@@ -286,13 +286,13 @@ bool rtllib_get_ts(struct rtllib_device *ieee, struct ts_common_info **ppTS,
 
 	if (!list_empty(pUnusedList)) {
 		(*ppTS) = list_entry(pUnusedList->next,
-			  struct ts_common_info, List);
-		list_del_init(&(*ppTS)->List);
+			  struct ts_common_info, list);
+		list_del_init(&(*ppTS)->list);
 		if (TxRxSelect == TX_DIR) {
 			struct tx_ts_record *tmp =
 				container_of(*ppTS,
 				struct tx_ts_record,
-				TsCommonInfo);
+				ts_common_info);
 			ResetTxTsEntry(tmp);
 		} else {
 			struct rx_ts_record *ts =
@@ -305,11 +305,11 @@ bool rtllib_get_ts(struct rtllib_device *ieee, struct ts_common_info **ppTS,
 		netdev_dbg(ieee->dev,
 			   "to init current TS, UP:%d, Dir:%d, addr: %pM ppTs=%p\n",
 			   UP, Dir, addr, *ppTS);
-		ts_info->ucTSID = UP;
+		ts_info->ts_id = UP;
 		ts_info->ucDirection = Dir;
 
-		MakeTSEntry(*ppTS, addr, &TSpec);
-		list_add_tail(&((*ppTS)->List), pAddmitList);
+		MakeTSEntry(*ppTS, addr, &tspec);
+		list_add_tail(&((*ppTS)->list), pAddmitList);
 
 		return true;
 	}
@@ -335,10 +335,10 @@ static void RemoveTsEntry(struct rtllib_device *ieee,
 		while (!list_empty(&ts->rx_pending_pkt_list)) {
 			pRxReorderEntry = (struct rx_reorder_entry *)
 					list_entry(ts->rx_pending_pkt_list.prev,
-					struct rx_reorder_entry, List);
+					struct rx_reorder_entry, list);
 			netdev_dbg(ieee->dev,  "%s(): Delete SeqNum %d!\n",
 				   __func__, pRxReorderEntry->SeqNum);
-			list_del_init(&pRxReorderEntry->List);
+			list_del_init(&pRxReorderEntry->list);
 			{
 				int i = 0;
 				struct rtllib_rxb *prxb = pRxReorderEntry->prxb;
@@ -350,13 +350,13 @@ static void RemoveTsEntry(struct rtllib_device *ieee,
 				kfree(prxb);
 				prxb = NULL;
 			}
-			list_add_tail(&pRxReorderEntry->List,
+			list_add_tail(&pRxReorderEntry->list,
 				      &ieee->RxReorder_Unused_List);
 		}
 	} else {
 		struct tx_ts_record *pTxTS = (struct tx_ts_record *)pTs;
 
-		del_timer_sync(&pTxTS->TsAddBaTimer);
+		del_timer_sync(&pTxTS->ts_add_ba_timer);
 	}
 }
 
@@ -366,37 +366,37 @@ void RemovePeerTS(struct rtllib_device *ieee, u8 *addr)
 
 	netdev_info(ieee->dev, "===========>%s, %pM\n", __func__, addr);
 
-	list_for_each_entry_safe(ts, pTmpTS, &ieee->Tx_TS_Pending_List, List) {
+	list_for_each_entry_safe(ts, pTmpTS, &ieee->Tx_TS_Pending_List, list) {
 		if (memcmp(ts->addr, addr, 6) == 0) {
 			RemoveTsEntry(ieee, ts, TX_DIR);
-			list_del_init(&ts->List);
-			list_add_tail(&ts->List, &ieee->Tx_TS_Unused_List);
+			list_del_init(&ts->list);
+			list_add_tail(&ts->list, &ieee->Tx_TS_Unused_List);
 		}
 	}
 
-	list_for_each_entry_safe(ts, pTmpTS, &ieee->Tx_TS_Admit_List, List) {
+	list_for_each_entry_safe(ts, pTmpTS, &ieee->Tx_TS_Admit_List, list) {
 		if (memcmp(ts->addr, addr, 6) == 0) {
 			netdev_info(ieee->dev,
 				    "====>remove Tx_TS_admin_list\n");
 			RemoveTsEntry(ieee, ts, TX_DIR);
-			list_del_init(&ts->List);
-			list_add_tail(&ts->List, &ieee->Tx_TS_Unused_List);
+			list_del_init(&ts->list);
+			list_add_tail(&ts->list, &ieee->Tx_TS_Unused_List);
 		}
 	}
 
-	list_for_each_entry_safe(ts, pTmpTS, &ieee->Rx_TS_Pending_List, List) {
+	list_for_each_entry_safe(ts, pTmpTS, &ieee->Rx_TS_Pending_List, list) {
 		if (memcmp(ts->addr, addr, 6) == 0) {
 			RemoveTsEntry(ieee, ts, RX_DIR);
-			list_del_init(&ts->List);
-			list_add_tail(&ts->List, &ieee->Rx_TS_Unused_List);
+			list_del_init(&ts->list);
+			list_add_tail(&ts->list, &ieee->Rx_TS_Unused_List);
 		}
 	}
 
-	list_for_each_entry_safe(ts, pTmpTS, &ieee->Rx_TS_Admit_List, List) {
+	list_for_each_entry_safe(ts, pTmpTS, &ieee->Rx_TS_Admit_List, list) {
 		if (memcmp(ts->addr, addr, 6) == 0) {
 			RemoveTsEntry(ieee, ts, RX_DIR);
-			list_del_init(&ts->List);
-			list_add_tail(&ts->List, &ieee->Rx_TS_Unused_List);
+			list_del_init(&ts->list);
+			list_add_tail(&ts->list, &ieee->Rx_TS_Unused_List);
 		}
 	}
 }
@@ -406,43 +406,43 @@ void RemoveAllTS(struct rtllib_device *ieee)
 {
 	struct ts_common_info *ts, *pTmpTS;
 
-	list_for_each_entry_safe(ts, pTmpTS, &ieee->Tx_TS_Pending_List, List) {
+	list_for_each_entry_safe(ts, pTmpTS, &ieee->Tx_TS_Pending_List, list) {
 		RemoveTsEntry(ieee, ts, TX_DIR);
-		list_del_init(&ts->List);
-		list_add_tail(&ts->List, &ieee->Tx_TS_Unused_List);
+		list_del_init(&ts->list);
+		list_add_tail(&ts->list, &ieee->Tx_TS_Unused_List);
 	}
 
-	list_for_each_entry_safe(ts, pTmpTS, &ieee->Tx_TS_Admit_List, List) {
+	list_for_each_entry_safe(ts, pTmpTS, &ieee->Tx_TS_Admit_List, list) {
 		RemoveTsEntry(ieee, ts, TX_DIR);
-		list_del_init(&ts->List);
-		list_add_tail(&ts->List, &ieee->Tx_TS_Unused_List);
+		list_del_init(&ts->list);
+		list_add_tail(&ts->list, &ieee->Tx_TS_Unused_List);
 	}
 
-	list_for_each_entry_safe(ts, pTmpTS, &ieee->Rx_TS_Pending_List, List) {
+	list_for_each_entry_safe(ts, pTmpTS, &ieee->Rx_TS_Pending_List, list) {
 		RemoveTsEntry(ieee, ts, RX_DIR);
-		list_del_init(&ts->List);
-		list_add_tail(&ts->List, &ieee->Rx_TS_Unused_List);
+		list_del_init(&ts->list);
+		list_add_tail(&ts->list, &ieee->Rx_TS_Unused_List);
 	}
 
-	list_for_each_entry_safe(ts, pTmpTS, &ieee->Rx_TS_Admit_List, List) {
+	list_for_each_entry_safe(ts, pTmpTS, &ieee->Rx_TS_Admit_List, list) {
 		RemoveTsEntry(ieee, ts, RX_DIR);
-		list_del_init(&ts->List);
-		list_add_tail(&ts->List, &ieee->Rx_TS_Unused_List);
+		list_del_init(&ts->list);
+		list_add_tail(&ts->list, &ieee->Rx_TS_Unused_List);
 	}
 }
 
 void TsStartAddBaProcess(struct rtllib_device *ieee, struct tx_ts_record *pTxTS)
 {
-	if (pTxTS->bAddBaReqInProgress == false) {
-		pTxTS->bAddBaReqInProgress = true;
+	if (pTxTS->add_ba_req_in_progress == false) {
+		pTxTS->add_ba_req_in_progress = true;
 
-		if (pTxTS->bAddBaReqDelayed) {
+		if (pTxTS->add_ba_req_delayed) {
 			netdev_dbg(ieee->dev, "Start ADDBA after 60 sec!!\n");
-			mod_timer(&pTxTS->TsAddBaTimer, jiffies +
+			mod_timer(&pTxTS->ts_add_ba_timer, jiffies +
 				  msecs_to_jiffies(TS_ADDBA_DELAY));
 		} else {
 			netdev_dbg(ieee->dev, "Immediately Start ADDBA\n");
-			mod_timer(&pTxTS->TsAddBaTimer, jiffies + 10);
+			mod_timer(&pTxTS->ts_add_ba_timer, jiffies + 10);
 		}
 	} else {
 		netdev_dbg(ieee->dev, "BA timer is already added\n");
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index d2cf3cfaaaba..7b39a1987fdd 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -103,9 +103,6 @@ struct cb_desc {
 	/* Tx Desc Related flags (8-9) */
 	u8 bLastIniPkt:1;
 	u8 bCmdOrInit:1;
-	u8 bFirstSeg:1;
-	u8 bLastSeg:1;
-	u8 bEncrypt:1;
 	u8 tx_dis_rate_fallback:1;
 	u8 tx_use_drv_assinged_rate:1;
 	u8 bHwSec:1;
@@ -117,8 +114,8 @@ struct cb_desc {
 	u8 bRTSEnable:1;
 	u8 bUseShortGI:1;
 	u8 bUseShortPreamble:1;
-	u8 bTxEnableFwCalcDur:1;
-	u8 bAMPDUEnable:1;
+	u8 tx_enable_fw_calc_dur:1;
+	u8 ampdu_enable:1;
 	u8 bRTSSTBC:1;
 	u8 RTSSC:1;
 
@@ -139,7 +136,6 @@ struct cb_desc {
 	u8 bAMSDU:1;
 	u8 bFromAggrQ:1;
 	u8 reserved6:6;
-	u8 macId;
 	u8 priority;
 
 	/* Tx firmware related element(20-27) */
@@ -471,7 +467,6 @@ enum _REG_PREAMBLE_MODE {
  *       any adverse affects.
  */
 struct rtllib_rx_stats {
-	u64 mac_time;
 	s8  rssi;
 	u8  signal;
 	u8  noise;
@@ -1047,7 +1042,7 @@ struct bandwidth_autoswitch {
 #define REORDER_WIN_SIZE	128
 #define REORDER_ENTRY_NUM	128
 struct rx_reorder_entry {
-	struct list_head	List;
+	struct list_head	list;
 	u16			SeqNum;
 	struct rtllib_rxb *prxb;
 };
@@ -1123,8 +1118,8 @@ struct rt_link_detect {
 	u16				SlotNum;
 	u16				SlotIndex;
 
-	u32				NumTxOkInPeriod;
-	u32				NumRxOkInPeriod;
+	u32				num_tx_ok_in_period;
+	u32				num_rx_ok_in_period;
 	u32				NumRxUnicastOkInPeriod;
 	bool				bBusyTraffic;
 	bool				bHigherBusyTraffic;
@@ -1169,7 +1164,7 @@ struct rt_pmkid_list {
 	u8 Bssid[ETH_ALEN];
 	u8 PMKID[16];
 	u8 SsidBuf[33];
-	u8 bUsed;
+	u8 used;
 };
 
 /*************** DRIVER STATUS   *****/
@@ -1192,7 +1187,7 @@ struct rtllib_device {
 	unsigned long status;
 	u8	CntAfterLink;
 
-	enum rt_op_mode OpMode;
+	enum rt_op_mode op_mode;
 
 	/* The last AssocReq/Resp IEs */
 	u8 *assocreq_ies, *assocresp_ies;
@@ -1224,17 +1219,17 @@ struct rtllib_device {
 	u8	HTHighestOperaRate;
 	u8	tx_dis_rate_fallback;
 	u8	tx_use_drv_assinged_rate;
-	u8	bTxEnableFwCalcDur;
+	u8	tx_enable_fw_calc_dur;
 	atomic_t	atm_swbw;
 
 	struct list_head		Tx_TS_Admit_List;
 	struct list_head		Tx_TS_Pending_List;
 	struct list_head		Tx_TS_Unused_List;
-	struct tx_ts_record TxTsRecord[TOTAL_TS_NUM];
+	struct tx_ts_record tx_ts_records[TOTAL_TS_NUM];
 	struct list_head		Rx_TS_Admit_List;
 	struct list_head		Rx_TS_Pending_List;
 	struct list_head		Rx_TS_Unused_List;
-	struct rx_ts_record RxTsRecord[TOTAL_TS_NUM];
+	struct rx_ts_record rx_ts_records[TOTAL_TS_NUM];
 	struct rx_reorder_entry RxReorderEntry[128];
 	struct list_head		RxReorder_Unused_List;
 
@@ -1321,12 +1316,8 @@ struct rtllib_device {
 	u16 scan_watch_dog;
 
 	/* map of allowed channels. 0 is dummy */
-	void *dot11d_info;
-	bool global_domain;
 	u8 active_channel_map[MAX_CHANNEL_NUMBER+1];
 
-	u8   bss_start_channel;
-
 	int rate;       /* current rate */
 	int basic_rate;
 
@@ -1391,7 +1382,7 @@ struct rtllib_device {
 	int mgmt_queue_head;
 	int mgmt_queue_tail;
 	u8 AsocRetryCount;
-	struct sk_buff_head skb_waitQ[MAX_QUEUE_SIZE];
+	struct sk_buff_head skb_waitq[MAX_QUEUE_SIZE];
 
 	bool	bdynamic_txpower_enable;
 
@@ -1411,7 +1402,7 @@ struct rtllib_device {
 	bool FwRWRF;
 
 	struct rt_link_detect link_detect_info;
-	bool bIsAggregateFrame;
+	bool is_aggregate_frame;
 	struct rt_pwr_save_ctrl pwr_save_ctrl;
 
 	/* used if IEEE_SOFTMAC_TX_QUEUE is set */
@@ -1421,7 +1412,6 @@ struct rtllib_device {
 	struct timer_list associate_timer;
 
 	/* used if IEEE_SOFTMAC_BEACONS is set */
-	struct timer_list beacon_timer;
 	u8 need_sw_enc;
 	struct work_struct associate_complete_wq;
 	struct work_struct ips_leave_wq;
@@ -1469,7 +1459,7 @@ struct rtllib_device {
 	 * This function can sleep. the driver should ensure
 	 * the radio has been switched before return.
 	 */
-	void (*set_chan)(struct net_device *dev, short ch);
+	void (*set_chan)(struct net_device *dev, u8 ch);
 
 	/* indicate the driver that the link state is changed
 	 * for example it may indicate the card is associated now.
@@ -1687,8 +1677,8 @@ void rtllib_sta_ps_send_pspoll_frame(struct rtllib_device *ieee);
 void rtllib_start_protocol(struct rtllib_device *ieee);
 void rtllib_stop_protocol(struct rtllib_device *ieee);
 
-void rtllib_EnableNetMonitorMode(struct net_device *dev, bool bInitState);
-void rtllib_DisableNetMonitorMode(struct net_device *dev, bool bInitState);
+void rtllib_enable_net_monitor_mode(struct net_device *dev, bool init_state);
+void rtllib_disable_net_monitor_mode(struct net_device *dev, bool init_state);
 
 void rtllib_softmac_stop_protocol(struct rtllib_device *ieee);
 void rtllib_softmac_start_protocol(struct rtllib_device *ieee);
@@ -1696,7 +1686,6 @@ void rtllib_softmac_start_protocol(struct rtllib_device *ieee);
 void rtllib_reset_queue(struct rtllib_device *ieee);
 void rtllib_wake_all_queues(struct rtllib_device *ieee);
 void rtllib_stop_all_queues(struct rtllib_device *ieee);
-struct sk_buff *rtllib_get_beacon(struct rtllib_device *ieee);
 
 void notify_wx_assoc_event(struct rtllib_device *ieee);
 void rtllib_ps_tx_ack(struct rtllib_device *ieee, short success);
@@ -1758,39 +1747,37 @@ int rtllib_wx_get_rts(struct rtllib_device *ieee, struct iw_request_info *info,
 		      union iwreq_data *wrqu, char *extra);
 #define MAX_RECEIVE_BUFFER_SIZE 9100
 
-void HTSetConnectBwMode(struct rtllib_device *ieee,
+void ht_set_connect_bw_mode(struct rtllib_device *ieee,
 			enum ht_channel_width bandwidth,
 			enum ht_extchnl_offset Offset);
 void ht_update_default_setting(struct rtllib_device *ieee);
-void HTConstructCapabilityElement(struct rtllib_device *ieee,
+void ht_construct_capability_element(struct rtllib_device *ieee,
 				  u8 *posHTCap, u8 *len,
 				  u8 isEncrypt, bool bAssoc);
-void HTConstructInfoElement(struct rtllib_device *ieee,
-			    u8 *posHTInfo, u8 *len, u8 isEncrypt);
-void HTConstructRT2RTAggElement(struct rtllib_device *ieee,
+void ht_construct_rt2rt_agg_element(struct rtllib_device *ieee,
 				u8 *posRT2RTAgg, u8 *len);
-void HTOnAssocRsp(struct rtllib_device *ieee);
-void HTInitializeHTInfo(struct rtllib_device *ieee);
-void HTInitializeBssDesc(struct bss_ht *pBssHT);
-void HTResetSelfAndSavePeerSetting(struct rtllib_device *ieee,
+void ht_on_assoc_rsp(struct rtllib_device *ieee);
+void ht_initialize_ht_info(struct rtllib_device *ieee);
+void ht_initialize_bss_desc(struct bss_ht *pBssHT);
+void ht_reset_self_and_save_peer_setting(struct rtllib_device *ieee,
 				   struct rtllib_network *pNetwork);
 void HT_update_self_and_peer_setting(struct rtllib_device *ieee,
 				     struct rtllib_network *pNetwork);
-u8 HTGetHighestMCSRate(struct rtllib_device *ieee, u8 *pMCSRateSet,
+u8 ht_get_highest_mcs_rate(struct rtllib_device *ieee, u8 *pMCSRateSet,
 		       u8 *pMCSFilter);
 extern u8 MCS_FILTER_ALL[];
 extern u16 MCS_DATA_RATE[2][2][77];
-u8 HTCCheck(struct rtllib_device *ieee, u8 *pFrame);
-void HTResetIOTSetting(struct rt_hi_throughput *ht_info);
-bool IsHTHalfNmodeAPs(struct rtllib_device *ieee);
-u16  TxCountToDataRate(struct rtllib_device *ieee, u8 nDataRate);
+u8 ht_c_check(struct rtllib_device *ieee, u8 *pFrame);
+void ht_reset_iot_setting(struct rt_hi_throughput *ht_info);
+bool is_ht_half_nmode_aps(struct rtllib_device *ieee);
+u16  tx_count_to_data_rate(struct rtllib_device *ieee, u8 nDataRate);
 int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb);
 int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb);
 int rtllib_rx_DELBA(struct rtllib_device *ieee, struct sk_buff *skb);
 void rtllib_ts_init_add_ba(struct rtllib_device *ieee, struct tx_ts_record *ts,
-			   u8 policy, u8 bOverwritePending);
+			   u8 policy, u8 overwrite_pending);
 void rtllib_ts_init_del_ba(struct rtllib_device *ieee,
-			   struct ts_common_info *pTsCommonInfo,
+			   struct ts_common_info *ts_common_info,
 			   enum tr_select TxRxSelect);
 void rtllib_ba_setup_timeout(struct timer_list *t);
 void rtllib_tx_ba_inact_timeout(struct timer_list *t);
diff --git a/drivers/staging/rtl8192e/rtllib_module.c b/drivers/staging/rtl8192e/rtllib_module.c
index 95b6d6b9429c..e7af4a25b0be 100644
--- a/drivers/staging/rtl8192e/rtllib_module.c
+++ b/drivers/staging/rtl8192e/rtllib_module.c
@@ -123,7 +123,7 @@ struct net_device *alloc_rtllib(int sizeof_priv)
 		goto free_softmac;
 
 	ht_update_default_setting(ieee);
-	HTInitializeHTInfo(ieee);
+	ht_initialize_ht_info(ieee);
 	rtllib_ts_init(ieee);
 	for (i = 0; i < IEEE_IBSS_MAC_HASH_SIZE; i++)
 		INIT_LIST_HEAD(&ieee->ibss_mac_hash[i]);
diff --git a/drivers/staging/rtl8192e/rtllib_rx.c b/drivers/staging/rtl8192e/rtllib_rx.c
index ecaa4dec3f94..4df20f4d6bf9 100644
--- a/drivers/staging/rtl8192e/rtllib_rx.c
+++ b/drivers/staging/rtl8192e/rtllib_rx.c
@@ -34,7 +34,6 @@
 #include <linux/ctype.h>
 
 #include "rtllib.h"
-#include "dot11d.h"
 
 static void rtllib_rx_mgt(struct rtllib_device *ieee, struct sk_buff *skb,
 			  struct rtllib_rx_stats *stats);
@@ -412,19 +411,19 @@ static bool AddReorderEntry(struct rx_ts_record *ts,
 	while (pList->next != &ts->rx_pending_pkt_list) {
 		if (SN_LESS(pReorderEntry->SeqNum, ((struct rx_reorder_entry *)
 		    list_entry(pList->next, struct rx_reorder_entry,
-		    List))->SeqNum))
+		    list))->SeqNum))
 			pList = pList->next;
 		else if (SN_EQUAL(pReorderEntry->SeqNum,
 			((struct rx_reorder_entry *)list_entry(pList->next,
-			struct rx_reorder_entry, List))->SeqNum))
+			struct rx_reorder_entry, list))->SeqNum))
 			return false;
 		else
 			break;
 	}
-	pReorderEntry->List.next = pList->next;
-	pReorderEntry->List.next->prev = &pReorderEntry->List;
-	pReorderEntry->List.prev = pList;
-	pList->next = &pReorderEntry->List;
+	pReorderEntry->list.next = pList->next;
+	pReorderEntry->list.next->prev = &pReorderEntry->list;
+	pReorderEntry->list.prev = pList;
+	pList->next = &pReorderEntry->list;
 
 	return true;
 }
@@ -505,15 +504,15 @@ void rtllib_FlushRxTsPendingPkts(struct rtllib_device *ieee,
 
 		pRxReorderEntry = (struct rx_reorder_entry *)
 				  list_entry(ts->rx_pending_pkt_list.prev,
-					     struct rx_reorder_entry, List);
+					     struct rx_reorder_entry, list);
 		netdev_dbg(ieee->dev, "%s(): Indicate SeqNum %d!\n", __func__,
 			   pRxReorderEntry->SeqNum);
-		list_del_init(&pRxReorderEntry->List);
+		list_del_init(&pRxReorderEntry->list);
 
 		ieee->RfdArray[RfdCnt] = pRxReorderEntry->prxb;
 
 		RfdCnt = RfdCnt + 1;
-		list_add_tail(&pRxReorderEntry->List,
+		list_add_tail(&pRxReorderEntry->list,
 			      &ieee->RxReorder_Unused_List);
 	}
 	rtllib_indicate_packets(ieee, ieee->RfdArray, RfdCnt);
@@ -602,8 +601,8 @@ static void RxReorderIndicatePacket(struct rtllib_device *ieee,
 		if (!list_empty(&ieee->RxReorder_Unused_List)) {
 			pReorderEntry = (struct rx_reorder_entry *)
 					list_entry(ieee->RxReorder_Unused_List.next,
-					struct rx_reorder_entry, List);
-			list_del_init(&pReorderEntry->List);
+					struct rx_reorder_entry, list);
+			list_del_init(&pReorderEntry->list);
 
 			/* Make a reorder entry and insert
 			 * into a the packet list.
@@ -618,7 +617,7 @@ static void RxReorderIndicatePacket(struct rtllib_device *ieee,
 					   "%s(): Duplicate packet is dropped. IndicateSeq: %d, NewSeq: %d\n",
 					   __func__, ts->rx_indicate_seq,
 					   SeqNum);
-				list_add_tail(&pReorderEntry->List,
+				list_add_tail(&pReorderEntry->list,
 					      &ieee->RxReorder_Unused_List);
 
 				for (i = 0; i < prxb->nr_subframes; i++)
@@ -658,7 +657,7 @@ static void RxReorderIndicatePacket(struct rtllib_device *ieee,
 		pReorderEntry = (struct rx_reorder_entry *)
 					list_entry(ts->rx_pending_pkt_list.prev,
 						   struct rx_reorder_entry,
-						   List);
+						   list);
 		if (SN_LESS(pReorderEntry->SeqNum, ts->rx_indicate_seq) ||
 		    SN_EQUAL(pReorderEntry->SeqNum, ts->rx_indicate_seq)) {
 			/* This protect struct buffer from overflow. */
@@ -670,7 +669,7 @@ static void RxReorderIndicatePacket(struct rtllib_device *ieee,
 				break;
 			}
 
-			list_del_init(&pReorderEntry->List);
+			list_del_init(&pReorderEntry->list);
 
 			if (SN_EQUAL(pReorderEntry->SeqNum, ts->rx_indicate_seq))
 				ts->rx_indicate_seq = (ts->rx_indicate_seq + 1) %
@@ -681,7 +680,7 @@ static void RxReorderIndicatePacket(struct rtllib_device *ieee,
 				   __func__, pReorderEntry->SeqNum);
 			index++;
 
-			list_add_tail(&pReorderEntry->List,
+			list_add_tail(&pReorderEntry->list,
 				      &ieee->RxReorder_Unused_List);
 		} else {
 			bPktInBuf = true;
@@ -731,7 +730,7 @@ static u8 parse_subframe(struct rtllib_device *ieee, struct sk_buff *skb,
 
 	u16		LLCOffset = sizeof(struct ieee80211_hdr_3addr);
 	u16		ChkLength;
-	bool		bIsAggregateFrame = false;
+	bool		is_aggregate_frame = false;
 	u16		nSubframe_Length;
 	u8		nPadding_Length = 0;
 	u16		SeqNum = 0;
@@ -740,7 +739,7 @@ static u8 parse_subframe(struct rtllib_device *ieee, struct sk_buff *skb,
 	SeqNum = WLAN_GET_SEQ_SEQ(le16_to_cpu(hdr->seq_ctrl));
 	if ((RTLLIB_QOS_HAS_SEQ(fc)) &&
 	   (((union frameqos *)(skb->data + RTLLIB_3ADDR_LEN))->field.reserved))
-		bIsAggregateFrame = true;
+		is_aggregate_frame = true;
 
 	if (RTLLIB_QOS_HAS_SEQ(fc))
 		LLCOffset += 2;
@@ -753,8 +752,8 @@ static u8 parse_subframe(struct rtllib_device *ieee, struct sk_buff *skb,
 		return 0;
 
 	skb_pull(skb, LLCOffset);
-	ieee->bIsAggregateFrame = bIsAggregateFrame;
-	if (!bIsAggregateFrame) {
+	ieee->is_aggregate_frame = is_aggregate_frame;
+	if (!is_aggregate_frame) {
 		rxb->nr_subframes = 1;
 
 		/* altered by clark 3/30/2010
@@ -858,7 +857,7 @@ static size_t rtllib_rx_get_hdrlen(struct rtllib_device *ieee,
 	size_t hdrlen;
 
 	hdrlen = rtllib_get_hdrlen(fc);
-	if (HTCCheck(ieee, skb->data)) {
+	if (ht_c_check(ieee, skb->data)) {
 		if (net_ratelimit())
 			netdev_info(ieee->dev, "%s: find HTCControl!\n",
 				    __func__);
@@ -1151,7 +1150,7 @@ static void rtllib_rx_check_leave_lps(struct rtllib_device *ieee, u8 unicast,
 	if (unicast) {
 		if (ieee->link_state == MAC80211_LINKED) {
 			if (((ieee->link_detect_info.NumRxUnicastOkInPeriod +
-			    ieee->link_detect_info.NumTxOkInPeriod) > 8) ||
+			    ieee->link_detect_info.num_tx_ok_in_period) > 8) ||
 			    (ieee->link_detect_info.NumRxUnicastOkInPeriod > 2)) {
 				ieee->leisure_ps_leave(ieee->dev);
 			}
@@ -1286,7 +1285,7 @@ static int rtllib_rx_InfraAdhoc(struct rtllib_device *ieee, struct sk_buff *skb,
 
 	/* Update statstics for AP roaming */
 	ieee->link_detect_info.NumRecvDataInPeriod++;
-	ieee->link_detect_info.NumRxOkInPeriod++;
+	ieee->link_detect_info.num_rx_ok_in_period++;
 
 	/* Data frame - extract src/dst addresses */
 	rtllib_rx_extract_addr(ieee, hdr, dst, src, bssid);
@@ -1359,7 +1358,7 @@ static int rtllib_rx_InfraAdhoc(struct rtllib_device *ieee, struct sk_buff *skb,
 	/* Update WAPI PN */
 
 	/* Check if leave LPS */
-	if (ieee->bIsAggregateFrame)
+	if (ieee->is_aggregate_frame)
 		nr_subframes = rxb->nr_subframes;
 	else
 		nr_subframes = 1;
@@ -1402,7 +1401,7 @@ static int rtllib_rx_Monitor(struct rtllib_device *ieee, struct sk_buff *skb,
 		return 0;
 	}
 
-	if (HTCCheck(ieee, skb->data)) {
+	if (ht_c_check(ieee, skb->data)) {
 		if (net_ratelimit())
 			netdev_info(ieee->dev, "%s: Find HTCControl!\n",
 				    __func__);
@@ -1663,35 +1662,6 @@ static const char *get_info_element_string(u16 id)
 	}
 }
 
-static inline void rtllib_extract_country_ie(
-	struct rtllib_device *ieee,
-	struct rtllib_info_element *info_element,
-	struct rtllib_network *network,
-	u8 *addr2)
-{
-	if (IS_DOT11D_ENABLE(ieee)) {
-		if (info_element->len != 0) {
-			memcpy(network->CountryIeBuf, info_element->data,
-			       info_element->len);
-			network->CountryIeLen = info_element->len;
-
-			if (!IS_COUNTRY_IE_VALID(ieee)) {
-				if (rtllib_act_scanning(ieee, false) &&
-				    ieee->FirstIe_InScan)
-					netdev_info(ieee->dev,
-						    "Received beacon CountryIE, SSID: <%s>\n",
-						    network->ssid);
-				dot11d_update_country(ieee, addr2,
-						       info_element->len,
-						       info_element->data);
-			}
-		}
-
-		if (IS_EQUAL_CIE_SRC(ieee, addr2))
-			UPDATE_CIE_WATCHDOG(ieee);
-	}
-}
-
 static void rtllib_parse_mife_generic(struct rtllib_device *ieee,
 				      struct rtllib_info_element *info_element,
 				      struct rtllib_network *network,
@@ -2146,8 +2116,6 @@ int rtllib_parse_info_param(struct rtllib_device *ieee,
 		case MFIE_TYPE_COUNTRY:
 			netdev_dbg(ieee->dev, "MFIE_TYPE_COUNTRY: %d bytes\n",
 				   info_element->len);
-			rtllib_extract_country_ie(ieee, info_element, network,
-						  network->bssid);
 			break;
 /* TODO */
 		default:
@@ -2221,7 +2189,7 @@ static inline int rtllib_network_init(
 	network->RSSI = stats->SignalStrength;
 	network->CountryIeLen = 0;
 	memset(network->CountryIeBuf, 0, MAX_IE_LEN);
-	HTInitializeBssDesc(&network->bssht);
+	ht_initialize_bss_desc(&network->bssht);
 	network->flags |= NETWORK_HAS_CCK;
 
 	network->wpa_ie_len = 0;
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 42d652fe8601..b9278b26accd 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -18,7 +18,6 @@
 #include <linux/uaccess.h>
 #include <linux/etherdevice.h>
 #include <linux/ieee80211.h>
-#include "dot11d.h"
 
 static void rtllib_sta_wakeup(struct rtllib_device *ieee, short nl);
 
@@ -45,7 +44,7 @@ static unsigned int rtllib_MFIE_rate_len(struct rtllib_device *ieee)
  * Then it updates the pointer so that
  * it points after the new MFIE tag added.
  */
-static void rtllib_MFIE_Brate(struct rtllib_device *ieee, u8 **tag_p)
+static void rtllib_mfie_brate(struct rtllib_device *ieee, u8 **tag_p)
 {
 	u8 *tag = *tag_p;
 
@@ -62,7 +61,7 @@ static void rtllib_MFIE_Brate(struct rtllib_device *ieee, u8 **tag_p)
 	*tag_p = tag;
 }
 
-static void rtllib_MFIE_Grate(struct rtllib_device *ieee, u8 **tag_p)
+static void rtllib_mfie_grate(struct rtllib_device *ieee, u8 **tag_p)
 {
 	u8 *tag = *tag_p;
 
@@ -83,7 +82,7 @@ static void rtllib_MFIE_Grate(struct rtllib_device *ieee, u8 **tag_p)
 	*tag_p = tag;
 }
 
-static void rtllib_WMM_Info(struct rtllib_device *ieee, u8 **tag_p)
+static void rtllib_wmm_info(struct rtllib_device *ieee, u8 **tag_p)
 {
 	u8 *tag = *tag_p;
 
@@ -99,7 +98,7 @@ static void rtllib_WMM_Info(struct rtllib_device *ieee, u8 **tag_p)
 	*tag_p = tag;
 }
 
-static void rtllib_TURBO_Info(struct rtllib_device *ieee, u8 **tag_p)
+static void rtllib_turbo_info(struct rtllib_device *ieee, u8 **tag_p)
 {
 	u8 *tag = *tag_p;
 
@@ -135,32 +134,33 @@ static void enqueue_mgmt(struct rtllib_device *ieee, struct sk_buff *skb)
 
 static void init_mgmt_queue(struct rtllib_device *ieee)
 {
-	ieee->mgmt_queue_tail = ieee->mgmt_queue_head = 0;
+	ieee->mgmt_queue_tail = 0;
+	ieee->mgmt_queue_head = 0;
 }
 
 u8 MgntQuery_TxRateExcludeCCKRates(struct rtllib_device *ieee)
 {
 	u16	i;
-	u8	QueryRate = 0;
-	u8	BasicRate;
+	u8	query_rate = 0;
+	u8	basic_rate;
 
 	for (i = 0; i < ieee->current_network.rates_len; i++) {
-		BasicRate = ieee->current_network.rates[i] & 0x7F;
-		if (!rtllib_is_cck_rate(BasicRate)) {
-			if (QueryRate == 0) {
-				QueryRate = BasicRate;
+		basic_rate = ieee->current_network.rates[i] & 0x7F;
+		if (!rtllib_is_cck_rate(basic_rate)) {
+			if (query_rate == 0) {
+				query_rate = basic_rate;
 			} else {
-				if (BasicRate < QueryRate)
-					QueryRate = BasicRate;
+				if (basic_rate < query_rate)
+					query_rate = basic_rate;
 			}
 		}
 	}
 
-	if (QueryRate == 0) {
-		QueryRate = 12;
-		netdev_info(ieee->dev, "No BasicRate found!!\n");
+	if (query_rate == 0) {
+		query_rate = 12;
+		netdev_info(ieee->dev, "No basic_rate found!!\n");
 	}
-	return QueryRate;
+	return query_rate;
 }
 
 static u8 MgntQuery_MgntFrameTxRate(struct rtllib_device *ieee)
@@ -173,12 +173,8 @@ static u8 MgntQuery_MgntFrameTxRate(struct rtllib_device *ieee)
 	else
 		rate = ieee->basic_rate & 0x7f;
 
-	if (rate == 0) {
-		if (ieee->mode == WIRELESS_MODE_N_24G && !ht_info->bCurSuppCCK)
-			rate = 0x0c;
-		else
-			rate = 0x02;
-	}
+	if (rate == 0)
+		rate = 0x02;
 
 	return rate;
 }
@@ -240,7 +236,7 @@ inline void softmac_mgmt_xmit(struct sk_buff *skb, struct rtllib_device *ieee)
 		/* check whether the managed packet queued greater than 5 */
 		if (!ieee->check_nic_enough_desc(ieee->dev,
 						 tcb_desc->queue_index) ||
-		    skb_queue_len(&ieee->skb_waitQ[tcb_desc->queue_index]) ||
+		    skb_queue_len(&ieee->skb_waitq[tcb_desc->queue_index]) ||
 		    ieee->queue_stop) {
 			/* insert the skb packet to the management queue
 			 *
@@ -250,7 +246,7 @@ inline void softmac_mgmt_xmit(struct sk_buff *skb, struct rtllib_device *ieee)
 			netdev_info(ieee->dev,
 			       "%s():insert to waitqueue, queue_index:%d!\n",
 			       __func__, tcb_desc->queue_index);
-			skb_queue_tail(&ieee->skb_waitQ[tcb_desc->queue_index],
+			skb_queue_tail(&ieee->skb_waitq[tcb_desc->queue_index],
 				       skb);
 		} else {
 			ieee->softmac_hard_start_xmit(skb, ieee->dev);
@@ -345,65 +341,34 @@ static inline struct sk_buff *rtllib_probe_req(struct rtllib_device *ieee)
 	memcpy(tag, ieee->current_network.ssid, len);
 	tag += len;
 
-	rtllib_MFIE_Brate(ieee, &tag);
-	rtllib_MFIE_Grate(ieee, &tag);
+	rtllib_mfie_brate(ieee, &tag);
+	rtllib_mfie_grate(ieee, &tag);
 
 	return skb;
 }
 
-static struct sk_buff *rtllib_get_beacon_(struct rtllib_device *ieee);
-
-static void rtllib_send_beacon(struct rtllib_device *ieee)
-{
-	struct sk_buff *skb;
-
-	if (!ieee->ieee_up)
-		return;
-	skb = rtllib_get_beacon_(ieee);
-
-	if (skb) {
-		softmac_mgmt_xmit(skb, ieee);
-		ieee->softmac_stats.tx_beacons++;
-	}
-
-	if (ieee->beacon_txing && ieee->ieee_up)
-		mod_timer(&ieee->beacon_timer, jiffies +
-			  (msecs_to_jiffies(ieee->current_network.beacon_interval - 5)));
-}
-
-static void rtllib_send_beacon_cb(struct timer_list *t)
-{
-	struct rtllib_device *ieee =
-		from_timer(ieee, t, beacon_timer);
-	unsigned long flags;
-
-	spin_lock_irqsave(&ieee->beacon_lock, flags);
-	rtllib_send_beacon(ieee);
-	spin_unlock_irqrestore(&ieee->beacon_lock, flags);
-}
-
 /* Enables network monitor mode, all rx packets will be received. */
-void rtllib_EnableNetMonitorMode(struct net_device *dev,
-		bool bInitState)
+void rtllib_enable_net_monitor_mode(struct net_device *dev,
+		bool init_state)
 {
 	struct rtllib_device *ieee = netdev_priv_rsl(dev);
 
 	netdev_info(dev, "========>Enter Monitor Mode\n");
 
-	ieee->AllowAllDestAddrHandler(dev, true, !bInitState);
+	ieee->AllowAllDestAddrHandler(dev, true, !init_state);
 }
 
 /* Disables network monitor mode. Only packets destinated to
  * us will be received.
  */
-void rtllib_DisableNetMonitorMode(struct net_device *dev,
-		bool bInitState)
+void rtllib_disable_net_monitor_mode(struct net_device *dev,
+		bool init_state)
 {
 	struct rtllib_device *ieee = netdev_priv_rsl(dev);
 
 	netdev_info(dev, "========>Exit Monitor Mode\n");
 
-	ieee->AllowAllDestAddrHandler(dev, false, !bInitState);
+	ieee->AllowAllDestAddrHandler(dev, false, !init_state);
 }
 
 static void rtllib_send_probe(struct rtllib_device *ieee)
@@ -425,12 +390,6 @@ static void rtllib_send_probe_requests(struct rtllib_device *ieee)
 	}
 }
 
-static void rtllib_update_active_chan_map(struct rtllib_device *ieee)
-{
-	memcpy(ieee->active_channel_map, GET_DOT11D_INFO(ieee)->channel_map,
-	       MAX_CHANNEL_NUMBER + 1);
-}
-
 /* this performs syncro scan blocking the caller until all channels
  * in the allowed channel map has been checked.
  */
@@ -439,8 +398,6 @@ static void rtllib_softmac_scan_syncro(struct rtllib_device *ieee)
 	union iwreq_data wrqu;
 	short ch = 0;
 
-	rtllib_update_active_chan_map(ieee);
-
 	ieee->be_scan_inprogress = true;
 
 	mutex_lock(&ieee->scan_mutex);
@@ -492,10 +449,6 @@ out:
 	ieee->actscanning = false;
 	ieee->sync_scan_hurryup = 0;
 
-	if (ieee->link_state >= MAC80211_LINKED) {
-		if (IS_DOT11D_ENABLE(ieee))
-			dot11d_scan_complete(ieee);
-	}
 	mutex_unlock(&ieee->scan_mutex);
 
 	ieee->be_scan_inprogress = false;
@@ -510,8 +463,6 @@ static void rtllib_softmac_scan_wq(void *data)
 				     struct rtllib_device, softmac_scan_wq);
 	u8 last_channel = ieee->current_network.channel;
 
-	rtllib_update_active_chan_map(ieee);
-
 	if (!ieee->ieee_up)
 		return;
 	if (rtllib_act_scanning(ieee, true))
@@ -552,8 +503,6 @@ static void rtllib_softmac_scan_wq(void *data)
 	return;
 
 out:
-	if (IS_DOT11D_ENABLE(ieee))
-		dot11d_scan_complete(ieee);
 	ieee->current_network.channel = last_channel;
 
 out1:
@@ -609,10 +558,6 @@ static void rtllib_start_scan(struct rtllib_device *ieee)
 {
 	ieee->rtllib_ips_leave_wq(ieee->dev);
 
-	if (IS_DOT11D_ENABLE(ieee)) {
-		if (IS_COUNTRY_IE_VALID(ieee))
-			RESET_CIE_WATCHDOG(ieee);
-	}
 	if (ieee->softmac_features & IEEE_SOFTMAC_SCAN) {
 		if (ieee->scanning_continue == 0) {
 			ieee->actscanning = true;
@@ -625,10 +570,6 @@ static void rtllib_start_scan(struct rtllib_device *ieee)
 /* called with wx_mutex held */
 void rtllib_start_scan_syncro(struct rtllib_device *ieee)
 {
-	if (IS_DOT11D_ENABLE(ieee)) {
-		if (IS_COUNTRY_IE_VALID(ieee))
-			RESET_CIE_WATCHDOG(ieee);
-	}
 	ieee->sync_scan_hurryup = 0;
 	if (ieee->softmac_features & IEEE_SOFTMAC_SCAN)
 		rtllib_softmac_scan_syncro(ieee);
@@ -677,152 +618,6 @@ rtllib_authentication_req(struct rtllib_network *beacon,
 	return skb;
 }
 
-static struct sk_buff *rtllib_probe_resp(struct rtllib_device *ieee,
-					 const u8 *dest)
-{
-	u8 *tag;
-	int beacon_size;
-	struct rtllib_probe_response *beacon_buf;
-	struct sk_buff *skb = NULL;
-	int encrypt;
-	int atim_len, erp_len;
-	struct lib80211_crypt_data *crypt;
-
-	char *ssid = ieee->current_network.ssid;
-	int ssid_len = ieee->current_network.ssid_len;
-	int rate_len = ieee->current_network.rates_len + 2;
-	int rate_ex_len = ieee->current_network.rates_ex_len;
-	int wpa_ie_len = ieee->wpa_ie_len;
-	u8 erpinfo_content = 0;
-
-	u8 *tmp_ht_cap_buf = NULL;
-	u8 tmp_ht_cap_len = 0;
-	u8 *tmp_ht_info_buf = NULL;
-	u8 tmp_ht_info_len = 0;
-	struct rt_hi_throughput *ht_info = ieee->ht_info;
-	u8 *tmp_generic_ie_buf = NULL;
-	u8 tmp_generic_ie_len = 0;
-
-	if (rate_ex_len > 0)
-		rate_ex_len += 2;
-
-	if (ieee->current_network.capability & WLAN_CAPABILITY_IBSS)
-		atim_len = 4;
-	else
-		atim_len = 0;
-
-	if ((ieee->current_network.mode == WIRELESS_MODE_G) ||
-	   (ieee->current_network.mode == WIRELESS_MODE_N_24G &&
-	   ieee->ht_info->bCurSuppCCK)) {
-		erp_len = 3;
-		erpinfo_content = 0;
-		if (ieee->current_network.buseprotection)
-			erpinfo_content |= ERP_UseProtection;
-	} else {
-		erp_len = 0;
-	}
-
-	crypt = ieee->crypt_info.crypt[ieee->crypt_info.tx_keyidx];
-	encrypt = crypt && crypt->ops &&
-		((strcmp(crypt->ops->name, "R-WEP") == 0 || wpa_ie_len));
-	if (ieee->ht_info->current_ht_support) {
-		tmp_ht_cap_buf = (u8 *)&(ieee->ht_info->SelfHTCap);
-		tmp_ht_cap_len = sizeof(ieee->ht_info->SelfHTCap);
-		tmp_ht_info_buf = (u8 *)&(ieee->ht_info->SelfHTInfo);
-		tmp_ht_info_len = sizeof(ieee->ht_info->SelfHTInfo);
-		HTConstructCapabilityElement(ieee, tmp_ht_cap_buf,
-					     &tmp_ht_cap_len, encrypt, false);
-		HTConstructInfoElement(ieee, tmp_ht_info_buf, &tmp_ht_info_len,
-				       encrypt);
-
-		if (ht_info->reg_rt2rt_aggregation) {
-			tmp_generic_ie_buf = ieee->ht_info->sz_rt2rt_agg_buf;
-			tmp_generic_ie_len =
-				 sizeof(ieee->ht_info->sz_rt2rt_agg_buf);
-			HTConstructRT2RTAggElement(ieee, tmp_generic_ie_buf,
-						   &tmp_generic_ie_len);
-		}
-	}
-
-	beacon_size = sizeof(struct rtllib_probe_response) + 2 +
-		ssid_len + 3 + rate_len + rate_ex_len + atim_len + erp_len
-		+ wpa_ie_len + ieee->tx_headroom;
-	skb = dev_alloc_skb(beacon_size);
-	if (!skb)
-		return NULL;
-
-	skb_reserve(skb, ieee->tx_headroom);
-
-	beacon_buf = skb_put(skb, (beacon_size - ieee->tx_headroom));
-	ether_addr_copy(beacon_buf->header.addr1, dest);
-	ether_addr_copy(beacon_buf->header.addr2, ieee->dev->dev_addr);
-	ether_addr_copy(beacon_buf->header.addr3, ieee->current_network.bssid);
-
-	beacon_buf->header.duration_id = 0;
-	beacon_buf->beacon_interval =
-		cpu_to_le16(ieee->current_network.beacon_interval);
-	beacon_buf->capability =
-		cpu_to_le16(ieee->current_network.capability &
-		WLAN_CAPABILITY_IBSS);
-	beacon_buf->capability |=
-		cpu_to_le16(ieee->current_network.capability &
-		WLAN_CAPABILITY_SHORT_PREAMBLE);
-
-	if (ieee->current_network.capability & WLAN_CAPABILITY_SHORT_SLOT_TIME)
-		beacon_buf->capability |=
-			cpu_to_le16(WLAN_CAPABILITY_SHORT_SLOT_TIME);
-
-	crypt = ieee->crypt_info.crypt[ieee->crypt_info.tx_keyidx];
-	if (encrypt)
-		beacon_buf->capability |= cpu_to_le16(WLAN_CAPABILITY_PRIVACY);
-
-	beacon_buf->header.frame_control = cpu_to_le16(IEEE80211_STYPE_PROBE_RESP);
-	beacon_buf->info_element[0].id = MFIE_TYPE_SSID;
-	beacon_buf->info_element[0].len = ssid_len;
-
-	tag = (u8 *)beacon_buf->info_element[0].data;
-
-	memcpy(tag, ssid, ssid_len);
-
-	tag += ssid_len;
-
-	*(tag++) = MFIE_TYPE_RATES;
-	*(tag++) = rate_len - 2;
-	memcpy(tag, ieee->current_network.rates, rate_len - 2);
-	tag += rate_len - 2;
-
-	*(tag++) = MFIE_TYPE_DS_SET;
-	*(tag++) = 1;
-	*(tag++) = ieee->current_network.channel;
-
-	if (atim_len) {
-		u16 val16;
-		*(tag++) = MFIE_TYPE_IBSS_SET;
-		*(tag++) = 2;
-		val16 = ieee->current_network.atim_window;
-		memcpy((u8 *)tag, (u8 *)&val16, 2);
-		tag += 2;
-	}
-
-	if (erp_len) {
-		*(tag++) = MFIE_TYPE_ERP;
-		*(tag++) = 1;
-		*(tag++) = erpinfo_content;
-	}
-	if (rate_ex_len) {
-		*(tag++) = MFIE_TYPE_RATES_EX;
-		*(tag++) = rate_ex_len - 2;
-		memcpy(tag, ieee->current_network.rates_ex, rate_ex_len - 2);
-		tag += rate_ex_len - 2;
-	}
-
-	if (wpa_ie_len) {
-		memcpy(tag, ieee->wpa_ie, ieee->wpa_ie_len);
-		tag += ieee->wpa_ie_len;
-	}
-	return skb;
-}
-
 static struct sk_buff *rtllib_null_func(struct rtllib_device *ieee, short pwr)
 {
 	struct sk_buff *skb;
@@ -875,7 +670,7 @@ static inline int SecIsInPMKIDList(struct rtllib_device *ieee, u8 *bssid)
 	int i = 0;
 
 	do {
-		if ((ieee->PMKIDList[i].bUsed) &&
+		if ((ieee->PMKIDList[i].used) &&
 		   (memcmp(ieee->PMKIDList[i].Bssid, bssid, ETH_ALEN) == 0))
 			break;
 		i++;
@@ -933,15 +728,15 @@ rtllib_association_req(struct rtllib_network *beacon,
 	}
 
 	if (ieee->ht_info->current_ht_support && ieee->ht_info->enable_ht) {
-		ht_cap_buf = (u8 *)&(ieee->ht_info->SelfHTCap);
+		ht_cap_buf = (u8 *)&ieee->ht_info->SelfHTCap;
 		ht_cap_len = sizeof(ieee->ht_info->SelfHTCap);
-		HTConstructCapabilityElement(ieee, ht_cap_buf, &ht_cap_len,
+		ht_construct_capability_element(ieee, ht_cap_buf, &ht_cap_len,
 					     encrypt, true);
 		if (ieee->ht_info->current_rt2rt_aggregation) {
 			realtek_ie_buf = ieee->ht_info->sz_rt2rt_agg_buf;
 			realtek_ie_len =
 				 sizeof(ieee->ht_info->sz_rt2rt_agg_buf);
-			HTConstructRT2RTAggElement(ieee, realtek_ie_buf,
+			ht_construct_rt2rt_agg_element(ieee, realtek_ie_buf,
 						   &realtek_ie_len);
 		}
 	}
@@ -1071,7 +866,7 @@ rtllib_association_req(struct rtllib_network *beacon,
 		tag += osCcxVerNum.Length;
 	}
 	if (ieee->ht_info->current_ht_support && ieee->ht_info->enable_ht) {
-		if (ieee->ht_info->ePeerHTSpecVer != HT_SPEC_VER_EWC) {
+		if (ieee->ht_info->peer_ht_spec_ver != HT_SPEC_VER_EWC) {
 			tag = skb_put(skb, ht_cap_len);
 			*tag++ = MFIE_TYPE_HT_CAP;
 			*tag++ = ht_cap_len - 2;
@@ -1093,7 +888,7 @@ rtllib_association_req(struct rtllib_network *beacon,
 	}
 	if (wmm_info_len) {
 		tag = skb_put(skb, wmm_info_len);
-		rtllib_WMM_Info(ieee, &tag);
+		rtllib_wmm_info(ieee, &tag);
 	}
 
 	if (wps_ie_len && ieee->wps_ie)
@@ -1101,11 +896,11 @@ rtllib_association_req(struct rtllib_network *beacon,
 
 	if (turbo_info_len) {
 		tag = skb_put(skb, turbo_info_len);
-		rtllib_TURBO_Info(ieee, &tag);
+		rtllib_turbo_info(ieee, &tag);
 	}
 
 	if (ieee->ht_info->current_ht_support && ieee->ht_info->enable_ht) {
-		if (ieee->ht_info->ePeerHTSpecVer == HT_SPEC_VER_EWC) {
+		if (ieee->ht_info->peer_ht_spec_ver == HT_SPEC_VER_EWC) {
 			tag = skb_put(skb, ht_cap_len);
 			*tag++ = MFIE_TYPE_GENERIC;
 			*tag++ = ht_cap_len - 2;
@@ -1123,7 +918,7 @@ rtllib_association_req(struct rtllib_network *beacon,
 
 	kfree(ieee->assocreq_ies);
 	ieee->assocreq_ies = NULL;
-	ies = &(hdr->info_element[0].id);
+	ies = &hdr->info_element[0].id;
 	ieee->assocreq_ies_len = (skb->data + skb->len) - ies;
 	ieee->assocreq_ies = kmemdup(ies, ieee->assocreq_ies_len, GFP_ATOMIC);
 	if (!ieee->assocreq_ies)
@@ -1269,7 +1064,7 @@ static void rtllib_associate_complete_wq(void *data)
 	}
 	if (ieee->ht_info->current_ht_support && ieee->ht_info->enable_ht) {
 		netdev_info(ieee->dev, "Successfully associated, ht enabled\n");
-		HTOnAssocRsp(ieee);
+		ht_on_assoc_rsp(ieee);
 	} else {
 		netdev_info(ieee->dev,
 			    "Successfully associated, ht not enabled(%d, %d)\n",
@@ -1314,7 +1109,7 @@ static void rtllib_associate_procedure_wq(void *data)
 	mutex_lock(&ieee->wx_mutex);
 
 	rtllib_stop_scan(ieee);
-	HTSetConnectBwMode(ieee, HT_CHANNEL_WIDTH_20, HT_EXTCHNL_OFFSET_NO_EXT);
+	ht_set_connect_bw_mode(ieee, HT_CHANNEL_WIDTH_20, HT_EXTCHNL_OFFSET_NO_EXT);
 	if (ieee->rf_power_state == rf_off) {
 		ieee->rtllib_ips_leave_wq(ieee->dev);
 		mutex_unlock(&ieee->wx_mutex);
@@ -1417,21 +1212,20 @@ inline void rtllib_softmac_new_net(struct rtllib_device *ieee,
 			   !(ieee->softmac_features & IEEE_SOFTMAC_SCAN))
 				rtllib_stop_scan_syncro(ieee);
 
-			HTResetIOTSetting(ieee->ht_info);
+			ht_reset_iot_setting(ieee->ht_info);
 			ieee->wmm_acm = 0;
 			if (ieee->iw_mode == IW_MODE_INFRA) {
 				/* Join the network for the first time */
 				ieee->AsocRetryCount = 0;
 				if ((ieee->current_network.qos_data.supported == 1) &&
 				    ieee->current_network.bssht.bd_support_ht)
-					HTResetSelfAndSavePeerSetting(ieee,
+					ht_reset_self_and_save_peer_setting(ieee,
 						 &(ieee->current_network));
 				else
 					ieee->ht_info->current_ht_support = false;
 
 				ieee->link_state = RTLLIB_ASSOCIATING;
-				schedule_delayed_work(
-					   &ieee->associate_procedure_wq, 0);
+				schedule_delayed_work(&ieee->associate_procedure_wq, 0);
 			} else {
 				if (rtllib_is_54g(&ieee->current_network)) {
 					ieee->rate = 108;
@@ -1825,7 +1619,7 @@ rtllib_rx_assoc_resp(struct rtllib_device *ieee, struct sk_buff *skb,
 
 			kfree(ieee->assocresp_ies);
 			ieee->assocresp_ies = NULL;
-			ies = &(assoc_resp->info_element[0].id);
+			ies = &assoc_resp->info_element[0].id;
 			ieee->assocresp_ies_len = (skb->data + skb->len) - ies;
 			ieee->assocresp_ies = kmemdup(ies,
 						      ieee->assocresp_ies_len,
@@ -1841,8 +1635,7 @@ rtllib_rx_assoc_resp(struct rtllib_device *ieee, struct sk_buff *skb,
 				    "Association response status code 0x%x\n",
 				    errcode);
 			if (ieee->AsocRetryCount < RT_ASOC_RETRY_LIMIT)
-				schedule_delayed_work(
-					 &ieee->associate_procedure_wq, 0);
+				schedule_delayed_work(&ieee->associate_procedure_wq, 0);
 			else
 				rtllib_associate_abort(ieee);
 		}
@@ -1872,7 +1665,7 @@ static void rtllib_rx_auth_resp(struct rtllib_device *ieee, struct sk_buff *skb)
 		ieee->softmac_stats.rx_auth_rs_ok++;
 		if (!(ieee->ht_info->iot_action & HT_IOT_ACT_PURE_N_MODE)) {
 			if (!ieee->GetNmodeSupportBySecCfg(ieee->dev)) {
-				if (IsHTHalfNmodeAPs(ieee)) {
+				if (is_ht_half_nmode_aps(ieee)) {
 					bSupportNmode = true;
 					bHalfSupportNmode = true;
 				} else {
@@ -2030,7 +1823,7 @@ void rtllib_softmac_xmit(struct rtllib_txb *txb, struct rtllib_device *ieee)
 	 * the wait queue
 	 */
 	for (i = 0; i < txb->nr_frags; i++) {
-		queue_len = skb_queue_len(&ieee->skb_waitQ[queue_index]);
+		queue_len = skb_queue_len(&ieee->skb_waitq[queue_index]);
 		if ((queue_len  != 0) ||
 		    (!ieee->check_nic_enough_desc(ieee->dev, queue_index)) ||
 		    (ieee->queue_stop)) {
@@ -2039,13 +1832,12 @@ void rtllib_softmac_xmit(struct rtllib_txb *txb, struct rtllib_device *ieee)
 			 * to check it any more.
 			 */
 			if (queue_len < 200)
-				skb_queue_tail(&ieee->skb_waitQ[queue_index],
+				skb_queue_tail(&ieee->skb_waitq[queue_index],
 					       txb->fragments[i]);
 			else
 				kfree_skb(txb->fragments[i]);
 		} else {
-			ieee->softmac_data_hard_start_xmit(
-					txb->fragments[i],
+			ieee->softmac_data_hard_start_xmit(txb->fragments[i],
 					ieee->dev, ieee->rate);
 		}
 	}
@@ -2090,10 +1882,6 @@ static void rtllib_start_bss(struct rtllib_device *ieee)
 {
 	unsigned long flags;
 
-	if (IS_DOT11D_ENABLE(ieee) && !IS_COUNTRY_IE_VALID(ieee)) {
-		if (!ieee->global_domain)
-			return;
-	}
 	/* check if we have already found the net we
 	 * are interested in (if any).
 	 * if not (we are disassociated and we are not
@@ -2121,6 +1909,7 @@ static void rtllib_link_change_wq(void *data)
 				     struct rtllib_device, link_change_wq);
 	ieee->link_change(ieee->dev);
 }
+
 /* called only in userspace context */
 void rtllib_disassociate(struct rtllib_device *ieee)
 {
@@ -2128,8 +1917,6 @@ void rtllib_disassociate(struct rtllib_device *ieee)
 	if (ieee->softmac_features & IEEE_SOFTMAC_TX_QUEUE)
 		rtllib_reset_queue(ieee);
 
-	if (IS_DOT11D_ENABLE(ieee))
-		dot11d_reset(ieee);
 	ieee->link_state = MAC80211_NOLINK;
 	ieee->is_set_key = false;
 	ieee->wap_set = 0;
@@ -2181,46 +1968,6 @@ exit:
 	mutex_unlock(&ieee->wx_mutex);
 }
 
-static struct sk_buff *rtllib_get_beacon_(struct rtllib_device *ieee)
-{
-	static const u8 broadcast_addr[] = {
-		0xff, 0xff, 0xff, 0xff, 0xff, 0xff
-	};
-	struct sk_buff *skb;
-	struct rtllib_probe_response *b;
-
-	skb = rtllib_probe_resp(ieee, broadcast_addr);
-
-	if (!skb)
-		return NULL;
-
-	b = (struct rtllib_probe_response *)skb->data;
-	b->header.frame_control = cpu_to_le16(IEEE80211_STYPE_BEACON);
-
-	return skb;
-}
-
-struct sk_buff *rtllib_get_beacon(struct rtllib_device *ieee)
-{
-	struct sk_buff *skb;
-	struct rtllib_probe_response *b;
-
-	skb = rtllib_get_beacon_(ieee);
-	if (!skb)
-		return NULL;
-
-	b = (struct rtllib_probe_response *)skb->data;
-	b->header.seq_ctrl = cpu_to_le16(ieee->seq_ctrl[0] << 4);
-
-	if (ieee->seq_ctrl[0] == 0xFFF)
-		ieee->seq_ctrl[0] = 0;
-	else
-		ieee->seq_ctrl[0]++;
-
-	return skb;
-}
-EXPORT_SYMBOL(rtllib_get_beacon);
-
 void rtllib_softmac_stop_protocol(struct rtllib_device *ieee)
 {
 	rtllib_stop_scan_syncro(ieee);
@@ -2279,8 +2026,6 @@ void rtllib_start_protocol(struct rtllib_device *ieee)
 	short ch = 0;
 	int i = 0;
 
-	rtllib_update_active_chan_map(ieee);
-
 	if (ieee->proto_started)
 		return;
 
@@ -2326,18 +2071,15 @@ int rtllib_softmac_init(struct rtllib_device *ieee)
 	ieee->link_state = MAC80211_NOLINK;
 	for (i = 0; i < 5; i++)
 		ieee->seq_ctrl[i] = 0;
-	ieee->dot11d_info = kzalloc(sizeof(struct rt_dot11d_info), GFP_ATOMIC);
-	if (!ieee->dot11d_info)
-		return -ENOMEM;
 
 	ieee->link_detect_info.SlotIndex = 0;
 	ieee->link_detect_info.SlotNum = 2;
 	ieee->link_detect_info.NumRecvBcnInPeriod = 0;
 	ieee->link_detect_info.NumRecvDataInPeriod = 0;
-	ieee->link_detect_info.NumTxOkInPeriod = 0;
-	ieee->link_detect_info.NumRxOkInPeriod = 0;
+	ieee->link_detect_info.num_tx_ok_in_period = 0;
+	ieee->link_detect_info.num_rx_ok_in_period = 0;
 	ieee->link_detect_info.NumRxUnicastOkInPeriod = 0;
-	ieee->bIsAggregateFrame = false;
+	ieee->is_aggregate_frame = false;
 	ieee->assoc_id = 0;
 	ieee->queue_stop = 0;
 	ieee->scanning_continue = 0;
@@ -2369,8 +2111,6 @@ int rtllib_softmac_init(struct rtllib_device *ieee)
 
 	timer_setup(&ieee->associate_timer, rtllib_associate_abort_cb, 0);
 
-	timer_setup(&ieee->beacon_timer, rtllib_send_beacon_cb, 0);
-
 	INIT_DELAYED_WORK(&ieee->link_change_wq, (void *)rtllib_link_change_wq);
 	INIT_WORK(&ieee->associate_complete_wq, (void *)rtllib_associate_complete_wq);
 	INIT_DELAYED_WORK(&ieee->associate_procedure_wq, (void *)rtllib_associate_procedure_wq);
@@ -2404,9 +2144,6 @@ void rtllib_softmac_free(struct rtllib_device *ieee)
 	cancel_work_sync(&ieee->ips_leave_wq);
 	cancel_work_sync(&ieee->wx_sync_scan_wq);
 	cancel_work_sync(&ieee->ps_task);
-
-	kfree(ieee->dot11d_info);
-	ieee->dot11d_info = NULL;
 }
 
 static inline struct sk_buff *
@@ -2493,7 +2230,7 @@ u8 rtllib_ap_sec_type(struct rtllib_device *ieee)
 		return SEC_ALG_WEP;
 	} else if ((wpa_ie_len != 0)) {
 		if (((ieee->wpa_ie[0] == 0xdd) &&
-		    (!memcmp(&(ieee->wpa_ie[14]), ccmp_ie, 4))) ||
+		    (!memcmp(&ieee->wpa_ie[14], ccmp_ie, 4))) ||
 		    ((ieee->wpa_ie[0] == 0x30) &&
 		    (!memcmp(&ieee->wpa_ie[10], ccmp_rsn_ie, 4))))
 			return SEC_ALG_CCMP;
@@ -2508,7 +2245,7 @@ static void rtllib_MlmeDisassociateRequest(struct rtllib_device *rtllib,
 					   u8 *asSta, u8 asRsn)
 {
 	u8 i;
-	u8	OpMode;
+	u8	op_mode;
 
 	RemovePeerTS(rtllib, asSta);
 
@@ -2517,10 +2254,10 @@ static void rtllib_MlmeDisassociateRequest(struct rtllib_device *rtllib,
 
 		for (i = 0; i < 6; i++)
 			rtllib->current_network.bssid[i] = 0x22;
-		OpMode = RT_OP_MODE_NO_LINK;
-		rtllib->OpMode = RT_OP_MODE_NO_LINK;
+		op_mode = RT_OP_MODE_NO_LINK;
+		rtllib->op_mode = RT_OP_MODE_NO_LINK;
 		rtllib->SetHwRegHandler(rtllib->dev, HW_VAR_MEDIA_STATUS,
-					(u8 *)(&OpMode));
+					(u8 *)(&op_mode));
 		rtllib_disassociate(rtllib);
 
 		rtllib->SetHwRegHandler(rtllib->dev, HW_VAR_BSSID,
@@ -2528,11 +2265,7 @@ static void rtllib_MlmeDisassociateRequest(struct rtllib_device *rtllib,
 	}
 }
 
-static void
-rtllib_MgntDisconnectAP(
-	struct rtllib_device *rtllib,
-	u8 asRsn
-)
+static void rtllib_MgntDisconnectAP(struct rtllib_device *rtllib, u8 asRsn)
 {
 	bool bFilterOutNonAssociatedBSSID = false;
 
diff --git a/drivers/staging/rtl8192e/rtllib_softmac_wx.c b/drivers/staging/rtl8192e/rtllib_softmac_wx.c
index f32584291704..2afa701e5445 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac_wx.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac_wx.c
@@ -14,7 +14,6 @@
 #include <linux/etherdevice.h>
 
 #include "rtllib.h"
-#include "dot11d.h"
 
 int rtllib_wx_set_freq(struct rtllib_device *ieee, struct iw_request_info *a,
 			     union iwreq_data *wrqu, char *b)
@@ -208,7 +207,7 @@ int rtllib_wx_get_rate(struct rtllib_device *ieee,
 {
 	u32 tmp_rate;
 
-	tmp_rate = TxCountToDataRate(ieee,
+	tmp_rate = tx_count_to_data_rate(ieee,
 				     ieee->softmac_stats.CurrentShowTxate);
 	wrqu->bitrate.value = tmp_rate * 500000;
 
@@ -267,11 +266,11 @@ int rtllib_wx_set_mode(struct rtllib_device *ieee, struct iw_request_info *a,
 
 	if (wrqu->mode == IW_MODE_MONITOR) {
 		ieee->dev->type = ARPHRD_IEEE80211;
-		rtllib_EnableNetMonitorMode(ieee->dev, false);
+		rtllib_enable_net_monitor_mode(ieee->dev, false);
 	} else {
 		ieee->dev->type = ARPHRD_ETHER;
 		if (ieee->iw_mode == IW_MODE_MONITOR)
-			rtllib_DisableNetMonitorMode(ieee->dev, false);
+			rtllib_disable_net_monitor_mode(ieee->dev, false);
 	}
 
 	if (!ieee->proto_started) {
@@ -318,10 +317,10 @@ void rtllib_wx_sync_scan_wq(void *data)
 	ieee->ScanOperationBackupHandler(ieee->dev, SCAN_OPT_BACKUP);
 
 	if (ieee->ht_info->current_ht_support && ieee->ht_info->enable_ht &&
-	    ieee->ht_info->bCurBW40MHz) {
+	    ieee->ht_info->cur_bw_40mhz) {
 		b40M = 1;
 		chan_offset = ieee->ht_info->CurSTAExtChnlOffset;
-		bandwidth = (enum ht_channel_width)ieee->ht_info->bCurBW40MHz;
+		bandwidth = (enum ht_channel_width)ieee->ht_info->cur_bw_40mhz;
 		ieee->set_bw_mode_handler(ieee->dev, HT_CHANNEL_WIDTH_20,
 				       HT_EXTCHNL_OFFSET_NO_EXT);
 	}
diff --git a/drivers/staging/rtl8192e/rtllib_tx.c b/drivers/staging/rtl8192e/rtllib_tx.c
index 9bf679438ad1..f7098a2ba8b0 100644
--- a/drivers/staging/rtl8192e/rtllib_tx.c
+++ b/drivers/staging/rtl8192e/rtllib_tx.c
@@ -267,7 +267,7 @@ static void rtllib_tx_query_agg_cap(struct rtllib_device *ieee,
 				    struct cb_desc *tcb_desc)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
-	struct tx_ts_record *pTxTs = NULL;
+	struct tx_ts_record *ts = NULL;
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 
 	if (rtllib_act_scanning(ieee, false))
@@ -288,52 +288,35 @@ static void rtllib_tx_query_agg_cap(struct rtllib_device *ieee,
 
 	if (!ieee->GetNmodeSupportBySecCfg(ieee->dev))
 		return;
-	if (ht_info->bCurrentAMPDUEnable) {
-		if (!rtllib_get_ts(ieee, (struct ts_common_info **)(&pTxTs), hdr->addr1,
+	if (ht_info->current_ampdu_enable) {
+		if (!rtllib_get_ts(ieee, (struct ts_common_info **)(&ts), hdr->addr1,
 			   skb->priority, TX_DIR, true)) {
 			netdev_info(ieee->dev, "%s: can't get TS\n", __func__);
 			return;
 		}
-		if (!pTxTs->TxAdmittedBARecord.b_valid) {
+		if (!ts->tx_admitted_ba_record.b_valid) {
 			if (ieee->wpa_ie_len && (ieee->pairwise_key_type ==
 			    KEY_TYPE_NA)) {
 				;
 			} else if (tcb_desc->bdhcp == 1) {
 				;
-			} else if (!pTxTs->bDisable_AddBa) {
-				TsStartAddBaProcess(ieee, pTxTs);
+			} else if (!ts->disable_add_ba) {
+				TsStartAddBaProcess(ieee, ts);
 			}
-			goto FORCED_AGG_SETTING;
-		} else if (!pTxTs->bUsingBa) {
-			if (SN_LESS(pTxTs->TxAdmittedBARecord.ba_start_seq_ctrl.field.seq_num,
-				    (pTxTs->TxCurSeq + 1) % 4096))
-				pTxTs->bUsingBa = true;
+			return;
+		} else if (!ts->using_ba) {
+			if (SN_LESS(ts->tx_admitted_ba_record.ba_start_seq_ctrl.field.seq_num,
+				    (ts->tx_cur_seq + 1) % 4096))
+				ts->using_ba = true;
 			else
-				goto FORCED_AGG_SETTING;
+				return;
 		}
 		if (ieee->iw_mode == IW_MODE_INFRA) {
-			tcb_desc->bAMPDUEnable = true;
+			tcb_desc->ampdu_enable = true;
 			tcb_desc->ampdu_factor = ht_info->CurrentAMPDUFactor;
 			tcb_desc->ampdu_density = ht_info->current_mpdu_density;
 		}
 	}
-FORCED_AGG_SETTING:
-	switch (ht_info->ForcedAMPDUMode) {
-	case HT_AGG_AUTO:
-		break;
-
-	case HT_AGG_FORCE_ENABLE:
-		tcb_desc->bAMPDUEnable = true;
-		tcb_desc->ampdu_density = ht_info->forced_mpdu_density;
-		tcb_desc->ampdu_factor = ht_info->forced_ampdu_factor;
-		break;
-
-	case HT_AGG_FORCE_DISABLE:
-		tcb_desc->bAMPDUEnable = false;
-		tcb_desc->ampdu_density = 0;
-		tcb_desc->ampdu_factor = 0;
-		break;
-	}
 }
 
 static void rtllib_query_ShortPreambleMode(struct rtllib_device *ieee,
@@ -357,14 +340,9 @@ static void rtllib_query_HTCapShortGI(struct rtllib_device *ieee,
 	if (!ht_info->current_ht_support || !ht_info->enable_ht)
 		return;
 
-	if (ht_info->forced_short_gi) {
-		tcb_desc->bUseShortGI = true;
-		return;
-	}
-
-	if (ht_info->bCurBW40MHz && ht_info->bCurShortGI40MHz)
+	if (ht_info->cur_bw_40mhz && ht_info->cur_short_gi_40mhz)
 		tcb_desc->bUseShortGI = true;
-	else if (!ht_info->bCurBW40MHz && ht_info->bCurShortGI20MHz)
+	else if (!ht_info->cur_bw_40mhz && ht_info->cur_short_gi_20mhz)
 		tcb_desc->bUseShortGI = true;
 }
 
@@ -383,7 +361,7 @@ static void rtllib_query_BandwidthMode(struct rtllib_device *ieee,
 
 	if ((tcb_desc->data_rate & 0x80) == 0)
 		return;
-	if (ht_info->bCurBW40MHz && ht_info->cur_tx_bw40mhz &&
+	if (ht_info->cur_bw_40mhz && ht_info->cur_tx_bw40mhz &&
 	    !ieee->bandwidth_auto_switch.bforced_tx20Mhz)
 		tcb_desc->bPacketBW = true;
 }
@@ -441,9 +419,9 @@ static void rtllib_query_protectionmode(struct rtllib_device *ieee,
 		if (ht_info->current_ht_support && ht_info->enable_ht) {
 			u8 HTOpMode = ht_info->current_op_mode;
 
-			if ((ht_info->bCurBW40MHz && (HTOpMode == 2 ||
+			if ((ht_info->cur_bw_40mhz && (HTOpMode == 2 ||
 						      HTOpMode == 3)) ||
-			     (!ht_info->bCurBW40MHz && HTOpMode == 3)) {
+			     (!ht_info->cur_bw_40mhz && HTOpMode == 3)) {
 				tcb_desc->rts_rate = MGN_24M;
 				tcb_desc->bRTSEnable = true;
 				break;
@@ -454,7 +432,7 @@ static void rtllib_query_protectionmode(struct rtllib_device *ieee,
 			tcb_desc->bRTSEnable = true;
 			break;
 		}
-		if (tcb_desc->bAMPDUEnable) {
+		if (tcb_desc->ampdu_enable) {
 			tcb_desc->rts_rate = MGN_24M;
 			tcb_desc->bRTSEnable = false;
 			break;
@@ -500,8 +478,8 @@ static u16 rtllib_query_seqnum(struct rtllib_device *ieee, struct sk_buff *skb,
 		if (!rtllib_get_ts(ieee, (struct ts_common_info **)(&ts), dst,
 			   skb->priority, TX_DIR, true))
 			return 0;
-		seqnum = ts->TxCurSeq;
-		ts->TxCurSeq = (ts->TxCurSeq + 1) % 4096;
+		seqnum = ts->tx_cur_seq;
+		ts->tx_cur_seq = (ts->tx_cur_seq + 1) % 4096;
 		return seqnum;
 	}
 	return 0;
@@ -847,7 +825,7 @@ static int rtllib_xmit_inter(struct sk_buff *skb, struct net_device *dev)
 	if (txb) {
 		tcb_desc = (struct cb_desc *)
 				(txb->fragments[0]->cb + MAX_DEV_ADDR_SIZE);
-		tcb_desc->bTxEnableFwCalcDur = 1;
+		tcb_desc->tx_enable_fw_calc_dur = 1;
 		tcb_desc->priority = skb->priority;
 
 		if (ether_type == ETH_P_PAE) {
diff --git a/drivers/staging/rtl8192e/rtllib_wx.c b/drivers/staging/rtl8192e/rtllib_wx.c
index a37250de7ba3..f92ec0faf4d5 100644
--- a/drivers/staging/rtl8192e/rtllib_wx.c
+++ b/drivers/staging/rtl8192e/rtllib_wx.c
@@ -134,7 +134,7 @@ static inline char *rtl819x_translate_scan(struct rtllib_device *ieee,
 				((ht_cap->ShortGI40Mhz) ? 1 : 0) :
 				((ht_cap->ShortGI20Mhz) ? 1 : 0);
 
-		max_mcs = HTGetHighestMCSRate(ieee, ht_cap->MCS,
+		max_mcs = ht_get_highest_mcs_rate(ieee, ht_cap->MCS,
 					      MCS_FILTER_ALL);
 		rate = MCS_DATA_RATE[is40M][isShortGI][max_mcs & 0x7f];
 		if (rate > max_rate)
diff --git a/drivers/staging/rtl8712/os_intfs.c b/drivers/staging/rtl8712/os_intfs.c
index b18e6d9c832b..7554613fe7e1 100644
--- a/drivers/staging/rtl8712/os_intfs.c
+++ b/drivers/staging/rtl8712/os_intfs.c
@@ -221,8 +221,7 @@ struct net_device *r8712_init_netdev(void)
 
 static u32 start_drv_threads(struct _adapter *padapter)
 {
-	padapter->cmd_thread = kthread_run(r8712_cmd_thread, padapter, "%s",
-					  padapter->pnetdev->name);
+	padapter->cmd_thread = kthread_run(r8712_cmd_thread, padapter, "%s", padapter->pnetdev->name);
 	if (IS_ERR(padapter->cmd_thread))
 		return _FAIL;
 	return _SUCCESS;
diff --git a/drivers/staging/rtl8712/rtl8712_efuse.c b/drivers/staging/rtl8712/rtl8712_efuse.c
index c9400e40a1d6..a39d6c06648f 100644
--- a/drivers/staging/rtl8712/rtl8712_efuse.c
+++ b/drivers/staging/rtl8712/rtl8712_efuse.c
@@ -213,8 +213,8 @@ u16 r8712_efuse_get_current_size(struct _adapter *adapter)
 	u8 hworden = 0;
 	u8 efuse_data, word_cnts = 0;
 
-	while (bContinual && efuse_one_byte_read(adapter, efuse_addr,
-	       &efuse_data) && (efuse_addr < efuse_available_max_size)) {
+	while (bContinual && efuse_one_byte_read(adapter, efuse_addr, &efuse_data) &&
+	       (efuse_addr < efuse_available_max_size)) {
 		if (efuse_data != 0xFF) {
 			hworden =  efuse_data & 0x0F;
 			word_cnts = calculate_word_cnts(hworden);
@@ -252,9 +252,8 @@ u8 r8712_efuse_pg_packet_read(struct _adapter *adapter, u8 offset, u8 *data)
 				memset(tmpdata, 0xFF, PGPKT_DATA_SIZE);
 				for (tmpidx = 0; tmpidx < word_cnts * 2;
 				     tmpidx++) {
-					if (efuse_one_byte_read(adapter,
-					    efuse_addr + 1 + tmpidx,
-					    &efuse_data)) {
+					if (efuse_one_byte_read(adapter, efuse_addr + 1 + tmpidx,
+								&efuse_data)) {
 						tmpdata[tmpidx] = efuse_data;
 					} else {
 						ret = false;
diff --git a/drivers/staging/rtl8712/rtl8712_recv.c b/drivers/staging/rtl8712/rtl8712_recv.c
index 7da014ab0723..a3c4713c59b3 100644
--- a/drivers/staging/rtl8712/rtl8712_recv.c
+++ b/drivers/staging/rtl8712/rtl8712_recv.c
@@ -267,8 +267,7 @@ union recv_frame *r8712_recvframe_chk_defrag(struct _adapter *padapter,
 				/*the first fragment*/
 				if (!list_empty(&pdefrag_q->queue)) {
 					/*free current defrag_q */
-					r8712_free_recvframe_queue(pdefrag_q,
-							     pfree_recv_queue);
+					r8712_free_recvframe_queue(pdefrag_q, pfree_recv_queue);
 				}
 			}
 			/* Then enqueue the 0~(n-1) fragment to the defrag_q */
diff --git a/drivers/staging/rtl8712/rtl8712_xmit.c b/drivers/staging/rtl8712/rtl8712_xmit.c
index 4cb01f590673..d7d678b04ca8 100644
--- a/drivers/staging/rtl8712/rtl8712_xmit.c
+++ b/drivers/staging/rtl8712/rtl8712_xmit.c
@@ -147,9 +147,8 @@ static u32 get_ff_hwaddr(struct xmit_frame *pxmitframe)
 }
 
 static struct xmit_frame *dequeue_one_xmitframe(struct xmit_priv *pxmitpriv,
-					 struct hw_xmit *phwxmit,
-					 struct tx_servq *ptxservq,
-					 struct  __queue *pframe_queue)
+						struct hw_xmit *phwxmit, struct tx_servq *ptxservq,
+						struct  __queue *pframe_queue)
 {
 	struct list_head *xmitframe_plist, *xmitframe_phead;
 	struct	xmit_frame *pxmitframe = NULL;
@@ -167,7 +166,7 @@ static struct xmit_frame *dequeue_one_xmitframe(struct xmit_priv *pxmitpriv,
 }
 
 static struct xmit_frame *dequeue_xframe_ex(struct xmit_priv *pxmitpriv,
-				     struct hw_xmit *phwxmit_i, sint entry)
+					    struct hw_xmit *phwxmit_i, sint entry)
 {
 	unsigned long irqL0;
 	struct list_head *sta_plist, *sta_phead;
@@ -197,11 +196,10 @@ static struct xmit_frame *dequeue_xframe_ex(struct xmit_priv *pxmitpriv,
 		sta_phead = &phwxmit->sta_queue->queue;
 		sta_plist = sta_phead->next;
 		while (!end_of_queue_search(sta_phead, sta_plist)) {
-			ptxservq = container_of(sta_plist, struct tx_servq,
-						tx_pending);
+			ptxservq = container_of(sta_plist, struct tx_servq, tx_pending);
 			pframe_queue = &ptxservq->sta_pending;
-			pxmitframe = dequeue_one_xmitframe(pxmitpriv, phwxmit,
-				     ptxservq, pframe_queue);
+			pxmitframe = dequeue_one_xmitframe(pxmitpriv, phwxmit, ptxservq,
+							   pframe_queue);
 			if (pxmitframe) {
 				phwxmit->accnt--;
 				goto exit_dequeue_xframe_ex;
@@ -221,8 +219,7 @@ exit_dequeue_xframe_ex:
 	return pxmitframe;
 }
 
-void r8712_do_queue_select(struct _adapter *padapter,
-			   struct pkt_attrib *pattrib)
+void r8712_do_queue_select(struct _adapter *padapter, struct pkt_attrib *pattrib)
 {
 	unsigned int qsel = 0;
 	struct dvobj_priv *pdvobj = &padapter->dvobjpriv;
@@ -292,14 +289,12 @@ void r8712_append_mpdu_unit(struct xmit_buf *pxmitbuf,
 	r8712_xmit_complete(padapter, pxmitframe);
 	if (pxmitframe->attrib.ether_type != 0x0806) {
 		if ((pxmitframe->attrib.ether_type != 0x888e) &&
-			(pxmitframe->attrib.dhcp_pkt != 1)) {
-			r8712_issue_addbareq_cmd(padapter,
-					pxmitframe->attrib.priority);
+		    (pxmitframe->attrib.dhcp_pkt != 1)) {
+			r8712_issue_addbareq_cmd(padapter, pxmitframe->attrib.priority);
 		}
 	}
 	pxmitframe->last[0] = 1;
-	update_txdesc(pxmitframe, (uint *)(pxmitframe->buf_addr),
-		pxmitframe->attrib.last_txcmdsz);
+	update_txdesc(pxmitframe, (uint *)(pxmitframe->buf_addr), pxmitframe->attrib.last_txcmdsz);
 	/*padding zero */
 	last_txcmdsz = pxmitframe->attrib.last_txcmdsz;
 	padding_sz = (8 - (last_txcmdsz % 8));
@@ -333,8 +328,7 @@ void r8712_xmitframe_aggr_1st(struct xmit_buf *pxmitbuf,
 	pxmitbuf->aggr_nr = 1;
 }
 
-u16 r8712_xmitframe_aggr_next(struct xmit_buf *pxmitbuf,
-			struct xmit_frame *pxmitframe)
+u16 r8712_xmitframe_aggr_next(struct xmit_buf *pxmitbuf, struct xmit_frame *pxmitframe)
 {
 	pxmitframe->pxmitbuf = pxmitbuf;
 	pxmitbuf->priv_data = pxmitframe;
@@ -374,9 +368,9 @@ void r8712_dump_aggr_xframe(struct xmit_buf *pxmitbuf,
 	pxmitframe->bpending[0] = false;
 	pxmitframe->mem_addr = pxmitbuf->pbuf;
 
-	if ((pdvobj->ishighspeed && ((total_length + TXDESC_SIZE) % 0x200) ==
-	     0) || ((!pdvobj->ishighspeed && ((total_length + TXDESC_SIZE) %
-					      0x40) == 0))) {
+	if ((pdvobj->ishighspeed && ((total_length + TXDESC_SIZE) % 0x200) == 0) ||
+	    ((!pdvobj->ishighspeed && ((total_length + TXDESC_SIZE) %
+	    0x40) == 0))) {
 		ptxdesc->txdw0 |= cpu_to_le32
 			(((TXDESC_SIZE + OFFSET_SZ + 8) << OFFSET_SHT) &
 			 0x00ff0000);
@@ -387,8 +381,8 @@ void r8712_dump_aggr_xframe(struct xmit_buf *pxmitbuf,
 			 0x00ff0000);
 		/*default = 32 bytes for TX Desc*/
 	}
-	r8712_write_port(pxmitframe->padapter, RTL8712_DMA_H2CCMD,
-			total_length + TXDESC_SIZE, (u8 *)pxmitframe);
+	r8712_write_port(pxmitframe->padapter, RTL8712_DMA_H2CCMD, total_length + TXDESC_SIZE,
+			 (u8 *)pxmitframe);
 }
 
 #endif
@@ -618,14 +612,12 @@ int r8712_xmitframe_complete(struct _adapter *padapter,
 	pxmitframe = dequeue_xframe_ex(pxmitpriv, phwxmits, hwentry);
 	/* need to remember the 1st frame */
 	if (pxmitframe) {
-
 #ifdef CONFIG_R8712_TX_AGGR
 		/* 1. dequeue 2nd frame
 		 * 2. aggr if 2nd xframe is dequeued, else dump directly
 		 */
 		if (AGGR_NR_HIGH_BOUND > 1)
-			p2ndxmitframe = dequeue_xframe_ex(pxmitpriv, phwxmits,
-							hwentry);
+			p2ndxmitframe = dequeue_xframe_ex(pxmitpriv, phwxmits, hwentry);
 		if (pxmitframe->frame_tag != DATA_FRAMETAG) {
 			r8712_free_xmitbuf(pxmitpriv, pxmitbuf);
 			return false;
@@ -639,16 +631,12 @@ int r8712_xmitframe_complete(struct _adapter *padapter,
 		if (p2ndxmitframe) {
 			u16 total_length;
 
-			total_length = r8712_xmitframe_aggr_next(
-				pxmitbuf, p2ndxmitframe);
+			total_length = r8712_xmitframe_aggr_next(pxmitbuf, p2ndxmitframe);
 			do {
-				p2ndxmitframe = dequeue_xframe_ex(
-					pxmitpriv, phwxmits, hwentry);
+				p2ndxmitframe = dequeue_xframe_ex(pxmitpriv, phwxmits, hwentry);
 				if (p2ndxmitframe)
 					total_length =
-						r8712_xmitframe_aggr_next(
-							pxmitbuf,
-							p2ndxmitframe);
+						r8712_xmitframe_aggr_next(pxmitbuf, p2ndxmitframe);
 				else
 					break;
 			} while (total_length <= 0x1800 &&
@@ -662,8 +650,8 @@ int r8712_xmitframe_complete(struct _adapter *padapter,
 		xmitframe_xmitbuf_attach(pxmitframe, pxmitbuf);
 		if (pxmitframe->frame_tag == DATA_FRAMETAG) {
 			if (pxmitframe->attrib.priority <= 15)
-				res = r8712_xmitframe_coalesce(padapter,
-					pxmitframe->pkt, pxmitframe);
+				res = r8712_xmitframe_coalesce(padapter, pxmitframe->pkt,
+							       pxmitframe);
 			/* always return ndis_packet after
 			 * r8712_xmitframe_coalesce
 			 */
@@ -714,10 +702,10 @@ static void dump_xframe(struct _adapter *padapter,
 		ff_hwaddr = get_ff_hwaddr(pxmitframe);
 #ifdef CONFIG_R8712_TX_AGGR
 		r8712_write_port(padapter, RTL8712_DMA_H2CCMD, w_sz,
-				(unsigned char *)pxmitframe);
+				 (unsigned char *)pxmitframe);
 #else
 		r8712_write_port(padapter, ff_hwaddr, w_sz,
-			   (unsigned char *)pxmitframe);
+				 (unsigned char *)pxmitframe);
 #endif
 		mem_addr += w_sz;
 		mem_addr = (u8 *)RND4(((addr_t)(mem_addr)));
diff --git a/drivers/staging/rtl8712/rtl871x_cmd.c b/drivers/staging/rtl8712/rtl871x_cmd.c
index 4be96df5a329..bbd4a13c7bb9 100644
--- a/drivers/staging/rtl8712/rtl871x_cmd.c
+++ b/drivers/staging/rtl8712/rtl871x_cmd.c
@@ -242,8 +242,7 @@ void r8712_set_chplan_cmd(struct _adapter *padapter, int chplan)
 		kfree(ph2c);
 		return;
 	}
-	init_h2fwcmd_w_parm_no_rsp(ph2c, psetchplanpara,
-				GEN_CMD_CODE(_SetChannelPlan));
+	init_h2fwcmd_w_parm_no_rsp(ph2c, psetchplanpara, GEN_CMD_CODE(_SetChannelPlan));
 	psetchplanpara->ChannelPlan = chplan;
 	r8712_enqueue_cmd(pcmdpriv, ph2c);
 }
@@ -302,8 +301,7 @@ void r8712_getbbrfreg_cmdrsp_callback(struct _adapter *padapter,
 	padapter->mppriv.workparam.bcompleted = true;
 }
 
-void r8712_readtssi_cmdrsp_callback(struct _adapter *padapter,
-				struct cmd_obj *pcmd)
+void r8712_readtssi_cmdrsp_callback(struct _adapter *padapter, struct cmd_obj *pcmd)
 {
 	kfree(pcmd->parmbuf);
 	kfree(pcmd);
@@ -374,11 +372,10 @@ int r8712_joinbss_cmd(struct _adapter  *padapter, struct wlan_network *pnetwork)
 	psecuritypriv->authenticator_ie[0] = (unsigned char)
 					     psecnetwork->IELength;
 	if ((psecnetwork->IELength - 12) < (256 - 1))
-		memcpy(&psecuritypriv->authenticator_ie[1],
-			&psecnetwork->IEs[12], psecnetwork->IELength - 12);
+		memcpy(&psecuritypriv->authenticator_ie[1], &psecnetwork->IEs[12],
+		       psecnetwork->IELength - 12);
 	else
-		memcpy(&psecuritypriv->authenticator_ie[1],
-			&psecnetwork->IEs[12], (256 - 1));
+		memcpy(&psecuritypriv->authenticator_ie[1], &psecnetwork->IEs[12], (256 - 1));
 	psecnetwork->IELength = 0;
 	/*
 	 * If the driver wants to use the bssid to create the connection.
@@ -388,19 +385,15 @@ int r8712_joinbss_cmd(struct _adapter  *padapter, struct wlan_network *pnetwork)
 	if (!pmlmepriv->assoc_by_bssid)
 		ether_addr_copy(&pmlmepriv->assoc_bssid[0],
 				&pnetwork->network.MacAddress[0]);
-	psecnetwork->IELength = r8712_restruct_sec_ie(padapter,
-						&pnetwork->network.IEs[0],
-						&psecnetwork->IEs[0],
-						pnetwork->network.IELength);
+	psecnetwork->IELength = r8712_restruct_sec_ie(padapter, &pnetwork->network.IEs[0],
+						      &psecnetwork->IEs[0], pnetwork->network.IELength);
 	pqospriv->qos_option = 0;
 	if (pregistrypriv->wmm_enable) {
 		u32 tmp_len;
 
-		tmp_len = r8712_restruct_wmm_ie(padapter,
-					  &pnetwork->network.IEs[0],
-					  &psecnetwork->IEs[0],
-					  pnetwork->network.IELength,
-					  psecnetwork->IELength);
+		tmp_len = r8712_restruct_wmm_ie(padapter, &pnetwork->network.IEs[0],
+						&psecnetwork->IEs[0], pnetwork->network.IELength,
+						psecnetwork->IELength);
 		if (psecnetwork->IELength != tmp_len) {
 			psecnetwork->IELength = tmp_len;
 			pqospriv->qos_option = 1; /* WMM IE in beacon */
@@ -427,39 +420,28 @@ int r8712_joinbss_cmd(struct _adapter  *padapter, struct wlan_network *pnetwork)
 	psecuritypriv->supplicant_ie[0] = (u8)psecnetwork->IELength;
 	if (psecnetwork->IELength < 255)
 		memcpy(&psecuritypriv->supplicant_ie[1], &psecnetwork->IEs[0],
-			psecnetwork->IELength);
+		       psecnetwork->IELength);
 	else
 		memcpy(&psecuritypriv->supplicant_ie[1], &psecnetwork->IEs[0],
-			255);
+		       255);
 	/* get cmdsz before endian conversion */
 	pcmd->cmdsz = r8712_get_wlan_bssid_ex_sz(psecnetwork);
 #ifdef __BIG_ENDIAN
 	/* wlan_network endian conversion */
 	psecnetwork->Length = cpu_to_le32(psecnetwork->Length);
-	psecnetwork->Ssid.SsidLength = cpu_to_le32(
-				       psecnetwork->Ssid.SsidLength);
+	psecnetwork->Ssid.SsidLength = cpu_to_le32(psecnetwork->Ssid.SsidLength);
 	psecnetwork->Privacy = cpu_to_le32(psecnetwork->Privacy);
 	psecnetwork->Rssi = cpu_to_le32(psecnetwork->Rssi);
-	psecnetwork->NetworkTypeInUse = cpu_to_le32(
-					psecnetwork->NetworkTypeInUse);
-	psecnetwork->Configuration.ATIMWindow = cpu_to_le32(
-				psecnetwork->Configuration.ATIMWindow);
-	psecnetwork->Configuration.BeaconPeriod = cpu_to_le32(
-				 psecnetwork->Configuration.BeaconPeriod);
-	psecnetwork->Configuration.DSConfig = cpu_to_le32(
-				psecnetwork->Configuration.DSConfig);
-	psecnetwork->Configuration.FHConfig.DwellTime = cpu_to_le32(
-				psecnetwork->Configuration.FHConfig.DwellTime);
-	psecnetwork->Configuration.FHConfig.HopPattern = cpu_to_le32(
-				psecnetwork->Configuration.FHConfig.HopPattern);
-	psecnetwork->Configuration.FHConfig.HopSet = cpu_to_le32(
-				psecnetwork->Configuration.FHConfig.HopSet);
-	psecnetwork->Configuration.FHConfig.Length = cpu_to_le32(
-				psecnetwork->Configuration.FHConfig.Length);
-	psecnetwork->Configuration.Length = cpu_to_le32(
-				psecnetwork->Configuration.Length);
-	psecnetwork->InfrastructureMode = cpu_to_le32(
-				psecnetwork->InfrastructureMode);
+	psecnetwork->NetworkTypeInUse = cpu_to_le32(psecnetwork->NetworkTypeInUse);
+	psecnetwork->Configuration.ATIMWindow = cpu_to_le32(psecnetwork->Configuration.ATIMWindow);
+	psecnetwork->Configuration.BeaconPeriod = cpu_to_le32(psecnetwork->Configuration.BeaconPeriod);
+	psecnetwork->Configuration.DSConfig = cpu_to_le32(psecnetwork->Configuration.DSConfig);
+	psecnetwork->Configuration.FHConfig.DwellTime = cpu_to_le32(psecnetwork->Configuration.FHConfig.DwellTime);
+	psecnetwork->Configuration.FHConfig.HopPattern = cpu_to_le32(psecnetwork->Configuration.FHConfig.HopPattern);
+	psecnetwork->Configuration.FHConfig.HopSet = cpu_to_le32(psecnetwork->Configuration.FHConfig.HopSet);
+	psecnetwork->Configuration.FHConfig.Length = cpu_to_le32(psecnetwork->Configuration.FHConfig.Length);
+	psecnetwork->Configuration.Length = cpu_to_le32(psecnetwork->Configuration.Length);
+	psecnetwork->InfrastructureMode = cpu_to_le32(psecnetwork->InfrastructureMode);
 	psecnetwork->IELength = cpu_to_le32(psecnetwork->IELength);
 #endif
 	INIT_LIST_HEAD(&pcmd->list);
@@ -485,13 +467,12 @@ void r8712_disassoc_cmd(struct _adapter *padapter) /* for sta_mode */
 		kfree(pdisconnect_cmd);
 		return;
 	}
-	init_h2fwcmd_w_parm_no_rsp(pdisconnect_cmd, pdisconnect,
-				   _DisConnect_CMD_);
+	init_h2fwcmd_w_parm_no_rsp(pdisconnect_cmd, pdisconnect, _DisConnect_CMD_);
 	r8712_enqueue_cmd(pcmdpriv, pdisconnect_cmd);
 }
 
 void r8712_setopmode_cmd(struct _adapter *padapter,
-		 enum NDIS_802_11_NETWORK_INFRASTRUCTURE networktype)
+			 enum NDIS_802_11_NETWORK_INFRASTRUCTURE networktype)
 {
 	struct cmd_obj *ph2c;
 	struct setopmode_parm *psetop;
@@ -543,14 +524,12 @@ void r8712_setstakey_cmd(struct _adapter *padapter, u8 *psta, u8 unicast_key)
 		psetstakey_para->algorithm = (unsigned char)
 					    psecuritypriv->PrivacyAlgrthm;
 	else
-		GET_ENCRY_ALGO(psecuritypriv, sta,
-			       psetstakey_para->algorithm, false);
+		GET_ENCRY_ALGO(psecuritypriv, sta, psetstakey_para->algorithm, false);
 	if (unicast_key)
 		memcpy(&psetstakey_para->key, &sta->x_UncstKey, 16);
 	else
-		memcpy(&psetstakey_para->key,
-			&psecuritypriv->XGrpKey[
-			psecuritypriv->XGrpKeyid - 1]. skey, 16);
+		memcpy(&psetstakey_para->key, &psecuritypriv->XGrpKey[psecuritypriv->XGrpKeyid - 1].
+		       skey, 16);
 	r8712_enqueue_cmd(pcmdpriv, ph2c);
 }
 
@@ -568,8 +547,7 @@ void r8712_setMacAddr_cmd(struct _adapter *padapter, const u8 *mac_addr)
 		kfree(ph2c);
 		return;
 	}
-	init_h2fwcmd_w_parm_no_rsp(ph2c, psetMacAddr_para,
-				   _SetMacAddress_CMD_);
+	init_h2fwcmd_w_parm_no_rsp(ph2c, psetMacAddr_para, _SetMacAddress_CMD_);
 	ether_addr_copy(psetMacAddr_para->MacAddr, mac_addr);
 	r8712_enqueue_cmd(pcmdpriv, ph2c);
 }
@@ -589,8 +567,7 @@ void r8712_addbareq_cmd(struct _adapter *padapter, u8 tid)
 		return;
 	}
 	paddbareq_parm->tid = tid;
-	init_h2fwcmd_w_parm_no_rsp(ph2c, paddbareq_parm,
-				   GEN_CMD_CODE(_AddBAReq));
+	init_h2fwcmd_w_parm_no_rsp(ph2c, paddbareq_parm, GEN_CMD_CODE(_AddBAReq));
 	r8712_enqueue_cmd_ex(pcmdpriv, ph2c);
 }
 
@@ -644,13 +621,11 @@ void r8712_joinbss_cmd_callback(struct _adapter *padapter, struct cmd_obj *pcmd)
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
 
 	if (pcmd->res != H2C_SUCCESS)
-		mod_timer(&pmlmepriv->assoc_timer,
-			  jiffies + msecs_to_jiffies(1));
+		mod_timer(&pmlmepriv->assoc_timer, jiffies + msecs_to_jiffies(1));
 	r8712_free_cmd_obj(pcmd);
 }
 
-void r8712_createbss_cmd_callback(struct _adapter *padapter,
-				  struct cmd_obj *pcmd)
+void r8712_createbss_cmd_callback(struct _adapter *padapter, struct cmd_obj *pcmd)
 {
 	unsigned long irqL;
 	struct sta_info *psta = NULL;
@@ -660,8 +635,7 @@ void r8712_createbss_cmd_callback(struct _adapter *padapter,
 	struct wlan_network *tgt_network = &(pmlmepriv->cur_network);
 
 	if (pcmd->res != H2C_SUCCESS)
-		mod_timer(&pmlmepriv->assoc_timer,
-			  jiffies + msecs_to_jiffies(1));
+		mod_timer(&pmlmepriv->assoc_timer, jiffies + msecs_to_jiffies(1));
 	del_timer(&pmlmepriv->assoc_timer);
 #ifdef __BIG_ENDIAN
 	/* endian_convert */
@@ -670,31 +644,21 @@ void r8712_createbss_cmd_callback(struct _adapter *padapter,
 	pnetwork->Privacy = le32_to_cpu(pnetwork->Privacy);
 	pnetwork->Rssi = le32_to_cpu(pnetwork->Rssi);
 	pnetwork->NetworkTypeInUse = le32_to_cpu(pnetwork->NetworkTypeInUse);
-	pnetwork->Configuration.ATIMWindow =
-		le32_to_cpu(pnetwork->Configuration.ATIMWindow);
-	pnetwork->Configuration.DSConfig =
-		le32_to_cpu(pnetwork->Configuration.DSConfig);
-	pnetwork->Configuration.FHConfig.DwellTime =
-		le32_to_cpu(pnetwork->Configuration.FHConfig.DwellTime);
-	pnetwork->Configuration.FHConfig.HopPattern =
-		le32_to_cpu(pnetwork->Configuration.FHConfig.HopPattern);
-	pnetwork->Configuration.FHConfig.HopSet =
-		le32_to_cpu(pnetwork->Configuration.FHConfig.HopSet);
-	pnetwork->Configuration.FHConfig.Length =
-		le32_to_cpu(pnetwork->Configuration.FHConfig.Length);
-	pnetwork->Configuration.Length =
-		le32_to_cpu(pnetwork->Configuration.Length);
-	pnetwork->InfrastructureMode =
-		le32_to_cpu(pnetwork->InfrastructureMode);
+	pnetwork->Configuration.ATIMWindow = le32_to_cpu(pnetwork->Configuration.ATIMWindow);
+	pnetwork->Configuration.DSConfig = le32_to_cpu(pnetwork->Configuration.DSConfig);
+	pnetwork->Configuration.FHConfig.DwellTime = le32_to_cpu(pnetwork->Configuration.FHConfig.DwellTime);
+	pnetwork->Configuration.FHConfig.HopPattern = le32_to_cpu(pnetwork->Configuration.FHConfig.HopPattern);
+	pnetwork->Configuration.FHConfig.HopSet = le32_to_cpu(pnetwork->Configuration.FHConfig.HopSet);
+	pnetwork->Configuration.FHConfig.Length = le32_to_cpu(pnetwork->Configuration.FHConfig.Length);
+	pnetwork->Configuration.Length = le32_to_cpu(pnetwork->Configuration.Length);
+	pnetwork->InfrastructureMode = le32_to_cpu(pnetwork->InfrastructureMode);
 	pnetwork->IELength = le32_to_cpu(pnetwork->IELength);
 #endif
 	spin_lock_irqsave(&pmlmepriv->lock, irqL);
 	if ((pmlmepriv->fw_state) & WIFI_AP_STATE) {
-		psta = r8712_get_stainfo(&padapter->stapriv,
-					 pnetwork->MacAddress);
+		psta = r8712_get_stainfo(&padapter->stapriv, pnetwork->MacAddress);
 		if (!psta) {
-			psta = r8712_alloc_stainfo(&padapter->stapriv,
-						   pnetwork->MacAddress);
+			psta = r8712_alloc_stainfo(&padapter->stapriv, pnetwork->MacAddress);
 			if (!psta)
 				goto createbss_cmd_fail;
 		}
@@ -702,20 +666,17 @@ void r8712_createbss_cmd_callback(struct _adapter *padapter,
 	} else {
 		pwlan = _r8712_alloc_network(pmlmepriv);
 		if (!pwlan) {
-			pwlan = r8712_get_oldest_wlan_network(
-				&pmlmepriv->scanned_queue);
+			pwlan = r8712_get_oldest_wlan_network(&pmlmepriv->scanned_queue);
 			if (!pwlan)
 				goto createbss_cmd_fail;
 			pwlan->last_scanned = jiffies;
 		} else {
-			list_add_tail(&(pwlan->list),
-					 &pmlmepriv->scanned_queue.queue);
+			list_add_tail(&(pwlan->list), &pmlmepriv->scanned_queue.queue);
 		}
 		pnetwork->Length = r8712_get_wlan_bssid_ex_sz(pnetwork);
 		memcpy(&(pwlan->network), pnetwork, pnetwork->Length);
 		pwlan->fixed = true;
-		memcpy(&tgt_network->network, pnetwork,
-			(r8712_get_wlan_bssid_ex_sz(pnetwork)));
+		memcpy(&tgt_network->network, pnetwork, (r8712_get_wlan_bssid_ex_sz(pnetwork)));
 		if (pmlmepriv->fw_state & _FW_UNDER_LINKING)
 			pmlmepriv->fw_state ^= _FW_UNDER_LINKING;
 		/*
@@ -728,14 +689,11 @@ createbss_cmd_fail:
 	r8712_free_cmd_obj(pcmd);
 }
 
-void r8712_setstaKey_cmdrsp_callback(struct _adapter *padapter,
-				     struct cmd_obj *pcmd)
+void r8712_setstaKey_cmdrsp_callback(struct _adapter *padapter, struct cmd_obj *pcmd)
 {
 	struct sta_priv *pstapriv = &padapter->stapriv;
-	struct set_stakey_rsp *psetstakey_rsp = (struct set_stakey_rsp *)
-						(pcmd->rsp);
-	struct sta_info *psta = r8712_get_stainfo(pstapriv,
-						  psetstakey_rsp->addr);
+	struct set_stakey_rsp *psetstakey_rsp = (struct set_stakey_rsp *) (pcmd->rsp);
+	struct sta_info *psta = r8712_get_stainfo(pstapriv, psetstakey_rsp->addr);
 
 	if (!psta)
 		goto exit;
@@ -750,27 +708,23 @@ void r8712_setassocsta_cmdrsp_callback(struct _adapter *padapter,
 	unsigned long	irqL;
 	struct sta_priv *pstapriv = &padapter->stapriv;
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
-	struct set_assocsta_parm *passocsta_parm =
-				(struct set_assocsta_parm *)(pcmd->parmbuf);
-	struct set_assocsta_rsp *passocsta_rsp =
-				(struct set_assocsta_rsp *) (pcmd->rsp);
-	struct sta_info *psta = r8712_get_stainfo(pstapriv,
-						  passocsta_parm->addr);
+	struct set_assocsta_parm *passocsta_parm = (struct set_assocsta_parm *)(pcmd->parmbuf);
+	struct set_assocsta_rsp *passocsta_rsp = (struct set_assocsta_rsp *) (pcmd->rsp);
+	struct sta_info *psta = r8712_get_stainfo(pstapriv, passocsta_parm->addr);
 
 	if (!psta)
 		return;
 	psta->aid = psta->mac_id = passocsta_rsp->cam_id;
 	spin_lock_irqsave(&pmlmepriv->lock, irqL);
-	if ((check_fwstate(pmlmepriv, WIFI_MP_STATE)) &&
-	    (check_fwstate(pmlmepriv, _FW_UNDER_LINKING)))
+	if ((check_fwstate(pmlmepriv, WIFI_MP_STATE)) && (check_fwstate(pmlmepriv, _FW_UNDER_LINKING)))
 		pmlmepriv->fw_state ^= _FW_UNDER_LINKING;
 	set_fwstate(pmlmepriv, _FW_LINKED);
 	spin_unlock_irqrestore(&pmlmepriv->lock, irqL);
 	r8712_free_cmd_obj(pcmd);
 }
 
-void r8712_disconnectCtrlEx_cmd(struct _adapter *adapter, u32 enableDrvCtrl,
-			u32 tryPktCnt, u32 tryPktInterval, u32 firstStageTO)
+void r8712_disconnectCtrlEx_cmd(struct _adapter *adapter, u32 enableDrvCtrl, u32 tryPktCnt,
+				u32 tryPktInterval, u32 firstStageTO)
 {
 	struct cmd_obj *ph2c;
 	struct DisconnectCtrlEx_param *param;
@@ -790,7 +744,6 @@ void r8712_disconnectCtrlEx_cmd(struct _adapter *adapter, u32 enableDrvCtrl,
 	param->TryPktInterval = (unsigned char)tryPktInterval;
 	param->FirstStageTO = (unsigned int)firstStageTO;
 
-	init_h2fwcmd_w_parm_no_rsp(ph2c, param,
-				GEN_CMD_CODE(_DisconnectCtrlEx));
+	init_h2fwcmd_w_parm_no_rsp(ph2c, param, GEN_CMD_CODE(_DisconnectCtrlEx));
 	r8712_enqueue_cmd(pcmdpriv, ph2c);
 }
diff --git a/drivers/staging/rtl8712/rtl871x_cmd.h b/drivers/staging/rtl8712/rtl871x_cmd.h
index 8453d8de8248..2613b3c2acfc 100644
--- a/drivers/staging/rtl8712/rtl871x_cmd.h
+++ b/drivers/staging/rtl8712/rtl871x_cmd.h
@@ -716,39 +716,28 @@ struct DisconnectCtrlEx_param {
 #define H2C_RESERVED			0x07
 
 void r8712_setMacAddr_cmd(struct _adapter *padapter, const u8 *mac_addr);
-u8 r8712_sitesurvey_cmd(struct _adapter *padapter,
-			struct ndis_802_11_ssid *pssid);
+u8 r8712_sitesurvey_cmd(struct _adapter *padapter, struct ndis_802_11_ssid *pssid);
 int r8712_createbss_cmd(struct _adapter *padapter);
 void r8712_setstakey_cmd(struct _adapter *padapter, u8 *psta, u8 unicast_key);
-int r8712_joinbss_cmd(struct _adapter *padapter,
-		      struct wlan_network *pnetwork);
+int r8712_joinbss_cmd(struct _adapter *padapter, struct wlan_network *pnetwork);
 void r8712_disassoc_cmd(struct _adapter *padapter);
-void r8712_setopmode_cmd(struct _adapter *padapter,
-		 enum NDIS_802_11_NETWORK_INFRASTRUCTURE networktype);
+void r8712_setopmode_cmd(struct _adapter *padapter, enum NDIS_802_11_NETWORK_INFRASTRUCTURE networktype);
 int r8712_setdatarate_cmd(struct _adapter *padapter, u8 *rateset);
 void r8712_set_chplan_cmd(struct _adapter  *padapter, int chplan);
 int r8712_getrfreg_cmd(struct _adapter *padapter, u8 offset, u8 *pval);
 int r8712_setrfreg_cmd(struct _adapter  *padapter, u8 offset, u32 val);
 void r8712_addbareq_cmd(struct _adapter *padapter, u8 tid);
 void r8712_wdg_wk_cmd(struct _adapter *padapter);
-void r8712_survey_cmd_callback(struct _adapter  *padapter,
-			       struct cmd_obj *pcmd);
-void r8712_disassoc_cmd_callback(struct _adapter  *padapter,
-				 struct cmd_obj *pcmd);
-void r8712_joinbss_cmd_callback(struct _adapter  *padapter,
-				struct cmd_obj *pcmd);
-void r8712_createbss_cmd_callback(struct _adapter *padapter,
-				  struct cmd_obj *pcmd);
-void r8712_getbbrfreg_cmdrsp_callback(struct _adapter *padapter,
-				      struct cmd_obj *pcmd);
-void r8712_readtssi_cmdrsp_callback(struct _adapter *padapter,
-				struct cmd_obj *pcmd);
-void r8712_setstaKey_cmdrsp_callback(struct _adapter  *padapter,
-				     struct cmd_obj *pcmd);
-void r8712_setassocsta_cmdrsp_callback(struct _adapter  *padapter,
-				       struct cmd_obj *pcmd);
-void r8712_disconnectCtrlEx_cmd(struct _adapter *adapter, u32 enableDrvCtrl,
-			u32 tryPktCnt, u32 tryPktInterval, u32 firstStageTO);
+void r8712_survey_cmd_callback(struct _adapter  *padapter, struct cmd_obj *pcmd);
+void r8712_disassoc_cmd_callback(struct _adapter  *padapter, struct cmd_obj *pcmd);
+void r8712_joinbss_cmd_callback(struct _adapter  *padapter, struct cmd_obj *pcmd);
+void r8712_createbss_cmd_callback(struct _adapter *padapter, struct cmd_obj *pcmd);
+void r8712_getbbrfreg_cmdrsp_callback(struct _adapter *padapter, struct cmd_obj *pcmd);
+void r8712_readtssi_cmdrsp_callback(struct _adapter *padapter, struct cmd_obj *pcmd);
+void r8712_setstaKey_cmdrsp_callback(struct _adapter  *padapter, struct cmd_obj *pcmd);
+void r8712_setassocsta_cmdrsp_callback(struct _adapter  *padapter, struct cmd_obj *pcmd);
+void r8712_disconnectCtrlEx_cmd(struct _adapter *adapter, u32 enableDrvCtrl, u32 tryPktCnt, 
+				u32 tryPktInterval, u32 firstStageTO);
 
 struct _cmd_callback {
 	u32	cmd_code;
diff --git a/drivers/staging/rtl8712/rtl871x_ioctl_linux.c b/drivers/staging/rtl8712/rtl871x_ioctl_linux.c
index 36f6904d25ab..0653aa27b1fa 100644
--- a/drivers/staging/rtl8712/rtl871x_ioctl_linux.c
+++ b/drivers/staging/rtl8712/rtl871x_ioctl_linux.c
@@ -59,8 +59,7 @@ void r8712_indicate_wx_assoc_event(struct _adapter *padapter)
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
 
 	wrqu.ap_addr.sa_family = ARPHRD_ETHER;
-	memcpy(wrqu.ap_addr.sa_data, pmlmepriv->cur_network.network.MacAddress,
-		ETH_ALEN);
+	memcpy(wrqu.ap_addr.sa_data, pmlmepriv->cur_network.network.MacAddress, ETH_ALEN);
 	wireless_send_event(padapter->pnetdev, SIOCGIWAP, &wrqu, NULL);
 }
 
@@ -111,11 +110,9 @@ static inline void handle_group_key(struct ieee_param *param,
 		memcpy(grk[param->u.crypt.idx - 1].skey,
 		       &param->u.crypt.key[24], 8);
 		padapter->securitypriv.binstallGrpkey = true;
-		r8712_set_key(padapter, &padapter->securitypriv,
-			param->u.crypt.idx);
+		r8712_set_key(padapter, &padapter->securitypriv, param->u.crypt.idx);
 		if (padapter->registrypriv.power_mgnt > PS_MODE_ACTIVE) {
-			if (padapter->registrypriv.power_mgnt !=
-			    padapter->pwrctrlpriv.pwr_mode)
+			if (padapter->registrypriv.power_mgnt != padapter->pwrctrlpriv.pwr_mode)
 				mod_timer(&padapter->mlmepriv.dhcp_timer,
 					  jiffies + msecs_to_jiffies(60000));
 		}
@@ -148,13 +145,11 @@ static noinline_for_stack char *translate_scan_wpa(struct iw_request_info *info,
 		memset(iwe, 0, sizeof(*iwe));
 		iwe->cmd = IWEVCUSTOM;
 		iwe->u.data.length = (u16)strlen(buf);
-		start = iwe_stream_add_point(info, start, stop,
-			iwe, buf);
+		start = iwe_stream_add_point(info, start, stop, iwe, buf);
 		memset(iwe, 0, sizeof(*iwe));
 		iwe->cmd = IWEVGENIE;
 		iwe->u.data.length = (u16)wpa_len;
-		start = iwe_stream_add_point(info, start, stop,
-			iwe, wpa_ie);
+		start = iwe_stream_add_point(info, start, stop, iwe, wpa_ie);
 	}
 	if (rsn_len > 0) {
 		memset(buf, 0, MAX_WPA_IE_LEN);
@@ -168,13 +163,11 @@ static noinline_for_stack char *translate_scan_wpa(struct iw_request_info *info,
 		memset(iwe, 0, sizeof(*iwe));
 		iwe->cmd = IWEVCUSTOM;
 		iwe->u.data.length = strlen(buf);
-		start = iwe_stream_add_point(info, start, stop,
-			iwe, buf);
+		start = iwe_stream_add_point(info, start, stop, iwe, buf);
 		memset(iwe, 0, sizeof(*iwe));
 		iwe->cmd = IWEVGENIE;
 		iwe->u.data.length = rsn_len;
-		start = iwe_stream_add_point(info, start, stop, iwe,
-			rsn_ie);
+		start = iwe_stream_add_point(info, start, stop, iwe, rsn_ie);
 	}
 
 	return start;
@@ -189,14 +182,11 @@ static noinline_for_stack char *translate_scan_wps(struct iw_request_info *info,
 	u8 wps_ie[512];
 	uint wps_ielen;
 
-	if (r8712_get_wps_ie(pnetwork->network.IEs,
-	    pnetwork->network.IELength,
-	    wps_ie, &wps_ielen)) {
+	if (r8712_get_wps_ie(pnetwork->network.IEs, pnetwork->network.IELength, wps_ie, &wps_ielen)) {
 		if (wps_ielen > 2) {
 			iwe->cmd = IWEVGENIE;
 			iwe->u.data.length = (u16)wps_ielen;
-			start = iwe_stream_add_point(info, start, stop,
-				iwe, wps_ie);
+			start = iwe_stream_add_point(info, start, stop, iwe, wps_ie);
 		}
 	}
 
@@ -259,16 +249,14 @@ static char *translate_scan(struct _adapter *padapter,
 	start = iwe_stream_add_event(info, start, stop, &iwe, IW_EV_CHAR_LEN);
 	/* Add mode */
 	iwe.cmd = SIOCGIWMODE;
-	memcpy((u8 *)&cap, r8712_get_capability_from_ie(pnetwork->network.IEs),
-		2);
+	memcpy((u8 *)&cap, r8712_get_capability_from_ie(pnetwork->network.IEs), 2);
 	le16_to_cpus(&cap);
 	if (cap & (WLAN_CAPABILITY_IBSS | WLAN_CAPABILITY_ESS)) {
 		if (cap & WLAN_CAPABILITY_ESS)
 			iwe.u.mode = (u32)IW_MODE_MASTER;
 		else
 			iwe.u.mode = (u32)IW_MODE_ADHOC;
-		start = iwe_stream_add_event(info, start, stop, &iwe,
-			IW_EV_UINT_LEN);
+		start = iwe_stream_add_event(info, start, stop, &iwe, IW_EV_UINT_LEN);
 	}
 	/* Add frequency/channel */
 	iwe.cmd = SIOCGIWFREQ;
@@ -276,28 +264,23 @@ static char *translate_scan(struct _adapter *padapter,
 		/*  check legal index */
 		u8 dsconfig = pnetwork->network.Configuration.DSConfig;
 
-		if (dsconfig >= 1 && dsconfig <= sizeof(
-		    ieee80211_wlan_frequencies) / sizeof(long))
-			iwe.u.freq.m =
-				(s32)(ieee80211_wlan_frequencies
-				      [dsconfig - 1] * 100000);
+		if (dsconfig >= 1 && dsconfig <= sizeof(ieee80211_wlan_frequencies) / sizeof(long))
+			iwe.u.freq.m = (s32)(ieee80211_wlan_frequencies[dsconfig - 1] * 100000);
 		else
 			iwe.u.freq.m = 0;
 	}
 	iwe.u.freq.e = (s16)1;
 	iwe.u.freq.i = (u8)pnetwork->network.Configuration.DSConfig;
 	start = iwe_stream_add_event(info, start, stop, &iwe,
-		IW_EV_FREQ_LEN);
+				     IW_EV_FREQ_LEN);
 	/* Add encryption capability */
 	iwe.cmd = SIOCGIWENCODE;
 	if (cap & WLAN_CAPABILITY_PRIVACY)
-		iwe.u.data.flags = (u16)(IW_ENCODE_ENABLED |
-				    IW_ENCODE_NOKEY);
+		iwe.u.data.flags = (u16)(IW_ENCODE_ENABLED | IW_ENCODE_NOKEY);
 	else
 		iwe.u.data.flags = (u16)(IW_ENCODE_DISABLED);
 	iwe.u.data.length = (u16)0;
-	start = iwe_stream_add_point(info, start, stop, &iwe,
-		pnetwork->network.Ssid.Ssid);
+	start = iwe_stream_add_point(info, start, stop, &iwe, pnetwork->network.Ssid.Ssid);
 	/*Add basic and extended rates */
 	current_val = start + iwe_stream_lcp_len(info);
 	iwe.cmd = SIOCGIWRATE;
@@ -307,10 +290,9 @@ static char *translate_scan(struct _adapter *padapter,
 	i = 0;
 	while (pnetwork->network.rates[i] != 0) {
 		/* Bit rate given in 500 kb/s units */
-		iwe.u.bitrate.value = (pnetwork->network.rates[i++] &
-				      0x7F) * 500000;
-		current_val = iwe_stream_add_value(info, start, current_val,
-			      stop, &iwe, IW_EV_PARAM_LEN);
+		iwe.u.bitrate.value = (pnetwork->network.rates[i++] & 0x7F) * 500000;
+		current_val = iwe_stream_add_value(info, start, current_val, stop, &iwe,
+						   IW_EV_PARAM_LEN);
 	}
 	/* Check if we added any event */
 	if ((current_val - start) > iwe_stream_lcp_len(info))
@@ -324,8 +306,7 @@ static char *translate_scan(struct _adapter *padapter,
 	iwe.cmd = IWEVQUAL;
 	rssi = r8712_signal_scale_mapping(pnetwork->network.Rssi);
 	/* we only update signal_level (signal strength) that is rssi. */
-	iwe.u.qual.updated = (u8)(IW_QUAL_QUAL_INVALID | IW_QUAL_LEVEL_UPDATED |
-				  IW_QUAL_NOISE_INVALID);
+	iwe.u.qual.updated = (u8)(IW_QUAL_QUAL_INVALID | IW_QUAL_LEVEL_UPDATED | IW_QUAL_NOISE_INVALID);
 	iwe.u.qual.level = rssi;  /* signal strength */
 	iwe.u.qual.qual = 0; /* signal quality */
 	iwe.u.qual.noise = 0; /* noise level */
@@ -490,71 +471,59 @@ static int r871x_set_wpa_ie(struct _adapter *padapter, char *pie,
 			goto exit;
 		}
 		if (r8712_parse_wpa_ie(buf, ielen, &group_cipher,
-		    &pairwise_cipher) == 0) {
+				       &pairwise_cipher) == 0) {
 			padapter->securitypriv.AuthAlgrthm = 2;
 			padapter->securitypriv.ndisauthtype =
 				  Ndis802_11AuthModeWPAPSK;
 		}
 		if (r8712_parse_wpa2_ie(buf, ielen, &group_cipher,
-		    &pairwise_cipher) == 0) {
+					&pairwise_cipher) == 0) {
 			padapter->securitypriv.AuthAlgrthm = 2;
 			padapter->securitypriv.ndisauthtype =
 				  Ndis802_11AuthModeWPA2PSK;
 		}
 		switch (group_cipher) {
 		case WPA_CIPHER_NONE:
-			padapter->securitypriv.XGrpPrivacy =
-				 _NO_PRIVACY_;
-			padapter->securitypriv.ndisencryptstatus =
-				 Ndis802_11EncryptionDisabled;
+			padapter->securitypriv.XGrpPrivacy = _NO_PRIVACY_;
+			padapter->securitypriv.ndisencryptstatus = Ndis802_11EncryptionDisabled;
 			break;
 		case WPA_CIPHER_WEP40:
 			padapter->securitypriv.XGrpPrivacy = _WEP40_;
-			padapter->securitypriv.ndisencryptstatus =
-				 Ndis802_11Encryption1Enabled;
+			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled;
 			break;
 		case WPA_CIPHER_TKIP:
 			padapter->securitypriv.XGrpPrivacy = _TKIP_;
-			padapter->securitypriv.ndisencryptstatus =
-				 Ndis802_11Encryption2Enabled;
+			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption2Enabled;
 			break;
 		case WPA_CIPHER_CCMP:
 			padapter->securitypriv.XGrpPrivacy = _AES_;
-			padapter->securitypriv.ndisencryptstatus =
-				 Ndis802_11Encryption3Enabled;
+			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption3Enabled;
 			break;
 		case WPA_CIPHER_WEP104:
 			padapter->securitypriv.XGrpPrivacy = _WEP104_;
-			padapter->securitypriv.ndisencryptstatus =
-				 Ndis802_11Encryption1Enabled;
+			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled;
 			break;
 		}
 		switch (pairwise_cipher) {
 		case WPA_CIPHER_NONE:
-			padapter->securitypriv.PrivacyAlgrthm =
-				 _NO_PRIVACY_;
-			padapter->securitypriv.ndisencryptstatus =
-				 Ndis802_11EncryptionDisabled;
+			padapter->securitypriv.PrivacyAlgrthm = _NO_PRIVACY_;
+			padapter->securitypriv.ndisencryptstatus = Ndis802_11EncryptionDisabled;
 			break;
 		case WPA_CIPHER_WEP40:
 			padapter->securitypriv.PrivacyAlgrthm = _WEP40_;
-			padapter->securitypriv.ndisencryptstatus =
-				 Ndis802_11Encryption1Enabled;
+			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled;
 			break;
 		case WPA_CIPHER_TKIP:
 			padapter->securitypriv.PrivacyAlgrthm = _TKIP_;
-			padapter->securitypriv.ndisencryptstatus =
-				 Ndis802_11Encryption2Enabled;
+			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption2Enabled;
 			break;
 		case WPA_CIPHER_CCMP:
 			padapter->securitypriv.PrivacyAlgrthm = _AES_;
-			padapter->securitypriv.ndisencryptstatus =
-				 Ndis802_11Encryption3Enabled;
+			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption3Enabled;
 			break;
 		case WPA_CIPHER_WEP104:
 			padapter->securitypriv.PrivacyAlgrthm = _WEP104_;
-			padapter->securitypriv.ndisencryptstatus =
-				 Ndis802_11Encryption1Enabled;
+			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled;
 			break;
 		}
 		padapter->securitypriv.wps_phase = false;
@@ -574,8 +543,8 @@ static int r871x_set_wpa_ie(struct _adapter *padapter, char *pie,
 					    (buf[cnt + 1] + 2) :
 					    (MAX_WPA_IE_LEN << 2);
 					memcpy(padapter->securitypriv.wps_ie,
-					    &buf[cnt],
-					    padapter->securitypriv.wps_ie_len);
+					       &buf[cnt],
+					       padapter->securitypriv.wps_ie_len);
 					padapter->securitypriv.wps_phase =
 								 true;
 					netdev_info(padapter->pnetdev, "r8712u: SET WPS_IE, wps_phase==true\n");
@@ -592,8 +561,7 @@ exit:
 	return ret;
 }
 
-static int r8711_wx_get_name(struct net_device *dev,
-			     struct iw_request_info *info,
+static int r8711_wx_get_name(struct net_device *dev, struct iw_request_info *info,
 			     union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
@@ -604,8 +572,7 @@ static int r8711_wx_get_name(struct net_device *dev,
 	struct wlan_bssid_ex *pcur_bss = &pmlmepriv->cur_network.network;
 	u8 *prates;
 
-	if (check_fwstate(pmlmepriv, _FW_LINKED | WIFI_ADHOC_MASTER_STATE) ==
-	    true) {
+	if (check_fwstate(pmlmepriv, _FW_LINKED | WIFI_ADHOC_MASTER_STATE) == true) {
 		/* parsing HT_CAP_IE */
 		p = r8712_get_ie(&pcur_bss->IEs[12], WLAN_EID_HT_CAPABILITY,
 				 &ht_ielen, pcur_bss->IELength - 12);
@@ -658,9 +625,7 @@ static int r8711_wx_set_freq(struct net_device *dev,
 	int rc = 0;
 
 /* If setting by frequency, convert to a channel */
-	if ((fwrq->e == 1) &&
-	  (fwrq->m >= 241200000) &&
-	  (fwrq->m <= 248700000)) {
+	if ((fwrq->e == 1) && (fwrq->m >= 241200000) && (fwrq->m <= 248700000)) {
 		int f = fwrq->m / 100000;
 		int c = 0;
 
@@ -685,8 +650,7 @@ static int r8711_wx_set_freq(struct net_device *dev,
 	return rc;
 }
 
-static int r8711_wx_get_freq(struct net_device *dev,
-			     struct iw_request_info *info,
+static int r8711_wx_get_freq(struct net_device *dev, struct iw_request_info *info,
 			     union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
@@ -745,7 +709,7 @@ static int r8711_wx_get_mode(struct net_device *dev, struct iw_request_info *a,
 	if (check_fwstate(pmlmepriv, WIFI_STATION_STATE))
 		wrqu->mode = IW_MODE_INFRA;
 	else if (check_fwstate(pmlmepriv,
-		 WIFI_ADHOC_MASTER_STATE | WIFI_ADHOC_STATE))
+			       WIFI_ADHOC_MASTER_STATE | WIFI_ADHOC_STATE))
 		wrqu->mode = IW_MODE_ADHOC;
 	else if (check_fwstate(pmlmepriv, WIFI_AP_STATE))
 		wrqu->mode = IW_MODE_MASTER;
@@ -754,9 +718,8 @@ static int r8711_wx_get_mode(struct net_device *dev, struct iw_request_info *a,
 	return 0;
 }
 
-static int r871x_wx_set_pmkid(struct net_device *dev,
-			     struct iw_request_info *a,
-			     union iwreq_data *wrqu, char *extra)
+static int r871x_wx_set_pmkid(struct net_device *dev, struct iw_request_info *a,
+			      union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
 	struct security_priv *psecuritypriv = &padapter->securitypriv;
@@ -828,7 +791,7 @@ static int r871x_wx_set_pmkid(struct net_device *dev,
 		break;
 	case IW_PMKSA_FLUSH:
 		memset(psecuritypriv->PMKIDList, 0,
-			sizeof(struct RT_PMKID_LIST) * NUM_PMKID_CACHE);
+		       sizeof(struct RT_PMKID_LIST) * NUM_PMKID_CACHE);
 		psecuritypriv->PMKIDIndex = 0;
 		intReturn = true;
 		break;
@@ -850,9 +813,8 @@ static int r8711_wx_get_sens(struct net_device *dev,
 	return 0;
 }
 
-static int r8711_wx_get_range(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
+static int r8711_wx_get_range(struct net_device *dev, struct iw_request_info *info,
+			      union iwreq_data *wrqu, char *extra)
 {
 	struct iw_range *range = (struct iw_range *)extra;
 	u16 val;
@@ -912,9 +874,9 @@ static int r8711_wx_get_rate(struct net_device *dev,
 			     union iwreq_data *wrqu, char *extra);
 
 static int r871x_wx_set_priv(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *awrq,
-				char *extra)
+			     struct iw_request_info *info,
+			     union iwreq_data *awrq,
+			     char *extra)
 {
 	int ret = 0, len = 0;
 	char *ext;
@@ -995,12 +957,10 @@ static int r871x_wx_set_priv(struct net_device *dev,
 		);
 		sprintf(ext, "OK");
 	} else {
-		netdev_info(dev, "r8712u: %s: unknown Command %s.\n",
-			    __func__, ext);
+		netdev_info(dev, "r8712u: %s: unknown Command %s.\n", __func__, ext);
 		goto FREE_EXT;
 	}
-	if (copy_to_user(dwrq->pointer, ext,
-				min(dwrq->length, (__u16)(strlen(ext) + 1))))
+	if (copy_to_user(dwrq->pointer, ext, min(dwrq->length, (__u16)(strlen(ext) + 1))))
 		ret = -EFAULT;
 
 FREE_EXT:
@@ -1021,10 +981,8 @@ FREE_EXT:
  * For this operation to succeed, there is no need for the interface to be up.
  *
  */
-static int r8711_wx_set_wap(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *awrq,
-			 char *extra)
+static int r8711_wx_set_wap(struct net_device *dev, struct iw_request_info *info,
+			    union iwreq_data *awrq, char *extra)
 {
 	int ret = -EINPROGRESS;
 	struct _adapter *padapter = netdev_priv(dev);
@@ -1072,17 +1030,15 @@ static int r8711_wx_set_wap(struct net_device *dev,
 	return ret;
 }
 
-static int r8711_wx_get_wap(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
+static int r8711_wx_get_wap(struct net_device *dev, struct iw_request_info *info,
+			    union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
 	struct wlan_bssid_ex *pcur_bss = &pmlmepriv->cur_network.network;
 
 	wrqu->ap_addr.sa_family = ARPHRD_ETHER;
-	if (check_fwstate(pmlmepriv, _FW_LINKED | WIFI_ADHOC_MASTER_STATE |
-				     WIFI_AP_STATE))
+	if (check_fwstate(pmlmepriv, _FW_LINKED | WIFI_ADHOC_MASTER_STATE | WIFI_AP_STATE))
 		ether_addr_copy(wrqu->ap_addr.sa_data, pcur_bss->MacAddress);
 	else
 		eth_zero_addr(wrqu->ap_addr.sa_data);
@@ -1122,9 +1078,8 @@ static int r871x_wx_set_mlme(struct net_device *dev,
  * For this operation to succeed, the interface is brought Up beforehand.
  *
  */
-static int r8711_wx_set_scan(struct net_device *dev,
-			struct iw_request_info *a,
-			union iwreq_data *wrqu, char *extra)
+static int r8711_wx_set_scan(struct net_device *dev, struct iw_request_info *a,
+			     union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
@@ -1150,8 +1105,7 @@ static int r8711_wx_set_scan(struct net_device *dev,
 			unsigned long irqL;
 			u32 len = min_t(u8, req->essid_len, IW_ESSID_MAX_SIZE);
 
-			memset((unsigned char *)&ssid, 0,
-				 sizeof(struct ndis_802_11_ssid));
+			memset((unsigned char *)&ssid, 0, sizeof(struct ndis_802_11_ssid));
 			memcpy(ssid.Ssid, req->essid, len);
 			ssid.SsidLength = len;
 			spin_lock_irqsave(&pmlmepriv->lock, irqL);
@@ -1173,9 +1127,8 @@ static int r8711_wx_set_scan(struct net_device *dev,
 	return 0;
 }
 
-static int r8711_wx_get_scan(struct net_device *dev,
-				struct iw_request_info *a,
-				union iwreq_data *wrqu, char *extra)
+static int r8711_wx_get_scan(struct net_device *dev, struct iw_request_info *a,
+			     union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
@@ -1189,8 +1142,7 @@ static int r8711_wx_get_scan(struct net_device *dev,
 
 	if (padapter->driver_stopped)
 		return -EINVAL;
-	while (check_fwstate(pmlmepriv, _FW_UNDER_SURVEY |
-			     _FW_UNDER_LINKING)) {
+	while (check_fwstate(pmlmepriv, _FW_UNDER_SURVEY | _FW_UNDER_LINKING)) {
 		msleep(30);
 		cnt++;
 		if (cnt > 100)
@@ -1228,9 +1180,8 @@ static int r8711_wx_get_scan(struct net_device *dev,
  * For this operation to succeed, there is no need for the interface to be Up.
  *
  */
-static int r8711_wx_set_essid(struct net_device *dev,
-				struct iw_request_info *a,
-				union iwreq_data *wrqu, char *extra)
+static int r8711_wx_set_essid(struct net_device *dev, struct iw_request_info *a,
+			      union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
@@ -1268,8 +1219,7 @@ static int r8711_wx_set_essid(struct net_device *dev,
 			if ((!memcmp(dst_ssid, src_ssid, ndis_ssid.SsidLength))
 			    && (pnetwork->network.Ssid.SsidLength ==
 			     ndis_ssid.SsidLength)) {
-				if (check_fwstate(pmlmepriv,
-							WIFI_ADHOC_STATE)) {
+				if (check_fwstate(pmlmepriv, WIFI_ADHOC_STATE)) {
 					if (pnetwork->network.
 						InfrastructureMode
 						!=
@@ -1291,9 +1241,8 @@ static int r8711_wx_set_essid(struct net_device *dev,
 	return -EINPROGRESS;
 }
 
-static int r8711_wx_get_essid(struct net_device *dev,
-				struct iw_request_info *a,
-				union iwreq_data *wrqu, char *extra)
+static int r8711_wx_get_essid(struct net_device *dev, struct iw_request_info *a,
+			      union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
@@ -1311,9 +1260,8 @@ static int r8711_wx_get_essid(struct net_device *dev,
 	return ret;
 }
 
-static int r8711_wx_set_rate(struct net_device *dev,
-				struct iw_request_info *a,
-				union iwreq_data *wrqu, char *extra)
+static int r8711_wx_set_rate(struct net_device *dev, struct iw_request_info *a,
+			     union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
 	u32 target_rate = wrqu->bitrate.value;
@@ -1382,8 +1330,7 @@ set_rate:
 	return r8712_setdatarate_cmd(padapter, datarates);
 }
 
-static int r8711_wx_get_rate(struct net_device *dev,
-			     struct iw_request_info *info,
+static int r8711_wx_get_rate(struct net_device *dev, struct iw_request_info *info,
 			     union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
@@ -1437,9 +1384,8 @@ static int r8711_wx_get_rate(struct net_device *dev,
 	return 0;
 }
 
-static int r8711_wx_get_rts(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
+static int r8711_wx_get_rts(struct net_device *dev, struct iw_request_info *info,
+			    union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
 
@@ -1448,9 +1394,8 @@ static int r8711_wx_get_rts(struct net_device *dev,
 	return 0;
 }
 
-static int r8711_wx_set_frag(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
+static int r8711_wx_set_frag(struct net_device *dev, struct iw_request_info *info,
+			     union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
 
diff --git a/drivers/staging/rtl8712/rtl871x_mp_phy_regdef.h b/drivers/staging/rtl8712/rtl871x_mp_phy_regdef.h
index a08c5d2f59e3..bb9f83d58225 100644
--- a/drivers/staging/rtl8712/rtl871x_mp_phy_regdef.h
+++ b/drivers/staging/rtl8712/rtl871x_mp_phy_regdef.h
@@ -126,7 +126,7 @@
 #define	rFPGA0_AnalogParameter3		0x888	/* Useless now */
 #define	rFPGA0_AnalogParameter4		0x88c
 
-#define	rFPGA0_XA_LSSIReadBack		0x8a0	/* Tranceiver LSSI Readback */
+#define	rFPGA0_XA_LSSIReadBack		0x8a0	/* Transceiver LSSI Readback */
 #define	rFPGA0_XB_LSSIReadBack		0x8a4
 #define	rFPGA0_XC_LSSIReadBack		0x8a8
 #define	rFPGA0_XD_LSSIReadBack		0x8ac
diff --git a/drivers/staging/vc04_services/interface/TODO b/drivers/staging/vc04_services/interface/TODO
index 6d9d4a800aa7..05eb5140d096 100644
--- a/drivers/staging/vc04_services/interface/TODO
+++ b/drivers/staging/vc04_services/interface/TODO
@@ -23,11 +23,6 @@ should properly handle a module unload. This also includes that all
 resources must be freed (kthreads, debugfs entries, ...) and global
 variables avoided.
 
-* Cleanup logging mechanism
-
-The driver should probably be using the standard kernel logging mechanisms
-such as dev_info, dev_dbg, and friends.
-
 * Documentation
 
 A short top-down description of this driver's architecture (function of
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
index 9fb8f657cc78..1579bd4e5263 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
@@ -255,8 +255,7 @@ create_pagelist(struct vchiq_instance *instance, char *buf, char __user *ubuf,
 	pagelist = dma_alloc_coherent(instance->state->dev, pagelist_size, &dma_addr,
 				      GFP_KERNEL);
 
-	vchiq_log_trace(instance->state->dev, VCHIQ_ARM,
-			"%s - %pK", __func__, pagelist);
+	dev_dbg(instance->state->dev, "arm: %pK\n", pagelist);
 
 	if (!pagelist)
 		return NULL;
@@ -311,9 +310,8 @@ create_pagelist(struct vchiq_instance *instance, char *buf, char __user *ubuf,
 						   type == PAGELIST_READ, pages);
 
 		if (actual_pages != num_pages) {
-			vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
-					"%s - only %d/%d pages locked",
-					__func__, actual_pages, num_pages);
+			dev_dbg(instance->state->dev, "arm: Only %d/%d pages locked\n",
+				actual_pages, num_pages);
 
 			/* This is probably due to the process being killed */
 			if (actual_pages > 0)
@@ -407,8 +405,7 @@ free_pagelist(struct vchiq_instance *instance, struct vchiq_pagelist_info *pagel
 	struct page **pages = pagelistinfo->pages;
 	unsigned int num_pages = pagelistinfo->num_pages;
 
-	vchiq_log_trace(instance->state->dev, VCHIQ_ARM,
-			"%s - %pK, %d", __func__, pagelistinfo->pagelist, actual);
+	dev_dbg(instance->state->dev, "arm: %pK, %d\n", pagelistinfo->pagelist, actual);
 
 	/*
 	 * NOTE: dma_unmap_sg must be called before the
@@ -556,8 +553,8 @@ static int vchiq_platform_init(struct platform_device *pdev, struct vchiq_state
 		return -ENXIO;
 	}
 
-	vchiq_log_debug(&pdev->dev, VCHIQ_ARM, "vchiq_init - done (slots %pK, phys %pad)",
-			vchiq_slot_zero, &slot_phys);
+	dev_dbg(&pdev->dev, "arm: vchiq_init - done (slots %pK, phys %pad)\n",
+		vchiq_slot_zero, &slot_phys);
 
 	vchiq_call_connected_callbacks();
 
@@ -659,13 +656,9 @@ vchiq_complete_bulk(struct vchiq_instance *instance, struct vchiq_bulk *bulk)
 			      bulk->actual);
 }
 
-int vchiq_dump_platform_state(void *dump_context)
+void vchiq_dump_platform_state(struct seq_file *f)
 {
-	char buf[80];
-	int len;
-
-	len = snprintf(buf, sizeof(buf), "  Platform: 2835 (VC master)");
-	return vchiq_dump(dump_context, buf, len + 1);
+	seq_puts(f, "  Platform: 2835 (VC master)\n");
 }
 
 #define VCHIQ_INIT_RETRIES 10
@@ -687,19 +680,17 @@ int vchiq_initialise(struct vchiq_instance **instance_out)
 		usleep_range(500, 600);
 	}
 	if (i == VCHIQ_INIT_RETRIES) {
-		vchiq_log_error(state->dev, VCHIQ_CORE, "%s: videocore not initialized\n",
-				__func__);
+		dev_err(state->dev, "core: %s: Videocore not initialized\n", __func__);
 		ret = -ENOTCONN;
 		goto failed;
 	} else if (i > 0) {
-		vchiq_log_warning(state->dev, VCHIQ_CORE,
-				  "%s: videocore initialized after %d retries\n", __func__, i);
+		dev_warn(state->dev, "core: %s: videocore initialized after %d retries\n",
+			 __func__, i);
 	}
 
 	instance = kzalloc(sizeof(*instance), GFP_KERNEL);
 	if (!instance) {
-		vchiq_log_error(state->dev, VCHIQ_CORE,
-				"%s: error allocating vchiq instance\n", __func__);
+		dev_err(state->dev, "core: %s: Cannot allocate vchiq instance\n", __func__);
 		ret = -ENOMEM;
 		goto failed;
 	}
@@ -714,8 +705,7 @@ int vchiq_initialise(struct vchiq_instance **instance_out)
 	ret = 0;
 
 failed:
-	vchiq_log_trace(state->dev, VCHIQ_CORE,
-			"%s(%p): returning %d", __func__, instance, ret);
+	dev_dbg(state->dev, "core: (%p): returning %d\n", instance, ret);
 
 	return ret;
 }
@@ -728,9 +718,9 @@ void free_bulk_waiter(struct vchiq_instance *instance)
 	list_for_each_entry_safe(waiter, next,
 				 &instance->bulk_waiter_list, list) {
 		list_del(&waiter->list);
-		vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
-				"bulk_waiter - cleaned up %pK for pid %d",
-				waiter, waiter->pid);
+		dev_dbg(instance->state->dev,
+			"arm: bulk_waiter - cleaned up %pK for pid %d\n",
+			waiter, waiter->pid);
 		kfree(waiter);
 	}
 }
@@ -748,8 +738,7 @@ int vchiq_shutdown(struct vchiq_instance *instance)
 
 	mutex_unlock(&state->mutex);
 
-	vchiq_log_trace(state->dev, VCHIQ_CORE,
-			"%s(%p): returning %d", __func__, instance, status);
+	dev_dbg(state->dev, "core: (%p): returning %d\n", instance, status);
 
 	free_bulk_waiter(instance);
 	kfree(instance);
@@ -769,8 +758,8 @@ int vchiq_connect(struct vchiq_instance *instance)
 	struct vchiq_state *state = instance->state;
 
 	if (mutex_lock_killable(&state->mutex)) {
-		vchiq_log_trace(state->dev, VCHIQ_CORE,
-				"%s: call to mutex_lock failed", __func__);
+		dev_dbg(state->dev,
+			"core: call to mutex_lock failed\n");
 		status = -EAGAIN;
 		goto failed;
 	}
@@ -782,8 +771,7 @@ int vchiq_connect(struct vchiq_instance *instance)
 	mutex_unlock(&state->mutex);
 
 failed:
-	vchiq_log_trace(state->dev, VCHIQ_CORE,
-			"%s(%p): returning %d", __func__, instance, status);
+	dev_dbg(state->dev, "core: (%p): returning %d\n", instance, status);
 
 	return status;
 }
@@ -814,8 +802,7 @@ vchiq_add_service(struct vchiq_instance *instance,
 		status = -EINVAL;
 	}
 
-	vchiq_log_trace(state->dev, VCHIQ_CORE,
-			"%s(%p): returning %d", __func__, instance, status);
+	dev_dbg(state->dev, "core: (%p): returning %d\n", instance, status);
 
 	return status;
 }
@@ -846,8 +833,7 @@ vchiq_open_service(struct vchiq_instance *instance,
 	}
 
 failed:
-	vchiq_log_trace(state->dev, VCHIQ_CORE,
-			"%s(%p): returning %d", __func__, instance, status);
+	dev_dbg(state->dev, "core: (%p): returning %d\n", instance, status);
 
 	return status;
 }
@@ -971,8 +957,7 @@ vchiq_blocking_bulk_transfer(struct vchiq_instance *instance, unsigned int handl
 	} else {
 		waiter = kzalloc(sizeof(*waiter), GFP_KERNEL);
 		if (!waiter) {
-			vchiq_log_error(service->state->dev, VCHIQ_CORE,
-					"%s - out of memory", __func__);
+			dev_err(service->state->dev, "core: %s: - Out of memory\n", __func__);
 			return -ENOMEM;
 		}
 	}
@@ -995,9 +980,8 @@ vchiq_blocking_bulk_transfer(struct vchiq_instance *instance, unsigned int handl
 		mutex_lock(&instance->bulk_waiter_list_mutex);
 		list_add(&waiter->list, &instance->bulk_waiter_list);
 		mutex_unlock(&instance->bulk_waiter_list_mutex);
-		vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
-				"saved bulk_waiter %pK for pid %d", waiter,
-				current->pid);
+		dev_dbg(instance->state->dev, "arm: saved bulk_waiter %pK for pid %d\n",
+			waiter, current->pid);
 	}
 
 	return status;
@@ -1017,16 +1001,13 @@ add_completion(struct vchiq_instance *instance, enum vchiq_reason reason,
 	while ((insert - instance->completion_remove) >= MAX_COMPLETIONS) {
 		/* Out of space - wait for the client */
 		DEBUG_TRACE(SERVICE_CALLBACK_LINE);
-		vchiq_log_trace(instance->state->dev, VCHIQ_CORE,
-				"%s - completion queue full", __func__);
+		dev_dbg(instance->state->dev, "core: completion queue full\n");
 		DEBUG_COUNT(COMPLETION_QUEUE_FULL_COUNT);
 		if (wait_for_completion_interruptible(&instance->remove_event)) {
-			vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
-					"service_callback interrupted");
+			dev_dbg(instance->state->dev, "arm: service_callback interrupted\n");
 			return -EAGAIN;
 		} else if (instance->closing) {
-			vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
-					"service_callback closing");
+			dev_dbg(instance->state->dev, "arm: service_callback closing\n");
 			return 0;
 		}
 		DEBUG_TRACE(SERVICE_CALLBACK_LINE);
@@ -1106,11 +1087,10 @@ service_callback(struct vchiq_instance *instance, enum vchiq_reason reason,
 	vchiq_service_get(service);
 	rcu_read_unlock();
 
-	vchiq_log_trace(service->state->dev, VCHIQ_ARM,
-			"%s - service %lx(%d,%p), reason %d, header %lx, instance %lx, bulk_userdata %lx",
-			__func__, (unsigned long)user_service, service->localport,
-			user_service->userdata, reason, (unsigned long)header,
-			(unsigned long)instance, (unsigned long)bulk_userdata);
+	dev_dbg(service->state->dev,
+		"arm: service %p(%d,%p), reason %d, header %p, instance %p, bulk_userdata %p\n",
+		user_service, service->localport, user_service->userdata,
+		reason, header, instance, bulk_userdata);
 
 	if (header && user_service->is_vchi) {
 		spin_lock(&msg_queue_spinlock);
@@ -1119,8 +1099,7 @@ service_callback(struct vchiq_instance *instance, enum vchiq_reason reason,
 			spin_unlock(&msg_queue_spinlock);
 			DEBUG_TRACE(SERVICE_CALLBACK_LINE);
 			DEBUG_COUNT(MSG_QUEUE_FULL_COUNT);
-			vchiq_log_trace(service->state->dev, VCHIQ_ARM,
-					"%s - msg queue full", __func__);
+			dev_dbg(service->state->dev, "arm: msg queue full\n");
 			/*
 			 * If there is no MESSAGE_AVAILABLE in the completion
 			 * queue, add one
@@ -1129,8 +1108,8 @@ service_callback(struct vchiq_instance *instance, enum vchiq_reason reason,
 				instance->completion_remove) < 0) {
 				int status;
 
-				vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
-						"Inserting extra MESSAGE_AVAILABLE");
+				dev_dbg(instance->state->dev,
+					"arm: Inserting extra MESSAGE_AVAILABLE\n");
 				DEBUG_TRACE(SERVICE_CALLBACK_LINE);
 				status = add_completion(instance, reason, NULL, user_service,
 							bulk_userdata);
@@ -1143,14 +1122,12 @@ service_callback(struct vchiq_instance *instance, enum vchiq_reason reason,
 
 			DEBUG_TRACE(SERVICE_CALLBACK_LINE);
 			if (wait_for_completion_interruptible(&user_service->remove_event)) {
-				vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
-						"%s interrupted", __func__);
+				dev_dbg(instance->state->dev, "arm: interrupted\n");
 				DEBUG_TRACE(SERVICE_CALLBACK_LINE);
 				vchiq_service_put(service);
 				return -EAGAIN;
 			} else if (instance->closing) {
-				vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
-						"%s closing", __func__);
+				dev_dbg(instance->state->dev, "arm: closing\n");
 				DEBUG_TRACE(SERVICE_CALLBACK_LINE);
 				vchiq_service_put(service);
 				return -EINVAL;
@@ -1190,56 +1167,13 @@ service_callback(struct vchiq_instance *instance, enum vchiq_reason reason,
 		bulk_userdata);
 }
 
-int vchiq_dump(void *dump_context, const char *str, int len)
-{
-	struct dump_context *context = (struct dump_context *)dump_context;
-	int copy_bytes;
-
-	if (context->actual >= context->space)
-		return 0;
-
-	if (context->offset > 0) {
-		int skip_bytes = min_t(int, len, context->offset);
-
-		str += skip_bytes;
-		len -= skip_bytes;
-		context->offset -= skip_bytes;
-		if (context->offset > 0)
-			return 0;
-	}
-	copy_bytes = min_t(int, len, context->space - context->actual);
-	if (copy_bytes == 0)
-		return 0;
-	if (copy_to_user(context->buf + context->actual, str,
-			 copy_bytes))
-		return -EFAULT;
-	context->actual += copy_bytes;
-	len -= copy_bytes;
-
-	/*
-	 * If the terminating NUL is included in the length, then it
-	 * marks the end of a line and should be replaced with a
-	 * carriage return.
-	 */
-	if ((len == 0) && (str[copy_bytes - 1] == '\0')) {
-		char cr = '\n';
-
-		if (copy_to_user(context->buf + context->actual - 1,
-				 &cr, 1))
-			return -EFAULT;
-	}
-	return 0;
-}
-
-int vchiq_dump_platform_instances(void *dump_context)
+void vchiq_dump_platform_instances(struct seq_file *f)
 {
 	struct vchiq_state *state = vchiq_get_state();
-	char buf[80];
-	int len;
 	int i;
 
 	if (!state)
-		return -ENOTCONN;
+		return;
 
 	/*
 	 * There is no list of instances, so instead scan all services,
@@ -1264,7 +1198,6 @@ int vchiq_dump_platform_instances(void *dump_context)
 	for (i = 0; i < state->unused_service; i++) {
 		struct vchiq_service *service;
 		struct vchiq_instance *instance;
-		int err;
 
 		rcu_read_lock();
 		service = rcu_dereference(state->services[i]);
@@ -1280,43 +1213,35 @@ int vchiq_dump_platform_instances(void *dump_context)
 		}
 		rcu_read_unlock();
 
-		len = snprintf(buf, sizeof(buf),
-			       "Instance %pK: pid %d,%s completions %d/%d",
-			       instance, instance->pid,
-			       instance->connected ? " connected, " :
-			       "",
-			       instance->completion_insert -
-			       instance->completion_remove,
-			       MAX_COMPLETIONS);
-		err = vchiq_dump(dump_context, buf, len + 1);
-		if (err)
-			return err;
+		seq_printf(f, "Instance %pK: pid %d,%s completions %d/%d\n",
+			   instance, instance->pid,
+			   instance->connected ? " connected, " :
+			   "",
+			   instance->completion_insert -
+			   instance->completion_remove,
+			   MAX_COMPLETIONS);
 		instance->mark = 1;
 	}
-	return 0;
 }
 
-int vchiq_dump_platform_service_state(void *dump_context,
-				      struct vchiq_service *service)
+void vchiq_dump_platform_service_state(struct seq_file *f,
+				       struct vchiq_service *service)
 {
 	struct user_service *user_service =
 			(struct user_service *)service->base.userdata;
-	char buf[80];
-	int len;
 
-	len = scnprintf(buf, sizeof(buf), "  instance %pK", service->instance);
+	seq_printf(f, "  instance %pK", service->instance);
 
 	if ((service->base.callback == service_callback) && user_service->is_vchi) {
-		len += scnprintf(buf + len, sizeof(buf) - len, ", %d/%d messages",
-				 user_service->msg_insert - user_service->msg_remove,
-				 MSG_QUEUE_SIZE);
+		seq_printf(f, ", %d/%d messages",
+			   user_service->msg_insert - user_service->msg_remove,
+			   MSG_QUEUE_SIZE);
 
 		if (user_service->dequeue_pending)
-			len += scnprintf(buf + len, sizeof(buf) - len,
-				" (dequeue pending)");
+			seq_puts(f, " (dequeue pending)");
 	}
 
-	return vchiq_dump(dump_context, buf, len + 1);
+	seq_puts(f, "\n");
 }
 
 struct vchiq_state *
@@ -1346,8 +1271,8 @@ vchiq_keepalive_vchiq_callback(struct vchiq_instance *instance,
 			       struct vchiq_header *header,
 			       unsigned int service_user, void *bulk_user)
 {
-	vchiq_log_error(instance->state->dev, VCHIQ_SUSPEND,
-			"%s callback reason %d", __func__, reason);
+	dev_err(instance->state->dev, "suspend: %s: callback reason %d\n",
+		__func__, reason);
 	return 0;
 }
 
@@ -1371,22 +1296,20 @@ vchiq_keepalive_thread_func(void *v)
 
 	ret = vchiq_initialise(&instance);
 	if (ret) {
-		vchiq_log_error(state->dev, VCHIQ_SUSPEND,
-				"%s vchiq_initialise failed %d", __func__, ret);
+		dev_err(state->dev, "suspend: %s: vchiq_initialise failed %d\n", __func__, ret);
 		goto exit;
 	}
 
 	status = vchiq_connect(instance);
 	if (status) {
-		vchiq_log_error(state->dev, VCHIQ_SUSPEND,
-				"%s vchiq_connect failed %d", __func__, status);
+		dev_err(state->dev, "suspend: %s: vchiq_connect failed %d\n", __func__, status);
 		goto shutdown;
 	}
 
 	status = vchiq_add_service(instance, &params, &ka_handle);
 	if (status) {
-		vchiq_log_error(state->dev, VCHIQ_SUSPEND,
-				"%s vchiq_open_service failed %d", __func__, status);
+		dev_err(state->dev, "suspend: %s: vchiq_open_service failed %d\n",
+			__func__, status);
 		goto shutdown;
 	}
 
@@ -1394,8 +1317,7 @@ vchiq_keepalive_thread_func(void *v)
 		long rc = 0, uc = 0;
 
 		if (wait_for_completion_interruptible(&arm_state->ka_evt)) {
-			vchiq_log_error(state->dev, VCHIQ_SUSPEND,
-					"%s interrupted", __func__);
+			dev_err(state->dev, "suspend: %s: interrupted\n", __func__);
 			flush_signals(current);
 			continue;
 		}
@@ -1415,16 +1337,15 @@ vchiq_keepalive_thread_func(void *v)
 			atomic_inc(&arm_state->ka_use_ack_count);
 			status = vchiq_use_service(instance, ka_handle);
 			if (status) {
-				vchiq_log_error(state->dev, VCHIQ_SUSPEND,
-						"%s vchiq_use_service error %d", __func__, status);
+				dev_err(state->dev, "suspend: %s: vchiq_use_service error %d\n",
+					__func__, status);
 			}
 		}
 		while (rc--) {
 			status = vchiq_release_service(instance, ka_handle);
 			if (status) {
-				vchiq_log_error(state->dev, VCHIQ_SUSPEND,
-						"%s vchiq_release_service error %d", __func__,
-						status);
+				dev_err(state->dev, "suspend: %s: vchiq_release_service error %d\n",
+					__func__, status);
 			}
 		}
 	}
@@ -1459,7 +1380,7 @@ vchiq_use_internal(struct vchiq_state *state, struct vchiq_service *service,
 			 service->client_id);
 		entity_uc = &service->service_use_count;
 	} else {
-		vchiq_log_error(state->dev, VCHIQ_SUSPEND, "%s null service ptr", __func__);
+		dev_err(state->dev, "suspend: %s: null service ptr\n", __func__);
 		ret = -EINVAL;
 		goto out;
 	}
@@ -1468,8 +1389,8 @@ vchiq_use_internal(struct vchiq_state *state, struct vchiq_service *service,
 	local_uc = ++arm_state->videocore_use_count;
 	++(*entity_uc);
 
-	vchiq_log_trace(state->dev, VCHIQ_SUSPEND, "%s %s count %d, state count %d",
-			__func__, entity, *entity_uc, local_uc);
+	dev_dbg(state->dev, "suspend: %s count %d, state count %d\n",
+		entity, *entity_uc, local_uc);
 
 	write_unlock_bh(&arm_state->susp_res_lock);
 
@@ -1488,7 +1409,7 @@ vchiq_use_internal(struct vchiq_state *state, struct vchiq_service *service,
 	}
 
 out:
-	vchiq_log_trace(state->dev, VCHIQ_SUSPEND, "%s exit %d", __func__, ret);
+	dev_dbg(state->dev, "suspend: exit %d\n", ret);
 	return ret;
 }
 
@@ -1526,14 +1447,14 @@ vchiq_release_internal(struct vchiq_state *state, struct vchiq_service *service)
 	--arm_state->videocore_use_count;
 	--(*entity_uc);
 
-	vchiq_log_trace(state->dev, VCHIQ_SUSPEND, "%s %s count %d, state count %d",
-			__func__, entity, *entity_uc, arm_state->videocore_use_count);
+	dev_dbg(state->dev, "suspend: %s count %d, state count %d\n",
+		entity, *entity_uc, arm_state->videocore_use_count);
 
 unlock:
 	write_unlock_bh(&arm_state->susp_res_lock);
 
 out:
-	vchiq_log_trace(state->dev, VCHIQ_SUSPEND, "%s exit %d", __func__, ret);
+	dev_dbg(state->dev, "suspend: exit %d\n", ret);
 	return ret;
 }
 
@@ -1707,20 +1628,19 @@ vchiq_dump_service_use_state(struct vchiq_state *state)
 	read_unlock_bh(&arm_state->susp_res_lock);
 
 	if (only_nonzero)
-		vchiq_log_warning(state->dev, VCHIQ_SUSPEND,
-				  "Too many active services (%d). Only dumping up to first %d services with non-zero use-count",
-				  active_services, found);
+		dev_warn(state->dev,
+			 "suspend: Too many active services (%d). Only dumping up to first %d services with non-zero use-count\n",
+			 active_services, found);
 
 	for (i = 0; i < found; i++) {
-		vchiq_log_warning(state->dev, VCHIQ_SUSPEND,
-				  "%p4cc:%d service count %d %s",
-				  &service_data[i].fourcc,
-				  service_data[i].clientid, service_data[i].use_count,
-				  service_data[i].use_count ? nz : "");
+		dev_warn(state->dev,
+			 "suspend: %p4cc:%d service count %d %s\n",
+			 &service_data[i].fourcc,
+			 service_data[i].clientid, service_data[i].use_count,
+			 service_data[i].use_count ? nz : "");
 	}
-	vchiq_log_warning(state->dev, VCHIQ_SUSPEND, "VCHIQ use count %d", peer_count);
-	vchiq_log_warning(state->dev, VCHIQ_SUSPEND, "Overall vchiq instance use count %d",
-			  vc_use_count);
+	dev_warn(state->dev, "suspend: VCHIQ use count %d\n", peer_count);
+	dev_warn(state->dev, "suspend: Overall vchiq instance use count %d\n", vc_use_count);
 
 	kfree(service_data);
 }
@@ -1742,10 +1662,10 @@ vchiq_check_service(struct vchiq_service *service)
 	read_unlock_bh(&arm_state->susp_res_lock);
 
 	if (ret) {
-		vchiq_log_error(service->state->dev, VCHIQ_SUSPEND,
-				"%s ERROR - %p4cc:%d service count %d, state count %d", __func__,
-				&service->base.fourcc, service->client_id,
-				service->service_use_count, arm_state->videocore_use_count);
+		dev_err(service->state->dev,
+			"suspend: %s:  %p4cc:%d service count %d, state count %d\n",
+			__func__, &service->base.fourcc, service->client_id,
+			service->service_use_count, arm_state->videocore_use_count);
 		vchiq_dump_service_use_state(service->state);
 	}
 out:
@@ -1759,8 +1679,8 @@ void vchiq_platform_conn_state_changed(struct vchiq_state *state,
 	struct vchiq_arm_state *arm_state = vchiq_platform_get_arm_state(state);
 	char threadname[16];
 
-	vchiq_log_debug(state->dev, VCHIQ_SUSPEND, "%d: %s->%s", state->id,
-			get_conn_state_name(oldstate), get_conn_state_name(newstate));
+	dev_dbg(state->dev, "suspend: %d: %s->%s\n",
+		state->id, get_conn_state_name(oldstate), get_conn_state_name(newstate));
 	if (state->conn_state != VCHIQ_CONNSTATE_CONNECTED)
 		return;
 
@@ -1778,9 +1698,8 @@ void vchiq_platform_conn_state_changed(struct vchiq_state *state,
 					      (void *)state,
 					      threadname);
 	if (IS_ERR(arm_state->ka_thread)) {
-		vchiq_log_error(state->dev, VCHIQ_SUSPEND,
-				"vchiq: FATAL: couldn't create thread %s",
-				threadname);
+		dev_err(state->dev, "suspend: Couldn't create thread %s\n",
+			threadname);
 	} else {
 		wake_up_process(arm_state->ka_thread);
 	}
@@ -1825,9 +1744,8 @@ static int vchiq_probe(struct platform_device *pdev)
 
 	vchiq_debugfs_init();
 
-	vchiq_log_debug(&pdev->dev, VCHIQ_ARM,
-			"vchiq: platform initialised - version %d (min %d)",
-			VCHIQ_VERSION, VCHIQ_VERSION_MIN);
+	dev_dbg(&pdev->dev, "arm: platform initialised - version %d (min %d)\n",
+		VCHIQ_VERSION, VCHIQ_VERSION_MIN);
 
 	/*
 	 * Simply exit on error since the function handles cleanup in
@@ -1835,8 +1753,7 @@ static int vchiq_probe(struct platform_device *pdev)
 	 */
 	err = vchiq_register_chrdev(&pdev->dev);
 	if (err) {
-		vchiq_log_warning(&pdev->dev, VCHIQ_ARM,
-				  "Failed to initialize vchiq cdev");
+		dev_warn(&pdev->dev, "arm: Failed to initialize vchiq cdev\n");
 		goto error_exit;
 	}
 
@@ -1846,7 +1763,7 @@ static int vchiq_probe(struct platform_device *pdev)
 	return 0;
 
 failed_platform_init:
-	vchiq_log_warning(&pdev->dev, VCHIQ_ARM, "could not initialize vchiq platform");
+	dev_warn(&pdev->dev, "arm: Could not initialize vchiq platform\n");
 error_exit:
 	return err;
 }
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h
index 7cdc3d70bd2c..7844ef765a00 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h
@@ -69,13 +69,6 @@ struct vchiq_instance {
 	struct vchiq_debugfs_node debugfs_node;
 };
 
-struct dump_context {
-	char __user *buf;
-	size_t actual;
-	size_t space;
-	loff_t offset;
-};
-
 extern spinlock_t msg_queue_spinlock;
 extern struct vchiq_state g_state;
 
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_connected.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_connected.c
index b3928bd8c9c6..3cad13f09e37 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_connected.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_connected.c
@@ -27,7 +27,7 @@ static void connected_init(void)
  * be made immediately, otherwise it will be deferred until
  * vchiq_call_connected_callbacks is called.
  */
-void vchiq_add_connected_callback(void (*callback)(void))
+void vchiq_add_connected_callback(struct vchiq_device *device, void (*callback)(void))
 {
 	connected_init();
 
@@ -39,9 +39,9 @@ void vchiq_add_connected_callback(void (*callback)(void))
 		callback();
 	} else {
 		if (g_num_deferred_callbacks >= MAX_CALLBACKS) {
-			vchiq_log_error(NULL, VCHIQ_CORE,
-					"There already %d callback registered - please increase MAX_CALLBACKS",
-					g_num_deferred_callbacks);
+			dev_err(&device->dev,
+				"core: There already %d callback registered - please increase MAX_CALLBACKS\n",
+				g_num_deferred_callbacks);
 		} else {
 			g_deferred_callback[g_num_deferred_callbacks] =
 				callback;
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_connected.h b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_connected.h
index 4caf5e30099d..e4ed56446f8a 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_connected.h
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_connected.h
@@ -1,10 +1,12 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /* Copyright (c) 2010-2012 Broadcom. All rights reserved. */
 
+#include "vchiq_bus.h"
+
 #ifndef VCHIQ_CONNECTED_H
 #define VCHIQ_CONNECTED_H
 
-void vchiq_add_connected_callback(void (*callback)(void));
+void vchiq_add_connected_callback(struct vchiq_device *device, void (*callback)(void));
 void vchiq_call_connected_callbacks(void);
 
 #endif /* VCHIQ_CONNECTED_H */
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
index 39b857da2d42..76c27778154a 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
@@ -217,10 +217,10 @@ static const char *msg_type_str(unsigned int msg_type)
 static inline void
 set_service_state(struct vchiq_service *service, int newstate)
 {
-	vchiq_log_debug(service->state->dev, VCHIQ_CORE, "%d: srv:%d %s->%s",
-			service->state->id, service->localport,
-			srvstate_names[service->srvstate],
-			srvstate_names[newstate]);
+	dev_dbg(service->state->dev, "core: %d: srv:%d %s->%s\n",
+		service->state->id, service->localport,
+		srvstate_names[service->srvstate],
+		srvstate_names[newstate]);
 	service->srvstate = newstate;
 }
 
@@ -245,8 +245,7 @@ find_service_by_handle(struct vchiq_instance *instance, unsigned int handle)
 		return service;
 	}
 	rcu_read_unlock();
-	vchiq_log_debug(service->state->dev, VCHIQ_CORE,
-			"Invalid service handle 0x%x", handle);
+	dev_dbg(instance->state->dev, "core: Invalid service handle 0x%x\n", handle);
 	return NULL;
 }
 
@@ -266,8 +265,7 @@ find_service_by_port(struct vchiq_state *state, unsigned int localport)
 		}
 		rcu_read_unlock();
 	}
-	vchiq_log_debug(state->dev, VCHIQ_CORE,
-			"Invalid port %u", localport);
+	dev_dbg(state->dev, "core: Invalid port %u\n", localport);
 	return NULL;
 }
 
@@ -287,8 +285,7 @@ find_service_for_instance(struct vchiq_instance *instance, unsigned int handle)
 		return service;
 	}
 	rcu_read_unlock();
-	vchiq_log_debug(service->state->dev, VCHIQ_CORE,
-			"Invalid service handle 0x%x", handle);
+	dev_dbg(instance->state->dev, "core: Invalid service handle 0x%x\n", handle);
 	return NULL;
 }
 
@@ -310,8 +307,7 @@ find_closed_service_for_instance(struct vchiq_instance *instance, unsigned int h
 		return service;
 	}
 	rcu_read_unlock();
-	vchiq_log_debug(service->state->dev, VCHIQ_CORE,
-			"Invalid service handle 0x%x", handle);
+	dev_dbg(instance->state->dev, "core: Invalid service handle 0x%x\n", handle);
 	return service;
 }
 
@@ -459,15 +455,15 @@ make_service_callback(struct vchiq_service *service, enum vchiq_reason reason,
 {
 	int status;
 
-	vchiq_log_trace(service->state->dev, VCHIQ_CORE, "%d: callback:%d (%s, %pK, %pK)",
-			service->state->id, service->localport, reason_names[reason],
-			header, bulk_userdata);
+	dev_dbg(service->state->dev, "core: %d: callback:%d (%s, %pK, %pK)\n",
+		service->state->id, service->localport, reason_names[reason],
+		header, bulk_userdata);
 	status = service->base.callback(service->instance, reason, header, service->handle,
 					bulk_userdata);
 	if (status && (status != -EAGAIN)) {
-		vchiq_log_warning(service->state->dev, VCHIQ_CORE,
-				  "%d: ignoring ERROR from callback to service %x",
-				  service->state->id, service->handle);
+		dev_warn(service->state->dev,
+			 "core: %d: ignoring ERROR from callback to service %x\n",
+			 service->state->id, service->handle);
 		status = 0;
 	}
 
@@ -482,8 +478,8 @@ vchiq_set_conn_state(struct vchiq_state *state, enum vchiq_connstate newstate)
 {
 	enum vchiq_connstate oldstate = state->conn_state;
 
-	vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: %s->%s", state->id, conn_state_names[oldstate],
-			conn_state_names[newstate]);
+	dev_dbg(state->dev, "core: %d: %s->%s\n",
+		state->id, conn_state_names[oldstate], conn_state_names[newstate]);
 	state->conn_state = newstate;
 	vchiq_platform_conn_state_changed(state, oldstate, newstate);
 }
@@ -741,10 +737,10 @@ process_free_data_message(struct vchiq_state *state, u32 *service_found,
 		 */
 		complete(&quota->quota_event);
 	} else if (count == 0) {
-		vchiq_log_error(state->dev, VCHIQ_CORE,
-				"service %d message_use_count=%d (header %pK, msgid %x, header->msgid %x, header->size %x)",
-				port, quota->message_use_count, header, msgid, header->msgid,
-				header->size);
+		dev_err(state->dev,
+			"core: service %d message_use_count=%d (header %pK, msgid %x, header->msgid %x, header->size %x)\n",
+			port, quota->message_use_count, header, msgid,
+			header->msgid, header->size);
 		WARN(1, "invalid message use count\n");
 	}
 	if (!BITSET_IS_SET(service_found, port)) {
@@ -763,12 +759,12 @@ process_free_data_message(struct vchiq_state *state, u32 *service_found,
 			 * it has dropped below its quota
 			 */
 			complete(&quota->quota_event);
-			vchiq_log_trace(state->dev, VCHIQ_CORE, "%d: pfq:%d %x@%pK - slot_use->%d",
-					state->id, port, header->size, header, count - 1);
+			dev_dbg(state->dev, "core: %d: pfq:%d %x@%pK - slot_use->%d\n",
+				state->id, port, header->size, header, count - 1);
 		} else {
-			vchiq_log_error(state->dev, VCHIQ_CORE,
-					"service %d slot_use_count=%d (header %pK, msgid %x, header->msgid %x, header->size %x)",
-					port, count, header, msgid, header->msgid, header->size);
+			dev_err(state->dev,
+				"core: service %d slot_use_count=%d (header %pK, msgid %x, header->msgid %x, header->size %x)\n",
+				port, count, header, msgid, header->msgid, header->size);
 			WARN(1, "bad slot use count\n");
 		}
 	}
@@ -809,9 +805,9 @@ process_free_queue(struct vchiq_state *state, u32 *service_found,
 		 */
 		rmb();
 
-		vchiq_log_trace(state->dev, VCHIQ_CORE, "%d: pfq %d=%pK %x %x",
-				state->id, slot_index, data, local->slot_queue_recycle,
-				slot_queue_available);
+		dev_dbg(state->dev, "core: %d: pfq %d=%pK %x %x\n",
+			state->id, slot_index, data, local->slot_queue_recycle,
+			slot_queue_available);
 
 		/* Initialise the bitmask for services which have used this slot */
 		memset(service_found, 0, length);
@@ -831,9 +827,9 @@ process_free_queue(struct vchiq_state *state, u32 *service_found,
 
 			pos += calc_stride(header->size);
 			if (pos > VCHIQ_SLOT_SIZE) {
-				vchiq_log_error(state->dev, VCHIQ_CORE,
-						"pfq - pos %x: header %pK, msgid %x, header->msgid %x, header->size %x",
-						pos, header, msgid, header->msgid, header->size);
+				dev_err(state->dev,
+					"core: pfq - pos %x: header %pK, msgid %x, header->msgid %x, header->size %x\n",
+					pos, header, msgid, header->msgid, header->size);
 				WARN(1, "invalid slot position\n");
 			}
 		}
@@ -980,10 +976,10 @@ queue_message(struct vchiq_state *state, struct vchiq_service *service,
 		       ((tx_end_index != quota->previous_tx_index) &&
 			(quota->slot_use_count == quota->slot_quota))) {
 			spin_unlock(&quota_spinlock);
-			vchiq_log_trace(state->dev, VCHIQ_CORE,
-					"%d: qm:%d %s,%zx - quota stall (msg %d, slot %d)",
-					state->id, service->localport, msg_type_str(type), size,
-					quota->message_use_count, quota->slot_use_count);
+			dev_dbg(state->dev,
+				"core: %d: qm:%d %s,%zx - quota stall (msg %d, slot %d)\n",
+				state->id, service->localport, msg_type_str(type), size,
+				quota->message_use_count, quota->slot_use_count);
 			VCHIQ_SERVICE_STATS_INC(service, quota_stalls);
 			mutex_unlock(&state->slot_mutex);
 			if (wait_for_completion_interruptible(&quota->quota_event))
@@ -1023,9 +1019,9 @@ queue_message(struct vchiq_state *state, struct vchiq_service *service,
 		int tx_end_index;
 		int slot_use_count;
 
-		vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: qm %s@%pK,%zx (%d->%d)", state->id,
-				msg_type_str(VCHIQ_MSG_TYPE(msgid)), header, size,
-				VCHIQ_MSG_SRCPORT(msgid), VCHIQ_MSG_DSTPORT(msgid));
+		dev_dbg(state->dev, "core: %d: qm %s@%pK,%zx (%d->%d)\n",
+			state->id, msg_type_str(VCHIQ_MSG_TYPE(msgid)), header, size,
+			VCHIQ_MSG_SRCPORT(msgid), VCHIQ_MSG_DSTPORT(msgid));
 
 		WARN_ON(flags & (QMFLAGS_NO_MUTEX_LOCK |
 				 QMFLAGS_NO_MUTEX_UNLOCK));
@@ -1073,17 +1069,16 @@ queue_message(struct vchiq_state *state, struct vchiq_service *service,
 		spin_unlock(&quota_spinlock);
 
 		if (slot_use_count)
-			vchiq_log_trace(state->dev, VCHIQ_CORE,
-					"%d: qm:%d %s,%zx - slot_use->%d (hdr %p)", state->id,
-					service->localport, msg_type_str(VCHIQ_MSG_TYPE(msgid)),
-					size, slot_use_count, header);
+			dev_dbg(state->dev, "core: %d: qm:%d %s,%zx - slot_use->%d (hdr %p)\n",
+				state->id, service->localport, msg_type_str(VCHIQ_MSG_TYPE(msgid)),
+				size, slot_use_count, header);
 
 		VCHIQ_SERVICE_STATS_INC(service, ctrl_tx_count);
 		VCHIQ_SERVICE_STATS_ADD(service, ctrl_tx_bytes, size);
 	} else {
-		vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: qm %s@%pK,%zx (%d->%d)", state->id,
-				msg_type_str(VCHIQ_MSG_TYPE(msgid)), header, size,
-				VCHIQ_MSG_SRCPORT(msgid), VCHIQ_MSG_DSTPORT(msgid));
+		dev_dbg(state->dev, "core: %d: qm %s@%pK,%zx (%d->%d)\n",
+			state->id, msg_type_str(VCHIQ_MSG_TYPE(msgid)), header, size,
+			VCHIQ_MSG_SRCPORT(msgid), VCHIQ_MSG_DSTPORT(msgid));
 		if (size != 0) {
 			/*
 			 * It is assumed for now that this code path
@@ -1111,11 +1106,9 @@ queue_message(struct vchiq_state *state, struct vchiq_service *service,
 			? service->base.fourcc
 			: VCHIQ_MAKE_FOURCC('?', '?', '?', '?');
 
-		vchiq_log_debug(state->dev, VCHIQ_CORE_MSG,
-				"Sent Msg %s(%u) to %p4cc s:%u d:%d len:%zu",
-				msg_type_str(VCHIQ_MSG_TYPE(msgid)), VCHIQ_MSG_TYPE(msgid),
-				&svc_fourcc, VCHIQ_MSG_SRCPORT(msgid),
-				VCHIQ_MSG_DSTPORT(msgid), size);
+		dev_dbg(state->dev, "core_msg: Sent Msg %s(%u) to %p4cc s:%u d:%d len:%zu\n",
+			msg_type_str(VCHIQ_MSG_TYPE(msgid)), VCHIQ_MSG_TYPE(msgid),
+			&svc_fourcc, VCHIQ_MSG_SRCPORT(msgid), VCHIQ_MSG_DSTPORT(msgid), size);
 	}
 
 	/* Make sure the new header is visible to the peer. */
@@ -1167,15 +1160,13 @@ queue_message_sync(struct vchiq_state *state, struct vchiq_service *service,
 		int oldmsgid = header->msgid;
 
 		if (oldmsgid != VCHIQ_MSGID_PADDING)
-			vchiq_log_error(state->dev, VCHIQ_CORE, "%d: qms - msgid %x, not PADDING",
-					state->id, oldmsgid);
+			dev_err(state->dev, "core: %d: qms - msgid %x, not PADDING\n",
+				state->id, oldmsgid);
 	}
 
-	vchiq_log_debug(state->dev, VCHIQ_SYNC,
-			"%d: qms %s@%pK,%x (%d->%d)", state->id,
-			msg_type_str(VCHIQ_MSG_TYPE(msgid)),
-			header, size, VCHIQ_MSG_SRCPORT(msgid),
-			VCHIQ_MSG_DSTPORT(msgid));
+	dev_dbg(state->dev, "sync: %d: qms %s@%pK,%x (%d->%d)\n",
+		state->id, msg_type_str(VCHIQ_MSG_TYPE(msgid)), header, size,
+		VCHIQ_MSG_SRCPORT(msgid), VCHIQ_MSG_DSTPORT(msgid));
 
 	callback_result =
 		copy_message_data(copy_callback, context,
@@ -1205,11 +1196,11 @@ queue_message_sync(struct vchiq_state *state, struct vchiq_service *service,
 	svc_fourcc = service ? service->base.fourcc
 			     : VCHIQ_MAKE_FOURCC('?', '?', '?', '?');
 
-	vchiq_log_trace(state->dev, VCHIQ_SYNC,
-			"Sent Sync Msg %s(%u) to %p4cc s:%u d:%d len:%d",
-			msg_type_str(VCHIQ_MSG_TYPE(msgid)), VCHIQ_MSG_TYPE(msgid),
-			&svc_fourcc, VCHIQ_MSG_SRCPORT(msgid),
-			VCHIQ_MSG_DSTPORT(msgid), size);
+	dev_dbg(state->dev,
+		"sync: Sent Sync Msg %s(%u) to %p4cc s:%u d:%d len:%d\n",
+		msg_type_str(VCHIQ_MSG_TYPE(msgid)), VCHIQ_MSG_TYPE(msgid),
+		&svc_fourcc, VCHIQ_MSG_SRCPORT(msgid),
+		VCHIQ_MSG_DSTPORT(msgid), size);
 
 	remote_event_signal(&state->remote->sync_trigger);
 
@@ -1261,9 +1252,9 @@ release_slot(struct vchiq_state *state, struct vchiq_slot_info *slot_info,
 			VCHIQ_SLOT_QUEUE_MASK] =
 			SLOT_INDEX_FROM_INFO(state, slot_info);
 		state->remote->slot_queue_recycle = slot_queue_recycle + 1;
-		vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: %s %d - recycle->%x",
-				state->id, __func__, SLOT_INDEX_FROM_INFO(state, slot_info),
-				state->remote->slot_queue_recycle);
+		dev_dbg(state->dev, "core: %d: %d - recycle->%x\n",
+			state->id, SLOT_INDEX_FROM_INFO(state, slot_info),
+			state->remote->slot_queue_recycle);
 
 		/*
 		 * A write barrier is necessary, but remote_event_signal
@@ -1298,11 +1289,11 @@ notify_bulks(struct vchiq_service *service, struct vchiq_bulk_queue *queue,
 {
 	int status = 0;
 
-	vchiq_log_trace(service->state->dev, VCHIQ_CORE,
-			"%d: nb:%d %cx - p=%x rn=%x r=%x",
-			service->state->id, service->localport,
-			(queue == &service->bulk_tx) ? 't' : 'r',
-			queue->process, queue->remote_notify, queue->remove);
+	dev_dbg(service->state->dev,
+		"core: %d: nb:%d %cx - p=%x rn=%x r=%x\n",
+		service->state->id, service->localport,
+		(queue == &service->bulk_tx) ? 't' : 'r',
+		queue->process, queue->remote_notify, queue->remove);
 
 	queue->remote_notify = queue->process;
 
@@ -1382,8 +1373,8 @@ poll_services_of_group(struct vchiq_state *state, int group)
 
 		service_flags = atomic_xchg(&service->poll_flags, 0);
 		if (service_flags & BIT(VCHIQ_POLL_REMOVE)) {
-			vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: ps - remove %d<->%d",
-					state->id, service->localport, service->remoteport);
+			dev_dbg(state->dev, "core: %d: ps - remove %d<->%d\n",
+				state->id, service->localport, service->remoteport);
 
 			/*
 			 * Make it look like a client, because
@@ -1395,8 +1386,8 @@ poll_services_of_group(struct vchiq_state *state, int group)
 			if (vchiq_close_service_internal(service, NO_CLOSE_RECVD))
 				request_poll(state, service, VCHIQ_POLL_REMOVE);
 		} else if (service_flags & BIT(VCHIQ_POLL_TERMINATE)) {
-			vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: ps - terminate %d<->%d",
-					state->id, service->localport, service->remoteport);
+			dev_dbg(state->dev, "core: %d: ps - terminate %d<->%d\n",
+				state->id, service->localport, service->remoteport);
 			if (vchiq_close_service_internal(service, NO_CLOSE_RECVD))
 				request_poll(state, service, VCHIQ_POLL_TERMINATE);
 		}
@@ -1425,11 +1416,11 @@ abort_outstanding_bulks(struct vchiq_service *service,
 {
 	int is_tx = (queue == &service->bulk_tx);
 
-	vchiq_log_trace(service->state->dev, VCHIQ_CORE,
-			"%d: aob:%d %cx - li=%x ri=%x p=%x",
-			service->state->id, service->localport,
-			is_tx ? 't' : 'r', queue->local_insert,
-			queue->remote_insert, queue->process);
+	dev_dbg(service->state->dev,
+		"core: %d: aob:%d %cx - li=%x ri=%x p=%x\n",
+		service->state->id, service->localport,
+		is_tx ? 't' : 'r', queue->local_insert,
+		queue->remote_insert, queue->process);
 
 	WARN_ON((int)(queue->local_insert - queue->process) < 0);
 	WARN_ON((int)(queue->remote_insert - queue->process) < 0);
@@ -1448,11 +1439,11 @@ abort_outstanding_bulks(struct vchiq_service *service,
 		if (queue->process != queue->local_insert) {
 			vchiq_complete_bulk(service->instance, bulk);
 
-			vchiq_log_debug(service->state->dev, VCHIQ_CORE_MSG,
-					"%s %p4cc d:%d ABORTED - tx len:%d, rx len:%d",
-					is_tx ? "Send Bulk to" : "Recv Bulk from",
-					&service->base.fourcc,
-					service->remoteport, bulk->size, bulk->remote_size);
+			dev_dbg(service->state->dev,
+				"core_msg: %s %p4cc d:%d ABORTED - tx len:%d, rx len:%d\n",
+				is_tx ? "Send Bulk to" : "Recv Bulk from",
+				&service->base.fourcc,
+				service->remoteport, bulk->size, bulk->remote_size);
 		} else {
 			/* fabricate a matching dummy bulk */
 			bulk->data = 0;
@@ -1485,8 +1476,8 @@ parse_open(struct vchiq_state *state, struct vchiq_header *header)
 
 	payload = (struct vchiq_open_payload *)header->data;
 	fourcc = payload->fourcc;
-	vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: prs OPEN@%pK (%d->'%p4cc')",
-			state->id, header, localport, &fourcc);
+	dev_dbg(state->dev, "core: %d: prs OPEN@%pK (%d->'%p4cc')\n",
+		state->id, header, localport, &fourcc);
 
 	service = get_listening_service(state, fourcc);
 	if (!service)
@@ -1609,17 +1600,17 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 				vchiq_service_put(service);
 			service = get_connected_service(state, remoteport);
 			if (service)
-				vchiq_log_warning(state->dev, VCHIQ_CORE,
-						  "%d: prs %s@%pK (%d->%d) - found connected service %d",
-						  state->id, msg_type_str(type), header,
-						  remoteport, localport, service->localport);
+				dev_warn(state->dev,
+					 "core: %d: prs %s@%pK (%d->%d) - found connected service %d\n",
+					 state->id, msg_type_str(type), header,
+					 remoteport, localport, service->localport);
 		}
 
 		if (!service) {
-			vchiq_log_error(state->dev, VCHIQ_CORE,
-					"%d: prs %s@%pK (%d->%d) - invalid/closed service %d",
-					state->id, msg_type_str(type), header, remoteport,
-					localport, localport);
+			dev_err(state->dev,
+				"core: %d: prs %s@%pK (%d->%d) - invalid/closed service %d\n",
+				state->id, msg_type_str(type), header, remoteport,
+				localport, localport);
 			goto skip_message;
 		}
 		break;
@@ -1631,18 +1622,15 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 	svc_fourcc = service ? service->base.fourcc
 			     : VCHIQ_MAKE_FOURCC('?', '?', '?', '?');
 
-	vchiq_log_debug(state->dev, VCHIQ_CORE_MSG,
-			"Rcvd Msg %s(%u) from %p4cc s:%d d:%d len:%d",
-			msg_type_str(type), type, &svc_fourcc,
-			remoteport, localport, size);
+	dev_dbg(state->dev, "core_msg: Rcvd Msg %s(%u) from %p4cc s:%d d:%d len:%d\n",
+		msg_type_str(type), type, &svc_fourcc, remoteport, localport, size);
 	if (size > 0)
 		vchiq_log_dump_mem(state->dev, "Rcvd", 0, header->data, min(16, size));
 
 	if (((unsigned long)header & VCHIQ_SLOT_MASK) +
 	    calc_stride(size) > VCHIQ_SLOT_SIZE) {
-		vchiq_log_error(state->dev, VCHIQ_CORE,
-				"header %pK (msgid %x) - size %x too big for slot",
-				header, (unsigned int)msgid, (unsigned int)size);
+		dev_err(state->dev, "core: header %pK (msgid %x) - size %x too big for slot\n",
+			header, (unsigned int)msgid, (unsigned int)size);
 		WARN(1, "oversized for slot\n");
 	}
 
@@ -1659,37 +1647,36 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 				header->data;
 			service->peer_version = payload->version;
 		}
-		vchiq_log_debug(state->dev, VCHIQ_CORE,
-				"%d: prs OPENACK@%pK,%x (%d->%d) v:%d",
-				state->id, header, size, remoteport, localport,
-				service->peer_version);
+		dev_dbg(state->dev,
+			"core: %d: prs OPENACK@%pK,%x (%d->%d) v:%d\n",
+			state->id, header, size, remoteport, localport,
+			service->peer_version);
 		if (service->srvstate == VCHIQ_SRVSTATE_OPENING) {
 			service->remoteport = remoteport;
 			set_service_state(service, VCHIQ_SRVSTATE_OPEN);
 			complete(&service->remove_event);
 		} else {
-			vchiq_log_error(state->dev, VCHIQ_CORE, "OPENACK received in state %s",
-					srvstate_names[service->srvstate]);
+			dev_err(state->dev, "core: OPENACK received in state %s\n",
+				srvstate_names[service->srvstate]);
 		}
 		break;
 	case VCHIQ_MSG_CLOSE:
 		WARN_ON(size); /* There should be no data */
 
-		vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: prs CLOSE@%pK (%d->%d)",
-				state->id, header, remoteport, localport);
+		dev_dbg(state->dev, "core: %d: prs CLOSE@%pK (%d->%d)\n",
+			state->id, header, remoteport, localport);
 
 		mark_service_closing_internal(service, 1);
 
 		if (vchiq_close_service_internal(service, CLOSE_RECVD) == -EAGAIN)
 			goto bail_not_ready;
 
-		vchiq_log_debug(state->dev, VCHIQ_CORE, "Close Service %p4cc s:%u d:%d",
-				&service->base.fourcc,
-				service->localport, service->remoteport);
+		dev_dbg(state->dev, "core: Close Service %p4cc s:%u d:%d\n",
+			&service->base.fourcc, service->localport, service->remoteport);
 		break;
 	case VCHIQ_MSG_DATA:
-		vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: prs DATA@%pK,%x (%d->%d)",
-				state->id, header, size, remoteport, localport);
+		dev_dbg(state->dev, "core: %d: prs DATA@%pK,%x (%d->%d)\n",
+			state->id, header, size, remoteport, localport);
 
 		if ((service->remoteport == remoteport) &&
 		    (service->srvstate == VCHIQ_SRVSTATE_OPEN)) {
@@ -1708,8 +1695,8 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 		}
 		break;
 	case VCHIQ_MSG_CONNECT:
-		vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: prs CONNECT@%pK",
-				state->id, header);
+		dev_dbg(state->dev, "core: %d: prs CONNECT@%pK\n",
+			state->id, header);
 		state->version_common =	((struct vchiq_slot_zero *)
 					 state->slot_data)->version;
 		complete(&state->connect);
@@ -1740,11 +1727,10 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 			}
 			if ((int)(queue->remote_insert -
 				queue->local_insert) >= 0) {
-				vchiq_log_error(state->dev, VCHIQ_CORE,
-						"%d: prs %s@%pK (%d->%d) unexpected (ri=%d,li=%d)",
-						state->id, msg_type_str(type), header, remoteport,
-						localport, queue->remote_insert,
-						queue->local_insert);
+				dev_err(state->dev,
+					"core: %d: prs %s@%pK (%d->%d) unexpected (ri=%d,li=%d)\n",
+					state->id, msg_type_str(type), header, remoteport,
+					localport, queue->remote_insert, queue->local_insert);
 				mutex_unlock(&service->bulk_mutex);
 				break;
 			}
@@ -1761,15 +1747,14 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 			bulk->actual = *(int *)header->data;
 			queue->remote_insert++;
 
-			vchiq_log_debug(state->dev, VCHIQ_CORE,
-					"%d: prs %s@%pK (%d->%d) %x@%pad",
-					state->id, msg_type_str(type), header, remoteport,
-					localport, bulk->actual, &bulk->data);
+			dev_dbg(state->dev, "core: %d: prs %s@%pK (%d->%d) %x@%pad\n",
+				state->id, msg_type_str(type), header, remoteport,
+				localport, bulk->actual, &bulk->data);
 
-			vchiq_log_trace(state->dev, VCHIQ_CORE, "%d: prs:%d %cx li=%x ri=%x p=%x",
-					state->id, localport,
-					(type == VCHIQ_MSG_BULK_RX_DONE) ? 'r' : 't',
-					queue->local_insert, queue->remote_insert, queue->process);
+			dev_dbg(state->dev, "core: %d: prs:%d %cx li=%x ri=%x p=%x\n",
+				state->id, localport,
+				(type == VCHIQ_MSG_BULK_RX_DONE) ? 'r' : 't',
+				queue->local_insert, queue->remote_insert, queue->process);
 
 			DEBUG_TRACE(PARSE_LINE);
 			WARN_ON(queue->process == queue->local_insert);
@@ -1782,16 +1767,16 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 		}
 		break;
 	case VCHIQ_MSG_PADDING:
-		vchiq_log_trace(state->dev, VCHIQ_CORE, "%d: prs PADDING@%pK,%x",
-				state->id, header, size);
+		dev_dbg(state->dev, "core: %d: prs PADDING@%pK,%x\n",
+			state->id, header, size);
 		break;
 	case VCHIQ_MSG_PAUSE:
 		/* If initiated, signal the application thread */
-		vchiq_log_trace(state->dev, VCHIQ_CORE, "%d: prs PAUSE@%pK,%x",
-				state->id, header, size);
+		dev_dbg(state->dev, "core: %d: prs PAUSE@%pK,%x\n",
+			state->id, header, size);
 		if (state->conn_state == VCHIQ_CONNSTATE_PAUSED) {
-			vchiq_log_error(state->dev, VCHIQ_CORE,
-					"%d: PAUSE received in state PAUSED", state->id);
+			dev_err(state->dev, "core: %d: PAUSE received in state PAUSED\n",
+				state->id);
 			break;
 		}
 		if (state->conn_state != VCHIQ_CONNSTATE_PAUSE_SENT) {
@@ -1804,8 +1789,8 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 		vchiq_set_conn_state(state, VCHIQ_CONNSTATE_PAUSED);
 		break;
 	case VCHIQ_MSG_RESUME:
-		vchiq_log_trace(state->dev, VCHIQ_CORE, "%d: prs RESUME@%pK,%x",
-				state->id, header, size);
+		dev_dbg(state->dev, "core: %d: prs RESUME@%pK,%x\n",
+			state->id, header, size);
 		/* Release the slot mutex */
 		mutex_unlock(&state->slot_mutex);
 		vchiq_set_conn_state(state, VCHIQ_CONNSTATE_CONNECTED);
@@ -1821,8 +1806,8 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 		break;
 
 	default:
-		vchiq_log_error(state->dev, VCHIQ_CORE, "%d: prs invalid msgid %x@%pK,%x",
-				state->id, msgid, header, size);
+		dev_err(state->dev, "core: %d: prs invalid msgid %x@%pK,%x\n",
+			state->id, msgid, header, size);
 		WARN(1, "invalid message\n");
 		break;
 	}
@@ -1932,7 +1917,7 @@ handle_poll(struct vchiq_state *state)
 			 * since the PAUSE should have flushed
 			 * through outstanding messages.
 			 */
-			vchiq_log_error(state->dev, VCHIQ_CORE, "Failed to send RESUME message");
+			dev_err(state->dev, "core: Failed to send RESUME message\n");
 		}
 		break;
 	default:
@@ -2032,21 +2017,18 @@ sync_func(void *v)
 		service = find_service_by_port(state, localport);
 
 		if (!service) {
-			vchiq_log_error(state->dev, VCHIQ_SYNC,
-					"%d: sf %s@%pK (%d->%d) - invalid/closed service %d",
-					state->id, msg_type_str(type), header,
-					remoteport, localport, localport);
+			dev_err(state->dev,
+				"sync: %d: sf %s@%pK (%d->%d) - invalid/closed service %d\n",
+				state->id, msg_type_str(type), header, remoteport,
+				localport, localport);
 			release_message_sync(state, header);
 			continue;
 		}
 
-		svc_fourcc = service ? service->base.fourcc
-				     : VCHIQ_MAKE_FOURCC('?', '?', '?', '?');
+		svc_fourcc = service->base.fourcc;
 
-		vchiq_log_trace(state->dev, VCHIQ_SYNC,
-				"Rcvd Msg %s from %p4cc s:%d d:%d len:%d",
-				msg_type_str(type), &svc_fourcc,
-				remoteport, localport, size);
+		dev_dbg(state->dev, "sync: Rcvd Msg %s from %p4cc s:%d d:%d len:%d\n",
+			msg_type_str(type), &svc_fourcc, remoteport, localport, size);
 		if (size > 0)
 			vchiq_log_dump_mem(state->dev, "Rcvd", 0, header->data, min(16, size));
 
@@ -2058,9 +2040,9 @@ sync_func(void *v)
 					header->data;
 				service->peer_version = payload->version;
 			}
-			vchiq_log_debug(state->dev, VCHIQ_SYNC, "%d: sf OPENACK@%pK,%x (%d->%d) v:%d",
-					state->id, header, size, remoteport, localport,
-					service->peer_version);
+			dev_err(state->dev, "sync: %d: sf OPENACK@%pK,%x (%d->%d) v:%d\n",
+				state->id, header, size, remoteport, localport,
+				service->peer_version);
 			if (service->srvstate == VCHIQ_SRVSTATE_OPENING) {
 				service->remoteport = remoteport;
 				set_service_state(service, VCHIQ_SRVSTATE_OPENSYNC);
@@ -2071,22 +2053,22 @@ sync_func(void *v)
 			break;
 
 		case VCHIQ_MSG_DATA:
-			vchiq_log_trace(state->dev, VCHIQ_SYNC, "%d: sf DATA@%pK,%x (%d->%d)",
-					state->id, header, size, remoteport, localport);
+			dev_dbg(state->dev, "sync: %d: sf DATA@%pK,%x (%d->%d)\n",
+				state->id, header, size, remoteport, localport);
 
 			if ((service->remoteport == remoteport) &&
 			    (service->srvstate == VCHIQ_SRVSTATE_OPENSYNC)) {
 				if (make_service_callback(service, VCHIQ_MESSAGE_AVAILABLE, header,
 							  NULL) == -EAGAIN)
-					vchiq_log_error(state->dev, VCHIQ_SYNC,
-							"synchronous callback to service %d returns -EAGAIN",
-							localport);
+					dev_err(state->dev,
+						"sync: error: synchronous callback to service %d returns -EAGAIN\n",
+						localport);
 			}
 			break;
 
 		default:
-			vchiq_log_error(state->dev, VCHIQ_SYNC, "%d: sf unexpected msgid %x@%pK,%x",
-					state->id, msgid, header, size);
+			dev_err(state->dev, "sync: error: %d: sf unexpected msgid %x@%pK,%x\n",
+				state->id, msgid, header, size);
 			release_message_sync(state, header);
 			break;
 		}
@@ -2119,8 +2101,8 @@ vchiq_init_slots(struct device *dev, void *mem_base, int mem_size)
 	num_slots -= first_data_slot;
 
 	if (num_slots < 4) {
-		vchiq_log_error(dev, VCHIQ_CORE, "%s - insufficient memory %x bytes",
-				__func__, mem_size);
+		dev_err(dev, "core: %s: Insufficient memory %x bytes\n",
+			__func__, mem_size);
 		return NULL;
 	}
 
@@ -2462,9 +2444,9 @@ vchiq_add_service_internal(struct vchiq_state *state,
 	/* Bring this service online */
 	set_service_state(service, srvstate);
 
-	vchiq_log_debug(state->dev, VCHIQ_CORE_MSG, "%s Service %p4cc SrcPort:%d",
-			(srvstate == VCHIQ_SRVSTATE_OPENING) ? "Open" : "Add",
-			&params->fourcc, service->localport);
+	dev_dbg(state->dev, "core_msg: %s Service %p4cc SrcPort:%d\n",
+		(srvstate == VCHIQ_SRVSTATE_OPENING) ? "Open" : "Add",
+		&params->fourcc, service->localport);
 
 	/* Don't unlock the service - leave it with a ref_count of 1. */
 
@@ -2501,11 +2483,10 @@ vchiq_open_service_internal(struct vchiq_service *service, int client_id)
 	} else if ((service->srvstate != VCHIQ_SRVSTATE_OPEN) &&
 		   (service->srvstate != VCHIQ_SRVSTATE_OPENSYNC)) {
 		if (service->srvstate != VCHIQ_SRVSTATE_CLOSEWAIT)
-			vchiq_log_error(service->state->dev, VCHIQ_CORE,
-					"%d: osi - srvstate = %s (ref %u)",
-					service->state->id,
-					srvstate_names[service->srvstate],
-					kref_read(&service->ref_count));
+			dev_err(service->state->dev,
+				"core: %d: osi - srvstate = %s (ref %u)\n",
+				service->state->id, srvstate_names[service->srvstate],
+				kref_read(&service->ref_count));
 		status = -EINVAL;
 		VCHIQ_SERVICE_STATS_INC(service, error_count);
 		vchiq_release_service_internal(service);
@@ -2560,15 +2541,14 @@ release_service_messages(struct vchiq_service *service)
 			int port = VCHIQ_MSG_DSTPORT(msgid);
 
 			if ((port == service->localport) && (msgid & VCHIQ_MSGID_CLAIMED)) {
-				vchiq_log_debug(state->dev, VCHIQ_CORE,
-						"  fsi - hdr %pK", header);
+				dev_dbg(state->dev, "core:  fsi - hdr %pK\n", header);
 				release_slot(state, slot_info, header, NULL);
 			}
 			pos += calc_stride(header->size);
 			if (pos > VCHIQ_SLOT_SIZE) {
-				vchiq_log_error(state->dev, VCHIQ_CORE,
-						"fsi - pos %x: header %pK, msgid %x, header->msgid %x, header->size %x",
-						pos, header, msgid, header->msgid, header->size);
+				dev_err(state->dev,
+					"core: fsi - pos %x: header %pK, msgid %x, header->msgid %x, header->size %x\n",
+					pos, header, msgid, header->msgid, header->size);
 				WARN(1, "invalid slot position\n");
 			}
 		}
@@ -2622,8 +2602,8 @@ close_service_complete(struct vchiq_service *service, int failstate)
 	case VCHIQ_SRVSTATE_LISTENING:
 		break;
 	default:
-		vchiq_log_error(service->state->dev, VCHIQ_CORE, "%s(%x) called in state %s",
-				__func__, service->handle, srvstate_names[service->srvstate]);
+		dev_err(service->state->dev, "core: (%x) called in state %s\n",
+			service->handle, srvstate_names[service->srvstate]);
 		WARN(1, "%s in unexpected state\n", __func__);
 		return -EINVAL;
 	}
@@ -2669,8 +2649,9 @@ vchiq_close_service_internal(struct vchiq_service *service, int close_recvd)
 	int close_id = MAKE_CLOSE(service->localport,
 				  VCHIQ_MSG_DSTPORT(service->remoteport));
 
-	vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: csi:%d,%d (%s)", service->state->id,
-			service->localport, close_recvd, srvstate_names[service->srvstate]);
+	dev_dbg(state->dev, "core: %d: csi:%d,%d (%s)\n",
+		service->state->id, service->localport, close_recvd,
+		srvstate_names[service->srvstate]);
 
 	switch (service->srvstate) {
 	case VCHIQ_SRVSTATE_CLOSED:
@@ -2678,8 +2659,8 @@ vchiq_close_service_internal(struct vchiq_service *service, int close_recvd)
 	case VCHIQ_SRVSTATE_LISTENING:
 	case VCHIQ_SRVSTATE_CLOSEWAIT:
 		if (close_recvd) {
-			vchiq_log_error(state->dev, VCHIQ_CORE, "%s(1) called in state %s",
-					__func__, srvstate_names[service->srvstate]);
+			dev_err(state->dev, "core: (1) called in state %s\n",
+				srvstate_names[service->srvstate]);
 		} else if (is_server) {
 			if (service->srvstate == VCHIQ_SRVSTATE_LISTENING) {
 				status = -EINVAL;
@@ -2766,8 +2747,8 @@ vchiq_close_service_internal(struct vchiq_service *service, int close_recvd)
 		break;
 
 	default:
-		vchiq_log_error(state->dev, VCHIQ_CORE, "%s(%d) called in state %s", __func__,
-				close_recvd, srvstate_names[service->srvstate]);
+		dev_err(state->dev, "core: (%d) called in state %s\n",
+			close_recvd, srvstate_names[service->srvstate]);
 		break;
 	}
 
@@ -2780,8 +2761,8 @@ vchiq_terminate_service_internal(struct vchiq_service *service)
 {
 	struct vchiq_state *state = service->state;
 
-	vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: tsi - (%d<->%d)", state->id,
-			service->localport, service->remoteport);
+	dev_dbg(state->dev, "core: %d: tsi - (%d<->%d)\n",
+		state->id, service->localport, service->remoteport);
 
 	mark_service_closing(service);
 
@@ -2795,8 +2776,7 @@ vchiq_free_service_internal(struct vchiq_service *service)
 {
 	struct vchiq_state *state = service->state;
 
-	vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: fsi - (%d)",
-			state->id, service->localport);
+	dev_dbg(state->dev, "core: %d: fsi - (%d)\n", state->id, service->localport);
 
 	switch (service->srvstate) {
 	case VCHIQ_SRVSTATE_OPENING:
@@ -2806,8 +2786,8 @@ vchiq_free_service_internal(struct vchiq_service *service)
 	case VCHIQ_SRVSTATE_CLOSEWAIT:
 		break;
 	default:
-		vchiq_log_error(state->dev, VCHIQ_CORE, "%d: fsi - (%d) in state %s", state->id,
-				service->localport, srvstate_names[service->srvstate]);
+		dev_err(state->dev, "core: %d: fsi - (%d) in state %s\n",
+			state->id, service->localport, srvstate_names[service->srvstate]);
 		return;
 	}
 
@@ -2876,8 +2856,8 @@ vchiq_close_service(struct vchiq_instance *instance, unsigned int handle)
 	if (!service)
 		return -EINVAL;
 
-	vchiq_log_debug(service->state->dev, VCHIQ_CORE, "%d: close_service:%d",
-			service->state->id, service->localport);
+	dev_dbg(service->state->dev, "core: %d: close_service:%d\n",
+		service->state->id, service->localport);
 
 	if ((service->srvstate == VCHIQ_SRVSTATE_FREE) ||
 	    (service->srvstate == VCHIQ_SRVSTATE_LISTENING) ||
@@ -2907,10 +2887,10 @@ vchiq_close_service(struct vchiq_instance *instance, unsigned int handle)
 		    (service->srvstate == VCHIQ_SRVSTATE_OPEN))
 			break;
 
-		vchiq_log_warning(service->state->dev, VCHIQ_CORE,
-				  "%d: close_service:%d - waiting in state %s",
-				  service->state->id, service->localport,
-				  srvstate_names[service->srvstate]);
+		dev_warn(service->state->dev,
+			 "core: %d: close_service:%d - waiting in state %s\n",
+			 service->state->id, service->localport,
+			 srvstate_names[service->srvstate]);
 	}
 
 	if (!status &&
@@ -2934,8 +2914,8 @@ vchiq_remove_service(struct vchiq_instance *instance, unsigned int handle)
 	if (!service)
 		return -EINVAL;
 
-	vchiq_log_debug(service->state->dev, VCHIQ_CORE, "%d: remove_service:%d",
-			service->state->id, service->localport);
+	dev_dbg(service->state->dev, "core: %d: remove_service:%d\n",
+		service->state->id, service->localport);
 
 	if (service->srvstate == VCHIQ_SRVSTATE_FREE) {
 		vchiq_service_put(service);
@@ -2968,10 +2948,10 @@ vchiq_remove_service(struct vchiq_instance *instance, unsigned int handle)
 		    (service->srvstate == VCHIQ_SRVSTATE_OPEN))
 			break;
 
-		vchiq_log_warning(service->state->dev, VCHIQ_CORE,
-				  "%d: remove_service:%d - waiting in state %s",
-				  service->state->id, service->localport,
-				  srvstate_names[service->srvstate]);
+		dev_warn(service->state->dev,
+			 "core: %d: remove_service:%d - waiting in state %s\n",
+			 service->state->id, service->localport,
+			 srvstate_names[service->srvstate]);
 	}
 
 	if (!status && (service->srvstate != VCHIQ_SRVSTATE_FREE))
@@ -3078,9 +3058,9 @@ int vchiq_bulk_transfer(struct vchiq_instance *instance, unsigned int handle,
 	 */
 	wmb();
 
-	vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: bt (%d->%d) %cx %x@%pad %pK",
-			state->id, service->localport, service->remoteport,
-			dir_char, size, &bulk->data, userdata);
+	dev_dbg(state->dev, "core: %d: bt (%d->%d) %cx %x@%pad %pK\n",
+		state->id, service->localport, service->remoteport,
+		dir_char, size, &bulk->data, userdata);
 
 	/*
 	 * The slot mutex must be held when the service is being closed, so
@@ -3115,9 +3095,9 @@ int vchiq_bulk_transfer(struct vchiq_instance *instance, unsigned int handle,
 	mutex_unlock(&state->slot_mutex);
 	mutex_unlock(&service->bulk_mutex);
 
-	vchiq_log_trace(state->dev, VCHIQ_CORE, "%d: bt:%d %cx li=%x ri=%x p=%x",
-			state->id, service->localport, dir_char, queue->local_insert,
-			queue->remote_insert, queue->process);
+	dev_dbg(state->dev, "core: %d: bt:%d %cx li=%x ri=%x p=%x\n",
+		state->id, service->localport, dir_char, queue->local_insert,
+		queue->remote_insert, queue->process);
 
 waiting:
 	vchiq_service_put(service);
@@ -3372,8 +3352,8 @@ vchiq_set_service_option(struct vchiq_instance *instance, unsigned int handle,
 	return ret;
 }
 
-static int
-vchiq_dump_shared_state(void *dump_context, struct vchiq_state *state,
+static void
+vchiq_dump_shared_state(struct seq_file *f, struct vchiq_state *state,
 			struct vchiq_shared_state *shared, const char *label)
 {
 	static const char *const debug_names[] = {
@@ -3390,146 +3370,44 @@ vchiq_dump_shared_state(void *dump_context, struct vchiq_state *state,
 		"COMPLETION_QUEUE_FULL_COUNT"
 	};
 	int i;
-	char buf[80];
-	int len;
-	int err;
-
-	len = scnprintf(buf, sizeof(buf), "  %s: slots %d-%d tx_pos=%x recycle=%x",
-			label, shared->slot_first, shared->slot_last,
-			shared->tx_pos, shared->slot_queue_recycle);
-	err = vchiq_dump(dump_context, buf, len + 1);
-	if (err)
-		return err;
-
-	len = scnprintf(buf, sizeof(buf), "    Slots claimed:");
-	err = vchiq_dump(dump_context, buf, len + 1);
-	if (err)
-		return err;
+
+	seq_printf(f, "  %s: slots %d-%d tx_pos=%x recycle=%x\n",
+		   label, shared->slot_first, shared->slot_last,
+		   shared->tx_pos, shared->slot_queue_recycle);
+
+	seq_puts(f, "    Slots claimed:\n");
 
 	for (i = shared->slot_first; i <= shared->slot_last; i++) {
 		struct vchiq_slot_info slot_info =
 						*SLOT_INFO_FROM_INDEX(state, i);
 		if (slot_info.use_count != slot_info.release_count) {
-			len = scnprintf(buf, sizeof(buf), "      %d: %d/%d", i, slot_info.use_count,
-					slot_info.release_count);
-			err = vchiq_dump(dump_context, buf, len + 1);
-			if (err)
-				return err;
+			seq_printf(f, "      %d: %d/%d\n", i, slot_info.use_count,
+				   slot_info.release_count);
 		}
 	}
 
 	for (i = 1; i < shared->debug[DEBUG_ENTRIES]; i++) {
-		len = scnprintf(buf, sizeof(buf), "    DEBUG: %s = %d(%x)",
-				debug_names[i], shared->debug[i], shared->debug[i]);
-		err = vchiq_dump(dump_context, buf, len + 1);
-		if (err)
-			return err;
-	}
-	return 0;
-}
-
-int vchiq_dump_state(void *dump_context, struct vchiq_state *state)
-{
-	char buf[80];
-	int len;
-	int i;
-	int err;
-
-	len = scnprintf(buf, sizeof(buf), "State %d: %s", state->id,
-			conn_state_names[state->conn_state]);
-	err = vchiq_dump(dump_context, buf, len + 1);
-	if (err)
-		return err;
-
-	len = scnprintf(buf, sizeof(buf), "  tx_pos=%x(@%pK), rx_pos=%x(@%pK)",
-			state->local->tx_pos,
-			state->tx_data + (state->local_tx_pos & VCHIQ_SLOT_MASK),
-			state->rx_pos,
-			state->rx_data + (state->rx_pos & VCHIQ_SLOT_MASK));
-	err = vchiq_dump(dump_context, buf, len + 1);
-	if (err)
-		return err;
-
-	len = scnprintf(buf, sizeof(buf), "  Version: %d (min %d)",
-			VCHIQ_VERSION, VCHIQ_VERSION_MIN);
-	err = vchiq_dump(dump_context, buf, len + 1);
-	if (err)
-		return err;
-
-	if (VCHIQ_ENABLE_STATS) {
-		len = scnprintf(buf, sizeof(buf),
-				"  Stats: ctrl_tx_count=%d, ctrl_rx_count=%d, error_count=%d",
-				state->stats.ctrl_tx_count, state->stats.ctrl_rx_count,
-				state->stats.error_count);
-		err = vchiq_dump(dump_context, buf, len + 1);
-		if (err)
-			return err;
-	}
-
-	len = scnprintf(buf, sizeof(buf),
-			"  Slots: %d available (%d data), %d recyclable, %d stalls (%d data)",
-			((state->slot_queue_available * VCHIQ_SLOT_SIZE) -
-			state->local_tx_pos) / VCHIQ_SLOT_SIZE,
-			state->data_quota - state->data_use_count,
-			state->local->slot_queue_recycle - state->slot_queue_available,
-			state->stats.slot_stalls, state->stats.data_stalls);
-	err = vchiq_dump(dump_context, buf, len + 1);
-	if (err)
-		return err;
-
-	err = vchiq_dump_platform_state(dump_context);
-	if (err)
-		return err;
-
-	err = vchiq_dump_shared_state(dump_context,
-				      state,
-				      state->local,
-				      "Local");
-	if (err)
-		return err;
-	err = vchiq_dump_shared_state(dump_context,
-				      state,
-				      state->remote,
-				      "Remote");
-	if (err)
-		return err;
-
-	err = vchiq_dump_platform_instances(dump_context);
-	if (err)
-		return err;
-
-	for (i = 0; i < state->unused_service; i++) {
-		struct vchiq_service *service = find_service_by_port(state, i);
-
-		if (service) {
-			err = vchiq_dump_service_state(dump_context, service);
-			vchiq_service_put(service);
-			if (err)
-				return err;
-		}
+		seq_printf(f, "    DEBUG: %s = %d(%x)\n",
+			   debug_names[i], shared->debug[i], shared->debug[i]);
 	}
-	return 0;
 }
 
-int vchiq_dump_service_state(void *dump_context, struct vchiq_service *service)
+static void
+vchiq_dump_service_state(struct seq_file *f, struct vchiq_service *service)
 {
-	char buf[80];
-	int len;
-	int err;
 	unsigned int ref_count;
 
 	/*Don't include the lock just taken*/
 	ref_count = kref_read(&service->ref_count) - 1;
-	len = scnprintf(buf, sizeof(buf), "Service %u: %s (ref %u)",
-			service->localport, srvstate_names[service->srvstate],
-			ref_count);
+	seq_printf(f, "Service %u: %s (ref %u)", service->localport,
+		   srvstate_names[service->srvstate], ref_count);
 
 	if (service->srvstate != VCHIQ_SRVSTATE_FREE) {
 		char remoteport[30];
 		struct vchiq_service_quota *quota =
 			&service->state->service_quotas[service->localport];
 		int fourcc = service->base.fourcc;
-		int tx_pending, rx_pending;
+		int tx_pending, rx_pending, tx_size = 0, rx_size = 0;
 
 		if (service->remoteport != VCHIQ_PORT_FREE) {
 			int len2 = scnprintf(remoteport, sizeof(remoteport),
@@ -3542,68 +3420,100 @@ int vchiq_dump_service_state(void *dump_context, struct vchiq_service *service)
 			strscpy(remoteport, "n/a", sizeof(remoteport));
 		}
 
-		len += scnprintf(buf + len, sizeof(buf) - len,
-				 " '%p4cc' remote %s (msg use %d/%d, slot use %d/%d)",
-				 &fourcc, remoteport,
-				 quota->message_use_count, quota->message_quota,
-				 quota->slot_use_count, quota->slot_quota);
-
-		err = vchiq_dump(dump_context, buf, len + 1);
-		if (err)
-			return err;
+		seq_printf(f, " '%p4cc' remote %s (msg use %d/%d, slot use %d/%d)\n",
+			   &fourcc, remoteport,
+			   quota->message_use_count, quota->message_quota,
+			   quota->slot_use_count, quota->slot_quota);
 
 		tx_pending = service->bulk_tx.local_insert -
 			service->bulk_tx.remote_insert;
+		if (tx_pending) {
+			unsigned int i = BULK_INDEX(service->bulk_tx.remove);
+
+			tx_size = service->bulk_tx.bulks[i].size;
+		}
 
 		rx_pending = service->bulk_rx.local_insert -
 			service->bulk_rx.remote_insert;
+		if (rx_pending) {
+			unsigned int i = BULK_INDEX(service->bulk_rx.remove);
 
-		len = scnprintf(buf, sizeof(buf),
-				"  Bulk: tx_pending=%d (size %d), rx_pending=%d (size %d)",
-				tx_pending,
-				tx_pending ?
-				service->bulk_tx.bulks[BULK_INDEX(service->bulk_tx.remove)].size :
-				0, rx_pending, rx_pending ?
-				service->bulk_rx.bulks[BULK_INDEX(service->bulk_rx.remove)].size :
-				0);
+			rx_size = service->bulk_rx.bulks[i].size;
+		}
+
+		seq_printf(f, "  Bulk: tx_pending=%d (size %d), rx_pending=%d (size %d)\n",
+			   tx_pending, tx_size, rx_pending, rx_size);
 
 		if (VCHIQ_ENABLE_STATS) {
-			err = vchiq_dump(dump_context, buf, len + 1);
-			if (err)
-				return err;
+			seq_printf(f, "  Ctrl: tx_count=%d, tx_bytes=%llu, rx_count=%d, rx_bytes=%llu\n",
+				   service->stats.ctrl_tx_count,
+				   service->stats.ctrl_tx_bytes,
+				   service->stats.ctrl_rx_count,
+				   service->stats.ctrl_rx_bytes);
+
+			seq_printf(f, "  Bulk: tx_count=%d, tx_bytes=%llu, rx_count=%d, rx_bytes=%llu\n",
+				   service->stats.bulk_tx_count,
+				   service->stats.bulk_tx_bytes,
+				   service->stats.bulk_rx_count,
+				   service->stats.bulk_rx_bytes);
+
+			seq_printf(f, "  %d quota stalls, %d slot stalls, %d bulk stalls, %d aborted, %d errors\n",
+				   service->stats.quota_stalls,
+				   service->stats.slot_stalls,
+				   service->stats.bulk_stalls,
+				   service->stats.bulk_aborted_count,
+				   service->stats.error_count);
+		}
+	}
 
-			len = scnprintf(buf, sizeof(buf),
-					"  Ctrl: tx_count=%d, tx_bytes=%llu, rx_count=%d, rx_bytes=%llu",
-					service->stats.ctrl_tx_count, service->stats.ctrl_tx_bytes,
-					service->stats.ctrl_rx_count, service->stats.ctrl_rx_bytes);
-			err = vchiq_dump(dump_context, buf, len + 1);
-			if (err)
-				return err;
+	vchiq_dump_platform_service_state(f, service);
+}
 
-			len = scnprintf(buf, sizeof(buf),
-					"  Bulk: tx_count=%d, tx_bytes=%llu, rx_count=%d, rx_bytes=%llu",
-					service->stats.bulk_tx_count, service->stats.bulk_tx_bytes,
-					service->stats.bulk_rx_count, service->stats.bulk_rx_bytes);
-			err = vchiq_dump(dump_context, buf, len + 1);
-			if (err)
-				return err;
+void vchiq_dump_state(struct seq_file *f, struct vchiq_state *state)
+{
+	int i;
 
-			len = scnprintf(buf, sizeof(buf),
-					"  %d quota stalls, %d slot stalls, %d bulk stalls, %d aborted, %d errors",
-					service->stats.quota_stalls, service->stats.slot_stalls,
-					service->stats.bulk_stalls,
-					service->stats.bulk_aborted_count,
-					service->stats.error_count);
-		}
+	seq_printf(f, "State %d: %s\n", state->id,
+		   conn_state_names[state->conn_state]);
+
+	seq_printf(f, "  tx_pos=%x(@%pK), rx_pos=%x(@%pK)\n",
+		   state->local->tx_pos,
+		   state->tx_data + (state->local_tx_pos & VCHIQ_SLOT_MASK),
+		   state->rx_pos,
+		   state->rx_data + (state->rx_pos & VCHIQ_SLOT_MASK));
+
+	seq_printf(f, "  Version: %d (min %d)\n", VCHIQ_VERSION,
+		   VCHIQ_VERSION_MIN);
+
+	if (VCHIQ_ENABLE_STATS) {
+		seq_printf(f, "  Stats: ctrl_tx_count=%d, ctrl_rx_count=%d, error_count=%d\n",
+			   state->stats.ctrl_tx_count, state->stats.ctrl_rx_count,
+			   state->stats.error_count);
 	}
 
-	err = vchiq_dump(dump_context, buf, len + 1);
-	if (err)
-		return err;
+	seq_printf(f, "  Slots: %d available (%d data), %d recyclable, %d stalls (%d data)\n",
+		   ((state->slot_queue_available * VCHIQ_SLOT_SIZE) -
+		   state->local_tx_pos) / VCHIQ_SLOT_SIZE,
+		   state->data_quota - state->data_use_count,
+		   state->local->slot_queue_recycle - state->slot_queue_available,
+		   state->stats.slot_stalls, state->stats.data_stalls);
+
+	vchiq_dump_platform_state(f);
+
+	vchiq_dump_shared_state(f, state, state->local, "Local");
+
+	vchiq_dump_shared_state(f, state, state->remote, "Remote");
+
+	vchiq_dump_platform_instances(f);
 
-	if (service->srvstate != VCHIQ_SRVSTATE_FREE)
-		err = vchiq_dump_platform_service_state(dump_context, service);
-	return err;
+	for (i = 0; i < state->unused_service; i++) {
+		struct vchiq_service *service = find_service_by_port(state, i);
+
+		if (service) {
+			vchiq_dump_service_state(f, service);
+			vchiq_service_put(service);
+		}
+	}
 }
 
 int vchiq_send_remote_use(struct vchiq_state *state)
@@ -3653,9 +3563,9 @@ void vchiq_log_dump_mem(struct device *dev, const char *label, u32 addr,
 		*s++ = '\0';
 
 		if (label && (*label != '\0'))
-			vchiq_log_trace(dev, VCHIQ_CORE, "%s: %08x: %s", label, addr, line_buf);
+			dev_dbg(dev, "core: %s: %08x: %s\n", label, addr, line_buf);
 		else
-			vchiq_log_trace(dev, VCHIQ_CORE, "%s: %08x: %s", label, addr, line_buf);
+			dev_dbg(dev, "core: %s: %08x: %s\n", label, addr, line_buf);
 
 		addr += 16;
 		mem += 16;
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
index 161358db457c..c8527551b58c 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
@@ -6,6 +6,7 @@
 
 #include <linux/mutex.h>
 #include <linux/completion.h>
+#include <linux/debugfs.h>
 #include <linux/dev_printk.h>
 #include <linux/kthread.h>
 #include <linux/kref.h>
@@ -31,44 +32,6 @@
 #define VCHIQ_SLOT_SIZE     4096
 #define VCHIQ_MAX_MSG_SIZE  (VCHIQ_SLOT_SIZE - sizeof(struct vchiq_header))
 
-enum vchiq_log_category {
-	VCHIQ_ARM,
-	VCHIQ_CORE,
-	VCHIQ_CORE_MSG,
-	VCHIQ_SYNC,
-	VCHIQ_SUSPEND,
-};
-
-static inline const char *log_category_str(enum vchiq_log_category c)
-{
-	static const char * const strings[] = {
-		"vchiq_arm",
-		"vchiq_core",
-		"vchiq_core_msg",
-		"vchiq_sync",
-		"vchiq_suspend",
-	};
-
-	return strings[c];
-};
-
-#ifndef vchiq_log_error
-#define vchiq_log_error(dev, cat, fmt, ...) \
-	do { dev_dbg(dev, "%s error: " fmt, log_category_str(cat), ##__VA_ARGS__); } while (0)
-#endif
-#ifndef vchiq_log_warning
-#define vchiq_log_warning(dev, cat, fmt, ...) \
-	do { dev_dbg(dev, "%s warning: " fmt, log_category_str(cat), ##__VA_ARGS__); } while (0)
-#endif
-#ifndef vchiq_log_debug
-#define vchiq_log_debug(dev, cat, fmt, ...) \
-	do { dev_dbg(dev, "%s debug: " fmt, log_category_str(cat), ##__VA_ARGS__); } while (0)
-#endif
-#ifndef vchiq_log_trace
-#define vchiq_log_trace(dev, cat, fmt, ...) \
-	do { dev_dbg(dev, "%s trace: " fmt, log_category_str(cat), ##__VA_ARGS__); } while (0)
-#endif
-
 #define VCHIQ_SLOT_MASK        (VCHIQ_SLOT_SIZE - 1)
 #define VCHIQ_SLOT_QUEUE_MASK  (VCHIQ_MAX_SLOTS_PER_SIDE - 1)
 #define VCHIQ_SLOT_ZERO_SLOTS  DIV_ROUND_UP(sizeof(struct vchiq_slot_zero), \
@@ -504,11 +467,8 @@ vchiq_bulk_transfer(struct vchiq_instance *instance, unsigned int handle, void *
 		    void __user *uoffset, int size, void *userdata, enum vchiq_bulk_mode mode,
 		    enum vchiq_bulk_dir dir);
 
-extern int
-vchiq_dump_state(void *dump_context, struct vchiq_state *state);
-
-extern int
-vchiq_dump_service_state(void *dump_context, struct vchiq_service *service);
+extern void
+vchiq_dump_state(struct seq_file *f, struct vchiq_state *state);
 
 extern void
 vchiq_loud_error_header(void);
@@ -564,13 +524,11 @@ void vchiq_complete_bulk(struct vchiq_instance *instance, struct vchiq_bulk *bul
 
 void remote_event_signal(struct remote_event *event);
 
-int vchiq_dump(void *dump_context, const char *str, int len);
-
-int vchiq_dump_platform_state(void *dump_context);
+void vchiq_dump_platform_state(struct seq_file *f);
 
-int vchiq_dump_platform_instances(void *dump_context);
+void vchiq_dump_platform_instances(struct seq_file *f);
 
-int vchiq_dump_platform_service_state(void *dump_context, struct vchiq_service *service);
+void vchiq_dump_platform_service_state(struct seq_file *f, struct vchiq_service *service);
 
 int vchiq_use_service_internal(struct vchiq_service *service);
 
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.c
index 58db78a9c8d4..d833e4e2973a 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.c
@@ -40,6 +40,13 @@ static int debugfs_trace_show(struct seq_file *f, void *offset)
 	return 0;
 }
 
+static int vchiq_dump_show(struct seq_file *f, void *offset)
+{
+	vchiq_dump_state(f, &g_state);
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(vchiq_dump);
+
 static int debugfs_trace_open(struct inode *inode, struct file *file)
 {
 	return single_open(file, debugfs_trace_show, inode->i_private);
@@ -115,6 +122,9 @@ void vchiq_debugfs_init(void)
 {
 	vchiq_dbg_dir = debugfs_create_dir("vchiq", NULL);
 	vchiq_dbg_clients = debugfs_create_dir("clients", vchiq_dbg_dir);
+
+	debugfs_create_file("state", S_IFREG | 0444, vchiq_dbg_dir, NULL,
+			    &vchiq_dump_fops);
 }
 
 /* remove all the debugfs entries */
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c
index 0bc93f48c14c..4d9deeeb637a 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c
@@ -47,9 +47,8 @@ user_service_free(void *userdata)
 
 static void close_delivered(struct user_service *user_service)
 {
-	vchiq_log_debug(user_service->service->state->dev, VCHIQ_ARM,
-			"%s(handle=%x)",
-			__func__, user_service->service->handle);
+	dev_dbg(user_service->service->state->dev,
+		"arm: (handle=%x)\n", user_service->service->handle);
 
 	if (user_service->close_pending) {
 		/* Allow the underlying service to be culled */
@@ -235,8 +234,7 @@ static int vchiq_ioc_dequeue_message(struct vchiq_instance *instance,
 			spin_unlock(&msg_queue_spinlock);
 			DEBUG_TRACE(DEQUEUE_MESSAGE_LINE);
 			if (wait_for_completion_interruptible(&user_service->insert_event)) {
-				vchiq_log_debug(service->state->dev, VCHIQ_ARM,
-						"DEQUEUE_MESSAGE interrupted");
+				dev_dbg(service->state->dev, "arm: DEQUEUE_MESSAGE interrupted\n");
 				ret = -EINTR;
 				break;
 			}
@@ -271,9 +269,9 @@ static int vchiq_ioc_dequeue_message(struct vchiq_instance *instance,
 			ret = -EFAULT;
 		}
 	} else {
-		vchiq_log_error(service->state->dev, VCHIQ_ARM,
-				"header %pK: bufsize %x < size %x",
-				header, args->bufsize, header->size);
+		dev_err(service->state->dev,
+			"arm: header %pK: bufsize %x < size %x\n",
+			header, args->bufsize, header->size);
 		WARN(1, "invalid size\n");
 		ret = -EMSGSIZE;
 	}
@@ -318,13 +316,13 @@ static int vchiq_irq_queue_bulk_tx_rx(struct vchiq_instance *instance,
 		}
 		mutex_unlock(&instance->bulk_waiter_list_mutex);
 		if (!waiter) {
-			vchiq_log_error(service->state->dev, VCHIQ_ARM,
-					"no bulk_waiter found for pid %d", current->pid);
+			dev_err(service->state->dev,
+				"arm: no bulk_waiter found for pid %d\n", current->pid);
 			ret = -ESRCH;
 			goto out;
 		}
-		vchiq_log_debug(service->state->dev, VCHIQ_ARM,
-				"found bulk_waiter %pK for pid %d", waiter, current->pid);
+		dev_dbg(service->state->dev, "arm: found bulk_waiter %pK for pid %d\n",
+			waiter, current->pid);
 		userdata = &waiter->bulk_waiter;
 	} else {
 		userdata = args->userdata;
@@ -355,8 +353,8 @@ static int vchiq_irq_queue_bulk_tx_rx(struct vchiq_instance *instance,
 		mutex_lock(&instance->bulk_waiter_list_mutex);
 		list_add(&waiter->list, &instance->bulk_waiter_list);
 		mutex_unlock(&instance->bulk_waiter_list_mutex);
-		vchiq_log_debug(service->state->dev, VCHIQ_ARM,
-				"saved bulk_waiter %pK for pid %d", waiter, current->pid);
+		dev_dbg(service->state->dev, "arm: saved bulk_waiter %pK for pid %d\n",
+			waiter, current->pid);
 
 		ret = put_user(mode_waiting, mode);
 	}
@@ -455,8 +453,7 @@ static int vchiq_ioc_await_completion(struct vchiq_instance *instance,
 		mutex_lock(&instance->completion_mutex);
 		if (rc) {
 			DEBUG_TRACE(AWAIT_COMPLETION_LINE);
-			vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
-					"AWAIT_COMPLETION interrupted");
+			dev_dbg(instance->state->dev, "arm: AWAIT_COMPLETION interrupted\n");
 			ret = -EINTR;
 			goto out;
 		}
@@ -501,10 +498,10 @@ static int vchiq_ioc_await_completion(struct vchiq_instance *instance,
 			msglen = header->size + sizeof(struct vchiq_header);
 			/* This must be a VCHIQ-style service */
 			if (args->msgbufsize < msglen) {
-				vchiq_log_error(service->state->dev, VCHIQ_ARM,
-						"header %pK: msgbufsize %x < msglen %x",
-						header, args->msgbufsize, msglen);
-						WARN(1, "invalid message size\n");
+				dev_err(service->state->dev,
+					"arm: header %pK: msgbufsize %x < msglen %x\n",
+					header, args->msgbufsize, msglen);
+				WARN(1, "invalid message size\n");
 				if (ret == 0)
 					ret = -EMSGSIZE;
 				break;
@@ -582,10 +579,9 @@ vchiq_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	long ret = 0;
 	int i, rc;
 
-	vchiq_log_trace(instance->state->dev, VCHIQ_ARM,
-			"%s - instance %pK, cmd %s, arg %lx", __func__, instance,
-			((_IOC_TYPE(cmd) == VCHIQ_IOC_MAGIC) && (_IOC_NR(cmd) <= VCHIQ_IOC_MAX)) ?
-			ioctl_names[_IOC_NR(cmd)] : "<invalid>", arg);
+	dev_dbg(instance->state->dev, "arm: instance %pK, cmd %s, arg %lx\n", instance,
+		((_IOC_TYPE(cmd) == VCHIQ_IOC_MAGIC) && (_IOC_NR(cmd) <= VCHIQ_IOC_MAX)) ?
+		ioctl_names[_IOC_NR(cmd)] : "<invalid>", arg);
 
 	switch (cmd) {
 	case VCHIQ_IOC_SHUTDOWN:
@@ -618,9 +614,9 @@ vchiq_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		}
 		rc = mutex_lock_killable(&instance->state->mutex);
 		if (rc) {
-			vchiq_log_error(instance->state->dev, VCHIQ_ARM,
-					"vchiq: connect: could not lock mutex for state %d: %d",
-					instance->state->id, rc);
+			dev_err(instance->state->dev,
+				"arm: vchiq: connect: could not lock mutex for state %d: %d\n",
+				instance->state->id, rc);
 			ret = -EINTR;
 			break;
 		}
@@ -630,8 +626,8 @@ vchiq_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		if (!status)
 			instance->connected = 1;
 		else
-			vchiq_log_error(instance->state->dev, VCHIQ_ARM,
-					"vchiq: could not connect: %d", status);
+			dev_err(instance->state->dev,
+				"arm: vchiq: could not connect: %d\n", status);
 		break;
 
 	case VCHIQ_IOC_CREATE_SERVICE: {
@@ -700,13 +696,13 @@ vchiq_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 				vchiq_use_service_internal(service) :
 				vchiq_release_service_internal(service);
 			if (ret) {
-				vchiq_log_error(instance->state->dev, VCHIQ_SUSPEND,
-						"%s: cmd %s returned error %ld for service %p4cc:%03d",
-						__func__, (cmd == VCHIQ_IOC_USE_SERVICE) ?
-						"VCHIQ_IOC_USE_SERVICE" :
-						"VCHIQ_IOC_RELEASE_SERVICE",
-						ret, &service->base.fourcc,
-						service->client_id);
+				dev_err(instance->state->dev,
+					"suspend: cmd %s returned error %ld for service %p4cc:%03d\n",
+					(cmd == VCHIQ_IOC_USE_SERVICE) ?
+					"VCHIQ_IOC_USE_SERVICE" :
+					"VCHIQ_IOC_RELEASE_SERVICE",
+					ret, &service->base.fourcc,
+					service->client_id);
 			}
 		} else {
 			ret = -EINVAL;
@@ -868,15 +864,15 @@ vchiq_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	}
 
 	if (!status && (ret < 0) && (ret != -EINTR) && (ret != -EWOULDBLOCK)) {
-		vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
-				"  ioctl instance %pK, cmd %s -> status %d, %ld",
-				instance, (_IOC_NR(cmd) <= VCHIQ_IOC_MAX) ?
-				ioctl_names[_IOC_NR(cmd)] : "<invalid>", status, ret);
+		dev_dbg(instance->state->dev,
+			"arm: ioctl instance %pK, cmd %s -> status %d, %ld\n",
+			instance, (_IOC_NR(cmd) <= VCHIQ_IOC_MAX) ?
+			ioctl_names[_IOC_NR(cmd)] : "<invalid>", status, ret);
 	} else {
-		vchiq_log_trace(instance->state->dev, VCHIQ_ARM,
-				"  ioctl instance %pK, cmd %s -> status %d, %ld",
-				instance, (_IOC_NR(cmd) <= VCHIQ_IOC_MAX) ?
-				ioctl_names[_IOC_NR(cmd)] : "<invalid>", status, ret);
+		dev_dbg(instance->state->dev,
+			"arm: ioctl instance %pK, cmd %s -> status %d\n, %ld\n",
+			instance, (_IOC_NR(cmd) <= VCHIQ_IOC_MAX) ?
+			ioctl_names[_IOC_NR(cmd)] : "<invalid>", status, ret);
 	}
 
 	return ret;
@@ -1170,11 +1166,10 @@ static int vchiq_open(struct inode *inode, struct file *file)
 	struct vchiq_state *state = vchiq_get_state();
 	struct vchiq_instance *instance;
 
-	vchiq_log_debug(state->dev, VCHIQ_ARM, "vchiq_open");
+	dev_dbg(state->dev, "arm: vchiq open\n");
 
 	if (!state) {
-		vchiq_log_error(state->dev, VCHIQ_ARM,
-				"vchiq has no connection to VideoCore");
+		dev_err(state->dev, "arm: vchiq has no connection to VideoCore\n");
 		return -ENOTCONN;
 	}
 
@@ -1206,8 +1201,7 @@ static int vchiq_release(struct inode *inode, struct file *file)
 	int ret = 0;
 	int i;
 
-	vchiq_log_debug(state->dev, VCHIQ_ARM, "%s: instance=%lx", __func__,
-			(unsigned long)instance);
+	dev_dbg(state->dev, "arm: instance=%p\n", instance);
 
 	if (!state) {
 		ret = -EPERM;
@@ -1306,26 +1300,6 @@ out:
 	return ret;
 }
 
-static ssize_t
-vchiq_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
-{
-	struct dump_context context;
-	int err;
-
-	context.buf = buf;
-	context.actual = 0;
-	context.space = count;
-	context.offset = *ppos;
-
-	err = vchiq_dump_state(&context, &g_state);
-	if (err)
-		return err;
-
-	*ppos += context.actual;
-
-	return context.actual;
-}
-
 static const struct file_operations
 vchiq_fops = {
 	.owner = THIS_MODULE,
@@ -1335,7 +1309,6 @@ vchiq_fops = {
 #endif
 	.open = vchiq_open,
 	.release = vchiq_release,
-	.read = vchiq_read
 };
 
 static struct miscdevice vchiq_miscdev = {
diff --git a/drivers/staging/vme_user/Kconfig b/drivers/staging/vme_user/Kconfig
index d65cc5510649..8e5df6ce36e8 100644
--- a/drivers/staging/vme_user/Kconfig
+++ b/drivers/staging/vme_user/Kconfig
@@ -3,18 +3,32 @@ menuconfig VME_BUS
 	bool "VME bridge support"
 	depends on PCI
 	help
-	  If you say Y here you get support for the VME bridge Framework.
+	  Enable support for VME (VersaModular Eurocard bus) bridge modules.
+	  The bridge allows connecting VME devices to systems with existing
+	  interfaces (like USB or PCI) by means of translating VME protocol
+	  operations.
+
+	  Note that this only enables the bridge framework. You'll also
+	  likely want to enable driver for specific bridge device you have
+	  to actually use it. If unsure, say N.
 
 if VME_BUS
 
 comment "VME Bridge Drivers"
 
 config VME_TSI148
-	tristate "Tempe"
+	tristate "Tundra TSI148 VME bridge support"
 	depends on HAS_DMA
 	help
-	 If you say Y here you get support for the Tundra TSI148 VME bridge
-	 chip.
+	 If you say Y here you get support for the Tundra TSI148 VME-to-PCI/X
+	 bridge chip (and pin-compatible clones).
+
+	 TSI148 is a high-performant, 2eSST and VME64-compliant VME-to-PCI/X
+	 interconnect bridge with support for PCI and PCI-X bus interface.
+	 It is primarily used in industrial and embedded systems.
+
+	 To compile this driver as a module, say M - the module will be
+	 called vme_tsi148. If unsure, say N.
 
 config VME_FAKE
 	tristate "Fake"
diff --git a/drivers/staging/vme_user/vme.c b/drivers/staging/vme_user/vme.c
index 5c416c31ec57..e9461a7a7ab8 100644
--- a/drivers/staging/vme_user/vme.c
+++ b/drivers/staging/vme_user/vme.c
@@ -340,8 +340,8 @@ int vme_slave_set(struct vme_resource *resource, int enabled,
 	image = list_entry(resource->entry, struct vme_slave_resource, list);
 
 	if (!bridge->slave_set) {
-		dev_err(bridge->parent, "Function not supported\n");
-		return -ENOSYS;
+		dev_err(bridge->parent, "%s not supported\n", __func__);
+		return -EINVAL;
 	}
 
 	if (!(((image->address_attr & aspace) == aspace) &&
diff --git a/drivers/staging/vt6655/card.c b/drivers/staging/vt6655/card.c
index 350ab8f3778a..36183f2a64c1 100644
--- a/drivers/staging/vt6655/card.c
+++ b/drivers/staging/vt6655/card.c
@@ -10,12 +10,12 @@
  *      CARDvUpdateBasicTopRate - Update BasicTopRate
  *      CARDbAddBasicRate - Add to BasicRateSet
  *      CARDbIsOFDMinBasicRate - Check if any OFDM rate is in BasicRateSet
- *      CARDqGetTSFOffset - Calculate TSFOffset
+ *      card_get_tsf_offset - Calculate TSFOffset
  *      vt6655_get_current_tsf - Read Current NIC TSF counter
- *      CARDqGetNextTBTT - Calculate Next Beacon TSF counter
+ *      card_get_next_tbtt - Calculate Next Beacon TSF counter
  *      CARDvSetFirstNextTBTT - Set NIC Beacon time
  *      CARDvUpdateNextTBTT - Sync. NIC Beacon time
- *      CARDbRadioPowerOff - Turn Off NIC Radio Power
+ *      card_radio_power_off - Turn Off NIC Radio Power
  *
  * Revision History:
  *      06-10-2003 Bryan YC Fan:  Re-write codes to support VT3253 spec.
@@ -280,7 +280,7 @@ bool card_set_phy_parameter(struct vnt_private *priv, u8 bb_type)
  *  In:
  *      priv            - The adapter to be sync.
  *      rx_rate         - data rate of receive beacon
- *      qwBSSTimestamp  - Rx BCN's TSF
+ *      bss_timestamp   - Rx BCN's TSF
  *      qwLocalTSF      - Local TSF
  *  Out:
  *      none
@@ -288,20 +288,20 @@ bool card_set_phy_parameter(struct vnt_private *priv, u8 bb_type)
  * Return Value: none
  */
 bool card_update_tsf(struct vnt_private *priv, unsigned char rx_rate,
-		    u64 qwBSSTimestamp)
+		    u64 bss_timestamp)
 {
 	u64 local_tsf;
-	u64 qwTSFOffset = 0;
+	u64 tsf_offset = 0;
 
 	local_tsf = vt6655_get_current_tsf(priv);
 
-	if (qwBSSTimestamp != local_tsf) {
-		qwTSFOffset = CARDqGetTSFOffset(rx_rate, qwBSSTimestamp,
+	if (bss_timestamp != local_tsf) {
+		tsf_offset = card_get_tsf_offset(rx_rate, bss_timestamp,
 						local_tsf);
 		/* adjust TSF, HW's TSF add TSF Offset reg */
-		qwTSFOffset =  le64_to_cpu(qwTSFOffset);
-		iowrite32((u32)qwTSFOffset, priv->port_offset + MAC_REG_TSFOFST);
-		iowrite32((u32)(qwTSFOffset >> 32), priv->port_offset + MAC_REG_TSFOFST + 4);
+		tsf_offset =  le64_to_cpu(tsf_offset);
+		iowrite32((u32)tsf_offset, priv->port_offset + MAC_REG_TSFOFST);
+		iowrite32((u32)(tsf_offset >> 32), priv->port_offset + MAC_REG_TSFOFST + 4);
 		vt6655_mac_reg_bits_on(priv->port_offset, MAC_REG_TFTCTL, TFTCTL_TSFSYNCEN);
 	}
 	return true;
@@ -314,28 +314,28 @@ bool card_update_tsf(struct vnt_private *priv, unsigned char rx_rate,
  * Parameters:
  *  In:
  *      priv         - The adapter to be set.
- *      wBeaconInterval - Beacon Interval
+ *      beacon_interval - Beacon Interval
  *  Out:
  *      none
  *
  * Return Value: true if succeed; otherwise false
  */
-bool CARDbSetBeaconPeriod(struct vnt_private *priv,
-			  unsigned short wBeaconInterval)
+bool card_set_beacon_period(struct vnt_private *priv,
+			  unsigned short beacon_interval)
 {
-	u64 qwNextTBTT;
+	u64 next_tbtt;
 
-	qwNextTBTT = vt6655_get_current_tsf(priv); /* Get Local TSF counter */
+	next_tbtt = vt6655_get_current_tsf(priv); /* Get Local TSF counter */
 
-	qwNextTBTT = CARDqGetNextTBTT(qwNextTBTT, wBeaconInterval);
+	next_tbtt = card_get_next_tbtt(next_tbtt, beacon_interval);
 
 	/* set HW beacon interval */
-	iowrite16(wBeaconInterval, priv->port_offset + MAC_REG_BI);
-	priv->wBeaconInterval = wBeaconInterval;
+	iowrite16(beacon_interval, priv->port_offset + MAC_REG_BI);
+	priv->beacon_interval = beacon_interval;
 	/* Set NextTBTT */
-	qwNextTBTT =  le64_to_cpu(qwNextTBTT);
-	iowrite32((u32)qwNextTBTT, priv->port_offset + MAC_REG_NEXTTBTT);
-	iowrite32((u32)(qwNextTBTT >> 32), priv->port_offset + MAC_REG_NEXTTBTT + 4);
+	next_tbtt =  le64_to_cpu(next_tbtt);
+	iowrite32((u32)next_tbtt, priv->port_offset + MAC_REG_NEXTTBTT);
+	iowrite32((u32)(next_tbtt >> 32), priv->port_offset + MAC_REG_NEXTTBTT + 4);
 	vt6655_mac_reg_bits_on(priv->port_offset, MAC_REG_TFTCTL, TFTCTL_TBTTSYNCEN);
 
 	return true;
@@ -351,7 +351,7 @@ bool CARDbSetBeaconPeriod(struct vnt_private *priv,
  *      none
  *
  */
-void CARDbRadioPowerOff(struct vnt_private *priv)
+void card_radio_power_off(struct vnt_private *priv)
 {
 	if (priv->radio_off)
 		return;
@@ -382,29 +382,29 @@ void CARDbRadioPowerOff(struct vnt_private *priv)
 	vt6655_mac_reg_bits_on(priv->port_offset, MAC_REG_GPIOCTL0, LED_ACTSET);  /* LED issue */
 }
 
-void CARDvSafeResetTx(struct vnt_private *priv)
+void card_safe_reset_tx(struct vnt_private *priv)
 {
 	unsigned int uu;
-	struct vnt_tx_desc *pCurrTD;
+	struct vnt_tx_desc *curr_td;
 
 	/* initialize TD index */
-	priv->apTailTD[0] = &priv->apTD0Rings[0];
+	priv->tail_td[0] = &priv->apTD0Rings[0];
 	priv->apCurrTD[0] = &priv->apTD0Rings[0];
 
-	priv->apTailTD[1] = &priv->apTD1Rings[0];
+	priv->tail_td[1] = &priv->apTD1Rings[0];
 	priv->apCurrTD[1] = &priv->apTD1Rings[0];
 
 	for (uu = 0; uu < TYPE_MAXTD; uu++)
 		priv->iTDUsed[uu] = 0;
 
 	for (uu = 0; uu < priv->opts.tx_descs[0]; uu++) {
-		pCurrTD = &priv->apTD0Rings[uu];
-		pCurrTD->td0.owner = OWNED_BY_HOST;
+		curr_td = &priv->apTD0Rings[uu];
+		curr_td->td0.owner = OWNED_BY_HOST;
 		/* init all Tx Packet pointer to NULL */
 	}
 	for (uu = 0; uu < priv->opts.tx_descs[1]; uu++) {
-		pCurrTD = &priv->apTD1Rings[uu];
-		pCurrTD->td0.owner = OWNED_BY_HOST;
+		curr_td = &priv->apTD1Rings[uu];
+		curr_td->td0.owner = OWNED_BY_HOST;
 		/* init all Tx Packet pointer to NULL */
 	}
 
@@ -708,7 +708,7 @@ unsigned char card_get_pkt_type(struct vnt_private *priv)
  *
  * Return Value: TSF Offset value
  */
-u64 CARDqGetTSFOffset(unsigned char rx_rate, u64 qwTSF1, u64 qwTSF2)
+u64 card_get_tsf_offset(unsigned char rx_rate, u64 qwTSF1, u64 qwTSF2)
 {
 	unsigned short wRxBcnTSFOffst;
 
@@ -764,11 +764,11 @@ u64 vt6655_get_current_tsf(struct vnt_private *priv)
  *
  * Return Value: TSF value of next Beacon
  */
-u64 CARDqGetNextTBTT(u64 qwTSF, unsigned short wBeaconInterval)
+u64 card_get_next_tbtt(u64 qwTSF, unsigned short beacon_interval)
 {
 	u32 beacon_int;
 
-	beacon_int = wBeaconInterval * 1024;
+	beacon_int = beacon_interval * 1024;
 	if (beacon_int) {
 		do_div(qwTSF, beacon_int);
 		qwTSF += 1;
@@ -785,25 +785,25 @@ u64 CARDqGetNextTBTT(u64 qwTSF, unsigned short wBeaconInterval)
  * Parameters:
  *  In:
  *      iobase          - IO Base
- *      wBeaconInterval - Beacon Interval
+ *      beacon_interval - Beacon Interval
  *  Out:
  *      none
  *
  * Return Value: none
  */
 void CARDvSetFirstNextTBTT(struct vnt_private *priv,
-			   unsigned short wBeaconInterval)
+			   unsigned short beacon_interval)
 {
 	void __iomem *iobase = priv->port_offset;
-	u64 qwNextTBTT;
+	u64 next_tbtt;
 
-	qwNextTBTT = vt6655_get_current_tsf(priv); /* Get Local TSF counter */
+	next_tbtt = vt6655_get_current_tsf(priv); /* Get Local TSF counter */
 
-	qwNextTBTT = CARDqGetNextTBTT(qwNextTBTT, wBeaconInterval);
+	next_tbtt = card_get_next_tbtt(next_tbtt, beacon_interval);
 	/* Set NextTBTT */
-	qwNextTBTT =  le64_to_cpu(qwNextTBTT);
-	iowrite32((u32)qwNextTBTT, iobase + MAC_REG_NEXTTBTT);
-	iowrite32((u32)(qwNextTBTT >> 32), iobase + MAC_REG_NEXTTBTT + 4);
+	next_tbtt =  le64_to_cpu(next_tbtt);
+	iowrite32((u32)next_tbtt, iobase + MAC_REG_NEXTTBTT);
+	iowrite32((u32)(next_tbtt >> 32), iobase + MAC_REG_NEXTTBTT + 4);
 	vt6655_mac_reg_bits_on(iobase, MAC_REG_TFTCTL, TFTCTL_TBTTSYNCEN);
 }
 
@@ -815,18 +815,18 @@ void CARDvSetFirstNextTBTT(struct vnt_private *priv,
  *  In:
  *      priv         - The adapter to be set
  *      qwTSF           - Current TSF counter
- *      wBeaconInterval - Beacon Interval
+ *      beacon_interval - Beacon Interval
  *  Out:
  *      none
  *
  * Return Value: none
  */
 void CARDvUpdateNextTBTT(struct vnt_private *priv, u64 qwTSF,
-			 unsigned short wBeaconInterval)
+			 unsigned short beacon_interval)
 {
 	void __iomem *iobase = priv->port_offset;
 
-	qwTSF = CARDqGetNextTBTT(qwTSF, wBeaconInterval);
+	qwTSF = card_get_next_tbtt(qwTSF, beacon_interval);
 	/* Set NextTBTT */
 	qwTSF =  le64_to_cpu(qwTSF);
 	iowrite32((u32)qwTSF, iobase + MAC_REG_NEXTTBTT);
diff --git a/drivers/staging/vt6655/card.h b/drivers/staging/vt6655/card.h
index 19689a291f5b..f52e42564e81 100644
--- a/drivers/staging/vt6655/card.h
+++ b/drivers/staging/vt6655/card.h
@@ -43,20 +43,20 @@ void card_set_rspinf(struct vnt_private *priv, u8 bb_type);
 void CARDvUpdateBasicTopRate(struct vnt_private *priv);
 bool CARDbIsOFDMinBasicRate(struct vnt_private *priv);
 void CARDvSetFirstNextTBTT(struct vnt_private *priv,
-			   unsigned short wBeaconInterval);
+			   unsigned short beacon_interval);
 void CARDvUpdateNextTBTT(struct vnt_private *priv, u64 qwTSF,
-			 unsigned short wBeaconInterval);
+			 unsigned short beacon_interval);
 u64 vt6655_get_current_tsf(struct vnt_private *priv);
-u64 CARDqGetNextTBTT(u64 qwTSF, unsigned short wBeaconInterval);
-u64 CARDqGetTSFOffset(unsigned char rx_rate, u64 qwTSF1, u64 qwTSF2);
+u64 card_get_next_tbtt(u64 qwTSF, unsigned short beacon_interval);
+u64 card_get_tsf_offset(unsigned char rx_rate, u64 qwTSF1, u64 qwTSF2);
 unsigned char card_get_pkt_type(struct vnt_private *priv);
-void CARDvSafeResetTx(struct vnt_private *priv);
+void card_safe_reset_tx(struct vnt_private *priv);
 void CARDvSafeResetRx(struct vnt_private *priv);
-void CARDbRadioPowerOff(struct vnt_private *priv);
+void card_radio_power_off(struct vnt_private *priv);
 bool card_set_phy_parameter(struct vnt_private *priv, u8 bb_type);
 bool card_update_tsf(struct vnt_private *priv, unsigned char rx_rate,
-		    u64 qwBSSTimestamp);
-bool CARDbSetBeaconPeriod(struct vnt_private *priv,
-			  unsigned short wBeaconInterval);
+		    u64 bss_timestamp);
+bool card_set_beacon_period(struct vnt_private *priv,
+			  unsigned short beacon_interval);
 
 #endif /* __CARD_H__ */
diff --git a/drivers/staging/vt6655/device.h b/drivers/staging/vt6655/device.h
index d9ee0b7401fe..0212240ba23f 100644
--- a/drivers/staging/vt6655/device.h
+++ b/drivers/staging/vt6655/device.h
@@ -133,7 +133,7 @@ struct vnt_private {
 	volatile int                iTDUsed[TYPE_MAXTD];
 
 	struct vnt_tx_desc *apCurrTD[TYPE_MAXTD];
-	struct vnt_tx_desc *apTailTD[TYPE_MAXTD];
+	struct vnt_tx_desc *tail_td[TYPE_MAXTD];
 
 	struct vnt_tx_desc *apTD0Rings;
 	struct vnt_tx_desc *apTD1Rings;
@@ -281,7 +281,7 @@ struct vnt_private {
 
 	unsigned char abyEEPROM[EEP_MAX_CONTEXT_SIZE]; /* unsigned long alignment */
 
-	unsigned short wBeaconInterval;
+	unsigned short beacon_interval;
 	u16 wake_up_count;
 
 	struct work_struct interrupt_work;
diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c
index 7d297526e653..b0b262de6480 100644
--- a/drivers/staging/vt6655/device_main.c
+++ b/drivers/staging/vt6655/device_main.c
@@ -454,7 +454,7 @@ static void device_init_registers(struct vnt_private *priv)
 	}
 
 	if (priv->hw_radio_off || priv->bRadioControlOff)
-		CARDbRadioPowerOff(priv);
+		card_radio_power_off(priv);
 
 	/* get Permanent network address */
 	SROMvReadEtherAddress(priv->port_offset, priv->abyCurrentNetAddr);
@@ -463,7 +463,7 @@ static void device_init_registers(struct vnt_private *priv)
 	/* reset Tx pointer */
 	CARDvSafeResetRx(priv);
 	/* reset Rx pointer */
-	CARDvSafeResetTx(priv);
+	card_safe_reset_tx(priv);
 
 	if (priv->local_id <= REV_ID_VT3253_A1)
 		vt6655_mac_reg_bits_on(priv->port_offset, MAC_REG_RCR, RCR_WPAERR);
@@ -737,7 +737,7 @@ static int device_init_td0_ring(struct vnt_private *priv)
 
 	if (i > 0)
 		priv->apTD0Rings[i - 1].next_desc = cpu_to_le32(priv->td0_pool_dma);
-	priv->apTailTD[0] = priv->apCurrTD[0] = &priv->apTD0Rings[0];
+	priv->tail_td[0] = priv->apCurrTD[0] = &priv->apTD0Rings[0];
 
 	return 0;
 
@@ -777,7 +777,7 @@ static int device_init_td1_ring(struct vnt_private *priv)
 
 	if (i > 0)
 		priv->apTD1Rings[i - 1].next_desc = cpu_to_le32(priv->td1_pool_dma);
-	priv->apTailTD[1] = priv->apCurrTD[1] = &priv->apTD1Rings[0];
+	priv->tail_td[1] = priv->apCurrTD[1] = &priv->apTD1Rings[0];
 
 	return 0;
 
@@ -969,7 +969,7 @@ static int device_tx_srv(struct vnt_private *priv, unsigned int idx)
 	unsigned char byTsr0;
 	unsigned char byTsr1;
 
-	for (desc = priv->apTailTD[idx]; priv->iTDUsed[idx] > 0; desc = desc->next) {
+	for (desc = priv->tail_td[idx]; priv->iTDUsed[idx] > 0; desc = desc->next) {
 		if (desc->td0.owner == OWNED_BY_NIC)
 			break;
 		if (works++ > 15)
@@ -1007,7 +1007,7 @@ static int device_tx_srv(struct vnt_private *priv, unsigned int idx)
 		}
 	}
 
-	priv->apTailTD[idx] = desc;
+	priv->tail_td[idx] = desc;
 
 	return works;
 }
@@ -1349,7 +1349,7 @@ static void vnt_stop(struct ieee80211_hw *hw)
 
 	MACbShutdown(priv);
 	MACbSoftwareReset(priv);
-	CARDbRadioPowerOff(priv);
+	card_radio_power_off(priv);
 
 	device_free_td0_ring(priv);
 	device_free_td1_ring(priv);
@@ -1537,7 +1537,7 @@ static void vnt_bss_info_changed(struct ieee80211_hw *hw,
 			card_update_tsf(priv, conf->beacon_rate->hw_value,
 				       conf->sync_tsf);
 
-			CARDbSetBeaconPeriod(priv, conf->beacon_int);
+			card_set_beacon_period(priv, conf->beacon_int);
 
 			CARDvSetFirstNextTBTT(priv, conf->beacon_int);
 		} else {
@@ -1712,7 +1712,7 @@ static int vnt_init(struct vnt_private *priv)
 
 	priv->mac_hw = true;
 
-	CARDbRadioPowerOff(priv);
+	card_radio_power_off(priv);
 
 	return 0;
 }
diff --git a/drivers/staging/vt6655/rxtx.c b/drivers/staging/vt6655/rxtx.c
index 522d34ca9b0f..5e5ed582c35e 100644
--- a/drivers/staging/vt6655/rxtx.c
+++ b/drivers/staging/vt6655/rxtx.c
@@ -1456,7 +1456,7 @@ int vnt_beacon_enable(struct vnt_private *priv, struct ieee80211_vif *vif,
 
 	CARDvSetFirstNextTBTT(priv, conf->beacon_int);
 
-	CARDbSetBeaconPeriod(priv, conf->beacon_int);
+	card_set_beacon_period(priv, conf->beacon_int);
 
 	return vnt_beacon_make(priv, vif);
 }
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index a5f58988130a..c1fbcdd16182 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -759,6 +759,29 @@ static ssize_t emulate_tas_store(struct config_item *item,
 	return count;
 }
 
+static int target_try_configure_unmap(struct se_device *dev,
+				      const char *config_opt)
+{
+	if (!dev->transport->configure_unmap) {
+		pr_err("Generic Block Discard not supported\n");
+		return -ENOSYS;
+	}
+
+	if (!target_dev_configured(dev)) {
+		pr_err("Generic Block Discard setup for %s requires device to be configured\n",
+		       config_opt);
+		return -ENODEV;
+	}
+
+	if (!dev->transport->configure_unmap(dev)) {
+		pr_err("Generic Block Discard setup for %s failed\n",
+		       config_opt);
+		return -ENOSYS;
+	}
+
+	return 0;
+}
+
 static ssize_t emulate_tpu_store(struct config_item *item,
 		const char *page, size_t count)
 {
@@ -776,11 +799,9 @@ static ssize_t emulate_tpu_store(struct config_item *item,
 	 * Discard supported is detected iblock_create_virtdevice().
 	 */
 	if (flag && !da->max_unmap_block_desc_count) {
-		if (!dev->transport->configure_unmap ||
-		    !dev->transport->configure_unmap(dev)) {
-			pr_err("Generic Block Discard not supported\n");
-			return -ENOSYS;
-		}
+		ret = target_try_configure_unmap(dev, "emulate_tpu");
+		if (ret)
+			return ret;
 	}
 
 	da->emulate_tpu = flag;
@@ -806,11 +827,9 @@ static ssize_t emulate_tpws_store(struct config_item *item,
 	 * Discard supported is detected iblock_create_virtdevice().
 	 */
 	if (flag && !da->max_unmap_block_desc_count) {
-		if (!dev->transport->configure_unmap ||
-		    !dev->transport->configure_unmap(dev)) {
-			pr_err("Generic Block Discard not supported\n");
-			return -ENOSYS;
-		}
+		ret = target_try_configure_unmap(dev, "emulate_tpws");
+		if (ret)
+			return ret;
 	}
 
 	da->emulate_tpws = flag;
@@ -1022,12 +1041,9 @@ static ssize_t unmap_zeroes_data_store(struct config_item *item,
 	 * Discard supported is detected iblock_configure_device().
 	 */
 	if (flag && !da->max_unmap_block_desc_count) {
-		if (!dev->transport->configure_unmap ||
-		    !dev->transport->configure_unmap(dev)) {
-			pr_err("dev[%p]: Thin Provisioning LBPRZ will not be set because max_unmap_block_desc_count is zero\n",
-			       da->da_dev);
-			return -ENOSYS;
-		}
+		ret = target_try_configure_unmap(dev, "unmap_zeroes_data");
+		if (ret)
+			return ret;
 	}
 	da->unmap_zeroes_data = flag;
 	pr_debug("dev[%p]: SE Device Thin Provisioning LBPRZ bit: %d\n",
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 506193e870c4..7a85e6477e46 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -147,7 +147,6 @@ int transport_lookup_tmr_lun(struct se_cmd *se_cmd)
 	struct se_session *se_sess = se_cmd->se_sess;
 	struct se_node_acl *nacl = se_sess->se_node_acl;
 	struct se_tmr_req *se_tmr = se_cmd->se_tmr_req;
-	unsigned long flags;
 
 	rcu_read_lock();
 	deve = target_nacl_find_deve(nacl, se_cmd->orig_fe_lun);
@@ -178,10 +177,6 @@ out_unlock:
 	se_cmd->se_dev = rcu_dereference_raw(se_lun->lun_se_dev);
 	se_tmr->tmr_dev = rcu_dereference_raw(se_lun->lun_se_dev);
 
-	spin_lock_irqsave(&se_tmr->tmr_dev->se_tmr_lock, flags);
-	list_add_tail(&se_tmr->tmr_list, &se_tmr->tmr_dev->dev_tmr_list);
-	spin_unlock_irqrestore(&se_tmr->tmr_dev->se_tmr_lock, flags);
-
 	return 0;
 }
 EXPORT_SYMBOL(transport_lookup_tmr_lun);
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 8eb9eb7ce5df..7f6ca8177845 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -91,7 +91,7 @@ static int iblock_configure_device(struct se_device *dev)
 {
 	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
 	struct request_queue *q;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct block_device *bd;
 	struct blk_integrity *bi;
 	blk_mode_t mode = BLK_OPEN_READ;
@@ -117,14 +117,14 @@ static int iblock_configure_device(struct se_device *dev)
 	else
 		dev->dev_flags |= DF_READ_ONLY;
 
-	bdev_handle = bdev_open_by_path(ib_dev->ibd_udev_path, mode, ib_dev,
+	bdev_file = bdev_file_open_by_path(ib_dev->ibd_udev_path, mode, ib_dev,
 					NULL);
-	if (IS_ERR(bdev_handle)) {
-		ret = PTR_ERR(bdev_handle);
+	if (IS_ERR(bdev_file)) {
+		ret = PTR_ERR(bdev_file);
 		goto out_free_bioset;
 	}
-	ib_dev->ibd_bdev_handle = bdev_handle;
-	ib_dev->ibd_bd = bd = bdev_handle->bdev;
+	ib_dev->ibd_bdev_file = bdev_file;
+	ib_dev->ibd_bd = bd = file_bdev(bdev_file);
 
 	q = bdev_get_queue(bd);
 
@@ -180,7 +180,7 @@ static int iblock_configure_device(struct se_device *dev)
 	return 0;
 
 out_blkdev_put:
-	bdev_release(ib_dev->ibd_bdev_handle);
+	fput(ib_dev->ibd_bdev_file);
 out_free_bioset:
 	bioset_exit(&ib_dev->ibd_bio_set);
 out:
@@ -205,8 +205,8 @@ static void iblock_destroy_device(struct se_device *dev)
 {
 	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
 
-	if (ib_dev->ibd_bdev_handle)
-		bdev_release(ib_dev->ibd_bdev_handle);
+	if (ib_dev->ibd_bdev_file)
+		fput(ib_dev->ibd_bdev_file);
 	bioset_exit(&ib_dev->ibd_bio_set);
 }
 
diff --git a/drivers/target/target_core_iblock.h b/drivers/target/target_core_iblock.h
index 683f9a55945b..91f6f4280666 100644
--- a/drivers/target/target_core_iblock.h
+++ b/drivers/target/target_core_iblock.h
@@ -32,7 +32,7 @@ struct iblock_dev {
 	u32	ibd_flags;
 	struct bio_set	ibd_bio_set;
 	struct block_device *ibd_bd;
-	struct bdev_handle *ibd_bdev_handle;
+	struct file *ibd_bdev_file;
 	bool ibd_readonly;
 	struct iblock_dev_plug *ibd_plug;
 } ____cacheline_aligned;
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 41b7489d37ce..f98ebb18666b 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -352,7 +352,7 @@ static int pscsi_create_type_disk(struct se_device *dev, struct scsi_device *sd)
 	struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr;
 	struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
 	struct Scsi_Host *sh = sd->host;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	int ret;
 
 	if (scsi_device_get(sd)) {
@@ -366,18 +366,18 @@ static int pscsi_create_type_disk(struct se_device *dev, struct scsi_device *sd)
 	 * Claim exclusive struct block_device access to struct scsi_device
 	 * for TYPE_DISK and TYPE_ZBC using supplied udev_path
 	 */
-	bdev_handle = bdev_open_by_path(dev->udev_path,
+	bdev_file = bdev_file_open_by_path(dev->udev_path,
 				BLK_OPEN_WRITE | BLK_OPEN_READ, pdv, NULL);
-	if (IS_ERR(bdev_handle)) {
+	if (IS_ERR(bdev_file)) {
 		pr_err("pSCSI: bdev_open_by_path() failed\n");
 		scsi_device_put(sd);
-		return PTR_ERR(bdev_handle);
+		return PTR_ERR(bdev_file);
 	}
-	pdv->pdv_bdev_handle = bdev_handle;
+	pdv->pdv_bdev_file = bdev_file;
 
 	ret = pscsi_add_device_to_list(dev, sd);
 	if (ret) {
-		bdev_release(bdev_handle);
+		fput(bdev_file);
 		scsi_device_put(sd);
 		return ret;
 	}
@@ -564,9 +564,9 @@ static void pscsi_destroy_device(struct se_device *dev)
 		 * from pscsi_create_type_disk()
 		 */
 		if ((sd->type == TYPE_DISK || sd->type == TYPE_ZBC) &&
-		    pdv->pdv_bdev_handle) {
-			bdev_release(pdv->pdv_bdev_handle);
-			pdv->pdv_bdev_handle = NULL;
+		    pdv->pdv_bdev_file) {
+			fput(pdv->pdv_bdev_file);
+			pdv->pdv_bdev_file = NULL;
 		}
 		/*
 		 * For HBA mode PHV_LLD_SCSI_HOST_NO, release the reference
@@ -907,12 +907,15 @@ new_bio:
 
 	return 0;
 fail:
-	if (bio)
-		bio_put(bio);
+	if (bio) {
+		bio_uninit(bio);
+		kfree(bio);
+	}
 	while (req->bio) {
 		bio = req->bio;
 		req->bio = bio->bi_next;
-		bio_put(bio);
+		bio_uninit(bio);
+		kfree(bio);
 	}
 	req->biotail = NULL;
 	return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
@@ -994,8 +997,8 @@ static sector_t pscsi_get_blocks(struct se_device *dev)
 {
 	struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
 
-	if (pdv->pdv_bdev_handle)
-		return bdev_nr_sectors(pdv->pdv_bdev_handle->bdev);
+	if (pdv->pdv_bdev_file)
+		return bdev_nr_sectors(file_bdev(pdv->pdv_bdev_file));
 	return 0;
 }
 
diff --git a/drivers/target/target_core_pscsi.h b/drivers/target/target_core_pscsi.h
index b0a3ef136592..9acaa21e4c78 100644
--- a/drivers/target/target_core_pscsi.h
+++ b/drivers/target/target_core_pscsi.h
@@ -37,7 +37,7 @@ struct pscsi_dev_virt {
 	int	pdv_channel_id;
 	int	pdv_target_id;
 	int	pdv_lun_id;
-	struct bdev_handle *pdv_bdev_handle;
+	struct file *pdv_bdev_file;
 	struct scsi_device *pdv_sd;
 	struct Scsi_Host *pdv_lld_host;
 } ____cacheline_aligned;
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 670cfb7bd426..73d0d6133ac8 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -3629,6 +3629,10 @@ int transport_generic_handle_tmr(
 	unsigned long flags;
 	bool aborted = false;
 
+	spin_lock_irqsave(&cmd->se_dev->se_tmr_lock, flags);
+	list_add_tail(&cmd->se_tmr_req->tmr_list, &cmd->se_dev->dev_tmr_list);
+	spin_unlock_irqrestore(&cmd->se_dev->se_tmr_lock, flags);
+
 	spin_lock_irqsave(&cmd->t_state_lock, flags);
 	if (cmd->transport_state & CMD_T_ABORTED) {
 		aborted = true;
diff --git a/drivers/tee/optee/device.c b/drivers/tee/optee/device.c
index 4b1092127694..1892e49a8e6a 100644
--- a/drivers/tee/optee/device.c
+++ b/drivers/tee/optee/device.c
@@ -90,13 +90,14 @@ static int optee_register_device(const uuid_t *device_uuid, u32 func)
 	if (rc) {
 		pr_err("device registration failed, err: %d\n", rc);
 		put_device(&optee_device->dev);
+		return rc;
 	}
 
 	if (func == PTA_CMD_GET_DEVICES_SUPP)
 		device_create_file(&optee_device->dev,
 				   &dev_attr_need_supplicant);
 
-	return rc;
+	return 0;
 }
 
 static int __optee_enumerate_devices(u32 func)
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index 59883502eff4..17a8ae5e991d 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -33,6 +33,13 @@ config THERMAL_STATISTICS
 
 	  If in doubt, say N.
 
+config THERMAL_DEBUGFS
+	bool "Thermal subsystem debug support"
+	depends on DEBUG_FS
+	help
+	  Say Y to allow the thermal subsystem to collect diagnostic
+	  information that can be accessed via debugfs.
+
 config THERMAL_EMERGENCY_POWEROFF_DELAY_MS
 	int "Emergency poweroff delay in milli-seconds"
 	default 0
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index a8318d671036..d77d7fe99a84 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -10,6 +10,8 @@ thermal_sys-y			+= thermal_trip.o thermal_helpers.o
 # netlink interface to manage the thermal framework
 thermal_sys-$(CONFIG_THERMAL_NETLINK)		+= thermal_netlink.o
 
+thermal_sys-$(CONFIG_THERMAL_DEBUGFS)	+= thermal_debugfs.o
+
 # interface to/from other layers providing sensors
 thermal_sys-$(CONFIG_THERMAL_HWMON)		+= thermal_hwmon.o
 thermal_sys-$(CONFIG_THERMAL_OF)		+= thermal_of.o
diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c
index 7b6aa265ff6a..81e061f183ad 100644
--- a/drivers/thermal/gov_power_allocator.c
+++ b/drivers/thermal/gov_power_allocator.c
@@ -762,7 +762,7 @@ static int power_allocator_throttle(struct thermal_zone_device *tz,
 
 	trip = params->trip_switch_on;
 	if (trip && tz->temperature < trip->temperature) {
-		update = tz->last_temperature >= trip->temperature;
+		update = tz->passive;
 		tz->passive = 0;
 		reset_pid_controller(params);
 		allow_maximum_power(tz, update);
diff --git a/drivers/thermal/intel/intel_hfi.c b/drivers/thermal/intel/intel_hfi.c
index 22445403b520..3b04c6ec4fca 100644
--- a/drivers/thermal/intel/intel_hfi.c
+++ b/drivers/thermal/intel/intel_hfi.c
@@ -35,7 +35,9 @@
 #include <linux/processor.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/suspend.h>
 #include <linux/string.h>
+#include <linux/syscore_ops.h>
 #include <linux/topology.h>
 #include <linux/workqueue.h>
 
@@ -571,6 +573,30 @@ static __init int hfi_parse_features(void)
 	return 0;
 }
 
+static void hfi_do_enable(void)
+{
+	/* This code runs only on the boot CPU. */
+	struct hfi_cpu_info *info = &per_cpu(hfi_cpu_info, 0);
+	struct hfi_instance *hfi_instance = info->hfi_instance;
+
+	/* No locking needed. There is no concurrency with CPU online. */
+	hfi_set_hw_table(hfi_instance);
+	hfi_enable();
+}
+
+static int hfi_do_disable(void)
+{
+	/* No locking needed. There is no concurrency with CPU offline. */
+	hfi_disable();
+
+	return 0;
+}
+
+static struct syscore_ops hfi_pm_ops = {
+	.resume = hfi_do_enable,
+	.suspend = hfi_do_disable,
+};
+
 void __init intel_hfi_init(void)
 {
 	struct hfi_instance *hfi_instance;
@@ -602,6 +628,8 @@ void __init intel_hfi_init(void)
 	if (!hfi_updates_wq)
 		goto err_nomem;
 
+	register_syscore_ops(&hfi_pm_ops);
+
 	return;
 
 err_nomem:
diff --git a/drivers/thermal/intel/intel_powerclamp.c b/drivers/thermal/intel/intel_powerclamp.c
index 5ac5cb60bae6..bc6eb0dd66a4 100644
--- a/drivers/thermal/intel/intel_powerclamp.c
+++ b/drivers/thermal/intel/intel_powerclamp.c
@@ -49,7 +49,6 @@
  */
 #define DEFAULT_DURATION_JIFFIES (6)
 
-static unsigned int target_mwait;
 static struct dentry *debug_dir;
 static bool poll_pkg_cstate_enable;
 
@@ -312,34 +311,6 @@ MODULE_PARM_DESC(window_size, "sliding window in number of clamping cycles\n"
 	"\twindow size results in slower response time but more smooth\n"
 	"\tclamping results. default to 2.");
 
-static void find_target_mwait(void)
-{
-	unsigned int eax, ebx, ecx, edx;
-	unsigned int highest_cstate = 0;
-	unsigned int highest_subcstate = 0;
-	int i;
-
-	if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
-		return;
-
-	cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx);
-
-	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) ||
-	    !(ecx & CPUID5_ECX_INTERRUPT_BREAK))
-		return;
-
-	edx >>= MWAIT_SUBSTATE_SIZE;
-	for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
-		if (edx & MWAIT_SUBSTATE_MASK) {
-			highest_cstate = i;
-			highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
-		}
-	}
-	target_mwait = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
-		(highest_subcstate - 1);
-
-}
-
 struct pkg_cstate_info {
 	bool skip;
 	int msr_index;
@@ -759,9 +730,6 @@ static int __init powerclamp_probe(void)
 		return -ENODEV;
 	}
 
-	/* find the deepest mwait value */
-	find_target_mwait();
-
 	return 0;
 }
 
diff --git a/drivers/thermal/loongson2_thermal.c b/drivers/thermal/loongson2_thermal.c
index 99ca0c7bc41c..0f475fe46bc9 100644
--- a/drivers/thermal/loongson2_thermal.c
+++ b/drivers/thermal/loongson2_thermal.c
@@ -8,9 +8,10 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/minmax.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/thermal.h>
 #include <linux/units.h>
 #include "thermal_hwmon.h"
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index fa88d8707241..dfaa6341694a 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -211,7 +211,7 @@ exit:
 	mutex_unlock(&tz->lock);
 	mutex_unlock(&thermal_governor_lock);
 
-	thermal_notify_tz_gov_change(tz->id, policy);
+	thermal_notify_tz_gov_change(tz, policy);
 
 	return ret;
 }
@@ -381,9 +381,8 @@ static void handle_thermal_trip(struct thermal_zone_device *tz,
 		 * the threshold and the trip temperature will be equal.
 		 */
 		if (tz->temperature >= trip->temperature) {
-			thermal_notify_tz_trip_up(tz->id,
-						  thermal_zone_trip_id(tz, trip),
-						  tz->temperature);
+			thermal_notify_tz_trip_up(tz, trip);
+			thermal_debug_tz_trip_up(tz, trip);
 			trip->threshold = trip->temperature - trip->hysteresis;
 		} else {
 			trip->threshold = trip->temperature;
@@ -400,9 +399,8 @@ static void handle_thermal_trip(struct thermal_zone_device *tz,
 		 * the trip.
 		 */
 		if (tz->temperature < trip->temperature - trip->hysteresis) {
-			thermal_notify_tz_trip_down(tz->id,
-						    thermal_zone_trip_id(tz, trip),
-						    tz->temperature);
+			thermal_notify_tz_trip_down(tz, trip);
+			thermal_debug_tz_trip_down(tz, trip);
 			trip->threshold = trip->temperature;
 		} else {
 			trip->threshold = trip->temperature - trip->hysteresis;
@@ -434,6 +432,7 @@ static void update_temperature(struct thermal_zone_device *tz)
 	trace_thermal_temperature(tz);
 
 	thermal_genl_sampling_temp(tz->id, temp);
+	thermal_debug_update_temp(tz);
 }
 
 static void thermal_zone_device_check(struct work_struct *work)
@@ -505,9 +504,9 @@ static int thermal_zone_device_set_mode(struct thermal_zone_device *tz,
 	mutex_unlock(&tz->lock);
 
 	if (mode == THERMAL_DEVICE_ENABLED)
-		thermal_notify_tz_enable(tz->id);
+		thermal_notify_tz_enable(tz);
 	else
-		thermal_notify_tz_disable(tz->id);
+		thermal_notify_tz_disable(tz);
 
 	return ret;
 }
@@ -846,7 +845,7 @@ static void thermal_release(struct device *dev)
 			    sizeof("cooling_device") - 1)) {
 		cdev = to_cooling_device(dev);
 		thermal_cooling_device_destroy_sysfs(cdev);
-		kfree(cdev->type);
+		kfree_const(cdev->type);
 		ida_free(&thermal_cdev_ida, cdev->id);
 		kfree(cdev);
 	}
@@ -918,7 +917,7 @@ __thermal_cooling_device_register(struct device_node *np,
 	cdev->id = ret;
 	id = ret;
 
-	cdev->type = kstrdup(type ? type : "", GFP_KERNEL);
+	cdev->type = kstrdup_const(type ? type : "", GFP_KERNEL);
 	if (!cdev->type) {
 		ret = -ENOMEM;
 		goto out_ida_remove;
@@ -964,12 +963,14 @@ __thermal_cooling_device_register(struct device_node *np,
 
 	mutex_unlock(&thermal_list_lock);
 
+	thermal_debug_cdev_add(cdev);
+
 	return cdev;
 
 out_cooling_dev:
 	thermal_cooling_device_destroy_sysfs(cdev);
 out_cdev_type:
-	kfree(cdev->type);
+	kfree_const(cdev->type);
 out_ida_remove:
 	ida_free(&thermal_cdev_ida, id);
 out_kfree_cdev:
@@ -1170,6 +1171,8 @@ void thermal_cooling_device_unregister(struct thermal_cooling_device *cdev)
 	if (!cdev)
 		return;
 
+	thermal_debug_cdev_remove(cdev);
+
 	mutex_lock(&thermal_list_lock);
 
 	if (!thermal_cooling_device_present(cdev)) {
@@ -1411,7 +1414,9 @@ thermal_zone_device_register_with_trips(const char *type, struct thermal_trip *t
 	if (atomic_cmpxchg(&tz->need_update, 1, 0))
 		thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
 
-	thermal_notify_tz_create(tz->id, tz->type);
+	thermal_notify_tz_create(tz);
+
+	thermal_debug_tz_add(tz);
 
 	return tz;
 
@@ -1470,14 +1475,13 @@ EXPORT_SYMBOL_GPL(thermal_zone_device);
  */
 void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 {
-	int tz_id;
 	struct thermal_cooling_device *cdev;
 	struct thermal_zone_device *pos = NULL;
 
 	if (!tz)
 		return;
 
-	tz_id = tz->id;
+	thermal_debug_tz_remove(tz);
 
 	mutex_lock(&thermal_list_lock);
 	list_for_each_entry(pos, &thermal_tz_list, node)
@@ -1514,7 +1518,7 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 
 	put_device(&tz->device);
 
-	thermal_notify_tz_delete(tz_id);
+	thermal_notify_tz_delete(tz);
 
 	wait_for_completion(&tz->removal);
 	kfree(tz);
@@ -1636,6 +1640,8 @@ static int __init thermal_init(void)
 {
 	int result;
 
+	thermal_debug_init();
+
 	result = thermal_netlink_init();
 	if (result)
 		goto error;
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index 4e023d54fd27..e9c099ecdd0f 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -13,6 +13,7 @@
 #include <linux/thermal.h>
 
 #include "thermal_netlink.h"
+#include "thermal_debugfs.h"
 
 /* Default Thermal Governor */
 #if defined(CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE)
diff --git a/drivers/thermal/thermal_debugfs.c b/drivers/thermal/thermal_debugfs.c
new file mode 100644
index 000000000000..c617e8b9f0dd
--- /dev/null
+++ b/drivers/thermal/thermal_debugfs.c
@@ -0,0 +1,839 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2023 Linaro Limited
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@linaro.org>
+ *
+ * Thermal subsystem debug support
+ */
+#include <linux/debugfs.h>
+#include <linux/ktime.h>
+#include <linux/list.h>
+#include <linux/minmax.h>
+#include <linux/mutex.h>
+#include <linux/thermal.h>
+
+#include "thermal_core.h"
+
+static struct dentry *d_root;
+static struct dentry *d_cdev;
+static struct dentry *d_tz;
+
+/*
+ * Length of the string containing the thermal zone id or the cooling
+ * device id, including the ending nul character. We can reasonably
+ * assume there won't be more than 256 thermal zones as the maximum
+ * observed today is around 32.
+ */
+#define IDSLENGTH 4
+
+/*
+ * The cooling device transition list is stored in a hash table where
+ * the size is CDEVSTATS_HASH_SIZE. The majority of cooling devices
+ * have dozen of states but some can have much more, so a hash table
+ * is more adequate in this case, because the cost of browsing the entire
+ * list when storing the transitions may not be negligible.
+ */
+#define CDEVSTATS_HASH_SIZE 16
+
+/**
+ * struct cdev_debugfs - per cooling device statistics structure
+ * A cooling device can have a high number of states. Showing the
+ * transitions on a matrix based representation can be overkill given
+ * most of the transitions won't happen and we end up with a matrix
+ * filled with zero. Instead, we show the transitions which actually
+ * happened.
+ *
+ * Every transition updates the current_state and the timestamp. The
+ * transitions and the durations are stored in lists.
+ *
+ * @total: the number of transitions for this cooling device
+ * @current_state: the current cooling device state
+ * @timestamp: the state change timestamp
+ * @transitions: an array of lists containing the state transitions
+ * @durations: an array of lists containing the residencies of each state
+ */
+struct cdev_debugfs {
+	u32 total;
+	int current_state;
+	ktime_t timestamp;
+	struct list_head transitions[CDEVSTATS_HASH_SIZE];
+	struct list_head durations[CDEVSTATS_HASH_SIZE];
+};
+
+/**
+ * struct cdev_record - Common structure for cooling device entry
+ *
+ * The following common structure allows to store the information
+ * related to the transitions and to the state residencies. They are
+ * identified with a id which is associated to a value. It is used as
+ * nodes for the "transitions" and "durations" above.
+ *
+ * @node: node to insert the structure in a list
+ * @id: identifier of the value which can be a state or a transition
+ * @residency: a ktime_t representing a state residency duration
+ * @count: a number of occurrences
+ */
+struct cdev_record {
+	struct list_head node;
+	int id;
+	union {
+                ktime_t residency;
+                u64 count;
+        };
+};
+
+/**
+ * struct trip_stats - Thermal trip statistics
+ *
+ * The trip_stats structure has the relevant information to show the
+ * statistics related to temperature going above a trip point.
+ *
+ * @timestamp: the trip crossing timestamp
+ * @duration: total time when the zone temperature was above the trip point
+ * @count: the number of times the zone temperature was above the trip point
+ * @max: maximum recorded temperature above the trip point
+ * @min: minimum recorded temperature above the trip point
+ * @avg: average temperature above the trip point
+ */
+struct trip_stats {
+	ktime_t timestamp;
+	ktime_t duration;
+	int count;
+	int max;
+	int min;
+	int avg;
+};
+
+/**
+ * struct tz_episode - A mitigation episode information
+ *
+ * The tz_episode structure describes a mitigation episode. A
+ * mitigation episode begins the trip point with the lower temperature
+ * is crossed the way up and ends when it is crossed the way
+ * down. During this episode we can have multiple trip points crossed
+ * the way up and down if there are multiple trip described in the
+ * firmware after the lowest temperature trip point.
+ *
+ * @timestamp: first trip point crossed the way up
+ * @duration: total duration of the mitigation episode
+ * @node: a list element to be added to the list of tz events
+ * @trip_stats: per trip point statistics, flexible array
+ */
+struct tz_episode {
+	ktime_t timestamp;
+	ktime_t duration;
+	struct list_head node;
+	struct trip_stats trip_stats[];
+};
+
+/**
+ * struct tz_debugfs - Store all mitigation episodes for a thermal zone
+ *
+ * The tz_debugfs structure contains the list of the mitigation
+ * episodes and has to track which trip point has been crossed in
+ * order to handle correctly nested trip point mitigation episodes.
+ *
+ * We keep the history of the trip point crossed in an array and as we
+ * can go back and forth inside this history, eg. trip 0,1,2,1,2,1,0,
+ * we keep track of the current position in the history array.
+ *
+ * @tz_episodes: a list of thermal mitigation episodes
+ * @trips_crossed: an array of trip points crossed by id
+ * @nr_trips: the number of trip points currently being crossed
+ */
+struct tz_debugfs {
+	struct list_head tz_episodes;
+	int *trips_crossed;
+	int nr_trips;
+};
+
+/**
+ * struct thermal_debugfs - High level structure for a thermal object in debugfs
+ *
+ * The thermal_debugfs structure is the common structure used by the
+ * cooling device or the thermal zone to store the statistics.
+ *
+ * @d_top: top directory of the thermal object directory
+ * @lock: per object lock to protect the internals
+ *
+ * @cdev_dbg: a cooling device debug structure
+ * @tz_dbg: a thermal zone debug structure
+ */
+struct thermal_debugfs {
+	struct dentry *d_top;
+	struct mutex lock;
+	union {
+		struct cdev_debugfs cdev_dbg;
+		struct tz_debugfs tz_dbg;
+	};
+};
+
+void thermal_debug_init(void)
+{
+	d_root = debugfs_create_dir("thermal", NULL);
+	if (!d_root)
+		return;
+
+	d_cdev = debugfs_create_dir("cooling_devices", d_root);
+	if (!d_cdev)
+		return;
+
+	d_tz = debugfs_create_dir("thermal_zones", d_root);
+}
+
+static struct thermal_debugfs *thermal_debugfs_add_id(struct dentry *d, int id)
+{
+	struct thermal_debugfs *thermal_dbg;
+	char ids[IDSLENGTH];
+
+	thermal_dbg = kzalloc(sizeof(*thermal_dbg), GFP_KERNEL);
+	if (!thermal_dbg)
+		return NULL;
+
+	mutex_init(&thermal_dbg->lock);
+
+	snprintf(ids, IDSLENGTH, "%d", id);
+
+	thermal_dbg->d_top = debugfs_create_dir(ids, d);
+	if (!thermal_dbg->d_top) {
+		kfree(thermal_dbg);
+		return NULL;
+	}
+
+	return thermal_dbg;
+}
+
+static void thermal_debugfs_remove_id(struct thermal_debugfs *thermal_dbg)
+{
+	if (!thermal_dbg)
+		return;
+
+	debugfs_remove(thermal_dbg->d_top);
+
+	kfree(thermal_dbg);
+}
+
+static struct cdev_record *
+thermal_debugfs_cdev_record_alloc(struct thermal_debugfs *thermal_dbg,
+				  struct list_head *lists, int id)
+{
+	struct cdev_record *cdev_record;
+
+	cdev_record = kzalloc(sizeof(*cdev_record), GFP_KERNEL);
+	if (!cdev_record)
+		return NULL;
+
+	cdev_record->id = id;
+	INIT_LIST_HEAD(&cdev_record->node);
+	list_add_tail(&cdev_record->node,
+		      &lists[cdev_record->id % CDEVSTATS_HASH_SIZE]);
+
+	return cdev_record;
+}
+
+static struct cdev_record *
+thermal_debugfs_cdev_record_find(struct thermal_debugfs *thermal_dbg,
+				 struct list_head *lists, int id)
+{
+	struct cdev_record *entry;
+
+	list_for_each_entry(entry, &lists[id % CDEVSTATS_HASH_SIZE], node)
+		if (entry->id == id)
+			return entry;
+
+	return NULL;
+}
+
+static struct cdev_record *
+thermal_debugfs_cdev_record_get(struct thermal_debugfs *thermal_dbg,
+				struct list_head *lists, int id)
+{
+	struct cdev_record *cdev_record;
+
+	cdev_record = thermal_debugfs_cdev_record_find(thermal_dbg, lists, id);
+	if (cdev_record)
+		return cdev_record;
+
+	return thermal_debugfs_cdev_record_alloc(thermal_dbg, lists, id);
+}
+
+static void thermal_debugfs_cdev_clear(struct cdev_debugfs *cdev_dbg)
+{
+	int i;
+	struct cdev_record *entry, *tmp;
+
+	for (i = 0; i < CDEVSTATS_HASH_SIZE; i++) {
+
+		list_for_each_entry_safe(entry, tmp,
+					 &cdev_dbg->transitions[i], node) {
+			list_del(&entry->node);
+			kfree(entry);
+		}
+
+		list_for_each_entry_safe(entry, tmp,
+					 &cdev_dbg->durations[i], node) {
+			list_del(&entry->node);
+			kfree(entry);
+		}
+	}
+
+	cdev_dbg->total = 0;
+}
+
+static void *cdev_seq_start(struct seq_file *s, loff_t *pos)
+{
+	struct thermal_debugfs *thermal_dbg = s->private;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	return (*pos < CDEVSTATS_HASH_SIZE) ? pos : NULL;
+}
+
+static void *cdev_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	(*pos)++;
+
+	return (*pos < CDEVSTATS_HASH_SIZE) ? pos : NULL;
+}
+
+static void cdev_seq_stop(struct seq_file *s, void *v)
+{
+	struct thermal_debugfs *thermal_dbg = s->private;
+
+	mutex_unlock(&thermal_dbg->lock);
+}
+
+static int cdev_tt_seq_show(struct seq_file *s, void *v)
+{
+	struct thermal_debugfs *thermal_dbg = s->private;
+	struct cdev_debugfs *cdev_dbg = &thermal_dbg->cdev_dbg;
+	struct list_head *transitions = cdev_dbg->transitions;
+	struct cdev_record *entry;
+	int i = *(loff_t *)v;
+
+	if (!i)
+		seq_puts(s, "Transition\tOccurences\n");
+
+	list_for_each_entry(entry, &transitions[i], node) {
+		/*
+		 * Assuming maximum cdev states is 1024, the longer
+		 * string for a transition would be "1024->1024\0"
+		 */
+		char buffer[11];
+
+		snprintf(buffer, ARRAY_SIZE(buffer), "%d->%d",
+			 entry->id >> 16, entry->id & 0xFFFF);
+
+		seq_printf(s, "%-10s\t%-10llu\n", buffer, entry->count);
+	}
+
+	return 0;
+}
+
+static const struct seq_operations tt_sops = {
+	.start = cdev_seq_start,
+	.next = cdev_seq_next,
+	.stop = cdev_seq_stop,
+	.show = cdev_tt_seq_show,
+};
+
+DEFINE_SEQ_ATTRIBUTE(tt);
+
+static int cdev_dt_seq_show(struct seq_file *s, void *v)
+{
+	struct thermal_debugfs *thermal_dbg = s->private;
+	struct cdev_debugfs *cdev_dbg = &thermal_dbg->cdev_dbg;
+	struct list_head *durations = cdev_dbg->durations;
+	struct cdev_record *entry;
+	int i = *(loff_t *)v;
+
+	if (!i)
+		seq_puts(s, "State\tResidency\n");
+
+	list_for_each_entry(entry, &durations[i], node) {
+		s64 duration = ktime_to_ms(entry->residency);
+
+		if (entry->id == cdev_dbg->current_state)
+			duration += ktime_ms_delta(ktime_get(),
+						   cdev_dbg->timestamp);
+
+		seq_printf(s, "%-5d\t%-10llu\n", entry->id, duration);
+	}
+
+	return 0;
+}
+
+static const struct seq_operations dt_sops = {
+	.start = cdev_seq_start,
+	.next = cdev_seq_next,
+	.stop = cdev_seq_stop,
+	.show = cdev_dt_seq_show,
+};
+
+DEFINE_SEQ_ATTRIBUTE(dt);
+
+static int cdev_clear_set(void *data, u64 val)
+{
+	struct thermal_debugfs *thermal_dbg = data;
+
+	if (!val)
+		return -EINVAL;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	thermal_debugfs_cdev_clear(&thermal_dbg->cdev_dbg);
+
+	mutex_unlock(&thermal_dbg->lock);
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(cdev_clear_fops, NULL, cdev_clear_set, "%llu\n");
+
+/**
+ * thermal_debug_cdev_state_update - Update a cooling device state change
+ *
+ * Computes a transition and the duration of the previous state residency.
+ *
+ * @cdev : a pointer to a cooling device
+ * @new_state: an integer corresponding to the new cooling device state
+ */
+void thermal_debug_cdev_state_update(const struct thermal_cooling_device *cdev,
+				     int new_state)
+{
+	struct thermal_debugfs *thermal_dbg = cdev->debugfs;
+	struct cdev_debugfs *cdev_dbg;
+	struct cdev_record *cdev_record;
+	int transition, old_state;
+
+	if (!thermal_dbg || (thermal_dbg->cdev_dbg.current_state == new_state))
+		return;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	cdev_dbg = &thermal_dbg->cdev_dbg;
+
+	old_state = cdev_dbg->current_state;
+
+	/*
+	 * Get the old state information in the durations list. If
+	 * this one does not exist, a new allocated one will be
+	 * returned. Recompute the total duration in the old state and
+	 * get a new timestamp for the new state.
+	 */
+	cdev_record = thermal_debugfs_cdev_record_get(thermal_dbg,
+						      cdev_dbg->durations,
+						      old_state);
+	if (cdev_record) {
+		ktime_t now = ktime_get();
+		ktime_t delta = ktime_sub(now, cdev_dbg->timestamp);
+		cdev_record->residency = ktime_add(cdev_record->residency, delta);
+		cdev_dbg->timestamp = now;
+	}
+
+	cdev_dbg->current_state = new_state;
+	transition = (old_state << 16) | new_state;
+
+	/*
+	 * Get the transition in the transitions list. If this one
+	 * does not exist, a new allocated one will be returned.
+	 * Increment the occurrence of this transition which is stored
+	 * in the value field.
+	 */
+	cdev_record = thermal_debugfs_cdev_record_get(thermal_dbg,
+						      cdev_dbg->transitions,
+						      transition);
+	if (cdev_record)
+		cdev_record->count++;
+
+	cdev_dbg->total++;
+
+	mutex_unlock(&thermal_dbg->lock);
+}
+
+/**
+ * thermal_debug_cdev_add - Add a cooling device debugfs entry
+ *
+ * Allocates a cooling device object for debug, initializes the
+ * statistics and create the entries in sysfs.
+ * @cdev: a pointer to a cooling device
+ */
+void thermal_debug_cdev_add(struct thermal_cooling_device *cdev)
+{
+	struct thermal_debugfs *thermal_dbg;
+	struct cdev_debugfs *cdev_dbg;
+	int i;
+
+	thermal_dbg = thermal_debugfs_add_id(d_cdev, cdev->id);
+	if (!thermal_dbg)
+		return;
+
+	cdev_dbg = &thermal_dbg->cdev_dbg;
+
+	for (i = 0; i < CDEVSTATS_HASH_SIZE; i++) {
+		INIT_LIST_HEAD(&cdev_dbg->transitions[i]);
+		INIT_LIST_HEAD(&cdev_dbg->durations[i]);
+	}
+
+	cdev_dbg->current_state = 0;
+	cdev_dbg->timestamp = ktime_get();
+
+	debugfs_create_file("trans_table", 0400, thermal_dbg->d_top,
+			    thermal_dbg, &tt_fops);
+
+	debugfs_create_file("time_in_state_ms", 0400, thermal_dbg->d_top,
+			    thermal_dbg, &dt_fops);
+
+	debugfs_create_file("clear", 0200, thermal_dbg->d_top,
+			    thermal_dbg, &cdev_clear_fops);
+
+	debugfs_create_u32("total_trans", 0400, thermal_dbg->d_top,
+			   &cdev_dbg->total);
+
+	cdev->debugfs = thermal_dbg;
+}
+
+/**
+ * thermal_debug_cdev_remove - Remove a cooling device debugfs entry
+ *
+ * Frees the statistics memory data and remove the debugfs entry
+ *
+ * @cdev: a pointer to a cooling device
+ */
+void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev)
+{
+	struct thermal_debugfs *thermal_dbg = cdev->debugfs;
+
+	if (!thermal_dbg)
+		return;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	thermal_debugfs_cdev_clear(&thermal_dbg->cdev_dbg);
+	cdev->debugfs = NULL;
+
+	mutex_unlock(&thermal_dbg->lock);
+
+	thermal_debugfs_remove_id(thermal_dbg);
+}
+
+static struct tz_episode *thermal_debugfs_tz_event_alloc(struct thermal_zone_device *tz,
+							ktime_t now)
+{
+	struct tz_episode *tze;
+	int i;
+
+	tze = kzalloc(struct_size(tze, trip_stats, tz->num_trips), GFP_KERNEL);
+	if (!tze)
+		return NULL;
+
+	INIT_LIST_HEAD(&tze->node);
+	tze->timestamp = now;
+
+	for (i = 0; i < tz->num_trips; i++) {
+		tze->trip_stats[i].min = INT_MAX;
+		tze->trip_stats[i].max = INT_MIN;
+	}
+
+	return tze;
+}
+
+void thermal_debug_tz_trip_up(struct thermal_zone_device *tz,
+			      const struct thermal_trip *trip)
+{
+	struct tz_episode *tze;
+	struct tz_debugfs *tz_dbg;
+	struct thermal_debugfs *thermal_dbg = tz->debugfs;
+	int temperature = tz->temperature;
+	int trip_id = thermal_zone_trip_id(tz, trip);
+	ktime_t now = ktime_get();
+
+	if (!thermal_dbg)
+		return;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	tz_dbg = &thermal_dbg->tz_dbg;
+
+	/*
+	 * The mitigation is starting. A mitigation can contain
+	 * several episodes where each of them is related to a
+	 * temperature crossing a trip point. The episodes are
+	 * nested. That means when the temperature is crossing the
+	 * first trip point, the duration begins to be measured. If
+	 * the temperature continues to increase and reaches the
+	 * second trip point, the duration of the first trip must be
+	 * also accumulated.
+	 *
+	 * eg.
+	 *
+	 * temp
+	 *   ^
+	 *   |             --------
+	 * trip 2         /        \         ------
+	 *   |           /|        |\      /|      |\
+	 * trip 1       / |        | `----  |      | \
+	 *   |         /| |        |        |      | |\
+	 * trip 0     / | |        |        |      | | \
+	 *   |       /| | |        |        |      | | |\
+	 *   |      / | | |        |        |      | | | `--
+	 *   |     /  | | |        |        |      | | |
+	 *   |-----   | | |        |        |      | | |
+	 *   |        | | |        |        |      | | |
+	 *    --------|-|-|--------|--------|------|-|-|------------------> time
+	 *            | | |<--t2-->|        |<-t2'>| | |
+	 *            | |                            | |
+	 *            | |<------------t1------------>| |
+	 *            |                                |
+	 *            |<-------------t0--------------->|
+	 *
+	 */
+	if (!tz_dbg->nr_trips) {
+		tze = thermal_debugfs_tz_event_alloc(tz, now);
+		if (!tze)
+			goto unlock;
+
+		list_add(&tze->node, &tz_dbg->tz_episodes);
+	}
+
+	/*
+	 * Each time a trip point is crossed the way up, the trip_id
+	 * is stored in the trip_crossed array and the nr_trips is
+	 * incremented. A nr_trips equal to zero means we are entering
+	 * a mitigation episode.
+	 *
+	 * The trip ids may not be in the ascending order but the
+	 * result in the array trips_crossed will be in the ascending
+	 * temperature order. The function detecting when a trip point
+	 * is crossed the way down will handle the very rare case when
+	 * the trip points may have been reordered during this
+	 * mitigation episode.
+	 */
+	tz_dbg->trips_crossed[tz_dbg->nr_trips++] = trip_id;
+
+	tze = list_first_entry(&tz_dbg->tz_episodes, struct tz_episode, node);
+	tze->trip_stats[trip_id].timestamp = now;
+	tze->trip_stats[trip_id].max = max(tze->trip_stats[trip_id].max, temperature);
+	tze->trip_stats[trip_id].min = min(tze->trip_stats[trip_id].min, temperature);
+	tze->trip_stats[trip_id].avg = tze->trip_stats[trip_id].avg +
+		(temperature - tze->trip_stats[trip_id].avg) /
+		tze->trip_stats[trip_id].count;
+
+unlock:
+	mutex_unlock(&thermal_dbg->lock);
+}
+
+void thermal_debug_tz_trip_down(struct thermal_zone_device *tz,
+				const struct thermal_trip *trip)
+{
+	struct thermal_debugfs *thermal_dbg = tz->debugfs;
+	struct tz_episode *tze;
+	struct tz_debugfs *tz_dbg;
+	ktime_t delta, now = ktime_get();
+	int trip_id = thermal_zone_trip_id(tz, trip);
+	int i;
+
+	if (!thermal_dbg)
+		return;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	tz_dbg = &thermal_dbg->tz_dbg;
+
+	/*
+	 * The temperature crosses the way down but there was not
+	 * mitigation detected before. That may happen when the
+	 * temperature is greater than a trip point when registering a
+	 * thermal zone, which is a common use case as the kernel has
+	 * no mitigation mechanism yet at boot time.
+	 */
+	if (!tz_dbg->nr_trips)
+		goto out;
+
+	for (i = tz_dbg->nr_trips - 1; i >= 0; i--) {
+		if (tz_dbg->trips_crossed[i] == trip_id)
+			break;
+	}
+
+	if (i < 0)
+		goto out;
+
+	tz_dbg->nr_trips--;
+
+	if (i < tz_dbg->nr_trips)
+		tz_dbg->trips_crossed[i] = tz_dbg->trips_crossed[tz_dbg->nr_trips];
+
+	tze = list_first_entry(&tz_dbg->tz_episodes, struct tz_episode, node);
+
+	delta = ktime_sub(now, tze->trip_stats[trip_id].timestamp);
+
+	tze->trip_stats[trip_id].duration =
+		ktime_add(delta, tze->trip_stats[trip_id].duration);
+
+	/*
+	 * This event closes the mitigation as we are crossing the
+	 * last trip point the way down.
+	 */
+	if (!tz_dbg->nr_trips)
+		tze->duration = ktime_sub(now, tze->timestamp);
+
+out:
+	mutex_unlock(&thermal_dbg->lock);
+}
+
+void thermal_debug_update_temp(struct thermal_zone_device *tz)
+{
+	struct thermal_debugfs *thermal_dbg = tz->debugfs;
+	struct tz_episode *tze;
+	struct tz_debugfs *tz_dbg;
+	int trip_id, i;
+
+	if (!thermal_dbg)
+		return;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	tz_dbg = &thermal_dbg->tz_dbg;
+
+	if (!tz_dbg->nr_trips)
+		goto out;
+
+	for (i = 0; i < tz_dbg->nr_trips; i++) {
+		trip_id = tz_dbg->trips_crossed[i];
+		tze = list_first_entry(&tz_dbg->tz_episodes, struct tz_episode, node);
+		tze->trip_stats[trip_id].count++;
+		tze->trip_stats[trip_id].max = max(tze->trip_stats[trip_id].max, tz->temperature);
+		tze->trip_stats[trip_id].min = min(tze->trip_stats[trip_id].min, tz->temperature);
+		tze->trip_stats[trip_id].avg = tze->trip_stats[trip_id].avg +
+			(tz->temperature - tze->trip_stats[trip_id].avg) /
+			tze->trip_stats[trip_id].count;
+	}
+out:
+	mutex_unlock(&thermal_dbg->lock);
+}
+
+static void *tze_seq_start(struct seq_file *s, loff_t *pos)
+{
+	struct thermal_zone_device *tz = s->private;
+	struct thermal_debugfs *thermal_dbg = tz->debugfs;
+	struct tz_debugfs *tz_dbg = &thermal_dbg->tz_dbg;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	return seq_list_start(&tz_dbg->tz_episodes, *pos);
+}
+
+static void *tze_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	struct thermal_zone_device *tz = s->private;
+	struct thermal_debugfs *thermal_dbg = tz->debugfs;
+	struct tz_debugfs *tz_dbg = &thermal_dbg->tz_dbg;
+
+	return seq_list_next(v, &tz_dbg->tz_episodes, pos);
+}
+
+static void tze_seq_stop(struct seq_file *s, void *v)
+{
+	struct thermal_zone_device *tz = s->private;
+	struct thermal_debugfs *thermal_dbg = tz->debugfs;
+
+	mutex_unlock(&thermal_dbg->lock);
+}
+
+static int tze_seq_show(struct seq_file *s, void *v)
+{
+	struct thermal_zone_device *tz = s->private;
+	struct thermal_trip *trip;
+	struct tz_episode *tze;
+	const char *type;
+	int trip_id;
+
+	tze = list_entry((struct list_head *)v, struct tz_episode, node);
+
+	seq_printf(s, ",-Mitigation at %lluus, duration=%llums\n",
+		   ktime_to_us(tze->timestamp),
+		   ktime_to_ms(tze->duration));
+
+	seq_printf(s, "| trip |     type | temp(°mC) | hyst(°mC) |  duration  |  avg(°mC) |  min(°mC) |  max(°mC) |\n");
+
+	for_each_trip(tz, trip) {
+		/*
+		 * There is no possible mitigation happening at the
+		 * critical trip point, so the stats will be always
+		 * zero, skip this trip point
+		 */
+		if (trip->type == THERMAL_TRIP_CRITICAL)
+			continue;
+
+		if (trip->type == THERMAL_TRIP_PASSIVE)
+			type = "passive";
+		else if (trip->type == THERMAL_TRIP_ACTIVE)
+			type = "active";
+		else
+			type = "hot";
+
+		trip_id = thermal_zone_trip_id(tz, trip);
+
+		seq_printf(s, "| %*d | %*s | %*d | %*d | %*lld | %*d | %*d | %*d |\n",
+			   4 , trip_id,
+			   8, type,
+			   9, trip->temperature,
+			   9, trip->hysteresis,
+			   10, ktime_to_ms(tze->trip_stats[trip_id].duration),
+			   9, tze->trip_stats[trip_id].avg,
+			   9, tze->trip_stats[trip_id].min,
+			   9, tze->trip_stats[trip_id].max);
+	}
+
+	return 0;
+}
+
+static const struct seq_operations tze_sops = {
+	.start = tze_seq_start,
+	.next = tze_seq_next,
+	.stop = tze_seq_stop,
+	.show = tze_seq_show,
+};
+
+DEFINE_SEQ_ATTRIBUTE(tze);
+
+void thermal_debug_tz_add(struct thermal_zone_device *tz)
+{
+	struct thermal_debugfs *thermal_dbg;
+	struct tz_debugfs *tz_dbg;
+
+	thermal_dbg = thermal_debugfs_add_id(d_tz, tz->id);
+	if (!thermal_dbg)
+		return;
+
+	tz_dbg = &thermal_dbg->tz_dbg;
+
+	tz_dbg->trips_crossed = kzalloc(sizeof(int) * tz->num_trips, GFP_KERNEL);
+	if (!tz_dbg->trips_crossed) {
+		thermal_debugfs_remove_id(thermal_dbg);
+		return;
+	}
+
+	INIT_LIST_HEAD(&tz_dbg->tz_episodes);
+
+	debugfs_create_file("mitigations", 0400, thermal_dbg->d_top, tz, &tze_fops);
+
+	tz->debugfs = thermal_dbg;
+}
+
+void thermal_debug_tz_remove(struct thermal_zone_device *tz)
+{
+	struct thermal_debugfs *thermal_dbg = tz->debugfs;
+
+	if (!thermal_dbg)
+		return;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	tz->debugfs = NULL;
+
+	mutex_unlock(&thermal_dbg->lock);
+
+	thermal_debugfs_remove_id(thermal_dbg);
+}
diff --git a/drivers/thermal/thermal_debugfs.h b/drivers/thermal/thermal_debugfs.h
new file mode 100644
index 000000000000..155b9af5fe87
--- /dev/null
+++ b/drivers/thermal/thermal_debugfs.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifdef CONFIG_THERMAL_DEBUGFS
+void thermal_debug_init(void);
+void thermal_debug_cdev_add(struct thermal_cooling_device *cdev);
+void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev);
+void thermal_debug_cdev_state_update(const struct thermal_cooling_device *cdev, int state);
+void thermal_debug_tz_add(struct thermal_zone_device *tz);
+void thermal_debug_tz_remove(struct thermal_zone_device *tz);
+void thermal_debug_tz_trip_up(struct thermal_zone_device *tz,
+			      const struct thermal_trip *trip);
+void thermal_debug_tz_trip_down(struct thermal_zone_device *tz,
+				const struct thermal_trip *trip);
+void thermal_debug_update_temp(struct thermal_zone_device *tz);
+#else
+static inline void thermal_debug_init(void) {}
+static inline void thermal_debug_cdev_add(struct thermal_cooling_device *cdev) {}
+static inline void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev) {}
+static inline void thermal_debug_cdev_state_update(const struct thermal_cooling_device *cdev,
+						   int state) {}
+static inline void thermal_debug_tz_add(struct thermal_zone_device *tz) {}
+static inline void thermal_debug_tz_remove(struct thermal_zone_device *tz) {}
+static inline void thermal_debug_tz_trip_up(struct thermal_zone_device *tz,
+					    const struct thermal_trip *trip) {};
+static inline void thermal_debug_tz_trip_down(struct thermal_zone_device *tz,
+					      const struct thermal_trip *trip) {}
+static inline void thermal_debug_update_temp(struct thermal_zone_device *tz) {}
+#endif /* CONFIG_THERMAL_DEBUGFS */
diff --git a/drivers/thermal/thermal_helpers.c b/drivers/thermal/thermal_helpers.c
index c3982e0f0075..0329f4a71b02 100644
--- a/drivers/thermal/thermal_helpers.c
+++ b/drivers/thermal/thermal_helpers.c
@@ -146,14 +146,23 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(thermal_zone_get_temp);
 
-static void thermal_cdev_set_cur_state(struct thermal_cooling_device *cdev,
-				       int target)
+static int thermal_cdev_set_cur_state(struct thermal_cooling_device *cdev, int state)
 {
-	if (cdev->ops->set_cur_state(cdev, target))
-		return;
+	int ret;
+
+	/*
+	 * No check is needed for the ops->set_cur_state as the
+	 * registering function checked the ops are correctly set
+	 */
+	ret = cdev->ops->set_cur_state(cdev, state);
+	if (ret)
+		return ret;
 
-	thermal_notify_cdev_state_update(cdev->id, target);
-	thermal_cooling_device_stats_update(cdev, target);
+	thermal_notify_cdev_state_update(cdev, state);
+	thermal_cooling_device_stats_update(cdev, state);
+	thermal_debug_cdev_state_update(cdev, state);
+
+	return 0;
 }
 
 void __thermal_cdev_update(struct thermal_cooling_device *cdev)
diff --git a/drivers/thermal/thermal_netlink.c b/drivers/thermal/thermal_netlink.c
index 332052e24a86..76a231a29654 100644
--- a/drivers/thermal/thermal_netlink.c
+++ b/drivers/thermal/thermal_netlink.c
@@ -148,7 +148,7 @@ static int thermal_genl_event_tz_trip_up(struct param *p)
 	return 0;
 }
 
-static int thermal_genl_event_tz_trip_add(struct param *p)
+static int thermal_genl_event_tz_trip_change(struct param *p)
 {
 	if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_ID, p->tz_id) ||
 	    nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_TRIP_ID, p->trip_id) ||
@@ -160,15 +160,6 @@ static int thermal_genl_event_tz_trip_add(struct param *p)
 	return 0;
 }
 
-static int thermal_genl_event_tz_trip_delete(struct param *p)
-{
-	if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_ID, p->tz_id) ||
-	    nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_TRIP_ID, p->trip_id))
-		return -EMSGSIZE;
-
-	return 0;
-}
-
 static int thermal_genl_event_cdev_add(struct param *p)
 {
 	if (nla_put_string(p->msg, THERMAL_GENL_ATTR_CDEV_NAME,
@@ -258,9 +249,6 @@ int thermal_genl_event_tz_disable(struct param *p)
 int thermal_genl_event_tz_trip_down(struct param *p)
 	__attribute__((alias("thermal_genl_event_tz_trip_up")));
 
-int thermal_genl_event_tz_trip_change(struct param *p)
-	__attribute__((alias("thermal_genl_event_tz_trip_add")));
-
 static cb_t event_cb[] = {
 	[THERMAL_GENL_EVENT_TZ_CREATE]		= thermal_genl_event_tz_create,
 	[THERMAL_GENL_EVENT_TZ_DELETE]		= thermal_genl_event_tz_delete,
@@ -269,8 +257,6 @@ static cb_t event_cb[] = {
 	[THERMAL_GENL_EVENT_TZ_TRIP_UP]		= thermal_genl_event_tz_trip_up,
 	[THERMAL_GENL_EVENT_TZ_TRIP_DOWN]	= thermal_genl_event_tz_trip_down,
 	[THERMAL_GENL_EVENT_TZ_TRIP_CHANGE]	= thermal_genl_event_tz_trip_change,
-	[THERMAL_GENL_EVENT_TZ_TRIP_ADD]	= thermal_genl_event_tz_trip_add,
-	[THERMAL_GENL_EVENT_TZ_TRIP_DELETE]	= thermal_genl_event_tz_trip_delete,
 	[THERMAL_GENL_EVENT_CDEV_ADD]		= thermal_genl_event_cdev_add,
 	[THERMAL_GENL_EVENT_CDEV_DELETE]	= thermal_genl_event_cdev_delete,
 	[THERMAL_GENL_EVENT_CDEV_STATE_UPDATE]	= thermal_genl_event_cdev_state_update,
@@ -318,100 +304,93 @@ out_free_msg:
 	return ret;
 }
 
-int thermal_notify_tz_create(int tz_id, const char *name)
+int thermal_notify_tz_create(const struct thermal_zone_device *tz)
 {
-	struct param p = { .tz_id = tz_id, .name = name };
+	struct param p = { .tz_id = tz->id, .name = tz->type };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_CREATE, &p);
 }
 
-int thermal_notify_tz_delete(int tz_id)
+int thermal_notify_tz_delete(const struct thermal_zone_device *tz)
 {
-	struct param p = { .tz_id = tz_id };
+	struct param p = { .tz_id = tz->id };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_DELETE, &p);
 }
 
-int thermal_notify_tz_enable(int tz_id)
+int thermal_notify_tz_enable(const struct thermal_zone_device *tz)
 {
-	struct param p = { .tz_id = tz_id };
+	struct param p = { .tz_id = tz->id };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_ENABLE, &p);
 }
 
-int thermal_notify_tz_disable(int tz_id)
+int thermal_notify_tz_disable(const struct thermal_zone_device *tz)
 {
-	struct param p = { .tz_id = tz_id };
+	struct param p = { .tz_id = tz->id };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_DISABLE, &p);
 }
 
-int thermal_notify_tz_trip_down(int tz_id, int trip_id, int temp)
+int thermal_notify_tz_trip_down(const struct thermal_zone_device *tz,
+				const struct thermal_trip *trip)
 {
-	struct param p = { .tz_id = tz_id, .trip_id = trip_id, .temp = temp };
+	struct param p = { .tz_id = tz->id,
+			   .trip_id = thermal_zone_trip_id(tz, trip),
+			   .temp = tz->temperature };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_DOWN, &p);
 }
 
-int thermal_notify_tz_trip_up(int tz_id, int trip_id, int temp)
+int thermal_notify_tz_trip_up(const struct thermal_zone_device *tz,
+			      const struct thermal_trip *trip)
 {
-	struct param p = { .tz_id = tz_id, .trip_id = trip_id, .temp = temp };
+	struct param p = { .tz_id = tz->id,
+			   .trip_id = thermal_zone_trip_id(tz, trip),
+			   .temp = tz->temperature };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_UP, &p);
 }
 
-int thermal_notify_tz_trip_add(int tz_id, int trip_id, int trip_type,
-			       int trip_temp, int trip_hyst)
-{
-	struct param p = { .tz_id = tz_id, .trip_id = trip_id,
-			   .trip_type = trip_type, .trip_temp = trip_temp,
-			   .trip_hyst = trip_hyst };
-
-	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_ADD, &p);
-}
-
-int thermal_notify_tz_trip_delete(int tz_id, int trip_id)
-{
-	struct param p = { .tz_id = tz_id, .trip_id = trip_id };
-
-	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_DELETE, &p);
-}
-
-int thermal_notify_tz_trip_change(int tz_id, int trip_id, int trip_type,
-				  int trip_temp, int trip_hyst)
+int thermal_notify_tz_trip_change(const struct thermal_zone_device *tz,
+				  const struct thermal_trip *trip)
 {
-	struct param p = { .tz_id = tz_id, .trip_id = trip_id,
-			   .trip_type = trip_type, .trip_temp = trip_temp,
-			   .trip_hyst = trip_hyst };
+	struct param p = { .tz_id = tz->id,
+			   .trip_id = thermal_zone_trip_id(tz, trip),
+			   .trip_type = trip->type,
+			   .trip_temp = trip->temperature,
+			   .trip_hyst = trip->hysteresis };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_CHANGE, &p);
 }
 
-int thermal_notify_cdev_state_update(int cdev_id, int cdev_state)
+int thermal_notify_cdev_state_update(const struct thermal_cooling_device *cdev,
+				     int state)
 {
-	struct param p = { .cdev_id = cdev_id, .cdev_state = cdev_state };
+	struct param p = { .cdev_id = cdev->id, .cdev_state = state };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_CDEV_STATE_UPDATE, &p);
 }
 
-int thermal_notify_cdev_add(int cdev_id, const char *name, int cdev_max_state)
+int thermal_notify_cdev_add(const struct thermal_cooling_device *cdev)
 {
-	struct param p = { .cdev_id = cdev_id, .name = name,
-			   .cdev_max_state = cdev_max_state };
+	struct param p = { .cdev_id = cdev->id, .name = cdev->type,
+			   .cdev_max_state = cdev->max_state };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_CDEV_ADD, &p);
 }
 
-int thermal_notify_cdev_delete(int cdev_id)
+int thermal_notify_cdev_delete(const struct thermal_cooling_device *cdev)
 {
-	struct param p = { .cdev_id = cdev_id };
+	struct param p = { .cdev_id = cdev->id };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_CDEV_DELETE, &p);
 }
 
-int thermal_notify_tz_gov_change(int tz_id, const char *name)
+int thermal_notify_tz_gov_change(const struct thermal_zone_device *tz,
+				 const char *name)
 {
-	struct param p = { .tz_id = tz_id, .name = name };
+	struct param p = { .tz_id = tz->id, .name = name };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_GOV_CHANGE, &p);
 }
diff --git a/drivers/thermal/thermal_netlink.h b/drivers/thermal/thermal_netlink.h
index 0a9987c3bc57..93a927e144d5 100644
--- a/drivers/thermal/thermal_netlink.h
+++ b/drivers/thermal/thermal_netlink.h
@@ -10,25 +10,30 @@ struct thermal_genl_cpu_caps {
 	int efficiency;
 };
 
+struct thermal_zone_device;
+struct thermal_trip;
+struct thermal_cooling_device;
+
 /* Netlink notification function */
 #ifdef CONFIG_THERMAL_NETLINK
 int __init thermal_netlink_init(void);
 void __init thermal_netlink_exit(void);
-int thermal_notify_tz_create(int tz_id, const char *name);
-int thermal_notify_tz_delete(int tz_id);
-int thermal_notify_tz_enable(int tz_id);
-int thermal_notify_tz_disable(int tz_id);
-int thermal_notify_tz_trip_down(int tz_id, int id, int temp);
-int thermal_notify_tz_trip_up(int tz_id, int id, int temp);
-int thermal_notify_tz_trip_delete(int tz_id, int id);
-int thermal_notify_tz_trip_add(int tz_id, int id, int type,
-			       int temp, int hyst);
-int thermal_notify_tz_trip_change(int tz_id, int id, int type,
-				  int temp, int hyst);
-int thermal_notify_cdev_state_update(int cdev_id, int state);
-int thermal_notify_cdev_add(int cdev_id, const char *name, int max_state);
-int thermal_notify_cdev_delete(int cdev_id);
-int thermal_notify_tz_gov_change(int tz_id, const char *name);
+int thermal_notify_tz_create(const struct thermal_zone_device *tz);
+int thermal_notify_tz_delete(const struct thermal_zone_device *tz);
+int thermal_notify_tz_enable(const struct thermal_zone_device *tz);
+int thermal_notify_tz_disable(const struct thermal_zone_device *tz);
+int thermal_notify_tz_trip_down(const struct thermal_zone_device *tz,
+				const struct thermal_trip *trip);
+int thermal_notify_tz_trip_up(const struct thermal_zone_device *tz,
+			      const struct thermal_trip *trip);
+int thermal_notify_tz_trip_change(const struct thermal_zone_device *tz,
+				  const struct thermal_trip *trip);
+int thermal_notify_cdev_state_update(const struct thermal_cooling_device *cdev,
+				     int state);
+int thermal_notify_cdev_add(const struct thermal_cooling_device *cdev);
+int thermal_notify_cdev_delete(const struct thermal_cooling_device *cdev);
+int thermal_notify_tz_gov_change(const struct thermal_zone_device *tz,
+				 const char *name);
 int thermal_genl_sampling_temp(int id, int temp);
 int thermal_genl_cpu_capability_event(int count,
 				      struct thermal_genl_cpu_caps *caps);
@@ -38,70 +43,62 @@ static inline int thermal_netlink_init(void)
 	return 0;
 }
 
-static inline int thermal_notify_tz_create(int tz_id, const char *name)
-{
-	return 0;
-}
-
-static inline int thermal_notify_tz_delete(int tz_id)
-{
-	return 0;
-}
-
-static inline int thermal_notify_tz_enable(int tz_id)
+static inline int thermal_notify_tz_create(const struct thermal_zone_device *tz)
 {
 	return 0;
 }
 
-static inline int thermal_notify_tz_disable(int tz_id)
+static inline int thermal_notify_tz_delete(const struct thermal_zone_device *tz)
 {
 	return 0;
 }
 
-static inline int thermal_notify_tz_trip_down(int tz_id, int id, int temp)
+static inline int thermal_notify_tz_enable(const struct thermal_zone_device *tz)
 {
 	return 0;
 }
 
-static inline int thermal_notify_tz_trip_up(int tz_id, int id, int temp)
+static inline int thermal_notify_tz_disable(const struct thermal_zone_device *tz)
 {
 	return 0;
 }
 
-static inline int thermal_notify_tz_trip_delete(int tz_id, int id)
+static inline int thermal_notify_tz_trip_down(const struct thermal_zone_device *tz,
+					      const struct thermal_trip *trip)
 {
 	return 0;
 }
 
-static inline int thermal_notify_tz_trip_add(int tz_id, int id, int type,
-					     int temp, int hyst)
+static inline int thermal_notify_tz_trip_up(const struct thermal_zone_device *tz,
+					    const struct thermal_trip *trip)
 {
 	return 0;
 }
 
-static inline int thermal_notify_tz_trip_change(int tz_id, int id, int type,
-						int temp, int hyst)
+static inline int thermal_notify_tz_trip_change(const struct thermal_zone_device *tz,
+						const struct thermal_trip *trip)
 {
 	return 0;
 }
 
-static inline int thermal_notify_cdev_state_update(int cdev_id, int state)
+static inline int thermal_notify_cdev_state_update(const struct thermal_cooling_device *cdev,
+						   int state)
 {
 	return 0;
 }
 
-static inline int thermal_notify_cdev_add(int cdev_id, const char *name,
-					  int max_state)
+static inline int thermal_notify_cdev_add(const struct thermal_cooling_device *cdev)
 {
 	return 0;
 }
 
-static inline int thermal_notify_cdev_delete(int cdev_id)
+static inline int thermal_notify_cdev_delete(const struct thermal_cooling_device *cdev)
 {
 	return 0;
 }
 
-static inline int thermal_notify_tz_gov_change(int tz_id, const char *name)
+static inline int thermal_notify_tz_gov_change(const struct thermal_zone_device *tz,
+					       const char *name)
 {
 	return 0;
 }
diff --git a/drivers/thermal/thermal_trip.c b/drivers/thermal/thermal_trip.c
index 8bffa1e5e206..c875a26d5adf 100644
--- a/drivers/thermal/thermal_trip.c
+++ b/drivers/thermal/thermal_trip.c
@@ -155,9 +155,7 @@ int thermal_zone_trip_id(const struct thermal_zone_device *tz,
 void thermal_zone_trip_updated(struct thermal_zone_device *tz,
 			       const struct thermal_trip *trip)
 {
-	thermal_notify_tz_trip_change(tz->id, thermal_zone_trip_id(tz, trip),
-				      trip->type, trip->temperature,
-				      trip->hysteresis);
+	thermal_notify_tz_trip_change(tz, trip);
 	__thermal_zone_device_update(tz, THERMAL_TRIP_CHANGED);
 }
 
@@ -168,8 +166,6 @@ void thermal_zone_set_trip_temp(struct thermal_zone_device *tz,
 		return;
 
 	trip->temperature = temp;
-	thermal_notify_tz_trip_change(tz->id, thermal_zone_trip_id(tz, trip),
-				      trip->type, trip->temperature,
-				      trip->hysteresis);
+	thermal_notify_tz_trip_change(tz, trip);
 }
 EXPORT_SYMBOL_GPL(thermal_zone_set_trip_temp);
diff --git a/drivers/thunderbolt/domain.c b/drivers/thunderbolt/domain.c
index ec7b5f65804e..9fb1a64f3300 100644
--- a/drivers/thunderbolt/domain.c
+++ b/drivers/thunderbolt/domain.c
@@ -307,7 +307,7 @@ static const struct attribute_group *domain_attr_groups[] = {
 	NULL,
 };
 
-struct bus_type tb_bus_type = {
+const struct bus_type tb_bus_type = {
 	.name = "thunderbolt",
 	.match = tb_service_match,
 	.probe = tb_service_probe,
diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c
index d8b9c734abd3..56790d50f9e3 100644
--- a/drivers/thunderbolt/icm.c
+++ b/drivers/thunderbolt/icm.c
@@ -1020,7 +1020,7 @@ icm_tr_driver_ready(struct tb *tb, enum tb_security_level *security_level,
 
 	memset(&reply, 0, sizeof(reply));
 	ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply),
-			  1, 10, 2000);
+			  1, 10, 250);
 	if (ret)
 		return ret;
 
diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c
index 4b7bec74e89f..fb4f46e51753 100644
--- a/drivers/thunderbolt/nhi.c
+++ b/drivers/thunderbolt/nhi.c
@@ -1517,6 +1517,10 @@ static struct pci_device_id nhi_ids[] = {
 	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTL_P_NHI1),
 	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_LNL_NHI0),
+	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_LNL_NHI1),
+	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_80G_NHI) },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_40G_NHI) },
 
diff --git a/drivers/thunderbolt/nhi.h b/drivers/thunderbolt/nhi.h
index 0f029ce75882..7a07c7c1a9c2 100644
--- a/drivers/thunderbolt/nhi.h
+++ b/drivers/thunderbolt/nhi.h
@@ -90,6 +90,8 @@ extern const struct tb_nhi_ops icl_nhi_ops;
 #define PCI_DEVICE_ID_INTEL_TGL_H_NHI1			0x9a21
 #define PCI_DEVICE_ID_INTEL_RPL_NHI0			0xa73e
 #define PCI_DEVICE_ID_INTEL_RPL_NHI1			0xa76d
+#define PCI_DEVICE_ID_INTEL_LNL_NHI0			0xa833
+#define PCI_DEVICE_ID_INTEL_LNL_NHI1			0xa834
 
 #define PCI_CLASS_SERIAL_USB_USB4			0x0c0340
 
diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
index 44e9b09de47a..fad40c4bc710 100644
--- a/drivers/thunderbolt/switch.c
+++ b/drivers/thunderbolt/switch.c
@@ -941,22 +941,6 @@ int tb_port_get_link_generation(struct tb_port *port)
 	}
 }
 
-static const char *width_name(enum tb_link_width width)
-{
-	switch (width) {
-	case TB_LINK_WIDTH_SINGLE:
-		return "symmetric, single lane";
-	case TB_LINK_WIDTH_DUAL:
-		return "symmetric, dual lanes";
-	case TB_LINK_WIDTH_ASYM_TX:
-		return "asymmetric, 3 transmitters, 1 receiver";
-	case TB_LINK_WIDTH_ASYM_RX:
-		return "asymmetric, 3 receivers, 1 transmitter";
-	default:
-		return "unknown";
-	}
-}
-
 /**
  * tb_port_get_link_width() - Get current link width
  * @port: Port to check (USB4 or CIO)
@@ -1265,6 +1249,9 @@ int tb_port_update_credits(struct tb_port *port)
 	ret = tb_port_do_update_credits(port);
 	if (ret)
 		return ret;
+
+	if (!port->dual_link_port)
+		return 0;
 	return tb_port_do_update_credits(port->dual_link_port);
 }
 
@@ -2769,7 +2756,7 @@ static void tb_switch_link_init(struct tb_switch *sw)
 		return;
 
 	tb_sw_dbg(sw, "current link speed %u.0 Gb/s\n", sw->link_speed);
-	tb_sw_dbg(sw, "current link width %s\n", width_name(sw->link_width));
+	tb_sw_dbg(sw, "current link width %s\n", tb_width_name(sw->link_width));
 
 	bonded = sw->link_width >= TB_LINK_WIDTH_DUAL;
 
@@ -2789,6 +2776,19 @@ static void tb_switch_link_init(struct tb_switch *sw)
 	if (down->dual_link_port)
 		down->dual_link_port->bonded = bonded;
 	tb_port_update_credits(down);
+
+	if (tb_port_get_link_generation(up) < 4)
+		return;
+
+	/*
+	 * Set the Gen 4 preferred link width. This is what the router
+	 * prefers when the link is brought up. If the router does not
+	 * support asymmetric link configuration, this also will be set
+	 * to TB_LINK_WIDTH_DUAL.
+	 */
+	sw->preferred_link_width = sw->link_width;
+	tb_sw_dbg(sw, "preferred link width %s\n",
+		  tb_width_name(sw->preferred_link_width));
 }
 
 /**
@@ -3029,7 +3029,7 @@ int tb_switch_set_link_width(struct tb_switch *sw, enum tb_link_width width)
 
 	tb_switch_update_link_attributes(sw);
 
-	tb_sw_dbg(sw, "link width set to %s\n", width_name(width));
+	tb_sw_dbg(sw, "link width set to %s\n", tb_width_name(width));
 	return ret;
 }
 
diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c
index fd49f86e0353..846d2813bb1a 100644
--- a/drivers/thunderbolt/tb.c
+++ b/drivers/thunderbolt/tb.c
@@ -513,8 +513,6 @@ static void tb_port_unconfigure_xdomain(struct tb_port *port)
 		usb4_port_unconfigure_xdomain(port);
 	else
 		tb_lc_unconfigure_xdomain(port);
-
-	tb_port_enable(port->dual_link_port);
 }
 
 static void tb_scan_xdomain(struct tb_port *port)
@@ -1087,15 +1085,14 @@ static int tb_configure_asym(struct tb *tb, struct tb_port *src_port,
 			     struct tb_port *dst_port, int requested_up,
 			     int requested_down)
 {
+	bool clx = false, clx_disabled = false, downstream;
 	struct tb_switch *sw;
-	bool clx, downstream;
 	struct tb_port *up;
 	int ret = 0;
 
 	if (!asym_threshold)
 		return 0;
 
-	/* Disable CL states before doing any transitions */
 	downstream = tb_port_path_direction_downstream(src_port, dst_port);
 	/* Pick up router deepest in the hierarchy */
 	if (downstream)
@@ -1103,11 +1100,10 @@ static int tb_configure_asym(struct tb *tb, struct tb_port *src_port,
 	else
 		sw = src_port->sw;
 
-	clx = tb_disable_clx(sw);
-
 	tb_for_each_upstream_port_on_path(src_port, dst_port, up) {
+		struct tb_port *down = tb_switch_downstream_port(up->sw);
+		enum tb_link_width width_up, width_down;
 		int consumed_up, consumed_down;
-		enum tb_link_width width;
 
 		ret = tb_consumed_dp_bandwidth(tb, src_port, dst_port, up,
 					       &consumed_up, &consumed_down);
@@ -1128,7 +1124,8 @@ static int tb_configure_asym(struct tb *tb, struct tb_port *src_port,
 			if (consumed_down + requested_down < asym_threshold)
 				continue;
 
-			width = TB_LINK_WIDTH_ASYM_RX;
+			width_up = TB_LINK_WIDTH_ASYM_RX;
+			width_down = TB_LINK_WIDTH_ASYM_TX;
 		} else {
 			/* Upstream, the opposite of above */
 			if (consumed_down + requested_down >= TB_ASYM_MIN) {
@@ -1138,22 +1135,34 @@ static int tb_configure_asym(struct tb *tb, struct tb_port *src_port,
 			if (consumed_up + requested_up < asym_threshold)
 				continue;
 
-			width = TB_LINK_WIDTH_ASYM_TX;
+			width_up = TB_LINK_WIDTH_ASYM_TX;
+			width_down = TB_LINK_WIDTH_ASYM_RX;
 		}
 
-		if (up->sw->link_width == width)
+		if (up->sw->link_width == width_up)
 			continue;
 
-		if (!tb_port_width_supported(up, width))
+		if (!tb_port_width_supported(up, width_up) ||
+		    !tb_port_width_supported(down, width_down))
 			continue;
 
+		/*
+		 * Disable CL states before doing any transitions. We
+		 * delayed it until now that we know there is a real
+		 * transition taking place.
+		 */
+		if (!clx_disabled) {
+			clx = tb_disable_clx(sw);
+			clx_disabled = true;
+		}
+
 		tb_sw_dbg(up->sw, "configuring asymmetric link\n");
 
 		/*
 		 * Here requested + consumed > threshold so we need to
 		 * transtion the link into asymmetric now.
 		 */
-		ret = tb_switch_set_link_width(up->sw, width);
+		ret = tb_switch_set_link_width(up->sw, width_up);
 		if (ret) {
 			tb_sw_warn(up->sw, "failed to set link width\n");
 			break;
@@ -1174,24 +1183,24 @@ static int tb_configure_asym(struct tb *tb, struct tb_port *src_port,
  * @dst_port: Destination adapter
  * @requested_up: New lower bandwidth request upstream (Mb/s)
  * @requested_down: New lower bandwidth request downstream (Mb/s)
+ * @keep_asym: Keep asymmetric link if preferred
  *
  * Goes over each link from @src_port to @dst_port and tries to
  * transition the link to symmetric if the currently consumed bandwidth
- * allows.
+ * allows and link asymmetric preference is ignored (if @keep_asym is %false).
  */
 static int tb_configure_sym(struct tb *tb, struct tb_port *src_port,
 			    struct tb_port *dst_port, int requested_up,
-			    int requested_down)
+			    int requested_down, bool keep_asym)
 {
+	bool clx = false, clx_disabled = false, downstream;
 	struct tb_switch *sw;
-	bool clx, downstream;
 	struct tb_port *up;
 	int ret = 0;
 
 	if (!asym_threshold)
 		return 0;
 
-	/* Disable CL states before doing any transitions */
 	downstream = tb_port_path_direction_downstream(src_port, dst_port);
 	/* Pick up router deepest in the hierarchy */
 	if (downstream)
@@ -1199,8 +1208,6 @@ static int tb_configure_sym(struct tb *tb, struct tb_port *src_port,
 	else
 		sw = src_port->sw;
 
-	clx = tb_disable_clx(sw);
-
 	tb_for_each_upstream_port_on_path(src_port, dst_port, up) {
 		int consumed_up, consumed_down;
 
@@ -1233,6 +1240,25 @@ static int tb_configure_sym(struct tb *tb, struct tb_port *src_port,
 		if (up->sw->link_width == TB_LINK_WIDTH_DUAL)
 			continue;
 
+		/*
+		 * Here consumed < threshold so we can transition the
+		 * link to symmetric.
+		 *
+		 * However, if the router prefers asymmetric link we
+		 * honor that (unless @keep_asym is %false).
+		 */
+		if (keep_asym &&
+		    up->sw->preferred_link_width > TB_LINK_WIDTH_DUAL) {
+			tb_sw_dbg(up->sw, "keeping preferred asymmetric link\n");
+			continue;
+		}
+
+		/* Disable CL states before doing any transitions */
+		if (!clx_disabled) {
+			clx = tb_disable_clx(sw);
+			clx_disabled = true;
+		}
+
 		tb_sw_dbg(up->sw, "configuring symmetric link\n");
 
 		ret = tb_switch_set_link_width(up->sw, TB_LINK_WIDTH_DUAL);
@@ -1280,7 +1306,7 @@ static void tb_configure_link(struct tb_port *down, struct tb_port *up,
 		struct tb_port *host_port;
 
 		host_port = tb_port_at(tb_route(sw), tb->root_switch);
-		tb_configure_sym(tb, host_port, up, 0, 0);
+		tb_configure_sym(tb, host_port, up, 0, 0, false);
 	}
 
 	/* Set the link configured */
@@ -1465,7 +1491,7 @@ static void tb_deactivate_and_free_tunnel(struct tb_tunnel *tunnel)
 		 * If bandwidth on a link is < asym_threshold
 		 * transition the link to symmetric.
 		 */
-		tb_configure_sym(tb, src_port, dst_port, 0, 0);
+		tb_configure_sym(tb, src_port, dst_port, 0, 0, true);
 		/* Now we can allow the domain to runtime suspend again */
 		pm_runtime_mark_last_busy(&dst_port->sw->dev);
 		pm_runtime_put_autosuspend(&dst_port->sw->dev);
@@ -1901,7 +1927,7 @@ static void tb_dp_resource_available(struct tb *tb, struct tb_port *port)
 			return;
 	}
 
-	tb_port_dbg(port, "DP %s resource available\n",
+	tb_port_dbg(port, "DP %s resource available after hotplug\n",
 		    tb_port_is_dpin(port) ? "IN" : "OUT");
 	list_add_tail(&port->list, &tcm->dp_resources);
 
@@ -2287,7 +2313,7 @@ static int tb_alloc_dp_bandwidth(struct tb_tunnel *tunnel, int *requested_up,
 		 * If bandwidth on a link is < asym_threshold transition
 		 * the link to symmetric.
 		 */
-		tb_configure_sym(tb, in, out, *requested_up, *requested_down);
+		tb_configure_sym(tb, in, out, *requested_up, *requested_down, true);
 		/*
 		 * If requested bandwidth is less or equal than what is
 		 * currently allocated to that tunnel we simply change
@@ -2330,7 +2356,7 @@ static int tb_alloc_dp_bandwidth(struct tb_tunnel *tunnel, int *requested_up,
 		ret = tb_configure_asym(tb, in, out, *requested_up,
 					*requested_down);
 		if (ret) {
-			tb_configure_sym(tb, in, out, 0, 0);
+			tb_configure_sym(tb, in, out, 0, 0, true);
 			return ret;
 		}
 
@@ -2338,7 +2364,7 @@ static int tb_alloc_dp_bandwidth(struct tb_tunnel *tunnel, int *requested_up,
 						requested_down);
 		if (ret) {
 			tb_tunnel_warn(tunnel, "failed to allocate bandwidth\n");
-			tb_configure_sym(tb, in, out, 0, 0);
+			tb_configure_sym(tb, in, out, 0, 0, true);
 		}
 	} else {
 		ret = -ENOBUFS;
diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h
index e299e53473ae..997c5a536905 100644
--- a/drivers/thunderbolt/tb.h
+++ b/drivers/thunderbolt/tb.h
@@ -125,6 +125,7 @@ struct tb_switch_tmu {
  * @device_name: Name of the device (or %NULL if not known)
  * @link_speed: Speed of the link in Gb/s
  * @link_width: Width of the upstream facing link
+ * @preferred_link_width: Router preferred link width (only set for Gen 4 links)
  * @link_usb4: Upstream link is USB4
  * @generation: Switch Thunderbolt generation
  * @cap_plug_events: Offset to the plug events capability (%0 if not found)
@@ -178,6 +179,7 @@ struct tb_switch {
 	const char *device_name;
 	unsigned int link_speed;
 	enum tb_link_width link_width;
+	enum tb_link_width preferred_link_width;
 	bool link_usb4;
 	unsigned int generation;
 	int cap_plug_events;
@@ -568,6 +570,22 @@ static inline struct tb_port *tb_port_at(u64 route, struct tb_switch *sw)
 	return &sw->ports[port];
 }
 
+static inline const char *tb_width_name(enum tb_link_width width)
+{
+	switch (width) {
+	case TB_LINK_WIDTH_SINGLE:
+		return "symmetric, single lane";
+	case TB_LINK_WIDTH_DUAL:
+		return "symmetric, dual lanes";
+	case TB_LINK_WIDTH_ASYM_TX:
+		return "asymmetric, 3 transmitters, 1 receiver";
+	case TB_LINK_WIDTH_ASYM_RX:
+		return "asymmetric, 3 receivers, 1 transmitter";
+	default:
+		return "unknown";
+	}
+}
+
 /**
  * tb_port_has_remote() - Does the port have switch connected downstream
  * @port: Port to check
diff --git a/drivers/thunderbolt/tb_regs.h b/drivers/thunderbolt/tb_regs.h
index 87e4795275fe..6f798f6a2b84 100644
--- a/drivers/thunderbolt/tb_regs.h
+++ b/drivers/thunderbolt/tb_regs.h
@@ -203,7 +203,7 @@ struct tb_regs_switch_header {
 #define ROUTER_CS_5_WOP				BIT(1)
 #define ROUTER_CS_5_WOU				BIT(2)
 #define ROUTER_CS_5_WOD				BIT(3)
-#define ROUTER_CS_5_C3S				BIT(23)
+#define ROUTER_CS_5_CNS				BIT(23)
 #define ROUTER_CS_5_PTO				BIT(24)
 #define ROUTER_CS_5_UTO				BIT(25)
 #define ROUTER_CS_5_HCO				BIT(26)
diff --git a/drivers/thunderbolt/tmu.c b/drivers/thunderbolt/tmu.c
index 11f2aec2a5d3..9a259c72e5a7 100644
--- a/drivers/thunderbolt/tmu.c
+++ b/drivers/thunderbolt/tmu.c
@@ -894,7 +894,7 @@ static int tb_switch_tmu_change_mode(struct tb_switch *sw)
 
 	ret = tb_switch_set_tmu_mode_params(sw, sw->tmu.mode_request);
 	if (ret)
-		return ret;
+		goto out;
 
 	/* Program the new mode and the downstream router lane adapter */
 	switch (sw->tmu.mode_request) {
diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c
index 7534cd3a81f4..6fffb2c82d3d 100644
--- a/drivers/thunderbolt/tunnel.c
+++ b/drivers/thunderbolt/tunnel.c
@@ -173,16 +173,28 @@ static int tb_pci_set_ext_encapsulation(struct tb_tunnel *tunnel, bool enable)
 	int ret;
 
 	/* Only supported of both routers are at least USB4 v2 */
-	if (tb_port_get_link_generation(port) < 4)
+	if ((usb4_switch_version(tunnel->src_port->sw) < 2) ||
+	   (usb4_switch_version(tunnel->dst_port->sw) < 2))
+		return 0;
+
+	if (enable && tb_port_get_link_generation(port) < 4)
 		return 0;
 
 	ret = usb4_pci_port_set_ext_encapsulation(tunnel->src_port, enable);
 	if (ret)
 		return ret;
 
+	/*
+	 * Downstream router could be unplugged so disable of encapsulation
+	 * in upstream router is still possible.
+	 */
 	ret = usb4_pci_port_set_ext_encapsulation(tunnel->dst_port, enable);
-	if (ret)
-		return ret;
+	if (ret) {
+		if (enable)
+			return ret;
+		if (ret != -ENODEV)
+			return ret;
+	}
 
 	tb_tunnel_dbg(tunnel, "extended encapsulation %s\n",
 		      str_enabled_disabled(enable));
@@ -199,14 +211,21 @@ static int tb_pci_activate(struct tb_tunnel *tunnel, bool activate)
 			return res;
 	}
 
-	res = tb_pci_port_enable(tunnel->src_port, activate);
+	if (activate)
+		res = tb_pci_port_enable(tunnel->dst_port, activate);
+	else
+		res = tb_pci_port_enable(tunnel->src_port, activate);
 	if (res)
 		return res;
 
-	if (tb_port_is_pcie_up(tunnel->dst_port)) {
-		res = tb_pci_port_enable(tunnel->dst_port, activate);
+
+	if (activate) {
+		res = tb_pci_port_enable(tunnel->src_port, activate);
 		if (res)
 			return res;
+	} else {
+		/* Downstream router could be unplugged */
+		tb_pci_port_enable(tunnel->dst_port, activate);
 	}
 
 	return activate ? 0 : tb_pci_set_ext_encapsulation(tunnel, activate);
@@ -1067,8 +1086,7 @@ static int tb_dp_alloc_bandwidth(struct tb_tunnel *tunnel, int *alloc_up,
 	return 0;
 }
 
-static int tb_dp_read_dprx(struct tb_tunnel *tunnel, u32 *rate, u32 *lanes,
-			   int timeout_msec)
+static int tb_dp_wait_dprx(struct tb_tunnel *tunnel, int timeout_msec)
 {
 	ktime_t timeout = ktime_add_ms(ktime_get(), timeout_msec);
 	struct tb_port *in = tunnel->src_port;
@@ -1087,15 +1105,13 @@ static int tb_dp_read_dprx(struct tb_tunnel *tunnel, u32 *rate, u32 *lanes,
 			return ret;
 
 		if (val & DP_COMMON_CAP_DPRX_DONE) {
-			*rate = tb_dp_cap_get_rate(val);
-			*lanes = tb_dp_cap_get_lanes(val);
-
 			tb_tunnel_dbg(tunnel, "DPRX read done\n");
 			return 0;
 		}
 		usleep_range(100, 150);
 	} while (ktime_before(ktime_get(), timeout));
 
+	tb_tunnel_dbg(tunnel, "DPRX read timeout\n");
 	return -ETIMEDOUT;
 }
 
@@ -1110,6 +1126,7 @@ static int tb_dp_read_cap(struct tb_tunnel *tunnel, unsigned int cap, u32 *rate,
 	switch (cap) {
 	case DP_LOCAL_CAP:
 	case DP_REMOTE_CAP:
+	case DP_COMMON_CAP:
 		break;
 
 	default:
@@ -1182,7 +1199,7 @@ static int tb_dp_consumed_bandwidth(struct tb_tunnel *tunnel, int *consumed_up,
 		 * reduced one). Otherwise return the remote (possibly
 		 * reduced) caps.
 		 */
-		ret = tb_dp_read_dprx(tunnel, &rate, &lanes, 150);
+		ret = tb_dp_wait_dprx(tunnel, 150);
 		if (ret) {
 			if (ret == -ETIMEDOUT)
 				ret = tb_dp_read_cap(tunnel, DP_REMOTE_CAP,
@@ -1190,6 +1207,9 @@ static int tb_dp_consumed_bandwidth(struct tb_tunnel *tunnel, int *consumed_up,
 			if (ret)
 				return ret;
 		}
+		ret = tb_dp_read_cap(tunnel, DP_COMMON_CAP, &rate, &lanes);
+		if (ret)
+			return ret;
 	} else if (sw->generation >= 2) {
 		ret = tb_dp_read_cap(tunnel, DP_REMOTE_CAP, &rate, &lanes);
 		if (ret)
@@ -1313,8 +1333,6 @@ static void tb_dp_dump(struct tb_tunnel *tunnel)
 		      "DP IN maximum supported bandwidth %u Mb/s x%u = %u Mb/s\n",
 		      rate, lanes, tb_dp_bandwidth(rate, lanes));
 
-	out = tunnel->dst_port;
-
 	if (tb_port_read(out, &dp_cap, TB_CFG_PORT,
 			 out->cap_adap + DP_LOCAL_CAP, 1))
 		return;
diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c
index f8f0d24ff6e4..1515eff8cc3e 100644
--- a/drivers/thunderbolt/usb4.c
+++ b/drivers/thunderbolt/usb4.c
@@ -290,7 +290,7 @@ int usb4_switch_setup(struct tb_switch *sw)
 	}
 
 	/* TBT3 supported by the CM */
-	val |= ROUTER_CS_5_C3S;
+	val &= ~ROUTER_CS_5_CNS;
 
 	return tb_sw_write(sw, &val, TB_CFG_SWITCH, ROUTER_CS_5, 1);
 }
diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c
index 9803f0bbf20d..9495742913d5 100644
--- a/drivers/thunderbolt/xdomain.c
+++ b/drivers/thunderbolt/xdomain.c
@@ -1462,6 +1462,11 @@ static int tb_xdomain_get_properties(struct tb_xdomain *xd)
 				tb_port_disable(port->dual_link_port);
 		}
 
+		dev_dbg(&xd->dev, "current link speed %u.0 Gb/s\n",
+			xd->link_speed);
+		dev_dbg(&xd->dev, "current link width %s\n",
+			tb_width_name(xd->link_width));
+
 		if (device_add(&xd->dev)) {
 			dev_err(&xd->dev, "failed to add XDomain device\n");
 			return -ENODEV;
@@ -1895,6 +1900,50 @@ struct device_type tb_xdomain_type = {
 };
 EXPORT_SYMBOL_GPL(tb_xdomain_type);
 
+static void tb_xdomain_link_init(struct tb_xdomain *xd, struct tb_port *down)
+{
+	if (!down->dual_link_port)
+		return;
+
+	/*
+	 * Gen 4 links come up already as bonded so only update the port
+	 * structures here.
+	 */
+	if (tb_port_get_link_generation(down) >= 4) {
+		down->bonded = true;
+		down->dual_link_port->bonded = true;
+	} else {
+		xd->bonding_possible = true;
+	}
+}
+
+static void tb_xdomain_link_exit(struct tb_xdomain *xd)
+{
+	struct tb_port *down = tb_xdomain_downstream_port(xd);
+
+	if (!down->dual_link_port)
+		return;
+
+	if (tb_port_get_link_generation(down) >= 4) {
+		down->bonded = false;
+		down->dual_link_port->bonded = false;
+	} else if (xd->link_width > TB_LINK_WIDTH_SINGLE) {
+		/*
+		 * Just return port structures back to way they were and
+		 * update credits. No need to update userspace because
+		 * the XDomain is removed soon anyway.
+		 */
+		tb_port_lane_bonding_disable(down);
+		tb_port_update_credits(down);
+	} else if (down->dual_link_port) {
+		/*
+		 * Re-enable the lane 1 adapter we disabled at the end
+		 * of tb_xdomain_get_properties().
+		 */
+		tb_port_enable(down->dual_link_port);
+	}
+}
+
 /**
  * tb_xdomain_alloc() - Allocate new XDomain object
  * @tb: Domain where the XDomain belongs
@@ -1945,7 +1994,8 @@ struct tb_xdomain *tb_xdomain_alloc(struct tb *tb, struct device *parent,
 			goto err_free_local_uuid;
 	} else {
 		xd->needs_uuid = true;
-		xd->bonding_possible = !!down->dual_link_port;
+
+		tb_xdomain_link_init(xd, down);
 	}
 
 	device_initialize(&xd->dev);
@@ -2014,6 +2064,8 @@ void tb_xdomain_remove(struct tb_xdomain *xd)
 
 	device_for_each_child_reverse(&xd->dev, xd, unregister_service);
 
+	tb_xdomain_link_exit(xd);
+
 	/*
 	 * Undo runtime PM here explicitly because it is possible that
 	 * the XDomain was never added to the bus and thus device_del()
diff --git a/drivers/tty/amiserial.c b/drivers/tty/amiserial.c
index 785558c65ae8..7716ce0d35bc 100644
--- a/drivers/tty/amiserial.c
+++ b/drivers/tty/amiserial.c
@@ -81,7 +81,7 @@ struct serial_state {
 	int			quot;
 	int			IER; 	/* Interrupt Enable Register */
 	int			MCR; 	/* Modem control register */
-	int			x_char;	/* xon/xoff character */
+	u8			x_char;	/* xon/xoff character */
 };
 
 static struct tty_driver *serial_driver;
@@ -178,9 +178,9 @@ static void receive_chars(struct serial_state *info)
 {
         int status;
 	int serdatr;
-	unsigned char ch, flag;
+	u8 ch, flag;
 	struct	async_icount *icount;
-	int oe = 0;
+	bool overrun = false;
 
 	icount = &info->icount;
 
@@ -230,7 +230,7 @@ static void receive_chars(struct serial_state *info)
 	   * should be ignored.
 	   */
 	  if (status & info->ignore_status_mask)
-	    goto out;
+		  return;
 
 	  status &= info->read_status_mask;
 
@@ -251,15 +251,13 @@ static void receive_chars(struct serial_state *info)
 	     * reported immediately, and doesn't
 	     * affect the current character
 	     */
-	     oe = 1;
+	     overrun = true;
 	  }
 	}
 	tty_insert_flip_char(&info->tport, ch, flag);
-	if (oe == 1)
+	if (overrun)
 		tty_insert_flip_char(&info->tport, 0, TTY_OVERRUN);
 	tty_flip_buffer_push(&info->tport);
-out:
-	return;
 }
 
 static void transmit_chars(struct serial_state *info)
@@ -813,7 +811,7 @@ static void rs_flush_buffer(struct tty_struct *tty)
  * This function is used to send a high-priority XON/XOFF character to
  * the device
  */
-static void rs_send_xchar(struct tty_struct *tty, char ch)
+static void rs_send_xchar(struct tty_struct *tty, u8 ch)
 {
 	struct serial_state *info = tty->driver_data;
         unsigned long flags;
diff --git a/drivers/tty/ehv_bytechan.c b/drivers/tty/ehv_bytechan.c
index a067628e01c8..69508d7a4135 100644
--- a/drivers/tty/ehv_bytechan.c
+++ b/drivers/tty/ehv_bytechan.c
@@ -49,7 +49,7 @@ struct ehv_bc_data {
 	unsigned int tx_irq;
 
 	spinlock_t lock;	/* lock for transmit buffer */
-	unsigned char buf[BUF_SIZE];	/* transmit circular buffer */
+	u8 buf[BUF_SIZE];	/* transmit circular buffer */
 	unsigned int head;	/* circular buffer head */
 	unsigned int tail;	/* circular buffer tail */
 
@@ -138,14 +138,17 @@ static int find_console_handle(void)
 
 static unsigned int local_ev_byte_channel_send(unsigned int handle,
 					       unsigned int *count,
-					       const char *p)
+					       const u8 *p)
 {
-	char buffer[EV_BYTE_CHANNEL_MAX_BYTES];
+	u8 buffer[EV_BYTE_CHANNEL_MAX_BYTES];
 	unsigned int c = *count;
 
+	/*
+	 * ev_byte_channel_send() expects at least EV_BYTE_CHANNEL_MAX_BYTES
+	 * (16 B) in the buffer. Fake it using a local buffer if needed.
+	 */
 	if (c < sizeof(buffer)) {
-		memcpy(buffer, p, c);
-		memset(&buffer[c], 0, sizeof(buffer) - c);
+		memcpy_and_pad(buffer, sizeof(buffer), p, c, 0);
 		p = buffer;
 	}
 	return ev_byte_channel_send(handle, count, p);
@@ -163,7 +166,7 @@ static unsigned int local_ev_byte_channel_send(unsigned int handle,
  * has been sent, or if some error has occurred.
  *
  */
-static void byte_channel_spin_send(const char data)
+static void byte_channel_spin_send(const u8 data)
 {
 	int ret, count;
 
@@ -471,8 +474,7 @@ static ssize_t ehv_bc_tty_write(struct tty_struct *ttys, const u8 *s,
 {
 	struct ehv_bc_data *bc = ttys->driver_data;
 	unsigned long flags;
-	unsigned int len;
-	unsigned int written = 0;
+	size_t len, written = 0;
 
 	while (1) {
 		spin_lock_irqsave(&bc->lock, flags);
diff --git a/drivers/tty/goldfish.c b/drivers/tty/goldfish.c
index 4591f940b7a1..d27979eabfdf 100644
--- a/drivers/tty/goldfish.c
+++ b/drivers/tty/goldfish.c
@@ -50,10 +50,8 @@ static u32 goldfish_tty_line_count = 8;
 static u32 goldfish_tty_current_line_count;
 static struct goldfish_tty *goldfish_ttys;
 
-static void do_rw_io(struct goldfish_tty *qtty,
-		     unsigned long address,
-		     unsigned int count,
-		     int is_write)
+static void do_rw_io(struct goldfish_tty *qtty, unsigned long address,
+		     size_t count, bool is_write)
 {
 	unsigned long irq_flags;
 	void __iomem *base = qtty->base;
@@ -73,10 +71,8 @@ static void do_rw_io(struct goldfish_tty *qtty,
 	spin_unlock_irqrestore(&qtty->lock, irq_flags);
 }
 
-static void goldfish_tty_rw(struct goldfish_tty *qtty,
-			    unsigned long addr,
-			    unsigned int count,
-			    int is_write)
+static void goldfish_tty_rw(struct goldfish_tty *qtty, unsigned long addr,
+			    size_t count, bool is_write)
 {
 	dma_addr_t dma_handle;
 	enum dma_data_direction dma_dir;
@@ -125,20 +121,18 @@ static void goldfish_tty_rw(struct goldfish_tty *qtty,
 	}
 }
 
-static void goldfish_tty_do_write(int line, const u8 *buf, unsigned int count)
+static void goldfish_tty_do_write(int line, const u8 *buf, size_t count)
 {
 	struct goldfish_tty *qtty = &goldfish_ttys[line];
-	unsigned long address = (unsigned long)(void *)buf;
 
-	goldfish_tty_rw(qtty, address, count, 1);
+	goldfish_tty_rw(qtty, (unsigned long)buf, count, true);
 }
 
 static irqreturn_t goldfish_tty_interrupt(int irq, void *dev_id)
 {
 	struct goldfish_tty *qtty = dev_id;
 	void __iomem *base = qtty->base;
-	unsigned long address;
-	unsigned char *buf;
+	u8 *buf;
 	u32 count;
 
 	count = gf_ioread32(base + GOLDFISH_TTY_REG_BYTES_READY);
@@ -147,8 +141,7 @@ static irqreturn_t goldfish_tty_interrupt(int irq, void *dev_id)
 
 	count = tty_prepare_flip_string(&qtty->port, &buf, count);
 
-	address = (unsigned long)(void *)buf;
-	goldfish_tty_rw(qtty, address, count, 0);
+	goldfish_tty_rw(qtty, (unsigned long)buf, count, false);
 
 	tty_flip_buffer_push(&qtty->port);
 	return IRQ_HANDLED;
diff --git a/drivers/tty/hvc/Kconfig b/drivers/tty/hvc/Kconfig
index 4f9264d005c0..c2a4e88b328f 100644
--- a/drivers/tty/hvc/Kconfig
+++ b/drivers/tty/hvc/Kconfig
@@ -108,13 +108,15 @@ config HVC_DCC_SERIALIZE_SMP
 
 config HVC_RISCV_SBI
 	bool "RISC-V SBI console support"
-	depends on RISCV_SBI_V01
+	depends on RISCV_SBI && NONPORTABLE
 	select HVC_DRIVER
 	help
 	  This enables support for console output via RISC-V SBI calls, which
-	  is normally used only during boot to output printk.
+	  is normally used only during boot to output printk.  This driver
+	  conflicts with real console drivers and should not be enabled on
+	  systems that directly access the console.
 
-	  If you don't know what do to here, say Y.
+	  If you don't know what do to here, say N.
 
 config HVCS
 	tristate "IBM Hypervisor Virtual Console Server support"
diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c
index 959fae54ca39..cd1f657f782d 100644
--- a/drivers/tty/hvc/hvc_console.c
+++ b/drivers/tty/hvc/hvc_console.c
@@ -922,8 +922,7 @@ struct hvc_struct *hvc_alloc(uint32_t vtermno, int data,
 			return ERR_PTR(err);
 	}
 
-	hp = kzalloc(ALIGN(sizeof(*hp), sizeof(long)) + outbuf_size,
-			GFP_KERNEL);
+	hp = kzalloc(struct_size(hp, outbuf, outbuf_size), GFP_KERNEL);
 	if (!hp)
 		return ERR_PTR(-ENOMEM);
 
@@ -931,7 +930,6 @@ struct hvc_struct *hvc_alloc(uint32_t vtermno, int data,
 	hp->data = data;
 	hp->ops = ops;
 	hp->outbuf_size = outbuf_size;
-	hp->outbuf = &((char *)hp)[ALIGN(sizeof(*hp), sizeof(long))];
 
 	tty_port_init(&hp->port);
 	hp->port.ops = &hvc_port_ops;
@@ -976,7 +974,7 @@ struct hvc_struct *hvc_alloc(uint32_t vtermno, int data,
 }
 EXPORT_SYMBOL_GPL(hvc_alloc);
 
-int hvc_remove(struct hvc_struct *hp)
+void hvc_remove(struct hvc_struct *hp)
 {
 	unsigned long flags;
 	struct tty_struct *tty;
@@ -1010,7 +1008,6 @@ int hvc_remove(struct hvc_struct *hp)
 		tty_vhangup(tty);
 		tty_kref_put(tty);
 	}
-	return 0;
 }
 EXPORT_SYMBOL_GPL(hvc_remove);
 
diff --git a/drivers/tty/hvc/hvc_console.h b/drivers/tty/hvc/hvc_console.h
index 9668f821db01..cf4c1af08a7c 100644
--- a/drivers/tty/hvc/hvc_console.h
+++ b/drivers/tty/hvc/hvc_console.h
@@ -37,7 +37,6 @@ struct hvc_struct {
 	spinlock_t lock;
 	int index;
 	int do_wakeup;
-	char *outbuf;
 	int outbuf_size;
 	int n_outbuf;
 	uint32_t vtermno;
@@ -48,12 +47,13 @@ struct hvc_struct {
 	struct work_struct tty_resize;
 	struct list_head next;
 	unsigned long flags;
+	u8 outbuf[] __aligned(sizeof(long));
 };
 
 /* implemented by a low level driver */
 struct hv_ops {
-	int (*get_chars)(uint32_t vtermno, char *buf, int count);
-	int (*put_chars)(uint32_t vtermno, const char *buf, int count);
+	ssize_t (*get_chars)(uint32_t vtermno, u8 *buf, size_t count);
+	ssize_t (*put_chars)(uint32_t vtermno, const u8 *buf, size_t count);
 	int (*flush)(uint32_t vtermno, bool wait);
 
 	/* Callbacks for notification. Called in open, close and hangup */
@@ -77,7 +77,7 @@ extern int hvc_instantiate(uint32_t vtermno, int index,
 extern struct hvc_struct * hvc_alloc(uint32_t vtermno, int data,
 				     const struct hv_ops *ops, int outbuf_size);
 /* remove a vterm from hvc tty operation (module_exit or hotplug remove) */
-extern int hvc_remove(struct hvc_struct *hp);
+extern void hvc_remove(struct hvc_struct *hp);
 
 /* data available */
 int hvc_poll(struct hvc_struct *hp);
diff --git a/drivers/tty/hvc/hvc_dcc.c b/drivers/tty/hvc/hvc_dcc.c
index 1751108cf763..dfc5c9c38f07 100644
--- a/drivers/tty/hvc/hvc_dcc.c
+++ b/drivers/tty/hvc/hvc_dcc.c
@@ -26,10 +26,10 @@
 /* Lock to serialize access to DCC fifo */
 static DEFINE_SPINLOCK(dcc_lock);
 
-static DEFINE_KFIFO(inbuf, unsigned char, DCC_INBUF_SIZE);
-static DEFINE_KFIFO(outbuf, unsigned char, DCC_OUTBUF_SIZE);
+static DEFINE_KFIFO(inbuf, u8, DCC_INBUF_SIZE);
+static DEFINE_KFIFO(outbuf, u8, DCC_OUTBUF_SIZE);
 
-static void dcc_uart_console_putchar(struct uart_port *port, unsigned char ch)
+static void dcc_uart_console_putchar(struct uart_port *port, u8 ch)
 {
 	while (__dcc_getstatus() & DCC_STATUS_TX)
 		cpu_relax();
@@ -47,6 +47,14 @@ static void dcc_early_write(struct console *con, const char *s, unsigned n)
 static int __init dcc_early_console_setup(struct earlycon_device *device,
 					  const char *opt)
 {
+	unsigned int count = 0x4000000;
+
+	while (--count && (__dcc_getstatus() & DCC_STATUS_TX))
+		cpu_relax();
+
+	if (__dcc_getstatus() & DCC_STATUS_TX)
+		return -ENODEV;
+
 	device->con->write = dcc_early_write;
 
 	return 0;
@@ -54,9 +62,9 @@ static int __init dcc_early_console_setup(struct earlycon_device *device,
 
 EARLYCON_DECLARE(dcc, dcc_early_console_setup);
 
-static int hvc_dcc_put_chars(uint32_t vt, const char *buf, int count)
+static ssize_t hvc_dcc_put_chars(uint32_t vt, const u8 *buf, size_t count)
 {
-	int i;
+	size_t i;
 
 	for (i = 0; i < count; i++) {
 		while (__dcc_getstatus() & DCC_STATUS_TX)
@@ -68,9 +76,9 @@ static int hvc_dcc_put_chars(uint32_t vt, const char *buf, int count)
 	return count;
 }
 
-static int hvc_dcc_get_chars(uint32_t vt, char *buf, int count)
+static ssize_t hvc_dcc_get_chars(uint32_t vt, u8 *buf, size_t count)
 {
-	int i;
+	size_t i;
 
 	for (i = 0; i < count; ++i)
 		if (__dcc_getstatus() & DCC_STATUS_RX)
@@ -149,8 +157,8 @@ static DECLARE_WORK(dcc_pwork, dcc_put_work);
  */
 static void dcc_get_work(struct work_struct *work)
 {
-	unsigned char ch;
 	unsigned long irqflags;
+	u8 ch;
 
 	/*
 	 * Read characters from DCC and put them into the input FIFO, as
@@ -172,10 +180,10 @@ static DECLARE_WORK(dcc_gwork, dcc_get_work);
  * Write characters directly to the DCC if we're on core 0 and the FIFO
  * is empty, or write them to the FIFO if we're not.
  */
-static int hvc_dcc0_put_chars(u32 vt, const char *buf, int count)
+static ssize_t hvc_dcc0_put_chars(u32 vt, const u8 *buf, size_t count)
 {
-	int len;
 	unsigned long irqflags;
+	ssize_t len;
 
 	if (!IS_ENABLED(CONFIG_HVC_DCC_SERIALIZE_SMP))
 		return hvc_dcc_put_chars(vt, buf, count);
@@ -211,10 +219,10 @@ static int hvc_dcc0_put_chars(u32 vt, const char *buf, int count)
  * Read characters directly from the DCC if we're on core 0 and the FIFO
  * is empty, or read them from the FIFO if we're not.
  */
-static int hvc_dcc0_get_chars(u32 vt, char *buf, int count)
+static ssize_t hvc_dcc0_get_chars(u32 vt, u8 *buf, size_t count)
 {
-	int len;
 	unsigned long irqflags;
+	ssize_t len;
 
 	if (!IS_ENABLED(CONFIG_HVC_DCC_SERIALIZE_SMP))
 		return hvc_dcc_get_chars(vt, buf, count);
diff --git a/drivers/tty/hvc/hvc_iucv.c b/drivers/tty/hvc/hvc_iucv.c
index 543f35ddf523..fdecc0d63731 100644
--- a/drivers/tty/hvc/hvc_iucv.c
+++ b/drivers/tty/hvc/hvc_iucv.c
@@ -215,11 +215,11 @@ static void destroy_tty_buffer_list(struct list_head *list)
  * If the IUCV path has been severed, then -EPIPE is returned to cause a
  * hang up (that is issued by the HVC layer).
  */
-static int hvc_iucv_write(struct hvc_iucv_private *priv,
-			  char *buf, int count, int *has_more_data)
+static ssize_t hvc_iucv_write(struct hvc_iucv_private *priv,
+			      u8 *buf, size_t count, int *has_more_data)
 {
 	struct iucv_tty_buffer *rb;
-	int written;
+	ssize_t written;
 	int rc;
 
 	/* immediately return if there is no IUCV connection */
@@ -312,10 +312,10 @@ out_written:
  *		the routine locks the struct hvc_iucv_private->lock to call
  *		helper functions.
  */
-static int hvc_iucv_get_chars(uint32_t vtermno, char *buf, int count)
+static ssize_t hvc_iucv_get_chars(uint32_t vtermno, u8 *buf, size_t count)
 {
 	struct hvc_iucv_private *priv = hvc_iucv_get_private(vtermno);
-	int written;
+	ssize_t written;
 	int has_more_data;
 
 	if (count <= 0)
@@ -352,8 +352,8 @@ static int hvc_iucv_get_chars(uint32_t vtermno, char *buf, int count)
  * If an existing IUCV communicaton path has been severed, -EPIPE is returned
  * (that can be passed to HVC layer to cause a tty hangup).
  */
-static int hvc_iucv_queue(struct hvc_iucv_private *priv, const char *buf,
-			  int count)
+static ssize_t hvc_iucv_queue(struct hvc_iucv_private *priv, const u8 *buf,
+			      size_t count)
 {
 	size_t len;
 
@@ -455,12 +455,12 @@ static void hvc_iucv_sndbuf_work(struct work_struct *work)
  * Locking:	The method gets called under an irqsave() spinlock; and
  *		locks struct hvc_iucv_private->lock.
  */
-static int hvc_iucv_put_chars(uint32_t vtermno, const char *buf, int count)
+static ssize_t hvc_iucv_put_chars(uint32_t vtermno, const u8 *buf, size_t count)
 {
 	struct hvc_iucv_private *priv = hvc_iucv_get_private(vtermno);
 	int queued;
 
-	if (count <= 0)
+	if (!count)
 		return 0;
 
 	if (!priv)
diff --git a/drivers/tty/hvc/hvc_opal.c b/drivers/tty/hvc/hvc_opal.c
index 992e199e0ea8..095c33ad10f8 100644
--- a/drivers/tty/hvc/hvc_opal.c
+++ b/drivers/tty/hvc/hvc_opal.c
@@ -58,7 +58,7 @@ static const struct hv_ops hvc_opal_raw_ops = {
 	.notifier_hangup = notifier_hangup_irq,
 };
 
-static int hvc_opal_hvsi_get_chars(uint32_t vtermno, char *buf, int count)
+static ssize_t hvc_opal_hvsi_get_chars(uint32_t vtermno, u8 *buf, size_t count)
 {
 	struct hvc_opal_priv *pv = hvc_opal_privs[vtermno];
 
@@ -68,7 +68,8 @@ static int hvc_opal_hvsi_get_chars(uint32_t vtermno, char *buf, int count)
 	return hvsilib_get_chars(&pv->hvsi, buf, count);
 }
 
-static int hvc_opal_hvsi_put_chars(uint32_t vtermno, const char *buf, int count)
+static ssize_t hvc_opal_hvsi_put_chars(uint32_t vtermno, const u8 *buf,
+				       size_t count)
 {
 	struct hvc_opal_priv *pv = hvc_opal_privs[vtermno];
 
@@ -232,24 +233,21 @@ static int hvc_opal_probe(struct platform_device *dev)
 	return 0;
 }
 
-static int hvc_opal_remove(struct platform_device *dev)
+static void hvc_opal_remove(struct platform_device *dev)
 {
 	struct hvc_struct *hp = dev_get_drvdata(&dev->dev);
-	int rc, termno;
+	int termno;
 
 	termno = hp->vtermno;
-	rc = hvc_remove(hp);
-	if (rc == 0) {
-		if (hvc_opal_privs[termno] != &hvc_opal_boot_priv)
-			kfree(hvc_opal_privs[termno]);
-		hvc_opal_privs[termno] = NULL;
-	}
-	return rc;
+	hvc_remove(hp);
+	if (hvc_opal_privs[termno] != &hvc_opal_boot_priv)
+		kfree(hvc_opal_privs[termno]);
+	hvc_opal_privs[termno] = NULL;
 }
 
 static struct platform_driver hvc_opal_driver = {
 	.probe		= hvc_opal_probe,
-	.remove		= hvc_opal_remove,
+	.remove_new	= hvc_opal_remove,
 	.driver		= {
 		.name	= hvc_opal_name,
 		.of_match_table	= hvc_opal_match,
diff --git a/drivers/tty/hvc/hvc_riscv_sbi.c b/drivers/tty/hvc/hvc_riscv_sbi.c
index 31f53fa77e4a..cede8a572594 100644
--- a/drivers/tty/hvc/hvc_riscv_sbi.c
+++ b/drivers/tty/hvc/hvc_riscv_sbi.c
@@ -15,9 +15,9 @@
 
 #include "hvc_console.h"
 
-static int hvc_sbi_tty_put(uint32_t vtermno, const char *buf, int count)
+static ssize_t hvc_sbi_tty_put(uint32_t vtermno, const u8 *buf, size_t count)
 {
-	int i;
+	size_t i;
 
 	for (i = 0; i < count; i++)
 		sbi_console_putchar(buf[i]);
@@ -25,9 +25,10 @@ static int hvc_sbi_tty_put(uint32_t vtermno, const char *buf, int count)
 	return i;
 }
 
-static int hvc_sbi_tty_get(uint32_t vtermno, char *buf, int count)
+static ssize_t hvc_sbi_tty_get(uint32_t vtermno, u8 *buf, size_t count)
 {
-	int i, c;
+	size_t i;
+	int c;
 
 	for (i = 0; i < count; i++) {
 		c = sbi_console_getchar();
@@ -39,21 +40,44 @@ static int hvc_sbi_tty_get(uint32_t vtermno, char *buf, int count)
 	return i;
 }
 
-static const struct hv_ops hvc_sbi_ops = {
+static const struct hv_ops hvc_sbi_v01_ops = {
 	.get_chars = hvc_sbi_tty_get,
 	.put_chars = hvc_sbi_tty_put,
 };
 
-static int __init hvc_sbi_init(void)
+static ssize_t hvc_sbi_dbcn_tty_put(uint32_t vtermno, const u8 *buf, size_t count)
 {
-	return PTR_ERR_OR_ZERO(hvc_alloc(0, 0, &hvc_sbi_ops, 16));
+	return sbi_debug_console_write(buf, count);
 }
-device_initcall(hvc_sbi_init);
 
-static int __init hvc_sbi_console_init(void)
+static ssize_t hvc_sbi_dbcn_tty_get(uint32_t vtermno, u8 *buf, size_t count)
 {
-	hvc_instantiate(0, 0, &hvc_sbi_ops);
+	return sbi_debug_console_read(buf, count);
+}
+
+static const struct hv_ops hvc_sbi_dbcn_ops = {
+	.put_chars = hvc_sbi_dbcn_tty_put,
+	.get_chars = hvc_sbi_dbcn_tty_get,
+};
+
+static int __init hvc_sbi_init(void)
+{
+	int err;
+
+	if (sbi_debug_console_available) {
+		err = PTR_ERR_OR_ZERO(hvc_alloc(0, 0, &hvc_sbi_dbcn_ops, 256));
+		if (err)
+			return err;
+		hvc_instantiate(0, 0, &hvc_sbi_dbcn_ops);
+	} else if (IS_ENABLED(CONFIG_RISCV_SBI_V01)) {
+		err = PTR_ERR_OR_ZERO(hvc_alloc(0, 0, &hvc_sbi_v01_ops, 256));
+		if (err)
+			return err;
+		hvc_instantiate(0, 0, &hvc_sbi_v01_ops);
+	} else {
+		return -ENODEV;
+	}
 
 	return 0;
 }
-console_initcall(hvc_sbi_console_init);
+device_initcall(hvc_sbi_init);
diff --git a/drivers/tty/hvc/hvc_rtas.c b/drivers/tty/hvc/hvc_rtas.c
index 184d325abeed..a0b90275b37f 100644
--- a/drivers/tty/hvc/hvc_rtas.c
+++ b/drivers/tty/hvc/hvc_rtas.c
@@ -31,10 +31,10 @@ static struct hvc_struct *hvc_rtas_dev;
 static int rtascons_put_char_token = RTAS_UNKNOWN_SERVICE;
 static int rtascons_get_char_token = RTAS_UNKNOWN_SERVICE;
 
-static inline int hvc_rtas_write_console(uint32_t vtermno, const char *buf,
-		int count)
+static ssize_t hvc_rtas_write_console(uint32_t vtermno, const u8 *buf,
+				      size_t count)
 {
-	int i;
+	size_t i;
 
 	for (i = 0; i < count; i++) {
 		if (rtas_call(rtascons_put_char_token, 1, 1, NULL, buf[i]))
@@ -44,9 +44,10 @@ static inline int hvc_rtas_write_console(uint32_t vtermno, const char *buf,
 	return i;
 }
 
-static int hvc_rtas_read_console(uint32_t vtermno, char *buf, int count)
+static ssize_t hvc_rtas_read_console(uint32_t vtermno, u8 *buf, size_t count)
 {
-	int i, c;
+	size_t i;
+	int c;
 
 	for (i = 0; i < count; i++) {
 		if (rtas_call(rtascons_get_char_token, 0, 2, &c))
diff --git a/drivers/tty/hvc/hvc_udbg.c b/drivers/tty/hvc/hvc_udbg.c
index ff0dcc56413c..fdc2699b78dc 100644
--- a/drivers/tty/hvc/hvc_udbg.c
+++ b/drivers/tty/hvc/hvc_udbg.c
@@ -19,9 +19,9 @@
 
 static struct hvc_struct *hvc_udbg_dev;
 
-static int hvc_udbg_put(uint32_t vtermno, const char *buf, int count)
+static ssize_t hvc_udbg_put(uint32_t vtermno, const u8 *buf, size_t count)
 {
-	int i;
+	size_t i;
 
 	for (i = 0; i < count && udbg_putc; i++)
 		udbg_putc(buf[i]);
@@ -29,9 +29,10 @@ static int hvc_udbg_put(uint32_t vtermno, const char *buf, int count)
 	return i;
 }
 
-static int hvc_udbg_get(uint32_t vtermno, char *buf, int count)
+static ssize_t hvc_udbg_get(uint32_t vtermno, u8 *buf, size_t count)
 {
-	int i, c;
+	size_t i;
+	int c;
 
 	if (!udbg_getc_poll)
 		return 0;
diff --git a/drivers/tty/hvc/hvc_vio.c b/drivers/tty/hvc/hvc_vio.c
index 736b230f5ec0..47930601a26a 100644
--- a/drivers/tty/hvc/hvc_vio.c
+++ b/drivers/tty/hvc/hvc_vio.c
@@ -58,20 +58,20 @@ struct hvterm_priv {
 	hv_protocol_t		proto;	/* Raw data or HVSI packets */
 	struct hvsi_priv	hvsi;	/* HVSI specific data */
 	spinlock_t		buf_lock;
-	char			buf[SIZE_VIO_GET_CHARS];
-	int			left;
-	int			offset;
+	u8			buf[SIZE_VIO_GET_CHARS];
+	size_t			left;
+	size_t			offset;
 };
 static struct hvterm_priv *hvterm_privs[MAX_NR_HVC_CONSOLES];
 /* For early boot console */
 static struct hvterm_priv hvterm_priv0;
 
-static int hvterm_raw_get_chars(uint32_t vtermno, char *buf, int count)
+static ssize_t hvterm_raw_get_chars(uint32_t vtermno, u8 *buf, size_t count)
 {
 	struct hvterm_priv *pv = hvterm_privs[vtermno];
 	unsigned long i;
 	unsigned long flags;
-	int got;
+	size_t got;
 
 	if (WARN_ON(!pv))
 		return 0;
@@ -115,7 +115,8 @@ static int hvterm_raw_get_chars(uint32_t vtermno, char *buf, int count)
  *       you are sending fewer chars.
  * @count: number of chars to send.
  */
-static int hvterm_raw_put_chars(uint32_t vtermno, const char *buf, int count)
+static ssize_t hvterm_raw_put_chars(uint32_t vtermno, const u8 *buf,
+				    size_t count)
 {
 	struct hvterm_priv *pv = hvterm_privs[vtermno];
 
@@ -133,7 +134,7 @@ static const struct hv_ops hvterm_raw_ops = {
 	.notifier_hangup = notifier_hangup_irq,
 };
 
-static int hvterm_hvsi_get_chars(uint32_t vtermno, char *buf, int count)
+static ssize_t hvterm_hvsi_get_chars(uint32_t vtermno, u8 *buf, size_t count)
 {
 	struct hvterm_priv *pv = hvterm_privs[vtermno];
 
@@ -143,7 +144,8 @@ static int hvterm_hvsi_get_chars(uint32_t vtermno, char *buf, int count)
 	return hvsilib_get_chars(&pv->hvsi, buf, count);
 }
 
-static int hvterm_hvsi_put_chars(uint32_t vtermno, const char *buf, int count)
+static ssize_t hvterm_hvsi_put_chars(uint32_t vtermno, const u8 *buf,
+				     size_t count)
 {
 	struct hvterm_priv *pv = hvterm_privs[vtermno];
 
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 34c01874f45b..0e497501f8e3 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -84,13 +84,13 @@ static inline void notify_daemon(struct xencons_info *cons)
 	notify_remote_via_evtchn(cons->evtchn);
 }
 
-static int __write_console(struct xencons_info *xencons,
-		const char *data, int len)
+static ssize_t __write_console(struct xencons_info *xencons,
+			       const u8 *data, size_t len)
 {
 	XENCONS_RING_IDX cons, prod;
 	struct xencons_interface *intf = xencons->intf;
-	int sent = 0;
 	unsigned long flags;
+	size_t sent = 0;
 
 	spin_lock_irqsave(&xencons->ring_lock, flags);
 	cons = intf->out_cons;
@@ -115,10 +115,11 @@ static int __write_console(struct xencons_info *xencons,
 	return sent;
 }
 
-static int domU_write_console(uint32_t vtermno, const char *data, int len)
+static ssize_t domU_write_console(uint32_t vtermno, const u8 *data, size_t len)
 {
-	int ret = len;
 	struct xencons_info *cons = vtermno_to_xencons(vtermno);
+	size_t ret = len;
+
 	if (cons == NULL)
 		return -EINVAL;
 
@@ -129,7 +130,7 @@ static int domU_write_console(uint32_t vtermno, const char *data, int len)
 	 * kernel is crippled.
 	 */
 	while (len) {
-		int sent = __write_console(cons, data, len);
+		ssize_t sent = __write_console(cons, data, len);
 
 		if (sent < 0)
 			return sent;
@@ -144,14 +145,14 @@ static int domU_write_console(uint32_t vtermno, const char *data, int len)
 	return ret;
 }
 
-static int domU_read_console(uint32_t vtermno, char *buf, int len)
+static ssize_t domU_read_console(uint32_t vtermno, u8 *buf, size_t len)
 {
 	struct xencons_interface *intf;
 	XENCONS_RING_IDX cons, prod;
-	int recv = 0;
 	struct xencons_info *xencons = vtermno_to_xencons(vtermno);
 	unsigned int eoiflag = 0;
 	unsigned long flags;
+	size_t recv = 0;
 
 	if (xencons == NULL)
 		return -EINVAL;
@@ -209,7 +210,7 @@ static const struct hv_ops domU_hvc_ops = {
 	.notifier_hangup = notifier_hangup_irq,
 };
 
-static int dom0_read_console(uint32_t vtermno, char *buf, int len)
+static ssize_t dom0_read_console(uint32_t vtermno, u8 *buf, size_t len)
 {
 	return HYPERVISOR_console_io(CONSOLEIO_read, len, buf);
 }
@@ -218,9 +219,9 @@ static int dom0_read_console(uint32_t vtermno, char *buf, int len)
  * Either for a dom0 to write to the system console, or a domU with a
  * debug version of Xen
  */
-static int dom0_write_console(uint32_t vtermno, const char *str, int len)
+static ssize_t dom0_write_console(uint32_t vtermno, const u8 *str, size_t len)
 {
-	int rc = HYPERVISOR_console_io(CONSOLEIO_write, len, (char *)str);
+	int rc = HYPERVISOR_console_io(CONSOLEIO_write, len, (u8 *)str);
 	if (rc < 0)
 		return rc;
 
diff --git a/drivers/tty/hvc/hvsi_lib.c b/drivers/tty/hvc/hvsi_lib.c
index 09289c8154ae..22e1bc4d8a66 100644
--- a/drivers/tty/hvc/hvsi_lib.c
+++ b/drivers/tty/hvc/hvsi_lib.c
@@ -12,7 +12,7 @@ static int hvsi_send_packet(struct hvsi_priv *pv, struct hvsi_header *packet)
 	packet->seqno = cpu_to_be16(atomic_inc_return(&pv->seqno));
 
 	/* Assumes that always succeeds, works in practice */
-	return pv->put_chars(pv->termno, (char *)packet, packet->len);
+	return pv->put_chars(pv->termno, (u8 *)packet, packet->len);
 }
 
 static void hvsi_start_handshake(struct hvsi_priv *pv)
@@ -178,9 +178,10 @@ static int hvsi_get_packet(struct hvsi_priv *pv)
 	return 0;
 }
 
-int hvsilib_get_chars(struct hvsi_priv *pv, char *buf, int count)
+ssize_t hvsilib_get_chars(struct hvsi_priv *pv, u8 *buf, size_t count)
 {
-	unsigned int tries, read = 0;
+	unsigned int tries;
+	size_t read = 0;
 
 	if (WARN_ON(!pv))
 		return -ENXIO;
@@ -199,7 +200,7 @@ int hvsilib_get_chars(struct hvsi_priv *pv, char *buf, int count)
 	for (tries = 1; count && tries < 2; tries++) {
 		/* Consume existing data packet */
 		if (pv->inbuf_pktlen) {
-			unsigned int l = min(count, (int)pv->inbuf_pktlen);
+			size_t l = min(count, pv->inbuf_pktlen);
 			memcpy(&buf[read], &pv->inbuf[pv->inbuf_cur], l);
 			pv->inbuf_cur += l;
 			pv->inbuf_pktlen -= l;
@@ -228,10 +229,11 @@ int hvsilib_get_chars(struct hvsi_priv *pv, char *buf, int count)
 	return read;
 }
 
-int hvsilib_put_chars(struct hvsi_priv *pv, const char *buf, int count)
+ssize_t hvsilib_put_chars(struct hvsi_priv *pv, const u8 *buf, size_t count)
 {
 	struct hvsi_data dp;
-	int rc, adjcount = min(count, HVSI_MAX_OUTGOING_DATA);
+	size_t adjcount = min_t(size_t, count, HVSI_MAX_OUTGOING_DATA);
+	int rc;
 
 	if (WARN_ON(!pv))
 		return -ENODEV;
@@ -411,9 +413,9 @@ void hvsilib_close(struct hvsi_priv *pv, struct hvc_struct *hp)
 }
 
 void hvsilib_init(struct hvsi_priv *pv,
-		  int (*get_chars)(uint32_t termno, char *buf, int count),
-		  int (*put_chars)(uint32_t termno, const char *buf,
-				   int count),
+		  ssize_t (*get_chars)(uint32_t termno, u8 *buf, size_t count),
+		  ssize_t (*put_chars)(uint32_t termno, const u8 *buf,
+				       size_t count),
 		  int termno, int is_console)
 {
 	memset(pv, 0, sizeof(*pv));
diff --git a/drivers/tty/ipwireless/main.h b/drivers/tty/ipwireless/main.h
index 73818bb64416..a5728a5b3f83 100644
--- a/drivers/tty/ipwireless/main.h
+++ b/drivers/tty/ipwireless/main.h
@@ -49,9 +49,6 @@ struct ipw_dev {
 
 	void __iomem *common_memory;
 
-	/* Reference to attribute memory, containing CIS data */
-	void *attribute_memory;
-
 	/* Hardware context */
 	struct ipw_hardware *hardware;
 	/* Network layer context */
diff --git a/drivers/tty/mips_ejtag_fdc.c b/drivers/tty/mips_ejtag_fdc.c
index 369ec71c24ef..aac80b69a069 100644
--- a/drivers/tty/mips_ejtag_fdc.c
+++ b/drivers/tty/mips_ejtag_fdc.c
@@ -213,16 +213,16 @@ struct fdc_word {
  */
 
 /* ranges >= 1 && sizes[0] >= 1 */
-static struct fdc_word mips_ejtag_fdc_encode(const char **ptrs,
+static struct fdc_word mips_ejtag_fdc_encode(const u8 **ptrs,
 					     unsigned int *sizes,
 					     unsigned int ranges)
 {
 	struct fdc_word word = { 0, 0 };
-	const char **ptrs_end = ptrs + ranges;
+	const u8 **ptrs_end = ptrs + ranges;
 
 	for (; ptrs < ptrs_end; ++ptrs) {
-		const char *ptr = *(ptrs++);
-		const char *end = ptr + *(sizes++);
+		const u8 *ptr = *(ptrs++);
+		const u8 *end = ptr + *(sizes++);
 
 		for (; ptr < end; ++ptr) {
 			word.word |= (u8)*ptr << (8*word.bytes);
@@ -417,7 +417,7 @@ static unsigned int mips_ejtag_fdc_put_chan(struct mips_ejtag_fdc_tty *priv,
 {
 	struct mips_ejtag_fdc_tty_port *dport;
 	struct tty_struct *tty;
-	const char *ptrs[2];
+	const u8 *ptrs[2];
 	unsigned int sizes[2] = { 0 };
 	struct fdc_word word = { .bytes = 0 };
 	unsigned long flags;
diff --git a/drivers/tty/moxa.c b/drivers/tty/moxa.c
index bf3f87ba3a92..ebaada8db929 100644
--- a/drivers/tty/moxa.c
+++ b/drivers/tty/moxa.c
@@ -514,7 +514,7 @@ static void MoxaPortLineCtrl(struct moxa_port *, bool, bool);
 static void MoxaPortFlowCtrl(struct moxa_port *, int, int, int, int, int);
 static int MoxaPortLineStatus(struct moxa_port *);
 static void MoxaPortFlushData(struct moxa_port *, int);
-static int MoxaPortWriteData(struct tty_struct *, const unsigned char *, int);
+static ssize_t MoxaPortWriteData(struct tty_struct *, const u8 *, size_t);
 static int MoxaPortReadData(struct moxa_port *);
 static unsigned int MoxaPortTxQueue(struct moxa_port *);
 static int MoxaPortRxQueue(struct moxa_port *);
@@ -1933,10 +1933,10 @@ static void MoxaPortFlushData(struct moxa_port *port, int mode)
  *
  *      Function 20:    Write data.
  *      Syntax:
- *      int  MoxaPortWriteData(int port, unsigned char * buffer, int length);
+ *      ssize_t  MoxaPortWriteData(int port, u8 *buffer, size_t length);
  *           int port           : port number (0 - 127)
- *           unsigned char * buffer     : pointer to write data buffer.
- *           int length         : write data length
+ *           u8 *buffer         : pointer to write data buffer.
+ *           size_t length      : write data length
  *
  *           return:    0 - length      : real write data length
  *
@@ -2163,11 +2163,12 @@ static int MoxaPortLineStatus(struct moxa_port *port)
 	return val;
 }
 
-static int MoxaPortWriteData(struct tty_struct *tty, const u8 *buffer, int len)
+static ssize_t MoxaPortWriteData(struct tty_struct *tty, const u8 *buffer,
+				 size_t len)
 {
 	struct moxa_port *port = tty->driver_data;
 	void __iomem *baseAddr, *ofsAddr, *ofs;
-	unsigned int c, total;
+	size_t c, total;
 	u16 head, tail, tx_mask, spage, epage;
 	u16 pageno, pageofs, bufhead;
 
@@ -2224,8 +2225,8 @@ static int MoxaPortWriteData(struct tty_struct *tty, const u8 *buffer, int len)
 static int MoxaPortReadData(struct moxa_port *port)
 {
 	struct tty_struct *tty = port->port.tty;
-	unsigned char *dst;
 	void __iomem *baseAddr, *ofsAddr, *ofs;
+	u8 *dst;
 	unsigned int count, len, total;
 	u16 tail, rx_mask, spage, epage;
 	u16 pageno, pageofs, bufhead, head;
diff --git a/drivers/tty/mxser.c b/drivers/tty/mxser.c
index 6ce7f259968f..458bb1280ebf 100644
--- a/drivers/tty/mxser.c
+++ b/drivers/tty/mxser.c
@@ -264,7 +264,7 @@ struct mxser_port {
 	u8 rx_low_water;
 	int type;		/* UART type */
 
-	unsigned char x_char;	/* xon/xoff character */
+	u8 x_char;		/* xon/xoff character */
 	u8 IER;			/* Interrupt Enable Register */
 	u8 MCR;			/* Modem control register */
 	u8 FCR;			/* FIFO control register */
@@ -905,7 +905,7 @@ static ssize_t mxser_write(struct tty_struct *tty, const u8 *buf, size_t count)
 {
 	struct mxser_port *info = tty->driver_data;
 	unsigned long flags;
-	int written;
+	size_t written;
 	bool is_empty;
 
 	spin_lock_irqsave(&info->slock, flags);
@@ -1521,7 +1521,7 @@ static u8 mxser_receive_chars_old(struct tty_struct *tty,
 			if (++ignored > 100)
 				break;
 		} else {
-			char flag = 0;
+			u8 flag = 0;
 			if (status & UART_LSR_BRK_ERROR_BITS) {
 				if (status & UART_LSR_BI) {
 					flag = TTY_BREAK;
@@ -1585,7 +1585,7 @@ static void mxser_transmit_chars(struct tty_struct *tty, struct mxser_port *port
 
 	count = port->xmit_fifo_size;
 	do {
-		unsigned char c;
+		u8 c;
 
 		if (!kfifo_get(&port->port.xmit_fifo, &c))
 			break;
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index a3ab3946e4ad..4036566febcb 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -124,8 +124,8 @@ struct gsm_msg {
 	u8 addr;		/* DLCI address + flags */
 	u8 ctrl;		/* Control byte + flags */
 	unsigned int len;	/* Length of data block (can be zero) */
-	unsigned char *data;	/* Points into buffer but not at the start */
-	unsigned char buffer[];
+	u8 *data;	/* Points into buffer but not at the start */
+	u8 buffer[];
 };
 
 enum gsm_dlci_state {
@@ -283,7 +283,7 @@ struct gsm_mux {
 	/* Bits for GSM mode decoding */
 
 	/* Framing Layer */
-	unsigned char *buf;
+	u8 *buf;
 	enum gsm_mux_state state;
 	unsigned int len;
 	unsigned int address;
@@ -2856,7 +2856,7 @@ invalid:
  *	Receive bytes in gsm mode 0
  */
 
-static void gsm0_receive(struct gsm_mux *gsm, unsigned char c)
+static void gsm0_receive(struct gsm_mux *gsm, u8 c)
 {
 	unsigned int len;
 
@@ -2947,7 +2947,7 @@ static void gsm0_receive(struct gsm_mux *gsm, unsigned char c)
  *	Receive bytes in mode 1 (Advanced option)
  */
 
-static void gsm1_receive(struct gsm_mux *gsm, unsigned char c)
+static void gsm1_receive(struct gsm_mux *gsm, u8 c)
 {
 	/* handle XON/XOFF */
 	if ((c & ISO_IEC_646_MASK) == XON) {
@@ -3541,7 +3541,7 @@ static void gsmld_receive_buf(struct tty_struct *tty, const u8 *cp,
 			      const u8 *fp, size_t count)
 {
 	struct gsm_mux *gsm = tty->disc_data;
-	char flags = TTY_NORMAL;
+	u8 flags = TTY_NORMAL;
 
 	if (debug & DBG_DATA)
 		gsm_hex_dump_bytes(__func__, cp, count);
@@ -3711,7 +3711,7 @@ static ssize_t gsmld_write(struct tty_struct *tty, struct file *file,
 {
 	struct gsm_mux *gsm = tty->disc_data;
 	unsigned long flags;
-	int space;
+	size_t space;
 	int ret;
 
 	if (!gsm)
@@ -3909,8 +3909,7 @@ static void gsm_mux_net_tx_timeout(struct net_device *net, unsigned int txqueue)
 	net->stats.tx_errors++;
 }
 
-static void gsm_mux_rx_netchar(struct gsm_dlci *dlci,
-				const unsigned char *in_buf, int size)
+static void gsm_mux_rx_netchar(struct gsm_dlci *dlci, const u8 *in_buf, int size)
 {
 	struct net_device *net = dlci->net;
 	struct sk_buff *skb;
diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c
index a670419efe79..1615f074ab86 100644
--- a/drivers/tty/n_hdlc.c
+++ b/drivers/tty/n_hdlc.c
@@ -109,8 +109,8 @@
 
 struct n_hdlc_buf {
 	struct list_head  list_item;
-	int		  count;
-	char		  buf[];
+	size_t		  count;
+	u8		  buf[];
 };
 
 struct n_hdlc_buf_list {
@@ -263,9 +263,9 @@ static int n_hdlc_tty_open(struct tty_struct *tty)
  */
 static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty)
 {
-	register int actual;
 	unsigned long flags;
 	struct n_hdlc_buf *tbuf;
+	ssize_t actual;
 
 check_again:
 
@@ -281,7 +281,7 @@ check_again:
 
 	tbuf = n_hdlc_buf_get(&n_hdlc->tx_buf_list);
 	while (tbuf) {
-		pr_debug("sending frame %p, count=%d\n", tbuf, tbuf->count);
+		pr_debug("sending frame %p, count=%zu\n", tbuf, tbuf->count);
 
 		/* Send the next block of data to device */
 		set_bit(TTY_DO_WRITE_WAKEUP, &tty->flags);
@@ -521,9 +521,9 @@ static ssize_t n_hdlc_tty_write(struct tty_struct *tty, struct file *file,
 				const u8 *data, size_t count)
 {
 	struct n_hdlc *n_hdlc = tty->disc_data;
-	int error = 0;
 	DECLARE_WAITQUEUE(wait, current);
 	struct n_hdlc_buf *tbuf;
+	ssize_t error = 0;
 
 	pr_debug("%s() called count=%zd\n", __func__, count);
 
diff --git a/drivers/tty/nozomi.c b/drivers/tty/nozomi.c
index 02cd40147b3a..e28a921c1637 100644
--- a/drivers/tty/nozomi.c
+++ b/drivers/tty/nozomi.c
@@ -65,24 +65,8 @@ do {							\
 #define DBG3(args...) DBG_(0x04, ##args)
 #define DBG4(args...) DBG_(0x08, ##args)
 
-/* TODO: rewrite to optimize macros... */
-
 #define TMP_BUF_MAX 256
 
-#define DUMP(buf__, len__)						\
-	do {								\
-		char tbuf[TMP_BUF_MAX] = {0};				\
-		if (len__ > 1) {					\
-			u32 data_len = min_t(u32, len__, TMP_BUF_MAX);	\
-			strscpy(tbuf, buf__, data_len);			\
-			if (tbuf[data_len - 2] == '\r')			\
-				tbuf[data_len - 2] = 'r';		\
-			DBG1("SENDING: '%s' (%d+n)", tbuf, len__);	\
-		} else {						\
-			DBG1("SENDING: '%s' (%d)", tbuf, len__);	\
-		}							\
-	} while (0)
-
 /*    Defines */
 #define NOZOMI_NAME		"nozomi"
 #define NOZOMI_NAME_TTY		"nozomi_tty"
@@ -754,8 +738,6 @@ static int send_data(enum port_type index, struct nozomi *dc)
 		return 0;
 	}
 
-	/* DUMP(buf, size); */
-
 	/* Write length + data */
 	write_mem32(addr, (u32 *) &size, 4);
 	write_mem32(addr + 4, (u32 *) dc->send_buf, size);
@@ -801,11 +783,10 @@ static int receive_data(enum port_type index, struct nozomi *dc)
 			tty_insert_flip_char(&port->port, buf[0], TTY_NORMAL);
 			size = 0;
 		} else if (size < RECEIVE_BUF_MAX) {
-			size -= tty_insert_flip_string(&port->port,
-					(char *)buf, size);
+			size -= tty_insert_flip_string(&port->port, buf, size);
 		} else {
-			i = tty_insert_flip_string(&port->port,
-					(char *)buf, RECEIVE_BUF_MAX);
+			i = tty_insert_flip_string(&port->port, buf,
+						   RECEIVE_BUF_MAX);
 			size -= i;
 			offset += i;
 		}
@@ -1602,10 +1583,10 @@ static void ntty_hangup(struct tty_struct *tty)
 static ssize_t ntty_write(struct tty_struct *tty, const u8 *buffer,
 			  size_t count)
 {
-	int rval = -EINVAL;
 	struct nozomi *dc = get_dc_by_tty(tty);
 	struct port *port = tty->driver_data;
 	unsigned long flags;
+	size_t rval;
 
 	if (!dc || !port)
 		return -ENODEV;
diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c
index a5fdaf5e148e..822a5cd05566 100644
--- a/drivers/tty/serdev/core.c
+++ b/drivers/tty/serdev/core.c
@@ -77,7 +77,7 @@ static bool is_serdev_device(const struct device *dev)
 static void serdev_ctrl_release(struct device *dev)
 {
 	struct serdev_controller *ctrl = to_serdev_controller(dev);
-	ida_simple_remove(&ctrl_ida, ctrl->nr);
+	ida_free(&ctrl_ida, ctrl->nr);
 	kfree(ctrl);
 }
 
@@ -225,8 +225,7 @@ EXPORT_SYMBOL_GPL(serdev_device_write_wakeup);
  * Return: The number of bytes written (less than count if not enough room in
  * the write buffer), or a negative errno on errors.
  */
-int serdev_device_write_buf(struct serdev_device *serdev,
-			    const unsigned char *buf, size_t count)
+int serdev_device_write_buf(struct serdev_device *serdev, const u8 *buf, size_t count)
 {
 	struct serdev_controller *ctrl = serdev->ctrl;
 
@@ -259,13 +258,12 @@ EXPORT_SYMBOL_GPL(serdev_device_write_buf);
  * -ETIMEDOUT or -ERESTARTSYS if interrupted before any bytes were written, or
  * a negative errno on errors.
  */
-int serdev_device_write(struct serdev_device *serdev,
-			const unsigned char *buf, size_t count,
-			long timeout)
+ssize_t serdev_device_write(struct serdev_device *serdev, const u8 *buf,
+			    size_t count, long timeout)
 {
 	struct serdev_controller *ctrl = serdev->ctrl;
-	int written = 0;
-	int ret;
+	size_t written = 0;
+	ssize_t ret;
 
 	if (!ctrl || !ctrl->ops->write_buf || !serdev->ops->write_wakeup)
 		return -EINVAL;
@@ -468,6 +466,7 @@ EXPORT_SYMBOL_GPL(serdev_device_alloc);
 
 /**
  * serdev_controller_alloc() - Allocate a new serdev controller
+ * @host:	serial port hardware controller device
  * @parent:	parent device
  * @size:	size of private data
  *
@@ -476,8 +475,9 @@ EXPORT_SYMBOL_GPL(serdev_device_alloc);
  * The allocated private data region may be accessed via
  * serdev_controller_get_drvdata()
  */
-struct serdev_controller *serdev_controller_alloc(struct device *parent,
-					      size_t size)
+struct serdev_controller *serdev_controller_alloc(struct device *host,
+						  struct device *parent,
+						  size_t size)
 {
 	struct serdev_controller *ctrl;
 	int id;
@@ -489,7 +489,7 @@ struct serdev_controller *serdev_controller_alloc(struct device *parent,
 	if (!ctrl)
 		return NULL;
 
-	id = ida_simple_get(&ctrl_ida, 0, 0, GFP_KERNEL);
+	id = ida_alloc(&ctrl_ida, GFP_KERNEL);
 	if (id < 0) {
 		dev_err(parent,
 			"unable to allocate serdev controller identifier.\n");
@@ -502,7 +502,8 @@ struct serdev_controller *serdev_controller_alloc(struct device *parent,
 	ctrl->dev.type = &serdev_ctrl_type;
 	ctrl->dev.bus = &serdev_bus_type;
 	ctrl->dev.parent = parent;
-	device_set_node(&ctrl->dev, dev_fwnode(parent));
+	ctrl->host = host;
+	device_set_node(&ctrl->dev, dev_fwnode(host));
 	serdev_controller_set_drvdata(ctrl, &ctrl[1]);
 
 	dev_set_name(&ctrl->dev, "serial%d", id);
@@ -665,7 +666,7 @@ static int acpi_serdev_check_resources(struct serdev_controller *ctrl,
 		acpi_get_parent(adev->handle, &lookup.controller_handle);
 
 	/* Make sure controller and ResourceSource handle match */
-	if (!device_match_acpi_handle(ctrl->dev.parent, lookup.controller_handle))
+	if (!device_match_acpi_handle(ctrl->host, lookup.controller_handle))
 		return -ENODEV;
 
 	return 0;
@@ -730,7 +731,7 @@ static int acpi_serdev_register_devices(struct serdev_controller *ctrl)
 	bool skip;
 	int ret;
 
-	if (!has_acpi_companion(ctrl->dev.parent))
+	if (!has_acpi_companion(ctrl->host))
 		return -ENODEV;
 
 	/*
@@ -739,7 +740,7 @@ static int acpi_serdev_register_devices(struct serdev_controller *ctrl)
 	 * succeed in this case, so that the proper serdev devices can be
 	 * added "manually" later.
 	 */
-	ret = acpi_quirk_skip_serdev_enumeration(ctrl->dev.parent, &skip);
+	ret = acpi_quirk_skip_serdev_enumeration(ctrl->host, &skip);
 	if (ret)
 		return ret;
 	if (skip)
diff --git a/drivers/tty/serdev/serdev-ttyport.c b/drivers/tty/serdev/serdev-ttyport.c
index e3856814ce77..e94e090cf0a1 100644
--- a/drivers/tty/serdev/serdev-ttyport.c
+++ b/drivers/tty/serdev/serdev-ttyport.c
@@ -74,7 +74,7 @@ static const struct tty_port_client_operations client_ops = {
  * Callback functions from the serdev core.
  */
 
-static int ttyport_write_buf(struct serdev_controller *ctrl, const unsigned char *data, size_t len)
+static ssize_t ttyport_write_buf(struct serdev_controller *ctrl, const u8 *data, size_t len)
 {
 	struct serport *serport = serdev_controller_get_drvdata(ctrl);
 	struct tty_struct *tty = serport->tty;
@@ -274,6 +274,7 @@ static const struct serdev_controller_ops ctrl_ops = {
 };
 
 struct device *serdev_tty_port_register(struct tty_port *port,
+					struct device *host,
 					struct device *parent,
 					struct tty_driver *drv, int idx)
 {
@@ -284,7 +285,7 @@ struct device *serdev_tty_port_register(struct tty_port *port,
 	if (!port || !drv || !parent)
 		return ERR_PTR(-ENODEV);
 
-	ctrl = serdev_controller_alloc(parent, sizeof(struct serport));
+	ctrl = serdev_controller_alloc(host, parent, sizeof(struct serport));
 	if (!ctrl)
 		return ERR_PTR(-ENOMEM);
 	serport = serdev_controller_get_drvdata(ctrl);
diff --git a/drivers/tty/serial/8250/8250_aspeed_vuart.c b/drivers/tty/serial/8250/8250_aspeed_vuart.c
index d7482ae33a1c..8c2aaf7af7b7 100644
--- a/drivers/tty/serial/8250/8250_aspeed_vuart.c
+++ b/drivers/tty/serial/8250/8250_aspeed_vuart.c
@@ -566,7 +566,7 @@ err_sysfs_remove:
 	return rc;
 }
 
-static int aspeed_vuart_remove(struct platform_device *pdev)
+static void aspeed_vuart_remove(struct platform_device *pdev)
 {
 	struct aspeed_vuart *vuart = platform_get_drvdata(pdev);
 
@@ -574,8 +574,6 @@ static int aspeed_vuart_remove(struct platform_device *pdev)
 	aspeed_vuart_set_enabled(vuart, false);
 	serial8250_unregister_port(vuart->line);
 	sysfs_remove_group(&vuart->dev->kobj, &aspeed_vuart_attr_group);
-
-	return 0;
 }
 
 static const struct of_device_id aspeed_vuart_table[] = {
@@ -590,7 +588,7 @@ static struct platform_driver aspeed_vuart_driver = {
 		.of_match_table = aspeed_vuart_table,
 	},
 	.probe = aspeed_vuart_probe,
-	.remove = aspeed_vuart_remove,
+	.remove_new = aspeed_vuart_remove,
 };
 
 module_platform_driver(aspeed_vuart_driver);
diff --git a/drivers/tty/serial/8250/8250_bcm2835aux.c b/drivers/tty/serial/8250/8250_bcm2835aux.c
index 15a2387a5b25..beac6b340ace 100644
--- a/drivers/tty/serial/8250/8250_bcm2835aux.c
+++ b/drivers/tty/serial/8250/8250_bcm2835aux.c
@@ -119,6 +119,8 @@ static int bcm2835aux_serial_probe(struct platform_device *pdev)
 
 	/* get the clock - this also enables the HW */
 	data->clk = devm_clk_get_optional(&pdev->dev, NULL);
+	if (IS_ERR(data->clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(data->clk), "could not get clk\n");
 
 	/* get the interrupt */
 	ret = platform_get_irq(pdev, 0);
@@ -195,14 +197,12 @@ dis_clk:
 	return ret;
 }
 
-static int bcm2835aux_serial_remove(struct platform_device *pdev)
+static void bcm2835aux_serial_remove(struct platform_device *pdev)
 {
 	struct bcm2835aux_data *data = platform_get_drvdata(pdev);
 
 	serial8250_unregister_port(data->line);
 	clk_disable_unprepare(data->clk);
-
-	return 0;
 }
 
 static const struct bcm2835_aux_serial_driver_data bcm2835_acpi_data = {
@@ -228,7 +228,7 @@ static struct platform_driver bcm2835aux_serial_driver = {
 		.acpi_match_table = bcm2835aux_serial_acpi_match,
 	},
 	.probe  = bcm2835aux_serial_probe,
-	.remove = bcm2835aux_serial_remove,
+	.remove_new = bcm2835aux_serial_remove,
 };
 module_platform_driver(bcm2835aux_serial_driver);
 
diff --git a/drivers/tty/serial/8250/8250_bcm7271.c b/drivers/tty/serial/8250/8250_bcm7271.c
index 55dea2539c47..504c4c020857 100644
--- a/drivers/tty/serial/8250/8250_bcm7271.c
+++ b/drivers/tty/serial/8250/8250_bcm7271.c
@@ -1121,7 +1121,7 @@ release_dma:
 	return ret;
 }
 
-static int brcmuart_remove(struct platform_device *pdev)
+static void brcmuart_remove(struct platform_device *pdev)
 {
 	struct brcmuart_priv *priv = platform_get_drvdata(pdev);
 
@@ -1131,7 +1131,6 @@ static int brcmuart_remove(struct platform_device *pdev)
 	brcmuart_free_bufs(&pdev->dev, priv);
 	if (priv->dma_enabled)
 		brcmuart_arbitration(priv, 0);
-	return 0;
 }
 
 static int __maybe_unused brcmuart_suspend(struct device *dev)
@@ -1207,7 +1206,7 @@ static struct platform_driver brcmuart_platform_driver = {
 		.of_match_table = brcmuart_dt_ids,
 	},
 	.probe		= brcmuart_probe,
-	.remove		= brcmuart_remove,
+	.remove_new	= brcmuart_remove,
 };
 
 static int __init brcmuart_init(void)
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 912733151858..b62ad9006780 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -883,7 +883,7 @@ static int serial8250_probe(struct platform_device *dev)
 /*
  * Remove serial ports registered against a platform device.
  */
-static int serial8250_remove(struct platform_device *dev)
+static void serial8250_remove(struct platform_device *dev)
 {
 	int i;
 
@@ -893,7 +893,6 @@ static int serial8250_remove(struct platform_device *dev)
 		if (up->port.dev == &dev->dev)
 			serial8250_unregister_port(i);
 	}
-	return 0;
 }
 
 static int serial8250_suspend(struct platform_device *dev, pm_message_t state)
@@ -926,7 +925,7 @@ static int serial8250_resume(struct platform_device *dev)
 
 static struct platform_driver serial8250_isa_driver = {
 	.probe		= serial8250_probe,
-	.remove		= serial8250_remove,
+	.remove_new	= serial8250_remove,
 	.suspend	= serial8250_suspend,
 	.resume		= serial8250_resume,
 	.driver		= {
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index e6218766d0c8..c1d43f040c43 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -357,9 +357,9 @@ static void dw8250_set_termios(struct uart_port *p, struct ktermios *termios,
 	long rate;
 	int ret;
 
-	clk_disable_unprepare(d->clk);
 	rate = clk_round_rate(d->clk, newrate);
-	if (rate > 0) {
+	if (rate > 0 && p->uartclk != rate) {
+		clk_disable_unprepare(d->clk);
 		/*
 		 * Note that any clock-notifer worker will block in
 		 * serial8250_update_uartclk() until we are done.
@@ -367,8 +367,8 @@ static void dw8250_set_termios(struct uart_port *p, struct ktermios *termios,
 		ret = clk_set_rate(d->clk, newrate);
 		if (!ret)
 			p->uartclk = rate;
+		clk_prepare_enable(d->clk);
 	}
-	clk_prepare_enable(d->clk);
 
 	dw8250_do_set_termios(p, termios, old);
 }
@@ -663,7 +663,7 @@ static int dw8250_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int dw8250_remove(struct platform_device *pdev)
+static void dw8250_remove(struct platform_device *pdev)
 {
 	struct dw8250_data *data = platform_get_drvdata(pdev);
 	struct device *dev = &pdev->dev;
@@ -680,8 +680,6 @@ static int dw8250_remove(struct platform_device *pdev)
 
 	pm_runtime_disable(dev);
 	pm_runtime_put_noidle(dev);
-
-	return 0;
 }
 
 static int dw8250_suspend(struct device *dev)
@@ -790,7 +788,7 @@ static struct platform_driver dw8250_platform_driver = {
 		.acpi_match_table = dw8250_acpi_match,
 	},
 	.probe			= dw8250_probe,
-	.remove			= dw8250_remove,
+	.remove_new		= dw8250_remove,
 };
 
 module_platform_driver(dw8250_platform_driver);
diff --git a/drivers/tty/serial/8250/8250_dwlib.c b/drivers/tty/serial/8250/8250_dwlib.c
index 84843e204a5e..3e33ddf7bc80 100644
--- a/drivers/tty/serial/8250/8250_dwlib.c
+++ b/drivers/tty/serial/8250/8250_dwlib.c
@@ -259,17 +259,6 @@ void dw8250_setup_port(struct uart_port *p)
 	}
 	up->capabilities |= UART_CAP_NOTEMT;
 
-	/*
-	 * If the Component Version Register returns zero, we know that
-	 * ADDITIONAL_FEATURES are not enabled. No need to go any further.
-	 */
-	reg = dw8250_readl_ext(p, DW_UART_UCV);
-	if (!reg)
-		return;
-
-	dev_dbg(p->dev, "Designware UART version %c.%c%c\n",
-		(reg >> 24) & 0xff, (reg >> 16) & 0xff, (reg >> 8) & 0xff);
-
 	/* Preserve value written by firmware or bootloader  */
 	old_dlf = dw8250_readl_ext(p, DW_UART_DLF);
 	dw8250_writel_ext(p, DW_UART_DLF, ~0U);
@@ -282,6 +271,11 @@ void dw8250_setup_port(struct uart_port *p)
 		p->set_divisor = dw8250_set_divisor;
 	}
 
+	reg = dw8250_readl_ext(p, DW_UART_UCV);
+	if (reg)
+		dev_dbg(p->dev, "Designware UART version %c.%c%c\n",
+			(reg >> 24) & 0xff, (reg >> 16) & 0xff, (reg >> 8) & 0xff);
+
 	reg = dw8250_readl_ext(p, DW_UART_CPR);
 	if (!reg) {
 		reg = data->pdata->cpr_val;
diff --git a/drivers/tty/serial/8250/8250_em.c b/drivers/tty/serial/8250/8250_em.c
index ef5019e944ea..a754755100ff 100644
--- a/drivers/tty/serial/8250/8250_em.c
+++ b/drivers/tty/serial/8250/8250_em.c
@@ -200,12 +200,11 @@ static int serial8250_em_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int serial8250_em_remove(struct platform_device *pdev)
+static void serial8250_em_remove(struct platform_device *pdev)
 {
 	struct serial8250_em_priv *priv = platform_get_drvdata(pdev);
 
 	serial8250_unregister_port(priv->line);
-	return 0;
 }
 
 static const struct of_device_id serial8250_em_dt_ids[] = {
@@ -220,7 +219,7 @@ static struct platform_driver serial8250_em_platform_driver = {
 		.of_match_table = serial8250_em_dt_ids,
 	},
 	.probe			= serial8250_em_probe,
-	.remove			= serial8250_em_remove,
+	.remove_new		= serial8250_em_remove,
 };
 
 module_platform_driver(serial8250_em_platform_driver);
diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c
index 6085d356ad86..23366f868ae3 100644
--- a/drivers/tty/serial/8250/8250_exar.c
+++ b/drivers/tty/serial/8250/8250_exar.c
@@ -480,7 +480,7 @@ static int sealevel_rs485_config(struct uart_port *port, struct ktermios *termio
 }
 
 static const struct serial_rs485 generic_rs485_supported = {
-	.flags = SER_RS485_ENABLED,
+	.flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND,
 };
 
 static const struct exar8250_platform exar8250_default_platform = {
@@ -524,7 +524,8 @@ static int iot2040_rs485_config(struct uart_port *port, struct ktermios *termios
 }
 
 static const struct serial_rs485 iot2040_rs485_supported = {
-	.flags = SER_RS485_ENABLED | SER_RS485_RX_DURING_TX | SER_RS485_TERMINATE_BUS,
+	.flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND |
+		 SER_RS485_RX_DURING_TX | SER_RS485_TERMINATE_BUS,
 };
 
 static const struct property_entry iot2040_gpio_properties[] = {
diff --git a/drivers/tty/serial/8250/8250_fsl.c b/drivers/tty/serial/8250/8250_fsl.c
index f522eb5026c9..b4ed442082a8 100644
--- a/drivers/tty/serial/8250/8250_fsl.c
+++ b/drivers/tty/serial/8250/8250_fsl.c
@@ -51,7 +51,8 @@ int fsl8250_handle_irq(struct uart_port *port)
 	 * immediately and interrupt the CPU again. The hardware clears LSR.BI
 	 * when the next valid char is read.)
 	 */
-	if (unlikely(up->lsr_saved_flags & UART_LSR_BI)) {
+	if (unlikely((iir & UART_IIR_ID) == UART_IIR_RLSI &&
+		     (up->lsr_saved_flags & UART_LSR_BI))) {
 		up->lsr_saved_flags &= ~UART_LSR_BI;
 		port->serial_in(port, UART_RX);
 		uart_port_unlock_irqrestore(&up->port, flags);
@@ -159,12 +160,11 @@ static int fsl8250_acpi_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int fsl8250_acpi_remove(struct platform_device *pdev)
+static void fsl8250_acpi_remove(struct platform_device *pdev)
 {
 	struct fsl8250_data *data = platform_get_drvdata(pdev);
 
 	serial8250_unregister_port(data->line);
-	return 0;
 }
 
 static const struct acpi_device_id fsl_8250_acpi_id[] = {
@@ -179,7 +179,7 @@ static struct platform_driver fsl8250_platform_driver = {
 		.acpi_match_table	= ACPI_PTR(fsl_8250_acpi_id),
 	},
 	.probe			= fsl8250_acpi_probe,
-	.remove			= fsl8250_acpi_remove,
+	.remove_new		= fsl8250_acpi_remove,
 };
 
 module_platform_driver(fsl8250_platform_driver);
diff --git a/drivers/tty/serial/8250/8250_ingenic.c b/drivers/tty/serial/8250/8250_ingenic.c
index 4c4c4da73ad0..a12f737924c0 100644
--- a/drivers/tty/serial/8250/8250_ingenic.c
+++ b/drivers/tty/serial/8250/8250_ingenic.c
@@ -320,14 +320,13 @@ out:
 	return err;
 }
 
-static int ingenic_uart_remove(struct platform_device *pdev)
+static void ingenic_uart_remove(struct platform_device *pdev)
 {
 	struct ingenic_uart_data *data = platform_get_drvdata(pdev);
 
 	serial8250_unregister_port(data->line);
 	clk_disable_unprepare(data->clk_module);
 	clk_disable_unprepare(data->clk_baud);
-	return 0;
 }
 
 static const struct ingenic_uart_config jz4740_uart_config = {
@@ -368,7 +367,7 @@ static struct platform_driver ingenic_uart_platform_driver = {
 		.of_match_table	= of_match,
 	},
 	.probe			= ingenic_uart_probe,
-	.remove			= ingenic_uart_remove,
+	.remove_new		= ingenic_uart_remove,
 };
 
 module_platform_driver(ingenic_uart_platform_driver);
diff --git a/drivers/tty/serial/8250/8250_ioc3.c b/drivers/tty/serial/8250/8250_ioc3.c
index d5a39e105a76..50c77c3dacf2 100644
--- a/drivers/tty/serial/8250/8250_ioc3.c
+++ b/drivers/tty/serial/8250/8250_ioc3.c
@@ -75,17 +75,16 @@ static int serial8250_ioc3_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int serial8250_ioc3_remove(struct platform_device *pdev)
+static void serial8250_ioc3_remove(struct platform_device *pdev)
 {
 	struct ioc3_8250_data *data = platform_get_drvdata(pdev);
 
 	serial8250_unregister_port(data->line);
-	return 0;
 }
 
 static struct platform_driver serial8250_ioc3_driver = {
 	.probe  = serial8250_ioc3_probe,
-	.remove = serial8250_ioc3_remove,
+	.remove_new = serial8250_ioc3_remove,
 	.driver = {
 		.name = "ioc3-serial8250",
 	}
diff --git a/drivers/tty/serial/8250/8250_lpc18xx.c b/drivers/tty/serial/8250/8250_lpc18xx.c
index 6dc85aaba5d0..8d728a6a5991 100644
--- a/drivers/tty/serial/8250/8250_lpc18xx.c
+++ b/drivers/tty/serial/8250/8250_lpc18xx.c
@@ -182,15 +182,13 @@ dis_clk_reg:
 	return ret;
 }
 
-static int lpc18xx_serial_remove(struct platform_device *pdev)
+static void lpc18xx_serial_remove(struct platform_device *pdev)
 {
 	struct lpc18xx_uart_data *data = platform_get_drvdata(pdev);
 
 	serial8250_unregister_port(data->line);
 	clk_disable_unprepare(data->clk_uart);
 	clk_disable_unprepare(data->clk_reg);
-
-	return 0;
 }
 
 static const struct of_device_id lpc18xx_serial_match[] = {
@@ -201,7 +199,7 @@ MODULE_DEVICE_TABLE(of, lpc18xx_serial_match);
 
 static struct platform_driver lpc18xx_serial_driver = {
 	.probe  = lpc18xx_serial_probe,
-	.remove = lpc18xx_serial_remove,
+	.remove_new = lpc18xx_serial_remove,
 	.driver = {
 		.name = "lpc18xx-uart",
 		.of_match_table = lpc18xx_serial_match,
diff --git a/drivers/tty/serial/8250/8250_lpss.c b/drivers/tty/serial/8250/8250_lpss.c
index 0e43bdfb7459..776ec1ef29d6 100644
--- a/drivers/tty/serial/8250/8250_lpss.c
+++ b/drivers/tty/serial/8250/8250_lpss.c
@@ -287,17 +287,14 @@ static int lpss8250_dma_setup(struct lpss8250 *lpss, struct uart_8250_port *port
 		return 0;
 	}
 
-	rx_param = devm_kzalloc(dev, sizeof(*rx_param), GFP_KERNEL);
+	rx_param = devm_kmemdup(dev, &lpss->dma_param, sizeof(*rx_param), GFP_KERNEL);
 	if (!rx_param)
 		return -ENOMEM;
 
-	tx_param = devm_kzalloc(dev, sizeof(*tx_param), GFP_KERNEL);
+	tx_param = devm_kmemdup(dev, &lpss->dma_param, sizeof(*tx_param), GFP_KERNEL);
 	if (!tx_param)
 		return -ENOMEM;
 
-	*rx_param = lpss->dma_param;
-	*tx_param = lpss->dma_param;
-
 	dma->fn = lpss8250_dma_filter;
 	dma->rx_param = rx_param;
 	dma->tx_param = tx_param;
diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c
index 23457daae8a1..9ff6bbe9c086 100644
--- a/drivers/tty/serial/8250/8250_mtk.c
+++ b/drivers/tty/serial/8250/8250_mtk.c
@@ -581,7 +581,7 @@ static int mtk8250_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int mtk8250_remove(struct platform_device *pdev)
+static void mtk8250_remove(struct platform_device *pdev)
 {
 	struct mtk8250_data *data = platform_get_drvdata(pdev);
 
@@ -591,8 +591,6 @@ static int mtk8250_remove(struct platform_device *pdev)
 
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_put_noidle(&pdev->dev);
-
-	return 0;
 }
 
 static int __maybe_unused mtk8250_suspend(struct device *dev)
@@ -652,7 +650,7 @@ static struct platform_driver mtk8250_platform_driver = {
 		.of_match_table	= mtk8250_of_match,
 	},
 	.probe			= mtk8250_probe,
-	.remove			= mtk8250_remove,
+	.remove_new		= mtk8250_remove,
 };
 module_platform_driver(mtk8250_platform_driver);
 
diff --git a/drivers/tty/serial/8250/8250_of.c b/drivers/tty/serial/8250/8250_of.c
index ef3e745bd09c..34f17a9785e7 100644
--- a/drivers/tty/serial/8250/8250_of.c
+++ b/drivers/tty/serial/8250/8250_of.c
@@ -251,7 +251,7 @@ err_free:
 /*
  * Release a line
  */
-static int of_platform_serial_remove(struct platform_device *ofdev)
+static void of_platform_serial_remove(struct platform_device *ofdev)
 {
 	struct of_serial_info *info = platform_get_drvdata(ofdev);
 
@@ -261,7 +261,6 @@ static int of_platform_serial_remove(struct platform_device *ofdev)
 	pm_runtime_put_sync(&ofdev->dev);
 	pm_runtime_disable(&ofdev->dev);
 	kfree(info);
-	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -337,7 +336,7 @@ static struct platform_driver of_platform_serial_driver = {
 		.pm = &of_serial_pm_ops,
 	},
 	.probe = of_platform_serial_probe,
-	.remove = of_platform_serial_remove,
+	.remove_new = of_platform_serial_remove,
 };
 
 module_platform_driver(of_platform_serial_driver);
diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c
index 578f35895b27..6942990a333c 100644
--- a/drivers/tty/serial/8250/8250_omap.c
+++ b/drivers/tty/serial/8250/8250_omap.c
@@ -1586,7 +1586,7 @@ err:
 	return ret;
 }
 
-static int omap8250_remove(struct platform_device *pdev)
+static void omap8250_remove(struct platform_device *pdev)
 {
 	struct omap8250_priv *priv = platform_get_drvdata(pdev);
 	struct uart_8250_port *up;
@@ -1594,7 +1594,7 @@ static int omap8250_remove(struct platform_device *pdev)
 
 	err = pm_runtime_resume_and_get(&pdev->dev);
 	if (err)
-		return err;
+		dev_err(&pdev->dev, "Failed to resume hardware\n");
 
 	up = serial8250_get_port(priv->line);
 	omap_8250_shutdown(&up->port);
@@ -1606,7 +1606,6 @@ static int omap8250_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 	cpu_latency_qos_remove_request(&priv->pm_qos_request);
 	device_init_wakeup(&pdev->dev, false);
-	return 0;
 }
 
 static int omap8250_prepare(struct device *dev)
@@ -1865,7 +1864,7 @@ static struct platform_driver omap8250_platform_driver = {
 		.of_match_table = omap8250_dt_ids,
 	},
 	.probe			= omap8250_probe,
-	.remove			= omap8250_remove,
+	.remove_new		= omap8250_remove,
 };
 module_platform_driver(omap8250_platform_driver);
 
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 614be0f13a31..0d35c77fad9e 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -19,6 +19,7 @@
 #include <linux/serial_core.h>
 #include <linux/8250_pci.h>
 #include <linux/bitops.h>
+#include <linux/bitfield.h>
 
 #include <asm/byteorder.h>
 #include <asm/io.h>
@@ -1970,6 +1971,20 @@ pci_sunix_setup(struct serial_private *priv,
 
 #define MOXA_GPIO_PIN2	BIT(2)
 
+#define MOXA_RS232	0x00
+#define MOXA_RS422	0x01
+#define MOXA_RS485_4W	0x0B
+#define MOXA_RS485_2W	0x0F
+#define MOXA_UIR_OFFSET	0x04
+#define MOXA_EVEN_RS_MASK	GENMASK(3, 0)
+#define MOXA_ODD_RS_MASK	GENMASK(7, 4)
+
+enum {
+	MOXA_SUPP_RS232 = BIT(0),
+	MOXA_SUPP_RS422 = BIT(1),
+	MOXA_SUPP_RS485 = BIT(2),
+};
+
 static bool pci_moxa_is_mini_pcie(unsigned short device)
 {
 	if (device == PCI_DEVICE_ID_MOXA_CP102N	||
@@ -1983,12 +1998,54 @@ static bool pci_moxa_is_mini_pcie(unsigned short device)
 	return false;
 }
 
+static unsigned int pci_moxa_supported_rs(struct pci_dev *dev)
+{
+	switch (dev->device & 0x0F00) {
+	case 0x0000:
+	case 0x0600:
+		return MOXA_SUPP_RS232;
+	case 0x0100:
+		return MOXA_SUPP_RS232 | MOXA_SUPP_RS422 | MOXA_SUPP_RS485;
+	case 0x0300:
+		return MOXA_SUPP_RS422 | MOXA_SUPP_RS485;
+	}
+	return 0;
+}
+
+static int pci_moxa_set_interface(const struct pci_dev *dev,
+				  unsigned int port_idx,
+				  u8 mode)
+{
+	resource_size_t iobar_addr = pci_resource_start(dev, 2);
+	resource_size_t UIR_addr = iobar_addr + MOXA_UIR_OFFSET + port_idx / 2;
+	u8 val;
+
+	val = inb(UIR_addr);
+
+	if (port_idx % 2) {
+		val &= ~MOXA_ODD_RS_MASK;
+		val |= FIELD_PREP(MOXA_ODD_RS_MASK, mode);
+	} else {
+		val &= ~MOXA_EVEN_RS_MASK;
+		val |= FIELD_PREP(MOXA_EVEN_RS_MASK, mode);
+	}
+	outb(val, UIR_addr);
+
+	return 0;
+}
+
 static int pci_moxa_init(struct pci_dev *dev)
 {
 	unsigned short device = dev->device;
 	resource_size_t iobar_addr = pci_resource_start(dev, 2);
-	unsigned int num_ports = (device & 0x00F0) >> 4;
-	u8 val;
+	unsigned int num_ports = (device & 0x00F0) >> 4, i;
+	u8 val, init_mode = MOXA_RS232;
+
+	if (!(pci_moxa_supported_rs(dev) & MOXA_SUPP_RS232)) {
+		init_mode = MOXA_RS422;
+	}
+	for (i = 0; i < num_ports; ++i)
+		pci_moxa_set_interface(dev, i, init_mode);
 
 	/*
 	 * Enable hardware buffer to prevent break signal output when system boots up.
diff --git a/drivers/tty/serial/8250/8250_pci1xxxx.c b/drivers/tty/serial/8250/8250_pci1xxxx.c
index 9f9e21981929..2dda737b1660 100644
--- a/drivers/tty/serial/8250/8250_pci1xxxx.c
+++ b/drivers/tty/serial/8250/8250_pci1xxxx.c
@@ -9,15 +9,21 @@
 
 #include <linux/bitfield.h>
 #include <linux/bitops.h>
+#include <linux/delay.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/serial_core.h>
+#include <linux/serial_reg.h>
+#include <linux/serial_8250.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/units.h>
 #include <linux/tty.h>
+#include <linux/tty_flip.h>
+#include <linux/8250_pci.h>
 
 #include <asm/byteorder.h>
 
@@ -52,6 +58,17 @@
 #define PCI_SUBDEVICE_ID_EFAR_PCI11400		PCI_DEVICE_ID_EFAR_PCI11400
 #define PCI_SUBDEVICE_ID_EFAR_PCI11414		PCI_DEVICE_ID_EFAR_PCI11414
 
+#define UART_SYSTEM_ADDR_BASE			0x1000
+#define UART_DEV_REV_REG			(UART_SYSTEM_ADDR_BASE + 0x00)
+#define UART_DEV_REV_MASK			GENMASK(7, 0)
+#define UART_SYSLOCK_REG			(UART_SYSTEM_ADDR_BASE + 0xA0)
+#define UART_SYSLOCK				BIT(2)
+#define SYSLOCK_SLEEP_TIMEOUT			100
+#define SYSLOCK_RETRY_CNT			1000
+
+#define UART_RX_BYTE_FIFO			0x00
+#define UART_FIFO_CTL				0x02
+
 #define UART_ACTV_REG				0x11
 #define UART_BLOCK_SET_ACTIVE			BIT(0)
 
@@ -82,8 +99,59 @@
 #define UART_RESET_REG				0x94
 #define UART_RESET_D3_RESET_DISABLE		BIT(16)
 
+#define UART_BURST_STATUS_REG			0x9C
+#define UART_RX_BURST_FIFO			0xA4
+
 #define MAX_PORTS				4
 #define PORT_OFFSET				0x100
+#define RX_BUF_SIZE				512
+#define UART_BYTE_SIZE                          1
+#define UART_BURST_SIZE				4
+
+#define UART_BST_STAT_RX_COUNT_MASK		0x00FF
+#define UART_BST_STAT_IIR_INT_PEND		0x100000
+#define UART_LSR_OVERRUN_ERR_CLR		0x43
+#define UART_BST_STAT_LSR_RX_MASK		0x9F000000
+#define UART_BST_STAT_LSR_RX_ERR_MASK		0x9E000000
+#define UART_BST_STAT_LSR_OVERRUN_ERR		0x2000000
+#define UART_BST_STAT_LSR_PARITY_ERR		0x4000000
+#define UART_BST_STAT_LSR_FRAME_ERR		0x8000000
+
+struct pci1xxxx_8250 {
+	unsigned int nr;
+	u8 dev_rev;
+	u8 pad[3];
+	void __iomem *membase;
+	int line[] __counted_by(nr);
+};
+
+static const struct serial_rs485 pci1xxxx_rs485_supported = {
+	.flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND |
+		 SER_RS485_RTS_AFTER_SEND,
+	.delay_rts_after_send = 1,
+	/* Delay RTS before send is not supported */
+};
+
+static int pci1xxxx_set_sys_lock(struct pci1xxxx_8250 *port)
+{
+	writel(UART_SYSLOCK, port->membase + UART_SYSLOCK_REG);
+	return readl(port->membase + UART_SYSLOCK_REG);
+}
+
+static int pci1xxxx_acquire_sys_lock(struct pci1xxxx_8250 *port)
+{
+	u32 regval;
+
+	return readx_poll_timeout(pci1xxxx_set_sys_lock, port, regval,
+				  (regval & UART_SYSLOCK),
+				  SYSLOCK_SLEEP_TIMEOUT,
+				  SYSLOCK_RETRY_CNT * SYSLOCK_SLEEP_TIMEOUT);
+}
+
+static void pci1xxxx_release_sys_lock(struct pci1xxxx_8250 *port)
+{
+	writel(0x0, port->membase + UART_SYSLOCK_REG);
+}
 
 static const int logical_to_physical_port_idx[][MAX_PORTS] = {
 	{0,  1,  2,  3}, /* PCI12000, PCI11010, PCI11101, PCI11400, PCI11414 */
@@ -104,12 +172,6 @@ static const int logical_to_physical_port_idx[][MAX_PORTS] = {
 	{3, -1, -1, -1}, /* PCI1p3 */
 };
 
-struct pci1xxxx_8250 {
-	unsigned int nr;
-	void __iomem *membase;
-	int line[] __counted_by(nr);
-};
-
 static int pci1xxxx_get_num_ports(struct pci_dev *dev)
 {
 	switch (dev->subsystem_device) {
@@ -205,12 +267,102 @@ static int pci1xxxx_rs485_config(struct uart_port *port,
 	return 0;
 }
 
-static const struct serial_rs485 pci1xxxx_rs485_supported = {
-	.flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND |
-		 SER_RS485_RTS_AFTER_SEND,
-	.delay_rts_after_send = 1,
-	/* Delay RTS before send is not supported */
-};
+static u32 pci1xxxx_read_burst_status(struct uart_port *port)
+{
+	u32 status;
+
+	status = readl(port->membase + UART_BURST_STATUS_REG);
+	if (status & UART_BST_STAT_LSR_RX_ERR_MASK) {
+		if (status & UART_BST_STAT_LSR_OVERRUN_ERR) {
+			writeb(UART_LSR_OVERRUN_ERR_CLR,
+			       port->membase + UART_FIFO_CTL);
+			port->icount.overrun++;
+		}
+
+		if (status & UART_BST_STAT_LSR_FRAME_ERR)
+			port->icount.frame++;
+
+		if (status & UART_BST_STAT_LSR_PARITY_ERR)
+			port->icount.parity++;
+	}
+	return status;
+}
+
+static void pci1xxxx_process_read_data(struct uart_port *port,
+				       unsigned char *rx_buff, u32 *buff_index,
+				       u32 *valid_byte_count)
+{
+	u32 valid_burst_count = *valid_byte_count / UART_BURST_SIZE;
+	u32 *burst_buf;
+
+	/*
+	 * Depending on the RX Trigger Level the number of bytes that can be
+	 * stored in RX FIFO at a time varies. Each transaction reads data
+	 * in DWORDs. If there are less than four remaining valid_byte_count
+	 * to read, the data is received one byte at a time.
+	 */
+	while (valid_burst_count--) {
+		if (*buff_index > (RX_BUF_SIZE - UART_BURST_SIZE))
+			break;
+		burst_buf = (u32 *)&rx_buff[*buff_index];
+		*burst_buf = readl(port->membase + UART_RX_BURST_FIFO);
+		*buff_index += UART_BURST_SIZE;
+		*valid_byte_count -= UART_BURST_SIZE;
+	}
+
+	while (*valid_byte_count) {
+		if (*buff_index >= RX_BUF_SIZE)
+			break;
+		rx_buff[*buff_index] = readb(port->membase +
+					     UART_RX_BYTE_FIFO);
+		*buff_index += UART_BYTE_SIZE;
+		*valid_byte_count -= UART_BYTE_SIZE;
+	}
+}
+
+static void pci1xxxx_rx_burst(struct uart_port *port, u32 uart_status)
+{
+	u32 valid_byte_count = uart_status & UART_BST_STAT_RX_COUNT_MASK;
+	struct tty_port *tty_port = &port->state->port;
+	unsigned char rx_buff[RX_BUF_SIZE];
+	u32 buff_index = 0;
+	u32 copied_len;
+
+	if (valid_byte_count != 0 &&
+	    valid_byte_count < RX_BUF_SIZE) {
+		pci1xxxx_process_read_data(port, rx_buff, &buff_index,
+					   &valid_byte_count);
+
+		copied_len = (u32)tty_insert_flip_string(tty_port, rx_buff,
+							 buff_index);
+
+		if (copied_len != buff_index)
+			port->icount.overrun += buff_index - copied_len;
+
+		port->icount.rx += buff_index;
+		tty_flip_buffer_push(tty_port);
+	}
+}
+
+static int pci1xxxx_handle_irq(struct uart_port *port)
+{
+	unsigned long flags;
+	u32 status;
+
+	status = pci1xxxx_read_burst_status(port);
+
+	if (status & UART_BST_STAT_IIR_INT_PEND)
+		return 0;
+
+	spin_lock_irqsave(&port->lock, flags);
+
+	if (status & UART_BST_STAT_LSR_RX_MASK)
+		pci1xxxx_rx_burst(port, status);
+
+	spin_unlock_irqrestore(&port->lock, flags);
+
+	return 1;
+}
 
 static bool pci1xxxx_port_suspend(int line)
 {
@@ -323,7 +475,7 @@ static int pci1xxxx_resume(struct device *dev)
 }
 
 static int pci1xxxx_setup(struct pci_dev *pdev,
-			  struct uart_8250_port *port, int port_idx)
+			  struct uart_8250_port *port, int port_idx, int rev)
 {
 	int ret;
 
@@ -335,6 +487,10 @@ static int pci1xxxx_setup(struct pci_dev *pdev,
 	port->port.rs485_config = pci1xxxx_rs485_config;
 	port->port.rs485_supported = pci1xxxx_rs485_supported;
 
+	/* From C0 rev Burst operation is supported */
+	if (rev >= 0xC0)
+		port->port.handle_irq = pci1xxxx_handle_irq;
+
 	ret = serial8250_pci_setup_port(pdev, port, 0, PORT_OFFSET * port_idx, 0);
 	if (ret < 0)
 		return ret;
@@ -370,6 +526,27 @@ static int pci1xxxx_logical_to_physical_port_translate(int subsys_dev, int port)
 	return logical_to_physical_port_idx[0][port];
 }
 
+static int pci1xxxx_get_device_revision(struct pci1xxxx_8250 *priv)
+{
+	u32 regval;
+	int ret;
+
+	/*
+	 * DEV REV is a system register, HW Syslock bit
+	 * should be acquired before accessing the register
+	 */
+	ret = pci1xxxx_acquire_sys_lock(priv);
+	if (ret)
+		return ret;
+
+	regval = readl(priv->membase + UART_DEV_REV_REG);
+	priv->dev_rev = regval & UART_DEV_REV_MASK;
+
+	pci1xxxx_release_sys_lock(priv);
+
+	return 0;
+}
+
 static int pci1xxxx_serial_probe(struct pci_dev *pdev,
 				 const struct pci_device_id *id)
 {
@@ -381,6 +558,7 @@ static int pci1xxxx_serial_probe(struct pci_dev *pdev,
 	int num_vectors;
 	int subsys_dev;
 	int port_idx;
+	int ret;
 	int rc;
 
 	rc = pcim_enable_device(pdev);
@@ -397,6 +575,10 @@ static int pci1xxxx_serial_probe(struct pci_dev *pdev,
 	if (!priv->membase)
 		return -ENOMEM;
 
+	ret = pci1xxxx_get_device_revision(priv);
+	if (ret)
+		return ret;
+
 	pci_set_master(pdev);
 
 	priv->nr = nr_ports;
@@ -428,7 +610,7 @@ static int pci1xxxx_serial_probe(struct pci_dev *pdev,
 		else
 			uart.port.irq = pci_irq_vector(pdev, 0);
 
-		rc = pci1xxxx_setup(pdev, &uart, port_idx);
+		rc = pci1xxxx_setup(pdev, &uart, port_idx, priv->dev_rev);
 		if (rc) {
 			dev_warn(dev, "Failed to setup port %u\n", i);
 			continue;
diff --git a/drivers/tty/serial/8250/8250_pxa.c b/drivers/tty/serial/8250/8250_pxa.c
index a5b3ea27fc90..77686da42ce8 100644
--- a/drivers/tty/serial/8250/8250_pxa.c
+++ b/drivers/tty/serial/8250/8250_pxa.c
@@ -146,20 +146,18 @@ static int serial_pxa_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int serial_pxa_remove(struct platform_device *pdev)
+static void serial_pxa_remove(struct platform_device *pdev)
 {
 	struct pxa8250_data *data = platform_get_drvdata(pdev);
 
 	serial8250_unregister_port(data->line);
 
 	clk_unprepare(data->clk);
-
-	return 0;
 }
 
 static struct platform_driver serial_pxa_driver = {
 	.probe          = serial_pxa_probe,
-	.remove         = serial_pxa_remove,
+	.remove_new     = serial_pxa_remove,
 
 	.driver		= {
 		.name	= "pxa2xx-uart",
diff --git a/drivers/tty/serial/8250/8250_tegra.c b/drivers/tty/serial/8250/8250_tegra.c
index 89956bbf34d9..ba352262df75 100644
--- a/drivers/tty/serial/8250/8250_tegra.c
+++ b/drivers/tty/serial/8250/8250_tegra.c
@@ -128,15 +128,13 @@ err_clkdisable:
 	return ret;
 }
 
-static int tegra_uart_remove(struct platform_device *pdev)
+static void tegra_uart_remove(struct platform_device *pdev)
 {
 	struct tegra_uart *uart = platform_get_drvdata(pdev);
 
 	serial8250_unregister_port(uart->line);
 	reset_control_assert(uart->rst);
 	clk_disable_unprepare(uart->clk);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -192,7 +190,7 @@ static struct platform_driver tegra_uart_driver = {
 		.acpi_match_table = ACPI_PTR(tegra_uart_acpi_match),
 	},
 	.probe = tegra_uart_probe,
-	.remove = tegra_uart_remove,
+	.remove_new = tegra_uart_remove,
 };
 
 module_platform_driver(tegra_uart_driver);
diff --git a/drivers/tty/serial/8250/8250_uniphier.c b/drivers/tty/serial/8250/8250_uniphier.c
index a405155264b1..6399a38ecce2 100644
--- a/drivers/tty/serial/8250/8250_uniphier.c
+++ b/drivers/tty/serial/8250/8250_uniphier.c
@@ -241,14 +241,12 @@ static int uniphier_uart_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int uniphier_uart_remove(struct platform_device *pdev)
+static void uniphier_uart_remove(struct platform_device *pdev)
 {
 	struct uniphier8250_priv *priv = platform_get_drvdata(pdev);
 
 	serial8250_unregister_port(priv->line);
 	clk_disable_unprepare(priv->clk);
-
-	return 0;
 }
 
 static int __maybe_unused uniphier_uart_suspend(struct device *dev)
@@ -293,7 +291,7 @@ MODULE_DEVICE_TABLE(of, uniphier_uart_match);
 
 static struct platform_driver uniphier_uart_platform_driver = {
 	.probe		= uniphier_uart_probe,
-	.remove		= uniphier_uart_remove,
+	.remove_new	= uniphier_uart_remove,
 	.driver = {
 		.name	= "uniphier-uart",
 		.of_match_table = uniphier_uart_match,
diff --git a/drivers/tty/serial/8250/serial_cs.c b/drivers/tty/serial/8250/serial_cs.c
index dc2ef05a10eb..2056aed46688 100644
--- a/drivers/tty/serial/8250/serial_cs.c
+++ b/drivers/tty/serial/8250/serial_cs.c
@@ -90,12 +90,6 @@ struct serial_info {
 	const struct serial_quirk *quirk;
 };
 
-struct serial_cfg_mem {
-	tuple_t tuple;
-	cisparse_t parse;
-	u_char buf[256];
-};
-
 /*
  * vers_1 5.0, "Brain Boxes", "2-Port RS232 card", "r6"
  * manfid 0x0160, 0x0104
diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 732c893c8d16..ffcf4882b25f 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -87,7 +87,7 @@ config SERIAL_EARLYCON_SEMIHOST
 
 config SERIAL_EARLYCON_RISCV_SBI
 	bool "Early console using RISC-V SBI"
-	depends on RISCV_SBI_V01
+	depends on RISCV_SBI
 	select SERIAL_CORE
 	select SERIAL_CORE_CONSOLE
 	select SERIAL_EARLYCON
@@ -532,6 +532,9 @@ config SERIAL_UARTLITE_NR_UARTS
 	help
 	  Set this to the number of uartlites in your system, or the number
 	  you think you might implement.
+	  If maximum number of uartlite serial ports is more than 4, then the
+	  driver uses dynamic allocation instead of static allocation for major
+	  number.
 
 config SERIAL_SUNCORE
 	bool
diff --git a/drivers/tty/serial/altera_jtaguart.c b/drivers/tty/serial/altera_jtaguart.c
index 7090b251dd4d..effcba71ea77 100644
--- a/drivers/tty/serial/altera_jtaguart.c
+++ b/drivers/tty/serial/altera_jtaguart.c
@@ -425,7 +425,7 @@ static int altera_jtaguart_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int altera_jtaguart_remove(struct platform_device *pdev)
+static void altera_jtaguart_remove(struct platform_device *pdev)
 {
 	struct uart_port *port;
 	int i = pdev->id;
@@ -436,8 +436,6 @@ static int altera_jtaguart_remove(struct platform_device *pdev)
 	port = &altera_jtaguart_ports[i];
 	uart_remove_one_port(&altera_jtaguart_driver, port);
 	iounmap(port->membase);
-
-	return 0;
 }
 
 #ifdef CONFIG_OF
@@ -451,7 +449,7 @@ MODULE_DEVICE_TABLE(of, altera_jtaguart_match);
 
 static struct platform_driver altera_jtaguart_platform_driver = {
 	.probe	= altera_jtaguart_probe,
-	.remove	= altera_jtaguart_remove,
+	.remove_new = altera_jtaguart_remove,
 	.driver	= {
 		.name		= DRV_NAME,
 		.of_match_table	= of_match_ptr(altera_jtaguart_match),
diff --git a/drivers/tty/serial/altera_uart.c b/drivers/tty/serial/altera_uart.c
index 77835ac68df2..897f0995b2fe 100644
--- a/drivers/tty/serial/altera_uart.c
+++ b/drivers/tty/serial/altera_uart.c
@@ -305,7 +305,7 @@ static int altera_uart_startup(struct uart_port *port)
 		int ret;
 
 		ret = request_irq(port->irq, altera_uart_interrupt, 0,
-				DRV_NAME, port);
+				dev_name(port->dev), port);
 		if (ret) {
 			pr_err(DRV_NAME ": unable to attach Altera UART %d "
 			       "interrupt vector=%d\n", port->line, port->irq);
@@ -595,7 +595,7 @@ static int altera_uart_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int altera_uart_remove(struct platform_device *pdev)
+static void altera_uart_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 
@@ -604,8 +604,6 @@ static int altera_uart_remove(struct platform_device *pdev)
 		port->mapbase = 0;
 		iounmap(port->membase);
 	}
-
-	return 0;
 }
 
 #ifdef CONFIG_OF
@@ -619,7 +617,7 @@ MODULE_DEVICE_TABLE(of, altera_uart_match);
 
 static struct platform_driver altera_uart_platform_driver = {
 	.probe	= altera_uart_probe,
-	.remove	= altera_uart_remove,
+	.remove_new = altera_uart_remove,
 	.driver	= {
 		.name		= DRV_NAME,
 		.of_match_table	= of_match_ptr(altera_uart_match),
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index b7635363373e..cf2c890a560f 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -50,8 +50,8 @@
 
 #define AMBA_ISR_PASS_LIMIT	256
 
-#define UART_DR_ERROR		(UART011_DR_OE|UART011_DR_BE|UART011_DR_PE|UART011_DR_FE)
-#define UART_DUMMY_DR_RX	(1 << 16)
+#define UART_DR_ERROR		(UART011_DR_OE | UART011_DR_BE | UART011_DR_PE | UART011_DR_FE)
+#define UART_DUMMY_DR_RX	BIT(16)
 
 enum {
 	REG_DR,
@@ -125,7 +125,7 @@ static unsigned int get_fifosize_arm(struct amba_device *dev)
 
 static struct vendor_data vendor_arm = {
 	.reg_offset		= pl011_std_offsets,
-	.ifls			= UART011_IFLS_RX4_8|UART011_IFLS_TX4_8,
+	.ifls			= UART011_IFLS_RX4_8 | UART011_IFLS_TX4_8,
 	.fr_busy		= UART01x_FR_BUSY,
 	.fr_dsr			= UART01x_FR_DSR,
 	.fr_cts			= UART01x_FR_CTS,
@@ -203,7 +203,7 @@ static unsigned int get_fifosize_st(struct amba_device *dev)
 
 static struct vendor_data vendor_st = {
 	.reg_offset		= pl011_st_offsets,
-	.ifls			= UART011_IFLS_RX_HALF|UART011_IFLS_TX_HALF,
+	.ifls			= UART011_IFLS_RX_HALF | UART011_IFLS_TX_HALF,
 	.fr_busy		= UART01x_FR_BUSY,
 	.fr_dsr			= UART01x_FR_DSR,
 	.fr_cts			= UART01x_FR_CTS,
@@ -277,13 +277,13 @@ struct uart_amba_port {
 static unsigned int pl011_tx_empty(struct uart_port *port);
 
 static unsigned int pl011_reg_to_offset(const struct uart_amba_port *uap,
-	unsigned int reg)
+					unsigned int reg)
 {
 	return uap->reg_offset[reg];
 }
 
 static unsigned int pl011_read(const struct uart_amba_port *uap,
-	unsigned int reg)
+			       unsigned int reg)
 {
 	void __iomem *addr = uap->port.membase + pl011_reg_to_offset(uap, reg);
 
@@ -292,7 +292,7 @@ static unsigned int pl011_read(const struct uart_amba_port *uap,
 }
 
 static void pl011_write(unsigned int val, const struct uart_amba_port *uap,
-	unsigned int reg)
+			unsigned int reg)
 {
 	void __iomem *addr = uap->port.membase + pl011_reg_to_offset(uap, reg);
 
@@ -330,10 +330,11 @@ static int pl011_fifo_to_tty(struct uart_amba_port *uap)
 				uap->port.icount.brk++;
 				if (uart_handle_break(&uap->port))
 					continue;
-			} else if (ch & UART011_DR_PE)
+			} else if (ch & UART011_DR_PE) {
 				uap->port.icount.parity++;
-			else if (ch & UART011_DR_FE)
+			} else if (ch & UART011_DR_FE) {
 				uap->port.icount.frame++;
+			}
 			if (ch & UART011_DR_OE)
 				uap->port.icount.overrun++;
 
@@ -358,7 +359,6 @@ static int pl011_fifo_to_tty(struct uart_amba_port *uap)
 	return fifotaken;
 }
 
-
 /*
  * All the DMA operation mode stuff goes inside this ifdef.
  * This assumes that you have a generic DMA device interface,
@@ -369,7 +369,7 @@ static int pl011_fifo_to_tty(struct uart_amba_port *uap)
 #define PL011_DMA_BUFFER_SIZE PAGE_SIZE
 
 static int pl011_dmabuf_init(struct dma_chan *chan, struct pl011_dmabuf *db,
-	enum dma_data_direction dir)
+			     enum dma_data_direction dir)
 {
 	db->buf = dma_alloc_coherent(chan->device->dev, PL011_DMA_BUFFER_SIZE,
 				     &db->dma, GFP_KERNEL);
@@ -381,7 +381,7 @@ static int pl011_dmabuf_init(struct dma_chan *chan, struct pl011_dmabuf *db,
 }
 
 static void pl011_dmabuf_free(struct dma_chan *chan, struct pl011_dmabuf *db,
-	enum dma_data_direction dir)
+			      enum dma_data_direction dir)
 {
 	if (db->buf) {
 		dma_free_coherent(chan->device->dev,
@@ -424,7 +424,7 @@ static void pl011_dma_probe(struct uart_amba_port *uap)
 		dma_cap_set(DMA_SLAVE, mask);
 
 		chan = dma_request_channel(mask, plat->dma_filter,
-						plat->dma_tx_param);
+					   plat->dma_tx_param);
 		if (!chan) {
 			dev_err(uap->port.dev, "no TX DMA channel!\n");
 			return;
@@ -438,9 +438,9 @@ static void pl011_dma_probe(struct uart_amba_port *uap)
 		 dma_chan_name(uap->dmatx.chan));
 
 	/* Optionally make use of an RX channel as well */
-	chan = dma_request_slave_channel(dev, "rx");
+	chan = dma_request_chan(dev, "rx");
 
-	if (!chan && plat && plat->dma_rx_param) {
+	if (IS_ERR(chan) && plat && plat->dma_rx_param) {
 		chan = dma_request_channel(mask, plat->dma_filter, plat->dma_rx_param);
 
 		if (!chan) {
@@ -449,7 +449,7 @@ static void pl011_dma_probe(struct uart_amba_port *uap)
 		}
 	}
 
-	if (chan) {
+	if (!IS_ERR(chan)) {
 		struct dma_slave_config rx_conf = {
 			.src_addr = uap->port.mapbase +
 				pl011_reg_to_offset(uap, REG_DR),
@@ -465,12 +465,12 @@ static void pl011_dma_probe(struct uart_amba_port *uap)
 		 * If the controller does, check for suitable residue processing
 		 * otherwise assime all is well.
 		 */
-		if (0 == dma_get_slave_caps(chan, &caps)) {
+		if (dma_get_slave_caps(chan, &caps) == 0) {
 			if (caps.residue_granularity ==
 					DMA_RESIDUE_GRANULARITY_DESCRIPTOR) {
 				dma_release_channel(chan);
 				dev_info(uap->port.dev,
-					"RX DMA disabled - no residue processing\n");
+					 "RX DMA disabled - no residue processing\n");
 				return;
 			}
 		}
@@ -499,18 +499,16 @@ static void pl011_dma_probe(struct uart_amba_port *uap)
 			else
 				uap->dmarx.poll_timeout = 3000;
 		} else if (!plat && dev->of_node) {
-			uap->dmarx.auto_poll_rate = of_property_read_bool(
-						dev->of_node, "auto-poll");
+			uap->dmarx.auto_poll_rate =
+					of_property_read_bool(dev->of_node, "auto-poll");
 			if (uap->dmarx.auto_poll_rate) {
 				u32 x;
 
-				if (0 == of_property_read_u32(dev->of_node,
-						"poll-rate-ms", &x))
+				if (of_property_read_u32(dev->of_node, "poll-rate-ms", &x) == 0)
 					uap->dmarx.poll_rate = x;
 				else
 					uap->dmarx.poll_rate = 100;
-				if (0 == of_property_read_u32(dev->of_node,
-						"poll-timeout-ms", &x))
+				if (of_property_read_u32(dev->of_node, "poll-timeout-ms", &x) == 0)
 					uap->dmarx.poll_timeout = x;
 				else
 					uap->dmarx.poll_timeout = 3000;
@@ -547,7 +545,7 @@ static void pl011_dma_tx_callback(void *data)
 	uart_port_lock_irqsave(&uap->port, &flags);
 	if (uap->dmatx.queued)
 		dma_unmap_single(dmatx->chan->device->dev, dmatx->dma,
-				dmatx->len, DMA_TO_DEVICE);
+				 dmatx->len, DMA_TO_DEVICE);
 
 	dmacr = uap->dmacr;
 	uap->dmacr = dmacr & ~UART011_TXDMAE;
@@ -618,9 +616,9 @@ static int pl011_dma_tx_refill(struct uart_amba_port *uap)
 	if (count > PL011_DMA_BUFFER_SIZE)
 		count = PL011_DMA_BUFFER_SIZE;
 
-	if (xmit->tail < xmit->head)
+	if (xmit->tail < xmit->head) {
 		memcpy(&dmatx->buf[0], &xmit->buf[xmit->tail], count);
-	else {
+	} else {
 		size_t first = UART_XMIT_SIZE - xmit->tail;
 		size_t second;
 
@@ -643,7 +641,7 @@ static int pl011_dma_tx_refill(struct uart_amba_port *uap)
 	}
 
 	desc = dmaengine_prep_slave_single(chan, dmatx->dma, dmatx->len, DMA_MEM_TO_DEV,
-					     DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+					   DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc) {
 		dma_unmap_single(dma_dev->dev, dmatx->dma, dmatx->len, DMA_TO_DEVICE);
 		uap->dmatx.queued = false;
@@ -754,8 +752,9 @@ static inline bool pl011_dma_tx_start(struct uart_amba_port *uap)
 			if (pl011_dma_tx_refill(uap) > 0) {
 				uap->im &= ~UART011_TXIM;
 				pl011_write(uap->im, uap, REG_IMSC);
-			} else
+			} else {
 				ret = false;
+			}
 		} else if (!(uap->dmacr & UART011_TXDMAE)) {
 			uap->dmacr |= UART011_TXDMAE;
 			pl011_write(uap->dmacr, uap, REG_DMACR);
@@ -832,8 +831,8 @@ static int pl011_dma_rx_trigger_dma(struct uart_amba_port *uap)
 	dbuf = uap->dmarx.use_buf_b ?
 		&uap->dmarx.dbuf_b : &uap->dmarx.dbuf_a;
 	desc = dmaengine_prep_slave_single(rxchan, dbuf->dma, dbuf->len,
-					DMA_DEV_TO_MEM,
-					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+					   DMA_DEV_TO_MEM,
+					   DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	/*
 	 * If the DMA engine is busy and cannot prepare a
 	 * channel, no big deal, the driver will fall back
@@ -889,14 +888,12 @@ static void pl011_dma_rx_chars(struct uart_amba_port *uap,
 
 	/* Pick the remain data from the DMA */
 	if (pending) {
-
 		/*
 		 * First take all chars in the DMA pipe, then look in the FIFO.
 		 * Note that tty_insert_flip_buf() tries to take as many chars
 		 * as it can.
 		 */
-		dma_count = tty_insert_flip_string(port, dbuf->buf + dmataken,
-				pending);
+		dma_count = tty_insert_flip_string(port, dbuf->buf + dmataken, pending);
 
 		uap->port.icount.rx += dma_count;
 		if (dma_count < pending)
@@ -978,8 +975,8 @@ static void pl011_dma_rx_irq(struct uart_amba_port *uap)
 	/* Switch buffer & re-trigger DMA job */
 	dmarx->use_buf_b = !dmarx->use_buf_b;
 	if (pl011_dma_rx_trigger_dma(uap)) {
-		dev_dbg(uap->port.dev, "could not retrigger RX DMA job "
-			"fall back to interrupt mode\n");
+		dev_dbg(uap->port.dev,
+			"could not retrigger RX DMA job fall back to interrupt mode\n");
 		uap->im |= UART011_RXIM;
 		pl011_write(uap->im, uap, REG_IMSC);
 	}
@@ -1026,8 +1023,8 @@ static void pl011_dma_rx_callback(void *data)
 	 * get some IRQ immediately from RX.
 	 */
 	if (ret) {
-		dev_dbg(uap->port.dev, "could not retrigger RX DMA job "
-			"fall back to interrupt mode\n");
+		dev_dbg(uap->port.dev,
+			"could not retrigger RX DMA job fall back to interrupt mode\n");
 		uap->im |= UART011_RXIM;
 		pl011_write(uap->im, uap, REG_IMSC);
 	}
@@ -1072,7 +1069,7 @@ static void pl011_dma_rx_poll(struct timer_list *t)
 		dmataken = dbuf->len - dmarx->last_residue;
 		size = dmarx->last_residue - state.residue;
 		dma_count = tty_insert_flip_string(port, dbuf->buf + dmataken,
-				size);
+						   size);
 		if (dma_count == size)
 			dmarx->last_residue =  state.residue;
 		dmarx->last_jiffies = jiffies;
@@ -1085,7 +1082,6 @@ static void pl011_dma_rx_poll(struct timer_list *t)
 	 */
 	if (jiffies_to_msecs(jiffies - dmarx->last_jiffies)
 			> uap->dmarx.poll_timeout) {
-
 		uart_port_lock_irqsave(&uap->port, &flags);
 		pl011_dma_rx_stop(uap);
 		uap->im |= UART011_RXIM;
@@ -1097,7 +1093,7 @@ static void pl011_dma_rx_poll(struct timer_list *t)
 		del_timer(&uap->dmarx.timer);
 	} else {
 		mod_timer(&uap->dmarx.timer,
-			jiffies + msecs_to_jiffies(uap->dmarx.poll_rate));
+			  jiffies + msecs_to_jiffies(uap->dmarx.poll_rate));
 	}
 }
 
@@ -1113,7 +1109,6 @@ static void pl011_dma_startup(struct uart_amba_port *uap)
 
 	uap->dmatx.buf = kmalloc(PL011_DMA_BUFFER_SIZE, GFP_KERNEL | __GFP_DMA);
 	if (!uap->dmatx.buf) {
-		dev_err(uap->port.dev, "no memory for DMA TX buffer\n");
 		uap->port.fifosize = uap->fifosize;
 		return;
 	}
@@ -1129,7 +1124,7 @@ static void pl011_dma_startup(struct uart_amba_port *uap)
 
 	/* Allocate and map DMA RX buffers */
 	ret = pl011_dmabuf_init(uap->dmarx.chan, &uap->dmarx.dbuf_a,
-			       DMA_FROM_DEVICE);
+				DMA_FROM_DEVICE);
 	if (ret) {
 		dev_err(uap->port.dev, "failed to init DMA %s: %d\n",
 			"RX buffer A", ret);
@@ -1137,12 +1132,12 @@ static void pl011_dma_startup(struct uart_amba_port *uap)
 	}
 
 	ret = pl011_dmabuf_init(uap->dmarx.chan, &uap->dmarx.dbuf_b,
-			       DMA_FROM_DEVICE);
+				DMA_FROM_DEVICE);
 	if (ret) {
 		dev_err(uap->port.dev, "failed to init DMA %s: %d\n",
 			"RX buffer B", ret);
 		pl011_dmabuf_free(uap->dmarx.chan, &uap->dmarx.dbuf_a,
-				 DMA_FROM_DEVICE);
+				  DMA_FROM_DEVICE);
 		goto skip_rx;
 	}
 
@@ -1164,13 +1159,12 @@ skip_rx:
 
 	if (uap->using_rx_dma) {
 		if (pl011_dma_rx_trigger_dma(uap))
-			dev_dbg(uap->port.dev, "could not trigger initial "
-				"RX DMA job, fall back to interrupt mode\n");
+			dev_dbg(uap->port.dev,
+				"could not trigger initial RX DMA job, fall back to interrupt mode\n");
 		if (uap->dmarx.poll_rate) {
 			timer_setup(&uap->dmarx.timer, pl011_dma_rx_poll, 0);
 			mod_timer(&uap->dmarx.timer,
-				jiffies +
-				msecs_to_jiffies(uap->dmarx.poll_rate));
+				  jiffies + msecs_to_jiffies(uap->dmarx.poll_rate));
 			uap->dmarx.last_residue = PL011_DMA_BUFFER_SIZE;
 			uap->dmarx.last_jiffies = jiffies;
 		}
@@ -1345,11 +1339,41 @@ static void pl011_start_tx_pio(struct uart_amba_port *uap)
 	}
 }
 
+static void pl011_rs485_tx_start(struct uart_amba_port *uap)
+{
+	struct uart_port *port = &uap->port;
+	u32 cr;
+
+	/* Enable transmitter */
+	cr = pl011_read(uap, REG_CR);
+	cr |= UART011_CR_TXE;
+
+	/* Disable receiver if half-duplex */
+	if (!(port->rs485.flags & SER_RS485_RX_DURING_TX))
+		cr &= ~UART011_CR_RXE;
+
+	if (port->rs485.flags & SER_RS485_RTS_ON_SEND)
+		cr &= ~UART011_CR_RTS;
+	else
+		cr |= UART011_CR_RTS;
+
+	pl011_write(cr, uap, REG_CR);
+
+	if (port->rs485.delay_rts_before_send)
+		mdelay(port->rs485.delay_rts_before_send);
+
+	uap->rs485_tx_started = true;
+}
+
 static void pl011_start_tx(struct uart_port *port)
 {
 	struct uart_amba_port *uap =
 	    container_of(port, struct uart_amba_port, port);
 
+	if ((uap->port.rs485.flags & SER_RS485_ENABLED) &&
+	    !uap->rs485_tx_started)
+		pl011_rs485_tx_start(uap);
+
 	if (!pl011_dma_tx_start(uap))
 		pl011_start_tx_pio(uap);
 }
@@ -1359,8 +1383,8 @@ static void pl011_stop_rx(struct uart_port *port)
 	struct uart_amba_port *uap =
 	    container_of(port, struct uart_amba_port, port);
 
-	uap->im &= ~(UART011_RXIM|UART011_RTIM|UART011_FEIM|
-		     UART011_PEIM|UART011_BEIM|UART011_OEIM);
+	uap->im &= ~(UART011_RXIM | UART011_RTIM | UART011_FEIM |
+		     UART011_PEIM | UART011_BEIM | UART011_OEIM);
 	pl011_write(uap->im, uap, REG_IMSC);
 
 	pl011_dma_rx_stop(uap);
@@ -1380,7 +1404,7 @@ static void pl011_enable_ms(struct uart_port *port)
 	struct uart_amba_port *uap =
 	    container_of(port, struct uart_amba_port, port);
 
-	uap->im |= UART011_RIMIM|UART011_CTSMIM|UART011_DCDMIM|UART011_DSRMIM;
+	uap->im |= UART011_RIMIM | UART011_CTSMIM | UART011_DCDMIM | UART011_DSRMIM;
 	pl011_write(uap->im, uap, REG_IMSC);
 }
 
@@ -1398,8 +1422,8 @@ __acquires(&uap->port.lock)
 	 */
 	if (pl011_dma_rx_available(uap)) {
 		if (pl011_dma_rx_trigger_dma(uap)) {
-			dev_dbg(uap->port.dev, "could not trigger RX DMA job "
-				"fall back to interrupt mode again\n");
+			dev_dbg(uap->port.dev,
+				"could not trigger RX DMA job fall back to interrupt mode again\n");
 			uap->im |= UART011_RXIM;
 			pl011_write(uap->im, uap, REG_IMSC);
 		} else {
@@ -1409,8 +1433,7 @@ __acquires(&uap->port.lock)
 				uap->dmarx.last_jiffies = jiffies;
 				uap->dmarx.last_residue	= PL011_DMA_BUFFER_SIZE;
 				mod_timer(&uap->dmarx.timer,
-					jiffies +
-					msecs_to_jiffies(uap->dmarx.poll_rate));
+					  jiffies + msecs_to_jiffies(uap->dmarx.poll_rate));
 			}
 #endif
 		}
@@ -1431,42 +1454,12 @@ static bool pl011_tx_char(struct uart_amba_port *uap, unsigned char c,
 	return true;
 }
 
-static void pl011_rs485_tx_start(struct uart_amba_port *uap)
-{
-	struct uart_port *port = &uap->port;
-	u32 cr;
-
-	/* Enable transmitter */
-	cr = pl011_read(uap, REG_CR);
-	cr |= UART011_CR_TXE;
-
-	/* Disable receiver if half-duplex */
-	if (!(port->rs485.flags & SER_RS485_RX_DURING_TX))
-		cr &= ~UART011_CR_RXE;
-
-	if (port->rs485.flags & SER_RS485_RTS_ON_SEND)
-		cr &= ~UART011_CR_RTS;
-	else
-		cr |= UART011_CR_RTS;
-
-	pl011_write(cr, uap, REG_CR);
-
-	if (port->rs485.delay_rts_before_send)
-		mdelay(port->rs485.delay_rts_before_send);
-
-	uap->rs485_tx_started = true;
-}
-
 /* Returns true if tx interrupts have to be (kept) enabled  */
 static bool pl011_tx_chars(struct uart_amba_port *uap, bool from_irq)
 {
 	struct circ_buf *xmit = &uap->port.state->xmit;
 	int count = uap->fifosize >> 1;
 
-	if ((uap->port.rs485.flags & SER_RS485_ENABLED) &&
-	    !uap->rs485_tx_started)
-		pl011_rs485_tx_start(uap);
-
 	if (uap->port.x_char) {
 		if (!pl011_tx_char(uap, uap->port.x_char, from_irq))
 			return true;
@@ -1557,18 +1550,17 @@ static irqreturn_t pl011_int(int irq, void *dev_id)
 		do {
 			check_apply_cts_event_workaround(uap);
 
-			pl011_write(status & ~(UART011_TXIS|UART011_RTIS|
-					       UART011_RXIS),
+			pl011_write(status & ~(UART011_TXIS | UART011_RTIS | UART011_RXIS),
 				    uap, REG_ICR);
 
-			if (status & (UART011_RTIS|UART011_RXIS)) {
+			if (status & (UART011_RTIS | UART011_RXIS)) {
 				if (pl011_dma_rx_running(uap))
 					pl011_dma_rx_irq(uap);
 				else
 					pl011_rx_chars(uap);
 			}
-			if (status & (UART011_DSRMIS|UART011_DCDMIS|
-				      UART011_CTSMIS|UART011_RIMIS))
+			if (status & (UART011_DSRMIS | UART011_DCDMIS |
+				      UART011_CTSMIS | UART011_RIMIS))
 				pl011_modem_status(uap);
 			if (status & UART011_TXIS)
 				pl011_tx_chars(uap, true);
@@ -1598,6 +1590,12 @@ static unsigned int pl011_tx_empty(struct uart_port *port)
 							0 : TIOCSER_TEMT;
 }
 
+static void pl011_maybe_set_bit(bool cond, unsigned int *ptr, unsigned int mask)
+{
+	if (cond)
+		*ptr |= mask;
+}
+
 static unsigned int pl011_get_mctrl(struct uart_port *port)
 {
 	struct uart_amba_port *uap =
@@ -1605,18 +1603,22 @@ static unsigned int pl011_get_mctrl(struct uart_port *port)
 	unsigned int result = 0;
 	unsigned int status = pl011_read(uap, REG_FR);
 
-#define TIOCMBIT(uartbit, tiocmbit)	\
-	if (status & uartbit)		\
-		result |= tiocmbit
+	pl011_maybe_set_bit(status & UART01x_FR_DCD, &result, TIOCM_CAR);
+	pl011_maybe_set_bit(status & uap->vendor->fr_dsr, &result, TIOCM_DSR);
+	pl011_maybe_set_bit(status & uap->vendor->fr_cts, &result, TIOCM_CTS);
+	pl011_maybe_set_bit(status & uap->vendor->fr_ri, &result, TIOCM_RNG);
 
-	TIOCMBIT(UART01x_FR_DCD, TIOCM_CAR);
-	TIOCMBIT(uap->vendor->fr_dsr, TIOCM_DSR);
-	TIOCMBIT(uap->vendor->fr_cts, TIOCM_CTS);
-	TIOCMBIT(uap->vendor->fr_ri, TIOCM_RNG);
-#undef TIOCMBIT
 	return result;
 }
 
+static void pl011_assign_bit(bool cond, unsigned int *ptr, unsigned int mask)
+{
+	if (cond)
+		*ptr |= mask;
+	else
+		*ptr &= ~mask;
+}
+
 static void pl011_set_mctrl(struct uart_port *port, unsigned int mctrl)
 {
 	struct uart_amba_port *uap =
@@ -1625,23 +1627,16 @@ static void pl011_set_mctrl(struct uart_port *port, unsigned int mctrl)
 
 	cr = pl011_read(uap, REG_CR);
 
-#define	TIOCMBIT(tiocmbit, uartbit)		\
-	if (mctrl & tiocmbit)		\
-		cr |= uartbit;		\
-	else				\
-		cr &= ~uartbit
-
-	TIOCMBIT(TIOCM_RTS, UART011_CR_RTS);
-	TIOCMBIT(TIOCM_DTR, UART011_CR_DTR);
-	TIOCMBIT(TIOCM_OUT1, UART011_CR_OUT1);
-	TIOCMBIT(TIOCM_OUT2, UART011_CR_OUT2);
-	TIOCMBIT(TIOCM_LOOP, UART011_CR_LBE);
+	pl011_assign_bit(mctrl & TIOCM_RTS, &cr, UART011_CR_RTS);
+	pl011_assign_bit(mctrl & TIOCM_DTR, &cr, UART011_CR_DTR);
+	pl011_assign_bit(mctrl & TIOCM_OUT1, &cr, UART011_CR_OUT1);
+	pl011_assign_bit(mctrl & TIOCM_OUT2, &cr, UART011_CR_OUT2);
+	pl011_assign_bit(mctrl & TIOCM_LOOP, &cr, UART011_CR_LBE);
 
 	if (port->status & UPSTAT_AUTORTS) {
 		/* We need to disable auto-RTS if we want to turn RTS off */
-		TIOCMBIT(TIOCM_RTS, UART011_CR_RTSEN);
+		pl011_assign_bit(mctrl & TIOCM_RTS, &cr, UART011_CR_RTSEN);
 	}
-#undef TIOCMBIT
 
 	pl011_write(cr, uap, REG_CR);
 }
@@ -1707,8 +1702,7 @@ static int pl011_get_poll_char(struct uart_port *port)
 	return pl011_read(uap, REG_DR);
 }
 
-static void pl011_put_poll_char(struct uart_port *port,
-			 unsigned char ch)
+static void pl011_put_poll_char(struct uart_port *port, unsigned char ch)
 {
 	struct uart_amba_port *uap =
 	    container_of(port, struct uart_amba_port, port);
@@ -1909,14 +1903,13 @@ static int sbsa_uart_startup(struct uart_port *port)
 	return 0;
 }
 
-static void pl011_shutdown_channel(struct uart_amba_port *uap,
-					unsigned int lcrh)
+static void pl011_shutdown_channel(struct uart_amba_port *uap, unsigned int lcrh)
 {
-      unsigned long val;
+	unsigned long val;
 
-      val = pl011_read(uap, lcrh);
-      val &= ~(UART01x_LCRH_BRK | UART01x_LCRH_FEN);
-      pl011_write(val, uap, lcrh);
+	val = pl011_read(uap, lcrh);
+	val &= ~(UART01x_LCRH_BRK | UART01x_LCRH_FEN);
+	pl011_write(val, uap, lcrh);
 }
 
 /*
@@ -2065,7 +2058,7 @@ pl011_set_termios(struct uart_port *port, struct ktermios *termios,
 		uap->dmarx.poll_rate = DIV_ROUND_UP(10000000, baud);
 #endif
 
-	if (baud > port->uartclk/16)
+	if (baud > port->uartclk / 16)
 		quot = DIV_ROUND_CLOSEST(port->uartclk * 8, baud);
 	else
 		quot = DIV_ROUND_CLOSEST(port->uartclk * 4, baud);
@@ -2147,9 +2140,9 @@ pl011_set_termios(struct uart_port *port, struct ktermios *termios,
 	 * else we see data corruption.
 	 */
 	if (uap->vendor->oversampling) {
-		if ((baud >= 3000000) && (baud < 3250000) && (quot > 1))
+		if (baud >= 3000000 && baud < 3250000 && quot > 1)
 			quot -= 1;
-		else if ((baud > 3250000) && (quot > 2))
+		else if (baud > 3250000 && quot > 2)
 			quot -= 2;
 	}
 	/* Set baud rate */
@@ -2218,13 +2211,14 @@ static void pl011_config_port(struct uart_port *port, int flags)
 static int pl011_verify_port(struct uart_port *port, struct serial_struct *ser)
 {
 	int ret = 0;
+
 	if (ser->type != PORT_UNKNOWN && ser->type != PORT_AMBA)
 		ret = -EINVAL;
 	if (ser->irq < 0 || ser->irq >= nr_irqs)
 		ret = -EINVAL;
 	if (ser->baud_base < 9600)
 		ret = -EINVAL;
-	if (port->mapbase != (unsigned long) ser->iomem_base)
+	if (port->mapbase != (unsigned long)ser->iomem_base)
 		ret = -EINVAL;
 	return ret;
 }
@@ -2369,35 +2363,34 @@ pl011_console_write(struct console *co, const char *s, unsigned int count)
 static void pl011_console_get_options(struct uart_amba_port *uap, int *baud,
 				      int *parity, int *bits)
 {
-	if (pl011_read(uap, REG_CR) & UART01x_CR_UARTEN) {
-		unsigned int lcr_h, ibrd, fbrd;
+	unsigned int lcr_h, ibrd, fbrd;
 
-		lcr_h = pl011_read(uap, REG_LCRH_TX);
+	if (!(pl011_read(uap, REG_CR) & UART01x_CR_UARTEN))
+		return;
 
-		*parity = 'n';
-		if (lcr_h & UART01x_LCRH_PEN) {
-			if (lcr_h & UART01x_LCRH_EPS)
-				*parity = 'e';
-			else
-				*parity = 'o';
-		}
+	lcr_h = pl011_read(uap, REG_LCRH_TX);
 
-		if ((lcr_h & 0x60) == UART01x_LCRH_WLEN_7)
-			*bits = 7;
+	*parity = 'n';
+	if (lcr_h & UART01x_LCRH_PEN) {
+		if (lcr_h & UART01x_LCRH_EPS)
+			*parity = 'e';
 		else
-			*bits = 8;
+			*parity = 'o';
+	}
 
-		ibrd = pl011_read(uap, REG_IBRD);
-		fbrd = pl011_read(uap, REG_FBRD);
+	if ((lcr_h & 0x60) == UART01x_LCRH_WLEN_7)
+		*bits = 7;
+	else
+		*bits = 8;
 
-		*baud = uap->port.uartclk * 4 / (64 * ibrd + fbrd);
+	ibrd = pl011_read(uap, REG_IBRD);
+	fbrd = pl011_read(uap, REG_FBRD);
 
-		if (uap->vendor->oversampling) {
-			if (pl011_read(uap, REG_CR)
-				  & ST_UART011_CR_OVSFACT)
-				*baud *= 2;
-		}
-	}
+	*baud = uap->port.uartclk * 4 / (64 * ibrd + fbrd);
+
+	if (uap->vendor->oversampling &&
+	    (pl011_read(uap, REG_CR) & ST_UART011_CR_OVSFACT))
+		*baud *= 2;
 }
 
 static int pl011_console_setup(struct console *co, char *options)
@@ -2533,7 +2526,7 @@ static void qdf2400_e44_putc(struct uart_port *port, unsigned char c)
 		cpu_relax();
 }
 
-static void qdf2400_e44_early_write(struct console *con, const char *s, unsigned n)
+static void qdf2400_e44_early_write(struct console *con, const char *s, unsigned int n)
 {
 	struct earlycon_device *dev = con->data;
 
@@ -2552,7 +2545,7 @@ static void pl011_putc(struct uart_port *port, unsigned char c)
 		cpu_relax();
 }
 
-static void pl011_early_write(struct console *con, const char *s, unsigned n)
+static void pl011_early_write(struct console *con, const char *s, unsigned int n)
 {
 	struct earlycon_device *dev = con->data;
 
@@ -2613,7 +2606,9 @@ static int __init pl011_early_console_setup(struct earlycon_device *device,
 
 	return 0;
 }
+
 OF_EARLYCON_DECLARE(pl011, "arm,pl011", pl011_early_console_setup);
+
 OF_EARLYCON_DECLARE(pl011, "arm,sbsa-uart", pl011_early_console_setup);
 
 /*
@@ -2636,6 +2631,7 @@ qdf2400_e44_early_console_setup(struct earlycon_device *device,
 	device->con->write = qdf2400_e44_early_write;
 	return 0;
 }
+
 EARLYCON_DECLARE(qdf2400_e44, qdf2400_e44_early_console_setup);
 
 #else
@@ -2655,8 +2651,8 @@ static struct uart_driver amba_reg = {
 static int pl011_probe_dt_alias(int index, struct device *dev)
 {
 	struct device_node *np;
-	static bool seen_dev_with_alias = false;
-	static bool seen_dev_without_alias = false;
+	static bool seen_dev_with_alias;
+	static bool seen_dev_without_alias;
 	int ret = index;
 
 	if (!IS_ENABLED(CONFIG_OF))
@@ -2672,7 +2668,7 @@ static int pl011_probe_dt_alias(int index, struct device *dev)
 		ret = index;
 	} else {
 		seen_dev_with_alias = true;
-		if (ret >= ARRAY_SIZE(amba_ports) || amba_ports[ret] != NULL) {
+		if (ret >= ARRAY_SIZE(amba_ports) || amba_ports[ret]) {
 			dev_warn(dev, "requested serial port %d  not available.\n", ret);
 			ret = index;
 		}
@@ -2706,7 +2702,7 @@ static int pl011_find_free_port(void)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(amba_ports); i++)
-		if (amba_ports[i] == NULL)
+		if (!amba_ports[i])
 			return i;
 
 	return -EBUSY;
@@ -2873,6 +2869,22 @@ static int pl011_resume(struct device *dev)
 
 static SIMPLE_DEV_PM_OPS(pl011_dev_pm_ops, pl011_suspend, pl011_resume);
 
+#ifdef CONFIG_ACPI_SPCR_TABLE
+static void qpdf2400_erratum44_workaround(struct device *dev,
+					  struct uart_amba_port *uap)
+{
+	if (!qdf2400_e44_present)
+		return;
+
+	dev_info(dev, "working around QDF2400 SoC erratum 44\n");
+	uap->vendor = &vendor_qdt_qdf2400_e44;
+}
+#else
+static void qpdf2400_erratum44_workaround(struct device *dev,
+					  struct uart_amba_port *uap)
+{ /* empty */ }
+#endif
+
 static int sbsa_uart_probe(struct platform_device *pdev)
 {
 	struct uart_amba_port *uap;
@@ -2908,13 +2920,8 @@ static int sbsa_uart_probe(struct platform_device *pdev)
 		return ret;
 	uap->port.irq	= ret;
 
-#ifdef CONFIG_ACPI_SPCR_TABLE
-	if (qdf2400_e44_present) {
-		dev_info(&pdev->dev, "working around QDF2400 SoC erratum 44\n");
-		uap->vendor = &vendor_qdt_qdf2400_e44;
-	} else
-#endif
-		uap->vendor = &vendor_sbsa;
+	uap->vendor = &vendor_sbsa;
+	qpdf2400_erratum44_workaround(&pdev->dev, uap);
 
 	uap->reg_offset	= uap->vendor->reg_offset;
 	uap->fifosize	= 32;
@@ -2935,13 +2942,12 @@ static int sbsa_uart_probe(struct platform_device *pdev)
 	return pl011_register_port(uap);
 }
 
-static int sbsa_uart_remove(struct platform_device *pdev)
+static void sbsa_uart_remove(struct platform_device *pdev)
 {
 	struct uart_amba_port *uap = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&amba_reg, &uap->port);
 	pl011_unregister_port(uap);
-	return 0;
 }
 
 static const struct of_device_id sbsa_uart_of_match[] = {
@@ -2959,7 +2965,7 @@ MODULE_DEVICE_TABLE(acpi, sbsa_uart_acpi_match);
 
 static struct platform_driver arm_sbsa_uart_platform_driver = {
 	.probe		= sbsa_uart_probe,
-	.remove		= sbsa_uart_remove,
+	.remove_new	= sbsa_uart_remove,
 	.driver	= {
 		.name	= "sbsa-uart",
 		.pm	= &pl011_dev_pm_ops,
@@ -2998,7 +3004,7 @@ static struct amba_driver pl011_driver = {
 
 static int __init pl011_init(void)
 {
-	printk(KERN_INFO "Serial: AMBA PL011 UART driver\n");
+	pr_info("Serial: AMBA PL011 UART driver\n");
 
 	if (platform_driver_register(&arm_sbsa_uart_platform_driver))
 		pr_warn("could not register SBSA UART platform driver\n");
diff --git a/drivers/tty/serial/apbuart.c b/drivers/tty/serial/apbuart.c
index 716cb014c028..364599f256db 100644
--- a/drivers/tty/serial/apbuart.c
+++ b/drivers/tty/serial/apbuart.c
@@ -122,7 +122,7 @@ static void apbuart_tx_chars(struct uart_port *port)
 {
 	u8 ch;
 
-	uart_port_tx_limited(port, ch, port->fifosize >> 1,
+	uart_port_tx_limited(port, ch, port->fifosize,
 		true,
 		UART_PUT_CHAR(port, ch),
 		({}));
diff --git a/drivers/tty/serial/ar933x_uart.c b/drivers/tty/serial/ar933x_uart.c
index ffd234673177..8d09ace062e5 100644
--- a/drivers/tty/serial/ar933x_uart.c
+++ b/drivers/tty/serial/ar933x_uart.c
@@ -818,7 +818,7 @@ err_disable_clk:
 	return ret;
 }
 
-static int ar933x_uart_remove(struct platform_device *pdev)
+static void ar933x_uart_remove(struct platform_device *pdev)
 {
 	struct ar933x_uart_port *up;
 
@@ -828,8 +828,6 @@ static int ar933x_uart_remove(struct platform_device *pdev)
 		uart_remove_one_port(&ar933x_uart_driver, &up->port);
 		clk_disable_unprepare(up->clk);
 	}
-
-	return 0;
 }
 
 #ifdef CONFIG_OF
@@ -842,7 +840,7 @@ MODULE_DEVICE_TABLE(of, ar933x_uart_of_ids);
 
 static struct platform_driver ar933x_uart_platform_driver = {
 	.probe		= ar933x_uart_probe,
-	.remove		= ar933x_uart_remove,
+	.remove_new	= ar933x_uart_remove,
 	.driver		= {
 		.name		= DRIVER_NAME,
 		.of_match_table = of_match_ptr(ar933x_uart_of_ids),
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index 1946fafc3f3e..85667f709515 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -1013,14 +1013,18 @@ static int atmel_prepare_tx_dma(struct uart_port *port)
 	struct device *mfd_dev = port->dev->parent;
 	dma_cap_mask_t		mask;
 	struct dma_slave_config config;
+	struct dma_chan *chan;
 	int ret, nent;
 
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);
 
-	atmel_port->chan_tx = dma_request_slave_channel(mfd_dev, "tx");
-	if (atmel_port->chan_tx == NULL)
+	chan = dma_request_chan(mfd_dev, "tx");
+	if (IS_ERR(chan)) {
+		atmel_port->chan_tx = NULL;
 		goto chan_err;
+	}
+	atmel_port->chan_tx = chan;
 	dev_info(port->dev, "using %s for tx DMA transfers\n",
 		dma_chan_name(atmel_port->chan_tx));
 
@@ -1188,6 +1192,7 @@ static int atmel_prepare_rx_dma(struct uart_port *port)
 	dma_cap_mask_t		mask;
 	struct dma_slave_config config;
 	struct circ_buf		*ring;
+	struct dma_chan *chan;
 	int ret, nent;
 
 	ring = &atmel_port->rx_ring;
@@ -1195,9 +1200,12 @@ static int atmel_prepare_rx_dma(struct uart_port *port)
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_CYCLIC, mask);
 
-	atmel_port->chan_rx = dma_request_slave_channel(mfd_dev, "rx");
-	if (atmel_port->chan_rx == NULL)
+	chan = dma_request_chan(mfd_dev, "rx");
+	if (IS_ERR(chan)) {
+		atmel_port->chan_rx = NULL;
 		goto chan_err;
+	}
+	atmel_port->chan_rx = chan;
 	dev_info(port->dev, "using %s for rx DMA transfers\n",
 		dma_chan_name(atmel_port->chan_rx));
 
@@ -3001,7 +3009,7 @@ err:
  * protocol that needs bitbanging on IO lines, but use the regular serial
  * port in the normal case.
  */
-static int atmel_serial_remove(struct platform_device *pdev)
+static void atmel_serial_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 	struct atmel_uart_port *atmel_port = to_atmel_uart_port(port);
@@ -3020,8 +3028,6 @@ static int atmel_serial_remove(struct platform_device *pdev)
 	clear_bit(port->line, atmel_ports_in_use);
 
 	pdev->dev.of_node = NULL;
-
-	return 0;
 }
 
 static SIMPLE_DEV_PM_OPS(atmel_serial_pm_ops, atmel_serial_suspend,
@@ -3029,7 +3035,7 @@ static SIMPLE_DEV_PM_OPS(atmel_serial_pm_ops, atmel_serial_suspend,
 
 static struct platform_driver atmel_serial_driver = {
 	.probe		= atmel_serial_probe,
-	.remove		= atmel_serial_remove,
+	.remove_new	= atmel_serial_remove,
 	.driver		= {
 		.name			= "atmel_usart_serial",
 		.of_match_table		= of_match_ptr(atmel_serial_dt_ids),
diff --git a/drivers/tty/serial/bcm63xx_uart.c b/drivers/tty/serial/bcm63xx_uart.c
index 4a08fd5ee61b..a3cefa153456 100644
--- a/drivers/tty/serial/bcm63xx_uart.c
+++ b/drivers/tty/serial/bcm63xx_uart.c
@@ -868,7 +868,7 @@ static int bcm_uart_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int bcm_uart_remove(struct platform_device *pdev)
+static void bcm_uart_remove(struct platform_device *pdev)
 {
 	struct uart_port *port;
 
@@ -876,7 +876,6 @@ static int bcm_uart_remove(struct platform_device *pdev)
 	uart_remove_one_port(&bcm_uart_driver, port);
 	/* mark port as free */
 	ports[pdev->id].membase = NULL;
-	return 0;
 }
 
 static const struct of_device_id bcm63xx_of_match[] = {
@@ -890,7 +889,7 @@ MODULE_DEVICE_TABLE(of, bcm63xx_of_match);
  */
 static struct platform_driver bcm_uart_platform_driver = {
 	.probe	= bcm_uart_probe,
-	.remove	= bcm_uart_remove,
+	.remove_new = bcm_uart_remove,
 	.driver	= {
 		.name  = "bcm63xx_uart",
 		.of_match_table = bcm63xx_of_match,
diff --git a/drivers/tty/serial/clps711x.c b/drivers/tty/serial/clps711x.c
index 55d19937efbd..7927725b8957 100644
--- a/drivers/tty/serial/clps711x.c
+++ b/drivers/tty/serial/clps711x.c
@@ -510,13 +510,11 @@ static int uart_clps711x_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int uart_clps711x_remove(struct platform_device *pdev)
+static void uart_clps711x_remove(struct platform_device *pdev)
 {
 	struct clps711x_port *s = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&clps711x_uart, &s->port);
-
-	return 0;
 }
 
 static const struct of_device_id __maybe_unused clps711x_uart_dt_ids[] = {
@@ -531,7 +529,7 @@ static struct platform_driver clps711x_uart_platform = {
 		.of_match_table	= of_match_ptr(clps711x_uart_dt_ids),
 	},
 	.probe	= uart_clps711x_probe,
-	.remove	= uart_clps711x_remove,
+	.remove_new = uart_clps711x_remove,
 };
 
 static int __init uart_clps711x_init(void)
diff --git a/drivers/tty/serial/cpm_uart.c b/drivers/tty/serial/cpm_uart.c
index be4af6eda4c2..df56c6c5afd0 100644
--- a/drivers/tty/serial/cpm_uart.c
+++ b/drivers/tty/serial/cpm_uart.c
@@ -1549,13 +1549,11 @@ static int cpm_uart_probe(struct platform_device *ofdev)
 	return ret;
 }
 
-static int cpm_uart_remove(struct platform_device *ofdev)
+static void cpm_uart_remove(struct platform_device *ofdev)
 {
 	struct uart_cpm_port *pinfo = platform_get_drvdata(ofdev);
 
 	uart_remove_one_port(&cpm_reg, &pinfo->port);
-
-	return 0;
 }
 
 static const struct of_device_id cpm_uart_match[] = {
@@ -1581,7 +1579,7 @@ static struct platform_driver cpm_uart_driver = {
 		.of_match_table = cpm_uart_match,
 	},
 	.probe = cpm_uart_probe,
-	.remove = cpm_uart_remove,
+	.remove_new = cpm_uart_remove,
  };
 
 static int __init cpm_uart_init(void)
diff --git a/drivers/tty/serial/digicolor-usart.c b/drivers/tty/serial/digicolor-usart.c
index 5004125f3045..e419c4bde8b7 100644
--- a/drivers/tty/serial/digicolor-usart.c
+++ b/drivers/tty/serial/digicolor-usart.c
@@ -503,13 +503,11 @@ static int digicolor_uart_probe(struct platform_device *pdev)
 	return uart_add_one_port(&digicolor_uart, &dp->port);
 }
 
-static int digicolor_uart_remove(struct platform_device *pdev)
+static void digicolor_uart_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&digicolor_uart, port);
-
-	return 0;
 }
 
 static const struct of_device_id digicolor_uart_dt_ids[] = {
@@ -524,7 +522,7 @@ static struct platform_driver digicolor_uart_platform = {
 		.of_match_table	= of_match_ptr(digicolor_uart_dt_ids),
 	},
 	.probe	= digicolor_uart_probe,
-	.remove	= digicolor_uart_remove,
+	.remove_new = digicolor_uart_remove,
 };
 
 static int __init digicolor_uart_init(void)
diff --git a/drivers/tty/serial/earlycon-riscv-sbi.c b/drivers/tty/serial/earlycon-riscv-sbi.c
index 27afb0b74ea7..0162155f0c83 100644
--- a/drivers/tty/serial/earlycon-riscv-sbi.c
+++ b/drivers/tty/serial/earlycon-riscv-sbi.c
@@ -15,17 +15,38 @@ static void sbi_putc(struct uart_port *port, unsigned char c)
 	sbi_console_putchar(c);
 }
 
-static void sbi_console_write(struct console *con,
-			      const char *s, unsigned n)
+static void sbi_0_1_console_write(struct console *con,
+				  const char *s, unsigned int n)
 {
 	struct earlycon_device *dev = con->data;
 	uart_console_write(&dev->port, s, n, sbi_putc);
 }
 
+static void sbi_dbcn_console_write(struct console *con,
+				   const char *s, unsigned int n)
+{
+	int ret;
+
+	while (n) {
+		ret = sbi_debug_console_write(s, n);
+		if (ret < 0)
+			break;
+
+		s += ret;
+		n -= ret;
+	}
+}
+
 static int __init early_sbi_setup(struct earlycon_device *device,
 				  const char *opt)
 {
-	device->con->write = sbi_console_write;
+	if (sbi_debug_console_available)
+		device->con->write = sbi_dbcn_console_write;
+	else if (IS_ENABLED(CONFIG_RISCV_SBI_V01))
+		device->con->write = sbi_0_1_console_write;
+	else
+		return -ENODEV;
+
 	return 0;
 }
 EARLYCON_DECLARE(sbi, early_sbi_setup);
diff --git a/drivers/tty/serial/esp32_acm.c b/drivers/tty/serial/esp32_acm.c
index cb28a87736aa..d4e8bdb1cdef 100644
--- a/drivers/tty/serial/esp32_acm.c
+++ b/drivers/tty/serial/esp32_acm.c
@@ -8,7 +8,7 @@
 #include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
+#include <linux/platform_device.h>
 #include <linux/serial_core.h>
 #include <linux/slab.h>
 #include <linux/tty_flip.h>
@@ -413,18 +413,17 @@ static int esp32s3_acm_probe(struct platform_device *pdev)
 	return uart_add_one_port(&esp32s3_acm_reg, port);
 }
 
-static int esp32s3_acm_remove(struct platform_device *pdev)
+static void esp32s3_acm_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&esp32s3_acm_reg, port);
-	return 0;
 }
 
 
 static struct platform_driver esp32s3_acm_driver = {
 	.probe		= esp32s3_acm_probe,
-	.remove		= esp32s3_acm_remove,
+	.remove_new	= esp32s3_acm_remove,
 	.driver		= {
 		.name	= DRIVER_NAME,
 		.of_match_table	= esp32s3_acm_dt_ids,
diff --git a/drivers/tty/serial/esp32_uart.c b/drivers/tty/serial/esp32_uart.c
index 85c9c5ad7cc5..6fc61f323355 100644
--- a/drivers/tty/serial/esp32_uart.c
+++ b/drivers/tty/serial/esp32_uart.c
@@ -9,7 +9,8 @@
 #include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/serial_core.h>
 #include <linux/slab.h>
 #include <linux/tty_flip.h>
@@ -678,16 +679,11 @@ static struct uart_driver esp32_uart_reg = {
 static int esp32_uart_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
-	static const struct of_device_id *match;
 	struct uart_port *port;
 	struct esp32_port *sport;
 	struct resource *res;
 	int ret;
 
-	match = of_match_device(esp32_uart_dt_ids, &pdev->dev);
-	if (!match)
-		return -ENODEV;
-
 	sport = devm_kzalloc(&pdev->dev, sizeof(*sport), GFP_KERNEL);
 	if (!sport)
 		return -ENOMEM;
@@ -728,7 +724,7 @@ static int esp32_uart_probe(struct platform_device *pdev)
 	port->flags = UPF_BOOT_AUTOCONF;
 	port->has_sysrq = 1;
 	port->fifosize = ESP32_UART_TX_FIFO_SIZE;
-	port->private_data = (void *)match->data;
+	port->private_data = (void *)device_get_match_data(&pdev->dev);
 
 	esp32_uart_ports[port->line] = sport;
 
@@ -737,19 +733,17 @@ static int esp32_uart_probe(struct platform_device *pdev)
 	return uart_add_one_port(&esp32_uart_reg, port);
 }
 
-static int esp32_uart_remove(struct platform_device *pdev)
+static void esp32_uart_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&esp32_uart_reg, port);
-
-	return 0;
 }
 
 
 static struct platform_driver esp32_uart_driver = {
 	.probe		= esp32_uart_probe,
-	.remove		= esp32_uart_remove,
+	.remove_new	= esp32_uart_remove,
 	.driver		= {
 		.name	= DRIVER_NAME,
 		.of_match_table	= esp32_uart_dt_ids,
diff --git a/drivers/tty/serial/fsl_linflexuart.c b/drivers/tty/serial/fsl_linflexuart.c
index 3bdaf1ddc309..52c87876a88d 100644
--- a/drivers/tty/serial/fsl_linflexuart.c
+++ b/drivers/tty/serial/fsl_linflexuart.c
@@ -851,13 +851,11 @@ static int linflex_probe(struct platform_device *pdev)
 	return uart_add_one_port(&linflex_reg, sport);
 }
 
-static int linflex_remove(struct platform_device *pdev)
+static void linflex_remove(struct platform_device *pdev)
 {
 	struct uart_port *sport = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&linflex_reg, sport);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -884,7 +882,7 @@ static SIMPLE_DEV_PM_OPS(linflex_pm_ops, linflex_suspend, linflex_resume);
 
 static struct platform_driver linflex_driver = {
 	.probe		= linflex_probe,
-	.remove		= linflex_remove,
+	.remove_new	= linflex_remove,
 	.driver		= {
 		.name	= DRIVER_NAME,
 		.of_match_table	= linflex_dt_ids,
diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c
index 6d0cfb2e86b4..bbcbc91482af 100644
--- a/drivers/tty/serial/fsl_lpuart.c
+++ b/drivers/tty/serial/fsl_lpuart.c
@@ -2345,9 +2345,12 @@ lpuart32_set_termios(struct uart_port *port, struct ktermios *termios,
 
 	lpuart32_write(&sport->port, bd, UARTBAUD);
 	lpuart32_serial_setbrg(sport, baud);
-	lpuart32_write(&sport->port, modem, UARTMODIR);
-	lpuart32_write(&sport->port, ctrl, UARTCTRL);
+	/* disable CTS before enabling UARTCTRL_TE to avoid pending idle preamble */
+	lpuart32_write(&sport->port, modem & ~UARTMODIR_TXCTSE, UARTMODIR);
 	/* restore control register */
+	lpuart32_write(&sport->port, ctrl, UARTCTRL);
+	/* re-enable the CTS if needed */
+	lpuart32_write(&sport->port, modem, UARTMODIR);
 
 	if ((ctrl & (UARTCTRL_PE | UARTCTRL_M)) == UARTCTRL_PE)
 		sport->is_cs7 = true;
@@ -2959,7 +2962,7 @@ failed_reset:
 	return ret;
 }
 
-static int lpuart_remove(struct platform_device *pdev)
+static void lpuart_remove(struct platform_device *pdev)
 {
 	struct lpuart_port *sport = platform_get_drvdata(pdev);
 
@@ -2976,7 +2979,6 @@ static int lpuart_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_set_suspended(&pdev->dev);
 	pm_runtime_dont_use_autosuspend(&pdev->dev);
-	return 0;
 }
 
 static int lpuart_runtime_suspend(struct device *dev)
@@ -3210,7 +3212,7 @@ static const struct dev_pm_ops lpuart_pm_ops = {
 
 static struct platform_driver lpuart_driver = {
 	.probe		= lpuart_probe,
-	.remove		= lpuart_remove,
+	.remove_new	= lpuart_remove,
 	.driver		= {
 		.name	= "fsl-lpuart",
 		.of_match_table = lpuart_dt_ids,
diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index 708b9852a575..e14813250616 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -415,13 +415,13 @@ static void imx_uart_stop_tx(struct uart_port *port)
 	ucr1 = imx_uart_readl(sport, UCR1);
 	imx_uart_writel(sport, ucr1 & ~UCR1_TRDYEN, UCR1);
 
+	ucr4 = imx_uart_readl(sport, UCR4);
 	usr2 = imx_uart_readl(sport, USR2);
-	if (!(usr2 & USR2_TXDC)) {
+	if ((!(usr2 & USR2_TXDC)) && (ucr4 & UCR4_TCEN)) {
 		/* The shifter is still busy, so retry once TC triggers */
 		return;
 	}
 
-	ucr4 = imx_uart_readl(sport, UCR4);
 	ucr4 &= ~UCR4_TCEN;
 	imx_uart_writel(sport, ucr4, UCR4);
 
@@ -462,8 +462,7 @@ static void imx_uart_stop_tx(struct uart_port *port)
 	}
 }
 
-/* called with port.lock taken and irqs off */
-static void imx_uart_stop_rx(struct uart_port *port)
+static void imx_uart_stop_rx_with_loopback_ctrl(struct uart_port *port, bool loopback)
 {
 	struct imx_port *sport = (struct imx_port *)port;
 	u32 ucr1, ucr2, ucr4, uts;
@@ -485,7 +484,7 @@ static void imx_uart_stop_rx(struct uart_port *port)
 	/* See SER_RS485_ENABLED/UTS_LOOP comment in imx_uart_probe() */
 	if (port->rs485.flags & SER_RS485_ENABLED &&
 	    port->rs485.flags & SER_RS485_RTS_ON_SEND &&
-	    sport->have_rtscts && !sport->have_rtsgpio) {
+	    sport->have_rtscts && !sport->have_rtsgpio && loopback) {
 		uts = imx_uart_readl(sport, imx_uart_uts_reg(sport));
 		uts |= UTS_LOOP;
 		imx_uart_writel(sport, uts, imx_uart_uts_reg(sport));
@@ -498,6 +497,16 @@ static void imx_uart_stop_rx(struct uart_port *port)
 }
 
 /* called with port.lock taken and irqs off */
+static void imx_uart_stop_rx(struct uart_port *port)
+{
+	/*
+	 * Stop RX and enable loopback in order to make sure RS485 bus
+	 * is not blocked. Se comment in imx_uart_probe().
+	 */
+	imx_uart_stop_rx_with_loopback_ctrl(port, true);
+}
+
+/* called with port.lock taken and irqs off */
 static void imx_uart_enable_ms(struct uart_port *port)
 {
 	struct imx_port *sport = (struct imx_port *)port;
@@ -682,9 +691,14 @@ static void imx_uart_start_tx(struct uart_port *port)
 				imx_uart_rts_inactive(sport, &ucr2);
 			imx_uart_writel(sport, ucr2, UCR2);
 
+			/*
+			 * Since we are about to transmit we can not stop RX
+			 * with loopback enabled because that will make our
+			 * transmitted data being just looped to RX.
+			 */
 			if (!(port->rs485.flags & SER_RS485_RX_DURING_TX) &&
 			    !port->rs485_rx_during_tx_gpio)
-				imx_uart_stop_rx(port);
+				imx_uart_stop_rx_with_loopback_ctrl(port, false);
 
 			sport->tx_state = WAIT_AFTER_RTS;
 
@@ -1336,15 +1350,18 @@ static int imx_uart_dma_init(struct imx_port *sport)
 {
 	struct dma_slave_config slave_config = {};
 	struct device *dev = sport->port.dev;
+	struct dma_chan *chan;
 	int ret;
 
 	/* Prepare for RX : */
-	sport->dma_chan_rx = dma_request_slave_channel(dev, "rx");
-	if (!sport->dma_chan_rx) {
+	chan = dma_request_chan(dev, "rx");
+	if (IS_ERR(chan)) {
 		dev_dbg(dev, "cannot get the DMA channel.\n");
-		ret = -EINVAL;
+		sport->dma_chan_rx = NULL;
+		ret = PTR_ERR(chan);
 		goto err;
 	}
+	sport->dma_chan_rx = chan;
 
 	slave_config.direction = DMA_DEV_TO_MEM;
 	slave_config.src_addr = sport->port.mapbase + URXD0;
@@ -1366,12 +1383,14 @@ static int imx_uart_dma_init(struct imx_port *sport)
 	sport->rx_ring.buf = sport->rx_buf;
 
 	/* Prepare for TX : */
-	sport->dma_chan_tx = dma_request_slave_channel(dev, "tx");
-	if (!sport->dma_chan_tx) {
+	chan = dma_request_chan(dev, "tx");
+	if (IS_ERR(chan)) {
 		dev_err(dev, "cannot get the TX DMA channel!\n");
-		ret = -EINVAL;
+		sport->dma_chan_tx = NULL;
+		ret = PTR_ERR(chan);
 		goto err;
 	}
+	sport->dma_chan_tx = chan;
 
 	slave_config.direction = DMA_MEM_TO_DEV;
 	slave_config.dst_addr = sport->port.mapbase + URTX0;
@@ -1943,10 +1962,6 @@ static int imx_uart_rs485_config(struct uart_port *port, struct ktermios *termio
 	    rs485conf->flags & SER_RS485_RX_DURING_TX)
 		imx_uart_start_rx(port);
 
-	if (port->rs485_rx_during_tx_gpio)
-		gpiod_set_value_cansleep(port->rs485_rx_during_tx_gpio,
-					 !!(rs485conf->flags & SER_RS485_RX_DURING_TX));
-
 	return 0;
 }
 
@@ -2210,7 +2225,6 @@ static enum hrtimer_restart imx_trigger_stop_tx(struct hrtimer *t)
 	return HRTIMER_NORESTART;
 }
 
-static const struct serial_rs485 imx_no_rs485 = {};	/* No RS485 if no RTS */
 static const struct serial_rs485 imx_rs485_supported = {
 	.flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | SER_RS485_RTS_AFTER_SEND |
 		 SER_RS485_RX_DURING_TX,
@@ -2294,8 +2308,6 @@ static int imx_uart_probe(struct platform_device *pdev)
 	/* RTS is required to control the RS485 transmitter */
 	if (sport->have_rtscts || sport->have_rtsgpio)
 		sport->port.rs485_supported = imx_rs485_supported;
-	else
-		sport->port.rs485_supported = imx_no_rs485;
 	sport->port.flags = UPF_BOOT_AUTOCONF;
 	timer_setup(&sport->timer, imx_uart_timeout, 0);
 
@@ -2322,19 +2334,13 @@ static int imx_uart_probe(struct platform_device *pdev)
 	/* For register access, we only need to enable the ipg clock. */
 	ret = clk_prepare_enable(sport->clk_ipg);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to enable per clk: %d\n", ret);
+		dev_err(&pdev->dev, "failed to enable ipg clk: %d\n", ret);
 		return ret;
 	}
 
 	ret = uart_get_rs485_mode(&sport->port);
-	if (ret) {
-		clk_disable_unprepare(sport->clk_ipg);
-		return ret;
-	}
-
-	if (sport->port.rs485.flags & SER_RS485_ENABLED &&
-	    (!sport->have_rtscts && !sport->have_rtsgpio))
-		dev_err(&pdev->dev, "no RTS control, disabling rs485\n");
+	if (ret)
+		goto err_clk;
 
 	/*
 	 * If using the i.MX UART RTS/CTS control then the RTS (CTS_B)
@@ -2414,8 +2420,6 @@ static int imx_uart_probe(struct platform_device *pdev)
 		imx_uart_writel(sport, ucr3, UCR3);
 	}
 
-	clk_disable_unprepare(sport->clk_ipg);
-
 	hrtimer_init(&sport->trigger_start_tx, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hrtimer_init(&sport->trigger_stop_tx, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	sport->trigger_start_tx.function = imx_trigger_start_tx;
@@ -2431,7 +2435,7 @@ static int imx_uart_probe(struct platform_device *pdev)
 		if (ret) {
 			dev_err(&pdev->dev, "failed to request rx irq: %d\n",
 				ret);
-			return ret;
+			goto err_clk;
 		}
 
 		ret = devm_request_irq(&pdev->dev, txirq, imx_uart_txint, 0,
@@ -2439,7 +2443,7 @@ static int imx_uart_probe(struct platform_device *pdev)
 		if (ret) {
 			dev_err(&pdev->dev, "failed to request tx irq: %d\n",
 				ret);
-			return ret;
+			goto err_clk;
 		}
 
 		ret = devm_request_irq(&pdev->dev, rtsirq, imx_uart_rtsint, 0,
@@ -2447,14 +2451,14 @@ static int imx_uart_probe(struct platform_device *pdev)
 		if (ret) {
 			dev_err(&pdev->dev, "failed to request rts irq: %d\n",
 				ret);
-			return ret;
+			goto err_clk;
 		}
 	} else {
 		ret = devm_request_irq(&pdev->dev, rxirq, imx_uart_int, 0,
 				       dev_name(&pdev->dev), sport);
 		if (ret) {
 			dev_err(&pdev->dev, "failed to request irq: %d\n", ret);
-			return ret;
+			goto err_clk;
 		}
 	}
 
@@ -2462,16 +2466,19 @@ static int imx_uart_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, sport);
 
-	return uart_add_one_port(&imx_uart_uart_driver, &sport->port);
+	ret = uart_add_one_port(&imx_uart_uart_driver, &sport->port);
+
+err_clk:
+	clk_disable_unprepare(sport->clk_ipg);
+
+	return ret;
 }
 
-static int imx_uart_remove(struct platform_device *pdev)
+static void imx_uart_remove(struct platform_device *pdev)
 {
 	struct imx_port *sport = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&imx_uart_uart_driver, &sport->port);
-
-	return 0;
 }
 
 static void imx_uart_restore_context(struct imx_port *sport)
@@ -2640,7 +2647,7 @@ static const struct dev_pm_ops imx_uart_pm_ops = {
 
 static struct platform_driver imx_uart_platform_driver = {
 	.probe = imx_uart_probe,
-	.remove = imx_uart_remove,
+	.remove_new = imx_uart_remove,
 
 	.driver = {
 		.name = "imx-uart",
diff --git a/drivers/tty/serial/jsm/jsm.h b/drivers/tty/serial/jsm/jsm.h
index 8489c07f4cd5..df55e5dc5afc 100644
--- a/drivers/tty/serial/jsm/jsm.h
+++ b/drivers/tty/serial/jsm/jsm.h
@@ -115,8 +115,6 @@ struct board_ops {
 	void (*send_start_character)(struct jsm_channel *ch);
 	void (*send_stop_character)(struct jsm_channel *ch);
 	void (*copy_data_from_queue_to_uart)(struct jsm_channel *ch);
-	u32 (*get_uart_bytes_left)(struct jsm_channel *ch);
-	void (*send_immediate_char)(struct jsm_channel *ch, unsigned char);
 };
 
 
@@ -127,7 +125,6 @@ struct jsm_board
 {
 	int		boardnum;	/* Board number: 0-32 */
 
-	int		type;		/* Type of board */
 	u8		rev;		/* PCI revision ID */
 	struct pci_dev	*pci_dev;
 	u32		maxports;	/* MAX ports this board can handle */
@@ -155,8 +152,6 @@ struct jsm_board
 	u32		bd_dividend;	/* Board/UARTs specific dividend */
 
 	struct board_ops *bd_ops;
-
-	struct list_head jsm_board_entry;
 };
 
 /************************************************************************
diff --git a/drivers/tty/serial/jsm/jsm_cls.c b/drivers/tty/serial/jsm/jsm_cls.c
index 3fd57ac3ad81..1eda48964c0b 100644
--- a/drivers/tty/serial/jsm/jsm_cls.c
+++ b/drivers/tty/serial/jsm/jsm_cls.c
@@ -878,28 +878,6 @@ static void cls_uart_off(struct jsm_channel *ch)
 }
 
 /*
- * cls_get_uarts_bytes_left.
- * Returns 0 is nothing left in the FIFO, returns 1 otherwise.
- *
- * The channel lock MUST be held by the calling function.
- */
-static u32 cls_get_uart_bytes_left(struct jsm_channel *ch)
-{
-	u8 left = 0;
-	u8 lsr = readb(&ch->ch_cls_uart->lsr);
-
-	/* Determine whether the Transmitter is empty or not */
-	if (!(lsr & UART_LSR_TEMT))
-		left = 1;
-	else {
-		ch->ch_flags |= (CH_TX_FIFO_EMPTY | CH_TX_FIFO_LWM);
-		left = 0;
-	}
-
-	return left;
-}
-
-/*
  * cls_send_break.
  * Starts sending a break thru the UART.
  *
@@ -916,18 +894,6 @@ static void cls_send_break(struct jsm_channel *ch)
 	}
 }
 
-/*
- * cls_send_immediate_char.
- * Sends a specific character as soon as possible to the UART,
- * jumping over any bytes that might be in the write queue.
- *
- * The channel lock MUST be held by the calling function.
- */
-static void cls_send_immediate_char(struct jsm_channel *ch, unsigned char c)
-{
-	writeb(c, &ch->ch_cls_uart->txrx);
-}
-
 struct board_ops jsm_cls_ops = {
 	.intr =				cls_intr,
 	.uart_init =			cls_uart_init,
@@ -943,7 +909,5 @@ struct board_ops jsm_cls_ops = {
 	.send_start_character =		cls_send_start_character,
 	.send_stop_character =		cls_send_stop_character,
 	.copy_data_from_queue_to_uart = cls_copy_data_from_queue_to_uart,
-	.get_uart_bytes_left =		cls_get_uart_bytes_left,
-	.send_immediate_char =		cls_send_immediate_char
 };
 
diff --git a/drivers/tty/serial/jsm/jsm_neo.c b/drivers/tty/serial/jsm/jsm_neo.c
index 2bd640428970..1fa10f19368f 100644
--- a/drivers/tty/serial/jsm/jsm_neo.c
+++ b/drivers/tty/serial/jsm/jsm_neo.c
@@ -1309,25 +1309,6 @@ static void neo_uart_off(struct jsm_channel *ch)
 	writeb(0, &ch->ch_neo_uart->ier);
 }
 
-static u32 neo_get_uart_bytes_left(struct jsm_channel *ch)
-{
-	u8 left = 0;
-	u8 lsr = readb(&ch->ch_neo_uart->lsr);
-
-	/* We must cache the LSR as some of the bits get reset once read... */
-	ch->ch_cached_lsr |= lsr;
-
-	/* Determine whether the Transmitter is empty or not */
-	if (!(lsr & UART_LSR_TEMT))
-		left = 1;
-	else {
-		ch->ch_flags |= (CH_TX_FIFO_EMPTY | CH_TX_FIFO_LWM);
-		left = 0;
-	}
-
-	return left;
-}
-
 /* Channel lock MUST be held by the calling function! */
 static void neo_send_break(struct jsm_channel *ch)
 {
@@ -1348,25 +1329,6 @@ static void neo_send_break(struct jsm_channel *ch)
 	}
 }
 
-/*
- * neo_send_immediate_char.
- *
- * Sends a specific character as soon as possible to the UART,
- * jumping over any bytes that might be in the write queue.
- *
- * The channel lock MUST be held by the calling function.
- */
-static void neo_send_immediate_char(struct jsm_channel *ch, unsigned char c)
-{
-	if (!ch)
-		return;
-
-	writeb(c, &ch->ch_neo_uart->txrx);
-
-	/* flush write operation */
-	neo_pci_posting_flush(ch->ch_bd);
-}
-
 struct board_ops jsm_neo_ops = {
 	.intr				= neo_intr,
 	.uart_init			= neo_uart_init,
@@ -1382,6 +1344,4 @@ struct board_ops jsm_neo_ops = {
 	.send_start_character		= neo_send_start_character,
 	.send_stop_character		= neo_send_stop_character,
 	.copy_data_from_queue_to_uart	= neo_copy_data_from_queue_to_uart,
-	.get_uart_bytes_left		= neo_get_uart_bytes_left,
-	.send_immediate_char		= neo_send_immediate_char
 };
diff --git a/drivers/tty/serial/lantiq.c b/drivers/tty/serial/lantiq.c
index 3adb60c683f7..a0731773ce75 100644
--- a/drivers/tty/serial/lantiq.c
+++ b/drivers/tty/serial/lantiq.c
@@ -887,13 +887,11 @@ static int lqasc_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int lqasc_remove(struct platform_device *pdev)
+static void lqasc_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&lqasc_reg, port);
-
-	return 0;
 }
 
 static const struct ltq_soc_data soc_data_lantiq = {
@@ -917,7 +915,7 @@ MODULE_DEVICE_TABLE(of, ltq_asc_match);
 
 static struct platform_driver lqasc_driver = {
 	.probe		= lqasc_probe,
-	.remove		= lqasc_remove,
+	.remove_new	= lqasc_remove,
 	.driver		= {
 		.name	= DRVNAME,
 		.of_match_table = ltq_asc_match,
diff --git a/drivers/tty/serial/liteuart.c b/drivers/tty/serial/liteuart.c
index a25ab1efe38f..3ce369f76349 100644
--- a/drivers/tty/serial/liteuart.c
+++ b/drivers/tty/serial/liteuart.c
@@ -336,15 +336,13 @@ err_erase_id:
 	return ret;
 }
 
-static int liteuart_remove(struct platform_device *pdev)
+static void liteuart_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 	unsigned int line = port->line;
 
 	uart_remove_one_port(&liteuart_driver, port);
 	xa_erase(&liteuart_array, line);
-
-	return 0;
 }
 
 static const struct of_device_id liteuart_of_match[] = {
@@ -355,7 +353,7 @@ MODULE_DEVICE_TABLE(of, liteuart_of_match);
 
 static struct platform_driver liteuart_platform_driver = {
 	.probe = liteuart_probe,
-	.remove = liteuart_remove,
+	.remove_new = liteuart_remove,
 	.driver = {
 		.name = KBUILD_MODNAME,
 		.of_match_table = liteuart_of_match,
diff --git a/drivers/tty/serial/lpc32xx_hs.c b/drivers/tty/serial/lpc32xx_hs.c
index 5149a947b7fe..ec20329f0603 100644
--- a/drivers/tty/serial/lpc32xx_hs.c
+++ b/drivers/tty/serial/lpc32xx_hs.c
@@ -659,13 +659,11 @@ static int serial_hs_lpc32xx_probe(struct platform_device *pdev)
 /*
  * Remove serial ports registered against a platform device.
  */
-static int serial_hs_lpc32xx_remove(struct platform_device *pdev)
+static void serial_hs_lpc32xx_remove(struct platform_device *pdev)
 {
 	struct lpc32xx_hsuart_port *p = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&lpc32xx_hs_reg, &p->port);
-
-	return 0;
 }
 
 
@@ -702,7 +700,7 @@ MODULE_DEVICE_TABLE(of, serial_hs_lpc32xx_dt_ids);
 
 static struct platform_driver serial_hs_lpc32xx_driver = {
 	.probe		= serial_hs_lpc32xx_probe,
-	.remove		= serial_hs_lpc32xx_remove,
+	.remove_new	= serial_hs_lpc32xx_remove,
 	.suspend	= serial_hs_lpc32xx_suspend,
 	.resume		= serial_hs_lpc32xx_resume,
 	.driver		= {
diff --git a/drivers/tty/serial/ma35d1_serial.c b/drivers/tty/serial/ma35d1_serial.c
index 21b574f78b86..19f0a305cc43 100644
--- a/drivers/tty/serial/ma35d1_serial.c
+++ b/drivers/tty/serial/ma35d1_serial.c
@@ -558,7 +558,7 @@ static void ma35d1serial_console_write(struct console *co, const char *s, u32 co
 	u32 ier;
 
 	if ((co->index < 0) || (co->index >= MA35_UART_NR)) {
-		pr_warn("Failed to write on ononsole port %x, out of range\n",
+		pr_warn("Failed to write on console port %x, out of range\n",
 			co->index);
 		return;
 	}
@@ -754,14 +754,13 @@ err_iounmap:
 /*
  * Remove serial ports registered against a platform device.
  */
-static int ma35d1serial_remove(struct platform_device *dev)
+static void ma35d1serial_remove(struct platform_device *dev)
 {
 	struct uart_port *port = platform_get_drvdata(dev);
 	struct uart_ma35d1_port *up = to_ma35d1_uart_port(port);
 
 	uart_remove_one_port(&ma35d1serial_reg, port);
 	clk_disable_unprepare(up->clk);
-	return 0;
 }
 
 static int ma35d1serial_suspend(struct platform_device *dev, pm_message_t state)
@@ -794,7 +793,7 @@ static int ma35d1serial_resume(struct platform_device *dev)
 
 static struct platform_driver ma35d1serial_driver = {
 	.probe      = ma35d1serial_probe,
-	.remove     = ma35d1serial_remove,
+	.remove_new = ma35d1serial_remove,
 	.suspend    = ma35d1serial_suspend,
 	.resume     = ma35d1serial_resume,
 	.driver     = {
diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c
index 97e4965b73d4..10bf6d75bf9e 100644
--- a/drivers/tty/serial/max310x.c
+++ b/drivers/tty/serial/max310x.c
@@ -237,6 +237,14 @@
 #define MAX310x_REV_MASK		(0xf8)
 #define MAX310X_WRITE_BIT		0x80
 
+/* Port startup definitions */
+#define MAX310X_PORT_STARTUP_WAIT_RETRIES	20 /* Number of retries */
+#define MAX310X_PORT_STARTUP_WAIT_DELAY_MS	10 /* Delay between retries */
+
+/* Crystal-related definitions */
+#define MAX310X_XTAL_WAIT_RETRIES	20 /* Number of retries */
+#define MAX310X_XTAL_WAIT_DELAY_MS	10 /* Delay between retries */
+
 /* MAX3107 specific */
 #define MAX3107_REV_ID			(0xa0)
 
@@ -583,7 +591,7 @@ static int max310x_update_best_err(unsigned long f, long *besterr)
 	return 1;
 }
 
-static u32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s,
+static s32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s,
 			       unsigned long freq, bool xtal)
 {
 	unsigned int div, clksrc, pllcfg = 0;
@@ -641,12 +649,20 @@ static u32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s,
 
 	/* Wait for crystal */
 	if (xtal) {
-		unsigned int val;
-		msleep(10);
-		regmap_read(s->regmap, MAX310X_STS_IRQSTS_REG, &val);
-		if (!(val & MAX310X_STS_CLKREADY_BIT)) {
-			dev_warn(dev, "clock is not stable yet\n");
-		}
+		bool stable = false;
+		unsigned int try = 0, val = 0;
+
+		do {
+			msleep(MAX310X_XTAL_WAIT_DELAY_MS);
+			regmap_read(s->regmap, MAX310X_STS_IRQSTS_REG, &val);
+
+			if (val & MAX310X_STS_CLKREADY_BIT)
+				stable = true;
+		} while (!stable && (++try < MAX310X_XTAL_WAIT_RETRIES));
+
+		if (!stable)
+			return dev_err_probe(dev, -EAGAIN,
+					     "clock is not stable\n");
 	}
 
 	return bestfreq;
@@ -780,7 +796,7 @@ static void max310x_handle_tx(struct uart_port *port)
 	to_send = uart_circ_chars_pending(xmit);
 	until_end = CIRC_CNT_TO_END(xmit->head, xmit->tail, UART_XMIT_SIZE);
 	if (likely(to_send)) {
-		/* Limit to size of TX FIFO */
+		/* Limit to space available in TX FIFO */
 		txlen = max310x_port_read(port, MAX310X_TXFIFOLVL_REG);
 		txlen = port->fifosize - txlen;
 		to_send = (to_send > txlen) ? txlen : to_send;
@@ -1271,7 +1287,7 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty
 {
 	int i, ret, fmin, fmax, freq;
 	struct max310x_port *s;
-	u32 uartclk = 0;
+	s32 uartclk = 0;
 	bool xtal;
 
 	for (i = 0; i < devtype->nr; i++)
@@ -1334,6 +1350,9 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty
 		goto out_clk;
 
 	for (i = 0; i < devtype->nr; i++) {
+		bool started = false;
+		unsigned int try = 0, val = 0;
+
 		/* Reset port */
 		regmap_write(regmaps[i], MAX310X_MODE2_REG,
 			     MAX310X_MODE2_RST_BIT);
@@ -1342,13 +1361,27 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty
 
 		/* Wait for port startup */
 		do {
-			regmap_read(regmaps[i], MAX310X_BRGDIVLSB_REG, &ret);
-		} while (ret != 0x01);
+			msleep(MAX310X_PORT_STARTUP_WAIT_DELAY_MS);
+			regmap_read(regmaps[i], MAX310X_BRGDIVLSB_REG, &val);
+
+			if (val == 0x01)
+				started = true;
+		} while (!started && (++try < MAX310X_PORT_STARTUP_WAIT_RETRIES));
+
+		if (!started) {
+			ret = dev_err_probe(dev, -EAGAIN, "port reset failed\n");
+			goto out_uart;
+		}
 
 		regmap_write(regmaps[i], MAX310X_MODE1_REG, devtype->mode1);
 	}
 
 	uartclk = max310x_set_ref_clk(dev, s, freq, xtal);
+	if (uartclk < 0) {
+		ret = uartclk;
+		goto out_uart;
+	}
+
 	dev_dbg(dev, "Reference clock set to %i Hz\n", uartclk);
 
 	for (i = 0; i < devtype->nr; i++) {
diff --git a/drivers/tty/serial/mcf.c b/drivers/tty/serial/mcf.c
index 91b15243f6c6..8690a45239e0 100644
--- a/drivers/tty/serial/mcf.c
+++ b/drivers/tty/serial/mcf.c
@@ -627,7 +627,7 @@ static int mcf_probe(struct platform_device *pdev)
 
 /****************************************************************************/
 
-static int mcf_remove(struct platform_device *pdev)
+static void mcf_remove(struct platform_device *pdev)
 {
 	struct uart_port *port;
 	int i;
@@ -637,15 +637,13 @@ static int mcf_remove(struct platform_device *pdev)
 		if (port)
 			uart_remove_one_port(&mcf_driver, port);
 	}
-
-	return 0;
 }
 
 /****************************************************************************/
 
 static struct platform_driver mcf_platform_driver = {
 	.probe		= mcf_probe,
-	.remove		= mcf_remove,
+	.remove_new	= mcf_remove,
 	.driver		= {
 		.name	= "mcfuart",
 	},
diff --git a/drivers/tty/serial/meson_uart.c b/drivers/tty/serial/meson_uart.c
index 8dd84617e715..8395688f5ee9 100644
--- a/drivers/tty/serial/meson_uart.c
+++ b/drivers/tty/serial/meson_uart.c
@@ -795,7 +795,7 @@ static int meson_uart_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int meson_uart_remove(struct platform_device *pdev)
+static void meson_uart_remove(struct platform_device *pdev)
 {
 	struct uart_driver *uart_driver;
 	struct uart_port *port;
@@ -807,12 +807,10 @@ static int meson_uart_remove(struct platform_device *pdev)
 
 	for (int id = 0; id < AML_UART_PORT_NUM; id++)
 		if (meson_ports[id])
-			return 0;
+			return;
 
 	/* No more available uart ports, unregister uart driver */
 	uart_unregister_driver(uart_driver);
-
-	return 0;
 }
 
 static struct meson_uart_data meson_g12a_uart_data = {
@@ -852,7 +850,7 @@ MODULE_DEVICE_TABLE(of, meson_uart_dt_match);
 
 static  struct platform_driver meson_uart_platform_driver = {
 	.probe		= meson_uart_probe,
-	.remove		= meson_uart_remove,
+	.remove_new	= meson_uart_remove,
 	.driver		= {
 		.name		= "meson_uart",
 		.of_match_table	= meson_uart_dt_match,
diff --git a/drivers/tty/serial/milbeaut_usio.c b/drivers/tty/serial/milbeaut_usio.c
index db3b81f2aa57..da4c6f7e2a30 100644
--- a/drivers/tty/serial/milbeaut_usio.c
+++ b/drivers/tty/serial/milbeaut_usio.c
@@ -552,15 +552,13 @@ failed:
 	return ret;
 }
 
-static int mlb_usio_remove(struct platform_device *pdev)
+static void mlb_usio_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = &mlb_usio_ports[pdev->id];
 	struct clk *clk = port->private_data;
 
 	uart_remove_one_port(&mlb_usio_uart_driver, port);
 	clk_disable_unprepare(clk);
-
-	return 0;
 }
 
 static const struct of_device_id mlb_usio_dt_ids[] = {
@@ -571,7 +569,7 @@ MODULE_DEVICE_TABLE(of, mlb_usio_dt_ids);
 
 static struct platform_driver mlb_usio_driver = {
 	.probe          = mlb_usio_probe,
-	.remove         = mlb_usio_remove,
+	.remove_new     = mlb_usio_remove,
 	.driver         = {
 		.name   = USIO_NAME,
 		.of_match_table = mlb_usio_dt_ids,
diff --git a/drivers/tty/serial/mpc52xx_uart.c b/drivers/tty/serial/mpc52xx_uart.c
index a252465e745f..95dae5e27b28 100644
--- a/drivers/tty/serial/mpc52xx_uart.c
+++ b/drivers/tty/serial/mpc52xx_uart.c
@@ -1765,15 +1765,12 @@ static int mpc52xx_uart_of_probe(struct platform_device *op)
 	return 0;
 }
 
-static int
-mpc52xx_uart_of_remove(struct platform_device *op)
+static void mpc52xx_uart_of_remove(struct platform_device *op)
 {
 	struct uart_port *port = platform_get_drvdata(op);
 
 	if (port)
 		uart_remove_one_port(&mpc52xx_uart_driver, port);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -1846,7 +1843,7 @@ MODULE_DEVICE_TABLE(of, mpc52xx_uart_of_match);
 
 static struct platform_driver mpc52xx_uart_of_driver = {
 	.probe		= mpc52xx_uart_of_probe,
-	.remove		= mpc52xx_uart_of_remove,
+	.remove_new	= mpc52xx_uart_of_remove,
 #ifdef CONFIG_PM
 	.suspend	= mpc52xx_uart_of_suspend,
 	.resume		= mpc52xx_uart_of_resume,
diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c
index 597264b546fd..e24204ad35de 100644
--- a/drivers/tty/serial/msm_serial.c
+++ b/drivers/tty/serial/msm_serial.c
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/clk.h>
 #include <linux/platform_device.h>
+#include <linux/pm_opp.h>
 #include <linux/delay.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
@@ -1131,7 +1132,7 @@ static int msm_set_baud_rate(struct uart_port *port, unsigned int baud,
 	uart_port_unlock_irqrestore(port, flags);
 
 	entry = msm_find_best_baud(port, baud, &rate);
-	clk_set_rate(msm_port->clk, rate);
+	dev_pm_opp_set_rate(port->dev, rate);
 	baud = rate / 16 / entry->divisor;
 
 	uart_port_lock_irqsave(port, &flags);
@@ -1186,6 +1187,7 @@ static void msm_init_clock(struct uart_port *port)
 {
 	struct msm_port *msm_port = to_msm_port(port);
 
+	dev_pm_opp_set_rate(port->dev, port->uartclk);
 	clk_prepare_enable(msm_port->clk);
 	clk_prepare_enable(msm_port->pclk);
 	msm_serial_set_mnd_regs(port);
@@ -1239,6 +1241,7 @@ err_irq:
 
 	clk_disable_unprepare(msm_port->pclk);
 	clk_disable_unprepare(msm_port->clk);
+	dev_pm_opp_set_rate(port->dev, 0);
 
 	return ret;
 }
@@ -1254,6 +1257,7 @@ static void msm_shutdown(struct uart_port *port)
 		msm_release_dma(msm_port);
 
 	clk_disable_unprepare(msm_port->clk);
+	dev_pm_opp_set_rate(port->dev, 0);
 
 	free_irq(port->irq, port);
 }
@@ -1419,11 +1423,13 @@ static void msm_power(struct uart_port *port, unsigned int state,
 
 	switch (state) {
 	case 0:
+		dev_pm_opp_set_rate(port->dev, port->uartclk);
 		clk_prepare_enable(msm_port->clk);
 		clk_prepare_enable(msm_port->pclk);
 		break;
 	case 3:
 		clk_disable_unprepare(msm_port->clk);
+		dev_pm_opp_set_rate(port->dev, 0);
 		clk_disable_unprepare(msm_port->pclk);
 		break;
 	default:
@@ -1789,7 +1795,7 @@ static int msm_serial_probe(struct platform_device *pdev)
 	struct resource *resource;
 	struct uart_port *port;
 	const struct of_device_id *id;
-	int irq, line;
+	int irq, line, ret;
 
 	if (pdev->dev.of_node)
 		line = of_alias_get_id(pdev->dev.of_node, "serial");
@@ -1824,6 +1830,15 @@ static int msm_serial_probe(struct platform_device *pdev)
 			return PTR_ERR(msm_port->pclk);
 	}
 
+	ret = devm_pm_opp_set_clkname(&pdev->dev, "core");
+	if (ret)
+		return ret;
+
+	/* OPP table is optional */
+	ret = devm_pm_opp_of_add_table(&pdev->dev);
+	if (ret && ret != -ENODEV)
+		return dev_err_probe(&pdev->dev, ret, "invalid OPP table\n");
+
 	port->uartclk = clk_get_rate(msm_port->clk);
 	dev_info(&pdev->dev, "uartclk = %d\n", port->uartclk);
 
@@ -1843,13 +1858,11 @@ static int msm_serial_probe(struct platform_device *pdev)
 	return uart_add_one_port(&msm_uart_driver, port);
 }
 
-static int msm_serial_remove(struct platform_device *pdev)
+static void msm_serial_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&msm_uart_driver, port);
-
-	return 0;
 }
 
 static const struct of_device_id msm_match_table[] = {
@@ -1882,7 +1895,7 @@ static const struct dev_pm_ops msm_serial_dev_pm_ops = {
 };
 
 static struct platform_driver msm_platform_driver = {
-	.remove = msm_serial_remove,
+	.remove_new = msm_serial_remove,
 	.probe = msm_serial_probe,
 	.driver = {
 		.name = "msm_serial",
diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c
index 8eeecf8ad359..4749331fe618 100644
--- a/drivers/tty/serial/mxs-auart.c
+++ b/drivers/tty/serial/mxs-auart.c
@@ -605,13 +605,16 @@ static void mxs_auart_tx_chars(struct mxs_auart_port *s)
 		return;
 	}
 
-	pending = uart_port_tx(&s->port, ch,
+	pending = uart_port_tx_flags(&s->port, ch, UART_TX_NOSTOP,
 		!(mxs_read(s, REG_STAT) & AUART_STAT_TXFF),
 		mxs_write(ch, s, REG_DATA));
 	if (pending)
 		mxs_set(AUART_INTR_TXIEN, s, REG_INTR);
 	else
 		mxs_clr(AUART_INTR_TXIEN, s, REG_INTR);
+
+	if (uart_tx_stopped(&s->port))
+               mxs_auart_stop_tx(&s->port);
 }
 
 static void mxs_auart_rx_char(struct mxs_auart_port *s)
@@ -904,21 +907,27 @@ static void mxs_auart_dma_exit(struct mxs_auart_port *s)
 
 static int mxs_auart_dma_init(struct mxs_auart_port *s)
 {
+	struct dma_chan *chan;
+
 	if (auart_dma_enabled(s))
 		return 0;
 
 	/* init for RX */
-	s->rx_dma_chan = dma_request_slave_channel(s->dev, "rx");
-	if (!s->rx_dma_chan)
+	chan = dma_request_chan(s->dev, "rx");
+	if (IS_ERR(chan))
 		goto err_out;
+	s->rx_dma_chan = chan;
+
 	s->rx_dma_buf = kzalloc(UART_XMIT_SIZE, GFP_KERNEL | GFP_DMA);
 	if (!s->rx_dma_buf)
 		goto err_out;
 
 	/* init for TX */
-	s->tx_dma_chan = dma_request_slave_channel(s->dev, "tx");
-	if (!s->tx_dma_chan)
+	chan = dma_request_chan(s->dev, "tx");
+	if (IS_ERR(chan))
 		goto err_out;
+	s->tx_dma_chan = chan;
+
 	s->tx_dma_buf = kzalloc(UART_XMIT_SIZE, GFP_KERNEL | GFP_DMA);
 	if (!s->tx_dma_buf)
 		goto err_out;
@@ -1686,7 +1695,7 @@ out_disable_clks:
 	return ret;
 }
 
-static int mxs_auart_remove(struct platform_device *pdev)
+static void mxs_auart_remove(struct platform_device *pdev)
 {
 	struct mxs_auart_port *s = platform_get_drvdata(pdev);
 
@@ -1698,13 +1707,11 @@ static int mxs_auart_remove(struct platform_device *pdev)
 		clk_disable_unprepare(s->clk);
 		clk_disable_unprepare(s->clk_ahb);
 	}
-
-	return 0;
 }
 
 static struct platform_driver mxs_auart_driver = {
 	.probe = mxs_auart_probe,
-	.remove = mxs_auart_remove,
+	.remove_new = mxs_auart_remove,
 	.driver = {
 		.name = "mxs-auart",
 		.of_match_table = mxs_auart_dt_ids,
diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
index ad4c1c5d0a7f..f5a0b401af63 100644
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -1483,6 +1483,13 @@ static struct omap_uart_port_info *of_get_uart_port_info(struct device *dev)
 	return omap_up_info;
 }
 
+static const struct serial_rs485 serial_omap_rs485_supported = {
+	.flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | SER_RS485_RTS_AFTER_SEND |
+		 SER_RS485_RX_DURING_TX,
+	.delay_rts_before_send = 1,
+	.delay_rts_after_send = 1,
+};
+
 static int serial_omap_probe_rs485(struct uart_omap_port *up,
 				   struct device *dev)
 {
@@ -1497,6 +1504,9 @@ static int serial_omap_probe_rs485(struct uart_omap_port *up,
 	if (!np)
 		return 0;
 
+	up->port.rs485_config = serial_omap_config_rs485;
+	up->port.rs485_supported = serial_omap_rs485_supported;
+
 	ret = uart_get_rs485_mode(&up->port);
 	if (ret)
 		return ret;
@@ -1531,13 +1541,6 @@ static int serial_omap_probe_rs485(struct uart_omap_port *up,
 	return 0;
 }
 
-static const struct serial_rs485 serial_omap_rs485_supported = {
-	.flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | SER_RS485_RTS_AFTER_SEND |
-		 SER_RS485_RX_DURING_TX,
-	.delay_rts_before_send = 1,
-	.delay_rts_after_send = 1,
-};
-
 static int serial_omap_probe(struct platform_device *pdev)
 {
 	struct omap_uart_port_info *omap_up_info = dev_get_platdata(&pdev->dev);
@@ -1604,17 +1607,11 @@ static int serial_omap_probe(struct platform_device *pdev)
 		dev_info(up->port.dev, "no wakeirq for uart%d\n",
 			 up->port.line);
 
-	ret = serial_omap_probe_rs485(up, &pdev->dev);
-	if (ret < 0)
-		goto err_rs485;
-
 	sprintf(up->name, "OMAP UART%d", up->port.line);
 	up->port.mapbase = mem->start;
 	up->port.membase = base;
 	up->port.flags = omap_up_info->flags;
 	up->port.uartclk = omap_up_info->uartclk;
-	up->port.rs485_config = serial_omap_config_rs485;
-	up->port.rs485_supported = serial_omap_rs485_supported;
 	if (!up->port.uartclk) {
 		up->port.uartclk = DEFAULT_CLK_SPEED;
 		dev_warn(&pdev->dev,
@@ -1622,6 +1619,10 @@ static int serial_omap_probe(struct platform_device *pdev)
 			 DEFAULT_CLK_SPEED);
 	}
 
+	ret = serial_omap_probe_rs485(up, &pdev->dev);
+	if (ret < 0)
+		goto err_rs485;
+
 	up->latency = PM_QOS_CPU_LATENCY_DEFAULT_VALUE;
 	up->calc_latency = PM_QOS_CPU_LATENCY_DEFAULT_VALUE;
 	cpu_latency_qos_add_request(&up->pm_qos_request, up->latency);
@@ -1658,7 +1659,7 @@ err_port_line:
 	return ret;
 }
 
-static int serial_omap_remove(struct platform_device *dev)
+static void serial_omap_remove(struct platform_device *dev)
 {
 	struct uart_omap_port *up = platform_get_drvdata(dev);
 
@@ -1670,8 +1671,6 @@ static int serial_omap_remove(struct platform_device *dev)
 	pm_runtime_disable(up->dev);
 	cpu_latency_qos_remove_request(&up->pm_qos_request);
 	device_init_wakeup(&dev->dev, false);
-
-	return 0;
 }
 
 /*
@@ -1808,7 +1807,7 @@ MODULE_DEVICE_TABLE(of, omap_serial_of_match);
 
 static struct platform_driver serial_omap_driver = {
 	.probe          = serial_omap_probe,
-	.remove         = serial_omap_remove,
+	.remove_new     = serial_omap_remove,
 	.driver		= {
 		.name	= OMAP_SERIAL_DRIVER_NAME,
 		.pm	= &serial_omap_dev_pm_ops,
diff --git a/drivers/tty/serial/owl-uart.c b/drivers/tty/serial/owl-uart.c
index 919f5e5aa0f1..d9fe85397741 100644
--- a/drivers/tty/serial/owl-uart.c
+++ b/drivers/tty/serial/owl-uart.c
@@ -725,20 +725,18 @@ static int owl_uart_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int owl_uart_remove(struct platform_device *pdev)
+static void owl_uart_remove(struct platform_device *pdev)
 {
 	struct owl_uart_port *owl_port = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&owl_uart_driver, &owl_port->port);
 	owl_uart_ports[pdev->id] = NULL;
 	clk_disable_unprepare(owl_port->clk);
-
-	return 0;
 }
 
 static struct platform_driver owl_uart_platform_driver = {
 	.probe = owl_uart_probe,
-	.remove = owl_uart_remove,
+	.remove_new = owl_uart_remove,
 	.driver = {
 		.name = "owl-uart",
 		.of_match_table = owl_uart_dt_matches,
diff --git a/drivers/tty/serial/pic32_uart.c b/drivers/tty/serial/pic32_uart.c
index 3a95bf5d55d3..bbb46e6e98a2 100644
--- a/drivers/tty/serial/pic32_uart.c
+++ b/drivers/tty/serial/pic32_uart.c
@@ -938,7 +938,7 @@ err:
 	return ret;
 }
 
-static int pic32_uart_remove(struct platform_device *pdev)
+static void pic32_uart_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 	struct pic32_sport *sport = to_pic32_sport(port);
@@ -947,9 +947,6 @@ static int pic32_uart_remove(struct platform_device *pdev)
 	clk_disable_unprepare(sport->clk);
 	platform_set_drvdata(pdev, NULL);
 	pic32_sports[sport->idx] = NULL;
-
-	/* automatic unroll of sport and gpios */
-	return 0;
 }
 
 static const struct of_device_id pic32_serial_dt_ids[] = {
@@ -960,7 +957,7 @@ MODULE_DEVICE_TABLE(of, pic32_serial_dt_ids);
 
 static struct platform_driver pic32_uart_platform_driver = {
 	.probe		= pic32_uart_probe,
-	.remove		= pic32_uart_remove,
+	.remove_new	= pic32_uart_remove,
 	.driver		= {
 		.name	= PIC32_DEV_NAME,
 		.of_match_table	= of_match_ptr(pic32_serial_dt_ids),
diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
index 7e78f97e8f43..99e08737f293 100644
--- a/drivers/tty/serial/qcom_geni_serial.c
+++ b/drivers/tty/serial/qcom_geni_serial.c
@@ -851,19 +851,21 @@ static void qcom_geni_serial_stop_tx(struct uart_port *uport)
 }
 
 static void qcom_geni_serial_send_chunk_fifo(struct uart_port *uport,
-					     unsigned int remaining)
+					     unsigned int chunk)
 {
 	struct qcom_geni_serial_port *port = to_dev_port(uport);
 	struct circ_buf *xmit = &uport->state->xmit;
-	unsigned int tx_bytes;
+	unsigned int tx_bytes, c, remaining = chunk;
 	u8 buf[BYTES_PER_FIFO_WORD];
 
 	while (remaining) {
 		memset(buf, 0, sizeof(buf));
 		tx_bytes = min(remaining, BYTES_PER_FIFO_WORD);
 
-		memcpy(buf, &xmit->buf[xmit->tail], tx_bytes);
-		uart_xmit_advance(uport, tx_bytes);
+		for (c = 0; c < tx_bytes ; c++) {
+			buf[c] = xmit->buf[xmit->tail];
+			uart_xmit_advance(uport, 1);
+		}
 
 		iowrite32_rep(uport->membase + SE_GENI_TX_FIFOn, buf, 1);
 
@@ -1696,7 +1698,7 @@ static int qcom_geni_serial_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int qcom_geni_serial_remove(struct platform_device *pdev)
+static void qcom_geni_serial_remove(struct platform_device *pdev)
 {
 	struct qcom_geni_serial_port *port = platform_get_drvdata(pdev);
 	struct uart_driver *drv = port->private_data.drv;
@@ -1704,8 +1706,6 @@ static int qcom_geni_serial_remove(struct platform_device *pdev)
 	dev_pm_clear_wake_irq(&pdev->dev);
 	device_init_wakeup(&pdev->dev, false);
 	uart_remove_one_port(drv, &port->uport);
-
-	return 0;
 }
 
 static int qcom_geni_serial_sys_suspend(struct device *dev)
@@ -1805,7 +1805,7 @@ static const struct of_device_id qcom_geni_serial_match_table[] = {
 MODULE_DEVICE_TABLE(of, qcom_geni_serial_match_table);
 
 static struct platform_driver qcom_geni_serial_platform_driver = {
-	.remove = qcom_geni_serial_remove,
+	.remove_new = qcom_geni_serial_remove,
 	.probe = qcom_geni_serial_probe,
 	.driver = {
 		.name = "qcom_geni_serial",
diff --git a/drivers/tty/serial/rda-uart.c b/drivers/tty/serial/rda-uart.c
index d824c8318f33..13deb355cf1b 100644
--- a/drivers/tty/serial/rda-uart.c
+++ b/drivers/tty/serial/rda-uart.c
@@ -780,19 +780,17 @@ static int rda_uart_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int rda_uart_remove(struct platform_device *pdev)
+static void rda_uart_remove(struct platform_device *pdev)
 {
 	struct rda_uart_port *rda_port = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&rda_uart_driver, &rda_port->port);
 	rda_uart_ports[pdev->id] = NULL;
-
-	return 0;
 }
 
 static struct platform_driver rda_uart_platform_driver = {
 	.probe = rda_uart_probe,
-	.remove = rda_uart_remove,
+	.remove_new = rda_uart_remove,
 	.driver = {
 		.name = "rda-uart",
 		.of_match_table = rda_uart_dt_matches,
diff --git a/drivers/tty/serial/rp2.c b/drivers/tty/serial/rp2.c
index d46a81cddfcd..4132fcff7d4e 100644
--- a/drivers/tty/serial/rp2.c
+++ b/drivers/tty/serial/rp2.c
@@ -178,7 +178,6 @@ struct rp2_card;
 struct rp2_uart_port {
 	struct uart_port		port;
 	int				idx;
-	int				ignore_rx;
 	struct rp2_card			*card;
 	void __iomem			*asic_base;
 	void __iomem			*base;
diff --git a/drivers/tty/serial/sa1100.c b/drivers/tty/serial/sa1100.c
index be7bcd75d9f4..79c794fa6545 100644
--- a/drivers/tty/serial/sa1100.c
+++ b/drivers/tty/serial/sa1100.c
@@ -870,19 +870,17 @@ static int sa1100_serial_probe(struct platform_device *dev)
 	return 0;
 }
 
-static int sa1100_serial_remove(struct platform_device *pdev)
+static void sa1100_serial_remove(struct platform_device *pdev)
 {
 	struct sa1100_port *sport = platform_get_drvdata(pdev);
 
 	if (sport)
 		uart_remove_one_port(&sa1100_reg, &sport->port);
-
-	return 0;
 }
 
 static struct platform_driver sa11x0_serial_driver = {
 	.probe		= sa1100_serial_probe,
-	.remove		= sa1100_serial_remove,
+	.remove_new	= sa1100_serial_remove,
 	.suspend	= sa1100_serial_suspend,
 	.resume		= sa1100_serial_resume,
 	.driver		= {
diff --git a/drivers/tty/serial/samsung_tty.c b/drivers/tty/serial/samsung_tty.c
index 66bd6c090ace..71d17d804fda 100644
--- a/drivers/tty/serial/samsung_tty.c
+++ b/drivers/tty/serial/samsung_tty.c
@@ -2054,7 +2054,7 @@ static int s3c24xx_serial_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int s3c24xx_serial_remove(struct platform_device *dev)
+static void s3c24xx_serial_remove(struct platform_device *dev)
 {
 	struct uart_port *port = s3c24xx_dev_to_port(&dev->dev);
 
@@ -2063,8 +2063,6 @@ static int s3c24xx_serial_remove(struct platform_device *dev)
 	}
 
 	uart_unregister_driver(&s3c24xx_uart_drv);
-
-	return 0;
 }
 
 /* UART power management code */
@@ -2627,7 +2625,7 @@ MODULE_DEVICE_TABLE(of, s3c24xx_uart_dt_match);
 
 static struct platform_driver samsung_serial_driver = {
 	.probe		= s3c24xx_serial_probe,
-	.remove		= s3c24xx_serial_remove,
+	.remove_new	= s3c24xx_serial_remove,
 	.id_table	= s3c24xx_serial_driver_ids,
 	.driver		= {
 		.name	= "samsung-uart",
diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index cf0c6120d30e..929206a9a6e1 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -24,10 +24,12 @@
 #include <linux/tty_flip.h>
 #include <linux/spi/spi.h>
 #include <linux/uaccess.h>
+#include <linux/units.h>
 #include <uapi/linux/sched/types.h>
 
 #define SC16IS7XX_NAME			"sc16is7xx"
 #define SC16IS7XX_MAX_DEVS		8
+#define SC16IS7XX_MAX_PORTS		2 /* Maximum number of UART ports per IC. */
 
 /* SC16IS7XX register definitions */
 #define SC16IS7XX_RHR_REG		(0x00) /* RX FIFO */
@@ -300,8 +302,8 @@
 
 
 /* Misc definitions */
+#define SC16IS7XX_SPI_READ_BIT		BIT(7)
 #define SC16IS7XX_FIFO_SIZE		(64)
-#define SC16IS7XX_REG_SHIFT		2
 #define SC16IS7XX_GPIOS_PER_BANK	4
 
 struct sc16is7xx_devtype {
@@ -322,18 +324,19 @@ struct sc16is7xx_one_config {
 
 struct sc16is7xx_one {
 	struct uart_port		port;
-	u8				line;
+	struct regmap			*regmap;
+	struct mutex			efr_lock; /* EFR registers access */
 	struct kthread_work		tx_work;
 	struct kthread_work		reg_work;
 	struct kthread_delayed_work	ms_work;
 	struct sc16is7xx_one_config	config;
-	bool				irda_mode;
 	unsigned int			old_mctrl;
+	u8				old_lcr; /* Value before EFR access. */
+	bool				irda_mode;
 };
 
 struct sc16is7xx_port {
 	const struct sc16is7xx_devtype	*devtype;
-	struct regmap			*regmap;
 	struct clk			*clk;
 #ifdef CONFIG_GPIOLIB
 	struct gpio_chip		gpio;
@@ -343,65 +346,47 @@ struct sc16is7xx_port {
 	unsigned char			buf[SC16IS7XX_FIFO_SIZE];
 	struct kthread_worker		kworker;
 	struct task_struct		*kworker_task;
-	struct mutex			efr_lock;
 	struct sc16is7xx_one		p[];
 };
 
-static unsigned long sc16is7xx_lines;
+static DECLARE_BITMAP(sc16is7xx_lines, SC16IS7XX_MAX_DEVS);
 
 static struct uart_driver sc16is7xx_uart = {
 	.owner		= THIS_MODULE,
+	.driver_name    = SC16IS7XX_NAME,
 	.dev_name	= "ttySC",
 	.nr		= SC16IS7XX_MAX_DEVS,
 };
 
-static void sc16is7xx_ier_set(struct uart_port *port, u8 bit);
-static void sc16is7xx_stop_tx(struct uart_port *port);
-
 #define to_sc16is7xx_one(p,e)	((container_of((p), struct sc16is7xx_one, e)))
 
-static int sc16is7xx_line(struct uart_port *port)
-{
-	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
-
-	return one->line;
-}
-
 static u8 sc16is7xx_port_read(struct uart_port *port, u8 reg)
 {
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 	unsigned int val = 0;
-	const u8 line = sc16is7xx_line(port);
 
-	regmap_read(s->regmap, (reg << SC16IS7XX_REG_SHIFT) | line, &val);
+	regmap_read(one->regmap, reg, &val);
 
 	return val;
 }
 
 static void sc16is7xx_port_write(struct uart_port *port, u8 reg, u8 val)
 {
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
-	const u8 line = sc16is7xx_line(port);
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 
-	regmap_write(s->regmap, (reg << SC16IS7XX_REG_SHIFT) | line, val);
+	regmap_write(one->regmap, reg, val);
 }
 
-static void sc16is7xx_fifo_read(struct uart_port *port, unsigned int rxlen)
+static void sc16is7xx_fifo_read(struct uart_port *port, u8 *rxbuf, unsigned int rxlen)
 {
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
-	const u8 line = sc16is7xx_line(port);
-	u8 addr = (SC16IS7XX_RHR_REG << SC16IS7XX_REG_SHIFT) | line;
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 
-	regcache_cache_bypass(s->regmap, true);
-	regmap_raw_read(s->regmap, addr, s->buf, rxlen);
-	regcache_cache_bypass(s->regmap, false);
+	regmap_noinc_read(one->regmap, SC16IS7XX_RHR_REG, rxbuf, rxlen);
 }
 
-static void sc16is7xx_fifo_write(struct uart_port *port, u8 to_send)
+static void sc16is7xx_fifo_write(struct uart_port *port, u8 *txbuf, u8 to_send)
 {
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
-	const u8 line = sc16is7xx_line(port);
-	u8 addr = (SC16IS7XX_THR_REG << SC16IS7XX_REG_SHIFT) | line;
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 
 	/*
 	 * Don't send zero-length data, at least on SPI it confuses the chip
@@ -410,39 +395,101 @@ static void sc16is7xx_fifo_write(struct uart_port *port, u8 to_send)
 	if (unlikely(!to_send))
 		return;
 
-	regcache_cache_bypass(s->regmap, true);
-	regmap_raw_write(s->regmap, addr, s->buf, to_send);
-	regcache_cache_bypass(s->regmap, false);
+	regmap_noinc_write(one->regmap, SC16IS7XX_THR_REG, txbuf, to_send);
 }
 
 static void sc16is7xx_port_update(struct uart_port *port, u8 reg,
 				  u8 mask, u8 val)
 {
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
+
+	regmap_update_bits(one->regmap, reg, mask, val);
+}
+
+static void sc16is7xx_power(struct uart_port *port, int on)
+{
+	sc16is7xx_port_update(port, SC16IS7XX_IER_REG,
+			      SC16IS7XX_IER_SLEEP_BIT,
+			      on ? 0 : SC16IS7XX_IER_SLEEP_BIT);
+}
+
+/*
+ * In an amazing feat of design, the Enhanced Features Register (EFR)
+ * shares the address of the Interrupt Identification Register (IIR).
+ * Access to EFR is switched on by writing a magic value (0xbf) to the
+ * Line Control Register (LCR). Any interrupt firing during this time will
+ * see the EFR where it expects the IIR to be, leading to
+ * "Unexpected interrupt" messages.
+ *
+ * Prevent this possibility by claiming a mutex while accessing the EFR,
+ * and claiming the same mutex from within the interrupt handler. This is
+ * similar to disabling the interrupt, but that doesn't work because the
+ * bulk of the interrupt processing is run as a workqueue job in thread
+ * context.
+ */
+static void sc16is7xx_efr_lock(struct uart_port *port)
+{
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
+
+	mutex_lock(&one->efr_lock);
+
+	/* Backup content of LCR. */
+	one->old_lcr = sc16is7xx_port_read(port, SC16IS7XX_LCR_REG);
+
+	/* Enable access to Enhanced register set */
+	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, SC16IS7XX_LCR_CONF_MODE_B);
+
+	/* Disable cache updates when writing to EFR registers */
+	regcache_cache_bypass(one->regmap, true);
+}
+
+static void sc16is7xx_efr_unlock(struct uart_port *port)
+{
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
+
+	/* Re-enable cache updates when writing to normal registers */
+	regcache_cache_bypass(one->regmap, false);
+
+	/* Restore original content of LCR */
+	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, one->old_lcr);
+
+	mutex_unlock(&one->efr_lock);
+}
+
+static void sc16is7xx_ier_clear(struct uart_port *port, u8 bit)
+{
 	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
-	const u8 line = sc16is7xx_line(port);
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
+
+	lockdep_assert_held_once(&port->lock);
 
-	regmap_update_bits(s->regmap, (reg << SC16IS7XX_REG_SHIFT) | line,
-			   mask, val);
+	one->config.flags |= SC16IS7XX_RECONF_IER;
+	one->config.ier_mask |= bit;
+	one->config.ier_val &= ~bit;
+	kthread_queue_work(&s->kworker, &one->reg_work);
 }
 
-static int sc16is7xx_alloc_line(void)
+static void sc16is7xx_ier_set(struct uart_port *port, u8 bit)
 {
-	int i;
+	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 
-	BUILD_BUG_ON(SC16IS7XX_MAX_DEVS > BITS_PER_LONG);
+	lockdep_assert_held_once(&port->lock);
 
-	for (i = 0; i < SC16IS7XX_MAX_DEVS; i++)
-		if (!test_and_set_bit(i, &sc16is7xx_lines))
-			break;
+	one->config.flags |= SC16IS7XX_RECONF_IER;
+	one->config.ier_mask |= bit;
+	one->config.ier_val |= bit;
+	kthread_queue_work(&s->kworker, &one->reg_work);
+}
 
-	return i;
+static void sc16is7xx_stop_tx(struct uart_port *port)
+{
+	sc16is7xx_ier_clear(port, SC16IS7XX_IER_THRI_BIT);
 }
 
-static void sc16is7xx_power(struct uart_port *port, int on)
+static void sc16is7xx_stop_rx(struct uart_port *port)
 {
-	sc16is7xx_port_update(port, SC16IS7XX_IER_REG,
-			      SC16IS7XX_IER_SLEEP_BIT,
-			      on ? 0 : SC16IS7XX_IER_SLEEP_BIT);
+	sc16is7xx_ier_clear(port, SC16IS7XX_IER_RDI_BIT);
 }
 
 static const struct sc16is7xx_devtype sc16is74x_devtype = {
@@ -477,7 +524,7 @@ static const struct sc16is7xx_devtype sc16is762_devtype = {
 
 static bool sc16is7xx_regmap_volatile(struct device *dev, unsigned int reg)
 {
-	switch (reg >> SC16IS7XX_REG_SHIFT) {
+	switch (reg) {
 	case SC16IS7XX_RHR_REG:
 	case SC16IS7XX_IIR_REG:
 	case SC16IS7XX_LSR_REG:
@@ -488,85 +535,60 @@ static bool sc16is7xx_regmap_volatile(struct device *dev, unsigned int reg)
 	case SC16IS7XX_IOCONTROL_REG:
 		return true;
 	default:
-		break;
+		return false;
 	}
-
-	return false;
 }
 
 static bool sc16is7xx_regmap_precious(struct device *dev, unsigned int reg)
 {
-	switch (reg >> SC16IS7XX_REG_SHIFT) {
+	switch (reg) {
 	case SC16IS7XX_RHR_REG:
 		return true;
 	default:
-		break;
+		return false;
 	}
+}
 
-	return false;
+static bool sc16is7xx_regmap_noinc(struct device *dev, unsigned int reg)
+{
+	return reg == SC16IS7XX_RHR_REG;
 }
 
 static int sc16is7xx_set_baud(struct uart_port *port, int baud)
 {
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 	u8 lcr;
 	u8 prescaler = 0;
 	unsigned long clk = port->uartclk, div = clk / 16 / baud;
 
-	if (div > 0xffff) {
+	if (div >= BIT(16)) {
 		prescaler = SC16IS7XX_MCR_CLKSEL_BIT;
 		div /= 4;
 	}
 
-	/* In an amazing feat of design, the Enhanced Features Register shares
-	 * the address of the Interrupt Identification Register, and is
-	 * switched in by writing a magic value (0xbf) to the Line Control
-	 * Register. Any interrupt firing during this time will see the EFR
-	 * where it expects the IIR to be, leading to "Unexpected interrupt"
-	 * messages.
-	 *
-	 * Prevent this possibility by claiming a mutex while accessing the
-	 * EFR, and claiming the same mutex from within the interrupt handler.
-	 * This is similar to disabling the interrupt, but that doesn't work
-	 * because the bulk of the interrupt processing is run as a workqueue
-	 * job in thread context.
-	 */
-	mutex_lock(&s->efr_lock);
-
-	lcr = sc16is7xx_port_read(port, SC16IS7XX_LCR_REG);
-
-	/* Open the LCR divisors for configuration */
-	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG,
-			     SC16IS7XX_LCR_CONF_MODE_B);
-
 	/* Enable enhanced features */
-	regcache_cache_bypass(s->regmap, true);
+	sc16is7xx_efr_lock(port);
 	sc16is7xx_port_update(port, SC16IS7XX_EFR_REG,
 			      SC16IS7XX_EFR_ENABLE_BIT,
 			      SC16IS7XX_EFR_ENABLE_BIT);
-
-	regcache_cache_bypass(s->regmap, false);
-
-	/* Put LCR back to the normal mode */
-	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, lcr);
-
-	mutex_unlock(&s->efr_lock);
+	sc16is7xx_efr_unlock(port);
 
 	sc16is7xx_port_update(port, SC16IS7XX_MCR_REG,
 			      SC16IS7XX_MCR_CLKSEL_BIT,
 			      prescaler);
 
-	/* Open the LCR divisors for configuration */
+	/* Backup LCR and access special register set (DLL/DLH) */
+	lcr = sc16is7xx_port_read(port, SC16IS7XX_LCR_REG);
 	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG,
 			     SC16IS7XX_LCR_CONF_MODE_A);
 
 	/* Write the new divisor */
-	regcache_cache_bypass(s->regmap, true);
+	regcache_cache_bypass(one->regmap, true);
 	sc16is7xx_port_write(port, SC16IS7XX_DLH_REG, div / 256);
 	sc16is7xx_port_write(port, SC16IS7XX_DLL_REG, div % 256);
-	regcache_cache_bypass(s->regmap, false);
+	regcache_cache_bypass(one->regmap, false);
 
-	/* Put LCR back to the normal mode */
+	/* Restore LCR and access to general register set */
 	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, lcr);
 
 	return DIV_ROUND_CLOSEST(clk / 16, div);
@@ -602,7 +624,7 @@ static void sc16is7xx_handle_rx(struct uart_port *port, unsigned int rxlen,
 			s->buf[0] = sc16is7xx_port_read(port, SC16IS7XX_RHR_REG);
 			bytes_read = 1;
 		} else {
-			sc16is7xx_fifo_read(port, rxlen);
+			sc16is7xx_fifo_read(port, s->buf, rxlen);
 			bytes_read = rxlen;
 		}
 
@@ -675,7 +697,7 @@ static void sc16is7xx_handle_tx(struct uart_port *port)
 	/* Get length of data pending in circular buffer */
 	to_send = uart_circ_chars_pending(xmit);
 	if (likely(to_send)) {
-		/* Limit to size of TX FIFO */
+		/* Limit to space available in TX FIFO */
 		txlen = sc16is7xx_port_read(port, SC16IS7XX_TXLVL_REG);
 		if (txlen > SC16IS7XX_FIFO_SIZE) {
 			dev_err_ratelimited(port->dev,
@@ -691,7 +713,7 @@ static void sc16is7xx_handle_tx(struct uart_port *port)
 			uart_xmit_advance(port, 1);
 		}
 
-		sc16is7xx_fifo_write(port, to_send);
+		sc16is7xx_fifo_write(port, s->buf, to_send);
 	}
 
 	uart_port_lock_irqsave(port, &flags);
@@ -700,6 +722,8 @@ static void sc16is7xx_handle_tx(struct uart_port *port)
 
 	if (uart_circ_empty(xmit))
 		sc16is7xx_stop_tx(port);
+	else
+		sc16is7xx_ier_set(port, SC16IS7XX_IER_THRI_BIT);
 	uart_port_unlock_irqrestore(port, flags);
 }
 
@@ -718,11 +742,10 @@ static unsigned int sc16is7xx_get_hwmctrl(struct uart_port *port)
 static void sc16is7xx_update_mlines(struct sc16is7xx_one *one)
 {
 	struct uart_port *port = &one->port;
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
 	unsigned long flags;
 	unsigned int status, changed;
 
-	lockdep_assert_held_once(&s->efr_lock);
+	lockdep_assert_held_once(&one->efr_lock);
 
 	status = sc16is7xx_get_hwmctrl(port);
 	changed = status ^ one->old_mctrl;
@@ -748,74 +771,77 @@ static void sc16is7xx_update_mlines(struct sc16is7xx_one *one)
 
 static bool sc16is7xx_port_irq(struct sc16is7xx_port *s, int portno)
 {
+	bool rc = true;
+	unsigned int iir, rxlen;
 	struct uart_port *port = &s->p[portno].port;
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 
-	do {
-		unsigned int iir, rxlen;
-		struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
-
-		iir = sc16is7xx_port_read(port, SC16IS7XX_IIR_REG);
-		if (iir & SC16IS7XX_IIR_NO_INT_BIT)
-			return false;
-
-		iir &= SC16IS7XX_IIR_ID_MASK;
-
-		switch (iir) {
-		case SC16IS7XX_IIR_RDI_SRC:
-		case SC16IS7XX_IIR_RLSE_SRC:
-		case SC16IS7XX_IIR_RTOI_SRC:
-		case SC16IS7XX_IIR_XOFFI_SRC:
-			rxlen = sc16is7xx_port_read(port, SC16IS7XX_RXLVL_REG);
-
-			/*
-			 * There is a silicon bug that makes the chip report a
-			 * time-out interrupt but no data in the FIFO. This is
-			 * described in errata section 18.1.4.
-			 *
-			 * When this happens, read one byte from the FIFO to
-			 * clear the interrupt.
-			 */
-			if (iir == SC16IS7XX_IIR_RTOI_SRC && !rxlen)
-				rxlen = 1;
-
-			if (rxlen)
-				sc16is7xx_handle_rx(port, rxlen, iir);
-			break;
+	mutex_lock(&one->efr_lock);
+
+	iir = sc16is7xx_port_read(port, SC16IS7XX_IIR_REG);
+	if (iir & SC16IS7XX_IIR_NO_INT_BIT) {
+		rc = false;
+		goto out_port_irq;
+	}
+
+	iir &= SC16IS7XX_IIR_ID_MASK;
+
+	switch (iir) {
+	case SC16IS7XX_IIR_RDI_SRC:
+	case SC16IS7XX_IIR_RLSE_SRC:
+	case SC16IS7XX_IIR_RTOI_SRC:
+	case SC16IS7XX_IIR_XOFFI_SRC:
+		rxlen = sc16is7xx_port_read(port, SC16IS7XX_RXLVL_REG);
+
+		/*
+		 * There is a silicon bug that makes the chip report a
+		 * time-out interrupt but no data in the FIFO. This is
+		 * described in errata section 18.1.4.
+		 *
+		 * When this happens, read one byte from the FIFO to
+		 * clear the interrupt.
+		 */
+		if (iir == SC16IS7XX_IIR_RTOI_SRC && !rxlen)
+			rxlen = 1;
+
+		if (rxlen)
+			sc16is7xx_handle_rx(port, rxlen, iir);
+		break;
 		/* CTSRTS interrupt comes only when CTS goes inactive */
-		case SC16IS7XX_IIR_CTSRTS_SRC:
-		case SC16IS7XX_IIR_MSI_SRC:
-			sc16is7xx_update_mlines(one);
-			break;
-		case SC16IS7XX_IIR_THRI_SRC:
-			sc16is7xx_handle_tx(port);
-			break;
-		default:
-			dev_err_ratelimited(port->dev,
-					    "ttySC%i: Unexpected interrupt: %x",
-					    port->line, iir);
-			break;
-		}
-	} while (0);
-	return true;
+	case SC16IS7XX_IIR_CTSRTS_SRC:
+	case SC16IS7XX_IIR_MSI_SRC:
+		sc16is7xx_update_mlines(one);
+		break;
+	case SC16IS7XX_IIR_THRI_SRC:
+		sc16is7xx_handle_tx(port);
+		break;
+	default:
+		dev_err_ratelimited(port->dev,
+				    "ttySC%i: Unexpected interrupt: %x",
+				    port->line, iir);
+		break;
+	}
+
+out_port_irq:
+	mutex_unlock(&one->efr_lock);
+
+	return rc;
 }
 
 static irqreturn_t sc16is7xx_irq(int irq, void *dev_id)
 {
-	struct sc16is7xx_port *s = (struct sc16is7xx_port *)dev_id;
+	bool keep_polling;
 
-	mutex_lock(&s->efr_lock);
+	struct sc16is7xx_port *s = (struct sc16is7xx_port *)dev_id;
 
-	while (1) {
-		bool keep_polling = false;
+	do {
 		int i;
 
+		keep_polling = false;
+
 		for (i = 0; i < s->devtype->nr_uart; ++i)
 			keep_polling |= sc16is7xx_port_irq(s, i);
-		if (!keep_polling)
-			break;
-	}
-
-	mutex_unlock(&s->efr_lock);
+	} while (keep_polling);
 
 	return IRQ_HANDLED;
 }
@@ -823,20 +849,15 @@ static irqreturn_t sc16is7xx_irq(int irq, void *dev_id)
 static void sc16is7xx_tx_proc(struct kthread_work *ws)
 {
 	struct uart_port *port = &(to_sc16is7xx_one(ws, tx_work)->port);
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
-	unsigned long flags;
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 
 	if ((port->rs485.flags & SER_RS485_ENABLED) &&
 	    (port->rs485.delay_rts_before_send > 0))
 		msleep(port->rs485.delay_rts_before_send);
 
-	mutex_lock(&s->efr_lock);
+	mutex_lock(&one->efr_lock);
 	sc16is7xx_handle_tx(port);
-	mutex_unlock(&s->efr_lock);
-
-	uart_port_lock_irqsave(port, &flags);
-	sc16is7xx_ier_set(port, SC16IS7XX_IER_THRI_BIT);
-	uart_port_unlock_irqrestore(port, flags);
+	mutex_unlock(&one->efr_lock);
 }
 
 static void sc16is7xx_reconf_rs485(struct uart_port *port)
@@ -897,51 +918,15 @@ static void sc16is7xx_reg_proc(struct kthread_work *ws)
 		sc16is7xx_reconf_rs485(&one->port);
 }
 
-static void sc16is7xx_ier_clear(struct uart_port *port, u8 bit)
-{
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
-	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
-
-	lockdep_assert_held_once(&port->lock);
-
-	one->config.flags |= SC16IS7XX_RECONF_IER;
-	one->config.ier_mask |= bit;
-	one->config.ier_val &= ~bit;
-	kthread_queue_work(&s->kworker, &one->reg_work);
-}
-
-static void sc16is7xx_ier_set(struct uart_port *port, u8 bit)
-{
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
-	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
-
-	lockdep_assert_held_once(&port->lock);
-
-	one->config.flags |= SC16IS7XX_RECONF_IER;
-	one->config.ier_mask |= bit;
-	one->config.ier_val |= bit;
-	kthread_queue_work(&s->kworker, &one->reg_work);
-}
-
-static void sc16is7xx_stop_tx(struct uart_port *port)
-{
-	sc16is7xx_ier_clear(port, SC16IS7XX_IER_THRI_BIT);
-}
-
-static void sc16is7xx_stop_rx(struct uart_port *port)
-{
-	sc16is7xx_ier_clear(port, SC16IS7XX_IER_RDI_BIT);
-}
-
 static void sc16is7xx_ms_proc(struct kthread_work *ws)
 {
 	struct sc16is7xx_one *one = to_sc16is7xx_one(ws, ms_work.work);
 	struct sc16is7xx_port *s = dev_get_drvdata(one->port.dev);
 
 	if (one->port.state) {
-		mutex_lock(&s->efr_lock);
+		mutex_lock(&one->efr_lock);
 		sc16is7xx_update_mlines(one);
-		mutex_unlock(&s->efr_lock);
+		mutex_unlock(&one->efr_lock);
 
 		kthread_queue_delayed_work(&s->kworker, &one->ms_work, HZ);
 	}
@@ -1025,7 +1010,6 @@ static void sc16is7xx_set_termios(struct uart_port *port,
 				  struct ktermios *termios,
 				  const struct ktermios *old)
 {
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
 	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 	unsigned int lcr, flow = 0;
 	int baud;
@@ -1083,17 +1067,7 @@ static void sc16is7xx_set_termios(struct uart_port *port,
 	if (!(termios->c_cflag & CREAD))
 		port->ignore_status_mask |= SC16IS7XX_LSR_BRK_ERROR_MASK;
 
-	/* As above, claim the mutex while accessing the EFR. */
-	mutex_lock(&s->efr_lock);
-
-	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG,
-			     SC16IS7XX_LCR_CONF_MODE_B);
-
 	/* Configure flow control */
-	regcache_cache_bypass(s->regmap, true);
-	sc16is7xx_port_write(port, SC16IS7XX_XON1_REG, termios->c_cc[VSTART]);
-	sc16is7xx_port_write(port, SC16IS7XX_XOFF1_REG, termios->c_cc[VSTOP]);
-
 	port->status &= ~(UPSTAT_AUTOCTS | UPSTAT_AUTORTS);
 	if (termios->c_cflag & CRTSCTS) {
 		flow |= SC16IS7XX_EFR_AUTOCTS_BIT |
@@ -1105,16 +1079,16 @@ static void sc16is7xx_set_termios(struct uart_port *port,
 	if (termios->c_iflag & IXOFF)
 		flow |= SC16IS7XX_EFR_SWFLOW1_BIT;
 
-	sc16is7xx_port_update(port,
-			      SC16IS7XX_EFR_REG,
-			      SC16IS7XX_EFR_FLOWCTRL_BITS,
-			      flow);
-	regcache_cache_bypass(s->regmap, false);
-
 	/* Update LCR register */
 	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, lcr);
 
-	mutex_unlock(&s->efr_lock);
+	/* Update EFR registers */
+	sc16is7xx_efr_lock(port);
+	sc16is7xx_port_write(port, SC16IS7XX_XON1_REG, termios->c_cc[VSTART]);
+	sc16is7xx_port_write(port, SC16IS7XX_XOFF1_REG, termios->c_cc[VSTOP]);
+	sc16is7xx_port_update(port, SC16IS7XX_EFR_REG,
+			      SC16IS7XX_EFR_FLOWCTRL_BITS, flow);
+	sc16is7xx_efr_unlock(port);
 
 	/* Get baud rate generator configuration */
 	baud = uart_get_baud_rate(port, termios, old,
@@ -1160,7 +1134,6 @@ static int sc16is7xx_config_rs485(struct uart_port *port, struct ktermios *termi
 static int sc16is7xx_startup(struct uart_port *port)
 {
 	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
 	unsigned int val;
 	unsigned long flags;
 
@@ -1177,7 +1150,7 @@ static int sc16is7xx_startup(struct uart_port *port)
 	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG,
 			     SC16IS7XX_LCR_CONF_MODE_B);
 
-	regcache_cache_bypass(s->regmap, true);
+	regcache_cache_bypass(one->regmap, true);
 
 	/* Enable write access to enhanced features and internal clock div */
 	sc16is7xx_port_update(port, SC16IS7XX_EFR_REG,
@@ -1195,7 +1168,7 @@ static int sc16is7xx_startup(struct uart_port *port)
 			     SC16IS7XX_TCR_RX_RESUME(24) |
 			     SC16IS7XX_TCR_RX_HALT(48));
 
-	regcache_cache_bypass(s->regmap, false);
+	regcache_cache_bypass(one->regmap, false);
 
 	/* Now, initialize the UART */
 	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, SC16IS7XX_LCR_WORD_LEN_8);
@@ -1425,7 +1398,7 @@ static void sc16is7xx_setup_irda_ports(struct sc16is7xx_port *s)
 	int i;
 	int ret;
 	int count;
-	u32 irda_port[2];
+	u32 irda_port[SC16IS7XX_MAX_PORTS];
 	struct device *dev = s->p[0].port.dev;
 
 	count = device_property_count_u32(dev, "irda-mode-ports");
@@ -1446,12 +1419,13 @@ static void sc16is7xx_setup_irda_ports(struct sc16is7xx_port *s)
 /*
  * Configure ports designated to operate as modem control lines.
  */
-static int sc16is7xx_setup_mctrl_ports(struct sc16is7xx_port *s)
+static int sc16is7xx_setup_mctrl_ports(struct sc16is7xx_port *s,
+				       struct regmap *regmap)
 {
 	int i;
 	int ret;
 	int count;
-	u32 mctrl_port[2];
+	u32 mctrl_port[SC16IS7XX_MAX_PORTS];
 	struct device *dev = s->p[0].port.dev;
 
 	count = device_property_count_u32(dev, "nxp,modem-control-line-ports");
@@ -1475,8 +1449,8 @@ static int sc16is7xx_setup_mctrl_ports(struct sc16is7xx_port *s)
 
 	if (s->mctrl_mask)
 		regmap_update_bits(
-			s->regmap,
-			SC16IS7XX_IOCONTROL_REG << SC16IS7XX_REG_SHIFT,
+			regmap,
+			SC16IS7XX_IOCONTROL_REG,
 			SC16IS7XX_IOCONTROL_MODEM_A_BIT |
 			SC16IS7XX_IOCONTROL_MODEM_B_BIT, s->mctrl_mask);
 
@@ -1491,7 +1465,7 @@ static const struct serial_rs485 sc16is7xx_rs485_supported = {
 
 static int sc16is7xx_probe(struct device *dev,
 			   const struct sc16is7xx_devtype *devtype,
-			   struct regmap *regmap, int irq)
+			   struct regmap *regmaps[], int irq)
 {
 	unsigned long freq = 0, *pfreq = dev_get_platdata(dev);
 	unsigned int val;
@@ -1499,16 +1473,20 @@ static int sc16is7xx_probe(struct device *dev,
 	int i, ret;
 	struct sc16is7xx_port *s;
 
-	if (IS_ERR(regmap))
-		return PTR_ERR(regmap);
+	for (i = 0; i < devtype->nr_uart; i++)
+		if (IS_ERR(regmaps[i]))
+			return PTR_ERR(regmaps[i]);
 
 	/*
 	 * This device does not have an identification register that would
 	 * tell us if we are really connected to the correct device.
 	 * The best we can do is to check if communication is at all possible.
+	 *
+	 * Note: regmap[0] is used in the probe function to access registers
+	 * common to all channels/ports, as it is guaranteed to be present on
+	 * all variants.
 	 */
-	ret = regmap_read(regmap,
-			  SC16IS7XX_LSR_REG << SC16IS7XX_REG_SHIFT, &val);
+	ret = regmap_read(regmaps[0], SC16IS7XX_LSR_REG, &val);
 	if (ret < 0)
 		return -EPROBE_DEFER;
 
@@ -1542,10 +1520,8 @@ static int sc16is7xx_probe(struct device *dev,
 			return -EINVAL;
 	}
 
-	s->regmap = regmap;
 	s->devtype = devtype;
 	dev_set_drvdata(dev, s);
-	mutex_init(&s->efr_lock);
 
 	kthread_init_worker(&s->kworker);
 	s->kworker_task = kthread_run(kthread_worker_fn, &s->kworker,
@@ -1557,11 +1533,17 @@ static int sc16is7xx_probe(struct device *dev,
 	sched_set_fifo(s->kworker_task);
 
 	/* reset device, purging any pending irq / data */
-	regmap_write(s->regmap, SC16IS7XX_IOCONTROL_REG << SC16IS7XX_REG_SHIFT,
-			SC16IS7XX_IOCONTROL_SRESET_BIT);
+	regmap_write(regmaps[0], SC16IS7XX_IOCONTROL_REG,
+		     SC16IS7XX_IOCONTROL_SRESET_BIT);
 
 	for (i = 0; i < devtype->nr_uart; ++i) {
-		s->p[i].line		= i;
+		s->p[i].port.line = find_first_zero_bit(sc16is7xx_lines,
+							SC16IS7XX_MAX_DEVS);
+		if (s->p[i].port.line >= SC16IS7XX_MAX_DEVS) {
+			ret = -ERANGE;
+			goto out_ports;
+		}
+
 		/* Initialize port data */
 		s->p[i].port.dev	= dev;
 		s->p[i].port.irq	= irq;
@@ -1581,12 +1563,9 @@ static int sc16is7xx_probe(struct device *dev,
 		s->p[i].port.rs485_supported = sc16is7xx_rs485_supported;
 		s->p[i].port.ops	= &sc16is7xx_ops;
 		s->p[i].old_mctrl	= 0;
-		s->p[i].port.line	= sc16is7xx_alloc_line();
+		s->p[i].regmap		= regmaps[i];
 
-		if (s->p[i].port.line >= SC16IS7XX_MAX_DEVS) {
-			ret = -ENOMEM;
-			goto out_ports;
-		}
+		mutex_init(&s->p[i].efr_lock);
 
 		ret = uart_get_rs485_mode(&s->p[i].port);
 		if (ret)
@@ -1603,20 +1582,25 @@ static int sc16is7xx_probe(struct device *dev,
 		kthread_init_work(&s->p[i].tx_work, sc16is7xx_tx_proc);
 		kthread_init_work(&s->p[i].reg_work, sc16is7xx_reg_proc);
 		kthread_init_delayed_work(&s->p[i].ms_work, sc16is7xx_ms_proc);
+
 		/* Register port */
-		uart_add_one_port(&sc16is7xx_uart, &s->p[i].port);
+		ret = uart_add_one_port(&sc16is7xx_uart, &s->p[i].port);
+		if (ret)
+			goto out_ports;
+
+		set_bit(s->p[i].port.line, sc16is7xx_lines);
 
 		/* Enable EFR */
 		sc16is7xx_port_write(&s->p[i].port, SC16IS7XX_LCR_REG,
 				     SC16IS7XX_LCR_CONF_MODE_B);
 
-		regcache_cache_bypass(s->regmap, true);
+		regcache_cache_bypass(regmaps[i], true);
 
 		/* Enable write access to enhanced features */
 		sc16is7xx_port_write(&s->p[i].port, SC16IS7XX_EFR_REG,
 				     SC16IS7XX_EFR_ENABLE_BIT);
 
-		regcache_cache_bypass(s->regmap, false);
+		regcache_cache_bypass(regmaps[i], false);
 
 		/* Restore access to general registers */
 		sc16is7xx_port_write(&s->p[i].port, SC16IS7XX_LCR_REG, 0x00);
@@ -1627,7 +1611,7 @@ static int sc16is7xx_probe(struct device *dev,
 
 	sc16is7xx_setup_irda_ports(s);
 
-	ret = sc16is7xx_setup_mctrl_ports(s);
+	ret = sc16is7xx_setup_mctrl_ports(s, regmaps[0]);
 	if (ret)
 		goto out_ports;
 
@@ -1662,10 +1646,9 @@ static int sc16is7xx_probe(struct device *dev,
 #endif
 
 out_ports:
-	for (i--; i >= 0; i--) {
-		uart_remove_one_port(&sc16is7xx_uart, &s->p[i].port);
-		clear_bit(s->p[i].port.line, &sc16is7xx_lines);
-	}
+	for (i = 0; i < devtype->nr_uart; i++)
+		if (test_and_clear_bit(s->p[i].port.line, sc16is7xx_lines))
+			uart_remove_one_port(&sc16is7xx_uart, &s->p[i].port);
 
 	kthread_stop(s->kworker_task);
 
@@ -1687,8 +1670,8 @@ static void sc16is7xx_remove(struct device *dev)
 
 	for (i = 0; i < s->devtype->nr_uart; i++) {
 		kthread_cancel_delayed_work_sync(&s->p[i].ms_work);
-		uart_remove_one_port(&sc16is7xx_uart, &s->p[i].port);
-		clear_bit(s->p[i].port.line, &sc16is7xx_lines);
+		if (test_and_clear_bit(s->p[i].port.line, sc16is7xx_lines))
+			uart_remove_one_port(&sc16is7xx_uart, &s->p[i].port);
 		sc16is7xx_power(&s->p[i].port, 0);
 	}
 
@@ -1710,45 +1693,74 @@ static const struct of_device_id __maybe_unused sc16is7xx_dt_ids[] = {
 MODULE_DEVICE_TABLE(of, sc16is7xx_dt_ids);
 
 static struct regmap_config regcfg = {
-	.reg_bits = 7,
-	.pad_bits = 1,
+	.reg_bits = 5,
+	.pad_bits = 3,
 	.val_bits = 8,
 	.cache_type = REGCACHE_RBTREE,
 	.volatile_reg = sc16is7xx_regmap_volatile,
 	.precious_reg = sc16is7xx_regmap_precious,
+	.writeable_noinc_reg = sc16is7xx_regmap_noinc,
+	.readable_noinc_reg = sc16is7xx_regmap_noinc,
+	.max_raw_read = SC16IS7XX_FIFO_SIZE,
+	.max_raw_write = SC16IS7XX_FIFO_SIZE,
+	.max_register = SC16IS7XX_EFCR_REG,
 };
 
+static const char *sc16is7xx_regmap_name(u8 port_id)
+{
+	switch (port_id) {
+	case 0:	return "port0";
+	case 1:	return "port1";
+	default:
+		WARN_ON(true);
+		return NULL;
+	}
+}
+
+static unsigned int sc16is7xx_regmap_port_mask(unsigned int port_id)
+{
+	/* CH1,CH0 are at bits 2:1. */
+	return port_id << 1;
+}
+
 #ifdef CONFIG_SERIAL_SC16IS7XX_SPI
 static int sc16is7xx_spi_probe(struct spi_device *spi)
 {
 	const struct sc16is7xx_devtype *devtype;
-	struct regmap *regmap;
+	struct regmap *regmaps[SC16IS7XX_MAX_PORTS];
+	unsigned int i;
 	int ret;
 
 	/* Setup SPI bus */
 	spi->bits_per_word	= 8;
-	/* only supports mode 0 on SC16IS762 */
+	/* For all variants, only mode 0 is supported */
+	if ((spi->mode & SPI_MODE_X_MASK) != SPI_MODE_0)
+		return dev_err_probe(&spi->dev, -EINVAL, "Unsupported SPI mode\n");
+
 	spi->mode		= spi->mode ? : SPI_MODE_0;
-	spi->max_speed_hz	= spi->max_speed_hz ? : 15000000;
+	spi->max_speed_hz	= spi->max_speed_hz ? : 4 * HZ_PER_MHZ;
 	ret = spi_setup(spi);
 	if (ret)
 		return ret;
 
-	if (spi->dev.of_node) {
-		devtype = device_get_match_data(&spi->dev);
-		if (!devtype)
-			return -ENODEV;
-	} else {
-		const struct spi_device_id *id_entry = spi_get_device_id(spi);
+	devtype = spi_get_device_match_data(spi);
+	if (!devtype)
+		return dev_err_probe(&spi->dev, -ENODEV, "Failed to match device\n");
 
-		devtype = (struct sc16is7xx_devtype *)id_entry->driver_data;
+	for (i = 0; i < devtype->nr_uart; i++) {
+		regcfg.name = sc16is7xx_regmap_name(i);
+		/*
+		 * If read_flag_mask is 0, the regmap code sets it to a default
+		 * of 0x80. Since we specify our own mask, we must add the READ
+		 * bit ourselves:
+		 */
+		regcfg.read_flag_mask = sc16is7xx_regmap_port_mask(i) |
+			SC16IS7XX_SPI_READ_BIT;
+		regcfg.write_flag_mask = sc16is7xx_regmap_port_mask(i);
+		regmaps[i] = devm_regmap_init_spi(spi, &regcfg);
 	}
 
-	regcfg.max_register = (0xf << SC16IS7XX_REG_SHIFT) |
-			      (devtype->nr_uart - 1);
-	regmap = devm_regmap_init_spi(spi, &regcfg);
-
-	return sc16is7xx_probe(&spi->dev, devtype, regmap, spi->irq);
+	return sc16is7xx_probe(&spi->dev, devtype, regmaps, spi->irq);
 }
 
 static void sc16is7xx_spi_remove(struct spi_device *spi)
@@ -1778,30 +1790,27 @@ static struct spi_driver sc16is7xx_spi_uart_driver = {
 	.remove		= sc16is7xx_spi_remove,
 	.id_table	= sc16is7xx_spi_id_table,
 };
-
-MODULE_ALIAS("spi:sc16is7xx");
 #endif
 
 #ifdef CONFIG_SERIAL_SC16IS7XX_I2C
 static int sc16is7xx_i2c_probe(struct i2c_client *i2c)
 {
-	const struct i2c_device_id *id = i2c_client_get_device_id(i2c);
 	const struct sc16is7xx_devtype *devtype;
-	struct regmap *regmap;
-
-	if (i2c->dev.of_node) {
-		devtype = device_get_match_data(&i2c->dev);
-		if (!devtype)
-			return -ENODEV;
-	} else {
-		devtype = (struct sc16is7xx_devtype *)id->driver_data;
+	struct regmap *regmaps[SC16IS7XX_MAX_PORTS];
+	unsigned int i;
+
+	devtype = i2c_get_match_data(i2c);
+	if (!devtype)
+		return dev_err_probe(&i2c->dev, -ENODEV, "Failed to match device\n");
+
+	for (i = 0; i < devtype->nr_uart; i++) {
+		regcfg.name = sc16is7xx_regmap_name(i);
+		regcfg.read_flag_mask = sc16is7xx_regmap_port_mask(i);
+		regcfg.write_flag_mask = sc16is7xx_regmap_port_mask(i);
+		regmaps[i] = devm_regmap_init_i2c(i2c, &regcfg);
 	}
 
-	regcfg.max_register = (0xf << SC16IS7XX_REG_SHIFT) |
-			      (devtype->nr_uart - 1);
-	regmap = devm_regmap_init_i2c(i2c, &regcfg);
-
-	return sc16is7xx_probe(&i2c->dev, devtype, regmap, i2c->irq);
+	return sc16is7xx_probe(&i2c->dev, devtype, regmaps, i2c->irq);
 }
 
 static void sc16is7xx_i2c_remove(struct i2c_client *client)
diff --git a/drivers/tty/serial/sccnxp.c b/drivers/tty/serial/sccnxp.c
index 2be2c1098025..f24217a560d7 100644
--- a/drivers/tty/serial/sccnxp.c
+++ b/drivers/tty/serial/sccnxp.c
@@ -1021,7 +1021,7 @@ err_out:
 	return ret;
 }
 
-static int sccnxp_remove(struct platform_device *pdev)
+static void sccnxp_remove(struct platform_device *pdev)
 {
 	int i;
 	struct sccnxp_port *s = platform_get_drvdata(pdev);
@@ -1036,10 +1036,11 @@ static int sccnxp_remove(struct platform_device *pdev)
 
 	uart_unregister_driver(&s->uart);
 
-	if (!IS_ERR(s->regulator))
-		return regulator_disable(s->regulator);
-
-	return 0;
+	if (!IS_ERR(s->regulator)) {
+		int ret = regulator_disable(s->regulator);
+		if (ret)
+			dev_err(&pdev->dev, "Failed to disable regulator\n");
+	}
 }
 
 static struct platform_driver sccnxp_uart_driver = {
@@ -1047,7 +1048,7 @@ static struct platform_driver sccnxp_uart_driver = {
 		.name	= SCCNXP_NAME,
 	},
 	.probe		= sccnxp_probe,
-	.remove		= sccnxp_remove,
+	.remove_new	= sccnxp_remove,
 	.id_table	= sccnxp_id_table,
 };
 module_platform_driver(sccnxp_uart_driver);
diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c
index 6d4006b41975..525f3a2f7bd4 100644
--- a/drivers/tty/serial/serial-tegra.c
+++ b/drivers/tty/serial/serial-tegra.c
@@ -1611,13 +1611,12 @@ static int tegra_uart_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int tegra_uart_remove(struct platform_device *pdev)
+static void tegra_uart_remove(struct platform_device *pdev)
 {
 	struct tegra_uart_port *tup = platform_get_drvdata(pdev);
 	struct uart_port *u = &tup->uport;
 
 	uart_remove_one_port(&tegra_uart_driver, u);
-	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -1644,7 +1643,7 @@ static const struct dev_pm_ops tegra_uart_pm_ops = {
 
 static struct platform_driver tegra_uart_platform_driver = {
 	.probe		= tegra_uart_probe,
-	.remove		= tegra_uart_remove,
+	.remove_new	= tegra_uart_remove,
 	.driver		= {
 		.name	= "serial-tegra",
 		.of_match_table = tegra_uart_of_match,
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index f1348a509552..d6a58a9e072a 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -156,7 +156,7 @@ static void __uart_start(struct uart_state *state)
 	 * enabled, serial_port_runtime_resume() calls start_tx() again
 	 * after enabling the device.
 	 */
-	if (!pm_runtime_enabled(port->dev) || pm_runtime_active(port->dev))
+	if (pm_runtime_active(&port_dev->dev))
 		port->ops->start_tx(port);
 	pm_runtime_mark_last_busy(&port_dev->dev);
 	pm_runtime_put_autosuspend(&port_dev->dev);
@@ -410,11 +410,10 @@ void
 uart_update_timeout(struct uart_port *port, unsigned int cflag,
 		    unsigned int baud)
 {
-	unsigned int size = tty_get_frame_size(cflag);
-	u64 frame_time;
+	u64 temp = tty_get_frame_size(cflag);
 
-	frame_time = (u64)size * NSEC_PER_SEC;
-	port->frame_time = DIV64_U64_ROUND_UP(frame_time, baud);
+	temp *= NSEC_PER_SEC;
+	port->frame_time = (unsigned int)DIV64_U64_ROUND_UP(temp, baud);
 }
 EXPORT_SYMBOL(uart_update_timeout);
 
@@ -687,7 +686,7 @@ EXPORT_SYMBOL_GPL(uart_xchar_out);
  * This function is used to send a high-priority XON/XOFF character to
  * the device
  */
-static void uart_send_xchar(struct tty_struct *tty, char ch)
+static void uart_send_xchar(struct tty_struct *tty, u8 ch)
 {
 	struct uart_state *state = tty->driver_data;
 	struct uart_port *port;
@@ -1085,8 +1084,8 @@ static int uart_tiocmget(struct tty_struct *tty)
 		goto out;
 
 	if (!tty_io_error(tty)) {
-		result = uport->mctrl;
 		uart_port_lock_irq(uport);
+		result = uport->mctrl;
 		result |= uport->ops->get_mctrl(uport);
 		uart_port_unlock_irq(uport);
 	}
@@ -1371,20 +1370,34 @@ static void uart_sanitize_serial_rs485(struct uart_port *port, struct serial_rs4
 		return;
 	}
 
-	/* Pick sane settings if the user hasn't */
-	if ((supported_flags & (SER_RS485_RTS_ON_SEND|SER_RS485_RTS_AFTER_SEND)) &&
-	    !(rs485->flags & SER_RS485_RTS_ON_SEND) ==
-	    !(rs485->flags & SER_RS485_RTS_AFTER_SEND)) {
-		dev_warn_ratelimited(port->dev,
-			"%s (%d): invalid RTS setting, using RTS_ON_SEND instead\n",
-			port->name, port->line);
-		rs485->flags |= SER_RS485_RTS_ON_SEND;
-		rs485->flags &= ~SER_RS485_RTS_AFTER_SEND;
-		supported_flags |= SER_RS485_RTS_ON_SEND|SER_RS485_RTS_AFTER_SEND;
+	/* Clear other RS485 flags but SER_RS485_TERMINATE_BUS and return if enabling RS422 */
+	if (rs485->flags & SER_RS485_MODE_RS422) {
+		rs485->flags &= (SER_RS485_ENABLED | SER_RS485_MODE_RS422 | SER_RS485_TERMINATE_BUS);
+		return;
 	}
 
 	rs485->flags &= supported_flags;
 
+	/* Pick sane settings if the user hasn't */
+	if (!(rs485->flags & SER_RS485_RTS_ON_SEND) ==
+	    !(rs485->flags & SER_RS485_RTS_AFTER_SEND)) {
+		if (supported_flags & SER_RS485_RTS_ON_SEND) {
+			rs485->flags |= SER_RS485_RTS_ON_SEND;
+			rs485->flags &= ~SER_RS485_RTS_AFTER_SEND;
+
+			dev_warn_ratelimited(port->dev,
+				"%s (%d): invalid RTS setting, using RTS_ON_SEND instead\n",
+				port->name, port->line);
+		} else {
+			rs485->flags |= SER_RS485_RTS_AFTER_SEND;
+			rs485->flags &= ~SER_RS485_RTS_ON_SEND;
+
+			dev_warn_ratelimited(port->dev,
+				"%s (%d): invalid RTS setting, using RTS_AFTER_SEND instead\n",
+				port->name, port->line);
+		}
+	}
+
 	uart_sanitize_serial_rs485_delays(port, rs485);
 
 	/* Return clean padding area to userspace */
@@ -1402,6 +1415,16 @@ static void uart_set_rs485_termination(struct uart_port *port,
 				 !!(rs485->flags & SER_RS485_TERMINATE_BUS));
 }
 
+static void uart_set_rs485_rx_during_tx(struct uart_port *port,
+					const struct serial_rs485 *rs485)
+{
+	if (!(rs485->flags & SER_RS485_ENABLED))
+		return;
+
+	gpiod_set_value_cansleep(port->rs485_rx_during_tx_gpio,
+				 !!(rs485->flags & SER_RS485_RX_DURING_TX));
+}
+
 static int uart_rs485_config(struct uart_port *port)
 {
 	struct serial_rs485 *rs485 = &port->rs485;
@@ -1413,12 +1436,17 @@ static int uart_rs485_config(struct uart_port *port)
 
 	uart_sanitize_serial_rs485(port, rs485);
 	uart_set_rs485_termination(port, rs485);
+	uart_set_rs485_rx_during_tx(port, rs485);
 
 	uart_port_lock_irqsave(port, &flags);
 	ret = port->rs485_config(port, NULL, rs485);
 	uart_port_unlock_irqrestore(port, flags);
-	if (ret)
+	if (ret) {
 		memset(rs485, 0, sizeof(*rs485));
+		/* unset GPIOs */
+		gpiod_set_value_cansleep(port->rs485_term_gpio, 0);
+		gpiod_set_value_cansleep(port->rs485_rx_during_tx_gpio, 0);
+	}
 
 	return ret;
 }
@@ -1446,7 +1474,7 @@ static int uart_set_rs485_config(struct tty_struct *tty, struct uart_port *port,
 	int ret;
 	unsigned long flags;
 
-	if (!port->rs485_config)
+	if (!(port->rs485_supported.flags & SER_RS485_ENABLED))
 		return -ENOTTY;
 
 	if (copy_from_user(&rs485, rs485_user, sizeof(*rs485_user)))
@@ -1457,6 +1485,7 @@ static int uart_set_rs485_config(struct tty_struct *tty, struct uart_port *port,
 		return ret;
 	uart_sanitize_serial_rs485(port, &rs485);
 	uart_set_rs485_termination(port, &rs485);
+	uart_set_rs485_rx_during_tx(port, &rs485);
 
 	uart_port_lock_irqsave(port, &flags);
 	ret = port->rs485_config(port, &tty->termios, &rs485);
@@ -1468,8 +1497,14 @@ static int uart_set_rs485_config(struct tty_struct *tty, struct uart_port *port,
 			port->ops->set_mctrl(port, port->mctrl);
 	}
 	uart_port_unlock_irqrestore(port, flags);
-	if (ret)
+	if (ret) {
+		/* restore old GPIO settings */
+		gpiod_set_value_cansleep(port->rs485_term_gpio,
+			!!(port->rs485.flags & SER_RS485_TERMINATE_BUS));
+		gpiod_set_value_cansleep(port->rs485_rx_during_tx_gpio,
+			!!(port->rs485.flags & SER_RS485_RX_DURING_TX));
 		return ret;
+	}
 
 	if (copy_to_user(rs485_user, &port->rs485, sizeof(port->rs485)))
 		return -EFAULT;
@@ -2342,7 +2377,7 @@ int uart_suspend_port(struct uart_driver *drv, struct uart_port *uport)
 
 	mutex_lock(&port->mutex);
 
-	tty_dev = device_find_child(uport->dev, &match, serial_match_port);
+	tty_dev = device_find_child(&uport->port_dev->dev, &match, serial_match_port);
 	if (tty_dev && device_may_wakeup(tty_dev)) {
 		enable_irq_wake(uport->irq);
 		put_device(tty_dev);
@@ -2423,7 +2458,7 @@ int uart_resume_port(struct uart_driver *drv, struct uart_port *uport)
 
 	mutex_lock(&port->mutex);
 
-	tty_dev = device_find_child(uport->dev, &match, serial_match_port);
+	tty_dev = device_find_child(&uport->port_dev->dev, &match, serial_match_port);
 	if (!uport->suspended && device_may_wakeup(tty_dev)) {
 		if (irqd_is_wakeup_set(irq_get_irq_data((uport->irq))))
 			disable_irq_wake(uport->irq);
@@ -2633,7 +2668,8 @@ static int uart_poll_init(struct tty_driver *driver, int line, char *options)
 	mutex_lock(&tport->mutex);
 
 	port = uart_port_check(state);
-	if (!port || !(port->ops->poll_get_char && port->ops->poll_put_char)) {
+	if (!port || port->type == PORT_UNKNOWN ||
+	    !(port->ops->poll_get_char && port->ops->poll_put_char)) {
 		ret = -1;
 		goto out;
 	}
@@ -3153,7 +3189,8 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u
 	 * setserial to be used to alter this port's parameters.
 	 */
 	tty_dev = tty_port_register_device_attr_serdev(port, drv->tty_driver,
-			uport->line, uport->dev, port, uport->tty_groups);
+			uport->line, uport->dev, &uport->port_dev->dev, port,
+			uport->tty_groups);
 	if (!IS_ERR(tty_dev)) {
 		device_set_wakeup_capable(tty_dev, 1);
 	} else {
@@ -3570,6 +3607,9 @@ int uart_get_rs485_mode(struct uart_port *port)
 	u32 rs485_delay[2];
 	int ret;
 
+	if (!(port->rs485_supported.flags & SER_RS485_ENABLED))
+		return 0;
+
 	ret = device_property_read_u32_array(dev, "rs485-rts-delay",
 					     rs485_delay, 2);
 	if (!ret) {
@@ -3620,6 +3660,8 @@ int uart_get_rs485_mode(struct uart_port *port)
 	if (IS_ERR(desc))
 		return dev_err_probe(dev, PTR_ERR(desc), "Cannot get rs485-rx-during-tx-gpios\n");
 	port->rs485_rx_during_tx_gpio = desc;
+	if (port->rs485_rx_during_tx_gpio)
+		port->rs485_supported.flags |= SER_RS485_RX_DURING_TX;
 
 	return 0;
 }
diff --git a/drivers/tty/serial/serial_port.c b/drivers/tty/serial/serial_port.c
index 88975a4df306..72b6f4f326e2 100644
--- a/drivers/tty/serial/serial_port.c
+++ b/drivers/tty/serial/serial_port.c
@@ -46,8 +46,31 @@ out:
 	return 0;
 }
 
+static int serial_port_runtime_suspend(struct device *dev)
+{
+	struct serial_port_device *port_dev = to_serial_base_port_device(dev);
+	struct uart_port *port = port_dev->port;
+	unsigned long flags;
+	bool busy;
+
+	if (port->flags & UPF_DEAD)
+		return 0;
+
+	uart_port_lock_irqsave(port, &flags);
+	busy = __serial_port_busy(port);
+	if (busy)
+		port->ops->start_tx(port);
+	uart_port_unlock_irqrestore(port, flags);
+
+	if (busy)
+		pm_runtime_mark_last_busy(dev);
+
+	return busy ? -EBUSY : 0;
+}
+
 static DEFINE_RUNTIME_DEV_PM_OPS(serial_port_pm,
-				 NULL, serial_port_runtime_resume, NULL);
+				 serial_port_runtime_suspend,
+				 serial_port_runtime_resume, NULL);
 
 static int serial_port_probe(struct device *dev)
 {
diff --git a/drivers/tty/serial/serial_txx9.c b/drivers/tty/serial/serial_txx9.c
index eaa980722455..e1897894a4ef 100644
--- a/drivers/tty/serial/serial_txx9.c
+++ b/drivers/tty/serial/serial_txx9.c
@@ -1052,7 +1052,7 @@ static int serial_txx9_probe(struct platform_device *dev)
 /*
  * Remove serial ports registered against a platform device.
  */
-static int serial_txx9_remove(struct platform_device *dev)
+static void serial_txx9_remove(struct platform_device *dev)
 {
 	int i;
 
@@ -1062,7 +1062,6 @@ static int serial_txx9_remove(struct platform_device *dev)
 		if (up->dev == &dev->dev)
 			serial_txx9_unregister_port(i);
 	}
-	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -1097,7 +1096,7 @@ static int serial_txx9_resume(struct platform_device *dev)
 
 static struct platform_driver serial_txx9_plat_driver = {
 	.probe		= serial_txx9_probe,
-	.remove		= serial_txx9_remove,
+	.remove_new	= serial_txx9_remove,
 #ifdef CONFIG_PM
 	.suspend	= serial_txx9_suspend,
 	.resume		= serial_txx9_resume,
diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index 84ab434c94ba..a85e7b9a2e49 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -1558,10 +1558,9 @@ static struct dma_chan *sci_request_dma_chan(struct uart_port *port,
 	struct dma_slave_config cfg;
 	int ret;
 
-	chan = dma_request_slave_channel(port->dev,
-					 dir == DMA_MEM_TO_DEV ? "tx" : "rx");
-	if (!chan) {
-		dev_dbg(port->dev, "dma_request_slave_channel failed\n");
+	chan = dma_request_chan(port->dev, dir == DMA_MEM_TO_DEV ? "tx" : "rx");
+	if (IS_ERR(chan)) {
+		dev_dbg(port->dev, "dma_request_chan failed\n");
 		return NULL;
 	}
 
@@ -3190,7 +3189,7 @@ static struct uart_driver sci_uart_driver = {
 	.cons		= SCI_CONSOLE,
 };
 
-static int sci_remove(struct platform_device *dev)
+static void sci_remove(struct platform_device *dev)
 {
 	struct sci_port *port = platform_get_drvdata(dev);
 	unsigned int type = port->port.type;	/* uart_remove_... clears it */
@@ -3204,8 +3203,6 @@ static int sci_remove(struct platform_device *dev)
 		device_remove_file(&dev->dev, &dev_attr_rx_fifo_trigger);
 	if (type == PORT_SCIFA || type == PORT_SCIFB || type == PORT_HSCIF)
 		device_remove_file(&dev->dev, &dev_attr_rx_fifo_timeout);
-
-	return 0;
 }
 
 
@@ -3470,7 +3467,7 @@ static SIMPLE_DEV_PM_OPS(sci_dev_pm_ops, sci_suspend, sci_resume);
 
 static struct platform_driver sci_driver = {
 	.probe		= sci_probe,
-	.remove		= sci_remove,
+	.remove_new	= sci_remove,
 	.driver		= {
 		.name	= "sh-sci",
 		.pm	= &sci_dev_pm_ops,
diff --git a/drivers/tty/serial/sifive.c b/drivers/tty/serial/sifive.c
index b296e57a9dee..a4cc569a78a2 100644
--- a/drivers/tty/serial/sifive.c
+++ b/drivers/tty/serial/sifive.c
@@ -1007,7 +1007,7 @@ probe_out1:
 	return r;
 }
 
-static int sifive_serial_remove(struct platform_device *dev)
+static void sifive_serial_remove(struct platform_device *dev)
 {
 	struct sifive_serial_port *ssp = platform_get_drvdata(dev);
 
@@ -1015,8 +1015,6 @@ static int sifive_serial_remove(struct platform_device *dev)
 	uart_remove_one_port(&sifive_serial_uart_driver, &ssp->port);
 	free_irq(ssp->port.irq, ssp);
 	clk_notifier_unregister(ssp->clk, &ssp->clk_notifier);
-
-	return 0;
 }
 
 static int sifive_serial_suspend(struct device *dev)
@@ -1033,8 +1031,8 @@ static int sifive_serial_resume(struct device *dev)
 	return uart_resume_port(&sifive_serial_uart_driver, &ssp->port);
 }
 
-DEFINE_SIMPLE_DEV_PM_OPS(sifive_uart_pm_ops, sifive_serial_suspend,
-			 sifive_serial_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(sifive_uart_pm_ops, sifive_serial_suspend,
+				sifive_serial_resume);
 
 static const struct of_device_id sifive_serial_of_match[] = {
 	{ .compatible = "sifive,fu540-c000-uart0" },
@@ -1045,7 +1043,7 @@ MODULE_DEVICE_TABLE(of, sifive_serial_of_match);
 
 static struct platform_driver sifive_serial_platform_driver = {
 	.probe		= sifive_serial_probe,
-	.remove		= sifive_serial_remove,
+	.remove_new	= sifive_serial_remove,
 	.driver		= {
 		.name	= SIFIVE_SERIAL_NAME,
 		.pm = pm_sleep_ptr(&sifive_uart_pm_ops),
diff --git a/drivers/tty/serial/sprd_serial.c b/drivers/tty/serial/sprd_serial.c
index f257525f9299..15f14fa593da 100644
--- a/drivers/tty/serial/sprd_serial.c
+++ b/drivers/tty/serial/sprd_serial.c
@@ -1076,7 +1076,7 @@ static struct uart_driver sprd_uart_driver = {
 	.cons = SPRD_CONSOLE,
 };
 
-static int sprd_remove(struct platform_device *dev)
+static void sprd_remove(struct platform_device *dev)
 {
 	struct sprd_uart_port *sup = platform_get_drvdata(dev);
 
@@ -1089,8 +1089,6 @@ static int sprd_remove(struct platform_device *dev)
 
 	if (!sprd_ports_num)
 		uart_unregister_driver(&sprd_uart_driver);
-
-	return 0;
 }
 
 static bool sprd_uart_is_console(struct uart_port *uport)
@@ -1257,7 +1255,7 @@ MODULE_DEVICE_TABLE(of, serial_ids);
 
 static struct platform_driver sprd_platform_driver = {
 	.probe		= sprd_probe,
-	.remove		= sprd_remove,
+	.remove_new	= sprd_remove,
 	.driver		= {
 		.name	= "sprd_serial",
 		.of_match_table = serial_ids,
diff --git a/drivers/tty/serial/st-asc.c b/drivers/tty/serial/st-asc.c
index a821f5d76a26..bbb5595d7e24 100644
--- a/drivers/tty/serial/st-asc.c
+++ b/drivers/tty/serial/st-asc.c
@@ -793,13 +793,11 @@ static int asc_serial_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int asc_serial_remove(struct platform_device *pdev)
+static void asc_serial_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&asc_uart_driver, port);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -932,7 +930,7 @@ static const struct dev_pm_ops asc_serial_pm_ops = {
 
 static struct platform_driver asc_serial_driver = {
 	.probe		= asc_serial_probe,
-	.remove		= asc_serial_remove,
+	.remove_new	= asc_serial_remove,
 	.driver	= {
 		.name	= DRIVER_NAME,
 		.pm	= &asc_serial_pm_ops,
diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c
index 3048620315d6..693e932d6feb 100644
--- a/drivers/tty/serial/stm32-usart.c
+++ b/drivers/tty/serial/stm32-usart.c
@@ -226,12 +226,6 @@ static int stm32_usart_config_rs485(struct uart_port *port, struct ktermios *ter
 
 	stm32_usart_clr_bits(port, ofs->cr1, BIT(cfg->uart_enable_bit));
 
-	if (port->rs485_rx_during_tx_gpio)
-		gpiod_set_value_cansleep(port->rs485_rx_during_tx_gpio,
-					 !!(rs485conf->flags & SER_RS485_RX_DURING_TX));
-	else
-		rs485conf->flags |= SER_RS485_RX_DURING_TX;
-
 	if (rs485conf->flags & SER_RS485_ENABLED) {
 		cr1 = readl_relaxed(port->membase + ofs->cr1);
 		cr3 = readl_relaxed(port->membase + ofs->cr3);
@@ -256,6 +250,10 @@ static int stm32_usart_config_rs485(struct uart_port *port, struct ktermios *ter
 
 		writel_relaxed(cr3, port->membase + ofs->cr3);
 		writel_relaxed(cr1, port->membase + ofs->cr1);
+
+		if (!port->rs485_rx_during_tx_gpio)
+			rs485conf->flags |= SER_RS485_RX_DURING_TX;
+
 	} else {
 		stm32_usart_clr_bits(port, ofs->cr3,
 				     USART_CR3_DEM | USART_CR3_DEP);
@@ -1822,7 +1820,7 @@ err_dma_rx:
 	return ret;
 }
 
-static int stm32_usart_serial_remove(struct platform_device *pdev)
+static void stm32_usart_serial_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 	struct stm32_port *stm32_port = to_stm32_port(port);
@@ -1861,8 +1859,6 @@ static int stm32_usart_serial_remove(struct platform_device *pdev)
 	}
 
 	stm32_usart_deinit_port(stm32_port);
-
-	return 0;
 }
 
 static void __maybe_unused stm32_usart_console_putchar(struct uart_port *port, unsigned char ch)
@@ -2146,7 +2142,7 @@ static const struct dev_pm_ops stm32_serial_pm_ops = {
 
 static struct platform_driver stm32_serial_driver = {
 	.probe		= stm32_usart_serial_probe,
-	.remove		= stm32_usart_serial_remove,
+	.remove_new	= stm32_usart_serial_remove,
 	.driver	= {
 		.name	= DRIVER_NAME,
 		.pm	= &stm32_serial_pm_ops,
diff --git a/drivers/tty/serial/sunhv.c b/drivers/tty/serial/sunhv.c
index 5bfc0040f17b..8d612ab80680 100644
--- a/drivers/tty/serial/sunhv.c
+++ b/drivers/tty/serial/sunhv.c
@@ -595,7 +595,7 @@ out_free_port:
 	return err;
 }
 
-static int hv_remove(struct platform_device *dev)
+static void hv_remove(struct platform_device *dev)
 {
 	struct uart_port *port = platform_get_drvdata(dev);
 
@@ -608,8 +608,6 @@ static int hv_remove(struct platform_device *dev)
 	kfree(con_write_page);
 	kfree(port);
 	sunhv_port = NULL;
-
-	return 0;
 }
 
 static const struct of_device_id hv_match[] = {
@@ -630,7 +628,7 @@ static struct platform_driver hv_driver = {
 		.of_match_table = hv_match,
 	},
 	.probe		= hv_probe,
-	.remove		= hv_remove,
+	.remove_new	= hv_remove,
 };
 
 static int __init sunhv_init(void)
diff --git a/drivers/tty/serial/sunplus-uart.c b/drivers/tty/serial/sunplus-uart.c
index 4251f4e1ba99..99f5285819d4 100644
--- a/drivers/tty/serial/sunplus-uart.c
+++ b/drivers/tty/serial/sunplus-uart.c
@@ -662,13 +662,11 @@ static int sunplus_uart_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int sunplus_uart_remove(struct platform_device *pdev)
+static void sunplus_uart_remove(struct platform_device *pdev)
 {
 	struct sunplus_uart_port *sup = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&sunplus_uart_driver, &sup->port);
-
-	return 0;
 }
 
 static int __maybe_unused sunplus_uart_suspend(struct device *dev)
@@ -703,7 +701,7 @@ MODULE_DEVICE_TABLE(of, sp_uart_of_match);
 
 static struct platform_driver sunplus_uart_platform_driver = {
 	.probe		= sunplus_uart_probe,
-	.remove		= sunplus_uart_remove,
+	.remove_new	= sunplus_uart_remove,
 	.driver = {
 		.name	= "sunplus_uart",
 		.of_match_table = sp_uart_of_match,
diff --git a/drivers/tty/serial/sunsab.c b/drivers/tty/serial/sunsab.c
index 6aa51a6f8063..1ea2f33a07a7 100644
--- a/drivers/tty/serial/sunsab.c
+++ b/drivers/tty/serial/sunsab.c
@@ -443,7 +443,7 @@ static void sunsab_start_tx(struct uart_port *port)
 
 	up->interrupt_mask1 &= ~(SAB82532_IMR1_ALLS|SAB82532_IMR1_XPR);
 	writeb(up->interrupt_mask1, &up->regs->w.imr1);
-	
+
 	if (!test_bit(SAB82532_XPR, &up->irqflags))
 		return;
 
@@ -549,7 +549,7 @@ static int sunsab_startup(struct uart_port *port)
 	(void) readb(&up->regs->r.isr1);
 
 	/*
-	 * Now, initialize the UART 
+	 * Now, initialize the UART
 	 */
 	writeb(0, &up->regs->w.ccr0);				/* power-down */
 	writeb(SAB82532_CCR0_MCE | SAB82532_CCR0_SC_NRZ |
@@ -563,7 +563,7 @@ static int sunsab_startup(struct uart_port *port)
 			   SAB82532_MODE_RAC);
 	writeb(up->cached_mode, &up->regs->w.mode);
 	writeb(SAB82532_RFC_DPS|SAB82532_RFC_RFTH_32, &up->regs->w.rfc);
-	
+
 	tmp = readb(&up->regs->rw.ccr0);
 	tmp |= SAB82532_CCR0_PU;	/* power-up */
 	writeb(tmp, &up->regs->rw.ccr0);
@@ -607,7 +607,7 @@ static void sunsab_shutdown(struct uart_port *port)
 	up->cached_dafo &= ~SAB82532_DAFO_XBRK;
 	writeb(up->cached_dafo, &up->regs->rw.dafo);
 
-	/* Disable Receiver */	
+	/* Disable Receiver */
 	up->cached_mode &= ~SAB82532_MODE_RAC;
 	writeb(up->cached_mode, &up->regs->rw.mode);
 
@@ -622,7 +622,7 @@ static void sunsab_shutdown(struct uart_port *port)
 	 * speed the chip was configured for when the port was open).
 	 */
 #if 0
-	/* Power Down */	
+	/* Power Down */
 	tmp = readb(&up->regs->rw.ccr0);
 	tmp &= ~SAB82532_CCR0_PU;
 	writeb(tmp, &up->regs->rw.ccr0);
@@ -649,7 +649,7 @@ static void calc_ebrg(int baud, int *n_ret, int *m_ret)
 		*m_ret = 0;
 		return;
 	}
-     
+
 	/*
 	 * We scale numbers by 10 so that we get better accuracy
 	 * without having to use floating point.  Here we increment m
@@ -788,7 +788,7 @@ static const char *sunsab_type(struct uart_port *port)
 {
 	struct uart_sunsab_port *up = (void *)port;
 	static char buf[36];
-	
+
 	sprintf(buf, "SAB82532 %s", sab82532_version[up->type]);
 	return buf;
 }
@@ -933,7 +933,7 @@ static int sunsab_console_setup(struct console *con, char *options)
 	sunsab_set_mctrl(&up->port, TIOCM_DTR | TIOCM_RTS);
 
 	uart_port_unlock_irqrestore(&up->port, flags);
-	
+
 	return 0;
 }
 
@@ -1066,7 +1066,7 @@ out:
 	return err;
 }
 
-static int sab_remove(struct platform_device *op)
+static void sab_remove(struct platform_device *op)
 {
 	struct uart_sunsab_port *up = platform_get_drvdata(op);
 
@@ -1078,8 +1078,6 @@ static int sab_remove(struct platform_device *op)
 	of_iounmap(&op->resource[0],
 		   up[0].port.membase,
 		   sizeof(union sab82532_async_regs));
-
-	return 0;
 }
 
 static const struct of_device_id sab_match[] = {
@@ -1100,7 +1098,7 @@ static struct platform_driver sab_driver = {
 		.of_match_table = sab_match,
 	},
 	.probe		= sab_probe,
-	.remove		= sab_remove,
+	.remove_new	= sab_remove,
 };
 
 static int __init sunsab_init(void)
diff --git a/drivers/tty/serial/sunsu.c b/drivers/tty/serial/sunsu.c
index 1e051cc2591c..c8b65f4b2710 100644
--- a/drivers/tty/serial/sunsu.c
+++ b/drivers/tty/serial/sunsu.c
@@ -1515,7 +1515,7 @@ out_unmap:
 	return err;
 }
 
-static int su_remove(struct platform_device *op)
+static void su_remove(struct platform_device *op)
 {
 	struct uart_sunsu_port *up = platform_get_drvdata(op);
 	bool kbdms = false;
@@ -1536,8 +1536,6 @@ static int su_remove(struct platform_device *op)
 
 	if (kbdms)
 		kfree(up);
-
-	return 0;
 }
 
 static const struct of_device_id su_match[] = {
@@ -1565,7 +1563,7 @@ static struct platform_driver su_driver = {
 		.of_match_table = su_match,
 	},
 	.probe		= su_probe,
-	.remove		= su_remove,
+	.remove_new	= su_remove,
 };
 
 static int __init sunsu_init(void)
diff --git a/drivers/tty/serial/sunzilog.c b/drivers/tty/serial/sunzilog.c
index d3b5e864b727..c99289c6c8f8 100644
--- a/drivers/tty/serial/sunzilog.c
+++ b/drivers/tty/serial/sunzilog.c
@@ -1513,7 +1513,7 @@ static void zs_remove_one(struct uart_sunzilog_port *up)
 		uart_remove_one_port(&sunzilog_reg, &up->port);
 }
 
-static int zs_remove(struct platform_device *op)
+static void zs_remove(struct platform_device *op)
 {
 	struct uart_sunzilog_port *up = platform_get_drvdata(op);
 	struct zilog_layout __iomem *regs;
@@ -1523,8 +1523,6 @@ static int zs_remove(struct platform_device *op)
 
 	regs = sunzilog_chip_regs[up[0].port.line / 2];
 	of_iounmap(&op->resource[0], regs, sizeof(struct zilog_layout));
-
-	return 0;
 }
 
 static const struct of_device_id zs_match[] = {
@@ -1541,7 +1539,7 @@ static struct platform_driver zs_driver = {
 		.of_match_table = zs_match,
 	},
 	.probe		= zs_probe,
-	.remove		= zs_remove,
+	.remove_new	= zs_remove,
 };
 
 static int __init sunzilog_init(void)
diff --git a/drivers/tty/serial/tegra-tcu.c b/drivers/tty/serial/tegra-tcu.c
index 65069daf36ec..d9c78320eb02 100644
--- a/drivers/tty/serial/tegra-tcu.c
+++ b/drivers/tty/serial/tegra-tcu.c
@@ -266,7 +266,7 @@ free_tx:
 	return err;
 }
 
-static int tegra_tcu_remove(struct platform_device *pdev)
+static void tegra_tcu_remove(struct platform_device *pdev)
 {
 	struct tegra_tcu *tcu = platform_get_drvdata(pdev);
 
@@ -277,8 +277,6 @@ static int tegra_tcu_remove(struct platform_device *pdev)
 	uart_remove_one_port(&tcu->driver, &tcu->port);
 	uart_unregister_driver(&tcu->driver);
 	mbox_free_channel(tcu->tx);
-
-	return 0;
 }
 
 static const struct of_device_id tegra_tcu_match[] = {
@@ -293,7 +291,7 @@ static struct platform_driver tegra_tcu_driver = {
 		.of_match_table = tegra_tcu_match,
 	},
 	.probe = tegra_tcu_probe,
-	.remove = tegra_tcu_remove,
+	.remove_new = tegra_tcu_remove,
 };
 module_platform_driver(tegra_tcu_driver);
 
diff --git a/drivers/tty/serial/timbuart.c b/drivers/tty/serial/timbuart.c
index 0cc6524f5e8b..4bc89a9b380a 100644
--- a/drivers/tty/serial/timbuart.c
+++ b/drivers/tty/serial/timbuart.c
@@ -473,7 +473,7 @@ err_mem:
 	return err;
 }
 
-static int timbuart_remove(struct platform_device *dev)
+static void timbuart_remove(struct platform_device *dev)
 {
 	struct timbuart_port *uart = platform_get_drvdata(dev);
 
@@ -481,8 +481,6 @@ static int timbuart_remove(struct platform_device *dev)
 	uart_remove_one_port(&timbuart_driver, &uart->port);
 	uart_unregister_driver(&timbuart_driver);
 	kfree(uart);
-
-	return 0;
 }
 
 static struct platform_driver timbuart_platform_driver = {
@@ -490,7 +488,7 @@ static struct platform_driver timbuart_platform_driver = {
 		.name	= "timb-uart",
 	},
 	.probe		= timbuart_probe,
-	.remove		= timbuart_remove,
+	.remove_new	= timbuart_remove,
 };
 
 module_platform_driver(timbuart_platform_driver);
diff --git a/drivers/tty/serial/uartlite.c b/drivers/tty/serial/uartlite.c
index 404c14acafa5..10ba41b7be99 100644
--- a/drivers/tty/serial/uartlite.c
+++ b/drivers/tty/serial/uartlite.c
@@ -24,8 +24,13 @@
 #include <linux/pm_runtime.h>
 
 #define ULITE_NAME		"ttyUL"
+#if CONFIG_SERIAL_UARTLITE_NR_UARTS > 4
+#define ULITE_MAJOR             0       /* use dynamic node allocation */
+#define ULITE_MINOR             0
+#else
 #define ULITE_MAJOR		204
 #define ULITE_MINOR		187
+#endif
 #define ULITE_NR_UARTS		CONFIG_SERIAL_UARTLITE_NR_UARTS
 
 /* ---------------------------------------------------------------------
@@ -62,11 +67,11 @@ static struct uart_port *console_port;
 #endif
 
 /**
- * struct uartlite_data: Driver private data
- * reg_ops: Functions to read/write registers
- * clk: Our parent clock, if present
- * baud: The baud rate configured when this device was synthesized
- * cflags: The cflags for parity and data bits
+ * struct uartlite_data - Driver private data
+ * @reg_ops: Functions to read/write registers
+ * @clk: Our parent clock, if present
+ * @baud: The baud rate configured when this device was synthesized
+ * @cflags: The cflags for parity and data bits
  */
 struct uartlite_data {
 	const struct uartlite_reg_ops *reg_ops;
@@ -890,7 +895,7 @@ of_err:
 	return ret;
 }
 
-static int ulite_remove(struct platform_device *pdev)
+static void ulite_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = dev_get_drvdata(&pdev->dev);
 	struct uartlite_data *pdata = port->private_data;
@@ -900,7 +905,6 @@ static int ulite_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_set_suspended(&pdev->dev);
 	pm_runtime_dont_use_autosuspend(&pdev->dev);
-	return 0;
 }
 
 /* work with hotplug and coldplug */
@@ -908,7 +912,7 @@ MODULE_ALIAS("platform:uartlite");
 
 static struct platform_driver ulite_platform_driver = {
 	.probe = ulite_probe,
-	.remove = ulite_remove,
+	.remove_new = ulite_remove,
 	.driver = {
 		.name  = "uartlite",
 		.of_match_table = of_match_ptr(ulite_of_match),
diff --git a/drivers/tty/serial/ucc_uart.c b/drivers/tty/serial/ucc_uart.c
index ed7a6bb5596a..397b95dff7ed 100644
--- a/drivers/tty/serial/ucc_uart.c
+++ b/drivers/tty/serial/ucc_uart.c
@@ -189,10 +189,10 @@ struct uart_qe_port {
 	u16 tx_fifosize;
 	int wait_closing;
 	u32 flags;
-	struct qe_bd *rx_bd_base;
-	struct qe_bd *rx_cur;
-	struct qe_bd *tx_bd_base;
-	struct qe_bd *tx_cur;
+	struct qe_bd __iomem *rx_bd_base;
+	struct qe_bd __iomem *rx_cur;
+	struct qe_bd __iomem *tx_bd_base;
+	struct qe_bd __iomem *tx_cur;
 	unsigned char *tx_buf;
 	unsigned char *rx_buf;
 	void *bd_virt;  	/* virtual address of the BD buffers */
@@ -258,7 +258,7 @@ static unsigned int qe_uart_tx_empty(struct uart_port *port)
 {
 	struct uart_qe_port *qe_port =
 		container_of(port, struct uart_qe_port, port);
-	struct qe_bd *bdp = qe_port->tx_bd_base;
+	struct qe_bd __iomem *bdp = qe_port->tx_bd_base;
 
 	while (1) {
 		if (ioread16be(&bdp->status) & BD_SC_READY)
@@ -330,7 +330,7 @@ static void qe_uart_stop_tx(struct uart_port *port)
  */
 static int qe_uart_tx_pump(struct uart_qe_port *qe_port)
 {
-	struct qe_bd *bdp;
+	struct qe_bd __iomem *bdp;
 	unsigned char *p;
 	unsigned int count;
 	struct uart_port *port = &qe_port->port;
@@ -341,7 +341,7 @@ static int qe_uart_tx_pump(struct uart_qe_port *qe_port)
 		/* Pick next descriptor and fill from buffer */
 		bdp = qe_port->tx_cur;
 
-		p = qe2cpu_addr(be32_to_cpu(bdp->buf), qe_port);
+		p = qe2cpu_addr(ioread32be(&bdp->buf), qe_port);
 
 		*p++ = port->x_char;
 		iowrite16be(1, &bdp->length);
@@ -368,7 +368,7 @@ static int qe_uart_tx_pump(struct uart_qe_port *qe_port)
 
 	while (!(ioread16be(&bdp->status) & BD_SC_READY) && !uart_circ_empty(xmit)) {
 		count = 0;
-		p = qe2cpu_addr(be32_to_cpu(bdp->buf), qe_port);
+		p = qe2cpu_addr(ioread32be(&bdp->buf), qe_port);
 		while (count < qe_port->tx_fifosize) {
 			*p++ = xmit->buf[xmit->tail];
 			uart_xmit_advance(port, 1);
@@ -460,7 +460,7 @@ static void qe_uart_int_rx(struct uart_qe_port *qe_port)
 	unsigned char ch, *cp;
 	struct uart_port *port = &qe_port->port;
 	struct tty_port *tport = &port->state->port;
-	struct qe_bd *bdp;
+	struct qe_bd __iomem *bdp;
 	u16 status;
 	unsigned int flg;
 
@@ -487,7 +487,7 @@ static void qe_uart_int_rx(struct uart_qe_port *qe_port)
 		}
 
 		/* get pointer */
-		cp = qe2cpu_addr(be32_to_cpu(bdp->buf), qe_port);
+		cp = qe2cpu_addr(ioread32be(&bdp->buf), qe_port);
 
 		/* loop through the buffer */
 		while (i-- > 0) {
@@ -590,7 +590,7 @@ static void qe_uart_initbd(struct uart_qe_port *qe_port)
 {
 	int i;
 	void *bd_virt;
-	struct qe_bd *bdp;
+	struct qe_bd __iomem *bdp;
 
 	/* Set the physical address of the host memory buffers in the buffer
 	 * descriptors, and the virtual address for us to work with.
@@ -648,7 +648,7 @@ static void qe_uart_init_ucc(struct uart_qe_port *qe_port)
 {
 	u32 cecr_subblock;
 	struct ucc_slow __iomem *uccp = qe_port->uccp;
-	struct ucc_uart_pram *uccup = qe_port->uccup;
+	struct ucc_uart_pram __iomem *uccup = qe_port->uccup;
 
 	unsigned int i;
 
@@ -983,7 +983,7 @@ static int qe_uart_request_port(struct uart_port *port)
 
 	qe_port->us_private = uccs;
 	qe_port->uccp = uccs->us_regs;
-	qe_port->uccup = (struct ucc_uart_pram *) uccs->us_pram;
+	qe_port->uccup = (struct ucc_uart_pram __iomem *)uccs->us_pram;
 	qe_port->rx_bd_base = uccs->rx_bd;
 	qe_port->tx_bd_base = uccs->tx_bd;
 
@@ -1156,7 +1156,7 @@ static void uart_firmware_cont(const struct firmware *fw, void *context)
 
 	firmware = (struct qe_firmware *) fw->data;
 
-	if (firmware->header.length != fw->size) {
+	if (be32_to_cpu(firmware->header.length) != fw->size) {
 		dev_err(dev, "invalid firmware\n");
 		goto out;
 	}
@@ -1459,7 +1459,7 @@ out_free:
 	return ret;
 }
 
-static int ucc_uart_remove(struct platform_device *ofdev)
+static void ucc_uart_remove(struct platform_device *ofdev)
 {
 	struct uart_qe_port *qe_port = platform_get_drvdata(ofdev);
 
@@ -1470,8 +1470,6 @@ static int ucc_uart_remove(struct platform_device *ofdev)
 	of_node_put(qe_port->np);
 
 	kfree(qe_port);
-
-	return 0;
 }
 
 static const struct of_device_id ucc_uart_match[] = {
@@ -1492,7 +1490,7 @@ static struct platform_driver ucc_uart_of_driver = {
 		.of_match_table    = ucc_uart_match,
 	},
 	.probe  	= ucc_uart_probe,
-	.remove 	= ucc_uart_remove,
+	.remove_new 	= ucc_uart_remove,
 };
 
 static int __init ucc_uart_init(void)
diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index 66a45a634158..920762d7b4a4 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -1663,10 +1663,8 @@ err_out_unregister_driver:
 /**
  * cdns_uart_remove - called when the platform driver is unregistered
  * @pdev: Pointer to the platform device structure
- *
- * Return: 0 on success, negative errno otherwise
  */
-static int cdns_uart_remove(struct platform_device *pdev)
+static void cdns_uart_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 	struct cdns_uart *cdns_uart_data = port->private_data;
@@ -1692,12 +1690,11 @@ static int cdns_uart_remove(struct platform_device *pdev)
 
 	if (!--instances)
 		uart_unregister_driver(cdns_uart_data->cdns_uart_driver);
-	return 0;
 }
 
 static struct platform_driver cdns_uart_platform_driver = {
 	.probe   = cdns_uart_probe,
-	.remove  = cdns_uart_remove,
+	.remove_new = cdns_uart_remove,
 	.driver  = {
 		.name = CDNS_UART_NAME,
 		.of_match_table = cdns_uart_of_match,
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 6b4a28bcf2f5..02217e3c916b 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -1150,16 +1150,29 @@ EXPORT_SYMBOL(unregister_sysrq_key);
 #ifdef CONFIG_PROC_FS
 /*
  * writing 'C' to /proc/sysrq-trigger is like sysrq-C
+ * Normally, only the first character written is processed.
+ * However, if the first character is an underscore,
+ * all characters are processed.
  */
 static ssize_t write_sysrq_trigger(struct file *file, const char __user *buf,
 				   size_t count, loff_t *ppos)
 {
-	if (count) {
+	bool bulk = false;
+	size_t i;
+
+	for (i = 0; i < count; i++) {
 		char c;
 
-		if (get_user(c, buf))
+		if (get_user(c, buf + i))
 			return -EFAULT;
-		__handle_sysrq(c, false);
+
+		if (c == '_')
+			bulk = true;
+		else
+			__handle_sysrq(c, false);
+
+		if (!bulk)
+			break;
 	}
 
 	return count;
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 06414e43e0b5..407b0d87b7c1 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -852,9 +852,9 @@ static ssize_t iterate_tty_read(struct tty_ldisc *ld, struct tty_struct *tty,
 {
 	void *cookie = NULL;
 	unsigned long offset = 0;
-	char kernel_buf[64];
 	ssize_t retval = 0;
 	size_t copied, count = iov_iter_count(to);
+	u8 kernel_buf[64];
 
 	do {
 		ssize_t size = min(count, sizeof(kernel_buf));
@@ -995,7 +995,7 @@ static ssize_t iterate_tty_write(struct tty_ldisc *ld, struct tty_struct *tty,
 
 	/* write_buf/write_cnt is protected by the atomic_write_lock mutex */
 	if (tty->write_cnt < chunk) {
-		unsigned char *buf_chunk;
+		u8 *buf_chunk;
 
 		if (chunk < 1024)
 			chunk = 1024;
@@ -1047,6 +1047,7 @@ out:
 	return ret;
 }
 
+#ifdef CONFIG_PRINT_QUOTA_WARNING
 /**
  * tty_write_message - write a message to a certain tty, not just the console.
  * @tty: the destination tty_struct
@@ -1057,6 +1058,8 @@ out:
  * needed.
  *
  * We must still hold the BTM and test the CLOSING flag for the moment.
+ *
+ * This function is DEPRECATED, do not use in new code.
  */
 void tty_write_message(struct tty_struct *tty, char *msg)
 {
@@ -1069,6 +1072,7 @@ void tty_write_message(struct tty_struct *tty, char *msg)
 		tty_write_unlock(tty);
 	}
 }
+#endif
 
 static ssize_t file_tty_write(struct file *file, struct kiocb *iocb, struct iov_iter *from)
 {
@@ -1145,7 +1149,7 @@ ssize_t redirected_tty_write(struct kiocb *iocb, struct iov_iter *iter)
  *
  * Locking: none for xchar method, write ordering for write method.
  */
-int tty_send_xchar(struct tty_struct *tty, char ch)
+int tty_send_xchar(struct tty_struct *tty, u8 ch)
 {
 	bool was_stopped = tty->flow.stopped;
 
@@ -2274,10 +2278,10 @@ static bool tty_legacy_tiocsti __read_mostly = IS_ENABLED(CONFIG_LEGACY_TIOCSTI)
  *  * Called functions take tty_ldiscs_lock
  *  * current->signal->tty check is safe without locks
  */
-static int tiocsti(struct tty_struct *tty, char __user *p)
+static int tiocsti(struct tty_struct *tty, u8 __user *p)
 {
-	char ch, mbz = 0;
 	struct tty_ldisc *ld;
+	u8 ch;
 
 	if (!tty_legacy_tiocsti && !capable(CAP_SYS_ADMIN))
 		return -EIO;
@@ -2292,7 +2296,7 @@ static int tiocsti(struct tty_struct *tty, char __user *p)
 		return -EIO;
 	tty_buffer_lock_exclusive(tty->port);
 	if (ld->ops->receive_buf)
-		ld->ops->receive_buf(tty, &ch, &mbz, 1);
+		ld->ops->receive_buf(tty, &ch, NULL, 1);
 	tty_buffer_unlock_exclusive(tty->port);
 	tty_ldisc_deref(ld);
 	return 0;
@@ -2489,6 +2493,9 @@ static int send_break(struct tty_struct *tty, unsigned int duration)
 	if (!retval) {
 		msleep_interruptible(duration);
 		retval = tty->ops->break_ctl(tty, 0);
+	} else if (retval == -EOPNOTSUPP) {
+		/* some drivers can tell only dynamically */
+		retval = 0;
 	}
 	tty_write_unlock(tty);
 
@@ -2499,6 +2506,24 @@ static int send_break(struct tty_struct *tty, unsigned int duration)
 }
 
 /**
+ * tty_get_tiocm - get tiocm status register
+ * @tty: tty device
+ *
+ * Obtain the modem status bits from the tty driver if the feature
+ * is supported.
+ */
+int tty_get_tiocm(struct tty_struct *tty)
+{
+	int retval = -ENOTTY;
+
+	if (tty->ops->tiocmget)
+		retval = tty->ops->tiocmget(tty);
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(tty_get_tiocm);
+
+/**
  * tty_tiocmget - get modem status
  * @tty: tty device
  * @p: pointer to result
@@ -2510,14 +2535,12 @@ static int send_break(struct tty_struct *tty, unsigned int duration)
  */
 static int tty_tiocmget(struct tty_struct *tty, int __user *p)
 {
-	int retval = -ENOTTY;
+	int retval;
 
-	if (tty->ops->tiocmget) {
-		retval = tty->ops->tiocmget(tty);
+	retval = tty_get_tiocm(tty);
+	if (retval >= 0)
+		retval = put_user(retval, p);
 
-		if (retval >= 0)
-			retval = put_user(retval, p);
-	}
 	return retval;
 }
 
@@ -3138,7 +3161,7 @@ struct tty_struct *alloc_tty_struct(struct tty_driver *driver, int idx)
  *
  * Return: the number of characters successfully output.
  */
-int tty_put_char(struct tty_struct *tty, unsigned char ch)
+int tty_put_char(struct tty_struct *tty, u8 ch)
 {
 	if (tty->ops->put_char)
 		return tty->ops->put_char(tty, ch);
diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c
index 4b499301a3db..85de90eebc7b 100644
--- a/drivers/tty/tty_ioctl.c
+++ b/drivers/tty/tty_ioctl.c
@@ -844,7 +844,7 @@ int tty_mode_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg)
 			ret = -EFAULT;
 		return ret;
 	case TIOCSLCKTRMIOS:
-		if (!capable(CAP_SYS_ADMIN))
+		if (!checkpoint_restore_ns_capable(&init_user_ns))
 			return -EPERM;
 		copy_termios_locked(real_tty, &kterm);
 		if (user_termios_to_kernel_termios(&kterm,
@@ -861,7 +861,7 @@ int tty_mode_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg)
 			ret = -EFAULT;
 		return ret;
 	case TIOCSLCKTRMIOS:
-		if (!capable(CAP_SYS_ADMIN))
+		if (!checkpoint_restore_ns_capable(&init_user_ns))
 			return -EPERM;
 		copy_termios_locked(real_tty, &kterm);
 		if (user_termios_to_kernel_termios_1(&kterm,
diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c
index 63c125250961..14cca33d2269 100644
--- a/drivers/tty/tty_port.c
+++ b/drivers/tty/tty_port.c
@@ -171,7 +171,8 @@ EXPORT_SYMBOL_GPL(tty_port_register_device_attr);
  * @port: tty_port of the device
  * @driver: tty_driver for this device
  * @index: index of the tty
- * @device: parent if exists, otherwise NULL
+ * @host: serial port hardware device
+ * @parent: parent if exists, otherwise NULL
  * @drvdata: driver data for the device
  * @attr_grp: attribute group for the device
  *
@@ -180,20 +181,20 @@ EXPORT_SYMBOL_GPL(tty_port_register_device_attr);
  */
 struct device *tty_port_register_device_attr_serdev(struct tty_port *port,
 		struct tty_driver *driver, unsigned index,
-		struct device *device, void *drvdata,
+		struct device *host, struct device *parent, void *drvdata,
 		const struct attribute_group **attr_grp)
 {
 	struct device *dev;
 
 	tty_port_link_device(port, driver, index);
 
-	dev = serdev_tty_port_register(port, device, driver, index);
+	dev = serdev_tty_port_register(port, host, parent, driver, index);
 	if (PTR_ERR(dev) != -ENODEV) {
 		/* Skip creating cdev if we registered a serdev device */
 		return dev;
 	}
 
-	return tty_register_device_attr(driver, index, device, drvdata,
+	return tty_register_device_attr(driver, index, parent, drvdata,
 			attr_grp);
 }
 EXPORT_SYMBOL_GPL(tty_port_register_device_attr_serdev);
@@ -203,17 +204,18 @@ EXPORT_SYMBOL_GPL(tty_port_register_device_attr_serdev);
  * @port: tty_port of the device
  * @driver: tty_driver for this device
  * @index: index of the tty
- * @device: parent if exists, otherwise NULL
+ * @host: serial port hardware controller device
+ * @parent: parent if exists, otherwise NULL
  *
  * Register a serdev or tty device depending on if the parent device has any
  * defined serdev clients or not.
  */
 struct device *tty_port_register_device_serdev(struct tty_port *port,
 		struct tty_driver *driver, unsigned index,
-		struct device *device)
+		struct device *host, struct device *parent)
 {
 	return tty_port_register_device_attr_serdev(port, driver, index,
-			device, NULL, NULL);
+			host, parent, NULL, NULL);
 }
 EXPORT_SYMBOL_GPL(tty_port_register_device_serdev);
 
@@ -245,7 +247,7 @@ int tty_port_alloc_xmit_buf(struct tty_port *port)
 	/* We may sleep in get_zeroed_page() */
 	mutex_lock(&port->buf_mutex);
 	if (port->xmit_buf == NULL) {
-		port->xmit_buf = (unsigned char *)get_zeroed_page(GFP_KERNEL);
+		port->xmit_buf = (u8 *)get_zeroed_page(GFP_KERNEL);
 		if (port->xmit_buf)
 			kfifo_init(&port->xmit_fifo, port->xmit_buf, PAGE_SIZE);
 	}
diff --git a/drivers/tty/vt/consolemap.c b/drivers/tty/vt/consolemap.c
index 5e39a4f430ee..82d70083fead 100644
--- a/drivers/tty/vt/consolemap.c
+++ b/drivers/tty/vt/consolemap.c
@@ -644,7 +644,7 @@ int con_set_unimap(struct vc_data *vc, ushort ct, struct unipair __user *list)
 	if (!ct)
 		return 0;
 
-	unilist = vmemdup_user(list, array_size(sizeof(*unilist), ct));
+	unilist = vmemdup_array_user(list, ct, sizeof(*unilist));
 	if (IS_ERR(unilist))
 		return PTR_ERR(unilist);
 
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index 12a192e1196b..a2116e135a82 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -1772,12 +1772,10 @@ int vt_do_diacrit(unsigned int cmd, void __user *udp, int perm)
 			return -EINVAL;
 
 		if (ct) {
-
-			dia = memdup_user(a->kbdiacr,
-					sizeof(struct kbdiacr) * ct);
+			dia = memdup_array_user(a->kbdiacr,
+						ct, sizeof(struct kbdiacr));
 			if (IS_ERR(dia))
 				return PTR_ERR(dia);
-
 		}
 
 		spin_lock_irqsave(&kbd_event_lock, flags);
@@ -1811,8 +1809,8 @@ int vt_do_diacrit(unsigned int cmd, void __user *udp, int perm)
 			return -EINVAL;
 
 		if (ct) {
-			buf = memdup_user(a->kbdiacruc,
-					  ct * sizeof(struct kbdiacruc));
+			buf = memdup_array_user(a->kbdiacruc,
+						ct, sizeof(struct kbdiacruc));
 			if (IS_ERR(buf))
 				return PTR_ERR(buf);
 		} 
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 156efda7c80d..38a765eadbe2 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -381,7 +381,7 @@ static void vc_uniscr_delete(struct vc_data *vc, unsigned int nr)
 		u32 *ln = vc->vc_uni_lines[vc->state.y];
 		unsigned int x = vc->state.x, cols = vc->vc_cols;
 
-		memcpy(&ln[x], &ln[x + nr], (cols - x - nr) * sizeof(*ln));
+		memmove(&ln[x], &ln[x + nr], (cols - x - nr) * sizeof(*ln));
 		memset32(&ln[cols - nr], ' ', nr);
 	}
 }
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index d1e33328ff3f..eac7fff6992d 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -1469,7 +1469,7 @@ static int ufshcd_devfreq_target(struct device *dev,
 	int ret = 0;
 	struct ufs_hba *hba = dev_get_drvdata(dev);
 	ktime_t start;
-	bool scale_up, sched_clk_scaling_suspend_work = false;
+	bool scale_up = false, sched_clk_scaling_suspend_work = false;
 	struct list_head *clk_list = &hba->clk_list_head;
 	struct ufs_clk_info *clki;
 	unsigned long irq_flags;
@@ -3057,7 +3057,7 @@ bool ufshcd_cmd_inflight(struct scsi_cmnd *cmd)
  */
 static int ufshcd_clear_cmd(struct ufs_hba *hba, u32 task_tag)
 {
-	u32 mask = 1U << task_tag;
+	u32 mask;
 	unsigned long flags;
 	int err;
 
@@ -3075,6 +3075,8 @@ static int ufshcd_clear_cmd(struct ufs_hba *hba, u32 task_tag)
 		return 0;
 	}
 
+	mask = 1U << task_tag;
+
 	/* clear outstanding transaction before retry */
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	ufshcd_utrl_clear(hba, mask);
@@ -6352,7 +6354,6 @@ static void ufshcd_err_handling_prepare(struct ufs_hba *hba)
 		ufshcd_hold(hba);
 		if (!ufshcd_is_clkgating_allowed(hba))
 			ufshcd_setup_clocks(hba, true);
-		ufshcd_release(hba);
 		pm_op = hba->is_sys_suspended ? UFS_SYSTEM_PM : UFS_RUNTIME_PM;
 		ufshcd_vops_resume(hba, pm_op);
 	} else {
@@ -8725,7 +8726,6 @@ static int ufshcd_add_lus(struct ufs_hba *hba)
 
 	ufs_bsg_probe(hba);
 	scsi_scan_host(hba->host);
-	pm_runtime_put_sync(hba->dev);
 
 out:
 	return ret;
@@ -8994,15 +8994,12 @@ static void ufshcd_async_scan(void *data, async_cookie_t cookie)
 
 	/* Probe and add UFS logical units  */
 	ret = ufshcd_add_lus(hba);
+
 out:
-	/*
-	 * If we failed to initialize the device or the device is not
-	 * present, turn off the power/clocks etc.
-	 */
-	if (ret) {
-		pm_runtime_put_sync(hba->dev);
-		ufshcd_hba_exit(hba);
-	}
+	pm_runtime_put_sync(hba->dev);
+
+	if (ret)
+		dev_err(hba->dev, "%s failed: %d\n", __func__, ret);
 }
 
 static enum scsi_timeout_action ufshcd_eh_timed_out(struct scsi_cmnd *scmd)
@@ -10596,7 +10593,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	err = blk_mq_alloc_tag_set(&hba->tmf_tag_set);
 	if (err < 0)
 		goto out_remove_scsi_host;
-	hba->tmf_queue = blk_mq_init_queue(&hba->tmf_tag_set);
+	hba->tmf_queue = blk_mq_alloc_queue(&hba->tmf_tag_set, NULL, NULL);
 	if (IS_ERR(hba->tmf_queue)) {
 		err = PTR_ERR(hba->tmf_queue);
 		goto free_tmf_tag_set;
diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c
index 480787048e75..39eef470f8fa 100644
--- a/drivers/ufs/host/ufs-qcom.c
+++ b/drivers/ufs/host/ufs-qcom.c
@@ -1716,7 +1716,7 @@ static int ufs_qcom_config_esi(struct ufs_hba *hba)
 					     ufs_qcom_write_msi_msg);
 	if (ret) {
 		dev_err(hba->dev, "Failed to request Platform MSI %d\n", ret);
-		goto out;
+		return ret;
 	}
 
 	msi_lock_descs(hba->dev);
@@ -1750,11 +1750,8 @@ static int ufs_qcom_config_esi(struct ufs_hba *hba)
 				    FIELD_PREP(ESI_VEC_MASK, MAX_ESI_VEC - 1),
 				    REG_UFS_CFG3);
 		ufshcd_mcq_enable_esi(hba);
-	}
-
-out:
-	if (!ret)
 		host->esi_enabled = true;
+	}
 
 	return ret;
 }
diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c
index 62082d64ece0..2d572f6c8ec8 100644
--- a/drivers/uio/uio.c
+++ b/drivers/uio/uio.c
@@ -466,13 +466,13 @@ static int uio_open(struct inode *inode, struct file *filep)
 
 	mutex_lock(&minor_lock);
 	idev = idr_find(&uio_idr, iminor(inode));
-	mutex_unlock(&minor_lock);
 	if (!idev) {
 		ret = -ENODEV;
+		mutex_unlock(&minor_lock);
 		goto out;
 	}
-
 	get_device(&idev->dev);
+	mutex_unlock(&minor_lock);
 
 	if (!try_module_get(idev->owner)) {
 		ret = -ENODEV;
@@ -1064,9 +1064,8 @@ void uio_unregister_device(struct uio_info *info)
 	wake_up_interruptible(&idev->wait);
 	kill_fasync(&idev->async_queue, SIGIO, POLL_HUP);
 
-	device_unregister(&idev->dev);
-
 	uio_free_minor(minor);
+	device_unregister(&idev->dev);
 
 	return;
 }
diff --git a/drivers/usb/atm/ueagle-atm.c b/drivers/usb/atm/ueagle-atm.c
index 5812f7ea7f90..16703815be0c 100644
--- a/drivers/usb/atm/ueagle-atm.c
+++ b/drivers/usb/atm/ueagle-atm.c
@@ -546,7 +546,7 @@ MODULE_PARM_DESC(annex,
 
 #define uea_wait(sc, cond, timeo) \
 ({ \
-	int _r = wait_event_interruptible_timeout(sc->sync_q, \
+	int _r = wait_event_freezable_timeout(sc->sync_q, \
 			(cond) || kthread_should_stop(), timeo); \
 	if (kthread_should_stop()) \
 		_r = -ENODEV; \
@@ -1896,7 +1896,6 @@ static int uea_kthread(void *data)
 			ret = sc->stat(sc);
 		if (ret != -EAGAIN)
 			uea_wait(sc, 0, msecs_to_jiffies(1000));
-		try_to_freeze();
 	}
 	uea_leaves(INS_TO_USBDEV(sc));
 	return ret;
@@ -2252,7 +2251,7 @@ static ssize_t stat_status_show(struct device *dev, struct device_attribute *att
 	sc = dev_to_uea(dev);
 	if (!sc)
 		goto out;
-	ret = snprintf(buf, 10, "%08x\n", sc->stats.phy.state);
+	ret = sysfs_emit(buf, "%08x\n", sc->stats.phy.state);
 out:
 	mutex_unlock(&uea_mutex);
 	return ret;
@@ -2318,19 +2317,19 @@ static ssize_t stat_human_status_show(struct device *dev,
 
 	switch (modem_state) {
 	case 0:
-		ret = sprintf(buf, "Modem is booting\n");
+		ret = sysfs_emit(buf, "Modem is booting\n");
 		break;
 	case 1:
-		ret = sprintf(buf, "Modem is initializing\n");
+		ret = sysfs_emit(buf, "Modem is initializing\n");
 		break;
 	case 2:
-		ret = sprintf(buf, "Modem is operational\n");
+		ret = sysfs_emit(buf, "Modem is operational\n");
 		break;
 	case 3:
-		ret = sprintf(buf, "Modem synchronization failed\n");
+		ret = sysfs_emit(buf, "Modem synchronization failed\n");
 		break;
 	default:
-		ret = sprintf(buf, "Modem state is unknown\n");
+		ret = sysfs_emit(buf, "Modem state is unknown\n");
 		break;
 	}
 out:
@@ -2364,7 +2363,7 @@ static ssize_t stat_delin_show(struct device *dev, struct device_attribute *attr
 			delin = "LOSS";
 	}
 
-	ret = sprintf(buf, "%s\n", delin);
+	ret = sysfs_emit(buf, "%s\n", delin);
 out:
 	mutex_unlock(&uea_mutex);
 	return ret;
@@ -2384,7 +2383,7 @@ static ssize_t stat_##name##_show(struct device *dev,		\
 	sc = dev_to_uea(dev);					\
 	if (!sc)						\
 		goto out;					\
-	ret = snprintf(buf, 10, "%08x\n", sc->stats.phy.name);	\
+	ret = sysfs_emit(buf, "%08x\n", sc->stats.phy.name);	\
 	if (reset)						\
 		sc->stats.phy.name = 0;				\
 out:								\
diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c
index 11a5b3437c32..fd1beb10bba7 100644
--- a/drivers/usb/cdns3/cdns3-gadget.c
+++ b/drivers/usb/cdns3/cdns3-gadget.c
@@ -828,7 +828,11 @@ void cdns3_gadget_giveback(struct cdns3_endpoint *priv_ep,
 			return;
 	}
 
-	if (request->complete) {
+	/*
+	 * zlp request is appended by driver, needn't call usb_gadget_giveback_request() to notify
+	 * gadget composite driver.
+	 */
+	if (request->complete && request->buf != priv_dev->zlp_buf) {
 		spin_unlock(&priv_dev->lock);
 		usb_gadget_giveback_request(&priv_ep->endpoint,
 					    request);
@@ -1119,6 +1123,8 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep,
 	dma_addr_t trb_dma;
 	u32 togle_pcs = 1;
 	int sg_iter = 0;
+	int num_trb_req;
+	int trb_burst;
 	int num_trb;
 	int address;
 	u32 control;
@@ -1126,16 +1132,15 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep,
 	u16 total_tdl = 0;
 	struct scatterlist *s = NULL;
 	bool sg_supported = !!(request->num_mapped_sgs);
+	u32 ioc = request->no_interrupt ? 0 : TRB_IOC;
+
+	num_trb_req = sg_supported ? request->num_mapped_sgs : 1;
 
+	/* ISO transfer require each SOF have a TD, each TD include some TRBs */
 	if (priv_ep->type == USB_ENDPOINT_XFER_ISOC)
-		num_trb = priv_ep->interval;
+		num_trb = priv_ep->interval * num_trb_req;
 	else
-		num_trb = sg_supported ? request->num_mapped_sgs : 1;
-
-	if (num_trb > priv_ep->free_trbs) {
-		priv_ep->flags |= EP_RING_FULL;
-		return -ENOBUFS;
-	}
+		num_trb = num_trb_req;
 
 	priv_req = to_cdns3_request(request);
 	address = priv_ep->endpoint.desc->bEndpointAddress;
@@ -1184,14 +1189,31 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep,
 
 		link_trb->control = cpu_to_le32(((priv_ep->pcs) ? TRB_CYCLE : 0) |
 				    TRB_TYPE(TRB_LINK) | TRB_TOGGLE | ch_bit);
+
+		if (priv_ep->type == USB_ENDPOINT_XFER_ISOC) {
+			/*
+			 * ISO require LINK TRB must be first one of TD.
+			 * Fill LINK TRBs for left trb space to simply software process logic.
+			 */
+			while (priv_ep->enqueue) {
+				*trb = *link_trb;
+				trace_cdns3_prepare_trb(priv_ep, trb);
+
+				cdns3_ep_inc_enq(priv_ep);
+				trb = priv_ep->trb_pool + priv_ep->enqueue;
+				priv_req->trb = trb;
+			}
+		}
+	}
+
+	if (num_trb > priv_ep->free_trbs) {
+		priv_ep->flags |= EP_RING_FULL;
+		return -ENOBUFS;
 	}
 
 	if (priv_dev->dev_ver <= DEV_VER_V2)
 		togle_pcs = cdns3_wa1_update_guard(priv_ep, trb);
 
-	if (sg_supported)
-		s = request->sg;
-
 	/* set incorrect Cycle Bit for first trb*/
 	control = priv_ep->pcs ? 0 : TRB_CYCLE;
 	trb->length = 0;
@@ -1209,6 +1231,9 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep,
 	do {
 		u32 length;
 
+		if (!(sg_iter % num_trb_req) && sg_supported)
+			s = request->sg;
+
 		/* fill TRB */
 		control |= TRB_TYPE(TRB_NORMAL);
 		if (sg_supported) {
@@ -1223,7 +1248,36 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep,
 			total_tdl += DIV_ROUND_UP(length,
 					       priv_ep->endpoint.maxpacket);
 
-		trb->length |= cpu_to_le32(TRB_BURST_LEN(priv_ep->trb_burst_size) |
+		trb_burst = priv_ep->trb_burst_size;
+
+		/*
+		 * Supposed DMA cross 4k bounder problem should be fixed at DEV_VER_V2, but still
+		 * met problem when do ISO transfer if sg enabled.
+		 *
+		 * Data pattern likes below when sg enabled, package size is 1k and mult is 2
+		 *       [UVC Header(8B) ] [data(3k - 8)] ...
+		 *
+		 * The received data at offset 0xd000 will get 0xc000 data, len 0x70. Error happen
+		 * as below pattern:
+		 *	0xd000: wrong
+		 *	0xe000: wrong
+		 *	0xf000: correct
+		 *	0x10000: wrong
+		 *	0x11000: wrong
+		 *	0x12000: correct
+		 *	...
+		 *
+		 * But it is still unclear about why error have not happen below 0xd000, it should
+		 * cross 4k bounder. But anyway, the below code can fix this problem.
+		 *
+		 * To avoid DMA cross 4k bounder at ISO transfer, reduce burst len according to 16.
+		 */
+		if (priv_ep->type == USB_ENDPOINT_XFER_ISOC && priv_dev->dev_ver <= DEV_VER_V2)
+			if (ALIGN_DOWN(trb->buffer, SZ_4K) !=
+			    ALIGN_DOWN(trb->buffer + length, SZ_4K))
+				trb_burst = 16;
+
+		trb->length |= cpu_to_le32(TRB_BURST_LEN(trb_burst) |
 					TRB_LEN(length));
 		pcs = priv_ep->pcs ? TRB_CYCLE : 0;
 
@@ -1235,11 +1289,11 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep,
 			control |= pcs;
 
 		if (priv_ep->type == USB_ENDPOINT_XFER_ISOC  && !priv_ep->dir) {
-			control |= TRB_IOC | TRB_ISP;
+			control |= ioc | TRB_ISP;
 		} else {
 			/* for last element in TD or in SG list */
 			if (sg_iter == (num_trb - 1) && sg_iter != 0)
-				control |= pcs | TRB_IOC | TRB_ISP;
+				control |= pcs | ioc | TRB_ISP;
 		}
 
 		if (sg_iter)
@@ -1250,7 +1304,7 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep,
 		if (sg_supported) {
 			trb->control |= cpu_to_le32(TRB_ISP);
 			/* Don't set chain bit for last TRB */
-			if (sg_iter < num_trb - 1)
+			if ((sg_iter % num_trb_req) < num_trb_req - 1)
 				trb->control |= cpu_to_le32(TRB_CHAIN);
 
 			s = sg_next(s);
@@ -1270,7 +1324,7 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep,
 	priv_req->num_of_trb = num_trb;
 
 	if (sg_iter == 1)
-		trb->control |= cpu_to_le32(TRB_IOC | TRB_ISP);
+		trb->control |= cpu_to_le32(ioc | TRB_ISP);
 
 	if (priv_dev->dev_ver < DEV_VER_V2 &&
 	    (priv_ep->flags & EP_TDLCHK_EN)) {
@@ -1508,6 +1562,12 @@ static void cdns3_transfer_completed(struct cdns3_device *priv_dev,
 
 		/* The TRB was changed as link TRB, and the request was handled at ep_dequeue */
 		while (TRB_FIELD_TO_TYPE(le32_to_cpu(trb->control)) == TRB_LINK) {
+
+			/* ISO ep_traddr may stop at LINK TRB */
+			if (priv_ep->dequeue == cdns3_get_dma_pos(priv_dev, priv_ep) &&
+			    priv_ep->type == USB_ENDPOINT_XFER_ISOC)
+				break;
+
 			trace_cdns3_complete_trb(priv_ep, trb);
 			cdns3_ep_inc_deq(priv_ep);
 			trb = priv_ep->trb_pool + priv_ep->dequeue;
@@ -1540,6 +1600,10 @@ static void cdns3_transfer_completed(struct cdns3_device *priv_dev,
 			}
 
 			if (request_handled) {
+				/* TRBs are duplicated by priv_ep->interval time for ISO IN */
+				if (priv_ep->type == USB_ENDPOINT_XFER_ISOC && priv_ep->dir)
+					request->actual /= priv_ep->interval;
+
 				cdns3_gadget_giveback(priv_ep, priv_req, 0);
 				request_handled = false;
 				transfer_end = false;
@@ -2035,11 +2099,10 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable)
 	bool is_iso_ep = (priv_ep->type == USB_ENDPOINT_XFER_ISOC);
 	struct cdns3_device *priv_dev = priv_ep->cdns3_dev;
 	u32 bEndpointAddress = priv_ep->num | priv_ep->dir;
-	u32 max_packet_size = 0;
-	u8 maxburst = 0;
+	u32 max_packet_size = priv_ep->wMaxPacketSize;
+	u8 maxburst = priv_ep->bMaxBurst;
 	u32 ep_cfg = 0;
 	u8 buffering;
-	u8 mult = 0;
 	int ret;
 
 	buffering = priv_dev->ep_buf_size - 1;
@@ -2061,8 +2124,7 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable)
 		break;
 	default:
 		ep_cfg = EP_CFG_EPTYPE(USB_ENDPOINT_XFER_ISOC);
-		mult = priv_dev->ep_iso_burst - 1;
-		buffering = mult + 1;
+		buffering = (priv_ep->bMaxBurst + 1) * (priv_ep->mult + 1) - 1;
 	}
 
 	switch (priv_dev->gadget.speed) {
@@ -2073,17 +2135,8 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable)
 		max_packet_size = is_iso_ep ? 1024 : 512;
 		break;
 	case USB_SPEED_SUPER:
-		/* It's limitation that driver assumes in driver. */
-		mult = 0;
-		max_packet_size = 1024;
-		if (priv_ep->type == USB_ENDPOINT_XFER_ISOC) {
-			maxburst = priv_dev->ep_iso_burst - 1;
-			buffering = (mult + 1) *
-				    (maxburst + 1);
-
-			if (priv_ep->interval > 1)
-				buffering++;
-		} else {
+		if (priv_ep->type != USB_ENDPOINT_XFER_ISOC) {
+			max_packet_size = 1024;
 			maxburst = priv_dev->ep_buf_size - 1;
 		}
 		break;
@@ -2112,7 +2165,6 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable)
 	if (priv_dev->dev_ver < DEV_VER_V2)
 		priv_ep->trb_burst_size = 16;
 
-	mult = min_t(u8, mult, EP_CFG_MULT_MAX);
 	buffering = min_t(u8, buffering, EP_CFG_BUFFERING_MAX);
 	maxburst = min_t(u8, maxburst, EP_CFG_MAXBURST_MAX);
 
@@ -2146,7 +2198,7 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable)
 	}
 
 	ep_cfg |= EP_CFG_MAXPKTSIZE(max_packet_size) |
-		  EP_CFG_MULT(mult) |
+		  EP_CFG_MULT(priv_ep->mult) |			/* must match EP setting */
 		  EP_CFG_BUFFERING(buffering) |
 		  EP_CFG_MAXBURST(maxburst);
 
@@ -2236,6 +2288,13 @@ usb_ep *cdns3_gadget_match_ep(struct usb_gadget *gadget,
 	priv_ep->type = usb_endpoint_type(desc);
 	priv_ep->flags |= EP_CLAIMED;
 	priv_ep->interval = desc->bInterval ? BIT(desc->bInterval - 1) : 0;
+	priv_ep->wMaxPacketSize =  usb_endpoint_maxp(desc);
+	priv_ep->mult = USB_EP_MAXP_MULT(priv_ep->wMaxPacketSize);
+	priv_ep->wMaxPacketSize &= USB_ENDPOINT_MAXP_MASK;
+	if (priv_ep->type == USB_ENDPOINT_XFER_ISOC && comp_desc) {
+		priv_ep->mult =  USB_SS_MULT(comp_desc->bmAttributes) - 1;
+		priv_ep->bMaxBurst = comp_desc->bMaxBurst;
+	}
 
 	spin_unlock_irqrestore(&priv_dev->lock, flags);
 	return &priv_ep->endpoint;
@@ -2485,11 +2544,11 @@ static int cdns3_gadget_ep_disable(struct usb_ep *ep)
 
 	while (!list_empty(&priv_ep->wa2_descmiss_req_list)) {
 		priv_req = cdns3_next_priv_request(&priv_ep->wa2_descmiss_req_list);
+		list_del_init(&priv_req->list);
 
 		kfree(priv_req->request.buf);
 		cdns3_gadget_ep_free_request(&priv_ep->endpoint,
 					     &priv_req->request);
-		list_del_init(&priv_req->list);
 		--priv_ep->wa2_counter;
 	}
 
@@ -3019,22 +3078,40 @@ static int cdns3_gadget_check_config(struct usb_gadget *gadget)
 	struct cdns3_endpoint *priv_ep;
 	struct usb_ep *ep;
 	int n_in = 0;
+	int iso = 0;
+	int out = 1;
 	int total;
+	int n;
 
 	list_for_each_entry(ep, &gadget->ep_list, ep_list) {
 		priv_ep = ep_to_cdns3_ep(ep);
-		if ((priv_ep->flags & EP_CLAIMED) && (ep->address & USB_DIR_IN))
-			n_in++;
+		if (!(priv_ep->flags & EP_CLAIMED))
+			continue;
+
+		n = (priv_ep->mult + 1) * (priv_ep->bMaxBurst + 1);
+		if (ep->address & USB_DIR_IN) {
+			/*
+			 * ISO transfer: DMA start move data when get ISO, only transfer
+			 * data as min(TD size, iso). No benefit for allocate bigger
+			 * internal memory than 'iso'.
+			 */
+			if (priv_ep->type == USB_ENDPOINT_XFER_ISOC)
+				iso += n;
+			else
+				n_in++;
+		} else {
+			if (priv_ep->type == USB_ENDPOINT_XFER_ISOC)
+				out = max_t(int, out, n);
+		}
 	}
 
 	/* 2KB are reserved for EP0, 1KB for out*/
-	total = 2 + n_in + 1;
+	total = 2 + n_in + out + iso;
 
 	if (total > priv_dev->onchip_buffers)
 		return -ENOMEM;
 
-	priv_dev->ep_buf_size = priv_dev->ep_iso_burst =
-			(priv_dev->onchip_buffers - 2) / (n_in + 1);
+	priv_dev->ep_buf_size = (priv_dev->onchip_buffers - 2 - iso) / (n_in + out);
 
 	return 0;
 }
diff --git a/drivers/usb/cdns3/cdns3-gadget.h b/drivers/usb/cdns3/cdns3-gadget.h
index fbe4a8e3aa89..086a7bb83897 100644
--- a/drivers/usb/cdns3/cdns3-gadget.h
+++ b/drivers/usb/cdns3/cdns3-gadget.h
@@ -1168,6 +1168,9 @@ struct cdns3_endpoint {
 	u8			dir;
 	u8			num;
 	u8			type;
+	u8			mult;
+	u8			bMaxBurst;
+	u16			wMaxPacketSize;
 	int			interval;
 
 	int			free_trbs;
diff --git a/drivers/usb/cdns3/cdns3-plat.c b/drivers/usb/cdns3/cdns3-plat.c
index 2c1aca84f226..3ef8e3c872a3 100644
--- a/drivers/usb/cdns3/cdns3-plat.c
+++ b/drivers/usb/cdns3/cdns3-plat.c
@@ -87,16 +87,20 @@ static int cdns3_plat_probe(struct platform_device *pdev)
 	cdns->dev_irq = platform_get_irq_byname(pdev, "peripheral");
 
 	if (cdns->dev_irq < 0)
-		return cdns->dev_irq;
+		return dev_err_probe(dev, cdns->dev_irq,
+				     "Failed to get peripheral IRQ\n");
 
 	regs = devm_platform_ioremap_resource_byname(pdev, "dev");
 	if (IS_ERR(regs))
-		return PTR_ERR(regs);
+		return dev_err_probe(dev, PTR_ERR(regs),
+				     "Failed to get dev base\n");
+
 	cdns->dev_regs	= regs;
 
 	cdns->otg_irq = platform_get_irq_byname(pdev, "otg");
 	if (cdns->otg_irq < 0)
-		return cdns->otg_irq;
+		return dev_err_probe(dev, cdns->otg_irq,
+				     "Failed to get otg IRQ\n");
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "otg");
 	if (!res) {
@@ -119,7 +123,8 @@ static int cdns3_plat_probe(struct platform_device *pdev)
 
 	cdns->usb2_phy = devm_phy_optional_get(dev, "cdns3,usb2-phy");
 	if (IS_ERR(cdns->usb2_phy))
-		return PTR_ERR(cdns->usb2_phy);
+		return dev_err_probe(dev, PTR_ERR(cdns->usb2_phy),
+				     "Failed to get cdn3,usb2-phy\n");
 
 	ret = phy_init(cdns->usb2_phy);
 	if (ret)
@@ -127,7 +132,8 @@ static int cdns3_plat_probe(struct platform_device *pdev)
 
 	cdns->usb3_phy = devm_phy_optional_get(dev, "cdns3,usb3-phy");
 	if (IS_ERR(cdns->usb3_phy))
-		return PTR_ERR(cdns->usb3_phy);
+		return dev_err_probe(dev, PTR_ERR(cdns->usb3_phy),
+				     "Failed to get cdn3,usb3-phy\n");
 
 	ret = phy_init(cdns->usb3_phy);
 	if (ret)
diff --git a/drivers/usb/cdns3/cdns3-starfive.c b/drivers/usb/cdns3/cdns3-starfive.c
index a7265b86e427..c04d196abd87 100644
--- a/drivers/usb/cdns3/cdns3-starfive.c
+++ b/drivers/usb/cdns3/cdns3-starfive.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/**
+/*
  * cdns3-starfive.c - StarFive specific Glue layer for Cadence USB Controller
  *
  * Copyright (C) 2023 StarFive Technology Co., Ltd.
diff --git a/drivers/usb/cdns3/cdnsp-debug.h b/drivers/usb/cdns3/cdnsp-debug.h
index ad617b7455b9..cd138acdcce1 100644
--- a/drivers/usb/cdns3/cdnsp-debug.h
+++ b/drivers/usb/cdns3/cdnsp-debug.h
@@ -187,202 +187,202 @@ static inline const char *cdnsp_decode_trb(char *str, size_t size, u32 field0,
 
 	switch (type) {
 	case TRB_LINK:
-		ret = snprintf(str, size,
-			       "LINK %08x%08x intr %ld type '%s' flags %c:%c:%c:%c",
-			       field1, field0, GET_INTR_TARGET(field2),
-			       cdnsp_trb_type_string(type),
-			       field3 & TRB_IOC ? 'I' : 'i',
-			       field3 & TRB_CHAIN ? 'C' : 'c',
-			       field3 & TRB_TC ? 'T' : 't',
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"LINK %08x%08x intr %ld type '%s' flags %c:%c:%c:%c",
+				field1, field0, GET_INTR_TARGET(field2),
+				cdnsp_trb_type_string(type),
+				field3 & TRB_IOC ? 'I' : 'i',
+				field3 & TRB_CHAIN ? 'C' : 'c',
+				field3 & TRB_TC ? 'T' : 't',
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_TRANSFER:
 	case TRB_COMPLETION:
 	case TRB_PORT_STATUS:
 	case TRB_HC_EVENT:
-		ret = snprintf(str, size,
-			       "ep%d%s(%d) type '%s' TRB %08x%08x status '%s'"
-			       " len %ld slot %ld flags %c:%c",
-			       ep_num, ep_id % 2 ? "out" : "in",
-			       TRB_TO_EP_INDEX(field3),
-			       cdnsp_trb_type_string(type), field1, field0,
-			       cdnsp_trb_comp_code_string(GET_COMP_CODE(field2)),
-			       EVENT_TRB_LEN(field2), TRB_TO_SLOT_ID(field3),
-			       field3 & EVENT_DATA ? 'E' : 'e',
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"ep%d%s(%d) type '%s' TRB %08x%08x status '%s'"
+				" len %ld slot %ld flags %c:%c",
+				ep_num, ep_id % 2 ? "out" : "in",
+				TRB_TO_EP_INDEX(field3),
+				cdnsp_trb_type_string(type), field1, field0,
+				cdnsp_trb_comp_code_string(GET_COMP_CODE(field2)),
+				EVENT_TRB_LEN(field2), TRB_TO_SLOT_ID(field3),
+				field3 & EVENT_DATA ? 'E' : 'e',
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_MFINDEX_WRAP:
-		ret = snprintf(str, size, "%s: flags %c",
-			       cdnsp_trb_type_string(type),
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size, "%s: flags %c",
+				cdnsp_trb_type_string(type),
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_SETUP:
-		ret = snprintf(str, size,
-			       "type '%s' bRequestType %02x bRequest %02x "
-			       "wValue %02x%02x wIndex %02x%02x wLength %d "
-			       "length %ld TD size %ld intr %ld Setup ID %ld "
-			       "flags %c:%c:%c",
-			       cdnsp_trb_type_string(type),
-			       field0 & 0xff,
-			       (field0 & 0xff00) >> 8,
-			       (field0 & 0xff000000) >> 24,
-			       (field0 & 0xff0000) >> 16,
-			       (field1 & 0xff00) >> 8,
-			       field1 & 0xff,
-			       (field1 & 0xff000000) >> 16 |
-			       (field1 & 0xff0000) >> 16,
-			       TRB_LEN(field2), GET_TD_SIZE(field2),
-			       GET_INTR_TARGET(field2),
-			       TRB_SETUPID_TO_TYPE(field3),
-			       field3 & TRB_IDT ? 'D' : 'd',
-			       field3 & TRB_IOC ? 'I' : 'i',
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"type '%s' bRequestType %02x bRequest %02x "
+				"wValue %02x%02x wIndex %02x%02x wLength %d "
+				"length %ld TD size %ld intr %ld Setup ID %ld "
+				"flags %c:%c:%c",
+				cdnsp_trb_type_string(type),
+				field0 & 0xff,
+				(field0 & 0xff00) >> 8,
+				(field0 & 0xff000000) >> 24,
+				(field0 & 0xff0000) >> 16,
+				(field1 & 0xff00) >> 8,
+				field1 & 0xff,
+				(field1 & 0xff000000) >> 16 |
+				(field1 & 0xff0000) >> 16,
+				TRB_LEN(field2), GET_TD_SIZE(field2),
+				GET_INTR_TARGET(field2),
+				TRB_SETUPID_TO_TYPE(field3),
+				field3 & TRB_IDT ? 'D' : 'd',
+				field3 & TRB_IOC ? 'I' : 'i',
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_DATA:
-		ret = snprintf(str, size,
-			       "type '%s' Buffer %08x%08x length %ld TD size %ld "
-			       "intr %ld flags %c:%c:%c:%c:%c:%c:%c",
-			       cdnsp_trb_type_string(type),
-			       field1, field0, TRB_LEN(field2),
-			       GET_TD_SIZE(field2),
-			       GET_INTR_TARGET(field2),
-			       field3 & TRB_IDT ? 'D' : 'i',
-			       field3 & TRB_IOC ? 'I' : 'i',
-			       field3 & TRB_CHAIN ? 'C' : 'c',
-			       field3 & TRB_NO_SNOOP ? 'S' : 's',
-			       field3 & TRB_ISP ? 'I' : 'i',
-			       field3 & TRB_ENT ? 'E' : 'e',
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"type '%s' Buffer %08x%08x length %ld TD size %ld "
+				"intr %ld flags %c:%c:%c:%c:%c:%c:%c",
+				cdnsp_trb_type_string(type),
+				field1, field0, TRB_LEN(field2),
+				GET_TD_SIZE(field2),
+				GET_INTR_TARGET(field2),
+				field3 & TRB_IDT ? 'D' : 'i',
+				field3 & TRB_IOC ? 'I' : 'i',
+				field3 & TRB_CHAIN ? 'C' : 'c',
+				field3 & TRB_NO_SNOOP ? 'S' : 's',
+				field3 & TRB_ISP ? 'I' : 'i',
+				field3 & TRB_ENT ? 'E' : 'e',
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_STATUS:
-		ret = snprintf(str, size,
-			       "Buffer %08x%08x length %ld TD size %ld intr"
-			       "%ld type '%s' flags %c:%c:%c:%c",
-			       field1, field0, TRB_LEN(field2),
-			       GET_TD_SIZE(field2),
-			       GET_INTR_TARGET(field2),
-			       cdnsp_trb_type_string(type),
-			       field3 & TRB_IOC ? 'I' : 'i',
-			       field3 & TRB_CHAIN ? 'C' : 'c',
-			       field3 & TRB_ENT ? 'E' : 'e',
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"Buffer %08x%08x length %ld TD size %ld intr"
+				"%ld type '%s' flags %c:%c:%c:%c",
+				field1, field0, TRB_LEN(field2),
+				GET_TD_SIZE(field2),
+				GET_INTR_TARGET(field2),
+				cdnsp_trb_type_string(type),
+				field3 & TRB_IOC ? 'I' : 'i',
+				field3 & TRB_CHAIN ? 'C' : 'c',
+				field3 & TRB_ENT ? 'E' : 'e',
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_NORMAL:
 	case TRB_ISOC:
 	case TRB_EVENT_DATA:
 	case TRB_TR_NOOP:
-		ret = snprintf(str, size,
-			       "type '%s' Buffer %08x%08x length %ld "
-			       "TD size %ld intr %ld "
-			       "flags %c:%c:%c:%c:%c:%c:%c:%c:%c",
-			       cdnsp_trb_type_string(type),
-			       field1, field0, TRB_LEN(field2),
-			       GET_TD_SIZE(field2),
-			       GET_INTR_TARGET(field2),
-			       field3 & TRB_BEI ? 'B' : 'b',
-			       field3 & TRB_IDT ? 'T' : 't',
-			       field3 & TRB_IOC ? 'I' : 'i',
-			       field3 & TRB_CHAIN ? 'C' : 'c',
-			       field3 & TRB_NO_SNOOP ? 'S' : 's',
-			       field3 & TRB_ISP ? 'I' : 'i',
-			       field3 & TRB_ENT ? 'E' : 'e',
-			       field3 & TRB_CYCLE ? 'C' : 'c',
-			       !(field3 & TRB_EVENT_INVALIDATE) ? 'V' : 'v');
+		ret = scnprintf(str, size,
+				"type '%s' Buffer %08x%08x length %ld "
+				"TD size %ld intr %ld "
+				"flags %c:%c:%c:%c:%c:%c:%c:%c:%c",
+				cdnsp_trb_type_string(type),
+				field1, field0, TRB_LEN(field2),
+				GET_TD_SIZE(field2),
+				GET_INTR_TARGET(field2),
+				field3 & TRB_BEI ? 'B' : 'b',
+				field3 & TRB_IDT ? 'T' : 't',
+				field3 & TRB_IOC ? 'I' : 'i',
+				field3 & TRB_CHAIN ? 'C' : 'c',
+				field3 & TRB_NO_SNOOP ? 'S' : 's',
+				field3 & TRB_ISP ? 'I' : 'i',
+				field3 & TRB_ENT ? 'E' : 'e',
+				field3 & TRB_CYCLE ? 'C' : 'c',
+				!(field3 & TRB_EVENT_INVALIDATE) ? 'V' : 'v');
 		break;
 	case TRB_CMD_NOOP:
 	case TRB_ENABLE_SLOT:
-		ret = snprintf(str, size, "%s: flags %c",
-			       cdnsp_trb_type_string(type),
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size, "%s: flags %c",
+				cdnsp_trb_type_string(type),
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_DISABLE_SLOT:
-		ret = snprintf(str, size, "%s: slot %ld flags %c",
-			       cdnsp_trb_type_string(type),
-			       TRB_TO_SLOT_ID(field3),
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size, "%s: slot %ld flags %c",
+				cdnsp_trb_type_string(type),
+				TRB_TO_SLOT_ID(field3),
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_ADDR_DEV:
-		ret = snprintf(str, size,
-			       "%s: ctx %08x%08x slot %ld flags %c:%c",
-			       cdnsp_trb_type_string(type), field1, field0,
-			       TRB_TO_SLOT_ID(field3),
-			       field3 & TRB_BSR ? 'B' : 'b',
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"%s: ctx %08x%08x slot %ld flags %c:%c",
+				cdnsp_trb_type_string(type), field1, field0,
+				TRB_TO_SLOT_ID(field3),
+				field3 & TRB_BSR ? 'B' : 'b',
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_CONFIG_EP:
-		ret = snprintf(str, size,
-			       "%s: ctx %08x%08x slot %ld flags %c:%c",
-			       cdnsp_trb_type_string(type), field1, field0,
-			       TRB_TO_SLOT_ID(field3),
-			       field3 & TRB_DC ? 'D' : 'd',
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"%s: ctx %08x%08x slot %ld flags %c:%c",
+				cdnsp_trb_type_string(type), field1, field0,
+				TRB_TO_SLOT_ID(field3),
+				field3 & TRB_DC ? 'D' : 'd',
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_EVAL_CONTEXT:
-		ret = snprintf(str, size,
-			       "%s: ctx %08x%08x slot %ld flags %c",
-			       cdnsp_trb_type_string(type), field1, field0,
-			       TRB_TO_SLOT_ID(field3),
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"%s: ctx %08x%08x slot %ld flags %c",
+				cdnsp_trb_type_string(type), field1, field0,
+				TRB_TO_SLOT_ID(field3),
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_RESET_EP:
 	case TRB_HALT_ENDPOINT:
-		ret = snprintf(str, size,
-			       "%s: ep%d%s(%d) ctx %08x%08x slot %ld flags %c",
-			       cdnsp_trb_type_string(type),
-			       ep_num, ep_id % 2 ? "out" : "in",
-			       TRB_TO_EP_INDEX(field3), field1, field0,
-			       TRB_TO_SLOT_ID(field3),
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"%s: ep%d%s(%d) ctx %08x%08x slot %ld flags %c",
+				cdnsp_trb_type_string(type),
+				ep_num, ep_id % 2 ? "out" : "in",
+				TRB_TO_EP_INDEX(field3), field1, field0,
+				TRB_TO_SLOT_ID(field3),
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_STOP_RING:
-		ret = snprintf(str, size,
-			       "%s: ep%d%s(%d) slot %ld sp %d flags %c",
-			       cdnsp_trb_type_string(type),
-			       ep_num, ep_id % 2 ? "out" : "in",
-			       TRB_TO_EP_INDEX(field3),
-			       TRB_TO_SLOT_ID(field3),
-			       TRB_TO_SUSPEND_PORT(field3),
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"%s: ep%d%s(%d) slot %ld sp %d flags %c",
+				cdnsp_trb_type_string(type),
+				ep_num, ep_id % 2 ? "out" : "in",
+				TRB_TO_EP_INDEX(field3),
+				TRB_TO_SLOT_ID(field3),
+				TRB_TO_SUSPEND_PORT(field3),
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_SET_DEQ:
-		ret = snprintf(str, size,
-			       "%s: ep%d%s(%d) deq %08x%08x stream %ld slot %ld  flags %c",
-			       cdnsp_trb_type_string(type),
-			       ep_num, ep_id % 2 ? "out" : "in",
-			       TRB_TO_EP_INDEX(field3), field1, field0,
-			       TRB_TO_STREAM_ID(field2),
-			       TRB_TO_SLOT_ID(field3),
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"%s: ep%d%s(%d) deq %08x%08x stream %ld slot %ld  flags %c",
+				cdnsp_trb_type_string(type),
+				ep_num, ep_id % 2 ? "out" : "in",
+				TRB_TO_EP_INDEX(field3), field1, field0,
+				TRB_TO_STREAM_ID(field2),
+				TRB_TO_SLOT_ID(field3),
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_RESET_DEV:
-		ret = snprintf(str, size, "%s: slot %ld flags %c",
-			       cdnsp_trb_type_string(type),
-			       TRB_TO_SLOT_ID(field3),
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size, "%s: slot %ld flags %c",
+				cdnsp_trb_type_string(type),
+				TRB_TO_SLOT_ID(field3),
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_ENDPOINT_NRDY:
 		temp = TRB_TO_HOST_STREAM(field2);
 
-		ret = snprintf(str, size,
-			       "%s: ep%d%s(%d) H_SID %x%s%s D_SID %lx flags %c:%c",
-			       cdnsp_trb_type_string(type),
-			       ep_num, ep_id % 2 ? "out" : "in",
-			       TRB_TO_EP_INDEX(field3), temp,
-			       temp == STREAM_PRIME_ACK ? "(PRIME)" : "",
-			       temp == STREAM_REJECTED ? "(REJECTED)" : "",
-			       TRB_TO_DEV_STREAM(field0),
-			       field3 & TRB_STAT ? 'S' : 's',
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"%s: ep%d%s(%d) H_SID %x%s%s D_SID %lx flags %c:%c",
+				cdnsp_trb_type_string(type),
+				ep_num, ep_id % 2 ? "out" : "in",
+				TRB_TO_EP_INDEX(field3), temp,
+				temp == STREAM_PRIME_ACK ? "(PRIME)" : "",
+				temp == STREAM_REJECTED ? "(REJECTED)" : "",
+				TRB_TO_DEV_STREAM(field0),
+				field3 & TRB_STAT ? 'S' : 's',
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	default:
-		ret = snprintf(str, size,
-			       "type '%s' -> raw %08x %08x %08x %08x",
-			       cdnsp_trb_type_string(type),
-			       field0, field1, field2, field3);
+		ret = scnprintf(str, size,
+				"type '%s' -> raw %08x %08x %08x %08x",
+				cdnsp_trb_type_string(type),
+				field0, field1, field2, field3);
 	}
 
-	if (ret >= size)
-		pr_info("CDNSP: buffer overflowed.\n");
+	if (ret == size - 1)
+		pr_info("CDNSP: buffer may be truncated.\n");
 
 	return str;
 }
@@ -465,32 +465,32 @@ static inline const char *cdnsp_decode_portsc(char *str, size_t size,
 {
 	int ret;
 
-	ret = snprintf(str, size, "%s %s %s Link:%s PortSpeed:%d ",
-		       portsc & PORT_POWER ? "Powered" : "Powered-off",
-		       portsc & PORT_CONNECT ? "Connected" : "Not-connected",
-		       portsc & PORT_PED ? "Enabled" : "Disabled",
-		       cdnsp_portsc_link_state_string(portsc),
-		       DEV_PORT_SPEED(portsc));
+	ret = scnprintf(str, size, "%s %s %s Link:%s PortSpeed:%d ",
+			portsc & PORT_POWER ? "Powered" : "Powered-off",
+			portsc & PORT_CONNECT ? "Connected" : "Not-connected",
+			portsc & PORT_PED ? "Enabled" : "Disabled",
+			cdnsp_portsc_link_state_string(portsc),
+			DEV_PORT_SPEED(portsc));
 
 	if (portsc & PORT_RESET)
-		ret += snprintf(str + ret, size - ret, "In-Reset ");
+		ret += scnprintf(str + ret, size - ret, "In-Reset ");
 
-	ret += snprintf(str + ret, size - ret, "Change: ");
+	ret += scnprintf(str + ret, size - ret, "Change: ");
 	if (portsc & PORT_CSC)
-		ret += snprintf(str + ret, size - ret, "CSC ");
+		ret += scnprintf(str + ret, size - ret, "CSC ");
 	if (portsc & PORT_WRC)
-		ret += snprintf(str + ret, size - ret, "WRC ");
+		ret += scnprintf(str + ret, size - ret, "WRC ");
 	if (portsc & PORT_RC)
-		ret += snprintf(str + ret, size - ret, "PRC ");
+		ret += scnprintf(str + ret, size - ret, "PRC ");
 	if (portsc & PORT_PLC)
-		ret += snprintf(str + ret, size - ret, "PLC ");
+		ret += scnprintf(str + ret, size - ret, "PLC ");
 	if (portsc & PORT_CEC)
-		ret += snprintf(str + ret, size - ret, "CEC ");
-	ret += snprintf(str + ret, size - ret, "Wake: ");
+		ret += scnprintf(str + ret, size - ret, "CEC ");
+	ret += scnprintf(str + ret, size - ret, "Wake: ");
 	if (portsc & PORT_WKCONN_E)
-		ret += snprintf(str + ret, size - ret, "WCE ");
+		ret += scnprintf(str + ret, size - ret, "WCE ");
 	if (portsc & PORT_WKDISC_E)
-		ret += snprintf(str + ret, size - ret, "WDE ");
+		ret += scnprintf(str + ret, size - ret, "WDE ");
 
 	return str;
 }
@@ -562,20 +562,20 @@ static inline const char *cdnsp_decode_ep_context(char *str, size_t size,
 
 	avg = EP_AVG_TRB_LENGTH(tx_info);
 
-	ret = snprintf(str, size, "State %s mult %d max P. Streams %d %s",
-		       cdnsp_ep_state_string(ep_state), mult,
-		       max_pstr, lsa ? "LSA " : "");
+	ret = scnprintf(str, size, "State %s mult %d max P. Streams %d %s",
+			cdnsp_ep_state_string(ep_state), mult,
+			max_pstr, lsa ? "LSA " : "");
 
-	ret += snprintf(str + ret, size - ret,
-			"interval %d us max ESIT payload %d CErr %d ",
-			(1 << interval) * 125, esit, cerr);
+	ret += scnprintf(str + ret, size - ret,
+			 "interval %d us max ESIT payload %d CErr %d ",
+			 (1 << interval) * 125, esit, cerr);
 
-	ret += snprintf(str + ret, size - ret,
-			"Type %s %sburst %d maxp %d deq %016llx ",
-			cdnsp_ep_type_string(ep_type), hid ? "HID" : "",
-			burst, maxp, deq);
+	ret += scnprintf(str + ret, size - ret,
+			 "Type %s %sburst %d maxp %d deq %016llx ",
+			 cdnsp_ep_type_string(ep_type), hid ? "HID" : "",
+			 burst, maxp, deq);
 
-	ret += snprintf(str + ret, size - ret, "avg trb len %d", avg);
+	ret += scnprintf(str + ret, size - ret, "avg trb len %d", avg);
 
 	return str;
 }
diff --git a/drivers/usb/cdns3/core.c b/drivers/usb/cdns3/core.c
index 33548771a0d3..465e9267b49c 100644
--- a/drivers/usb/cdns3/core.c
+++ b/drivers/usb/cdns3/core.c
@@ -395,7 +395,6 @@ pm_put:
 	return ret;
 }
 
-
 /**
  * cdns_wakeup_irq - interrupt handler for wakeup events
  * @irq: irq number for cdns3/cdnsp core device
diff --git a/drivers/usb/cdns3/drd.c b/drivers/usb/cdns3/drd.c
index 04b6d12f2b9a..ee917f1b091c 100644
--- a/drivers/usb/cdns3/drd.c
+++ b/drivers/usb/cdns3/drd.c
@@ -156,7 +156,8 @@ bool cdns_is_device(struct cdns *cdns)
  */
 static void cdns_otg_disable_irq(struct cdns *cdns)
 {
-	writel(0, &cdns->otg_irq_regs->ien);
+	if (cdns->version)
+		writel(0, &cdns->otg_irq_regs->ien);
 }
 
 /**
@@ -422,15 +423,20 @@ int cdns_drd_init(struct cdns *cdns)
 
 		cdns->otg_regs = (void __iomem *)&cdns->otg_v1_regs->cmd;
 
-		if (readl(&cdns->otg_cdnsp_regs->did) == OTG_CDNSP_DID) {
+		state = readl(&cdns->otg_cdnsp_regs->did);
+
+		if (OTG_CDNSP_CHECK_DID(state)) {
 			cdns->otg_irq_regs = (struct cdns_otg_irq_regs __iomem *)
 					      &cdns->otg_cdnsp_regs->ien;
 			cdns->version  = CDNSP_CONTROLLER_V2;
-		} else {
+		} else if (OTG_CDNS3_CHECK_DID(state)) {
 			cdns->otg_irq_regs = (struct cdns_otg_irq_regs __iomem *)
 					      &cdns->otg_v1_regs->ien;
 			writel(1, &cdns->otg_v1_regs->simulate);
 			cdns->version  = CDNS3_CONTROLLER_V1;
+		} else {
+			dev_err(cdns->dev, "not supporte DID=0x%08x\n", state);
+			return -EINVAL;
 		}
 
 		dev_dbg(cdns->dev, "DRD version v1 (ID: %08x, rev: %08x)\n",
@@ -483,7 +489,6 @@ int cdns_drd_exit(struct cdns *cdns)
 	return 0;
 }
 
-
 /* Indicate the cdns3 core was power lost before */
 bool cdns_power_is_lost(struct cdns *cdns)
 {
diff --git a/drivers/usb/cdns3/drd.h b/drivers/usb/cdns3/drd.h
index cbdf94f73ed9..d72370c321d3 100644
--- a/drivers/usb/cdns3/drd.h
+++ b/drivers/usb/cdns3/drd.h
@@ -79,7 +79,11 @@ struct cdnsp_otg_regs {
 	__le32 susp_timing_ctrl;
 };
 
-#define OTG_CDNSP_DID	0x0004034E
+/* CDNSP driver supports 0x000403xx Cadence USB controller family. */
+#define OTG_CDNSP_CHECK_DID(did) (((did) & GENMASK(31, 8)) == 0x00040300)
+
+/* CDNS3 driver supports 0x000402xx Cadence USB controller family. */
+#define OTG_CDNS3_CHECK_DID(did) (((did) & GENMASK(31, 8)) == 0x00040200)
 
 /*
  * Common registers interface for both CDNS3 and CDNSP version of DRD.
diff --git a/drivers/usb/cdns3/host.c b/drivers/usb/cdns3/host.c
index 6164fc4c96a4..ceca4d839dfd 100644
--- a/drivers/usb/cdns3/host.c
+++ b/drivers/usb/cdns3/host.c
@@ -18,6 +18,11 @@
 #include "../host/xhci.h"
 #include "../host/xhci-plat.h"
 
+/*
+ * The XECP_PORT_CAP_REG and XECP_AUX_CTRL_REG1 exist only
+ * in Cadence USB3 dual-role controller, so it can't be used
+ * with Cadence CDNSP dual-role controller.
+ */
 #define XECP_PORT_CAP_REG	0x8000
 #define XECP_AUX_CTRL_REG1	0x8120
 
@@ -57,6 +62,8 @@ static const struct xhci_plat_priv xhci_plat_cdns3_xhci = {
 	.resume_quirk = xhci_cdns3_resume_quirk,
 };
 
+static const struct xhci_plat_priv xhci_plat_cdnsp_xhci;
+
 static int __cdns_host_init(struct cdns *cdns)
 {
 	struct platform_device *xhci;
@@ -81,8 +88,13 @@ static int __cdns_host_init(struct cdns *cdns)
 		goto err1;
 	}
 
-	cdns->xhci_plat_data = kmemdup(&xhci_plat_cdns3_xhci,
-			sizeof(struct xhci_plat_priv), GFP_KERNEL);
+	if (cdns->version < CDNSP_CONTROLLER_V2)
+		cdns->xhci_plat_data = kmemdup(&xhci_plat_cdns3_xhci,
+				sizeof(struct xhci_plat_priv), GFP_KERNEL);
+	else
+		cdns->xhci_plat_data = kmemdup(&xhci_plat_cdnsp_xhci,
+				sizeof(struct xhci_plat_priv), GFP_KERNEL);
+
 	if (!cdns->xhci_plat_data) {
 		ret = -ENOMEM;
 		goto err1;
diff --git a/drivers/usb/chipidea/ci.h b/drivers/usb/chipidea/ci.h
index d9bb3d3f026e..2a38e1eb6546 100644
--- a/drivers/usb/chipidea/ci.h
+++ b/drivers/usb/chipidea/ci.h
@@ -176,6 +176,7 @@ struct hw_bank {
  * @enabled_otg_timer_bits: bits of enabled otg timers
  * @next_otg_timer: next nearest enabled timer to be expired
  * @work: work for role changing
+ * @power_lost_work: work for power lost handling
  * @wq: workqueue thread
  * @qh_pool: allocation pool for queue heads
  * @td_pool: allocation pool for transfer descriptors
@@ -226,6 +227,7 @@ struct ci_hdrc {
 	enum otg_fsm_timer		next_otg_timer;
 	struct usb_role_switch		*role_switch;
 	struct work_struct		work;
+	struct work_struct		power_lost_work;
 	struct workqueue_struct		*wq;
 
 	struct dma_pool			*qh_pool;
diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c
index e28bb2f2612d..ae9a6a17ec6e 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -96,6 +96,7 @@ struct ci_hdrc_imx_data {
 	struct usb_phy *phy;
 	struct platform_device *ci_pdev;
 	struct clk *clk;
+	struct clk *clk_wakeup;
 	struct imx_usbmisc_data *usbmisc_data;
 	bool supports_runtime_pm;
 	bool override_phy_control;
@@ -199,7 +200,7 @@ static int imx_get_clks(struct device *dev)
 
 	data->clk_ipg = devm_clk_get(dev, "ipg");
 	if (IS_ERR(data->clk_ipg)) {
-		/* If the platform only needs one clocks */
+		/* If the platform only needs one primary clock */
 		data->clk = devm_clk_get(dev, NULL);
 		if (IS_ERR(data->clk)) {
 			ret = PTR_ERR(data->clk);
@@ -208,6 +209,13 @@ static int imx_get_clks(struct device *dev)
 				PTR_ERR(data->clk), PTR_ERR(data->clk_ipg));
 			return ret;
 		}
+		/* Get wakeup clock. Not all of the platforms need to
+		 * handle this clock. So make it optional.
+		 */
+		data->clk_wakeup = devm_clk_get_optional(dev, "usb_wakeup_clk");
+		if (IS_ERR(data->clk_wakeup))
+			ret = dev_err_probe(dev, PTR_ERR(data->clk_wakeup),
+					"Failed to get wakeup clk\n");
 		return ret;
 	}
 
@@ -423,6 +431,10 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 	if (ret)
 		goto disable_hsic_regulator;
 
+	ret = clk_prepare_enable(data->clk_wakeup);
+	if (ret)
+		goto err_wakeup_clk;
+
 	data->phy = devm_usb_get_phy_by_phandle(dev, "fsl,usbphy", 0);
 	if (IS_ERR(data->phy)) {
 		ret = PTR_ERR(data->phy);
@@ -504,6 +516,8 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 disable_device:
 	ci_hdrc_remove_device(data->ci_pdev);
 err_clk:
+	clk_disable_unprepare(data->clk_wakeup);
+err_wakeup_clk:
 	imx_disable_unprepare_clks(dev);
 disable_hsic_regulator:
 	if (data->hsic_pad_regulator)
@@ -530,6 +544,7 @@ static void ci_hdrc_imx_remove(struct platform_device *pdev)
 		usb_phy_shutdown(data->phy);
 	if (data->ci_pdev) {
 		imx_disable_unprepare_clks(&pdev->dev);
+		clk_disable_unprepare(data->clk_wakeup);
 		if (data->plat_data->flags & CI_HDRC_PMQOS)
 			cpu_latency_qos_remove_request(&data->pm_qos_req);
 		if (data->hsic_pad_regulator)
diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c
index 7ac39a281b8c..835bf2428dc6 100644
--- a/drivers/usb/chipidea/core.c
+++ b/drivers/usb/chipidea/core.c
@@ -523,6 +523,13 @@ static irqreturn_t ci_irq_handler(int irq, void *data)
 	u32 otgsc = 0;
 
 	if (ci->in_lpm) {
+		/*
+		 * If we already have a wakeup irq pending there,
+		 * let's just return to wait resume finished firstly.
+		 */
+		if (ci->wakeup_int)
+			return IRQ_HANDLED;
+
 		disable_irq_nosync(irq);
 		ci->wakeup_int = true;
 		pm_runtime_get(ci->dev);
@@ -849,6 +856,27 @@ static int ci_extcon_register(struct ci_hdrc *ci)
 	return 0;
 }
 
+static void ci_power_lost_work(struct work_struct *work)
+{
+	struct ci_hdrc *ci = container_of(work, struct ci_hdrc, power_lost_work);
+	enum ci_role role;
+
+	disable_irq_nosync(ci->irq);
+	pm_runtime_get_sync(ci->dev);
+	if (!ci_otg_is_fsm_mode(ci)) {
+		role = ci_get_role(ci);
+
+		if (ci->role != role) {
+			ci_handle_id_switch(ci);
+		} else if (role == CI_ROLE_GADGET) {
+			if (ci->is_otg && hw_read_otgsc(ci, OTGSC_BSV))
+				usb_gadget_vbus_connect(&ci->gadget);
+		}
+	}
+	pm_runtime_put_sync(ci->dev);
+	enable_irq(ci->irq);
+}
+
 static DEFINE_IDA(ci_ida);
 
 struct platform_device *ci_hdrc_add_device(struct device *dev,
@@ -862,7 +890,7 @@ struct platform_device *ci_hdrc_add_device(struct device *dev,
 	if (ret)
 		return ERR_PTR(ret);
 
-	id = ida_simple_get(&ci_ida, 0, 0, GFP_KERNEL);
+	id = ida_alloc(&ci_ida, GFP_KERNEL);
 	if (id < 0)
 		return ERR_PTR(id);
 
@@ -892,7 +920,7 @@ struct platform_device *ci_hdrc_add_device(struct device *dev,
 err:
 	platform_device_put(pdev);
 put_id:
-	ida_simple_remove(&ci_ida, id);
+	ida_free(&ci_ida, id);
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(ci_hdrc_add_device);
@@ -901,7 +929,7 @@ void ci_hdrc_remove_device(struct platform_device *pdev)
 {
 	int id = pdev->id;
 	platform_device_unregister(pdev);
-	ida_simple_remove(&ci_ida, id);
+	ida_free(&ci_ida, id);
 }
 EXPORT_SYMBOL_GPL(ci_hdrc_remove_device);
 
@@ -1038,6 +1066,8 @@ static int ci_hdrc_probe(struct platform_device *pdev)
 
 	spin_lock_init(&ci->lock);
 	mutex_init(&ci->mutex);
+	INIT_WORK(&ci->power_lost_work, ci_power_lost_work);
+
 	ci->dev = dev;
 	ci->platdata = dev_get_platdata(dev);
 	ci->imx28_write_fix = !!(ci->platdata->flags &
@@ -1389,25 +1419,6 @@ static int ci_suspend(struct device *dev)
 	return 0;
 }
 
-static void ci_handle_power_lost(struct ci_hdrc *ci)
-{
-	enum ci_role role;
-
-	disable_irq_nosync(ci->irq);
-	if (!ci_otg_is_fsm_mode(ci)) {
-		role = ci_get_role(ci);
-
-		if (ci->role != role) {
-			ci_handle_id_switch(ci);
-		} else if (role == CI_ROLE_GADGET) {
-			if (ci->is_otg && hw_read_otgsc(ci, OTGSC_BSV))
-				usb_gadget_vbus_connect(&ci->gadget);
-		}
-	}
-
-	enable_irq(ci->irq);
-}
-
 static int ci_resume(struct device *dev)
 {
 	struct ci_hdrc *ci = dev_get_drvdata(dev);
@@ -1439,7 +1450,7 @@ static int ci_resume(struct device *dev)
 		ci_role(ci)->resume(ci, power_lost);
 
 	if (power_lost)
-		ci_handle_power_lost(ci);
+		queue_work(system_freezable_wq, &ci->power_lost_work);
 
 	if (ci->supports_runtime_pm) {
 		pm_runtime_disable(dev);
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index 0b7bd3c643c3..2d7f616270c1 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -688,7 +688,8 @@ static int _hardware_dequeue(struct ci_hw_ep *hwep, struct ci_hw_req *hwreq)
 		if ((TD_STATUS_ACTIVE & tmptoken) != 0) {
 			int n = hw_ep_bit(hwep->num, hwep->dir);
 
-			if (ci->rev == CI_REVISION_24)
+			if (ci->rev == CI_REVISION_24 ||
+			    ci->rev == CI_REVISION_22)
 				if (!hw_read(ci, OP_ENDPTSTAT, BIT(n)))
 					reprime_dtd(ci, hwep, node);
 			hwreq->req.status = -EALREADY;
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index a1f4e1ead97f..0e7439dba8fe 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -916,6 +916,9 @@ static int acm_tty_break_ctl(struct tty_struct *tty, int state)
 	struct acm *acm = tty->driver_data;
 	int retval;
 
+	if (!(acm->ctrl_caps & USB_CDC_CAP_BRK))
+		return -EOPNOTSUPP;
+
 	retval = acm_send_break(acm, state ? 0xffff : 0);
 	if (retval < 0)
 		dev_dbg(&acm->control->dev,
diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c
index 84d91b1c1eed..0886b19d2e1c 100644
--- a/drivers/usb/common/ulpi.c
+++ b/drivers/usb/common/ulpi.c
@@ -301,7 +301,7 @@ static int ulpi_register(struct device *dev, struct ulpi *ulpi)
 		return ret;
 	}
 
-	root = debugfs_create_dir(dev_name(dev), ulpi_root);
+	root = debugfs_create_dir(dev_name(&ulpi->dev), ulpi_root);
 	debugfs_create_file("regs", 0444, root, ulpi, &ulpi_regs_fops);
 
 	dev_dbg(&ulpi->dev, "registered ULPI PHY: vendor %04x, product %04x\n",
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index f58a0299fb3b..e01b1913d02b 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -189,13 +189,13 @@ static int usb_create_newid_files(struct usb_driver *usb_drv)
 		goto exit;
 
 	if (usb_drv->probe != NULL) {
-		error = driver_create_file(&usb_drv->drvwrap.driver,
+		error = driver_create_file(&usb_drv->driver,
 					   &driver_attr_new_id);
 		if (error == 0) {
-			error = driver_create_file(&usb_drv->drvwrap.driver,
+			error = driver_create_file(&usb_drv->driver,
 					&driver_attr_remove_id);
 			if (error)
-				driver_remove_file(&usb_drv->drvwrap.driver,
+				driver_remove_file(&usb_drv->driver,
 						&driver_attr_new_id);
 		}
 	}
@@ -209,9 +209,9 @@ static void usb_remove_newid_files(struct usb_driver *usb_drv)
 		return;
 
 	if (usb_drv->probe != NULL) {
-		driver_remove_file(&usb_drv->drvwrap.driver,
+		driver_remove_file(&usb_drv->driver,
 				&driver_attr_remove_id);
-		driver_remove_file(&usb_drv->drvwrap.driver,
+		driver_remove_file(&usb_drv->driver,
 				   &driver_attr_new_id);
 	}
 }
@@ -290,7 +290,10 @@ static int usb_probe_device(struct device *dev)
 	 * specialised device drivers prior to setting the
 	 * use_generic_driver bit.
 	 */
-	error = udriver->probe(udev);
+	if (udriver->probe)
+		error = udriver->probe(udev);
+	else if (!udriver->generic_subclass)
+		error = -EINVAL;
 	if (error == -ENODEV && udriver != &usb_generic_driver &&
 	    (udriver->id_table || udriver->match)) {
 		udev->use_generic_driver = 1;
@@ -549,7 +552,7 @@ int usb_driver_claim_interface(struct usb_driver *driver,
 	if (!iface->authorized)
 		return -ENODEV;
 
-	dev->driver = &driver->drvwrap.driver;
+	dev->driver = &driver->driver;
 	usb_set_intfdata(iface, data);
 	iface->needs_binding = 0;
 
@@ -612,7 +615,7 @@ void usb_driver_release_interface(struct usb_driver *driver,
 	struct device *dev = &iface->dev;
 
 	/* this should never happen, don't release something that's not ours */
-	if (!dev->driver || dev->driver != &driver->drvwrap.driver)
+	if (!dev->driver || dev->driver != &driver->driver)
 		return;
 
 	/* don't release from within disconnect() */
@@ -947,7 +950,7 @@ static int __usb_bus_reprobe_drivers(struct device *dev, void *data)
 	int ret;
 
 	/* Don't reprobe if current driver isn't usb_generic_driver */
-	if (dev->driver != &usb_generic_driver.drvwrap.driver)
+	if (dev->driver != &usb_generic_driver.driver)
 		return 0;
 
 	udev = to_usb_device(dev);
@@ -961,6 +964,11 @@ static int __usb_bus_reprobe_drivers(struct device *dev, void *data)
 	return 0;
 }
 
+bool is_usb_device_driver(const struct device_driver *drv)
+{
+	return drv->probe == usb_probe_device;
+}
+
 /**
  * usb_register_device_driver - register a USB device (not interface) driver
  * @new_udriver: USB operations for the device driver
@@ -980,15 +988,14 @@ int usb_register_device_driver(struct usb_device_driver *new_udriver,
 	if (usb_disabled())
 		return -ENODEV;
 
-	new_udriver->drvwrap.for_devices = 1;
-	new_udriver->drvwrap.driver.name = new_udriver->name;
-	new_udriver->drvwrap.driver.bus = &usb_bus_type;
-	new_udriver->drvwrap.driver.probe = usb_probe_device;
-	new_udriver->drvwrap.driver.remove = usb_unbind_device;
-	new_udriver->drvwrap.driver.owner = owner;
-	new_udriver->drvwrap.driver.dev_groups = new_udriver->dev_groups;
+	new_udriver->driver.name = new_udriver->name;
+	new_udriver->driver.bus = &usb_bus_type;
+	new_udriver->driver.probe = usb_probe_device;
+	new_udriver->driver.remove = usb_unbind_device;
+	new_udriver->driver.owner = owner;
+	new_udriver->driver.dev_groups = new_udriver->dev_groups;
 
-	retval = driver_register(&new_udriver->drvwrap.driver);
+	retval = driver_register(&new_udriver->driver);
 
 	if (!retval) {
 		pr_info("%s: registered new device driver %s\n",
@@ -1020,7 +1027,7 @@ void usb_deregister_device_driver(struct usb_device_driver *udriver)
 	pr_info("%s: deregistering device driver %s\n",
 			usbcore_name, udriver->name);
 
-	driver_unregister(&udriver->drvwrap.driver);
+	driver_unregister(&udriver->driver);
 }
 EXPORT_SYMBOL_GPL(usb_deregister_device_driver);
 
@@ -1048,18 +1055,17 @@ int usb_register_driver(struct usb_driver *new_driver, struct module *owner,
 	if (usb_disabled())
 		return -ENODEV;
 
-	new_driver->drvwrap.for_devices = 0;
-	new_driver->drvwrap.driver.name = new_driver->name;
-	new_driver->drvwrap.driver.bus = &usb_bus_type;
-	new_driver->drvwrap.driver.probe = usb_probe_interface;
-	new_driver->drvwrap.driver.remove = usb_unbind_interface;
-	new_driver->drvwrap.driver.owner = owner;
-	new_driver->drvwrap.driver.mod_name = mod_name;
-	new_driver->drvwrap.driver.dev_groups = new_driver->dev_groups;
+	new_driver->driver.name = new_driver->name;
+	new_driver->driver.bus = &usb_bus_type;
+	new_driver->driver.probe = usb_probe_interface;
+	new_driver->driver.remove = usb_unbind_interface;
+	new_driver->driver.owner = owner;
+	new_driver->driver.mod_name = mod_name;
+	new_driver->driver.dev_groups = new_driver->dev_groups;
 	spin_lock_init(&new_driver->dynids.lock);
 	INIT_LIST_HEAD(&new_driver->dynids.list);
 
-	retval = driver_register(&new_driver->drvwrap.driver);
+	retval = driver_register(&new_driver->driver);
 	if (retval)
 		goto out;
 
@@ -1074,7 +1080,7 @@ out:
 	return retval;
 
 out_newid:
-	driver_unregister(&new_driver->drvwrap.driver);
+	driver_unregister(&new_driver->driver);
 
 	pr_err("%s: error %d registering interface driver %s\n",
 		usbcore_name, retval, new_driver->name);
@@ -1099,7 +1105,7 @@ void usb_deregister(struct usb_driver *driver)
 			usbcore_name, driver->name);
 
 	usb_remove_newid_files(driver);
-	driver_unregister(&driver->drvwrap.driver);
+	driver_unregister(&driver->driver);
 	usb_free_dynids(driver);
 }
 EXPORT_SYMBOL_GPL(usb_deregister);
diff --git a/drivers/usb/core/generic.c b/drivers/usb/core/generic.c
index 740342a2812a..b134bff5c3fe 100644
--- a/drivers/usb/core/generic.c
+++ b/drivers/usb/core/generic.c
@@ -59,10 +59,26 @@ int usb_choose_configuration(struct usb_device *udev)
 	int num_configs;
 	int insufficient_power = 0;
 	struct usb_host_config *c, *best;
+	struct usb_device_driver *udriver;
+
+	/*
+	 * If a USB device (not an interface) doesn't have a driver then the
+	 * kernel has no business trying to select or install a configuration
+	 * for it.
+	 */
+	if (!udev->dev.driver)
+		return -1;
+	udriver = to_usb_device_driver(udev->dev.driver);
 
 	if (usb_device_is_owned(udev))
 		return 0;
 
+	if (udriver->choose_configuration) {
+		i = udriver->choose_configuration(udev);
+		if (i >= 0)
+			return i;
+	}
+
 	best = NULL;
 	c = udev->config;
 	num_configs = udev->descriptor.bNumConfigurations;
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 87480a6e6d93..e38a4124f610 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -47,12 +47,24 @@
 #define USB_VENDOR_TEXAS_INSTRUMENTS		0x0451
 #define USB_PRODUCT_TUSB8041_USB3		0x8140
 #define USB_PRODUCT_TUSB8041_USB2		0x8142
-#define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND	0x01
-#define HUB_QUIRK_DISABLE_AUTOSUSPEND		0x02
+#define USB_VENDOR_MICROCHIP			0x0424
+#define USB_PRODUCT_USB4913			0x4913
+#define USB_PRODUCT_USB4914			0x4914
+#define USB_PRODUCT_USB4915			0x4915
+#define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND	BIT(0)
+#define HUB_QUIRK_DISABLE_AUTOSUSPEND		BIT(1)
+#define HUB_QUIRK_REDUCE_FRAME_INTR_BINTERVAL	BIT(2)
 
 #define USB_TP_TRANSMISSION_DELAY	40	/* ns */
 #define USB_TP_TRANSMISSION_DELAY_MAX	65535	/* ns */
 #define USB_PING_RESPONSE_TIME		400	/* ns */
+#define USB_REDUCE_FRAME_INTR_BINTERVAL	9
+
+/*
+ * The SET_ADDRESS request timeout will be 500 ms when
+ * USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT quirk flag is set.
+ */
+#define USB_SHORT_SET_ADDRESS_REQ_TIMEOUT	500  /* ms */
 
 /* Protect struct usb_device->state and ->children members
  * Note: Both are also protected by ->dev.sem, except that ->state can
@@ -1904,6 +1916,14 @@ static int hub_probe(struct usb_interface *intf, const struct usb_device_id *id)
 		usb_autopm_get_interface_no_resume(intf);
 	}
 
+	if ((id->driver_info & HUB_QUIRK_REDUCE_FRAME_INTR_BINTERVAL) &&
+	    desc->endpoint[0].desc.bInterval > USB_REDUCE_FRAME_INTR_BINTERVAL) {
+		desc->endpoint[0].desc.bInterval =
+			USB_REDUCE_FRAME_INTR_BINTERVAL;
+		/* Tell the HCD about the interrupt ep's new bInterval */
+		usb_set_interface(hdev, 0, 0);
+	}
+
 	if (hub_configure(hub, &desc->endpoint[0].desc) >= 0) {
 		onboard_hub_create_pdevs(hdev, &hub->onboard_hub_devs);
 
@@ -2033,9 +2053,19 @@ static void update_port_device_state(struct usb_device *udev)
 
 	if (udev->parent) {
 		hub = usb_hub_to_struct_hub(udev->parent);
-		port_dev = hub->ports[udev->portnum - 1];
-		WRITE_ONCE(port_dev->state, udev->state);
-		sysfs_notify_dirent(port_dev->state_kn);
+
+		/*
+		 * The Link Layer Validation System Driver (lvstest)
+		 * has a test step to unbind the hub before running the
+		 * rest of the procedure. This triggers hub_disconnect
+		 * which will set the hub's maxchild to 0, further
+		 * resulting in usb_hub_to_struct_hub returning NULL.
+		 */
+		if (hub) {
+			port_dev = hub->ports[udev->portnum - 1];
+			WRITE_ONCE(port_dev->state, udev->state);
+			sysfs_notify_dirent(port_dev->state_kn);
+		}
 	}
 }
 
@@ -2368,17 +2398,25 @@ static int usb_enumerate_device_otg(struct usb_device *udev)
 			}
 		} else if (desc->bLength == sizeof
 				(struct usb_otg_descriptor)) {
-			/* Set a_alt_hnp_support for legacy otg device */
-			err = usb_control_msg(udev,
-				usb_sndctrlpipe(udev, 0),
-				USB_REQ_SET_FEATURE, 0,
-				USB_DEVICE_A_ALT_HNP_SUPPORT,
-				0, NULL, 0,
-				USB_CTRL_SET_TIMEOUT);
-			if (err < 0)
-				dev_err(&udev->dev,
-					"set a_alt_hnp_support failed: %d\n",
-					err);
+			/*
+			 * We are operating on a legacy OTP device
+			 * These should be told that they are operating
+			 * on the wrong port if we have another port that does
+			 * support HNP
+			 */
+			if (bus->otg_port != 0) {
+				/* Set a_alt_hnp_support for legacy otg device */
+				err = usb_control_msg(udev,
+					usb_sndctrlpipe(udev, 0),
+					USB_REQ_SET_FEATURE, 0,
+					USB_DEVICE_A_ALT_HNP_SUPPORT,
+					0, NULL, 0,
+					USB_CTRL_SET_TIMEOUT);
+				if (err < 0)
+					dev_err(&udev->dev,
+						"set a_alt_hnp_support failed: %d\n",
+						err);
+			}
 		}
 	}
 #endif
@@ -4626,7 +4664,12 @@ EXPORT_SYMBOL_GPL(usb_ep0_reinit);
 static int hub_set_address(struct usb_device *udev, int devnum)
 {
 	int retval;
+	unsigned int timeout_ms = USB_CTRL_SET_TIMEOUT;
 	struct usb_hcd *hcd = bus_to_hcd(udev->bus);
+	struct usb_hub *hub = usb_hub_to_struct_hub(udev->parent);
+
+	if (hub->hdev->quirks & USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT)
+		timeout_ms = USB_SHORT_SET_ADDRESS_REQ_TIMEOUT;
 
 	/*
 	 * The host controller will choose the device address,
@@ -4639,11 +4682,11 @@ static int hub_set_address(struct usb_device *udev, int devnum)
 	if (udev->state != USB_STATE_DEFAULT)
 		return -EINVAL;
 	if (hcd->driver->address_device)
-		retval = hcd->driver->address_device(hcd, udev);
+		retval = hcd->driver->address_device(hcd, udev, timeout_ms);
 	else
 		retval = usb_control_msg(udev, usb_sndaddr0pipe(),
 				USB_REQ_SET_ADDRESS, 0, devnum, 0,
-				NULL, 0, USB_CTRL_SET_TIMEOUT);
+				NULL, 0, timeout_ms);
 	if (retval == 0) {
 		update_devnum(udev, devnum);
 		/* Device now using proper address. */
@@ -5895,6 +5938,21 @@ static const struct usb_device_id hub_id_table[] = {
       .idVendor = USB_VENDOR_TEXAS_INSTRUMENTS,
       .idProduct = USB_PRODUCT_TUSB8041_USB3,
       .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND},
+	{ .match_flags = USB_DEVICE_ID_MATCH_VENDOR
+			| USB_DEVICE_ID_MATCH_PRODUCT,
+	  .idVendor = USB_VENDOR_MICROCHIP,
+	  .idProduct = USB_PRODUCT_USB4913,
+	  .driver_info = HUB_QUIRK_REDUCE_FRAME_INTR_BINTERVAL},
+	{ .match_flags = USB_DEVICE_ID_MATCH_VENDOR
+			| USB_DEVICE_ID_MATCH_PRODUCT,
+	  .idVendor = USB_VENDOR_MICROCHIP,
+	  .idProduct = USB_PRODUCT_USB4914,
+	  .driver_info = HUB_QUIRK_REDUCE_FRAME_INTR_BINTERVAL},
+	{ .match_flags = USB_DEVICE_ID_MATCH_VENDOR
+			| USB_DEVICE_ID_MATCH_PRODUCT,
+	  .idVendor = USB_VENDOR_MICROCHIP,
+	  .idProduct = USB_PRODUCT_USB4915,
+	  .driver_info = HUB_QUIRK_REDUCE_FRAME_INTR_BINTERVAL},
     { .match_flags = USB_DEVICE_ID_MATCH_DEV_CLASS,
       .bDeviceClass = USB_CLASS_HUB},
     { .match_flags = USB_DEVICE_ID_MATCH_INT_CLASS,
diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c
index c628c1abc907..4d63496f98b6 100644
--- a/drivers/usb/core/port.c
+++ b/drivers/usb/core/port.c
@@ -573,7 +573,7 @@ static int match_location(struct usb_device *peer_hdev, void *p)
 	struct usb_hub *peer_hub = usb_hub_to_struct_hub(peer_hdev);
 	struct usb_device *hdev = to_usb_device(port_dev->dev.parent->parent);
 
-	if (!peer_hub)
+	if (!peer_hub || port_dev->connect_type == USB_PORT_NOT_USED)
 		return 0;
 
 	hcd = bus_to_hcd(hdev->bus);
@@ -584,7 +584,8 @@ static int match_location(struct usb_device *peer_hdev, void *p)
 
 	for (port1 = 1; port1 <= peer_hdev->maxchild; port1++) {
 		peer = peer_hub->ports[port1 - 1];
-		if (peer && peer->location == port_dev->location) {
+		if (peer && peer->connect_type != USB_PORT_NOT_USED &&
+		    peer->location == port_dev->location) {
 			link_peers_report(port_dev, peer);
 			return 1; /* done */
 		}
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 15e9bd180a1d..b4783574b8e6 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -138,6 +138,9 @@ static int quirks_param_set(const char *value, const struct kernel_param *kp)
 			case 'o':
 				flags |= USB_QUIRK_HUB_SLOW_RESET;
 				break;
+			case 'p':
+				flags |= USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT;
+				break;
 			/* Ignore unrecognized flag characters */
 			}
 		}
@@ -527,6 +530,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 
 	{ USB_DEVICE(0x2386, 0x350e), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* APTIV AUTOMOTIVE HUB */
+	{ USB_DEVICE(0x2c48, 0x0132), .driver_info =
+			USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT },
+
 	/* DJI CineSSD */
 	{ USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM },
 
diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c
index 2a938cf47ccd..dc8d9228a5e7 100644
--- a/drivers/usb/core/usb.c
+++ b/drivers/usb/core/usb.c
@@ -431,7 +431,7 @@ struct usb_interface *usb_find_interface(struct usb_driver *drv, int minor)
 	struct device *dev;
 
 	argb.minor = minor;
-	argb.drv = &drv->drvwrap.driver;
+	argb.drv = &drv->driver;
 
 	dev = bus_find_device(&usb_bus_type, NULL, &argb, __find_interface);
 
diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h
index 60363153fc3f..bfecb50773b6 100644
--- a/drivers/usb/core/usb.h
+++ b/drivers/usb/core/usb.h
@@ -175,13 +175,7 @@ static inline int is_root_hub(struct usb_device *udev)
 	return (udev->parent == NULL);
 }
 
-/* Do the same for device drivers and interface drivers. */
-
-static inline int is_usb_device_driver(struct device_driver *drv)
-{
-	return container_of(drv, struct usbdrv_wrap, driver)->
-			for_devices;
-}
+extern bool is_usb_device_driver(const struct device_driver *drv);
 
 /* for labeling diagnostics */
 extern const char *usbcore_name;
diff --git a/drivers/usb/dwc2/params.c b/drivers/usb/dwc2/params.c
index fb03162ae9b7..eb677c3cfd0b 100644
--- a/drivers/usb/dwc2/params.c
+++ b/drivers/usb/dwc2/params.c
@@ -130,6 +130,7 @@ static void dwc2_set_rk_params(struct dwc2_hsotg *hsotg)
 	p->lpm_clock_gating = false;
 	p->besl = false;
 	p->hird_threshold_en = false;
+	p->no_clock_gating = true;
 }
 
 static void dwc2_set_ltq_params(struct dwc2_hsotg *hsotg)
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index b101dbf8c5dc..3e55838c0001 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -277,48 +277,11 @@ int dwc3_core_soft_reset(struct dwc3 *dwc)
 	/*
 	 * We're resetting only the device side because, if we're in host mode,
 	 * XHCI driver will reset the host block. If dwc3 was configured for
-	 * host-only mode or current role is host, then we can return early.
+	 * host-only mode, then we can return early.
 	 */
 	if (dwc->current_dr_role == DWC3_GCTL_PRTCAP_HOST)
 		return 0;
 
-	/*
-	 * If the dr_mode is host and the dwc->current_dr_role is not the
-	 * corresponding DWC3_GCTL_PRTCAP_HOST, then the dwc3_core_init_mode
-	 * isn't executed yet. Ensure the phy is ready before the controller
-	 * updates the GCTL.PRTCAPDIR or other settings by soft-resetting
-	 * the phy.
-	 *
-	 * Note: GUSB3PIPECTL[n] and GUSB2PHYCFG[n] are port settings where n
-	 * is port index. If this is a multiport host, then we need to reset
-	 * all active ports.
-	 */
-	if (dwc->dr_mode == USB_DR_MODE_HOST) {
-		u32 usb3_port;
-		u32 usb2_port;
-
-		usb3_port = dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0));
-		usb3_port |= DWC3_GUSB3PIPECTL_PHYSOFTRST;
-		dwc3_writel(dwc->regs, DWC3_GUSB3PIPECTL(0), usb3_port);
-
-		usb2_port = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0));
-		usb2_port |= DWC3_GUSB2PHYCFG_PHYSOFTRST;
-		dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), usb2_port);
-
-		/* Small delay for phy reset assertion */
-		usleep_range(1000, 2000);
-
-		usb3_port &= ~DWC3_GUSB3PIPECTL_PHYSOFTRST;
-		dwc3_writel(dwc->regs, DWC3_GUSB3PIPECTL(0), usb3_port);
-
-		usb2_port &= ~DWC3_GUSB2PHYCFG_PHYSOFTRST;
-		dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), usb2_port);
-
-		/* Wait for clock synchronization */
-		msleep(50);
-		return 0;
-	}
-
 	reg = dwc3_readl(dwc->regs, DWC3_DCTL);
 	reg |= DWC3_DCTL_CSFTRST;
 	reg &= ~DWC3_DCTL_RUN_STOP;
@@ -1367,6 +1330,18 @@ static int dwc3_core_init(struct dwc3 *dwc)
 
 	dwc3_config_threshold(dwc);
 
+	/*
+	 * Modify this for all supported Super Speed ports when
+	 * multiport support is added.
+	 */
+	if (hw_mode != DWC3_GHWPARAMS0_MODE_GADGET &&
+	    (DWC3_IP_IS(DWC31)) &&
+	    dwc->maximum_speed == USB_SPEED_SUPER) {
+		reg = dwc3_readl(dwc->regs, DWC3_LLUCTL);
+		reg |= DWC3_LLUCTL_FORCE_GEN1;
+		dwc3_writel(dwc->regs, DWC3_LLUCTL, reg);
+	}
+
 	return 0;
 
 err_power_off_phy:
@@ -2340,12 +2315,15 @@ static int dwc3_resume(struct device *dev)
 
 	pinctrl_pm_select_default_state(dev);
 
+	pm_runtime_disable(dev);
+	pm_runtime_set_active(dev);
+
 	ret = dwc3_resume_common(dwc, PMSG_RESUME);
-	if (ret)
+	if (ret) {
+		pm_runtime_set_suspended(dev);
 		return ret;
+	}
 
-	pm_runtime_disable(dev);
-	pm_runtime_set_active(dev);
 	pm_runtime_enable(dev);
 
 	return 0;
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index efe6caf4d0e8..e120611a5174 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -172,6 +172,8 @@
 #define DWC3_OEVTEN		0xcc0C
 #define DWC3_OSTS		0xcc10
 
+#define DWC3_LLUCTL		0xd024
+
 /* Bit fields */
 
 /* Global SoC Bus Configuration INCRx Register 0 */
@@ -657,6 +659,9 @@
 #define DWC3_OSTS_VBUSVLD		BIT(1)
 #define DWC3_OSTS_CONIDSTS		BIT(0)
 
+/* Force Gen1 speed on Gen2 link */
+#define DWC3_LLUCTL_FORCE_GEN1		BIT(10)
+
 /* Structures */
 
 struct dwc3_trb;
diff --git a/drivers/usb/dwc3/dwc3-imx8mp.c b/drivers/usb/dwc3/dwc3-imx8mp.c
index a1e15f2fffdb..8ee448068503 100644
--- a/drivers/usb/dwc3/dwc3-imx8mp.c
+++ b/drivers/usb/dwc3/dwc3-imx8mp.c
@@ -363,8 +363,10 @@ static int __maybe_unused dwc3_imx8mp_pm_resume(struct device *dev)
 	}
 
 	ret = clk_prepare_enable(dwc3_imx->hsio_clk);
-	if (ret)
+	if (ret) {
+		clk_disable_unprepare(dwc3_imx->suspend_clk);
 		return ret;
+	}
 
 	ret = dwc3_imx8mp_resume(dwc3_imx, PMSG_RESUME);
 
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 6604845c397c..39564e17f3b0 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -51,6 +51,8 @@
 #define PCI_DEVICE_ID_INTEL_MTLP		0x7ec1
 #define PCI_DEVICE_ID_INTEL_MTLS		0x7f6f
 #define PCI_DEVICE_ID_INTEL_MTL			0x7e7e
+#define PCI_DEVICE_ID_INTEL_ARLH		0x7ec1
+#define PCI_DEVICE_ID_INTEL_ARLH_PCH		0x777e
 #define PCI_DEVICE_ID_INTEL_TGL			0x9a15
 #define PCI_DEVICE_ID_AMD_MR			0x163a
 
@@ -421,6 +423,8 @@ static const struct pci_device_id dwc3_pci_id_table[] = {
 	{ PCI_DEVICE_DATA(INTEL, MTLP, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, MTL, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, MTLS, &dwc3_pci_intel_swnode) },
+	{ PCI_DEVICE_DATA(INTEL, ARLH, &dwc3_pci_intel_swnode) },
+	{ PCI_DEVICE_DATA(INTEL, ARLH_PCH, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, TGL, &dwc3_pci_intel_swnode) },
 
 	{ PCI_DEVICE_DATA(AMD, NL_USB, &dwc3_pci_amd_swnode) },
diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c
index fdf6d5d3c2ad..dbd6a5b2b289 100644
--- a/drivers/usb/dwc3/dwc3-qcom.c
+++ b/drivers/usb/dwc3/dwc3-qcom.c
@@ -57,7 +57,7 @@ struct dwc3_acpi_pdata {
 	u32			qscratch_base_offset;
 	u32			qscratch_base_size;
 	u32			dwc3_core_base_size;
-	int			hs_phy_irq_index;
+	int			qusb2_phy_irq_index;
 	int			dp_hs_phy_irq_index;
 	int			dm_hs_phy_irq_index;
 	int			ss_phy_irq_index;
@@ -73,7 +73,7 @@ struct dwc3_qcom {
 	int			num_clocks;
 	struct reset_control	*resets;
 
-	int			hs_phy_irq;
+	int			qusb2_phy_irq;
 	int			dp_hs_phy_irq;
 	int			dm_hs_phy_irq;
 	int			ss_phy_irq;
@@ -372,7 +372,7 @@ static void dwc3_qcom_disable_wakeup_irq(int irq)
 
 static void dwc3_qcom_disable_interrupts(struct dwc3_qcom *qcom)
 {
-	dwc3_qcom_disable_wakeup_irq(qcom->hs_phy_irq);
+	dwc3_qcom_disable_wakeup_irq(qcom->qusb2_phy_irq);
 
 	if (qcom->usb2_speed == USB_SPEED_LOW) {
 		dwc3_qcom_disable_wakeup_irq(qcom->dm_hs_phy_irq);
@@ -389,7 +389,7 @@ static void dwc3_qcom_disable_interrupts(struct dwc3_qcom *qcom)
 
 static void dwc3_qcom_enable_interrupts(struct dwc3_qcom *qcom)
 {
-	dwc3_qcom_enable_wakeup_irq(qcom->hs_phy_irq, 0);
+	dwc3_qcom_enable_wakeup_irq(qcom->qusb2_phy_irq, 0);
 
 	/*
 	 * Configure DP/DM line interrupts based on the USB2 device attached to
@@ -542,19 +542,19 @@ static int dwc3_qcom_setup_irq(struct platform_device *pdev)
 	int irq;
 	int ret;
 
-	irq = dwc3_qcom_get_irq(pdev, "hs_phy_irq",
-				pdata ? pdata->hs_phy_irq_index : -1);
+	irq = dwc3_qcom_get_irq(pdev, "qusb2_phy",
+				pdata ? pdata->qusb2_phy_irq_index : -1);
 	if (irq > 0) {
 		/* Keep wakeup interrupts disabled until suspend */
 		ret = devm_request_threaded_irq(qcom->dev, irq, NULL,
 					qcom_dwc3_resume_irq,
 					IRQF_ONESHOT | IRQF_NO_AUTOEN,
-					"qcom_dwc3 HS", qcom);
+					"qcom_dwc3 QUSB2", qcom);
 		if (ret) {
-			dev_err(qcom->dev, "hs_phy_irq failed: %d\n", ret);
+			dev_err(qcom->dev, "qusb2_phy_irq failed: %d\n", ret);
 			return ret;
 		}
-		qcom->hs_phy_irq = irq;
+		qcom->qusb2_phy_irq = irq;
 	}
 
 	irq = dwc3_qcom_get_irq(pdev, "dp_hs_phy_irq",
@@ -1058,7 +1058,7 @@ static const struct dwc3_acpi_pdata sdm845_acpi_pdata = {
 	.qscratch_base_offset = SDM845_QSCRATCH_BASE_OFFSET,
 	.qscratch_base_size = SDM845_QSCRATCH_SIZE,
 	.dwc3_core_base_size = SDM845_DWC3_CORE_SIZE,
-	.hs_phy_irq_index = 1,
+	.qusb2_phy_irq_index = 1,
 	.dp_hs_phy_irq_index = 4,
 	.dm_hs_phy_irq_index = 3,
 	.ss_phy_irq_index = 2
@@ -1068,7 +1068,7 @@ static const struct dwc3_acpi_pdata sdm845_acpi_urs_pdata = {
 	.qscratch_base_offset = SDM845_QSCRATCH_BASE_OFFSET,
 	.qscratch_base_size = SDM845_QSCRATCH_SIZE,
 	.dwc3_core_base_size = SDM845_DWC3_CORE_SIZE,
-	.hs_phy_irq_index = 1,
+	.qusb2_phy_irq_index = 1,
 	.dp_hs_phy_irq_index = 4,
 	.dm_hs_phy_irq_index = 3,
 	.ss_phy_irq_index = 2,
diff --git a/drivers/usb/dwc3/dwc3-xilinx.c b/drivers/usb/dwc3/dwc3-xilinx.c
index 5b7e92f476de..6095f4dee6ce 100644
--- a/drivers/usb/dwc3/dwc3-xilinx.c
+++ b/drivers/usb/dwc3/dwc3-xilinx.c
@@ -293,11 +293,15 @@ static int dwc3_xlnx_probe(struct platform_device *pdev)
 		goto err_clk_put;
 
 	pm_runtime_set_active(dev);
-	pm_runtime_enable(dev);
+	ret = devm_pm_runtime_enable(dev);
+	if (ret < 0)
+		goto err_pm_set_suspended;
+
 	pm_suspend_ignore_children(dev, false);
-	pm_runtime_get_sync(dev);
+	return pm_runtime_resume_and_get(dev);
 
-	return 0;
+err_pm_set_suspended:
+	pm_runtime_set_suspended(dev);
 
 err_clk_put:
 	clk_bulk_disable_unprepare(priv_data->num_clocks, priv_data->clks);
@@ -315,7 +319,6 @@ static void dwc3_xlnx_remove(struct platform_device *pdev)
 	clk_bulk_disable_unprepare(priv_data->num_clocks, priv_data->clks);
 	priv_data->num_clocks = 0;
 
-	pm_runtime_disable(dev);
 	pm_runtime_put_noidle(dev);
 	pm_runtime_set_suspended(dev);
 }
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index b94243237293..6ae8a36f21cf 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -238,7 +238,10 @@ void dwc3_ep0_stall_and_restart(struct dwc3 *dwc)
 		struct dwc3_request	*req;
 
 		req = next_request(&dep->pending_list);
-		dwc3_gadget_giveback(dep, req, -ECONNRESET);
+		if (!dwc->connected)
+			dwc3_gadget_giveback(dep, req, -ESHUTDOWN);
+		else
+			dwc3_gadget_giveback(dep, req, -ECONNRESET);
 	}
 
 	dwc->eps[0]->trb_enqueue = 0;
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 858fe4c299b7..28f49400f3e8 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -2103,7 +2103,17 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep,
 
 	list_for_each_entry(r, &dep->pending_list, list) {
 		if (r == req) {
-			dwc3_gadget_giveback(dep, req, -ECONNRESET);
+			/*
+			 * Explicitly check for EP0/1 as dequeue for those
+			 * EPs need to be handled differently.  Control EP
+			 * only deals with one USB req, and giveback will
+			 * occur during dwc3_ep0_stall_and_restart().  EP0
+			 * requests are never added to started_list.
+			 */
+			if (dep->number > 1)
+				dwc3_gadget_giveback(dep, req, -ECONNRESET);
+			else
+				dwc3_ep0_reset_state(dwc);
 			goto out;
 		}
 	}
@@ -2640,6 +2650,11 @@ static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc)
 	int ret;
 
 	spin_lock_irqsave(&dwc->lock, flags);
+	if (!dwc->pullups_connected) {
+		spin_unlock_irqrestore(&dwc->lock, flags);
+		return 0;
+	}
+
 	dwc->connected = false;
 
 	/*
@@ -3973,6 +3988,13 @@ static void dwc3_gadget_disconnect_interrupt(struct dwc3 *dwc)
 	usb_gadget_set_state(dwc->gadget, USB_STATE_NOTATTACHED);
 
 	dwc3_ep0_reset_state(dwc);
+
+	/*
+	 * Request PM idle to address condition where usage count is
+	 * already decremented to zero, but waiting for the disconnect
+	 * interrupt to set dwc->connected to FALSE.
+	 */
+	pm_request_idle(dwc->dev);
 }
 
 static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc)
@@ -4686,15 +4708,13 @@ int dwc3_gadget_suspend(struct dwc3 *dwc)
 	unsigned long flags;
 	int ret;
 
-	if (!dwc->gadget_driver)
-		return 0;
-
 	ret = dwc3_gadget_soft_disconnect(dwc);
 	if (ret)
 		goto err;
 
 	spin_lock_irqsave(&dwc->lock, flags);
-	dwc3_disconnect_gadget(dwc);
+	if (dwc->gadget_driver)
+		dwc3_disconnect_gadget(dwc);
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
 	return 0;
diff --git a/drivers/usb/dwc3/host.c b/drivers/usb/dwc3/host.c
index 61f57fe5bb78..43230915323c 100644
--- a/drivers/usb/dwc3/host.c
+++ b/drivers/usb/dwc3/host.c
@@ -61,7 +61,7 @@ out:
 
 int dwc3_host_init(struct dwc3 *dwc)
 {
-	struct property_entry	props[4];
+	struct property_entry	props[5];
 	struct platform_device	*xhci;
 	int			ret, irq;
 	int			prop_idx = 0;
@@ -89,6 +89,8 @@ int dwc3_host_init(struct dwc3 *dwc)
 
 	memset(props, 0, sizeof(struct property_entry) * ARRAY_SIZE(props));
 
+	props[prop_idx++] = PROPERTY_ENTRY_BOOL("xhci-sg-trb-cache-size-quirk");
+
 	if (dwc->usb3_lpm_capable)
 		props[prop_idx++] = PROPERTY_ENTRY_BOOL("usb3-lpm-capable");
 
diff --git a/drivers/usb/fotg210/fotg210-hcd.c b/drivers/usb/fotg210/fotg210-hcd.c
index 7bf810a0c98a..8c5aaf860635 100644
--- a/drivers/usb/fotg210/fotg210-hcd.c
+++ b/drivers/usb/fotg210/fotg210-hcd.c
@@ -404,9 +404,9 @@ static void qh_lines(struct fotg210_hcd *fotg210, struct fotg210_qh *qh,
 			else if (td->hw_alt_next != list_end)
 				mark = '/';
 		}
-		temp = snprintf(next, size,
-				"\n\t%p%c%s len=%d %08x urb %p",
-				td, mark, ({ char *tmp;
+		temp = scnprintf(next, size,
+				 "\n\t%p%c%s len=%d %08x urb %p",
+				 td, mark, ({ char *tmp;
 				switch ((scratch>>8)&0x03) {
 				case 0:
 					tmp = "out";
@@ -424,15 +424,11 @@ static void qh_lines(struct fotg210_hcd *fotg210, struct fotg210_qh *qh,
 				(scratch >> 16) & 0x7fff,
 				scratch,
 				td->urb);
-		if (size < temp)
-			temp = size;
 		size -= temp;
 		next += temp;
 	}
 
-	temp = snprintf(next, size, "\n");
-	if (size < temp)
-		temp = size;
+	temp = scnprintf(next, size, "\n");
 
 	size -= temp;
 	next += temp;
diff --git a/drivers/usb/fotg210/fotg210-udc.c b/drivers/usb/fotg210/fotg210-udc.c
index f7ea84070554..0bae12e34f9a 100644
--- a/drivers/usb/fotg210/fotg210-udc.c
+++ b/drivers/usb/fotg210/fotg210-udc.c
@@ -1094,10 +1094,10 @@ static int fotg210_udc_stop(struct usb_gadget *g)
 
 /**
  * fotg210_vbus_session - Called by external transceiver to enable/disable udc
- * @_gadget: usb gadget
+ * @g: usb gadget
  * @is_active: 0 if should disable UDC VBUS, 1 if should enable
  *
- * Returns 0
+ * Returns: %0
  */
 static int fotg210_vbus_session(struct usb_gadget *g, int is_active)
 {
@@ -1122,7 +1122,7 @@ static const struct usb_gadget_ops fotg210_gadget_ops = {
  *
  * Called by the USB Phy when a cable connect or disconnect is sensed.
  *
- * Returns NOTIFY_OK or NOTIFY_DONE
+ * Returns: NOTIFY_OK or NOTIFY_DONE
  */
 static int fotg210_phy_event(struct notifier_block *nb, unsigned long action,
 			     void *data)
diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index 4c639e9ddedc..ce3cfa1f36f5 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -606,10 +606,11 @@ static struct config_group *function_make(
 	char *instance_name;
 	int ret;
 
-	ret = snprintf(buf, MAX_NAME_LEN, "%s", name);
-	if (ret >= MAX_NAME_LEN)
+	if (strlen(name) >= MAX_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
+	scnprintf(buf, MAX_NAME_LEN, "%s", name);
+
 	func_name = buf;
 	instance_name = strchr(func_name, '.');
 	if (!instance_name) {
@@ -701,10 +702,12 @@ static struct config_group *config_desc_make(
 	int ret;
 
 	gi = container_of(group, struct gadget_info, configs_group);
-	ret = snprintf(buf, MAX_NAME_LEN, "%s", name);
-	if (ret >= MAX_NAME_LEN)
+
+	if (strlen(name) >= MAX_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
+	scnprintf(buf, MAX_NAME_LEN, "%s", name);
+
 	num_str = strchr(buf, '.');
 	if (!num_str) {
 		pr_err("Unable to locate . in name.bConfigurationValue\n");
@@ -812,7 +815,7 @@ static ssize_t gadget_string_s_show(struct config_item *item, char *page)
 	struct gadget_string *string = to_gadget_string(item);
 	int ret;
 
-	ret = snprintf(page, sizeof(string->string), "%s\n", string->string);
+	ret = sysfs_emit(page, "%s\n", string->string);
 	return ret;
 }
 
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index fdd0fc7b8f25..6bff6cb93789 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -2931,9 +2931,8 @@ static int __ffs_func_bind_do_os_desc(enum ffs_os_desc_type type,
 
 		t = &func->function.os_desc_table[desc->bFirstInterfaceNumber];
 		t->if_id = func->interfaces_nums[desc->bFirstInterfaceNumber];
-		memcpy(t->os_desc->ext_compat_id, &desc->CompatibleID,
-		       ARRAY_SIZE(desc->CompatibleID) +
-		       ARRAY_SIZE(desc->SubCompatibleID));
+		memcpy(t->os_desc->ext_compat_id, &desc->IDs,
+		       sizeof_field(struct usb_ext_compat_desc, IDs));
 		length = sizeof(*desc);
 	}
 		break;
diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c
index 722a3ab2b337..c265a1f62fc1 100644
--- a/drivers/usb/gadget/function/f_mass_storage.c
+++ b/drivers/usb/gadget/function/f_mass_storage.c
@@ -545,21 +545,37 @@ static int start_transfer(struct fsg_dev *fsg, struct usb_ep *ep,
 
 static bool start_in_transfer(struct fsg_common *common, struct fsg_buffhd *bh)
 {
+	int rc;
+
 	if (!fsg_is_set(common))
 		return false;
 	bh->state = BUF_STATE_SENDING;
-	if (start_transfer(common->fsg, common->fsg->bulk_in, bh->inreq))
+	rc = start_transfer(common->fsg, common->fsg->bulk_in, bh->inreq);
+	if (rc) {
 		bh->state = BUF_STATE_EMPTY;
+		if (rc == -ESHUTDOWN) {
+			common->running = 0;
+			return false;
+		}
+	}
 	return true;
 }
 
 static bool start_out_transfer(struct fsg_common *common, struct fsg_buffhd *bh)
 {
+	int rc;
+
 	if (!fsg_is_set(common))
 		return false;
 	bh->state = BUF_STATE_RECEIVING;
-	if (start_transfer(common->fsg, common->fsg->bulk_out, bh->outreq))
+	rc = start_transfer(common->fsg, common->fsg->bulk_out, bh->outreq);
+	if (rc) {
 		bh->state = BUF_STATE_FULL;
+		if (rc == -ESHUTDOWN) {
+			common->running = 0;
+			return false;
+		}
+	}
 	return true;
 }
 
diff --git a/drivers/usb/gadget/function/f_midi.c b/drivers/usb/gadget/function/f_midi.c
index 5335845d697b..20c6fbd94f32 100644
--- a/drivers/usb/gadget/function/f_midi.c
+++ b/drivers/usb/gadget/function/f_midi.c
@@ -1177,11 +1177,11 @@ F_MIDI_OPT(out_ports, true, MAX_PORTS);
 static ssize_t f_midi_opts_id_show(struct config_item *item, char *page)
 {
 	struct f_midi_opts *opts = to_f_midi_opts(item);
-	int result;
+	ssize_t result;
 
 	mutex_lock(&opts->lock);
 	if (opts->id) {
-		result = strlcpy(page, opts->id, PAGE_SIZE);
+		result = strscpy(page, opts->id, PAGE_SIZE);
 	} else {
 		page[0] = 0;
 		result = 0;
diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index cc0ed29a4adc..28f4e6552e84 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -103,6 +103,16 @@ static inline struct f_ncm *func_to_ncm(struct usb_function *f)
 /* Delay for the transmit to wait before sending an unfilled NTB frame. */
 #define TX_TIMEOUT_NSECS	300000
 
+/*
+ * Although max mtu as dictated by u_ether is 15412 bytes, setting
+ * max_segment_size to 15426 would not be efficient. If user chooses segment
+ * size to be (>= 8192), then we can't aggregate more than one buffer in each
+ * NTB (assuming each packet coming from network layer is >= 8192 bytes) as ep
+ * maxpacket limit is 16384. So let max_segment_size be limited to 8000 to allow
+ * at least 2 packets to be aggregated reducing wastage of NTB buffer space
+ */
+#define MAX_DATAGRAM_SIZE	8000
+
 #define FORMATS_SUPPORTED	(USB_CDC_NCM_NTB16_SUPPORTED |	\
 				 USB_CDC_NCM_NTB32_SUPPORTED)
 
@@ -179,7 +189,6 @@ static struct usb_cdc_ether_desc ecm_desc = {
 	/* this descriptor actually adds value, surprise! */
 	/* .iMACAddress = DYNAMIC */
 	.bmEthernetStatistics =	cpu_to_le32(0), /* no statistics */
-	.wMaxSegmentSize =	cpu_to_le16(ETH_FRAME_LEN),
 	.wNumberMCFilters =	cpu_to_le16(0),
 	.bNumberPowerFilters =	0,
 };
@@ -1166,11 +1175,15 @@ static int ncm_unwrap_ntb(struct gether *port,
 	struct sk_buff	*skb2;
 	int		ret = -EINVAL;
 	unsigned	ntb_max = le32_to_cpu(ntb_parameters.dwNtbOutMaxSize);
-	unsigned	frame_max = le16_to_cpu(ecm_desc.wMaxSegmentSize);
+	unsigned	frame_max;
 	const struct ndp_parser_opts *opts = ncm->parser_opts;
 	unsigned	crc_len = ncm->is_crc ? sizeof(uint32_t) : 0;
 	int		dgram_counter;
 	int		to_process = skb->len;
+	struct f_ncm_opts *ncm_opts;
+
+	ncm_opts = container_of(port->func.fi, struct f_ncm_opts, func_inst);
+	frame_max = ncm_opts->max_segment_size;
 
 parse_ntb:
 	tmp = (__le16 *)ntb_ptr;
@@ -1325,7 +1338,15 @@ parse_ntb:
 	     "Parsed NTB with %d frames\n", dgram_counter);
 
 	to_process -= block_len;
-	if (to_process != 0) {
+
+	/*
+	 * Windows NCM driver avoids USB ZLPs by adding a 1-byte
+	 * zero pad as needed.
+	 */
+	if (to_process == 1 &&
+	    (*(unsigned char *)(ntb_ptr + block_len) == 0x00)) {
+		to_process--;
+	} else if ((to_process > 0) && (block_len != 0)) {
 		ntb_ptr = (unsigned char *)(ntb_ptr + block_len);
 		goto parse_ntb;
 	}
@@ -1430,8 +1451,10 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
 
 	mutex_lock(&ncm_opts->lock);
 	gether_set_gadget(ncm_opts->net, cdev->gadget);
-	if (!ncm_opts->bound)
+	if (!ncm_opts->bound) {
+		ncm_opts->net->mtu = (ncm_opts->max_segment_size - ETH_HLEN);
 		status = gether_register_netdev(ncm_opts->net);
+	}
 	mutex_unlock(&ncm_opts->lock);
 
 	if (status)
@@ -1474,6 +1497,8 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
 	ncm_data_intf.bInterfaceNumber = status;
 	ncm_union_desc.bSlaveInterface0 = status;
 
+	ecm_desc.wMaxSegmentSize = cpu_to_le16(ncm_opts->max_segment_size);
+
 	status = -ENODEV;
 
 	/* allocate instance-specific endpoints */
@@ -1576,11 +1601,56 @@ USB_ETHERNET_CONFIGFS_ITEM_ATTR_QMULT(ncm);
 /* f_ncm_opts_ifname */
 USB_ETHERNET_CONFIGFS_ITEM_ATTR_IFNAME(ncm);
 
+static ssize_t ncm_opts_max_segment_size_show(struct config_item *item,
+					      char *page)
+{
+	struct f_ncm_opts *opts = to_f_ncm_opts(item);
+	u16 segment_size;
+
+	mutex_lock(&opts->lock);
+	segment_size = opts->max_segment_size;
+	mutex_unlock(&opts->lock);
+
+	return sysfs_emit(page, "%u\n", segment_size);
+}
+
+static ssize_t ncm_opts_max_segment_size_store(struct config_item *item,
+					       const char *page, size_t len)
+{
+	struct f_ncm_opts *opts = to_f_ncm_opts(item);
+	u16 segment_size;
+	int ret;
+
+	mutex_lock(&opts->lock);
+	if (opts->refcnt) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	ret = kstrtou16(page, 0, &segment_size);
+	if (ret)
+		goto out;
+
+	if (segment_size > MAX_DATAGRAM_SIZE) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	opts->max_segment_size = segment_size;
+	ret = len;
+out:
+	mutex_unlock(&opts->lock);
+	return ret;
+}
+
+CONFIGFS_ATTR(ncm_opts_, max_segment_size);
+
 static struct configfs_attribute *ncm_attrs[] = {
 	&ncm_opts_attr_dev_addr,
 	&ncm_opts_attr_host_addr,
 	&ncm_opts_attr_qmult,
 	&ncm_opts_attr_ifname,
+	&ncm_opts_attr_max_segment_size,
 	NULL,
 };
 
@@ -1623,6 +1693,7 @@ static struct usb_function_instance *ncm_alloc_inst(void)
 		kfree(opts);
 		return ERR_CAST(net);
 	}
+	opts->max_segment_size = ETH_FRAME_LEN;
 	INIT_LIST_HEAD(&opts->ncm_os_desc.ext_prop);
 
 	descs[0] = &opts->ncm_os_desc;
diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c
index ff33f31bcdf6..37befd6db001 100644
--- a/drivers/usb/gadget/function/f_tcm.c
+++ b/drivers/usb/gadget/function/f_tcm.c
@@ -1504,8 +1504,8 @@ static ssize_t tcm_usbg_tpg_nexus_show(struct config_item *item, char *page)
 		ret = -ENODEV;
 		goto out;
 	}
-	ret = snprintf(page, PAGE_SIZE, "%s\n",
-			tv_nexus->tvn_se_sess->se_node_acl->initiatorname);
+	ret = sysfs_emit(page, "%s\n",
+			 tv_nexus->tvn_se_sess->se_node_acl->initiatorname);
 out:
 	mutex_unlock(&tpg->tpg_mutex);
 	return ret;
diff --git a/drivers/usb/gadget/function/f_uac1.c b/drivers/usb/gadget/function/f_uac1.c
index 6f0e1d803dc2..7de74a3dd392 100644
--- a/drivers/usb/gadget/function/f_uac1.c
+++ b/drivers/usb/gadget/function/f_uac1.c
@@ -292,6 +292,77 @@ static struct usb_descriptor_header *f_audio_desc[] = {
 	NULL,
 };
 
+/* Standard ISO OUT Endpoint Descriptor */
+static struct usb_endpoint_descriptor ss_as_out_ep_desc  = {
+	.bLength =		USB_DT_ENDPOINT_AUDIO_SIZE,
+	.bDescriptorType =	USB_DT_ENDPOINT,
+	.bEndpointAddress =	USB_DIR_OUT,
+	.bmAttributes =		USB_ENDPOINT_SYNC_ADAPTIVE
+				| USB_ENDPOINT_XFER_ISOC,
+	.wMaxPacketSize	=	cpu_to_le16(UAC1_OUT_EP_MAX_PACKET_SIZE),
+	.bInterval =		4,
+};
+
+static struct usb_ss_ep_comp_descriptor ss_as_out_ep_desc_comp = {
+	.bLength		= sizeof(ss_as_out_ep_desc_comp),
+	.bDescriptorType	= USB_DT_SS_ENDPOINT_COMP,
+	.bMaxBurst		= 0,
+	.bmAttributes		= 0,
+	/* wBytesPerInterval = DYNAMIC */
+};
+
+/* Standard ISO OUT Endpoint Descriptor */
+static struct usb_endpoint_descriptor ss_as_in_ep_desc  = {
+	.bLength =		USB_DT_ENDPOINT_AUDIO_SIZE,
+	.bDescriptorType =	USB_DT_ENDPOINT,
+	.bEndpointAddress =	USB_DIR_IN,
+	.bmAttributes =		USB_ENDPOINT_SYNC_ASYNC
+				| USB_ENDPOINT_XFER_ISOC,
+	.wMaxPacketSize	=	cpu_to_le16(UAC1_OUT_EP_MAX_PACKET_SIZE),
+	.bInterval =		4,
+};
+
+static struct usb_ss_ep_comp_descriptor ss_as_in_ep_desc_comp = {
+	.bLength		= sizeof(ss_as_in_ep_desc_comp),
+	.bDescriptorType	= USB_DT_SS_ENDPOINT_COMP,
+	.bMaxBurst		= 0,
+	.bmAttributes		= 0,
+	/* wBytesPerInterval = DYNAMIC */
+};
+
+static struct usb_descriptor_header *f_audio_ss_desc[] = {
+	(struct usb_descriptor_header *)&ac_interface_desc,
+	(struct usb_descriptor_header *)&ac_header_desc,
+
+	(struct usb_descriptor_header *)&usb_out_it_desc,
+	(struct usb_descriptor_header *)&io_out_ot_desc,
+	(struct usb_descriptor_header *)&io_in_it_desc,
+	(struct usb_descriptor_header *)&usb_in_ot_desc,
+
+	(struct usb_descriptor_header *)&as_out_interface_alt_0_desc,
+	(struct usb_descriptor_header *)&as_out_interface_alt_1_desc,
+	(struct usb_descriptor_header *)&as_out_header_desc,
+
+	(struct usb_descriptor_header *)&as_out_type_i_desc,
+
+	//(struct usb_descriptor_header *)&as_out_ep_desc,
+	(struct usb_descriptor_header *)&ss_as_out_ep_desc,
+	(struct usb_descriptor_header *)&ss_as_out_ep_desc_comp,
+	(struct usb_descriptor_header *)&as_iso_out_desc,
+
+	(struct usb_descriptor_header *)&as_in_interface_alt_0_desc,
+	(struct usb_descriptor_header *)&as_in_interface_alt_1_desc,
+	(struct usb_descriptor_header *)&as_in_header_desc,
+
+	(struct usb_descriptor_header *)&as_in_type_i_desc,
+
+	//(struct usb_descriptor_header *)&as_in_ep_desc,
+	(struct usb_descriptor_header *)&ss_as_in_ep_desc,
+	(struct usb_descriptor_header *)&ss_as_in_ep_desc_comp,
+	(struct usb_descriptor_header *)&as_iso_in_desc,
+	NULL,
+};
+
 enum {
 	STR_AC_IF,
 	STR_USB_OUT_IT,
@@ -1352,6 +1423,7 @@ static int f_audio_bind(struct usb_configuration *c, struct usb_function *f)
 		ep = usb_ep_autoconfig(cdev->gadget, &as_out_ep_desc);
 		if (!ep)
 			goto err_free_fu;
+		ss_as_out_ep_desc.bEndpointAddress = as_out_ep_desc.bEndpointAddress;
 		audio->out_ep = ep;
 		audio->out_ep->desc = &as_out_ep_desc;
 	}
@@ -1360,6 +1432,7 @@ static int f_audio_bind(struct usb_configuration *c, struct usb_function *f)
 		ep = usb_ep_autoconfig(cdev->gadget, &as_in_ep_desc);
 		if (!ep)
 			goto err_free_fu;
+		ss_as_in_ep_desc.bEndpointAddress = as_in_ep_desc.bEndpointAddress;
 		audio->in_ep = ep;
 		audio->in_ep->desc = &as_in_ep_desc;
 	}
@@ -1367,8 +1440,8 @@ static int f_audio_bind(struct usb_configuration *c, struct usb_function *f)
 	setup_descriptor(audio_opts);
 
 	/* copy descriptors, and track endpoint copies */
-	status = usb_assign_descriptors(f, f_audio_desc, f_audio_desc, NULL,
-					NULL);
+	status = usb_assign_descriptors(f, f_audio_desc, f_audio_desc, f_audio_ss_desc,
+					f_audio_ss_desc);
 	if (status)
 		goto err_free_fu;
 
@@ -1561,7 +1634,7 @@ static ssize_t f_uac1_opts_##name##_show(struct config_item *item,	\
 	int result;							\
 									\
 	mutex_lock(&opts->lock);					\
-	result = snprintf(page, sizeof(opts->name), "%s", opts->name);	\
+	result = scnprintf(page, sizeof(opts->name), "%s", opts->name);	\
 	mutex_unlock(&opts->lock);					\
 									\
 	return result;							\
@@ -1579,7 +1652,7 @@ static ssize_t f_uac1_opts_##name##_store(struct config_item *item,	\
 		goto end;						\
 	}								\
 									\
-	ret = snprintf(opts->name, min(sizeof(opts->name), len),	\
+	ret = scnprintf(opts->name, min(sizeof(opts->name), len),	\
 			"%s", page);					\
 									\
 end:									\
@@ -1685,7 +1758,7 @@ static struct usb_function_instance *f_audio_alloc_inst(void)
 
 	opts->req_number = UAC1_DEF_REQ_NUM;
 
-	snprintf(opts->function_name, sizeof(opts->function_name), "AC Interface");
+	scnprintf(opts->function_name, sizeof(opts->function_name), "AC Interface");
 
 	return &opts->func_inst;
 }
diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c
index f9a0f07a7476..383f6854cfec 100644
--- a/drivers/usb/gadget/function/f_uac2.c
+++ b/drivers/usb/gadget/function/f_uac2.c
@@ -2045,7 +2045,7 @@ static ssize_t f_uac2_opts_##name##_show(struct config_item *item,	\
 	int result;							\
 									\
 	mutex_lock(&opts->lock);					\
-	result = snprintf(page, sizeof(opts->name), "%s", opts->name);	\
+	result = scnprintf(page, sizeof(opts->name), "%s", opts->name);	\
 	mutex_unlock(&opts->lock);					\
 									\
 	return result;							\
@@ -2063,7 +2063,7 @@ static ssize_t f_uac2_opts_##name##_store(struct config_item *item,	\
 		goto end;						\
 	}								\
 									\
-	ret = snprintf(opts->name, min(sizeof(opts->name), len),	\
+	ret = scnprintf(opts->name, min(sizeof(opts->name), len),	\
 			"%s", page);					\
 									\
 end:									\
@@ -2187,7 +2187,7 @@ static struct usb_function_instance *afunc_alloc_inst(void)
 	opts->req_number = UAC2_DEF_REQ_NUM;
 	opts->fb_max = FBACK_FAST_MAX;
 
-	snprintf(opts->function_name, sizeof(opts->function_name), "Source/Sink");
+	scnprintf(opts->function_name, sizeof(opts->function_name), "Source/Sink");
 
 	opts->p_terminal_type = UAC2_DEF_P_TERM_TYPE;
 	opts->c_terminal_type = UAC2_DEF_C_TERM_TYPE;
diff --git a/drivers/usb/gadget/function/f_uvc.c b/drivers/usb/gadget/function/f_uvc.c
index 786379f1b7b7..929666805bd2 100644
--- a/drivers/usb/gadget/function/f_uvc.c
+++ b/drivers/usb/gadget/function/f_uvc.c
@@ -263,10 +263,13 @@ uvc_function_setup(struct usb_function *f, const struct usb_ctrlrequest *ctrl)
 	return 0;
 }
 
-void uvc_function_setup_continue(struct uvc_device *uvc)
+void uvc_function_setup_continue(struct uvc_device *uvc, int disable_ep)
 {
 	struct usb_composite_dev *cdev = uvc->func.config->cdev;
 
+	if (disable_ep && uvc->video.ep)
+		usb_ep_disable(uvc->video.ep);
+
 	usb_composite_setup_continue(cdev);
 }
 
@@ -337,15 +340,11 @@ uvc_function_set_alt(struct usb_function *f, unsigned interface, unsigned alt)
 		if (uvc->state != UVC_STATE_STREAMING)
 			return 0;
 
-		if (uvc->video.ep)
-			usb_ep_disable(uvc->video.ep);
-
 		memset(&v4l2_event, 0, sizeof(v4l2_event));
 		v4l2_event.type = UVC_EVENT_STREAMOFF;
 		v4l2_event_queue(&uvc->vdev, &v4l2_event);
 
-		uvc->state = UVC_STATE_CONNECTED;
-		return 0;
+		return USB_GADGET_DELAYED_STATUS;
 
 	case 1:
 		if (uvc->state != UVC_STATE_CONNECTED)
@@ -722,13 +721,29 @@ uvc_function_bind(struct usb_configuration *c, struct usb_function *f)
 	}
 	uvc->enable_interrupt_ep = opts->enable_interrupt_ep;
 
-	ep = usb_ep_autoconfig(cdev->gadget, &uvc_fs_streaming_ep);
+	/*
+	 * gadget_is_{super|dual}speed() API check UDC controller capitblity. It should pass down
+	 * highest speed endpoint descriptor to UDC controller. So UDC controller driver can reserve
+	 * enough resource at check_config(), especially mult and maxburst. So UDC driver (such as
+	 * cdns3) can know need at least (mult + 1) * (maxburst + 1) * wMaxPacketSize internal
+	 * memory for this uvc functions. This is the only straightforward method to resolve the UDC
+	 * resource allocation issue in the current gadget framework.
+	 */
+	if (gadget_is_superspeed(c->cdev->gadget))
+		ep = usb_ep_autoconfig_ss(cdev->gadget, &uvc_ss_streaming_ep,
+					  &uvc_ss_streaming_comp);
+	else if (gadget_is_dualspeed(cdev->gadget))
+		ep = usb_ep_autoconfig(cdev->gadget, &uvc_hs_streaming_ep);
+	else
+		ep = usb_ep_autoconfig(cdev->gadget, &uvc_fs_streaming_ep);
+
 	if (!ep) {
 		uvcg_info(f, "Unable to allocate streaming EP\n");
 		goto error;
 	}
 	uvc->video.ep = ep;
 
+	uvc_fs_streaming_ep.bEndpointAddress = uvc->video.ep->address;
 	uvc_hs_streaming_ep.bEndpointAddress = uvc->video.ep->address;
 	uvc_ss_streaming_ep.bEndpointAddress = uvc->video.ep->address;
 
@@ -960,7 +975,8 @@ static void uvc_free(struct usb_function *f)
 	struct uvc_device *uvc = to_uvc(f);
 	struct f_uvc_opts *opts = container_of(f->fi, struct f_uvc_opts,
 					       func_inst);
-	config_item_put(&uvc->header->item);
+	if (!opts->header)
+		config_item_put(&uvc->header->item);
 	--opts->refcnt;
 	kfree(uvc);
 }
@@ -1052,25 +1068,29 @@ static struct usb_function *uvc_alloc(struct usb_function_instance *fi)
 	uvc->desc.hs_streaming = opts->hs_streaming;
 	uvc->desc.ss_streaming = opts->ss_streaming;
 
-	streaming = config_group_find_item(&opts->func_inst.group, "streaming");
-	if (!streaming)
-		goto err_config;
-
-	header = config_group_find_item(to_config_group(streaming), "header");
-	config_item_put(streaming);
-	if (!header)
-		goto err_config;
-
-	h = config_group_find_item(to_config_group(header), "h");
-	config_item_put(header);
-	if (!h)
-		goto err_config;
-
-	uvc->header = to_uvcg_streaming_header(h);
-	if (!uvc->header->linked) {
-		mutex_unlock(&opts->lock);
-		kfree(uvc);
-		return ERR_PTR(-EBUSY);
+	if (opts->header) {
+		uvc->header = opts->header;
+	} else {
+		streaming = config_group_find_item(&opts->func_inst.group, "streaming");
+		if (!streaming)
+			goto err_config;
+
+		header = config_group_find_item(to_config_group(streaming), "header");
+		config_item_put(streaming);
+		if (!header)
+			goto err_config;
+
+		h = config_group_find_item(to_config_group(header), "h");
+		config_item_put(header);
+		if (!h)
+			goto err_config;
+
+		uvc->header = to_uvcg_streaming_header(h);
+		if (!uvc->header->linked) {
+			mutex_unlock(&opts->lock);
+			kfree(uvc);
+			return ERR_PTR(-EBUSY);
+		}
 	}
 
 	uvc->desc.extension_units = &opts->extension_units;
diff --git a/drivers/usb/gadget/function/f_uvc.h b/drivers/usb/gadget/function/f_uvc.h
index 1db972d4beeb..083aef0c65c6 100644
--- a/drivers/usb/gadget/function/f_uvc.h
+++ b/drivers/usb/gadget/function/f_uvc.h
@@ -11,7 +11,7 @@
 
 struct uvc_device;
 
-void uvc_function_setup_continue(struct uvc_device *uvc);
+void uvc_function_setup_continue(struct uvc_device *uvc, int disable_ep);
 
 void uvc_function_connect(struct uvc_device *uvc);
 
diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index 9d1c40c152d8..3c5a6f6ac341 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -1163,6 +1163,8 @@ struct net_device *gether_connect(struct gether *link)
 		if (netif_running(dev->net))
 			eth_start(dev, GFP_ATOMIC);
 
+		netif_device_attach(dev->net);
+
 	/* on error, disable any endpoints  */
 	} else {
 		(void) usb_ep_disable(link->out_ep);
diff --git a/drivers/usb/gadget/function/u_ncm.h b/drivers/usb/gadget/function/u_ncm.h
index 5408854d8407..49ec095cdb4b 100644
--- a/drivers/usb/gadget/function/u_ncm.h
+++ b/drivers/usb/gadget/function/u_ncm.h
@@ -31,6 +31,8 @@ struct f_ncm_opts {
 	 */
 	struct mutex			lock;
 	int				refcnt;
+
+	u16				max_segment_size;
 };
 
 #endif /* U_NCM_H */
diff --git a/drivers/usb/gadget/function/u_uvc.h b/drivers/usb/gadget/function/u_uvc.h
index 1ce58f61253c..3ac392cbb779 100644
--- a/drivers/usb/gadget/function/u_uvc.h
+++ b/drivers/usb/gadget/function/u_uvc.h
@@ -98,6 +98,12 @@ struct f_uvc_opts {
 	 */
 	struct mutex			lock;
 	int				refcnt;
+
+	/*
+	 * Only for legacy gadget. Shall be NULL for configfs-composed gadgets,
+	 * which is guaranteed by alloc_inst implementation of f_uvc doing kzalloc.
+	 */
+	struct uvcg_streaming_header	*header;
 };
 
 #endif /* U_UVC_H */
diff --git a/drivers/usb/gadget/function/uvc.h b/drivers/usb/gadget/function/uvc.h
index 6751de8b63ad..cb35687b11e7 100644
--- a/drivers/usb/gadget/function/uvc.h
+++ b/drivers/usb/gadget/function/uvc.h
@@ -81,6 +81,7 @@ struct uvc_request {
 	struct sg_table sgt;
 	u8 header[UVCG_REQUEST_HEADER_LEN];
 	struct uvc_buffer *last_buf;
+	struct list_head list;
 };
 
 struct uvc_video {
@@ -101,9 +102,18 @@ struct uvc_video {
 	unsigned int uvc_num_requests;
 
 	/* Requests */
+	bool is_enabled; /* tracks whether video stream is enabled */
 	unsigned int req_size;
-	struct uvc_request *ureq;
+	struct list_head ureqs; /* all uvc_requests allocated by uvc_video */
+
+	/* USB requests that the video pump thread can encode into */
 	struct list_head req_free;
+
+	/*
+	 * USB requests video pump thread has already encoded into. These are
+	 * ready to be queued to the endpoint.
+	 */
+	struct list_head req_ready;
 	spinlock_t req_lock;
 
 	unsigned int req_int_count;
@@ -177,7 +187,7 @@ struct uvc_file_handle {
  * Functions
  */
 
-extern void uvc_function_setup_continue(struct uvc_device *uvc);
+extern void uvc_function_setup_continue(struct uvc_device *uvc, int disable_ep);
 extern void uvc_function_connect(struct uvc_device *uvc);
 extern void uvc_function_disconnect(struct uvc_device *uvc);
 
diff --git a/drivers/usb/gadget/function/uvc_configfs.c b/drivers/usb/gadget/function/uvc_configfs.c
index 9bf0e985acfa..7e704b2bcfd1 100644
--- a/drivers/usb/gadget/function/uvc_configfs.c
+++ b/drivers/usb/gadget/function/uvc_configfs.c
@@ -3414,7 +3414,7 @@ static ssize_t f_uvc_opts_string_##cname##_show(struct config_item *item,\
 	int result;							\
 									\
 	mutex_lock(&opts->lock);					\
-	result = snprintf(page, sizeof(opts->aname), "%s", opts->aname);\
+	result = scnprintf(page, sizeof(opts->aname), "%s", opts->aname);\
 	mutex_unlock(&opts->lock);					\
 									\
 	return result;							\
diff --git a/drivers/usb/gadget/function/uvc_v4l2.c b/drivers/usb/gadget/function/uvc_v4l2.c
index 3f0a9795c0d4..c7e5fa4f29e0 100644
--- a/drivers/usb/gadget/function/uvc_v4l2.c
+++ b/drivers/usb/gadget/function/uvc_v4l2.c
@@ -443,7 +443,7 @@ uvc_v4l2_streamon(struct file *file, void *fh, enum v4l2_buf_type type)
 		return -EINVAL;
 
 	/* Enable UVC video. */
-	ret = uvcg_video_enable(video, 1);
+	ret = uvcg_video_enable(video);
 	if (ret < 0)
 		return ret;
 
@@ -451,7 +451,7 @@ uvc_v4l2_streamon(struct file *file, void *fh, enum v4l2_buf_type type)
 	 * Complete the alternate setting selection setup phase now that
 	 * userspace is ready to provide video frames.
 	 */
-	uvc_function_setup_continue(uvc);
+	uvc_function_setup_continue(uvc, 0);
 	uvc->state = UVC_STATE_STREAMING;
 
 	return 0;
@@ -463,11 +463,18 @@ uvc_v4l2_streamoff(struct file *file, void *fh, enum v4l2_buf_type type)
 	struct video_device *vdev = video_devdata(file);
 	struct uvc_device *uvc = video_get_drvdata(vdev);
 	struct uvc_video *video = &uvc->video;
+	int ret = 0;
 
 	if (type != video->queue.queue.type)
 		return -EINVAL;
 
-	return uvcg_video_enable(video, 0);
+	ret = uvcg_video_disable(video);
+	if (ret < 0)
+		return ret;
+
+	uvc->state = UVC_STATE_CONNECTED;
+	uvc_function_setup_continue(uvc, 1);
+	return 0;
 }
 
 static int
@@ -500,7 +507,7 @@ uvc_v4l2_subscribe_event(struct v4l2_fh *fh,
 static void uvc_v4l2_disable(struct uvc_device *uvc)
 {
 	uvc_function_disconnect(uvc);
-	uvcg_video_enable(&uvc->video, 0);
+	uvcg_video_disable(&uvc->video);
 	uvcg_free_buffers(&uvc->video.queue);
 	uvc->func_connected = false;
 	wake_up_interruptible(&uvc->func_connected_queue);
@@ -647,4 +654,3 @@ const struct v4l2_file_operations uvc_v4l2_fops = {
 	.get_unmapped_area = uvcg_v4l2_get_unmapped_area,
 #endif
 };
-
diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c
index 91af3b1ef0d4..dd3241fc6939 100644
--- a/drivers/usb/gadget/function/uvc_video.c
+++ b/drivers/usb/gadget/function/uvc_video.c
@@ -227,6 +227,28 @@ uvc_video_encode_isoc(struct usb_request *req, struct uvc_video *video,
  * Request handling
  */
 
+/*
+ * Callers must take care to hold req_lock when this function may be called
+ * from multiple threads. For example, when frames are streaming to the host.
+ */
+static void
+uvc_video_free_request(struct uvc_request *ureq, struct usb_ep *ep)
+{
+	sg_free_table(&ureq->sgt);
+	if (ureq->req && ep) {
+		usb_ep_free_request(ep, ureq->req);
+		ureq->req = NULL;
+	}
+
+	kfree(ureq->req_buffer);
+	ureq->req_buffer = NULL;
+
+	if (!list_empty(&ureq->list))
+		list_del_init(&ureq->list);
+
+	kfree(ureq);
+}
+
 static int uvcg_video_ep_queue(struct uvc_video *video, struct usb_request *req)
 {
 	int ret;
@@ -247,14 +269,127 @@ static int uvcg_video_ep_queue(struct uvc_video *video, struct usb_request *req)
 	return ret;
 }
 
+/* This function must be called with video->req_lock held. */
+static int uvcg_video_usb_req_queue(struct uvc_video *video,
+	struct usb_request *req, bool queue_to_ep)
+{
+	bool is_bulk = video->max_payload_size;
+	struct list_head *list = NULL;
+
+	if (!video->is_enabled)
+		return -ENODEV;
+
+	if (queue_to_ep) {
+		struct uvc_request *ureq = req->context;
+		/*
+		 * With USB3 handling more requests at a higher speed, we can't
+		 * afford to generate an interrupt for every request. Decide to
+		 * interrupt:
+		 *
+		 * - When no more requests are available in the free queue, as
+		 *   this may be our last chance to refill the endpoint's
+		 *   request queue.
+		 *
+		 * - When this is request is the last request for the video
+		 *   buffer, as we want to start sending the next video buffer
+		 *   ASAP in case it doesn't get started already in the next
+		 *   iteration of this loop.
+		 *
+		 * - Four times over the length of the requests queue (as
+		 *   indicated by video->uvc_num_requests), as a trade-off
+		 *   between latency and interrupt load.
+		 */
+		if (list_empty(&video->req_free) || ureq->last_buf ||
+			!(video->req_int_count %
+			DIV_ROUND_UP(video->uvc_num_requests, 4))) {
+			video->req_int_count = 0;
+			req->no_interrupt = 0;
+		} else {
+			req->no_interrupt = 1;
+		}
+		video->req_int_count++;
+		return uvcg_video_ep_queue(video, req);
+	}
+	/*
+	 * If we're not queuing to the ep, for isoc we're queuing
+	 * to the req_ready list, otherwise req_free.
+	 */
+	list = is_bulk ? &video->req_free : &video->req_ready;
+	list_add_tail(&req->list, list);
+	return 0;
+}
+
+/*
+ * Must only be called from uvcg_video_enable - since after that we only want to
+ * queue requests to the endpoint from the uvc_video_complete complete handler.
+ * This function is needed in order to 'kick start' the flow of requests from
+ * gadget driver to the usb controller.
+ */
+static void uvc_video_ep_queue_initial_requests(struct uvc_video *video)
+{
+	struct usb_request *req = NULL;
+	unsigned long flags = 0;
+	unsigned int count = 0;
+	int ret = 0;
+
+	/*
+	 * We only queue half of the free list since we still want to have
+	 * some free usb_requests in the free list for the video_pump async_wq
+	 * thread to encode uvc buffers into. Otherwise we could get into a
+	 * situation where the free list does not have any usb requests to
+	 * encode into - we always end up queueing 0 length requests to the
+	 * end point.
+	 */
+	unsigned int half_list_size = video->uvc_num_requests / 2;
+
+	spin_lock_irqsave(&video->req_lock, flags);
+	/*
+	 * Take these requests off the free list and queue them all to the
+	 * endpoint. Since we queue 0 length requests with the req_lock held,
+	 * there isn't any 'data' race involved here with the complete handler.
+	 */
+	while (count < half_list_size) {
+		req = list_first_entry(&video->req_free, struct usb_request,
+					list);
+		list_del(&req->list);
+		req->length = 0;
+		ret = uvcg_video_ep_queue(video, req);
+		if (ret < 0) {
+			uvcg_queue_cancel(&video->queue, 0);
+			break;
+		}
+		count++;
+	}
+	spin_unlock_irqrestore(&video->req_lock, flags);
+}
+
 static void
 uvc_video_complete(struct usb_ep *ep, struct usb_request *req)
 {
 	struct uvc_request *ureq = req->context;
 	struct uvc_video *video = ureq->video;
 	struct uvc_video_queue *queue = &video->queue;
-	struct uvc_device *uvc = video->uvc;
+	struct uvc_buffer *last_buf;
 	unsigned long flags;
+	bool is_bulk = video->max_payload_size;
+	int ret = 0;
+
+	spin_lock_irqsave(&video->req_lock, flags);
+	if (!video->is_enabled) {
+		/*
+		 * When is_enabled is false, uvcg_video_disable() ensures
+		 * that in-flight uvc_buffers are returned, so we can
+		 * safely call free_request without worrying about
+		 * last_buf.
+		 */
+		uvc_video_free_request(ureq, ep);
+		spin_unlock_irqrestore(&video->req_lock, flags);
+		return;
+	}
+
+	last_buf = ureq->last_buf;
+	ureq->last_buf = NULL;
+	spin_unlock_irqrestore(&video->req_lock, flags);
 
 	switch (req->status) {
 	case 0:
@@ -277,44 +412,85 @@ uvc_video_complete(struct usb_ep *ep, struct usb_request *req)
 		uvcg_queue_cancel(queue, 0);
 	}
 
-	if (ureq->last_buf) {
-		uvcg_complete_buffer(&video->queue, ureq->last_buf);
-		ureq->last_buf = NULL;
+	if (last_buf) {
+		spin_lock_irqsave(&queue->irqlock, flags);
+		uvcg_complete_buffer(queue, last_buf);
+		spin_unlock_irqrestore(&queue->irqlock, flags);
 	}
 
 	spin_lock_irqsave(&video->req_lock, flags);
-	list_add_tail(&req->list, &video->req_free);
+	/*
+	 * Video stream might have been disabled while we were
+	 * processing the current usb_request. So make sure
+	 * we're still streaming before queueing the usb_request
+	 * back to req_free
+	 */
+	if (video->is_enabled) {
+		/*
+		 * Here we check whether any request is available in the ready
+		 * list. If it is, queue it to the ep and add the current
+		 * usb_request to the req_free list - for video_pump to fill in.
+		 * Otherwise, just use the current usb_request to queue a 0
+		 * length request to the ep. Since we always add to the req_free
+		 * list if we dequeue from the ready list, there will never
+		 * be a situation where the req_free list is completely out of
+		 * requests and cannot recover.
+		 */
+		struct usb_request *to_queue = req;
+
+		to_queue->length = 0;
+		if (!list_empty(&video->req_ready)) {
+			to_queue = list_first_entry(&video->req_ready,
+				struct usb_request, list);
+			list_del(&to_queue->list);
+			list_add_tail(&req->list, &video->req_free);
+			/*
+			 * Queue work to the wq as well since it is possible that a
+			 * buffer may not have been completely encoded with the set of
+			 * in-flight usb requests for whih the complete callbacks are
+			 * firing.
+			 * In that case, if we do not queue work to the worker thread,
+			 * the buffer will never be marked as complete - and therefore
+			 * not be returned to userpsace. As a result,
+			 * dequeue -> queue -> dequeue flow of uvc buffers will not
+			 * happen.
+			 */
+			queue_work(video->async_wq, &video->pump);
+		}
+		/*
+		 * Queue to the endpoint. The actual queueing to ep will
+		 * only happen on one thread - the async_wq for bulk endpoints
+		 * and this thread for isoc endpoints.
+		 */
+		ret = uvcg_video_usb_req_queue(video, to_queue, !is_bulk);
+		if (ret < 0) {
+			/*
+			 * Endpoint error, but the stream is still enabled.
+			 * Put request back in req_free for it to be cleaned
+			 * up later.
+			 */
+			list_add_tail(&to_queue->list, &video->req_free);
+		}
+	} else {
+		uvc_video_free_request(ureq, ep);
+		ret = 0;
+	}
 	spin_unlock_irqrestore(&video->req_lock, flags);
-
-	if (uvc->state == UVC_STATE_STREAMING)
-		queue_work(video->async_wq, &video->pump);
+	if (ret < 0)
+		uvcg_queue_cancel(queue, 0);
 }
 
 static int
 uvc_video_free_requests(struct uvc_video *video)
 {
-	unsigned int i;
-
-	if (video->ureq) {
-		for (i = 0; i < video->uvc_num_requests; ++i) {
-			sg_free_table(&video->ureq[i].sgt);
+	struct uvc_request *ureq, *temp;
 
-			if (video->ureq[i].req) {
-				usb_ep_free_request(video->ep, video->ureq[i].req);
-				video->ureq[i].req = NULL;
-			}
-
-			if (video->ureq[i].req_buffer) {
-				kfree(video->ureq[i].req_buffer);
-				video->ureq[i].req_buffer = NULL;
-			}
-		}
-
-		kfree(video->ureq);
-		video->ureq = NULL;
-	}
+	list_for_each_entry_safe(ureq, temp, &video->ureqs, list)
+		uvc_video_free_request(ureq, video->ep);
 
+	INIT_LIST_HEAD(&video->ureqs);
 	INIT_LIST_HEAD(&video->req_free);
+	INIT_LIST_HEAD(&video->req_ready);
 	video->req_size = 0;
 	return 0;
 }
@@ -322,6 +498,7 @@ uvc_video_free_requests(struct uvc_video *video)
 static int
 uvc_video_alloc_requests(struct uvc_video *video)
 {
+	struct uvc_request *ureq;
 	unsigned int req_size;
 	unsigned int i;
 	int ret = -ENOMEM;
@@ -332,29 +509,33 @@ uvc_video_alloc_requests(struct uvc_video *video)
 		 * max_t(unsigned int, video->ep->maxburst, 1)
 		 * (video->ep->mult);
 
-	video->ureq = kcalloc(video->uvc_num_requests, sizeof(struct uvc_request), GFP_KERNEL);
-	if (video->ureq == NULL)
-		return -ENOMEM;
+	for (i = 0; i < video->uvc_num_requests; i++) {
+		ureq = kzalloc(sizeof(struct uvc_request), GFP_KERNEL);
+		if (ureq == NULL)
+			goto error;
+
+		INIT_LIST_HEAD(&ureq->list);
 
-	for (i = 0; i < video->uvc_num_requests; ++i) {
-		video->ureq[i].req_buffer = kmalloc(req_size, GFP_KERNEL);
-		if (video->ureq[i].req_buffer == NULL)
+		list_add_tail(&ureq->list, &video->ureqs);
+
+		ureq->req_buffer = kmalloc(req_size, GFP_KERNEL);
+		if (ureq->req_buffer == NULL)
 			goto error;
 
-		video->ureq[i].req = usb_ep_alloc_request(video->ep, GFP_KERNEL);
-		if (video->ureq[i].req == NULL)
+		ureq->req = usb_ep_alloc_request(video->ep, GFP_KERNEL);
+		if (ureq->req == NULL)
 			goto error;
 
-		video->ureq[i].req->buf = video->ureq[i].req_buffer;
-		video->ureq[i].req->length = 0;
-		video->ureq[i].req->complete = uvc_video_complete;
-		video->ureq[i].req->context = &video->ureq[i];
-		video->ureq[i].video = video;
-		video->ureq[i].last_buf = NULL;
+		ureq->req->buf = ureq->req_buffer;
+		ureq->req->length = 0;
+		ureq->req->complete = uvc_video_complete;
+		ureq->req->context = ureq;
+		ureq->video = video;
+		ureq->last_buf = NULL;
 
-		list_add_tail(&video->ureq[i].req->list, &video->req_free);
+		list_add_tail(&ureq->req->list, &video->req_free);
 		/* req_size/PAGE_SIZE + 1 for overruns and + 1 for header */
-		sg_alloc_table(&video->ureq[i].sgt,
+		sg_alloc_table(&ureq->sgt,
 			       DIV_ROUND_UP(req_size - UVCG_REQUEST_HEADER_LEN,
 					    PAGE_SIZE) + 2, GFP_KERNEL);
 	}
@@ -387,16 +568,18 @@ static void uvcg_video_pump(struct work_struct *work)
 	struct usb_request *req = NULL;
 	struct uvc_buffer *buf;
 	unsigned long flags;
-	bool buf_done;
-	int ret;
+	int ret = 0;
+
+	while (true) {
+		if (!video->ep->enabled)
+			return;
 
-	while (video->ep->enabled) {
 		/*
-		 * Retrieve the first available USB request, protected by the
-		 * request lock.
+		 * Check is_enabled and retrieve the first available USB
+		 * request, protected by the request lock.
 		 */
 		spin_lock_irqsave(&video->req_lock, flags);
-		if (list_empty(&video->req_free)) {
+		if (!video->is_enabled || list_empty(&video->req_free)) {
 			spin_unlock_irqrestore(&video->req_lock, flags);
 			return;
 		}
@@ -414,15 +597,6 @@ static void uvcg_video_pump(struct work_struct *work)
 
 		if (buf != NULL) {
 			video->encode(req, video, buf);
-			buf_done = buf->state == UVC_BUF_STATE_DONE;
-		} else if (!(queue->flags & UVC_QUEUE_DISCONNECTED) && !is_bulk) {
-			/*
-			 * No video buffer available; the queue is still connected and
-			 * we're transferring over ISOC. Queue a 0 length request to
-			 * prevent missed ISOC transfers.
-			 */
-			req->length = 0;
-			buf_done = false;
 		} else {
 			/*
 			 * Either the queue has been disconnected or no video buffer
@@ -433,83 +607,139 @@ static void uvcg_video_pump(struct work_struct *work)
 			break;
 		}
 
-		/*
-		 * With USB3 handling more requests at a higher speed, we can't
-		 * afford to generate an interrupt for every request. Decide to
-		 * interrupt:
-		 *
-		 * - When no more requests are available in the free queue, as
-		 *   this may be our last chance to refill the endpoint's
-		 *   request queue.
-		 *
-		 * - When this is request is the last request for the video
-		 *   buffer, as we want to start sending the next video buffer
-		 *   ASAP in case it doesn't get started already in the next
-		 *   iteration of this loop.
-		 *
-		 * - Four times over the length of the requests queue (as
-		 *   indicated by video->uvc_num_requests), as a trade-off
-		 *   between latency and interrupt load.
-		 */
-		if (list_empty(&video->req_free) || buf_done ||
-		    !(video->req_int_count %
-		       DIV_ROUND_UP(video->uvc_num_requests, 4))) {
-			video->req_int_count = 0;
-			req->no_interrupt = 0;
-		} else {
-			req->no_interrupt = 1;
-		}
-
-		/* Queue the USB request */
-		ret = uvcg_video_ep_queue(video, req);
 		spin_unlock_irqrestore(&queue->irqlock, flags);
 
+		spin_lock_irqsave(&video->req_lock, flags);
+		/* For bulk end points we queue from the worker thread
+		 * since we would preferably not want to wait on requests
+		 * to be ready, in the uvcg_video_complete() handler.
+		 * For isoc endpoints we add the request to the ready list
+		 * and only queue it to the endpoint from the complete handler.
+		 */
+		ret = uvcg_video_usb_req_queue(video, req, is_bulk);
+		spin_unlock_irqrestore(&video->req_lock, flags);
+
 		if (ret < 0) {
 			uvcg_queue_cancel(queue, 0);
 			break;
 		}
 
-		/* Endpoint now owns the request */
+		/* The request is owned by  the endpoint / ready list. */
 		req = NULL;
-		video->req_int_count++;
 	}
 
 	if (!req)
 		return;
 
 	spin_lock_irqsave(&video->req_lock, flags);
-	list_add_tail(&req->list, &video->req_free);
+	if (video->is_enabled)
+		list_add_tail(&req->list, &video->req_free);
+	else
+		uvc_video_free_request(req->context, video->ep);
 	spin_unlock_irqrestore(&video->req_lock, flags);
-	return;
 }
 
 /*
- * Enable or disable the video stream.
+ * Disable the video stream
  */
-int uvcg_video_enable(struct uvc_video *video, int enable)
+int
+uvcg_video_disable(struct uvc_video *video)
 {
-	unsigned int i;
-	int ret;
+	unsigned long flags;
+	struct list_head inflight_bufs;
+	struct usb_request *req, *temp;
+	struct uvc_buffer *buf, *btemp;
+	struct uvc_request *ureq, *utemp;
 
 	if (video->ep == NULL) {
 		uvcg_info(&video->uvc->func,
-			  "Video enable failed, device is uninitialized.\n");
+			  "Video disable failed, device is uninitialized.\n");
 		return -ENODEV;
 	}
 
-	if (!enable) {
-		cancel_work_sync(&video->pump);
-		uvcg_queue_cancel(&video->queue, 0);
+	INIT_LIST_HEAD(&inflight_bufs);
+	spin_lock_irqsave(&video->req_lock, flags);
+	video->is_enabled = false;
+
+	/*
+	 * Remove any in-flight buffers from the uvc_requests
+	 * because we want to return them before cancelling the
+	 * queue. This ensures that we aren't stuck waiting for
+	 * all complete callbacks to come through before disabling
+	 * vb2 queue.
+	 */
+	list_for_each_entry(ureq, &video->ureqs, list) {
+		if (ureq->last_buf) {
+			list_add_tail(&ureq->last_buf->queue, &inflight_bufs);
+			ureq->last_buf = NULL;
+		}
+	}
+	spin_unlock_irqrestore(&video->req_lock, flags);
 
-		for (i = 0; i < video->uvc_num_requests; ++i)
-			if (video->ureq && video->ureq[i].req)
-				usb_ep_dequeue(video->ep, video->ureq[i].req);
+	cancel_work_sync(&video->pump);
+	uvcg_queue_cancel(&video->queue, 0);
+
+	spin_lock_irqsave(&video->req_lock, flags);
+	/*
+	 * Remove all uvc_requests from ureqs with list_del_init
+	 * This lets uvc_video_free_request correctly identify
+	 * if the uvc_request is attached to a list or not when freeing
+	 * memory.
+	 */
+	list_for_each_entry_safe(ureq, utemp, &video->ureqs, list)
+		list_del_init(&ureq->list);
+
+	list_for_each_entry_safe(req, temp, &video->req_free, list) {
+		list_del(&req->list);
+		uvc_video_free_request(req->context, video->ep);
+	}
 
-		uvc_video_free_requests(video);
-		uvcg_queue_enable(&video->queue, 0);
-		return 0;
+	list_for_each_entry_safe(req, temp, &video->req_ready, list) {
+		list_del(&req->list);
+		uvc_video_free_request(req->context, video->ep);
 	}
 
+	INIT_LIST_HEAD(&video->ureqs);
+	INIT_LIST_HEAD(&video->req_free);
+	INIT_LIST_HEAD(&video->req_ready);
+	video->req_size = 0;
+	spin_unlock_irqrestore(&video->req_lock, flags);
+
+	/*
+	 * Return all the video buffers before disabling the queue.
+	 */
+	spin_lock_irqsave(&video->queue.irqlock, flags);
+	list_for_each_entry_safe(buf, btemp, &inflight_bufs, queue) {
+		list_del(&buf->queue);
+		uvcg_complete_buffer(&video->queue, buf);
+	}
+	spin_unlock_irqrestore(&video->queue.irqlock, flags);
+
+	uvcg_queue_enable(&video->queue, 0);
+	return 0;
+}
+
+/*
+ * Enable the video stream.
+ */
+int uvcg_video_enable(struct uvc_video *video)
+{
+	int ret;
+
+	if (video->ep == NULL) {
+		uvcg_info(&video->uvc->func,
+			  "Video enable failed, device is uninitialized.\n");
+		return -ENODEV;
+	}
+
+	/*
+	 * Safe to access request related fields without req_lock because
+	 * this is the only thread currently active, and no other
+	 * request handling thread will become active until this function
+	 * returns.
+	 */
+	video->is_enabled = true;
+
 	if ((ret = uvcg_queue_enable(&video->queue, 1)) < 0)
 		return ret;
 
@@ -525,7 +755,7 @@ int uvcg_video_enable(struct uvc_video *video, int enable)
 
 	video->req_int_count = 0;
 
-	queue_work(video->async_wq, &video->pump);
+	uvc_video_ep_queue_initial_requests(video);
 
 	return ret;
 }
@@ -535,7 +765,10 @@ int uvcg_video_enable(struct uvc_video *video, int enable)
  */
 int uvcg_video_init(struct uvc_video *video, struct uvc_device *uvc)
 {
+	video->is_enabled = false;
+	INIT_LIST_HEAD(&video->ureqs);
 	INIT_LIST_HEAD(&video->req_free);
+	INIT_LIST_HEAD(&video->req_ready);
 	spin_lock_init(&video->req_lock);
 	INIT_WORK(&video->pump, uvcg_video_pump);
 
diff --git a/drivers/usb/gadget/function/uvc_video.h b/drivers/usb/gadget/function/uvc_video.h
index 03adeefa343b..8ef6259741f1 100644
--- a/drivers/usb/gadget/function/uvc_video.h
+++ b/drivers/usb/gadget/function/uvc_video.h
@@ -14,7 +14,8 @@
 
 struct uvc_video;
 
-int uvcg_video_enable(struct uvc_video *video, int enable);
+int uvcg_video_enable(struct uvc_video *video);
+int uvcg_video_disable(struct uvc_video *video);
 
 int uvcg_video_init(struct uvc_video *video, struct uvc_device *uvc);
 
diff --git a/drivers/usb/gadget/legacy/webcam.c b/drivers/usb/gadget/legacy/webcam.c
index c06dd1af7a0c..c395438d3978 100644
--- a/drivers/usb/gadget/legacy/webcam.c
+++ b/drivers/usb/gadget/legacy/webcam.c
@@ -12,6 +12,7 @@
 #include <linux/usb/video.h>
 
 #include "u_uvc.h"
+#include "uvc_configfs.h"
 
 USB_GADGET_COMPOSITE_OPTIONS();
 
@@ -84,8 +85,6 @@ static struct usb_device_descriptor webcam_device_descriptor = {
 	.bNumConfigurations	= 0, /* dynamic */
 };
 
-DECLARE_UVC_HEADER_DESCRIPTOR(1);
-
 static const struct UVC_HEADER_DESCRIPTOR(1) uvc_control_header = {
 	.bLength		= UVC_DT_HEADER_SIZE(1),
 	.bDescriptorType	= USB_DT_CS_INTERFACE,
@@ -158,43 +157,112 @@ static const struct UVC_INPUT_HEADER_DESCRIPTOR(1, 2) uvc_input_header = {
 	.bmaControls[1][0]	= 4,
 };
 
-static const struct uvc_format_uncompressed uvc_format_yuv = {
-	.bLength		= UVC_DT_FORMAT_UNCOMPRESSED_SIZE,
-	.bDescriptorType	= USB_DT_CS_INTERFACE,
-	.bDescriptorSubType	= UVC_VS_FORMAT_UNCOMPRESSED,
-	.bFormatIndex		= 1,
-	.bNumFrameDescriptors	= 2,
-	.guidFormat		=
-		{ 'Y',  'U',  'Y',  '2', 0x00, 0x00, 0x10, 0x00,
-		 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71},
-	.bBitsPerPixel		= 16,
-	.bDefaultFrameIndex	= 1,
-	.bAspectRatioX		= 0,
-	.bAspectRatioY		= 0,
-	.bmInterlaceFlags	= 0,
-	.bCopyProtect		= 0,
+static const struct uvcg_color_matching uvcg_color_matching = {
+	.desc = {
+		.bLength		= UVC_DT_COLOR_MATCHING_SIZE,
+		.bDescriptorType	= USB_DT_CS_INTERFACE,
+		.bDescriptorSubType	= UVC_VS_COLORFORMAT,
+		.bColorPrimaries	= 1,
+		.bTransferCharacteristics	= 1,
+		.bMatrixCoefficients	= 4,
+	},
+};
+
+static struct uvcg_uncompressed uvcg_format_yuv = {
+	.fmt = {
+		.type			= UVCG_UNCOMPRESSED,
+		/* add to .frames and fill .num_frames at runtime */
+		.color_matching		= (struct uvcg_color_matching *)&uvcg_color_matching,
+	},
+	.desc = {
+		.bLength		= UVC_DT_FORMAT_UNCOMPRESSED_SIZE,
+		.bDescriptorType	= USB_DT_CS_INTERFACE,
+		.bDescriptorSubType	= UVC_VS_FORMAT_UNCOMPRESSED,
+		.bFormatIndex		= 1,
+		.bNumFrameDescriptors	= 2,
+		.guidFormat		= {
+			'Y',  'U',  'Y',  '2', 0x00, 0x00, 0x10, 0x00,
+			 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71
+		},
+		.bBitsPerPixel		= 16,
+		.bDefaultFrameIndex	= 1,
+		.bAspectRatioX		= 0,
+		.bAspectRatioY		= 0,
+		.bmInterlaceFlags	= 0,
+		.bCopyProtect		= 0,
+	},
+};
+
+static struct uvcg_format_ptr uvcg_format_ptr_yuv = {
+	.fmt = &uvcg_format_yuv.fmt,
 };
 
 DECLARE_UVC_FRAME_UNCOMPRESSED(1);
 DECLARE_UVC_FRAME_UNCOMPRESSED(3);
 
+#define UVCG_WIDTH_360P			640
+#define UVCG_HEIGHT_360P		360
+#define UVCG_MIN_BITRATE_360P		18432000
+#define UVCG_MAX_BITRATE_360P		55296000
+#define UVCG_MAX_VIDEO_FB_SZ_360P	460800
+#define UVCG_FRM_INTERV_0_360P		666666
+#define UVCG_FRM_INTERV_1_360P		1000000
+#define UVCG_FRM_INTERV_2_360P		5000000
+#define UVCG_DEFAULT_FRM_INTERV_360P	UVCG_FRM_INTERV_0_360P
+
 static const struct UVC_FRAME_UNCOMPRESSED(3) uvc_frame_yuv_360p = {
 	.bLength		= UVC_DT_FRAME_UNCOMPRESSED_SIZE(3),
 	.bDescriptorType	= USB_DT_CS_INTERFACE,
 	.bDescriptorSubType	= UVC_VS_FRAME_UNCOMPRESSED,
 	.bFrameIndex		= 1,
 	.bmCapabilities		= 0,
-	.wWidth			= cpu_to_le16(640),
-	.wHeight		= cpu_to_le16(360),
-	.dwMinBitRate		= cpu_to_le32(18432000),
-	.dwMaxBitRate		= cpu_to_le32(55296000),
-	.dwMaxVideoFrameBufferSize	= cpu_to_le32(460800),
-	.dwDefaultFrameInterval	= cpu_to_le32(666666),
+	.wWidth			= cpu_to_le16(UVCG_WIDTH_360P),
+	.wHeight		= cpu_to_le16(UVCG_HEIGHT_360P),
+	.dwMinBitRate		= cpu_to_le32(UVCG_MIN_BITRATE_360P),
+	.dwMaxBitRate		= cpu_to_le32(UVCG_MAX_BITRATE_360P),
+	.dwMaxVideoFrameBufferSize	= cpu_to_le32(UVCG_MAX_VIDEO_FB_SZ_360P),
+	.dwDefaultFrameInterval	= cpu_to_le32(UVCG_DEFAULT_FRM_INTERV_360P),
 	.bFrameIntervalType	= 3,
-	.dwFrameInterval[0]	= cpu_to_le32(666666),
-	.dwFrameInterval[1]	= cpu_to_le32(1000000),
-	.dwFrameInterval[2]	= cpu_to_le32(5000000),
+	.dwFrameInterval[0]	= cpu_to_le32(UVCG_FRM_INTERV_0_360P),
+	.dwFrameInterval[1]	= cpu_to_le32(UVCG_FRM_INTERV_1_360P),
+	.dwFrameInterval[2]	= cpu_to_le32(UVCG_FRM_INTERV_2_360P),
+};
+
+static u32 uvcg_frame_yuv_360p_dw_frame_interval[] = {
+	[0] = UVCG_FRM_INTERV_0_360P,
+	[1] = UVCG_FRM_INTERV_1_360P,
+	[2] = UVCG_FRM_INTERV_2_360P,
+};
+
+static const struct uvcg_frame uvcg_frame_yuv_360p = {
+	.fmt_type		= UVCG_UNCOMPRESSED,
+	.frame = {
+		.b_length			= UVC_DT_FRAME_UNCOMPRESSED_SIZE(3),
+		.b_descriptor_type		= USB_DT_CS_INTERFACE,
+		.b_descriptor_subtype		= UVC_VS_FRAME_UNCOMPRESSED,
+		.b_frame_index			= 1,
+		.bm_capabilities		= 0,
+		.w_width			= UVCG_WIDTH_360P,
+		.w_height			= UVCG_HEIGHT_360P,
+		.dw_min_bit_rate		= UVCG_MIN_BITRATE_360P,
+		.dw_max_bit_rate		= UVCG_MAX_BITRATE_360P,
+		.dw_max_video_frame_buffer_size	= UVCG_MAX_VIDEO_FB_SZ_360P,
+		.dw_default_frame_interval	= UVCG_DEFAULT_FRM_INTERV_360P,
+		.b_frame_interval_type		= 3,
+	},
+	.dw_frame_interval	= uvcg_frame_yuv_360p_dw_frame_interval,
+};
+
+static struct uvcg_frame_ptr uvcg_frame_ptr_yuv_360p = {
+	.frm = (struct uvcg_frame *)&uvcg_frame_yuv_360p,
 };
+#define UVCG_WIDTH_720P			1280
+#define UVCG_HEIGHT_720P		720
+#define UVCG_MIN_BITRATE_720P		29491200
+#define UVCG_MAX_BITRATE_720P		29491200
+#define UVCG_MAX_VIDEO_FB_SZ_720P	1843200
+#define UVCG_FRM_INTERV_0_720P		5000000
+#define UVCG_DEFAULT_FRM_INTERV_720P	UVCG_FRM_INTERV_0_720P
 
 static const struct UVC_FRAME_UNCOMPRESSED(1) uvc_frame_yuv_720p = {
 	.bLength		= UVC_DT_FRAME_UNCOMPRESSED_SIZE(1),
@@ -202,28 +270,66 @@ static const struct UVC_FRAME_UNCOMPRESSED(1) uvc_frame_yuv_720p = {
 	.bDescriptorSubType	= UVC_VS_FRAME_UNCOMPRESSED,
 	.bFrameIndex		= 2,
 	.bmCapabilities		= 0,
-	.wWidth			= cpu_to_le16(1280),
-	.wHeight		= cpu_to_le16(720),
-	.dwMinBitRate		= cpu_to_le32(29491200),
-	.dwMaxBitRate		= cpu_to_le32(29491200),
-	.dwMaxVideoFrameBufferSize	= cpu_to_le32(1843200),
-	.dwDefaultFrameInterval	= cpu_to_le32(5000000),
+	.wWidth			= cpu_to_le16(UVCG_WIDTH_720P),
+	.wHeight		= cpu_to_le16(UVCG_HEIGHT_720P),
+	.dwMinBitRate		= cpu_to_le32(UVCG_MIN_BITRATE_720P),
+	.dwMaxBitRate		= cpu_to_le32(UVCG_MAX_BITRATE_720P),
+	.dwMaxVideoFrameBufferSize	= cpu_to_le32(UVCG_MAX_VIDEO_FB_SZ_720P),
+	.dwDefaultFrameInterval	= cpu_to_le32(UVCG_DEFAULT_FRM_INTERV_720P),
 	.bFrameIntervalType	= 1,
-	.dwFrameInterval[0]	= cpu_to_le32(5000000),
+	.dwFrameInterval[0]	= cpu_to_le32(UVCG_FRM_INTERV_0_720P),
 };
 
-static const struct uvc_format_mjpeg uvc_format_mjpg = {
-	.bLength		= UVC_DT_FORMAT_MJPEG_SIZE,
-	.bDescriptorType	= USB_DT_CS_INTERFACE,
-	.bDescriptorSubType	= UVC_VS_FORMAT_MJPEG,
-	.bFormatIndex		= 2,
-	.bNumFrameDescriptors	= 2,
-	.bmFlags		= 0,
-	.bDefaultFrameIndex	= 1,
-	.bAspectRatioX		= 0,
-	.bAspectRatioY		= 0,
-	.bmInterlaceFlags	= 0,
-	.bCopyProtect		= 0,
+static u32 uvcg_frame_yuv_720p_dw_frame_interval[] = {
+	[0] = UVCG_FRM_INTERV_0_720P,
+};
+
+static const struct uvcg_frame uvcg_frame_yuv_720p = {
+	.fmt_type		= UVCG_UNCOMPRESSED,
+	.frame = {
+		.b_length			= UVC_DT_FRAME_UNCOMPRESSED_SIZE(1),
+		.b_descriptor_type		= USB_DT_CS_INTERFACE,
+		.b_descriptor_subtype		= UVC_VS_FRAME_UNCOMPRESSED,
+		.b_frame_index			= 2,
+		.bm_capabilities		= 0,
+		.w_width			= UVCG_WIDTH_720P,
+		.w_height			= UVCG_HEIGHT_720P,
+		.dw_min_bit_rate		= UVCG_MIN_BITRATE_720P,
+		.dw_max_bit_rate		= UVCG_MAX_BITRATE_720P,
+		.dw_max_video_frame_buffer_size	= UVCG_MAX_VIDEO_FB_SZ_720P,
+		.dw_default_frame_interval	= UVCG_DEFAULT_FRM_INTERV_720P,
+		.b_frame_interval_type		= 1,
+	},
+	.dw_frame_interval	= uvcg_frame_yuv_720p_dw_frame_interval,
+};
+
+static struct uvcg_frame_ptr uvcg_frame_ptr_yuv_720p = {
+	.frm = (struct uvcg_frame *)&uvcg_frame_yuv_720p,
+};
+
+static struct uvcg_mjpeg uvcg_format_mjpeg = {
+	.fmt = {
+		.type			= UVCG_MJPEG,
+		/* add to .frames and fill .num_frames at runtime */
+		.color_matching		= (struct uvcg_color_matching *)&uvcg_color_matching,
+	},
+	.desc = {
+		.bLength		= UVC_DT_FORMAT_MJPEG_SIZE,
+		.bDescriptorType	= USB_DT_CS_INTERFACE,
+		.bDescriptorSubType	= UVC_VS_FORMAT_MJPEG,
+		.bFormatIndex		= 2,
+		.bNumFrameDescriptors	= 2,
+		.bmFlags		= 0,
+		.bDefaultFrameIndex	= 1,
+		.bAspectRatioX		= 0,
+		.bAspectRatioY		= 0,
+		.bmInterlaceFlags	= 0,
+		.bCopyProtect		= 0,
+	},
+};
+
+static struct uvcg_format_ptr uvcg_format_ptr_mjpeg = {
+	.fmt = &uvcg_format_mjpeg.fmt,
 };
 
 DECLARE_UVC_FRAME_MJPEG(1);
@@ -235,16 +341,45 @@ static const struct UVC_FRAME_MJPEG(3) uvc_frame_mjpg_360p = {
 	.bDescriptorSubType	= UVC_VS_FRAME_MJPEG,
 	.bFrameIndex		= 1,
 	.bmCapabilities		= 0,
-	.wWidth			= cpu_to_le16(640),
-	.wHeight		= cpu_to_le16(360),
-	.dwMinBitRate		= cpu_to_le32(18432000),
-	.dwMaxBitRate		= cpu_to_le32(55296000),
-	.dwMaxVideoFrameBufferSize	= cpu_to_le32(460800),
-	.dwDefaultFrameInterval	= cpu_to_le32(666666),
+	.wWidth			= cpu_to_le16(UVCG_WIDTH_360P),
+	.wHeight		= cpu_to_le16(UVCG_HEIGHT_360P),
+	.dwMinBitRate		= cpu_to_le32(UVCG_MIN_BITRATE_360P),
+	.dwMaxBitRate		= cpu_to_le32(UVCG_MAX_BITRATE_360P),
+	.dwMaxVideoFrameBufferSize	= cpu_to_le32(UVCG_MAX_VIDEO_FB_SZ_360P),
+	.dwDefaultFrameInterval	= cpu_to_le32(UVCG_DEFAULT_FRM_INTERV_360P),
 	.bFrameIntervalType	= 3,
-	.dwFrameInterval[0]	= cpu_to_le32(666666),
-	.dwFrameInterval[1]	= cpu_to_le32(1000000),
-	.dwFrameInterval[2]	= cpu_to_le32(5000000),
+	.dwFrameInterval[0]	= cpu_to_le32(UVCG_FRM_INTERV_0_360P),
+	.dwFrameInterval[1]	= cpu_to_le32(UVCG_FRM_INTERV_1_360P),
+	.dwFrameInterval[2]	= cpu_to_le32(UVCG_FRM_INTERV_2_360P),
+};
+
+static u32 uvcg_frame_mjpeg_360p_dw_frame_interval[] = {
+	[0] = UVCG_FRM_INTERV_0_360P,
+	[1] = UVCG_FRM_INTERV_1_360P,
+	[2] = UVCG_FRM_INTERV_2_360P,
+};
+
+static const struct uvcg_frame uvcg_frame_mjpeg_360p = {
+	.fmt_type		= UVCG_MJPEG,
+	.frame = {
+		.b_length			= UVC_DT_FRAME_MJPEG_SIZE(3),
+		.b_descriptor_type		= USB_DT_CS_INTERFACE,
+		.b_descriptor_subtype		= UVC_VS_FRAME_MJPEG,
+		.b_frame_index			= 1,
+		.bm_capabilities		= 0,
+		.w_width			= UVCG_WIDTH_360P,
+		.w_height			= UVCG_HEIGHT_360P,
+		.dw_min_bit_rate		= UVCG_MIN_BITRATE_360P,
+		.dw_max_bit_rate		= UVCG_MAX_BITRATE_360P,
+		.dw_max_video_frame_buffer_size	= UVCG_MAX_VIDEO_FB_SZ_360P,
+		.dw_default_frame_interval	= UVCG_DEFAULT_FRM_INTERV_360P,
+		.b_frame_interval_type		= 3,
+	},
+	.dw_frame_interval	= uvcg_frame_mjpeg_360p_dw_frame_interval,
+};
+
+static struct uvcg_frame_ptr uvcg_frame_ptr_mjpeg_360p = {
+	.frm = (struct uvcg_frame *)&uvcg_frame_mjpeg_360p,
 };
 
 static const struct UVC_FRAME_MJPEG(1) uvc_frame_mjpg_720p = {
@@ -253,23 +388,44 @@ static const struct UVC_FRAME_MJPEG(1) uvc_frame_mjpg_720p = {
 	.bDescriptorSubType	= UVC_VS_FRAME_MJPEG,
 	.bFrameIndex		= 2,
 	.bmCapabilities		= 0,
-	.wWidth			= cpu_to_le16(1280),
-	.wHeight		= cpu_to_le16(720),
-	.dwMinBitRate		= cpu_to_le32(29491200),
-	.dwMaxBitRate		= cpu_to_le32(29491200),
-	.dwMaxVideoFrameBufferSize	= cpu_to_le32(1843200),
-	.dwDefaultFrameInterval	= cpu_to_le32(5000000),
+	.wWidth			= cpu_to_le16(UVCG_WIDTH_720P),
+	.wHeight		= cpu_to_le16(UVCG_HEIGHT_720P),
+	.dwMinBitRate		= cpu_to_le32(UVCG_MIN_BITRATE_720P),
+	.dwMaxBitRate		= cpu_to_le32(UVCG_MAX_BITRATE_720P),
+	.dwMaxVideoFrameBufferSize	= cpu_to_le32(UVCG_MAX_VIDEO_FB_SZ_720P),
+	.dwDefaultFrameInterval	= cpu_to_le32(UVCG_DEFAULT_FRM_INTERV_720P),
 	.bFrameIntervalType	= 1,
-	.dwFrameInterval[0]	= cpu_to_le32(5000000),
+	.dwFrameInterval[0]	= cpu_to_le32(UVCG_FRM_INTERV_0_720P),
 };
 
-static const struct uvc_color_matching_descriptor uvc_color_matching = {
-	.bLength		= UVC_DT_COLOR_MATCHING_SIZE,
-	.bDescriptorType	= USB_DT_CS_INTERFACE,
-	.bDescriptorSubType	= UVC_VS_COLORFORMAT,
-	.bColorPrimaries	= 1,
-	.bTransferCharacteristics	= 1,
-	.bMatrixCoefficients	= 4,
+static u32 uvcg_frame_mjpeg_720p_dw_frame_interval[] = {
+	[0] = UVCG_FRM_INTERV_0_720P,
+};
+
+static const struct uvcg_frame uvcg_frame_mjpeg_720p = {
+	.fmt_type		= UVCG_MJPEG,
+	.frame = {
+		.b_length			= UVC_DT_FRAME_MJPEG_SIZE(1),
+		.b_descriptor_type		= USB_DT_CS_INTERFACE,
+		.b_descriptor_subtype		= UVC_VS_FRAME_MJPEG,
+		.b_frame_index			= 2,
+		.bm_capabilities		= 0,
+		.w_width			= UVCG_WIDTH_720P,
+		.w_height			= UVCG_HEIGHT_720P,
+		.dw_min_bit_rate		= UVCG_MIN_BITRATE_720P,
+		.dw_max_bit_rate		= UVCG_MAX_BITRATE_720P,
+		.dw_max_video_frame_buffer_size	= UVCG_MAX_VIDEO_FB_SZ_720P,
+		.dw_default_frame_interval	= UVCG_DEFAULT_FRM_INTERV_720P,
+		.b_frame_interval_type		= 1,
+	},
+	.dw_frame_interval	= uvcg_frame_mjpeg_720p_dw_frame_interval,
+};
+
+static struct uvcg_frame_ptr uvcg_frame_ptr_mjpeg_720p = {
+	.frm = (struct uvcg_frame *)&uvcg_frame_mjpeg_720p,
+};
+
+static struct uvcg_streaming_header uvcg_streaming_header = {
 };
 
 static const struct uvc_descriptor_header * const uvc_fs_control_cls[] = {
@@ -290,40 +446,40 @@ static const struct uvc_descriptor_header * const uvc_ss_control_cls[] = {
 
 static const struct uvc_descriptor_header * const uvc_fs_streaming_cls[] = {
 	(const struct uvc_descriptor_header *) &uvc_input_header,
-	(const struct uvc_descriptor_header *) &uvc_format_yuv,
+	(const struct uvc_descriptor_header *) &uvcg_format_yuv.desc,
 	(const struct uvc_descriptor_header *) &uvc_frame_yuv_360p,
 	(const struct uvc_descriptor_header *) &uvc_frame_yuv_720p,
-	(const struct uvc_descriptor_header *) &uvc_color_matching,
-	(const struct uvc_descriptor_header *) &uvc_format_mjpg,
+	(const struct uvc_descriptor_header *) &uvcg_color_matching.desc,
+	(const struct uvc_descriptor_header *) &uvcg_format_mjpeg.desc,
 	(const struct uvc_descriptor_header *) &uvc_frame_mjpg_360p,
 	(const struct uvc_descriptor_header *) &uvc_frame_mjpg_720p,
-	(const struct uvc_descriptor_header *) &uvc_color_matching,
+	(const struct uvc_descriptor_header *) &uvcg_color_matching.desc,
 	NULL,
 };
 
 static const struct uvc_descriptor_header * const uvc_hs_streaming_cls[] = {
 	(const struct uvc_descriptor_header *) &uvc_input_header,
-	(const struct uvc_descriptor_header *) &uvc_format_yuv,
+	(const struct uvc_descriptor_header *) &uvcg_format_yuv.desc,
 	(const struct uvc_descriptor_header *) &uvc_frame_yuv_360p,
 	(const struct uvc_descriptor_header *) &uvc_frame_yuv_720p,
-	(const struct uvc_descriptor_header *) &uvc_color_matching,
-	(const struct uvc_descriptor_header *) &uvc_format_mjpg,
+	(const struct uvc_descriptor_header *) &uvcg_color_matching.desc,
+	(const struct uvc_descriptor_header *) &uvcg_format_mjpeg.desc,
 	(const struct uvc_descriptor_header *) &uvc_frame_mjpg_360p,
 	(const struct uvc_descriptor_header *) &uvc_frame_mjpg_720p,
-	(const struct uvc_descriptor_header *) &uvc_color_matching,
+	(const struct uvc_descriptor_header *) &uvcg_color_matching.desc,
 	NULL,
 };
 
 static const struct uvc_descriptor_header * const uvc_ss_streaming_cls[] = {
 	(const struct uvc_descriptor_header *) &uvc_input_header,
-	(const struct uvc_descriptor_header *) &uvc_format_yuv,
+	(const struct uvc_descriptor_header *) &uvcg_format_yuv.desc,
 	(const struct uvc_descriptor_header *) &uvc_frame_yuv_360p,
 	(const struct uvc_descriptor_header *) &uvc_frame_yuv_720p,
-	(const struct uvc_descriptor_header *) &uvc_color_matching,
-	(const struct uvc_descriptor_header *) &uvc_format_mjpg,
+	(const struct uvc_descriptor_header *) &uvcg_color_matching.desc,
+	(const struct uvc_descriptor_header *) &uvcg_format_mjpeg.desc,
 	(const struct uvc_descriptor_header *) &uvc_frame_mjpg_360p,
 	(const struct uvc_descriptor_header *) &uvc_frame_mjpg_720p,
-	(const struct uvc_descriptor_header *) &uvc_color_matching,
+	(const struct uvc_descriptor_header *) &uvcg_color_matching.desc,
 	NULL,
 };
 
@@ -387,6 +543,23 @@ webcam_bind(struct usb_composite_dev *cdev)
 	uvc_opts->hs_streaming = uvc_hs_streaming_cls;
 	uvc_opts->ss_streaming = uvc_ss_streaming_cls;
 
+	INIT_LIST_HEAD(&uvcg_format_yuv.fmt.frames);
+	list_add_tail(&uvcg_frame_ptr_yuv_360p.entry, &uvcg_format_yuv.fmt.frames);
+	list_add_tail(&uvcg_frame_ptr_yuv_720p.entry, &uvcg_format_yuv.fmt.frames);
+	uvcg_format_yuv.fmt.num_frames = 2;
+
+	INIT_LIST_HEAD(&uvcg_format_mjpeg.fmt.frames);
+	list_add_tail(&uvcg_frame_ptr_mjpeg_360p.entry, &uvcg_format_mjpeg.fmt.frames);
+	list_add_tail(&uvcg_frame_ptr_mjpeg_720p.entry, &uvcg_format_mjpeg.fmt.frames);
+	uvcg_format_mjpeg.fmt.num_frames = 2;
+
+	INIT_LIST_HEAD(&uvcg_streaming_header.formats);
+	list_add_tail(&uvcg_format_ptr_yuv.entry, &uvcg_streaming_header.formats);
+	list_add_tail(&uvcg_format_ptr_mjpeg.entry, &uvcg_streaming_header.formats);
+	uvcg_streaming_header.num_fmt = 2;
+
+	uvc_opts->header = &uvcg_streaming_header;
+
 	/* Allocate string descriptor numbers ... note that string contents
 	 * can be overridden by the composite_dev glue.
 	 */
diff --git a/drivers/usb/gadget/udc/at91_udc.c b/drivers/usb/gadget/udc/at91_udc.c
index 30ea4a9d5301..e3bf17a98b38 100644
--- a/drivers/usb/gadget/udc/at91_udc.c
+++ b/drivers/usb/gadget/udc/at91_udc.c
@@ -1924,7 +1924,7 @@ err_unprepare_fclk:
 	return retval;
 }
 
-static int at91udc_remove(struct platform_device *pdev)
+static void at91udc_remove(struct platform_device *pdev)
 {
 	struct at91_udc *udc = platform_get_drvdata(pdev);
 	unsigned long	flags;
@@ -1932,8 +1932,11 @@ static int at91udc_remove(struct platform_device *pdev)
 	DBG("remove\n");
 
 	usb_del_gadget_udc(&udc->gadget);
-	if (udc->driver)
-		return -EBUSY;
+	if (udc->driver) {
+		dev_err(&pdev->dev,
+			"Driver still in use but removing anyhow\n");
+		return;
+	}
 
 	spin_lock_irqsave(&udc->lock, flags);
 	pullup(udc, 0);
@@ -1943,8 +1946,6 @@ static int at91udc_remove(struct platform_device *pdev)
 	remove_debug_file(udc);
 	clk_unprepare(udc->fclk);
 	clk_unprepare(udc->iclk);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -2001,7 +2002,7 @@ static int at91udc_resume(struct platform_device *pdev)
 
 static struct platform_driver at91_udc_driver = {
 	.probe		= at91udc_probe,
-	.remove		= at91udc_remove,
+	.remove_new	= at91udc_remove,
 	.shutdown	= at91udc_shutdown,
 	.suspend	= at91udc_suspend,
 	.resume		= at91udc_resume,
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index 02b1bef5e22e..b76885d78e8a 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -94,7 +94,7 @@ static ssize_t queue_dbg_read(struct file *file, char __user *buf,
 
 	inode_lock(file_inode(file));
 	list_for_each_entry_safe(req, tmp_req, queue, queue) {
-		len = snprintf(tmpbuf, sizeof(tmpbuf),
+		len = scnprintf(tmpbuf, sizeof(tmpbuf),
 				"%8p %08x %c%c%c %5d %c%c%c\n",
 				req->req.buf, req->req.length,
 				req->req.no_interrupt ? 'i' : 'I',
@@ -104,7 +104,6 @@ static ssize_t queue_dbg_read(struct file *file, char __user *buf,
 				req->submitted ? 'F' : 'f',
 				req->using_dma ? 'D' : 'd',
 				req->last_transaction ? 'L' : 'l');
-		len = min(len, sizeof(tmpbuf));
 		if (len > nbytes)
 			break;
 
diff --git a/drivers/usb/gadget/udc/cdns2/cdns2-debug.h b/drivers/usb/gadget/udc/cdns2/cdns2-debug.h
index be9ae0d28a40..f5f330004190 100644
--- a/drivers/usb/gadget/udc/cdns2/cdns2-debug.h
+++ b/drivers/usb/gadget/udc/cdns2/cdns2-debug.h
@@ -16,34 +16,34 @@ static inline const char *cdns2_decode_usb_irq(char *str, size_t size,
 {
 	int ret;
 
-	ret = snprintf(str, size, "usbirq: 0x%02x - ", usb_irq);
+	ret = scnprintf(str, size, "usbirq: 0x%02x - ", usb_irq);
 
 	if (usb_irq & USBIRQ_SOF)
-		ret += snprintf(str + ret, size - ret, "SOF ");
+		ret += scnprintf(str + ret, size - ret, "SOF ");
 	if (usb_irq & USBIRQ_SUTOK)
-		ret += snprintf(str + ret, size - ret, "SUTOK ");
+		ret += scnprintf(str + ret, size - ret, "SUTOK ");
 	if (usb_irq & USBIRQ_SUDAV)
-		ret += snprintf(str + ret, size - ret, "SETUP ");
+		ret += scnprintf(str + ret, size - ret, "SETUP ");
 	if (usb_irq & USBIRQ_SUSPEND)
-		ret += snprintf(str + ret, size - ret, "Suspend ");
+		ret += scnprintf(str + ret, size - ret, "Suspend ");
 	if (usb_irq & USBIRQ_URESET)
-		ret += snprintf(str + ret, size - ret, "Reset ");
+		ret += scnprintf(str + ret, size - ret, "Reset ");
 	if (usb_irq & USBIRQ_HSPEED)
-		ret += snprintf(str + ret, size - ret, "HS ");
+		ret += scnprintf(str + ret, size - ret, "HS ");
 	if (usb_irq & USBIRQ_LPM)
-		ret += snprintf(str + ret, size - ret, "LPM ");
+		ret += scnprintf(str + ret, size - ret, "LPM ");
 
-	ret += snprintf(str + ret, size - ret, ", EXT: 0x%02x - ", ext_irq);
+	ret += scnprintf(str + ret, size - ret, ", EXT: 0x%02x - ", ext_irq);
 
 	if (ext_irq & EXTIRQ_WAKEUP)
-		ret += snprintf(str + ret, size - ret, "Wakeup ");
+		ret += scnprintf(str + ret, size - ret, "Wakeup ");
 	if (ext_irq & EXTIRQ_VBUSFAULT_FALL)
-		ret += snprintf(str + ret, size - ret, "VBUS_FALL ");
+		ret += scnprintf(str + ret, size - ret, "VBUS_FALL ");
 	if (ext_irq & EXTIRQ_VBUSFAULT_RISE)
-		ret += snprintf(str + ret, size - ret, "VBUS_RISE ");
+		ret += scnprintf(str + ret, size - ret, "VBUS_RISE ");
 
-	if (ret >= size)
-		pr_info("CDNS2: buffer overflowed.\n");
+	if (ret == size - 1)
+		pr_info("CDNS2: buffer may be truncated.\n");
 
 	return str;
 }
@@ -54,28 +54,28 @@ static inline const char *cdns2_decode_dma_irq(char *str, size_t size,
 {
 	int ret;
 
-	ret = snprintf(str, size, "ISTS: %08x, %s: %08x ",
-		       ep_ists, ep_name, ep_sts);
+	ret = scnprintf(str, size, "ISTS: %08x, %s: %08x ",
+			ep_ists, ep_name, ep_sts);
 
 	if (ep_sts & DMA_EP_STS_IOC)
-		ret += snprintf(str + ret, size - ret, "IOC ");
+		ret += scnprintf(str + ret, size - ret, "IOC ");
 	if (ep_sts & DMA_EP_STS_ISP)
-		ret += snprintf(str + ret, size - ret, "ISP ");
+		ret += scnprintf(str + ret, size - ret, "ISP ");
 	if (ep_sts & DMA_EP_STS_DESCMIS)
-		ret += snprintf(str + ret, size - ret, "DESCMIS ");
+		ret += scnprintf(str + ret, size - ret, "DESCMIS ");
 	if (ep_sts & DMA_EP_STS_TRBERR)
-		ret += snprintf(str + ret, size - ret, "TRBERR ");
+		ret += scnprintf(str + ret, size - ret, "TRBERR ");
 	if (ep_sts & DMA_EP_STS_OUTSMM)
-		ret += snprintf(str + ret, size - ret, "OUTSMM ");
+		ret += scnprintf(str + ret, size - ret, "OUTSMM ");
 	if (ep_sts & DMA_EP_STS_ISOERR)
-		ret += snprintf(str + ret, size - ret, "ISOERR ");
+		ret += scnprintf(str + ret, size - ret, "ISOERR ");
 	if (ep_sts & DMA_EP_STS_DBUSY)
-		ret += snprintf(str + ret, size - ret, "DBUSY ");
+		ret += scnprintf(str + ret, size - ret, "DBUSY ");
 	if (DMA_EP_STS_CCS(ep_sts))
-		ret += snprintf(str + ret, size - ret, "CCS ");
+		ret += scnprintf(str + ret, size - ret, "CCS ");
 
-	if (ret >= size)
-		pr_info("CDNS2: buffer overflowed.\n");
+	if (ret == size - 1)
+		pr_info("CDNS2: buffer may be truncated.\n");
 
 	return str;
 }
@@ -105,43 +105,43 @@ static inline const char *cdns2_raw_ring(struct cdns2_endpoint *pep,
 	int ret;
 	int i;
 
-	ret = snprintf(str, size, "\n\t\tTR for %s:", pep->name);
+	ret = scnprintf(str, size, "\n\t\tTR for %s:", pep->name);
 
 	trb = &trbs[ring->dequeue];
 	dma = cdns2_trb_virt_to_dma(pep, trb);
-	ret += snprintf(str + ret, size - ret,
-			"\n\t\tRing deq index: %d, trb: V=%p, P=0x%pad\n",
-			ring->dequeue, trb, &dma);
+	ret += scnprintf(str + ret, size - ret,
+			 "\n\t\tRing deq index: %d, trb: V=%p, P=0x%pad\n",
+			 ring->dequeue, trb, &dma);
 
 	trb = &trbs[ring->enqueue];
 	dma = cdns2_trb_virt_to_dma(pep, trb);
-	ret += snprintf(str + ret, size - ret,
-			"\t\tRing enq index: %d, trb: V=%p, P=0x%pad\n",
-			ring->enqueue, trb, &dma);
+	ret += scnprintf(str + ret, size - ret,
+			 "\t\tRing enq index: %d, trb: V=%p, P=0x%pad\n",
+			 ring->enqueue, trb, &dma);
 
-	ret += snprintf(str + ret, size - ret,
-			"\t\tfree trbs: %d, CCS=%d, PCS=%d\n",
-			ring->free_trbs, ring->ccs, ring->pcs);
+	ret += scnprintf(str + ret, size - ret,
+			 "\t\tfree trbs: %d, CCS=%d, PCS=%d\n",
+			 ring->free_trbs, ring->ccs, ring->pcs);
 
 	if (TRBS_PER_SEGMENT > 40) {
-		ret += snprintf(str + ret, size - ret,
-				"\t\tTransfer ring %d too big\n", TRBS_PER_SEGMENT);
+		ret += scnprintf(str + ret, size - ret,
+				 "\t\tTransfer ring %d too big\n", TRBS_PER_SEGMENT);
 		return str;
 	}
 
 	dma = ring->dma;
 	for (i = 0; i < TRBS_PER_SEGMENT; ++i) {
 		trb = &trbs[i];
-		ret += snprintf(str + ret, size - ret,
-				"\t\t@%pad %08x %08x %08x\n", &dma,
-				le32_to_cpu(trb->buffer),
-				le32_to_cpu(trb->length),
-				le32_to_cpu(trb->control));
+		ret += scnprintf(str + ret, size - ret,
+				 "\t\t@%pad %08x %08x %08x\n", &dma,
+				 le32_to_cpu(trb->buffer),
+				 le32_to_cpu(trb->length),
+				 le32_to_cpu(trb->control));
 		dma += sizeof(*trb);
 	}
 
-	if (ret >= size)
-		pr_info("CDNS2: buffer overflowed.\n");
+	if (ret == size - 1)
+		pr_info("CDNS2: buffer may be truncated.\n");
 
 	return str;
 }
@@ -166,36 +166,36 @@ static inline const char *cdns2_decode_trb(char *str, size_t size, u32 flags,
 
 	switch (type) {
 	case TRB_LINK:
-		ret = snprintf(str, size,
-			       "LINK %08x type '%s' flags %c:%c:%c%c:%c",
-			       buffer, cdns2_trb_type_string(type),
-			       flags & TRB_CYCLE ? 'C' : 'c',
-			       flags & TRB_TOGGLE ? 'T' : 't',
-			       flags & TRB_CHAIN ? 'C' : 'c',
-			       flags & TRB_CHAIN ? 'H' : 'h',
-			       flags & TRB_IOC ? 'I' : 'i');
+		ret = scnprintf(str, size,
+				"LINK %08x type '%s' flags %c:%c:%c%c:%c",
+				buffer, cdns2_trb_type_string(type),
+				flags & TRB_CYCLE ? 'C' : 'c',
+				flags & TRB_TOGGLE ? 'T' : 't',
+				flags & TRB_CHAIN ? 'C' : 'c',
+				flags & TRB_CHAIN ? 'H' : 'h',
+				flags & TRB_IOC ? 'I' : 'i');
 		break;
 	case TRB_NORMAL:
-		ret = snprintf(str, size,
-			       "type: '%s', Buffer: %08x, length: %ld, burst len: %ld, "
-			       "flags %c:%c:%c%c:%c",
-			       cdns2_trb_type_string(type),
-			       buffer, TRB_LEN(length),
-			       TRB_FIELD_TO_BURST(length),
-			       flags & TRB_CYCLE ? 'C' : 'c',
-			       flags & TRB_ISP ? 'I' : 'i',
-			       flags & TRB_CHAIN ? 'C' : 'c',
-			       flags & TRB_CHAIN ? 'H' : 'h',
-			       flags & TRB_IOC ? 'I' : 'i');
+		ret = scnprintf(str, size,
+				"type: '%s', Buffer: %08x, length: %ld, burst len: %ld, "
+				"flags %c:%c:%c%c:%c",
+				cdns2_trb_type_string(type),
+				buffer, TRB_LEN(length),
+				TRB_FIELD_TO_BURST(length),
+				flags & TRB_CYCLE ? 'C' : 'c',
+				flags & TRB_ISP ? 'I' : 'i',
+				flags & TRB_CHAIN ? 'C' : 'c',
+				flags & TRB_CHAIN ? 'H' : 'h',
+				flags & TRB_IOC ? 'I' : 'i');
 		break;
 	default:
-		ret = snprintf(str, size, "type '%s' -> raw %08x %08x %08x",
-			       cdns2_trb_type_string(type),
-			       buffer, length, flags);
+		ret = scnprintf(str, size, "type '%s' -> raw %08x %08x %08x",
+				cdns2_trb_type_string(type),
+				buffer, length, flags);
 	}
 
-	if (ret >= size)
-		pr_info("CDNS2: buffer overflowed.\n");
+	if (ret == size - 1)
+		pr_info("CDNS2: buffer may be truncated.\n");
 
 	return str;
 }
diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c
index 2693a10eb0c7..e8042c158f6d 100644
--- a/drivers/usb/gadget/udc/fsl_udc_core.c
+++ b/drivers/usb/gadget/udc/fsl_udc_core.c
@@ -1360,7 +1360,7 @@ static void ch9getstatus(struct fsl_udc *udc, u8 request_type, u16 value,
 	udc->ep0_dir = USB_DIR_IN;
 	/* Borrow the per device status_req */
 	req = udc->status_req;
-	/* Fill in the reqest structure */
+	/* Fill in the request structure */
 	*((u16 *) req->req.buf) = cpu_to_le16(tmp);
 
 	req->ep = ep;
@@ -2532,15 +2532,18 @@ err_kfree:
 /* Driver removal function
  * Free resources and finish pending transactions
  */
-static int fsl_udc_remove(struct platform_device *pdev)
+static void fsl_udc_remove(struct platform_device *pdev)
 {
 	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	struct fsl_usb2_platform_data *pdata = dev_get_platdata(&pdev->dev);
 
 	DECLARE_COMPLETION_ONSTACK(done);
 
-	if (!udc_controller)
-		return -ENODEV;
+	if (!udc_controller) {
+		dev_err(&pdev->dev,
+			"Driver still in use but removing anyhow\n");
+		return;
+	}
 
 	udc_controller->done = &done;
 	usb_del_gadget_udc(&udc_controller->gadget);
@@ -2568,8 +2571,6 @@ static int fsl_udc_remove(struct platform_device *pdev)
 	 */
 	if (pdata->exit)
 		pdata->exit(pdev);
-
-	return 0;
 }
 
 /*-----------------------------------------------------------------
@@ -2667,7 +2668,7 @@ static const struct platform_device_id fsl_udc_devtype[] = {
 MODULE_DEVICE_TABLE(platform, fsl_udc_devtype);
 static struct platform_driver udc_driver = {
 	.probe		= fsl_udc_probe,
-	.remove		= fsl_udc_remove,
+	.remove_new	= fsl_udc_remove,
 	.id_table	= fsl_udc_devtype,
 	/* these suspend and resume are not usb suspend and resume */
 	.suspend	= fsl_udc_suspend,
diff --git a/drivers/usb/gadget/udc/gr_udc.c b/drivers/usb/gadget/udc/gr_udc.c
index c6dfa7cccc11..fb901be5dac1 100644
--- a/drivers/usb/gadget/udc/gr_udc.c
+++ b/drivers/usb/gadget/udc/gr_udc.c
@@ -2089,15 +2089,18 @@ static void gr_ep_remove(struct gr_udc *dev, int num, int is_in)
 				  ep->tailbuf, ep->tailbuf_paddr);
 }
 
-static int gr_remove(struct platform_device *pdev)
+static void gr_remove(struct platform_device *pdev)
 {
 	struct gr_udc *dev = platform_get_drvdata(pdev);
 	int i;
 
 	if (dev->added)
 		usb_del_gadget_udc(&dev->gadget); /* Shuts everything down */
-	if (dev->driver)
-		return -EBUSY;
+	if (dev->driver) {
+		dev_err(&pdev->dev,
+			"Driver still in use but removing anyhow\n");
+		return;
+	}
 
 	gr_dfs_delete(dev);
 	dma_pool_destroy(dev->desc_pool);
@@ -2110,8 +2113,6 @@ static int gr_remove(struct platform_device *pdev)
 		gr_ep_remove(dev, i, 0);
 	for (i = 0; i < dev->nepi; i++)
 		gr_ep_remove(dev, i, 1);
-
-	return 0;
 }
 static int gr_request_irq(struct gr_udc *dev, int irq)
 {
@@ -2248,7 +2249,7 @@ static struct platform_driver gr_driver = {
 		.of_match_table = gr_match,
 	},
 	.probe = gr_probe,
-	.remove = gr_remove,
+	.remove_new = gr_remove,
 };
 module_platform_driver(gr_driver);
 
diff --git a/drivers/usb/gadget/udc/lpc32xx_udc.c b/drivers/usb/gadget/udc/lpc32xx_udc.c
index a917cc9a32ab..d5f29f8fe481 100644
--- a/drivers/usb/gadget/udc/lpc32xx_udc.c
+++ b/drivers/usb/gadget/udc/lpc32xx_udc.c
@@ -3174,13 +3174,16 @@ i2c_fail:
 	return retval;
 }
 
-static int lpc32xx_udc_remove(struct platform_device *pdev)
+static void lpc32xx_udc_remove(struct platform_device *pdev)
 {
 	struct lpc32xx_udc *udc = platform_get_drvdata(pdev);
 
 	usb_del_gadget_udc(&udc->gadget);
-	if (udc->driver)
-		return -EBUSY;
+	if (udc->driver) {
+		dev_err(&pdev->dev,
+			"Driver still in use but removing anyhow\n");
+		return;
+	}
 
 	udc_clk_set(udc, 1);
 	udc_disable(udc);
@@ -3194,8 +3197,6 @@ static int lpc32xx_udc_remove(struct platform_device *pdev)
 			  udc->udca_v_base, udc->udca_p_base);
 
 	clk_disable_unprepare(udc->usb_slv_clk);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -3255,7 +3256,7 @@ MODULE_DEVICE_TABLE(of, lpc32xx_udc_of_match);
 
 static struct platform_driver lpc32xx_udc_driver = {
 	.probe		= lpc32xx_udc_probe,
-	.remove		= lpc32xx_udc_remove,
+	.remove_new	= lpc32xx_udc_remove,
 	.shutdown	= lpc32xx_udc_shutdown,
 	.suspend	= lpc32xx_udc_suspend,
 	.resume		= lpc32xx_udc_resume,
diff --git a/drivers/usb/gadget/udc/mv_udc_core.c b/drivers/usb/gadget/udc/mv_udc_core.c
index d888dcda2bc8..78308b64955d 100644
--- a/drivers/usb/gadget/udc/mv_udc_core.c
+++ b/drivers/usb/gadget/udc/mv_udc_core.c
@@ -1451,7 +1451,7 @@ udc_prime_status(struct mv_udc *udc, u8 direction, u16 status, bool empty)
 
 	req = udc->status_req;
 
-	/* fill in the reqest structure */
+	/* fill in the request structure */
 	if (empty == false) {
 		*((u16 *) req->req.buf) = cpu_to_le16(status);
 		req->req.length = 2;
diff --git a/drivers/usb/gadget/udc/omap_udc.c b/drivers/usb/gadget/udc/omap_udc.c
index 10c5d7f726a1..f90eeecf27de 100644
--- a/drivers/usb/gadget/udc/omap_udc.c
+++ b/drivers/usb/gadget/udc/omap_udc.c
@@ -2036,7 +2036,8 @@ static irqreturn_t omap_udc_iso_irq(int irq, void *_dev)
 
 static inline int machine_without_vbus_sense(void)
 {
-	return  machine_is_omap_osk() || machine_is_sx1();
+	return  machine_is_omap_osk() || machine_is_omap_palmte() ||
+		machine_is_sx1();
 }
 
 static int omap_udc_start(struct usb_gadget *g,
diff --git a/drivers/usb/gadget/udc/pch_udc.c b/drivers/usb/gadget/udc/pch_udc.c
index 4f8617210d85..169f72665739 100644
--- a/drivers/usb/gadget/udc/pch_udc.c
+++ b/drivers/usb/gadget/udc/pch_udc.c
@@ -274,7 +274,6 @@ struct pch_udc_cfg_data {
  * @td_data:		for data request
  * @dev:		reference to device struct
  * @offset_addr:	offset address of ep register
- * @desc:		for this ep
  * @queue:		queue for requests
  * @num:		endpoint number
  * @in:			endpoint is IN
diff --git a/drivers/usb/gadget/udc/pxa25x_udc.c b/drivers/usb/gadget/udc/pxa25x_udc.c
index df0551ecc810..1ac26cb49ecf 100644
--- a/drivers/usb/gadget/udc/pxa25x_udc.c
+++ b/drivers/usb/gadget/udc/pxa25x_udc.c
@@ -2397,12 +2397,15 @@ static void pxa25x_udc_shutdown(struct platform_device *_dev)
 	pullup_off();
 }
 
-static int pxa25x_udc_remove(struct platform_device *pdev)
+static void pxa25x_udc_remove(struct platform_device *pdev)
 {
 	struct pxa25x_udc *dev = platform_get_drvdata(pdev);
 
-	if (dev->driver)
-		return -EBUSY;
+	if (dev->driver) {
+		dev_err(&pdev->dev,
+			"Driver still in use but removing anyhow\n");
+		return;
+	}
 
 	usb_del_gadget_udc(&dev->gadget);
 	dev->pullup = 0;
@@ -2414,7 +2417,6 @@ static int pxa25x_udc_remove(struct platform_device *pdev)
 		dev->transceiver = NULL;
 
 	the_controller = NULL;
-	return 0;
 }
 
 /*-------------------------------------------------------------------------*/
@@ -2472,7 +2474,7 @@ static int pxa25x_udc_resume(struct platform_device *dev)
 static struct platform_driver udc_driver = {
 	.shutdown	= pxa25x_udc_shutdown,
 	.probe		= pxa25x_udc_probe,
-	.remove		= pxa25x_udc_remove,
+	.remove_new	= pxa25x_udc_remove,
 	.suspend	= pxa25x_udc_suspend,
 	.resume		= pxa25x_udc_resume,
 	.driver		= {
diff --git a/drivers/usb/host/max3421-hcd.c b/drivers/usb/host/max3421-hcd.c
index d152d72de126..9fe4f48b1898 100644
--- a/drivers/usb/host/max3421-hcd.c
+++ b/drivers/usb/host/max3421-hcd.c
@@ -1158,12 +1158,12 @@ dump_eps(struct usb_hcd *hcd)
 		end = dp + sizeof(ubuf);
 		*dp = '\0';
 		list_for_each_entry(urb, &ep->urb_list, urb_list) {
-			ret = snprintf(dp, end - dp, " %p(%d.%s %d/%d)", urb,
-				       usb_pipetype(urb->pipe),
-				       usb_urb_dir_in(urb) ? "IN" : "OUT",
-				       urb->actual_length,
-				       urb->transfer_buffer_length);
-			if (ret < 0 || ret >= end - dp)
+			ret = scnprintf(dp, end - dp, " %p(%d.%s %d/%d)", urb,
+					usb_pipetype(urb->pipe),
+					usb_urb_dir_in(urb) ? "IN" : "OUT",
+					urb->actual_length,
+					urb->transfer_buffer_length);
+			if (ret == end - dp - 1)
 				break;	/* error or buffer full */
 			dp += ret;
 		}
@@ -1255,9 +1255,9 @@ max3421_handle_irqs(struct usb_hcd *hcd)
 			end = sbuf + sizeof(sbuf);
 			*dp = '\0';
 			for (i = 0; i < 16; ++i) {
-				int ret = snprintf(dp, end - dp, " %lu",
-						   max3421_hcd->err_stat[i]);
-				if (ret < 0 || ret >= end - dp)
+				int ret = scnprintf(dp, end - dp, " %lu",
+						    max3421_hcd->err_stat[i]);
+				if (ret == end - dp - 1)
 					break;	/* error or buffer full */
 				dp += ret;
 			}
diff --git a/drivers/usb/host/uhci-grlib.c b/drivers/usb/host/uhci-grlib.c
index ac3fc5970315..cfebb833668e 100644
--- a/drivers/usb/host/uhci-grlib.c
+++ b/drivers/usb/host/uhci-grlib.c
@@ -22,6 +22,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
+#include <linux/platform_device.h>
 
 static int uhci_grlib_init(struct usb_hcd *hcd)
 {
diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index b40d9238d447..d82935d31126 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -6,9 +6,24 @@
  *
  * Author: Lu Baolu <baolu.lu@linux.intel.com>
  */
+#include <linux/bug.h>
+#include <linux/device.h>
 #include <linux/dma-mapping.h>
-#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/kstrtox.h>
+#include <linux/list.h>
 #include <linux/nls.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+
+#include <linux/io-64-nonatomic-lo-hi.h>
+
+#include <asm/byteorder.h>
 
 #include "xhci.h"
 #include "xhci-trace.h"
@@ -28,7 +43,7 @@ static void dbc_ring_free(struct device *dev, struct xhci_ring *ring)
 	if (!ring)
 		return;
 
-	if (ring->first_seg && ring->first_seg->trbs) {
+	if (ring->first_seg) {
 		dma_free_coherent(dev, TRB_SEGMENT_SIZE,
 				  ring->first_seg->trbs,
 				  ring->first_seg->dma);
@@ -374,13 +389,13 @@ static void xhci_dbc_eps_init(struct xhci_dbc *dbc)
 
 static void xhci_dbc_eps_exit(struct xhci_dbc *dbc)
 {
-	memset(dbc->eps, 0, sizeof(struct dbc_ep) * ARRAY_SIZE(dbc->eps));
+	memset(dbc->eps, 0, sizeof_field(struct xhci_dbc, eps));
 }
 
 static int dbc_erst_alloc(struct device *dev, struct xhci_ring *evt_ring,
 		    struct xhci_erst *erst, gfp_t flags)
 {
-	erst->entries = dma_alloc_coherent(dev, sizeof(struct xhci_erst_entry),
+	erst->entries = dma_alloc_coherent(dev, sizeof(*erst->entries),
 					   &erst->erst_dma_addr, flags);
 	if (!erst->entries)
 		return -ENOMEM;
@@ -394,9 +409,8 @@ static int dbc_erst_alloc(struct device *dev, struct xhci_ring *evt_ring,
 
 static void dbc_erst_free(struct device *dev, struct xhci_erst *erst)
 {
-	if (erst->entries)
-		dma_free_coherent(dev, sizeof(struct xhci_erst_entry),
-				  erst->entries, erst->erst_dma_addr);
+	dma_free_coherent(dev, sizeof(*erst->entries), erst->entries,
+			  erst->erst_dma_addr);
 	erst->entries = NULL;
 }
 
@@ -495,7 +509,7 @@ static int xhci_dbc_mem_init(struct xhci_dbc *dbc, gfp_t flags)
 		goto ctx_fail;
 
 	/* Allocate the string table: */
-	dbc->string_size = sizeof(struct dbc_str_descs);
+	dbc->string_size = sizeof(*dbc->string);
 	dbc->string = dma_alloc_coherent(dev, dbc->string_size,
 					 &dbc->string_dma, flags);
 	if (!dbc->string)
@@ -543,11 +557,8 @@ static void xhci_dbc_mem_cleanup(struct xhci_dbc *dbc)
 
 	xhci_dbc_eps_exit(dbc);
 
-	if (dbc->string) {
-		dma_free_coherent(dbc->dev, dbc->string_size,
-				  dbc->string, dbc->string_dma);
-		dbc->string = NULL;
-	}
+	dma_free_coherent(dbc->dev, dbc->string_size, dbc->string, dbc->string_dma);
+	dbc->string = NULL;
 
 	dbc_free_ctx(dbc->dev, dbc->ctx);
 	dbc->ctx = NULL;
@@ -597,7 +608,7 @@ static int xhci_do_dbc_start(struct xhci_dbc *dbc)
 static int xhci_do_dbc_stop(struct xhci_dbc *dbc)
 {
 	if (dbc->state == DS_DISABLED)
-		return -1;
+		return -EINVAL;
 
 	writel(0, &dbc->regs->control);
 	dbc->state = DS_DISABLED;
@@ -650,11 +661,11 @@ static void xhci_dbc_stop(struct xhci_dbc *dbc)
 	spin_lock_irqsave(&dbc->lock, flags);
 	ret = xhci_do_dbc_stop(dbc);
 	spin_unlock_irqrestore(&dbc->lock, flags);
+	if (ret)
+		return;
 
-	if (!ret) {
-		xhci_dbc_mem_cleanup(dbc);
-		pm_runtime_put_sync(dbc->dev); /* note, was self.controller */
-	}
+	xhci_dbc_mem_cleanup(dbc);
+	pm_runtime_put_sync(dbc->dev); /* note, was self.controller */
 }
 
 static void
@@ -914,41 +925,29 @@ static void xhci_dbc_handle_events(struct work_struct *work)
 	mod_delayed_work(system_wq, &dbc->event_work, 1);
 }
 
+static const char * const dbc_state_strings[DS_MAX] = {
+	[DS_DISABLED] = "disabled",
+	[DS_INITIALIZED] = "initialized",
+	[DS_ENABLED] = "enabled",
+	[DS_CONNECTED] = "connected",
+	[DS_CONFIGURED] = "configured",
+	[DS_STALLED] = "stalled",
+};
+
 static ssize_t dbc_show(struct device *dev,
 			struct device_attribute *attr,
 			char *buf)
 {
-	const char		*p;
 	struct xhci_dbc		*dbc;
 	struct xhci_hcd		*xhci;
 
 	xhci = hcd_to_xhci(dev_get_drvdata(dev));
 	dbc = xhci->dbc;
 
-	switch (dbc->state) {
-	case DS_DISABLED:
-		p = "disabled";
-		break;
-	case DS_INITIALIZED:
-		p = "initialized";
-		break;
-	case DS_ENABLED:
-		p = "enabled";
-		break;
-	case DS_CONNECTED:
-		p = "connected";
-		break;
-	case DS_CONFIGURED:
-		p = "configured";
-		break;
-	case DS_STALLED:
-		p = "stalled";
-		break;
-	default:
-		p = "unknown";
-	}
+	if (dbc->state >= ARRAY_SIZE(dbc_state_strings))
+		return sysfs_emit(buf, "unknown\n");
 
-	return sprintf(buf, "%s\n", p);
+	return sysfs_emit(buf, "%s\n", dbc_state_strings[dbc->state]);
 }
 
 static ssize_t dbc_store(struct device *dev,
@@ -961,9 +960,9 @@ static ssize_t dbc_store(struct device *dev,
 	xhci = hcd_to_xhci(dev_get_drvdata(dev));
 	dbc = xhci->dbc;
 
-	if (!strncmp(buf, "enable", 6))
+	if (sysfs_streq(buf, "enable"))
 		xhci_dbc_start(dbc);
-	else if (!strncmp(buf, "disable", 7))
+	else if (sysfs_streq(buf, "disable"))
 		xhci_dbc_stop(dbc);
 	else
 		return -EINVAL;
@@ -981,7 +980,7 @@ static ssize_t dbc_idVendor_show(struct device *dev,
 	xhci = hcd_to_xhci(dev_get_drvdata(dev));
 	dbc = xhci->dbc;
 
-	return sprintf(buf, "%04x\n", dbc->idVendor);
+	return sysfs_emit(buf, "%04x\n", dbc->idVendor);
 }
 
 static ssize_t dbc_idVendor_store(struct device *dev,
@@ -993,9 +992,11 @@ static ssize_t dbc_idVendor_store(struct device *dev,
 	void __iomem		*ptr;
 	u16			value;
 	u32			dev_info;
+	int ret;
 
-	if (kstrtou16(buf, 0, &value))
-		return -EINVAL;
+	ret = kstrtou16(buf, 0, &value);
+	if (ret)
+		return ret;
 
 	xhci = hcd_to_xhci(dev_get_drvdata(dev));
 	dbc = xhci->dbc;
@@ -1021,7 +1022,7 @@ static ssize_t dbc_idProduct_show(struct device *dev,
 	xhci = hcd_to_xhci(dev_get_drvdata(dev));
 	dbc = xhci->dbc;
 
-	return sprintf(buf, "%04x\n", dbc->idProduct);
+	return sysfs_emit(buf, "%04x\n", dbc->idProduct);
 }
 
 static ssize_t dbc_idProduct_store(struct device *dev,
@@ -1033,9 +1034,11 @@ static ssize_t dbc_idProduct_store(struct device *dev,
 	void __iomem		*ptr;
 	u32			dev_info;
 	u16			value;
+	int ret;
 
-	if (kstrtou16(buf, 0, &value))
-		return -EINVAL;
+	ret = kstrtou16(buf, 0, &value);
+	if (ret)
+		return ret;
 
 	xhci = hcd_to_xhci(dev_get_drvdata(dev));
 	dbc = xhci->dbc;
@@ -1060,7 +1063,7 @@ static ssize_t dbc_bcdDevice_show(struct device *dev,
 	xhci = hcd_to_xhci(dev_get_drvdata(dev));
 	dbc = xhci->dbc;
 
-	return sprintf(buf, "%04x\n", dbc->bcdDevice);
+	return sysfs_emit(buf, "%04x\n", dbc->bcdDevice);
 }
 
 static ssize_t dbc_bcdDevice_store(struct device *dev,
@@ -1072,9 +1075,11 @@ static ssize_t dbc_bcdDevice_store(struct device *dev,
 	void __iomem *ptr;
 	u32 dev_info;
 	u16 value;
+	int ret;
 
-	if (kstrtou16(buf, 0, &value))
-		return -EINVAL;
+	ret = kstrtou16(buf, 0, &value);
+	if (ret)
+		return ret;
 
 	xhci = hcd_to_xhci(dev_get_drvdata(dev));
 	dbc = xhci->dbc;
@@ -1100,7 +1105,7 @@ static ssize_t dbc_bInterfaceProtocol_show(struct device *dev,
 	xhci = hcd_to_xhci(dev_get_drvdata(dev));
 	dbc = xhci->dbc;
 
-	return sprintf(buf, "%02x\n", dbc->bInterfaceProtocol);
+	return sysfs_emit(buf, "%02x\n", dbc->bInterfaceProtocol);
 }
 
 static ssize_t dbc_bInterfaceProtocol_store(struct device *dev,
@@ -1114,9 +1119,13 @@ static ssize_t dbc_bInterfaceProtocol_store(struct device *dev,
 	u8 value;
 	int ret;
 
-	/* bInterfaceProtocol is 8 bit, but xhci only supports values 0 and 1 */
+	/* bInterfaceProtocol is 8 bit, but... */
 	ret = kstrtou8(buf, 0, &value);
-	if (ret || value > 1)
+	if (ret)
+		return ret;
+
+	/* ...xhci only supports values 0 and 1 */
+	if (value > 1)
 		return -EINVAL;
 
 	xhci = hcd_to_xhci(dev_get_drvdata(dev));
@@ -1139,7 +1148,7 @@ static DEVICE_ATTR_RW(dbc_idProduct);
 static DEVICE_ATTR_RW(dbc_bcdDevice);
 static DEVICE_ATTR_RW(dbc_bInterfaceProtocol);
 
-static struct attribute *dbc_dev_attributes[] = {
+static struct attribute *dbc_dev_attrs[] = {
 	&dev_attr_dbc.attr,
 	&dev_attr_dbc_idVendor.attr,
 	&dev_attr_dbc_idProduct.attr,
@@ -1147,10 +1156,7 @@ static struct attribute *dbc_dev_attributes[] = {
 	&dev_attr_dbc_bInterfaceProtocol.attr,
 	NULL
 };
-
-static const struct attribute_group dbc_dev_attrib_grp = {
-	.attrs = dbc_dev_attributes,
-};
+ATTRIBUTE_GROUPS(dbc_dev);
 
 struct xhci_dbc *
 xhci_alloc_dbc(struct device *dev, void __iomem *base, const struct dbc_driver *driver)
@@ -1176,7 +1182,7 @@ xhci_alloc_dbc(struct device *dev, void __iomem *base, const struct dbc_driver *
 	INIT_DELAYED_WORK(&dbc->event_work, xhci_dbc_handle_events);
 	spin_lock_init(&dbc->lock);
 
-	ret = sysfs_create_group(&dev->kobj, &dbc_dev_attrib_grp);
+	ret = sysfs_create_groups(&dev->kobj, dbc_dev_groups);
 	if (ret)
 		goto err;
 
@@ -1195,7 +1201,7 @@ void xhci_dbc_remove(struct xhci_dbc *dbc)
 	xhci_dbc_stop(dbc);
 
 	/* remove sysfs files */
-	sysfs_remove_group(&dbc->dev->kobj, &dbc_dev_attrib_grp);
+	sysfs_remove_groups(&dbc->dev->kobj, dbc_dev_groups);
 
 	kfree(dbc);
 }
diff --git a/drivers/usb/host/xhci-dbgcap.h b/drivers/usb/host/xhci-dbgcap.h
index 51a7ab3ba0ca..e39e3ae1677a 100644
--- a/drivers/usb/host/xhci-dbgcap.h
+++ b/drivers/usb/host/xhci-dbgcap.h
@@ -82,6 +82,7 @@ enum dbc_state {
 	DS_CONNECTED,
 	DS_CONFIGURED,
 	DS_STALLED,
+	DS_MAX
 };
 
 struct dbc_ep {
diff --git a/drivers/usb/host/xhci-debugfs.c b/drivers/usb/host/xhci-debugfs.c
index 6d142cd61bd6..f8ba15e7c225 100644
--- a/drivers/usb/host/xhci-debugfs.c
+++ b/drivers/usb/host/xhci-debugfs.c
@@ -693,7 +693,7 @@ void xhci_debugfs_init(struct xhci_hcd *xhci)
 				     "command-ring",
 				     xhci->debugfs_root);
 
-	xhci_debugfs_create_ring_dir(xhci, &xhci->interrupter->event_ring,
+	xhci_debugfs_create_ring_dir(xhci, &xhci->interrupters[0]->event_ring,
 				     "event-ring",
 				     xhci->debugfs_root);
 
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 62116586848b..a7716202a8dd 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -323,6 +323,7 @@ void xhci_initialize_ring_info(struct xhci_ring *ring,
 	 */
 	ring->num_trbs_free = ring->num_segs * (TRBS_PER_SEGMENT - 1) - 1;
 }
+EXPORT_SYMBOL_GPL(xhci_initialize_ring_info);
 
 /* Allocate segments and link them for a ring */
 static int xhci_alloc_segments_for_ring(struct xhci_hcd *xhci,
@@ -1739,6 +1740,8 @@ struct xhci_command *xhci_alloc_command(struct xhci_hcd *xhci,
 	}
 
 	command->status = 0;
+	/* set default timeout to 5000 ms */
+	command->timeout_ms = XHCI_CMD_DEFAULT_TIMEOUT;
 	INIT_LIST_HEAD(&command->cmd_list);
 	return command;
 }
@@ -1853,6 +1856,31 @@ xhci_free_interrupter(struct xhci_hcd *xhci, struct xhci_interrupter *ir)
 	kfree(ir);
 }
 
+void xhci_remove_secondary_interrupter(struct usb_hcd *hcd, struct xhci_interrupter *ir)
+{
+	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
+	unsigned int intr_num;
+
+	spin_lock_irq(&xhci->lock);
+
+	/* interrupter 0 is primary interrupter, don't touch it */
+	if (!ir || !ir->intr_num || ir->intr_num >= xhci->max_interrupters) {
+		xhci_dbg(xhci, "Invalid secondary interrupter, can't remove\n");
+		spin_unlock_irq(&xhci->lock);
+		return;
+	}
+
+	intr_num = ir->intr_num;
+
+	xhci_remove_interrupter(xhci, ir);
+	xhci->interrupters[intr_num] = NULL;
+
+	spin_unlock_irq(&xhci->lock);
+
+	xhci_free_interrupter(xhci, ir);
+}
+EXPORT_SYMBOL_GPL(xhci_remove_secondary_interrupter);
+
 void xhci_mem_cleanup(struct xhci_hcd *xhci)
 {
 	struct device	*dev = xhci_to_hcd(xhci)->self.sysdev;
@@ -1860,10 +1888,14 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)
 
 	cancel_delayed_work_sync(&xhci->cmd_timer);
 
-	xhci_remove_interrupter(xhci, xhci->interrupter);
-	xhci_free_interrupter(xhci, xhci->interrupter);
-	xhci->interrupter = NULL;
-	xhci_dbg_trace(xhci, trace_xhci_dbg_init, "Freed primary event ring");
+	for (i = 0; i < xhci->max_interrupters; i++) {
+		if (xhci->interrupters[i]) {
+			xhci_remove_interrupter(xhci, xhci->interrupters[i]);
+			xhci_free_interrupter(xhci, xhci->interrupters[i]);
+			xhci->interrupters[i] = NULL;
+		}
+	}
+	xhci_dbg_trace(xhci, trace_xhci_dbg_init, "Freed interrupters");
 
 	if (xhci->cmd_ring)
 		xhci_ring_free(xhci, xhci->cmd_ring);
@@ -1933,6 +1965,7 @@ no_bw:
 	for (i = 0; i < xhci->num_port_caps; i++)
 		kfree(xhci->port_caps[i].psi);
 	kfree(xhci->port_caps);
+	kfree(xhci->interrupters);
 	xhci->num_port_caps = 0;
 
 	xhci->usb2_rhub.ports = NULL;
@@ -1941,6 +1974,7 @@ no_bw:
 	xhci->rh_bw = NULL;
 	xhci->ext_caps = NULL;
 	xhci->port_caps = NULL;
+	xhci->interrupters = NULL;
 
 	xhci->page_size = 0;
 	xhci->page_shift = 0;
@@ -2246,18 +2280,20 @@ static int xhci_setup_port_arrays(struct xhci_hcd *xhci, gfp_t flags)
 }
 
 static struct xhci_interrupter *
-xhci_alloc_interrupter(struct xhci_hcd *xhci, gfp_t flags)
+xhci_alloc_interrupter(struct xhci_hcd *xhci, int segs, gfp_t flags)
 {
 	struct device *dev = xhci_to_hcd(xhci)->self.sysdev;
 	struct xhci_interrupter *ir;
-	unsigned int num_segs;
+	unsigned int num_segs = segs;
 	int ret;
 
 	ir = kzalloc_node(sizeof(*ir), flags, dev_to_node(dev));
 	if (!ir)
 		return NULL;
 
-	num_segs = min_t(unsigned int, 1 << HCS_ERST_MAX(xhci->hcs_params2),
+	/* number of ring segments should be greater than 0 */
+	if (segs <= 0)
+		num_segs = min_t(unsigned int, 1 << HCS_ERST_MAX(xhci->hcs_params2),
 			 ERST_MAX_SEGS);
 
 	ir->event_ring = xhci_ring_alloc(xhci, num_segs, 1, TYPE_EVENT, 0,
@@ -2286,12 +2322,19 @@ xhci_add_interrupter(struct xhci_hcd *xhci, struct xhci_interrupter *ir,
 	u64 erst_base;
 	u32 erst_size;
 
-	if (intr_num > xhci->max_interrupters) {
+	if (intr_num >= xhci->max_interrupters) {
 		xhci_warn(xhci, "Can't add interrupter %d, max interrupters %d\n",
 			  intr_num, xhci->max_interrupters);
 		return -EINVAL;
 	}
 
+	if (xhci->interrupters[intr_num]) {
+		xhci_warn(xhci, "Interrupter %d\n already set up", intr_num);
+		return -EINVAL;
+	}
+
+	xhci->interrupters[intr_num] = ir;
+	ir->intr_num = intr_num;
 	ir->ir_set = &xhci->run_regs->ir_set[intr_num];
 
 	/* set ERST count with the number of entries in the segment table */
@@ -2311,10 +2354,52 @@ xhci_add_interrupter(struct xhci_hcd *xhci, struct xhci_interrupter *ir,
 	return 0;
 }
 
+struct xhci_interrupter *
+xhci_create_secondary_interrupter(struct usb_hcd *hcd, int num_seg)
+{
+	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
+	struct xhci_interrupter *ir;
+	unsigned int i;
+	int err = -ENOSPC;
+
+	if (!xhci->interrupters || xhci->max_interrupters <= 1)
+		return NULL;
+
+	ir = xhci_alloc_interrupter(xhci, num_seg, GFP_KERNEL);
+	if (!ir)
+		return NULL;
+
+	spin_lock_irq(&xhci->lock);
+
+	/* Find available secondary interrupter, interrupter 0 is reserved for primary */
+	for (i = 1; i < xhci->max_interrupters; i++) {
+		if (xhci->interrupters[i] == NULL) {
+			err = xhci_add_interrupter(xhci, ir, i);
+			break;
+		}
+	}
+
+	spin_unlock_irq(&xhci->lock);
+
+	if (err) {
+		xhci_warn(xhci, "Failed to add secondary interrupter, max interrupters %d\n",
+			  xhci->max_interrupters);
+		xhci_free_interrupter(xhci, ir);
+		return NULL;
+	}
+
+	xhci_dbg(xhci, "Add secondary interrupter %d, max interrupters %d\n",
+		 i, xhci->max_interrupters);
+
+	return ir;
+}
+EXPORT_SYMBOL_GPL(xhci_create_secondary_interrupter);
+
 int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 {
-	dma_addr_t	dma;
+	struct xhci_interrupter *ir;
 	struct device	*dev = xhci_to_hcd(xhci)->self.sysdev;
+	dma_addr_t	dma;
 	unsigned int	val, val2;
 	u64		val_64;
 	u32		page_size, temp;
@@ -2438,11 +2523,14 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 	/* Allocate and set up primary interrupter 0 with an event ring. */
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
 		       "Allocating primary event ring");
-	xhci->interrupter = xhci_alloc_interrupter(xhci, flags);
-	if (!xhci->interrupter)
+	xhci->interrupters = kcalloc_node(xhci->max_interrupters, sizeof(*xhci->interrupters),
+					  flags, dev_to_node(dev));
+
+	ir = xhci_alloc_interrupter(xhci, 0, flags);
+	if (!ir)
 		goto fail;
 
-	if (xhci_add_interrupter(xhci, xhci->interrupter, 0))
+	if (xhci_add_interrupter(xhci, ir, 0))
 		goto fail;
 
 	xhci->isoc_bei_interval = AVOID_BEI_INTERVAL_MAX;
diff --git a/drivers/usb/host/xhci-mtk.c b/drivers/usb/host/xhci-mtk.c
index bbdf1b0b7be1..3252e3d2d79c 100644
--- a/drivers/usb/host/xhci-mtk.c
+++ b/drivers/usb/host/xhci-mtk.c
@@ -7,6 +7,7 @@
  *  Chunfeng Yun <chunfeng.yun@mediatek.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/dma-mapping.h>
 #include <linux/iopoll.h>
 #include <linux/kernel.h>
@@ -73,6 +74,9 @@
 #define FRMCNT_LEV1_RANG	(0x12b << 8)
 #define FRMCNT_LEV1_RANG_MASK	GENMASK(19, 8)
 
+#define HSCH_CFG1		0x960
+#define SCH3_RXFIFO_DEPTH_MASK	GENMASK(21, 20)
+
 #define SS_GEN2_EOF_CFG		0x990
 #define SSG2EOF_OFFSET		0x3c
 
@@ -114,6 +118,8 @@
 #define SSC_IP_SLEEP_EN	BIT(4)
 #define SSC_SPM_INT_EN		BIT(1)
 
+#define SCH_FIFO_TO_KB(x)	((x) >> 10)
+
 enum ssusb_uwk_vers {
 	SSUSB_UWK_V1 = 1,
 	SSUSB_UWK_V2,
@@ -165,6 +171,35 @@ static void xhci_mtk_set_frame_interval(struct xhci_hcd_mtk *mtk)
 	writel(value, hcd->regs + SS_GEN2_EOF_CFG);
 }
 
+/*
+ * workaround: usb3.2 gen1 isoc rx hw issue
+ * host send out unexpected ACK afer device fininsh a burst transfer with
+ * a short packet.
+ */
+static void xhci_mtk_rxfifo_depth_set(struct xhci_hcd_mtk *mtk)
+{
+	struct usb_hcd *hcd = mtk->hcd;
+	u32 value;
+
+	if (!mtk->rxfifo_depth)
+		return;
+
+	value = readl(hcd->regs + HSCH_CFG1);
+	value &= ~SCH3_RXFIFO_DEPTH_MASK;
+	value |= FIELD_PREP(SCH3_RXFIFO_DEPTH_MASK,
+			    SCH_FIFO_TO_KB(mtk->rxfifo_depth) - 1);
+	writel(value, hcd->regs + HSCH_CFG1);
+}
+
+static void xhci_mtk_init_quirk(struct xhci_hcd_mtk *mtk)
+{
+	/* workaround only for mt8195 */
+	xhci_mtk_set_frame_interval(mtk);
+
+	/* workaround for SoCs using SSUSB about before IPM v1.6.0 */
+	xhci_mtk_rxfifo_depth_set(mtk);
+}
+
 static int xhci_mtk_host_enable(struct xhci_hcd_mtk *mtk)
 {
 	struct mu3c_ippc_regs __iomem *ippc = mtk->ippc_regs;
@@ -448,8 +483,7 @@ static int xhci_mtk_setup(struct usb_hcd *hcd)
 		if (ret)
 			return ret;
 
-		/* workaround only for mt8195 */
-		xhci_mtk_set_frame_interval(mtk);
+		xhci_mtk_init_quirk(mtk);
 	}
 
 	ret = xhci_gen_setup(hcd, xhci_mtk_quirks);
@@ -527,6 +561,8 @@ static int xhci_mtk_probe(struct platform_device *pdev)
 	of_property_read_u32(node, "mediatek,u2p-dis-msk",
 			     &mtk->u2p_dis_msk);
 
+	of_property_read_u32(node, "rx-fifo-depth", &mtk->rxfifo_depth);
+
 	ret = usb_wakeup_of_property_parse(mtk, node);
 	if (ret) {
 		dev_err(dev, "failed to parse uwk property\n");
diff --git a/drivers/usb/host/xhci-mtk.h b/drivers/usb/host/xhci-mtk.h
index 39f7ae7d3087..f5e2bd66bb1b 100644
--- a/drivers/usb/host/xhci-mtk.h
+++ b/drivers/usb/host/xhci-mtk.h
@@ -171,6 +171,8 @@ struct xhci_hcd_mtk {
 	struct regmap *uwk;
 	u32 uwk_reg_base;
 	u32 uwk_vers;
+	/* quirk */
+	u32 rxfifo_depth;
 };
 
 static inline struct xhci_hcd_mtk *hcd_to_mtk(struct usb_hcd *hcd)
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index d6fc08e5db8f..b534ca9752be 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -95,10 +95,9 @@ static void xhci_msix_sync_irqs(struct xhci_hcd *xhci)
 
 	if (hcd->msix_enabled) {
 		struct pci_dev *pdev = to_pci_dev(hcd->self.controller);
-		int i;
 
-		for (i = 0; i < xhci->msix_count; i++)
-			synchronize_irq(pci_irq_vector(pdev, i));
+		/* for now, the driver only supports one primary interrupter */
+		synchronize_irq(pci_irq_vector(pdev, 0));
 	}
 }
 
@@ -112,100 +111,18 @@ static void xhci_cleanup_msix(struct xhci_hcd *xhci)
 	if (hcd->irq > 0)
 		return;
 
-	if (hcd->msix_enabled) {
-		int i;
-
-		for (i = 0; i < xhci->msix_count; i++)
-			free_irq(pci_irq_vector(pdev, i), xhci_to_hcd(xhci));
-	} else {
-		free_irq(pci_irq_vector(pdev, 0), xhci_to_hcd(xhci));
-	}
-
+	free_irq(pci_irq_vector(pdev, 0), xhci_to_hcd(xhci));
 	pci_free_irq_vectors(pdev);
 	hcd->msix_enabled = 0;
 }
 
-/*
- * Set up MSI
- */
-static int xhci_setup_msi(struct xhci_hcd *xhci)
-{
-	int ret;
-	/*
-	 * TODO:Check with MSI Soc for sysdev
-	 */
-	struct pci_dev  *pdev = to_pci_dev(xhci_to_hcd(xhci)->self.controller);
-
-	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI);
-	if (ret < 0) {
-		xhci_dbg_trace(xhci, trace_xhci_dbg_init,
-				"failed to allocate MSI entry");
-		return ret;
-	}
-
-	ret = request_irq(pdev->irq, xhci_msi_irq,
-				0, "xhci_hcd", xhci_to_hcd(xhci));
-	if (ret) {
-		xhci_dbg_trace(xhci, trace_xhci_dbg_init,
-				"disable MSI interrupt");
-		pci_free_irq_vectors(pdev);
-	}
-
-	return ret;
-}
-
-/*
- * Set up MSI-X
- */
-static int xhci_setup_msix(struct xhci_hcd *xhci)
-{
-	int i, ret;
-	struct usb_hcd *hcd = xhci_to_hcd(xhci);
-	struct pci_dev *pdev = to_pci_dev(hcd->self.controller);
-
-	/*
-	 * calculate number of msi-x vectors supported.
-	 * - HCS_MAX_INTRS: the max number of interrupts the host can handle,
-	 *   with max number of interrupters based on the xhci HCSPARAMS1.
-	 * - num_online_cpus: maximum msi-x vectors per CPUs core.
-	 *   Add additional 1 vector to ensure always available interrupt.
-	 */
-	xhci->msix_count = min(num_online_cpus() + 1,
-				HCS_MAX_INTRS(xhci->hcs_params1));
-
-	ret = pci_alloc_irq_vectors(pdev, xhci->msix_count, xhci->msix_count,
-			PCI_IRQ_MSIX);
-	if (ret < 0) {
-		xhci_dbg_trace(xhci, trace_xhci_dbg_init,
-				"Failed to enable MSI-X");
-		return ret;
-	}
-
-	for (i = 0; i < xhci->msix_count; i++) {
-		ret = request_irq(pci_irq_vector(pdev, i), xhci_msi_irq, 0,
-				"xhci_hcd", xhci_to_hcd(xhci));
-		if (ret)
-			goto disable_msix;
-	}
-
-	hcd->msix_enabled = 1;
-	return ret;
-
-disable_msix:
-	xhci_dbg_trace(xhci, trace_xhci_dbg_init, "disable MSI-X interrupt");
-	while (--i >= 0)
-		free_irq(pci_irq_vector(pdev, i), xhci_to_hcd(xhci));
-	pci_free_irq_vectors(pdev);
-	return ret;
-}
-
+/* Try enabling MSI-X with MSI and legacy IRQ as fallback */
 static int xhci_try_enable_msi(struct usb_hcd *hcd)
 {
+	struct pci_dev *pdev = to_pci_dev(hcd->self.controller);
 	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
-	struct pci_dev  *pdev;
 	int ret;
 
-	pdev = to_pci_dev(xhci_to_hcd(xhci)->self.controller);
 	/*
 	 * Some Fresco Logic host controllers advertise MSI, but fail to
 	 * generate interrupts.  Don't even try to enable MSI.
@@ -218,32 +135,53 @@ static int xhci_try_enable_msi(struct usb_hcd *hcd)
 		free_irq(hcd->irq, hcd);
 	hcd->irq = 0;
 
-	ret = xhci_setup_msix(xhci);
-	if (ret)
-		/* fall back to msi*/
-		ret = xhci_setup_msi(xhci);
+	/*
+	 * calculate number of MSI-X vectors supported.
+	 * - HCS_MAX_INTRS: the max number of interrupts the host can handle,
+	 *   with max number of interrupters based on the xhci HCSPARAMS1.
+	 * - num_online_cpus: maximum MSI-X vectors per CPUs core.
+	 *   Add additional 1 vector to ensure always available interrupt.
+	 */
+	xhci->nvecs = min(num_online_cpus() + 1,
+			  HCS_MAX_INTRS(xhci->hcs_params1));
 
-	if (!ret) {
-		hcd->msi_enabled = 1;
-		return 0;
+	/* TODO: Check with MSI Soc for sysdev */
+	xhci->nvecs = pci_alloc_irq_vectors(pdev, 1, xhci->nvecs,
+					    PCI_IRQ_MSIX | PCI_IRQ_MSI);
+	if (xhci->nvecs < 0) {
+		xhci_dbg_trace(xhci, trace_xhci_dbg_init,
+			       "failed to allocate IRQ vectors");
+		goto legacy_irq;
 	}
 
+	ret = request_irq(pci_irq_vector(pdev, 0), xhci_msi_irq, 0, "xhci_hcd",
+			  xhci_to_hcd(xhci));
+	if (ret)
+		goto free_irq_vectors;
+
+	hcd->msi_enabled = 1;
+	hcd->msix_enabled = pdev->msix_enabled;
+	return 0;
+
+free_irq_vectors:
+	xhci_dbg_trace(xhci, trace_xhci_dbg_init, "disable %s interrupt",
+		       pdev->msix_enabled ? "MSI-X" : "MSI");
+	pci_free_irq_vectors(pdev);
+
+legacy_irq:
 	if (!pdev->irq) {
 		xhci_err(xhci, "No msi-x/msi found and no IRQ in BIOS\n");
 		return -EINVAL;
 	}
 
- legacy_irq:
 	if (!strlen(hcd->irq_descr))
 		snprintf(hcd->irq_descr, sizeof(hcd->irq_descr), "%s:usb%d",
 			 hcd->driver->description, hcd->self.busnum);
 
-	/* fall back to legacy interrupt*/
-	ret = request_irq(pdev->irq, &usb_hcd_irq, IRQF_SHARED,
-			hcd->irq_descr, hcd);
+	/* fall back to legacy interrupt */
+	ret = request_irq(pdev->irq, &usb_hcd_irq, IRQF_SHARED, hcd->irq_descr, hcd);
 	if (ret) {
-		xhci_err(xhci, "request interrupt %d failed\n",
-				pdev->irq);
+		xhci_err(xhci, "request interrupt %d failed\n", pdev->irq);
 		return ret;
 	}
 	hcd->irq = pdev->irq;
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index 732cdeb73920..3d071b875308 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -131,6 +131,9 @@ static const struct of_device_id usb_xhci_of_match[] = {
 		.compatible = "brcm,xhci-brcm-v2",
 		.data = &xhci_plat_brcm,
 	}, {
+		.compatible = "brcm,bcm2711-xhci",
+		.data = &xhci_plat_brcm,
+	}, {
 		.compatible = "brcm,bcm7445-xhci",
 		.data = &xhci_plat_brcm,
 	},
@@ -250,6 +253,9 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s
 		if (device_property_read_bool(tmpdev, "quirk-broken-port-ped"))
 			xhci->quirks |= XHCI_BROKEN_PORT_PED;
 
+		if (device_property_read_bool(tmpdev, "xhci-sg-trb-cache-size-quirk"))
+			xhci->quirks |= XHCI_SG_TRB_CACHE_SIZE_QUIRK;
+
 		device_property_read_u32(tmpdev, "imod-interval-ns",
 					 &xhci->imod_interval);
 	}
@@ -433,7 +439,7 @@ void xhci_plat_remove(struct platform_device *dev)
 }
 EXPORT_SYMBOL_GPL(xhci_plat_remove);
 
-static int __maybe_unused xhci_plat_suspend(struct device *dev)
+static int xhci_plat_suspend(struct device *dev)
 {
 	struct usb_hcd	*hcd = dev_get_drvdata(dev);
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
@@ -461,7 +467,7 @@ static int __maybe_unused xhci_plat_suspend(struct device *dev)
 	return 0;
 }
 
-static int __maybe_unused xhci_plat_resume(struct device *dev)
+static int xhci_plat_resume_common(struct device *dev, struct pm_message pmsg)
 {
 	struct usb_hcd	*hcd = dev_get_drvdata(dev);
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
@@ -483,7 +489,7 @@ static int __maybe_unused xhci_plat_resume(struct device *dev)
 	if (ret)
 		goto disable_clks;
 
-	ret = xhci_resume(xhci, PMSG_RESUME);
+	ret = xhci_resume(xhci, pmsg);
 	if (ret)
 		goto disable_clks;
 
@@ -502,6 +508,16 @@ disable_clks:
 	return ret;
 }
 
+static int xhci_plat_resume(struct device *dev)
+{
+	return xhci_plat_resume_common(dev, PMSG_RESUME);
+}
+
+static int xhci_plat_restore(struct device *dev)
+{
+	return xhci_plat_resume_common(dev, PMSG_RESTORE);
+}
+
 static int __maybe_unused xhci_plat_runtime_suspend(struct device *dev)
 {
 	struct usb_hcd  *hcd = dev_get_drvdata(dev);
@@ -524,7 +540,12 @@ static int __maybe_unused xhci_plat_runtime_resume(struct device *dev)
 }
 
 const struct dev_pm_ops xhci_plat_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(xhci_plat_suspend, xhci_plat_resume)
+	.suspend = pm_sleep_ptr(xhci_plat_suspend),
+	.resume = pm_sleep_ptr(xhci_plat_resume),
+	.freeze = pm_sleep_ptr(xhci_plat_suspend),
+	.thaw = pm_sleep_ptr(xhci_plat_resume),
+	.poweroff = pm_sleep_ptr(xhci_plat_suspend),
+	.restore = pm_sleep_ptr(xhci_plat_restore),
 
 	SET_RUNTIME_PM_OPS(xhci_plat_runtime_suspend,
 			   xhci_plat_runtime_resume,
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index f3b5e6345858..4f64b814d4aa 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -326,7 +326,13 @@ static unsigned int xhci_ring_expansion_needed(struct xhci_hcd *xhci, struct xhc
 	/* how many trbs will be queued past the enqueue segment? */
 	trbs_past_seg = enq_used + num_trbs - (TRBS_PER_SEGMENT - 1);
 
-	if (trbs_past_seg <= 0)
+	/*
+	 * Consider expanding the ring already if num_trbs fills the current
+	 * segment (i.e. trbs_past_seg == 0), not only when num_trbs goes into
+	 * the next segment. Avoids confusing full ring with special empty ring
+	 * case below
+	 */
+	if (trbs_past_seg < 0)
 		return 0;
 
 	/* Empty ring special case, enqueue stuck on link trb while dequeue advanced */
@@ -366,9 +372,10 @@ void xhci_ring_cmd_db(struct xhci_hcd *xhci)
 	readl(&xhci->dba->doorbell[0]);
 }
 
-static bool xhci_mod_cmd_timer(struct xhci_hcd *xhci, unsigned long delay)
+static bool xhci_mod_cmd_timer(struct xhci_hcd *xhci)
 {
-	return mod_delayed_work(system_wq, &xhci->cmd_timer, delay);
+	return mod_delayed_work(system_wq, &xhci->cmd_timer,
+			msecs_to_jiffies(xhci->current_cmd->timeout_ms));
 }
 
 static struct xhci_command *xhci_next_queued_cmd(struct xhci_hcd *xhci)
@@ -412,7 +419,7 @@ static void xhci_handle_stopped_cmd_ring(struct xhci_hcd *xhci,
 	if ((xhci->cmd_ring->dequeue != xhci->cmd_ring->enqueue) &&
 	    !(xhci->xhc_state & XHCI_STATE_DYING)) {
 		xhci->current_cmd = cur_cmd;
-		xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT);
+		xhci_mod_cmd_timer(xhci);
 		xhci_ring_cmd_db(xhci);
 	}
 }
@@ -1787,7 +1794,7 @@ static void handle_cmd_completion(struct xhci_hcd *xhci,
 	if (!list_is_singular(&xhci->cmd_list)) {
 		xhci->current_cmd = list_first_entry(&cmd->cmd_list,
 						struct xhci_command, cmd_list);
-		xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT);
+		xhci_mod_cmd_timer(xhci);
 	} else if (xhci->current_cmd == cmd) {
 		xhci->current_cmd = NULL;
 	}
@@ -2375,6 +2382,9 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep,
 	/* handle completion code */
 	switch (trb_comp_code) {
 	case COMP_SUCCESS:
+		/* Don't overwrite status if TD had an error, see xHCI 4.9.1 */
+		if (td->error_mid_td)
+			break;
 		if (remaining) {
 			frame->status = short_framestatus;
 			if (xhci->quirks & XHCI_TRUST_TX_LENGTH)
@@ -2390,9 +2400,13 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep,
 	case COMP_BANDWIDTH_OVERRUN_ERROR:
 		frame->status = -ECOMM;
 		break;
-	case COMP_ISOCH_BUFFER_OVERRUN:
 	case COMP_BABBLE_DETECTED_ERROR:
+		sum_trbs_for_length = true;
+		fallthrough;
+	case COMP_ISOCH_BUFFER_OVERRUN:
 		frame->status = -EOVERFLOW;
+		if (ep_trb != td->last_trb)
+			td->error_mid_td = true;
 		break;
 	case COMP_INCOMPATIBLE_DEVICE_ERROR:
 	case COMP_STALL_ERROR:
@@ -2400,8 +2414,9 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep,
 		break;
 	case COMP_USB_TRANSACTION_ERROR:
 		frame->status = -EPROTO;
+		sum_trbs_for_length = true;
 		if (ep_trb != td->last_trb)
-			return 0;
+			td->error_mid_td = true;
 		break;
 	case COMP_STOPPED:
 		sum_trbs_for_length = true;
@@ -2421,6 +2436,9 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep,
 		break;
 	}
 
+	if (td->urb_length_set)
+		goto finish_td;
+
 	if (sum_trbs_for_length)
 		frame->actual_length = sum_trb_lengths(xhci, ep->ring, ep_trb) +
 			ep_trb_len - remaining;
@@ -2429,6 +2447,14 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep,
 
 	td->urb->actual_length += frame->actual_length;
 
+finish_td:
+	/* Don't give back TD yet if we encountered an error mid TD */
+	if (td->error_mid_td && ep_trb != td->last_trb) {
+		xhci_dbg(xhci, "Error mid isoc TD, wait for final completion event\n");
+		td->urb_length_set = true;
+		return 0;
+	}
+
 	return finish_td(xhci, ep, ep_ring, td, trb_comp_code);
 }
 
@@ -2807,17 +2833,51 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 		}
 
 		if (!ep_seg) {
-			if (!ep->skip ||
-			    !usb_endpoint_xfer_isoc(&td->urb->ep->desc)) {
-				/* Some host controllers give a spurious
-				 * successful event after a short transfer.
-				 * Ignore it.
-				 */
-				if ((xhci->quirks & XHCI_SPURIOUS_SUCCESS) &&
-						ep_ring->last_td_was_short) {
-					ep_ring->last_td_was_short = false;
-					goto cleanup;
+
+			if (ep->skip && usb_endpoint_xfer_isoc(&td->urb->ep->desc)) {
+				skip_isoc_td(xhci, td, ep, status);
+				goto cleanup;
+			}
+
+			/*
+			 * Some hosts give a spurious success event after a short
+			 * transfer. Ignore it.
+			 */
+			if ((xhci->quirks & XHCI_SPURIOUS_SUCCESS) &&
+			    ep_ring->last_td_was_short) {
+				ep_ring->last_td_was_short = false;
+				goto cleanup;
+			}
+
+			/*
+			 * xhci 4.10.2 states isoc endpoints should continue
+			 * processing the next TD if there was an error mid TD.
+			 * So host like NEC don't generate an event for the last
+			 * isoc TRB even if the IOC flag is set.
+			 * xhci 4.9.1 states that if there are errors in mult-TRB
+			 * TDs xHC should generate an error for that TRB, and if xHC
+			 * proceeds to the next TD it should genete an event for
+			 * any TRB with IOC flag on the way. Other host follow this.
+			 * So this event might be for the next TD.
+			 */
+			if (td->error_mid_td &&
+			    !list_is_last(&td->td_list, &ep_ring->td_list)) {
+				struct xhci_td *td_next = list_next_entry(td, td_list);
+
+				ep_seg = trb_in_td(xhci, td_next->start_seg, td_next->first_trb,
+						   td_next->last_trb, ep_trb_dma, false);
+				if (ep_seg) {
+					/* give back previous TD, start handling new */
+					xhci_dbg(xhci, "Missing TD completion event after mid TD error\n");
+					ep_ring->dequeue = td->last_trb;
+					ep_ring->deq_seg = td->last_trb_seg;
+					inc_deq(xhci, ep_ring);
+					xhci_td_cleanup(xhci, td, ep_ring, td->status);
+					td = td_next;
 				}
+			}
+
+			if (!ep_seg) {
 				/* HC is busted, give up! */
 				xhci_err(xhci,
 					"ERROR Transfer event TRB DMA ptr not "
@@ -2829,9 +2889,6 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 					  ep_trb_dma, true);
 				return -ESHUTDOWN;
 			}
-
-			skip_isoc_td(xhci, td, ep, status);
-			goto cleanup;
 		}
 		if (trb_comp_code == COMP_SHORT_PACKET)
 			ep_ring->last_td_was_short = true;
@@ -3060,7 +3117,7 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd)
 	writel(status, &xhci->op_regs->status);
 
 	/* This is the handler of the primary interrupter */
-	ir = xhci->interrupter;
+	ir = xhci->interrupters[0];
 	if (!hcd->msi_enabled) {
 		u32 irq_pending;
 		irq_pending = readl(&ir->ir_set->irq_pending);
@@ -4287,7 +4344,7 @@ static int queue_command(struct xhci_hcd *xhci, struct xhci_command *cmd,
 	/* if there are no other commands queued we start the timeout timer */
 	if (list_empty(&xhci->cmd_list)) {
 		xhci->current_cmd = cmd;
-		xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT);
+		xhci_mod_cmd_timer(xhci);
 	}
 
 	list_add_tail(&cmd->cmd_list, &xhci->cmd_list);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 884b0898d9c9..c057c42c36f4 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -480,7 +480,7 @@ static int xhci_init(struct usb_hcd *hcd)
 
 static int xhci_run_finished(struct xhci_hcd *xhci)
 {
-	struct xhci_interrupter *ir = xhci->interrupter;
+	struct xhci_interrupter *ir = xhci->interrupters[0];
 	unsigned long	flags;
 	u32		temp;
 
@@ -532,7 +532,7 @@ int xhci_run(struct usb_hcd *hcd)
 	u64 temp_64;
 	int ret;
 	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
-	struct xhci_interrupter *ir = xhci->interrupter;
+	struct xhci_interrupter *ir = xhci->interrupters[0];
 	/* Start the xHCI host controller running only after the USB 2.0 roothub
 	 * is setup.
 	 */
@@ -596,7 +596,7 @@ void xhci_stop(struct usb_hcd *hcd)
 {
 	u32 temp;
 	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
-	struct xhci_interrupter *ir = xhci->interrupter;
+	struct xhci_interrupter *ir = xhci->interrupters[0];
 
 	mutex_lock(&xhci->mutex);
 
@@ -692,36 +692,51 @@ EXPORT_SYMBOL_GPL(xhci_shutdown);
 #ifdef CONFIG_PM
 static void xhci_save_registers(struct xhci_hcd *xhci)
 {
-	struct xhci_interrupter *ir = xhci->interrupter;
+	struct xhci_interrupter *ir;
+	unsigned int i;
 
 	xhci->s3.command = readl(&xhci->op_regs->command);
 	xhci->s3.dev_nt = readl(&xhci->op_regs->dev_notification);
 	xhci->s3.dcbaa_ptr = xhci_read_64(xhci, &xhci->op_regs->dcbaa_ptr);
 	xhci->s3.config_reg = readl(&xhci->op_regs->config_reg);
 
-	if (!ir)
-		return;
+	/* save both primary and all secondary interrupters */
+	/* fixme, shold we lock  to prevent race with remove secondary interrupter? */
+	for (i = 0; i < xhci->max_interrupters; i++) {
+		ir = xhci->interrupters[i];
+		if (!ir)
+			continue;
 
-	ir->s3_erst_size = readl(&ir->ir_set->erst_size);
-	ir->s3_erst_base = xhci_read_64(xhci, &ir->ir_set->erst_base);
-	ir->s3_erst_dequeue = xhci_read_64(xhci, &ir->ir_set->erst_dequeue);
-	ir->s3_irq_pending = readl(&ir->ir_set->irq_pending);
-	ir->s3_irq_control = readl(&ir->ir_set->irq_control);
+		ir->s3_erst_size = readl(&ir->ir_set->erst_size);
+		ir->s3_erst_base = xhci_read_64(xhci, &ir->ir_set->erst_base);
+		ir->s3_erst_dequeue = xhci_read_64(xhci, &ir->ir_set->erst_dequeue);
+		ir->s3_irq_pending = readl(&ir->ir_set->irq_pending);
+		ir->s3_irq_control = readl(&ir->ir_set->irq_control);
+	}
 }
 
 static void xhci_restore_registers(struct xhci_hcd *xhci)
 {
-	struct xhci_interrupter *ir = xhci->interrupter;
+	struct xhci_interrupter *ir;
+	unsigned int i;
 
 	writel(xhci->s3.command, &xhci->op_regs->command);
 	writel(xhci->s3.dev_nt, &xhci->op_regs->dev_notification);
 	xhci_write_64(xhci, xhci->s3.dcbaa_ptr, &xhci->op_regs->dcbaa_ptr);
 	writel(xhci->s3.config_reg, &xhci->op_regs->config_reg);
-	writel(ir->s3_erst_size, &ir->ir_set->erst_size);
-	xhci_write_64(xhci, ir->s3_erst_base, &ir->ir_set->erst_base);
-	xhci_write_64(xhci, ir->s3_erst_dequeue, &ir->ir_set->erst_dequeue);
-	writel(ir->s3_irq_pending, &ir->ir_set->irq_pending);
-	writel(ir->s3_irq_control, &ir->ir_set->irq_control);
+
+	/* FIXME should we lock to protect against freeing of interrupters */
+	for (i = 0; i < xhci->max_interrupters; i++) {
+		ir = xhci->interrupters[i];
+		if (!ir)
+			continue;
+
+		writel(ir->s3_erst_size, &ir->ir_set->erst_size);
+		xhci_write_64(xhci, ir->s3_erst_base, &ir->ir_set->erst_base);
+		xhci_write_64(xhci, ir->s3_erst_dequeue, &ir->ir_set->erst_dequeue);
+		writel(ir->s3_irq_pending, &ir->ir_set->irq_pending);
+		writel(ir->s3_irq_control, &ir->ir_set->irq_control);
+	}
 }
 
 static void xhci_set_cmd_ring_deq(struct xhci_hcd *xhci)
@@ -1084,7 +1099,7 @@ int xhci_resume(struct xhci_hcd *xhci, pm_message_t msg)
 		xhci_dbg(xhci, "// Disabling event ring interrupts\n");
 		temp = readl(&xhci->op_regs->status);
 		writel((temp & ~0x1fff) | STS_EINT, &xhci->op_regs->status);
-		xhci_disable_interrupter(xhci->interrupter);
+		xhci_disable_interrupter(xhci->interrupters[0]);
 
 		xhci_dbg(xhci, "cleaning up memory\n");
 		xhci_mem_cleanup(xhci);
@@ -1438,10 +1453,8 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci,
  * descriptor.  If the usb_device's max packet size changes after that point,
  * we need to issue an evaluate context command and wait on it.
  */
-static int xhci_check_maxpacket(struct xhci_hcd *xhci, unsigned int slot_id,
-		unsigned int ep_index, struct urb *urb, gfp_t mem_flags)
+static int xhci_check_ep0_maxpacket(struct xhci_hcd *xhci, struct xhci_virt_device *vdev)
 {
-	struct xhci_container_ctx *out_ctx;
 	struct xhci_input_control_ctx *ctrl_ctx;
 	struct xhci_ep_ctx *ep_ctx;
 	struct xhci_command *command;
@@ -1449,11 +1462,15 @@ static int xhci_check_maxpacket(struct xhci_hcd *xhci, unsigned int slot_id,
 	int hw_max_packet_size;
 	int ret = 0;
 
-	out_ctx = xhci->devs[slot_id]->out_ctx;
-	ep_ctx = xhci_get_ep_ctx(xhci, out_ctx, ep_index);
+	ep_ctx = xhci_get_ep_ctx(xhci, vdev->out_ctx, 0);
 	hw_max_packet_size = MAX_PACKET_DECODED(le32_to_cpu(ep_ctx->ep_info2));
-	max_packet_size = usb_endpoint_maxp(&urb->dev->ep0.desc);
-	if (hw_max_packet_size != max_packet_size) {
+	max_packet_size = usb_endpoint_maxp(&vdev->udev->ep0.desc);
+
+	if (hw_max_packet_size == max_packet_size)
+		return 0;
+
+	switch (max_packet_size) {
+	case 8: case 16: case 32: case 64: case 9:
 		xhci_dbg_trace(xhci,  trace_xhci_dbg_context_change,
 				"Max Packet Size for ep 0 changed.");
 		xhci_dbg_trace(xhci,  trace_xhci_dbg_context_change,
@@ -1465,28 +1482,22 @@ static int xhci_check_maxpacket(struct xhci_hcd *xhci, unsigned int slot_id,
 		xhci_dbg_trace(xhci,  trace_xhci_dbg_context_change,
 				"Issuing evaluate context command.");
 
-		/* Set up the input context flags for the command */
-		/* FIXME: This won't work if a non-default control endpoint
-		 * changes max packet sizes.
-		 */
-
-		command = xhci_alloc_command(xhci, true, mem_flags);
+		command = xhci_alloc_command(xhci, true, GFP_KERNEL);
 		if (!command)
 			return -ENOMEM;
 
-		command->in_ctx = xhci->devs[slot_id]->in_ctx;
+		command->in_ctx = vdev->in_ctx;
 		ctrl_ctx = xhci_get_input_control_ctx(command->in_ctx);
 		if (!ctrl_ctx) {
 			xhci_warn(xhci, "%s: Could not get input context, bad type.\n",
 					__func__);
 			ret = -ENOMEM;
-			goto command_cleanup;
+			break;
 		}
 		/* Set up the modified control endpoint 0 */
-		xhci_endpoint_copy(xhci, xhci->devs[slot_id]->in_ctx,
-				xhci->devs[slot_id]->out_ctx, ep_index);
+		xhci_endpoint_copy(xhci, vdev->in_ctx, vdev->out_ctx, 0);
 
-		ep_ctx = xhci_get_ep_ctx(xhci, command->in_ctx, ep_index);
+		ep_ctx = xhci_get_ep_ctx(xhci, command->in_ctx, 0);
 		ep_ctx->ep_info &= cpu_to_le32(~EP_STATE_MASK);/* must clear */
 		ep_ctx->ep_info2 &= cpu_to_le32(~MAX_PACKET_MASK);
 		ep_ctx->ep_info2 |= cpu_to_le32(MAX_PACKET(max_packet_size));
@@ -1494,17 +1505,20 @@ static int xhci_check_maxpacket(struct xhci_hcd *xhci, unsigned int slot_id,
 		ctrl_ctx->add_flags = cpu_to_le32(EP0_FLAG);
 		ctrl_ctx->drop_flags = 0;
 
-		ret = xhci_configure_endpoint(xhci, urb->dev, command,
-				true, false);
-
-		/* Clean up the input context for later use by bandwidth
-		 * functions.
-		 */
+		ret = xhci_configure_endpoint(xhci, vdev->udev, command,
+					      true, false);
+		/* Clean up the input context for later use by bandwidth functions */
 		ctrl_ctx->add_flags = cpu_to_le32(SLOT_FLAG);
-command_cleanup:
-		kfree(command->completion);
-		kfree(command);
+		break;
+	default:
+		dev_dbg(&vdev->udev->dev, "incorrect max packet size %d for ep0\n",
+			max_packet_size);
+		return -EINVAL;
 	}
+
+	kfree(command->completion);
+	kfree(command);
+
 	return ret;
 }
 
@@ -1522,24 +1536,7 @@ static int xhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag
 	struct urb_priv	*urb_priv;
 	int num_tds;
 
-	if (!urb)
-		return -EINVAL;
-	ret = xhci_check_args(hcd, urb->dev, urb->ep,
-					true, true, __func__);
-	if (ret <= 0)
-		return ret ? ret : -EINVAL;
-
-	slot_id = urb->dev->slot_id;
 	ep_index = xhci_get_endpoint_index(&urb->ep->desc);
-	ep_state = &xhci->devs[slot_id]->eps[ep_index].ep_state;
-
-	if (!HCD_HW_ACCESSIBLE(hcd))
-		return -ESHUTDOWN;
-
-	if (xhci->devs[slot_id]->flags & VDEV_PORT_ERROR) {
-		xhci_dbg(xhci, "Can't queue urb, port error, link inactive\n");
-		return -ENODEV;
-	}
 
 	if (usb_endpoint_xfer_isoc(&urb->ep->desc))
 		num_tds = urb->number_of_packets;
@@ -1561,22 +1558,27 @@ static int xhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag
 
 	trace_xhci_urb_enqueue(urb);
 
-	if (usb_endpoint_xfer_control(&urb->ep->desc)) {
-		/* Check to see if the max packet size for the default control
-		 * endpoint changed during FS device enumeration
-		 */
-		if (urb->dev->speed == USB_SPEED_FULL) {
-			ret = xhci_check_maxpacket(xhci, slot_id,
-					ep_index, urb, mem_flags);
-			if (ret < 0) {
-				xhci_urb_free_priv(urb_priv);
-				urb->hcpriv = NULL;
-				return ret;
-			}
-		}
+	spin_lock_irqsave(&xhci->lock, flags);
+
+	ret = xhci_check_args(hcd, urb->dev, urb->ep,
+			      true, true, __func__);
+	if (ret <= 0) {
+		ret = ret ? ret : -EINVAL;
+		goto free_priv;
 	}
 
-	spin_lock_irqsave(&xhci->lock, flags);
+	slot_id = urb->dev->slot_id;
+
+	if (!HCD_HW_ACCESSIBLE(hcd)) {
+		ret = -ESHUTDOWN;
+		goto free_priv;
+	}
+
+	if (xhci->devs[slot_id]->flags & VDEV_PORT_ERROR) {
+		xhci_dbg(xhci, "Can't queue urb, port error, link inactive\n");
+		ret = -ENODEV;
+		goto free_priv;
+	}
 
 	if (xhci->xhc_state & XHCI_STATE_DYING) {
 		xhci_dbg(xhci, "Ep 0x%x: URB %p submitted for non-responsive xHCI host.\n",
@@ -1584,6 +1586,9 @@ static int xhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag
 		ret = -ESHUTDOWN;
 		goto free_priv;
 	}
+
+	ep_state = &xhci->devs[slot_id]->eps[ep_index].ep_state;
+
 	if (*ep_state & (EP_GETTING_STREAMS | EP_GETTING_NO_STREAMS)) {
 		xhci_warn(xhci, "WARN: Can't enqueue URB, ep in streams transition state %x\n",
 			  *ep_state);
@@ -3087,6 +3092,9 @@ done:
  * of an endpoint that isn't in the halted state this function will issue a
  * configure endpoint command with the Drop and Add bits set for the target
  * endpoint. Refer to the additional note in xhci spcification section 4.6.8.
+ *
+ * vdev may be lost due to xHC restore error and re-initialization during S3/S4
+ * resume. A new vdev will be allocated later by xhci_discover_or_reset_device()
  */
 
 static void xhci_endpoint_reset(struct usb_hcd *hcd,
@@ -3104,19 +3112,37 @@ static void xhci_endpoint_reset(struct usb_hcd *hcd,
 	int err;
 
 	xhci = hcd_to_xhci(hcd);
+	ep_index = xhci_get_endpoint_index(&host_ep->desc);
+
+	/*
+	 * Usb core assumes a max packet value for ep0 on FS devices until the
+	 * real value is read from the descriptor. Core resets Ep0 if values
+	 * mismatch. Reconfigure the xhci ep0 endpoint context here in that case
+	 */
+	if (usb_endpoint_xfer_control(&host_ep->desc) && ep_index == 0) {
+
+		udev = container_of(host_ep, struct usb_device, ep0);
+		if (udev->speed != USB_SPEED_FULL || !udev->slot_id)
+			return;
+
+		vdev = xhci->devs[udev->slot_id];
+		if (!vdev || vdev->udev != udev)
+			return;
+
+		xhci_check_ep0_maxpacket(xhci, vdev);
+
+		/* Nothing else should be done here for ep0 during ep reset */
+		return;
+	}
+
 	if (!host_ep->hcpriv)
 		return;
 	udev = (struct usb_device *) host_ep->hcpriv;
 	vdev = xhci->devs[udev->slot_id];
 
-	/*
-	 * vdev may be lost due to xHC restore error and re-initialization
-	 * during S3/S4 resume. A new vdev will be allocated later by
-	 * xhci_discover_or_reset_device()
-	 */
 	if (!udev->slot_id || !vdev)
 		return;
-	ep_index = xhci_get_endpoint_index(&host_ep->desc);
+
 	ep = &vdev->eps[ep_index];
 
 	/* Bail out if toggle is already being cleared by a endpoint reset */
@@ -4029,12 +4055,18 @@ disable_slot:
 	return 0;
 }
 
-/*
- * Issue an Address Device command and optionally send a corresponding
- * SetAddress request to the device.
+/**
+ * xhci_setup_device - issues an Address Device command to assign a unique
+ *			USB bus address.
+ * @hcd: USB host controller data structure.
+ * @udev: USB dev structure representing the connected device.
+ * @setup: Enum specifying setup mode: address only or with context.
+ * @timeout_ms: Max wait time (ms) for the command operation to complete.
+ *
+ * Return: 0 if successful; otherwise, negative error code.
  */
 static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev,
-			     enum xhci_setup_dev setup)
+			     enum xhci_setup_dev setup, unsigned int timeout_ms)
 {
 	const char *act = setup == SETUP_CONTEXT_ONLY ? "context" : "address";
 	unsigned long flags;
@@ -4091,6 +4123,7 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev,
 	}
 
 	command->in_ctx = virt_dev->in_ctx;
+	command->timeout_ms = timeout_ms;
 
 	slot_ctx = xhci_get_slot_ctx(xhci, virt_dev->in_ctx);
 	ctrl_ctx = xhci_get_input_control_ctx(virt_dev->in_ctx);
@@ -4217,14 +4250,16 @@ out:
 	return ret;
 }
 
-static int xhci_address_device(struct usb_hcd *hcd, struct usb_device *udev)
+static int xhci_address_device(struct usb_hcd *hcd, struct usb_device *udev,
+			       unsigned int timeout_ms)
 {
-	return xhci_setup_device(hcd, udev, SETUP_CONTEXT_ADDRESS);
+	return xhci_setup_device(hcd, udev, SETUP_CONTEXT_ADDRESS, timeout_ms);
 }
 
 static int xhci_enable_device(struct usb_hcd *hcd, struct usb_device *udev)
 {
-	return xhci_setup_device(hcd, udev, SETUP_CONTEXT_ONLY);
+	return xhci_setup_device(hcd, udev, SETUP_CONTEXT_ONLY,
+				 XHCI_CMD_DEFAULT_TIMEOUT);
 }
 
 /*
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 3ea5c092bba7..6f82d404883f 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -791,6 +791,8 @@ struct xhci_command {
 	struct completion		*completion;
 	union xhci_trb			*command_trb;
 	struct list_head		cmd_list;
+	/* xHCI command response timeout in milliseconds */
+	unsigned int			timeout_ms;
 };
 
 /* drop context bitmasks */
@@ -1547,11 +1549,15 @@ struct xhci_td {
 	struct xhci_segment	*bounce_seg;
 	/* actual_length of the URB has already been set */
 	bool			urb_length_set;
+	bool			error_mid_td;
 	unsigned int		num_trbs;
 };
 
-/* xHCI command default timeout value */
-#define XHCI_CMD_DEFAULT_TIMEOUT	(5 * HZ)
+/*
+ * xHCI command default timeout value in milliseconds.
+ * USB 3.2 spec, section 9.2.6.1
+ */
+#define XHCI_CMD_DEFAULT_TIMEOUT	5000
 
 /* command descriptor */
 struct xhci_cd {
@@ -1760,8 +1766,8 @@ struct xhci_hcd {
 	int		page_size;
 	/* Valid values are 12 to 20, inclusive */
 	int		page_shift;
-	/* msi-x vectors */
-	int		msix_count;
+	/* MSI-X/MSI vectors */
+	int		nvecs;
 	/* optional clocks */
 	struct clk		*clk;
 	struct clk		*reg_clk;
@@ -1769,7 +1775,7 @@ struct xhci_hcd {
 	struct reset_control *reset;
 	/* data structures */
 	struct xhci_device_context_array *dcbaa;
-	struct xhci_interrupter *interrupter;
+	struct xhci_interrupter **interrupters;
 	struct xhci_ring	*cmd_ring;
 	unsigned int            cmd_ring_state;
 #define CMD_RING_STATE_RUNNING         (1 << 0)
@@ -2080,6 +2086,10 @@ struct xhci_container_ctx *xhci_alloc_container_ctx(struct xhci_hcd *xhci,
 		int type, gfp_t flags);
 void xhci_free_container_ctx(struct xhci_hcd *xhci,
 		struct xhci_container_ctx *ctx);
+struct xhci_interrupter *
+xhci_create_secondary_interrupter(struct usb_hcd *hcd, int num_seg);
+void xhci_remove_secondary_interrupter(struct usb_hcd
+				       *hcd, struct xhci_interrupter *ir);
 
 /* xHCI host controller glue */
 typedef void (*xhci_get_quirks_t)(struct device *, struct xhci_hcd *);
diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c
index 1e3df27bab58..6d28467ce352 100644
--- a/drivers/usb/misc/iowarrior.c
+++ b/drivers/usb/misc/iowarrior.c
@@ -501,7 +501,6 @@ static long iowarrior_ioctl(struct file *file, unsigned int cmd,
 		dev->minor, cmd, arg);
 
 	retval = 0;
-	io_res = 0;
 	switch (cmd) {
 	case IOW_WRITE:
 		if (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW24 ||
diff --git a/drivers/usb/misc/onboard_usb_hub.c b/drivers/usb/misc/onboard_usb_hub.c
index 2b45404e9732..0dd2b032c90b 100644
--- a/drivers/usb/misc/onboard_usb_hub.c
+++ b/drivers/usb/misc/onboard_usb_hub.c
@@ -5,8 +5,10 @@
  * Copyright (c) 2022, Google LLC
  */
 
+#include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/export.h>
+#include <linux/err.h>
 #include <linux/gpio/consumer.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -60,15 +62,22 @@ struct onboard_hub {
 	bool going_away;
 	struct list_head udev_list;
 	struct mutex lock;
+	struct clk *clk;
 };
 
 static int onboard_hub_power_on(struct onboard_hub *hub)
 {
 	int err;
 
+	err = clk_prepare_enable(hub->clk);
+	if (err) {
+		dev_err(hub->dev, "failed to enable clock: %pe\n", ERR_PTR(err));
+		return err;
+	}
+
 	err = regulator_bulk_enable(hub->pdata->num_supplies, hub->supplies);
 	if (err) {
-		dev_err(hub->dev, "failed to enable supplies: %d\n", err);
+		dev_err(hub->dev, "failed to enable supplies: %pe\n", ERR_PTR(err));
 		return err;
 	}
 
@@ -88,10 +97,12 @@ static int onboard_hub_power_off(struct onboard_hub *hub)
 
 	err = regulator_bulk_disable(hub->pdata->num_supplies, hub->supplies);
 	if (err) {
-		dev_err(hub->dev, "failed to disable supplies: %d\n", err);
+		dev_err(hub->dev, "failed to disable supplies: %pe\n", ERR_PTR(err));
 		return err;
 	}
 
+	clk_disable_unprepare(hub->clk);
+
 	hub->is_powered_on = false;
 
 	return 0;
@@ -233,9 +244,9 @@ static void onboard_hub_attach_usb_driver(struct work_struct *work)
 {
 	int err;
 
-	err = driver_attach(&onboard_hub_usbdev_driver.drvwrap.driver);
+	err = driver_attach(&onboard_hub_usbdev_driver.driver);
 	if (err)
-		pr_err("Failed to attach USB driver: %d\n", err);
+		pr_err("Failed to attach USB driver: %pe\n", ERR_PTR(err));
 }
 
 static int onboard_hub_probe(struct platform_device *pdev)
@@ -262,10 +273,14 @@ static int onboard_hub_probe(struct platform_device *pdev)
 
 	err = devm_regulator_bulk_get(dev, hub->pdata->num_supplies, hub->supplies);
 	if (err) {
-		dev_err(dev, "Failed to get regulator supplies: %d\n", err);
+		dev_err(dev, "Failed to get regulator supplies: %pe\n", ERR_PTR(err));
 		return err;
 	}
 
+	hub->clk = devm_clk_get_optional(dev, NULL);
+	if (IS_ERR(hub->clk))
+		return dev_err_probe(dev, PTR_ERR(hub->clk), "failed to get clock\n");
+
 	hub->reset_gpio = devm_gpiod_get_optional(dev, "reset",
 						  GPIOD_OUT_HIGH);
 	if (IS_ERR(hub->reset_gpio))
@@ -426,6 +441,7 @@ static void onboard_hub_usbdev_disconnect(struct usb_device *udev)
 static const struct usb_device_id onboard_hub_id_table[] = {
 	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6504) }, /* CYUSB33{0,1,2}x/CYUSB230x 3.0 */
 	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6506) }, /* CYUSB33{0,1,2}x/CYUSB230x 2.0 */
+	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6570) }, /* CY7C6563x 2.0 */
 	{ USB_DEVICE(VENDOR_ID_GENESYS, 0x0608) }, /* Genesys Logic GL850G USB 2.0 */
 	{ USB_DEVICE(VENDOR_ID_GENESYS, 0x0610) }, /* Genesys Logic GL852G USB 2.0 */
 	{ USB_DEVICE(VENDOR_ID_GENESYS, 0x0620) }, /* Genesys Logic GL3523 USB 3.1 */
diff --git a/drivers/usb/misc/onboard_usb_hub.h b/drivers/usb/misc/onboard_usb_hub.h
index 292110e64a1d..f360d5cf8d8a 100644
--- a/drivers/usb/misc/onboard_usb_hub.h
+++ b/drivers/usb/misc/onboard_usb_hub.h
@@ -36,6 +36,11 @@ static const struct onboard_hub_pdata cypress_hx3_data = {
 	.num_supplies = 2,
 };
 
+static const struct onboard_hub_pdata cypress_hx2vl_data = {
+	.reset_us = 1,
+	.num_supplies = 1,
+};
+
 static const struct onboard_hub_pdata genesys_gl850g_data = {
 	.reset_us = 3,
 	.num_supplies = 1,
@@ -61,6 +66,7 @@ static const struct of_device_id onboard_hub_match[] = {
 	{ .compatible = "usb451,8142", .data = &ti_tusb8041_data, },
 	{ .compatible = "usb4b4,6504", .data = &cypress_hx3_data, },
 	{ .compatible = "usb4b4,6506", .data = &cypress_hx3_data, },
+	{ .compatible = "usb4b4,6570", .data = &cypress_hx2vl_data, },
 	{ .compatible = "usb5e3,608", .data = &genesys_gl850g_data, },
 	{ .compatible = "usb5e3,610", .data = &genesys_gl852g_data, },
 	{ .compatible = "usb5e3,620", .data = &genesys_gl852g_data, },
diff --git a/drivers/usb/misc/qcom_eud.c b/drivers/usb/misc/qcom_eud.c
index 7f371ea1248c..26e9b8749d8a 100644
--- a/drivers/usb/misc/qcom_eud.c
+++ b/drivers/usb/misc/qcom_eud.c
@@ -205,6 +205,9 @@ static int eud_probe(struct platform_device *pdev)
 		return PTR_ERR(chip->mode_mgr);
 
 	chip->irq = platform_get_irq(pdev, 0);
+	if (chip->irq < 0)
+		return chip->irq;
+
 	ret = devm_request_threaded_irq(&pdev->dev, chip->irq, handle_eud_irq,
 			handle_eud_irq_thread, IRQF_ONESHOT, NULL, chip);
 	if (ret)
diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c
index c640f98d20c5..9a0649d23693 100644
--- a/drivers/usb/misc/yurex.c
+++ b/drivers/usb/misc/yurex.c
@@ -34,6 +34,8 @@
 #define YUREX_BUF_SIZE		8
 #define YUREX_WRITE_TIMEOUT	(HZ*2)
 
+#define MAX_S64_STRLEN 20 /* {-}922337203685477580{7,8} */
+
 /* table of devices that work with this driver */
 static struct usb_device_id yurex_table[] = {
 	{ USB_DEVICE(YUREX_VENDOR_ID, YUREX_PRODUCT_ID) },
@@ -401,7 +403,7 @@ static ssize_t yurex_read(struct file *file, char __user *buffer, size_t count,
 {
 	struct usb_yurex *dev;
 	int len = 0;
-	char in_buffer[20];
+	char in_buffer[MAX_S64_STRLEN];
 	unsigned long flags;
 
 	dev = file->private_data;
@@ -412,14 +414,16 @@ static ssize_t yurex_read(struct file *file, char __user *buffer, size_t count,
 		return -ENODEV;
 	}
 
+	if (WARN_ON_ONCE(dev->bbu > S64_MAX || dev->bbu < S64_MIN)) {
+		mutex_unlock(&dev->io_mutex);
+		return -EIO;
+	}
+
 	spin_lock_irqsave(&dev->lock, flags);
-	len = snprintf(in_buffer, 20, "%lld\n", dev->bbu);
+	scnprintf(in_buffer, MAX_S64_STRLEN, "%lld\n", dev->bbu);
 	spin_unlock_irqrestore(&dev->lock, flags);
 	mutex_unlock(&dev->io_mutex);
 
-	if (WARN_ON_ONCE(len >= sizeof(in_buffer)))
-		return -EIO;
-
 	return simple_read_from_buffer(buffer, count, ppos, in_buffer, len);
 }
 
diff --git a/drivers/usb/mon/mon_bin.c b/drivers/usb/mon/mon_bin.c
index 9ca9305243fe..4e30de4db1c0 100644
--- a/drivers/usb/mon/mon_bin.c
+++ b/drivers/usb/mon/mon_bin.c
@@ -1250,14 +1250,19 @@ static vm_fault_t mon_bin_vma_fault(struct vm_fault *vmf)
 	struct mon_reader_bin *rp = vmf->vma->vm_private_data;
 	unsigned long offset, chunk_idx;
 	struct page *pageptr;
+	unsigned long flags;
 
+	spin_lock_irqsave(&rp->b_lock, flags);
 	offset = vmf->pgoff << PAGE_SHIFT;
-	if (offset >= rp->b_size)
+	if (offset >= rp->b_size) {
+		spin_unlock_irqrestore(&rp->b_lock, flags);
 		return VM_FAULT_SIGBUS;
+	}
 	chunk_idx = offset / CHUNK_SIZE;
 	pageptr = rp->b_vec[chunk_idx].pg;
 	get_page(pageptr);
 	vmf->page = pageptr;
+	spin_unlock_irqrestore(&rp->b_lock, flags);
 	return 0;
 }
 
diff --git a/drivers/usb/mon/mon_stat.c b/drivers/usb/mon/mon_stat.c
index 98ab0cc473d6..3c23805ab1a4 100644
--- a/drivers/usb/mon/mon_stat.c
+++ b/drivers/usb/mon/mon_stat.c
@@ -35,9 +35,9 @@ static int mon_stat_open(struct inode *inode, struct file *file)
 
 	mbus = inode->i_private;
 
-	sp->slen = snprintf(sp->str, STAT_BUF_SIZE,
-	    "nreaders %d events %u text_lost %u\n",
-	    mbus->nreaders, mbus->cnt_events, mbus->cnt_text_lost);
+	sp->slen = scnprintf(sp->str, STAT_BUF_SIZE,
+			     "nreaders %d events %u text_lost %u\n",
+			     mbus->nreaders, mbus->cnt_events, mbus->cnt_text_lost);
 
 	file->private_data = sp;
 	return 0;
diff --git a/drivers/usb/mon/mon_text.c b/drivers/usb/mon/mon_text.c
index 39cb14164652..2fe9b95bac1d 100644
--- a/drivers/usb/mon/mon_text.c
+++ b/drivers/usb/mon/mon_text.c
@@ -352,7 +352,7 @@ static int mon_text_open(struct inode *inode, struct file *file)
 	rp->r.rnf_error = mon_text_error;
 	rp->r.rnf_complete = mon_text_complete;
 
-	snprintf(rp->slab_name, SLAB_NAME_SZ, "mon_text_%p", rp);
+	scnprintf(rp->slab_name, SLAB_NAME_SZ, "mon_text_%p", rp);
 	rp->e_slab = kmem_cache_create(rp->slab_name,
 	    sizeof(struct mon_event_text), sizeof(long), 0,
 	    mon_text_ctor);
@@ -700,46 +700,28 @@ static const struct file_operations mon_fops_text_u = {
 
 int mon_text_add(struct mon_bus *mbus, const struct usb_bus *ubus)
 {
-	enum { NAMESZ = 10 };
+	enum { NAMESZ = 12 };
 	char name[NAMESZ];
 	int busnum = ubus? ubus->busnum: 0;
-	int rc;
 
 	if (mon_dir == NULL)
 		return 0;
 
 	if (ubus != NULL) {
-		rc = snprintf(name, NAMESZ, "%dt", busnum);
-		if (rc <= 0 || rc >= NAMESZ)
-			goto err_print_t;
+		scnprintf(name, NAMESZ, "%dt", busnum);
 		mbus->dent_t = debugfs_create_file(name, 0600, mon_dir, mbus,
 							     &mon_fops_text_t);
 	}
 
-	rc = snprintf(name, NAMESZ, "%du", busnum);
-	if (rc <= 0 || rc >= NAMESZ)
-		goto err_print_u;
+	scnprintf(name, NAMESZ, "%du", busnum);
 	mbus->dent_u = debugfs_create_file(name, 0600, mon_dir, mbus,
 					   &mon_fops_text_u);
 
-	rc = snprintf(name, NAMESZ, "%ds", busnum);
-	if (rc <= 0 || rc >= NAMESZ)
-		goto err_print_s;
+	scnprintf(name, NAMESZ, "%ds", busnum);
 	mbus->dent_s = debugfs_create_file(name, 0600, mon_dir, mbus,
 					   &mon_fops_stat);
 
 	return 1;
-
-err_print_s:
-	debugfs_remove(mbus->dent_u);
-	mbus->dent_u = NULL;
-err_print_u:
-	if (ubus != NULL) {
-		debugfs_remove(mbus->dent_t);
-		mbus->dent_t = NULL;
-	}
-err_print_t:
-	return 0;
 }
 
 void mon_text_del(struct mon_bus *mbus)
diff --git a/drivers/usb/phy/phy-generic.c b/drivers/usb/phy/phy-generic.c
index 770081b828a4..9ab50f26db60 100644
--- a/drivers/usb/phy/phy-generic.c
+++ b/drivers/usb/phy/phy-generic.c
@@ -46,15 +46,21 @@ EXPORT_SYMBOL_GPL(usb_phy_generic_unregister);
 static int nop_set_suspend(struct usb_phy *x, int suspend)
 {
 	struct usb_phy_generic *nop = dev_get_drvdata(x->dev);
+	int ret = 0;
 
-	if (!IS_ERR(nop->clk)) {
-		if (suspend)
+	if (suspend) {
+		if (!IS_ERR(nop->clk))
 			clk_disable_unprepare(nop->clk);
-		else
+		if (!IS_ERR(nop->vcc) && !device_may_wakeup(x->dev))
+			ret = regulator_disable(nop->vcc);
+	} else {
+		if (!IS_ERR(nop->vcc) && !device_may_wakeup(x->dev))
+			ret = regulator_enable(nop->vcc);
+		if (!IS_ERR(nop->clk))
 			clk_prepare_enable(nop->clk);
 	}
 
-	return 0;
+	return ret;
 }
 
 static void nop_reset(struct usb_phy_generic *nop)
diff --git a/drivers/usb/phy/phy-mxs-usb.c b/drivers/usb/phy/phy-mxs-usb.c
index acd46b72899e..920a32cd094d 100644
--- a/drivers/usb/phy/phy-mxs-usb.c
+++ b/drivers/usb/phy/phy-mxs-usb.c
@@ -388,8 +388,7 @@ static void __mxs_phy_disconnect_line(struct mxs_phy *mxs_phy, bool disconnect)
 
 static bool mxs_phy_is_otg_host(struct mxs_phy *mxs_phy)
 {
-	return IS_ENABLED(CONFIG_USB_OTG) &&
-		mxs_phy->phy.last_event == USB_EVENT_ID;
+	return mxs_phy->phy.last_event == USB_EVENT_ID;
 }
 
 static void mxs_phy_disconnect_line(struct mxs_phy *mxs_phy, bool on)
diff --git a/drivers/usb/phy/phy-twl6030-usb.c b/drivers/usb/phy/phy-twl6030-usb.c
index c3ce6b1054f1..da09cff55abc 100644
--- a/drivers/usb/phy/phy-twl6030-usb.c
+++ b/drivers/usb/phy/phy-twl6030-usb.c
@@ -179,16 +179,16 @@ static ssize_t vbus_show(struct device *dev,
 
 	switch (twl->linkstat) {
 	case MUSB_VBUS_VALID:
-	       ret = snprintf(buf, PAGE_SIZE, "vbus\n");
+	       ret = sysfs_emit(buf, "vbus\n");
 	       break;
 	case MUSB_ID_GROUND:
-	       ret = snprintf(buf, PAGE_SIZE, "id\n");
+	       ret = sysfs_emit(buf, "id\n");
 	       break;
 	case MUSB_VBUS_OFF:
-	       ret = snprintf(buf, PAGE_SIZE, "none\n");
+	       ret = sysfs_emit(buf, "none\n");
 	       break;
 	default:
-	       ret = snprintf(buf, PAGE_SIZE, "UNKNOWN\n");
+	       ret = sysfs_emit(buf, "UNKNOWN\n");
 	}
 	spin_unlock_irqrestore(&twl->lock, flags);
 
diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c
index ae41578bd014..70165dd86b5d 100644
--- a/drivers/usb/roles/class.c
+++ b/drivers/usb/roles/class.c
@@ -21,7 +21,9 @@ static const struct class role_class = {
 struct usb_role_switch {
 	struct device dev;
 	struct mutex lock; /* device lock*/
+	struct module *module; /* the module this device depends on */
 	enum usb_role role;
+	bool registered;
 
 	/* From descriptor */
 	struct device *usb2_port;
@@ -48,6 +50,9 @@ int usb_role_switch_set_role(struct usb_role_switch *sw, enum usb_role role)
 	if (IS_ERR_OR_NULL(sw))
 		return 0;
 
+	if (!sw->registered)
+		return -EOPNOTSUPP;
+
 	mutex_lock(&sw->lock);
 
 	ret = sw->set(sw, role);
@@ -73,7 +78,7 @@ enum usb_role usb_role_switch_get_role(struct usb_role_switch *sw)
 {
 	enum usb_role role;
 
-	if (IS_ERR_OR_NULL(sw))
+	if (IS_ERR_OR_NULL(sw) || !sw->registered)
 		return USB_ROLE_NONE;
 
 	mutex_lock(&sw->lock);
@@ -135,7 +140,7 @@ struct usb_role_switch *usb_role_switch_get(struct device *dev)
 						  usb_role_switch_match);
 
 	if (!IS_ERR_OR_NULL(sw))
-		WARN_ON(!try_module_get(sw->dev.parent->driver->owner));
+		WARN_ON(!try_module_get(sw->module));
 
 	return sw;
 }
@@ -157,7 +162,7 @@ struct usb_role_switch *fwnode_usb_role_switch_get(struct fwnode_handle *fwnode)
 		sw = fwnode_connection_find_match(fwnode, "usb-role-switch",
 						  NULL, usb_role_switch_match);
 	if (!IS_ERR_OR_NULL(sw))
-		WARN_ON(!try_module_get(sw->dev.parent->driver->owner));
+		WARN_ON(!try_module_get(sw->module));
 
 	return sw;
 }
@@ -172,7 +177,7 @@ EXPORT_SYMBOL_GPL(fwnode_usb_role_switch_get);
 void usb_role_switch_put(struct usb_role_switch *sw)
 {
 	if (!IS_ERR_OR_NULL(sw)) {
-		module_put(sw->dev.parent->driver->owner);
+		module_put(sw->module);
 		put_device(&sw->dev);
 	}
 }
@@ -189,15 +194,18 @@ struct usb_role_switch *
 usb_role_switch_find_by_fwnode(const struct fwnode_handle *fwnode)
 {
 	struct device *dev;
+	struct usb_role_switch *sw = NULL;
 
 	if (!fwnode)
 		return NULL;
 
 	dev = class_find_device_by_fwnode(&role_class, fwnode);
-	if (dev)
-		WARN_ON(!try_module_get(dev->parent->driver->owner));
+	if (dev) {
+		sw = to_role_switch(dev);
+		WARN_ON(!try_module_get(sw->module));
+	}
 
-	return dev ? to_role_switch(dev) : NULL;
+	return sw;
 }
 EXPORT_SYMBOL_GPL(usb_role_switch_find_by_fwnode);
 
@@ -338,6 +346,7 @@ usb_role_switch_register(struct device *parent,
 	sw->set = desc->set;
 	sw->get = desc->get;
 
+	sw->module = parent->driver->owner;
 	sw->dev.parent = parent;
 	sw->dev.fwnode = desc->fwnode;
 	sw->dev.class = &role_class;
@@ -352,6 +361,8 @@ usb_role_switch_register(struct device *parent,
 		return ERR_PTR(ret);
 	}
 
+	sw->registered = true;
+
 	/* TODO: Symlinks for the host port and the device controller. */
 
 	return sw;
@@ -366,8 +377,10 @@ EXPORT_SYMBOL_GPL(usb_role_switch_register);
  */
 void usb_role_switch_unregister(struct usb_role_switch *sw)
 {
-	if (!IS_ERR_OR_NULL(sw))
+	if (!IS_ERR_OR_NULL(sw)) {
+		sw->registered = false;
 		device_unregister(&sw->dev);
+	}
 }
 EXPORT_SYMBOL_GPL(usb_role_switch_unregister);
 
diff --git a/drivers/usb/serial/bus.c b/drivers/usb/serial/bus.c
index 3eb8dc3a1a8f..6c812d01b37d 100644
--- a/drivers/usb/serial/bus.c
+++ b/drivers/usb/serial/bus.c
@@ -113,7 +113,7 @@ static ssize_t new_id_store(struct device_driver *driver,
 	if (retval >= 0 && usb_drv->usb_driver != NULL)
 		retval = usb_store_new_id(&usb_drv->usb_driver->dynids,
 					  usb_drv->usb_driver->id_table,
-					  &usb_drv->usb_driver->drvwrap.driver,
+					  &usb_drv->usb_driver->driver,
 					  buf, count);
 	return retval;
 }
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 1e61fe043171..923e0ed85444 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -146,6 +146,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */
 	{ USB_DEVICE(0x10C4, 0x8664) }, /* AC-Services CAN-IF */
 	{ USB_DEVICE(0x10C4, 0x8665) }, /* AC-Services OBD-IF */
+	{ USB_DEVICE(0x10C4, 0x87ED) }, /* IMST USB-Stick for Smart Meter */
 	{ USB_DEVICE(0x10C4, 0x8856) },	/* CEL EM357 ZigBee USB Stick - LR */
 	{ USB_DEVICE(0x10C4, 0x8857) },	/* CEL EM357 ZigBee USB Stick */
 	{ USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 72390dbf0769..2ae124c49d44 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -2269,6 +2269,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0111, 0xff) },			/* Fibocom FM160 (MBIM mode) */
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) },			/* Fibocom NL668-AM/NL652-EU (laptop MBIM) */
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a2, 0xff) },			/* Fibocom FM101-GL (laptop MBIM) */
+	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a3, 0xff) },			/* Fibocom FM101-GL (laptop MBIM) */
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a4, 0xff),			/* Fibocom FM101-GL (laptop MBIM) */
 	  .driver_info = RSVD(4) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) },			/* LongSung M5710 */
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index b1e844bf31f8..703a9c563557 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -184,6 +184,8 @@ static const struct usb_device_id id_table[] = {
 	{DEVICE_SWI(0x413c, 0x81d0)},   /* Dell Wireless 5819 */
 	{DEVICE_SWI(0x413c, 0x81d1)},   /* Dell Wireless 5818 */
 	{DEVICE_SWI(0x413c, 0x81d2)},   /* Dell Wireless 5818 */
+	{DEVICE_SWI(0x413c, 0x8217)},	/* Dell Wireless DW5826e */
+	{DEVICE_SWI(0x413c, 0x8218)},	/* Dell Wireless DW5826e QDL */
 
 	/* Huawei devices */
 	{DEVICE_HWI(0x03f0, 0x581d)},	/* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index 17b09f03ef84..f1e91eb7f8a4 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -1521,7 +1521,7 @@ int usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[]
 
 	/* Now set udriver's id_table and look for matches */
 	udriver->id_table = id_table;
-	rc = driver_attach(&udriver->drvwrap.driver);
+	rc = driver_attach(&udriver->driver);
 	return 0;
 
 err_deregister_drivers:
diff --git a/drivers/usb/storage/isd200.c b/drivers/usb/storage/isd200.c
index 4e0eef1440b7..300aeef160e7 100644
--- a/drivers/usb/storage/isd200.c
+++ b/drivers/usb/storage/isd200.c
@@ -1105,7 +1105,7 @@ static void isd200_dump_driveid(struct us_data *us, u16 *id)
 static int isd200_get_inquiry_data( struct us_data *us )
 {
 	struct isd200_info *info = (struct isd200_info *)us->extra;
-	int retStatus = ISD200_GOOD;
+	int retStatus;
 	u16 *id = info->id;
 
 	usb_stor_dbg(us, "Entering isd200_get_inquiry_data\n");
@@ -1137,6 +1137,13 @@ static int isd200_get_inquiry_data( struct us_data *us )
 				isd200_fix_driveid(id);
 				isd200_dump_driveid(us, id);
 
+				/* Prevent division by 0 in isd200_scsi_to_ata() */
+				if (id[ATA_ID_HEADS] == 0 || id[ATA_ID_SECTORS] == 0) {
+					usb_stor_dbg(us, "   Invalid ATA Identify data\n");
+					retStatus = ISD200_ERROR;
+					goto Done;
+				}
+
 				memset(&info->InquiryData, 0, sizeof(info->InquiryData));
 
 				/* Standard IDE interface only supports disks */
@@ -1202,6 +1209,7 @@ static int isd200_get_inquiry_data( struct us_data *us )
 		}
 	}
 
+ Done:
 	usb_stor_dbg(us, "Leaving isd200_get_inquiry_data %08X\n", retStatus);
 
 	return(retStatus);
@@ -1481,22 +1489,27 @@ static int isd200_init_info(struct us_data *us)
 
 static int isd200_Initialization(struct us_data *us)
 {
+	int rc = 0;
+
 	usb_stor_dbg(us, "ISD200 Initialization...\n");
 
 	/* Initialize ISD200 info struct */
 
-	if (isd200_init_info(us) == ISD200_ERROR) {
+	if (isd200_init_info(us) < 0) {
 		usb_stor_dbg(us, "ERROR Initializing ISD200 Info struct\n");
+		rc = -ENOMEM;
 	} else {
 		/* Get device specific data */
 
-		if (isd200_get_inquiry_data(us) != ISD200_GOOD)
+		if (isd200_get_inquiry_data(us) != ISD200_GOOD) {
 			usb_stor_dbg(us, "ISD200 Initialization Failure\n");
-		else
+			rc = -EINVAL;
+		} else {
 			usb_stor_dbg(us, "ISD200 Initialization complete\n");
+		}
 	}
 
-	return 0;
+	return rc;
 }
 
 
diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c
index c54e9805da53..12cf9940e5b6 100644
--- a/drivers/usb/storage/scsiglue.c
+++ b/drivers/usb/storage/scsiglue.c
@@ -180,6 +180,13 @@ static int slave_configure(struct scsi_device *sdev)
 		sdev->use_192_bytes_for_3f = 1;
 
 		/*
+		 * Some devices report generic values until the media has been
+		 * accessed. Force a READ(10) prior to querying device
+		 * characteristics.
+		 */
+		sdev->read_before_ms = 1;
+
+		/*
 		 * Some devices don't like MODE SENSE with page=0x3f,
 		 * which is the command used for checking if a device
 		 * is write-protected.  Now that we tell the sd driver
diff --git a/drivers/usb/storage/sierra_ms.c b/drivers/usb/storage/sierra_ms.c
index 0774ba22fb66..177fa6cd143a 100644
--- a/drivers/usb/storage/sierra_ms.c
+++ b/drivers/usb/storage/sierra_ms.c
@@ -98,26 +98,26 @@ static ssize_t truinst_show(struct device *dev, struct device_attribute *attr,
 	struct usb_device *udev = interface_to_usbdev(intf);
 	int result;
 	if (swi_tru_install == TRU_FORCE_MS) {
-		result = snprintf(buf, PAGE_SIZE, "Forced Mass Storage\n");
+		result = sysfs_emit(buf, "Forced Mass Storage\n");
 	} else {
 		swocInfo = kmalloc(sizeof(struct swoc_info), GFP_KERNEL);
 		if (!swocInfo) {
-			snprintf(buf, PAGE_SIZE, "Error\n");
+			sysfs_emit(buf, "Error\n");
 			return -ENOMEM;
 		}
 		result = sierra_get_swoc_info(udev, swocInfo);
 		if (result < 0) {
 			dev_dbg(dev, "SWIMS: failed SWoC query\n");
 			kfree(swocInfo);
-			snprintf(buf, PAGE_SIZE, "Error\n");
+			sysfs_emit(buf, "Error\n");
 			return -EIO;
 		}
 		debug_swoc(dev, swocInfo);
-		result = snprintf(buf, PAGE_SIZE,
-			"REV=%02d SKU=%04X VER=%04X\n",
-			swocInfo->rev,
-			swocInfo->LinuxSKU,
-			swocInfo->LinuxVer);
+		result = sysfs_emit(buf,
+				    "REV=%02d SKU=%04X VER=%04X\n",
+				    swocInfo->rev,
+				    swocInfo->LinuxSKU,
+				    swocInfo->LinuxVer);
 		kfree(swocInfo);
 	}
 	return result;
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 696bb0b23599..71ace274761f 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -879,6 +879,13 @@ static int uas_slave_configure(struct scsi_device *sdev)
 		sdev->guess_capacity = 1;
 
 	/*
+	 * Some devices report generic values until the media has been
+	 * accessed. Force a READ(10) prior to querying device
+	 * characteristics.
+	 */
+	sdev->read_before_ms = 1;
+
+	/*
 	 * Some devices don't like MODE SENSE with page=0x3f,
 	 * which is the command used for checking if a device
 	 * is write-protected.  Now that we tell the sd driver
@@ -1246,7 +1253,7 @@ static struct usb_driver uas_driver = {
 	.suspend = uas_suspend,
 	.resume = uas_resume,
 	.reset_resume = uas_reset_resume,
-	.drvwrap.driver.shutdown = uas_shutdown,
+	.driver.shutdown = uas_shutdown,
 	.id_table = uas_usb_ids,
 };
 
diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c
index f81bec0c7b86..f8ea3054be54 100644
--- a/drivers/usb/typec/altmodes/displayport.c
+++ b/drivers/usb/typec/altmodes/displayport.c
@@ -559,16 +559,21 @@ static ssize_t hpd_show(struct device *dev, struct device_attribute *attr, char
 }
 static DEVICE_ATTR_RO(hpd);
 
-static struct attribute *dp_altmode_attrs[] = {
+static struct attribute *displayport_attrs[] = {
 	&dev_attr_configuration.attr,
 	&dev_attr_pin_assignment.attr,
 	&dev_attr_hpd.attr,
 	NULL
 };
 
-static const struct attribute_group dp_altmode_group = {
+static const struct attribute_group displayport_group = {
 	.name = "displayport",
-	.attrs = dp_altmode_attrs,
+	.attrs = displayport_attrs,
+};
+
+static const struct attribute_group *displayport_groups[] = {
+	&displayport_group,
+	NULL,
 };
 
 int dp_altmode_probe(struct typec_altmode *alt)
@@ -576,7 +581,6 @@ int dp_altmode_probe(struct typec_altmode *alt)
 	const struct typec_altmode *port = typec_altmode_get_partner(alt);
 	struct fwnode_handle *fwnode;
 	struct dp_altmode *dp;
-	int ret;
 
 	/* FIXME: Port can only be DFP_U. */
 
@@ -587,10 +591,6 @@ int dp_altmode_probe(struct typec_altmode *alt)
 	      DP_CAP_PIN_ASSIGN_DFP_D(alt->vdo)))
 		return -ENODEV;
 
-	ret = sysfs_create_group(&alt->dev.kobj, &dp_altmode_group);
-	if (ret)
-		return ret;
-
 	dp = devm_kzalloc(&alt->dev, sizeof(*dp), GFP_KERNEL);
 	if (!dp)
 		return -ENOMEM;
@@ -624,7 +624,6 @@ void dp_altmode_remove(struct typec_altmode *alt)
 {
 	struct dp_altmode *dp = typec_altmode_get_drvdata(alt);
 
-	sysfs_remove_group(&alt->dev.kobj, &dp_altmode_group);
 	cancel_work_sync(&dp->work);
 
 	if (dp->connector_fwnode) {
@@ -649,6 +648,7 @@ static struct typec_altmode_driver dp_altmode_driver = {
 	.driver = {
 		.name = "typec_displayport",
 		.owner = THIS_MODULE,
+		.dev_groups = displayport_groups,
 	},
 };
 module_typec_altmode_driver(dp_altmode_driver);
diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index 16a670828dde..015aa9253353 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -263,11 +263,13 @@ static void typec_altmode_put_partner(struct altmode *altmode)
 {
 	struct altmode *partner = altmode->partner;
 	struct typec_altmode *adev;
+	struct typec_altmode *partner_adev;
 
 	if (!partner)
 		return;
 
 	adev = &altmode->adev;
+	partner_adev = &partner->adev;
 
 	if (is_typec_plug(adev->dev.parent)) {
 		struct typec_plug *plug = to_typec_plug(adev->dev.parent);
@@ -276,7 +278,7 @@ static void typec_altmode_put_partner(struct altmode *altmode)
 	} else {
 		partner->partner = NULL;
 	}
-	put_device(&adev->dev);
+	put_device(&partner_adev->dev);
 }
 
 /**
@@ -476,7 +478,7 @@ static int altmode_id_get(struct device *dev)
 	else
 		ids = &to_typec_port(dev)->mode_ids;
 
-	return ida_simple_get(ids, 0, 0, GFP_KERNEL);
+	return ida_alloc(ids, GFP_KERNEL);
 }
 
 static void altmode_id_remove(struct device *dev, int id)
@@ -490,7 +492,7 @@ static void altmode_id_remove(struct device *dev, int id)
 	else
 		ids = &to_typec_port(dev)->mode_ids;
 
-	ida_simple_remove(ids, id);
+	ida_free(ids, id);
 }
 
 static void typec_altmode_release(struct device *dev)
@@ -1798,7 +1800,7 @@ static void typec_release(struct device *dev)
 {
 	struct typec_port *port = to_typec_port(dev);
 
-	ida_simple_remove(&typec_index_ida, port->id);
+	ida_free(&typec_index_ida, port->id);
 	ida_destroy(&port->mode_ids);
 	typec_switch_put(port->sw);
 	typec_mux_put(port->mux);
@@ -2231,7 +2233,8 @@ void typec_port_register_altmodes(struct typec_port *port,
 	struct typec_altmode_desc desc;
 	struct typec_altmode *alt;
 	size_t index = 0;
-	u32 svid, vdo;
+	u16 svid;
+	u32 vdo;
 	int ret;
 
 	altmodes_node = device_get_named_child_node(&port->dev, "altmodes");
@@ -2239,7 +2242,7 @@ void typec_port_register_altmodes(struct typec_port *port,
 		return; /* No altmodes specified */
 
 	fwnode_for_each_child_node(altmodes_node, child) {
-		ret = fwnode_property_read_u32(child, "svid", &svid);
+		ret = fwnode_property_read_u16(child, "svid", &svid);
 		if (ret) {
 			dev_err(&port->dev, "Error reading svid for altmode %s\n",
 				fwnode_get_name(child));
@@ -2297,7 +2300,7 @@ struct typec_port *typec_register_port(struct device *parent,
 	if (!port)
 		return ERR_PTR(-ENOMEM);
 
-	id = ida_simple_get(&typec_index_ida, 0, 0, GFP_KERNEL);
+	id = ida_alloc(&typec_index_ida, GFP_KERNEL);
 	if (id < 0) {
 		kfree(port);
 		return ERR_PTR(id);
diff --git a/drivers/usb/typec/mux/Kconfig b/drivers/usb/typec/mux/Kconfig
index 38416fb0cc3c..d2cb5e733e57 100644
--- a/drivers/usb/typec/mux/Kconfig
+++ b/drivers/usb/typec/mux/Kconfig
@@ -56,4 +56,14 @@ config TYPEC_MUX_PTN36502
 	  Say Y or M if your system has a NXP PTN36502 Type-C redriver chip
 	  found on some devices with a Type-C port.
 
+config TYPEC_MUX_WCD939X_USBSS
+	tristate "Qualcomm WCD939x USBSS Analog Audio Switch driver"
+	depends on I2C
+	select REGMAP_I2C
+	help
+	  Driver for the Qualcomm WCD939x Audio Codec USBSS domain which
+	  provides support for muxing analog audio and sideband signals on a
+	  common USB Type-C connector.
+	  If compiled as a module, the module will be named wcd939x-usbss.
+
 endmenu
diff --git a/drivers/usb/typec/mux/Makefile b/drivers/usb/typec/mux/Makefile
index 9d6a5557b0bd..57dc9ac6f8dc 100644
--- a/drivers/usb/typec/mux/Makefile
+++ b/drivers/usb/typec/mux/Makefile
@@ -6,3 +6,4 @@ obj-$(CONFIG_TYPEC_MUX_PI3USB30532)	+= pi3usb30532.o
 obj-$(CONFIG_TYPEC_MUX_INTEL_PMC)	+= intel_pmc_mux.o
 obj-$(CONFIG_TYPEC_MUX_NB7VPQ904M)	+= nb7vpq904m.o
 obj-$(CONFIG_TYPEC_MUX_PTN36502)	+= ptn36502.o
+obj-$(CONFIG_TYPEC_MUX_WCD939X_USBSS)	+= wcd939x-usbss.o
diff --git a/drivers/usb/typec/mux/wcd939x-usbss.c b/drivers/usb/typec/mux/wcd939x-usbss.c
new file mode 100644
index 000000000000..d46c353dfaf2
--- /dev/null
+++ b/drivers/usb/typec/mux/wcd939x-usbss.c
@@ -0,0 +1,779 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (C) 2023 Linaro Ltd.
+ */
+
+#include <linux/bits.h>
+#include <linux/i2c.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/regmap.h>
+#include <linux/bitfield.h>
+#include <linux/gpio/consumer.h>
+#include <linux/usb/typec_dp.h>
+#include <linux/usb/typec_mux.h>
+
+#define WCD_USBSS_PMP_OUT1			0x2
+
+#define WCD_USBSS_DP_DN_MISC1			0x20
+
+#define WCD_USBSS_DP_DN_MISC1_DP_PCOMP_2X_DYN_BST_ON_EN			BIT(3)
+#define WCD_USBSS_DP_DN_MISC1_DN_PCOMP_2X_DYN_BST_ON_EN			BIT(0)
+
+#define WCD_USBSS_MG1_EN			0x24
+
+#define WCD_USBSS_MG1_EN_CT_SNS_EN					BIT(1)
+
+#define WCD_USBSS_MG1_BIAS			0x25
+
+#define WCD_USBSS_MG1_BIAS_PCOMP_DYN_BST_EN				BIT(3)
+
+#define WCD_USBSS_MG1_MISC			0x27
+
+#define WCD_USBSS_MG1_MISC_PCOMP_2X_DYN_BST_ON_EN			BIT(5)
+
+#define WCD_USBSS_MG2_EN			0x28
+
+#define WCD_USBSS_MG2_EN_CT_SNS_EN					BIT(1)
+
+#define WCD_USBSS_MG2_BIAS			0x29
+
+#define WCD_USBSS_MG2_BIAS_PCOMP_DYN_BST_EN				BIT(3)
+
+#define WCD_USBSS_MG2_MISC			0x30
+
+#define WCD_USBSS_MG2_MISC_PCOMP_2X_DYN_BST_ON_EN			BIT(5)
+
+#define WCD_USBSS_DISP_AUXP_THRESH		0x80
+
+#define WCD_USBSS_DISP_AUXP_THRESH_DISP_AUXP_OVPON_CM			GENMASK(7, 5)
+
+#define WCD_USBSS_DISP_AUXP_CTL			0x81
+
+#define WCD_USBSS_DISP_AUXP_CTL_LK_CANCEL_TRK_COEFF			GENMASK(2, 0)
+
+#define WCD_USBSS_CPLDO_CTL2			0xa1
+
+#define WCD_USBSS_SWITCH_SETTINGS_ENABLE	0x403
+
+#define WCD_USBSS_SWITCH_SETTINGS_ENABLE_DEVICE_ENABLE			BIT(7)
+#define WCD_USBSS_SWITCH_SETTINGS_ENABLE_DP_AUXP_TO_MGX_SWITCHES	BIT(6)
+#define WCD_USBSS_SWITCH_SETTINGS_ENABLE_DP_AUXM_TO_MGX_SWITCHES	BIT(5)
+#define WCD_USBSS_SWITCH_SETTINGS_ENABLE_DNL_SWITCHES			BIT(4)
+#define WCD_USBSS_SWITCH_SETTINGS_ENABLE_DPR_SWITCHES			BIT(3)
+#define WCD_USBSS_SWITCH_SETTINGS_ENABLE_SENSE_SWITCHES			BIT(2)
+#define WCD_USBSS_SWITCH_SETTINGS_ENABLE_MIC_SWITCHES			BIT(1)
+#define WCD_USBSS_SWITCH_SETTINGS_ENABLE_AGND_SWITCHES			BIT(0)
+
+#define WCD_USBSS_SWITCH_SELECT0		0x404
+
+#define WCD_USBSS_SWITCH_SELECT0_DP_AUXP_SWITCHES			BIT(7)	/* 1-> MG2 */
+#define WCD_USBSS_SWITCH_SELECT0_DP_AUXM_SWITCHES			BIT(6)	/* 1-> MG2 */
+#define WCD_USBSS_SWITCH_SELECT0_DNL_SWITCHES				GENMASK(5, 4)
+#define WCD_USBSS_SWITCH_SELECT0_DPR_SWITCHES				GENMASK(3, 2)
+#define WCD_USBSS_SWITCH_SELECT0_SENSE_SWITCHES				BIT(1)	/* 1-> SBU2 */
+#define WCD_USBSS_SWITCH_SELECT0_MIC_SWITCHES				BIT(0)	/* 1-> MG2 */
+
+#define WCD_USBSS_SWITCH_SELECT0_DNL_SWITCH_L		0
+#define WCD_USBSS_SWITCH_SELECT0_DNL_SWITCH_DN		1
+#define WCD_USBSS_SWITCH_SELECT0_DNL_SWITCH_DN2		2
+
+#define WCD_USBSS_SWITCH_SELECT0_DPR_SWITCH_R		0
+#define WCD_USBSS_SWITCH_SELECT0_DPR_SWITCH_DP		1
+#define WCD_USBSS_SWITCH_SELECT0_DPR_SWITCH_DR2		2
+
+#define WCD_USBSS_SWITCH_SELECT1		0x405
+
+#define WCD_USBSS_SWITCH_SELECT1_AGND_SWITCHES				BIT(0)	/* 1-> MG2 */
+
+#define WCD_USBSS_DELAY_R_SW			0x40d
+#define WCD_USBSS_DELAY_MIC_SW			0x40e
+#define WCD_USBSS_DELAY_SENSE_SW		0x40f
+#define WCD_USBSS_DELAY_GND_SW			0x410
+#define WCD_USBSS_DELAY_L_SW			0x411
+
+#define WCD_USBSS_FUNCTION_ENABLE		0x413
+
+#define WCD_USBSS_FUNCTION_ENABLE_SOURCE_SELECT				GENMASK(1, 0)
+
+#define WCD_USBSS_FUNCTION_ENABLE_SOURCE_SELECT_MANUAL		1
+#define WCD_USBSS_FUNCTION_ENABLE_SOURCE_SELECT_AUDIO_FSM	2
+
+#define WCD_USBSS_EQUALIZER1			0x415
+
+#define WCD_USBSS_EQUALIZER1_EQ_EN					BIT(7)
+#define WCD_USBSS_EQUALIZER1_BW_SETTINGS				GENMASK(6, 3)
+
+#define WCD_USBSS_USB_SS_CNTL			0x419
+
+#define WCD_USBSS_USB_SS_CNTL_STANDBY_STATE				BIT(4)
+#define WCD_USBSS_USB_SS_CNTL_RCO_EN					BIT(3)
+#define WCD_USBSS_USB_SS_CNTL_USB_SS_MODE				GENMASK(2, 0)
+
+#define WCD_USBSS_USB_SS_CNTL_USB_SS_MODE_AATC		2
+#define WCD_USBSS_USB_SS_CNTL_USB_SS_MODE_USB		5
+
+#define WCD_USBSS_AUDIO_FSM_START		0x433
+
+#define WCD_USBSS_AUDIO_FSM_START_AUDIO_FSM_AUDIO_TRIG			BIT(0)
+
+#define WCD_USBSS_RATIO_SPKR_REXT_L_LSB		0x461
+#define WCD_USBSS_RATIO_SPKR_REXT_L_MSB		0x462
+#define WCD_USBSS_RATIO_SPKR_REXT_R_LSB		0x463
+#define WCD_USBSS_RATIO_SPKR_REXT_R_MSB		0x464
+#define WCD_USBSS_AUD_COEF_L_K0_0		0x475
+#define WCD_USBSS_AUD_COEF_L_K0_1		0x476
+#define WCD_USBSS_AUD_COEF_L_K0_2		0x477
+#define WCD_USBSS_AUD_COEF_L_K1_0		0x478
+#define WCD_USBSS_AUD_COEF_L_K1_1		0x479
+#define WCD_USBSS_AUD_COEF_L_K2_0		0x47a
+#define WCD_USBSS_AUD_COEF_L_K2_1		0x47b
+#define WCD_USBSS_AUD_COEF_L_K3_0		0x47c
+#define WCD_USBSS_AUD_COEF_L_K3_1		0x47d
+#define WCD_USBSS_AUD_COEF_L_K4_0		0x47e
+#define WCD_USBSS_AUD_COEF_L_K4_1		0x47f
+#define WCD_USBSS_AUD_COEF_L_K5_0		0x480
+#define WCD_USBSS_AUD_COEF_L_K5_1		0x481
+#define WCD_USBSS_AUD_COEF_R_K0_0		0x482
+#define WCD_USBSS_AUD_COEF_R_K0_1		0x483
+#define WCD_USBSS_AUD_COEF_R_K0_2		0x484
+#define WCD_USBSS_AUD_COEF_R_K1_0		0x485
+#define WCD_USBSS_AUD_COEF_R_K1_1		0x486
+#define WCD_USBSS_AUD_COEF_R_K2_0		0x487
+#define WCD_USBSS_AUD_COEF_R_K2_1		0x488
+#define WCD_USBSS_AUD_COEF_R_K3_0		0x489
+#define WCD_USBSS_AUD_COEF_R_K3_1		0x48a
+#define WCD_USBSS_AUD_COEF_R_K4_0		0x48b
+#define WCD_USBSS_AUD_COEF_R_K4_1		0x48c
+#define WCD_USBSS_AUD_COEF_R_K5_0		0x48d
+#define WCD_USBSS_AUD_COEF_R_K5_1		0x48e
+#define WCD_USBSS_GND_COEF_L_K0_0		0x48f
+#define WCD_USBSS_GND_COEF_L_K0_1		0x490
+#define WCD_USBSS_GND_COEF_L_K0_2		0x491
+#define WCD_USBSS_GND_COEF_L_K1_0		0x492
+#define WCD_USBSS_GND_COEF_L_K1_1		0x493
+#define WCD_USBSS_GND_COEF_L_K2_0		0x494
+#define WCD_USBSS_GND_COEF_L_K2_1		0x495
+#define WCD_USBSS_GND_COEF_L_K3_0		0x496
+#define WCD_USBSS_GND_COEF_L_K3_1		0x497
+#define WCD_USBSS_GND_COEF_L_K4_0		0x498
+#define WCD_USBSS_GND_COEF_L_K4_1		0x499
+#define WCD_USBSS_GND_COEF_L_K5_0		0x49a
+#define WCD_USBSS_GND_COEF_L_K5_1		0x49b
+#define WCD_USBSS_GND_COEF_R_K0_0		0x49c
+#define WCD_USBSS_GND_COEF_R_K0_1		0x49d
+#define WCD_USBSS_GND_COEF_R_K0_2		0x49e
+#define WCD_USBSS_GND_COEF_R_K1_0		0x49f
+#define WCD_USBSS_GND_COEF_R_K1_1		0x4a0
+#define WCD_USBSS_GND_COEF_R_K2_0		0x4a1
+#define WCD_USBSS_GND_COEF_R_K2_1		0x4a2
+#define WCD_USBSS_GND_COEF_R_K3_0		0x4a3
+#define WCD_USBSS_GND_COEF_R_K3_1		0x4a4
+#define WCD_USBSS_GND_COEF_R_K4_0		0x4a5
+#define WCD_USBSS_GND_COEF_R_K4_1		0x4a6
+#define WCD_USBSS_GND_COEF_R_K5_0		0x4a7
+#define WCD_USBSS_GND_COEF_R_K5_1		0x4a8
+
+#define WCD_USBSS_MAX_REGISTER			0x4c1
+
+struct wcd939x_usbss {
+	struct i2c_client *client;
+	struct gpio_desc *reset_gpio;
+	struct regulator *vdd_supply;
+
+	/* used to serialize concurrent change requests */
+	struct mutex lock;
+
+	struct typec_switch_dev *sw;
+	struct typec_mux_dev *mux;
+
+	struct regmap *regmap;
+
+	struct typec_mux *codec;
+	struct typec_switch *codec_switch;
+
+	enum typec_orientation orientation;
+	unsigned long mode;
+	unsigned int svid;
+};
+
+static const struct regmap_range_cfg wcd939x_usbss_ranges[] = {
+	{
+		.range_min = 0,
+		.range_max = WCD_USBSS_MAX_REGISTER,
+		.selector_reg = 0x0,
+		.selector_mask = 0xff,
+		.selector_shift = 0,
+		.window_start = 0,
+		.window_len = 0x100,
+	},
+};
+
+static const struct regmap_config wcd939x_usbss_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = WCD_USBSS_MAX_REGISTER,
+	.ranges = wcd939x_usbss_ranges,
+	.num_ranges = ARRAY_SIZE(wcd939x_usbss_ranges),
+};
+
+/* Linearlizer coefficients for 32ohm load */
+static const struct {
+	unsigned int offset;
+	unsigned int mask;
+	unsigned int value;
+} wcd939x_usbss_coeff_init[] = {
+	{ WCD_USBSS_AUD_COEF_L_K5_0, GENMASK(7, 0), 0x39 },
+	{ WCD_USBSS_AUD_COEF_R_K5_0, GENMASK(7, 0), 0x39 },
+	{ WCD_USBSS_GND_COEF_L_K2_0, GENMASK(7, 0), 0xe8 },
+	{ WCD_USBSS_GND_COEF_L_K4_0, GENMASK(7, 0), 0x73 },
+	{ WCD_USBSS_GND_COEF_R_K2_0, GENMASK(7, 0), 0xe8 },
+	{ WCD_USBSS_GND_COEF_R_K4_0, GENMASK(7, 0), 0x73 },
+	{ WCD_USBSS_RATIO_SPKR_REXT_L_LSB, GENMASK(7, 0), 0x00 },
+	{ WCD_USBSS_RATIO_SPKR_REXT_L_MSB, GENMASK(6, 0), 0x04 },
+	{ WCD_USBSS_RATIO_SPKR_REXT_R_LSB, GENMASK(7, 0), 0x00 },
+	{ WCD_USBSS_RATIO_SPKR_REXT_R_MSB, GENMASK(6, 0), 0x04 },
+};
+
+static int wcd939x_usbss_set(struct wcd939x_usbss *usbss)
+{
+	bool reverse = (usbss->orientation == TYPEC_ORIENTATION_REVERSE);
+	bool enable_audio = false;
+	bool enable_usb = false;
+	bool enable_dp = false;
+	int ret;
+
+	/* USB Mode */
+	if (usbss->mode < TYPEC_STATE_MODAL ||
+	    (!usbss->svid && (usbss->mode == TYPEC_MODE_USB2 ||
+			      usbss->mode == TYPEC_MODE_USB3))) {
+		enable_usb = true;
+	} else if (usbss->svid) {
+		switch (usbss->mode) {
+		/* DP Only */
+		case TYPEC_DP_STATE_C:
+		case TYPEC_DP_STATE_E:
+			enable_dp = true;
+			break;
+
+		/* DP + USB */
+		case TYPEC_DP_STATE_D:
+		case TYPEC_DP_STATE_F:
+			enable_usb = true;
+			enable_dp = true;
+			break;
+
+		default:
+			return -EOPNOTSUPP;
+		}
+	} else if (usbss->mode == TYPEC_MODE_AUDIO) {
+		enable_audio = true;
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	/* Disable all switches */
+	ret = regmap_clear_bits(usbss->regmap, WCD_USBSS_SWITCH_SETTINGS_ENABLE,
+				WCD_USBSS_SWITCH_SETTINGS_ENABLE_DP_AUXP_TO_MGX_SWITCHES |
+				WCD_USBSS_SWITCH_SETTINGS_ENABLE_DP_AUXM_TO_MGX_SWITCHES |
+				WCD_USBSS_SWITCH_SETTINGS_ENABLE_DPR_SWITCHES |
+				WCD_USBSS_SWITCH_SETTINGS_ENABLE_DNL_SWITCHES |
+				WCD_USBSS_SWITCH_SETTINGS_ENABLE_SENSE_SWITCHES |
+				WCD_USBSS_SWITCH_SETTINGS_ENABLE_MIC_SWITCHES |
+				WCD_USBSS_SWITCH_SETTINGS_ENABLE_AGND_SWITCHES);
+	if (ret)
+		return ret;
+
+	/* Clear switches */
+	ret = regmap_clear_bits(usbss->regmap, WCD_USBSS_SWITCH_SELECT0,
+				WCD_USBSS_SWITCH_SELECT0_DP_AUXP_SWITCHES |
+				WCD_USBSS_SWITCH_SELECT0_DP_AUXM_SWITCHES |
+				WCD_USBSS_SWITCH_SELECT0_DPR_SWITCHES |
+				WCD_USBSS_SWITCH_SELECT0_DNL_SWITCHES |
+				WCD_USBSS_SWITCH_SELECT0_SENSE_SWITCHES |
+				WCD_USBSS_SWITCH_SELECT0_MIC_SWITCHES);
+	if (ret)
+		return ret;
+
+	ret = regmap_clear_bits(usbss->regmap, WCD_USBSS_SWITCH_SELECT1,
+				WCD_USBSS_SWITCH_SELECT1_AGND_SWITCHES);
+	if (ret)
+		return ret;
+
+	/* Enable OVP_MG1_BIAS PCOMP_DYN_BST_EN */
+	ret = regmap_set_bits(usbss->regmap, WCD_USBSS_MG1_BIAS,
+			      WCD_USBSS_MG1_BIAS_PCOMP_DYN_BST_EN);
+	if (ret)
+		return ret;
+
+	/* Enable OVP_MG2_BIAS PCOMP_DYN_BST_EN */
+	ret = regmap_set_bits(usbss->regmap, WCD_USBSS_MG2_BIAS,
+			      WCD_USBSS_MG2_BIAS_PCOMP_DYN_BST_EN);
+	if (ret)
+		return ret;
+
+	/* Disable Equalizer in safe mode */
+	ret = regmap_clear_bits(usbss->regmap, WCD_USBSS_EQUALIZER1,
+				WCD_USBSS_EQUALIZER1_EQ_EN);
+	if (ret)
+		return ret;
+
+	/* Start FSM with all disabled, force write */
+	ret = regmap_write_bits(usbss->regmap, WCD_USBSS_AUDIO_FSM_START,
+				WCD_USBSS_AUDIO_FSM_START_AUDIO_FSM_AUDIO_TRIG,
+				WCD_USBSS_AUDIO_FSM_START_AUDIO_FSM_AUDIO_TRIG);
+
+	/* 35us to allow the SBU switch to turn off */
+	usleep_range(35, 1000);
+
+	/* Setup Audio Accessory mux/switch */
+	if (enable_audio) {
+		int i;
+
+		/*
+		 * AATC switch configuration:
+		 * "Normal":
+		 * - R: DNR
+		 * - L: DNL
+		 * - Sense: GSBU2
+		 * - Mic: MG1
+		 * - AGND: MG2
+		 * "Swapped":
+		 * - R: DNR
+		 * - L: DNL
+		 * - Sense: GSBU1
+		 * - Mic: MG2
+		 * - AGND: MG1
+		 * Swapped information is given by the codec MBHC logic
+		 */
+
+		/* Set AATC mode */
+		ret = regmap_update_bits(usbss->regmap, WCD_USBSS_USB_SS_CNTL,
+					 WCD_USBSS_USB_SS_CNTL_USB_SS_MODE,
+					 FIELD_PREP(WCD_USBSS_USB_SS_CNTL_USB_SS_MODE,
+						    WCD_USBSS_USB_SS_CNTL_USB_SS_MODE_AATC));
+		if (ret)
+			return ret;
+
+		/* Select L for DNL_SWITCHES and R for DPR_SWITCHES */
+		ret = regmap_update_bits(usbss->regmap, WCD_USBSS_SWITCH_SELECT0,
+				WCD_USBSS_SWITCH_SELECT0_DPR_SWITCHES |
+				WCD_USBSS_SWITCH_SELECT0_DNL_SWITCHES,
+				FIELD_PREP(WCD_USBSS_SWITCH_SELECT0_DNL_SWITCHES,
+					WCD_USBSS_SWITCH_SELECT0_DNL_SWITCH_L) |
+				FIELD_PREP(WCD_USBSS_SWITCH_SELECT0_DPR_SWITCHES,
+					WCD_USBSS_SWITCH_SELECT0_DPR_SWITCH_R));
+		if (ret)
+			return ret;
+
+		if (reverse)
+			/* Select MG2 for MIC, SBU1 for Sense */
+			ret = regmap_update_bits(usbss->regmap, WCD_USBSS_SWITCH_SELECT0,
+						 WCD_USBSS_SWITCH_SELECT0_MIC_SWITCHES,
+						 WCD_USBSS_SWITCH_SELECT0_MIC_SWITCHES);
+		else
+			/* Select MG1 for MIC, SBU2 for Sense */
+			ret = regmap_update_bits(usbss->regmap, WCD_USBSS_SWITCH_SELECT0,
+						 WCD_USBSS_SWITCH_SELECT0_SENSE_SWITCHES,
+						 WCD_USBSS_SWITCH_SELECT0_SENSE_SWITCHES);
+		if (ret)
+			return ret;
+
+		if (reverse)
+			/* Disable OVP_MG1_BIAS PCOMP_DYN_BST_EN */
+			ret = regmap_clear_bits(usbss->regmap, WCD_USBSS_MG1_BIAS,
+						WCD_USBSS_MG1_BIAS_PCOMP_DYN_BST_EN);
+		else
+			/* Disable OVP_MG2_BIAS PCOMP_DYN_BST_EN */
+			ret = regmap_clear_bits(usbss->regmap, WCD_USBSS_MG2_BIAS,
+						WCD_USBSS_MG2_BIAS_PCOMP_DYN_BST_EN);
+		if (ret)
+			return ret;
+
+		/*  Enable SENSE, MIC switches */
+		ret = regmap_set_bits(usbss->regmap, WCD_USBSS_SWITCH_SETTINGS_ENABLE,
+				      WCD_USBSS_SWITCH_SETTINGS_ENABLE_SENSE_SWITCHES |
+				      WCD_USBSS_SWITCH_SETTINGS_ENABLE_MIC_SWITCHES);
+		if (ret)
+			return ret;
+
+		if (reverse)
+			/* Select MG1 for AGND_SWITCHES */
+			ret = regmap_clear_bits(usbss->regmap, WCD_USBSS_SWITCH_SELECT1,
+						WCD_USBSS_SWITCH_SELECT1_AGND_SWITCHES);
+		else
+			/* Select MG2 for AGND_SWITCHES */
+			ret = regmap_set_bits(usbss->regmap, WCD_USBSS_SWITCH_SELECT1,
+					      WCD_USBSS_SWITCH_SELECT1_AGND_SWITCHES);
+		if (ret)
+			return ret;
+
+		/* Enable AGND switches */
+		ret = regmap_set_bits(usbss->regmap, WCD_USBSS_SWITCH_SETTINGS_ENABLE,
+				      WCD_USBSS_SWITCH_SETTINGS_ENABLE_AGND_SWITCHES);
+		if (ret)
+			return ret;
+
+		/* Enable DPR, DNL switches */
+		ret = regmap_set_bits(usbss->regmap, WCD_USBSS_SWITCH_SETTINGS_ENABLE,
+				      WCD_USBSS_SWITCH_SETTINGS_ENABLE_DNL_SWITCHES |
+				      WCD_USBSS_SWITCH_SETTINGS_ENABLE_DPR_SWITCHES);
+		if (ret)
+			return ret;
+
+		/* Setup FSM delays */
+		ret = regmap_write(usbss->regmap, WCD_USBSS_DELAY_L_SW, 0x02);
+		if (ret)
+			return ret;
+
+		ret = regmap_write(usbss->regmap, WCD_USBSS_DELAY_R_SW, 0x02);
+		if (ret)
+			return ret;
+
+		ret = regmap_write(usbss->regmap, WCD_USBSS_DELAY_MIC_SW, 0x01);
+		if (ret)
+			return ret;
+
+		/* Start FSM, force write */
+		ret = regmap_write_bits(usbss->regmap, WCD_USBSS_AUDIO_FSM_START,
+					WCD_USBSS_AUDIO_FSM_START_AUDIO_FSM_AUDIO_TRIG,
+					WCD_USBSS_AUDIO_FSM_START_AUDIO_FSM_AUDIO_TRIG);
+		if (ret)
+			return ret;
+
+		/* Default Linearlizer coefficients */
+		for (i = 0; i < ARRAY_SIZE(wcd939x_usbss_coeff_init); ++i)
+			regmap_update_bits(usbss->regmap,
+					   wcd939x_usbss_coeff_init[i].offset,
+					   wcd939x_usbss_coeff_init[i].mask,
+					   wcd939x_usbss_coeff_init[i].value);
+
+		return 0;
+	}
+
+	ret = regmap_update_bits(usbss->regmap, WCD_USBSS_USB_SS_CNTL,
+				 WCD_USBSS_USB_SS_CNTL_USB_SS_MODE,
+				 FIELD_PREP(WCD_USBSS_USB_SS_CNTL_USB_SS_MODE,
+					    WCD_USBSS_USB_SS_CNTL_USB_SS_MODE_USB));
+	if (ret)
+		return ret;
+
+	/* Enable USB muxes */
+	if (enable_usb) {
+		/* Do not enable Equalizer in safe mode */
+		if (usbss->mode != TYPEC_STATE_SAFE) {
+			ret = regmap_set_bits(usbss->regmap, WCD_USBSS_EQUALIZER1,
+					      WCD_USBSS_EQUALIZER1_EQ_EN);
+			if (ret)
+				return ret;
+		}
+
+		/* Select DN for DNL_SWITCHES and DP for DPR_SWITCHES */
+		ret = regmap_update_bits(usbss->regmap, WCD_USBSS_SWITCH_SELECT0,
+					 WCD_USBSS_SWITCH_SELECT0_DPR_SWITCHES |
+					 WCD_USBSS_SWITCH_SELECT0_DNL_SWITCHES,
+					 FIELD_PREP(WCD_USBSS_SWITCH_SELECT0_DNL_SWITCHES,
+						    WCD_USBSS_SWITCH_SELECT0_DNL_SWITCH_DN) |
+					 FIELD_PREP(WCD_USBSS_SWITCH_SELECT0_DPR_SWITCHES,
+						    WCD_USBSS_SWITCH_SELECT0_DPR_SWITCH_DP));
+		if (ret)
+			return ret;
+
+		/* Enable DNL_SWITCHES and DPR_SWITCHES */
+		ret = regmap_set_bits(usbss->regmap, WCD_USBSS_SWITCH_SETTINGS_ENABLE,
+				      WCD_USBSS_SWITCH_SETTINGS_ENABLE_DPR_SWITCHES |
+				      WCD_USBSS_SWITCH_SETTINGS_ENABLE_DNL_SWITCHES);
+		if (ret)
+			return ret;
+	}
+
+	/* Enable DP AUX muxes */
+	if (enable_dp) {
+		/* Update Leakage Canceller Coefficient for AUXP pins */
+		ret = regmap_update_bits(usbss->regmap, WCD_USBSS_DISP_AUXP_CTL,
+					 WCD_USBSS_DISP_AUXP_CTL_LK_CANCEL_TRK_COEFF,
+					 FIELD_PREP(WCD_USBSS_DISP_AUXP_CTL_LK_CANCEL_TRK_COEFF,
+						    5));
+		if (ret)
+			return ret;
+
+		ret = regmap_set_bits(usbss->regmap, WCD_USBSS_DISP_AUXP_THRESH,
+				      WCD_USBSS_DISP_AUXP_THRESH_DISP_AUXP_OVPON_CM);
+		if (ret)
+			return ret;
+
+		if (reverse)
+			/* Select MG2 for AUXP and MG1 for AUXM */
+			ret = regmap_update_bits(usbss->regmap, WCD_USBSS_SWITCH_SELECT0,
+						 WCD_USBSS_SWITCH_SELECT0_DP_AUXP_SWITCHES |
+						 WCD_USBSS_SWITCH_SELECT0_DP_AUXM_SWITCHES,
+						 WCD_USBSS_SWITCH_SELECT0_DP_AUXP_SWITCHES);
+		else
+			/* Select MG1 for AUXP and MG2 for AUXM */
+			ret = regmap_update_bits(usbss->regmap, WCD_USBSS_SWITCH_SELECT0,
+						 WCD_USBSS_SWITCH_SELECT0_DP_AUXP_SWITCHES |
+						 WCD_USBSS_SWITCH_SELECT0_DP_AUXM_SWITCHES,
+						 WCD_USBSS_SWITCH_SELECT0_DP_AUXM_SWITCHES);
+		if (ret)
+			return ret;
+
+		/* Enable DP_AUXP_TO_MGX and DP_AUXM_TO_MGX switches */
+		ret = regmap_set_bits(usbss->regmap, WCD_USBSS_SWITCH_SETTINGS_ENABLE,
+				      WCD_USBSS_SWITCH_SETTINGS_ENABLE_DP_AUXP_TO_MGX_SWITCHES |
+				      WCD_USBSS_SWITCH_SETTINGS_ENABLE_DP_AUXM_TO_MGX_SWITCHES);
+
+		/* 15us to allow the SBU switch to turn on again */
+		usleep_range(15, 1000);
+	}
+
+	return 0;
+}
+
+static int wcd939x_usbss_switch_set(struct typec_switch_dev *sw,
+				    enum typec_orientation orientation)
+{
+	struct wcd939x_usbss *usbss = typec_switch_get_drvdata(sw);
+	int ret = 0;
+
+	mutex_lock(&usbss->lock);
+
+	if (usbss->orientation != orientation) {
+		usbss->orientation = orientation;
+
+		ret = wcd939x_usbss_set(usbss);
+	}
+
+	mutex_unlock(&usbss->lock);
+
+	if (ret)
+		return ret;
+
+	/* Report orientation to codec after switch has been done */
+	return typec_switch_set(usbss->codec_switch, orientation);
+}
+
+static int wcd939x_usbss_mux_set(struct typec_mux_dev *mux,
+				 struct typec_mux_state *state)
+{
+	struct wcd939x_usbss *usbss = typec_mux_get_drvdata(mux);
+	int ret = 0;
+
+	mutex_lock(&usbss->lock);
+
+	if (usbss->mode != state->mode) {
+		usbss->mode = state->mode;
+
+		if (state->alt)
+			usbss->svid = state->alt->svid;
+		else
+			usbss->svid = 0; // No SVID
+
+		ret = wcd939x_usbss_set(usbss);
+	}
+
+	mutex_unlock(&usbss->lock);
+
+	if (ret)
+		return ret;
+
+	/* Report event to codec after switch has been done */
+	return typec_mux_set(usbss->codec, state);
+}
+
+static int wcd939x_usbss_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct typec_switch_desc sw_desc = { };
+	struct typec_mux_desc mux_desc = { };
+	struct wcd939x_usbss *usbss;
+	int ret;
+
+	usbss = devm_kzalloc(dev, sizeof(*usbss), GFP_KERNEL);
+	if (!usbss)
+		return -ENOMEM;
+
+	usbss->client = client;
+	mutex_init(&usbss->lock);
+
+	usbss->regmap = devm_regmap_init_i2c(client, &wcd939x_usbss_regmap_config);
+	if (IS_ERR(usbss->regmap))
+		return dev_err_probe(dev, PTR_ERR(usbss->regmap), "failed to initialize regmap\n");
+
+	usbss->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(usbss->reset_gpio))
+		return dev_err_probe(dev, PTR_ERR(usbss->reset_gpio),
+				     "unable to acquire reset gpio\n");
+
+	usbss->vdd_supply = devm_regulator_get_optional(dev, "vdd");
+	if (IS_ERR(usbss->vdd_supply))
+		return PTR_ERR(usbss->vdd_supply);
+
+	/* Get Codec's MUX & Switch devices */
+	usbss->codec = fwnode_typec_mux_get(dev->fwnode);
+	if (IS_ERR(usbss->codec))
+		return dev_err_probe(dev, PTR_ERR(usbss->codec),
+				     "failed to acquire codec mode-switch\n");
+
+	usbss->codec_switch = fwnode_typec_switch_get(dev->fwnode);
+	if (IS_ERR(usbss->codec_switch)) {
+		ret = dev_err_probe(dev, PTR_ERR(usbss->codec_switch),
+				    "failed to acquire codec orientation-switch\n");
+		goto err_mux_put;
+	}
+
+	usbss->mode = TYPEC_STATE_SAFE;
+	usbss->orientation = TYPEC_ORIENTATION_NONE;
+
+	gpiod_set_value(usbss->reset_gpio, 1);
+
+	ret = regulator_enable(usbss->vdd_supply);
+	if (ret) {
+		dev_err(dev, "Failed to enable vdd: %d\n", ret);
+		goto err_mux_switch;
+	}
+
+	msleep(20);
+
+	gpiod_set_value(usbss->reset_gpio, 0);
+
+	msleep(20);
+
+	/* Disable standby */
+	ret = regmap_clear_bits(usbss->regmap, WCD_USBSS_USB_SS_CNTL,
+				WCD_USBSS_USB_SS_CNTL_STANDBY_STATE);
+	if (ret)
+		goto err_regulator_disable;
+
+	/* Set manual mode by default */
+	ret = regmap_update_bits(usbss->regmap, WCD_USBSS_FUNCTION_ENABLE,
+				 WCD_USBSS_FUNCTION_ENABLE_SOURCE_SELECT,
+				 FIELD_PREP(WCD_USBSS_FUNCTION_ENABLE_SOURCE_SELECT,
+					    WCD_USBSS_FUNCTION_ENABLE_SOURCE_SELECT_MANUAL));
+	if (ret)
+		goto err_regulator_disable;
+
+	/* Enable dynamic boosting for DP and DN */
+	ret = regmap_set_bits(usbss->regmap, WCD_USBSS_DP_DN_MISC1,
+			      WCD_USBSS_DP_DN_MISC1_DP_PCOMP_2X_DYN_BST_ON_EN |
+			      WCD_USBSS_DP_DN_MISC1_DN_PCOMP_2X_DYN_BST_ON_EN);
+	if (ret)
+		goto err_regulator_disable;
+
+	/* Enable dynamic boosting for MG1 OVP */
+	ret = regmap_set_bits(usbss->regmap, WCD_USBSS_MG1_MISC,
+			      WCD_USBSS_MG1_MISC_PCOMP_2X_DYN_BST_ON_EN);
+	if (ret)
+		goto err_regulator_disable;
+
+	/* Enable dynamic boosting for MG2 OVP */
+	ret = regmap_set_bits(usbss->regmap, WCD_USBSS_MG2_MISC,
+			      WCD_USBSS_MG2_MISC_PCOMP_2X_DYN_BST_ON_EN);
+	if (ret)
+		goto err_regulator_disable;
+
+	/* Write 0xFF to WCD_USBSS_CPLDO_CTL2 */
+	ret = regmap_set_bits(usbss->regmap, WCD_USBSS_CPLDO_CTL2, 0xff);
+	if (ret)
+		goto err_regulator_disable;
+
+	/* Set RCO_EN: WCD_USBSS_USB_SS_CNTL Bit<3> --> 0x0 --> 0x1 */
+	ret = regmap_clear_bits(usbss->regmap, WCD_USBSS_USB_SS_CNTL,
+				WCD_USBSS_USB_SS_CNTL_RCO_EN);
+	if (ret)
+		goto err_regulator_disable;
+
+	ret = regmap_set_bits(usbss->regmap, WCD_USBSS_USB_SS_CNTL,
+			      WCD_USBSS_USB_SS_CNTL_RCO_EN);
+	if (ret)
+		goto err_regulator_disable;
+
+	/* Disable all switches but enable the mux */
+	ret = regmap_write(usbss->regmap, WCD_USBSS_SWITCH_SETTINGS_ENABLE,
+			   WCD_USBSS_SWITCH_SETTINGS_ENABLE_DEVICE_ENABLE);
+	if (ret)
+		goto err_regulator_disable;
+
+	/* Setup in SAFE mode */
+	ret = wcd939x_usbss_set(usbss);
+	if (ret)
+		goto err_regulator_disable;
+
+	sw_desc.drvdata = usbss;
+	sw_desc.fwnode = dev_fwnode(dev);
+	sw_desc.set = wcd939x_usbss_switch_set;
+
+	usbss->sw = typec_switch_register(dev, &sw_desc);
+	if (IS_ERR(usbss->sw)) {
+		ret = dev_err_probe(dev, PTR_ERR(usbss->sw), "failed to register typec switch\n");
+		goto err_regulator_disable;
+	}
+
+	mux_desc.drvdata = usbss;
+	mux_desc.fwnode = dev_fwnode(dev);
+	mux_desc.set = wcd939x_usbss_mux_set;
+
+	usbss->mux = typec_mux_register(dev, &mux_desc);
+	if (IS_ERR(usbss->mux)) {
+		ret = dev_err_probe(dev, PTR_ERR(usbss->mux), "failed to register typec mux\n");
+		goto err_switch_unregister;
+	}
+
+	i2c_set_clientdata(client, usbss);
+
+	return 0;
+
+err_switch_unregister:
+	typec_switch_unregister(usbss->sw);
+
+err_regulator_disable:
+	regulator_disable(usbss->vdd_supply);
+
+err_mux_switch:
+	typec_switch_put(usbss->codec_switch);
+
+err_mux_put:
+	typec_mux_put(usbss->codec);
+
+	return ret;
+}
+
+static void wcd939x_usbss_remove(struct i2c_client *client)
+{
+	struct wcd939x_usbss *usbss = i2c_get_clientdata(client);
+
+	typec_mux_unregister(usbss->mux);
+	typec_switch_unregister(usbss->sw);
+
+	regulator_disable(usbss->vdd_supply);
+
+	typec_switch_put(usbss->codec_switch);
+	typec_mux_put(usbss->codec);
+}
+
+static const struct i2c_device_id wcd939x_usbss_table[] = {
+	{ "wcd9390-usbss" },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, wcd939x_usbss_table);
+
+static const struct of_device_id wcd939x_usbss_of_table[] = {
+	{ .compatible = "qcom,wcd9390-usbss" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, wcd939x_usbss_of_table);
+
+static struct i2c_driver wcd939x_usbss_driver = {
+	.driver = {
+		.name = "wcd939x-usbss",
+		.of_match_table = wcd939x_usbss_of_table,
+	},
+	.probe		= wcd939x_usbss_probe,
+	.remove		= wcd939x_usbss_remove,
+	.id_table	= wcd939x_usbss_table,
+};
+module_i2c_driver(wcd939x_usbss_driver);
+
+MODULE_DESCRIPTION("Qualcomm WCD939x USBSS driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/typec/pd.c b/drivers/usb/typec/pd.c
index 85d015cdbe1f..b9cca2be76fc 100644
--- a/drivers/usb/typec/pd.c
+++ b/drivers/usb/typec/pd.c
@@ -468,7 +468,7 @@ static struct device_type pd_capabilities_type = {
 /**
  * usb_power_delivery_register_capabilities - Register a set of capabilities.
  * @pd: The USB PD instance that the capabilities belong to.
- * @desc: Description of the Capablities Message.
+ * @desc: Description of the Capabilities Message.
  *
  * This function registers a Capabilities Message described in @desc. The
  * capabilities will have their own sub-directory under @pd in sysfs.
@@ -571,7 +571,7 @@ static void pd_release(struct device *dev)
 {
 	struct usb_power_delivery *pd = to_usb_power_delivery(dev);
 
-	ida_simple_remove(&pd_ida, pd->id);
+	ida_free(&pd_ida, pd->id);
 	kfree(pd);
 }
 
@@ -616,7 +616,7 @@ usb_power_delivery_register(struct device *parent, struct usb_power_delivery_des
 	if (!pd)
 		return ERR_PTR(-ENOMEM);
 
-	ret = ida_simple_get(&pd_ida, 0, 0, GFP_KERNEL);
+	ret = ida_alloc(&pd_ida, GFP_KERNEL);
 	if (ret < 0) {
 		kfree(pd);
 		return ERR_PTR(ret);
diff --git a/drivers/usb/typec/tcpm/tcpci_maxim_core.c b/drivers/usb/typec/tcpm/tcpci_maxim_core.c
index 9454b12a073c..7fb966fd639b 100644
--- a/drivers/usb/typec/tcpm/tcpci_maxim_core.c
+++ b/drivers/usb/typec/tcpm/tcpci_maxim_core.c
@@ -92,11 +92,16 @@ static void max_tcpci_init_regs(struct max_tcpci_chip *chip)
 		return;
 	}
 
+	/* Vconn Over Current Protection */
+	ret = max_tcpci_write8(chip, TCPC_FAULT_STATUS_MASK, TCPC_FAULT_STATUS_MASK_VCONN_OC);
+	if (ret < 0)
+		return;
+
 	alert_mask = TCPC_ALERT_TX_SUCCESS | TCPC_ALERT_TX_DISCARDED | TCPC_ALERT_TX_FAILED |
 		TCPC_ALERT_RX_HARD_RST | TCPC_ALERT_RX_STATUS | TCPC_ALERT_CC_STATUS |
 		TCPC_ALERT_VBUS_DISCNCT | TCPC_ALERT_RX_BUF_OVF | TCPC_ALERT_POWER_STATUS |
 		/* Enable Extended alert for detecting Fast Role Swap Signal */
-		TCPC_ALERT_EXTND | TCPC_ALERT_EXTENDED_STATUS;
+		TCPC_ALERT_EXTND | TCPC_ALERT_EXTENDED_STATUS | TCPC_ALERT_FAULT;
 
 	ret = max_tcpci_write16(chip, TCPC_ALERT_MASK, alert_mask);
 	if (ret < 0) {
@@ -295,6 +300,19 @@ static irqreturn_t _max_tcpci_irq(struct max_tcpci_chip *chip, u16 status)
 		}
 	}
 
+	if (status & TCPC_ALERT_FAULT) {
+		ret = max_tcpci_read8(chip, TCPC_FAULT_STATUS, &reg_status);
+		if (ret < 0)
+			return ret;
+
+		ret = max_tcpci_write8(chip, TCPC_FAULT_STATUS, reg_status);
+		if (ret < 0)
+			return ret;
+
+		if (reg_status & TCPC_FAULT_STATUS_VCONN_OC)
+			tcpm_port_error_recovery(chip->port);
+	}
+
 	if (status & TCPC_ALERT_EXTND) {
 		ret = max_tcpci_read8(chip, TCPC_ALERT_EXTENDED, &reg_status);
 		if (ret < 0)
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index bfb6f9481e87..096597231027 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -251,6 +251,7 @@ enum frs_typec_current {
 #define TCPM_FRS_EVENT		BIT(3)
 #define TCPM_SOURCING_VBUS	BIT(4)
 #define TCPM_PORT_CLEAN		BIT(5)
+#define TCPM_PORT_ERROR		BIT(6)
 
 #define LOG_BUFFER_ENTRIES	1024
 #define LOG_BUFFER_ENTRY_SIZE	128
@@ -296,6 +297,15 @@ struct pd_pps_data {
 	bool active;
 };
 
+struct pd_data {
+	struct usb_power_delivery *pd;
+	struct usb_power_delivery_capabilities *source_cap;
+	struct usb_power_delivery_capabilities_desc source_desc;
+	struct usb_power_delivery_capabilities *sink_cap;
+	struct usb_power_delivery_capabilities_desc sink_desc;
+	unsigned int operating_snk_mw;
+};
+
 struct tcpm_port {
 	struct device *dev;
 
@@ -397,12 +407,14 @@ struct tcpm_port {
 	unsigned int rx_msgid;
 
 	/* USB PD objects */
-	struct usb_power_delivery *pd;
+	struct usb_power_delivery **pds;
+	struct pd_data **pd_list;
 	struct usb_power_delivery_capabilities *port_source_caps;
 	struct usb_power_delivery_capabilities *port_sink_caps;
 	struct usb_power_delivery *partner_pd;
 	struct usb_power_delivery_capabilities *partner_source_caps;
 	struct usb_power_delivery_capabilities *partner_sink_caps;
+	struct usb_power_delivery *selected_pd;
 
 	/* Partner capabilities/requests */
 	u32 sink_request;
@@ -412,6 +424,7 @@ struct tcpm_port {
 	unsigned int nr_sink_caps;
 
 	/* Local capabilities */
+	unsigned int pd_count;
 	u32 src_pdo[PDO_MAX_OBJECTS];
 	unsigned int nr_src_pdo;
 	u32 snk_pdo[PDO_MAX_OBJECTS];
@@ -2847,7 +2860,7 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port,
 					   PD_MSG_CTRL_NOT_SUPP,
 					   NONE_AMS);
 		} else {
-			if (port->send_discover) {
+			if (port->send_discover && port->negotiated_rev < PD_REV30) {
 				tcpm_queue_message(port, PD_MSG_CTRL_WAIT);
 				break;
 			}
@@ -2863,7 +2876,7 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port,
 					   PD_MSG_CTRL_NOT_SUPP,
 					   NONE_AMS);
 		} else {
-			if (port->send_discover) {
+			if (port->send_discover && port->negotiated_rev < PD_REV30) {
 				tcpm_queue_message(port, PD_MSG_CTRL_WAIT);
 				break;
 			}
@@ -2872,7 +2885,7 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port,
 		}
 		break;
 	case PD_CTRL_VCONN_SWAP:
-		if (port->send_discover) {
+		if (port->send_discover && port->negotiated_rev < PD_REV30) {
 			tcpm_queue_message(port, PD_MSG_CTRL_WAIT);
 			break;
 		}
@@ -3730,9 +3743,6 @@ static void tcpm_detach(struct tcpm_port *port)
 	if (tcpm_port_is_disconnected(port))
 		port->hard_reset_count = 0;
 
-	port->try_src_count = 0;
-	port->try_snk_count = 0;
-
 	if (!port->attached)
 		return;
 
@@ -4401,7 +4411,8 @@ static void run_state_machine(struct tcpm_port *port)
 			tcpm_set_current_limit(port, tcpm_get_current_limit(port), 5000);
 		tcpm_swap_complete(port, 0);
 		tcpm_typec_connect(port);
-		mod_enable_frs_delayed_work(port, 0);
+		if (port->pd_capable && port->source_caps[0] & PDO_FIXED_DUAL_ROLE)
+			mod_enable_frs_delayed_work(port, 0);
 		tcpm_pps_complete(port, port->pps_status);
 
 		if (port->ams != NONE_AMS)
@@ -4862,8 +4873,11 @@ static void run_state_machine(struct tcpm_port *port)
 		break;
 	case PORT_RESET:
 		tcpm_reset_port(port);
-		tcpm_set_cc(port, tcpm_default_state(port) == SNK_UNATTACHED ?
-			    TYPEC_CC_RD : tcpm_rp_cc(port));
+		if (port->self_powered)
+			tcpm_set_cc(port, TYPEC_CC_OPEN);
+		else
+			tcpm_set_cc(port, tcpm_default_state(port) == SNK_UNATTACHED ?
+				    TYPEC_CC_RD : tcpm_rp_cc(port));
 		tcpm_set_state(port, PORT_RESET_WAIT_OFF,
 			       PD_T_ERROR_RECOVERY);
 		break;
@@ -5487,6 +5501,10 @@ static void tcpm_pd_event_handler(struct kthread_work *work)
 					tcpm_set_state(port, tcpm_default_state(port), 0);
 			}
 		}
+		if (events & TCPM_PORT_ERROR) {
+			tcpm_log(port, "port triggering error recovery");
+			tcpm_set_state(port, ERROR_RECOVERY, 0);
+		}
 
 		spin_lock(&port->pd_event_lock);
 	}
@@ -5554,6 +5572,15 @@ bool tcpm_port_is_toggling(struct tcpm_port *port)
 }
 EXPORT_SYMBOL_GPL(tcpm_port_is_toggling);
 
+void tcpm_port_error_recovery(struct tcpm_port *port)
+{
+	spin_lock(&port->pd_event_lock);
+	port->pd_events |= TCPM_PORT_ERROR;
+	spin_unlock(&port->pd_event_lock);
+	kthread_queue_work(port->wq, &port->event_work);
+}
+EXPORT_SYMBOL_GPL(tcpm_port_error_recovery);
+
 static void tcpm_enable_frs_work(struct kthread_work *work)
 {
 	struct tcpm_port *port = container_of(work, struct tcpm_port, enable_frs);
@@ -6045,12 +6072,114 @@ port_unlock:
 	return 0;
 }
 
+static struct pd_data *tcpm_find_pd_data(struct tcpm_port *port, struct usb_power_delivery *pd)
+{
+	int i;
+
+	for (i = 0; port->pd_list[i]; i++) {
+		if (port->pd_list[i]->pd == pd)
+			return port->pd_list[i];
+	}
+
+	return ERR_PTR(-ENODATA);
+}
+
+static struct usb_power_delivery **tcpm_pd_get(struct typec_port *p)
+{
+	struct tcpm_port *port = typec_get_drvdata(p);
+
+	return port->pds;
+}
+
+static int tcpm_pd_set(struct typec_port *p, struct usb_power_delivery *pd)
+{
+	struct tcpm_port *port = typec_get_drvdata(p);
+	struct pd_data *data;
+	int i, ret = 0;
+
+	mutex_lock(&port->lock);
+
+	if (port->selected_pd == pd)
+		goto unlock;
+
+	data = tcpm_find_pd_data(port, pd);
+	if (IS_ERR(data)) {
+		ret = PTR_ERR(data);
+		goto unlock;
+	}
+
+	if (data->sink_desc.pdo[0]) {
+		for (i = 0; i < PDO_MAX_OBJECTS && data->sink_desc.pdo[i]; i++)
+			port->snk_pdo[i] = data->sink_desc.pdo[i];
+		port->nr_snk_pdo = i + 1;
+		port->operating_snk_mw = data->operating_snk_mw;
+	}
+
+	if (data->source_desc.pdo[0]) {
+		for (i = 0; i < PDO_MAX_OBJECTS && data->source_desc.pdo[i]; i++)
+			port->snk_pdo[i] = data->source_desc.pdo[i];
+		port->nr_src_pdo = i + 1;
+	}
+
+	switch (port->state) {
+	case SRC_UNATTACHED:
+	case SRC_ATTACH_WAIT:
+	case SRC_TRYWAIT:
+		tcpm_set_cc(port, tcpm_rp_cc(port));
+		break;
+	case SRC_SEND_CAPABILITIES:
+	case SRC_SEND_CAPABILITIES_TIMEOUT:
+	case SRC_NEGOTIATE_CAPABILITIES:
+	case SRC_READY:
+	case SRC_WAIT_NEW_CAPABILITIES:
+		port->caps_count = 0;
+		port->upcoming_state = SRC_SEND_CAPABILITIES;
+		ret = tcpm_ams_start(port, POWER_NEGOTIATION);
+		if (ret == -EAGAIN) {
+			port->upcoming_state = INVALID_STATE;
+			goto unlock;
+		}
+		break;
+	case SNK_NEGOTIATE_CAPABILITIES:
+	case SNK_NEGOTIATE_PPS_CAPABILITIES:
+	case SNK_READY:
+	case SNK_TRANSITION_SINK:
+	case SNK_TRANSITION_SINK_VBUS:
+		if (port->pps_data.active)
+			port->upcoming_state = SNK_NEGOTIATE_PPS_CAPABILITIES;
+		else if (port->pd_capable)
+			port->upcoming_state = SNK_NEGOTIATE_CAPABILITIES;
+		else
+			break;
+
+		port->update_sink_caps = true;
+
+		ret = tcpm_ams_start(port, POWER_NEGOTIATION);
+		if (ret == -EAGAIN) {
+			port->upcoming_state = INVALID_STATE;
+			goto unlock;
+		}
+		break;
+	default:
+		break;
+	}
+
+	port->port_source_caps = data->source_cap;
+	port->port_sink_caps = data->sink_cap;
+	port->selected_pd = pd;
+unlock:
+	mutex_unlock(&port->lock);
+	return ret;
+}
+
 static const struct typec_operations tcpm_ops = {
 	.try_role = tcpm_try_role,
 	.dr_set = tcpm_dr_set,
 	.pr_set = tcpm_pr_set,
 	.vconn_set = tcpm_vconn_set,
-	.port_type_set = tcpm_port_type_set
+	.port_type_set = tcpm_port_type_set,
+	.pd_get = tcpm_pd_get,
+	.pd_set = tcpm_pd_set
 };
 
 void tcpm_tcpc_reset(struct tcpm_port *port)
@@ -6064,58 +6193,63 @@ EXPORT_SYMBOL_GPL(tcpm_tcpc_reset);
 
 static void tcpm_port_unregister_pd(struct tcpm_port *port)
 {
-	usb_power_delivery_unregister_capabilities(port->port_sink_caps);
+	int i;
+
 	port->port_sink_caps = NULL;
-	usb_power_delivery_unregister_capabilities(port->port_source_caps);
 	port->port_source_caps = NULL;
-	usb_power_delivery_unregister(port->pd);
-	port->pd = NULL;
+	for (i = 0; i < port->pd_count; i++) {
+		usb_power_delivery_unregister_capabilities(port->pd_list[i]->sink_cap);
+		kfree(port->pd_list[i]->sink_cap);
+		usb_power_delivery_unregister_capabilities(port->pd_list[i]->source_cap);
+		kfree(port->pd_list[i]->source_cap);
+		devm_kfree(port->dev, port->pd_list[i]);
+		port->pd_list[i] = NULL;
+		usb_power_delivery_unregister(port->pds[i]);
+		port->pds[i] = NULL;
+	}
 }
 
 static int tcpm_port_register_pd(struct tcpm_port *port)
 {
 	struct usb_power_delivery_desc desc = { port->typec_caps.pd_revision };
-	struct usb_power_delivery_capabilities_desc caps = { };
 	struct usb_power_delivery_capabilities *cap;
-	int ret;
+	int ret, i;
 
 	if (!port->nr_src_pdo && !port->nr_snk_pdo)
 		return 0;
 
-	port->pd = usb_power_delivery_register(port->dev, &desc);
-	if (IS_ERR(port->pd)) {
-		ret = PTR_ERR(port->pd);
-		goto err_unregister;
-	}
-
-	if (port->nr_src_pdo) {
-		memcpy_and_pad(caps.pdo, sizeof(caps.pdo), port->src_pdo,
-			       port->nr_src_pdo * sizeof(u32), 0);
-		caps.role = TYPEC_SOURCE;
-
-		cap = usb_power_delivery_register_capabilities(port->pd, &caps);
-		if (IS_ERR(cap)) {
-			ret = PTR_ERR(cap);
+	for (i = 0; i < port->pd_count; i++) {
+		port->pds[i] = usb_power_delivery_register(port->dev, &desc);
+		if (IS_ERR(port->pds[i])) {
+			ret = PTR_ERR(port->pds[i]);
 			goto err_unregister;
 		}
-
-		port->port_source_caps = cap;
-	}
-
-	if (port->nr_snk_pdo) {
-		memcpy_and_pad(caps.pdo, sizeof(caps.pdo), port->snk_pdo,
-			       port->nr_snk_pdo * sizeof(u32), 0);
-		caps.role = TYPEC_SINK;
-
-		cap = usb_power_delivery_register_capabilities(port->pd, &caps);
-		if (IS_ERR(cap)) {
-			ret = PTR_ERR(cap);
-			goto err_unregister;
+		port->pd_list[i]->pd = port->pds[i];
+
+		if (port->pd_list[i]->source_desc.pdo[0]) {
+			cap = usb_power_delivery_register_capabilities(port->pds[i],
+								&port->pd_list[i]->source_desc);
+			if (IS_ERR(cap)) {
+				ret = PTR_ERR(cap);
+				goto err_unregister;
+			}
+			port->pd_list[i]->source_cap = cap;
 		}
 
-		port->port_sink_caps = cap;
+		if (port->pd_list[i]->sink_desc.pdo[0]) {
+			cap = usb_power_delivery_register_capabilities(port->pds[i],
+								&port->pd_list[i]->sink_desc);
+			if (IS_ERR(cap)) {
+				ret = PTR_ERR(cap);
+				goto err_unregister;
+			}
+			port->pd_list[i]->sink_cap = cap;
+		}
 	}
 
+	port->port_source_caps = port->pd_list[0]->source_cap;
+	port->port_sink_caps = port->pd_list[0]->sink_cap;
+	port->selected_pd = port->pds[0];
 	return 0;
 
 err_unregister:
@@ -6124,12 +6258,15 @@ err_unregister:
 	return ret;
 }
 
-static int tcpm_fw_get_caps(struct tcpm_port *port,
-			    struct fwnode_handle *fwnode)
+static int tcpm_fw_get_caps(struct tcpm_port *port, struct fwnode_handle *fwnode)
 {
+	struct fwnode_handle *capabilities, *child, *caps = NULL;
+	unsigned int nr_src_pdo, nr_snk_pdo;
 	const char *opmode_str;
-	int ret;
-	u32 mw, frs_current;
+	u32 *src_pdo, *snk_pdo;
+	u32 uw, frs_current;
+	int ret = 0, i;
+	int mode;
 
 	if (!fwnode)
 		return -EINVAL;
@@ -6147,30 +6284,20 @@ static int tcpm_fw_get_caps(struct tcpm_port *port,
 	if (ret < 0)
 		return ret;
 
+	mode = 0;
+
+	if (fwnode_property_read_bool(fwnode, "accessory-mode-audio"))
+		port->typec_caps.accessory[mode++] = TYPEC_ACCESSORY_AUDIO;
+
+	if (fwnode_property_read_bool(fwnode, "accessory-mode-debug"))
+		port->typec_caps.accessory[mode++] = TYPEC_ACCESSORY_DEBUG;
+
 	port->port_type = port->typec_caps.type;
 	port->pd_supported = !fwnode_property_read_bool(fwnode, "pd-disable");
-
 	port->slow_charger_loop = fwnode_property_read_bool(fwnode, "slow-charger-loop");
-	if (port->port_type == TYPEC_PORT_SNK)
-		goto sink;
-
-	/* Get Source PDOs for the PD port or Source Rp value for the non-PD port */
-	if (port->pd_supported) {
-		ret = fwnode_property_count_u32(fwnode, "source-pdos");
-		if (ret == 0)
-			return -EINVAL;
-		else if (ret < 0)
-			return ret;
+	port->self_powered = fwnode_property_read_bool(fwnode, "self-powered");
 
-		port->nr_src_pdo = min(ret, PDO_MAX_OBJECTS);
-		ret = fwnode_property_read_u32_array(fwnode, "source-pdos",
-						     port->src_pdo, port->nr_src_pdo);
-		if (ret)
-			return ret;
-		ret = tcpm_validate_caps(port, port->src_pdo, port->nr_src_pdo);
-		if (ret)
-			return ret;
-	} else {
+	if (!port->pd_supported) {
 		ret = fwnode_property_read_string(fwnode, "typec-power-opmode", &opmode_str);
 		if (ret)
 			return ret;
@@ -6178,45 +6305,150 @@ static int tcpm_fw_get_caps(struct tcpm_port *port,
 		if (ret < 0)
 			return ret;
 		port->src_rp = tcpm_pwr_opmode_to_rp(ret);
-	}
-
-	if (port->port_type == TYPEC_PORT_SRC)
 		return 0;
+	}
 
-sink:
-	port->self_powered = fwnode_property_read_bool(fwnode, "self-powered");
-
-	if (!port->pd_supported)
-		return 0;
-
-	/* Get sink pdos */
-	ret = fwnode_property_count_u32(fwnode, "sink-pdos");
-	if (ret <= 0)
-		return -EINVAL;
-
-	port->nr_snk_pdo = min(ret, PDO_MAX_OBJECTS);
-	ret = fwnode_property_read_u32_array(fwnode, "sink-pdos",
-					     port->snk_pdo, port->nr_snk_pdo);
-	if ((ret < 0) || tcpm_validate_caps(port, port->snk_pdo,
-					    port->nr_snk_pdo))
-		return -EINVAL;
-
-	if (fwnode_property_read_u32(fwnode, "op-sink-microwatt", &mw) < 0)
-		return -EINVAL;
-	port->operating_snk_mw = mw / 1000;
+	/* The following code are applicable to pd-capable ports, i.e. pd_supported is true. */
 
 	/* FRS can only be supported by DRP ports */
 	if (port->port_type == TYPEC_PORT_DRP) {
 		ret = fwnode_property_read_u32(fwnode, "new-source-frs-typec-current",
 					       &frs_current);
-		if (ret >= 0 && frs_current <= FRS_5V_3A)
+		if (!ret && frs_current <= FRS_5V_3A)
 			port->new_source_frs_current = frs_current;
+
+		if (ret)
+			ret = 0;
+	}
+
+	/* For the backward compatibility, "capabilities" node is optional. */
+	capabilities = fwnode_get_named_child_node(fwnode, "capabilities");
+	if (!capabilities) {
+		port->pd_count = 1;
+	} else {
+		fwnode_for_each_child_node(capabilities, child)
+			port->pd_count++;
+
+		if (!port->pd_count) {
+			ret = -ENODATA;
+			goto put_capabilities;
+		}
+	}
+
+	port->pds = devm_kcalloc(port->dev, port->pd_count, sizeof(struct usb_power_delivery *),
+				 GFP_KERNEL);
+	if (!port->pds) {
+		ret = -ENOMEM;
+		goto put_capabilities;
+	}
+
+	port->pd_list = devm_kcalloc(port->dev, port->pd_count, sizeof(struct pd_data *),
+				     GFP_KERNEL);
+	if (!port->pd_list) {
+		ret = -ENOMEM;
+		goto put_capabilities;
+	}
+
+	for (i = 0; i < port->pd_count; i++) {
+		port->pd_list[i] = devm_kzalloc(port->dev, sizeof(struct pd_data), GFP_KERNEL);
+		if (!port->pd_list[i]) {
+			ret = -ENOMEM;
+			goto put_capabilities;
+		}
+
+		src_pdo = port->pd_list[i]->source_desc.pdo;
+		port->pd_list[i]->source_desc.role = TYPEC_SOURCE;
+		snk_pdo = port->pd_list[i]->sink_desc.pdo;
+		port->pd_list[i]->sink_desc.role = TYPEC_SINK;
+
+		/* If "capabilities" is NULL, fall back to single pd cap population. */
+		if (!capabilities)
+			caps = fwnode;
+		else
+			caps = fwnode_get_next_child_node(capabilities, caps);
+
+		if (port->port_type != TYPEC_PORT_SNK) {
+			ret = fwnode_property_count_u32(caps, "source-pdos");
+			if (ret == 0) {
+				ret = -EINVAL;
+				goto put_caps;
+			}
+			if (ret < 0)
+				goto put_caps;
+
+			nr_src_pdo = min(ret, PDO_MAX_OBJECTS);
+			ret = fwnode_property_read_u32_array(caps, "source-pdos", src_pdo,
+							     nr_src_pdo);
+			if (ret)
+				goto put_caps;
+
+			ret = tcpm_validate_caps(port, src_pdo, nr_src_pdo);
+			if (ret)
+				goto put_caps;
+
+			if (i == 0) {
+				port->nr_src_pdo = nr_src_pdo;
+				memcpy_and_pad(port->src_pdo, sizeof(u32) * PDO_MAX_OBJECTS,
+					       port->pd_list[0]->source_desc.pdo,
+					       sizeof(u32) * nr_src_pdo,
+					       0);
+			}
+		}
+
+		if (port->port_type != TYPEC_PORT_SRC) {
+			ret = fwnode_property_count_u32(caps, "sink-pdos");
+			if (ret == 0) {
+				ret = -EINVAL;
+				goto put_caps;
+			}
+
+			if (ret < 0)
+				goto put_caps;
+
+			nr_snk_pdo = min(ret, PDO_MAX_OBJECTS);
+			ret = fwnode_property_read_u32_array(caps, "sink-pdos", snk_pdo,
+							     nr_snk_pdo);
+			if (ret)
+				goto put_caps;
+
+			ret = tcpm_validate_caps(port, snk_pdo, nr_snk_pdo);
+			if (ret)
+				goto put_caps;
+
+			if (fwnode_property_read_u32(caps, "op-sink-microwatt", &uw) < 0) {
+				ret = -EINVAL;
+				goto put_caps;
+			}
+
+			port->pd_list[i]->operating_snk_mw = uw / 1000;
+
+			if (i == 0) {
+				port->nr_snk_pdo = nr_snk_pdo;
+				memcpy_and_pad(port->snk_pdo, sizeof(u32) * PDO_MAX_OBJECTS,
+					       port->pd_list[0]->sink_desc.pdo,
+					       sizeof(u32) * nr_snk_pdo,
+					       0);
+				port->operating_snk_mw = port->pd_list[0]->operating_snk_mw;
+			}
+		}
 	}
 
+put_caps:
+	if (caps != fwnode)
+		fwnode_handle_put(caps);
+put_capabilities:
+	fwnode_handle_put(capabilities);
+	return ret;
+}
+
+static int tcpm_fw_get_snk_vdos(struct tcpm_port *port, struct fwnode_handle *fwnode)
+{
+	int ret;
+
 	/* sink-vdos is optional */
 	ret = fwnode_property_count_u32(fwnode, "sink-vdos");
 	if (ret < 0)
-		ret = 0;
+		return 0;
 
 	port->nr_snk_vdo = min(ret, VDO_MAX_OBJECTS);
 	if (port->nr_snk_vdo) {
@@ -6584,10 +6816,12 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 	err = tcpm_fw_get_caps(port, tcpc->fwnode);
 	if (err < 0)
 		goto out_destroy_wq;
+	err = tcpm_fw_get_snk_vdos(port, tcpc->fwnode);
+	if (err < 0)
+		goto out_destroy_wq;
 
 	port->try_role = port->typec_caps.prefer_role;
 
-	port->typec_caps.fwnode = tcpc->fwnode;
 	port->typec_caps.revision = 0x0120;	/* Type-C spec release 1.2 */
 	port->typec_caps.pd_revision = 0x0300;	/* USB-PD spec release 3.0 */
 	port->typec_caps.svdm_version = SVDM_VER_2_0;
@@ -6596,7 +6830,6 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 	port->typec_caps.orientation_aware = 1;
 
 	port->partner_desc.identity = &port->partner_ident;
-	port->port_type = port->typec_caps.type;
 
 	port->role_sw = usb_role_switch_get(port->dev);
 	if (!port->role_sw)
@@ -6615,7 +6848,8 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 	if (err)
 		goto out_role_sw_put;
 
-	port->typec_caps.pd = port->pd;
+	if (port->pds)
+		port->typec_caps.pd = port->pds[0];
 
 	port->typec_port = typec_register_port(port->dev, &port->typec_caps);
 	if (IS_ERR(port->typec_port)) {
diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c
index 196535ad996d..0717cfcd9f8c 100644
--- a/drivers/usb/typec/tipd/core.c
+++ b/drivers/usb/typec/tipd/core.c
@@ -8,6 +8,7 @@
 
 #include <linux/i2c.h>
 #include <linux/acpi.h>
+#include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/power_supply.h>
@@ -64,6 +65,9 @@
 #define TPS_PBMC_RC	0 /* Return code */
 #define TPS_PBMC_DPCS	2 /* device patch complete status */
 
+/* reset de-assertion to ready for operation */
+#define TPS_SETUP_MS			1000
+
 enum {
 	TPS_PORTINFO_SINK,
 	TPS_PORTINFO_SINK_ACCESSORY,
@@ -111,6 +115,8 @@ struct tipd_data {
 	void (*trace_power_status)(u16 status);
 	void (*trace_status)(u32 status);
 	int (*apply_patch)(struct tps6598x *tps);
+	int (*init)(struct tps6598x *tps);
+	int (*reset)(struct tps6598x *tps);
 };
 
 struct tps6598x {
@@ -119,6 +125,7 @@ struct tps6598x {
 	struct mutex lock; /* device lock */
 	u8 i2c_protocol:1;
 
+	struct gpio_desc *reset;
 	struct typec_port *port;
 	struct typec_partner *partner;
 	struct usb_pd_identity partner_identity;
@@ -323,7 +330,7 @@ static void tps6598x_disconnect(struct tps6598x *tps, u32 status)
 }
 
 static int tps6598x_exec_cmd_tmo(struct tps6598x *tps, const char *cmd,
-			     size_t in_len, u8 *in_data,
+			     size_t in_len, const u8 *in_data,
 			     size_t out_len, u8 *out_data,
 			     u32 cmd_timeout_ms, u32 res_delay_ms)
 {
@@ -389,7 +396,7 @@ static int tps6598x_exec_cmd_tmo(struct tps6598x *tps, const char *cmd,
 }
 
 static int tps6598x_exec_cmd(struct tps6598x *tps, const char *cmd,
-			     size_t in_len, u8 *in_data,
+			     size_t in_len, const u8 *in_data,
 			     size_t out_len, u8 *out_data)
 {
 	return tps6598x_exec_cmd_tmo(tps, cmd, in_len, in_data,
@@ -866,6 +873,30 @@ tps6598x_register_port(struct tps6598x *tps, struct fwnode_handle *fwnode)
 	return 0;
 }
 
+static int tps_request_firmware(struct tps6598x *tps, const struct firmware **fw)
+{
+	const char *firmware_name;
+	int ret;
+
+	ret = device_property_read_string(tps->dev, "firmware-name",
+					  &firmware_name);
+	if (ret)
+		return ret;
+
+	ret = request_firmware(fw, firmware_name, tps->dev);
+	if (ret) {
+		dev_err(tps->dev, "failed to retrieve \"%s\"\n", firmware_name);
+		return ret;
+	}
+
+	if ((*fw)->size == 0) {
+		release_firmware(*fw);
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
 static int
 tps25750_write_firmware(struct tps6598x *tps,
 			u8 bpms_addr, const u8 *data, size_t len)
@@ -954,16 +985,9 @@ static int tps25750_start_patch_burst_mode(struct tps6598x *tps)
 	if (ret)
 		return ret;
 
-	ret = request_firmware(&fw, firmware_name, tps->dev);
-	if (ret) {
-		dev_err(tps->dev, "failed to retrieve \"%s\"\n", firmware_name);
+	ret = tps_request_firmware(tps, &fw);
+	if (ret)
 		return ret;
-	}
-
-	if (fw->size == 0) {
-		ret = -EINVAL;
-		goto release_fw;
-	}
 
 	ret = of_property_match_string(np, "reg-names", "patch-address");
 	if (ret < 0) {
@@ -1101,6 +1125,76 @@ wait_for_app:
 	return 0;
 };
 
+static int tps6598x_apply_patch(struct tps6598x *tps)
+{
+	u8 in = TPS_PTCS_CONTENT_DEV | TPS_PTCS_CONTENT_APP;
+	u8 out[TPS_MAX_LEN] = {0};
+	size_t in_len = sizeof(in);
+	size_t copied_bytes = 0;
+	size_t bytes_left;
+	const struct firmware *fw;
+	const char *firmware_name;
+	int ret;
+
+	ret = device_property_read_string(tps->dev, "firmware-name",
+					  &firmware_name);
+	if (ret)
+		return ret;
+
+	ret = tps_request_firmware(tps, &fw);
+	if (ret)
+		return ret;
+
+	ret = tps6598x_exec_cmd(tps, "PTCs", in_len, &in,
+				TPS_PTCS_OUT_BYTES, out);
+	if (ret || out[TPS_PTCS_STATUS] == TPS_PTCS_STATUS_FAIL) {
+		if (!ret)
+			ret = -EBUSY;
+		dev_err(tps->dev, "Update start failed (%d)\n", ret);
+		goto release_fw;
+	}
+
+	bytes_left = fw->size;
+	while (bytes_left) {
+		if (bytes_left < TPS_MAX_LEN)
+			in_len = bytes_left;
+		else
+			in_len = TPS_MAX_LEN;
+		ret = tps6598x_exec_cmd(tps, "PTCd", in_len,
+					fw->data + copied_bytes,
+					TPS_PTCD_OUT_BYTES, out);
+		if (ret || out[TPS_PTCD_TRANSFER_STATUS] ||
+		    out[TPS_PTCD_LOADING_STATE] == TPS_PTCD_LOAD_ERR) {
+			if (!ret)
+				ret = -EBUSY;
+			dev_err(tps->dev, "Patch download failed (%d)\n", ret);
+			goto release_fw;
+		}
+		copied_bytes += in_len;
+		bytes_left -= in_len;
+	}
+
+	ret = tps6598x_exec_cmd(tps, "PTCc", 0, NULL, TPS_PTCC_OUT_BYTES, out);
+	if (ret || out[TPS_PTCC_DEV] || out[TPS_PTCC_APP]) {
+		if (!ret)
+			ret = -EBUSY;
+		dev_err(tps->dev, "Update completion failed (%d)\n", ret);
+		goto release_fw;
+	}
+	msleep(TPS_SETUP_MS);
+	dev_info(tps->dev, "Firmware update succeeded\n");
+
+release_fw:
+	release_firmware(fw);
+
+	return ret;
+};
+
+static int cd321x_init(struct tps6598x *tps)
+{
+	return 0;
+}
+
 static int tps25750_init(struct tps6598x *tps)
 {
 	int ret;
@@ -1119,6 +1213,26 @@ static int tps25750_init(struct tps6598x *tps)
 	return 0;
 }
 
+static int tps6598x_init(struct tps6598x *tps)
+{
+	return tps->data->apply_patch(tps);
+}
+
+static int cd321x_reset(struct tps6598x *tps)
+{
+	return 0;
+}
+
+static int tps25750_reset(struct tps6598x *tps)
+{
+	return tps6598x_exec_cmd_tmo(tps, "GAID", 0, NULL, 0, NULL, 2000, 0);
+}
+
+static int tps6598x_reset(struct tps6598x *tps)
+{
+	return 0;
+}
+
 static int
 tps25750_register_port(struct tps6598x *tps, struct fwnode_handle *fwnode)
 {
@@ -1182,7 +1296,6 @@ static int tps6598x_probe(struct i2c_client *client)
 	u32 vid;
 	int ret;
 	u64 mask1;
-	bool is_tps25750;
 
 	tps = devm_kzalloc(&client->dev, sizeof(*tps), GFP_KERNEL);
 	if (!tps)
@@ -1191,12 +1304,18 @@ static int tps6598x_probe(struct i2c_client *client)
 	mutex_init(&tps->lock);
 	tps->dev = &client->dev;
 
+	tps->reset = devm_gpiod_get_optional(tps->dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(tps->reset))
+		return dev_err_probe(tps->dev, PTR_ERR(tps->reset),
+				     "failed to get reset GPIO\n");
+	if (tps->reset)
+		msleep(TPS_SETUP_MS);
+
 	tps->regmap = devm_regmap_init_i2c(client, &tps6598x_regmap_config);
 	if (IS_ERR(tps->regmap))
 		return PTR_ERR(tps->regmap);
 
-	is_tps25750 = device_is_compatible(tps->dev, "ti,tps25750");
-	if (!is_tps25750) {
+	if (!device_is_compatible(tps->dev, "ti,tps25750")) {
 		ret = tps6598x_read32(tps, TPS_REG_VID, &vid);
 		if (ret < 0 || !vid)
 			return -ENODEV;
@@ -1239,8 +1358,8 @@ static int tps6598x_probe(struct i2c_client *client)
 	if (ret < 0)
 		return ret;
 
-	if (is_tps25750 && ret == TPS_MODE_PTCH) {
-		ret = tps25750_init(tps);
+	if (ret == TPS_MODE_PTCH) {
+		ret = tps->data->init(tps);
 		if (ret)
 			return ret;
 	}
@@ -1328,8 +1447,8 @@ err_clear_mask:
 	tps6598x_write64(tps, TPS_REG_INT_MASK1, 0);
 err_reset_controller:
 	/* Reset PD controller to remove any applied patch */
-	if (is_tps25750)
-		tps6598x_exec_cmd_tmo(tps, "GAID", 0, NULL, 0, NULL, 2000, 0);
+	tps->data->reset(tps);
+
 	return ret;
 }
 
@@ -1346,8 +1465,10 @@ static void tps6598x_remove(struct i2c_client *client)
 	usb_role_switch_put(tps->role_sw);
 
 	/* Reset PD controller to remove any applied patch */
-	if (device_is_compatible(tps->dev, "ti,tps25750"))
-		tps6598x_exec_cmd_tmo(tps, "GAID", 0, NULL, 0, NULL, 2000, 0);
+	tps->data->reset(tps);
+
+	if (tps->reset)
+		gpiod_set_value_cansleep(tps->reset, 1);
 }
 
 static int __maybe_unused tps6598x_suspend(struct device *dev)
@@ -1358,6 +1479,8 @@ static int __maybe_unused tps6598x_suspend(struct device *dev)
 	if (tps->wakeup) {
 		disable_irq(client->irq);
 		enable_irq_wake(client->irq);
+	} else if (tps->reset) {
+		gpiod_set_value_cansleep(tps->reset, 1);
 	}
 
 	if (!client->irq)
@@ -1376,8 +1499,8 @@ static int __maybe_unused tps6598x_resume(struct device *dev)
 	if (ret < 0)
 		return ret;
 
-	if (device_is_compatible(tps->dev, "ti,tps25750") && ret == TPS_MODE_PTCH) {
-		ret = tps25750_init(tps);
+	if (ret == TPS_MODE_PTCH) {
+		ret = tps->data->init(tps);
 		if (ret)
 			return ret;
 	}
@@ -1385,6 +1508,9 @@ static int __maybe_unused tps6598x_resume(struct device *dev)
 	if (tps->wakeup) {
 		disable_irq_wake(client->irq);
 		enable_irq(client->irq);
+	} else if (tps->reset) {
+		gpiod_set_value_cansleep(tps->reset, 0);
+		msleep(TPS_SETUP_MS);
 	}
 
 	if (!client->irq)
@@ -1403,6 +1529,8 @@ static const struct tipd_data cd321x_data = {
 	.register_port = tps6598x_register_port,
 	.trace_power_status = trace_tps6598x_power_status,
 	.trace_status = trace_tps6598x_status,
+	.init = cd321x_init,
+	.reset = cd321x_reset,
 };
 
 static const struct tipd_data tps6598x_data = {
@@ -1410,6 +1538,9 @@ static const struct tipd_data tps6598x_data = {
 	.register_port = tps6598x_register_port,
 	.trace_power_status = trace_tps6598x_power_status,
 	.trace_status = trace_tps6598x_status,
+	.apply_patch = tps6598x_apply_patch,
+	.init = tps6598x_init,
+	.reset = tps6598x_reset,
 };
 
 static const struct tipd_data tps25750_data = {
@@ -1418,6 +1549,8 @@ static const struct tipd_data tps25750_data = {
 	.trace_power_status = trace_tps25750_power_status,
 	.trace_status = trace_tps25750_status,
 	.apply_patch = tps25750_apply_patch,
+	.init = tps25750_init,
+	.reset = tps25750_reset,
 };
 
 static const struct of_device_id tps6598x_of_match[] = {
diff --git a/drivers/usb/typec/tipd/tps6598x.h b/drivers/usb/typec/tipd/tps6598x.h
index 01609bf509e4..89b24519463a 100644
--- a/drivers/usb/typec/tipd/tps6598x.h
+++ b/drivers/usb/typec/tipd/tps6598x.h
@@ -235,4 +235,22 @@
 /* SLEEP CONF REG */
 #define TPS_SLEEP_CONF_SLEEP_MODE_ALLOWED	BIT(0)
 
+/* Start Patch Download Sequence */
+#define TPS_PTCS_CONTENT_APP			BIT(0)
+#define TPS_PTCS_CONTENT_DEV			BIT(1)
+#define TPS_PTCS_OUT_BYTES			4
+#define TPS_PTCS_STATUS				1
+
+#define TPS_PTCS_STATUS_FAIL			0x80
+/* Patch Download */
+#define TPS_PTCD_OUT_BYTES			10
+#define TPS_PTCD_TRANSFER_STATUS		1
+#define TPS_PTCD_LOADING_STATE			2
+
+#define TPS_PTCD_LOAD_ERR			0x09
+/* Patch Download Complete */
+#define TPS_PTCC_OUT_BYTES			4
+#define TPS_PTCC_DEV				2
+#define TPS_PTCC_APP				3
+
 #endif /* __TPS6598X_H__ */
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index 5392ec698959..14f5a7bfae2e 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -938,7 +938,9 @@ static void ucsi_handle_connector_change(struct work_struct *work)
 
 	clear_bit(EVENT_PENDING, &con->ucsi->flags);
 
+	mutex_lock(&ucsi->ppm_lock);
 	ret = ucsi_acknowledge_connector_change(ucsi);
+	mutex_unlock(&ucsi->ppm_lock);
 	if (ret)
 		dev_err(ucsi->dev, "%s: ACK failed (%d)", __func__, ret);
 
diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c
index 6bbf490ac401..928eacbeb21a 100644
--- a/drivers/usb/typec/ucsi/ucsi_acpi.c
+++ b/drivers/usb/typec/ucsi/ucsi_acpi.c
@@ -25,6 +25,8 @@ struct ucsi_acpi {
 	unsigned long flags;
 	guid_t guid;
 	u64 cmd;
+	bool dell_quirk_probed;
+	bool dell_quirk_active;
 };
 
 static int ucsi_acpi_dsm(struct ucsi_acpi *ua, int func)
@@ -73,9 +75,13 @@ static int ucsi_acpi_sync_write(struct ucsi *ucsi, unsigned int offset,
 				const void *val, size_t val_len)
 {
 	struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi);
+	bool ack = UCSI_COMMAND(*(u64 *)val) == UCSI_ACK_CC_CI;
 	int ret;
 
-	set_bit(COMMAND_PENDING, &ua->flags);
+	if (ack)
+		set_bit(ACK_PENDING, &ua->flags);
+	else
+		set_bit(COMMAND_PENDING, &ua->flags);
 
 	ret = ucsi_acpi_async_write(ucsi, offset, val, val_len);
 	if (ret)
@@ -85,7 +91,10 @@ static int ucsi_acpi_sync_write(struct ucsi *ucsi, unsigned int offset,
 		ret = -ETIMEDOUT;
 
 out_clear_bit:
-	clear_bit(COMMAND_PENDING, &ua->flags);
+	if (ack)
+		clear_bit(ACK_PENDING, &ua->flags);
+	else
+		clear_bit(COMMAND_PENDING, &ua->flags);
 
 	return ret;
 }
@@ -119,12 +128,73 @@ static const struct ucsi_operations ucsi_zenbook_ops = {
 	.async_write = ucsi_acpi_async_write
 };
 
-static const struct dmi_system_id zenbook_dmi_id[] = {
+/*
+ * Some Dell laptops expect that an ACK command with the
+ * UCSI_ACK_CONNECTOR_CHANGE bit set is followed by a (separate)
+ * ACK command that only has the UCSI_ACK_COMMAND_COMPLETE bit set.
+ * If this is not done events are not delivered to OSPM and
+ * subsequent commands will timeout.
+ */
+static int
+ucsi_dell_sync_write(struct ucsi *ucsi, unsigned int offset,
+		     const void *val, size_t val_len)
+{
+	struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi);
+	u64 cmd = *(u64 *)val, ack = 0;
+	int ret;
+
+	if (UCSI_COMMAND(cmd) == UCSI_ACK_CC_CI &&
+	    cmd & UCSI_ACK_CONNECTOR_CHANGE)
+		ack = UCSI_ACK_CC_CI | UCSI_ACK_COMMAND_COMPLETE;
+
+	ret = ucsi_acpi_sync_write(ucsi, offset, val, val_len);
+	if (ret != 0)
+		return ret;
+	if (ack == 0)
+		return ret;
+
+	if (!ua->dell_quirk_probed) {
+		ua->dell_quirk_probed = true;
+
+		cmd = UCSI_GET_CAPABILITY;
+		ret = ucsi_acpi_sync_write(ucsi, UCSI_CONTROL, &cmd,
+					   sizeof(cmd));
+		if (ret == 0)
+			return ucsi_acpi_sync_write(ucsi, UCSI_CONTROL,
+						    &ack, sizeof(ack));
+		if (ret != -ETIMEDOUT)
+			return ret;
+
+		ua->dell_quirk_active = true;
+		dev_err(ua->dev, "Firmware bug: Additional ACK required after ACKing a connector change.\n");
+		dev_err(ua->dev, "Firmware bug: Enabling workaround\n");
+	}
+
+	if (!ua->dell_quirk_active)
+		return ret;
+
+	return ucsi_acpi_sync_write(ucsi, UCSI_CONTROL, &ack, sizeof(ack));
+}
+
+static const struct ucsi_operations ucsi_dell_ops = {
+	.read = ucsi_acpi_read,
+	.sync_write = ucsi_dell_sync_write,
+	.async_write = ucsi_acpi_async_write
+};
+
+static const struct dmi_system_id ucsi_acpi_quirks[] = {
 	{
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX325UA_UM325UA"),
 		},
+		.driver_data = (void *)&ucsi_zenbook_ops,
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		},
+		.driver_data = (void *)&ucsi_dell_ops,
 	},
 	{ }
 };
@@ -142,8 +212,10 @@ static void ucsi_acpi_notify(acpi_handle handle, u32 event, void *data)
 	if (UCSI_CCI_CONNECTOR(cci))
 		ucsi_connector_change(ua->ucsi, UCSI_CCI_CONNECTOR(cci));
 
-	if (test_bit(COMMAND_PENDING, &ua->flags) &&
-	    cci & (UCSI_CCI_ACK_COMPLETE | UCSI_CCI_COMMAND_COMPLETE))
+	if (cci & UCSI_CCI_ACK_COMPLETE && test_bit(ACK_PENDING, &ua->flags))
+		complete(&ua->complete);
+	if (cci & UCSI_CCI_COMMAND_COMPLETE &&
+	    test_bit(COMMAND_PENDING, &ua->flags))
 		complete(&ua->complete);
 }
 
@@ -151,6 +223,7 @@ static int ucsi_acpi_probe(struct platform_device *pdev)
 {
 	struct acpi_device *adev = ACPI_COMPANION(&pdev->dev);
 	const struct ucsi_operations *ops = &ucsi_acpi_ops;
+	const struct dmi_system_id *id;
 	struct ucsi_acpi *ua;
 	struct resource *res;
 	acpi_status status;
@@ -180,8 +253,9 @@ static int ucsi_acpi_probe(struct platform_device *pdev)
 	init_completion(&ua->complete);
 	ua->dev = &pdev->dev;
 
-	if (dmi_check_system(zenbook_dmi_id))
-		ops = &ucsi_zenbook_ops;
+	id = dmi_first_match(ucsi_acpi_quirks);
+	if (id)
+		ops = id->driver_data;
 
 	ua->ucsi = ucsi_create(&pdev->dev, ops);
 	if (IS_ERR(ua->ucsi))
diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c
index 53a7ede8556d..faccc942b381 100644
--- a/drivers/usb/typec/ucsi/ucsi_glink.c
+++ b/drivers/usb/typec/ucsi/ucsi_glink.c
@@ -301,6 +301,7 @@ static const struct of_device_id pmic_glink_ucsi_of_quirks[] = {
 	{ .compatible = "qcom,sc8180x-pmic-glink", .data = (void *)UCSI_NO_PARTNER_PDOS, },
 	{ .compatible = "qcom,sc8280xp-pmic-glink", .data = (void *)UCSI_NO_PARTNER_PDOS, },
 	{ .compatible = "qcom,sm8350-pmic-glink", .data = (void *)UCSI_NO_PARTNER_PDOS, },
+	{ .compatible = "qcom,sm8550-pmic-glink", .data = (void *)UCSI_NO_PARTNER_PDOS, },
 	{}
 };
 
diff --git a/drivers/usb/usbip/stub_main.c b/drivers/usb/usbip/stub_main.c
index 0a6624d37929..79110a69d697 100644
--- a/drivers/usb/usbip/stub_main.c
+++ b/drivers/usb/usbip/stub_main.c
@@ -377,14 +377,14 @@ static int __init usbip_host_init(void)
 		goto err_usb_register;
 	}
 
-	ret = driver_create_file(&stub_driver.drvwrap.driver,
+	ret = driver_create_file(&stub_driver.driver,
 				 &driver_attr_match_busid);
 	if (ret) {
 		pr_err("driver_create_file failed\n");
 		goto err_create_file;
 	}
 
-	ret = driver_create_file(&stub_driver.drvwrap.driver,
+	ret = driver_create_file(&stub_driver.driver,
 				 &driver_attr_rebind);
 	if (ret) {
 		pr_err("driver_create_file failed\n");
@@ -402,10 +402,10 @@ err_usb_register:
 
 static void __exit usbip_host_exit(void)
 {
-	driver_remove_file(&stub_driver.drvwrap.driver,
+	driver_remove_file(&stub_driver.driver,
 			   &driver_attr_match_busid);
 
-	driver_remove_file(&stub_driver.drvwrap.driver,
+	driver_remove_file(&stub_driver.driver,
 			   &driver_attr_rebind);
 
 	/*
diff --git a/drivers/usb/usbip/vudc.h b/drivers/usb/usbip/vudc.h
index 1bd4bc005829..faf61c9c6a98 100644
--- a/drivers/usb/usbip/vudc.h
+++ b/drivers/usb/usbip/vudc.h
@@ -173,6 +173,6 @@ struct vudc_device *alloc_vudc_device(int devid);
 void put_vudc_device(struct vudc_device *udc_dev);
 
 int vudc_probe(struct platform_device *pdev);
-int vudc_remove(struct platform_device *pdev);
+void vudc_remove(struct platform_device *pdev);
 
 #endif /* __USBIP_VUDC_H */
diff --git a/drivers/usb/usbip/vudc_dev.c b/drivers/usb/usbip/vudc_dev.c
index 44b04c54c086..f11535020e35 100644
--- a/drivers/usb/usbip/vudc_dev.c
+++ b/drivers/usb/usbip/vudc_dev.c
@@ -628,12 +628,11 @@ out:
 	return ret;
 }
 
-int vudc_remove(struct platform_device *pdev)
+void vudc_remove(struct platform_device *pdev)
 {
 	struct vudc *udc = platform_get_drvdata(pdev);
 
 	usb_del_gadget_udc(&udc->gadget);
 	cleanup_vudc_hw(udc);
 	kfree(udc);
-	return 0;
 }
diff --git a/drivers/usb/usbip/vudc_main.c b/drivers/usb/usbip/vudc_main.c
index 993e721cb840..8bee553e4894 100644
--- a/drivers/usb/usbip/vudc_main.c
+++ b/drivers/usb/usbip/vudc_main.c
@@ -19,7 +19,7 @@ MODULE_PARM_DESC(num, "number of emulated controllers");
 
 static struct platform_driver vudc_driver = {
 	.probe		= vudc_probe,
-	.remove		= vudc_remove,
+	.remove_new	= vudc_remove,
 	.driver		= {
 		.name	= GADGET_NAME,
 		.dev_groups = vudc_groups,
diff --git a/drivers/vdpa/alibaba/eni_vdpa.c b/drivers/vdpa/alibaba/eni_vdpa.c
index 5a09a09cca70..cce3d1837104 100644
--- a/drivers/vdpa/alibaba/eni_vdpa.c
+++ b/drivers/vdpa/alibaba/eni_vdpa.c
@@ -497,7 +497,7 @@ static int eni_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (!eni_vdpa->vring) {
 		ret = -ENOMEM;
 		ENI_ERR(pdev, "failed to allocate virtqueues\n");
-		goto err;
+		goto err_remove_vp_legacy;
 	}
 
 	for (i = 0; i < eni_vdpa->queues; i++) {
@@ -509,11 +509,13 @@ static int eni_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	ret = vdpa_register_device(&eni_vdpa->vdpa, eni_vdpa->queues);
 	if (ret) {
 		ENI_ERR(pdev, "failed to register to vdpa bus\n");
-		goto err;
+		goto err_remove_vp_legacy;
 	}
 
 	return 0;
 
+err_remove_vp_legacy:
+	vp_legacy_remove(&eni_vdpa->ldev);
 err:
 	put_device(&eni_vdpa->vdpa.dev);
 	return ret;
diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
index 84547d998bcf..50aac8fe57ef 100644
--- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
@@ -35,6 +35,9 @@ struct mlx5_vdpa_mr {
 	struct vhost_iotlb *iotlb;
 
 	bool user_mr;
+
+	refcount_t refcount;
+	struct list_head mr_list;
 };
 
 struct mlx5_vdpa_resources {
@@ -93,6 +96,7 @@ struct mlx5_vdpa_dev {
 	u32 generation;
 
 	struct mlx5_vdpa_mr *mr[MLX5_VDPA_NUM_AS];
+	struct list_head mr_list_head;
 	/* serialize mr access */
 	struct mutex mr_mtx;
 	struct mlx5_control_vq cvq;
@@ -118,8 +122,10 @@ int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, u32 mkey);
 struct mlx5_vdpa_mr *mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
 					 struct vhost_iotlb *iotlb);
 void mlx5_vdpa_destroy_mr_resources(struct mlx5_vdpa_dev *mvdev);
-void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev,
-			  struct mlx5_vdpa_mr *mr);
+void mlx5_vdpa_get_mr(struct mlx5_vdpa_dev *mvdev,
+		      struct mlx5_vdpa_mr *mr);
+void mlx5_vdpa_put_mr(struct mlx5_vdpa_dev *mvdev,
+		      struct mlx5_vdpa_mr *mr);
 void mlx5_vdpa_update_mr(struct mlx5_vdpa_dev *mvdev,
 			 struct mlx5_vdpa_mr *mr,
 			 unsigned int asid);
diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
index 2197c46e563a..4758914ccf86 100644
--- a/drivers/vdpa/mlx5/core/mr.c
+++ b/drivers/vdpa/mlx5/core/mr.c
@@ -498,32 +498,54 @@ static void destroy_user_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr
 
 static void _mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr)
 {
+	if (WARN_ON(!mr))
+		return;
+
 	if (mr->user_mr)
 		destroy_user_mr(mvdev, mr);
 	else
 		destroy_dma_mr(mvdev, mr);
 
 	vhost_iotlb_free(mr->iotlb);
+
+	list_del(&mr->mr_list);
+
+	kfree(mr);
 }
 
-void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev,
-			  struct mlx5_vdpa_mr *mr)
+static void _mlx5_vdpa_put_mr(struct mlx5_vdpa_dev *mvdev,
+			      struct mlx5_vdpa_mr *mr)
 {
 	if (!mr)
 		return;
 
+	if (refcount_dec_and_test(&mr->refcount))
+		_mlx5_vdpa_destroy_mr(mvdev, mr);
+}
+
+void mlx5_vdpa_put_mr(struct mlx5_vdpa_dev *mvdev,
+		      struct mlx5_vdpa_mr *mr)
+{
 	mutex_lock(&mvdev->mr_mtx);
+	_mlx5_vdpa_put_mr(mvdev, mr);
+	mutex_unlock(&mvdev->mr_mtx);
+}
 
-	_mlx5_vdpa_destroy_mr(mvdev, mr);
+static void _mlx5_vdpa_get_mr(struct mlx5_vdpa_dev *mvdev,
+			      struct mlx5_vdpa_mr *mr)
+{
+	if (!mr)
+		return;
 
-	for (int i = 0; i < MLX5_VDPA_NUM_AS; i++) {
-		if (mvdev->mr[i] == mr)
-			mvdev->mr[i] = NULL;
-	}
+	refcount_inc(&mr->refcount);
+}
 
+void mlx5_vdpa_get_mr(struct mlx5_vdpa_dev *mvdev,
+		      struct mlx5_vdpa_mr *mr)
+{
+	mutex_lock(&mvdev->mr_mtx);
+	_mlx5_vdpa_get_mr(mvdev, mr);
 	mutex_unlock(&mvdev->mr_mtx);
-
-	kfree(mr);
 }
 
 void mlx5_vdpa_update_mr(struct mlx5_vdpa_dev *mvdev,
@@ -534,10 +556,23 @@ void mlx5_vdpa_update_mr(struct mlx5_vdpa_dev *mvdev,
 
 	mutex_lock(&mvdev->mr_mtx);
 
+	_mlx5_vdpa_put_mr(mvdev, old_mr);
 	mvdev->mr[asid] = new_mr;
-	if (old_mr) {
-		_mlx5_vdpa_destroy_mr(mvdev, old_mr);
-		kfree(old_mr);
+
+	mutex_unlock(&mvdev->mr_mtx);
+}
+
+static void mlx5_vdpa_show_mr_leaks(struct mlx5_vdpa_dev *mvdev)
+{
+	struct mlx5_vdpa_mr *mr;
+
+	mutex_lock(&mvdev->mr_mtx);
+
+	list_for_each_entry(mr, &mvdev->mr_list_head, mr_list) {
+
+		mlx5_vdpa_warn(mvdev, "mkey still alive after resource delete: "
+				      "mr: %p, mkey: 0x%x, refcount: %u\n",
+				       mr, mr->mkey, refcount_read(&mr->refcount));
 	}
 
 	mutex_unlock(&mvdev->mr_mtx);
@@ -547,9 +582,11 @@ void mlx5_vdpa_update_mr(struct mlx5_vdpa_dev *mvdev,
 void mlx5_vdpa_destroy_mr_resources(struct mlx5_vdpa_dev *mvdev)
 {
 	for (int i = 0; i < MLX5_VDPA_NUM_AS; i++)
-		mlx5_vdpa_destroy_mr(mvdev, mvdev->mr[i]);
+		mlx5_vdpa_update_mr(mvdev, NULL, i);
 
 	prune_iotlb(mvdev->cvq.iotlb);
+
+	mlx5_vdpa_show_mr_leaks(mvdev);
 }
 
 static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
@@ -576,6 +613,8 @@ static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
 	if (err)
 		goto err_iotlb;
 
+	list_add_tail(&mr->mr_list, &mvdev->mr_list_head);
+
 	return 0;
 
 err_iotlb:
@@ -607,6 +646,8 @@ struct mlx5_vdpa_mr *mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
 	if (err)
 		goto out_err;
 
+	refcount_set(&mr->refcount, 1);
+
 	return mr;
 
 out_err:
@@ -651,7 +692,7 @@ int mlx5_vdpa_reset_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid)
 	if (asid >= MLX5_VDPA_NUM_AS)
 		return -EINVAL;
 
-	mlx5_vdpa_destroy_mr(mvdev, mvdev->mr[asid]);
+	mlx5_vdpa_update_mr(mvdev, NULL, asid);
 
 	if (asid == 0 && MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
 		if (mlx5_vdpa_create_dma_mr(mvdev))
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 26ba7da6b410..778821bab7d9 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -120,6 +120,12 @@ struct mlx5_vdpa_virtqueue {
 	u16 avail_idx;
 	u16 used_idx;
 	int fw_state;
+
+	u64 modified_fields;
+
+	struct mlx5_vdpa_mr *vq_mr;
+	struct mlx5_vdpa_mr *desc_mr;
+
 	struct msi_map map;
 
 	/* keep last in the struct */
@@ -943,6 +949,14 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque
 	kfree(in);
 	mvq->virtq_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
 
+	mlx5_vdpa_get_mr(mvdev, vq_mr);
+	mvq->vq_mr = vq_mr;
+
+	if (vq_desc_mr && MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, desc_group_mkey_supported)) {
+		mlx5_vdpa_get_mr(mvdev, vq_desc_mr);
+		mvq->desc_mr = vq_desc_mr;
+	}
+
 	return 0;
 
 err_cmd:
@@ -969,6 +983,12 @@ static void destroy_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtq
 	}
 	mvq->fw_state = MLX5_VIRTIO_NET_Q_OBJECT_NONE;
 	umems_destroy(ndev, mvq);
+
+	mlx5_vdpa_put_mr(&ndev->mvdev, mvq->vq_mr);
+	mvq->vq_mr = NULL;
+
+	mlx5_vdpa_put_mr(&ndev->mvdev, mvq->desc_mr);
+	mvq->desc_mr = NULL;
 }
 
 static u32 get_rqpn(struct mlx5_vdpa_virtqueue *mvq, bool fw)
@@ -1167,7 +1187,12 @@ err_cmd:
 	return err;
 }
 
-static bool is_valid_state_change(int oldstate, int newstate)
+static bool is_resumable(struct mlx5_vdpa_net *ndev)
+{
+	return ndev->mvdev.vdev.config->resume;
+}
+
+static bool is_valid_state_change(int oldstate, int newstate, bool resumable)
 {
 	switch (oldstate) {
 	case MLX5_VIRTIO_NET_Q_OBJECT_STATE_INIT:
@@ -1175,25 +1200,43 @@ static bool is_valid_state_change(int oldstate, int newstate)
 	case MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY:
 		return newstate == MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND;
 	case MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND:
+		return resumable ? newstate == MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY : false;
 	case MLX5_VIRTIO_NET_Q_OBJECT_STATE_ERR:
 	default:
 		return false;
 	}
 }
 
-static int modify_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq, int state)
+static bool modifiable_virtqueue_fields(struct mlx5_vdpa_virtqueue *mvq)
+{
+	/* Only state is always modifiable */
+	if (mvq->modified_fields & ~MLX5_VIRTQ_MODIFY_MASK_STATE)
+		return mvq->fw_state == MLX5_VIRTIO_NET_Q_OBJECT_STATE_INIT ||
+		       mvq->fw_state == MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND;
+
+	return true;
+}
+
+static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
+			    struct mlx5_vdpa_virtqueue *mvq,
+			    int state)
 {
 	int inlen = MLX5_ST_SZ_BYTES(modify_virtio_net_q_in);
 	u32 out[MLX5_ST_SZ_DW(modify_virtio_net_q_out)] = {};
+	struct mlx5_vdpa_dev *mvdev = &ndev->mvdev;
+	struct mlx5_vdpa_mr *desc_mr = NULL;
+	struct mlx5_vdpa_mr *vq_mr = NULL;
+	bool state_change = false;
 	void *obj_context;
 	void *cmd_hdr;
+	void *vq_ctx;
 	void *in;
 	int err;
 
 	if (mvq->fw_state == MLX5_VIRTIO_NET_Q_OBJECT_NONE)
 		return 0;
 
-	if (!is_valid_state_change(mvq->fw_state, state))
+	if (!modifiable_virtqueue_fields(mvq))
 		return -EINVAL;
 
 	in = kzalloc(inlen, GFP_KERNEL);
@@ -1208,17 +1251,83 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque
 	MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, uid, ndev->mvdev.res.uid);
 
 	obj_context = MLX5_ADDR_OF(modify_virtio_net_q_in, in, obj_context);
-	MLX5_SET64(virtio_net_q_object, obj_context, modify_field_select,
-		   MLX5_VIRTQ_MODIFY_MASK_STATE);
-	MLX5_SET(virtio_net_q_object, obj_context, state, state);
+	vq_ctx = MLX5_ADDR_OF(virtio_net_q_object, obj_context, virtio_q_context);
+
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_STATE) {
+		if (!is_valid_state_change(mvq->fw_state, state, is_resumable(ndev))) {
+			err = -EINVAL;
+			goto done;
+		}
+
+		MLX5_SET(virtio_net_q_object, obj_context, state, state);
+		state_change = true;
+	}
+
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_ADDRS) {
+		MLX5_SET64(virtio_q, vq_ctx, desc_addr, mvq->desc_addr);
+		MLX5_SET64(virtio_q, vq_ctx, used_addr, mvq->device_addr);
+		MLX5_SET64(virtio_q, vq_ctx, available_addr, mvq->driver_addr);
+	}
+
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_AVAIL_IDX)
+		MLX5_SET(virtio_net_q_object, obj_context, hw_available_index, mvq->avail_idx);
+
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX)
+		MLX5_SET(virtio_net_q_object, obj_context, hw_used_index, mvq->used_idx);
+
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY) {
+		vq_mr = mvdev->mr[mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP]];
+
+		if (vq_mr)
+			MLX5_SET(virtio_q, vq_ctx, virtio_q_mkey, vq_mr->mkey);
+		else
+			mvq->modified_fields &= ~MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY;
+	}
+
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY) {
+		desc_mr = mvdev->mr[mvdev->group2asid[MLX5_VDPA_DATAVQ_DESC_GROUP]];
+
+		if (desc_mr && MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, desc_group_mkey_supported))
+			MLX5_SET(virtio_q, vq_ctx, desc_group_mkey, desc_mr->mkey);
+		else
+			mvq->modified_fields &= ~MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY;
+	}
+
+	MLX5_SET64(virtio_net_q_object, obj_context, modify_field_select, mvq->modified_fields);
 	err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out));
-	kfree(in);
-	if (!err)
+	if (err)
+		goto done;
+
+	if (state_change)
 		mvq->fw_state = state;
 
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY) {
+		mlx5_vdpa_put_mr(mvdev, mvq->vq_mr);
+		mlx5_vdpa_get_mr(mvdev, vq_mr);
+		mvq->vq_mr = vq_mr;
+	}
+
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY) {
+		mlx5_vdpa_put_mr(mvdev, mvq->desc_mr);
+		mlx5_vdpa_get_mr(mvdev, desc_mr);
+		mvq->desc_mr = desc_mr;
+	}
+
+	mvq->modified_fields = 0;
+
+done:
+	kfree(in);
 	return err;
 }
 
+static int modify_virtqueue_state(struct mlx5_vdpa_net *ndev,
+				  struct mlx5_vdpa_virtqueue *mvq,
+				  unsigned int state)
+{
+	mvq->modified_fields |= MLX5_VIRTQ_MODIFY_MASK_STATE;
+	return modify_virtqueue(ndev, mvq, state);
+}
+
 static int counter_set_alloc(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
 {
 	u32 in[MLX5_ST_SZ_DW(create_virtio_q_counters_in)] = {};
@@ -1347,7 +1456,7 @@ static int setup_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
 		goto err_vq;
 
 	if (mvq->ready) {
-		err = modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY);
+		err = modify_virtqueue_state(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY);
 		if (err) {
 			mlx5_vdpa_warn(&ndev->mvdev, "failed to modify to ready vq idx %d(%d)\n",
 				       idx, err);
@@ -1382,7 +1491,7 @@ static void suspend_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *m
 	if (mvq->fw_state != MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY)
 		return;
 
-	if (modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND))
+	if (modify_virtqueue_state(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND))
 		mlx5_vdpa_warn(&ndev->mvdev, "modify to suspend failed\n");
 
 	if (query_virtqueue(ndev, mvq, &attr)) {
@@ -1401,12 +1510,31 @@ static void suspend_vqs(struct mlx5_vdpa_net *ndev)
 		suspend_vq(ndev, &ndev->vqs[i]);
 }
 
+static void resume_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
+{
+	if (!mvq->initialized || !is_resumable(ndev))
+		return;
+
+	if (mvq->fw_state != MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND)
+		return;
+
+	if (modify_virtqueue_state(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY))
+		mlx5_vdpa_warn(&ndev->mvdev, "modify to resume failed for vq %u\n", mvq->index);
+}
+
+static void resume_vqs(struct mlx5_vdpa_net *ndev)
+{
+	for (int i = 0; i < ndev->mvdev.max_vqs; i++)
+		resume_vq(ndev, &ndev->vqs[i]);
+}
+
 static void teardown_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
 {
 	if (!mvq->initialized)
 		return;
 
 	suspend_vq(ndev, mvq);
+	mvq->modified_fields = 0;
 	destroy_virtqueue(ndev, mvq);
 	dealloc_vector(ndev, mvq);
 	counter_set_dealloc(ndev, mvq);
@@ -2138,6 +2266,7 @@ static int mlx5_vdpa_set_vq_address(struct vdpa_device *vdev, u16 idx, u64 desc_
 	mvq->desc_addr = desc_area;
 	mvq->device_addr = device_area;
 	mvq->driver_addr = driver_area;
+	mvq->modified_fields |= MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_ADDRS;
 	return 0;
 }
 
@@ -2207,7 +2336,7 @@ static void mlx5_vdpa_set_vq_ready(struct vdpa_device *vdev, u16 idx, bool ready
 	if (!ready) {
 		suspend_vq(ndev, mvq);
 	} else {
-		err = modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY);
+		err = modify_virtqueue_state(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY);
 		if (err) {
 			mlx5_vdpa_warn(mvdev, "modify VQ %d to ready failed (%d)\n", idx, err);
 			ready = false;
@@ -2255,6 +2384,8 @@ static int mlx5_vdpa_set_vq_state(struct vdpa_device *vdev, u16 idx,
 
 	mvq->used_idx = state->split.avail_index;
 	mvq->avail_idx = state->split.avail_index;
+	mvq->modified_fields |= MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_AVAIL_IDX |
+				MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX;
 	return 0;
 }
 
@@ -2703,24 +2834,35 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev,
 				unsigned int asid)
 {
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+	bool teardown = !is_resumable(ndev);
 	int err;
 
 	suspend_vqs(ndev);
-	err = save_channels_info(ndev);
-	if (err)
-		return err;
+	if (teardown) {
+		err = save_channels_info(ndev);
+		if (err)
+			return err;
 
-	teardown_driver(ndev);
+		teardown_driver(ndev);
+	}
 
 	mlx5_vdpa_update_mr(mvdev, new_mr, asid);
 
+	for (int i = 0; i < ndev->cur_num_vqs; i++)
+		ndev->vqs[i].modified_fields |= MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY |
+						MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY;
+
 	if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK) || mvdev->suspended)
 		return 0;
 
-	restore_channels_info(ndev);
-	err = setup_driver(mvdev);
-	if (err)
-		return err;
+	if (teardown) {
+		restore_channels_info(ndev);
+		err = setup_driver(mvdev);
+		if (err)
+			return err;
+	}
+
+	resume_vqs(ndev);
 
 	return 0;
 }
@@ -2804,8 +2946,10 @@ static void clear_vqs_ready(struct mlx5_vdpa_net *ndev)
 {
 	int i;
 
-	for (i = 0; i < ndev->mvdev.max_vqs; i++)
+	for (i = 0; i < ndev->mvdev.max_vqs; i++) {
 		ndev->vqs[i].ready = false;
+		ndev->vqs[i].modified_fields = 0;
+	}
 
 	ndev->mvdev.cvq.ready = false;
 }
@@ -2982,7 +3126,7 @@ static int set_map_data(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
 	return mlx5_vdpa_update_cvq_iotlb(mvdev, iotlb, asid);
 
 out_err:
-	mlx5_vdpa_destroy_mr(mvdev, new_mr);
+	mlx5_vdpa_put_mr(mvdev, new_mr);
 	return err;
 }
 
@@ -3229,6 +3373,23 @@ static int mlx5_vdpa_suspend(struct vdpa_device *vdev)
 	return 0;
 }
 
+static int mlx5_vdpa_resume(struct vdpa_device *vdev)
+{
+	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+	struct mlx5_vdpa_net *ndev;
+
+	ndev = to_mlx5_vdpa_ndev(mvdev);
+
+	mlx5_vdpa_info(mvdev, "resuming device\n");
+
+	down_write(&ndev->reslock);
+	mvdev->suspended = false;
+	resume_vqs(ndev);
+	register_link_notifier(ndev);
+	up_write(&ndev->reslock);
+	return 0;
+}
+
 static int mlx5_set_group_asid(struct vdpa_device *vdev, u32 group,
 			       unsigned int asid)
 {
@@ -3285,6 +3446,7 @@ static const struct vdpa_config_ops mlx5_vdpa_ops = {
 	.get_vq_dma_dev = mlx5_get_vq_dma_dev,
 	.free = mlx5_vdpa_free,
 	.suspend = mlx5_vdpa_suspend,
+	.resume = mlx5_vdpa_resume, /* Op disabled if not supported. */
 };
 
 static int query_mtu(struct mlx5_core_dev *mdev, u16 *mtu)
@@ -3560,6 +3722,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
 	if (err)
 		goto err_mpfs;
 
+	INIT_LIST_HEAD(&mvdev->mr_list_head);
+
 	if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
 		err = mlx5_vdpa_create_dma_mr(mvdev);
 		if (err)
@@ -3656,6 +3820,9 @@ static int mlx5v_probe(struct auxiliary_device *adev,
 	if (!MLX5_CAP_DEV_VDPA_EMULATION(mdev, desc_group_mkey_supported))
 		mgtdev->vdpa_ops.get_vq_desc_group = NULL;
 
+	if (!MLX5_CAP_DEV_VDPA_EMULATION(mdev, freeze_to_rdy_supported))
+		mgtdev->vdpa_ops.resume = NULL;
+
 	err = vdpa_mgmtdev_register(&mgtdev->mgtdev);
 	if (err)
 		goto reg_err;
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index a7612e0783b3..d0695680b282 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -131,7 +131,7 @@ static void vdpa_release_dev(struct device *d)
 	if (ops->free)
 		ops->free(vdev);
 
-	ida_simple_remove(&vdpa_index_ida, vdev->index);
+	ida_free(&vdpa_index_ida, vdev->index);
 	kfree(vdev->driver_override);
 	kfree(vdev);
 }
@@ -205,7 +205,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 	return vdev;
 
 err_name:
-	ida_simple_remove(&vdpa_index_ida, vdev->index);
+	ida_free(&vdpa_index_ida, vdev->index);
 err_ida:
 	kfree(vdev);
 err:
diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index 6bda6dbb4878..ceae52fd7586 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -80,6 +80,16 @@ config VFIO_VIRQFD
 	select EVENTFD
 	default n
 
+config VFIO_DEBUGFS
+	bool "Export VFIO internals in DebugFS"
+	depends on DEBUG_FS
+	help
+	  Allows exposure of VFIO device internals. This option enables
+	  the use of debugfs by VFIO drivers as required. The device can
+	  cause the VFIO code create a top-level debug/vfio directory
+	  during initialization, and then populate a subdirectory with
+	  entries as required.
+
 source "drivers/vfio/pci/Kconfig"
 source "drivers/vfio/platform/Kconfig"
 source "drivers/vfio/mdev/Kconfig"
diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile
index 68c05705200f..b2fc9fb499d8 100644
--- a/drivers/vfio/Makefile
+++ b/drivers/vfio/Makefile
@@ -7,6 +7,7 @@ vfio-$(CONFIG_VFIO_GROUP) += group.o
 vfio-$(CONFIG_IOMMUFD) += iommufd.o
 vfio-$(CONFIG_VFIO_CONTAINER) += container.o
 vfio-$(CONFIG_VFIO_VIRQFD) += virqfd.o
+vfio-$(CONFIG_VFIO_DEBUGFS) += debugfs.o
 
 obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o
 obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o
diff --git a/drivers/vfio/debugfs.c b/drivers/vfio/debugfs.c
new file mode 100644
index 000000000000..298bd866f157
--- /dev/null
+++ b/drivers/vfio/debugfs.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, HiSilicon Ltd.
+ */
+
+#include <linux/device.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/vfio.h>
+#include "vfio.h"
+
+static struct dentry *vfio_debugfs_root;
+
+static int vfio_device_state_read(struct seq_file *seq, void *data)
+{
+	struct device *vf_dev = seq->private;
+	struct vfio_device *vdev = container_of(vf_dev,
+						struct vfio_device, device);
+	enum vfio_device_mig_state state;
+	int ret;
+
+	BUILD_BUG_ON(VFIO_DEVICE_STATE_NR !=
+		     VFIO_DEVICE_STATE_PRE_COPY_P2P + 1);
+
+	ret = vdev->mig_ops->migration_get_state(vdev, &state);
+	if (ret)
+		return -EINVAL;
+
+	switch (state) {
+	case VFIO_DEVICE_STATE_ERROR:
+		seq_puts(seq, "ERROR\n");
+		break;
+	case VFIO_DEVICE_STATE_STOP:
+		seq_puts(seq, "STOP\n");
+		break;
+	case VFIO_DEVICE_STATE_RUNNING:
+		seq_puts(seq, "RUNNING\n");
+		break;
+	case VFIO_DEVICE_STATE_STOP_COPY:
+		seq_puts(seq, "STOP_COPY\n");
+		break;
+	case VFIO_DEVICE_STATE_RESUMING:
+		seq_puts(seq, "RESUMING\n");
+		break;
+	case VFIO_DEVICE_STATE_RUNNING_P2P:
+		seq_puts(seq, "RUNNING_P2P\n");
+		break;
+	case VFIO_DEVICE_STATE_PRE_COPY:
+		seq_puts(seq, "PRE_COPY\n");
+		break;
+	case VFIO_DEVICE_STATE_PRE_COPY_P2P:
+		seq_puts(seq, "PRE_COPY_P2P\n");
+		break;
+	default:
+		seq_puts(seq, "Invalid\n");
+	}
+
+	return 0;
+}
+
+void vfio_device_debugfs_init(struct vfio_device *vdev)
+{
+	struct device *dev = &vdev->device;
+
+	vdev->debug_root = debugfs_create_dir(dev_name(vdev->dev),
+					      vfio_debugfs_root);
+
+	if (vdev->mig_ops) {
+		struct dentry *vfio_dev_migration = NULL;
+
+		vfio_dev_migration = debugfs_create_dir("migration",
+							vdev->debug_root);
+		debugfs_create_devm_seqfile(dev, "state", vfio_dev_migration,
+					    vfio_device_state_read);
+	}
+}
+
+void vfio_device_debugfs_exit(struct vfio_device *vdev)
+{
+	debugfs_remove_recursive(vdev->debug_root);
+}
+
+void vfio_debugfs_create_root(void)
+{
+	vfio_debugfs_root = debugfs_create_dir("vfio", NULL);
+}
+
+void vfio_debugfs_remove_root(void)
+{
+	debugfs_remove_recursive(vfio_debugfs_root);
+	vfio_debugfs_root = NULL;
+}
diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig
index 8125e5f37832..18c397df566d 100644
--- a/drivers/vfio/pci/Kconfig
+++ b/drivers/vfio/pci/Kconfig
@@ -65,4 +65,6 @@ source "drivers/vfio/pci/hisilicon/Kconfig"
 
 source "drivers/vfio/pci/pds/Kconfig"
 
+source "drivers/vfio/pci/virtio/Kconfig"
+
 endmenu
diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile
index 45167be462d8..046139a4eca5 100644
--- a/drivers/vfio/pci/Makefile
+++ b/drivers/vfio/pci/Makefile
@@ -13,3 +13,5 @@ obj-$(CONFIG_MLX5_VFIO_PCI)           += mlx5/
 obj-$(CONFIG_HISI_ACC_VFIO_PCI) += hisilicon/
 
 obj-$(CONFIG_PDS_VFIO_PCI) += pds/
+
+obj-$(CONFIG_VIRTIO_VFIO_PCI) += virtio/
diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
index b2f9778c8366..4d27465c8f1a 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
@@ -694,6 +694,7 @@ static ssize_t hisi_acc_vf_resume_write(struct file *filp, const char __user *bu
 					size_t len, loff_t *pos)
 {
 	struct hisi_acc_vf_migration_file *migf = filp->private_data;
+	u8 *vf_data = (u8 *)&migf->vf_data;
 	loff_t requested_length;
 	ssize_t done = 0;
 	int ret;
@@ -715,7 +716,7 @@ static ssize_t hisi_acc_vf_resume_write(struct file *filp, const char __user *bu
 		goto out_unlock;
 	}
 
-	ret = copy_from_user(&migf->vf_data, buf, len);
+	ret = copy_from_user(vf_data + *pos, buf, len);
 	if (ret) {
 		done = -EFAULT;
 		goto out_unlock;
@@ -835,7 +836,9 @@ static ssize_t hisi_acc_vf_save_read(struct file *filp, char __user *buf, size_t
 
 	len = min_t(size_t, migf->total_length - *pos, len);
 	if (len) {
-		ret = copy_to_user(buf, &migf->vf_data, len);
+		u8 *vf_data = (u8 *)&migf->vf_data;
+
+		ret = copy_to_user(buf, vf_data + *pos, len);
 		if (ret) {
 			done = -EFAULT;
 			goto out_unlock;
diff --git a/drivers/vfio/pci/pds/dirty.c b/drivers/vfio/pci/pds/dirty.c
index c937aa6f3954..8ddf4346fcd5 100644
--- a/drivers/vfio/pci/pds/dirty.c
+++ b/drivers/vfio/pci/pds/dirty.c
@@ -70,7 +70,7 @@ out_free_region_info:
 	kfree(region_info);
 }
 
-static int pds_vfio_dirty_alloc_bitmaps(struct pds_vfio_dirty *dirty,
+static int pds_vfio_dirty_alloc_bitmaps(struct pds_vfio_region *region,
 					unsigned long bytes)
 {
 	unsigned long *host_seq_bmp, *host_ack_bmp;
@@ -85,47 +85,63 @@ static int pds_vfio_dirty_alloc_bitmaps(struct pds_vfio_dirty *dirty,
 		return -ENOMEM;
 	}
 
-	dirty->host_seq.bmp = host_seq_bmp;
-	dirty->host_ack.bmp = host_ack_bmp;
+	region->host_seq = host_seq_bmp;
+	region->host_ack = host_ack_bmp;
+	region->bmp_bytes = bytes;
 
 	return 0;
 }
 
 static void pds_vfio_dirty_free_bitmaps(struct pds_vfio_dirty *dirty)
 {
-	vfree(dirty->host_seq.bmp);
-	vfree(dirty->host_ack.bmp);
-	dirty->host_seq.bmp = NULL;
-	dirty->host_ack.bmp = NULL;
+	if (!dirty->regions)
+		return;
+
+	for (int i = 0; i < dirty->num_regions; i++) {
+		struct pds_vfio_region *region = &dirty->regions[i];
+
+		vfree(region->host_seq);
+		vfree(region->host_ack);
+		region->host_seq = NULL;
+		region->host_ack = NULL;
+		region->bmp_bytes = 0;
+	}
 }
 
 static void __pds_vfio_dirty_free_sgl(struct pds_vfio_pci_device *pds_vfio,
-				      struct pds_vfio_bmp_info *bmp_info)
+				      struct pds_vfio_region *region)
 {
 	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
 	struct device *pdsc_dev = &pci_physfn(pdev)->dev;
 
-	dma_unmap_single(pdsc_dev, bmp_info->sgl_addr,
-			 bmp_info->num_sge * sizeof(struct pds_lm_sg_elem),
+	dma_unmap_single(pdsc_dev, region->sgl_addr,
+			 region->num_sge * sizeof(struct pds_lm_sg_elem),
 			 DMA_BIDIRECTIONAL);
-	kfree(bmp_info->sgl);
+	kfree(region->sgl);
 
-	bmp_info->num_sge = 0;
-	bmp_info->sgl = NULL;
-	bmp_info->sgl_addr = 0;
+	region->num_sge = 0;
+	region->sgl = NULL;
+	region->sgl_addr = 0;
 }
 
 static void pds_vfio_dirty_free_sgl(struct pds_vfio_pci_device *pds_vfio)
 {
-	if (pds_vfio->dirty.host_seq.sgl)
-		__pds_vfio_dirty_free_sgl(pds_vfio, &pds_vfio->dirty.host_seq);
-	if (pds_vfio->dirty.host_ack.sgl)
-		__pds_vfio_dirty_free_sgl(pds_vfio, &pds_vfio->dirty.host_ack);
+	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
+
+	if (!dirty->regions)
+		return;
+
+	for (int i = 0; i < dirty->num_regions; i++) {
+		struct pds_vfio_region *region = &dirty->regions[i];
+
+		if (region->sgl)
+			__pds_vfio_dirty_free_sgl(pds_vfio, region);
+	}
 }
 
-static int __pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
-				      struct pds_vfio_bmp_info *bmp_info,
-				      u32 page_count)
+static int pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
+				    struct pds_vfio_region *region,
+				    u32 page_count)
 {
 	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
 	struct device *pdsc_dev = &pci_physfn(pdev)->dev;
@@ -147,32 +163,81 @@ static int __pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
 		return -EIO;
 	}
 
-	bmp_info->sgl = sgl;
-	bmp_info->num_sge = max_sge;
-	bmp_info->sgl_addr = sgl_addr;
+	region->sgl = sgl;
+	region->num_sge = max_sge;
+	region->sgl_addr = sgl_addr;
 
 	return 0;
 }
 
-static int pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
-				    u32 page_count)
+static void pds_vfio_dirty_free_regions(struct pds_vfio_dirty *dirty)
 {
+	vfree(dirty->regions);
+	dirty->regions = NULL;
+	dirty->num_regions = 0;
+}
+
+static int pds_vfio_dirty_alloc_regions(struct pds_vfio_pci_device *pds_vfio,
+					struct pds_lm_dirty_region_info *region_info,
+					u64 region_page_size, u8 num_regions)
+{
+	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
 	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
+	u32 dev_bmp_offset_byte = 0;
 	int err;
 
-	err = __pds_vfio_dirty_alloc_sgl(pds_vfio, &dirty->host_seq,
-					 page_count);
-	if (err)
-		return err;
+	dirty->regions = vcalloc(num_regions, sizeof(struct pds_vfio_region));
+	if (!dirty->regions)
+		return -ENOMEM;
+	dirty->num_regions = num_regions;
+
+	for (int i = 0; i < num_regions; i++) {
+		struct pds_lm_dirty_region_info *ri = &region_info[i];
+		struct pds_vfio_region *region = &dirty->regions[i];
+		u64 region_size, region_start;
+		u32 page_count;
+
+		/* page_count might be adjusted by the device */
+		page_count = le32_to_cpu(ri->page_count);
+		region_start = le64_to_cpu(ri->dma_base);
+		region_size = page_count * region_page_size;
+
+		err = pds_vfio_dirty_alloc_bitmaps(region,
+						   page_count / BITS_PER_BYTE);
+		if (err) {
+			dev_err(&pdev->dev, "Failed to alloc dirty bitmaps: %pe\n",
+				ERR_PTR(err));
+			goto out_free_regions;
+		}
 
-	err = __pds_vfio_dirty_alloc_sgl(pds_vfio, &dirty->host_ack,
-					 page_count);
-	if (err) {
-		__pds_vfio_dirty_free_sgl(pds_vfio, &dirty->host_seq);
-		return err;
+		err = pds_vfio_dirty_alloc_sgl(pds_vfio, region, page_count);
+		if (err) {
+			dev_err(&pdev->dev, "Failed to alloc dirty sg lists: %pe\n",
+				ERR_PTR(err));
+			goto out_free_regions;
+		}
+
+		region->size = region_size;
+		region->start = region_start;
+		region->page_size = region_page_size;
+		region->dev_bmp_offset_start_byte = dev_bmp_offset_byte;
+
+		dev_bmp_offset_byte += page_count / BITS_PER_BYTE;
+		if (dev_bmp_offset_byte % BITS_PER_BYTE) {
+			dev_err(&pdev->dev, "Device bitmap offset is mis-aligned\n");
+			err = -EINVAL;
+			goto out_free_regions;
+		}
 	}
 
 	return 0;
+
+out_free_regions:
+	pds_vfio_dirty_free_bitmaps(dirty);
+	pds_vfio_dirty_free_sgl(pds_vfio);
+	pds_vfio_dirty_free_regions(dirty);
+
+	return err;
 }
 
 static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio,
@@ -181,16 +246,14 @@ static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio,
 {
 	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
 	struct device *pdsc_dev = &pci_physfn(pdev)->dev;
-	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
-	u64 region_start, region_size, region_page_size;
 	struct pds_lm_dirty_region_info *region_info;
 	struct interval_tree_node *node = NULL;
+	u64 region_page_size = *page_size;
 	u8 max_regions = 0, num_regions;
 	dma_addr_t regions_dma = 0;
 	u32 num_ranges = nnodes;
-	u32 page_count;
-	u16 len;
 	int err;
+	u16 len;
 
 	dev_dbg(&pdev->dev, "vf%u: Start dirty page tracking\n",
 		pds_vfio->vf_id);
@@ -217,39 +280,38 @@ static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio,
 		return -EOPNOTSUPP;
 	}
 
-	/*
-	 * Only support 1 region for now. If there are any large gaps in the
-	 * VM's address regions, then this would be a waste of memory as we are
-	 * generating 2 bitmaps (ack/seq) from the min address to the max
-	 * address of the VM's address regions. In the future, if we support
-	 * more than one region in the device/driver we can split the bitmaps
-	 * on the largest address region gaps. We can do this split up to the
-	 * max_regions times returned from the dirty_status command.
-	 */
-	max_regions = 1;
 	if (num_ranges > max_regions) {
 		vfio_combine_iova_ranges(ranges, nnodes, max_regions);
 		num_ranges = max_regions;
 	}
 
+	region_info = kcalloc(num_ranges, sizeof(*region_info), GFP_KERNEL);
+	if (!region_info)
+		return -ENOMEM;
+	len = num_ranges * sizeof(*region_info);
+
 	node = interval_tree_iter_first(ranges, 0, ULONG_MAX);
 	if (!node)
 		return -EINVAL;
+	for (int i = 0; i < num_ranges; i++) {
+		struct pds_lm_dirty_region_info *ri = &region_info[i];
+		u64 region_size = node->last - node->start + 1;
+		u64 region_start = node->start;
+		u32 page_count;
 
-	region_size = node->last - node->start + 1;
-	region_start = node->start;
-	region_page_size = *page_size;
+		page_count = DIV_ROUND_UP(region_size, region_page_size);
 
-	len = sizeof(*region_info);
-	region_info = kzalloc(len, GFP_KERNEL);
-	if (!region_info)
-		return -ENOMEM;
+		ri->dma_base = cpu_to_le64(region_start);
+		ri->page_count = cpu_to_le32(page_count);
+		ri->page_size_log2 = ilog2(region_page_size);
 
-	page_count = DIV_ROUND_UP(region_size, region_page_size);
+		dev_dbg(&pdev->dev,
+			"region_info[%d]: region_start 0x%llx region_end 0x%lx region_size 0x%llx page_count %u page_size %llu\n",
+			i, region_start, node->last, region_size, page_count,
+			region_page_size);
 
-	region_info->dma_base = cpu_to_le64(region_start);
-	region_info->page_count = cpu_to_le32(page_count);
-	region_info->page_size_log2 = ilog2(region_page_size);
+		node = interval_tree_iter_next(node, 0, ULONG_MAX);
+	}
 
 	regions_dma = dma_map_single(pdsc_dev, (void *)region_info, len,
 				     DMA_BIDIRECTIONAL);
@@ -258,39 +320,20 @@ static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio,
 		goto out_free_region_info;
 	}
 
-	err = pds_vfio_dirty_enable_cmd(pds_vfio, regions_dma, max_regions);
+	err = pds_vfio_dirty_enable_cmd(pds_vfio, regions_dma, num_ranges);
 	dma_unmap_single(pdsc_dev, regions_dma, len, DMA_BIDIRECTIONAL);
 	if (err)
 		goto out_free_region_info;
 
-	/*
-	 * page_count might be adjusted by the device,
-	 * update it before freeing region_info DMA
-	 */
-	page_count = le32_to_cpu(region_info->page_count);
-
-	dev_dbg(&pdev->dev,
-		"region_info: regions_dma 0x%llx dma_base 0x%llx page_count %u page_size_log2 %u\n",
-		regions_dma, region_start, page_count,
-		(u8)ilog2(region_page_size));
-
-	err = pds_vfio_dirty_alloc_bitmaps(dirty, page_count / BITS_PER_BYTE);
-	if (err) {
-		dev_err(&pdev->dev, "Failed to alloc dirty bitmaps: %pe\n",
-			ERR_PTR(err));
-		goto out_free_region_info;
-	}
-
-	err = pds_vfio_dirty_alloc_sgl(pds_vfio, page_count);
+	err = pds_vfio_dirty_alloc_regions(pds_vfio, region_info,
+					   region_page_size, num_ranges);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to alloc dirty sg lists: %pe\n",
-			ERR_PTR(err));
-		goto out_free_bitmaps;
+		dev_err(&pdev->dev,
+			"Failed to allocate %d regions for tracking dirty regions: %pe\n",
+			num_regions, ERR_PTR(err));
+		goto out_dirty_disable;
 	}
 
-	dirty->region_start = region_start;
-	dirty->region_size = region_size;
-	dirty->region_page_size = region_page_size;
 	pds_vfio_dirty_set_enabled(pds_vfio);
 
 	pds_vfio_print_guest_region_info(pds_vfio, max_regions);
@@ -299,8 +342,8 @@ static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio,
 
 	return 0;
 
-out_free_bitmaps:
-	pds_vfio_dirty_free_bitmaps(dirty);
+out_dirty_disable:
+	pds_vfio_dirty_disable_cmd(pds_vfio);
 out_free_region_info:
 	kfree(region_info);
 	return err;
@@ -314,6 +357,7 @@ void pds_vfio_dirty_disable(struct pds_vfio_pci_device *pds_vfio, bool send_cmd)
 			pds_vfio_dirty_disable_cmd(pds_vfio);
 		pds_vfio_dirty_free_sgl(pds_vfio);
 		pds_vfio_dirty_free_bitmaps(&pds_vfio->dirty);
+		pds_vfio_dirty_free_regions(&pds_vfio->dirty);
 	}
 
 	if (send_cmd)
@@ -321,8 +365,9 @@ void pds_vfio_dirty_disable(struct pds_vfio_pci_device *pds_vfio, bool send_cmd)
 }
 
 static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
-				  struct pds_vfio_bmp_info *bmp_info,
-				  u32 offset, u32 bmp_bytes, bool read_seq)
+				  struct pds_vfio_region *region,
+				  unsigned long *seq_ack_bmp, u32 offset,
+				  u32 bmp_bytes, bool read_seq)
 {
 	const char *bmp_type_str = read_seq ? "read_seq" : "write_ack";
 	u8 dma_dir = read_seq ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
@@ -339,7 +384,7 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
 	int err;
 	int i;
 
-	bmp = (void *)((u64)bmp_info->bmp + offset);
+	bmp = (void *)((u64)seq_ack_bmp + offset);
 	page_offset = offset_in_page(bmp);
 	bmp -= page_offset;
 
@@ -375,7 +420,7 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
 		goto out_free_sg_table;
 
 	for_each_sgtable_dma_sg(&sg_table, sg, i) {
-		struct pds_lm_sg_elem *sg_elem = &bmp_info->sgl[i];
+		struct pds_lm_sg_elem *sg_elem = &region->sgl[i];
 
 		sg_elem->addr = cpu_to_le64(sg_dma_address(sg));
 		sg_elem->len = cpu_to_le32(sg_dma_len(sg));
@@ -383,15 +428,16 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
 
 	num_sge = sg_table.nents;
 	size = num_sge * sizeof(struct pds_lm_sg_elem);
-	dma_sync_single_for_device(pdsc_dev, bmp_info->sgl_addr, size, dma_dir);
-	err = pds_vfio_dirty_seq_ack_cmd(pds_vfio, bmp_info->sgl_addr, num_sge,
+	offset += region->dev_bmp_offset_start_byte;
+	dma_sync_single_for_device(pdsc_dev, region->sgl_addr, size, dma_dir);
+	err = pds_vfio_dirty_seq_ack_cmd(pds_vfio, region->sgl_addr, num_sge,
 					 offset, bmp_bytes, read_seq);
 	if (err)
 		dev_err(&pdev->dev,
 			"Dirty bitmap %s failed offset %u bmp_bytes %u num_sge %u DMA 0x%llx: %pe\n",
 			bmp_type_str, offset, bmp_bytes,
-			num_sge, bmp_info->sgl_addr, ERR_PTR(err));
-	dma_sync_single_for_cpu(pdsc_dev, bmp_info->sgl_addr, size, dma_dir);
+			num_sge, region->sgl_addr, ERR_PTR(err));
+	dma_sync_single_for_cpu(pdsc_dev, region->sgl_addr, size, dma_dir);
 
 	dma_unmap_sgtable(pdsc_dev, &sg_table, dma_dir, 0);
 out_free_sg_table:
@@ -403,32 +449,36 @@ out_free_pages:
 }
 
 static int pds_vfio_dirty_write_ack(struct pds_vfio_pci_device *pds_vfio,
+				   struct pds_vfio_region *region,
 				    u32 offset, u32 len)
 {
-	return pds_vfio_dirty_seq_ack(pds_vfio, &pds_vfio->dirty.host_ack,
+
+	return pds_vfio_dirty_seq_ack(pds_vfio, region, region->host_ack,
 				      offset, len, WRITE_ACK);
 }
 
 static int pds_vfio_dirty_read_seq(struct pds_vfio_pci_device *pds_vfio,
+				   struct pds_vfio_region *region,
 				   u32 offset, u32 len)
 {
-	return pds_vfio_dirty_seq_ack(pds_vfio, &pds_vfio->dirty.host_seq,
+	return pds_vfio_dirty_seq_ack(pds_vfio, region, region->host_seq,
 				      offset, len, READ_SEQ);
 }
 
 static int pds_vfio_dirty_process_bitmaps(struct pds_vfio_pci_device *pds_vfio,
+					  struct pds_vfio_region *region,
 					  struct iova_bitmap *dirty_bitmap,
 					  u32 bmp_offset, u32 len_bytes)
 {
-	u64 page_size = pds_vfio->dirty.region_page_size;
-	u64 region_start = pds_vfio->dirty.region_start;
+	u64 page_size = region->page_size;
+	u64 region_start = region->start;
 	u32 bmp_offset_bit;
 	__le64 *seq, *ack;
 	int dword_count;
 
 	dword_count = len_bytes / sizeof(u64);
-	seq = (__le64 *)((u64)pds_vfio->dirty.host_seq.bmp + bmp_offset);
-	ack = (__le64 *)((u64)pds_vfio->dirty.host_ack.bmp + bmp_offset);
+	seq = (__le64 *)((u64)region->host_seq + bmp_offset);
+	ack = (__le64 *)((u64)region->host_ack + bmp_offset);
 	bmp_offset_bit = bmp_offset * 8;
 
 	for (int i = 0; i < dword_count; i++) {
@@ -451,12 +501,28 @@ static int pds_vfio_dirty_process_bitmaps(struct pds_vfio_pci_device *pds_vfio,
 	return 0;
 }
 
+static struct pds_vfio_region *
+pds_vfio_get_region(struct pds_vfio_pci_device *pds_vfio, unsigned long iova)
+{
+	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
+
+	for (int i = 0; i < dirty->num_regions; i++) {
+		struct pds_vfio_region *region = &dirty->regions[i];
+
+		if (iova >= region->start &&
+		    iova < (region->start + region->size))
+			return region;
+	}
+
+	return NULL;
+}
+
 static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio,
 			       struct iova_bitmap *dirty_bitmap,
 			       unsigned long iova, unsigned long length)
 {
 	struct device *dev = &pds_vfio->vfio_coredev.pdev->dev;
-	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
+	struct pds_vfio_region *region;
 	u64 bmp_offset, bmp_bytes;
 	u64 bitmap_size, pages;
 	int err;
@@ -469,26 +535,31 @@ static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio,
 		return -EINVAL;
 	}
 
-	pages = DIV_ROUND_UP(length, pds_vfio->dirty.region_page_size);
+	region = pds_vfio_get_region(pds_vfio, iova);
+	if (!region) {
+		dev_err(dev, "vf%u: Failed to find region that contains iova 0x%lx length 0x%lx\n",
+			pds_vfio->vf_id, iova, length);
+		return -EINVAL;
+	}
+
+	pages = DIV_ROUND_UP(length, region->page_size);
 	bitmap_size =
 		round_up(pages, sizeof(u64) * BITS_PER_BYTE) / BITS_PER_BYTE;
 
 	dev_dbg(dev,
 		"vf%u: iova 0x%lx length %lu page_size %llu pages %llu bitmap_size %llu\n",
-		pds_vfio->vf_id, iova, length, pds_vfio->dirty.region_page_size,
+		pds_vfio->vf_id, iova, length, region->page_size,
 		pages, bitmap_size);
 
-	if (!length || ((dirty->region_start + iova + length) >
-			(dirty->region_start + dirty->region_size))) {
+	if (!length || ((iova - region->start + length) > region->size)) {
 		dev_err(dev, "Invalid iova 0x%lx and/or length 0x%lx to sync\n",
 			iova, length);
 		return -EINVAL;
 	}
 
 	/* bitmap is modified in 64 bit chunks */
-	bmp_bytes = ALIGN(DIV_ROUND_UP(length / dirty->region_page_size,
-				       sizeof(u64)),
-			  sizeof(u64));
+	bmp_bytes = ALIGN(DIV_ROUND_UP(length / region->page_size,
+				       sizeof(u64)), sizeof(u64));
 	if (bmp_bytes != bitmap_size) {
 		dev_err(dev,
 			"Calculated bitmap bytes %llu not equal to bitmap size %llu\n",
@@ -496,22 +567,30 @@ static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio,
 		return -EINVAL;
 	}
 
-	bmp_offset = DIV_ROUND_UP(iova / dirty->region_page_size, sizeof(u64));
+	if (bmp_bytes > region->bmp_bytes) {
+		dev_err(dev,
+			"Calculated bitmap bytes %llu larger than region's cached bmp_bytes %llu\n",
+			bmp_bytes, region->bmp_bytes);
+		return -EINVAL;
+	}
+
+	bmp_offset = DIV_ROUND_UP((iova - region->start) /
+				  region->page_size, sizeof(u64));
 
 	dev_dbg(dev,
 		"Syncing dirty bitmap, iova 0x%lx length 0x%lx, bmp_offset %llu bmp_bytes %llu\n",
 		iova, length, bmp_offset, bmp_bytes);
 
-	err = pds_vfio_dirty_read_seq(pds_vfio, bmp_offset, bmp_bytes);
+	err = pds_vfio_dirty_read_seq(pds_vfio, region, bmp_offset, bmp_bytes);
 	if (err)
 		return err;
 
-	err = pds_vfio_dirty_process_bitmaps(pds_vfio, dirty_bitmap, bmp_offset,
-					     bmp_bytes);
+	err = pds_vfio_dirty_process_bitmaps(pds_vfio, region, dirty_bitmap,
+					     bmp_offset, bmp_bytes);
 	if (err)
 		return err;
 
-	err = pds_vfio_dirty_write_ack(pds_vfio, bmp_offset, bmp_bytes);
+	err = pds_vfio_dirty_write_ack(pds_vfio, region, bmp_offset, bmp_bytes);
 	if (err)
 		return err;
 
diff --git a/drivers/vfio/pci/pds/dirty.h b/drivers/vfio/pci/pds/dirty.h
index f78da25d75ca..c8e23018b801 100644
--- a/drivers/vfio/pci/pds/dirty.h
+++ b/drivers/vfio/pci/pds/dirty.h
@@ -4,20 +4,22 @@
 #ifndef _DIRTY_H_
 #define _DIRTY_H_
 
-struct pds_vfio_bmp_info {
-	unsigned long *bmp;
-	u32 bmp_bytes;
+struct pds_vfio_region {
+	unsigned long *host_seq;
+	unsigned long *host_ack;
+	u64 bmp_bytes;
+	u64 size;
+	u64 start;
+	u64 page_size;
 	struct pds_lm_sg_elem *sgl;
 	dma_addr_t sgl_addr;
+	u32 dev_bmp_offset_start_byte;
 	u16 num_sge;
 };
 
 struct pds_vfio_dirty {
-	struct pds_vfio_bmp_info host_seq;
-	struct pds_vfio_bmp_info host_ack;
-	u64 region_size;
-	u64 region_start;
-	u64 region_page_size;
+	struct pds_vfio_region *regions;
+	u8 num_regions;
 	bool is_enabled;
 };
 
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index e27de61ac9fe..07fea08ea8a2 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -38,7 +38,7 @@
 #define vfio_iowrite8	iowrite8
 
 #define VFIO_IOWRITE(size) \
-static int vfio_pci_iowrite##size(struct vfio_pci_core_device *vdev,		\
+int vfio_pci_core_iowrite##size(struct vfio_pci_core_device *vdev,	\
 			bool test_mem, u##size val, void __iomem *io)	\
 {									\
 	if (test_mem) {							\
@@ -55,7 +55,8 @@ static int vfio_pci_iowrite##size(struct vfio_pci_core_device *vdev,		\
 		up_read(&vdev->memory_lock);				\
 									\
 	return 0;							\
-}
+}									\
+EXPORT_SYMBOL_GPL(vfio_pci_core_iowrite##size);
 
 VFIO_IOWRITE(8)
 VFIO_IOWRITE(16)
@@ -65,7 +66,7 @@ VFIO_IOWRITE(64)
 #endif
 
 #define VFIO_IOREAD(size) \
-static int vfio_pci_ioread##size(struct vfio_pci_core_device *vdev,		\
+int vfio_pci_core_ioread##size(struct vfio_pci_core_device *vdev,	\
 			bool test_mem, u##size *val, void __iomem *io)	\
 {									\
 	if (test_mem) {							\
@@ -82,7 +83,8 @@ static int vfio_pci_ioread##size(struct vfio_pci_core_device *vdev,		\
 		up_read(&vdev->memory_lock);				\
 									\
 	return 0;							\
-}
+}									\
+EXPORT_SYMBOL_GPL(vfio_pci_core_ioread##size);
 
 VFIO_IOREAD(8)
 VFIO_IOREAD(16)
@@ -119,13 +121,13 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 				if (copy_from_user(&val, buf, 4))
 					return -EFAULT;
 
-				ret = vfio_pci_iowrite32(vdev, test_mem,
-							 val, io + off);
+				ret = vfio_pci_core_iowrite32(vdev, test_mem,
+							      val, io + off);
 				if (ret)
 					return ret;
 			} else {
-				ret = vfio_pci_ioread32(vdev, test_mem,
-							&val, io + off);
+				ret = vfio_pci_core_ioread32(vdev, test_mem,
+							     &val, io + off);
 				if (ret)
 					return ret;
 
@@ -141,13 +143,13 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 				if (copy_from_user(&val, buf, 2))
 					return -EFAULT;
 
-				ret = vfio_pci_iowrite16(vdev, test_mem,
-							 val, io + off);
+				ret = vfio_pci_core_iowrite16(vdev, test_mem,
+							      val, io + off);
 				if (ret)
 					return ret;
 			} else {
-				ret = vfio_pci_ioread16(vdev, test_mem,
-							&val, io + off);
+				ret = vfio_pci_core_ioread16(vdev, test_mem,
+							     &val, io + off);
 				if (ret)
 					return ret;
 
@@ -163,13 +165,13 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 				if (copy_from_user(&val, buf, 1))
 					return -EFAULT;
 
-				ret = vfio_pci_iowrite8(vdev, test_mem,
-							val, io + off);
+				ret = vfio_pci_core_iowrite8(vdev, test_mem,
+							     val, io + off);
 				if (ret)
 					return ret;
 			} else {
-				ret = vfio_pci_ioread8(vdev, test_mem,
-						       &val, io + off);
+				ret = vfio_pci_core_ioread8(vdev, test_mem,
+							    &val, io + off);
 				if (ret)
 					return ret;
 
@@ -200,7 +202,7 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 	return done;
 }
 
-static int vfio_pci_setup_barmap(struct vfio_pci_core_device *vdev, int bar)
+int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar)
 {
 	struct pci_dev *pdev = vdev->pdev;
 	int ret;
@@ -223,6 +225,7 @@ static int vfio_pci_setup_barmap(struct vfio_pci_core_device *vdev, int bar)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(vfio_pci_core_setup_barmap);
 
 ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
 			size_t count, loff_t *ppos, bool iswrite)
@@ -262,7 +265,7 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
 		}
 		x_end = end;
 	} else {
-		int ret = vfio_pci_setup_barmap(vdev, bar);
+		int ret = vfio_pci_core_setup_barmap(vdev, bar);
 		if (ret) {
 			done = ret;
 			goto out;
@@ -363,21 +366,21 @@ static void vfio_pci_ioeventfd_do_write(struct vfio_pci_ioeventfd *ioeventfd,
 {
 	switch (ioeventfd->count) {
 	case 1:
-		vfio_pci_iowrite8(ioeventfd->vdev, test_mem,
-				  ioeventfd->data, ioeventfd->addr);
+		vfio_pci_core_iowrite8(ioeventfd->vdev, test_mem,
+				       ioeventfd->data, ioeventfd->addr);
 		break;
 	case 2:
-		vfio_pci_iowrite16(ioeventfd->vdev, test_mem,
-				   ioeventfd->data, ioeventfd->addr);
+		vfio_pci_core_iowrite16(ioeventfd->vdev, test_mem,
+					ioeventfd->data, ioeventfd->addr);
 		break;
 	case 4:
-		vfio_pci_iowrite32(ioeventfd->vdev, test_mem,
-				   ioeventfd->data, ioeventfd->addr);
+		vfio_pci_core_iowrite32(ioeventfd->vdev, test_mem,
+					ioeventfd->data, ioeventfd->addr);
 		break;
 #ifdef iowrite64
 	case 8:
-		vfio_pci_iowrite64(ioeventfd->vdev, test_mem,
-				   ioeventfd->data, ioeventfd->addr);
+		vfio_pci_core_iowrite64(ioeventfd->vdev, test_mem,
+					ioeventfd->data, ioeventfd->addr);
 		break;
 #endif
 	}
@@ -438,7 +441,7 @@ int vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset,
 		return -EINVAL;
 #endif
 
-	ret = vfio_pci_setup_barmap(vdev, bar);
+	ret = vfio_pci_core_setup_barmap(vdev, bar);
 	if (ret)
 		return ret;
 
diff --git a/drivers/vfio/pci/virtio/Kconfig b/drivers/vfio/pci/virtio/Kconfig
new file mode 100644
index 000000000000..bd80eca4a196
--- /dev/null
+++ b/drivers/vfio/pci/virtio/Kconfig
@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config VIRTIO_VFIO_PCI
+        tristate "VFIO support for VIRTIO NET PCI devices"
+        depends on VIRTIO_PCI && VIRTIO_PCI_ADMIN_LEGACY
+        select VFIO_PCI_CORE
+        help
+          This provides support for exposing VIRTIO NET VF devices which support
+          legacy IO access, using the VFIO framework that can work with a legacy
+          virtio driver in the guest.
+          Based on PCIe spec, VFs do not support I/O Space.
+          As of that this driver emulates I/O BAR in software to let a VF be
+          seen as a transitional device by its users and let it work with
+          a legacy driver.
+
+          If you don't know what to do here, say N.
diff --git a/drivers/vfio/pci/virtio/Makefile b/drivers/vfio/pci/virtio/Makefile
new file mode 100644
index 000000000000..7171105baf33
--- /dev/null
+++ b/drivers/vfio/pci/virtio/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_VIRTIO_VFIO_PCI) += virtio-vfio-pci.o
+virtio-vfio-pci-y := main.o
diff --git a/drivers/vfio/pci/virtio/main.c b/drivers/vfio/pci/virtio/main.c
new file mode 100644
index 000000000000..d5af683837d3
--- /dev/null
+++ b/drivers/vfio/pci/virtio/main.c
@@ -0,0 +1,576 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/pm_runtime.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/vfio.h>
+#include <linux/vfio_pci_core.h>
+#include <linux/virtio_pci.h>
+#include <linux/virtio_net.h>
+#include <linux/virtio_pci_admin.h>
+
+struct virtiovf_pci_core_device {
+	struct vfio_pci_core_device core_device;
+	u8 *bar0_virtual_buf;
+	/* synchronize access to the virtual buf */
+	struct mutex bar_mutex;
+	void __iomem *notify_addr;
+	u64 notify_offset;
+	__le32 pci_base_addr_0;
+	__le16 pci_cmd;
+	u8 bar0_virtual_buf_size;
+	u8 notify_bar;
+};
+
+static int
+virtiovf_issue_legacy_rw_cmd(struct virtiovf_pci_core_device *virtvdev,
+			     loff_t pos, char __user *buf,
+			     size_t count, bool read)
+{
+	bool msix_enabled =
+		(virtvdev->core_device.irq_type == VFIO_PCI_MSIX_IRQ_INDEX);
+	struct pci_dev *pdev = virtvdev->core_device.pdev;
+	u8 *bar0_buf = virtvdev->bar0_virtual_buf;
+	bool common;
+	u8 offset;
+	int ret;
+
+	common = pos < VIRTIO_PCI_CONFIG_OFF(msix_enabled);
+	/* offset within the relevant configuration area */
+	offset = common ? pos : pos - VIRTIO_PCI_CONFIG_OFF(msix_enabled);
+	mutex_lock(&virtvdev->bar_mutex);
+	if (read) {
+		if (common)
+			ret = virtio_pci_admin_legacy_common_io_read(pdev, offset,
+					count, bar0_buf + pos);
+		else
+			ret = virtio_pci_admin_legacy_device_io_read(pdev, offset,
+					count, bar0_buf + pos);
+		if (ret)
+			goto out;
+		if (copy_to_user(buf, bar0_buf + pos, count))
+			ret = -EFAULT;
+	} else {
+		if (copy_from_user(bar0_buf + pos, buf, count)) {
+			ret = -EFAULT;
+			goto out;
+		}
+
+		if (common)
+			ret = virtio_pci_admin_legacy_common_io_write(pdev, offset,
+					count, bar0_buf + pos);
+		else
+			ret = virtio_pci_admin_legacy_device_io_write(pdev, offset,
+					count, bar0_buf + pos);
+	}
+out:
+	mutex_unlock(&virtvdev->bar_mutex);
+	return ret;
+}
+
+static int
+virtiovf_pci_bar0_rw(struct virtiovf_pci_core_device *virtvdev,
+		     loff_t pos, char __user *buf,
+		     size_t count, bool read)
+{
+	struct vfio_pci_core_device *core_device = &virtvdev->core_device;
+	struct pci_dev *pdev = core_device->pdev;
+	u16 queue_notify;
+	int ret;
+
+	if (!(le16_to_cpu(virtvdev->pci_cmd) & PCI_COMMAND_IO))
+		return -EIO;
+
+	if (pos + count > virtvdev->bar0_virtual_buf_size)
+		return -EINVAL;
+
+	ret = pm_runtime_resume_and_get(&pdev->dev);
+	if (ret) {
+		pci_info_ratelimited(pdev, "runtime resume failed %d\n", ret);
+		return -EIO;
+	}
+
+	switch (pos) {
+	case VIRTIO_PCI_QUEUE_NOTIFY:
+		if (count != sizeof(queue_notify)) {
+			ret = -EINVAL;
+			goto end;
+		}
+		if (read) {
+			ret = vfio_pci_core_ioread16(core_device, true, &queue_notify,
+						     virtvdev->notify_addr);
+			if (ret)
+				goto end;
+			if (copy_to_user(buf, &queue_notify,
+					 sizeof(queue_notify))) {
+				ret = -EFAULT;
+				goto end;
+			}
+		} else {
+			if (copy_from_user(&queue_notify, buf, count)) {
+				ret = -EFAULT;
+				goto end;
+			}
+			ret = vfio_pci_core_iowrite16(core_device, true, queue_notify,
+						      virtvdev->notify_addr);
+		}
+		break;
+	default:
+		ret = virtiovf_issue_legacy_rw_cmd(virtvdev, pos, buf, count,
+						   read);
+	}
+
+end:
+	pm_runtime_put(&pdev->dev);
+	return ret ? ret : count;
+}
+
+static bool range_intersect_range(loff_t range1_start, size_t count1,
+				  loff_t range2_start, size_t count2,
+				  loff_t *start_offset,
+				  size_t *intersect_count,
+				  size_t *register_offset)
+{
+	if (range1_start <= range2_start &&
+	    range1_start + count1 > range2_start) {
+		*start_offset = range2_start - range1_start;
+		*intersect_count = min_t(size_t, count2,
+					 range1_start + count1 - range2_start);
+		*register_offset = 0;
+		return true;
+	}
+
+	if (range1_start > range2_start &&
+	    range1_start < range2_start + count2) {
+		*start_offset = 0;
+		*intersect_count = min_t(size_t, count1,
+					 range2_start + count2 - range1_start);
+		*register_offset = range1_start - range2_start;
+		return true;
+	}
+
+	return false;
+}
+
+static ssize_t virtiovf_pci_read_config(struct vfio_device *core_vdev,
+					char __user *buf, size_t count,
+					loff_t *ppos)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
+	size_t register_offset;
+	loff_t copy_offset;
+	size_t copy_count;
+	__le32 val32;
+	__le16 val16;
+	u8 val8;
+	int ret;
+
+	ret = vfio_pci_core_read(core_vdev, buf, count, ppos);
+	if (ret < 0)
+		return ret;
+
+	if (range_intersect_range(pos, count, PCI_DEVICE_ID, sizeof(val16),
+				  &copy_offset, &copy_count, &register_offset)) {
+		val16 = cpu_to_le16(VIRTIO_TRANS_ID_NET);
+		if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset, copy_count))
+			return -EFAULT;
+	}
+
+	if ((le16_to_cpu(virtvdev->pci_cmd) & PCI_COMMAND_IO) &&
+	    range_intersect_range(pos, count, PCI_COMMAND, sizeof(val16),
+				  &copy_offset, &copy_count, &register_offset)) {
+		if (copy_from_user((void *)&val16 + register_offset, buf + copy_offset,
+				   copy_count))
+			return -EFAULT;
+		val16 |= cpu_to_le16(PCI_COMMAND_IO);
+		if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset,
+				 copy_count))
+			return -EFAULT;
+	}
+
+	if (range_intersect_range(pos, count, PCI_REVISION_ID, sizeof(val8),
+				  &copy_offset, &copy_count, &register_offset)) {
+		/* Transional needs to have revision 0 */
+		val8 = 0;
+		if (copy_to_user(buf + copy_offset, &val8, copy_count))
+			return -EFAULT;
+	}
+
+	if (range_intersect_range(pos, count, PCI_BASE_ADDRESS_0, sizeof(val32),
+				  &copy_offset, &copy_count, &register_offset)) {
+		u32 bar_mask = ~(virtvdev->bar0_virtual_buf_size - 1);
+		u32 pci_base_addr_0 = le32_to_cpu(virtvdev->pci_base_addr_0);
+
+		val32 = cpu_to_le32((pci_base_addr_0 & bar_mask) | PCI_BASE_ADDRESS_SPACE_IO);
+		if (copy_to_user(buf + copy_offset, (void *)&val32 + register_offset, copy_count))
+			return -EFAULT;
+	}
+
+	if (range_intersect_range(pos, count, PCI_SUBSYSTEM_ID, sizeof(val16),
+				  &copy_offset, &copy_count, &register_offset)) {
+		/*
+		 * Transitional devices use the PCI subsystem device id as
+		 * virtio device id, same as legacy driver always did.
+		 */
+		val16 = cpu_to_le16(VIRTIO_ID_NET);
+		if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset,
+				 copy_count))
+			return -EFAULT;
+	}
+
+	if (range_intersect_range(pos, count, PCI_SUBSYSTEM_VENDOR_ID, sizeof(val16),
+				  &copy_offset, &copy_count, &register_offset)) {
+		val16 = cpu_to_le16(PCI_VENDOR_ID_REDHAT_QUMRANET);
+		if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset,
+				 copy_count))
+			return -EFAULT;
+	}
+
+	return count;
+}
+
+static ssize_t
+virtiovf_pci_core_read(struct vfio_device *core_vdev, char __user *buf,
+		       size_t count, loff_t *ppos)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
+	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
+
+	if (!count)
+		return 0;
+
+	if (index == VFIO_PCI_CONFIG_REGION_INDEX)
+		return virtiovf_pci_read_config(core_vdev, buf, count, ppos);
+
+	if (index == VFIO_PCI_BAR0_REGION_INDEX)
+		return virtiovf_pci_bar0_rw(virtvdev, pos, buf, count, true);
+
+	return vfio_pci_core_read(core_vdev, buf, count, ppos);
+}
+
+static ssize_t virtiovf_pci_write_config(struct vfio_device *core_vdev,
+					 const char __user *buf, size_t count,
+					 loff_t *ppos)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
+	size_t register_offset;
+	loff_t copy_offset;
+	size_t copy_count;
+
+	if (range_intersect_range(pos, count, PCI_COMMAND, sizeof(virtvdev->pci_cmd),
+				  &copy_offset, &copy_count,
+				  &register_offset)) {
+		if (copy_from_user((void *)&virtvdev->pci_cmd + register_offset,
+				   buf + copy_offset,
+				   copy_count))
+			return -EFAULT;
+	}
+
+	if (range_intersect_range(pos, count, PCI_BASE_ADDRESS_0,
+				  sizeof(virtvdev->pci_base_addr_0),
+				  &copy_offset, &copy_count,
+				  &register_offset)) {
+		if (copy_from_user((void *)&virtvdev->pci_base_addr_0 + register_offset,
+				   buf + copy_offset,
+				   copy_count))
+			return -EFAULT;
+	}
+
+	return vfio_pci_core_write(core_vdev, buf, count, ppos);
+}
+
+static ssize_t
+virtiovf_pci_core_write(struct vfio_device *core_vdev, const char __user *buf,
+			size_t count, loff_t *ppos)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
+	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
+
+	if (!count)
+		return 0;
+
+	if (index == VFIO_PCI_CONFIG_REGION_INDEX)
+		return virtiovf_pci_write_config(core_vdev, buf, count, ppos);
+
+	if (index == VFIO_PCI_BAR0_REGION_INDEX)
+		return virtiovf_pci_bar0_rw(virtvdev, pos, (char __user *)buf, count, false);
+
+	return vfio_pci_core_write(core_vdev, buf, count, ppos);
+}
+
+static int
+virtiovf_pci_ioctl_get_region_info(struct vfio_device *core_vdev,
+				   unsigned int cmd, unsigned long arg)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	unsigned long minsz = offsetofend(struct vfio_region_info, offset);
+	void __user *uarg = (void __user *)arg;
+	struct vfio_region_info info = {};
+
+	if (copy_from_user(&info, uarg, minsz))
+		return -EFAULT;
+
+	if (info.argsz < minsz)
+		return -EINVAL;
+
+	switch (info.index) {
+	case VFIO_PCI_BAR0_REGION_INDEX:
+		info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
+		info.size = virtvdev->bar0_virtual_buf_size;
+		info.flags = VFIO_REGION_INFO_FLAG_READ |
+			     VFIO_REGION_INFO_FLAG_WRITE;
+		return copy_to_user(uarg, &info, minsz) ? -EFAULT : 0;
+	default:
+		return vfio_pci_core_ioctl(core_vdev, cmd, arg);
+	}
+}
+
+static long
+virtiovf_vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd,
+			     unsigned long arg)
+{
+	switch (cmd) {
+	case VFIO_DEVICE_GET_REGION_INFO:
+		return virtiovf_pci_ioctl_get_region_info(core_vdev, cmd, arg);
+	default:
+		return vfio_pci_core_ioctl(core_vdev, cmd, arg);
+	}
+}
+
+static int
+virtiovf_set_notify_addr(struct virtiovf_pci_core_device *virtvdev)
+{
+	struct vfio_pci_core_device *core_device = &virtvdev->core_device;
+	int ret;
+
+	/*
+	 * Setup the BAR where the 'notify' exists to be used by vfio as well
+	 * This will let us mmap it only once and use it when needed.
+	 */
+	ret = vfio_pci_core_setup_barmap(core_device,
+					 virtvdev->notify_bar);
+	if (ret)
+		return ret;
+
+	virtvdev->notify_addr = core_device->barmap[virtvdev->notify_bar] +
+			virtvdev->notify_offset;
+	return 0;
+}
+
+static int virtiovf_pci_open_device(struct vfio_device *core_vdev)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	struct vfio_pci_core_device *vdev = &virtvdev->core_device;
+	int ret;
+
+	ret = vfio_pci_core_enable(vdev);
+	if (ret)
+		return ret;
+
+	if (virtvdev->bar0_virtual_buf) {
+		/*
+		 * Upon close_device() the vfio_pci_core_disable() is called
+		 * and will close all the previous mmaps, so it seems that the
+		 * valid life cycle for the 'notify' addr is per open/close.
+		 */
+		ret = virtiovf_set_notify_addr(virtvdev);
+		if (ret) {
+			vfio_pci_core_disable(vdev);
+			return ret;
+		}
+	}
+
+	vfio_pci_core_finish_enable(vdev);
+	return 0;
+}
+
+static int virtiovf_get_device_config_size(unsigned short device)
+{
+	/* Network card */
+	return offsetofend(struct virtio_net_config, status);
+}
+
+static int virtiovf_read_notify_info(struct virtiovf_pci_core_device *virtvdev)
+{
+	u64 offset;
+	int ret;
+	u8 bar;
+
+	ret = virtio_pci_admin_legacy_io_notify_info(virtvdev->core_device.pdev,
+				VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_OWNER_MEM,
+				&bar, &offset);
+	if (ret)
+		return ret;
+
+	virtvdev->notify_bar = bar;
+	virtvdev->notify_offset = offset;
+	return 0;
+}
+
+static int virtiovf_pci_init_device(struct vfio_device *core_vdev)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	struct pci_dev *pdev;
+	int ret;
+
+	ret = vfio_pci_core_init_dev(core_vdev);
+	if (ret)
+		return ret;
+
+	pdev = virtvdev->core_device.pdev;
+	ret = virtiovf_read_notify_info(virtvdev);
+	if (ret)
+		return ret;
+
+	virtvdev->bar0_virtual_buf_size = VIRTIO_PCI_CONFIG_OFF(true) +
+				virtiovf_get_device_config_size(pdev->device);
+	BUILD_BUG_ON(!is_power_of_2(virtvdev->bar0_virtual_buf_size));
+	virtvdev->bar0_virtual_buf = kzalloc(virtvdev->bar0_virtual_buf_size,
+					     GFP_KERNEL);
+	if (!virtvdev->bar0_virtual_buf)
+		return -ENOMEM;
+	mutex_init(&virtvdev->bar_mutex);
+	return 0;
+}
+
+static void virtiovf_pci_core_release_dev(struct vfio_device *core_vdev)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+
+	kfree(virtvdev->bar0_virtual_buf);
+	vfio_pci_core_release_dev(core_vdev);
+}
+
+static const struct vfio_device_ops virtiovf_vfio_pci_tran_ops = {
+	.name = "virtio-vfio-pci-trans",
+	.init = virtiovf_pci_init_device,
+	.release = virtiovf_pci_core_release_dev,
+	.open_device = virtiovf_pci_open_device,
+	.close_device = vfio_pci_core_close_device,
+	.ioctl = virtiovf_vfio_pci_core_ioctl,
+	.device_feature = vfio_pci_core_ioctl_feature,
+	.read = virtiovf_pci_core_read,
+	.write = virtiovf_pci_core_write,
+	.mmap = vfio_pci_core_mmap,
+	.request = vfio_pci_core_request,
+	.match = vfio_pci_core_match,
+	.bind_iommufd = vfio_iommufd_physical_bind,
+	.unbind_iommufd = vfio_iommufd_physical_unbind,
+	.attach_ioas = vfio_iommufd_physical_attach_ioas,
+	.detach_ioas = vfio_iommufd_physical_detach_ioas,
+};
+
+static const struct vfio_device_ops virtiovf_vfio_pci_ops = {
+	.name = "virtio-vfio-pci",
+	.init = vfio_pci_core_init_dev,
+	.release = vfio_pci_core_release_dev,
+	.open_device = virtiovf_pci_open_device,
+	.close_device = vfio_pci_core_close_device,
+	.ioctl = vfio_pci_core_ioctl,
+	.device_feature = vfio_pci_core_ioctl_feature,
+	.read = vfio_pci_core_read,
+	.write = vfio_pci_core_write,
+	.mmap = vfio_pci_core_mmap,
+	.request = vfio_pci_core_request,
+	.match = vfio_pci_core_match,
+	.bind_iommufd = vfio_iommufd_physical_bind,
+	.unbind_iommufd = vfio_iommufd_physical_unbind,
+	.attach_ioas = vfio_iommufd_physical_attach_ioas,
+	.detach_ioas = vfio_iommufd_physical_detach_ioas,
+};
+
+static bool virtiovf_bar0_exists(struct pci_dev *pdev)
+{
+	struct resource *res = pdev->resource;
+
+	return res->flags;
+}
+
+static int virtiovf_pci_probe(struct pci_dev *pdev,
+			      const struct pci_device_id *id)
+{
+	const struct vfio_device_ops *ops = &virtiovf_vfio_pci_ops;
+	struct virtiovf_pci_core_device *virtvdev;
+	int ret;
+
+	if (pdev->is_virtfn && virtio_pci_admin_has_legacy_io(pdev) &&
+	    !virtiovf_bar0_exists(pdev))
+		ops = &virtiovf_vfio_pci_tran_ops;
+
+	virtvdev = vfio_alloc_device(virtiovf_pci_core_device, core_device.vdev,
+				     &pdev->dev, ops);
+	if (IS_ERR(virtvdev))
+		return PTR_ERR(virtvdev);
+
+	dev_set_drvdata(&pdev->dev, &virtvdev->core_device);
+	ret = vfio_pci_core_register_device(&virtvdev->core_device);
+	if (ret)
+		goto out;
+	return 0;
+out:
+	vfio_put_device(&virtvdev->core_device.vdev);
+	return ret;
+}
+
+static void virtiovf_pci_remove(struct pci_dev *pdev)
+{
+	struct virtiovf_pci_core_device *virtvdev = dev_get_drvdata(&pdev->dev);
+
+	vfio_pci_core_unregister_device(&virtvdev->core_device);
+	vfio_put_device(&virtvdev->core_device.vdev);
+}
+
+static const struct pci_device_id virtiovf_pci_table[] = {
+	/* Only virtio-net is supported/tested so far */
+	{ PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_REDHAT_QUMRANET, 0x1041) },
+	{}
+};
+
+MODULE_DEVICE_TABLE(pci, virtiovf_pci_table);
+
+static void virtiovf_pci_aer_reset_done(struct pci_dev *pdev)
+{
+	struct virtiovf_pci_core_device *virtvdev = dev_get_drvdata(&pdev->dev);
+
+	virtvdev->pci_cmd = 0;
+}
+
+static const struct pci_error_handlers virtiovf_err_handlers = {
+	.reset_done = virtiovf_pci_aer_reset_done,
+	.error_detected = vfio_pci_core_aer_err_detected,
+};
+
+static struct pci_driver virtiovf_pci_driver = {
+	.name = KBUILD_MODNAME,
+	.id_table = virtiovf_pci_table,
+	.probe = virtiovf_pci_probe,
+	.remove = virtiovf_pci_remove,
+	.err_handler = &virtiovf_err_handlers,
+	.driver_managed_dma = true,
+};
+
+module_pci_driver(virtiovf_pci_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Yishai Hadas <yishaih@nvidia.com>");
+MODULE_DESCRIPTION(
+	"VIRTIO VFIO PCI - User Level meta-driver for VIRTIO NET devices");
diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h
index 307e3f29b527..bde84ad344e5 100644
--- a/drivers/vfio/vfio.h
+++ b/drivers/vfio/vfio.h
@@ -448,4 +448,18 @@ static inline void vfio_device_put_kvm(struct vfio_device *device)
 }
 #endif
 
+#ifdef CONFIG_VFIO_DEBUGFS
+void vfio_debugfs_create_root(void);
+void vfio_debugfs_remove_root(void);
+
+void vfio_device_debugfs_init(struct vfio_device *vdev);
+void vfio_device_debugfs_exit(struct vfio_device *vdev);
+#else
+static inline void vfio_debugfs_create_root(void) { }
+static inline void vfio_debugfs_remove_root(void) { }
+
+static inline void vfio_device_debugfs_init(struct vfio_device *vdev) { }
+static inline void vfio_device_debugfs_exit(struct vfio_device *vdev) { }
+#endif /* CONFIG_VFIO_DEBUGFS */
+
 #endif
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index eacd6ec04de5..b2854d7939ce 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -1436,7 +1436,7 @@ static int vfio_iommu_map(struct vfio_iommu *iommu, dma_addr_t iova,
 	list_for_each_entry(d, &iommu->domain_list, next) {
 		ret = iommu_map(d->domain, iova, (phys_addr_t)pfn << PAGE_SHIFT,
 				npage << PAGE_SHIFT, prot | IOMMU_CACHE,
-				GFP_KERNEL);
+				GFP_KERNEL_ACCOUNT);
 		if (ret)
 			goto unwind;
 
@@ -1750,7 +1750,8 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
 			}
 
 			ret = iommu_map(domain->domain, iova, phys, size,
-					dma->prot | IOMMU_CACHE, GFP_KERNEL);
+					dma->prot | IOMMU_CACHE,
+					GFP_KERNEL_ACCOUNT);
 			if (ret) {
 				if (!dma->iommu_mapped) {
 					vfio_unpin_pages_remote(dma, iova,
@@ -1845,7 +1846,8 @@ static void vfio_test_domain_fgsp(struct vfio_domain *domain, struct list_head *
 			continue;
 
 		ret = iommu_map(domain->domain, start, page_to_phys(pages), PAGE_SIZE * 2,
-				IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE, GFP_KERNEL);
+				IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE,
+				GFP_KERNEL_ACCOUNT);
 		if (!ret) {
 			size_t unmapped = iommu_unmap(domain->domain, start, PAGE_SIZE);
 
diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
index 8d4995ada74a..1cc93aac99a2 100644
--- a/drivers/vfio/vfio_main.c
+++ b/drivers/vfio/vfio_main.c
@@ -311,6 +311,7 @@ static int __vfio_register_dev(struct vfio_device *device,
 	refcount_set(&device->refcount, 1);
 
 	vfio_device_group_register(device);
+	vfio_device_debugfs_init(device);
 
 	return 0;
 err_out:
@@ -378,6 +379,7 @@ void vfio_unregister_group_dev(struct vfio_device *device)
 		}
 	}
 
+	vfio_device_debugfs_exit(device);
 	/* Balances vfio_device_set_group in register path */
 	vfio_device_remove_group(device);
 }
@@ -1676,6 +1678,7 @@ static int __init vfio_init(void)
 	if (ret)
 		goto err_alloc_dev_chrdev;
 
+	vfio_debugfs_create_root();
 	pr_info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
 	return 0;
 
@@ -1691,6 +1694,7 @@ err_virqfd:
 
 static void __exit vfio_cleanup(void)
 {
+	vfio_debugfs_remove_root();
 	ida_destroy(&vfio.device_ida);
 	vfio_cdev_cleanup();
 	class_destroy(vfio.device_class);
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 173beda74b38..bc4a51e4638b 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -59,6 +59,7 @@ struct vhost_vdpa {
 	int in_batch;
 	struct vdpa_iova_range range;
 	u32 batch_asid;
+	bool suspended;
 };
 
 static DEFINE_IDA(vhost_vdpa_ida);
@@ -232,6 +233,8 @@ static int _compat_vdpa_reset(struct vhost_vdpa *v)
 	struct vdpa_device *vdpa = v->vdpa;
 	u32 flags = 0;
 
+	v->suspended = false;
+
 	if (v->vdev.vqs) {
 		flags |= !vhost_backend_has_feature(v->vdev.vqs[0],
 						    VHOST_BACKEND_F_IOTLB_PERSIST) ?
@@ -590,11 +593,16 @@ static long vhost_vdpa_suspend(struct vhost_vdpa *v)
 {
 	struct vdpa_device *vdpa = v->vdpa;
 	const struct vdpa_config_ops *ops = vdpa->config;
+	int ret;
 
 	if (!ops->suspend)
 		return -EOPNOTSUPP;
 
-	return ops->suspend(vdpa);
+	ret = ops->suspend(vdpa);
+	if (!ret)
+		v->suspended = true;
+
+	return ret;
 }
 
 /* After a successful return of this ioctl the device resumes processing
@@ -605,11 +613,16 @@ static long vhost_vdpa_resume(struct vhost_vdpa *v)
 {
 	struct vdpa_device *vdpa = v->vdpa;
 	const struct vdpa_config_ops *ops = vdpa->config;
+	int ret;
 
 	if (!ops->resume)
 		return -EOPNOTSUPP;
 
-	return ops->resume(vdpa);
+	ret = ops->resume(vdpa);
+	if (!ret)
+		v->suspended = false;
+
+	return ret;
 }
 
 static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
@@ -690,6 +703,9 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
 
 	switch (cmd) {
 	case VHOST_SET_VRING_ADDR:
+		if ((ops->get_status(vdpa) & VIRTIO_CONFIG_S_DRIVER_OK) && !v->suspended)
+			return -EINVAL;
+
 		if (ops->set_vq_address(vdpa, idx,
 					(u64)(uintptr_t)vq->desc,
 					(u64)(uintptr_t)vq->avail,
@@ -698,6 +714,9 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
 		break;
 
 	case VHOST_SET_VRING_BASE:
+		if ((ops->get_status(vdpa) & VIRTIO_CONFIG_S_DRIVER_OK) && !v->suspended)
+			return -EINVAL;
+
 		if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) {
 			vq_state.packed.last_avail_idx = vq->last_avail_idx & 0x7fff;
 			vq_state.packed.last_avail_counter = !!(vq->last_avail_idx & 0x8000);
@@ -968,7 +987,8 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,
 			r = ops->set_map(vdpa, asid, iotlb);
 	} else {
 		r = iommu_map(v->domain, iova, pa, size,
-			      perm_to_iommu_flags(perm), GFP_KERNEL);
+			      perm_to_iommu_flags(perm),
+			      GFP_KERNEL_ACCOUNT);
 	}
 	if (r) {
 		vhost_iotlb_del_range(iotlb, iova, iova + size - 1);
diff --git a/drivers/video/backlight/Kconfig b/drivers/video/backlight/Kconfig
index 94d092091b5e..ea2d0d69bd8c 100644
--- a/drivers/video/backlight/Kconfig
+++ b/drivers/video/backlight/Kconfig
@@ -395,6 +395,17 @@ config BACKLIGHT_LP8788
 	help
 	  This supports TI LP8788 backlight driver.
 
+config BACKLIGHT_MP3309C
+	tristate "Backlight Driver for MPS MP3309C"
+	depends on I2C && PWM
+	select REGMAP_I2C
+	help
+	  This supports MPS MP3309C backlight WLED driver in both PWM and
+	  analog/I2C dimming modes.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called mp3309c.
+
 config BACKLIGHT_PANDORA
 	tristate "Backlight driver for Pandora console"
 	depends on TWL4030_CORE
diff --git a/drivers/video/backlight/Makefile b/drivers/video/backlight/Makefile
index 67d3ff39be3c..06966cb20459 100644
--- a/drivers/video/backlight/Makefile
+++ b/drivers/video/backlight/Makefile
@@ -43,6 +43,7 @@ obj-$(CONFIG_BACKLIGHT_LP855X)		+= lp855x_bl.o
 obj-$(CONFIG_BACKLIGHT_LP8788)		+= lp8788_bl.o
 obj-$(CONFIG_BACKLIGHT_LV5207LP)	+= lv5207lp.o
 obj-$(CONFIG_BACKLIGHT_MAX8925)		+= max8925_bl.o
+obj-$(CONFIG_BACKLIGHT_MP3309C)		+= mp3309c.o
 obj-$(CONFIG_BACKLIGHT_MT6370)		+= mt6370-backlight.o
 obj-$(CONFIG_BACKLIGHT_OMAP1)		+= omap1_bl.o
 obj-$(CONFIG_BACKLIGHT_PANDORA)		+= pandora_bl.o
diff --git a/drivers/video/backlight/hx8357.c b/drivers/video/backlight/hx8357.c
index f76d2469d490..d7298376cf74 100644
--- a/drivers/video/backlight/hx8357.c
+++ b/drivers/video/backlight/hx8357.c
@@ -6,11 +6,11 @@
  */
 
 #include <linux/delay.h>
+#include <linux/gpio/consumer.h>
 #include <linux/lcd.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-#include <linux/of_gpio.h>
 #include <linux/spi/spi.h>
 
 #define HX8357_NUM_IM_PINS	3
@@ -83,11 +83,10 @@
 #define HX8369_SET_GAMMA_CURVE_RELATED		0xe0
 
 struct hx8357_data {
-	unsigned		im_pins[HX8357_NUM_IM_PINS];
-	unsigned		reset;
+	struct gpio_descs	*im_pins;
+	struct gpio_desc	*reset;
 	struct spi_device	*spi;
 	int			state;
-	bool			use_im_pins;
 };
 
 static u8 hx8357_seq_power[] = {
@@ -321,11 +320,11 @@ static void hx8357_lcd_reset(struct lcd_device *lcdev)
 	struct hx8357_data *lcd = lcd_get_data(lcdev);
 
 	/* Reset the screen */
-	gpio_set_value(lcd->reset, 1);
+	gpiod_set_value(lcd->reset, 0);
 	usleep_range(10000, 12000);
-	gpio_set_value(lcd->reset, 0);
+	gpiod_set_value(lcd->reset, 1);
 	usleep_range(10000, 12000);
-	gpio_set_value(lcd->reset, 1);
+	gpiod_set_value(lcd->reset, 0);
 
 	/* The controller needs 120ms to recover from reset */
 	msleep(120);
@@ -340,10 +339,10 @@ static int hx8357_lcd_init(struct lcd_device *lcdev)
 	 * Set the interface selection pins to SPI mode, with three
 	 * wires
 	 */
-	if (lcd->use_im_pins) {
-		gpio_set_value_cansleep(lcd->im_pins[0], 1);
-		gpio_set_value_cansleep(lcd->im_pins[1], 0);
-		gpio_set_value_cansleep(lcd->im_pins[2], 1);
+	if (lcd->im_pins) {
+		gpiod_set_value_cansleep(lcd->im_pins->desc[0], 1);
+		gpiod_set_value_cansleep(lcd->im_pins->desc[1], 0);
+		gpiod_set_value_cansleep(lcd->im_pins->desc[2], 1);
 	}
 
 	ret = hx8357_spi_write_array(lcdev, hx8357_seq_power,
@@ -580,6 +579,7 @@ MODULE_DEVICE_TABLE(of, hx8357_dt_ids);
 
 static int hx8357_probe(struct spi_device *spi)
 {
+	struct device *dev = &spi->dev;
 	struct lcd_device *lcdev;
 	struct hx8357_data *lcd;
 	const struct of_device_id *match;
@@ -601,49 +601,19 @@ static int hx8357_probe(struct spi_device *spi)
 	if (!match || !match->data)
 		return -EINVAL;
 
-	lcd->reset = of_get_named_gpio(spi->dev.of_node, "gpios-reset", 0);
-	if (!gpio_is_valid(lcd->reset)) {
-		dev_err(&spi->dev, "Missing dt property: gpios-reset\n");
-		return -EINVAL;
-	}
+	lcd->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(lcd->reset))
+		return dev_err_probe(dev, PTR_ERR(lcd->reset), "failed to request reset GPIO\n");
+	gpiod_set_consumer_name(lcd->reset, "hx8357-reset");
 
-	ret = devm_gpio_request_one(&spi->dev, lcd->reset,
-				    GPIOF_OUT_INIT_HIGH,
-				    "hx8357-reset");
-	if (ret) {
-		dev_err(&spi->dev,
-			"failed to request gpio %d: %d\n",
-			lcd->reset, ret);
-		return -EINVAL;
-	}
+	lcd->im_pins = devm_gpiod_get_array_optional(dev, "im", GPIOD_OUT_LOW);
+	if (IS_ERR(lcd->im_pins))
+		return dev_err_probe(dev, PTR_ERR(lcd->im_pins), "failed to request im GPIOs\n");
+	if (lcd->im_pins->ndescs < HX8357_NUM_IM_PINS)
+		return dev_err_probe(dev, -EINVAL, "not enough im GPIOs\n");
 
-	if (of_property_present(spi->dev.of_node, "im-gpios")) {
-		lcd->use_im_pins = 1;
-
-		for (i = 0; i < HX8357_NUM_IM_PINS; i++) {
-			lcd->im_pins[i] = of_get_named_gpio(spi->dev.of_node,
-							    "im-gpios", i);
-			if (lcd->im_pins[i] == -EPROBE_DEFER) {
-				dev_info(&spi->dev, "GPIO requested is not here yet, deferring the probe\n");
-				return -EPROBE_DEFER;
-			}
-			if (!gpio_is_valid(lcd->im_pins[i])) {
-				dev_err(&spi->dev, "Missing dt property: im-gpios\n");
-				return -EINVAL;
-			}
-
-			ret = devm_gpio_request_one(&spi->dev, lcd->im_pins[i],
-						    GPIOF_OUT_INIT_LOW,
-						    "im_pins");
-			if (ret) {
-				dev_err(&spi->dev, "failed to request gpio %d: %d\n",
-					lcd->im_pins[i], ret);
-				return -EINVAL;
-			}
-		}
-	} else {
-		lcd->use_im_pins = 0;
-	}
+	for (i = 0; i < HX8357_NUM_IM_PINS; i++)
+		gpiod_set_consumer_name(lcd->im_pins->desc[i], "im_pins");
 
 	lcdev = devm_lcd_device_register(&spi->dev, "mxsfb", &spi->dev, lcd,
 					&hx8357_ops);
diff --git a/drivers/video/backlight/ili922x.c b/drivers/video/backlight/ili922x.c
index e7b6bd827986..c8e0e655dc86 100644
--- a/drivers/video/backlight/ili922x.c
+++ b/drivers/video/backlight/ili922x.c
@@ -81,7 +81,7 @@
 #define START_RW_WRITE		0
 #define START_RW_READ		1
 
-/**
+/*
  * START_BYTE(id, rs, rw)
  *
  * Set the start byte according to the required operation.
@@ -100,7 +100,7 @@
 #define START_BYTE(id, rs, rw)	\
 	(0x70 | (((id) & 0x01) << 2) | (((rs) & 0x01) << 1) | ((rw) & 0x01))
 
-/**
+/*
  * CHECK_FREQ_REG(spi_device s, spi_transfer x) - Check the frequency
  *	for the SPI transfer. According to the datasheet, the controller
  *	accept higher frequency for the GRAM transfer, but it requires
@@ -269,6 +269,10 @@ static int ili922x_write(struct spi_device *spi, u8 reg, u16 value)
 	spi_message_add_tail(&xfer_regindex, &msg);
 
 	ret = spi_sync(spi, &msg);
+	if (ret < 0) {
+		dev_err(&spi->dev, "Error sending SPI message 0x%x", ret);
+		return ret;
+	}
 
 	spi_message_init(&msg);
 	tbuf[0] = set_tx_byte(START_BYTE(ili922x_id, START_RS_REG,
diff --git a/drivers/video/backlight/mp3309c.c b/drivers/video/backlight/mp3309c.c
new file mode 100644
index 000000000000..34d71259fac1
--- /dev/null
+++ b/drivers/video/backlight/mp3309c.c
@@ -0,0 +1,444 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Driver for MPS MP3309C White LED driver with I2C interface
+ *
+ * This driver support both analog (by I2C commands) and PWM dimming control
+ * modes.
+ *
+ * Copyright (C) 2023 ASEM Srl
+ * Author: Flavio Suligoi <f.suligoi@asem.it>
+ *
+ * Based on pwm_bl.c
+ */
+
+#include <linux/backlight.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/pwm.h>
+#include <linux/regmap.h>
+
+#define REG_I2C_0	0x00
+#define REG_I2C_1	0x01
+
+#define REG_I2C_0_EN	0x80
+#define REG_I2C_0_D0	0x40
+#define REG_I2C_0_D1	0x20
+#define REG_I2C_0_D2	0x10
+#define REG_I2C_0_D3	0x08
+#define REG_I2C_0_D4	0x04
+#define REG_I2C_0_RSRV1	0x02
+#define REG_I2C_0_RSRV2	0x01
+
+#define REG_I2C_1_RSRV1	0x80
+#define REG_I2C_1_DIMS	0x40
+#define REG_I2C_1_SYNC	0x20
+#define REG_I2C_1_OVP0	0x10
+#define REG_I2C_1_OVP1	0x08
+#define REG_I2C_1_VOS	0x04
+#define REG_I2C_1_LEDO	0x02
+#define REG_I2C_1_OTP	0x01
+
+#define ANALOG_I2C_NUM_LEVELS	32		/* 0..31 */
+#define ANALOG_I2C_REG_MASK	0x7c
+
+#define MP3309C_PWM_DEFAULT_NUM_LEVELS	256	/* 0..255 */
+
+enum mp3309c_status_value {
+	FIRST_POWER_ON,
+	BACKLIGHT_OFF,
+	BACKLIGHT_ON,
+};
+
+enum mp3309c_dimming_mode_value {
+	DIMMING_PWM,
+	DIMMING_ANALOG_I2C,
+};
+
+struct mp3309c_platform_data {
+	unsigned int max_brightness;
+	unsigned int default_brightness;
+	unsigned int *levels;
+	u8  dimming_mode;
+	u8  over_voltage_protection;
+	bool sync_mode;
+	u8 status;
+};
+
+struct mp3309c_chip {
+	struct device *dev;
+	struct mp3309c_platform_data *pdata;
+	struct backlight_device *bl;
+	struct gpio_desc *enable_gpio;
+	struct regmap *regmap;
+	struct pwm_device *pwmd;
+};
+
+static const struct regmap_config mp3309c_regmap = {
+	.name = "mp3309c_regmap",
+	.reg_bits = 8,
+	.reg_stride = 1,
+	.val_bits = 8,
+	.max_register = REG_I2C_1,
+};
+
+static int mp3309c_enable_device(struct mp3309c_chip *chip)
+{
+	u8 reg_val;
+	int ret;
+
+	/* I2C register #0 - Device enable */
+	ret = regmap_update_bits(chip->regmap, REG_I2C_0, REG_I2C_0_EN,
+				 REG_I2C_0_EN);
+	if (ret)
+		return ret;
+
+	/*
+	 * I2C register #1 - Set working mode:
+	 *  - set one of the two dimming mode:
+	 *    - PWM dimming using an external PWM dimming signal
+	 *    - analog dimming using I2C commands
+	 *  - enable/disable synchronous mode
+	 *  - set overvoltage protection (OVP)
+	 */
+	reg_val = 0x00;
+	if (chip->pdata->dimming_mode == DIMMING_PWM)
+		reg_val |= REG_I2C_1_DIMS;
+	if (chip->pdata->sync_mode)
+		reg_val |= REG_I2C_1_SYNC;
+	reg_val |= chip->pdata->over_voltage_protection;
+	ret = regmap_write(chip->regmap, REG_I2C_1, reg_val);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int mp3309c_bl_update_status(struct backlight_device *bl)
+{
+	struct mp3309c_chip *chip = bl_get_data(bl);
+	int brightness = backlight_get_brightness(bl);
+	struct pwm_state pwmstate;
+	unsigned int analog_val, bits_val;
+	int i, ret;
+
+	if (chip->pdata->dimming_mode == DIMMING_PWM) {
+		/*
+		 * PWM control mode
+		 */
+		pwm_get_state(chip->pwmd, &pwmstate);
+		pwm_set_relative_duty_cycle(&pwmstate,
+					    chip->pdata->levels[brightness],
+					    chip->pdata->levels[chip->pdata->max_brightness]);
+		pwmstate.enabled = true;
+		ret = pwm_apply_state(chip->pwmd, &pwmstate);
+		if (ret)
+			return ret;
+
+		switch (chip->pdata->status) {
+		case FIRST_POWER_ON:
+		case BACKLIGHT_OFF:
+			/*
+			 * After 20ms of low pwm signal level, the chip turns
+			 * off automatically. In this case, before enabling the
+			 * chip again, we must wait about 10ms for pwm signal to
+			 * stabilize.
+			 */
+			if (brightness > 0) {
+				msleep(10);
+				mp3309c_enable_device(chip);
+				chip->pdata->status = BACKLIGHT_ON;
+			} else {
+				chip->pdata->status = BACKLIGHT_OFF;
+			}
+			break;
+		case BACKLIGHT_ON:
+			if (brightness == 0)
+				chip->pdata->status = BACKLIGHT_OFF;
+			break;
+		}
+	} else {
+		/*
+		 * Analog (by I2C command) control mode
+		 *
+		 * The first time, before setting brightness, we must enable the
+		 * device
+		 */
+		if (chip->pdata->status == FIRST_POWER_ON)
+			mp3309c_enable_device(chip);
+
+		/*
+		 * Dimming mode I2C command (fixed dimming range 0..31)
+		 *
+		 * The 5 bits of the dimming analog value D4..D0 is allocated
+		 * in the I2C register #0, in the following way:
+		 *
+		 *     +--+--+--+--+--+--+--+--+
+		 *     |EN|D0|D1|D2|D3|D4|XX|XX|
+		 *     +--+--+--+--+--+--+--+--+
+		 */
+		analog_val = brightness;
+		bits_val = 0;
+		for (i = 0; i <= 5; i++)
+			bits_val += ((analog_val >> i) & 0x01) << (6 - i);
+		ret = regmap_update_bits(chip->regmap, REG_I2C_0,
+					 ANALOG_I2C_REG_MASK, bits_val);
+		if (ret)
+			return ret;
+
+		if (brightness > 0)
+			chip->pdata->status = BACKLIGHT_ON;
+		else
+			chip->pdata->status = BACKLIGHT_OFF;
+	}
+
+	return 0;
+}
+
+static const struct backlight_ops mp3309c_bl_ops = {
+	.update_status = mp3309c_bl_update_status,
+};
+
+static int pm3309c_parse_dt_node(struct mp3309c_chip *chip,
+				 struct mp3309c_platform_data *pdata)
+{
+	struct device_node *node = chip->dev->of_node;
+	struct property *prop_pwms;
+	struct property *prop_levels = NULL;
+	int length = 0;
+	int ret, i;
+	unsigned int num_levels, tmp_value;
+
+	if (!node) {
+		dev_err(chip->dev, "failed to get DT node\n");
+		return -ENODEV;
+	}
+
+	/*
+	 * Dimming mode: the MP3309C provides two dimming control mode:
+	 *
+	 * - PWM mode
+	 * - Analog by I2C control mode (default)
+	 *
+	 * I2C control mode is assumed as default but, if the pwms property is
+	 * found in the backlight node, the mode switches to PWM mode.
+	 */
+	pdata->dimming_mode = DIMMING_ANALOG_I2C;
+	prop_pwms = of_find_property(node, "pwms", &length);
+	if (prop_pwms) {
+		chip->pwmd = devm_pwm_get(chip->dev, NULL);
+		if (IS_ERR(chip->pwmd))
+			return dev_err_probe(chip->dev, PTR_ERR(chip->pwmd),
+					     "error getting pwm data\n");
+		pdata->dimming_mode = DIMMING_PWM;
+		pwm_apply_args(chip->pwmd);
+	}
+
+	/*
+	 * In I2C control mode the dimming levels (0..31) are fixed by the
+	 * hardware, while in PWM control mode they can be chosen by the user,
+	 * to allow nonlinear mappings.
+	 */
+	if  (pdata->dimming_mode == DIMMING_ANALOG_I2C) {
+		/*
+		 * Analog (by I2C commands) control mode: fixed 0..31 brightness
+		 * levels
+		 */
+		num_levels = ANALOG_I2C_NUM_LEVELS;
+
+		/* Enable GPIO used in I2C dimming mode only */
+		chip->enable_gpio = devm_gpiod_get(chip->dev, "enable",
+						   GPIOD_OUT_HIGH);
+		if (IS_ERR(chip->enable_gpio))
+			return dev_err_probe(chip->dev,
+					     PTR_ERR(chip->enable_gpio),
+					     "error getting enable gpio\n");
+	} else {
+		/*
+		 * PWM control mode: check for brightness level in DT
+		 */
+		prop_levels = of_find_property(node, "brightness-levels",
+					       &length);
+		if (prop_levels) {
+			/* Read brightness levels from DT */
+			num_levels = length / sizeof(u32);
+			if (num_levels < 2)
+				return -EINVAL;
+		} else {
+			/* Use default brightness levels */
+			num_levels = MP3309C_PWM_DEFAULT_NUM_LEVELS;
+		}
+	}
+
+	/* Fill brightness levels array */
+	pdata->levels = devm_kcalloc(chip->dev, num_levels,
+				     sizeof(*pdata->levels), GFP_KERNEL);
+	if (!pdata->levels)
+		return -ENOMEM;
+	if (prop_levels) {
+		ret = of_property_read_u32_array(node, "brightness-levels",
+						 pdata->levels,
+						 num_levels);
+		if (ret < 0)
+			return ret;
+	} else {
+		for (i = 0; i < num_levels; i++)
+			pdata->levels[i] = i;
+	}
+
+	pdata->max_brightness = num_levels - 1;
+
+	ret = of_property_read_u32(node, "default-brightness",
+				   &pdata->default_brightness);
+	if (ret)
+		pdata->default_brightness = pdata->max_brightness;
+	if (pdata->default_brightness > pdata->max_brightness) {
+		dev_err(chip->dev,
+			"default brightness exceeds max brightness\n");
+		pdata->default_brightness = pdata->max_brightness;
+	}
+
+	/*
+	 * Over-voltage protection (OVP)
+	 *
+	 * This (optional) property values are:
+	 *
+	 *  - 13.5V
+	 *  - 24V
+	 *  - 35.5V (hardware default setting)
+	 *
+	 * If missing, the default value for OVP is 35.5V
+	 */
+	pdata->over_voltage_protection = REG_I2C_1_OVP1;
+	if (!of_property_read_u32(node, "mps,overvoltage-protection-microvolt",
+				  &tmp_value)) {
+		switch (tmp_value) {
+		case 13500000:
+			pdata->over_voltage_protection = 0x00;
+			break;
+		case 24000000:
+			pdata->over_voltage_protection = REG_I2C_1_OVP0;
+			break;
+		case 35500000:
+			pdata->over_voltage_protection = REG_I2C_1_OVP1;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	/* Synchronous (default) and non-synchronous mode */
+	pdata->sync_mode = true;
+	if (of_property_read_bool(node, "mps,no-sync-mode"))
+		pdata->sync_mode = false;
+
+	return 0;
+}
+
+static int mp3309c_probe(struct i2c_client *client)
+{
+	struct mp3309c_platform_data *pdata = dev_get_platdata(&client->dev);
+	struct mp3309c_chip *chip;
+	struct backlight_properties props;
+	struct pwm_state pwmstate;
+	int ret;
+
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
+		dev_err(&client->dev, "failed to check i2c functionality\n");
+		return -EOPNOTSUPP;
+	}
+
+	chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	chip->dev = &client->dev;
+
+	chip->regmap = devm_regmap_init_i2c(client, &mp3309c_regmap);
+	if (IS_ERR(chip->regmap))
+		return dev_err_probe(&client->dev, PTR_ERR(chip->regmap),
+				     "failed to allocate register map\n");
+
+	i2c_set_clientdata(client, chip);
+
+	if (!pdata) {
+		pdata = devm_kzalloc(chip->dev, sizeof(*pdata), GFP_KERNEL);
+		if (!pdata)
+			return -ENOMEM;
+
+		ret = pm3309c_parse_dt_node(chip, pdata);
+		if (ret)
+			return ret;
+	}
+	chip->pdata = pdata;
+
+	/* Backlight properties */
+	props.brightness = pdata->default_brightness;
+	props.max_brightness = pdata->max_brightness;
+	props.scale = BACKLIGHT_SCALE_LINEAR;
+	props.type = BACKLIGHT_RAW;
+	props.power = FB_BLANK_UNBLANK;
+	props.fb_blank = FB_BLANK_UNBLANK;
+	chip->bl = devm_backlight_device_register(chip->dev, "mp3309c",
+						  chip->dev, chip,
+						  &mp3309c_bl_ops, &props);
+	if (IS_ERR(chip->bl))
+		return dev_err_probe(chip->dev, PTR_ERR(chip->bl),
+				     "error registering backlight device\n");
+
+	/* In PWM dimming mode, enable pwm device */
+	if (chip->pdata->dimming_mode == DIMMING_PWM) {
+		pwm_init_state(chip->pwmd, &pwmstate);
+		pwm_set_relative_duty_cycle(&pwmstate,
+					    chip->pdata->default_brightness,
+					    chip->pdata->max_brightness);
+		pwmstate.enabled = true;
+		ret = pwm_apply_state(chip->pwmd, &pwmstate);
+		if (ret)
+			return dev_err_probe(chip->dev, ret,
+					     "error setting pwm device\n");
+	}
+
+	chip->pdata->status = FIRST_POWER_ON;
+	backlight_update_status(chip->bl);
+
+	return 0;
+}
+
+static void mp3309c_remove(struct i2c_client *client)
+{
+	struct mp3309c_chip *chip = i2c_get_clientdata(client);
+	struct backlight_device *bl = chip->bl;
+
+	bl->props.power = FB_BLANK_POWERDOWN;
+	bl->props.brightness = 0;
+	backlight_update_status(chip->bl);
+}
+
+static const struct of_device_id mp3309c_match_table[] = {
+	{ .compatible = "mps,mp3309c", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, mp3309c_match_table);
+
+static const struct i2c_device_id mp3309c_id[] = {
+	{ "mp3309c", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, mp3309c_id);
+
+static struct i2c_driver mp3309c_i2c_driver = {
+	.driver	= {
+			.name		= KBUILD_MODNAME,
+			.of_match_table	= mp3309c_match_table,
+	},
+	.probe		= mp3309c_probe,
+	.remove		= mp3309c_remove,
+	.id_table	= mp3309c_id,
+};
+
+module_i2c_driver(mp3309c_i2c_driver);
+
+MODULE_DESCRIPTION("Backlight Driver for MPS MP3309C");
+MODULE_AUTHOR("Flavio Suligoi <f.suligoi@asem.it>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c
index 35c716e9043c..ffcebf6aa76a 100644
--- a/drivers/video/backlight/pwm_bl.c
+++ b/drivers/video/backlight/pwm_bl.c
@@ -461,10 +461,9 @@ static int pwm_backlight_probe(struct platform_device *pdev)
 
 	if (!data) {
 		ret = pwm_backlight_parse_dt(&pdev->dev, &defdata);
-		if (ret < 0) {
-			dev_err(&pdev->dev, "failed to find platform data\n");
-			return ret;
-		}
+		if (ret < 0)
+			return dev_err_probe(&pdev->dev, ret,
+					     "failed to find platform data\n");
 
 		data = &defdata;
 	}
@@ -493,24 +492,27 @@ static int pwm_backlight_probe(struct platform_device *pdev)
 	pb->enable_gpio = devm_gpiod_get_optional(&pdev->dev, "enable",
 						  GPIOD_ASIS);
 	if (IS_ERR(pb->enable_gpio)) {
-		ret = PTR_ERR(pb->enable_gpio);
+		ret = dev_err_probe(&pdev->dev, PTR_ERR(pb->enable_gpio),
+				    "failed to acquire enable GPIO\n");
 		goto err_alloc;
 	}
 
 	pb->power_supply = devm_regulator_get_optional(&pdev->dev, "power");
 	if (IS_ERR(pb->power_supply)) {
 		ret = PTR_ERR(pb->power_supply);
-		if (ret == -ENODEV)
+		if (ret == -ENODEV) {
 			pb->power_supply = NULL;
-		else
+		} else {
+			dev_err_probe(&pdev->dev, ret,
+				      "failed to acquire power regulator\n");
 			goto err_alloc;
+		}
 	}
 
 	pb->pwm = devm_pwm_get(&pdev->dev, NULL);
 	if (IS_ERR(pb->pwm)) {
-		ret = PTR_ERR(pb->pwm);
-		if (ret != -EPROBE_DEFER)
-			dev_err(&pdev->dev, "unable to request PWM\n");
+		ret = dev_err_probe(&pdev->dev, PTR_ERR(pb->pwm),
+				    "unable to request PWM\n");
 		goto err_alloc;
 	}
 
@@ -530,8 +532,8 @@ static int pwm_backlight_probe(struct platform_device *pdev)
 
 	ret = pwm_apply_might_sleep(pb->pwm, &state);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to apply initial PWM state: %d\n",
-			ret);
+		dev_err_probe(&pdev->dev, ret,
+			      "failed to apply initial PWM state");
 		goto err_alloc;
 	}
 
@@ -568,8 +570,8 @@ static int pwm_backlight_probe(struct platform_device *pdev)
 		ret = pwm_backlight_brightness_default(&pdev->dev, data,
 						       state.period);
 		if (ret < 0) {
-			dev_err(&pdev->dev,
-				"failed to setup default brightness table\n");
+			dev_err_probe(&pdev->dev, ret,
+				      "failed to setup default brightness table\n");
 			goto err_alloc;
 		}
 
@@ -597,8 +599,8 @@ static int pwm_backlight_probe(struct platform_device *pdev)
 	bl = backlight_device_register(dev_name(&pdev->dev), &pdev->dev, pb,
 				       &pwm_backlight_ops, &props);
 	if (IS_ERR(bl)) {
-		dev_err(&pdev->dev, "failed to register backlight\n");
-		ret = PTR_ERR(bl);
+		ret = dev_err_probe(&pdev->dev, PTR_ERR(bl),
+				    "failed to register backlight\n");
 		goto err_alloc;
 	}
 
diff --git a/drivers/video/console/Kconfig b/drivers/video/console/Kconfig
index 83c2d7329ca5..bc31db6ef7d2 100644
--- a/drivers/video/console/Kconfig
+++ b/drivers/video/console/Kconfig
@@ -7,7 +7,7 @@ menu "Console display driver support"
 
 config VGA_CONSOLE
 	bool "VGA text console" if EXPERT || !X86
-	depends on ALPHA || IA64 || X86 || \
+	depends on ALPHA || X86 || \
 		(ARM && ARCH_FOOTBRIDGE) || \
 		(MIPS && (MIPS_MALTA || SIBYTE_BCM112X || SIBYTE_SB1250 || SIBYTE_BCM1x80 || SNI_RM))
 	select APERTURE_HELPERS if (DRM || FB || VFIO_PCI_CORE)
diff --git a/drivers/video/fbdev/core/fb_ddc.c b/drivers/video/fbdev/core/fb_ddc.c
index 8bf5f2f54be7..e25143219862 100644
--- a/drivers/video/fbdev/core/fb_ddc.c
+++ b/drivers/video/fbdev/core/fb_ddc.c
@@ -116,7 +116,6 @@ unsigned char *fb_ddc_read(struct i2c_adapter *adapter)
 	algo_data->setsda(algo_data->data, 1);
 	algo_data->setscl(algo_data->data, 1);
 
-	adapter->class |= I2C_CLASS_DDC;
 	return edid;
 }
 
diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index 63af6ab034b5..46823c2e2ba1 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -631,8 +631,7 @@ static void fbcon_prepare_logo(struct vc_data *vc, struct fb_info *info,
 
 	if (logo_lines > vc->vc_bottom) {
 		logo_shown = FBCON_LOGO_CANSHOW;
-		printk(KERN_INFO
-		       "fbcon_init: disable boot-logo (boot-logo bigger than screen).\n");
+		pr_info("fbcon: disable boot-logo (boot-logo bigger than screen).\n");
 	} else {
 		logo_shown = FBCON_LOGO_DRAW;
 		vc->vc_top = logo_lines;
@@ -2400,11 +2399,9 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount,
 	struct fbcon_ops *ops = info->fbcon_par;
 	struct fbcon_display *p = &fb_display[vc->vc_num];
 	int resize, ret, old_userfont, old_width, old_height, old_charcount;
-	char *old_data = NULL;
+	u8 *old_data = vc->vc_font.data;
 
 	resize = (w != vc->vc_font.width) || (h != vc->vc_font.height);
-	if (p->userfont)
-		old_data = vc->vc_font.data;
 	vc->vc_font.data = (void *)(p->fontdata = data);
 	old_userfont = p->userfont;
 	if ((p->userfont = userfont))
@@ -2438,13 +2435,13 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount,
 		update_screen(vc);
 	}
 
-	if (old_data && (--REFCOUNT(old_data) == 0))
+	if (old_userfont && (--REFCOUNT(old_data) == 0))
 		kfree(old_data - FONT_EXTRA_WORDS * sizeof(int));
 	return 0;
 
 err_out:
 	p->fontdata = old_data;
-	vc->vc_font.data = (void *)old_data;
+	vc->vc_font.data = old_data;
 
 	if (userfont) {
 		p->userfont = old_userfont;
diff --git a/drivers/video/fbdev/cyber2000fb.c b/drivers/video/fbdev/cyber2000fb.c
index abb87d3576db..986760b90465 100644
--- a/drivers/video/fbdev/cyber2000fb.c
+++ b/drivers/video/fbdev/cyber2000fb.c
@@ -1227,7 +1227,6 @@ static int cyber2000fb_setup_ddc_bus(struct cfb_info *cfb)
 	strscpy(cfb->ddc_adapter.name, cfb->fb.fix.id,
 		sizeof(cfb->ddc_adapter.name));
 	cfb->ddc_adapter.owner		= THIS_MODULE;
-	cfb->ddc_adapter.class		= I2C_CLASS_DDC;
 	cfb->ddc_adapter.algo_data	= &cfb->ddc_algo;
 	cfb->ddc_adapter.dev.parent	= cfb->fb.device;
 	cfb->ddc_algo.setsda		= cyber2000fb_ddc_setsda;
diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c
index c26ee6fd73c9..8fdccf033b2d 100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -1010,8 +1010,6 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
 			goto getmem_done;
 		}
 		pr_info("Unable to allocate enough contiguous physical memory on Gen 1 VM. Using MMIO instead.\n");
-	} else {
-		goto err1;
 	}
 
 	/*
diff --git a/drivers/video/fbdev/i740fb.c b/drivers/video/fbdev/i740fb.c
index 1897e65ab703..9b74dae71472 100644
--- a/drivers/video/fbdev/i740fb.c
+++ b/drivers/video/fbdev/i740fb.c
@@ -163,7 +163,6 @@ static int i740fb_setup_ddc_bus(struct fb_info *info)
 	strscpy(par->ddc_adapter.name, info->fix.id,
 		sizeof(par->ddc_adapter.name));
 	par->ddc_adapter.owner		= THIS_MODULE;
-	par->ddc_adapter.class		= I2C_CLASS_DDC;
 	par->ddc_adapter.algo_data	= &par->ddc_algo;
 	par->ddc_adapter.dev.parent	= info->device;
 	par->ddc_algo.setsda		= i740fb_ddc_setsda;
diff --git a/drivers/video/fbdev/matrox/i2c-matroxfb.c b/drivers/video/fbdev/matrox/i2c-matroxfb.c
index e2e4705e3fe0..bb048e14b2cf 100644
--- a/drivers/video/fbdev/matrox/i2c-matroxfb.c
+++ b/drivers/video/fbdev/matrox/i2c-matroxfb.c
@@ -100,8 +100,7 @@ static const struct i2c_algo_bit_data matrox_i2c_algo_template =
 };
 
 static int i2c_bus_reg(struct i2c_bit_adapter* b, struct matrox_fb_info* minfo, 
-		unsigned int data, unsigned int clock, const char *name,
-		int class)
+		unsigned int data, unsigned int clock, const char *name)
 {
 	int err;
 
@@ -112,7 +111,6 @@ static int i2c_bus_reg(struct i2c_bit_adapter* b, struct matrox_fb_info* minfo,
 	snprintf(b->adapter.name, sizeof(b->adapter.name), name,
 		minfo->fbcon.node);
 	i2c_set_adapdata(&b->adapter, b);
-	b->adapter.class = class;
 	b->adapter.algo_data = &b->bac;
 	b->adapter.dev.parent = &minfo->pcidev->dev;
 	b->bac = matrox_i2c_algo_template;
@@ -160,27 +158,24 @@ static void* i2c_matroxfb_probe(struct matrox_fb_info* minfo) {
 		case MGA_2164:
 			err = i2c_bus_reg(&m2info->ddc1, minfo,
 					  DDC1B_DATA, DDC1B_CLK,
-					  "DDC:fb%u #0", I2C_CLASS_DDC);
+					  "DDC:fb%u #0");
 			break;
 		default:
 			err = i2c_bus_reg(&m2info->ddc1, minfo,
 					  DDC1_DATA, DDC1_CLK,
-					  "DDC:fb%u #0", I2C_CLASS_DDC);
+					  "DDC:fb%u #0");
 			break;
 	}
 	if (err)
 		goto fail_ddc1;
 	if (minfo->devflags.dualhead) {
-		err = i2c_bus_reg(&m2info->ddc2, minfo,
-				  DDC2_DATA, DDC2_CLK,
-				  "DDC:fb%u #1", I2C_CLASS_DDC);
+		err = i2c_bus_reg(&m2info->ddc2, minfo, DDC2_DATA, DDC2_CLK, "DDC:fb%u #1");
 		if (err == -ENODEV) {
 			printk(KERN_INFO "i2c-matroxfb: VGA->TV plug detected, DDC unavailable.\n");
 		} else if (err)
 			printk(KERN_INFO "i2c-matroxfb: Could not register secondary output i2c bus. Continuing anyway.\n");
 		/* Register maven bus even on G450/G550 */
-		err = i2c_bus_reg(&m2info->maven, minfo,
-				  MAT_DATA, MAT_CLK, "MAVEN:fb%u", 0);
+		err = i2c_bus_reg(&m2info->maven, minfo, MAT_DATA, MAT_CLK, "MAVEN:fb%u");
 		if (err)
 			printk(KERN_INFO "i2c-matroxfb: Could not register Maven i2c bus. Continuing anyway.\n");
 		else {
diff --git a/drivers/video/fbdev/s3fb.c b/drivers/video/fbdev/s3fb.c
index 589b349cb63e..07722a5ea8ef 100644
--- a/drivers/video/fbdev/s3fb.c
+++ b/drivers/video/fbdev/s3fb.c
@@ -252,7 +252,6 @@ static int s3fb_setup_ddc_bus(struct fb_info *info)
 	strscpy(par->ddc_adapter.name, info->fix.id,
 		sizeof(par->ddc_adapter.name));
 	par->ddc_adapter.owner		= THIS_MODULE;
-	par->ddc_adapter.class		= I2C_CLASS_DDC;
 	par->ddc_adapter.algo_data	= &par->ddc_algo;
 	par->ddc_adapter.dev.parent	= info->device;
 	par->ddc_algo.setsda		= s3fb_ddc_setsda;
diff --git a/drivers/video/fbdev/savage/savagefb_driver.c b/drivers/video/fbdev/savage/savagefb_driver.c
index dddd6afcb972..ebc9aeffdde7 100644
--- a/drivers/video/fbdev/savage/savagefb_driver.c
+++ b/drivers/video/fbdev/savage/savagefb_driver.c
@@ -869,6 +869,9 @@ static int savagefb_check_var(struct fb_var_screeninfo   *var,
 
 	DBG("savagefb_check_var");
 
+	if (!var->pixclock)
+		return -EINVAL;
+
 	var->transp.offset = 0;
 	var->transp.length = 0;
 	switch (var->bits_per_pixel) {
diff --git a/drivers/video/fbdev/sis/sis_main.c b/drivers/video/fbdev/sis/sis_main.c
index 803ccb6aa479..009bf1d92644 100644
--- a/drivers/video/fbdev/sis/sis_main.c
+++ b/drivers/video/fbdev/sis/sis_main.c
@@ -1444,6 +1444,8 @@ sisfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 
 	vtotal = var->upper_margin + var->lower_margin + var->vsync_len;
 
+	if (!var->pixclock)
+		return -EINVAL;
 	pixclock = var->pixclock;
 
 	if((var->vmode & FB_VMODE_MASK) == FB_VMODE_NONINTERLACED) {
diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c
index 2de0e675fd15..8e5bac27542d 100644
--- a/drivers/video/fbdev/stifb.c
+++ b/drivers/video/fbdev/stifb.c
@@ -1158,7 +1158,7 @@ stifb_init_display(struct stifb_info *fb)
 	    }
 	    break;
 	}
-	stifb_blank(0, (struct fb_info *)fb);	/* 0=enable screen */
+	stifb_blank(0, fb->info);	/* 0=enable screen */
 
 	SETUP_FB(fb);
 }
diff --git a/drivers/video/fbdev/tdfxfb.c b/drivers/video/fbdev/tdfxfb.c
index 22aa953138b0..51ebe78359ec 100644
--- a/drivers/video/fbdev/tdfxfb.c
+++ b/drivers/video/fbdev/tdfxfb.c
@@ -1267,7 +1267,6 @@ static int tdfxfb_setup_ddc_bus(struct tdfxfb_i2c_chan *chan, const char *name,
 
 	strscpy(chan->adapter.name, name, sizeof(chan->adapter.name));
 	chan->adapter.owner		= THIS_MODULE;
-	chan->adapter.class		= I2C_CLASS_DDC;
 	chan->adapter.algo_data		= &chan->algo;
 	chan->adapter.dev.parent	= dev;
 	chan->algo.setsda		= tdfxfb_ddc_setsda;
diff --git a/drivers/video/fbdev/tridentfb.c b/drivers/video/fbdev/tridentfb.c
index 816d40b6f689..516cf2a18757 100644
--- a/drivers/video/fbdev/tridentfb.c
+++ b/drivers/video/fbdev/tridentfb.c
@@ -274,7 +274,6 @@ static int tridentfb_setup_ddc_bus(struct fb_info *info)
 	strscpy(par->ddc_adapter.name, info->fix.id,
 		sizeof(par->ddc_adapter.name));
 	par->ddc_adapter.owner		= THIS_MODULE;
-	par->ddc_adapter.class		= I2C_CLASS_DDC;
 	par->ddc_adapter.algo_data	= &par->ddc_algo;
 	par->ddc_adapter.dev.parent	= info->device;
 	if (is_oldclock(par->chip_id)) { /* not sure if this check is OK */
diff --git a/drivers/video/fbdev/via/via_i2c.c b/drivers/video/fbdev/via/via_i2c.c
index c35e530e0ec9..582502810575 100644
--- a/drivers/video/fbdev/via/via_i2c.c
+++ b/drivers/video/fbdev/via/via_i2c.c
@@ -201,7 +201,6 @@ static int create_i2c_bus(struct i2c_adapter *adapter,
 	sprintf(adapter->name, "viafb i2c io_port idx 0x%02x",
 		adap_cfg->ioport_index);
 	adapter->owner = THIS_MODULE;
-	adapter->class = I2C_CLASS_DDC;
 	adapter->algo_data = algo;
 	if (pdev)
 		adapter->dev.parent = &pdev->dev;
diff --git a/drivers/video/fbdev/vt8500lcdfb.c b/drivers/video/fbdev/vt8500lcdfb.c
index 42c25dc85197..ac73937073a7 100644
--- a/drivers/video/fbdev/vt8500lcdfb.c
+++ b/drivers/video/fbdev/vt8500lcdfb.c
@@ -374,7 +374,6 @@ static int vt8500lcd_probe(struct platform_device *pdev)
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
-		dev_err(&pdev->dev, "no IRQ defined\n");
 		ret = -ENODEV;
 		goto failed_free_palette;
 	}
diff --git a/drivers/virt/vboxguest/vboxguest_core.c b/drivers/virt/vboxguest/vboxguest_core.c
index dfd69bd77f53..c6e9855998ab 100644
--- a/drivers/virt/vboxguest/vboxguest_core.c
+++ b/drivers/virt/vboxguest/vboxguest_core.c
@@ -33,16 +33,15 @@
 	 VMMDEV_REQUESTOR_CON_DONT_KNOW | VMMDEV_REQUESTOR_TRUST_NOT_GIVEN)
 
 /**
- * Reserves memory in which the VMM can relocate any guest mappings
- * that are floating around.
+ * vbg_guest_mappings_init - Reserves memory in which the VMM can
+ *	relocate any guest mappings that are floating around.
+ * @gdev:		The Guest extension device.
  *
  * This operation is a little bit tricky since the VMM might not accept
  * just any address because of address clashes between the three contexts
  * it operates in, so we try several times.
  *
  * Failure to reserve the guest mappings is ignored.
- *
- * @gdev:		The Guest extension device.
  */
 static void vbg_guest_mappings_init(struct vbg_dev *gdev)
 {
@@ -125,7 +124,7 @@ out:
 }
 
 /**
- * Undo what vbg_guest_mappings_init did.
+ * vbg_guest_mappings_exit - Undo what vbg_guest_mappings_init did.
  *
  * @gdev:		The Guest extension device.
  */
@@ -166,9 +165,10 @@ static void vbg_guest_mappings_exit(struct vbg_dev *gdev)
 }
 
 /**
- * Report the guest information to the host.
- * Return: 0 or negative errno value.
+ * vbg_report_guest_info - Report the guest information to the host.
  * @gdev:		The Guest extension device.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_report_guest_info(struct vbg_dev *gdev)
 {
@@ -229,10 +229,11 @@ out_free:
 }
 
 /**
- * Report the guest driver status to the host.
- * Return: 0 or negative errno value.
+ * vbg_report_driver_status - Report the guest driver status to the host.
  * @gdev:		The Guest extension device.
  * @active:		Flag whether the driver is now active or not.
+ *
+ * Return: 0 or negative errno value.
  */
 static int vbg_report_driver_status(struct vbg_dev *gdev, bool active)
 {
@@ -261,10 +262,12 @@ static int vbg_report_driver_status(struct vbg_dev *gdev, bool active)
 }
 
 /**
- * Inflate the balloon by one chunk. The caller owns the balloon mutex.
- * Return: 0 or negative errno value.
+ * vbg_balloon_inflate - Inflate the balloon by one chunk. The caller
+ * owns the balloon mutex.
  * @gdev:		The Guest extension device.
  * @chunk_idx:		Index of the chunk.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_balloon_inflate(struct vbg_dev *gdev, u32 chunk_idx)
 {
@@ -312,10 +315,12 @@ out_error:
 }
 
 /**
- * Deflate the balloon by one chunk. The caller owns the balloon mutex.
- * Return: 0 or negative errno value.
+ * vbg_balloon_deflate - Deflate the balloon by one chunk. The caller
+ * owns the balloon mutex.
  * @gdev:		The Guest extension device.
  * @chunk_idx:		Index of the chunk.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_balloon_deflate(struct vbg_dev *gdev, u32 chunk_idx)
 {
@@ -344,7 +349,7 @@ static int vbg_balloon_deflate(struct vbg_dev *gdev, u32 chunk_idx)
 	return 0;
 }
 
-/**
+/*
  * Respond to VMMDEV_EVENT_BALLOON_CHANGE_REQUEST events, query the size
  * the host wants the balloon to be and adjust accordingly.
  */
@@ -409,7 +414,7 @@ static void vbg_balloon_work(struct work_struct *work)
 	}
 }
 
-/**
+/*
  * Callback for heartbeat timer.
  */
 static void vbg_heartbeat_timer(struct timer_list *t)
@@ -422,11 +427,12 @@ static void vbg_heartbeat_timer(struct timer_list *t)
 }
 
 /**
- * Configure the host to check guest's heartbeat
- * and get heartbeat interval from the host.
- * Return: 0 or negative errno value.
+ * vbg_heartbeat_host_config - Configure the host to check guest's heartbeat
+ *	and get heartbeat interval from the host.
  * @gdev:		The Guest extension device.
  * @enabled:		Set true to enable guest heartbeat checks on host.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_heartbeat_host_config(struct vbg_dev *gdev, bool enabled)
 {
@@ -449,9 +455,11 @@ static int vbg_heartbeat_host_config(struct vbg_dev *gdev, bool enabled)
 }
 
 /**
- * Initializes the heartbeat timer. This feature may be disabled by the host.
- * Return: 0 or negative errno value.
+ * vbg_heartbeat_init - Initializes the heartbeat timer. This feature
+ * may be disabled by the host.
  * @gdev:		The Guest extension device.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_heartbeat_init(struct vbg_dev *gdev)
 {
@@ -481,7 +489,8 @@ static int vbg_heartbeat_init(struct vbg_dev *gdev)
 }
 
 /**
- * Cleanup hearbeat code, stop HB timer and disable host heartbeat checking.
+ * vbg_heartbeat_exit - Cleanup heartbeat code, stop HB timer and disable
+ *	host heartbeat checking.
  * @gdev:		The Guest extension device.
  */
 static void vbg_heartbeat_exit(struct vbg_dev *gdev)
@@ -493,11 +502,12 @@ static void vbg_heartbeat_exit(struct vbg_dev *gdev)
 }
 
 /**
- * Applies a change to the bit usage tracker.
- * Return: true if the mask changed, false if not.
+ * vbg_track_bit_usage - Applies a change to the bit usage tracker.
  * @tracker:		The bit usage tracker.
  * @changed:		The bits to change.
  * @previous:		The previous value of the bits.
+ *
+ * Return: %true if the mask changed, %false if not.
  */
 static bool vbg_track_bit_usage(struct vbg_bit_usage_tracker *tracker,
 				u32 changed, u32 previous)
@@ -529,10 +539,12 @@ static bool vbg_track_bit_usage(struct vbg_bit_usage_tracker *tracker,
 }
 
 /**
- * Init and termination worker for resetting the (host) event filter on the host
- * Return: 0 or negative errno value.
+ * vbg_reset_host_event_filter - Init and termination worker for
+ *	resetting the (host) event filter on the host
  * @gdev:		   The Guest extension device.
  * @fixed_events:	   Fixed events (init time).
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_reset_host_event_filter(struct vbg_dev *gdev,
 				       u32 fixed_events)
@@ -556,12 +568,8 @@ static int vbg_reset_host_event_filter(struct vbg_dev *gdev,
 }
 
 /**
- * Changes the event filter mask for the given session.
- *
- * This is called in response to VBG_IOCTL_CHANGE_FILTER_MASK as well as to
- * do session cleanup. Takes the session mutex.
- *
- * Return: 0 or negative errno value.
+ * vbg_set_session_event_filter - Changes the event filter mask for the
+ *	given session.
  * @gdev:			The Guest extension device.
  * @session:			The session.
  * @or_mask:			The events to add.
@@ -570,6 +578,11 @@ static int vbg_reset_host_event_filter(struct vbg_dev *gdev,
  *				This tweaks the error handling so we perform
  *				proper session cleanup even if the host
  *				misbehaves.
+ *
+ * This is called in response to VBG_IOCTL_CHANGE_FILTER_MASK as well as to
+ * do session cleanup. Takes the session mutex.
+ *
+ * Return: 0 or negative errno value.
  */
 static int vbg_set_session_event_filter(struct vbg_dev *gdev,
 					struct vbg_session *session,
@@ -637,9 +650,11 @@ out:
 }
 
 /**
- * Init and termination worker for set guest capabilities to zero on the host.
- * Return: 0 or negative errno value.
+ * vbg_reset_host_capabilities - Init and termination worker for set
+ *	guest capabilities to zero on the host.
  * @gdev:		The Guest extension device.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_reset_host_capabilities(struct vbg_dev *gdev)
 {
@@ -662,12 +677,14 @@ static int vbg_reset_host_capabilities(struct vbg_dev *gdev)
 }
 
 /**
- * Set guest capabilities on the host.
- * Must be called with gdev->session_mutex hold.
- * Return: 0 or negative errno value.
+ * vbg_set_host_capabilities - Set guest capabilities on the host.
  * @gdev:			The Guest extension device.
  * @session:			The session.
  * @session_termination:	Set if we're called by the session cleanup code.
+ *
+ * Must be called with gdev->session_mutex hold.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_set_host_capabilities(struct vbg_dev *gdev,
 				     struct vbg_session *session,
@@ -704,9 +721,8 @@ static int vbg_set_host_capabilities(struct vbg_dev *gdev,
 }
 
 /**
- * Acquire (get exclusive access) guest capabilities for a session.
- * Takes the session mutex.
- * Return: 0 or negative errno value.
+ * vbg_acquire_session_capabilities - Acquire (get exclusive access)
+ *	guest capabilities for a session.
  * @gdev:			The Guest extension device.
  * @session:			The session.
  * @flags:			Flags (VBGL_IOC_AGC_FLAGS_XXX).
@@ -716,6 +732,10 @@ static int vbg_set_host_capabilities(struct vbg_dev *gdev,
  *				This tweaks the error handling so we perform
  *				proper session cleanup even if the host
  *				misbehaves.
+ *
+ * Takes the session mutex.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_acquire_session_capabilities(struct vbg_dev *gdev,
 					    struct vbg_session *session,
@@ -811,8 +831,8 @@ out:
 }
 
 /**
- * Sets the guest capabilities for a session. Takes the session mutex.
- * Return: 0 or negative errno value.
+ * vbg_set_session_capabilities - Sets the guest capabilities for a
+ *	session. Takes the session mutex.
  * @gdev:			The Guest extension device.
  * @session:			The session.
  * @or_mask:			The capabilities to add.
@@ -821,6 +841,8 @@ out:
  *				This tweaks the error handling so we perform
  *				proper session cleanup even if the host
  *				misbehaves.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_set_session_capabilities(struct vbg_dev *gdev,
 					struct vbg_session *session,
@@ -866,9 +888,10 @@ out:
 }
 
 /**
- * vbg_query_host_version get the host feature mask and version information.
- * Return: 0 or negative errno value.
+ * vbg_query_host_version - get the host feature mask and version information.
  * @gdev:		The Guest extension device.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_query_host_version(struct vbg_dev *gdev)
 {
@@ -905,19 +928,18 @@ out:
 }
 
 /**
- * Initializes the VBoxGuest device extension when the
- * device driver is loaded.
+ * vbg_core_init - Initializes the VBoxGuest device extension when the
+ *	device driver is loaded.
+ * @gdev:		The Guest extension device.
+ * @fixed_events:	Events that will be enabled upon init and no client
+ *			will ever be allowed to mask.
  *
  * The native code locates the VMMDev on the PCI bus and retrieve
  * the MMIO and I/O port ranges, this function will take care of
  * mapping the MMIO memory (if present). Upon successful return
  * the native code should set up the interrupt handler.
  *
- * Return: 0 or negative errno value.
- *
- * @gdev:		The Guest extension device.
- * @fixed_events:	Events that will be enabled upon init and no client
- *			will ever be allowed to mask.
+ * Return: %0 or negative errno value.
  */
 int vbg_core_init(struct vbg_dev *gdev, u32 fixed_events)
 {
@@ -1017,11 +1039,12 @@ err_free_reqs:
 }
 
 /**
- * Call this on exit to clean-up vboxguest-core managed resources.
+ * vbg_core_exit - Call this on exit to clean-up vboxguest-core managed
+ *	resources.
+ * @gdev:		The Guest extension device.
  *
  * The native code should call this before the driver is loaded,
  * but don't call this on shutdown.
- * @gdev:		The Guest extension device.
  */
 void vbg_core_exit(struct vbg_dev *gdev)
 {
@@ -1046,12 +1069,13 @@ void vbg_core_exit(struct vbg_dev *gdev)
 }
 
 /**
- * Creates a VBoxGuest user session.
+ * vbg_core_open_session - Creates a VBoxGuest user session.
+ * @gdev:		The Guest extension device.
+ * @requestor:		VMMDEV_REQUESTOR_* flags
  *
  * vboxguest_linux.c calls this when userspace opens the char-device.
+ *
  * Return: A pointer to the new session or an ERR_PTR on error.
- * @gdev:		The Guest extension device.
- * @requestor:		VMMDEV_REQUESTOR_* flags
  */
 struct vbg_session *vbg_core_open_session(struct vbg_dev *gdev, u32 requestor)
 {
@@ -1068,7 +1092,7 @@ struct vbg_session *vbg_core_open_session(struct vbg_dev *gdev, u32 requestor)
 }
 
 /**
- * Closes a VBoxGuest session.
+ * vbg_core_close_session - Closes a VBoxGuest session.
  * @session:		The session to close (and free).
  */
 void vbg_core_close_session(struct vbg_session *session)
@@ -1250,11 +1274,13 @@ static int vbg_ioctl_interrupt_all_wait_events(struct vbg_dev *gdev,
 }
 
 /**
- * Checks if the VMM request is allowed in the context of the given session.
- * Return: 0 or negative errno value.
+ * vbg_req_allowed - Checks if the VMM request is allowed in the
+ *	context of the given session.
  * @gdev:		The Guest extension device.
  * @session:		The calling session.
  * @req:		The request.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_req_allowed(struct vbg_dev *gdev, struct vbg_session *session,
 			   const struct vmmdev_request_header *req)
@@ -1670,11 +1696,12 @@ static int vbg_ioctl_write_core_dump(struct vbg_dev *gdev,
 }
 
 /**
- * Common IOCtl for user to kernel communication.
- * Return: 0 or negative errno value.
+ * vbg_core_ioctl - Common IOCtl for user to kernel communication.
  * @session:	The client session.
  * @req:	The requested function.
  * @data:	The i/o data buffer, minimum size sizeof(struct vbg_ioctl_hdr).
+ *
+ * Return: %0 or negative errno value.
  */
 int vbg_core_ioctl(struct vbg_session *session, unsigned int req, void *data)
 {
@@ -1744,11 +1771,12 @@ int vbg_core_ioctl(struct vbg_session *session, unsigned int req, void *data)
 }
 
 /**
- * Report guest supported mouse-features to the host.
+ * vbg_core_set_mouse_status - Report guest supported mouse-features to the host.
  *
- * Return: 0 or negative errno value.
  * @gdev:		The Guest extension device.
  * @features:		The set of features to report to the host.
+ *
+ * Return: %0 or negative errno value.
  */
 int vbg_core_set_mouse_status(struct vbg_dev *gdev, u32 features)
 {
@@ -1772,7 +1800,7 @@ int vbg_core_set_mouse_status(struct vbg_dev *gdev, u32 features)
 	return vbg_status_code_to_errno(rc);
 }
 
-/** Core interrupt service routine. */
+/* Core interrupt service routine. */
 irqreturn_t vbg_core_isr(int irq, void *dev_id)
 {
 	struct vbg_dev *gdev = dev_id;
diff --git a/drivers/virt/vboxguest/vboxguest_linux.c b/drivers/virt/vboxguest/vboxguest_linux.c
index c47e62dc55da..8c92ea5b7305 100644
--- a/drivers/virt/vboxguest/vboxguest_linux.c
+++ b/drivers/virt/vboxguest/vboxguest_linux.c
@@ -81,10 +81,11 @@ static int vbg_misc_device_user_open(struct inode *inode, struct file *filp)
 }
 
 /**
- * Close device.
- * Return: 0 on success, negated errno on failure.
+ * vbg_misc_device_close - Close device.
  * @inode:		Pointer to inode info structure.
  * @filp:		Associated file pointer.
+ *
+ * Return: %0 on success, negated errno on failure.
  */
 static int vbg_misc_device_close(struct inode *inode, struct file *filp)
 {
@@ -94,11 +95,12 @@ static int vbg_misc_device_close(struct inode *inode, struct file *filp)
 }
 
 /**
- * Device I/O Control entry point.
- * Return: 0 on success, negated errno on failure.
+ * vbg_misc_device_ioctl - Device I/O Control entry point.
  * @filp:		Associated file pointer.
  * @req:		The request specified to ioctl().
  * @arg:		The argument specified to ioctl().
+ *
+ * Return: %0 on success, negated errno on failure.
  */
 static long vbg_misc_device_ioctl(struct file *filp, unsigned int req,
 				  unsigned long arg)
@@ -173,7 +175,7 @@ out:
 	return ret;
 }
 
-/** The file_operations structures. */
+/* The file_operations structures. */
 static const struct file_operations vbg_misc_device_fops = {
 	.owner			= THIS_MODULE,
 	.open			= vbg_misc_device_open,
@@ -193,7 +195,7 @@ static const struct file_operations vbg_misc_device_user_fops = {
 #endif
 };
 
-/**
+/*
  * Called when the input device is first opened.
  *
  * Sets up absolute mouse reporting.
@@ -206,7 +208,7 @@ static int vbg_input_open(struct input_dev *input)
 	return vbg_core_set_mouse_status(gdev, feat);
 }
 
-/**
+/*
  * Called if all open handles to the input device are closed.
  *
  * Disables absolute reporting.
@@ -218,7 +220,7 @@ static void vbg_input_close(struct input_dev *input)
 	vbg_core_set_mouse_status(gdev, 0);
 }
 
-/**
+/*
  * Creates the kernel input device.
  *
  * Return: 0 on success, negated errno on failure.
@@ -277,7 +279,7 @@ static struct attribute *vbg_pci_attrs[] = {
 };
 ATTRIBUTE_GROUPS(vbg_pci);
 
-/**
+/*
  * Does the PCI detection and init of the device.
  *
  * Return: 0 on success, negated errno on failure.
@@ -453,7 +455,7 @@ void vbg_put_gdev(struct vbg_dev *gdev)
 }
 EXPORT_SYMBOL(vbg_put_gdev);
 
-/**
+/*
  * Callback for mouse events.
  *
  * This is called at the end of the ISR, after leaving the event spinlock, if
diff --git a/drivers/virt/vboxguest/vboxguest_utils.c b/drivers/virt/vboxguest/vboxguest_utils.c
index 8d195e3f8301..1c02b3c0d934 100644
--- a/drivers/virt/vboxguest/vboxguest_utils.c
+++ b/drivers/virt/vboxguest/vboxguest_utils.c
@@ -237,14 +237,16 @@ static int hgcm_call_preprocess_linaddr(
 }
 
 /**
- * Preprocesses the HGCM call, validate parameters, alloc bounce buffers and
- * figure out how much extra storage we need for page lists.
- * Return: 0 or negative errno value.
+ * hgcm_call_preprocess - Preprocesses the HGCM call, validate parameters,
+ *	alloc bounce buffers and figure out how much extra storage we need for
+ *	page lists.
  * @src_parm:         Pointer to source function call parameters
  * @parm_count:       Number of function call parameters.
  * @bounce_bufs_ret:  Where to return the allocated bouncebuffer array
  * @extra:            Where to return the extra request space needed for
  *                    physical page lists.
+ *
+ * Return: %0 or negative errno value.
  */
 static int hgcm_call_preprocess(
 	const struct vmmdev_hgcm_function_parameter *src_parm,
@@ -301,10 +303,11 @@ static int hgcm_call_preprocess(
 }
 
 /**
- * Translates linear address types to page list direction flags.
+ * hgcm_call_linear_addr_type_to_pagelist_flags - Translates linear address
+ *	types to page list direction flags.
+ * @type:  The type.
  *
  * Return: page list flags.
- * @type:  The type.
  */
 static u32 hgcm_call_linear_addr_type_to_pagelist_flags(
 	enum vmmdev_hgcm_function_parameter_type type)
@@ -369,7 +372,8 @@ static void hgcm_call_init_linaddr(struct vmmdev_hgcm_call *call,
 }
 
 /**
- * Initializes the call request that we're sending to the host.
+ * hgcm_call_init_call - Initializes the call request that we're sending
+ *	to the host.
  * @call:            The call to initialize.
  * @client_id:       The client ID of the caller.
  * @function:        The function number of the function to call.
@@ -425,7 +429,9 @@ static void hgcm_call_init_call(
 }
 
 /**
- * Tries to cancel a pending HGCM call.
+ * hgcm_cancel_call - Tries to cancel a pending HGCM call.
+ * @gdev:        The VBoxGuest device extension.
+ * @call:        The call to cancel.
  *
  * Return: VBox status code
  */
@@ -459,13 +465,15 @@ static int hgcm_cancel_call(struct vbg_dev *gdev, struct vmmdev_hgcm_call *call)
 }
 
 /**
- * Performs the call and completion wait.
- * Return: 0 or negative errno value.
+ * vbg_hgcm_do_call - Performs the call and completion wait.
  * @gdev:        The VBoxGuest device extension.
  * @call:        The call to execute.
  * @timeout_ms:  Timeout in ms.
+ * @interruptible: whether this call is interruptible
  * @leak_it:     Where to return the leak it / free it, indicator.
  *               Cancellation fun.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_hgcm_do_call(struct vbg_dev *gdev, struct vmmdev_hgcm_call *call,
 			    u32 timeout_ms, bool interruptible, bool *leak_it)
@@ -545,13 +553,14 @@ static int vbg_hgcm_do_call(struct vbg_dev *gdev, struct vmmdev_hgcm_call *call,
 }
 
 /**
- * Copies the result of the call back to the caller info structure and user
- * buffers.
- * Return: 0 or negative errno value.
+ * hgcm_call_copy_back_result - Copies the result of the call back to
+ *	the caller info structure and user buffers.
  * @call:            HGCM call request.
  * @dst_parm:        Pointer to function call parameters destination.
  * @parm_count:      Number of function call parameters.
  * @bounce_bufs:     The bouncebuffer array.
+ *
+ * Return: %0 or negative errno value.
  */
 static int hgcm_call_copy_back_result(
 	const struct vmmdev_hgcm_call *call,
diff --git a/drivers/virt/vmgenid.c b/drivers/virt/vmgenid.c
index a1c467a0e9f7..b67a28da4702 100644
--- a/drivers/virt/vmgenid.c
+++ b/drivers/virt/vmgenid.c
@@ -68,6 +68,7 @@ out:
 static void vmgenid_notify(struct acpi_device *device, u32 event)
 {
 	struct vmgenid_state *state = acpi_driver_data(device);
+	char *envp[] = { "NEW_VMGENID=1", NULL };
 	u8 old_id[VMGENID_SIZE];
 
 	memcpy(old_id, state->this_id, sizeof(old_id));
@@ -75,6 +76,7 @@ static void vmgenid_notify(struct acpi_device *device, u32 event)
 	if (!memcmp(old_id, state->this_id, sizeof(old_id)))
 		return;
 	add_vmfork_randomness(state->this_id, sizeof(state->this_id));
+	kobject_uevent_env(&device->dev.kobj, KOBJ_CHANGE, envp);
 }
 
 static const struct acpi_device_id vmgenid_ids[] = {
diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index 0a53a61231c2..c17193544268 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -60,6 +60,11 @@ config VIRTIO_PCI
 
 	  If unsure, say M.
 
+config VIRTIO_PCI_ADMIN_LEGACY
+	bool
+	depends on VIRTIO_PCI && (X86 || COMPILE_TEST)
+	default y
+
 config VIRTIO_PCI_LEGACY
 	bool "Support for legacy virtio draft 0.9.X and older devices"
 	default y
diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
index 8e98d24917cc..73ace62af440 100644
--- a/drivers/virtio/Makefile
+++ b/drivers/virtio/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o
 obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o
 virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o
 virtio_pci-$(CONFIG_VIRTIO_PCI_LEGACY) += virtio_pci_legacy.o
+virtio_pci-$(CONFIG_VIRTIO_PCI_ADMIN_LEGACY) += virtio_pci_admin_legacy_io.o
 obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
 obj-$(CONFIG_VIRTIO_INPUT) += virtio_input.o
 obj-$(CONFIG_VIRTIO_VDPA) += virtio_vdpa.o
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 3893dc29eb26..f4080692b351 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -302,9 +302,15 @@ static int virtio_dev_probe(struct device *_d)
 	if (err)
 		goto err;
 
+	if (dev->config->create_avq) {
+		err = dev->config->create_avq(dev);
+		if (err)
+			goto err;
+	}
+
 	err = drv->probe(dev);
 	if (err)
-		goto err;
+		goto err_probe;
 
 	/* If probe didn't do it, mark device DRIVER_OK ourselves. */
 	if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK))
@@ -316,6 +322,10 @@ static int virtio_dev_probe(struct device *_d)
 	virtio_config_enable(dev);
 
 	return 0;
+
+err_probe:
+	if (dev->config->destroy_avq)
+		dev->config->destroy_avq(dev);
 err:
 	virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
 	return err;
@@ -331,6 +341,9 @@ static void virtio_dev_remove(struct device *_d)
 
 	drv->remove(dev);
 
+	if (dev->config->destroy_avq)
+		dev->config->destroy_avq(dev);
+
 	/* Driver should have reset device. */
 	WARN_ON_ONCE(dev->config->get_status(dev));
 
@@ -489,13 +502,20 @@ EXPORT_SYMBOL_GPL(unregister_virtio_device);
 int virtio_device_freeze(struct virtio_device *dev)
 {
 	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+	int ret;
 
 	virtio_config_disable(dev);
 
 	dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED;
 
-	if (drv && drv->freeze)
-		return drv->freeze(dev);
+	if (drv && drv->freeze) {
+		ret = drv->freeze(dev);
+		if (ret)
+			return ret;
+	}
+
+	if (dev->config->destroy_avq)
+		dev->config->destroy_avq(dev);
 
 	return 0;
 }
@@ -532,10 +552,16 @@ int virtio_device_restore(struct virtio_device *dev)
 	if (ret)
 		goto err;
 
+	if (dev->config->create_avq) {
+		ret = dev->config->create_avq(dev);
+		if (ret)
+			goto err;
+	}
+
 	if (drv->restore) {
 		ret = drv->restore(dev);
 		if (ret)
-			goto err;
+			goto err_restore;
 	}
 
 	/* If restore didn't do it, mark device DRIVER_OK ourselves. */
@@ -546,6 +572,9 @@ int virtio_device_restore(struct virtio_device *dev)
 
 	return 0;
 
+err_restore:
+	if (dev->config->destroy_avq)
+		dev->config->destroy_avq(dev);
 err:
 	virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
 	return ret;
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 59cdc0292dce..1f5b3dd31fcf 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -119,6 +119,11 @@ struct virtio_balloon {
 	/* Free page reporting device */
 	struct virtqueue *reporting_vq;
 	struct page_reporting_dev_info pr_dev_info;
+
+	/* State for keeping the wakeup_source active while adjusting the balloon */
+	spinlock_t adjustment_lock;
+	bool adjustment_signal_pending;
+	bool adjustment_in_progress;
 };
 
 static const struct virtio_device_id id_table[] = {
@@ -437,6 +442,31 @@ static void virtio_balloon_queue_free_page_work(struct virtio_balloon *vb)
 	queue_work(vb->balloon_wq, &vb->report_free_page_work);
 }
 
+static void start_update_balloon_size(struct virtio_balloon *vb)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&vb->adjustment_lock, flags);
+	vb->adjustment_signal_pending = true;
+	if (!vb->adjustment_in_progress) {
+		vb->adjustment_in_progress = true;
+		pm_stay_awake(vb->vdev->dev.parent);
+	}
+	spin_unlock_irqrestore(&vb->adjustment_lock, flags);
+
+	queue_work(system_freezable_wq, &vb->update_balloon_size_work);
+}
+
+static void end_update_balloon_size(struct virtio_balloon *vb)
+{
+	spin_lock_irq(&vb->adjustment_lock);
+	if (!vb->adjustment_signal_pending && vb->adjustment_in_progress) {
+		vb->adjustment_in_progress = false;
+		pm_relax(vb->vdev->dev.parent);
+	}
+	spin_unlock_irq(&vb->adjustment_lock);
+}
+
 static void virtballoon_changed(struct virtio_device *vdev)
 {
 	struct virtio_balloon *vb = vdev->priv;
@@ -444,8 +474,7 @@ static void virtballoon_changed(struct virtio_device *vdev)
 
 	spin_lock_irqsave(&vb->stop_update_lock, flags);
 	if (!vb->stop_update) {
-		queue_work(system_freezable_wq,
-			   &vb->update_balloon_size_work);
+		start_update_balloon_size(vb);
 		virtio_balloon_queue_free_page_work(vb);
 	}
 	spin_unlock_irqrestore(&vb->stop_update_lock, flags);
@@ -476,19 +505,25 @@ static void update_balloon_size_func(struct work_struct *work)
 
 	vb = container_of(work, struct virtio_balloon,
 			  update_balloon_size_work);
-	diff = towards_target(vb);
 
-	if (!diff)
-		return;
+	spin_lock_irq(&vb->adjustment_lock);
+	vb->adjustment_signal_pending = false;
+	spin_unlock_irq(&vb->adjustment_lock);
 
-	if (diff > 0)
-		diff -= fill_balloon(vb, diff);
-	else
-		diff += leak_balloon(vb, -diff);
-	update_balloon_size(vb);
+	diff = towards_target(vb);
+
+	if (diff) {
+		if (diff > 0)
+			diff -= fill_balloon(vb, diff);
+		else
+			diff += leak_balloon(vb, -diff);
+		update_balloon_size(vb);
+	}
 
 	if (diff)
 		queue_work(system_freezable_wq, work);
+	else
+		end_update_balloon_size(vb);
 }
 
 static int init_vqs(struct virtio_balloon *vb)
@@ -992,6 +1027,8 @@ static int virtballoon_probe(struct virtio_device *vdev)
 			goto out_unregister_oom;
 	}
 
+	spin_lock_init(&vb->adjustment_lock);
+
 	virtio_device_ready(vdev);
 
 	if (towards_target(vb))
diff --git a/drivers/virtio/virtio_pci_admin_legacy_io.c b/drivers/virtio/virtio_pci_admin_legacy_io.c
new file mode 100644
index 000000000000..819cfbbc67c3
--- /dev/null
+++ b/drivers/virtio/virtio_pci_admin_legacy_io.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+
+#include <linux/virtio_pci_admin.h>
+#include "virtio_pci_common.h"
+
+/*
+ * virtio_pci_admin_has_legacy_io - Checks whether the legacy IO
+ * commands are supported
+ * @dev: VF pci_dev
+ *
+ * Returns true on success.
+ */
+bool virtio_pci_admin_has_legacy_io(struct pci_dev *pdev)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_pci_device *vp_dev;
+
+	if (!virtio_dev)
+		return false;
+
+	if (!virtio_has_feature(virtio_dev, VIRTIO_F_ADMIN_VQ))
+		return false;
+
+	vp_dev = to_vp_device(virtio_dev);
+
+	if ((vp_dev->admin_vq.supported_cmds & VIRTIO_LEGACY_ADMIN_CMD_BITMAP) ==
+		VIRTIO_LEGACY_ADMIN_CMD_BITMAP)
+		return true;
+	return false;
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_has_legacy_io);
+
+static int virtio_pci_admin_legacy_io_write(struct pci_dev *pdev, u16 opcode,
+					    u8 offset, u8 size, u8 *buf)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_admin_cmd_legacy_wr_data *data;
+	struct virtio_admin_cmd cmd = {};
+	struct scatterlist data_sg;
+	int vf_id;
+	int ret;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	data = kzalloc(sizeof(*data) + size, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->offset = offset;
+	memcpy(data->registers, buf, size);
+	sg_init_one(&data_sg, data, sizeof(*data) + size);
+	cmd.opcode = cpu_to_le16(opcode);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.data_sg = &data_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+
+	kfree(data);
+	return ret;
+}
+
+/*
+ * virtio_pci_admin_legacy_io_write_common - Write legacy common configuration
+ * of a member device
+ * @dev: VF pci_dev
+ * @offset: starting byte offset within the common configuration area to write to
+ * @size: size of the data to write
+ * @buf: buffer which holds the data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_common_io_write(struct pci_dev *pdev, u8 offset,
+					    u8 size, u8 *buf)
+{
+	return virtio_pci_admin_legacy_io_write(pdev,
+					VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_WRITE,
+					offset, size, buf);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_common_io_write);
+
+/*
+ * virtio_pci_admin_legacy_io_write_device - Write legacy device configuration
+ * of a member device
+ * @dev: VF pci_dev
+ * @offset: starting byte offset within the device configuration area to write to
+ * @size: size of the data to write
+ * @buf: buffer which holds the data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_device_io_write(struct pci_dev *pdev, u8 offset,
+					    u8 size, u8 *buf)
+{
+	return virtio_pci_admin_legacy_io_write(pdev,
+					VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_WRITE,
+					offset, size, buf);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_device_io_write);
+
+static int virtio_pci_admin_legacy_io_read(struct pci_dev *pdev, u16 opcode,
+					   u8 offset, u8 size, u8 *buf)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_admin_cmd_legacy_rd_data *data;
+	struct scatterlist data_sg, result_sg;
+	struct virtio_admin_cmd cmd = {};
+	int vf_id;
+	int ret;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->offset = offset;
+	sg_init_one(&data_sg, data, sizeof(*data));
+	sg_init_one(&result_sg, buf, size);
+	cmd.opcode = cpu_to_le16(opcode);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.data_sg = &data_sg;
+	cmd.result_sg = &result_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+
+	kfree(data);
+	return ret;
+}
+
+/*
+ * virtio_pci_admin_legacy_device_io_read - Read legacy device configuration of
+ * a member device
+ * @dev: VF pci_dev
+ * @offset: starting byte offset within the device configuration area to read from
+ * @size: size of the data to be read
+ * @buf: buffer to hold the returned data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_device_io_read(struct pci_dev *pdev, u8 offset,
+					   u8 size, u8 *buf)
+{
+	return virtio_pci_admin_legacy_io_read(pdev,
+					VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ,
+					offset, size, buf);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_device_io_read);
+
+/*
+ * virtio_pci_admin_legacy_common_io_read - Read legacy common configuration of
+ * a member device
+ * @dev: VF pci_dev
+ * @offset: starting byte offset within the common configuration area to read from
+ * @size: size of the data to be read
+ * @buf: buffer to hold the returned data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_common_io_read(struct pci_dev *pdev, u8 offset,
+					   u8 size, u8 *buf)
+{
+	return virtio_pci_admin_legacy_io_read(pdev,
+					VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_READ,
+					offset, size, buf);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_common_io_read);
+
+/*
+ * virtio_pci_admin_legacy_io_notify_info - Read the queue notification
+ * information for legacy interface
+ * @dev: VF pci_dev
+ * @req_bar_flags: requested bar flags
+ * @bar: on output the BAR number of the owner or member device
+ * @bar_offset: on output the offset within bar
+ *
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_io_notify_info(struct pci_dev *pdev,
+					   u8 req_bar_flags, u8 *bar,
+					   u64 *bar_offset)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_admin_cmd_notify_info_result *result;
+	struct virtio_admin_cmd cmd = {};
+	struct scatterlist result_sg;
+	int vf_id;
+	int ret;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	result = kzalloc(sizeof(*result), GFP_KERNEL);
+	if (!result)
+		return -ENOMEM;
+
+	sg_init_one(&result_sg, result, sizeof(*result));
+	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.result_sg = &result_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+	if (!ret) {
+		struct virtio_admin_cmd_notify_info_data *entry;
+		int i;
+
+		ret = -ENOENT;
+		for (i = 0; i < VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO; i++) {
+			entry = &result->entries[i];
+			if (entry->flags == VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_END)
+				break;
+			if (entry->flags != req_bar_flags)
+				continue;
+			*bar = entry->bar;
+			*bar_offset = le64_to_cpu(entry->offset);
+			ret = 0;
+			break;
+		}
+	}
+
+	kfree(result);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_io_notify_info);
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 7a5593997e0e..b655fccaf773 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -236,6 +236,9 @@ void vp_del_vqs(struct virtio_device *vdev)
 	int i;
 
 	list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
+		if (vp_dev->is_avq(vdev, vq->index))
+			continue;
+
 		if (vp_dev->per_vq_vectors) {
 			int v = vp_dev->vqs[vq->index]->msix_vector;
 
@@ -492,8 +495,40 @@ static int virtio_pci_restore(struct device *dev)
 	return virtio_device_restore(&vp_dev->vdev);
 }
 
+static bool vp_supports_pm_no_reset(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	u16 pmcsr;
+
+	if (!pci_dev->pm_cap)
+		return false;
+
+	pci_read_config_word(pci_dev, pci_dev->pm_cap + PCI_PM_CTRL, &pmcsr);
+	if (PCI_POSSIBLE_ERROR(pmcsr)) {
+		dev_err(dev, "Unable to query pmcsr");
+		return false;
+	}
+
+	return pmcsr & PCI_PM_CTRL_NO_SOFT_RESET;
+}
+
+static int virtio_pci_suspend(struct device *dev)
+{
+	return vp_supports_pm_no_reset(dev) ? 0 : virtio_pci_freeze(dev);
+}
+
+static int virtio_pci_resume(struct device *dev)
+{
+	return vp_supports_pm_no_reset(dev) ? 0 : virtio_pci_restore(dev);
+}
+
 static const struct dev_pm_ops virtio_pci_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(virtio_pci_freeze, virtio_pci_restore)
+	.suspend = virtio_pci_suspend,
+	.resume = virtio_pci_resume,
+	.freeze = virtio_pci_freeze,
+	.thaw = virtio_pci_restore,
+	.poweroff = virtio_pci_freeze,
+	.restore = virtio_pci_restore,
 };
 #endif
 
@@ -642,6 +677,17 @@ static struct pci_driver virtio_pci_driver = {
 	.sriov_configure = virtio_pci_sriov_configure,
 };
 
+struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev)
+{
+	struct virtio_pci_device *pf_vp_dev;
+
+	pf_vp_dev = pci_iov_get_pf_drvdata(pdev, &virtio_pci_driver);
+	if (IS_ERR(pf_vp_dev))
+		return NULL;
+
+	return &pf_vp_dev->vdev;
+}
+
 module_pci_driver(virtio_pci_driver);
 
 MODULE_AUTHOR("Anthony Liguori <aliguori@us.ibm.com>");
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index 4b773bd7c58c..7fef52bee455 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -29,6 +29,7 @@
 #include <linux/virtio_pci_modern.h>
 #include <linux/highmem.h>
 #include <linux/spinlock.h>
+#include <linux/mutex.h>
 
 struct virtio_pci_vq_info {
 	/* the actual virtqueue */
@@ -41,6 +42,17 @@ struct virtio_pci_vq_info {
 	unsigned int msix_vector;
 };
 
+struct virtio_pci_admin_vq {
+	/* Virtqueue info associated with this admin queue. */
+	struct virtio_pci_vq_info info;
+	/* serializing admin commands execution and virtqueue deletion */
+	struct mutex cmd_lock;
+	u64 supported_cmds;
+	/* Name of the admin queue: avq.$vq_index. */
+	char name[10];
+	u16 vq_index;
+};
+
 /* Our device structure */
 struct virtio_pci_device {
 	struct virtio_device vdev;
@@ -58,9 +70,13 @@ struct virtio_pci_device {
 	spinlock_t lock;
 	struct list_head virtqueues;
 
-	/* array of all queues for house-keeping */
+	/* Array of all virtqueues reported in the
+	 * PCI common config num_queues field
+	 */
 	struct virtio_pci_vq_info **vqs;
 
+	struct virtio_pci_admin_vq admin_vq;
+
 	/* MSI-X support */
 	int msix_enabled;
 	int intx_enabled;
@@ -86,6 +102,7 @@ struct virtio_pci_device {
 	void (*del_vq)(struct virtio_pci_vq_info *info);
 
 	u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector);
+	bool (*is_avq)(struct virtio_device *vdev, unsigned int index);
 };
 
 /* Constants for MSI-X */
@@ -139,4 +156,27 @@ static inline void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev)
 int virtio_pci_modern_probe(struct virtio_pci_device *);
 void virtio_pci_modern_remove(struct virtio_pci_device *);
 
+struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev);
+
+#define VIRTIO_LEGACY_ADMIN_CMD_BITMAP \
+	(BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_WRITE) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_READ) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_WRITE) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO))
+
+/* Unlike modern drivers which support hardware virtio devices, legacy drivers
+ * assume software-based devices: e.g. they don't use proper memory barriers
+ * on ARM, use big endian on PPC, etc. X86 drivers are mostly ok though, more
+ * or less by chance. For now, only support legacy IO on X86.
+ */
+#ifdef CONFIG_VIRTIO_PCI_ADMIN_LEGACY
+#define VIRTIO_ADMIN_CMD_BITMAP VIRTIO_LEGACY_ADMIN_CMD_BITMAP
+#else
+#define VIRTIO_ADMIN_CMD_BITMAP 0
+#endif
+
+int vp_modern_admin_cmd_exec(struct virtio_device *vdev,
+			     struct virtio_admin_cmd *cmd);
+
 #endif
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index ee6a386d250b..f62b530aa3b5 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -19,6 +19,8 @@
 #define VIRTIO_RING_NO_LEGACY
 #include "virtio_pci_common.h"
 
+#define VIRTIO_AVQ_SGS_MAX	4
+
 static u64 vp_get_features(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -26,6 +28,187 @@ static u64 vp_get_features(struct virtio_device *vdev)
 	return vp_modern_get_features(&vp_dev->mdev);
 }
 
+static bool vp_is_avq(struct virtio_device *vdev, unsigned int index)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return false;
+
+	return index == vp_dev->admin_vq.vq_index;
+}
+
+static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq,
+				    u16 opcode,
+				    struct scatterlist **sgs,
+				    unsigned int out_num,
+				    unsigned int in_num,
+				    void *data)
+{
+	struct virtqueue *vq;
+	int ret, len;
+
+	vq = admin_vq->info.vq;
+	if (!vq)
+		return -EIO;
+
+	if (opcode != VIRTIO_ADMIN_CMD_LIST_QUERY &&
+	    opcode != VIRTIO_ADMIN_CMD_LIST_USE &&
+	    !((1ULL << opcode) & admin_vq->supported_cmds))
+		return -EOPNOTSUPP;
+
+	ret = virtqueue_add_sgs(vq, sgs, out_num, in_num, data, GFP_KERNEL);
+	if (ret < 0)
+		return -EIO;
+
+	if (unlikely(!virtqueue_kick(vq)))
+		return -EIO;
+
+	while (!virtqueue_get_buf(vq, &len) &&
+	       !virtqueue_is_broken(vq))
+		cpu_relax();
+
+	if (virtqueue_is_broken(vq))
+		return -EIO;
+
+	return 0;
+}
+
+int vp_modern_admin_cmd_exec(struct virtio_device *vdev,
+			     struct virtio_admin_cmd *cmd)
+{
+	struct scatterlist *sgs[VIRTIO_AVQ_SGS_MAX], hdr, stat;
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_admin_cmd_status *va_status;
+	unsigned int out_num = 0, in_num = 0;
+	struct virtio_admin_cmd_hdr *va_hdr;
+	u16 status;
+	int ret;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return -EOPNOTSUPP;
+
+	va_status = kzalloc(sizeof(*va_status), GFP_KERNEL);
+	if (!va_status)
+		return -ENOMEM;
+
+	va_hdr = kzalloc(sizeof(*va_hdr), GFP_KERNEL);
+	if (!va_hdr) {
+		ret = -ENOMEM;
+		goto err_alloc;
+	}
+
+	va_hdr->opcode = cmd->opcode;
+	va_hdr->group_type = cmd->group_type;
+	va_hdr->group_member_id = cmd->group_member_id;
+
+	/* Add header */
+	sg_init_one(&hdr, va_hdr, sizeof(*va_hdr));
+	sgs[out_num] = &hdr;
+	out_num++;
+
+	if (cmd->data_sg) {
+		sgs[out_num] = cmd->data_sg;
+		out_num++;
+	}
+
+	/* Add return status */
+	sg_init_one(&stat, va_status, sizeof(*va_status));
+	sgs[out_num + in_num] = &stat;
+	in_num++;
+
+	if (cmd->result_sg) {
+		sgs[out_num + in_num] = cmd->result_sg;
+		in_num++;
+	}
+
+	mutex_lock(&vp_dev->admin_vq.cmd_lock);
+	ret = virtqueue_exec_admin_cmd(&vp_dev->admin_vq,
+				       le16_to_cpu(cmd->opcode),
+				       sgs, out_num, in_num, sgs);
+	mutex_unlock(&vp_dev->admin_vq.cmd_lock);
+
+	if (ret) {
+		dev_err(&vdev->dev,
+			"Failed to execute command on admin vq: %d\n.", ret);
+		goto err_cmd_exec;
+	}
+
+	status = le16_to_cpu(va_status->status);
+	if (status != VIRTIO_ADMIN_STATUS_OK) {
+		dev_err(&vdev->dev,
+			"admin command error: status(%#x) qualifier(%#x)\n",
+			status, le16_to_cpu(va_status->status_qualifier));
+		ret = -status;
+	}
+
+err_cmd_exec:
+	kfree(va_hdr);
+err_alloc:
+	kfree(va_status);
+	return ret;
+}
+
+static void virtio_pci_admin_cmd_list_init(struct virtio_device *virtio_dev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(virtio_dev);
+	struct virtio_admin_cmd cmd = {};
+	struct scatterlist result_sg;
+	struct scatterlist data_sg;
+	__le64 *data;
+	int ret;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return;
+
+	sg_init_one(&result_sg, data, sizeof(*data));
+	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_LIST_QUERY);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.result_sg = &result_sg;
+
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+	if (ret)
+		goto end;
+
+	*data &= cpu_to_le64(VIRTIO_ADMIN_CMD_BITMAP);
+	sg_init_one(&data_sg, data, sizeof(*data));
+	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_LIST_USE);
+	cmd.data_sg = &data_sg;
+	cmd.result_sg = NULL;
+
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+	if (ret)
+		goto end;
+
+	vp_dev->admin_vq.supported_cmds = le64_to_cpu(*data);
+end:
+	kfree(data);
+}
+
+static void vp_modern_avq_activate(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return;
+
+	__virtqueue_unbreak(admin_vq->info.vq);
+	virtio_pci_admin_cmd_list_init(vdev);
+}
+
+static void vp_modern_avq_deactivate(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return;
+
+	__virtqueue_break(admin_vq->info.vq);
+}
+
 static void vp_transport_features(struct virtio_device *vdev, u64 features)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -37,6 +220,9 @@ static void vp_transport_features(struct virtio_device *vdev, u64 features)
 
 	if (features & BIT_ULL(VIRTIO_F_RING_RESET))
 		__virtio_set_bit(vdev, VIRTIO_F_RING_RESET);
+
+	if (features & BIT_ULL(VIRTIO_F_ADMIN_VQ))
+		__virtio_set_bit(vdev, VIRTIO_F_ADMIN_VQ);
 }
 
 static int __vp_check_common_size_one_feature(struct virtio_device *vdev, u32 fbit,
@@ -69,6 +255,9 @@ static int vp_check_common_size(struct virtio_device *vdev)
 	if (vp_check_common_size_one_feature(vdev, VIRTIO_F_RING_RESET, queue_reset))
 		return -EINVAL;
 
+	if (vp_check_common_size_one_feature(vdev, VIRTIO_F_ADMIN_VQ, admin_queue_num))
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -195,6 +384,8 @@ static void vp_set_status(struct virtio_device *vdev, u8 status)
 	/* We should never be setting status to 0. */
 	BUG_ON(status == 0);
 	vp_modern_set_status(&vp_dev->mdev, status);
+	if (status & VIRTIO_CONFIG_S_DRIVER_OK)
+		vp_modern_avq_activate(vdev);
 }
 
 static void vp_reset(struct virtio_device *vdev)
@@ -211,6 +402,9 @@ static void vp_reset(struct virtio_device *vdev)
 	 */
 	while (vp_modern_get_status(mdev))
 		msleep(1);
+
+	vp_modern_avq_deactivate(vdev);
+
 	/* Flush pending VQ/configuration callbacks. */
 	vp_synchronize_vectors(vdev);
 }
@@ -345,6 +539,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 	bool (*notify)(struct virtqueue *vq);
 	struct virtqueue *vq;
+	bool is_avq;
 	u16 num;
 	int err;
 
@@ -353,11 +548,13 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	else
 		notify = vp_notify;
 
-	if (index >= vp_modern_get_num_queues(mdev))
+	is_avq = vp_is_avq(&vp_dev->vdev, index);
+	if (index >= vp_modern_get_num_queues(mdev) && !is_avq)
 		return ERR_PTR(-EINVAL);
 
+	num = is_avq ?
+		VIRTIO_AVQ_SGS_MAX : vp_modern_get_queue_size(mdev, index);
 	/* Check if queue is either not available or already active. */
-	num = vp_modern_get_queue_size(mdev, index);
 	if (!num || vp_modern_get_queue_enable(mdev, index))
 		return ERR_PTR(-ENOENT);
 
@@ -383,6 +580,12 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 		goto err;
 	}
 
+	if (is_avq) {
+		mutex_lock(&vp_dev->admin_vq.cmd_lock);
+		vp_dev->admin_vq.info.vq = vq;
+		mutex_unlock(&vp_dev->admin_vq.cmd_lock);
+	}
+
 	return vq;
 
 err:
@@ -418,6 +621,12 @@ static void del_vq(struct virtio_pci_vq_info *info)
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 
+	if (vp_is_avq(&vp_dev->vdev, vq->index)) {
+		mutex_lock(&vp_dev->admin_vq.cmd_lock);
+		vp_dev->admin_vq.info.vq = NULL;
+		mutex_unlock(&vp_dev->admin_vq.cmd_lock);
+	}
+
 	if (vp_dev->msix_enabled)
 		vp_modern_queue_vector(mdev, vq->index,
 				       VIRTIO_MSI_NO_VECTOR);
@@ -527,6 +736,45 @@ static bool vp_get_shm_region(struct virtio_device *vdev,
 	return true;
 }
 
+static int vp_modern_create_avq(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_admin_vq *avq;
+	struct virtqueue *vq;
+	u16 admin_q_num;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return 0;
+
+	admin_q_num = vp_modern_avq_num(&vp_dev->mdev);
+	if (!admin_q_num)
+		return -EINVAL;
+
+	avq = &vp_dev->admin_vq;
+	avq->vq_index = vp_modern_avq_index(&vp_dev->mdev);
+	sprintf(avq->name, "avq.%u", avq->vq_index);
+	vq = vp_dev->setup_vq(vp_dev, &vp_dev->admin_vq.info, avq->vq_index, NULL,
+			      avq->name, NULL, VIRTIO_MSI_NO_VECTOR);
+	if (IS_ERR(vq)) {
+		dev_err(&vdev->dev, "failed to setup admin virtqueue, err=%ld",
+			PTR_ERR(vq));
+		return PTR_ERR(vq);
+	}
+
+	vp_modern_set_queue_enable(&vp_dev->mdev, avq->info.vq->index, true);
+	return 0;
+}
+
+static void vp_modern_destroy_avq(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return;
+
+	vp_dev->del_vq(&vp_dev->admin_vq.info);
+}
+
 static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.get		= NULL,
 	.set		= NULL,
@@ -545,6 +793,8 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.get_shm_region  = vp_get_shm_region,
 	.disable_vq_and_reset = vp_modern_disable_vq_and_reset,
 	.enable_vq_after_reset = vp_modern_enable_vq_after_reset,
+	.create_avq = vp_modern_create_avq,
+	.destroy_avq = vp_modern_destroy_avq,
 };
 
 static const struct virtio_config_ops virtio_pci_config_ops = {
@@ -565,6 +815,8 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 	.get_shm_region  = vp_get_shm_region,
 	.disable_vq_and_reset = vp_modern_disable_vq_and_reset,
 	.enable_vq_after_reset = vp_modern_enable_vq_after_reset,
+	.create_avq = vp_modern_create_avq,
+	.destroy_avq = vp_modern_destroy_avq,
 };
 
 /* the PCI probing function */
@@ -588,9 +840,11 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 	vp_dev->config_vector = vp_config_vector;
 	vp_dev->setup_vq = setup_vq;
 	vp_dev->del_vq = del_vq;
+	vp_dev->is_avq = vp_is_avq;
 	vp_dev->isr = mdev->isr;
 	vp_dev->vdev.id = mdev->id;
 
+	mutex_init(&vp_dev->admin_vq.cmd_lock);
 	return 0;
 }
 
@@ -598,5 +852,6 @@ void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev)
 {
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 
+	mutex_destroy(&vp_dev->admin_vq.cmd_lock);
 	vp_modern_remove(mdev);
 }
diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c
index 7de8b1ebabac..0d3dbfaf4b23 100644
--- a/drivers/virtio/virtio_pci_modern_dev.c
+++ b/drivers/virtio/virtio_pci_modern_dev.c
@@ -207,6 +207,10 @@ static inline void check_offsets(void)
 		     offsetof(struct virtio_pci_modern_common_cfg, queue_notify_data));
 	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_RESET !=
 		     offsetof(struct virtio_pci_modern_common_cfg, queue_reset));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_ADM_Q_IDX !=
+		     offsetof(struct virtio_pci_modern_common_cfg, admin_queue_index));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_ADM_Q_NUM !=
+		     offsetof(struct virtio_pci_modern_common_cfg, admin_queue_num));
 }
 
 /*
@@ -296,7 +300,7 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev)
 	mdev->common = vp_modern_map_capability(mdev, common,
 			      sizeof(struct virtio_pci_common_cfg), 4, 0,
 			      offsetofend(struct virtio_pci_modern_common_cfg,
-					  queue_reset),
+					  admin_queue_num),
 			      &mdev->common_len, NULL);
 	if (!mdev->common)
 		goto err_map_common;
@@ -719,6 +723,24 @@ void __iomem *vp_modern_map_vq_notify(struct virtio_pci_modern_device *mdev,
 }
 EXPORT_SYMBOL_GPL(vp_modern_map_vq_notify);
 
+u16 vp_modern_avq_num(struct virtio_pci_modern_device *mdev)
+{
+	struct virtio_pci_modern_common_cfg __iomem *cfg;
+
+	cfg = (struct virtio_pci_modern_common_cfg __iomem *)mdev->common;
+	return vp_ioread16(&cfg->admin_queue_num);
+}
+EXPORT_SYMBOL_GPL(vp_modern_avq_num);
+
+u16 vp_modern_avq_index(struct virtio_pci_modern_device *mdev)
+{
+	struct virtio_pci_modern_common_cfg __iomem *cfg;
+
+	cfg = (struct virtio_pci_modern_common_cfg __iomem *)mdev->common;
+	return vp_ioread16(&cfg->admin_queue_index);
+}
+EXPORT_SYMBOL_GPL(vp_modern_avq_index);
+
 MODULE_VERSION("0.1");
 MODULE_DESCRIPTION("Modern Virtio PCI Device");
 MODULE_AUTHOR("Jason Wang <jasowang@redhat.com>");
diff --git a/drivers/w1/masters/Kconfig b/drivers/w1/masters/Kconfig
index ad316573288a..513c0b114337 100644
--- a/drivers/w1/masters/Kconfig
+++ b/drivers/w1/masters/Kconfig
@@ -5,6 +5,17 @@
 
 menu "1-wire Bus Masters"
 
+config W1_MASTER_AMD_AXI
+	tristate "AMD AXI 1-wire bus host"
+	help
+	  Say Y here is you want to support the AMD AXI 1-wire IP core.
+	  This driver makes use of the programmable logic IP to perform
+	  correctly timed 1 wire transactions without relying on GPIO timing
+	  through the kernel.
+
+	  This driver can also be built as a module.  If so, the module will be
+	  called amd_w1_axi.
+
 config W1_MASTER_MATROX
 	tristate "Matrox G400 transport layer for 1-wire"
 	depends on PCI
diff --git a/drivers/w1/masters/Makefile b/drivers/w1/masters/Makefile
index c5d85a827e52..6c5a21f9b88c 100644
--- a/drivers/w1/masters/Makefile
+++ b/drivers/w1/masters/Makefile
@@ -3,6 +3,7 @@
 # Makefile for 1-wire bus master drivers.
 #
 
+obj-$(CONFIG_W1_MASTER_AMD_AXI)		+= amd_axi_w1.o
 obj-$(CONFIG_W1_MASTER_MATROX)		+= matrox_w1.o
 obj-$(CONFIG_W1_MASTER_DS2490)		+= ds2490.o
 obj-$(CONFIG_W1_MASTER_DS2482)		+= ds2482.o
diff --git a/drivers/w1/masters/amd_axi_w1.c b/drivers/w1/masters/amd_axi_w1.c
new file mode 100644
index 000000000000..4d3a68ca9263
--- /dev/null
+++ b/drivers/w1/masters/amd_axi_w1.c
@@ -0,0 +1,396 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * amd_axi_w1 - AMD 1Wire programmable logic bus host driver
+ *
+ * Copyright (C) 2022-2023 Advanced Micro Devices, Inc. All Rights Reserved.
+ */
+
+#include <linux/atomic.h>
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/types.h>
+#include <linux/wait.h>
+
+#include <linux/w1.h>
+
+/* 1-wire AMD IP definition */
+#define AXIW1_IPID	0x10ee4453
+/* Registers offset */
+#define AXIW1_INST_REG	0x0
+#define AXIW1_CTRL_REG	0x4
+#define AXIW1_IRQE_REG	0x8
+#define AXIW1_STAT_REG	0xC
+#define AXIW1_DATA_REG	0x10
+#define AXIW1_IPVER_REG	0x18
+#define AXIW1_IPID_REG	0x1C
+/* Instructions */
+#define AXIW1_INITPRES	0x0800
+#define AXIW1_READBIT	0x0C00
+#define AXIW1_WRITEBIT	0x0E00
+#define AXIW1_READBYTE	0x0D00
+#define AXIW1_WRITEBYTE	0x0F00
+/* Status flag masks */
+#define AXIW1_DONE	BIT(0)
+#define AXIW1_READY	BIT(4)
+#define AXIW1_PRESENCE	BIT(31)
+#define AXIW1_MAJORVER_MASK	GENMASK(23, 8)
+#define AXIW1_MINORVER_MASK	GENMASK(7, 0)
+/* Control flag */
+#define AXIW1_GO	BIT(0)
+#define AXI_CLEAR	0
+#define AXI_RESET	BIT(31)
+#define AXIW1_READDATA	BIT(0)
+/* Interrupt Enable */
+#define AXIW1_READY_IRQ_EN	BIT(4)
+#define AXIW1_DONE_IRQ_EN	BIT(0)
+
+#define AXIW1_TIMEOUT	msecs_to_jiffies(100)
+
+#define DRIVER_NAME	"amd_axi_w1"
+
+struct amd_axi_w1_local {
+	struct device *dev;
+	void __iomem *base_addr;
+	int irq;
+	atomic_t flag;			/* Set on IRQ, cleared once serviced */
+	wait_queue_head_t wait_queue;
+	struct w1_bus_master bus_host;
+};
+
+/**
+ * amd_axi_w1_wait_irq_interruptible_timeout() - Wait for IRQ with timeout.
+ *
+ * @amd_axi_w1_local:	Pointer to device structure
+ * @IRQ:		IRQ channel to wait on
+ *
+ * Return:		%0 - OK, %-EINTR - Interrupted, %-EBUSY - Timed out
+ */
+static int amd_axi_w1_wait_irq_interruptible_timeout(struct amd_axi_w1_local *amd_axi_w1_local,
+						     u32 IRQ)
+{
+	int ret;
+
+	/* Enable the IRQ requested and wait for flag to indicate it's been triggered */
+	iowrite32(IRQ, amd_axi_w1_local->base_addr + AXIW1_IRQE_REG);
+	ret = wait_event_interruptible_timeout(amd_axi_w1_local->wait_queue,
+					       atomic_read(&amd_axi_w1_local->flag) != 0,
+					       AXIW1_TIMEOUT);
+	if (ret < 0) {
+		dev_err(amd_axi_w1_local->dev, "Wait IRQ Interrupted\n");
+		return -EINTR;
+	}
+
+	if (!ret) {
+		dev_err(amd_axi_w1_local->dev, "Wait IRQ Timeout\n");
+		return -EBUSY;
+	}
+
+	atomic_set(&amd_axi_w1_local->flag, 0);
+	return 0;
+}
+
+/**
+ * amd_axi_w1_touch_bit() - Performs the touch-bit function - write a 0 or 1 and reads the level.
+ *
+ * @data:	Pointer to device structure
+ * @bit:	The level to write
+ *
+ * Return:	The level read
+ */
+static u8 amd_axi_w1_touch_bit(void *data, u8 bit)
+{
+	struct amd_axi_w1_local *amd_axi_w1_local = data;
+	u8 val = 0;
+	int rc;
+
+	/* Wait for READY signal to be 1 to ensure 1-wire IP is ready */
+	while ((ioread32(amd_axi_w1_local->base_addr + AXIW1_STAT_REG) & AXIW1_READY) == 0) {
+		rc = amd_axi_w1_wait_irq_interruptible_timeout(amd_axi_w1_local,
+							       AXIW1_READY_IRQ_EN);
+		if (rc < 0)
+			return 1; /* Callee doesn't test for error. Return inactive bus state */
+	}
+
+	if (bit)
+		/* Read. Write read Bit command in register 0 */
+		iowrite32(AXIW1_READBIT, amd_axi_w1_local->base_addr + AXIW1_INST_REG);
+	else
+		/* Write. Write tx Bit command in instruction register with bit to transmit */
+		iowrite32(AXIW1_WRITEBIT + (bit & 0x01),
+			  amd_axi_w1_local->base_addr + AXIW1_INST_REG);
+
+	/* Write Go signal and clear control reset signal in control register */
+	iowrite32(AXIW1_GO, amd_axi_w1_local->base_addr + AXIW1_CTRL_REG);
+
+	/* Wait for done signal to be 1 */
+	while ((ioread32(amd_axi_w1_local->base_addr + AXIW1_STAT_REG) & AXIW1_DONE) != 1) {
+		rc = amd_axi_w1_wait_irq_interruptible_timeout(amd_axi_w1_local, AXIW1_DONE_IRQ_EN);
+		if (rc < 0)
+			return 1; /* Callee doesn't test for error. Return inactive bus state */
+	}
+
+	/* If read, Retrieve data from register */
+	if (bit)
+		val = (u8)(ioread32(amd_axi_w1_local->base_addr + AXIW1_DATA_REG) & AXIW1_READDATA);
+
+	/* Clear Go signal in register 1 */
+	iowrite32(AXI_CLEAR, amd_axi_w1_local->base_addr + AXIW1_CTRL_REG);
+
+	return val;
+}
+
+/**
+ * amd_axi_w1_read_byte - Performs the read byte function.
+ *
+ * @data:	Pointer to device structure
+ * Return:	The value read
+ */
+static u8 amd_axi_w1_read_byte(void *data)
+{
+	struct amd_axi_w1_local *amd_axi_w1_local = data;
+	u8 val = 0;
+	int rc;
+
+	/* Wait for READY signal to be 1 to ensure 1-wire IP is ready */
+	while ((ioread32(amd_axi_w1_local->base_addr + AXIW1_STAT_REG) & AXIW1_READY) == 0) {
+		rc = amd_axi_w1_wait_irq_interruptible_timeout(amd_axi_w1_local,
+							       AXIW1_READY_IRQ_EN);
+		if (rc < 0)
+			return 0xFF; /* Return inactive bus state */
+	}
+
+	/* Write read Byte command in instruction register*/
+	iowrite32(AXIW1_READBYTE, amd_axi_w1_local->base_addr + AXIW1_INST_REG);
+
+	/* Write Go signal and clear control reset signal in control register */
+	iowrite32(AXIW1_GO, amd_axi_w1_local->base_addr + AXIW1_CTRL_REG);
+
+	/* Wait for done signal to be 1 */
+	while ((ioread32(amd_axi_w1_local->base_addr + AXIW1_STAT_REG) & AXIW1_DONE) != 1) {
+		rc = amd_axi_w1_wait_irq_interruptible_timeout(amd_axi_w1_local, AXIW1_DONE_IRQ_EN);
+		if (rc < 0)
+			return 0xFF; /* Return inactive bus state */
+	}
+
+	/* Retrieve LSB bit in data register to get RX byte */
+	val = (u8)(ioread32(amd_axi_w1_local->base_addr + AXIW1_DATA_REG) & 0x000000FF);
+
+	/* Clear Go signal in control register */
+	iowrite32(AXI_CLEAR, amd_axi_w1_local->base_addr + AXIW1_CTRL_REG);
+
+	return val;
+}
+
+/**
+ * amd_axi_w1_write_byte - Performs the write byte function.
+ *
+ * @data:	The ds2482 channel pointer
+ * @val:	The value to write
+ */
+static void amd_axi_w1_write_byte(void *data, u8 val)
+{
+	struct amd_axi_w1_local *amd_axi_w1_local = data;
+	int rc;
+
+	/* Wait for READY signal to be 1 to ensure 1-wire IP is ready */
+	while ((ioread32(amd_axi_w1_local->base_addr + AXIW1_STAT_REG) & AXIW1_READY) == 0) {
+		rc = amd_axi_w1_wait_irq_interruptible_timeout(amd_axi_w1_local,
+							       AXIW1_READY_IRQ_EN);
+		if (rc < 0)
+			return;
+	}
+
+	/* Write tx Byte command in instruction register with bit to transmit */
+	iowrite32(AXIW1_WRITEBYTE + val, amd_axi_w1_local->base_addr + AXIW1_INST_REG);
+
+	/* Write Go signal and clear control reset signal in register 1 */
+	iowrite32(AXIW1_GO, amd_axi_w1_local->base_addr + AXIW1_CTRL_REG);
+
+	/* Wait for done signal to be 1 */
+	while ((ioread32(amd_axi_w1_local->base_addr + AXIW1_STAT_REG) & AXIW1_DONE) != 1) {
+		rc = amd_axi_w1_wait_irq_interruptible_timeout(amd_axi_w1_local,
+							       AXIW1_DONE_IRQ_EN);
+		if (rc < 0)
+			return;
+	}
+
+	/* Clear Go signal in control register */
+	iowrite32(AXI_CLEAR, amd_axi_w1_local->base_addr + AXIW1_CTRL_REG);
+}
+
+/**
+ * amd_axi_w1_reset_bus() - Issues a reset bus sequence.
+ *
+ * @data:	the bus host data struct
+ * Return:	0=Device present, 1=No device present or error
+ */
+static u8 amd_axi_w1_reset_bus(void *data)
+{
+	struct amd_axi_w1_local *amd_axi_w1_local = data;
+	u8 val = 0;
+	int rc;
+
+	/* Reset 1-wire Axi IP */
+	iowrite32(AXI_RESET, amd_axi_w1_local->base_addr + AXIW1_CTRL_REG);
+
+	/* Wait for READY signal to be 1 to ensure 1-wire IP is ready */
+	while ((ioread32(amd_axi_w1_local->base_addr + AXIW1_STAT_REG) & AXIW1_READY) == 0) {
+		rc = amd_axi_w1_wait_irq_interruptible_timeout(amd_axi_w1_local,
+							       AXIW1_READY_IRQ_EN);
+		if (rc < 0)
+			return 1; /* Something went wrong with the hardware */
+	}
+	/* Write Initialization command in instruction register */
+	iowrite32(AXIW1_INITPRES, amd_axi_w1_local->base_addr + AXIW1_INST_REG);
+
+	/* Write Go signal and clear control reset signal in register 1 */
+	iowrite32(AXIW1_GO, amd_axi_w1_local->base_addr + AXIW1_CTRL_REG);
+
+	/* Wait for done signal to be 1 */
+	while ((ioread32(amd_axi_w1_local->base_addr + AXIW1_STAT_REG) & AXIW1_DONE) != 1) {
+		rc = amd_axi_w1_wait_irq_interruptible_timeout(amd_axi_w1_local, AXIW1_DONE_IRQ_EN);
+		if (rc < 0)
+			return 1; /* Something went wrong with the hardware */
+	}
+	/* Retrieve MSB bit in status register to get failure bit */
+	if ((ioread32(amd_axi_w1_local->base_addr + AXIW1_STAT_REG) & AXIW1_PRESENCE) != 0)
+		val = 1;
+
+	/* Clear Go signal in control register */
+	iowrite32(AXI_CLEAR, amd_axi_w1_local->base_addr + AXIW1_CTRL_REG);
+
+	return val;
+}
+
+/* Reset the 1-wire AXI IP. Put the IP in reset state and clear registers */
+static void amd_axi_w1_reset(struct amd_axi_w1_local *amd_axi_w1_local)
+{
+	iowrite32(AXI_RESET, amd_axi_w1_local->base_addr + AXIW1_CTRL_REG);
+	iowrite32(AXI_CLEAR, amd_axi_w1_local->base_addr + AXIW1_INST_REG);
+	iowrite32(AXI_CLEAR, amd_axi_w1_local->base_addr + AXIW1_IRQE_REG);
+	iowrite32(AXI_CLEAR, amd_axi_w1_local->base_addr + AXIW1_STAT_REG);
+	iowrite32(AXI_CLEAR, amd_axi_w1_local->base_addr + AXIW1_DATA_REG);
+}
+
+static irqreturn_t amd_axi_w1_irq(int irq, void *lp)
+{
+	struct amd_axi_w1_local *amd_axi_w1_local = lp;
+
+	/* Reset interrupt trigger */
+	iowrite32(AXI_CLEAR, amd_axi_w1_local->base_addr + AXIW1_IRQE_REG);
+
+	atomic_set(&amd_axi_w1_local->flag, 1);
+	wake_up_interruptible(&amd_axi_w1_local->wait_queue);
+
+	return IRQ_HANDLED;
+}
+
+static int amd_axi_w1_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct amd_axi_w1_local *lp;
+	struct clk *clk;
+	u32 ver_major, ver_minor;
+	int val, rc = 0;
+
+	lp = devm_kzalloc(dev, sizeof(*lp), GFP_KERNEL);
+	if (!lp)
+		return -ENOMEM;
+
+	lp->dev = dev;
+	lp->base_addr = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(lp->base_addr))
+		return PTR_ERR(lp->base_addr);
+
+	lp->irq = platform_get_irq(pdev, 0);
+	if (lp->irq < 0)
+		return lp->irq;
+
+	rc = devm_request_irq(dev, lp->irq, &amd_axi_w1_irq, IRQF_TRIGGER_HIGH, DRIVER_NAME, lp);
+	if (rc)
+		return rc;
+
+	/* Initialize wait queue and flag */
+	init_waitqueue_head(&lp->wait_queue);
+
+	clk = devm_clk_get_enabled(dev, NULL);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	/* Verify IP presence in HW */
+	if (ioread32(lp->base_addr + AXIW1_IPID_REG) != AXIW1_IPID) {
+		dev_err(dev, "AMD 1-wire IP not detected in hardware\n");
+		return -ENODEV;
+	}
+
+	/*
+	 * Allow for future driver expansion supporting new hardware features
+	 * This driver currently only supports hardware 1.x, but include logic
+	 * to detect if a potentially incompatible future version is used
+	 * by reading major version ID. It is highly undesirable for new IP versions
+	 * to break the API, but this code will at least allow for graceful failure
+	 * should that happen. Future new features can be enabled by hardware
+	 * incrementing the minor version and augmenting the driver to detect capability
+	 * using the minor version number
+	 */
+	val = ioread32(lp->base_addr + AXIW1_IPVER_REG);
+	ver_major = FIELD_GET(AXIW1_MAJORVER_MASK, val);
+	ver_minor = FIELD_GET(AXIW1_MINORVER_MASK, val);
+
+	if (ver_major != 1) {
+		dev_err(dev, "AMD AXI W1 host version %u.%u is not supported by this driver",
+			ver_major, ver_minor);
+		return -ENODEV;
+	}
+
+	lp->bus_host.data = lp;
+	lp->bus_host.touch_bit = amd_axi_w1_touch_bit;
+	lp->bus_host.read_byte = amd_axi_w1_read_byte;
+	lp->bus_host.write_byte = amd_axi_w1_write_byte;
+	lp->bus_host.reset_bus = amd_axi_w1_reset_bus;
+
+	amd_axi_w1_reset(lp);
+
+	platform_set_drvdata(pdev, lp);
+	rc = w1_add_master_device(&lp->bus_host);
+	if (rc) {
+		dev_err(dev, "Could not add host device\n");
+		return rc;
+	}
+
+	return 0;
+}
+
+static void amd_axi_w1_remove(struct platform_device *pdev)
+{
+	struct amd_axi_w1_local *lp = platform_get_drvdata(pdev);
+
+	w1_remove_master_device(&lp->bus_host);
+}
+
+static const struct of_device_id amd_axi_w1_of_match[] = {
+	{ .compatible = "amd,axi-1wire-host" },
+	{ /* end of list */ },
+};
+MODULE_DEVICE_TABLE(of, amd_axi_w1_of_match);
+
+static struct platform_driver amd_axi_w1_driver = {
+	.probe = amd_axi_w1_probe,
+	.remove_new = amd_axi_w1_remove,
+	.driver = {
+		.name = DRIVER_NAME,
+		.of_match_table = amd_axi_w1_of_match,
+	},
+};
+module_platform_driver(amd_axi_w1_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Kris Chaplin <kris.chaplin@amd.com>");
+MODULE_DESCRIPTION("Driver for AMD AXI 1 Wire IP core");
diff --git a/drivers/w1/masters/ds2490.c b/drivers/w1/masters/ds2490.c
index 5f5b97e24700..e1cac0730cbb 100644
--- a/drivers/w1/masters/ds2490.c
+++ b/drivers/w1/masters/ds2490.c
@@ -98,6 +98,8 @@
 #define ST_EPOF				0x80
 /* Status transfer size, 16 bytes status, 16 byte result flags */
 #define ST_SIZE				0x20
+/* 1-wire data i/o fifo size, 128 bytes */
+#define FIFO_SIZE			0x80
 
 /* Result Register flags */
 #define RR_DETECT			0xA5 /* New device detected */
@@ -614,14 +616,11 @@ static int ds_read_byte(struct ds_device *dev, u8 *byte)
 	return 0;
 }
 
-static int ds_read_block(struct ds_device *dev, u8 *buf, int len)
+static int read_block_chunk(struct ds_device *dev, u8 *buf, int len)
 {
 	struct ds_status st;
 	int err;
 
-	if (len > 64*1024)
-		return -E2BIG;
-
 	memset(buf, 0xFF, len);
 
 	err = ds_send_data(dev, buf, len);
@@ -640,6 +639,24 @@ static int ds_read_block(struct ds_device *dev, u8 *buf, int len)
 	return err;
 }
 
+static int ds_read_block(struct ds_device *dev, u8 *buf, int len)
+{
+	int err, to_read, rem = len;
+
+	if (len > 64 * 1024)
+		return -E2BIG;
+
+	do {
+		to_read = rem <= FIFO_SIZE ? rem : FIFO_SIZE;
+		err = read_block_chunk(dev, &buf[len - rem], to_read);
+		if (err < 0)
+			return err;
+		rem -= to_read;
+	} while (rem);
+
+	return err;
+}
+
 static int ds_write_block(struct ds_device *dev, u8 *buf, int len)
 {
 	int err;
diff --git a/drivers/w1/masters/w1-gpio.c b/drivers/w1/masters/w1-gpio.c
index e45acb6d916e..05c67038ed20 100644
--- a/drivers/w1/masters/w1-gpio.c
+++ b/drivers/w1/masters/w1-gpio.c
@@ -9,7 +9,6 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
-#include <linux/w1-gpio.h>
 #include <linux/gpio/consumer.h>
 #include <linux/of_platform.h>
 #include <linux/err.h>
@@ -18,27 +17,33 @@
 
 #include <linux/w1.h>
 
+struct w1_gpio_ddata {
+	struct gpio_desc *gpiod;
+	struct gpio_desc *pullup_gpiod;
+	unsigned int pullup_duration;
+};
+
 static u8 w1_gpio_set_pullup(void *data, int delay)
 {
-	struct w1_gpio_platform_data *pdata = data;
+	struct w1_gpio_ddata *ddata = data;
 
 	if (delay) {
-		pdata->pullup_duration = delay;
+		ddata->pullup_duration = delay;
 	} else {
-		if (pdata->pullup_duration) {
+		if (ddata->pullup_duration) {
 			/*
 			 * This will OVERRIDE open drain emulation and force-pull
 			 * the line high for some time.
 			 */
-			gpiod_set_raw_value(pdata->gpiod, 1);
-			msleep(pdata->pullup_duration);
+			gpiod_set_raw_value(ddata->gpiod, 1);
+			msleep(ddata->pullup_duration);
 			/*
 			 * This will simply set the line as input since we are doing
 			 * open drain emulation in the GPIO library.
 			 */
-			gpiod_set_value(pdata->gpiod, 1);
+			gpiod_set_value(ddata->gpiod, 1);
 		}
-		pdata->pullup_duration = 0;
+		ddata->pullup_duration = 0;
 	}
 
 	return 0;
@@ -46,16 +51,16 @@ static u8 w1_gpio_set_pullup(void *data, int delay)
 
 static void w1_gpio_write_bit(void *data, u8 bit)
 {
-	struct w1_gpio_platform_data *pdata = data;
+	struct w1_gpio_ddata *ddata = data;
 
-	gpiod_set_value(pdata->gpiod, bit);
+	gpiod_set_value(ddata->gpiod, bit);
 }
 
 static u8 w1_gpio_read_bit(void *data)
 {
-	struct w1_gpio_platform_data *pdata = data;
+	struct w1_gpio_ddata *ddata = data;
 
-	return gpiod_get_value(pdata->gpiod) ? 1 : 0;
+	return gpiod_get_value(ddata->gpiod) ? 1 : 0;
 }
 
 #if defined(CONFIG_OF)
@@ -69,58 +74,48 @@ MODULE_DEVICE_TABLE(of, w1_gpio_dt_ids);
 static int w1_gpio_probe(struct platform_device *pdev)
 {
 	struct w1_bus_master *master;
-	struct w1_gpio_platform_data *pdata;
+	struct w1_gpio_ddata *ddata;
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
 	/* Enforce open drain mode by default */
 	enum gpiod_flags gflags = GPIOD_OUT_LOW_OPEN_DRAIN;
 	int err;
 
-	if (of_have_populated_dt()) {
-		pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
-		if (!pdata)
-			return -ENOMEM;
-
-		/*
-		 * This parameter means that something else than the gpiolib has
-		 * already set the line into open drain mode, so we should just
-		 * driver it high/low like we are in full control of the line and
-		 * open drain will happen transparently.
-		 */
-		if (of_property_present(np, "linux,open-drain"))
-			gflags = GPIOD_OUT_LOW;
-
-		pdev->dev.platform_data = pdata;
-	}
-	pdata = dev_get_platdata(dev);
+	ddata = devm_kzalloc(&pdev->dev, sizeof(*ddata), GFP_KERNEL);
+	if (!ddata)
+		return -ENOMEM;
 
-	if (!pdata) {
-		dev_err(dev, "No configuration data\n");
-		return -ENXIO;
-	}
+	/*
+	 * This parameter means that something else than the gpiolib has
+	 * already set the line into open drain mode, so we should just
+	 * driver it high/low like we are in full control of the line and
+	 * open drain will happen transparently.
+	 */
+	if (of_property_present(np, "linux,open-drain"))
+		gflags = GPIOD_OUT_LOW;
 
 	master = devm_kzalloc(dev, sizeof(struct w1_bus_master),
 			GFP_KERNEL);
 	if (!master)
 		return -ENOMEM;
 
-	pdata->gpiod = devm_gpiod_get_index(dev, NULL, 0, gflags);
-	if (IS_ERR(pdata->gpiod)) {
+	ddata->gpiod = devm_gpiod_get_index(dev, NULL, 0, gflags);
+	if (IS_ERR(ddata->gpiod)) {
 		dev_err(dev, "gpio_request (pin) failed\n");
-		return PTR_ERR(pdata->gpiod);
+		return PTR_ERR(ddata->gpiod);
 	}
 
-	pdata->pullup_gpiod =
+	ddata->pullup_gpiod =
 		devm_gpiod_get_index_optional(dev, NULL, 1, GPIOD_OUT_LOW);
-	if (IS_ERR(pdata->pullup_gpiod)) {
+	if (IS_ERR(ddata->pullup_gpiod)) {
 		dev_err(dev, "gpio_request_one "
 			"(ext_pullup_enable_pin) failed\n");
-		return PTR_ERR(pdata->pullup_gpiod);
+		return PTR_ERR(ddata->pullup_gpiod);
 	}
 
-	master->data = pdata;
+	master->data = ddata;
 	master->read_bit = w1_gpio_read_bit;
-	gpiod_direction_output(pdata->gpiod, 1);
+	gpiod_direction_output(ddata->gpiod, 1);
 	master->write_bit = w1_gpio_write_bit;
 
 	/*
@@ -138,11 +133,8 @@ static int w1_gpio_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	if (pdata->enable_external_pullup)
-		pdata->enable_external_pullup(1);
-
-	if (pdata->pullup_gpiod)
-		gpiod_set_value(pdata->pullup_gpiod, 1);
+	if (ddata->pullup_gpiod)
+		gpiod_set_value(ddata->pullup_gpiod, 1);
 
 	platform_set_drvdata(pdev, master);
 
@@ -152,45 +144,19 @@ static int w1_gpio_probe(struct platform_device *pdev)
 static int w1_gpio_remove(struct platform_device *pdev)
 {
 	struct w1_bus_master *master = platform_get_drvdata(pdev);
-	struct w1_gpio_platform_data *pdata = dev_get_platdata(&pdev->dev);
-
-	if (pdata->enable_external_pullup)
-		pdata->enable_external_pullup(0);
+	struct w1_gpio_ddata *ddata = master->data;
 
-	if (pdata->pullup_gpiod)
-		gpiod_set_value(pdata->pullup_gpiod, 0);
+	if (ddata->pullup_gpiod)
+		gpiod_set_value(ddata->pullup_gpiod, 0);
 
 	w1_remove_master_device(master);
 
 	return 0;
 }
 
-static int __maybe_unused w1_gpio_suspend(struct device *dev)
-{
-	struct w1_gpio_platform_data *pdata = dev_get_platdata(dev);
-
-	if (pdata->enable_external_pullup)
-		pdata->enable_external_pullup(0);
-
-	return 0;
-}
-
-static int __maybe_unused w1_gpio_resume(struct device *dev)
-{
-	struct w1_gpio_platform_data *pdata = dev_get_platdata(dev);
-
-	if (pdata->enable_external_pullup)
-		pdata->enable_external_pullup(1);
-
-	return 0;
-}
-
-static SIMPLE_DEV_PM_OPS(w1_gpio_pm_ops, w1_gpio_suspend, w1_gpio_resume);
-
 static struct platform_driver w1_gpio_driver = {
 	.driver = {
 		.name	= "w1-gpio",
-		.pm	= &w1_gpio_pm_ops,
 		.of_match_table = of_match_ptr(w1_gpio_dt_ids),
 	},
 	.probe = w1_gpio_probe,
diff --git a/drivers/w1/slaves/w1_ds2433.c b/drivers/w1/slaves/w1_ds2433.c
index 9f21fd98f799..250b7f7ec429 100644
--- a/drivers/w1/slaves/w1_ds2433.c
+++ b/drivers/w1/slaves/w1_ds2433.c
@@ -1,8 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- *	w1_ds2433.c - w1 family 23 (DS2433) driver
+ *	w1_ds2433.c - w1 family 23 (DS2433) & 43 (DS28EC20) eeprom driver
  *
  * Copyright (c) 2005 Ben Gardner <bgardner@wabtec.com>
+ * Copyright (c) 2023 Marc Ferland <marc.ferland@sonatest.com>
  */
 
 #include <linux/kernel.h>
@@ -23,23 +24,45 @@
 #include <linux/w1.h>
 
 #define W1_EEPROM_DS2433	0x23
+#define W1_EEPROM_DS28EC20	0x43
+
+#define W1_EEPROM_DS2433_SIZE	512
+#define W1_EEPROM_DS28EC20_SIZE 2560
 
-#define W1_EEPROM_SIZE		512
-#define W1_PAGE_COUNT		16
 #define W1_PAGE_SIZE		32
 #define W1_PAGE_BITS		5
 #define W1_PAGE_MASK		0x1F
-
-#define W1_F23_TIME		300
+#define W1_VALIDCRC_MAX		96
 
 #define W1_F23_READ_EEPROM	0xF0
 #define W1_F23_WRITE_SCRATCH	0x0F
 #define W1_F23_READ_SCRATCH	0xAA
 #define W1_F23_COPY_SCRATCH	0x55
 
+struct ds2433_config {
+	size_t eeprom_size;		/* eeprom size in bytes */
+	unsigned int page_count;	/* number of 256 bits pages */
+	unsigned int tprog;		/* time in ms for page programming */
+};
+
+static const struct ds2433_config config_f23 = {
+	.eeprom_size = W1_EEPROM_DS2433_SIZE,
+	.page_count = 16,
+	.tprog = 5,
+};
+
+static const struct ds2433_config config_f43 = {
+	.eeprom_size = W1_EEPROM_DS28EC20_SIZE,
+	.page_count = 80,
+	.tprog = 10,
+};
+
 struct w1_f23_data {
-	u8	memory[W1_EEPROM_SIZE];
-	u32	validcrc;
+#ifdef CONFIG_W1_SLAVE_DS2433_CRC
+	u8 *memory;
+	DECLARE_BITMAP(validcrc, W1_VALIDCRC_MAX);
+#endif
+	const struct ds2433_config *cfg;
 };
 
 /*
@@ -64,11 +87,11 @@ static int w1_f23_refresh_block(struct w1_slave *sl, struct w1_f23_data *data,
 	u8	wrbuf[3];
 	int	off = block * W1_PAGE_SIZE;
 
-	if (data->validcrc & (1 << block))
+	if (test_bit(block, data->validcrc))
 		return 0;
 
 	if (w1_reset_select_slave(sl)) {
-		data->validcrc = 0;
+		bitmap_zero(data->validcrc, data->cfg->page_count);
 		return -EIO;
 	}
 
@@ -80,7 +103,7 @@ static int w1_f23_refresh_block(struct w1_slave *sl, struct w1_f23_data *data,
 
 	/* cache the block if the CRC is valid */
 	if (crc16(CRC16_INIT, &data->memory[off], W1_PAGE_SIZE) == CRC16_VALID)
-		data->validcrc |= (1 << block);
+		set_bit(block, data->validcrc);
 
 	return 0;
 }
@@ -98,7 +121,7 @@ static ssize_t eeprom_read(struct file *filp, struct kobject *kobj,
 	u8 wrbuf[3];
 #endif
 
-	count = w1_f23_fix_count(off, count, W1_EEPROM_SIZE);
+	count = w1_f23_fix_count(off, count, bin_attr->size);
 	if (!count)
 		return 0;
 
@@ -153,9 +176,7 @@ out_up:
  */
 static int w1_f23_write(struct w1_slave *sl, int addr, int len, const u8 *data)
 {
-#ifdef CONFIG_W1_SLAVE_DS2433_CRC
 	struct w1_f23_data *f23 = sl->family_data;
-#endif
 	u8 wrbuf[4];
 	u8 rdbuf[W1_PAGE_SIZE + 3];
 	u8 es = (addr + len - 1) & 0x1f;
@@ -191,13 +212,13 @@ static int w1_f23_write(struct w1_slave *sl, int addr, int len, const u8 *data)
 	wrbuf[3] = es;
 	w1_write_block(sl->master, wrbuf, 4);
 
-	/* Sleep for 5 ms to wait for the write to complete */
-	msleep(5);
+	/* Sleep for tprog ms to wait for the write to complete */
+	msleep(f23->cfg->tprog);
 
 	/* Reset the bus to wake up the EEPROM (this may not be needed) */
 	w1_reset_bus(sl->master);
 #ifdef CONFIG_W1_SLAVE_DS2433_CRC
-	f23->validcrc &= ~(1 << (addr >> W1_PAGE_BITS));
+	clear_bit(addr >> W1_PAGE_BITS, f23->validcrc);
 #endif
 	return 0;
 }
@@ -209,7 +230,7 @@ static ssize_t eeprom_write(struct file *filp, struct kobject *kobj,
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
 	int addr, len, idx;
 
-	count = w1_f23_fix_count(off, count, W1_EEPROM_SIZE);
+	count = w1_f23_fix_count(off, count, bin_attr->size);
 	if (!count)
 		return 0;
 
@@ -253,10 +274,22 @@ out_up:
 	return count;
 }
 
-static BIN_ATTR_RW(eeprom, W1_EEPROM_SIZE);
+static struct bin_attribute bin_attr_f23_eeprom = {
+	.attr = { .name = "eeprom", .mode = 0644 },
+	.read = eeprom_read,
+	.write = eeprom_write,
+	.size = W1_EEPROM_DS2433_SIZE,
+};
+
+static struct bin_attribute bin_attr_f43_eeprom = {
+	.attr = { .name = "eeprom", .mode = 0644 },
+	.read = eeprom_read,
+	.write = eeprom_write,
+	.size = W1_EEPROM_DS28EC20_SIZE,
+};
 
 static struct bin_attribute *w1_f23_bin_attributes[] = {
-	&bin_attr_eeprom,
+	&bin_attr_f23_eeprom,
 	NULL,
 };
 
@@ -269,26 +302,63 @@ static const struct attribute_group *w1_f23_groups[] = {
 	NULL,
 };
 
+static struct bin_attribute *w1_f43_bin_attributes[] = {
+	&bin_attr_f43_eeprom,
+	NULL,
+};
+
+static const struct attribute_group w1_f43_group = {
+	.bin_attrs = w1_f43_bin_attributes,
+};
+
+static const struct attribute_group *w1_f43_groups[] = {
+	&w1_f43_group,
+	NULL,
+};
+
 static int w1_f23_add_slave(struct w1_slave *sl)
 {
-#ifdef CONFIG_W1_SLAVE_DS2433_CRC
 	struct w1_f23_data *data;
 
 	data = kzalloc(sizeof(struct w1_f23_data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
+
+	switch (sl->family->fid) {
+	case W1_EEPROM_DS2433:
+		data->cfg = &config_f23;
+		break;
+	case W1_EEPROM_DS28EC20:
+		data->cfg = &config_f43;
+		break;
+	}
+
+#ifdef CONFIG_W1_SLAVE_DS2433_CRC
+	if (data->cfg->page_count > W1_VALIDCRC_MAX) {
+		dev_err(&sl->dev, "page count too big for crc bitmap\n");
+		kfree(data);
+		return -EINVAL;
+	}
+	data->memory = kzalloc(data->cfg->eeprom_size, GFP_KERNEL);
+	if (!data->memory) {
+		kfree(data);
+		return -ENOMEM;
+	}
+	bitmap_zero(data->validcrc, data->cfg->page_count);
+#endif /* CONFIG_W1_SLAVE_DS2433_CRC */
 	sl->family_data = data;
 
-#endif	/* CONFIG_W1_SLAVE_DS2433_CRC */
 	return 0;
 }
 
 static void w1_f23_remove_slave(struct w1_slave *sl)
 {
-#ifdef CONFIG_W1_SLAVE_DS2433_CRC
-	kfree(sl->family_data);
+	struct w1_f23_data *data = sl->family_data;
 	sl->family_data = NULL;
-#endif	/* CONFIG_W1_SLAVE_DS2433_CRC */
+#ifdef CONFIG_W1_SLAVE_DS2433_CRC
+	kfree(data->memory);
+#endif /* CONFIG_W1_SLAVE_DS2433_CRC */
+	kfree(data);
 }
 
 static const struct w1_family_ops w1_f23_fops = {
@@ -297,13 +367,53 @@ static const struct w1_family_ops w1_f23_fops = {
 	.groups		= w1_f23_groups,
 };
 
+static const struct w1_family_ops w1_f43_fops = {
+	.add_slave      = w1_f23_add_slave,
+	.remove_slave   = w1_f23_remove_slave,
+	.groups         = w1_f43_groups,
+};
+
 static struct w1_family w1_family_23 = {
 	.fid = W1_EEPROM_DS2433,
 	.fops = &w1_f23_fops,
 };
-module_w1_family(w1_family_23);
+
+static struct w1_family w1_family_43 = {
+	.fid = W1_EEPROM_DS28EC20,
+	.fops = &w1_f43_fops,
+};
+
+static int __init w1_ds2433_init(void)
+{
+	int err;
+
+	err = w1_register_family(&w1_family_23);
+	if (err)
+		return err;
+
+	err = w1_register_family(&w1_family_43);
+	if (err)
+		goto err_43;
+
+	return 0;
+
+err_43:
+	w1_unregister_family(&w1_family_23);
+	return err;
+}
+
+static void __exit w1_ds2433_exit(void)
+{
+	w1_unregister_family(&w1_family_23);
+	w1_unregister_family(&w1_family_43);
+}
+
+module_init(w1_ds2433_init);
+module_exit(w1_ds2433_exit);
 
 MODULE_AUTHOR("Ben Gardner <bgardner@wabtec.com>");
-MODULE_DESCRIPTION("w1 family 23 driver for DS2433, 4kb EEPROM");
+MODULE_AUTHOR("Marc Ferland <marc.ferland@sonatest.com>");
+MODULE_DESCRIPTION("w1 family 23/43 driver for DS2433 (4kb) and DS28EC20 (20kb)");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("w1-family-" __stringify(W1_EEPROM_DS2433));
+MODULE_ALIAS("w1-family-" __stringify(W1_EEPROM_DS28EC20));
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index b8cfea7812d6..3b9f080109d7 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -923,8 +923,8 @@ static void shutdown_pirq(struct irq_data *data)
 		return;
 
 	do_mask(info, EVT_MASK_REASON_EXPLICIT);
-	xen_evtchn_close(evtchn);
 	xen_irq_info_cleanup(info);
+	xen_evtchn_close(evtchn);
 }
 
 static void enable_pirq(struct irq_data *data)
@@ -956,6 +956,7 @@ EXPORT_SYMBOL_GPL(xen_irq_from_gsi);
 static void __unbind_from_irq(struct irq_info *info, unsigned int irq)
 {
 	evtchn_port_t evtchn;
+	bool close_evtchn = false;
 
 	if (!info) {
 		xen_irq_free_desc(irq);
@@ -975,7 +976,7 @@ static void __unbind_from_irq(struct irq_info *info, unsigned int irq)
 		struct xenbus_device *dev;
 
 		if (!info->is_static)
-			xen_evtchn_close(evtchn);
+			close_evtchn = true;
 
 		switch (info->type) {
 		case IRQT_VIRQ:
@@ -995,6 +996,9 @@ static void __unbind_from_irq(struct irq_info *info, unsigned int irq)
 		}
 
 		xen_irq_info_cleanup(info);
+
+		if (close_evtchn)
+			xen_evtchn_close(evtchn);
 	}
 
 	xen_free_irq(info);
diff --git a/drivers/xen/gntalloc.c b/drivers/xen/gntalloc.c
index 26ffb8755ffb..f93f73ecefee 100644
--- a/drivers/xen/gntalloc.c
+++ b/drivers/xen/gntalloc.c
@@ -317,7 +317,7 @@ static long gntalloc_ioctl_alloc(struct gntalloc_file_private_data *priv,
 		rc = -EFAULT;
 		goto out_free;
 	}
-	if (copy_to_user(arg->gref_ids, gref_ids,
+	if (copy_to_user(arg->gref_ids_flex, gref_ids,
 			sizeof(gref_ids[0]) * op.count)) {
 		rc = -EFAULT;
 		goto out_free;
diff --git a/drivers/xen/gntdev-dmabuf.c b/drivers/xen/gntdev-dmabuf.c
index 4440e626b797..42adc2c1e06b 100644
--- a/drivers/xen/gntdev-dmabuf.c
+++ b/drivers/xen/gntdev-dmabuf.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/dma-buf.h>
+#include <linux/dma-direct.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/uaccess.h>
@@ -50,7 +51,7 @@ struct gntdev_dmabuf {
 
 	/* Number of pages this buffer has. */
 	int nr_pages;
-	/* Pages of this buffer. */
+	/* Pages of this buffer (only for dma-buf export). */
 	struct page **pages;
 };
 
@@ -484,7 +485,7 @@ out:
 /* DMA buffer import support. */
 
 static int
-dmabuf_imp_grant_foreign_access(struct page **pages, u32 *refs,
+dmabuf_imp_grant_foreign_access(unsigned long *gfns, u32 *refs,
 				int count, int domid)
 {
 	grant_ref_t priv_gref_head;
@@ -507,7 +508,7 @@ dmabuf_imp_grant_foreign_access(struct page **pages, u32 *refs,
 		}
 
 		gnttab_grant_foreign_access_ref(cur_ref, domid,
-						xen_page_to_gfn(pages[i]), 0);
+						gfns[i], 0);
 		refs[i] = cur_ref;
 	}
 
@@ -529,7 +530,6 @@ static void dmabuf_imp_end_foreign_access(u32 *refs, int count)
 
 static void dmabuf_imp_free_storage(struct gntdev_dmabuf *gntdev_dmabuf)
 {
-	kfree(gntdev_dmabuf->pages);
 	kfree(gntdev_dmabuf->u.imp.refs);
 	kfree(gntdev_dmabuf);
 }
@@ -549,12 +549,6 @@ static struct gntdev_dmabuf *dmabuf_imp_alloc_storage(int count)
 	if (!gntdev_dmabuf->u.imp.refs)
 		goto fail;
 
-	gntdev_dmabuf->pages = kcalloc(count,
-				       sizeof(gntdev_dmabuf->pages[0]),
-				       GFP_KERNEL);
-	if (!gntdev_dmabuf->pages)
-		goto fail;
-
 	gntdev_dmabuf->nr_pages = count;
 
 	for (i = 0; i < count; i++)
@@ -576,7 +570,8 @@ dmabuf_imp_to_refs(struct gntdev_dmabuf_priv *priv, struct device *dev,
 	struct dma_buf *dma_buf;
 	struct dma_buf_attachment *attach;
 	struct sg_table *sgt;
-	struct sg_page_iter sg_iter;
+	struct sg_dma_page_iter sg_iter;
+	unsigned long *gfns;
 	int i;
 
 	dma_buf = dma_buf_get(fd);
@@ -624,26 +619,31 @@ dmabuf_imp_to_refs(struct gntdev_dmabuf_priv *priv, struct device *dev,
 
 	gntdev_dmabuf->u.imp.sgt = sgt;
 
-	/* Now convert sgt to array of pages and check for page validity. */
+	gfns = kcalloc(count, sizeof(*gfns), GFP_KERNEL);
+	if (!gfns) {
+		ret = ERR_PTR(-ENOMEM);
+		goto fail_unmap;
+	}
+
+	/*
+	 * Now convert sgt to array of gfns without accessing underlying pages.
+	 * It is not allowed to access the underlying struct page of an sg table
+	 * exported by DMA-buf, but since we deal with special Xen dma device here
+	 * (not a normal physical one) look at the dma addresses in the sg table
+	 * and then calculate gfns directly from them.
+	 */
 	i = 0;
-	for_each_sgtable_page(sgt, &sg_iter, 0) {
-		struct page *page = sg_page_iter_page(&sg_iter);
-		/*
-		 * Check if page is valid: this can happen if we are given
-		 * a page from VRAM or other resources which are not backed
-		 * by a struct page.
-		 */
-		if (!pfn_valid(page_to_pfn(page))) {
-			ret = ERR_PTR(-EINVAL);
-			goto fail_unmap;
-		}
+	for_each_sgtable_dma_page(sgt, &sg_iter, 0) {
+		dma_addr_t addr = sg_page_iter_dma_address(&sg_iter);
+		unsigned long pfn = bfn_to_pfn(XEN_PFN_DOWN(dma_to_phys(dev, addr)));
 
-		gntdev_dmabuf->pages[i++] = page;
+		gfns[i++] = pfn_to_gfn(pfn);
 	}
 
-	ret = ERR_PTR(dmabuf_imp_grant_foreign_access(gntdev_dmabuf->pages,
+	ret = ERR_PTR(dmabuf_imp_grant_foreign_access(gfns,
 						      gntdev_dmabuf->u.imp.refs,
 						      count, domid));
+	kfree(gfns);
 	if (IS_ERR(ret))
 		goto fail_end_access;
 
diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c
index 508655273145..c63f317e3df3 100644
--- a/drivers/xen/pcpu.c
+++ b/drivers/xen/pcpu.c
@@ -65,7 +65,7 @@ struct pcpu {
 	uint32_t flags;
 };
 
-static struct bus_type xen_pcpu_subsys = {
+static const struct bus_type xen_pcpu_subsys = {
 	.name = "xen_cpu",
 	.dev_name = "xen_cpu",
 };
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 35b6e306026a..67dfa4778864 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -1223,18 +1223,13 @@ struct privcmd_kernel_ioreq *alloc_ioreq(struct privcmd_ioeventfd *ioeventfd)
 	kioreq->ioreq = (struct ioreq *)(page_to_virt(pages[0]));
 	mmap_write_unlock(mm);
 
-	size = sizeof(*ports) * kioreq->vcpus;
-	ports = kzalloc(size, GFP_KERNEL);
-	if (!ports) {
-		ret = -ENOMEM;
+	ports = memdup_array_user(u64_to_user_ptr(ioeventfd->ports),
+				  kioreq->vcpus, sizeof(*ports));
+	if (IS_ERR(ports)) {
+		ret = PTR_ERR(ports);
 		goto error_kfree;
 	}
 
-	if (copy_from_user(ports, u64_to_user_ptr(ioeventfd->ports), size)) {
-		ret = -EFAULT;
-		goto error_kfree_ports;
-	}
-
 	for (i = 0; i < kioreq->vcpus; i++) {
 		kioreq->ports[i].vcpu = i;
 		kioreq->ports[i].port = ports[i];
@@ -1256,7 +1251,7 @@ struct privcmd_kernel_ioreq *alloc_ioreq(struct privcmd_ioeventfd *ioeventfd)
 error_unbind:
 	while (--i >= 0)
 		unbind_from_irqhandler(irq_from_evtchn(ports[i]), &kioreq->ports[i]);
-error_kfree_ports:
+
 	kfree(ports);
 error_kfree:
 	kfree(kioreq);
diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c
index 8cd583db20b1..b293d7652f15 100644
--- a/drivers/xen/xen-balloon.c
+++ b/drivers/xen/xen-balloon.c
@@ -237,7 +237,7 @@ static const struct attribute_group *balloon_groups[] = {
 	NULL
 };
 
-static struct bus_type balloon_subsys = {
+static const struct bus_type balloon_subsys = {
 	.name = BALLOON_CLASS_NAME,
 	.dev_name = BALLOON_CLASS_NAME,
 };
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index d4b251925796..51b3124b0d56 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -116,14 +116,17 @@ EXPORT_SYMBOL_GPL(xenbus_strstate);
  * @dev: xenbus device
  * @path: path to watch
  * @watch: watch to register
+ * @will_handle: events queuing determine callback
  * @callback: callback to register
  *
  * Register a @watch on the given path, using the given xenbus_watch structure
- * for storage, and the given @callback function as the callback.  Return 0 on
- * success, or -errno on error.  On success, the given @path will be saved as
- * @watch->node, and remains the caller's to free.  On error, @watch->node will
- * be NULL, the device will switch to %XenbusStateClosing, and the error will
- * be saved in the store.
+ * for storage, @will_handle function as the callback to determine if each
+ * event need to be queued, and the given @callback function as the callback.
+ * On success, the given @path will be saved as @watch->node, and remains the
+ * caller's to free.  On error, @watch->node will be NULL, the device will
+ * switch to %XenbusStateClosing, and the error will be saved in the store.
+ *
+ * Returns: %0 on success or -errno on error
  */
 int xenbus_watch_path(struct xenbus_device *dev, const char *path,
 		      struct xenbus_watch *watch,
@@ -156,16 +159,20 @@ EXPORT_SYMBOL_GPL(xenbus_watch_path);
  * xenbus_watch_pathfmt - register a watch on a sprintf-formatted path
  * @dev: xenbus device
  * @watch: watch to register
+ * @will_handle: events queuing determine callback
  * @callback: callback to register
  * @pathfmt: format of path to watch
  *
  * Register a watch on the given @path, using the given xenbus_watch
- * structure for storage, and the given @callback function as the callback.
- * Return 0 on success, or -errno on error.  On success, the watched path
- * (@path/@path2) will be saved as @watch->node, and becomes the caller's to
- * kfree().  On error, watch->node will be NULL, so the caller has nothing to
+ * structure for storage, @will_handle function as the callback to determine if
+ * each event need to be queued, and the given @callback function as the
+ * callback.  On success, the watched path (@path/@path2) will be saved
+ * as @watch->node, and becomes the caller's to kfree().
+ * On error, watch->node will be NULL, so the caller has nothing to
  * free, the device will switch to %XenbusStateClosing, and the error will be
  * saved in the store.
+ *
+ * Returns: %0 on success or -errno on error
  */
 int xenbus_watch_pathfmt(struct xenbus_device *dev,
 			 struct xenbus_watch *watch,
@@ -255,13 +262,15 @@ abort:
 }
 
 /**
- * xenbus_switch_state
+ * xenbus_switch_state - save the new state of a driver
  * @dev: xenbus device
  * @state: new state
  *
  * Advertise in the store a change of the given driver to the given new_state.
- * Return 0 on success, or -errno on error.  On error, the device will switch
- * to XenbusStateClosing, and the error will be saved in the store.
+ * On error, the device will switch to XenbusStateClosing, and the error
+ * will be saved in the store.
+ *
+ * Returns: %0 on success or -errno on error
  */
 int xenbus_switch_state(struct xenbus_device *dev, enum xenbus_state state)
 {
@@ -305,7 +314,7 @@ static void xenbus_va_dev_error(struct xenbus_device *dev, int err,
 }
 
 /**
- * xenbus_dev_error
+ * xenbus_dev_error - place an error message into the store
  * @dev: xenbus device
  * @err: error to report
  * @fmt: error message format
@@ -324,7 +333,7 @@ void xenbus_dev_error(struct xenbus_device *dev, int err, const char *fmt, ...)
 EXPORT_SYMBOL_GPL(xenbus_dev_error);
 
 /**
- * xenbus_dev_fatal
+ * xenbus_dev_fatal - put an error messages into the store and then shutdown
  * @dev: xenbus device
  * @err: error to report
  * @fmt: error message format
@@ -346,7 +355,7 @@ void xenbus_dev_fatal(struct xenbus_device *dev, int err, const char *fmt, ...)
 }
 EXPORT_SYMBOL_GPL(xenbus_dev_fatal);
 
-/**
+/*
  * Equivalent to xenbus_dev_fatal(dev, err, fmt, args), but helps
  * avoiding recursion within xenbus_switch_state.
  */
@@ -453,7 +462,7 @@ void xenbus_teardown_ring(void **vaddr, unsigned int nr_pages,
 }
 EXPORT_SYMBOL_GPL(xenbus_teardown_ring);
 
-/**
+/*
  * Allocate an event channel for the given xenbus_device, assigning the newly
  * created local port to *port.  Return 0 on success, or -errno on error.  On
  * error, the device will switch to XenbusStateClosing, and the error will be
@@ -479,7 +488,7 @@ int xenbus_alloc_evtchn(struct xenbus_device *dev, evtchn_port_t *port)
 EXPORT_SYMBOL_GPL(xenbus_alloc_evtchn);
 
 
-/**
+/*
  * Free an existing event channel. Returns 0 on success or -errno on error.
  */
 int xenbus_free_evtchn(struct xenbus_device *dev, evtchn_port_t port)
@@ -499,7 +508,7 @@ EXPORT_SYMBOL_GPL(xenbus_free_evtchn);
 
 
 /**
- * xenbus_map_ring_valloc
+ * xenbus_map_ring_valloc - allocate & map pages of VA space
  * @dev: xenbus device
  * @gnt_refs: grant reference array
  * @nr_grefs: number of grant references
@@ -507,10 +516,11 @@ EXPORT_SYMBOL_GPL(xenbus_free_evtchn);
  *
  * Map @nr_grefs pages of memory into this domain from another
  * domain's grant table.  xenbus_map_ring_valloc allocates @nr_grefs
- * pages of virtual address space, maps the pages to that address, and
- * sets *vaddr to that address.  Returns 0 on success, and -errno on
- * error. If an error is returned, device will switch to
+ * pages of virtual address space, maps the pages to that address, and sets
+ * *vaddr to that address.  If an error is returned, device will switch to
  * XenbusStateClosing and the error message will be saved in XenStore.
+ *
+ * Returns: %0 on success or -errno on error
  */
 int xenbus_map_ring_valloc(struct xenbus_device *dev, grant_ref_t *gnt_refs,
 			   unsigned int nr_grefs, void **vaddr)
@@ -599,14 +609,15 @@ static int __xenbus_map_ring(struct xenbus_device *dev,
 }
 
 /**
- * xenbus_unmap_ring
+ * xenbus_unmap_ring - unmap memory from another domain
  * @dev: xenbus device
  * @handles: grant handle array
  * @nr_handles: number of handles in the array
  * @vaddrs: addresses to unmap
  *
  * Unmap memory in this domain that was imported from another domain.
- * Returns 0 on success and returns GNTST_* on error
+ *
+ * Returns: %0 on success or GNTST_* on error
  * (see xen/include/interface/grant_table.h).
  */
 static int xenbus_unmap_ring(struct xenbus_device *dev, grant_handle_t *handles,
@@ -712,7 +723,7 @@ static int xenbus_map_ring_hvm(struct xenbus_device *dev,
 }
 
 /**
- * xenbus_unmap_ring_vfree
+ * xenbus_unmap_ring_vfree - unmap a page of memory from another domain
  * @dev: xenbus device
  * @vaddr: addr to unmap
  *
@@ -720,7 +731,8 @@ static int xenbus_map_ring_hvm(struct xenbus_device *dev,
  * Unmap a page of memory in this domain that was imported from another domain.
  * Use xenbus_unmap_ring_vfree if you mapped in your memory with
  * xenbus_map_ring_valloc (it will free the virtual address space).
- * Returns 0 on success and returns GNTST_* on error
+ *
+ * Returns: %0 on success or GNTST_* on error
  * (see xen/include/interface/grant_table.h).
  */
 int xenbus_unmap_ring_vfree(struct xenbus_device *dev, void *vaddr)
@@ -916,10 +928,10 @@ static int xenbus_unmap_ring_hvm(struct xenbus_device *dev, void *vaddr)
 }
 
 /**
- * xenbus_read_driver_state
+ * xenbus_read_driver_state - read state from a store path
  * @path: path for driver
  *
- * Return the state of the driver rooted at the given store path, or
+ * Returns: the state of the driver rooted at the given store path, or
  * XenbusStateUnknown if no state can be read.
  */
 enum xenbus_state xenbus_read_driver_state(const char *path)
diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h
index 731e3d14b67d..0e8418066a48 100644
--- a/fs/9p/v9fs_vfs.h
+++ b/fs/9p/v9fs_vfs.h
@@ -42,6 +42,7 @@ struct inode *v9fs_alloc_inode(struct super_block *sb);
 void v9fs_free_inode(struct inode *inode);
 struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode,
 			     dev_t rdev);
+void v9fs_set_netfs_context(struct inode *inode);
 int v9fs_init_inode(struct v9fs_session_info *v9ses,
 		    struct inode *inode, umode_t mode, dev_t rdev);
 void v9fs_evict_inode(struct inode *inode);
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 8a635999a7d6..047855033d32 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -19,12 +19,45 @@
 #include <linux/netfs.h>
 #include <net/9p/9p.h>
 #include <net/9p/client.h>
+#include <trace/events/netfs.h>
 
 #include "v9fs.h"
 #include "v9fs_vfs.h"
 #include "cache.h"
 #include "fid.h"
 
+static void v9fs_upload_to_server(struct netfs_io_subrequest *subreq)
+{
+	struct p9_fid *fid = subreq->rreq->netfs_priv;
+	int err, len;
+
+	trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
+	len = p9_client_write(fid, subreq->start, &subreq->io_iter, &err);
+	netfs_write_subrequest_terminated(subreq, len ?: err, false);
+}
+
+static void v9fs_upload_to_server_worker(struct work_struct *work)
+{
+	struct netfs_io_subrequest *subreq =
+		container_of(work, struct netfs_io_subrequest, work);
+
+	v9fs_upload_to_server(subreq);
+}
+
+/*
+ * Set up write requests for a writeback slice.  We need to add a write request
+ * for each write we want to make.
+ */
+static void v9fs_create_write_requests(struct netfs_io_request *wreq, loff_t start, size_t len)
+{
+	struct netfs_io_subrequest *subreq;
+
+	subreq = netfs_create_write_request(wreq, NETFS_UPLOAD_TO_SERVER,
+					    start, len, v9fs_upload_to_server_worker);
+	if (subreq)
+		netfs_queue_write_request(subreq);
+}
+
 /**
  * v9fs_issue_read - Issue a read from 9P
  * @subreq: The read to make
@@ -33,14 +66,10 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq)
 {
 	struct netfs_io_request *rreq = subreq->rreq;
 	struct p9_fid *fid = rreq->netfs_priv;
-	struct iov_iter to;
-	loff_t pos = subreq->start + subreq->transferred;
-	size_t len = subreq->len   - subreq->transferred;
 	int total, err;
 
-	iov_iter_xarray(&to, ITER_DEST, &rreq->mapping->i_pages, pos, len);
-
-	total = p9_client_read(fid, pos, &to, &err);
+	total = p9_client_read(fid, subreq->start + subreq->transferred,
+			       &subreq->io_iter, &err);
 
 	/* if we just extended the file size, any portion not in
 	 * cache won't be on server and is zeroes */
@@ -50,25 +79,42 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq)
 }
 
 /**
- * v9fs_init_request - Initialise a read request
+ * v9fs_init_request - Initialise a request
  * @rreq: The read request
  * @file: The file being read from
  */
 static int v9fs_init_request(struct netfs_io_request *rreq, struct file *file)
 {
-	struct p9_fid *fid = file->private_data;
-
-	BUG_ON(!fid);
+	struct p9_fid *fid;
+	bool writing = (rreq->origin == NETFS_READ_FOR_WRITE ||
+			rreq->origin == NETFS_WRITEBACK ||
+			rreq->origin == NETFS_WRITETHROUGH ||
+			rreq->origin == NETFS_LAUNDER_WRITE ||
+			rreq->origin == NETFS_UNBUFFERED_WRITE ||
+			rreq->origin == NETFS_DIO_WRITE);
+
+	if (file) {
+		fid = file->private_data;
+		if (!fid)
+			goto no_fid;
+		p9_fid_get(fid);
+	} else {
+		fid = v9fs_fid_find_inode(rreq->inode, writing, INVALID_UID, true);
+		if (!fid)
+			goto no_fid;
+	}
 
 	/* we might need to read from a fid that was opened write-only
 	 * for read-modify-write of page cache, use the writeback fid
 	 * for that */
-	WARN_ON(rreq->origin == NETFS_READ_FOR_WRITE &&
-			!(fid->mode & P9_ORDWR));
-
-	p9_fid_get(fid);
+	WARN_ON(rreq->origin == NETFS_READ_FOR_WRITE && !(fid->mode & P9_ORDWR));
 	rreq->netfs_priv = fid;
 	return 0;
+
+no_fid:
+	WARN_ONCE(1, "folio expected an open fid inode->i_ino=%lx\n",
+		  rreq->inode->i_ino);
+	return -EINVAL;
 }
 
 /**
@@ -82,281 +128,20 @@ static void v9fs_free_request(struct netfs_io_request *rreq)
 	p9_fid_put(fid);
 }
 
-/**
- * v9fs_begin_cache_operation - Begin a cache operation for a read
- * @rreq: The read request
- */
-static int v9fs_begin_cache_operation(struct netfs_io_request *rreq)
-{
-#ifdef CONFIG_9P_FSCACHE
-	struct fscache_cookie *cookie = v9fs_inode_cookie(V9FS_I(rreq->inode));
-
-	return fscache_begin_read_operation(&rreq->cache_resources, cookie);
-#else
-	return -ENOBUFS;
-#endif
-}
-
 const struct netfs_request_ops v9fs_req_ops = {
 	.init_request		= v9fs_init_request,
 	.free_request		= v9fs_free_request,
-	.begin_cache_operation	= v9fs_begin_cache_operation,
 	.issue_read		= v9fs_issue_read,
+	.create_write_requests	= v9fs_create_write_requests,
 };
 
-/**
- * v9fs_release_folio - release the private state associated with a folio
- * @folio: The folio to be released
- * @gfp: The caller's allocation restrictions
- *
- * Returns true if the page can be released, false otherwise.
- */
-
-static bool v9fs_release_folio(struct folio *folio, gfp_t gfp)
-{
-	if (folio_test_private(folio))
-		return false;
-#ifdef CONFIG_9P_FSCACHE
-	if (folio_test_fscache(folio)) {
-		if (current_is_kswapd() || !(gfp & __GFP_FS))
-			return false;
-		folio_wait_fscache(folio);
-	}
-	fscache_note_page_release(v9fs_inode_cookie(V9FS_I(folio_inode(folio))));
-#endif
-	return true;
-}
-
-static void v9fs_invalidate_folio(struct folio *folio, size_t offset,
-				 size_t length)
-{
-	folio_wait_fscache(folio);
-}
-
-#ifdef CONFIG_9P_FSCACHE
-static void v9fs_write_to_cache_done(void *priv, ssize_t transferred_or_error,
-				     bool was_async)
-{
-	struct v9fs_inode *v9inode = priv;
-	__le32 version;
-
-	if (IS_ERR_VALUE(transferred_or_error) &&
-	    transferred_or_error != -ENOBUFS) {
-		version = cpu_to_le32(v9inode->qid.version);
-		fscache_invalidate(v9fs_inode_cookie(v9inode), &version,
-				   i_size_read(&v9inode->netfs.inode), 0);
-	}
-}
-#endif
-
-static int v9fs_vfs_write_folio_locked(struct folio *folio)
-{
-	struct inode *inode = folio_inode(folio);
-	loff_t start = folio_pos(folio);
-	loff_t i_size = i_size_read(inode);
-	struct iov_iter from;
-	size_t len = folio_size(folio);
-	struct p9_fid *writeback_fid;
-	int err;
-	struct v9fs_inode __maybe_unused *v9inode = V9FS_I(inode);
-	struct fscache_cookie __maybe_unused *cookie = v9fs_inode_cookie(v9inode);
-
-	if (start >= i_size)
-		return 0; /* Simultaneous truncation occurred */
-
-	len = min_t(loff_t, i_size - start, len);
-
-	iov_iter_xarray(&from, ITER_SOURCE, &folio_mapping(folio)->i_pages, start, len);
-
-	writeback_fid = v9fs_fid_find_inode(inode, true, INVALID_UID, true);
-	if (!writeback_fid) {
-		WARN_ONCE(1, "folio expected an open fid inode->i_private=%p\n",
-			inode->i_private);
-		return -EINVAL;
-	}
-
-	folio_wait_fscache(folio);
-	folio_start_writeback(folio);
-
-	p9_client_write(writeback_fid, start, &from, &err);
-
-#ifdef CONFIG_9P_FSCACHE
-	if (err == 0 &&
-		fscache_cookie_enabled(cookie) &&
-		test_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags)) {
-		folio_start_fscache(folio);
-		fscache_write_to_cache(v9fs_inode_cookie(v9inode),
-					folio_mapping(folio), start, len, i_size,
-					v9fs_write_to_cache_done, v9inode,
-					true);
-	}
-#endif
-
-	folio_end_writeback(folio);
-	p9_fid_put(writeback_fid);
-
-	return err;
-}
-
-static int v9fs_vfs_writepage(struct page *page, struct writeback_control *wbc)
-{
-	struct folio *folio = page_folio(page);
-	int retval;
-
-	p9_debug(P9_DEBUG_VFS, "folio %p\n", folio);
-
-	retval = v9fs_vfs_write_folio_locked(folio);
-	if (retval < 0) {
-		if (retval == -EAGAIN) {
-			folio_redirty_for_writepage(wbc, folio);
-			retval = 0;
-		} else {
-			mapping_set_error(folio_mapping(folio), retval);
-		}
-	} else
-		retval = 0;
-
-	folio_unlock(folio);
-	return retval;
-}
-
-static int v9fs_launder_folio(struct folio *folio)
-{
-	int retval;
-
-	if (folio_clear_dirty_for_io(folio)) {
-		retval = v9fs_vfs_write_folio_locked(folio);
-		if (retval)
-			return retval;
-	}
-	folio_wait_fscache(folio);
-	return 0;
-}
-
-/**
- * v9fs_direct_IO - 9P address space operation for direct I/O
- * @iocb: target I/O control block
- * @iter: The data/buffer to use
- *
- * The presence of v9fs_direct_IO() in the address space ops vector
- * allowes open() O_DIRECT flags which would have failed otherwise.
- *
- * In the non-cached mode, we shunt off direct read and write requests before
- * the VFS gets them, so this method should never be called.
- *
- * Direct IO is not 'yet' supported in the cached mode. Hence when
- * this routine is called through generic_file_aio_read(), the read/write fails
- * with an error.
- *
- */
-static ssize_t
-v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
-{
-	struct file *file = iocb->ki_filp;
-	loff_t pos = iocb->ki_pos;
-	ssize_t n;
-	int err = 0;
-
-	if (iov_iter_rw(iter) == WRITE) {
-		n = p9_client_write(file->private_data, pos, iter, &err);
-		if (n) {
-			struct inode *inode = file_inode(file);
-			loff_t i_size = i_size_read(inode);
-
-			if (pos + n > i_size)
-				inode_add_bytes(inode, pos + n - i_size);
-		}
-	} else {
-		n = p9_client_read(file->private_data, pos, iter, &err);
-	}
-	return n ? n : err;
-}
-
-static int v9fs_write_begin(struct file *filp, struct address_space *mapping,
-			    loff_t pos, unsigned int len,
-			    struct page **subpagep, void **fsdata)
-{
-	int retval;
-	struct folio *folio;
-	struct v9fs_inode *v9inode = V9FS_I(mapping->host);
-
-	p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping);
-
-	/* Prefetch area to be written into the cache if we're caching this
-	 * file.  We need to do this before we get a lock on the page in case
-	 * there's more than one writer competing for the same cache block.
-	 */
-	retval = netfs_write_begin(&v9inode->netfs, filp, mapping, pos, len, &folio, fsdata);
-	if (retval < 0)
-		return retval;
-
-	*subpagep = &folio->page;
-	return retval;
-}
-
-static int v9fs_write_end(struct file *filp, struct address_space *mapping,
-			  loff_t pos, unsigned int len, unsigned int copied,
-			  struct page *subpage, void *fsdata)
-{
-	loff_t last_pos = pos + copied;
-	struct folio *folio = page_folio(subpage);
-	struct inode *inode = mapping->host;
-
-	p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping);
-
-	if (!folio_test_uptodate(folio)) {
-		if (unlikely(copied < len)) {
-			copied = 0;
-			goto out;
-		}
-
-		folio_mark_uptodate(folio);
-	}
-
-	/*
-	 * No need to use i_size_read() here, the i_size
-	 * cannot change under us because we hold the i_mutex.
-	 */
-	if (last_pos > inode->i_size) {
-		inode_add_bytes(inode, last_pos - inode->i_size);
-		i_size_write(inode, last_pos);
-#ifdef CONFIG_9P_FSCACHE
-		fscache_update_cookie(v9fs_inode_cookie(V9FS_I(inode)), NULL,
-			&last_pos);
-#endif
-	}
-	folio_mark_dirty(folio);
-out:
-	folio_unlock(folio);
-	folio_put(folio);
-
-	return copied;
-}
-
-#ifdef CONFIG_9P_FSCACHE
-/*
- * Mark a page as having been made dirty and thus needing writeback.  We also
- * need to pin the cache object to write back to.
- */
-static bool v9fs_dirty_folio(struct address_space *mapping, struct folio *folio)
-{
-	struct v9fs_inode *v9inode = V9FS_I(mapping->host);
-
-	return fscache_dirty_folio(mapping, folio, v9fs_inode_cookie(v9inode));
-}
-#else
-#define v9fs_dirty_folio filemap_dirty_folio
-#endif
-
 const struct address_space_operations v9fs_addr_operations = {
-	.read_folio = netfs_read_folio,
-	.readahead = netfs_readahead,
-	.dirty_folio = v9fs_dirty_folio,
-	.writepage = v9fs_vfs_writepage,
-	.write_begin = v9fs_write_begin,
-	.write_end = v9fs_write_end,
-	.release_folio = v9fs_release_folio,
-	.invalidate_folio = v9fs_invalidate_folio,
-	.launder_folio = v9fs_launder_folio,
-	.direct_IO = v9fs_direct_IO,
+	.read_folio		= netfs_read_folio,
+	.readahead		= netfs_readahead,
+	.dirty_folio		= netfs_dirty_folio,
+	.release_folio		= netfs_release_folio,
+	.invalidate_folio	= netfs_invalidate_folio,
+	.launder_folio		= netfs_launder_folio,
+	.direct_IO		= noop_direct_IO,
+	.writepages		= netfs_writepages,
 };
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 11cd8d23f6f2..abdbbaee5184 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -107,7 +107,7 @@ static int v9fs_file_lock(struct file *filp, int cmd, struct file_lock *fl)
 
 	p9_debug(P9_DEBUG_VFS, "filp: %p lock: %p\n", filp, fl);
 
-	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
+	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->c.flc_type != F_UNLCK) {
 		filemap_write_and_wait(inode->i_mapping);
 		invalidate_mapping_pages(&inode->i_data, 0, -1);
 	}
@@ -121,13 +121,12 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
 	struct p9_fid *fid;
 	uint8_t status = P9_LOCK_ERROR;
 	int res = 0;
-	unsigned char fl_type;
 	struct v9fs_session_info *v9ses;
 
 	fid = filp->private_data;
 	BUG_ON(fid == NULL);
 
-	BUG_ON((fl->fl_flags & FL_POSIX) != FL_POSIX);
+	BUG_ON((fl->c.flc_flags & FL_POSIX) != FL_POSIX);
 
 	res = locks_lock_file_wait(filp, fl);
 	if (res < 0)
@@ -136,7 +135,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
 	/* convert posix lock to p9 tlock args */
 	memset(&flock, 0, sizeof(flock));
 	/* map the lock type */
-	switch (fl->fl_type) {
+	switch (fl->c.flc_type) {
 	case F_RDLCK:
 		flock.type = P9_LOCK_TYPE_RDLCK;
 		break;
@@ -152,7 +151,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
 		flock.length = 0;
 	else
 		flock.length = fl->fl_end - fl->fl_start + 1;
-	flock.proc_id = fl->fl_pid;
+	flock.proc_id = fl->c.flc_pid;
 	flock.client_id = fid->clnt->name;
 	if (IS_SETLKW(cmd))
 		flock.flags = P9_LOCK_FLAGS_BLOCK;
@@ -207,12 +206,13 @@ out_unlock:
 	 * incase server returned error for lock request, revert
 	 * it locally
 	 */
-	if (res < 0 && fl->fl_type != F_UNLCK) {
-		fl_type = fl->fl_type;
-		fl->fl_type = F_UNLCK;
+	if (res < 0 && fl->c.flc_type != F_UNLCK) {
+		unsigned char type = fl->c.flc_type;
+
+		fl->c.flc_type = F_UNLCK;
 		/* Even if this fails we want to return the remote error */
 		locks_lock_file_wait(filp, fl);
-		fl->fl_type = fl_type;
+		fl->c.flc_type = type;
 	}
 	if (flock.client_id != fid->clnt->name)
 		kfree(flock.client_id);
@@ -234,7 +234,7 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl)
 	 * if we have a conflicting lock locally, no need to validate
 	 * with server
 	 */
-	if (fl->fl_type != F_UNLCK)
+	if (fl->c.flc_type != F_UNLCK)
 		return res;
 
 	/* convert posix lock to p9 tgetlock args */
@@ -245,7 +245,7 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl)
 		glock.length = 0;
 	else
 		glock.length = fl->fl_end - fl->fl_start + 1;
-	glock.proc_id = fl->fl_pid;
+	glock.proc_id = fl->c.flc_pid;
 	glock.client_id = fid->clnt->name;
 
 	res = p9_client_getlock_dotl(fid, &glock);
@@ -254,13 +254,13 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl)
 	/* map 9p lock type to os lock type */
 	switch (glock.type) {
 	case P9_LOCK_TYPE_RDLCK:
-		fl->fl_type = F_RDLCK;
+		fl->c.flc_type = F_RDLCK;
 		break;
 	case P9_LOCK_TYPE_WRLCK:
-		fl->fl_type = F_WRLCK;
+		fl->c.flc_type = F_WRLCK;
 		break;
 	case P9_LOCK_TYPE_UNLCK:
-		fl->fl_type = F_UNLCK;
+		fl->c.flc_type = F_UNLCK;
 		break;
 	}
 	if (glock.type != P9_LOCK_TYPE_UNLCK) {
@@ -269,7 +269,7 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl)
 			fl->fl_end = OFFSET_MAX;
 		else
 			fl->fl_end = glock.start + glock.length - 1;
-		fl->fl_pid = -glock.proc_id;
+		fl->c.flc_pid = -glock.proc_id;
 	}
 out:
 	if (glock.client_id != fid->clnt->name)
@@ -293,7 +293,7 @@ static int v9fs_file_lock_dotl(struct file *filp, int cmd, struct file_lock *fl)
 	p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %pD\n",
 		 filp, cmd, fl, filp);
 
-	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
+	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->c.flc_type != F_UNLCK) {
 		filemap_write_and_wait(inode->i_mapping);
 		invalidate_mapping_pages(&inode->i_data, 0, -1);
 	}
@@ -324,16 +324,16 @@ static int v9fs_file_flock_dotl(struct file *filp, int cmd,
 	p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %pD\n",
 		 filp, cmd, fl, filp);
 
-	if (!(fl->fl_flags & FL_FLOCK))
+	if (!(fl->c.flc_flags & FL_FLOCK))
 		goto out_err;
 
-	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
+	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->c.flc_type != F_UNLCK) {
 		filemap_write_and_wait(inode->i_mapping);
 		invalidate_mapping_pages(&inode->i_data, 0, -1);
 	}
 	/* Convert flock to posix lock */
-	fl->fl_flags |= FL_POSIX;
-	fl->fl_flags ^= FL_FLOCK;
+	fl->c.flc_flags |= FL_POSIX;
+	fl->c.flc_flags ^= FL_FLOCK;
 
 	if (IS_SETLK(cmd) | IS_SETLKW(cmd))
 		ret = v9fs_file_do_lock(filp, cmd, fl);
@@ -353,25 +353,15 @@ static ssize_t
 v9fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct p9_fid *fid = iocb->ki_filp->private_data;
-	int ret, err = 0;
 
 	p9_debug(P9_DEBUG_VFS, "fid %d count %zu offset %lld\n",
 		 fid->fid, iov_iter_count(to), iocb->ki_pos);
 
-	if (!(fid->mode & P9L_DIRECT)) {
-		p9_debug(P9_DEBUG_VFS, "(cached)\n");
-		return generic_file_read_iter(iocb, to);
-	}
-
-	if (iocb->ki_filp->f_flags & O_NONBLOCK)
-		ret = p9_client_read_once(fid, iocb->ki_pos, to, &err);
-	else
-		ret = p9_client_read(fid, iocb->ki_pos, to, &err);
-	if (!ret)
-		return err;
+	if (fid->mode & P9L_DIRECT)
+		return netfs_unbuffered_read_iter(iocb, to);
 
-	iocb->ki_pos += ret;
-	return ret;
+	p9_debug(P9_DEBUG_VFS, "(cached)\n");
+	return netfs_file_read_iter(iocb, to);
 }
 
 /*
@@ -407,46 +397,14 @@ v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct p9_fid *fid = file->private_data;
-	ssize_t retval;
-	loff_t origin;
-	int err = 0;
 
 	p9_debug(P9_DEBUG_VFS, "fid %d\n", fid->fid);
 
-	if (!(fid->mode & (P9L_DIRECT | P9L_NOWRITECACHE))) {
-		p9_debug(P9_DEBUG_CACHE, "(cached)\n");
-		return generic_file_write_iter(iocb, from);
-	}
-
-	retval = generic_write_checks(iocb, from);
-	if (retval <= 0)
-		return retval;
+	if (fid->mode & (P9L_DIRECT | P9L_NOWRITECACHE))
+		return netfs_unbuffered_write_iter(iocb, from);
 
-	origin = iocb->ki_pos;
-	retval = p9_client_write(file->private_data, iocb->ki_pos, from, &err);
-	if (retval > 0) {
-		struct inode *inode = file_inode(file);
-		loff_t i_size;
-		unsigned long pg_start, pg_end;
-
-		pg_start = origin >> PAGE_SHIFT;
-		pg_end = (origin + retval - 1) >> PAGE_SHIFT;
-		if (inode->i_mapping && inode->i_mapping->nrpages)
-			invalidate_inode_pages2_range(inode->i_mapping,
-						      pg_start, pg_end);
-		iocb->ki_pos += retval;
-		i_size = i_size_read(inode);
-		if (iocb->ki_pos > i_size) {
-			inode_add_bytes(inode, iocb->ki_pos - i_size);
-			/*
-			 * Need to serialize against i_size_write() in
-			 * v9fs_stat2inode()
-			 */
-			v9fs_i_size_write(inode, iocb->ki_pos);
-		}
-		return retval;
-	}
-	return err;
+	p9_debug(P9_DEBUG_CACHE, "(cached)\n");
+	return netfs_file_write_iter(iocb, from);
 }
 
 static int v9fs_file_fsync(struct file *filp, loff_t start, loff_t end,
@@ -519,36 +477,7 @@ v9fs_file_mmap(struct file *filp, struct vm_area_struct *vma)
 static vm_fault_t
 v9fs_vm_page_mkwrite(struct vm_fault *vmf)
 {
-	struct folio *folio = page_folio(vmf->page);
-	struct file *filp = vmf->vma->vm_file;
-	struct inode *inode = file_inode(filp);
-
-
-	p9_debug(P9_DEBUG_VFS, "folio %p fid %lx\n",
-		 folio, (unsigned long)filp->private_data);
-
-	/* Wait for the page to be written to the cache before we allow it to
-	 * be modified.  We then assume the entire page will need writing back.
-	 */
-#ifdef CONFIG_9P_FSCACHE
-	if (folio_test_fscache(folio) &&
-	    folio_wait_fscache_killable(folio) < 0)
-		return VM_FAULT_NOPAGE;
-#endif
-
-	/* Update file times before taking page lock */
-	file_update_time(filp);
-
-	if (folio_lock_killable(folio) < 0)
-		return VM_FAULT_RETRY;
-	if (folio_mapping(folio) != inode->i_mapping)
-		goto out_unlock;
-	folio_wait_stable(folio);
-
-	return VM_FAULT_LOCKED;
-out_unlock:
-	folio_unlock(folio);
-	return VM_FAULT_NOPAGE;
+	return netfs_page_mkwrite(vmf, NULL);
 }
 
 static void v9fs_mmap_vm_close(struct vm_area_struct *vma)
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index b845ee18a80b..32572982f72e 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -246,10 +246,10 @@ void v9fs_free_inode(struct inode *inode)
 /*
  * Set parameters for the netfs library
  */
-static void v9fs_set_netfs_context(struct inode *inode)
+void v9fs_set_netfs_context(struct inode *inode)
 {
 	struct v9fs_inode *v9inode = V9FS_I(inode);
-	netfs_inode_init(&v9inode->netfs, &v9fs_req_ops);
+	netfs_inode_init(&v9inode->netfs, &v9fs_req_ops, true);
 }
 
 int v9fs_init_inode(struct v9fs_session_info *v9ses,
@@ -326,8 +326,6 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses,
 		err = -EINVAL;
 		goto error;
 	}
-
-	v9fs_set_netfs_context(inode);
 error:
 	return err;
 
@@ -359,6 +357,7 @@ struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t rdev)
 		iput(inode);
 		return ERR_PTR(err);
 	}
+	v9fs_set_netfs_context(inode);
 	return inode;
 }
 
@@ -374,11 +373,8 @@ void v9fs_evict_inode(struct inode *inode)
 
 	truncate_inode_pages_final(&inode->i_data);
 
-#ifdef CONFIG_9P_FSCACHE
 	version = cpu_to_le32(v9inode->qid.version);
-	fscache_clear_inode_writeback(v9fs_inode_cookie(v9inode), inode,
-				      &version);
-#endif
+	netfs_clear_inode_writeback(inode, &version);
 
 	clear_inode(inode);
 	filemap_fdatawrite(&inode->i_data);
@@ -464,6 +460,7 @@ static struct inode *v9fs_qid_iget(struct super_block *sb,
 		goto error;
 
 	v9fs_stat2inode(st, inode, sb, 0);
+	v9fs_set_netfs_context(inode);
 	v9fs_cache_inode_get_cookie(inode);
 	unlock_new_inode(inode);
 	return inode;
@@ -1113,7 +1110,7 @@ static int v9fs_vfs_setattr(struct mnt_idmap *idmap,
 	if ((iattr->ia_valid & ATTR_SIZE) &&
 		 iattr->ia_size != i_size_read(inode)) {
 		truncate_setsize(inode, iattr->ia_size);
-		truncate_pagecache(inode, iattr->ia_size);
+		netfs_resize_file(netfs_inode(inode), iattr->ia_size, true);
 
 #ifdef CONFIG_9P_FSCACHE
 		if (v9ses->cache & CACHE_FSCACHE) {
@@ -1181,6 +1178,7 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
 	mode |= inode->i_mode & ~S_IALLUGO;
 	inode->i_mode = mode;
 
+	v9inode->netfs.remote_i_size = stat->length;
 	if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE))
 		v9fs_i_size_write(inode, stat->length);
 	/* not real number of blocks, but 512 byte ones ... */
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index c7319af2f471..3505227e1704 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -128,6 +128,7 @@ static struct inode *v9fs_qid_iget_dotl(struct super_block *sb,
 		goto error;
 
 	v9fs_stat2inode_dotl(st, inode, 0);
+	v9fs_set_netfs_context(inode);
 	v9fs_cache_inode_get_cookie(inode);
 	retval = v9fs_get_acl(inode, fid);
 	if (retval)
@@ -598,7 +599,7 @@ int v9fs_vfs_setattr_dotl(struct mnt_idmap *idmap,
 	if ((iattr->ia_valid & ATTR_SIZE) && iattr->ia_size !=
 		 i_size_read(inode)) {
 		truncate_setsize(inode, iattr->ia_size);
-		truncate_pagecache(inode, iattr->ia_size);
+		netfs_resize_file(netfs_inode(inode), iattr->ia_size, true);
 
 #ifdef CONFIG_9P_FSCACHE
 		if (v9ses->cache & CACHE_FSCACHE)
@@ -655,6 +656,7 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode,
 		mode |= inode->i_mode & ~S_IALLUGO;
 		inode->i_mode = mode;
 
+		v9inode->netfs.remote_i_size = stat->st_size;
 		if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE))
 			v9fs_i_size_write(inode, stat->st_size);
 		inode->i_blocks = stat->st_blocks;
@@ -683,8 +685,10 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode,
 			inode->i_mode = mode;
 		}
 		if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE) &&
-		    stat->st_result_mask & P9_STATS_SIZE)
+		    stat->st_result_mask & P9_STATS_SIZE) {
+			v9inode->netfs.remote_i_size = stat->st_size;
 			v9fs_i_size_write(inode, stat->st_size);
+		}
 		if (stat->st_result_mask & P9_STATS_BLOCKS)
 			inode->i_blocks = stat->st_blocks;
 	}
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 73db55c050bf..941f7d0e0bfa 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -289,31 +289,21 @@ static int v9fs_drop_inode(struct inode *inode)
 static int v9fs_write_inode(struct inode *inode,
 			    struct writeback_control *wbc)
 {
-	struct v9fs_inode *v9inode;
-
 	/*
 	 * send an fsync request to server irrespective of
 	 * wbc->sync_mode.
 	 */
 	p9_debug(P9_DEBUG_VFS, "%s: inode %p\n", __func__, inode);
-
-	v9inode = V9FS_I(inode);
-	fscache_unpin_writeback(wbc, v9fs_inode_cookie(v9inode));
-
-	return 0;
+	return netfs_unpin_writeback(inode, wbc);
 }
 
 static int v9fs_write_inode_dotl(struct inode *inode,
 				 struct writeback_control *wbc)
 {
-	struct v9fs_inode *v9inode;
 
-	v9inode = V9FS_I(inode);
 	p9_debug(P9_DEBUG_VFS, "%s: inode %p\n", __func__, inode);
 
-	fscache_unpin_writeback(wbc, v9fs_inode_cookie(v9inode));
-
-	return 0;
+	return netfs_unpin_writeback(inode, wbc);
 }
 
 static const struct super_operations v9fs_super_ops = {
diff --git a/fs/Kconfig b/fs/Kconfig
index a3159831ba98..4bc7dd420874 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -144,7 +144,6 @@ source "fs/overlayfs/Kconfig"
 menu "Caches"
 
 source "fs/netfs/Kconfig"
-source "fs/fscache/Kconfig"
 source "fs/cachefiles/Kconfig"
 
 endmenu
@@ -163,7 +162,6 @@ menu "DOS/FAT/EXFAT/NT Filesystems"
 
 source "fs/fat/Kconfig"
 source "fs/exfat/Kconfig"
-source "fs/ntfs/Kconfig"
 source "fs/ntfs3/Kconfig"
 
 endmenu
@@ -175,6 +173,13 @@ source "fs/proc/Kconfig"
 source "fs/kernfs/Kconfig"
 source "fs/sysfs/Kconfig"
 
+config FS_PID
+	bool "Pseudo filesystem for process file descriptors"
+	depends on 64BIT
+	default y
+	help
+	  Pidfs implements advanced features for process file descriptors.
+
 config TMPFS
 	bool "Tmpfs virtual memory file system support (former shm fs)"
 	depends on SHMEM
diff --git a/fs/Makefile b/fs/Makefile
index a6962c588962..6ecc9b0a53f2 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -15,7 +15,7 @@ obj-y :=	open.o read_write.o file_table.o super.o \
 		pnode.o splice.o sync.o utimes.o d_path.o \
 		stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \
 		fs_types.o fs_context.o fs_parser.o fsopen.o init.o \
-		kernel_read_file.o mnt_idmapping.o remap_range.o
+		kernel_read_file.o mnt_idmapping.o remap_range.o pidfs.o
 
 obj-$(CONFIG_BUFFER_HEAD)	+= buffer.o mpage.o
 obj-$(CONFIG_PROC_FS)		+= proc_namespace.o
@@ -61,7 +61,6 @@ obj-$(CONFIG_DLM)		+= dlm/
  
 # Do not add any filesystems before this line
 obj-$(CONFIG_NETFS_SUPPORT)	+= netfs/
-obj-$(CONFIG_FSCACHE)		+= fscache/
 obj-$(CONFIG_REISERFS_FS)	+= reiserfs/
 obj-$(CONFIG_EXT4_FS)		+= ext4/
 # We place ext4 before ext2 so that clean ext3 root fs's do NOT mount using the
@@ -92,7 +91,6 @@ obj-y				+= unicode/
 obj-$(CONFIG_SYSV_FS)		+= sysv/
 obj-$(CONFIG_SMBFS)		+= smb/
 obj-$(CONFIG_HPFS_FS)		+= hpfs/
-obj-$(CONFIG_NTFS_FS)		+= ntfs/
 obj-$(CONFIG_NTFS3_FS)		+= ntfs3/
 obj-$(CONFIG_UFS_FS)		+= ufs/
 obj-$(CONFIG_EFS_FS)		+= efs/
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index 60685ec76d98..2e612834329a 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -105,6 +105,7 @@ struct affs_sb_info {
 	int work_queued;		/* non-zero delayed work is queued */
 	struct delayed_work sb_work;	/* superblock flush delayed work */
 	spinlock_t work_lock;		/* protects sb_work and work_queued */
+	struct rcu_head rcu;
 };
 
 #define AFFS_MOUNT_SF_INTL		0x0001 /* International filesystem. */
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 58b391446ae1..b56a95cf414a 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -640,7 +640,7 @@ static void affs_kill_sb(struct super_block *sb)
 		affs_brelse(sbi->s_root_bh);
 		kfree(sbi->s_prefix);
 		mutex_destroy(&sbi->s_bmlock);
-		kfree(sbi);
+		kfree_rcu(sbi, rcu);
 	}
 }
 
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index c14533ef108f..8a67fc427e74 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -124,7 +124,7 @@ static void afs_dir_read_cleanup(struct afs_read *req)
 		if (xas_retry(&xas, folio))
 			continue;
 		BUG_ON(xa_is_value(folio));
-		ASSERTCMP(folio_file_mapping(folio), ==, mapping);
+		ASSERTCMP(folio->mapping, ==, mapping);
 
 		folio_put(folio);
 	}
@@ -202,12 +202,12 @@ static void afs_dir_dump(struct afs_vnode *dvnode, struct afs_read *req)
 		if (xas_retry(&xas, folio))
 			continue;
 
-		BUG_ON(folio_file_mapping(folio) != mapping);
+		BUG_ON(folio->mapping != mapping);
 
 		size = min_t(loff_t, folio_size(folio), req->actual_len - folio_pos(folio));
 		for (offset = 0; offset < size; offset += sizeof(*block)) {
 			block = kmap_local_folio(folio, offset);
-			pr_warn("[%02lx] %32phN\n", folio_index(folio) + offset, block);
+			pr_warn("[%02lx] %32phN\n", folio->index + offset, block);
 			kunmap_local(block);
 		}
 	}
@@ -233,7 +233,7 @@ static int afs_dir_check(struct afs_vnode *dvnode, struct afs_read *req)
 		if (xas_retry(&xas, folio))
 			continue;
 
-		BUG_ON(folio_file_mapping(folio) != mapping);
+		BUG_ON(folio->mapping != mapping);
 
 		if (!afs_dir_check_folio(dvnode, folio, req->actual_len)) {
 			afs_dir_dump(dvnode, req);
@@ -474,6 +474,16 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode,
 			continue;
 		}
 
+		/* Don't expose silly rename entries to userspace. */
+		if (nlen > 6 &&
+		    dire->u.name[0] == '.' &&
+		    ctx->actor != afs_lookup_filldir &&
+		    ctx->actor != afs_lookup_one_filldir &&
+		    memcmp(dire->u.name, ".__afs", 6) == 0) {
+			ctx->pos = blkoff + next * sizeof(union afs_xdr_dirent);
+			continue;
+		}
+
 		/* found the next entry */
 		if (!dir_emit(ctx, dire->u.name, nlen,
 			      ntohl(dire->u.vnode),
@@ -708,6 +718,8 @@ static void afs_do_lookup_success(struct afs_operation *op)
 			break;
 		}
 
+		if (vp->scb.status.abort_code)
+			trace_afs_bulkstat_error(op, &vp->fid, i, vp->scb.status.abort_code);
 		if (!vp->scb.have_status && !vp->scb.have_error)
 			continue;
 
@@ -897,12 +909,16 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry,
 		afs_begin_vnode_operation(op);
 		afs_wait_for_operation(op);
 	}
-	inode = ERR_PTR(afs_op_error(op));
 
 out_op:
 	if (!afs_op_error(op)) {
-		inode = &op->file[1].vnode->netfs.inode;
-		op->file[1].vnode = NULL;
+		if (op->file[1].scb.status.abort_code) {
+			afs_op_accumulate_error(op, -ECONNABORTED,
+						op->file[1].scb.status.abort_code);
+		} else {
+			inode = &op->file[1].vnode->netfs.inode;
+			op->file[1].vnode = NULL;
+		}
 	}
 
 	if (op->file[0].scb.have_status)
@@ -2022,7 +2038,7 @@ static bool afs_dir_release_folio(struct folio *folio, gfp_t gfp_flags)
 {
 	struct afs_vnode *dvnode = AFS_FS_I(folio_inode(folio));
 
-	_enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, folio_index(folio));
+	_enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, folio->index);
 
 	folio_detach_private(folio);
 
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index 2cd40ba601f1..c4d2711e20ad 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -76,7 +76,7 @@ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root)
 	/* there shouldn't be an existing inode */
 	BUG_ON(!(inode->i_state & I_NEW));
 
-	netfs_inode_init(&vnode->netfs, NULL);
+	netfs_inode_init(&vnode->netfs, NULL, false);
 	inode->i_size		= 0;
 	inode->i_mode		= S_IFDIR | S_IRUGO | S_IXUGO;
 	if (root) {
@@ -258,16 +258,7 @@ const struct inode_operations afs_dynroot_inode_operations = {
 	.lookup		= afs_dynroot_lookup,
 };
 
-/*
- * Dirs in the dynamic root don't need revalidation.
- */
-static int afs_dynroot_d_revalidate(struct dentry *dentry, unsigned int flags)
-{
-	return 1;
-}
-
 const struct dentry_operations afs_dynroot_dentry_operations = {
-	.d_revalidate	= afs_dynroot_d_revalidate,
 	.d_delete	= always_delete_dentry,
 	.d_release	= afs_d_release,
 	.d_automount	= afs_d_automount,
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 30914e0d9cb2..ef2cc8f565d2 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -20,9 +20,6 @@
 
 static int afs_file_mmap(struct file *file, struct vm_area_struct *vma);
 static int afs_symlink_read_folio(struct file *file, struct folio *folio);
-static void afs_invalidate_folio(struct folio *folio, size_t offset,
-			       size_t length);
-static bool afs_release_folio(struct folio *folio, gfp_t gfp_flags);
 
 static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter);
 static ssize_t afs_file_splice_read(struct file *in, loff_t *ppos,
@@ -37,7 +34,7 @@ const struct file_operations afs_file_operations = {
 	.release	= afs_release,
 	.llseek		= generic_file_llseek,
 	.read_iter	= afs_file_read_iter,
-	.write_iter	= afs_file_write,
+	.write_iter	= netfs_file_write_iter,
 	.mmap		= afs_file_mmap,
 	.splice_read	= afs_file_splice_read,
 	.splice_write	= iter_file_splice_write,
@@ -53,22 +50,21 @@ const struct inode_operations afs_file_inode_operations = {
 };
 
 const struct address_space_operations afs_file_aops = {
+	.direct_IO	= noop_direct_IO,
 	.read_folio	= netfs_read_folio,
 	.readahead	= netfs_readahead,
-	.dirty_folio	= afs_dirty_folio,
-	.launder_folio	= afs_launder_folio,
-	.release_folio	= afs_release_folio,
-	.invalidate_folio = afs_invalidate_folio,
-	.write_begin	= afs_write_begin,
-	.write_end	= afs_write_end,
-	.writepages	= afs_writepages,
+	.dirty_folio	= netfs_dirty_folio,
+	.launder_folio	= netfs_launder_folio,
+	.release_folio	= netfs_release_folio,
+	.invalidate_folio = netfs_invalidate_folio,
 	.migrate_folio	= filemap_migrate_folio,
+	.writepages	= afs_writepages,
 };
 
 const struct address_space_operations afs_symlink_aops = {
 	.read_folio	= afs_symlink_read_folio,
-	.release_folio	= afs_release_folio,
-	.invalidate_folio = afs_invalidate_folio,
+	.release_folio	= netfs_release_folio,
+	.invalidate_folio = netfs_invalidate_folio,
 	.migrate_folio	= filemap_migrate_folio,
 };
 
@@ -323,11 +319,7 @@ static void afs_issue_read(struct netfs_io_subrequest *subreq)
 	fsreq->len	= subreq->len   - subreq->transferred;
 	fsreq->key	= key_get(subreq->rreq->netfs_priv);
 	fsreq->vnode	= vnode;
-	fsreq->iter	= &fsreq->def_iter;
-
-	iov_iter_xarray(&fsreq->def_iter, ITER_DEST,
-			&fsreq->vnode->netfs.inode.i_mapping->i_pages,
-			fsreq->pos, fsreq->len);
+	fsreq->iter	= &subreq->io_iter;
 
 	afs_fetch_data(fsreq->vnode, fsreq);
 	afs_put_read(fsreq);
@@ -359,22 +351,13 @@ static int afs_symlink_read_folio(struct file *file, struct folio *folio)
 
 static int afs_init_request(struct netfs_io_request *rreq, struct file *file)
 {
-	rreq->netfs_priv = key_get(afs_file_key(file));
+	if (file)
+		rreq->netfs_priv = key_get(afs_file_key(file));
+	rreq->rsize = 256 * 1024;
+	rreq->wsize = 256 * 1024;
 	return 0;
 }
 
-static int afs_begin_cache_operation(struct netfs_io_request *rreq)
-{
-#ifdef CONFIG_AFS_FSCACHE
-	struct afs_vnode *vnode = AFS_FS_I(rreq->inode);
-
-	return fscache_begin_read_operation(&rreq->cache_resources,
-					    afs_vnode_cache(vnode));
-#else
-	return -ENOBUFS;
-#endif
-}
-
 static int afs_check_write_begin(struct file *file, loff_t pos, unsigned len,
 				 struct folio **foliop, void **_fsdata)
 {
@@ -388,128 +371,37 @@ static void afs_free_request(struct netfs_io_request *rreq)
 	key_put(rreq->netfs_priv);
 }
 
-const struct netfs_request_ops afs_req_ops = {
-	.init_request		= afs_init_request,
-	.free_request		= afs_free_request,
-	.begin_cache_operation	= afs_begin_cache_operation,
-	.check_write_begin	= afs_check_write_begin,
-	.issue_read		= afs_issue_read,
-};
-
-int afs_write_inode(struct inode *inode, struct writeback_control *wbc)
+static void afs_update_i_size(struct inode *inode, loff_t new_i_size)
 {
-	fscache_unpin_writeback(wbc, afs_vnode_cache(AFS_FS_I(inode)));
-	return 0;
-}
-
-/*
- * Adjust the dirty region of the page on truncation or full invalidation,
- * getting rid of the markers altogether if the region is entirely invalidated.
- */
-static void afs_invalidate_dirty(struct folio *folio, size_t offset,
-				 size_t length)
-{
-	struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio));
-	unsigned long priv;
-	unsigned int f, t, end = offset + length;
-
-	priv = (unsigned long)folio_get_private(folio);
-
-	/* we clean up only if the entire page is being invalidated */
-	if (offset == 0 && length == folio_size(folio))
-		goto full_invalidate;
-
-	 /* If the page was dirtied by page_mkwrite(), the PTE stays writable
-	  * and we don't get another notification to tell us to expand it
-	  * again.
-	  */
-	if (afs_is_folio_dirty_mmapped(priv))
-		return;
-
-	/* We may need to shorten the dirty region */
-	f = afs_folio_dirty_from(folio, priv);
-	t = afs_folio_dirty_to(folio, priv);
-
-	if (t <= offset || f >= end)
-		return; /* Doesn't overlap */
-
-	if (f < offset && t > end)
-		return; /* Splits the dirty region - just absorb it */
-
-	if (f >= offset && t <= end)
-		goto undirty;
+	struct afs_vnode *vnode = AFS_FS_I(inode);
+	loff_t i_size;
 
-	if (f < offset)
-		t = offset;
-	else
-		f = end;
-	if (f == t)
-		goto undirty;
-
-	priv = afs_folio_dirty(folio, f, t);
-	folio_change_private(folio, (void *)priv);
-	trace_afs_folio_dirty(vnode, tracepoint_string("trunc"), folio);
-	return;
-
-undirty:
-	trace_afs_folio_dirty(vnode, tracepoint_string("undirty"), folio);
-	folio_clear_dirty_for_io(folio);
-full_invalidate:
-	trace_afs_folio_dirty(vnode, tracepoint_string("inval"), folio);
-	folio_detach_private(folio);
+	write_seqlock(&vnode->cb_lock);
+	i_size = i_size_read(&vnode->netfs.inode);
+	if (new_i_size > i_size) {
+		i_size_write(&vnode->netfs.inode, new_i_size);
+		inode_set_bytes(&vnode->netfs.inode, new_i_size);
+	}
+	write_sequnlock(&vnode->cb_lock);
+	fscache_update_cookie(afs_vnode_cache(vnode), NULL, &new_i_size);
 }
 
-/*
- * invalidate part or all of a page
- * - release a page and clean up its private data if offset is 0 (indicating
- *   the entire page)
- */
-static void afs_invalidate_folio(struct folio *folio, size_t offset,
-			       size_t length)
+static void afs_netfs_invalidate_cache(struct netfs_io_request *wreq)
 {
-	_enter("{%lu},%zu,%zu", folio->index, offset, length);
-
-	BUG_ON(!folio_test_locked(folio));
+	struct afs_vnode *vnode = AFS_FS_I(wreq->inode);
 
-	if (folio_get_private(folio))
-		afs_invalidate_dirty(folio, offset, length);
-
-	folio_wait_fscache(folio);
-	_leave("");
+	afs_invalidate_cache(vnode, 0);
 }
 
-/*
- * release a page and clean up its private state if it's not busy
- * - return true if the page can now be released, false if not
- */
-static bool afs_release_folio(struct folio *folio, gfp_t gfp)
-{
-	struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio));
-
-	_enter("{{%llx:%llu}[%lu],%lx},%x",
-	       vnode->fid.vid, vnode->fid.vnode, folio_index(folio), folio->flags,
-	       gfp);
-
-	/* deny if folio is being written to the cache and the caller hasn't
-	 * elected to wait */
-#ifdef CONFIG_AFS_FSCACHE
-	if (folio_test_fscache(folio)) {
-		if (current_is_kswapd() || !(gfp & __GFP_FS))
-			return false;
-		folio_wait_fscache(folio);
-	}
-	fscache_note_page_release(afs_vnode_cache(vnode));
-#endif
-
-	if (folio_test_private(folio)) {
-		trace_afs_folio_dirty(vnode, tracepoint_string("rel"), folio);
-		folio_detach_private(folio);
-	}
-
-	/* Indicate that the folio can be released */
-	_leave(" = T");
-	return true;
-}
+const struct netfs_request_ops afs_req_ops = {
+	.init_request		= afs_init_request,
+	.free_request		= afs_free_request,
+	.check_write_begin	= afs_check_write_begin,
+	.issue_read		= afs_issue_read,
+	.update_i_size		= afs_update_i_size,
+	.invalidate_cache	= afs_netfs_invalidate_cache,
+	.create_write_requests	= afs_create_write_requests,
+};
 
 static void afs_add_open_mmap(struct afs_vnode *vnode)
 {
@@ -525,13 +417,17 @@ static void afs_add_open_mmap(struct afs_vnode *vnode)
 
 static void afs_drop_open_mmap(struct afs_vnode *vnode)
 {
-	if (!atomic_dec_and_test(&vnode->cb_nr_mmap))
+	if (atomic_add_unless(&vnode->cb_nr_mmap, -1, 1))
 		return;
 
 	down_write(&vnode->volume->open_mmaps_lock);
 
-	if (atomic_read(&vnode->cb_nr_mmap) == 0)
+	read_seqlock_excl(&vnode->cb_lock);
+	// the only place where ->cb_nr_mmap may hit 0
+	// see __afs_break_callback() for the other side...
+	if (atomic_dec_and_test(&vnode->cb_nr_mmap))
 		list_del_init(&vnode->cb_mmap_link);
+	read_sequnlock_excl(&vnode->cb_lock);
 
 	up_write(&vnode->volume->open_mmaps_lock);
 	flush_work(&vnode->cb_work);
@@ -576,28 +472,39 @@ static vm_fault_t afs_vm_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pg
 
 static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
-	struct afs_vnode *vnode = AFS_FS_I(file_inode(iocb->ki_filp));
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct afs_vnode *vnode = AFS_FS_I(inode);
 	struct afs_file *af = iocb->ki_filp->private_data;
-	int ret;
+	ssize_t ret;
 
-	ret = afs_validate(vnode, af->key);
+	if (iocb->ki_flags & IOCB_DIRECT)
+		return netfs_unbuffered_read_iter(iocb, iter);
+
+	ret = netfs_start_io_read(inode);
 	if (ret < 0)
 		return ret;
-
-	return generic_file_read_iter(iocb, iter);
+	ret = afs_validate(vnode, af->key);
+	if (ret == 0)
+		ret = filemap_read(iocb, iter, 0);
+	netfs_end_io_read(inode);
+	return ret;
 }
 
 static ssize_t afs_file_splice_read(struct file *in, loff_t *ppos,
 				    struct pipe_inode_info *pipe,
 				    size_t len, unsigned int flags)
 {
-	struct afs_vnode *vnode = AFS_FS_I(file_inode(in));
+	struct inode *inode = file_inode(in);
+	struct afs_vnode *vnode = AFS_FS_I(inode);
 	struct afs_file *af = in->private_data;
-	int ret;
+	ssize_t ret;
 
-	ret = afs_validate(vnode, af->key);
+	ret = netfs_start_io_read(inode);
 	if (ret < 0)
 		return ret;
-
-	return filemap_splice_read(in, ppos, pipe, len, flags);
+	ret = afs_validate(vnode, af->key);
+	if (ret == 0)
+		ret = filemap_splice_read(in, ppos, pipe, len, flags);
+	netfs_end_io_read(inode);
+	return ret;
 }
diff --git a/fs/afs/flock.c b/fs/afs/flock.c
index 9c6dea3139f5..f0e96a35093f 100644
--- a/fs/afs/flock.c
+++ b/fs/afs/flock.c
@@ -93,13 +93,13 @@ static void afs_grant_locks(struct afs_vnode *vnode)
 	bool exclusive = (vnode->lock_type == AFS_LOCK_WRITE);
 
 	list_for_each_entry_safe(p, _p, &vnode->pending_locks, fl_u.afs.link) {
-		if (!exclusive && p->fl_type == F_WRLCK)
+		if (!exclusive && lock_is_write(p))
 			continue;
 
 		list_move_tail(&p->fl_u.afs.link, &vnode->granted_locks);
 		p->fl_u.afs.state = AFS_LOCK_GRANTED;
 		trace_afs_flock_op(vnode, p, afs_flock_op_grant);
-		wake_up(&p->fl_wait);
+		locks_wake_up(p);
 	}
 }
 
@@ -112,25 +112,24 @@ static void afs_next_locker(struct afs_vnode *vnode, int error)
 {
 	struct file_lock *p, *_p, *next = NULL;
 	struct key *key = vnode->lock_key;
-	unsigned int fl_type = F_RDLCK;
+	unsigned int type = F_RDLCK;
 
 	_enter("");
 
 	if (vnode->lock_type == AFS_LOCK_WRITE)
-		fl_type = F_WRLCK;
+		type = F_WRLCK;
 
 	list_for_each_entry_safe(p, _p, &vnode->pending_locks, fl_u.afs.link) {
 		if (error &&
-		    p->fl_type == fl_type &&
-		    afs_file_key(p->fl_file) == key) {
+		    p->c.flc_type == type &&
+		    afs_file_key(p->c.flc_file) == key) {
 			list_del_init(&p->fl_u.afs.link);
 			p->fl_u.afs.state = error;
-			wake_up(&p->fl_wait);
+			locks_wake_up(p);
 		}
 
 		/* Select the next locker to hand off to. */
-		if (next &&
-		    (next->fl_type == F_WRLCK || p->fl_type == F_RDLCK))
+		if (next && (lock_is_write(next) || lock_is_read(p)))
 			continue;
 		next = p;
 	}
@@ -142,7 +141,7 @@ static void afs_next_locker(struct afs_vnode *vnode, int error)
 		afs_set_lock_state(vnode, AFS_VNODE_LOCK_SETTING);
 		next->fl_u.afs.state = AFS_LOCK_YOUR_TRY;
 		trace_afs_flock_op(vnode, next, afs_flock_op_wake);
-		wake_up(&next->fl_wait);
+		locks_wake_up(next);
 	} else {
 		afs_set_lock_state(vnode, AFS_VNODE_LOCK_NONE);
 		trace_afs_flock_ev(vnode, NULL, afs_flock_no_lockers, 0);
@@ -166,7 +165,7 @@ static void afs_kill_lockers_enoent(struct afs_vnode *vnode)
 			       struct file_lock, fl_u.afs.link);
 		list_del_init(&p->fl_u.afs.link);
 		p->fl_u.afs.state = -ENOENT;
-		wake_up(&p->fl_wait);
+		locks_wake_up(p);
 	}
 
 	key_put(vnode->lock_key);
@@ -464,14 +463,14 @@ static int afs_do_setlk(struct file *file, struct file_lock *fl)
 
 	_enter("{%llx:%llu},%llu-%llu,%u,%u",
 	       vnode->fid.vid, vnode->fid.vnode,
-	       fl->fl_start, fl->fl_end, fl->fl_type, mode);
+	       fl->fl_start, fl->fl_end, fl->c.flc_type, mode);
 
 	fl->fl_ops = &afs_lock_ops;
 	INIT_LIST_HEAD(&fl->fl_u.afs.link);
 	fl->fl_u.afs.state = AFS_LOCK_PENDING;
 
 	partial = (fl->fl_start != 0 || fl->fl_end != OFFSET_MAX);
-	type = (fl->fl_type == F_RDLCK) ? AFS_LOCK_READ : AFS_LOCK_WRITE;
+	type = lock_is_read(fl) ? AFS_LOCK_READ : AFS_LOCK_WRITE;
 	if (mode == afs_flock_mode_write && partial)
 		type = AFS_LOCK_WRITE;
 
@@ -524,7 +523,7 @@ static int afs_do_setlk(struct file *file, struct file_lock *fl)
 	}
 
 	if (vnode->lock_state == AFS_VNODE_LOCK_NONE &&
-	    !(fl->fl_flags & FL_SLEEP)) {
+	    !(fl->c.flc_flags & FL_SLEEP)) {
 		ret = -EAGAIN;
 		if (type == AFS_LOCK_READ) {
 			if (vnode->status.lock_count == -1)
@@ -621,7 +620,7 @@ skip_server_lock:
 	return 0;
 
 lock_is_contended:
-	if (!(fl->fl_flags & FL_SLEEP)) {
+	if (!(fl->c.flc_flags & FL_SLEEP)) {
 		list_del_init(&fl->fl_u.afs.link);
 		afs_next_locker(vnode, 0);
 		ret = -EAGAIN;
@@ -641,7 +640,7 @@ need_to_wait:
 	spin_unlock(&vnode->lock);
 
 	trace_afs_flock_ev(vnode, fl, afs_flock_waiting, 0);
-	ret = wait_event_interruptible(fl->fl_wait,
+	ret = wait_event_interruptible(fl->c.flc_wait,
 				       fl->fl_u.afs.state != AFS_LOCK_PENDING);
 	trace_afs_flock_ev(vnode, fl, afs_flock_waited, ret);
 
@@ -704,7 +703,8 @@ static int afs_do_unlk(struct file *file, struct file_lock *fl)
 	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
 	int ret;
 
-	_enter("{%llx:%llu},%u", vnode->fid.vid, vnode->fid.vnode, fl->fl_type);
+	_enter("{%llx:%llu},%u", vnode->fid.vid, vnode->fid.vnode,
+	       fl->c.flc_type);
 
 	trace_afs_flock_op(vnode, fl, afs_flock_op_unlock);
 
@@ -730,11 +730,11 @@ static int afs_do_getlk(struct file *file, struct file_lock *fl)
 	if (vnode->lock_state == AFS_VNODE_LOCK_DELETED)
 		return -ENOENT;
 
-	fl->fl_type = F_UNLCK;
+	fl->c.flc_type = F_UNLCK;
 
 	/* check local lock records first */
 	posix_test_lock(file, fl);
-	if (fl->fl_type == F_UNLCK) {
+	if (lock_is_unlock(fl)) {
 		/* no local locks; consult the server */
 		ret = afs_fetch_status(vnode, key, false, NULL);
 		if (ret < 0)
@@ -743,18 +743,18 @@ static int afs_do_getlk(struct file *file, struct file_lock *fl)
 		lock_count = READ_ONCE(vnode->status.lock_count);
 		if (lock_count != 0) {
 			if (lock_count > 0)
-				fl->fl_type = F_RDLCK;
+				fl->c.flc_type = F_RDLCK;
 			else
-				fl->fl_type = F_WRLCK;
+				fl->c.flc_type = F_WRLCK;
 			fl->fl_start = 0;
 			fl->fl_end = OFFSET_MAX;
-			fl->fl_pid = 0;
+			fl->c.flc_pid = 0;
 		}
 	}
 
 	ret = 0;
 error:
-	_leave(" = %d [%hd]", ret, fl->fl_type);
+	_leave(" = %d [%hd]", ret, fl->c.flc_type);
 	return ret;
 }
 
@@ -769,7 +769,7 @@ int afs_lock(struct file *file, int cmd, struct file_lock *fl)
 
 	_enter("{%llx:%llu},%d,{t=%x,fl=%x,r=%Ld:%Ld}",
 	       vnode->fid.vid, vnode->fid.vnode, cmd,
-	       fl->fl_type, fl->fl_flags,
+	       fl->c.flc_type, fl->c.flc_flags,
 	       (long long) fl->fl_start, (long long) fl->fl_end);
 
 	if (IS_GETLK(cmd))
@@ -778,7 +778,7 @@ int afs_lock(struct file *file, int cmd, struct file_lock *fl)
 	fl->fl_u.afs.debug_id = atomic_inc_return(&afs_file_lock_debug_id);
 	trace_afs_flock_op(vnode, fl, afs_flock_op_lock);
 
-	if (fl->fl_type == F_UNLCK)
+	if (lock_is_unlock(fl))
 		ret = afs_do_unlk(file, fl);
 	else
 		ret = afs_do_setlk(file, fl);
@@ -804,7 +804,7 @@ int afs_flock(struct file *file, int cmd, struct file_lock *fl)
 
 	_enter("{%llx:%llu},%d,{t=%x,fl=%x}",
 	       vnode->fid.vid, vnode->fid.vnode, cmd,
-	       fl->fl_type, fl->fl_flags);
+	       fl->c.flc_type, fl->c.flc_flags);
 
 	/*
 	 * No BSD flocks over NFS allowed.
@@ -813,14 +813,14 @@ int afs_flock(struct file *file, int cmd, struct file_lock *fl)
 	 * Not sure whether that would be unique, though, or whether
 	 * that would break in other places.
 	 */
-	if (!(fl->fl_flags & FL_FLOCK))
+	if (!(fl->c.flc_flags & FL_FLOCK))
 		return -ENOLCK;
 
 	fl->fl_u.afs.debug_id = atomic_inc_return(&afs_file_lock_debug_id);
 	trace_afs_flock_op(vnode, fl, afs_flock_op_flock);
 
 	/* we're simulating flock() locks using posix locks on the server */
-	if (fl->fl_type == F_UNLCK)
+	if (lock_is_unlock(fl))
 		ret = afs_do_unlk(file, fl);
 	else
 		ret = afs_do_setlk(file, fl);
@@ -843,7 +843,7 @@ int afs_flock(struct file *file, int cmd, struct file_lock *fl)
  */
 static void afs_fl_copy_lock(struct file_lock *new, struct file_lock *fl)
 {
-	struct afs_vnode *vnode = AFS_FS_I(file_inode(fl->fl_file));
+	struct afs_vnode *vnode = AFS_FS_I(file_inode(fl->c.flc_file));
 
 	_enter("");
 
@@ -861,7 +861,7 @@ static void afs_fl_copy_lock(struct file_lock *new, struct file_lock *fl)
  */
 static void afs_fl_release_private(struct file_lock *fl)
 {
-	struct afs_vnode *vnode = AFS_FS_I(file_inode(fl->fl_file));
+	struct afs_vnode *vnode = AFS_FS_I(file_inode(fl->c.flc_file));
 
 	_enter("");
 
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 4f04f6f33f46..94fc049aff58 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -58,7 +58,7 @@ static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *paren
  */
 static void afs_set_netfs_context(struct afs_vnode *vnode)
 {
-	netfs_inode_init(&vnode->netfs, &afs_req_ops);
+	netfs_inode_init(&vnode->netfs, &afs_req_ops, true);
 }
 
 /*
@@ -166,6 +166,7 @@ static void afs_apply_status(struct afs_operation *op,
 	struct inode *inode = &vnode->netfs.inode;
 	struct timespec64 t;
 	umode_t mode;
+	bool unexpected_jump = false;
 	bool data_changed = false;
 	bool change_size = vp->set_size;
 
@@ -230,6 +231,7 @@ static void afs_apply_status(struct afs_operation *op,
 		}
 		change_size = true;
 		data_changed = true;
+		unexpected_jump = true;
 	} else if (vnode->status.type == AFS_FTYPE_DIR) {
 		/* Expected directory change is handled elsewhere so
 		 * that we can locally edit the directory and save on a
@@ -249,8 +251,10 @@ static void afs_apply_status(struct afs_operation *op,
 		 * what's on the server.
 		 */
 		vnode->netfs.remote_i_size = status->size;
-		if (change_size) {
+		if (change_size || status->size > i_size_read(inode)) {
 			afs_set_i_size(vnode, status->size);
+			if (unexpected_jump)
+				vnode->netfs.zero_point = status->size;
 			inode_set_ctime_to_ts(inode, t);
 			inode_set_atime_to_ts(inode, t);
 		}
@@ -647,7 +651,7 @@ void afs_evict_inode(struct inode *inode)
 	truncate_inode_pages_final(&inode->i_data);
 
 	afs_set_cache_aux(vnode, &aux);
-	fscache_clear_inode_writeback(afs_vnode_cache(vnode), inode, &aux);
+	netfs_clear_inode_writeback(inode, &aux);
 	clear_inode(inode);
 
 	while (!list_empty(&vnode->wb_keys)) {
@@ -689,17 +693,17 @@ static void afs_setattr_success(struct afs_operation *op)
 static void afs_setattr_edit_file(struct afs_operation *op)
 {
 	struct afs_vnode_param *vp = &op->file[0];
-	struct inode *inode = &vp->vnode->netfs.inode;
+	struct afs_vnode *vnode = vp->vnode;
 
 	if (op->setattr.attr->ia_valid & ATTR_SIZE) {
 		loff_t size = op->setattr.attr->ia_size;
 		loff_t i_size = op->setattr.old_i_size;
 
-		if (size < i_size)
-			truncate_pagecache(inode, size);
-		if (size != i_size)
-			fscache_resize_cookie(afs_vnode_cache(vp->vnode),
-					      vp->scb.status.size);
+		if (size != i_size) {
+			truncate_setsize(&vnode->netfs.inode, size);
+			netfs_resize_file(&vnode->netfs, size, true);
+			fscache_resize_cookie(afs_vnode_cache(vnode), size);
+		}
 	}
 }
 
@@ -767,11 +771,11 @@ int afs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		 */
 		if (!(attr->ia_valid & (supported & ~ATTR_SIZE & ~ATTR_MTIME)) &&
 		    attr->ia_size < i_size &&
-		    attr->ia_size > vnode->status.size) {
-			truncate_pagecache(inode, attr->ia_size);
+		    attr->ia_size > vnode->netfs.remote_i_size) {
+			truncate_setsize(inode, attr->ia_size);
+			netfs_resize_file(&vnode->netfs, size, false);
 			fscache_resize_cookie(afs_vnode_cache(vnode),
 					      attr->ia_size);
-			i_size_write(inode, attr->ia_size);
 			ret = 0;
 			goto out_unlock;
 		}
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 55aa0679d8ce..6ce5a612937c 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -321,8 +321,7 @@ struct afs_net {
 	struct list_head	fs_probe_slow;	/* List of afs_server to probe at 5m intervals */
 	struct hlist_head	fs_proc;	/* procfs servers list */
 
-	struct hlist_head	fs_addresses4;	/* afs_server (by lowest IPv4 addr) */
-	struct hlist_head	fs_addresses6;	/* afs_server (by lowest IPv6 addr) */
+	struct hlist_head	fs_addresses;	/* afs_server (by lowest IPv6 addr) */
 	seqlock_t		fs_addr_lock;	/* For fs_addresses[46] */
 
 	struct work_struct	fs_manager;
@@ -561,8 +560,7 @@ struct afs_server {
 	struct afs_server __rcu	*uuid_next;	/* Next server with same UUID */
 	struct afs_server	*uuid_prev;	/* Previous server with same UUID */
 	struct list_head	probe_link;	/* Link in net->fs_probe_list */
-	struct hlist_node	addr4_link;	/* Link in net->fs_addresses4 */
-	struct hlist_node	addr6_link;	/* Link in net->fs_addresses6 */
+	struct hlist_node	addr_link;	/* Link in net->fs_addresses6 */
 	struct hlist_node	proc_link;	/* Link in net->fs_proc */
 	struct list_head	volumes;	/* RCU list of afs_server_entry objects */
 	struct afs_server	*gc_next;	/* Next server in manager's list */
@@ -985,62 +983,6 @@ static inline void afs_invalidate_cache(struct afs_vnode *vnode, unsigned int fl
 			   i_size_read(&vnode->netfs.inode), flags);
 }
 
-/*
- * We use folio->private to hold the amount of the folio that we've written to,
- * splitting the field into two parts.  However, we need to represent a range
- * 0...FOLIO_SIZE, so we reduce the resolution if the size of the folio
- * exceeds what we can encode.
- */
-#ifdef CONFIG_64BIT
-#define __AFS_FOLIO_PRIV_MASK		0x7fffffffUL
-#define __AFS_FOLIO_PRIV_SHIFT		32
-#define __AFS_FOLIO_PRIV_MMAPPED	0x80000000UL
-#else
-#define __AFS_FOLIO_PRIV_MASK		0x7fffUL
-#define __AFS_FOLIO_PRIV_SHIFT		16
-#define __AFS_FOLIO_PRIV_MMAPPED	0x8000UL
-#endif
-
-static inline unsigned int afs_folio_dirty_resolution(struct folio *folio)
-{
-	int shift = folio_shift(folio) - (__AFS_FOLIO_PRIV_SHIFT - 1);
-	return (shift > 0) ? shift : 0;
-}
-
-static inline size_t afs_folio_dirty_from(struct folio *folio, unsigned long priv)
-{
-	unsigned long x = priv & __AFS_FOLIO_PRIV_MASK;
-
-	/* The lower bound is inclusive */
-	return x << afs_folio_dirty_resolution(folio);
-}
-
-static inline size_t afs_folio_dirty_to(struct folio *folio, unsigned long priv)
-{
-	unsigned long x = (priv >> __AFS_FOLIO_PRIV_SHIFT) & __AFS_FOLIO_PRIV_MASK;
-
-	/* The upper bound is immediately beyond the region */
-	return (x + 1) << afs_folio_dirty_resolution(folio);
-}
-
-static inline unsigned long afs_folio_dirty(struct folio *folio, size_t from, size_t to)
-{
-	unsigned int res = afs_folio_dirty_resolution(folio);
-	from >>= res;
-	to = (to - 1) >> res;
-	return (to << __AFS_FOLIO_PRIV_SHIFT) | from;
-}
-
-static inline unsigned long afs_folio_dirty_mmapped(unsigned long priv)
-{
-	return priv | __AFS_FOLIO_PRIV_MMAPPED;
-}
-
-static inline bool afs_is_folio_dirty_mmapped(unsigned long priv)
-{
-	return priv & __AFS_FOLIO_PRIV_MMAPPED;
-}
-
 #include <trace/events/afs.h>
 
 /*****************************************************************************/
@@ -1167,7 +1109,6 @@ extern int afs_release(struct inode *, struct file *);
 extern int afs_fetch_data(struct afs_vnode *, struct afs_read *);
 extern struct afs_read *afs_alloc_read(gfp_t);
 extern void afs_put_read(struct afs_read *);
-extern int afs_write_inode(struct inode *, struct writeback_control *);
 
 static inline struct afs_read *afs_get_read(struct afs_read *req)
 {
@@ -1658,24 +1599,11 @@ extern int afs_check_volume_status(struct afs_volume *, struct afs_operation *);
 /*
  * write.c
  */
-#ifdef CONFIG_AFS_FSCACHE
-bool afs_dirty_folio(struct address_space *, struct folio *);
-#else
-#define afs_dirty_folio filemap_dirty_folio
-#endif
-extern int afs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata);
-extern int afs_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct page *page, void *fsdata);
-extern int afs_writepage(struct page *, struct writeback_control *);
 extern int afs_writepages(struct address_space *, struct writeback_control *);
-extern ssize_t afs_file_write(struct kiocb *, struct iov_iter *);
 extern int afs_fsync(struct file *, loff_t, loff_t, int);
 extern vm_fault_t afs_page_mkwrite(struct vm_fault *vmf);
 extern void afs_prune_wb_keys(struct afs_vnode *);
-int afs_launder_folio(struct folio *);
+void afs_create_write_requests(struct netfs_io_request *wreq, loff_t start, size_t len);
 
 /*
  * xattr.c
diff --git a/fs/afs/main.c b/fs/afs/main.c
index 1b3bd21c168a..a14f6013e316 100644
--- a/fs/afs/main.c
+++ b/fs/afs/main.c
@@ -90,8 +90,7 @@ static int __net_init afs_net_init(struct net *net_ns)
 	INIT_LIST_HEAD(&net->fs_probe_slow);
 	INIT_HLIST_HEAD(&net->fs_proc);
 
-	INIT_HLIST_HEAD(&net->fs_addresses4);
-	INIT_HLIST_HEAD(&net->fs_addresses6);
+	INIT_HLIST_HEAD(&net->fs_addresses);
 	seqlock_init(&net->fs_addr_lock);
 
 	INIT_WORK(&net->fs_manager, afs_manage_servers);
diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index 3bd02571f30d..15eab053af6d 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -166,7 +166,7 @@ static int afs_proc_addr_prefs_show(struct seq_file *m, void *v)
 
 	if (!preflist) {
 		seq_puts(m, "NO PREFS\n");
-		return 0;
+		goto out;
 	}
 
 	seq_printf(m, "PROT SUBNET                                      PRIOR (v=%u n=%u/%u/%u)\n",
@@ -191,7 +191,8 @@ static int afs_proc_addr_prefs_show(struct seq_file *m, void *v)
 		}
 	}
 
-	rcu_read_lock();
+out:
+	rcu_read_unlock();
 	return 0;
 }
 
diff --git a/fs/afs/server.c b/fs/afs/server.c
index e169121f603e..038f9d0ae3af 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -38,7 +38,7 @@ struct afs_server *afs_find_server(struct afs_net *net, const struct rxrpc_peer
 		seq++; /* 2 on the 1st/lockless path, otherwise odd */
 		read_seqbegin_or_lock(&net->fs_addr_lock, &seq);
 
-		hlist_for_each_entry_rcu(server, &net->fs_addresses6, addr6_link) {
+		hlist_for_each_entry_rcu(server, &net->fs_addresses, addr_link) {
 			estate = rcu_dereference(server->endpoint_state);
 			alist = estate->addresses;
 			for (i = 0; i < alist->nr_addrs; i++)
@@ -177,10 +177,8 @@ added_dup:
 	 * bit, but anything we might want to do gets messy and memory
 	 * intensive.
 	 */
-	if (alist->nr_ipv4 > 0)
-		hlist_add_head_rcu(&server->addr4_link, &net->fs_addresses4);
-	if (alist->nr_addrs > alist->nr_ipv4)
-		hlist_add_head_rcu(&server->addr6_link, &net->fs_addresses6);
+	if (alist->nr_addrs > 0)
+		hlist_add_head_rcu(&server->addr_link, &net->fs_addresses);
 
 	write_sequnlock(&net->fs_addr_lock);
 
@@ -511,10 +509,8 @@ static void afs_gc_servers(struct afs_net *net, struct afs_server *gc_list)
 
 			list_del(&server->probe_link);
 			hlist_del_rcu(&server->proc_link);
-			if (!hlist_unhashed(&server->addr4_link))
-				hlist_del_rcu(&server->addr4_link);
-			if (!hlist_unhashed(&server->addr6_link))
-				hlist_del_rcu(&server->addr6_link);
+			if (!hlist_unhashed(&server->addr_link))
+				hlist_del_rcu(&server->addr_link);
 		}
 		write_sequnlock(&net->fs_lock);
 
diff --git a/fs/afs/super.c b/fs/afs/super.c
index ae2d66a52add..f3ba1c3e72f5 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -55,7 +55,7 @@ int afs_net_id;
 static const struct super_operations afs_super_ops = {
 	.statfs		= afs_statfs,
 	.alloc_inode	= afs_alloc_inode,
-	.write_inode	= afs_write_inode,
+	.write_inode	= netfs_unpin_writeback,
 	.drop_inode	= afs_drop_inode,
 	.destroy_inode	= afs_destroy_inode,
 	.free_inode	= afs_free_inode,
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index 020ecd45e476..af3a3f57c1b3 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -353,7 +353,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key)
 {
 	struct afs_server_list *new, *old, *discard;
 	struct afs_vldb_entry *vldb;
-	char idbuf[16];
+	char idbuf[24];
 	int ret, idsz;
 
 	_enter("");
@@ -361,7 +361,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key)
 	/* We look up an ID by passing it as a decimal string in the
 	 * operation's name parameter.
 	 */
-	idsz = sprintf(idbuf, "%llu", volume->vid);
+	idsz = snprintf(idbuf, sizeof(idbuf), "%llu", volume->vid);
 
 	vldb = afs_vl_lookup_vldb(volume->cell, key, idbuf, idsz);
 	if (IS_ERR(vldb)) {
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 61d34ad2ca7d..74402d95a884 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -12,309 +12,17 @@
 #include <linux/writeback.h>
 #include <linux/pagevec.h>
 #include <linux/netfs.h>
+#include <trace/events/netfs.h>
 #include "internal.h"
 
-static int afs_writepages_region(struct address_space *mapping,
-				 struct writeback_control *wbc,
-				 loff_t start, loff_t end, loff_t *_next,
-				 bool max_one_loop);
-
-static void afs_write_to_cache(struct afs_vnode *vnode, loff_t start, size_t len,
-			       loff_t i_size, bool caching);
-
-#ifdef CONFIG_AFS_FSCACHE
-/*
- * Mark a page as having been made dirty and thus needing writeback.  We also
- * need to pin the cache object to write back to.
- */
-bool afs_dirty_folio(struct address_space *mapping, struct folio *folio)
-{
-	return fscache_dirty_folio(mapping, folio,
-				afs_vnode_cache(AFS_FS_I(mapping->host)));
-}
-static void afs_folio_start_fscache(bool caching, struct folio *folio)
-{
-	if (caching)
-		folio_start_fscache(folio);
-}
-#else
-static void afs_folio_start_fscache(bool caching, struct folio *folio)
-{
-}
-#endif
-
-/*
- * Flush out a conflicting write.  This may extend the write to the surrounding
- * pages if also dirty and contiguous to the conflicting region..
- */
-static int afs_flush_conflicting_write(struct address_space *mapping,
-				       struct folio *folio)
-{
-	struct writeback_control wbc = {
-		.sync_mode	= WB_SYNC_ALL,
-		.nr_to_write	= LONG_MAX,
-		.range_start	= folio_pos(folio),
-		.range_end	= LLONG_MAX,
-	};
-	loff_t next;
-
-	return afs_writepages_region(mapping, &wbc, folio_pos(folio), LLONG_MAX,
-				     &next, true);
-}
-
-/*
- * prepare to perform part of a write to a page
- */
-int afs_write_begin(struct file *file, struct address_space *mapping,
-		    loff_t pos, unsigned len,
-		    struct page **_page, void **fsdata)
-{
-	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
-	struct folio *folio;
-	unsigned long priv;
-	unsigned f, from;
-	unsigned t, to;
-	pgoff_t index;
-	int ret;
-
-	_enter("{%llx:%llu},%llx,%x",
-	       vnode->fid.vid, vnode->fid.vnode, pos, len);
-
-	/* Prefetch area to be written into the cache if we're caching this
-	 * file.  We need to do this before we get a lock on the page in case
-	 * there's more than one writer competing for the same cache block.
-	 */
-	ret = netfs_write_begin(&vnode->netfs, file, mapping, pos, len, &folio, fsdata);
-	if (ret < 0)
-		return ret;
-
-	index = folio_index(folio);
-	from = pos - index * PAGE_SIZE;
-	to = from + len;
-
-try_again:
-	/* See if this page is already partially written in a way that we can
-	 * merge the new write with.
-	 */
-	if (folio_test_private(folio)) {
-		priv = (unsigned long)folio_get_private(folio);
-		f = afs_folio_dirty_from(folio, priv);
-		t = afs_folio_dirty_to(folio, priv);
-		ASSERTCMP(f, <=, t);
-
-		if (folio_test_writeback(folio)) {
-			trace_afs_folio_dirty(vnode, tracepoint_string("alrdy"), folio);
-			folio_unlock(folio);
-			goto wait_for_writeback;
-		}
-		/* If the file is being filled locally, allow inter-write
-		 * spaces to be merged into writes.  If it's not, only write
-		 * back what the user gives us.
-		 */
-		if (!test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags) &&
-		    (to < f || from > t))
-			goto flush_conflicting_write;
-	}
-
-	*_page = folio_file_page(folio, pos / PAGE_SIZE);
-	_leave(" = 0");
-	return 0;
-
-	/* The previous write and this write aren't adjacent or overlapping, so
-	 * flush the page out.
-	 */
-flush_conflicting_write:
-	trace_afs_folio_dirty(vnode, tracepoint_string("confl"), folio);
-	folio_unlock(folio);
-
-	ret = afs_flush_conflicting_write(mapping, folio);
-	if (ret < 0)
-		goto error;
-
-wait_for_writeback:
-	ret = folio_wait_writeback_killable(folio);
-	if (ret < 0)
-		goto error;
-
-	ret = folio_lock_killable(folio);
-	if (ret < 0)
-		goto error;
-	goto try_again;
-
-error:
-	folio_put(folio);
-	_leave(" = %d", ret);
-	return ret;
-}
-
-/*
- * finalise part of a write to a page
- */
-int afs_write_end(struct file *file, struct address_space *mapping,
-		  loff_t pos, unsigned len, unsigned copied,
-		  struct page *subpage, void *fsdata)
-{
-	struct folio *folio = page_folio(subpage);
-	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
-	unsigned long priv;
-	unsigned int f, from = offset_in_folio(folio, pos);
-	unsigned int t, to = from + copied;
-	loff_t i_size, write_end_pos;
-
-	_enter("{%llx:%llu},{%lx}",
-	       vnode->fid.vid, vnode->fid.vnode, folio_index(folio));
-
-	if (!folio_test_uptodate(folio)) {
-		if (copied < len) {
-			copied = 0;
-			goto out;
-		}
-
-		folio_mark_uptodate(folio);
-	}
-
-	if (copied == 0)
-		goto out;
-
-	write_end_pos = pos + copied;
-
-	i_size = i_size_read(&vnode->netfs.inode);
-	if (write_end_pos > i_size) {
-		write_seqlock(&vnode->cb_lock);
-		i_size = i_size_read(&vnode->netfs.inode);
-		if (write_end_pos > i_size)
-			afs_set_i_size(vnode, write_end_pos);
-		write_sequnlock(&vnode->cb_lock);
-		fscache_update_cookie(afs_vnode_cache(vnode), NULL, &write_end_pos);
-	}
-
-	if (folio_test_private(folio)) {
-		priv = (unsigned long)folio_get_private(folio);
-		f = afs_folio_dirty_from(folio, priv);
-		t = afs_folio_dirty_to(folio, priv);
-		if (from < f)
-			f = from;
-		if (to > t)
-			t = to;
-		priv = afs_folio_dirty(folio, f, t);
-		folio_change_private(folio, (void *)priv);
-		trace_afs_folio_dirty(vnode, tracepoint_string("dirty+"), folio);
-	} else {
-		priv = afs_folio_dirty(folio, from, to);
-		folio_attach_private(folio, (void *)priv);
-		trace_afs_folio_dirty(vnode, tracepoint_string("dirty"), folio);
-	}
-
-	if (folio_mark_dirty(folio))
-		_debug("dirtied %lx", folio_index(folio));
-
-out:
-	folio_unlock(folio);
-	folio_put(folio);
-	return copied;
-}
-
-/*
- * kill all the pages in the given range
- */
-static void afs_kill_pages(struct address_space *mapping,
-			   loff_t start, loff_t len)
-{
-	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
-	struct folio *folio;
-	pgoff_t index = start / PAGE_SIZE;
-	pgoff_t last = (start + len - 1) / PAGE_SIZE, next;
-
-	_enter("{%llx:%llu},%llx @%llx",
-	       vnode->fid.vid, vnode->fid.vnode, len, start);
-
-	do {
-		_debug("kill %lx (to %lx)", index, last);
-
-		folio = filemap_get_folio(mapping, index);
-		if (IS_ERR(folio)) {
-			next = index + 1;
-			continue;
-		}
-
-		next = folio_next_index(folio);
-
-		folio_clear_uptodate(folio);
-		folio_end_writeback(folio);
-		folio_lock(folio);
-		generic_error_remove_folio(mapping, folio);
-		folio_unlock(folio);
-		folio_put(folio);
-
-	} while (index = next, index <= last);
-
-	_leave("");
-}
-
-/*
- * Redirty all the pages in a given range.
- */
-static void afs_redirty_pages(struct writeback_control *wbc,
-			      struct address_space *mapping,
-			      loff_t start, loff_t len)
-{
-	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
-	struct folio *folio;
-	pgoff_t index = start / PAGE_SIZE;
-	pgoff_t last = (start + len - 1) / PAGE_SIZE, next;
-
-	_enter("{%llx:%llu},%llx @%llx",
-	       vnode->fid.vid, vnode->fid.vnode, len, start);
-
-	do {
-		_debug("redirty %llx @%llx", len, start);
-
-		folio = filemap_get_folio(mapping, index);
-		if (IS_ERR(folio)) {
-			next = index + 1;
-			continue;
-		}
-
-		next = index + folio_nr_pages(folio);
-		folio_redirty_for_writepage(wbc, folio);
-		folio_end_writeback(folio);
-		folio_put(folio);
-	} while (index = next, index <= last);
-
-	_leave("");
-}
-
 /*
  * completion of write to server
  */
 static void afs_pages_written_back(struct afs_vnode *vnode, loff_t start, unsigned int len)
 {
-	struct address_space *mapping = vnode->netfs.inode.i_mapping;
-	struct folio *folio;
-	pgoff_t end;
-
-	XA_STATE(xas, &mapping->i_pages, start / PAGE_SIZE);
-
 	_enter("{%llx:%llu},{%x @%llx}",
 	       vnode->fid.vid, vnode->fid.vnode, len, start);
 
-	rcu_read_lock();
-
-	end = (start + len - 1) / PAGE_SIZE;
-	xas_for_each(&xas, folio, end) {
-		if (!folio_test_writeback(folio)) {
-			kdebug("bad %x @%llx page %lx %lx",
-			       len, start, folio_index(folio), end);
-			ASSERT(folio_test_writeback(folio));
-		}
-
-		trace_afs_folio_dirty(vnode, tracepoint_string("clear"), folio);
-		folio_detach_private(folio);
-		folio_end_writeback(folio);
-	}
-
-	rcu_read_unlock();
-
 	afs_prune_wb_keys(vnode);
 	_leave("");
 }
@@ -451,363 +159,53 @@ try_next_key:
 	return afs_put_operation(op);
 }
 
-/*
- * Extend the region to be written back to include subsequent contiguously
- * dirty pages if possible, but don't sleep while doing so.
- *
- * If this page holds new content, then we can include filler zeros in the
- * writeback.
- */
-static void afs_extend_writeback(struct address_space *mapping,
-				 struct afs_vnode *vnode,
-				 long *_count,
-				 loff_t start,
-				 loff_t max_len,
-				 bool new_content,
-				 bool caching,
-				 unsigned int *_len)
+static void afs_upload_to_server(struct netfs_io_subrequest *subreq)
 {
-	struct folio_batch fbatch;
-	struct folio *folio;
-	unsigned long priv;
-	unsigned int psize, filler = 0;
-	unsigned int f, t;
-	loff_t len = *_len;
-	pgoff_t index = (start + len) / PAGE_SIZE;
-	bool stop = true;
-	unsigned int i;
-
-	XA_STATE(xas, &mapping->i_pages, index);
-	folio_batch_init(&fbatch);
-
-	do {
-		/* Firstly, we gather up a batch of contiguous dirty pages
-		 * under the RCU read lock - but we can't clear the dirty flags
-		 * there if any of those pages are mapped.
-		 */
-		rcu_read_lock();
-
-		xas_for_each(&xas, folio, ULONG_MAX) {
-			stop = true;
-			if (xas_retry(&xas, folio))
-				continue;
-			if (xa_is_value(folio))
-				break;
-			if (folio_index(folio) != index)
-				break;
-
-			if (!folio_try_get_rcu(folio)) {
-				xas_reset(&xas);
-				continue;
-			}
-
-			/* Has the page moved or been split? */
-			if (unlikely(folio != xas_reload(&xas))) {
-				folio_put(folio);
-				break;
-			}
-
-			if (!folio_trylock(folio)) {
-				folio_put(folio);
-				break;
-			}
-			if (!folio_test_dirty(folio) ||
-			    folio_test_writeback(folio) ||
-			    folio_test_fscache(folio)) {
-				folio_unlock(folio);
-				folio_put(folio);
-				break;
-			}
-
-			psize = folio_size(folio);
-			priv = (unsigned long)folio_get_private(folio);
-			f = afs_folio_dirty_from(folio, priv);
-			t = afs_folio_dirty_to(folio, priv);
-			if (f != 0 && !new_content) {
-				folio_unlock(folio);
-				folio_put(folio);
-				break;
-			}
-
-			len += filler + t;
-			filler = psize - t;
-			if (len >= max_len || *_count <= 0)
-				stop = true;
-			else if (t == psize || new_content)
-				stop = false;
-
-			index += folio_nr_pages(folio);
-			if (!folio_batch_add(&fbatch, folio))
-				break;
-			if (stop)
-				break;
-		}
-
-		if (!stop)
-			xas_pause(&xas);
-		rcu_read_unlock();
-
-		/* Now, if we obtained any folios, we can shift them to being
-		 * writable and mark them for caching.
-		 */
-		if (!folio_batch_count(&fbatch))
-			break;
-
-		for (i = 0; i < folio_batch_count(&fbatch); i++) {
-			folio = fbatch.folios[i];
-			trace_afs_folio_dirty(vnode, tracepoint_string("store+"), folio);
-
-			if (!folio_clear_dirty_for_io(folio))
-				BUG();
-			folio_start_writeback(folio);
-			afs_folio_start_fscache(caching, folio);
-
-			*_count -= folio_nr_pages(folio);
-			folio_unlock(folio);
-		}
+	struct afs_vnode *vnode = AFS_FS_I(subreq->rreq->inode);
+	ssize_t ret;
 
-		folio_batch_release(&fbatch);
-		cond_resched();
-	} while (!stop);
+	_enter("%x[%x],%zx",
+	       subreq->rreq->debug_id, subreq->debug_index, subreq->io_iter.count);
 
-	*_len = len;
+	trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
+	ret = afs_store_data(vnode, &subreq->io_iter, subreq->start,
+			     subreq->rreq->origin == NETFS_LAUNDER_WRITE);
+	netfs_write_subrequest_terminated(subreq, ret < 0 ? ret : subreq->len,
+					  false);
 }
 
-/*
- * Synchronously write back the locked page and any subsequent non-locked dirty
- * pages.
- */
-static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping,
-						struct writeback_control *wbc,
-						struct folio *folio,
-						loff_t start, loff_t end)
+static void afs_upload_to_server_worker(struct work_struct *work)
 {
-	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
-	struct iov_iter iter;
-	unsigned long priv;
-	unsigned int offset, to, len, max_len;
-	loff_t i_size = i_size_read(&vnode->netfs.inode);
-	bool new_content = test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags);
-	bool caching = fscache_cookie_enabled(afs_vnode_cache(vnode));
-	long count = wbc->nr_to_write;
-	int ret;
-
-	_enter(",%lx,%llx-%llx", folio_index(folio), start, end);
-
-	folio_start_writeback(folio);
-	afs_folio_start_fscache(caching, folio);
-
-	count -= folio_nr_pages(folio);
-
-	/* Find all consecutive lockable dirty pages that have contiguous
-	 * written regions, stopping when we find a page that is not
-	 * immediately lockable, is not dirty or is missing, or we reach the
-	 * end of the range.
-	 */
-	priv = (unsigned long)folio_get_private(folio);
-	offset = afs_folio_dirty_from(folio, priv);
-	to = afs_folio_dirty_to(folio, priv);
-	trace_afs_folio_dirty(vnode, tracepoint_string("store"), folio);
-
-	len = to - offset;
-	start += offset;
-	if (start < i_size) {
-		/* Trim the write to the EOF; the extra data is ignored.  Also
-		 * put an upper limit on the size of a single storedata op.
-		 */
-		max_len = 65536 * 4096;
-		max_len = min_t(unsigned long long, max_len, end - start + 1);
-		max_len = min_t(unsigned long long, max_len, i_size - start);
-
-		if (len < max_len &&
-		    (to == folio_size(folio) || new_content))
-			afs_extend_writeback(mapping, vnode, &count,
-					     start, max_len, new_content,
-					     caching, &len);
-		len = min_t(loff_t, len, max_len);
-	}
-
-	/* We now have a contiguous set of dirty pages, each with writeback
-	 * set; the first page is still locked at this point, but all the rest
-	 * have been unlocked.
-	 */
-	folio_unlock(folio);
-
-	if (start < i_size) {
-		_debug("write back %x @%llx [%llx]", len, start, i_size);
-
-		/* Speculatively write to the cache.  We have to fix this up
-		 * later if the store fails.
-		 */
-		afs_write_to_cache(vnode, start, len, i_size, caching);
-
-		iov_iter_xarray(&iter, ITER_SOURCE, &mapping->i_pages, start, len);
-		ret = afs_store_data(vnode, &iter, start, false);
-	} else {
-		_debug("write discard %x @%llx [%llx]", len, start, i_size);
-
-		/* The dirty region was entirely beyond the EOF. */
-		fscache_clear_page_bits(mapping, start, len, caching);
-		afs_pages_written_back(vnode, start, len);
-		ret = 0;
-	}
-
-	switch (ret) {
-	case 0:
-		wbc->nr_to_write = count;
-		ret = len;
-		break;
+	struct netfs_io_subrequest *subreq =
+		container_of(work, struct netfs_io_subrequest, work);
 
-	default:
-		pr_notice("kAFS: Unexpected error from FS.StoreData %d\n", ret);
-		fallthrough;
-	case -EACCES:
-	case -EPERM:
-	case -ENOKEY:
-	case -EKEYEXPIRED:
-	case -EKEYREJECTED:
-	case -EKEYREVOKED:
-	case -ENETRESET:
-		afs_redirty_pages(wbc, mapping, start, len);
-		mapping_set_error(mapping, ret);
-		break;
-
-	case -EDQUOT:
-	case -ENOSPC:
-		afs_redirty_pages(wbc, mapping, start, len);
-		mapping_set_error(mapping, -ENOSPC);
-		break;
-
-	case -EROFS:
-	case -EIO:
-	case -EREMOTEIO:
-	case -EFBIG:
-	case -ENOENT:
-	case -ENOMEDIUM:
-	case -ENXIO:
-		trace_afs_file_error(vnode, ret, afs_file_error_writeback_fail);
-		afs_kill_pages(mapping, start, len);
-		mapping_set_error(mapping, ret);
-		break;
-	}
-
-	_leave(" = %d", ret);
-	return ret;
+	afs_upload_to_server(subreq);
 }
 
 /*
- * write a region of pages back to the server
+ * Set up write requests for a writeback slice.  We need to add a write request
+ * for each write we want to make.
  */
-static int afs_writepages_region(struct address_space *mapping,
-				 struct writeback_control *wbc,
-				 loff_t start, loff_t end, loff_t *_next,
-				 bool max_one_loop)
+void afs_create_write_requests(struct netfs_io_request *wreq, loff_t start, size_t len)
 {
-	struct folio *folio;
-	struct folio_batch fbatch;
-	ssize_t ret;
-	unsigned int i;
-	int n, skips = 0;
-
-	_enter("%llx,%llx,", start, end);
-	folio_batch_init(&fbatch);
-
-	do {
-		pgoff_t index = start / PAGE_SIZE;
-
-		n = filemap_get_folios_tag(mapping, &index, end / PAGE_SIZE,
-					PAGECACHE_TAG_DIRTY, &fbatch);
-
-		if (!n)
-			break;
-		for (i = 0; i < n; i++) {
-			folio = fbatch.folios[i];
-			start = folio_pos(folio); /* May regress with THPs */
-
-			_debug("wback %lx", folio_index(folio));
-
-			/* At this point we hold neither the i_pages lock nor the
-			 * page lock: the page may be truncated or invalidated
-			 * (changing page->mapping to NULL), or even swizzled
-			 * back from swapper_space to tmpfs file mapping
-			 */
-try_again:
-			if (wbc->sync_mode != WB_SYNC_NONE) {
-				ret = folio_lock_killable(folio);
-				if (ret < 0) {
-					folio_batch_release(&fbatch);
-					return ret;
-				}
-			} else {
-				if (!folio_trylock(folio))
-					continue;
-			}
-
-			if (folio->mapping != mapping ||
-			    !folio_test_dirty(folio)) {
-				start += folio_size(folio);
-				folio_unlock(folio);
-				continue;
-			}
-
-			if (folio_test_writeback(folio) ||
-			    folio_test_fscache(folio)) {
-				folio_unlock(folio);
-				if (wbc->sync_mode != WB_SYNC_NONE) {
-					folio_wait_writeback(folio);
-#ifdef CONFIG_AFS_FSCACHE
-					folio_wait_fscache(folio);
-#endif
-					goto try_again;
-				}
-
-				start += folio_size(folio);
-				if (wbc->sync_mode == WB_SYNC_NONE) {
-					if (skips >= 5 || need_resched()) {
-						*_next = start;
-						folio_batch_release(&fbatch);
-						_leave(" = 0 [%llx]", *_next);
-						return 0;
-					}
-					skips++;
-				}
-				continue;
-			}
-
-			if (!folio_clear_dirty_for_io(folio))
-				BUG();
-			ret = afs_write_back_from_locked_folio(mapping, wbc,
-					folio, start, end);
-			if (ret < 0) {
-				_leave(" = %zd", ret);
-				folio_batch_release(&fbatch);
-				return ret;
-			}
-
-			start += ret;
-		}
+	struct netfs_io_subrequest *subreq;
 
-		folio_batch_release(&fbatch);
-		cond_resched();
-	} while (wbc->nr_to_write > 0);
+	_enter("%x,%llx-%llx", wreq->debug_id, start, start + len);
 
-	*_next = start;
-	_leave(" = 0 [%llx]", *_next);
-	return 0;
+	subreq = netfs_create_write_request(wreq, NETFS_UPLOAD_TO_SERVER,
+					    start, len, afs_upload_to_server_worker);
+	if (subreq)
+		netfs_queue_write_request(subreq);
 }
 
 /*
  * write some of the pending data back to the server
  */
-int afs_writepages(struct address_space *mapping,
-		   struct writeback_control *wbc)
+int afs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
 	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
-	loff_t start, next;
 	int ret;
 
-	_enter("");
-
 	/* We have to be careful as we can end up racing with setattr()
 	 * truncating the pagecache since the caller doesn't take a lock here
 	 * to prevent it.
@@ -817,69 +215,12 @@ int afs_writepages(struct address_space *mapping,
 	else if (!down_read_trylock(&vnode->validate_lock))
 		return 0;
 
-	if (wbc->range_cyclic) {
-		start = mapping->writeback_index * PAGE_SIZE;
-		ret = afs_writepages_region(mapping, wbc, start, LLONG_MAX,
-					    &next, false);
-		if (ret == 0) {
-			mapping->writeback_index = next / PAGE_SIZE;
-			if (start > 0 && wbc->nr_to_write > 0) {
-				ret = afs_writepages_region(mapping, wbc, 0,
-							    start, &next, false);
-				if (ret == 0)
-					mapping->writeback_index =
-						next / PAGE_SIZE;
-			}
-		}
-	} else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) {
-		ret = afs_writepages_region(mapping, wbc, 0, LLONG_MAX,
-					    &next, false);
-		if (wbc->nr_to_write > 0 && ret == 0)
-			mapping->writeback_index = next / PAGE_SIZE;
-	} else {
-		ret = afs_writepages_region(mapping, wbc,
-					    wbc->range_start, wbc->range_end,
-					    &next, false);
-	}
-
+	ret = netfs_writepages(mapping, wbc);
 	up_read(&vnode->validate_lock);
-	_leave(" = %d", ret);
 	return ret;
 }
 
 /*
- * write to an AFS file
- */
-ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from)
-{
-	struct afs_vnode *vnode = AFS_FS_I(file_inode(iocb->ki_filp));
-	struct afs_file *af = iocb->ki_filp->private_data;
-	ssize_t result;
-	size_t count = iov_iter_count(from);
-
-	_enter("{%llx:%llu},{%zu},",
-	       vnode->fid.vid, vnode->fid.vnode, count);
-
-	if (IS_SWAPFILE(&vnode->netfs.inode)) {
-		printk(KERN_INFO
-		       "AFS: Attempt to write to active swap file!\n");
-		return -EBUSY;
-	}
-
-	if (!count)
-		return 0;
-
-	result = afs_validate(vnode, af->key);
-	if (result < 0)
-		return result;
-
-	result = generic_file_write_iter(iocb, from);
-
-	_leave(" = %zd", result);
-	return result;
-}
-
-/*
  * flush any dirty pages for this process, and check for write errors.
  * - the return status from this call provides a reliable indication of
  *   whether any write errors occurred for this process.
@@ -907,59 +248,11 @@ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
  */
 vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
 {
-	struct folio *folio = page_folio(vmf->page);
 	struct file *file = vmf->vma->vm_file;
-	struct inode *inode = file_inode(file);
-	struct afs_vnode *vnode = AFS_FS_I(inode);
-	struct afs_file *af = file->private_data;
-	unsigned long priv;
-	vm_fault_t ret = VM_FAULT_RETRY;
-
-	_enter("{{%llx:%llu}},{%lx}", vnode->fid.vid, vnode->fid.vnode, folio_index(folio));
-
-	afs_validate(vnode, af->key);
 
-	sb_start_pagefault(inode->i_sb);
-
-	/* Wait for the page to be written to the cache before we allow it to
-	 * be modified.  We then assume the entire page will need writing back.
-	 */
-#ifdef CONFIG_AFS_FSCACHE
-	if (folio_test_fscache(folio) &&
-	    folio_wait_fscache_killable(folio) < 0)
-		goto out;
-#endif
-
-	if (folio_wait_writeback_killable(folio))
-		goto out;
-
-	if (folio_lock_killable(folio) < 0)
-		goto out;
-
-	/* We mustn't change folio->private until writeback is complete as that
-	 * details the portion of the page we need to write back and we might
-	 * need to redirty the page if there's a problem.
-	 */
-	if (folio_wait_writeback_killable(folio) < 0) {
-		folio_unlock(folio);
-		goto out;
-	}
-
-	priv = afs_folio_dirty(folio, 0, folio_size(folio));
-	priv = afs_folio_dirty_mmapped(priv);
-	if (folio_test_private(folio)) {
-		folio_change_private(folio, (void *)priv);
-		trace_afs_folio_dirty(vnode, tracepoint_string("mkwrite+"), folio);
-	} else {
-		folio_attach_private(folio, (void *)priv);
-		trace_afs_folio_dirty(vnode, tracepoint_string("mkwrite"), folio);
-	}
-	file_update_time(file);
-
-	ret = VM_FAULT_LOCKED;
-out:
-	sb_end_pagefault(inode->i_sb);
-	return ret;
+	if (afs_validate(AFS_FS_I(file_inode(file)), afs_file_key(file)) < 0)
+		return VM_FAULT_SIGBUS;
+	return netfs_page_mkwrite(vmf, NULL);
 }
 
 /*
@@ -989,64 +282,3 @@ void afs_prune_wb_keys(struct afs_vnode *vnode)
 		afs_put_wb_key(wbk);
 	}
 }
-
-/*
- * Clean up a page during invalidation.
- */
-int afs_launder_folio(struct folio *folio)
-{
-	struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio));
-	struct iov_iter iter;
-	struct bio_vec bv;
-	unsigned long priv;
-	unsigned int f, t;
-	int ret = 0;
-
-	_enter("{%lx}", folio->index);
-
-	priv = (unsigned long)folio_get_private(folio);
-	if (folio_clear_dirty_for_io(folio)) {
-		f = 0;
-		t = folio_size(folio);
-		if (folio_test_private(folio)) {
-			f = afs_folio_dirty_from(folio, priv);
-			t = afs_folio_dirty_to(folio, priv);
-		}
-
-		bvec_set_folio(&bv, folio, t - f, f);
-		iov_iter_bvec(&iter, ITER_SOURCE, &bv, 1, bv.bv_len);
-
-		trace_afs_folio_dirty(vnode, tracepoint_string("launder"), folio);
-		ret = afs_store_data(vnode, &iter, folio_pos(folio) + f, true);
-	}
-
-	trace_afs_folio_dirty(vnode, tracepoint_string("laundered"), folio);
-	folio_detach_private(folio);
-	folio_wait_fscache(folio);
-	return ret;
-}
-
-/*
- * Deal with the completion of writing the data to the cache.
- */
-static void afs_write_to_cache_done(void *priv, ssize_t transferred_or_error,
-				    bool was_async)
-{
-	struct afs_vnode *vnode = priv;
-
-	if (IS_ERR_VALUE(transferred_or_error) &&
-	    transferred_or_error != -ENOBUFS)
-		afs_invalidate_cache(vnode, 0);
-}
-
-/*
- * Save the write to the cache also.
- */
-static void afs_write_to_cache(struct afs_vnode *vnode,
-			       loff_t start, size_t len, loff_t i_size,
-			       bool caching)
-{
-	fscache_write_to_cache(afs_vnode_cache(vnode),
-			       vnode->netfs.inode.i_mapping, start, len, i_size,
-			       afs_write_to_cache_done, vnode, caching);
-}
diff --git a/fs/aio.c b/fs/aio.c
index bb2ff48991f3..9cdaa2faa536 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -589,13 +589,24 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events)
 
 void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel)
 {
-	struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, rw);
-	struct kioctx *ctx = req->ki_ctx;
+	struct aio_kiocb *req;
+	struct kioctx *ctx;
 	unsigned long flags;
 
+	/*
+	 * kiocb didn't come from aio or is neither a read nor a write, hence
+	 * ignore it.
+	 */
+	if (!(iocb->ki_flags & IOCB_AIO_RW))
+		return;
+
+	req = container_of(iocb, struct aio_kiocb, rw);
+
 	if (WARN_ON_ONCE(!list_empty(&req->ki_list)))
 		return;
 
+	ctx = req->ki_ctx;
+
 	spin_lock_irqsave(&ctx->ctx_lock, flags);
 	list_add_tail(&req->ki_list, &ctx->active_reqs);
 	req->ki_cancel = cancel;
@@ -1509,7 +1520,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb)
 	req->ki_complete = aio_complete_rw;
 	req->private = NULL;
 	req->ki_pos = iocb->aio_offset;
-	req->ki_flags = req->ki_filp->f_iocb_flags;
+	req->ki_flags = req->ki_filp->f_iocb_flags | IOCB_AIO_RW;
 	if (iocb->aio_flags & IOCB_FLAG_RESFD)
 		req->ki_flags |= IOCB_EVENTFD;
 	if (iocb->aio_flags & IOCB_FLAG_IOPRIO) {
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index d26222b7eefe..0496cb5b6eab 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -79,7 +79,7 @@ static struct file *__anon_inode_getfile(const char *name,
 					 const struct file_operations *fops,
 					 void *priv, int flags,
 					 const struct inode *context_inode,
-					 bool secure)
+					 bool make_inode)
 {
 	struct inode *inode;
 	struct file *file;
@@ -87,7 +87,7 @@ static struct file *__anon_inode_getfile(const char *name,
 	if (fops->owner && !try_module_get(fops->owner))
 		return ERR_PTR(-ENOENT);
 
-	if (secure) {
+	if (make_inode) {
 		inode =	anon_inode_make_secure_inode(name, context_inode);
 		if (IS_ERR(inode)) {
 			file = ERR_CAST(inode);
@@ -149,13 +149,10 @@ struct file *anon_inode_getfile(const char *name,
 EXPORT_SYMBOL_GPL(anon_inode_getfile);
 
 /**
- * anon_inode_getfile_secure - Like anon_inode_getfile(), but creates a new
+ * anon_inode_create_getfile - Like anon_inode_getfile(), but creates a new
  *                             !S_PRIVATE anon inode rather than reuse the
  *                             singleton anon inode and calls the
- *                             inode_init_security_anon() LSM hook.  This
- *                             allows for both the inode to have its own
- *                             security context and for the LSM to enforce
- *                             policy on the inode's creation.
+ *                             inode_init_security_anon() LSM hook.
  *
  * @name:    [in]    name of the "class" of the new file
  * @fops:    [in]    file operations for the new file
@@ -164,11 +161,21 @@ EXPORT_SYMBOL_GPL(anon_inode_getfile);
  * @context_inode:
  *           [in]    the logical relationship with the new inode (optional)
  *
+ * Create a new anonymous inode and file pair.  This can be done for two
+ * reasons:
+ *
+ * - for the inode to have its own security context, so that LSMs can enforce
+ *   policy on the inode's creation;
+ *
+ * - if the caller needs a unique inode, for example in order to customize
+ *   the size returned by fstat()
+ *
  * The LSM may use @context_inode in inode_init_security_anon(), but a
- * reference to it is not held.  Returns the newly created file* or an error
- * pointer.  See the anon_inode_getfile() documentation for more information.
+ * reference to it is not held.
+ *
+ * Returns the newly created file* or an error pointer.
  */
-struct file *anon_inode_getfile_secure(const char *name,
+struct file *anon_inode_create_getfile(const char *name,
 				       const struct file_operations *fops,
 				       void *priv, int flags,
 				       const struct inode *context_inode)
@@ -176,12 +183,13 @@ struct file *anon_inode_getfile_secure(const char *name,
 	return __anon_inode_getfile(name, fops, priv, flags,
 				    context_inode, true);
 }
+EXPORT_SYMBOL_GPL(anon_inode_create_getfile);
 
 static int __anon_inode_getfd(const char *name,
 			      const struct file_operations *fops,
 			      void *priv, int flags,
 			      const struct inode *context_inode,
-			      bool secure)
+			      bool make_inode)
 {
 	int error, fd;
 	struct file *file;
@@ -192,7 +200,7 @@ static int __anon_inode_getfd(const char *name,
 	fd = error;
 
 	file = __anon_inode_getfile(name, fops, priv, flags, context_inode,
-				    secure);
+				    make_inode);
 	if (IS_ERR(file)) {
 		error = PTR_ERR(file);
 		goto err_put_unused_fd;
@@ -231,10 +239,9 @@ int anon_inode_getfd(const char *name, const struct file_operations *fops,
 EXPORT_SYMBOL_GPL(anon_inode_getfd);
 
 /**
- * anon_inode_getfd_secure - Like anon_inode_getfd(), but creates a new
+ * anon_inode_create_getfd - Like anon_inode_getfd(), but creates a new
  * !S_PRIVATE anon inode rather than reuse the singleton anon inode, and calls
- * the inode_init_security_anon() LSM hook. This allows the inode to have its
- * own security context and for a LSM to reject creation of the inode.
+ * the inode_init_security_anon() LSM hook.
  *
  * @name:    [in]    name of the "class" of the new file
  * @fops:    [in]    file operations for the new file
@@ -243,16 +250,26 @@ EXPORT_SYMBOL_GPL(anon_inode_getfd);
  * @context_inode:
  *           [in]    the logical relationship with the new inode (optional)
  *
+ * Create a new anonymous inode and file pair.  This can be done for two
+ * reasons:
+ *
+ * - for the inode to have its own security context, so that LSMs can enforce
+ *   policy on the inode's creation;
+ *
+ * - if the caller needs a unique inode, for example in order to customize
+ *   the size returned by fstat()
+ *
  * The LSM may use @context_inode in inode_init_security_anon(), but a
  * reference to it is not held.
+ *
+ * Returns a newly created file descriptor or an error code.
  */
-int anon_inode_getfd_secure(const char *name, const struct file_operations *fops,
+int anon_inode_create_getfd(const char *name, const struct file_operations *fops,
 			    void *priv, int flags,
 			    const struct inode *context_inode)
 {
 	return __anon_inode_getfd(name, fops, priv, flags, context_inode, true);
 }
-EXPORT_SYMBOL_GPL(anon_inode_getfd_secure);
 
 static int __init anon_inode_init(void)
 {
diff --git a/fs/attr.c b/fs/attr.c
index 5a13f0c8495f..49d23b5dbab4 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -352,7 +352,7 @@ int may_setattr(struct mnt_idmap *idmap, struct inode *inode,
 EXPORT_SYMBOL(may_setattr);
 
 /**
- * notify_change - modify attributes of a filesytem object
+ * notify_change - modify attributes of a filesystem object
  * @idmap:	idmap of the mount the inode was found from
  * @dentry:	object affected
  * @attr:	new attributes
diff --git a/fs/backing-file.c b/fs/backing-file.c
index a681f38d84d8..740185198db3 100644
--- a/fs/backing-file.c
+++ b/fs/backing-file.c
@@ -325,9 +325,7 @@ EXPORT_SYMBOL_GPL(backing_file_mmap);
 
 static int __init backing_aio_init(void)
 {
-	backing_aio_cachep = kmem_cache_create("backing_aio",
-					       sizeof(struct backing_aio),
-					       0, SLAB_HWCACHE_ALIGN, NULL);
+	backing_aio_cachep = KMEM_CACHE(backing_aio, SLAB_HWCACHE_ALIGN);
 	if (!backing_aio_cachep)
 		return -ENOMEM;
 
diff --git a/fs/bcachefs/Makefile b/fs/bcachefs/Makefile
index 7423a3557c68..1a05cecda7cc 100644
--- a/fs/bcachefs/Makefile
+++ b/fs/bcachefs/Makefile
@@ -27,7 +27,6 @@ bcachefs-y		:=	\
 	checksum.o		\
 	clock.o			\
 	compress.o		\
-	counters.o		\
 	darray.o		\
 	debug.o			\
 	dirent.o		\
@@ -71,6 +70,7 @@ bcachefs-y		:=	\
 	reflink.o		\
 	replicas.o		\
 	sb-clean.o		\
+	sb-counters.o		\
 	sb-downgrade.o		\
 	sb-errors.o		\
 	sb-members.o		\
diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c
index a09b9d00226a..fd3e175d8342 100644
--- a/fs/bcachefs/alloc_background.c
+++ b/fs/bcachefs/alloc_background.c
@@ -273,7 +273,7 @@ int bch2_alloc_v4_invalid(struct bch_fs *c, struct bkey_s_c k,
 		bkey_fsck_err_on(!bch2_bucket_sectors_dirty(*a.v),
 				 c, err, alloc_key_dirty_sectors_0,
 				 "data_type %s but dirty_sectors==0",
-				 bch2_data_types[a.v->data_type]);
+				 bch2_data_type_str(a.v->data_type));
 		break;
 	case BCH_DATA_cached:
 		bkey_fsck_err_on(!a.v->cached_sectors ||
@@ -321,16 +321,12 @@ void bch2_alloc_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c
 {
 	struct bch_alloc_v4 _a;
 	const struct bch_alloc_v4 *a = bch2_alloc_to_v4(k, &_a);
-	unsigned i;
 
 	prt_newline(out);
 	printbuf_indent_add(out, 2);
 
-	prt_printf(out, "gen %u oldest_gen %u data_type %s",
-	       a->gen, a->oldest_gen,
-	       a->data_type < BCH_DATA_NR
-	       ? bch2_data_types[a->data_type]
-	       : "(invalid data type)");
+	prt_printf(out, "gen %u oldest_gen %u data_type ", a->gen, a->oldest_gen);
+	bch2_prt_data_type(out, a->data_type);
 	prt_newline(out);
 	prt_printf(out, "journal_seq       %llu",	a->journal_seq);
 	prt_newline(out);
@@ -353,23 +349,6 @@ void bch2_alloc_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c
 	prt_printf(out, "fragmentation     %llu",	a->fragmentation_lru);
 	prt_newline(out);
 	prt_printf(out, "bp_start          %llu", BCH_ALLOC_V4_BACKPOINTERS_START(a));
-	prt_newline(out);
-
-	if (BCH_ALLOC_V4_NR_BACKPOINTERS(a)) {
-		struct bkey_s_c_alloc_v4 a_raw = bkey_s_c_to_alloc_v4(k);
-		const struct bch_backpointer *bps = alloc_v4_backpointers_c(a_raw.v);
-
-		prt_printf(out, "backpointers:     %llu", BCH_ALLOC_V4_NR_BACKPOINTERS(a_raw.v));
-		printbuf_indent_add(out, 2);
-
-		for (i = 0; i < BCH_ALLOC_V4_NR_BACKPOINTERS(a_raw.v); i++) {
-			prt_newline(out);
-			bch2_backpointer_to_text(out, &bps[i]);
-		}
-
-		printbuf_indent_sub(out, 2);
-	}
-
 	printbuf_indent_sub(out, 2);
 }
 
@@ -839,7 +818,7 @@ int bch2_trigger_alloc(struct btree_trans *trans,
 		}
 	}
 
-	if (!(flags & BTREE_TRIGGER_TRANSACTIONAL) && (flags & BTREE_TRIGGER_INSERT)) {
+	if ((flags & BTREE_TRIGGER_ATOMIC) && (flags & BTREE_TRIGGER_INSERT)) {
 		struct bch_alloc_v4 *new_a = bkey_s_to_alloc_v4(new).v;
 		u64 journal_seq = trans->journal_res.seq;
 		u64 bucket_journal_seq = new_a->journal_seq;
@@ -1625,13 +1604,36 @@ int bch2_check_alloc_to_lru_refs(struct bch_fs *c)
 	return ret;
 }
 
+struct discard_buckets_state {
+	u64		seen;
+	u64		open;
+	u64		need_journal_commit;
+	u64		discarded;
+	struct bch_dev	*ca;
+	u64		need_journal_commit_this_dev;
+};
+
+static void discard_buckets_next_dev(struct bch_fs *c, struct discard_buckets_state *s, struct bch_dev *ca)
+{
+	if (s->ca == ca)
+		return;
+
+	if (s->ca && s->need_journal_commit_this_dev >
+	    bch2_dev_usage_read(s->ca).d[BCH_DATA_free].buckets)
+		bch2_journal_flush_async(&c->journal, NULL);
+
+	if (s->ca)
+		percpu_ref_put(&s->ca->ref);
+	if (ca)
+		percpu_ref_get(&ca->ref);
+	s->ca = ca;
+	s->need_journal_commit_this_dev = 0;
+}
+
 static int bch2_discard_one_bucket(struct btree_trans *trans,
 				   struct btree_iter *need_discard_iter,
 				   struct bpos *discard_pos_done,
-				   u64 *seen,
-				   u64 *open,
-				   u64 *need_journal_commit,
-				   u64 *discarded)
+				   struct discard_buckets_state *s)
 {
 	struct bch_fs *c = trans->c;
 	struct bpos pos = need_discard_iter->pos;
@@ -1643,20 +1645,24 @@ static int bch2_discard_one_bucket(struct btree_trans *trans,
 	int ret = 0;
 
 	ca = bch_dev_bkey_exists(c, pos.inode);
+
 	if (!percpu_ref_tryget(&ca->io_ref)) {
 		bch2_btree_iter_set_pos(need_discard_iter, POS(pos.inode + 1, 0));
 		return 0;
 	}
 
+	discard_buckets_next_dev(c, s, ca);
+
 	if (bch2_bucket_is_open_safe(c, pos.inode, pos.offset)) {
-		(*open)++;
+		s->open++;
 		goto out;
 	}
 
 	if (bch2_bucket_needs_journal_commit(&c->buckets_waiting_for_journal,
 			c->journal.flushed_seq_ondisk,
 			pos.inode, pos.offset)) {
-		(*need_journal_commit)++;
+		s->need_journal_commit++;
+		s->need_journal_commit_this_dev++;
 		goto out;
 	}
 
@@ -1709,7 +1715,7 @@ static int bch2_discard_one_bucket(struct btree_trans *trans,
 		 * This works without any other locks because this is the only
 		 * thread that removes items from the need_discard tree
 		 */
-		bch2_trans_unlock(trans);
+		bch2_trans_unlock_long(trans);
 		blkdev_issue_discard(ca->disk_sb.bdev,
 				     k.k->p.offset * ca->mi.bucket_size,
 				     ca->mi.bucket_size,
@@ -1732,9 +1738,9 @@ write:
 		goto out;
 
 	count_event(c, bucket_discard);
-	(*discarded)++;
+	s->discarded++;
 out:
-	(*seen)++;
+	s->seen++;
 	bch2_trans_iter_exit(trans, &iter);
 	percpu_ref_put(&ca->io_ref);
 	printbuf_exit(&buf);
@@ -1744,7 +1750,7 @@ out:
 static void bch2_do_discards_work(struct work_struct *work)
 {
 	struct bch_fs *c = container_of(work, struct bch_fs, discard_work);
-	u64 seen = 0, open = 0, need_journal_commit = 0, discarded = 0;
+	struct discard_buckets_state s = {};
 	struct bpos discard_pos_done = POS_MAX;
 	int ret;
 
@@ -1756,19 +1762,14 @@ static void bch2_do_discards_work(struct work_struct *work)
 	ret = bch2_trans_run(c,
 		for_each_btree_key(trans, iter,
 				   BTREE_ID_need_discard, POS_MIN, 0, k,
-			bch2_discard_one_bucket(trans, &iter, &discard_pos_done,
-						&seen,
-						&open,
-						&need_journal_commit,
-						&discarded)));
-
-	if (need_journal_commit * 2 > seen)
-		bch2_journal_flush_async(&c->journal, NULL);
+			bch2_discard_one_bucket(trans, &iter, &discard_pos_done, &s)));
 
-	bch2_write_ref_put(c, BCH_WRITE_REF_discard);
+	discard_buckets_next_dev(c, &s, NULL);
 
-	trace_discard_buckets(c, seen, open, need_journal_commit, discarded,
+	trace_discard_buckets(c, s.seen, s.open, s.need_journal_commit, s.discarded,
 			      bch2_err_str(ret));
+
+	bch2_write_ref_put(c, BCH_WRITE_REF_discard);
 }
 
 void bch2_do_discards(struct bch_fs *c)
diff --git a/fs/bcachefs/alloc_background_format.h b/fs/bcachefs/alloc_background_format.h
new file mode 100644
index 000000000000..b4ec20be93b8
--- /dev/null
+++ b/fs/bcachefs/alloc_background_format.h
@@ -0,0 +1,92 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_ALLOC_BACKGROUND_FORMAT_H
+#define _BCACHEFS_ALLOC_BACKGROUND_FORMAT_H
+
+struct bch_alloc {
+	struct bch_val		v;
+	__u8			fields;
+	__u8			gen;
+	__u8			data[];
+} __packed __aligned(8);
+
+#define BCH_ALLOC_FIELDS_V1()			\
+	x(read_time,		16)		\
+	x(write_time,		16)		\
+	x(data_type,		8)		\
+	x(dirty_sectors,	16)		\
+	x(cached_sectors,	16)		\
+	x(oldest_gen,		8)		\
+	x(stripe,		32)		\
+	x(stripe_redundancy,	8)
+
+enum {
+#define x(name, _bits) BCH_ALLOC_FIELD_V1_##name,
+	BCH_ALLOC_FIELDS_V1()
+#undef x
+};
+
+struct bch_alloc_v2 {
+	struct bch_val		v;
+	__u8			nr_fields;
+	__u8			gen;
+	__u8			oldest_gen;
+	__u8			data_type;
+	__u8			data[];
+} __packed __aligned(8);
+
+#define BCH_ALLOC_FIELDS_V2()			\
+	x(read_time,		64)		\
+	x(write_time,		64)		\
+	x(dirty_sectors,	32)		\
+	x(cached_sectors,	32)		\
+	x(stripe,		32)		\
+	x(stripe_redundancy,	8)
+
+struct bch_alloc_v3 {
+	struct bch_val		v;
+	__le64			journal_seq;
+	__le32			flags;
+	__u8			nr_fields;
+	__u8			gen;
+	__u8			oldest_gen;
+	__u8			data_type;
+	__u8			data[];
+} __packed __aligned(8);
+
+LE32_BITMASK(BCH_ALLOC_V3_NEED_DISCARD,struct bch_alloc_v3, flags,  0,  1)
+LE32_BITMASK(BCH_ALLOC_V3_NEED_INC_GEN,struct bch_alloc_v3, flags,  1,  2)
+
+struct bch_alloc_v4 {
+	struct bch_val		v;
+	__u64			journal_seq;
+	__u32			flags;
+	__u8			gen;
+	__u8			oldest_gen;
+	__u8			data_type;
+	__u8			stripe_redundancy;
+	__u32			dirty_sectors;
+	__u32			cached_sectors;
+	__u64			io_time[2];
+	__u32			stripe;
+	__u32			nr_external_backpointers;
+	__u64			fragmentation_lru;
+} __packed __aligned(8);
+
+#define BCH_ALLOC_V4_U64s_V0	6
+#define BCH_ALLOC_V4_U64s	(sizeof(struct bch_alloc_v4) / sizeof(__u64))
+
+BITMASK(BCH_ALLOC_V4_NEED_DISCARD,	struct bch_alloc_v4, flags,  0,  1)
+BITMASK(BCH_ALLOC_V4_NEED_INC_GEN,	struct bch_alloc_v4, flags,  1,  2)
+BITMASK(BCH_ALLOC_V4_BACKPOINTERS_START,struct bch_alloc_v4, flags,  2,  8)
+BITMASK(BCH_ALLOC_V4_NR_BACKPOINTERS,	struct bch_alloc_v4, flags,  8,  14)
+
+#define KEY_TYPE_BUCKET_GENS_BITS	8
+#define KEY_TYPE_BUCKET_GENS_NR		(1U << KEY_TYPE_BUCKET_GENS_BITS)
+#define KEY_TYPE_BUCKET_GENS_MASK	(KEY_TYPE_BUCKET_GENS_NR - 1)
+
+struct bch_bucket_gens {
+	struct bch_val		v;
+	u8			gens[KEY_TYPE_BUCKET_GENS_NR];
+} __packed __aligned(8);
+
+#endif /* _BCACHEFS_ALLOC_BACKGROUND_FORMAT_H */
diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c
index b0ff47998a94..633d3223b353 100644
--- a/fs/bcachefs/alloc_foreground.c
+++ b/fs/bcachefs/alloc_foreground.c
@@ -1525,10 +1525,11 @@ static void bch2_open_bucket_to_text(struct printbuf *out, struct bch_fs *c, str
 	unsigned data_type = ob->data_type;
 	barrier(); /* READ_ONCE() doesn't work on bitfields */
 
-	prt_printf(out, "%zu ref %u %s %u:%llu gen %u allocated %u/%u",
+	prt_printf(out, "%zu ref %u ",
 		   ob - c->open_buckets,
-		   atomic_read(&ob->pin),
-		   data_type < BCH_DATA_NR ? bch2_data_types[data_type] : "invalid data type",
+		   atomic_read(&ob->pin));
+	bch2_prt_data_type(out, data_type);
+	prt_printf(out, " %u:%llu gen %u allocated %u/%u",
 		   ob->dev, ob->bucket, ob->gen,
 		   ca->mi.bucket_size - ob->sectors_free, ca->mi.bucket_size);
 	if (ob->ec)
diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c
index e358a2ffffde..569b97904da4 100644
--- a/fs/bcachefs/backpointers.c
+++ b/fs/bcachefs/backpointers.c
@@ -68,9 +68,11 @@ void bch2_backpointer_to_text(struct printbuf *out, const struct bch_backpointer
 
 void bch2_backpointer_k_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k)
 {
-	prt_str(out, "bucket=");
-	bch2_bpos_to_text(out, bp_pos_to_bucket(c, k.k->p));
-	prt_str(out, " ");
+	if (bch2_dev_exists2(c, k.k->p.inode)) {
+		prt_str(out, "bucket=");
+		bch2_bpos_to_text(out, bp_pos_to_bucket(c, k.k->p));
+		prt_str(out, " ");
+	}
 
 	bch2_backpointer_to_text(out, bkey_s_c_to_backpointer(k).v);
 }
@@ -400,13 +402,24 @@ int bch2_check_btree_backpointers(struct bch_fs *c)
 	return ret;
 }
 
+static inline bool bkey_and_val_eq(struct bkey_s_c l, struct bkey_s_c r)
+{
+	return bpos_eq(l.k->p, r.k->p) &&
+		bkey_bytes(l.k) == bkey_bytes(r.k) &&
+		!memcmp(l.v, r.v, bkey_val_bytes(l.k));
+}
+
+struct extents_to_bp_state {
+	struct bpos	bucket_start;
+	struct bpos	bucket_end;
+	struct bkey_buf last_flushed;
+};
+
 static int check_bp_exists(struct btree_trans *trans,
+			   struct extents_to_bp_state *s,
 			   struct bpos bucket,
 			   struct bch_backpointer bp,
-			   struct bkey_s_c orig_k,
-			   struct bpos bucket_start,
-			   struct bpos bucket_end,
-			   struct bkey_buf *last_flushed)
+			   struct bkey_s_c orig_k)
 {
 	struct bch_fs *c = trans->c;
 	struct btree_iter bp_iter = { NULL };
@@ -417,8 +430,8 @@ static int check_bp_exists(struct btree_trans *trans,
 
 	bch2_bkey_buf_init(&tmp);
 
-	if (bpos_lt(bucket, bucket_start) ||
-	    bpos_gt(bucket, bucket_end))
+	if (bpos_lt(bucket, s->bucket_start) ||
+	    bpos_gt(bucket, s->bucket_end))
 		return 0;
 
 	if (!bch2_dev_bucket_exists(c, bucket))
@@ -433,11 +446,9 @@ static int check_bp_exists(struct btree_trans *trans,
 
 	if (bp_k.k->type != KEY_TYPE_backpointer ||
 	    memcmp(bkey_s_c_to_backpointer(bp_k).v, &bp, sizeof(bp))) {
-		if (!bpos_eq(orig_k.k->p, last_flushed->k->k.p) ||
-		    bkey_bytes(orig_k.k) != bkey_bytes(&last_flushed->k->k) ||
-		    memcmp(orig_k.v, &last_flushed->k->v, bkey_val_bytes(orig_k.k))) {
-			bch2_bkey_buf_reassemble(&tmp, c, orig_k);
+		bch2_bkey_buf_reassemble(&tmp, c, orig_k);
 
+		if (!bkey_and_val_eq(orig_k, bkey_i_to_s_c(s->last_flushed.k))) {
 			if (bp.level) {
 				bch2_trans_unlock(trans);
 				bch2_btree_interior_updates_flush(c);
@@ -447,7 +458,7 @@ static int check_bp_exists(struct btree_trans *trans,
 			if (ret)
 				goto err;
 
-			bch2_bkey_buf_copy(last_flushed, c, tmp.k);
+			bch2_bkey_buf_copy(&s->last_flushed, c, tmp.k);
 			ret = -BCH_ERR_transaction_restart_write_buffer_flush;
 			goto out;
 		}
@@ -475,10 +486,8 @@ missing:
 }
 
 static int check_extent_to_backpointers(struct btree_trans *trans,
+					struct extents_to_bp_state *s,
 					enum btree_id btree, unsigned level,
-					struct bpos bucket_start,
-					struct bpos bucket_end,
-					struct bkey_buf *last_flushed,
 					struct bkey_s_c k)
 {
 	struct bch_fs *c = trans->c;
@@ -498,9 +507,7 @@ static int check_extent_to_backpointers(struct btree_trans *trans,
 		bch2_extent_ptr_to_bp(c, btree, level,
 				      k, p, &bucket_pos, &bp);
 
-		ret = check_bp_exists(trans, bucket_pos, bp, k,
-				      bucket_start, bucket_end,
-				      last_flushed);
+		ret = check_bp_exists(trans, s, bucket_pos, bp, k);
 		if (ret)
 			return ret;
 	}
@@ -509,10 +516,8 @@ static int check_extent_to_backpointers(struct btree_trans *trans,
 }
 
 static int check_btree_root_to_backpointers(struct btree_trans *trans,
+					    struct extents_to_bp_state *s,
 					    enum btree_id btree_id,
-					    struct bpos bucket_start,
-					    struct bpos bucket_end,
-					    struct bkey_buf *last_flushed,
 					    int *level)
 {
 	struct bch_fs *c = trans->c;
@@ -536,9 +541,7 @@ retry:
 	*level = b->c.level;
 
 	k = bkey_i_to_s_c(&b->key);
-	ret = check_extent_to_backpointers(trans, btree_id, b->c.level + 1,
-				      bucket_start, bucket_end,
-				      last_flushed, k);
+	ret = check_extent_to_backpointers(trans, s, btree_id, b->c.level + 1, k);
 err:
 	bch2_trans_iter_exit(trans, &iter);
 	return ret;
@@ -559,7 +562,7 @@ static size_t btree_nodes_fit_in_ram(struct bch_fs *c)
 
 	si_meminfo(&i);
 	mem_bytes = i.totalram * i.mem_unit;
-	return div_u64(mem_bytes >> 1, btree_bytes(c));
+	return div_u64(mem_bytes >> 1, c->opts.btree_node_size);
 }
 
 static int bch2_get_btree_in_memory_pos(struct btree_trans *trans,
@@ -610,43 +613,35 @@ static int bch2_get_btree_in_memory_pos(struct btree_trans *trans,
 }
 
 static int bch2_check_extents_to_backpointers_pass(struct btree_trans *trans,
-						   struct bpos bucket_start,
-						   struct bpos bucket_end)
+						   struct extents_to_bp_state *s)
 {
 	struct bch_fs *c = trans->c;
-	struct btree_iter iter;
-	enum btree_id btree_id;
-	struct bkey_s_c k;
-	struct bkey_buf last_flushed;
 	int ret = 0;
 
-	bch2_bkey_buf_init(&last_flushed);
-	bkey_init(&last_flushed.k->k);
-
-	for (btree_id = 0; btree_id < btree_id_nr_alive(c); btree_id++) {
+	for (enum btree_id btree_id = 0;
+	     btree_id < btree_id_nr_alive(c);
+	     btree_id++) {
 		int level, depth = btree_type_has_ptrs(btree_id) ? 0 : 1;
 
 		ret = commit_do(trans, NULL, NULL,
 				BCH_TRANS_COMMIT_no_enospc,
-				check_btree_root_to_backpointers(trans, btree_id,
-							bucket_start, bucket_end,
-							&last_flushed, &level));
+				check_btree_root_to_backpointers(trans, s, btree_id, &level));
 		if (ret)
 			return ret;
 
 		while (level >= depth) {
+			struct btree_iter iter;
 			bch2_trans_node_iter_init(trans, &iter, btree_id, POS_MIN, 0,
 						  level,
 						  BTREE_ITER_PREFETCH);
 			while (1) {
 				bch2_trans_begin(trans);
-				k = bch2_btree_iter_peek(&iter);
+
+				struct bkey_s_c k = bch2_btree_iter_peek(&iter);
 				if (!k.k)
 					break;
 				ret = bkey_err(k) ?:
-					check_extent_to_backpointers(trans, btree_id, level,
-								     bucket_start, bucket_end,
-								     &last_flushed, k) ?:
+					check_extent_to_backpointers(trans, s, btree_id, level, k) ?:
 					bch2_trans_commit(trans, NULL, NULL,
 							  BCH_TRANS_COMMIT_no_enospc);
 				if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) {
@@ -668,7 +663,6 @@ static int bch2_check_extents_to_backpointers_pass(struct btree_trans *trans,
 		}
 	}
 
-	bch2_bkey_buf_exit(&last_flushed, c);
 	return 0;
 }
 
@@ -731,37 +725,43 @@ static int bch2_get_alloc_in_memory_pos(struct btree_trans *trans,
 int bch2_check_extents_to_backpointers(struct bch_fs *c)
 {
 	struct btree_trans *trans = bch2_trans_get(c);
-	struct bpos start = POS_MIN, end;
+	struct extents_to_bp_state s = { .bucket_start = POS_MIN };
 	int ret;
 
+	bch2_bkey_buf_init(&s.last_flushed);
+	bkey_init(&s.last_flushed.k->k);
+
 	while (1) {
-		ret = bch2_get_alloc_in_memory_pos(trans, start, &end);
+		ret = bch2_get_alloc_in_memory_pos(trans, s.bucket_start, &s.bucket_end);
 		if (ret)
 			break;
 
-		if (bpos_eq(start, POS_MIN) && !bpos_eq(end, SPOS_MAX))
+		if ( bpos_eq(s.bucket_start, POS_MIN) &&
+		    !bpos_eq(s.bucket_end, SPOS_MAX))
 			bch_verbose(c, "%s(): alloc info does not fit in ram, running in multiple passes with %zu nodes per pass",
 				    __func__, btree_nodes_fit_in_ram(c));
 
-		if (!bpos_eq(start, POS_MIN) || !bpos_eq(end, SPOS_MAX)) {
+		if (!bpos_eq(s.bucket_start, POS_MIN) ||
+		    !bpos_eq(s.bucket_end, SPOS_MAX)) {
 			struct printbuf buf = PRINTBUF;
 
 			prt_str(&buf, "check_extents_to_backpointers(): ");
-			bch2_bpos_to_text(&buf, start);
+			bch2_bpos_to_text(&buf, s.bucket_start);
 			prt_str(&buf, "-");
-			bch2_bpos_to_text(&buf, end);
+			bch2_bpos_to_text(&buf, s.bucket_end);
 
 			bch_verbose(c, "%s", buf.buf);
 			printbuf_exit(&buf);
 		}
 
-		ret = bch2_check_extents_to_backpointers_pass(trans, start, end);
-		if (ret || bpos_eq(end, SPOS_MAX))
+		ret = bch2_check_extents_to_backpointers_pass(trans, &s);
+		if (ret || bpos_eq(s.bucket_end, SPOS_MAX))
 			break;
 
-		start = bpos_successor(end);
+		s.bucket_start = bpos_successor(s.bucket_end);
 	}
 	bch2_trans_put(trans);
+	bch2_bkey_buf_exit(&s.last_flushed, c);
 
 	bch_err_fn(c, ret);
 	return ret;
diff --git a/fs/bcachefs/backpointers.h b/fs/bcachefs/backpointers.h
index 737e2396ade7..327365a9feac 100644
--- a/fs/bcachefs/backpointers.h
+++ b/fs/bcachefs/backpointers.h
@@ -2,6 +2,7 @@
 #ifndef _BCACHEFS_BACKPOINTERS_BACKGROUND_H
 #define _BCACHEFS_BACKPOINTERS_BACKGROUND_H
 
+#include "btree_cache.h"
 #include "btree_iter.h"
 #include "btree_update.h"
 #include "buckets.h"
diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index dac383e37181..69d0d60d50e3 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -1204,11 +1204,6 @@ static inline unsigned block_sectors(const struct bch_fs *c)
 	return c->opts.block_size >> 9;
 }
 
-static inline size_t btree_sectors(const struct bch_fs *c)
-{
-	return c->opts.btree_node_size >> 9;
-}
-
 static inline bool btree_id_cached(const struct bch_fs *c, enum btree_id btree)
 {
 	return c->btree_key_cache_btrees & (1U << btree);
@@ -1254,6 +1249,18 @@ static inline struct stdio_redirect *bch2_fs_stdio_redirect(struct bch_fs *c)
 	return stdio;
 }
 
+static inline unsigned metadata_replicas_required(struct bch_fs *c)
+{
+	return min(c->opts.metadata_replicas,
+		   c->opts.metadata_replicas_required);
+}
+
+static inline unsigned data_replicas_required(struct bch_fs *c)
+{
+	return min(c->opts.data_replicas,
+		   c->opts.data_replicas_required);
+}
+
 #define BKEY_PADDED_ONSTACK(key, pad)				\
 	struct { struct bkey_i key; __u64 key ## _pad[pad]; }
 
diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index 0d5ac4184fbc..0668b682a21c 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -417,600 +417,12 @@ struct bch_set {
 	struct bch_val		v;
 };
 
-/* Extents */
-
-/*
- * In extent bkeys, the value is a list of pointers (bch_extent_ptr), optionally
- * preceded by checksum/compression information (bch_extent_crc32 or
- * bch_extent_crc64).
- *
- * One major determining factor in the format of extents is how we handle and
- * represent extents that have been partially overwritten and thus trimmed:
- *
- * If an extent is not checksummed or compressed, when the extent is trimmed we
- * don't have to remember the extent we originally allocated and wrote: we can
- * merely adjust ptr->offset to point to the start of the data that is currently
- * live. The size field in struct bkey records the current (live) size of the
- * extent, and is also used to mean "size of region on disk that we point to" in
- * this case.
- *
- * Thus an extent that is not checksummed or compressed will consist only of a
- * list of bch_extent_ptrs, with none of the fields in
- * bch_extent_crc32/bch_extent_crc64.
- *
- * When an extent is checksummed or compressed, it's not possible to read only
- * the data that is currently live: we have to read the entire extent that was
- * originally written, and then return only the part of the extent that is
- * currently live.
- *
- * Thus, in addition to the current size of the extent in struct bkey, we need
- * to store the size of the originally allocated space - this is the
- * compressed_size and uncompressed_size fields in bch_extent_crc32/64. Also,
- * when the extent is trimmed, instead of modifying the offset field of the
- * pointer, we keep a second smaller offset field - "offset into the original
- * extent of the currently live region".
- *
- * The other major determining factor is replication and data migration:
- *
- * Each pointer may have its own bch_extent_crc32/64. When doing a replicated
- * write, we will initially write all the replicas in the same format, with the
- * same checksum type and compression format - however, when copygc runs later (or
- * tiering/cache promotion, anything that moves data), it is not in general
- * going to rewrite all the pointers at once - one of the replicas may be in a
- * bucket on one device that has very little fragmentation while another lives
- * in a bucket that has become heavily fragmented, and thus is being rewritten
- * sooner than the rest.
- *
- * Thus it will only move a subset of the pointers (or in the case of
- * tiering/cache promotion perhaps add a single pointer without dropping any
- * current pointers), and if the extent has been partially overwritten it must
- * write only the currently live portion (or copygc would not be able to reduce
- * fragmentation!) - which necessitates a different bch_extent_crc format for
- * the new pointer.
- *
- * But in the interests of space efficiency, we don't want to store one
- * bch_extent_crc for each pointer if we don't have to.
- *
- * Thus, a bch_extent consists of bch_extent_crc32s, bch_extent_crc64s, and
- * bch_extent_ptrs appended arbitrarily one after the other. We determine the
- * type of a given entry with a scheme similar to utf8 (except we're encoding a
- * type, not a size), encoding the type in the position of the first set bit:
- *
- * bch_extent_crc32	- 0b1
- * bch_extent_ptr	- 0b10
- * bch_extent_crc64	- 0b100
- *
- * We do it this way because bch_extent_crc32 is _very_ constrained on bits (and
- * bch_extent_crc64 is the least constrained).
- *
- * Then, each bch_extent_crc32/64 applies to the pointers that follow after it,
- * until the next bch_extent_crc32/64.
- *
- * If there are no bch_extent_crcs preceding a bch_extent_ptr, then that pointer
- * is neither checksummed nor compressed.
- */
-
 /* 128 bits, sufficient for cryptographic MACs: */
 struct bch_csum {
 	__le64			lo;
 	__le64			hi;
 } __packed __aligned(8);
 
-#define BCH_EXTENT_ENTRY_TYPES()		\
-	x(ptr,			0)		\
-	x(crc32,		1)		\
-	x(crc64,		2)		\
-	x(crc128,		3)		\
-	x(stripe_ptr,		4)		\
-	x(rebalance,		5)
-#define BCH_EXTENT_ENTRY_MAX	6
-
-enum bch_extent_entry_type {
-#define x(f, n) BCH_EXTENT_ENTRY_##f = n,
-	BCH_EXTENT_ENTRY_TYPES()
-#undef x
-};
-
-/* Compressed/uncompressed size are stored biased by 1: */
-struct bch_extent_crc32 {
-#if defined(__LITTLE_ENDIAN_BITFIELD)
-	__u32			type:2,
-				_compressed_size:7,
-				_uncompressed_size:7,
-				offset:7,
-				_unused:1,
-				csum_type:4,
-				compression_type:4;
-	__u32			csum;
-#elif defined (__BIG_ENDIAN_BITFIELD)
-	__u32			csum;
-	__u32			compression_type:4,
-				csum_type:4,
-				_unused:1,
-				offset:7,
-				_uncompressed_size:7,
-				_compressed_size:7,
-				type:2;
-#endif
-} __packed __aligned(8);
-
-#define CRC32_SIZE_MAX		(1U << 7)
-#define CRC32_NONCE_MAX		0
-
-struct bch_extent_crc64 {
-#if defined(__LITTLE_ENDIAN_BITFIELD)
-	__u64			type:3,
-				_compressed_size:9,
-				_uncompressed_size:9,
-				offset:9,
-				nonce:10,
-				csum_type:4,
-				compression_type:4,
-				csum_hi:16;
-#elif defined (__BIG_ENDIAN_BITFIELD)
-	__u64			csum_hi:16,
-				compression_type:4,
-				csum_type:4,
-				nonce:10,
-				offset:9,
-				_uncompressed_size:9,
-				_compressed_size:9,
-				type:3;
-#endif
-	__u64			csum_lo;
-} __packed __aligned(8);
-
-#define CRC64_SIZE_MAX		(1U << 9)
-#define CRC64_NONCE_MAX		((1U << 10) - 1)
-
-struct bch_extent_crc128 {
-#if defined(__LITTLE_ENDIAN_BITFIELD)
-	__u64			type:4,
-				_compressed_size:13,
-				_uncompressed_size:13,
-				offset:13,
-				nonce:13,
-				csum_type:4,
-				compression_type:4;
-#elif defined (__BIG_ENDIAN_BITFIELD)
-	__u64			compression_type:4,
-				csum_type:4,
-				nonce:13,
-				offset:13,
-				_uncompressed_size:13,
-				_compressed_size:13,
-				type:4;
-#endif
-	struct bch_csum		csum;
-} __packed __aligned(8);
-
-#define CRC128_SIZE_MAX		(1U << 13)
-#define CRC128_NONCE_MAX	((1U << 13) - 1)
-
-/*
- * @reservation - pointer hasn't been written to, just reserved
- */
-struct bch_extent_ptr {
-#if defined(__LITTLE_ENDIAN_BITFIELD)
-	__u64			type:1,
-				cached:1,
-				unused:1,
-				unwritten:1,
-				offset:44, /* 8 petabytes */
-				dev:8,
-				gen:8;
-#elif defined (__BIG_ENDIAN_BITFIELD)
-	__u64			gen:8,
-				dev:8,
-				offset:44,
-				unwritten:1,
-				unused:1,
-				cached:1,
-				type:1;
-#endif
-} __packed __aligned(8);
-
-struct bch_extent_stripe_ptr {
-#if defined(__LITTLE_ENDIAN_BITFIELD)
-	__u64			type:5,
-				block:8,
-				redundancy:4,
-				idx:47;
-#elif defined (__BIG_ENDIAN_BITFIELD)
-	__u64			idx:47,
-				redundancy:4,
-				block:8,
-				type:5;
-#endif
-};
-
-struct bch_extent_rebalance {
-#if defined(__LITTLE_ENDIAN_BITFIELD)
-	__u64			type:6,
-				unused:34,
-				compression:8, /* enum bch_compression_opt */
-				target:16;
-#elif defined (__BIG_ENDIAN_BITFIELD)
-	__u64			target:16,
-				compression:8,
-				unused:34,
-				type:6;
-#endif
-};
-
-union bch_extent_entry {
-#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ ||  __BITS_PER_LONG == 64
-	unsigned long			type;
-#elif __BITS_PER_LONG == 32
-	struct {
-		unsigned long		pad;
-		unsigned long		type;
-	};
-#else
-#error edit for your odd byteorder.
-#endif
-
-#define x(f, n) struct bch_extent_##f	f;
-	BCH_EXTENT_ENTRY_TYPES()
-#undef x
-};
-
-struct bch_btree_ptr {
-	struct bch_val		v;
-
-	__u64			_data[0];
-	struct bch_extent_ptr	start[];
-} __packed __aligned(8);
-
-struct bch_btree_ptr_v2 {
-	struct bch_val		v;
-
-	__u64			mem_ptr;
-	__le64			seq;
-	__le16			sectors_written;
-	__le16			flags;
-	struct bpos		min_key;
-	__u64			_data[0];
-	struct bch_extent_ptr	start[];
-} __packed __aligned(8);
-
-LE16_BITMASK(BTREE_PTR_RANGE_UPDATED,	struct bch_btree_ptr_v2, flags, 0, 1);
-
-struct bch_extent {
-	struct bch_val		v;
-
-	__u64			_data[0];
-	union bch_extent_entry	start[];
-} __packed __aligned(8);
-
-struct bch_reservation {
-	struct bch_val		v;
-
-	__le32			generation;
-	__u8			nr_replicas;
-	__u8			pad[3];
-} __packed __aligned(8);
-
-/* Maximum size (in u64s) a single pointer could be: */
-#define BKEY_EXTENT_PTR_U64s_MAX\
-	((sizeof(struct bch_extent_crc128) +			\
-	  sizeof(struct bch_extent_ptr)) / sizeof(__u64))
-
-/* Maximum possible size of an entire extent value: */
-#define BKEY_EXTENT_VAL_U64s_MAX				\
-	(1 + BKEY_EXTENT_PTR_U64s_MAX * (BCH_REPLICAS_MAX + 1))
-
-/* * Maximum possible size of an entire extent, key + value: */
-#define BKEY_EXTENT_U64s_MAX		(BKEY_U64s + BKEY_EXTENT_VAL_U64s_MAX)
-
-/* Btree pointers don't carry around checksums: */
-#define BKEY_BTREE_PTR_VAL_U64s_MAX				\
-	((sizeof(struct bch_btree_ptr_v2) +			\
-	  sizeof(struct bch_extent_ptr) * BCH_REPLICAS_MAX) / sizeof(__u64))
-#define BKEY_BTREE_PTR_U64s_MAX					\
-	(BKEY_U64s + BKEY_BTREE_PTR_VAL_U64s_MAX)
-
-/* Inodes */
-
-#define BLOCKDEV_INODE_MAX	4096
-
-#define BCACHEFS_ROOT_INO	4096
-
-struct bch_inode {
-	struct bch_val		v;
-
-	__le64			bi_hash_seed;
-	__le32			bi_flags;
-	__le16			bi_mode;
-	__u8			fields[];
-} __packed __aligned(8);
-
-struct bch_inode_v2 {
-	struct bch_val		v;
-
-	__le64			bi_journal_seq;
-	__le64			bi_hash_seed;
-	__le64			bi_flags;
-	__le16			bi_mode;
-	__u8			fields[];
-} __packed __aligned(8);
-
-struct bch_inode_v3 {
-	struct bch_val		v;
-
-	__le64			bi_journal_seq;
-	__le64			bi_hash_seed;
-	__le64			bi_flags;
-	__le64			bi_sectors;
-	__le64			bi_size;
-	__le64			bi_version;
-	__u8			fields[];
-} __packed __aligned(8);
-
-#define INODEv3_FIELDS_START_INITIAL	6
-#define INODEv3_FIELDS_START_CUR	(offsetof(struct bch_inode_v3, fields) / sizeof(__u64))
-
-struct bch_inode_generation {
-	struct bch_val		v;
-
-	__le32			bi_generation;
-	__le32			pad;
-} __packed __aligned(8);
-
-/*
- * bi_subvol and bi_parent_subvol are only set for subvolume roots:
- */
-
-#define BCH_INODE_FIELDS_v2()			\
-	x(bi_atime,			96)	\
-	x(bi_ctime,			96)	\
-	x(bi_mtime,			96)	\
-	x(bi_otime,			96)	\
-	x(bi_size,			64)	\
-	x(bi_sectors,			64)	\
-	x(bi_uid,			32)	\
-	x(bi_gid,			32)	\
-	x(bi_nlink,			32)	\
-	x(bi_generation,		32)	\
-	x(bi_dev,			32)	\
-	x(bi_data_checksum,		8)	\
-	x(bi_compression,		8)	\
-	x(bi_project,			32)	\
-	x(bi_background_compression,	8)	\
-	x(bi_data_replicas,		8)	\
-	x(bi_promote_target,		16)	\
-	x(bi_foreground_target,		16)	\
-	x(bi_background_target,		16)	\
-	x(bi_erasure_code,		16)	\
-	x(bi_fields_set,		16)	\
-	x(bi_dir,			64)	\
-	x(bi_dir_offset,		64)	\
-	x(bi_subvol,			32)	\
-	x(bi_parent_subvol,		32)
-
-#define BCH_INODE_FIELDS_v3()			\
-	x(bi_atime,			96)	\
-	x(bi_ctime,			96)	\
-	x(bi_mtime,			96)	\
-	x(bi_otime,			96)	\
-	x(bi_uid,			32)	\
-	x(bi_gid,			32)	\
-	x(bi_nlink,			32)	\
-	x(bi_generation,		32)	\
-	x(bi_dev,			32)	\
-	x(bi_data_checksum,		8)	\
-	x(bi_compression,		8)	\
-	x(bi_project,			32)	\
-	x(bi_background_compression,	8)	\
-	x(bi_data_replicas,		8)	\
-	x(bi_promote_target,		16)	\
-	x(bi_foreground_target,		16)	\
-	x(bi_background_target,		16)	\
-	x(bi_erasure_code,		16)	\
-	x(bi_fields_set,		16)	\
-	x(bi_dir,			64)	\
-	x(bi_dir_offset,		64)	\
-	x(bi_subvol,			32)	\
-	x(bi_parent_subvol,		32)	\
-	x(bi_nocow,			8)
-
-/* subset of BCH_INODE_FIELDS */
-#define BCH_INODE_OPTS()			\
-	x(data_checksum,		8)	\
-	x(compression,			8)	\
-	x(project,			32)	\
-	x(background_compression,	8)	\
-	x(data_replicas,		8)	\
-	x(promote_target,		16)	\
-	x(foreground_target,		16)	\
-	x(background_target,		16)	\
-	x(erasure_code,			16)	\
-	x(nocow,			8)
-
-enum inode_opt_id {
-#define x(name, ...)				\
-	Inode_opt_##name,
-	BCH_INODE_OPTS()
-#undef  x
-	Inode_opt_nr,
-};
-
-#define BCH_INODE_FLAGS()			\
-	x(sync,				0)	\
-	x(immutable,			1)	\
-	x(append,			2)	\
-	x(nodump,			3)	\
-	x(noatime,			4)	\
-	x(i_size_dirty,			5)	\
-	x(i_sectors_dirty,		6)	\
-	x(unlinked,			7)	\
-	x(backptr_untrusted,		8)
-
-/* bits 20+ reserved for packed fields below: */
-
-enum bch_inode_flags {
-#define x(t, n)	BCH_INODE_##t = 1U << n,
-	BCH_INODE_FLAGS()
-#undef x
-};
-
-enum __bch_inode_flags {
-#define x(t, n)	__BCH_INODE_##t = n,
-	BCH_INODE_FLAGS()
-#undef x
-};
-
-LE32_BITMASK(INODE_STR_HASH,	struct bch_inode, bi_flags, 20, 24);
-LE32_BITMASK(INODE_NR_FIELDS,	struct bch_inode, bi_flags, 24, 31);
-LE32_BITMASK(INODE_NEW_VARINT,	struct bch_inode, bi_flags, 31, 32);
-
-LE64_BITMASK(INODEv2_STR_HASH,	struct bch_inode_v2, bi_flags, 20, 24);
-LE64_BITMASK(INODEv2_NR_FIELDS,	struct bch_inode_v2, bi_flags, 24, 31);
-
-LE64_BITMASK(INODEv3_STR_HASH,	struct bch_inode_v3, bi_flags, 20, 24);
-LE64_BITMASK(INODEv3_NR_FIELDS,	struct bch_inode_v3, bi_flags, 24, 31);
-
-LE64_BITMASK(INODEv3_FIELDS_START,
-				struct bch_inode_v3, bi_flags, 31, 36);
-LE64_BITMASK(INODEv3_MODE,	struct bch_inode_v3, bi_flags, 36, 52);
-
-/* Dirents */
-
-/*
- * Dirents (and xattrs) have to implement string lookups; since our b-tree
- * doesn't support arbitrary length strings for the key, we instead index by a
- * 64 bit hash (currently truncated sha1) of the string, stored in the offset
- * field of the key - using linear probing to resolve hash collisions. This also
- * provides us with the readdir cookie posix requires.
- *
- * Linear probing requires us to use whiteouts for deletions, in the event of a
- * collision:
- */
-
-struct bch_dirent {
-	struct bch_val		v;
-
-	/* Target inode number: */
-	union {
-	__le64			d_inum;
-	struct {		/* DT_SUBVOL */
-	__le32			d_child_subvol;
-	__le32			d_parent_subvol;
-	};
-	};
-
-	/*
-	 * Copy of mode bits 12-15 from the target inode - so userspace can get
-	 * the filetype without having to do a stat()
-	 */
-	__u8			d_type;
-
-	__u8			d_name[];
-} __packed __aligned(8);
-
-#define DT_SUBVOL	16
-#define BCH_DT_MAX	17
-
-#define BCH_NAME_MAX	512
-
-/* Xattrs */
-
-#define KEY_TYPE_XATTR_INDEX_USER			0
-#define KEY_TYPE_XATTR_INDEX_POSIX_ACL_ACCESS	1
-#define KEY_TYPE_XATTR_INDEX_POSIX_ACL_DEFAULT	2
-#define KEY_TYPE_XATTR_INDEX_TRUSTED			3
-#define KEY_TYPE_XATTR_INDEX_SECURITY	        4
-
-struct bch_xattr {
-	struct bch_val		v;
-	__u8			x_type;
-	__u8			x_name_len;
-	__le16			x_val_len;
-	__u8			x_name[];
-} __packed __aligned(8);
-
-/* Bucket/allocation information: */
-
-struct bch_alloc {
-	struct bch_val		v;
-	__u8			fields;
-	__u8			gen;
-	__u8			data[];
-} __packed __aligned(8);
-
-#define BCH_ALLOC_FIELDS_V1()			\
-	x(read_time,		16)		\
-	x(write_time,		16)		\
-	x(data_type,		8)		\
-	x(dirty_sectors,	16)		\
-	x(cached_sectors,	16)		\
-	x(oldest_gen,		8)		\
-	x(stripe,		32)		\
-	x(stripe_redundancy,	8)
-
-enum {
-#define x(name, _bits) BCH_ALLOC_FIELD_V1_##name,
-	BCH_ALLOC_FIELDS_V1()
-#undef x
-};
-
-struct bch_alloc_v2 {
-	struct bch_val		v;
-	__u8			nr_fields;
-	__u8			gen;
-	__u8			oldest_gen;
-	__u8			data_type;
-	__u8			data[];
-} __packed __aligned(8);
-
-#define BCH_ALLOC_FIELDS_V2()			\
-	x(read_time,		64)		\
-	x(write_time,		64)		\
-	x(dirty_sectors,	32)		\
-	x(cached_sectors,	32)		\
-	x(stripe,		32)		\
-	x(stripe_redundancy,	8)
-
-struct bch_alloc_v3 {
-	struct bch_val		v;
-	__le64			journal_seq;
-	__le32			flags;
-	__u8			nr_fields;
-	__u8			gen;
-	__u8			oldest_gen;
-	__u8			data_type;
-	__u8			data[];
-} __packed __aligned(8);
-
-LE32_BITMASK(BCH_ALLOC_V3_NEED_DISCARD,struct bch_alloc_v3, flags,  0,  1)
-LE32_BITMASK(BCH_ALLOC_V3_NEED_INC_GEN,struct bch_alloc_v3, flags,  1,  2)
-
-struct bch_alloc_v4 {
-	struct bch_val		v;
-	__u64			journal_seq;
-	__u32			flags;
-	__u8			gen;
-	__u8			oldest_gen;
-	__u8			data_type;
-	__u8			stripe_redundancy;
-	__u32			dirty_sectors;
-	__u32			cached_sectors;
-	__u64			io_time[2];
-	__u32			stripe;
-	__u32			nr_external_backpointers;
-	__u64			fragmentation_lru;
-} __packed __aligned(8);
-
-#define BCH_ALLOC_V4_U64s_V0	6
-#define BCH_ALLOC_V4_U64s	(sizeof(struct bch_alloc_v4) / sizeof(__u64))
-
-BITMASK(BCH_ALLOC_V4_NEED_DISCARD,	struct bch_alloc_v4, flags,  0,  1)
-BITMASK(BCH_ALLOC_V4_NEED_INC_GEN,	struct bch_alloc_v4, flags,  1,  2)
-BITMASK(BCH_ALLOC_V4_BACKPOINTERS_START,struct bch_alloc_v4, flags,  2,  8)
-BITMASK(BCH_ALLOC_V4_NR_BACKPOINTERS,	struct bch_alloc_v4, flags,  8,  14)
-
-#define BCH_ALLOC_V4_NR_BACKPOINTERS_MAX	40
-
 struct bch_backpointer {
 	struct bch_val		v;
 	__u8			btree_id;
@@ -1021,154 +433,6 @@ struct bch_backpointer {
 	struct bpos		pos;
 } __packed __aligned(8);
 
-#define KEY_TYPE_BUCKET_GENS_BITS	8
-#define KEY_TYPE_BUCKET_GENS_NR		(1U << KEY_TYPE_BUCKET_GENS_BITS)
-#define KEY_TYPE_BUCKET_GENS_MASK	(KEY_TYPE_BUCKET_GENS_NR - 1)
-
-struct bch_bucket_gens {
-	struct bch_val		v;
-	u8			gens[KEY_TYPE_BUCKET_GENS_NR];
-} __packed __aligned(8);
-
-/* Quotas: */
-
-enum quota_types {
-	QTYP_USR		= 0,
-	QTYP_GRP		= 1,
-	QTYP_PRJ		= 2,
-	QTYP_NR			= 3,
-};
-
-enum quota_counters {
-	Q_SPC			= 0,
-	Q_INO			= 1,
-	Q_COUNTERS		= 2,
-};
-
-struct bch_quota_counter {
-	__le64			hardlimit;
-	__le64			softlimit;
-};
-
-struct bch_quota {
-	struct bch_val		v;
-	struct bch_quota_counter c[Q_COUNTERS];
-} __packed __aligned(8);
-
-/* Erasure coding */
-
-struct bch_stripe {
-	struct bch_val		v;
-	__le16			sectors;
-	__u8			algorithm;
-	__u8			nr_blocks;
-	__u8			nr_redundant;
-
-	__u8			csum_granularity_bits;
-	__u8			csum_type;
-	__u8			pad;
-
-	struct bch_extent_ptr	ptrs[];
-} __packed __aligned(8);
-
-/* Reflink: */
-
-struct bch_reflink_p {
-	struct bch_val		v;
-	__le64			idx;
-	/*
-	 * A reflink pointer might point to an indirect extent which is then
-	 * later split (by copygc or rebalance). If we only pointed to part of
-	 * the original indirect extent, and then one of the fragments is
-	 * outside the range we point to, we'd leak a refcount: so when creating
-	 * reflink pointers, we need to store pad values to remember the full
-	 * range we were taking a reference on.
-	 */
-	__le32			front_pad;
-	__le32			back_pad;
-} __packed __aligned(8);
-
-struct bch_reflink_v {
-	struct bch_val		v;
-	__le64			refcount;
-	union bch_extent_entry	start[0];
-	__u64			_data[];
-} __packed __aligned(8);
-
-struct bch_indirect_inline_data {
-	struct bch_val		v;
-	__le64			refcount;
-	u8			data[];
-};
-
-/* Inline data */
-
-struct bch_inline_data {
-	struct bch_val		v;
-	u8			data[];
-};
-
-/* Subvolumes: */
-
-#define SUBVOL_POS_MIN		POS(0, 1)
-#define SUBVOL_POS_MAX		POS(0, S32_MAX)
-#define BCACHEFS_ROOT_SUBVOL	1
-
-struct bch_subvolume {
-	struct bch_val		v;
-	__le32			flags;
-	__le32			snapshot;
-	__le64			inode;
-	/*
-	 * Snapshot subvolumes form a tree, separate from the snapshot nodes
-	 * tree - if this subvolume is a snapshot, this is the ID of the
-	 * subvolume it was created from:
-	 */
-	__le32			parent;
-	__le32			pad;
-	bch_le128		otime;
-};
-
-LE32_BITMASK(BCH_SUBVOLUME_RO,		struct bch_subvolume, flags,  0,  1)
-/*
- * We need to know whether a subvolume is a snapshot so we can know whether we
- * can delete it (or whether it should just be rm -rf'd)
- */
-LE32_BITMASK(BCH_SUBVOLUME_SNAP,	struct bch_subvolume, flags,  1,  2)
-LE32_BITMASK(BCH_SUBVOLUME_UNLINKED,	struct bch_subvolume, flags,  2,  3)
-
-/* Snapshots */
-
-struct bch_snapshot {
-	struct bch_val		v;
-	__le32			flags;
-	__le32			parent;
-	__le32			children[2];
-	__le32			subvol;
-	/* corresponds to a bch_snapshot_tree in BTREE_ID_snapshot_trees */
-	__le32			tree;
-	__le32			depth;
-	__le32			skip[3];
-};
-
-LE32_BITMASK(BCH_SNAPSHOT_DELETED,	struct bch_snapshot, flags,  0,  1)
-
-/* True if a subvolume points to this snapshot node: */
-LE32_BITMASK(BCH_SNAPSHOT_SUBVOL,	struct bch_snapshot, flags,  1,  2)
-
-/*
- * Snapshot trees:
- *
- * The snapshot_trees btree gives us persistent indentifier for each tree of
- * bch_snapshot nodes, and allow us to record and easily find the root/master
- * subvolume that other snapshots were created from:
- */
-struct bch_snapshot_tree {
-	struct bch_val		v;
-	__le32			master_subvol;
-	__le32			root_snapshot;
-};
-
 /* LRU btree: */
 
 struct bch_lru {
@@ -1178,33 +442,6 @@ struct bch_lru {
 
 #define LRU_ID_STRIPES		(1U << 16)
 
-/* Logged operations btree: */
-
-struct bch_logged_op_truncate {
-	struct bch_val		v;
-	__le32			subvol;
-	__le32			pad;
-	__le64			inum;
-	__le64			new_i_size;
-};
-
-enum logged_op_finsert_state {
-	LOGGED_OP_FINSERT_start,
-	LOGGED_OP_FINSERT_shift_extents,
-	LOGGED_OP_FINSERT_finish,
-};
-
-struct bch_logged_op_finsert {
-	struct bch_val		v;
-	__u8			state;
-	__u8			pad[3];
-	__le32			subvol;
-	__le64			inum;
-	__le64			dst_offset;
-	__le64			src_offset;
-	__le64			pos;
-};
-
 /* Optional/variable size superblock sections: */
 
 struct bch_sb_field {
@@ -1230,6 +467,19 @@ struct bch_sb_field {
 	x(ext,				13)	\
 	x(downgrade,			14)
 
+#include "alloc_background_format.h"
+#include "extents_format.h"
+#include "reflink_format.h"
+#include "ec_format.h"
+#include "inode_format.h"
+#include "dirent_format.h"
+#include "xattr_format.h"
+#include "quota_format.h"
+#include "logged_ops_format.h"
+#include "snapshot_format.h"
+#include "subvolume_format.h"
+#include "sb-counters_format.h"
+
 enum bch_sb_field_type {
 #define x(f, nr)	BCH_SB_FIELD_##f = nr,
 	BCH_SB_FIELDS()
@@ -1465,23 +715,6 @@ struct bch_sb_field_replicas {
 	struct bch_replicas_entry_v1 entries[];
 } __packed __aligned(8);
 
-/* BCH_SB_FIELD_quota: */
-
-struct bch_sb_quota_counter {
-	__le32				timelimit;
-	__le32				warnlimit;
-};
-
-struct bch_sb_quota_type {
-	__le64				flags;
-	struct bch_sb_quota_counter	c[Q_COUNTERS];
-};
-
-struct bch_sb_field_quota {
-	struct bch_sb_field		field;
-	struct bch_sb_quota_type	q[QTYP_NR];
-} __packed __aligned(8);
-
 /* BCH_SB_FIELD_disk_groups: */
 
 #define BCH_SB_LABEL_SIZE		32
@@ -1500,101 +733,6 @@ struct bch_sb_field_disk_groups {
 	struct bch_disk_group	entries[];
 } __packed __aligned(8);
 
-/* BCH_SB_FIELD_counters */
-
-#define BCH_PERSISTENT_COUNTERS()				\
-	x(io_read,					0)	\
-	x(io_write,					1)	\
-	x(io_move,					2)	\
-	x(bucket_invalidate,				3)	\
-	x(bucket_discard,				4)	\
-	x(bucket_alloc,					5)	\
-	x(bucket_alloc_fail,				6)	\
-	x(btree_cache_scan,				7)	\
-	x(btree_cache_reap,				8)	\
-	x(btree_cache_cannibalize,			9)	\
-	x(btree_cache_cannibalize_lock,			10)	\
-	x(btree_cache_cannibalize_lock_fail,		11)	\
-	x(btree_cache_cannibalize_unlock,		12)	\
-	x(btree_node_write,				13)	\
-	x(btree_node_read,				14)	\
-	x(btree_node_compact,				15)	\
-	x(btree_node_merge,				16)	\
-	x(btree_node_split,				17)	\
-	x(btree_node_rewrite,				18)	\
-	x(btree_node_alloc,				19)	\
-	x(btree_node_free,				20)	\
-	x(btree_node_set_root,				21)	\
-	x(btree_path_relock_fail,			22)	\
-	x(btree_path_upgrade_fail,			23)	\
-	x(btree_reserve_get_fail,			24)	\
-	x(journal_entry_full,				25)	\
-	x(journal_full,					26)	\
-	x(journal_reclaim_finish,			27)	\
-	x(journal_reclaim_start,			28)	\
-	x(journal_write,				29)	\
-	x(read_promote,					30)	\
-	x(read_bounce,					31)	\
-	x(read_split,					33)	\
-	x(read_retry,					32)	\
-	x(read_reuse_race,				34)	\
-	x(move_extent_read,				35)	\
-	x(move_extent_write,				36)	\
-	x(move_extent_finish,				37)	\
-	x(move_extent_fail,				38)	\
-	x(move_extent_start_fail,			39)	\
-	x(copygc,					40)	\
-	x(copygc_wait,					41)	\
-	x(gc_gens_end,					42)	\
-	x(gc_gens_start,				43)	\
-	x(trans_blocked_journal_reclaim,		44)	\
-	x(trans_restart_btree_node_reused,		45)	\
-	x(trans_restart_btree_node_split,		46)	\
-	x(trans_restart_fault_inject,			47)	\
-	x(trans_restart_iter_upgrade,			48)	\
-	x(trans_restart_journal_preres_get,		49)	\
-	x(trans_restart_journal_reclaim,		50)	\
-	x(trans_restart_journal_res_get,		51)	\
-	x(trans_restart_key_cache_key_realloced,	52)	\
-	x(trans_restart_key_cache_raced,		53)	\
-	x(trans_restart_mark_replicas,			54)	\
-	x(trans_restart_mem_realloced,			55)	\
-	x(trans_restart_memory_allocation_failure,	56)	\
-	x(trans_restart_relock,				57)	\
-	x(trans_restart_relock_after_fill,		58)	\
-	x(trans_restart_relock_key_cache_fill,		59)	\
-	x(trans_restart_relock_next_node,		60)	\
-	x(trans_restart_relock_parent_for_fill,		61)	\
-	x(trans_restart_relock_path,			62)	\
-	x(trans_restart_relock_path_intent,		63)	\
-	x(trans_restart_too_many_iters,			64)	\
-	x(trans_restart_traverse,			65)	\
-	x(trans_restart_upgrade,			66)	\
-	x(trans_restart_would_deadlock,			67)	\
-	x(trans_restart_would_deadlock_write,		68)	\
-	x(trans_restart_injected,			69)	\
-	x(trans_restart_key_cache_upgrade,		70)	\
-	x(trans_traverse_all,				71)	\
-	x(transaction_commit,				72)	\
-	x(write_super,					73)	\
-	x(trans_restart_would_deadlock_recursion_limit,	74)	\
-	x(trans_restart_write_buffer_flush,		75)	\
-	x(trans_restart_split_race,			76)	\
-	x(write_buffer_flush_slowpath,			77)	\
-	x(write_buffer_flush_sync,			78)
-
-enum bch_persistent_counters {
-#define x(t, n, ...) BCH_COUNTER_##t,
-	BCH_PERSISTENT_COUNTERS()
-#undef x
-	BCH_COUNTER_NR
-};
-
-struct bch_sb_field_counters {
-	struct bch_sb_field	field;
-	__le64			d[];
-};
-
 /*
  * On clean shutdown, store btree roots and current journal sequence number in
  * the superblock:
diff --git a/fs/bcachefs/bkey.c b/fs/bcachefs/bkey.c
index abdb05507d16..76e79a15ba08 100644
--- a/fs/bcachefs/bkey.c
+++ b/fs/bcachefs/bkey.c
@@ -33,7 +33,7 @@ void bch2_bkey_packed_to_binary_text(struct printbuf *out,
 			next_key_bits -= 64;
 		}
 
-		bch2_prt_u64_binary(out, v, min(word_bits, nr_key_bits));
+		bch2_prt_u64_base2_nbits(out, v, min(word_bits, nr_key_bits));
 
 		if (!next_key_bits)
 			break;
diff --git a/fs/bcachefs/bkey_methods.c b/fs/bcachefs/bkey_methods.c
index 761f5e33b1e6..5e52684764eb 100644
--- a/fs/bcachefs/bkey_methods.c
+++ b/fs/bcachefs/bkey_methods.c
@@ -63,8 +63,17 @@ static int key_type_cookie_invalid(struct bch_fs *c, struct bkey_s_c k,
 	return 0;
 }
 
+static void key_type_cookie_to_text(struct printbuf *out, struct bch_fs *c,
+				    struct bkey_s_c k)
+{
+	struct bkey_s_c_cookie ck = bkey_s_c_to_cookie(k);
+
+	prt_printf(out, "%llu", le64_to_cpu(ck.v->cookie));
+}
+
 #define bch2_bkey_ops_cookie ((struct bkey_ops) {	\
 	.key_invalid	= key_type_cookie_invalid,	\
+	.val_to_text	= key_type_cookie_to_text,	\
 	.min_val_size	= 8,				\
 })
 
diff --git a/fs/bcachefs/bkey_methods.h b/fs/bcachefs/bkey_methods.h
index ee82283722b7..03efe8ee565a 100644
--- a/fs/bcachefs/bkey_methods.h
+++ b/fs/bcachefs/bkey_methods.h
@@ -83,9 +83,10 @@ enum btree_update_flags {
 
 	__BTREE_TRIGGER_NORUN,
 	__BTREE_TRIGGER_TRANSACTIONAL,
+	__BTREE_TRIGGER_ATOMIC,
+	__BTREE_TRIGGER_GC,
 	__BTREE_TRIGGER_INSERT,
 	__BTREE_TRIGGER_OVERWRITE,
-	__BTREE_TRIGGER_GC,
 	__BTREE_TRIGGER_BUCKET_INVALIDATE,
 };
 
@@ -107,6 +108,10 @@ enum btree_update_flags {
  * causing us to go emergency read-only)
  */
 #define BTREE_TRIGGER_TRANSACTIONAL	(1U << __BTREE_TRIGGER_TRANSACTIONAL)
+#define BTREE_TRIGGER_ATOMIC		(1U << __BTREE_TRIGGER_ATOMIC)
+
+/* We're in gc/fsck: running triggers to recalculate e.g. disk usage */
+#define BTREE_TRIGGER_GC		(1U << __BTREE_TRIGGER_GC)
 
 /* @new is entering the btree */
 #define BTREE_TRIGGER_INSERT		(1U << __BTREE_TRIGGER_INSERT)
@@ -114,9 +119,6 @@ enum btree_update_flags {
 /* @old is leaving the btree */
 #define BTREE_TRIGGER_OVERWRITE		(1U << __BTREE_TRIGGER_OVERWRITE)
 
-/* We're in gc/fsck: running triggers to recalculate e.g. disk usage */
-#define BTREE_TRIGGER_GC		(1U << __BTREE_TRIGGER_GC)
-
 /* signal from bucket invalidate path to alloc trigger */
 #define BTREE_TRIGGER_BUCKET_INVALIDATE	(1U << __BTREE_TRIGGER_BUCKET_INVALIDATE)
 
diff --git a/fs/bcachefs/bset.c b/fs/bcachefs/bset.c
index 74bf8eb90a4c..3fd1085b6c61 100644
--- a/fs/bcachefs/bset.c
+++ b/fs/bcachefs/bset.c
@@ -720,7 +720,7 @@ static noinline void __build_ro_aux_tree(struct btree *b, struct bset_tree *t)
 {
 	struct bkey_packed *prev = NULL, *k = btree_bkey_first(b, t);
 	struct bkey_i min_key, max_key;
-	unsigned j, cacheline = 1;
+	unsigned cacheline = 1;
 
 	t->size = min(bkey_to_cacheline(b, t, btree_bkey_last(b, t)),
 		      bset_ro_tree_capacity(b, t));
@@ -823,13 +823,12 @@ void bch2_bset_init_first(struct btree *b, struct bset *i)
 	set_btree_bset(b, t, i);
 }
 
-void bch2_bset_init_next(struct bch_fs *c, struct btree *b,
-			 struct btree_node_entry *bne)
+void bch2_bset_init_next(struct btree *b, struct btree_node_entry *bne)
 {
 	struct bset *i = &bne->keys;
 	struct bset_tree *t;
 
-	BUG_ON(bset_byte_offset(b, bne) >= btree_bytes(c));
+	BUG_ON(bset_byte_offset(b, bne) >= btree_buf_bytes(b));
 	BUG_ON((void *) bne < (void *) btree_bkey_last(b, bset_tree_last(b)));
 	BUG_ON(b->nsets >= MAX_BSETS);
 
diff --git a/fs/bcachefs/bset.h b/fs/bcachefs/bset.h
index 632c2b8c5460..79c77baaa383 100644
--- a/fs/bcachefs/bset.h
+++ b/fs/bcachefs/bset.h
@@ -264,8 +264,7 @@ static inline struct bset *bset_next_set(struct btree *b,
 void bch2_btree_keys_init(struct btree *);
 
 void bch2_bset_init_first(struct btree *, struct bset *);
-void bch2_bset_init_next(struct bch_fs *, struct btree *,
-			 struct btree_node_entry *);
+void bch2_bset_init_next(struct btree *, struct btree_node_entry *);
 void bch2_bset_build_aux_tree(struct btree *, struct bset_tree *, bool);
 
 void bch2_bset_insert(struct btree *, struct btree_node_iter *,
diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c
index 8e2488a4b58d..d7c81beac14a 100644
--- a/fs/bcachefs/btree_cache.c
+++ b/fs/bcachefs/btree_cache.c
@@ -60,7 +60,7 @@ static void btree_node_data_free(struct bch_fs *c, struct btree *b)
 
 	clear_btree_node_just_written(b);
 
-	kvpfree(b->data, btree_bytes(c));
+	kvpfree(b->data, btree_buf_bytes(b));
 	b->data = NULL;
 #ifdef __KERNEL__
 	kvfree(b->aux_data);
@@ -94,7 +94,7 @@ static int btree_node_data_alloc(struct bch_fs *c, struct btree *b, gfp_t gfp)
 {
 	BUG_ON(b->data || b->aux_data);
 
-	b->data = kvpmalloc(btree_bytes(c), gfp);
+	b->data = kvpmalloc(btree_buf_bytes(b), gfp);
 	if (!b->data)
 		return -BCH_ERR_ENOMEM_btree_node_mem_alloc;
 #ifdef __KERNEL__
@@ -107,7 +107,7 @@ static int btree_node_data_alloc(struct bch_fs *c, struct btree *b, gfp_t gfp)
 		b->aux_data = NULL;
 #endif
 	if (!b->aux_data) {
-		kvpfree(b->data, btree_bytes(c));
+		kvpfree(b->data, btree_buf_bytes(b));
 		b->data = NULL;
 		return -BCH_ERR_ENOMEM_btree_node_mem_alloc;
 	}
@@ -126,7 +126,7 @@ static struct btree *__btree_node_mem_alloc(struct bch_fs *c, gfp_t gfp)
 	bkey_btree_ptr_init(&b->key);
 	INIT_LIST_HEAD(&b->list);
 	INIT_LIST_HEAD(&b->write_blocked);
-	b->byte_order = ilog2(btree_bytes(c));
+	b->byte_order = ilog2(c->opts.btree_node_size);
 	return b;
 }
 
@@ -408,7 +408,7 @@ void bch2_fs_btree_cache_exit(struct bch_fs *c)
 	if (c->verify_data)
 		list_move(&c->verify_data->list, &bc->live);
 
-	kvpfree(c->verify_ondisk, btree_bytes(c));
+	kvpfree(c->verify_ondisk, c->opts.btree_node_size);
 
 	for (i = 0; i < btree_id_nr_alive(c); i++) {
 		struct btree_root *r = bch2_btree_id_root(c, i);
@@ -1192,7 +1192,7 @@ void bch2_btree_node_to_text(struct printbuf *out, struct bch_fs *c, const struc
 	       "    failed unpacked %zu\n",
 	       b->unpack_fn_len,
 	       b->nr.live_u64s * sizeof(u64),
-	       btree_bytes(c) - sizeof(struct btree_node),
+	       btree_buf_bytes(b) - sizeof(struct btree_node),
 	       b->nr.live_u64s * 100 / btree_max_u64s(c),
 	       b->sib_u64s[0],
 	       b->sib_u64s[1],
diff --git a/fs/bcachefs/btree_cache.h b/fs/bcachefs/btree_cache.h
index 4e1af5882052..6d33885fdbde 100644
--- a/fs/bcachefs/btree_cache.h
+++ b/fs/bcachefs/btree_cache.h
@@ -74,22 +74,27 @@ static inline bool btree_node_hashed(struct btree *b)
 	     _iter = 0;	_iter < (_tbl)->size; _iter++)			\
 		rht_for_each_entry_rcu((_b), (_pos), _tbl, _iter, hash)
 
-static inline size_t btree_bytes(struct bch_fs *c)
+static inline size_t btree_buf_bytes(const struct btree *b)
 {
-	return c->opts.btree_node_size;
+	return 1UL << b->byte_order;
 }
 
-static inline size_t btree_max_u64s(struct bch_fs *c)
+static inline size_t btree_buf_max_u64s(const struct btree *b)
 {
-	return (btree_bytes(c) - sizeof(struct btree_node)) / sizeof(u64);
+	return (btree_buf_bytes(b) - sizeof(struct btree_node)) / sizeof(u64);
 }
 
-static inline size_t btree_pages(struct bch_fs *c)
+static inline size_t btree_max_u64s(const struct bch_fs *c)
 {
-	return btree_bytes(c) / PAGE_SIZE;
+	return (c->opts.btree_node_size - sizeof(struct btree_node)) / sizeof(u64);
 }
 
-static inline unsigned btree_blocks(struct bch_fs *c)
+static inline size_t btree_sectors(const struct bch_fs *c)
+{
+	return c->opts.btree_node_size >> SECTOR_SHIFT;
+}
+
+static inline unsigned btree_blocks(const struct bch_fs *c)
 {
 	return btree_sectors(c) >> c->block_bits;
 }
diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index 49b4ade758c3..1102995643b1 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -597,7 +597,7 @@ static int bch2_check_fix_ptrs(struct btree_trans *trans, enum btree_id btree_id
 			      "bucket %u:%zu data type %s ptr gen %u missing in alloc btree\n"
 			      "while marking %s",
 			      p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr),
-			      bch2_data_types[ptr_data_type(k->k, &p.ptr)],
+			      bch2_data_type_str(ptr_data_type(k->k, &p.ptr)),
 			      p.ptr.gen,
 			      (printbuf_reset(&buf),
 			       bch2_bkey_val_to_text(&buf, c, *k), buf.buf)))) {
@@ -615,7 +615,7 @@ static int bch2_check_fix_ptrs(struct btree_trans *trans, enum btree_id btree_id
 			      "bucket %u:%zu data type %s ptr gen in the future: %u > %u\n"
 			      "while marking %s",
 			      p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr),
-			      bch2_data_types[ptr_data_type(k->k, &p.ptr)],
+			      bch2_data_type_str(ptr_data_type(k->k, &p.ptr)),
 			      p.ptr.gen, g->gen,
 			      (printbuf_reset(&buf),
 			       bch2_bkey_val_to_text(&buf, c, *k), buf.buf)))) {
@@ -637,7 +637,7 @@ static int bch2_check_fix_ptrs(struct btree_trans *trans, enum btree_id btree_id
 			      "bucket %u:%zu gen %u data type %s: ptr gen %u too stale\n"
 			      "while marking %s",
 			      p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr), g->gen,
-			      bch2_data_types[ptr_data_type(k->k, &p.ptr)],
+			      bch2_data_type_str(ptr_data_type(k->k, &p.ptr)),
 			      p.ptr.gen,
 			      (printbuf_reset(&buf),
 			       bch2_bkey_val_to_text(&buf, c, *k), buf.buf))))
@@ -649,7 +649,7 @@ static int bch2_check_fix_ptrs(struct btree_trans *trans, enum btree_id btree_id
 			      "bucket %u:%zu data type %s stale dirty ptr: %u < %u\n"
 			      "while marking %s",
 			      p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr),
-			      bch2_data_types[ptr_data_type(k->k, &p.ptr)],
+			      bch2_data_type_str(ptr_data_type(k->k, &p.ptr)),
 			      p.ptr.gen, g->gen,
 			      (printbuf_reset(&buf),
 			       bch2_bkey_val_to_text(&buf, c, *k), buf.buf))))
@@ -664,8 +664,8 @@ static int bch2_check_fix_ptrs(struct btree_trans *trans, enum btree_id btree_id
 				"bucket %u:%zu different types of data in same bucket: %s, %s\n"
 				"while marking %s",
 				p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr),
-				bch2_data_types[g->data_type],
-				bch2_data_types[data_type],
+				bch2_data_type_str(g->data_type),
+				bch2_data_type_str(data_type),
 				(printbuf_reset(&buf),
 				 bch2_bkey_val_to_text(&buf, c, *k), buf.buf))) {
 			if (data_type == BCH_DATA_btree) {
@@ -1238,11 +1238,11 @@ static int bch2_gc_done(struct bch_fs *c,
 
 		for (i = 0; i < BCH_DATA_NR; i++) {
 			copy_dev_field(dev_usage_buckets_wrong,
-				       d[i].buckets,	"%s buckets", bch2_data_types[i]);
+				       d[i].buckets,	"%s buckets", bch2_data_type_str(i));
 			copy_dev_field(dev_usage_sectors_wrong,
-				       d[i].sectors,	"%s sectors", bch2_data_types[i]);
+				       d[i].sectors,	"%s sectors", bch2_data_type_str(i));
 			copy_dev_field(dev_usage_fragmented_wrong,
-				       d[i].fragmented,	"%s fragmented", bch2_data_types[i]);
+				       d[i].fragmented,	"%s fragmented", bch2_data_type_str(i));
 		}
 	}
 
@@ -1253,19 +1253,19 @@ static int bch2_gc_done(struct bch_fs *c,
 			bch2_acc_percpu_u64s((u64 __percpu *) c->usage_gc, nr);
 
 		copy_fs_field(fs_usage_hidden_wrong,
-			      hidden,		"hidden");
+			      b.hidden,		"hidden");
 		copy_fs_field(fs_usage_btree_wrong,
-			      btree,		"btree");
+			      b.btree,		"btree");
 
 		if (!metadata_only) {
 			copy_fs_field(fs_usage_data_wrong,
-				      data,	"data");
+				      b.data,	"data");
 			copy_fs_field(fs_usage_cached_wrong,
-				      cached,	"cached");
+				      b.cached,	"cached");
 			copy_fs_field(fs_usage_reserved_wrong,
-				      reserved,	"reserved");
+				      b.reserved,	"reserved");
 			copy_fs_field(fs_usage_nr_inodes_wrong,
-				      nr_inodes,"nr_inodes");
+				      b.nr_inodes,"nr_inodes");
 
 			for (i = 0; i < BCH_REPLICAS_MAX; i++)
 				copy_fs_field(fs_usage_persistent_reserved_wrong,
@@ -1417,8 +1417,8 @@ static int bch2_alloc_write_key(struct btree_trans *trans,
 			": got %s, should be %s",
 			iter->pos.inode, iter->pos.offset,
 			gc.gen,
-			bch2_data_types[new.data_type],
-			bch2_data_types[gc.data_type]))
+			bch2_data_type_str(new.data_type),
+			bch2_data_type_str(gc.data_type)))
 		new.data_type = gc.data_type;
 
 #define copy_bucket_field(_errtype, _f)					\
@@ -1428,7 +1428,7 @@ static int bch2_alloc_write_key(struct btree_trans *trans,
 			": got %u, should be %u",			\
 			iter->pos.inode, iter->pos.offset,		\
 			gc.gen,						\
-			bch2_data_types[gc.data_type],			\
+			bch2_data_type_str(gc.data_type),		\
 			new._f, gc._f))					\
 		new._f = gc._f;						\
 
diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index 33db48e2153f..aa9b6cbe3226 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -112,7 +112,7 @@ static void *btree_bounce_alloc(struct bch_fs *c, size_t size,
 	unsigned flags = memalloc_nofs_save();
 	void *p;
 
-	BUG_ON(size > btree_bytes(c));
+	BUG_ON(size > c->opts.btree_node_size);
 
 	*used_mempool = false;
 	p = vpmalloc(size, __GFP_NOWARN|GFP_NOWAIT);
@@ -174,8 +174,8 @@ static void bch2_sort_whiteouts(struct bch_fs *c, struct btree *b)
 
 	ptrs = ptrs_end = ((void *) new_whiteouts + bytes);
 
-	for (k = unwritten_whiteouts_start(c, b);
-	     k != unwritten_whiteouts_end(c, b);
+	for (k = unwritten_whiteouts_start(b);
+	     k != unwritten_whiteouts_end(b);
 	     k = bkey_p_next(k))
 		*--ptrs = k;
 
@@ -192,7 +192,7 @@ static void bch2_sort_whiteouts(struct bch_fs *c, struct btree *b)
 	verify_no_dups(b, new_whiteouts,
 		       (void *) ((u64 *) new_whiteouts + b->whiteout_u64s));
 
-	memcpy_u64s(unwritten_whiteouts_start(c, b),
+	memcpy_u64s(unwritten_whiteouts_start(b),
 		    new_whiteouts, b->whiteout_u64s);
 
 	btree_bounce_free(c, bytes, used_mempool, new_whiteouts);
@@ -313,7 +313,7 @@ static void btree_node_sort(struct bch_fs *c, struct btree *b,
 	}
 
 	bytes = sorting_entire_node
-		? btree_bytes(c)
+		? btree_buf_bytes(b)
 		: __vstruct_bytes(struct btree_node, u64s);
 
 	out = btree_bounce_alloc(c, bytes, &used_mempool);
@@ -338,7 +338,7 @@ static void btree_node_sort(struct bch_fs *c, struct btree *b,
 	if (sorting_entire_node) {
 		u64s = le16_to_cpu(out->keys.u64s);
 
-		BUG_ON(bytes != btree_bytes(c));
+		BUG_ON(bytes != btree_buf_bytes(b));
 
 		/*
 		 * Our temporary buffer is the same size as the btree node's
@@ -502,7 +502,7 @@ void bch2_btree_init_next(struct btree_trans *trans, struct btree *b)
 
 	bne = want_new_bset(c, b);
 	if (bne)
-		bch2_bset_init_next(c, b, bne);
+		bch2_bset_init_next(b, bne);
 
 	bch2_btree_build_aux_trees(b);
 
@@ -1160,7 +1160,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 			     ptr_written, b->written);
 	} else {
 		for (bne = write_block(b);
-		     bset_byte_offset(b, bne) < btree_bytes(c);
+		     bset_byte_offset(b, bne) < btree_buf_bytes(b);
 		     bne = (void *) bne + block_bytes(c))
 			btree_err_on(bne->keys.seq == b->data->keys.seq &&
 				     !bch2_journal_seq_is_blacklisted(c,
@@ -1172,7 +1172,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 				     "found bset signature after last bset");
 	}
 
-	sorted = btree_bounce_alloc(c, btree_bytes(c), &used_mempool);
+	sorted = btree_bounce_alloc(c, btree_buf_bytes(b), &used_mempool);
 	sorted->keys.u64s = 0;
 
 	set_btree_bset(b, b->set, &b->data->keys);
@@ -1188,7 +1188,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 
 	BUG_ON(b->nr.live_u64s != u64s);
 
-	btree_bounce_free(c, btree_bytes(c), used_mempool, sorted);
+	btree_bounce_free(c, btree_buf_bytes(b), used_mempool, sorted);
 
 	if (updated_range)
 		bch2_btree_node_drop_keys_outside_node(b);
@@ -1284,7 +1284,7 @@ static void btree_node_read_work(struct work_struct *work)
 		rb->have_ioref		= bch2_dev_get_ioref(ca, READ);
 		bio_reset(bio, NULL, REQ_OP_READ|REQ_SYNC|REQ_META);
 		bio->bi_iter.bi_sector	= rb->pick.ptr.offset;
-		bio->bi_iter.bi_size	= btree_bytes(c);
+		bio->bi_iter.bi_size	= btree_buf_bytes(b);
 
 		if (rb->have_ioref) {
 			bio_set_dev(bio, ca->disk_sb.bdev);
@@ -1512,7 +1512,7 @@ fsck_err:
 	}
 
 	if (best >= 0) {
-		memcpy(b->data, ra->buf[best], btree_bytes(c));
+		memcpy(b->data, ra->buf[best], btree_buf_bytes(b));
 		ret = bch2_btree_node_read_done(c, NULL, b, false, saw_error);
 	} else {
 		ret = -1;
@@ -1578,7 +1578,7 @@ static int btree_node_read_all_replicas(struct bch_fs *c, struct btree *b, bool
 	for (i = 0; i < ra->nr; i++) {
 		ra->buf[i] = mempool_alloc(&c->btree_bounce_pool, GFP_NOFS);
 		ra->bio[i] = bio_alloc_bioset(NULL,
-					      buf_pages(ra->buf[i], btree_bytes(c)),
+					      buf_pages(ra->buf[i], btree_buf_bytes(b)),
 					      REQ_OP_READ|REQ_SYNC|REQ_META,
 					      GFP_NOFS,
 					      &c->btree_bio);
@@ -1598,7 +1598,7 @@ static int btree_node_read_all_replicas(struct bch_fs *c, struct btree *b, bool
 		rb->pick		= pick;
 		rb->bio.bi_iter.bi_sector = pick.ptr.offset;
 		rb->bio.bi_end_io	= btree_node_read_all_replicas_endio;
-		bch2_bio_map(&rb->bio, ra->buf[i], btree_bytes(c));
+		bch2_bio_map(&rb->bio, ra->buf[i], btree_buf_bytes(b));
 
 		if (rb->have_ioref) {
 			this_cpu_add(ca->io_done->sectors[READ][BCH_DATA_btree],
@@ -1665,7 +1665,7 @@ void bch2_btree_node_read(struct btree_trans *trans, struct btree *b,
 	ca = bch_dev_bkey_exists(c, pick.ptr.dev);
 
 	bio = bio_alloc_bioset(NULL,
-			       buf_pages(b->data, btree_bytes(c)),
+			       buf_pages(b->data, btree_buf_bytes(b)),
 			       REQ_OP_READ|REQ_SYNC|REQ_META,
 			       GFP_NOFS,
 			       &c->btree_bio);
@@ -1679,7 +1679,7 @@ void bch2_btree_node_read(struct btree_trans *trans, struct btree *b,
 	INIT_WORK(&rb->work, btree_node_read_work);
 	bio->bi_iter.bi_sector	= pick.ptr.offset;
 	bio->bi_end_io		= btree_node_read_endio;
-	bch2_bio_map(bio, b->data, btree_bytes(c));
+	bch2_bio_map(bio, b->data, btree_buf_bytes(b));
 
 	if (rb->have_ioref) {
 		this_cpu_add(ca->io_done->sectors[READ][BCH_DATA_btree],
@@ -2074,8 +2074,8 @@ do_write:
 	i->u64s		= 0;
 
 	sort_iter_add(&sort_iter.iter,
-		      unwritten_whiteouts_start(c, b),
-		      unwritten_whiteouts_end(c, b));
+		      unwritten_whiteouts_start(b),
+		      unwritten_whiteouts_end(b));
 	SET_BSET_SEPARATE_WHITEOUTS(i, false);
 
 	b->whiteout_u64s = 0;
@@ -2251,7 +2251,7 @@ bool bch2_btree_post_write_cleanup(struct bch_fs *c, struct btree *b)
 
 	bne = want_new_bset(c, b);
 	if (bne)
-		bch2_bset_init_next(c, b, bne);
+		bch2_bset_init_next(b, bne);
 
 	bch2_btree_build_aux_trees(b);
 
diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index fa298289e016..3ef338df82f5 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/btree_iter.c
@@ -1337,7 +1337,7 @@ void bch2_path_put(struct btree_trans *trans, btree_path_idx_t path_idx, bool in
 
 	if (path->should_be_locked &&
 	    !trans->restarted &&
-	    (!dup || !bch2_btree_path_relock_norestart(trans, dup, _THIS_IP_)))
+	    (!dup || !bch2_btree_path_relock_norestart(trans, dup)))
 		return;
 
 	if (dup) {
@@ -2156,7 +2156,9 @@ struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos e
 		 * isn't monotonically increasing before FILTER_SNAPSHOTS, and
 		 * that's what we check against in extents mode:
 		 */
-		if (k.k->p.inode > end.inode)
+		if (unlikely(!(iter->flags & BTREE_ITER_IS_EXTENTS)
+			     ? bkey_gt(k.k->p, end)
+			     : k.k->p.inode > end.inode))
 			goto end;
 
 		if (iter->update_path &&
diff --git a/fs/bcachefs/btree_iter.h b/fs/bcachefs/btree_iter.h
index da2b74fa63fc..24772538e4cc 100644
--- a/fs/bcachefs/btree_iter.h
+++ b/fs/bcachefs/btree_iter.h
@@ -819,6 +819,11 @@ __bch2_btree_iter_peek_and_restart(struct btree_trans *trans,
 #define for_each_btree_key_continue_norestart(_iter, _flags, _k, _ret)	\
 	for_each_btree_key_upto_continue_norestart(_iter, SPOS_MAX, _flags, _k, _ret)
 
+/*
+ * This should not be used in a fastpath, without first trying _do in
+ * nonblocking mode - it will cause excessive transaction restarts and
+ * potentially livelocking:
+ */
 #define drop_locks_do(_trans, _do)					\
 ({									\
 	bch2_trans_unlock(_trans);					\
diff --git a/fs/bcachefs/btree_locking.c b/fs/bcachefs/btree_locking.c
index 2d1c95c42f24..684397442338 100644
--- a/fs/bcachefs/btree_locking.c
+++ b/fs/bcachefs/btree_locking.c
@@ -92,7 +92,7 @@ static noinline void print_cycle(struct printbuf *out, struct lock_graph *g)
 			continue;
 
 		bch2_btree_trans_to_text(out, i->trans);
-		bch2_prt_task_backtrace(out, task, i == g->g ? 5 : 1);
+		bch2_prt_task_backtrace(out, task, i == g->g ? 5 : 1, GFP_NOWAIT);
 	}
 }
 
@@ -227,7 +227,7 @@ static noinline int break_cycle(struct lock_graph *g, struct printbuf *cycle)
 			prt_printf(&buf, "backtrace:");
 			prt_newline(&buf);
 			printbuf_indent_add(&buf, 2);
-			bch2_prt_task_backtrace(&buf, trans->locking_wait.task, 2);
+			bch2_prt_task_backtrace(&buf, trans->locking_wait.task, 2, GFP_NOWAIT);
 			printbuf_indent_sub(&buf, 2);
 			prt_newline(&buf);
 		}
@@ -631,8 +631,7 @@ int bch2_btree_path_relock_intent(struct btree_trans *trans,
 }
 
 __flatten
-bool bch2_btree_path_relock_norestart(struct btree_trans *trans,
-			struct btree_path *path, unsigned long trace_ip)
+bool bch2_btree_path_relock_norestart(struct btree_trans *trans, struct btree_path *path)
 {
 	struct get_locks_fail f;
 
@@ -642,7 +641,7 @@ bool bch2_btree_path_relock_norestart(struct btree_trans *trans,
 int __bch2_btree_path_relock(struct btree_trans *trans,
 			struct btree_path *path, unsigned long trace_ip)
 {
-	if (!bch2_btree_path_relock_norestart(trans, path, trace_ip)) {
+	if (!bch2_btree_path_relock_norestart(trans, path)) {
 		trace_and_count(trans->c, trans_restart_relock_path, trans, trace_ip, path);
 		return btree_trans_restart(trans, BCH_ERR_transaction_restart_relock_path);
 	}
@@ -759,12 +758,39 @@ int bch2_trans_relock(struct btree_trans *trans)
 	if (unlikely(trans->restarted))
 		return -((int) trans->restarted);
 
-	trans_for_each_path(trans, path, i)
+	trans_for_each_path(trans, path, i) {
+		struct get_locks_fail f;
+
 		if (path->should_be_locked &&
-		    !bch2_btree_path_relock_norestart(trans, path, _RET_IP_)) {
-			trace_and_count(trans->c, trans_restart_relock, trans, _RET_IP_, path);
+		    !btree_path_get_locks(trans, path, false, &f)) {
+			if (trace_trans_restart_relock_enabled()) {
+				struct printbuf buf = PRINTBUF;
+
+				bch2_bpos_to_text(&buf, path->pos);
+				prt_printf(&buf, " l=%u seq=%u node seq=",
+					   f.l, path->l[f.l].lock_seq);
+				if (IS_ERR_OR_NULL(f.b)) {
+					prt_str(&buf, bch2_err_str(PTR_ERR(f.b)));
+				} else {
+					prt_printf(&buf, "%u", f.b->c.lock.seq);
+
+					struct six_lock_count c =
+						bch2_btree_node_lock_counts(trans, NULL, &f.b->c, f.l);
+					prt_printf(&buf, " self locked %u.%u.%u", c.n[0], c.n[1], c.n[2]);
+
+					c = six_lock_counts(&f.b->c.lock);
+					prt_printf(&buf, " total locked %u.%u.%u", c.n[0], c.n[1], c.n[2]);
+				}
+
+				trace_trans_restart_relock(trans, _RET_IP_, buf.buf);
+				printbuf_exit(&buf);
+			}
+
+			count_event(trans->c, trans_restart_relock);
 			return btree_trans_restart(trans, BCH_ERR_transaction_restart_relock);
 		}
+	}
+
 	return 0;
 }
 
@@ -778,7 +804,7 @@ int bch2_trans_relock_notrace(struct btree_trans *trans)
 
 	trans_for_each_path(trans, path, i)
 		if (path->should_be_locked &&
-		    !bch2_btree_path_relock_norestart(trans, path, _RET_IP_)) {
+		    !bch2_btree_path_relock_norestart(trans, path)) {
 			return btree_trans_restart(trans, BCH_ERR_transaction_restart_relock);
 		}
 	return 0;
diff --git a/fs/bcachefs/btree_locking.h b/fs/bcachefs/btree_locking.h
index cc5500a957a1..4bd72c855da1 100644
--- a/fs/bcachefs/btree_locking.h
+++ b/fs/bcachefs/btree_locking.h
@@ -312,8 +312,7 @@ void bch2_btree_node_lock_write_nofail(struct btree_trans *,
 
 /* relock: */
 
-bool bch2_btree_path_relock_norestart(struct btree_trans *,
-				      struct btree_path *, unsigned long);
+bool bch2_btree_path_relock_norestart(struct btree_trans *, struct btree_path *);
 int __bch2_btree_path_relock(struct btree_trans *,
 			     struct btree_path *, unsigned long);
 
@@ -353,12 +352,6 @@ static inline bool bch2_btree_node_relock_notrace(struct btree_trans *trans,
 
 /* upgrade */
 
-
-struct get_locks_fail {
-	unsigned	l;
-	struct btree	*b;
-};
-
 bool bch2_btree_path_upgrade_noupgrade_sibs(struct btree_trans *,
 			       struct btree_path *, unsigned,
 			       struct get_locks_fail *);
diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c
index 90eb8065ff2d..30d69a6d133e 100644
--- a/fs/bcachefs/btree_trans_commit.c
+++ b/fs/bcachefs/btree_trans_commit.c
@@ -139,8 +139,7 @@ bool bch2_btree_bset_insert_key(struct btree_trans *trans,
 	EBUG_ON(bkey_deleted(&insert->k) && bkey_val_u64s(&insert->k));
 	EBUG_ON(bpos_lt(insert->k.p, b->data->min_key));
 	EBUG_ON(bpos_gt(insert->k.p, b->data->max_key));
-	EBUG_ON(insert->k.u64s >
-		bch_btree_keys_u64s_remaining(trans->c, b));
+	EBUG_ON(insert->k.u64s > bch2_btree_keys_u64s_remaining(b));
 	EBUG_ON(!b->c.level && !bpos_eq(insert->k.p, path->pos));
 
 	k = bch2_btree_node_iter_peek_all(node_iter, b);
@@ -160,7 +159,7 @@ bool bch2_btree_bset_insert_key(struct btree_trans *trans,
 		k->type = KEY_TYPE_deleted;
 
 		if (k->needs_whiteout)
-			push_whiteout(trans->c, b, insert->k.p);
+			push_whiteout(b, insert->k.p);
 		k->needs_whiteout = false;
 
 		if (k >= btree_bset_last(b)->start) {
@@ -348,9 +347,7 @@ static noinline void journal_transaction_name(struct btree_trans *trans)
 static inline int btree_key_can_insert(struct btree_trans *trans,
 				       struct btree *b, unsigned u64s)
 {
-	struct bch_fs *c = trans->c;
-
-	if (!bch2_btree_node_insert_fits(c, b, u64s))
+	if (!bch2_btree_node_insert_fits(b, u64s))
 		return -BCH_ERR_btree_insert_btree_node_full;
 
 	return 0;
@@ -418,7 +415,7 @@ static int btree_key_can_insert_cached(struct btree_trans *trans, unsigned flags
 		return 0;
 
 	new_u64s	= roundup_pow_of_two(u64s);
-	new_k		= krealloc(ck->k, new_u64s * sizeof(u64), GFP_NOWAIT);
+	new_k		= krealloc(ck->k, new_u64s * sizeof(u64), GFP_NOWAIT|__GFP_NOWARN);
 	if (unlikely(!new_k))
 		return btree_key_can_insert_cached_slowpath(trans, flags, path, new_u64s);
 
@@ -448,9 +445,6 @@ static int run_one_mem_trigger(struct btree_trans *trans,
 	if (unlikely(flags & BTREE_TRIGGER_NORUN))
 		return 0;
 
-	if (!btree_node_type_needs_gc(__btree_node_type(i->level, i->btree_id)))
-		return 0;
-
 	if (old_ops->trigger == new_ops->trigger) {
 		ret   = bch2_key_trigger(trans, i->btree_id, i->level,
 				old, bkey_i_to_s(new),
@@ -586,9 +580,6 @@ static int bch2_trans_commit_run_triggers(struct btree_trans *trans)
 
 static noinline int bch2_trans_commit_run_gc_triggers(struct btree_trans *trans)
 {
-	struct bch_fs *c = trans->c;
-	int ret = 0;
-
 	trans_for_each_update(trans, i) {
 		/*
 		 * XXX: synchronization of cached update triggers with gc
@@ -596,14 +587,15 @@ static noinline int bch2_trans_commit_run_gc_triggers(struct btree_trans *trans)
 		 */
 		BUG_ON(i->cached || i->level);
 
-		if (gc_visited(c, gc_pos_btree_node(insert_l(trans, i)->b))) {
-			ret = run_one_mem_trigger(trans, i, i->flags|BTREE_TRIGGER_GC);
+		if (btree_node_type_needs_gc(__btree_node_type(i->level, i->btree_id)) &&
+		    gc_visited(trans->c, gc_pos_btree_node(insert_l(trans, i)->b))) {
+			int ret = run_one_mem_trigger(trans, i, i->flags|BTREE_TRIGGER_GC);
 			if (ret)
-				break;
+				return ret;
 		}
 	}
 
-	return ret;
+	return 0;
 }
 
 static inline int
@@ -680,6 +672,9 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags,
 	    bch2_trans_fs_usage_apply(trans, trans->fs_usage_deltas))
 		return -BCH_ERR_btree_insert_need_mark_replicas;
 
+	/* XXX: we only want to run this if deltas are nonzero */
+	bch2_trans_account_disk_usage_change(trans);
+
 	h = trans->hooks;
 	while (h) {
 		ret = h->fn(trans, h);
@@ -689,8 +684,8 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags,
 	}
 
 	trans_for_each_update(trans, i)
-		if (BTREE_NODE_TYPE_HAS_MEM_TRIGGERS & (1U << i->bkey_type)) {
-			ret = run_one_mem_trigger(trans, i, i->flags);
+		if (BTREE_NODE_TYPE_HAS_ATOMIC_TRIGGERS & (1U << i->bkey_type)) {
+			ret = run_one_mem_trigger(trans, i, BTREE_TRIGGER_ATOMIC|i->flags);
 			if (ret)
 				goto fatal_err;
 		}
@@ -994,6 +989,8 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags)
 	    !trans->journal_entries_u64s)
 		goto out_reset;
 
+	memset(&trans->fs_usage_delta, 0, sizeof(trans->fs_usage_delta));
+
 	ret = bch2_trans_commit_run_triggers(trans);
 	if (ret)
 		goto out_reset;
diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h
index d530307046f4..4a5a64499eb7 100644
--- a/fs/bcachefs/btree_types.h
+++ b/fs/bcachefs/btree_types.h
@@ -430,6 +430,9 @@ struct btree_trans {
 	struct journal_res	journal_res;
 	u64			*journal_seq;
 	struct disk_reservation *disk_res;
+
+	struct bch_fs_usage_base fs_usage_delta;
+
 	unsigned		journal_u64s;
 	unsigned		extra_disk_res; /* XXX kill */
 	struct replicas_delta_list *fs_usage_deltas;
@@ -653,7 +656,7 @@ const char *bch2_btree_node_type_str(enum btree_node_type);
 	 BIT_ULL(BKEY_TYPE_reflink)|			\
 	 BIT_ULL(BKEY_TYPE_btree))
 
-#define BTREE_NODE_TYPE_HAS_MEM_TRIGGERS		\
+#define BTREE_NODE_TYPE_HAS_ATOMIC_TRIGGERS		\
 	(BIT_ULL(BKEY_TYPE_alloc)|			\
 	 BIT_ULL(BKEY_TYPE_inodes)|			\
 	 BIT_ULL(BKEY_TYPE_stripes)|			\
@@ -661,7 +664,7 @@ const char *bch2_btree_node_type_str(enum btree_node_type);
 
 #define BTREE_NODE_TYPE_HAS_TRIGGERS			\
 	(BTREE_NODE_TYPE_HAS_TRANS_TRIGGERS|		\
-	 BTREE_NODE_TYPE_HAS_MEM_TRIGGERS)
+	 BTREE_NODE_TYPE_HAS_ATOMIC_TRIGGERS)
 
 static inline bool btree_node_type_needs_gc(enum btree_node_type type)
 {
@@ -738,4 +741,9 @@ enum btree_node_sibling {
 	btree_next_sib,
 };
 
+struct get_locks_fail {
+	unsigned	l;
+	struct btree	*b;
+};
+
 #endif /* _BCACHEFS_BTREE_TYPES_H */
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index 44f9dfa28a09..4530b14ff2c3 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -159,7 +159,7 @@ static bool bch2_btree_node_format_fits(struct bch_fs *c, struct btree *b,
 {
 	size_t u64s = btree_node_u64s_with_format(nr, &b->format, new_f);
 
-	return __vstruct_bytes(struct btree_node, u64s) < btree_bytes(c);
+	return __vstruct_bytes(struct btree_node, u64s) < btree_buf_bytes(b);
 }
 
 /* Btree node freeing/allocation: */
@@ -280,7 +280,8 @@ retry:
 				      writepoint_ptr(&c->btree_write_point),
 				      &devs_have,
 				      res->nr_replicas,
-				      c->opts.metadata_replicas_required,
+				      min(res->nr_replicas,
+					  c->opts.metadata_replicas_required),
 				      watermark, 0, cl, &wp);
 	if (unlikely(ret))
 		return ERR_PTR(ret);
@@ -1097,7 +1098,7 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 		 * Always check for space for two keys, even if we won't have to
 		 * split at prior level - it might have been a merge instead:
 		 */
-		if (bch2_btree_node_insert_fits(c, path->l[update_level].b,
+		if (bch2_btree_node_insert_fits(path->l[update_level].b,
 						BKEY_BTREE_PTR_U64s_MAX * 2))
 			break;
 
@@ -1401,7 +1402,7 @@ static void __btree_split_node(struct btree_update *as,
 
 		unsigned u64s = nr_keys[i].nr_keys * n[i]->data->format.key_u64s +
 			nr_keys[i].val_u64s;
-		if (__vstruct_bytes(struct btree_node, u64s) > btree_bytes(as->c))
+		if (__vstruct_bytes(struct btree_node, u64s) > btree_buf_bytes(b))
 			n[i]->data->format = b->format;
 
 		btree_node_set_format(n[i], n[i]->data->format);
@@ -1703,7 +1704,7 @@ static int bch2_btree_insert_node(struct btree_update *as, struct btree_trans *t
 
 	bch2_btree_node_prep_for_write(trans, path, b);
 
-	if (!bch2_btree_node_insert_fits(c, b, bch2_keylist_u64s(keys))) {
+	if (!bch2_btree_node_insert_fits(b, bch2_keylist_u64s(keys))) {
 		bch2_btree_node_unlock_write(trans, path, b);
 		goto split;
 	}
diff --git a/fs/bcachefs/btree_update_interior.h b/fs/bcachefs/btree_update_interior.h
index adfc62083844..c593c925d1e3 100644
--- a/fs/bcachefs/btree_update_interior.h
+++ b/fs/bcachefs/btree_update_interior.h
@@ -184,21 +184,19 @@ static inline void btree_node_reset_sib_u64s(struct btree *b)
 	b->sib_u64s[1] = b->nr.live_u64s;
 }
 
-static inline void *btree_data_end(struct bch_fs *c, struct btree *b)
+static inline void *btree_data_end(struct btree *b)
 {
-	return (void *) b->data + btree_bytes(c);
+	return (void *) b->data + btree_buf_bytes(b);
 }
 
-static inline struct bkey_packed *unwritten_whiteouts_start(struct bch_fs *c,
-							    struct btree *b)
+static inline struct bkey_packed *unwritten_whiteouts_start(struct btree *b)
 {
-	return (void *) ((u64 *) btree_data_end(c, b) - b->whiteout_u64s);
+	return (void *) ((u64 *) btree_data_end(b) - b->whiteout_u64s);
 }
 
-static inline struct bkey_packed *unwritten_whiteouts_end(struct bch_fs *c,
-							  struct btree *b)
+static inline struct bkey_packed *unwritten_whiteouts_end(struct btree *b)
 {
-	return btree_data_end(c, b);
+	return btree_data_end(b);
 }
 
 static inline void *write_block(struct btree *b)
@@ -221,13 +219,11 @@ static inline bool bkey_written(struct btree *b, struct bkey_packed *k)
 	return __btree_addr_written(b, k);
 }
 
-static inline ssize_t __bch_btree_u64s_remaining(struct bch_fs *c,
-						 struct btree *b,
-						 void *end)
+static inline ssize_t __bch2_btree_u64s_remaining(struct btree *b, void *end)
 {
 	ssize_t used = bset_byte_offset(b, end) / sizeof(u64) +
 		b->whiteout_u64s;
-	ssize_t total = c->opts.btree_node_size >> 3;
+	ssize_t total = btree_buf_bytes(b) >> 3;
 
 	/* Always leave one extra u64 for bch2_varint_decode: */
 	used++;
@@ -235,10 +231,9 @@ static inline ssize_t __bch_btree_u64s_remaining(struct bch_fs *c,
 	return total - used;
 }
 
-static inline size_t bch_btree_keys_u64s_remaining(struct bch_fs *c,
-						   struct btree *b)
+static inline size_t bch2_btree_keys_u64s_remaining(struct btree *b)
 {
-	ssize_t remaining = __bch_btree_u64s_remaining(c, b,
+	ssize_t remaining = __bch2_btree_u64s_remaining(b,
 				btree_bkey_last(b, bset_tree_last(b)));
 
 	BUG_ON(remaining < 0);
@@ -260,14 +255,13 @@ static inline unsigned btree_write_set_buffer(struct btree *b)
 	return 8 << BTREE_WRITE_SET_U64s_BITS;
 }
 
-static inline struct btree_node_entry *want_new_bset(struct bch_fs *c,
-						     struct btree *b)
+static inline struct btree_node_entry *want_new_bset(struct bch_fs *c, struct btree *b)
 {
 	struct bset_tree *t = bset_tree_last(b);
 	struct btree_node_entry *bne = max(write_block(b),
 			(void *) btree_bkey_last(b, bset_tree_last(b)));
 	ssize_t remaining_space =
-		__bch_btree_u64s_remaining(c, b, bne->keys.start);
+		__bch2_btree_u64s_remaining(b, bne->keys.start);
 
 	if (unlikely(bset_written(b, bset(b, t)))) {
 		if (remaining_space > (ssize_t) (block_bytes(c) >> 3))
@@ -281,12 +275,11 @@ static inline struct btree_node_entry *want_new_bset(struct bch_fs *c,
 	return NULL;
 }
 
-static inline void push_whiteout(struct bch_fs *c, struct btree *b,
-				 struct bpos pos)
+static inline void push_whiteout(struct btree *b, struct bpos pos)
 {
 	struct bkey_packed k;
 
-	BUG_ON(bch_btree_keys_u64s_remaining(c, b) < BKEY_U64s);
+	BUG_ON(bch2_btree_keys_u64s_remaining(b) < BKEY_U64s);
 	EBUG_ON(btree_node_just_written(b));
 
 	if (!bkey_pack_pos(&k, pos, b)) {
@@ -299,20 +292,19 @@ static inline void push_whiteout(struct bch_fs *c, struct btree *b,
 	k.needs_whiteout = true;
 
 	b->whiteout_u64s += k.u64s;
-	bkey_p_copy(unwritten_whiteouts_start(c, b), &k);
+	bkey_p_copy(unwritten_whiteouts_start(b), &k);
 }
 
 /*
  * write lock must be held on @b (else the dirty bset that we were going to
  * insert into could be written out from under us)
  */
-static inline bool bch2_btree_node_insert_fits(struct bch_fs *c,
-					       struct btree *b, unsigned u64s)
+static inline bool bch2_btree_node_insert_fits(struct btree *b, unsigned u64s)
 {
 	if (unlikely(btree_node_need_rewrite(b)))
 		return false;
 
-	return u64s <= bch_btree_keys_u64s_remaining(c, b);
+	return u64s <= bch2_btree_keys_u64s_remaining(b);
 }
 
 void bch2_btree_updates_to_text(struct printbuf *, struct bch_fs *);
diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c
index 5c1169c78daf..ac7844861966 100644
--- a/fs/bcachefs/btree_write_buffer.c
+++ b/fs/bcachefs/btree_write_buffer.c
@@ -125,13 +125,12 @@ static inline int wb_flush_one(struct btree_trans *trans, struct btree_iter *ite
 			       struct btree_write_buffered_key *wb,
 			       bool *write_locked, size_t *fast)
 {
-	struct bch_fs *c = trans->c;
 	struct btree_path *path;
 	int ret;
 
 	EBUG_ON(!wb->journal_seq);
-	EBUG_ON(!c->btree_write_buffer.flushing.pin.seq);
-	EBUG_ON(c->btree_write_buffer.flushing.pin.seq > wb->journal_seq);
+	EBUG_ON(!trans->c->btree_write_buffer.flushing.pin.seq);
+	EBUG_ON(trans->c->btree_write_buffer.flushing.pin.seq > wb->journal_seq);
 
 	ret = bch2_btree_iter_traverse(iter);
 	if (ret)
@@ -155,7 +154,7 @@ static inline int wb_flush_one(struct btree_trans *trans, struct btree_iter *ite
 		*write_locked = true;
 	}
 
-	if (unlikely(!bch2_btree_node_insert_fits(c, path->l[0].b, wb->k.k.u64s))) {
+	if (unlikely(!bch2_btree_node_insert_fits(path->l[0].b, wb->k.k.u64s))) {
 		*write_locked = false;
 		return wb_flush_one_slowpath(trans, iter, wb);
 	}
diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c
index d83ea0e53df3..54f7826ac498 100644
--- a/fs/bcachefs/buckets.c
+++ b/fs/bcachefs/buckets.c
@@ -25,7 +25,7 @@
 
 #include <linux/preempt.h>
 
-static inline void fs_usage_data_type_to_base(struct bch_fs_usage *fs_usage,
+static inline void fs_usage_data_type_to_base(struct bch_fs_usage_base *fs_usage,
 					      enum bch_data_type data_type,
 					      s64 sectors)
 {
@@ -54,20 +54,20 @@ void bch2_fs_usage_initialize(struct bch_fs *c)
 		bch2_fs_usage_acc_to_base(c, i);
 
 	for (unsigned i = 0; i < BCH_REPLICAS_MAX; i++)
-		usage->reserved += usage->persistent_reserved[i];
+		usage->b.reserved += usage->persistent_reserved[i];
 
 	for (unsigned i = 0; i < c->replicas.nr; i++) {
 		struct bch_replicas_entry_v1 *e =
 			cpu_replicas_entry(&c->replicas, i);
 
-		fs_usage_data_type_to_base(usage, e->data_type, usage->replicas[i]);
+		fs_usage_data_type_to_base(&usage->b, e->data_type, usage->replicas[i]);
 	}
 
 	for_each_member_device(c, ca) {
 		struct bch_dev_usage dev = bch2_dev_usage_read(ca);
 
-		usage->hidden += (dev.d[BCH_DATA_sb].buckets +
-				  dev.d[BCH_DATA_journal].buckets) *
+		usage->b.hidden += (dev.d[BCH_DATA_sb].buckets +
+				    dev.d[BCH_DATA_journal].buckets) *
 			ca->mi.bucket_size;
 	}
 
@@ -188,15 +188,15 @@ void bch2_fs_usage_to_text(struct printbuf *out,
 	prt_printf(out, "capacity:\t\t\t%llu\n", c->capacity);
 
 	prt_printf(out, "hidden:\t\t\t\t%llu\n",
-	       fs_usage->u.hidden);
+	       fs_usage->u.b.hidden);
 	prt_printf(out, "data:\t\t\t\t%llu\n",
-	       fs_usage->u.data);
+	       fs_usage->u.b.data);
 	prt_printf(out, "cached:\t\t\t\t%llu\n",
-	       fs_usage->u.cached);
+	       fs_usage->u.b.cached);
 	prt_printf(out, "reserved:\t\t\t%llu\n",
-	       fs_usage->u.reserved);
+	       fs_usage->u.b.reserved);
 	prt_printf(out, "nr_inodes:\t\t\t%llu\n",
-	       fs_usage->u.nr_inodes);
+	       fs_usage->u.b.nr_inodes);
 	prt_printf(out, "online reserved:\t\t%llu\n",
 	       fs_usage->online_reserved);
 
@@ -225,10 +225,10 @@ static u64 reserve_factor(u64 r)
 
 u64 bch2_fs_sectors_used(struct bch_fs *c, struct bch_fs_usage_online *fs_usage)
 {
-	return min(fs_usage->u.hidden +
-		   fs_usage->u.btree +
-		   fs_usage->u.data +
-		   reserve_factor(fs_usage->u.reserved +
+	return min(fs_usage->u.b.hidden +
+		   fs_usage->u.b.btree +
+		   fs_usage->u.b.data +
+		   reserve_factor(fs_usage->u.b.reserved +
 				  fs_usage->online_reserved),
 		   c->capacity);
 }
@@ -240,17 +240,17 @@ __bch2_fs_usage_read_short(struct bch_fs *c)
 	u64 data, reserved;
 
 	ret.capacity = c->capacity -
-		bch2_fs_usage_read_one(c, &c->usage_base->hidden);
+		bch2_fs_usage_read_one(c, &c->usage_base->b.hidden);
 
-	data		= bch2_fs_usage_read_one(c, &c->usage_base->data) +
-		bch2_fs_usage_read_one(c, &c->usage_base->btree);
-	reserved	= bch2_fs_usage_read_one(c, &c->usage_base->reserved) +
+	data		= bch2_fs_usage_read_one(c, &c->usage_base->b.data) +
+		bch2_fs_usage_read_one(c, &c->usage_base->b.btree);
+	reserved	= bch2_fs_usage_read_one(c, &c->usage_base->b.reserved) +
 		percpu_u64_get(c->online_reserved);
 
 	ret.used	= min(ret.capacity, data + reserve_factor(reserved));
 	ret.free	= ret.capacity - ret.used;
 
-	ret.nr_inodes	= bch2_fs_usage_read_one(c, &c->usage_base->nr_inodes);
+	ret.nr_inodes	= bch2_fs_usage_read_one(c, &c->usage_base->b.nr_inodes);
 
 	return ret;
 }
@@ -284,7 +284,7 @@ void bch2_dev_usage_to_text(struct printbuf *out, struct bch_dev_usage *usage)
 	prt_newline(out);
 
 	for (unsigned i = 0; i < BCH_DATA_NR; i++) {
-		prt_str(out, bch2_data_types[i]);
+		bch2_prt_data_type(out, i);
 		prt_tab(out);
 		prt_u64(out, usage->d[i].buckets);
 		prt_tab_rjust(out);
@@ -308,9 +308,9 @@ void bch2_dev_usage_update(struct bch_fs *c, struct bch_dev *ca,
 	fs_usage = fs_usage_ptr(c, journal_seq, gc);
 
 	if (data_type_is_hidden(old->data_type))
-		fs_usage->hidden -= ca->mi.bucket_size;
+		fs_usage->b.hidden -= ca->mi.bucket_size;
 	if (data_type_is_hidden(new->data_type))
-		fs_usage->hidden += ca->mi.bucket_size;
+		fs_usage->b.hidden += ca->mi.bucket_size;
 
 	u = dev_usage_ptr(ca, journal_seq, gc);
 
@@ -359,7 +359,7 @@ static inline int __update_replicas(struct bch_fs *c,
 	if (idx < 0)
 		return -1;
 
-	fs_usage_data_type_to_base(fs_usage, r->data_type, sectors);
+	fs_usage_data_type_to_base(&fs_usage->b, r->data_type, sectors);
 	fs_usage->replicas[idx]		+= sectors;
 	return 0;
 }
@@ -394,7 +394,7 @@ int bch2_update_replicas(struct bch_fs *c, struct bkey_s_c k,
 
 	preempt_disable();
 	fs_usage = fs_usage_ptr(c, journal_seq, gc);
-	fs_usage_data_type_to_base(fs_usage, r->data_type, sectors);
+	fs_usage_data_type_to_base(&fs_usage->b, r->data_type, sectors);
 	fs_usage->replicas[idx]		+= sectors;
 	preempt_enable();
 err:
@@ -523,8 +523,8 @@ int bch2_mark_metadata_bucket(struct bch_fs *c, struct bch_dev *ca,
 	if (bch2_fs_inconsistent_on(g->data_type &&
 			g->data_type != data_type, c,
 			"different types of data in same bucket: %s, %s",
-			bch2_data_types[g->data_type],
-			bch2_data_types[data_type])) {
+			bch2_data_type_str(g->data_type),
+			bch2_data_type_str(data_type))) {
 		ret = -EIO;
 		goto err;
 	}
@@ -532,7 +532,7 @@ int bch2_mark_metadata_bucket(struct bch_fs *c, struct bch_dev *ca,
 	if (bch2_fs_inconsistent_on((u64) g->dirty_sectors + sectors > ca->mi.bucket_size, c,
 			"bucket %u:%zu gen %u data type %s sector count overflow: %u + %u > bucket size",
 			ca->dev_idx, b, g->gen,
-			bch2_data_types[g->data_type ?: data_type],
+			bch2_data_type_str(g->data_type ?: data_type),
 			g->dirty_sectors, sectors)) {
 		ret = -EIO;
 		goto err;
@@ -575,7 +575,7 @@ int bch2_check_bucket_ref(struct btree_trans *trans,
 			"bucket %u:%zu gen %u data type %s: ptr gen %u newer than bucket gen\n"
 			"while marking %s",
 			ptr->dev, bucket_nr, b_gen,
-			bch2_data_types[bucket_data_type ?: ptr_data_type],
+			bch2_data_type_str(bucket_data_type ?: ptr_data_type),
 			ptr->gen,
 			(bch2_bkey_val_to_text(&buf, c, k), buf.buf));
 		ret = -EIO;
@@ -588,7 +588,7 @@ int bch2_check_bucket_ref(struct btree_trans *trans,
 			"bucket %u:%zu gen %u data type %s: ptr gen %u too stale\n"
 			"while marking %s",
 			ptr->dev, bucket_nr, b_gen,
-			bch2_data_types[bucket_data_type ?: ptr_data_type],
+			bch2_data_type_str(bucket_data_type ?: ptr_data_type),
 			ptr->gen,
 			(printbuf_reset(&buf),
 			 bch2_bkey_val_to_text(&buf, c, k), buf.buf));
@@ -603,7 +603,7 @@ int bch2_check_bucket_ref(struct btree_trans *trans,
 			"while marking %s",
 			ptr->dev, bucket_nr, b_gen,
 			*bucket_gen(ca, bucket_nr),
-			bch2_data_types[bucket_data_type ?: ptr_data_type],
+			bch2_data_type_str(bucket_data_type ?: ptr_data_type),
 			ptr->gen,
 			(printbuf_reset(&buf),
 			 bch2_bkey_val_to_text(&buf, c, k), buf.buf));
@@ -624,8 +624,8 @@ int bch2_check_bucket_ref(struct btree_trans *trans,
 			"bucket %u:%zu gen %u different types of data in same bucket: %s, %s\n"
 			"while marking %s",
 			ptr->dev, bucket_nr, b_gen,
-			bch2_data_types[bucket_data_type],
-			bch2_data_types[ptr_data_type],
+			bch2_data_type_str(bucket_data_type),
+			bch2_data_type_str(ptr_data_type),
 			(printbuf_reset(&buf),
 			 bch2_bkey_val_to_text(&buf, c, k), buf.buf));
 		ret = -EIO;
@@ -638,7 +638,7 @@ int bch2_check_bucket_ref(struct btree_trans *trans,
 			"bucket %u:%zu gen %u data type %s sector count overflow: %u + %lli > U32_MAX\n"
 			"while marking %s",
 			ptr->dev, bucket_nr, b_gen,
-			bch2_data_types[bucket_data_type ?: ptr_data_type],
+			bch2_data_type_str(bucket_data_type ?: ptr_data_type),
 			bucket_sectors, sectors,
 			(printbuf_reset(&buf),
 			 bch2_bkey_val_to_text(&buf, c, k), buf.buf));
@@ -677,11 +677,11 @@ void bch2_trans_fs_usage_revert(struct btree_trans *trans,
 		BUG_ON(__update_replicas(c, dst, &d->r, -d->delta));
 	}
 
-	dst->nr_inodes -= deltas->nr_inodes;
+	dst->b.nr_inodes -= deltas->nr_inodes;
 
 	for (i = 0; i < BCH_REPLICAS_MAX; i++) {
 		added				-= deltas->persistent_reserved[i];
-		dst->reserved			-= deltas->persistent_reserved[i];
+		dst->b.reserved			-= deltas->persistent_reserved[i];
 		dst->persistent_reserved[i]	-= deltas->persistent_reserved[i];
 	}
 
@@ -694,48 +694,25 @@ void bch2_trans_fs_usage_revert(struct btree_trans *trans,
 	percpu_up_read(&c->mark_lock);
 }
 
-int bch2_trans_fs_usage_apply(struct btree_trans *trans,
-			      struct replicas_delta_list *deltas)
+void bch2_trans_account_disk_usage_change(struct btree_trans *trans)
 {
 	struct bch_fs *c = trans->c;
+	u64 disk_res_sectors = trans->disk_res ? trans->disk_res->sectors : 0;
 	static int warned_disk_usage = 0;
 	bool warn = false;
-	u64 disk_res_sectors = trans->disk_res ? trans->disk_res->sectors : 0;
-	struct replicas_delta *d, *d2;
-	struct replicas_delta *top = (void *) deltas->d + deltas->used;
-	struct bch_fs_usage *dst;
-	s64 added = 0, should_not_have_added;
-	unsigned i;
 
 	percpu_down_read(&c->mark_lock);
 	preempt_disable();
-	dst = fs_usage_ptr(c, trans->journal_res.seq, false);
-
-	for (d = deltas->d; d != top; d = replicas_delta_next(d)) {
-		switch (d->r.data_type) {
-		case BCH_DATA_btree:
-		case BCH_DATA_user:
-		case BCH_DATA_parity:
-			added += d->delta;
-		}
+	struct bch_fs_usage_base *dst = &fs_usage_ptr(c, trans->journal_res.seq, false)->b;
+	struct bch_fs_usage_base *src = &trans->fs_usage_delta;
 
-		if (__update_replicas(c, dst, &d->r, d->delta))
-			goto need_mark;
-	}
-
-	dst->nr_inodes += deltas->nr_inodes;
-
-	for (i = 0; i < BCH_REPLICAS_MAX; i++) {
-		added				+= deltas->persistent_reserved[i];
-		dst->reserved			+= deltas->persistent_reserved[i];
-		dst->persistent_reserved[i]	+= deltas->persistent_reserved[i];
-	}
+	s64 added = src->btree + src->data + src->reserved;
 
 	/*
 	 * Not allowed to reduce sectors_available except by getting a
 	 * reservation:
 	 */
-	should_not_have_added = added - (s64) disk_res_sectors;
+	s64 should_not_have_added = added - (s64) disk_res_sectors;
 	if (unlikely(should_not_have_added > 0)) {
 		u64 old, new, v = atomic64_read(&c->sectors_available);
 
@@ -754,6 +731,13 @@ int bch2_trans_fs_usage_apply(struct btree_trans *trans,
 		this_cpu_sub(*c->online_reserved, added);
 	}
 
+	dst->hidden	+= src->hidden;
+	dst->btree	+= src->btree;
+	dst->data	+= src->data;
+	dst->cached	+= src->cached;
+	dst->reserved	+= src->reserved;
+	dst->nr_inodes	+= src->nr_inodes;
+
 	preempt_enable();
 	percpu_up_read(&c->mark_lock);
 
@@ -761,6 +745,34 @@ int bch2_trans_fs_usage_apply(struct btree_trans *trans,
 		bch2_trans_inconsistent(trans,
 					"disk usage increased %lli more than %llu sectors reserved)",
 					should_not_have_added, disk_res_sectors);
+}
+
+int bch2_trans_fs_usage_apply(struct btree_trans *trans,
+			      struct replicas_delta_list *deltas)
+{
+	struct bch_fs *c = trans->c;
+	struct replicas_delta *d, *d2;
+	struct replicas_delta *top = (void *) deltas->d + deltas->used;
+	struct bch_fs_usage *dst;
+	unsigned i;
+
+	percpu_down_read(&c->mark_lock);
+	preempt_disable();
+	dst = fs_usage_ptr(c, trans->journal_res.seq, false);
+
+	for (d = deltas->d; d != top; d = replicas_delta_next(d))
+		if (__update_replicas(c, dst, &d->r, d->delta))
+			goto need_mark;
+
+	dst->b.nr_inodes += deltas->nr_inodes;
+
+	for (i = 0; i < BCH_REPLICAS_MAX; i++) {
+		dst->b.reserved			+= deltas->persistent_reserved[i];
+		dst->persistent_reserved[i]	+= deltas->persistent_reserved[i];
+	}
+
+	preempt_enable();
+	percpu_up_read(&c->mark_lock);
 	return 0;
 need_mark:
 	/* revert changes: */
@@ -1084,7 +1096,7 @@ static int __trigger_reservation(struct btree_trans *trans,
 		struct bch_fs_usage *fs_usage = this_cpu_ptr(c->usage_gc);
 
 		replicas = min(replicas, ARRAY_SIZE(fs_usage->persistent_reserved));
-		fs_usage->reserved				+= sectors;
+		fs_usage->b.reserved				+= sectors;
 		fs_usage->persistent_reserved[replicas - 1]	+= sectors;
 
 		preempt_enable();
@@ -1130,9 +1142,9 @@ static int __bch2_trans_mark_metadata_bucket(struct btree_trans *trans,
 			"bucket %llu:%llu gen %u different types of data in same bucket: %s, %s\n"
 			"while marking %s",
 			iter.pos.inode, iter.pos.offset, a->v.gen,
-			bch2_data_types[a->v.data_type],
-			bch2_data_types[type],
-			bch2_data_types[type]);
+			bch2_data_type_str(a->v.data_type),
+			bch2_data_type_str(type),
+			bch2_data_type_str(type));
 		ret = -EIO;
 		goto err;
 	}
diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h
index 2c95cc5d86be..6387e039f789 100644
--- a/fs/bcachefs/buckets.h
+++ b/fs/bcachefs/buckets.h
@@ -356,6 +356,8 @@ int bch2_trigger_reservation(struct btree_trans *, enum btree_id, unsigned,
 	ret;											\
 })
 
+void bch2_trans_account_disk_usage_change(struct btree_trans *);
+
 void bch2_trans_fs_usage_revert(struct btree_trans *, struct replicas_delta_list *);
 int bch2_trans_fs_usage_apply(struct btree_trans *, struct replicas_delta_list *);
 
@@ -385,6 +387,21 @@ static inline bool is_superblock_bucket(struct bch_dev *ca, u64 b)
 	return false;
 }
 
+static inline const char *bch2_data_type_str(enum bch_data_type type)
+{
+	return type < BCH_DATA_NR
+		? __bch2_data_types[type]
+		: "(invalid data type)";
+}
+
+static inline void bch2_prt_data_type(struct printbuf *out, enum bch_data_type type)
+{
+	if (type < BCH_DATA_NR)
+		prt_str(out, __bch2_data_types[type]);
+	else
+		prt_printf(out, "(invalid data type %u)", type);
+}
+
 /* disk reservations: */
 
 static inline void bch2_disk_reservation_put(struct bch_fs *c,
diff --git a/fs/bcachefs/buckets_types.h b/fs/bcachefs/buckets_types.h
index 783f71017204..6a31740222a7 100644
--- a/fs/bcachefs/buckets_types.h
+++ b/fs/bcachefs/buckets_types.h
@@ -45,23 +45,18 @@ struct bch_dev_usage {
 	}			d[BCH_DATA_NR];
 };
 
-struct bch_fs_usage {
-	/* all fields are in units of 512 byte sectors: */
+struct bch_fs_usage_base {
 	u64			hidden;
 	u64			btree;
 	u64			data;
 	u64			cached;
 	u64			reserved;
 	u64			nr_inodes;
+};
 
-	/* XXX: add stats for compression ratio */
-#if 0
-	u64			uncompressed;
-	u64			compressed;
-#endif
-
-	/* broken out: */
-
+struct bch_fs_usage {
+	/* all fields are in units of 512 byte sectors: */
+	struct bch_fs_usage_base b;
 	u64			persistent_reserved[BCH_REPLICAS_MAX];
 	u64			replicas[];
 };
diff --git a/fs/bcachefs/clock.c b/fs/bcachefs/clock.c
index f41889093a2c..363644451106 100644
--- a/fs/bcachefs/clock.c
+++ b/fs/bcachefs/clock.c
@@ -109,7 +109,7 @@ void bch2_kthread_io_clock_wait(struct io_clock *clock,
 	if (cpu_timeout != MAX_SCHEDULE_TIMEOUT)
 		mod_timer(&wait.cpu_timer, cpu_timeout + jiffies);
 
-	while (1) {
+	do {
 		set_current_state(TASK_INTERRUPTIBLE);
 		if (kthread && kthread_should_stop())
 			break;
@@ -119,7 +119,7 @@ void bch2_kthread_io_clock_wait(struct io_clock *clock,
 
 		schedule();
 		try_to_freeze();
-	}
+	} while (0);
 
 	__set_current_state(TASK_RUNNING);
 	del_timer_sync(&wait.cpu_timer);
diff --git a/fs/bcachefs/compress.h b/fs/bcachefs/compress.h
index 607fd5e232c9..58c2eb45570f 100644
--- a/fs/bcachefs/compress.h
+++ b/fs/bcachefs/compress.h
@@ -47,6 +47,14 @@ static inline enum bch_compression_type bch2_compression_opt_to_type(unsigned v)
 	return __bch2_compression_opt_to_type[bch2_compression_decode(v).type];
 }
 
+static inline void bch2_prt_compression_type(struct printbuf *out, enum bch_compression_type type)
+{
+	if (type < BCH_COMPRESSION_TYPE_NR)
+		prt_str(out, __bch2_compression_types[type]);
+	else
+		prt_printf(out, "(invalid compression type %u)", type);
+}
+
 int bch2_bio_uncompress_inplace(struct bch_fs *, struct bio *,
 				struct bch_extent_crc_unpacked *);
 int bch2_bio_uncompress(struct bch_fs *, struct bio *, struct bio *,
diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c
index 6f13477ff652..4150feca42a2 100644
--- a/fs/bcachefs/data_update.c
+++ b/fs/bcachefs/data_update.c
@@ -285,9 +285,7 @@ restart_drop_extra_replicas:
 						k.k->p, bkey_start_pos(&insert->k)) ?:
 			bch2_insert_snapshot_whiteouts(trans, m->btree_id,
 						k.k->p, insert->k.p) ?:
-			bch2_bkey_set_needs_rebalance(c, insert,
-						      op->opts.background_target,
-						      op->opts.background_compression) ?:
+			bch2_bkey_set_needs_rebalance(c, insert, &op->opts) ?:
 			bch2_trans_update(trans, &iter, insert,
 				BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE) ?:
 			bch2_trans_commit(trans, &op->res,
@@ -529,7 +527,7 @@ int bch2_data_update_init(struct btree_trans *trans,
 		BCH_WRITE_DATA_ENCODED|
 		BCH_WRITE_MOVE|
 		m->data_opts.write_flags;
-	m->op.compression_opt	= io_opts.background_compression ?: io_opts.compression;
+	m->op.compression_opt	= background_compression(io_opts);
 	m->op.watermark		= m->data_opts.btree_insert_flags & BCH_WATERMARK_MASK;
 
 	bkey_for_each_ptr(ptrs, ptr)
diff --git a/fs/bcachefs/debug.c b/fs/bcachefs/debug.c
index d6418948495f..7bdba8507fc9 100644
--- a/fs/bcachefs/debug.c
+++ b/fs/bcachefs/debug.c
@@ -44,19 +44,19 @@ static bool bch2_btree_verify_replica(struct bch_fs *c, struct btree *b,
 		return false;
 
 	bio = bio_alloc_bioset(ca->disk_sb.bdev,
-			       buf_pages(n_sorted, btree_bytes(c)),
+			       buf_pages(n_sorted, btree_buf_bytes(b)),
 			       REQ_OP_READ|REQ_META,
 			       GFP_NOFS,
 			       &c->btree_bio);
 	bio->bi_iter.bi_sector	= pick.ptr.offset;
-	bch2_bio_map(bio, n_sorted, btree_bytes(c));
+	bch2_bio_map(bio, n_sorted, btree_buf_bytes(b));
 
 	submit_bio_wait(bio);
 
 	bio_put(bio);
 	percpu_ref_put(&ca->io_ref);
 
-	memcpy(n_ondisk, n_sorted, btree_bytes(c));
+	memcpy(n_ondisk, n_sorted, btree_buf_bytes(b));
 
 	v->written = 0;
 	if (bch2_btree_node_read_done(c, ca, v, false, &saw_error) || saw_error)
@@ -137,7 +137,7 @@ void __bch2_btree_verify(struct bch_fs *c, struct btree *b)
 	mutex_lock(&c->verify_lock);
 
 	if (!c->verify_ondisk) {
-		c->verify_ondisk = kvpmalloc(btree_bytes(c), GFP_KERNEL);
+		c->verify_ondisk = kvpmalloc(btree_buf_bytes(b), GFP_KERNEL);
 		if (!c->verify_ondisk)
 			goto out;
 	}
@@ -199,19 +199,19 @@ void bch2_btree_node_ondisk_to_text(struct printbuf *out, struct bch_fs *c,
 		return;
 	}
 
-	n_ondisk = kvpmalloc(btree_bytes(c), GFP_KERNEL);
+	n_ondisk = kvpmalloc(btree_buf_bytes(b), GFP_KERNEL);
 	if (!n_ondisk) {
 		prt_printf(out, "memory allocation failure\n");
 		goto out;
 	}
 
 	bio = bio_alloc_bioset(ca->disk_sb.bdev,
-			       buf_pages(n_ondisk, btree_bytes(c)),
+			       buf_pages(n_ondisk, btree_buf_bytes(b)),
 			       REQ_OP_READ|REQ_META,
 			       GFP_NOFS,
 			       &c->btree_bio);
 	bio->bi_iter.bi_sector	= pick.ptr.offset;
-	bch2_bio_map(bio, n_ondisk, btree_bytes(c));
+	bch2_bio_map(bio, n_ondisk, btree_buf_bytes(b));
 
 	ret = submit_bio_wait(bio);
 	if (ret) {
@@ -293,7 +293,7 @@ void bch2_btree_node_ondisk_to_text(struct printbuf *out, struct bch_fs *c,
 out:
 	if (bio)
 		bio_put(bio);
-	kvpfree(n_ondisk, btree_bytes(c));
+	kvpfree(n_ondisk, btree_buf_bytes(b));
 	percpu_ref_put(&ca->io_ref);
 }
 
@@ -627,7 +627,7 @@ restart:
 		prt_printf(&i->buf, "backtrace:");
 		prt_newline(&i->buf);
 		printbuf_indent_add(&i->buf, 2);
-		bch2_prt_task_backtrace(&i->buf, task, 0);
+		bch2_prt_task_backtrace(&i->buf, task, 0, GFP_KERNEL);
 		printbuf_indent_sub(&i->buf, 2);
 		prt_newline(&i->buf);
 
diff --git a/fs/bcachefs/dirent_format.h b/fs/bcachefs/dirent_format.h
new file mode 100644
index 000000000000..5e116b88e814
--- /dev/null
+++ b/fs/bcachefs/dirent_format.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_DIRENT_FORMAT_H
+#define _BCACHEFS_DIRENT_FORMAT_H
+
+/*
+ * Dirents (and xattrs) have to implement string lookups; since our b-tree
+ * doesn't support arbitrary length strings for the key, we instead index by a
+ * 64 bit hash (currently truncated sha1) of the string, stored in the offset
+ * field of the key - using linear probing to resolve hash collisions. This also
+ * provides us with the readdir cookie posix requires.
+ *
+ * Linear probing requires us to use whiteouts for deletions, in the event of a
+ * collision:
+ */
+
+struct bch_dirent {
+	struct bch_val		v;
+
+	/* Target inode number: */
+	union {
+	__le64			d_inum;
+	struct {		/* DT_SUBVOL */
+	__le32			d_child_subvol;
+	__le32			d_parent_subvol;
+	};
+	};
+
+	/*
+	 * Copy of mode bits 12-15 from the target inode - so userspace can get
+	 * the filetype without having to do a stat()
+	 */
+	__u8			d_type;
+
+	__u8			d_name[];
+} __packed __aligned(8);
+
+#define DT_SUBVOL	16
+#define BCH_DT_MAX	17
+
+#define BCH_NAME_MAX	512
+
+#endif /* _BCACHEFS_DIRENT_FORMAT_H */
diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c
index d802bc63c8d0..d503af270024 100644
--- a/fs/bcachefs/ec.c
+++ b/fs/bcachefs/ec.c
@@ -190,7 +190,7 @@ static int bch2_trans_mark_stripe_bucket(struct btree_trans *trans,
 					       a->v.stripe_redundancy, trans,
 				"bucket %llu:%llu gen %u data type %s dirty_sectors %u: multiple stripes using same bucket (%u, %llu)",
 				iter.pos.inode, iter.pos.offset, a->v.gen,
-				bch2_data_types[a->v.data_type],
+				bch2_data_type_str(a->v.data_type),
 				a->v.dirty_sectors,
 				a->v.stripe, s.k->p.offset)) {
 			ret = -EIO;
@@ -200,7 +200,7 @@ static int bch2_trans_mark_stripe_bucket(struct btree_trans *trans,
 		if (bch2_trans_inconsistent_on(data_type && a->v.dirty_sectors, trans,
 				"bucket %llu:%llu gen %u data type %s dirty_sectors %u: data already in stripe bucket %llu",
 				iter.pos.inode, iter.pos.offset, a->v.gen,
-				bch2_data_types[a->v.data_type],
+				bch2_data_type_str(a->v.data_type),
 				a->v.dirty_sectors,
 				s.k->p.offset)) {
 			ret = -EIO;
@@ -367,7 +367,7 @@ int bch2_trigger_stripe(struct btree_trans *trans,
 		}
 	}
 
-	if (!(flags & (BTREE_TRIGGER_TRANSACTIONAL|BTREE_TRIGGER_GC))) {
+	if (flags & BTREE_TRIGGER_ATOMIC) {
 		struct stripe *m = genradix_ptr(&c->stripes, idx);
 
 		if (!m) {
diff --git a/fs/bcachefs/ec_format.h b/fs/bcachefs/ec_format.h
new file mode 100644
index 000000000000..44ce88ba08d7
--- /dev/null
+++ b/fs/bcachefs/ec_format.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_EC_FORMAT_H
+#define _BCACHEFS_EC_FORMAT_H
+
+struct bch_stripe {
+	struct bch_val		v;
+	__le16			sectors;
+	__u8			algorithm;
+	__u8			nr_blocks;
+	__u8			nr_redundant;
+
+	__u8			csum_granularity_bits;
+	__u8			csum_type;
+	__u8			pad;
+
+	struct bch_extent_ptr	ptrs[];
+} __packed __aligned(8);
+
+#endif /* _BCACHEFS_EC_FORMAT_H */
diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c
index 82ec056f4cdb..61395b113df9 100644
--- a/fs/bcachefs/extents.c
+++ b/fs/bcachefs/extents.c
@@ -8,6 +8,7 @@
 
 #include "bcachefs.h"
 #include "bkey_methods.h"
+#include "btree_cache.h"
 #include "btree_gc.h"
 #include "btree_io.h"
 #include "btree_iter.h"
@@ -1018,12 +1019,12 @@ void bch2_bkey_ptrs_to_text(struct printbuf *out, struct bch_fs *c,
 			struct bch_extent_crc_unpacked crc =
 				bch2_extent_crc_unpack(k.k, entry_to_crc(entry));
 
-			prt_printf(out, "crc: c_size %u size %u offset %u nonce %u csum %s compress %s",
+			prt_printf(out, "crc: c_size %u size %u offset %u nonce %u csum %s compress ",
 			       crc.compressed_size,
 			       crc.uncompressed_size,
 			       crc.offset, crc.nonce,
-			       bch2_csum_types[crc.csum_type],
-			       bch2_compression_types[crc.compression_type]);
+			       bch2_csum_types[crc.csum_type]);
+			bch2_prt_compression_type(out, crc.compression_type);
 			break;
 		}
 		case BCH_EXTENT_ENTRY_stripe_ptr: {
@@ -1334,10 +1335,12 @@ bool bch2_bkey_needs_rebalance(struct bch_fs *c, struct bkey_s_c k)
 }
 
 int bch2_bkey_set_needs_rebalance(struct bch_fs *c, struct bkey_i *_k,
-				  unsigned target, unsigned compression)
+				  struct bch_io_opts *opts)
 {
 	struct bkey_s k = bkey_i_to_s(_k);
 	struct bch_extent_rebalance *r;
+	unsigned target = opts->background_target;
+	unsigned compression = background_compression(*opts);
 	bool needs_rebalance;
 
 	if (!bkey_extent_is_direct_data(k.k))
diff --git a/fs/bcachefs/extents.h b/fs/bcachefs/extents.h
index a855c94d43dd..6bf839d69e84 100644
--- a/fs/bcachefs/extents.h
+++ b/fs/bcachefs/extents.h
@@ -708,7 +708,7 @@ unsigned bch2_bkey_ptrs_need_rebalance(struct bch_fs *, struct bkey_s_c,
 bool bch2_bkey_needs_rebalance(struct bch_fs *, struct bkey_s_c);
 
 int bch2_bkey_set_needs_rebalance(struct bch_fs *, struct bkey_i *,
-				  unsigned, unsigned);
+				  struct bch_io_opts *);
 
 /* Generic extent code: */
 
diff --git a/fs/bcachefs/extents_format.h b/fs/bcachefs/extents_format.h
new file mode 100644
index 000000000000..3bd2fdbb0817
--- /dev/null
+++ b/fs/bcachefs/extents_format.h
@@ -0,0 +1,295 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_EXTENTS_FORMAT_H
+#define _BCACHEFS_EXTENTS_FORMAT_H
+
+/*
+ * In extent bkeys, the value is a list of pointers (bch_extent_ptr), optionally
+ * preceded by checksum/compression information (bch_extent_crc32 or
+ * bch_extent_crc64).
+ *
+ * One major determining factor in the format of extents is how we handle and
+ * represent extents that have been partially overwritten and thus trimmed:
+ *
+ * If an extent is not checksummed or compressed, when the extent is trimmed we
+ * don't have to remember the extent we originally allocated and wrote: we can
+ * merely adjust ptr->offset to point to the start of the data that is currently
+ * live. The size field in struct bkey records the current (live) size of the
+ * extent, and is also used to mean "size of region on disk that we point to" in
+ * this case.
+ *
+ * Thus an extent that is not checksummed or compressed will consist only of a
+ * list of bch_extent_ptrs, with none of the fields in
+ * bch_extent_crc32/bch_extent_crc64.
+ *
+ * When an extent is checksummed or compressed, it's not possible to read only
+ * the data that is currently live: we have to read the entire extent that was
+ * originally written, and then return only the part of the extent that is
+ * currently live.
+ *
+ * Thus, in addition to the current size of the extent in struct bkey, we need
+ * to store the size of the originally allocated space - this is the
+ * compressed_size and uncompressed_size fields in bch_extent_crc32/64. Also,
+ * when the extent is trimmed, instead of modifying the offset field of the
+ * pointer, we keep a second smaller offset field - "offset into the original
+ * extent of the currently live region".
+ *
+ * The other major determining factor is replication and data migration:
+ *
+ * Each pointer may have its own bch_extent_crc32/64. When doing a replicated
+ * write, we will initially write all the replicas in the same format, with the
+ * same checksum type and compression format - however, when copygc runs later (or
+ * tiering/cache promotion, anything that moves data), it is not in general
+ * going to rewrite all the pointers at once - one of the replicas may be in a
+ * bucket on one device that has very little fragmentation while another lives
+ * in a bucket that has become heavily fragmented, and thus is being rewritten
+ * sooner than the rest.
+ *
+ * Thus it will only move a subset of the pointers (or in the case of
+ * tiering/cache promotion perhaps add a single pointer without dropping any
+ * current pointers), and if the extent has been partially overwritten it must
+ * write only the currently live portion (or copygc would not be able to reduce
+ * fragmentation!) - which necessitates a different bch_extent_crc format for
+ * the new pointer.
+ *
+ * But in the interests of space efficiency, we don't want to store one
+ * bch_extent_crc for each pointer if we don't have to.
+ *
+ * Thus, a bch_extent consists of bch_extent_crc32s, bch_extent_crc64s, and
+ * bch_extent_ptrs appended arbitrarily one after the other. We determine the
+ * type of a given entry with a scheme similar to utf8 (except we're encoding a
+ * type, not a size), encoding the type in the position of the first set bit:
+ *
+ * bch_extent_crc32	- 0b1
+ * bch_extent_ptr	- 0b10
+ * bch_extent_crc64	- 0b100
+ *
+ * We do it this way because bch_extent_crc32 is _very_ constrained on bits (and
+ * bch_extent_crc64 is the least constrained).
+ *
+ * Then, each bch_extent_crc32/64 applies to the pointers that follow after it,
+ * until the next bch_extent_crc32/64.
+ *
+ * If there are no bch_extent_crcs preceding a bch_extent_ptr, then that pointer
+ * is neither checksummed nor compressed.
+ */
+
+#define BCH_EXTENT_ENTRY_TYPES()		\
+	x(ptr,			0)		\
+	x(crc32,		1)		\
+	x(crc64,		2)		\
+	x(crc128,		3)		\
+	x(stripe_ptr,		4)		\
+	x(rebalance,		5)
+#define BCH_EXTENT_ENTRY_MAX	6
+
+enum bch_extent_entry_type {
+#define x(f, n) BCH_EXTENT_ENTRY_##f = n,
+	BCH_EXTENT_ENTRY_TYPES()
+#undef x
+};
+
+/* Compressed/uncompressed size are stored biased by 1: */
+struct bch_extent_crc32 {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	__u32			type:2,
+				_compressed_size:7,
+				_uncompressed_size:7,
+				offset:7,
+				_unused:1,
+				csum_type:4,
+				compression_type:4;
+	__u32			csum;
+#elif defined (__BIG_ENDIAN_BITFIELD)
+	__u32			csum;
+	__u32			compression_type:4,
+				csum_type:4,
+				_unused:1,
+				offset:7,
+				_uncompressed_size:7,
+				_compressed_size:7,
+				type:2;
+#endif
+} __packed __aligned(8);
+
+#define CRC32_SIZE_MAX		(1U << 7)
+#define CRC32_NONCE_MAX		0
+
+struct bch_extent_crc64 {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	__u64			type:3,
+				_compressed_size:9,
+				_uncompressed_size:9,
+				offset:9,
+				nonce:10,
+				csum_type:4,
+				compression_type:4,
+				csum_hi:16;
+#elif defined (__BIG_ENDIAN_BITFIELD)
+	__u64			csum_hi:16,
+				compression_type:4,
+				csum_type:4,
+				nonce:10,
+				offset:9,
+				_uncompressed_size:9,
+				_compressed_size:9,
+				type:3;
+#endif
+	__u64			csum_lo;
+} __packed __aligned(8);
+
+#define CRC64_SIZE_MAX		(1U << 9)
+#define CRC64_NONCE_MAX		((1U << 10) - 1)
+
+struct bch_extent_crc128 {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	__u64			type:4,
+				_compressed_size:13,
+				_uncompressed_size:13,
+				offset:13,
+				nonce:13,
+				csum_type:4,
+				compression_type:4;
+#elif defined (__BIG_ENDIAN_BITFIELD)
+	__u64			compression_type:4,
+				csum_type:4,
+				nonce:13,
+				offset:13,
+				_uncompressed_size:13,
+				_compressed_size:13,
+				type:4;
+#endif
+	struct bch_csum		csum;
+} __packed __aligned(8);
+
+#define CRC128_SIZE_MAX		(1U << 13)
+#define CRC128_NONCE_MAX	((1U << 13) - 1)
+
+/*
+ * @reservation - pointer hasn't been written to, just reserved
+ */
+struct bch_extent_ptr {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	__u64			type:1,
+				cached:1,
+				unused:1,
+				unwritten:1,
+				offset:44, /* 8 petabytes */
+				dev:8,
+				gen:8;
+#elif defined (__BIG_ENDIAN_BITFIELD)
+	__u64			gen:8,
+				dev:8,
+				offset:44,
+				unwritten:1,
+				unused:1,
+				cached:1,
+				type:1;
+#endif
+} __packed __aligned(8);
+
+struct bch_extent_stripe_ptr {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	__u64			type:5,
+				block:8,
+				redundancy:4,
+				idx:47;
+#elif defined (__BIG_ENDIAN_BITFIELD)
+	__u64			idx:47,
+				redundancy:4,
+				block:8,
+				type:5;
+#endif
+};
+
+struct bch_extent_rebalance {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	__u64			type:6,
+				unused:34,
+				compression:8, /* enum bch_compression_opt */
+				target:16;
+#elif defined (__BIG_ENDIAN_BITFIELD)
+	__u64			target:16,
+				compression:8,
+				unused:34,
+				type:6;
+#endif
+};
+
+union bch_extent_entry {
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ ||  __BITS_PER_LONG == 64
+	unsigned long			type;
+#elif __BITS_PER_LONG == 32
+	struct {
+		unsigned long		pad;
+		unsigned long		type;
+	};
+#else
+#error edit for your odd byteorder.
+#endif
+
+#define x(f, n) struct bch_extent_##f	f;
+	BCH_EXTENT_ENTRY_TYPES()
+#undef x
+};
+
+struct bch_btree_ptr {
+	struct bch_val		v;
+
+	__u64			_data[0];
+	struct bch_extent_ptr	start[];
+} __packed __aligned(8);
+
+struct bch_btree_ptr_v2 {
+	struct bch_val		v;
+
+	__u64			mem_ptr;
+	__le64			seq;
+	__le16			sectors_written;
+	__le16			flags;
+	struct bpos		min_key;
+	__u64			_data[0];
+	struct bch_extent_ptr	start[];
+} __packed __aligned(8);
+
+LE16_BITMASK(BTREE_PTR_RANGE_UPDATED,	struct bch_btree_ptr_v2, flags, 0, 1);
+
+struct bch_extent {
+	struct bch_val		v;
+
+	__u64			_data[0];
+	union bch_extent_entry	start[];
+} __packed __aligned(8);
+
+/* Maximum size (in u64s) a single pointer could be: */
+#define BKEY_EXTENT_PTR_U64s_MAX\
+	((sizeof(struct bch_extent_crc128) +			\
+	  sizeof(struct bch_extent_ptr)) / sizeof(__u64))
+
+/* Maximum possible size of an entire extent value: */
+#define BKEY_EXTENT_VAL_U64s_MAX				\
+	(1 + BKEY_EXTENT_PTR_U64s_MAX * (BCH_REPLICAS_MAX + 1))
+
+/* * Maximum possible size of an entire extent, key + value: */
+#define BKEY_EXTENT_U64s_MAX		(BKEY_U64s + BKEY_EXTENT_VAL_U64s_MAX)
+
+/* Btree pointers don't carry around checksums: */
+#define BKEY_BTREE_PTR_VAL_U64s_MAX				\
+	((sizeof(struct bch_btree_ptr_v2) +			\
+	  sizeof(struct bch_extent_ptr) * BCH_REPLICAS_MAX) / sizeof(__u64))
+#define BKEY_BTREE_PTR_U64s_MAX					\
+	(BKEY_U64s + BKEY_BTREE_PTR_VAL_U64s_MAX)
+
+struct bch_reservation {
+	struct bch_val		v;
+
+	__le32			generation;
+	__u8			nr_replicas;
+	__u8			pad[3];
+} __packed __aligned(8);
+
+struct bch_inline_data {
+	struct bch_val		v;
+	u8			data[];
+};
+
+#endif /* _BCACHEFS_EXTENTS_FORMAT_H */
diff --git a/fs/bcachefs/eytzinger.h b/fs/bcachefs/eytzinger.h
index 9637f636e32d..b04750dbf870 100644
--- a/fs/bcachefs/eytzinger.h
+++ b/fs/bcachefs/eytzinger.h
@@ -156,7 +156,7 @@ static inline unsigned inorder_to_eytzinger1(unsigned i, unsigned size)
 }
 
 #define eytzinger1_for_each(_i, _size)			\
-	for ((_i) = eytzinger1_first((_size));		\
+	for (unsigned (_i) = eytzinger1_first((_size));	\
 	     (_i) != 0;					\
 	     (_i) = eytzinger1_next((_i), (_size)))
 
@@ -227,7 +227,7 @@ static inline unsigned inorder_to_eytzinger0(unsigned i, unsigned size)
 }
 
 #define eytzinger0_for_each(_i, _size)			\
-	for ((_i) = eytzinger0_first((_size));		\
+	for (unsigned (_i) = eytzinger0_first((_size));	\
 	     (_i) != -1;				\
 	     (_i) = eytzinger0_next((_i), (_size)))
 
diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c
index 73c12e565af5..27710cdd5710 100644
--- a/fs/bcachefs/fs-io-buffered.c
+++ b/fs/bcachefs/fs-io-buffered.c
@@ -303,18 +303,6 @@ void bch2_readahead(struct readahead_control *ractl)
 	darray_exit(&readpages_iter.folios);
 }
 
-static void __bchfs_readfolio(struct bch_fs *c, struct bch_read_bio *rbio,
-			     subvol_inum inum, struct folio *folio)
-{
-	bch2_folio_create(folio, __GFP_NOFAIL);
-
-	rbio->bio.bi_opf = REQ_OP_READ|REQ_SYNC;
-	rbio->bio.bi_iter.bi_sector = folio_sector(folio);
-	BUG_ON(!bio_add_folio(&rbio->bio, folio, folio_size(folio), 0));
-
-	bch2_trans_run(c, (bchfs_read(trans, rbio, inum, NULL), 0));
-}
-
 static void bch2_read_single_folio_end_io(struct bio *bio)
 {
 	complete(bio->bi_private);
@@ -329,6 +317,9 @@ int bch2_read_single_folio(struct folio *folio, struct address_space *mapping)
 	int ret;
 	DECLARE_COMPLETION_ONSTACK(done);
 
+	if (!bch2_folio_create(folio, GFP_KERNEL))
+		return -ENOMEM;
+
 	bch2_inode_opts_get(&opts, c, &inode->ei_inode);
 
 	rbio = rbio_init(bio_alloc_bioset(NULL, 1, REQ_OP_READ, GFP_KERNEL, &c->bio_read),
@@ -336,7 +327,11 @@ int bch2_read_single_folio(struct folio *folio, struct address_space *mapping)
 	rbio->bio.bi_private = &done;
 	rbio->bio.bi_end_io = bch2_read_single_folio_end_io;
 
-	__bchfs_readfolio(c, rbio, inode_inum(inode), folio);
+	rbio->bio.bi_opf = REQ_OP_READ|REQ_SYNC;
+	rbio->bio.bi_iter.bi_sector = folio_sector(folio);
+	BUG_ON(!bio_add_folio(&rbio->bio, folio, folio_size(folio), 0));
+
+	bch2_trans_run(c, (bchfs_read(trans, rbio, inode_inum(inode), NULL), 0));
 	wait_for_completion(&done);
 
 	ret = blk_status_to_errno(rbio->bio.bi_status);
diff --git a/fs/bcachefs/fs-io-direct.c b/fs/bcachefs/fs-io-direct.c
index fdd57c5785c9..33cb6da3a5ad 100644
--- a/fs/bcachefs/fs-io-direct.c
+++ b/fs/bcachefs/fs-io-direct.c
@@ -77,6 +77,10 @@ static int bch2_direct_IO_read(struct kiocb *req, struct iov_iter *iter)
 
 	bch2_inode_opts_get(&opts, c, &inode->ei_inode);
 
+	/* bios must be 512 byte aligned: */
+	if ((offset|iter->count) & (SECTOR_SIZE - 1))
+		return -EINVAL;
+
 	ret = min_t(loff_t, iter->count,
 		    max_t(loff_t, 0, i_size_read(&inode->v) - offset));
 
@@ -84,6 +88,8 @@ static int bch2_direct_IO_read(struct kiocb *req, struct iov_iter *iter)
 		return ret;
 
 	shorten = iov_iter_count(iter) - round_up(ret, block_bytes(c));
+	if (shorten >= iter->count)
+		shorten = 0;
 	iter->count -= shorten;
 
 	bio = bio_alloc_bioset(NULL,
diff --git a/fs/bcachefs/fs-io-pagecache.c b/fs/bcachefs/fs-io-pagecache.c
index ff664fd0d8ef..d359aa9b33b8 100644
--- a/fs/bcachefs/fs-io-pagecache.c
+++ b/fs/bcachefs/fs-io-pagecache.c
@@ -309,39 +309,49 @@ void bch2_mark_pagecache_unallocated(struct bch_inode_info *inode,
 	}
 }
 
-void bch2_mark_pagecache_reserved(struct bch_inode_info *inode,
-				  u64 start, u64 end)
+int bch2_mark_pagecache_reserved(struct bch_inode_info *inode,
+				 u64 *start, u64 end,
+				 bool nonblocking)
 {
 	struct bch_fs *c = inode->v.i_sb->s_fs_info;
-	pgoff_t index = start >> PAGE_SECTORS_SHIFT;
+	pgoff_t index = *start >> PAGE_SECTORS_SHIFT;
 	pgoff_t end_index = (end - 1) >> PAGE_SECTORS_SHIFT;
 	struct folio_batch fbatch;
 	s64 i_sectors_delta = 0;
-	unsigned i, j;
+	int ret = 0;
 
-	if (end <= start)
-		return;
+	if (end <= *start)
+		return 0;
 
 	folio_batch_init(&fbatch);
 
 	while (filemap_get_folios(inode->v.i_mapping,
 				  &index, end_index, &fbatch)) {
-		for (i = 0; i < folio_batch_count(&fbatch); i++) {
+		for (unsigned i = 0; i < folio_batch_count(&fbatch); i++) {
 			struct folio *folio = fbatch.folios[i];
+
+			if (!nonblocking)
+				folio_lock(folio);
+			else if (!folio_trylock(folio)) {
+				folio_batch_release(&fbatch);
+				ret = -EAGAIN;
+				break;
+			}
+
 			u64 folio_start = folio_sector(folio);
 			u64 folio_end = folio_end_sector(folio);
-			unsigned folio_offset = max(start, folio_start) - folio_start;
-			unsigned folio_len = min(end, folio_end) - folio_offset - folio_start;
-			struct bch_folio *s;
 
 			BUG_ON(end <= folio_start);
 
-			folio_lock(folio);
-			s = bch2_folio(folio);
+			*start = min(end, folio_end);
 
+			struct bch_folio *s = bch2_folio(folio);
 			if (s) {
+				unsigned folio_offset = max(*start, folio_start) - folio_start;
+				unsigned folio_len = min(end, folio_end) - folio_offset - folio_start;
+
 				spin_lock(&s->lock);
-				for (j = folio_offset; j < folio_offset + folio_len; j++) {
+				for (unsigned j = folio_offset; j < folio_offset + folio_len; j++) {
 					i_sectors_delta -= s->s[j].state == SECTOR_dirty;
 					bch2_folio_sector_set(folio, s, j,
 						folio_sector_reserve(s->s[j].state));
@@ -356,6 +366,7 @@ void bch2_mark_pagecache_reserved(struct bch_inode_info *inode,
 	}
 
 	bch2_i_sectors_acct(c, inode, NULL, i_sectors_delta);
+	return ret;
 }
 
 static inline unsigned sectors_to_reserve(struct bch_folio_sector *s,
diff --git a/fs/bcachefs/fs-io-pagecache.h b/fs/bcachefs/fs-io-pagecache.h
index 27f712ae37a6..8cbaba6565b4 100644
--- a/fs/bcachefs/fs-io-pagecache.h
+++ b/fs/bcachefs/fs-io-pagecache.h
@@ -143,7 +143,7 @@ int bch2_folio_set(struct bch_fs *, subvol_inum, struct folio **, unsigned);
 void bch2_bio_page_state_set(struct bio *, struct bkey_s_c);
 
 void bch2_mark_pagecache_unallocated(struct bch_inode_info *, u64, u64);
-void bch2_mark_pagecache_reserved(struct bch_inode_info *, u64, u64);
+int bch2_mark_pagecache_reserved(struct bch_inode_info *, u64 *, u64, bool);
 
 int bch2_get_folio_disk_reservation(struct bch_fs *,
 				struct bch_inode_info *,
diff --git a/fs/bcachefs/fs-io.c b/fs/bcachefs/fs-io.c
index 98bd5babab19..8c70123b6a0c 100644
--- a/fs/bcachefs/fs-io.c
+++ b/fs/bcachefs/fs-io.c
@@ -79,7 +79,7 @@ void bch2_inode_flush_nocow_writes_async(struct bch_fs *c,
 			continue;
 
 		bio = container_of(bio_alloc_bioset(ca->disk_sb.bdev, 0,
-						    REQ_OP_FLUSH,
+						    REQ_OP_WRITE|REQ_PREFLUSH,
 						    GFP_KERNEL,
 						    &c->nocow_flush_bioset),
 				   struct nocow_flush, bio);
@@ -675,8 +675,11 @@ static int __bchfs_fallocate(struct bch_inode_info *inode, int mode,
 
 		bch2_i_sectors_acct(c, inode, &quota_res, i_sectors_delta);
 
-		drop_locks_do(trans,
-			(bch2_mark_pagecache_reserved(inode, hole_start, iter.pos.offset), 0));
+		if (bch2_mark_pagecache_reserved(inode, &hole_start,
+						 iter.pos.offset, true))
+			drop_locks_do(trans,
+				bch2_mark_pagecache_reserved(inode, &hole_start,
+							     iter.pos.offset, false));
 bkey_err:
 		bch2_quota_reservation_put(c, inode, &quota_res);
 		if (bch2_err_matches(ret, BCH_ERR_transaction_restart))
diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c
index 1cbc5807bc80..3dc8630ff9fe 100644
--- a/fs/bcachefs/fs-ioctl.c
+++ b/fs/bcachefs/fs-ioctl.c
@@ -337,11 +337,12 @@ static long __bch2_ioctl_subvolume_create(struct bch_fs *c, struct file *filp,
 	if (arg.flags & BCH_SUBVOL_SNAPSHOT_RO)
 		create_flags |= BCH_CREATE_SNAPSHOT_RO;
 
-	/* why do we need this lock? */
-	down_read(&c->vfs_sb->s_umount);
-
-	if (arg.flags & BCH_SUBVOL_SNAPSHOT_CREATE)
+	if (arg.flags & BCH_SUBVOL_SNAPSHOT_CREATE) {
+		/* sync_inodes_sb enforce s_umount is locked */
+		down_read(&c->vfs_sb->s_umount);
 		sync_inodes_sb(c->vfs_sb);
+		up_read(&c->vfs_sb->s_umount);
+	}
 retry:
 	if (arg.src_ptr) {
 		error = user_path_at(arg.dirfd,
@@ -425,8 +426,6 @@ err2:
 		goto retry;
 	}
 err1:
-	up_read(&c->vfs_sb->s_umount);
-
 	return error;
 }
 
@@ -456,6 +455,7 @@ static long bch2_ioctl_subvolume_destroy(struct bch_fs *c, struct file *filp,
 	if (IS_ERR(victim))
 		return PTR_ERR(victim);
 
+	dir = d_inode(path.dentry);
 	if (victim->d_sb->s_fs_info != c) {
 		ret = -EXDEV;
 		goto err;
@@ -464,14 +464,13 @@ static long bch2_ioctl_subvolume_destroy(struct bch_fs *c, struct file *filp,
 		ret = -ENOENT;
 		goto err;
 	}
-	dir = d_inode(path.dentry);
 	ret = __bch2_unlink(dir, victim, true);
 	if (!ret) {
 		fsnotify_rmdir(dir, victim);
 		d_delete(victim);
 	}
-	inode_unlock(dir);
 err:
+	inode_unlock(dir);
 	dput(victim);
 	path_put(&path);
 	return ret;
diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index ec419b8e2c43..77ae65542db9 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -435,7 +435,7 @@ static int bch2_link(struct dentry *old_dentry, struct inode *vdir,
 		bch2_subvol_is_ro(c, inode->ei_subvol) ?:
 		__bch2_link(c, inode, dir, dentry);
 	if (unlikely(ret))
-		return ret;
+		return bch2_err_class(ret);
 
 	ihold(&inode->v);
 	d_instantiate(dentry, &inode->v);
@@ -487,8 +487,9 @@ static int bch2_unlink(struct inode *vdir, struct dentry *dentry)
 	struct bch_inode_info *dir= to_bch_ei(vdir);
 	struct bch_fs *c = dir->v.i_sb->s_fs_info;
 
-	return bch2_subvol_is_ro(c, dir->ei_subvol) ?:
+	int ret = bch2_subvol_is_ro(c, dir->ei_subvol) ?:
 		__bch2_unlink(vdir, dentry, false);
+	return bch2_err_class(ret);
 }
 
 static int bch2_symlink(struct mnt_idmap *idmap,
@@ -523,7 +524,7 @@ static int bch2_symlink(struct mnt_idmap *idmap,
 	return 0;
 err:
 	iput(&inode->v);
-	return ret;
+	return bch2_err_class(ret);
 }
 
 static int bch2_mkdir(struct mnt_idmap *idmap,
@@ -641,7 +642,7 @@ err:
 			   src_inode,
 			   dst_inode);
 
-	return ret;
+	return bch2_err_class(ret);
 }
 
 static void bch2_setattr_copy(struct mnt_idmap *idmap,
diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 4f0ecd605675..6a760777bafb 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -119,22 +119,19 @@ static int lookup_inode(struct btree_trans *trans, u64 inode_nr,
 	if (!ret)
 		*snapshot = iter.pos.snapshot;
 err:
-	bch_err_msg(trans->c, ret, "fetching inode %llu:%u", inode_nr, *snapshot);
 	bch2_trans_iter_exit(trans, &iter);
 	return ret;
 }
 
-static int __lookup_dirent(struct btree_trans *trans,
+static int lookup_dirent_in_snapshot(struct btree_trans *trans,
 			   struct bch_hash_info hash_info,
 			   subvol_inum dir, struct qstr *name,
-			   u64 *target, unsigned *type)
+			   u64 *target, unsigned *type, u32 snapshot)
 {
 	struct btree_iter iter;
 	struct bkey_s_c_dirent d;
-	int ret;
-
-	ret = bch2_hash_lookup(trans, &iter, bch2_dirent_hash_desc,
-			       &hash_info, dir, name, 0);
+	int ret = bch2_hash_lookup_in_snapshot(trans, &iter, bch2_dirent_hash_desc,
+			       &hash_info, dir, name, 0, snapshot);
 	if (ret)
 		return ret;
 
@@ -225,15 +222,16 @@ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot,
 
 	struct bch_inode_unpacked root_inode;
 	struct bch_hash_info root_hash_info;
-	ret = lookup_inode(trans, root_inum.inum, &root_inode, &snapshot);
+	u32 root_inode_snapshot = snapshot;
+	ret = lookup_inode(trans, root_inum.inum, &root_inode, &root_inode_snapshot);
 	bch_err_msg(c, ret, "looking up root inode");
 	if (ret)
 		return ret;
 
 	root_hash_info = bch2_hash_info_init(c, &root_inode);
 
-	ret = __lookup_dirent(trans, root_hash_info, root_inum,
-			      &lostfound_str, &inum, &d_type);
+	ret = lookup_dirent_in_snapshot(trans, root_hash_info, root_inum,
+			      &lostfound_str, &inum, &d_type, snapshot);
 	if (bch2_err_matches(ret, ENOENT))
 		goto create_lostfound;
 
@@ -250,7 +248,10 @@ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot,
 	 * The bch2_check_dirents pass has already run, dangling dirents
 	 * shouldn't exist here:
 	 */
-	return lookup_inode(trans, inum, lostfound, &snapshot);
+	ret = lookup_inode(trans, inum, lostfound, &snapshot);
+	bch_err_msg(c, ret, "looking up lost+found %llu:%u in (root inode %llu, snapshot root %u)",
+		    inum, snapshot, root_inum.inum, bch2_snapshot_root(c, snapshot));
+	return ret;
 
 create_lostfound:
 	/*
diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c
index 37dce96f48ac..086f0090b03a 100644
--- a/fs/bcachefs/inode.c
+++ b/fs/bcachefs/inode.c
@@ -506,22 +506,33 @@ fsck_err:
 static void __bch2_inode_unpacked_to_text(struct printbuf *out,
 					  struct bch_inode_unpacked *inode)
 {
-	prt_printf(out, "mode=%o ", inode->bi_mode);
+	printbuf_indent_add(out, 2);
+	prt_printf(out, "mode=%o", inode->bi_mode);
+	prt_newline(out);
 
 	prt_str(out, "flags=");
 	prt_bitflags(out, bch2_inode_flag_strs, inode->bi_flags & ((1U << 20) - 1));
 	prt_printf(out, " (%x)", inode->bi_flags);
+	prt_newline(out);
 
-	prt_printf(out, " journal_seq=%llu bi_size=%llu bi_sectors=%llu bi_version=%llu",
-	       inode->bi_journal_seq,
-	       inode->bi_size,
-	       inode->bi_sectors,
-	       inode->bi_version);
+	prt_printf(out, "journal_seq=%llu", inode->bi_journal_seq);
+	prt_newline(out);
+
+	prt_printf(out, "bi_size=%llu", inode->bi_size);
+	prt_newline(out);
+
+	prt_printf(out, "bi_sectors=%llu", inode->bi_sectors);
+	prt_newline(out);
+
+	prt_newline(out);
+	prt_printf(out, "bi_version=%llu", inode->bi_version);
 
 #define x(_name, _bits)						\
-	prt_printf(out, " "#_name "=%llu", (u64) inode->_name);
+	prt_printf(out, #_name "=%llu", (u64) inode->_name);	\
+	prt_newline(out);
 	BCH_INODE_FIELDS_v3()
 #undef  x
+	printbuf_indent_sub(out, 2);
 }
 
 void bch2_inode_unpacked_to_text(struct printbuf *out, struct bch_inode_unpacked *inode)
@@ -587,7 +598,7 @@ int bch2_trigger_inode(struct btree_trans *trans,
 		}
 	}
 
-	if (!(flags & BTREE_TRIGGER_TRANSACTIONAL) && (flags & BTREE_TRIGGER_INSERT)) {
+	if ((flags & BTREE_TRIGGER_ATOMIC) && (flags & BTREE_TRIGGER_INSERT)) {
 		BUG_ON(!trans->journal_res.seq);
 
 		bkey_s_to_inode_v3(new).v->bi_journal_seq = cpu_to_le64(trans->journal_res.seq);
@@ -597,7 +608,7 @@ int bch2_trigger_inode(struct btree_trans *trans,
 		struct bch_fs *c = trans->c;
 
 		percpu_down_read(&c->mark_lock);
-		this_cpu_add(c->usage_gc->nr_inodes, nr);
+		this_cpu_add(c->usage_gc->b.nr_inodes, nr);
 		percpu_up_read(&c->mark_lock);
 	}
 
diff --git a/fs/bcachefs/inode_format.h b/fs/bcachefs/inode_format.h
new file mode 100644
index 000000000000..83d107331edf
--- /dev/null
+++ b/fs/bcachefs/inode_format.h
@@ -0,0 +1,166 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_INODE_FORMAT_H
+#define _BCACHEFS_INODE_FORMAT_H
+
+#define BLOCKDEV_INODE_MAX	4096
+#define BCACHEFS_ROOT_INO	4096
+
+struct bch_inode {
+	struct bch_val		v;
+
+	__le64			bi_hash_seed;
+	__le32			bi_flags;
+	__le16			bi_mode;
+	__u8			fields[];
+} __packed __aligned(8);
+
+struct bch_inode_v2 {
+	struct bch_val		v;
+
+	__le64			bi_journal_seq;
+	__le64			bi_hash_seed;
+	__le64			bi_flags;
+	__le16			bi_mode;
+	__u8			fields[];
+} __packed __aligned(8);
+
+struct bch_inode_v3 {
+	struct bch_val		v;
+
+	__le64			bi_journal_seq;
+	__le64			bi_hash_seed;
+	__le64			bi_flags;
+	__le64			bi_sectors;
+	__le64			bi_size;
+	__le64			bi_version;
+	__u8			fields[];
+} __packed __aligned(8);
+
+#define INODEv3_FIELDS_START_INITIAL	6
+#define INODEv3_FIELDS_START_CUR	(offsetof(struct bch_inode_v3, fields) / sizeof(__u64))
+
+struct bch_inode_generation {
+	struct bch_val		v;
+
+	__le32			bi_generation;
+	__le32			pad;
+} __packed __aligned(8);
+
+/*
+ * bi_subvol and bi_parent_subvol are only set for subvolume roots:
+ */
+
+#define BCH_INODE_FIELDS_v2()			\
+	x(bi_atime,			96)	\
+	x(bi_ctime,			96)	\
+	x(bi_mtime,			96)	\
+	x(bi_otime,			96)	\
+	x(bi_size,			64)	\
+	x(bi_sectors,			64)	\
+	x(bi_uid,			32)	\
+	x(bi_gid,			32)	\
+	x(bi_nlink,			32)	\
+	x(bi_generation,		32)	\
+	x(bi_dev,			32)	\
+	x(bi_data_checksum,		8)	\
+	x(bi_compression,		8)	\
+	x(bi_project,			32)	\
+	x(bi_background_compression,	8)	\
+	x(bi_data_replicas,		8)	\
+	x(bi_promote_target,		16)	\
+	x(bi_foreground_target,		16)	\
+	x(bi_background_target,		16)	\
+	x(bi_erasure_code,		16)	\
+	x(bi_fields_set,		16)	\
+	x(bi_dir,			64)	\
+	x(bi_dir_offset,		64)	\
+	x(bi_subvol,			32)	\
+	x(bi_parent_subvol,		32)
+
+#define BCH_INODE_FIELDS_v3()			\
+	x(bi_atime,			96)	\
+	x(bi_ctime,			96)	\
+	x(bi_mtime,			96)	\
+	x(bi_otime,			96)	\
+	x(bi_uid,			32)	\
+	x(bi_gid,			32)	\
+	x(bi_nlink,			32)	\
+	x(bi_generation,		32)	\
+	x(bi_dev,			32)	\
+	x(bi_data_checksum,		8)	\
+	x(bi_compression,		8)	\
+	x(bi_project,			32)	\
+	x(bi_background_compression,	8)	\
+	x(bi_data_replicas,		8)	\
+	x(bi_promote_target,		16)	\
+	x(bi_foreground_target,		16)	\
+	x(bi_background_target,		16)	\
+	x(bi_erasure_code,		16)	\
+	x(bi_fields_set,		16)	\
+	x(bi_dir,			64)	\
+	x(bi_dir_offset,		64)	\
+	x(bi_subvol,			32)	\
+	x(bi_parent_subvol,		32)	\
+	x(bi_nocow,			8)
+
+/* subset of BCH_INODE_FIELDS */
+#define BCH_INODE_OPTS()			\
+	x(data_checksum,		8)	\
+	x(compression,			8)	\
+	x(project,			32)	\
+	x(background_compression,	8)	\
+	x(data_replicas,		8)	\
+	x(promote_target,		16)	\
+	x(foreground_target,		16)	\
+	x(background_target,		16)	\
+	x(erasure_code,			16)	\
+	x(nocow,			8)
+
+enum inode_opt_id {
+#define x(name, ...)				\
+	Inode_opt_##name,
+	BCH_INODE_OPTS()
+#undef  x
+	Inode_opt_nr,
+};
+
+#define BCH_INODE_FLAGS()			\
+	x(sync,				0)	\
+	x(immutable,			1)	\
+	x(append,			2)	\
+	x(nodump,			3)	\
+	x(noatime,			4)	\
+	x(i_size_dirty,			5)	\
+	x(i_sectors_dirty,		6)	\
+	x(unlinked,			7)	\
+	x(backptr_untrusted,		8)
+
+/* bits 20+ reserved for packed fields below: */
+
+enum bch_inode_flags {
+#define x(t, n)	BCH_INODE_##t = 1U << n,
+	BCH_INODE_FLAGS()
+#undef x
+};
+
+enum __bch_inode_flags {
+#define x(t, n)	__BCH_INODE_##t = n,
+	BCH_INODE_FLAGS()
+#undef x
+};
+
+LE32_BITMASK(INODE_STR_HASH,	struct bch_inode, bi_flags, 20, 24);
+LE32_BITMASK(INODE_NR_FIELDS,	struct bch_inode, bi_flags, 24, 31);
+LE32_BITMASK(INODE_NEW_VARINT,	struct bch_inode, bi_flags, 31, 32);
+
+LE64_BITMASK(INODEv2_STR_HASH,	struct bch_inode_v2, bi_flags, 20, 24);
+LE64_BITMASK(INODEv2_NR_FIELDS,	struct bch_inode_v2, bi_flags, 24, 31);
+
+LE64_BITMASK(INODEv3_STR_HASH,	struct bch_inode_v3, bi_flags, 20, 24);
+LE64_BITMASK(INODEv3_NR_FIELDS,	struct bch_inode_v3, bi_flags, 24, 31);
+
+LE64_BITMASK(INODEv3_FIELDS_START,
+				struct bch_inode_v3, bi_flags, 31, 36);
+LE64_BITMASK(INODEv3_MODE,	struct bch_inode_v3, bi_flags, 36, 52);
+
+#endif /* _BCACHEFS_INODE_FORMAT_H */
diff --git a/fs/bcachefs/io_misc.c b/fs/bcachefs/io_misc.c
index ca6d5f516aa2..1baf78594cca 100644
--- a/fs/bcachefs/io_misc.c
+++ b/fs/bcachefs/io_misc.c
@@ -442,9 +442,7 @@ case LOGGED_OP_FINSERT_shift_extents:
 
 		op->v.pos = cpu_to_le64(insert ? bkey_start_offset(&delete.k) : delete.k.p.offset);
 
-		ret =   bch2_bkey_set_needs_rebalance(c, copy,
-					opts.background_target,
-					opts.background_compression) ?:
+		ret =   bch2_bkey_set_needs_rebalance(c, copy, &opts) ?:
 			bch2_btree_insert_trans(trans, BTREE_ID_extents, &delete, 0) ?:
 			bch2_btree_insert_trans(trans, BTREE_ID_extents, copy, 0) ?:
 			bch2_logged_op_update(trans, &op->k_i) ?:
diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c
index 33c0e783d546..2c098ac017b3 100644
--- a/fs/bcachefs/io_write.c
+++ b/fs/bcachefs/io_write.c
@@ -362,9 +362,7 @@ static int bch2_write_index_default(struct bch_write_op *op)
 				     bkey_start_pos(&sk.k->k),
 				     BTREE_ITER_SLOTS|BTREE_ITER_INTENT);
 
-		ret =   bch2_bkey_set_needs_rebalance(c, sk.k,
-					op->opts.background_target,
-					op->opts.background_compression) ?:
+		ret =   bch2_bkey_set_needs_rebalance(c, sk.k, &op->opts) ?:
 			bch2_extent_update(trans, inum, &iter, sk.k,
 					&op->res,
 					op->new_i_size, &op->i_sectors_delta,
@@ -1447,10 +1445,11 @@ err:
 			op->flags |= BCH_WRITE_DONE;
 
 			if (ret < 0) {
-				bch_err_inum_offset_ratelimited(c,
-					op->pos.inode,
-					op->pos.offset << 9,
-					"%s(): error: %s", __func__, bch2_err_str(ret));
+				if (!(op->flags & BCH_WRITE_ALLOC_NOWAIT))
+					bch_err_inum_offset_ratelimited(c,
+						op->pos.inode,
+						op->pos.offset << 9,
+						"%s(): error: %s", __func__, bch2_err_str(ret));
 				op->error = ret;
 				break;
 			}
@@ -1565,6 +1564,7 @@ CLOSURE_CALLBACK(bch2_write)
 	BUG_ON(!op->write_point.v);
 	BUG_ON(bkey_eq(op->pos, POS_MAX));
 
+	op->nr_replicas_required = min_t(unsigned, op->nr_replicas_required, op->nr_replicas);
 	op->start_time = local_clock();
 	bch2_keylist_init(&op->insert_keys, op->inline_keys);
 	wbio_init(bio)->put_bio = false;
diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c
index 8538ef34f62b..bc890776eb57 100644
--- a/fs/bcachefs/journal.c
+++ b/fs/bcachefs/journal.c
@@ -27,6 +27,47 @@ static const char * const bch2_journal_errors[] = {
 	NULL
 };
 
+static void bch2_journal_buf_to_text(struct printbuf *out, struct journal *j, u64 seq)
+{
+	union journal_res_state s = READ_ONCE(j->reservations);
+	unsigned i = seq & JOURNAL_BUF_MASK;
+	struct journal_buf *buf = j->buf + i;
+
+	prt_printf(out, "seq:");
+	prt_tab(out);
+	prt_printf(out, "%llu", seq);
+	prt_newline(out);
+	printbuf_indent_add(out, 2);
+
+	prt_printf(out, "refcount:");
+	prt_tab(out);
+	prt_printf(out, "%u", journal_state_count(s, i));
+	prt_newline(out);
+
+	prt_printf(out, "size:");
+	prt_tab(out);
+	prt_human_readable_u64(out, vstruct_bytes(buf->data));
+	prt_newline(out);
+
+	prt_printf(out, "expires");
+	prt_tab(out);
+	prt_printf(out, "%li jiffies", buf->expires - jiffies);
+	prt_newline(out);
+
+	printbuf_indent_sub(out, 2);
+}
+
+static void bch2_journal_bufs_to_text(struct printbuf *out, struct journal *j)
+{
+	if (!out->nr_tabstops)
+		printbuf_tabstop_push(out, 24);
+
+	for (u64 seq = journal_last_unwritten_seq(j);
+	     seq <= journal_cur_seq(j);
+	     seq++)
+		bch2_journal_buf_to_text(out, j, seq);
+}
+
 static inline bool journal_seq_unwritten(struct journal *j, u64 seq)
 {
 	return seq > j->seq_ondisk;
@@ -156,7 +197,7 @@ void bch2_journal_buf_put_final(struct journal *j, u64 seq, bool write)
  * We don't close a journal_buf until the next journal_buf is finished writing,
  * and can be opened again - this also initializes the next journal_buf:
  */
-static void __journal_entry_close(struct journal *j, unsigned closed_val)
+static void __journal_entry_close(struct journal *j, unsigned closed_val, bool trace)
 {
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 	struct journal_buf *buf = journal_cur_buf(j);
@@ -185,7 +226,17 @@ static void __journal_entry_close(struct journal *j, unsigned closed_val)
 	/* Close out old buffer: */
 	buf->data->u64s		= cpu_to_le32(old.cur_entry_offset);
 
-	trace_journal_entry_close(c, vstruct_bytes(buf->data));
+	if (trace_journal_entry_close_enabled() && trace) {
+		struct printbuf pbuf = PRINTBUF;
+		pbuf.atomic++;
+
+		prt_str(&pbuf, "entry size: ");
+		prt_human_readable_u64(&pbuf, vstruct_bytes(buf->data));
+		prt_newline(&pbuf);
+		bch2_prt_task_backtrace(&pbuf, current, 1, GFP_NOWAIT);
+		trace_journal_entry_close(c, pbuf.buf);
+		printbuf_exit(&pbuf);
+	}
 
 	sectors = vstruct_blocks_plus(buf->data, c->block_bits,
 				      buf->u64s_reserved) << c->block_bits;
@@ -225,7 +276,7 @@ static void __journal_entry_close(struct journal *j, unsigned closed_val)
 void bch2_journal_halt(struct journal *j)
 {
 	spin_lock(&j->lock);
-	__journal_entry_close(j, JOURNAL_ENTRY_ERROR_VAL);
+	__journal_entry_close(j, JOURNAL_ENTRY_ERROR_VAL, true);
 	if (!j->err_seq)
 		j->err_seq = journal_cur_seq(j);
 	journal_wake(j);
@@ -239,7 +290,7 @@ static bool journal_entry_want_write(struct journal *j)
 
 	/* Don't close it yet if we already have a write in flight: */
 	if (ret)
-		__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL);
+		__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL, true);
 	else if (nr_unwritten_journal_entries(j)) {
 		struct journal_buf *buf = journal_cur_buf(j);
 
@@ -406,7 +457,7 @@ static void journal_write_work(struct work_struct *work)
 	if (delta > 0)
 		mod_delayed_work(c->io_complete_wq, &j->write_work, delta);
 	else
-		__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL);
+		__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL, true);
 unlock:
 	spin_unlock(&j->lock);
 }
@@ -463,13 +514,21 @@ retry:
 	    buf->buf_size < JOURNAL_ENTRY_SIZE_MAX)
 		j->buf_size_want = max(j->buf_size_want, buf->buf_size << 1);
 
-	__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL);
+	__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL, false);
 	ret = journal_entry_open(j);
 
 	if (ret == JOURNAL_ERR_max_in_flight) {
 		track_event_change(&c->times[BCH_TIME_blocked_journal_max_in_flight],
 				   &j->max_in_flight_start, true);
-		trace_and_count(c, journal_entry_full, c);
+		if (trace_journal_entry_full_enabled()) {
+			struct printbuf buf = PRINTBUF;
+			buf.atomic++;
+
+			bch2_journal_bufs_to_text(&buf, j);
+			trace_journal_entry_full(c, buf.buf);
+			printbuf_exit(&buf);
+		}
+		count_event(c, journal_entry_full);
 	}
 unlock:
 	can_discard = j->can_discard;
@@ -549,7 +608,7 @@ void bch2_journal_entry_res_resize(struct journal *j,
 		/*
 		 * Not enough room in current journal entry, have to flush it:
 		 */
-		__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL);
+		__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL, true);
 	} else {
 		journal_cur_buf(j)->u64s_reserved += d;
 	}
@@ -606,7 +665,7 @@ recheck_need_open:
 		struct journal_res res = { 0 };
 
 		if (journal_entry_is_open(j))
-			__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL);
+			__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL, true);
 
 		spin_unlock(&j->lock);
 
@@ -786,7 +845,7 @@ static struct journal_buf *__bch2_next_write_buffer_flush_journal_buf(struct jou
 
 		if (buf->need_flush_to_write_buffer) {
 			if (seq == journal_cur_seq(j))
-				__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL);
+				__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL, true);
 
 			union journal_res_state s;
 			s.v = atomic64_read_acquire(&j->reservations.counter);
@@ -1339,35 +1398,9 @@ void __bch2_journal_debug_to_text(struct printbuf *out, struct journal *j)
 	}
 
 	prt_newline(out);
-
-	for (u64 seq = journal_cur_seq(j);
-	     seq >= journal_last_unwritten_seq(j);
-	     --seq) {
-		unsigned i = seq & JOURNAL_BUF_MASK;
-
-		prt_printf(out, "unwritten entry:");
-		prt_tab(out);
-		prt_printf(out, "%llu", seq);
-		prt_newline(out);
-		printbuf_indent_add(out, 2);
-
-		prt_printf(out, "refcount:");
-		prt_tab(out);
-		prt_printf(out, "%u", journal_state_count(s, i));
-		prt_newline(out);
-
-		prt_printf(out, "sectors:");
-		prt_tab(out);
-		prt_printf(out, "%u", j->buf[i].sectors);
-		prt_newline(out);
-
-		prt_printf(out, "expires");
-		prt_tab(out);
-		prt_printf(out, "%li jiffies", j->buf[i].expires - jiffies);
-		prt_newline(out);
-
-		printbuf_indent_sub(out, 2);
-	}
+	prt_printf(out, "unwritten entries:");
+	prt_newline(out);
+	bch2_journal_bufs_to_text(out, j);
 
 	prt_printf(out,
 	       "replay done:\t\t%i\n",
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index b0f4dd491e12..47805193f18c 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -683,10 +683,7 @@ static void journal_entry_dev_usage_to_text(struct printbuf *out, struct bch_fs
 	prt_printf(out, "dev=%u", le32_to_cpu(u->dev));
 
 	for (i = 0; i < nr_types; i++) {
-		if (i < BCH_DATA_NR)
-			prt_printf(out, " %s", bch2_data_types[i]);
-		else
-			prt_printf(out, " (unknown data type %u)", i);
+		bch2_prt_data_type(out, i);
 		prt_printf(out, ": buckets=%llu sectors=%llu fragmented=%llu",
 		       le64_to_cpu(u->d[i].buckets),
 		       le64_to_cpu(u->d[i].sectors),
@@ -1481,6 +1478,8 @@ static int journal_write_alloc(struct journal *j, struct journal_buf *w)
 		c->opts.foreground_target;
 	unsigned i, replicas = 0, replicas_want =
 		READ_ONCE(c->opts.metadata_replicas);
+	unsigned replicas_need = min_t(unsigned, replicas_want,
+				       READ_ONCE(c->opts.metadata_replicas_required));
 
 	rcu_read_lock();
 retry:
@@ -1529,7 +1528,7 @@ done:
 
 	BUG_ON(bkey_val_u64s(&w->key.k) > BCH_REPLICAS_MAX);
 
-	return replicas >= c->opts.metadata_replicas_required ? 0 : -EROFS;
+	return replicas >= replicas_need ? 0 : -EROFS;
 }
 
 static void journal_buf_realloc(struct journal *j, struct journal_buf *buf)
@@ -1991,7 +1990,8 @@ CLOSURE_CALLBACK(bch2_journal_write)
 			percpu_ref_get(&ca->io_ref);
 
 			bio = ca->journal.bio;
-			bio_reset(bio, ca->disk_sb.bdev, REQ_OP_FLUSH);
+			bio_reset(bio, ca->disk_sb.bdev,
+				  REQ_OP_WRITE|REQ_PREFLUSH);
 			bio->bi_end_io		= journal_write_endio;
 			bio->bi_private		= ca;
 			closure_bio_submit(bio, cl);
diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c
index 820d25e19e5f..c33dca641575 100644
--- a/fs/bcachefs/journal_reclaim.c
+++ b/fs/bcachefs/journal_reclaim.c
@@ -205,7 +205,7 @@ void bch2_journal_space_available(struct journal *j)
 
 	j->can_discard = can_discard;
 
-	if (nr_online < c->opts.metadata_replicas_required) {
+	if (nr_online < metadata_replicas_required(c)) {
 		ret = JOURNAL_ERR_insufficient_devices;
 		goto out;
 	}
@@ -892,9 +892,11 @@ int bch2_journal_flush_device_pins(struct journal *j, int dev_idx)
 					 journal_seq_pin(j, seq)->devs);
 		seq++;
 
-		spin_unlock(&j->lock);
-		ret = bch2_mark_replicas(c, &replicas.e);
-		spin_lock(&j->lock);
+		if (replicas.e.nr_devs) {
+			spin_unlock(&j->lock);
+			ret = bch2_mark_replicas(c, &replicas.e);
+			spin_lock(&j->lock);
+		}
 	}
 	spin_unlock(&j->lock);
 err:
diff --git a/fs/bcachefs/logged_ops_format.h b/fs/bcachefs/logged_ops_format.h
new file mode 100644
index 000000000000..6a4bf7129dba
--- /dev/null
+++ b/fs/bcachefs/logged_ops_format.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_LOGGED_OPS_FORMAT_H
+#define _BCACHEFS_LOGGED_OPS_FORMAT_H
+
+struct bch_logged_op_truncate {
+	struct bch_val		v;
+	__le32			subvol;
+	__le32			pad;
+	__le64			inum;
+	__le64			new_i_size;
+};
+
+enum logged_op_finsert_state {
+	LOGGED_OP_FINSERT_start,
+	LOGGED_OP_FINSERT_shift_extents,
+	LOGGED_OP_FINSERT_finish,
+};
+
+struct bch_logged_op_finsert {
+	struct bch_val		v;
+	__u8			state;
+	__u8			pad[3];
+	__le32			subvol;
+	__le64			inum;
+	__le64			dst_offset;
+	__le64			src_offset;
+	__le64			pos;
+};
+
+#endif /* _BCACHEFS_LOGGED_OPS_FORMAT_H */
diff --git a/fs/bcachefs/mean_and_variance.h b/fs/bcachefs/mean_and_variance.h
index b2be565bb8f2..64df11ab422b 100644
--- a/fs/bcachefs/mean_and_variance.h
+++ b/fs/bcachefs/mean_and_variance.h
@@ -17,7 +17,7 @@
  * Rust and rustc has issues with u128.
  */
 
-#if defined(__SIZEOF_INT128__) && defined(__KERNEL__)
+#if defined(__SIZEOF_INT128__) && defined(__KERNEL__) && !defined(CONFIG_PARISC)
 
 typedef struct {
 	unsigned __int128 v;
diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c
index 7a33319dcd16..bf68ea49447b 100644
--- a/fs/bcachefs/move.c
+++ b/fs/bcachefs/move.c
@@ -6,9 +6,11 @@
 #include "backpointers.h"
 #include "bkey_buf.h"
 #include "btree_gc.h"
+#include "btree_io.h"
 #include "btree_update.h"
 #include "btree_update_interior.h"
 #include "btree_write_buffer.h"
+#include "compress.h"
 #include "disk_groups.h"
 #include "ec.h"
 #include "errcode.h"
@@ -34,12 +36,46 @@ const char * const bch2_data_ops_strs[] = {
 	NULL
 };
 
-static void trace_move_extent2(struct bch_fs *c, struct bkey_s_c k)
+static void bch2_data_update_opts_to_text(struct printbuf *out, struct bch_fs *c,
+					  struct bch_io_opts *io_opts,
+					  struct data_update_opts *data_opts)
+{
+	printbuf_tabstop_push(out, 20);
+	prt_str(out, "rewrite ptrs:");
+	prt_tab(out);
+	bch2_prt_u64_base2(out, data_opts->rewrite_ptrs);
+	prt_newline(out);
+
+	prt_str(out, "kill ptrs: ");
+	prt_tab(out);
+	bch2_prt_u64_base2(out, data_opts->kill_ptrs);
+	prt_newline(out);
+
+	prt_str(out, "target: ");
+	prt_tab(out);
+	bch2_target_to_text(out, c, data_opts->target);
+	prt_newline(out);
+
+	prt_str(out, "compression: ");
+	prt_tab(out);
+	bch2_compression_opt_to_text(out, background_compression(*io_opts));
+	prt_newline(out);
+
+	prt_str(out, "extra replicas: ");
+	prt_tab(out);
+	prt_u64(out, data_opts->extra_replicas);
+}
+
+static void trace_move_extent2(struct bch_fs *c, struct bkey_s_c k,
+			       struct bch_io_opts *io_opts,
+			       struct data_update_opts *data_opts)
 {
 	if (trace_move_extent_enabled()) {
 		struct printbuf buf = PRINTBUF;
 
 		bch2_bkey_val_to_text(&buf, c, k);
+		prt_newline(&buf);
+		bch2_data_update_opts_to_text(&buf, c, io_opts, data_opts);
 		trace_move_extent(c, buf.buf);
 		printbuf_exit(&buf);
 	}
@@ -111,6 +147,15 @@ static void move_write(struct moving_io *io)
 		return;
 	}
 
+	if (trace_move_extent_write_enabled()) {
+		struct bch_fs *c = io->write.op.c;
+		struct printbuf buf = PRINTBUF;
+
+		bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(io->write.k.k));
+		trace_move_extent_write(c, buf.buf);
+		printbuf_exit(&buf);
+	}
+
 	closure_get(&io->write.ctxt->cl);
 	atomic_add(io->write_sectors, &io->write.ctxt->write_sectors);
 	atomic_inc(&io->write.ctxt->write_ios);
@@ -241,9 +286,10 @@ int bch2_move_extent(struct moving_context *ctxt,
 	unsigned sectors = k.k->size, pages;
 	int ret = -ENOMEM;
 
+	trace_move_extent2(c, k, &io_opts, &data_opts);
+
 	if (ctxt->stats)
 		ctxt->stats->pos = BBPOS(iter->btree_id, iter->pos);
-	trace_move_extent2(c, k);
 
 	bch2_data_update_opts_normalize(k, &data_opts);
 
@@ -759,6 +805,8 @@ int bch2_evacuate_bucket(struct moving_context *ctxt,
 			if (!b)
 				goto next;
 
+			unsigned sectors = btree_ptr_sectors_written(&b->key);
+
 			ret = bch2_btree_node_rewrite(trans, &iter, b, 0);
 			bch2_trans_iter_exit(trans, &iter);
 
@@ -768,11 +816,10 @@ int bch2_evacuate_bucket(struct moving_context *ctxt,
 				goto err;
 
 			if (ctxt->rate)
-				bch2_ratelimit_increment(ctxt->rate,
-							 c->opts.btree_node_size >> 9);
+				bch2_ratelimit_increment(ctxt->rate, sectors);
 			if (ctxt->stats) {
-				atomic64_add(c->opts.btree_node_size >> 9, &ctxt->stats->sectors_seen);
-				atomic64_add(c->opts.btree_node_size >> 9, &ctxt->stats->sectors_moved);
+				atomic64_add(sectors, &ctxt->stats->sectors_seen);
+				atomic64_add(sectors, &ctxt->stats->sectors_moved);
 			}
 		}
 next:
@@ -1083,9 +1130,9 @@ int bch2_data_job(struct bch_fs *c,
 
 void bch2_move_stats_to_text(struct printbuf *out, struct bch_move_stats *stats)
 {
-	prt_printf(out, "%s: data type=%s pos=",
-		   stats->name,
-		   bch2_data_types[stats->data_type]);
+	prt_printf(out, "%s: data type==", stats->name);
+	bch2_prt_data_type(out, stats->data_type);
+	prt_str(out, " pos=");
 	bch2_bbpos_to_text(out, stats->pos);
 	prt_newline(out);
 	printbuf_indent_add(out, 2);
diff --git a/fs/bcachefs/opts.c b/fs/bcachefs/opts.c
index 8e6f230eac38..b1ed0b9a20d3 100644
--- a/fs/bcachefs/opts.c
+++ b/fs/bcachefs/opts.c
@@ -52,7 +52,7 @@ const char * const bch2_csum_opts[] = {
 	NULL
 };
 
-const char * const bch2_compression_types[] = {
+const char * const __bch2_compression_types[] = {
 	BCH_COMPRESSION_TYPES()
 	NULL
 };
@@ -72,7 +72,7 @@ const char * const bch2_str_hash_opts[] = {
 	NULL
 };
 
-const char * const bch2_data_types[] = {
+const char * const __bch2_data_types[] = {
 	BCH_DATA_TYPES()
 	NULL
 };
diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h
index 93a24fef4214..9a4b7faa3765 100644
--- a/fs/bcachefs/opts.h
+++ b/fs/bcachefs/opts.h
@@ -18,11 +18,11 @@ extern const char * const bch2_sb_compat[];
 extern const char * const __bch2_btree_ids[];
 extern const char * const bch2_csum_types[];
 extern const char * const bch2_csum_opts[];
-extern const char * const bch2_compression_types[];
+extern const char * const __bch2_compression_types[];
 extern const char * const bch2_compression_opts[];
 extern const char * const bch2_str_hash_types[];
 extern const char * const bch2_str_hash_opts[];
-extern const char * const bch2_data_types[];
+extern const char * const __bch2_data_types[];
 extern const char * const bch2_member_states[];
 extern const char * const bch2_jset_entry_types[];
 extern const char * const bch2_fs_usage_types[];
@@ -564,6 +564,11 @@ struct bch_io_opts {
 #undef x
 };
 
+static inline unsigned background_compression(struct bch_io_opts opts)
+{
+	return opts.background_compression ?: opts.compression;
+}
+
 struct bch_io_opts bch2_opts_to_inode_opts(struct bch_opts);
 bool bch2_opt_is_inode_opt(enum bch_opt_id);
 
diff --git a/fs/bcachefs/printbuf.c b/fs/bcachefs/printbuf.c
index accf246c3233..b27d22925929 100644
--- a/fs/bcachefs/printbuf.c
+++ b/fs/bcachefs/printbuf.c
@@ -56,6 +56,7 @@ void bch2_prt_vprintf(struct printbuf *out, const char *fmt, va_list args)
 
 		va_copy(args2, args);
 		len = vsnprintf(out->buf + out->pos, printbuf_remaining(out), fmt, args2);
+		va_end(args2);
 	} while (len + 1 >= printbuf_remaining(out) &&
 		 !bch2_printbuf_make_room(out, len + 1));
 
diff --git a/fs/bcachefs/quota_format.h b/fs/bcachefs/quota_format.h
new file mode 100644
index 000000000000..dc34347ef6c7
--- /dev/null
+++ b/fs/bcachefs/quota_format.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_QUOTA_FORMAT_H
+#define _BCACHEFS_QUOTA_FORMAT_H
+
+/* KEY_TYPE_quota: */
+
+enum quota_types {
+	QTYP_USR		= 0,
+	QTYP_GRP		= 1,
+	QTYP_PRJ		= 2,
+	QTYP_NR			= 3,
+};
+
+enum quota_counters {
+	Q_SPC			= 0,
+	Q_INO			= 1,
+	Q_COUNTERS		= 2,
+};
+
+struct bch_quota_counter {
+	__le64			hardlimit;
+	__le64			softlimit;
+};
+
+struct bch_quota {
+	struct bch_val		v;
+	struct bch_quota_counter c[Q_COUNTERS];
+} __packed __aligned(8);
+
+/* BCH_SB_FIELD_quota: */
+
+struct bch_sb_quota_counter {
+	__le32				timelimit;
+	__le32				warnlimit;
+};
+
+struct bch_sb_quota_type {
+	__le64				flags;
+	struct bch_sb_quota_counter	c[Q_COUNTERS];
+};
+
+struct bch_sb_field_quota {
+	struct bch_sb_field		field;
+	struct bch_sb_quota_type	q[QTYP_NR];
+} __packed __aligned(8);
+
+#endif /* _BCACHEFS_QUOTA_FORMAT_H */
diff --git a/fs/bcachefs/rebalance.c b/fs/bcachefs/rebalance.c
index 95f46cb3b5bd..22d1017aa49b 100644
--- a/fs/bcachefs/rebalance.c
+++ b/fs/bcachefs/rebalance.c
@@ -177,8 +177,7 @@ static struct bkey_s_c next_rebalance_extent(struct btree_trans *trans,
 		prt_str(&buf, "target=");
 		bch2_target_to_text(&buf, c, r->target);
 		prt_str(&buf, " compression=");
-		struct bch_compression_opt opt = __bch2_compression_decode(r->compression);
-		prt_str(&buf, bch2_compression_opts[opt.type]);
+		bch2_compression_opt_to_text(&buf, r->compression);
 		prt_str(&buf, " ");
 		bch2_bkey_val_to_text(&buf, c, k);
 
@@ -254,13 +253,12 @@ static bool rebalance_pred(struct bch_fs *c, void *arg,
 
 	if (k.k->p.inode) {
 		target		= io_opts->background_target;
-		compression	= io_opts->background_compression ?: io_opts->compression;
+		compression	= background_compression(*io_opts);
 	} else {
 		const struct bch_extent_rebalance *r = bch2_bkey_rebalance_opts(k);
 
 		target		= r ? r->target : io_opts->background_target;
-		compression	= r ? r->compression :
-			(io_opts->background_compression ?: io_opts->compression);
+		compression	= r ? r->compression : background_compression(*io_opts);
 	}
 
 	data_opts->rewrite_ptrs		= bch2_bkey_ptrs_need_rebalance(c, k, target, compression);
@@ -371,6 +369,7 @@ static int do_rebalance(struct moving_context *ctxt)
 	    !kthread_should_stop() &&
 	    !atomic64_read(&r->work_stats.sectors_seen) &&
 	    !atomic64_read(&r->scan_stats.sectors_seen)) {
+		bch2_moving_ctxt_flush_all(ctxt);
 		bch2_trans_unlock_long(trans);
 		rebalance_wait(c);
 	}
@@ -385,7 +384,6 @@ static int bch2_rebalance_thread(void *arg)
 	struct bch_fs *c = arg;
 	struct bch_fs_rebalance *r = &c->rebalance;
 	struct moving_context ctxt;
-	int ret;
 
 	set_freezable();
 
@@ -393,8 +391,7 @@ static int bch2_rebalance_thread(void *arg)
 			      writepoint_ptr(&c->rebalance_write_point),
 			      true);
 
-	while (!kthread_should_stop() &&
-	       !(ret = do_rebalance(&ctxt)))
+	while (!kthread_should_stop() && !do_rebalance(&ctxt))
 		;
 
 	bch2_moving_ctxt_exit(&ctxt);
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 725214605a05..21e13bb4335b 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -280,7 +280,7 @@ static int journal_replay_entry_early(struct bch_fs *c,
 					le64_to_cpu(u->v);
 			break;
 		case BCH_FS_USAGE_inodes:
-			c->usage_base->nr_inodes = le64_to_cpu(u->v);
+			c->usage_base->b.nr_inodes = le64_to_cpu(u->v);
 			break;
 		case BCH_FS_USAGE_key_version:
 			atomic64_set(&c->key_version,
@@ -577,8 +577,9 @@ u64 bch2_recovery_passes_from_stable(u64 v)
 
 static bool check_version_upgrade(struct bch_fs *c)
 {
-	unsigned latest_compatible = bch2_latest_compatible_version(c->sb.version);
 	unsigned latest_version	= bcachefs_metadata_version_current;
+	unsigned latest_compatible = min(latest_version,
+					 bch2_latest_compatible_version(c->sb.version));
 	unsigned old_version = c->sb.version_upgrade_complete ?: c->sb.version;
 	unsigned new_version = 0;
 
@@ -597,7 +598,7 @@ static bool check_version_upgrade(struct bch_fs *c)
 			new_version = latest_version;
 			break;
 		case BCH_VERSION_UPGRADE_none:
-			new_version = old_version;
+			new_version = min(old_version, latest_version);
 			break;
 		}
 	}
@@ -774,7 +775,7 @@ int bch2_fs_recovery(struct bch_fs *c)
 		goto err;
 	}
 
-	if (!(c->opts.nochanges && c->opts.norecovery)) {
+	if (!c->opts.nochanges) {
 		mutex_lock(&c->sb_lock);
 		bool write_sb = false;
 
@@ -804,7 +805,7 @@ int bch2_fs_recovery(struct bch_fs *c)
 		if (bch2_check_version_downgrade(c)) {
 			struct printbuf buf = PRINTBUF;
 
-			prt_str(&buf, "Version downgrade required:\n");
+			prt_str(&buf, "Version downgrade required:");
 
 			__le64 passes = ext->recovery_passes_required[0];
 			bch2_sb_set_downgrade(c,
@@ -812,7 +813,7 @@ int bch2_fs_recovery(struct bch_fs *c)
 					BCH_VERSION_MINOR(c->sb.version));
 			passes = ext->recovery_passes_required[0] & ~passes;
 			if (passes) {
-				prt_str(&buf, "  running recovery passes: ");
+				prt_str(&buf, "\n  running recovery passes: ");
 				prt_bitflags(&buf, bch2_recovery_passes,
 					     bch2_recovery_passes_from_stable(le64_to_cpu(passes)));
 			}
diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c
index faa5d3670058..c47c66c2b394 100644
--- a/fs/bcachefs/reflink.c
+++ b/fs/bcachefs/reflink.c
@@ -292,10 +292,10 @@ static inline void check_indirect_extent_deleting(struct bkey_s new, unsigned *f
 	}
 }
 
-int bch2_trans_mark_reflink_v(struct btree_trans *trans,
-			      enum btree_id btree_id, unsigned level,
-			      struct bkey_s_c old, struct bkey_s new,
-			      unsigned flags)
+int bch2_trigger_reflink_v(struct btree_trans *trans,
+			   enum btree_id btree_id, unsigned level,
+			   struct bkey_s_c old, struct bkey_s new,
+			   unsigned flags)
 {
 	if ((flags & BTREE_TRIGGER_TRANSACTIONAL) &&
 	    (flags & BTREE_TRIGGER_INSERT))
@@ -324,7 +324,7 @@ void bch2_indirect_inline_data_to_text(struct printbuf *out,
 	       min(datalen, 32U), d.v->data);
 }
 
-int bch2_trans_mark_indirect_inline_data(struct btree_trans *trans,
+int bch2_trigger_indirect_inline_data(struct btree_trans *trans,
 			      enum btree_id btree_id, unsigned level,
 			      struct bkey_s_c old, struct bkey_s new,
 			      unsigned flags)
@@ -486,6 +486,13 @@ s64 bch2_remap_range(struct bch_fs *c,
 
 		bch2_btree_iter_set_snapshot(&dst_iter, dst_snapshot);
 
+		if (dst_inum.inum < src_inum.inum) {
+			/* Avoid some lock cycle transaction restarts */
+			ret = bch2_btree_iter_traverse(&dst_iter);
+			if (ret)
+				continue;
+		}
+
 		dst_done = dst_iter.pos.offset - dst_start.offset;
 		src_want = POS(src_start.inode, src_start.offset + dst_done);
 		bch2_btree_iter_set_pos(&src_iter, src_want);
@@ -538,9 +545,7 @@ s64 bch2_remap_range(struct bch_fs *c,
 				min(src_k.k->p.offset - src_want.offset,
 				    dst_end.offset - dst_iter.pos.offset));
 
-		ret =   bch2_bkey_set_needs_rebalance(c, new_dst.k,
-					opts.background_target,
-					opts.background_compression) ?:
+		ret =   bch2_bkey_set_needs_rebalance(c, new_dst.k, &opts) ?:
 			bch2_extent_update(trans, dst_inum, &dst_iter,
 					new_dst.k, &disk_res,
 					new_i_size, i_sectors_delta,
diff --git a/fs/bcachefs/reflink.h b/fs/bcachefs/reflink.h
index 8ee778ec0022..4d8867289717 100644
--- a/fs/bcachefs/reflink.h
+++ b/fs/bcachefs/reflink.h
@@ -24,14 +24,14 @@ int bch2_reflink_v_invalid(struct bch_fs *, struct bkey_s_c,
 			   enum bkey_invalid_flags, struct printbuf *);
 void bch2_reflink_v_to_text(struct printbuf *, struct bch_fs *,
 			    struct bkey_s_c);
-int bch2_trans_mark_reflink_v(struct btree_trans *, enum btree_id, unsigned,
+int bch2_trigger_reflink_v(struct btree_trans *, enum btree_id, unsigned,
 			      struct bkey_s_c, struct bkey_s, unsigned);
 
 #define bch2_bkey_ops_reflink_v ((struct bkey_ops) {		\
 	.key_invalid	= bch2_reflink_v_invalid,		\
 	.val_to_text	= bch2_reflink_v_to_text,		\
 	.swab		= bch2_ptr_swab,			\
-	.trigger	= bch2_trans_mark_reflink_v,		\
+	.trigger	= bch2_trigger_reflink_v,		\
 	.min_val_size	= 8,					\
 })
 
@@ -39,7 +39,7 @@ int bch2_indirect_inline_data_invalid(struct bch_fs *, struct bkey_s_c,
 				      enum bkey_invalid_flags, struct printbuf *);
 void bch2_indirect_inline_data_to_text(struct printbuf *,
 				struct bch_fs *, struct bkey_s_c);
-int bch2_trans_mark_indirect_inline_data(struct btree_trans *,
+int bch2_trigger_indirect_inline_data(struct btree_trans *,
 					 enum btree_id, unsigned,
 			      struct bkey_s_c, struct bkey_s,
 			      unsigned);
@@ -47,7 +47,7 @@ int bch2_trans_mark_indirect_inline_data(struct btree_trans *,
 #define bch2_bkey_ops_indirect_inline_data ((struct bkey_ops) {	\
 	.key_invalid	= bch2_indirect_inline_data_invalid,	\
 	.val_to_text	= bch2_indirect_inline_data_to_text,	\
-	.trigger	= bch2_trans_mark_indirect_inline_data,	\
+	.trigger	= bch2_trigger_indirect_inline_data,	\
 	.min_val_size	= 8,					\
 })
 
diff --git a/fs/bcachefs/reflink_format.h b/fs/bcachefs/reflink_format.h
new file mode 100644
index 000000000000..6772eebb1fc6
--- /dev/null
+++ b/fs/bcachefs/reflink_format.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_REFLINK_FORMAT_H
+#define _BCACHEFS_REFLINK_FORMAT_H
+
+struct bch_reflink_p {
+	struct bch_val		v;
+	__le64			idx;
+	/*
+	 * A reflink pointer might point to an indirect extent which is then
+	 * later split (by copygc or rebalance). If we only pointed to part of
+	 * the original indirect extent, and then one of the fragments is
+	 * outside the range we point to, we'd leak a refcount: so when creating
+	 * reflink pointers, we need to store pad values to remember the full
+	 * range we were taking a reference on.
+	 */
+	__le32			front_pad;
+	__le32			back_pad;
+} __packed __aligned(8);
+
+struct bch_reflink_v {
+	struct bch_val		v;
+	__le64			refcount;
+	union bch_extent_entry	start[0];
+	__u64			_data[];
+} __packed __aligned(8);
+
+struct bch_indirect_inline_data {
+	struct bch_val		v;
+	__le64			refcount;
+	u8			data[];
+};
+
+#endif /* _BCACHEFS_REFLINK_FORMAT_H */
diff --git a/fs/bcachefs/replicas.c b/fs/bcachefs/replicas.c
index 92ba56ef1fc8..cc2672c12031 100644
--- a/fs/bcachefs/replicas.c
+++ b/fs/bcachefs/replicas.c
@@ -9,6 +9,12 @@
 static int bch2_cpu_replicas_to_sb_replicas(struct bch_fs *,
 					    struct bch_replicas_cpu *);
 
+/* Some (buggy!) compilers don't allow memcmp to be passed as a pointer */
+static int bch2_memcmp(const void *l, const void *r, size_t size)
+{
+	return memcmp(l, r, size);
+}
+
 /* Replicas tracking - in memory: */
 
 static void verify_replicas_entry(struct bch_replicas_entry_v1 *e)
@@ -33,21 +39,16 @@ void bch2_replicas_entry_sort(struct bch_replicas_entry_v1 *e)
 
 static void bch2_cpu_replicas_sort(struct bch_replicas_cpu *r)
 {
-	eytzinger0_sort(r->entries, r->nr, r->entry_size, memcmp, NULL);
+	eytzinger0_sort(r->entries, r->nr, r->entry_size, bch2_memcmp, NULL);
 }
 
 static void bch2_replicas_entry_v0_to_text(struct printbuf *out,
 					   struct bch_replicas_entry_v0 *e)
 {
-	unsigned i;
-
-	if (e->data_type < BCH_DATA_NR)
-		prt_printf(out, "%s", bch2_data_types[e->data_type]);
-	else
-		prt_printf(out, "(invalid data type %u)", e->data_type);
+	bch2_prt_data_type(out, e->data_type);
 
 	prt_printf(out, ": %u [", e->nr_devs);
-	for (i = 0; i < e->nr_devs; i++)
+	for (unsigned i = 0; i < e->nr_devs; i++)
 		prt_printf(out, i ? " %u" : "%u", e->devs[i]);
 	prt_printf(out, "]");
 }
@@ -55,15 +56,10 @@ static void bch2_replicas_entry_v0_to_text(struct printbuf *out,
 void bch2_replicas_entry_to_text(struct printbuf *out,
 				 struct bch_replicas_entry_v1 *e)
 {
-	unsigned i;
-
-	if (e->data_type < BCH_DATA_NR)
-		prt_printf(out, "%s", bch2_data_types[e->data_type]);
-	else
-		prt_printf(out, "(invalid data type %u)", e->data_type);
+	bch2_prt_data_type(out, e->data_type);
 
 	prt_printf(out, ": %u/%u [", e->nr_required, e->nr_devs);
-	for (i = 0; i < e->nr_devs; i++)
+	for (unsigned i = 0; i < e->nr_devs; i++)
 		prt_printf(out, i ? " %u" : "%u", e->devs[i]);
 	prt_printf(out, "]");
 }
@@ -831,7 +827,7 @@ static int bch2_cpu_replicas_validate(struct bch_replicas_cpu *cpu_r,
 	sort_cmp_size(cpu_r->entries,
 		      cpu_r->nr,
 		      cpu_r->entry_size,
-		      memcmp, NULL);
+		      bch2_memcmp, NULL);
 
 	for (i = 0; i < cpu_r->nr; i++) {
 		struct bch_replicas_entry_v1 *e =
diff --git a/fs/bcachefs/sb-clean.c b/fs/bcachefs/sb-clean.c
index 9632f36f5f31..b6bf0ebe7e84 100644
--- a/fs/bcachefs/sb-clean.c
+++ b/fs/bcachefs/sb-clean.c
@@ -207,7 +207,7 @@ void bch2_journal_super_entries_add_common(struct bch_fs *c,
 
 		u->entry.type	= BCH_JSET_ENTRY_usage;
 		u->entry.btree_id = BCH_FS_USAGE_inodes;
-		u->v		= cpu_to_le64(c->usage_base->nr_inodes);
+		u->v		= cpu_to_le64(c->usage_base->b.nr_inodes);
 	}
 
 	{
diff --git a/fs/bcachefs/counters.c b/fs/bcachefs/sb-counters.c
index 02a996e06a64..7dc898761bb3 100644
--- a/fs/bcachefs/counters.c
+++ b/fs/bcachefs/sb-counters.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "bcachefs.h"
 #include "super-io.h"
-#include "counters.h"
+#include "sb-counters.h"
 
 /* BCH_SB_FIELD_counters */
 
diff --git a/fs/bcachefs/counters.h b/fs/bcachefs/sb-counters.h
index 4778aa19bf34..81f8aec9fcb1 100644
--- a/fs/bcachefs/counters.h
+++ b/fs/bcachefs/sb-counters.h
@@ -1,11 +1,10 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _BCACHEFS_COUNTERS_H
-#define _BCACHEFS_COUNTERS_H
+#ifndef _BCACHEFS_SB_COUNTERS_H
+#define _BCACHEFS_SB_COUNTERS_H
 
 #include "bcachefs.h"
 #include "super-io.h"
 
-
 int bch2_sb_counters_to_cpu(struct bch_fs *);
 int bch2_sb_counters_from_cpu(struct bch_fs *);
 
@@ -14,4 +13,4 @@ int bch2_fs_counters_init(struct bch_fs *);
 
 extern const struct bch_sb_field_ops bch_sb_field_ops_counters;
 
-#endif // _BCACHEFS_COUNTERS_H
+#endif // _BCACHEFS_SB_COUNTERS_H
diff --git a/fs/bcachefs/sb-counters_format.h b/fs/bcachefs/sb-counters_format.h
new file mode 100644
index 000000000000..62ea478215d0
--- /dev/null
+++ b/fs/bcachefs/sb-counters_format.h
@@ -0,0 +1,98 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_SB_COUNTERS_FORMAT_H
+#define _BCACHEFS_SB_COUNTERS_FORMAT_H
+
+#define BCH_PERSISTENT_COUNTERS()				\
+	x(io_read,					0)	\
+	x(io_write,					1)	\
+	x(io_move,					2)	\
+	x(bucket_invalidate,				3)	\
+	x(bucket_discard,				4)	\
+	x(bucket_alloc,					5)	\
+	x(bucket_alloc_fail,				6)	\
+	x(btree_cache_scan,				7)	\
+	x(btree_cache_reap,				8)	\
+	x(btree_cache_cannibalize,			9)	\
+	x(btree_cache_cannibalize_lock,			10)	\
+	x(btree_cache_cannibalize_lock_fail,		11)	\
+	x(btree_cache_cannibalize_unlock,		12)	\
+	x(btree_node_write,				13)	\
+	x(btree_node_read,				14)	\
+	x(btree_node_compact,				15)	\
+	x(btree_node_merge,				16)	\
+	x(btree_node_split,				17)	\
+	x(btree_node_rewrite,				18)	\
+	x(btree_node_alloc,				19)	\
+	x(btree_node_free,				20)	\
+	x(btree_node_set_root,				21)	\
+	x(btree_path_relock_fail,			22)	\
+	x(btree_path_upgrade_fail,			23)	\
+	x(btree_reserve_get_fail,			24)	\
+	x(journal_entry_full,				25)	\
+	x(journal_full,					26)	\
+	x(journal_reclaim_finish,			27)	\
+	x(journal_reclaim_start,			28)	\
+	x(journal_write,				29)	\
+	x(read_promote,					30)	\
+	x(read_bounce,					31)	\
+	x(read_split,					33)	\
+	x(read_retry,					32)	\
+	x(read_reuse_race,				34)	\
+	x(move_extent_read,				35)	\
+	x(move_extent_write,				36)	\
+	x(move_extent_finish,				37)	\
+	x(move_extent_fail,				38)	\
+	x(move_extent_start_fail,			39)	\
+	x(copygc,					40)	\
+	x(copygc_wait,					41)	\
+	x(gc_gens_end,					42)	\
+	x(gc_gens_start,				43)	\
+	x(trans_blocked_journal_reclaim,		44)	\
+	x(trans_restart_btree_node_reused,		45)	\
+	x(trans_restart_btree_node_split,		46)	\
+	x(trans_restart_fault_inject,			47)	\
+	x(trans_restart_iter_upgrade,			48)	\
+	x(trans_restart_journal_preres_get,		49)	\
+	x(trans_restart_journal_reclaim,		50)	\
+	x(trans_restart_journal_res_get,		51)	\
+	x(trans_restart_key_cache_key_realloced,	52)	\
+	x(trans_restart_key_cache_raced,		53)	\
+	x(trans_restart_mark_replicas,			54)	\
+	x(trans_restart_mem_realloced,			55)	\
+	x(trans_restart_memory_allocation_failure,	56)	\
+	x(trans_restart_relock,				57)	\
+	x(trans_restart_relock_after_fill,		58)	\
+	x(trans_restart_relock_key_cache_fill,		59)	\
+	x(trans_restart_relock_next_node,		60)	\
+	x(trans_restart_relock_parent_for_fill,		61)	\
+	x(trans_restart_relock_path,			62)	\
+	x(trans_restart_relock_path_intent,		63)	\
+	x(trans_restart_too_many_iters,			64)	\
+	x(trans_restart_traverse,			65)	\
+	x(trans_restart_upgrade,			66)	\
+	x(trans_restart_would_deadlock,			67)	\
+	x(trans_restart_would_deadlock_write,		68)	\
+	x(trans_restart_injected,			69)	\
+	x(trans_restart_key_cache_upgrade,		70)	\
+	x(trans_traverse_all,				71)	\
+	x(transaction_commit,				72)	\
+	x(write_super,					73)	\
+	x(trans_restart_would_deadlock_recursion_limit,	74)	\
+	x(trans_restart_write_buffer_flush,		75)	\
+	x(trans_restart_split_race,			76)	\
+	x(write_buffer_flush_slowpath,			77)	\
+	x(write_buffer_flush_sync,			78)
+
+enum bch_persistent_counters {
+#define x(t, n, ...) BCH_COUNTER_##t,
+	BCH_PERSISTENT_COUNTERS()
+#undef x
+	BCH_COUNTER_NR
+};
+
+struct bch_sb_field_counters {
+	struct bch_sb_field	field;
+	__le64			d[];
+};
+
+#endif /* _BCACHEFS_SB_COUNTERS_FORMAT_H */
diff --git a/fs/bcachefs/sb-members.c b/fs/bcachefs/sb-members.c
index a44a238bf8b5..eff5ce18c69c 100644
--- a/fs/bcachefs/sb-members.c
+++ b/fs/bcachefs/sb-members.c
@@ -251,7 +251,7 @@ static void member_to_text(struct printbuf *out,
 	prt_printf(out, "Data allowed:");
 	prt_tab(out);
 	if (BCH_MEMBER_DATA_ALLOWED(&m))
-		prt_bitflags(out, bch2_data_types, BCH_MEMBER_DATA_ALLOWED(&m));
+		prt_bitflags(out, __bch2_data_types, BCH_MEMBER_DATA_ALLOWED(&m));
 	else
 		prt_printf(out, "(none)");
 	prt_newline(out);
@@ -259,7 +259,7 @@ static void member_to_text(struct printbuf *out,
 	prt_printf(out, "Has data:");
 	prt_tab(out);
 	if (data_have)
-		prt_bitflags(out, bch2_data_types, data_have);
+		prt_bitflags(out, __bch2_data_types, data_have);
 	else
 		prt_printf(out, "(none)");
 	prt_newline(out);
@@ -421,7 +421,7 @@ void bch2_dev_errors_reset(struct bch_dev *ca)
 	m = bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx);
 	for (unsigned i = 0; i < ARRAY_SIZE(m->errors_at_reset); i++)
 		m->errors_at_reset[i] = cpu_to_le64(atomic64_read(&ca->errors[i]));
-	m->errors_reset_time = ktime_get_real_seconds();
+	m->errors_reset_time = cpu_to_le64(ktime_get_real_seconds());
 
 	bch2_write_super(c);
 	mutex_unlock(&c->sb_lock);
diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c
index 56af937523ff..ac6ba04d5521 100644
--- a/fs/bcachefs/snapshot.c
+++ b/fs/bcachefs/snapshot.c
@@ -728,7 +728,7 @@ static int check_snapshot(struct btree_trans *trans,
 		return 0;
 
 	memset(&s, 0, sizeof(s));
-	memcpy(&s, k.v, bkey_val_bytes(k.k));
+	memcpy(&s, k.v, min(sizeof(s), bkey_val_bytes(k.k)));
 
 	id = le32_to_cpu(s.parent);
 	if (id) {
@@ -1053,6 +1053,8 @@ static int create_snapids(struct btree_trans *trans, u32 parent, u32 tree,
 		n->v.subvol	= cpu_to_le32(snapshot_subvols[i]);
 		n->v.tree	= cpu_to_le32(tree);
 		n->v.depth	= cpu_to_le32(depth);
+		n->v.btime.lo	= cpu_to_le64(bch2_current_time(c));
+		n->v.btime.hi	= 0;
 
 		for (j = 0; j < ARRAY_SIZE(n->v.skip); j++)
 			n->v.skip[j] = cpu_to_le32(bch2_snapshot_skiplist_get(c, parent));
@@ -1681,5 +1683,5 @@ int bch2_snapshots_read(struct bch_fs *c)
 
 void bch2_fs_snapshots_exit(struct bch_fs *c)
 {
-	kfree(rcu_dereference_protected(c->snapshots, true));
+	kvfree(rcu_dereference_protected(c->snapshots, true));
 }
diff --git a/fs/bcachefs/snapshot_format.h b/fs/bcachefs/snapshot_format.h
new file mode 100644
index 000000000000..aabcd3a74cd9
--- /dev/null
+++ b/fs/bcachefs/snapshot_format.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_SNAPSHOT_FORMAT_H
+#define _BCACHEFS_SNAPSHOT_FORMAT_H
+
+struct bch_snapshot {
+	struct bch_val		v;
+	__le32			flags;
+	__le32			parent;
+	__le32			children[2];
+	__le32			subvol;
+	/* corresponds to a bch_snapshot_tree in BTREE_ID_snapshot_trees */
+	__le32			tree;
+	__le32			depth;
+	__le32			skip[3];
+	bch_le128		btime;
+};
+
+LE32_BITMASK(BCH_SNAPSHOT_DELETED,	struct bch_snapshot, flags,  0,  1)
+
+/* True if a subvolume points to this snapshot node: */
+LE32_BITMASK(BCH_SNAPSHOT_SUBVOL,	struct bch_snapshot, flags,  1,  2)
+
+/*
+ * Snapshot trees:
+ *
+ * The snapshot_trees btree gives us persistent indentifier for each tree of
+ * bch_snapshot nodes, and allow us to record and easily find the root/master
+ * subvolume that other snapshots were created from:
+ */
+struct bch_snapshot_tree {
+	struct bch_val		v;
+	__le32			master_subvol;
+	__le32			root_snapshot;
+};
+
+#endif /* _BCACHEFS_SNAPSHOT_FORMAT_H */
diff --git a/fs/bcachefs/str_hash.h b/fs/bcachefs/str_hash.h
index 89fdb7c21134..fcaa5a888744 100644
--- a/fs/bcachefs/str_hash.h
+++ b/fs/bcachefs/str_hash.h
@@ -160,21 +160,16 @@ static inline bool is_visible_key(struct bch_hash_desc desc, subvol_inum inum, s
 }
 
 static __always_inline int
-bch2_hash_lookup(struct btree_trans *trans,
+bch2_hash_lookup_in_snapshot(struct btree_trans *trans,
 		 struct btree_iter *iter,
 		 const struct bch_hash_desc desc,
 		 const struct bch_hash_info *info,
 		 subvol_inum inum, const void *key,
-		 unsigned flags)
+		 unsigned flags, u32 snapshot)
 {
 	struct bkey_s_c k;
-	u32 snapshot;
 	int ret;
 
-	ret = bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot);
-	if (ret)
-		return ret;
-
 	for_each_btree_key_upto_norestart(trans, *iter, desc.btree_id,
 			   SPOS(inum.inum, desc.hash_key(info, key), snapshot),
 			   POS(inum.inum, U64_MAX),
@@ -195,6 +190,19 @@ bch2_hash_lookup(struct btree_trans *trans,
 }
 
 static __always_inline int
+bch2_hash_lookup(struct btree_trans *trans,
+		 struct btree_iter *iter,
+		 const struct bch_hash_desc desc,
+		 const struct bch_hash_info *info,
+		 subvol_inum inum, const void *key,
+		 unsigned flags)
+{
+	u32 snapshot;
+	return  bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot) ?:
+		bch2_hash_lookup_in_snapshot(trans, iter, desc, info, inum, key, flags, snapshot);
+}
+
+static __always_inline int
 bch2_hash_hole(struct btree_trans *trans,
 	       struct btree_iter *iter,
 	       const struct bch_hash_desc desc,
diff --git a/fs/bcachefs/subvolume_format.h b/fs/bcachefs/subvolume_format.h
new file mode 100644
index 000000000000..af79134b07d6
--- /dev/null
+++ b/fs/bcachefs/subvolume_format.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_SUBVOLUME_FORMAT_H
+#define _BCACHEFS_SUBVOLUME_FORMAT_H
+
+#define SUBVOL_POS_MIN		POS(0, 1)
+#define SUBVOL_POS_MAX		POS(0, S32_MAX)
+#define BCACHEFS_ROOT_SUBVOL	1
+
+struct bch_subvolume {
+	struct bch_val		v;
+	__le32			flags;
+	__le32			snapshot;
+	__le64			inode;
+	/*
+	 * Snapshot subvolumes form a tree, separate from the snapshot nodes
+	 * tree - if this subvolume is a snapshot, this is the ID of the
+	 * subvolume it was created from:
+	 *
+	 * This is _not_ necessarily the subvolume of the directory containing
+	 * this subvolume:
+	 */
+	__le32			parent;
+	__le32			pad;
+	bch_le128		otime;
+};
+
+LE32_BITMASK(BCH_SUBVOLUME_RO,		struct bch_subvolume, flags,  0,  1)
+/*
+ * We need to know whether a subvolume is a snapshot so we can know whether we
+ * can delete it (or whether it should just be rm -rf'd)
+ */
+LE32_BITMASK(BCH_SUBVOLUME_SNAP,	struct bch_subvolume, flags,  1,  2)
+LE32_BITMASK(BCH_SUBVOLUME_UNLINKED,	struct bch_subvolume, flags,  2,  3)
+
+#endif /* _BCACHEFS_SUBVOLUME_FORMAT_H */
diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c
index 6d3db5cce5f6..bd64eb68e84a 100644
--- a/fs/bcachefs/super-io.c
+++ b/fs/bcachefs/super-io.c
@@ -2,7 +2,6 @@
 
 #include "bcachefs.h"
 #include "checksum.h"
-#include "counters.h"
 #include "disk_groups.h"
 #include "ec.h"
 #include "error.h"
@@ -13,6 +12,7 @@
 #include "replicas.h"
 #include "quota.h"
 #include "sb-clean.h"
+#include "sb-counters.h"
 #include "sb-downgrade.h"
 #include "sb-errors.h"
 #include "sb-members.h"
@@ -142,8 +142,8 @@ void bch2_sb_field_delete(struct bch_sb_handle *sb,
 void bch2_free_super(struct bch_sb_handle *sb)
 {
 	kfree(sb->bio);
-	if (!IS_ERR_OR_NULL(sb->bdev_handle))
-		bdev_release(sb->bdev_handle);
+	if (!IS_ERR_OR_NULL(sb->s_bdev_file))
+		fput(sb->s_bdev_file);
 	kfree(sb->holder);
 	kfree(sb->sb_name);
 
@@ -704,22 +704,22 @@ retry:
 	if (!opt_get(*opts, nochanges))
 		sb->mode |= BLK_OPEN_WRITE;
 
-	sb->bdev_handle = bdev_open_by_path(path, sb->mode, sb->holder, &bch2_sb_handle_bdev_ops);
-	if (IS_ERR(sb->bdev_handle) &&
-	    PTR_ERR(sb->bdev_handle) == -EACCES &&
+	sb->s_bdev_file = bdev_file_open_by_path(path, sb->mode, sb->holder, &bch2_sb_handle_bdev_ops);
+	if (IS_ERR(sb->s_bdev_file) &&
+	    PTR_ERR(sb->s_bdev_file) == -EACCES &&
 	    opt_get(*opts, read_only)) {
 		sb->mode &= ~BLK_OPEN_WRITE;
 
-		sb->bdev_handle = bdev_open_by_path(path, sb->mode, sb->holder, &bch2_sb_handle_bdev_ops);
-		if (!IS_ERR(sb->bdev_handle))
+		sb->s_bdev_file = bdev_file_open_by_path(path, sb->mode, sb->holder, &bch2_sb_handle_bdev_ops);
+		if (!IS_ERR(sb->s_bdev_file))
 			opt_set(*opts, nochanges, true);
 	}
 
-	if (IS_ERR(sb->bdev_handle)) {
-		ret = PTR_ERR(sb->bdev_handle);
-		goto out;
+	if (IS_ERR(sb->s_bdev_file)) {
+		ret = PTR_ERR(sb->s_bdev_file);
+		goto err;
 	}
-	sb->bdev = sb->bdev_handle->bdev;
+	sb->bdev = file_bdev(sb->s_bdev_file);
 
 	ret = bch2_sb_realloc(sb, 0);
 	if (ret) {
@@ -1321,7 +1321,9 @@ void bch2_sb_to_text(struct printbuf *out, struct bch_sb *sb,
 
 	prt_printf(out, "Superblock size:");
 	prt_tab(out);
-	prt_printf(out, "%zu", vstruct_bytes(sb));
+	prt_units_u64(out, vstruct_bytes(sb));
+	prt_str(out, "/");
+	prt_units_u64(out, 512ULL << sb->layout.sb_max_size_bits);
 	prt_newline(out);
 
 	prt_printf(out, "Clean:");
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index 9dbc35940197..6b23e11825e6 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -23,7 +23,6 @@
 #include "checksum.h"
 #include "clock.h"
 #include "compress.h"
-#include "counters.h"
 #include "debug.h"
 #include "disk_groups.h"
 #include "ec.h"
@@ -49,6 +48,7 @@
 #include "recovery.h"
 #include "replicas.h"
 #include "sb-clean.h"
+#include "sb-counters.h"
 #include "sb-errors.h"
 #include "sb-members.h"
 #include "snapshot.h"
@@ -883,7 +883,7 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts)
 	    !(c->pcpu = alloc_percpu(struct bch_fs_pcpu)) ||
 	    !(c->online_reserved = alloc_percpu(u64)) ||
 	    mempool_init_kvpmalloc_pool(&c->btree_bounce_pool, 1,
-					btree_bytes(c)) ||
+					c->opts.btree_node_size) ||
 	    mempool_init_kmalloc_pool(&c->large_bkey_pool, 1, 2048) ||
 	    !(c->unused_inode_hints = kcalloc(1U << c->inode_shard_bits,
 					      sizeof(u64), GFP_KERNEL))) {
@@ -1386,8 +1386,8 @@ static int bch2_dev_attach_bdev(struct bch_fs *c, struct bch_sb_handle *sb)
 	prt_bdevname(&name, ca->disk_sb.bdev);
 
 	if (c->sb.nr_devices == 1)
-		strlcpy(c->name, name.buf, sizeof(c->name));
-	strlcpy(ca->name, name.buf, sizeof(ca->name));
+		strscpy(c->name, name.buf, sizeof(c->name));
+	strscpy(ca->name, name.buf, sizeof(ca->name));
 
 	printbuf_exit(&name);
 
@@ -1428,10 +1428,10 @@ bool bch2_dev_state_allowed(struct bch_fs *c, struct bch_dev *ca,
 
 		required = max(!(flags & BCH_FORCE_IF_METADATA_DEGRADED)
 			       ? c->opts.metadata_replicas
-			       : c->opts.metadata_replicas_required,
+			       : metadata_replicas_required(c),
 			       !(flags & BCH_FORCE_IF_DATA_DEGRADED)
 			       ? c->opts.data_replicas
-			       : c->opts.data_replicas_required);
+			       : data_replicas_required(c));
 
 		return nr_rw >= required;
 	case BCH_MEMBER_STATE_failed:
@@ -1625,7 +1625,7 @@ int bch2_dev_remove(struct bch_fs *c, struct bch_dev *ca, int flags)
 	if (data) {
 		struct printbuf data_has = PRINTBUF;
 
-		prt_bitflags(&data_has, bch2_data_types, data);
+		prt_bitflags(&data_has, __bch2_data_types, data);
 		bch_err(ca, "Remove failed, still has data (%s)", data_has.buf);
 		printbuf_exit(&data_has);
 		ret = -EBUSY;
diff --git a/fs/bcachefs/super_types.h b/fs/bcachefs/super_types.h
index 0e5a14fc8e7f..ec784d975f66 100644
--- a/fs/bcachefs/super_types.h
+++ b/fs/bcachefs/super_types.h
@@ -4,7 +4,7 @@
 
 struct bch_sb_handle {
 	struct bch_sb		*sb;
-	struct bdev_handle	*bdev_handle;
+	struct file		*s_bdev_file;
 	struct block_device	*bdev;
 	char			*sb_name;
 	struct bio		*bio;
diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c
index 8ed52319ff68..cee80c47feea 100644
--- a/fs/bcachefs/sysfs.c
+++ b/fs/bcachefs/sysfs.c
@@ -21,6 +21,7 @@
 #include "btree_gc.h"
 #include "buckets.h"
 #include "clock.h"
+#include "compress.h"
 #include "disk_groups.h"
 #include "ec.h"
 #include "inode.h"
@@ -247,7 +248,7 @@ static size_t bch2_btree_cache_size(struct bch_fs *c)
 
 	mutex_lock(&c->btree_cache.lock);
 	list_for_each_entry(b, &c->btree_cache.live, list)
-		ret += btree_bytes(c);
+		ret += btree_buf_bytes(b);
 
 	mutex_unlock(&c->btree_cache.lock);
 	return ret;
@@ -330,7 +331,7 @@ static int bch2_compression_stats_to_text(struct printbuf *out, struct bch_fs *c
 	prt_newline(out);
 
 	for (unsigned i = 0; i < ARRAY_SIZE(s); i++) {
-		prt_str(out, bch2_compression_types[i]);
+		bch2_prt_compression_type(out, i);
 		prt_tab(out);
 
 		prt_human_readable_u64(out, s[i].sectors_compressed << 9);
@@ -725,8 +726,10 @@ STORE(bch2_fs_opts_dir)
 	bch2_opt_set_sb(c, opt, v);
 	bch2_opt_set_by_id(&c->opts, id, v);
 
-	if ((id == Opt_background_target ||
-	     id == Opt_background_compression) && v)
+	if (v &&
+	    (id == Opt_background_target ||
+	     id == Opt_background_compression ||
+	     (id == Opt_compression && !c->opts.background_compression)))
 		bch2_set_rebalance_needs_scan(c, 0);
 
 	ret = size;
@@ -883,7 +886,7 @@ static void dev_io_done_to_text(struct printbuf *out, struct bch_dev *ca)
 
 		for (i = 1; i < BCH_DATA_NR; i++)
 			prt_printf(out, "%-12s:%12llu\n",
-			       bch2_data_types[i],
+			       bch2_data_type_str(i),
 			       percpu_u64_get(&ca->io_done->sectors[rw][i]) << 9);
 	}
 }
@@ -908,7 +911,7 @@ SHOW(bch2_dev)
 	}
 
 	if (attr == &sysfs_has_data) {
-		prt_bitflags(out, bch2_data_types, bch2_dev_has_data(c, ca));
+		prt_bitflags(out, __bch2_data_types, bch2_dev_has_data(c, ca));
 		prt_char(out, '\n');
 	}
 
diff --git a/fs/bcachefs/thread_with_file.c b/fs/bcachefs/thread_with_file.c
index b1c867aa2b58..9220d7de10db 100644
--- a/fs/bcachefs/thread_with_file.c
+++ b/fs/bcachefs/thread_with_file.c
@@ -53,9 +53,9 @@ int bch2_run_thread_with_file(struct thread_with_file *thr,
 	if (ret)
 		goto err;
 
-	fd_install(fd, file);
 	get_task_struct(thr->task);
 	wake_up_process(thr->task);
+	fd_install(fd, file);
 	return fd;
 err:
 	if (fd >= 0)
diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h
index c94876b3bb06..293b90d704fb 100644
--- a/fs/bcachefs/trace.h
+++ b/fs/bcachefs/trace.h
@@ -46,7 +46,7 @@ DECLARE_EVENT_CLASS(fs_str,
 		__assign_str(str, str);
 	),
 
-	TP_printk("%d,%d %s", MAJOR(__entry->dev), MINOR(__entry->dev), __get_str(str))
+	TP_printk("%d,%d\n%s", MAJOR(__entry->dev), MINOR(__entry->dev), __get_str(str))
 );
 
 DECLARE_EVENT_CLASS(trans_str,
@@ -273,28 +273,14 @@ DEFINE_EVENT(bch_fs, journal_full,
 	TP_ARGS(c)
 );
 
-DEFINE_EVENT(bch_fs, journal_entry_full,
-	TP_PROTO(struct bch_fs *c),
-	TP_ARGS(c)
+DEFINE_EVENT(fs_str, journal_entry_full,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
 );
 
-TRACE_EVENT(journal_entry_close,
-	TP_PROTO(struct bch_fs *c, unsigned bytes),
-	TP_ARGS(c, bytes),
-
-	TP_STRUCT__entry(
-		__field(dev_t,		dev			)
-		__field(u32,		bytes			)
-	),
-
-	TP_fast_assign(
-		__entry->dev			= c->dev;
-		__entry->bytes			= bytes;
-	),
-
-	TP_printk("%d,%d entry bytes %u",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->bytes)
+DEFINE_EVENT(fs_str, journal_entry_close,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
 );
 
 DEFINE_EVENT(bio, journal_write,
@@ -542,7 +528,7 @@ TRACE_EVENT(btree_path_relock_fail,
 		__entry->level			= path->level;
 		TRACE_BPOS_assign(pos, path->pos);
 
-		c = bch2_btree_node_lock_counts(trans, NULL, &path->l[level].b->c, level),
+		c = bch2_btree_node_lock_counts(trans, NULL, &path->l[level].b->c, level);
 		__entry->self_read_count	= c.n[SIX_LOCK_read];
 		__entry->self_intent_count	= c.n[SIX_LOCK_intent];
 
@@ -827,40 +813,28 @@ TRACE_EVENT(bucket_evacuate,
 );
 
 DEFINE_EVENT(fs_str, move_extent,
-	TP_PROTO(struct bch_fs *c, const char *k),
-	TP_ARGS(c, k)
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
 );
 
 DEFINE_EVENT(fs_str, move_extent_read,
-	TP_PROTO(struct bch_fs *c, const char *k),
-	TP_ARGS(c, k)
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
 );
 
 DEFINE_EVENT(fs_str, move_extent_write,
-	TP_PROTO(struct bch_fs *c, const char *k),
-	TP_ARGS(c, k)
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
 );
 
 DEFINE_EVENT(fs_str, move_extent_finish,
-	TP_PROTO(struct bch_fs *c, const char *k),
-	TP_ARGS(c, k)
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
 );
 
-TRACE_EVENT(move_extent_fail,
-	TP_PROTO(struct bch_fs *c, const char *msg),
-	TP_ARGS(c, msg),
-
-	TP_STRUCT__entry(
-		__field(dev_t,		dev			)
-		__string(msg,		msg			)
-	),
-
-	TP_fast_assign(
-		__entry->dev		= c->dev;
-		__assign_str(msg, msg);
-	),
-
-	TP_printk("%d:%d %s", MAJOR(__entry->dev), MINOR(__entry->dev), __get_str(msg))
+DEFINE_EVENT(fs_str, move_extent_fail,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
 );
 
 DEFINE_EVENT(fs_str, move_extent_start_fail,
@@ -1039,7 +1013,7 @@ TRACE_EVENT(trans_restart_split_race,
 		__entry->level		= b->c.level;
 		__entry->written	= b->written;
 		__entry->blocks		= btree_blocks(trans->c);
-		__entry->u64s_remaining	= bch_btree_keys_u64s_remaining(trans->c, b);
+		__entry->u64s_remaining	= bch2_btree_keys_u64s_remaining(b);
 	),
 
 	TP_printk("%s %pS l=%u written %u/%u u64s remaining %u",
@@ -1146,8 +1120,6 @@ DEFINE_EVENT(transaction_restart_iter,	trans_restart_btree_node_split,
 	TP_ARGS(trans, caller_ip, path)
 );
 
-struct get_locks_fail;
-
 TRACE_EVENT(trans_restart_upgrade,
 	TP_PROTO(struct btree_trans *trans,
 		 unsigned long caller_ip,
@@ -1195,11 +1167,9 @@ TRACE_EVENT(trans_restart_upgrade,
 		  __entry->node_seq)
 );
 
-DEFINE_EVENT(transaction_restart_iter,	trans_restart_relock,
-	TP_PROTO(struct btree_trans *trans,
-		 unsigned long caller_ip,
-		 struct btree_path *path),
-	TP_ARGS(trans, caller_ip, path)
+DEFINE_EVENT(trans_str,	trans_restart_relock,
+	TP_PROTO(struct btree_trans *trans, unsigned long caller_ip, const char *str),
+	TP_ARGS(trans, caller_ip, str)
 );
 
 DEFINE_EVENT(transaction_restart_iter,	trans_restart_relock_next_node,
diff --git a/fs/bcachefs/util.c b/fs/bcachefs/util.c
index c2ef7cddaa4f..3a32faa86b5c 100644
--- a/fs/bcachefs/util.c
+++ b/fs/bcachefs/util.c
@@ -241,12 +241,17 @@ bool bch2_is_zero(const void *_p, size_t n)
 	return true;
 }
 
-void bch2_prt_u64_binary(struct printbuf *out, u64 v, unsigned nr_bits)
+void bch2_prt_u64_base2_nbits(struct printbuf *out, u64 v, unsigned nr_bits)
 {
 	while (nr_bits)
 		prt_char(out, '0' + ((v >> --nr_bits) & 1));
 }
 
+void bch2_prt_u64_base2(struct printbuf *out, u64 v)
+{
+	bch2_prt_u64_base2_nbits(out, v, fls64(v) ?: 1);
+}
+
 void bch2_print_string_as_lines(const char *prefix, const char *lines)
 {
 	const char *p;
@@ -267,14 +272,14 @@ void bch2_print_string_as_lines(const char *prefix, const char *lines)
 	console_unlock();
 }
 
-int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *task, unsigned skipnr)
+int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *task, unsigned skipnr,
+			gfp_t gfp)
 {
 #ifdef CONFIG_STACKTRACE
 	unsigned nr_entries = 0;
-	int ret = 0;
 
 	stack->nr = 0;
-	ret = darray_make_room(stack, 32);
+	int ret = darray_make_room_gfp(stack, 32, gfp);
 	if (ret)
 		return ret;
 
@@ -284,7 +289,7 @@ int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *task, unsigne
 	do {
 		nr_entries = stack_trace_save_tsk(task, stack->data, stack->size, skipnr + 1);
 	} while (nr_entries == stack->size &&
-		 !(ret = darray_make_room(stack, stack->size * 2)));
+		 !(ret = darray_make_room_gfp(stack, stack->size * 2, gfp)));
 
 	stack->nr = nr_entries;
 	up_read(&task->signal->exec_update_lock);
@@ -303,10 +308,10 @@ void bch2_prt_backtrace(struct printbuf *out, bch_stacktrace *stack)
 	}
 }
 
-int bch2_prt_task_backtrace(struct printbuf *out, struct task_struct *task, unsigned skipnr)
+int bch2_prt_task_backtrace(struct printbuf *out, struct task_struct *task, unsigned skipnr, gfp_t gfp)
 {
 	bch_stacktrace stack = { 0 };
-	int ret = bch2_save_backtrace(&stack, task, skipnr + 1);
+	int ret = bch2_save_backtrace(&stack, task, skipnr + 1, gfp);
 
 	bch2_prt_backtrace(out, &stack);
 	darray_exit(&stack);
@@ -413,14 +418,15 @@ static inline void bch2_time_stats_update_one(struct bch2_time_stats *stats,
 		bch2_quantiles_update(&stats->quantiles, duration);
 	}
 
-	if (time_after64(end, stats->last_event)) {
+	if (stats->last_event && time_after64(end, stats->last_event)) {
 		freq = end - stats->last_event;
 		mean_and_variance_update(&stats->freq_stats, freq);
 		mean_and_variance_weighted_update(&stats->freq_stats_weighted, freq);
 		stats->max_freq = max(stats->max_freq, freq);
 		stats->min_freq = min(stats->min_freq, freq);
-		stats->last_event = end;
 	}
+
+	stats->last_event = end;
 }
 
 static void __bch2_time_stats_clear_buffer(struct bch2_time_stats *stats,
@@ -1186,7 +1192,9 @@ int bch2_split_devs(const char *_dev_name, darray_str *ret)
 {
 	darray_init(ret);
 
-	char *dev_name = kstrdup(_dev_name, GFP_KERNEL), *s = dev_name;
+	char *dev_name, *s, *orig;
+
+	dev_name = orig = kstrdup(_dev_name, GFP_KERNEL);
 	if (!dev_name)
 		return -ENOMEM;
 
@@ -1201,10 +1209,10 @@ int bch2_split_devs(const char *_dev_name, darray_str *ret)
 		}
 	}
 
-	kfree(dev_name);
+	kfree(orig);
 	return 0;
 err:
 	bch2_darray_str_exit(ret);
-	kfree(dev_name);
+	kfree(orig);
 	return -ENOMEM;
 }
diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h
index c75fc31915d3..b414736d59a5 100644
--- a/fs/bcachefs/util.h
+++ b/fs/bcachefs/util.h
@@ -342,14 +342,15 @@ bool bch2_is_zero(const void *, size_t);
 
 u64 bch2_read_flag_list(char *, const char * const[]);
 
-void bch2_prt_u64_binary(struct printbuf *, u64, unsigned);
+void bch2_prt_u64_base2_nbits(struct printbuf *, u64, unsigned);
+void bch2_prt_u64_base2(struct printbuf *, u64);
 
 void bch2_print_string_as_lines(const char *prefix, const char *lines);
 
 typedef DARRAY(unsigned long) bch_stacktrace;
-int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *, unsigned);
+int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *, unsigned, gfp_t);
 void bch2_prt_backtrace(struct printbuf *, bch_stacktrace *);
-int bch2_prt_task_backtrace(struct printbuf *, struct task_struct *, unsigned);
+int bch2_prt_task_backtrace(struct printbuf *, struct task_struct *, unsigned, gfp_t);
 
 static inline void prt_bdevname(struct printbuf *out, struct block_device *bdev)
 {
diff --git a/fs/bcachefs/xattr.c b/fs/bcachefs/xattr.c
index 5a1858fb9879..9c0d2316031b 100644
--- a/fs/bcachefs/xattr.c
+++ b/fs/bcachefs/xattr.c
@@ -590,8 +590,9 @@ err:
 	mutex_unlock(&inode->ei_update_lock);
 
 	if (value &&
-	    (opt_id == Opt_background_compression ||
-	     opt_id == Opt_background_target))
+	    (opt_id == Opt_background_target ||
+	     opt_id == Opt_background_compression ||
+	     (opt_id == Opt_compression && !inode_opt_get(c, &inode->ei_inode, background_compression))))
 		bch2_set_rebalance_needs_scan(c, inode->ei_inode.bi_inum);
 
 	return bch2_err_class(ret);
diff --git a/fs/bcachefs/xattr_format.h b/fs/bcachefs/xattr_format.h
new file mode 100644
index 000000000000..e9f810539552
--- /dev/null
+++ b/fs/bcachefs/xattr_format.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_XATTR_FORMAT_H
+#define _BCACHEFS_XATTR_FORMAT_H
+
+#define KEY_TYPE_XATTR_INDEX_USER		0
+#define KEY_TYPE_XATTR_INDEX_POSIX_ACL_ACCESS	1
+#define KEY_TYPE_XATTR_INDEX_POSIX_ACL_DEFAULT	2
+#define KEY_TYPE_XATTR_INDEX_TRUSTED		3
+#define KEY_TYPE_XATTR_INDEX_SECURITY	        4
+
+struct bch_xattr {
+	struct bch_val		v;
+	__u8			x_type;
+	__u8			x_name_len;
+	__le16			x_val_len;
+	__u8			x_name[];
+} __packed __aligned(8);
+
+#endif /* _BCACHEFS_XATTR_FORMAT_H */
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index a9be9ac99222..378d9103a207 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1455,6 +1455,7 @@ out:
  */
 void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 {
+	LIST_HEAD(retry_list);
 	struct btrfs_block_group *block_group;
 	struct btrfs_space_info *space_info;
 	struct btrfs_trans_handle *trans;
@@ -1476,6 +1477,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 
 	spin_lock(&fs_info->unused_bgs_lock);
 	while (!list_empty(&fs_info->unused_bgs)) {
+		u64 used;
 		int trimming;
 
 		block_group = list_first_entry(&fs_info->unused_bgs,
@@ -1511,9 +1513,9 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 			goto next;
 		}
 
+		spin_lock(&space_info->lock);
 		spin_lock(&block_group->lock);
-		if (block_group->reserved || block_group->pinned ||
-		    block_group->used || block_group->ro ||
+		if (btrfs_is_block_group_used(block_group) || block_group->ro ||
 		    list_is_singular(&block_group->list)) {
 			/*
 			 * We want to bail if we made new allocations or have
@@ -1523,10 +1525,49 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 			 */
 			trace_btrfs_skip_unused_block_group(block_group);
 			spin_unlock(&block_group->lock);
+			spin_unlock(&space_info->lock);
 			up_write(&space_info->groups_sem);
 			goto next;
 		}
+
+		/*
+		 * The block group may be unused but there may be space reserved
+		 * accounting with the existence of that block group, that is,
+		 * space_info->bytes_may_use was incremented by a task but no
+		 * space was yet allocated from the block group by the task.
+		 * That space may or may not be allocated, as we are generally
+		 * pessimistic about space reservation for metadata as well as
+		 * for data when using compression (as we reserve space based on
+		 * the worst case, when data can't be compressed, and before
+		 * actually attempting compression, before starting writeback).
+		 *
+		 * So check if the total space of the space_info minus the size
+		 * of this block group is less than the used space of the
+		 * space_info - if that's the case, then it means we have tasks
+		 * that might be relying on the block group in order to allocate
+		 * extents, and add back the block group to the unused list when
+		 * we finish, so that we retry later in case no tasks ended up
+		 * needing to allocate extents from the block group.
+		 */
+		used = btrfs_space_info_used(space_info, true);
+		if (space_info->total_bytes - block_group->length < used) {
+			/*
+			 * Add a reference for the list, compensate for the ref
+			 * drop under the "next" label for the
+			 * fs_info->unused_bgs list.
+			 */
+			btrfs_get_block_group(block_group);
+			list_add_tail(&block_group->bg_list, &retry_list);
+
+			trace_btrfs_skip_unused_block_group(block_group);
+			spin_unlock(&block_group->lock);
+			spin_unlock(&space_info->lock);
+			up_write(&space_info->groups_sem);
+			goto next;
+		}
+
 		spin_unlock(&block_group->lock);
+		spin_unlock(&space_info->lock);
 
 		/* We don't want to force the issue, only flip if it's ok. */
 		ret = inc_block_group_ro(block_group, 0);
@@ -1650,12 +1691,16 @@ next:
 		btrfs_put_block_group(block_group);
 		spin_lock(&fs_info->unused_bgs_lock);
 	}
+	list_splice_tail(&retry_list, &fs_info->unused_bgs);
 	spin_unlock(&fs_info->unused_bgs_lock);
 	mutex_unlock(&fs_info->reclaim_bgs_lock);
 	return;
 
 flip_async:
 	btrfs_end_transaction(trans);
+	spin_lock(&fs_info->unused_bgs_lock);
+	list_splice_tail(&retry_list, &fs_info->unused_bgs);
+	spin_unlock(&fs_info->unused_bgs_lock);
 	mutex_unlock(&fs_info->reclaim_bgs_lock);
 	btrfs_put_block_group(block_group);
 	btrfs_discard_punt_unused_bgs_list(fs_info);
@@ -2684,6 +2729,37 @@ next:
 		btrfs_dec_delayed_refs_rsv_bg_inserts(fs_info);
 		list_del_init(&block_group->bg_list);
 		clear_bit(BLOCK_GROUP_FLAG_NEW, &block_group->runtime_flags);
+
+		/*
+		 * If the block group is still unused, add it to the list of
+		 * unused block groups. The block group may have been created in
+		 * order to satisfy a space reservation, in which case the
+		 * extent allocation only happens later. But often we don't
+		 * actually need to allocate space that we previously reserved,
+		 * so the block group may become unused for a long time. For
+		 * example for metadata we generally reserve space for a worst
+		 * possible scenario, but then don't end up allocating all that
+		 * space or none at all (due to no need to COW, extent buffers
+		 * were already COWed in the current transaction and still
+		 * unwritten, tree heights lower than the maximum possible
+		 * height, etc). For data we generally reserve the axact amount
+		 * of space we are going to allocate later, the exception is
+		 * when using compression, as we must reserve space based on the
+		 * uncompressed data size, because the compression is only done
+		 * when writeback triggered and we don't know how much space we
+		 * are actually going to need, so we reserve the uncompressed
+		 * size because the data may be uncompressible in the worst case.
+		 */
+		if (ret == 0) {
+			bool used;
+
+			spin_lock(&block_group->lock);
+			used = btrfs_is_block_group_used(block_group);
+			spin_unlock(&block_group->lock);
+
+			if (!used)
+				btrfs_mark_bg_unused(block_group);
+		}
 	}
 	btrfs_trans_release_chunk_metadata(trans);
 }
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index c4a1f01cc1c2..962b11983901 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -257,6 +257,13 @@ static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group)
 	return (block_group->start + block_group->length);
 }
 
+static inline bool btrfs_is_block_group_used(const struct btrfs_block_group *bg)
+{
+	lockdep_assert_held(&bg->lock);
+
+	return (bg->used > 0 || bg->reserved > 0 || bg->pinned > 0);
+}
+
 static inline bool btrfs_is_block_group_data_only(
 					struct btrfs_block_group *block_group)
 {
diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c
index ceb5f586a2d5..1043a8142351 100644
--- a/fs/btrfs/block-rsv.c
+++ b/fs/btrfs/block-rsv.c
@@ -494,7 +494,7 @@ struct btrfs_block_rsv *btrfs_use_block_rsv(struct btrfs_trans_handle *trans,
 
 	block_rsv = get_block_rsv(trans, root);
 
-	if (unlikely(block_rsv->size == 0))
+	if (unlikely(btrfs_block_rsv_size(block_rsv) == 0))
 		goto try_reserve;
 again:
 	ret = btrfs_block_rsv_use_bytes(block_rsv, blocksize);
diff --git a/fs/btrfs/block-rsv.h b/fs/btrfs/block-rsv.h
index b0bd12b8652f..43a9a6b5a79f 100644
--- a/fs/btrfs/block-rsv.h
+++ b/fs/btrfs/block-rsv.h
@@ -101,4 +101,36 @@ static inline bool btrfs_block_rsv_full(const struct btrfs_block_rsv *rsv)
 	return data_race(rsv->full);
 }
 
+/*
+ * Get the reserved mount of a block reserve in a context where getting a stale
+ * value is acceptable, instead of accessing it directly and trigger data race
+ * warning from KCSAN.
+ */
+static inline u64 btrfs_block_rsv_reserved(struct btrfs_block_rsv *rsv)
+{
+	u64 ret;
+
+	spin_lock(&rsv->lock);
+	ret = rsv->reserved;
+	spin_unlock(&rsv->lock);
+
+	return ret;
+}
+
+/*
+ * Get the size of a block reserve in a context where getting a stale value is
+ * acceptable, instead of accessing it directly and trigger data race warning
+ * from KCSAN.
+ */
+static inline u64 btrfs_block_rsv_size(struct btrfs_block_rsv *rsv)
+{
+	u64 ret;
+
+	spin_lock(&rsv->lock);
+	ret = rsv->size;
+	spin_unlock(&rsv->lock);
+
+	return ret;
+}
+
 #endif /* BTRFS_BLOCK_RSV_H */
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 193168214eeb..68345f73d429 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -141,16 +141,16 @@ static int compression_decompress_bio(struct list_head *ws,
 }
 
 static int compression_decompress(int type, struct list_head *ws,
-               const u8 *data_in, struct page *dest_page,
-               unsigned long start_byte, size_t srclen, size_t destlen)
+		const u8 *data_in, struct page *dest_page,
+		unsigned long dest_pgoff, size_t srclen, size_t destlen)
 {
 	switch (type) {
 	case BTRFS_COMPRESS_ZLIB: return zlib_decompress(ws, data_in, dest_page,
-						start_byte, srclen, destlen);
+						dest_pgoff, srclen, destlen);
 	case BTRFS_COMPRESS_LZO:  return lzo_decompress(ws, data_in, dest_page,
-						start_byte, srclen, destlen);
+						dest_pgoff, srclen, destlen);
 	case BTRFS_COMPRESS_ZSTD: return zstd_decompress(ws, data_in, dest_page,
-						start_byte, srclen, destlen);
+						dest_pgoff, srclen, destlen);
 	case BTRFS_COMPRESS_NONE:
 	default:
 		/*
@@ -1037,14 +1037,23 @@ static int btrfs_decompress_bio(struct compressed_bio *cb)
  * start_byte tells us the offset into the compressed data we're interested in
  */
 int btrfs_decompress(int type, const u8 *data_in, struct page *dest_page,
-		     unsigned long start_byte, size_t srclen, size_t destlen)
+		     unsigned long dest_pgoff, size_t srclen, size_t destlen)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb);
 	struct list_head *workspace;
+	const u32 sectorsize = fs_info->sectorsize;
 	int ret;
 
+	/*
+	 * The full destination page range should not exceed the page size.
+	 * And the @destlen should not exceed sectorsize, as this is only called for
+	 * inline file extents, which should not exceed sectorsize.
+	 */
+	ASSERT(dest_pgoff + destlen <= PAGE_SIZE && destlen <= sectorsize);
+
 	workspace = get_workspace(type, 0);
 	ret = compression_decompress(type, workspace, data_in, dest_page,
-				     start_byte, srclen, destlen);
+				     dest_pgoff, srclen, destlen);
 	put_workspace(type, workspace);
 
 	return ret;
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 93cc92974dee..afd7e50d073d 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -148,7 +148,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
 		unsigned long *total_in, unsigned long *total_out);
 int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
 int zlib_decompress(struct list_head *ws, const u8 *data_in,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen);
 struct list_head *zlib_alloc_workspace(unsigned int level);
 void zlib_free_workspace(struct list_head *ws);
@@ -159,7 +159,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
 		unsigned long *total_in, unsigned long *total_out);
 int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
 int lzo_decompress(struct list_head *ws, const u8 *data_in,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen);
 struct list_head *lzo_alloc_workspace(unsigned int level);
 void lzo_free_workspace(struct list_head *ws);
diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c
index c276b136ab63..5b0b64571418 100644
--- a/fs/btrfs/defrag.c
+++ b/fs/btrfs/defrag.c
@@ -1046,7 +1046,7 @@ static int defrag_collect_targets(struct btrfs_inode *inode,
 			goto add;
 
 		/* Skip too large extent */
-		if (range_len >= extent_thresh)
+		if (em->len >= extent_thresh)
 			goto next;
 
 		/*
diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c
index 2833e8ef4c09..acf9f4b6c044 100644
--- a/fs/btrfs/delalloc-space.c
+++ b/fs/btrfs/delalloc-space.c
@@ -245,7 +245,6 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 	struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
 	u64 reserve_size = 0;
 	u64 qgroup_rsv_size = 0;
-	u64 csum_leaves;
 	unsigned outstanding_extents;
 
 	lockdep_assert_held(&inode->lock);
@@ -260,10 +259,12 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 						outstanding_extents);
 		reserve_size += btrfs_calc_metadata_size(fs_info, 1);
 	}
-	csum_leaves = btrfs_csum_bytes_to_leaves(fs_info,
-						 inode->csum_bytes);
-	reserve_size += btrfs_calc_insert_metadata_size(fs_info,
-							csum_leaves);
+	if (!(inode->flags & BTRFS_INODE_NODATASUM)) {
+		u64 csum_leaves;
+
+		csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, inode->csum_bytes);
+		reserve_size += btrfs_calc_insert_metadata_size(fs_info, csum_leaves);
+	}
 	/*
 	 * For qgroup rsv, the calculation is very simple:
 	 * account one nodesize for each outstanding extent
@@ -278,14 +279,20 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 	spin_unlock(&block_rsv->lock);
 }
 
-static void calc_inode_reservations(struct btrfs_fs_info *fs_info,
+static void calc_inode_reservations(struct btrfs_inode *inode,
 				    u64 num_bytes, u64 disk_num_bytes,
 				    u64 *meta_reserve, u64 *qgroup_reserve)
 {
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	u64 nr_extents = count_max_extents(fs_info, num_bytes);
-	u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes);
+	u64 csum_leaves;
 	u64 inode_update = btrfs_calc_metadata_size(fs_info, 1);
 
+	if (inode->flags & BTRFS_INODE_NODATASUM)
+		csum_leaves = 0;
+	else
+		csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes);
+
 	*meta_reserve = btrfs_calc_insert_metadata_size(fs_info,
 						nr_extents + csum_leaves);
 
@@ -337,7 +344,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
 	 * everything out and try again, which is bad.  This way we just
 	 * over-reserve slightly, and clean up the mess when we are done.
 	 */
-	calc_inode_reservations(fs_info, num_bytes, disk_num_bytes,
+	calc_inode_reservations(inode, num_bytes, disk_num_bytes,
 				&meta_reserve, &qgroup_reserve);
 	ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true,
 						 noflush);
@@ -359,7 +366,8 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
 	nr_extents = count_max_extents(fs_info, num_bytes);
 	spin_lock(&inode->lock);
 	btrfs_mod_outstanding_extents(inode, nr_extents);
-	inode->csum_bytes += disk_num_bytes;
+	if (!(inode->flags & BTRFS_INODE_NODATASUM))
+		inode->csum_bytes += disk_num_bytes;
 	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
 	spin_unlock(&inode->lock);
 
@@ -393,7 +401,8 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
 
 	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
 	spin_lock(&inode->lock);
-	inode->csum_bytes -= num_bytes;
+	if (!(inode->flags & BTRFS_INODE_NODATASUM))
+		inode->csum_bytes -= num_bytes;
 	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
 	spin_unlock(&inode->lock);
 
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 1502d664c892..fb33027e5a4c 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -246,7 +246,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	struct btrfs_device *device;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct block_device *bdev;
 	u64 devid = BTRFS_DEV_REPLACE_DEVID;
 	int ret = 0;
@@ -257,13 +257,13 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 		return -EINVAL;
 	}
 
-	bdev_handle = bdev_open_by_path(device_path, BLK_OPEN_WRITE,
+	bdev_file = bdev_file_open_by_path(device_path, BLK_OPEN_WRITE,
 					fs_info->bdev_holder, NULL);
-	if (IS_ERR(bdev_handle)) {
+	if (IS_ERR(bdev_file)) {
 		btrfs_err(fs_info, "target device %s is invalid!", device_path);
-		return PTR_ERR(bdev_handle);
+		return PTR_ERR(bdev_file);
 	}
-	bdev = bdev_handle->bdev;
+	bdev = file_bdev(bdev_file);
 
 	if (!btrfs_check_device_zone_type(fs_info, bdev)) {
 		btrfs_err(fs_info,
@@ -314,7 +314,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	device->commit_bytes_used = device->bytes_used;
 	device->fs_info = fs_info;
 	device->bdev = bdev;
-	device->bdev_handle = bdev_handle;
+	device->bdev_file = bdev_file;
 	set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
 	set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state);
 	device->dev_stats_valid = 1;
@@ -335,7 +335,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	return 0;
 
 error:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 	return ret;
 }
 
@@ -725,6 +725,23 @@ leave:
 	return ret;
 }
 
+static int btrfs_check_replace_dev_names(struct btrfs_ioctl_dev_replace_args *args)
+{
+	if (args->start.srcdevid == 0) {
+		if (memchr(args->start.srcdev_name, 0,
+			   sizeof(args->start.srcdev_name)) == NULL)
+			return -ENAMETOOLONG;
+	} else {
+		args->start.srcdev_name[0] = 0;
+	}
+
+	if (memchr(args->start.tgtdev_name, 0,
+		   sizeof(args->start.tgtdev_name)) == NULL)
+	    return -ENAMETOOLONG;
+
+	return 0;
+}
+
 int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info,
 			    struct btrfs_ioctl_dev_replace_args *args)
 {
@@ -737,10 +754,9 @@ int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info,
 	default:
 		return -EINVAL;
 	}
-
-	if ((args->start.srcdevid == 0 && args->start.srcdev_name[0] == '\0') ||
-	    args->start.tgtdev_name[0] == '\0')
-		return -EINVAL;
+	ret = btrfs_check_replace_dev_names(args);
+	if (ret < 0)
+		return ret;
 
 	ret = btrfs_dev_replace_start(fs_info, args->start.tgtdev_name,
 					args->start.srcdevid,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index c6907d533fe8..c843563914ca 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1307,12 +1307,12 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info)
  *
  * @objectid:	root id
  * @anon_dev:	preallocated anonymous block device number for new roots,
- * 		pass 0 for new allocation.
+ *		pass NULL for a new allocation.
  * @check_ref:	whether to check root item references, If true, return -ENOENT
  *		for orphan roots
  */
 static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info,
-					     u64 objectid, dev_t anon_dev,
+					     u64 objectid, dev_t *anon_dev,
 					     bool check_ref)
 {
 	struct btrfs_root *root;
@@ -1336,8 +1336,17 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info,
 again:
 	root = btrfs_lookup_fs_root(fs_info, objectid);
 	if (root) {
-		/* Shouldn't get preallocated anon_dev for cached roots */
-		ASSERT(!anon_dev);
+		/*
+		 * Some other caller may have read out the newly inserted
+		 * subvolume already (for things like backref walk etc).  Not
+		 * that common but still possible.  In that case, we just need
+		 * to free the anon_dev.
+		 */
+		if (unlikely(anon_dev && *anon_dev)) {
+			free_anon_bdev(*anon_dev);
+			*anon_dev = 0;
+		}
+
 		if (check_ref && btrfs_root_refs(&root->root_item) == 0) {
 			btrfs_put_root(root);
 			return ERR_PTR(-ENOENT);
@@ -1357,7 +1366,7 @@ again:
 		goto fail;
 	}
 
-	ret = btrfs_init_fs_root(root, anon_dev);
+	ret = btrfs_init_fs_root(root, anon_dev ? *anon_dev : 0);
 	if (ret)
 		goto fail;
 
@@ -1393,7 +1402,7 @@ fail:
 	 * root's anon_dev to 0 to avoid a double free, once by btrfs_put_root()
 	 * and once again by our caller.
 	 */
-	if (anon_dev)
+	if (anon_dev && *anon_dev)
 		root->anon_dev = 0;
 	btrfs_put_root(root);
 	return ERR_PTR(ret);
@@ -1409,7 +1418,7 @@ fail:
 struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
 				     u64 objectid, bool check_ref)
 {
-	return btrfs_get_root_ref(fs_info, objectid, 0, check_ref);
+	return btrfs_get_root_ref(fs_info, objectid, NULL, check_ref);
 }
 
 /*
@@ -1417,11 +1426,11 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
  * the anonymous block device id
  *
  * @objectid:	tree objectid
- * @anon_dev:	if zero, allocate a new anonymous block device or use the
- *		parameter value
+ * @anon_dev:	if NULL, allocate a new anonymous block device or use the
+ *		parameter value if not NULL
  */
 struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
-					 u64 objectid, dev_t anon_dev)
+					 u64 objectid, dev_t *anon_dev)
 {
 	return btrfs_get_root_ref(fs_info, objectid, anon_dev, true);
 }
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 9413726b329b..eb3473d1c1ac 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -61,7 +61,7 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info);
 struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
 				     u64 objectid, bool check_ref);
 struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
-					 u64 objectid, dev_t anon_dev);
+					 u64 objectid, dev_t *anon_dev);
 struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info,
 						 struct btrfs_path *path,
 						 u64 objectid);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index f396aba92c57..8e8cc1111277 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1260,7 +1260,8 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len,
 	u64 bytes_left, end;
 	u64 aligned_start = ALIGN(start, 1 << SECTOR_SHIFT);
 
-	if (WARN_ON(start != aligned_start)) {
+	/* Adjust the range to be aligned to 512B sectors if necessary. */
+	if (start != aligned_start) {
 		len -= aligned_start - start;
 		len = round_down(len, 1 << SECTOR_SHIFT);
 		start = aligned_start;
@@ -4298,6 +4299,42 @@ static int prepare_allocation_clustered(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
+static int prepare_allocation_zoned(struct btrfs_fs_info *fs_info,
+				    struct find_free_extent_ctl *ffe_ctl)
+{
+	if (ffe_ctl->for_treelog) {
+		spin_lock(&fs_info->treelog_bg_lock);
+		if (fs_info->treelog_bg)
+			ffe_ctl->hint_byte = fs_info->treelog_bg;
+		spin_unlock(&fs_info->treelog_bg_lock);
+	} else if (ffe_ctl->for_data_reloc) {
+		spin_lock(&fs_info->relocation_bg_lock);
+		if (fs_info->data_reloc_bg)
+			ffe_ctl->hint_byte = fs_info->data_reloc_bg;
+		spin_unlock(&fs_info->relocation_bg_lock);
+	} else if (ffe_ctl->flags & BTRFS_BLOCK_GROUP_DATA) {
+		struct btrfs_block_group *block_group;
+
+		spin_lock(&fs_info->zone_active_bgs_lock);
+		list_for_each_entry(block_group, &fs_info->zone_active_bgs, active_bg_list) {
+			/*
+			 * No lock is OK here because avail is monotinically
+			 * decreasing, and this is just a hint.
+			 */
+			u64 avail = block_group->zone_capacity - block_group->alloc_offset;
+
+			if (block_group_bits(block_group, ffe_ctl->flags) &&
+			    avail >= ffe_ctl->num_bytes) {
+				ffe_ctl->hint_byte = block_group->start;
+				break;
+			}
+		}
+		spin_unlock(&fs_info->zone_active_bgs_lock);
+	}
+
+	return 0;
+}
+
 static int prepare_allocation(struct btrfs_fs_info *fs_info,
 			      struct find_free_extent_ctl *ffe_ctl,
 			      struct btrfs_space_info *space_info,
@@ -4308,19 +4345,7 @@ static int prepare_allocation(struct btrfs_fs_info *fs_info,
 		return prepare_allocation_clustered(fs_info, ffe_ctl,
 						    space_info, ins);
 	case BTRFS_EXTENT_ALLOC_ZONED:
-		if (ffe_ctl->for_treelog) {
-			spin_lock(&fs_info->treelog_bg_lock);
-			if (fs_info->treelog_bg)
-				ffe_ctl->hint_byte = fs_info->treelog_bg;
-			spin_unlock(&fs_info->treelog_bg_lock);
-		}
-		if (ffe_ctl->for_data_reloc) {
-			spin_lock(&fs_info->relocation_bg_lock);
-			if (fs_info->data_reloc_bg)
-				ffe_ctl->hint_byte = fs_info->data_reloc_bg;
-			spin_unlock(&fs_info->relocation_bg_lock);
-		}
-		return 0;
+		return prepare_allocation_zoned(fs_info, ffe_ctl);
 	default:
 		BUG();
 	}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index cfd2967f04a2..8b4bef05e222 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2480,6 +2480,7 @@ static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo,
 				struct fiemap_cache *cache,
 				u64 offset, u64 phys, u64 len, u32 flags)
 {
+	u64 cache_end;
 	int ret = 0;
 
 	/* Set at the end of extent_fiemap(). */
@@ -2489,15 +2490,102 @@ static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo,
 		goto assign;
 
 	/*
-	 * Sanity check, extent_fiemap() should have ensured that new
-	 * fiemap extent won't overlap with cached one.
-	 * Not recoverable.
+	 * When iterating the extents of the inode, at extent_fiemap(), we may
+	 * find an extent that starts at an offset behind the end offset of the
+	 * previous extent we processed. This happens if fiemap is called
+	 * without FIEMAP_FLAG_SYNC and there are ordered extents completing
+	 * while we call btrfs_next_leaf() (through fiemap_next_leaf_item()).
 	 *
-	 * NOTE: Physical address can overlap, due to compression
+	 * For example we are in leaf X processing its last item, which is the
+	 * file extent item for file range [512K, 1M[, and after
+	 * btrfs_next_leaf() releases the path, there's an ordered extent that
+	 * completes for the file range [768K, 2M[, and that results in trimming
+	 * the file extent item so that it now corresponds to the file range
+	 * [512K, 768K[ and a new file extent item is inserted for the file
+	 * range [768K, 2M[, which may end up as the last item of leaf X or as
+	 * the first item of the next leaf - in either case btrfs_next_leaf()
+	 * will leave us with a path pointing to the new extent item, for the
+	 * file range [768K, 2M[, since that's the first key that follows the
+	 * last one we processed. So in order not to report overlapping extents
+	 * to user space, we trim the length of the previously cached extent and
+	 * emit it.
+	 *
+	 * Upon calling btrfs_next_leaf() we may also find an extent with an
+	 * offset smaller than or equals to cache->offset, and this happens
+	 * when we had a hole or prealloc extent with several delalloc ranges in
+	 * it, but after btrfs_next_leaf() released the path, delalloc was
+	 * flushed and the resulting ordered extents were completed, so we can
+	 * now have found a file extent item for an offset that is smaller than
+	 * or equals to what we have in cache->offset. We deal with this as
+	 * described below.
 	 */
-	if (cache->offset + cache->len > offset) {
-		WARN_ON(1);
-		return -EINVAL;
+	cache_end = cache->offset + cache->len;
+	if (cache_end > offset) {
+		if (offset == cache->offset) {
+			/*
+			 * We cached a dealloc range (found in the io tree) for
+			 * a hole or prealloc extent and we have now found a
+			 * file extent item for the same offset. What we have
+			 * now is more recent and up to date, so discard what
+			 * we had in the cache and use what we have just found.
+			 */
+			goto assign;
+		} else if (offset > cache->offset) {
+			/*
+			 * The extent range we previously found ends after the
+			 * offset of the file extent item we found and that
+			 * offset falls somewhere in the middle of that previous
+			 * extent range. So adjust the range we previously found
+			 * to end at the offset of the file extent item we have
+			 * just found, since this extent is more up to date.
+			 * Emit that adjusted range and cache the file extent
+			 * item we have just found. This corresponds to the case
+			 * where a previously found file extent item was split
+			 * due to an ordered extent completing.
+			 */
+			cache->len = offset - cache->offset;
+			goto emit;
+		} else {
+			const u64 range_end = offset + len;
+
+			/*
+			 * The offset of the file extent item we have just found
+			 * is behind the cached offset. This means we were
+			 * processing a hole or prealloc extent for which we
+			 * have found delalloc ranges (in the io tree), so what
+			 * we have in the cache is the last delalloc range we
+			 * found while the file extent item we found can be
+			 * either for a whole delalloc range we previously
+			 * emmitted or only a part of that range.
+			 *
+			 * We have two cases here:
+			 *
+			 * 1) The file extent item's range ends at or behind the
+			 *    cached extent's end. In this case just ignore the
+			 *    current file extent item because we don't want to
+			 *    overlap with previous ranges that may have been
+			 *    emmitted already;
+			 *
+			 * 2) The file extent item starts behind the currently
+			 *    cached extent but its end offset goes beyond the
+			 *    end offset of the cached extent. We don't want to
+			 *    overlap with a previous range that may have been
+			 *    emmitted already, so we emit the currently cached
+			 *    extent and then partially store the current file
+			 *    extent item's range in the cache, for the subrange
+			 *    going the cached extent's end to the end of the
+			 *    file extent item.
+			 */
+			if (range_end <= cache_end)
+				return 0;
+
+			if (!(flags & (FIEMAP_EXTENT_ENCODED | FIEMAP_EXTENT_DELALLOC)))
+				phys += cache_end - offset;
+
+			offset = cache_end;
+			len = range_end - cache_end;
+			goto emit;
+		}
 	}
 
 	/*
@@ -2517,6 +2605,7 @@ static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo,
 		return 0;
 	}
 
+emit:
 	/* Not mergeable, need to submit cached one */
 	ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys,
 				      cache->len, cache->flags);
@@ -2689,16 +2778,34 @@ static int fiemap_process_hole(struct btrfs_inode *inode,
 	 * it beyond i_size.
 	 */
 	while (cur_offset < end && cur_offset < i_size) {
+		struct extent_state *cached_state = NULL;
 		u64 delalloc_start;
 		u64 delalloc_end;
 		u64 prealloc_start;
+		u64 lockstart;
+		u64 lockend;
 		u64 prealloc_len = 0;
 		bool delalloc;
 
+		lockstart = round_down(cur_offset, inode->root->fs_info->sectorsize);
+		lockend = round_up(end, inode->root->fs_info->sectorsize);
+
+		/*
+		 * We are only locking for the delalloc range because that's the
+		 * only thing that can change here.  With fiemap we have a lock
+		 * on the inode, so no buffered or direct writes can happen.
+		 *
+		 * However mmaps and normal page writeback will cause this to
+		 * change arbitrarily.  We have to lock the extent lock here to
+		 * make sure that nobody messes with the tree while we're doing
+		 * btrfs_find_delalloc_in_range.
+		 */
+		lock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
 		delalloc = btrfs_find_delalloc_in_range(inode, cur_offset, end,
 							delalloc_cached_state,
 							&delalloc_start,
 							&delalloc_end);
+		unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
 		if (!delalloc)
 			break;
 
@@ -2866,15 +2973,15 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 		  u64 start, u64 len)
 {
 	const u64 ino = btrfs_ino(inode);
-	struct extent_state *cached_state = NULL;
 	struct extent_state *delalloc_cached_state = NULL;
 	struct btrfs_path *path;
 	struct fiemap_cache cache = { 0 };
 	struct btrfs_backref_share_check_ctx *backref_ctx;
 	u64 last_extent_end;
 	u64 prev_extent_end;
-	u64 lockstart;
-	u64 lockend;
+	u64 range_start;
+	u64 range_end;
+	const u64 sectorsize = inode->root->fs_info->sectorsize;
 	bool stopped = false;
 	int ret;
 
@@ -2885,22 +2992,19 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 		goto out;
 	}
 
-	lockstart = round_down(start, inode->root->fs_info->sectorsize);
-	lockend = round_up(start + len, inode->root->fs_info->sectorsize);
-	prev_extent_end = lockstart;
-
-	btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED);
-	lock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
+	range_start = round_down(start, sectorsize);
+	range_end = round_up(start + len, sectorsize);
+	prev_extent_end = range_start;
 
 	ret = fiemap_find_last_extent_offset(inode, path, &last_extent_end);
 	if (ret < 0)
-		goto out_unlock;
+		goto out;
 	btrfs_release_path(path);
 
 	path->reada = READA_FORWARD;
-	ret = fiemap_search_slot(inode, path, lockstart);
+	ret = fiemap_search_slot(inode, path, range_start);
 	if (ret < 0) {
-		goto out_unlock;
+		goto out;
 	} else if (ret > 0) {
 		/*
 		 * No file extent item found, but we may have delalloc between
@@ -2910,7 +3014,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 		goto check_eof_delalloc;
 	}
 
-	while (prev_extent_end < lockend) {
+	while (prev_extent_end < range_end) {
 		struct extent_buffer *leaf = path->nodes[0];
 		struct btrfs_file_extent_item *ei;
 		struct btrfs_key key;
@@ -2933,21 +3037,21 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 		 * The first iteration can leave us at an extent item that ends
 		 * before our range's start. Move to the next item.
 		 */
-		if (extent_end <= lockstart)
+		if (extent_end <= range_start)
 			goto next_item;
 
 		backref_ctx->curr_leaf_bytenr = leaf->start;
 
 		/* We have in implicit hole (NO_HOLES feature enabled). */
 		if (prev_extent_end < key.offset) {
-			const u64 range_end = min(key.offset, lockend) - 1;
+			const u64 hole_end = min(key.offset, range_end) - 1;
 
 			ret = fiemap_process_hole(inode, fieinfo, &cache,
 						  &delalloc_cached_state,
 						  backref_ctx, 0, 0, 0,
-						  prev_extent_end, range_end);
+						  prev_extent_end, hole_end);
 			if (ret < 0) {
-				goto out_unlock;
+				goto out;
 			} else if (ret > 0) {
 				/* fiemap_fill_next_extent() told us to stop. */
 				stopped = true;
@@ -2955,7 +3059,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 			}
 
 			/* We've reached the end of the fiemap range, stop. */
-			if (key.offset >= lockend) {
+			if (key.offset >= range_end) {
 				stopped = true;
 				break;
 			}
@@ -3003,7 +3107,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 								  extent_gen,
 								  backref_ctx);
 				if (ret < 0)
-					goto out_unlock;
+					goto out;
 				else if (ret > 0)
 					flags |= FIEMAP_EXTENT_SHARED;
 			}
@@ -3014,7 +3118,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 		}
 
 		if (ret < 0) {
-			goto out_unlock;
+			goto out;
 		} else if (ret > 0) {
 			/* fiemap_fill_next_extent() told us to stop. */
 			stopped = true;
@@ -3025,12 +3129,12 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 next_item:
 		if (fatal_signal_pending(current)) {
 			ret = -EINTR;
-			goto out_unlock;
+			goto out;
 		}
 
 		ret = fiemap_next_leaf_item(inode, path);
 		if (ret < 0) {
-			goto out_unlock;
+			goto out;
 		} else if (ret > 0) {
 			/* No more file extent items for this inode. */
 			break;
@@ -3049,29 +3153,41 @@ check_eof_delalloc:
 	btrfs_free_path(path);
 	path = NULL;
 
-	if (!stopped && prev_extent_end < lockend) {
+	if (!stopped && prev_extent_end < range_end) {
 		ret = fiemap_process_hole(inode, fieinfo, &cache,
 					  &delalloc_cached_state, backref_ctx,
-					  0, 0, 0, prev_extent_end, lockend - 1);
+					  0, 0, 0, prev_extent_end, range_end - 1);
 		if (ret < 0)
-			goto out_unlock;
-		prev_extent_end = lockend;
+			goto out;
+		prev_extent_end = range_end;
 	}
 
 	if (cache.cached && cache.offset + cache.len >= last_extent_end) {
 		const u64 i_size = i_size_read(&inode->vfs_inode);
 
 		if (prev_extent_end < i_size) {
+			struct extent_state *cached_state = NULL;
 			u64 delalloc_start;
 			u64 delalloc_end;
+			u64 lockstart;
+			u64 lockend;
 			bool delalloc;
 
+			lockstart = round_down(prev_extent_end, sectorsize);
+			lockend = round_up(i_size, sectorsize);
+
+			/*
+			 * See the comment in fiemap_process_hole as to why
+			 * we're doing the locking here.
+			 */
+			lock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
 			delalloc = btrfs_find_delalloc_in_range(inode,
 								prev_extent_end,
 								i_size - 1,
 								&delalloc_cached_state,
 								&delalloc_start,
 								&delalloc_end);
+			unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
 			if (!delalloc)
 				cache.flags |= FIEMAP_EXTENT_LAST;
 		} else {
@@ -3080,10 +3196,6 @@ check_eof_delalloc:
 	}
 
 	ret = emit_last_fiemap_cache(fieinfo, &cache);
-
-out_unlock:
-	unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
-	btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
 out:
 	free_extent_state(delalloc_cached_state);
 	btrfs_free_backref_share_ctx(backref_ctx);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 809b11472a80..4795738d5785 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3184,8 +3184,23 @@ out:
 			unwritten_start += logical_len;
 		clear_extent_uptodate(io_tree, unwritten_start, end, NULL);
 
-		/* Drop extent maps for the part of the extent we didn't write. */
-		btrfs_drop_extent_map_range(inode, unwritten_start, end, false);
+		/*
+		 * Drop extent maps for the part of the extent we didn't write.
+		 *
+		 * We have an exception here for the free_space_inode, this is
+		 * because when we do btrfs_get_extent() on the free space inode
+		 * we will search the commit root.  If this is a new block group
+		 * we won't find anything, and we will trip over the assert in
+		 * writepage where we do ASSERT(em->block_start !=
+		 * EXTENT_MAP_HOLE).
+		 *
+		 * Theoretically we could also skip this for any NOCOW extent as
+		 * we don't mess with the extent map tree in the NOCOW case, but
+		 * for now simply skip this if we are the free space inode.
+		 */
+		if (!btrfs_is_free_space_inode(inode))
+			btrfs_drop_extent_map_range(inode, unwritten_start,
+						    end, false);
 
 		/*
 		 * If the ordered extent had an IOERR or something else went
@@ -4458,6 +4473,8 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 	u64 root_flags;
 	int ret;
 
+	down_write(&fs_info->subvol_sem);
+
 	/*
 	 * Don't allow to delete a subvolume with send in progress. This is
 	 * inside the inode lock so the error handling that has to drop the bit
@@ -4469,25 +4486,25 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 		btrfs_warn(fs_info,
 			   "attempt to delete subvolume %llu during send",
 			   dest->root_key.objectid);
-		return -EPERM;
+		ret = -EPERM;
+		goto out_up_write;
 	}
 	if (atomic_read(&dest->nr_swapfiles)) {
 		spin_unlock(&dest->root_item_lock);
 		btrfs_warn(fs_info,
 			   "attempt to delete subvolume %llu with active swapfile",
 			   root->root_key.objectid);
-		return -EPERM;
+		ret = -EPERM;
+		goto out_up_write;
 	}
 	root_flags = btrfs_root_flags(&dest->root_item);
 	btrfs_set_root_flags(&dest->root_item,
 			     root_flags | BTRFS_ROOT_SUBVOL_DEAD);
 	spin_unlock(&dest->root_item_lock);
 
-	down_write(&fs_info->subvol_sem);
-
 	ret = may_destroy_subvol(dest);
 	if (ret)
-		goto out_up_write;
+		goto out_undead;
 
 	btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
 	/*
@@ -4497,7 +4514,7 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 	 */
 	ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true);
 	if (ret)
-		goto out_up_write;
+		goto out_undead;
 
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
@@ -4563,15 +4580,17 @@ out_end_trans:
 	inode->i_flags |= S_DEAD;
 out_release:
 	btrfs_subvolume_release_metadata(root, &block_rsv);
-out_up_write:
-	up_write(&fs_info->subvol_sem);
+out_undead:
 	if (ret) {
 		spin_lock(&dest->root_item_lock);
 		root_flags = btrfs_root_flags(&dest->root_item);
 		btrfs_set_root_flags(&dest->root_item,
 				root_flags & ~BTRFS_ROOT_SUBVOL_DEAD);
 		spin_unlock(&dest->root_item_lock);
-	} else {
+	}
+out_up_write:
+	up_write(&fs_info->subvol_sem);
+	if (!ret) {
 		d_invalidate(dentry);
 		btrfs_prune_dentries(dest);
 		ASSERT(dest->send_in_progress == 0);
@@ -7816,6 +7835,7 @@ struct iomap_dio *btrfs_dio_write(struct kiocb *iocb, struct iov_iter *iter,
 static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			u64 start, u64 len)
 {
+	struct btrfs_inode *btrfs_inode = BTRFS_I(inode);
 	int	ret;
 
 	ret = fiemap_prep(inode, fieinfo, start, &len, 0);
@@ -7841,7 +7861,26 @@ static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			return ret;
 	}
 
-	return extent_fiemap(BTRFS_I(inode), fieinfo, start, len);
+	btrfs_inode_lock(btrfs_inode, BTRFS_ILOCK_SHARED);
+
+	/*
+	 * We did an initial flush to avoid holding the inode's lock while
+	 * triggering writeback and waiting for the completion of IO and ordered
+	 * extents. Now after we locked the inode we do it again, because it's
+	 * possible a new write may have happened in between those two steps.
+	 */
+	if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) {
+		ret = btrfs_wait_ordered_range(inode, 0, LLONG_MAX);
+		if (ret) {
+			btrfs_inode_unlock(btrfs_inode, BTRFS_ILOCK_SHARED);
+			return ret;
+		}
+	}
+
+	ret = extent_fiemap(btrfs_inode, fieinfo, start, len);
+	btrfs_inode_unlock(btrfs_inode, BTRFS_ILOCK_SHARED);
+
+	return ret;
 }
 
 static int btrfs_writepages(struct address_space *mapping,
@@ -10269,6 +10308,13 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
 	if (encoded->encryption != BTRFS_ENCODED_IO_ENCRYPTION_NONE)
 		return -EINVAL;
 
+	/*
+	 * Compressed extents should always have checksums, so error out if we
+	 * have a NOCOW file or inode was created while mounted with NODATASUM.
+	 */
+	if (inode->flags & BTRFS_INODE_NODATASUM)
+		return -EINVAL;
+
 	orig_count = iov_iter_count(from);
 
 	/* The extent size must be sane. */
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 41b479861b3c..9876ee27f069 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -721,7 +721,7 @@ static noinline int create_subvol(struct mnt_idmap *idmap,
 	free_extent_buffer(leaf);
 	leaf = NULL;
 
-	new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev);
+	new_root = btrfs_get_new_fs_root(fs_info, objectid, &anon_dev);
 	if (IS_ERR(new_root)) {
 		ret = PTR_ERR(new_root);
 		btrfs_abort_transaction(trans, ret);
@@ -790,6 +790,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 		return -EOPNOTSUPP;
 	}
 
+	if (btrfs_root_refs(&root->root_item) == 0)
+		return -ENOENT;
+
 	if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))
 		return -EINVAL;
 
@@ -2608,6 +2611,10 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
 				ret = -EFAULT;
 				goto out;
 			}
+			if (range.flags & ~BTRFS_DEFRAG_RANGE_FLAGS_SUPP) {
+				ret = -EOPNOTSUPP;
+				goto out;
+			}
 			/* compression requires us to start the IO */
 			if ((range.flags & BTRFS_DEFRAG_RANGE_COMPRESS)) {
 				range.flags |= BTRFS_DEFRAG_RANGE_START_IO;
@@ -2691,7 +2698,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ioctl_vol_args_v2 *vol_args;
-	struct bdev_handle *bdev_handle = NULL;
+	struct file *bdev_file = NULL;
 	int ret;
 	bool cancel = false;
 
@@ -2728,7 +2735,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 		goto err_drop;
 
 	/* Exclusive operation is now claimed */
-	ret = btrfs_rm_device(fs_info, &args, &bdev_handle);
+	ret = btrfs_rm_device(fs_info, &args, &bdev_file);
 
 	btrfs_exclop_finish(fs_info);
 
@@ -2742,8 +2749,8 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 	}
 err_drop:
 	mnt_drop_write_file(file);
-	if (bdev_handle)
-		bdev_release(bdev_handle);
+	if (bdev_file)
+		fput(bdev_file);
 out:
 	btrfs_put_dev_args_from_path(&args);
 	kfree(vol_args);
@@ -2756,7 +2763,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ioctl_vol_args *vol_args;
-	struct bdev_handle *bdev_handle = NULL;
+	struct file *bdev_file = NULL;
 	int ret;
 	bool cancel = false;
 
@@ -2783,15 +2790,15 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 	ret = exclop_start_or_cancel_reloc(fs_info, BTRFS_EXCLOP_DEV_REMOVE,
 					   cancel);
 	if (ret == 0) {
-		ret = btrfs_rm_device(fs_info, &args, &bdev_handle);
+		ret = btrfs_rm_device(fs_info, &args, &bdev_file);
 		if (!ret)
 			btrfs_info(fs_info, "disk deleted %s", vol_args->name);
 		btrfs_exclop_finish(fs_info);
 	}
 
 	mnt_drop_write_file(file);
-	if (bdev_handle)
-		bdev_release(bdev_handle);
+	if (bdev_file)
+		fput(bdev_file);
 out:
 	btrfs_put_dev_args_from_path(&args);
 	kfree(vol_args);
@@ -3808,6 +3815,11 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg)
 		goto out;
 	}
 
+	if (sa->create && is_fstree(sa->qgroupid)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index 1131d5a29d61..e43bc0fdc74e 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -425,16 +425,16 @@ int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 }
 
 int lzo_decompress(struct list_head *ws, const u8 *data_in,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
+	struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb);
+	const u32 sectorsize = fs_info->sectorsize;
 	size_t in_len;
 	size_t out_len;
 	size_t max_segment_len = WORKSPACE_BUF_LENGTH;
 	int ret = 0;
-	char *kaddr;
-	unsigned long bytes;
 
 	if (srclen < LZO_LEN || srclen > max_segment_len + LZO_LEN * 2)
 		return -EUCLEAN;
@@ -451,7 +451,7 @@ int lzo_decompress(struct list_head *ws, const u8 *data_in,
 	}
 	data_in += LZO_LEN;
 
-	out_len = PAGE_SIZE;
+	out_len = sectorsize;
 	ret = lzo1x_decompress_safe(data_in, in_len, workspace->buf, &out_len);
 	if (ret != LZO_E_OK) {
 		pr_warn("BTRFS: decompress failed!\n");
@@ -459,29 +459,13 @@ int lzo_decompress(struct list_head *ws, const u8 *data_in,
 		goto out;
 	}
 
-	if (out_len < start_byte) {
+	ASSERT(out_len <= sectorsize);
+	memcpy_to_page(dest_page, dest_pgoff, workspace->buf, out_len);
+	/* Early end, considered as an error. */
+	if (unlikely(out_len < destlen)) {
 		ret = -EIO;
-		goto out;
+		memzero_page(dest_page, dest_pgoff + out_len, destlen - out_len);
 	}
-
-	/*
-	 * the caller is already checking against PAGE_SIZE, but lets
-	 * move this check closer to the memcpy/memset
-	 */
-	destlen = min_t(unsigned long, destlen, PAGE_SIZE);
-	bytes = min_t(unsigned long, destlen, out_len - start_byte);
-
-	kaddr = kmap_local_page(dest_page);
-	memcpy(kaddr, workspace->buf + start_byte, bytes);
-
-	/*
-	 * btrfs_getblock is doing a zero on the tail of the page too,
-	 * but this will cover anything missing from the decompressed
-	 * data.
-	 */
-	if (bytes < destlen)
-		memset(kaddr+bytes, 0, destlen-bytes);
-	kunmap_local(kaddr);
 out:
 	return ret;
 }
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 63b426cc7798..5470e1cdf10c 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1736,6 +1736,15 @@ out:
 	return ret;
 }
 
+static bool qgroup_has_usage(struct btrfs_qgroup *qgroup)
+{
+	return (qgroup->rfer > 0 || qgroup->rfer_cmpr > 0 ||
+		qgroup->excl > 0 || qgroup->excl_cmpr > 0 ||
+		qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA] > 0 ||
+		qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC] > 0 ||
+		qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS] > 0);
+}
+
 int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
@@ -1755,6 +1764,11 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 		goto out;
 	}
 
+	if (is_fstree(qgroupid) && qgroup_has_usage(qgroup)) {
+		ret = -EBUSY;
+		goto out;
+	}
+
 	/* Check if there are no children of this qgroup */
 	if (!list_empty(&qgroup->members)) {
 		ret = -EBUSY;
diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index 6486f0d7e993..8c4fc98ca9ce 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -889,8 +889,10 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
 out_unlock:
 	spin_unlock(&fs_info->ref_verify_lock);
 out:
-	if (ret)
+	if (ret) {
+		btrfs_free_ref_cache(fs_info);
 		btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY);
+	}
 	return ret;
 }
 
@@ -1021,8 +1023,8 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info)
 		}
 	}
 	if (ret) {
-		btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY);
 		btrfs_free_ref_cache(fs_info);
+		btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY);
 	}
 	btrfs_free_path(path);
 	return ret;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index a01807cbd4d4..0123d2728923 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1098,12 +1098,22 @@ out:
 static void scrub_read_endio(struct btrfs_bio *bbio)
 {
 	struct scrub_stripe *stripe = bbio->private;
+	struct bio_vec *bvec;
+	int sector_nr = calc_sector_number(stripe, bio_first_bvec_all(&bbio->bio));
+	int num_sectors;
+	u32 bio_size = 0;
+	int i;
+
+	ASSERT(sector_nr < stripe->nr_sectors);
+	bio_for_each_bvec_all(bvec, &bbio->bio, i)
+		bio_size += bvec->bv_len;
+	num_sectors = bio_size >> stripe->bg->fs_info->sectorsize_bits;
 
 	if (bbio->bio.bi_status) {
-		bitmap_set(&stripe->io_error_bitmap, 0, stripe->nr_sectors);
-		bitmap_set(&stripe->error_bitmap, 0, stripe->nr_sectors);
+		bitmap_set(&stripe->io_error_bitmap, sector_nr, num_sectors);
+		bitmap_set(&stripe->error_bitmap, sector_nr, num_sectors);
 	} else {
-		bitmap_clear(&stripe->io_error_bitmap, 0, stripe->nr_sectors);
+		bitmap_clear(&stripe->io_error_bitmap, sector_nr, num_sectors);
 	}
 	bio_put(&bbio->bio);
 	if (atomic_dec_and_test(&stripe->pending_io)) {
@@ -1636,6 +1646,9 @@ static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx,
 {
 	struct btrfs_fs_info *fs_info = stripe->bg->fs_info;
 	struct btrfs_bio *bbio = NULL;
+	unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start +
+				      stripe->bg->length - stripe->logical) >>
+				  fs_info->sectorsize_bits;
 	u64 stripe_len = BTRFS_STRIPE_LEN;
 	int mirror = stripe->mirror_num;
 	int i;
@@ -1646,6 +1659,10 @@ static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx,
 		struct page *page = scrub_stripe_get_page(stripe, i);
 		unsigned int pgoff = scrub_stripe_get_page_offset(stripe, i);
 
+		/* We're beyond the chunk boundary, no need to read anymore. */
+		if (i >= nr_sectors)
+			break;
+
 		/* The current sector cannot be merged, submit the bio. */
 		if (bbio &&
 		    ((i > 0 &&
@@ -1701,6 +1718,9 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx,
 {
 	struct btrfs_fs_info *fs_info = sctx->fs_info;
 	struct btrfs_bio *bbio;
+	unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start +
+				      stripe->bg->length - stripe->logical) >>
+				  fs_info->sectorsize_bits;
 	int mirror = stripe->mirror_num;
 
 	ASSERT(stripe->bg);
@@ -1715,14 +1735,16 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx,
 	bbio = btrfs_bio_alloc(SCRUB_STRIPE_PAGES, REQ_OP_READ, fs_info,
 			       scrub_read_endio, stripe);
 
-	/* Read the whole stripe. */
 	bbio->bio.bi_iter.bi_sector = stripe->logical >> SECTOR_SHIFT;
-	for (int i = 0; i < BTRFS_STRIPE_LEN >> PAGE_SHIFT; i++) {
+	/* Read the whole range inside the chunk boundary. */
+	for (unsigned int cur = 0; cur < nr_sectors; cur++) {
+		struct page *page = scrub_stripe_get_page(stripe, cur);
+		unsigned int pgoff = scrub_stripe_get_page_offset(stripe, cur);
 		int ret;
 
-		ret = bio_add_page(&bbio->bio, stripe->pages[i], PAGE_SIZE, 0);
+		ret = bio_add_page(&bbio->bio, page, fs_info->sectorsize, pgoff);
 		/* We should have allocated enough bio vectors. */
-		ASSERT(ret == PAGE_SIZE);
+		ASSERT(ret == fs_info->sectorsize);
 	}
 	atomic_inc(&stripe->pending_io);
 
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 4e36550618e5..e48a063ef085 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -6705,11 +6705,20 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
 				if (ret)
 					goto out;
 			}
-			if (sctx->cur_inode_last_extent <
-			    sctx->cur_inode_size) {
-				ret = send_hole(sctx, sctx->cur_inode_size);
-				if (ret)
+			if (sctx->cur_inode_last_extent < sctx->cur_inode_size) {
+				ret = range_is_hole_in_parent(sctx,
+						      sctx->cur_inode_last_extent,
+						      sctx->cur_inode_size);
+				if (ret < 0) {
 					goto out;
+				} else if (ret == 0) {
+					ret = send_hole(sctx, sctx->cur_inode_size);
+					if (ret < 0)
+						goto out;
+				} else {
+					/* Range is already a hole, skip. */
+					ret = 0;
+				}
 			}
 		}
 		if (need_truncate) {
@@ -8111,7 +8120,7 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg)
 	}
 
 	if (arg->flags & ~BTRFS_SEND_FLAG_MASK) {
-		ret = -EINVAL;
+		ret = -EOPNOTSUPP;
 		goto out;
 	}
 
@@ -8205,8 +8214,8 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg)
 		goto out;
 	}
 
-	sctx->clone_roots = kvcalloc(sizeof(*sctx->clone_roots),
-				     arg->clone_sources_count + 1,
+	sctx->clone_roots = kvcalloc(arg->clone_sources_count + 1,
+				     sizeof(*sctx->clone_roots),
 				     GFP_KERNEL);
 	if (!sctx->clone_roots) {
 		ret = -ENOMEM;
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 571bb13587d5..3b54eb583474 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -856,7 +856,7 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info,
 static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info,
 				    struct btrfs_space_info *space_info)
 {
-	u64 global_rsv_size = fs_info->global_block_rsv.reserved;
+	const u64 global_rsv_size = btrfs_block_rsv_reserved(&fs_info->global_block_rsv);
 	u64 ordered, delalloc;
 	u64 thresh;
 	u64 used;
@@ -956,8 +956,8 @@ static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info,
 	ordered = percpu_counter_read_positive(&fs_info->ordered_bytes) >> 1;
 	delalloc = percpu_counter_read_positive(&fs_info->delalloc_bytes);
 	if (ordered >= delalloc)
-		used += fs_info->delayed_refs_rsv.reserved +
-			fs_info->delayed_block_rsv.reserved;
+		used += btrfs_block_rsv_reserved(&fs_info->delayed_refs_rsv) +
+			btrfs_block_rsv_reserved(&fs_info->delayed_block_rsv);
 	else
 		used += space_info->bytes_may_use - global_rsv_size;
 
@@ -1173,7 +1173,7 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work)
 		enum btrfs_flush_state flush;
 		u64 delalloc_size = 0;
 		u64 to_reclaim, block_rsv_size;
-		u64 global_rsv_size = global_rsv->reserved;
+		const u64 global_rsv_size = btrfs_block_rsv_reserved(global_rsv);
 
 		loops++;
 
@@ -1185,9 +1185,9 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work)
 		 * assume it's tied up in delalloc reservations.
 		 */
 		block_rsv_size = global_rsv_size +
-			delayed_block_rsv->reserved +
-			delayed_refs_rsv->reserved +
-			trans_rsv->reserved;
+			btrfs_block_rsv_reserved(delayed_block_rsv) +
+			btrfs_block_rsv_reserved(delayed_refs_rsv) +
+			btrfs_block_rsv_reserved(trans_rsv);
 		if (block_rsv_size < space_info->bytes_may_use)
 			delalloc_size = space_info->bytes_may_use - block_rsv_size;
 
@@ -1207,16 +1207,16 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work)
 			to_reclaim = delalloc_size;
 			flush = FLUSH_DELALLOC;
 		} else if (space_info->bytes_pinned >
-			   (delayed_block_rsv->reserved +
-			    delayed_refs_rsv->reserved)) {
+			   (btrfs_block_rsv_reserved(delayed_block_rsv) +
+			    btrfs_block_rsv_reserved(delayed_refs_rsv))) {
 			to_reclaim = space_info->bytes_pinned;
 			flush = COMMIT_TRANS;
-		} else if (delayed_block_rsv->reserved >
-			   delayed_refs_rsv->reserved) {
-			to_reclaim = delayed_block_rsv->reserved;
+		} else if (btrfs_block_rsv_reserved(delayed_block_rsv) >
+			   btrfs_block_rsv_reserved(delayed_refs_rsv)) {
+			to_reclaim = btrfs_block_rsv_reserved(delayed_block_rsv);
 			flush = FLUSH_DELAYED_ITEMS_NR;
 		} else {
-			to_reclaim = delayed_refs_rsv->reserved;
+			to_reclaim = btrfs_block_rsv_reserved(delayed_refs_rsv);
 			flush = FLUSH_DELAYED_REFS_NR;
 		}
 
diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c
index 93511d54abf8..0e49dab8dad2 100644
--- a/fs/btrfs/subpage.c
+++ b/fs/btrfs/subpage.c
@@ -475,7 +475,8 @@ void btrfs_subpage_set_writeback(const struct btrfs_fs_info *fs_info,
 
 	spin_lock_irqsave(&subpage->lock, flags);
 	bitmap_set(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits);
-	folio_start_writeback(folio);
+	if (!folio_test_writeback(folio))
+		folio_start_writeback(folio);
 	spin_unlock_irqrestore(&subpage->lock, flags);
 }
 
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 896acfda1789..101f786963d4 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1457,6 +1457,14 @@ static int btrfs_reconfigure(struct fs_context *fc)
 
 	btrfs_info_to_ctx(fs_info, &old_ctx);
 
+	/*
+	 * This is our "bind mount" trick, we don't want to allow the user to do
+	 * anything other than mount a different ro/rw and a different subvol,
+	 * all of the mount options should be maintained.
+	 */
+	if (mount_reconfigure)
+		ctx->mount_opt = old_ctx.mount_opt;
+
 	sync_filesystem(sb);
 	set_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
 
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 5b3333ceef04..bf8e64c766b6 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -564,56 +564,22 @@ static int btrfs_reserve_trans_metadata(struct btrfs_fs_info *fs_info,
 					u64 num_bytes,
 					u64 *delayed_refs_bytes)
 {
-	struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv;
 	struct btrfs_space_info *si = fs_info->trans_block_rsv.space_info;
-	u64 extra_delayed_refs_bytes = 0;
-	u64 bytes;
+	u64 bytes = num_bytes + *delayed_refs_bytes;
 	int ret;
 
 	/*
-	 * If there's a gap between the size of the delayed refs reserve and
-	 * its reserved space, than some tasks have added delayed refs or bumped
-	 * its size otherwise (due to block group creation or removal, or block
-	 * group item update). Also try to allocate that gap in order to prevent
-	 * using (and possibly abusing) the global reserve when committing the
-	 * transaction.
-	 */
-	if (flush == BTRFS_RESERVE_FLUSH_ALL &&
-	    !btrfs_block_rsv_full(delayed_refs_rsv)) {
-		spin_lock(&delayed_refs_rsv->lock);
-		if (delayed_refs_rsv->size > delayed_refs_rsv->reserved)
-			extra_delayed_refs_bytes = delayed_refs_rsv->size -
-				delayed_refs_rsv->reserved;
-		spin_unlock(&delayed_refs_rsv->lock);
-	}
-
-	bytes = num_bytes + *delayed_refs_bytes + extra_delayed_refs_bytes;
-
-	/*
 	 * We want to reserve all the bytes we may need all at once, so we only
 	 * do 1 enospc flushing cycle per transaction start.
 	 */
 	ret = btrfs_reserve_metadata_bytes(fs_info, si, bytes, flush);
-	if (ret == 0) {
-		if (extra_delayed_refs_bytes > 0)
-			btrfs_migrate_to_delayed_refs_rsv(fs_info,
-							  extra_delayed_refs_bytes);
-		return 0;
-	}
-
-	if (extra_delayed_refs_bytes > 0) {
-		bytes -= extra_delayed_refs_bytes;
-		ret = btrfs_reserve_metadata_bytes(fs_info, si, bytes, flush);
-		if (ret == 0)
-			return 0;
-	}
 
 	/*
 	 * If we are an emergency flush, which can steal from the global block
 	 * reserve, then attempt to not reserve space for the delayed refs, as
 	 * we will consume space for them from the global block reserve.
 	 */
-	if (flush == BTRFS_RESERVE_FLUSH_ALL_STEAL) {
+	if (ret && flush == BTRFS_RESERVE_FLUSH_ALL_STEAL) {
 		bytes -= *delayed_refs_bytes;
 		*delayed_refs_bytes = 0;
 		ret = btrfs_reserve_metadata_bytes(fs_info, si, bytes, flush);
@@ -1868,7 +1834,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	}
 
 	key.offset = (u64)-1;
-	pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev);
+	pending->snap = btrfs_get_new_fs_root(fs_info, objectid, &pending->anon_dev);
 	if (IS_ERR(pending->snap)) {
 		ret = PTR_ERR(pending->snap);
 		pending->snap = NULL;
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 50fdc69fdddf..6eccf8496486 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1436,7 +1436,7 @@ static int check_extent_item(struct extent_buffer *leaf,
 		if (unlikely(ptr + btrfs_extent_inline_ref_size(inline_type) > end)) {
 			extent_err(leaf, slot,
 "inline ref item overflows extent item, ptr %lu iref size %u end %lu",
-				   ptr, inline_type, end);
+				   ptr, btrfs_extent_inline_ref_size(inline_type), end);
 			return -EUCLEAN;
 		}
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 4c32497311d2..e180da4cc227 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -468,39 +468,39 @@ static noinline struct btrfs_fs_devices *find_fsid(
 
 static int
 btrfs_get_bdev_and_sb(const char *device_path, blk_mode_t flags, void *holder,
-		      int flush, struct bdev_handle **bdev_handle,
+		      int flush, struct file **bdev_file,
 		      struct btrfs_super_block **disk_super)
 {
 	struct block_device *bdev;
 	int ret;
 
-	*bdev_handle = bdev_open_by_path(device_path, flags, holder, NULL);
+	*bdev_file = bdev_file_open_by_path(device_path, flags, holder, NULL);
 
-	if (IS_ERR(*bdev_handle)) {
-		ret = PTR_ERR(*bdev_handle);
+	if (IS_ERR(*bdev_file)) {
+		ret = PTR_ERR(*bdev_file);
 		goto error;
 	}
-	bdev = (*bdev_handle)->bdev;
+	bdev = file_bdev(*bdev_file);
 
 	if (flush)
 		sync_blockdev(bdev);
 	ret = set_blocksize(bdev, BTRFS_BDEV_BLOCKSIZE);
 	if (ret) {
-		bdev_release(*bdev_handle);
+		fput(*bdev_file);
 		goto error;
 	}
 	invalidate_bdev(bdev);
 	*disk_super = btrfs_read_dev_super(bdev);
 	if (IS_ERR(*disk_super)) {
 		ret = PTR_ERR(*disk_super);
-		bdev_release(*bdev_handle);
+		fput(*bdev_file);
 		goto error;
 	}
 
 	return 0;
 
 error:
-	*bdev_handle = NULL;
+	*bdev_file = NULL;
 	return ret;
 }
 
@@ -643,7 +643,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 			struct btrfs_device *device, blk_mode_t flags,
 			void *holder)
 {
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct btrfs_super_block *disk_super;
 	u64 devid;
 	int ret;
@@ -654,7 +654,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 		return -EINVAL;
 
 	ret = btrfs_get_bdev_and_sb(device->name->str, flags, holder, 1,
-				    &bdev_handle, &disk_super);
+				    &bdev_file, &disk_super);
 	if (ret)
 		return ret;
 
@@ -678,20 +678,20 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 		clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
 		fs_devices->seeding = true;
 	} else {
-		if (bdev_read_only(bdev_handle->bdev))
+		if (bdev_read_only(file_bdev(bdev_file)))
 			clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
 		else
 			set_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
 	}
 
-	if (!bdev_nonrot(bdev_handle->bdev))
+	if (!bdev_nonrot(file_bdev(bdev_file)))
 		fs_devices->rotating = true;
 
-	if (bdev_max_discard_sectors(bdev_handle->bdev))
+	if (bdev_max_discard_sectors(file_bdev(bdev_file)))
 		fs_devices->discardable = true;
 
-	device->bdev_handle = bdev_handle;
-	device->bdev = bdev_handle->bdev;
+	device->bdev_file = bdev_file;
+	device->bdev = file_bdev(bdev_file);
 	clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
 
 	fs_devices->open_devices++;
@@ -706,7 +706,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 
 error_free_page:
 	btrfs_release_disk_super(disk_super);
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 
 	return -EINVAL;
 }
@@ -1015,10 +1015,10 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices,
 		if (device->devid == BTRFS_DEV_REPLACE_DEVID)
 			continue;
 
-		if (device->bdev_handle) {
-			bdev_release(device->bdev_handle);
+		if (device->bdev_file) {
+			fput(device->bdev_file);
 			device->bdev = NULL;
-			device->bdev_handle = NULL;
+			device->bdev_file = NULL;
 			fs_devices->open_devices--;
 		}
 		if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
@@ -1063,7 +1063,7 @@ static void btrfs_close_bdev(struct btrfs_device *device)
 		invalidate_bdev(device->bdev);
 	}
 
-	bdev_release(device->bdev_handle);
+	fput(device->bdev_file);
 }
 
 static void btrfs_close_one_device(struct btrfs_device *device)
@@ -1316,7 +1316,7 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags,
 	struct btrfs_super_block *disk_super;
 	bool new_device_added = false;
 	struct btrfs_device *device = NULL;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	u64 bytenr, bytenr_orig;
 	int ret;
 
@@ -1339,18 +1339,18 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags,
 	 * values temporarily, as the device paths of the fsid are the only
 	 * required information for assembling the volume.
 	 */
-	bdev_handle = bdev_open_by_path(path, flags, NULL, NULL);
-	if (IS_ERR(bdev_handle))
-		return ERR_CAST(bdev_handle);
+	bdev_file = bdev_file_open_by_path(path, flags, NULL, NULL);
+	if (IS_ERR(bdev_file))
+		return ERR_CAST(bdev_file);
 
 	bytenr_orig = btrfs_sb_offset(0);
-	ret = btrfs_sb_log_location_bdev(bdev_handle->bdev, 0, READ, &bytenr);
+	ret = btrfs_sb_log_location_bdev(file_bdev(bdev_file), 0, READ, &bytenr);
 	if (ret) {
 		device = ERR_PTR(ret);
 		goto error_bdev_put;
 	}
 
-	disk_super = btrfs_read_disk_super(bdev_handle->bdev, bytenr,
+	disk_super = btrfs_read_disk_super(file_bdev(bdev_file), bytenr,
 					   bytenr_orig);
 	if (IS_ERR(disk_super)) {
 		device = ERR_CAST(disk_super);
@@ -1381,7 +1381,7 @@ free_disk_super:
 	btrfs_release_disk_super(disk_super);
 
 error_bdev_put:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 
 	return device;
 }
@@ -2057,7 +2057,7 @@ void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
 
 int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 		    struct btrfs_dev_lookup_args *args,
-		    struct bdev_handle **bdev_handle)
+		    struct file **bdev_file)
 {
 	struct btrfs_trans_handle *trans;
 	struct btrfs_device *device;
@@ -2166,7 +2166,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 
 	btrfs_assign_next_active_device(device, NULL);
 
-	if (device->bdev_handle) {
+	if (device->bdev_file) {
 		cur_devices->open_devices--;
 		/* remove sysfs entry */
 		btrfs_sysfs_remove_device(device);
@@ -2182,9 +2182,9 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 	 * free the device.
 	 *
 	 * We cannot call btrfs_close_bdev() here because we're holding the sb
-	 * write lock, and bdev_release() will pull in the ->open_mutex on
-	 * the block device and it's dependencies.  Instead just flush the
-	 * device and let the caller do the final bdev_release.
+	 * write lock, and fput() on the block device will pull in the
+	 * ->open_mutex on the block device and it's dependencies.  Instead
+	 *  just flush the device and let the caller do the final bdev_release.
 	 */
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
 		btrfs_scratch_superblocks(fs_info, device->bdev,
@@ -2195,7 +2195,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 		}
 	}
 
-	*bdev_handle = device->bdev_handle;
+	*bdev_file = device->bdev_file;
 	synchronize_rcu();
 	btrfs_free_device(device);
 
@@ -2332,7 +2332,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
 				 const char *path)
 {
 	struct btrfs_super_block *disk_super;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	int ret;
 
 	if (!path || !path[0])
@@ -2350,7 +2350,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
 	}
 
 	ret = btrfs_get_bdev_and_sb(path, BLK_OPEN_READ, NULL, 0,
-				    &bdev_handle, &disk_super);
+				    &bdev_file, &disk_super);
 	if (ret) {
 		btrfs_put_dev_args_from_path(args);
 		return ret;
@@ -2363,7 +2363,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
 	else
 		memcpy(args->fsid, disk_super->fsid, BTRFS_FSID_SIZE);
 	btrfs_release_disk_super(disk_super);
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 	return 0;
 }
 
@@ -2583,7 +2583,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	struct btrfs_root *root = fs_info->dev_root;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_device *device;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct super_block *sb = fs_info->sb;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	struct btrfs_fs_devices *seed_devices = NULL;
@@ -2596,12 +2596,12 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	if (sb_rdonly(sb) && !fs_devices->seeding)
 		return -EROFS;
 
-	bdev_handle = bdev_open_by_path(device_path, BLK_OPEN_WRITE,
+	bdev_file = bdev_file_open_by_path(device_path, BLK_OPEN_WRITE,
 					fs_info->bdev_holder, NULL);
-	if (IS_ERR(bdev_handle))
-		return PTR_ERR(bdev_handle);
+	if (IS_ERR(bdev_file))
+		return PTR_ERR(bdev_file);
 
-	if (!btrfs_check_device_zone_type(fs_info, bdev_handle->bdev)) {
+	if (!btrfs_check_device_zone_type(fs_info, file_bdev(bdev_file))) {
 		ret = -EINVAL;
 		goto error;
 	}
@@ -2613,11 +2613,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 		locked = true;
 	}
 
-	sync_blockdev(bdev_handle->bdev);
+	sync_blockdev(file_bdev(bdev_file));
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(device, &fs_devices->devices, dev_list) {
-		if (device->bdev == bdev_handle->bdev) {
+		if (device->bdev == file_bdev(bdev_file)) {
 			ret = -EEXIST;
 			rcu_read_unlock();
 			goto error;
@@ -2633,8 +2633,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	}
 
 	device->fs_info = fs_info;
-	device->bdev_handle = bdev_handle;
-	device->bdev = bdev_handle->bdev;
+	device->bdev_file = bdev_file;
+	device->bdev = file_bdev(bdev_file);
 	ret = lookup_bdev(device_path, &device->devt);
 	if (ret)
 		goto error_free_device;
@@ -2817,7 +2817,7 @@ error_free_zone:
 error_free_device:
 	btrfs_free_device(device);
 error:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 	if (locked) {
 		mutex_unlock(&uuid_mutex);
 		up_write(&sb->s_umount);
@@ -3087,7 +3087,6 @@ struct btrfs_chunk_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
 	map = btrfs_find_chunk_map(fs_info, logical, length);
 
 	if (unlikely(!map)) {
-		read_unlock(&fs_info->mapping_tree_lock);
 		btrfs_crit(fs_info,
 			   "unable to find chunk map for logical %llu length %llu",
 			   logical, length);
@@ -3095,7 +3094,6 @@ struct btrfs_chunk_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
 	}
 
 	if (unlikely(map->start > logical || map->start + map->chunk_len <= logical)) {
-		read_unlock(&fs_info->mapping_tree_lock);
 		btrfs_crit(fs_info,
 			   "found a bad chunk map, wanted %llu-%llu, found %llu-%llu",
 			   logical, logical + length, map->start,
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 53f87f398da7..a11854912d53 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -90,7 +90,7 @@ struct btrfs_device {
 
 	u64 generation;
 
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct block_device *bdev;
 
 	struct btrfs_zoned_device_info *zone_info;
@@ -661,7 +661,7 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 void btrfs_put_dev_args_from_path(struct btrfs_dev_lookup_args *args);
 int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 		    struct btrfs_dev_lookup_args *args,
-		    struct bdev_handle **bdev_handle);
+		    struct file **bdev_file);
 void __exit btrfs_cleanup_fs_uuids(void);
 int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len);
 int btrfs_grow_device(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 36cf1f0e338e..8da66ea699e8 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -354,18 +354,13 @@ done:
 }
 
 int zlib_decompress(struct list_head *ws, const u8 *data_in,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret = 0;
 	int wbits = MAX_WBITS;
-	unsigned long bytes_left;
-	unsigned long total_out = 0;
-	unsigned long pg_offset = 0;
-
-	destlen = min_t(unsigned long, destlen, PAGE_SIZE);
-	bytes_left = destlen;
+	unsigned long to_copy;
 
 	workspace->strm.next_in = data_in;
 	workspace->strm.avail_in = srclen;
@@ -390,60 +385,30 @@ int zlib_decompress(struct list_head *ws, const u8 *data_in,
 		return -EIO;
 	}
 
-	while (bytes_left > 0) {
-		unsigned long buf_start;
-		unsigned long buf_offset;
-		unsigned long bytes;
-
-		ret = zlib_inflate(&workspace->strm, Z_NO_FLUSH);
-		if (ret != Z_OK && ret != Z_STREAM_END)
-			break;
-
-		buf_start = total_out;
-		total_out = workspace->strm.total_out;
-
-		if (total_out == buf_start) {
-			ret = -EIO;
-			break;
-		}
-
-		if (total_out <= start_byte)
-			goto next;
-
-		if (total_out > start_byte && buf_start < start_byte)
-			buf_offset = start_byte - buf_start;
-		else
-			buf_offset = 0;
-
-		bytes = min(PAGE_SIZE - pg_offset,
-			    PAGE_SIZE - (buf_offset % PAGE_SIZE));
-		bytes = min(bytes, bytes_left);
+	/*
+	 * Everything (in/out buf) should be at most one sector, there should
+	 * be no need to switch any input/output buffer.
+	 */
+	ret = zlib_inflate(&workspace->strm, Z_FINISH);
+	to_copy = min(workspace->strm.total_out, destlen);
+	if (ret != Z_STREAM_END)
+		goto out;
 
-		memcpy_to_page(dest_page, pg_offset,
-			       workspace->buf + buf_offset, bytes);
+	memcpy_to_page(dest_page, dest_pgoff, workspace->buf, to_copy);
 
-		pg_offset += bytes;
-		bytes_left -= bytes;
-next:
-		workspace->strm.next_out = workspace->buf;
-		workspace->strm.avail_out = workspace->buf_size;
-	}
-
-	if (ret != Z_STREAM_END && bytes_left != 0)
+out:
+	if (unlikely(to_copy != destlen)) {
+		pr_warn_ratelimited("BTRFS: infalte failed, decompressed=%lu expected=%zu\n",
+					to_copy, destlen);
 		ret = -EIO;
-	else
+	} else {
 		ret = 0;
+	}
 
 	zlib_inflateEnd(&workspace->strm);
 
-	/*
-	 * this should only happen if zlib returned fewer bytes than we
-	 * expected.  btrfs_get_block is responsible for zeroing from the
-	 * end of the inline extent (destlen) to the end of the page
-	 */
-	if (pg_offset < destlen) {
-		memzero_page(dest_page, pg_offset, destlen - pg_offset);
-	}
+	if (unlikely(to_copy < destlen))
+		memzero_page(dest_page, dest_pgoff + to_copy, destlen - to_copy);
 	return ret;
 }
 
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 5bd76813b23f..aea51fd850cd 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -824,11 +824,14 @@ static int sb_log_location(struct block_device *bdev, struct blk_zone *zones,
 			reset = &zones[1];
 
 		if (reset && reset->cond != BLK_ZONE_COND_EMPTY) {
+			unsigned int nofs_flags;
+
 			ASSERT(sb_zone_is_full(reset));
 
+			nofs_flags = memalloc_nofs_save();
 			ret = blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
-					       reset->start, reset->len,
-					       GFP_NOFS);
+					       reset->start, reset->len);
+			memalloc_nofs_restore(nofs_flags);
 			if (ret)
 				return ret;
 
@@ -974,11 +977,14 @@ int btrfs_advance_sb_log(struct btrfs_device *device, int mirror)
 			 * explicit ZONE_FINISH is not necessary.
 			 */
 			if (zone->wp != zone->start + zone->capacity) {
+				unsigned int nofs_flags;
 				int ret;
 
+				nofs_flags = memalloc_nofs_save();
 				ret = blkdev_zone_mgmt(device->bdev,
 						REQ_OP_ZONE_FINISH, zone->start,
-						zone->len, GFP_NOFS);
+						zone->len);
+				memalloc_nofs_restore(nofs_flags);
 				if (ret)
 					return ret;
 			}
@@ -996,11 +1002,13 @@ int btrfs_advance_sb_log(struct btrfs_device *device, int mirror)
 
 int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror)
 {
+	unsigned int nofs_flags;
 	sector_t zone_sectors;
 	sector_t nr_sectors;
 	u8 zone_sectors_shift;
 	u32 sb_zone;
 	u32 nr_zones;
+	int ret;
 
 	zone_sectors = bdev_zone_sectors(bdev);
 	zone_sectors_shift = ilog2(zone_sectors);
@@ -1011,9 +1019,12 @@ int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror)
 	if (sb_zone + 1 >= nr_zones)
 		return -ENOENT;
 
-	return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
-				zone_start_sector(sb_zone, bdev),
-				zone_sectors * BTRFS_NR_SB_LOG_ZONES, GFP_NOFS);
+	nofs_flags = memalloc_nofs_save();
+	ret = blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
+			       zone_start_sector(sb_zone, bdev),
+			       zone_sectors * BTRFS_NR_SB_LOG_ZONES);
+	memalloc_nofs_restore(nofs_flags);
+	return ret;
 }
 
 /*
@@ -1124,12 +1135,14 @@ static void btrfs_dev_clear_active_zone(struct btrfs_device *device, u64 pos)
 int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical,
 			    u64 length, u64 *bytes)
 {
+	unsigned int nofs_flags;
 	int ret;
 
 	*bytes = 0;
+	nofs_flags = memalloc_nofs_save();
 	ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_RESET,
-			       physical >> SECTOR_SHIFT, length >> SECTOR_SHIFT,
-			       GFP_NOFS);
+			       physical >> SECTOR_SHIFT, length >> SECTOR_SHIFT);
+	memalloc_nofs_restore(nofs_flags);
 	if (ret)
 		return ret;
 
@@ -1639,6 +1652,15 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 	}
 
 out:
+	/* Reject non SINGLE data profiles without RST */
+	if ((map->type & BTRFS_BLOCK_GROUP_DATA) &&
+	    (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) &&
+	    !fs_info->stripe_root) {
+		btrfs_err(fs_info, "zoned: data %s needs raid-stripe-tree",
+			  btrfs_bg_type_to_raid_name(map->type));
+		return -EINVAL;
+	}
+
 	if (cache->alloc_offset > cache->zone_capacity) {
 		btrfs_err(fs_info,
 "zoned: invalid write pointer %llu (larger than zone capacity %llu) in block group %llu",
@@ -1670,6 +1692,7 @@ out:
 	}
 	bitmap_free(active);
 	kfree(zone_info);
+	btrfs_free_chunk_map(map);
 
 	return ret;
 }
@@ -2055,6 +2078,7 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
 
 	map = block_group->physical_map;
 
+	spin_lock(&fs_info->zone_active_bgs_lock);
 	spin_lock(&block_group->lock);
 	if (test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags)) {
 		ret = true;
@@ -2067,7 +2091,6 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
 		goto out_unlock;
 	}
 
-	spin_lock(&fs_info->zone_active_bgs_lock);
 	for (i = 0; i < map->num_stripes; i++) {
 		struct btrfs_zoned_device_info *zinfo;
 		int reserved = 0;
@@ -2087,20 +2110,17 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
 		 */
 		if (atomic_read(&zinfo->active_zones_left) <= reserved) {
 			ret = false;
-			spin_unlock(&fs_info->zone_active_bgs_lock);
 			goto out_unlock;
 		}
 
 		if (!btrfs_dev_set_active_zone(device, physical)) {
 			/* Cannot activate the zone */
 			ret = false;
-			spin_unlock(&fs_info->zone_active_bgs_lock);
 			goto out_unlock;
 		}
 		if (!is_data)
 			zinfo->reserved_active_zones--;
 	}
-	spin_unlock(&fs_info->zone_active_bgs_lock);
 
 	/* Successfully activated all the zones */
 	set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags);
@@ -2108,8 +2128,6 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
 
 	/* For the active block group list */
 	btrfs_get_block_group(block_group);
-
-	spin_lock(&fs_info->zone_active_bgs_lock);
 	list_add_tail(&block_group->active_bg_list, &fs_info->zone_active_bgs);
 	spin_unlock(&fs_info->zone_active_bgs_lock);
 
@@ -2117,6 +2135,7 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
 
 out_unlock:
 	spin_unlock(&block_group->lock);
+	spin_unlock(&fs_info->zone_active_bgs_lock);
 	return ret;
 }
 
@@ -2238,14 +2257,16 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ
 		struct btrfs_device *device = map->stripes[i].dev;
 		const u64 physical = map->stripes[i].physical;
 		struct btrfs_zoned_device_info *zinfo = device->zone_info;
+		unsigned int nofs_flags;
 
 		if (zinfo->max_active_zones == 0)
 			continue;
 
+		nofs_flags = memalloc_nofs_save();
 		ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH,
 				       physical >> SECTOR_SHIFT,
-				       zinfo->zone_size >> SECTOR_SHIFT,
-				       GFP_NOFS);
+				       zinfo->zone_size >> SECTOR_SHIFT);
+		memalloc_nofs_restore(nofs_flags);
 
 		if (ret)
 			return ret;
diff --git a/fs/buffer.c b/fs/buffer.c
index d3bcf601d3e5..4f73d23c2c46 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -55,7 +55,7 @@
 
 static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
 static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
-			  struct writeback_control *wbc);
+			  enum rw_hint hint, struct writeback_control *wbc);
 
 #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers)
 
@@ -464,7 +464,7 @@ EXPORT_SYMBOL(mark_buffer_async_write);
  * a successful fsync().  For example, ext2 indirect blocks need to be
  * written back and waited upon before fsync() returns.
  *
- * The functions mark_buffer_inode_dirty(), fsync_inode_buffers(),
+ * The functions mark_buffer_dirty_inode(), fsync_inode_buffers(),
  * inode_has_buffers() and invalidate_inode_buffers() are provided for the
  * management of a list of dependent buffers at ->i_mapping->i_private_list.
  *
@@ -1889,7 +1889,8 @@ int __block_write_full_folio(struct inode *inode, struct folio *folio,
 	do {
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
-			submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, wbc);
+			submit_bh_wbc(REQ_OP_WRITE | write_flags, bh,
+				      inode->i_write_hint, wbc);
 			nr_underway++;
 		}
 		bh = next;
@@ -1944,7 +1945,8 @@ recover:
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
 			clear_buffer_dirty(bh);
-			submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, wbc);
+			submit_bh_wbc(REQ_OP_WRITE | write_flags, bh,
+				      inode->i_write_hint, wbc);
 			nr_underway++;
 		}
 		bh = next;
@@ -2756,6 +2758,7 @@ static void end_bio_bh_io_sync(struct bio *bio)
 }
 
 static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
+			  enum rw_hint write_hint,
 			  struct writeback_control *wbc)
 {
 	const enum req_op op = opf & REQ_OP_MASK;
@@ -2783,6 +2786,7 @@ static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
 	fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO);
 
 	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
+	bio->bi_write_hint = write_hint;
 
 	__bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
 
@@ -2802,7 +2806,7 @@ static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
 
 void submit_bh(blk_opf_t opf, struct buffer_head *bh)
 {
-	submit_bh_wbc(opf, bh, NULL);
+	submit_bh_wbc(opf, bh, WRITE_LIFE_NOT_SET, NULL);
 }
 EXPORT_SYMBOL(submit_bh);
 
@@ -3121,12 +3125,8 @@ void __init buffer_init(void)
 	unsigned long nrpages;
 	int ret;
 
-	bh_cachep = kmem_cache_create("buffer_head",
-			sizeof(struct buffer_head), 0,
-				(SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|
-				SLAB_MEM_SPREAD),
-				NULL);
-
+	bh_cachep = KMEM_CACHE(buffer_head,
+				SLAB_RECLAIM_ACCOUNT|SLAB_PANIC);
 	/*
 	 * Limit the bh occupancy to 10% of ZONE_NORMAL
 	 */
diff --git a/fs/cachefiles/Kconfig b/fs/cachefiles/Kconfig
index 8df715640a48..c5a070550ee3 100644
--- a/fs/cachefiles/Kconfig
+++ b/fs/cachefiles/Kconfig
@@ -2,7 +2,7 @@
 
 config CACHEFILES
 	tristate "Filesystem caching on files"
-	depends on FSCACHE && BLOCK
+	depends on NETFS_SUPPORT && FSCACHE && BLOCK
 	help
 	  This permits use of a mounted filesystem as a cache for other
 	  filesystems - primarily networking filesystems - thus allowing fast
diff --git a/fs/cachefiles/cache.c b/fs/cachefiles/cache.c
index 7077f72e6f47..f449f7340aad 100644
--- a/fs/cachefiles/cache.c
+++ b/fs/cachefiles/cache.c
@@ -168,6 +168,8 @@ error_unsupported:
 	dput(root);
 error_open_root:
 	cachefiles_end_secure(cache, saved_cred);
+	put_cred(cache->cache_cred);
+	cache->cache_cred = NULL;
 error_getsec:
 	fscache_relinquish_cache(cache_cookie);
 	cache->cache = NULL;
diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c
index 3f24905f4066..6465e2574230 100644
--- a/fs/cachefiles/daemon.c
+++ b/fs/cachefiles/daemon.c
@@ -816,6 +816,7 @@ static void cachefiles_daemon_unbind(struct cachefiles_cache *cache)
 	cachefiles_put_directory(cache->graveyard);
 	cachefiles_put_directory(cache->store);
 	mntput(cache->mnt);
+	put_cred(cache->cache_cred);
 
 	kfree(cache->rootdirname);
 	kfree(cache->secctx);
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index 4a87c9d714a9..d33169f0018b 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -246,7 +246,7 @@ extern bool cachefiles_begin_operation(struct netfs_cache_resources *cres,
 				       enum fscache_want_state want_state);
 extern int __cachefiles_prepare_write(struct cachefiles_object *object,
 				      struct file *file,
-				      loff_t *_start, size_t *_len,
+				      loff_t *_start, size_t *_len, size_t upper_len,
 				      bool no_space_allocated_yet);
 extern int __cachefiles_write(struct cachefiles_object *object,
 			      struct file *file,
diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c
index 5857241c5918..1d685357e67f 100644
--- a/fs/cachefiles/io.c
+++ b/fs/cachefiles/io.c
@@ -517,18 +517,26 @@ cachefiles_prepare_ondemand_read(struct netfs_cache_resources *cres,
  */
 int __cachefiles_prepare_write(struct cachefiles_object *object,
 			       struct file *file,
-			       loff_t *_start, size_t *_len,
+			       loff_t *_start, size_t *_len, size_t upper_len,
 			       bool no_space_allocated_yet)
 {
 	struct cachefiles_cache *cache = object->volume->cache;
 	loff_t start = *_start, pos;
-	size_t len = *_len, down;
+	size_t len = *_len;
 	int ret;
 
 	/* Round to DIO size */
-	down = start - round_down(start, PAGE_SIZE);
-	*_start = start - down;
-	*_len = round_up(down + len, PAGE_SIZE);
+	start = round_down(*_start, PAGE_SIZE);
+	if (start != *_start || *_len > upper_len) {
+		/* Probably asked to cache a streaming write written into the
+		 * pagecache when the cookie was temporarily out of service to
+		 * culling.
+		 */
+		fscache_count_dio_misfit();
+		return -ENOBUFS;
+	}
+
+	*_len = round_up(len, PAGE_SIZE);
 
 	/* We need to work out whether there's sufficient disk space to perform
 	 * the write - but we can skip that check if we have space already
@@ -539,7 +547,7 @@ int __cachefiles_prepare_write(struct cachefiles_object *object,
 
 	pos = cachefiles_inject_read_error();
 	if (pos == 0)
-		pos = vfs_llseek(file, *_start, SEEK_DATA);
+		pos = vfs_llseek(file, start, SEEK_DATA);
 	if (pos < 0 && pos >= (loff_t)-MAX_ERRNO) {
 		if (pos == -ENXIO)
 			goto check_space; /* Unallocated tail */
@@ -547,7 +555,7 @@ int __cachefiles_prepare_write(struct cachefiles_object *object,
 					  cachefiles_trace_seek_error);
 		return pos;
 	}
-	if ((u64)pos >= (u64)*_start + *_len)
+	if ((u64)pos >= (u64)start + *_len)
 		goto check_space; /* Unallocated region */
 
 	/* We have a block that's at least partially filled - if we're low on
@@ -560,13 +568,13 @@ int __cachefiles_prepare_write(struct cachefiles_object *object,
 
 	pos = cachefiles_inject_read_error();
 	if (pos == 0)
-		pos = vfs_llseek(file, *_start, SEEK_HOLE);
+		pos = vfs_llseek(file, start, SEEK_HOLE);
 	if (pos < 0 && pos >= (loff_t)-MAX_ERRNO) {
 		trace_cachefiles_io_error(object, file_inode(file), pos,
 					  cachefiles_trace_seek_error);
 		return pos;
 	}
-	if ((u64)pos >= (u64)*_start + *_len)
+	if ((u64)pos >= (u64)start + *_len)
 		return 0; /* Fully allocated */
 
 	/* Partially allocated, but insufficient space: cull. */
@@ -574,7 +582,7 @@ int __cachefiles_prepare_write(struct cachefiles_object *object,
 	ret = cachefiles_inject_remove_error();
 	if (ret == 0)
 		ret = vfs_fallocate(file, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
-				    *_start, *_len);
+				    start, *_len);
 	if (ret < 0) {
 		trace_cachefiles_io_error(object, file_inode(file), ret,
 					  cachefiles_trace_fallocate_error);
@@ -591,8 +599,8 @@ check_space:
 }
 
 static int cachefiles_prepare_write(struct netfs_cache_resources *cres,
-				    loff_t *_start, size_t *_len, loff_t i_size,
-				    bool no_space_allocated_yet)
+				    loff_t *_start, size_t *_len, size_t upper_len,
+				    loff_t i_size, bool no_space_allocated_yet)
 {
 	struct cachefiles_object *object = cachefiles_cres_object(cres);
 	struct cachefiles_cache *cache = object->volume->cache;
@@ -608,7 +616,7 @@ static int cachefiles_prepare_write(struct netfs_cache_resources *cres,
 
 	cachefiles_begin_secure(cache, &saved_cred);
 	ret = __cachefiles_prepare_write(object, cachefiles_cres_file(cres),
-					 _start, _len,
+					 _start, _len, upper_len,
 					 no_space_allocated_yet);
 	cachefiles_end_secure(cache, saved_cred);
 	return ret;
diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c
index b8fbbb1961bb..4ba42f1fa3b4 100644
--- a/fs/cachefiles/ondemand.c
+++ b/fs/cachefiles/ondemand.c
@@ -50,7 +50,7 @@ static ssize_t cachefiles_ondemand_fd_write_iter(struct kiocb *kiocb,
 		return -ENOBUFS;
 
 	cachefiles_begin_secure(cache, &saved_cred);
-	ret = __cachefiles_prepare_write(object, file, &pos, &len, true);
+	ret = __cachefiles_prepare_write(object, file, &pos, &len, len, true);
 	cachefiles_end_secure(cache, saved_cred);
 	if (ret < 0)
 		return ret;
@@ -539,6 +539,9 @@ int cachefiles_ondemand_init_object(struct cachefiles_object *object)
 	struct fscache_volume *volume = object->volume->vcookie;
 	size_t volume_key_size, cookie_key_size, data_len;
 
+	if (!object->ondemand)
+		return 0;
+
 	/*
 	 * CacheFiles will firstly check the cache file under the root cache
 	 * directory. If the coherency check failed, it will fallback to
diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig
index 94df854147d3..7249d70e1a43 100644
--- a/fs/ceph/Kconfig
+++ b/fs/ceph/Kconfig
@@ -7,6 +7,7 @@ config CEPH_FS
 	select CRYPTO_AES
 	select CRYPTO
 	select NETFS_SUPPORT
+	select FS_ENCRYPTION_ALGS if FS_ENCRYPTION
 	default n
 	help
 	  Choose Y or M here to include support for mounting the
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 13af429ab030..1340d77124ae 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -159,27 +159,7 @@ static void ceph_invalidate_folio(struct folio *folio, size_t offset,
 		ceph_put_snap_context(snapc);
 	}
 
-	folio_wait_fscache(folio);
-}
-
-static bool ceph_release_folio(struct folio *folio, gfp_t gfp)
-{
-	struct inode *inode = folio->mapping->host;
-	struct ceph_client *cl = ceph_inode_to_client(inode);
-
-	doutc(cl, "%llx.%llx idx %lu (%sdirty)\n", ceph_vinop(inode),
-	      folio->index, folio_test_dirty(folio) ? "" : "not ");
-
-	if (folio_test_private(folio))
-		return false;
-
-	if (folio_test_fscache(folio)) {
-		if (current_is_kswapd() || !(gfp & __GFP_FS))
-			return false;
-		folio_wait_fscache(folio);
-	}
-	ceph_fscache_note_page_release(inode);
-	return true;
+	netfs_invalidate_folio(folio, offset, length);
 }
 
 static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq)
@@ -357,6 +337,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	u64 len = subreq->len;
 	bool sparse = IS_ENCRYPTED(inode) || ceph_test_mount_opt(fsc, SPARSEREAD);
 	u64 off = subreq->start;
+	int extent_cnt;
 
 	if (ceph_inode_is_shutdown(inode)) {
 		err = -EIO;
@@ -370,8 +351,8 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino,
 			off, &len, 0, 1, sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ,
-			CEPH_OSD_FLAG_READ | fsc->client->osdc.client->options->read_from_replica,
-			NULL, ci->i_truncate_seq, ci->i_truncate_size, false);
+			CEPH_OSD_FLAG_READ, NULL, ci->i_truncate_seq,
+			ci->i_truncate_size, false);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		req = NULL;
@@ -379,7 +360,8 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	}
 
 	if (sparse) {
-		err = ceph_alloc_sparse_ext_map(&req->r_ops[0]);
+		extent_cnt = __ceph_sparse_read_ext_count(inode, len);
+		err = ceph_alloc_sparse_ext_map(&req->r_ops[0], extent_cnt);
 		if (err)
 			goto out;
 	}
@@ -509,7 +491,6 @@ static void ceph_netfs_free_request(struct netfs_io_request *rreq)
 const struct netfs_request_ops ceph_netfs_ops = {
 	.init_request		= ceph_init_request,
 	.free_request		= ceph_netfs_free_request,
-	.begin_cache_operation	= ceph_begin_cache_operation,
 	.issue_read		= ceph_netfs_issue_read,
 	.expand_readahead	= ceph_netfs_expand_readahead,
 	.clamp_length		= ceph_netfs_clamp_length,
@@ -1586,7 +1567,7 @@ const struct address_space_operations ceph_aops = {
 	.write_end = ceph_write_end,
 	.dirty_folio = ceph_dirty_folio,
 	.invalidate_folio = ceph_invalidate_folio,
-	.release_folio = ceph_release_folio,
+	.release_folio = netfs_release_folio,
 	.direct_IO = noop_direct_IO,
 };
 
diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
index dc502daac49a..20efac020394 100644
--- a/fs/ceph/cache.h
+++ b/fs/ceph/cache.h
@@ -43,38 +43,19 @@ static inline void ceph_fscache_resize(struct inode *inode, loff_t to)
 	}
 }
 
-static inline void ceph_fscache_unpin_writeback(struct inode *inode,
+static inline int ceph_fscache_unpin_writeback(struct inode *inode,
 						struct writeback_control *wbc)
 {
-	fscache_unpin_writeback(wbc, ceph_fscache_cookie(ceph_inode(inode)));
+	return netfs_unpin_writeback(inode, wbc);
 }
 
-static inline int ceph_fscache_dirty_folio(struct address_space *mapping,
-		struct folio *folio)
-{
-	struct ceph_inode_info *ci = ceph_inode(mapping->host);
-
-	return fscache_dirty_folio(mapping, folio, ceph_fscache_cookie(ci));
-}
-
-static inline int ceph_begin_cache_operation(struct netfs_io_request *rreq)
-{
-	struct fscache_cookie *cookie = ceph_fscache_cookie(ceph_inode(rreq->inode));
-
-	return fscache_begin_read_operation(&rreq->cache_resources, cookie);
-}
+#define ceph_fscache_dirty_folio netfs_dirty_folio
 
 static inline bool ceph_is_cache_enabled(struct inode *inode)
 {
 	return fscache_cookie_enabled(ceph_fscache_cookie(ceph_inode(inode)));
 }
 
-static inline void ceph_fscache_note_page_release(struct inode *inode)
-{
-	struct ceph_inode_info *ci = ceph_inode(inode);
-
-	fscache_note_page_release(ceph_fscache_cookie(ci));
-}
 #else /* CONFIG_CEPH_FSCACHE */
 static inline int ceph_fscache_register_fs(struct ceph_fs_client* fsc,
 					   struct fs_context *fc)
@@ -119,30 +100,18 @@ static inline void ceph_fscache_resize(struct inode *inode, loff_t to)
 {
 }
 
-static inline void ceph_fscache_unpin_writeback(struct inode *inode,
-						struct writeback_control *wbc)
+static inline int ceph_fscache_unpin_writeback(struct inode *inode,
+					       struct writeback_control *wbc)
 {
+	return 0;
 }
 
-static inline int ceph_fscache_dirty_folio(struct address_space *mapping,
-		struct folio *folio)
-{
-	return filemap_dirty_folio(mapping, folio);
-}
+#define ceph_fscache_dirty_folio filemap_dirty_folio
 
 static inline bool ceph_is_cache_enabled(struct inode *inode)
 {
 	return false;
 }
-
-static inline int ceph_begin_cache_operation(struct netfs_io_request *rreq)
-{
-	return -ENOBUFS;
-}
-
-static inline void ceph_fscache_note_page_release(struct inode *inode)
-{
-}
 #endif /* CONFIG_CEPH_FSCACHE */
 
 #endif
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 2c0b8dc3dd0d..7fb4aae97412 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1452,7 +1452,7 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap,
 	if (flushing & CEPH_CAP_XATTR_EXCL) {
 		arg->old_xattr_buf = __ceph_build_xattrs_blob(ci);
 		arg->xattr_version = ci->i_xattrs.version;
-		arg->xattr_buf = ci->i_xattrs.blob;
+		arg->xattr_buf = ceph_buffer_get(ci->i_xattrs.blob);
 	} else {
 		arg->xattr_buf = NULL;
 		arg->old_xattr_buf = NULL;
@@ -1553,6 +1553,7 @@ static void __send_cap(struct cap_msg_args *arg, struct ceph_inode_info *ci)
 	encode_cap_msg(msg, arg);
 	ceph_con_send(&arg->session->s_con, msg);
 	ceph_buffer_put(arg->old_xattr_buf);
+	ceph_buffer_put(arg->xattr_buf);
 	if (arg->wake)
 		wake_up_all(&ci->i_cap_wq);
 }
@@ -2155,6 +2156,30 @@ retry:
 		      ceph_cap_string(cap->implemented),
 		      ceph_cap_string(revoking));
 
+		/* completed revocation? going down and there are no caps? */
+		if (revoking) {
+			if ((revoking & cap_used) == 0) {
+				doutc(cl, "completed revocation of %s\n",
+				      ceph_cap_string(cap->implemented & ~cap->issued));
+				goto ack;
+			}
+
+			/*
+			 * If the "i_wrbuffer_ref" was increased by mmap or generic
+			 * cache write just before the ceph_check_caps() is called,
+			 * the Fb capability revoking will fail this time. Then we
+			 * must wait for the BDI's delayed work to flush the dirty
+			 * pages and to release the "i_wrbuffer_ref", which will cost
+			 * at most 5 seconds. That means the MDS needs to wait at
+			 * most 5 seconds to finished the Fb capability's revocation.
+			 *
+			 * Let's queue a writeback for it.
+			 */
+			if (S_ISREG(inode->i_mode) && ci->i_wrbuffer_ref &&
+			    (revoking & CEPH_CAP_FILE_BUFFER))
+				queue_writeback = true;
+		}
+
 		if (cap == ci->i_auth_cap &&
 		    (cap->issued & CEPH_CAP_FILE_WR)) {
 			/* request larger max_size from MDS? */
@@ -2182,30 +2207,6 @@ retry:
 			}
 		}
 
-		/* completed revocation? going down and there are no caps? */
-		if (revoking) {
-			if ((revoking & cap_used) == 0) {
-				doutc(cl, "completed revocation of %s\n",
-				      ceph_cap_string(cap->implemented & ~cap->issued));
-				goto ack;
-			}
-
-			/*
-			 * If the "i_wrbuffer_ref" was increased by mmap or generic
-			 * cache write just before the ceph_check_caps() is called,
-			 * the Fb capability revoking will fail this time. Then we
-			 * must wait for the BDI's delayed work to flush the dirty
-			 * pages and to release the "i_wrbuffer_ref", which will cost
-			 * at most 5 seconds. That means the MDS needs to wait at
-			 * most 5 seconds to finished the Fb capability's revocation.
-			 *
-			 * Let's queue a writeback for it.
-			 */
-			if (S_ISREG(inode->i_mode) && ci->i_wrbuffer_ref &&
-			    (revoking & CEPH_CAP_FILE_BUFFER))
-				queue_writeback = true;
-		}
-
 		/* want more caps from mds? */
 		if (want & ~cap->mds_wanted) {
 			if (want & ~(cap->mds_wanted | cap->issued))
@@ -3215,7 +3216,6 @@ static int ceph_try_drop_cap_snap(struct ceph_inode_info *ci,
 
 enum put_cap_refs_mode {
 	PUT_CAP_REFS_SYNC = 0,
-	PUT_CAP_REFS_NO_CHECK,
 	PUT_CAP_REFS_ASYNC,
 };
 
@@ -3331,11 +3331,6 @@ void ceph_put_cap_refs_async(struct ceph_inode_info *ci, int had)
 	__ceph_put_cap_refs(ci, had, PUT_CAP_REFS_ASYNC);
 }
 
-void ceph_put_cap_refs_no_check_caps(struct ceph_inode_info *ci, int had)
-{
-	__ceph_put_cap_refs(ci, had, PUT_CAP_REFS_NO_CHECK);
-}
-
 /*
  * Release @nr WRBUFFER refs on dirty pages for the given @snapc snap
  * context.  Adjust per-snap dirty page accounting as appropriate.
@@ -4777,7 +4772,22 @@ int ceph_drop_caps_for_unlink(struct inode *inode)
 		if (__ceph_caps_dirty(ci)) {
 			struct ceph_mds_client *mdsc =
 				ceph_inode_to_fs_client(inode)->mdsc;
-			__cap_delay_requeue_front(mdsc, ci);
+
+			doutc(mdsc->fsc->client, "%p %llx.%llx\n", inode,
+			      ceph_vinop(inode));
+			spin_lock(&mdsc->cap_unlink_delay_lock);
+			ci->i_ceph_flags |= CEPH_I_FLUSH;
+			if (!list_empty(&ci->i_cap_delay_list))
+				list_del_init(&ci->i_cap_delay_list);
+			list_add_tail(&ci->i_cap_delay_list,
+				      &mdsc->cap_unlink_delay_list);
+			spin_unlock(&mdsc->cap_unlink_delay_lock);
+
+			/*
+			 * Fire the work immediately, because the MDS maybe
+			 * waiting for caps release.
+			 */
+			ceph_queue_cap_unlink_work(mdsc);
 		}
 	}
 	spin_unlock(&ci->i_ceph_lock);
@@ -4887,13 +4897,15 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry,
 			       struct inode *dir,
 			       int mds, int drop, int unless)
 {
-	struct dentry *parent = NULL;
 	struct ceph_mds_request_release *rel = *p;
 	struct ceph_dentry_info *di = ceph_dentry(dentry);
 	struct ceph_client *cl;
 	int force = 0;
 	int ret;
 
+	/* This shouldn't happen */
+	BUG_ON(!dir);
+
 	/*
 	 * force an record for the directory caps if we have a dentry lease.
 	 * this is racy (can't take i_ceph_lock and d_lock together), but it
@@ -4903,14 +4915,9 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry,
 	spin_lock(&dentry->d_lock);
 	if (di->lease_session && di->lease_session->s_mds == mds)
 		force = 1;
-	if (!dir) {
-		parent = dget(dentry->d_parent);
-		dir = d_inode(parent);
-	}
 	spin_unlock(&dentry->d_lock);
 
 	ret = ceph_encode_inode_release(p, dir, mds, drop, unless, force);
-	dput(parent);
 
 	cl = ceph_inode_to_client(dir);
 	spin_lock(&dentry->d_lock);
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 678596684596..0e9f56eaba1e 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1593,10 +1593,12 @@ struct ceph_lease_walk_control {
 	unsigned long dir_lease_ttl;
 };
 
+static int __dir_lease_check(const struct dentry *, struct ceph_lease_walk_control *);
+static int __dentry_lease_check(const struct dentry *);
+
 static unsigned long
 __dentry_leases_walk(struct ceph_mds_client *mdsc,
-		     struct ceph_lease_walk_control *lwc,
-		     int (*check)(struct dentry*, void*))
+		     struct ceph_lease_walk_control *lwc)
 {
 	struct ceph_dentry_info *di, *tmp;
 	struct dentry *dentry, *last = NULL;
@@ -1624,7 +1626,10 @@ __dentry_leases_walk(struct ceph_mds_client *mdsc,
 			goto next;
 		}
 
-		ret = check(dentry, lwc);
+		if (lwc->dir_lease)
+			ret = __dir_lease_check(dentry, lwc);
+		else
+			ret = __dentry_lease_check(dentry);
 		if (ret & TOUCH) {
 			/* move it into tail of dir lease list */
 			__dentry_dir_lease_touch(mdsc, di);
@@ -1681,7 +1686,7 @@ next:
 	return freed;
 }
 
-static int __dentry_lease_check(struct dentry *dentry, void *arg)
+static int __dentry_lease_check(const struct dentry *dentry)
 {
 	struct ceph_dentry_info *di = ceph_dentry(dentry);
 	int ret;
@@ -1696,9 +1701,9 @@ static int __dentry_lease_check(struct dentry *dentry, void *arg)
 	return DELETE;
 }
 
-static int __dir_lease_check(struct dentry *dentry, void *arg)
+static int __dir_lease_check(const struct dentry *dentry,
+			     struct ceph_lease_walk_control *lwc)
 {
-	struct ceph_lease_walk_control *lwc = arg;
 	struct ceph_dentry_info *di = ceph_dentry(dentry);
 
 	int ret = __dir_lease_try_check(dentry);
@@ -1737,7 +1742,7 @@ int ceph_trim_dentries(struct ceph_mds_client *mdsc)
 
 	lwc.dir_lease = false;
 	lwc.nr_to_scan  = CEPH_CAPS_PER_RELEASE * 2;
-	freed = __dentry_leases_walk(mdsc, &lwc, __dentry_lease_check);
+	freed = __dentry_leases_walk(mdsc, &lwc);
 	if (!lwc.nr_to_scan) /* more invalid leases */
 		return -EAGAIN;
 
@@ -1747,7 +1752,7 @@ int ceph_trim_dentries(struct ceph_mds_client *mdsc)
 	lwc.dir_lease = true;
 	lwc.expire_dir_lease = freed < count;
 	lwc.dir_lease_ttl = mdsc->fsc->mount_options->caps_wanted_delay_max * HZ;
-	freed +=__dentry_leases_walk(mdsc, &lwc, __dir_lease_check);
+	freed +=__dentry_leases_walk(mdsc, &lwc);
 	if (!lwc.nr_to_scan) /* more to check */
 		return -EAGAIN;
 
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 726af69d4d62..a79f163ae4ed 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -286,8 +286,6 @@ static struct dentry *__snapfh_to_dentry(struct super_block *sb,
 		doutc(cl, "%llx.%llx parent %llx hash %x err=%d", vino.ino,
 		      vino.snap, sfh->parent_ino, sfh->hash, err);
 	}
-	if (IS_ERR(inode))
-		return ERR_CAST(inode);
 	/* see comments in ceph_get_parent() */
 	return unlinked ? d_obtain_root(inode) : d_obtain_alias(inode);
 }
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index d380d9dad0e0..abe8028d95bf 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1029,6 +1029,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 		struct ceph_osd_req_op *op;
 		u64 read_off = off;
 		u64 read_len = len;
+		int extent_cnt;
 
 		/* determine new offset/length if encrypted */
 		ceph_fscrypt_adjust_off_and_len(inode, &read_off, &read_len);
@@ -1068,7 +1069,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 
 		op = &req->r_ops[0];
 		if (sparse) {
-			ret = ceph_alloc_sparse_ext_map(op);
+			extent_cnt = __ceph_sparse_read_ext_count(inode, read_len);
+			ret = ceph_alloc_sparse_ext_map(op, extent_cnt);
 			if (ret) {
 				ceph_osdc_put_request(req);
 				break;
@@ -1465,6 +1467,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 		ssize_t len;
 		struct ceph_osd_req_op *op;
 		int readop = sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ;
+		int extent_cnt;
 
 		if (write)
 			size = min_t(u64, size, fsc->mount_options->wsize);
@@ -1528,7 +1531,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 		osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len);
 		op = &req->r_ops[0];
 		if (sparse) {
-			ret = ceph_alloc_sparse_ext_map(op);
+			extent_cnt = __ceph_sparse_read_ext_count(inode, size);
+			ret = ceph_alloc_sparse_ext_map(op, extent_cnt);
 			if (ret) {
 				ceph_osdc_put_request(req);
 				break;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 0679240f06db..7b2e77517f23 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -78,6 +78,8 @@ struct inode *ceph_new_inode(struct inode *dir, struct dentry *dentry,
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 
+	inode->i_blkbits = CEPH_FSCRYPT_BLOCK_SHIFT;
+
 	if (!S_ISLNK(*mode)) {
 		err = ceph_pre_init_acls(dir, mode, as_ctx);
 		if (err < 0)
@@ -574,7 +576,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	doutc(fsc->client, "%p\n", &ci->netfs.inode);
 
 	/* Set parameters for the netfs library */
-	netfs_inode_init(&ci->netfs, &ceph_netfs_ops);
+	netfs_inode_init(&ci->netfs, &ceph_netfs_ops, false);
 
 	spin_lock_init(&ci->i_ceph_lock);
 
@@ -694,7 +696,7 @@ void ceph_evict_inode(struct inode *inode)
 	percpu_counter_dec(&mdsc->metric.total_inodes);
 
 	truncate_inode_pages_final(&inode->i_data);
-	if (inode->i_state & I_PINNING_FSCACHE_WB)
+	if (inode->i_state & I_PINNING_NETFS_WB)
 		ceph_fscache_unuse_cookie(inode, true);
 	clear_inode(inode);
 
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index e07ad29ff8b9..ebf4ac0055dd 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -33,7 +33,7 @@ void __init ceph_flock_init(void)
 
 static void ceph_fl_copy_lock(struct file_lock *dst, struct file_lock *src)
 {
-	struct inode *inode = file_inode(dst->fl_file);
+	struct inode *inode = file_inode(dst->c.flc_file);
 	atomic_inc(&ceph_inode(inode)->i_filelock_ref);
 	dst->fl_u.ceph.inode = igrab(inode);
 }
@@ -110,17 +110,18 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct inode *inode,
 	else
 		length = fl->fl_end - fl->fl_start + 1;
 
-	owner = secure_addr(fl->fl_owner);
+	owner = secure_addr(fl->c.flc_owner);
 
 	doutc(cl, "rule: %d, op: %d, owner: %llx, pid: %llu, "
 		    "start: %llu, length: %llu, wait: %d, type: %d\n",
-		    (int)lock_type, (int)operation, owner, (u64)fl->fl_pid,
-		    fl->fl_start, length, wait, fl->fl_type);
+		    (int)lock_type, (int)operation, owner,
+		    (u64) fl->c.flc_pid,
+		    fl->fl_start, length, wait, fl->c.flc_type);
 
 	req->r_args.filelock_change.rule = lock_type;
 	req->r_args.filelock_change.type = cmd;
 	req->r_args.filelock_change.owner = cpu_to_le64(owner);
-	req->r_args.filelock_change.pid = cpu_to_le64((u64)fl->fl_pid);
+	req->r_args.filelock_change.pid = cpu_to_le64((u64) fl->c.flc_pid);
 	req->r_args.filelock_change.start = cpu_to_le64(fl->fl_start);
 	req->r_args.filelock_change.length = cpu_to_le64(length);
 	req->r_args.filelock_change.wait = wait;
@@ -130,13 +131,13 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct inode *inode,
 		err = ceph_mdsc_wait_request(mdsc, req, wait ?
 					ceph_lock_wait_for_completion : NULL);
 	if (!err && operation == CEPH_MDS_OP_GETFILELOCK) {
-		fl->fl_pid = -le64_to_cpu(req->r_reply_info.filelock_reply->pid);
+		fl->c.flc_pid = -le64_to_cpu(req->r_reply_info.filelock_reply->pid);
 		if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type)
-			fl->fl_type = F_RDLCK;
+			fl->c.flc_type = F_RDLCK;
 		else if (CEPH_LOCK_EXCL == req->r_reply_info.filelock_reply->type)
-			fl->fl_type = F_WRLCK;
+			fl->c.flc_type = F_WRLCK;
 		else
-			fl->fl_type = F_UNLCK;
+			fl->c.flc_type = F_UNLCK;
 
 		fl->fl_start = le64_to_cpu(req->r_reply_info.filelock_reply->start);
 		length = le64_to_cpu(req->r_reply_info.filelock_reply->start) +
@@ -150,8 +151,8 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct inode *inode,
 	ceph_mdsc_put_request(req);
 	doutc(cl, "rule: %d, op: %d, pid: %llu, start: %llu, "
 	      "length: %llu, wait: %d, type: %d, err code %d\n",
-	      (int)lock_type, (int)operation, (u64)fl->fl_pid,
-	      fl->fl_start, length, wait, fl->fl_type, err);
+	      (int)lock_type, (int)operation, (u64) fl->c.flc_pid,
+	      fl->fl_start, length, wait, fl->c.flc_type, err);
 	return err;
 }
 
@@ -227,10 +228,10 @@ static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc,
 static int try_unlock_file(struct file *file, struct file_lock *fl)
 {
 	int err;
-	unsigned int orig_flags = fl->fl_flags;
-	fl->fl_flags |= FL_EXISTS;
+	unsigned int orig_flags = fl->c.flc_flags;
+	fl->c.flc_flags |= FL_EXISTS;
 	err = locks_lock_file_wait(file, fl);
-	fl->fl_flags = orig_flags;
+	fl->c.flc_flags = orig_flags;
 	if (err == -ENOENT) {
 		if (!(orig_flags & FL_EXISTS))
 			err = 0;
@@ -253,13 +254,13 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
 	u8 wait = 0;
 	u8 lock_cmd;
 
-	if (!(fl->fl_flags & FL_POSIX))
+	if (!(fl->c.flc_flags & FL_POSIX))
 		return -ENOLCK;
 
 	if (ceph_inode_is_shutdown(inode))
 		return -ESTALE;
 
-	doutc(cl, "fl_owner: %p\n", fl->fl_owner);
+	doutc(cl, "fl_owner: %p\n", fl->c.flc_owner);
 
 	/* set wait bit as appropriate, then make command as Ceph expects it*/
 	if (IS_GETLK(cmd))
@@ -273,19 +274,19 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
 	}
 	spin_unlock(&ci->i_ceph_lock);
 	if (err < 0) {
-		if (op == CEPH_MDS_OP_SETFILELOCK && F_UNLCK == fl->fl_type)
+		if (op == CEPH_MDS_OP_SETFILELOCK && lock_is_unlock(fl))
 			posix_lock_file(file, fl, NULL);
 		return err;
 	}
 
-	if (F_RDLCK == fl->fl_type)
+	if (lock_is_read(fl))
 		lock_cmd = CEPH_LOCK_SHARED;
-	else if (F_WRLCK == fl->fl_type)
+	else if (lock_is_write(fl))
 		lock_cmd = CEPH_LOCK_EXCL;
 	else
 		lock_cmd = CEPH_LOCK_UNLOCK;
 
-	if (op == CEPH_MDS_OP_SETFILELOCK && F_UNLCK == fl->fl_type) {
+	if (op == CEPH_MDS_OP_SETFILELOCK && lock_is_unlock(fl)) {
 		err = try_unlock_file(file, fl);
 		if (err <= 0)
 			return err;
@@ -293,7 +294,7 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
 
 	err = ceph_lock_message(CEPH_LOCK_FCNTL, op, inode, lock_cmd, wait, fl);
 	if (!err) {
-		if (op == CEPH_MDS_OP_SETFILELOCK && F_UNLCK != fl->fl_type) {
+		if (op == CEPH_MDS_OP_SETFILELOCK && F_UNLCK != fl->c.flc_type) {
 			doutc(cl, "locking locally\n");
 			err = posix_lock_file(file, fl, NULL);
 			if (err) {
@@ -319,13 +320,13 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 	u8 wait = 0;
 	u8 lock_cmd;
 
-	if (!(fl->fl_flags & FL_FLOCK))
+	if (!(fl->c.flc_flags & FL_FLOCK))
 		return -ENOLCK;
 
 	if (ceph_inode_is_shutdown(inode))
 		return -ESTALE;
 
-	doutc(cl, "fl_file: %p\n", fl->fl_file);
+	doutc(cl, "fl_file: %p\n", fl->c.flc_file);
 
 	spin_lock(&ci->i_ceph_lock);
 	if (ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) {
@@ -333,7 +334,7 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 	}
 	spin_unlock(&ci->i_ceph_lock);
 	if (err < 0) {
-		if (F_UNLCK == fl->fl_type)
+		if (lock_is_unlock(fl))
 			locks_lock_file_wait(file, fl);
 		return err;
 	}
@@ -341,14 +342,14 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 	if (IS_SETLKW(cmd))
 		wait = 1;
 
-	if (F_RDLCK == fl->fl_type)
+	if (lock_is_read(fl))
 		lock_cmd = CEPH_LOCK_SHARED;
-	else if (F_WRLCK == fl->fl_type)
+	else if (lock_is_write(fl))
 		lock_cmd = CEPH_LOCK_EXCL;
 	else
 		lock_cmd = CEPH_LOCK_UNLOCK;
 
-	if (F_UNLCK == fl->fl_type) {
+	if (lock_is_unlock(fl)) {
 		err = try_unlock_file(file, fl);
 		if (err <= 0)
 			return err;
@@ -356,7 +357,7 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 
 	err = ceph_lock_message(CEPH_LOCK_FLOCK, CEPH_MDS_OP_SETFILELOCK,
 				inode, lock_cmd, wait, fl);
-	if (!err && F_UNLCK != fl->fl_type) {
+	if (!err && F_UNLCK != fl->c.flc_type) {
 		err = locks_lock_file_wait(file, fl);
 		if (err) {
 			ceph_lock_message(CEPH_LOCK_FLOCK,
@@ -385,9 +386,9 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
 	ctx = locks_inode_context(inode);
 	if (ctx) {
 		spin_lock(&ctx->flc_lock);
-		list_for_each_entry(lock, &ctx->flc_posix, fl_list)
+		for_each_file_lock(lock, &ctx->flc_posix)
 			++(*fcntl_count);
-		list_for_each_entry(lock, &ctx->flc_flock, fl_list)
+		for_each_file_lock(lock, &ctx->flc_flock)
 			++(*flock_count);
 		spin_unlock(&ctx->flc_lock);
 	}
@@ -408,10 +409,10 @@ static int lock_to_ceph_filelock(struct inode *inode,
 	cephlock->start = cpu_to_le64(lock->fl_start);
 	cephlock->length = cpu_to_le64(lock->fl_end - lock->fl_start + 1);
 	cephlock->client = cpu_to_le64(0);
-	cephlock->pid = cpu_to_le64((u64)lock->fl_pid);
-	cephlock->owner = cpu_to_le64(secure_addr(lock->fl_owner));
+	cephlock->pid = cpu_to_le64((u64) lock->c.flc_pid);
+	cephlock->owner = cpu_to_le64(secure_addr(lock->c.flc_owner));
 
-	switch (lock->fl_type) {
+	switch (lock->c.flc_type) {
 	case F_RDLCK:
 		cephlock->type = CEPH_LOCK_SHARED;
 		break;
@@ -422,7 +423,8 @@ static int lock_to_ceph_filelock(struct inode *inode,
 		cephlock->type = CEPH_LOCK_UNLOCK;
 		break;
 	default:
-		doutc(cl, "Have unknown lock type %d\n", lock->fl_type);
+		doutc(cl, "Have unknown lock type %d\n",
+		      lock->c.flc_type);
 		err = -EINVAL;
 	}
 
@@ -453,7 +455,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 		return 0;
 
 	spin_lock(&ctx->flc_lock);
-	list_for_each_entry(lock, &ctx->flc_posix, fl_list) {
+	for_each_file_lock(lock, &ctx->flc_posix) {
 		++seen_fcntl;
 		if (seen_fcntl > num_fcntl_locks) {
 			err = -ENOSPC;
@@ -464,7 +466,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 			goto fail;
 		++l;
 	}
-	list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
+	for_each_file_lock(lock, &ctx->flc_flock) {
 		++seen_flock;
 		if (seen_flock > num_flock_locks) {
 			err = -ENOSPC;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 02ebfabfc8ee..3ab9c268a8bb 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1089,7 +1089,7 @@ void ceph_mdsc_release_request(struct kref *kref)
 	struct ceph_mds_request *req = container_of(kref,
 						    struct ceph_mds_request,
 						    r_kref);
-	ceph_mdsc_release_dir_caps_no_check(req);
+	ceph_mdsc_release_dir_caps_async(req);
 	destroy_reply_info(&req->r_reply_info);
 	if (req->r_request)
 		ceph_msg_put(req->r_request);
@@ -1534,7 +1534,8 @@ static int encode_metric_spec(void **p, void *end)
  * session message, specialization for CEPH_SESSION_REQUEST_OPEN
  * to include additional client metadata fields.
  */
-static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u64 seq)
+static struct ceph_msg *
+create_session_full_msg(struct ceph_mds_client *mdsc, int op, u64 seq)
 {
 	struct ceph_msg *msg;
 	struct ceph_mds_session_head *h;
@@ -1578,6 +1579,9 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 		size = METRIC_BYTES(count);
 	extra_bytes += 2 + 4 + 4 + size;
 
+	/* flags, mds auth caps and oldest_client_tid */
+	extra_bytes += 4 + 4 + 8;
+
 	/* Allocate the message */
 	msg = ceph_msg_new(CEPH_MSG_CLIENT_SESSION, sizeof(*h) + extra_bytes,
 			   GFP_NOFS, false);
@@ -1589,16 +1593,16 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 	end = p + msg->front.iov_len;
 
 	h = p;
-	h->op = cpu_to_le32(CEPH_SESSION_REQUEST_OPEN);
+	h->op = cpu_to_le32(op);
 	h->seq = cpu_to_le64(seq);
 
 	/*
 	 * Serialize client metadata into waiting buffer space, using
 	 * the format that userspace expects for map<string, string>
 	 *
-	 * ClientSession messages with metadata are v4
+	 * ClientSession messages with metadata are v7
 	 */
-	msg->hdr.version = cpu_to_le16(4);
+	msg->hdr.version = cpu_to_le16(7);
 	msg->hdr.compat_version = cpu_to_le16(1);
 
 	/* The write pointer, following the session_head structure */
@@ -1634,6 +1638,15 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 		return ERR_PTR(ret);
 	}
 
+	/* version == 5, flags */
+	ceph_encode_32(&p, 0);
+
+	/* version == 6, mds auth caps */
+	ceph_encode_32(&p, 0);
+
+	/* version == 7, oldest_client_tid */
+	ceph_encode_64(&p, mdsc->oldest_tid);
+
 	msg->front.iov_len = p - msg->front.iov_base;
 	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
 
@@ -1663,7 +1676,8 @@ static int __open_session(struct ceph_mds_client *mdsc,
 	session->s_renew_requested = jiffies;
 
 	/* send connect message */
-	msg = create_session_open_msg(mdsc, session->s_seq);
+	msg = create_session_full_msg(mdsc, CEPH_SESSION_REQUEST_OPEN,
+				      session->s_seq);
 	if (IS_ERR(msg))
 		return PTR_ERR(msg);
 	ceph_con_send(&session->s_con, msg);
@@ -2028,10 +2042,10 @@ static int send_renew_caps(struct ceph_mds_client *mdsc,
 
 	doutc(cl, "to mds%d (%s)\n", session->s_mds,
 	      ceph_mds_state_name(state));
-	msg = ceph_create_session_msg(CEPH_SESSION_REQUEST_RENEWCAPS,
+	msg = create_session_full_msg(mdsc, CEPH_SESSION_REQUEST_RENEWCAPS,
 				      ++session->s_renew_seq);
-	if (!msg)
-		return -ENOMEM;
+	if (IS_ERR(msg))
+		return PTR_ERR(msg);
 	ceph_con_send(&session->s_con, msg);
 	return 0;
 }
@@ -2470,6 +2484,50 @@ void ceph_reclaim_caps_nr(struct ceph_mds_client *mdsc, int nr)
 	}
 }
 
+void ceph_queue_cap_unlink_work(struct ceph_mds_client *mdsc)
+{
+	struct ceph_client *cl = mdsc->fsc->client;
+	if (mdsc->stopping)
+		return;
+
+        if (queue_work(mdsc->fsc->cap_wq, &mdsc->cap_unlink_work)) {
+                doutc(cl, "caps unlink work queued\n");
+        } else {
+                doutc(cl, "failed to queue caps unlink work\n");
+        }
+}
+
+static void ceph_cap_unlink_work(struct work_struct *work)
+{
+	struct ceph_mds_client *mdsc =
+		container_of(work, struct ceph_mds_client, cap_unlink_work);
+	struct ceph_client *cl = mdsc->fsc->client;
+
+	doutc(cl, "begin\n");
+	spin_lock(&mdsc->cap_unlink_delay_lock);
+	while (!list_empty(&mdsc->cap_unlink_delay_list)) {
+		struct ceph_inode_info *ci;
+		struct inode *inode;
+
+		ci = list_first_entry(&mdsc->cap_unlink_delay_list,
+				      struct ceph_inode_info,
+				      i_cap_delay_list);
+		list_del_init(&ci->i_cap_delay_list);
+
+		inode = igrab(&ci->netfs.inode);
+		if (inode) {
+			spin_unlock(&mdsc->cap_unlink_delay_lock);
+			doutc(cl, "on %p %llx.%llx\n", inode,
+			      ceph_vinop(inode));
+			ceph_check_caps(ci, CHECK_CAPS_FLUSH);
+			iput(inode);
+			spin_lock(&mdsc->cap_unlink_delay_lock);
+		}
+	}
+	spin_unlock(&mdsc->cap_unlink_delay_lock);
+	doutc(cl, "done\n");
+}
+
 /*
  * requests
  */
@@ -4128,12 +4186,12 @@ static void handle_session(struct ceph_mds_session *session,
 			pr_info_client(cl, "mds%d reconnect success\n",
 				       session->s_mds);
 
+		session->s_features = features;
 		if (session->s_state == CEPH_MDS_SESSION_OPEN) {
 			pr_notice_client(cl, "mds%d is already opened\n",
 					 session->s_mds);
 		} else {
 			session->s_state = CEPH_MDS_SESSION_OPEN;
-			session->s_features = features;
 			renewed_caps(mdsc, session, 0);
 			if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT,
 				     &session->s_features))
@@ -4247,7 +4305,7 @@ void ceph_mdsc_release_dir_caps(struct ceph_mds_request *req)
 	}
 }
 
-void ceph_mdsc_release_dir_caps_no_check(struct ceph_mds_request *req)
+void ceph_mdsc_release_dir_caps_async(struct ceph_mds_request *req)
 {
 	struct ceph_client *cl = req->r_mdsc->fsc->client;
 	int dcaps;
@@ -4255,8 +4313,7 @@ void ceph_mdsc_release_dir_caps_no_check(struct ceph_mds_request *req)
 	dcaps = xchg(&req->r_dir_caps, 0);
 	if (dcaps) {
 		doutc(cl, "releasing r_dir_caps=%s\n", ceph_cap_string(dcaps));
-		ceph_put_cap_refs_no_check_caps(ceph_inode(req->r_parent),
-						dcaps);
+		ceph_put_cap_refs_async(ceph_inode(req->r_parent), dcaps);
 	}
 }
 
@@ -4292,7 +4349,7 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc,
 		if (req->r_session->s_mds != session->s_mds)
 			continue;
 
-		ceph_mdsc_release_dir_caps_no_check(req);
+		ceph_mdsc_release_dir_caps_async(req);
 
 		__send_request(session, req, true);
 	}
@@ -5346,6 +5403,8 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
 	INIT_LIST_HEAD(&mdsc->cap_delay_list);
 	INIT_LIST_HEAD(&mdsc->cap_wait_list);
 	spin_lock_init(&mdsc->cap_delay_lock);
+	INIT_LIST_HEAD(&mdsc->cap_unlink_delay_list);
+	spin_lock_init(&mdsc->cap_unlink_delay_lock);
 	INIT_LIST_HEAD(&mdsc->snap_flush_list);
 	spin_lock_init(&mdsc->snap_flush_lock);
 	mdsc->last_cap_flush_tid = 1;
@@ -5354,6 +5413,7 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
 	spin_lock_init(&mdsc->cap_dirty_lock);
 	init_waitqueue_head(&mdsc->cap_flushing_wq);
 	INIT_WORK(&mdsc->cap_reclaim_work, ceph_cap_reclaim_work);
+	INIT_WORK(&mdsc->cap_unlink_work, ceph_cap_unlink_work);
 	err = ceph_metric_init(&mdsc->metric);
 	if (err)
 		goto err_mdsmap;
@@ -5627,6 +5687,7 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc)
 	ceph_cleanup_global_and_empty_realms(mdsc);
 
 	cancel_work_sync(&mdsc->cap_reclaim_work);
+	cancel_work_sync(&mdsc->cap_unlink_work);
 	cancel_delayed_work_sync(&mdsc->delayed_work); /* cancel timer */
 
 	doutc(cl, "done\n");
@@ -5870,7 +5931,8 @@ static void mds_peer_reset(struct ceph_connection *con)
 
 	pr_warn_client(mdsc->fsc->client, "mds%d closed our session\n",
 		       s->s_mds);
-	if (READ_ONCE(mdsc->fsc->mount_state) != CEPH_MOUNT_FENCE_IO)
+	if (READ_ONCE(mdsc->fsc->mount_state) != CEPH_MOUNT_FENCE_IO &&
+	    ceph_mdsmap_get_state(mdsc->mdsmap, s->s_mds) >= CEPH_MDS_STATE_RECONNECT)
 		send_mds_reconnect(mdsc, s);
 }
 
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 2e6ddaa13d72..03f8ff00874f 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -462,6 +462,8 @@ struct ceph_mds_client {
 	unsigned long    last_renew_caps;  /* last time we renewed our caps */
 	struct list_head cap_delay_list;   /* caps with delayed release */
 	spinlock_t       cap_delay_lock;   /* protects cap_delay_list */
+	struct list_head cap_unlink_delay_list;  /* caps with delayed release for unlink */
+	spinlock_t       cap_unlink_delay_lock;  /* protects cap_unlink_delay_list */
 	struct list_head snap_flush_list;  /* cap_snaps ready to flush */
 	spinlock_t       snap_flush_lock;
 
@@ -475,6 +477,8 @@ struct ceph_mds_client {
 	struct work_struct cap_reclaim_work;
 	atomic_t	   cap_reclaim_pending;
 
+	struct work_struct cap_unlink_work;
+
 	/*
 	 * Cap reservations
 	 *
@@ -552,7 +556,7 @@ extern int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
 				struct inode *dir,
 				struct ceph_mds_request *req);
 extern void ceph_mdsc_release_dir_caps(struct ceph_mds_request *req);
-extern void ceph_mdsc_release_dir_caps_no_check(struct ceph_mds_request *req);
+extern void ceph_mdsc_release_dir_caps_async(struct ceph_mds_request *req);
 static inline void ceph_mdsc_get_request(struct ceph_mds_request *req)
 {
 	kref_get(&req->r_kref);
@@ -574,6 +578,7 @@ extern void ceph_flush_cap_releases(struct ceph_mds_client *mdsc,
 				    struct ceph_mds_session *session);
 extern void ceph_queue_cap_reclaim_work(struct ceph_mds_client *mdsc);
 extern void ceph_reclaim_caps_nr(struct ceph_mds_client *mdsc, int nr);
+extern void ceph_queue_cap_unlink_work(struct ceph_mds_client *mdsc);
 extern int ceph_iterate_session_caps(struct ceph_mds_session *session,
 				     int (*cb)(struct inode *, int mds, void *),
 				     void *arg);
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index fae97c25ce58..8109aba66e02 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -380,10 +380,11 @@ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p,
 		ceph_decode_skip_8(p, end, bad_ext);
 		/* required_client_features */
 		ceph_decode_skip_set(p, end, 64, bad_ext);
+		/* bal_rank_mask */
+		ceph_decode_skip_string(p, end, bad_ext);
+	}
+	if (mdsmap_ev >= 18) {
 		ceph_decode_64_safe(p, end, m->m_max_xattr_size, bad_ext);
-	} else {
-		/* This forces the usage of the (sync) SETXATTR Op */
-		m->m_max_xattr_size = 0;
 	}
 bad_ext:
 	doutc(cl, "m_enabled: %d, m_damaged: %d, m_num_laggy: %d\n",
diff --git a/fs/ceph/mdsmap.h b/fs/ceph/mdsmap.h
index 89f1931f1ba6..1f2171dd01bf 100644
--- a/fs/ceph/mdsmap.h
+++ b/fs/ceph/mdsmap.h
@@ -27,7 +27,11 @@ struct ceph_mdsmap {
 	u32 m_session_timeout;          /* seconds */
 	u32 m_session_autoclose;        /* seconds */
 	u64 m_max_file_size;
-	u64 m_max_xattr_size;		/* maximum size for xattrs blob */
+	/*
+	 * maximum size for xattrs blob.
+	 * Zeroed by default to force the usage of the (sync) SETXATTR Op.
+	 */
+	u64 m_max_xattr_size;
 	u32 m_max_mds;			/* expected up:active mds number */
 	u32 m_num_active_mds;		/* actual up:active mds number */
 	u32 possible_max_rank;		/* possible max rank index */
diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c
index 9d36c3532de1..06ee397e0c3a 100644
--- a/fs/ceph/quota.c
+++ b/fs/ceph/quota.c
@@ -197,10 +197,10 @@ void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc)
 }
 
 /*
- * This function walks through the snaprealm for an inode and returns the
- * ceph_snap_realm for the first snaprealm that has quotas set (max_files,
+ * This function walks through the snaprealm for an inode and set the
+ * realmp with the first snaprealm that has quotas set (max_files,
  * max_bytes, or any, depending on the 'which_quota' argument).  If the root is
- * reached, return the root ceph_snap_realm instead.
+ * reached, set the realmp with the root ceph_snap_realm instead.
  *
  * Note that the caller is responsible for calling ceph_put_snap_realm() on the
  * returned realm.
@@ -211,10 +211,9 @@ void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc)
  * this function will return -EAGAIN; otherwise, the snaprealms walk-through
  * will be restarted.
  */
-static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc,
-					       struct inode *inode,
-					       enum quota_get_realm which_quota,
-					       bool retry)
+static int get_quota_realm(struct ceph_mds_client *mdsc, struct inode *inode,
+			   enum quota_get_realm which_quota,
+			   struct ceph_snap_realm **realmp, bool retry)
 {
 	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_inode_info *ci = NULL;
@@ -222,8 +221,10 @@ static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc,
 	struct inode *in;
 	bool has_quota;
 
+	if (realmp)
+		*realmp = NULL;
 	if (ceph_snap(inode) != CEPH_NOSNAP)
-		return NULL;
+		return 0;
 
 restart:
 	realm = ceph_inode(inode)->i_snap_realm;
@@ -250,7 +251,7 @@ restart:
 				break;
 			ceph_put_snap_realm(mdsc, realm);
 			if (!retry)
-				return ERR_PTR(-EAGAIN);
+				return -EAGAIN;
 			goto restart;
 		}
 
@@ -259,8 +260,11 @@ restart:
 		iput(in);
 
 		next = realm->parent;
-		if (has_quota || !next)
-		       return realm;
+		if (has_quota || !next) {
+			if (realmp)
+				*realmp = realm;
+			return 0;
+		}
 
 		ceph_get_snap_realm(mdsc, next);
 		ceph_put_snap_realm(mdsc, realm);
@@ -269,7 +273,7 @@ restart:
 	if (realm)
 		ceph_put_snap_realm(mdsc, realm);
 
-	return NULL;
+	return 0;
 }
 
 bool ceph_quota_is_same_realm(struct inode *old, struct inode *new)
@@ -277,6 +281,7 @@ bool ceph_quota_is_same_realm(struct inode *old, struct inode *new)
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(old->i_sb);
 	struct ceph_snap_realm *old_realm, *new_realm;
 	bool is_same;
+	int ret;
 
 restart:
 	/*
@@ -286,9 +291,9 @@ restart:
 	 * dropped and we can then restart the whole operation.
 	 */
 	down_read(&mdsc->snap_rwsem);
-	old_realm = get_quota_realm(mdsc, old, QUOTA_GET_ANY, true);
-	new_realm = get_quota_realm(mdsc, new, QUOTA_GET_ANY, false);
-	if (PTR_ERR(new_realm) == -EAGAIN) {
+	get_quota_realm(mdsc, old, QUOTA_GET_ANY, &old_realm, true);
+	ret = get_quota_realm(mdsc, new, QUOTA_GET_ANY, &new_realm, false);
+	if (ret == -EAGAIN) {
 		up_read(&mdsc->snap_rwsem);
 		if (old_realm)
 			ceph_put_snap_realm(mdsc, old_realm);
@@ -492,8 +497,8 @@ bool ceph_quota_update_statfs(struct ceph_fs_client *fsc, struct kstatfs *buf)
 	bool is_updated = false;
 
 	down_read(&mdsc->snap_rwsem);
-	realm = get_quota_realm(mdsc, d_inode(fsc->sb->s_root),
-				QUOTA_GET_MAX_BYTES, true);
+	get_quota_realm(mdsc, d_inode(fsc->sb->s_root), QUOTA_GET_MAX_BYTES,
+			&realm, true);
 	up_read(&mdsc->snap_rwsem);
 	if (!realm)
 		return false;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index fe0f64a0acb2..b63b4cd9b5b6 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -3,6 +3,7 @@
 #define _FS_CEPH_SUPER_H
 
 #include <linux/ceph/ceph_debug.h>
+#include <linux/ceph/osd_client.h>
 
 #include <asm/unaligned.h>
 #include <linux/backing-dev.h>
@@ -1254,8 +1255,6 @@ extern void ceph_take_cap_refs(struct ceph_inode_info *ci, int caps,
 extern void ceph_get_cap_refs(struct ceph_inode_info *ci, int caps);
 extern void ceph_put_cap_refs(struct ceph_inode_info *ci, int had);
 extern void ceph_put_cap_refs_async(struct ceph_inode_info *ci, int had);
-extern void ceph_put_cap_refs_no_check_caps(struct ceph_inode_info *ci,
-					    int had);
 extern void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 				       struct ceph_snap_context *snapc);
 extern void __ceph_remove_capsnap(struct inode *inode,
@@ -1407,6 +1406,19 @@ static inline void __ceph_update_quota(struct ceph_inode_info *ci,
 		ceph_adjust_quota_realms_count(&ci->netfs.inode, has_quota);
 }
 
+static inline int __ceph_sparse_read_ext_count(struct inode *inode, u64 len)
+{
+	int cnt = 0;
+
+	if (IS_ENCRYPTED(inode)) {
+		cnt = len >> CEPH_FSCRYPT_BLOCK_SHIFT;
+		if (cnt > CEPH_SPARSE_EXT_ARRAY_INITIAL)
+			cnt = 0;
+	}
+
+	return cnt;
+}
+
 extern void ceph_handle_quota(struct ceph_mds_client *mdsc,
 			      struct ceph_mds_session *session,
 			      struct ceph_msg *msg);
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index 0c7c2528791e..a50356c541f6 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -24,6 +24,8 @@
 #include <linux/pid_namespace.h>
 #include <linux/uaccess.h>
 #include <linux/fs.h>
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
 #include <linux/vmalloc.h>
 
 #include <linux/coda.h>
@@ -87,10 +89,10 @@ void coda_destroy_inodecache(void)
 	kmem_cache_destroy(coda_inode_cachep);
 }
 
-static int coda_remount(struct super_block *sb, int *flags, char *data)
+static int coda_reconfigure(struct fs_context *fc)
 {
-	sync_filesystem(sb);
-	*flags |= SB_NOATIME;
+	sync_filesystem(fc->root->d_sb);
+	fc->sb_flags |= SB_NOATIME;
 	return 0;
 }
 
@@ -102,78 +104,102 @@ static const struct super_operations coda_super_operations =
 	.evict_inode	= coda_evict_inode,
 	.put_super	= coda_put_super,
 	.statfs		= coda_statfs,
-	.remount_fs	= coda_remount,
 };
 
-static int get_device_index(struct coda_mount_data *data)
+struct coda_fs_context {
+	int	idx;
+};
+
+enum {
+	Opt_fd,
+};
+
+static const struct fs_parameter_spec coda_param_specs[] = {
+	fsparam_fd	("fd",	Opt_fd),
+	{}
+};
+
+static int coda_parse_fd(struct fs_context *fc, int fd)
 {
+	struct coda_fs_context *ctx = fc->fs_private;
 	struct fd f;
 	struct inode *inode;
 	int idx;
 
-	if (data == NULL) {
-		pr_warn("%s: Bad mount data\n", __func__);
-		return -1;
-	}
-
-	if (data->version != CODA_MOUNT_VERSION) {
-		pr_warn("%s: Bad mount version\n", __func__);
-		return -1;
-	}
-
-	f = fdget(data->fd);
+	f = fdget(fd);
 	if (!f.file)
-		goto Ebadf;
+		return -EBADF;
 	inode = file_inode(f.file);
 	if (!S_ISCHR(inode->i_mode) || imajor(inode) != CODA_PSDEV_MAJOR) {
 		fdput(f);
-		goto Ebadf;
+		return invalf(fc, "code: Not coda psdev");
 	}
 
 	idx = iminor(inode);
 	fdput(f);
 
-	if (idx < 0 || idx >= MAX_CODADEVS) {
-		pr_warn("%s: Bad minor number\n", __func__);
-		return -1;
+	if (idx < 0 || idx >= MAX_CODADEVS)
+		return invalf(fc, "coda: Bad minor number");
+	ctx->idx = idx;
+	return 0;
+}
+
+static int coda_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct fs_parse_result result;
+	int opt;
+
+	opt = fs_parse(fc, coda_param_specs, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_fd:
+		return coda_parse_fd(fc, result.uint_32);
 	}
 
-	return idx;
-Ebadf:
-	pr_warn("%s: Bad file\n", __func__);
-	return -1;
+	return 0;
+}
+
+/*
+ * Parse coda's binary mount data form.  We ignore any errors and go with index
+ * 0 if we get one for backward compatibility.
+ */
+static int coda_parse_monolithic(struct fs_context *fc, void *_data)
+{
+	struct coda_mount_data *data = _data;
+
+	if (!data)
+		return invalf(fc, "coda: Bad mount data");
+
+	if (data->version != CODA_MOUNT_VERSION)
+		return invalf(fc, "coda: Bad mount version");
+
+	coda_parse_fd(fc, data->fd);
+	return 0;
 }
 
-static int coda_fill_super(struct super_block *sb, void *data, int silent)
+static int coda_fill_super(struct super_block *sb, struct fs_context *fc)
 {
+	struct coda_fs_context *ctx = fc->fs_private;
 	struct inode *root = NULL;
 	struct venus_comm *vc;
 	struct CodaFid fid;
 	int error;
-	int idx;
-
-	if (task_active_pid_ns(current) != &init_pid_ns)
-		return -EINVAL;
-
-	idx = get_device_index((struct coda_mount_data *) data);
 
-	/* Ignore errors in data, for backward compatibility */
-	if(idx == -1)
-		idx = 0;
-	
-	pr_info("%s: device index: %i\n", __func__,  idx);
+	infof(fc, "coda: device index: %i\n", ctx->idx);
 
-	vc = &coda_comms[idx];
+	vc = &coda_comms[ctx->idx];
 	mutex_lock(&vc->vc_mutex);
 
 	if (!vc->vc_inuse) {
-		pr_warn("%s: No pseudo device\n", __func__);
+		errorf(fc, "coda: No pseudo device");
 		error = -EINVAL;
 		goto unlock_out;
 	}
 
 	if (vc->vc_sb) {
-		pr_warn("%s: Device already mounted\n", __func__);
+		errorf(fc, "coda: Device already mounted");
 		error = -EBUSY;
 		goto unlock_out;
 	}
@@ -313,18 +339,45 @@ static int coda_statfs(struct dentry *dentry, struct kstatfs *buf)
 	return 0; 
 }
 
-/* init_coda: used by filesystems.c to register coda */
+static int coda_get_tree(struct fs_context *fc)
+{
+	if (task_active_pid_ns(current) != &init_pid_ns)
+		return -EINVAL;
 
-static struct dentry *coda_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+	return get_tree_nodev(fc, coda_fill_super);
+}
+
+static void coda_free_fc(struct fs_context *fc)
 {
-	return mount_nodev(fs_type, flags, data, coda_fill_super);
+	kfree(fc->fs_private);
+}
+
+static const struct fs_context_operations coda_context_ops = {
+	.free		= coda_free_fc,
+	.parse_param	= coda_parse_param,
+	.parse_monolithic = coda_parse_monolithic,
+	.get_tree	= coda_get_tree,
+	.reconfigure	= coda_reconfigure,
+};
+
+static int coda_init_fs_context(struct fs_context *fc)
+{
+	struct coda_fs_context *ctx;
+
+	ctx = kzalloc(sizeof(struct coda_fs_context), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	fc->fs_private = ctx;
+	fc->ops = &coda_context_ops;
+	return 0;
 }
 
 struct file_system_type coda_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "coda",
-	.mount		= coda_mount,
+	.init_fs_context = coda_init_fs_context,
+	.parameters	= coda_param_specs,
 	.kill_sb	= kill_anon_super,
 	.fs_flags	= FS_BINARY_MOUNTDATA,
 };
diff --git a/fs/coredump.c b/fs/coredump.c
index f258c17c1841..be6403b4b14b 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -872,6 +872,9 @@ static int dump_emit_page(struct coredump_params *cprm, struct page *page)
 	loff_t pos;
 	ssize_t n;
 
+	if (!page)
+		return 0;
+
 	if (cprm->to_skip) {
 		if (!__dump_skip(cprm, cprm->to_skip))
 			return 0;
@@ -884,7 +887,6 @@ static int dump_emit_page(struct coredump_params *cprm, struct page *page)
 	pos = file->f_pos;
 	bvec_set_page(&bvec, page, PAGE_SIZE, 0);
 	iov_iter_bvec(&iter, ITER_SOURCE, &bvec, 1, PAGE_SIZE);
-	iov_iter_set_copy_mc(&iter);
 	n = __kernel_write_iter(cprm->file, &iter, &pos);
 	if (n != PAGE_SIZE)
 		return 0;
@@ -895,10 +897,44 @@ static int dump_emit_page(struct coredump_params *cprm, struct page *page)
 	return 1;
 }
 
+/*
+ * If we might get machine checks from kernel accesses during the
+ * core dump, let's get those errors early rather than during the
+ * IO. This is not performance-critical enough to warrant having
+ * all the machine check logic in the iovec paths.
+ */
+#ifdef copy_mc_to_kernel
+
+#define dump_page_alloc() alloc_page(GFP_KERNEL)
+#define dump_page_free(x) __free_page(x)
+static struct page *dump_page_copy(struct page *src, struct page *dst)
+{
+	void *buf = kmap_local_page(src);
+	size_t left = copy_mc_to_kernel(page_address(dst), buf, PAGE_SIZE);
+	kunmap_local(buf);
+	return left ? NULL : dst;
+}
+
+#else
+
+/* We just want to return non-NULL; it's never used. */
+#define dump_page_alloc() ERR_PTR(-EINVAL)
+#define dump_page_free(x) ((void)(x))
+static inline struct page *dump_page_copy(struct page *src, struct page *dst)
+{
+	return src;
+}
+#endif
+
 int dump_user_range(struct coredump_params *cprm, unsigned long start,
 		    unsigned long len)
 {
 	unsigned long addr;
+	struct page *dump_page;
+
+	dump_page = dump_page_alloc();
+	if (!dump_page)
+		return 0;
 
 	for (addr = start; addr < start + len; addr += PAGE_SIZE) {
 		struct page *page;
@@ -912,14 +948,17 @@ int dump_user_range(struct coredump_params *cprm, unsigned long start,
 		 */
 		page = get_dump_page(addr);
 		if (page) {
-			int stop = !dump_emit_page(cprm, page);
+			int stop = !dump_emit_page(cprm, dump_page_copy(page, dump_page));
 			put_page(page);
-			if (stop)
+			if (stop) {
+				dump_page_free(dump_page);
 				return 0;
+			}
 		} else {
 			dump_skip(cprm, PAGE_SIZE);
 		}
 	}
+	dump_page_free(dump_page);
 	return 1;
 }
 #endif
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 60dbfa0f8805..39e75131fd5a 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -495,7 +495,7 @@ static void cramfs_kill_sb(struct super_block *sb)
 		sb->s_mtd = NULL;
 	} else if (IS_ENABLED(CONFIG_CRAMFS_BLOCKDEV) && sb->s_bdev) {
 		sync_blockdev(sb->s_bdev);
-		bdev_release(sb->s_bdev_handle);
+		fput(sb->s_bdev_file);
 	}
 	kfree(sbi);
 }
diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index 7b3fc189593a..0ad52fbe51c9 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -74,13 +74,7 @@ struct fscrypt_nokey_name {
 
 static inline bool fscrypt_is_dot_dotdot(const struct qstr *str)
 {
-	if (str->len == 1 && str->name[0] == '.')
-		return true;
-
-	if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.')
-		return true;
-
-	return false;
+	return is_dot_dotdot(str->name, str->len);
 }
 
 /**
diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index 52504dd478d3..104771c3d3f6 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -102,11 +102,8 @@ int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry,
 	if (err && err != -ENOENT)
 		return err;
 
-	if (fname->is_nokey_name) {
-		spin_lock(&dentry->d_lock);
-		dentry->d_flags |= DCACHE_NOKEY_NAME;
-		spin_unlock(&dentry->d_lock);
-	}
+	fscrypt_prepare_dentry(dentry, fname->is_nokey_name);
+
 	return err;
 }
 EXPORT_SYMBOL_GPL(__fscrypt_prepare_lookup);
@@ -131,12 +128,10 @@ EXPORT_SYMBOL_GPL(__fscrypt_prepare_lookup);
 int fscrypt_prepare_lookup_partial(struct inode *dir, struct dentry *dentry)
 {
 	int err = fscrypt_get_encryption_info(dir, true);
+	bool is_nokey_name = (!err && !fscrypt_has_encryption_key(dir));
+
+	fscrypt_prepare_dentry(dentry, is_nokey_name);
 
-	if (!err && !fscrypt_has_encryption_key(dir)) {
-		spin_lock(&dentry->d_lock);
-		dentry->d_flags |= DCACHE_NOKEY_NAME;
-		spin_unlock(&dentry->d_lock);
-	}
 	return err;
 }
 EXPORT_SYMBOL_GPL(fscrypt_prepare_lookup_partial);
diff --git a/fs/dcache.c b/fs/dcache.c
index b813528fb147..71a8e943a0fa 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -3061,7 +3061,10 @@ static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry)
 		if (d_unhashed(dentry) || !dentry->d_inode)
 			return D_WALK_SKIP;
 
-		dentry->d_lockref.count--;
+		if (!(dentry->d_flags & DCACHE_GENOCIDE)) {
+			dentry->d_flags |= DCACHE_GENOCIDE;
+			dentry->d_lockref.count--;
+		}
 	}
 	return D_WALK_CONTINUE;
 }
@@ -3136,7 +3139,7 @@ static void __init dcache_init(void)
 	 * of the dcache.
 	 */
 	dentry_cache = KMEM_CACHE_USERCOPY(dentry,
-		SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD|SLAB_ACCOUNT,
+		SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_ACCOUNT,
 		d_iname);
 
 	/* Hash may have been set up in dcache_init_early */
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 60456263a338..62c97ff9e852 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -410,6 +410,8 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio,
 		bio->bi_end_io = dio_bio_end_io;
 	if (dio->is_pinned)
 		bio_set_flag(bio, BIO_PAGE_PINNED);
+	bio->bi_write_hint = file_inode(dio->iocb->ki_filp)->i_write_hint;
+
 	sdio->bio = bio;
 	sdio->logical_offset_in_bio = sdio->cur_page_fs_offset;
 }
diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c
index d814c5121367..9ca83ef70ed1 100644
--- a/fs/dlm/plock.c
+++ b/fs/dlm/plock.c
@@ -138,14 +138,14 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 	}
 
 	op->info.optype		= DLM_PLOCK_OP_LOCK;
-	op->info.pid		= fl->fl_pid;
-	op->info.ex		= (fl->fl_type == F_WRLCK);
-	op->info.wait		= !!(fl->fl_flags & FL_SLEEP);
+	op->info.pid		= fl->c.flc_pid;
+	op->info.ex		= lock_is_write(fl);
+	op->info.wait		= !!(fl->c.flc_flags & FL_SLEEP);
 	op->info.fsid		= ls->ls_global_id;
 	op->info.number		= number;
 	op->info.start		= fl->fl_start;
 	op->info.end		= fl->fl_end;
-	op->info.owner = (__u64)(long)fl->fl_owner;
+	op->info.owner = (__u64)(long) fl->c.flc_owner;
 	/* async handling */
 	if (fl->fl_lmops && fl->fl_lmops->lm_grant) {
 		op_data = kzalloc(sizeof(*op_data), GFP_NOFS);
@@ -258,7 +258,7 @@ static int dlm_plock_callback(struct plock_op *op)
 	}
 
 	/* got fs lock; bookkeep locally as well: */
-	flc->fl_flags &= ~FL_SLEEP;
+	flc->c.flc_flags &= ~FL_SLEEP;
 	if (posix_lock_file(file, flc, NULL)) {
 		/*
 		 * This can only happen in the case of kmalloc() failure.
@@ -291,7 +291,7 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 	struct dlm_ls *ls;
 	struct plock_op *op;
 	int rv;
-	unsigned char fl_flags = fl->fl_flags;
+	unsigned char saved_flags = fl->c.flc_flags;
 
 	ls = dlm_find_lockspace_local(lockspace);
 	if (!ls)
@@ -304,7 +304,7 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 	}
 
 	/* cause the vfs unlock to return ENOENT if lock is not found */
-	fl->fl_flags |= FL_EXISTS;
+	fl->c.flc_flags |= FL_EXISTS;
 
 	rv = locks_lock_file_wait(file, fl);
 	if (rv == -ENOENT) {
@@ -317,14 +317,14 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 	}
 
 	op->info.optype		= DLM_PLOCK_OP_UNLOCK;
-	op->info.pid		= fl->fl_pid;
+	op->info.pid		= fl->c.flc_pid;
 	op->info.fsid		= ls->ls_global_id;
 	op->info.number		= number;
 	op->info.start		= fl->fl_start;
 	op->info.end		= fl->fl_end;
-	op->info.owner = (__u64)(long)fl->fl_owner;
+	op->info.owner = (__u64)(long) fl->c.flc_owner;
 
-	if (fl->fl_flags & FL_CLOSE) {
+	if (fl->c.flc_flags & FL_CLOSE) {
 		op->info.flags |= DLM_PLOCK_FL_CLOSE;
 		send_op(op);
 		rv = 0;
@@ -345,7 +345,7 @@ out_free:
 	dlm_release_plock_op(op);
 out:
 	dlm_put_lockspace(ls);
-	fl->fl_flags = fl_flags;
+	fl->c.flc_flags = saved_flags;
 	return rv;
 }
 EXPORT_SYMBOL_GPL(dlm_posix_unlock);
@@ -375,14 +375,14 @@ int dlm_posix_cancel(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 		return -EINVAL;
 
 	memset(&info, 0, sizeof(info));
-	info.pid = fl->fl_pid;
-	info.ex = (fl->fl_type == F_WRLCK);
+	info.pid = fl->c.flc_pid;
+	info.ex = lock_is_write(fl);
 	info.fsid = ls->ls_global_id;
 	dlm_put_lockspace(ls);
 	info.number = number;
 	info.start = fl->fl_start;
 	info.end = fl->fl_end;
-	info.owner = (__u64)(long)fl->fl_owner;
+	info.owner = (__u64)(long) fl->c.flc_owner;
 
 	rv = do_lock_cancel(&info);
 	switch (rv) {
@@ -437,13 +437,13 @@ int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 	}
 
 	op->info.optype		= DLM_PLOCK_OP_GET;
-	op->info.pid		= fl->fl_pid;
-	op->info.ex		= (fl->fl_type == F_WRLCK);
+	op->info.pid		= fl->c.flc_pid;
+	op->info.ex		= lock_is_write(fl);
 	op->info.fsid		= ls->ls_global_id;
 	op->info.number		= number;
 	op->info.start		= fl->fl_start;
 	op->info.end		= fl->fl_end;
-	op->info.owner = (__u64)(long)fl->fl_owner;
+	op->info.owner = (__u64)(long) fl->c.flc_owner;
 
 	send_op(op);
 	wait_event(recv_wq, (op->done != 0));
@@ -455,16 +455,16 @@ int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 
 	rv = op->info.rv;
 
-	fl->fl_type = F_UNLCK;
+	fl->c.flc_type = F_UNLCK;
 	if (rv == -ENOENT)
 		rv = 0;
 	else if (rv > 0) {
 		locks_init_lock(fl);
-		fl->fl_type = (op->info.ex) ? F_WRLCK : F_RDLCK;
-		fl->fl_flags = FL_POSIX;
-		fl->fl_pid = op->info.pid;
+		fl->c.flc_type = (op->info.ex) ? F_WRLCK : F_RDLCK;
+		fl->c.flc_flags = FL_POSIX;
+		fl->c.flc_pid = op->info.pid;
 		if (op->info.nodeid != dlm_our_nodeid())
-			fl->fl_pid = -fl->fl_pid;
+			fl->c.flc_pid = -fl->c.flc_pid;
 		fl->fl_start = op->info.start;
 		fl->fl_end = op->info.end;
 		rv = 0;
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 03bd55069d86..2fe0f3af1a08 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1949,16 +1949,6 @@ out:
 	return rc;
 }
 
-static bool is_dot_dotdot(const char *name, size_t name_size)
-{
-	if (name_size == 1 && name[0] == '.')
-		return true;
-	else if (name_size == 2 && name[0] == '.' && name[1] == '.')
-		return true;
-
-	return false;
-}
-
 /**
  * ecryptfs_decode_and_decrypt_filename - converts the encoded cipher text name to decoded plaintext
  * @plaintext_name: The plaintext name
diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h
index 169252e6dc46..f7206158ee81 100644
--- a/fs/efivarfs/internal.h
+++ b/fs/efivarfs/internal.h
@@ -38,7 +38,7 @@ struct efivar_entry {
 
 int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *,
 			    struct list_head *),
-		void *data, bool duplicates, struct list_head *head);
+		void *data, struct list_head *head);
 
 int efivar_entry_add(struct efivar_entry *entry, struct list_head *head);
 void __efivar_entry_add(struct efivar_entry *entry, struct list_head *head);
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index 6038dd39367a..bb14462f6d99 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -343,12 +343,7 @@ static int efivarfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	if (err)
 		return err;
 
-	err = efivar_init(efivarfs_callback, (void *)sb, true,
-			  &sfi->efivarfs_list);
-	if (err)
-		efivar_entry_iter(efivarfs_destroy, &sfi->efivarfs_list, NULL);
-
-	return err;
+	return efivar_init(efivarfs_callback, sb, &sfi->efivarfs_list);
 }
 
 static int efivarfs_get_tree(struct fs_context *fc)
diff --git a/fs/efivarfs/vars.c b/fs/efivarfs/vars.c
index 114ff0fd4e55..4d722af1014f 100644
--- a/fs/efivarfs/vars.c
+++ b/fs/efivarfs/vars.c
@@ -361,7 +361,6 @@ static void dup_variable_bug(efi_char16_t *str16, efi_guid_t *vendor_guid,
  * efivar_init - build the initial list of EFI variables
  * @func: callback function to invoke for every variable
  * @data: function-specific data to pass to @func
- * @duplicates: error if we encounter duplicates on @head?
  * @head: initialised head of variable list
  *
  * Get every EFI variable from the firmware and invoke @func. @func
@@ -371,9 +370,9 @@ static void dup_variable_bug(efi_char16_t *str16, efi_guid_t *vendor_guid,
  */
 int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *,
 			    struct list_head *),
-		void *data, bool duplicates, struct list_head *head)
+		void *data, struct list_head *head)
 {
-	unsigned long variable_name_size = 1024;
+	unsigned long variable_name_size = 512;
 	efi_char16_t *variable_name;
 	efi_status_t status;
 	efi_guid_t vendor_guid;
@@ -390,12 +389,13 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *,
 		goto free;
 
 	/*
-	 * Per EFI spec, the maximum storage allocated for both
-	 * the variable name and variable data is 1024 bytes.
+	 * A small set of old UEFI implementations reject sizes
+	 * above a certain threshold, the lowest seen in the wild
+	 * is 512.
 	 */
 
 	do {
-		variable_name_size = 1024;
+		variable_name_size = 512;
 
 		status = efivar_get_next_variable(&variable_name_size,
 						  variable_name,
@@ -413,8 +413,7 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *,
 			 * we'll ever see a different variable name,
 			 * and may end up looping here forever.
 			 */
-			if (duplicates &&
-			    variable_is_present(variable_name, &vendor_guid,
+			if (variable_is_present(variable_name, &vendor_guid,
 						head)) {
 				dup_variable_bug(variable_name, &vendor_guid,
 						 variable_name_size);
@@ -432,9 +431,13 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *,
 			break;
 		case EFI_NOT_FOUND:
 			break;
+		case EFI_BUFFER_TOO_SMALL:
+			pr_warn("efivars: Variable name size exceeds maximum (%lu > 512)\n",
+				variable_name_size);
+			status = EFI_NOT_FOUND;
+			break;
 		default:
-			printk(KERN_WARNING "efivars: get_next_variable: status=%lx\n",
-				status);
+			pr_warn("efivars: get_next_variable: status=%lx\n", status);
 			status = EFI_NOT_FOUND;
 			break;
 		}
diff --git a/fs/efs/super.c b/fs/efs/super.c
index f17fdac76b2e..e4421c10caeb 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -14,19 +14,14 @@
 #include <linux/buffer_head.h>
 #include <linux/vfs.h>
 #include <linux/blkdev.h>
-
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
 #include "efs.h"
 #include <linux/efs_vh.h>
 #include <linux/efs_fs_sb.h>
 
 static int efs_statfs(struct dentry *dentry, struct kstatfs *buf);
-static int efs_fill_super(struct super_block *s, void *d, int silent);
-
-static struct dentry *efs_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
-{
-	return mount_bdev(fs_type, flags, dev_name, data, efs_fill_super);
-}
+static int efs_init_fs_context(struct fs_context *fc);
 
 static void efs_kill_sb(struct super_block *s)
 {
@@ -35,15 +30,6 @@ static void efs_kill_sb(struct super_block *s)
 	kfree(sbi);
 }
 
-static struct file_system_type efs_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "efs",
-	.mount		= efs_mount,
-	.kill_sb	= efs_kill_sb,
-	.fs_flags	= FS_REQUIRES_DEV,
-};
-MODULE_ALIAS_FS("efs");
-
 static struct pt_types sgi_pt_types[] = {
 	{0x00,		"SGI vh"},
 	{0x01,		"SGI trkrepl"},
@@ -63,6 +49,27 @@ static struct pt_types sgi_pt_types[] = {
 	{0,		NULL}
 };
 
+enum {
+	Opt_explicit_open,
+};
+
+static const struct fs_parameter_spec efs_param_spec[] = {
+	fsparam_flag    ("explicit-open",       Opt_explicit_open),
+	{}
+};
+
+/*
+ * File system definition and registration.
+ */
+static struct file_system_type efs_fs_type = {
+	.owner			= THIS_MODULE,
+	.name			= "efs",
+	.kill_sb		= efs_kill_sb,
+	.fs_flags		= FS_REQUIRES_DEV,
+	.init_fs_context	= efs_init_fs_context,
+	.parameters		= efs_param_spec,
+};
+MODULE_ALIAS_FS("efs");
 
 static struct kmem_cache * efs_inode_cachep;
 
@@ -91,8 +98,8 @@ static int __init init_inodecache(void)
 {
 	efs_inode_cachep = kmem_cache_create("efs_inode_cache",
 				sizeof(struct efs_inode_info), 0,
-				SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|
-				SLAB_ACCOUNT, init_once);
+				SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT,
+				init_once);
 	if (efs_inode_cachep == NULL)
 		return -ENOMEM;
 	return 0;
@@ -108,18 +115,10 @@ static void destroy_inodecache(void)
 	kmem_cache_destroy(efs_inode_cachep);
 }
 
-static int efs_remount(struct super_block *sb, int *flags, char *data)
-{
-	sync_filesystem(sb);
-	*flags |= SB_RDONLY;
-	return 0;
-}
-
 static const struct super_operations efs_superblock_operations = {
 	.alloc_inode	= efs_alloc_inode,
 	.free_inode	= efs_free_inode,
 	.statfs		= efs_statfs,
-	.remount_fs	= efs_remount,
 };
 
 static const struct export_operations efs_export_ops = {
@@ -249,26 +248,26 @@ static int efs_validate_super(struct efs_sb_info *sb, struct efs_super *super) {
 	return 0;    
 }
 
-static int efs_fill_super(struct super_block *s, void *d, int silent)
+static int efs_fill_super(struct super_block *s, struct fs_context *fc)
 {
 	struct efs_sb_info *sb;
 	struct buffer_head *bh;
 	struct inode *root;
 
- 	sb = kzalloc(sizeof(struct efs_sb_info), GFP_KERNEL);
+	sb = kzalloc(sizeof(struct efs_sb_info), GFP_KERNEL);
 	if (!sb)
 		return -ENOMEM;
 	s->s_fs_info = sb;
 	s->s_time_min = 0;
 	s->s_time_max = U32_MAX;
- 
+
 	s->s_magic		= EFS_SUPER_MAGIC;
 	if (!sb_set_blocksize(s, EFS_BLOCKSIZE)) {
 		pr_err("device does not support %d byte blocks\n",
 			EFS_BLOCKSIZE);
 		return -EINVAL;
 	}
-  
+
 	/* read the vh (volume header) block */
 	bh = sb_bread(s, 0);
 
@@ -294,7 +293,7 @@ static int efs_fill_super(struct super_block *s, void *d, int silent)
 		pr_err("cannot read superblock\n");
 		return -EIO;
 	}
-		
+
 	if (efs_validate_super(sb, (struct efs_super *) bh->b_data)) {
 #ifdef DEBUG
 		pr_warn("invalid superblock at block %u\n",
@@ -328,6 +327,61 @@ static int efs_fill_super(struct super_block *s, void *d, int silent)
 	return 0;
 }
 
+static void efs_free_fc(struct fs_context *fc)
+{
+	kfree(fc->fs_private);
+}
+
+static int efs_get_tree(struct fs_context *fc)
+{
+	return get_tree_bdev(fc, efs_fill_super);
+}
+
+static int efs_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	int token;
+	struct fs_parse_result result;
+
+	token = fs_parse(fc, efs_param_spec, param, &result);
+	if (token < 0)
+		return token;
+	return 0;
+}
+
+static int efs_reconfigure(struct fs_context *fc)
+{
+	sync_filesystem(fc->root->d_sb);
+
+	return 0;
+}
+
+struct efs_context {
+	unsigned long s_mount_opts;
+};
+
+static const struct fs_context_operations efs_context_opts = {
+	.parse_param	= efs_parse_param,
+	.get_tree	= efs_get_tree,
+	.reconfigure	= efs_reconfigure,
+	.free		= efs_free_fc,
+};
+
+/*
+ * Set up the filesystem mount context.
+ */
+static int efs_init_fs_context(struct fs_context *fc)
+{
+	struct efs_context *ctx;
+
+	ctx = kzalloc(sizeof(struct efs_context), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+	fc->fs_private = ctx;
+	fc->ops = &efs_context_opts;
+
+	return 0;
+}
+
 static int efs_statfs(struct dentry *dentry, struct kstatfs *buf) {
 	struct super_block *sb = dentry->d_sb;
 	struct efs_sb_info *sbi = SUPER_INFO(sb);
diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig
index 1d318f85232d..fffd3919343e 100644
--- a/fs/erofs/Kconfig
+++ b/fs/erofs/Kconfig
@@ -114,8 +114,11 @@ config EROFS_FS_ZIP_DEFLATE
 
 config EROFS_FS_ONDEMAND
 	bool "EROFS fscache-based on-demand read support"
-	depends on CACHEFILES_ONDEMAND && (EROFS_FS=m && FSCACHE || EROFS_FS=y && FSCACHE=y)
-	default n
+	depends on EROFS_FS
+	select NETFS_SUPPORT
+	select FSCACHE
+	select CACHEFILES
+	select CACHEFILES_ONDEMAND
 	help
 	  This permits EROFS to use fscache-backed data blobs with on-demand
 	  read support.
diff --git a/fs/erofs/compress.h b/fs/erofs/compress.h
index 279933e007d2..7cc5841577b2 100644
--- a/fs/erofs/compress.h
+++ b/fs/erofs/compress.h
@@ -11,13 +11,12 @@
 struct z_erofs_decompress_req {
 	struct super_block *sb;
 	struct page **in, **out;
-
 	unsigned short pageofs_in, pageofs_out;
 	unsigned int inputsize, outputsize;
 
-	/* indicate the algorithm will be used for decompression */
-	unsigned int alg;
+	unsigned int alg;       /* the algorithm for decompression */
 	bool inplace_io, partial_decoding, fillgaps;
+	gfp_t gfp;      /* allocation flags for extra temporary buffers */
 };
 
 struct z_erofs_decompressor {
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index c98aeda8abb2..52524bd9698b 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -220,7 +220,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 			up_read(&devs->rwsem);
 			return 0;
 		}
-		map->m_bdev = dif->bdev_handle ? dif->bdev_handle->bdev : NULL;
+		map->m_bdev = dif->bdev_file ? file_bdev(dif->bdev_file) : NULL;
 		map->m_daxdev = dif->dax_dev;
 		map->m_dax_part_off = dif->dax_part_off;
 		map->m_fscache = dif->fscache;
@@ -238,8 +238,8 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 			if (map->m_pa >= startoff &&
 			    map->m_pa < startoff + length) {
 				map->m_pa -= startoff;
-				map->m_bdev = dif->bdev_handle ?
-					      dif->bdev_handle->bdev : NULL;
+				map->m_bdev = dif->bdev_file ?
+					      file_bdev(dif->bdev_file) : NULL;
 				map->m_daxdev = dif->dax_dev;
 				map->m_dax_part_off = dif->dax_part_off;
 				map->m_fscache = dif->fscache;
@@ -447,5 +447,6 @@ const struct file_operations erofs_file_fops = {
 	.llseek		= generic_file_llseek,
 	.read_iter	= erofs_file_read_iter,
 	.mmap		= erofs_file_mmap,
+	.get_unmapped_area = thp_get_unmapped_area,
 	.splice_read	= filemap_splice_read,
 };
diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
index 1d65b9f60a39..2ec9b2bb628d 100644
--- a/fs/erofs/decompressor.c
+++ b/fs/erofs/decompressor.c
@@ -111,8 +111,9 @@ static int z_erofs_lz4_prepare_dstpages(struct z_erofs_lz4_decompress_ctx *ctx,
 			victim = availables[--top];
 			get_page(victim);
 		} else {
-			victim = erofs_allocpage(pagepool,
-						 GFP_KERNEL | __GFP_NOFAIL);
+			victim = erofs_allocpage(pagepool, rq->gfp);
+			if (!victim)
+				return -ENOMEM;
 			set_page_private(victim, Z_EROFS_SHORTLIVED_PAGE);
 		}
 		rq->out[i] = victim;
@@ -322,7 +323,8 @@ static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq,
 	unsigned int cur = 0, ni = 0, no, pi, po, insz, cnt;
 	u8 *kin;
 
-	DBG_BUGON(rq->outputsize > rq->inputsize);
+	if (rq->outputsize > rq->inputsize)
+		return -EOPNOTSUPP;
 	if (rq->alg == Z_EROFS_COMPRESSION_INTERLACED) {
 		cur = bs - (rq->pageofs_out & (bs - 1));
 		pi = (rq->pageofs_in + rq->inputsize - cur) & ~PAGE_MASK;
@@ -408,7 +410,7 @@ int z_erofs_parse_cfgs(struct super_block *sb, struct erofs_super_block *dsb)
 	int size, ret = 0;
 
 	if (!erofs_sb_has_compr_cfgs(sbi)) {
-		sbi->available_compr_algs = Z_EROFS_COMPRESSION_LZ4;
+		sbi->available_compr_algs = 1 << Z_EROFS_COMPRESSION_LZ4;
 		return z_erofs_load_lz4_config(sb, dsb, NULL, 0);
 	}
 
diff --git a/fs/erofs/decompressor_deflate.c b/fs/erofs/decompressor_deflate.c
index 4a64a9c91dd3..b98872058abe 100644
--- a/fs/erofs/decompressor_deflate.c
+++ b/fs/erofs/decompressor_deflate.c
@@ -95,7 +95,7 @@ int z_erofs_load_deflate_config(struct super_block *sb,
 }
 
 int z_erofs_deflate_decompress(struct z_erofs_decompress_req *rq,
-			       struct page **pagepool)
+			       struct page **pgpl)
 {
 	const unsigned int nrpages_out =
 		PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT;
@@ -158,8 +158,12 @@ again:
 			strm->z.avail_out = min_t(u32, outsz, PAGE_SIZE - pofs);
 			outsz -= strm->z.avail_out;
 			if (!rq->out[no]) {
-				rq->out[no] = erofs_allocpage(pagepool,
-						GFP_KERNEL | __GFP_NOFAIL);
+				rq->out[no] = erofs_allocpage(pgpl, rq->gfp);
+				if (!rq->out[no]) {
+					kout = NULL;
+					err = -ENOMEM;
+					break;
+				}
 				set_page_private(rq->out[no],
 						 Z_EROFS_SHORTLIVED_PAGE);
 			}
@@ -211,8 +215,11 @@ again:
 
 			DBG_BUGON(erofs_page_is_managed(EROFS_SB(sb),
 							rq->in[j]));
-			tmppage = erofs_allocpage(pagepool,
-						  GFP_KERNEL | __GFP_NOFAIL);
+			tmppage = erofs_allocpage(pgpl, rq->gfp);
+			if (!tmppage) {
+				err = -ENOMEM;
+				goto failed;
+			}
 			set_page_private(tmppage, Z_EROFS_SHORTLIVED_PAGE);
 			copy_highpage(tmppage, rq->in[j]);
 			rq->in[j] = tmppage;
@@ -230,7 +237,7 @@ again:
 			break;
 		}
 	}
-
+failed:
 	if (zlib_inflateEnd(&strm->z) != Z_OK && !err)
 		err = -EIO;
 	if (kout)
diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c
index 2dd14f99c1dc..6ca357d83cfa 100644
--- a/fs/erofs/decompressor_lzma.c
+++ b/fs/erofs/decompressor_lzma.c
@@ -148,7 +148,7 @@ again:
 }
 
 int z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq,
-			    struct page **pagepool)
+			    struct page **pgpl)
 {
 	const unsigned int nrpages_out =
 		PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT;
@@ -215,8 +215,11 @@ again:
 						   PAGE_SIZE - pageofs);
 			outlen -= strm->buf.out_size;
 			if (!rq->out[no] && rq->fillgaps) {	/* deduped */
-				rq->out[no] = erofs_allocpage(pagepool,
-						GFP_KERNEL | __GFP_NOFAIL);
+				rq->out[no] = erofs_allocpage(pgpl, rq->gfp);
+				if (!rq->out[no]) {
+					err = -ENOMEM;
+					break;
+				}
 				set_page_private(rq->out[no],
 						 Z_EROFS_SHORTLIVED_PAGE);
 			}
@@ -258,8 +261,11 @@ again:
 
 			DBG_BUGON(erofs_page_is_managed(EROFS_SB(rq->sb),
 							rq->in[j]));
-			tmppage = erofs_allocpage(pagepool,
-						  GFP_KERNEL | __GFP_NOFAIL);
+			tmppage = erofs_allocpage(pgpl, rq->gfp);
+			if (!tmppage) {
+				err = -ENOMEM;
+				goto failed;
+			}
 			set_page_private(tmppage, Z_EROFS_SHORTLIVED_PAGE);
 			copy_highpage(tmppage, rq->in[j]);
 			rq->in[j] = tmppage;
@@ -277,6 +283,7 @@ again:
 			break;
 		}
 	}
+failed:
 	if (no < nrpages_out && strm->buf.out)
 		kunmap(rq->out[no]);
 	if (ni < nrpages_in)
diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c
index 87ff35bff8d5..89a7c2453aae 100644
--- a/fs/erofs/fscache.c
+++ b/fs/erofs/fscache.c
@@ -165,10 +165,10 @@ static int erofs_fscache_read_folios_async(struct fscache_cookie *cookie,
 static int erofs_fscache_meta_read_folio(struct file *data, struct folio *folio)
 {
 	int ret;
-	struct erofs_fscache *ctx = folio_mapping(folio)->host->i_private;
+	struct erofs_fscache *ctx = folio->mapping->host->i_private;
 	struct erofs_fscache_request *req;
 
-	req = erofs_fscache_req_alloc(folio_mapping(folio),
+	req = erofs_fscache_req_alloc(folio->mapping,
 				folio_pos(folio), folio_size(folio));
 	if (IS_ERR(req)) {
 		folio_unlock(folio);
@@ -276,7 +276,7 @@ static int erofs_fscache_read_folio(struct file *file, struct folio *folio)
 	struct erofs_fscache_request *req;
 	int ret;
 
-	req = erofs_fscache_req_alloc(folio_mapping(folio),
+	req = erofs_fscache_req_alloc(folio->mapping,
 			folio_pos(folio), folio_size(folio));
 	if (IS_ERR(req)) {
 		folio_unlock(folio);
@@ -381,11 +381,12 @@ static int erofs_fscache_init_domain(struct super_block *sb)
 		goto out;
 
 	if (!erofs_pseudo_mnt) {
-		erofs_pseudo_mnt = kern_mount(&erofs_fs_type);
-		if (IS_ERR(erofs_pseudo_mnt)) {
-			err = PTR_ERR(erofs_pseudo_mnt);
+		struct vfsmount *mnt = kern_mount(&erofs_fs_type);
+		if (IS_ERR(mnt)) {
+			err = PTR_ERR(mnt);
 			goto out;
 		}
+		erofs_pseudo_mnt = mnt;
 	}
 
 	domain->volume = sbi->volume;
@@ -459,7 +460,7 @@ static struct erofs_fscache *erofs_fscache_acquire_cookie(struct super_block *sb
 
 	inode->i_size = OFFSET_MAX;
 	inode->i_mapping->a_ops = &erofs_fscache_meta_aops;
-	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
+	mapping_set_gfp_mask(inode->i_mapping, GFP_KERNEL);
 	inode->i_blkbits = EROFS_SB(sb)->blkszbits;
 	inode->i_private = ctx;
 
diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
index 3d616dea55dc..36e638e8b53a 100644
--- a/fs/erofs/inode.c
+++ b/fs/erofs/inode.c
@@ -60,7 +60,7 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 		} else {
 			const unsigned int gotten = sb->s_blocksize - *ofs;
 
-			copied = kmalloc(vi->inode_isize, GFP_NOFS);
+			copied = kmalloc(vi->inode_isize, GFP_KERNEL);
 			if (!copied) {
 				err = -ENOMEM;
 				goto err_out;
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index b0409badb017..0f0706325b7b 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -49,7 +49,7 @@ typedef u32 erofs_blk_t;
 struct erofs_device_info {
 	char *path;
 	struct erofs_fscache *fscache;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct dax_device *dax_dev;
 	u64 dax_part_off;
 
diff --git a/fs/erofs/namei.c b/fs/erofs/namei.c
index d4f631d39f0f..f0110a78acb2 100644
--- a/fs/erofs/namei.c
+++ b/fs/erofs/namei.c
@@ -130,24 +130,24 @@ static void *erofs_find_target_block(struct erofs_buf *target,
 			/* string comparison without already matched prefix */
 			diff = erofs_dirnamecmp(name, &dname, &matched);
 
-			if (!diff) {
-				*_ndirents = 0;
-				goto out;
-			} else if (diff > 0) {
-				head = mid + 1;
-				startprfx = matched;
-
-				if (!IS_ERR(candidate))
-					erofs_put_metabuf(target);
-				*target = buf;
-				candidate = de;
-				*_ndirents = ndirents;
-			} else {
+			if (diff < 0) {
 				erofs_put_metabuf(&buf);
-
 				back = mid - 1;
 				endprfx = matched;
+				continue;
+			}
+
+			if (!IS_ERR(candidate))
+				erofs_put_metabuf(target);
+			*target = buf;
+			if (!diff) {
+				*_ndirents = 0;
+				return de;
 			}
+			head = mid + 1;
+			startprfx = matched;
+			candidate = de;
+			*_ndirents = ndirents;
 			continue;
 		}
 out:		/* free if the candidate is valid */
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 5f60f163bd56..9b4b66dcdd4f 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -177,7 +177,7 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
 	struct erofs_sb_info *sbi = EROFS_SB(sb);
 	struct erofs_fscache *fscache;
 	struct erofs_deviceslot *dis;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	void *ptr;
 
 	ptr = erofs_read_metabuf(buf, sb, erofs_blknr(sb, *pos), EROFS_KMAP);
@@ -201,12 +201,12 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
 			return PTR_ERR(fscache);
 		dif->fscache = fscache;
 	} else if (!sbi->devs->flatdev) {
-		bdev_handle = bdev_open_by_path(dif->path, BLK_OPEN_READ,
+		bdev_file = bdev_file_open_by_path(dif->path, BLK_OPEN_READ,
 						sb->s_type, NULL);
-		if (IS_ERR(bdev_handle))
-			return PTR_ERR(bdev_handle);
-		dif->bdev_handle = bdev_handle;
-		dif->dax_dev = fs_dax_get_by_bdev(bdev_handle->bdev,
+		if (IS_ERR(bdev_file))
+			return PTR_ERR(bdev_file);
+		dif->bdev_file = bdev_file;
+		dif->dax_dev = fs_dax_get_by_bdev(file_bdev(bdev_file),
 				&dif->dax_part_off, NULL, NULL);
 	}
 
@@ -754,8 +754,8 @@ static int erofs_release_device_info(int id, void *ptr, void *data)
 	struct erofs_device_info *dif = ptr;
 
 	fs_put_dax(dif->dax_dev, NULL);
-	if (dif->bdev_handle)
-		bdev_release(dif->bdev_handle);
+	if (dif->bdev_file)
+		fput(dif->bdev_file);
 	erofs_fscache_unregister_cookie(dif->fscache);
 	dif->fscache = NULL;
 	kfree(dif->path);
diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c
index 5dea308764b4..e146d09151af 100644
--- a/fs/erofs/utils.c
+++ b/fs/erofs/utils.c
@@ -81,7 +81,7 @@ struct erofs_workgroup *erofs_insert_workgroup(struct super_block *sb,
 repeat:
 	xa_lock(&sbi->managed_pslots);
 	pre = __xa_cmpxchg(&sbi->managed_pslots, grp->index,
-			   NULL, grp, GFP_NOFS);
+			   NULL, grp, GFP_KERNEL);
 	if (pre) {
 		if (xa_is_err(pre)) {
 			pre = ERR_PTR(xa_err(pre));
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 692c0c39be63..ff0aa72b0db3 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -82,6 +82,9 @@ struct z_erofs_pcluster {
 	/* L: indicate several pageofs_outs or not */
 	bool multibases;
 
+	/* L: whether extra buffer allocations are best-effort */
+	bool besteffort;
+
 	/* A: compressed bvecs (can be cached or inplaced pages) */
 	struct z_erofs_bvec compressed_bvecs[];
 };
@@ -230,7 +233,7 @@ static int z_erofs_bvec_enqueue(struct z_erofs_bvec_iter *iter,
 		struct page *nextpage = *candidate_bvpage;
 
 		if (!nextpage) {
-			nextpage = erofs_allocpage(pagepool, GFP_NOFS);
+			nextpage = erofs_allocpage(pagepool, GFP_KERNEL);
 			if (!nextpage)
 				return -ENOMEM;
 			set_page_private(nextpage, Z_EROFS_SHORTLIVED_PAGE);
@@ -302,7 +305,7 @@ static struct z_erofs_pcluster *z_erofs_alloc_pcluster(unsigned int size)
 		if (nrpages > pcs->maxpages)
 			continue;
 
-		pcl = kmem_cache_zalloc(pcs->slab, GFP_NOFS);
+		pcl = kmem_cache_zalloc(pcs->slab, GFP_KERNEL);
 		if (!pcl)
 			return ERR_PTR(-ENOMEM);
 		pcl->pclustersize = size;
@@ -563,21 +566,19 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe)
 			__GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;
 	unsigned int i;
 
-	if (i_blocksize(fe->inode) != PAGE_SIZE)
-		return;
-	if (fe->mode < Z_EROFS_PCLUSTER_FOLLOWED)
+	if (i_blocksize(fe->inode) != PAGE_SIZE ||
+	    fe->mode < Z_EROFS_PCLUSTER_FOLLOWED)
 		return;
 
 	for (i = 0; i < pclusterpages; ++i) {
 		struct page *page, *newpage;
 		void *t;	/* mark pages just found for debugging */
 
-		/* the compressed page was loaded before */
+		/* Inaccurate check w/o locking to avoid unneeded lookups */
 		if (READ_ONCE(pcl->compressed_bvecs[i].page))
 			continue;
 
 		page = find_get_page(mc, pcl->obj.index + i);
-
 		if (page) {
 			t = (void *)((unsigned long)page | 1);
 			newpage = NULL;
@@ -597,9 +598,13 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe)
 			set_page_private(newpage, Z_EROFS_PREALLOCATED_PAGE);
 			t = (void *)((unsigned long)newpage | 1);
 		}
-
-		if (!cmpxchg_relaxed(&pcl->compressed_bvecs[i].page, NULL, t))
+		spin_lock(&pcl->obj.lockref.lock);
+		if (!pcl->compressed_bvecs[i].page) {
+			pcl->compressed_bvecs[i].page = t;
+			spin_unlock(&pcl->obj.lockref.lock);
 			continue;
+		}
+		spin_unlock(&pcl->obj.lockref.lock);
 
 		if (page)
 			put_page(page);
@@ -694,7 +699,7 @@ static void z_erofs_cache_invalidate_folio(struct folio *folio,
 	DBG_BUGON(stop > folio_size(folio) || stop < length);
 
 	if (offset == 0 && stop == folio_size(folio))
-		while (!z_erofs_cache_release_folio(folio, GFP_NOFS))
+		while (!z_erofs_cache_release_folio(folio, 0))
 			cond_resched();
 }
 
@@ -713,36 +718,30 @@ int erofs_init_managed_cache(struct super_block *sb)
 	set_nlink(inode, 1);
 	inode->i_size = OFFSET_MAX;
 	inode->i_mapping->a_ops = &z_erofs_cache_aops;
-	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
+	mapping_set_gfp_mask(inode->i_mapping, GFP_KERNEL);
 	EROFS_SB(sb)->managed_cache = inode;
 	return 0;
 }
 
-static bool z_erofs_try_inplace_io(struct z_erofs_decompress_frontend *fe,
-				   struct z_erofs_bvec *bvec)
-{
-	struct z_erofs_pcluster *const pcl = fe->pcl;
-
-	while (fe->icur > 0) {
-		if (!cmpxchg(&pcl->compressed_bvecs[--fe->icur].page,
-			     NULL, bvec->page)) {
-			pcl->compressed_bvecs[fe->icur] = *bvec;
-			return true;
-		}
-	}
-	return false;
-}
-
 /* callers must be with pcluster lock held */
 static int z_erofs_attach_page(struct z_erofs_decompress_frontend *fe,
 			       struct z_erofs_bvec *bvec, bool exclusive)
 {
+	struct z_erofs_pcluster *pcl = fe->pcl;
 	int ret;
 
 	if (exclusive) {
 		/* give priority for inplaceio to use file pages first */
-		if (z_erofs_try_inplace_io(fe, bvec))
+		spin_lock(&pcl->obj.lockref.lock);
+		while (fe->icur > 0) {
+			if (pcl->compressed_bvecs[--fe->icur].page)
+				continue;
+			pcl->compressed_bvecs[fe->icur] = *bvec;
+			spin_unlock(&pcl->obj.lockref.lock);
 			return 0;
+		}
+		spin_unlock(&pcl->obj.lockref.lock);
+
 		/* otherwise, check if it can be used as a bvpage */
 		if (fe->mode >= Z_EROFS_PCLUSTER_FOLLOWED &&
 		    !fe->candidate_bvpage)
@@ -964,7 +963,7 @@ static int z_erofs_read_fragment(struct super_block *sb, struct page *page,
 }
 
 static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe,
-				struct page *page)
+				struct page *page, bool ra)
 {
 	struct inode *const inode = fe->inode;
 	struct erofs_map_blocks *const map = &fe->map;
@@ -1014,6 +1013,7 @@ repeat:
 		err = z_erofs_pcluster_begin(fe);
 		if (err)
 			goto out;
+		fe->pcl->besteffort |= !ra;
 	}
 
 	/*
@@ -1280,6 +1280,9 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
 					.inplace_io = overlapped,
 					.partial_decoding = pcl->partial,
 					.fillgaps = pcl->multibases,
+					.gfp = pcl->besteffort ?
+						GFP_KERNEL | __GFP_NOFAIL :
+						GFP_NOWAIT | __GFP_NORETRY
 				 }, be->pagepool);
 
 	/* must handle all compressed pages before actual file pages */
@@ -1322,6 +1325,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
 	pcl->length = 0;
 	pcl->partial = true;
 	pcl->multibases = false;
+	pcl->besteffort = false;
 	pcl->bvset.nextpage = NULL;
 	pcl->vcnt = 0;
 
@@ -1423,23 +1427,26 @@ static void z_erofs_fill_bio_vec(struct bio_vec *bvec,
 {
 	gfp_t gfp = mapping_gfp_mask(mc);
 	bool tocache = false;
-	struct z_erofs_bvec *zbv = pcl->compressed_bvecs + nr;
+	struct z_erofs_bvec zbv;
 	struct address_space *mapping;
-	struct page *page, *oldpage;
+	struct page *page;
 	int justfound, bs = i_blocksize(f->inode);
 
 	/* Except for inplace pages, the entire page can be used for I/Os */
 	bvec->bv_offset = 0;
 	bvec->bv_len = PAGE_SIZE;
 repeat:
-	oldpage = READ_ONCE(zbv->page);
-	if (!oldpage)
+	spin_lock(&pcl->obj.lockref.lock);
+	zbv = pcl->compressed_bvecs[nr];
+	page = zbv.page;
+	justfound = (unsigned long)page & 1UL;
+	page = (struct page *)((unsigned long)page & ~1UL);
+	pcl->compressed_bvecs[nr].page = page;
+	spin_unlock(&pcl->obj.lockref.lock);
+	if (!page)
 		goto out_allocpage;
 
-	justfound = (unsigned long)oldpage & 1UL;
-	page = (struct page *)((unsigned long)oldpage & ~1UL);
 	bvec->bv_page = page;
-
 	DBG_BUGON(z_erofs_is_shortlived_page(page));
 	/*
 	 * Handle preallocated cached pages.  We tried to allocate such pages
@@ -1448,7 +1455,6 @@ repeat:
 	 */
 	if (page->private == Z_EROFS_PREALLOCATED_PAGE) {
 		set_page_private(page, 0);
-		WRITE_ONCE(zbv->page, page);
 		tocache = true;
 		goto out_tocache;
 	}
@@ -1459,9 +1465,9 @@ repeat:
 	 * therefore it is impossible for `mapping` to be NULL.
 	 */
 	if (mapping && mapping != mc) {
-		if (zbv->offset < 0)
-			bvec->bv_offset = round_up(-zbv->offset, bs);
-		bvec->bv_len = round_up(zbv->end, bs) - bvec->bv_offset;
+		if (zbv.offset < 0)
+			bvec->bv_offset = round_up(-zbv.offset, bs);
+		bvec->bv_len = round_up(zbv.end, bs) - bvec->bv_offset;
 		return;
 	}
 
@@ -1471,7 +1477,6 @@ repeat:
 
 	/* the cached page is still in managed cache */
 	if (page->mapping == mc) {
-		WRITE_ONCE(zbv->page, page);
 		/*
 		 * The cached page is still available but without a valid
 		 * `->private` pcluster hint.  Let's reconnect them.
@@ -1503,11 +1508,15 @@ repeat:
 	put_page(page);
 out_allocpage:
 	page = erofs_allocpage(&f->pagepool, gfp | __GFP_NOFAIL);
-	if (oldpage != cmpxchg(&zbv->page, oldpage, page)) {
+	spin_lock(&pcl->obj.lockref.lock);
+	if (pcl->compressed_bvecs[nr].page) {
 		erofs_pagepool_add(&f->pagepool, page);
+		spin_unlock(&pcl->obj.lockref.lock);
 		cond_resched();
 		goto repeat;
 	}
+	pcl->compressed_bvecs[nr].page = page;
+	spin_unlock(&pcl->obj.lockref.lock);
 	bvec->bv_page = page;
 out_tocache:
 	if (!tocache || bs != PAGE_SIZE ||
@@ -1685,6 +1694,7 @@ submit_bio_retry:
 
 			if (cur + bvec.bv_len > end)
 				bvec.bv_len = end - cur;
+			DBG_BUGON(bvec.bv_len < sb->s_blocksize);
 			if (!bio_add_page(bio, bvec.bv_page, bvec.bv_len,
 					  bvec.bv_offset))
 				goto submit_bio_retry;
@@ -1785,7 +1795,7 @@ static void z_erofs_pcluster_readmore(struct z_erofs_decompress_frontend *f,
 			if (PageUptodate(page))
 				unlock_page(page);
 			else
-				(void)z_erofs_do_read_page(f, page);
+				(void)z_erofs_do_read_page(f, page, !!rac);
 			put_page(page);
 		}
 
@@ -1806,7 +1816,7 @@ static int z_erofs_read_folio(struct file *file, struct folio *folio)
 	f.headoffset = (erofs_off_t)folio->index << PAGE_SHIFT;
 
 	z_erofs_pcluster_readmore(&f, NULL, true);
-	err = z_erofs_do_read_page(&f, &folio->page);
+	err = z_erofs_do_read_page(&f, &folio->page, false);
 	z_erofs_pcluster_readmore(&f, NULL, false);
 	z_erofs_pcluster_end(&f);
 
@@ -1847,7 +1857,7 @@ static void z_erofs_readahead(struct readahead_control *rac)
 		folio = head;
 		head = folio_get_private(folio);
 
-		err = z_erofs_do_read_page(&f, &folio->page);
+		err = z_erofs_do_read_page(&f, &folio->page, true);
 		if (err && err != -EINTR)
 			erofs_err(inode->i_sb, "readahead error at folio %lu @ nid %llu",
 				  folio->index, EROFS_I(inode)->nid);
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 9753875e41cb..e313c936351d 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -454,7 +454,7 @@ static int z_erofs_do_map_blocks(struct inode *inode,
 		.map = map,
 	};
 	int err = 0;
-	unsigned int lclusterbits, endoff;
+	unsigned int lclusterbits, endoff, afmt;
 	unsigned long initial_lcn;
 	unsigned long long ofs, end;
 
@@ -543,17 +543,20 @@ static int z_erofs_do_map_blocks(struct inode *inode,
 			err = -EFSCORRUPTED;
 			goto unmap_out;
 		}
-		if (vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER)
-			map->m_algorithmformat =
-				Z_EROFS_COMPRESSION_INTERLACED;
-		else
-			map->m_algorithmformat =
-				Z_EROFS_COMPRESSION_SHIFTED;
-	} else if (m.headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2) {
-		map->m_algorithmformat = vi->z_algorithmtype[1];
+		afmt = vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER ?
+			Z_EROFS_COMPRESSION_INTERLACED :
+			Z_EROFS_COMPRESSION_SHIFTED;
 	} else {
-		map->m_algorithmformat = vi->z_algorithmtype[0];
+		afmt = m.headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2 ?
+			vi->z_algorithmtype[1] : vi->z_algorithmtype[0];
+		if (!(EROFS_I_SB(inode)->available_compr_algs & (1 << afmt))) {
+			erofs_err(inode->i_sb, "inconsistent algorithmtype %u for nid %llu",
+				  afmt, vi->nid);
+			err = -EFSCORRUPTED;
+			goto unmap_out;
+		}
 	}
+	map->m_algorithmformat = afmt;
 
 	if ((flags & EROFS_GET_BLOCKS_FIEMAP) ||
 	    ((flags & EROFS_GET_BLOCKS_READMORE) &&
diff --git a/fs/eventfd.c b/fs/eventfd.c
index ad8186d47ba7..9afdb722fa92 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -251,7 +251,7 @@ static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t c
 	ssize_t res;
 	__u64 ucnt;
 
-	if (count < sizeof(ucnt))
+	if (count != sizeof(ucnt))
 		return -EINVAL;
 	if (copy_from_user(&ucnt, buf, sizeof(ucnt)))
 		return -EFAULT;
@@ -283,13 +283,18 @@ static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t c
 static void eventfd_show_fdinfo(struct seq_file *m, struct file *f)
 {
 	struct eventfd_ctx *ctx = f->private_data;
+	__u64 cnt;
 
 	spin_lock_irq(&ctx->wqh.lock);
-	seq_printf(m, "eventfd-count: %16llx\n",
-		   (unsigned long long)ctx->count);
+	cnt = ctx->count;
 	spin_unlock_irq(&ctx->wqh.lock);
-	seq_printf(m, "eventfd-id: %d\n", ctx->id);
-	seq_printf(m, "eventfd-semaphore: %d\n",
+
+	seq_printf(m,
+		   "eventfd-count: %16llx\n"
+		   "eventfd-id: %d\n"
+		   "eventfd-semaphore: %d\n",
+		   cnt,
+		   ctx->id,
 		   !!(ctx->flags & EFD_SEMAPHORE));
 }
 #endif
@@ -383,6 +388,7 @@ static int do_eventfd(unsigned int count, int flags)
 	/* Check the EFD_* constants for consistency.  */
 	BUILD_BUG_ON(EFD_CLOEXEC != O_CLOEXEC);
 	BUILD_BUG_ON(EFD_NONBLOCK != O_NONBLOCK);
+	BUILD_BUG_ON(EFD_SEMAPHORE != (1 << 0));
 
 	if (flags & ~EFD_FLAGS_SET)
 		return -EINVAL;
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 3534d36a1474..39ac6fdf8bca 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -206,7 +206,7 @@ struct eventpoll {
 	 */
 	struct epitem *ovflist;
 
-	/* wakeup_source used when ep_scan_ready_list is running */
+	/* wakeup_source used when ep_send_events or __ep_eventpoll_poll is running */
 	struct wakeup_source *ws;
 
 	/* The user that created the eventpoll descriptor */
@@ -678,12 +678,6 @@ static void ep_done_scan(struct eventpoll *ep,
 	write_unlock_irq(&ep->lock);
 }
 
-static void epi_rcu_free(struct rcu_head *head)
-{
-	struct epitem *epi = container_of(head, struct epitem, rcu);
-	kmem_cache_free(epi_cache, epi);
-}
-
 static void ep_get(struct eventpoll *ep)
 {
 	refcount_inc(&ep->refcount);
@@ -767,7 +761,7 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
 	 * ep->mtx. The rcu read side, reverse_path_check_proc(), does not make
 	 * use of the rbn field.
 	 */
-	call_rcu(&epi->rcu, epi_rcu_free);
+	kfree_rcu(epi, rcu);
 
 	percpu_counter_dec(&ep->user->epoll_watches);
 	return ep_refcount_dec_and_test(ep);
@@ -1153,7 +1147,7 @@ static inline bool chain_epi_lockless(struct epitem *epi)
  * This callback takes a read lock in order not to contend with concurrent
  * events from another file descriptor, thus all modifications to ->rdllist
  * or ->ovflist are lockless.  Read lock is paired with the write lock from
- * ep_scan_ready_list(), which stops all list modifications and guarantees
+ * ep_start/done_scan(), which stops all list modifications and guarantees
  * that lists state is seen correctly.
  *
  * Another thing worth to mention is that ep_poll_callback() can be called
@@ -1751,7 +1745,7 @@ static int ep_send_events(struct eventpoll *ep,
 			 * availability. At this point, no one can insert
 			 * into ep->rdllist besides us. The epoll_ctl()
 			 * callers are locked out by
-			 * ep_scan_ready_list() holding "mtx" and the
+			 * ep_send_events() holding "mtx" and the
 			 * poll callback will queue them in ep->ovflist.
 			 */
 			list_add_tail(&epi->rdllink, &ep->rdllist);
@@ -1904,7 +1898,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 		__set_current_state(TASK_INTERRUPTIBLE);
 
 		/*
-		 * Do the final check under the lock. ep_scan_ready_list()
+		 * Do the final check under the lock. ep_start/done_scan()
 		 * plays with two lists (->rdllist and ->ovflist) and there
 		 * is always a race when both lists are empty for short
 		 * period of time although events are pending, so lock is
diff --git a/fs/exec.c b/fs/exec.c
index 73e4045df271..ece3ab0998e1 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -128,7 +128,7 @@ SYSCALL_DEFINE1(uselib, const char __user *, library)
 	struct filename *tmp = getname(library);
 	int error = PTR_ERR(tmp);
 	static const struct open_flags uselib_flags = {
-		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
+		.open_flag = O_LARGEFILE | O_RDONLY,
 		.acc_mode = MAY_READ | MAY_EXEC,
 		.intent = LOOKUP_OPEN,
 		.lookup_flags = LOOKUP_FOLLOW,
@@ -904,6 +904,10 @@ EXPORT_SYMBOL(transfer_args_to_stack);
 
 #endif /* CONFIG_MMU */
 
+/*
+ * On success, caller must call do_close_execat() on the returned
+ * struct file to close it.
+ */
 static struct file *do_open_execat(int fd, struct filename *name, int flags)
 {
 	struct file *file;
@@ -948,6 +952,17 @@ exit:
 	return ERR_PTR(err);
 }
 
+/**
+ * open_exec - Open a path name for execution
+ *
+ * @name: path name to open with the intent of executing it.
+ *
+ * Returns ERR_PTR on failure or allocated struct file on success.
+ *
+ * As this is a wrapper for the internal do_open_execat(), callers
+ * must call allow_write_access() before fput() on release. Also see
+ * do_close_execat().
+ */
 struct file *open_exec(const char *name)
 {
 	struct filename *filename = getname_kernel(name);
@@ -1143,7 +1158,6 @@ static int de_thread(struct task_struct *tsk)
 
 		BUG_ON(leader->exit_state != EXIT_ZOMBIE);
 		leader->exit_state = EXIT_DEAD;
-
 		/*
 		 * We are going to release_task()->ptrace_unlink() silently,
 		 * the tracer can sleep in do_wait(). EXIT_DEAD guarantees
@@ -1409,6 +1423,9 @@ int begin_new_exec(struct linux_binprm * bprm)
 
 out_unlock:
 	up_write(&me->signal->exec_update_lock);
+	if (!bprm->cred)
+		mutex_unlock(&me->signal->cred_guard_mutex);
+
 out:
 	return retval;
 }
@@ -1484,6 +1501,15 @@ static int prepare_bprm_creds(struct linux_binprm *bprm)
 	return -ENOMEM;
 }
 
+/* Matches do_open_execat() */
+static void do_close_execat(struct file *file)
+{
+	if (!file)
+		return;
+	allow_write_access(file);
+	fput(file);
+}
+
 static void free_bprm(struct linux_binprm *bprm)
 {
 	if (bprm->mm) {
@@ -1495,10 +1521,7 @@ static void free_bprm(struct linux_binprm *bprm)
 		mutex_unlock(&current->signal->cred_guard_mutex);
 		abort_creds(bprm->cred);
 	}
-	if (bprm->file) {
-		allow_write_access(bprm->file);
-		fput(bprm->file);
-	}
+	do_close_execat(bprm->file);
 	if (bprm->executable)
 		fput(bprm->executable);
 	/* If a binfmt changed the interp, free it. */
@@ -1508,12 +1531,23 @@ static void free_bprm(struct linux_binprm *bprm)
 	kfree(bprm);
 }
 
-static struct linux_binprm *alloc_bprm(int fd, struct filename *filename)
+static struct linux_binprm *alloc_bprm(int fd, struct filename *filename, int flags)
 {
-	struct linux_binprm *bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
+	struct linux_binprm *bprm;
+	struct file *file;
 	int retval = -ENOMEM;
-	if (!bprm)
-		goto out;
+
+	file = do_open_execat(fd, filename, flags);
+	if (IS_ERR(file))
+		return ERR_CAST(file);
+
+	bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
+	if (!bprm) {
+		do_close_execat(file);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	bprm->file = file;
 
 	if (fd == AT_FDCWD || filename->name[0] == '/') {
 		bprm->filename = filename->name;
@@ -1526,18 +1560,28 @@ static struct linux_binprm *alloc_bprm(int fd, struct filename *filename)
 		if (!bprm->fdpath)
 			goto out_free;
 
+		/*
+		 * Record that a name derived from an O_CLOEXEC fd will be
+		 * inaccessible after exec.  This allows the code in exec to
+		 * choose to fail when the executable is not mmaped into the
+		 * interpreter and an open file descriptor is not passed to
+		 * the interpreter.  This makes for a better user experience
+		 * than having the interpreter start and then immediately fail
+		 * when it finds the executable is inaccessible.
+		 */
+		if (get_close_on_exec(fd))
+			bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE;
+
 		bprm->filename = bprm->fdpath;
 	}
 	bprm->interp = bprm->filename;
 
 	retval = bprm_mm_init(bprm);
-	if (retval)
-		goto out_free;
-	return bprm;
+	if (!retval)
+		return bprm;
 
 out_free:
 	free_bprm(bprm);
-out:
 	return ERR_PTR(retval);
 }
 
@@ -1588,6 +1632,7 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
 	}
 	rcu_read_unlock();
 
+	/* "users" and "in_exec" locked for copy_fs() */
 	if (p->fs->users > n_fs)
 		bprm->unsafe |= LSM_UNSAFE_SHARE;
 	else
@@ -1804,13 +1849,8 @@ static int exec_binprm(struct linux_binprm *bprm)
 	return 0;
 }
 
-/*
- * sys_execve() executes a new program.
- */
-static int bprm_execve(struct linux_binprm *bprm,
-		       int fd, struct filename *filename, int flags)
+static int bprm_execve(struct linux_binprm *bprm)
 {
-	struct file *file;
 	int retval;
 
 	retval = prepare_bprm_creds(bprm);
@@ -1826,26 +1866,8 @@ static int bprm_execve(struct linux_binprm *bprm,
 	current->in_execve = 1;
 	sched_mm_cid_before_execve(current);
 
-	file = do_open_execat(fd, filename, flags);
-	retval = PTR_ERR(file);
-	if (IS_ERR(file))
-		goto out_unmark;
-
 	sched_exec();
 
-	bprm->file = file;
-	/*
-	 * Record that a name derived from an O_CLOEXEC fd will be
-	 * inaccessible after exec.  This allows the code in exec to
-	 * choose to fail when the executable is not mmaped into the
-	 * interpreter and an open file descriptor is not passed to
-	 * the interpreter.  This makes for a better user experience
-	 * than having the interpreter start and then immediately fail
-	 * when it finds the executable is inaccessible.
-	 */
-	if (bprm->fdpath && get_close_on_exec(fd))
-		bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE;
-
 	/* Set the unchanging part of bprm->cred */
 	retval = security_bprm_creds_for_exec(bprm);
 	if (retval)
@@ -1875,7 +1897,6 @@ out:
 	if (bprm->point_of_no_return && !fatal_signal_pending(current))
 		force_fatal_sig(SIGSEGV);
 
-out_unmark:
 	sched_mm_cid_after_execve(current);
 	current->fs->in_exec = 0;
 	current->in_execve = 0;
@@ -1910,7 +1931,7 @@ static int do_execveat_common(int fd, struct filename *filename,
 	 * further execve() calls fail. */
 	current->flags &= ~PF_NPROC_EXCEEDED;
 
-	bprm = alloc_bprm(fd, filename);
+	bprm = alloc_bprm(fd, filename, flags);
 	if (IS_ERR(bprm)) {
 		retval = PTR_ERR(bprm);
 		goto out_ret;
@@ -1959,7 +1980,7 @@ static int do_execveat_common(int fd, struct filename *filename,
 		bprm->argc = 1;
 	}
 
-	retval = bprm_execve(bprm, fd, filename, flags);
+	retval = bprm_execve(bprm);
 out_free:
 	free_bprm(bprm);
 
@@ -1984,7 +2005,7 @@ int kernel_execve(const char *kernel_filename,
 	if (IS_ERR(filename))
 		return PTR_ERR(filename);
 
-	bprm = alloc_bprm(fd, filename);
+	bprm = alloc_bprm(fd, filename, 0);
 	if (IS_ERR(bprm)) {
 		retval = PTR_ERR(bprm);
 		goto out_ret;
@@ -2019,7 +2040,7 @@ int kernel_execve(const char *kernel_filename,
 	if (retval < 0)
 		goto out_free;
 
-	retval = bprm_execve(bprm, fd, filename, 0);
+	retval = bprm_execve(bprm);
 out_free:
 	free_bprm(bprm);
 out_ret:
diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h
index 9474cd50da6d..361595433480 100644
--- a/fs/exfat/exfat_fs.h
+++ b/fs/exfat/exfat_fs.h
@@ -275,6 +275,7 @@ struct exfat_sb_info {
 
 	spinlock_t inode_hash_lock;
 	struct hlist_head inode_hashtable[EXFAT_HASH_SIZE];
+	struct rcu_head rcu;
 };
 
 #define EXFAT_CACHE_VALID	0
diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index d25a96a148af..cc00f1a7a1e1 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -35,13 +35,18 @@ static int exfat_cont_expand(struct inode *inode, loff_t size)
 	if (new_num_clusters == num_clusters)
 		goto out;
 
-	exfat_chain_set(&clu, ei->start_clu, num_clusters, ei->flags);
-	ret = exfat_find_last_cluster(sb, &clu, &last_clu);
-	if (ret)
-		return ret;
+	if (num_clusters) {
+		exfat_chain_set(&clu, ei->start_clu, num_clusters, ei->flags);
+		ret = exfat_find_last_cluster(sb, &clu, &last_clu);
+		if (ret)
+			return ret;
+
+		clu.dir = last_clu + 1;
+	} else {
+		last_clu = EXFAT_EOF_CLUSTER;
+		clu.dir = EXFAT_EOF_CLUSTER;
+	}
 
-	clu.dir = (last_clu == EXFAT_EOF_CLUSTER) ?
-			EXFAT_EOF_CLUSTER : last_clu + 1;
 	clu.size = 0;
 	clu.flags = ei->flags;
 
@@ -51,17 +56,19 @@ static int exfat_cont_expand(struct inode *inode, loff_t size)
 		return ret;
 
 	/* Append new clusters to chain */
-	if (clu.flags != ei->flags) {
-		exfat_chain_cont_cluster(sb, ei->start_clu, num_clusters);
-		ei->flags = ALLOC_FAT_CHAIN;
-	}
-	if (clu.flags == ALLOC_FAT_CHAIN)
-		if (exfat_ent_set(sb, last_clu, clu.dir))
-			goto free_clu;
-
-	if (num_clusters == 0)
+	if (num_clusters) {
+		if (clu.flags != ei->flags)
+			if (exfat_chain_cont_cluster(sb, ei->start_clu, num_clusters))
+				goto free_clu;
+
+		if (clu.flags == ALLOC_FAT_CHAIN)
+			if (exfat_ent_set(sb, last_clu, clu.dir))
+				goto free_clu;
+	} else
 		ei->start_clu = clu.dir;
 
+	ei->flags = clu.flags;
+
 out:
 	inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
 	/* Expanded range not zeroed, do not update valid_size */
diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c
index 522edcbb2ce4..0687f952956c 100644
--- a/fs/exfat/inode.c
+++ b/fs/exfat/inode.c
@@ -501,7 +501,7 @@ static ssize_t exfat_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	struct inode *inode = mapping->host;
 	struct exfat_inode_info *ei = EXFAT_I(inode);
 	loff_t pos = iocb->ki_pos;
-	loff_t size = iocb->ki_pos + iov_iter_count(iter);
+	loff_t size = pos + iov_iter_count(iter);
 	int rw = iov_iter_rw(iter);
 	ssize_t ret;
 
@@ -525,11 +525,10 @@ static ssize_t exfat_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	 */
 	ret = blockdev_direct_IO(iocb, inode, iter, exfat_get_block);
 	if (ret < 0) {
-		if (rw == WRITE)
+		if (rw == WRITE && ret != -EIOCBQUEUED)
 			exfat_write_failed(mapping, size);
 
-		if (ret != -EIOCBQUEUED)
-			return ret;
+		return ret;
 	} else
 		size = pos + ret;
 
diff --git a/fs/exfat/nls.c b/fs/exfat/nls.c
index 705710f93e2d..afdf13c34ff5 100644
--- a/fs/exfat/nls.c
+++ b/fs/exfat/nls.c
@@ -655,7 +655,6 @@ static int exfat_load_upcase_table(struct super_block *sb,
 	unsigned int sect_size = sb->s_blocksize;
 	unsigned int i, index = 0;
 	u32 chksum = 0;
-	int ret;
 	unsigned char skip = false;
 	unsigned short *upcase_table;
 
@@ -673,8 +672,7 @@ static int exfat_load_upcase_table(struct super_block *sb,
 		if (!bh) {
 			exfat_err(sb, "failed to read sector(0x%llx)",
 				  (unsigned long long)sector);
-			ret = -EIO;
-			goto free_table;
+			return -EIO;
 		}
 		sector++;
 		for (i = 0; i < sect_size && index <= 0xFFFF; i += 2) {
@@ -701,15 +699,12 @@ static int exfat_load_upcase_table(struct super_block *sb,
 
 	exfat_err(sb, "failed to load upcase table (idx : 0x%08x, chksum : 0x%08x, utbl_chksum : 0x%08x)",
 		  index, chksum, utbl_checksum);
-	ret = -EINVAL;
-free_table:
-	exfat_free_upcase_table(sbi);
-	return ret;
+	return -EINVAL;
 }
 
 static int exfat_load_default_upcase_table(struct super_block *sb)
 {
-	int i, ret = -EIO;
+	int i;
 	struct exfat_sb_info *sbi = EXFAT_SB(sb);
 	unsigned char skip = false;
 	unsigned short uni = 0, *upcase_table;
@@ -740,8 +735,7 @@ static int exfat_load_default_upcase_table(struct super_block *sb)
 		return 0;
 
 	/* FATAL error: default upcase table has error */
-	exfat_free_upcase_table(sbi);
-	return ret;
+	return -EIO;
 }
 
 int exfat_create_upcase_table(struct super_block *sb)
diff --git a/fs/exfat/super.c b/fs/exfat/super.c
index d9d4fa91010b..fcb658267765 100644
--- a/fs/exfat/super.c
+++ b/fs/exfat/super.c
@@ -39,9 +39,6 @@ static void exfat_put_super(struct super_block *sb)
 	exfat_free_bitmap(sbi);
 	brelse(sbi->boot_bh);
 	mutex_unlock(&sbi->s_lock);
-
-	unload_nls(sbi->nls_io);
-	exfat_free_upcase_table(sbi);
 }
 
 static int exfat_sync_fs(struct super_block *sb, int wait)
@@ -600,7 +597,7 @@ static int __exfat_fill_super(struct super_block *sb)
 	ret = exfat_load_bitmap(sb);
 	if (ret) {
 		exfat_err(sb, "failed to load alloc-bitmap");
-		goto free_upcase_table;
+		goto free_bh;
 	}
 
 	ret = exfat_count_used_clusters(sb, &sbi->used_clusters);
@@ -613,8 +610,6 @@ static int __exfat_fill_super(struct super_block *sb)
 
 free_alloc_bitmap:
 	exfat_free_bitmap(sbi);
-free_upcase_table:
-	exfat_free_upcase_table(sbi);
 free_bh:
 	brelse(sbi->boot_bh);
 	return ret;
@@ -701,12 +696,10 @@ put_inode:
 	sb->s_root = NULL;
 
 free_table:
-	exfat_free_upcase_table(sbi);
 	exfat_free_bitmap(sbi);
 	brelse(sbi->boot_bh);
 
 check_nls_io:
-	unload_nls(sbi->nls_io);
 	return err;
 }
 
@@ -771,13 +764,22 @@ static int exfat_init_fs_context(struct fs_context *fc)
 	return 0;
 }
 
+static void delayed_free(struct rcu_head *p)
+{
+	struct exfat_sb_info *sbi = container_of(p, struct exfat_sb_info, rcu);
+
+	unload_nls(sbi->nls_io);
+	exfat_free_upcase_table(sbi);
+	exfat_free_sbi(sbi);
+}
+
 static void exfat_kill_sb(struct super_block *sb)
 {
 	struct exfat_sb_info *sbi = sb->s_fs_info;
 
 	kill_block_super(sb);
 	if (sbi)
-		exfat_free_sbi(sbi);
+		call_rcu(&sbi->rcu, delayed_free);
 }
 
 static struct file_system_type exfat_fs_type = {
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 3ae0154c5680..07ea3d62b298 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -255,7 +255,7 @@ static bool filldir_one(struct dir_context *ctx, const char *name, int len,
 		container_of(ctx, struct getdents_callback, ctx);
 
 	buf->sequence++;
-	if (buf->ino == ino && len <= NAME_MAX) {
+	if (buf->ino == ino && len <= NAME_MAX && !is_dot_dotdot(name, len)) {
 		memcpy(buf->name, name, len);
 		buf->name[len] = '\0';
 		buf->found = 1;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index a5d784872303..3c0d7d143036 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -252,8 +252,10 @@ struct ext4_allocation_request {
 #define EXT4_MAP_MAPPED		BIT(BH_Mapped)
 #define EXT4_MAP_UNWRITTEN	BIT(BH_Unwritten)
 #define EXT4_MAP_BOUNDARY	BIT(BH_Boundary)
+#define EXT4_MAP_DELAYED	BIT(BH_Delay)
 #define EXT4_MAP_FLAGS		(EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
-				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY)
+				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
+				 EXT4_MAP_DELAYED)
 
 struct ext4_map_blocks {
 	ext4_fsblk_t m_pblk;
@@ -1548,7 +1550,7 @@ struct ext4_sb_info {
 	unsigned long s_commit_interval;
 	u32 s_max_batch_time;
 	u32 s_min_batch_time;
-	struct bdev_handle *s_journal_bdev_handle;
+	struct file *s_journal_bdev_file;
 #ifdef CONFIG_QUOTA
 	/* Names of quota files with journalled quota */
 	char __rcu *s_qf_names[EXT4_MAXQUOTAS];
@@ -2912,10 +2914,10 @@ extern const struct seq_operations ext4_mb_seq_groups_ops;
 extern const struct seq_operations ext4_mb_seq_structs_summary_ops;
 extern int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset);
 extern int ext4_mb_init(struct super_block *);
-extern int ext4_mb_release(struct super_block *);
+extern void ext4_mb_release(struct super_block *);
 extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
 				struct ext4_allocation_request *, int *);
-extern void ext4_discard_preallocations(struct inode *, unsigned int);
+extern void ext4_discard_preallocations(struct inode *);
 extern int __init ext4_init_mballoc(void);
 extern void ext4_exit_mballoc(void);
 extern ext4_group_t ext4_mb_prefetch(struct super_block *sb,
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 01299b55a567..7669d154c05e 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -100,7 +100,7 @@ static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped)
 	 * i_rwsem. So we can safely drop the i_data_sem here.
 	 */
 	BUG_ON(EXT4_JOURNAL(inode) == NULL);
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 	up_write(&EXT4_I(inode)->i_data_sem);
 	*dropped = 1;
 	return 0;
@@ -2229,7 +2229,7 @@ static int ext4_fill_es_cache_info(struct inode *inode,
 
 
 /*
- * ext4_ext_determine_hole - determine hole around given block
+ * ext4_ext_find_hole - find hole around given block according to the given path
  * @inode:	inode we lookup in
  * @path:	path in extent tree to @lblk
  * @lblk:	pointer to logical block around which we want to determine hole
@@ -2241,9 +2241,9 @@ static int ext4_fill_es_cache_info(struct inode *inode,
  * The function returns the length of a hole starting at @lblk. We update @lblk
  * to the beginning of the hole if we managed to find it.
  */
-static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode,
-					   struct ext4_ext_path *path,
-					   ext4_lblk_t *lblk)
+static ext4_lblk_t ext4_ext_find_hole(struct inode *inode,
+				      struct ext4_ext_path *path,
+				      ext4_lblk_t *lblk)
 {
 	int depth = ext_depth(inode);
 	struct ext4_extent *ex;
@@ -2271,30 +2271,6 @@ static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode,
 }
 
 /*
- * ext4_ext_put_gap_in_cache:
- * calculate boundaries of the gap that the requested block fits into
- * and cache this gap
- */
-static void
-ext4_ext_put_gap_in_cache(struct inode *inode, ext4_lblk_t hole_start,
-			  ext4_lblk_t hole_len)
-{
-	struct extent_status es;
-
-	ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start,
-				  hole_start + hole_len - 1, &es);
-	if (es.es_len) {
-		/* There's delayed extent containing lblock? */
-		if (es.es_lblk <= hole_start)
-			return;
-		hole_len = min(es.es_lblk - hole_start, hole_len);
-	}
-	ext_debug(inode, " -> %u:%u\n", hole_start, hole_len);
-	ext4_es_insert_extent(inode, hole_start, hole_len, ~0,
-			      EXTENT_STATUS_HOLE);
-}
-
-/*
  * ext4_ext_rm_idx:
  * removes index from the index block.
  */
@@ -4062,6 +4038,72 @@ static int get_implied_cluster_alloc(struct super_block *sb,
 	return 0;
 }
 
+/*
+ * Determine hole length around the given logical block, first try to
+ * locate and expand the hole from the given @path, and then adjust it
+ * if it's partially or completely converted to delayed extents, insert
+ * it into the extent cache tree if it's indeed a hole, finally return
+ * the length of the determined extent.
+ */
+static ext4_lblk_t ext4_ext_determine_insert_hole(struct inode *inode,
+						  struct ext4_ext_path *path,
+						  ext4_lblk_t lblk)
+{
+	ext4_lblk_t hole_start, len;
+	struct extent_status es;
+
+	hole_start = lblk;
+	len = ext4_ext_find_hole(inode, path, &hole_start);
+again:
+	ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start,
+				  hole_start + len - 1, &es);
+	if (!es.es_len)
+		goto insert_hole;
+
+	/*
+	 * There's a delalloc extent in the hole, handle it if the delalloc
+	 * extent is in front of, behind and straddle the queried range.
+	 */
+	if (lblk >= es.es_lblk + es.es_len) {
+		/*
+		 * The delalloc extent is in front of the queried range,
+		 * find again from the queried start block.
+		 */
+		len -= lblk - hole_start;
+		hole_start = lblk;
+		goto again;
+	} else if (in_range(lblk, es.es_lblk, es.es_len)) {
+		/*
+		 * The delalloc extent containing lblk, it must have been
+		 * added after ext4_map_blocks() checked the extent status
+		 * tree so we are not holding i_rwsem and delalloc info is
+		 * only stabilized by i_data_sem we are going to release
+		 * soon. Don't modify the extent status tree and report
+		 * extent as a hole, just adjust the length to the delalloc
+		 * extent's after lblk.
+		 */
+		len = es.es_lblk + es.es_len - lblk;
+		return len;
+	} else {
+		/*
+		 * The delalloc extent is partially or completely behind
+		 * the queried range, update hole length until the
+		 * beginning of the delalloc extent.
+		 */
+		len = min(es.es_lblk - hole_start, len);
+	}
+
+insert_hole:
+	/* Put just found gap into cache to speed up subsequent requests */
+	ext_debug(inode, " -> %u:%u\n", hole_start, len);
+	ext4_es_insert_extent(inode, hole_start, len, ~0, EXTENT_STATUS_HOLE);
+
+	/* Update hole_len to reflect hole size after lblk */
+	if (hole_start != lblk)
+		len -= lblk - hole_start;
+
+	return len;
+}
 
 /*
  * Block allocation/map/preallocation routine for extents based files
@@ -4179,22 +4221,12 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	 * we couldn't try to create block if create flag is zero
 	 */
 	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
-		ext4_lblk_t hole_start, hole_len;
+		ext4_lblk_t len;
 
-		hole_start = map->m_lblk;
-		hole_len = ext4_ext_determine_hole(inode, path, &hole_start);
-		/*
-		 * put just found gap into cache to speed up
-		 * subsequent requests
-		 */
-		ext4_ext_put_gap_in_cache(inode, hole_start, hole_len);
+		len = ext4_ext_determine_insert_hole(inode, path, map->m_lblk);
 
-		/* Update hole_len to reflect hole size after map->m_lblk */
-		if (hole_start != map->m_lblk)
-			hole_len -= map->m_lblk - hole_start;
 		map->m_pblk = 0;
-		map->m_len = min_t(unsigned int, map->m_len, hole_len);
-
+		map->m_len = min_t(unsigned int, map->m_len, len);
 		goto out;
 	}
 
@@ -4313,7 +4345,7 @@ got_allocated_blocks:
 			 * not a good idea to call discard here directly,
 			 * but otherwise we'd need to call it every free().
 			 */
-			ext4_discard_preallocations(inode, 0);
+			ext4_discard_preallocations(inode);
 			if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
 				fb_flags = EXT4_FREE_BLOCKS_NO_QUOT_UPDATE;
 			ext4_free_blocks(handle, inode, NULL, newblock,
@@ -5357,7 +5389,7 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len)
 	ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle);
 
 	down_write(&EXT4_I(inode)->i_data_sem);
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 	ext4_es_remove_extent(inode, punch_start, EXT_MAX_BLOCKS - punch_start);
 
 	ret = ext4_ext_remove_space(inode, punch_start, punch_stop - 1);
@@ -5365,7 +5397,7 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len)
 		up_write(&EXT4_I(inode)->i_data_sem);
 		goto out_stop;
 	}
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 
 	ret = ext4_ext_shift_extents(inode, handle, punch_stop,
 				     punch_stop - punch_start, SHIFT_LEFT);
@@ -5497,7 +5529,7 @@ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len)
 		goto out_stop;
 
 	down_write(&EXT4_I(inode)->i_data_sem);
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 
 	path = ext4_find_extent(inode, offset_lblk, NULL, 0);
 	if (IS_ERR(path)) {
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 6aa15dafc677..54d6ff22585c 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -174,7 +174,7 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
 			(atomic_read(&inode->i_writecount) == 1) &&
 			!EXT4_I(inode)->i_reserved_data_blocks) {
 		down_write(&EXT4_I(inode)->i_data_sem);
-		ext4_discard_preallocations(inode, 0);
+		ext4_discard_preallocations(inode);
 		up_write(&EXT4_I(inode)->i_data_sem);
 	}
 	if (is_dx(inode) && filp->private_data)
diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c
index 11e6f33677a2..df853c4d3a8c 100644
--- a/fs/ext4/fsmap.c
+++ b/fs/ext4/fsmap.c
@@ -576,9 +576,9 @@ static bool ext4_getfsmap_is_valid_device(struct super_block *sb,
 	if (fm->fmr_device == 0 || fm->fmr_device == UINT_MAX ||
 	    fm->fmr_device == new_encode_dev(sb->s_bdev->bd_dev))
 		return true;
-	if (EXT4_SB(sb)->s_journal_bdev_handle &&
+	if (EXT4_SB(sb)->s_journal_bdev_file &&
 	    fm->fmr_device ==
-	    new_encode_dev(EXT4_SB(sb)->s_journal_bdev_handle->bdev->bd_dev))
+	    new_encode_dev(file_bdev(EXT4_SB(sb)->s_journal_bdev_file)->bd_dev))
 		return true;
 	return false;
 }
@@ -648,9 +648,9 @@ int ext4_getfsmap(struct super_block *sb, struct ext4_fsmap_head *head,
 	memset(handlers, 0, sizeof(handlers));
 	handlers[0].gfd_dev = new_encode_dev(sb->s_bdev->bd_dev);
 	handlers[0].gfd_fn = ext4_getfsmap_datadev;
-	if (EXT4_SB(sb)->s_journal_bdev_handle) {
+	if (EXT4_SB(sb)->s_journal_bdev_file) {
 		handlers[1].gfd_dev = new_encode_dev(
-			EXT4_SB(sb)->s_journal_bdev_handle->bdev->bd_dev);
+			file_bdev(EXT4_SB(sb)->s_journal_bdev_file)->bd_dev);
 		handlers[1].gfd_fn = ext4_getfsmap_logdev;
 	}
 
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index a9f3716119d3..d8ca7f64f952 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -714,7 +714,7 @@ static int ext4_ind_trunc_restart_fn(handle_t *handle, struct inode *inode,
 	 * i_rwsem. So we can safely drop the i_data_sem here.
 	 */
 	BUG_ON(EXT4_JOURNAL(inode) == NULL);
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 	up_write(&EXT4_I(inode)->i_data_sem);
 	*dropped = 1;
 	return 0;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 5af1b0b8680e..2ccf3b5e3a7c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -371,7 +371,7 @@ void ext4_da_update_reserve_space(struct inode *inode,
 	 */
 	if ((ei->i_reserved_data_blocks == 0) &&
 	    !inode_is_open_for_write(inode))
-		ext4_discard_preallocations(inode, 0);
+		ext4_discard_preallocations(inode);
 }
 
 static int __check_block_validity(struct inode *inode, const char *func,
@@ -515,6 +515,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 			map->m_len = retval;
 		} else if (ext4_es_is_delayed(&es) || ext4_es_is_hole(&es)) {
 			map->m_pblk = 0;
+			map->m_flags |= ext4_es_is_delayed(&es) ?
+					EXT4_MAP_DELAYED : 0;
 			retval = es.es_len - (map->m_lblk - es.es_lblk);
 			if (retval > map->m_len)
 				retval = map->m_len;
@@ -1703,11 +1705,8 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 
 	/* Lookup extent status tree firstly */
 	if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) {
-		if (ext4_es_is_hole(&es)) {
-			retval = 0;
-			down_read(&EXT4_I(inode)->i_data_sem);
+		if (ext4_es_is_hole(&es))
 			goto add_delayed;
-		}
 
 		/*
 		 * Delayed extent could be allocated by fallocate.
@@ -1749,26 +1748,11 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 		retval = ext4_ext_map_blocks(NULL, inode, map, 0);
 	else
 		retval = ext4_ind_map_blocks(NULL, inode, map, 0);
-
-add_delayed:
-	if (retval == 0) {
-		int ret;
-
-		/*
-		 * XXX: __block_prepare_write() unmaps passed block,
-		 * is it OK?
-		 */
-
-		ret = ext4_insert_delayed_block(inode, map->m_lblk);
-		if (ret != 0) {
-			retval = ret;
-			goto out_unlock;
-		}
-
-		map_bh(bh, inode->i_sb, invalid_block);
-		set_buffer_new(bh);
-		set_buffer_delay(bh);
-	} else if (retval > 0) {
+	if (retval < 0) {
+		up_read(&EXT4_I(inode)->i_data_sem);
+		return retval;
+	}
+	if (retval > 0) {
 		unsigned int status;
 
 		if (unlikely(retval != map->m_len)) {
@@ -1783,11 +1767,21 @@ add_delayed:
 				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
 		ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
 				      map->m_pblk, status);
+		up_read(&EXT4_I(inode)->i_data_sem);
+		return retval;
 	}
+	up_read(&EXT4_I(inode)->i_data_sem);
 
-out_unlock:
-	up_read((&EXT4_I(inode)->i_data_sem));
+add_delayed:
+	down_write(&EXT4_I(inode)->i_data_sem);
+	retval = ext4_insert_delayed_block(inode, map->m_lblk);
+	up_write(&EXT4_I(inode)->i_data_sem);
+	if (retval)
+		return retval;
 
+	map_bh(bh, inode->i_sb, invalid_block);
+	set_buffer_new(bh);
+	set_buffer_delay(bh);
 	return retval;
 }
 
@@ -3268,6 +3262,9 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
 		iomap->addr = (u64) map->m_pblk << blkbits;
 		if (flags & IOMAP_DAX)
 			iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off;
+	} else if (map->m_flags & EXT4_MAP_DELAYED) {
+		iomap->type = IOMAP_DELALLOC;
+		iomap->addr = IOMAP_NULL_ADDR;
 	} else {
 		iomap->type = IOMAP_HOLE;
 		iomap->addr = IOMAP_NULL_ADDR;
@@ -3430,35 +3427,11 @@ const struct iomap_ops ext4_iomap_overwrite_ops = {
 	.iomap_end		= ext4_iomap_end,
 };
 
-static bool ext4_iomap_is_delalloc(struct inode *inode,
-				   struct ext4_map_blocks *map)
-{
-	struct extent_status es;
-	ext4_lblk_t offset = 0, end = map->m_lblk + map->m_len - 1;
-
-	ext4_es_find_extent_range(inode, &ext4_es_is_delayed,
-				  map->m_lblk, end, &es);
-
-	if (!es.es_len || es.es_lblk > end)
-		return false;
-
-	if (es.es_lblk > map->m_lblk) {
-		map->m_len = es.es_lblk - map->m_lblk;
-		return false;
-	}
-
-	offset = map->m_lblk - es.es_lblk;
-	map->m_len = es.es_len - offset;
-
-	return true;
-}
-
 static int ext4_iomap_begin_report(struct inode *inode, loff_t offset,
 				   loff_t length, unsigned int flags,
 				   struct iomap *iomap, struct iomap *srcmap)
 {
 	int ret;
-	bool delalloc = false;
 	struct ext4_map_blocks map;
 	u8 blkbits = inode->i_blkbits;
 
@@ -3499,13 +3472,8 @@ static int ext4_iomap_begin_report(struct inode *inode, loff_t offset,
 	ret = ext4_map_blocks(NULL, inode, &map, 0);
 	if (ret < 0)
 		return ret;
-	if (ret == 0)
-		delalloc = ext4_iomap_is_delalloc(inode, &map);
-
 set_iomap:
 	ext4_set_iomap(inode, iomap, &map, offset, length, flags);
-	if (delalloc && iomap->type == IOMAP_HOLE)
-		iomap->type = IOMAP_DELALLOC;
 
 	return 0;
 }
@@ -4015,12 +3983,12 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
 
 	/* If there are blocks to remove, do it */
 	if (stop_block > first_block) {
+		ext4_lblk_t hole_len = stop_block - first_block;
 
 		down_write(&EXT4_I(inode)->i_data_sem);
-		ext4_discard_preallocations(inode, 0);
+		ext4_discard_preallocations(inode);
 
-		ext4_es_remove_extent(inode, first_block,
-				      stop_block - first_block);
+		ext4_es_remove_extent(inode, first_block, hole_len);
 
 		if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 			ret = ext4_ext_remove_space(inode, first_block,
@@ -4029,6 +3997,8 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
 			ret = ext4_ind_remove_space(handle, inode, first_block,
 						    stop_block);
 
+		ext4_es_insert_extent(inode, first_block, hole_len, ~0,
+				      EXTENT_STATUS_HOLE);
 		up_write(&EXT4_I(inode)->i_data_sem);
 	}
 	ext4_fc_track_range(handle, inode, first_block, stop_block);
@@ -4170,7 +4140,7 @@ int ext4_truncate(struct inode *inode)
 
 	down_write(&EXT4_I(inode)->i_data_sem);
 
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 		err = ext4_ext_truncate(handle, inode);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index aa6be510eb8f..7160a71044c8 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -467,7 +467,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 	ext4_reset_inode_seed(inode);
 	ext4_reset_inode_seed(inode_bl);
 
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 
 	err = ext4_mark_inode_dirty(handle, inode);
 	if (err < 0) {
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index f44f668e407f..e4f7cf9d89c4 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -564,14 +564,14 @@ static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b,
 
 			blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
 			blocknr += EXT4_C2B(EXT4_SB(sb), first + i);
+			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			ext4_grp_locked_error(sb, e4b->bd_group,
 					      inode ? inode->i_ino : 0,
 					      blocknr,
 					      "freeing block already freed "
 					      "(bit %u)",
 					      first + i);
-			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
-					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 		}
 		mb_clear_bit(first + i, e4b->bd_info->bb_bitmap);
 	}
@@ -677,7 +677,7 @@ do {									\
 	}								\
 } while (0)
 
-static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
+static void __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 				const char *function, int line)
 {
 	struct super_block *sb = e4b->bd_sb;
@@ -696,7 +696,7 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 	void *buddy2;
 
 	if (e4b->bd_info->bb_check_counter++ % 10)
-		return 0;
+		return;
 
 	while (order > 1) {
 		buddy = mb_find_buddy(e4b, order, &max);
@@ -758,7 +758,7 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 
 	grp = ext4_get_group_info(sb, e4b->bd_group);
 	if (!grp)
-		return NULL;
+		return;
 	list_for_each(cur, &grp->bb_prealloc_list) {
 		ext4_group_t groupnr;
 		struct ext4_prealloc_space *pa;
@@ -768,7 +768,6 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 		for (i = 0; i < pa->pa_len; i++)
 			MB_CHECK_ASSERT(mb_test_bit(k + i, buddy));
 	}
-	return 0;
 }
 #undef MB_CHECK_ASSERT
 #define mb_check_buddy(e4b) __mb_check_buddy(e4b,	\
@@ -842,7 +841,7 @@ mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp)
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	int new_order;
 
-	if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_free == 0)
+	if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_fragments == 0)
 		return;
 
 	new_order = mb_avg_fragment_size_order(sb,
@@ -871,7 +870,7 @@ mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp)
  * cr level needs an update.
  */
 static void ext4_mb_choose_next_group_p2_aligned(struct ext4_allocation_context *ac,
-			enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups)
+			enum criteria *new_cr, ext4_group_t *group)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_group_info *iter;
@@ -945,7 +944,7 @@ ext4_mb_find_good_group_avg_frag_lists(struct ext4_allocation_context *ac, int o
  * order. Updates *new_cr if cr level needs an update.
  */
 static void ext4_mb_choose_next_group_goal_fast(struct ext4_allocation_context *ac,
-		enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups)
+		enum criteria *new_cr, ext4_group_t *group)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_group_info *grp = NULL;
@@ -990,7 +989,7 @@ static void ext4_mb_choose_next_group_goal_fast(struct ext4_allocation_context *
  * much and fall to CR_GOAL_LEN_SLOW in that case.
  */
 static void ext4_mb_choose_next_group_best_avail(struct ext4_allocation_context *ac,
-		enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups)
+		enum criteria *new_cr, ext4_group_t *group)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_group_info *grp = NULL;
@@ -1125,11 +1124,11 @@ static void ext4_mb_choose_next_group(struct ext4_allocation_context *ac,
 	}
 
 	if (*new_cr == CR_POWER2_ALIGNED) {
-		ext4_mb_choose_next_group_p2_aligned(ac, new_cr, group, ngroups);
+		ext4_mb_choose_next_group_p2_aligned(ac, new_cr, group);
 	} else if (*new_cr == CR_GOAL_LEN_FAST) {
-		ext4_mb_choose_next_group_goal_fast(ac, new_cr, group, ngroups);
+		ext4_mb_choose_next_group_goal_fast(ac, new_cr, group);
 	} else if (*new_cr == CR_BEST_AVAIL_LEN) {
-		ext4_mb_choose_next_group_best_avail(ac, new_cr, group, ngroups);
+		ext4_mb_choose_next_group_best_avail(ac, new_cr, group);
 	} else {
 		/*
 		 * TODO: For CR=2, we can arrange groups in an rb tree sorted by
@@ -1233,6 +1232,24 @@ void ext4_mb_generate_buddy(struct super_block *sb,
 	atomic64_add(period, &sbi->s_mb_generation_time);
 }
 
+static void mb_regenerate_buddy(struct ext4_buddy *e4b)
+{
+	int count;
+	int order = 1;
+	void *buddy;
+
+	while ((buddy = mb_find_buddy(e4b, order++, &count)))
+		mb_set_bits(buddy, 0, count);
+
+	e4b->bd_info->bb_fragments = 0;
+	memset(e4b->bd_info->bb_counters, 0,
+		sizeof(*e4b->bd_info->bb_counters) *
+		(e4b->bd_sb->s_blocksize_bits + 2));
+
+	ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy,
+		e4b->bd_bitmap, e4b->bd_group, e4b->bd_info);
+}
+
 /* The buddy information is attached the buddy cache inode
  * for convenience. The information regarding each group
  * is loaded via ext4_mb_load_buddy. The information involve
@@ -1891,11 +1908,6 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 	mb_check_buddy(e4b);
 	mb_free_blocks_double(inode, e4b, first, count);
 
-	this_cpu_inc(discard_pa_seq);
-	e4b->bd_info->bb_free += count;
-	if (first < e4b->bd_info->bb_first_free)
-		e4b->bd_info->bb_first_free = first;
-
 	/* access memory sequentially: check left neighbour,
 	 * clear range and then check right neighbour
 	 */
@@ -1909,21 +1921,31 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 		struct ext4_sb_info *sbi = EXT4_SB(sb);
 		ext4_fsblk_t blocknr;
 
+		/*
+		 * Fastcommit replay can free already freed blocks which
+		 * corrupts allocation info. Regenerate it.
+		 */
+		if (sbi->s_mount_state & EXT4_FC_REPLAY) {
+			mb_regenerate_buddy(e4b);
+			goto check;
+		}
+
 		blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
 		blocknr += EXT4_C2B(sbi, block);
-		if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
-			ext4_grp_locked_error(sb, e4b->bd_group,
-					      inode ? inode->i_ino : 0,
-					      blocknr,
-					      "freeing already freed block (bit %u); block bitmap corrupt.",
-					      block);
-			ext4_mark_group_bitmap_corrupted(
-				sb, e4b->bd_group,
+		ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
 				EXT4_GROUP_INFO_BBITMAP_CORRUPT);
-		}
-		goto done;
+		ext4_grp_locked_error(sb, e4b->bd_group,
+				      inode ? inode->i_ino : 0, blocknr,
+				      "freeing already freed block (bit %u); block bitmap corrupt.",
+				      block);
+		return;
 	}
 
+	this_cpu_inc(discard_pa_seq);
+	e4b->bd_info->bb_free += count;
+	if (first < e4b->bd_info->bb_first_free)
+		e4b->bd_info->bb_first_free = first;
+
 	/* let's maintain fragments counter */
 	if (left_is_free && right_is_free)
 		e4b->bd_info->bb_fragments--;
@@ -1948,9 +1970,9 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 	if (first <= last)
 		mb_buddy_mark_free(e4b, first >> 1, last >> 1);
 
-done:
 	mb_set_largest_free_order(sb, e4b->bd_info);
 	mb_update_avg_fragment_size(sb, e4b->bd_info);
+check:
 	mb_check_buddy(e4b);
 }
 
@@ -2276,6 +2298,9 @@ void ext4_mb_try_best_found(struct ext4_allocation_context *ac,
 		return;
 
 	ext4_lock_group(ac->ac_sb, group);
+	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
+		goto out;
+
 	max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex);
 
 	if (max > 0) {
@@ -2283,6 +2308,7 @@ void ext4_mb_try_best_found(struct ext4_allocation_context *ac,
 		ext4_mb_use_best_found(ac, e4b);
 	}
 
+out:
 	ext4_unlock_group(ac->ac_sb, group);
 	ext4_mb_unload_buddy(e4b);
 }
@@ -2309,12 +2335,10 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
 	if (err)
 		return err;
 
-	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) {
-		ext4_mb_unload_buddy(e4b);
-		return 0;
-	}
-
 	ext4_lock_group(ac->ac_sb, group);
+	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
+		goto out;
+
 	max = mb_find_extent(e4b, ac->ac_g_ex.fe_start,
 			     ac->ac_g_ex.fe_len, &ex);
 	ex.fe_logical = 0xDEADFA11; /* debug value */
@@ -2347,6 +2371,7 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
 		ac->ac_b_ex = ex;
 		ext4_mb_use_best_found(ac, e4b);
 	}
+out:
 	ext4_unlock_group(ac->ac_sb, group);
 	ext4_mb_unload_buddy(e4b);
 
@@ -2380,12 +2405,12 @@ void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac,
 
 		k = mb_find_next_zero_bit(buddy, max, 0);
 		if (k >= max) {
+			ext4_mark_group_bitmap_corrupted(ac->ac_sb,
+					e4b->bd_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			ext4_grp_locked_error(ac->ac_sb, e4b->bd_group, 0, 0,
 				"%d free clusters of order %d. But found 0",
 				grp->bb_counters[i], i);
-			ext4_mark_group_bitmap_corrupted(ac->ac_sb,
-					 e4b->bd_group,
-					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			break;
 		}
 		ac->ac_found++;
@@ -2436,12 +2461,12 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
 			 * free blocks even though group info says we
 			 * have free blocks
 			 */
+			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
 					"%d free clusters as per "
 					"group info. But bitmap says 0",
 					free);
-			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
-					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			break;
 		}
 
@@ -2467,12 +2492,12 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
 		if (WARN_ON(ex.fe_len <= 0))
 			break;
 		if (free < ex.fe_len) {
+			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
 					"%d free clusters as per "
 					"group info. But got %d blocks",
 					free, ex.fe_len);
-			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
-					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			/*
 			 * The number of free blocks differs. This mostly
 			 * indicate that the bitmap is corrupt. So exit
@@ -3725,7 +3750,7 @@ static int ext4_mb_cleanup_pa(struct ext4_group_info *grp)
 	return count;
 }
 
-int ext4_mb_release(struct super_block *sb)
+void ext4_mb_release(struct super_block *sb)
 {
 	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	ext4_group_t i;
@@ -3801,8 +3826,6 @@ int ext4_mb_release(struct super_block *sb)
 	}
 
 	free_percpu(sbi->s_locality_groups);
-
-	return 0;
 }
 
 static inline int ext4_issue_discard(struct super_block *sb,
@@ -5284,7 +5307,7 @@ static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac)
  * the caller MUST hold group/inode locks.
  * TODO: optimize the case when there are no in-core structures yet
  */
-static noinline_for_stack int
+static noinline_for_stack void
 ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 			struct ext4_prealloc_space *pa)
 {
@@ -5334,11 +5357,9 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 		 */
 	}
 	atomic_add(free, &sbi->s_mb_discarded);
-
-	return 0;
 }
 
-static noinline_for_stack int
+static noinline_for_stack void
 ext4_mb_release_group_pa(struct ext4_buddy *e4b,
 				struct ext4_prealloc_space *pa)
 {
@@ -5352,13 +5373,11 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b,
 	if (unlikely(group != e4b->bd_group && pa->pa_len != 0)) {
 		ext4_warning(sb, "bad group: expected %u, group %u, pa_start %llu",
 			     e4b->bd_group, group, pa->pa_pstart);
-		return 0;
+		return;
 	}
 	mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len);
 	atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded);
 	trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len);
-
-	return 0;
 }
 
 /*
@@ -5479,7 +5498,7 @@ out_dbg:
  *
  * FIXME!! Make sure it is valid at all the call sites
  */
-void ext4_discard_preallocations(struct inode *inode, unsigned int needed)
+void ext4_discard_preallocations(struct inode *inode)
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct super_block *sb = inode->i_sb;
@@ -5491,9 +5510,8 @@ void ext4_discard_preallocations(struct inode *inode, unsigned int needed)
 	struct rb_node *iter;
 	int err;
 
-	if (!S_ISREG(inode->i_mode)) {
+	if (!S_ISREG(inode->i_mode))
 		return;
-	}
 
 	if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)
 		return;
@@ -5501,15 +5519,12 @@ void ext4_discard_preallocations(struct inode *inode, unsigned int needed)
 	mb_debug(sb, "discard preallocation for inode %lu\n",
 		 inode->i_ino);
 	trace_ext4_discard_preallocations(inode,
-			atomic_read(&ei->i_prealloc_active), needed);
-
-	if (needed == 0)
-		needed = UINT_MAX;
+			atomic_read(&ei->i_prealloc_active));
 
 repeat:
 	/* first, collect all pa's in the inode */
 	write_lock(&ei->i_prealloc_lock);
-	for (iter = rb_first(&ei->i_prealloc_node); iter && needed;
+	for (iter = rb_first(&ei->i_prealloc_node); iter;
 	     iter = rb_next(iter)) {
 		pa = rb_entry(iter, struct ext4_prealloc_space,
 			      pa_node.inode_node);
@@ -5533,7 +5548,6 @@ repeat:
 			spin_unlock(&pa->pa_lock);
 			rb_erase(&pa->pa_node.inode_node, &ei->i_prealloc_node);
 			list_add(&pa->u.pa_tmp_list, &list);
-			needed--;
 			continue;
 		}
 
@@ -5943,7 +5957,7 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac)
 /*
  * release all resource we used in allocation
  */
-static int ext4_mb_release_context(struct ext4_allocation_context *ac)
+static void ext4_mb_release_context(struct ext4_allocation_context *ac)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_prealloc_space *pa = ac->ac_pa;
@@ -5980,7 +5994,6 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac)
 	if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC)
 		mutex_unlock(&ac->ac_lg->lg_mutex);
 	ext4_mb_collect_stats(ac);
-	return 0;
 }
 
 static int ext4_mb_discard_preallocations(struct super_block *sb, int needed)
@@ -6761,6 +6774,9 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group))
 	bool set_trimmed = false;
 	void *bitmap;
 
+	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
+		return 0;
+
 	last = ext4_last_grp_cluster(sb, e4b->bd_group);
 	bitmap = e4b->bd_bitmap;
 	if (start == 0 && max >= last)
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index d7aeb5da7d86..56938532b4ce 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -192,7 +192,6 @@ struct ext4_allocation_context {
 	 */
 	ext4_grpblk_t	ac_orig_goal_len;
 
-	__u32 ac_groups_considered;
 	__u32 ac_flags;		/* allocation hints */
 	__u16 ac_groups_scanned;
 	__u16 ac_groups_linear_remaining;
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 3aa57376d9c2..7cd4afa4de1d 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -618,6 +618,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
 		goto out;
 	o_end = o_start + len;
 
+	*moved_len = 0;
 	while (o_start < o_end) {
 		struct ext4_extent *ex;
 		ext4_lblk_t cur_blk, next_blk;
@@ -672,7 +673,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
 		 */
 		ext4_double_up_write_data_sem(orig_inode, donor_inode);
 		/* Swap original branches with new branches */
-		move_extent_per_page(o_filp, donor_inode,
+		*moved_len += move_extent_per_page(o_filp, donor_inode,
 				     orig_page_index, donor_page_index,
 				     offset_in_page, cur_len,
 				     unwritten, &ret);
@@ -682,14 +683,11 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
 		o_start += cur_len;
 		d_start += cur_len;
 	}
-	*moved_len = o_start - orig_blk;
-	if (*moved_len > len)
-		*moved_len = len;
 
 out:
 	if (*moved_len) {
-		ext4_discard_preallocations(orig_inode, 0);
-		ext4_discard_preallocations(donor_inode, 0);
+		ext4_discard_preallocations(orig_inode);
+		ext4_discard_preallocations(donor_inode);
 	}
 
 	ext4_free_ext_path(path);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 05b647e6bc19..5e4f65c14dfb 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1762,7 +1762,6 @@ static struct buffer_head *ext4_lookup_entry(struct inode *dir,
 	struct buffer_head *bh;
 
 	err = ext4_fname_prepare_lookup(dir, dentry, &fname);
-	generic_set_encrypted_ci_d_ops(dentry);
 	if (err == -ENOENT)
 		return NULL;
 	if (err)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index dcba0f85dfe2..a8ba84eabab2 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1359,14 +1359,14 @@ static void ext4_put_super(struct super_block *sb)
 
 	sync_blockdev(sb->s_bdev);
 	invalidate_bdev(sb->s_bdev);
-	if (sbi->s_journal_bdev_handle) {
+	if (sbi->s_journal_bdev_file) {
 		/*
 		 * Invalidate the journal device's buffers.  We don't want them
 		 * floating about in memory - the physical journal device may
 		 * hotswapped, and it breaks the `ro-after' testing code.
 		 */
-		sync_blockdev(sbi->s_journal_bdev_handle->bdev);
-		invalidate_bdev(sbi->s_journal_bdev_handle->bdev);
+		sync_blockdev(file_bdev(sbi->s_journal_bdev_file));
+		invalidate_bdev(file_bdev(sbi->s_journal_bdev_file));
 	}
 
 	ext4_xattr_destroy_cache(sbi->s_ea_inode_cache);
@@ -1525,7 +1525,7 @@ void ext4_clear_inode(struct inode *inode)
 	ext4_fc_del(inode);
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 	ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
 	dquot_drop(inode);
 	if (EXT4_I(inode)->jinode) {
@@ -4233,7 +4233,7 @@ int ext4_calculate_overhead(struct super_block *sb)
 	 * Add the internal journal blocks whether the journal has been
 	 * loaded or not
 	 */
-	if (sbi->s_journal && !sbi->s_journal_bdev_handle)
+	if (sbi->s_journal && !sbi->s_journal_bdev_file)
 		overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_total_len);
 	else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) {
 		/* j_inum for internal journal is non-zero */
@@ -5346,7 +5346,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 		sb->s_qcop = &ext4_qctl_operations;
 	sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ;
 #endif
-	memcpy(&sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
+	super_set_uuid(sb, es->s_uuid, sizeof(es->s_uuid));
 
 	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
 	mutex_init(&sbi->s_orphan_lock);
@@ -5484,6 +5484,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 		goto failed_mount4;
 	}
 
+	generic_set_sb_d_ops(sb);
 	sb->s_root = d_make_root(root);
 	if (!sb->s_root) {
 		ext4_msg(sb, KERN_ERR, "get root dentry failed");
@@ -5670,9 +5671,9 @@ failed_mount:
 #endif
 	fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy);
 	brelse(sbi->s_sbh);
-	if (sbi->s_journal_bdev_handle) {
-		invalidate_bdev(sbi->s_journal_bdev_handle->bdev);
-		bdev_release(sbi->s_journal_bdev_handle);
+	if (sbi->s_journal_bdev_file) {
+		invalidate_bdev(file_bdev(sbi->s_journal_bdev_file));
+		fput(sbi->s_journal_bdev_file);
 	}
 out_fail:
 	invalidate_bdev(sb->s_bdev);
@@ -5842,30 +5843,30 @@ static journal_t *ext4_open_inode_journal(struct super_block *sb,
 	return journal;
 }
 
-static struct bdev_handle *ext4_get_journal_blkdev(struct super_block *sb,
+static struct file *ext4_get_journal_blkdev(struct super_block *sb,
 					dev_t j_dev, ext4_fsblk_t *j_start,
 					ext4_fsblk_t *j_len)
 {
 	struct buffer_head *bh;
 	struct block_device *bdev;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	int hblock, blocksize;
 	ext4_fsblk_t sb_block;
 	unsigned long offset;
 	struct ext4_super_block *es;
 	int errno;
 
-	bdev_handle = bdev_open_by_dev(j_dev,
+	bdev_file = bdev_file_open_by_dev(j_dev,
 		BLK_OPEN_READ | BLK_OPEN_WRITE | BLK_OPEN_RESTRICT_WRITES,
 		sb, &fs_holder_ops);
-	if (IS_ERR(bdev_handle)) {
+	if (IS_ERR(bdev_file)) {
 		ext4_msg(sb, KERN_ERR,
 			 "failed to open journal device unknown-block(%u,%u) %ld",
-			 MAJOR(j_dev), MINOR(j_dev), PTR_ERR(bdev_handle));
-		return bdev_handle;
+			 MAJOR(j_dev), MINOR(j_dev), PTR_ERR(bdev_file));
+		return bdev_file;
 	}
 
-	bdev = bdev_handle->bdev;
+	bdev = file_bdev(bdev_file);
 	blocksize = sb->s_blocksize;
 	hblock = bdev_logical_block_size(bdev);
 	if (blocksize < hblock) {
@@ -5912,12 +5913,12 @@ static struct bdev_handle *ext4_get_journal_blkdev(struct super_block *sb,
 	*j_start = sb_block + 1;
 	*j_len = ext4_blocks_count(es);
 	brelse(bh);
-	return bdev_handle;
+	return bdev_file;
 
 out_bh:
 	brelse(bh);
 out_bdev:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 	return ERR_PTR(errno);
 }
 
@@ -5927,14 +5928,14 @@ static journal_t *ext4_open_dev_journal(struct super_block *sb,
 	journal_t *journal;
 	ext4_fsblk_t j_start;
 	ext4_fsblk_t j_len;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	int errno = 0;
 
-	bdev_handle = ext4_get_journal_blkdev(sb, j_dev, &j_start, &j_len);
-	if (IS_ERR(bdev_handle))
-		return ERR_CAST(bdev_handle);
+	bdev_file = ext4_get_journal_blkdev(sb, j_dev, &j_start, &j_len);
+	if (IS_ERR(bdev_file))
+		return ERR_CAST(bdev_file);
 
-	journal = jbd2_journal_init_dev(bdev_handle->bdev, sb->s_bdev, j_start,
+	journal = jbd2_journal_init_dev(file_bdev(bdev_file), sb->s_bdev, j_start,
 					j_len, sb->s_blocksize);
 	if (IS_ERR(journal)) {
 		ext4_msg(sb, KERN_ERR, "failed to create device journal");
@@ -5949,14 +5950,14 @@ static journal_t *ext4_open_dev_journal(struct super_block *sb,
 		goto out_journal;
 	}
 	journal->j_private = sb;
-	EXT4_SB(sb)->s_journal_bdev_handle = bdev_handle;
+	EXT4_SB(sb)->s_journal_bdev_file = bdev_file;
 	ext4_init_journal_params(sb, journal);
 	return journal;
 
 out_journal:
 	jbd2_journal_destroy(journal);
 out_bdev:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 	return ERR_PTR(errno);
 }
 
@@ -7314,12 +7315,12 @@ static inline int ext3_feature_set_ok(struct super_block *sb)
 static void ext4_kill_sb(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct bdev_handle *handle = sbi ? sbi->s_journal_bdev_handle : NULL;
+	struct file *bdev_file = sbi ? sbi->s_journal_bdev_file : NULL;
 
 	kill_block_super(sb);
 
-	if (handle)
-		bdev_release(handle);
+	if (bdev_file)
+		fput(bdev_file);
 }
 
 static struct file_system_type ext4_fs_type = {
diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c
index 75bf1f88843c..645240cc0229 100644
--- a/fs/ext4/symlink.c
+++ b/fs/ext4/symlink.c
@@ -92,10 +92,12 @@ static const char *ext4_get_link(struct dentry *dentry, struct inode *inode,
 
 	if (!dentry) {
 		bh = ext4_getblk(NULL, inode, 0, EXT4_GET_BLOCKS_CACHED_NOWAIT);
-		if (IS_ERR(bh))
-			return ERR_CAST(bh);
-		if (!bh || !ext4_buffer_uptodate(bh))
+		if (IS_ERR(bh) || !bh)
 			return ERR_PTR(-ECHILD);
+		if (!ext4_buffer_uptodate(bh)) {
+			brelse(bh);
+			return ERR_PTR(-ECHILD);
+		}
 	} else {
 		bh = ext4_bread(NULL, inode, 0, 0);
 		if (IS_ERR(bh))
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 65294e3b0bef..4c77e8ce5c75 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -24,6 +24,7 @@
 #include <linux/blkdev.h>
 #include <linux/quotaops.h>
 #include <linux/part_stat.h>
+#include <linux/rw_hint.h>
 #include <crypto/hash.h>
 
 #include <linux/fscrypt.h>
@@ -1239,7 +1240,7 @@ struct f2fs_bio_info {
 #define FDEV(i)				(sbi->devs[i])
 #define RDEV(i)				(raw_super->devs[i])
 struct f2fs_dev_info {
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct block_device *bdev;
 	char path[MAX_PATH_LEN];
 	unsigned int total_segments;
@@ -3364,17 +3365,6 @@ static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi)
 	return is_set_ckpt_flags(sbi, CP_ERROR_FLAG);
 }
 
-static inline bool is_dot_dotdot(const u8 *name, size_t len)
-{
-	if (len == 1 && name[0] == '.')
-		return true;
-
-	if (len == 2 && name[0] == '.' && name[1] == '.')
-		return true;
-
-	return false;
-}
-
 static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
 					size_t size, gfp_t flags)
 {
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index b3bb815fc6aa..f7f63a567d86 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -531,7 +531,6 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 	}
 
 	err = f2fs_prepare_lookup(dir, dentry, &fname);
-	generic_set_encrypted_ci_d_ops(dentry);
 	if (err == -ENOENT)
 		goto out_splice;
 	if (err)
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 4c8836ded90f..e1065ba70207 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -1971,9 +1971,15 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi,
 		}
 
 		if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) {
+			unsigned int nofs_flags;
+			int ret;
+
 			trace_f2fs_issue_reset_zone(bdev, blkstart);
-			return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
-						sector, nr_sects, GFP_NOFS);
+			nofs_flags = memalloc_nofs_save();
+			ret = blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
+						sector, nr_sects);
+			memalloc_nofs_restore(nofs_flags);
+			return ret;
 		}
 
 		__queue_zone_reset_cmd(sbi, bdev, blkstart, lblkstart, blklen);
@@ -4865,6 +4871,7 @@ static int check_zone_write_pointer(struct f2fs_sb_info *sbi,
 	block_t zone_block, valid_block_cnt;
 	unsigned int log_sectors_per_block = sbi->log_blocksize - SECTOR_SHIFT;
 	int ret;
+	unsigned int nofs_flags;
 
 	if (zone->type != BLK_ZONE_TYPE_SEQWRITE_REQ)
 		return 0;
@@ -4912,8 +4919,10 @@ static int check_zone_write_pointer(struct f2fs_sb_info *sbi,
 		    "pointer: valid block[0x%x,0x%x] cond[0x%x]",
 		    zone_segno, valid_block_cnt, zone->cond);
 
+	nofs_flags = memalloc_nofs_save();
 	ret = blkdev_zone_mgmt(fdev->bdev, REQ_OP_ZONE_FINISH,
-				zone->start, zone->len, GFP_NOFS);
+				zone->start, zone->len);
+	memalloc_nofs_restore(nofs_flags);
 	if (ret == -EOPNOTSUPP) {
 		ret = blkdev_issue_zeroout(fdev->bdev, zone->wp,
 					zone->len - (zone->wp - zone->start),
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index d00d21a8b53a..b880b746f226 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1605,7 +1605,7 @@ static void destroy_device_list(struct f2fs_sb_info *sbi)
 
 	for (i = 0; i < sbi->s_ndevs; i++) {
 		if (i > 0)
-			bdev_release(FDEV(i).bdev_handle);
+			fput(FDEV(i).bdev_file);
 #ifdef CONFIG_BLK_DEV_ZONED
 		kvfree(FDEV(i).blkz_seq);
 #endif
@@ -4247,7 +4247,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 
 	for (i = 0; i < max_devices; i++) {
 		if (i == 0)
-			FDEV(0).bdev_handle = sbi->sb->s_bdev_handle;
+			FDEV(0).bdev_file = sbi->sb->s_bdev_file;
 		else if (!RDEV(i).path[0])
 			break;
 
@@ -4267,14 +4267,14 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 				FDEV(i).end_blk = FDEV(i).start_blk +
 					(FDEV(i).total_segments <<
 					sbi->log_blocks_per_seg) - 1;
-				FDEV(i).bdev_handle = bdev_open_by_path(
+				FDEV(i).bdev_file = bdev_file_open_by_path(
 					FDEV(i).path, mode, sbi->sb, NULL);
 			}
 		}
-		if (IS_ERR(FDEV(i).bdev_handle))
-			return PTR_ERR(FDEV(i).bdev_handle);
+		if (IS_ERR(FDEV(i).bdev_file))
+			return PTR_ERR(FDEV(i).bdev_file);
 
-		FDEV(i).bdev = FDEV(i).bdev_handle->bdev;
+		FDEV(i).bdev = file_bdev(FDEV(i).bdev_file);
 		/* to release errored devices */
 		sbi->s_ndevs = i + 1;
 
@@ -4496,7 +4496,7 @@ try_onemore:
 	sb->s_time_gran = 1;
 	sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
 		(test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0);
-	memcpy(&sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
+	super_set_uuid(sb, (void *) raw_super->uuid, sizeof(raw_super->uuid));
 	sb->s_iflags |= SB_I_CGROUPWB;
 
 	/* init f2fs-specific super block info */
@@ -4660,6 +4660,7 @@ try_onemore:
 		goto free_node_inode;
 	}
 
+	generic_set_sb_d_ops(sb);
 	sb->s_root = d_make_root(root); /* allocate root dentry */
 	if (!sb->s_root) {
 		err = -ENOMEM;
@@ -4880,6 +4881,7 @@ free_sbi:
 	if (sbi->s_chksum_driver)
 		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi);
+	sb->s_fs_info = NULL;
 
 	/* give only one another chance */
 	if (retry_cnt > 0 && skip_recovery) {
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 1fac3dabf130..5c813696d1ff 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -1762,6 +1762,9 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
 	else /* fat 16 or 12 */
 		sbi->vol_id = bpb.fat16_vol_id;
 
+	__le32 vol_id_le = cpu_to_le32(sbi->vol_id);
+	super_set_uuid(sb, (void *) &vol_id_le, sizeof(vol_id_le));
+
 	sbi->dir_per_block = sb->s_blocksize / sizeof(struct msdos_dir_entry);
 	sbi->dir_per_block_bits = ffs(sbi->dir_per_block) - 1;
 
diff --git a/fs/fcntl.c b/fs/fcntl.c
index c80a6acad742..54cc85d3338e 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -27,6 +27,7 @@
 #include <linux/memfd.h>
 #include <linux/compat.h>
 #include <linux/mount.h>
+#include <linux/rw_hint.h>
 
 #include <linux/poll.h>
 #include <asm/siginfo.h>
@@ -268,8 +269,15 @@ static int f_getowner_uids(struct file *filp, unsigned long arg)
 }
 #endif
 
-static bool rw_hint_valid(enum rw_hint hint)
+static bool rw_hint_valid(u64 hint)
 {
+	BUILD_BUG_ON(WRITE_LIFE_NOT_SET != RWH_WRITE_LIFE_NOT_SET);
+	BUILD_BUG_ON(WRITE_LIFE_NONE != RWH_WRITE_LIFE_NONE);
+	BUILD_BUG_ON(WRITE_LIFE_SHORT != RWH_WRITE_LIFE_SHORT);
+	BUILD_BUG_ON(WRITE_LIFE_MEDIUM != RWH_WRITE_LIFE_MEDIUM);
+	BUILD_BUG_ON(WRITE_LIFE_LONG != RWH_WRITE_LIFE_LONG);
+	BUILD_BUG_ON(WRITE_LIFE_EXTREME != RWH_WRITE_LIFE_EXTREME);
+
 	switch (hint) {
 	case RWH_WRITE_LIFE_NOT_SET:
 	case RWH_WRITE_LIFE_NONE:
@@ -283,34 +291,40 @@ static bool rw_hint_valid(enum rw_hint hint)
 	}
 }
 
-static long fcntl_rw_hint(struct file *file, unsigned int cmd,
-			  unsigned long arg)
+static long fcntl_get_rw_hint(struct file *file, unsigned int cmd,
+			      unsigned long arg)
 {
 	struct inode *inode = file_inode(file);
 	u64 __user *argp = (u64 __user *)arg;
-	enum rw_hint hint;
-	u64 h;
+	u64 hint = READ_ONCE(inode->i_write_hint);
 
-	switch (cmd) {
-	case F_GET_RW_HINT:
-		h = inode->i_write_hint;
-		if (copy_to_user(argp, &h, sizeof(*argp)))
-			return -EFAULT;
-		return 0;
-	case F_SET_RW_HINT:
-		if (copy_from_user(&h, argp, sizeof(h)))
-			return -EFAULT;
-		hint = (enum rw_hint) h;
-		if (!rw_hint_valid(hint))
-			return -EINVAL;
+	if (copy_to_user(argp, &hint, sizeof(*argp)))
+		return -EFAULT;
+	return 0;
+}
 
-		inode_lock(inode);
-		inode->i_write_hint = hint;
-		inode_unlock(inode);
-		return 0;
-	default:
+static long fcntl_set_rw_hint(struct file *file, unsigned int cmd,
+			      unsigned long arg)
+{
+	struct inode *inode = file_inode(file);
+	u64 __user *argp = (u64 __user *)arg;
+	u64 hint;
+
+	if (copy_from_user(&hint, argp, sizeof(hint)))
+		return -EFAULT;
+	if (!rw_hint_valid(hint))
 		return -EINVAL;
-	}
+
+	WRITE_ONCE(inode->i_write_hint, hint);
+
+	/*
+	 * file->f_mapping->host may differ from inode. As an example,
+	 * blkdev_open() modifies file->f_mapping.
+	 */
+	if (file->f_mapping->host != inode)
+		WRITE_ONCE(file->f_mapping->host->i_write_hint, hint);
+
+	return 0;
 }
 
 static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
@@ -416,8 +430,10 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 		err = memfd_fcntl(filp, cmd, argi);
 		break;
 	case F_GET_RW_HINT:
+		err = fcntl_get_rw_hint(filp, cmd, arg);
+		break;
 	case F_SET_RW_HINT:
-		err = fcntl_rw_hint(filp, cmd, arg);
+		err = fcntl_set_rw_hint(filp, cmd, arg);
 		break;
 	default:
 		break;
@@ -846,12 +862,6 @@ int send_sigurg(struct fown_struct *fown)
 static DEFINE_SPINLOCK(fasync_lock);
 static struct kmem_cache *fasync_cache __ro_after_init;
 
-static void fasync_free_rcu(struct rcu_head *head)
-{
-	kmem_cache_free(fasync_cache,
-			container_of(head, struct fasync_struct, fa_rcu));
-}
-
 /*
  * Remove a fasync entry. If successfully removed, return
  * positive and clear the FASYNC flag. If no entry exists,
@@ -877,7 +887,7 @@ int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp)
 		write_unlock_irq(&fa->fa_lock);
 
 		*fp = fa->fa_next;
-		call_rcu(&fa->fa_rcu, fasync_free_rcu);
+		kfree_rcu(fa, fa_rcu);
 		filp->f_flags &= ~FASYNC;
 		result = 1;
 		break;
diff --git a/fs/fhandle.c b/fs/fhandle.c
index 18b3ba8dc8ea..57a12614addf 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -36,7 +36,7 @@ static long do_sys_name_to_handle(const struct path *path,
 	if (f_handle.handle_bytes > MAX_HANDLE_SZ)
 		return -EINVAL;
 
-	handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
+	handle = kzalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
 			 GFP_KERNEL);
 	if (!handle)
 		return -ENOMEM;
diff --git a/fs/file_table.c b/fs/file_table.c
index b991f90571b4..6925522faa0a 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -276,21 +276,15 @@ struct file *alloc_empty_backing_file(int flags, const struct cred *cred)
 }
 
 /**
- * alloc_file - allocate and initialize a 'struct file'
+ * file_init_path - initialize a 'struct file' based on path
  *
+ * @file: the file to set up
  * @path: the (dentry, vfsmount) pair for the new file
- * @flags: O_... flags with which the new file will be opened
  * @fop: the 'struct file_operations' for the new file
  */
-static struct file *alloc_file(const struct path *path, int flags,
-		const struct file_operations *fop)
+static void file_init_path(struct file *file, const struct path *path,
+			   const struct file_operations *fop)
 {
-	struct file *file;
-
-	file = alloc_empty_file(flags, current_cred());
-	if (IS_ERR(file))
-		return file;
-
 	file->f_path = *path;
 	file->f_inode = path->dentry->d_inode;
 	file->f_mapping = path->dentry->d_inode->i_mapping;
@@ -309,22 +303,51 @@ static struct file *alloc_file(const struct path *path, int flags,
 	file->f_op = fop;
 	if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_inc(path->dentry->d_inode);
+}
+
+/**
+ * alloc_file - allocate and initialize a 'struct file'
+ *
+ * @path: the (dentry, vfsmount) pair for the new file
+ * @flags: O_... flags with which the new file will be opened
+ * @fop: the 'struct file_operations' for the new file
+ */
+static struct file *alloc_file(const struct path *path, int flags,
+		const struct file_operations *fop)
+{
+	struct file *file;
+
+	file = alloc_empty_file(flags, current_cred());
+	if (!IS_ERR(file))
+		file_init_path(file, path, fop);
 	return file;
 }
 
-struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt,
-				const char *name, int flags,
-				const struct file_operations *fops)
+static inline int alloc_path_pseudo(const char *name, struct inode *inode,
+				    struct vfsmount *mnt, struct path *path)
 {
 	struct qstr this = QSTR_INIT(name, strlen(name));
+
+	path->dentry = d_alloc_pseudo(mnt->mnt_sb, &this);
+	if (!path->dentry)
+		return -ENOMEM;
+	path->mnt = mntget(mnt);
+	d_instantiate(path->dentry, inode);
+	return 0;
+}
+
+struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt,
+			       const char *name, int flags,
+			       const struct file_operations *fops)
+{
+	int ret;
 	struct path path;
 	struct file *file;
 
-	path.dentry = d_alloc_pseudo(mnt->mnt_sb, &this);
-	if (!path.dentry)
-		return ERR_PTR(-ENOMEM);
-	path.mnt = mntget(mnt);
-	d_instantiate(path.dentry, inode);
+	ret = alloc_path_pseudo(name, inode, mnt, &path);
+	if (ret)
+		return ERR_PTR(ret);
+
 	file = alloc_file(&path, flags, fops);
 	if (IS_ERR(file)) {
 		ihold(inode);
@@ -334,6 +357,30 @@ struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt,
 }
 EXPORT_SYMBOL(alloc_file_pseudo);
 
+struct file *alloc_file_pseudo_noaccount(struct inode *inode,
+					 struct vfsmount *mnt, const char *name,
+					 int flags,
+					 const struct file_operations *fops)
+{
+	int ret;
+	struct path path;
+	struct file *file;
+
+	ret = alloc_path_pseudo(name, inode, mnt, &path);
+	if (ret)
+		return ERR_PTR(ret);
+
+	file = alloc_empty_file_noaccount(flags, current_cred());
+	if (IS_ERR(file)) {
+		ihold(inode);
+		path_put(&path);
+		return file;
+	}
+	file_init_path(file, &path, fops);
+	return file;
+}
+EXPORT_SYMBOL_GPL(alloc_file_pseudo_noaccount);
+
 struct file *alloc_file_clone(struct file *base, int flags,
 				const struct file_operations *fops)
 {
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 1767493dffda..e4f17c53ddfc 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -141,6 +141,31 @@ static void wb_wakeup(struct bdi_writeback *wb)
 	spin_unlock_irq(&wb->work_lock);
 }
 
+/*
+ * This function is used when the first inode for this wb is marked dirty. It
+ * wakes-up the corresponding bdi thread which should then take care of the
+ * periodic background write-out of dirty inodes. Since the write-out would
+ * starts only 'dirty_writeback_interval' centisecs from now anyway, we just
+ * set up a timer which wakes the bdi thread up later.
+ *
+ * Note, we wouldn't bother setting up the timer, but this function is on the
+ * fast-path (used by '__mark_inode_dirty()'), so we save few context switches
+ * by delaying the wake-up.
+ *
+ * We have to be careful not to postpone flush work if it is scheduled for
+ * earlier. Thus we use queue_delayed_work().
+ */
+static void wb_wakeup_delayed(struct bdi_writeback *wb)
+{
+	unsigned long timeout;
+
+	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
+	spin_lock_irq(&wb->work_lock);
+	if (test_bit(WB_registered, &wb->state))
+		queue_delayed_work(bdi_wq, &wb->dwork, timeout);
+	spin_unlock_irq(&wb->work_lock);
+}
+
 static void finish_writeback_work(struct bdi_writeback *wb,
 				  struct wb_writeback_work *work)
 {
@@ -1675,11 +1700,11 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 
 	if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
 		inode->i_state |= I_DIRTY_PAGES;
-	else if (unlikely(inode->i_state & I_PINNING_FSCACHE_WB)) {
+	else if (unlikely(inode->i_state & I_PINNING_NETFS_WB)) {
 		if (!(inode->i_state & I_DIRTY_PAGES)) {
-			inode->i_state &= ~I_PINNING_FSCACHE_WB;
-			wbc->unpinned_fscache_wb = true;
-			dirty |= I_PINNING_FSCACHE_WB; /* Cause write_inode */
+			inode->i_state &= ~I_PINNING_NETFS_WB;
+			wbc->unpinned_netfs_wb = true;
+			dirty |= I_PINNING_NETFS_WB; /* Cause write_inode */
 		}
 	}
 
@@ -1691,7 +1716,7 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 		if (ret == 0)
 			ret = err;
 	}
-	wbc->unpinned_fscache_wb = false;
+	wbc->unpinned_netfs_wb = false;
 	trace_writeback_single_inode(inode, wbc, nr_to_write);
 	return ret;
 }
diff --git a/fs/fs_parser.c b/fs/fs_parser.c
index edb3712dcfa5..a4d6ca0b8971 100644
--- a/fs/fs_parser.c
+++ b/fs/fs_parser.c
@@ -83,8 +83,8 @@ static const struct fs_parameter_spec *fs_lookup_key(
 }
 
 /*
- * fs_parse - Parse a filesystem configuration parameter
- * @fc: The filesystem context to log errors through.
+ * __fs_parse - Parse a filesystem configuration parameter
+ * @log: The filesystem context to log errors through.
  * @desc: The parameter description to use.
  * @param: The parameter.
  * @result: Where to place the result of the parse
diff --git a/fs/fscache/Kconfig b/fs/fscache/Kconfig
deleted file mode 100644
index b313a978ae0a..000000000000
--- a/fs/fscache/Kconfig
+++ /dev/null
@@ -1,40 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-
-config FSCACHE
-	tristate "General filesystem local caching manager"
-	select NETFS_SUPPORT
-	help
-	  This option enables a generic filesystem caching manager that can be
-	  used by various network and other filesystems to cache data locally.
-	  Different sorts of caches can be plugged in, depending on the
-	  resources available.
-
-	  See Documentation/filesystems/caching/fscache.rst for more information.
-
-config FSCACHE_STATS
-	bool "Gather statistical information on local caching"
-	depends on FSCACHE && PROC_FS
-	select NETFS_STATS
-	help
-	  This option causes statistical information to be gathered on local
-	  caching and exported through file:
-
-		/proc/fs/fscache/stats
-
-	  The gathering of statistics adds a certain amount of overhead to
-	  execution as there are a quite a few stats gathered, and on a
-	  multi-CPU system these may be on cachelines that keep bouncing
-	  between CPUs.  On the other hand, the stats are very useful for
-	  debugging purposes.  Saying 'Y' here is recommended.
-
-	  See Documentation/filesystems/caching/fscache.rst for more information.
-
-config FSCACHE_DEBUG
-	bool "Debug FS-Cache"
-	depends on FSCACHE
-	help
-	  This permits debugging to be dynamically enabled in the local caching
-	  management module.  If this is set, the debugging output may be
-	  enabled by setting bits in /sys/modules/fscache/parameter/debug.
-
-	  See Documentation/filesystems/caching/fscache.rst for more information.
diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile
deleted file mode 100644
index afb090ea16c4..000000000000
--- a/fs/fscache/Makefile
+++ /dev/null
@@ -1,16 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile for general filesystem caching code
-#
-
-fscache-y := \
-	cache.o \
-	cookie.o \
-	io.o \
-	main.o \
-	volume.o
-
-fscache-$(CONFIG_PROC_FS) += proc.o
-fscache-$(CONFIG_FSCACHE_STATS) += stats.o
-
-obj-$(CONFIG_FSCACHE) := fscache.o
diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h
deleted file mode 100644
index 1336f517e9b1..000000000000
--- a/fs/fscache/internal.h
+++ /dev/null
@@ -1,277 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* Internal definitions for FS-Cache
- *
- * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- */
-
-#ifdef pr_fmt
-#undef pr_fmt
-#endif
-
-#define pr_fmt(fmt) "FS-Cache: " fmt
-
-#include <linux/slab.h>
-#include <linux/fscache-cache.h>
-#include <trace/events/fscache.h>
-#include <linux/sched.h>
-#include <linux/seq_file.h>
-
-/*
- * cache.c
- */
-#ifdef CONFIG_PROC_FS
-extern const struct seq_operations fscache_caches_seq_ops;
-#endif
-bool fscache_begin_cache_access(struct fscache_cache *cache, enum fscache_access_trace why);
-void fscache_end_cache_access(struct fscache_cache *cache, enum fscache_access_trace why);
-struct fscache_cache *fscache_lookup_cache(const char *name, bool is_cache);
-void fscache_put_cache(struct fscache_cache *cache, enum fscache_cache_trace where);
-
-static inline enum fscache_cache_state fscache_cache_state(const struct fscache_cache *cache)
-{
-	return smp_load_acquire(&cache->state);
-}
-
-static inline bool fscache_cache_is_live(const struct fscache_cache *cache)
-{
-	return fscache_cache_state(cache) == FSCACHE_CACHE_IS_ACTIVE;
-}
-
-static inline void fscache_set_cache_state(struct fscache_cache *cache,
-					   enum fscache_cache_state new_state)
-{
-	smp_store_release(&cache->state, new_state);
-
-}
-
-static inline bool fscache_set_cache_state_maybe(struct fscache_cache *cache,
-						 enum fscache_cache_state old_state,
-						 enum fscache_cache_state new_state)
-{
-	return try_cmpxchg_release(&cache->state, &old_state, new_state);
-}
-
-/*
- * cookie.c
- */
-extern struct kmem_cache *fscache_cookie_jar;
-#ifdef CONFIG_PROC_FS
-extern const struct seq_operations fscache_cookies_seq_ops;
-#endif
-extern struct timer_list fscache_cookie_lru_timer;
-
-extern void fscache_print_cookie(struct fscache_cookie *cookie, char prefix);
-extern bool fscache_begin_cookie_access(struct fscache_cookie *cookie,
-					enum fscache_access_trace why);
-
-static inline void fscache_see_cookie(struct fscache_cookie *cookie,
-				      enum fscache_cookie_trace where)
-{
-	trace_fscache_cookie(cookie->debug_id, refcount_read(&cookie->ref),
-			     where);
-}
-
-/*
- * main.c
- */
-extern unsigned fscache_debug;
-
-extern unsigned int fscache_hash(unsigned int salt, const void *data, size_t len);
-
-/*
- * proc.c
- */
-#ifdef CONFIG_PROC_FS
-extern int __init fscache_proc_init(void);
-extern void fscache_proc_cleanup(void);
-#else
-#define fscache_proc_init()	(0)
-#define fscache_proc_cleanup()	do {} while (0)
-#endif
-
-/*
- * stats.c
- */
-#ifdef CONFIG_FSCACHE_STATS
-extern atomic_t fscache_n_volumes;
-extern atomic_t fscache_n_volumes_collision;
-extern atomic_t fscache_n_volumes_nomem;
-extern atomic_t fscache_n_cookies;
-extern atomic_t fscache_n_cookies_lru;
-extern atomic_t fscache_n_cookies_lru_expired;
-extern atomic_t fscache_n_cookies_lru_removed;
-extern atomic_t fscache_n_cookies_lru_dropped;
-
-extern atomic_t fscache_n_acquires;
-extern atomic_t fscache_n_acquires_ok;
-extern atomic_t fscache_n_acquires_oom;
-
-extern atomic_t fscache_n_invalidates;
-
-extern atomic_t fscache_n_relinquishes;
-extern atomic_t fscache_n_relinquishes_retire;
-extern atomic_t fscache_n_relinquishes_dropped;
-
-extern atomic_t fscache_n_resizes;
-extern atomic_t fscache_n_resizes_null;
-
-static inline void fscache_stat(atomic_t *stat)
-{
-	atomic_inc(stat);
-}
-
-static inline void fscache_stat_d(atomic_t *stat)
-{
-	atomic_dec(stat);
-}
-
-#define __fscache_stat(stat) (stat)
-
-int fscache_stats_show(struct seq_file *m, void *v);
-#else
-
-#define __fscache_stat(stat) (NULL)
-#define fscache_stat(stat) do {} while (0)
-#define fscache_stat_d(stat) do {} while (0)
-#endif
-
-/*
- * volume.c
- */
-#ifdef CONFIG_PROC_FS
-extern const struct seq_operations fscache_volumes_seq_ops;
-#endif
-
-struct fscache_volume *fscache_get_volume(struct fscache_volume *volume,
-					  enum fscache_volume_trace where);
-void fscache_put_volume(struct fscache_volume *volume,
-			enum fscache_volume_trace where);
-bool fscache_begin_volume_access(struct fscache_volume *volume,
-				 struct fscache_cookie *cookie,
-				 enum fscache_access_trace why);
-void fscache_create_volume(struct fscache_volume *volume, bool wait);
-
-
-/*****************************************************************************/
-/*
- * debug tracing
- */
-#define dbgprintk(FMT, ...) \
-	printk("[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__)
-
-#define kenter(FMT, ...) dbgprintk("==> %s("FMT")", __func__, ##__VA_ARGS__)
-#define kleave(FMT, ...) dbgprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
-#define kdebug(FMT, ...) dbgprintk(FMT, ##__VA_ARGS__)
-
-#define kjournal(FMT, ...) no_printk(FMT, ##__VA_ARGS__)
-
-#ifdef __KDEBUG
-#define _enter(FMT, ...) kenter(FMT, ##__VA_ARGS__)
-#define _leave(FMT, ...) kleave(FMT, ##__VA_ARGS__)
-#define _debug(FMT, ...) kdebug(FMT, ##__VA_ARGS__)
-
-#elif defined(CONFIG_FSCACHE_DEBUG)
-#define _enter(FMT, ...)			\
-do {						\
-	if (__do_kdebug(ENTER))			\
-		kenter(FMT, ##__VA_ARGS__);	\
-} while (0)
-
-#define _leave(FMT, ...)			\
-do {						\
-	if (__do_kdebug(LEAVE))			\
-		kleave(FMT, ##__VA_ARGS__);	\
-} while (0)
-
-#define _debug(FMT, ...)			\
-do {						\
-	if (__do_kdebug(DEBUG))			\
-		kdebug(FMT, ##__VA_ARGS__);	\
-} while (0)
-
-#else
-#define _enter(FMT, ...) no_printk("==> %s("FMT")", __func__, ##__VA_ARGS__)
-#define _leave(FMT, ...) no_printk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
-#define _debug(FMT, ...) no_printk(FMT, ##__VA_ARGS__)
-#endif
-
-/*
- * determine whether a particular optional debugging point should be logged
- * - we need to go through three steps to persuade cpp to correctly join the
- *   shorthand in FSCACHE_DEBUG_LEVEL with its prefix
- */
-#define ____do_kdebug(LEVEL, POINT) \
-	unlikely((fscache_debug & \
-		  (FSCACHE_POINT_##POINT << (FSCACHE_DEBUG_ ## LEVEL * 3))))
-#define ___do_kdebug(LEVEL, POINT) \
-	____do_kdebug(LEVEL, POINT)
-#define __do_kdebug(POINT) \
-	___do_kdebug(FSCACHE_DEBUG_LEVEL, POINT)
-
-#define FSCACHE_DEBUG_CACHE	0
-#define FSCACHE_DEBUG_COOKIE	1
-#define FSCACHE_DEBUG_OBJECT	2
-#define FSCACHE_DEBUG_OPERATION	3
-
-#define FSCACHE_POINT_ENTER	1
-#define FSCACHE_POINT_LEAVE	2
-#define FSCACHE_POINT_DEBUG	4
-
-#ifndef FSCACHE_DEBUG_LEVEL
-#define FSCACHE_DEBUG_LEVEL CACHE
-#endif
-
-/*
- * assertions
- */
-#if 1 /* defined(__KDEBUGALL) */
-
-#define ASSERT(X)							\
-do {									\
-	if (unlikely(!(X))) {						\
-		pr_err("\n");					\
-		pr_err("Assertion failed\n");	\
-		BUG();							\
-	}								\
-} while (0)
-
-#define ASSERTCMP(X, OP, Y)						\
-do {									\
-	if (unlikely(!((X) OP (Y)))) {					\
-		pr_err("\n");					\
-		pr_err("Assertion failed\n");	\
-		pr_err("%lx " #OP " %lx is false\n",		\
-		       (unsigned long)(X), (unsigned long)(Y));		\
-		BUG();							\
-	}								\
-} while (0)
-
-#define ASSERTIF(C, X)							\
-do {									\
-	if (unlikely((C) && !(X))) {					\
-		pr_err("\n");					\
-		pr_err("Assertion failed\n");	\
-		BUG();							\
-	}								\
-} while (0)
-
-#define ASSERTIFCMP(C, X, OP, Y)					\
-do {									\
-	if (unlikely((C) && !((X) OP (Y)))) {				\
-		pr_err("\n");					\
-		pr_err("Assertion failed\n");	\
-		pr_err("%lx " #OP " %lx is false\n",		\
-		       (unsigned long)(X), (unsigned long)(Y));		\
-		BUG();							\
-	}								\
-} while (0)
-
-#else
-
-#define ASSERT(X)			do {} while (0)
-#define ASSERTCMP(X, OP, Y)		do {} while (0)
-#define ASSERTIF(C, X)			do {} while (0)
-#define ASSERTIFCMP(C, X, OP, Y)	do {} while (0)
-
-#endif /* assert or not */
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index 91e89e68177e..b6cad106c37e 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -474,8 +474,7 @@ err:
 
 static void cuse_fc_release(struct fuse_conn *fc)
 {
-	struct cuse_conn *cc = fc_to_cc(fc);
-	kfree_rcu(cc, fc.rcu);
+	kfree(fc_to_cc(fc));
 }
 
 /**
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 148a71b8b4d0..c007b0f0c3a7 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2509,14 +2509,14 @@ static int convert_fuse_file_lock(struct fuse_conn *fc,
 		 * translate it into the caller's pid namespace.
 		 */
 		rcu_read_lock();
-		fl->fl_pid = pid_nr_ns(find_pid_ns(ffl->pid, fc->pid_ns), &init_pid_ns);
+		fl->c.flc_pid = pid_nr_ns(find_pid_ns(ffl->pid, fc->pid_ns), &init_pid_ns);
 		rcu_read_unlock();
 		break;
 
 	default:
 		return -EIO;
 	}
-	fl->fl_type = ffl->type;
+	fl->c.flc_type = ffl->type;
 	return 0;
 }
 
@@ -2530,10 +2530,10 @@ static void fuse_lk_fill(struct fuse_args *args, struct file *file,
 
 	memset(inarg, 0, sizeof(*inarg));
 	inarg->fh = ff->fh;
-	inarg->owner = fuse_lock_owner_id(fc, fl->fl_owner);
+	inarg->owner = fuse_lock_owner_id(fc, fl->c.flc_owner);
 	inarg->lk.start = fl->fl_start;
 	inarg->lk.end = fl->fl_end;
-	inarg->lk.type = fl->fl_type;
+	inarg->lk.type = fl->c.flc_type;
 	inarg->lk.pid = pid;
 	if (flock)
 		inarg->lk_flags |= FUSE_LK_FLOCK;
@@ -2570,8 +2570,8 @@ static int fuse_setlk(struct file *file, struct file_lock *fl, int flock)
 	struct fuse_mount *fm = get_fuse_mount(inode);
 	FUSE_ARGS(args);
 	struct fuse_lk_in inarg;
-	int opcode = (fl->fl_flags & FL_SLEEP) ? FUSE_SETLKW : FUSE_SETLK;
-	struct pid *pid = fl->fl_type != F_UNLCK ? task_tgid(current) : NULL;
+	int opcode = (fl->c.flc_flags & FL_SLEEP) ? FUSE_SETLKW : FUSE_SETLK;
+	struct pid *pid = fl->c.flc_type != F_UNLCK ? task_tgid(current) : NULL;
 	pid_t pid_nr = pid_nr_ns(pid, fm->fc->pid_ns);
 	int err;
 
@@ -2581,7 +2581,7 @@ static int fuse_setlk(struct file *file, struct file_lock *fl, int flock)
 	}
 
 	/* Unlock on close is handled by the flush method */
-	if ((fl->fl_flags & FL_CLOSE_POSIX) == FL_CLOSE_POSIX)
+	if ((fl->c.flc_flags & FL_CLOSE_POSIX) == FL_CLOSE_POSIX)
 		return 0;
 
 	fuse_lk_fill(&args, file, fl, opcode, pid_nr, flock, &inarg);
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 1df83eebda92..bcbe34488862 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -888,6 +888,7 @@ struct fuse_mount {
 
 	/* Entry on fc->mounts */
 	struct list_head fc_entry;
+	struct rcu_head rcu;
 };
 
 static inline struct fuse_mount *get_fuse_mount_super(struct super_block *sb)
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 2a6d44f91729..516ea2979a90 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -930,6 +930,14 @@ void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm,
 }
 EXPORT_SYMBOL_GPL(fuse_conn_init);
 
+static void delayed_release(struct rcu_head *p)
+{
+	struct fuse_conn *fc = container_of(p, struct fuse_conn, rcu);
+
+	put_user_ns(fc->user_ns);
+	fc->release(fc);
+}
+
 void fuse_conn_put(struct fuse_conn *fc)
 {
 	if (refcount_dec_and_test(&fc->count)) {
@@ -941,13 +949,12 @@ void fuse_conn_put(struct fuse_conn *fc)
 		if (fiq->ops->release)
 			fiq->ops->release(fiq);
 		put_pid_ns(fc->pid_ns);
-		put_user_ns(fc->user_ns);
 		bucket = rcu_dereference_protected(fc->curr_bucket, 1);
 		if (bucket) {
 			WARN_ON(atomic_read(&bucket->count) != 1);
 			kfree(bucket);
 		}
-		fc->release(fc);
+		call_rcu(&fc->rcu, delayed_release);
 	}
 }
 EXPORT_SYMBOL_GPL(fuse_conn_put);
@@ -1366,7 +1373,7 @@ EXPORT_SYMBOL_GPL(fuse_send_init);
 void fuse_free_conn(struct fuse_conn *fc)
 {
 	WARN_ON(!list_empty(&fc->devices));
-	kfree_rcu(fc, rcu);
+	kfree(fc);
 }
 EXPORT_SYMBOL_GPL(fuse_free_conn);
 
@@ -1902,7 +1909,7 @@ static void fuse_sb_destroy(struct super_block *sb)
 void fuse_mount_destroy(struct fuse_mount *fm)
 {
 	fuse_conn_put(fm->fc);
-	kfree(fm);
+	kfree_rcu(fm, rcu);
 }
 EXPORT_SYMBOL(fuse_mount_destroy);
 
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index d9ccfd27e4f1..789af5c8fade 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -2465,7 +2465,7 @@ out:
 }
 
 static int gfs2_map_blocks(struct iomap_writepage_ctx *wpc, struct inode *inode,
-		loff_t offset)
+		loff_t offset, unsigned int len)
 {
 	int ret;
 
diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c
index 177f1f41f225..2e215e8c3c88 100644
--- a/fs/gfs2/dentry.c
+++ b/fs/gfs2/dentry.c
@@ -32,25 +32,21 @@
 
 static int gfs2_drevalidate(struct dentry *dentry, unsigned int flags)
 {
-	struct dentry *parent = NULL;
+	struct dentry *parent;
 	struct gfs2_sbd *sdp;
 	struct gfs2_inode *dip;
-	struct inode *dinode, *inode;
+	struct inode *inode;
 	struct gfs2_holder d_gh;
 	struct gfs2_inode *ip = NULL;
 	int error, valid = 0;
 	int had_lock = 0;
 
-	if (flags & LOOKUP_RCU) {
-		dinode = d_inode_rcu(READ_ONCE(dentry->d_parent));
-		if (!dinode)
-			return -ECHILD;
-	} else {
-		parent = dget_parent(dentry);
-		dinode = d_inode(parent);
-	}
-	sdp = GFS2_SB(dinode);
-	dip = GFS2_I(dinode);
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	parent = dget_parent(dentry);
+	sdp = GFS2_SB(d_inode(parent));
+	dip = GFS2_I(d_inode(parent));
 	inode = d_inode(dentry);
 
 	if (inode) {
@@ -66,8 +62,7 @@ static int gfs2_drevalidate(struct dentry *dentry, unsigned int flags)
 
 	had_lock = (gfs2_glock_is_locked_by_me(dip->i_gl) != NULL);
 	if (!had_lock) {
-		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED,
-					   flags & LOOKUP_RCU ? GL_NOBLOCK : 0, &d_gh);
+		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
 		if (error)
 			goto out;
 	}
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 992ca4effb50..4c42ada60ae7 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -1440,10 +1440,10 @@ static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl)
 	struct gfs2_sbd *sdp = GFS2_SB(file->f_mapping->host);
 	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
 
-	if (!(fl->fl_flags & FL_POSIX))
+	if (!(fl->c.flc_flags & FL_POSIX))
 		return -ENOLCK;
 	if (gfs2_withdrawing_or_withdrawn(sdp)) {
-		if (fl->fl_type == F_UNLCK)
+		if (lock_is_unlock(fl))
 			locks_lock_file_wait(file, fl);
 		return -EIO;
 	}
@@ -1451,7 +1451,7 @@ static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl)
 		return dlm_posix_cancel(ls->ls_dlm, ip->i_no_addr, file, fl);
 	else if (IS_GETLK(cmd))
 		return dlm_posix_get(ls->ls_dlm, ip->i_no_addr, file, fl);
-	else if (fl->fl_type == F_UNLCK)
+	else if (lock_is_unlock(fl))
 		return dlm_posix_unlock(ls->ls_dlm, ip->i_no_addr, file, fl);
 	else
 		return dlm_posix_lock(ls->ls_dlm, ip->i_no_addr, file, cmd, fl);
@@ -1483,7 +1483,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
 	int error = 0;
 	int sleeptime;
 
-	state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
+	state = lock_is_write(fl) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
 	flags = GL_EXACT | GL_NOPID;
 	if (!IS_SETLKW(cmd))
 		flags |= LM_FLAG_TRY_1CB;
@@ -1495,8 +1495,8 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
 		if (fl_gh->gh_state == state)
 			goto out;
 		locks_init_lock(&request);
-		request.fl_type = F_UNLCK;
-		request.fl_flags = FL_FLOCK;
+		request.c.flc_type = F_UNLCK;
+		request.c.flc_flags = FL_FLOCK;
 		locks_lock_file_wait(file, &request);
 		gfs2_glock_dq(fl_gh);
 		gfs2_holder_reinit(state, flags, fl_gh);
@@ -1557,10 +1557,10 @@ static void do_unflock(struct file *file, struct file_lock *fl)
 
 static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl)
 {
-	if (!(fl->fl_flags & FL_FLOCK))
+	if (!(fl->c.flc_flags & FL_FLOCK))
 		return -ENOLCK;
 
-	if (fl->fl_type == F_UNLCK) {
+	if (lock_is_unlock(fl)) {
 		do_unflock(file, fl);
 		return 0;
 	} else {
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 6bfc9383b7b8..1b95db2c3aac 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1882,10 +1882,10 @@ int gfs2_permission(struct mnt_idmap *idmap, struct inode *inode,
 		WARN_ON_ONCE(!may_not_block);
 		return -ECHILD;
         }
-	if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) {
-		int noblock = may_not_block ? GL_NOBLOCK : 0;
-		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
-					   LM_FLAG_ANY | noblock, &i_gh);
+	if (gfs2_glock_is_locked_by_me(gl) == NULL) {
+		if (may_not_block)
+			return -ECHILD;
+		error = gfs2_glock_nq_init(gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
 		if (error)
 			return error;
 	}
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 1281e60be639..572d58e86296 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -214,7 +214,7 @@ static void gfs2_sb_in(struct gfs2_sbd *sdp, const void *buf)
 
 	memcpy(sb->sb_lockproto, str->sb_lockproto, GFS2_LOCKNAME_LEN);
 	memcpy(sb->sb_locktable, str->sb_locktable, GFS2_LOCKNAME_LEN);
-	memcpy(&s->s_uuid, str->sb_uuid, 16);
+	super_set_uuid(s, str->sb_uuid, 16);
 }
 
 /**
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 7ededcb720c1..012a3d003fbe 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -190,6 +190,7 @@ struct hfsplus_sb_info {
 	int work_queued;               /* non-zero delayed work is queued */
 	struct delayed_work sync_work; /* FS sync delayed work */
 	spinlock_t work_lock;          /* protects sync_work and work_queued */
+	struct rcu_head rcu;
 };
 
 #define HFSPLUS_SB_WRITEBACKUP	0
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 1986b4f18a90..97920202790f 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -277,6 +277,14 @@ void hfsplus_mark_mdb_dirty(struct super_block *sb)
 	spin_unlock(&sbi->work_lock);
 }
 
+static void delayed_free(struct rcu_head *p)
+{
+	struct hfsplus_sb_info *sbi = container_of(p, struct hfsplus_sb_info, rcu);
+
+	unload_nls(sbi->nls);
+	kfree(sbi);
+}
+
 static void hfsplus_put_super(struct super_block *sb)
 {
 	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
@@ -302,9 +310,7 @@ static void hfsplus_put_super(struct super_block *sb)
 	hfs_btree_close(sbi->ext_tree);
 	kfree(sbi->s_vhdr_buf);
 	kfree(sbi->s_backup_vhdr_buf);
-	unload_nls(sbi->nls);
-	kfree(sb->s_fs_info);
-	sb->s_fs_info = NULL;
+	call_rcu(&sbi->rcu, delayed_free);
 }
 
 static int hfsplus_statfs(struct dentry *dentry, struct kstatfs *buf)
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index b0cb70400996..ce9346099c72 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -30,7 +30,7 @@ struct hfsplus_wd {
  * @sector: block to read or write, for blocks of HFSPLUS_SECTOR_SIZE bytes
  * @buf: buffer for I/O
  * @data: output pointer for location of requested data
- * @opf: request op flags
+ * @opf: I/O operation type and flags
  *
  * The unit of I/O is hfsplus_min_io_size(sb), which may be bigger than
  * HFSPLUS_SECTOR_SIZE, and @buf must be sized accordingly. On reads
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index ea5b8e57d904..6502c7e776d1 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -100,6 +100,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	loff_t len, vma_len;
 	int ret;
 	struct hstate *h = hstate_file(file);
+	vm_flags_t vm_flags;
 
 	/*
 	 * vma address alignment (but not the pgoff alignment) has
@@ -141,10 +142,20 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	file_accessed(file);
 
 	ret = -ENOMEM;
+
+	vm_flags = vma->vm_flags;
+	/*
+	 * for SHM_HUGETLB, the pages are reserved in the shmget() call so skip
+	 * reserving here. Note: only for SHM hugetlbfs file, the inode
+	 * flag S_PRIVATE is set.
+	 */
+	if (inode->i_flags & S_PRIVATE)
+		vm_flags |= VM_NORESERVE;
+
 	if (!hugetlb_reserve_pages(inode,
 				vma->vm_pgoff >> huge_page_order(h),
 				len >> huge_page_shift(h), vma,
-				vma->vm_flags))
+				vm_flags))
 		goto out;
 
 	ret = 0;
@@ -340,7 +351,7 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		} else {
 			folio_unlock(folio);
 
-			if (!folio_test_has_hwpoisoned(folio))
+			if (!folio_test_hwpoison(folio))
 				want = nr;
 			else {
 				/*
@@ -922,7 +933,7 @@ static int hugetlbfs_setattr(struct mnt_idmap *idmap,
 	unsigned int ia_valid = attr->ia_valid;
 	struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
 
-	error = setattr_prepare(&nop_mnt_idmap, dentry, attr);
+	error = setattr_prepare(idmap, dentry, attr);
 	if (error)
 		return error;
 
@@ -939,7 +950,7 @@ static int hugetlbfs_setattr(struct mnt_idmap *idmap,
 		hugetlb_vmtruncate(inode, newsize);
 	}
 
-	setattr_copy(&nop_mnt_idmap, inode, attr);
+	setattr_copy(idmap, inode, attr);
 	mark_inode_dirty(inode);
 	return 0;
 }
@@ -974,6 +985,7 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
 static struct lock_class_key hugetlbfs_i_mmap_rwsem_key;
 
 static struct inode *hugetlbfs_get_inode(struct super_block *sb,
+					struct mnt_idmap *idmap,
 					struct inode *dir,
 					umode_t mode, dev_t dev)
 {
@@ -995,7 +1007,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 		struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
 
 		inode->i_ino = get_next_ino();
-		inode_init_owner(&nop_mnt_idmap, inode, dir, mode);
+		inode_init_owner(idmap, inode, dir, mode);
 		lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
 				&hugetlbfs_i_mmap_rwsem_key);
 		inode->i_mapping->a_ops = &hugetlbfs_aops;
@@ -1039,7 +1051,7 @@ static int hugetlbfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 {
 	struct inode *inode;
 
-	inode = hugetlbfs_get_inode(dir->i_sb, dir, mode, dev);
+	inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode, dev);
 	if (!inode)
 		return -ENOSPC;
 	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
@@ -1051,7 +1063,7 @@ static int hugetlbfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 static int hugetlbfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 			   struct dentry *dentry, umode_t mode)
 {
-	int retval = hugetlbfs_mknod(&nop_mnt_idmap, dir, dentry,
+	int retval = hugetlbfs_mknod(idmap, dir, dentry,
 				     mode | S_IFDIR, 0);
 	if (!retval)
 		inc_nlink(dir);
@@ -1062,7 +1074,7 @@ static int hugetlbfs_create(struct mnt_idmap *idmap,
 			    struct inode *dir, struct dentry *dentry,
 			    umode_t mode, bool excl)
 {
-	return hugetlbfs_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFREG, 0);
+	return hugetlbfs_mknod(idmap, dir, dentry, mode | S_IFREG, 0);
 }
 
 static int hugetlbfs_tmpfile(struct mnt_idmap *idmap,
@@ -1071,7 +1083,7 @@ static int hugetlbfs_tmpfile(struct mnt_idmap *idmap,
 {
 	struct inode *inode;
 
-	inode = hugetlbfs_get_inode(dir->i_sb, dir, mode | S_IFREG, 0);
+	inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode | S_IFREG, 0);
 	if (!inode)
 		return -ENOSPC;
 	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
@@ -1083,10 +1095,11 @@ static int hugetlbfs_symlink(struct mnt_idmap *idmap,
 			     struct inode *dir, struct dentry *dentry,
 			     const char *symname)
 {
+	const umode_t mode = S_IFLNK|S_IRWXUGO;
 	struct inode *inode;
 	int error = -ENOSPC;
 
-	inode = hugetlbfs_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0);
+	inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode, 0);
 	if (inode) {
 		int l = strlen(symname)+1;
 		error = page_symlink(inode, symname, l);
@@ -1354,6 +1367,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par
 {
 	struct hugetlbfs_fs_context *ctx = fc->fs_private;
 	struct fs_parse_result result;
+	struct hstate *h;
 	char *rest;
 	unsigned long ps;
 	int opt;
@@ -1398,11 +1412,12 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par
 
 	case Opt_pagesize:
 		ps = memparse(param->string, &rest);
-		ctx->hstate = size_to_hstate(ps);
-		if (!ctx->hstate) {
+		h = size_to_hstate(ps);
+		if (!h) {
 			pr_err("Unsupported page size %lu MB\n", ps / SZ_1M);
 			return -EINVAL;
 		}
+		ctx->hstate = h;
 		return 0;
 
 	case Opt_min_size:
@@ -1553,6 +1568,7 @@ static struct file_system_type hugetlbfs_fs_type = {
 	.init_fs_context	= hugetlbfs_init_fs_context,
 	.parameters		= hugetlb_fs_parameters,
 	.kill_sb		= kill_litter_super,
+	.fs_flags               = FS_ALLOW_IDMAP,
 };
 
 static struct vfsmount *hugetlbfs_vfsmount[HUGE_MAX_HSTATE];
@@ -1606,7 +1622,9 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 	}
 
 	file = ERR_PTR(-ENOSPC);
-	inode = hugetlbfs_get_inode(mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0);
+	/* hugetlbfs_vfsmount[] mounts do not use idmapped mounts.  */
+	inode = hugetlbfs_get_inode(mnt->mnt_sb, &nop_mnt_idmap, NULL,
+				    S_IFREG | S_IRWXUGO, 0);
 	if (!inode)
 		goto out;
 	if (creat_flags == HUGETLB_SHMFS_INODE)
diff --git a/fs/inode.c b/fs/inode.c
index 91048c4c9c9e..d290f007b3d1 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -20,6 +20,7 @@
 #include <linux/ratelimit.h>
 #include <linux/list_lru.h>
 #include <linux/iversion.h>
+#include <linux/rw_hint.h>
 #include <trace/events/writeback.h>
 #include "internal.h"
 
@@ -588,7 +589,8 @@ void dump_mapping(const struct address_space *mapping)
 	}
 
 	dentry_ptr = container_of(dentry_first, struct dentry, d_u.d_alias);
-	if (get_kernel_nofault(dentry, dentry_ptr)) {
+	if (get_kernel_nofault(dentry, dentry_ptr) ||
+	    !dentry.d_parent || !dentry.d_name.name) {
 		pr_warn("aops:%ps ino:%lx invalid dentry:%px\n",
 				a_ops, ino, dentry_ptr);
 		return;
@@ -2285,7 +2287,7 @@ void __init inode_init(void)
 					 sizeof(struct inode),
 					 0,
 					 (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|
-					 SLAB_MEM_SPREAD|SLAB_ACCOUNT),
+					 SLAB_ACCOUNT),
 					 init_once);
 
 	/* Hash may have been set up in inode_init_early */
@@ -2509,7 +2511,7 @@ struct timespec64 inode_set_ctime_current(struct inode *inode)
 {
 	struct timespec64 now = current_time(inode);
 
-	inode_set_ctime(inode, now.tv_sec, now.tv_nsec);
+	inode_set_ctime_to_ts(inode, now);
 	return now;
 }
 EXPORT_SYMBOL(inode_set_ctime_current);
diff --git a/fs/internal.h b/fs/internal.h
index b67406435fc0..49c1fcfee4b3 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -183,6 +183,7 @@ extern struct open_how build_open_how(int flags, umode_t mode);
 extern int build_open_flags(const struct open_how *how, struct open_flags *op);
 struct file *file_close_fd_locked(struct files_struct *files, unsigned fd);
 
+long do_ftruncate(struct file *file, loff_t length, int small);
 long do_sys_ftruncate(unsigned int fd, loff_t length, int small);
 int chmod_common(const struct path *path, umode_t mode);
 int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
@@ -310,3 +311,10 @@ ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *po
 struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns);
 struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap);
 void mnt_idmap_put(struct mnt_idmap *idmap);
+struct stashed_operations {
+	void (*put_data)(void *data);
+	void (*init_inode)(struct inode *inode, void *data);
+};
+int path_from_stashed(struct dentry **stashed, unsigned long ino,
+		      struct vfsmount *mnt, void *data, struct path *path);
+void stashed_dentry_prune(struct dentry *dentry);
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 76cf22ac97d7..1d5abfdf0f22 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -763,6 +763,33 @@ static int ioctl_fssetxattr(struct file *file, void __user *argp)
 	return err;
 }
 
+static int ioctl_getfsuuid(struct file *file, void __user *argp)
+{
+	struct super_block *sb = file_inode(file)->i_sb;
+	struct fsuuid2 u = { .len = sb->s_uuid_len, };
+
+	if (!sb->s_uuid_len)
+		return -ENOIOCTLCMD;
+
+	memcpy(&u.uuid[0], &sb->s_uuid, sb->s_uuid_len);
+
+	return copy_to_user(argp, &u, sizeof(u)) ? -EFAULT : 0;
+}
+
+static int ioctl_get_fs_sysfs_path(struct file *file, void __user *argp)
+{
+	struct super_block *sb = file_inode(file)->i_sb;
+
+	if (!strlen(sb->s_sysfs_name))
+		return -ENOIOCTLCMD;
+
+	struct fs_sysfs_path u = {};
+
+	u.len = scnprintf(u.name, sizeof(u.name), "%s/%s", sb->s_type->name, sb->s_sysfs_name);
+
+	return copy_to_user(argp, &u, sizeof(u)) ? -EFAULT : 0;
+}
+
 /*
  * do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d.
  * It's just a simple helper for sys_ioctl and compat_sys_ioctl.
@@ -845,6 +872,12 @@ static int do_vfs_ioctl(struct file *filp, unsigned int fd,
 	case FS_IOC_FSSETXATTR:
 		return ioctl_fssetxattr(filp, argp);
 
+	case FS_IOC_GETFSUUID:
+		return ioctl_getfsuuid(filp, argp);
+
+	case FS_IOC_GETFSSYSFSPATH:
+		return ioctl_get_fs_sysfs_path(filp, argp);
+
 	default:
 		if (S_ISREG(inode->i_mode))
 			return file_ioctl(filp, cmd, argp);
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 093c4515b22a..4e8e41c8b3c0 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2010 Red Hat, Inc.
- * Copyright (C) 2016-2019 Christoph Hellwig.
+ * Copyright (C) 2016-2023 Christoph Hellwig.
  */
 #include <linux/module.h>
 #include <linux/compiler.h>
@@ -95,6 +95,44 @@ static inline bool ifs_block_is_dirty(struct folio *folio,
 	return test_bit(block + blks_per_folio, ifs->state);
 }
 
+static unsigned ifs_find_dirty_range(struct folio *folio,
+		struct iomap_folio_state *ifs, u64 *range_start, u64 range_end)
+{
+	struct inode *inode = folio->mapping->host;
+	unsigned start_blk =
+		offset_in_folio(folio, *range_start) >> inode->i_blkbits;
+	unsigned end_blk = min_not_zero(
+		offset_in_folio(folio, range_end) >> inode->i_blkbits,
+		i_blocks_per_folio(inode, folio));
+	unsigned nblks = 1;
+
+	while (!ifs_block_is_dirty(folio, ifs, start_blk))
+		if (++start_blk == end_blk)
+			return 0;
+
+	while (start_blk + nblks < end_blk) {
+		if (!ifs_block_is_dirty(folio, ifs, start_blk + nblks))
+			break;
+		nblks++;
+	}
+
+	*range_start = folio_pos(folio) + (start_blk << inode->i_blkbits);
+	return nblks << inode->i_blkbits;
+}
+
+static unsigned iomap_find_dirty_range(struct folio *folio, u64 *range_start,
+		u64 range_end)
+{
+	struct iomap_folio_state *ifs = folio->private;
+
+	if (*range_start >= range_end)
+		return 0;
+
+	if (ifs)
+		return ifs_find_dirty_range(folio, ifs, range_start, range_end);
+	return range_end - *range_start;
+}
+
 static void ifs_clear_range_dirty(struct folio *folio,
 		struct iomap_folio_state *ifs, size_t off, size_t len)
 {
@@ -1454,15 +1492,10 @@ out_unlock:
 EXPORT_SYMBOL_GPL(iomap_page_mkwrite);
 
 static void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
-		size_t len, int error)
+		size_t len)
 {
 	struct iomap_folio_state *ifs = folio->private;
 
-	if (error) {
-		folio_set_error(folio);
-		mapping_set_error(inode->i_mapping, error);
-	}
-
 	WARN_ON_ONCE(i_blocks_per_folio(inode, folio) > 1 && !ifs);
 	WARN_ON_ONCE(ifs && atomic_read(&ifs->write_bytes_pending) <= 0);
 
@@ -1479,40 +1512,29 @@ static u32
 iomap_finish_ioend(struct iomap_ioend *ioend, int error)
 {
 	struct inode *inode = ioend->io_inode;
-	struct bio *bio = &ioend->io_inline_bio;
-	struct bio *last = ioend->io_bio, *next;
-	u64 start = bio->bi_iter.bi_sector;
-	loff_t offset = ioend->io_offset;
-	bool quiet = bio_flagged(bio, BIO_QUIET);
+	struct bio *bio = &ioend->io_bio;
+	struct folio_iter fi;
 	u32 folio_count = 0;
 
-	for (bio = &ioend->io_inline_bio; bio; bio = next) {
-		struct folio_iter fi;
-
-		/*
-		 * For the last bio, bi_private points to the ioend, so we
-		 * need to explicitly end the iteration here.
-		 */
-		if (bio == last)
-			next = NULL;
-		else
-			next = bio->bi_private;
-
-		/* walk all folios in bio, ending page IO on them */
-		bio_for_each_folio_all(fi, bio) {
-			iomap_finish_folio_write(inode, fi.folio, fi.length,
-					error);
-			folio_count++;
+	if (error) {
+		mapping_set_error(inode->i_mapping, error);
+		if (!bio_flagged(bio, BIO_QUIET)) {
+			pr_err_ratelimited(
+"%s: writeback error on inode %lu, offset %lld, sector %llu",
+				inode->i_sb->s_id, inode->i_ino,
+				ioend->io_offset, ioend->io_sector);
 		}
-		bio_put(bio);
 	}
-	/* The ioend has been freed by bio_put() */
 
-	if (unlikely(error && !quiet)) {
-		printk_ratelimited(KERN_ERR
-"%s: writeback error on inode %lu, offset %lld, sector %llu",
-			inode->i_sb->s_id, inode->i_ino, offset, start);
+	/* walk all folios in bio, ending page IO on them */
+	bio_for_each_folio_all(fi, bio) {
+		if (error)
+			folio_set_error(fi.folio);
+		iomap_finish_folio_write(inode, fi.folio, fi.length);
+		folio_count++;
 	}
+
+	bio_put(bio);	/* frees the ioend */
 	return folio_count;
 }
 
@@ -1553,7 +1575,7 @@ EXPORT_SYMBOL_GPL(iomap_finish_ioends);
 static bool
 iomap_ioend_can_merge(struct iomap_ioend *ioend, struct iomap_ioend *next)
 {
-	if (ioend->io_bio->bi_status != next->io_bio->bi_status)
+	if (ioend->io_bio.bi_status != next->io_bio.bi_status)
 		return false;
 	if ((ioend->io_flags & IOMAP_F_SHARED) ^
 	    (next->io_flags & IOMAP_F_SHARED))
@@ -1618,47 +1640,46 @@ EXPORT_SYMBOL_GPL(iomap_sort_ioends);
 
 static void iomap_writepage_end_bio(struct bio *bio)
 {
-	struct iomap_ioend *ioend = bio->bi_private;
-
-	iomap_finish_ioend(ioend, blk_status_to_errno(bio->bi_status));
+	iomap_finish_ioend(iomap_ioend_from_bio(bio),
+			blk_status_to_errno(bio->bi_status));
 }
 
 /*
  * Submit the final bio for an ioend.
  *
  * If @error is non-zero, it means that we have a situation where some part of
- * the submission process has failed after we've marked pages for writeback
- * and unlocked them.  In this situation, we need to fail the bio instead of
- * submitting it.  This typically only happens on a filesystem shutdown.
+ * the submission process has failed after we've marked pages for writeback.
+ * We cannot cancel ioend directly in that case, so call the bio end I/O handler
+ * with the error status here to run the normal I/O completion handler to clear
+ * the writeback bit and let the file system proess the errors.
  */
-static int
-iomap_submit_ioend(struct iomap_writepage_ctx *wpc, struct iomap_ioend *ioend,
-		int error)
+static int iomap_submit_ioend(struct iomap_writepage_ctx *wpc, int error)
 {
-	ioend->io_bio->bi_private = ioend;
-	ioend->io_bio->bi_end_io = iomap_writepage_end_bio;
+	if (!wpc->ioend)
+		return error;
 
+	/*
+	 * Let the file systems prepare the I/O submission and hook in an I/O
+	 * comletion handler.  This also needs to happen in case after a
+	 * failure happened so that the file system end I/O handler gets called
+	 * to clean up.
+	 */
 	if (wpc->ops->prepare_ioend)
-		error = wpc->ops->prepare_ioend(ioend, error);
+		error = wpc->ops->prepare_ioend(wpc->ioend, error);
+
 	if (error) {
-		/*
-		 * If we're failing the IO now, just mark the ioend with an
-		 * error and finish it.  This will run IO completion immediately
-		 * as there is only one reference to the ioend at this point in
-		 * time.
-		 */
-		ioend->io_bio->bi_status = errno_to_blk_status(error);
-		bio_endio(ioend->io_bio);
-		return error;
+		wpc->ioend->io_bio.bi_status = errno_to_blk_status(error);
+		bio_endio(&wpc->ioend->io_bio);
+	} else {
+		submit_bio(&wpc->ioend->io_bio);
 	}
 
-	submit_bio(ioend->io_bio);
-	return 0;
+	wpc->ioend = NULL;
+	return error;
 }
 
-static struct iomap_ioend *
-iomap_alloc_ioend(struct inode *inode, struct iomap_writepage_ctx *wpc,
-		loff_t offset, sector_t sector, struct writeback_control *wbc)
+static struct iomap_ioend *iomap_alloc_ioend(struct iomap_writepage_ctx *wpc,
+		struct writeback_control *wbc, struct inode *inode, loff_t pos)
 {
 	struct iomap_ioend *ioend;
 	struct bio *bio;
@@ -1666,63 +1687,42 @@ iomap_alloc_ioend(struct inode *inode, struct iomap_writepage_ctx *wpc,
 	bio = bio_alloc_bioset(wpc->iomap.bdev, BIO_MAX_VECS,
 			       REQ_OP_WRITE | wbc_to_write_flags(wbc),
 			       GFP_NOFS, &iomap_ioend_bioset);
-	bio->bi_iter.bi_sector = sector;
+	bio->bi_iter.bi_sector = iomap_sector(&wpc->iomap, pos);
+	bio->bi_end_io = iomap_writepage_end_bio;
 	wbc_init_bio(wbc, bio);
+	bio->bi_write_hint = inode->i_write_hint;
 
-	ioend = container_of(bio, struct iomap_ioend, io_inline_bio);
+	ioend = iomap_ioend_from_bio(bio);
 	INIT_LIST_HEAD(&ioend->io_list);
 	ioend->io_type = wpc->iomap.type;
 	ioend->io_flags = wpc->iomap.flags;
 	ioend->io_inode = inode;
 	ioend->io_size = 0;
-	ioend->io_folios = 0;
-	ioend->io_offset = offset;
-	ioend->io_bio = bio;
-	ioend->io_sector = sector;
-	return ioend;
-}
-
-/*
- * Allocate a new bio, and chain the old bio to the new one.
- *
- * Note that we have to perform the chaining in this unintuitive order
- * so that the bi_private linkage is set up in the right direction for the
- * traversal in iomap_finish_ioend().
- */
-static struct bio *
-iomap_chain_bio(struct bio *prev)
-{
-	struct bio *new;
-
-	new = bio_alloc(prev->bi_bdev, BIO_MAX_VECS, prev->bi_opf, GFP_NOFS);
-	bio_clone_blkg_association(new, prev);
-	new->bi_iter.bi_sector = bio_end_sector(prev);
+	ioend->io_offset = pos;
+	ioend->io_sector = bio->bi_iter.bi_sector;
 
-	bio_chain(prev, new);
-	bio_get(prev);		/* for iomap_finish_ioend */
-	submit_bio(prev);
-	return new;
+	wpc->nr_folios = 0;
+	return ioend;
 }
 
-static bool
-iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t offset,
-		sector_t sector)
+static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos)
 {
 	if ((wpc->iomap.flags & IOMAP_F_SHARED) !=
 	    (wpc->ioend->io_flags & IOMAP_F_SHARED))
 		return false;
 	if (wpc->iomap.type != wpc->ioend->io_type)
 		return false;
-	if (offset != wpc->ioend->io_offset + wpc->ioend->io_size)
+	if (pos != wpc->ioend->io_offset + wpc->ioend->io_size)
 		return false;
-	if (sector != bio_end_sector(wpc->ioend->io_bio))
+	if (iomap_sector(&wpc->iomap, pos) !=
+	    bio_end_sector(&wpc->ioend->io_bio))
 		return false;
 	/*
 	 * Limit ioend bio chain lengths to minimise IO completion latency. This
 	 * also prevents long tight loops ending page writeback on all the
 	 * folios in the ioend.
 	 */
-	if (wpc->ioend->io_folios >= IOEND_BATCH_SIZE)
+	if (wpc->nr_folios >= IOEND_BATCH_SIZE)
 		return false;
 	return true;
 }
@@ -1730,255 +1730,238 @@ iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t offset,
 /*
  * Test to see if we have an existing ioend structure that we could append to
  * first; otherwise finish off the current ioend and start another.
+ *
+ * If a new ioend is created and cached, the old ioend is submitted to the block
+ * layer instantly.  Batching optimisations are provided by higher level block
+ * plugging.
+ *
+ * At the end of a writeback pass, there will be a cached ioend remaining on the
+ * writepage context that the caller will need to submit.
  */
-static void
-iomap_add_to_ioend(struct inode *inode, loff_t pos, struct folio *folio,
-		struct iomap_folio_state *ifs, struct iomap_writepage_ctx *wpc,
-		struct writeback_control *wbc, struct list_head *iolist)
+static int iomap_add_to_ioend(struct iomap_writepage_ctx *wpc,
+		struct writeback_control *wbc, struct folio *folio,
+		struct inode *inode, loff_t pos, unsigned len)
 {
-	sector_t sector = iomap_sector(&wpc->iomap, pos);
-	unsigned len = i_blocksize(inode);
+	struct iomap_folio_state *ifs = folio->private;
 	size_t poff = offset_in_folio(folio, pos);
+	int error;
 
-	if (!wpc->ioend || !iomap_can_add_to_ioend(wpc, pos, sector)) {
-		if (wpc->ioend)
-			list_add(&wpc->ioend->io_list, iolist);
-		wpc->ioend = iomap_alloc_ioend(inode, wpc, pos, sector, wbc);
+	if (!wpc->ioend || !iomap_can_add_to_ioend(wpc, pos)) {
+new_ioend:
+		error = iomap_submit_ioend(wpc, 0);
+		if (error)
+			return error;
+		wpc->ioend = iomap_alloc_ioend(wpc, wbc, inode, pos);
 	}
 
-	if (!bio_add_folio(wpc->ioend->io_bio, folio, len, poff)) {
-		wpc->ioend->io_bio = iomap_chain_bio(wpc->ioend->io_bio);
-		bio_add_folio_nofail(wpc->ioend->io_bio, folio, len, poff);
-	}
+	if (!bio_add_folio(&wpc->ioend->io_bio, folio, len, poff))
+		goto new_ioend;
 
 	if (ifs)
 		atomic_add(len, &ifs->write_bytes_pending);
 	wpc->ioend->io_size += len;
 	wbc_account_cgroup_owner(wbc, &folio->page, len);
+	return 0;
 }
 
-/*
- * We implement an immediate ioend submission policy here to avoid needing to
- * chain multiple ioends and hence nest mempool allocations which can violate
- * the forward progress guarantees we need to provide. The current ioend we're
- * adding blocks to is cached in the writepage context, and if the new block
- * doesn't append to the cached ioend, it will create a new ioend and cache that
- * instead.
- *
- * If a new ioend is created and cached, the old ioend is returned and queued
- * locally for submission once the entire page is processed or an error has been
- * detected.  While ioends are submitted immediately after they are completed,
- * batching optimisations are provided by higher level block plugging.
- *
- * At the end of a writeback pass, there will be a cached ioend remaining on the
- * writepage context that the caller will need to submit.
- */
-static int
-iomap_writepage_map(struct iomap_writepage_ctx *wpc,
-		struct writeback_control *wbc, struct inode *inode,
-		struct folio *folio, u64 end_pos)
+static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc,
+		struct writeback_control *wbc, struct folio *folio,
+		struct inode *inode, u64 pos, unsigned dirty_len,
+		unsigned *count)
 {
-	struct iomap_folio_state *ifs = folio->private;
-	struct iomap_ioend *ioend, *next;
-	unsigned len = i_blocksize(inode);
-	unsigned nblocks = i_blocks_per_folio(inode, folio);
-	u64 pos = folio_pos(folio);
-	int error = 0, count = 0, i;
-	LIST_HEAD(submit_list);
-
-	WARN_ON_ONCE(end_pos <= pos);
-
-	if (!ifs && nblocks > 1) {
-		ifs = ifs_alloc(inode, folio, 0);
-		iomap_set_range_dirty(folio, 0, end_pos - pos);
-	}
+	int error;
 
-	WARN_ON_ONCE(ifs && atomic_read(&ifs->write_bytes_pending) != 0);
-
-	/*
-	 * Walk through the folio to find areas to write back. If we
-	 * run off the end of the current map or find the current map
-	 * invalid, grab a new one.
-	 */
-	for (i = 0; i < nblocks && pos < end_pos; i++, pos += len) {
-		if (ifs && !ifs_block_is_dirty(folio, ifs, i))
-			continue;
+	do {
+		unsigned map_len;
 
-		error = wpc->ops->map_blocks(wpc, inode, pos);
+		error = wpc->ops->map_blocks(wpc, inode, pos, dirty_len);
 		if (error)
 			break;
-		trace_iomap_writepage_map(inode, &wpc->iomap);
-		if (WARN_ON_ONCE(wpc->iomap.type == IOMAP_INLINE))
-			continue;
-		if (wpc->iomap.type == IOMAP_HOLE)
-			continue;
-		iomap_add_to_ioend(inode, pos, folio, ifs, wpc, wbc,
-				 &submit_list);
-		count++;
-	}
-	if (count)
-		wpc->ioend->io_folios++;
+		trace_iomap_writepage_map(inode, pos, dirty_len, &wpc->iomap);
 
-	WARN_ON_ONCE(!wpc->ioend && !list_empty(&submit_list));
-	WARN_ON_ONCE(!folio_test_locked(folio));
-	WARN_ON_ONCE(folio_test_writeback(folio));
-	WARN_ON_ONCE(folio_test_dirty(folio));
+		map_len = min_t(u64, dirty_len,
+			wpc->iomap.offset + wpc->iomap.length - pos);
+		WARN_ON_ONCE(!folio->private && map_len < dirty_len);
+
+		switch (wpc->iomap.type) {
+		case IOMAP_INLINE:
+			WARN_ON_ONCE(1);
+			error = -EIO;
+			break;
+		case IOMAP_HOLE:
+			break;
+		default:
+			error = iomap_add_to_ioend(wpc, wbc, folio, inode, pos,
+					map_len);
+			if (!error)
+				(*count)++;
+			break;
+		}
+		dirty_len -= map_len;
+		pos += map_len;
+	} while (dirty_len && !error);
 
 	/*
 	 * We cannot cancel the ioend directly here on error.  We may have
 	 * already set other pages under writeback and hence we have to run I/O
 	 * completion to mark the error state of the pages under writeback
 	 * appropriately.
+	 *
+	 * Just let the file system know what portion of the folio failed to
+	 * map.
 	 */
-	if (unlikely(error)) {
-		/*
-		 * Let the filesystem know what portion of the current page
-		 * failed to map. If the page hasn't been added to ioend, it
-		 * won't be affected by I/O completion and we must unlock it
-		 * now.
-		 */
-		if (wpc->ops->discard_folio)
-			wpc->ops->discard_folio(folio, pos);
-		if (!count) {
-			folio_unlock(folio);
-			goto done;
-		}
-	}
-
-	/*
-	 * We can have dirty bits set past end of file in page_mkwrite path
-	 * while mapping the last partial folio. Hence it's better to clear
-	 * all the dirty bits in the folio here.
-	 */
-	iomap_clear_range_dirty(folio, 0, folio_size(folio));
-	folio_start_writeback(folio);
-	folio_unlock(folio);
-
-	/*
-	 * Preserve the original error if there was one; catch
-	 * submission errors here and propagate into subsequent ioend
-	 * submissions.
-	 */
-	list_for_each_entry_safe(ioend, next, &submit_list, io_list) {
-		int error2;
-
-		list_del_init(&ioend->io_list);
-		error2 = iomap_submit_ioend(wpc, ioend, error);
-		if (error2 && !error)
-			error = error2;
-	}
-
-	/*
-	 * We can end up here with no error and nothing to write only if we race
-	 * with a partial page truncate on a sub-page block sized filesystem.
-	 */
-	if (!count)
-		folio_end_writeback(folio);
-done:
-	mapping_set_error(inode->i_mapping, error);
+	if (error && wpc->ops->discard_folio)
+		wpc->ops->discard_folio(folio, pos);
 	return error;
 }
 
 /*
- * Write out a dirty page.
+ * Check interaction of the folio with the file end.
  *
- * For delalloc space on the page, we need to allocate space and flush it.
- * For unwritten space on the page, we need to start the conversion to
- * regular allocated space.
+ * If the folio is entirely beyond i_size, return false.  If it straddles
+ * i_size, adjust end_pos and zero all data beyond i_size.
  */
-static int iomap_do_writepage(struct folio *folio,
-		struct writeback_control *wbc, void *data)
+static bool iomap_writepage_handle_eof(struct folio *folio, struct inode *inode,
+		u64 *end_pos)
 {
-	struct iomap_writepage_ctx *wpc = data;
-	struct inode *inode = folio->mapping->host;
-	u64 end_pos, isize;
-
-	trace_iomap_writepage(inode, folio_pos(folio), folio_size(folio));
+	u64 isize = i_size_read(inode);
 
-	/*
-	 * Refuse to write the folio out if we're called from reclaim context.
-	 *
-	 * This avoids stack overflows when called from deeply used stacks in
-	 * random callers for direct reclaim or memcg reclaim.  We explicitly
-	 * allow reclaim from kswapd as the stack usage there is relatively low.
-	 *
-	 * This should never happen except in the case of a VM regression so
-	 * warn about it.
-	 */
-	if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) ==
-			PF_MEMALLOC))
-		goto redirty;
-
-	/*
-	 * Is this folio beyond the end of the file?
-	 *
-	 * The folio index is less than the end_index, adjust the end_pos
-	 * to the highest offset that this folio should represent.
-	 * -----------------------------------------------------
-	 * |			file mapping	       | <EOF> |
-	 * -----------------------------------------------------
-	 * | Page ... | Page N-2 | Page N-1 |  Page N  |       |
-	 * ^--------------------------------^----------|--------
-	 * |     desired writeback range    |      see else    |
-	 * ---------------------------------^------------------|
-	 */
-	isize = i_size_read(inode);
-	end_pos = folio_pos(folio) + folio_size(folio);
-	if (end_pos > isize) {
-		/*
-		 * Check whether the page to write out is beyond or straddles
-		 * i_size or not.
-		 * -------------------------------------------------------
-		 * |		file mapping		        | <EOF>  |
-		 * -------------------------------------------------------
-		 * | Page ... | Page N-2 | Page N-1 |  Page N   | Beyond |
-		 * ^--------------------------------^-----------|---------
-		 * |				    |      Straddles     |
-		 * ---------------------------------^-----------|--------|
-		 */
+	if (*end_pos > isize) {
 		size_t poff = offset_in_folio(folio, isize);
 		pgoff_t end_index = isize >> PAGE_SHIFT;
 
 		/*
-		 * Skip the page if it's fully outside i_size, e.g.
-		 * due to a truncate operation that's in progress.  We've
-		 * cleaned this page and truncate will finish things off for
-		 * us.
+		 * If the folio is entirely ouside of i_size, skip it.
+		 *
+		 * This can happen due to a truncate operation that is in
+		 * progress and in that case truncate will finish it off once
+		 * we've dropped the folio lock.
 		 *
-		 * Note that the end_index is unsigned long.  If the given
-		 * offset is greater than 16TB on a 32-bit system then if we
-		 * checked if the page is fully outside i_size with
-		 * "if (page->index >= end_index + 1)", "end_index + 1" would
-		 * overflow and evaluate to 0.  Hence this page would be
+		 * Note that the pgoff_t used for end_index is an unsigned long.
+		 * If the given offset is greater than 16TB on a 32-bit system,
+		 * then if we checked if the folio is fully outside i_size with
+		 * "if (folio->index >= end_index + 1)", "end_index + 1" would
+		 * overflow and evaluate to 0.  Hence this folio would be
 		 * redirtied and written out repeatedly, which would result in
 		 * an infinite loop; the user program performing this operation
 		 * would hang.  Instead, we can detect this situation by
-		 * checking if the page is totally beyond i_size or if its
+		 * checking if the folio is totally beyond i_size or if its
 		 * offset is just equal to the EOF.
 		 */
 		if (folio->index > end_index ||
 		    (folio->index == end_index && poff == 0))
-			goto unlock;
+			return false;
 
 		/*
-		 * The page straddles i_size.  It must be zeroed out on each
-		 * and every writepage invocation because it may be mmapped.
-		 * "A file is mapped in multiples of the page size.  For a file
-		 * that is not a multiple of the page size, the remaining
-		 * memory is zeroed when mapped, and writes to that region are
-		 * not written out to the file."
+		 * The folio straddles i_size.
+		 *
+		 * It must be zeroed out on each and every writepage invocation
+		 * because it may be mmapped:
+		 *
+		 *    A file is mapped in multiples of the page size.  For a
+		 *    file that is not a multiple of the page size, the
+		 *    remaining memory is zeroed when mapped, and writes to that
+		 *    region are not written out to the file.
+		 *
+		 * Also adjust the writeback range to skip all blocks entirely
+		 * beyond i_size.
 		 */
 		folio_zero_segment(folio, poff, folio_size(folio));
-		end_pos = isize;
+		*end_pos = round_up(isize, i_blocksize(inode));
+	}
+
+	return true;
+}
+
+static int iomap_writepage_map(struct iomap_writepage_ctx *wpc,
+		struct writeback_control *wbc, struct folio *folio)
+{
+	struct iomap_folio_state *ifs = folio->private;
+	struct inode *inode = folio->mapping->host;
+	u64 pos = folio_pos(folio);
+	u64 end_pos = pos + folio_size(folio);
+	unsigned count = 0;
+	int error = 0;
+	u32 rlen;
+
+	WARN_ON_ONCE(!folio_test_locked(folio));
+	WARN_ON_ONCE(folio_test_dirty(folio));
+	WARN_ON_ONCE(folio_test_writeback(folio));
+
+	trace_iomap_writepage(inode, pos, folio_size(folio));
+
+	if (!iomap_writepage_handle_eof(folio, inode, &end_pos)) {
+		folio_unlock(folio);
+		return 0;
+	}
+	WARN_ON_ONCE(end_pos <= pos);
+
+	if (i_blocks_per_folio(inode, folio) > 1) {
+		if (!ifs) {
+			ifs = ifs_alloc(inode, folio, 0);
+			iomap_set_range_dirty(folio, 0, end_pos - pos);
+		}
+
+		/*
+		 * Keep the I/O completion handler from clearing the writeback
+		 * bit until we have submitted all blocks by adding a bias to
+		 * ifs->write_bytes_pending, which is dropped after submitting
+		 * all blocks.
+		 */
+		WARN_ON_ONCE(atomic_read(&ifs->write_bytes_pending) != 0);
+		atomic_inc(&ifs->write_bytes_pending);
 	}
 
-	return iomap_writepage_map(wpc, wbc, inode, folio, end_pos);
+	/*
+	 * Set the writeback bit ASAP, as the I/O completion for the single
+	 * block per folio case happen hit as soon as we're submitting the bio.
+	 */
+	folio_start_writeback(folio);
 
-redirty:
-	folio_redirty_for_writepage(wbc, folio);
-unlock:
+	/*
+	 * Walk through the folio to find dirty areas to write back.
+	 */
+	while ((rlen = iomap_find_dirty_range(folio, &pos, end_pos))) {
+		error = iomap_writepage_map_blocks(wpc, wbc, folio, inode,
+				pos, rlen, &count);
+		if (error)
+			break;
+		pos += rlen;
+	}
+
+	if (count)
+		wpc->nr_folios++;
+
+	/*
+	 * We can have dirty bits set past end of file in page_mkwrite path
+	 * while mapping the last partial folio. Hence it's better to clear
+	 * all the dirty bits in the folio here.
+	 */
+	iomap_clear_range_dirty(folio, 0, folio_size(folio));
+
+	/*
+	 * Usually the writeback bit is cleared by the I/O completion handler.
+	 * But we may end up either not actually writing any blocks, or (when
+	 * there are multiple blocks in a folio) all I/O might have finished
+	 * already at this point.  In that case we need to clear the writeback
+	 * bit ourselves right after unlocking the page.
+	 */
 	folio_unlock(folio);
-	return 0;
+	if (ifs) {
+		if (atomic_dec_and_test(&ifs->write_bytes_pending))
+			folio_end_writeback(folio);
+	} else {
+		if (!count)
+			folio_end_writeback(folio);
+	}
+	mapping_set_error(inode->i_mapping, error);
+	return error;
+}
+
+static int iomap_do_writepage(struct folio *folio,
+		struct writeback_control *wbc, void *data)
+{
+	return iomap_writepage_map(data, wbc, folio);
 }
 
 int
@@ -1988,18 +1971,24 @@ iomap_writepages(struct address_space *mapping, struct writeback_control *wbc,
 {
 	int			ret;
 
+	/*
+	 * Writeback from reclaim context should never happen except in the case
+	 * of a VM regression so warn about it and refuse to write the data.
+	 */
+	if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC | PF_KSWAPD)) ==
+			PF_MEMALLOC))
+		return -EIO;
+
 	wpc->ops = ops;
 	ret = write_cache_pages(mapping, wbc, iomap_do_writepage, wpc);
-	if (!wpc->ioend)
-		return ret;
-	return iomap_submit_ioend(wpc, wpc->ioend, ret);
+	return iomap_submit_ioend(wpc, ret);
 }
 EXPORT_SYMBOL_GPL(iomap_writepages);
 
 static int __init iomap_init(void)
 {
 	return bioset_init(&iomap_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE),
-			   offsetof(struct iomap_ioend, io_inline_bio),
+			   offsetof(struct iomap_ioend, io_bio),
 			   BIOSET_NEED_BVECS);
 }
 fs_initcall(iomap_init);
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index bcd3f8cf5ea4..f3b43d223a46 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -380,6 +380,7 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
 		fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits,
 					  GFP_KERNEL);
 		bio->bi_iter.bi_sector = iomap_sector(iomap, pos);
+		bio->bi_write_hint = inode->i_write_hint;
 		bio->bi_ioprio = dio->iocb->ki_ioprio;
 		bio->bi_private = dio;
 		bio->bi_end_io = iomap_dio_bio_end_io;
diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h
index c16fd55f5595..0a991c4ce87d 100644
--- a/fs/iomap/trace.h
+++ b/fs/iomap/trace.h
@@ -154,7 +154,48 @@ DEFINE_EVENT(iomap_class, name,	\
 	TP_ARGS(inode, iomap))
 DEFINE_IOMAP_EVENT(iomap_iter_dstmap);
 DEFINE_IOMAP_EVENT(iomap_iter_srcmap);
-DEFINE_IOMAP_EVENT(iomap_writepage_map);
+
+TRACE_EVENT(iomap_writepage_map,
+	TP_PROTO(struct inode *inode, u64 pos, unsigned int dirty_len,
+		 struct iomap *iomap),
+	TP_ARGS(inode, pos, dirty_len, iomap),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(u64, ino)
+		__field(u64, pos)
+		__field(u64, dirty_len)
+		__field(u64, addr)
+		__field(loff_t, offset)
+		__field(u64, length)
+		__field(u16, type)
+		__field(u16, flags)
+		__field(dev_t, bdev)
+	),
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->pos = pos;
+		__entry->dirty_len = dirty_len;
+		__entry->addr = iomap->addr;
+		__entry->offset = iomap->offset;
+		__entry->length = iomap->length;
+		__entry->type = iomap->type;
+		__entry->flags = iomap->flags;
+		__entry->bdev = iomap->bdev ? iomap->bdev->bd_dev : 0;
+	),
+	TP_printk("dev %d:%d ino 0x%llx bdev %d:%d pos 0x%llx dirty len 0x%llx "
+		  "addr 0x%llx offset 0x%llx length 0x%llx type %s flags %s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  MAJOR(__entry->bdev), MINOR(__entry->bdev),
+		  __entry->pos,
+		  __entry->dirty_len,
+		  __entry->addr,
+		  __entry->offset,
+		  __entry->length,
+		  __print_symbolic(__entry->type, IOMAP_TYPE_STRINGS),
+		  __print_flags(__entry->flags, "|", IOMAP_F_FLAGS_STRINGS))
+);
 
 TRACE_EVENT(iomap_iter,
 	TP_PROTO(struct iomap_iter *iter, const void *ops,
@@ -165,6 +206,7 @@ TRACE_EVENT(iomap_iter,
 		__field(u64, ino)
 		__field(loff_t, pos)
 		__field(u64, length)
+		__field(s64, processed)
 		__field(unsigned int, flags)
 		__field(const void *, ops)
 		__field(unsigned long, caller)
@@ -174,15 +216,17 @@ TRACE_EVENT(iomap_iter,
 		__entry->ino = iter->inode->i_ino;
 		__entry->pos = iter->pos;
 		__entry->length = iomap_length(iter);
+		__entry->processed = iter->processed;
 		__entry->flags = iter->flags;
 		__entry->ops = ops;
 		__entry->caller = caller;
 	),
-	TP_printk("dev %d:%d ino 0x%llx pos 0x%llx length 0x%llx flags %s (0x%x) ops %ps caller %pS",
+	TP_printk("dev %d:%d ino 0x%llx pos 0x%llx length 0x%llx processed %lld flags %s (0x%x) ops %ps caller %pS",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		   __entry->ino,
 		   __entry->pos,
 		   __entry->length,
+		   __entry->processed,
 		   __print_flags(__entry->flags, "|", IOMAP_FLAGS_STRINGS),
 		   __entry->flags,
 		   __entry->ops,
diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c
index 8eec84c651bf..cb3cda1390ad 100644
--- a/fs/jfs/jfs_dmap.c
+++ b/fs/jfs/jfs_dmap.c
@@ -2763,9 +2763,7 @@ static int dbBackSplit(dmtree_t *tp, int leafno, bool is_ctl)
  *	leafno	- the number of the leaf to be updated.
  *	newval	- the new value for the leaf.
  *
- * RETURN VALUES:
- *  0		- success
- *	-EIO	- i/o error
+ * RETURN VALUES: none
  */
 static int dbJoin(dmtree_t *tp, int leafno, int newval, bool is_ctl)
 {
@@ -2792,10 +2790,6 @@ static int dbJoin(dmtree_t *tp, int leafno, int newval, bool is_ctl)
 		 * get the buddy size (number of words covered) of
 		 * the new value.
 		 */
-
-		if ((newval - tp->dmt_budmin) > BUDMIN)
-			return -EIO;
-
 		budsz = BUDSIZE(newval, tp->dmt_budmin);
 
 		/* try to join.
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index cb6d1fda66a7..73389c68e251 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -1058,7 +1058,7 @@ void jfs_syncpt(struct jfs_log *log, int hard_sync)
 int lmLogOpen(struct super_block *sb)
 {
 	int rc;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct jfs_log *log;
 	struct jfs_sb_info *sbi = JFS_SBI(sb);
 
@@ -1070,7 +1070,7 @@ int lmLogOpen(struct super_block *sb)
 
 	mutex_lock(&jfs_log_mutex);
 	list_for_each_entry(log, &jfs_external_logs, journal_list) {
-		if (log->bdev_handle->bdev->bd_dev == sbi->logdev) {
+		if (file_bdev(log->bdev_file)->bd_dev == sbi->logdev) {
 			if (!uuid_equal(&log->uuid, &sbi->loguuid)) {
 				jfs_warn("wrong uuid on JFS journal");
 				mutex_unlock(&jfs_log_mutex);
@@ -1100,14 +1100,14 @@ int lmLogOpen(struct super_block *sb)
 	 * file systems to log may have n-to-1 relationship;
 	 */
 
-	bdev_handle = bdev_open_by_dev(sbi->logdev,
+	bdev_file = bdev_file_open_by_dev(sbi->logdev,
 			BLK_OPEN_READ | BLK_OPEN_WRITE, log, NULL);
-	if (IS_ERR(bdev_handle)) {
-		rc = PTR_ERR(bdev_handle);
+	if (IS_ERR(bdev_file)) {
+		rc = PTR_ERR(bdev_file);
 		goto free;
 	}
 
-	log->bdev_handle = bdev_handle;
+	log->bdev_file = bdev_file;
 	uuid_copy(&log->uuid, &sbi->loguuid);
 
 	/*
@@ -1141,7 +1141,7 @@ journal_found:
 	lbmLogShutdown(log);
 
       close:		/* close external log device */
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 
       free:		/* free log descriptor */
 	mutex_unlock(&jfs_log_mutex);
@@ -1162,7 +1162,7 @@ static int open_inline_log(struct super_block *sb)
 	init_waitqueue_head(&log->syncwait);
 
 	set_bit(log_INLINELOG, &log->flag);
-	log->bdev_handle = sb->s_bdev_handle;
+	log->bdev_file = sb->s_bdev_file;
 	log->base = addressPXD(&JFS_SBI(sb)->logpxd);
 	log->size = lengthPXD(&JFS_SBI(sb)->logpxd) >>
 	    (L2LOGPSIZE - sb->s_blocksize_bits);
@@ -1436,7 +1436,7 @@ int lmLogClose(struct super_block *sb)
 {
 	struct jfs_sb_info *sbi = JFS_SBI(sb);
 	struct jfs_log *log = sbi->log;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	int rc = 0;
 
 	jfs_info("lmLogClose: log:0x%p", log);
@@ -1482,10 +1482,10 @@ int lmLogClose(struct super_block *sb)
 	 *	external log as separate logical volume
 	 */
 	list_del(&log->journal_list);
-	bdev_handle = log->bdev_handle;
+	bdev_file = log->bdev_file;
 	rc = lmLogShutdown(log);
 
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 
 	kfree(log);
 
@@ -1972,7 +1972,7 @@ static int lbmRead(struct jfs_log * log, int pn, struct lbuf ** bpp)
 
 	bp->l_flag |= lbmREAD;
 
-	bio = bio_alloc(log->bdev_handle->bdev, 1, REQ_OP_READ, GFP_NOFS);
+	bio = bio_alloc(file_bdev(log->bdev_file), 1, REQ_OP_READ, GFP_NOFS);
 	bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9);
 	__bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset);
 	BUG_ON(bio->bi_iter.bi_size != LOGPSIZE);
@@ -2115,7 +2115,7 @@ static void lbmStartIO(struct lbuf * bp)
 	jfs_info("lbmStartIO");
 
 	if (!log->no_integrity)
-		bdev = log->bdev_handle->bdev;
+		bdev = file_bdev(log->bdev_file);
 
 	bio = bio_alloc(bdev, 1, REQ_OP_WRITE | REQ_SYNC,
 			GFP_NOFS);
diff --git a/fs/jfs/jfs_logmgr.h b/fs/jfs/jfs_logmgr.h
index 84aa2d253907..8b8994e48cd0 100644
--- a/fs/jfs/jfs_logmgr.h
+++ b/fs/jfs/jfs_logmgr.h
@@ -356,7 +356,7 @@ struct jfs_log {
 				 *    before writing syncpt.
 				 */
 	struct list_head journal_list; /* Global list */
-	struct bdev_handle *bdev_handle; /* 4: log lv pointer */
+	struct file *bdev_file;	/* 4: log lv pointer */
 	int serial;		/* 4: log mount serial number */
 
 	s64 base;		/* @8: log extent address (inline log ) */
diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c
index 9b5c6a20b30c..98f9a432c336 100644
--- a/fs/jfs/jfs_mount.c
+++ b/fs/jfs/jfs_mount.c
@@ -431,7 +431,7 @@ int updateSuper(struct super_block *sb, uint state)
 	if (state == FM_MOUNT) {
 		/* record log's dev_t and mount serial number */
 		j_sb->s_logdev = cpu_to_le32(
-			new_encode_dev(sbi->log->bdev_handle->bdev->bd_dev));
+			new_encode_dev(file_bdev(sbi->log->bdev_file)->bd_dev));
 		j_sb->s_logserial = cpu_to_le32(sbi->log->serial);
 	} else if (state == FM_CLEAN) {
 		/*
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 8d8e556bd610..73f09a762b79 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -932,7 +932,7 @@ static int __init init_jfs_fs(void)
 
 	jfs_inode_cachep =
 	    kmem_cache_create_usercopy("jfs_ip", sizeof(struct jfs_inode_info),
-			0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT,
+			0, SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT,
 			offsetof(struct jfs_inode_info, i_inline_all),
 			sizeof_field(struct jfs_inode_info, i_inline_all),
 			init_once);
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 8b2bd65d70e7..bce1d7ac95ca 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -54,9 +54,9 @@ static bool kernfs_lockdep(struct kernfs_node *kn)
 static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen)
 {
 	if (!kn)
-		return strlcpy(buf, "(null)", buflen);
+		return strscpy(buf, "(null)", buflen);
 
-	return strlcpy(buf, kn->parent ? kn->name : "/", buflen);
+	return strscpy(buf, kn->parent ? kn->name : "/", buflen);
 }
 
 /* kernfs_node_depth - compute depth from @from to @to */
@@ -127,7 +127,7 @@ static struct kernfs_node *kernfs_common_ancestor(struct kernfs_node *a,
  *
  * [3] when @kn_to is %NULL result will be "(null)"
  *
- * Return: the length of the full path.  If the full length is equal to or
+ * Return: the length of the constructed path.  If the path would have been
  * greater than @buflen, @buf contains the truncated path with the trailing
  * '\0'.  On error, -errno is returned.
  */
@@ -138,16 +138,17 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
 	struct kernfs_node *kn, *common;
 	const char parent_str[] = "/..";
 	size_t depth_from, depth_to, len = 0;
+	ssize_t copied;
 	int i, j;
 
 	if (!kn_to)
-		return strlcpy(buf, "(null)", buflen);
+		return strscpy(buf, "(null)", buflen);
 
 	if (!kn_from)
 		kn_from = kernfs_root(kn_to)->kn;
 
 	if (kn_from == kn_to)
-		return strlcpy(buf, "/", buflen);
+		return strscpy(buf, "/", buflen);
 
 	common = kernfs_common_ancestor(kn_from, kn_to);
 	if (WARN_ON(!common))
@@ -158,18 +159,19 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
 
 	buf[0] = '\0';
 
-	for (i = 0; i < depth_from; i++)
-		len += strlcpy(buf + len, parent_str,
-			       len < buflen ? buflen - len : 0);
+	for (i = 0; i < depth_from; i++) {
+		copied = strscpy(buf + len, parent_str, buflen - len);
+		if (copied < 0)
+			return copied;
+		len += copied;
+	}
 
 	/* Calculate how many bytes we need for the rest */
 	for (i = depth_to - 1; i >= 0; i--) {
 		for (kn = kn_to, j = 0; j < i; j++)
 			kn = kn->parent;
-		len += strlcpy(buf + len, "/",
-			       len < buflen ? buflen - len : 0);
-		len += strlcpy(buf + len, kn->name,
-			       len < buflen ? buflen - len : 0);
+
+		len += scnprintf(buf + len, buflen - len, "/%s", kn->name);
 	}
 
 	return len;
@@ -182,12 +184,12 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
  * @buflen: size of @buf
  *
  * Copies the name of @kn into @buf of @buflen bytes.  The behavior is
- * similar to strlcpy().
+ * similar to strscpy().
  *
  * Fills buffer with "(null)" if @kn is %NULL.
  *
- * Return: the length of @kn's name and if @buf isn't long enough,
- * it's filled up to @buflen-1 and nul terminated.
+ * Return: the resulting length of @buf. If @buf isn't long enough,
+ * it's filled up to @buflen-1 and nul terminated, and returns -E2BIG.
  *
  * This function can be called from any context.
  */
@@ -214,7 +216,7 @@ int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen)
  * path (which includes '..'s) as needed to reach from @from to @to is
  * returned.
  *
- * Return: the length of the full path.  If the full length is equal to or
+ * Return: the length of the constructed path.  If the path would have been
  * greater than @buflen, @buf contains the truncated path with the trailing
  * '\0'.  On error, -errno is returned.
  */
@@ -265,12 +267,10 @@ void pr_cont_kernfs_path(struct kernfs_node *kn)
 	sz = kernfs_path_from_node(kn, NULL, kernfs_pr_cont_buf,
 				   sizeof(kernfs_pr_cont_buf));
 	if (sz < 0) {
-		pr_cont("(error)");
-		goto out;
-	}
-
-	if (sz >= sizeof(kernfs_pr_cont_buf)) {
-		pr_cont("(name too long)");
+		if (sz == -E2BIG)
+			pr_cont("(name too long)");
+		else
+			pr_cont("(error)");
 		goto out;
 	}
 
@@ -676,6 +676,18 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
 {
 	struct kernfs_node *kn;
 
+	if (parent->mode & S_ISGID) {
+		/* this code block imitates inode_init_owner() for
+		 * kernfs
+		 */
+
+		if (parent->iattr)
+			gid = parent->iattr->ia_gid;
+
+		if (flags & KERNFS_DIR)
+			mode |= S_ISGID;
+	}
+
 	kn = __kernfs_new_node(kernfs_root(parent), parent,
 			       name, mode, uid, gid, flags);
 	if (kn) {
@@ -850,16 +862,16 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
 					  const unsigned char *path,
 					  const void *ns)
 {
-	size_t len;
+	ssize_t len;
 	char *p, *name;
 
 	lockdep_assert_held_read(&kernfs_root(parent)->kernfs_rwsem);
 
 	spin_lock_irq(&kernfs_pr_cont_lock);
 
-	len = strlcpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf));
+	len = strscpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf));
 
-	if (len >= sizeof(kernfs_pr_cont_buf)) {
+	if (len < 0) {
 		spin_unlock_irq(&kernfs_pr_cont_lock);
 		return NULL;
 	}
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index f0cb729e9a97..ffa4565c275a 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -447,7 +447,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma)
 	 * warnings and we don't want to add spurious locking dependency
 	 * between the two.  Check whether mmap is actually implemented
 	 * without grabbing @of->mutex by testing HAS_MMAP flag.  See the
-	 * comment in kernfs_file_open() for more details.
+	 * comment in kernfs_fop_open() for more details.
 	 */
 	if (!(of->kn->flags & KERNFS_HAS_MMAP))
 		return -ENODEV;
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 4628edde2e7e..e29f4edf9572 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -125,9 +125,6 @@ static struct dentry *__kernfs_fh_to_dentry(struct super_block *sb,
 
 	inode = kernfs_get_inode(sb, kn);
 	kernfs_put(kn);
-	if (!inode)
-		return ERR_PTR(-ESTALE);
-
 	return d_obtain_alias(inode);
 }
 
@@ -361,7 +358,9 @@ int kernfs_get_tree(struct fs_context *fc)
 		}
 		sb->s_flags |= SB_ACTIVE;
 
-		uuid_gen(&sb->s_uuid);
+		uuid_t uuid;
+		uuid_gen(&uuid);
+		super_set_uuid(sb, uuid.b, sizeof(uuid));
 
 		down_write(&root->kernfs_supers_rwsem);
 		list_add(&info->node, &info->root->supers);
diff --git a/fs/libfs.c b/fs/libfs.c
index eec6031b0155..0d14ae808fcf 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -23,6 +23,7 @@
 #include <linux/fsnotify.h>
 #include <linux/unicode.h>
 #include <linux/fscrypt.h>
+#include <linux/pidfs.h>
 
 #include <linux/uaccess.h>
 
@@ -240,17 +241,22 @@ const struct inode_operations simple_dir_inode_operations = {
 };
 EXPORT_SYMBOL(simple_dir_inode_operations);
 
-static void offset_set(struct dentry *dentry, u32 offset)
+/* 0 is '.', 1 is '..', so always start with offset 2 or more */
+enum {
+	DIR_OFFSET_MIN	= 2,
+};
+
+static void offset_set(struct dentry *dentry, long offset)
 {
-	dentry->d_fsdata = (void *)((uintptr_t)(offset));
+	dentry->d_fsdata = (void *)offset;
 }
 
-static u32 dentry2offset(struct dentry *dentry)
+static long dentry2offset(struct dentry *dentry)
 {
-	return (u32)((uintptr_t)(dentry->d_fsdata));
+	return (long)dentry->d_fsdata;
 }
 
-static struct lock_class_key simple_offset_xa_lock;
+static struct lock_class_key simple_offset_lock_class;
 
 /**
  * simple_offset_init - initialize an offset_ctx
@@ -259,11 +265,9 @@ static struct lock_class_key simple_offset_xa_lock;
  */
 void simple_offset_init(struct offset_ctx *octx)
 {
-	xa_init_flags(&octx->xa, XA_FLAGS_ALLOC1);
-	lockdep_set_class(&octx->xa.xa_lock, &simple_offset_xa_lock);
-
-	/* 0 is '.', 1 is '..', so always start with offset 2 */
-	octx->next_offset = 2;
+	mt_init_flags(&octx->mt, MT_FLAGS_ALLOC_RANGE);
+	lockdep_set_class(&octx->mt.ma_lock, &simple_offset_lock_class);
+	octx->next_offset = DIR_OFFSET_MIN;
 }
 
 /**
@@ -271,20 +275,19 @@ void simple_offset_init(struct offset_ctx *octx)
  * @octx: directory offset ctx to be updated
  * @dentry: new dentry being added
  *
- * Returns zero on success. @so_ctx and the dentry offset are updated.
+ * Returns zero on success. @octx and the dentry's offset are updated.
  * Otherwise, a negative errno value is returned.
  */
 int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry)
 {
-	static const struct xa_limit limit = XA_LIMIT(2, U32_MAX);
-	u32 offset;
+	unsigned long offset;
 	int ret;
 
 	if (dentry2offset(dentry) != 0)
 		return -EBUSY;
 
-	ret = xa_alloc_cyclic(&octx->xa, &offset, dentry, limit,
-			      &octx->next_offset, GFP_KERNEL);
+	ret = mtree_alloc_cyclic(&octx->mt, &offset, dentry, DIR_OFFSET_MIN,
+				 LONG_MAX, &octx->next_offset, GFP_KERNEL);
 	if (ret < 0)
 		return ret;
 
@@ -300,17 +303,49 @@ int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry)
  */
 void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry)
 {
-	u32 offset;
+	long offset;
 
 	offset = dentry2offset(dentry);
 	if (offset == 0)
 		return;
 
-	xa_erase(&octx->xa, offset);
+	mtree_erase(&octx->mt, offset);
 	offset_set(dentry, 0);
 }
 
 /**
+ * simple_offset_empty - Check if a dentry can be unlinked
+ * @dentry: dentry to be tested
+ *
+ * Returns 0 if @dentry is a non-empty directory; otherwise returns 1.
+ */
+int simple_offset_empty(struct dentry *dentry)
+{
+	struct inode *inode = d_inode(dentry);
+	struct offset_ctx *octx;
+	struct dentry *child;
+	unsigned long index;
+	int ret = 1;
+
+	if (!inode || !S_ISDIR(inode->i_mode))
+		return ret;
+
+	index = DIR_OFFSET_MIN;
+	octx = inode->i_op->get_offset_ctx(inode);
+	mt_for_each(&octx->mt, child, index, LONG_MAX) {
+		spin_lock(&child->d_lock);
+		if (simple_positive(child)) {
+			spin_unlock(&child->d_lock);
+			ret = 0;
+			break;
+		}
+		spin_unlock(&child->d_lock);
+	}
+
+	return ret;
+}
+
+/**
  * simple_offset_rename_exchange - exchange rename with directory offsets
  * @old_dir: parent of dentry being moved
  * @old_dentry: dentry being moved
@@ -327,8 +362,8 @@ int simple_offset_rename_exchange(struct inode *old_dir,
 {
 	struct offset_ctx *old_ctx = old_dir->i_op->get_offset_ctx(old_dir);
 	struct offset_ctx *new_ctx = new_dir->i_op->get_offset_ctx(new_dir);
-	u32 old_index = dentry2offset(old_dentry);
-	u32 new_index = dentry2offset(new_dentry);
+	long old_index = dentry2offset(old_dentry);
+	long new_index = dentry2offset(new_dentry);
 	int ret;
 
 	simple_offset_remove(old_ctx, old_dentry);
@@ -354,9 +389,9 @@ int simple_offset_rename_exchange(struct inode *old_dir,
 
 out_restore:
 	offset_set(old_dentry, old_index);
-	xa_store(&old_ctx->xa, old_index, old_dentry, GFP_KERNEL);
+	mtree_store(&old_ctx->mt, old_index, old_dentry, GFP_KERNEL);
 	offset_set(new_dentry, new_index);
-	xa_store(&new_ctx->xa, new_index, new_dentry, GFP_KERNEL);
+	mtree_store(&new_ctx->mt, new_index, new_dentry, GFP_KERNEL);
 	return ret;
 }
 
@@ -369,7 +404,7 @@ out_restore:
  */
 void simple_offset_destroy(struct offset_ctx *octx)
 {
-	xa_destroy(&octx->xa);
+	mtree_destroy(&octx->mt);
 }
 
 /**
@@ -399,15 +434,16 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence)
 
 	/* In this case, ->private_data is protected by f_pos_lock */
 	file->private_data = NULL;
-	return vfs_setpos(file, offset, U32_MAX);
+	return vfs_setpos(file, offset, LONG_MAX);
 }
 
-static struct dentry *offset_find_next(struct xa_state *xas)
+static struct dentry *offset_find_next(struct offset_ctx *octx, loff_t offset)
 {
+	MA_STATE(mas, &octx->mt, offset, offset);
 	struct dentry *child, *found = NULL;
 
 	rcu_read_lock();
-	child = xas_next_entry(xas, U32_MAX);
+	child = mas_find(&mas, LONG_MAX);
 	if (!child)
 		goto out;
 	spin_lock(&child->d_lock);
@@ -421,8 +457,8 @@ out:
 
 static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry)
 {
-	u32 offset = dentry2offset(dentry);
 	struct inode *inode = d_inode(dentry);
+	long offset = dentry2offset(dentry);
 
 	return ctx->actor(ctx, dentry->d_name.name, dentry->d_name.len, offset,
 			  inode->i_ino, fs_umode_to_dtype(inode->i_mode));
@@ -430,12 +466,11 @@ static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry)
 
 static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
 {
-	struct offset_ctx *so_ctx = inode->i_op->get_offset_ctx(inode);
-	XA_STATE(xas, &so_ctx->xa, ctx->pos);
+	struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode);
 	struct dentry *dentry;
 
 	while (true) {
-		dentry = offset_find_next(&xas);
+		dentry = offset_find_next(octx, ctx->pos);
 		if (!dentry)
 			return ERR_PTR(-ENOENT);
 
@@ -444,8 +479,8 @@ static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
 			break;
 		}
 
+		ctx->pos = dentry2offset(dentry) + 1;
 		dput(dentry);
-		ctx->pos = xas.xa_index + 1;
 	}
 	return NULL;
 }
@@ -481,7 +516,7 @@ static int offset_readdir(struct file *file, struct dir_context *ctx)
 		return 0;
 
 	/* In this case, ->private_data is protected by f_pos_lock */
-	if (ctx->pos == 2)
+	if (ctx->pos == DIR_OFFSET_MIN)
 		file->private_data = NULL;
 	else if (file->private_data == ERR_PTR(-ENOENT))
 		return 0;
@@ -1580,7 +1615,7 @@ EXPORT_SYMBOL(alloc_anon_inode);
  * All arguments are ignored and it just returns -EINVAL.
  */
 int
-simple_nosetlease(struct file *filp, int arg, struct file_lock **flp,
+simple_nosetlease(struct file *filp, int arg, struct file_lease **flp,
 		  void **priv)
 {
 	return -EINVAL;
@@ -1704,16 +1739,28 @@ bool is_empty_dir_inode(struct inode *inode)
 static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
 				const char *str, const struct qstr *name)
 {
-	const struct dentry *parent = READ_ONCE(dentry->d_parent);
-	const struct inode *dir = READ_ONCE(parent->d_inode);
-	const struct super_block *sb = dentry->d_sb;
-	const struct unicode_map *um = sb->s_encoding;
-	struct qstr qstr = QSTR_INIT(str, len);
+	const struct dentry *parent;
+	const struct inode *dir;
 	char strbuf[DNAME_INLINE_LEN];
-	int ret;
+	struct qstr qstr;
+
+	/*
+	 * Attempt a case-sensitive match first. It is cheaper and
+	 * should cover most lookups, including all the sane
+	 * applications that expect a case-sensitive filesystem.
+	 *
+	 * This comparison is safe under RCU because the caller
+	 * guarantees the consistency between str and len. See
+	 * __d_lookup_rcu_op_compare() for details.
+	 */
+	if (len == name->len && !memcmp(str, name->name, len))
+		return 0;
 
+	parent = READ_ONCE(dentry->d_parent);
+	dir = READ_ONCE(parent->d_inode);
 	if (!dir || !IS_CASEFOLDED(dir))
-		goto fallback;
+		return 1;
+
 	/*
 	 * If the dentry name is stored in-line, then it may be concurrently
 	 * modified by a rename.  If this happens, the VFS will eventually retry
@@ -1724,20 +1771,14 @@ static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
 	if (len <= DNAME_INLINE_LEN - 1) {
 		memcpy(strbuf, str, len);
 		strbuf[len] = 0;
-		qstr.name = strbuf;
+		str = strbuf;
 		/* prevent compiler from optimizing out the temporary buffer */
 		barrier();
 	}
-	ret = utf8_strncasecmp(um, name, &qstr);
-	if (ret >= 0)
-		return ret;
+	qstr.len = len;
+	qstr.name = str;
 
-	if (sb_has_strict_encoding(sb))
-		return -EINVAL;
-fallback:
-	if (len != name->len)
-		return 1;
-	return !!memcmp(str, name->name, len);
+	return utf8_strncasecmp(dentry->d_sb->s_encoding, name, &qstr);
 }
 
 /**
@@ -1752,7 +1793,7 @@ static int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
 	const struct inode *dir = READ_ONCE(dentry->d_inode);
 	struct super_block *sb = dentry->d_sb;
 	const struct unicode_map *um = sb->s_encoding;
-	int ret = 0;
+	int ret;
 
 	if (!dir || !IS_CASEFOLDED(dir))
 		return 0;
@@ -1766,73 +1807,45 @@ static int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
 static const struct dentry_operations generic_ci_dentry_ops = {
 	.d_hash = generic_ci_d_hash,
 	.d_compare = generic_ci_d_compare,
-};
-#endif
-
 #ifdef CONFIG_FS_ENCRYPTION
-static const struct dentry_operations generic_encrypted_dentry_ops = {
 	.d_revalidate = fscrypt_d_revalidate,
+#endif
 };
 #endif
 
-#if defined(CONFIG_FS_ENCRYPTION) && IS_ENABLED(CONFIG_UNICODE)
-static const struct dentry_operations generic_encrypted_ci_dentry_ops = {
-	.d_hash = generic_ci_d_hash,
-	.d_compare = generic_ci_d_compare,
+#ifdef CONFIG_FS_ENCRYPTION
+static const struct dentry_operations generic_encrypted_dentry_ops = {
 	.d_revalidate = fscrypt_d_revalidate,
 };
 #endif
 
 /**
- * generic_set_encrypted_ci_d_ops - helper for setting d_ops for given dentry
- * @dentry:	dentry to set ops on
- *
- * Casefolded directories need d_hash and d_compare set, so that the dentries
- * contained in them are handled case-insensitively.  Note that these operations
- * are needed on the parent directory rather than on the dentries in it, and
- * while the casefolding flag can be toggled on and off on an empty directory,
- * dentry_operations can't be changed later.  As a result, if the filesystem has
- * casefolding support enabled at all, we have to give all dentries the
- * casefolding operations even if their inode doesn't have the casefolding flag
- * currently (and thus the casefolding ops would be no-ops for now).
- *
- * Encryption works differently in that the only dentry operation it needs is
- * d_revalidate, which it only needs on dentries that have the no-key name flag.
- * The no-key flag can't be set "later", so we don't have to worry about that.
+ * generic_set_sb_d_ops - helper for choosing the set of
+ * filesystem-wide dentry operations for the enabled features
+ * @sb: superblock to be configured
  *
- * Finally, to maximize compatibility with overlayfs (which isn't compatible
- * with certain dentry operations) and to avoid taking an unnecessary
- * performance hit, we use custom dentry_operations for each possible
- * combination rather than always installing all operations.
+ * Filesystems supporting casefolding and/or fscrypt can call this
+ * helper at mount-time to configure sb->s_d_op to best set of dentry
+ * operations required for the enabled features. The helper must be
+ * called after these have been configured, but before the root dentry
+ * is created.
  */
-void generic_set_encrypted_ci_d_ops(struct dentry *dentry)
+void generic_set_sb_d_ops(struct super_block *sb)
 {
-#ifdef CONFIG_FS_ENCRYPTION
-	bool needs_encrypt_ops = dentry->d_flags & DCACHE_NOKEY_NAME;
-#endif
 #if IS_ENABLED(CONFIG_UNICODE)
-	bool needs_ci_ops = dentry->d_sb->s_encoding;
-#endif
-#if defined(CONFIG_FS_ENCRYPTION) && IS_ENABLED(CONFIG_UNICODE)
-	if (needs_encrypt_ops && needs_ci_ops) {
-		d_set_d_op(dentry, &generic_encrypted_ci_dentry_ops);
+	if (sb->s_encoding) {
+		sb->s_d_op = &generic_ci_dentry_ops;
 		return;
 	}
 #endif
 #ifdef CONFIG_FS_ENCRYPTION
-	if (needs_encrypt_ops) {
-		d_set_d_op(dentry, &generic_encrypted_dentry_ops);
-		return;
-	}
-#endif
-#if IS_ENABLED(CONFIG_UNICODE)
-	if (needs_ci_ops) {
-		d_set_d_op(dentry, &generic_ci_dentry_ops);
+	if (sb->s_cop) {
+		sb->s_d_op = &generic_encrypted_dentry_ops;
 		return;
 	}
 #endif
 }
-EXPORT_SYMBOL(generic_set_encrypted_ci_d_ops);
+EXPORT_SYMBOL(generic_set_sb_d_ops);
 
 /**
  * inode_maybe_inc_iversion - increments i_version
@@ -1973,3 +1986,144 @@ struct timespec64 simple_inode_init_ts(struct inode *inode)
 	return ts;
 }
 EXPORT_SYMBOL(simple_inode_init_ts);
+
+static inline struct dentry *get_stashed_dentry(struct dentry *stashed)
+{
+	struct dentry *dentry;
+
+	guard(rcu)();
+	dentry = READ_ONCE(stashed);
+	if (!dentry)
+		return NULL;
+	if (!lockref_get_not_dead(&dentry->d_lockref))
+		return NULL;
+	return dentry;
+}
+
+static struct dentry *prepare_anon_dentry(struct dentry **stashed,
+					  unsigned long ino,
+					  struct super_block *sb,
+					  void *data)
+{
+	struct dentry *dentry;
+	struct inode *inode;
+	const struct stashed_operations *sops = sb->s_fs_info;
+
+	dentry = d_alloc_anon(sb);
+	if (!dentry)
+		return ERR_PTR(-ENOMEM);
+
+	inode = new_inode_pseudo(sb);
+	if (!inode) {
+		dput(dentry);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	inode->i_ino = ino;
+	inode->i_flags |= S_IMMUTABLE;
+	inode->i_mode = S_IFREG;
+	simple_inode_init_ts(inode);
+	sops->init_inode(inode, data);
+
+	/* Notice when this is changed. */
+	WARN_ON_ONCE(!S_ISREG(inode->i_mode));
+	WARN_ON_ONCE(!IS_IMMUTABLE(inode));
+
+	/* Store address of location where dentry's supposed to be stashed. */
+	dentry->d_fsdata = stashed;
+
+	/* @data is now owned by the fs */
+	d_instantiate(dentry, inode);
+	return dentry;
+}
+
+static struct dentry *stash_dentry(struct dentry **stashed,
+				   struct dentry *dentry)
+{
+	guard(rcu)();
+	for (;;) {
+		struct dentry *old;
+
+		/* Assume any old dentry was cleared out. */
+		old = cmpxchg(stashed, NULL, dentry);
+		if (likely(!old))
+			return dentry;
+
+		/* Check if somebody else installed a reusable dentry. */
+		if (lockref_get_not_dead(&old->d_lockref))
+			return old;
+
+		/* There's an old dead dentry there, try to take it over. */
+		if (likely(try_cmpxchg(stashed, &old, dentry)))
+			return dentry;
+	}
+}
+
+/**
+ * path_from_stashed - create path from stashed or new dentry
+ * @stashed:    where to retrieve or stash dentry
+ * @ino:        inode number to use
+ * @mnt:        mnt of the filesystems to use
+ * @data:       data to store in inode->i_private
+ * @path:       path to create
+ *
+ * The function tries to retrieve a stashed dentry from @stashed. If the dentry
+ * is still valid then it will be reused. If the dentry isn't able the function
+ * will allocate a new dentry and inode. It will then check again whether it
+ * can reuse an existing dentry in case one has been added in the meantime or
+ * update @stashed with the newly added dentry.
+ *
+ * Special-purpose helper for nsfs and pidfs.
+ *
+ * Return: On success zero and on failure a negative error is returned.
+ */
+int path_from_stashed(struct dentry **stashed, unsigned long ino,
+		      struct vfsmount *mnt, void *data, struct path *path)
+{
+	struct dentry *dentry;
+	const struct stashed_operations *sops = mnt->mnt_sb->s_fs_info;
+
+	/* See if dentry can be reused. */
+	path->dentry = get_stashed_dentry(*stashed);
+	if (path->dentry) {
+		sops->put_data(data);
+		goto out_path;
+	}
+
+	/* Allocate a new dentry. */
+	dentry = prepare_anon_dentry(stashed, ino, mnt->mnt_sb, data);
+	if (IS_ERR(dentry)) {
+		sops->put_data(data);
+		return PTR_ERR(dentry);
+	}
+
+	/* Added a new dentry. @data is now owned by the filesystem. */
+	path->dentry = stash_dentry(stashed, dentry);
+	if (path->dentry != dentry)
+		dput(dentry);
+
+out_path:
+	WARN_ON_ONCE(path->dentry->d_fsdata != stashed);
+	WARN_ON_ONCE(d_inode(path->dentry)->i_private != data);
+	path->mnt = mntget(mnt);
+	return 0;
+}
+
+void stashed_dentry_prune(struct dentry *dentry)
+{
+	struct dentry **stashed = dentry->d_fsdata;
+	struct inode *inode = d_inode(dentry);
+
+	if (WARN_ON_ONCE(!stashed))
+		return;
+
+	if (!inode)
+		return;
+
+	/*
+	 * Only replace our own @dentry as someone else might've
+	 * already cleared out @dentry and stashed their own
+	 * dentry in there.
+	 */
+	cmpxchg(stashed, dentry, NULL);
+}
diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c
index 8161667c976f..527458db4525 100644
--- a/fs/lockd/clnt4xdr.c
+++ b/fs/lockd/clnt4xdr.c
@@ -243,7 +243,7 @@ static void encode_nlm4_holder(struct xdr_stream *xdr,
 	u64 l_offset, l_len;
 	__be32 *p;
 
-	encode_bool(xdr, lock->fl.fl_type == F_RDLCK);
+	encode_bool(xdr, lock->fl.c.flc_type == F_RDLCK);
 	encode_int32(xdr, lock->svid);
 	encode_netobj(xdr, lock->oh.data, lock->oh.len);
 
@@ -270,7 +270,7 @@ static int decode_nlm4_holder(struct xdr_stream *xdr, struct nlm_res *result)
 		goto out_overflow;
 	exclusive = be32_to_cpup(p++);
 	lock->svid = be32_to_cpup(p);
-	fl->fl_pid = (pid_t)lock->svid;
+	fl->c.flc_pid = (pid_t)lock->svid;
 
 	error = decode_netobj(xdr, &lock->oh);
 	if (unlikely(error))
@@ -280,8 +280,8 @@ static int decode_nlm4_holder(struct xdr_stream *xdr, struct nlm_res *result)
 	if (unlikely(p == NULL))
 		goto out_overflow;
 
-	fl->fl_flags = FL_POSIX;
-	fl->fl_type  = exclusive != 0 ? F_WRLCK : F_RDLCK;
+	fl->c.flc_flags = FL_POSIX;
+	fl->c.flc_type  = exclusive != 0 ? F_WRLCK : F_RDLCK;
 	p = xdr_decode_hyper(p, &l_offset);
 	xdr_decode_hyper(p, &l_len);
 	nlm4svc_set_file_lock_range(fl, l_offset, l_len);
@@ -357,7 +357,7 @@ static void nlm4_xdr_enc_testargs(struct rpc_rqst *req,
 	const struct nlm_lock *lock = &args->lock;
 
 	encode_cookie(xdr, &args->cookie);
-	encode_bool(xdr, lock->fl.fl_type == F_WRLCK);
+	encode_bool(xdr, lock->fl.c.flc_type == F_WRLCK);
 	encode_nlm4_lock(xdr, lock);
 }
 
@@ -380,7 +380,7 @@ static void nlm4_xdr_enc_lockargs(struct rpc_rqst *req,
 
 	encode_cookie(xdr, &args->cookie);
 	encode_bool(xdr, args->block);
-	encode_bool(xdr, lock->fl.fl_type == F_WRLCK);
+	encode_bool(xdr, lock->fl.c.flc_type == F_WRLCK);
 	encode_nlm4_lock(xdr, lock);
 	encode_bool(xdr, args->reclaim);
 	encode_int32(xdr, args->state);
@@ -403,7 +403,7 @@ static void nlm4_xdr_enc_cancargs(struct rpc_rqst *req,
 
 	encode_cookie(xdr, &args->cookie);
 	encode_bool(xdr, args->block);
-	encode_bool(xdr, lock->fl.fl_type == F_WRLCK);
+	encode_bool(xdr, lock->fl.c.flc_type == F_WRLCK);
 	encode_nlm4_lock(xdr, lock);
 }
 
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index 5d85715be763..a7e0519ec024 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -185,7 +185,7 @@ __be32 nlmclnt_grant(const struct sockaddr *addr, const struct nlm_lock *lock)
 			continue;
 		if (!rpc_cmp_addr(nlm_addr(block->b_host), addr))
 			continue;
-		if (nfs_compare_fh(NFS_FH(file_inode(fl_blocked->fl_file)), fh) != 0)
+		if (nfs_compare_fh(NFS_FH(file_inode(fl_blocked->c.flc_file)), fh) != 0)
 			continue;
 		/* Alright, we found a lock. Set the return status
 		 * and wake up the caller
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index fba6c7fa7474..cebcc283b7ce 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -133,7 +133,8 @@ static void nlmclnt_setlockargs(struct nlm_rqst *req, struct file_lock *fl)
 	char *nodename = req->a_host->h_rpcclnt->cl_nodename;
 
 	nlmclnt_next_cookie(&argp->cookie);
-	memcpy(&lock->fh, NFS_FH(file_inode(fl->fl_file)), sizeof(struct nfs_fh));
+	memcpy(&lock->fh, NFS_FH(file_inode(fl->c.flc_file)),
+	       sizeof(struct nfs_fh));
 	lock->caller  = nodename;
 	lock->oh.data = req->a_owner;
 	lock->oh.len  = snprintf(req->a_owner, sizeof(req->a_owner), "%u@%s",
@@ -142,7 +143,7 @@ static void nlmclnt_setlockargs(struct nlm_rqst *req, struct file_lock *fl)
 	lock->svid = fl->fl_u.nfs_fl.owner->pid;
 	lock->fl.fl_start = fl->fl_start;
 	lock->fl.fl_end = fl->fl_end;
-	lock->fl.fl_type = fl->fl_type;
+	lock->fl.c.flc_type = fl->c.flc_type;
 }
 
 static void nlmclnt_release_lockargs(struct nlm_rqst *req)
@@ -182,7 +183,7 @@ int nlmclnt_proc(struct nlm_host *host, int cmd, struct file_lock *fl, void *dat
 	call->a_callback_data = data;
 
 	if (IS_SETLK(cmd) || IS_SETLKW(cmd)) {
-		if (fl->fl_type != F_UNLCK) {
+		if (fl->c.flc_type != F_UNLCK) {
 			call->a_args.block = IS_SETLKW(cmd) ? 1 : 0;
 			status = nlmclnt_lock(call, fl);
 		} else
@@ -432,13 +433,14 @@ nlmclnt_test(struct nlm_rqst *req, struct file_lock *fl)
 {
 	int	status;
 
-	status = nlmclnt_call(nfs_file_cred(fl->fl_file), req, NLMPROC_TEST);
+	status = nlmclnt_call(nfs_file_cred(fl->c.flc_file), req,
+			      NLMPROC_TEST);
 	if (status < 0)
 		goto out;
 
 	switch (req->a_res.status) {
 		case nlm_granted:
-			fl->fl_type = F_UNLCK;
+			fl->c.flc_type = F_UNLCK;
 			break;
 		case nlm_lck_denied:
 			/*
@@ -446,8 +448,8 @@ nlmclnt_test(struct nlm_rqst *req, struct file_lock *fl)
 			 */
 			fl->fl_start = req->a_res.lock.fl.fl_start;
 			fl->fl_end = req->a_res.lock.fl.fl_end;
-			fl->fl_type = req->a_res.lock.fl.fl_type;
-			fl->fl_pid = -req->a_res.lock.fl.fl_pid;
+			fl->c.flc_type = req->a_res.lock.fl.c.flc_type;
+			fl->c.flc_pid = -req->a_res.lock.fl.c.flc_pid;
 			break;
 		default:
 			status = nlm_stat_to_errno(req->a_res.status);
@@ -485,14 +487,15 @@ static const struct file_lock_operations nlmclnt_lock_ops = {
 static void nlmclnt_locks_init_private(struct file_lock *fl, struct nlm_host *host)
 {
 	fl->fl_u.nfs_fl.state = 0;
-	fl->fl_u.nfs_fl.owner = nlmclnt_find_lockowner(host, fl->fl_owner);
+	fl->fl_u.nfs_fl.owner = nlmclnt_find_lockowner(host,
+						       fl->c.flc_owner);
 	INIT_LIST_HEAD(&fl->fl_u.nfs_fl.list);
 	fl->fl_ops = &nlmclnt_lock_ops;
 }
 
 static int do_vfs_lock(struct file_lock *fl)
 {
-	return locks_lock_file_wait(fl->fl_file, fl);
+	return locks_lock_file_wait(fl->c.flc_file, fl);
 }
 
 /*
@@ -518,12 +521,12 @@ static int do_vfs_lock(struct file_lock *fl)
 static int
 nlmclnt_lock(struct nlm_rqst *req, struct file_lock *fl)
 {
-	const struct cred *cred = nfs_file_cred(fl->fl_file);
+	const struct cred *cred = nfs_file_cred(fl->c.flc_file);
 	struct nlm_host	*host = req->a_host;
 	struct nlm_res	*resp = &req->a_res;
 	struct nlm_wait block;
-	unsigned char fl_flags = fl->fl_flags;
-	unsigned char fl_type;
+	unsigned char flags = fl->c.flc_flags;
+	unsigned char type;
 	__be32 b_status;
 	int status = -ENOLCK;
 
@@ -531,9 +534,9 @@ nlmclnt_lock(struct nlm_rqst *req, struct file_lock *fl)
 		goto out;
 	req->a_args.state = nsm_local_state;
 
-	fl->fl_flags |= FL_ACCESS;
+	fl->c.flc_flags |= FL_ACCESS;
 	status = do_vfs_lock(fl);
-	fl->fl_flags = fl_flags;
+	fl->c.flc_flags = flags;
 	if (status < 0)
 		goto out;
 
@@ -591,11 +594,11 @@ again:
 			goto again;
 		}
 		/* Ensure the resulting lock will get added to granted list */
-		fl->fl_flags |= FL_SLEEP;
+		fl->c.flc_flags |= FL_SLEEP;
 		if (do_vfs_lock(fl) < 0)
 			printk(KERN_WARNING "%s: VFS is out of sync with lock manager!\n", __func__);
 		up_read(&host->h_rwsem);
-		fl->fl_flags = fl_flags;
+		fl->c.flc_flags = flags;
 		status = 0;
 	}
 	if (status < 0)
@@ -605,7 +608,7 @@ again:
 	 * cases NLM_LCK_DENIED is returned for a permanent error.  So
 	 * turn it into an ENOLCK.
 	 */
-	if (resp->status == nlm_lck_denied && (fl_flags & FL_SLEEP))
+	if (resp->status == nlm_lck_denied && (flags & FL_SLEEP))
 		status = -ENOLCK;
 	else
 		status = nlm_stat_to_errno(resp->status);
@@ -622,13 +625,13 @@ out_unlock:
 			   req->a_host->h_addrlen, req->a_res.status);
 	dprintk("lockd: lock attempt ended in fatal error.\n"
 		"       Attempting to unlock.\n");
-	fl_type = fl->fl_type;
-	fl->fl_type = F_UNLCK;
+	type = fl->c.flc_type;
+	fl->c.flc_type = F_UNLCK;
 	down_read(&host->h_rwsem);
 	do_vfs_lock(fl);
 	up_read(&host->h_rwsem);
-	fl->fl_type = fl_type;
-	fl->fl_flags = fl_flags;
+	fl->c.flc_type = type;
+	fl->c.flc_flags = flags;
 	nlmclnt_async_call(cred, req, NLMPROC_UNLOCK, &nlmclnt_unlock_ops);
 	return status;
 }
@@ -651,12 +654,14 @@ nlmclnt_reclaim(struct nlm_host *host, struct file_lock *fl,
 	nlmclnt_setlockargs(req, fl);
 	req->a_args.reclaim = 1;
 
-	status = nlmclnt_call(nfs_file_cred(fl->fl_file), req, NLMPROC_LOCK);
+	status = nlmclnt_call(nfs_file_cred(fl->c.flc_file), req,
+			      NLMPROC_LOCK);
 	if (status >= 0 && req->a_res.status == nlm_granted)
 		return 0;
 
 	printk(KERN_WARNING "lockd: failed to reclaim lock for pid %d "
-				"(errno %d, status %d)\n", fl->fl_pid,
+				"(errno %d, status %d)\n",
+				fl->c.flc_pid,
 				status, ntohl(req->a_res.status));
 
 	/*
@@ -683,26 +688,26 @@ nlmclnt_unlock(struct nlm_rqst *req, struct file_lock *fl)
 	struct nlm_host	*host = req->a_host;
 	struct nlm_res	*resp = &req->a_res;
 	int status;
-	unsigned char fl_flags = fl->fl_flags;
+	unsigned char flags = fl->c.flc_flags;
 
 	/*
 	 * Note: the server is supposed to either grant us the unlock
 	 * request, or to deny it with NLM_LCK_DENIED_GRACE_PERIOD. In either
 	 * case, we want to unlock.
 	 */
-	fl->fl_flags |= FL_EXISTS;
+	fl->c.flc_flags |= FL_EXISTS;
 	down_read(&host->h_rwsem);
 	status = do_vfs_lock(fl);
 	up_read(&host->h_rwsem);
-	fl->fl_flags = fl_flags;
+	fl->c.flc_flags = flags;
 	if (status == -ENOENT) {
 		status = 0;
 		goto out;
 	}
 
 	refcount_inc(&req->a_count);
-	status = nlmclnt_async_call(nfs_file_cred(fl->fl_file), req,
-			NLMPROC_UNLOCK, &nlmclnt_unlock_ops);
+	status = nlmclnt_async_call(nfs_file_cred(fl->c.flc_file), req,
+				    NLMPROC_UNLOCK, &nlmclnt_unlock_ops);
 	if (status < 0)
 		goto out;
 
@@ -795,8 +800,8 @@ static int nlmclnt_cancel(struct nlm_host *host, int block, struct file_lock *fl
 	req->a_args.block = block;
 
 	refcount_inc(&req->a_count);
-	status = nlmclnt_async_call(nfs_file_cred(fl->fl_file), req,
-			NLMPROC_CANCEL, &nlmclnt_cancel_ops);
+	status = nlmclnt_async_call(nfs_file_cred(fl->c.flc_file), req,
+				    NLMPROC_CANCEL, &nlmclnt_cancel_ops);
 	if (status == 0 && req->a_res.status == nlm_lck_denied)
 		status = -ENOLCK;
 	nlmclnt_release_call(req);
diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c
index 4df62f635529..a3e97278b997 100644
--- a/fs/lockd/clntxdr.c
+++ b/fs/lockd/clntxdr.c
@@ -238,7 +238,7 @@ static void encode_nlm_holder(struct xdr_stream *xdr,
 	u32 l_offset, l_len;
 	__be32 *p;
 
-	encode_bool(xdr, lock->fl.fl_type == F_RDLCK);
+	encode_bool(xdr, lock->fl.c.flc_type == F_RDLCK);
 	encode_int32(xdr, lock->svid);
 	encode_netobj(xdr, lock->oh.data, lock->oh.len);
 
@@ -265,7 +265,7 @@ static int decode_nlm_holder(struct xdr_stream *xdr, struct nlm_res *result)
 		goto out_overflow;
 	exclusive = be32_to_cpup(p++);
 	lock->svid = be32_to_cpup(p);
-	fl->fl_pid = (pid_t)lock->svid;
+	fl->c.flc_pid = (pid_t)lock->svid;
 
 	error = decode_netobj(xdr, &lock->oh);
 	if (unlikely(error))
@@ -275,8 +275,8 @@ static int decode_nlm_holder(struct xdr_stream *xdr, struct nlm_res *result)
 	if (unlikely(p == NULL))
 		goto out_overflow;
 
-	fl->fl_flags = FL_POSIX;
-	fl->fl_type  = exclusive != 0 ? F_WRLCK : F_RDLCK;
+	fl->c.flc_flags = FL_POSIX;
+	fl->c.flc_type  = exclusive != 0 ? F_WRLCK : F_RDLCK;
 	l_offset = be32_to_cpup(p++);
 	l_len = be32_to_cpup(p);
 	end = l_offset + l_len - 1;
@@ -357,7 +357,7 @@ static void nlm_xdr_enc_testargs(struct rpc_rqst *req,
 	const struct nlm_lock *lock = &args->lock;
 
 	encode_cookie(xdr, &args->cookie);
-	encode_bool(xdr, lock->fl.fl_type == F_WRLCK);
+	encode_bool(xdr, lock->fl.c.flc_type == F_WRLCK);
 	encode_nlm_lock(xdr, lock);
 }
 
@@ -380,7 +380,7 @@ static void nlm_xdr_enc_lockargs(struct rpc_rqst *req,
 
 	encode_cookie(xdr, &args->cookie);
 	encode_bool(xdr, args->block);
-	encode_bool(xdr, lock->fl.fl_type == F_WRLCK);
+	encode_bool(xdr, lock->fl.c.flc_type == F_WRLCK);
 	encode_nlm_lock(xdr, lock);
 	encode_bool(xdr, args->reclaim);
 	encode_int32(xdr, args->state);
@@ -403,7 +403,7 @@ static void nlm_xdr_enc_cancargs(struct rpc_rqst *req,
 
 	encode_cookie(xdr, &args->cookie);
 	encode_bool(xdr, args->block);
-	encode_bool(xdr, lock->fl.fl_type == F_WRLCK);
+	encode_bool(xdr, lock->fl.c.flc_type == F_WRLCK);
 	encode_nlm_lock(xdr, lock);
 }
 
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index b72023a6b4c1..8a72c418cdcc 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -52,16 +52,16 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
 		*filp = file;
 
 		/* Set up the missing parts of the file_lock structure */
-		lock->fl.fl_flags = FL_POSIX;
-		lock->fl.fl_file  = file->f_file[mode];
-		lock->fl.fl_pid = current->tgid;
+		lock->fl.c.flc_flags = FL_POSIX;
+		lock->fl.c.flc_file  = file->f_file[mode];
+		lock->fl.c.flc_pid = current->tgid;
 		lock->fl.fl_start = (loff_t)lock->lock_start;
 		lock->fl.fl_end = lock->lock_len ?
 				   (loff_t)(lock->lock_start + lock->lock_len - 1) :
 				   OFFSET_MAX;
 		lock->fl.fl_lmops = &nlmsvc_lock_operations;
 		nlmsvc_locks_init_private(&lock->fl, host, (pid_t)lock->svid);
-		if (!lock->fl.fl_owner) {
+		if (!lock->fl.c.flc_owner) {
 			/* lockowner allocation has failed */
 			nlmsvc_release_host(host);
 			return nlm_lck_denied_nolocks;
@@ -106,7 +106,7 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp)
 	if ((resp->status = nlm4svc_retrieve_args(rqstp, argp, &host, &file)))
 		return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
 
-	test_owner = argp->lock.fl.fl_owner;
+	test_owner = argp->lock.fl.c.flc_owner;
 	/* Now check for conflicting locks */
 	resp->status = nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock, &resp->cookie);
 	if (resp->status == nlm_drop_reply)
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index 2dc10900ad1c..1f2149db10f2 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -150,16 +150,17 @@ nlmsvc_lookup_block(struct nlm_file *file, struct nlm_lock *lock)
 	struct file_lock	*fl;
 
 	dprintk("lockd: nlmsvc_lookup_block f=%p pd=%d %Ld-%Ld ty=%d\n",
-				file, lock->fl.fl_pid,
+				file, lock->fl.c.flc_pid,
 				(long long)lock->fl.fl_start,
-				(long long)lock->fl.fl_end, lock->fl.fl_type);
+				(long long)lock->fl.fl_end,
+				lock->fl.c.flc_type);
 	spin_lock(&nlm_blocked_lock);
 	list_for_each_entry(block, &nlm_blocked, b_list) {
 		fl = &block->b_call->a_args.lock.fl;
 		dprintk("lockd: check f=%p pd=%d %Ld-%Ld ty=%d cookie=%s\n",
-				block->b_file, fl->fl_pid,
+				block->b_file, fl->c.flc_pid,
 				(long long)fl->fl_start,
-				(long long)fl->fl_end, fl->fl_type,
+				(long long)fl->fl_end, fl->c.flc_type,
 				nlmdbg_cookie2a(&block->b_call->a_args.cookie));
 		if (block->b_file == file && nlm_compare_locks(fl, &lock->fl)) {
 			kref_get(&block->b_count);
@@ -244,7 +245,7 @@ nlmsvc_create_block(struct svc_rqst *rqstp, struct nlm_host *host,
 		goto failed_free;
 
 	/* Set notifier function for VFS, and init args */
-	call->a_args.lock.fl.fl_flags |= FL_SLEEP;
+	call->a_args.lock.fl.c.flc_flags |= FL_SLEEP;
 	call->a_args.lock.fl.fl_lmops = &nlmsvc_lock_operations;
 	nlmclnt_next_cookie(&call->a_args.cookie);
 
@@ -402,14 +403,14 @@ static struct nlm_lockowner *nlmsvc_find_lockowner(struct nlm_host *host, pid_t
 void
 nlmsvc_release_lockowner(struct nlm_lock *lock)
 {
-	if (lock->fl.fl_owner)
-		nlmsvc_put_lockowner(lock->fl.fl_owner);
+	if (lock->fl.c.flc_owner)
+		nlmsvc_put_lockowner(lock->fl.c.flc_owner);
 }
 
 void nlmsvc_locks_init_private(struct file_lock *fl, struct nlm_host *host,
 						pid_t pid)
 {
-	fl->fl_owner = nlmsvc_find_lockowner(host, pid);
+	fl->c.flc_owner = nlmsvc_find_lockowner(host, pid);
 }
 
 /*
@@ -425,7 +426,7 @@ static int nlmsvc_setgrantargs(struct nlm_rqst *call, struct nlm_lock *lock)
 
 	/* set default data area */
 	call->a_args.lock.oh.data = call->a_owner;
-	call->a_args.lock.svid = ((struct nlm_lockowner *)lock->fl.fl_owner)->pid;
+	call->a_args.lock.svid = ((struct nlm_lockowner *) lock->fl.c.flc_owner)->pid;
 
 	if (lock->oh.len > NLMCLNT_OHSIZE) {
 		void *data = kmalloc(lock->oh.len, GFP_KERNEL);
@@ -489,7 +490,8 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 
 	dprintk("lockd: nlmsvc_lock(%s/%ld, ty=%d, pi=%d, %Ld-%Ld, bl=%d)\n",
 				inode->i_sb->s_id, inode->i_ino,
-				lock->fl.fl_type, lock->fl.fl_pid,
+				lock->fl.c.flc_type,
+				lock->fl.c.flc_pid,
 				(long long)lock->fl.fl_start,
 				(long long)lock->fl.fl_end,
 				wait);
@@ -512,7 +514,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 			goto out;
 		lock = &block->b_call->a_args.lock;
 	} else
-		lock->fl.fl_flags &= ~FL_SLEEP;
+		lock->fl.c.flc_flags &= ~FL_SLEEP;
 
 	if (block->b_flags & B_QUEUED) {
 		dprintk("lockd: nlmsvc_lock deferred block %p flags %d\n",
@@ -560,10 +562,10 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 	spin_unlock(&nlm_blocked_lock);
 
 	if (!wait)
-		lock->fl.fl_flags &= ~FL_SLEEP;
+		lock->fl.c.flc_flags &= ~FL_SLEEP;
 	mode = lock_to_openmode(&lock->fl);
 	error = vfs_lock_file(file->f_file[mode], F_SETLK, &lock->fl, NULL);
-	lock->fl.fl_flags &= ~FL_SLEEP;
+	lock->fl.c.flc_flags &= ~FL_SLEEP;
 
 	dprintk("lockd: vfs_lock_file returned %d\n", error);
 	switch (error) {
@@ -616,7 +618,7 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
 	dprintk("lockd: nlmsvc_testlock(%s/%ld, ty=%d, %Ld-%Ld)\n",
 				nlmsvc_file_inode(file)->i_sb->s_id,
 				nlmsvc_file_inode(file)->i_ino,
-				lock->fl.fl_type,
+				lock->fl.c.flc_type,
 				(long long)lock->fl.fl_start,
 				(long long)lock->fl.fl_end);
 
@@ -636,19 +638,19 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
 		goto out;
 	}
 
-	if (lock->fl.fl_type == F_UNLCK) {
+	if (lock->fl.c.flc_type == F_UNLCK) {
 		ret = nlm_granted;
 		goto out;
 	}
 
 	dprintk("lockd: conflicting lock(ty=%d, %Ld-%Ld)\n",
-		lock->fl.fl_type, (long long)lock->fl.fl_start,
+		lock->fl.c.flc_type, (long long)lock->fl.fl_start,
 		(long long)lock->fl.fl_end);
 	conflock->caller = "somehost";	/* FIXME */
 	conflock->len = strlen(conflock->caller);
 	conflock->oh.len = 0;		/* don't return OH info */
-	conflock->svid = lock->fl.fl_pid;
-	conflock->fl.fl_type = lock->fl.fl_type;
+	conflock->svid = lock->fl.c.flc_pid;
+	conflock->fl.c.flc_type = lock->fl.c.flc_type;
 	conflock->fl.fl_start = lock->fl.fl_start;
 	conflock->fl.fl_end = lock->fl.fl_end;
 	locks_release_private(&lock->fl);
@@ -673,21 +675,21 @@ nlmsvc_unlock(struct net *net, struct nlm_file *file, struct nlm_lock *lock)
 	dprintk("lockd: nlmsvc_unlock(%s/%ld, pi=%d, %Ld-%Ld)\n",
 				nlmsvc_file_inode(file)->i_sb->s_id,
 				nlmsvc_file_inode(file)->i_ino,
-				lock->fl.fl_pid,
+				lock->fl.c.flc_pid,
 				(long long)lock->fl.fl_start,
 				(long long)lock->fl.fl_end);
 
 	/* First, cancel any lock that might be there */
 	nlmsvc_cancel_blocked(net, file, lock);
 
-	lock->fl.fl_type = F_UNLCK;
-	lock->fl.fl_file = file->f_file[O_RDONLY];
-	if (lock->fl.fl_file)
-		error = vfs_lock_file(lock->fl.fl_file, F_SETLK,
+	lock->fl.c.flc_type = F_UNLCK;
+	lock->fl.c.flc_file = file->f_file[O_RDONLY];
+	if (lock->fl.c.flc_file)
+		error = vfs_lock_file(lock->fl.c.flc_file, F_SETLK,
 					&lock->fl, NULL);
-	lock->fl.fl_file = file->f_file[O_WRONLY];
-	if (lock->fl.fl_file)
-		error |= vfs_lock_file(lock->fl.fl_file, F_SETLK,
+	lock->fl.c.flc_file = file->f_file[O_WRONLY];
+	if (lock->fl.c.flc_file)
+		error |= vfs_lock_file(lock->fl.c.flc_file, F_SETLK,
 					&lock->fl, NULL);
 
 	return (error < 0)? nlm_lck_denied_nolocks : nlm_granted;
@@ -710,7 +712,7 @@ nlmsvc_cancel_blocked(struct net *net, struct nlm_file *file, struct nlm_lock *l
 	dprintk("lockd: nlmsvc_cancel(%s/%ld, pi=%d, %Ld-%Ld)\n",
 				nlmsvc_file_inode(file)->i_sb->s_id,
 				nlmsvc_file_inode(file)->i_ino,
-				lock->fl.fl_pid,
+				lock->fl.c.flc_pid,
 				(long long)lock->fl.fl_start,
 				(long long)lock->fl.fl_end);
 
@@ -863,12 +865,12 @@ nlmsvc_grant_blocked(struct nlm_block *block)
 	/* vfs_lock_file() can mangle fl_start and fl_end, but we need
 	 * them unchanged for the GRANT_MSG
 	 */
-	lock->fl.fl_flags |= FL_SLEEP;
+	lock->fl.c.flc_flags |= FL_SLEEP;
 	fl_start = lock->fl.fl_start;
 	fl_end = lock->fl.fl_end;
 	mode = lock_to_openmode(&lock->fl);
 	error = vfs_lock_file(file->f_file[mode], F_SETLK, &lock->fl, NULL);
-	lock->fl.fl_flags &= ~FL_SLEEP;
+	lock->fl.c.flc_flags &= ~FL_SLEEP;
 	lock->fl.fl_start = fl_start;
 	lock->fl.fl_end = fl_end;
 
@@ -993,8 +995,8 @@ nlmsvc_grant_reply(struct nlm_cookie *cookie, __be32 status)
 		/* Client doesn't want it, just unlock it */
 		nlmsvc_unlink_block(block);
 		fl = &block->b_call->a_args.lock.fl;
-		fl->fl_type = F_UNLCK;
-		error = vfs_lock_file(fl->fl_file, F_SETLK, fl, NULL);
+		fl->c.flc_type = F_UNLCK;
+		error = vfs_lock_file(fl->c.flc_file, F_SETLK, fl, NULL);
 		if (error)
 			pr_warn("lockd: unable to unlock lock rejected by client!\n");
 		break;
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 32784f508c81..a03220e66ce0 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -77,12 +77,12 @@ nlmsvc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
 
 		/* Set up the missing parts of the file_lock structure */
 		mode = lock_to_openmode(&lock->fl);
-		lock->fl.fl_flags = FL_POSIX;
-		lock->fl.fl_file  = file->f_file[mode];
-		lock->fl.fl_pid = current->tgid;
+		lock->fl.c.flc_flags = FL_POSIX;
+		lock->fl.c.flc_file  = file->f_file[mode];
+		lock->fl.c.flc_pid = current->tgid;
 		lock->fl.fl_lmops = &nlmsvc_lock_operations;
 		nlmsvc_locks_init_private(&lock->fl, host, (pid_t)lock->svid);
-		if (!lock->fl.fl_owner) {
+		if (!lock->fl.c.flc_owner) {
 			/* lockowner allocation has failed */
 			nlmsvc_release_host(host);
 			return nlm_lck_denied_nolocks;
@@ -127,7 +127,7 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp)
 	if ((resp->status = nlmsvc_retrieve_args(rqstp, argp, &host, &file)))
 		return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
 
-	test_owner = argp->lock.fl.fl_owner;
+	test_owner = argp->lock.fl.c.flc_owner;
 
 	/* Now check for conflicting locks */
 	resp->status = cast_status(nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock, &resp->cookie));
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index e3b6229e7ae5..9103896164f6 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -73,7 +73,7 @@ static inline unsigned int file_hash(struct nfs_fh *f)
 
 int lock_to_openmode(struct file_lock *lock)
 {
-	return (lock->fl_type == F_WRLCK) ? O_WRONLY : O_RDONLY;
+	return lock_is_write(lock) ? O_WRONLY : O_RDONLY;
 }
 
 /*
@@ -181,18 +181,18 @@ static int nlm_unlock_files(struct nlm_file *file, const struct file_lock *fl)
 	struct file_lock lock;
 
 	locks_init_lock(&lock);
-	lock.fl_type  = F_UNLCK;
+	lock.c.flc_type  = F_UNLCK;
 	lock.fl_start = 0;
 	lock.fl_end   = OFFSET_MAX;
-	lock.fl_owner = fl->fl_owner;
-	lock.fl_pid   = fl->fl_pid;
-	lock.fl_flags = FL_POSIX;
+	lock.c.flc_owner = fl->c.flc_owner;
+	lock.c.flc_pid   = fl->c.flc_pid;
+	lock.c.flc_flags = FL_POSIX;
 
-	lock.fl_file = file->f_file[O_RDONLY];
-	if (lock.fl_file && vfs_lock_file(lock.fl_file, F_SETLK, &lock, NULL))
+	lock.c.flc_file = file->f_file[O_RDONLY];
+	if (lock.c.flc_file && vfs_lock_file(lock.c.flc_file, F_SETLK, &lock, NULL))
 		goto out_err;
-	lock.fl_file = file->f_file[O_WRONLY];
-	if (lock.fl_file && vfs_lock_file(lock.fl_file, F_SETLK, &lock, NULL))
+	lock.c.flc_file = file->f_file[O_WRONLY];
+	if (lock.c.flc_file && vfs_lock_file(lock.c.flc_file, F_SETLK, &lock, NULL))
 		goto out_err;
 	return 0;
 out_err:
@@ -218,14 +218,14 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file,
 again:
 	file->f_locks = 0;
 	spin_lock(&flctx->flc_lock);
-	list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
+	for_each_file_lock(fl, &flctx->flc_posix) {
 		if (fl->fl_lmops != &nlmsvc_lock_operations)
 			continue;
 
 		/* update current lock count */
 		file->f_locks++;
 
-		lockhost = ((struct nlm_lockowner *)fl->fl_owner)->host;
+		lockhost = ((struct nlm_lockowner *) fl->c.flc_owner)->host;
 		if (match(lockhost, host)) {
 
 			spin_unlock(&flctx->flc_lock);
@@ -272,7 +272,7 @@ nlm_file_inuse(struct nlm_file *file)
 
 	if (flctx && !list_empty_careful(&flctx->flc_posix)) {
 		spin_lock(&flctx->flc_lock);
-		list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
+		for_each_file_lock(fl, &flctx->flc_posix) {
 			if (fl->fl_lmops == &nlmsvc_lock_operations) {
 				spin_unlock(&flctx->flc_lock);
 				return 1;
diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c
index 2fb5748dae0c..adfcce2bf11b 100644
--- a/fs/lockd/xdr.c
+++ b/fs/lockd/xdr.c
@@ -88,8 +88,8 @@ svcxdr_decode_lock(struct xdr_stream *xdr, struct nlm_lock *lock)
 		return false;
 
 	locks_init_lock(fl);
-	fl->fl_flags = FL_POSIX;
-	fl->fl_type  = F_RDLCK;
+	fl->c.flc_flags = FL_POSIX;
+	fl->c.flc_type  = F_RDLCK;
 	end = start + len - 1;
 	fl->fl_start = s32_to_loff_t(start);
 	if (len == 0 || end < 0)
@@ -107,7 +107,7 @@ svcxdr_encode_holder(struct xdr_stream *xdr, const struct nlm_lock *lock)
 	s32 start, len;
 
 	/* exclusive */
-	if (xdr_stream_encode_bool(xdr, fl->fl_type != F_RDLCK) < 0)
+	if (xdr_stream_encode_bool(xdr, fl->c.flc_type != F_RDLCK) < 0)
 		return false;
 	if (xdr_stream_encode_u32(xdr, lock->svid) < 0)
 		return false;
@@ -164,7 +164,7 @@ nlmsvc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 	if (!svcxdr_decode_lock(xdr, &argp->lock))
 		return false;
 	if (exclusive)
-		argp->lock.fl.fl_type = F_WRLCK;
+		argp->lock.fl.c.flc_type = F_WRLCK;
 
 	return true;
 }
@@ -184,7 +184,7 @@ nlmsvc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 	if (!svcxdr_decode_lock(xdr, &argp->lock))
 		return false;
 	if (exclusive)
-		argp->lock.fl.fl_type = F_WRLCK;
+		argp->lock.fl.c.flc_type = F_WRLCK;
 	if (xdr_stream_decode_bool(xdr, &argp->reclaim) < 0)
 		return false;
 	if (xdr_stream_decode_u32(xdr, &argp->state) < 0)
@@ -209,7 +209,7 @@ nlmsvc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 	if (!svcxdr_decode_lock(xdr, &argp->lock))
 		return false;
 	if (exclusive)
-		argp->lock.fl.fl_type = F_WRLCK;
+		argp->lock.fl.c.flc_type = F_WRLCK;
 
 	return true;
 }
@@ -223,7 +223,7 @@ nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 		return false;
 	if (!svcxdr_decode_lock(xdr, &argp->lock))
 		return false;
-	argp->lock.fl.fl_type = F_UNLCK;
+	argp->lock.fl.c.flc_type = F_UNLCK;
 
 	return true;
 }
diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c
index 5fcbf30cd275..3d28b9c3ed15 100644
--- a/fs/lockd/xdr4.c
+++ b/fs/lockd/xdr4.c
@@ -89,8 +89,8 @@ svcxdr_decode_lock(struct xdr_stream *xdr, struct nlm_lock *lock)
 		return false;
 
 	locks_init_lock(fl);
-	fl->fl_flags = FL_POSIX;
-	fl->fl_type  = F_RDLCK;
+	fl->c.flc_flags = FL_POSIX;
+	fl->c.flc_type  = F_RDLCK;
 	nlm4svc_set_file_lock_range(fl, lock->lock_start, lock->lock_len);
 	return true;
 }
@@ -102,7 +102,7 @@ svcxdr_encode_holder(struct xdr_stream *xdr, const struct nlm_lock *lock)
 	s64 start, len;
 
 	/* exclusive */
-	if (xdr_stream_encode_bool(xdr, fl->fl_type != F_RDLCK) < 0)
+	if (xdr_stream_encode_bool(xdr, fl->c.flc_type != F_RDLCK) < 0)
 		return false;
 	if (xdr_stream_encode_u32(xdr, lock->svid) < 0)
 		return false;
@@ -159,7 +159,7 @@ nlm4svc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 	if (!svcxdr_decode_lock(xdr, &argp->lock))
 		return false;
 	if (exclusive)
-		argp->lock.fl.fl_type = F_WRLCK;
+		argp->lock.fl.c.flc_type = F_WRLCK;
 
 	return true;
 }
@@ -179,7 +179,7 @@ nlm4svc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 	if (!svcxdr_decode_lock(xdr, &argp->lock))
 		return false;
 	if (exclusive)
-		argp->lock.fl.fl_type = F_WRLCK;
+		argp->lock.fl.c.flc_type = F_WRLCK;
 	if (xdr_stream_decode_bool(xdr, &argp->reclaim) < 0)
 		return false;
 	if (xdr_stream_decode_u32(xdr, &argp->state) < 0)
@@ -204,7 +204,7 @@ nlm4svc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 	if (!svcxdr_decode_lock(xdr, &argp->lock))
 		return false;
 	if (exclusive)
-		argp->lock.fl.fl_type = F_WRLCK;
+		argp->lock.fl.c.flc_type = F_WRLCK;
 
 	return true;
 }
@@ -218,7 +218,7 @@ nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 		return false;
 	if (!svcxdr_decode_lock(xdr, &argp->lock))
 		return false;
-	argp->lock.fl.fl_type = F_UNLCK;
+	argp->lock.fl.c.flc_type = F_UNLCK;
 
 	return true;
 }
diff --git a/fs/locks.c b/fs/locks.c
index cc7c117ee192..90c8746874de 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -48,7 +48,6 @@
  * children.
  *
  */
-
 #include <linux/capability.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
@@ -70,24 +69,28 @@
 
 #include <linux/uaccess.h>
 
-#define IS_POSIX(fl)	(fl->fl_flags & FL_POSIX)
-#define IS_FLOCK(fl)	(fl->fl_flags & FL_FLOCK)
-#define IS_LEASE(fl)	(fl->fl_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT))
-#define IS_OFDLCK(fl)	(fl->fl_flags & FL_OFDLCK)
-#define IS_REMOTELCK(fl)	(fl->fl_pid <= 0)
+static struct file_lock *file_lock(struct file_lock_core *flc)
+{
+	return container_of(flc, struct file_lock, c);
+}
+
+static struct file_lease *file_lease(struct file_lock_core *flc)
+{
+	return container_of(flc, struct file_lease, c);
+}
 
-static bool lease_breaking(struct file_lock *fl)
+static bool lease_breaking(struct file_lease *fl)
 {
-	return fl->fl_flags & (FL_UNLOCK_PENDING | FL_DOWNGRADE_PENDING);
+	return fl->c.flc_flags & (FL_UNLOCK_PENDING | FL_DOWNGRADE_PENDING);
 }
 
-static int target_leasetype(struct file_lock *fl)
+static int target_leasetype(struct file_lease *fl)
 {
-	if (fl->fl_flags & FL_UNLOCK_PENDING)
+	if (fl->c.flc_flags & FL_UNLOCK_PENDING)
 		return F_UNLCK;
-	if (fl->fl_flags & FL_DOWNGRADE_PENDING)
+	if (fl->c.flc_flags & FL_DOWNGRADE_PENDING)
 		return F_RDLCK;
-	return fl->fl_type;
+	return fl->c.flc_type;
 }
 
 static int leases_enable = 1;
@@ -168,6 +171,7 @@ static DEFINE_SPINLOCK(blocked_lock_lock);
 
 static struct kmem_cache *flctx_cache __ro_after_init;
 static struct kmem_cache *filelock_cache __ro_after_init;
+static struct kmem_cache *filelease_cache __ro_after_init;
 
 static struct file_lock_context *
 locks_get_lock_context(struct inode *inode, int type)
@@ -204,11 +208,12 @@ out:
 static void
 locks_dump_ctx_list(struct list_head *list, char *list_type)
 {
-	struct file_lock *fl;
+	struct file_lock_core *flc;
 
-	list_for_each_entry(fl, list, fl_list) {
-		pr_warn("%s: fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", list_type, fl->fl_owner, fl->fl_flags, fl->fl_type, fl->fl_pid);
-	}
+	list_for_each_entry(flc, list, flc_list)
+		pr_warn("%s: fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n",
+			list_type, flc->flc_owner, flc->flc_flags,
+			flc->flc_type, flc->flc_pid);
 }
 
 static void
@@ -229,19 +234,19 @@ locks_check_ctx_lists(struct inode *inode)
 }
 
 static void
-locks_check_ctx_file_list(struct file *filp, struct list_head *list,
-				char *list_type)
+locks_check_ctx_file_list(struct file *filp, struct list_head *list, char *list_type)
 {
-	struct file_lock *fl;
+	struct file_lock_core *flc;
 	struct inode *inode = file_inode(filp);
 
-	list_for_each_entry(fl, list, fl_list)
-		if (fl->fl_file == filp)
+	list_for_each_entry(flc, list, flc_list)
+		if (flc->flc_file == filp)
 			pr_warn("Leaked %s lock on dev=0x%x:0x%x ino=0x%lx "
 				" fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n",
 				list_type, MAJOR(inode->i_sb->s_dev),
 				MINOR(inode->i_sb->s_dev), inode->i_ino,
-				fl->fl_owner, fl->fl_flags, fl->fl_type, fl->fl_pid);
+				flc->flc_owner, flc->flc_flags,
+				flc->flc_type, flc->flc_pid);
 }
 
 void
@@ -255,13 +260,13 @@ locks_free_lock_context(struct inode *inode)
 	}
 }
 
-static void locks_init_lock_heads(struct file_lock *fl)
+static void locks_init_lock_heads(struct file_lock_core *flc)
 {
-	INIT_HLIST_NODE(&fl->fl_link);
-	INIT_LIST_HEAD(&fl->fl_list);
-	INIT_LIST_HEAD(&fl->fl_blocked_requests);
-	INIT_LIST_HEAD(&fl->fl_blocked_member);
-	init_waitqueue_head(&fl->fl_wait);
+	INIT_HLIST_NODE(&flc->flc_link);
+	INIT_LIST_HEAD(&flc->flc_list);
+	INIT_LIST_HEAD(&flc->flc_blocked_requests);
+	INIT_LIST_HEAD(&flc->flc_blocked_member);
+	init_waitqueue_head(&flc->flc_wait);
 }
 
 /* Allocate an empty lock structure. */
@@ -270,19 +275,33 @@ struct file_lock *locks_alloc_lock(void)
 	struct file_lock *fl = kmem_cache_zalloc(filelock_cache, GFP_KERNEL);
 
 	if (fl)
-		locks_init_lock_heads(fl);
+		locks_init_lock_heads(&fl->c);
 
 	return fl;
 }
 EXPORT_SYMBOL_GPL(locks_alloc_lock);
 
+/* Allocate an empty lock structure. */
+struct file_lease *locks_alloc_lease(void)
+{
+	struct file_lease *fl = kmem_cache_zalloc(filelease_cache, GFP_KERNEL);
+
+	if (fl)
+		locks_init_lock_heads(&fl->c);
+
+	return fl;
+}
+EXPORT_SYMBOL_GPL(locks_alloc_lease);
+
 void locks_release_private(struct file_lock *fl)
 {
-	BUG_ON(waitqueue_active(&fl->fl_wait));
-	BUG_ON(!list_empty(&fl->fl_list));
-	BUG_ON(!list_empty(&fl->fl_blocked_requests));
-	BUG_ON(!list_empty(&fl->fl_blocked_member));
-	BUG_ON(!hlist_unhashed(&fl->fl_link));
+	struct file_lock_core *flc = &fl->c;
+
+	BUG_ON(waitqueue_active(&flc->flc_wait));
+	BUG_ON(!list_empty(&flc->flc_list));
+	BUG_ON(!list_empty(&flc->flc_blocked_requests));
+	BUG_ON(!list_empty(&flc->flc_blocked_member));
+	BUG_ON(!hlist_unhashed(&flc->flc_link));
 
 	if (fl->fl_ops) {
 		if (fl->fl_ops->fl_release_private)
@@ -292,8 +311,8 @@ void locks_release_private(struct file_lock *fl)
 
 	if (fl->fl_lmops) {
 		if (fl->fl_lmops->lm_put_owner) {
-			fl->fl_lmops->lm_put_owner(fl->fl_owner);
-			fl->fl_owner = NULL;
+			fl->fl_lmops->lm_put_owner(flc->flc_owner);
+			flc->flc_owner = NULL;
 		}
 		fl->fl_lmops = NULL;
 	}
@@ -309,16 +328,15 @@ EXPORT_SYMBOL_GPL(locks_release_private);
  *   %true: @owner has at least one blocker
  *   %false: @owner has no blockers
  */
-bool locks_owner_has_blockers(struct file_lock_context *flctx,
-		fl_owner_t owner)
+bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner)
 {
-	struct file_lock *fl;
+	struct file_lock_core *flc;
 
 	spin_lock(&flctx->flc_lock);
-	list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
-		if (fl->fl_owner != owner)
+	list_for_each_entry(flc, &flctx->flc_posix, flc_list) {
+		if (flc->flc_owner != owner)
 			continue;
-		if (!list_empty(&fl->fl_blocked_requests)) {
+		if (!list_empty(&flc->flc_blocked_requests)) {
 			spin_unlock(&flctx->flc_lock);
 			return true;
 		}
@@ -336,35 +354,52 @@ void locks_free_lock(struct file_lock *fl)
 }
 EXPORT_SYMBOL(locks_free_lock);
 
+/* Free a lease which is not in use. */
+void locks_free_lease(struct file_lease *fl)
+{
+	kmem_cache_free(filelease_cache, fl);
+}
+EXPORT_SYMBOL(locks_free_lease);
+
 static void
 locks_dispose_list(struct list_head *dispose)
 {
-	struct file_lock *fl;
+	struct file_lock_core *flc;
 
 	while (!list_empty(dispose)) {
-		fl = list_first_entry(dispose, struct file_lock, fl_list);
-		list_del_init(&fl->fl_list);
-		locks_free_lock(fl);
+		flc = list_first_entry(dispose, struct file_lock_core, flc_list);
+		list_del_init(&flc->flc_list);
+		if (flc->flc_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT))
+			locks_free_lease(file_lease(flc));
+		else
+			locks_free_lock(file_lock(flc));
 	}
 }
 
 void locks_init_lock(struct file_lock *fl)
 {
 	memset(fl, 0, sizeof(struct file_lock));
-	locks_init_lock_heads(fl);
+	locks_init_lock_heads(&fl->c);
 }
 EXPORT_SYMBOL(locks_init_lock);
 
+void locks_init_lease(struct file_lease *fl)
+{
+	memset(fl, 0, sizeof(*fl));
+	locks_init_lock_heads(&fl->c);
+}
+EXPORT_SYMBOL(locks_init_lease);
+
 /*
  * Initialize a new lock from an existing file_lock structure.
  */
 void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
 {
-	new->fl_owner = fl->fl_owner;
-	new->fl_pid = fl->fl_pid;
-	new->fl_file = NULL;
-	new->fl_flags = fl->fl_flags;
-	new->fl_type = fl->fl_type;
+	new->c.flc_owner = fl->c.flc_owner;
+	new->c.flc_pid = fl->c.flc_pid;
+	new->c.flc_file = NULL;
+	new->c.flc_flags = fl->c.flc_flags;
+	new->c.flc_type = fl->c.flc_type;
 	new->fl_start = fl->fl_start;
 	new->fl_end = fl->fl_end;
 	new->fl_lmops = fl->fl_lmops;
@@ -372,7 +407,7 @@ void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
 
 	if (fl->fl_lmops) {
 		if (fl->fl_lmops->lm_get_owner)
-			fl->fl_lmops->lm_get_owner(fl->fl_owner);
+			fl->fl_lmops->lm_get_owner(fl->c.flc_owner);
 	}
 }
 EXPORT_SYMBOL(locks_copy_conflock);
@@ -384,7 +419,7 @@ void locks_copy_lock(struct file_lock *new, struct file_lock *fl)
 
 	locks_copy_conflock(new, fl);
 
-	new->fl_file = fl->fl_file;
+	new->c.flc_file = fl->c.flc_file;
 	new->fl_ops = fl->fl_ops;
 
 	if (fl->fl_ops) {
@@ -400,15 +435,17 @@ static void locks_move_blocks(struct file_lock *new, struct file_lock *fl)
 
 	/*
 	 * As ctx->flc_lock is held, new requests cannot be added to
-	 * ->fl_blocked_requests, so we don't need a lock to check if it
+	 * ->flc_blocked_requests, so we don't need a lock to check if it
 	 * is empty.
 	 */
-	if (list_empty(&fl->fl_blocked_requests))
+	if (list_empty(&fl->c.flc_blocked_requests))
 		return;
 	spin_lock(&blocked_lock_lock);
-	list_splice_init(&fl->fl_blocked_requests, &new->fl_blocked_requests);
-	list_for_each_entry(f, &new->fl_blocked_requests, fl_blocked_member)
-		f->fl_blocker = new;
+	list_splice_init(&fl->c.flc_blocked_requests,
+			 &new->c.flc_blocked_requests);
+	list_for_each_entry(f, &new->c.flc_blocked_requests,
+			    c.flc_blocked_member)
+		f->c.flc_blocker = &new->c;
 	spin_unlock(&blocked_lock_lock);
 }
 
@@ -429,21 +466,21 @@ static void flock_make_lock(struct file *filp, struct file_lock *fl, int type)
 {
 	locks_init_lock(fl);
 
-	fl->fl_file = filp;
-	fl->fl_owner = filp;
-	fl->fl_pid = current->tgid;
-	fl->fl_flags = FL_FLOCK;
-	fl->fl_type = type;
+	fl->c.flc_file = filp;
+	fl->c.flc_owner = filp;
+	fl->c.flc_pid = current->tgid;
+	fl->c.flc_flags = FL_FLOCK;
+	fl->c.flc_type = type;
 	fl->fl_end = OFFSET_MAX;
 }
 
-static int assign_type(struct file_lock *fl, int type)
+static int assign_type(struct file_lock_core *flc, int type)
 {
 	switch (type) {
 	case F_RDLCK:
 	case F_WRLCK:
 	case F_UNLCK:
-		fl->fl_type = type;
+		flc->flc_type = type;
 		break;
 	default:
 		return -EINVAL;
@@ -488,14 +525,14 @@ static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl,
 	} else
 		fl->fl_end = OFFSET_MAX;
 
-	fl->fl_owner = current->files;
-	fl->fl_pid = current->tgid;
-	fl->fl_file = filp;
-	fl->fl_flags = FL_POSIX;
+	fl->c.flc_owner = current->files;
+	fl->c.flc_pid = current->tgid;
+	fl->c.flc_file = filp;
+	fl->c.flc_flags = FL_POSIX;
 	fl->fl_ops = NULL;
 	fl->fl_lmops = NULL;
 
-	return assign_type(fl, l->l_type);
+	return assign_type(&fl->c, l->l_type);
 }
 
 /* Verify a "struct flock" and copy it to a "struct file_lock" as a POSIX
@@ -516,16 +553,16 @@ static int flock_to_posix_lock(struct file *filp, struct file_lock *fl,
 
 /* default lease lock manager operations */
 static bool
-lease_break_callback(struct file_lock *fl)
+lease_break_callback(struct file_lease *fl)
 {
 	kill_fasync(&fl->fl_fasync, SIGIO, POLL_MSG);
 	return false;
 }
 
 static void
-lease_setup(struct file_lock *fl, void **priv)
+lease_setup(struct file_lease *fl, void **priv)
 {
-	struct file *filp = fl->fl_file;
+	struct file *filp = fl->c.flc_file;
 	struct fasync_struct *fa = *priv;
 
 	/*
@@ -539,7 +576,7 @@ lease_setup(struct file_lock *fl, void **priv)
 	__f_setown(filp, task_pid(current), PIDTYPE_TGID, 0);
 }
 
-static const struct lock_manager_operations lease_manager_ops = {
+static const struct lease_manager_operations lease_manager_ops = {
 	.lm_break = lease_break_callback,
 	.lm_change = lease_modify,
 	.lm_setup = lease_setup,
@@ -548,27 +585,24 @@ static const struct lock_manager_operations lease_manager_ops = {
 /*
  * Initialize a lease, use the default lock manager operations
  */
-static int lease_init(struct file *filp, int type, struct file_lock *fl)
+static int lease_init(struct file *filp, int type, struct file_lease *fl)
 {
-	if (assign_type(fl, type) != 0)
+	if (assign_type(&fl->c, type) != 0)
 		return -EINVAL;
 
-	fl->fl_owner = filp;
-	fl->fl_pid = current->tgid;
+	fl->c.flc_owner = filp;
+	fl->c.flc_pid = current->tgid;
 
-	fl->fl_file = filp;
-	fl->fl_flags = FL_LEASE;
-	fl->fl_start = 0;
-	fl->fl_end = OFFSET_MAX;
-	fl->fl_ops = NULL;
+	fl->c.flc_file = filp;
+	fl->c.flc_flags = FL_LEASE;
 	fl->fl_lmops = &lease_manager_ops;
 	return 0;
 }
 
 /* Allocate a file_lock initialised to this type of lease */
-static struct file_lock *lease_alloc(struct file *filp, int type)
+static struct file_lease *lease_alloc(struct file *filp, int type)
 {
-	struct file_lock *fl = locks_alloc_lock();
+	struct file_lease *fl = locks_alloc_lease();
 	int error = -ENOMEM;
 
 	if (fl == NULL)
@@ -576,7 +610,7 @@ static struct file_lock *lease_alloc(struct file *filp, int type)
 
 	error = lease_init(filp, type, fl);
 	if (error) {
-		locks_free_lock(fl);
+		locks_free_lease(fl);
 		return ERR_PTR(error);
 	}
 	return fl;
@@ -593,26 +627,26 @@ static inline int locks_overlap(struct file_lock *fl1, struct file_lock *fl2)
 /*
  * Check whether two locks have the same owner.
  */
-static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2)
+static int posix_same_owner(struct file_lock_core *fl1, struct file_lock_core *fl2)
 {
-	return fl1->fl_owner == fl2->fl_owner;
+	return fl1->flc_owner == fl2->flc_owner;
 }
 
 /* Must be called with the flc_lock held! */
-static void locks_insert_global_locks(struct file_lock *fl)
+static void locks_insert_global_locks(struct file_lock_core *flc)
 {
 	struct file_lock_list_struct *fll = this_cpu_ptr(&file_lock_list);
 
 	percpu_rwsem_assert_held(&file_rwsem);
 
 	spin_lock(&fll->lock);
-	fl->fl_link_cpu = smp_processor_id();
-	hlist_add_head(&fl->fl_link, &fll->hlist);
+	flc->flc_link_cpu = smp_processor_id();
+	hlist_add_head(&flc->flc_link, &fll->hlist);
 	spin_unlock(&fll->lock);
 }
 
 /* Must be called with the flc_lock held! */
-static void locks_delete_global_locks(struct file_lock *fl)
+static void locks_delete_global_locks(struct file_lock_core *flc)
 {
 	struct file_lock_list_struct *fll;
 
@@ -623,33 +657,33 @@ static void locks_delete_global_locks(struct file_lock *fl)
 	 * is done while holding the flc_lock, and new insertions into the list
 	 * also require that it be held.
 	 */
-	if (hlist_unhashed(&fl->fl_link))
+	if (hlist_unhashed(&flc->flc_link))
 		return;
 
-	fll = per_cpu_ptr(&file_lock_list, fl->fl_link_cpu);
+	fll = per_cpu_ptr(&file_lock_list, flc->flc_link_cpu);
 	spin_lock(&fll->lock);
-	hlist_del_init(&fl->fl_link);
+	hlist_del_init(&flc->flc_link);
 	spin_unlock(&fll->lock);
 }
 
 static unsigned long
-posix_owner_key(struct file_lock *fl)
+posix_owner_key(struct file_lock_core *flc)
 {
-	return (unsigned long)fl->fl_owner;
+	return (unsigned long) flc->flc_owner;
 }
 
-static void locks_insert_global_blocked(struct file_lock *waiter)
+static void locks_insert_global_blocked(struct file_lock_core *waiter)
 {
 	lockdep_assert_held(&blocked_lock_lock);
 
-	hash_add(blocked_hash, &waiter->fl_link, posix_owner_key(waiter));
+	hash_add(blocked_hash, &waiter->flc_link, posix_owner_key(waiter));
 }
 
-static void locks_delete_global_blocked(struct file_lock *waiter)
+static void locks_delete_global_blocked(struct file_lock_core *waiter)
 {
 	lockdep_assert_held(&blocked_lock_lock);
 
-	hash_del(&waiter->fl_link);
+	hash_del(&waiter->flc_link);
 }
 
 /* Remove waiter from blocker's block list.
@@ -657,41 +691,39 @@ static void locks_delete_global_blocked(struct file_lock *waiter)
  *
  * Must be called with blocked_lock_lock held.
  */
-static void __locks_delete_block(struct file_lock *waiter)
+static void __locks_unlink_block(struct file_lock_core *waiter)
 {
 	locks_delete_global_blocked(waiter);
-	list_del_init(&waiter->fl_blocked_member);
+	list_del_init(&waiter->flc_blocked_member);
 }
 
-static void __locks_wake_up_blocks(struct file_lock *blocker)
+static void __locks_wake_up_blocks(struct file_lock_core *blocker)
 {
-	while (!list_empty(&blocker->fl_blocked_requests)) {
-		struct file_lock *waiter;
+	while (!list_empty(&blocker->flc_blocked_requests)) {
+		struct file_lock_core *waiter;
+		struct file_lock *fl;
 
-		waiter = list_first_entry(&blocker->fl_blocked_requests,
-					  struct file_lock, fl_blocked_member);
-		__locks_delete_block(waiter);
-		if (waiter->fl_lmops && waiter->fl_lmops->lm_notify)
-			waiter->fl_lmops->lm_notify(waiter);
+		waiter = list_first_entry(&blocker->flc_blocked_requests,
+					  struct file_lock_core, flc_blocked_member);
+
+		fl = file_lock(waiter);
+		__locks_unlink_block(waiter);
+		if ((waiter->flc_flags & (FL_POSIX | FL_FLOCK)) &&
+		    fl->fl_lmops && fl->fl_lmops->lm_notify)
+			fl->fl_lmops->lm_notify(fl);
 		else
-			wake_up(&waiter->fl_wait);
+			locks_wake_up(fl);
 
 		/*
-		 * The setting of fl_blocker to NULL marks the "done"
+		 * The setting of flc_blocker to NULL marks the "done"
 		 * point in deleting a block. Paired with acquire at the top
 		 * of locks_delete_block().
 		 */
-		smp_store_release(&waiter->fl_blocker, NULL);
+		smp_store_release(&waiter->flc_blocker, NULL);
 	}
 }
 
-/**
- *	locks_delete_block - stop waiting for a file lock
- *	@waiter: the lock which was waiting
- *
- *	lockd/nfsd need to disconnect the lock while working on it.
- */
-int locks_delete_block(struct file_lock *waiter)
+static int __locks_delete_block(struct file_lock_core *waiter)
 {
 	int status = -ENOENT;
 
@@ -716,24 +748,35 @@ int locks_delete_block(struct file_lock *waiter)
 	 * no new locks can be inserted into its fl_blocked_requests list, and
 	 * can avoid doing anything further if the list is empty.
 	 */
-	if (!smp_load_acquire(&waiter->fl_blocker) &&
-	    list_empty(&waiter->fl_blocked_requests))
+	if (!smp_load_acquire(&waiter->flc_blocker) &&
+	    list_empty(&waiter->flc_blocked_requests))
 		return status;
 
 	spin_lock(&blocked_lock_lock);
-	if (waiter->fl_blocker)
+	if (waiter->flc_blocker)
 		status = 0;
 	__locks_wake_up_blocks(waiter);
-	__locks_delete_block(waiter);
+	__locks_unlink_block(waiter);
 
 	/*
 	 * The setting of fl_blocker to NULL marks the "done" point in deleting
 	 * a block. Paired with acquire at the top of this function.
 	 */
-	smp_store_release(&waiter->fl_blocker, NULL);
+	smp_store_release(&waiter->flc_blocker, NULL);
 	spin_unlock(&blocked_lock_lock);
 	return status;
 }
+
+/**
+ *	locks_delete_block - stop waiting for a file lock
+ *	@waiter: the lock which was waiting
+ *
+ *	lockd/nfsd need to disconnect the lock while working on it.
+ */
+int locks_delete_block(struct file_lock *waiter)
+{
+	return __locks_delete_block(&waiter->c);
+}
 EXPORT_SYMBOL(locks_delete_block);
 
 /* Insert waiter into blocker's block list.
@@ -751,26 +794,28 @@ EXPORT_SYMBOL(locks_delete_block);
  * waiters, and add beneath any waiter that blocks the new waiter.
  * Thus wakeups don't happen until needed.
  */
-static void __locks_insert_block(struct file_lock *blocker,
-				 struct file_lock *waiter,
-				 bool conflict(struct file_lock *,
-					       struct file_lock *))
+static void __locks_insert_block(struct file_lock_core *blocker,
+				 struct file_lock_core *waiter,
+				 bool conflict(struct file_lock_core *,
+					       struct file_lock_core *))
 {
-	struct file_lock *fl;
-	BUG_ON(!list_empty(&waiter->fl_blocked_member));
+	struct file_lock_core *flc;
 
+	BUG_ON(!list_empty(&waiter->flc_blocked_member));
 new_blocker:
-	list_for_each_entry(fl, &blocker->fl_blocked_requests, fl_blocked_member)
-		if (conflict(fl, waiter)) {
-			blocker =  fl;
+	list_for_each_entry(flc, &blocker->flc_blocked_requests, flc_blocked_member)
+		if (conflict(flc, waiter)) {
+			blocker =  flc;
 			goto new_blocker;
 		}
-	waiter->fl_blocker = blocker;
-	list_add_tail(&waiter->fl_blocked_member, &blocker->fl_blocked_requests);
-	if (IS_POSIX(blocker) && !IS_OFDLCK(blocker))
+	waiter->flc_blocker = blocker;
+	list_add_tail(&waiter->flc_blocked_member,
+		      &blocker->flc_blocked_requests);
+
+	if ((blocker->flc_flags & (FL_POSIX|FL_OFDLCK)) == FL_POSIX)
 		locks_insert_global_blocked(waiter);
 
-	/* The requests in waiter->fl_blocked are known to conflict with
+	/* The requests in waiter->flc_blocked are known to conflict with
 	 * waiter, but might not conflict with blocker, or the requests
 	 * and lock which block it.  So they all need to be woken.
 	 */
@@ -778,10 +823,10 @@ new_blocker:
 }
 
 /* Must be called with flc_lock held. */
-static void locks_insert_block(struct file_lock *blocker,
-			       struct file_lock *waiter,
-			       bool conflict(struct file_lock *,
-					     struct file_lock *))
+static void locks_insert_block(struct file_lock_core *blocker,
+			       struct file_lock_core *waiter,
+			       bool conflict(struct file_lock_core *,
+					     struct file_lock_core *))
 {
 	spin_lock(&blocked_lock_lock);
 	__locks_insert_block(blocker, waiter, conflict);
@@ -793,7 +838,7 @@ static void locks_insert_block(struct file_lock *blocker,
  *
  * Must be called with the inode->flc_lock held!
  */
-static void locks_wake_up_blocks(struct file_lock *blocker)
+static void locks_wake_up_blocks(struct file_lock_core *blocker)
 {
 	/*
 	 * Avoid taking global lock if list is empty. This is safe since new
@@ -802,7 +847,7 @@ static void locks_wake_up_blocks(struct file_lock *blocker)
 	 * fl_blocked_requests list does not require the flc_lock, so we must
 	 * recheck list_empty() after acquiring the blocked_lock_lock.
 	 */
-	if (list_empty(&blocker->fl_blocked_requests))
+	if (list_empty(&blocker->flc_blocked_requests))
 		return;
 
 	spin_lock(&blocked_lock_lock);
@@ -811,39 +856,39 @@ static void locks_wake_up_blocks(struct file_lock *blocker)
 }
 
 static void
-locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before)
+locks_insert_lock_ctx(struct file_lock_core *fl, struct list_head *before)
 {
-	list_add_tail(&fl->fl_list, before);
+	list_add_tail(&fl->flc_list, before);
 	locks_insert_global_locks(fl);
 }
 
 static void
-locks_unlink_lock_ctx(struct file_lock *fl)
+locks_unlink_lock_ctx(struct file_lock_core *fl)
 {
 	locks_delete_global_locks(fl);
-	list_del_init(&fl->fl_list);
+	list_del_init(&fl->flc_list);
 	locks_wake_up_blocks(fl);
 }
 
 static void
-locks_delete_lock_ctx(struct file_lock *fl, struct list_head *dispose)
+locks_delete_lock_ctx(struct file_lock_core *fl, struct list_head *dispose)
 {
 	locks_unlink_lock_ctx(fl);
 	if (dispose)
-		list_add(&fl->fl_list, dispose);
+		list_add(&fl->flc_list, dispose);
 	else
-		locks_free_lock(fl);
+		locks_free_lock(file_lock(fl));
 }
 
 /* Determine if lock sys_fl blocks lock caller_fl. Common functionality
  * checks for shared/exclusive status of overlapping locks.
  */
-static bool locks_conflict(struct file_lock *caller_fl,
-			   struct file_lock *sys_fl)
+static bool locks_conflict(struct file_lock_core *caller_flc,
+			   struct file_lock_core *sys_flc)
 {
-	if (sys_fl->fl_type == F_WRLCK)
+	if (sys_flc->flc_type == F_WRLCK)
 		return true;
-	if (caller_fl->fl_type == F_WRLCK)
+	if (caller_flc->flc_type == F_WRLCK)
 		return true;
 	return false;
 }
@@ -851,20 +896,23 @@ static bool locks_conflict(struct file_lock *caller_fl,
 /* Determine if lock sys_fl blocks lock caller_fl. POSIX specific
  * checking before calling the locks_conflict().
  */
-static bool posix_locks_conflict(struct file_lock *caller_fl,
-				 struct file_lock *sys_fl)
+static bool posix_locks_conflict(struct file_lock_core *caller_flc,
+				 struct file_lock_core *sys_flc)
 {
+	struct file_lock *caller_fl = file_lock(caller_flc);
+	struct file_lock *sys_fl = file_lock(sys_flc);
+
 	/* POSIX locks owned by the same process do not conflict with
 	 * each other.
 	 */
-	if (posix_same_owner(caller_fl, sys_fl))
+	if (posix_same_owner(caller_flc, sys_flc))
 		return false;
 
 	/* Check whether they overlap */
 	if (!locks_overlap(caller_fl, sys_fl))
 		return false;
 
-	return locks_conflict(caller_fl, sys_fl);
+	return locks_conflict(caller_flc, sys_flc);
 }
 
 /* Determine if lock sys_fl blocks lock caller_fl. Used on xx_GETLK
@@ -873,28 +921,31 @@ static bool posix_locks_conflict(struct file_lock *caller_fl,
 static bool posix_test_locks_conflict(struct file_lock *caller_fl,
 				      struct file_lock *sys_fl)
 {
+	struct file_lock_core *caller = &caller_fl->c;
+	struct file_lock_core *sys = &sys_fl->c;
+
 	/* F_UNLCK checks any locks on the same fd. */
-	if (caller_fl->fl_type == F_UNLCK) {
-		if (!posix_same_owner(caller_fl, sys_fl))
+	if (lock_is_unlock(caller_fl)) {
+		if (!posix_same_owner(caller, sys))
 			return false;
 		return locks_overlap(caller_fl, sys_fl);
 	}
-	return posix_locks_conflict(caller_fl, sys_fl);
+	return posix_locks_conflict(caller, sys);
 }
 
 /* Determine if lock sys_fl blocks lock caller_fl. FLOCK specific
  * checking before calling the locks_conflict().
  */
-static bool flock_locks_conflict(struct file_lock *caller_fl,
-				 struct file_lock *sys_fl)
+static bool flock_locks_conflict(struct file_lock_core *caller_flc,
+				 struct file_lock_core *sys_flc)
 {
 	/* FLOCK locks referring to the same filp do not conflict with
 	 * each other.
 	 */
-	if (caller_fl->fl_file == sys_fl->fl_file)
+	if (caller_flc->flc_file == sys_flc->flc_file)
 		return false;
 
-	return locks_conflict(caller_fl, sys_fl);
+	return locks_conflict(caller_flc, sys_flc);
 }
 
 void
@@ -908,13 +959,13 @@ posix_test_lock(struct file *filp, struct file_lock *fl)
 
 	ctx = locks_inode_context(inode);
 	if (!ctx || list_empty_careful(&ctx->flc_posix)) {
-		fl->fl_type = F_UNLCK;
+		fl->c.flc_type = F_UNLCK;
 		return;
 	}
 
 retry:
 	spin_lock(&ctx->flc_lock);
-	list_for_each_entry(cfl, &ctx->flc_posix, fl_list) {
+	list_for_each_entry(cfl, &ctx->flc_posix, c.flc_list) {
 		if (!posix_test_locks_conflict(fl, cfl))
 			continue;
 		if (cfl->fl_lmops && cfl->fl_lmops->lm_lock_expirable
@@ -930,7 +981,7 @@ retry:
 		locks_copy_conflock(fl, cfl);
 		goto out;
 	}
-	fl->fl_type = F_UNLCK;
+	fl->c.flc_type = F_UNLCK;
 out:
 	spin_unlock(&ctx->flc_lock);
 	return;
@@ -972,25 +1023,27 @@ EXPORT_SYMBOL(posix_test_lock);
 
 #define MAX_DEADLK_ITERATIONS 10
 
-/* Find a lock that the owner of the given block_fl is blocking on. */
-static struct file_lock *what_owner_is_waiting_for(struct file_lock *block_fl)
+/* Find a lock that the owner of the given @blocker is blocking on. */
+static struct file_lock_core *what_owner_is_waiting_for(struct file_lock_core *blocker)
 {
-	struct file_lock *fl;
+	struct file_lock_core *flc;
 
-	hash_for_each_possible(blocked_hash, fl, fl_link, posix_owner_key(block_fl)) {
-		if (posix_same_owner(fl, block_fl)) {
-			while (fl->fl_blocker)
-				fl = fl->fl_blocker;
-			return fl;
+	hash_for_each_possible(blocked_hash, flc, flc_link, posix_owner_key(blocker)) {
+		if (posix_same_owner(flc, blocker)) {
+			while (flc->flc_blocker)
+				flc = flc->flc_blocker;
+			return flc;
 		}
 	}
 	return NULL;
 }
 
 /* Must be called with the blocked_lock_lock held! */
-static int posix_locks_deadlock(struct file_lock *caller_fl,
-				struct file_lock *block_fl)
+static bool posix_locks_deadlock(struct file_lock *caller_fl,
+				 struct file_lock *block_fl)
 {
+	struct file_lock_core *caller = &caller_fl->c;
+	struct file_lock_core *blocker = &block_fl->c;
 	int i = 0;
 
 	lockdep_assert_held(&blocked_lock_lock);
@@ -999,16 +1052,16 @@ static int posix_locks_deadlock(struct file_lock *caller_fl,
 	 * This deadlock detector can't reasonably detect deadlocks with
 	 * FL_OFDLCK locks, since they aren't owned by a process, per-se.
 	 */
-	if (IS_OFDLCK(caller_fl))
-		return 0;
+	if (caller->flc_flags & FL_OFDLCK)
+		return false;
 
-	while ((block_fl = what_owner_is_waiting_for(block_fl))) {
+	while ((blocker = what_owner_is_waiting_for(blocker))) {
 		if (i++ > MAX_DEADLK_ITERATIONS)
-			return 0;
-		if (posix_same_owner(caller_fl, block_fl))
-			return 1;
+			return false;
+		if (posix_same_owner(caller, blocker))
+			return true;
 	}
-	return 0;
+	return false;
 }
 
 /* Try to create a FLOCK lock on filp. We always insert new FLOCK locks
@@ -1027,14 +1080,14 @@ static int flock_lock_inode(struct inode *inode, struct file_lock *request)
 	bool found = false;
 	LIST_HEAD(dispose);
 
-	ctx = locks_get_lock_context(inode, request->fl_type);
+	ctx = locks_get_lock_context(inode, request->c.flc_type);
 	if (!ctx) {
-		if (request->fl_type != F_UNLCK)
+		if (request->c.flc_type != F_UNLCK)
 			return -ENOMEM;
-		return (request->fl_flags & FL_EXISTS) ? -ENOENT : 0;
+		return (request->c.flc_flags & FL_EXISTS) ? -ENOENT : 0;
 	}
 
-	if (!(request->fl_flags & FL_ACCESS) && (request->fl_type != F_UNLCK)) {
+	if (!(request->c.flc_flags & FL_ACCESS) && (request->c.flc_type != F_UNLCK)) {
 		new_fl = locks_alloc_lock();
 		if (!new_fl)
 			return -ENOMEM;
@@ -1042,41 +1095,41 @@ static int flock_lock_inode(struct inode *inode, struct file_lock *request)
 
 	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
-	if (request->fl_flags & FL_ACCESS)
+	if (request->c.flc_flags & FL_ACCESS)
 		goto find_conflict;
 
-	list_for_each_entry(fl, &ctx->flc_flock, fl_list) {
-		if (request->fl_file != fl->fl_file)
+	list_for_each_entry(fl, &ctx->flc_flock, c.flc_list) {
+		if (request->c.flc_file != fl->c.flc_file)
 			continue;
-		if (request->fl_type == fl->fl_type)
+		if (request->c.flc_type == fl->c.flc_type)
 			goto out;
 		found = true;
-		locks_delete_lock_ctx(fl, &dispose);
+		locks_delete_lock_ctx(&fl->c, &dispose);
 		break;
 	}
 
-	if (request->fl_type == F_UNLCK) {
-		if ((request->fl_flags & FL_EXISTS) && !found)
+	if (lock_is_unlock(request)) {
+		if ((request->c.flc_flags & FL_EXISTS) && !found)
 			error = -ENOENT;
 		goto out;
 	}
 
 find_conflict:
-	list_for_each_entry(fl, &ctx->flc_flock, fl_list) {
-		if (!flock_locks_conflict(request, fl))
+	list_for_each_entry(fl, &ctx->flc_flock, c.flc_list) {
+		if (!flock_locks_conflict(&request->c, &fl->c))
 			continue;
 		error = -EAGAIN;
-		if (!(request->fl_flags & FL_SLEEP))
+		if (!(request->c.flc_flags & FL_SLEEP))
 			goto out;
 		error = FILE_LOCK_DEFERRED;
-		locks_insert_block(fl, request, flock_locks_conflict);
+		locks_insert_block(&fl->c, &request->c, flock_locks_conflict);
 		goto out;
 	}
-	if (request->fl_flags & FL_ACCESS)
+	if (request->c.flc_flags & FL_ACCESS)
 		goto out;
 	locks_copy_lock(new_fl, request);
 	locks_move_blocks(new_fl, request);
-	locks_insert_lock_ctx(new_fl, &ctx->flc_flock);
+	locks_insert_lock_ctx(&new_fl->c, &ctx->flc_flock);
 	new_fl = NULL;
 	error = 0;
 
@@ -1105,9 +1158,9 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,
 	void *owner;
 	void (*func)(void);
 
-	ctx = locks_get_lock_context(inode, request->fl_type);
+	ctx = locks_get_lock_context(inode, request->c.flc_type);
 	if (!ctx)
-		return (request->fl_type == F_UNLCK) ? 0 : -ENOMEM;
+		return lock_is_unlock(request) ? 0 : -ENOMEM;
 
 	/*
 	 * We may need two file_lock structures for this operation,
@@ -1115,8 +1168,8 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,
 	 *
 	 * In some cases we can be sure, that no new locks will be needed
 	 */
-	if (!(request->fl_flags & FL_ACCESS) &&
-	    (request->fl_type != F_UNLCK ||
+	if (!(request->c.flc_flags & FL_ACCESS) &&
+	    (request->c.flc_type != F_UNLCK ||
 	     request->fl_start != 0 || request->fl_end != OFFSET_MAX)) {
 		new_fl = locks_alloc_lock();
 		new_fl2 = locks_alloc_lock();
@@ -1130,9 +1183,9 @@ retry:
 	 * there are any, either return error or put the request on the
 	 * blocker's list of waiters and the global blocked_hash.
 	 */
-	if (request->fl_type != F_UNLCK) {
-		list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
-			if (!posix_locks_conflict(request, fl))
+	if (request->c.flc_type != F_UNLCK) {
+		list_for_each_entry(fl, &ctx->flc_posix, c.flc_list) {
+			if (!posix_locks_conflict(&request->c, &fl->c))
 				continue;
 			if (fl->fl_lmops && fl->fl_lmops->lm_lock_expirable
 				&& (*fl->fl_lmops->lm_lock_expirable)(fl)) {
@@ -1148,7 +1201,7 @@ retry:
 			if (conflock)
 				locks_copy_conflock(conflock, fl);
 			error = -EAGAIN;
-			if (!(request->fl_flags & FL_SLEEP))
+			if (!(request->c.flc_flags & FL_SLEEP))
 				goto out;
 			/*
 			 * Deadlock detection and insertion into the blocked
@@ -1160,10 +1213,10 @@ retry:
 			 * Ensure that we don't find any locks blocked on this
 			 * request during deadlock detection.
 			 */
-			__locks_wake_up_blocks(request);
+			__locks_wake_up_blocks(&request->c);
 			if (likely(!posix_locks_deadlock(request, fl))) {
 				error = FILE_LOCK_DEFERRED;
-				__locks_insert_block(fl, request,
+				__locks_insert_block(&fl->c, &request->c,
 						     posix_locks_conflict);
 			}
 			spin_unlock(&blocked_lock_lock);
@@ -1173,22 +1226,22 @@ retry:
 
 	/* If we're just looking for a conflict, we're done. */
 	error = 0;
-	if (request->fl_flags & FL_ACCESS)
+	if (request->c.flc_flags & FL_ACCESS)
 		goto out;
 
 	/* Find the first old lock with the same owner as the new lock */
-	list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
-		if (posix_same_owner(request, fl))
+	list_for_each_entry(fl, &ctx->flc_posix, c.flc_list) {
+		if (posix_same_owner(&request->c, &fl->c))
 			break;
 	}
 
 	/* Process locks with this owner. */
-	list_for_each_entry_safe_from(fl, tmp, &ctx->flc_posix, fl_list) {
-		if (!posix_same_owner(request, fl))
+	list_for_each_entry_safe_from(fl, tmp, &ctx->flc_posix, c.flc_list) {
+		if (!posix_same_owner(&request->c, &fl->c))
 			break;
 
 		/* Detect adjacent or overlapping regions (if same lock type) */
-		if (request->fl_type == fl->fl_type) {
+		if (request->c.flc_type == fl->c.flc_type) {
 			/* In all comparisons of start vs end, use
 			 * "start - 1" rather than "end + 1". If end
 			 * is OFFSET_MAX, end + 1 will become negative.
@@ -1215,7 +1268,7 @@ retry:
 			else
 				request->fl_end = fl->fl_end;
 			if (added) {
-				locks_delete_lock_ctx(fl, &dispose);
+				locks_delete_lock_ctx(&fl->c, &dispose);
 				continue;
 			}
 			request = fl;
@@ -1228,7 +1281,7 @@ retry:
 				continue;
 			if (fl->fl_start > request->fl_end)
 				break;
-			if (request->fl_type == F_UNLCK)
+			if (lock_is_unlock(request))
 				added = true;
 			if (fl->fl_start < request->fl_start)
 				left = fl;
@@ -1244,7 +1297,7 @@ retry:
 				 * one (This may happen several times).
 				 */
 				if (added) {
-					locks_delete_lock_ctx(fl, &dispose);
+					locks_delete_lock_ctx(&fl->c, &dispose);
 					continue;
 				}
 				/*
@@ -1261,8 +1314,9 @@ retry:
 				locks_move_blocks(new_fl, request);
 				request = new_fl;
 				new_fl = NULL;
-				locks_insert_lock_ctx(request, &fl->fl_list);
-				locks_delete_lock_ctx(fl, &dispose);
+				locks_insert_lock_ctx(&request->c,
+						      &fl->c.flc_list);
+				locks_delete_lock_ctx(&fl->c, &dispose);
 				added = true;
 			}
 		}
@@ -1279,8 +1333,8 @@ retry:
 
 	error = 0;
 	if (!added) {
-		if (request->fl_type == F_UNLCK) {
-			if (request->fl_flags & FL_EXISTS)
+		if (lock_is_unlock(request)) {
+			if (request->c.flc_flags & FL_EXISTS)
 				error = -ENOENT;
 			goto out;
 		}
@@ -1291,7 +1345,7 @@ retry:
 		}
 		locks_copy_lock(new_fl, request);
 		locks_move_blocks(new_fl, request);
-		locks_insert_lock_ctx(new_fl, &fl->fl_list);
+		locks_insert_lock_ctx(&new_fl->c, &fl->c.flc_list);
 		fl = new_fl;
 		new_fl = NULL;
 	}
@@ -1303,14 +1357,14 @@ retry:
 			left = new_fl2;
 			new_fl2 = NULL;
 			locks_copy_lock(left, right);
-			locks_insert_lock_ctx(left, &fl->fl_list);
+			locks_insert_lock_ctx(&left->c, &fl->c.flc_list);
 		}
 		right->fl_start = request->fl_end + 1;
-		locks_wake_up_blocks(right);
+		locks_wake_up_blocks(&right->c);
 	}
 	if (left) {
 		left->fl_end = request->fl_start - 1;
-		locks_wake_up_blocks(left);
+		locks_wake_up_blocks(&left->c);
 	}
  out:
 	spin_unlock(&ctx->flc_lock);
@@ -1364,8 +1418,8 @@ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl)
 		error = posix_lock_inode(inode, fl, NULL);
 		if (error != FILE_LOCK_DEFERRED)
 			break;
-		error = wait_event_interruptible(fl->fl_wait,
-					list_empty(&fl->fl_blocked_member));
+		error = wait_event_interruptible(fl->c.flc_wait,
+						 list_empty(&fl->c.flc_blocked_member));
 		if (error)
 			break;
 	}
@@ -1373,37 +1427,37 @@ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl)
 	return error;
 }
 
-static void lease_clear_pending(struct file_lock *fl, int arg)
+static void lease_clear_pending(struct file_lease *fl, int arg)
 {
 	switch (arg) {
 	case F_UNLCK:
-		fl->fl_flags &= ~FL_UNLOCK_PENDING;
+		fl->c.flc_flags &= ~FL_UNLOCK_PENDING;
 		fallthrough;
 	case F_RDLCK:
-		fl->fl_flags &= ~FL_DOWNGRADE_PENDING;
+		fl->c.flc_flags &= ~FL_DOWNGRADE_PENDING;
 	}
 }
 
 /* We already had a lease on this file; just change its type */
-int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose)
+int lease_modify(struct file_lease *fl, int arg, struct list_head *dispose)
 {
-	int error = assign_type(fl, arg);
+	int error = assign_type(&fl->c, arg);
 
 	if (error)
 		return error;
 	lease_clear_pending(fl, arg);
-	locks_wake_up_blocks(fl);
+	locks_wake_up_blocks(&fl->c);
 	if (arg == F_UNLCK) {
-		struct file *filp = fl->fl_file;
+		struct file *filp = fl->c.flc_file;
 
 		f_delown(filp);
 		filp->f_owner.signum = 0;
-		fasync_helper(0, fl->fl_file, 0, &fl->fl_fasync);
+		fasync_helper(0, fl->c.flc_file, 0, &fl->fl_fasync);
 		if (fl->fl_fasync != NULL) {
 			printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync);
 			fl->fl_fasync = NULL;
 		}
-		locks_delete_lock_ctx(fl, dispose);
+		locks_delete_lock_ctx(&fl->c, dispose);
 	}
 	return 0;
 }
@@ -1420,11 +1474,11 @@ static bool past_time(unsigned long then)
 static void time_out_leases(struct inode *inode, struct list_head *dispose)
 {
 	struct file_lock_context *ctx = inode->i_flctx;
-	struct file_lock *fl, *tmp;
+	struct file_lease *fl, *tmp;
 
 	lockdep_assert_held(&ctx->flc_lock);
 
-	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) {
+	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list) {
 		trace_time_out_leases(inode, fl);
 		if (past_time(fl->fl_downgrade_time))
 			lease_modify(fl, F_RDLCK, dispose);
@@ -1433,38 +1487,40 @@ static void time_out_leases(struct inode *inode, struct list_head *dispose)
 	}
 }
 
-static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker)
+static bool leases_conflict(struct file_lock_core *lc, struct file_lock_core *bc)
 {
 	bool rc;
+	struct file_lease *lease = file_lease(lc);
+	struct file_lease *breaker = file_lease(bc);
 
 	if (lease->fl_lmops->lm_breaker_owns_lease
 			&& lease->fl_lmops->lm_breaker_owns_lease(lease))
 		return false;
-	if ((breaker->fl_flags & FL_LAYOUT) != (lease->fl_flags & FL_LAYOUT)) {
+	if ((bc->flc_flags & FL_LAYOUT) != (lc->flc_flags & FL_LAYOUT)) {
 		rc = false;
 		goto trace;
 	}
-	if ((breaker->fl_flags & FL_DELEG) && (lease->fl_flags & FL_LEASE)) {
+	if ((bc->flc_flags & FL_DELEG) && (lc->flc_flags & FL_LEASE)) {
 		rc = false;
 		goto trace;
 	}
 
-	rc = locks_conflict(breaker, lease);
+	rc = locks_conflict(bc, lc);
 trace:
 	trace_leases_conflict(rc, lease, breaker);
 	return rc;
 }
 
 static bool
-any_leases_conflict(struct inode *inode, struct file_lock *breaker)
+any_leases_conflict(struct inode *inode, struct file_lease *breaker)
 {
 	struct file_lock_context *ctx = inode->i_flctx;
-	struct file_lock *fl;
+	struct file_lock_core *flc;
 
 	lockdep_assert_held(&ctx->flc_lock);
 
-	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
-		if (leases_conflict(fl, breaker))
+	list_for_each_entry(flc, &ctx->flc_lease, flc_list) {
+		if (leases_conflict(flc, &breaker->c))
 			return true;
 	}
 	return false;
@@ -1487,7 +1543,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 {
 	int error = 0;
 	struct file_lock_context *ctx;
-	struct file_lock *new_fl, *fl, *tmp;
+	struct file_lease *new_fl, *fl, *tmp;
 	unsigned long break_time;
 	int want_write = (mode & O_ACCMODE) != O_RDONLY;
 	LIST_HEAD(dispose);
@@ -1495,7 +1551,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 	new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK);
 	if (IS_ERR(new_fl))
 		return PTR_ERR(new_fl);
-	new_fl->fl_flags = type;
+	new_fl->c.flc_flags = type;
 
 	/* typically we will check that ctx is non-NULL before calling */
 	ctx = locks_inode_context(inode);
@@ -1519,22 +1575,22 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 			break_time++;	/* so that 0 means no break time */
 	}
 
-	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) {
-		if (!leases_conflict(fl, new_fl))
+	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list) {
+		if (!leases_conflict(&fl->c, &new_fl->c))
 			continue;
 		if (want_write) {
-			if (fl->fl_flags & FL_UNLOCK_PENDING)
+			if (fl->c.flc_flags & FL_UNLOCK_PENDING)
 				continue;
-			fl->fl_flags |= FL_UNLOCK_PENDING;
+			fl->c.flc_flags |= FL_UNLOCK_PENDING;
 			fl->fl_break_time = break_time;
 		} else {
 			if (lease_breaking(fl))
 				continue;
-			fl->fl_flags |= FL_DOWNGRADE_PENDING;
+			fl->c.flc_flags |= FL_DOWNGRADE_PENDING;
 			fl->fl_downgrade_time = break_time;
 		}
 		if (fl->fl_lmops->lm_break(fl))
-			locks_delete_lock_ctx(fl, &dispose);
+			locks_delete_lock_ctx(&fl->c, &dispose);
 	}
 
 	if (list_empty(&ctx->flc_lease))
@@ -1547,26 +1603,26 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 	}
 
 restart:
-	fl = list_first_entry(&ctx->flc_lease, struct file_lock, fl_list);
+	fl = list_first_entry(&ctx->flc_lease, struct file_lease, c.flc_list);
 	break_time = fl->fl_break_time;
 	if (break_time != 0)
 		break_time -= jiffies;
 	if (break_time == 0)
 		break_time++;
-	locks_insert_block(fl, new_fl, leases_conflict);
+	locks_insert_block(&fl->c, &new_fl->c, leases_conflict);
 	trace_break_lease_block(inode, new_fl);
 	spin_unlock(&ctx->flc_lock);
 	percpu_up_read(&file_rwsem);
 
 	locks_dispose_list(&dispose);
-	error = wait_event_interruptible_timeout(new_fl->fl_wait,
-					list_empty(&new_fl->fl_blocked_member),
-					break_time);
+	error = wait_event_interruptible_timeout(new_fl->c.flc_wait,
+						 list_empty(&new_fl->c.flc_blocked_member),
+						 break_time);
 
 	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
 	trace_break_lease_unblock(inode, new_fl);
-	locks_delete_block(new_fl);
+	__locks_delete_block(&new_fl->c);
 	if (error >= 0) {
 		/*
 		 * Wait for the next conflicting lease that has not been
@@ -1583,7 +1639,7 @@ out:
 	percpu_up_read(&file_rwsem);
 	locks_dispose_list(&dispose);
 free_lock:
-	locks_free_lock(new_fl);
+	locks_free_lease(new_fl);
 	return error;
 }
 EXPORT_SYMBOL(__break_lease);
@@ -1601,14 +1657,14 @@ void lease_get_mtime(struct inode *inode, struct timespec64 *time)
 {
 	bool has_lease = false;
 	struct file_lock_context *ctx;
-	struct file_lock *fl;
+	struct file_lock_core *flc;
 
 	ctx = locks_inode_context(inode);
 	if (ctx && !list_empty_careful(&ctx->flc_lease)) {
 		spin_lock(&ctx->flc_lock);
-		fl = list_first_entry_or_null(&ctx->flc_lease,
-					      struct file_lock, fl_list);
-		if (fl && (fl->fl_type == F_WRLCK))
+		flc = list_first_entry_or_null(&ctx->flc_lease,
+					       struct file_lock_core, flc_list);
+		if (flc && flc->flc_type == F_WRLCK)
 			has_lease = true;
 		spin_unlock(&ctx->flc_lock);
 	}
@@ -1643,7 +1699,7 @@ EXPORT_SYMBOL(lease_get_mtime);
  */
 int fcntl_getlease(struct file *filp)
 {
-	struct file_lock *fl;
+	struct file_lease *fl;
 	struct inode *inode = file_inode(filp);
 	struct file_lock_context *ctx;
 	int type = F_UNLCK;
@@ -1654,8 +1710,8 @@ int fcntl_getlease(struct file *filp)
 		percpu_down_read(&file_rwsem);
 		spin_lock(&ctx->flc_lock);
 		time_out_leases(inode, &dispose);
-		list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
-			if (fl->fl_file != filp)
+		list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) {
+			if (fl->c.flc_file != filp)
 				continue;
 			type = target_leasetype(fl);
 			break;
@@ -1715,12 +1771,12 @@ check_conflicting_open(struct file *filp, const int arg, int flags)
 }
 
 static int
-generic_add_lease(struct file *filp, int arg, struct file_lock **flp, void **priv)
+generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **priv)
 {
-	struct file_lock *fl, *my_fl = NULL, *lease;
+	struct file_lease *fl, *my_fl = NULL, *lease;
 	struct inode *inode = file_inode(filp);
 	struct file_lock_context *ctx;
-	bool is_deleg = (*flp)->fl_flags & FL_DELEG;
+	bool is_deleg = (*flp)->c.flc_flags & FL_DELEG;
 	int error;
 	LIST_HEAD(dispose);
 
@@ -1746,7 +1802,7 @@ generic_add_lease(struct file *filp, int arg, struct file_lock **flp, void **pri
 	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
 	time_out_leases(inode, &dispose);
-	error = check_conflicting_open(filp, arg, lease->fl_flags);
+	error = check_conflicting_open(filp, arg, lease->c.flc_flags);
 	if (error)
 		goto out;
 
@@ -1759,9 +1815,9 @@ generic_add_lease(struct file *filp, int arg, struct file_lock **flp, void **pri
 	 * except for this filp.
 	 */
 	error = -EAGAIN;
-	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
-		if (fl->fl_file == filp &&
-		    fl->fl_owner == lease->fl_owner) {
+	list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) {
+		if (fl->c.flc_file == filp &&
+		    fl->c.flc_owner == lease->c.flc_owner) {
 			my_fl = fl;
 			continue;
 		}
@@ -1776,7 +1832,7 @@ generic_add_lease(struct file *filp, int arg, struct file_lock **flp, void **pri
 		 * Modifying our existing lease is OK, but no getting a
 		 * new lease if someone else is opening for write:
 		 */
-		if (fl->fl_flags & FL_UNLOCK_PENDING)
+		if (fl->c.flc_flags & FL_UNLOCK_PENDING)
 			goto out;
 	}
 
@@ -1792,7 +1848,7 @@ generic_add_lease(struct file *filp, int arg, struct file_lock **flp, void **pri
 	if (!leases_enable)
 		goto out;
 
-	locks_insert_lock_ctx(lease, &ctx->flc_lease);
+	locks_insert_lock_ctx(&lease->c, &ctx->flc_lease);
 	/*
 	 * The check in break_lease() is lockless. It's possible for another
 	 * open to race in after we did the earlier check for a conflicting
@@ -1803,9 +1859,9 @@ generic_add_lease(struct file *filp, int arg, struct file_lock **flp, void **pri
 	 * precedes these checks.
 	 */
 	smp_mb();
-	error = check_conflicting_open(filp, arg, lease->fl_flags);
+	error = check_conflicting_open(filp, arg, lease->c.flc_flags);
 	if (error) {
-		locks_unlink_lock_ctx(lease);
+		locks_unlink_lock_ctx(&lease->c);
 		goto out;
 	}
 
@@ -1826,7 +1882,7 @@ out:
 static int generic_delete_lease(struct file *filp, void *owner)
 {
 	int error = -EAGAIN;
-	struct file_lock *fl, *victim = NULL;
+	struct file_lease *fl, *victim = NULL;
 	struct inode *inode = file_inode(filp);
 	struct file_lock_context *ctx;
 	LIST_HEAD(dispose);
@@ -1839,9 +1895,9 @@ static int generic_delete_lease(struct file *filp, void *owner)
 
 	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
-	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
-		if (fl->fl_file == filp &&
-		    fl->fl_owner == owner) {
+	list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) {
+		if (fl->c.flc_file == filp &&
+		    fl->c.flc_owner == owner) {
 			victim = fl;
 			break;
 		}
@@ -1866,21 +1922,9 @@ static int generic_delete_lease(struct file *filp, void *owner)
  *	The (input) flp->fl_lmops->lm_break function is required
  *	by break_lease().
  */
-int generic_setlease(struct file *filp, int arg, struct file_lock **flp,
+int generic_setlease(struct file *filp, int arg, struct file_lease **flp,
 			void **priv)
 {
-	struct inode *inode = file_inode(filp);
-	vfsuid_t vfsuid = i_uid_into_vfsuid(file_mnt_idmap(filp), inode);
-	int error;
-
-	if ((!vfsuid_eq_kuid(vfsuid, current_fsuid())) && !capable(CAP_LEASE))
-		return -EACCES;
-	if (!S_ISREG(inode->i_mode))
-		return -EINVAL;
-	error = security_file_lock(filp, arg);
-	if (error)
-		return error;
-
 	switch (arg) {
 	case F_UNLCK:
 		return generic_delete_lease(filp, *priv);
@@ -1913,7 +1957,7 @@ lease_notifier_chain_init(void)
 }
 
 static inline void
-setlease_notifier(int arg, struct file_lock *lease)
+setlease_notifier(int arg, struct file_lease *lease)
 {
 	if (arg != F_UNLCK)
 		srcu_notifier_call_chain(&lease_notifier_chain, arg, lease);
@@ -1931,6 +1975,19 @@ void lease_unregister_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL_GPL(lease_unregister_notifier);
 
+
+int
+kernel_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv)
+{
+	if (lease)
+		setlease_notifier(arg, *lease);
+	if (filp->f_op->setlease)
+		return filp->f_op->setlease(filp, arg, lease, priv);
+	else
+		return generic_setlease(filp, arg, lease, priv);
+}
+EXPORT_SYMBOL_GPL(kernel_setlease);
+
 /**
  * vfs_setlease        -       sets a lease on an open file
  * @filp:	file pointer
@@ -1949,20 +2006,26 @@ EXPORT_SYMBOL_GPL(lease_unregister_notifier);
  * may be NULL if the lm_setup operation doesn't require it.
  */
 int
-vfs_setlease(struct file *filp, int arg, struct file_lock **lease, void **priv)
+vfs_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv)
 {
-	if (lease)
-		setlease_notifier(arg, *lease);
-	if (filp->f_op->setlease)
-		return filp->f_op->setlease(filp, arg, lease, priv);
-	else
-		return generic_setlease(filp, arg, lease, priv);
+	struct inode *inode = file_inode(filp);
+	vfsuid_t vfsuid = i_uid_into_vfsuid(file_mnt_idmap(filp), inode);
+	int error;
+
+	if ((!vfsuid_eq_kuid(vfsuid, current_fsuid())) && !capable(CAP_LEASE))
+		return -EACCES;
+	if (!S_ISREG(inode->i_mode))
+		return -EINVAL;
+	error = security_file_lock(filp, arg);
+	if (error)
+		return error;
+	return kernel_setlease(filp, arg, lease, priv);
 }
 EXPORT_SYMBOL_GPL(vfs_setlease);
 
 static int do_fcntl_add_lease(unsigned int fd, struct file *filp, int arg)
 {
-	struct file_lock *fl;
+	struct file_lease *fl;
 	struct fasync_struct *new;
 	int error;
 
@@ -1972,14 +2035,14 @@ static int do_fcntl_add_lease(unsigned int fd, struct file *filp, int arg)
 
 	new = fasync_alloc();
 	if (!new) {
-		locks_free_lock(fl);
+		locks_free_lease(fl);
 		return -ENOMEM;
 	}
 	new->fa_fd = fd;
 
 	error = vfs_setlease(filp, arg, &fl, (void **)&new);
 	if (fl)
-		locks_free_lock(fl);
+		locks_free_lease(fl);
 	if (new)
 		fasync_free(new);
 	return error;
@@ -2017,8 +2080,8 @@ static int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl)
 		error = flock_lock_inode(inode, fl);
 		if (error != FILE_LOCK_DEFERRED)
 			break;
-		error = wait_event_interruptible(fl->fl_wait,
-				list_empty(&fl->fl_blocked_member));
+		error = wait_event_interruptible(fl->c.flc_wait,
+						 list_empty(&fl->c.flc_blocked_member));
 		if (error)
 			break;
 	}
@@ -2036,7 +2099,7 @@ static int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl)
 int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl)
 {
 	int res = 0;
-	switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) {
+	switch (fl->c.flc_flags & (FL_POSIX|FL_FLOCK)) {
 		case FL_POSIX:
 			res = posix_lock_inode_wait(inode, fl);
 			break;
@@ -2098,13 +2161,13 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
 
 	flock_make_lock(f.file, &fl, type);
 
-	error = security_file_lock(f.file, fl.fl_type);
+	error = security_file_lock(f.file, fl.c.flc_type);
 	if (error)
 		goto out_putf;
 
 	can_sleep = !(cmd & LOCK_NB);
 	if (can_sleep)
-		fl.fl_flags |= FL_SLEEP;
+		fl.c.flc_flags |= FL_SLEEP;
 
 	if (f.file->f_op->flock)
 		error = f.file->f_op->flock(f.file,
@@ -2130,7 +2193,7 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
  */
 int vfs_test_lock(struct file *filp, struct file_lock *fl)
 {
-	WARN_ON_ONCE(filp != fl->fl_file);
+	WARN_ON_ONCE(filp != fl->c.flc_file);
 	if (filp->f_op->lock)
 		return filp->f_op->lock(filp, F_GETLK, fl);
 	posix_test_lock(filp, fl);
@@ -2145,25 +2208,28 @@ EXPORT_SYMBOL_GPL(vfs_test_lock);
  *
  * Used to translate a fl_pid into a namespace virtual pid number
  */
-static pid_t locks_translate_pid(struct file_lock *fl, struct pid_namespace *ns)
+static pid_t locks_translate_pid(struct file_lock_core *fl, struct pid_namespace *ns)
 {
 	pid_t vnr;
 	struct pid *pid;
 
-	if (IS_OFDLCK(fl))
+	if (fl->flc_flags & FL_OFDLCK)
 		return -1;
-	if (IS_REMOTELCK(fl))
-		return fl->fl_pid;
+
+	/* Remote locks report a negative pid value */
+	if (fl->flc_pid <= 0)
+		return fl->flc_pid;
+
 	/*
 	 * If the flock owner process is dead and its pid has been already
 	 * freed, the translation below won't work, but we still want to show
 	 * flock owner pid number in init pidns.
 	 */
 	if (ns == &init_pid_ns)
-		return (pid_t)fl->fl_pid;
+		return (pid_t) fl->flc_pid;
 
 	rcu_read_lock();
-	pid = find_pid_ns(fl->fl_pid, &init_pid_ns);
+	pid = find_pid_ns(fl->flc_pid, &init_pid_ns);
 	vnr = pid_nr_ns(pid, ns);
 	rcu_read_unlock();
 	return vnr;
@@ -2171,7 +2237,7 @@ static pid_t locks_translate_pid(struct file_lock *fl, struct pid_namespace *ns)
 
 static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl)
 {
-	flock->l_pid = locks_translate_pid(fl, task_active_pid_ns(current));
+	flock->l_pid = locks_translate_pid(&fl->c, task_active_pid_ns(current));
 #if BITS_PER_LONG == 32
 	/*
 	 * Make sure we can represent the posix lock via
@@ -2186,19 +2252,19 @@ static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl)
 	flock->l_len = fl->fl_end == OFFSET_MAX ? 0 :
 		fl->fl_end - fl->fl_start + 1;
 	flock->l_whence = 0;
-	flock->l_type = fl->fl_type;
+	flock->l_type = fl->c.flc_type;
 	return 0;
 }
 
 #if BITS_PER_LONG == 32
 static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl)
 {
-	flock->l_pid = locks_translate_pid(fl, task_active_pid_ns(current));
+	flock->l_pid = locks_translate_pid(&fl->c, task_active_pid_ns(current));
 	flock->l_start = fl->fl_start;
 	flock->l_len = fl->fl_end == OFFSET_MAX ? 0 :
 		fl->fl_end - fl->fl_start + 1;
 	flock->l_whence = 0;
-	flock->l_type = fl->fl_type;
+	flock->l_type = fl->c.flc_type;
 }
 #endif
 
@@ -2227,16 +2293,16 @@ int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock *flock)
 		if (flock->l_pid != 0)
 			goto out;
 
-		fl->fl_flags |= FL_OFDLCK;
-		fl->fl_owner = filp;
+		fl->c.flc_flags |= FL_OFDLCK;
+		fl->c.flc_owner = filp;
 	}
 
 	error = vfs_test_lock(filp, fl);
 	if (error)
 		goto out;
 
-	flock->l_type = fl->fl_type;
-	if (fl->fl_type != F_UNLCK) {
+	flock->l_type = fl->c.flc_type;
+	if (fl->c.flc_type != F_UNLCK) {
 		error = posix_lock_to_flock(flock, fl);
 		if (error)
 			goto out;
@@ -2283,7 +2349,7 @@ out:
  */
 int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf)
 {
-	WARN_ON_ONCE(filp != fl->fl_file);
+	WARN_ON_ONCE(filp != fl->c.flc_file);
 	if (filp->f_op->lock)
 		return filp->f_op->lock(filp, cmd, fl);
 	else
@@ -2296,7 +2362,7 @@ static int do_lock_file_wait(struct file *filp, unsigned int cmd,
 {
 	int error;
 
-	error = security_file_lock(filp, fl->fl_type);
+	error = security_file_lock(filp, fl->c.flc_type);
 	if (error)
 		return error;
 
@@ -2304,8 +2370,8 @@ static int do_lock_file_wait(struct file *filp, unsigned int cmd,
 		error = vfs_lock_file(filp, cmd, fl, NULL);
 		if (error != FILE_LOCK_DEFERRED)
 			break;
-		error = wait_event_interruptible(fl->fl_wait,
-					list_empty(&fl->fl_blocked_member));
+		error = wait_event_interruptible(fl->c.flc_wait,
+						 list_empty(&fl->c.flc_blocked_member));
 		if (error)
 			break;
 	}
@@ -2318,13 +2384,13 @@ static int do_lock_file_wait(struct file *filp, unsigned int cmd,
 static int
 check_fmode_for_setlk(struct file_lock *fl)
 {
-	switch (fl->fl_type) {
+	switch (fl->c.flc_type) {
 	case F_RDLCK:
-		if (!(fl->fl_file->f_mode & FMODE_READ))
+		if (!(fl->c.flc_file->f_mode & FMODE_READ))
 			return -EBADF;
 		break;
 	case F_WRLCK:
-		if (!(fl->fl_file->f_mode & FMODE_WRITE))
+		if (!(fl->c.flc_file->f_mode & FMODE_WRITE))
 			return -EBADF;
 	}
 	return 0;
@@ -2363,8 +2429,8 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
 			goto out;
 
 		cmd = F_SETLK;
-		file_lock->fl_flags |= FL_OFDLCK;
-		file_lock->fl_owner = filp;
+		file_lock->c.flc_flags |= FL_OFDLCK;
+		file_lock->c.flc_owner = filp;
 		break;
 	case F_OFD_SETLKW:
 		error = -EINVAL;
@@ -2372,11 +2438,11 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
 			goto out;
 
 		cmd = F_SETLKW;
-		file_lock->fl_flags |= FL_OFDLCK;
-		file_lock->fl_owner = filp;
+		file_lock->c.flc_flags |= FL_OFDLCK;
+		file_lock->c.flc_owner = filp;
 		fallthrough;
 	case F_SETLKW:
-		file_lock->fl_flags |= FL_SLEEP;
+		file_lock->c.flc_flags |= FL_SLEEP;
 	}
 
 	error = do_lock_file_wait(filp, cmd, file_lock);
@@ -2386,8 +2452,8 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
 	 * lock that was just acquired. There is no need to do that when we're
 	 * unlocking though, or for OFD locks.
 	 */
-	if (!error && file_lock->fl_type != F_UNLCK &&
-	    !(file_lock->fl_flags & FL_OFDLCK)) {
+	if (!error && file_lock->c.flc_type != F_UNLCK &&
+	    !(file_lock->c.flc_flags & FL_OFDLCK)) {
 		struct files_struct *files = current->files;
 		/*
 		 * We need that spin_lock here - it prevents reordering between
@@ -2398,7 +2464,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
 		f = files_lookup_fd_locked(files, fd);
 		spin_unlock(&files->file_lock);
 		if (f != filp) {
-			file_lock->fl_type = F_UNLCK;
+			file_lock->c.flc_type = F_UNLCK;
 			error = do_lock_file_wait(filp, cmd, file_lock);
 			WARN_ON_ONCE(error);
 			error = -EBADF;
@@ -2437,16 +2503,16 @@ int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 *flock)
 		if (flock->l_pid != 0)
 			goto out;
 
-		fl->fl_flags |= FL_OFDLCK;
-		fl->fl_owner = filp;
+		fl->c.flc_flags |= FL_OFDLCK;
+		fl->c.flc_owner = filp;
 	}
 
 	error = vfs_test_lock(filp, fl);
 	if (error)
 		goto out;
 
-	flock->l_type = fl->fl_type;
-	if (fl->fl_type != F_UNLCK)
+	flock->l_type = fl->c.flc_type;
+	if (fl->c.flc_type != F_UNLCK)
 		posix_lock_to_flock64(flock, fl);
 
 out:
@@ -2486,8 +2552,8 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
 			goto out;
 
 		cmd = F_SETLK64;
-		file_lock->fl_flags |= FL_OFDLCK;
-		file_lock->fl_owner = filp;
+		file_lock->c.flc_flags |= FL_OFDLCK;
+		file_lock->c.flc_owner = filp;
 		break;
 	case F_OFD_SETLKW:
 		error = -EINVAL;
@@ -2495,11 +2561,11 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
 			goto out;
 
 		cmd = F_SETLKW64;
-		file_lock->fl_flags |= FL_OFDLCK;
-		file_lock->fl_owner = filp;
+		file_lock->c.flc_flags |= FL_OFDLCK;
+		file_lock->c.flc_owner = filp;
 		fallthrough;
 	case F_SETLKW64:
-		file_lock->fl_flags |= FL_SLEEP;
+		file_lock->c.flc_flags |= FL_SLEEP;
 	}
 
 	error = do_lock_file_wait(filp, cmd, file_lock);
@@ -2509,8 +2575,8 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
 	 * lock that was just acquired. There is no need to do that when we're
 	 * unlocking though, or for OFD locks.
 	 */
-	if (!error && file_lock->fl_type != F_UNLCK &&
-	    !(file_lock->fl_flags & FL_OFDLCK)) {
+	if (!error && file_lock->c.flc_type != F_UNLCK &&
+	    !(file_lock->c.flc_flags & FL_OFDLCK)) {
 		struct files_struct *files = current->files;
 		/*
 		 * We need that spin_lock here - it prevents reordering between
@@ -2521,7 +2587,7 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
 		f = files_lookup_fd_locked(files, fd);
 		spin_unlock(&files->file_lock);
 		if (f != filp) {
-			file_lock->fl_type = F_UNLCK;
+			file_lock->c.flc_type = F_UNLCK;
 			error = do_lock_file_wait(filp, cmd, file_lock);
 			WARN_ON_ONCE(error);
 			error = -EBADF;
@@ -2555,13 +2621,13 @@ void locks_remove_posix(struct file *filp, fl_owner_t owner)
 		return;
 
 	locks_init_lock(&lock);
-	lock.fl_type = F_UNLCK;
-	lock.fl_flags = FL_POSIX | FL_CLOSE;
+	lock.c.flc_type = F_UNLCK;
+	lock.c.flc_flags = FL_POSIX | FL_CLOSE;
 	lock.fl_start = 0;
 	lock.fl_end = OFFSET_MAX;
-	lock.fl_owner = owner;
-	lock.fl_pid = current->tgid;
-	lock.fl_file = filp;
+	lock.c.flc_owner = owner;
+	lock.c.flc_pid = current->tgid;
+	lock.c.flc_file = filp;
 	lock.fl_ops = NULL;
 	lock.fl_lmops = NULL;
 
@@ -2584,7 +2650,7 @@ locks_remove_flock(struct file *filp, struct file_lock_context *flctx)
 		return;
 
 	flock_make_lock(filp, &fl, F_UNLCK);
-	fl.fl_flags |= FL_CLOSE;
+	fl.c.flc_flags |= FL_CLOSE;
 
 	if (filp->f_op->flock)
 		filp->f_op->flock(filp, F_SETLKW, &fl);
@@ -2599,7 +2665,7 @@ locks_remove_flock(struct file *filp, struct file_lock_context *flctx)
 static void
 locks_remove_lease(struct file *filp, struct file_lock_context *ctx)
 {
-	struct file_lock *fl, *tmp;
+	struct file_lease *fl, *tmp;
 	LIST_HEAD(dispose);
 
 	if (list_empty(&ctx->flc_lease))
@@ -2607,8 +2673,8 @@ locks_remove_lease(struct file *filp, struct file_lock_context *ctx)
 
 	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
-	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list)
-		if (filp == fl->fl_file)
+	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list)
+		if (filp == fl->c.flc_file)
 			lease_modify(fl, F_UNLCK, &dispose);
 	spin_unlock(&ctx->flc_lock);
 	percpu_up_read(&file_rwsem);
@@ -2652,7 +2718,7 @@ void locks_remove_file(struct file *filp)
  */
 int vfs_cancel_lock(struct file *filp, struct file_lock *fl)
 {
-	WARN_ON_ONCE(filp != fl->fl_file);
+	WARN_ON_ONCE(filp != fl->c.flc_file);
 	if (filp->f_op->lock)
 		return filp->f_op->lock(filp, F_CANCELLK, fl);
 	return 0;
@@ -2691,69 +2757,73 @@ struct locks_iterator {
 	loff_t	li_pos;
 };
 
-static void lock_get_status(struct seq_file *f, struct file_lock *fl,
+static void lock_get_status(struct seq_file *f, struct file_lock_core *flc,
 			    loff_t id, char *pfx, int repeat)
 {
 	struct inode *inode = NULL;
-	unsigned int fl_pid;
+	unsigned int pid;
 	struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb);
-	int type;
+	int type = flc->flc_type;
+	struct file_lock *fl = file_lock(flc);
+
+	pid = locks_translate_pid(flc, proc_pidns);
 
-	fl_pid = locks_translate_pid(fl, proc_pidns);
 	/*
 	 * If lock owner is dead (and pid is freed) or not visible in current
 	 * pidns, zero is shown as a pid value. Check lock info from
 	 * init_pid_ns to get saved lock pid value.
 	 */
-
-	if (fl->fl_file != NULL)
-		inode = file_inode(fl->fl_file);
+	if (flc->flc_file != NULL)
+		inode = file_inode(flc->flc_file);
 
 	seq_printf(f, "%lld: ", id);
 
 	if (repeat)
 		seq_printf(f, "%*s", repeat - 1 + (int)strlen(pfx), pfx);
 
-	if (IS_POSIX(fl)) {
-		if (fl->fl_flags & FL_ACCESS)
+	if (flc->flc_flags & FL_POSIX) {
+		if (flc->flc_flags & FL_ACCESS)
 			seq_puts(f, "ACCESS");
-		else if (IS_OFDLCK(fl))
+		else if (flc->flc_flags & FL_OFDLCK)
 			seq_puts(f, "OFDLCK");
 		else
 			seq_puts(f, "POSIX ");
 
 		seq_printf(f, " %s ",
 			     (inode == NULL) ? "*NOINODE*" : "ADVISORY ");
-	} else if (IS_FLOCK(fl)) {
+	} else if (flc->flc_flags & FL_FLOCK) {
 		seq_puts(f, "FLOCK  ADVISORY  ");
-	} else if (IS_LEASE(fl)) {
-		if (fl->fl_flags & FL_DELEG)
+	} else if (flc->flc_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT)) {
+		struct file_lease *lease = file_lease(flc);
+
+		type = target_leasetype(lease);
+
+		if (flc->flc_flags & FL_DELEG)
 			seq_puts(f, "DELEG  ");
 		else
 			seq_puts(f, "LEASE  ");
 
-		if (lease_breaking(fl))
+		if (lease_breaking(lease))
 			seq_puts(f, "BREAKING  ");
-		else if (fl->fl_file)
+		else if (flc->flc_file)
 			seq_puts(f, "ACTIVE    ");
 		else
 			seq_puts(f, "BREAKER   ");
 	} else {
 		seq_puts(f, "UNKNOWN UNKNOWN  ");
 	}
-	type = IS_LEASE(fl) ? target_leasetype(fl) : fl->fl_type;
 
 	seq_printf(f, "%s ", (type == F_WRLCK) ? "WRITE" :
 			     (type == F_RDLCK) ? "READ" : "UNLCK");
 	if (inode) {
 		/* userspace relies on this representation of dev_t */
-		seq_printf(f, "%d %02x:%02x:%lu ", fl_pid,
+		seq_printf(f, "%d %02x:%02x:%lu ", pid,
 				MAJOR(inode->i_sb->s_dev),
 				MINOR(inode->i_sb->s_dev), inode->i_ino);
 	} else {
-		seq_printf(f, "%d <none>:0 ", fl_pid);
+		seq_printf(f, "%d <none>:0 ", pid);
 	}
-	if (IS_POSIX(fl)) {
+	if (flc->flc_flags & FL_POSIX) {
 		if (fl->fl_end == OFFSET_MAX)
 			seq_printf(f, "%Ld EOF\n", fl->fl_start);
 		else
@@ -2763,17 +2833,18 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
 	}
 }
 
-static struct file_lock *get_next_blocked_member(struct file_lock *node)
+static struct file_lock_core *get_next_blocked_member(struct file_lock_core *node)
 {
-	struct file_lock *tmp;
+	struct file_lock_core *tmp;
 
 	/* NULL node or root node */
-	if (node == NULL || node->fl_blocker == NULL)
+	if (node == NULL || node->flc_blocker == NULL)
 		return NULL;
 
 	/* Next member in the linked list could be itself */
-	tmp = list_next_entry(node, fl_blocked_member);
-	if (list_entry_is_head(tmp, &node->fl_blocker->fl_blocked_requests, fl_blocked_member)
+	tmp = list_next_entry(node, flc_blocked_member);
+	if (list_entry_is_head(tmp, &node->flc_blocker->flc_blocked_requests,
+			       flc_blocked_member)
 		|| tmp == node) {
 		return NULL;
 	}
@@ -2784,18 +2855,18 @@ static struct file_lock *get_next_blocked_member(struct file_lock *node)
 static int locks_show(struct seq_file *f, void *v)
 {
 	struct locks_iterator *iter = f->private;
-	struct file_lock *cur, *tmp;
+	struct file_lock_core *cur, *tmp;
 	struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb);
 	int level = 0;
 
-	cur = hlist_entry(v, struct file_lock, fl_link);
+	cur = hlist_entry(v, struct file_lock_core, flc_link);
 
 	if (locks_translate_pid(cur, proc_pidns) == 0)
 		return 0;
 
-	/* View this crossed linked list as a binary tree, the first member of fl_blocked_requests
-	 * is the left child of current node, the next silibing in fl_blocked_member is the
-	 * right child, we can alse get the parent of current node from fl_blocker, so this
+	/* View this crossed linked list as a binary tree, the first member of flc_blocked_requests
+	 * is the left child of current node, the next silibing in flc_blocked_member is the
+	 * right child, we can alse get the parent of current node from flc_blocker, so this
 	 * question becomes traversal of a binary tree
 	 */
 	while (cur != NULL) {
@@ -2804,17 +2875,18 @@ static int locks_show(struct seq_file *f, void *v)
 		else
 			lock_get_status(f, cur, iter->li_pos, "", level);
 
-		if (!list_empty(&cur->fl_blocked_requests)) {
+		if (!list_empty(&cur->flc_blocked_requests)) {
 			/* Turn left */
-			cur = list_first_entry_or_null(&cur->fl_blocked_requests,
-				struct file_lock, fl_blocked_member);
+			cur = list_first_entry_or_null(&cur->flc_blocked_requests,
+						       struct file_lock_core,
+						       flc_blocked_member);
 			level++;
 		} else {
 			/* Turn right */
 			tmp = get_next_blocked_member(cur);
 			/* Fall back to parent node */
-			while (tmp == NULL && cur->fl_blocker != NULL) {
-				cur = cur->fl_blocker;
+			while (tmp == NULL && cur->flc_blocker != NULL) {
+				cur = cur->flc_blocker;
 				level--;
 				tmp = get_next_blocked_member(cur);
 			}
@@ -2829,14 +2901,13 @@ static void __show_fd_locks(struct seq_file *f,
 			struct list_head *head, int *id,
 			struct file *filp, struct files_struct *files)
 {
-	struct file_lock *fl;
+	struct file_lock_core *fl;
 
-	list_for_each_entry(fl, head, fl_list) {
+	list_for_each_entry(fl, head, flc_list) {
 
-		if (filp != fl->fl_file)
+		if (filp != fl->flc_file)
 			continue;
-		if (fl->fl_owner != files &&
-		    fl->fl_owner != filp)
+		if (fl->flc_owner != files && fl->flc_owner != filp)
 			continue;
 
 		(*id)++;
@@ -2915,6 +2986,9 @@ static int __init filelock_init(void)
 	filelock_cache = kmem_cache_create("file_lock_cache",
 			sizeof(struct file_lock), 0, SLAB_PANIC, NULL);
 
+	filelease_cache = kmem_cache_create("file_lock_cache",
+			sizeof(struct file_lease), 0, SLAB_PANIC, NULL);
+
 	for_each_possible_cpu(i) {
 		struct file_lock_list_struct *fll = per_cpu_ptr(&file_lock_list, i);
 
diff --git a/fs/mbcache.c b/fs/mbcache.c
index 82aa7a35db26..e60a840999aa 100644
--- a/fs/mbcache.c
+++ b/fs/mbcache.c
@@ -426,9 +426,7 @@ EXPORT_SYMBOL(mb_cache_destroy);
 
 static int __init mbcache_init(void)
 {
-	mb_entry_cache = kmem_cache_create("mbcache",
-				sizeof(struct mb_cache_entry), 0,
-				SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
+	mb_entry_cache = KMEM_CACHE(mb_cache_entry, SLAB_RECLAIM_ACCOUNT);
 	if (!mb_entry_cache)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 73f37f298087..7cbd2b9f4d11 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -87,7 +87,7 @@ static int __init init_inodecache(void)
 	minix_inode_cachep = kmem_cache_create("minix_inode_cache",
 					     sizeof(struct minix_inode_info),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
+						SLAB_ACCOUNT),
 					     init_once);
 	if (minix_inode_cachep == NULL)
 		return -ENOMEM;
diff --git a/fs/mnt_idmapping.c b/fs/mnt_idmapping.c
index 64c5205e2b5e..3c60f1eaca61 100644
--- a/fs/mnt_idmapping.c
+++ b/fs/mnt_idmapping.c
@@ -214,7 +214,7 @@ static int copy_mnt_idmap(struct uid_gid_map *map_from,
 	 * anything at all.
 	 */
 	if (nr_extents == 0)
-		return 0;
+		return -EINVAL;
 
 	/*
 	 * Here we know that nr_extents is greater than zero which means
diff --git a/fs/mpage.c b/fs/mpage.c
index 738882e0766d..fa8b99a199fa 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -605,6 +605,7 @@ alloc_new:
 				GFP_NOFS);
 		bio->bi_iter.bi_sector = first_block << (blkbits - 9);
 		wbc_init_bio(wbc, bio);
+		bio->bi_write_hint = inode->i_write_hint;
 	}
 
 	/*
diff --git a/fs/namei.c b/fs/namei.c
index 4e0de939fea1..d0c4a3e9278e 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1717,7 +1717,11 @@ static inline int may_lookup(struct mnt_idmap *idmap,
 {
 	if (nd->flags & LOOKUP_RCU) {
 		int err = inode_permission(idmap, nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
-		if (err != -ECHILD || !try_to_unlazy(nd))
+		if (!err)		// success, keep going
+			return 0;
+		if (!try_to_unlazy(nd))
+			return -ECHILD;	// redo it all non-lazy
+		if (err != -ECHILD)	// hard error
 			return err;
 	}
 	return inode_permission(idmap, nd->inode, MAY_EXEC);
@@ -2676,10 +2680,8 @@ static int lookup_one_common(struct mnt_idmap *idmap,
 	if (!len)
 		return -EACCES;
 
-	if (unlikely(name[0] == '.')) {
-		if (len < 2 || (len == 2 && name[1] == '.'))
-			return -EACCES;
-	}
+	if (is_dot_dotdot(name, len))
+		return -EACCES;
 
 	while (len--) {
 		unsigned int c = *(const unsigned char *)name++;
diff --git a/fs/namespace.c b/fs/namespace.c
index ef1fd6829814..5a51315c6678 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -4472,10 +4472,15 @@ static int do_mount_setattr(struct path *path, struct mount_kattr *kattr)
 	/*
 	 * If this is an attached mount make sure it's located in the callers
 	 * mount namespace. If it's not don't let the caller interact with it.
-	 * If this is a detached mount make sure it has an anonymous mount
-	 * namespace attached to it, i.e. we've created it via OPEN_TREE_CLONE.
+	 *
+	 * If this mount doesn't have a parent it's most often simply a
+	 * detached mount with an anonymous mount namespace. IOW, something
+	 * that's simply not attached yet. But there are apparently also users
+	 * that do change mount properties on the rootfs itself. That obviously
+	 * neither has a parent nor is it a detached mount so we cannot
+	 * unconditionally check for detached mounts.
 	 */
-	if (!(mnt_has_parent(mnt) ? check_mnt(mnt) : is_anon_ns(mnt->mnt_ns)))
+	if ((mnt_has_parent(mnt) || !is_anon_ns(mnt->mnt_ns)) && !check_mnt(mnt))
 		goto out;
 
 	/*
@@ -5042,13 +5047,12 @@ static struct mount *listmnt_next(struct mount *curr)
 	return node_to_mount(rb_next(&curr->mnt_node));
 }
 
-static ssize_t do_listmount(struct mount *first, struct path *orig, u64 mnt_id,
-			    u64 __user *buf, size_t bufsize,
-			    const struct path *root)
+static ssize_t do_listmount(struct mount *first, struct path *orig,
+			    u64 mnt_parent_id, u64 __user *mnt_ids,
+			    size_t nr_mnt_ids, const struct path *root)
 {
 	struct mount *r;
-	ssize_t ctr;
-	int err;
+	ssize_t ret;
 
 	/*
 	 * Don't trigger audit denials. We just want to determine what
@@ -5058,50 +5062,57 @@ static ssize_t do_listmount(struct mount *first, struct path *orig, u64 mnt_id,
 	    !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
-	err = security_sb_statfs(orig->dentry);
-	if (err)
-		return err;
+	ret = security_sb_statfs(orig->dentry);
+	if (ret)
+		return ret;
 
-	for (ctr = 0, r = first; r && ctr < bufsize; r = listmnt_next(r)) {
-		if (r->mnt_id_unique == mnt_id)
+	for (ret = 0, r = first; r && nr_mnt_ids; r = listmnt_next(r)) {
+		if (r->mnt_id_unique == mnt_parent_id)
 			continue;
 		if (!is_path_reachable(r, r->mnt.mnt_root, orig))
 			continue;
-		ctr = array_index_nospec(ctr, bufsize);
-		if (put_user(r->mnt_id_unique, buf + ctr))
+		if (put_user(r->mnt_id_unique, mnt_ids))
 			return -EFAULT;
-		if (check_add_overflow(ctr, 1, &ctr))
-			return -ERANGE;
+		mnt_ids++;
+		nr_mnt_ids--;
+		ret++;
 	}
-	return ctr;
+	return ret;
 }
 
-SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req,
-		u64 __user *, buf, size_t, bufsize, unsigned int, flags)
+SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, u64 __user *,
+		mnt_ids, size_t, nr_mnt_ids, unsigned int, flags)
 {
 	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
 	struct mnt_id_req kreq;
 	struct mount *first;
 	struct path root, orig;
-	u64 mnt_id, last_mnt_id;
+	u64 mnt_parent_id, last_mnt_id;
+	const size_t maxcount = (size_t)-1 >> 3;
 	ssize_t ret;
 
 	if (flags)
 		return -EINVAL;
 
+	if (unlikely(nr_mnt_ids > maxcount))
+		return -EFAULT;
+
+	if (!access_ok(mnt_ids, nr_mnt_ids * sizeof(*mnt_ids)))
+		return -EFAULT;
+
 	ret = copy_mnt_id_req(req, &kreq);
 	if (ret)
 		return ret;
-	mnt_id = kreq.mnt_id;
+	mnt_parent_id = kreq.mnt_id;
 	last_mnt_id = kreq.param;
 
 	down_read(&namespace_sem);
 	get_fs_root(current->fs, &root);
-	if (mnt_id == LSMT_ROOT) {
+	if (mnt_parent_id == LSMT_ROOT) {
 		orig = root;
 	} else {
 		ret = -ENOENT;
-		orig.mnt  = lookup_mnt_in_ns(mnt_id, ns);
+		orig.mnt = lookup_mnt_in_ns(mnt_parent_id, ns);
 		if (!orig.mnt)
 			goto err;
 		orig.dentry = orig.mnt->mnt_root;
@@ -5111,7 +5122,7 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req,
 	else
 		first = mnt_find_id_at(ns, last_mnt_id + 1);
 
-	ret = do_listmount(first, &orig, mnt_id, buf, bufsize, &root);
+	ret = do_listmount(first, &orig, mnt_parent_id, mnt_ids, nr_mnt_ids, &root);
 err:
 	path_put(&root);
 	up_read(&namespace_sem);
diff --git a/fs/netfs/Kconfig b/fs/netfs/Kconfig
index b4db21022cb4..bec805e0c44c 100644
--- a/fs/netfs/Kconfig
+++ b/fs/netfs/Kconfig
@@ -21,3 +21,42 @@ config NETFS_STATS
 	  multi-CPU system these may be on cachelines that keep bouncing
 	  between CPUs.  On the other hand, the stats are very useful for
 	  debugging purposes.  Saying 'Y' here is recommended.
+
+config FSCACHE
+	bool "General filesystem local caching manager"
+	depends on NETFS_SUPPORT
+	help
+	  This option enables a generic filesystem caching manager that can be
+	  used by various network and other filesystems to cache data locally.
+	  Different sorts of caches can be plugged in, depending on the
+	  resources available.
+
+	  See Documentation/filesystems/caching/fscache.rst for more information.
+
+config FSCACHE_STATS
+	bool "Gather statistical information on local caching"
+	depends on FSCACHE && PROC_FS
+	select NETFS_STATS
+	help
+	  This option causes statistical information to be gathered on local
+	  caching and exported through file:
+
+		/proc/fs/fscache/stats
+
+	  The gathering of statistics adds a certain amount of overhead to
+	  execution as there are a quite a few stats gathered, and on a
+	  multi-CPU system these may be on cachelines that keep bouncing
+	  between CPUs.  On the other hand, the stats are very useful for
+	  debugging purposes.  Saying 'Y' here is recommended.
+
+	  See Documentation/filesystems/caching/fscache.rst for more information.
+
+config FSCACHE_DEBUG
+	bool "Debug FS-Cache"
+	depends on FSCACHE
+	help
+	  This permits debugging to be dynamically enabled in the local caching
+	  management module.  If this is set, the debugging output may be
+	  enabled by setting bits in /sys/modules/fscache/parameter/debug.
+
+	  See Documentation/filesystems/caching/fscache.rst for more information.
diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile
index 386d6fb92793..d4d1d799819e 100644
--- a/fs/netfs/Makefile
+++ b/fs/netfs/Makefile
@@ -2,11 +2,29 @@
 
 netfs-y := \
 	buffered_read.o \
+	buffered_write.o \
+	direct_read.o \
+	direct_write.o \
 	io.o \
 	iterator.o \
+	locking.o \
 	main.o \
-	objects.o
+	misc.o \
+	objects.o \
+	output.o
 
 netfs-$(CONFIG_NETFS_STATS) += stats.o
 
-obj-$(CONFIG_NETFS_SUPPORT) := netfs.o
+netfs-$(CONFIG_FSCACHE) += \
+	fscache_cache.o \
+	fscache_cookie.o \
+	fscache_io.o \
+	fscache_main.o \
+	fscache_volume.o
+
+ifeq ($(CONFIG_PROC_FS),y)
+netfs-$(CONFIG_FSCACHE) += fscache_proc.o
+endif
+netfs-$(CONFIG_FSCACHE_STATS) += fscache_stats.o
+
+obj-$(CONFIG_NETFS_SUPPORT) += netfs.o
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 2cd3ccf4c439..3298c29b5548 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -16,6 +16,7 @@
 void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
 {
 	struct netfs_io_subrequest *subreq;
+	struct netfs_folio *finfo;
 	struct folio *folio;
 	pgoff_t start_page = rreq->start / PAGE_SIZE;
 	pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1;
@@ -63,6 +64,7 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
 				break;
 			}
 			if (!folio_started && test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) {
+				trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache);
 				folio_start_fscache(folio);
 				folio_started = true;
 			}
@@ -86,11 +88,20 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
 
 		if (!pg_failed) {
 			flush_dcache_folio(folio);
+			finfo = netfs_folio_info(folio);
+			if (finfo) {
+				trace_netfs_folio(folio, netfs_folio_trace_filled_gaps);
+				if (finfo->netfs_group)
+					folio_change_private(folio, finfo->netfs_group);
+				else
+					folio_detach_private(folio);
+				kfree(finfo);
+			}
 			folio_mark_uptodate(folio);
 		}
 
 		if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) {
-			if (folio_index(folio) == rreq->no_unlock_folio &&
+			if (folio->index == rreq->no_unlock_folio &&
 			    test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags))
 				_debug("no unlock");
 			else
@@ -147,6 +158,15 @@ static void netfs_rreq_expand(struct netfs_io_request *rreq,
 	}
 }
 
+/*
+ * Begin an operation, and fetch the stored zero point value from the cookie if
+ * available.
+ */
+static int netfs_begin_cache_read(struct netfs_io_request *rreq, struct netfs_inode *ctx)
+{
+	return fscache_begin_read_operation(&rreq->cache_resources, netfs_i_cookie(ctx));
+}
+
 /**
  * netfs_readahead - Helper to manage a read request
  * @ractl: The description of the readahead request
@@ -180,11 +200,9 @@ void netfs_readahead(struct readahead_control *ractl)
 	if (IS_ERR(rreq))
 		return;
 
-	if (ctx->ops->begin_cache_operation) {
-		ret = ctx->ops->begin_cache_operation(rreq);
-		if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
-			goto cleanup_free;
-	}
+	ret = netfs_begin_cache_read(rreq, ctx);
+	if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
+		goto cleanup_free;
 
 	netfs_stat(&netfs_n_rh_readahead);
 	trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl),
@@ -192,6 +210,10 @@ void netfs_readahead(struct readahead_control *ractl)
 
 	netfs_rreq_expand(rreq, ractl);
 
+	/* Set up the output buffer */
+	iov_iter_xarray(&rreq->iter, ITER_DEST, &ractl->mapping->i_pages,
+			rreq->start, rreq->len);
+
 	/* Drop the refs on the folios here rather than in the cache or
 	 * filesystem.  The locks will be dropped in netfs_rreq_unlock().
 	 */
@@ -199,6 +221,7 @@ void netfs_readahead(struct readahead_control *ractl)
 		;
 
 	netfs_begin_read(rreq, false);
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
 	return;
 
 cleanup_free:
@@ -223,12 +246,13 @@ EXPORT_SYMBOL(netfs_readahead);
  */
 int netfs_read_folio(struct file *file, struct folio *folio)
 {
-	struct address_space *mapping = folio_file_mapping(folio);
+	struct address_space *mapping = folio->mapping;
 	struct netfs_io_request *rreq;
 	struct netfs_inode *ctx = netfs_inode(mapping->host);
+	struct folio *sink = NULL;
 	int ret;
 
-	_enter("%lx", folio_index(folio));
+	_enter("%lx", folio->index);
 
 	rreq = netfs_alloc_request(mapping, file,
 				   folio_file_pos(folio), folio_size(folio),
@@ -238,15 +262,64 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 		goto alloc_error;
 	}
 
-	if (ctx->ops->begin_cache_operation) {
-		ret = ctx->ops->begin_cache_operation(rreq);
-		if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
-			goto discard;
-	}
+	ret = netfs_begin_cache_read(rreq, ctx);
+	if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
+		goto discard;
 
 	netfs_stat(&netfs_n_rh_readpage);
 	trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage);
-	return netfs_begin_read(rreq, true);
+
+	/* Set up the output buffer */
+	if (folio_test_dirty(folio)) {
+		/* Handle someone trying to read from an unflushed streaming
+		 * write.  We fiddle the buffer so that a gap at the beginning
+		 * and/or a gap at the end get copied to, but the middle is
+		 * discarded.
+		 */
+		struct netfs_folio *finfo = netfs_folio_info(folio);
+		struct bio_vec *bvec;
+		unsigned int from = finfo->dirty_offset;
+		unsigned int to = from + finfo->dirty_len;
+		unsigned int off = 0, i = 0;
+		size_t flen = folio_size(folio);
+		size_t nr_bvec = flen / PAGE_SIZE + 2;
+		size_t part;
+
+		ret = -ENOMEM;
+		bvec = kmalloc_array(nr_bvec, sizeof(*bvec), GFP_KERNEL);
+		if (!bvec)
+			goto discard;
+
+		sink = folio_alloc(GFP_KERNEL, 0);
+		if (!sink)
+			goto discard;
+
+		trace_netfs_folio(folio, netfs_folio_trace_read_gaps);
+
+		rreq->direct_bv = bvec;
+		rreq->direct_bv_count = nr_bvec;
+		if (from > 0) {
+			bvec_set_folio(&bvec[i++], folio, from, 0);
+			off = from;
+		}
+		while (off < to) {
+			part = min_t(size_t, to - off, PAGE_SIZE);
+			bvec_set_folio(&bvec[i++], sink, part, 0);
+			off += part;
+		}
+		if (to < flen)
+			bvec_set_folio(&bvec[i++], folio, flen - to, to);
+		iov_iter_bvec(&rreq->iter, ITER_DEST, bvec, i, rreq->len);
+	} else {
+		iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
+				rreq->start, rreq->len);
+	}
+
+	ret = netfs_begin_read(rreq, true);
+	if (sink)
+		folio_put(sink);
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	return ret < 0 ? ret : 0;
 
 discard:
 	netfs_put_request(rreq, false, netfs_rreq_trace_put_discard);
@@ -387,14 +460,12 @@ retry:
 		ret = PTR_ERR(rreq);
 		goto error;
 	}
-	rreq->no_unlock_folio	= folio_index(folio);
+	rreq->no_unlock_folio	= folio->index;
 	__set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags);
 
-	if (ctx->ops->begin_cache_operation) {
-		ret = ctx->ops->begin_cache_operation(rreq);
-		if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
-			goto error_put;
-	}
+	ret = netfs_begin_cache_read(rreq, ctx);
+	if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
+		goto error_put;
 
 	netfs_stat(&netfs_n_rh_write_begin);
 	trace_netfs_read(rreq, pos, len, netfs_read_trace_write_begin);
@@ -405,6 +476,10 @@ retry:
 	ractl._nr_pages = folio_nr_pages(folio);
 	netfs_rreq_expand(rreq, &ractl);
 
+	/* Set up the output buffer */
+	iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
+			rreq->start, rreq->len);
+
 	/* We hold the folio locks, so we can drop the references */
 	folio_get(folio);
 	while (readahead_folio(&ractl))
@@ -413,6 +488,7 @@ retry:
 	ret = netfs_begin_read(rreq, true);
 	if (ret < 0)
 		goto error;
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
 
 have_folio:
 	ret = folio_wait_fscache_killable(folio);
@@ -434,3 +510,124 @@ error:
 	return ret;
 }
 EXPORT_SYMBOL(netfs_write_begin);
+
+/*
+ * Preload the data into a page we're proposing to write into.
+ */
+int netfs_prefetch_for_write(struct file *file, struct folio *folio,
+			     size_t offset, size_t len)
+{
+	struct netfs_io_request *rreq;
+	struct address_space *mapping = folio->mapping;
+	struct netfs_inode *ctx = netfs_inode(mapping->host);
+	unsigned long long start = folio_pos(folio);
+	size_t flen = folio_size(folio);
+	int ret;
+
+	_enter("%zx @%llx", flen, start);
+
+	ret = -ENOMEM;
+
+	rreq = netfs_alloc_request(mapping, file, start, flen,
+				   NETFS_READ_FOR_WRITE);
+	if (IS_ERR(rreq)) {
+		ret = PTR_ERR(rreq);
+		goto error;
+	}
+
+	rreq->no_unlock_folio = folio->index;
+	__set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags);
+	ret = netfs_begin_cache_read(rreq, ctx);
+	if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
+		goto error_put;
+
+	netfs_stat(&netfs_n_rh_write_begin);
+	trace_netfs_read(rreq, start, flen, netfs_read_trace_prefetch_for_write);
+
+	/* Set up the output buffer */
+	iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
+			rreq->start, rreq->len);
+
+	ret = netfs_begin_read(rreq, true);
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	return ret;
+
+error_put:
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_discard);
+error:
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/**
+ * netfs_buffered_read_iter - Filesystem buffered I/O read routine
+ * @iocb: kernel I/O control block
+ * @iter: destination for the data read
+ *
+ * This is the ->read_iter() routine for all filesystems that can use the page
+ * cache directly.
+ *
+ * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall be
+ * returned when no data can be read without waiting for I/O requests to
+ * complete; it doesn't prevent readahead.
+ *
+ * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O requests
+ * shall be made for the read or for readahead.  When no data can be read,
+ * -EAGAIN shall be returned.  When readahead would be triggered, a partial,
+ * possibly empty read shall be returned.
+ *
+ * Return:
+ * * number of bytes copied, even for partial reads
+ * * negative error code (or 0 if IOCB_NOIO) if nothing was read
+ */
+ssize_t netfs_buffered_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct netfs_inode *ictx = netfs_inode(inode);
+	ssize_t ret;
+
+	if (WARN_ON_ONCE((iocb->ki_flags & IOCB_DIRECT) ||
+			 test_bit(NETFS_ICTX_UNBUFFERED, &ictx->flags)))
+		return -EINVAL;
+
+	ret = netfs_start_io_read(inode);
+	if (ret == 0) {
+		ret = filemap_read(iocb, iter, 0);
+		netfs_end_io_read(inode);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(netfs_buffered_read_iter);
+
+/**
+ * netfs_file_read_iter - Generic filesystem read routine
+ * @iocb: kernel I/O control block
+ * @iter: destination for the data read
+ *
+ * This is the ->read_iter() routine for all filesystems that can use the page
+ * cache directly.
+ *
+ * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall be
+ * returned when no data can be read without waiting for I/O requests to
+ * complete; it doesn't prevent readahead.
+ *
+ * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O requests
+ * shall be made for the read or for readahead.  When no data can be read,
+ * -EAGAIN shall be returned.  When readahead would be triggered, a partial,
+ * possibly empty read shall be returned.
+ *
+ * Return:
+ * * number of bytes copied, even for partial reads
+ * * negative error code (or 0 if IOCB_NOIO) if nothing was read
+ */
+ssize_t netfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct netfs_inode *ictx = netfs_inode(iocb->ki_filp->f_mapping->host);
+
+	if ((iocb->ki_flags & IOCB_DIRECT) ||
+	    test_bit(NETFS_ICTX_UNBUFFERED, &ictx->flags))
+		return netfs_unbuffered_read_iter(iocb, iter);
+
+	return netfs_buffered_read_iter(iocb, iter);
+}
+EXPORT_SYMBOL(netfs_file_read_iter);
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
new file mode 100644
index 000000000000..9a0d32e4b422
--- /dev/null
+++ b/fs/netfs/buffered_write.c
@@ -0,0 +1,1257 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Network filesystem high-level write support.
+ *
+ * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/export.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/slab.h>
+#include <linux/pagevec.h>
+#include "internal.h"
+
+/*
+ * Determined write method.  Adjust netfs_folio_traces if this is changed.
+ */
+enum netfs_how_to_modify {
+	NETFS_FOLIO_IS_UPTODATE,	/* Folio is uptodate already */
+	NETFS_JUST_PREFETCH,		/* We have to read the folio anyway */
+	NETFS_WHOLE_FOLIO_MODIFY,	/* We're going to overwrite the whole folio */
+	NETFS_MODIFY_AND_CLEAR,		/* We can assume there is no data to be downloaded. */
+	NETFS_STREAMING_WRITE,		/* Store incomplete data in non-uptodate page. */
+	NETFS_STREAMING_WRITE_CONT,	/* Continue streaming write. */
+	NETFS_FLUSH_CONTENT,		/* Flush incompatible content. */
+};
+
+static void netfs_cleanup_buffered_write(struct netfs_io_request *wreq);
+
+static void netfs_set_group(struct folio *folio, struct netfs_group *netfs_group)
+{
+	if (netfs_group && !folio_get_private(folio))
+		folio_attach_private(folio, netfs_get_group(netfs_group));
+}
+
+#if IS_ENABLED(CONFIG_FSCACHE)
+static void netfs_folio_start_fscache(bool caching, struct folio *folio)
+{
+	if (caching)
+		folio_start_fscache(folio);
+}
+#else
+static void netfs_folio_start_fscache(bool caching, struct folio *folio)
+{
+}
+#endif
+
+/*
+ * Decide how we should modify a folio.  We might be attempting to do
+ * write-streaming, in which case we don't want to a local RMW cycle if we can
+ * avoid it.  If we're doing local caching or content crypto, we award that
+ * priority over avoiding RMW.  If the file is open readably, then we also
+ * assume that we may want to read what we wrote.
+ */
+static enum netfs_how_to_modify netfs_how_to_modify(struct netfs_inode *ctx,
+						    struct file *file,
+						    struct folio *folio,
+						    void *netfs_group,
+						    size_t flen,
+						    size_t offset,
+						    size_t len,
+						    bool maybe_trouble)
+{
+	struct netfs_folio *finfo = netfs_folio_info(folio);
+	loff_t pos = folio_file_pos(folio);
+
+	_enter("");
+
+	if (netfs_folio_group(folio) != netfs_group)
+		return NETFS_FLUSH_CONTENT;
+
+	if (folio_test_uptodate(folio))
+		return NETFS_FOLIO_IS_UPTODATE;
+
+	if (pos >= ctx->zero_point)
+		return NETFS_MODIFY_AND_CLEAR;
+
+	if (!maybe_trouble && offset == 0 && len >= flen)
+		return NETFS_WHOLE_FOLIO_MODIFY;
+
+	if (file->f_mode & FMODE_READ)
+		goto no_write_streaming;
+	if (test_bit(NETFS_ICTX_NO_WRITE_STREAMING, &ctx->flags))
+		goto no_write_streaming;
+
+	if (netfs_is_cache_enabled(ctx)) {
+		/* We don't want to get a streaming write on a file that loses
+		 * caching service temporarily because the backing store got
+		 * culled.
+		 */
+		if (!test_bit(NETFS_ICTX_NO_WRITE_STREAMING, &ctx->flags))
+			set_bit(NETFS_ICTX_NO_WRITE_STREAMING, &ctx->flags);
+		goto no_write_streaming;
+	}
+
+	if (!finfo)
+		return NETFS_STREAMING_WRITE;
+
+	/* We can continue a streaming write only if it continues on from the
+	 * previous.  If it overlaps, we must flush lest we suffer a partial
+	 * copy and disjoint dirty regions.
+	 */
+	if (offset == finfo->dirty_offset + finfo->dirty_len)
+		return NETFS_STREAMING_WRITE_CONT;
+	return NETFS_FLUSH_CONTENT;
+
+no_write_streaming:
+	if (finfo) {
+		netfs_stat(&netfs_n_wh_wstream_conflict);
+		return NETFS_FLUSH_CONTENT;
+	}
+	return NETFS_JUST_PREFETCH;
+}
+
+/*
+ * Grab a folio for writing and lock it.  Attempt to allocate as large a folio
+ * as possible to hold as much of the remaining length as possible in one go.
+ */
+static struct folio *netfs_grab_folio_for_write(struct address_space *mapping,
+						loff_t pos, size_t part)
+{
+	pgoff_t index = pos / PAGE_SIZE;
+	fgf_t fgp_flags = FGP_WRITEBEGIN;
+
+	if (mapping_large_folio_support(mapping))
+		fgp_flags |= fgf_set_order(pos % PAGE_SIZE + part);
+
+	return __filemap_get_folio(mapping, index, fgp_flags,
+				   mapping_gfp_mask(mapping));
+}
+
+/**
+ * netfs_perform_write - Copy data into the pagecache.
+ * @iocb: The operation parameters
+ * @iter: The source buffer
+ * @netfs_group: Grouping for dirty pages (eg. ceph snaps).
+ *
+ * Copy data into pagecache pages attached to the inode specified by @iocb.
+ * The caller must hold appropriate inode locks.
+ *
+ * Dirty pages are tagged with a netfs_folio struct if they're not up to date
+ * to indicate the range modified.  Dirty pages may also be tagged with a
+ * netfs-specific grouping such that data from an old group gets flushed before
+ * a new one is started.
+ */
+ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
+			    struct netfs_group *netfs_group)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	struct address_space *mapping = inode->i_mapping;
+	struct netfs_inode *ctx = netfs_inode(inode);
+	struct writeback_control wbc = {
+		.sync_mode	= WB_SYNC_NONE,
+		.for_sync	= true,
+		.nr_to_write	= LONG_MAX,
+		.range_start	= iocb->ki_pos,
+		.range_end	= iocb->ki_pos + iter->count,
+	};
+	struct netfs_io_request *wreq = NULL;
+	struct netfs_folio *finfo;
+	struct folio *folio;
+	enum netfs_how_to_modify howto;
+	enum netfs_folio_trace trace;
+	unsigned int bdp_flags = (iocb->ki_flags & IOCB_SYNC) ? 0: BDP_ASYNC;
+	ssize_t written = 0, ret;
+	loff_t i_size, pos = iocb->ki_pos, from, to;
+	size_t max_chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER;
+	bool maybe_trouble = false;
+
+	if (unlikely(test_bit(NETFS_ICTX_WRITETHROUGH, &ctx->flags) ||
+		     iocb->ki_flags & (IOCB_DSYNC | IOCB_SYNC))
+	    ) {
+		if (pos < i_size_read(inode)) {
+			ret = filemap_write_and_wait_range(mapping, pos, pos + iter->count);
+			if (ret < 0) {
+				goto out;
+			}
+		}
+
+		wbc_attach_fdatawrite_inode(&wbc, mapping->host);
+
+		wreq = netfs_begin_writethrough(iocb, iter->count);
+		if (IS_ERR(wreq)) {
+			wbc_detach_inode(&wbc);
+			ret = PTR_ERR(wreq);
+			wreq = NULL;
+			goto out;
+		}
+		if (!is_sync_kiocb(iocb))
+			wreq->iocb = iocb;
+		wreq->cleanup = netfs_cleanup_buffered_write;
+	}
+
+	do {
+		size_t flen;
+		size_t offset;	/* Offset into pagecache folio */
+		size_t part;	/* Bytes to write to folio */
+		size_t copied;	/* Bytes copied from user */
+
+		ret = balance_dirty_pages_ratelimited_flags(mapping, bdp_flags);
+		if (unlikely(ret < 0))
+			break;
+
+		offset = pos & (max_chunk - 1);
+		part = min(max_chunk - offset, iov_iter_count(iter));
+
+		/* Bring in the user pages that we will copy from _first_ lest
+		 * we hit a nasty deadlock on copying from the same page as
+		 * we're writing to, without it being marked uptodate.
+		 *
+		 * Not only is this an optimisation, but it is also required to
+		 * check that the address is actually valid, when atomic
+		 * usercopies are used below.
+		 *
+		 * We rely on the page being held onto long enough by the LRU
+		 * that we can grab it below if this causes it to be read.
+		 */
+		ret = -EFAULT;
+		if (unlikely(fault_in_iov_iter_readable(iter, part) == part))
+			break;
+
+		folio = netfs_grab_folio_for_write(mapping, pos, part);
+		if (IS_ERR(folio)) {
+			ret = PTR_ERR(folio);
+			break;
+		}
+
+		flen = folio_size(folio);
+		offset = pos & (flen - 1);
+		part = min_t(size_t, flen - offset, part);
+
+		if (signal_pending(current)) {
+			ret = written ? -EINTR : -ERESTARTSYS;
+			goto error_folio_unlock;
+		}
+
+		/* See if we need to prefetch the area we're going to modify.
+		 * We need to do this before we get a lock on the folio in case
+		 * there's more than one writer competing for the same cache
+		 * block.
+		 */
+		howto = netfs_how_to_modify(ctx, file, folio, netfs_group,
+					    flen, offset, part, maybe_trouble);
+		_debug("howto %u", howto);
+		switch (howto) {
+		case NETFS_JUST_PREFETCH:
+			ret = netfs_prefetch_for_write(file, folio, offset, part);
+			if (ret < 0) {
+				_debug("prefetch = %zd", ret);
+				goto error_folio_unlock;
+			}
+			break;
+		case NETFS_FOLIO_IS_UPTODATE:
+		case NETFS_WHOLE_FOLIO_MODIFY:
+		case NETFS_STREAMING_WRITE_CONT:
+			break;
+		case NETFS_MODIFY_AND_CLEAR:
+			zero_user_segment(&folio->page, 0, offset);
+			break;
+		case NETFS_STREAMING_WRITE:
+			ret = -EIO;
+			if (WARN_ON(folio_get_private(folio)))
+				goto error_folio_unlock;
+			break;
+		case NETFS_FLUSH_CONTENT:
+			trace_netfs_folio(folio, netfs_flush_content);
+			from = folio_pos(folio);
+			to = from + folio_size(folio) - 1;
+			folio_unlock(folio);
+			folio_put(folio);
+			ret = filemap_write_and_wait_range(mapping, from, to);
+			if (ret < 0)
+				goto error_folio_unlock;
+			continue;
+		}
+
+		if (mapping_writably_mapped(mapping))
+			flush_dcache_folio(folio);
+
+		copied = copy_folio_from_iter_atomic(folio, offset, part, iter);
+
+		flush_dcache_folio(folio);
+
+		/* Deal with a (partially) failed copy */
+		if (copied == 0) {
+			ret = -EFAULT;
+			goto error_folio_unlock;
+		}
+
+		trace = (enum netfs_folio_trace)howto;
+		switch (howto) {
+		case NETFS_FOLIO_IS_UPTODATE:
+		case NETFS_JUST_PREFETCH:
+			netfs_set_group(folio, netfs_group);
+			break;
+		case NETFS_MODIFY_AND_CLEAR:
+			zero_user_segment(&folio->page, offset + copied, flen);
+			netfs_set_group(folio, netfs_group);
+			folio_mark_uptodate(folio);
+			break;
+		case NETFS_WHOLE_FOLIO_MODIFY:
+			if (unlikely(copied < part)) {
+				maybe_trouble = true;
+				iov_iter_revert(iter, copied);
+				copied = 0;
+				goto retry;
+			}
+			netfs_set_group(folio, netfs_group);
+			folio_mark_uptodate(folio);
+			break;
+		case NETFS_STREAMING_WRITE:
+			if (offset == 0 && copied == flen) {
+				netfs_set_group(folio, netfs_group);
+				folio_mark_uptodate(folio);
+				trace = netfs_streaming_filled_page;
+				break;
+			}
+			finfo = kzalloc(sizeof(*finfo), GFP_KERNEL);
+			if (!finfo) {
+				iov_iter_revert(iter, copied);
+				ret = -ENOMEM;
+				goto error_folio_unlock;
+			}
+			finfo->netfs_group = netfs_get_group(netfs_group);
+			finfo->dirty_offset = offset;
+			finfo->dirty_len = copied;
+			folio_attach_private(folio, (void *)((unsigned long)finfo |
+							     NETFS_FOLIO_INFO));
+			break;
+		case NETFS_STREAMING_WRITE_CONT:
+			finfo = netfs_folio_info(folio);
+			finfo->dirty_len += copied;
+			if (finfo->dirty_offset == 0 && finfo->dirty_len == flen) {
+				if (finfo->netfs_group)
+					folio_change_private(folio, finfo->netfs_group);
+				else
+					folio_detach_private(folio);
+				folio_mark_uptodate(folio);
+				kfree(finfo);
+				trace = netfs_streaming_cont_filled_page;
+			}
+			break;
+		default:
+			WARN(true, "Unexpected modify type %u ix=%lx\n",
+			     howto, folio->index);
+			ret = -EIO;
+			goto error_folio_unlock;
+		}
+
+		trace_netfs_folio(folio, trace);
+
+		/* Update the inode size if we moved the EOF marker */
+		i_size = i_size_read(inode);
+		pos += copied;
+		if (pos > i_size) {
+			if (ctx->ops->update_i_size) {
+				ctx->ops->update_i_size(inode, pos);
+			} else {
+				i_size_write(inode, pos);
+#if IS_ENABLED(CONFIG_FSCACHE)
+				fscache_update_cookie(ctx->cache, NULL, &pos);
+#endif
+			}
+		}
+		written += copied;
+
+		if (likely(!wreq)) {
+			folio_mark_dirty(folio);
+		} else {
+			if (folio_test_dirty(folio))
+				/* Sigh.  mmap. */
+				folio_clear_dirty_for_io(folio);
+			/* We make multiple writes to the folio... */
+			if (!folio_test_writeback(folio)) {
+				folio_wait_fscache(folio);
+				folio_start_writeback(folio);
+				folio_start_fscache(folio);
+				if (wreq->iter.count == 0)
+					trace_netfs_folio(folio, netfs_folio_trace_wthru);
+				else
+					trace_netfs_folio(folio, netfs_folio_trace_wthru_plus);
+			}
+			netfs_advance_writethrough(wreq, copied,
+						   offset + copied == flen);
+		}
+	retry:
+		folio_unlock(folio);
+		folio_put(folio);
+		folio = NULL;
+
+		cond_resched();
+	} while (iov_iter_count(iter));
+
+out:
+	if (unlikely(wreq)) {
+		ret = netfs_end_writethrough(wreq, iocb);
+		wbc_detach_inode(&wbc);
+		if (ret == -EIOCBQUEUED)
+			return ret;
+	}
+
+	iocb->ki_pos += written;
+	_leave(" = %zd [%zd]", written, ret);
+	return written ? written : ret;
+
+error_folio_unlock:
+	folio_unlock(folio);
+	folio_put(folio);
+	goto out;
+}
+EXPORT_SYMBOL(netfs_perform_write);
+
+/**
+ * netfs_buffered_write_iter_locked - write data to a file
+ * @iocb:	IO state structure (file, offset, etc.)
+ * @from:	iov_iter with data to write
+ * @netfs_group: Grouping for dirty pages (eg. ceph snaps).
+ *
+ * This function does all the work needed for actually writing data to a
+ * file. It does all basic checks, removes SUID from the file, updates
+ * modification times and calls proper subroutines depending on whether we
+ * do direct IO or a standard buffered write.
+ *
+ * The caller must hold appropriate locks around this function and have called
+ * generic_write_checks() already.  The caller is also responsible for doing
+ * any necessary syncing afterwards.
+ *
+ * This function does *not* take care of syncing data in case of O_SYNC write.
+ * A caller has to handle it. This is mainly due to the fact that we want to
+ * avoid syncing under i_rwsem.
+ *
+ * Return:
+ * * number of bytes written, even for truncated writes
+ * * negative error code if no data has been written at all
+ */
+ssize_t netfs_buffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *from,
+					 struct netfs_group *netfs_group)
+{
+	struct file *file = iocb->ki_filp;
+	ssize_t ret;
+
+	trace_netfs_write_iter(iocb, from);
+
+	ret = file_remove_privs(file);
+	if (ret)
+		return ret;
+
+	ret = file_update_time(file);
+	if (ret)
+		return ret;
+
+	return netfs_perform_write(iocb, from, netfs_group);
+}
+EXPORT_SYMBOL(netfs_buffered_write_iter_locked);
+
+/**
+ * netfs_file_write_iter - write data to a file
+ * @iocb: IO state structure
+ * @from: iov_iter with data to write
+ *
+ * Perform a write to a file, writing into the pagecache if possible and doing
+ * an unbuffered write instead if not.
+ *
+ * Return:
+ * * Negative error code if no data has been written at all of
+ *   vfs_fsync_range() failed for a synchronous write
+ * * Number of bytes written, even for truncated writes
+ */
+ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	struct netfs_inode *ictx = netfs_inode(inode);
+	ssize_t ret;
+
+	_enter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode));
+
+	if (!iov_iter_count(from))
+		return 0;
+
+	if ((iocb->ki_flags & IOCB_DIRECT) ||
+	    test_bit(NETFS_ICTX_UNBUFFERED, &ictx->flags))
+		return netfs_unbuffered_write_iter(iocb, from);
+
+	ret = netfs_start_io_write(inode);
+	if (ret < 0)
+		return ret;
+
+	ret = generic_write_checks(iocb, from);
+	if (ret > 0)
+		ret = netfs_buffered_write_iter_locked(iocb, from, NULL);
+	netfs_end_io_write(inode);
+	if (ret > 0)
+		ret = generic_write_sync(iocb, ret);
+	return ret;
+}
+EXPORT_SYMBOL(netfs_file_write_iter);
+
+/*
+ * Notification that a previously read-only page is about to become writable.
+ * Note that the caller indicates a single page of a multipage folio.
+ */
+vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group)
+{
+	struct folio *folio = page_folio(vmf->page);
+	struct file *file = vmf->vma->vm_file;
+	struct inode *inode = file_inode(file);
+	vm_fault_t ret = VM_FAULT_RETRY;
+	int err;
+
+	_enter("%lx", folio->index);
+
+	sb_start_pagefault(inode->i_sb);
+
+	if (folio_wait_writeback_killable(folio))
+		goto out;
+
+	if (folio_lock_killable(folio) < 0)
+		goto out;
+
+	/* Can we see a streaming write here? */
+	if (WARN_ON(!folio_test_uptodate(folio))) {
+		ret = VM_FAULT_SIGBUS | VM_FAULT_LOCKED;
+		goto out;
+	}
+
+	if (netfs_folio_group(folio) != netfs_group) {
+		folio_unlock(folio);
+		err = filemap_fdatawait_range(inode->i_mapping,
+					      folio_pos(folio),
+					      folio_pos(folio) + folio_size(folio));
+		switch (err) {
+		case 0:
+			ret = VM_FAULT_RETRY;
+			goto out;
+		case -ENOMEM:
+			ret = VM_FAULT_OOM;
+			goto out;
+		default:
+			ret = VM_FAULT_SIGBUS;
+			goto out;
+		}
+	}
+
+	if (folio_test_dirty(folio))
+		trace_netfs_folio(folio, netfs_folio_trace_mkwrite_plus);
+	else
+		trace_netfs_folio(folio, netfs_folio_trace_mkwrite);
+	netfs_set_group(folio, netfs_group);
+	file_update_time(file);
+	ret = VM_FAULT_LOCKED;
+out:
+	sb_end_pagefault(inode->i_sb);
+	return ret;
+}
+EXPORT_SYMBOL(netfs_page_mkwrite);
+
+/*
+ * Kill all the pages in the given range
+ */
+static void netfs_kill_pages(struct address_space *mapping,
+			     loff_t start, loff_t len)
+{
+	struct folio *folio;
+	pgoff_t index = start / PAGE_SIZE;
+	pgoff_t last = (start + len - 1) / PAGE_SIZE, next;
+
+	_enter("%llx-%llx", start, start + len - 1);
+
+	do {
+		_debug("kill %lx (to %lx)", index, last);
+
+		folio = filemap_get_folio(mapping, index);
+		if (IS_ERR(folio)) {
+			next = index + 1;
+			continue;
+		}
+
+		next = folio_next_index(folio);
+
+		trace_netfs_folio(folio, netfs_folio_trace_kill);
+		folio_clear_uptodate(folio);
+		if (folio_test_fscache(folio))
+			folio_end_fscache(folio);
+		folio_end_writeback(folio);
+		folio_lock(folio);
+		generic_error_remove_folio(mapping, folio);
+		folio_unlock(folio);
+		folio_put(folio);
+
+	} while (index = next, index <= last);
+
+	_leave("");
+}
+
+/*
+ * Redirty all the pages in a given range.
+ */
+static void netfs_redirty_pages(struct address_space *mapping,
+				loff_t start, loff_t len)
+{
+	struct folio *folio;
+	pgoff_t index = start / PAGE_SIZE;
+	pgoff_t last = (start + len - 1) / PAGE_SIZE, next;
+
+	_enter("%llx-%llx", start, start + len - 1);
+
+	do {
+		_debug("redirty %llx @%llx", len, start);
+
+		folio = filemap_get_folio(mapping, index);
+		if (IS_ERR(folio)) {
+			next = index + 1;
+			continue;
+		}
+
+		next = folio_next_index(folio);
+		trace_netfs_folio(folio, netfs_folio_trace_redirty);
+		filemap_dirty_folio(mapping, folio);
+		if (folio_test_fscache(folio))
+			folio_end_fscache(folio);
+		folio_end_writeback(folio);
+		folio_put(folio);
+	} while (index = next, index <= last);
+
+	balance_dirty_pages_ratelimited(mapping);
+
+	_leave("");
+}
+
+/*
+ * Completion of write to server
+ */
+static void netfs_pages_written_back(struct netfs_io_request *wreq)
+{
+	struct address_space *mapping = wreq->mapping;
+	struct netfs_folio *finfo;
+	struct netfs_group *group = NULL;
+	struct folio *folio;
+	pgoff_t last;
+	int gcount = 0;
+
+	XA_STATE(xas, &mapping->i_pages, wreq->start / PAGE_SIZE);
+
+	_enter("%llx-%llx", wreq->start, wreq->start + wreq->len);
+
+	rcu_read_lock();
+
+	last = (wreq->start + wreq->len - 1) / PAGE_SIZE;
+	xas_for_each(&xas, folio, last) {
+		WARN(!folio_test_writeback(folio),
+		     "bad %zx @%llx page %lx %lx\n",
+		     wreq->len, wreq->start, folio->index, last);
+
+		if ((finfo = netfs_folio_info(folio))) {
+			/* Streaming writes cannot be redirtied whilst under
+			 * writeback, so discard the streaming record.
+			 */
+			folio_detach_private(folio);
+			group = finfo->netfs_group;
+			gcount++;
+			trace_netfs_folio(folio, netfs_folio_trace_clear_s);
+			kfree(finfo);
+		} else if ((group = netfs_folio_group(folio))) {
+			/* Need to detach the group pointer if the page didn't
+			 * get redirtied.  If it has been redirtied, then it
+			 * must be within the same group.
+			 */
+			if (folio_test_dirty(folio)) {
+				trace_netfs_folio(folio, netfs_folio_trace_redirtied);
+				goto end_wb;
+			}
+			if (folio_trylock(folio)) {
+				if (!folio_test_dirty(folio)) {
+					folio_detach_private(folio);
+					gcount++;
+					trace_netfs_folio(folio, netfs_folio_trace_clear_g);
+				} else {
+					trace_netfs_folio(folio, netfs_folio_trace_redirtied);
+				}
+				folio_unlock(folio);
+				goto end_wb;
+			}
+
+			xas_pause(&xas);
+			rcu_read_unlock();
+			folio_lock(folio);
+			if (!folio_test_dirty(folio)) {
+				folio_detach_private(folio);
+				gcount++;
+				trace_netfs_folio(folio, netfs_folio_trace_clear_g);
+			} else {
+				trace_netfs_folio(folio, netfs_folio_trace_redirtied);
+			}
+			folio_unlock(folio);
+			rcu_read_lock();
+		} else {
+			trace_netfs_folio(folio, netfs_folio_trace_clear);
+		}
+	end_wb:
+		if (folio_test_fscache(folio))
+			folio_end_fscache(folio);
+		xas_advance(&xas, folio_next_index(folio) - 1);
+		folio_end_writeback(folio);
+	}
+
+	rcu_read_unlock();
+	netfs_put_group_many(group, gcount);
+	_leave("");
+}
+
+/*
+ * Deal with the disposition of the folios that are under writeback to close
+ * out the operation.
+ */
+static void netfs_cleanup_buffered_write(struct netfs_io_request *wreq)
+{
+	struct address_space *mapping = wreq->mapping;
+
+	_enter("");
+
+	switch (wreq->error) {
+	case 0:
+		netfs_pages_written_back(wreq);
+		break;
+
+	default:
+		pr_notice("R=%08x Unexpected error %d\n", wreq->debug_id, wreq->error);
+		fallthrough;
+	case -EACCES:
+	case -EPERM:
+	case -ENOKEY:
+	case -EKEYEXPIRED:
+	case -EKEYREJECTED:
+	case -EKEYREVOKED:
+	case -ENETRESET:
+	case -EDQUOT:
+	case -ENOSPC:
+		netfs_redirty_pages(mapping, wreq->start, wreq->len);
+		break;
+
+	case -EROFS:
+	case -EIO:
+	case -EREMOTEIO:
+	case -EFBIG:
+	case -ENOENT:
+	case -ENOMEDIUM:
+	case -ENXIO:
+		netfs_kill_pages(mapping, wreq->start, wreq->len);
+		break;
+	}
+
+	if (wreq->error)
+		mapping_set_error(mapping, wreq->error);
+	if (wreq->netfs_ops->done)
+		wreq->netfs_ops->done(wreq);
+}
+
+/*
+ * Extend the region to be written back to include subsequent contiguously
+ * dirty pages if possible, but don't sleep while doing so.
+ *
+ * If this page holds new content, then we can include filler zeros in the
+ * writeback.
+ */
+static void netfs_extend_writeback(struct address_space *mapping,
+				   struct netfs_group *group,
+				   struct xa_state *xas,
+				   long *_count,
+				   loff_t start,
+				   loff_t max_len,
+				   bool caching,
+				   size_t *_len,
+				   size_t *_top)
+{
+	struct netfs_folio *finfo;
+	struct folio_batch fbatch;
+	struct folio *folio;
+	unsigned int i;
+	pgoff_t index = (start + *_len) / PAGE_SIZE;
+	size_t len;
+	void *priv;
+	bool stop = true;
+
+	folio_batch_init(&fbatch);
+
+	do {
+		/* Firstly, we gather up a batch of contiguous dirty pages
+		 * under the RCU read lock - but we can't clear the dirty flags
+		 * there if any of those pages are mapped.
+		 */
+		rcu_read_lock();
+
+		xas_for_each(xas, folio, ULONG_MAX) {
+			stop = true;
+			if (xas_retry(xas, folio))
+				continue;
+			if (xa_is_value(folio))
+				break;
+			if (folio->index != index) {
+				xas_reset(xas);
+				break;
+			}
+
+			if (!folio_try_get_rcu(folio)) {
+				xas_reset(xas);
+				continue;
+			}
+
+			/* Has the folio moved or been split? */
+			if (unlikely(folio != xas_reload(xas))) {
+				folio_put(folio);
+				xas_reset(xas);
+				break;
+			}
+
+			if (!folio_trylock(folio)) {
+				folio_put(folio);
+				xas_reset(xas);
+				break;
+			}
+			if (!folio_test_dirty(folio) ||
+			    folio_test_writeback(folio) ||
+			    folio_test_fscache(folio)) {
+				folio_unlock(folio);
+				folio_put(folio);
+				xas_reset(xas);
+				break;
+			}
+
+			stop = false;
+			len = folio_size(folio);
+			priv = folio_get_private(folio);
+			if ((const struct netfs_group *)priv != group) {
+				stop = true;
+				finfo = netfs_folio_info(folio);
+				if (finfo->netfs_group != group ||
+				    finfo->dirty_offset > 0) {
+					folio_unlock(folio);
+					folio_put(folio);
+					xas_reset(xas);
+					break;
+				}
+				len = finfo->dirty_len;
+			}
+
+			*_top += folio_size(folio);
+			index += folio_nr_pages(folio);
+			*_count -= folio_nr_pages(folio);
+			*_len += len;
+			if (*_len >= max_len || *_count <= 0)
+				stop = true;
+
+			if (!folio_batch_add(&fbatch, folio))
+				break;
+			if (stop)
+				break;
+		}
+
+		xas_pause(xas);
+		rcu_read_unlock();
+
+		/* Now, if we obtained any folios, we can shift them to being
+		 * writable and mark them for caching.
+		 */
+		if (!folio_batch_count(&fbatch))
+			break;
+
+		for (i = 0; i < folio_batch_count(&fbatch); i++) {
+			folio = fbatch.folios[i];
+			trace_netfs_folio(folio, netfs_folio_trace_store_plus);
+
+			if (!folio_clear_dirty_for_io(folio))
+				BUG();
+			folio_start_writeback(folio);
+			netfs_folio_start_fscache(caching, folio);
+			folio_unlock(folio);
+		}
+
+		folio_batch_release(&fbatch);
+		cond_resched();
+	} while (!stop);
+}
+
+/*
+ * Synchronously write back the locked page and any subsequent non-locked dirty
+ * pages.
+ */
+static ssize_t netfs_write_back_from_locked_folio(struct address_space *mapping,
+						  struct writeback_control *wbc,
+						  struct netfs_group *group,
+						  struct xa_state *xas,
+						  struct folio *folio,
+						  unsigned long long start,
+						  unsigned long long end)
+{
+	struct netfs_io_request *wreq;
+	struct netfs_folio *finfo;
+	struct netfs_inode *ctx = netfs_inode(mapping->host);
+	unsigned long long i_size = i_size_read(&ctx->inode);
+	size_t len, max_len;
+	bool caching = netfs_is_cache_enabled(ctx);
+	long count = wbc->nr_to_write;
+	int ret;
+
+	_enter(",%lx,%llx-%llx,%u", folio->index, start, end, caching);
+
+	wreq = netfs_alloc_request(mapping, NULL, start, folio_size(folio),
+				   NETFS_WRITEBACK);
+	if (IS_ERR(wreq)) {
+		folio_unlock(folio);
+		return PTR_ERR(wreq);
+	}
+
+	if (!folio_clear_dirty_for_io(folio))
+		BUG();
+	folio_start_writeback(folio);
+	netfs_folio_start_fscache(caching, folio);
+
+	count -= folio_nr_pages(folio);
+
+	/* Find all consecutive lockable dirty pages that have contiguous
+	 * written regions, stopping when we find a page that is not
+	 * immediately lockable, is not dirty or is missing, or we reach the
+	 * end of the range.
+	 */
+	trace_netfs_folio(folio, netfs_folio_trace_store);
+
+	len = wreq->len;
+	finfo = netfs_folio_info(folio);
+	if (finfo) {
+		start += finfo->dirty_offset;
+		if (finfo->dirty_offset + finfo->dirty_len != len) {
+			len = finfo->dirty_len;
+			goto cant_expand;
+		}
+		len = finfo->dirty_len;
+	}
+
+	if (start < i_size) {
+		/* Trim the write to the EOF; the extra data is ignored.  Also
+		 * put an upper limit on the size of a single storedata op.
+		 */
+		max_len = 65536 * 4096;
+		max_len = min_t(unsigned long long, max_len, end - start + 1);
+		max_len = min_t(unsigned long long, max_len, i_size - start);
+
+		if (len < max_len)
+			netfs_extend_writeback(mapping, group, xas, &count, start,
+					       max_len, caching, &len, &wreq->upper_len);
+	}
+
+cant_expand:
+	len = min_t(unsigned long long, len, i_size - start);
+
+	/* We now have a contiguous set of dirty pages, each with writeback
+	 * set; the first page is still locked at this point, but all the rest
+	 * have been unlocked.
+	 */
+	folio_unlock(folio);
+	wreq->start = start;
+	wreq->len = len;
+
+	if (start < i_size) {
+		_debug("write back %zx @%llx [%llx]", len, start, i_size);
+
+		/* Speculatively write to the cache.  We have to fix this up
+		 * later if the store fails.
+		 */
+		wreq->cleanup = netfs_cleanup_buffered_write;
+
+		iov_iter_xarray(&wreq->iter, ITER_SOURCE, &mapping->i_pages, start,
+				wreq->upper_len);
+		__set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags);
+		ret = netfs_begin_write(wreq, true, netfs_write_trace_writeback);
+		if (ret == 0 || ret == -EIOCBQUEUED)
+			wbc->nr_to_write -= len / PAGE_SIZE;
+	} else {
+		_debug("write discard %zx @%llx [%llx]", len, start, i_size);
+
+		/* The dirty region was entirely beyond the EOF. */
+		fscache_clear_page_bits(mapping, start, len, caching);
+		netfs_pages_written_back(wreq);
+		ret = 0;
+	}
+
+	netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
+	_leave(" = 1");
+	return 1;
+}
+
+/*
+ * Write a region of pages back to the server
+ */
+static ssize_t netfs_writepages_begin(struct address_space *mapping,
+				      struct writeback_control *wbc,
+				      struct netfs_group *group,
+				      struct xa_state *xas,
+				      unsigned long long *_start,
+				      unsigned long long end)
+{
+	const struct netfs_folio *finfo;
+	struct folio *folio;
+	unsigned long long start = *_start;
+	ssize_t ret;
+	void *priv;
+	int skips = 0;
+
+	_enter("%llx,%llx,", start, end);
+
+search_again:
+	/* Find the first dirty page in the group. */
+	rcu_read_lock();
+
+	for (;;) {
+		folio = xas_find_marked(xas, end / PAGE_SIZE, PAGECACHE_TAG_DIRTY);
+		if (xas_retry(xas, folio) || xa_is_value(folio))
+			continue;
+		if (!folio)
+			break;
+
+		if (!folio_try_get_rcu(folio)) {
+			xas_reset(xas);
+			continue;
+		}
+
+		if (unlikely(folio != xas_reload(xas))) {
+			folio_put(folio);
+			xas_reset(xas);
+			continue;
+		}
+
+		/* Skip any dirty folio that's not in the group of interest. */
+		priv = folio_get_private(folio);
+		if ((const struct netfs_group *)priv != group) {
+			finfo = netfs_folio_info(folio);
+			if (finfo->netfs_group != group) {
+				folio_put(folio);
+				continue;
+			}
+		}
+
+		xas_pause(xas);
+		break;
+	}
+	rcu_read_unlock();
+	if (!folio)
+		return 0;
+
+	start = folio_pos(folio); /* May regress with THPs */
+
+	_debug("wback %lx", folio->index);
+
+	/* At this point we hold neither the i_pages lock nor the page lock:
+	 * the page may be truncated or invalidated (changing page->mapping to
+	 * NULL), or even swizzled back from swapper_space to tmpfs file
+	 * mapping
+	 */
+lock_again:
+	if (wbc->sync_mode != WB_SYNC_NONE) {
+		ret = folio_lock_killable(folio);
+		if (ret < 0)
+			return ret;
+	} else {
+		if (!folio_trylock(folio))
+			goto search_again;
+	}
+
+	if (folio->mapping != mapping ||
+	    !folio_test_dirty(folio)) {
+		start += folio_size(folio);
+		folio_unlock(folio);
+		goto search_again;
+	}
+
+	if (folio_test_writeback(folio) ||
+	    folio_test_fscache(folio)) {
+		folio_unlock(folio);
+		if (wbc->sync_mode != WB_SYNC_NONE) {
+			folio_wait_writeback(folio);
+#ifdef CONFIG_FSCACHE
+			folio_wait_fscache(folio);
+#endif
+			goto lock_again;
+		}
+
+		start += folio_size(folio);
+		if (wbc->sync_mode == WB_SYNC_NONE) {
+			if (skips >= 5 || need_resched()) {
+				ret = 0;
+				goto out;
+			}
+			skips++;
+		}
+		goto search_again;
+	}
+
+	ret = netfs_write_back_from_locked_folio(mapping, wbc, group, xas,
+						 folio, start, end);
+out:
+	if (ret > 0)
+		*_start = start + ret;
+	_leave(" = %zd [%llx]", ret, *_start);
+	return ret;
+}
+
+/*
+ * Write a region of pages back to the server
+ */
+static int netfs_writepages_region(struct address_space *mapping,
+				   struct writeback_control *wbc,
+				   struct netfs_group *group,
+				   unsigned long long *_start,
+				   unsigned long long end)
+{
+	ssize_t ret;
+
+	XA_STATE(xas, &mapping->i_pages, *_start / PAGE_SIZE);
+
+	do {
+		ret = netfs_writepages_begin(mapping, wbc, group, &xas,
+					     _start, end);
+		if (ret > 0 && wbc->nr_to_write > 0)
+			cond_resched();
+	} while (ret > 0 && wbc->nr_to_write > 0);
+
+	return ret > 0 ? 0 : ret;
+}
+
+/*
+ * write some of the pending data back to the server
+ */
+int netfs_writepages(struct address_space *mapping,
+		     struct writeback_control *wbc)
+{
+	struct netfs_group *group = NULL;
+	loff_t start, end;
+	int ret;
+
+	_enter("");
+
+	/* We have to be careful as we can end up racing with setattr()
+	 * truncating the pagecache since the caller doesn't take a lock here
+	 * to prevent it.
+	 */
+
+	if (wbc->range_cyclic && mapping->writeback_index) {
+		start = mapping->writeback_index * PAGE_SIZE;
+		ret = netfs_writepages_region(mapping, wbc, group,
+					      &start, LLONG_MAX);
+		if (ret < 0)
+			goto out;
+
+		if (wbc->nr_to_write <= 0) {
+			mapping->writeback_index = start / PAGE_SIZE;
+			goto out;
+		}
+
+		start = 0;
+		end = mapping->writeback_index * PAGE_SIZE;
+		mapping->writeback_index = 0;
+		ret = netfs_writepages_region(mapping, wbc, group, &start, end);
+		if (ret == 0)
+			mapping->writeback_index = start / PAGE_SIZE;
+	} else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) {
+		start = 0;
+		ret = netfs_writepages_region(mapping, wbc, group,
+					      &start, LLONG_MAX);
+		if (wbc->nr_to_write > 0 && ret == 0)
+			mapping->writeback_index = start / PAGE_SIZE;
+	} else {
+		start = wbc->range_start;
+		ret = netfs_writepages_region(mapping, wbc, group,
+					      &start, wbc->range_end);
+	}
+
+out:
+	_leave(" = %d", ret);
+	return ret;
+}
+EXPORT_SYMBOL(netfs_writepages);
+
+/*
+ * Deal with the disposition of a laundered folio.
+ */
+static void netfs_cleanup_launder_folio(struct netfs_io_request *wreq)
+{
+	if (wreq->error) {
+		pr_notice("R=%08x Laundering error %d\n", wreq->debug_id, wreq->error);
+		mapping_set_error(wreq->mapping, wreq->error);
+	}
+}
+
+/**
+ * netfs_launder_folio - Clean up a dirty folio that's being invalidated
+ * @folio: The folio to clean
+ *
+ * This is called to write back a folio that's being invalidated when an inode
+ * is getting torn down.  Ideally, writepages would be used instead.
+ */
+int netfs_launder_folio(struct folio *folio)
+{
+	struct netfs_io_request *wreq;
+	struct address_space *mapping = folio->mapping;
+	struct netfs_folio *finfo = netfs_folio_info(folio);
+	struct netfs_group *group = netfs_folio_group(folio);
+	struct bio_vec bvec;
+	unsigned long long i_size = i_size_read(mapping->host);
+	unsigned long long start = folio_pos(folio);
+	size_t offset = 0, len;
+	int ret = 0;
+
+	if (finfo) {
+		offset = finfo->dirty_offset;
+		start += offset;
+		len = finfo->dirty_len;
+	} else {
+		len = folio_size(folio);
+	}
+	len = min_t(unsigned long long, len, i_size - start);
+
+	wreq = netfs_alloc_request(mapping, NULL, start, len, NETFS_LAUNDER_WRITE);
+	if (IS_ERR(wreq)) {
+		ret = PTR_ERR(wreq);
+		goto out;
+	}
+
+	if (!folio_clear_dirty_for_io(folio))
+		goto out_put;
+
+	trace_netfs_folio(folio, netfs_folio_trace_launder);
+
+	_debug("launder %llx-%llx", start, start + len - 1);
+
+	/* Speculatively write to the cache.  We have to fix this up later if
+	 * the store fails.
+	 */
+	wreq->cleanup = netfs_cleanup_launder_folio;
+
+	bvec_set_folio(&bvec, folio, len, offset);
+	iov_iter_bvec(&wreq->iter, ITER_SOURCE, &bvec, 1, len);
+	__set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags);
+	ret = netfs_begin_write(wreq, true, netfs_write_trace_launder);
+
+out_put:
+	folio_detach_private(folio);
+	netfs_put_group(group);
+	kfree(finfo);
+	netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
+out:
+	folio_wait_fscache(folio);
+	_leave(" = %d", ret);
+	return ret;
+}
+EXPORT_SYMBOL(netfs_launder_folio);
diff --git a/fs/netfs/direct_read.c b/fs/netfs/direct_read.c
new file mode 100644
index 000000000000..ad4370b3935d
--- /dev/null
+++ b/fs/netfs/direct_read.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Direct I/O support.
+ *
+ * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/export.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/slab.h>
+#include <linux/uio.h>
+#include <linux/sched/mm.h>
+#include <linux/task_io_accounting_ops.h>
+#include <linux/netfs.h>
+#include "internal.h"
+
+/**
+ * netfs_unbuffered_read_iter_locked - Perform an unbuffered or direct I/O read
+ * @iocb: The I/O control descriptor describing the read
+ * @iter: The output buffer (also specifies read length)
+ *
+ * Perform an unbuffered I/O or direct I/O from the file in @iocb to the
+ * output buffer.  No use is made of the pagecache.
+ *
+ * The caller must hold any appropriate locks.
+ */
+static ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct netfs_io_request *rreq;
+	ssize_t ret;
+	size_t orig_count = iov_iter_count(iter);
+	bool async = !is_sync_kiocb(iocb);
+
+	_enter("");
+
+	if (!orig_count)
+		return 0; /* Don't update atime */
+
+	ret = kiocb_write_and_wait(iocb, orig_count);
+	if (ret < 0)
+		return ret;
+	file_accessed(iocb->ki_filp);
+
+	rreq = netfs_alloc_request(iocb->ki_filp->f_mapping, iocb->ki_filp,
+				   iocb->ki_pos, orig_count,
+				   NETFS_DIO_READ);
+	if (IS_ERR(rreq))
+		return PTR_ERR(rreq);
+
+	netfs_stat(&netfs_n_rh_dio_read);
+	trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_dio_read);
+
+	/* If this is an async op, we have to keep track of the destination
+	 * buffer for ourselves as the caller's iterator will be trashed when
+	 * we return.
+	 *
+	 * In such a case, extract an iterator to represent as much of the the
+	 * output buffer as we can manage.  Note that the extraction might not
+	 * be able to allocate a sufficiently large bvec array and may shorten
+	 * the request.
+	 */
+	if (user_backed_iter(iter)) {
+		ret = netfs_extract_user_iter(iter, rreq->len, &rreq->iter, 0);
+		if (ret < 0)
+			goto out;
+		rreq->direct_bv = (struct bio_vec *)rreq->iter.bvec;
+		rreq->direct_bv_count = ret;
+		rreq->direct_bv_unpin = iov_iter_extract_will_pin(iter);
+		rreq->len = iov_iter_count(&rreq->iter);
+	} else {
+		rreq->iter = *iter;
+		rreq->len = orig_count;
+		rreq->direct_bv_unpin = false;
+		iov_iter_advance(iter, orig_count);
+	}
+
+	// TODO: Set up bounce buffer if needed
+
+	if (async)
+		rreq->iocb = iocb;
+
+	ret = netfs_begin_read(rreq, is_sync_kiocb(iocb));
+	if (ret < 0)
+		goto out; /* May be -EIOCBQUEUED */
+	if (!async) {
+		// TODO: Copy from bounce buffer
+		iocb->ki_pos += rreq->transferred;
+		ret = rreq->transferred;
+	}
+
+out:
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	if (ret > 0)
+		orig_count -= ret;
+	if (ret != -EIOCBQUEUED)
+		iov_iter_revert(iter, orig_count - iov_iter_count(iter));
+	return ret;
+}
+
+/**
+ * netfs_unbuffered_read_iter - Perform an unbuffered or direct I/O read
+ * @iocb: The I/O control descriptor describing the read
+ * @iter: The output buffer (also specifies read length)
+ *
+ * Perform an unbuffered I/O or direct I/O from the file in @iocb to the
+ * output buffer.  No use is made of the pagecache.
+ */
+ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	ssize_t ret;
+
+	if (!iter->count)
+		return 0; /* Don't update atime */
+
+	ret = netfs_start_io_direct(inode);
+	if (ret == 0) {
+		ret = netfs_unbuffered_read_iter_locked(iocb, iter);
+		netfs_end_io_direct(inode);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(netfs_unbuffered_read_iter);
diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
new file mode 100644
index 000000000000..bee047e20f5d
--- /dev/null
+++ b/fs/netfs/direct_write.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Unbuffered and direct write support.
+ *
+ * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/export.h>
+#include <linux/uio.h>
+#include "internal.h"
+
+static void netfs_cleanup_dio_write(struct netfs_io_request *wreq)
+{
+	struct inode *inode = wreq->inode;
+	unsigned long long end = wreq->start + wreq->len;
+
+	if (!wreq->error &&
+	    i_size_read(inode) < end) {
+		if (wreq->netfs_ops->update_i_size)
+			wreq->netfs_ops->update_i_size(inode, end);
+		else
+			i_size_write(inode, end);
+	}
+}
+
+/*
+ * Perform an unbuffered write where we may have to do an RMW operation on an
+ * encrypted file.  This can also be used for direct I/O writes.
+ */
+static ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *iter,
+						  struct netfs_group *netfs_group)
+{
+	struct netfs_io_request *wreq;
+	unsigned long long start = iocb->ki_pos;
+	unsigned long long end = start + iov_iter_count(iter);
+	ssize_t ret, n;
+	bool async = !is_sync_kiocb(iocb);
+
+	_enter("");
+
+	/* We're going to need a bounce buffer if what we transmit is going to
+	 * be different in some way to the source buffer, e.g. because it gets
+	 * encrypted/compressed or because it needs expanding to a block size.
+	 */
+	// TODO
+
+	_debug("uw %llx-%llx", start, end);
+
+	wreq = netfs_alloc_request(iocb->ki_filp->f_mapping, iocb->ki_filp,
+				   start, end - start,
+				   iocb->ki_flags & IOCB_DIRECT ?
+				   NETFS_DIO_WRITE : NETFS_UNBUFFERED_WRITE);
+	if (IS_ERR(wreq))
+		return PTR_ERR(wreq);
+
+	{
+		/* If this is an async op and we're not using a bounce buffer,
+		 * we have to save the source buffer as the iterator is only
+		 * good until we return.  In such a case, extract an iterator
+		 * to represent as much of the the output buffer as we can
+		 * manage.  Note that the extraction might not be able to
+		 * allocate a sufficiently large bvec array and may shorten the
+		 * request.
+		 */
+		if (async || user_backed_iter(iter)) {
+			n = netfs_extract_user_iter(iter, wreq->len, &wreq->iter, 0);
+			if (n < 0) {
+				ret = n;
+				goto out;
+			}
+			wreq->direct_bv = (struct bio_vec *)wreq->iter.bvec;
+			wreq->direct_bv_count = n;
+			wreq->direct_bv_unpin = iov_iter_extract_will_pin(iter);
+			wreq->len = iov_iter_count(&wreq->iter);
+		} else {
+			wreq->iter = *iter;
+		}
+
+		wreq->io_iter = wreq->iter;
+	}
+
+	/* Copy the data into the bounce buffer and encrypt it. */
+	// TODO
+
+	/* Dispatch the write. */
+	__set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags);
+	if (async)
+		wreq->iocb = iocb;
+	wreq->cleanup = netfs_cleanup_dio_write;
+	ret = netfs_begin_write(wreq, is_sync_kiocb(iocb),
+				iocb->ki_flags & IOCB_DIRECT ?
+				netfs_write_trace_dio_write :
+				netfs_write_trace_unbuffered_write);
+	if (ret < 0) {
+		_debug("begin = %zd", ret);
+		goto out;
+	}
+
+	if (!async) {
+		trace_netfs_rreq(wreq, netfs_rreq_trace_wait_ip);
+		wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS,
+			    TASK_UNINTERRUPTIBLE);
+
+		ret = wreq->error;
+		_debug("waited = %zd", ret);
+		if (ret == 0) {
+			ret = wreq->transferred;
+			iocb->ki_pos += ret;
+		}
+	} else {
+		ret = -EIOCBQUEUED;
+	}
+
+out:
+	netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
+	return ret;
+}
+
+/**
+ * netfs_unbuffered_write_iter - Unbuffered write to a file
+ * @iocb: IO state structure
+ * @from: iov_iter with data to write
+ *
+ * Do an unbuffered write to a file, writing the data directly to the server
+ * and not lodging the data in the pagecache.
+ *
+ * Return:
+ * * Negative error code if no data has been written at all of
+ *   vfs_fsync_range() failed for a synchronous write
+ * * Number of bytes written, even for truncated writes
+ */
+ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	struct netfs_inode *ictx = netfs_inode(inode);
+	unsigned long long end;
+	ssize_t ret;
+
+	_enter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode));
+
+	if (!iov_iter_count(from))
+		return 0;
+
+	trace_netfs_write_iter(iocb, from);
+	netfs_stat(&netfs_n_rh_dio_write);
+
+	ret = netfs_start_io_direct(inode);
+	if (ret < 0)
+		return ret;
+	ret = generic_write_checks(iocb, from);
+	if (ret <= 0)
+		goto out;
+	ret = file_remove_privs(file);
+	if (ret < 0)
+		goto out;
+	ret = file_update_time(file);
+	if (ret < 0)
+		goto out;
+	ret = kiocb_invalidate_pages(iocb, iov_iter_count(from));
+	if (ret < 0)
+		goto out;
+	end = iocb->ki_pos + iov_iter_count(from);
+	if (end > ictx->zero_point)
+		ictx->zero_point = end;
+
+	fscache_invalidate(netfs_i_cookie(ictx), NULL, i_size_read(inode),
+			   FSCACHE_INVAL_DIO_WRITE);
+	ret = netfs_unbuffered_write_iter_locked(iocb, from, NULL);
+out:
+	netfs_end_io_direct(inode);
+	return ret;
+}
+EXPORT_SYMBOL(netfs_unbuffered_write_iter);
diff --git a/fs/fscache/cache.c b/fs/netfs/fscache_cache.c
index d645f8b302a2..9397ed39b0b4 100644
--- a/fs/fscache/cache.c
+++ b/fs/netfs/fscache_cache.c
@@ -179,13 +179,14 @@ EXPORT_SYMBOL(fscache_acquire_cache);
 void fscache_put_cache(struct fscache_cache *cache,
 		       enum fscache_cache_trace where)
 {
-	unsigned int debug_id = cache->debug_id;
+	unsigned int debug_id;
 	bool zero;
 	int ref;
 
 	if (IS_ERR_OR_NULL(cache))
 		return;
 
+	debug_id = cache->debug_id;
 	zero = __refcount_dec_and_test(&cache->ref, &ref);
 	trace_fscache_cache(debug_id, ref - 1, where);
 
diff --git a/fs/fscache/cookie.c b/fs/netfs/fscache_cookie.c
index bce2492186d0..bce2492186d0 100644
--- a/fs/fscache/cookie.c
+++ b/fs/netfs/fscache_cookie.c
diff --git a/fs/netfs/fscache_internal.h b/fs/netfs/fscache_internal.h
new file mode 100644
index 000000000000..a09b948fcef2
--- /dev/null
+++ b/fs/netfs/fscache_internal.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Internal definitions for FS-Cache
+ *
+ * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include "internal.h"
+
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) "FS-Cache: " fmt
diff --git a/fs/fscache/io.c b/fs/netfs/fscache_io.c
index 0d2b8dec8f82..ad572f7ee897 100644
--- a/fs/fscache/io.c
+++ b/fs/netfs/fscache_io.c
@@ -158,46 +158,6 @@ int __fscache_begin_write_operation(struct netfs_cache_resources *cres,
 }
 EXPORT_SYMBOL(__fscache_begin_write_operation);
 
-/**
- * fscache_dirty_folio - Mark folio dirty and pin a cache object for writeback
- * @mapping: The mapping the folio belongs to.
- * @folio: The folio being dirtied.
- * @cookie: The cookie referring to the cache object
- *
- * Set the dirty flag on a folio and pin an in-use cache object in memory
- * so that writeback can later write to it.  This is intended
- * to be called from the filesystem's ->dirty_folio() method.
- *
- * Return: true if the dirty flag was set on the folio, false otherwise.
- */
-bool fscache_dirty_folio(struct address_space *mapping, struct folio *folio,
-				struct fscache_cookie *cookie)
-{
-	struct inode *inode = mapping->host;
-	bool need_use = false;
-
-	_enter("");
-
-	if (!filemap_dirty_folio(mapping, folio))
-		return false;
-	if (!fscache_cookie_valid(cookie))
-		return true;
-
-	if (!(inode->i_state & I_PINNING_FSCACHE_WB)) {
-		spin_lock(&inode->i_lock);
-		if (!(inode->i_state & I_PINNING_FSCACHE_WB)) {
-			inode->i_state |= I_PINNING_FSCACHE_WB;
-			need_use = true;
-		}
-		spin_unlock(&inode->i_lock);
-
-		if (need_use)
-			fscache_use_cookie(cookie, true);
-	}
-	return true;
-}
-EXPORT_SYMBOL(fscache_dirty_folio);
-
 struct fscache_write_request {
 	struct netfs_cache_resources cache_resources;
 	struct address_space	*mapping;
@@ -277,7 +237,7 @@ void __fscache_write_to_cache(struct fscache_cookie *cookie,
 				    fscache_access_io_write) < 0)
 		goto abandon_free;
 
-	ret = cres->ops->prepare_write(cres, &start, &len, i_size, false);
+	ret = cres->ops->prepare_write(cres, &start, &len, len, i_size, false);
 	if (ret < 0)
 		goto abandon_end;
 
diff --git a/fs/fscache/main.c b/fs/netfs/fscache_main.c
index dad85fd84f6f..42e98bb523e3 100644
--- a/fs/fscache/main.c
+++ b/fs/netfs/fscache_main.c
@@ -8,18 +8,9 @@
 #define FSCACHE_DEBUG_LEVEL CACHE
 #include <linux/module.h>
 #include <linux/init.h>
-#define CREATE_TRACE_POINTS
 #include "internal.h"
-
-MODULE_DESCRIPTION("FS Cache Manager");
-MODULE_AUTHOR("Red Hat, Inc.");
-MODULE_LICENSE("GPL");
-
-unsigned fscache_debug;
-module_param_named(debug, fscache_debug, uint,
-		   S_IWUSR | S_IRUGO);
-MODULE_PARM_DESC(fscache_debug,
-		 "FS-Cache debugging mask");
+#define CREATE_TRACE_POINTS
+#include <trace/events/fscache.h>
 
 EXPORT_TRACEPOINT_SYMBOL(fscache_access_cache);
 EXPORT_TRACEPOINT_SYMBOL(fscache_access_volume);
@@ -71,7 +62,7 @@ unsigned int fscache_hash(unsigned int salt, const void *data, size_t len)
 /*
  * initialise the fs caching module
  */
-static int __init fscache_init(void)
+int __init fscache_init(void)
 {
 	int ret = -ENOMEM;
 
@@ -92,7 +83,7 @@ static int __init fscache_init(void)
 		goto error_cookie_jar;
 	}
 
-	pr_notice("Loaded\n");
+	pr_notice("FS-Cache loaded\n");
 	return 0;
 
 error_cookie_jar:
@@ -103,19 +94,15 @@ error_wq:
 	return ret;
 }
 
-fs_initcall(fscache_init);
-
 /*
  * clean up on module removal
  */
-static void __exit fscache_exit(void)
+void __exit fscache_exit(void)
 {
 	_enter("");
 
 	kmem_cache_destroy(fscache_cookie_jar);
 	fscache_proc_cleanup();
 	destroy_workqueue(fscache_wq);
-	pr_notice("Unloaded\n");
+	pr_notice("FS-Cache unloaded\n");
 }
-
-module_exit(fscache_exit);
diff --git a/fs/fscache/proc.c b/fs/netfs/fscache_proc.c
index dc3b0e9c8cce..874d951bc390 100644
--- a/fs/fscache/proc.c
+++ b/fs/netfs/fscache_proc.c
@@ -12,41 +12,34 @@
 #include "internal.h"
 
 /*
- * initialise the /proc/fs/fscache/ directory
+ * Add files to /proc/fs/netfs/.
  */
 int __init fscache_proc_init(void)
 {
-	if (!proc_mkdir("fs/fscache", NULL))
-		goto error_dir;
+	if (!proc_symlink("fs/fscache", NULL, "netfs"))
+		goto error_sym;
 
-	if (!proc_create_seq("fs/fscache/caches", S_IFREG | 0444, NULL,
+	if (!proc_create_seq("fs/netfs/caches", S_IFREG | 0444, NULL,
 			     &fscache_caches_seq_ops))
 		goto error;
 
-	if (!proc_create_seq("fs/fscache/volumes", S_IFREG | 0444, NULL,
+	if (!proc_create_seq("fs/netfs/volumes", S_IFREG | 0444, NULL,
 			     &fscache_volumes_seq_ops))
 		goto error;
 
-	if (!proc_create_seq("fs/fscache/cookies", S_IFREG | 0444, NULL,
+	if (!proc_create_seq("fs/netfs/cookies", S_IFREG | 0444, NULL,
 			     &fscache_cookies_seq_ops))
 		goto error;
-
-#ifdef CONFIG_FSCACHE_STATS
-	if (!proc_create_single("fs/fscache/stats", S_IFREG | 0444, NULL,
-				fscache_stats_show))
-		goto error;
-#endif
-
 	return 0;
 
 error:
 	remove_proc_entry("fs/fscache", NULL);
-error_dir:
+error_sym:
 	return -ENOMEM;
 }
 
 /*
- * clean up the /proc/fs/fscache/ directory
+ * Clean up the /proc/fs/fscache symlink.
  */
 void fscache_proc_cleanup(void)
 {
diff --git a/fs/fscache/stats.c b/fs/netfs/fscache_stats.c
index fc94e5e79f1c..add21abdf713 100644
--- a/fs/fscache/stats.c
+++ b/fs/netfs/fscache_stats.c
@@ -48,13 +48,15 @@ atomic_t fscache_n_no_create_space;
 EXPORT_SYMBOL(fscache_n_no_create_space);
 atomic_t fscache_n_culled;
 EXPORT_SYMBOL(fscache_n_culled);
+atomic_t fscache_n_dio_misfit;
+EXPORT_SYMBOL(fscache_n_dio_misfit);
 
 /*
  * display the general statistics
  */
-int fscache_stats_show(struct seq_file *m, void *v)
+int fscache_stats_show(struct seq_file *m)
 {
-	seq_puts(m, "FS-Cache statistics\n");
+	seq_puts(m, "-- FS-Cache statistics --\n");
 	seq_printf(m, "Cookies: n=%d v=%d vcol=%u voom=%u\n",
 		   atomic_read(&fscache_n_cookies),
 		   atomic_read(&fscache_n_volumes),
@@ -93,10 +95,9 @@ int fscache_stats_show(struct seq_file *m, void *v)
 		   atomic_read(&fscache_n_no_create_space),
 		   atomic_read(&fscache_n_culled));
 
-	seq_printf(m, "IO     : rd=%u wr=%u\n",
+	seq_printf(m, "IO     : rd=%u wr=%u mis=%u\n",
 		   atomic_read(&fscache_n_read),
-		   atomic_read(&fscache_n_write));
-
-	netfs_stats_show(m);
+		   atomic_read(&fscache_n_write),
+		   atomic_read(&fscache_n_dio_misfit));
 	return 0;
 }
diff --git a/fs/fscache/volume.c b/fs/netfs/fscache_volume.c
index cdf991bdd9de..cdf991bdd9de 100644
--- a/fs/fscache/volume.c
+++ b/fs/netfs/fscache_volume.c
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 43fac1b14e40..ec7045d24400 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -5,9 +5,13 @@
  * Written by David Howells (dhowells@redhat.com)
  */
 
+#include <linux/slab.h>
+#include <linux/seq_file.h>
 #include <linux/netfs.h>
 #include <linux/fscache.h>
+#include <linux/fscache-cache.h>
 #include <trace/events/netfs.h>
+#include <trace/events/fscache.h>
 
 #ifdef pr_fmt
 #undef pr_fmt
@@ -19,6 +23,8 @@
  * buffered_read.c
  */
 void netfs_rreq_unlock_folios(struct netfs_io_request *rreq);
+int netfs_prefetch_for_write(struct file *file, struct folio *folio,
+			     size_t offset, size_t len);
 
 /*
  * io.c
@@ -29,6 +35,41 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync);
  * main.c
  */
 extern unsigned int netfs_debug;
+extern struct list_head netfs_io_requests;
+extern spinlock_t netfs_proc_lock;
+
+#ifdef CONFIG_PROC_FS
+static inline void netfs_proc_add_rreq(struct netfs_io_request *rreq)
+{
+	spin_lock(&netfs_proc_lock);
+	list_add_tail_rcu(&rreq->proc_link, &netfs_io_requests);
+	spin_unlock(&netfs_proc_lock);
+}
+static inline void netfs_proc_del_rreq(struct netfs_io_request *rreq)
+{
+	if (!list_empty(&rreq->proc_link)) {
+		spin_lock(&netfs_proc_lock);
+		list_del_rcu(&rreq->proc_link);
+		spin_unlock(&netfs_proc_lock);
+	}
+}
+#else
+static inline void netfs_proc_add_rreq(struct netfs_io_request *rreq) {}
+static inline void netfs_proc_del_rreq(struct netfs_io_request *rreq) {}
+#endif
+
+/*
+ * misc.c
+ */
+#define NETFS_FLAG_PUT_MARK		BIT(0)
+#define NETFS_FLAG_PAGECACHE_MARK	BIT(1)
+int netfs_xa_store_and_mark(struct xarray *xa, unsigned long index,
+			    struct folio *folio, unsigned int flags,
+			    gfp_t gfp_mask);
+int netfs_add_folios_to_buffer(struct xarray *buffer,
+			       struct address_space *mapping,
+			       pgoff_t index, pgoff_t to, gfp_t gfp_mask);
+void netfs_clear_buffer(struct xarray *buffer);
 
 /*
  * objects.c
@@ -50,9 +91,20 @@ static inline void netfs_see_request(struct netfs_io_request *rreq,
 }
 
 /*
+ * output.c
+ */
+int netfs_begin_write(struct netfs_io_request *wreq, bool may_wait,
+		      enum netfs_write_trace what);
+struct netfs_io_request *netfs_begin_writethrough(struct kiocb *iocb, size_t len);
+int netfs_advance_writethrough(struct netfs_io_request *wreq, size_t copied, bool to_page_end);
+int netfs_end_writethrough(struct netfs_io_request *wreq, struct kiocb *iocb);
+
+/*
  * stats.c
  */
 #ifdef CONFIG_NETFS_STATS
+extern atomic_t netfs_n_rh_dio_read;
+extern atomic_t netfs_n_rh_dio_write;
 extern atomic_t netfs_n_rh_readahead;
 extern atomic_t netfs_n_rh_readpage;
 extern atomic_t netfs_n_rh_rreq;
@@ -71,7 +123,15 @@ extern atomic_t netfs_n_rh_write_begin;
 extern atomic_t netfs_n_rh_write_done;
 extern atomic_t netfs_n_rh_write_failed;
 extern atomic_t netfs_n_rh_write_zskip;
+extern atomic_t netfs_n_wh_wstream_conflict;
+extern atomic_t netfs_n_wh_upload;
+extern atomic_t netfs_n_wh_upload_done;
+extern atomic_t netfs_n_wh_upload_failed;
+extern atomic_t netfs_n_wh_write;
+extern atomic_t netfs_n_wh_write_done;
+extern atomic_t netfs_n_wh_write_failed;
 
+int netfs_stats_show(struct seq_file *m, void *v);
 
 static inline void netfs_stat(atomic_t *stat)
 {
@@ -103,6 +163,176 @@ static inline bool netfs_is_cache_enabled(struct netfs_inode *ctx)
 #endif
 }
 
+/*
+ * Get a ref on a netfs group attached to a dirty page (e.g. a ceph snap).
+ */
+static inline struct netfs_group *netfs_get_group(struct netfs_group *netfs_group)
+{
+	if (netfs_group)
+		refcount_inc(&netfs_group->ref);
+	return netfs_group;
+}
+
+/*
+ * Dispose of a netfs group attached to a dirty page (e.g. a ceph snap).
+ */
+static inline void netfs_put_group(struct netfs_group *netfs_group)
+{
+	if (netfs_group && refcount_dec_and_test(&netfs_group->ref))
+		netfs_group->free(netfs_group);
+}
+
+/*
+ * Dispose of a netfs group attached to a dirty page (e.g. a ceph snap).
+ */
+static inline void netfs_put_group_many(struct netfs_group *netfs_group, int nr)
+{
+	if (netfs_group && refcount_sub_and_test(nr, &netfs_group->ref))
+		netfs_group->free(netfs_group);
+}
+
+/*
+ * fscache-cache.c
+ */
+#ifdef CONFIG_PROC_FS
+extern const struct seq_operations fscache_caches_seq_ops;
+#endif
+bool fscache_begin_cache_access(struct fscache_cache *cache, enum fscache_access_trace why);
+void fscache_end_cache_access(struct fscache_cache *cache, enum fscache_access_trace why);
+struct fscache_cache *fscache_lookup_cache(const char *name, bool is_cache);
+void fscache_put_cache(struct fscache_cache *cache, enum fscache_cache_trace where);
+
+static inline enum fscache_cache_state fscache_cache_state(const struct fscache_cache *cache)
+{
+	return smp_load_acquire(&cache->state);
+}
+
+static inline bool fscache_cache_is_live(const struct fscache_cache *cache)
+{
+	return fscache_cache_state(cache) == FSCACHE_CACHE_IS_ACTIVE;
+}
+
+static inline void fscache_set_cache_state(struct fscache_cache *cache,
+					   enum fscache_cache_state new_state)
+{
+	smp_store_release(&cache->state, new_state);
+
+}
+
+static inline bool fscache_set_cache_state_maybe(struct fscache_cache *cache,
+						 enum fscache_cache_state old_state,
+						 enum fscache_cache_state new_state)
+{
+	return try_cmpxchg_release(&cache->state, &old_state, new_state);
+}
+
+/*
+ * fscache-cookie.c
+ */
+extern struct kmem_cache *fscache_cookie_jar;
+#ifdef CONFIG_PROC_FS
+extern const struct seq_operations fscache_cookies_seq_ops;
+#endif
+extern struct timer_list fscache_cookie_lru_timer;
+
+extern void fscache_print_cookie(struct fscache_cookie *cookie, char prefix);
+extern bool fscache_begin_cookie_access(struct fscache_cookie *cookie,
+					enum fscache_access_trace why);
+
+static inline void fscache_see_cookie(struct fscache_cookie *cookie,
+				      enum fscache_cookie_trace where)
+{
+	trace_fscache_cookie(cookie->debug_id, refcount_read(&cookie->ref),
+			     where);
+}
+
+/*
+ * fscache-main.c
+ */
+extern unsigned int fscache_hash(unsigned int salt, const void *data, size_t len);
+#ifdef CONFIG_FSCACHE
+int __init fscache_init(void);
+void __exit fscache_exit(void);
+#else
+static inline int fscache_init(void) { return 0; }
+static inline void fscache_exit(void) {}
+#endif
+
+/*
+ * fscache-proc.c
+ */
+#ifdef CONFIG_PROC_FS
+extern int __init fscache_proc_init(void);
+extern void fscache_proc_cleanup(void);
+#else
+#define fscache_proc_init()	(0)
+#define fscache_proc_cleanup()	do {} while (0)
+#endif
+
+/*
+ * fscache-stats.c
+ */
+#ifdef CONFIG_FSCACHE_STATS
+extern atomic_t fscache_n_volumes;
+extern atomic_t fscache_n_volumes_collision;
+extern atomic_t fscache_n_volumes_nomem;
+extern atomic_t fscache_n_cookies;
+extern atomic_t fscache_n_cookies_lru;
+extern atomic_t fscache_n_cookies_lru_expired;
+extern atomic_t fscache_n_cookies_lru_removed;
+extern atomic_t fscache_n_cookies_lru_dropped;
+
+extern atomic_t fscache_n_acquires;
+extern atomic_t fscache_n_acquires_ok;
+extern atomic_t fscache_n_acquires_oom;
+
+extern atomic_t fscache_n_invalidates;
+
+extern atomic_t fscache_n_relinquishes;
+extern atomic_t fscache_n_relinquishes_retire;
+extern atomic_t fscache_n_relinquishes_dropped;
+
+extern atomic_t fscache_n_resizes;
+extern atomic_t fscache_n_resizes_null;
+
+static inline void fscache_stat(atomic_t *stat)
+{
+	atomic_inc(stat);
+}
+
+static inline void fscache_stat_d(atomic_t *stat)
+{
+	atomic_dec(stat);
+}
+
+#define __fscache_stat(stat) (stat)
+
+int fscache_stats_show(struct seq_file *m);
+#else
+
+#define __fscache_stat(stat) (NULL)
+#define fscache_stat(stat) do {} while (0)
+#define fscache_stat_d(stat) do {} while (0)
+
+static inline int fscache_stats_show(struct seq_file *m) { return 0; }
+#endif
+
+/*
+ * fscache-volume.c
+ */
+#ifdef CONFIG_PROC_FS
+extern const struct seq_operations fscache_volumes_seq_ops;
+#endif
+
+struct fscache_volume *fscache_get_volume(struct fscache_volume *volume,
+					  enum fscache_volume_trace where);
+void fscache_put_volume(struct fscache_volume *volume,
+			enum fscache_volume_trace where);
+bool fscache_begin_volume_access(struct fscache_volume *volume,
+				 struct fscache_cookie *cookie,
+				 enum fscache_access_trace why);
+void fscache_create_volume(struct fscache_volume *volume, bool wait);
+
 /*****************************************************************************/
 /*
  * debug tracing
@@ -143,3 +373,57 @@ do {						\
 #define _leave(FMT, ...) no_printk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
 #define _debug(FMT, ...) no_printk(FMT, ##__VA_ARGS__)
 #endif
+
+/*
+ * assertions
+ */
+#if 1 /* defined(__KDEBUGALL) */
+
+#define ASSERT(X)							\
+do {									\
+	if (unlikely(!(X))) {						\
+		pr_err("\n");					\
+		pr_err("Assertion failed\n");	\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTCMP(X, OP, Y)						\
+do {									\
+	if (unlikely(!((X) OP (Y)))) {					\
+		pr_err("\n");					\
+		pr_err("Assertion failed\n");	\
+		pr_err("%lx " #OP " %lx is false\n",		\
+		       (unsigned long)(X), (unsigned long)(Y));		\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTIF(C, X)							\
+do {									\
+	if (unlikely((C) && !(X))) {					\
+		pr_err("\n");					\
+		pr_err("Assertion failed\n");	\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTIFCMP(C, X, OP, Y)					\
+do {									\
+	if (unlikely((C) && !((X) OP (Y)))) {				\
+		pr_err("\n");					\
+		pr_err("Assertion failed\n");	\
+		pr_err("%lx " #OP " %lx is false\n",		\
+		       (unsigned long)(X), (unsigned long)(Y));		\
+		BUG();							\
+	}								\
+} while (0)
+
+#else
+
+#define ASSERT(X)			do {} while (0)
+#define ASSERTCMP(X, OP, Y)		do {} while (0)
+#define ASSERTIF(C, X)			do {} while (0)
+#define ASSERTIFCMP(C, X, OP, Y)	do {} while (0)
+
+#endif /* assert or not */
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index 7f753380e047..4261ad6c55b6 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -21,12 +21,7 @@
  */
 static void netfs_clear_unread(struct netfs_io_subrequest *subreq)
 {
-	struct iov_iter iter;
-
-	iov_iter_xarray(&iter, ITER_DEST, &subreq->rreq->mapping->i_pages,
-			subreq->start + subreq->transferred,
-			subreq->len   - subreq->transferred);
-	iov_iter_zero(iov_iter_count(&iter), &iter);
+	iov_iter_zero(iov_iter_count(&subreq->io_iter), &subreq->io_iter);
 }
 
 static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error,
@@ -46,14 +41,9 @@ static void netfs_read_from_cache(struct netfs_io_request *rreq,
 				  enum netfs_read_from_hole read_hole)
 {
 	struct netfs_cache_resources *cres = &rreq->cache_resources;
-	struct iov_iter iter;
 
 	netfs_stat(&netfs_n_rh_read);
-	iov_iter_xarray(&iter, ITER_DEST, &rreq->mapping->i_pages,
-			subreq->start + subreq->transferred,
-			subreq->len   - subreq->transferred);
-
-	cres->ops->read(cres, subreq->start, &iter, read_hole,
+	cres->ops->read(cres, subreq->start, &subreq->io_iter, read_hole,
 			netfs_cache_read_terminated, subreq);
 }
 
@@ -88,6 +78,13 @@ static void netfs_read_from_server(struct netfs_io_request *rreq,
 				   struct netfs_io_subrequest *subreq)
 {
 	netfs_stat(&netfs_n_rh_download);
+
+	if (rreq->origin != NETFS_DIO_READ &&
+	    iov_iter_count(&subreq->io_iter) != subreq->len - subreq->transferred)
+		pr_warn("R=%08x[%u] ITER PRE-MISMATCH %zx != %zx-%zx %lx\n",
+			rreq->debug_id, subreq->debug_index,
+			iov_iter_count(&subreq->io_iter), subreq->len,
+			subreq->transferred, subreq->flags);
 	rreq->netfs_ops->issue_read(subreq);
 }
 
@@ -127,9 +124,10 @@ static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq,
 			/* We might have multiple writes from the same huge
 			 * folio, but we mustn't unlock a folio more than once.
 			 */
-			if (have_unlocked && folio_index(folio) <= unlocked)
+			if (have_unlocked && folio->index <= unlocked)
 				continue;
-			unlocked = folio_index(folio);
+			unlocked = folio_next_index(folio) - 1;
+			trace_netfs_folio(folio, netfs_folio_trace_end_copy);
 			folio_end_fscache(folio);
 			have_unlocked = true;
 		}
@@ -201,7 +199,7 @@ static void netfs_rreq_do_write_to_cache(struct netfs_io_request *rreq)
 		}
 
 		ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len,
-					       rreq->i_size, true);
+					       subreq->len, rreq->i_size, true);
 		if (ret < 0) {
 			trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write);
 			trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip);
@@ -260,6 +258,30 @@ static void netfs_rreq_short_read(struct netfs_io_request *rreq,
 }
 
 /*
+ * Reset the subrequest iterator prior to resubmission.
+ */
+static void netfs_reset_subreq_iter(struct netfs_io_request *rreq,
+				    struct netfs_io_subrequest *subreq)
+{
+	size_t remaining = subreq->len - subreq->transferred;
+	size_t count = iov_iter_count(&subreq->io_iter);
+
+	if (count == remaining)
+		return;
+
+	_debug("R=%08x[%u] ITER RESUB-MISMATCH %zx != %zx-%zx-%llx %x\n",
+	       rreq->debug_id, subreq->debug_index,
+	       iov_iter_count(&subreq->io_iter), subreq->transferred,
+	       subreq->len, rreq->i_size,
+	       subreq->io_iter.iter_type);
+
+	if (count < remaining)
+		iov_iter_revert(&subreq->io_iter, remaining - count);
+	else
+		iov_iter_advance(&subreq->io_iter, count - remaining);
+}
+
+/*
  * Resubmit any short or failed operations.  Returns true if we got the rreq
  * ref back.
  */
@@ -287,6 +309,7 @@ static bool netfs_rreq_perform_resubmissions(struct netfs_io_request *rreq)
 			trace_netfs_sreq(subreq, netfs_sreq_trace_download_instead);
 			netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit);
 			atomic_inc(&rreq->nr_outstanding);
+			netfs_reset_subreq_iter(rreq, subreq);
 			netfs_read_from_server(rreq, subreq);
 		} else if (test_bit(NETFS_SREQ_SHORT_IO, &subreq->flags)) {
 			netfs_rreq_short_read(rreq, subreq);
@@ -321,6 +344,43 @@ static void netfs_rreq_is_still_valid(struct netfs_io_request *rreq)
 }
 
 /*
+ * Determine how much we can admit to having read from a DIO read.
+ */
+static void netfs_rreq_assess_dio(struct netfs_io_request *rreq)
+{
+	struct netfs_io_subrequest *subreq;
+	unsigned int i;
+	size_t transferred = 0;
+
+	for (i = 0; i < rreq->direct_bv_count; i++)
+		flush_dcache_page(rreq->direct_bv[i].bv_page);
+
+	list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
+		if (subreq->error || subreq->transferred == 0)
+			break;
+		transferred += subreq->transferred;
+		if (subreq->transferred < subreq->len)
+			break;
+	}
+
+	for (i = 0; i < rreq->direct_bv_count; i++)
+		flush_dcache_page(rreq->direct_bv[i].bv_page);
+
+	rreq->transferred = transferred;
+	task_io_account_read(transferred);
+
+	if (rreq->iocb) {
+		rreq->iocb->ki_pos += transferred;
+		if (rreq->iocb->ki_complete)
+			rreq->iocb->ki_complete(
+				rreq->iocb, rreq->error ? rreq->error : transferred);
+	}
+	if (rreq->netfs_ops->done)
+		rreq->netfs_ops->done(rreq);
+	inode_dio_end(rreq->inode);
+}
+
+/*
  * Assess the state of a read request and decide what to do next.
  *
  * Note that we could be in an ordinary kernel thread, on a workqueue or in
@@ -340,8 +400,12 @@ again:
 		return;
 	}
 
-	netfs_rreq_unlock_folios(rreq);
+	if (rreq->origin != NETFS_DIO_READ)
+		netfs_rreq_unlock_folios(rreq);
+	else
+		netfs_rreq_assess_dio(rreq);
 
+	trace_netfs_rreq(rreq, netfs_rreq_trace_wake_ip);
 	clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
 	wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS);
 
@@ -399,9 +463,9 @@ void netfs_subreq_terminated(struct netfs_io_subrequest *subreq,
 	struct netfs_io_request *rreq = subreq->rreq;
 	int u;
 
-	_enter("[%u]{%llx,%lx},%zd",
-	       subreq->debug_index, subreq->start, subreq->flags,
-	       transferred_or_error);
+	_enter("R=%x[%x]{%llx,%lx},%zd",
+	       rreq->debug_id, subreq->debug_index,
+	       subreq->start, subreq->flags, transferred_or_error);
 
 	switch (subreq->source) {
 	case NETFS_READ_FROM_CACHE:
@@ -501,15 +565,20 @@ static enum netfs_io_source netfs_cache_prepare_read(struct netfs_io_subrequest
  */
 static enum netfs_io_source
 netfs_rreq_prepare_read(struct netfs_io_request *rreq,
-			struct netfs_io_subrequest *subreq)
+			struct netfs_io_subrequest *subreq,
+			struct iov_iter *io_iter)
 {
-	enum netfs_io_source source;
+	enum netfs_io_source source = NETFS_DOWNLOAD_FROM_SERVER;
+	struct netfs_inode *ictx = netfs_inode(rreq->inode);
+	size_t lsize;
 
 	_enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size);
 
-	source = netfs_cache_prepare_read(subreq, rreq->i_size);
-	if (source == NETFS_INVALID_READ)
-		goto out;
+	if (rreq->origin != NETFS_DIO_READ) {
+		source = netfs_cache_prepare_read(subreq, rreq->i_size);
+		if (source == NETFS_INVALID_READ)
+			goto out;
+	}
 
 	if (source == NETFS_DOWNLOAD_FROM_SERVER) {
 		/* Call out to the netfs to let it shrink the request to fit
@@ -518,19 +587,52 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 		 * to make serial calls, it can indicate a short read and then
 		 * we will call it again.
 		 */
+		if (rreq->origin != NETFS_DIO_READ) {
+			if (subreq->start >= ictx->zero_point) {
+				source = NETFS_FILL_WITH_ZEROES;
+				goto set;
+			}
+			if (subreq->len > ictx->zero_point - subreq->start)
+				subreq->len = ictx->zero_point - subreq->start;
+		}
 		if (subreq->len > rreq->i_size - subreq->start)
 			subreq->len = rreq->i_size - subreq->start;
+		if (rreq->rsize && subreq->len > rreq->rsize)
+			subreq->len = rreq->rsize;
 
 		if (rreq->netfs_ops->clamp_length &&
 		    !rreq->netfs_ops->clamp_length(subreq)) {
 			source = NETFS_INVALID_READ;
 			goto out;
 		}
+
+		if (subreq->max_nr_segs) {
+			lsize = netfs_limit_iter(io_iter, 0, subreq->len,
+						 subreq->max_nr_segs);
+			if (subreq->len > lsize) {
+				subreq->len = lsize;
+				trace_netfs_sreq(subreq, netfs_sreq_trace_limited);
+			}
+		}
 	}
 
-	if (WARN_ON(subreq->len == 0))
+set:
+	if (subreq->len > rreq->len)
+		pr_warn("R=%08x[%u] SREQ>RREQ %zx > %zx\n",
+			rreq->debug_id, subreq->debug_index,
+			subreq->len, rreq->len);
+
+	if (WARN_ON(subreq->len == 0)) {
 		source = NETFS_INVALID_READ;
+		goto out;
+	}
 
+	subreq->source = source;
+	trace_netfs_sreq(subreq, netfs_sreq_trace_prepare);
+
+	subreq->io_iter = *io_iter;
+	iov_iter_truncate(&subreq->io_iter, subreq->len);
+	iov_iter_advance(io_iter, subreq->len);
 out:
 	subreq->source = source;
 	trace_netfs_sreq(subreq, netfs_sreq_trace_prepare);
@@ -541,6 +643,7 @@ out:
  * Slice off a piece of a read request and submit an I/O request for it.
  */
 static bool netfs_rreq_submit_slice(struct netfs_io_request *rreq,
+				    struct iov_iter *io_iter,
 				    unsigned int *_debug_index)
 {
 	struct netfs_io_subrequest *subreq;
@@ -552,7 +655,7 @@ static bool netfs_rreq_submit_slice(struct netfs_io_request *rreq,
 
 	subreq->debug_index	= (*_debug_index)++;
 	subreq->start		= rreq->start + rreq->submitted;
-	subreq->len		= rreq->len   - rreq->submitted;
+	subreq->len		= io_iter->count;
 
 	_debug("slice %llx,%zx,%zx", subreq->start, subreq->len, rreq->submitted);
 	list_add_tail(&subreq->rreq_link, &rreq->subrequests);
@@ -565,7 +668,7 @@ static bool netfs_rreq_submit_slice(struct netfs_io_request *rreq,
 	 * (the starts must coincide), in which case, we go around the loop
 	 * again and ask it to download the next piece.
 	 */
-	source = netfs_rreq_prepare_read(rreq, subreq);
+	source = netfs_rreq_prepare_read(rreq, subreq, io_iter);
 	if (source == NETFS_INVALID_READ)
 		goto subreq_failed;
 
@@ -603,6 +706,7 @@ subreq_failed:
  */
 int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 {
+	struct iov_iter io_iter;
 	unsigned int debug_index = 0;
 	int ret;
 
@@ -611,50 +715,73 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 
 	if (rreq->len == 0) {
 		pr_err("Zero-sized read [R=%x]\n", rreq->debug_id);
-		netfs_put_request(rreq, false, netfs_rreq_trace_put_zero_len);
 		return -EIO;
 	}
 
-	INIT_WORK(&rreq->work, netfs_rreq_work);
+	if (rreq->origin == NETFS_DIO_READ)
+		inode_dio_begin(rreq->inode);
 
-	if (sync)
-		netfs_get_request(rreq, netfs_rreq_trace_get_hold);
+	// TODO: Use bounce buffer if requested
+	rreq->io_iter = rreq->iter;
+
+	INIT_WORK(&rreq->work, netfs_rreq_work);
 
 	/* Chop the read into slices according to what the cache and the netfs
 	 * want and submit each one.
 	 */
+	netfs_get_request(rreq, netfs_rreq_trace_get_for_outstanding);
 	atomic_set(&rreq->nr_outstanding, 1);
+	io_iter = rreq->io_iter;
 	do {
-		if (!netfs_rreq_submit_slice(rreq, &debug_index))
+		_debug("submit %llx + %zx >= %llx",
+		       rreq->start, rreq->submitted, rreq->i_size);
+		if (rreq->origin == NETFS_DIO_READ &&
+		    rreq->start + rreq->submitted >= rreq->i_size)
+			break;
+		if (!netfs_rreq_submit_slice(rreq, &io_iter, &debug_index))
+			break;
+		if (test_bit(NETFS_RREQ_BLOCKED, &rreq->flags) &&
+		    test_bit(NETFS_RREQ_NONBLOCK, &rreq->flags))
 			break;
 
 	} while (rreq->submitted < rreq->len);
 
+	if (!rreq->submitted) {
+		netfs_put_request(rreq, false, netfs_rreq_trace_put_no_submit);
+		if (rreq->origin == NETFS_DIO_READ)
+			inode_dio_end(rreq->inode);
+		ret = 0;
+		goto out;
+	}
+
 	if (sync) {
-		/* Keep nr_outstanding incremented so that the ref always belongs to
-		 * us, and the service code isn't punted off to a random thread pool to
-		 * process.
+		/* Keep nr_outstanding incremented so that the ref always
+		 * belongs to us, and the service code isn't punted off to a
+		 * random thread pool to process.  Note that this might start
+		 * further work, such as writing to the cache.
 		 */
-		for (;;) {
-			wait_var_event(&rreq->nr_outstanding,
-				       atomic_read(&rreq->nr_outstanding) == 1);
+		wait_var_event(&rreq->nr_outstanding,
+			       atomic_read(&rreq->nr_outstanding) == 1);
+		if (atomic_dec_and_test(&rreq->nr_outstanding))
 			netfs_rreq_assess(rreq, false);
-			if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags))
-				break;
-			cond_resched();
-		}
+
+		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_ip);
+		wait_on_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS,
+			    TASK_UNINTERRUPTIBLE);
 
 		ret = rreq->error;
-		if (ret == 0 && rreq->submitted < rreq->len) {
+		if (ret == 0 && rreq->submitted < rreq->len &&
+		    rreq->origin != NETFS_DIO_READ) {
 			trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read);
 			ret = -EIO;
 		}
-		netfs_put_request(rreq, false, netfs_rreq_trace_put_hold);
 	} else {
 		/* If we decrement nr_outstanding to 0, the ref belongs to us. */
 		if (atomic_dec_and_test(&rreq->nr_outstanding))
 			netfs_rreq_assess(rreq, false);
-		ret = 0;
+		ret = -EIOCBQUEUED;
 	}
+
+out:
 	return ret;
 }
diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c
index 2ff07ba655a0..b781bbbf1d8d 100644
--- a/fs/netfs/iterator.c
+++ b/fs/netfs/iterator.c
@@ -101,3 +101,100 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
 	return npages;
 }
 EXPORT_SYMBOL_GPL(netfs_extract_user_iter);
+
+/*
+ * Select the span of a bvec iterator we're going to use.  Limit it by both maximum
+ * size and maximum number of segments.  Returns the size of the span in bytes.
+ */
+static size_t netfs_limit_bvec(const struct iov_iter *iter, size_t start_offset,
+			       size_t max_size, size_t max_segs)
+{
+	const struct bio_vec *bvecs = iter->bvec;
+	unsigned int nbv = iter->nr_segs, ix = 0, nsegs = 0;
+	size_t len, span = 0, n = iter->count;
+	size_t skip = iter->iov_offset + start_offset;
+
+	if (WARN_ON(!iov_iter_is_bvec(iter)) ||
+	    WARN_ON(start_offset > n) ||
+	    n == 0)
+		return 0;
+
+	while (n && ix < nbv && skip) {
+		len = bvecs[ix].bv_len;
+		if (skip < len)
+			break;
+		skip -= len;
+		n -= len;
+		ix++;
+	}
+
+	while (n && ix < nbv) {
+		len = min3(n, bvecs[ix].bv_len - skip, max_size);
+		span += len;
+		nsegs++;
+		ix++;
+		if (span >= max_size || nsegs >= max_segs)
+			break;
+		skip = 0;
+		n -= len;
+	}
+
+	return min(span, max_size);
+}
+
+/*
+ * Select the span of an xarray iterator we're going to use.  Limit it by both
+ * maximum size and maximum number of segments.  It is assumed that segments
+ * can be larger than a page in size, provided they're physically contiguous.
+ * Returns the size of the span in bytes.
+ */
+static size_t netfs_limit_xarray(const struct iov_iter *iter, size_t start_offset,
+				 size_t max_size, size_t max_segs)
+{
+	struct folio *folio;
+	unsigned int nsegs = 0;
+	loff_t pos = iter->xarray_start + iter->iov_offset;
+	pgoff_t index = pos / PAGE_SIZE;
+	size_t span = 0, n = iter->count;
+
+	XA_STATE(xas, iter->xarray, index);
+
+	if (WARN_ON(!iov_iter_is_xarray(iter)) ||
+	    WARN_ON(start_offset > n) ||
+	    n == 0)
+		return 0;
+	max_size = min(max_size, n - start_offset);
+
+	rcu_read_lock();
+	xas_for_each(&xas, folio, ULONG_MAX) {
+		size_t offset, flen, len;
+		if (xas_retry(&xas, folio))
+			continue;
+		if (WARN_ON(xa_is_value(folio)))
+			break;
+		if (WARN_ON(folio_test_hugetlb(folio)))
+			break;
+
+		flen = folio_size(folio);
+		offset = offset_in_folio(folio, pos);
+		len = min(max_size, flen - offset);
+		span += len;
+		nsegs++;
+		if (span >= max_size || nsegs >= max_segs)
+			break;
+	}
+
+	rcu_read_unlock();
+	return min(span, max_size);
+}
+
+size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset,
+			size_t max_size, size_t max_segs)
+{
+	if (iov_iter_is_bvec(iter))
+		return netfs_limit_bvec(iter, start_offset, max_size, max_segs);
+	if (iov_iter_is_xarray(iter))
+		return netfs_limit_xarray(iter, start_offset, max_size, max_segs);
+	BUG();
+}
+EXPORT_SYMBOL(netfs_limit_iter);
diff --git a/fs/netfs/locking.c b/fs/netfs/locking.c
new file mode 100644
index 000000000000..75dc52a49b3a
--- /dev/null
+++ b/fs/netfs/locking.c
@@ -0,0 +1,216 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * I/O and data path helper functionality.
+ *
+ * Borrowed from NFS Copyright (c) 2016 Trond Myklebust
+ */
+
+#include <linux/kernel.h>
+#include <linux/netfs.h>
+#include "internal.h"
+
+/*
+ * inode_dio_wait_interruptible - wait for outstanding DIO requests to finish
+ * @inode: inode to wait for
+ *
+ * Waits for all pending direct I/O requests to finish so that we can
+ * proceed with a truncate or equivalent operation.
+ *
+ * Must be called under a lock that serializes taking new references
+ * to i_dio_count, usually by inode->i_mutex.
+ */
+static int inode_dio_wait_interruptible(struct inode *inode)
+{
+	if (!atomic_read(&inode->i_dio_count))
+		return 0;
+
+	wait_queue_head_t *wq = bit_waitqueue(&inode->i_state, __I_DIO_WAKEUP);
+	DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP);
+
+	for (;;) {
+		prepare_to_wait(wq, &q.wq_entry, TASK_INTERRUPTIBLE);
+		if (!atomic_read(&inode->i_dio_count))
+			break;
+		if (signal_pending(current))
+			break;
+		schedule();
+	}
+	finish_wait(wq, &q.wq_entry);
+
+	return atomic_read(&inode->i_dio_count) ? -ERESTARTSYS : 0;
+}
+
+/* Call with exclusively locked inode->i_rwsem */
+static int netfs_block_o_direct(struct netfs_inode *ictx)
+{
+	if (!test_bit(NETFS_ICTX_ODIRECT, &ictx->flags))
+		return 0;
+	clear_bit(NETFS_ICTX_ODIRECT, &ictx->flags);
+	return inode_dio_wait_interruptible(&ictx->inode);
+}
+
+/**
+ * netfs_start_io_read - declare the file is being used for buffered reads
+ * @inode: file inode
+ *
+ * Declare that a buffered read operation is about to start, and ensure
+ * that we block all direct I/O.
+ * On exit, the function ensures that the NETFS_ICTX_ODIRECT flag is unset,
+ * and holds a shared lock on inode->i_rwsem to ensure that the flag
+ * cannot be changed.
+ * In practice, this means that buffered read operations are allowed to
+ * execute in parallel, thanks to the shared lock, whereas direct I/O
+ * operations need to wait to grab an exclusive lock in order to set
+ * NETFS_ICTX_ODIRECT.
+ * Note that buffered writes and truncates both take a write lock on
+ * inode->i_rwsem, meaning that those are serialised w.r.t. the reads.
+ */
+int netfs_start_io_read(struct inode *inode)
+	__acquires(inode->i_rwsem)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+
+	/* Be an optimist! */
+	if (down_read_interruptible(&inode->i_rwsem) < 0)
+		return -ERESTARTSYS;
+	if (test_bit(NETFS_ICTX_ODIRECT, &ictx->flags) == 0)
+		return 0;
+	up_read(&inode->i_rwsem);
+
+	/* Slow path.... */
+	if (down_write_killable(&inode->i_rwsem) < 0)
+		return -ERESTARTSYS;
+	if (netfs_block_o_direct(ictx) < 0) {
+		up_write(&inode->i_rwsem);
+		return -ERESTARTSYS;
+	}
+	downgrade_write(&inode->i_rwsem);
+	return 0;
+}
+EXPORT_SYMBOL(netfs_start_io_read);
+
+/**
+ * netfs_end_io_read - declare that the buffered read operation is done
+ * @inode: file inode
+ *
+ * Declare that a buffered read operation is done, and release the shared
+ * lock on inode->i_rwsem.
+ */
+void netfs_end_io_read(struct inode *inode)
+	__releases(inode->i_rwsem)
+{
+	up_read(&inode->i_rwsem);
+}
+EXPORT_SYMBOL(netfs_end_io_read);
+
+/**
+ * netfs_start_io_write - declare the file is being used for buffered writes
+ * @inode: file inode
+ *
+ * Declare that a buffered read operation is about to start, and ensure
+ * that we block all direct I/O.
+ */
+int netfs_start_io_write(struct inode *inode)
+	__acquires(inode->i_rwsem)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+
+	if (down_write_killable(&inode->i_rwsem) < 0)
+		return -ERESTARTSYS;
+	if (netfs_block_o_direct(ictx) < 0) {
+		up_write(&inode->i_rwsem);
+		return -ERESTARTSYS;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(netfs_start_io_write);
+
+/**
+ * netfs_end_io_write - declare that the buffered write operation is done
+ * @inode: file inode
+ *
+ * Declare that a buffered write operation is done, and release the
+ * lock on inode->i_rwsem.
+ */
+void netfs_end_io_write(struct inode *inode)
+	__releases(inode->i_rwsem)
+{
+	up_write(&inode->i_rwsem);
+}
+EXPORT_SYMBOL(netfs_end_io_write);
+
+/* Call with exclusively locked inode->i_rwsem */
+static int netfs_block_buffered(struct inode *inode)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+	int ret;
+
+	if (!test_bit(NETFS_ICTX_ODIRECT, &ictx->flags)) {
+		set_bit(NETFS_ICTX_ODIRECT, &ictx->flags);
+		if (inode->i_mapping->nrpages != 0) {
+			unmap_mapping_range(inode->i_mapping, 0, 0, 0);
+			ret = filemap_fdatawait(inode->i_mapping);
+			if (ret < 0) {
+				clear_bit(NETFS_ICTX_ODIRECT, &ictx->flags);
+				return ret;
+			}
+		}
+	}
+	return 0;
+}
+
+/**
+ * netfs_start_io_direct - declare the file is being used for direct i/o
+ * @inode: file inode
+ *
+ * Declare that a direct I/O operation is about to start, and ensure
+ * that we block all buffered I/O.
+ * On exit, the function ensures that the NETFS_ICTX_ODIRECT flag is set,
+ * and holds a shared lock on inode->i_rwsem to ensure that the flag
+ * cannot be changed.
+ * In practice, this means that direct I/O operations are allowed to
+ * execute in parallel, thanks to the shared lock, whereas buffered I/O
+ * operations need to wait to grab an exclusive lock in order to clear
+ * NETFS_ICTX_ODIRECT.
+ * Note that buffered writes and truncates both take a write lock on
+ * inode->i_rwsem, meaning that those are serialised w.r.t. O_DIRECT.
+ */
+int netfs_start_io_direct(struct inode *inode)
+	__acquires(inode->i_rwsem)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+	int ret;
+
+	/* Be an optimist! */
+	if (down_read_interruptible(&inode->i_rwsem) < 0)
+		return -ERESTARTSYS;
+	if (test_bit(NETFS_ICTX_ODIRECT, &ictx->flags) != 0)
+		return 0;
+	up_read(&inode->i_rwsem);
+
+	/* Slow path.... */
+	if (down_write_killable(&inode->i_rwsem) < 0)
+		return -ERESTARTSYS;
+	ret = netfs_block_buffered(inode);
+	if (ret < 0) {
+		up_write(&inode->i_rwsem);
+		return ret;
+	}
+	downgrade_write(&inode->i_rwsem);
+	return 0;
+}
+EXPORT_SYMBOL(netfs_start_io_direct);
+
+/**
+ * netfs_end_io_direct - declare that the direct i/o operation is done
+ * @inode: file inode
+ *
+ * Declare that a direct I/O operation is done, and release the shared
+ * lock on inode->i_rwsem.
+ */
+void netfs_end_io_direct(struct inode *inode)
+	__releases(inode->i_rwsem)
+{
+	up_read(&inode->i_rwsem);
+}
+EXPORT_SYMBOL(netfs_end_io_direct);
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index 068568702957..5e77618a7940 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -7,6 +7,8 @@
 
 #include <linux/module.h>
 #include <linux/export.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include "internal.h"
 #define CREATE_TRACE_POINTS
 #include <trace/events/netfs.h>
@@ -15,6 +17,113 @@ MODULE_DESCRIPTION("Network fs support");
 MODULE_AUTHOR("Red Hat, Inc.");
 MODULE_LICENSE("GPL");
 
+EXPORT_TRACEPOINT_SYMBOL(netfs_sreq);
+
 unsigned netfs_debug;
 module_param_named(debug, netfs_debug, uint, S_IWUSR | S_IRUGO);
 MODULE_PARM_DESC(netfs_debug, "Netfs support debugging mask");
+
+#ifdef CONFIG_PROC_FS
+LIST_HEAD(netfs_io_requests);
+DEFINE_SPINLOCK(netfs_proc_lock);
+
+static const char *netfs_origins[nr__netfs_io_origin] = {
+	[NETFS_READAHEAD]		= "RA",
+	[NETFS_READPAGE]		= "RP",
+	[NETFS_READ_FOR_WRITE]		= "RW",
+	[NETFS_WRITEBACK]		= "WB",
+	[NETFS_WRITETHROUGH]		= "WT",
+	[NETFS_LAUNDER_WRITE]		= "LW",
+	[NETFS_UNBUFFERED_WRITE]	= "UW",
+	[NETFS_DIO_READ]		= "DR",
+	[NETFS_DIO_WRITE]		= "DW",
+};
+
+/*
+ * Generate a list of I/O requests in /proc/fs/netfs/requests
+ */
+static int netfs_requests_seq_show(struct seq_file *m, void *v)
+{
+	struct netfs_io_request *rreq;
+
+	if (v == &netfs_io_requests) {
+		seq_puts(m,
+			 "REQUEST  OR REF FL ERR  OPS COVERAGE\n"
+			 "======== == === == ==== === =========\n"
+			 );
+		return 0;
+	}
+
+	rreq = list_entry(v, struct netfs_io_request, proc_link);
+	seq_printf(m,
+		   "%08x %s %3d %2lx %4d %3d @%04llx %zx/%zx",
+		   rreq->debug_id,
+		   netfs_origins[rreq->origin],
+		   refcount_read(&rreq->ref),
+		   rreq->flags,
+		   rreq->error,
+		   atomic_read(&rreq->nr_outstanding),
+		   rreq->start, rreq->submitted, rreq->len);
+	seq_putc(m, '\n');
+	return 0;
+}
+
+static void *netfs_requests_seq_start(struct seq_file *m, loff_t *_pos)
+	__acquires(rcu)
+{
+	rcu_read_lock();
+	return seq_list_start_head(&netfs_io_requests, *_pos);
+}
+
+static void *netfs_requests_seq_next(struct seq_file *m, void *v, loff_t *_pos)
+{
+	return seq_list_next(v, &netfs_io_requests, _pos);
+}
+
+static void netfs_requests_seq_stop(struct seq_file *m, void *v)
+	__releases(rcu)
+{
+	rcu_read_unlock();
+}
+
+static const struct seq_operations netfs_requests_seq_ops = {
+	.start  = netfs_requests_seq_start,
+	.next   = netfs_requests_seq_next,
+	.stop   = netfs_requests_seq_stop,
+	.show   = netfs_requests_seq_show,
+};
+#endif /* CONFIG_PROC_FS */
+
+static int __init netfs_init(void)
+{
+	int ret = -ENOMEM;
+
+	if (!proc_mkdir("fs/netfs", NULL))
+		goto error;
+	if (!proc_create_seq("fs/netfs/requests", S_IFREG | 0444, NULL,
+			     &netfs_requests_seq_ops))
+		goto error_proc;
+#ifdef CONFIG_FSCACHE_STATS
+	if (!proc_create_single("fs/netfs/stats", S_IFREG | 0444, NULL,
+				netfs_stats_show))
+		goto error_proc;
+#endif
+
+	ret = fscache_init();
+	if (ret < 0)
+		goto error_proc;
+	return 0;
+
+error_proc:
+	remove_proc_entry("fs/netfs", NULL);
+error:
+	return ret;
+}
+fs_initcall(netfs_init);
+
+static void __exit netfs_exit(void)
+{
+	fscache_exit();
+	remove_proc_entry("fs/netfs", NULL);
+}
+module_exit(netfs_exit);
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
new file mode 100644
index 000000000000..90051ced8e2a
--- /dev/null
+++ b/fs/netfs/misc.c
@@ -0,0 +1,260 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Miscellaneous routines.
+ *
+ * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/swap.h>
+#include "internal.h"
+
+/*
+ * Attach a folio to the buffer and maybe set marks on it to say that we need
+ * to put the folio later and twiddle the pagecache flags.
+ */
+int netfs_xa_store_and_mark(struct xarray *xa, unsigned long index,
+			    struct folio *folio, unsigned int flags,
+			    gfp_t gfp_mask)
+{
+	XA_STATE_ORDER(xas, xa, index, folio_order(folio));
+
+retry:
+	xas_lock(&xas);
+	for (;;) {
+		xas_store(&xas, folio);
+		if (!xas_error(&xas))
+			break;
+		xas_unlock(&xas);
+		if (!xas_nomem(&xas, gfp_mask))
+			return xas_error(&xas);
+		goto retry;
+	}
+
+	if (flags & NETFS_FLAG_PUT_MARK)
+		xas_set_mark(&xas, NETFS_BUF_PUT_MARK);
+	if (flags & NETFS_FLAG_PAGECACHE_MARK)
+		xas_set_mark(&xas, NETFS_BUF_PAGECACHE_MARK);
+	xas_unlock(&xas);
+	return xas_error(&xas);
+}
+
+/*
+ * Create the specified range of folios in the buffer attached to the read
+ * request.  The folios are marked with NETFS_BUF_PUT_MARK so that we know that
+ * these need freeing later.
+ */
+int netfs_add_folios_to_buffer(struct xarray *buffer,
+			       struct address_space *mapping,
+			       pgoff_t index, pgoff_t to, gfp_t gfp_mask)
+{
+	struct folio *folio;
+	int ret;
+
+	if (to + 1 == index) /* Page range is inclusive */
+		return 0;
+
+	do {
+		/* TODO: Figure out what order folio can be allocated here */
+		folio = filemap_alloc_folio(readahead_gfp_mask(mapping), 0);
+		if (!folio)
+			return -ENOMEM;
+		folio->index = index;
+		ret = netfs_xa_store_and_mark(buffer, index, folio,
+					      NETFS_FLAG_PUT_MARK, gfp_mask);
+		if (ret < 0) {
+			folio_put(folio);
+			return ret;
+		}
+
+		index += folio_nr_pages(folio);
+	} while (index <= to && index != 0);
+
+	return 0;
+}
+
+/*
+ * Clear an xarray buffer, putting a ref on the folios that have
+ * NETFS_BUF_PUT_MARK set.
+ */
+void netfs_clear_buffer(struct xarray *buffer)
+{
+	struct folio *folio;
+	XA_STATE(xas, buffer, 0);
+
+	rcu_read_lock();
+	xas_for_each_marked(&xas, folio, ULONG_MAX, NETFS_BUF_PUT_MARK) {
+		folio_put(folio);
+	}
+	rcu_read_unlock();
+	xa_destroy(buffer);
+}
+
+/**
+ * netfs_dirty_folio - Mark folio dirty and pin a cache object for writeback
+ * @mapping: The mapping the folio belongs to.
+ * @folio: The folio being dirtied.
+ *
+ * Set the dirty flag on a folio and pin an in-use cache object in memory so
+ * that writeback can later write to it.  This is intended to be called from
+ * the filesystem's ->dirty_folio() method.
+ *
+ * Return: true if the dirty flag was set on the folio, false otherwise.
+ */
+bool netfs_dirty_folio(struct address_space *mapping, struct folio *folio)
+{
+	struct inode *inode = mapping->host;
+	struct netfs_inode *ictx = netfs_inode(inode);
+	struct fscache_cookie *cookie = netfs_i_cookie(ictx);
+	bool need_use = false;
+
+	_enter("");
+
+	if (!filemap_dirty_folio(mapping, folio))
+		return false;
+	if (!fscache_cookie_valid(cookie))
+		return true;
+
+	if (!(inode->i_state & I_PINNING_NETFS_WB)) {
+		spin_lock(&inode->i_lock);
+		if (!(inode->i_state & I_PINNING_NETFS_WB)) {
+			inode->i_state |= I_PINNING_NETFS_WB;
+			need_use = true;
+		}
+		spin_unlock(&inode->i_lock);
+
+		if (need_use)
+			fscache_use_cookie(cookie, true);
+	}
+	return true;
+}
+EXPORT_SYMBOL(netfs_dirty_folio);
+
+/**
+ * netfs_unpin_writeback - Unpin writeback resources
+ * @inode: The inode on which the cookie resides
+ * @wbc: The writeback control
+ *
+ * Unpin the writeback resources pinned by netfs_dirty_folio().  This is
+ * intended to be called as/by the netfs's ->write_inode() method.
+ */
+int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc)
+{
+	struct fscache_cookie *cookie = netfs_i_cookie(netfs_inode(inode));
+
+	if (wbc->unpinned_netfs_wb)
+		fscache_unuse_cookie(cookie, NULL, NULL);
+	return 0;
+}
+EXPORT_SYMBOL(netfs_unpin_writeback);
+
+/**
+ * netfs_clear_inode_writeback - Clear writeback resources pinned by an inode
+ * @inode: The inode to clean up
+ * @aux: Auxiliary data to apply to the inode
+ *
+ * Clear any writeback resources held by an inode when the inode is evicted.
+ * This must be called before clear_inode() is called.
+ */
+void netfs_clear_inode_writeback(struct inode *inode, const void *aux)
+{
+	struct fscache_cookie *cookie = netfs_i_cookie(netfs_inode(inode));
+
+	if (inode->i_state & I_PINNING_NETFS_WB) {
+		loff_t i_size = i_size_read(inode);
+		fscache_unuse_cookie(cookie, aux, &i_size);
+	}
+}
+EXPORT_SYMBOL(netfs_clear_inode_writeback);
+
+/**
+ * netfs_invalidate_folio - Invalidate or partially invalidate a folio
+ * @folio: Folio proposed for release
+ * @offset: Offset of the invalidated region
+ * @length: Length of the invalidated region
+ *
+ * Invalidate part or all of a folio for a network filesystem.  The folio will
+ * be removed afterwards if the invalidated region covers the entire folio.
+ */
+void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
+{
+	struct netfs_folio *finfo = NULL;
+	size_t flen = folio_size(folio);
+
+	_enter("{%lx},%zx,%zx", folio->index, offset, length);
+
+	folio_wait_fscache(folio);
+
+	if (!folio_test_private(folio))
+		return;
+
+	finfo = netfs_folio_info(folio);
+
+	if (offset == 0 && length >= flen)
+		goto erase_completely;
+
+	if (finfo) {
+		/* We have a partially uptodate page from a streaming write. */
+		unsigned int fstart = finfo->dirty_offset;
+		unsigned int fend = fstart + finfo->dirty_len;
+		unsigned int end = offset + length;
+
+		if (offset >= fend)
+			return;
+		if (end <= fstart)
+			return;
+		if (offset <= fstart && end >= fend)
+			goto erase_completely;
+		if (offset <= fstart && end > fstart)
+			goto reduce_len;
+		if (offset > fstart && end >= fend)
+			goto move_start;
+		/* A partial write was split.  The caller has already zeroed
+		 * it, so just absorb the hole.
+		 */
+	}
+	return;
+
+erase_completely:
+	netfs_put_group(netfs_folio_group(folio));
+	folio_detach_private(folio);
+	folio_clear_uptodate(folio);
+	kfree(finfo);
+	return;
+reduce_len:
+	finfo->dirty_len = offset + length - finfo->dirty_offset;
+	return;
+move_start:
+	finfo->dirty_len -= offset - finfo->dirty_offset;
+	finfo->dirty_offset = offset;
+}
+EXPORT_SYMBOL(netfs_invalidate_folio);
+
+/**
+ * netfs_release_folio - Try to release a folio
+ * @folio: Folio proposed for release
+ * @gfp: Flags qualifying the release
+ *
+ * Request release of a folio and clean up its private state if it's not busy.
+ * Returns true if the folio can now be released, false if not
+ */
+bool netfs_release_folio(struct folio *folio, gfp_t gfp)
+{
+	struct netfs_inode *ctx = netfs_inode(folio_inode(folio));
+	unsigned long long end;
+
+	end = folio_pos(folio) + folio_size(folio);
+	if (end > ctx->zero_point)
+		ctx->zero_point = end;
+
+	if (folio_test_private(folio))
+		return false;
+	if (folio_test_fscache(folio)) {
+		if (current_is_kswapd() || !(gfp & __GFP_FS))
+			return false;
+		folio_wait_fscache(folio);
+	}
+
+	fscache_note_page_release(netfs_i_cookie(ctx));
+	return true;
+}
+EXPORT_SYMBOL(netfs_release_folio);
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index e17cdf53f6a7..610ceb5bd86c 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -20,14 +20,20 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 	struct inode *inode = file ? file_inode(file) : mapping->host;
 	struct netfs_inode *ctx = netfs_inode(inode);
 	struct netfs_io_request *rreq;
+	bool is_unbuffered = (origin == NETFS_UNBUFFERED_WRITE ||
+			      origin == NETFS_DIO_READ ||
+			      origin == NETFS_DIO_WRITE);
+	bool cached = !is_unbuffered && netfs_is_cache_enabled(ctx);
 	int ret;
 
-	rreq = kzalloc(sizeof(struct netfs_io_request), GFP_KERNEL);
+	rreq = kzalloc(ctx->ops->io_request_size ?: sizeof(struct netfs_io_request),
+		       GFP_KERNEL);
 	if (!rreq)
 		return ERR_PTR(-ENOMEM);
 
 	rreq->start	= start;
 	rreq->len	= len;
+	rreq->upper_len	= len;
 	rreq->origin	= origin;
 	rreq->netfs_ops	= ctx->ops;
 	rreq->mapping	= mapping;
@@ -35,8 +41,14 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 	rreq->i_size	= i_size_read(inode);
 	rreq->debug_id	= atomic_inc_return(&debug_ids);
 	INIT_LIST_HEAD(&rreq->subrequests);
+	INIT_WORK(&rreq->work, NULL);
 	refcount_set(&rreq->ref, 1);
+
 	__set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
+	if (cached)
+		__set_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags);
+	if (file && file->f_flags & O_NONBLOCK)
+		__set_bit(NETFS_RREQ_NONBLOCK, &rreq->flags);
 	if (rreq->netfs_ops->init_request) {
 		ret = rreq->netfs_ops->init_request(rreq, file);
 		if (ret < 0) {
@@ -45,6 +57,8 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 		}
 	}
 
+	trace_netfs_rreq_ref(rreq->debug_id, 1, netfs_rreq_trace_new);
+	netfs_proc_add_rreq(rreq);
 	netfs_stat(&netfs_n_rh_rreq);
 	return rreq;
 }
@@ -74,33 +88,47 @@ static void netfs_free_request(struct work_struct *work)
 {
 	struct netfs_io_request *rreq =
 		container_of(work, struct netfs_io_request, work);
+	unsigned int i;
 
 	trace_netfs_rreq(rreq, netfs_rreq_trace_free);
+	netfs_proc_del_rreq(rreq);
 	netfs_clear_subrequests(rreq, false);
 	if (rreq->netfs_ops->free_request)
 		rreq->netfs_ops->free_request(rreq);
 	if (rreq->cache_resources.ops)
 		rreq->cache_resources.ops->end_operation(&rreq->cache_resources);
-	kfree(rreq);
+	if (rreq->direct_bv) {
+		for (i = 0; i < rreq->direct_bv_count; i++) {
+			if (rreq->direct_bv[i].bv_page) {
+				if (rreq->direct_bv_unpin)
+					unpin_user_page(rreq->direct_bv[i].bv_page);
+			}
+		}
+		kvfree(rreq->direct_bv);
+	}
+	kfree_rcu(rreq, rcu);
 	netfs_stat_d(&netfs_n_rh_rreq);
 }
 
 void netfs_put_request(struct netfs_io_request *rreq, bool was_async,
 		       enum netfs_rreq_ref_trace what)
 {
-	unsigned int debug_id = rreq->debug_id;
+	unsigned int debug_id;
 	bool dead;
 	int r;
 
-	dead = __refcount_dec_and_test(&rreq->ref, &r);
-	trace_netfs_rreq_ref(debug_id, r - 1, what);
-	if (dead) {
-		if (was_async) {
-			rreq->work.func = netfs_free_request;
-			if (!queue_work(system_unbound_wq, &rreq->work))
-				BUG();
-		} else {
-			netfs_free_request(&rreq->work);
+	if (rreq) {
+		debug_id = rreq->debug_id;
+		dead = __refcount_dec_and_test(&rreq->ref, &r);
+		trace_netfs_rreq_ref(debug_id, r - 1, what);
+		if (dead) {
+			if (was_async) {
+				rreq->work.func = netfs_free_request;
+				if (!queue_work(system_unbound_wq, &rreq->work))
+					BUG();
+			} else {
+				netfs_free_request(&rreq->work);
+			}
 		}
 	}
 }
@@ -112,8 +140,11 @@ struct netfs_io_subrequest *netfs_alloc_subrequest(struct netfs_io_request *rreq
 {
 	struct netfs_io_subrequest *subreq;
 
-	subreq = kzalloc(sizeof(struct netfs_io_subrequest), GFP_KERNEL);
+	subreq = kzalloc(rreq->netfs_ops->io_subrequest_size ?:
+			 sizeof(struct netfs_io_subrequest),
+			 GFP_KERNEL);
 	if (subreq) {
+		INIT_WORK(&subreq->work, NULL);
 		INIT_LIST_HEAD(&subreq->rreq_link);
 		refcount_set(&subreq->ref, 2);
 		subreq->rreq = rreq;
@@ -140,6 +171,8 @@ static void netfs_free_subrequest(struct netfs_io_subrequest *subreq,
 	struct netfs_io_request *rreq = subreq->rreq;
 
 	trace_netfs_sreq(subreq, netfs_sreq_trace_free);
+	if (rreq->netfs_ops->free_subrequest)
+		rreq->netfs_ops->free_subrequest(subreq);
 	kfree(subreq);
 	netfs_stat_d(&netfs_n_rh_sreq);
 	netfs_put_request(rreq, was_async, netfs_rreq_trace_put_subreq);
diff --git a/fs/netfs/output.c b/fs/netfs/output.c
new file mode 100644
index 000000000000..625eb68f3e5a
--- /dev/null
+++ b/fs/netfs/output.c
@@ -0,0 +1,478 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Network filesystem high-level write support.
+ *
+ * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/slab.h>
+#include <linux/writeback.h>
+#include <linux/pagevec.h>
+#include "internal.h"
+
+/**
+ * netfs_create_write_request - Create a write operation.
+ * @wreq: The write request this is storing from.
+ * @dest: The destination type
+ * @start: Start of the region this write will modify
+ * @len: Length of the modification
+ * @worker: The worker function to handle the write(s)
+ *
+ * Allocate a write operation, set it up and add it to the list on a write
+ * request.
+ */
+struct netfs_io_subrequest *netfs_create_write_request(struct netfs_io_request *wreq,
+						       enum netfs_io_source dest,
+						       loff_t start, size_t len,
+						       work_func_t worker)
+{
+	struct netfs_io_subrequest *subreq;
+
+	subreq = netfs_alloc_subrequest(wreq);
+	if (subreq) {
+		INIT_WORK(&subreq->work, worker);
+		subreq->source	= dest;
+		subreq->start	= start;
+		subreq->len	= len;
+		subreq->debug_index = wreq->subreq_counter++;
+
+		switch (subreq->source) {
+		case NETFS_UPLOAD_TO_SERVER:
+			netfs_stat(&netfs_n_wh_upload);
+			break;
+		case NETFS_WRITE_TO_CACHE:
+			netfs_stat(&netfs_n_wh_write);
+			break;
+		default:
+			BUG();
+		}
+
+		subreq->io_iter = wreq->io_iter;
+		iov_iter_advance(&subreq->io_iter, subreq->start - wreq->start);
+		iov_iter_truncate(&subreq->io_iter, subreq->len);
+
+		trace_netfs_sreq_ref(wreq->debug_id, subreq->debug_index,
+				     refcount_read(&subreq->ref),
+				     netfs_sreq_trace_new);
+		atomic_inc(&wreq->nr_outstanding);
+		list_add_tail(&subreq->rreq_link, &wreq->subrequests);
+		trace_netfs_sreq(subreq, netfs_sreq_trace_prepare);
+	}
+
+	return subreq;
+}
+EXPORT_SYMBOL(netfs_create_write_request);
+
+/*
+ * Process a completed write request once all the component operations have
+ * been completed.
+ */
+static void netfs_write_terminated(struct netfs_io_request *wreq, bool was_async)
+{
+	struct netfs_io_subrequest *subreq;
+	struct netfs_inode *ctx = netfs_inode(wreq->inode);
+	size_t transferred = 0;
+
+	_enter("R=%x[]", wreq->debug_id);
+
+	trace_netfs_rreq(wreq, netfs_rreq_trace_write_done);
+
+	list_for_each_entry(subreq, &wreq->subrequests, rreq_link) {
+		if (subreq->error || subreq->transferred == 0)
+			break;
+		transferred += subreq->transferred;
+		if (subreq->transferred < subreq->len)
+			break;
+	}
+	wreq->transferred = transferred;
+
+	list_for_each_entry(subreq, &wreq->subrequests, rreq_link) {
+		if (!subreq->error)
+			continue;
+		switch (subreq->source) {
+		case NETFS_UPLOAD_TO_SERVER:
+			/* Depending on the type of failure, this may prevent
+			 * writeback completion unless we're in disconnected
+			 * mode.
+			 */
+			if (!wreq->error)
+				wreq->error = subreq->error;
+			break;
+
+		case NETFS_WRITE_TO_CACHE:
+			/* Failure doesn't prevent writeback completion unless
+			 * we're in disconnected mode.
+			 */
+			if (subreq->error != -ENOBUFS)
+				ctx->ops->invalidate_cache(wreq);
+			break;
+
+		default:
+			WARN_ON_ONCE(1);
+			if (!wreq->error)
+				wreq->error = -EIO;
+			return;
+		}
+	}
+
+	wreq->cleanup(wreq);
+
+	if (wreq->origin == NETFS_DIO_WRITE &&
+	    wreq->mapping->nrpages) {
+		pgoff_t first = wreq->start >> PAGE_SHIFT;
+		pgoff_t last = (wreq->start + wreq->transferred - 1) >> PAGE_SHIFT;
+		invalidate_inode_pages2_range(wreq->mapping, first, last);
+	}
+
+	if (wreq->origin == NETFS_DIO_WRITE)
+		inode_dio_end(wreq->inode);
+
+	_debug("finished");
+	trace_netfs_rreq(wreq, netfs_rreq_trace_wake_ip);
+	clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &wreq->flags);
+	wake_up_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS);
+
+	if (wreq->iocb) {
+		wreq->iocb->ki_pos += transferred;
+		if (wreq->iocb->ki_complete)
+			wreq->iocb->ki_complete(
+				wreq->iocb, wreq->error ? wreq->error : transferred);
+	}
+
+	netfs_clear_subrequests(wreq, was_async);
+	netfs_put_request(wreq, was_async, netfs_rreq_trace_put_complete);
+}
+
+/*
+ * Deal with the completion of writing the data to the cache.
+ */
+void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error,
+				       bool was_async)
+{
+	struct netfs_io_subrequest *subreq = _op;
+	struct netfs_io_request *wreq = subreq->rreq;
+	unsigned int u;
+
+	_enter("%x[%x] %zd", wreq->debug_id, subreq->debug_index, transferred_or_error);
+
+	switch (subreq->source) {
+	case NETFS_UPLOAD_TO_SERVER:
+		netfs_stat(&netfs_n_wh_upload_done);
+		break;
+	case NETFS_WRITE_TO_CACHE:
+		netfs_stat(&netfs_n_wh_write_done);
+		break;
+	case NETFS_INVALID_WRITE:
+		break;
+	default:
+		BUG();
+	}
+
+	if (IS_ERR_VALUE(transferred_or_error)) {
+		subreq->error = transferred_or_error;
+		trace_netfs_failure(wreq, subreq, transferred_or_error,
+				    netfs_fail_write);
+		goto failed;
+	}
+
+	if (WARN(transferred_or_error > subreq->len - subreq->transferred,
+		 "Subreq excess write: R%x[%x] %zd > %zu - %zu",
+		 wreq->debug_id, subreq->debug_index,
+		 transferred_or_error, subreq->len, subreq->transferred))
+		transferred_or_error = subreq->len - subreq->transferred;
+
+	subreq->error = 0;
+	subreq->transferred += transferred_or_error;
+
+	if (iov_iter_count(&subreq->io_iter) != subreq->len - subreq->transferred)
+		pr_warn("R=%08x[%u] ITER POST-MISMATCH %zx != %zx-%zx %x\n",
+			wreq->debug_id, subreq->debug_index,
+			iov_iter_count(&subreq->io_iter), subreq->len,
+			subreq->transferred, subreq->io_iter.iter_type);
+
+	if (subreq->transferred < subreq->len)
+		goto incomplete;
+
+	__clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags);
+out:
+	trace_netfs_sreq(subreq, netfs_sreq_trace_terminated);
+
+	/* If we decrement nr_outstanding to 0, the ref belongs to us. */
+	u = atomic_dec_return(&wreq->nr_outstanding);
+	if (u == 0)
+		netfs_write_terminated(wreq, was_async);
+	else if (u == 1)
+		wake_up_var(&wreq->nr_outstanding);
+
+	netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated);
+	return;
+
+incomplete:
+	if (transferred_or_error == 0) {
+		if (__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) {
+			subreq->error = -ENODATA;
+			goto failed;
+		}
+	} else {
+		__clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags);
+	}
+
+	__set_bit(NETFS_SREQ_SHORT_IO, &subreq->flags);
+	set_bit(NETFS_RREQ_INCOMPLETE_IO, &wreq->flags);
+	goto out;
+
+failed:
+	switch (subreq->source) {
+	case NETFS_WRITE_TO_CACHE:
+		netfs_stat(&netfs_n_wh_write_failed);
+		set_bit(NETFS_RREQ_INCOMPLETE_IO, &wreq->flags);
+		break;
+	case NETFS_UPLOAD_TO_SERVER:
+		netfs_stat(&netfs_n_wh_upload_failed);
+		set_bit(NETFS_RREQ_FAILED, &wreq->flags);
+		wreq->error = subreq->error;
+		break;
+	default:
+		break;
+	}
+	goto out;
+}
+EXPORT_SYMBOL(netfs_write_subrequest_terminated);
+
+static void netfs_write_to_cache_op(struct netfs_io_subrequest *subreq)
+{
+	struct netfs_io_request *wreq = subreq->rreq;
+	struct netfs_cache_resources *cres = &wreq->cache_resources;
+
+	trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
+
+	cres->ops->write(cres, subreq->start, &subreq->io_iter,
+			 netfs_write_subrequest_terminated, subreq);
+}
+
+static void netfs_write_to_cache_op_worker(struct work_struct *work)
+{
+	struct netfs_io_subrequest *subreq =
+		container_of(work, struct netfs_io_subrequest, work);
+
+	netfs_write_to_cache_op(subreq);
+}
+
+/**
+ * netfs_queue_write_request - Queue a write request for attention
+ * @subreq: The write request to be queued
+ *
+ * Queue the specified write request for processing by a worker thread.  We
+ * pass the caller's ref on the request to the worker thread.
+ */
+void netfs_queue_write_request(struct netfs_io_subrequest *subreq)
+{
+	if (!queue_work(system_unbound_wq, &subreq->work))
+		netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_wip);
+}
+EXPORT_SYMBOL(netfs_queue_write_request);
+
+/*
+ * Set up a op for writing to the cache.
+ */
+static void netfs_set_up_write_to_cache(struct netfs_io_request *wreq)
+{
+	struct netfs_cache_resources *cres = &wreq->cache_resources;
+	struct netfs_io_subrequest *subreq;
+	struct netfs_inode *ctx = netfs_inode(wreq->inode);
+	struct fscache_cookie *cookie = netfs_i_cookie(ctx);
+	loff_t start = wreq->start;
+	size_t len = wreq->len;
+	int ret;
+
+	if (!fscache_cookie_enabled(cookie)) {
+		clear_bit(NETFS_RREQ_WRITE_TO_CACHE, &wreq->flags);
+		return;
+	}
+
+	_debug("write to cache");
+	ret = fscache_begin_write_operation(cres, cookie);
+	if (ret < 0)
+		return;
+
+	ret = cres->ops->prepare_write(cres, &start, &len, wreq->upper_len,
+				       i_size_read(wreq->inode), true);
+	if (ret < 0)
+		return;
+
+	subreq = netfs_create_write_request(wreq, NETFS_WRITE_TO_CACHE, start, len,
+					    netfs_write_to_cache_op_worker);
+	if (!subreq)
+		return;
+
+	netfs_write_to_cache_op(subreq);
+}
+
+/*
+ * Begin the process of writing out a chunk of data.
+ *
+ * We are given a write request that holds a series of dirty regions and
+ * (partially) covers a sequence of folios, all of which are present.  The
+ * pages must have been marked as writeback as appropriate.
+ *
+ * We need to perform the following steps:
+ *
+ * (1) If encrypting, create an output buffer and encrypt each block of the
+ *     data into it, otherwise the output buffer will point to the original
+ *     folios.
+ *
+ * (2) If the data is to be cached, set up a write op for the entire output
+ *     buffer to the cache, if the cache wants to accept it.
+ *
+ * (3) If the data is to be uploaded (ie. not merely cached):
+ *
+ *     (a) If the data is to be compressed, create a compression buffer and
+ *         compress the data into it.
+ *
+ *     (b) For each destination we want to upload to, set up write ops to write
+ *         to that destination.  We may need multiple writes if the data is not
+ *         contiguous or the span exceeds wsize for a server.
+ */
+int netfs_begin_write(struct netfs_io_request *wreq, bool may_wait,
+		      enum netfs_write_trace what)
+{
+	struct netfs_inode *ctx = netfs_inode(wreq->inode);
+
+	_enter("R=%x %llx-%llx f=%lx",
+	       wreq->debug_id, wreq->start, wreq->start + wreq->len - 1,
+	       wreq->flags);
+
+	trace_netfs_write(wreq, what);
+	if (wreq->len == 0 || wreq->iter.count == 0) {
+		pr_err("Zero-sized write [R=%x]\n", wreq->debug_id);
+		return -EIO;
+	}
+
+	if (wreq->origin == NETFS_DIO_WRITE)
+		inode_dio_begin(wreq->inode);
+
+	wreq->io_iter = wreq->iter;
+
+	/* ->outstanding > 0 carries a ref */
+	netfs_get_request(wreq, netfs_rreq_trace_get_for_outstanding);
+	atomic_set(&wreq->nr_outstanding, 1);
+
+	/* Start the encryption/compression going.  We can do that in the
+	 * background whilst we generate a list of write ops that we want to
+	 * perform.
+	 */
+	// TODO: Encrypt or compress the region as appropriate
+
+	/* We need to write all of the region to the cache */
+	if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &wreq->flags))
+		netfs_set_up_write_to_cache(wreq);
+
+	/* However, we don't necessarily write all of the region to the server.
+	 * Caching of reads is being managed this way also.
+	 */
+	if (test_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags))
+		ctx->ops->create_write_requests(wreq, wreq->start, wreq->len);
+
+	if (atomic_dec_and_test(&wreq->nr_outstanding))
+		netfs_write_terminated(wreq, false);
+
+	if (!may_wait)
+		return -EIOCBQUEUED;
+
+	wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS,
+		    TASK_UNINTERRUPTIBLE);
+	return wreq->error;
+}
+
+/*
+ * Begin a write operation for writing through the pagecache.
+ */
+struct netfs_io_request *netfs_begin_writethrough(struct kiocb *iocb, size_t len)
+{
+	struct netfs_io_request *wreq;
+	struct file *file = iocb->ki_filp;
+
+	wreq = netfs_alloc_request(file->f_mapping, file, iocb->ki_pos, len,
+				   NETFS_WRITETHROUGH);
+	if (IS_ERR(wreq))
+		return wreq;
+
+	trace_netfs_write(wreq, netfs_write_trace_writethrough);
+
+	__set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags);
+	iov_iter_xarray(&wreq->iter, ITER_SOURCE, &wreq->mapping->i_pages, wreq->start, 0);
+	wreq->io_iter = wreq->iter;
+
+	/* ->outstanding > 0 carries a ref */
+	netfs_get_request(wreq, netfs_rreq_trace_get_for_outstanding);
+	atomic_set(&wreq->nr_outstanding, 1);
+	return wreq;
+}
+
+static void netfs_submit_writethrough(struct netfs_io_request *wreq, bool final)
+{
+	struct netfs_inode *ictx = netfs_inode(wreq->inode);
+	unsigned long long start;
+	size_t len;
+
+	if (!test_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags))
+		return;
+
+	start = wreq->start + wreq->submitted;
+	len = wreq->iter.count - wreq->submitted;
+	if (!final) {
+		len /= wreq->wsize; /* Round to number of maximum packets */
+		len *= wreq->wsize;
+	}
+
+	ictx->ops->create_write_requests(wreq, start, len);
+	wreq->submitted += len;
+}
+
+/*
+ * Advance the state of the write operation used when writing through the
+ * pagecache.  Data has been copied into the pagecache that we need to append
+ * to the request.  If we've added more than wsize then we need to create a new
+ * subrequest.
+ */
+int netfs_advance_writethrough(struct netfs_io_request *wreq, size_t copied, bool to_page_end)
+{
+	_enter("ic=%zu sb=%zu ws=%u cp=%zu tp=%u",
+	       wreq->iter.count, wreq->submitted, wreq->wsize, copied, to_page_end);
+
+	wreq->iter.count += copied;
+	wreq->io_iter.count += copied;
+	if (to_page_end && wreq->io_iter.count - wreq->submitted >= wreq->wsize)
+		netfs_submit_writethrough(wreq, false);
+
+	return wreq->error;
+}
+
+/*
+ * End a write operation used when writing through the pagecache.
+ */
+int netfs_end_writethrough(struct netfs_io_request *wreq, struct kiocb *iocb)
+{
+	int ret = -EIOCBQUEUED;
+
+	_enter("ic=%zu sb=%zu ws=%u",
+	       wreq->iter.count, wreq->submitted, wreq->wsize);
+
+	if (wreq->submitted < wreq->io_iter.count)
+		netfs_submit_writethrough(wreq, true);
+
+	if (atomic_dec_and_test(&wreq->nr_outstanding))
+		netfs_write_terminated(wreq, false);
+
+	if (is_sync_kiocb(iocb)) {
+		wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS,
+			    TASK_UNINTERRUPTIBLE);
+		ret = wreq->error;
+	}
+
+	netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
+	return ret;
+}
diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c
index 5510a7a14a40..deeba9f9dcf5 100644
--- a/fs/netfs/stats.c
+++ b/fs/netfs/stats.c
@@ -9,6 +9,8 @@
 #include <linux/seq_file.h>
 #include "internal.h"
 
+atomic_t netfs_n_rh_dio_read;
+atomic_t netfs_n_rh_dio_write;
 atomic_t netfs_n_rh_readahead;
 atomic_t netfs_n_rh_readpage;
 atomic_t netfs_n_rh_rreq;
@@ -27,32 +29,48 @@ atomic_t netfs_n_rh_write_begin;
 atomic_t netfs_n_rh_write_done;
 atomic_t netfs_n_rh_write_failed;
 atomic_t netfs_n_rh_write_zskip;
+atomic_t netfs_n_wh_wstream_conflict;
+atomic_t netfs_n_wh_upload;
+atomic_t netfs_n_wh_upload_done;
+atomic_t netfs_n_wh_upload_failed;
+atomic_t netfs_n_wh_write;
+atomic_t netfs_n_wh_write_done;
+atomic_t netfs_n_wh_write_failed;
 
-void netfs_stats_show(struct seq_file *m)
+int netfs_stats_show(struct seq_file *m, void *v)
 {
-	seq_printf(m, "RdHelp : RA=%u RP=%u WB=%u WBZ=%u rr=%u sr=%u\n",
+	seq_printf(m, "Netfs  : DR=%u DW=%u RA=%u RP=%u WB=%u WBZ=%u\n",
+		   atomic_read(&netfs_n_rh_dio_read),
+		   atomic_read(&netfs_n_rh_dio_write),
 		   atomic_read(&netfs_n_rh_readahead),
 		   atomic_read(&netfs_n_rh_readpage),
 		   atomic_read(&netfs_n_rh_write_begin),
-		   atomic_read(&netfs_n_rh_write_zskip),
-		   atomic_read(&netfs_n_rh_rreq),
-		   atomic_read(&netfs_n_rh_sreq));
-	seq_printf(m, "RdHelp : ZR=%u sh=%u sk=%u\n",
+		   atomic_read(&netfs_n_rh_write_zskip));
+	seq_printf(m, "Netfs  : ZR=%u sh=%u sk=%u\n",
 		   atomic_read(&netfs_n_rh_zero),
 		   atomic_read(&netfs_n_rh_short_read),
 		   atomic_read(&netfs_n_rh_write_zskip));
-	seq_printf(m, "RdHelp : DL=%u ds=%u df=%u di=%u\n",
+	seq_printf(m, "Netfs  : DL=%u ds=%u df=%u di=%u\n",
 		   atomic_read(&netfs_n_rh_download),
 		   atomic_read(&netfs_n_rh_download_done),
 		   atomic_read(&netfs_n_rh_download_failed),
 		   atomic_read(&netfs_n_rh_download_instead));
-	seq_printf(m, "RdHelp : RD=%u rs=%u rf=%u\n",
+	seq_printf(m, "Netfs  : RD=%u rs=%u rf=%u\n",
 		   atomic_read(&netfs_n_rh_read),
 		   atomic_read(&netfs_n_rh_read_done),
 		   atomic_read(&netfs_n_rh_read_failed));
-	seq_printf(m, "RdHelp : WR=%u ws=%u wf=%u\n",
-		   atomic_read(&netfs_n_rh_write),
-		   atomic_read(&netfs_n_rh_write_done),
-		   atomic_read(&netfs_n_rh_write_failed));
+	seq_printf(m, "Netfs  : UL=%u us=%u uf=%u\n",
+		   atomic_read(&netfs_n_wh_upload),
+		   atomic_read(&netfs_n_wh_upload_done),
+		   atomic_read(&netfs_n_wh_upload_failed));
+	seq_printf(m, "Netfs  : WR=%u ws=%u wf=%u\n",
+		   atomic_read(&netfs_n_wh_write),
+		   atomic_read(&netfs_n_wh_write_done),
+		   atomic_read(&netfs_n_wh_write_failed));
+	seq_printf(m, "Netfs  : rr=%u sr=%u wsc=%u\n",
+		   atomic_read(&netfs_n_rh_rreq),
+		   atomic_read(&netfs_n_rh_sreq),
+		   atomic_read(&netfs_n_wh_wstream_conflict));
+	return fscache_stats_show(m);
 }
 EXPORT_SYMBOL(netfs_stats_show);
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 01ac733a6320..f7e32d76e34d 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -169,8 +169,8 @@ config ROOT_NFS
 
 config NFS_FSCACHE
 	bool "Provide NFS client caching support"
-	depends on NFS_FS=m && FSCACHE || NFS_FS=y && FSCACHE=y
-	select NETFS_SUPPORT
+	depends on NFS_FS=m && NETFS_SUPPORT || NFS_FS=y && NETFS_SUPPORT=y
+	select FSCACHE
 	help
 	  Say Y here if you want NFS data to be cached locally on disc through
 	  the general filesystem cache manager
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index b4294a8aa2d4..f1eeb4914199 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -108,7 +108,7 @@ struct pnfs_block_dev {
 	struct pnfs_block_dev		*children;
 	u64				chunk_size;
 
-	struct bdev_handle		*bdev_handle;
+	struct file			*bdev_file;
 	u64				disk_offset;
 
 	u64				pr_key;
diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c
index c97ebc42ec0f..93ef7f864980 100644
--- a/fs/nfs/blocklayout/dev.c
+++ b/fs/nfs/blocklayout/dev.c
@@ -25,17 +25,17 @@ bl_free_device(struct pnfs_block_dev *dev)
 	} else {
 		if (dev->pr_registered) {
 			const struct pr_ops *ops =
-				dev->bdev_handle->bdev->bd_disk->fops->pr_ops;
+				file_bdev(dev->bdev_file)->bd_disk->fops->pr_ops;
 			int error;
 
-			error = ops->pr_register(dev->bdev_handle->bdev,
+			error = ops->pr_register(file_bdev(dev->bdev_file),
 				dev->pr_key, 0, false);
 			if (error)
 				pr_err("failed to unregister PR key.\n");
 		}
 
-		if (dev->bdev_handle)
-			bdev_release(dev->bdev_handle);
+		if (dev->bdev_file)
+			fput(dev->bdev_file);
 	}
 }
 
@@ -169,7 +169,7 @@ static bool bl_map_simple(struct pnfs_block_dev *dev, u64 offset,
 	map->start = dev->start;
 	map->len = dev->len;
 	map->disk_offset = dev->disk_offset;
-	map->bdev = dev->bdev_handle->bdev;
+	map->bdev = file_bdev(dev->bdev_file);
 	return true;
 }
 
@@ -236,26 +236,26 @@ bl_parse_simple(struct nfs_server *server, struct pnfs_block_dev *d,
 		struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
 {
 	struct pnfs_block_volume *v = &volumes[idx];
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	dev_t dev;
 
 	dev = bl_resolve_deviceid(server, v, gfp_mask);
 	if (!dev)
 		return -EIO;
 
-	bdev_handle = bdev_open_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_WRITE,
+	bdev_file = bdev_file_open_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_WRITE,
 				       NULL, NULL);
-	if (IS_ERR(bdev_handle)) {
+	if (IS_ERR(bdev_file)) {
 		printk(KERN_WARNING "pNFS: failed to open device %d:%d (%ld)\n",
-			MAJOR(dev), MINOR(dev), PTR_ERR(bdev_handle));
-		return PTR_ERR(bdev_handle);
+			MAJOR(dev), MINOR(dev), PTR_ERR(bdev_file));
+		return PTR_ERR(bdev_file);
 	}
-	d->bdev_handle = bdev_handle;
-	d->len = bdev_nr_bytes(bdev_handle->bdev);
+	d->bdev_file = bdev_file;
+	d->len = bdev_nr_bytes(file_bdev(bdev_file));
 	d->map = bl_map_simple;
 
 	printk(KERN_INFO "pNFS: using block device %s\n",
-		bdev_handle->bdev->bd_disk->disk_name);
+		file_bdev(bdev_file)->bd_disk->disk_name);
 	return 0;
 }
 
@@ -300,10 +300,10 @@ bl_validate_designator(struct pnfs_block_volume *v)
 	}
 }
 
-static struct bdev_handle *
+static struct file *
 bl_open_path(struct pnfs_block_volume *v, const char *prefix)
 {
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	const char *devname;
 
 	devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/%s%*phN",
@@ -311,15 +311,15 @@ bl_open_path(struct pnfs_block_volume *v, const char *prefix)
 	if (!devname)
 		return ERR_PTR(-ENOMEM);
 
-	bdev_handle = bdev_open_by_path(devname, BLK_OPEN_READ | BLK_OPEN_WRITE,
+	bdev_file = bdev_file_open_by_path(devname, BLK_OPEN_READ | BLK_OPEN_WRITE,
 					NULL, NULL);
-	if (IS_ERR(bdev_handle)) {
+	if (IS_ERR(bdev_file)) {
 		pr_warn("pNFS: failed to open device %s (%ld)\n",
-			devname, PTR_ERR(bdev_handle));
+			devname, PTR_ERR(bdev_file));
 	}
 
 	kfree(devname);
-	return bdev_handle;
+	return bdev_file;
 }
 
 static int
@@ -327,7 +327,7 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
 		struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
 {
 	struct pnfs_block_volume *v = &volumes[idx];
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	const struct pr_ops *ops;
 	int error;
 
@@ -340,14 +340,14 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
 	 * On other distributions like Debian, the default SCSI by-id path will
 	 * point to the dm-multipath device if one exists.
 	 */
-	bdev_handle = bl_open_path(v, "dm-uuid-mpath-0x");
-	if (IS_ERR(bdev_handle))
-		bdev_handle = bl_open_path(v, "wwn-0x");
-	if (IS_ERR(bdev_handle))
-		return PTR_ERR(bdev_handle);
-	d->bdev_handle = bdev_handle;
-
-	d->len = bdev_nr_bytes(d->bdev_handle->bdev);
+	bdev_file = bl_open_path(v, "dm-uuid-mpath-0x");
+	if (IS_ERR(bdev_file))
+		bdev_file = bl_open_path(v, "wwn-0x");
+	if (IS_ERR(bdev_file))
+		return PTR_ERR(bdev_file);
+	d->bdev_file = bdev_file;
+
+	d->len = bdev_nr_bytes(file_bdev(d->bdev_file));
 	d->map = bl_map_simple;
 	d->pr_key = v->scsi.pr_key;
 
@@ -355,20 +355,20 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
 		return -ENODEV;
 
 	pr_info("pNFS: using block device %s (reservation key 0x%llx)\n",
-		d->bdev_handle->bdev->bd_disk->disk_name, d->pr_key);
+		file_bdev(d->bdev_file)->bd_disk->disk_name, d->pr_key);
 
-	ops = d->bdev_handle->bdev->bd_disk->fops->pr_ops;
+	ops = file_bdev(d->bdev_file)->bd_disk->fops->pr_ops;
 	if (!ops) {
 		pr_err("pNFS: block device %s does not support reservations.",
-				d->bdev_handle->bdev->bd_disk->disk_name);
+				file_bdev(d->bdev_file)->bd_disk->disk_name);
 		error = -EINVAL;
 		goto out_blkdev_put;
 	}
 
-	error = ops->pr_register(d->bdev_handle->bdev, 0, d->pr_key, true);
+	error = ops->pr_register(file_bdev(d->bdev_file), 0, d->pr_key, true);
 	if (error) {
 		pr_err("pNFS: failed to register key for block device %s.",
-				d->bdev_handle->bdev->bd_disk->disk_name);
+				file_bdev(d->bdev_file)->bd_disk->disk_name);
 		goto out_blkdev_put;
 	}
 
@@ -376,7 +376,7 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
 	return 0;
 
 out_blkdev_put:
-	bdev_release(d->bdev_handle);
+	fput(d->bdev_file);
 	return error;
 }
 
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 44eca51b2808..fbdc9ca80f71 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -246,7 +246,7 @@ void nfs_free_client(struct nfs_client *clp)
 	put_nfs_version(clp->cl_nfs_mod);
 	kfree(clp->cl_hostname);
 	kfree(clp->cl_acceptor);
-	kfree(clp);
+	kfree_rcu(clp, rcu);
 }
 EXPORT_SYMBOL_GPL(nfs_free_client);
 
@@ -1006,6 +1006,14 @@ struct nfs_server *nfs_alloc_server(void)
 }
 EXPORT_SYMBOL_GPL(nfs_alloc_server);
 
+static void delayed_free(struct rcu_head *p)
+{
+	struct nfs_server *server = container_of(p, struct nfs_server, rcu);
+
+	nfs_free_iostats(server->io_stats);
+	kfree(server);
+}
+
 /*
  * Free up a server record
  */
@@ -1031,10 +1039,9 @@ void nfs_free_server(struct nfs_server *server)
 
 	ida_destroy(&server->lockowner_id);
 	ida_destroy(&server->openowner_id);
-	nfs_free_iostats(server->io_stats);
 	put_cred(server->cred);
-	kfree(server);
 	nfs_release_automount_timer();
+	call_rcu(&server->rcu, delayed_free);
 }
 EXPORT_SYMBOL_GPL(nfs_free_server);
 
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index fa1a14def45c..d4a42ce0c7e3 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -156,8 +156,8 @@ static int nfs_delegation_claim_locks(struct nfs4_state *state, const nfs4_state
 	list = &flctx->flc_posix;
 	spin_lock(&flctx->flc_lock);
 restart:
-	list_for_each_entry(fl, list, fl_list) {
-		if (nfs_file_open_context(fl->fl_file)->state != state)
+	for_each_file_lock(fl, list) {
+		if (nfs_file_open_context(fl->c.flc_file)->state != state)
 			continue;
 		spin_unlock(&flctx->flc_lock);
 		status = nfs4_lock_delegation_recall(fl, state, stateid);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index c8ecbe999059..ac505671efbd 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1431,9 +1431,9 @@ static bool nfs_verifier_is_delegated(struct dentry *dentry)
 static void nfs_set_verifier_locked(struct dentry *dentry, unsigned long verf)
 {
 	struct inode *inode = d_inode(dentry);
-	struct inode *dir = d_inode(dentry->d_parent);
+	struct inode *dir = d_inode_rcu(dentry->d_parent);
 
-	if (!nfs_verify_change_attribute(dir, verf))
+	if (!dir || !nfs_verify_change_attribute(dir, verf))
 		return;
 	if (inode && NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
 		nfs_set_verifier_delegated(&verf);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 8577ccf621f5..407c6e15afe2 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -720,15 +720,15 @@ do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 {
 	struct inode *inode = filp->f_mapping->host;
 	int status = 0;
-	unsigned int saved_type = fl->fl_type;
+	unsigned int saved_type = fl->c.flc_type;
 
 	/* Try local locking first */
 	posix_test_lock(filp, fl);
-	if (fl->fl_type != F_UNLCK) {
+	if (fl->c.flc_type != F_UNLCK) {
 		/* found a conflict */
 		goto out;
 	}
-	fl->fl_type = saved_type;
+	fl->c.flc_type = saved_type;
 
 	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
 		goto out_noconflict;
@@ -740,7 +740,7 @@ do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 out:
 	return status;
 out_noconflict:
-	fl->fl_type = F_UNLCK;
+	fl->c.flc_type = F_UNLCK;
 	goto out;
 }
 
@@ -765,7 +765,7 @@ do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 		 * 	If we're signalled while cleaning up locks on process exit, we
 		 * 	still need to complete the unlock.
 		 */
-		if (status < 0 && !(fl->fl_flags & FL_CLOSE))
+		if (status < 0 && !(fl->c.flc_flags & FL_CLOSE))
 			return status;
 	}
 
@@ -832,12 +832,12 @@ int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
 	int is_local = 0;
 
 	dprintk("NFS: lock(%pD2, t=%x, fl=%x, r=%lld:%lld)\n",
-			filp, fl->fl_type, fl->fl_flags,
+			filp, fl->c.flc_type, fl->c.flc_flags,
 			(long long)fl->fl_start, (long long)fl->fl_end);
 
 	nfs_inc_stats(inode, NFSIOS_VFSLOCK);
 
-	if (fl->fl_flags & FL_RECLAIM)
+	if (fl->c.flc_flags & FL_RECLAIM)
 		return -ENOGRACE;
 
 	if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FCNTL)
@@ -851,7 +851,7 @@ int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
 
 	if (IS_GETLK(cmd))
 		ret = do_getlk(filp, cmd, fl, is_local);
-	else if (fl->fl_type == F_UNLCK)
+	else if (lock_is_unlock(fl))
 		ret = do_unlk(filp, cmd, fl, is_local);
 	else
 		ret = do_setlk(filp, cmd, fl, is_local);
@@ -869,16 +869,16 @@ int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
 	int is_local = 0;
 
 	dprintk("NFS: flock(%pD2, t=%x, fl=%x)\n",
-			filp, fl->fl_type, fl->fl_flags);
+			filp, fl->c.flc_type, fl->c.flc_flags);
 
-	if (!(fl->fl_flags & FL_FLOCK))
+	if (!(fl->c.flc_flags & FL_FLOCK))
 		return -ENOLCK;
 
 	if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FLOCK)
 		is_local = 1;
 
 	/* We're simulating flock() locks using posix locks on the server */
-	if (fl->fl_type == F_UNLCK)
+	if (lock_is_unlock(fl))
 		return do_unlk(filp, cmd, fl, is_local);
 	return do_setlk(filp, cmd, fl, is_local);
 }
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index b05717fe0d4e..2d1bfee225c3 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -274,12 +274,6 @@ static void nfs_netfs_free_request(struct netfs_io_request *rreq)
 	put_nfs_open_context(rreq->netfs_priv);
 }
 
-static inline int nfs_netfs_begin_cache_operation(struct netfs_io_request *rreq)
-{
-	return fscache_begin_read_operation(&rreq->cache_resources,
-					    netfs_i_cookie(netfs_inode(rreq->inode)));
-}
-
 static struct nfs_netfs_io_data *nfs_netfs_alloc(struct netfs_io_subrequest *sreq)
 {
 	struct nfs_netfs_io_data *netfs;
@@ -387,7 +381,6 @@ void nfs_netfs_read_completion(struct nfs_pgio_header *hdr)
 const struct netfs_request_ops nfs_netfs_ops = {
 	.init_request		= nfs_netfs_init_request,
 	.free_request		= nfs_netfs_free_request,
-	.begin_cache_operation	= nfs_netfs_begin_cache_operation,
 	.issue_read		= nfs_netfs_issue_read,
 	.clamp_length		= nfs_netfs_clamp_length
 };
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index 5407ab8c8783..e3cb4923316b 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -80,7 +80,7 @@ static inline void nfs_netfs_put(struct nfs_netfs_io_data *netfs)
 }
 static inline void nfs_netfs_inode_init(struct nfs_inode *nfsi)
 {
-	netfs_inode_init(&nfsi->netfs, &nfs_netfs_ops);
+	netfs_inode_init(&nfsi->netfs, &nfs_netfs_ops, false);
 }
 extern void nfs_netfs_initiate_read(struct nfs_pgio_header *hdr);
 extern void nfs_netfs_read_completion(struct nfs_pgio_header *hdr);
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 2de66e4e8280..cbbe3f0193b8 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -963,7 +963,7 @@ nfs3_proc_lock(struct file *filp, int cmd, struct file_lock *fl)
 	struct nfs_open_context *ctx = nfs_file_open_context(filp);
 	int status;
 
-	if (fl->fl_flags & FL_CLOSE) {
+	if (fl->c.flc_flags & FL_CLOSE) {
 		l_ctx = nfs_get_lock_context(ctx);
 		if (IS_ERR(l_ctx))
 			l_ctx = NULL;
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 581698f1b7b2..6ff41ceb9f1c 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -330,7 +330,7 @@ extern int update_open_stateid(struct nfs4_state *state,
 				const nfs4_stateid *deleg_stateid,
 				fmode_t fmode);
 extern int nfs4_proc_setlease(struct file *file, int arg,
-			      struct file_lock **lease, void **priv);
+			      struct file_lease **lease, void **priv);
 extern int nfs4_proc_get_lease_time(struct nfs_client *clp,
 		struct nfs_fsinfo *fsinfo);
 extern void nfs4_update_changeattr(struct inode *dir,
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index e238abc78a13..1cd9652f3c28 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -439,7 +439,7 @@ void nfs42_ssc_unregister_ops(void)
 }
 #endif /* CONFIG_NFS_V4_2 */
 
-static int nfs4_setlease(struct file *file, int arg, struct file_lock **lease,
+static int nfs4_setlease(struct file *file, int arg, struct file_lease **lease,
 			 void **priv)
 {
 	return nfs4_proc_setlease(file, arg, lease, priv);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 23819a756508..815996cb27fc 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -6800,7 +6800,7 @@ static int _nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock
 	status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
 	switch (status) {
 		case 0:
-			request->fl_type = F_UNLCK;
+			request->c.flc_type = F_UNLCK;
 			break;
 		case -NFS4ERR_DENIED:
 			status = 0;
@@ -7018,8 +7018,8 @@ static struct rpc_task *nfs4_do_unlck(struct file_lock *fl,
 	/* Ensure this is an unlock - when canceling a lock, the
 	 * canceled lock is passed in, and it won't be an unlock.
 	 */
-	fl->fl_type = F_UNLCK;
-	if (fl->fl_flags & FL_CLOSE)
+	fl->c.flc_type = F_UNLCK;
+	if (fl->c.flc_flags & FL_CLOSE)
 		set_bit(NFS_CONTEXT_UNLOCK, &ctx->flags);
 
 	data = nfs4_alloc_unlockdata(fl, ctx, lsp, seqid);
@@ -7045,11 +7045,11 @@ static int nfs4_proc_unlck(struct nfs4_state *state, int cmd, struct file_lock *
 	struct rpc_task *task;
 	struct nfs_seqid *(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t);
 	int status = 0;
-	unsigned char fl_flags = request->fl_flags;
+	unsigned char saved_flags = request->c.flc_flags;
 
 	status = nfs4_set_lock_state(state, request);
 	/* Unlock _before_ we do the RPC call */
-	request->fl_flags |= FL_EXISTS;
+	request->c.flc_flags |= FL_EXISTS;
 	/* Exclude nfs_delegation_claim_locks() */
 	mutex_lock(&sp->so_delegreturn_mutex);
 	/* Exclude nfs4_reclaim_open_stateid() - note nesting! */
@@ -7073,14 +7073,16 @@ static int nfs4_proc_unlck(struct nfs4_state *state, int cmd, struct file_lock *
 	status = -ENOMEM;
 	if (IS_ERR(seqid))
 		goto out;
-	task = nfs4_do_unlck(request, nfs_file_open_context(request->fl_file), lsp, seqid);
+	task = nfs4_do_unlck(request,
+			     nfs_file_open_context(request->c.flc_file),
+			     lsp, seqid);
 	status = PTR_ERR(task);
 	if (IS_ERR(task))
 		goto out;
 	status = rpc_wait_for_completion_task(task);
 	rpc_put_task(task);
 out:
-	request->fl_flags = fl_flags;
+	request->c.flc_flags = saved_flags;
 	trace_nfs4_unlock(request, state, F_SETLK, status);
 	return status;
 }
@@ -7191,7 +7193,7 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata)
 		renew_lease(NFS_SERVER(d_inode(data->ctx->dentry)),
 				data->timestamp);
 		if (data->arg.new_lock && !data->cancelled) {
-			data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS);
+			data->fl.c.flc_flags &= ~(FL_SLEEP | FL_ACCESS);
 			if (locks_lock_inode_wait(lsp->ls_state->inode, &data->fl) < 0)
 				goto out_restart;
 		}
@@ -7292,7 +7294,8 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
 	if (nfs_server_capable(state->inode, NFS_CAP_MOVEABLE))
 		task_setup_data.flags |= RPC_TASK_MOVEABLE;
 
-	data = nfs4_alloc_lockdata(fl, nfs_file_open_context(fl->fl_file),
+	data = nfs4_alloc_lockdata(fl,
+				   nfs_file_open_context(fl->c.flc_file),
 				   fl->fl_u.nfs4_fl.owner, GFP_KERNEL);
 	if (data == NULL)
 		return -ENOMEM;
@@ -7398,10 +7401,10 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock
 {
 	struct nfs_inode *nfsi = NFS_I(state->inode);
 	struct nfs4_state_owner *sp = state->owner;
-	unsigned char fl_flags = request->fl_flags;
+	unsigned char flags = request->c.flc_flags;
 	int status;
 
-	request->fl_flags |= FL_ACCESS;
+	request->c.flc_flags |= FL_ACCESS;
 	status = locks_lock_inode_wait(state->inode, request);
 	if (status < 0)
 		goto out;
@@ -7410,7 +7413,7 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock
 	if (test_bit(NFS_DELEGATED_STATE, &state->flags)) {
 		/* Yes: cache locks! */
 		/* ...but avoid races with delegation recall... */
-		request->fl_flags = fl_flags & ~FL_SLEEP;
+		request->c.flc_flags = flags & ~FL_SLEEP;
 		status = locks_lock_inode_wait(state->inode, request);
 		up_read(&nfsi->rwsem);
 		mutex_unlock(&sp->so_delegreturn_mutex);
@@ -7420,7 +7423,7 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock
 	mutex_unlock(&sp->so_delegreturn_mutex);
 	status = _nfs4_do_setlk(state, cmd, request, NFS_LOCK_NEW);
 out:
-	request->fl_flags = fl_flags;
+	request->c.flc_flags = flags;
 	return status;
 }
 
@@ -7562,7 +7565,7 @@ nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request)
 	if (!(IS_SETLK(cmd) || IS_SETLKW(cmd)))
 		return -EINVAL;
 
-	if (request->fl_type == F_UNLCK) {
+	if (lock_is_unlock(request)) {
 		if (state != NULL)
 			return nfs4_proc_unlck(state, cmd, request);
 		return 0;
@@ -7571,7 +7574,7 @@ nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request)
 	if (state == NULL)
 		return -ENOLCK;
 
-	if ((request->fl_flags & FL_POSIX) &&
+	if ((request->c.flc_flags & FL_POSIX) &&
 	    !test_bit(NFS_STATE_POSIX_LOCKS, &state->flags))
 		return -ENOLCK;
 
@@ -7579,7 +7582,7 @@ nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request)
 	 * Don't rely on the VFS having checked the file open mode,
 	 * since it won't do this for flock() locks.
 	 */
-	switch (request->fl_type) {
+	switch (request->c.flc_type) {
 	case F_RDLCK:
 		if (!(filp->f_mode & FMODE_READ))
 			return -EBADF;
@@ -7601,7 +7604,7 @@ static int nfs4_delete_lease(struct file *file, void **priv)
 	return generic_setlease(file, F_UNLCK, NULL, priv);
 }
 
-static int nfs4_add_lease(struct file *file, int arg, struct file_lock **lease,
+static int nfs4_add_lease(struct file *file, int arg, struct file_lease **lease,
 			  void **priv)
 {
 	struct inode *inode = file_inode(file);
@@ -7619,7 +7622,7 @@ static int nfs4_add_lease(struct file *file, int arg, struct file_lock **lease,
 	return -EAGAIN;
 }
 
-int nfs4_proc_setlease(struct file *file, int arg, struct file_lock **lease,
+int nfs4_proc_setlease(struct file *file, int arg, struct file_lease **lease,
 		       void **priv)
 {
 	switch (arg) {
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 9a5d911a7edc..8cfabdbda336 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -847,15 +847,15 @@ void nfs4_close_sync(struct nfs4_state *state, fmode_t fmode)
  */
 static struct nfs4_lock_state *
 __nfs4_find_lock_state(struct nfs4_state *state,
-		       fl_owner_t fl_owner, fl_owner_t fl_owner2)
+		       fl_owner_t owner, fl_owner_t owner2)
 {
 	struct nfs4_lock_state *pos, *ret = NULL;
 	list_for_each_entry(pos, &state->lock_states, ls_locks) {
-		if (pos->ls_owner == fl_owner) {
+		if (pos->ls_owner == owner) {
 			ret = pos;
 			break;
 		}
-		if (pos->ls_owner == fl_owner2)
+		if (pos->ls_owner == owner2)
 			ret = pos;
 	}
 	if (ret)
@@ -868,7 +868,7 @@ __nfs4_find_lock_state(struct nfs4_state *state,
  * exists, return an uninitialized one.
  *
  */
-static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, fl_owner_t fl_owner)
+static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, fl_owner_t owner)
 {
 	struct nfs4_lock_state *lsp;
 	struct nfs_server *server = state->owner->so_server;
@@ -879,7 +879,7 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f
 	nfs4_init_seqid_counter(&lsp->ls_seqid);
 	refcount_set(&lsp->ls_count, 1);
 	lsp->ls_state = state;
-	lsp->ls_owner = fl_owner;
+	lsp->ls_owner = owner;
 	lsp->ls_seqid.owner_id = ida_alloc(&server->lockowner_id, GFP_KERNEL_ACCOUNT);
 	if (lsp->ls_seqid.owner_id < 0)
 		goto out_free;
@@ -980,7 +980,7 @@ int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl)
 
 	if (fl->fl_ops != NULL)
 		return 0;
-	lsp = nfs4_get_lock_state(state, fl->fl_owner);
+	lsp = nfs4_get_lock_state(state, fl->c.flc_owner);
 	if (lsp == NULL)
 		return -ENOMEM;
 	fl->fl_u.nfs4_fl.owner = lsp;
@@ -993,7 +993,7 @@ static int nfs4_copy_lock_stateid(nfs4_stateid *dst,
 		const struct nfs_lock_context *l_ctx)
 {
 	struct nfs4_lock_state *lsp;
-	fl_owner_t fl_owner, fl_flock_owner;
+	fl_owner_t owner, fl_flock_owner;
 	int ret = -ENOENT;
 
 	if (l_ctx == NULL)
@@ -1002,11 +1002,11 @@ static int nfs4_copy_lock_stateid(nfs4_stateid *dst,
 	if (test_bit(LK_STATE_IN_USE, &state->flags) == 0)
 		goto out;
 
-	fl_owner = l_ctx->lockowner;
+	owner = l_ctx->lockowner;
 	fl_flock_owner = l_ctx->open_context->flock_owner;
 
 	spin_lock(&state->state_lock);
-	lsp = __nfs4_find_lock_state(state, fl_owner, fl_flock_owner);
+	lsp = __nfs4_find_lock_state(state, owner, fl_flock_owner);
 	if (lsp && test_bit(NFS_LOCK_LOST, &lsp->ls_flags))
 		ret = -EIO;
 	else if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) {
@@ -1529,8 +1529,8 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
 	down_write(&nfsi->rwsem);
 	spin_lock(&flctx->flc_lock);
 restart:
-	list_for_each_entry(fl, list, fl_list) {
-		if (nfs_file_open_context(fl->fl_file)->state != state)
+	for_each_file_lock(fl, list) {
+		if (nfs_file_open_context(fl->c.flc_file)->state != state)
 			continue;
 		spin_unlock(&flctx->flc_lock);
 		status = ops->recover_lock(state, fl);
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index d27919d7241d..fd7cb15b08b2 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -699,7 +699,7 @@ DECLARE_EVENT_CLASS(nfs4_lock_event,
 
 			__entry->error = error < 0 ? -error : 0;
 			__entry->cmd = cmd;
-			__entry->type = request->fl_type;
+			__entry->type = request->c.flc_type;
 			__entry->start = request->fl_start;
 			__entry->end = request->fl_end;
 			__entry->dev = inode->i_sb->s_dev;
@@ -771,7 +771,7 @@ TRACE_EVENT(nfs4_set_lock,
 
 			__entry->error = error < 0 ? -error : 0;
 			__entry->cmd = cmd;
-			__entry->type = request->fl_type;
+			__entry->type = request->c.flc_type;
 			__entry->start = request->fl_start;
 			__entry->end = request->fl_end;
 			__entry->dev = inode->i_sb->s_dev;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 69406e60f391..1416099dfcd1 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1305,7 +1305,7 @@ static void encode_link(struct xdr_stream *xdr, const struct qstr *name, struct
 
 static inline int nfs4_lock_type(struct file_lock *fl, int block)
 {
-	if (fl->fl_type == F_RDLCK)
+	if (lock_is_read(fl))
 		return block ? NFS4_READW_LT : NFS4_READ_LT;
 	return block ? NFS4_WRITEW_LT : NFS4_WRITE_LT;
 }
@@ -5052,10 +5052,10 @@ static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl)
 		fl->fl_end = fl->fl_start + (loff_t)length - 1;
 		if (length == ~(uint64_t)0)
 			fl->fl_end = OFFSET_MAX;
-		fl->fl_type = F_WRLCK;
+		fl->c.flc_type = F_WRLCK;
 		if (type & 1)
-			fl->fl_type = F_RDLCK;
-		fl->fl_pid = 0;
+			fl->c.flc_type = F_RDLCK;
+		fl->c.flc_pid = 0;
 	}
 	p = xdr_decode_hyper(p, &clientid); /* read 8 bytes */
 	namelen = be32_to_cpup(p); /* read 4 bytes */  /* have read all 32 bytes now */
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index bb79d3a886ae..84bb85264572 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1301,7 +1301,7 @@ static bool
 is_whole_file_wrlock(struct file_lock *fl)
 {
 	return fl->fl_start == 0 && fl->fl_end == OFFSET_MAX &&
-			fl->fl_type == F_WRLCK;
+			lock_is_write(fl);
 }
 
 /* If we know the page is up to date, and we're not using byte range locks (or
@@ -1335,13 +1335,13 @@ static int nfs_can_extend_write(struct file *file, struct folio *folio,
 	spin_lock(&flctx->flc_lock);
 	if (!list_empty(&flctx->flc_posix)) {
 		fl = list_first_entry(&flctx->flc_posix, struct file_lock,
-					fl_list);
+					c.flc_list);
 		if (is_whole_file_wrlock(fl))
 			ret = 1;
 	} else if (!list_empty(&flctx->flc_flock)) {
 		fl = list_first_entry(&flctx->flc_flock, struct file_lock,
-					fl_list);
-		if (fl->fl_type == F_WRLCK)
+					c.flc_list);
+		if (lock_is_write(fl))
 			ret = 1;
 	}
 	spin_unlock(&flctx->flc_lock);
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 9cb7f0c33df5..b86d8494052c 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -662,8 +662,8 @@ nfsd_file_lease_notifier_call(struct notifier_block *nb, unsigned long arg,
 	struct file_lock *fl = data;
 
 	/* Only close files for F_SETLEASE leases */
-	if (fl->fl_flags & FL_LEASE)
-		nfsd_file_close_inode(file_inode(fl->fl_file));
+	if (fl->c.flc_flags & FL_LEASE)
+		nfsd_file_close_inode(file_inode(fl->c.flc_file));
 	return 0;
 }
 
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 926c29879c6a..32d23ef3e5de 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -674,7 +674,7 @@ static void nfs4_xdr_enc_cb_notify_lock(struct rpc_rqst *req,
 	const struct nfsd4_callback *cb = data;
 	const struct nfsd4_blocked_lock *nbl =
 		container_of(cb, struct nfsd4_blocked_lock, nbl_cb);
-	struct nfs4_lockowner *lo = (struct nfs4_lockowner *)nbl->nbl_lock.fl_owner;
+	struct nfs4_lockowner *lo = (struct nfs4_lockowner *)nbl->nbl_lock.c.flc_owner;
 	struct nfs4_cb_compound_hdr hdr = {
 		.ident = 0,
 		.minorversion = cb->cb_clp->cl_minorversion,
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 5e8096bc5eaa..4c0d00bdfbb1 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -25,7 +25,7 @@ static struct kmem_cache *nfs4_layout_cache;
 static struct kmem_cache *nfs4_layout_stateid_cache;
 
 static const struct nfsd4_callback_ops nfsd4_cb_layout_ops;
-static const struct lock_manager_operations nfsd4_layouts_lm_ops;
+static const struct lease_manager_operations nfsd4_layouts_lm_ops;
 
 const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] =  {
 #ifdef CONFIG_NFSD_FLEXFILELAYOUT
@@ -170,7 +170,7 @@ nfsd4_free_layout_stateid(struct nfs4_stid *stid)
 	spin_unlock(&fp->fi_lock);
 
 	if (!nfsd4_layout_ops[ls->ls_layout_type]->disable_recalls)
-		vfs_setlease(ls->ls_file->nf_file, F_UNLCK, NULL, (void **)&ls);
+		kernel_setlease(ls->ls_file->nf_file, F_UNLCK, NULL, (void **)&ls);
 	nfsd_file_put(ls->ls_file);
 
 	if (ls->ls_recalled)
@@ -182,27 +182,26 @@ nfsd4_free_layout_stateid(struct nfs4_stid *stid)
 static int
 nfsd4_layout_setlease(struct nfs4_layout_stateid *ls)
 {
-	struct file_lock *fl;
+	struct file_lease *fl;
 	int status;
 
 	if (nfsd4_layout_ops[ls->ls_layout_type]->disable_recalls)
 		return 0;
 
-	fl = locks_alloc_lock();
+	fl = locks_alloc_lease();
 	if (!fl)
 		return -ENOMEM;
-	locks_init_lock(fl);
+	locks_init_lease(fl);
 	fl->fl_lmops = &nfsd4_layouts_lm_ops;
-	fl->fl_flags = FL_LAYOUT;
-	fl->fl_type = F_RDLCK;
-	fl->fl_end = OFFSET_MAX;
-	fl->fl_owner = ls;
-	fl->fl_pid = current->tgid;
-	fl->fl_file = ls->ls_file->nf_file;
-
-	status = vfs_setlease(fl->fl_file, fl->fl_type, &fl, NULL);
+	fl->c.flc_flags = FL_LAYOUT;
+	fl->c.flc_type = F_RDLCK;
+	fl->c.flc_owner = ls;
+	fl->c.flc_pid = current->tgid;
+	fl->c.flc_file = ls->ls_file->nf_file;
+
+	status = kernel_setlease(fl->c.flc_file, fl->c.flc_type, &fl, NULL);
 	if (status) {
-		locks_free_lock(fl);
+		locks_free_lease(fl);
 		return status;
 	}
 	BUG_ON(fl != NULL);
@@ -723,7 +722,7 @@ static const struct nfsd4_callback_ops nfsd4_cb_layout_ops = {
 };
 
 static bool
-nfsd4_layout_lm_break(struct file_lock *fl)
+nfsd4_layout_lm_break(struct file_lease *fl)
 {
 	/*
 	 * We don't want the locks code to timeout the lease for us;
@@ -731,19 +730,19 @@ nfsd4_layout_lm_break(struct file_lock *fl)
 	 * in time:
 	 */
 	fl->fl_break_time = 0;
-	nfsd4_recall_file_layout(fl->fl_owner);
+	nfsd4_recall_file_layout(fl->c.flc_owner);
 	return false;
 }
 
 static int
-nfsd4_layout_lm_change(struct file_lock *onlist, int arg,
+nfsd4_layout_lm_change(struct file_lease *onlist, int arg,
 		struct list_head *dispose)
 {
 	BUG_ON(!(arg & F_UNLCK));
 	return lease_modify(onlist, arg, dispose);
 }
 
-static const struct lock_manager_operations nfsd4_layouts_lm_ops = {
+static const struct lease_manager_operations nfsd4_layouts_lm_ops = {
 	.lm_break	= nfsd4_layout_lm_break,
 	.lm_change	= nfsd4_layout_lm_change,
 };
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 2fa54cfd4882..9257425cbd1a 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1249,7 +1249,7 @@ static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp)
 
 	WARN_ON_ONCE(!fp->fi_delegees);
 
-	vfs_setlease(nf->nf_file, F_UNLCK, NULL, (void **)&dp);
+	kernel_setlease(nf->nf_file, F_UNLCK, NULL, (void **)&dp);
 	put_deleg_file(fp);
 }
 
@@ -4922,9 +4922,9 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
 
 /* Called from break_lease() with flc_lock held. */
 static bool
-nfsd_break_deleg_cb(struct file_lock *fl)
+nfsd_break_deleg_cb(struct file_lease *fl)
 {
-	struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner;
+	struct nfs4_delegation *dp = (struct nfs4_delegation *) fl->c.flc_owner;
 	struct nfs4_file *fp = dp->dl_stid.sc_file;
 	struct nfs4_client *clp = dp->dl_stid.sc_client;
 	struct nfsd_net *nn;
@@ -4945,10 +4945,8 @@ nfsd_break_deleg_cb(struct file_lock *fl)
 	 */
 	fl->fl_break_time = 0;
 
-	spin_lock(&fp->fi_lock);
 	fp->fi_had_conflict = true;
 	nfsd_break_one_deleg(dp);
-	spin_unlock(&fp->fi_lock);
 	return false;
 }
 
@@ -4960,9 +4958,9 @@ nfsd_break_deleg_cb(struct file_lock *fl)
  *   %true: Lease conflict was resolved
  *   %false: Lease conflict was not resolved.
  */
-static bool nfsd_breaker_owns_lease(struct file_lock *fl)
+static bool nfsd_breaker_owns_lease(struct file_lease *fl)
 {
-	struct nfs4_delegation *dl = fl->fl_owner;
+	struct nfs4_delegation *dl = fl->c.flc_owner;
 	struct svc_rqst *rqst;
 	struct nfs4_client *clp;
 
@@ -4977,10 +4975,10 @@ static bool nfsd_breaker_owns_lease(struct file_lock *fl)
 }
 
 static int
-nfsd_change_deleg_cb(struct file_lock *onlist, int arg,
+nfsd_change_deleg_cb(struct file_lease *onlist, int arg,
 		     struct list_head *dispose)
 {
-	struct nfs4_delegation *dp = (struct nfs4_delegation *)onlist->fl_owner;
+	struct nfs4_delegation *dp = (struct nfs4_delegation *) onlist->c.flc_owner;
 	struct nfs4_client *clp = dp->dl_stid.sc_client;
 
 	if (arg & F_UNLCK) {
@@ -4991,7 +4989,7 @@ nfsd_change_deleg_cb(struct file_lock *onlist, int arg,
 		return -EAGAIN;
 }
 
-static const struct lock_manager_operations nfsd_lease_mng_ops = {
+static const struct lease_manager_operations nfsd_lease_mng_ops = {
 	.lm_breaker_owns_lease = nfsd_breaker_owns_lease,
 	.lm_break = nfsd_break_deleg_cb,
 	.lm_change = nfsd_change_deleg_cb,
@@ -5331,21 +5329,20 @@ static bool nfsd4_cb_channel_good(struct nfs4_client *clp)
 	return clp->cl_minorversion && clp->cl_cb_state == NFSD4_CB_UNKNOWN;
 }
 
-static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp,
+static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp,
 						int flag)
 {
-	struct file_lock *fl;
+	struct file_lease *fl;
 
-	fl = locks_alloc_lock();
+	fl = locks_alloc_lease();
 	if (!fl)
 		return NULL;
 	fl->fl_lmops = &nfsd_lease_mng_ops;
-	fl->fl_flags = FL_DELEG;
-	fl->fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK;
-	fl->fl_end = OFFSET_MAX;
-	fl->fl_owner = (fl_owner_t)dp;
-	fl->fl_pid = current->tgid;
-	fl->fl_file = dp->dl_stid.sc_file->fi_deleg_file->nf_file;
+	fl->c.flc_flags = FL_DELEG;
+	fl->c.flc_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK;
+	fl->c.flc_owner = (fl_owner_t)dp;
+	fl->c.flc_pid = current->tgid;
+	fl->c.flc_file = dp->dl_stid.sc_file->fi_deleg_file->nf_file;
 	return fl;
 }
 
@@ -5463,7 +5460,7 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	struct nfs4_clnt_odstate *odstate = stp->st_clnt_odstate;
 	struct nfs4_delegation *dp;
 	struct nfsd_file *nf = NULL;
-	struct file_lock *fl;
+	struct file_lease *fl;
 	u32 dl_type;
 
 	/*
@@ -5533,9 +5530,10 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	if (!fl)
 		goto out_clnt_odstate;
 
-	status = vfs_setlease(fp->fi_deleg_file->nf_file, fl->fl_type, &fl, NULL);
+	status = kernel_setlease(fp->fi_deleg_file->nf_file,
+				      fl->c.flc_type, &fl, NULL);
 	if (fl)
-		locks_free_lock(fl);
+		locks_free_lease(fl);
 	if (status)
 		goto out_clnt_odstate;
 
@@ -5557,12 +5555,13 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	if (status)
 		goto out_unlock;
 
+	status = -EAGAIN;
+	if (fp->fi_had_conflict)
+		goto out_unlock;
+
 	spin_lock(&state_lock);
 	spin_lock(&fp->fi_lock);
-	if (fp->fi_had_conflict)
-		status = -EAGAIN;
-	else
-		status = hash_delegation_locked(dp, fp);
+	status = hash_delegation_locked(dp, fp);
 	spin_unlock(&fp->fi_lock);
 	spin_unlock(&state_lock);
 
@@ -5571,7 +5570,7 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 
 	return dp;
 out_unlock:
-	vfs_setlease(fp->fi_deleg_file->nf_file, F_UNLCK, NULL, (void **)&dp);
+	kernel_setlease(fp->fi_deleg_file->nf_file, F_UNLCK, NULL, (void **)&dp);
 out_clnt_odstate:
 	put_clnt_odstate(dp->dl_clnt_odstate);
 	nfs4_put_stid(&dp->dl_stid);
@@ -7149,7 +7148,7 @@ nfsd4_lm_put_owner(fl_owner_t owner)
 static bool
 nfsd4_lm_lock_expirable(struct file_lock *cfl)
 {
-	struct nfs4_lockowner *lo = (struct nfs4_lockowner *)cfl->fl_owner;
+	struct nfs4_lockowner *lo = (struct nfs4_lockowner *) cfl->c.flc_owner;
 	struct nfs4_client *clp = lo->lo_owner.so_client;
 	struct nfsd_net *nn;
 
@@ -7171,7 +7170,7 @@ nfsd4_lm_expire_lock(void)
 static void
 nfsd4_lm_notify(struct file_lock *fl)
 {
-	struct nfs4_lockowner		*lo = (struct nfs4_lockowner *)fl->fl_owner;
+	struct nfs4_lockowner		*lo = (struct nfs4_lockowner *) fl->c.flc_owner;
 	struct net			*net = lo->lo_owner.so_client->net;
 	struct nfsd_net			*nn = net_generic(net, nfsd_net_id);
 	struct nfsd4_blocked_lock	*nbl = container_of(fl,
@@ -7208,7 +7207,7 @@ nfs4_set_lock_denied(struct file_lock *fl, struct nfsd4_lock_denied *deny)
 	struct nfs4_lockowner *lo;
 
 	if (fl->fl_lmops == &nfsd_posix_mng_ops) {
-		lo = (struct nfs4_lockowner *) fl->fl_owner;
+		lo = (struct nfs4_lockowner *) fl->c.flc_owner;
 		xdr_netobj_dup(&deny->ld_owner, &lo->lo_owner.so_owner,
 						GFP_KERNEL);
 		if (!deny->ld_owner.data)
@@ -7227,7 +7226,7 @@ nevermind:
 	if (fl->fl_end != NFS4_MAX_UINT64)
 		deny->ld_length = fl->fl_end - fl->fl_start + 1;        
 	deny->ld_type = NFS4_READ_LT;
-	if (fl->fl_type != F_RDLCK)
+	if (fl->c.flc_type != F_RDLCK)
 		deny->ld_type = NFS4_WRITE_LT;
 }
 
@@ -7493,8 +7492,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	int lkflg;
 	int err;
 	bool new = false;
-	unsigned char fl_type;
-	unsigned int fl_flags = FL_POSIX;
+	unsigned char type;
+	unsigned int flags = FL_POSIX;
 	struct net *net = SVC_NET(rqstp);
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
@@ -7557,14 +7556,14 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		goto out;
 
 	if (lock->lk_reclaim)
-		fl_flags |= FL_RECLAIM;
+		flags |= FL_RECLAIM;
 
 	fp = lock_stp->st_stid.sc_file;
 	switch (lock->lk_type) {
 		case NFS4_READW_LT:
 			if (nfsd4_has_session(cstate) ||
 			    exportfs_lock_op_is_async(sb->s_export_op))
-				fl_flags |= FL_SLEEP;
+				flags |= FL_SLEEP;
 			fallthrough;
 		case NFS4_READ_LT:
 			spin_lock(&fp->fi_lock);
@@ -7572,12 +7571,12 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 			if (nf)
 				get_lock_access(lock_stp, NFS4_SHARE_ACCESS_READ);
 			spin_unlock(&fp->fi_lock);
-			fl_type = F_RDLCK;
+			type = F_RDLCK;
 			break;
 		case NFS4_WRITEW_LT:
 			if (nfsd4_has_session(cstate) ||
 			    exportfs_lock_op_is_async(sb->s_export_op))
-				fl_flags |= FL_SLEEP;
+				flags |= FL_SLEEP;
 			fallthrough;
 		case NFS4_WRITE_LT:
 			spin_lock(&fp->fi_lock);
@@ -7585,7 +7584,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 			if (nf)
 				get_lock_access(lock_stp, NFS4_SHARE_ACCESS_WRITE);
 			spin_unlock(&fp->fi_lock);
-			fl_type = F_WRLCK;
+			type = F_WRLCK;
 			break;
 		default:
 			status = nfserr_inval;
@@ -7605,7 +7604,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	 * on those filesystems:
 	 */
 	if (!exportfs_lock_op_is_async(sb->s_export_op))
-		fl_flags &= ~FL_SLEEP;
+		flags &= ~FL_SLEEP;
 
 	nbl = find_or_allocate_block(lock_sop, &fp->fi_fhandle, nn);
 	if (!nbl) {
@@ -7615,11 +7614,11 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	}
 
 	file_lock = &nbl->nbl_lock;
-	file_lock->fl_type = fl_type;
-	file_lock->fl_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(&lock_sop->lo_owner));
-	file_lock->fl_pid = current->tgid;
-	file_lock->fl_file = nf->nf_file;
-	file_lock->fl_flags = fl_flags;
+	file_lock->c.flc_type = type;
+	file_lock->c.flc_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(&lock_sop->lo_owner));
+	file_lock->c.flc_pid = current->tgid;
+	file_lock->c.flc_file = nf->nf_file;
+	file_lock->c.flc_flags = flags;
 	file_lock->fl_lmops = &nfsd_posix_mng_ops;
 	file_lock->fl_start = lock->lk_offset;
 	file_lock->fl_end = last_byte_offset(lock->lk_offset, lock->lk_length);
@@ -7632,7 +7631,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		goto out;
 	}
 
-	if (fl_flags & FL_SLEEP) {
+	if (flags & FL_SLEEP) {
 		nbl->nbl_time = ktime_get_boottime_seconds();
 		spin_lock(&nn->blocked_locks_lock);
 		list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked);
@@ -7669,7 +7668,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 out:
 	if (nbl) {
 		/* dequeue it if we queued it before */
-		if (fl_flags & FL_SLEEP) {
+		if (flags & FL_SLEEP) {
 			spin_lock(&nn->blocked_locks_lock);
 			if (!list_empty(&nbl->nbl_list) &&
 			    !list_empty(&nbl->nbl_lru)) {
@@ -7737,9 +7736,9 @@ static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct
 	err = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ));
 	if (err)
 		goto out;
-	lock->fl_file = nf->nf_file;
+	lock->c.flc_file = nf->nf_file;
 	err = nfserrno(vfs_test_lock(nf->nf_file, lock));
-	lock->fl_file = NULL;
+	lock->c.flc_file = NULL;
 out:
 	inode_unlock(inode);
 	nfsd_file_put(nf);
@@ -7784,11 +7783,11 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	switch (lockt->lt_type) {
 		case NFS4_READ_LT:
 		case NFS4_READW_LT:
-			file_lock->fl_type = F_RDLCK;
+			file_lock->c.flc_type = F_RDLCK;
 			break;
 		case NFS4_WRITE_LT:
 		case NFS4_WRITEW_LT:
-			file_lock->fl_type = F_WRLCK;
+			file_lock->c.flc_type = F_WRLCK;
 			break;
 		default:
 			dprintk("NFSD: nfs4_lockt: bad lock type!\n");
@@ -7798,9 +7797,9 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	lo = find_lockowner_str(cstate->clp, &lockt->lt_owner);
 	if (lo)
-		file_lock->fl_owner = (fl_owner_t)lo;
-	file_lock->fl_pid = current->tgid;
-	file_lock->fl_flags = FL_POSIX;
+		file_lock->c.flc_owner = (fl_owner_t)lo;
+	file_lock->c.flc_pid = current->tgid;
+	file_lock->c.flc_flags = FL_POSIX;
 
 	file_lock->fl_start = lockt->lt_offset;
 	file_lock->fl_end = last_byte_offset(lockt->lt_offset, lockt->lt_length);
@@ -7811,7 +7810,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (status)
 		goto out;
 
-	if (file_lock->fl_type != F_UNLCK) {
+	if (file_lock->c.flc_type != F_UNLCK) {
 		status = nfserr_denied;
 		nfs4_set_lock_denied(file_lock, &lockt->lt_denied);
 	}
@@ -7867,11 +7866,11 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		goto put_file;
 	}
 
-	file_lock->fl_type = F_UNLCK;
-	file_lock->fl_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(stp->st_stateowner));
-	file_lock->fl_pid = current->tgid;
-	file_lock->fl_file = nf->nf_file;
-	file_lock->fl_flags = FL_POSIX;
+	file_lock->c.flc_type = F_UNLCK;
+	file_lock->c.flc_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(stp->st_stateowner));
+	file_lock->c.flc_pid = current->tgid;
+	file_lock->c.flc_file = nf->nf_file;
+	file_lock->c.flc_flags = FL_POSIX;
 	file_lock->fl_lmops = &nfsd_posix_mng_ops;
 	file_lock->fl_start = locku->lu_offset;
 
@@ -7911,14 +7910,16 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
 {
 	struct file_lock *fl;
 	int status = false;
-	struct nfsd_file *nf = find_any_file(fp);
+	struct nfsd_file *nf;
 	struct inode *inode;
 	struct file_lock_context *flctx;
 
+	spin_lock(&fp->fi_lock);
+	nf = find_any_file_locked(fp);
 	if (!nf) {
 		/* Any valid lock stateid should have some sort of access */
 		WARN_ON_ONCE(1);
-		return status;
+		goto out;
 	}
 
 	inode = file_inode(nf->nf_file);
@@ -7926,15 +7927,16 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
 
 	if (flctx && !list_empty_careful(&flctx->flc_posix)) {
 		spin_lock(&flctx->flc_lock);
-		list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
-			if (fl->fl_owner == (fl_owner_t)lowner) {
+		for_each_file_lock(fl, &flctx->flc_posix) {
+			if (fl->c.flc_owner == (fl_owner_t)lowner) {
 				status = true;
 				break;
 			}
 		}
 		spin_unlock(&flctx->flc_lock);
 	}
-	nfsd_file_put(nf);
+out:
+	spin_unlock(&fp->fi_lock);
 	return status;
 }
 
@@ -7944,10 +7946,8 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
  * @cstate: NFSv4 COMPOUND state
  * @u: RELEASE_LOCKOWNER arguments
  *
- * The lockowner's so_count is bumped when a lock record is added
- * or when copying a conflicting lock. The latter case is brief,
- * but can lead to fleeting false positives when looking for
- * locks-in-use.
+ * Check if theree are any locks still held and if not - free the lockowner
+ * and any lock state that is owned.
  *
  * Return values:
  *   %nfs_ok: lockowner released or not found
@@ -7983,10 +7983,13 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
 		spin_unlock(&clp->cl_lock);
 		return nfs_ok;
 	}
-	if (atomic_read(&lo->lo_owner.so_count) != 2) {
-		spin_unlock(&clp->cl_lock);
-		nfs4_put_stateowner(&lo->lo_owner);
-		return nfserr_locks_held;
+
+	list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) {
+		if (check_for_locks(stp->st_stid.sc_file, lo)) {
+			spin_unlock(&clp->cl_lock);
+			nfs4_put_stateowner(&lo->lo_owner);
+			return nfserr_locks_held;
+		}
 	}
 	unhash_lockowner_locked(lo);
 	while (!list_empty(&lo->lo_owner.so_stateids)) {
@@ -8448,15 +8451,17 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode)
 {
 	__be32 status;
 	struct file_lock_context *ctx;
-	struct file_lock *fl;
+	struct file_lease *fl;
 	struct nfs4_delegation *dp;
 
 	ctx = locks_inode_context(inode);
 	if (!ctx)
 		return 0;
 	spin_lock(&ctx->flc_lock);
-	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
-		if (fl->fl_flags == FL_LAYOUT)
+	for_each_file_lock(fl, &ctx->flc_lease) {
+		unsigned char type = fl->c.flc_type;
+
+		if (fl->c.flc_flags == FL_LAYOUT)
 			continue;
 		if (fl->fl_lmops != &nfsd_lease_mng_ops) {
 			/*
@@ -8464,12 +8469,12 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode)
 			 * we are done; there isn't any write delegation
 			 * on this inode
 			 */
-			if (fl->fl_type == F_RDLCK)
+			if (type == F_RDLCK)
 				break;
 			goto break_lease;
 		}
-		if (fl->fl_type == F_WRLCK) {
-			dp = fl->fl_owner;
+		if (type == F_WRLCK) {
+			dp = fl->c.flc_owner;
 			if (dp->dl_recall.cb_clp == *(rqstp->rq_lease_breaker)) {
 				spin_unlock(&ctx->flc_lock);
 				return 0;
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index bec33b89a075..0e3fc5ba33c7 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -107,7 +107,13 @@ static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf)
 	nilfs_transaction_commit(inode->i_sb);
 
  mapped:
-	folio_wait_stable(folio);
+	/*
+	 * Since checksumming including data blocks is performed to determine
+	 * the validity of the log to be written and used for recovery, it is
+	 * necessary to wait for writeback to finish here, regardless of the
+	 * stable write requirement of the backing device.
+	 */
+	folio_wait_writeback(folio);
  out:
 	sb_end_pagefault(inode->i_sb);
 	return vmf_fs_error(ret);
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index 0955b657938f..a9b8d77c8c1d 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -472,9 +472,10 @@ static int nilfs_prepare_segment_for_recovery(struct the_nilfs *nilfs,
 
 static int nilfs_recovery_copy_block(struct the_nilfs *nilfs,
 				     struct nilfs_recovery_block *rb,
-				     struct page *page)
+				     loff_t pos, struct page *page)
 {
 	struct buffer_head *bh_org;
+	size_t from = pos & ~PAGE_MASK;
 	void *kaddr;
 
 	bh_org = __bread(nilfs->ns_bdev, rb->blocknr, nilfs->ns_blocksize);
@@ -482,7 +483,7 @@ static int nilfs_recovery_copy_block(struct the_nilfs *nilfs,
 		return -EIO;
 
 	kaddr = kmap_atomic(page);
-	memcpy(kaddr + bh_offset(bh_org), bh_org->b_data, bh_org->b_size);
+	memcpy(kaddr + from, bh_org->b_data, bh_org->b_size);
 	kunmap_atomic(kaddr);
 	brelse(bh_org);
 	return 0;
@@ -521,7 +522,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
 			goto failed_inode;
 		}
 
-		err = nilfs_recovery_copy_block(nilfs, rb, page);
+		err = nilfs_recovery_copy_block(nilfs, rb, pos, page);
 		if (unlikely(err))
 			goto failed_page;
 
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 2590a0860eab..2bfb08052d39 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -1703,7 +1703,6 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
 
 		list_for_each_entry(bh, &segbuf->sb_payload_buffers,
 				    b_assoc_buffers) {
-			set_buffer_async_write(bh);
 			if (bh == segbuf->sb_super_root) {
 				if (bh->b_folio != bd_folio) {
 					folio_lock(bd_folio);
@@ -1714,6 +1713,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
 				}
 				break;
 			}
+			set_buffer_async_write(bh);
 			if (bh->b_folio != fs_folio) {
 				nilfs_begin_folio_io(fs_folio);
 				fs_folio = bh->b_folio;
@@ -1800,7 +1800,6 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
 
 		list_for_each_entry(bh, &segbuf->sb_payload_buffers,
 				    b_assoc_buffers) {
-			clear_buffer_async_write(bh);
 			if (bh == segbuf->sb_super_root) {
 				clear_buffer_uptodate(bh);
 				if (bh->b_folio != bd_folio) {
@@ -1809,6 +1808,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
 				}
 				break;
 			}
+			clear_buffer_async_write(bh);
 			if (bh->b_folio != fs_folio) {
 				nilfs_end_folio_io(fs_folio, err);
 				fs_folio = bh->b_folio;
@@ -1896,8 +1896,9 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
 				 BIT(BH_Delay) | BIT(BH_NILFS_Volatile) |
 				 BIT(BH_NILFS_Redirected));
 
-			set_mask_bits(&bh->b_state, clear_bits, set_bits);
 			if (bh == segbuf->sb_super_root) {
+				set_buffer_uptodate(bh);
+				clear_buffer_dirty(bh);
 				if (bh->b_folio != bd_folio) {
 					folio_end_writeback(bd_folio);
 					bd_folio = bh->b_folio;
@@ -1905,6 +1906,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
 				update_sr = true;
 				break;
 			}
+			set_mask_bits(&bh->b_state, clear_bits, set_bits);
 			if (bh->b_folio != fs_folio) {
 				nilfs_end_folio_io(fs_folio, 0);
 				fs_folio = bh->b_folio;
diff --git a/fs/nsfs.c b/fs/nsfs.c
index 34e1e3e36733..7aaafb5cb9fc 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -27,26 +27,17 @@ static const struct file_operations ns_file_operations = {
 static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
 {
 	struct inode *inode = d_inode(dentry);
-	const struct proc_ns_operations *ns_ops = dentry->d_fsdata;
+	struct ns_common *ns = inode->i_private;
+	const struct proc_ns_operations *ns_ops = ns->ops;
 
 	return dynamic_dname(buffer, buflen, "%s:[%lu]",
 		ns_ops->name, inode->i_ino);
 }
 
-static void ns_prune_dentry(struct dentry *dentry)
-{
-	struct inode *inode = d_inode(dentry);
-	if (inode) {
-		struct ns_common *ns = inode->i_private;
-		atomic_long_set(&ns->stashed, 0);
-	}
-}
-
-const struct dentry_operations ns_dentry_operations =
-{
-	.d_prune	= ns_prune_dentry,
+const struct dentry_operations ns_dentry_operations = {
 	.d_delete	= always_delete_dentry,
 	.d_dname	= ns_dname,
+	.d_prune	= stashed_dentry_prune,
 };
 
 static void nsfs_evict(struct inode *inode)
@@ -56,67 +47,16 @@ static void nsfs_evict(struct inode *inode)
 	ns->ops->put(ns);
 }
 
-static int __ns_get_path(struct path *path, struct ns_common *ns)
-{
-	struct vfsmount *mnt = nsfs_mnt;
-	struct dentry *dentry;
-	struct inode *inode;
-	unsigned long d;
-
-	rcu_read_lock();
-	d = atomic_long_read(&ns->stashed);
-	if (!d)
-		goto slow;
-	dentry = (struct dentry *)d;
-	if (!lockref_get_not_dead(&dentry->d_lockref))
-		goto slow;
-	rcu_read_unlock();
-	ns->ops->put(ns);
-got_it:
-	path->mnt = mntget(mnt);
-	path->dentry = dentry;
-	return 0;
-slow:
-	rcu_read_unlock();
-	inode = new_inode_pseudo(mnt->mnt_sb);
-	if (!inode) {
-		ns->ops->put(ns);
-		return -ENOMEM;
-	}
-	inode->i_ino = ns->inum;
-	simple_inode_init_ts(inode);
-	inode->i_flags |= S_IMMUTABLE;
-	inode->i_mode = S_IFREG | S_IRUGO;
-	inode->i_fop = &ns_file_operations;
-	inode->i_private = ns;
-
-	dentry = d_make_root(inode);	/* not the normal use, but... */
-	if (!dentry)
-		return -ENOMEM;
-	dentry->d_fsdata = (void *)ns->ops;
-	d = atomic_long_cmpxchg(&ns->stashed, 0, (unsigned long)dentry);
-	if (d) {
-		d_delete(dentry);	/* make sure ->d_prune() does nothing */
-		dput(dentry);
-		cpu_relax();
-		return -EAGAIN;
-	}
-	goto got_it;
-}
-
 int ns_get_path_cb(struct path *path, ns_get_path_helper_t *ns_get_cb,
 		     void *private_data)
 {
-	int ret;
+	struct ns_common *ns;
 
-	do {
-		struct ns_common *ns = ns_get_cb(private_data);
-		if (!ns)
-			return -ENOENT;
-		ret = __ns_get_path(path, ns);
-	} while (ret == -EAGAIN);
+	ns = ns_get_cb(private_data);
+	if (!ns)
+		return -ENOENT;
 
-	return ret;
+	return path_from_stashed(&ns->stashed, ns->inum, nsfs_mnt, ns, path);
 }
 
 struct ns_get_path_task_args {
@@ -146,6 +86,7 @@ int open_related_ns(struct ns_common *ns,
 		   struct ns_common *(*get_ns)(struct ns_common *ns))
 {
 	struct path path = {};
+	struct ns_common *relative;
 	struct file *f;
 	int err;
 	int fd;
@@ -154,19 +95,15 @@ int open_related_ns(struct ns_common *ns,
 	if (fd < 0)
 		return fd;
 
-	do {
-		struct ns_common *relative;
-
-		relative = get_ns(ns);
-		if (IS_ERR(relative)) {
-			put_unused_fd(fd);
-			return PTR_ERR(relative);
-		}
-
-		err = __ns_get_path(&path, relative);
-	} while (err == -EAGAIN);
+	relative = get_ns(ns);
+	if (IS_ERR(relative)) {
+		put_unused_fd(fd);
+		return PTR_ERR(relative);
+	}
 
-	if (err) {
+	err = path_from_stashed(&relative->stashed, relative->inum, nsfs_mnt,
+				relative, &path);
+	if (err < 0) {
 		put_unused_fd(fd);
 		return err;
 	}
@@ -249,7 +186,8 @@ bool ns_match(const struct ns_common *ns, dev_t dev, ino_t ino)
 static int nsfs_show_path(struct seq_file *seq, struct dentry *dentry)
 {
 	struct inode *inode = d_inode(dentry);
-	const struct proc_ns_operations *ns_ops = dentry->d_fsdata;
+	const struct ns_common *ns = inode->i_private;
+	const struct proc_ns_operations *ns_ops = ns->ops;
 
 	seq_printf(seq, "%s:[%lu]", ns_ops->name, inode->i_ino);
 	return 0;
@@ -261,6 +199,24 @@ static const struct super_operations nsfs_ops = {
 	.show_path = nsfs_show_path,
 };
 
+static void nsfs_init_inode(struct inode *inode, void *data)
+{
+	inode->i_private = data;
+	inode->i_mode |= S_IRUGO;
+	inode->i_fop = &ns_file_operations;
+}
+
+static void nsfs_put_data(void *data)
+{
+	struct ns_common *ns = data;
+	ns->ops->put(ns);
+}
+
+static const struct stashed_operations nsfs_stashed_ops = {
+	.init_inode = nsfs_init_inode,
+	.put_data = nsfs_put_data,
+};
+
 static int nsfs_init_fs_context(struct fs_context *fc)
 {
 	struct pseudo_fs_context *ctx = init_pseudo(fc, NSFS_MAGIC);
@@ -268,6 +224,7 @@ static int nsfs_init_fs_context(struct fs_context *fc)
 		return -ENOMEM;
 	ctx->ops = &nsfs_ops;
 	ctx->dops = &ns_dentry_operations;
+	fc->s_fs_info = (void *)&nsfs_stashed_ops;
 	return 0;
 }
 
diff --git a/fs/ntfs/Kconfig b/fs/ntfs/Kconfig
deleted file mode 100644
index 7b2509741735..000000000000
--- a/fs/ntfs/Kconfig
+++ /dev/null
@@ -1,81 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-config NTFS_FS
-	tristate "NTFS file system support"
-	select BUFFER_HEAD
-	select NLS
-	help
-	  NTFS is the file system of Microsoft Windows NT, 2000, XP and 2003.
-
-	  Saying Y or M here enables read support.  There is partial, but
-	  safe, write support available.  For write support you must also
-	  say Y to "NTFS write support" below.
-
-	  There are also a number of user-space tools available, called
-	  ntfsprogs.  These include ntfsundelete and ntfsresize, that work
-	  without NTFS support enabled in the kernel.
-
-	  This is a rewrite from scratch of Linux NTFS support and replaced
-	  the old NTFS code starting with Linux 2.5.11.  A backport to
-	  the Linux 2.4 kernel series is separately available as a patch
-	  from the project web site.
-
-	  For more information see <file:Documentation/filesystems/ntfs.rst>
-	  and <http://www.linux-ntfs.org/>.
-
-	  To compile this file system support as a module, choose M here: the
-	  module will be called ntfs.
-
-	  If you are not using Windows NT, 2000, XP or 2003 in addition to
-	  Linux on your computer it is safe to say N.
-
-config NTFS_DEBUG
-	bool "NTFS debugging support"
-	depends on NTFS_FS
-	help
-	  If you are experiencing any problems with the NTFS file system, say
-	  Y here.  This will result in additional consistency checks to be
-	  performed by the driver as well as additional debugging messages to
-	  be written to the system log.  Note that debugging messages are
-	  disabled by default.  To enable them, supply the option debug_msgs=1
-	  at the kernel command line when booting the kernel or as an option
-	  to insmod when loading the ntfs module.  Once the driver is active,
-	  you can enable debugging messages by doing (as root):
-	  echo 1 > /proc/sys/fs/ntfs-debug
-	  Replacing the "1" with "0" would disable debug messages.
-
-	  If you leave debugging messages disabled, this results in little
-	  overhead, but enabling debug messages results in very significant
-	  slowdown of the system.
-
-	  When reporting bugs, please try to have available a full dump of
-	  debugging messages while the misbehaviour was occurring.
-
-config NTFS_RW
-	bool "NTFS write support"
-	depends on NTFS_FS
-	depends on PAGE_SIZE_LESS_THAN_64KB
-	help
-	  This enables the partial, but safe, write support in the NTFS driver.
-
-	  The only supported operation is overwriting existing files, without
-	  changing the file length.  No file or directory creation, deletion or
-	  renaming is possible.  Note only non-resident files can be written to
-	  so you may find that some very small files (<500 bytes or so) cannot
-	  be written to.
-
-	  While we cannot guarantee that it will not damage any data, we have
-	  so far not received a single report where the driver would have
-	  damaged someones data so we assume it is perfectly safe to use.
-
-	  Note:  While write support is safe in this version (a rewrite from
-	  scratch of the NTFS support), it should be noted that the old NTFS
-	  write support, included in Linux 2.5.10 and before (since 1997),
-	  is not safe.
-
-	  This is currently useful with TopologiLinux.  TopologiLinux is run
-	  on top of any DOS/Microsoft Windows system without partitioning your
-	  hard disk.  Unlike other Linux distributions TopologiLinux does not
-	  need its own partition.  For more information see
-	  <http://topologi-linux.sourceforge.net/>
-
-	  It is perfectly safe to say N here.
diff --git a/fs/ntfs/Makefile b/fs/ntfs/Makefile
deleted file mode 100644
index 3e736572ed00..000000000000
--- a/fs/ntfs/Makefile
+++ /dev/null
@@ -1,15 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-# Rules for making the NTFS driver.
-
-obj-$(CONFIG_NTFS_FS) += ntfs.o
-
-ntfs-y := aops.o attrib.o collate.o compress.o debug.o dir.o file.o \
-	  index.o inode.o mft.o mst.o namei.o runlist.o super.o sysctl.o \
-	  unistr.o upcase.o
-
-ntfs-$(CONFIG_NTFS_RW) += bitmap.o lcnalloc.o logfile.o quota.o usnjrnl.o
-
-ccflags-y := -DNTFS_VERSION=\"2.1.32\"
-ccflags-$(CONFIG_NTFS_DEBUG)	+= -DDEBUG
-ccflags-$(CONFIG_NTFS_RW)	+= -DNTFS_RW
-
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
deleted file mode 100644
index 2d01517a2d59..000000000000
--- a/fs/ntfs/aops.c
+++ /dev/null
@@ -1,1744 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * aops.c - NTFS kernel address space operations and page cache handling.
- *
- * Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc.
- * Copyright (c) 2002 Richard Russon
- */
-
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/gfp.h>
-#include <linux/mm.h>
-#include <linux/pagemap.h>
-#include <linux/swap.h>
-#include <linux/buffer_head.h>
-#include <linux/writeback.h>
-#include <linux/bit_spinlock.h>
-#include <linux/bio.h>
-
-#include "aops.h"
-#include "attrib.h"
-#include "debug.h"
-#include "inode.h"
-#include "mft.h"
-#include "runlist.h"
-#include "types.h"
-#include "ntfs.h"
-
-/**
- * ntfs_end_buffer_async_read - async io completion for reading attributes
- * @bh:		buffer head on which io is completed
- * @uptodate:	whether @bh is now uptodate or not
- *
- * Asynchronous I/O completion handler for reading pages belonging to the
- * attribute address space of an inode.  The inodes can either be files or
- * directories or they can be fake inodes describing some attribute.
- *
- * If NInoMstProtected(), perform the post read mst fixups when all IO on the
- * page has been completed and mark the page uptodate or set the error bit on
- * the page.  To determine the size of the records that need fixing up, we
- * cheat a little bit by setting the index_block_size in ntfs_inode to the ntfs
- * record size, and index_block_size_bits, to the log(base 2) of the ntfs
- * record size.
- */
-static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
-{
-	unsigned long flags;
-	struct buffer_head *first, *tmp;
-	struct page *page;
-	struct inode *vi;
-	ntfs_inode *ni;
-	int page_uptodate = 1;
-
-	page = bh->b_page;
-	vi = page->mapping->host;
-	ni = NTFS_I(vi);
-
-	if (likely(uptodate)) {
-		loff_t i_size;
-		s64 file_ofs, init_size;
-
-		set_buffer_uptodate(bh);
-
-		file_ofs = ((s64)page->index << PAGE_SHIFT) +
-				bh_offset(bh);
-		read_lock_irqsave(&ni->size_lock, flags);
-		init_size = ni->initialized_size;
-		i_size = i_size_read(vi);
-		read_unlock_irqrestore(&ni->size_lock, flags);
-		if (unlikely(init_size > i_size)) {
-			/* Race with shrinking truncate. */
-			init_size = i_size;
-		}
-		/* Check for the current buffer head overflowing. */
-		if (unlikely(file_ofs + bh->b_size > init_size)) {
-			int ofs;
-			void *kaddr;
-
-			ofs = 0;
-			if (file_ofs < init_size)
-				ofs = init_size - file_ofs;
-			kaddr = kmap_atomic(page);
-			memset(kaddr + bh_offset(bh) + ofs, 0,
-					bh->b_size - ofs);
-			flush_dcache_page(page);
-			kunmap_atomic(kaddr);
-		}
-	} else {
-		clear_buffer_uptodate(bh);
-		SetPageError(page);
-		ntfs_error(ni->vol->sb, "Buffer I/O error, logical block "
-				"0x%llx.", (unsigned long long)bh->b_blocknr);
-	}
-	first = page_buffers(page);
-	spin_lock_irqsave(&first->b_uptodate_lock, flags);
-	clear_buffer_async_read(bh);
-	unlock_buffer(bh);
-	tmp = bh;
-	do {
-		if (!buffer_uptodate(tmp))
-			page_uptodate = 0;
-		if (buffer_async_read(tmp)) {
-			if (likely(buffer_locked(tmp)))
-				goto still_busy;
-			/* Async buffers must be locked. */
-			BUG();
-		}
-		tmp = tmp->b_this_page;
-	} while (tmp != bh);
-	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
-	/*
-	 * If none of the buffers had errors then we can set the page uptodate,
-	 * but we first have to perform the post read mst fixups, if the
-	 * attribute is mst protected, i.e. if NInoMstProteced(ni) is true.
-	 * Note we ignore fixup errors as those are detected when
-	 * map_mft_record() is called which gives us per record granularity
-	 * rather than per page granularity.
-	 */
-	if (!NInoMstProtected(ni)) {
-		if (likely(page_uptodate && !PageError(page)))
-			SetPageUptodate(page);
-	} else {
-		u8 *kaddr;
-		unsigned int i, recs;
-		u32 rec_size;
-
-		rec_size = ni->itype.index.block_size;
-		recs = PAGE_SIZE / rec_size;
-		/* Should have been verified before we got here... */
-		BUG_ON(!recs);
-		kaddr = kmap_atomic(page);
-		for (i = 0; i < recs; i++)
-			post_read_mst_fixup((NTFS_RECORD*)(kaddr +
-					i * rec_size), rec_size);
-		kunmap_atomic(kaddr);
-		flush_dcache_page(page);
-		if (likely(page_uptodate && !PageError(page)))
-			SetPageUptodate(page);
-	}
-	unlock_page(page);
-	return;
-still_busy:
-	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
-	return;
-}
-
-/**
- * ntfs_read_block - fill a @folio of an address space with data
- * @folio:	page cache folio to fill with data
- *
- * We read each buffer asynchronously and when all buffers are read in, our io
- * completion handler ntfs_end_buffer_read_async(), if required, automatically
- * applies the mst fixups to the folio before finally marking it uptodate and
- * unlocking it.
- *
- * We only enforce allocated_size limit because i_size is checked for in
- * generic_file_read().
- *
- * Return 0 on success and -errno on error.
- *
- * Contains an adapted version of fs/buffer.c::block_read_full_folio().
- */
-static int ntfs_read_block(struct folio *folio)
-{
-	loff_t i_size;
-	VCN vcn;
-	LCN lcn;
-	s64 init_size;
-	struct inode *vi;
-	ntfs_inode *ni;
-	ntfs_volume *vol;
-	runlist_element *rl;
-	struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE];
-	sector_t iblock, lblock, zblock;
-	unsigned long flags;
-	unsigned int blocksize, vcn_ofs;
-	int i, nr;
-	unsigned char blocksize_bits;
-
-	vi = folio->mapping->host;
-	ni = NTFS_I(vi);
-	vol = ni->vol;
-
-	/* $MFT/$DATA must have its complete runlist in memory at all times. */
-	BUG_ON(!ni->runlist.rl && !ni->mft_no && !NInoAttr(ni));
-
-	blocksize = vol->sb->s_blocksize;
-	blocksize_bits = vol->sb->s_blocksize_bits;
-
-	head = folio_buffers(folio);
-	if (!head)
-		head = create_empty_buffers(folio, blocksize, 0);
-	bh = head;
-
-	/*
-	 * We may be racing with truncate.  To avoid some of the problems we
-	 * now take a snapshot of the various sizes and use those for the whole
-	 * of the function.  In case of an extending truncate it just means we
-	 * may leave some buffers unmapped which are now allocated.  This is
-	 * not a problem since these buffers will just get mapped when a write
-	 * occurs.  In case of a shrinking truncate, we will detect this later
-	 * on due to the runlist being incomplete and if the folio is being
-	 * fully truncated, truncate will throw it away as soon as we unlock
-	 * it so no need to worry what we do with it.
-	 */
-	iblock = (s64)folio->index << (PAGE_SHIFT - blocksize_bits);
-	read_lock_irqsave(&ni->size_lock, flags);
-	lblock = (ni->allocated_size + blocksize - 1) >> blocksize_bits;
-	init_size = ni->initialized_size;
-	i_size = i_size_read(vi);
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	if (unlikely(init_size > i_size)) {
-		/* Race with shrinking truncate. */
-		init_size = i_size;
-	}
-	zblock = (init_size + blocksize - 1) >> blocksize_bits;
-
-	/* Loop through all the buffers in the folio. */
-	rl = NULL;
-	nr = i = 0;
-	do {
-		int err = 0;
-
-		if (unlikely(buffer_uptodate(bh)))
-			continue;
-		if (unlikely(buffer_mapped(bh))) {
-			arr[nr++] = bh;
-			continue;
-		}
-		bh->b_bdev = vol->sb->s_bdev;
-		/* Is the block within the allowed limits? */
-		if (iblock < lblock) {
-			bool is_retry = false;
-
-			/* Convert iblock into corresponding vcn and offset. */
-			vcn = (VCN)iblock << blocksize_bits >>
-					vol->cluster_size_bits;
-			vcn_ofs = ((VCN)iblock << blocksize_bits) &
-					vol->cluster_size_mask;
-			if (!rl) {
-lock_retry_remap:
-				down_read(&ni->runlist.lock);
-				rl = ni->runlist.rl;
-			}
-			if (likely(rl != NULL)) {
-				/* Seek to element containing target vcn. */
-				while (rl->length && rl[1].vcn <= vcn)
-					rl++;
-				lcn = ntfs_rl_vcn_to_lcn(rl, vcn);
-			} else
-				lcn = LCN_RL_NOT_MAPPED;
-			/* Successful remap. */
-			if (lcn >= 0) {
-				/* Setup buffer head to correct block. */
-				bh->b_blocknr = ((lcn << vol->cluster_size_bits)
-						+ vcn_ofs) >> blocksize_bits;
-				set_buffer_mapped(bh);
-				/* Only read initialized data blocks. */
-				if (iblock < zblock) {
-					arr[nr++] = bh;
-					continue;
-				}
-				/* Fully non-initialized data block, zero it. */
-				goto handle_zblock;
-			}
-			/* It is a hole, need to zero it. */
-			if (lcn == LCN_HOLE)
-				goto handle_hole;
-			/* If first try and runlist unmapped, map and retry. */
-			if (!is_retry && lcn == LCN_RL_NOT_MAPPED) {
-				is_retry = true;
-				/*
-				 * Attempt to map runlist, dropping lock for
-				 * the duration.
-				 */
-				up_read(&ni->runlist.lock);
-				err = ntfs_map_runlist(ni, vcn);
-				if (likely(!err))
-					goto lock_retry_remap;
-				rl = NULL;
-			} else if (!rl)
-				up_read(&ni->runlist.lock);
-			/*
-			 * If buffer is outside the runlist, treat it as a
-			 * hole.  This can happen due to concurrent truncate
-			 * for example.
-			 */
-			if (err == -ENOENT || lcn == LCN_ENOENT) {
-				err = 0;
-				goto handle_hole;
-			}
-			/* Hard error, zero out region. */
-			if (!err)
-				err = -EIO;
-			bh->b_blocknr = -1;
-			folio_set_error(folio);
-			ntfs_error(vol->sb, "Failed to read from inode 0x%lx, "
-					"attribute type 0x%x, vcn 0x%llx, "
-					"offset 0x%x because its location on "
-					"disk could not be determined%s "
-					"(error code %i).", ni->mft_no,
-					ni->type, (unsigned long long)vcn,
-					vcn_ofs, is_retry ? " even after "
-					"retrying" : "", err);
-		}
-		/*
-		 * Either iblock was outside lblock limits or
-		 * ntfs_rl_vcn_to_lcn() returned error.  Just zero that portion
-		 * of the folio and set the buffer uptodate.
-		 */
-handle_hole:
-		bh->b_blocknr = -1UL;
-		clear_buffer_mapped(bh);
-handle_zblock:
-		folio_zero_range(folio, i * blocksize, blocksize);
-		if (likely(!err))
-			set_buffer_uptodate(bh);
-	} while (i++, iblock++, (bh = bh->b_this_page) != head);
-
-	/* Release the lock if we took it. */
-	if (rl)
-		up_read(&ni->runlist.lock);
-
-	/* Check we have at least one buffer ready for i/o. */
-	if (nr) {
-		struct buffer_head *tbh;
-
-		/* Lock the buffers. */
-		for (i = 0; i < nr; i++) {
-			tbh = arr[i];
-			lock_buffer(tbh);
-			tbh->b_end_io = ntfs_end_buffer_async_read;
-			set_buffer_async_read(tbh);
-		}
-		/* Finally, start i/o on the buffers. */
-		for (i = 0; i < nr; i++) {
-			tbh = arr[i];
-			if (likely(!buffer_uptodate(tbh)))
-				submit_bh(REQ_OP_READ, tbh);
-			else
-				ntfs_end_buffer_async_read(tbh, 1);
-		}
-		return 0;
-	}
-	/* No i/o was scheduled on any of the buffers. */
-	if (likely(!folio_test_error(folio)))
-		folio_mark_uptodate(folio);
-	else /* Signal synchronous i/o error. */
-		nr = -EIO;
-	folio_unlock(folio);
-	return nr;
-}
-
-/**
- * ntfs_read_folio - fill a @folio of a @file with data from the device
- * @file:	open file to which the folio @folio belongs or NULL
- * @folio:	page cache folio to fill with data
- *
- * For non-resident attributes, ntfs_read_folio() fills the @folio of the open
- * file @file by calling the ntfs version of the generic block_read_full_folio()
- * function, ntfs_read_block(), which in turn creates and reads in the buffers
- * associated with the folio asynchronously.
- *
- * For resident attributes, OTOH, ntfs_read_folio() fills @folio by copying the
- * data from the mft record (which at this stage is most likely in memory) and
- * fills the remainder with zeroes. Thus, in this case, I/O is synchronous, as
- * even if the mft record is not cached at this point in time, we need to wait
- * for it to be read in before we can do the copy.
- *
- * Return 0 on success and -errno on error.
- */
-static int ntfs_read_folio(struct file *file, struct folio *folio)
-{
-	struct page *page = &folio->page;
-	loff_t i_size;
-	struct inode *vi;
-	ntfs_inode *ni, *base_ni;
-	u8 *addr;
-	ntfs_attr_search_ctx *ctx;
-	MFT_RECORD *mrec;
-	unsigned long flags;
-	u32 attr_len;
-	int err = 0;
-
-retry_readpage:
-	BUG_ON(!PageLocked(page));
-	vi = page->mapping->host;
-	i_size = i_size_read(vi);
-	/* Is the page fully outside i_size? (truncate in progress) */
-	if (unlikely(page->index >= (i_size + PAGE_SIZE - 1) >>
-			PAGE_SHIFT)) {
-		zero_user(page, 0, PAGE_SIZE);
-		ntfs_debug("Read outside i_size - truncated?");
-		goto done;
-	}
-	/*
-	 * This can potentially happen because we clear PageUptodate() during
-	 * ntfs_writepage() of MstProtected() attributes.
-	 */
-	if (PageUptodate(page)) {
-		unlock_page(page);
-		return 0;
-	}
-	ni = NTFS_I(vi);
-	/*
-	 * Only $DATA attributes can be encrypted and only unnamed $DATA
-	 * attributes can be compressed.  Index root can have the flags set but
-	 * this means to create compressed/encrypted files, not that the
-	 * attribute is compressed/encrypted.  Note we need to check for
-	 * AT_INDEX_ALLOCATION since this is the type of both directory and
-	 * index inodes.
-	 */
-	if (ni->type != AT_INDEX_ALLOCATION) {
-		/* If attribute is encrypted, deny access, just like NT4. */
-		if (NInoEncrypted(ni)) {
-			BUG_ON(ni->type != AT_DATA);
-			err = -EACCES;
-			goto err_out;
-		}
-		/* Compressed data streams are handled in compress.c. */
-		if (NInoNonResident(ni) && NInoCompressed(ni)) {
-			BUG_ON(ni->type != AT_DATA);
-			BUG_ON(ni->name_len);
-			return ntfs_read_compressed_block(page);
-		}
-	}
-	/* NInoNonResident() == NInoIndexAllocPresent() */
-	if (NInoNonResident(ni)) {
-		/* Normal, non-resident data stream. */
-		return ntfs_read_block(folio);
-	}
-	/*
-	 * Attribute is resident, implying it is not compressed or encrypted.
-	 * This also means the attribute is smaller than an mft record and
-	 * hence smaller than a page, so can simply zero out any pages with
-	 * index above 0.  Note the attribute can actually be marked compressed
-	 * but if it is resident the actual data is not compressed so we are
-	 * ok to ignore the compressed flag here.
-	 */
-	if (unlikely(page->index > 0)) {
-		zero_user(page, 0, PAGE_SIZE);
-		goto done;
-	}
-	if (!NInoAttr(ni))
-		base_ni = ni;
-	else
-		base_ni = ni->ext.base_ntfs_ino;
-	/* Map, pin, and lock the mft record. */
-	mrec = map_mft_record(base_ni);
-	if (IS_ERR(mrec)) {
-		err = PTR_ERR(mrec);
-		goto err_out;
-	}
-	/*
-	 * If a parallel write made the attribute non-resident, drop the mft
-	 * record and retry the read_folio.
-	 */
-	if (unlikely(NInoNonResident(ni))) {
-		unmap_mft_record(base_ni);
-		goto retry_readpage;
-	}
-	ctx = ntfs_attr_get_search_ctx(base_ni, mrec);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto unm_err_out;
-	}
-	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err))
-		goto put_unm_err_out;
-	attr_len = le32_to_cpu(ctx->attr->data.resident.value_length);
-	read_lock_irqsave(&ni->size_lock, flags);
-	if (unlikely(attr_len > ni->initialized_size))
-		attr_len = ni->initialized_size;
-	i_size = i_size_read(vi);
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	if (unlikely(attr_len > i_size)) {
-		/* Race with shrinking truncate. */
-		attr_len = i_size;
-	}
-	addr = kmap_atomic(page);
-	/* Copy the data to the page. */
-	memcpy(addr, (u8*)ctx->attr +
-			le16_to_cpu(ctx->attr->data.resident.value_offset),
-			attr_len);
-	/* Zero the remainder of the page. */
-	memset(addr + attr_len, 0, PAGE_SIZE - attr_len);
-	flush_dcache_page(page);
-	kunmap_atomic(addr);
-put_unm_err_out:
-	ntfs_attr_put_search_ctx(ctx);
-unm_err_out:
-	unmap_mft_record(base_ni);
-done:
-	SetPageUptodate(page);
-err_out:
-	unlock_page(page);
-	return err;
-}
-
-#ifdef NTFS_RW
-
-/**
- * ntfs_write_block - write a @folio to the backing store
- * @folio:	page cache folio to write out
- * @wbc:	writeback control structure
- *
- * This function is for writing folios belonging to non-resident, non-mst
- * protected attributes to their backing store.
- *
- * For a folio with buffers, map and write the dirty buffers asynchronously
- * under folio writeback. For a folio without buffers, create buffers for the
- * folio, then proceed as above.
- *
- * If a folio doesn't have buffers the folio dirty state is definitive. If
- * a folio does have buffers, the folio dirty state is just a hint,
- * and the buffer dirty state is definitive. (A hint which has rules:
- * dirty buffers against a clean folio is illegal. Other combinations are
- * legal and need to be handled. In particular a dirty folio containing
- * clean buffers for example.)
- *
- * Return 0 on success and -errno on error.
- *
- * Based on ntfs_read_block() and __block_write_full_folio().
- */
-static int ntfs_write_block(struct folio *folio, struct writeback_control *wbc)
-{
-	VCN vcn;
-	LCN lcn;
-	s64 initialized_size;
-	loff_t i_size;
-	sector_t block, dblock, iblock;
-	struct inode *vi;
-	ntfs_inode *ni;
-	ntfs_volume *vol;
-	runlist_element *rl;
-	struct buffer_head *bh, *head;
-	unsigned long flags;
-	unsigned int blocksize, vcn_ofs;
-	int err;
-	bool need_end_writeback;
-	unsigned char blocksize_bits;
-
-	vi = folio->mapping->host;
-	ni = NTFS_I(vi);
-	vol = ni->vol;
-
-	ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, page index "
-			"0x%lx.", ni->mft_no, ni->type, folio->index);
-
-	BUG_ON(!NInoNonResident(ni));
-	BUG_ON(NInoMstProtected(ni));
-	blocksize = vol->sb->s_blocksize;
-	blocksize_bits = vol->sb->s_blocksize_bits;
-	head = folio_buffers(folio);
-	if (!head) {
-		BUG_ON(!folio_test_uptodate(folio));
-		head = create_empty_buffers(folio, blocksize,
-				(1 << BH_Uptodate) | (1 << BH_Dirty));
-	}
-	bh = head;
-
-	/* NOTE: Different naming scheme to ntfs_read_block()! */
-
-	/* The first block in the folio. */
-	block = (s64)folio->index << (PAGE_SHIFT - blocksize_bits);
-
-	read_lock_irqsave(&ni->size_lock, flags);
-	i_size = i_size_read(vi);
-	initialized_size = ni->initialized_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-
-	/* The first out of bounds block for the data size. */
-	dblock = (i_size + blocksize - 1) >> blocksize_bits;
-
-	/* The last (fully or partially) initialized block. */
-	iblock = initialized_size >> blocksize_bits;
-
-	/*
-	 * Be very careful.  We have no exclusion from block_dirty_folio
-	 * here, and the (potentially unmapped) buffers may become dirty at
-	 * any time.  If a buffer becomes dirty here after we've inspected it
-	 * then we just miss that fact, and the folio stays dirty.
-	 *
-	 * Buffers outside i_size may be dirtied by block_dirty_folio;
-	 * handle that here by just cleaning them.
-	 */
-
-	/*
-	 * Loop through all the buffers in the folio, mapping all the dirty
-	 * buffers to disk addresses and handling any aliases from the
-	 * underlying block device's mapping.
-	 */
-	rl = NULL;
-	err = 0;
-	do {
-		bool is_retry = false;
-
-		if (unlikely(block >= dblock)) {
-			/*
-			 * Mapped buffers outside i_size will occur, because
-			 * this folio can be outside i_size when there is a
-			 * truncate in progress. The contents of such buffers
-			 * were zeroed by ntfs_writepage().
-			 *
-			 * FIXME: What about the small race window where
-			 * ntfs_writepage() has not done any clearing because
-			 * the folio was within i_size but before we get here,
-			 * vmtruncate() modifies i_size?
-			 */
-			clear_buffer_dirty(bh);
-			set_buffer_uptodate(bh);
-			continue;
-		}
-
-		/* Clean buffers are not written out, so no need to map them. */
-		if (!buffer_dirty(bh))
-			continue;
-
-		/* Make sure we have enough initialized size. */
-		if (unlikely((block >= iblock) &&
-				(initialized_size < i_size))) {
-			/*
-			 * If this folio is fully outside initialized
-			 * size, zero out all folios between the current
-			 * initialized size and the current folio. Just
-			 * use ntfs_read_folio() to do the zeroing
-			 * transparently.
-			 */
-			if (block > iblock) {
-				// TODO:
-				// For each folio do:
-				// - read_cache_folio()
-				// Again for each folio do:
-				// - wait_on_folio_locked()
-				// - Check (folio_test_uptodate(folio) &&
-				//		!folio_test_error(folio))
-				// Update initialized size in the attribute and
-				// in the inode.
-				// Again, for each folio do:
-				//	block_dirty_folio();
-				// folio_put()
-				// We don't need to wait on the writes.
-				// Update iblock.
-			}
-			/*
-			 * The current folio straddles initialized size. Zero
-			 * all non-uptodate buffers and set them uptodate (and
-			 * dirty?). Note, there aren't any non-uptodate buffers
-			 * if the folio is uptodate.
-			 * FIXME: For an uptodate folio, the buffers may need to
-			 * be written out because they were not initialized on
-			 * disk before.
-			 */
-			if (!folio_test_uptodate(folio)) {
-				// TODO:
-				// Zero any non-uptodate buffers up to i_size.
-				// Set them uptodate and dirty.
-			}
-			// TODO:
-			// Update initialized size in the attribute and in the
-			// inode (up to i_size).
-			// Update iblock.
-			// FIXME: This is inefficient. Try to batch the two
-			// size changes to happen in one go.
-			ntfs_error(vol->sb, "Writing beyond initialized size "
-					"is not supported yet. Sorry.");
-			err = -EOPNOTSUPP;
-			break;
-			// Do NOT set_buffer_new() BUT DO clear buffer range
-			// outside write request range.
-			// set_buffer_uptodate() on complete buffers as well as
-			// set_buffer_dirty().
-		}
-
-		/* No need to map buffers that are already mapped. */
-		if (buffer_mapped(bh))
-			continue;
-
-		/* Unmapped, dirty buffer. Need to map it. */
-		bh->b_bdev = vol->sb->s_bdev;
-
-		/* Convert block into corresponding vcn and offset. */
-		vcn = (VCN)block << blocksize_bits;
-		vcn_ofs = vcn & vol->cluster_size_mask;
-		vcn >>= vol->cluster_size_bits;
-		if (!rl) {
-lock_retry_remap:
-			down_read(&ni->runlist.lock);
-			rl = ni->runlist.rl;
-		}
-		if (likely(rl != NULL)) {
-			/* Seek to element containing target vcn. */
-			while (rl->length && rl[1].vcn <= vcn)
-				rl++;
-			lcn = ntfs_rl_vcn_to_lcn(rl, vcn);
-		} else
-			lcn = LCN_RL_NOT_MAPPED;
-		/* Successful remap. */
-		if (lcn >= 0) {
-			/* Setup buffer head to point to correct block. */
-			bh->b_blocknr = ((lcn << vol->cluster_size_bits) +
-					vcn_ofs) >> blocksize_bits;
-			set_buffer_mapped(bh);
-			continue;
-		}
-		/* It is a hole, need to instantiate it. */
-		if (lcn == LCN_HOLE) {
-			u8 *kaddr;
-			unsigned long *bpos, *bend;
-
-			/* Check if the buffer is zero. */
-			kaddr = kmap_local_folio(folio, bh_offset(bh));
-			bpos = (unsigned long *)kaddr;
-			bend = (unsigned long *)(kaddr + blocksize);
-			do {
-				if (unlikely(*bpos))
-					break;
-			} while (likely(++bpos < bend));
-			kunmap_local(kaddr);
-			if (bpos == bend) {
-				/*
-				 * Buffer is zero and sparse, no need to write
-				 * it.
-				 */
-				bh->b_blocknr = -1;
-				clear_buffer_dirty(bh);
-				continue;
-			}
-			// TODO: Instantiate the hole.
-			// clear_buffer_new(bh);
-			// clean_bdev_bh_alias(bh);
-			ntfs_error(vol->sb, "Writing into sparse regions is "
-					"not supported yet. Sorry.");
-			err = -EOPNOTSUPP;
-			break;
-		}
-		/* If first try and runlist unmapped, map and retry. */
-		if (!is_retry && lcn == LCN_RL_NOT_MAPPED) {
-			is_retry = true;
-			/*
-			 * Attempt to map runlist, dropping lock for
-			 * the duration.
-			 */
-			up_read(&ni->runlist.lock);
-			err = ntfs_map_runlist(ni, vcn);
-			if (likely(!err))
-				goto lock_retry_remap;
-			rl = NULL;
-		} else if (!rl)
-			up_read(&ni->runlist.lock);
-		/*
-		 * If buffer is outside the runlist, truncate has cut it out
-		 * of the runlist.  Just clean and clear the buffer and set it
-		 * uptodate so it can get discarded by the VM.
-		 */
-		if (err == -ENOENT || lcn == LCN_ENOENT) {
-			bh->b_blocknr = -1;
-			clear_buffer_dirty(bh);
-			folio_zero_range(folio, bh_offset(bh), blocksize);
-			set_buffer_uptodate(bh);
-			err = 0;
-			continue;
-		}
-		/* Failed to map the buffer, even after retrying. */
-		if (!err)
-			err = -EIO;
-		bh->b_blocknr = -1;
-		ntfs_error(vol->sb, "Failed to write to inode 0x%lx, "
-				"attribute type 0x%x, vcn 0x%llx, offset 0x%x "
-				"because its location on disk could not be "
-				"determined%s (error code %i).", ni->mft_no,
-				ni->type, (unsigned long long)vcn,
-				vcn_ofs, is_retry ? " even after "
-				"retrying" : "", err);
-		break;
-	} while (block++, (bh = bh->b_this_page) != head);
-
-	/* Release the lock if we took it. */
-	if (rl)
-		up_read(&ni->runlist.lock);
-
-	/* For the error case, need to reset bh to the beginning. */
-	bh = head;
-
-	/* Just an optimization, so ->read_folio() is not called later. */
-	if (unlikely(!folio_test_uptodate(folio))) {
-		int uptodate = 1;
-		do {
-			if (!buffer_uptodate(bh)) {
-				uptodate = 0;
-				bh = head;
-				break;
-			}
-		} while ((bh = bh->b_this_page) != head);
-		if (uptodate)
-			folio_mark_uptodate(folio);
-	}
-
-	/* Setup all mapped, dirty buffers for async write i/o. */
-	do {
-		if (buffer_mapped(bh) && buffer_dirty(bh)) {
-			lock_buffer(bh);
-			if (test_clear_buffer_dirty(bh)) {
-				BUG_ON(!buffer_uptodate(bh));
-				mark_buffer_async_write(bh);
-			} else
-				unlock_buffer(bh);
-		} else if (unlikely(err)) {
-			/*
-			 * For the error case. The buffer may have been set
-			 * dirty during attachment to a dirty folio.
-			 */
-			if (err != -ENOMEM)
-				clear_buffer_dirty(bh);
-		}
-	} while ((bh = bh->b_this_page) != head);
-
-	if (unlikely(err)) {
-		// TODO: Remove the -EOPNOTSUPP check later on...
-		if (unlikely(err == -EOPNOTSUPP))
-			err = 0;
-		else if (err == -ENOMEM) {
-			ntfs_warning(vol->sb, "Error allocating memory. "
-					"Redirtying folio so we try again "
-					"later.");
-			/*
-			 * Put the folio back on mapping->dirty_pages, but
-			 * leave its buffer's dirty state as-is.
-			 */
-			folio_redirty_for_writepage(wbc, folio);
-			err = 0;
-		} else
-			folio_set_error(folio);
-	}
-
-	BUG_ON(folio_test_writeback(folio));
-	folio_start_writeback(folio);	/* Keeps try_to_free_buffers() away. */
-
-	/* Submit the prepared buffers for i/o. */
-	need_end_writeback = true;
-	do {
-		struct buffer_head *next = bh->b_this_page;
-		if (buffer_async_write(bh)) {
-			submit_bh(REQ_OP_WRITE, bh);
-			need_end_writeback = false;
-		}
-		bh = next;
-	} while (bh != head);
-	folio_unlock(folio);
-
-	/* If no i/o was started, need to end writeback here. */
-	if (unlikely(need_end_writeback))
-		folio_end_writeback(folio);
-
-	ntfs_debug("Done.");
-	return err;
-}
-
-/**
- * ntfs_write_mst_block - write a @page to the backing store
- * @page:	page cache page to write out
- * @wbc:	writeback control structure
- *
- * This function is for writing pages belonging to non-resident, mst protected
- * attributes to their backing store.  The only supported attributes are index
- * allocation and $MFT/$DATA.  Both directory inodes and index inodes are
- * supported for the index allocation case.
- *
- * The page must remain locked for the duration of the write because we apply
- * the mst fixups, write, and then undo the fixups, so if we were to unlock the
- * page before undoing the fixups, any other user of the page will see the
- * page contents as corrupt.
- *
- * We clear the page uptodate flag for the duration of the function to ensure
- * exclusion for the $MFT/$DATA case against someone mapping an mft record we
- * are about to apply the mst fixups to.
- *
- * Return 0 on success and -errno on error.
- *
- * Based on ntfs_write_block(), ntfs_mft_writepage(), and
- * write_mft_record_nolock().
- */
-static int ntfs_write_mst_block(struct page *page,
-		struct writeback_control *wbc)
-{
-	sector_t block, dblock, rec_block;
-	struct inode *vi = page->mapping->host;
-	ntfs_inode *ni = NTFS_I(vi);
-	ntfs_volume *vol = ni->vol;
-	u8 *kaddr;
-	unsigned int rec_size = ni->itype.index.block_size;
-	ntfs_inode *locked_nis[PAGE_SIZE / NTFS_BLOCK_SIZE];
-	struct buffer_head *bh, *head, *tbh, *rec_start_bh;
-	struct buffer_head *bhs[MAX_BUF_PER_PAGE];
-	runlist_element *rl;
-	int i, nr_locked_nis, nr_recs, nr_bhs, max_bhs, bhs_per_rec, err, err2;
-	unsigned bh_size, rec_size_bits;
-	bool sync, is_mft, page_is_dirty, rec_is_dirty;
-	unsigned char bh_size_bits;
-
-	if (WARN_ON(rec_size < NTFS_BLOCK_SIZE))
-		return -EINVAL;
-
-	ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, page index "
-			"0x%lx.", vi->i_ino, ni->type, page->index);
-	BUG_ON(!NInoNonResident(ni));
-	BUG_ON(!NInoMstProtected(ni));
-	is_mft = (S_ISREG(vi->i_mode) && !vi->i_ino);
-	/*
-	 * NOTE: ntfs_write_mst_block() would be called for $MFTMirr if a page
-	 * in its page cache were to be marked dirty.  However this should
-	 * never happen with the current driver and considering we do not
-	 * handle this case here we do want to BUG(), at least for now.
-	 */
-	BUG_ON(!(is_mft || S_ISDIR(vi->i_mode) ||
-			(NInoAttr(ni) && ni->type == AT_INDEX_ALLOCATION)));
-	bh_size = vol->sb->s_blocksize;
-	bh_size_bits = vol->sb->s_blocksize_bits;
-	max_bhs = PAGE_SIZE / bh_size;
-	BUG_ON(!max_bhs);
-	BUG_ON(max_bhs > MAX_BUF_PER_PAGE);
-
-	/* Were we called for sync purposes? */
-	sync = (wbc->sync_mode == WB_SYNC_ALL);
-
-	/* Make sure we have mapped buffers. */
-	bh = head = page_buffers(page);
-	BUG_ON(!bh);
-
-	rec_size_bits = ni->itype.index.block_size_bits;
-	BUG_ON(!(PAGE_SIZE >> rec_size_bits));
-	bhs_per_rec = rec_size >> bh_size_bits;
-	BUG_ON(!bhs_per_rec);
-
-	/* The first block in the page. */
-	rec_block = block = (sector_t)page->index <<
-			(PAGE_SHIFT - bh_size_bits);
-
-	/* The first out of bounds block for the data size. */
-	dblock = (i_size_read(vi) + bh_size - 1) >> bh_size_bits;
-
-	rl = NULL;
-	err = err2 = nr_bhs = nr_recs = nr_locked_nis = 0;
-	page_is_dirty = rec_is_dirty = false;
-	rec_start_bh = NULL;
-	do {
-		bool is_retry = false;
-
-		if (likely(block < rec_block)) {
-			if (unlikely(block >= dblock)) {
-				clear_buffer_dirty(bh);
-				set_buffer_uptodate(bh);
-				continue;
-			}
-			/*
-			 * This block is not the first one in the record.  We
-			 * ignore the buffer's dirty state because we could
-			 * have raced with a parallel mark_ntfs_record_dirty().
-			 */
-			if (!rec_is_dirty)
-				continue;
-			if (unlikely(err2)) {
-				if (err2 != -ENOMEM)
-					clear_buffer_dirty(bh);
-				continue;
-			}
-		} else /* if (block == rec_block) */ {
-			BUG_ON(block > rec_block);
-			/* This block is the first one in the record. */
-			rec_block += bhs_per_rec;
-			err2 = 0;
-			if (unlikely(block >= dblock)) {
-				clear_buffer_dirty(bh);
-				continue;
-			}
-			if (!buffer_dirty(bh)) {
-				/* Clean records are not written out. */
-				rec_is_dirty = false;
-				continue;
-			}
-			rec_is_dirty = true;
-			rec_start_bh = bh;
-		}
-		/* Need to map the buffer if it is not mapped already. */
-		if (unlikely(!buffer_mapped(bh))) {
-			VCN vcn;
-			LCN lcn;
-			unsigned int vcn_ofs;
-
-			bh->b_bdev = vol->sb->s_bdev;
-			/* Obtain the vcn and offset of the current block. */
-			vcn = (VCN)block << bh_size_bits;
-			vcn_ofs = vcn & vol->cluster_size_mask;
-			vcn >>= vol->cluster_size_bits;
-			if (!rl) {
-lock_retry_remap:
-				down_read(&ni->runlist.lock);
-				rl = ni->runlist.rl;
-			}
-			if (likely(rl != NULL)) {
-				/* Seek to element containing target vcn. */
-				while (rl->length && rl[1].vcn <= vcn)
-					rl++;
-				lcn = ntfs_rl_vcn_to_lcn(rl, vcn);
-			} else
-				lcn = LCN_RL_NOT_MAPPED;
-			/* Successful remap. */
-			if (likely(lcn >= 0)) {
-				/* Setup buffer head to correct block. */
-				bh->b_blocknr = ((lcn <<
-						vol->cluster_size_bits) +
-						vcn_ofs) >> bh_size_bits;
-				set_buffer_mapped(bh);
-			} else {
-				/*
-				 * Remap failed.  Retry to map the runlist once
-				 * unless we are working on $MFT which always
-				 * has the whole of its runlist in memory.
-				 */
-				if (!is_mft && !is_retry &&
-						lcn == LCN_RL_NOT_MAPPED) {
-					is_retry = true;
-					/*
-					 * Attempt to map runlist, dropping
-					 * lock for the duration.
-					 */
-					up_read(&ni->runlist.lock);
-					err2 = ntfs_map_runlist(ni, vcn);
-					if (likely(!err2))
-						goto lock_retry_remap;
-					if (err2 == -ENOMEM)
-						page_is_dirty = true;
-					lcn = err2;
-				} else {
-					err2 = -EIO;
-					if (!rl)
-						up_read(&ni->runlist.lock);
-				}
-				/* Hard error.  Abort writing this record. */
-				if (!err || err == -ENOMEM)
-					err = err2;
-				bh->b_blocknr = -1;
-				ntfs_error(vol->sb, "Cannot write ntfs record "
-						"0x%llx (inode 0x%lx, "
-						"attribute type 0x%x) because "
-						"its location on disk could "
-						"not be determined (error "
-						"code %lli).",
-						(long long)block <<
-						bh_size_bits >>
-						vol->mft_record_size_bits,
-						ni->mft_no, ni->type,
-						(long long)lcn);
-				/*
-				 * If this is not the first buffer, remove the
-				 * buffers in this record from the list of
-				 * buffers to write and clear their dirty bit
-				 * if not error -ENOMEM.
-				 */
-				if (rec_start_bh != bh) {
-					while (bhs[--nr_bhs] != rec_start_bh)
-						;
-					if (err2 != -ENOMEM) {
-						do {
-							clear_buffer_dirty(
-								rec_start_bh);
-						} while ((rec_start_bh =
-								rec_start_bh->
-								b_this_page) !=
-								bh);
-					}
-				}
-				continue;
-			}
-		}
-		BUG_ON(!buffer_uptodate(bh));
-		BUG_ON(nr_bhs >= max_bhs);
-		bhs[nr_bhs++] = bh;
-	} while (block++, (bh = bh->b_this_page) != head);
-	if (unlikely(rl))
-		up_read(&ni->runlist.lock);
-	/* If there were no dirty buffers, we are done. */
-	if (!nr_bhs)
-		goto done;
-	/* Map the page so we can access its contents. */
-	kaddr = kmap(page);
-	/* Clear the page uptodate flag whilst the mst fixups are applied. */
-	BUG_ON(!PageUptodate(page));
-	ClearPageUptodate(page);
-	for (i = 0; i < nr_bhs; i++) {
-		unsigned int ofs;
-
-		/* Skip buffers which are not at the beginning of records. */
-		if (i % bhs_per_rec)
-			continue;
-		tbh = bhs[i];
-		ofs = bh_offset(tbh);
-		if (is_mft) {
-			ntfs_inode *tni;
-			unsigned long mft_no;
-
-			/* Get the mft record number. */
-			mft_no = (((s64)page->index << PAGE_SHIFT) + ofs)
-					>> rec_size_bits;
-			/* Check whether to write this mft record. */
-			tni = NULL;
-			if (!ntfs_may_write_mft_record(vol, mft_no,
-					(MFT_RECORD*)(kaddr + ofs), &tni)) {
-				/*
-				 * The record should not be written.  This
-				 * means we need to redirty the page before
-				 * returning.
-				 */
-				page_is_dirty = true;
-				/*
-				 * Remove the buffers in this mft record from
-				 * the list of buffers to write.
-				 */
-				do {
-					bhs[i] = NULL;
-				} while (++i % bhs_per_rec);
-				continue;
-			}
-			/*
-			 * The record should be written.  If a locked ntfs
-			 * inode was returned, add it to the array of locked
-			 * ntfs inodes.
-			 */
-			if (tni)
-				locked_nis[nr_locked_nis++] = tni;
-		}
-		/* Apply the mst protection fixups. */
-		err2 = pre_write_mst_fixup((NTFS_RECORD*)(kaddr + ofs),
-				rec_size);
-		if (unlikely(err2)) {
-			if (!err || err == -ENOMEM)
-				err = -EIO;
-			ntfs_error(vol->sb, "Failed to apply mst fixups "
-					"(inode 0x%lx, attribute type 0x%x, "
-					"page index 0x%lx, page offset 0x%x)!"
-					"  Unmount and run chkdsk.", vi->i_ino,
-					ni->type, page->index, ofs);
-			/*
-			 * Mark all the buffers in this record clean as we do
-			 * not want to write corrupt data to disk.
-			 */
-			do {
-				clear_buffer_dirty(bhs[i]);
-				bhs[i] = NULL;
-			} while (++i % bhs_per_rec);
-			continue;
-		}
-		nr_recs++;
-	}
-	/* If no records are to be written out, we are done. */
-	if (!nr_recs)
-		goto unm_done;
-	flush_dcache_page(page);
-	/* Lock buffers and start synchronous write i/o on them. */
-	for (i = 0; i < nr_bhs; i++) {
-		tbh = bhs[i];
-		if (!tbh)
-			continue;
-		if (!trylock_buffer(tbh))
-			BUG();
-		/* The buffer dirty state is now irrelevant, just clean it. */
-		clear_buffer_dirty(tbh);
-		BUG_ON(!buffer_uptodate(tbh));
-		BUG_ON(!buffer_mapped(tbh));
-		get_bh(tbh);
-		tbh->b_end_io = end_buffer_write_sync;
-		submit_bh(REQ_OP_WRITE, tbh);
-	}
-	/* Synchronize the mft mirror now if not @sync. */
-	if (is_mft && !sync)
-		goto do_mirror;
-do_wait:
-	/* Wait on i/o completion of buffers. */
-	for (i = 0; i < nr_bhs; i++) {
-		tbh = bhs[i];
-		if (!tbh)
-			continue;
-		wait_on_buffer(tbh);
-		if (unlikely(!buffer_uptodate(tbh))) {
-			ntfs_error(vol->sb, "I/O error while writing ntfs "
-					"record buffer (inode 0x%lx, "
-					"attribute type 0x%x, page index "
-					"0x%lx, page offset 0x%lx)!  Unmount "
-					"and run chkdsk.", vi->i_ino, ni->type,
-					page->index, bh_offset(tbh));
-			if (!err || err == -ENOMEM)
-				err = -EIO;
-			/*
-			 * Set the buffer uptodate so the page and buffer
-			 * states do not become out of sync.
-			 */
-			set_buffer_uptodate(tbh);
-		}
-	}
-	/* If @sync, now synchronize the mft mirror. */
-	if (is_mft && sync) {
-do_mirror:
-		for (i = 0; i < nr_bhs; i++) {
-			unsigned long mft_no;
-			unsigned int ofs;
-
-			/*
-			 * Skip buffers which are not at the beginning of
-			 * records.
-			 */
-			if (i % bhs_per_rec)
-				continue;
-			tbh = bhs[i];
-			/* Skip removed buffers (and hence records). */
-			if (!tbh)
-				continue;
-			ofs = bh_offset(tbh);
-			/* Get the mft record number. */
-			mft_no = (((s64)page->index << PAGE_SHIFT) + ofs)
-					>> rec_size_bits;
-			if (mft_no < vol->mftmirr_size)
-				ntfs_sync_mft_mirror(vol, mft_no,
-						(MFT_RECORD*)(kaddr + ofs),
-						sync);
-		}
-		if (!sync)
-			goto do_wait;
-	}
-	/* Remove the mst protection fixups again. */
-	for (i = 0; i < nr_bhs; i++) {
-		if (!(i % bhs_per_rec)) {
-			tbh = bhs[i];
-			if (!tbh)
-				continue;
-			post_write_mst_fixup((NTFS_RECORD*)(kaddr +
-					bh_offset(tbh)));
-		}
-	}
-	flush_dcache_page(page);
-unm_done:
-	/* Unlock any locked inodes. */
-	while (nr_locked_nis-- > 0) {
-		ntfs_inode *tni, *base_tni;
-		
-		tni = locked_nis[nr_locked_nis];
-		/* Get the base inode. */
-		mutex_lock(&tni->extent_lock);
-		if (tni->nr_extents >= 0)
-			base_tni = tni;
-		else {
-			base_tni = tni->ext.base_ntfs_ino;
-			BUG_ON(!base_tni);
-		}
-		mutex_unlock(&tni->extent_lock);
-		ntfs_debug("Unlocking %s inode 0x%lx.",
-				tni == base_tni ? "base" : "extent",
-				tni->mft_no);
-		mutex_unlock(&tni->mrec_lock);
-		atomic_dec(&tni->count);
-		iput(VFS_I(base_tni));
-	}
-	SetPageUptodate(page);
-	kunmap(page);
-done:
-	if (unlikely(err && err != -ENOMEM)) {
-		/*
-		 * Set page error if there is only one ntfs record in the page.
-		 * Otherwise we would loose per-record granularity.
-		 */
-		if (ni->itype.index.block_size == PAGE_SIZE)
-			SetPageError(page);
-		NVolSetErrors(vol);
-	}
-	if (page_is_dirty) {
-		ntfs_debug("Page still contains one or more dirty ntfs "
-				"records.  Redirtying the page starting at "
-				"record 0x%lx.", page->index <<
-				(PAGE_SHIFT - rec_size_bits));
-		redirty_page_for_writepage(wbc, page);
-		unlock_page(page);
-	} else {
-		/*
-		 * Keep the VM happy.  This must be done otherwise the
-		 * radix-tree tag PAGECACHE_TAG_DIRTY remains set even though
-		 * the page is clean.
-		 */
-		BUG_ON(PageWriteback(page));
-		set_page_writeback(page);
-		unlock_page(page);
-		end_page_writeback(page);
-	}
-	if (likely(!err))
-		ntfs_debug("Done.");
-	return err;
-}
-
-/**
- * ntfs_writepage - write a @page to the backing store
- * @page:	page cache page to write out
- * @wbc:	writeback control structure
- *
- * This is called from the VM when it wants to have a dirty ntfs page cache
- * page cleaned.  The VM has already locked the page and marked it clean.
- *
- * For non-resident attributes, ntfs_writepage() writes the @page by calling
- * the ntfs version of the generic block_write_full_folio() function,
- * ntfs_write_block(), which in turn if necessary creates and writes the
- * buffers associated with the page asynchronously.
- *
- * For resident attributes, OTOH, ntfs_writepage() writes the @page by copying
- * the data to the mft record (which at this stage is most likely in memory).
- * The mft record is then marked dirty and written out asynchronously via the
- * vfs inode dirty code path for the inode the mft record belongs to or via the
- * vm page dirty code path for the page the mft record is in.
- *
- * Based on ntfs_read_folio() and fs/buffer.c::block_write_full_folio().
- *
- * Return 0 on success and -errno on error.
- */
-static int ntfs_writepage(struct page *page, struct writeback_control *wbc)
-{
-	struct folio *folio = page_folio(page);
-	loff_t i_size;
-	struct inode *vi = folio->mapping->host;
-	ntfs_inode *base_ni = NULL, *ni = NTFS_I(vi);
-	char *addr;
-	ntfs_attr_search_ctx *ctx = NULL;
-	MFT_RECORD *m = NULL;
-	u32 attr_len;
-	int err;
-
-retry_writepage:
-	BUG_ON(!folio_test_locked(folio));
-	i_size = i_size_read(vi);
-	/* Is the folio fully outside i_size? (truncate in progress) */
-	if (unlikely(folio->index >= (i_size + PAGE_SIZE - 1) >>
-			PAGE_SHIFT)) {
-		/*
-		 * The folio may have dirty, unmapped buffers.  Make them
-		 * freeable here, so the page does not leak.
-		 */
-		block_invalidate_folio(folio, 0, folio_size(folio));
-		folio_unlock(folio);
-		ntfs_debug("Write outside i_size - truncated?");
-		return 0;
-	}
-	/*
-	 * Only $DATA attributes can be encrypted and only unnamed $DATA
-	 * attributes can be compressed.  Index root can have the flags set but
-	 * this means to create compressed/encrypted files, not that the
-	 * attribute is compressed/encrypted.  Note we need to check for
-	 * AT_INDEX_ALLOCATION since this is the type of both directory and
-	 * index inodes.
-	 */
-	if (ni->type != AT_INDEX_ALLOCATION) {
-		/* If file is encrypted, deny access, just like NT4. */
-		if (NInoEncrypted(ni)) {
-			folio_unlock(folio);
-			BUG_ON(ni->type != AT_DATA);
-			ntfs_debug("Denying write access to encrypted file.");
-			return -EACCES;
-		}
-		/* Compressed data streams are handled in compress.c. */
-		if (NInoNonResident(ni) && NInoCompressed(ni)) {
-			BUG_ON(ni->type != AT_DATA);
-			BUG_ON(ni->name_len);
-			// TODO: Implement and replace this with
-			// return ntfs_write_compressed_block(page);
-			folio_unlock(folio);
-			ntfs_error(vi->i_sb, "Writing to compressed files is "
-					"not supported yet.  Sorry.");
-			return -EOPNOTSUPP;
-		}
-		// TODO: Implement and remove this check.
-		if (NInoNonResident(ni) && NInoSparse(ni)) {
-			folio_unlock(folio);
-			ntfs_error(vi->i_sb, "Writing to sparse files is not "
-					"supported yet.  Sorry.");
-			return -EOPNOTSUPP;
-		}
-	}
-	/* NInoNonResident() == NInoIndexAllocPresent() */
-	if (NInoNonResident(ni)) {
-		/* We have to zero every time due to mmap-at-end-of-file. */
-		if (folio->index >= (i_size >> PAGE_SHIFT)) {
-			/* The folio straddles i_size. */
-			unsigned int ofs = i_size & (folio_size(folio) - 1);
-			folio_zero_segment(folio, ofs, folio_size(folio));
-		}
-		/* Handle mst protected attributes. */
-		if (NInoMstProtected(ni))
-			return ntfs_write_mst_block(page, wbc);
-		/* Normal, non-resident data stream. */
-		return ntfs_write_block(folio, wbc);
-	}
-	/*
-	 * Attribute is resident, implying it is not compressed, encrypted, or
-	 * mst protected.  This also means the attribute is smaller than an mft
-	 * record and hence smaller than a folio, so can simply return error on
-	 * any folios with index above 0.  Note the attribute can actually be
-	 * marked compressed but if it is resident the actual data is not
-	 * compressed so we are ok to ignore the compressed flag here.
-	 */
-	BUG_ON(folio_buffers(folio));
-	BUG_ON(!folio_test_uptodate(folio));
-	if (unlikely(folio->index > 0)) {
-		ntfs_error(vi->i_sb, "BUG()! folio->index (0x%lx) > 0.  "
-				"Aborting write.", folio->index);
-		BUG_ON(folio_test_writeback(folio));
-		folio_start_writeback(folio);
-		folio_unlock(folio);
-		folio_end_writeback(folio);
-		return -EIO;
-	}
-	if (!NInoAttr(ni))
-		base_ni = ni;
-	else
-		base_ni = ni->ext.base_ntfs_ino;
-	/* Map, pin, and lock the mft record. */
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		m = NULL;
-		ctx = NULL;
-		goto err_out;
-	}
-	/*
-	 * If a parallel write made the attribute non-resident, drop the mft
-	 * record and retry the writepage.
-	 */
-	if (unlikely(NInoNonResident(ni))) {
-		unmap_mft_record(base_ni);
-		goto retry_writepage;
-	}
-	ctx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err))
-		goto err_out;
-	/*
-	 * Keep the VM happy.  This must be done otherwise
-	 * PAGECACHE_TAG_DIRTY remains set even though the folio is clean.
-	 */
-	BUG_ON(folio_test_writeback(folio));
-	folio_start_writeback(folio);
-	folio_unlock(folio);
-	attr_len = le32_to_cpu(ctx->attr->data.resident.value_length);
-	i_size = i_size_read(vi);
-	if (unlikely(attr_len > i_size)) {
-		/* Race with shrinking truncate or a failed truncate. */
-		attr_len = i_size;
-		/*
-		 * If the truncate failed, fix it up now.  If a concurrent
-		 * truncate, we do its job, so it does not have to do anything.
-		 */
-		err = ntfs_resident_attr_value_resize(ctx->mrec, ctx->attr,
-				attr_len);
-		/* Shrinking cannot fail. */
-		BUG_ON(err);
-	}
-	addr = kmap_local_folio(folio, 0);
-	/* Copy the data from the folio to the mft record. */
-	memcpy((u8*)ctx->attr +
-			le16_to_cpu(ctx->attr->data.resident.value_offset),
-			addr, attr_len);
-	/* Zero out of bounds area in the page cache folio. */
-	memset(addr + attr_len, 0, folio_size(folio) - attr_len);
-	kunmap_local(addr);
-	flush_dcache_folio(folio);
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	/* We are done with the folio. */
-	folio_end_writeback(folio);
-	/* Finally, mark the mft record dirty, so it gets written back. */
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-	return 0;
-err_out:
-	if (err == -ENOMEM) {
-		ntfs_warning(vi->i_sb, "Error allocating memory. Redirtying "
-				"page so we try again later.");
-		/*
-		 * Put the folio back on mapping->dirty_pages, but leave its
-		 * buffers' dirty state as-is.
-		 */
-		folio_redirty_for_writepage(wbc, folio);
-		err = 0;
-	} else {
-		ntfs_error(vi->i_sb, "Resident attribute write failed with "
-				"error %i.", err);
-		folio_set_error(folio);
-		NVolSetErrors(ni->vol);
-	}
-	folio_unlock(folio);
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(base_ni);
-	return err;
-}
-
-#endif	/* NTFS_RW */
-
-/**
- * ntfs_bmap - map logical file block to physical device block
- * @mapping:	address space mapping to which the block to be mapped belongs
- * @block:	logical block to map to its physical device block
- *
- * For regular, non-resident files (i.e. not compressed and not encrypted), map
- * the logical @block belonging to the file described by the address space
- * mapping @mapping to its physical device block.
- *
- * The size of the block is equal to the @s_blocksize field of the super block
- * of the mounted file system which is guaranteed to be smaller than or equal
- * to the cluster size thus the block is guaranteed to fit entirely inside the
- * cluster which means we do not need to care how many contiguous bytes are
- * available after the beginning of the block.
- *
- * Return the physical device block if the mapping succeeded or 0 if the block
- * is sparse or there was an error.
- *
- * Note: This is a problem if someone tries to run bmap() on $Boot system file
- * as that really is in block zero but there is nothing we can do.  bmap() is
- * just broken in that respect (just like it cannot distinguish sparse from
- * not available or error).
- */
-static sector_t ntfs_bmap(struct address_space *mapping, sector_t block)
-{
-	s64 ofs, size;
-	loff_t i_size;
-	LCN lcn;
-	unsigned long blocksize, flags;
-	ntfs_inode *ni = NTFS_I(mapping->host);
-	ntfs_volume *vol = ni->vol;
-	unsigned delta;
-	unsigned char blocksize_bits, cluster_size_shift;
-
-	ntfs_debug("Entering for mft_no 0x%lx, logical block 0x%llx.",
-			ni->mft_no, (unsigned long long)block);
-	if (ni->type != AT_DATA || !NInoNonResident(ni) || NInoEncrypted(ni)) {
-		ntfs_error(vol->sb, "BMAP does not make sense for %s "
-				"attributes, returning 0.",
-				(ni->type != AT_DATA) ? "non-data" :
-				(!NInoNonResident(ni) ? "resident" :
-				"encrypted"));
-		return 0;
-	}
-	/* None of these can happen. */
-	BUG_ON(NInoCompressed(ni));
-	BUG_ON(NInoMstProtected(ni));
-	blocksize = vol->sb->s_blocksize;
-	blocksize_bits = vol->sb->s_blocksize_bits;
-	ofs = (s64)block << blocksize_bits;
-	read_lock_irqsave(&ni->size_lock, flags);
-	size = ni->initialized_size;
-	i_size = i_size_read(VFS_I(ni));
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	/*
-	 * If the offset is outside the initialized size or the block straddles
-	 * the initialized size then pretend it is a hole unless the
-	 * initialized size equals the file size.
-	 */
-	if (unlikely(ofs >= size || (ofs + blocksize > size && size < i_size)))
-		goto hole;
-	cluster_size_shift = vol->cluster_size_bits;
-	down_read(&ni->runlist.lock);
-	lcn = ntfs_attr_vcn_to_lcn_nolock(ni, ofs >> cluster_size_shift, false);
-	up_read(&ni->runlist.lock);
-	if (unlikely(lcn < LCN_HOLE)) {
-		/*
-		 * Step down to an integer to avoid gcc doing a long long
-		 * comparision in the switch when we know @lcn is between
-		 * LCN_HOLE and LCN_EIO (i.e. -1 to -5).
-		 *
-		 * Otherwise older gcc (at least on some architectures) will
-		 * try to use __cmpdi2() which is of course not available in
-		 * the kernel.
-		 */
-		switch ((int)lcn) {
-		case LCN_ENOENT:
-			/*
-			 * If the offset is out of bounds then pretend it is a
-			 * hole.
-			 */
-			goto hole;
-		case LCN_ENOMEM:
-			ntfs_error(vol->sb, "Not enough memory to complete "
-					"mapping for inode 0x%lx.  "
-					"Returning 0.", ni->mft_no);
-			break;
-		default:
-			ntfs_error(vol->sb, "Failed to complete mapping for "
-					"inode 0x%lx.  Run chkdsk.  "
-					"Returning 0.", ni->mft_no);
-			break;
-		}
-		return 0;
-	}
-	if (lcn < 0) {
-		/* It is a hole. */
-hole:
-		ntfs_debug("Done (returning hole).");
-		return 0;
-	}
-	/*
-	 * The block is really allocated and fullfils all our criteria.
-	 * Convert the cluster to units of block size and return the result.
-	 */
-	delta = ofs & vol->cluster_size_mask;
-	if (unlikely(sizeof(block) < sizeof(lcn))) {
-		block = lcn = ((lcn << cluster_size_shift) + delta) >>
-				blocksize_bits;
-		/* If the block number was truncated return 0. */
-		if (unlikely(block != lcn)) {
-			ntfs_error(vol->sb, "Physical block 0x%llx is too "
-					"large to be returned, returning 0.",
-					(long long)lcn);
-			return 0;
-		}
-	} else
-		block = ((lcn << cluster_size_shift) + delta) >>
-				blocksize_bits;
-	ntfs_debug("Done (returning block 0x%llx).", (unsigned long long)lcn);
-	return block;
-}
-
-/*
- * ntfs_normal_aops - address space operations for normal inodes and attributes
- *
- * Note these are not used for compressed or mst protected inodes and
- * attributes.
- */
-const struct address_space_operations ntfs_normal_aops = {
-	.read_folio	= ntfs_read_folio,
-#ifdef NTFS_RW
-	.writepage	= ntfs_writepage,
-	.dirty_folio	= block_dirty_folio,
-#endif /* NTFS_RW */
-	.bmap		= ntfs_bmap,
-	.migrate_folio	= buffer_migrate_folio,
-	.is_partially_uptodate = block_is_partially_uptodate,
-	.error_remove_folio = generic_error_remove_folio,
-};
-
-/*
- * ntfs_compressed_aops - address space operations for compressed inodes
- */
-const struct address_space_operations ntfs_compressed_aops = {
-	.read_folio	= ntfs_read_folio,
-#ifdef NTFS_RW
-	.writepage	= ntfs_writepage,
-	.dirty_folio	= block_dirty_folio,
-#endif /* NTFS_RW */
-	.migrate_folio	= buffer_migrate_folio,
-	.is_partially_uptodate = block_is_partially_uptodate,
-	.error_remove_folio = generic_error_remove_folio,
-};
-
-/*
- * ntfs_mst_aops - general address space operations for mst protecteed inodes
- *			  and attributes
- */
-const struct address_space_operations ntfs_mst_aops = {
-	.read_folio	= ntfs_read_folio,	/* Fill page with data. */
-#ifdef NTFS_RW
-	.writepage	= ntfs_writepage,	/* Write dirty page to disk. */
-	.dirty_folio	= filemap_dirty_folio,
-#endif /* NTFS_RW */
-	.migrate_folio	= buffer_migrate_folio,
-	.is_partially_uptodate	= block_is_partially_uptodate,
-	.error_remove_folio = generic_error_remove_folio,
-};
-
-#ifdef NTFS_RW
-
-/**
- * mark_ntfs_record_dirty - mark an ntfs record dirty
- * @page:	page containing the ntfs record to mark dirty
- * @ofs:	byte offset within @page at which the ntfs record begins
- *
- * Set the buffers and the page in which the ntfs record is located dirty.
- *
- * The latter also marks the vfs inode the ntfs record belongs to dirty
- * (I_DIRTY_PAGES only).
- *
- * If the page does not have buffers, we create them and set them uptodate.
- * The page may not be locked which is why we need to handle the buffers under
- * the mapping->i_private_lock.  Once the buffers are marked dirty we no longer
- * need the lock since try_to_free_buffers() does not free dirty buffers.
- */
-void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) {
-	struct address_space *mapping = page->mapping;
-	ntfs_inode *ni = NTFS_I(mapping->host);
-	struct buffer_head *bh, *head, *buffers_to_free = NULL;
-	unsigned int end, bh_size, bh_ofs;
-
-	BUG_ON(!PageUptodate(page));
-	end = ofs + ni->itype.index.block_size;
-	bh_size = VFS_I(ni)->i_sb->s_blocksize;
-	spin_lock(&mapping->i_private_lock);
-	if (unlikely(!page_has_buffers(page))) {
-		spin_unlock(&mapping->i_private_lock);
-		bh = head = alloc_page_buffers(page, bh_size, true);
-		spin_lock(&mapping->i_private_lock);
-		if (likely(!page_has_buffers(page))) {
-			struct buffer_head *tail;
-
-			do {
-				set_buffer_uptodate(bh);
-				tail = bh;
-				bh = bh->b_this_page;
-			} while (bh);
-			tail->b_this_page = head;
-			attach_page_private(page, head);
-		} else
-			buffers_to_free = bh;
-	}
-	bh = head = page_buffers(page);
-	BUG_ON(!bh);
-	do {
-		bh_ofs = bh_offset(bh);
-		if (bh_ofs + bh_size <= ofs)
-			continue;
-		if (unlikely(bh_ofs >= end))
-			break;
-		set_buffer_dirty(bh);
-	} while ((bh = bh->b_this_page) != head);
-	spin_unlock(&mapping->i_private_lock);
-	filemap_dirty_folio(mapping, page_folio(page));
-	if (unlikely(buffers_to_free)) {
-		do {
-			bh = buffers_to_free->b_this_page;
-			free_buffer_head(buffers_to_free);
-			buffers_to_free = bh;
-		} while (buffers_to_free);
-	}
-}
-
-#endif /* NTFS_RW */
diff --git a/fs/ntfs/aops.h b/fs/ntfs/aops.h
deleted file mode 100644
index 8d0958a149cb..000000000000
--- a/fs/ntfs/aops.h
+++ /dev/null
@@ -1,88 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * aops.h - Defines for NTFS kernel address space operations and page cache
- *	    handling.  Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2004 Anton Altaparmakov
- * Copyright (c) 2002 Richard Russon
- */
-
-#ifndef _LINUX_NTFS_AOPS_H
-#define _LINUX_NTFS_AOPS_H
-
-#include <linux/mm.h>
-#include <linux/highmem.h>
-#include <linux/pagemap.h>
-#include <linux/fs.h>
-
-#include "inode.h"
-
-/**
- * ntfs_unmap_page - release a page that was mapped using ntfs_map_page()
- * @page:	the page to release
- *
- * Unpin, unmap and release a page that was obtained from ntfs_map_page().
- */
-static inline void ntfs_unmap_page(struct page *page)
-{
-	kunmap(page);
-	put_page(page);
-}
-
-/**
- * ntfs_map_page - map a page into accessible memory, reading it if necessary
- * @mapping:	address space for which to obtain the page
- * @index:	index into the page cache for @mapping of the page to map
- *
- * Read a page from the page cache of the address space @mapping at position
- * @index, where @index is in units of PAGE_SIZE, and not in bytes.
- *
- * If the page is not in memory it is loaded from disk first using the
- * read_folio method defined in the address space operations of @mapping
- * and the page is added to the page cache of @mapping in the process.
- *
- * If the page belongs to an mst protected attribute and it is marked as such
- * in its ntfs inode (NInoMstProtected()) the mst fixups are applied but no
- * error checking is performed.  This means the caller has to verify whether
- * the ntfs record(s) contained in the page are valid or not using one of the
- * ntfs_is_XXXX_record{,p}() macros, where XXXX is the record type you are
- * expecting to see.  (For details of the macros, see fs/ntfs/layout.h.)
- *
- * If the page is in high memory it is mapped into memory directly addressible
- * by the kernel.
- *
- * Finally the page count is incremented, thus pinning the page into place.
- *
- * The above means that page_address(page) can be used on all pages obtained
- * with ntfs_map_page() to get the kernel virtual address of the page.
- *
- * When finished with the page, the caller has to call ntfs_unmap_page() to
- * unpin, unmap and release the page.
- *
- * Note this does not grant exclusive access. If such is desired, the caller
- * must provide it independently of the ntfs_{un}map_page() calls by using
- * a {rw_}semaphore or other means of serialization. A spin lock cannot be
- * used as ntfs_map_page() can block.
- *
- * The unlocked and uptodate page is returned on success or an encoded error
- * on failure. Caller has to test for error using the IS_ERR() macro on the
- * return value. If that evaluates to 'true', the negative error code can be
- * obtained using PTR_ERR() on the return value of ntfs_map_page().
- */
-static inline struct page *ntfs_map_page(struct address_space *mapping,
-		unsigned long index)
-{
-	struct page *page = read_mapping_page(mapping, index, NULL);
-
-	if (!IS_ERR(page))
-		kmap(page);
-	return page;
-}
-
-#ifdef NTFS_RW
-
-extern void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs);
-
-#endif /* NTFS_RW */
-
-#endif /* _LINUX_NTFS_AOPS_H */
diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c
deleted file mode 100644
index f79408f9127a..000000000000
--- a/fs/ntfs/attrib.c
+++ /dev/null
@@ -1,2624 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * attrib.c - NTFS attribute operations.  Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2012 Anton Altaparmakov and Tuxera Inc.
- * Copyright (c) 2002 Richard Russon
- */
-
-#include <linux/buffer_head.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/swap.h>
-#include <linux/writeback.h>
-
-#include "attrib.h"
-#include "debug.h"
-#include "layout.h"
-#include "lcnalloc.h"
-#include "malloc.h"
-#include "mft.h"
-#include "ntfs.h"
-#include "types.h"
-
-/**
- * ntfs_map_runlist_nolock - map (a part of) a runlist of an ntfs inode
- * @ni:		ntfs inode for which to map (part of) a runlist
- * @vcn:	map runlist part containing this vcn
- * @ctx:	active attribute search context if present or NULL if not
- *
- * Map the part of a runlist containing the @vcn of the ntfs inode @ni.
- *
- * If @ctx is specified, it is an active search context of @ni and its base mft
- * record.  This is needed when ntfs_map_runlist_nolock() encounters unmapped
- * runlist fragments and allows their mapping.  If you do not have the mft
- * record mapped, you can specify @ctx as NULL and ntfs_map_runlist_nolock()
- * will perform the necessary mapping and unmapping.
- *
- * Note, ntfs_map_runlist_nolock() saves the state of @ctx on entry and
- * restores it before returning.  Thus, @ctx will be left pointing to the same
- * attribute on return as on entry.  However, the actual pointers in @ctx may
- * point to different memory locations on return, so you must remember to reset
- * any cached pointers from the @ctx, i.e. after the call to
- * ntfs_map_runlist_nolock(), you will probably want to do:
- *	m = ctx->mrec;
- *	a = ctx->attr;
- * Assuming you cache ctx->attr in a variable @a of type ATTR_RECORD * and that
- * you cache ctx->mrec in a variable @m of type MFT_RECORD *.
- *
- * Return 0 on success and -errno on error.  There is one special error code
- * which is not an error as such.  This is -ENOENT.  It means that @vcn is out
- * of bounds of the runlist.
- *
- * Note the runlist can be NULL after this function returns if @vcn is zero and
- * the attribute has zero allocated size, i.e. there simply is no runlist.
- *
- * WARNING: If @ctx is supplied, regardless of whether success or failure is
- *	    returned, you need to check IS_ERR(@ctx->mrec) and if 'true' the @ctx
- *	    is no longer valid, i.e. you need to either call
- *	    ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it.
- *	    In that case PTR_ERR(@ctx->mrec) will give you the error code for
- *	    why the mapping of the old inode failed.
- *
- * Locking: - The runlist described by @ni must be locked for writing on entry
- *	      and is locked on return.  Note the runlist will be modified.
- *	    - If @ctx is NULL, the base mft record of @ni must not be mapped on
- *	      entry and it will be left unmapped on return.
- *	    - If @ctx is not NULL, the base mft record must be mapped on entry
- *	      and it will be left mapped on return.
- */
-int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn, ntfs_attr_search_ctx *ctx)
-{
-	VCN end_vcn;
-	unsigned long flags;
-	ntfs_inode *base_ni;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
-	runlist_element *rl;
-	struct page *put_this_page = NULL;
-	int err = 0;
-	bool ctx_is_temporary, ctx_needs_reset;
-	ntfs_attr_search_ctx old_ctx = { NULL, };
-
-	ntfs_debug("Mapping runlist part containing vcn 0x%llx.",
-			(unsigned long long)vcn);
-	if (!NInoAttr(ni))
-		base_ni = ni;
-	else
-		base_ni = ni->ext.base_ntfs_ino;
-	if (!ctx) {
-		ctx_is_temporary = ctx_needs_reset = true;
-		m = map_mft_record(base_ni);
-		if (IS_ERR(m))
-			return PTR_ERR(m);
-		ctx = ntfs_attr_get_search_ctx(base_ni, m);
-		if (unlikely(!ctx)) {
-			err = -ENOMEM;
-			goto err_out;
-		}
-	} else {
-		VCN allocated_size_vcn;
-
-		BUG_ON(IS_ERR(ctx->mrec));
-		a = ctx->attr;
-		BUG_ON(!a->non_resident);
-		ctx_is_temporary = false;
-		end_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn);
-		read_lock_irqsave(&ni->size_lock, flags);
-		allocated_size_vcn = ni->allocated_size >>
-				ni->vol->cluster_size_bits;
-		read_unlock_irqrestore(&ni->size_lock, flags);
-		if (!a->data.non_resident.lowest_vcn && end_vcn <= 0)
-			end_vcn = allocated_size_vcn - 1;
-		/*
-		 * If we already have the attribute extent containing @vcn in
-		 * @ctx, no need to look it up again.  We slightly cheat in
-		 * that if vcn exceeds the allocated size, we will refuse to
-		 * map the runlist below, so there is definitely no need to get
-		 * the right attribute extent.
-		 */
-		if (vcn >= allocated_size_vcn || (a->type == ni->type &&
-				a->name_length == ni->name_len &&
-				!memcmp((u8*)a + le16_to_cpu(a->name_offset),
-				ni->name, ni->name_len) &&
-				sle64_to_cpu(a->data.non_resident.lowest_vcn)
-				<= vcn && end_vcn >= vcn))
-			ctx_needs_reset = false;
-		else {
-			/* Save the old search context. */
-			old_ctx = *ctx;
-			/*
-			 * If the currently mapped (extent) inode is not the
-			 * base inode we will unmap it when we reinitialize the
-			 * search context which means we need to get a
-			 * reference to the page containing the mapped mft
-			 * record so we do not accidentally drop changes to the
-			 * mft record when it has not been marked dirty yet.
-			 */
-			if (old_ctx.base_ntfs_ino && old_ctx.ntfs_ino !=
-					old_ctx.base_ntfs_ino) {
-				put_this_page = old_ctx.ntfs_ino->page;
-				get_page(put_this_page);
-			}
-			/*
-			 * Reinitialize the search context so we can lookup the
-			 * needed attribute extent.
-			 */
-			ntfs_attr_reinit_search_ctx(ctx);
-			ctx_needs_reset = true;
-		}
-	}
-	if (ctx_needs_reset) {
-		err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-				CASE_SENSITIVE, vcn, NULL, 0, ctx);
-		if (unlikely(err)) {
-			if (err == -ENOENT)
-				err = -EIO;
-			goto err_out;
-		}
-		BUG_ON(!ctx->attr->non_resident);
-	}
-	a = ctx->attr;
-	/*
-	 * Only decompress the mapping pairs if @vcn is inside it.  Otherwise
-	 * we get into problems when we try to map an out of bounds vcn because
-	 * we then try to map the already mapped runlist fragment and
-	 * ntfs_mapping_pairs_decompress() fails.
-	 */
-	end_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn) + 1;
-	if (unlikely(vcn && vcn >= end_vcn)) {
-		err = -ENOENT;
-		goto err_out;
-	}
-	rl = ntfs_mapping_pairs_decompress(ni->vol, a, ni->runlist.rl);
-	if (IS_ERR(rl))
-		err = PTR_ERR(rl);
-	else
-		ni->runlist.rl = rl;
-err_out:
-	if (ctx_is_temporary) {
-		if (likely(ctx))
-			ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(base_ni);
-	} else if (ctx_needs_reset) {
-		/*
-		 * If there is no attribute list, restoring the search context
-		 * is accomplished simply by copying the saved context back over
-		 * the caller supplied context.  If there is an attribute list,
-		 * things are more complicated as we need to deal with mapping
-		 * of mft records and resulting potential changes in pointers.
-		 */
-		if (NInoAttrList(base_ni)) {
-			/*
-			 * If the currently mapped (extent) inode is not the
-			 * one we had before, we need to unmap it and map the
-			 * old one.
-			 */
-			if (ctx->ntfs_ino != old_ctx.ntfs_ino) {
-				/*
-				 * If the currently mapped inode is not the
-				 * base inode, unmap it.
-				 */
-				if (ctx->base_ntfs_ino && ctx->ntfs_ino !=
-						ctx->base_ntfs_ino) {
-					unmap_extent_mft_record(ctx->ntfs_ino);
-					ctx->mrec = ctx->base_mrec;
-					BUG_ON(!ctx->mrec);
-				}
-				/*
-				 * If the old mapped inode is not the base
-				 * inode, map it.
-				 */
-				if (old_ctx.base_ntfs_ino &&
-						old_ctx.ntfs_ino !=
-						old_ctx.base_ntfs_ino) {
-retry_map:
-					ctx->mrec = map_mft_record(
-							old_ctx.ntfs_ino);
-					/*
-					 * Something bad has happened.  If out
-					 * of memory retry till it succeeds.
-					 * Any other errors are fatal and we
-					 * return the error code in ctx->mrec.
-					 * Let the caller deal with it...  We
-					 * just need to fudge things so the
-					 * caller can reinit and/or put the
-					 * search context safely.
-					 */
-					if (IS_ERR(ctx->mrec)) {
-						if (PTR_ERR(ctx->mrec) ==
-								-ENOMEM) {
-							schedule();
-							goto retry_map;
-						} else
-							old_ctx.ntfs_ino =
-								old_ctx.
-								base_ntfs_ino;
-					}
-				}
-			}
-			/* Update the changed pointers in the saved context. */
-			if (ctx->mrec != old_ctx.mrec) {
-				if (!IS_ERR(ctx->mrec))
-					old_ctx.attr = (ATTR_RECORD*)(
-							(u8*)ctx->mrec +
-							((u8*)old_ctx.attr -
-							(u8*)old_ctx.mrec));
-				old_ctx.mrec = ctx->mrec;
-			}
-		}
-		/* Restore the search context to the saved one. */
-		*ctx = old_ctx;
-		/*
-		 * We drop the reference on the page we took earlier.  In the
-		 * case that IS_ERR(ctx->mrec) is true this means we might lose
-		 * some changes to the mft record that had been made between
-		 * the last time it was marked dirty/written out and now.  This
-		 * at this stage is not a problem as the mapping error is fatal
-		 * enough that the mft record cannot be written out anyway and
-		 * the caller is very likely to shutdown the whole inode
-		 * immediately and mark the volume dirty for chkdsk to pick up
-		 * the pieces anyway.
-		 */
-		if (put_this_page)
-			put_page(put_this_page);
-	}
-	return err;
-}
-
-/**
- * ntfs_map_runlist - map (a part of) a runlist of an ntfs inode
- * @ni:		ntfs inode for which to map (part of) a runlist
- * @vcn:	map runlist part containing this vcn
- *
- * Map the part of a runlist containing the @vcn of the ntfs inode @ni.
- *
- * Return 0 on success and -errno on error.  There is one special error code
- * which is not an error as such.  This is -ENOENT.  It means that @vcn is out
- * of bounds of the runlist.
- *
- * Locking: - The runlist must be unlocked on entry and is unlocked on return.
- *	    - This function takes the runlist lock for writing and may modify
- *	      the runlist.
- */
-int ntfs_map_runlist(ntfs_inode *ni, VCN vcn)
-{
-	int err = 0;
-
-	down_write(&ni->runlist.lock);
-	/* Make sure someone else didn't do the work while we were sleeping. */
-	if (likely(ntfs_rl_vcn_to_lcn(ni->runlist.rl, vcn) <=
-			LCN_RL_NOT_MAPPED))
-		err = ntfs_map_runlist_nolock(ni, vcn, NULL);
-	up_write(&ni->runlist.lock);
-	return err;
-}
-
-/**
- * ntfs_attr_vcn_to_lcn_nolock - convert a vcn into a lcn given an ntfs inode
- * @ni:			ntfs inode of the attribute whose runlist to search
- * @vcn:		vcn to convert
- * @write_locked:	true if the runlist is locked for writing
- *
- * Find the virtual cluster number @vcn in the runlist of the ntfs attribute
- * described by the ntfs inode @ni and return the corresponding logical cluster
- * number (lcn).
- *
- * If the @vcn is not mapped yet, the attempt is made to map the attribute
- * extent containing the @vcn and the vcn to lcn conversion is retried.
- *
- * If @write_locked is true the caller has locked the runlist for writing and
- * if false for reading.
- *
- * Since lcns must be >= 0, we use negative return codes with special meaning:
- *
- * Return code	Meaning / Description
- * ==========================================
- *  LCN_HOLE	Hole / not allocated on disk.
- *  LCN_ENOENT	There is no such vcn in the runlist, i.e. @vcn is out of bounds.
- *  LCN_ENOMEM	Not enough memory to map runlist.
- *  LCN_EIO	Critical error (runlist/file is corrupt, i/o error, etc).
- *
- * Locking: - The runlist must be locked on entry and is left locked on return.
- *	    - If @write_locked is 'false', i.e. the runlist is locked for reading,
- *	      the lock may be dropped inside the function so you cannot rely on
- *	      the runlist still being the same when this function returns.
- */
-LCN ntfs_attr_vcn_to_lcn_nolock(ntfs_inode *ni, const VCN vcn,
-		const bool write_locked)
-{
-	LCN lcn;
-	unsigned long flags;
-	bool is_retry = false;
-
-	BUG_ON(!ni);
-	ntfs_debug("Entering for i_ino 0x%lx, vcn 0x%llx, %s_locked.",
-			ni->mft_no, (unsigned long long)vcn,
-			write_locked ? "write" : "read");
-	BUG_ON(!NInoNonResident(ni));
-	BUG_ON(vcn < 0);
-	if (!ni->runlist.rl) {
-		read_lock_irqsave(&ni->size_lock, flags);
-		if (!ni->allocated_size) {
-			read_unlock_irqrestore(&ni->size_lock, flags);
-			return LCN_ENOENT;
-		}
-		read_unlock_irqrestore(&ni->size_lock, flags);
-	}
-retry_remap:
-	/* Convert vcn to lcn.  If that fails map the runlist and retry once. */
-	lcn = ntfs_rl_vcn_to_lcn(ni->runlist.rl, vcn);
-	if (likely(lcn >= LCN_HOLE)) {
-		ntfs_debug("Done, lcn 0x%llx.", (long long)lcn);
-		return lcn;
-	}
-	if (lcn != LCN_RL_NOT_MAPPED) {
-		if (lcn != LCN_ENOENT)
-			lcn = LCN_EIO;
-	} else if (!is_retry) {
-		int err;
-
-		if (!write_locked) {
-			up_read(&ni->runlist.lock);
-			down_write(&ni->runlist.lock);
-			if (unlikely(ntfs_rl_vcn_to_lcn(ni->runlist.rl, vcn) !=
-					LCN_RL_NOT_MAPPED)) {
-				up_write(&ni->runlist.lock);
-				down_read(&ni->runlist.lock);
-				goto retry_remap;
-			}
-		}
-		err = ntfs_map_runlist_nolock(ni, vcn, NULL);
-		if (!write_locked) {
-			up_write(&ni->runlist.lock);
-			down_read(&ni->runlist.lock);
-		}
-		if (likely(!err)) {
-			is_retry = true;
-			goto retry_remap;
-		}
-		if (err == -ENOENT)
-			lcn = LCN_ENOENT;
-		else if (err == -ENOMEM)
-			lcn = LCN_ENOMEM;
-		else
-			lcn = LCN_EIO;
-	}
-	if (lcn != LCN_ENOENT)
-		ntfs_error(ni->vol->sb, "Failed with error code %lli.",
-				(long long)lcn);
-	return lcn;
-}
-
-/**
- * ntfs_attr_find_vcn_nolock - find a vcn in the runlist of an ntfs inode
- * @ni:		ntfs inode describing the runlist to search
- * @vcn:	vcn to find
- * @ctx:	active attribute search context if present or NULL if not
- *
- * Find the virtual cluster number @vcn in the runlist described by the ntfs
- * inode @ni and return the address of the runlist element containing the @vcn.
- *
- * If the @vcn is not mapped yet, the attempt is made to map the attribute
- * extent containing the @vcn and the vcn to lcn conversion is retried.
- *
- * If @ctx is specified, it is an active search context of @ni and its base mft
- * record.  This is needed when ntfs_attr_find_vcn_nolock() encounters unmapped
- * runlist fragments and allows their mapping.  If you do not have the mft
- * record mapped, you can specify @ctx as NULL and ntfs_attr_find_vcn_nolock()
- * will perform the necessary mapping and unmapping.
- *
- * Note, ntfs_attr_find_vcn_nolock() saves the state of @ctx on entry and
- * restores it before returning.  Thus, @ctx will be left pointing to the same
- * attribute on return as on entry.  However, the actual pointers in @ctx may
- * point to different memory locations on return, so you must remember to reset
- * any cached pointers from the @ctx, i.e. after the call to
- * ntfs_attr_find_vcn_nolock(), you will probably want to do:
- *	m = ctx->mrec;
- *	a = ctx->attr;
- * Assuming you cache ctx->attr in a variable @a of type ATTR_RECORD * and that
- * you cache ctx->mrec in a variable @m of type MFT_RECORD *.
- * Note you need to distinguish between the lcn of the returned runlist element
- * being >= 0 and LCN_HOLE.  In the later case you have to return zeroes on
- * read and allocate clusters on write.
- *
- * Return the runlist element containing the @vcn on success and
- * ERR_PTR(-errno) on error.  You need to test the return value with IS_ERR()
- * to decide if the return is success or failure and PTR_ERR() to get to the
- * error code if IS_ERR() is true.
- *
- * The possible error return codes are:
- *	-ENOENT - No such vcn in the runlist, i.e. @vcn is out of bounds.
- *	-ENOMEM - Not enough memory to map runlist.
- *	-EIO	- Critical error (runlist/file is corrupt, i/o error, etc).
- *
- * WARNING: If @ctx is supplied, regardless of whether success or failure is
- *	    returned, you need to check IS_ERR(@ctx->mrec) and if 'true' the @ctx
- *	    is no longer valid, i.e. you need to either call
- *	    ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it.
- *	    In that case PTR_ERR(@ctx->mrec) will give you the error code for
- *	    why the mapping of the old inode failed.
- *
- * Locking: - The runlist described by @ni must be locked for writing on entry
- *	      and is locked on return.  Note the runlist may be modified when
- *	      needed runlist fragments need to be mapped.
- *	    - If @ctx is NULL, the base mft record of @ni must not be mapped on
- *	      entry and it will be left unmapped on return.
- *	    - If @ctx is not NULL, the base mft record must be mapped on entry
- *	      and it will be left mapped on return.
- */
-runlist_element *ntfs_attr_find_vcn_nolock(ntfs_inode *ni, const VCN vcn,
-		ntfs_attr_search_ctx *ctx)
-{
-	unsigned long flags;
-	runlist_element *rl;
-	int err = 0;
-	bool is_retry = false;
-
-	BUG_ON(!ni);
-	ntfs_debug("Entering for i_ino 0x%lx, vcn 0x%llx, with%s ctx.",
-			ni->mft_no, (unsigned long long)vcn, ctx ? "" : "out");
-	BUG_ON(!NInoNonResident(ni));
-	BUG_ON(vcn < 0);
-	if (!ni->runlist.rl) {
-		read_lock_irqsave(&ni->size_lock, flags);
-		if (!ni->allocated_size) {
-			read_unlock_irqrestore(&ni->size_lock, flags);
-			return ERR_PTR(-ENOENT);
-		}
-		read_unlock_irqrestore(&ni->size_lock, flags);
-	}
-retry_remap:
-	rl = ni->runlist.rl;
-	if (likely(rl && vcn >= rl[0].vcn)) {
-		while (likely(rl->length)) {
-			if (unlikely(vcn < rl[1].vcn)) {
-				if (likely(rl->lcn >= LCN_HOLE)) {
-					ntfs_debug("Done.");
-					return rl;
-				}
-				break;
-			}
-			rl++;
-		}
-		if (likely(rl->lcn != LCN_RL_NOT_MAPPED)) {
-			if (likely(rl->lcn == LCN_ENOENT))
-				err = -ENOENT;
-			else
-				err = -EIO;
-		}
-	}
-	if (!err && !is_retry) {
-		/*
-		 * If the search context is invalid we cannot map the unmapped
-		 * region.
-		 */
-		if (IS_ERR(ctx->mrec))
-			err = PTR_ERR(ctx->mrec);
-		else {
-			/*
-			 * The @vcn is in an unmapped region, map the runlist
-			 * and retry.
-			 */
-			err = ntfs_map_runlist_nolock(ni, vcn, ctx);
-			if (likely(!err)) {
-				is_retry = true;
-				goto retry_remap;
-			}
-		}
-		if (err == -EINVAL)
-			err = -EIO;
-	} else if (!err)
-		err = -EIO;
-	if (err != -ENOENT)
-		ntfs_error(ni->vol->sb, "Failed with error code %i.", err);
-	return ERR_PTR(err);
-}
-
-/**
- * ntfs_attr_find - find (next) attribute in mft record
- * @type:	attribute type to find
- * @name:	attribute name to find (optional, i.e. NULL means don't care)
- * @name_len:	attribute name length (only needed if @name present)
- * @ic:		IGNORE_CASE or CASE_SENSITIVE (ignored if @name not present)
- * @val:	attribute value to find (optional, resident attributes only)
- * @val_len:	attribute value length
- * @ctx:	search context with mft record and attribute to search from
- *
- * You should not need to call this function directly.  Use ntfs_attr_lookup()
- * instead.
- *
- * ntfs_attr_find() takes a search context @ctx as parameter and searches the
- * mft record specified by @ctx->mrec, beginning at @ctx->attr, for an
- * attribute of @type, optionally @name and @val.
- *
- * If the attribute is found, ntfs_attr_find() returns 0 and @ctx->attr will
- * point to the found attribute.
- *
- * If the attribute is not found, ntfs_attr_find() returns -ENOENT and
- * @ctx->attr will point to the attribute before which the attribute being
- * searched for would need to be inserted if such an action were to be desired.
- *
- * On actual error, ntfs_attr_find() returns -EIO.  In this case @ctx->attr is
- * undefined and in particular do not rely on it not changing.
- *
- * If @ctx->is_first is 'true', the search begins with @ctx->attr itself.  If it
- * is 'false', the search begins after @ctx->attr.
- *
- * If @ic is IGNORE_CASE, the @name comparisson is not case sensitive and
- * @ctx->ntfs_ino must be set to the ntfs inode to which the mft record
- * @ctx->mrec belongs.  This is so we can get at the ntfs volume and hence at
- * the upcase table.  If @ic is CASE_SENSITIVE, the comparison is case
- * sensitive.  When @name is present, @name_len is the @name length in Unicode
- * characters.
- *
- * If @name is not present (NULL), we assume that the unnamed attribute is
- * being searched for.
- *
- * Finally, the resident attribute value @val is looked for, if present.  If
- * @val is not present (NULL), @val_len is ignored.
- *
- * ntfs_attr_find() only searches the specified mft record and it ignores the
- * presence of an attribute list attribute (unless it is the one being searched
- * for, obviously).  If you need to take attribute lists into consideration,
- * use ntfs_attr_lookup() instead (see below).  This also means that you cannot
- * use ntfs_attr_find() to search for extent records of non-resident
- * attributes, as extents with lowest_vcn != 0 are usually described by the
- * attribute list attribute only. - Note that it is possible that the first
- * extent is only in the attribute list while the last extent is in the base
- * mft record, so do not rely on being able to find the first extent in the
- * base mft record.
- *
- * Warning: Never use @val when looking for attribute types which can be
- *	    non-resident as this most likely will result in a crash!
- */
-static int ntfs_attr_find(const ATTR_TYPE type, const ntfschar *name,
-		const u32 name_len, const IGNORE_CASE_BOOL ic,
-		const u8 *val, const u32 val_len, ntfs_attr_search_ctx *ctx)
-{
-	ATTR_RECORD *a;
-	ntfs_volume *vol = ctx->ntfs_ino->vol;
-	ntfschar *upcase = vol->upcase;
-	u32 upcase_len = vol->upcase_len;
-
-	/*
-	 * Iterate over attributes in mft record starting at @ctx->attr, or the
-	 * attribute following that, if @ctx->is_first is 'true'.
-	 */
-	if (ctx->is_first) {
-		a = ctx->attr;
-		ctx->is_first = false;
-	} else
-		a = (ATTR_RECORD*)((u8*)ctx->attr +
-				le32_to_cpu(ctx->attr->length));
-	for (;;	a = (ATTR_RECORD*)((u8*)a + le32_to_cpu(a->length))) {
-		u8 *mrec_end = (u8 *)ctx->mrec +
-		               le32_to_cpu(ctx->mrec->bytes_allocated);
-		u8 *name_end;
-
-		/* check whether ATTR_RECORD wrap */
-		if ((u8 *)a < (u8 *)ctx->mrec)
-			break;
-
-		/* check whether Attribute Record Header is within bounds */
-		if ((u8 *)a > mrec_end ||
-		    (u8 *)a + sizeof(ATTR_RECORD) > mrec_end)
-			break;
-
-		/* check whether ATTR_RECORD's name is within bounds */
-		name_end = (u8 *)a + le16_to_cpu(a->name_offset) +
-			   a->name_length * sizeof(ntfschar);
-		if (name_end > mrec_end)
-			break;
-
-		ctx->attr = a;
-		if (unlikely(le32_to_cpu(a->type) > le32_to_cpu(type) ||
-				a->type == AT_END))
-			return -ENOENT;
-		if (unlikely(!a->length))
-			break;
-
-		/* check whether ATTR_RECORD's length wrap */
-		if ((u8 *)a + le32_to_cpu(a->length) < (u8 *)a)
-			break;
-		/* check whether ATTR_RECORD's length is within bounds */
-		if ((u8 *)a + le32_to_cpu(a->length) > mrec_end)
-			break;
-
-		if (a->type != type)
-			continue;
-		/*
-		 * If @name is present, compare the two names.  If @name is
-		 * missing, assume we want an unnamed attribute.
-		 */
-		if (!name) {
-			/* The search failed if the found attribute is named. */
-			if (a->name_length)
-				return -ENOENT;
-		} else if (!ntfs_are_names_equal(name, name_len,
-			    (ntfschar*)((u8*)a + le16_to_cpu(a->name_offset)),
-			    a->name_length, ic, upcase, upcase_len)) {
-			register int rc;
-
-			rc = ntfs_collate_names(name, name_len,
-					(ntfschar*)((u8*)a +
-					le16_to_cpu(a->name_offset)),
-					a->name_length, 1, IGNORE_CASE,
-					upcase, upcase_len);
-			/*
-			 * If @name collates before a->name, there is no
-			 * matching attribute.
-			 */
-			if (rc == -1)
-				return -ENOENT;
-			/* If the strings are not equal, continue search. */
-			if (rc)
-				continue;
-			rc = ntfs_collate_names(name, name_len,
-					(ntfschar*)((u8*)a +
-					le16_to_cpu(a->name_offset)),
-					a->name_length, 1, CASE_SENSITIVE,
-					upcase, upcase_len);
-			if (rc == -1)
-				return -ENOENT;
-			if (rc)
-				continue;
-		}
-		/*
-		 * The names match or @name not present and attribute is
-		 * unnamed.  If no @val specified, we have found the attribute
-		 * and are done.
-		 */
-		if (!val)
-			return 0;
-		/* @val is present; compare values. */
-		else {
-			register int rc;
-
-			rc = memcmp(val, (u8*)a + le16_to_cpu(
-					a->data.resident.value_offset),
-					min_t(u32, val_len, le32_to_cpu(
-					a->data.resident.value_length)));
-			/*
-			 * If @val collates before the current attribute's
-			 * value, there is no matching attribute.
-			 */
-			if (!rc) {
-				register u32 avl;
-
-				avl = le32_to_cpu(
-						a->data.resident.value_length);
-				if (val_len == avl)
-					return 0;
-				if (val_len < avl)
-					return -ENOENT;
-			} else if (rc < 0)
-				return -ENOENT;
-		}
-	}
-	ntfs_error(vol->sb, "Inode is corrupt.  Run chkdsk.");
-	NVolSetErrors(vol);
-	return -EIO;
-}
-
-/**
- * load_attribute_list - load an attribute list into memory
- * @vol:		ntfs volume from which to read
- * @runlist:		runlist of the attribute list
- * @al_start:		destination buffer
- * @size:		size of the destination buffer in bytes
- * @initialized_size:	initialized size of the attribute list
- *
- * Walk the runlist @runlist and load all clusters from it copying them into
- * the linear buffer @al. The maximum number of bytes copied to @al is @size
- * bytes. Note, @size does not need to be a multiple of the cluster size. If
- * @initialized_size is less than @size, the region in @al between
- * @initialized_size and @size will be zeroed and not read from disk.
- *
- * Return 0 on success or -errno on error.
- */
-int load_attribute_list(ntfs_volume *vol, runlist *runlist, u8 *al_start,
-		const s64 size, const s64 initialized_size)
-{
-	LCN lcn;
-	u8 *al = al_start;
-	u8 *al_end = al + initialized_size;
-	runlist_element *rl;
-	struct buffer_head *bh;
-	struct super_block *sb;
-	unsigned long block_size;
-	unsigned long block, max_block;
-	int err = 0;
-	unsigned char block_size_bits;
-
-	ntfs_debug("Entering.");
-	if (!vol || !runlist || !al || size <= 0 || initialized_size < 0 ||
-			initialized_size > size)
-		return -EINVAL;
-	if (!initialized_size) {
-		memset(al, 0, size);
-		return 0;
-	}
-	sb = vol->sb;
-	block_size = sb->s_blocksize;
-	block_size_bits = sb->s_blocksize_bits;
-	down_read(&runlist->lock);
-	rl = runlist->rl;
-	if (!rl) {
-		ntfs_error(sb, "Cannot read attribute list since runlist is "
-				"missing.");
-		goto err_out;	
-	}
-	/* Read all clusters specified by the runlist one run at a time. */
-	while (rl->length) {
-		lcn = ntfs_rl_vcn_to_lcn(rl, rl->vcn);
-		ntfs_debug("Reading vcn = 0x%llx, lcn = 0x%llx.",
-				(unsigned long long)rl->vcn,
-				(unsigned long long)lcn);
-		/* The attribute list cannot be sparse. */
-		if (lcn < 0) {
-			ntfs_error(sb, "ntfs_rl_vcn_to_lcn() failed.  Cannot "
-					"read attribute list.");
-			goto err_out;
-		}
-		block = lcn << vol->cluster_size_bits >> block_size_bits;
-		/* Read the run from device in chunks of block_size bytes. */
-		max_block = block + (rl->length << vol->cluster_size_bits >>
-				block_size_bits);
-		ntfs_debug("max_block = 0x%lx.", max_block);
-		do {
-			ntfs_debug("Reading block = 0x%lx.", block);
-			bh = sb_bread(sb, block);
-			if (!bh) {
-				ntfs_error(sb, "sb_bread() failed. Cannot "
-						"read attribute list.");
-				goto err_out;
-			}
-			if (al + block_size >= al_end)
-				goto do_final;
-			memcpy(al, bh->b_data, block_size);
-			brelse(bh);
-			al += block_size;
-		} while (++block < max_block);
-		rl++;
-	}
-	if (initialized_size < size) {
-initialize:
-		memset(al_start + initialized_size, 0, size - initialized_size);
-	}
-done:
-	up_read(&runlist->lock);
-	return err;
-do_final:
-	if (al < al_end) {
-		/*
-		 * Partial block.
-		 *
-		 * Note: The attribute list can be smaller than its allocation
-		 * by multiple clusters.  This has been encountered by at least
-		 * two people running Windows XP, thus we cannot do any
-		 * truncation sanity checking here. (AIA)
-		 */
-		memcpy(al, bh->b_data, al_end - al);
-		brelse(bh);
-		if (initialized_size < size)
-			goto initialize;
-		goto done;
-	}
-	brelse(bh);
-	/* Real overflow! */
-	ntfs_error(sb, "Attribute list buffer overflow. Read attribute list "
-			"is truncated.");
-err_out:
-	err = -EIO;
-	goto done;
-}
-
-/**
- * ntfs_external_attr_find - find an attribute in the attribute list of an inode
- * @type:	attribute type to find
- * @name:	attribute name to find (optional, i.e. NULL means don't care)
- * @name_len:	attribute name length (only needed if @name present)
- * @ic:		IGNORE_CASE or CASE_SENSITIVE (ignored if @name not present)
- * @lowest_vcn:	lowest vcn to find (optional, non-resident attributes only)
- * @val:	attribute value to find (optional, resident attributes only)
- * @val_len:	attribute value length
- * @ctx:	search context with mft record and attribute to search from
- *
- * You should not need to call this function directly.  Use ntfs_attr_lookup()
- * instead.
- *
- * Find an attribute by searching the attribute list for the corresponding
- * attribute list entry.  Having found the entry, map the mft record if the
- * attribute is in a different mft record/inode, ntfs_attr_find() the attribute
- * in there and return it.
- *
- * On first search @ctx->ntfs_ino must be the base mft record and @ctx must
- * have been obtained from a call to ntfs_attr_get_search_ctx().  On subsequent
- * calls @ctx->ntfs_ino can be any extent inode, too (@ctx->base_ntfs_ino is
- * then the base inode).
- *
- * After finishing with the attribute/mft record you need to call
- * ntfs_attr_put_search_ctx() to cleanup the search context (unmapping any
- * mapped inodes, etc).
- *
- * If the attribute is found, ntfs_external_attr_find() returns 0 and
- * @ctx->attr will point to the found attribute.  @ctx->mrec will point to the
- * mft record in which @ctx->attr is located and @ctx->al_entry will point to
- * the attribute list entry for the attribute.
- *
- * If the attribute is not found, ntfs_external_attr_find() returns -ENOENT and
- * @ctx->attr will point to the attribute in the base mft record before which
- * the attribute being searched for would need to be inserted if such an action
- * were to be desired.  @ctx->mrec will point to the mft record in which
- * @ctx->attr is located and @ctx->al_entry will point to the attribute list
- * entry of the attribute before which the attribute being searched for would
- * need to be inserted if such an action were to be desired.
- *
- * Thus to insert the not found attribute, one wants to add the attribute to
- * @ctx->mrec (the base mft record) and if there is not enough space, the
- * attribute should be placed in a newly allocated extent mft record.  The
- * attribute list entry for the inserted attribute should be inserted in the
- * attribute list attribute at @ctx->al_entry.
- *
- * On actual error, ntfs_external_attr_find() returns -EIO.  In this case
- * @ctx->attr is undefined and in particular do not rely on it not changing.
- */
-static int ntfs_external_attr_find(const ATTR_TYPE type,
-		const ntfschar *name, const u32 name_len,
-		const IGNORE_CASE_BOOL ic, const VCN lowest_vcn,
-		const u8 *val, const u32 val_len, ntfs_attr_search_ctx *ctx)
-{
-	ntfs_inode *base_ni, *ni;
-	ntfs_volume *vol;
-	ATTR_LIST_ENTRY *al_entry, *next_al_entry;
-	u8 *al_start, *al_end;
-	ATTR_RECORD *a;
-	ntfschar *al_name;
-	u32 al_name_len;
-	int err = 0;
-	static const char *es = " Unmount and run chkdsk.";
-
-	ni = ctx->ntfs_ino;
-	base_ni = ctx->base_ntfs_ino;
-	ntfs_debug("Entering for inode 0x%lx, type 0x%x.", ni->mft_no, type);
-	if (!base_ni) {
-		/* First call happens with the base mft record. */
-		base_ni = ctx->base_ntfs_ino = ctx->ntfs_ino;
-		ctx->base_mrec = ctx->mrec;
-	}
-	if (ni == base_ni)
-		ctx->base_attr = ctx->attr;
-	if (type == AT_END)
-		goto not_found;
-	vol = base_ni->vol;
-	al_start = base_ni->attr_list;
-	al_end = al_start + base_ni->attr_list_size;
-	if (!ctx->al_entry)
-		ctx->al_entry = (ATTR_LIST_ENTRY*)al_start;
-	/*
-	 * Iterate over entries in attribute list starting at @ctx->al_entry,
-	 * or the entry following that, if @ctx->is_first is 'true'.
-	 */
-	if (ctx->is_first) {
-		al_entry = ctx->al_entry;
-		ctx->is_first = false;
-	} else
-		al_entry = (ATTR_LIST_ENTRY*)((u8*)ctx->al_entry +
-				le16_to_cpu(ctx->al_entry->length));
-	for (;; al_entry = next_al_entry) {
-		/* Out of bounds check. */
-		if ((u8*)al_entry < base_ni->attr_list ||
-				(u8*)al_entry > al_end)
-			break;	/* Inode is corrupt. */
-		ctx->al_entry = al_entry;
-		/* Catch the end of the attribute list. */
-		if ((u8*)al_entry == al_end)
-			goto not_found;
-		if (!al_entry->length)
-			break;
-		if ((u8*)al_entry + 6 > al_end || (u8*)al_entry +
-				le16_to_cpu(al_entry->length) > al_end)
-			break;
-		next_al_entry = (ATTR_LIST_ENTRY*)((u8*)al_entry +
-				le16_to_cpu(al_entry->length));
-		if (le32_to_cpu(al_entry->type) > le32_to_cpu(type))
-			goto not_found;
-		if (type != al_entry->type)
-			continue;
-		/*
-		 * If @name is present, compare the two names.  If @name is
-		 * missing, assume we want an unnamed attribute.
-		 */
-		al_name_len = al_entry->name_length;
-		al_name = (ntfschar*)((u8*)al_entry + al_entry->name_offset);
-		if (!name) {
-			if (al_name_len)
-				goto not_found;
-		} else if (!ntfs_are_names_equal(al_name, al_name_len, name,
-				name_len, ic, vol->upcase, vol->upcase_len)) {
-			register int rc;
-
-			rc = ntfs_collate_names(name, name_len, al_name,
-					al_name_len, 1, IGNORE_CASE,
-					vol->upcase, vol->upcase_len);
-			/*
-			 * If @name collates before al_name, there is no
-			 * matching attribute.
-			 */
-			if (rc == -1)
-				goto not_found;
-			/* If the strings are not equal, continue search. */
-			if (rc)
-				continue;
-			/*
-			 * FIXME: Reverse engineering showed 0, IGNORE_CASE but
-			 * that is inconsistent with ntfs_attr_find().  The
-			 * subsequent rc checks were also different.  Perhaps I
-			 * made a mistake in one of the two.  Need to recheck
-			 * which is correct or at least see what is going on...
-			 * (AIA)
-			 */
-			rc = ntfs_collate_names(name, name_len, al_name,
-					al_name_len, 1, CASE_SENSITIVE,
-					vol->upcase, vol->upcase_len);
-			if (rc == -1)
-				goto not_found;
-			if (rc)
-				continue;
-		}
-		/*
-		 * The names match or @name not present and attribute is
-		 * unnamed.  Now check @lowest_vcn.  Continue search if the
-		 * next attribute list entry still fits @lowest_vcn.  Otherwise
-		 * we have reached the right one or the search has failed.
-		 */
-		if (lowest_vcn && (u8*)next_al_entry >= al_start	    &&
-				(u8*)next_al_entry + 6 < al_end		    &&
-				(u8*)next_al_entry + le16_to_cpu(
-					next_al_entry->length) <= al_end    &&
-				sle64_to_cpu(next_al_entry->lowest_vcn) <=
-					lowest_vcn			    &&
-				next_al_entry->type == al_entry->type	    &&
-				next_al_entry->name_length == al_name_len   &&
-				ntfs_are_names_equal((ntfschar*)((u8*)
-					next_al_entry +
-					next_al_entry->name_offset),
-					next_al_entry->name_length,
-					al_name, al_name_len, CASE_SENSITIVE,
-					vol->upcase, vol->upcase_len))
-			continue;
-		if (MREF_LE(al_entry->mft_reference) == ni->mft_no) {
-			if (MSEQNO_LE(al_entry->mft_reference) != ni->seq_no) {
-				ntfs_error(vol->sb, "Found stale mft "
-						"reference in attribute list "
-						"of base inode 0x%lx.%s",
-						base_ni->mft_no, es);
-				err = -EIO;
-				break;
-			}
-		} else { /* Mft references do not match. */
-			/* If there is a mapped record unmap it first. */
-			if (ni != base_ni)
-				unmap_extent_mft_record(ni);
-			/* Do we want the base record back? */
-			if (MREF_LE(al_entry->mft_reference) ==
-					base_ni->mft_no) {
-				ni = ctx->ntfs_ino = base_ni;
-				ctx->mrec = ctx->base_mrec;
-			} else {
-				/* We want an extent record. */
-				ctx->mrec = map_extent_mft_record(base_ni,
-						le64_to_cpu(
-						al_entry->mft_reference), &ni);
-				if (IS_ERR(ctx->mrec)) {
-					ntfs_error(vol->sb, "Failed to map "
-							"extent mft record "
-							"0x%lx of base inode "
-							"0x%lx.%s",
-							MREF_LE(al_entry->
-							mft_reference),
-							base_ni->mft_no, es);
-					err = PTR_ERR(ctx->mrec);
-					if (err == -ENOENT)
-						err = -EIO;
-					/* Cause @ctx to be sanitized below. */
-					ni = NULL;
-					break;
-				}
-				ctx->ntfs_ino = ni;
-			}
-			ctx->attr = (ATTR_RECORD*)((u8*)ctx->mrec +
-					le16_to_cpu(ctx->mrec->attrs_offset));
-		}
-		/*
-		 * ctx->vfs_ino, ctx->mrec, and ctx->attr now point to the
-		 * mft record containing the attribute represented by the
-		 * current al_entry.
-		 */
-		/*
-		 * We could call into ntfs_attr_find() to find the right
-		 * attribute in this mft record but this would be less
-		 * efficient and not quite accurate as ntfs_attr_find() ignores
-		 * the attribute instance numbers for example which become
-		 * important when one plays with attribute lists.  Also,
-		 * because a proper match has been found in the attribute list
-		 * entry above, the comparison can now be optimized.  So it is
-		 * worth re-implementing a simplified ntfs_attr_find() here.
-		 */
-		a = ctx->attr;
-		/*
-		 * Use a manual loop so we can still use break and continue
-		 * with the same meanings as above.
-		 */
-do_next_attr_loop:
-		if ((u8*)a < (u8*)ctx->mrec || (u8*)a > (u8*)ctx->mrec +
-				le32_to_cpu(ctx->mrec->bytes_allocated))
-			break;
-		if (a->type == AT_END)
-			break;
-		if (!a->length)
-			break;
-		if (al_entry->instance != a->instance)
-			goto do_next_attr;
-		/*
-		 * If the type and/or the name are mismatched between the
-		 * attribute list entry and the attribute record, there is
-		 * corruption so we break and return error EIO.
-		 */
-		if (al_entry->type != a->type)
-			break;
-		if (!ntfs_are_names_equal((ntfschar*)((u8*)a +
-				le16_to_cpu(a->name_offset)), a->name_length,
-				al_name, al_name_len, CASE_SENSITIVE,
-				vol->upcase, vol->upcase_len))
-			break;
-		ctx->attr = a;
-		/*
-		 * If no @val specified or @val specified and it matches, we
-		 * have found it!
-		 */
-		if (!val || (!a->non_resident && le32_to_cpu(
-				a->data.resident.value_length) == val_len &&
-				!memcmp((u8*)a +
-				le16_to_cpu(a->data.resident.value_offset),
-				val, val_len))) {
-			ntfs_debug("Done, found.");
-			return 0;
-		}
-do_next_attr:
-		/* Proceed to the next attribute in the current mft record. */
-		a = (ATTR_RECORD*)((u8*)a + le32_to_cpu(a->length));
-		goto do_next_attr_loop;
-	}
-	if (!err) {
-		ntfs_error(vol->sb, "Base inode 0x%lx contains corrupt "
-				"attribute list attribute.%s", base_ni->mft_no,
-				es);
-		err = -EIO;
-	}
-	if (ni != base_ni) {
-		if (ni)
-			unmap_extent_mft_record(ni);
-		ctx->ntfs_ino = base_ni;
-		ctx->mrec = ctx->base_mrec;
-		ctx->attr = ctx->base_attr;
-	}
-	if (err != -ENOMEM)
-		NVolSetErrors(vol);
-	return err;
-not_found:
-	/*
-	 * If we were looking for AT_END, we reset the search context @ctx and
-	 * use ntfs_attr_find() to seek to the end of the base mft record.
-	 */
-	if (type == AT_END) {
-		ntfs_attr_reinit_search_ctx(ctx);
-		return ntfs_attr_find(AT_END, name, name_len, ic, val, val_len,
-				ctx);
-	}
-	/*
-	 * The attribute was not found.  Before we return, we want to ensure
-	 * @ctx->mrec and @ctx->attr indicate the position at which the
-	 * attribute should be inserted in the base mft record.  Since we also
-	 * want to preserve @ctx->al_entry we cannot reinitialize the search
-	 * context using ntfs_attr_reinit_search_ctx() as this would set
-	 * @ctx->al_entry to NULL.  Thus we do the necessary bits manually (see
-	 * ntfs_attr_init_search_ctx() below).  Note, we _only_ preserve
-	 * @ctx->al_entry as the remaining fields (base_*) are identical to
-	 * their non base_ counterparts and we cannot set @ctx->base_attr
-	 * correctly yet as we do not know what @ctx->attr will be set to by
-	 * the call to ntfs_attr_find() below.
-	 */
-	if (ni != base_ni)
-		unmap_extent_mft_record(ni);
-	ctx->mrec = ctx->base_mrec;
-	ctx->attr = (ATTR_RECORD*)((u8*)ctx->mrec +
-			le16_to_cpu(ctx->mrec->attrs_offset));
-	ctx->is_first = true;
-	ctx->ntfs_ino = base_ni;
-	ctx->base_ntfs_ino = NULL;
-	ctx->base_mrec = NULL;
-	ctx->base_attr = NULL;
-	/*
-	 * In case there are multiple matches in the base mft record, need to
-	 * keep enumerating until we get an attribute not found response (or
-	 * another error), otherwise we would keep returning the same attribute
-	 * over and over again and all programs using us for enumeration would
-	 * lock up in a tight loop.
-	 */
-	do {
-		err = ntfs_attr_find(type, name, name_len, ic, val, val_len,
-				ctx);
-	} while (!err);
-	ntfs_debug("Done, not found.");
-	return err;
-}
-
-/**
- * ntfs_attr_lookup - find an attribute in an ntfs inode
- * @type:	attribute type to find
- * @name:	attribute name to find (optional, i.e. NULL means don't care)
- * @name_len:	attribute name length (only needed if @name present)
- * @ic:		IGNORE_CASE or CASE_SENSITIVE (ignored if @name not present)
- * @lowest_vcn:	lowest vcn to find (optional, non-resident attributes only)
- * @val:	attribute value to find (optional, resident attributes only)
- * @val_len:	attribute value length
- * @ctx:	search context with mft record and attribute to search from
- *
- * Find an attribute in an ntfs inode.  On first search @ctx->ntfs_ino must
- * be the base mft record and @ctx must have been obtained from a call to
- * ntfs_attr_get_search_ctx().
- *
- * This function transparently handles attribute lists and @ctx is used to
- * continue searches where they were left off at.
- *
- * After finishing with the attribute/mft record you need to call
- * ntfs_attr_put_search_ctx() to cleanup the search context (unmapping any
- * mapped inodes, etc).
- *
- * Return 0 if the search was successful and -errno if not.
- *
- * When 0, @ctx->attr is the found attribute and it is in mft record
- * @ctx->mrec.  If an attribute list attribute is present, @ctx->al_entry is
- * the attribute list entry of the found attribute.
- *
- * When -ENOENT, @ctx->attr is the attribute which collates just after the
- * attribute being searched for, i.e. if one wants to add the attribute to the
- * mft record this is the correct place to insert it into.  If an attribute
- * list attribute is present, @ctx->al_entry is the attribute list entry which
- * collates just after the attribute list entry of the attribute being searched
- * for, i.e. if one wants to add the attribute to the mft record this is the
- * correct place to insert its attribute list entry into.
- *
- * When -errno != -ENOENT, an error occurred during the lookup.  @ctx->attr is
- * then undefined and in particular you should not rely on it not changing.
- */
-int ntfs_attr_lookup(const ATTR_TYPE type, const ntfschar *name,
-		const u32 name_len, const IGNORE_CASE_BOOL ic,
-		const VCN lowest_vcn, const u8 *val, const u32 val_len,
-		ntfs_attr_search_ctx *ctx)
-{
-	ntfs_inode *base_ni;
-
-	ntfs_debug("Entering.");
-	BUG_ON(IS_ERR(ctx->mrec));
-	if (ctx->base_ntfs_ino)
-		base_ni = ctx->base_ntfs_ino;
-	else
-		base_ni = ctx->ntfs_ino;
-	/* Sanity check, just for debugging really. */
-	BUG_ON(!base_ni);
-	if (!NInoAttrList(base_ni) || type == AT_ATTRIBUTE_LIST)
-		return ntfs_attr_find(type, name, name_len, ic, val, val_len,
-				ctx);
-	return ntfs_external_attr_find(type, name, name_len, ic, lowest_vcn,
-			val, val_len, ctx);
-}
-
-/**
- * ntfs_attr_init_search_ctx - initialize an attribute search context
- * @ctx:	attribute search context to initialize
- * @ni:		ntfs inode with which to initialize the search context
- * @mrec:	mft record with which to initialize the search context
- *
- * Initialize the attribute search context @ctx with @ni and @mrec.
- */
-static inline void ntfs_attr_init_search_ctx(ntfs_attr_search_ctx *ctx,
-		ntfs_inode *ni, MFT_RECORD *mrec)
-{
-	*ctx = (ntfs_attr_search_ctx) {
-		.mrec = mrec,
-		/* Sanity checks are performed elsewhere. */
-		.attr = (ATTR_RECORD*)((u8*)mrec +
-				le16_to_cpu(mrec->attrs_offset)),
-		.is_first = true,
-		.ntfs_ino = ni,
-	};
-}
-
-/**
- * ntfs_attr_reinit_search_ctx - reinitialize an attribute search context
- * @ctx:	attribute search context to reinitialize
- *
- * Reinitialize the attribute search context @ctx, unmapping an associated
- * extent mft record if present, and initialize the search context again.
- *
- * This is used when a search for a new attribute is being started to reset
- * the search context to the beginning.
- */
-void ntfs_attr_reinit_search_ctx(ntfs_attr_search_ctx *ctx)
-{
-	if (likely(!ctx->base_ntfs_ino)) {
-		/* No attribute list. */
-		ctx->is_first = true;
-		/* Sanity checks are performed elsewhere. */
-		ctx->attr = (ATTR_RECORD*)((u8*)ctx->mrec +
-				le16_to_cpu(ctx->mrec->attrs_offset));
-		/*
-		 * This needs resetting due to ntfs_external_attr_find() which
-		 * can leave it set despite having zeroed ctx->base_ntfs_ino.
-		 */
-		ctx->al_entry = NULL;
-		return;
-	} /* Attribute list. */
-	if (ctx->ntfs_ino != ctx->base_ntfs_ino)
-		unmap_extent_mft_record(ctx->ntfs_ino);
-	ntfs_attr_init_search_ctx(ctx, ctx->base_ntfs_ino, ctx->base_mrec);
-	return;
-}
-
-/**
- * ntfs_attr_get_search_ctx - allocate/initialize a new attribute search context
- * @ni:		ntfs inode with which to initialize the search context
- * @mrec:	mft record with which to initialize the search context
- *
- * Allocate a new attribute search context, initialize it with @ni and @mrec,
- * and return it. Return NULL if allocation failed.
- */
-ntfs_attr_search_ctx *ntfs_attr_get_search_ctx(ntfs_inode *ni, MFT_RECORD *mrec)
-{
-	ntfs_attr_search_ctx *ctx;
-
-	ctx = kmem_cache_alloc(ntfs_attr_ctx_cache, GFP_NOFS);
-	if (ctx)
-		ntfs_attr_init_search_ctx(ctx, ni, mrec);
-	return ctx;
-}
-
-/**
- * ntfs_attr_put_search_ctx - release an attribute search context
- * @ctx:	attribute search context to free
- *
- * Release the attribute search context @ctx, unmapping an associated extent
- * mft record if present.
- */
-void ntfs_attr_put_search_ctx(ntfs_attr_search_ctx *ctx)
-{
-	if (ctx->base_ntfs_ino && ctx->ntfs_ino != ctx->base_ntfs_ino)
-		unmap_extent_mft_record(ctx->ntfs_ino);
-	kmem_cache_free(ntfs_attr_ctx_cache, ctx);
-	return;
-}
-
-#ifdef NTFS_RW
-
-/**
- * ntfs_attr_find_in_attrdef - find an attribute in the $AttrDef system file
- * @vol:	ntfs volume to which the attribute belongs
- * @type:	attribute type which to find
- *
- * Search for the attribute definition record corresponding to the attribute
- * @type in the $AttrDef system file.
- *
- * Return the attribute type definition record if found and NULL if not found.
- */
-static ATTR_DEF *ntfs_attr_find_in_attrdef(const ntfs_volume *vol,
-		const ATTR_TYPE type)
-{
-	ATTR_DEF *ad;
-
-	BUG_ON(!vol->attrdef);
-	BUG_ON(!type);
-	for (ad = vol->attrdef; (u8*)ad - (u8*)vol->attrdef <
-			vol->attrdef_size && ad->type; ++ad) {
-		/* We have not found it yet, carry on searching. */
-		if (likely(le32_to_cpu(ad->type) < le32_to_cpu(type)))
-			continue;
-		/* We found the attribute; return it. */
-		if (likely(ad->type == type))
-			return ad;
-		/* We have gone too far already.  No point in continuing. */
-		break;
-	}
-	/* Attribute not found. */
-	ntfs_debug("Attribute type 0x%x not found in $AttrDef.",
-			le32_to_cpu(type));
-	return NULL;
-}
-
-/**
- * ntfs_attr_size_bounds_check - check a size of an attribute type for validity
- * @vol:	ntfs volume to which the attribute belongs
- * @type:	attribute type which to check
- * @size:	size which to check
- *
- * Check whether the @size in bytes is valid for an attribute of @type on the
- * ntfs volume @vol.  This information is obtained from $AttrDef system file.
- *
- * Return 0 if valid, -ERANGE if not valid, or -ENOENT if the attribute is not
- * listed in $AttrDef.
- */
-int ntfs_attr_size_bounds_check(const ntfs_volume *vol, const ATTR_TYPE type,
-		const s64 size)
-{
-	ATTR_DEF *ad;
-
-	BUG_ON(size < 0);
-	/*
-	 * $ATTRIBUTE_LIST has a maximum size of 256kiB, but this is not
-	 * listed in $AttrDef.
-	 */
-	if (unlikely(type == AT_ATTRIBUTE_LIST && size > 256 * 1024))
-		return -ERANGE;
-	/* Get the $AttrDef entry for the attribute @type. */
-	ad = ntfs_attr_find_in_attrdef(vol, type);
-	if (unlikely(!ad))
-		return -ENOENT;
-	/* Do the bounds check. */
-	if (((sle64_to_cpu(ad->min_size) > 0) &&
-			size < sle64_to_cpu(ad->min_size)) ||
-			((sle64_to_cpu(ad->max_size) > 0) && size >
-			sle64_to_cpu(ad->max_size)))
-		return -ERANGE;
-	return 0;
-}
-
-/**
- * ntfs_attr_can_be_non_resident - check if an attribute can be non-resident
- * @vol:	ntfs volume to which the attribute belongs
- * @type:	attribute type which to check
- *
- * Check whether the attribute of @type on the ntfs volume @vol is allowed to
- * be non-resident.  This information is obtained from $AttrDef system file.
- *
- * Return 0 if the attribute is allowed to be non-resident, -EPERM if not, and
- * -ENOENT if the attribute is not listed in $AttrDef.
- */
-int ntfs_attr_can_be_non_resident(const ntfs_volume *vol, const ATTR_TYPE type)
-{
-	ATTR_DEF *ad;
-
-	/* Find the attribute definition record in $AttrDef. */
-	ad = ntfs_attr_find_in_attrdef(vol, type);
-	if (unlikely(!ad))
-		return -ENOENT;
-	/* Check the flags and return the result. */
-	if (ad->flags & ATTR_DEF_RESIDENT)
-		return -EPERM;
-	return 0;
-}
-
-/**
- * ntfs_attr_can_be_resident - check if an attribute can be resident
- * @vol:	ntfs volume to which the attribute belongs
- * @type:	attribute type which to check
- *
- * Check whether the attribute of @type on the ntfs volume @vol is allowed to
- * be resident.  This information is derived from our ntfs knowledge and may
- * not be completely accurate, especially when user defined attributes are
- * present.  Basically we allow everything to be resident except for index
- * allocation and $EA attributes.
- *
- * Return 0 if the attribute is allowed to be non-resident and -EPERM if not.
- *
- * Warning: In the system file $MFT the attribute $Bitmap must be non-resident
- *	    otherwise windows will not boot (blue screen of death)!  We cannot
- *	    check for this here as we do not know which inode's $Bitmap is
- *	    being asked about so the caller needs to special case this.
- */
-int ntfs_attr_can_be_resident(const ntfs_volume *vol, const ATTR_TYPE type)
-{
-	if (type == AT_INDEX_ALLOCATION)
-		return -EPERM;
-	return 0;
-}
-
-/**
- * ntfs_attr_record_resize - resize an attribute record
- * @m:		mft record containing attribute record
- * @a:		attribute record to resize
- * @new_size:	new size in bytes to which to resize the attribute record @a
- *
- * Resize the attribute record @a, i.e. the resident part of the attribute, in
- * the mft record @m to @new_size bytes.
- *
- * Return 0 on success and -errno on error.  The following error codes are
- * defined:
- *	-ENOSPC	- Not enough space in the mft record @m to perform the resize.
- *
- * Note: On error, no modifications have been performed whatsoever.
- *
- * Warning: If you make a record smaller without having copied all the data you
- *	    are interested in the data may be overwritten.
- */
-int ntfs_attr_record_resize(MFT_RECORD *m, ATTR_RECORD *a, u32 new_size)
-{
-	ntfs_debug("Entering for new_size %u.", new_size);
-	/* Align to 8 bytes if it is not already done. */
-	if (new_size & 7)
-		new_size = (new_size + 7) & ~7;
-	/* If the actual attribute length has changed, move things around. */
-	if (new_size != le32_to_cpu(a->length)) {
-		u32 new_muse = le32_to_cpu(m->bytes_in_use) -
-				le32_to_cpu(a->length) + new_size;
-		/* Not enough space in this mft record. */
-		if (new_muse > le32_to_cpu(m->bytes_allocated))
-			return -ENOSPC;
-		/* Move attributes following @a to their new location. */
-		memmove((u8*)a + new_size, (u8*)a + le32_to_cpu(a->length),
-				le32_to_cpu(m->bytes_in_use) - ((u8*)a -
-				(u8*)m) - le32_to_cpu(a->length));
-		/* Adjust @m to reflect the change in used space. */
-		m->bytes_in_use = cpu_to_le32(new_muse);
-		/* Adjust @a to reflect the new size. */
-		if (new_size >= offsetof(ATTR_REC, length) + sizeof(a->length))
-			a->length = cpu_to_le32(new_size);
-	}
-	return 0;
-}
-
-/**
- * ntfs_resident_attr_value_resize - resize the value of a resident attribute
- * @m:		mft record containing attribute record
- * @a:		attribute record whose value to resize
- * @new_size:	new size in bytes to which to resize the attribute value of @a
- *
- * Resize the value of the attribute @a in the mft record @m to @new_size bytes.
- * If the value is made bigger, the newly allocated space is cleared.
- *
- * Return 0 on success and -errno on error.  The following error codes are
- * defined:
- *	-ENOSPC	- Not enough space in the mft record @m to perform the resize.
- *
- * Note: On error, no modifications have been performed whatsoever.
- *
- * Warning: If you make a record smaller without having copied all the data you
- *	    are interested in the data may be overwritten.
- */
-int ntfs_resident_attr_value_resize(MFT_RECORD *m, ATTR_RECORD *a,
-		const u32 new_size)
-{
-	u32 old_size;
-
-	/* Resize the resident part of the attribute record. */
-	if (ntfs_attr_record_resize(m, a,
-			le16_to_cpu(a->data.resident.value_offset) + new_size))
-		return -ENOSPC;
-	/*
-	 * The resize succeeded!  If we made the attribute value bigger, clear
-	 * the area between the old size and @new_size.
-	 */
-	old_size = le32_to_cpu(a->data.resident.value_length);
-	if (new_size > old_size)
-		memset((u8*)a + le16_to_cpu(a->data.resident.value_offset) +
-				old_size, 0, new_size - old_size);
-	/* Finally update the length of the attribute value. */
-	a->data.resident.value_length = cpu_to_le32(new_size);
-	return 0;
-}
-
-/**
- * ntfs_attr_make_non_resident - convert a resident to a non-resident attribute
- * @ni:		ntfs inode describing the attribute to convert
- * @data_size:	size of the resident data to copy to the non-resident attribute
- *
- * Convert the resident ntfs attribute described by the ntfs inode @ni to a
- * non-resident one.
- *
- * @data_size must be equal to the attribute value size.  This is needed since
- * we need to know the size before we can map the mft record and our callers
- * always know it.  The reason we cannot simply read the size from the vfs
- * inode i_size is that this is not necessarily uptodate.  This happens when
- * ntfs_attr_make_non_resident() is called in the ->truncate call path(s).
- *
- * Return 0 on success and -errno on error.  The following error return codes
- * are defined:
- *	-EPERM	- The attribute is not allowed to be non-resident.
- *	-ENOMEM	- Not enough memory.
- *	-ENOSPC	- Not enough disk space.
- *	-EINVAL	- Attribute not defined on the volume.
- *	-EIO	- I/o error or other error.
- * Note that -ENOSPC is also returned in the case that there is not enough
- * space in the mft record to do the conversion.  This can happen when the mft
- * record is already very full.  The caller is responsible for trying to make
- * space in the mft record and trying again.  FIXME: Do we need a separate
- * error return code for this kind of -ENOSPC or is it always worth trying
- * again in case the attribute may then fit in a resident state so no need to
- * make it non-resident at all?  Ho-hum...  (AIA)
- *
- * NOTE to self: No changes in the attribute list are required to move from
- *		 a resident to a non-resident attribute.
- *
- * Locking: - The caller must hold i_mutex on the inode.
- */
-int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size)
-{
-	s64 new_size;
-	struct inode *vi = VFS_I(ni);
-	ntfs_volume *vol = ni->vol;
-	ntfs_inode *base_ni;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
-	ntfs_attr_search_ctx *ctx;
-	struct page *page;
-	runlist_element *rl;
-	u8 *kaddr;
-	unsigned long flags;
-	int mp_size, mp_ofs, name_ofs, arec_size, err, err2;
-	u32 attr_size;
-	u8 old_res_attr_flags;
-
-	/* Check that the attribute is allowed to be non-resident. */
-	err = ntfs_attr_can_be_non_resident(vol, ni->type);
-	if (unlikely(err)) {
-		if (err == -EPERM)
-			ntfs_debug("Attribute is not allowed to be "
-					"non-resident.");
-		else
-			ntfs_debug("Attribute not defined on the NTFS "
-					"volume!");
-		return err;
-	}
-	/*
-	 * FIXME: Compressed and encrypted attributes are not supported when
-	 * writing and we should never have gotten here for them.
-	 */
-	BUG_ON(NInoCompressed(ni));
-	BUG_ON(NInoEncrypted(ni));
-	/*
-	 * The size needs to be aligned to a cluster boundary for allocation
-	 * purposes.
-	 */
-	new_size = (data_size + vol->cluster_size - 1) &
-			~(vol->cluster_size - 1);
-	if (new_size > 0) {
-		/*
-		 * Will need the page later and since the page lock nests
-		 * outside all ntfs locks, we need to get the page now.
-		 */
-		page = find_or_create_page(vi->i_mapping, 0,
-				mapping_gfp_mask(vi->i_mapping));
-		if (unlikely(!page))
-			return -ENOMEM;
-		/* Start by allocating clusters to hold the attribute value. */
-		rl = ntfs_cluster_alloc(vol, 0, new_size >>
-				vol->cluster_size_bits, -1, DATA_ZONE, true);
-		if (IS_ERR(rl)) {
-			err = PTR_ERR(rl);
-			ntfs_debug("Failed to allocate cluster%s, error code "
-					"%i.", (new_size >>
-					vol->cluster_size_bits) > 1 ? "s" : "",
-					err);
-			goto page_err_out;
-		}
-	} else {
-		rl = NULL;
-		page = NULL;
-	}
-	/* Determine the size of the mapping pairs array. */
-	mp_size = ntfs_get_size_for_mapping_pairs(vol, rl, 0, -1);
-	if (unlikely(mp_size < 0)) {
-		err = mp_size;
-		ntfs_debug("Failed to get size for mapping pairs array, error "
-				"code %i.", err);
-		goto rl_err_out;
-	}
-	down_write(&ni->runlist.lock);
-	if (!NInoAttr(ni))
-		base_ni = ni;
-	else
-		base_ni = ni->ext.base_ntfs_ino;
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		m = NULL;
-		ctx = NULL;
-		goto err_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT)
-			err = -EIO;
-		goto err_out;
-	}
-	m = ctx->mrec;
-	a = ctx->attr;
-	BUG_ON(NInoNonResident(ni));
-	BUG_ON(a->non_resident);
-	/*
-	 * Calculate new offsets for the name and the mapping pairs array.
-	 */
-	if (NInoSparse(ni) || NInoCompressed(ni))
-		name_ofs = (offsetof(ATTR_REC,
-				data.non_resident.compressed_size) +
-				sizeof(a->data.non_resident.compressed_size) +
-				7) & ~7;
-	else
-		name_ofs = (offsetof(ATTR_REC,
-				data.non_resident.compressed_size) + 7) & ~7;
-	mp_ofs = (name_ofs + a->name_length * sizeof(ntfschar) + 7) & ~7;
-	/*
-	 * Determine the size of the resident part of the now non-resident
-	 * attribute record.
-	 */
-	arec_size = (mp_ofs + mp_size + 7) & ~7;
-	/*
-	 * If the page is not uptodate bring it uptodate by copying from the
-	 * attribute value.
-	 */
-	attr_size = le32_to_cpu(a->data.resident.value_length);
-	BUG_ON(attr_size != data_size);
-	if (page && !PageUptodate(page)) {
-		kaddr = kmap_atomic(page);
-		memcpy(kaddr, (u8*)a +
-				le16_to_cpu(a->data.resident.value_offset),
-				attr_size);
-		memset(kaddr + attr_size, 0, PAGE_SIZE - attr_size);
-		kunmap_atomic(kaddr);
-		flush_dcache_page(page);
-		SetPageUptodate(page);
-	}
-	/* Backup the attribute flag. */
-	old_res_attr_flags = a->data.resident.flags;
-	/* Resize the resident part of the attribute record. */
-	err = ntfs_attr_record_resize(m, a, arec_size);
-	if (unlikely(err))
-		goto err_out;
-	/*
-	 * Convert the resident part of the attribute record to describe a
-	 * non-resident attribute.
-	 */
-	a->non_resident = 1;
-	/* Move the attribute name if it exists and update the offset. */
-	if (a->name_length)
-		memmove((u8*)a + name_ofs, (u8*)a + le16_to_cpu(a->name_offset),
-				a->name_length * sizeof(ntfschar));
-	a->name_offset = cpu_to_le16(name_ofs);
-	/* Setup the fields specific to non-resident attributes. */
-	a->data.non_resident.lowest_vcn = 0;
-	a->data.non_resident.highest_vcn = cpu_to_sle64((new_size - 1) >>
-			vol->cluster_size_bits);
-	a->data.non_resident.mapping_pairs_offset = cpu_to_le16(mp_ofs);
-	memset(&a->data.non_resident.reserved, 0,
-			sizeof(a->data.non_resident.reserved));
-	a->data.non_resident.allocated_size = cpu_to_sle64(new_size);
-	a->data.non_resident.data_size =
-			a->data.non_resident.initialized_size =
-			cpu_to_sle64(attr_size);
-	if (NInoSparse(ni) || NInoCompressed(ni)) {
-		a->data.non_resident.compression_unit = 0;
-		if (NInoCompressed(ni) || vol->major_ver < 3)
-			a->data.non_resident.compression_unit = 4;
-		a->data.non_resident.compressed_size =
-				a->data.non_resident.allocated_size;
-	} else
-		a->data.non_resident.compression_unit = 0;
-	/* Generate the mapping pairs array into the attribute record. */
-	err = ntfs_mapping_pairs_build(vol, (u8*)a + mp_ofs,
-			arec_size - mp_ofs, rl, 0, -1, NULL);
-	if (unlikely(err)) {
-		ntfs_debug("Failed to build mapping pairs, error code %i.",
-				err);
-		goto undo_err_out;
-	}
-	/* Setup the in-memory attribute structure to be non-resident. */
-	ni->runlist.rl = rl;
-	write_lock_irqsave(&ni->size_lock, flags);
-	ni->allocated_size = new_size;
-	if (NInoSparse(ni) || NInoCompressed(ni)) {
-		ni->itype.compressed.size = ni->allocated_size;
-		if (a->data.non_resident.compression_unit) {
-			ni->itype.compressed.block_size = 1U << (a->data.
-					non_resident.compression_unit +
-					vol->cluster_size_bits);
-			ni->itype.compressed.block_size_bits =
-					ffs(ni->itype.compressed.block_size) -
-					1;
-			ni->itype.compressed.block_clusters = 1U <<
-					a->data.non_resident.compression_unit;
-		} else {
-			ni->itype.compressed.block_size = 0;
-			ni->itype.compressed.block_size_bits = 0;
-			ni->itype.compressed.block_clusters = 0;
-		}
-		vi->i_blocks = ni->itype.compressed.size >> 9;
-	} else
-		vi->i_blocks = ni->allocated_size >> 9;
-	write_unlock_irqrestore(&ni->size_lock, flags);
-	/*
-	 * This needs to be last since the address space operations ->read_folio
-	 * and ->writepage can run concurrently with us as they are not
-	 * serialized on i_mutex.  Note, we are not allowed to fail once we flip
-	 * this switch, which is another reason to do this last.
-	 */
-	NInoSetNonResident(ni);
-	/* Mark the mft record dirty, so it gets written back. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-	up_write(&ni->runlist.lock);
-	if (page) {
-		set_page_dirty(page);
-		unlock_page(page);
-		put_page(page);
-	}
-	ntfs_debug("Done.");
-	return 0;
-undo_err_out:
-	/* Convert the attribute back into a resident attribute. */
-	a->non_resident = 0;
-	/* Move the attribute name if it exists and update the offset. */
-	name_ofs = (offsetof(ATTR_RECORD, data.resident.reserved) +
-			sizeof(a->data.resident.reserved) + 7) & ~7;
-	if (a->name_length)
-		memmove((u8*)a + name_ofs, (u8*)a + le16_to_cpu(a->name_offset),
-				a->name_length * sizeof(ntfschar));
-	mp_ofs = (name_ofs + a->name_length * sizeof(ntfschar) + 7) & ~7;
-	a->name_offset = cpu_to_le16(name_ofs);
-	arec_size = (mp_ofs + attr_size + 7) & ~7;
-	/* Resize the resident part of the attribute record. */
-	err2 = ntfs_attr_record_resize(m, a, arec_size);
-	if (unlikely(err2)) {
-		/*
-		 * This cannot happen (well if memory corruption is at work it
-		 * could happen in theory), but deal with it as well as we can.
-		 * If the old size is too small, truncate the attribute,
-		 * otherwise simply give it a larger allocated size.
-		 * FIXME: Should check whether chkdsk complains when the
-		 * allocated size is much bigger than the resident value size.
-		 */
-		arec_size = le32_to_cpu(a->length);
-		if ((mp_ofs + attr_size) > arec_size) {
-			err2 = attr_size;
-			attr_size = arec_size - mp_ofs;
-			ntfs_error(vol->sb, "Failed to undo partial resident "
-					"to non-resident attribute "
-					"conversion.  Truncating inode 0x%lx, "
-					"attribute type 0x%x from %i bytes to "
-					"%i bytes to maintain metadata "
-					"consistency.  THIS MEANS YOU ARE "
-					"LOSING %i BYTES DATA FROM THIS %s.",
-					vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type),
-					err2, attr_size, err2 - attr_size,
-					((ni->type == AT_DATA) &&
-					!ni->name_len) ? "FILE": "ATTRIBUTE");
-			write_lock_irqsave(&ni->size_lock, flags);
-			ni->initialized_size = attr_size;
-			i_size_write(vi, attr_size);
-			write_unlock_irqrestore(&ni->size_lock, flags);
-		}
-	}
-	/* Setup the fields specific to resident attributes. */
-	a->data.resident.value_length = cpu_to_le32(attr_size);
-	a->data.resident.value_offset = cpu_to_le16(mp_ofs);
-	a->data.resident.flags = old_res_attr_flags;
-	memset(&a->data.resident.reserved, 0,
-			sizeof(a->data.resident.reserved));
-	/* Copy the data from the page back to the attribute value. */
-	if (page) {
-		kaddr = kmap_atomic(page);
-		memcpy((u8*)a + mp_ofs, kaddr, attr_size);
-		kunmap_atomic(kaddr);
-	}
-	/* Setup the allocated size in the ntfs inode in case it changed. */
-	write_lock_irqsave(&ni->size_lock, flags);
-	ni->allocated_size = arec_size - mp_ofs;
-	write_unlock_irqrestore(&ni->size_lock, flags);
-	/* Mark the mft record dirty, so it gets written back. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-err_out:
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(base_ni);
-	ni->runlist.rl = NULL;
-	up_write(&ni->runlist.lock);
-rl_err_out:
-	if (rl) {
-		if (ntfs_cluster_free_from_rl(vol, rl) < 0) {
-			ntfs_error(vol->sb, "Failed to release allocated "
-					"cluster(s) in error code path.  Run "
-					"chkdsk to recover the lost "
-					"cluster(s).");
-			NVolSetErrors(vol);
-		}
-		ntfs_free(rl);
-page_err_out:
-		unlock_page(page);
-		put_page(page);
-	}
-	if (err == -EINVAL)
-		err = -EIO;
-	return err;
-}
-
-/**
- * ntfs_attr_extend_allocation - extend the allocated space of an attribute
- * @ni:			ntfs inode of the attribute whose allocation to extend
- * @new_alloc_size:	new size in bytes to which to extend the allocation to
- * @new_data_size:	new size in bytes to which to extend the data to
- * @data_start:		beginning of region which is required to be non-sparse
- *
- * Extend the allocated space of an attribute described by the ntfs inode @ni
- * to @new_alloc_size bytes.  If @data_start is -1, the whole extension may be
- * implemented as a hole in the file (as long as both the volume and the ntfs
- * inode @ni have sparse support enabled).  If @data_start is >= 0, then the
- * region between the old allocated size and @data_start - 1 may be made sparse
- * but the regions between @data_start and @new_alloc_size must be backed by
- * actual clusters.
- *
- * If @new_data_size is -1, it is ignored.  If it is >= 0, then the data size
- * of the attribute is extended to @new_data_size.  Note that the i_size of the
- * vfs inode is not updated.  Only the data size in the base attribute record
- * is updated.  The caller has to update i_size separately if this is required.
- * WARNING: It is a BUG() for @new_data_size to be smaller than the old data
- * size as well as for @new_data_size to be greater than @new_alloc_size.
- *
- * For resident attributes this involves resizing the attribute record and if
- * necessary moving it and/or other attributes into extent mft records and/or
- * converting the attribute to a non-resident attribute which in turn involves
- * extending the allocation of a non-resident attribute as described below.
- *
- * For non-resident attributes this involves allocating clusters in the data
- * zone on the volume (except for regions that are being made sparse) and
- * extending the run list to describe the allocated clusters as well as
- * updating the mapping pairs array of the attribute.  This in turn involves
- * resizing the attribute record and if necessary moving it and/or other
- * attributes into extent mft records and/or splitting the attribute record
- * into multiple extent attribute records.
- *
- * Also, the attribute list attribute is updated if present and in some of the
- * above cases (the ones where extent mft records/attributes come into play),
- * an attribute list attribute is created if not already present.
- *
- * Return the new allocated size on success and -errno on error.  In the case
- * that an error is encountered but a partial extension at least up to
- * @data_start (if present) is possible, the allocation is partially extended
- * and this is returned.  This means the caller must check the returned size to
- * determine if the extension was partial.  If @data_start is -1 then partial
- * allocations are not performed.
- *
- * WARNING: Do not call ntfs_attr_extend_allocation() for $MFT/$DATA.
- *
- * Locking: This function takes the runlist lock of @ni for writing as well as
- * locking the mft record of the base ntfs inode.  These locks are maintained
- * throughout execution of the function.  These locks are required so that the
- * attribute can be resized safely and so that it can for example be converted
- * from resident to non-resident safely.
- *
- * TODO: At present attribute list attribute handling is not implemented.
- *
- * TODO: At present it is not safe to call this function for anything other
- * than the $DATA attribute(s) of an uncompressed and unencrypted file.
- */
-s64 ntfs_attr_extend_allocation(ntfs_inode *ni, s64 new_alloc_size,
-		const s64 new_data_size, const s64 data_start)
-{
-	VCN vcn;
-	s64 ll, allocated_size, start = data_start;
-	struct inode *vi = VFS_I(ni);
-	ntfs_volume *vol = ni->vol;
-	ntfs_inode *base_ni;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
-	ntfs_attr_search_ctx *ctx;
-	runlist_element *rl, *rl2;
-	unsigned long flags;
-	int err, mp_size;
-	u32 attr_len = 0; /* Silence stupid gcc warning. */
-	bool mp_rebuilt;
-
-#ifdef DEBUG
-	read_lock_irqsave(&ni->size_lock, flags);
-	allocated_size = ni->allocated_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, "
-			"old_allocated_size 0x%llx, "
-			"new_allocated_size 0x%llx, new_data_size 0x%llx, "
-			"data_start 0x%llx.", vi->i_ino,
-			(unsigned)le32_to_cpu(ni->type),
-			(unsigned long long)allocated_size,
-			(unsigned long long)new_alloc_size,
-			(unsigned long long)new_data_size,
-			(unsigned long long)start);
-#endif
-retry_extend:
-	/*
-	 * For non-resident attributes, @start and @new_size need to be aligned
-	 * to cluster boundaries for allocation purposes.
-	 */
-	if (NInoNonResident(ni)) {
-		if (start > 0)
-			start &= ~(s64)vol->cluster_size_mask;
-		new_alloc_size = (new_alloc_size + vol->cluster_size - 1) &
-				~(s64)vol->cluster_size_mask;
-	}
-	BUG_ON(new_data_size >= 0 && new_data_size > new_alloc_size);
-	/* Check if new size is allowed in $AttrDef. */
-	err = ntfs_attr_size_bounds_check(vol, ni->type, new_alloc_size);
-	if (unlikely(err)) {
-		/* Only emit errors when the write will fail completely. */
-		read_lock_irqsave(&ni->size_lock, flags);
-		allocated_size = ni->allocated_size;
-		read_unlock_irqrestore(&ni->size_lock, flags);
-		if (start < 0 || start >= allocated_size) {
-			if (err == -ERANGE) {
-				ntfs_error(vol->sb, "Cannot extend allocation "
-						"of inode 0x%lx, attribute "
-						"type 0x%x, because the new "
-						"allocation would exceed the "
-						"maximum allowed size for "
-						"this attribute type.",
-						vi->i_ino, (unsigned)
-						le32_to_cpu(ni->type));
-			} else {
-				ntfs_error(vol->sb, "Cannot extend allocation "
-						"of inode 0x%lx, attribute "
-						"type 0x%x, because this "
-						"attribute type is not "
-						"defined on the NTFS volume.  "
-						"Possible corruption!  You "
-						"should run chkdsk!",
-						vi->i_ino, (unsigned)
-						le32_to_cpu(ni->type));
-			}
-		}
-		/* Translate error code to be POSIX conformant for write(2). */
-		if (err == -ERANGE)
-			err = -EFBIG;
-		else
-			err = -EIO;
-		return err;
-	}
-	if (!NInoAttr(ni))
-		base_ni = ni;
-	else
-		base_ni = ni->ext.base_ntfs_ino;
-	/*
-	 * We will be modifying both the runlist (if non-resident) and the mft
-	 * record so lock them both down.
-	 */
-	down_write(&ni->runlist.lock);
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		m = NULL;
-		ctx = NULL;
-		goto err_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	read_lock_irqsave(&ni->size_lock, flags);
-	allocated_size = ni->allocated_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	/*
-	 * If non-resident, seek to the last extent.  If resident, there is
-	 * only one extent, so seek to that.
-	 */
-	vcn = NInoNonResident(ni) ? allocated_size >> vol->cluster_size_bits :
-			0;
-	/*
-	 * Abort if someone did the work whilst we waited for the locks.  If we
-	 * just converted the attribute from resident to non-resident it is
-	 * likely that exactly this has happened already.  We cannot quite
-	 * abort if we need to update the data size.
-	 */
-	if (unlikely(new_alloc_size <= allocated_size)) {
-		ntfs_debug("Allocated size already exceeds requested size.");
-		new_alloc_size = allocated_size;
-		if (new_data_size < 0)
-			goto done;
-		/*
-		 * We want the first attribute extent so that we can update the
-		 * data size.
-		 */
-		vcn = 0;
-	}
-	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-			CASE_SENSITIVE, vcn, NULL, 0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT)
-			err = -EIO;
-		goto err_out;
-	}
-	m = ctx->mrec;
-	a = ctx->attr;
-	/* Use goto to reduce indentation. */
-	if (a->non_resident)
-		goto do_non_resident_extend;
-	BUG_ON(NInoNonResident(ni));
-	/* The total length of the attribute value. */
-	attr_len = le32_to_cpu(a->data.resident.value_length);
-	/*
-	 * Extend the attribute record to be able to store the new attribute
-	 * size.  ntfs_attr_record_resize() will not do anything if the size is
-	 * not changing.
-	 */
-	if (new_alloc_size < vol->mft_record_size &&
-			!ntfs_attr_record_resize(m, a,
-			le16_to_cpu(a->data.resident.value_offset) +
-			new_alloc_size)) {
-		/* The resize succeeded! */
-		write_lock_irqsave(&ni->size_lock, flags);
-		ni->allocated_size = le32_to_cpu(a->length) -
-				le16_to_cpu(a->data.resident.value_offset);
-		write_unlock_irqrestore(&ni->size_lock, flags);
-		if (new_data_size >= 0) {
-			BUG_ON(new_data_size < attr_len);
-			a->data.resident.value_length =
-					cpu_to_le32((u32)new_data_size);
-		}
-		goto flush_done;
-	}
-	/*
-	 * We have to drop all the locks so we can call
-	 * ntfs_attr_make_non_resident().  This could be optimised by try-
-	 * locking the first page cache page and only if that fails dropping
-	 * the locks, locking the page, and redoing all the locking and
-	 * lookups.  While this would be a huge optimisation, it is not worth
-	 * it as this is definitely a slow code path.
-	 */
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-	up_write(&ni->runlist.lock);
-	/*
-	 * Not enough space in the mft record, try to make the attribute
-	 * non-resident and if successful restart the extension process.
-	 */
-	err = ntfs_attr_make_non_resident(ni, attr_len);
-	if (likely(!err))
-		goto retry_extend;
-	/*
-	 * Could not make non-resident.  If this is due to this not being
-	 * permitted for this attribute type or there not being enough space,
-	 * try to make other attributes non-resident.  Otherwise fail.
-	 */
-	if (unlikely(err != -EPERM && err != -ENOSPC)) {
-		/* Only emit errors when the write will fail completely. */
-		read_lock_irqsave(&ni->size_lock, flags);
-		allocated_size = ni->allocated_size;
-		read_unlock_irqrestore(&ni->size_lock, flags);
-		if (start < 0 || start >= allocated_size)
-			ntfs_error(vol->sb, "Cannot extend allocation of "
-					"inode 0x%lx, attribute type 0x%x, "
-					"because the conversion from resident "
-					"to non-resident attribute failed "
-					"with error code %i.", vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type), err);
-		if (err != -ENOMEM)
-			err = -EIO;
-		goto conv_err_out;
-	}
-	/* TODO: Not implemented from here, abort. */
-	read_lock_irqsave(&ni->size_lock, flags);
-	allocated_size = ni->allocated_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	if (start < 0 || start >= allocated_size) {
-		if (err == -ENOSPC)
-			ntfs_error(vol->sb, "Not enough space in the mft "
-					"record/on disk for the non-resident "
-					"attribute value.  This case is not "
-					"implemented yet.");
-		else /* if (err == -EPERM) */
-			ntfs_error(vol->sb, "This attribute type may not be "
-					"non-resident.  This case is not "
-					"implemented yet.");
-	}
-	err = -EOPNOTSUPP;
-	goto conv_err_out;
-#if 0
-	// TODO: Attempt to make other attributes non-resident.
-	if (!err)
-		goto do_resident_extend;
-	/*
-	 * Both the attribute list attribute and the standard information
-	 * attribute must remain in the base inode.  Thus, if this is one of
-	 * these attributes, we have to try to move other attributes out into
-	 * extent mft records instead.
-	 */
-	if (ni->type == AT_ATTRIBUTE_LIST ||
-			ni->type == AT_STANDARD_INFORMATION) {
-		// TODO: Attempt to move other attributes into extent mft
-		// records.
-		err = -EOPNOTSUPP;
-		if (!err)
-			goto do_resident_extend;
-		goto err_out;
-	}
-	// TODO: Attempt to move this attribute to an extent mft record, but
-	// only if it is not already the only attribute in an mft record in
-	// which case there would be nothing to gain.
-	err = -EOPNOTSUPP;
-	if (!err)
-		goto do_resident_extend;
-	/* There is nothing we can do to make enough space. )-: */
-	goto err_out;
-#endif
-do_non_resident_extend:
-	BUG_ON(!NInoNonResident(ni));
-	if (new_alloc_size == allocated_size) {
-		BUG_ON(vcn);
-		goto alloc_done;
-	}
-	/*
-	 * If the data starts after the end of the old allocation, this is a
-	 * $DATA attribute and sparse attributes are enabled on the volume and
-	 * for this inode, then create a sparse region between the old
-	 * allocated size and the start of the data.  Otherwise simply proceed
-	 * with filling the whole space between the old allocated size and the
-	 * new allocated size with clusters.
-	 */
-	if ((start >= 0 && start <= allocated_size) || ni->type != AT_DATA ||
-			!NVolSparseEnabled(vol) || NInoSparseDisabled(ni))
-		goto skip_sparse;
-	// TODO: This is not implemented yet.  We just fill in with real
-	// clusters for now...
-	ntfs_debug("Inserting holes is not-implemented yet.  Falling back to "
-			"allocating real clusters instead.");
-skip_sparse:
-	rl = ni->runlist.rl;
-	if (likely(rl)) {
-		/* Seek to the end of the runlist. */
-		while (rl->length)
-			rl++;
-	}
-	/* If this attribute extent is not mapped, map it now. */
-	if (unlikely(!rl || rl->lcn == LCN_RL_NOT_MAPPED ||
-			(rl->lcn == LCN_ENOENT && rl > ni->runlist.rl &&
-			(rl-1)->lcn == LCN_RL_NOT_MAPPED))) {
-		if (!rl && !allocated_size)
-			goto first_alloc;
-		rl = ntfs_mapping_pairs_decompress(vol, a, ni->runlist.rl);
-		if (IS_ERR(rl)) {
-			err = PTR_ERR(rl);
-			if (start < 0 || start >= allocated_size)
-				ntfs_error(vol->sb, "Cannot extend allocation "
-						"of inode 0x%lx, attribute "
-						"type 0x%x, because the "
-						"mapping of a runlist "
-						"fragment failed with error "
-						"code %i.", vi->i_ino,
-						(unsigned)le32_to_cpu(ni->type),
-						err);
-			if (err != -ENOMEM)
-				err = -EIO;
-			goto err_out;
-		}
-		ni->runlist.rl = rl;
-		/* Seek to the end of the runlist. */
-		while (rl->length)
-			rl++;
-	}
-	/*
-	 * We now know the runlist of the last extent is mapped and @rl is at
-	 * the end of the runlist.  We want to begin allocating clusters
-	 * starting at the last allocated cluster to reduce fragmentation.  If
-	 * there are no valid LCNs in the attribute we let the cluster
-	 * allocator choose the starting cluster.
-	 */
-	/* If the last LCN is a hole or simillar seek back to last real LCN. */
-	while (rl->lcn < 0 && rl > ni->runlist.rl)
-		rl--;
-first_alloc:
-	// FIXME: Need to implement partial allocations so at least part of the
-	// write can be performed when start >= 0.  (Needed for POSIX write(2)
-	// conformance.)
-	rl2 = ntfs_cluster_alloc(vol, allocated_size >> vol->cluster_size_bits,
-			(new_alloc_size - allocated_size) >>
-			vol->cluster_size_bits, (rl && (rl->lcn >= 0)) ?
-			rl->lcn + rl->length : -1, DATA_ZONE, true);
-	if (IS_ERR(rl2)) {
-		err = PTR_ERR(rl2);
-		if (start < 0 || start >= allocated_size)
-			ntfs_error(vol->sb, "Cannot extend allocation of "
-					"inode 0x%lx, attribute type 0x%x, "
-					"because the allocation of clusters "
-					"failed with error code %i.", vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type), err);
-		if (err != -ENOMEM && err != -ENOSPC)
-			err = -EIO;
-		goto err_out;
-	}
-	rl = ntfs_runlists_merge(ni->runlist.rl, rl2);
-	if (IS_ERR(rl)) {
-		err = PTR_ERR(rl);
-		if (start < 0 || start >= allocated_size)
-			ntfs_error(vol->sb, "Cannot extend allocation of "
-					"inode 0x%lx, attribute type 0x%x, "
-					"because the runlist merge failed "
-					"with error code %i.", vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type), err);
-		if (err != -ENOMEM)
-			err = -EIO;
-		if (ntfs_cluster_free_from_rl(vol, rl2)) {
-			ntfs_error(vol->sb, "Failed to release allocated "
-					"cluster(s) in error code path.  Run "
-					"chkdsk to recover the lost "
-					"cluster(s).");
-			NVolSetErrors(vol);
-		}
-		ntfs_free(rl2);
-		goto err_out;
-	}
-	ni->runlist.rl = rl;
-	ntfs_debug("Allocated 0x%llx clusters.", (long long)(new_alloc_size -
-			allocated_size) >> vol->cluster_size_bits);
-	/* Find the runlist element with which the attribute extent starts. */
-	ll = sle64_to_cpu(a->data.non_resident.lowest_vcn);
-	rl2 = ntfs_rl_find_vcn_nolock(rl, ll);
-	BUG_ON(!rl2);
-	BUG_ON(!rl2->length);
-	BUG_ON(rl2->lcn < LCN_HOLE);
-	mp_rebuilt = false;
-	/* Get the size for the new mapping pairs array for this extent. */
-	mp_size = ntfs_get_size_for_mapping_pairs(vol, rl2, ll, -1);
-	if (unlikely(mp_size <= 0)) {
-		err = mp_size;
-		if (start < 0 || start >= allocated_size)
-			ntfs_error(vol->sb, "Cannot extend allocation of "
-					"inode 0x%lx, attribute type 0x%x, "
-					"because determining the size for the "
-					"mapping pairs failed with error code "
-					"%i.", vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type), err);
-		err = -EIO;
-		goto undo_alloc;
-	}
-	/* Extend the attribute record to fit the bigger mapping pairs array. */
-	attr_len = le32_to_cpu(a->length);
-	err = ntfs_attr_record_resize(m, a, mp_size +
-			le16_to_cpu(a->data.non_resident.mapping_pairs_offset));
-	if (unlikely(err)) {
-		BUG_ON(err != -ENOSPC);
-		// TODO: Deal with this by moving this extent to a new mft
-		// record or by starting a new extent in a new mft record,
-		// possibly by extending this extent partially and filling it
-		// and creating a new extent for the remainder, or by making
-		// other attributes non-resident and/or by moving other
-		// attributes out of this mft record.
-		if (start < 0 || start >= allocated_size)
-			ntfs_error(vol->sb, "Not enough space in the mft "
-					"record for the extended attribute "
-					"record.  This case is not "
-					"implemented yet.");
-		err = -EOPNOTSUPP;
-		goto undo_alloc;
-	}
-	mp_rebuilt = true;
-	/* Generate the mapping pairs array directly into the attr record. */
-	err = ntfs_mapping_pairs_build(vol, (u8*)a +
-			le16_to_cpu(a->data.non_resident.mapping_pairs_offset),
-			mp_size, rl2, ll, -1, NULL);
-	if (unlikely(err)) {
-		if (start < 0 || start >= allocated_size)
-			ntfs_error(vol->sb, "Cannot extend allocation of "
-					"inode 0x%lx, attribute type 0x%x, "
-					"because building the mapping pairs "
-					"failed with error code %i.", vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type), err);
-		err = -EIO;
-		goto undo_alloc;
-	}
-	/* Update the highest_vcn. */
-	a->data.non_resident.highest_vcn = cpu_to_sle64((new_alloc_size >>
-			vol->cluster_size_bits) - 1);
-	/*
-	 * We now have extended the allocated size of the attribute.  Reflect
-	 * this in the ntfs_inode structure and the attribute record.
-	 */
-	if (a->data.non_resident.lowest_vcn) {
-		/*
-		 * We are not in the first attribute extent, switch to it, but
-		 * first ensure the changes will make it to disk later.
-		 */
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
-		mark_mft_record_dirty(ctx->ntfs_ino);
-		ntfs_attr_reinit_search_ctx(ctx);
-		err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-				CASE_SENSITIVE, 0, NULL, 0, ctx);
-		if (unlikely(err))
-			goto restore_undo_alloc;
-		/* @m is not used any more so no need to set it. */
-		a = ctx->attr;
-	}
-	write_lock_irqsave(&ni->size_lock, flags);
-	ni->allocated_size = new_alloc_size;
-	a->data.non_resident.allocated_size = cpu_to_sle64(new_alloc_size);
-	/*
-	 * FIXME: This would fail if @ni is a directory, $MFT, or an index,
-	 * since those can have sparse/compressed set.  For example can be
-	 * set compressed even though it is not compressed itself and in that
-	 * case the bit means that files are to be created compressed in the
-	 * directory...  At present this is ok as this code is only called for
-	 * regular files, and only for their $DATA attribute(s).
-	 * FIXME: The calculation is wrong if we created a hole above.  For now
-	 * it does not matter as we never create holes.
-	 */
-	if (NInoSparse(ni) || NInoCompressed(ni)) {
-		ni->itype.compressed.size += new_alloc_size - allocated_size;
-		a->data.non_resident.compressed_size =
-				cpu_to_sle64(ni->itype.compressed.size);
-		vi->i_blocks = ni->itype.compressed.size >> 9;
-	} else
-		vi->i_blocks = new_alloc_size >> 9;
-	write_unlock_irqrestore(&ni->size_lock, flags);
-alloc_done:
-	if (new_data_size >= 0) {
-		BUG_ON(new_data_size <
-				sle64_to_cpu(a->data.non_resident.data_size));
-		a->data.non_resident.data_size = cpu_to_sle64(new_data_size);
-	}
-flush_done:
-	/* Ensure the changes make it to disk. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-done:
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-	up_write(&ni->runlist.lock);
-	ntfs_debug("Done, new_allocated_size 0x%llx.",
-			(unsigned long long)new_alloc_size);
-	return new_alloc_size;
-restore_undo_alloc:
-	if (start < 0 || start >= allocated_size)
-		ntfs_error(vol->sb, "Cannot complete extension of allocation "
-				"of inode 0x%lx, attribute type 0x%x, because "
-				"lookup of first attribute extent failed with "
-				"error code %i.", vi->i_ino,
-				(unsigned)le32_to_cpu(ni->type), err);
-	if (err == -ENOENT)
-		err = -EIO;
-	ntfs_attr_reinit_search_ctx(ctx);
-	if (ntfs_attr_lookup(ni->type, ni->name, ni->name_len, CASE_SENSITIVE,
-			allocated_size >> vol->cluster_size_bits, NULL, 0,
-			ctx)) {
-		ntfs_error(vol->sb, "Failed to find last attribute extent of "
-				"attribute in error code path.  Run chkdsk to "
-				"recover.");
-		write_lock_irqsave(&ni->size_lock, flags);
-		ni->allocated_size = new_alloc_size;
-		/*
-		 * FIXME: This would fail if @ni is a directory...  See above.
-		 * FIXME: The calculation is wrong if we created a hole above.
-		 * For now it does not matter as we never create holes.
-		 */
-		if (NInoSparse(ni) || NInoCompressed(ni)) {
-			ni->itype.compressed.size += new_alloc_size -
-					allocated_size;
-			vi->i_blocks = ni->itype.compressed.size >> 9;
-		} else
-			vi->i_blocks = new_alloc_size >> 9;
-		write_unlock_irqrestore(&ni->size_lock, flags);
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(base_ni);
-		up_write(&ni->runlist.lock);
-		/*
-		 * The only thing that is now wrong is the allocated size of the
-		 * base attribute extent which chkdsk should be able to fix.
-		 */
-		NVolSetErrors(vol);
-		return err;
-	}
-	ctx->attr->data.non_resident.highest_vcn = cpu_to_sle64(
-			(allocated_size >> vol->cluster_size_bits) - 1);
-undo_alloc:
-	ll = allocated_size >> vol->cluster_size_bits;
-	if (ntfs_cluster_free(ni, ll, -1, ctx) < 0) {
-		ntfs_error(vol->sb, "Failed to release allocated cluster(s) "
-				"in error code path.  Run chkdsk to recover "
-				"the lost cluster(s).");
-		NVolSetErrors(vol);
-	}
-	m = ctx->mrec;
-	a = ctx->attr;
-	/*
-	 * If the runlist truncation fails and/or the search context is no
-	 * longer valid, we cannot resize the attribute record or build the
-	 * mapping pairs array thus we mark the inode bad so that no access to
-	 * the freed clusters can happen.
-	 */
-	if (ntfs_rl_truncate_nolock(vol, &ni->runlist, ll) || IS_ERR(m)) {
-		ntfs_error(vol->sb, "Failed to %s in error code path.  Run "
-				"chkdsk to recover.", IS_ERR(m) ?
-				"restore attribute search context" :
-				"truncate attribute runlist");
-		NVolSetErrors(vol);
-	} else if (mp_rebuilt) {
-		if (ntfs_attr_record_resize(m, a, attr_len)) {
-			ntfs_error(vol->sb, "Failed to restore attribute "
-					"record in error code path.  Run "
-					"chkdsk to recover.");
-			NVolSetErrors(vol);
-		} else /* if (success) */ {
-			if (ntfs_mapping_pairs_build(vol, (u8*)a + le16_to_cpu(
-					a->data.non_resident.
-					mapping_pairs_offset), attr_len -
-					le16_to_cpu(a->data.non_resident.
-					mapping_pairs_offset), rl2, ll, -1,
-					NULL)) {
-				ntfs_error(vol->sb, "Failed to restore "
-						"mapping pairs array in error "
-						"code path.  Run chkdsk to "
-						"recover.");
-				NVolSetErrors(vol);
-			}
-			flush_dcache_mft_record_page(ctx->ntfs_ino);
-			mark_mft_record_dirty(ctx->ntfs_ino);
-		}
-	}
-err_out:
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(base_ni);
-	up_write(&ni->runlist.lock);
-conv_err_out:
-	ntfs_debug("Failed.  Returning error code %i.", err);
-	return err;
-}
-
-/**
- * ntfs_attr_set - fill (a part of) an attribute with a byte
- * @ni:		ntfs inode describing the attribute to fill
- * @ofs:	offset inside the attribute at which to start to fill
- * @cnt:	number of bytes to fill
- * @val:	the unsigned 8-bit value with which to fill the attribute
- *
- * Fill @cnt bytes of the attribute described by the ntfs inode @ni starting at
- * byte offset @ofs inside the attribute with the constant byte @val.
- *
- * This function is effectively like memset() applied to an ntfs attribute.
- * Note this function actually only operates on the page cache pages belonging
- * to the ntfs attribute and it marks them dirty after doing the memset().
- * Thus it relies on the vm dirty page write code paths to cause the modified
- * pages to be written to the mft record/disk.
- *
- * Return 0 on success and -errno on error.  An error code of -ESPIPE means
- * that @ofs + @cnt were outside the end of the attribute and no write was
- * performed.
- */
-int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val)
-{
-	ntfs_volume *vol = ni->vol;
-	struct address_space *mapping;
-	struct page *page;
-	u8 *kaddr;
-	pgoff_t idx, end;
-	unsigned start_ofs, end_ofs, size;
-
-	ntfs_debug("Entering for ofs 0x%llx, cnt 0x%llx, val 0x%hx.",
-			(long long)ofs, (long long)cnt, val);
-	BUG_ON(ofs < 0);
-	BUG_ON(cnt < 0);
-	if (!cnt)
-		goto done;
-	/*
-	 * FIXME: Compressed and encrypted attributes are not supported when
-	 * writing and we should never have gotten here for them.
-	 */
-	BUG_ON(NInoCompressed(ni));
-	BUG_ON(NInoEncrypted(ni));
-	mapping = VFS_I(ni)->i_mapping;
-	/* Work out the starting index and page offset. */
-	idx = ofs >> PAGE_SHIFT;
-	start_ofs = ofs & ~PAGE_MASK;
-	/* Work out the ending index and page offset. */
-	end = ofs + cnt;
-	end_ofs = end & ~PAGE_MASK;
-	/* If the end is outside the inode size return -ESPIPE. */
-	if (unlikely(end > i_size_read(VFS_I(ni)))) {
-		ntfs_error(vol->sb, "Request exceeds end of attribute.");
-		return -ESPIPE;
-	}
-	end >>= PAGE_SHIFT;
-	/* If there is a first partial page, need to do it the slow way. */
-	if (start_ofs) {
-		page = read_mapping_page(mapping, idx, NULL);
-		if (IS_ERR(page)) {
-			ntfs_error(vol->sb, "Failed to read first partial "
-					"page (error, index 0x%lx).", idx);
-			return PTR_ERR(page);
-		}
-		/*
-		 * If the last page is the same as the first page, need to
-		 * limit the write to the end offset.
-		 */
-		size = PAGE_SIZE;
-		if (idx == end)
-			size = end_ofs;
-		kaddr = kmap_atomic(page);
-		memset(kaddr + start_ofs, val, size - start_ofs);
-		flush_dcache_page(page);
-		kunmap_atomic(kaddr);
-		set_page_dirty(page);
-		put_page(page);
-		balance_dirty_pages_ratelimited(mapping);
-		cond_resched();
-		if (idx == end)
-			goto done;
-		idx++;
-	}
-	/* Do the whole pages the fast way. */
-	for (; idx < end; idx++) {
-		/* Find or create the current page.  (The page is locked.) */
-		page = grab_cache_page(mapping, idx);
-		if (unlikely(!page)) {
-			ntfs_error(vol->sb, "Insufficient memory to grab "
-					"page (index 0x%lx).", idx);
-			return -ENOMEM;
-		}
-		kaddr = kmap_atomic(page);
-		memset(kaddr, val, PAGE_SIZE);
-		flush_dcache_page(page);
-		kunmap_atomic(kaddr);
-		/*
-		 * If the page has buffers, mark them uptodate since buffer
-		 * state and not page state is definitive in 2.6 kernels.
-		 */
-		if (page_has_buffers(page)) {
-			struct buffer_head *bh, *head;
-
-			bh = head = page_buffers(page);
-			do {
-				set_buffer_uptodate(bh);
-			} while ((bh = bh->b_this_page) != head);
-		}
-		/* Now that buffers are uptodate, set the page uptodate, too. */
-		SetPageUptodate(page);
-		/*
-		 * Set the page and all its buffers dirty and mark the inode
-		 * dirty, too.  The VM will write the page later on.
-		 */
-		set_page_dirty(page);
-		/* Finally unlock and release the page. */
-		unlock_page(page);
-		put_page(page);
-		balance_dirty_pages_ratelimited(mapping);
-		cond_resched();
-	}
-	/* If there is a last partial page, need to do it the slow way. */
-	if (end_ofs) {
-		page = read_mapping_page(mapping, idx, NULL);
-		if (IS_ERR(page)) {
-			ntfs_error(vol->sb, "Failed to read last partial page "
-					"(error, index 0x%lx).", idx);
-			return PTR_ERR(page);
-		}
-		kaddr = kmap_atomic(page);
-		memset(kaddr, val, end_ofs);
-		flush_dcache_page(page);
-		kunmap_atomic(kaddr);
-		set_page_dirty(page);
-		put_page(page);
-		balance_dirty_pages_ratelimited(mapping);
-		cond_resched();
-	}
-done:
-	ntfs_debug("Done.");
-	return 0;
-}
-
-#endif /* NTFS_RW */
diff --git a/fs/ntfs/attrib.h b/fs/ntfs/attrib.h
deleted file mode 100644
index fe0890d3d072..000000000000
--- a/fs/ntfs/attrib.h
+++ /dev/null
@@ -1,102 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * attrib.h - Defines for attribute handling in NTFS Linux kernel driver.
- *	      Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2005 Anton Altaparmakov
- * Copyright (c) 2002 Richard Russon
- */
-
-#ifndef _LINUX_NTFS_ATTRIB_H
-#define _LINUX_NTFS_ATTRIB_H
-
-#include "endian.h"
-#include "types.h"
-#include "layout.h"
-#include "inode.h"
-#include "runlist.h"
-#include "volume.h"
-
-/**
- * ntfs_attr_search_ctx - used in attribute search functions
- * @mrec:	buffer containing mft record to search
- * @attr:	attribute record in @mrec where to begin/continue search
- * @is_first:	if true ntfs_attr_lookup() begins search with @attr, else after
- *
- * Structure must be initialized to zero before the first call to one of the
- * attribute search functions. Initialize @mrec to point to the mft record to
- * search, and @attr to point to the first attribute within @mrec (not necessary
- * if calling the _first() functions), and set @is_first to 'true' (not necessary
- * if calling the _first() functions).
- *
- * If @is_first is 'true', the search begins with @attr. If @is_first is 'false',
- * the search begins after @attr. This is so that, after the first call to one
- * of the search attribute functions, we can call the function again, without
- * any modification of the search context, to automagically get the next
- * matching attribute.
- */
-typedef struct {
-	MFT_RECORD *mrec;
-	ATTR_RECORD *attr;
-	bool is_first;
-	ntfs_inode *ntfs_ino;
-	ATTR_LIST_ENTRY *al_entry;
-	ntfs_inode *base_ntfs_ino;
-	MFT_RECORD *base_mrec;
-	ATTR_RECORD *base_attr;
-} ntfs_attr_search_ctx;
-
-extern int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn,
-		ntfs_attr_search_ctx *ctx);
-extern int ntfs_map_runlist(ntfs_inode *ni, VCN vcn);
-
-extern LCN ntfs_attr_vcn_to_lcn_nolock(ntfs_inode *ni, const VCN vcn,
-		const bool write_locked);
-
-extern runlist_element *ntfs_attr_find_vcn_nolock(ntfs_inode *ni,
-		const VCN vcn, ntfs_attr_search_ctx *ctx);
-
-int ntfs_attr_lookup(const ATTR_TYPE type, const ntfschar *name,
-		const u32 name_len, const IGNORE_CASE_BOOL ic,
-		const VCN lowest_vcn, const u8 *val, const u32 val_len,
-		ntfs_attr_search_ctx *ctx);
-
-extern int load_attribute_list(ntfs_volume *vol, runlist *rl, u8 *al_start,
-		const s64 size, const s64 initialized_size);
-
-static inline s64 ntfs_attr_size(const ATTR_RECORD *a)
-{
-	if (!a->non_resident)
-		return (s64)le32_to_cpu(a->data.resident.value_length);
-	return sle64_to_cpu(a->data.non_resident.data_size);
-}
-
-extern void ntfs_attr_reinit_search_ctx(ntfs_attr_search_ctx *ctx);
-extern ntfs_attr_search_ctx *ntfs_attr_get_search_ctx(ntfs_inode *ni,
-		MFT_RECORD *mrec);
-extern void ntfs_attr_put_search_ctx(ntfs_attr_search_ctx *ctx);
-
-#ifdef NTFS_RW
-
-extern int ntfs_attr_size_bounds_check(const ntfs_volume *vol,
-		const ATTR_TYPE type, const s64 size);
-extern int ntfs_attr_can_be_non_resident(const ntfs_volume *vol,
-		const ATTR_TYPE type);
-extern int ntfs_attr_can_be_resident(const ntfs_volume *vol,
-		const ATTR_TYPE type);
-
-extern int ntfs_attr_record_resize(MFT_RECORD *m, ATTR_RECORD *a, u32 new_size);
-extern int ntfs_resident_attr_value_resize(MFT_RECORD *m, ATTR_RECORD *a,
-		const u32 new_size);
-
-extern int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size);
-
-extern s64 ntfs_attr_extend_allocation(ntfs_inode *ni, s64 new_alloc_size,
-		const s64 new_data_size, const s64 data_start);
-
-extern int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt,
-		const u8 val);
-
-#endif /* NTFS_RW */
-
-#endif /* _LINUX_NTFS_ATTRIB_H */
diff --git a/fs/ntfs/bitmap.c b/fs/ntfs/bitmap.c
deleted file mode 100644
index 0675b2400873..000000000000
--- a/fs/ntfs/bitmap.c
+++ /dev/null
@@ -1,179 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * bitmap.c - NTFS kernel bitmap handling.  Part of the Linux-NTFS project.
- *
- * Copyright (c) 2004-2005 Anton Altaparmakov
- */
-
-#ifdef NTFS_RW
-
-#include <linux/pagemap.h>
-
-#include "bitmap.h"
-#include "debug.h"
-#include "aops.h"
-#include "ntfs.h"
-
-/**
- * __ntfs_bitmap_set_bits_in_run - set a run of bits in a bitmap to a value
- * @vi:			vfs inode describing the bitmap
- * @start_bit:		first bit to set
- * @count:		number of bits to set
- * @value:		value to set the bits to (i.e. 0 or 1)
- * @is_rollback:	if 'true' this is a rollback operation
- *
- * Set @count bits starting at bit @start_bit in the bitmap described by the
- * vfs inode @vi to @value, where @value is either 0 or 1.
- *
- * @is_rollback should always be 'false', it is for internal use to rollback
- * errors.  You probably want to use ntfs_bitmap_set_bits_in_run() instead.
- *
- * Return 0 on success and -errno on error.
- */
-int __ntfs_bitmap_set_bits_in_run(struct inode *vi, const s64 start_bit,
-		const s64 count, const u8 value, const bool is_rollback)
-{
-	s64 cnt = count;
-	pgoff_t index, end_index;
-	struct address_space *mapping;
-	struct page *page;
-	u8 *kaddr;
-	int pos, len;
-	u8 bit;
-
-	BUG_ON(!vi);
-	ntfs_debug("Entering for i_ino 0x%lx, start_bit 0x%llx, count 0x%llx, "
-			"value %u.%s", vi->i_ino, (unsigned long long)start_bit,
-			(unsigned long long)cnt, (unsigned int)value,
-			is_rollback ? " (rollback)" : "");
-	BUG_ON(start_bit < 0);
-	BUG_ON(cnt < 0);
-	BUG_ON(value > 1);
-	/*
-	 * Calculate the indices for the pages containing the first and last
-	 * bits, i.e. @start_bit and @start_bit + @cnt - 1, respectively.
-	 */
-	index = start_bit >> (3 + PAGE_SHIFT);
-	end_index = (start_bit + cnt - 1) >> (3 + PAGE_SHIFT);
-
-	/* Get the page containing the first bit (@start_bit). */
-	mapping = vi->i_mapping;
-	page = ntfs_map_page(mapping, index);
-	if (IS_ERR(page)) {
-		if (!is_rollback)
-			ntfs_error(vi->i_sb, "Failed to map first page (error "
-					"%li), aborting.", PTR_ERR(page));
-		return PTR_ERR(page);
-	}
-	kaddr = page_address(page);
-
-	/* Set @pos to the position of the byte containing @start_bit. */
-	pos = (start_bit >> 3) & ~PAGE_MASK;
-
-	/* Calculate the position of @start_bit in the first byte. */
-	bit = start_bit & 7;
-
-	/* If the first byte is partial, modify the appropriate bits in it. */
-	if (bit) {
-		u8 *byte = kaddr + pos;
-		while ((bit & 7) && cnt) {
-			cnt--;
-			if (value)
-				*byte |= 1 << bit++;
-			else
-				*byte &= ~(1 << bit++);
-		}
-		/* If we are done, unmap the page and return success. */
-		if (!cnt)
-			goto done;
-
-		/* Update @pos to the new position. */
-		pos++;
-	}
-	/*
-	 * Depending on @value, modify all remaining whole bytes in the page up
-	 * to @cnt.
-	 */
-	len = min_t(s64, cnt >> 3, PAGE_SIZE - pos);
-	memset(kaddr + pos, value ? 0xff : 0, len);
-	cnt -= len << 3;
-
-	/* Update @len to point to the first not-done byte in the page. */
-	if (cnt < 8)
-		len += pos;
-
-	/* If we are not in the last page, deal with all subsequent pages. */
-	while (index < end_index) {
-		BUG_ON(cnt <= 0);
-
-		/* Update @index and get the next page. */
-		flush_dcache_page(page);
-		set_page_dirty(page);
-		ntfs_unmap_page(page);
-		page = ntfs_map_page(mapping, ++index);
-		if (IS_ERR(page))
-			goto rollback;
-		kaddr = page_address(page);
-		/*
-		 * Depending on @value, modify all remaining whole bytes in the
-		 * page up to @cnt.
-		 */
-		len = min_t(s64, cnt >> 3, PAGE_SIZE);
-		memset(kaddr, value ? 0xff : 0, len);
-		cnt -= len << 3;
-	}
-	/*
-	 * The currently mapped page is the last one.  If the last byte is
-	 * partial, modify the appropriate bits in it.  Note, @len is the
-	 * position of the last byte inside the page.
-	 */
-	if (cnt) {
-		u8 *byte;
-
-		BUG_ON(cnt > 7);
-
-		bit = cnt;
-		byte = kaddr + len;
-		while (bit--) {
-			if (value)
-				*byte |= 1 << bit;
-			else
-				*byte &= ~(1 << bit);
-		}
-	}
-done:
-	/* We are done.  Unmap the page and return success. */
-	flush_dcache_page(page);
-	set_page_dirty(page);
-	ntfs_unmap_page(page);
-	ntfs_debug("Done.");
-	return 0;
-rollback:
-	/*
-	 * Current state:
-	 *	- no pages are mapped
-	 *	- @count - @cnt is the number of bits that have been modified
-	 */
-	if (is_rollback)
-		return PTR_ERR(page);
-	if (count != cnt)
-		pos = __ntfs_bitmap_set_bits_in_run(vi, start_bit, count - cnt,
-				value ? 0 : 1, true);
-	else
-		pos = 0;
-	if (!pos) {
-		/* Rollback was successful. */
-		ntfs_error(vi->i_sb, "Failed to map subsequent page (error "
-				"%li), aborting.", PTR_ERR(page));
-	} else {
-		/* Rollback failed. */
-		ntfs_error(vi->i_sb, "Failed to map subsequent page (error "
-				"%li) and rollback failed (error %i).  "
-				"Aborting and leaving inconsistent metadata.  "
-				"Unmount and run chkdsk.", PTR_ERR(page), pos);
-		NVolSetErrors(NTFS_SB(vi->i_sb));
-	}
-	return PTR_ERR(page);
-}
-
-#endif /* NTFS_RW */
diff --git a/fs/ntfs/bitmap.h b/fs/ntfs/bitmap.h
deleted file mode 100644
index 9dd2224ca9c4..000000000000
--- a/fs/ntfs/bitmap.h
+++ /dev/null
@@ -1,104 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * bitmap.h - Defines for NTFS kernel bitmap handling.  Part of the Linux-NTFS
- *	      project.
- *
- * Copyright (c) 2004 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_BITMAP_H
-#define _LINUX_NTFS_BITMAP_H
-
-#ifdef NTFS_RW
-
-#include <linux/fs.h>
-
-#include "types.h"
-
-extern int __ntfs_bitmap_set_bits_in_run(struct inode *vi, const s64 start_bit,
-		const s64 count, const u8 value, const bool is_rollback);
-
-/**
- * ntfs_bitmap_set_bits_in_run - set a run of bits in a bitmap to a value
- * @vi:			vfs inode describing the bitmap
- * @start_bit:		first bit to set
- * @count:		number of bits to set
- * @value:		value to set the bits to (i.e. 0 or 1)
- *
- * Set @count bits starting at bit @start_bit in the bitmap described by the
- * vfs inode @vi to @value, where @value is either 0 or 1.
- *
- * Return 0 on success and -errno on error.
- */
-static inline int ntfs_bitmap_set_bits_in_run(struct inode *vi,
-		const s64 start_bit, const s64 count, const u8 value)
-{
-	return __ntfs_bitmap_set_bits_in_run(vi, start_bit, count, value,
-			false);
-}
-
-/**
- * ntfs_bitmap_set_run - set a run of bits in a bitmap
- * @vi:		vfs inode describing the bitmap
- * @start_bit:	first bit to set
- * @count:	number of bits to set
- *
- * Set @count bits starting at bit @start_bit in the bitmap described by the
- * vfs inode @vi.
- *
- * Return 0 on success and -errno on error.
- */
-static inline int ntfs_bitmap_set_run(struct inode *vi, const s64 start_bit,
-		const s64 count)
-{
-	return ntfs_bitmap_set_bits_in_run(vi, start_bit, count, 1);
-}
-
-/**
- * ntfs_bitmap_clear_run - clear a run of bits in a bitmap
- * @vi:		vfs inode describing the bitmap
- * @start_bit:	first bit to clear
- * @count:	number of bits to clear
- *
- * Clear @count bits starting at bit @start_bit in the bitmap described by the
- * vfs inode @vi.
- *
- * Return 0 on success and -errno on error.
- */
-static inline int ntfs_bitmap_clear_run(struct inode *vi, const s64 start_bit,
-		const s64 count)
-{
-	return ntfs_bitmap_set_bits_in_run(vi, start_bit, count, 0);
-}
-
-/**
- * ntfs_bitmap_set_bit - set a bit in a bitmap
- * @vi:		vfs inode describing the bitmap
- * @bit:	bit to set
- *
- * Set bit @bit in the bitmap described by the vfs inode @vi.
- *
- * Return 0 on success and -errno on error.
- */
-static inline int ntfs_bitmap_set_bit(struct inode *vi, const s64 bit)
-{
-	return ntfs_bitmap_set_run(vi, bit, 1);
-}
-
-/**
- * ntfs_bitmap_clear_bit - clear a bit in a bitmap
- * @vi:		vfs inode describing the bitmap
- * @bit:	bit to clear
- *
- * Clear bit @bit in the bitmap described by the vfs inode @vi.
- *
- * Return 0 on success and -errno on error.
- */
-static inline int ntfs_bitmap_clear_bit(struct inode *vi, const s64 bit)
-{
-	return ntfs_bitmap_clear_run(vi, bit, 1);
-}
-
-#endif /* NTFS_RW */
-
-#endif /* defined _LINUX_NTFS_BITMAP_H */
diff --git a/fs/ntfs/collate.c b/fs/ntfs/collate.c
deleted file mode 100644
index 3ab6ec96abfe..000000000000
--- a/fs/ntfs/collate.c
+++ /dev/null
@@ -1,110 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * collate.c - NTFS kernel collation handling.  Part of the Linux-NTFS project.
- *
- * Copyright (c) 2004 Anton Altaparmakov
- */
-
-#include "collate.h"
-#include "debug.h"
-#include "ntfs.h"
-
-static int ntfs_collate_binary(ntfs_volume *vol,
-		const void *data1, const int data1_len,
-		const void *data2, const int data2_len)
-{
-	int rc;
-
-	ntfs_debug("Entering.");
-	rc = memcmp(data1, data2, min(data1_len, data2_len));
-	if (!rc && (data1_len != data2_len)) {
-		if (data1_len < data2_len)
-			rc = -1;
-		else
-			rc = 1;
-	}
-	ntfs_debug("Done, returning %i", rc);
-	return rc;
-}
-
-static int ntfs_collate_ntofs_ulong(ntfs_volume *vol,
-		const void *data1, const int data1_len,
-		const void *data2, const int data2_len)
-{
-	int rc;
-	u32 d1, d2;
-
-	ntfs_debug("Entering.");
-	// FIXME:  We don't really want to bug here.
-	BUG_ON(data1_len != data2_len);
-	BUG_ON(data1_len != 4);
-	d1 = le32_to_cpup(data1);
-	d2 = le32_to_cpup(data2);
-	if (d1 < d2)
-		rc = -1;
-	else {
-		if (d1 == d2)
-			rc = 0;
-		else
-			rc = 1;
-	}
-	ntfs_debug("Done, returning %i", rc);
-	return rc;
-}
-
-typedef int (*ntfs_collate_func_t)(ntfs_volume *, const void *, const int,
-		const void *, const int);
-
-static ntfs_collate_func_t ntfs_do_collate0x0[3] = {
-	ntfs_collate_binary,
-	NULL/*ntfs_collate_file_name*/,
-	NULL/*ntfs_collate_unicode_string*/,
-};
-
-static ntfs_collate_func_t ntfs_do_collate0x1[4] = {
-	ntfs_collate_ntofs_ulong,
-	NULL/*ntfs_collate_ntofs_sid*/,
-	NULL/*ntfs_collate_ntofs_security_hash*/,
-	NULL/*ntfs_collate_ntofs_ulongs*/,
-};
-
-/**
- * ntfs_collate - collate two data items using a specified collation rule
- * @vol:	ntfs volume to which the data items belong
- * @cr:		collation rule to use when comparing the items
- * @data1:	first data item to collate
- * @data1_len:	length in bytes of @data1
- * @data2:	second data item to collate
- * @data2_len:	length in bytes of @data2
- *
- * Collate the two data items @data1 and @data2 using the collation rule @cr
- * and return -1, 0, ir 1 if @data1 is found, respectively, to collate before,
- * to match, or to collate after @data2.
- *
- * For speed we use the collation rule @cr as an index into two tables of
- * function pointers to call the appropriate collation function.
- */
-int ntfs_collate(ntfs_volume *vol, COLLATION_RULE cr,
-		const void *data1, const int data1_len,
-		const void *data2, const int data2_len) {
-	int i;
-
-	ntfs_debug("Entering.");
-	/*
-	 * FIXME:  At the moment we only support COLLATION_BINARY and
-	 * COLLATION_NTOFS_ULONG, so we BUG() for everything else for now.
-	 */
-	BUG_ON(cr != COLLATION_BINARY && cr != COLLATION_NTOFS_ULONG);
-	i = le32_to_cpu(cr);
-	BUG_ON(i < 0);
-	if (i <= 0x02)
-		return ntfs_do_collate0x0[i](vol, data1, data1_len,
-				data2, data2_len);
-	BUG_ON(i < 0x10);
-	i -= 0x10;
-	if (likely(i <= 3))
-		return ntfs_do_collate0x1[i](vol, data1, data1_len,
-				data2, data2_len);
-	BUG();
-	return 0;
-}
diff --git a/fs/ntfs/collate.h b/fs/ntfs/collate.h
deleted file mode 100644
index f2255619b4f4..000000000000
--- a/fs/ntfs/collate.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * collate.h - Defines for NTFS kernel collation handling.  Part of the
- *	       Linux-NTFS project.
- *
- * Copyright (c) 2004 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_COLLATE_H
-#define _LINUX_NTFS_COLLATE_H
-
-#include "types.h"
-#include "volume.h"
-
-static inline bool ntfs_is_collation_rule_supported(COLLATION_RULE cr) {
-	int i;
-
-	/*
-	 * FIXME:  At the moment we only support COLLATION_BINARY and
-	 * COLLATION_NTOFS_ULONG, so we return false for everything else for
-	 * now.
-	 */
-	if (unlikely(cr != COLLATION_BINARY && cr != COLLATION_NTOFS_ULONG))
-		return false;
-	i = le32_to_cpu(cr);
-	if (likely(((i >= 0) && (i <= 0x02)) ||
-			((i >= 0x10) && (i <= 0x13))))
-		return true;
-	return false;
-}
-
-extern int ntfs_collate(ntfs_volume *vol, COLLATION_RULE cr,
-		const void *data1, const int data1_len,
-		const void *data2, const int data2_len);
-
-#endif /* _LINUX_NTFS_COLLATE_H */
diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c
deleted file mode 100644
index 761aaa0195d6..000000000000
--- a/fs/ntfs/compress.c
+++ /dev/null
@@ -1,950 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * compress.c - NTFS kernel compressed attributes handling.
- *		Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2004 Anton Altaparmakov
- * Copyright (c) 2002 Richard Russon
- */
-
-#include <linux/fs.h>
-#include <linux/buffer_head.h>
-#include <linux/blkdev.h>
-#include <linux/vmalloc.h>
-#include <linux/slab.h>
-
-#include "attrib.h"
-#include "inode.h"
-#include "debug.h"
-#include "ntfs.h"
-
-/**
- * ntfs_compression_constants - enum of constants used in the compression code
- */
-typedef enum {
-	/* Token types and access mask. */
-	NTFS_SYMBOL_TOKEN	=	0,
-	NTFS_PHRASE_TOKEN	=	1,
-	NTFS_TOKEN_MASK		=	1,
-
-	/* Compression sub-block constants. */
-	NTFS_SB_SIZE_MASK	=	0x0fff,
-	NTFS_SB_SIZE		=	0x1000,
-	NTFS_SB_IS_COMPRESSED	=	0x8000,
-
-	/*
-	 * The maximum compression block size is by definition 16 * the cluster
-	 * size, with the maximum supported cluster size being 4kiB. Thus the
-	 * maximum compression buffer size is 64kiB, so we use this when
-	 * initializing the compression buffer.
-	 */
-	NTFS_MAX_CB_SIZE	= 64 * 1024,
-} ntfs_compression_constants;
-
-/*
- * ntfs_compression_buffer - one buffer for the decompression engine
- */
-static u8 *ntfs_compression_buffer;
-
-/*
- * ntfs_cb_lock - spinlock which protects ntfs_compression_buffer
- */
-static DEFINE_SPINLOCK(ntfs_cb_lock);
-
-/**
- * allocate_compression_buffers - allocate the decompression buffers
- *
- * Caller has to hold the ntfs_lock mutex.
- *
- * Return 0 on success or -ENOMEM if the allocations failed.
- */
-int allocate_compression_buffers(void)
-{
-	BUG_ON(ntfs_compression_buffer);
-
-	ntfs_compression_buffer = vmalloc(NTFS_MAX_CB_SIZE);
-	if (!ntfs_compression_buffer)
-		return -ENOMEM;
-	return 0;
-}
-
-/**
- * free_compression_buffers - free the decompression buffers
- *
- * Caller has to hold the ntfs_lock mutex.
- */
-void free_compression_buffers(void)
-{
-	BUG_ON(!ntfs_compression_buffer);
-	vfree(ntfs_compression_buffer);
-	ntfs_compression_buffer = NULL;
-}
-
-/**
- * zero_partial_compressed_page - zero out of bounds compressed page region
- */
-static void zero_partial_compressed_page(struct page *page,
-		const s64 initialized_size)
-{
-	u8 *kp = page_address(page);
-	unsigned int kp_ofs;
-
-	ntfs_debug("Zeroing page region outside initialized size.");
-	if (((s64)page->index << PAGE_SHIFT) >= initialized_size) {
-		clear_page(kp);
-		return;
-	}
-	kp_ofs = initialized_size & ~PAGE_MASK;
-	memset(kp + kp_ofs, 0, PAGE_SIZE - kp_ofs);
-	return;
-}
-
-/**
- * handle_bounds_compressed_page - test for&handle out of bounds compressed page
- */
-static inline void handle_bounds_compressed_page(struct page *page,
-		const loff_t i_size, const s64 initialized_size)
-{
-	if ((page->index >= (initialized_size >> PAGE_SHIFT)) &&
-			(initialized_size < i_size))
-		zero_partial_compressed_page(page, initialized_size);
-	return;
-}
-
-/**
- * ntfs_decompress - decompress a compression block into an array of pages
- * @dest_pages:		destination array of pages
- * @completed_pages:	scratch space to track completed pages
- * @dest_index:		current index into @dest_pages (IN/OUT)
- * @dest_ofs:		current offset within @dest_pages[@dest_index] (IN/OUT)
- * @dest_max_index:	maximum index into @dest_pages (IN)
- * @dest_max_ofs:	maximum offset within @dest_pages[@dest_max_index] (IN)
- * @xpage:		the target page (-1 if none) (IN)
- * @xpage_done:		set to 1 if xpage was completed successfully (IN/OUT)
- * @cb_start:		compression block to decompress (IN)
- * @cb_size:		size of compression block @cb_start in bytes (IN)
- * @i_size:		file size when we started the read (IN)
- * @initialized_size:	initialized file size when we started the read (IN)
- *
- * The caller must have disabled preemption. ntfs_decompress() reenables it when
- * the critical section is finished.
- *
- * This decompresses the compression block @cb_start into the array of
- * destination pages @dest_pages starting at index @dest_index into @dest_pages
- * and at offset @dest_pos into the page @dest_pages[@dest_index].
- *
- * When the page @dest_pages[@xpage] is completed, @xpage_done is set to 1.
- * If xpage is -1 or @xpage has not been completed, @xpage_done is not modified.
- *
- * @cb_start is a pointer to the compression block which needs decompressing
- * and @cb_size is the size of @cb_start in bytes (8-64kiB).
- *
- * Return 0 if success or -EOVERFLOW on error in the compressed stream.
- * @xpage_done indicates whether the target page (@dest_pages[@xpage]) was
- * completed during the decompression of the compression block (@cb_start).
- *
- * Warning: This function *REQUIRES* PAGE_SIZE >= 4096 or it will blow up
- * unpredicatbly! You have been warned!
- *
- * Note to hackers: This function may not sleep until it has finished accessing
- * the compression block @cb_start as it is a per-CPU buffer.
- */
-static int ntfs_decompress(struct page *dest_pages[], int completed_pages[],
-		int *dest_index, int *dest_ofs, const int dest_max_index,
-		const int dest_max_ofs, const int xpage, char *xpage_done,
-		u8 *const cb_start, const u32 cb_size, const loff_t i_size,
-		const s64 initialized_size)
-{
-	/*
-	 * Pointers into the compressed data, i.e. the compression block (cb),
-	 * and the therein contained sub-blocks (sb).
-	 */
-	u8 *cb_end = cb_start + cb_size; /* End of cb. */
-	u8 *cb = cb_start;	/* Current position in cb. */
-	u8 *cb_sb_start;	/* Beginning of the current sb in the cb. */
-	u8 *cb_sb_end;		/* End of current sb / beginning of next sb. */
-
-	/* Variables for uncompressed data / destination. */
-	struct page *dp;	/* Current destination page being worked on. */
-	u8 *dp_addr;		/* Current pointer into dp. */
-	u8 *dp_sb_start;	/* Start of current sub-block in dp. */
-	u8 *dp_sb_end;		/* End of current sb in dp (dp_sb_start +
-				   NTFS_SB_SIZE). */
-	u16 do_sb_start;	/* @dest_ofs when starting this sub-block. */
-	u16 do_sb_end;		/* @dest_ofs of end of this sb (do_sb_start +
-				   NTFS_SB_SIZE). */
-
-	/* Variables for tag and token parsing. */
-	u8 tag;			/* Current tag. */
-	int token;		/* Loop counter for the eight tokens in tag. */
-	int nr_completed_pages = 0;
-
-	/* Default error code. */
-	int err = -EOVERFLOW;
-
-	ntfs_debug("Entering, cb_size = 0x%x.", cb_size);
-do_next_sb:
-	ntfs_debug("Beginning sub-block at offset = 0x%zx in the cb.",
-			cb - cb_start);
-	/*
-	 * Have we reached the end of the compression block or the end of the
-	 * decompressed data?  The latter can happen for example if the current
-	 * position in the compression block is one byte before its end so the
-	 * first two checks do not detect it.
-	 */
-	if (cb == cb_end || !le16_to_cpup((le16*)cb) ||
-			(*dest_index == dest_max_index &&
-			*dest_ofs == dest_max_ofs)) {
-		int i;
-
-		ntfs_debug("Completed. Returning success (0).");
-		err = 0;
-return_error:
-		/* We can sleep from now on, so we drop lock. */
-		spin_unlock(&ntfs_cb_lock);
-		/* Second stage: finalize completed pages. */
-		if (nr_completed_pages > 0) {
-			for (i = 0; i < nr_completed_pages; i++) {
-				int di = completed_pages[i];
-
-				dp = dest_pages[di];
-				/*
-				 * If we are outside the initialized size, zero
-				 * the out of bounds page range.
-				 */
-				handle_bounds_compressed_page(dp, i_size,
-						initialized_size);
-				flush_dcache_page(dp);
-				kunmap(dp);
-				SetPageUptodate(dp);
-				unlock_page(dp);
-				if (di == xpage)
-					*xpage_done = 1;
-				else
-					put_page(dp);
-				dest_pages[di] = NULL;
-			}
-		}
-		return err;
-	}
-
-	/* Setup offsets for the current sub-block destination. */
-	do_sb_start = *dest_ofs;
-	do_sb_end = do_sb_start + NTFS_SB_SIZE;
-
-	/* Check that we are still within allowed boundaries. */
-	if (*dest_index == dest_max_index && do_sb_end > dest_max_ofs)
-		goto return_overflow;
-
-	/* Does the minimum size of a compressed sb overflow valid range? */
-	if (cb + 6 > cb_end)
-		goto return_overflow;
-
-	/* Setup the current sub-block source pointers and validate range. */
-	cb_sb_start = cb;
-	cb_sb_end = cb_sb_start + (le16_to_cpup((le16*)cb) & NTFS_SB_SIZE_MASK)
-			+ 3;
-	if (cb_sb_end > cb_end)
-		goto return_overflow;
-
-	/* Get the current destination page. */
-	dp = dest_pages[*dest_index];
-	if (!dp) {
-		/* No page present. Skip decompression of this sub-block. */
-		cb = cb_sb_end;
-
-		/* Advance destination position to next sub-block. */
-		*dest_ofs = (*dest_ofs + NTFS_SB_SIZE) & ~PAGE_MASK;
-		if (!*dest_ofs && (++*dest_index > dest_max_index))
-			goto return_overflow;
-		goto do_next_sb;
-	}
-
-	/* We have a valid destination page. Setup the destination pointers. */
-	dp_addr = (u8*)page_address(dp) + do_sb_start;
-
-	/* Now, we are ready to process the current sub-block (sb). */
-	if (!(le16_to_cpup((le16*)cb) & NTFS_SB_IS_COMPRESSED)) {
-		ntfs_debug("Found uncompressed sub-block.");
-		/* This sb is not compressed, just copy it into destination. */
-
-		/* Advance source position to first data byte. */
-		cb += 2;
-
-		/* An uncompressed sb must be full size. */
-		if (cb_sb_end - cb != NTFS_SB_SIZE)
-			goto return_overflow;
-
-		/* Copy the block and advance the source position. */
-		memcpy(dp_addr, cb, NTFS_SB_SIZE);
-		cb += NTFS_SB_SIZE;
-
-		/* Advance destination position to next sub-block. */
-		*dest_ofs += NTFS_SB_SIZE;
-		if (!(*dest_ofs &= ~PAGE_MASK)) {
-finalize_page:
-			/*
-			 * First stage: add current page index to array of
-			 * completed pages.
-			 */
-			completed_pages[nr_completed_pages++] = *dest_index;
-			if (++*dest_index > dest_max_index)
-				goto return_overflow;
-		}
-		goto do_next_sb;
-	}
-	ntfs_debug("Found compressed sub-block.");
-	/* This sb is compressed, decompress it into destination. */
-
-	/* Setup destination pointers. */
-	dp_sb_start = dp_addr;
-	dp_sb_end = dp_sb_start + NTFS_SB_SIZE;
-
-	/* Forward to the first tag in the sub-block. */
-	cb += 2;
-do_next_tag:
-	if (cb == cb_sb_end) {
-		/* Check if the decompressed sub-block was not full-length. */
-		if (dp_addr < dp_sb_end) {
-			int nr_bytes = do_sb_end - *dest_ofs;
-
-			ntfs_debug("Filling incomplete sub-block with "
-					"zeroes.");
-			/* Zero remainder and update destination position. */
-			memset(dp_addr, 0, nr_bytes);
-			*dest_ofs += nr_bytes;
-		}
-		/* We have finished the current sub-block. */
-		if (!(*dest_ofs &= ~PAGE_MASK))
-			goto finalize_page;
-		goto do_next_sb;
-	}
-
-	/* Check we are still in range. */
-	if (cb > cb_sb_end || dp_addr > dp_sb_end)
-		goto return_overflow;
-
-	/* Get the next tag and advance to first token. */
-	tag = *cb++;
-
-	/* Parse the eight tokens described by the tag. */
-	for (token = 0; token < 8; token++, tag >>= 1) {
-		u16 lg, pt, length, max_non_overlap;
-		register u16 i;
-		u8 *dp_back_addr;
-
-		/* Check if we are done / still in range. */
-		if (cb >= cb_sb_end || dp_addr > dp_sb_end)
-			break;
-
-		/* Determine token type and parse appropriately.*/
-		if ((tag & NTFS_TOKEN_MASK) == NTFS_SYMBOL_TOKEN) {
-			/*
-			 * We have a symbol token, copy the symbol across, and
-			 * advance the source and destination positions.
-			 */
-			*dp_addr++ = *cb++;
-			++*dest_ofs;
-
-			/* Continue with the next token. */
-			continue;
-		}
-
-		/*
-		 * We have a phrase token. Make sure it is not the first tag in
-		 * the sb as this is illegal and would confuse the code below.
-		 */
-		if (dp_addr == dp_sb_start)
-			goto return_overflow;
-
-		/*
-		 * Determine the number of bytes to go back (p) and the number
-		 * of bytes to copy (l). We use an optimized algorithm in which
-		 * we first calculate log2(current destination position in sb),
-		 * which allows determination of l and p in O(1) rather than
-		 * O(n). We just need an arch-optimized log2() function now.
-		 */
-		lg = 0;
-		for (i = *dest_ofs - do_sb_start - 1; i >= 0x10; i >>= 1)
-			lg++;
-
-		/* Get the phrase token into i. */
-		pt = le16_to_cpup((le16*)cb);
-
-		/*
-		 * Calculate starting position of the byte sequence in
-		 * the destination using the fact that p = (pt >> (12 - lg)) + 1
-		 * and make sure we don't go too far back.
-		 */
-		dp_back_addr = dp_addr - (pt >> (12 - lg)) - 1;
-		if (dp_back_addr < dp_sb_start)
-			goto return_overflow;
-
-		/* Now calculate the length of the byte sequence. */
-		length = (pt & (0xfff >> lg)) + 3;
-
-		/* Advance destination position and verify it is in range. */
-		*dest_ofs += length;
-		if (*dest_ofs > do_sb_end)
-			goto return_overflow;
-
-		/* The number of non-overlapping bytes. */
-		max_non_overlap = dp_addr - dp_back_addr;
-
-		if (length <= max_non_overlap) {
-			/* The byte sequence doesn't overlap, just copy it. */
-			memcpy(dp_addr, dp_back_addr, length);
-
-			/* Advance destination pointer. */
-			dp_addr += length;
-		} else {
-			/*
-			 * The byte sequence does overlap, copy non-overlapping
-			 * part and then do a slow byte by byte copy for the
-			 * overlapping part. Also, advance the destination
-			 * pointer.
-			 */
-			memcpy(dp_addr, dp_back_addr, max_non_overlap);
-			dp_addr += max_non_overlap;
-			dp_back_addr += max_non_overlap;
-			length -= max_non_overlap;
-			while (length--)
-				*dp_addr++ = *dp_back_addr++;
-		}
-
-		/* Advance source position and continue with the next token. */
-		cb += 2;
-	}
-
-	/* No tokens left in the current tag. Continue with the next tag. */
-	goto do_next_tag;
-
-return_overflow:
-	ntfs_error(NULL, "Failed. Returning -EOVERFLOW.");
-	goto return_error;
-}
-
-/**
- * ntfs_read_compressed_block - read a compressed block into the page cache
- * @page:	locked page in the compression block(s) we need to read
- *
- * When we are called the page has already been verified to be locked and the
- * attribute is known to be non-resident, not encrypted, but compressed.
- *
- * 1. Determine which compression block(s) @page is in.
- * 2. Get hold of all pages corresponding to this/these compression block(s).
- * 3. Read the (first) compression block.
- * 4. Decompress it into the corresponding pages.
- * 5. Throw the compressed data away and proceed to 3. for the next compression
- *    block or return success if no more compression blocks left.
- *
- * Warning: We have to be careful what we do about existing pages. They might
- * have been written to so that we would lose data if we were to just overwrite
- * them with the out-of-date uncompressed data.
- *
- * FIXME: For PAGE_SIZE > cb_size we are not doing the Right Thing(TM) at
- * the end of the file I think. We need to detect this case and zero the out
- * of bounds remainder of the page in question and mark it as handled. At the
- * moment we would just return -EIO on such a page. This bug will only become
- * apparent if pages are above 8kiB and the NTFS volume only uses 512 byte
- * clusters so is probably not going to be seen by anyone. Still this should
- * be fixed. (AIA)
- *
- * FIXME: Again for PAGE_SIZE > cb_size we are screwing up both in
- * handling sparse and compressed cbs. (AIA)
- *
- * FIXME: At the moment we don't do any zeroing out in the case that
- * initialized_size is less than data_size. This should be safe because of the
- * nature of the compression algorithm used. Just in case we check and output
- * an error message in read inode if the two sizes are not equal for a
- * compressed file. (AIA)
- */
-int ntfs_read_compressed_block(struct page *page)
-{
-	loff_t i_size;
-	s64 initialized_size;
-	struct address_space *mapping = page->mapping;
-	ntfs_inode *ni = NTFS_I(mapping->host);
-	ntfs_volume *vol = ni->vol;
-	struct super_block *sb = vol->sb;
-	runlist_element *rl;
-	unsigned long flags, block_size = sb->s_blocksize;
-	unsigned char block_size_bits = sb->s_blocksize_bits;
-	u8 *cb, *cb_pos, *cb_end;
-	struct buffer_head **bhs;
-	unsigned long offset, index = page->index;
-	u32 cb_size = ni->itype.compressed.block_size;
-	u64 cb_size_mask = cb_size - 1UL;
-	VCN vcn;
-	LCN lcn;
-	/* The first wanted vcn (minimum alignment is PAGE_SIZE). */
-	VCN start_vcn = (((s64)index << PAGE_SHIFT) & ~cb_size_mask) >>
-			vol->cluster_size_bits;
-	/*
-	 * The first vcn after the last wanted vcn (minimum alignment is again
-	 * PAGE_SIZE.
-	 */
-	VCN end_vcn = ((((s64)(index + 1UL) << PAGE_SHIFT) + cb_size - 1)
-			& ~cb_size_mask) >> vol->cluster_size_bits;
-	/* Number of compression blocks (cbs) in the wanted vcn range. */
-	unsigned int nr_cbs = (end_vcn - start_vcn) << vol->cluster_size_bits
-			>> ni->itype.compressed.block_size_bits;
-	/*
-	 * Number of pages required to store the uncompressed data from all
-	 * compression blocks (cbs) overlapping @page. Due to alignment
-	 * guarantees of start_vcn and end_vcn, no need to round up here.
-	 */
-	unsigned int nr_pages = (end_vcn - start_vcn) <<
-			vol->cluster_size_bits >> PAGE_SHIFT;
-	unsigned int xpage, max_page, cur_page, cur_ofs, i;
-	unsigned int cb_clusters, cb_max_ofs;
-	int block, max_block, cb_max_page, bhs_size, nr_bhs, err = 0;
-	struct page **pages;
-	int *completed_pages;
-	unsigned char xpage_done = 0;
-
-	ntfs_debug("Entering, page->index = 0x%lx, cb_size = 0x%x, nr_pages = "
-			"%i.", index, cb_size, nr_pages);
-	/*
-	 * Bad things happen if we get here for anything that is not an
-	 * unnamed $DATA attribute.
-	 */
-	BUG_ON(ni->type != AT_DATA);
-	BUG_ON(ni->name_len);
-
-	pages = kmalloc_array(nr_pages, sizeof(struct page *), GFP_NOFS);
-	completed_pages = kmalloc_array(nr_pages + 1, sizeof(int), GFP_NOFS);
-
-	/* Allocate memory to store the buffer heads we need. */
-	bhs_size = cb_size / block_size * sizeof(struct buffer_head *);
-	bhs = kmalloc(bhs_size, GFP_NOFS);
-
-	if (unlikely(!pages || !bhs || !completed_pages)) {
-		kfree(bhs);
-		kfree(pages);
-		kfree(completed_pages);
-		unlock_page(page);
-		ntfs_error(vol->sb, "Failed to allocate internal buffers.");
-		return -ENOMEM;
-	}
-
-	/*
-	 * We have already been given one page, this is the one we must do.
-	 * Once again, the alignment guarantees keep it simple.
-	 */
-	offset = start_vcn << vol->cluster_size_bits >> PAGE_SHIFT;
-	xpage = index - offset;
-	pages[xpage] = page;
-	/*
-	 * The remaining pages need to be allocated and inserted into the page
-	 * cache, alignment guarantees keep all the below much simpler. (-8
-	 */
-	read_lock_irqsave(&ni->size_lock, flags);
-	i_size = i_size_read(VFS_I(ni));
-	initialized_size = ni->initialized_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	max_page = ((i_size + PAGE_SIZE - 1) >> PAGE_SHIFT) -
-			offset;
-	/* Is the page fully outside i_size? (truncate in progress) */
-	if (xpage >= max_page) {
-		kfree(bhs);
-		kfree(pages);
-		kfree(completed_pages);
-		zero_user(page, 0, PAGE_SIZE);
-		ntfs_debug("Compressed read outside i_size - truncated?");
-		SetPageUptodate(page);
-		unlock_page(page);
-		return 0;
-	}
-	if (nr_pages < max_page)
-		max_page = nr_pages;
-	for (i = 0; i < max_page; i++, offset++) {
-		if (i != xpage)
-			pages[i] = grab_cache_page_nowait(mapping, offset);
-		page = pages[i];
-		if (page) {
-			/*
-			 * We only (re)read the page if it isn't already read
-			 * in and/or dirty or we would be losing data or at
-			 * least wasting our time.
-			 */
-			if (!PageDirty(page) && (!PageUptodate(page) ||
-					PageError(page))) {
-				ClearPageError(page);
-				kmap(page);
-				continue;
-			}
-			unlock_page(page);
-			put_page(page);
-			pages[i] = NULL;
-		}
-	}
-
-	/*
-	 * We have the runlist, and all the destination pages we need to fill.
-	 * Now read the first compression block.
-	 */
-	cur_page = 0;
-	cur_ofs = 0;
-	cb_clusters = ni->itype.compressed.block_clusters;
-do_next_cb:
-	nr_cbs--;
-	nr_bhs = 0;
-
-	/* Read all cb buffer heads one cluster at a time. */
-	rl = NULL;
-	for (vcn = start_vcn, start_vcn += cb_clusters; vcn < start_vcn;
-			vcn++) {
-		bool is_retry = false;
-
-		if (!rl) {
-lock_retry_remap:
-			down_read(&ni->runlist.lock);
-			rl = ni->runlist.rl;
-		}
-		if (likely(rl != NULL)) {
-			/* Seek to element containing target vcn. */
-			while (rl->length && rl[1].vcn <= vcn)
-				rl++;
-			lcn = ntfs_rl_vcn_to_lcn(rl, vcn);
-		} else
-			lcn = LCN_RL_NOT_MAPPED;
-		ntfs_debug("Reading vcn = 0x%llx, lcn = 0x%llx.",
-				(unsigned long long)vcn,
-				(unsigned long long)lcn);
-		if (lcn < 0) {
-			/*
-			 * When we reach the first sparse cluster we have
-			 * finished with the cb.
-			 */
-			if (lcn == LCN_HOLE)
-				break;
-			if (is_retry || lcn != LCN_RL_NOT_MAPPED)
-				goto rl_err;
-			is_retry = true;
-			/*
-			 * Attempt to map runlist, dropping lock for the
-			 * duration.
-			 */
-			up_read(&ni->runlist.lock);
-			if (!ntfs_map_runlist(ni, vcn))
-				goto lock_retry_remap;
-			goto map_rl_err;
-		}
-		block = lcn << vol->cluster_size_bits >> block_size_bits;
-		/* Read the lcn from device in chunks of block_size bytes. */
-		max_block = block + (vol->cluster_size >> block_size_bits);
-		do {
-			ntfs_debug("block = 0x%x.", block);
-			if (unlikely(!(bhs[nr_bhs] = sb_getblk(sb, block))))
-				goto getblk_err;
-			nr_bhs++;
-		} while (++block < max_block);
-	}
-
-	/* Release the lock if we took it. */
-	if (rl)
-		up_read(&ni->runlist.lock);
-
-	/* Setup and initiate io on all buffer heads. */
-	for (i = 0; i < nr_bhs; i++) {
-		struct buffer_head *tbh = bhs[i];
-
-		if (!trylock_buffer(tbh))
-			continue;
-		if (unlikely(buffer_uptodate(tbh))) {
-			unlock_buffer(tbh);
-			continue;
-		}
-		get_bh(tbh);
-		tbh->b_end_io = end_buffer_read_sync;
-		submit_bh(REQ_OP_READ, tbh);
-	}
-
-	/* Wait for io completion on all buffer heads. */
-	for (i = 0; i < nr_bhs; i++) {
-		struct buffer_head *tbh = bhs[i];
-
-		if (buffer_uptodate(tbh))
-			continue;
-		wait_on_buffer(tbh);
-		/*
-		 * We need an optimization barrier here, otherwise we start
-		 * hitting the below fixup code when accessing a loopback
-		 * mounted ntfs partition. This indicates either there is a
-		 * race condition in the loop driver or, more likely, gcc
-		 * overoptimises the code without the barrier and it doesn't
-		 * do the Right Thing(TM).
-		 */
-		barrier();
-		if (unlikely(!buffer_uptodate(tbh))) {
-			ntfs_warning(vol->sb, "Buffer is unlocked but not "
-					"uptodate! Unplugging the disk queue "
-					"and rescheduling.");
-			get_bh(tbh);
-			io_schedule();
-			put_bh(tbh);
-			if (unlikely(!buffer_uptodate(tbh)))
-				goto read_err;
-			ntfs_warning(vol->sb, "Buffer is now uptodate. Good.");
-		}
-	}
-
-	/*
-	 * Get the compression buffer. We must not sleep any more
-	 * until we are finished with it.
-	 */
-	spin_lock(&ntfs_cb_lock);
-	cb = ntfs_compression_buffer;
-
-	BUG_ON(!cb);
-
-	cb_pos = cb;
-	cb_end = cb + cb_size;
-
-	/* Copy the buffer heads into the contiguous buffer. */
-	for (i = 0; i < nr_bhs; i++) {
-		memcpy(cb_pos, bhs[i]->b_data, block_size);
-		cb_pos += block_size;
-	}
-
-	/* Just a precaution. */
-	if (cb_pos + 2 <= cb + cb_size)
-		*(u16*)cb_pos = 0;
-
-	/* Reset cb_pos back to the beginning. */
-	cb_pos = cb;
-
-	/* We now have both source (if present) and destination. */
-	ntfs_debug("Successfully read the compression block.");
-
-	/* The last page and maximum offset within it for the current cb. */
-	cb_max_page = (cur_page << PAGE_SHIFT) + cur_ofs + cb_size;
-	cb_max_ofs = cb_max_page & ~PAGE_MASK;
-	cb_max_page >>= PAGE_SHIFT;
-
-	/* Catch end of file inside a compression block. */
-	if (cb_max_page > max_page)
-		cb_max_page = max_page;
-
-	if (vcn == start_vcn - cb_clusters) {
-		/* Sparse cb, zero out page range overlapping the cb. */
-		ntfs_debug("Found sparse compression block.");
-		/* We can sleep from now on, so we drop lock. */
-		spin_unlock(&ntfs_cb_lock);
-		if (cb_max_ofs)
-			cb_max_page--;
-		for (; cur_page < cb_max_page; cur_page++) {
-			page = pages[cur_page];
-			if (page) {
-				if (likely(!cur_ofs))
-					clear_page(page_address(page));
-				else
-					memset(page_address(page) + cur_ofs, 0,
-							PAGE_SIZE -
-							cur_ofs);
-				flush_dcache_page(page);
-				kunmap(page);
-				SetPageUptodate(page);
-				unlock_page(page);
-				if (cur_page == xpage)
-					xpage_done = 1;
-				else
-					put_page(page);
-				pages[cur_page] = NULL;
-			}
-			cb_pos += PAGE_SIZE - cur_ofs;
-			cur_ofs = 0;
-			if (cb_pos >= cb_end)
-				break;
-		}
-		/* If we have a partial final page, deal with it now. */
-		if (cb_max_ofs && cb_pos < cb_end) {
-			page = pages[cur_page];
-			if (page)
-				memset(page_address(page) + cur_ofs, 0,
-						cb_max_ofs - cur_ofs);
-			/*
-			 * No need to update cb_pos at this stage:
-			 *	cb_pos += cb_max_ofs - cur_ofs;
-			 */
-			cur_ofs = cb_max_ofs;
-		}
-	} else if (vcn == start_vcn) {
-		/* We can't sleep so we need two stages. */
-		unsigned int cur2_page = cur_page;
-		unsigned int cur_ofs2 = cur_ofs;
-		u8 *cb_pos2 = cb_pos;
-
-		ntfs_debug("Found uncompressed compression block.");
-		/* Uncompressed cb, copy it to the destination pages. */
-		/*
-		 * TODO: As a big optimization, we could detect this case
-		 * before we read all the pages and use block_read_full_folio()
-		 * on all full pages instead (we still have to treat partial
-		 * pages especially but at least we are getting rid of the
-		 * synchronous io for the majority of pages.
-		 * Or if we choose not to do the read-ahead/-behind stuff, we
-		 * could just return block_read_full_folio(pages[xpage]) as long
-		 * as PAGE_SIZE <= cb_size.
-		 */
-		if (cb_max_ofs)
-			cb_max_page--;
-		/* First stage: copy data into destination pages. */
-		for (; cur_page < cb_max_page; cur_page++) {
-			page = pages[cur_page];
-			if (page)
-				memcpy(page_address(page) + cur_ofs, cb_pos,
-						PAGE_SIZE - cur_ofs);
-			cb_pos += PAGE_SIZE - cur_ofs;
-			cur_ofs = 0;
-			if (cb_pos >= cb_end)
-				break;
-		}
-		/* If we have a partial final page, deal with it now. */
-		if (cb_max_ofs && cb_pos < cb_end) {
-			page = pages[cur_page];
-			if (page)
-				memcpy(page_address(page) + cur_ofs, cb_pos,
-						cb_max_ofs - cur_ofs);
-			cb_pos += cb_max_ofs - cur_ofs;
-			cur_ofs = cb_max_ofs;
-		}
-		/* We can sleep from now on, so drop lock. */
-		spin_unlock(&ntfs_cb_lock);
-		/* Second stage: finalize pages. */
-		for (; cur2_page < cb_max_page; cur2_page++) {
-			page = pages[cur2_page];
-			if (page) {
-				/*
-				 * If we are outside the initialized size, zero
-				 * the out of bounds page range.
-				 */
-				handle_bounds_compressed_page(page, i_size,
-						initialized_size);
-				flush_dcache_page(page);
-				kunmap(page);
-				SetPageUptodate(page);
-				unlock_page(page);
-				if (cur2_page == xpage)
-					xpage_done = 1;
-				else
-					put_page(page);
-				pages[cur2_page] = NULL;
-			}
-			cb_pos2 += PAGE_SIZE - cur_ofs2;
-			cur_ofs2 = 0;
-			if (cb_pos2 >= cb_end)
-				break;
-		}
-	} else {
-		/* Compressed cb, decompress it into the destination page(s). */
-		unsigned int prev_cur_page = cur_page;
-
-		ntfs_debug("Found compressed compression block.");
-		err = ntfs_decompress(pages, completed_pages, &cur_page,
-				&cur_ofs, cb_max_page, cb_max_ofs, xpage,
-				&xpage_done, cb_pos, cb_size - (cb_pos - cb),
-				i_size, initialized_size);
-		/*
-		 * We can sleep from now on, lock already dropped by
-		 * ntfs_decompress().
-		 */
-		if (err) {
-			ntfs_error(vol->sb, "ntfs_decompress() failed in inode "
-					"0x%lx with error code %i. Skipping "
-					"this compression block.",
-					ni->mft_no, -err);
-			/* Release the unfinished pages. */
-			for (; prev_cur_page < cur_page; prev_cur_page++) {
-				page = pages[prev_cur_page];
-				if (page) {
-					flush_dcache_page(page);
-					kunmap(page);
-					unlock_page(page);
-					if (prev_cur_page != xpage)
-						put_page(page);
-					pages[prev_cur_page] = NULL;
-				}
-			}
-		}
-	}
-
-	/* Release the buffer heads. */
-	for (i = 0; i < nr_bhs; i++)
-		brelse(bhs[i]);
-
-	/* Do we have more work to do? */
-	if (nr_cbs)
-		goto do_next_cb;
-
-	/* We no longer need the list of buffer heads. */
-	kfree(bhs);
-
-	/* Clean up if we have any pages left. Should never happen. */
-	for (cur_page = 0; cur_page < max_page; cur_page++) {
-		page = pages[cur_page];
-		if (page) {
-			ntfs_error(vol->sb, "Still have pages left! "
-					"Terminating them with extreme "
-					"prejudice.  Inode 0x%lx, page index "
-					"0x%lx.", ni->mft_no, page->index);
-			flush_dcache_page(page);
-			kunmap(page);
-			unlock_page(page);
-			if (cur_page != xpage)
-				put_page(page);
-			pages[cur_page] = NULL;
-		}
-	}
-
-	/* We no longer need the list of pages. */
-	kfree(pages);
-	kfree(completed_pages);
-
-	/* If we have completed the requested page, we return success. */
-	if (likely(xpage_done))
-		return 0;
-
-	ntfs_debug("Failed. Returning error code %s.", err == -EOVERFLOW ?
-			"EOVERFLOW" : (!err ? "EIO" : "unknown error"));
-	return err < 0 ? err : -EIO;
-
-read_err:
-	ntfs_error(vol->sb, "IO error while reading compressed data.");
-	/* Release the buffer heads. */
-	for (i = 0; i < nr_bhs; i++)
-		brelse(bhs[i]);
-	goto err_out;
-
-map_rl_err:
-	ntfs_error(vol->sb, "ntfs_map_runlist() failed. Cannot read "
-			"compression block.");
-	goto err_out;
-
-rl_err:
-	up_read(&ni->runlist.lock);
-	ntfs_error(vol->sb, "ntfs_rl_vcn_to_lcn() failed. Cannot read "
-			"compression block.");
-	goto err_out;
-
-getblk_err:
-	up_read(&ni->runlist.lock);
-	ntfs_error(vol->sb, "getblk() failed. Cannot read compression block.");
-
-err_out:
-	kfree(bhs);
-	for (i = cur_page; i < max_page; i++) {
-		page = pages[i];
-		if (page) {
-			flush_dcache_page(page);
-			kunmap(page);
-			unlock_page(page);
-			if (i != xpage)
-				put_page(page);
-		}
-	}
-	kfree(pages);
-	kfree(completed_pages);
-	return -EIO;
-}
diff --git a/fs/ntfs/debug.c b/fs/ntfs/debug.c
deleted file mode 100644
index a3c1c5656f8f..000000000000
--- a/fs/ntfs/debug.c
+++ /dev/null
@@ -1,159 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * debug.c - NTFS kernel debug support. Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2004 Anton Altaparmakov
- */
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include "debug.h"
-
-/**
- * __ntfs_warning - output a warning to the syslog
- * @function:	name of function outputting the warning
- * @sb:		super block of mounted ntfs filesystem
- * @fmt:	warning string containing format specifications
- * @...:	a variable number of arguments specified in @fmt
- *
- * Outputs a warning to the syslog for the mounted ntfs filesystem described
- * by @sb.
- *
- * @fmt and the corresponding @... is printf style format string containing
- * the warning string and the corresponding format arguments, respectively.
- *
- * @function is the name of the function from which __ntfs_warning is being
- * called.
- *
- * Note, you should be using debug.h::ntfs_warning(@sb, @fmt, @...) instead
- * as this provides the @function parameter automatically.
- */
-void __ntfs_warning(const char *function, const struct super_block *sb,
-		const char *fmt, ...)
-{
-	struct va_format vaf;
-	va_list args;
-	int flen = 0;
-
-#ifndef DEBUG
-	if (!printk_ratelimit())
-		return;
-#endif
-	if (function)
-		flen = strlen(function);
-	va_start(args, fmt);
-	vaf.fmt = fmt;
-	vaf.va = &args;
-	if (sb)
-		pr_warn("(device %s): %s(): %pV\n",
-			sb->s_id, flen ? function : "", &vaf);
-	else
-		pr_warn("%s(): %pV\n", flen ? function : "", &vaf);
-	va_end(args);
-}
-
-/**
- * __ntfs_error - output an error to the syslog
- * @function:	name of function outputting the error
- * @sb:		super block of mounted ntfs filesystem
- * @fmt:	error string containing format specifications
- * @...:	a variable number of arguments specified in @fmt
- *
- * Outputs an error to the syslog for the mounted ntfs filesystem described
- * by @sb.
- *
- * @fmt and the corresponding @... is printf style format string containing
- * the error string and the corresponding format arguments, respectively.
- *
- * @function is the name of the function from which __ntfs_error is being
- * called.
- *
- * Note, you should be using debug.h::ntfs_error(@sb, @fmt, @...) instead
- * as this provides the @function parameter automatically.
- */
-void __ntfs_error(const char *function, const struct super_block *sb,
-		const char *fmt, ...)
-{
-	struct va_format vaf;
-	va_list args;
-	int flen = 0;
-
-#ifndef DEBUG
-	if (!printk_ratelimit())
-		return;
-#endif
-	if (function)
-		flen = strlen(function);
-	va_start(args, fmt);
-	vaf.fmt = fmt;
-	vaf.va = &args;
-	if (sb)
-		pr_err("(device %s): %s(): %pV\n",
-		       sb->s_id, flen ? function : "", &vaf);
-	else
-		pr_err("%s(): %pV\n", flen ? function : "", &vaf);
-	va_end(args);
-}
-
-#ifdef DEBUG
-
-/* If 1, output debug messages, and if 0, don't. */
-int debug_msgs = 0;
-
-void __ntfs_debug(const char *file, int line, const char *function,
-		const char *fmt, ...)
-{
-	struct va_format vaf;
-	va_list args;
-	int flen = 0;
-
-	if (!debug_msgs)
-		return;
-	if (function)
-		flen = strlen(function);
-	va_start(args, fmt);
-	vaf.fmt = fmt;
-	vaf.va = &args;
-	pr_debug("(%s, %d): %s(): %pV", file, line, flen ? function : "", &vaf);
-	va_end(args);
-}
-
-/* Dump a runlist. Caller has to provide synchronisation for @rl. */
-void ntfs_debug_dump_runlist(const runlist_element *rl)
-{
-	int i;
-	const char *lcn_str[5] = { "LCN_HOLE         ", "LCN_RL_NOT_MAPPED",
-				   "LCN_ENOENT       ", "LCN_unknown      " };
-
-	if (!debug_msgs)
-		return;
-	pr_debug("Dumping runlist (values in hex):\n");
-	if (!rl) {
-		pr_debug("Run list not present.\n");
-		return;
-	}
-	pr_debug("VCN              LCN               Run length\n");
-	for (i = 0; ; i++) {
-		LCN lcn = (rl + i)->lcn;
-
-		if (lcn < (LCN)0) {
-			int index = -lcn - 1;
-
-			if (index > -LCN_ENOENT - 1)
-				index = 3;
-			pr_debug("%-16Lx %s %-16Lx%s\n",
-					(long long)(rl + i)->vcn, lcn_str[index],
-					(long long)(rl + i)->length,
-					(rl + i)->length ? "" :
-						" (runlist end)");
-		} else
-			pr_debug("%-16Lx %-16Lx  %-16Lx%s\n",
-					(long long)(rl + i)->vcn,
-					(long long)(rl + i)->lcn,
-					(long long)(rl + i)->length,
-					(rl + i)->length ? "" :
-						" (runlist end)");
-		if (!(rl + i)->length)
-			break;
-	}
-}
-
-#endif
diff --git a/fs/ntfs/debug.h b/fs/ntfs/debug.h
deleted file mode 100644
index 6fdef388f129..000000000000
--- a/fs/ntfs/debug.h
+++ /dev/null
@@ -1,57 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * debug.h - NTFS kernel debug support. Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2004 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_DEBUG_H
-#define _LINUX_NTFS_DEBUG_H
-
-#include <linux/fs.h>
-
-#include "runlist.h"
-
-#ifdef DEBUG
-
-extern int debug_msgs;
-
-extern __printf(4, 5)
-void __ntfs_debug(const char *file, int line, const char *function,
-		  const char *format, ...);
-/**
- * ntfs_debug - write a debug level message to syslog
- * @f:		a printf format string containing the message
- * @...:	the variables to substitute into @f
- *
- * ntfs_debug() writes a DEBUG level message to the syslog but only if the
- * driver was compiled with -DDEBUG. Otherwise, the call turns into a NOP.
- */
-#define ntfs_debug(f, a...)						\
-	__ntfs_debug(__FILE__, __LINE__, __func__, f, ##a)
-
-extern void ntfs_debug_dump_runlist(const runlist_element *rl);
-
-#else	/* !DEBUG */
-
-#define ntfs_debug(fmt, ...)						\
-do {									\
-	if (0)								\
-		no_printk(fmt, ##__VA_ARGS__);				\
-} while (0)
-
-#define ntfs_debug_dump_runlist(rl)	do {} while (0)
-
-#endif	/* !DEBUG */
-
-extern  __printf(3, 4)
-void __ntfs_warning(const char *function, const struct super_block *sb,
-		    const char *fmt, ...);
-#define ntfs_warning(sb, f, a...)	__ntfs_warning(__func__, sb, f, ##a)
-
-extern  __printf(3, 4)
-void __ntfs_error(const char *function, const struct super_block *sb,
-		  const char *fmt, ...);
-#define ntfs_error(sb, f, a...)		__ntfs_error(__func__, sb, f, ##a)
-
-#endif /* _LINUX_NTFS_DEBUG_H */
diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c
deleted file mode 100644
index 629723a8d712..000000000000
--- a/fs/ntfs/dir.c
+++ /dev/null
@@ -1,1540 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * dir.c - NTFS kernel directory operations. Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2007 Anton Altaparmakov
- * Copyright (c) 2002 Richard Russon
- */
-
-#include <linux/buffer_head.h>
-#include <linux/slab.h>
-#include <linux/blkdev.h>
-
-#include "dir.h"
-#include "aops.h"
-#include "attrib.h"
-#include "mft.h"
-#include "debug.h"
-#include "ntfs.h"
-
-/*
- * The little endian Unicode string $I30 as a global constant.
- */
-ntfschar I30[5] = { cpu_to_le16('$'), cpu_to_le16('I'),
-		cpu_to_le16('3'),	cpu_to_le16('0'), 0 };
-
-/**
- * ntfs_lookup_inode_by_name - find an inode in a directory given its name
- * @dir_ni:	ntfs inode of the directory in which to search for the name
- * @uname:	Unicode name for which to search in the directory
- * @uname_len:	length of the name @uname in Unicode characters
- * @res:	return the found file name if necessary (see below)
- *
- * Look for an inode with name @uname in the directory with inode @dir_ni.
- * ntfs_lookup_inode_by_name() walks the contents of the directory looking for
- * the Unicode name. If the name is found in the directory, the corresponding
- * inode number (>= 0) is returned as a mft reference in cpu format, i.e. it
- * is a 64-bit number containing the sequence number.
- *
- * On error, a negative value is returned corresponding to the error code. In
- * particular if the inode is not found -ENOENT is returned. Note that you
- * can't just check the return value for being negative, you have to check the
- * inode number for being negative which you can extract using MREC(return
- * value).
- *
- * Note, @uname_len does not include the (optional) terminating NULL character.
- *
- * Note, we look for a case sensitive match first but we also look for a case
- * insensitive match at the same time. If we find a case insensitive match, we
- * save that for the case that we don't find an exact match, where we return
- * the case insensitive match and setup @res (which we allocate!) with the mft
- * reference, the file name type, length and with a copy of the little endian
- * Unicode file name itself. If we match a file name which is in the DOS name
- * space, we only return the mft reference and file name type in @res.
- * ntfs_lookup() then uses this to find the long file name in the inode itself.
- * This is to avoid polluting the dcache with short file names. We want them to
- * work but we don't care for how quickly one can access them. This also fixes
- * the dcache aliasing issues.
- *
- * Locking:  - Caller must hold i_mutex on the directory.
- *	     - Each page cache page in the index allocation mapping must be
- *	       locked whilst being accessed otherwise we may find a corrupt
- *	       page due to it being under ->writepage at the moment which
- *	       applies the mst protection fixups before writing out and then
- *	       removes them again after the write is complete after which it 
- *	       unlocks the page.
- */
-MFT_REF ntfs_lookup_inode_by_name(ntfs_inode *dir_ni, const ntfschar *uname,
-		const int uname_len, ntfs_name **res)
-{
-	ntfs_volume *vol = dir_ni->vol;
-	struct super_block *sb = vol->sb;
-	MFT_RECORD *m;
-	INDEX_ROOT *ir;
-	INDEX_ENTRY *ie;
-	INDEX_ALLOCATION *ia;
-	u8 *index_end;
-	u64 mref;
-	ntfs_attr_search_ctx *ctx;
-	int err, rc;
-	VCN vcn, old_vcn;
-	struct address_space *ia_mapping;
-	struct page *page;
-	u8 *kaddr;
-	ntfs_name *name = NULL;
-
-	BUG_ON(!S_ISDIR(VFS_I(dir_ni)->i_mode));
-	BUG_ON(NInoAttr(dir_ni));
-	/* Get hold of the mft record for the directory. */
-	m = map_mft_record(dir_ni);
-	if (IS_ERR(m)) {
-		ntfs_error(sb, "map_mft_record() failed with error code %ld.",
-				-PTR_ERR(m));
-		return ERR_MREF(PTR_ERR(m));
-	}
-	ctx = ntfs_attr_get_search_ctx(dir_ni, m);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	/* Find the index root attribute in the mft record. */
-	err = ntfs_attr_lookup(AT_INDEX_ROOT, I30, 4, CASE_SENSITIVE, 0, NULL,
-			0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT) {
-			ntfs_error(sb, "Index root attribute missing in "
-					"directory inode 0x%lx.",
-					dir_ni->mft_no);
-			err = -EIO;
-		}
-		goto err_out;
-	}
-	/* Get to the index root value (it's been verified in read_inode). */
-	ir = (INDEX_ROOT*)((u8*)ctx->attr +
-			le16_to_cpu(ctx->attr->data.resident.value_offset));
-	index_end = (u8*)&ir->index + le32_to_cpu(ir->index.index_length);
-	/* The first index entry. */
-	ie = (INDEX_ENTRY*)((u8*)&ir->index +
-			le32_to_cpu(ir->index.entries_offset));
-	/*
-	 * Loop until we exceed valid memory (corruption case) or until we
-	 * reach the last entry.
-	 */
-	for (;; ie = (INDEX_ENTRY*)((u8*)ie + le16_to_cpu(ie->length))) {
-		/* Bounds checks. */
-		if ((u8*)ie < (u8*)ctx->mrec || (u8*)ie +
-				sizeof(INDEX_ENTRY_HEADER) > index_end ||
-				(u8*)ie + le16_to_cpu(ie->key_length) >
-				index_end)
-			goto dir_err_out;
-		/*
-		 * The last entry cannot contain a name. It can however contain
-		 * a pointer to a child node in the B+tree so we just break out.
-		 */
-		if (ie->flags & INDEX_ENTRY_END)
-			break;
-		/*
-		 * We perform a case sensitive comparison and if that matches
-		 * we are done and return the mft reference of the inode (i.e.
-		 * the inode number together with the sequence number for
-		 * consistency checking). We convert it to cpu format before
-		 * returning.
-		 */
-		if (ntfs_are_names_equal(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length,
-				CASE_SENSITIVE, vol->upcase, vol->upcase_len)) {
-found_it:
-			/*
-			 * We have a perfect match, so we don't need to care
-			 * about having matched imperfectly before, so we can
-			 * free name and set *res to NULL.
-			 * However, if the perfect match is a short file name,
-			 * we need to signal this through *res, so that
-			 * ntfs_lookup() can fix dcache aliasing issues.
-			 * As an optimization we just reuse an existing
-			 * allocation of *res.
-			 */
-			if (ie->key.file_name.file_name_type == FILE_NAME_DOS) {
-				if (!name) {
-					name = kmalloc(sizeof(ntfs_name),
-							GFP_NOFS);
-					if (!name) {
-						err = -ENOMEM;
-						goto err_out;
-					}
-				}
-				name->mref = le64_to_cpu(
-						ie->data.dir.indexed_file);
-				name->type = FILE_NAME_DOS;
-				name->len = 0;
-				*res = name;
-			} else {
-				kfree(name);
-				*res = NULL;
-			}
-			mref = le64_to_cpu(ie->data.dir.indexed_file);
-			ntfs_attr_put_search_ctx(ctx);
-			unmap_mft_record(dir_ni);
-			return mref;
-		}
-		/*
-		 * For a case insensitive mount, we also perform a case
-		 * insensitive comparison (provided the file name is not in the
-		 * POSIX namespace). If the comparison matches, and the name is
-		 * in the WIN32 namespace, we cache the filename in *res so
-		 * that the caller, ntfs_lookup(), can work on it. If the
-		 * comparison matches, and the name is in the DOS namespace, we
-		 * only cache the mft reference and the file name type (we set
-		 * the name length to zero for simplicity).
-		 */
-		if (!NVolCaseSensitive(vol) &&
-				ie->key.file_name.file_name_type &&
-				ntfs_are_names_equal(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length,
-				IGNORE_CASE, vol->upcase, vol->upcase_len)) {
-			int name_size = sizeof(ntfs_name);
-			u8 type = ie->key.file_name.file_name_type;
-			u8 len = ie->key.file_name.file_name_length;
-
-			/* Only one case insensitive matching name allowed. */
-			if (name) {
-				ntfs_error(sb, "Found already allocated name "
-						"in phase 1. Please run chkdsk "
-						"and if that doesn't find any "
-						"errors please report you saw "
-						"this message to "
-						"linux-ntfs-dev@lists."
-						"sourceforge.net.");
-				goto dir_err_out;
-			}
-
-			if (type != FILE_NAME_DOS)
-				name_size += len * sizeof(ntfschar);
-			name = kmalloc(name_size, GFP_NOFS);
-			if (!name) {
-				err = -ENOMEM;
-				goto err_out;
-			}
-			name->mref = le64_to_cpu(ie->data.dir.indexed_file);
-			name->type = type;
-			if (type != FILE_NAME_DOS) {
-				name->len = len;
-				memcpy(name->name, ie->key.file_name.file_name,
-						len * sizeof(ntfschar));
-			} else
-				name->len = 0;
-			*res = name;
-		}
-		/*
-		 * Not a perfect match, need to do full blown collation so we
-		 * know which way in the B+tree we have to go.
-		 */
-		rc = ntfs_collate_names(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length, 1,
-				IGNORE_CASE, vol->upcase, vol->upcase_len);
-		/*
-		 * If uname collates before the name of the current entry, there
-		 * is definitely no such name in this index but we might need to
-		 * descend into the B+tree so we just break out of the loop.
-		 */
-		if (rc == -1)
-			break;
-		/* The names are not equal, continue the search. */
-		if (rc)
-			continue;
-		/*
-		 * Names match with case insensitive comparison, now try the
-		 * case sensitive comparison, which is required for proper
-		 * collation.
-		 */
-		rc = ntfs_collate_names(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length, 1,
-				CASE_SENSITIVE, vol->upcase, vol->upcase_len);
-		if (rc == -1)
-			break;
-		if (rc)
-			continue;
-		/*
-		 * Perfect match, this will never happen as the
-		 * ntfs_are_names_equal() call will have gotten a match but we
-		 * still treat it correctly.
-		 */
-		goto found_it;
-	}
-	/*
-	 * We have finished with this index without success. Check for the
-	 * presence of a child node and if not present return -ENOENT, unless
-	 * we have got a matching name cached in name in which case return the
-	 * mft reference associated with it.
-	 */
-	if (!(ie->flags & INDEX_ENTRY_NODE)) {
-		if (name) {
-			ntfs_attr_put_search_ctx(ctx);
-			unmap_mft_record(dir_ni);
-			return name->mref;
-		}
-		ntfs_debug("Entry not found.");
-		err = -ENOENT;
-		goto err_out;
-	} /* Child node present, descend into it. */
-	/* Consistency check: Verify that an index allocation exists. */
-	if (!NInoIndexAllocPresent(dir_ni)) {
-		ntfs_error(sb, "No index allocation attribute but index entry "
-				"requires one. Directory inode 0x%lx is "
-				"corrupt or driver bug.", dir_ni->mft_no);
-		goto err_out;
-	}
-	/* Get the starting vcn of the index_block holding the child node. */
-	vcn = sle64_to_cpup((sle64*)((u8*)ie + le16_to_cpu(ie->length) - 8));
-	ia_mapping = VFS_I(dir_ni)->i_mapping;
-	/*
-	 * We are done with the index root and the mft record. Release them,
-	 * otherwise we deadlock with ntfs_map_page().
-	 */
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(dir_ni);
-	m = NULL;
-	ctx = NULL;
-descend_into_child_node:
-	/*
-	 * Convert vcn to index into the index allocation attribute in units
-	 * of PAGE_SIZE and map the page cache page, reading it from
-	 * disk if necessary.
-	 */
-	page = ntfs_map_page(ia_mapping, vcn <<
-			dir_ni->itype.index.vcn_size_bits >> PAGE_SHIFT);
-	if (IS_ERR(page)) {
-		ntfs_error(sb, "Failed to map directory index page, error %ld.",
-				-PTR_ERR(page));
-		err = PTR_ERR(page);
-		goto err_out;
-	}
-	lock_page(page);
-	kaddr = (u8*)page_address(page);
-fast_descend_into_child_node:
-	/* Get to the index allocation block. */
-	ia = (INDEX_ALLOCATION*)(kaddr + ((vcn <<
-			dir_ni->itype.index.vcn_size_bits) & ~PAGE_MASK));
-	/* Bounds checks. */
-	if ((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_SIZE) {
-		ntfs_error(sb, "Out of bounds check failed. Corrupt directory "
-				"inode 0x%lx or driver bug.", dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	/* Catch multi sector transfer fixup errors. */
-	if (unlikely(!ntfs_is_indx_record(ia->magic))) {
-		ntfs_error(sb, "Directory index record with vcn 0x%llx is "
-				"corrupt.  Corrupt inode 0x%lx.  Run chkdsk.",
-				(unsigned long long)vcn, dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	if (sle64_to_cpu(ia->index_block_vcn) != vcn) {
-		ntfs_error(sb, "Actual VCN (0x%llx) of index buffer is "
-				"different from expected VCN (0x%llx). "
-				"Directory inode 0x%lx is corrupt or driver "
-				"bug.", (unsigned long long)
-				sle64_to_cpu(ia->index_block_vcn),
-				(unsigned long long)vcn, dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	if (le32_to_cpu(ia->index.allocated_size) + 0x18 !=
-			dir_ni->itype.index.block_size) {
-		ntfs_error(sb, "Index buffer (VCN 0x%llx) of directory inode "
-				"0x%lx has a size (%u) differing from the "
-				"directory specified size (%u). Directory "
-				"inode is corrupt or driver bug.",
-				(unsigned long long)vcn, dir_ni->mft_no,
-				le32_to_cpu(ia->index.allocated_size) + 0x18,
-				dir_ni->itype.index.block_size);
-		goto unm_err_out;
-	}
-	index_end = (u8*)ia + dir_ni->itype.index.block_size;
-	if (index_end > kaddr + PAGE_SIZE) {
-		ntfs_error(sb, "Index buffer (VCN 0x%llx) of directory inode "
-				"0x%lx crosses page boundary. Impossible! "
-				"Cannot access! This is probably a bug in the "
-				"driver.", (unsigned long long)vcn,
-				dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	index_end = (u8*)&ia->index + le32_to_cpu(ia->index.index_length);
-	if (index_end > (u8*)ia + dir_ni->itype.index.block_size) {
-		ntfs_error(sb, "Size of index buffer (VCN 0x%llx) of directory "
-				"inode 0x%lx exceeds maximum size.",
-				(unsigned long long)vcn, dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	/* The first index entry. */
-	ie = (INDEX_ENTRY*)((u8*)&ia->index +
-			le32_to_cpu(ia->index.entries_offset));
-	/*
-	 * Iterate similar to above big loop but applied to index buffer, thus
-	 * loop until we exceed valid memory (corruption case) or until we
-	 * reach the last entry.
-	 */
-	for (;; ie = (INDEX_ENTRY*)((u8*)ie + le16_to_cpu(ie->length))) {
-		/* Bounds check. */
-		if ((u8*)ie < (u8*)ia || (u8*)ie +
-				sizeof(INDEX_ENTRY_HEADER) > index_end ||
-				(u8*)ie + le16_to_cpu(ie->key_length) >
-				index_end) {
-			ntfs_error(sb, "Index entry out of bounds in "
-					"directory inode 0x%lx.",
-					dir_ni->mft_no);
-			goto unm_err_out;
-		}
-		/*
-		 * The last entry cannot contain a name. It can however contain
-		 * a pointer to a child node in the B+tree so we just break out.
-		 */
-		if (ie->flags & INDEX_ENTRY_END)
-			break;
-		/*
-		 * We perform a case sensitive comparison and if that matches
-		 * we are done and return the mft reference of the inode (i.e.
-		 * the inode number together with the sequence number for
-		 * consistency checking). We convert it to cpu format before
-		 * returning.
-		 */
-		if (ntfs_are_names_equal(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length,
-				CASE_SENSITIVE, vol->upcase, vol->upcase_len)) {
-found_it2:
-			/*
-			 * We have a perfect match, so we don't need to care
-			 * about having matched imperfectly before, so we can
-			 * free name and set *res to NULL.
-			 * However, if the perfect match is a short file name,
-			 * we need to signal this through *res, so that
-			 * ntfs_lookup() can fix dcache aliasing issues.
-			 * As an optimization we just reuse an existing
-			 * allocation of *res.
-			 */
-			if (ie->key.file_name.file_name_type == FILE_NAME_DOS) {
-				if (!name) {
-					name = kmalloc(sizeof(ntfs_name),
-							GFP_NOFS);
-					if (!name) {
-						err = -ENOMEM;
-						goto unm_err_out;
-					}
-				}
-				name->mref = le64_to_cpu(
-						ie->data.dir.indexed_file);
-				name->type = FILE_NAME_DOS;
-				name->len = 0;
-				*res = name;
-			} else {
-				kfree(name);
-				*res = NULL;
-			}
-			mref = le64_to_cpu(ie->data.dir.indexed_file);
-			unlock_page(page);
-			ntfs_unmap_page(page);
-			return mref;
-		}
-		/*
-		 * For a case insensitive mount, we also perform a case
-		 * insensitive comparison (provided the file name is not in the
-		 * POSIX namespace). If the comparison matches, and the name is
-		 * in the WIN32 namespace, we cache the filename in *res so
-		 * that the caller, ntfs_lookup(), can work on it. If the
-		 * comparison matches, and the name is in the DOS namespace, we
-		 * only cache the mft reference and the file name type (we set
-		 * the name length to zero for simplicity).
-		 */
-		if (!NVolCaseSensitive(vol) &&
-				ie->key.file_name.file_name_type &&
-				ntfs_are_names_equal(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length,
-				IGNORE_CASE, vol->upcase, vol->upcase_len)) {
-			int name_size = sizeof(ntfs_name);
-			u8 type = ie->key.file_name.file_name_type;
-			u8 len = ie->key.file_name.file_name_length;
-
-			/* Only one case insensitive matching name allowed. */
-			if (name) {
-				ntfs_error(sb, "Found already allocated name "
-						"in phase 2. Please run chkdsk "
-						"and if that doesn't find any "
-						"errors please report you saw "
-						"this message to "
-						"linux-ntfs-dev@lists."
-						"sourceforge.net.");
-				unlock_page(page);
-				ntfs_unmap_page(page);
-				goto dir_err_out;
-			}
-
-			if (type != FILE_NAME_DOS)
-				name_size += len * sizeof(ntfschar);
-			name = kmalloc(name_size, GFP_NOFS);
-			if (!name) {
-				err = -ENOMEM;
-				goto unm_err_out;
-			}
-			name->mref = le64_to_cpu(ie->data.dir.indexed_file);
-			name->type = type;
-			if (type != FILE_NAME_DOS) {
-				name->len = len;
-				memcpy(name->name, ie->key.file_name.file_name,
-						len * sizeof(ntfschar));
-			} else
-				name->len = 0;
-			*res = name;
-		}
-		/*
-		 * Not a perfect match, need to do full blown collation so we
-		 * know which way in the B+tree we have to go.
-		 */
-		rc = ntfs_collate_names(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length, 1,
-				IGNORE_CASE, vol->upcase, vol->upcase_len);
-		/*
-		 * If uname collates before the name of the current entry, there
-		 * is definitely no such name in this index but we might need to
-		 * descend into the B+tree so we just break out of the loop.
-		 */
-		if (rc == -1)
-			break;
-		/* The names are not equal, continue the search. */
-		if (rc)
-			continue;
-		/*
-		 * Names match with case insensitive comparison, now try the
-		 * case sensitive comparison, which is required for proper
-		 * collation.
-		 */
-		rc = ntfs_collate_names(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length, 1,
-				CASE_SENSITIVE, vol->upcase, vol->upcase_len);
-		if (rc == -1)
-			break;
-		if (rc)
-			continue;
-		/*
-		 * Perfect match, this will never happen as the
-		 * ntfs_are_names_equal() call will have gotten a match but we
-		 * still treat it correctly.
-		 */
-		goto found_it2;
-	}
-	/*
-	 * We have finished with this index buffer without success. Check for
-	 * the presence of a child node.
-	 */
-	if (ie->flags & INDEX_ENTRY_NODE) {
-		if ((ia->index.flags & NODE_MASK) == LEAF_NODE) {
-			ntfs_error(sb, "Index entry with child node found in "
-					"a leaf node in directory inode 0x%lx.",
-					dir_ni->mft_no);
-			goto unm_err_out;
-		}
-		/* Child node present, descend into it. */
-		old_vcn = vcn;
-		vcn = sle64_to_cpup((sle64*)((u8*)ie +
-				le16_to_cpu(ie->length) - 8));
-		if (vcn >= 0) {
-			/* If vcn is in the same page cache page as old_vcn we
-			 * recycle the mapped page. */
-			if (old_vcn << vol->cluster_size_bits >>
-					PAGE_SHIFT == vcn <<
-					vol->cluster_size_bits >>
-					PAGE_SHIFT)
-				goto fast_descend_into_child_node;
-			unlock_page(page);
-			ntfs_unmap_page(page);
-			goto descend_into_child_node;
-		}
-		ntfs_error(sb, "Negative child node vcn in directory inode "
-				"0x%lx.", dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	/*
-	 * No child node present, return -ENOENT, unless we have got a matching
-	 * name cached in name in which case return the mft reference
-	 * associated with it.
-	 */
-	if (name) {
-		unlock_page(page);
-		ntfs_unmap_page(page);
-		return name->mref;
-	}
-	ntfs_debug("Entry not found.");
-	err = -ENOENT;
-unm_err_out:
-	unlock_page(page);
-	ntfs_unmap_page(page);
-err_out:
-	if (!err)
-		err = -EIO;
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(dir_ni);
-	if (name) {
-		kfree(name);
-		*res = NULL;
-	}
-	return ERR_MREF(err);
-dir_err_out:
-	ntfs_error(sb, "Corrupt directory.  Aborting lookup.");
-	goto err_out;
-}
-
-#if 0
-
-// TODO: (AIA)
-// The algorithm embedded in this code will be required for the time when we
-// want to support adding of entries to directories, where we require correct
-// collation of file names in order not to cause corruption of the filesystem.
-
-/**
- * ntfs_lookup_inode_by_name - find an inode in a directory given its name
- * @dir_ni:	ntfs inode of the directory in which to search for the name
- * @uname:	Unicode name for which to search in the directory
- * @uname_len:	length of the name @uname in Unicode characters
- *
- * Look for an inode with name @uname in the directory with inode @dir_ni.
- * ntfs_lookup_inode_by_name() walks the contents of the directory looking for
- * the Unicode name. If the name is found in the directory, the corresponding
- * inode number (>= 0) is returned as a mft reference in cpu format, i.e. it
- * is a 64-bit number containing the sequence number.
- *
- * On error, a negative value is returned corresponding to the error code. In
- * particular if the inode is not found -ENOENT is returned. Note that you
- * can't just check the return value for being negative, you have to check the
- * inode number for being negative which you can extract using MREC(return
- * value).
- *
- * Note, @uname_len does not include the (optional) terminating NULL character.
- */
-u64 ntfs_lookup_inode_by_name(ntfs_inode *dir_ni, const ntfschar *uname,
-		const int uname_len)
-{
-	ntfs_volume *vol = dir_ni->vol;
-	struct super_block *sb = vol->sb;
-	MFT_RECORD *m;
-	INDEX_ROOT *ir;
-	INDEX_ENTRY *ie;
-	INDEX_ALLOCATION *ia;
-	u8 *index_end;
-	u64 mref;
-	ntfs_attr_search_ctx *ctx;
-	int err, rc;
-	IGNORE_CASE_BOOL ic;
-	VCN vcn, old_vcn;
-	struct address_space *ia_mapping;
-	struct page *page;
-	u8 *kaddr;
-
-	/* Get hold of the mft record for the directory. */
-	m = map_mft_record(dir_ni);
-	if (IS_ERR(m)) {
-		ntfs_error(sb, "map_mft_record() failed with error code %ld.",
-				-PTR_ERR(m));
-		return ERR_MREF(PTR_ERR(m));
-	}
-	ctx = ntfs_attr_get_search_ctx(dir_ni, m);
-	if (!ctx) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	/* Find the index root attribute in the mft record. */
-	err = ntfs_attr_lookup(AT_INDEX_ROOT, I30, 4, CASE_SENSITIVE, 0, NULL,
-			0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT) {
-			ntfs_error(sb, "Index root attribute missing in "
-					"directory inode 0x%lx.",
-					dir_ni->mft_no);
-			err = -EIO;
-		}
-		goto err_out;
-	}
-	/* Get to the index root value (it's been verified in read_inode). */
-	ir = (INDEX_ROOT*)((u8*)ctx->attr +
-			le16_to_cpu(ctx->attr->data.resident.value_offset));
-	index_end = (u8*)&ir->index + le32_to_cpu(ir->index.index_length);
-	/* The first index entry. */
-	ie = (INDEX_ENTRY*)((u8*)&ir->index +
-			le32_to_cpu(ir->index.entries_offset));
-	/*
-	 * Loop until we exceed valid memory (corruption case) or until we
-	 * reach the last entry.
-	 */
-	for (;; ie = (INDEX_ENTRY*)((u8*)ie + le16_to_cpu(ie->length))) {
-		/* Bounds checks. */
-		if ((u8*)ie < (u8*)ctx->mrec || (u8*)ie +
-				sizeof(INDEX_ENTRY_HEADER) > index_end ||
-				(u8*)ie + le16_to_cpu(ie->key_length) >
-				index_end)
-			goto dir_err_out;
-		/*
-		 * The last entry cannot contain a name. It can however contain
-		 * a pointer to a child node in the B+tree so we just break out.
-		 */
-		if (ie->flags & INDEX_ENTRY_END)
-			break;
-		/*
-		 * If the current entry has a name type of POSIX, the name is
-		 * case sensitive and not otherwise. This has the effect of us
-		 * not being able to access any POSIX file names which collate
-		 * after the non-POSIX one when they only differ in case, but
-		 * anyone doing screwy stuff like that deserves to burn in
-		 * hell... Doing that kind of stuff on NT4 actually causes
-		 * corruption on the partition even when using SP6a and Linux
-		 * is not involved at all.
-		 */
-		ic = ie->key.file_name.file_name_type ? IGNORE_CASE :
-				CASE_SENSITIVE;
-		/*
-		 * If the names match perfectly, we are done and return the
-		 * mft reference of the inode (i.e. the inode number together
-		 * with the sequence number for consistency checking. We
-		 * convert it to cpu format before returning.
-		 */
-		if (ntfs_are_names_equal(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length, ic,
-				vol->upcase, vol->upcase_len)) {
-found_it:
-			mref = le64_to_cpu(ie->data.dir.indexed_file);
-			ntfs_attr_put_search_ctx(ctx);
-			unmap_mft_record(dir_ni);
-			return mref;
-		}
-		/*
-		 * Not a perfect match, need to do full blown collation so we
-		 * know which way in the B+tree we have to go.
-		 */
-		rc = ntfs_collate_names(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length, 1,
-				IGNORE_CASE, vol->upcase, vol->upcase_len);
-		/*
-		 * If uname collates before the name of the current entry, there
-		 * is definitely no such name in this index but we might need to
-		 * descend into the B+tree so we just break out of the loop.
-		 */
-		if (rc == -1)
-			break;
-		/* The names are not equal, continue the search. */
-		if (rc)
-			continue;
-		/*
-		 * Names match with case insensitive comparison, now try the
-		 * case sensitive comparison, which is required for proper
-		 * collation.
-		 */
-		rc = ntfs_collate_names(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length, 1,
-				CASE_SENSITIVE, vol->upcase, vol->upcase_len);
-		if (rc == -1)
-			break;
-		if (rc)
-			continue;
-		/*
-		 * Perfect match, this will never happen as the
-		 * ntfs_are_names_equal() call will have gotten a match but we
-		 * still treat it correctly.
-		 */
-		goto found_it;
-	}
-	/*
-	 * We have finished with this index without success. Check for the
-	 * presence of a child node.
-	 */
-	if (!(ie->flags & INDEX_ENTRY_NODE)) {
-		/* No child node, return -ENOENT. */
-		err = -ENOENT;
-		goto err_out;
-	} /* Child node present, descend into it. */
-	/* Consistency check: Verify that an index allocation exists. */
-	if (!NInoIndexAllocPresent(dir_ni)) {
-		ntfs_error(sb, "No index allocation attribute but index entry "
-				"requires one. Directory inode 0x%lx is "
-				"corrupt or driver bug.", dir_ni->mft_no);
-		goto err_out;
-	}
-	/* Get the starting vcn of the index_block holding the child node. */
-	vcn = sle64_to_cpup((u8*)ie + le16_to_cpu(ie->length) - 8);
-	ia_mapping = VFS_I(dir_ni)->i_mapping;
-	/*
-	 * We are done with the index root and the mft record. Release them,
-	 * otherwise we deadlock with ntfs_map_page().
-	 */
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(dir_ni);
-	m = NULL;
-	ctx = NULL;
-descend_into_child_node:
-	/*
-	 * Convert vcn to index into the index allocation attribute in units
-	 * of PAGE_SIZE and map the page cache page, reading it from
-	 * disk if necessary.
-	 */
-	page = ntfs_map_page(ia_mapping, vcn <<
-			dir_ni->itype.index.vcn_size_bits >> PAGE_SHIFT);
-	if (IS_ERR(page)) {
-		ntfs_error(sb, "Failed to map directory index page, error %ld.",
-				-PTR_ERR(page));
-		err = PTR_ERR(page);
-		goto err_out;
-	}
-	lock_page(page);
-	kaddr = (u8*)page_address(page);
-fast_descend_into_child_node:
-	/* Get to the index allocation block. */
-	ia = (INDEX_ALLOCATION*)(kaddr + ((vcn <<
-			dir_ni->itype.index.vcn_size_bits) & ~PAGE_MASK));
-	/* Bounds checks. */
-	if ((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_SIZE) {
-		ntfs_error(sb, "Out of bounds check failed. Corrupt directory "
-				"inode 0x%lx or driver bug.", dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	/* Catch multi sector transfer fixup errors. */
-	if (unlikely(!ntfs_is_indx_record(ia->magic))) {
-		ntfs_error(sb, "Directory index record with vcn 0x%llx is "
-				"corrupt.  Corrupt inode 0x%lx.  Run chkdsk.",
-				(unsigned long long)vcn, dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	if (sle64_to_cpu(ia->index_block_vcn) != vcn) {
-		ntfs_error(sb, "Actual VCN (0x%llx) of index buffer is "
-				"different from expected VCN (0x%llx). "
-				"Directory inode 0x%lx is corrupt or driver "
-				"bug.", (unsigned long long)
-				sle64_to_cpu(ia->index_block_vcn),
-				(unsigned long long)vcn, dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	if (le32_to_cpu(ia->index.allocated_size) + 0x18 !=
-			dir_ni->itype.index.block_size) {
-		ntfs_error(sb, "Index buffer (VCN 0x%llx) of directory inode "
-				"0x%lx has a size (%u) differing from the "
-				"directory specified size (%u). Directory "
-				"inode is corrupt or driver bug.",
-				(unsigned long long)vcn, dir_ni->mft_no,
-				le32_to_cpu(ia->index.allocated_size) + 0x18,
-				dir_ni->itype.index.block_size);
-		goto unm_err_out;
-	}
-	index_end = (u8*)ia + dir_ni->itype.index.block_size;
-	if (index_end > kaddr + PAGE_SIZE) {
-		ntfs_error(sb, "Index buffer (VCN 0x%llx) of directory inode "
-				"0x%lx crosses page boundary. Impossible! "
-				"Cannot access! This is probably a bug in the "
-				"driver.", (unsigned long long)vcn,
-				dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	index_end = (u8*)&ia->index + le32_to_cpu(ia->index.index_length);
-	if (index_end > (u8*)ia + dir_ni->itype.index.block_size) {
-		ntfs_error(sb, "Size of index buffer (VCN 0x%llx) of directory "
-				"inode 0x%lx exceeds maximum size.",
-				(unsigned long long)vcn, dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	/* The first index entry. */
-	ie = (INDEX_ENTRY*)((u8*)&ia->index +
-			le32_to_cpu(ia->index.entries_offset));
-	/*
-	 * Iterate similar to above big loop but applied to index buffer, thus
-	 * loop until we exceed valid memory (corruption case) or until we
-	 * reach the last entry.
-	 */
-	for (;; ie = (INDEX_ENTRY*)((u8*)ie + le16_to_cpu(ie->length))) {
-		/* Bounds check. */
-		if ((u8*)ie < (u8*)ia || (u8*)ie +
-				sizeof(INDEX_ENTRY_HEADER) > index_end ||
-				(u8*)ie + le16_to_cpu(ie->key_length) >
-				index_end) {
-			ntfs_error(sb, "Index entry out of bounds in "
-					"directory inode 0x%lx.",
-					dir_ni->mft_no);
-			goto unm_err_out;
-		}
-		/*
-		 * The last entry cannot contain a name. It can however contain
-		 * a pointer to a child node in the B+tree so we just break out.
-		 */
-		if (ie->flags & INDEX_ENTRY_END)
-			break;
-		/*
-		 * If the current entry has a name type of POSIX, the name is
-		 * case sensitive and not otherwise. This has the effect of us
-		 * not being able to access any POSIX file names which collate
-		 * after the non-POSIX one when they only differ in case, but
-		 * anyone doing screwy stuff like that deserves to burn in
-		 * hell... Doing that kind of stuff on NT4 actually causes
-		 * corruption on the partition even when using SP6a and Linux
-		 * is not involved at all.
-		 */
-		ic = ie->key.file_name.file_name_type ? IGNORE_CASE :
-				CASE_SENSITIVE;
-		/*
-		 * If the names match perfectly, we are done and return the
-		 * mft reference of the inode (i.e. the inode number together
-		 * with the sequence number for consistency checking. We
-		 * convert it to cpu format before returning.
-		 */
-		if (ntfs_are_names_equal(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length, ic,
-				vol->upcase, vol->upcase_len)) {
-found_it2:
-			mref = le64_to_cpu(ie->data.dir.indexed_file);
-			unlock_page(page);
-			ntfs_unmap_page(page);
-			return mref;
-		}
-		/*
-		 * Not a perfect match, need to do full blown collation so we
-		 * know which way in the B+tree we have to go.
-		 */
-		rc = ntfs_collate_names(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length, 1,
-				IGNORE_CASE, vol->upcase, vol->upcase_len);
-		/*
-		 * If uname collates before the name of the current entry, there
-		 * is definitely no such name in this index but we might need to
-		 * descend into the B+tree so we just break out of the loop.
-		 */
-		if (rc == -1)
-			break;
-		/* The names are not equal, continue the search. */
-		if (rc)
-			continue;
-		/*
-		 * Names match with case insensitive comparison, now try the
-		 * case sensitive comparison, which is required for proper
-		 * collation.
-		 */
-		rc = ntfs_collate_names(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length, 1,
-				CASE_SENSITIVE, vol->upcase, vol->upcase_len);
-		if (rc == -1)
-			break;
-		if (rc)
-			continue;
-		/*
-		 * Perfect match, this will never happen as the
-		 * ntfs_are_names_equal() call will have gotten a match but we
-		 * still treat it correctly.
-		 */
-		goto found_it2;
-	}
-	/*
-	 * We have finished with this index buffer without success. Check for
-	 * the presence of a child node.
-	 */
-	if (ie->flags & INDEX_ENTRY_NODE) {
-		if ((ia->index.flags & NODE_MASK) == LEAF_NODE) {
-			ntfs_error(sb, "Index entry with child node found in "
-					"a leaf node in directory inode 0x%lx.",
-					dir_ni->mft_no);
-			goto unm_err_out;
-		}
-		/* Child node present, descend into it. */
-		old_vcn = vcn;
-		vcn = sle64_to_cpup((u8*)ie + le16_to_cpu(ie->length) - 8);
-		if (vcn >= 0) {
-			/* If vcn is in the same page cache page as old_vcn we
-			 * recycle the mapped page. */
-			if (old_vcn << vol->cluster_size_bits >>
-					PAGE_SHIFT == vcn <<
-					vol->cluster_size_bits >>
-					PAGE_SHIFT)
-				goto fast_descend_into_child_node;
-			unlock_page(page);
-			ntfs_unmap_page(page);
-			goto descend_into_child_node;
-		}
-		ntfs_error(sb, "Negative child node vcn in directory inode "
-				"0x%lx.", dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	/* No child node, return -ENOENT. */
-	ntfs_debug("Entry not found.");
-	err = -ENOENT;
-unm_err_out:
-	unlock_page(page);
-	ntfs_unmap_page(page);
-err_out:
-	if (!err)
-		err = -EIO;
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(dir_ni);
-	return ERR_MREF(err);
-dir_err_out:
-	ntfs_error(sb, "Corrupt directory. Aborting lookup.");
-	goto err_out;
-}
-
-#endif
-
-/**
- * ntfs_filldir - ntfs specific filldir method
- * @vol:	current ntfs volume
- * @ndir:	ntfs inode of current directory
- * @ia_page:	page in which the index allocation buffer @ie is in resides
- * @ie:		current index entry
- * @name:	buffer to use for the converted name
- * @actor:	what to feed the entries to
- *
- * Convert the Unicode @name to the loaded NLS and pass it to the @filldir
- * callback.
- *
- * If @ia_page is not NULL it is the locked page containing the index
- * allocation block containing the index entry @ie.
- *
- * Note, we drop (and then reacquire) the page lock on @ia_page across the
- * @filldir() call otherwise we would deadlock with NFSd when it calls ->lookup
- * since ntfs_lookup() will lock the same page.  As an optimization, we do not
- * retake the lock if we are returning a non-zero value as ntfs_readdir()
- * would need to drop the lock immediately anyway.
- */
-static inline int ntfs_filldir(ntfs_volume *vol,
-		ntfs_inode *ndir, struct page *ia_page, INDEX_ENTRY *ie,
-		u8 *name, struct dir_context *actor)
-{
-	unsigned long mref;
-	int name_len;
-	unsigned dt_type;
-	FILE_NAME_TYPE_FLAGS name_type;
-
-	name_type = ie->key.file_name.file_name_type;
-	if (name_type == FILE_NAME_DOS) {
-		ntfs_debug("Skipping DOS name space entry.");
-		return 0;
-	}
-	if (MREF_LE(ie->data.dir.indexed_file) == FILE_root) {
-		ntfs_debug("Skipping root directory self reference entry.");
-		return 0;
-	}
-	if (MREF_LE(ie->data.dir.indexed_file) < FILE_first_user &&
-			!NVolShowSystemFiles(vol)) {
-		ntfs_debug("Skipping system file.");
-		return 0;
-	}
-	name_len = ntfs_ucstonls(vol, (ntfschar*)&ie->key.file_name.file_name,
-			ie->key.file_name.file_name_length, &name,
-			NTFS_MAX_NAME_LEN * NLS_MAX_CHARSET_SIZE + 1);
-	if (name_len <= 0) {
-		ntfs_warning(vol->sb, "Skipping unrepresentable inode 0x%llx.",
-				(long long)MREF_LE(ie->data.dir.indexed_file));
-		return 0;
-	}
-	if (ie->key.file_name.file_attributes &
-			FILE_ATTR_DUP_FILE_NAME_INDEX_PRESENT)
-		dt_type = DT_DIR;
-	else
-		dt_type = DT_REG;
-	mref = MREF_LE(ie->data.dir.indexed_file);
-	/*
-	 * Drop the page lock otherwise we deadlock with NFS when it calls
-	 * ->lookup since ntfs_lookup() will lock the same page.
-	 */
-	if (ia_page)
-		unlock_page(ia_page);
-	ntfs_debug("Calling filldir for %s with len %i, fpos 0x%llx, inode "
-			"0x%lx, DT_%s.", name, name_len, actor->pos, mref,
-			dt_type == DT_DIR ? "DIR" : "REG");
-	if (!dir_emit(actor, name, name_len, mref, dt_type))
-		return 1;
-	/* Relock the page but not if we are aborting ->readdir. */
-	if (ia_page)
-		lock_page(ia_page);
-	return 0;
-}
-
-/*
- * We use the same basic approach as the old NTFS driver, i.e. we parse the
- * index root entries and then the index allocation entries that are marked
- * as in use in the index bitmap.
- *
- * While this will return the names in random order this doesn't matter for
- * ->readdir but OTOH results in a faster ->readdir.
- *
- * VFS calls ->readdir without BKL but with i_mutex held. This protects the VFS
- * parts (e.g. ->f_pos and ->i_size, and it also protects against directory
- * modifications).
- *
- * Locking:  - Caller must hold i_mutex on the directory.
- *	     - Each page cache page in the index allocation mapping must be
- *	       locked whilst being accessed otherwise we may find a corrupt
- *	       page due to it being under ->writepage at the moment which
- *	       applies the mst protection fixups before writing out and then
- *	       removes them again after the write is complete after which it 
- *	       unlocks the page.
- */
-static int ntfs_readdir(struct file *file, struct dir_context *actor)
-{
-	s64 ia_pos, ia_start, prev_ia_pos, bmp_pos;
-	loff_t i_size;
-	struct inode *bmp_vi, *vdir = file_inode(file);
-	struct super_block *sb = vdir->i_sb;
-	ntfs_inode *ndir = NTFS_I(vdir);
-	ntfs_volume *vol = NTFS_SB(sb);
-	MFT_RECORD *m;
-	INDEX_ROOT *ir = NULL;
-	INDEX_ENTRY *ie;
-	INDEX_ALLOCATION *ia;
-	u8 *name = NULL;
-	int rc, err, ir_pos, cur_bmp_pos;
-	struct address_space *ia_mapping, *bmp_mapping;
-	struct page *bmp_page = NULL, *ia_page = NULL;
-	u8 *kaddr, *bmp, *index_end;
-	ntfs_attr_search_ctx *ctx;
-
-	ntfs_debug("Entering for inode 0x%lx, fpos 0x%llx.",
-			vdir->i_ino, actor->pos);
-	rc = err = 0;
-	/* Are we at end of dir yet? */
-	i_size = i_size_read(vdir);
-	if (actor->pos >= i_size + vol->mft_record_size)
-		return 0;
-	/* Emulate . and .. for all directories. */
-	if (!dir_emit_dots(file, actor))
-		return 0;
-	m = NULL;
-	ctx = NULL;
-	/*
-	 * Allocate a buffer to store the current name being processed
-	 * converted to format determined by current NLS.
-	 */
-	name = kmalloc(NTFS_MAX_NAME_LEN * NLS_MAX_CHARSET_SIZE + 1, GFP_NOFS);
-	if (unlikely(!name)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	/* Are we jumping straight into the index allocation attribute? */
-	if (actor->pos >= vol->mft_record_size)
-		goto skip_index_root;
-	/* Get hold of the mft record for the directory. */
-	m = map_mft_record(ndir);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		m = NULL;
-		goto err_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(ndir, m);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	/* Get the offset into the index root attribute. */
-	ir_pos = (s64)actor->pos;
-	/* Find the index root attribute in the mft record. */
-	err = ntfs_attr_lookup(AT_INDEX_ROOT, I30, 4, CASE_SENSITIVE, 0, NULL,
-			0, ctx);
-	if (unlikely(err)) {
-		ntfs_error(sb, "Index root attribute missing in directory "
-				"inode 0x%lx.", vdir->i_ino);
-		goto err_out;
-	}
-	/*
-	 * Copy the index root attribute value to a buffer so that we can put
-	 * the search context and unmap the mft record before calling the
-	 * filldir() callback.  We need to do this because of NFSd which calls
-	 * ->lookup() from its filldir callback() and this causes NTFS to
-	 * deadlock as ntfs_lookup() maps the mft record of the directory and
-	 * we have got it mapped here already.  The only solution is for us to
-	 * unmap the mft record here so that a call to ntfs_lookup() is able to
-	 * map the mft record without deadlocking.
-	 */
-	rc = le32_to_cpu(ctx->attr->data.resident.value_length);
-	ir = kmalloc(rc, GFP_NOFS);
-	if (unlikely(!ir)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	/* Copy the index root value (it has been verified in read_inode). */
-	memcpy(ir, (u8*)ctx->attr +
-			le16_to_cpu(ctx->attr->data.resident.value_offset), rc);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(ndir);
-	ctx = NULL;
-	m = NULL;
-	index_end = (u8*)&ir->index + le32_to_cpu(ir->index.index_length);
-	/* The first index entry. */
-	ie = (INDEX_ENTRY*)((u8*)&ir->index +
-			le32_to_cpu(ir->index.entries_offset));
-	/*
-	 * Loop until we exceed valid memory (corruption case) or until we
-	 * reach the last entry or until filldir tells us it has had enough
-	 * or signals an error (both covered by the rc test).
-	 */
-	for (;; ie = (INDEX_ENTRY*)((u8*)ie + le16_to_cpu(ie->length))) {
-		ntfs_debug("In index root, offset 0x%zx.", (u8*)ie - (u8*)ir);
-		/* Bounds checks. */
-		if (unlikely((u8*)ie < (u8*)ir || (u8*)ie +
-				sizeof(INDEX_ENTRY_HEADER) > index_end ||
-				(u8*)ie + le16_to_cpu(ie->key_length) >
-				index_end))
-			goto err_out;
-		/* The last entry cannot contain a name. */
-		if (ie->flags & INDEX_ENTRY_END)
-			break;
-		/* Skip index root entry if continuing previous readdir. */
-		if (ir_pos > (u8*)ie - (u8*)ir)
-			continue;
-		/* Advance the position even if going to skip the entry. */
-		actor->pos = (u8*)ie - (u8*)ir;
-		/* Submit the name to the filldir callback. */
-		rc = ntfs_filldir(vol, ndir, NULL, ie, name, actor);
-		if (rc) {
-			kfree(ir);
-			goto abort;
-		}
-	}
-	/* We are done with the index root and can free the buffer. */
-	kfree(ir);
-	ir = NULL;
-	/* If there is no index allocation attribute we are finished. */
-	if (!NInoIndexAllocPresent(ndir))
-		goto EOD;
-	/* Advance fpos to the beginning of the index allocation. */
-	actor->pos = vol->mft_record_size;
-skip_index_root:
-	kaddr = NULL;
-	prev_ia_pos = -1LL;
-	/* Get the offset into the index allocation attribute. */
-	ia_pos = (s64)actor->pos - vol->mft_record_size;
-	ia_mapping = vdir->i_mapping;
-	ntfs_debug("Inode 0x%lx, getting index bitmap.", vdir->i_ino);
-	bmp_vi = ntfs_attr_iget(vdir, AT_BITMAP, I30, 4);
-	if (IS_ERR(bmp_vi)) {
-		ntfs_error(sb, "Failed to get bitmap attribute.");
-		err = PTR_ERR(bmp_vi);
-		goto err_out;
-	}
-	bmp_mapping = bmp_vi->i_mapping;
-	/* Get the starting bitmap bit position and sanity check it. */
-	bmp_pos = ia_pos >> ndir->itype.index.block_size_bits;
-	if (unlikely(bmp_pos >> 3 >= i_size_read(bmp_vi))) {
-		ntfs_error(sb, "Current index allocation position exceeds "
-				"index bitmap size.");
-		goto iput_err_out;
-	}
-	/* Get the starting bit position in the current bitmap page. */
-	cur_bmp_pos = bmp_pos & ((PAGE_SIZE * 8) - 1);
-	bmp_pos &= ~(u64)((PAGE_SIZE * 8) - 1);
-get_next_bmp_page:
-	ntfs_debug("Reading bitmap with page index 0x%llx, bit ofs 0x%llx",
-			(unsigned long long)bmp_pos >> (3 + PAGE_SHIFT),
-			(unsigned long long)bmp_pos &
-			(unsigned long long)((PAGE_SIZE * 8) - 1));
-	bmp_page = ntfs_map_page(bmp_mapping,
-			bmp_pos >> (3 + PAGE_SHIFT));
-	if (IS_ERR(bmp_page)) {
-		ntfs_error(sb, "Reading index bitmap failed.");
-		err = PTR_ERR(bmp_page);
-		bmp_page = NULL;
-		goto iput_err_out;
-	}
-	bmp = (u8*)page_address(bmp_page);
-	/* Find next index block in use. */
-	while (!(bmp[cur_bmp_pos >> 3] & (1 << (cur_bmp_pos & 7)))) {
-find_next_index_buffer:
-		cur_bmp_pos++;
-		/*
-		 * If we have reached the end of the bitmap page, get the next
-		 * page, and put away the old one.
-		 */
-		if (unlikely((cur_bmp_pos >> 3) >= PAGE_SIZE)) {
-			ntfs_unmap_page(bmp_page);
-			bmp_pos += PAGE_SIZE * 8;
-			cur_bmp_pos = 0;
-			goto get_next_bmp_page;
-		}
-		/* If we have reached the end of the bitmap, we are done. */
-		if (unlikely(((bmp_pos + cur_bmp_pos) >> 3) >= i_size))
-			goto unm_EOD;
-		ia_pos = (bmp_pos + cur_bmp_pos) <<
-				ndir->itype.index.block_size_bits;
-	}
-	ntfs_debug("Handling index buffer 0x%llx.",
-			(unsigned long long)bmp_pos + cur_bmp_pos);
-	/* If the current index buffer is in the same page we reuse the page. */
-	if ((prev_ia_pos & (s64)PAGE_MASK) !=
-			(ia_pos & (s64)PAGE_MASK)) {
-		prev_ia_pos = ia_pos;
-		if (likely(ia_page != NULL)) {
-			unlock_page(ia_page);
-			ntfs_unmap_page(ia_page);
-		}
-		/*
-		 * Map the page cache page containing the current ia_pos,
-		 * reading it from disk if necessary.
-		 */
-		ia_page = ntfs_map_page(ia_mapping, ia_pos >> PAGE_SHIFT);
-		if (IS_ERR(ia_page)) {
-			ntfs_error(sb, "Reading index allocation data failed.");
-			err = PTR_ERR(ia_page);
-			ia_page = NULL;
-			goto err_out;
-		}
-		lock_page(ia_page);
-		kaddr = (u8*)page_address(ia_page);
-	}
-	/* Get the current index buffer. */
-	ia = (INDEX_ALLOCATION*)(kaddr + (ia_pos & ~PAGE_MASK &
-					  ~(s64)(ndir->itype.index.block_size - 1)));
-	/* Bounds checks. */
-	if (unlikely((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_SIZE)) {
-		ntfs_error(sb, "Out of bounds check failed. Corrupt directory "
-				"inode 0x%lx or driver bug.", vdir->i_ino);
-		goto err_out;
-	}
-	/* Catch multi sector transfer fixup errors. */
-	if (unlikely(!ntfs_is_indx_record(ia->magic))) {
-		ntfs_error(sb, "Directory index record with vcn 0x%llx is "
-				"corrupt.  Corrupt inode 0x%lx.  Run chkdsk.",
-				(unsigned long long)ia_pos >>
-				ndir->itype.index.vcn_size_bits, vdir->i_ino);
-		goto err_out;
-	}
-	if (unlikely(sle64_to_cpu(ia->index_block_vcn) != (ia_pos &
-			~(s64)(ndir->itype.index.block_size - 1)) >>
-			ndir->itype.index.vcn_size_bits)) {
-		ntfs_error(sb, "Actual VCN (0x%llx) of index buffer is "
-				"different from expected VCN (0x%llx). "
-				"Directory inode 0x%lx is corrupt or driver "
-				"bug. ", (unsigned long long)
-				sle64_to_cpu(ia->index_block_vcn),
-				(unsigned long long)ia_pos >>
-				ndir->itype.index.vcn_size_bits, vdir->i_ino);
-		goto err_out;
-	}
-	if (unlikely(le32_to_cpu(ia->index.allocated_size) + 0x18 !=
-			ndir->itype.index.block_size)) {
-		ntfs_error(sb, "Index buffer (VCN 0x%llx) of directory inode "
-				"0x%lx has a size (%u) differing from the "
-				"directory specified size (%u). Directory "
-				"inode is corrupt or driver bug.",
-				(unsigned long long)ia_pos >>
-				ndir->itype.index.vcn_size_bits, vdir->i_ino,
-				le32_to_cpu(ia->index.allocated_size) + 0x18,
-				ndir->itype.index.block_size);
-		goto err_out;
-	}
-	index_end = (u8*)ia + ndir->itype.index.block_size;
-	if (unlikely(index_end > kaddr + PAGE_SIZE)) {
-		ntfs_error(sb, "Index buffer (VCN 0x%llx) of directory inode "
-				"0x%lx crosses page boundary. Impossible! "
-				"Cannot access! This is probably a bug in the "
-				"driver.", (unsigned long long)ia_pos >>
-				ndir->itype.index.vcn_size_bits, vdir->i_ino);
-		goto err_out;
-	}
-	ia_start = ia_pos & ~(s64)(ndir->itype.index.block_size - 1);
-	index_end = (u8*)&ia->index + le32_to_cpu(ia->index.index_length);
-	if (unlikely(index_end > (u8*)ia + ndir->itype.index.block_size)) {
-		ntfs_error(sb, "Size of index buffer (VCN 0x%llx) of directory "
-				"inode 0x%lx exceeds maximum size.",
-				(unsigned long long)ia_pos >>
-				ndir->itype.index.vcn_size_bits, vdir->i_ino);
-		goto err_out;
-	}
-	/* The first index entry in this index buffer. */
-	ie = (INDEX_ENTRY*)((u8*)&ia->index +
-			le32_to_cpu(ia->index.entries_offset));
-	/*
-	 * Loop until we exceed valid memory (corruption case) or until we
-	 * reach the last entry or until filldir tells us it has had enough
-	 * or signals an error (both covered by the rc test).
-	 */
-	for (;; ie = (INDEX_ENTRY*)((u8*)ie + le16_to_cpu(ie->length))) {
-		ntfs_debug("In index allocation, offset 0x%llx.",
-				(unsigned long long)ia_start +
-				(unsigned long long)((u8*)ie - (u8*)ia));
-		/* Bounds checks. */
-		if (unlikely((u8*)ie < (u8*)ia || (u8*)ie +
-				sizeof(INDEX_ENTRY_HEADER) > index_end ||
-				(u8*)ie + le16_to_cpu(ie->key_length) >
-				index_end))
-			goto err_out;
-		/* The last entry cannot contain a name. */
-		if (ie->flags & INDEX_ENTRY_END)
-			break;
-		/* Skip index block entry if continuing previous readdir. */
-		if (ia_pos - ia_start > (u8*)ie - (u8*)ia)
-			continue;
-		/* Advance the position even if going to skip the entry. */
-		actor->pos = (u8*)ie - (u8*)ia +
-				(sle64_to_cpu(ia->index_block_vcn) <<
-				ndir->itype.index.vcn_size_bits) +
-				vol->mft_record_size;
-		/*
-		 * Submit the name to the @filldir callback.  Note,
-		 * ntfs_filldir() drops the lock on @ia_page but it retakes it
-		 * before returning, unless a non-zero value is returned in
-		 * which case the page is left unlocked.
-		 */
-		rc = ntfs_filldir(vol, ndir, ia_page, ie, name, actor);
-		if (rc) {
-			/* @ia_page is already unlocked in this case. */
-			ntfs_unmap_page(ia_page);
-			ntfs_unmap_page(bmp_page);
-			iput(bmp_vi);
-			goto abort;
-		}
-	}
-	goto find_next_index_buffer;
-unm_EOD:
-	if (ia_page) {
-		unlock_page(ia_page);
-		ntfs_unmap_page(ia_page);
-	}
-	ntfs_unmap_page(bmp_page);
-	iput(bmp_vi);
-EOD:
-	/* We are finished, set fpos to EOD. */
-	actor->pos = i_size + vol->mft_record_size;
-abort:
-	kfree(name);
-	return 0;
-err_out:
-	if (bmp_page) {
-		ntfs_unmap_page(bmp_page);
-iput_err_out:
-		iput(bmp_vi);
-	}
-	if (ia_page) {
-		unlock_page(ia_page);
-		ntfs_unmap_page(ia_page);
-	}
-	kfree(ir);
-	kfree(name);
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(ndir);
-	if (!err)
-		err = -EIO;
-	ntfs_debug("Failed. Returning error code %i.", -err);
-	return err;
-}
-
-/**
- * ntfs_dir_open - called when an inode is about to be opened
- * @vi:		inode to be opened
- * @filp:	file structure describing the inode
- *
- * Limit directory size to the page cache limit on architectures where unsigned
- * long is 32-bits. This is the most we can do for now without overflowing the
- * page cache page index. Doing it this way means we don't run into problems
- * because of existing too large directories. It would be better to allow the
- * user to read the accessible part of the directory but I doubt very much
- * anyone is going to hit this check on a 32-bit architecture, so there is no
- * point in adding the extra complexity required to support this.
- *
- * On 64-bit architectures, the check is hopefully optimized away by the
- * compiler.
- */
-static int ntfs_dir_open(struct inode *vi, struct file *filp)
-{
-	if (sizeof(unsigned long) < 8) {
-		if (i_size_read(vi) > MAX_LFS_FILESIZE)
-			return -EFBIG;
-	}
-	return 0;
-}
-
-#ifdef NTFS_RW
-
-/**
- * ntfs_dir_fsync - sync a directory to disk
- * @filp:	directory to be synced
- * @start:	offset in bytes of the beginning of data range to sync
- * @end:	offset in bytes of the end of data range (inclusive)
- * @datasync:	if non-zero only flush user data and not metadata
- *
- * Data integrity sync of a directory to disk.  Used for fsync, fdatasync, and
- * msync system calls.  This function is based on file.c::ntfs_file_fsync().
- *
- * Write the mft record and all associated extent mft records as well as the
- * $INDEX_ALLOCATION and $BITMAP attributes and then sync the block device.
- *
- * If @datasync is true, we do not wait on the inode(s) to be written out
- * but we always wait on the page cache pages to be written out.
- *
- * Note: In the past @filp could be NULL so we ignore it as we don't need it
- * anyway.
- *
- * Locking: Caller must hold i_mutex on the inode.
- *
- * TODO: We should probably also write all attribute/index inodes associated
- * with this inode but since we have no simple way of getting to them we ignore
- * this problem for now.  We do write the $BITMAP attribute if it is present
- * which is the important one for a directory so things are not too bad.
- */
-static int ntfs_dir_fsync(struct file *filp, loff_t start, loff_t end,
-			  int datasync)
-{
-	struct inode *bmp_vi, *vi = filp->f_mapping->host;
-	int err, ret;
-	ntfs_attr na;
-
-	ntfs_debug("Entering for inode 0x%lx.", vi->i_ino);
-
-	err = file_write_and_wait_range(filp, start, end);
-	if (err)
-		return err;
-	inode_lock(vi);
-
-	BUG_ON(!S_ISDIR(vi->i_mode));
-	/* If the bitmap attribute inode is in memory sync it, too. */
-	na.mft_no = vi->i_ino;
-	na.type = AT_BITMAP;
-	na.name = I30;
-	na.name_len = 4;
-	bmp_vi = ilookup5(vi->i_sb, vi->i_ino, ntfs_test_inode, &na);
-	if (bmp_vi) {
- 		write_inode_now(bmp_vi, !datasync);
-		iput(bmp_vi);
-	}
-	ret = __ntfs_write_inode(vi, 1);
-	write_inode_now(vi, !datasync);
-	err = sync_blockdev(vi->i_sb->s_bdev);
-	if (unlikely(err && !ret))
-		ret = err;
-	if (likely(!ret))
-		ntfs_debug("Done.");
-	else
-		ntfs_warning(vi->i_sb, "Failed to f%ssync inode 0x%lx.  Error "
-				"%u.", datasync ? "data" : "", vi->i_ino, -ret);
-	inode_unlock(vi);
-	return ret;
-}
-
-#endif /* NTFS_RW */
-
-WRAP_DIR_ITER(ntfs_readdir) // FIXME!
-const struct file_operations ntfs_dir_ops = {
-	.llseek		= generic_file_llseek,	/* Seek inside directory. */
-	.read		= generic_read_dir,	/* Return -EISDIR. */
-	.iterate_shared	= shared_ntfs_readdir,	/* Read directory contents. */
-#ifdef NTFS_RW
-	.fsync		= ntfs_dir_fsync,	/* Sync a directory to disk. */
-#endif /* NTFS_RW */
-	/*.ioctl	= ,*/			/* Perform function on the
-						   mounted filesystem. */
-	.open		= ntfs_dir_open,	/* Open directory. */
-};
diff --git a/fs/ntfs/dir.h b/fs/ntfs/dir.h
deleted file mode 100644
index 0e326753df40..000000000000
--- a/fs/ntfs/dir.h
+++ /dev/null
@@ -1,34 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * dir.h - Defines for directory handling in NTFS Linux kernel driver. Part of
- *	   the Linux-NTFS project.
- *
- * Copyright (c) 2002-2004 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_DIR_H
-#define _LINUX_NTFS_DIR_H
-
-#include "layout.h"
-#include "inode.h"
-#include "types.h"
-
-/*
- * ntfs_name is used to return the file name to the caller of
- * ntfs_lookup_inode_by_name() in order for the caller (namei.c::ntfs_lookup())
- * to be able to deal with dcache aliasing issues.
- */
-typedef struct {
-	MFT_REF mref;
-	FILE_NAME_TYPE_FLAGS type;
-	u8 len;
-	ntfschar name[0];
-} __attribute__ ((__packed__)) ntfs_name;
-
-/* The little endian Unicode string $I30 as a global constant. */
-extern ntfschar I30[5];
-
-extern MFT_REF ntfs_lookup_inode_by_name(ntfs_inode *dir_ni,
-		const ntfschar *uname, const int uname_len, ntfs_name **res);
-
-#endif /* _LINUX_NTFS_FS_DIR_H */
diff --git a/fs/ntfs/endian.h b/fs/ntfs/endian.h
deleted file mode 100644
index f30c139bf9ae..000000000000
--- a/fs/ntfs/endian.h
+++ /dev/null
@@ -1,79 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * endian.h - Defines for endianness handling in NTFS Linux kernel driver.
- *	      Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2004 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_ENDIAN_H
-#define _LINUX_NTFS_ENDIAN_H
-
-#include <asm/byteorder.h>
-#include "types.h"
-
-/*
- * Signed endianness conversion functions.
- */
-
-static inline s16 sle16_to_cpu(sle16 x)
-{
-	return le16_to_cpu((__force le16)x);
-}
-
-static inline s32 sle32_to_cpu(sle32 x)
-{
-	return le32_to_cpu((__force le32)x);
-}
-
-static inline s64 sle64_to_cpu(sle64 x)
-{
-	return le64_to_cpu((__force le64)x);
-}
-
-static inline s16 sle16_to_cpup(sle16 *x)
-{
-	return le16_to_cpu(*(__force le16*)x);
-}
-
-static inline s32 sle32_to_cpup(sle32 *x)
-{
-	return le32_to_cpu(*(__force le32*)x);
-}
-
-static inline s64 sle64_to_cpup(sle64 *x)
-{
-	return le64_to_cpu(*(__force le64*)x);
-}
-
-static inline sle16 cpu_to_sle16(s16 x)
-{
-	return (__force sle16)cpu_to_le16(x);
-}
-
-static inline sle32 cpu_to_sle32(s32 x)
-{
-	return (__force sle32)cpu_to_le32(x);
-}
-
-static inline sle64 cpu_to_sle64(s64 x)
-{
-	return (__force sle64)cpu_to_le64(x);
-}
-
-static inline sle16 cpu_to_sle16p(s16 *x)
-{
-	return (__force sle16)cpu_to_le16(*x);
-}
-
-static inline sle32 cpu_to_sle32p(s32 *x)
-{
-	return (__force sle32)cpu_to_le32(*x);
-}
-
-static inline sle64 cpu_to_sle64p(s64 *x)
-{
-	return (__force sle64)cpu_to_le64(*x);
-}
-
-#endif /* _LINUX_NTFS_ENDIAN_H */
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
deleted file mode 100644
index 297c0b9db621..000000000000
--- a/fs/ntfs/file.c
+++ /dev/null
@@ -1,1997 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * file.c - NTFS kernel file operations.  Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2015 Anton Altaparmakov and Tuxera Inc.
- */
-
-#include <linux/blkdev.h>
-#include <linux/backing-dev.h>
-#include <linux/buffer_head.h>
-#include <linux/gfp.h>
-#include <linux/pagemap.h>
-#include <linux/pagevec.h>
-#include <linux/sched/signal.h>
-#include <linux/swap.h>
-#include <linux/uio.h>
-#include <linux/writeback.h>
-
-#include <asm/page.h>
-#include <linux/uaccess.h>
-
-#include "attrib.h"
-#include "bitmap.h"
-#include "inode.h"
-#include "debug.h"
-#include "lcnalloc.h"
-#include "malloc.h"
-#include "mft.h"
-#include "ntfs.h"
-
-/**
- * ntfs_file_open - called when an inode is about to be opened
- * @vi:		inode to be opened
- * @filp:	file structure describing the inode
- *
- * Limit file size to the page cache limit on architectures where unsigned long
- * is 32-bits. This is the most we can do for now without overflowing the page
- * cache page index. Doing it this way means we don't run into problems because
- * of existing too large files. It would be better to allow the user to read
- * the beginning of the file but I doubt very much anyone is going to hit this
- * check on a 32-bit architecture, so there is no point in adding the extra
- * complexity required to support this.
- *
- * On 64-bit architectures, the check is hopefully optimized away by the
- * compiler.
- *
- * After the check passes, just call generic_file_open() to do its work.
- */
-static int ntfs_file_open(struct inode *vi, struct file *filp)
-{
-	if (sizeof(unsigned long) < 8) {
-		if (i_size_read(vi) > MAX_LFS_FILESIZE)
-			return -EOVERFLOW;
-	}
-	return generic_file_open(vi, filp);
-}
-
-#ifdef NTFS_RW
-
-/**
- * ntfs_attr_extend_initialized - extend the initialized size of an attribute
- * @ni:			ntfs inode of the attribute to extend
- * @new_init_size:	requested new initialized size in bytes
- *
- * Extend the initialized size of an attribute described by the ntfs inode @ni
- * to @new_init_size bytes.  This involves zeroing any non-sparse space between
- * the old initialized size and @new_init_size both in the page cache and on
- * disk (if relevant complete pages are already uptodate in the page cache then
- * these are simply marked dirty).
- *
- * As a side-effect, the file size (vfs inode->i_size) may be incremented as,
- * in the resident attribute case, it is tied to the initialized size and, in
- * the non-resident attribute case, it may not fall below the initialized size.
- *
- * Note that if the attribute is resident, we do not need to touch the page
- * cache at all.  This is because if the page cache page is not uptodate we
- * bring it uptodate later, when doing the write to the mft record since we
- * then already have the page mapped.  And if the page is uptodate, the
- * non-initialized region will already have been zeroed when the page was
- * brought uptodate and the region may in fact already have been overwritten
- * with new data via mmap() based writes, so we cannot just zero it.  And since
- * POSIX specifies that the behaviour of resizing a file whilst it is mmap()ped
- * is unspecified, we choose not to do zeroing and thus we do not need to touch
- * the page at all.  For a more detailed explanation see ntfs_truncate() in
- * fs/ntfs/inode.c.
- *
- * Return 0 on success and -errno on error.  In the case that an error is
- * encountered it is possible that the initialized size will already have been
- * incremented some way towards @new_init_size but it is guaranteed that if
- * this is the case, the necessary zeroing will also have happened and that all
- * metadata is self-consistent.
- *
- * Locking: i_mutex on the vfs inode corrseponsind to the ntfs inode @ni must be
- *	    held by the caller.
- */
-static int ntfs_attr_extend_initialized(ntfs_inode *ni, const s64 new_init_size)
-{
-	s64 old_init_size;
-	loff_t old_i_size;
-	pgoff_t index, end_index;
-	unsigned long flags;
-	struct inode *vi = VFS_I(ni);
-	ntfs_inode *base_ni;
-	MFT_RECORD *m = NULL;
-	ATTR_RECORD *a;
-	ntfs_attr_search_ctx *ctx = NULL;
-	struct address_space *mapping;
-	struct page *page = NULL;
-	u8 *kattr;
-	int err;
-	u32 attr_len;
-
-	read_lock_irqsave(&ni->size_lock, flags);
-	old_init_size = ni->initialized_size;
-	old_i_size = i_size_read(vi);
-	BUG_ON(new_init_size > ni->allocated_size);
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, "
-			"old_initialized_size 0x%llx, "
-			"new_initialized_size 0x%llx, i_size 0x%llx.",
-			vi->i_ino, (unsigned)le32_to_cpu(ni->type),
-			(unsigned long long)old_init_size,
-			(unsigned long long)new_init_size, old_i_size);
-	if (!NInoAttr(ni))
-		base_ni = ni;
-	else
-		base_ni = ni->ext.base_ntfs_ino;
-	/* Use goto to reduce indentation and we need the label below anyway. */
-	if (NInoNonResident(ni))
-		goto do_non_resident_extend;
-	BUG_ON(old_init_size != old_i_size);
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		m = NULL;
-		goto err_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT)
-			err = -EIO;
-		goto err_out;
-	}
-	m = ctx->mrec;
-	a = ctx->attr;
-	BUG_ON(a->non_resident);
-	/* The total length of the attribute value. */
-	attr_len = le32_to_cpu(a->data.resident.value_length);
-	BUG_ON(old_i_size != (loff_t)attr_len);
-	/*
-	 * Do the zeroing in the mft record and update the attribute size in
-	 * the mft record.
-	 */
-	kattr = (u8*)a + le16_to_cpu(a->data.resident.value_offset);
-	memset(kattr + attr_len, 0, new_init_size - attr_len);
-	a->data.resident.value_length = cpu_to_le32((u32)new_init_size);
-	/* Finally, update the sizes in the vfs and ntfs inodes. */
-	write_lock_irqsave(&ni->size_lock, flags);
-	i_size_write(vi, new_init_size);
-	ni->initialized_size = new_init_size;
-	write_unlock_irqrestore(&ni->size_lock, flags);
-	goto done;
-do_non_resident_extend:
-	/*
-	 * If the new initialized size @new_init_size exceeds the current file
-	 * size (vfs inode->i_size), we need to extend the file size to the
-	 * new initialized size.
-	 */
-	if (new_init_size > old_i_size) {
-		m = map_mft_record(base_ni);
-		if (IS_ERR(m)) {
-			err = PTR_ERR(m);
-			m = NULL;
-			goto err_out;
-		}
-		ctx = ntfs_attr_get_search_ctx(base_ni, m);
-		if (unlikely(!ctx)) {
-			err = -ENOMEM;
-			goto err_out;
-		}
-		err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-				CASE_SENSITIVE, 0, NULL, 0, ctx);
-		if (unlikely(err)) {
-			if (err == -ENOENT)
-				err = -EIO;
-			goto err_out;
-		}
-		m = ctx->mrec;
-		a = ctx->attr;
-		BUG_ON(!a->non_resident);
-		BUG_ON(old_i_size != (loff_t)
-				sle64_to_cpu(a->data.non_resident.data_size));
-		a->data.non_resident.data_size = cpu_to_sle64(new_init_size);
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
-		mark_mft_record_dirty(ctx->ntfs_ino);
-		/* Update the file size in the vfs inode. */
-		i_size_write(vi, new_init_size);
-		ntfs_attr_put_search_ctx(ctx);
-		ctx = NULL;
-		unmap_mft_record(base_ni);
-		m = NULL;
-	}
-	mapping = vi->i_mapping;
-	index = old_init_size >> PAGE_SHIFT;
-	end_index = (new_init_size + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	do {
-		/*
-		 * Read the page.  If the page is not present, this will zero
-		 * the uninitialized regions for us.
-		 */
-		page = read_mapping_page(mapping, index, NULL);
-		if (IS_ERR(page)) {
-			err = PTR_ERR(page);
-			goto init_err_out;
-		}
-		/*
-		 * Update the initialized size in the ntfs inode.  This is
-		 * enough to make ntfs_writepage() work.
-		 */
-		write_lock_irqsave(&ni->size_lock, flags);
-		ni->initialized_size = (s64)(index + 1) << PAGE_SHIFT;
-		if (ni->initialized_size > new_init_size)
-			ni->initialized_size = new_init_size;
-		write_unlock_irqrestore(&ni->size_lock, flags);
-		/* Set the page dirty so it gets written out. */
-		set_page_dirty(page);
-		put_page(page);
-		/*
-		 * Play nice with the vm and the rest of the system.  This is
-		 * very much needed as we can potentially be modifying the
-		 * initialised size from a very small value to a really huge
-		 * value, e.g.
-		 *	f = open(somefile, O_TRUNC);
-		 *	truncate(f, 10GiB);
-		 *	seek(f, 10GiB);
-		 *	write(f, 1);
-		 * And this would mean we would be marking dirty hundreds of
-		 * thousands of pages or as in the above example more than
-		 * two and a half million pages!
-		 *
-		 * TODO: For sparse pages could optimize this workload by using
-		 * the FsMisc / MiscFs page bit as a "PageIsSparse" bit.  This
-		 * would be set in read_folio for sparse pages and here we would
-		 * not need to mark dirty any pages which have this bit set.
-		 * The only caveat is that we have to clear the bit everywhere
-		 * where we allocate any clusters that lie in the page or that
-		 * contain the page.
-		 *
-		 * TODO: An even greater optimization would be for us to only
-		 * call read_folio() on pages which are not in sparse regions as
-		 * determined from the runlist.  This would greatly reduce the
-		 * number of pages we read and make dirty in the case of sparse
-		 * files.
-		 */
-		balance_dirty_pages_ratelimited(mapping);
-		cond_resched();
-	} while (++index < end_index);
-	read_lock_irqsave(&ni->size_lock, flags);
-	BUG_ON(ni->initialized_size != new_init_size);
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	/* Now bring in sync the initialized_size in the mft record. */
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		m = NULL;
-		goto init_err_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto init_err_out;
-	}
-	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT)
-			err = -EIO;
-		goto init_err_out;
-	}
-	m = ctx->mrec;
-	a = ctx->attr;
-	BUG_ON(!a->non_resident);
-	a->data.non_resident.initialized_size = cpu_to_sle64(new_init_size);
-done:
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(base_ni);
-	ntfs_debug("Done, initialized_size 0x%llx, i_size 0x%llx.",
-			(unsigned long long)new_init_size, i_size_read(vi));
-	return 0;
-init_err_out:
-	write_lock_irqsave(&ni->size_lock, flags);
-	ni->initialized_size = old_init_size;
-	write_unlock_irqrestore(&ni->size_lock, flags);
-err_out:
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(base_ni);
-	ntfs_debug("Failed.  Returning error code %i.", err);
-	return err;
-}
-
-static ssize_t ntfs_prepare_file_for_write(struct kiocb *iocb,
-		struct iov_iter *from)
-{
-	loff_t pos;
-	s64 end, ll;
-	ssize_t err;
-	unsigned long flags;
-	struct file *file = iocb->ki_filp;
-	struct inode *vi = file_inode(file);
-	ntfs_inode *ni = NTFS_I(vi);
-	ntfs_volume *vol = ni->vol;
-
-	ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, pos "
-			"0x%llx, count 0x%zx.", vi->i_ino,
-			(unsigned)le32_to_cpu(ni->type),
-			(unsigned long long)iocb->ki_pos,
-			iov_iter_count(from));
-	err = generic_write_checks(iocb, from);
-	if (unlikely(err <= 0))
-		goto out;
-	/*
-	 * All checks have passed.  Before we start doing any writing we want
-	 * to abort any totally illegal writes.
-	 */
-	BUG_ON(NInoMstProtected(ni));
-	BUG_ON(ni->type != AT_DATA);
-	/* If file is encrypted, deny access, just like NT4. */
-	if (NInoEncrypted(ni)) {
-		/* Only $DATA attributes can be encrypted. */
-		/*
-		 * Reminder for later: Encrypted files are _always_
-		 * non-resident so that the content can always be encrypted.
-		 */
-		ntfs_debug("Denying write access to encrypted file.");
-		err = -EACCES;
-		goto out;
-	}
-	if (NInoCompressed(ni)) {
-		/* Only unnamed $DATA attribute can be compressed. */
-		BUG_ON(ni->name_len);
-		/*
-		 * Reminder for later: If resident, the data is not actually
-		 * compressed.  Only on the switch to non-resident does
-		 * compression kick in.  This is in contrast to encrypted files
-		 * (see above).
-		 */
-		ntfs_error(vi->i_sb, "Writing to compressed files is not "
-				"implemented yet.  Sorry.");
-		err = -EOPNOTSUPP;
-		goto out;
-	}
-	err = file_remove_privs(file);
-	if (unlikely(err))
-		goto out;
-	/*
-	 * Our ->update_time method always succeeds thus file_update_time()
-	 * cannot fail either so there is no need to check the return code.
-	 */
-	file_update_time(file);
-	pos = iocb->ki_pos;
-	/* The first byte after the last cluster being written to. */
-	end = (pos + iov_iter_count(from) + vol->cluster_size_mask) &
-			~(u64)vol->cluster_size_mask;
-	/*
-	 * If the write goes beyond the allocated size, extend the allocation
-	 * to cover the whole of the write, rounded up to the nearest cluster.
-	 */
-	read_lock_irqsave(&ni->size_lock, flags);
-	ll = ni->allocated_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	if (end > ll) {
-		/*
-		 * Extend the allocation without changing the data size.
-		 *
-		 * Note we ensure the allocation is big enough to at least
-		 * write some data but we do not require the allocation to be
-		 * complete, i.e. it may be partial.
-		 */
-		ll = ntfs_attr_extend_allocation(ni, end, -1, pos);
-		if (likely(ll >= 0)) {
-			BUG_ON(pos >= ll);
-			/* If the extension was partial truncate the write. */
-			if (end > ll) {
-				ntfs_debug("Truncating write to inode 0x%lx, "
-						"attribute type 0x%x, because "
-						"the allocation was only "
-						"partially extended.",
-						vi->i_ino, (unsigned)
-						le32_to_cpu(ni->type));
-				iov_iter_truncate(from, ll - pos);
-			}
-		} else {
-			err = ll;
-			read_lock_irqsave(&ni->size_lock, flags);
-			ll = ni->allocated_size;
-			read_unlock_irqrestore(&ni->size_lock, flags);
-			/* Perform a partial write if possible or fail. */
-			if (pos < ll) {
-				ntfs_debug("Truncating write to inode 0x%lx "
-						"attribute type 0x%x, because "
-						"extending the allocation "
-						"failed (error %d).",
-						vi->i_ino, (unsigned)
-						le32_to_cpu(ni->type),
-						(int)-err);
-				iov_iter_truncate(from, ll - pos);
-			} else {
-				if (err != -ENOSPC)
-					ntfs_error(vi->i_sb, "Cannot perform "
-							"write to inode "
-							"0x%lx, attribute "
-							"type 0x%x, because "
-							"extending the "
-							"allocation failed "
-							"(error %ld).",
-							vi->i_ino, (unsigned)
-							le32_to_cpu(ni->type),
-							(long)-err);
-				else
-					ntfs_debug("Cannot perform write to "
-							"inode 0x%lx, "
-							"attribute type 0x%x, "
-							"because there is not "
-							"space left.",
-							vi->i_ino, (unsigned)
-							le32_to_cpu(ni->type));
-				goto out;
-			}
-		}
-	}
-	/*
-	 * If the write starts beyond the initialized size, extend it up to the
-	 * beginning of the write and initialize all non-sparse space between
-	 * the old initialized size and the new one.  This automatically also
-	 * increments the vfs inode->i_size to keep it above or equal to the
-	 * initialized_size.
-	 */
-	read_lock_irqsave(&ni->size_lock, flags);
-	ll = ni->initialized_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	if (pos > ll) {
-		/*
-		 * Wait for ongoing direct i/o to complete before proceeding.
-		 * New direct i/o cannot start as we hold i_mutex.
-		 */
-		inode_dio_wait(vi);
-		err = ntfs_attr_extend_initialized(ni, pos);
-		if (unlikely(err < 0))
-			ntfs_error(vi->i_sb, "Cannot perform write to inode "
-					"0x%lx, attribute type 0x%x, because "
-					"extending the initialized size "
-					"failed (error %d).", vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type),
-					(int)-err);
-	}
-out:
-	return err;
-}
-
-/**
- * __ntfs_grab_cache_pages - obtain a number of locked pages
- * @mapping:	address space mapping from which to obtain page cache pages
- * @index:	starting index in @mapping at which to begin obtaining pages
- * @nr_pages:	number of page cache pages to obtain
- * @pages:	array of pages in which to return the obtained page cache pages
- * @cached_page: allocated but as yet unused page
- *
- * Obtain @nr_pages locked page cache pages from the mapping @mapping and
- * starting at index @index.
- *
- * If a page is newly created, add it to lru list
- *
- * Note, the page locks are obtained in ascending page index order.
- */
-static inline int __ntfs_grab_cache_pages(struct address_space *mapping,
-		pgoff_t index, const unsigned nr_pages, struct page **pages,
-		struct page **cached_page)
-{
-	int err, nr;
-
-	BUG_ON(!nr_pages);
-	err = nr = 0;
-	do {
-		pages[nr] = find_get_page_flags(mapping, index, FGP_LOCK |
-				FGP_ACCESSED);
-		if (!pages[nr]) {
-			if (!*cached_page) {
-				*cached_page = page_cache_alloc(mapping);
-				if (unlikely(!*cached_page)) {
-					err = -ENOMEM;
-					goto err_out;
-				}
-			}
-			err = add_to_page_cache_lru(*cached_page, mapping,
-				   index,
-				   mapping_gfp_constraint(mapping, GFP_KERNEL));
-			if (unlikely(err)) {
-				if (err == -EEXIST)
-					continue;
-				goto err_out;
-			}
-			pages[nr] = *cached_page;
-			*cached_page = NULL;
-		}
-		index++;
-		nr++;
-	} while (nr < nr_pages);
-out:
-	return err;
-err_out:
-	while (nr > 0) {
-		unlock_page(pages[--nr]);
-		put_page(pages[nr]);
-	}
-	goto out;
-}
-
-static inline void ntfs_submit_bh_for_read(struct buffer_head *bh)
-{
-	lock_buffer(bh);
-	get_bh(bh);
-	bh->b_end_io = end_buffer_read_sync;
-	submit_bh(REQ_OP_READ, bh);
-}
-
-/**
- * ntfs_prepare_pages_for_non_resident_write - prepare pages for receiving data
- * @pages:	array of destination pages
- * @nr_pages:	number of pages in @pages
- * @pos:	byte position in file at which the write begins
- * @bytes:	number of bytes to be written
- *
- * This is called for non-resident attributes from ntfs_file_buffered_write()
- * with i_mutex held on the inode (@pages[0]->mapping->host).  There are
- * @nr_pages pages in @pages which are locked but not kmap()ped.  The source
- * data has not yet been copied into the @pages.
- * 
- * Need to fill any holes with actual clusters, allocate buffers if necessary,
- * ensure all the buffers are mapped, and bring uptodate any buffers that are
- * only partially being written to.
- *
- * If @nr_pages is greater than one, we are guaranteed that the cluster size is
- * greater than PAGE_SIZE, that all pages in @pages are entirely inside
- * the same cluster and that they are the entirety of that cluster, and that
- * the cluster is sparse, i.e. we need to allocate a cluster to fill the hole.
- *
- * i_size is not to be modified yet.
- *
- * Return 0 on success or -errno on error.
- */
-static int ntfs_prepare_pages_for_non_resident_write(struct page **pages,
-		unsigned nr_pages, s64 pos, size_t bytes)
-{
-	VCN vcn, highest_vcn = 0, cpos, cend, bh_cpos, bh_cend;
-	LCN lcn;
-	s64 bh_pos, vcn_len, end, initialized_size;
-	sector_t lcn_block;
-	struct folio *folio;
-	struct inode *vi;
-	ntfs_inode *ni, *base_ni = NULL;
-	ntfs_volume *vol;
-	runlist_element *rl, *rl2;
-	struct buffer_head *bh, *head, *wait[2], **wait_bh = wait;
-	ntfs_attr_search_ctx *ctx = NULL;
-	MFT_RECORD *m = NULL;
-	ATTR_RECORD *a = NULL;
-	unsigned long flags;
-	u32 attr_rec_len = 0;
-	unsigned blocksize, u;
-	int err, mp_size;
-	bool rl_write_locked, was_hole, is_retry;
-	unsigned char blocksize_bits;
-	struct {
-		u8 runlist_merged:1;
-		u8 mft_attr_mapped:1;
-		u8 mp_rebuilt:1;
-		u8 attr_switched:1;
-	} status = { 0, 0, 0, 0 };
-
-	BUG_ON(!nr_pages);
-	BUG_ON(!pages);
-	BUG_ON(!*pages);
-	vi = pages[0]->mapping->host;
-	ni = NTFS_I(vi);
-	vol = ni->vol;
-	ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, start page "
-			"index 0x%lx, nr_pages 0x%x, pos 0x%llx, bytes 0x%zx.",
-			vi->i_ino, ni->type, pages[0]->index, nr_pages,
-			(long long)pos, bytes);
-	blocksize = vol->sb->s_blocksize;
-	blocksize_bits = vol->sb->s_blocksize_bits;
-	rl_write_locked = false;
-	rl = NULL;
-	err = 0;
-	vcn = lcn = -1;
-	vcn_len = 0;
-	lcn_block = -1;
-	was_hole = false;
-	cpos = pos >> vol->cluster_size_bits;
-	end = pos + bytes;
-	cend = (end + vol->cluster_size - 1) >> vol->cluster_size_bits;
-	/*
-	 * Loop over each buffer in each folio.  Use goto to
-	 * reduce indentation.
-	 */
-	u = 0;
-do_next_folio:
-	folio = page_folio(pages[u]);
-	bh_pos = folio_pos(folio);
-	head = folio_buffers(folio);
-	if (!head)
-		/*
-		 * create_empty_buffers() will create uptodate/dirty
-		 * buffers if the folio is uptodate/dirty.
-		 */
-		head = create_empty_buffers(folio, blocksize, 0);
-	bh = head;
-	do {
-		VCN cdelta;
-		s64 bh_end;
-		unsigned bh_cofs;
-
-		/* Clear buffer_new on all buffers to reinitialise state. */
-		if (buffer_new(bh))
-			clear_buffer_new(bh);
-		bh_end = bh_pos + blocksize;
-		bh_cpos = bh_pos >> vol->cluster_size_bits;
-		bh_cofs = bh_pos & vol->cluster_size_mask;
-		if (buffer_mapped(bh)) {
-			/*
-			 * The buffer is already mapped.  If it is uptodate,
-			 * ignore it.
-			 */
-			if (buffer_uptodate(bh))
-				continue;
-			/*
-			 * The buffer is not uptodate.  If the folio is uptodate
-			 * set the buffer uptodate and otherwise ignore it.
-			 */
-			if (folio_test_uptodate(folio)) {
-				set_buffer_uptodate(bh);
-				continue;
-			}
-			/*
-			 * Neither the folio nor the buffer are uptodate.  If
-			 * the buffer is only partially being written to, we
-			 * need to read it in before the write, i.e. now.
-			 */
-			if ((bh_pos < pos && bh_end > pos) ||
-					(bh_pos < end && bh_end > end)) {
-				/*
-				 * If the buffer is fully or partially within
-				 * the initialized size, do an actual read.
-				 * Otherwise, simply zero the buffer.
-				 */
-				read_lock_irqsave(&ni->size_lock, flags);
-				initialized_size = ni->initialized_size;
-				read_unlock_irqrestore(&ni->size_lock, flags);
-				if (bh_pos < initialized_size) {
-					ntfs_submit_bh_for_read(bh);
-					*wait_bh++ = bh;
-				} else {
-					folio_zero_range(folio, bh_offset(bh),
-							blocksize);
-					set_buffer_uptodate(bh);
-				}
-			}
-			continue;
-		}
-		/* Unmapped buffer.  Need to map it. */
-		bh->b_bdev = vol->sb->s_bdev;
-		/*
-		 * If the current buffer is in the same clusters as the map
-		 * cache, there is no need to check the runlist again.  The
-		 * map cache is made up of @vcn, which is the first cached file
-		 * cluster, @vcn_len which is the number of cached file
-		 * clusters, @lcn is the device cluster corresponding to @vcn,
-		 * and @lcn_block is the block number corresponding to @lcn.
-		 */
-		cdelta = bh_cpos - vcn;
-		if (likely(!cdelta || (cdelta > 0 && cdelta < vcn_len))) {
-map_buffer_cached:
-			BUG_ON(lcn < 0);
-			bh->b_blocknr = lcn_block +
-					(cdelta << (vol->cluster_size_bits -
-					blocksize_bits)) +
-					(bh_cofs >> blocksize_bits);
-			set_buffer_mapped(bh);
-			/*
-			 * If the folio is uptodate so is the buffer.  If the
-			 * buffer is fully outside the write, we ignore it if
-			 * it was already allocated and we mark it dirty so it
-			 * gets written out if we allocated it.  On the other
-			 * hand, if we allocated the buffer but we are not
-			 * marking it dirty we set buffer_new so we can do
-			 * error recovery.
-			 */
-			if (folio_test_uptodate(folio)) {
-				if (!buffer_uptodate(bh))
-					set_buffer_uptodate(bh);
-				if (unlikely(was_hole)) {
-					/* We allocated the buffer. */
-					clean_bdev_bh_alias(bh);
-					if (bh_end <= pos || bh_pos >= end)
-						mark_buffer_dirty(bh);
-					else
-						set_buffer_new(bh);
-				}
-				continue;
-			}
-			/* Page is _not_ uptodate. */
-			if (likely(!was_hole)) {
-				/*
-				 * Buffer was already allocated.  If it is not
-				 * uptodate and is only partially being written
-				 * to, we need to read it in before the write,
-				 * i.e. now.
-				 */
-				if (!buffer_uptodate(bh) && bh_pos < end &&
-						bh_end > pos &&
-						(bh_pos < pos ||
-						bh_end > end)) {
-					/*
-					 * If the buffer is fully or partially
-					 * within the initialized size, do an
-					 * actual read.  Otherwise, simply zero
-					 * the buffer.
-					 */
-					read_lock_irqsave(&ni->size_lock,
-							flags);
-					initialized_size = ni->initialized_size;
-					read_unlock_irqrestore(&ni->size_lock,
-							flags);
-					if (bh_pos < initialized_size) {
-						ntfs_submit_bh_for_read(bh);
-						*wait_bh++ = bh;
-					} else {
-						folio_zero_range(folio,
-								bh_offset(bh),
-								blocksize);
-						set_buffer_uptodate(bh);
-					}
-				}
-				continue;
-			}
-			/* We allocated the buffer. */
-			clean_bdev_bh_alias(bh);
-			/*
-			 * If the buffer is fully outside the write, zero it,
-			 * set it uptodate, and mark it dirty so it gets
-			 * written out.  If it is partially being written to,
-			 * zero region surrounding the write but leave it to
-			 * commit write to do anything else.  Finally, if the
-			 * buffer is fully being overwritten, do nothing.
-			 */
-			if (bh_end <= pos || bh_pos >= end) {
-				if (!buffer_uptodate(bh)) {
-					folio_zero_range(folio, bh_offset(bh),
-							blocksize);
-					set_buffer_uptodate(bh);
-				}
-				mark_buffer_dirty(bh);
-				continue;
-			}
-			set_buffer_new(bh);
-			if (!buffer_uptodate(bh) &&
-					(bh_pos < pos || bh_end > end)) {
-				u8 *kaddr;
-				unsigned pofs;
-					
-				kaddr = kmap_local_folio(folio, 0);
-				if (bh_pos < pos) {
-					pofs = bh_pos & ~PAGE_MASK;
-					memset(kaddr + pofs, 0, pos - bh_pos);
-				}
-				if (bh_end > end) {
-					pofs = end & ~PAGE_MASK;
-					memset(kaddr + pofs, 0, bh_end - end);
-				}
-				kunmap_local(kaddr);
-				flush_dcache_folio(folio);
-			}
-			continue;
-		}
-		/*
-		 * Slow path: this is the first buffer in the cluster.  If it
-		 * is outside allocated size and is not uptodate, zero it and
-		 * set it uptodate.
-		 */
-		read_lock_irqsave(&ni->size_lock, flags);
-		initialized_size = ni->allocated_size;
-		read_unlock_irqrestore(&ni->size_lock, flags);
-		if (bh_pos > initialized_size) {
-			if (folio_test_uptodate(folio)) {
-				if (!buffer_uptodate(bh))
-					set_buffer_uptodate(bh);
-			} else if (!buffer_uptodate(bh)) {
-				folio_zero_range(folio, bh_offset(bh),
-						blocksize);
-				set_buffer_uptodate(bh);
-			}
-			continue;
-		}
-		is_retry = false;
-		if (!rl) {
-			down_read(&ni->runlist.lock);
-retry_remap:
-			rl = ni->runlist.rl;
-		}
-		if (likely(rl != NULL)) {
-			/* Seek to element containing target cluster. */
-			while (rl->length && rl[1].vcn <= bh_cpos)
-				rl++;
-			lcn = ntfs_rl_vcn_to_lcn(rl, bh_cpos);
-			if (likely(lcn >= 0)) {
-				/*
-				 * Successful remap, setup the map cache and
-				 * use that to deal with the buffer.
-				 */
-				was_hole = false;
-				vcn = bh_cpos;
-				vcn_len = rl[1].vcn - vcn;
-				lcn_block = lcn << (vol->cluster_size_bits -
-						blocksize_bits);
-				cdelta = 0;
-				/*
-				 * If the number of remaining clusters touched
-				 * by the write is smaller or equal to the
-				 * number of cached clusters, unlock the
-				 * runlist as the map cache will be used from
-				 * now on.
-				 */
-				if (likely(vcn + vcn_len >= cend)) {
-					if (rl_write_locked) {
-						up_write(&ni->runlist.lock);
-						rl_write_locked = false;
-					} else
-						up_read(&ni->runlist.lock);
-					rl = NULL;
-				}
-				goto map_buffer_cached;
-			}
-		} else
-			lcn = LCN_RL_NOT_MAPPED;
-		/*
-		 * If it is not a hole and not out of bounds, the runlist is
-		 * probably unmapped so try to map it now.
-		 */
-		if (unlikely(lcn != LCN_HOLE && lcn != LCN_ENOENT)) {
-			if (likely(!is_retry && lcn == LCN_RL_NOT_MAPPED)) {
-				/* Attempt to map runlist. */
-				if (!rl_write_locked) {
-					/*
-					 * We need the runlist locked for
-					 * writing, so if it is locked for
-					 * reading relock it now and retry in
-					 * case it changed whilst we dropped
-					 * the lock.
-					 */
-					up_read(&ni->runlist.lock);
-					down_write(&ni->runlist.lock);
-					rl_write_locked = true;
-					goto retry_remap;
-				}
-				err = ntfs_map_runlist_nolock(ni, bh_cpos,
-						NULL);
-				if (likely(!err)) {
-					is_retry = true;
-					goto retry_remap;
-				}
-				/*
-				 * If @vcn is out of bounds, pretend @lcn is
-				 * LCN_ENOENT.  As long as the buffer is out
-				 * of bounds this will work fine.
-				 */
-				if (err == -ENOENT) {
-					lcn = LCN_ENOENT;
-					err = 0;
-					goto rl_not_mapped_enoent;
-				}
-			} else
-				err = -EIO;
-			/* Failed to map the buffer, even after retrying. */
-			bh->b_blocknr = -1;
-			ntfs_error(vol->sb, "Failed to write to inode 0x%lx, "
-					"attribute type 0x%x, vcn 0x%llx, "
-					"vcn offset 0x%x, because its "
-					"location on disk could not be "
-					"determined%s (error code %i).",
-					ni->mft_no, ni->type,
-					(unsigned long long)bh_cpos,
-					(unsigned)bh_pos &
-					vol->cluster_size_mask,
-					is_retry ? " even after retrying" : "",
-					err);
-			break;
-		}
-rl_not_mapped_enoent:
-		/*
-		 * The buffer is in a hole or out of bounds.  We need to fill
-		 * the hole, unless the buffer is in a cluster which is not
-		 * touched by the write, in which case we just leave the buffer
-		 * unmapped.  This can only happen when the cluster size is
-		 * less than the page cache size.
-		 */
-		if (unlikely(vol->cluster_size < PAGE_SIZE)) {
-			bh_cend = (bh_end + vol->cluster_size - 1) >>
-					vol->cluster_size_bits;
-			if ((bh_cend <= cpos || bh_cpos >= cend)) {
-				bh->b_blocknr = -1;
-				/*
-				 * If the buffer is uptodate we skip it.  If it
-				 * is not but the folio is uptodate, we can set
-				 * the buffer uptodate.  If the folio is not
-				 * uptodate, we can clear the buffer and set it
-				 * uptodate.  Whether this is worthwhile is
-				 * debatable and this could be removed.
-				 */
-				if (folio_test_uptodate(folio)) {
-					if (!buffer_uptodate(bh))
-						set_buffer_uptodate(bh);
-				} else if (!buffer_uptodate(bh)) {
-					folio_zero_range(folio, bh_offset(bh),
-						blocksize);
-					set_buffer_uptodate(bh);
-				}
-				continue;
-			}
-		}
-		/*
-		 * Out of bounds buffer is invalid if it was not really out of
-		 * bounds.
-		 */
-		BUG_ON(lcn != LCN_HOLE);
-		/*
-		 * We need the runlist locked for writing, so if it is locked
-		 * for reading relock it now and retry in case it changed
-		 * whilst we dropped the lock.
-		 */
-		BUG_ON(!rl);
-		if (!rl_write_locked) {
-			up_read(&ni->runlist.lock);
-			down_write(&ni->runlist.lock);
-			rl_write_locked = true;
-			goto retry_remap;
-		}
-		/* Find the previous last allocated cluster. */
-		BUG_ON(rl->lcn != LCN_HOLE);
-		lcn = -1;
-		rl2 = rl;
-		while (--rl2 >= ni->runlist.rl) {
-			if (rl2->lcn >= 0) {
-				lcn = rl2->lcn + rl2->length;
-				break;
-			}
-		}
-		rl2 = ntfs_cluster_alloc(vol, bh_cpos, 1, lcn, DATA_ZONE,
-				false);
-		if (IS_ERR(rl2)) {
-			err = PTR_ERR(rl2);
-			ntfs_debug("Failed to allocate cluster, error code %i.",
-					err);
-			break;
-		}
-		lcn = rl2->lcn;
-		rl = ntfs_runlists_merge(ni->runlist.rl, rl2);
-		if (IS_ERR(rl)) {
-			err = PTR_ERR(rl);
-			if (err != -ENOMEM)
-				err = -EIO;
-			if (ntfs_cluster_free_from_rl(vol, rl2)) {
-				ntfs_error(vol->sb, "Failed to release "
-						"allocated cluster in error "
-						"code path.  Run chkdsk to "
-						"recover the lost cluster.");
-				NVolSetErrors(vol);
-			}
-			ntfs_free(rl2);
-			break;
-		}
-		ni->runlist.rl = rl;
-		status.runlist_merged = 1;
-		ntfs_debug("Allocated cluster, lcn 0x%llx.",
-				(unsigned long long)lcn);
-		/* Map and lock the mft record and get the attribute record. */
-		if (!NInoAttr(ni))
-			base_ni = ni;
-		else
-			base_ni = ni->ext.base_ntfs_ino;
-		m = map_mft_record(base_ni);
-		if (IS_ERR(m)) {
-			err = PTR_ERR(m);
-			break;
-		}
-		ctx = ntfs_attr_get_search_ctx(base_ni, m);
-		if (unlikely(!ctx)) {
-			err = -ENOMEM;
-			unmap_mft_record(base_ni);
-			break;
-		}
-		status.mft_attr_mapped = 1;
-		err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-				CASE_SENSITIVE, bh_cpos, NULL, 0, ctx);
-		if (unlikely(err)) {
-			if (err == -ENOENT)
-				err = -EIO;
-			break;
-		}
-		m = ctx->mrec;
-		a = ctx->attr;
-		/*
-		 * Find the runlist element with which the attribute extent
-		 * starts.  Note, we cannot use the _attr_ version because we
-		 * have mapped the mft record.  That is ok because we know the
-		 * runlist fragment must be mapped already to have ever gotten
-		 * here, so we can just use the _rl_ version.
-		 */
-		vcn = sle64_to_cpu(a->data.non_resident.lowest_vcn);
-		rl2 = ntfs_rl_find_vcn_nolock(rl, vcn);
-		BUG_ON(!rl2);
-		BUG_ON(!rl2->length);
-		BUG_ON(rl2->lcn < LCN_HOLE);
-		highest_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn);
-		/*
-		 * If @highest_vcn is zero, calculate the real highest_vcn
-		 * (which can really be zero).
-		 */
-		if (!highest_vcn)
-			highest_vcn = (sle64_to_cpu(
-					a->data.non_resident.allocated_size) >>
-					vol->cluster_size_bits) - 1;
-		/*
-		 * Determine the size of the mapping pairs array for the new
-		 * extent, i.e. the old extent with the hole filled.
-		 */
-		mp_size = ntfs_get_size_for_mapping_pairs(vol, rl2, vcn,
-				highest_vcn);
-		if (unlikely(mp_size <= 0)) {
-			if (!(err = mp_size))
-				err = -EIO;
-			ntfs_debug("Failed to get size for mapping pairs "
-					"array, error code %i.", err);
-			break;
-		}
-		/*
-		 * Resize the attribute record to fit the new mapping pairs
-		 * array.
-		 */
-		attr_rec_len = le32_to_cpu(a->length);
-		err = ntfs_attr_record_resize(m, a, mp_size + le16_to_cpu(
-				a->data.non_resident.mapping_pairs_offset));
-		if (unlikely(err)) {
-			BUG_ON(err != -ENOSPC);
-			// TODO: Deal with this by using the current attribute
-			// and fill it with as much of the mapping pairs
-			// array as possible.  Then loop over each attribute
-			// extent rewriting the mapping pairs arrays as we go
-			// along and if when we reach the end we have not
-			// enough space, try to resize the last attribute
-			// extent and if even that fails, add a new attribute
-			// extent.
-			// We could also try to resize at each step in the hope
-			// that we will not need to rewrite every single extent.
-			// Note, we may need to decompress some extents to fill
-			// the runlist as we are walking the extents...
-			ntfs_error(vol->sb, "Not enough space in the mft "
-					"record for the extended attribute "
-					"record.  This case is not "
-					"implemented yet.");
-			err = -EOPNOTSUPP;
-			break ;
-		}
-		status.mp_rebuilt = 1;
-		/*
-		 * Generate the mapping pairs array directly into the attribute
-		 * record.
-		 */
-		err = ntfs_mapping_pairs_build(vol, (u8*)a + le16_to_cpu(
-				a->data.non_resident.mapping_pairs_offset),
-				mp_size, rl2, vcn, highest_vcn, NULL);
-		if (unlikely(err)) {
-			ntfs_error(vol->sb, "Cannot fill hole in inode 0x%lx, "
-					"attribute type 0x%x, because building "
-					"the mapping pairs failed with error "
-					"code %i.", vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type), err);
-			err = -EIO;
-			break;
-		}
-		/* Update the highest_vcn but only if it was not set. */
-		if (unlikely(!a->data.non_resident.highest_vcn))
-			a->data.non_resident.highest_vcn =
-					cpu_to_sle64(highest_vcn);
-		/*
-		 * If the attribute is sparse/compressed, update the compressed
-		 * size in the ntfs_inode structure and the attribute record.
-		 */
-		if (likely(NInoSparse(ni) || NInoCompressed(ni))) {
-			/*
-			 * If we are not in the first attribute extent, switch
-			 * to it, but first ensure the changes will make it to
-			 * disk later.
-			 */
-			if (a->data.non_resident.lowest_vcn) {
-				flush_dcache_mft_record_page(ctx->ntfs_ino);
-				mark_mft_record_dirty(ctx->ntfs_ino);
-				ntfs_attr_reinit_search_ctx(ctx);
-				err = ntfs_attr_lookup(ni->type, ni->name,
-						ni->name_len, CASE_SENSITIVE,
-						0, NULL, 0, ctx);
-				if (unlikely(err)) {
-					status.attr_switched = 1;
-					break;
-				}
-				/* @m is not used any more so do not set it. */
-				a = ctx->attr;
-			}
-			write_lock_irqsave(&ni->size_lock, flags);
-			ni->itype.compressed.size += vol->cluster_size;
-			a->data.non_resident.compressed_size =
-					cpu_to_sle64(ni->itype.compressed.size);
-			write_unlock_irqrestore(&ni->size_lock, flags);
-		}
-		/* Ensure the changes make it to disk. */
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
-		mark_mft_record_dirty(ctx->ntfs_ino);
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(base_ni);
-		/* Successfully filled the hole. */
-		status.runlist_merged = 0;
-		status.mft_attr_mapped = 0;
-		status.mp_rebuilt = 0;
-		/* Setup the map cache and use that to deal with the buffer. */
-		was_hole = true;
-		vcn = bh_cpos;
-		vcn_len = 1;
-		lcn_block = lcn << (vol->cluster_size_bits - blocksize_bits);
-		cdelta = 0;
-		/*
-		 * If the number of remaining clusters in the @pages is smaller
-		 * or equal to the number of cached clusters, unlock the
-		 * runlist as the map cache will be used from now on.
-		 */
-		if (likely(vcn + vcn_len >= cend)) {
-			up_write(&ni->runlist.lock);
-			rl_write_locked = false;
-			rl = NULL;
-		}
-		goto map_buffer_cached;
-	} while (bh_pos += blocksize, (bh = bh->b_this_page) != head);
-	/* If there are no errors, do the next page. */
-	if (likely(!err && ++u < nr_pages))
-		goto do_next_folio;
-	/* If there are no errors, release the runlist lock if we took it. */
-	if (likely(!err)) {
-		if (unlikely(rl_write_locked)) {
-			up_write(&ni->runlist.lock);
-			rl_write_locked = false;
-		} else if (unlikely(rl))
-			up_read(&ni->runlist.lock);
-		rl = NULL;
-	}
-	/* If we issued read requests, let them complete. */
-	read_lock_irqsave(&ni->size_lock, flags);
-	initialized_size = ni->initialized_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	while (wait_bh > wait) {
-		bh = *--wait_bh;
-		wait_on_buffer(bh);
-		if (likely(buffer_uptodate(bh))) {
-			folio = bh->b_folio;
-			bh_pos = folio_pos(folio) + bh_offset(bh);
-			/*
-			 * If the buffer overflows the initialized size, need
-			 * to zero the overflowing region.
-			 */
-			if (unlikely(bh_pos + blocksize > initialized_size)) {
-				int ofs = 0;
-
-				if (likely(bh_pos < initialized_size))
-					ofs = initialized_size - bh_pos;
-				folio_zero_segment(folio, bh_offset(bh) + ofs,
-						blocksize);
-			}
-		} else /* if (unlikely(!buffer_uptodate(bh))) */
-			err = -EIO;
-	}
-	if (likely(!err)) {
-		/* Clear buffer_new on all buffers. */
-		u = 0;
-		do {
-			bh = head = page_buffers(pages[u]);
-			do {
-				if (buffer_new(bh))
-					clear_buffer_new(bh);
-			} while ((bh = bh->b_this_page) != head);
-		} while (++u < nr_pages);
-		ntfs_debug("Done.");
-		return err;
-	}
-	if (status.attr_switched) {
-		/* Get back to the attribute extent we modified. */
-		ntfs_attr_reinit_search_ctx(ctx);
-		if (ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-				CASE_SENSITIVE, bh_cpos, NULL, 0, ctx)) {
-			ntfs_error(vol->sb, "Failed to find required "
-					"attribute extent of attribute in "
-					"error code path.  Run chkdsk to "
-					"recover.");
-			write_lock_irqsave(&ni->size_lock, flags);
-			ni->itype.compressed.size += vol->cluster_size;
-			write_unlock_irqrestore(&ni->size_lock, flags);
-			flush_dcache_mft_record_page(ctx->ntfs_ino);
-			mark_mft_record_dirty(ctx->ntfs_ino);
-			/*
-			 * The only thing that is now wrong is the compressed
-			 * size of the base attribute extent which chkdsk
-			 * should be able to fix.
-			 */
-			NVolSetErrors(vol);
-		} else {
-			m = ctx->mrec;
-			a = ctx->attr;
-			status.attr_switched = 0;
-		}
-	}
-	/*
-	 * If the runlist has been modified, need to restore it by punching a
-	 * hole into it and we then need to deallocate the on-disk cluster as
-	 * well.  Note, we only modify the runlist if we are able to generate a
-	 * new mapping pairs array, i.e. only when the mapped attribute extent
-	 * is not switched.
-	 */
-	if (status.runlist_merged && !status.attr_switched) {
-		BUG_ON(!rl_write_locked);
-		/* Make the file cluster we allocated sparse in the runlist. */
-		if (ntfs_rl_punch_nolock(vol, &ni->runlist, bh_cpos, 1)) {
-			ntfs_error(vol->sb, "Failed to punch hole into "
-					"attribute runlist in error code "
-					"path.  Run chkdsk to recover the "
-					"lost cluster.");
-			NVolSetErrors(vol);
-		} else /* if (success) */ {
-			status.runlist_merged = 0;
-			/*
-			 * Deallocate the on-disk cluster we allocated but only
-			 * if we succeeded in punching its vcn out of the
-			 * runlist.
-			 */
-			down_write(&vol->lcnbmp_lock);
-			if (ntfs_bitmap_clear_bit(vol->lcnbmp_ino, lcn)) {
-				ntfs_error(vol->sb, "Failed to release "
-						"allocated cluster in error "
-						"code path.  Run chkdsk to "
-						"recover the lost cluster.");
-				NVolSetErrors(vol);
-			}
-			up_write(&vol->lcnbmp_lock);
-		}
-	}
-	/*
-	 * Resize the attribute record to its old size and rebuild the mapping
-	 * pairs array.  Note, we only can do this if the runlist has been
-	 * restored to its old state which also implies that the mapped
-	 * attribute extent is not switched.
-	 */
-	if (status.mp_rebuilt && !status.runlist_merged) {
-		if (ntfs_attr_record_resize(m, a, attr_rec_len)) {
-			ntfs_error(vol->sb, "Failed to restore attribute "
-					"record in error code path.  Run "
-					"chkdsk to recover.");
-			NVolSetErrors(vol);
-		} else /* if (success) */ {
-			if (ntfs_mapping_pairs_build(vol, (u8*)a +
-					le16_to_cpu(a->data.non_resident.
-					mapping_pairs_offset), attr_rec_len -
-					le16_to_cpu(a->data.non_resident.
-					mapping_pairs_offset), ni->runlist.rl,
-					vcn, highest_vcn, NULL)) {
-				ntfs_error(vol->sb, "Failed to restore "
-						"mapping pairs array in error "
-						"code path.  Run chkdsk to "
-						"recover.");
-				NVolSetErrors(vol);
-			}
-			flush_dcache_mft_record_page(ctx->ntfs_ino);
-			mark_mft_record_dirty(ctx->ntfs_ino);
-		}
-	}
-	/* Release the mft record and the attribute. */
-	if (status.mft_attr_mapped) {
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(base_ni);
-	}
-	/* Release the runlist lock. */
-	if (rl_write_locked)
-		up_write(&ni->runlist.lock);
-	else if (rl)
-		up_read(&ni->runlist.lock);
-	/*
-	 * Zero out any newly allocated blocks to avoid exposing stale data.
-	 * If BH_New is set, we know that the block was newly allocated above
-	 * and that it has not been fully zeroed and marked dirty yet.
-	 */
-	nr_pages = u;
-	u = 0;
-	end = bh_cpos << vol->cluster_size_bits;
-	do {
-		folio = page_folio(pages[u]);
-		bh = head = folio_buffers(folio);
-		do {
-			if (u == nr_pages &&
-			    folio_pos(folio) + bh_offset(bh) >= end)
-				break;
-			if (!buffer_new(bh))
-				continue;
-			clear_buffer_new(bh);
-			if (!buffer_uptodate(bh)) {
-				if (folio_test_uptodate(folio))
-					set_buffer_uptodate(bh);
-				else {
-					folio_zero_range(folio, bh_offset(bh),
-							blocksize);
-					set_buffer_uptodate(bh);
-				}
-			}
-			mark_buffer_dirty(bh);
-		} while ((bh = bh->b_this_page) != head);
-	} while (++u <= nr_pages);
-	ntfs_error(vol->sb, "Failed.  Returning error code %i.", err);
-	return err;
-}
-
-static inline void ntfs_flush_dcache_pages(struct page **pages,
-		unsigned nr_pages)
-{
-	BUG_ON(!nr_pages);
-	/*
-	 * Warning: Do not do the decrement at the same time as the call to
-	 * flush_dcache_page() because it is a NULL macro on i386 and hence the
-	 * decrement never happens so the loop never terminates.
-	 */
-	do {
-		--nr_pages;
-		flush_dcache_page(pages[nr_pages]);
-	} while (nr_pages > 0);
-}
-
-/**
- * ntfs_commit_pages_after_non_resident_write - commit the received data
- * @pages:	array of destination pages
- * @nr_pages:	number of pages in @pages
- * @pos:	byte position in file at which the write begins
- * @bytes:	number of bytes to be written
- *
- * See description of ntfs_commit_pages_after_write(), below.
- */
-static inline int ntfs_commit_pages_after_non_resident_write(
-		struct page **pages, const unsigned nr_pages,
-		s64 pos, size_t bytes)
-{
-	s64 end, initialized_size;
-	struct inode *vi;
-	ntfs_inode *ni, *base_ni;
-	struct buffer_head *bh, *head;
-	ntfs_attr_search_ctx *ctx;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
-	unsigned long flags;
-	unsigned blocksize, u;
-	int err;
-
-	vi = pages[0]->mapping->host;
-	ni = NTFS_I(vi);
-	blocksize = vi->i_sb->s_blocksize;
-	end = pos + bytes;
-	u = 0;
-	do {
-		s64 bh_pos;
-		struct page *page;
-		bool partial;
-
-		page = pages[u];
-		bh_pos = (s64)page->index << PAGE_SHIFT;
-		bh = head = page_buffers(page);
-		partial = false;
-		do {
-			s64 bh_end;
-
-			bh_end = bh_pos + blocksize;
-			if (bh_end <= pos || bh_pos >= end) {
-				if (!buffer_uptodate(bh))
-					partial = true;
-			} else {
-				set_buffer_uptodate(bh);
-				mark_buffer_dirty(bh);
-			}
-		} while (bh_pos += blocksize, (bh = bh->b_this_page) != head);
-		/*
-		 * If all buffers are now uptodate but the page is not, set the
-		 * page uptodate.
-		 */
-		if (!partial && !PageUptodate(page))
-			SetPageUptodate(page);
-	} while (++u < nr_pages);
-	/*
-	 * Finally, if we do not need to update initialized_size or i_size we
-	 * are finished.
-	 */
-	read_lock_irqsave(&ni->size_lock, flags);
-	initialized_size = ni->initialized_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	if (end <= initialized_size) {
-		ntfs_debug("Done.");
-		return 0;
-	}
-	/*
-	 * Update initialized_size/i_size as appropriate, both in the inode and
-	 * the mft record.
-	 */
-	if (!NInoAttr(ni))
-		base_ni = ni;
-	else
-		base_ni = ni->ext.base_ntfs_ino;
-	/* Map, pin, and lock the mft record. */
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		m = NULL;
-		ctx = NULL;
-		goto err_out;
-	}
-	BUG_ON(!NInoNonResident(ni));
-	ctx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT)
-			err = -EIO;
-		goto err_out;
-	}
-	a = ctx->attr;
-	BUG_ON(!a->non_resident);
-	write_lock_irqsave(&ni->size_lock, flags);
-	BUG_ON(end > ni->allocated_size);
-	ni->initialized_size = end;
-	a->data.non_resident.initialized_size = cpu_to_sle64(end);
-	if (end > i_size_read(vi)) {
-		i_size_write(vi, end);
-		a->data.non_resident.data_size =
-				a->data.non_resident.initialized_size;
-	}
-	write_unlock_irqrestore(&ni->size_lock, flags);
-	/* Mark the mft record dirty, so it gets written back. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-	ntfs_debug("Done.");
-	return 0;
-err_out:
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(base_ni);
-	ntfs_error(vi->i_sb, "Failed to update initialized_size/i_size (error "
-			"code %i).", err);
-	if (err != -ENOMEM)
-		NVolSetErrors(ni->vol);
-	return err;
-}
-
-/**
- * ntfs_commit_pages_after_write - commit the received data
- * @pages:	array of destination pages
- * @nr_pages:	number of pages in @pages
- * @pos:	byte position in file at which the write begins
- * @bytes:	number of bytes to be written
- *
- * This is called from ntfs_file_buffered_write() with i_mutex held on the inode
- * (@pages[0]->mapping->host).  There are @nr_pages pages in @pages which are
- * locked but not kmap()ped.  The source data has already been copied into the
- * @page.  ntfs_prepare_pages_for_non_resident_write() has been called before
- * the data was copied (for non-resident attributes only) and it returned
- * success.
- *
- * Need to set uptodate and mark dirty all buffers within the boundary of the
- * write.  If all buffers in a page are uptodate we set the page uptodate, too.
- *
- * Setting the buffers dirty ensures that they get written out later when
- * ntfs_writepage() is invoked by the VM.
- *
- * Finally, we need to update i_size and initialized_size as appropriate both
- * in the inode and the mft record.
- *
- * This is modelled after fs/buffer.c::generic_commit_write(), which marks
- * buffers uptodate and dirty, sets the page uptodate if all buffers in the
- * page are uptodate, and updates i_size if the end of io is beyond i_size.  In
- * that case, it also marks the inode dirty.
- *
- * If things have gone as outlined in
- * ntfs_prepare_pages_for_non_resident_write(), we do not need to do any page
- * content modifications here for non-resident attributes.  For resident
- * attributes we need to do the uptodate bringing here which we combine with
- * the copying into the mft record which means we save one atomic kmap.
- *
- * Return 0 on success or -errno on error.
- */
-static int ntfs_commit_pages_after_write(struct page **pages,
-		const unsigned nr_pages, s64 pos, size_t bytes)
-{
-	s64 end, initialized_size;
-	loff_t i_size;
-	struct inode *vi;
-	ntfs_inode *ni, *base_ni;
-	struct page *page;
-	ntfs_attr_search_ctx *ctx;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
-	char *kattr, *kaddr;
-	unsigned long flags;
-	u32 attr_len;
-	int err;
-
-	BUG_ON(!nr_pages);
-	BUG_ON(!pages);
-	page = pages[0];
-	BUG_ON(!page);
-	vi = page->mapping->host;
-	ni = NTFS_I(vi);
-	ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, start page "
-			"index 0x%lx, nr_pages 0x%x, pos 0x%llx, bytes 0x%zx.",
-			vi->i_ino, ni->type, page->index, nr_pages,
-			(long long)pos, bytes);
-	if (NInoNonResident(ni))
-		return ntfs_commit_pages_after_non_resident_write(pages,
-				nr_pages, pos, bytes);
-	BUG_ON(nr_pages > 1);
-	/*
-	 * Attribute is resident, implying it is not compressed, encrypted, or
-	 * sparse.
-	 */
-	if (!NInoAttr(ni))
-		base_ni = ni;
-	else
-		base_ni = ni->ext.base_ntfs_ino;
-	BUG_ON(NInoNonResident(ni));
-	/* Map, pin, and lock the mft record. */
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		m = NULL;
-		ctx = NULL;
-		goto err_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT)
-			err = -EIO;
-		goto err_out;
-	}
-	a = ctx->attr;
-	BUG_ON(a->non_resident);
-	/* The total length of the attribute value. */
-	attr_len = le32_to_cpu(a->data.resident.value_length);
-	i_size = i_size_read(vi);
-	BUG_ON(attr_len != i_size);
-	BUG_ON(pos > attr_len);
-	end = pos + bytes;
-	BUG_ON(end > le32_to_cpu(a->length) -
-			le16_to_cpu(a->data.resident.value_offset));
-	kattr = (u8*)a + le16_to_cpu(a->data.resident.value_offset);
-	kaddr = kmap_atomic(page);
-	/* Copy the received data from the page to the mft record. */
-	memcpy(kattr + pos, kaddr + pos, bytes);
-	/* Update the attribute length if necessary. */
-	if (end > attr_len) {
-		attr_len = end;
-		a->data.resident.value_length = cpu_to_le32(attr_len);
-	}
-	/*
-	 * If the page is not uptodate, bring the out of bounds area(s)
-	 * uptodate by copying data from the mft record to the page.
-	 */
-	if (!PageUptodate(page)) {
-		if (pos > 0)
-			memcpy(kaddr, kattr, pos);
-		if (end < attr_len)
-			memcpy(kaddr + end, kattr + end, attr_len - end);
-		/* Zero the region outside the end of the attribute value. */
-		memset(kaddr + attr_len, 0, PAGE_SIZE - attr_len);
-		flush_dcache_page(page);
-		SetPageUptodate(page);
-	}
-	kunmap_atomic(kaddr);
-	/* Update initialized_size/i_size if necessary. */
-	read_lock_irqsave(&ni->size_lock, flags);
-	initialized_size = ni->initialized_size;
-	BUG_ON(end > ni->allocated_size);
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	BUG_ON(initialized_size != i_size);
-	if (end > initialized_size) {
-		write_lock_irqsave(&ni->size_lock, flags);
-		ni->initialized_size = end;
-		i_size_write(vi, end);
-		write_unlock_irqrestore(&ni->size_lock, flags);
-	}
-	/* Mark the mft record dirty, so it gets written back. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-	ntfs_debug("Done.");
-	return 0;
-err_out:
-	if (err == -ENOMEM) {
-		ntfs_warning(vi->i_sb, "Error allocating memory required to "
-				"commit the write.");
-		if (PageUptodate(page)) {
-			ntfs_warning(vi->i_sb, "Page is uptodate, setting "
-					"dirty so the write will be retried "
-					"later on by the VM.");
-			/*
-			 * Put the page on mapping->dirty_pages, but leave its
-			 * buffers' dirty state as-is.
-			 */
-			__set_page_dirty_nobuffers(page);
-			err = 0;
-		} else
-			ntfs_error(vi->i_sb, "Page is not uptodate.  Written "
-					"data has been lost.");
-	} else {
-		ntfs_error(vi->i_sb, "Resident attribute commit write failed "
-				"with error %i.", err);
-		NVolSetErrors(ni->vol);
-	}
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(base_ni);
-	return err;
-}
-
-/*
- * Copy as much as we can into the pages and return the number of bytes which
- * were successfully copied.  If a fault is encountered then clear the pages
- * out to (ofs + bytes) and return the number of bytes which were copied.
- */
-static size_t ntfs_copy_from_user_iter(struct page **pages, unsigned nr_pages,
-		unsigned ofs, struct iov_iter *i, size_t bytes)
-{
-	struct page **last_page = pages + nr_pages;
-	size_t total = 0;
-	unsigned len, copied;
-
-	do {
-		len = PAGE_SIZE - ofs;
-		if (len > bytes)
-			len = bytes;
-		copied = copy_page_from_iter_atomic(*pages, ofs, len, i);
-		total += copied;
-		bytes -= copied;
-		if (!bytes)
-			break;
-		if (copied < len)
-			goto err;
-		ofs = 0;
-	} while (++pages < last_page);
-out:
-	return total;
-err:
-	/* Zero the rest of the target like __copy_from_user(). */
-	len = PAGE_SIZE - copied;
-	do {
-		if (len > bytes)
-			len = bytes;
-		zero_user(*pages, copied, len);
-		bytes -= len;
-		copied = 0;
-		len = PAGE_SIZE;
-	} while (++pages < last_page);
-	goto out;
-}
-
-/**
- * ntfs_perform_write - perform buffered write to a file
- * @file:	file to write to
- * @i:		iov_iter with data to write
- * @pos:	byte offset in file at which to begin writing to
- */
-static ssize_t ntfs_perform_write(struct file *file, struct iov_iter *i,
-		loff_t pos)
-{
-	struct address_space *mapping = file->f_mapping;
-	struct inode *vi = mapping->host;
-	ntfs_inode *ni = NTFS_I(vi);
-	ntfs_volume *vol = ni->vol;
-	struct page *pages[NTFS_MAX_PAGES_PER_CLUSTER];
-	struct page *cached_page = NULL;
-	VCN last_vcn;
-	LCN lcn;
-	size_t bytes;
-	ssize_t status, written = 0;
-	unsigned nr_pages;
-
-	ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, pos "
-			"0x%llx, count 0x%lx.", vi->i_ino,
-			(unsigned)le32_to_cpu(ni->type),
-			(unsigned long long)pos,
-			(unsigned long)iov_iter_count(i));
-	/*
-	 * If a previous ntfs_truncate() failed, repeat it and abort if it
-	 * fails again.
-	 */
-	if (unlikely(NInoTruncateFailed(ni))) {
-		int err;
-
-		inode_dio_wait(vi);
-		err = ntfs_truncate(vi);
-		if (err || NInoTruncateFailed(ni)) {
-			if (!err)
-				err = -EIO;
-			ntfs_error(vol->sb, "Cannot perform write to inode "
-					"0x%lx, attribute type 0x%x, because "
-					"ntfs_truncate() failed (error code "
-					"%i).", vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type), err);
-			return err;
-		}
-	}
-	/*
-	 * Determine the number of pages per cluster for non-resident
-	 * attributes.
-	 */
-	nr_pages = 1;
-	if (vol->cluster_size > PAGE_SIZE && NInoNonResident(ni))
-		nr_pages = vol->cluster_size >> PAGE_SHIFT;
-	last_vcn = -1;
-	do {
-		VCN vcn;
-		pgoff_t start_idx;
-		unsigned ofs, do_pages, u;
-		size_t copied;
-
-		start_idx = pos >> PAGE_SHIFT;
-		ofs = pos & ~PAGE_MASK;
-		bytes = PAGE_SIZE - ofs;
-		do_pages = 1;
-		if (nr_pages > 1) {
-			vcn = pos >> vol->cluster_size_bits;
-			if (vcn != last_vcn) {
-				last_vcn = vcn;
-				/*
-				 * Get the lcn of the vcn the write is in.  If
-				 * it is a hole, need to lock down all pages in
-				 * the cluster.
-				 */
-				down_read(&ni->runlist.lock);
-				lcn = ntfs_attr_vcn_to_lcn_nolock(ni, pos >>
-						vol->cluster_size_bits, false);
-				up_read(&ni->runlist.lock);
-				if (unlikely(lcn < LCN_HOLE)) {
-					if (lcn == LCN_ENOMEM)
-						status = -ENOMEM;
-					else {
-						status = -EIO;
-						ntfs_error(vol->sb, "Cannot "
-							"perform write to "
-							"inode 0x%lx, "
-							"attribute type 0x%x, "
-							"because the attribute "
-							"is corrupt.",
-							vi->i_ino, (unsigned)
-							le32_to_cpu(ni->type));
-					}
-					break;
-				}
-				if (lcn == LCN_HOLE) {
-					start_idx = (pos & ~(s64)
-							vol->cluster_size_mask)
-							>> PAGE_SHIFT;
-					bytes = vol->cluster_size - (pos &
-							vol->cluster_size_mask);
-					do_pages = nr_pages;
-				}
-			}
-		}
-		if (bytes > iov_iter_count(i))
-			bytes = iov_iter_count(i);
-again:
-		/*
-		 * Bring in the user page(s) that we will copy from _first_.
-		 * Otherwise there is a nasty deadlock on copying from the same
-		 * page(s) as we are writing to, without it/them being marked
-		 * up-to-date.  Note, at present there is nothing to stop the
-		 * pages being swapped out between us bringing them into memory
-		 * and doing the actual copying.
-		 */
-		if (unlikely(fault_in_iov_iter_readable(i, bytes))) {
-			status = -EFAULT;
-			break;
-		}
-		/* Get and lock @do_pages starting at index @start_idx. */
-		status = __ntfs_grab_cache_pages(mapping, start_idx, do_pages,
-				pages, &cached_page);
-		if (unlikely(status))
-			break;
-		/*
-		 * For non-resident attributes, we need to fill any holes with
-		 * actual clusters and ensure all bufferes are mapped.  We also
-		 * need to bring uptodate any buffers that are only partially
-		 * being written to.
-		 */
-		if (NInoNonResident(ni)) {
-			status = ntfs_prepare_pages_for_non_resident_write(
-					pages, do_pages, pos, bytes);
-			if (unlikely(status)) {
-				do {
-					unlock_page(pages[--do_pages]);
-					put_page(pages[do_pages]);
-				} while (do_pages);
-				break;
-			}
-		}
-		u = (pos >> PAGE_SHIFT) - pages[0]->index;
-		copied = ntfs_copy_from_user_iter(pages + u, do_pages - u, ofs,
-					i, bytes);
-		ntfs_flush_dcache_pages(pages + u, do_pages - u);
-		status = 0;
-		if (likely(copied == bytes)) {
-			status = ntfs_commit_pages_after_write(pages, do_pages,
-					pos, bytes);
-		}
-		do {
-			unlock_page(pages[--do_pages]);
-			put_page(pages[do_pages]);
-		} while (do_pages);
-		if (unlikely(status < 0)) {
-			iov_iter_revert(i, copied);
-			break;
-		}
-		cond_resched();
-		if (unlikely(copied < bytes)) {
-			iov_iter_revert(i, copied);
-			if (copied)
-				bytes = copied;
-			else if (bytes > PAGE_SIZE - ofs)
-				bytes = PAGE_SIZE - ofs;
-			goto again;
-		}
-		pos += copied;
-		written += copied;
-		balance_dirty_pages_ratelimited(mapping);
-		if (fatal_signal_pending(current)) {
-			status = -EINTR;
-			break;
-		}
-	} while (iov_iter_count(i));
-	if (cached_page)
-		put_page(cached_page);
-	ntfs_debug("Done.  Returning %s (written 0x%lx, status %li).",
-			written ? "written" : "status", (unsigned long)written,
-			(long)status);
-	return written ? written : status;
-}
-
-/**
- * ntfs_file_write_iter - simple wrapper for ntfs_file_write_iter_nolock()
- * @iocb:	IO state structure
- * @from:	iov_iter with data to write
- *
- * Basically the same as generic_file_write_iter() except that it ends up
- * up calling ntfs_perform_write() instead of generic_perform_write() and that
- * O_DIRECT is not implemented.
- */
-static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
-{
-	struct file *file = iocb->ki_filp;
-	struct inode *vi = file_inode(file);
-	ssize_t written = 0;
-	ssize_t err;
-
-	inode_lock(vi);
-	/* We can write back this queue in page reclaim. */
-	err = ntfs_prepare_file_for_write(iocb, from);
-	if (iov_iter_count(from) && !err)
-		written = ntfs_perform_write(file, from, iocb->ki_pos);
-	inode_unlock(vi);
-	iocb->ki_pos += written;
-	if (likely(written > 0))
-		written = generic_write_sync(iocb, written);
-	return written ? written : err;
-}
-
-/**
- * ntfs_file_fsync - sync a file to disk
- * @filp:	file to be synced
- * @datasync:	if non-zero only flush user data and not metadata
- *
- * Data integrity sync of a file to disk.  Used for fsync, fdatasync, and msync
- * system calls.  This function is inspired by fs/buffer.c::file_fsync().
- *
- * If @datasync is false, write the mft record and all associated extent mft
- * records as well as the $DATA attribute and then sync the block device.
- *
- * If @datasync is true and the attribute is non-resident, we skip the writing
- * of the mft record and all associated extent mft records (this might still
- * happen due to the write_inode_now() call).
- *
- * Also, if @datasync is true, we do not wait on the inode to be written out
- * but we always wait on the page cache pages to be written out.
- *
- * Locking: Caller must hold i_mutex on the inode.
- *
- * TODO: We should probably also write all attribute/index inodes associated
- * with this inode but since we have no simple way of getting to them we ignore
- * this problem for now.
- */
-static int ntfs_file_fsync(struct file *filp, loff_t start, loff_t end,
-			   int datasync)
-{
-	struct inode *vi = filp->f_mapping->host;
-	int err, ret = 0;
-
-	ntfs_debug("Entering for inode 0x%lx.", vi->i_ino);
-
-	err = file_write_and_wait_range(filp, start, end);
-	if (err)
-		return err;
-	inode_lock(vi);
-
-	BUG_ON(S_ISDIR(vi->i_mode));
-	if (!datasync || !NInoNonResident(NTFS_I(vi)))
-		ret = __ntfs_write_inode(vi, 1);
-	write_inode_now(vi, !datasync);
-	/*
-	 * NOTE: If we were to use mapping->private_list (see ext2 and
-	 * fs/buffer.c) for dirty blocks then we could optimize the below to be
-	 * sync_mapping_buffers(vi->i_mapping).
-	 */
-	err = sync_blockdev(vi->i_sb->s_bdev);
-	if (unlikely(err && !ret))
-		ret = err;
-	if (likely(!ret))
-		ntfs_debug("Done.");
-	else
-		ntfs_warning(vi->i_sb, "Failed to f%ssync inode 0x%lx.  Error "
-				"%u.", datasync ? "data" : "", vi->i_ino, -ret);
-	inode_unlock(vi);
-	return ret;
-}
-
-#endif /* NTFS_RW */
-
-const struct file_operations ntfs_file_ops = {
-	.llseek		= generic_file_llseek,
-	.read_iter	= generic_file_read_iter,
-#ifdef NTFS_RW
-	.write_iter	= ntfs_file_write_iter,
-	.fsync		= ntfs_file_fsync,
-#endif /* NTFS_RW */
-	.mmap		= generic_file_mmap,
-	.open		= ntfs_file_open,
-	.splice_read	= filemap_splice_read,
-};
-
-const struct inode_operations ntfs_file_inode_ops = {
-#ifdef NTFS_RW
-	.setattr	= ntfs_setattr,
-#endif /* NTFS_RW */
-};
-
-const struct file_operations ntfs_empty_file_ops = {};
-
-const struct inode_operations ntfs_empty_inode_ops = {};
diff --git a/fs/ntfs/index.c b/fs/ntfs/index.c
deleted file mode 100644
index d46c2c03a032..000000000000
--- a/fs/ntfs/index.c
+++ /dev/null
@@ -1,440 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * index.c - NTFS kernel index handling.  Part of the Linux-NTFS project.
- *
- * Copyright (c) 2004-2005 Anton Altaparmakov
- */
-
-#include <linux/slab.h>
-
-#include "aops.h"
-#include "collate.h"
-#include "debug.h"
-#include "index.h"
-#include "ntfs.h"
-
-/**
- * ntfs_index_ctx_get - allocate and initialize a new index context
- * @idx_ni:	ntfs index inode with which to initialize the context
- *
- * Allocate a new index context, initialize it with @idx_ni and return it.
- * Return NULL if allocation failed.
- *
- * Locking:  Caller must hold i_mutex on the index inode.
- */
-ntfs_index_context *ntfs_index_ctx_get(ntfs_inode *idx_ni)
-{
-	ntfs_index_context *ictx;
-
-	ictx = kmem_cache_alloc(ntfs_index_ctx_cache, GFP_NOFS);
-	if (ictx)
-		*ictx = (ntfs_index_context){ .idx_ni = idx_ni };
-	return ictx;
-}
-
-/**
- * ntfs_index_ctx_put - release an index context
- * @ictx:	index context to free
- *
- * Release the index context @ictx, releasing all associated resources.
- *
- * Locking:  Caller must hold i_mutex on the index inode.
- */
-void ntfs_index_ctx_put(ntfs_index_context *ictx)
-{
-	if (ictx->entry) {
-		if (ictx->is_in_root) {
-			if (ictx->actx)
-				ntfs_attr_put_search_ctx(ictx->actx);
-			if (ictx->base_ni)
-				unmap_mft_record(ictx->base_ni);
-		} else {
-			struct page *page = ictx->page;
-			if (page) {
-				BUG_ON(!PageLocked(page));
-				unlock_page(page);
-				ntfs_unmap_page(page);
-			}
-		}
-	}
-	kmem_cache_free(ntfs_index_ctx_cache, ictx);
-	return;
-}
-
-/**
- * ntfs_index_lookup - find a key in an index and return its index entry
- * @key:	[IN] key for which to search in the index
- * @key_len:	[IN] length of @key in bytes
- * @ictx:	[IN/OUT] context describing the index and the returned entry
- *
- * Before calling ntfs_index_lookup(), @ictx must have been obtained from a
- * call to ntfs_index_ctx_get().
- *
- * Look for the @key in the index specified by the index lookup context @ictx.
- * ntfs_index_lookup() walks the contents of the index looking for the @key.
- *
- * If the @key is found in the index, 0 is returned and @ictx is setup to
- * describe the index entry containing the matching @key.  @ictx->entry is the
- * index entry and @ictx->data and @ictx->data_len are the index entry data and
- * its length in bytes, respectively.
- *
- * If the @key is not found in the index, -ENOENT is returned and @ictx is
- * setup to describe the index entry whose key collates immediately after the
- * search @key, i.e. this is the position in the index at which an index entry
- * with a key of @key would need to be inserted.
- *
- * If an error occurs return the negative error code and @ictx is left
- * untouched.
- *
- * When finished with the entry and its data, call ntfs_index_ctx_put() to free
- * the context and other associated resources.
- *
- * If the index entry was modified, call flush_dcache_index_entry_page()
- * immediately after the modification and either ntfs_index_entry_mark_dirty()
- * or ntfs_index_entry_write() before the call to ntfs_index_ctx_put() to
- * ensure that the changes are written to disk.
- *
- * Locking:  - Caller must hold i_mutex on the index inode.
- *	     - Each page cache page in the index allocation mapping must be
- *	       locked whilst being accessed otherwise we may find a corrupt
- *	       page due to it being under ->writepage at the moment which
- *	       applies the mst protection fixups before writing out and then
- *	       removes them again after the write is complete after which it 
- *	       unlocks the page.
- */
-int ntfs_index_lookup(const void *key, const int key_len,
-		ntfs_index_context *ictx)
-{
-	VCN vcn, old_vcn;
-	ntfs_inode *idx_ni = ictx->idx_ni;
-	ntfs_volume *vol = idx_ni->vol;
-	struct super_block *sb = vol->sb;
-	ntfs_inode *base_ni = idx_ni->ext.base_ntfs_ino;
-	MFT_RECORD *m;
-	INDEX_ROOT *ir;
-	INDEX_ENTRY *ie;
-	INDEX_ALLOCATION *ia;
-	u8 *index_end, *kaddr;
-	ntfs_attr_search_ctx *actx;
-	struct address_space *ia_mapping;
-	struct page *page;
-	int rc, err = 0;
-
-	ntfs_debug("Entering.");
-	BUG_ON(!NInoAttr(idx_ni));
-	BUG_ON(idx_ni->type != AT_INDEX_ALLOCATION);
-	BUG_ON(idx_ni->nr_extents != -1);
-	BUG_ON(!base_ni);
-	BUG_ON(!key);
-	BUG_ON(key_len <= 0);
-	if (!ntfs_is_collation_rule_supported(
-			idx_ni->itype.index.collation_rule)) {
-		ntfs_error(sb, "Index uses unsupported collation rule 0x%x.  "
-				"Aborting lookup.", le32_to_cpu(
-				idx_ni->itype.index.collation_rule));
-		return -EOPNOTSUPP;
-	}
-	/* Get hold of the mft record for the index inode. */
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		ntfs_error(sb, "map_mft_record() failed with error code %ld.",
-				-PTR_ERR(m));
-		return PTR_ERR(m);
-	}
-	actx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (unlikely(!actx)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	/* Find the index root attribute in the mft record. */
-	err = ntfs_attr_lookup(AT_INDEX_ROOT, idx_ni->name, idx_ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, actx);
-	if (unlikely(err)) {
-		if (err == -ENOENT) {
-			ntfs_error(sb, "Index root attribute missing in inode "
-					"0x%lx.", idx_ni->mft_no);
-			err = -EIO;
-		}
-		goto err_out;
-	}
-	/* Get to the index root value (it has been verified in read_inode). */
-	ir = (INDEX_ROOT*)((u8*)actx->attr +
-			le16_to_cpu(actx->attr->data.resident.value_offset));
-	index_end = (u8*)&ir->index + le32_to_cpu(ir->index.index_length);
-	/* The first index entry. */
-	ie = (INDEX_ENTRY*)((u8*)&ir->index +
-			le32_to_cpu(ir->index.entries_offset));
-	/*
-	 * Loop until we exceed valid memory (corruption case) or until we
-	 * reach the last entry.
-	 */
-	for (;; ie = (INDEX_ENTRY*)((u8*)ie + le16_to_cpu(ie->length))) {
-		/* Bounds checks. */
-		if ((u8*)ie < (u8*)actx->mrec || (u8*)ie +
-				sizeof(INDEX_ENTRY_HEADER) > index_end ||
-				(u8*)ie + le16_to_cpu(ie->length) > index_end)
-			goto idx_err_out;
-		/*
-		 * The last entry cannot contain a key.  It can however contain
-		 * a pointer to a child node in the B+tree so we just break out.
-		 */
-		if (ie->flags & INDEX_ENTRY_END)
-			break;
-		/* Further bounds checks. */
-		if ((u32)sizeof(INDEX_ENTRY_HEADER) +
-				le16_to_cpu(ie->key_length) >
-				le16_to_cpu(ie->data.vi.data_offset) ||
-				(u32)le16_to_cpu(ie->data.vi.data_offset) +
-				le16_to_cpu(ie->data.vi.data_length) >
-				le16_to_cpu(ie->length))
-			goto idx_err_out;
-		/* If the keys match perfectly, we setup @ictx and return 0. */
-		if ((key_len == le16_to_cpu(ie->key_length)) && !memcmp(key,
-				&ie->key, key_len)) {
-ir_done:
-			ictx->is_in_root = true;
-			ictx->ir = ir;
-			ictx->actx = actx;
-			ictx->base_ni = base_ni;
-			ictx->ia = NULL;
-			ictx->page = NULL;
-done:
-			ictx->entry = ie;
-			ictx->data = (u8*)ie +
-					le16_to_cpu(ie->data.vi.data_offset);
-			ictx->data_len = le16_to_cpu(ie->data.vi.data_length);
-			ntfs_debug("Done.");
-			return err;
-		}
-		/*
-		 * Not a perfect match, need to do full blown collation so we
-		 * know which way in the B+tree we have to go.
-		 */
-		rc = ntfs_collate(vol, idx_ni->itype.index.collation_rule, key,
-				key_len, &ie->key, le16_to_cpu(ie->key_length));
-		/*
-		 * If @key collates before the key of the current entry, there
-		 * is definitely no such key in this index but we might need to
-		 * descend into the B+tree so we just break out of the loop.
-		 */
-		if (rc == -1)
-			break;
-		/*
-		 * A match should never happen as the memcmp() call should have
-		 * cought it, but we still treat it correctly.
-		 */
-		if (!rc)
-			goto ir_done;
-		/* The keys are not equal, continue the search. */
-	}
-	/*
-	 * We have finished with this index without success.  Check for the
-	 * presence of a child node and if not present setup @ictx and return
-	 * -ENOENT.
-	 */
-	if (!(ie->flags & INDEX_ENTRY_NODE)) {
-		ntfs_debug("Entry not found.");
-		err = -ENOENT;
-		goto ir_done;
-	} /* Child node present, descend into it. */
-	/* Consistency check: Verify that an index allocation exists. */
-	if (!NInoIndexAllocPresent(idx_ni)) {
-		ntfs_error(sb, "No index allocation attribute but index entry "
-				"requires one.  Inode 0x%lx is corrupt or "
-				"driver bug.", idx_ni->mft_no);
-		goto err_out;
-	}
-	/* Get the starting vcn of the index_block holding the child node. */
-	vcn = sle64_to_cpup((sle64*)((u8*)ie + le16_to_cpu(ie->length) - 8));
-	ia_mapping = VFS_I(idx_ni)->i_mapping;
-	/*
-	 * We are done with the index root and the mft record.  Release them,
-	 * otherwise we deadlock with ntfs_map_page().
-	 */
-	ntfs_attr_put_search_ctx(actx);
-	unmap_mft_record(base_ni);
-	m = NULL;
-	actx = NULL;
-descend_into_child_node:
-	/*
-	 * Convert vcn to index into the index allocation attribute in units
-	 * of PAGE_SIZE and map the page cache page, reading it from
-	 * disk if necessary.
-	 */
-	page = ntfs_map_page(ia_mapping, vcn <<
-			idx_ni->itype.index.vcn_size_bits >> PAGE_SHIFT);
-	if (IS_ERR(page)) {
-		ntfs_error(sb, "Failed to map index page, error %ld.",
-				-PTR_ERR(page));
-		err = PTR_ERR(page);
-		goto err_out;
-	}
-	lock_page(page);
-	kaddr = (u8*)page_address(page);
-fast_descend_into_child_node:
-	/* Get to the index allocation block. */
-	ia = (INDEX_ALLOCATION*)(kaddr + ((vcn <<
-			idx_ni->itype.index.vcn_size_bits) & ~PAGE_MASK));
-	/* Bounds checks. */
-	if ((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_SIZE) {
-		ntfs_error(sb, "Out of bounds check failed.  Corrupt inode "
-				"0x%lx or driver bug.", idx_ni->mft_no);
-		goto unm_err_out;
-	}
-	/* Catch multi sector transfer fixup errors. */
-	if (unlikely(!ntfs_is_indx_record(ia->magic))) {
-		ntfs_error(sb, "Index record with vcn 0x%llx is corrupt.  "
-				"Corrupt inode 0x%lx.  Run chkdsk.",
-				(long long)vcn, idx_ni->mft_no);
-		goto unm_err_out;
-	}
-	if (sle64_to_cpu(ia->index_block_vcn) != vcn) {
-		ntfs_error(sb, "Actual VCN (0x%llx) of index buffer is "
-				"different from expected VCN (0x%llx).  Inode "
-				"0x%lx is corrupt or driver bug.",
-				(unsigned long long)
-				sle64_to_cpu(ia->index_block_vcn),
-				(unsigned long long)vcn, idx_ni->mft_no);
-		goto unm_err_out;
-	}
-	if (le32_to_cpu(ia->index.allocated_size) + 0x18 !=
-			idx_ni->itype.index.block_size) {
-		ntfs_error(sb, "Index buffer (VCN 0x%llx) of inode 0x%lx has "
-				"a size (%u) differing from the index "
-				"specified size (%u).  Inode is corrupt or "
-				"driver bug.", (unsigned long long)vcn,
-				idx_ni->mft_no,
-				le32_to_cpu(ia->index.allocated_size) + 0x18,
-				idx_ni->itype.index.block_size);
-		goto unm_err_out;
-	}
-	index_end = (u8*)ia + idx_ni->itype.index.block_size;
-	if (index_end > kaddr + PAGE_SIZE) {
-		ntfs_error(sb, "Index buffer (VCN 0x%llx) of inode 0x%lx "
-				"crosses page boundary.  Impossible!  Cannot "
-				"access!  This is probably a bug in the "
-				"driver.", (unsigned long long)vcn,
-				idx_ni->mft_no);
-		goto unm_err_out;
-	}
-	index_end = (u8*)&ia->index + le32_to_cpu(ia->index.index_length);
-	if (index_end > (u8*)ia + idx_ni->itype.index.block_size) {
-		ntfs_error(sb, "Size of index buffer (VCN 0x%llx) of inode "
-				"0x%lx exceeds maximum size.",
-				(unsigned long long)vcn, idx_ni->mft_no);
-		goto unm_err_out;
-	}
-	/* The first index entry. */
-	ie = (INDEX_ENTRY*)((u8*)&ia->index +
-			le32_to_cpu(ia->index.entries_offset));
-	/*
-	 * Iterate similar to above big loop but applied to index buffer, thus
-	 * loop until we exceed valid memory (corruption case) or until we
-	 * reach the last entry.
-	 */
-	for (;; ie = (INDEX_ENTRY*)((u8*)ie + le16_to_cpu(ie->length))) {
-		/* Bounds checks. */
-		if ((u8*)ie < (u8*)ia || (u8*)ie +
-				sizeof(INDEX_ENTRY_HEADER) > index_end ||
-				(u8*)ie + le16_to_cpu(ie->length) > index_end) {
-			ntfs_error(sb, "Index entry out of bounds in inode "
-					"0x%lx.", idx_ni->mft_no);
-			goto unm_err_out;
-		}
-		/*
-		 * The last entry cannot contain a key.  It can however contain
-		 * a pointer to a child node in the B+tree so we just break out.
-		 */
-		if (ie->flags & INDEX_ENTRY_END)
-			break;
-		/* Further bounds checks. */
-		if ((u32)sizeof(INDEX_ENTRY_HEADER) +
-				le16_to_cpu(ie->key_length) >
-				le16_to_cpu(ie->data.vi.data_offset) ||
-				(u32)le16_to_cpu(ie->data.vi.data_offset) +
-				le16_to_cpu(ie->data.vi.data_length) >
-				le16_to_cpu(ie->length)) {
-			ntfs_error(sb, "Index entry out of bounds in inode "
-					"0x%lx.", idx_ni->mft_no);
-			goto unm_err_out;
-		}
-		/* If the keys match perfectly, we setup @ictx and return 0. */
-		if ((key_len == le16_to_cpu(ie->key_length)) && !memcmp(key,
-				&ie->key, key_len)) {
-ia_done:
-			ictx->is_in_root = false;
-			ictx->actx = NULL;
-			ictx->base_ni = NULL;
-			ictx->ia = ia;
-			ictx->page = page;
-			goto done;
-		}
-		/*
-		 * Not a perfect match, need to do full blown collation so we
-		 * know which way in the B+tree we have to go.
-		 */
-		rc = ntfs_collate(vol, idx_ni->itype.index.collation_rule, key,
-				key_len, &ie->key, le16_to_cpu(ie->key_length));
-		/*
-		 * If @key collates before the key of the current entry, there
-		 * is definitely no such key in this index but we might need to
-		 * descend into the B+tree so we just break out of the loop.
-		 */
-		if (rc == -1)
-			break;
-		/*
-		 * A match should never happen as the memcmp() call should have
-		 * cought it, but we still treat it correctly.
-		 */
-		if (!rc)
-			goto ia_done;
-		/* The keys are not equal, continue the search. */
-	}
-	/*
-	 * We have finished with this index buffer without success.  Check for
-	 * the presence of a child node and if not present return -ENOENT.
-	 */
-	if (!(ie->flags & INDEX_ENTRY_NODE)) {
-		ntfs_debug("Entry not found.");
-		err = -ENOENT;
-		goto ia_done;
-	}
-	if ((ia->index.flags & NODE_MASK) == LEAF_NODE) {
-		ntfs_error(sb, "Index entry with child node found in a leaf "
-				"node in inode 0x%lx.", idx_ni->mft_no);
-		goto unm_err_out;
-	}
-	/* Child node present, descend into it. */
-	old_vcn = vcn;
-	vcn = sle64_to_cpup((sle64*)((u8*)ie + le16_to_cpu(ie->length) - 8));
-	if (vcn >= 0) {
-		/*
-		 * If vcn is in the same page cache page as old_vcn we recycle
-		 * the mapped page.
-		 */
-		if (old_vcn << vol->cluster_size_bits >>
-				PAGE_SHIFT == vcn <<
-				vol->cluster_size_bits >>
-				PAGE_SHIFT)
-			goto fast_descend_into_child_node;
-		unlock_page(page);
-		ntfs_unmap_page(page);
-		goto descend_into_child_node;
-	}
-	ntfs_error(sb, "Negative child node vcn in inode 0x%lx.",
-			idx_ni->mft_no);
-unm_err_out:
-	unlock_page(page);
-	ntfs_unmap_page(page);
-err_out:
-	if (!err)
-		err = -EIO;
-	if (actx)
-		ntfs_attr_put_search_ctx(actx);
-	if (m)
-		unmap_mft_record(base_ni);
-	return err;
-idx_err_out:
-	ntfs_error(sb, "Corrupt index.  Aborting lookup.");
-	goto err_out;
-}
diff --git a/fs/ntfs/index.h b/fs/ntfs/index.h
deleted file mode 100644
index bb3c3ae55138..000000000000
--- a/fs/ntfs/index.h
+++ /dev/null
@@ -1,134 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * index.h - Defines for NTFS kernel index handling.  Part of the Linux-NTFS
- *	     project.
- *
- * Copyright (c) 2004 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_INDEX_H
-#define _LINUX_NTFS_INDEX_H
-
-#include <linux/fs.h>
-
-#include "types.h"
-#include "layout.h"
-#include "inode.h"
-#include "attrib.h"
-#include "mft.h"
-#include "aops.h"
-
-/**
- * @idx_ni:	index inode containing the @entry described by this context
- * @entry:	index entry (points into @ir or @ia)
- * @data:	index entry data (points into @entry)
- * @data_len:	length in bytes of @data
- * @is_in_root:	'true' if @entry is in @ir and 'false' if it is in @ia
- * @ir:		index root if @is_in_root and NULL otherwise
- * @actx:	attribute search context if @is_in_root and NULL otherwise
- * @base_ni:	base inode if @is_in_root and NULL otherwise
- * @ia:		index block if @is_in_root is 'false' and NULL otherwise
- * @page:	page if @is_in_root is 'false' and NULL otherwise
- *
- * @idx_ni is the index inode this context belongs to.
- *
- * @entry is the index entry described by this context.  @data and @data_len
- * are the index entry data and its length in bytes, respectively.  @data
- * simply points into @entry.  This is probably what the user is interested in.
- *
- * If @is_in_root is 'true', @entry is in the index root attribute @ir described
- * by the attribute search context @actx and the base inode @base_ni.  @ia and
- * @page are NULL in this case.
- *
- * If @is_in_root is 'false', @entry is in the index allocation attribute and @ia
- * and @page point to the index allocation block and the mapped, locked page it
- * is in, respectively.  @ir, @actx and @base_ni are NULL in this case.
- *
- * To obtain a context call ntfs_index_ctx_get().
- *
- * We use this context to allow ntfs_index_lookup() to return the found index
- * @entry and its @data without having to allocate a buffer and copy the @entry
- * and/or its @data into it.
- *
- * When finished with the @entry and its @data, call ntfs_index_ctx_put() to
- * free the context and other associated resources.
- *
- * If the index entry was modified, call flush_dcache_index_entry_page()
- * immediately after the modification and either ntfs_index_entry_mark_dirty()
- * or ntfs_index_entry_write() before the call to ntfs_index_ctx_put() to
- * ensure that the changes are written to disk.
- */
-typedef struct {
-	ntfs_inode *idx_ni;
-	INDEX_ENTRY *entry;
-	void *data;
-	u16 data_len;
-	bool is_in_root;
-	INDEX_ROOT *ir;
-	ntfs_attr_search_ctx *actx;
-	ntfs_inode *base_ni;
-	INDEX_ALLOCATION *ia;
-	struct page *page;
-} ntfs_index_context;
-
-extern ntfs_index_context *ntfs_index_ctx_get(ntfs_inode *idx_ni);
-extern void ntfs_index_ctx_put(ntfs_index_context *ictx);
-
-extern int ntfs_index_lookup(const void *key, const int key_len,
-		ntfs_index_context *ictx);
-
-#ifdef NTFS_RW
-
-/**
- * ntfs_index_entry_flush_dcache_page - flush_dcache_page() for index entries
- * @ictx:	ntfs index context describing the index entry
- *
- * Call flush_dcache_page() for the page in which an index entry resides.
- *
- * This must be called every time an index entry is modified, just after the
- * modification.
- *
- * If the index entry is in the index root attribute, simply flush the page
- * containing the mft record containing the index root attribute.
- *
- * If the index entry is in an index block belonging to the index allocation
- * attribute, simply flush the page cache page containing the index block.
- */
-static inline void ntfs_index_entry_flush_dcache_page(ntfs_index_context *ictx)
-{
-	if (ictx->is_in_root)
-		flush_dcache_mft_record_page(ictx->actx->ntfs_ino);
-	else
-		flush_dcache_page(ictx->page);
-}
-
-/**
- * ntfs_index_entry_mark_dirty - mark an index entry dirty
- * @ictx:	ntfs index context describing the index entry
- *
- * Mark the index entry described by the index entry context @ictx dirty.
- *
- * If the index entry is in the index root attribute, simply mark the mft
- * record containing the index root attribute dirty.  This ensures the mft
- * record, and hence the index root attribute, will be written out to disk
- * later.
- *
- * If the index entry is in an index block belonging to the index allocation
- * attribute, mark the buffers belonging to the index record as well as the
- * page cache page the index block is in dirty.  This automatically marks the
- * VFS inode of the ntfs index inode to which the index entry belongs dirty,
- * too (I_DIRTY_PAGES) and this in turn ensures the page buffers, and hence the
- * dirty index block, will be written out to disk later.
- */
-static inline void ntfs_index_entry_mark_dirty(ntfs_index_context *ictx)
-{
-	if (ictx->is_in_root)
-		mark_mft_record_dirty(ictx->actx->ntfs_ino);
-	else
-		mark_ntfs_record_dirty(ictx->page,
-				(u8*)ictx->ia - (u8*)page_address(ictx->page));
-}
-
-#endif /* NTFS_RW */
-
-#endif /* _LINUX_NTFS_INDEX_H */
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
deleted file mode 100644
index aba1e22db4e9..000000000000
--- a/fs/ntfs/inode.c
+++ /dev/null
@@ -1,3102 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * inode.c - NTFS kernel inode handling.
- *
- * Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc.
- */
-
-#include <linux/buffer_head.h>
-#include <linux/fs.h>
-#include <linux/mm.h>
-#include <linux/mount.h>
-#include <linux/mutex.h>
-#include <linux/pagemap.h>
-#include <linux/quotaops.h>
-#include <linux/slab.h>
-#include <linux/log2.h>
-
-#include "aops.h"
-#include "attrib.h"
-#include "bitmap.h"
-#include "dir.h"
-#include "debug.h"
-#include "inode.h"
-#include "lcnalloc.h"
-#include "malloc.h"
-#include "mft.h"
-#include "time.h"
-#include "ntfs.h"
-
-/**
- * ntfs_test_inode - compare two (possibly fake) inodes for equality
- * @vi:		vfs inode which to test
- * @data:	data which is being tested with
- *
- * Compare the ntfs attribute embedded in the ntfs specific part of the vfs
- * inode @vi for equality with the ntfs attribute @data.
- *
- * If searching for the normal file/directory inode, set @na->type to AT_UNUSED.
- * @na->name and @na->name_len are then ignored.
- *
- * Return 1 if the attributes match and 0 if not.
- *
- * NOTE: This function runs with the inode_hash_lock spin lock held so it is not
- * allowed to sleep.
- */
-int ntfs_test_inode(struct inode *vi, void *data)
-{
-	ntfs_attr *na = (ntfs_attr *)data;
-	ntfs_inode *ni;
-
-	if (vi->i_ino != na->mft_no)
-		return 0;
-	ni = NTFS_I(vi);
-	/* If !NInoAttr(ni), @vi is a normal file or directory inode. */
-	if (likely(!NInoAttr(ni))) {
-		/* If not looking for a normal inode this is a mismatch. */
-		if (unlikely(na->type != AT_UNUSED))
-			return 0;
-	} else {
-		/* A fake inode describing an attribute. */
-		if (ni->type != na->type)
-			return 0;
-		if (ni->name_len != na->name_len)
-			return 0;
-		if (na->name_len && memcmp(ni->name, na->name,
-				na->name_len * sizeof(ntfschar)))
-			return 0;
-	}
-	/* Match! */
-	return 1;
-}
-
-/**
- * ntfs_init_locked_inode - initialize an inode
- * @vi:		vfs inode to initialize
- * @data:	data which to initialize @vi to
- *
- * Initialize the vfs inode @vi with the values from the ntfs attribute @data in
- * order to enable ntfs_test_inode() to do its work.
- *
- * If initializing the normal file/directory inode, set @na->type to AT_UNUSED.
- * In that case, @na->name and @na->name_len should be set to NULL and 0,
- * respectively. Although that is not strictly necessary as
- * ntfs_read_locked_inode() will fill them in later.
- *
- * Return 0 on success and -errno on error.
- *
- * NOTE: This function runs with the inode->i_lock spin lock held so it is not
- * allowed to sleep. (Hence the GFP_ATOMIC allocation.)
- */
-static int ntfs_init_locked_inode(struct inode *vi, void *data)
-{
-	ntfs_attr *na = (ntfs_attr *)data;
-	ntfs_inode *ni = NTFS_I(vi);
-
-	vi->i_ino = na->mft_no;
-
-	ni->type = na->type;
-	if (na->type == AT_INDEX_ALLOCATION)
-		NInoSetMstProtected(ni);
-
-	ni->name = na->name;
-	ni->name_len = na->name_len;
-
-	/* If initializing a normal inode, we are done. */
-	if (likely(na->type == AT_UNUSED)) {
-		BUG_ON(na->name);
-		BUG_ON(na->name_len);
-		return 0;
-	}
-
-	/* It is a fake inode. */
-	NInoSetAttr(ni);
-
-	/*
-	 * We have I30 global constant as an optimization as it is the name
-	 * in >99.9% of named attributes! The other <0.1% incur a GFP_ATOMIC
-	 * allocation but that is ok. And most attributes are unnamed anyway,
-	 * thus the fraction of named attributes with name != I30 is actually
-	 * absolutely tiny.
-	 */
-	if (na->name_len && na->name != I30) {
-		unsigned int i;
-
-		BUG_ON(!na->name);
-		i = na->name_len * sizeof(ntfschar);
-		ni->name = kmalloc(i + sizeof(ntfschar), GFP_ATOMIC);
-		if (!ni->name)
-			return -ENOMEM;
-		memcpy(ni->name, na->name, i);
-		ni->name[na->name_len] = 0;
-	}
-	return 0;
-}
-
-static int ntfs_read_locked_inode(struct inode *vi);
-static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi);
-static int ntfs_read_locked_index_inode(struct inode *base_vi,
-		struct inode *vi);
-
-/**
- * ntfs_iget - obtain a struct inode corresponding to a specific normal inode
- * @sb:		super block of mounted volume
- * @mft_no:	mft record number / inode number to obtain
- *
- * Obtain the struct inode corresponding to a specific normal inode (i.e. a
- * file or directory).
- *
- * If the inode is in the cache, it is just returned with an increased
- * reference count. Otherwise, a new struct inode is allocated and initialized,
- * and finally ntfs_read_locked_inode() is called to read in the inode and
- * fill in the remainder of the inode structure.
- *
- * Return the struct inode on success. Check the return value with IS_ERR() and
- * if true, the function failed and the error code is obtained from PTR_ERR().
- */
-struct inode *ntfs_iget(struct super_block *sb, unsigned long mft_no)
-{
-	struct inode *vi;
-	int err;
-	ntfs_attr na;
-
-	na.mft_no = mft_no;
-	na.type = AT_UNUSED;
-	na.name = NULL;
-	na.name_len = 0;
-
-	vi = iget5_locked(sb, mft_no, ntfs_test_inode,
-			ntfs_init_locked_inode, &na);
-	if (unlikely(!vi))
-		return ERR_PTR(-ENOMEM);
-
-	err = 0;
-
-	/* If this is a freshly allocated inode, need to read it now. */
-	if (vi->i_state & I_NEW) {
-		err = ntfs_read_locked_inode(vi);
-		unlock_new_inode(vi);
-	}
-	/*
-	 * There is no point in keeping bad inodes around if the failure was
-	 * due to ENOMEM. We want to be able to retry again later.
-	 */
-	if (unlikely(err == -ENOMEM)) {
-		iput(vi);
-		vi = ERR_PTR(err);
-	}
-	return vi;
-}
-
-/**
- * ntfs_attr_iget - obtain a struct inode corresponding to an attribute
- * @base_vi:	vfs base inode containing the attribute
- * @type:	attribute type
- * @name:	Unicode name of the attribute (NULL if unnamed)
- * @name_len:	length of @name in Unicode characters (0 if unnamed)
- *
- * Obtain the (fake) struct inode corresponding to the attribute specified by
- * @type, @name, and @name_len, which is present in the base mft record
- * specified by the vfs inode @base_vi.
- *
- * If the attribute inode is in the cache, it is just returned with an
- * increased reference count. Otherwise, a new struct inode is allocated and
- * initialized, and finally ntfs_read_locked_attr_inode() is called to read the
- * attribute and fill in the inode structure.
- *
- * Note, for index allocation attributes, you need to use ntfs_index_iget()
- * instead of ntfs_attr_iget() as working with indices is a lot more complex.
- *
- * Return the struct inode of the attribute inode on success. Check the return
- * value with IS_ERR() and if true, the function failed and the error code is
- * obtained from PTR_ERR().
- */
-struct inode *ntfs_attr_iget(struct inode *base_vi, ATTR_TYPE type,
-		ntfschar *name, u32 name_len)
-{
-	struct inode *vi;
-	int err;
-	ntfs_attr na;
-
-	/* Make sure no one calls ntfs_attr_iget() for indices. */
-	BUG_ON(type == AT_INDEX_ALLOCATION);
-
-	na.mft_no = base_vi->i_ino;
-	na.type = type;
-	na.name = name;
-	na.name_len = name_len;
-
-	vi = iget5_locked(base_vi->i_sb, na.mft_no, ntfs_test_inode,
-			ntfs_init_locked_inode, &na);
-	if (unlikely(!vi))
-		return ERR_PTR(-ENOMEM);
-
-	err = 0;
-
-	/* If this is a freshly allocated inode, need to read it now. */
-	if (vi->i_state & I_NEW) {
-		err = ntfs_read_locked_attr_inode(base_vi, vi);
-		unlock_new_inode(vi);
-	}
-	/*
-	 * There is no point in keeping bad attribute inodes around. This also
-	 * simplifies things in that we never need to check for bad attribute
-	 * inodes elsewhere.
-	 */
-	if (unlikely(err)) {
-		iput(vi);
-		vi = ERR_PTR(err);
-	}
-	return vi;
-}
-
-/**
- * ntfs_index_iget - obtain a struct inode corresponding to an index
- * @base_vi:	vfs base inode containing the index related attributes
- * @name:	Unicode name of the index
- * @name_len:	length of @name in Unicode characters
- *
- * Obtain the (fake) struct inode corresponding to the index specified by @name
- * and @name_len, which is present in the base mft record specified by the vfs
- * inode @base_vi.
- *
- * If the index inode is in the cache, it is just returned with an increased
- * reference count.  Otherwise, a new struct inode is allocated and
- * initialized, and finally ntfs_read_locked_index_inode() is called to read
- * the index related attributes and fill in the inode structure.
- *
- * Return the struct inode of the index inode on success. Check the return
- * value with IS_ERR() and if true, the function failed and the error code is
- * obtained from PTR_ERR().
- */
-struct inode *ntfs_index_iget(struct inode *base_vi, ntfschar *name,
-		u32 name_len)
-{
-	struct inode *vi;
-	int err;
-	ntfs_attr na;
-
-	na.mft_no = base_vi->i_ino;
-	na.type = AT_INDEX_ALLOCATION;
-	na.name = name;
-	na.name_len = name_len;
-
-	vi = iget5_locked(base_vi->i_sb, na.mft_no, ntfs_test_inode,
-			ntfs_init_locked_inode, &na);
-	if (unlikely(!vi))
-		return ERR_PTR(-ENOMEM);
-
-	err = 0;
-
-	/* If this is a freshly allocated inode, need to read it now. */
-	if (vi->i_state & I_NEW) {
-		err = ntfs_read_locked_index_inode(base_vi, vi);
-		unlock_new_inode(vi);
-	}
-	/*
-	 * There is no point in keeping bad index inodes around.  This also
-	 * simplifies things in that we never need to check for bad index
-	 * inodes elsewhere.
-	 */
-	if (unlikely(err)) {
-		iput(vi);
-		vi = ERR_PTR(err);
-	}
-	return vi;
-}
-
-struct inode *ntfs_alloc_big_inode(struct super_block *sb)
-{
-	ntfs_inode *ni;
-
-	ntfs_debug("Entering.");
-	ni = alloc_inode_sb(sb, ntfs_big_inode_cache, GFP_NOFS);
-	if (likely(ni != NULL)) {
-		ni->state = 0;
-		return VFS_I(ni);
-	}
-	ntfs_error(sb, "Allocation of NTFS big inode structure failed.");
-	return NULL;
-}
-
-void ntfs_free_big_inode(struct inode *inode)
-{
-	kmem_cache_free(ntfs_big_inode_cache, NTFS_I(inode));
-}
-
-static inline ntfs_inode *ntfs_alloc_extent_inode(void)
-{
-	ntfs_inode *ni;
-
-	ntfs_debug("Entering.");
-	ni = kmem_cache_alloc(ntfs_inode_cache, GFP_NOFS);
-	if (likely(ni != NULL)) {
-		ni->state = 0;
-		return ni;
-	}
-	ntfs_error(NULL, "Allocation of NTFS inode structure failed.");
-	return NULL;
-}
-
-static void ntfs_destroy_extent_inode(ntfs_inode *ni)
-{
-	ntfs_debug("Entering.");
-	BUG_ON(ni->page);
-	if (!atomic_dec_and_test(&ni->count))
-		BUG();
-	kmem_cache_free(ntfs_inode_cache, ni);
-}
-
-/*
- * The attribute runlist lock has separate locking rules from the
- * normal runlist lock, so split the two lock-classes:
- */
-static struct lock_class_key attr_list_rl_lock_class;
-
-/**
- * __ntfs_init_inode - initialize ntfs specific part of an inode
- * @sb:		super block of mounted volume
- * @ni:		freshly allocated ntfs inode which to initialize
- *
- * Initialize an ntfs inode to defaults.
- *
- * NOTE: ni->mft_no, ni->state, ni->type, ni->name, and ni->name_len are left
- * untouched. Make sure to initialize them elsewhere.
- *
- * Return zero on success and -ENOMEM on error.
- */
-void __ntfs_init_inode(struct super_block *sb, ntfs_inode *ni)
-{
-	ntfs_debug("Entering.");
-	rwlock_init(&ni->size_lock);
-	ni->initialized_size = ni->allocated_size = 0;
-	ni->seq_no = 0;
-	atomic_set(&ni->count, 1);
-	ni->vol = NTFS_SB(sb);
-	ntfs_init_runlist(&ni->runlist);
-	mutex_init(&ni->mrec_lock);
-	ni->page = NULL;
-	ni->page_ofs = 0;
-	ni->attr_list_size = 0;
-	ni->attr_list = NULL;
-	ntfs_init_runlist(&ni->attr_list_rl);
-	lockdep_set_class(&ni->attr_list_rl.lock,
-				&attr_list_rl_lock_class);
-	ni->itype.index.block_size = 0;
-	ni->itype.index.vcn_size = 0;
-	ni->itype.index.collation_rule = 0;
-	ni->itype.index.block_size_bits = 0;
-	ni->itype.index.vcn_size_bits = 0;
-	mutex_init(&ni->extent_lock);
-	ni->nr_extents = 0;
-	ni->ext.base_ntfs_ino = NULL;
-}
-
-/*
- * Extent inodes get MFT-mapped in a nested way, while the base inode
- * is still mapped. Teach this nesting to the lock validator by creating
- * a separate class for nested inode's mrec_lock's:
- */
-static struct lock_class_key extent_inode_mrec_lock_key;
-
-inline ntfs_inode *ntfs_new_extent_inode(struct super_block *sb,
-		unsigned long mft_no)
-{
-	ntfs_inode *ni = ntfs_alloc_extent_inode();
-
-	ntfs_debug("Entering.");
-	if (likely(ni != NULL)) {
-		__ntfs_init_inode(sb, ni);
-		lockdep_set_class(&ni->mrec_lock, &extent_inode_mrec_lock_key);
-		ni->mft_no = mft_no;
-		ni->type = AT_UNUSED;
-		ni->name = NULL;
-		ni->name_len = 0;
-	}
-	return ni;
-}
-
-/**
- * ntfs_is_extended_system_file - check if a file is in the $Extend directory
- * @ctx:	initialized attribute search context
- *
- * Search all file name attributes in the inode described by the attribute
- * search context @ctx and check if any of the names are in the $Extend system
- * directory.
- *
- * Return values:
- *	   1: file is in $Extend directory
- *	   0: file is not in $Extend directory
- *    -errno: failed to determine if the file is in the $Extend directory
- */
-static int ntfs_is_extended_system_file(ntfs_attr_search_ctx *ctx)
-{
-	int nr_links, err;
-
-	/* Restart search. */
-	ntfs_attr_reinit_search_ctx(ctx);
-
-	/* Get number of hard links. */
-	nr_links = le16_to_cpu(ctx->mrec->link_count);
-
-	/* Loop through all hard links. */
-	while (!(err = ntfs_attr_lookup(AT_FILE_NAME, NULL, 0, 0, 0, NULL, 0,
-			ctx))) {
-		FILE_NAME_ATTR *file_name_attr;
-		ATTR_RECORD *attr = ctx->attr;
-		u8 *p, *p2;
-
-		nr_links--;
-		/*
-		 * Maximum sanity checking as we are called on an inode that
-		 * we suspect might be corrupt.
-		 */
-		p = (u8*)attr + le32_to_cpu(attr->length);
-		if (p < (u8*)ctx->mrec || (u8*)p > (u8*)ctx->mrec +
-				le32_to_cpu(ctx->mrec->bytes_in_use)) {
-err_corrupt_attr:
-			ntfs_error(ctx->ntfs_ino->vol->sb, "Corrupt file name "
-					"attribute. You should run chkdsk.");
-			return -EIO;
-		}
-		if (attr->non_resident) {
-			ntfs_error(ctx->ntfs_ino->vol->sb, "Non-resident file "
-					"name. You should run chkdsk.");
-			return -EIO;
-		}
-		if (attr->flags) {
-			ntfs_error(ctx->ntfs_ino->vol->sb, "File name with "
-					"invalid flags. You should run "
-					"chkdsk.");
-			return -EIO;
-		}
-		if (!(attr->data.resident.flags & RESIDENT_ATTR_IS_INDEXED)) {
-			ntfs_error(ctx->ntfs_ino->vol->sb, "Unindexed file "
-					"name. You should run chkdsk.");
-			return -EIO;
-		}
-		file_name_attr = (FILE_NAME_ATTR*)((u8*)attr +
-				le16_to_cpu(attr->data.resident.value_offset));
-		p2 = (u8 *)file_name_attr + le32_to_cpu(attr->data.resident.value_length);
-		if (p2 < (u8*)attr || p2 > p)
-			goto err_corrupt_attr;
-		/* This attribute is ok, but is it in the $Extend directory? */
-		if (MREF_LE(file_name_attr->parent_directory) == FILE_Extend)
-			return 1;	/* YES, it's an extended system file. */
-	}
-	if (unlikely(err != -ENOENT))
-		return err;
-	if (unlikely(nr_links)) {
-		ntfs_error(ctx->ntfs_ino->vol->sb, "Inode hard link count "
-				"doesn't match number of name attributes. You "
-				"should run chkdsk.");
-		return -EIO;
-	}
-	return 0;	/* NO, it is not an extended system file. */
-}
-
-/**
- * ntfs_read_locked_inode - read an inode from its device
- * @vi:		inode to read
- *
- * ntfs_read_locked_inode() is called from ntfs_iget() to read the inode
- * described by @vi into memory from the device.
- *
- * The only fields in @vi that we need to/can look at when the function is
- * called are i_sb, pointing to the mounted device's super block, and i_ino,
- * the number of the inode to load.
- *
- * ntfs_read_locked_inode() maps, pins and locks the mft record number i_ino
- * for reading and sets up the necessary @vi fields as well as initializing
- * the ntfs inode.
- *
- * Q: What locks are held when the function is called?
- * A: i_state has I_NEW set, hence the inode is locked, also
- *    i_count is set to 1, so it is not going to go away
- *    i_flags is set to 0 and we have no business touching it.  Only an ioctl()
- *    is allowed to write to them. We should of course be honouring them but
- *    we need to do that using the IS_* macros defined in include/linux/fs.h.
- *    In any case ntfs_read_locked_inode() has nothing to do with i_flags.
- *
- * Return 0 on success and -errno on error.  In the error case, the inode will
- * have had make_bad_inode() executed on it.
- */
-static int ntfs_read_locked_inode(struct inode *vi)
-{
-	ntfs_volume *vol = NTFS_SB(vi->i_sb);
-	ntfs_inode *ni;
-	struct inode *bvi;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
-	STANDARD_INFORMATION *si;
-	ntfs_attr_search_ctx *ctx;
-	int err = 0;
-
-	ntfs_debug("Entering for i_ino 0x%lx.", vi->i_ino);
-
-	/* Setup the generic vfs inode parts now. */
-	vi->i_uid = vol->uid;
-	vi->i_gid = vol->gid;
-	vi->i_mode = 0;
-
-	/*
-	 * Initialize the ntfs specific part of @vi special casing
-	 * FILE_MFT which we need to do at mount time.
-	 */
-	if (vi->i_ino != FILE_MFT)
-		ntfs_init_big_inode(vi);
-	ni = NTFS_I(vi);
-
-	m = map_mft_record(ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		goto err_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(ni, m);
-	if (!ctx) {
-		err = -ENOMEM;
-		goto unm_err_out;
-	}
-
-	if (!(m->flags & MFT_RECORD_IN_USE)) {
-		ntfs_error(vi->i_sb, "Inode is not in use!");
-		goto unm_err_out;
-	}
-	if (m->base_mft_record) {
-		ntfs_error(vi->i_sb, "Inode is an extent inode!");
-		goto unm_err_out;
-	}
-
-	/* Transfer information from mft record into vfs and ntfs inodes. */
-	vi->i_generation = ni->seq_no = le16_to_cpu(m->sequence_number);
-
-	/*
-	 * FIXME: Keep in mind that link_count is two for files which have both
-	 * a long file name and a short file name as separate entries, so if
-	 * we are hiding short file names this will be too high. Either we need
-	 * to account for the short file names by subtracting them or we need
-	 * to make sure we delete files even though i_nlink is not zero which
-	 * might be tricky due to vfs interactions. Need to think about this
-	 * some more when implementing the unlink command.
-	 */
-	set_nlink(vi, le16_to_cpu(m->link_count));
-	/*
-	 * FIXME: Reparse points can have the directory bit set even though
-	 * they would be S_IFLNK. Need to deal with this further below when we
-	 * implement reparse points / symbolic links but it will do for now.
-	 * Also if not a directory, it could be something else, rather than
-	 * a regular file. But again, will do for now.
-	 */
-	/* Everyone gets all permissions. */
-	vi->i_mode |= S_IRWXUGO;
-	/* If read-only, no one gets write permissions. */
-	if (IS_RDONLY(vi))
-		vi->i_mode &= ~S_IWUGO;
-	if (m->flags & MFT_RECORD_IS_DIRECTORY) {
-		vi->i_mode |= S_IFDIR;
-		/*
-		 * Apply the directory permissions mask set in the mount
-		 * options.
-		 */
-		vi->i_mode &= ~vol->dmask;
-		/* Things break without this kludge! */
-		if (vi->i_nlink > 1)
-			set_nlink(vi, 1);
-	} else {
-		vi->i_mode |= S_IFREG;
-		/* Apply the file permissions mask set in the mount options. */
-		vi->i_mode &= ~vol->fmask;
-	}
-	/*
-	 * Find the standard information attribute in the mft record. At this
-	 * stage we haven't setup the attribute list stuff yet, so this could
-	 * in fact fail if the standard information is in an extent record, but
-	 * I don't think this actually ever happens.
-	 */
-	err = ntfs_attr_lookup(AT_STANDARD_INFORMATION, NULL, 0, 0, 0, NULL, 0,
-			ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT) {
-			/*
-			 * TODO: We should be performing a hot fix here (if the
-			 * recover mount option is set) by creating a new
-			 * attribute.
-			 */
-			ntfs_error(vi->i_sb, "$STANDARD_INFORMATION attribute "
-					"is missing.");
-		}
-		goto unm_err_out;
-	}
-	a = ctx->attr;
-	/* Get the standard information attribute value. */
-	if ((u8 *)a + le16_to_cpu(a->data.resident.value_offset)
-			+ le32_to_cpu(a->data.resident.value_length) >
-			(u8 *)ctx->mrec + vol->mft_record_size) {
-		ntfs_error(vi->i_sb, "Corrupt standard information attribute in inode.");
-		goto unm_err_out;
-	}
-	si = (STANDARD_INFORMATION*)((u8*)a +
-			le16_to_cpu(a->data.resident.value_offset));
-
-	/* Transfer information from the standard information into vi. */
-	/*
-	 * Note: The i_?times do not quite map perfectly onto the NTFS times,
-	 * but they are close enough, and in the end it doesn't really matter
-	 * that much...
-	 */
-	/*
-	 * mtime is the last change of the data within the file. Not changed
-	 * when only metadata is changed, e.g. a rename doesn't affect mtime.
-	 */
-	inode_set_mtime_to_ts(vi, ntfs2utc(si->last_data_change_time));
-	/*
-	 * ctime is the last change of the metadata of the file. This obviously
-	 * always changes, when mtime is changed. ctime can be changed on its
-	 * own, mtime is then not changed, e.g. when a file is renamed.
-	 */
-	inode_set_ctime_to_ts(vi, ntfs2utc(si->last_mft_change_time));
-	/*
-	 * Last access to the data within the file. Not changed during a rename
-	 * for example but changed whenever the file is written to.
-	 */
-	inode_set_atime_to_ts(vi, ntfs2utc(si->last_access_time));
-
-	/* Find the attribute list attribute if present. */
-	ntfs_attr_reinit_search_ctx(ctx);
-	err = ntfs_attr_lookup(AT_ATTRIBUTE_LIST, NULL, 0, 0, 0, NULL, 0, ctx);
-	if (err) {
-		if (unlikely(err != -ENOENT)) {
-			ntfs_error(vi->i_sb, "Failed to lookup attribute list "
-					"attribute.");
-			goto unm_err_out;
-		}
-	} else /* if (!err) */ {
-		if (vi->i_ino == FILE_MFT)
-			goto skip_attr_list_load;
-		ntfs_debug("Attribute list found in inode 0x%lx.", vi->i_ino);
-		NInoSetAttrList(ni);
-		a = ctx->attr;
-		if (a->flags & ATTR_COMPRESSION_MASK) {
-			ntfs_error(vi->i_sb, "Attribute list attribute is "
-					"compressed.");
-			goto unm_err_out;
-		}
-		if (a->flags & ATTR_IS_ENCRYPTED ||
-				a->flags & ATTR_IS_SPARSE) {
-			if (a->non_resident) {
-				ntfs_error(vi->i_sb, "Non-resident attribute "
-						"list attribute is encrypted/"
-						"sparse.");
-				goto unm_err_out;
-			}
-			ntfs_warning(vi->i_sb, "Resident attribute list "
-					"attribute in inode 0x%lx is marked "
-					"encrypted/sparse which is not true.  "
-					"However, Windows allows this and "
-					"chkdsk does not detect or correct it "
-					"so we will just ignore the invalid "
-					"flags and pretend they are not set.",
-					vi->i_ino);
-		}
-		/* Now allocate memory for the attribute list. */
-		ni->attr_list_size = (u32)ntfs_attr_size(a);
-		ni->attr_list = ntfs_malloc_nofs(ni->attr_list_size);
-		if (!ni->attr_list) {
-			ntfs_error(vi->i_sb, "Not enough memory to allocate "
-					"buffer for attribute list.");
-			err = -ENOMEM;
-			goto unm_err_out;
-		}
-		if (a->non_resident) {
-			NInoSetAttrListNonResident(ni);
-			if (a->data.non_resident.lowest_vcn) {
-				ntfs_error(vi->i_sb, "Attribute list has non "
-						"zero lowest_vcn.");
-				goto unm_err_out;
-			}
-			/*
-			 * Setup the runlist. No need for locking as we have
-			 * exclusive access to the inode at this time.
-			 */
-			ni->attr_list_rl.rl = ntfs_mapping_pairs_decompress(vol,
-					a, NULL);
-			if (IS_ERR(ni->attr_list_rl.rl)) {
-				err = PTR_ERR(ni->attr_list_rl.rl);
-				ni->attr_list_rl.rl = NULL;
-				ntfs_error(vi->i_sb, "Mapping pairs "
-						"decompression failed.");
-				goto unm_err_out;
-			}
-			/* Now load the attribute list. */
-			if ((err = load_attribute_list(vol, &ni->attr_list_rl,
-					ni->attr_list, ni->attr_list_size,
-					sle64_to_cpu(a->data.non_resident.
-					initialized_size)))) {
-				ntfs_error(vi->i_sb, "Failed to load "
-						"attribute list attribute.");
-				goto unm_err_out;
-			}
-		} else /* if (!a->non_resident) */ {
-			if ((u8*)a + le16_to_cpu(a->data.resident.value_offset)
-					+ le32_to_cpu(
-					a->data.resident.value_length) >
-					(u8*)ctx->mrec + vol->mft_record_size) {
-				ntfs_error(vi->i_sb, "Corrupt attribute list "
-						"in inode.");
-				goto unm_err_out;
-			}
-			/* Now copy the attribute list. */
-			memcpy(ni->attr_list, (u8*)a + le16_to_cpu(
-					a->data.resident.value_offset),
-					le32_to_cpu(
-					a->data.resident.value_length));
-		}
-	}
-skip_attr_list_load:
-	/*
-	 * If an attribute list is present we now have the attribute list value
-	 * in ntfs_ino->attr_list and it is ntfs_ino->attr_list_size bytes.
-	 */
-	if (S_ISDIR(vi->i_mode)) {
-		loff_t bvi_size;
-		ntfs_inode *bni;
-		INDEX_ROOT *ir;
-		u8 *ir_end, *index_end;
-
-		/* It is a directory, find index root attribute. */
-		ntfs_attr_reinit_search_ctx(ctx);
-		err = ntfs_attr_lookup(AT_INDEX_ROOT, I30, 4, CASE_SENSITIVE,
-				0, NULL, 0, ctx);
-		if (unlikely(err)) {
-			if (err == -ENOENT) {
-				// FIXME: File is corrupt! Hot-fix with empty
-				// index root attribute if recovery option is
-				// set.
-				ntfs_error(vi->i_sb, "$INDEX_ROOT attribute "
-						"is missing.");
-			}
-			goto unm_err_out;
-		}
-		a = ctx->attr;
-		/* Set up the state. */
-		if (unlikely(a->non_resident)) {
-			ntfs_error(vol->sb, "$INDEX_ROOT attribute is not "
-					"resident.");
-			goto unm_err_out;
-		}
-		/* Ensure the attribute name is placed before the value. */
-		if (unlikely(a->name_length && (le16_to_cpu(a->name_offset) >=
-				le16_to_cpu(a->data.resident.value_offset)))) {
-			ntfs_error(vol->sb, "$INDEX_ROOT attribute name is "
-					"placed after the attribute value.");
-			goto unm_err_out;
-		}
-		/*
-		 * Compressed/encrypted index root just means that the newly
-		 * created files in that directory should be created compressed/
-		 * encrypted. However index root cannot be both compressed and
-		 * encrypted.
-		 */
-		if (a->flags & ATTR_COMPRESSION_MASK)
-			NInoSetCompressed(ni);
-		if (a->flags & ATTR_IS_ENCRYPTED) {
-			if (a->flags & ATTR_COMPRESSION_MASK) {
-				ntfs_error(vi->i_sb, "Found encrypted and "
-						"compressed attribute.");
-				goto unm_err_out;
-			}
-			NInoSetEncrypted(ni);
-		}
-		if (a->flags & ATTR_IS_SPARSE)
-			NInoSetSparse(ni);
-		ir = (INDEX_ROOT*)((u8*)a +
-				le16_to_cpu(a->data.resident.value_offset));
-		ir_end = (u8*)ir + le32_to_cpu(a->data.resident.value_length);
-		if (ir_end > (u8*)ctx->mrec + vol->mft_record_size) {
-			ntfs_error(vi->i_sb, "$INDEX_ROOT attribute is "
-					"corrupt.");
-			goto unm_err_out;
-		}
-		index_end = (u8*)&ir->index +
-				le32_to_cpu(ir->index.index_length);
-		if (index_end > ir_end) {
-			ntfs_error(vi->i_sb, "Directory index is corrupt.");
-			goto unm_err_out;
-		}
-		if (ir->type != AT_FILE_NAME) {
-			ntfs_error(vi->i_sb, "Indexed attribute is not "
-					"$FILE_NAME.");
-			goto unm_err_out;
-		}
-		if (ir->collation_rule != COLLATION_FILE_NAME) {
-			ntfs_error(vi->i_sb, "Index collation rule is not "
-					"COLLATION_FILE_NAME.");
-			goto unm_err_out;
-		}
-		ni->itype.index.collation_rule = ir->collation_rule;
-		ni->itype.index.block_size = le32_to_cpu(ir->index_block_size);
-		if (ni->itype.index.block_size &
-				(ni->itype.index.block_size - 1)) {
-			ntfs_error(vi->i_sb, "Index block size (%u) is not a "
-					"power of two.",
-					ni->itype.index.block_size);
-			goto unm_err_out;
-		}
-		if (ni->itype.index.block_size > PAGE_SIZE) {
-			ntfs_error(vi->i_sb, "Index block size (%u) > "
-					"PAGE_SIZE (%ld) is not "
-					"supported.  Sorry.",
-					ni->itype.index.block_size,
-					PAGE_SIZE);
-			err = -EOPNOTSUPP;
-			goto unm_err_out;
-		}
-		if (ni->itype.index.block_size < NTFS_BLOCK_SIZE) {
-			ntfs_error(vi->i_sb, "Index block size (%u) < "
-					"NTFS_BLOCK_SIZE (%i) is not "
-					"supported.  Sorry.",
-					ni->itype.index.block_size,
-					NTFS_BLOCK_SIZE);
-			err = -EOPNOTSUPP;
-			goto unm_err_out;
-		}
-		ni->itype.index.block_size_bits =
-				ffs(ni->itype.index.block_size) - 1;
-		/* Determine the size of a vcn in the directory index. */
-		if (vol->cluster_size <= ni->itype.index.block_size) {
-			ni->itype.index.vcn_size = vol->cluster_size;
-			ni->itype.index.vcn_size_bits = vol->cluster_size_bits;
-		} else {
-			ni->itype.index.vcn_size = vol->sector_size;
-			ni->itype.index.vcn_size_bits = vol->sector_size_bits;
-		}
-
-		/* Setup the index allocation attribute, even if not present. */
-		NInoSetMstProtected(ni);
-		ni->type = AT_INDEX_ALLOCATION;
-		ni->name = I30;
-		ni->name_len = 4;
-
-		if (!(ir->index.flags & LARGE_INDEX)) {
-			/* No index allocation. */
-			vi->i_size = ni->initialized_size =
-					ni->allocated_size = 0;
-			/* We are done with the mft record, so we release it. */
-			ntfs_attr_put_search_ctx(ctx);
-			unmap_mft_record(ni);
-			m = NULL;
-			ctx = NULL;
-			goto skip_large_dir_stuff;
-		} /* LARGE_INDEX: Index allocation present. Setup state. */
-		NInoSetIndexAllocPresent(ni);
-		/* Find index allocation attribute. */
-		ntfs_attr_reinit_search_ctx(ctx);
-		err = ntfs_attr_lookup(AT_INDEX_ALLOCATION, I30, 4,
-				CASE_SENSITIVE, 0, NULL, 0, ctx);
-		if (unlikely(err)) {
-			if (err == -ENOENT)
-				ntfs_error(vi->i_sb, "$INDEX_ALLOCATION "
-						"attribute is not present but "
-						"$INDEX_ROOT indicated it is.");
-			else
-				ntfs_error(vi->i_sb, "Failed to lookup "
-						"$INDEX_ALLOCATION "
-						"attribute.");
-			goto unm_err_out;
-		}
-		a = ctx->attr;
-		if (!a->non_resident) {
-			ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute "
-					"is resident.");
-			goto unm_err_out;
-		}
-		/*
-		 * Ensure the attribute name is placed before the mapping pairs
-		 * array.
-		 */
-		if (unlikely(a->name_length && (le16_to_cpu(a->name_offset) >=
-				le16_to_cpu(
-				a->data.non_resident.mapping_pairs_offset)))) {
-			ntfs_error(vol->sb, "$INDEX_ALLOCATION attribute name "
-					"is placed after the mapping pairs "
-					"array.");
-			goto unm_err_out;
-		}
-		if (a->flags & ATTR_IS_ENCRYPTED) {
-			ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute "
-					"is encrypted.");
-			goto unm_err_out;
-		}
-		if (a->flags & ATTR_IS_SPARSE) {
-			ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute "
-					"is sparse.");
-			goto unm_err_out;
-		}
-		if (a->flags & ATTR_COMPRESSION_MASK) {
-			ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute "
-					"is compressed.");
-			goto unm_err_out;
-		}
-		if (a->data.non_resident.lowest_vcn) {
-			ntfs_error(vi->i_sb, "First extent of "
-					"$INDEX_ALLOCATION attribute has non "
-					"zero lowest_vcn.");
-			goto unm_err_out;
-		}
-		vi->i_size = sle64_to_cpu(a->data.non_resident.data_size);
-		ni->initialized_size = sle64_to_cpu(
-				a->data.non_resident.initialized_size);
-		ni->allocated_size = sle64_to_cpu(
-				a->data.non_resident.allocated_size);
-		/*
-		 * We are done with the mft record, so we release it. Otherwise
-		 * we would deadlock in ntfs_attr_iget().
-		 */
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(ni);
-		m = NULL;
-		ctx = NULL;
-		/* Get the index bitmap attribute inode. */
-		bvi = ntfs_attr_iget(vi, AT_BITMAP, I30, 4);
-		if (IS_ERR(bvi)) {
-			ntfs_error(vi->i_sb, "Failed to get bitmap attribute.");
-			err = PTR_ERR(bvi);
-			goto unm_err_out;
-		}
-		bni = NTFS_I(bvi);
-		if (NInoCompressed(bni) || NInoEncrypted(bni) ||
-				NInoSparse(bni)) {
-			ntfs_error(vi->i_sb, "$BITMAP attribute is compressed "
-					"and/or encrypted and/or sparse.");
-			goto iput_unm_err_out;
-		}
-		/* Consistency check bitmap size vs. index allocation size. */
-		bvi_size = i_size_read(bvi);
-		if ((bvi_size << 3) < (vi->i_size >>
-				ni->itype.index.block_size_bits)) {
-			ntfs_error(vi->i_sb, "Index bitmap too small (0x%llx) "
-					"for index allocation (0x%llx).",
-					bvi_size << 3, vi->i_size);
-			goto iput_unm_err_out;
-		}
-		/* No longer need the bitmap attribute inode. */
-		iput(bvi);
-skip_large_dir_stuff:
-		/* Setup the operations for this inode. */
-		vi->i_op = &ntfs_dir_inode_ops;
-		vi->i_fop = &ntfs_dir_ops;
-		vi->i_mapping->a_ops = &ntfs_mst_aops;
-	} else {
-		/* It is a file. */
-		ntfs_attr_reinit_search_ctx(ctx);
-
-		/* Setup the data attribute, even if not present. */
-		ni->type = AT_DATA;
-		ni->name = NULL;
-		ni->name_len = 0;
-
-		/* Find first extent of the unnamed data attribute. */
-		err = ntfs_attr_lookup(AT_DATA, NULL, 0, 0, 0, NULL, 0, ctx);
-		if (unlikely(err)) {
-			vi->i_size = ni->initialized_size =
-					ni->allocated_size = 0;
-			if (err != -ENOENT) {
-				ntfs_error(vi->i_sb, "Failed to lookup $DATA "
-						"attribute.");
-				goto unm_err_out;
-			}
-			/*
-			 * FILE_Secure does not have an unnamed $DATA
-			 * attribute, so we special case it here.
-			 */
-			if (vi->i_ino == FILE_Secure)
-				goto no_data_attr_special_case;
-			/*
-			 * Most if not all the system files in the $Extend
-			 * system directory do not have unnamed data
-			 * attributes so we need to check if the parent
-			 * directory of the file is FILE_Extend and if it is
-			 * ignore this error. To do this we need to get the
-			 * name of this inode from the mft record as the name
-			 * contains the back reference to the parent directory.
-			 */
-			if (ntfs_is_extended_system_file(ctx) > 0)
-				goto no_data_attr_special_case;
-			// FIXME: File is corrupt! Hot-fix with empty data
-			// attribute if recovery option is set.
-			ntfs_error(vi->i_sb, "$DATA attribute is missing.");
-			goto unm_err_out;
-		}
-		a = ctx->attr;
-		/* Setup the state. */
-		if (a->flags & (ATTR_COMPRESSION_MASK | ATTR_IS_SPARSE)) {
-			if (a->flags & ATTR_COMPRESSION_MASK) {
-				NInoSetCompressed(ni);
-				if (vol->cluster_size > 4096) {
-					ntfs_error(vi->i_sb, "Found "
-							"compressed data but "
-							"compression is "
-							"disabled due to "
-							"cluster size (%i) > "
-							"4kiB.",
-							vol->cluster_size);
-					goto unm_err_out;
-				}
-				if ((a->flags & ATTR_COMPRESSION_MASK)
-						!= ATTR_IS_COMPRESSED) {
-					ntfs_error(vi->i_sb, "Found unknown "
-							"compression method "
-							"or corrupt file.");
-					goto unm_err_out;
-				}
-			}
-			if (a->flags & ATTR_IS_SPARSE)
-				NInoSetSparse(ni);
-		}
-		if (a->flags & ATTR_IS_ENCRYPTED) {
-			if (NInoCompressed(ni)) {
-				ntfs_error(vi->i_sb, "Found encrypted and "
-						"compressed data.");
-				goto unm_err_out;
-			}
-			NInoSetEncrypted(ni);
-		}
-		if (a->non_resident) {
-			NInoSetNonResident(ni);
-			if (NInoCompressed(ni) || NInoSparse(ni)) {
-				if (NInoCompressed(ni) && a->data.non_resident.
-						compression_unit != 4) {
-					ntfs_error(vi->i_sb, "Found "
-							"non-standard "
-							"compression unit (%u "
-							"instead of 4).  "
-							"Cannot handle this.",
-							a->data.non_resident.
-							compression_unit);
-					err = -EOPNOTSUPP;
-					goto unm_err_out;
-				}
-				if (a->data.non_resident.compression_unit) {
-					ni->itype.compressed.block_size = 1U <<
-							(a->data.non_resident.
-							compression_unit +
-							vol->cluster_size_bits);
-					ni->itype.compressed.block_size_bits =
-							ffs(ni->itype.
-							compressed.
-							block_size) - 1;
-					ni->itype.compressed.block_clusters =
-							1U << a->data.
-							non_resident.
-							compression_unit;
-				} else {
-					ni->itype.compressed.block_size = 0;
-					ni->itype.compressed.block_size_bits =
-							0;
-					ni->itype.compressed.block_clusters =
-							0;
-				}
-				ni->itype.compressed.size = sle64_to_cpu(
-						a->data.non_resident.
-						compressed_size);
-			}
-			if (a->data.non_resident.lowest_vcn) {
-				ntfs_error(vi->i_sb, "First extent of $DATA "
-						"attribute has non zero "
-						"lowest_vcn.");
-				goto unm_err_out;
-			}
-			vi->i_size = sle64_to_cpu(
-					a->data.non_resident.data_size);
-			ni->initialized_size = sle64_to_cpu(
-					a->data.non_resident.initialized_size);
-			ni->allocated_size = sle64_to_cpu(
-					a->data.non_resident.allocated_size);
-		} else { /* Resident attribute. */
-			vi->i_size = ni->initialized_size = le32_to_cpu(
-					a->data.resident.value_length);
-			ni->allocated_size = le32_to_cpu(a->length) -
-					le16_to_cpu(
-					a->data.resident.value_offset);
-			if (vi->i_size > ni->allocated_size) {
-				ntfs_error(vi->i_sb, "Resident data attribute "
-						"is corrupt (size exceeds "
-						"allocation).");
-				goto unm_err_out;
-			}
-		}
-no_data_attr_special_case:
-		/* We are done with the mft record, so we release it. */
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(ni);
-		m = NULL;
-		ctx = NULL;
-		/* Setup the operations for this inode. */
-		vi->i_op = &ntfs_file_inode_ops;
-		vi->i_fop = &ntfs_file_ops;
-		vi->i_mapping->a_ops = &ntfs_normal_aops;
-		if (NInoMstProtected(ni))
-			vi->i_mapping->a_ops = &ntfs_mst_aops;
-		else if (NInoCompressed(ni))
-			vi->i_mapping->a_ops = &ntfs_compressed_aops;
-	}
-	/*
-	 * The number of 512-byte blocks used on disk (for stat). This is in so
-	 * far inaccurate as it doesn't account for any named streams or other
-	 * special non-resident attributes, but that is how Windows works, too,
-	 * so we are at least consistent with Windows, if not entirely
-	 * consistent with the Linux Way. Doing it the Linux Way would cause a
-	 * significant slowdown as it would involve iterating over all
-	 * attributes in the mft record and adding the allocated/compressed
-	 * sizes of all non-resident attributes present to give us the Linux
-	 * correct size that should go into i_blocks (after division by 512).
-	 */
-	if (S_ISREG(vi->i_mode) && (NInoCompressed(ni) || NInoSparse(ni)))
-		vi->i_blocks = ni->itype.compressed.size >> 9;
-	else
-		vi->i_blocks = ni->allocated_size >> 9;
-	ntfs_debug("Done.");
-	return 0;
-iput_unm_err_out:
-	iput(bvi);
-unm_err_out:
-	if (!err)
-		err = -EIO;
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(ni);
-err_out:
-	ntfs_error(vol->sb, "Failed with error code %i.  Marking corrupt "
-			"inode 0x%lx as bad.  Run chkdsk.", err, vi->i_ino);
-	make_bad_inode(vi);
-	if (err != -EOPNOTSUPP && err != -ENOMEM)
-		NVolSetErrors(vol);
-	return err;
-}
-
-/**
- * ntfs_read_locked_attr_inode - read an attribute inode from its base inode
- * @base_vi:	base inode
- * @vi:		attribute inode to read
- *
- * ntfs_read_locked_attr_inode() is called from ntfs_attr_iget() to read the
- * attribute inode described by @vi into memory from the base mft record
- * described by @base_ni.
- *
- * ntfs_read_locked_attr_inode() maps, pins and locks the base inode for
- * reading and looks up the attribute described by @vi before setting up the
- * necessary fields in @vi as well as initializing the ntfs inode.
- *
- * Q: What locks are held when the function is called?
- * A: i_state has I_NEW set, hence the inode is locked, also
- *    i_count is set to 1, so it is not going to go away
- *
- * Return 0 on success and -errno on error.  In the error case, the inode will
- * have had make_bad_inode() executed on it.
- *
- * Note this cannot be called for AT_INDEX_ALLOCATION.
- */
-static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi)
-{
-	ntfs_volume *vol = NTFS_SB(vi->i_sb);
-	ntfs_inode *ni, *base_ni;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
-	ntfs_attr_search_ctx *ctx;
-	int err = 0;
-
-	ntfs_debug("Entering for i_ino 0x%lx.", vi->i_ino);
-
-	ntfs_init_big_inode(vi);
-
-	ni	= NTFS_I(vi);
-	base_ni = NTFS_I(base_vi);
-
-	/* Just mirror the values from the base inode. */
-	vi->i_uid	= base_vi->i_uid;
-	vi->i_gid	= base_vi->i_gid;
-	set_nlink(vi, base_vi->i_nlink);
-	inode_set_mtime_to_ts(vi, inode_get_mtime(base_vi));
-	inode_set_ctime_to_ts(vi, inode_get_ctime(base_vi));
-	inode_set_atime_to_ts(vi, inode_get_atime(base_vi));
-	vi->i_generation = ni->seq_no = base_ni->seq_no;
-
-	/* Set inode type to zero but preserve permissions. */
-	vi->i_mode	= base_vi->i_mode & ~S_IFMT;
-
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		goto err_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (!ctx) {
-		err = -ENOMEM;
-		goto unm_err_out;
-	}
-	/* Find the attribute. */
-	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err))
-		goto unm_err_out;
-	a = ctx->attr;
-	if (a->flags & (ATTR_COMPRESSION_MASK | ATTR_IS_SPARSE)) {
-		if (a->flags & ATTR_COMPRESSION_MASK) {
-			NInoSetCompressed(ni);
-			if ((ni->type != AT_DATA) || (ni->type == AT_DATA &&
-					ni->name_len)) {
-				ntfs_error(vi->i_sb, "Found compressed "
-						"non-data or named data "
-						"attribute.  Please report "
-						"you saw this message to "
-						"linux-ntfs-dev@lists."
-						"sourceforge.net");
-				goto unm_err_out;
-			}
-			if (vol->cluster_size > 4096) {
-				ntfs_error(vi->i_sb, "Found compressed "
-						"attribute but compression is "
-						"disabled due to cluster size "
-						"(%i) > 4kiB.",
-						vol->cluster_size);
-				goto unm_err_out;
-			}
-			if ((a->flags & ATTR_COMPRESSION_MASK) !=
-					ATTR_IS_COMPRESSED) {
-				ntfs_error(vi->i_sb, "Found unknown "
-						"compression method.");
-				goto unm_err_out;
-			}
-		}
-		/*
-		 * The compressed/sparse flag set in an index root just means
-		 * to compress all files.
-		 */
-		if (NInoMstProtected(ni) && ni->type != AT_INDEX_ROOT) {
-			ntfs_error(vi->i_sb, "Found mst protected attribute "
-					"but the attribute is %s.  Please "
-					"report you saw this message to "
-					"linux-ntfs-dev@lists.sourceforge.net",
-					NInoCompressed(ni) ? "compressed" :
-					"sparse");
-			goto unm_err_out;
-		}
-		if (a->flags & ATTR_IS_SPARSE)
-			NInoSetSparse(ni);
-	}
-	if (a->flags & ATTR_IS_ENCRYPTED) {
-		if (NInoCompressed(ni)) {
-			ntfs_error(vi->i_sb, "Found encrypted and compressed "
-					"data.");
-			goto unm_err_out;
-		}
-		/*
-		 * The encryption flag set in an index root just means to
-		 * encrypt all files.
-		 */
-		if (NInoMstProtected(ni) && ni->type != AT_INDEX_ROOT) {
-			ntfs_error(vi->i_sb, "Found mst protected attribute "
-					"but the attribute is encrypted.  "
-					"Please report you saw this message "
-					"to linux-ntfs-dev@lists.sourceforge."
-					"net");
-			goto unm_err_out;
-		}
-		if (ni->type != AT_DATA) {
-			ntfs_error(vi->i_sb, "Found encrypted non-data "
-					"attribute.");
-			goto unm_err_out;
-		}
-		NInoSetEncrypted(ni);
-	}
-	if (!a->non_resident) {
-		/* Ensure the attribute name is placed before the value. */
-		if (unlikely(a->name_length && (le16_to_cpu(a->name_offset) >=
-				le16_to_cpu(a->data.resident.value_offset)))) {
-			ntfs_error(vol->sb, "Attribute name is placed after "
-					"the attribute value.");
-			goto unm_err_out;
-		}
-		if (NInoMstProtected(ni)) {
-			ntfs_error(vi->i_sb, "Found mst protected attribute "
-					"but the attribute is resident.  "
-					"Please report you saw this message to "
-					"linux-ntfs-dev@lists.sourceforge.net");
-			goto unm_err_out;
-		}
-		vi->i_size = ni->initialized_size = le32_to_cpu(
-				a->data.resident.value_length);
-		ni->allocated_size = le32_to_cpu(a->length) -
-				le16_to_cpu(a->data.resident.value_offset);
-		if (vi->i_size > ni->allocated_size) {
-			ntfs_error(vi->i_sb, "Resident attribute is corrupt "
-					"(size exceeds allocation).");
-			goto unm_err_out;
-		}
-	} else {
-		NInoSetNonResident(ni);
-		/*
-		 * Ensure the attribute name is placed before the mapping pairs
-		 * array.
-		 */
-		if (unlikely(a->name_length && (le16_to_cpu(a->name_offset) >=
-				le16_to_cpu(
-				a->data.non_resident.mapping_pairs_offset)))) {
-			ntfs_error(vol->sb, "Attribute name is placed after "
-					"the mapping pairs array.");
-			goto unm_err_out;
-		}
-		if (NInoCompressed(ni) || NInoSparse(ni)) {
-			if (NInoCompressed(ni) && a->data.non_resident.
-					compression_unit != 4) {
-				ntfs_error(vi->i_sb, "Found non-standard "
-						"compression unit (%u instead "
-						"of 4).  Cannot handle this.",
-						a->data.non_resident.
-						compression_unit);
-				err = -EOPNOTSUPP;
-				goto unm_err_out;
-			}
-			if (a->data.non_resident.compression_unit) {
-				ni->itype.compressed.block_size = 1U <<
-						(a->data.non_resident.
-						compression_unit +
-						vol->cluster_size_bits);
-				ni->itype.compressed.block_size_bits =
-						ffs(ni->itype.compressed.
-						block_size) - 1;
-				ni->itype.compressed.block_clusters = 1U <<
-						a->data.non_resident.
-						compression_unit;
-			} else {
-				ni->itype.compressed.block_size = 0;
-				ni->itype.compressed.block_size_bits = 0;
-				ni->itype.compressed.block_clusters = 0;
-			}
-			ni->itype.compressed.size = sle64_to_cpu(
-					a->data.non_resident.compressed_size);
-		}
-		if (a->data.non_resident.lowest_vcn) {
-			ntfs_error(vi->i_sb, "First extent of attribute has "
-					"non-zero lowest_vcn.");
-			goto unm_err_out;
-		}
-		vi->i_size = sle64_to_cpu(a->data.non_resident.data_size);
-		ni->initialized_size = sle64_to_cpu(
-				a->data.non_resident.initialized_size);
-		ni->allocated_size = sle64_to_cpu(
-				a->data.non_resident.allocated_size);
-	}
-	vi->i_mapping->a_ops = &ntfs_normal_aops;
-	if (NInoMstProtected(ni))
-		vi->i_mapping->a_ops = &ntfs_mst_aops;
-	else if (NInoCompressed(ni))
-		vi->i_mapping->a_ops = &ntfs_compressed_aops;
-	if ((NInoCompressed(ni) || NInoSparse(ni)) && ni->type != AT_INDEX_ROOT)
-		vi->i_blocks = ni->itype.compressed.size >> 9;
-	else
-		vi->i_blocks = ni->allocated_size >> 9;
-	/*
-	 * Make sure the base inode does not go away and attach it to the
-	 * attribute inode.
-	 */
-	igrab(base_vi);
-	ni->ext.base_ntfs_ino = base_ni;
-	ni->nr_extents = -1;
-
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-
-	ntfs_debug("Done.");
-	return 0;
-
-unm_err_out:
-	if (!err)
-		err = -EIO;
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-err_out:
-	ntfs_error(vol->sb, "Failed with error code %i while reading attribute "
-			"inode (mft_no 0x%lx, type 0x%x, name_len %i).  "
-			"Marking corrupt inode and base inode 0x%lx as bad.  "
-			"Run chkdsk.", err, vi->i_ino, ni->type, ni->name_len,
-			base_vi->i_ino);
-	make_bad_inode(vi);
-	if (err != -ENOMEM)
-		NVolSetErrors(vol);
-	return err;
-}
-
-/**
- * ntfs_read_locked_index_inode - read an index inode from its base inode
- * @base_vi:	base inode
- * @vi:		index inode to read
- *
- * ntfs_read_locked_index_inode() is called from ntfs_index_iget() to read the
- * index inode described by @vi into memory from the base mft record described
- * by @base_ni.
- *
- * ntfs_read_locked_index_inode() maps, pins and locks the base inode for
- * reading and looks up the attributes relating to the index described by @vi
- * before setting up the necessary fields in @vi as well as initializing the
- * ntfs inode.
- *
- * Note, index inodes are essentially attribute inodes (NInoAttr() is true)
- * with the attribute type set to AT_INDEX_ALLOCATION.  Apart from that, they
- * are setup like directory inodes since directories are a special case of
- * indices ao they need to be treated in much the same way.  Most importantly,
- * for small indices the index allocation attribute might not actually exist.
- * However, the index root attribute always exists but this does not need to
- * have an inode associated with it and this is why we define a new inode type
- * index.  Also, like for directories, we need to have an attribute inode for
- * the bitmap attribute corresponding to the index allocation attribute and we
- * can store this in the appropriate field of the inode, just like we do for
- * normal directory inodes.
- *
- * Q: What locks are held when the function is called?
- * A: i_state has I_NEW set, hence the inode is locked, also
- *    i_count is set to 1, so it is not going to go away
- *
- * Return 0 on success and -errno on error.  In the error case, the inode will
- * have had make_bad_inode() executed on it.
- */
-static int ntfs_read_locked_index_inode(struct inode *base_vi, struct inode *vi)
-{
-	loff_t bvi_size;
-	ntfs_volume *vol = NTFS_SB(vi->i_sb);
-	ntfs_inode *ni, *base_ni, *bni;
-	struct inode *bvi;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
-	ntfs_attr_search_ctx *ctx;
-	INDEX_ROOT *ir;
-	u8 *ir_end, *index_end;
-	int err = 0;
-
-	ntfs_debug("Entering for i_ino 0x%lx.", vi->i_ino);
-	ntfs_init_big_inode(vi);
-	ni	= NTFS_I(vi);
-	base_ni = NTFS_I(base_vi);
-	/* Just mirror the values from the base inode. */
-	vi->i_uid	= base_vi->i_uid;
-	vi->i_gid	= base_vi->i_gid;
-	set_nlink(vi, base_vi->i_nlink);
-	inode_set_mtime_to_ts(vi, inode_get_mtime(base_vi));
-	inode_set_ctime_to_ts(vi, inode_get_ctime(base_vi));
-	inode_set_atime_to_ts(vi, inode_get_atime(base_vi));
-	vi->i_generation = ni->seq_no = base_ni->seq_no;
-	/* Set inode type to zero but preserve permissions. */
-	vi->i_mode	= base_vi->i_mode & ~S_IFMT;
-	/* Map the mft record for the base inode. */
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		goto err_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (!ctx) {
-		err = -ENOMEM;
-		goto unm_err_out;
-	}
-	/* Find the index root attribute. */
-	err = ntfs_attr_lookup(AT_INDEX_ROOT, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT)
-			ntfs_error(vi->i_sb, "$INDEX_ROOT attribute is "
-					"missing.");
-		goto unm_err_out;
-	}
-	a = ctx->attr;
-	/* Set up the state. */
-	if (unlikely(a->non_resident)) {
-		ntfs_error(vol->sb, "$INDEX_ROOT attribute is not resident.");
-		goto unm_err_out;
-	}
-	/* Ensure the attribute name is placed before the value. */
-	if (unlikely(a->name_length && (le16_to_cpu(a->name_offset) >=
-			le16_to_cpu(a->data.resident.value_offset)))) {
-		ntfs_error(vol->sb, "$INDEX_ROOT attribute name is placed "
-				"after the attribute value.");
-		goto unm_err_out;
-	}
-	/*
-	 * Compressed/encrypted/sparse index root is not allowed, except for
-	 * directories of course but those are not dealt with here.
-	 */
-	if (a->flags & (ATTR_COMPRESSION_MASK | ATTR_IS_ENCRYPTED |
-			ATTR_IS_SPARSE)) {
-		ntfs_error(vi->i_sb, "Found compressed/encrypted/sparse index "
-				"root attribute.");
-		goto unm_err_out;
-	}
-	ir = (INDEX_ROOT*)((u8*)a + le16_to_cpu(a->data.resident.value_offset));
-	ir_end = (u8*)ir + le32_to_cpu(a->data.resident.value_length);
-	if (ir_end > (u8*)ctx->mrec + vol->mft_record_size) {
-		ntfs_error(vi->i_sb, "$INDEX_ROOT attribute is corrupt.");
-		goto unm_err_out;
-	}
-	index_end = (u8*)&ir->index + le32_to_cpu(ir->index.index_length);
-	if (index_end > ir_end) {
-		ntfs_error(vi->i_sb, "Index is corrupt.");
-		goto unm_err_out;
-	}
-	if (ir->type) {
-		ntfs_error(vi->i_sb, "Index type is not 0 (type is 0x%x).",
-				le32_to_cpu(ir->type));
-		goto unm_err_out;
-	}
-	ni->itype.index.collation_rule = ir->collation_rule;
-	ntfs_debug("Index collation rule is 0x%x.",
-			le32_to_cpu(ir->collation_rule));
-	ni->itype.index.block_size = le32_to_cpu(ir->index_block_size);
-	if (!is_power_of_2(ni->itype.index.block_size)) {
-		ntfs_error(vi->i_sb, "Index block size (%u) is not a power of "
-				"two.", ni->itype.index.block_size);
-		goto unm_err_out;
-	}
-	if (ni->itype.index.block_size > PAGE_SIZE) {
-		ntfs_error(vi->i_sb, "Index block size (%u) > PAGE_SIZE "
-				"(%ld) is not supported.  Sorry.",
-				ni->itype.index.block_size, PAGE_SIZE);
-		err = -EOPNOTSUPP;
-		goto unm_err_out;
-	}
-	if (ni->itype.index.block_size < NTFS_BLOCK_SIZE) {
-		ntfs_error(vi->i_sb, "Index block size (%u) < NTFS_BLOCK_SIZE "
-				"(%i) is not supported.  Sorry.",
-				ni->itype.index.block_size, NTFS_BLOCK_SIZE);
-		err = -EOPNOTSUPP;
-		goto unm_err_out;
-	}
-	ni->itype.index.block_size_bits = ffs(ni->itype.index.block_size) - 1;
-	/* Determine the size of a vcn in the index. */
-	if (vol->cluster_size <= ni->itype.index.block_size) {
-		ni->itype.index.vcn_size = vol->cluster_size;
-		ni->itype.index.vcn_size_bits = vol->cluster_size_bits;
-	} else {
-		ni->itype.index.vcn_size = vol->sector_size;
-		ni->itype.index.vcn_size_bits = vol->sector_size_bits;
-	}
-	/* Check for presence of index allocation attribute. */
-	if (!(ir->index.flags & LARGE_INDEX)) {
-		/* No index allocation. */
-		vi->i_size = ni->initialized_size = ni->allocated_size = 0;
-		/* We are done with the mft record, so we release it. */
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(base_ni);
-		m = NULL;
-		ctx = NULL;
-		goto skip_large_index_stuff;
-	} /* LARGE_INDEX:  Index allocation present.  Setup state. */
-	NInoSetIndexAllocPresent(ni);
-	/* Find index allocation attribute. */
-	ntfs_attr_reinit_search_ctx(ctx);
-	err = ntfs_attr_lookup(AT_INDEX_ALLOCATION, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT)
-			ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute is "
-					"not present but $INDEX_ROOT "
-					"indicated it is.");
-		else
-			ntfs_error(vi->i_sb, "Failed to lookup "
-					"$INDEX_ALLOCATION attribute.");
-		goto unm_err_out;
-	}
-	a = ctx->attr;
-	if (!a->non_resident) {
-		ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute is "
-				"resident.");
-		goto unm_err_out;
-	}
-	/*
-	 * Ensure the attribute name is placed before the mapping pairs array.
-	 */
-	if (unlikely(a->name_length && (le16_to_cpu(a->name_offset) >=
-			le16_to_cpu(
-			a->data.non_resident.mapping_pairs_offset)))) {
-		ntfs_error(vol->sb, "$INDEX_ALLOCATION attribute name is "
-				"placed after the mapping pairs array.");
-		goto unm_err_out;
-	}
-	if (a->flags & ATTR_IS_ENCRYPTED) {
-		ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute is "
-				"encrypted.");
-		goto unm_err_out;
-	}
-	if (a->flags & ATTR_IS_SPARSE) {
-		ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute is sparse.");
-		goto unm_err_out;
-	}
-	if (a->flags & ATTR_COMPRESSION_MASK) {
-		ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute is "
-				"compressed.");
-		goto unm_err_out;
-	}
-	if (a->data.non_resident.lowest_vcn) {
-		ntfs_error(vi->i_sb, "First extent of $INDEX_ALLOCATION "
-				"attribute has non zero lowest_vcn.");
-		goto unm_err_out;
-	}
-	vi->i_size = sle64_to_cpu(a->data.non_resident.data_size);
-	ni->initialized_size = sle64_to_cpu(
-			a->data.non_resident.initialized_size);
-	ni->allocated_size = sle64_to_cpu(a->data.non_resident.allocated_size);
-	/*
-	 * We are done with the mft record, so we release it.  Otherwise
-	 * we would deadlock in ntfs_attr_iget().
-	 */
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-	m = NULL;
-	ctx = NULL;
-	/* Get the index bitmap attribute inode. */
-	bvi = ntfs_attr_iget(base_vi, AT_BITMAP, ni->name, ni->name_len);
-	if (IS_ERR(bvi)) {
-		ntfs_error(vi->i_sb, "Failed to get bitmap attribute.");
-		err = PTR_ERR(bvi);
-		goto unm_err_out;
-	}
-	bni = NTFS_I(bvi);
-	if (NInoCompressed(bni) || NInoEncrypted(bni) ||
-			NInoSparse(bni)) {
-		ntfs_error(vi->i_sb, "$BITMAP attribute is compressed and/or "
-				"encrypted and/or sparse.");
-		goto iput_unm_err_out;
-	}
-	/* Consistency check bitmap size vs. index allocation size. */
-	bvi_size = i_size_read(bvi);
-	if ((bvi_size << 3) < (vi->i_size >> ni->itype.index.block_size_bits)) {
-		ntfs_error(vi->i_sb, "Index bitmap too small (0x%llx) for "
-				"index allocation (0x%llx).", bvi_size << 3,
-				vi->i_size);
-		goto iput_unm_err_out;
-	}
-	iput(bvi);
-skip_large_index_stuff:
-	/* Setup the operations for this index inode. */
-	vi->i_mapping->a_ops = &ntfs_mst_aops;
-	vi->i_blocks = ni->allocated_size >> 9;
-	/*
-	 * Make sure the base inode doesn't go away and attach it to the
-	 * index inode.
-	 */
-	igrab(base_vi);
-	ni->ext.base_ntfs_ino = base_ni;
-	ni->nr_extents = -1;
-
-	ntfs_debug("Done.");
-	return 0;
-iput_unm_err_out:
-	iput(bvi);
-unm_err_out:
-	if (!err)
-		err = -EIO;
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(base_ni);
-err_out:
-	ntfs_error(vi->i_sb, "Failed with error code %i while reading index "
-			"inode (mft_no 0x%lx, name_len %i.", err, vi->i_ino,
-			ni->name_len);
-	make_bad_inode(vi);
-	if (err != -EOPNOTSUPP && err != -ENOMEM)
-		NVolSetErrors(vol);
-	return err;
-}
-
-/*
- * The MFT inode has special locking, so teach the lock validator
- * about this by splitting off the locking rules of the MFT from
- * the locking rules of other inodes. The MFT inode can never be
- * accessed from the VFS side (or even internally), only by the
- * map_mft functions.
- */
-static struct lock_class_key mft_ni_runlist_lock_key, mft_ni_mrec_lock_key;
-
-/**
- * ntfs_read_inode_mount - special read_inode for mount time use only
- * @vi:		inode to read
- *
- * Read inode FILE_MFT at mount time, only called with super_block lock
- * held from within the read_super() code path.
- *
- * This function exists because when it is called the page cache for $MFT/$DATA
- * is not initialized and hence we cannot get at the contents of mft records
- * by calling map_mft_record*().
- *
- * Further it needs to cope with the circular references problem, i.e. cannot
- * load any attributes other than $ATTRIBUTE_LIST until $DATA is loaded, because
- * we do not know where the other extent mft records are yet and again, because
- * we cannot call map_mft_record*() yet.  Obviously this applies only when an
- * attribute list is actually present in $MFT inode.
- *
- * We solve these problems by starting with the $DATA attribute before anything
- * else and iterating using ntfs_attr_lookup($DATA) over all extents.  As each
- * extent is found, we ntfs_mapping_pairs_decompress() including the implied
- * ntfs_runlists_merge().  Each step of the iteration necessarily provides
- * sufficient information for the next step to complete.
- *
- * This should work but there are two possible pit falls (see inline comments
- * below), but only time will tell if they are real pits or just smoke...
- */
-int ntfs_read_inode_mount(struct inode *vi)
-{
-	VCN next_vcn, last_vcn, highest_vcn;
-	s64 block;
-	struct super_block *sb = vi->i_sb;
-	ntfs_volume *vol = NTFS_SB(sb);
-	struct buffer_head *bh;
-	ntfs_inode *ni;
-	MFT_RECORD *m = NULL;
-	ATTR_RECORD *a;
-	ntfs_attr_search_ctx *ctx;
-	unsigned int i, nr_blocks;
-	int err;
-
-	ntfs_debug("Entering.");
-
-	/* Initialize the ntfs specific part of @vi. */
-	ntfs_init_big_inode(vi);
-
-	ni = NTFS_I(vi);
-
-	/* Setup the data attribute. It is special as it is mst protected. */
-	NInoSetNonResident(ni);
-	NInoSetMstProtected(ni);
-	NInoSetSparseDisabled(ni);
-	ni->type = AT_DATA;
-	ni->name = NULL;
-	ni->name_len = 0;
-	/*
-	 * This sets up our little cheat allowing us to reuse the async read io
-	 * completion handler for directories.
-	 */
-	ni->itype.index.block_size = vol->mft_record_size;
-	ni->itype.index.block_size_bits = vol->mft_record_size_bits;
-
-	/* Very important! Needed to be able to call map_mft_record*(). */
-	vol->mft_ino = vi;
-
-	/* Allocate enough memory to read the first mft record. */
-	if (vol->mft_record_size > 64 * 1024) {
-		ntfs_error(sb, "Unsupported mft record size %i (max 64kiB).",
-				vol->mft_record_size);
-		goto err_out;
-	}
-	i = vol->mft_record_size;
-	if (i < sb->s_blocksize)
-		i = sb->s_blocksize;
-	m = (MFT_RECORD*)ntfs_malloc_nofs(i);
-	if (!m) {
-		ntfs_error(sb, "Failed to allocate buffer for $MFT record 0.");
-		goto err_out;
-	}
-
-	/* Determine the first block of the $MFT/$DATA attribute. */
-	block = vol->mft_lcn << vol->cluster_size_bits >>
-			sb->s_blocksize_bits;
-	nr_blocks = vol->mft_record_size >> sb->s_blocksize_bits;
-	if (!nr_blocks)
-		nr_blocks = 1;
-
-	/* Load $MFT/$DATA's first mft record. */
-	for (i = 0; i < nr_blocks; i++) {
-		bh = sb_bread(sb, block++);
-		if (!bh) {
-			ntfs_error(sb, "Device read failed.");
-			goto err_out;
-		}
-		memcpy((char*)m + (i << sb->s_blocksize_bits), bh->b_data,
-				sb->s_blocksize);
-		brelse(bh);
-	}
-
-	if (le32_to_cpu(m->bytes_allocated) != vol->mft_record_size) {
-		ntfs_error(sb, "Incorrect mft record size %u in superblock, should be %u.",
-				le32_to_cpu(m->bytes_allocated), vol->mft_record_size);
-		goto err_out;
-	}
-
-	/* Apply the mst fixups. */
-	if (post_read_mst_fixup((NTFS_RECORD*)m, vol->mft_record_size)) {
-		/* FIXME: Try to use the $MFTMirr now. */
-		ntfs_error(sb, "MST fixup failed. $MFT is corrupt.");
-		goto err_out;
-	}
-
-	/* Sanity check offset to the first attribute */
-	if (le16_to_cpu(m->attrs_offset) >= le32_to_cpu(m->bytes_allocated)) {
-		ntfs_error(sb, "Incorrect mft offset to the first attribute %u in superblock.",
-			       le16_to_cpu(m->attrs_offset));
-		goto err_out;
-	}
-
-	/* Need this to sanity check attribute list references to $MFT. */
-	vi->i_generation = ni->seq_no = le16_to_cpu(m->sequence_number);
-
-	/* Provides read_folio() for map_mft_record(). */
-	vi->i_mapping->a_ops = &ntfs_mst_aops;
-
-	ctx = ntfs_attr_get_search_ctx(ni, m);
-	if (!ctx) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-
-	/* Find the attribute list attribute if present. */
-	err = ntfs_attr_lookup(AT_ATTRIBUTE_LIST, NULL, 0, 0, 0, NULL, 0, ctx);
-	if (err) {
-		if (unlikely(err != -ENOENT)) {
-			ntfs_error(sb, "Failed to lookup attribute list "
-					"attribute. You should run chkdsk.");
-			goto put_err_out;
-		}
-	} else /* if (!err) */ {
-		ATTR_LIST_ENTRY *al_entry, *next_al_entry;
-		u8 *al_end;
-		static const char *es = "  Not allowed.  $MFT is corrupt.  "
-				"You should run chkdsk.";
-
-		ntfs_debug("Attribute list attribute found in $MFT.");
-		NInoSetAttrList(ni);
-		a = ctx->attr;
-		if (a->flags & ATTR_COMPRESSION_MASK) {
-			ntfs_error(sb, "Attribute list attribute is "
-					"compressed.%s", es);
-			goto put_err_out;
-		}
-		if (a->flags & ATTR_IS_ENCRYPTED ||
-				a->flags & ATTR_IS_SPARSE) {
-			if (a->non_resident) {
-				ntfs_error(sb, "Non-resident attribute list "
-						"attribute is encrypted/"
-						"sparse.%s", es);
-				goto put_err_out;
-			}
-			ntfs_warning(sb, "Resident attribute list attribute "
-					"in $MFT system file is marked "
-					"encrypted/sparse which is not true.  "
-					"However, Windows allows this and "
-					"chkdsk does not detect or correct it "
-					"so we will just ignore the invalid "
-					"flags and pretend they are not set.");
-		}
-		/* Now allocate memory for the attribute list. */
-		ni->attr_list_size = (u32)ntfs_attr_size(a);
-		if (!ni->attr_list_size) {
-			ntfs_error(sb, "Attr_list_size is zero");
-			goto put_err_out;
-		}
-		ni->attr_list = ntfs_malloc_nofs(ni->attr_list_size);
-		if (!ni->attr_list) {
-			ntfs_error(sb, "Not enough memory to allocate buffer "
-					"for attribute list.");
-			goto put_err_out;
-		}
-		if (a->non_resident) {
-			NInoSetAttrListNonResident(ni);
-			if (a->data.non_resident.lowest_vcn) {
-				ntfs_error(sb, "Attribute list has non zero "
-						"lowest_vcn. $MFT is corrupt. "
-						"You should run chkdsk.");
-				goto put_err_out;
-			}
-			/* Setup the runlist. */
-			ni->attr_list_rl.rl = ntfs_mapping_pairs_decompress(vol,
-					a, NULL);
-			if (IS_ERR(ni->attr_list_rl.rl)) {
-				err = PTR_ERR(ni->attr_list_rl.rl);
-				ni->attr_list_rl.rl = NULL;
-				ntfs_error(sb, "Mapping pairs decompression "
-						"failed with error code %i.",
-						-err);
-				goto put_err_out;
-			}
-			/* Now load the attribute list. */
-			if ((err = load_attribute_list(vol, &ni->attr_list_rl,
-					ni->attr_list, ni->attr_list_size,
-					sle64_to_cpu(a->data.
-					non_resident.initialized_size)))) {
-				ntfs_error(sb, "Failed to load attribute list "
-						"attribute with error code %i.",
-						-err);
-				goto put_err_out;
-			}
-		} else /* if (!ctx.attr->non_resident) */ {
-			if ((u8*)a + le16_to_cpu(
-					a->data.resident.value_offset) +
-					le32_to_cpu(
-					a->data.resident.value_length) >
-					(u8*)ctx->mrec + vol->mft_record_size) {
-				ntfs_error(sb, "Corrupt attribute list "
-						"attribute.");
-				goto put_err_out;
-			}
-			/* Now copy the attribute list. */
-			memcpy(ni->attr_list, (u8*)a + le16_to_cpu(
-					a->data.resident.value_offset),
-					le32_to_cpu(
-					a->data.resident.value_length));
-		}
-		/* The attribute list is now setup in memory. */
-		/*
-		 * FIXME: I don't know if this case is actually possible.
-		 * According to logic it is not possible but I have seen too
-		 * many weird things in MS software to rely on logic... Thus we
-		 * perform a manual search and make sure the first $MFT/$DATA
-		 * extent is in the base inode. If it is not we abort with an
-		 * error and if we ever see a report of this error we will need
-		 * to do some magic in order to have the necessary mft record
-		 * loaded and in the right place in the page cache. But
-		 * hopefully logic will prevail and this never happens...
-		 */
-		al_entry = (ATTR_LIST_ENTRY*)ni->attr_list;
-		al_end = (u8*)al_entry + ni->attr_list_size;
-		for (;; al_entry = next_al_entry) {
-			/* Out of bounds check. */
-			if ((u8*)al_entry < ni->attr_list ||
-					(u8*)al_entry > al_end)
-				goto em_put_err_out;
-			/* Catch the end of the attribute list. */
-			if ((u8*)al_entry == al_end)
-				goto em_put_err_out;
-			if (!al_entry->length)
-				goto em_put_err_out;
-			if ((u8*)al_entry + 6 > al_end || (u8*)al_entry +
-					le16_to_cpu(al_entry->length) > al_end)
-				goto em_put_err_out;
-			next_al_entry = (ATTR_LIST_ENTRY*)((u8*)al_entry +
-					le16_to_cpu(al_entry->length));
-			if (le32_to_cpu(al_entry->type) > le32_to_cpu(AT_DATA))
-				goto em_put_err_out;
-			if (AT_DATA != al_entry->type)
-				continue;
-			/* We want an unnamed attribute. */
-			if (al_entry->name_length)
-				goto em_put_err_out;
-			/* Want the first entry, i.e. lowest_vcn == 0. */
-			if (al_entry->lowest_vcn)
-				goto em_put_err_out;
-			/* First entry has to be in the base mft record. */
-			if (MREF_LE(al_entry->mft_reference) != vi->i_ino) {
-				/* MFT references do not match, logic fails. */
-				ntfs_error(sb, "BUG: The first $DATA extent "
-						"of $MFT is not in the base "
-						"mft record. Please report "
-						"you saw this message to "
-						"linux-ntfs-dev@lists."
-						"sourceforge.net");
-				goto put_err_out;
-			} else {
-				/* Sequence numbers must match. */
-				if (MSEQNO_LE(al_entry->mft_reference) !=
-						ni->seq_no)
-					goto em_put_err_out;
-				/* Got it. All is ok. We can stop now. */
-				break;
-			}
-		}
-	}
-
-	ntfs_attr_reinit_search_ctx(ctx);
-
-	/* Now load all attribute extents. */
-	a = NULL;
-	next_vcn = last_vcn = highest_vcn = 0;
-	while (!(err = ntfs_attr_lookup(AT_DATA, NULL, 0, 0, next_vcn, NULL, 0,
-			ctx))) {
-		runlist_element *nrl;
-
-		/* Cache the current attribute. */
-		a = ctx->attr;
-		/* $MFT must be non-resident. */
-		if (!a->non_resident) {
-			ntfs_error(sb, "$MFT must be non-resident but a "
-					"resident extent was found. $MFT is "
-					"corrupt. Run chkdsk.");
-			goto put_err_out;
-		}
-		/* $MFT must be uncompressed and unencrypted. */
-		if (a->flags & ATTR_COMPRESSION_MASK ||
-				a->flags & ATTR_IS_ENCRYPTED ||
-				a->flags & ATTR_IS_SPARSE) {
-			ntfs_error(sb, "$MFT must be uncompressed, "
-					"non-sparse, and unencrypted but a "
-					"compressed/sparse/encrypted extent "
-					"was found. $MFT is corrupt. Run "
-					"chkdsk.");
-			goto put_err_out;
-		}
-		/*
-		 * Decompress the mapping pairs array of this extent and merge
-		 * the result into the existing runlist. No need for locking
-		 * as we have exclusive access to the inode at this time and we
-		 * are a mount in progress task, too.
-		 */
-		nrl = ntfs_mapping_pairs_decompress(vol, a, ni->runlist.rl);
-		if (IS_ERR(nrl)) {
-			ntfs_error(sb, "ntfs_mapping_pairs_decompress() "
-					"failed with error code %ld.  $MFT is "
-					"corrupt.", PTR_ERR(nrl));
-			goto put_err_out;
-		}
-		ni->runlist.rl = nrl;
-
-		/* Are we in the first extent? */
-		if (!next_vcn) {
-			if (a->data.non_resident.lowest_vcn) {
-				ntfs_error(sb, "First extent of $DATA "
-						"attribute has non zero "
-						"lowest_vcn. $MFT is corrupt. "
-						"You should run chkdsk.");
-				goto put_err_out;
-			}
-			/* Get the last vcn in the $DATA attribute. */
-			last_vcn = sle64_to_cpu(
-					a->data.non_resident.allocated_size)
-					>> vol->cluster_size_bits;
-			/* Fill in the inode size. */
-			vi->i_size = sle64_to_cpu(
-					a->data.non_resident.data_size);
-			ni->initialized_size = sle64_to_cpu(
-					a->data.non_resident.initialized_size);
-			ni->allocated_size = sle64_to_cpu(
-					a->data.non_resident.allocated_size);
-			/*
-			 * Verify the number of mft records does not exceed
-			 * 2^32 - 1.
-			 */
-			if ((vi->i_size >> vol->mft_record_size_bits) >=
-					(1ULL << 32)) {
-				ntfs_error(sb, "$MFT is too big! Aborting.");
-				goto put_err_out;
-			}
-			/*
-			 * We have got the first extent of the runlist for
-			 * $MFT which means it is now relatively safe to call
-			 * the normal ntfs_read_inode() function.
-			 * Complete reading the inode, this will actually
-			 * re-read the mft record for $MFT, this time entering
-			 * it into the page cache with which we complete the
-			 * kick start of the volume. It should be safe to do
-			 * this now as the first extent of $MFT/$DATA is
-			 * already known and we would hope that we don't need
-			 * further extents in order to find the other
-			 * attributes belonging to $MFT. Only time will tell if
-			 * this is really the case. If not we will have to play
-			 * magic at this point, possibly duplicating a lot of
-			 * ntfs_read_inode() at this point. We will need to
-			 * ensure we do enough of its work to be able to call
-			 * ntfs_read_inode() on extents of $MFT/$DATA. But lets
-			 * hope this never happens...
-			 */
-			ntfs_read_locked_inode(vi);
-			if (is_bad_inode(vi)) {
-				ntfs_error(sb, "ntfs_read_inode() of $MFT "
-						"failed. BUG or corrupt $MFT. "
-						"Run chkdsk and if no errors "
-						"are found, please report you "
-						"saw this message to "
-						"linux-ntfs-dev@lists."
-						"sourceforge.net");
-				ntfs_attr_put_search_ctx(ctx);
-				/* Revert to the safe super operations. */
-				ntfs_free(m);
-				return -1;
-			}
-			/*
-			 * Re-initialize some specifics about $MFT's inode as
-			 * ntfs_read_inode() will have set up the default ones.
-			 */
-			/* Set uid and gid to root. */
-			vi->i_uid = GLOBAL_ROOT_UID;
-			vi->i_gid = GLOBAL_ROOT_GID;
-			/* Regular file. No access for anyone. */
-			vi->i_mode = S_IFREG;
-			/* No VFS initiated operations allowed for $MFT. */
-			vi->i_op = &ntfs_empty_inode_ops;
-			vi->i_fop = &ntfs_empty_file_ops;
-		}
-
-		/* Get the lowest vcn for the next extent. */
-		highest_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn);
-		next_vcn = highest_vcn + 1;
-
-		/* Only one extent or error, which we catch below. */
-		if (next_vcn <= 0)
-			break;
-
-		/* Avoid endless loops due to corruption. */
-		if (next_vcn < sle64_to_cpu(
-				a->data.non_resident.lowest_vcn)) {
-			ntfs_error(sb, "$MFT has corrupt attribute list "
-					"attribute. Run chkdsk.");
-			goto put_err_out;
-		}
-	}
-	if (err != -ENOENT) {
-		ntfs_error(sb, "Failed to lookup $MFT/$DATA attribute extent. "
-				"$MFT is corrupt. Run chkdsk.");
-		goto put_err_out;
-	}
-	if (!a) {
-		ntfs_error(sb, "$MFT/$DATA attribute not found. $MFT is "
-				"corrupt. Run chkdsk.");
-		goto put_err_out;
-	}
-	if (highest_vcn && highest_vcn != last_vcn - 1) {
-		ntfs_error(sb, "Failed to load the complete runlist for "
-				"$MFT/$DATA. Driver bug or corrupt $MFT. "
-				"Run chkdsk.");
-		ntfs_debug("highest_vcn = 0x%llx, last_vcn - 1 = 0x%llx",
-				(unsigned long long)highest_vcn,
-				(unsigned long long)last_vcn - 1);
-		goto put_err_out;
-	}
-	ntfs_attr_put_search_ctx(ctx);
-	ntfs_debug("Done.");
-	ntfs_free(m);
-
-	/*
-	 * Split the locking rules of the MFT inode from the
-	 * locking rules of other inodes:
-	 */
-	lockdep_set_class(&ni->runlist.lock, &mft_ni_runlist_lock_key);
-	lockdep_set_class(&ni->mrec_lock, &mft_ni_mrec_lock_key);
-
-	return 0;
-
-em_put_err_out:
-	ntfs_error(sb, "Couldn't find first extent of $DATA attribute in "
-			"attribute list. $MFT is corrupt. Run chkdsk.");
-put_err_out:
-	ntfs_attr_put_search_ctx(ctx);
-err_out:
-	ntfs_error(sb, "Failed. Marking inode as bad.");
-	make_bad_inode(vi);
-	ntfs_free(m);
-	return -1;
-}
-
-static void __ntfs_clear_inode(ntfs_inode *ni)
-{
-	/* Free all alocated memory. */
-	down_write(&ni->runlist.lock);
-	if (ni->runlist.rl) {
-		ntfs_free(ni->runlist.rl);
-		ni->runlist.rl = NULL;
-	}
-	up_write(&ni->runlist.lock);
-
-	if (ni->attr_list) {
-		ntfs_free(ni->attr_list);
-		ni->attr_list = NULL;
-	}
-
-	down_write(&ni->attr_list_rl.lock);
-	if (ni->attr_list_rl.rl) {
-		ntfs_free(ni->attr_list_rl.rl);
-		ni->attr_list_rl.rl = NULL;
-	}
-	up_write(&ni->attr_list_rl.lock);
-
-	if (ni->name_len && ni->name != I30) {
-		/* Catch bugs... */
-		BUG_ON(!ni->name);
-		kfree(ni->name);
-	}
-}
-
-void ntfs_clear_extent_inode(ntfs_inode *ni)
-{
-	ntfs_debug("Entering for inode 0x%lx.", ni->mft_no);
-
-	BUG_ON(NInoAttr(ni));
-	BUG_ON(ni->nr_extents != -1);
-
-#ifdef NTFS_RW
-	if (NInoDirty(ni)) {
-		if (!is_bad_inode(VFS_I(ni->ext.base_ntfs_ino)))
-			ntfs_error(ni->vol->sb, "Clearing dirty extent inode!  "
-					"Losing data!  This is a BUG!!!");
-		// FIXME:  Do something!!!
-	}
-#endif /* NTFS_RW */
-
-	__ntfs_clear_inode(ni);
-
-	/* Bye, bye... */
-	ntfs_destroy_extent_inode(ni);
-}
-
-/**
- * ntfs_evict_big_inode - clean up the ntfs specific part of an inode
- * @vi:		vfs inode pending annihilation
- *
- * When the VFS is going to remove an inode from memory, ntfs_clear_big_inode()
- * is called, which deallocates all memory belonging to the NTFS specific part
- * of the inode and returns.
- *
- * If the MFT record is dirty, we commit it before doing anything else.
- */
-void ntfs_evict_big_inode(struct inode *vi)
-{
-	ntfs_inode *ni = NTFS_I(vi);
-
-	truncate_inode_pages_final(&vi->i_data);
-	clear_inode(vi);
-
-#ifdef NTFS_RW
-	if (NInoDirty(ni)) {
-		bool was_bad = (is_bad_inode(vi));
-
-		/* Committing the inode also commits all extent inodes. */
-		ntfs_commit_inode(vi);
-
-		if (!was_bad && (is_bad_inode(vi) || NInoDirty(ni))) {
-			ntfs_error(vi->i_sb, "Failed to commit dirty inode "
-					"0x%lx.  Losing data!", vi->i_ino);
-			// FIXME:  Do something!!!
-		}
-	}
-#endif /* NTFS_RW */
-
-	/* No need to lock at this stage as no one else has a reference. */
-	if (ni->nr_extents > 0) {
-		int i;
-
-		for (i = 0; i < ni->nr_extents; i++)
-			ntfs_clear_extent_inode(ni->ext.extent_ntfs_inos[i]);
-		kfree(ni->ext.extent_ntfs_inos);
-	}
-
-	__ntfs_clear_inode(ni);
-
-	if (NInoAttr(ni)) {
-		/* Release the base inode if we are holding it. */
-		if (ni->nr_extents == -1) {
-			iput(VFS_I(ni->ext.base_ntfs_ino));
-			ni->nr_extents = 0;
-			ni->ext.base_ntfs_ino = NULL;
-		}
-	}
-	BUG_ON(ni->page);
-	if (!atomic_dec_and_test(&ni->count))
-		BUG();
-	return;
-}
-
-/**
- * ntfs_show_options - show mount options in /proc/mounts
- * @sf:		seq_file in which to write our mount options
- * @root:	root of the mounted tree whose mount options to display
- *
- * Called by the VFS once for each mounted ntfs volume when someone reads
- * /proc/mounts in order to display the NTFS specific mount options of each
- * mount. The mount options of fs specified by @root are written to the seq file
- * @sf and success is returned.
- */
-int ntfs_show_options(struct seq_file *sf, struct dentry *root)
-{
-	ntfs_volume *vol = NTFS_SB(root->d_sb);
-	int i;
-
-	seq_printf(sf, ",uid=%i", from_kuid_munged(&init_user_ns, vol->uid));
-	seq_printf(sf, ",gid=%i", from_kgid_munged(&init_user_ns, vol->gid));
-	if (vol->fmask == vol->dmask)
-		seq_printf(sf, ",umask=0%o", vol->fmask);
-	else {
-		seq_printf(sf, ",fmask=0%o", vol->fmask);
-		seq_printf(sf, ",dmask=0%o", vol->dmask);
-	}
-	seq_printf(sf, ",nls=%s", vol->nls_map->charset);
-	if (NVolCaseSensitive(vol))
-		seq_printf(sf, ",case_sensitive");
-	if (NVolShowSystemFiles(vol))
-		seq_printf(sf, ",show_sys_files");
-	if (!NVolSparseEnabled(vol))
-		seq_printf(sf, ",disable_sparse");
-	for (i = 0; on_errors_arr[i].val; i++) {
-		if (on_errors_arr[i].val & vol->on_errors)
-			seq_printf(sf, ",errors=%s", on_errors_arr[i].str);
-	}
-	seq_printf(sf, ",mft_zone_multiplier=%i", vol->mft_zone_multiplier);
-	return 0;
-}
-
-#ifdef NTFS_RW
-
-static const char *es = "  Leaving inconsistent metadata.  Unmount and run "
-		"chkdsk.";
-
-/**
- * ntfs_truncate - called when the i_size of an ntfs inode is changed
- * @vi:		inode for which the i_size was changed
- *
- * We only support i_size changes for normal files at present, i.e. not
- * compressed and not encrypted.  This is enforced in ntfs_setattr(), see
- * below.
- *
- * The kernel guarantees that @vi is a regular file (S_ISREG() is true) and
- * that the change is allowed.
- *
- * This implies for us that @vi is a file inode rather than a directory, index,
- * or attribute inode as well as that @vi is a base inode.
- *
- * Returns 0 on success or -errno on error.
- *
- * Called with ->i_mutex held.
- */
-int ntfs_truncate(struct inode *vi)
-{
-	s64 new_size, old_size, nr_freed, new_alloc_size, old_alloc_size;
-	VCN highest_vcn;
-	unsigned long flags;
-	ntfs_inode *base_ni, *ni = NTFS_I(vi);
-	ntfs_volume *vol = ni->vol;
-	ntfs_attr_search_ctx *ctx;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
-	const char *te = "  Leaving file length out of sync with i_size.";
-	int err, mp_size, size_change, alloc_change;
-
-	ntfs_debug("Entering for inode 0x%lx.", vi->i_ino);
-	BUG_ON(NInoAttr(ni));
-	BUG_ON(S_ISDIR(vi->i_mode));
-	BUG_ON(NInoMstProtected(ni));
-	BUG_ON(ni->nr_extents < 0);
-retry_truncate:
-	/*
-	 * Lock the runlist for writing and map the mft record to ensure it is
-	 * safe to mess with the attribute runlist and sizes.
-	 */
-	down_write(&ni->runlist.lock);
-	if (!NInoAttr(ni))
-		base_ni = ni;
-	else
-		base_ni = ni->ext.base_ntfs_ino;
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		ntfs_error(vi->i_sb, "Failed to map mft record for inode 0x%lx "
-				"(error code %d).%s", vi->i_ino, err, te);
-		ctx = NULL;
-		m = NULL;
-		goto old_bad_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (unlikely(!ctx)) {
-		ntfs_error(vi->i_sb, "Failed to allocate a search context for "
-				"inode 0x%lx (not enough memory).%s",
-				vi->i_ino, te);
-		err = -ENOMEM;
-		goto old_bad_out;
-	}
-	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT) {
-			ntfs_error(vi->i_sb, "Open attribute is missing from "
-					"mft record.  Inode 0x%lx is corrupt.  "
-					"Run chkdsk.%s", vi->i_ino, te);
-			err = -EIO;
-		} else
-			ntfs_error(vi->i_sb, "Failed to lookup attribute in "
-					"inode 0x%lx (error code %d).%s",
-					vi->i_ino, err, te);
-		goto old_bad_out;
-	}
-	m = ctx->mrec;
-	a = ctx->attr;
-	/*
-	 * The i_size of the vfs inode is the new size for the attribute value.
-	 */
-	new_size = i_size_read(vi);
-	/* The current size of the attribute value is the old size. */
-	old_size = ntfs_attr_size(a);
-	/* Calculate the new allocated size. */
-	if (NInoNonResident(ni))
-		new_alloc_size = (new_size + vol->cluster_size - 1) &
-				~(s64)vol->cluster_size_mask;
-	else
-		new_alloc_size = (new_size + 7) & ~7;
-	/* The current allocated size is the old allocated size. */
-	read_lock_irqsave(&ni->size_lock, flags);
-	old_alloc_size = ni->allocated_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	/*
-	 * The change in the file size.  This will be 0 if no change, >0 if the
-	 * size is growing, and <0 if the size is shrinking.
-	 */
-	size_change = -1;
-	if (new_size - old_size >= 0) {
-		size_change = 1;
-		if (new_size == old_size)
-			size_change = 0;
-	}
-	/* As above for the allocated size. */
-	alloc_change = -1;
-	if (new_alloc_size - old_alloc_size >= 0) {
-		alloc_change = 1;
-		if (new_alloc_size == old_alloc_size)
-			alloc_change = 0;
-	}
-	/*
-	 * If neither the size nor the allocation are being changed there is
-	 * nothing to do.
-	 */
-	if (!size_change && !alloc_change)
-		goto unm_done;
-	/* If the size is changing, check if new size is allowed in $AttrDef. */
-	if (size_change) {
-		err = ntfs_attr_size_bounds_check(vol, ni->type, new_size);
-		if (unlikely(err)) {
-			if (err == -ERANGE) {
-				ntfs_error(vol->sb, "Truncate would cause the "
-						"inode 0x%lx to %simum size "
-						"for its attribute type "
-						"(0x%x).  Aborting truncate.",
-						vi->i_ino,
-						new_size > old_size ? "exceed "
-						"the max" : "go under the min",
-						le32_to_cpu(ni->type));
-				err = -EFBIG;
-			} else {
-				ntfs_error(vol->sb, "Inode 0x%lx has unknown "
-						"attribute type 0x%x.  "
-						"Aborting truncate.",
-						vi->i_ino,
-						le32_to_cpu(ni->type));
-				err = -EIO;
-			}
-			/* Reset the vfs inode size to the old size. */
-			i_size_write(vi, old_size);
-			goto err_out;
-		}
-	}
-	if (NInoCompressed(ni) || NInoEncrypted(ni)) {
-		ntfs_warning(vi->i_sb, "Changes in inode size are not "
-				"supported yet for %s files, ignoring.",
-				NInoCompressed(ni) ? "compressed" :
-				"encrypted");
-		err = -EOPNOTSUPP;
-		goto bad_out;
-	}
-	if (a->non_resident)
-		goto do_non_resident_truncate;
-	BUG_ON(NInoNonResident(ni));
-	/* Resize the attribute record to best fit the new attribute size. */
-	if (new_size < vol->mft_record_size &&
-			!ntfs_resident_attr_value_resize(m, a, new_size)) {
-		/* The resize succeeded! */
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
-		mark_mft_record_dirty(ctx->ntfs_ino);
-		write_lock_irqsave(&ni->size_lock, flags);
-		/* Update the sizes in the ntfs inode and all is done. */
-		ni->allocated_size = le32_to_cpu(a->length) -
-				le16_to_cpu(a->data.resident.value_offset);
-		/*
-		 * Note ntfs_resident_attr_value_resize() has already done any
-		 * necessary data clearing in the attribute record.  When the
-		 * file is being shrunk vmtruncate() will already have cleared
-		 * the top part of the last partial page, i.e. since this is
-		 * the resident case this is the page with index 0.  However,
-		 * when the file is being expanded, the page cache page data
-		 * between the old data_size, i.e. old_size, and the new_size
-		 * has not been zeroed.  Fortunately, we do not need to zero it
-		 * either since on one hand it will either already be zero due
-		 * to both read_folio and writepage clearing partial page data
-		 * beyond i_size in which case there is nothing to do or in the
-		 * case of the file being mmap()ped at the same time, POSIX
-		 * specifies that the behaviour is unspecified thus we do not
-		 * have to do anything.  This means that in our implementation
-		 * in the rare case that the file is mmap()ped and a write
-		 * occurred into the mmap()ped region just beyond the file size
-		 * and writepage has not yet been called to write out the page
-		 * (which would clear the area beyond the file size) and we now
-		 * extend the file size to incorporate this dirty region
-		 * outside the file size, a write of the page would result in
-		 * this data being written to disk instead of being cleared.
-		 * Given both POSIX and the Linux mmap(2) man page specify that
-		 * this corner case is undefined, we choose to leave it like
-		 * that as this is much simpler for us as we cannot lock the
-		 * relevant page now since we are holding too many ntfs locks
-		 * which would result in a lock reversal deadlock.
-		 */
-		ni->initialized_size = new_size;
-		write_unlock_irqrestore(&ni->size_lock, flags);
-		goto unm_done;
-	}
-	/* If the above resize failed, this must be an attribute extension. */
-	BUG_ON(size_change < 0);
-	/*
-	 * We have to drop all the locks so we can call
-	 * ntfs_attr_make_non_resident().  This could be optimised by try-
-	 * locking the first page cache page and only if that fails dropping
-	 * the locks, locking the page, and redoing all the locking and
-	 * lookups.  While this would be a huge optimisation, it is not worth
-	 * it as this is definitely a slow code path as it only ever can happen
-	 * once for any given file.
-	 */
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-	up_write(&ni->runlist.lock);
-	/*
-	 * Not enough space in the mft record, try to make the attribute
-	 * non-resident and if successful restart the truncation process.
-	 */
-	err = ntfs_attr_make_non_resident(ni, old_size);
-	if (likely(!err))
-		goto retry_truncate;
-	/*
-	 * Could not make non-resident.  If this is due to this not being
-	 * permitted for this attribute type or there not being enough space,
-	 * try to make other attributes non-resident.  Otherwise fail.
-	 */
-	if (unlikely(err != -EPERM && err != -ENOSPC)) {
-		ntfs_error(vol->sb, "Cannot truncate inode 0x%lx, attribute "
-				"type 0x%x, because the conversion from "
-				"resident to non-resident attribute failed "
-				"with error code %i.", vi->i_ino,
-				(unsigned)le32_to_cpu(ni->type), err);
-		if (err != -ENOMEM)
-			err = -EIO;
-		goto conv_err_out;
-	}
-	/* TODO: Not implemented from here, abort. */
-	if (err == -ENOSPC)
-		ntfs_error(vol->sb, "Not enough space in the mft record/on "
-				"disk for the non-resident attribute value.  "
-				"This case is not implemented yet.");
-	else /* if (err == -EPERM) */
-		ntfs_error(vol->sb, "This attribute type may not be "
-				"non-resident.  This case is not implemented "
-				"yet.");
-	err = -EOPNOTSUPP;
-	goto conv_err_out;
-#if 0
-	// TODO: Attempt to make other attributes non-resident.
-	if (!err)
-		goto do_resident_extend;
-	/*
-	 * Both the attribute list attribute and the standard information
-	 * attribute must remain in the base inode.  Thus, if this is one of
-	 * these attributes, we have to try to move other attributes out into
-	 * extent mft records instead.
-	 */
-	if (ni->type == AT_ATTRIBUTE_LIST ||
-			ni->type == AT_STANDARD_INFORMATION) {
-		// TODO: Attempt to move other attributes into extent mft
-		// records.
-		err = -EOPNOTSUPP;
-		if (!err)
-			goto do_resident_extend;
-		goto err_out;
-	}
-	// TODO: Attempt to move this attribute to an extent mft record, but
-	// only if it is not already the only attribute in an mft record in
-	// which case there would be nothing to gain.
-	err = -EOPNOTSUPP;
-	if (!err)
-		goto do_resident_extend;
-	/* There is nothing we can do to make enough space. )-: */
-	goto err_out;
-#endif
-do_non_resident_truncate:
-	BUG_ON(!NInoNonResident(ni));
-	if (alloc_change < 0) {
-		highest_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn);
-		if (highest_vcn > 0 &&
-				old_alloc_size >> vol->cluster_size_bits >
-				highest_vcn + 1) {
-			/*
-			 * This attribute has multiple extents.  Not yet
-			 * supported.
-			 */
-			ntfs_error(vol->sb, "Cannot truncate inode 0x%lx, "
-					"attribute type 0x%x, because the "
-					"attribute is highly fragmented (it "
-					"consists of multiple extents) and "
-					"this case is not implemented yet.",
-					vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type));
-			err = -EOPNOTSUPP;
-			goto bad_out;
-		}
-	}
-	/*
-	 * If the size is shrinking, need to reduce the initialized_size and
-	 * the data_size before reducing the allocation.
-	 */
-	if (size_change < 0) {
-		/*
-		 * Make the valid size smaller (i_size is already up-to-date).
-		 */
-		write_lock_irqsave(&ni->size_lock, flags);
-		if (new_size < ni->initialized_size) {
-			ni->initialized_size = new_size;
-			a->data.non_resident.initialized_size =
-					cpu_to_sle64(new_size);
-		}
-		a->data.non_resident.data_size = cpu_to_sle64(new_size);
-		write_unlock_irqrestore(&ni->size_lock, flags);
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
-		mark_mft_record_dirty(ctx->ntfs_ino);
-		/* If the allocated size is not changing, we are done. */
-		if (!alloc_change)
-			goto unm_done;
-		/*
-		 * If the size is shrinking it makes no sense for the
-		 * allocation to be growing.
-		 */
-		BUG_ON(alloc_change > 0);
-	} else /* if (size_change >= 0) */ {
-		/*
-		 * The file size is growing or staying the same but the
-		 * allocation can be shrinking, growing or staying the same.
-		 */
-		if (alloc_change > 0) {
-			/*
-			 * We need to extend the allocation and possibly update
-			 * the data size.  If we are updating the data size,
-			 * since we are not touching the initialized_size we do
-			 * not need to worry about the actual data on disk.
-			 * And as far as the page cache is concerned, there
-			 * will be no pages beyond the old data size and any
-			 * partial region in the last page between the old and
-			 * new data size (or the end of the page if the new
-			 * data size is outside the page) does not need to be
-			 * modified as explained above for the resident
-			 * attribute truncate case.  To do this, we simply drop
-			 * the locks we hold and leave all the work to our
-			 * friendly helper ntfs_attr_extend_allocation().
-			 */
-			ntfs_attr_put_search_ctx(ctx);
-			unmap_mft_record(base_ni);
-			up_write(&ni->runlist.lock);
-			err = ntfs_attr_extend_allocation(ni, new_size,
-					size_change > 0 ? new_size : -1, -1);
-			/*
-			 * ntfs_attr_extend_allocation() will have done error
-			 * output already.
-			 */
-			goto done;
-		}
-		if (!alloc_change)
-			goto alloc_done;
-	}
-	/* alloc_change < 0 */
-	/* Free the clusters. */
-	nr_freed = ntfs_cluster_free(ni, new_alloc_size >>
-			vol->cluster_size_bits, -1, ctx);
-	m = ctx->mrec;
-	a = ctx->attr;
-	if (unlikely(nr_freed < 0)) {
-		ntfs_error(vol->sb, "Failed to release cluster(s) (error code "
-				"%lli).  Unmount and run chkdsk to recover "
-				"the lost cluster(s).", (long long)nr_freed);
-		NVolSetErrors(vol);
-		nr_freed = 0;
-	}
-	/* Truncate the runlist. */
-	err = ntfs_rl_truncate_nolock(vol, &ni->runlist,
-			new_alloc_size >> vol->cluster_size_bits);
-	/*
-	 * If the runlist truncation failed and/or the search context is no
-	 * longer valid, we cannot resize the attribute record or build the
-	 * mapping pairs array thus we mark the inode bad so that no access to
-	 * the freed clusters can happen.
-	 */
-	if (unlikely(err || IS_ERR(m))) {
-		ntfs_error(vol->sb, "Failed to %s (error code %li).%s",
-				IS_ERR(m) ?
-				"restore attribute search context" :
-				"truncate attribute runlist",
-				IS_ERR(m) ? PTR_ERR(m) : err, es);
-		err = -EIO;
-		goto bad_out;
-	}
-	/* Get the size for the shrunk mapping pairs array for the runlist. */
-	mp_size = ntfs_get_size_for_mapping_pairs(vol, ni->runlist.rl, 0, -1);
-	if (unlikely(mp_size <= 0)) {
-		ntfs_error(vol->sb, "Cannot shrink allocation of inode 0x%lx, "
-				"attribute type 0x%x, because determining the "
-				"size for the mapping pairs failed with error "
-				"code %i.%s", vi->i_ino,
-				(unsigned)le32_to_cpu(ni->type), mp_size, es);
-		err = -EIO;
-		goto bad_out;
-	}
-	/*
-	 * Shrink the attribute record for the new mapping pairs array.  Note,
-	 * this cannot fail since we are making the attribute smaller thus by
-	 * definition there is enough space to do so.
-	 */
-	err = ntfs_attr_record_resize(m, a, mp_size +
-			le16_to_cpu(a->data.non_resident.mapping_pairs_offset));
-	BUG_ON(err);
-	/*
-	 * Generate the mapping pairs array directly into the attribute record.
-	 */
-	err = ntfs_mapping_pairs_build(vol, (u8*)a +
-			le16_to_cpu(a->data.non_resident.mapping_pairs_offset),
-			mp_size, ni->runlist.rl, 0, -1, NULL);
-	if (unlikely(err)) {
-		ntfs_error(vol->sb, "Cannot shrink allocation of inode 0x%lx, "
-				"attribute type 0x%x, because building the "
-				"mapping pairs failed with error code %i.%s",
-				vi->i_ino, (unsigned)le32_to_cpu(ni->type),
-				err, es);
-		err = -EIO;
-		goto bad_out;
-	}
-	/* Update the allocated/compressed size as well as the highest vcn. */
-	a->data.non_resident.highest_vcn = cpu_to_sle64((new_alloc_size >>
-			vol->cluster_size_bits) - 1);
-	write_lock_irqsave(&ni->size_lock, flags);
-	ni->allocated_size = new_alloc_size;
-	a->data.non_resident.allocated_size = cpu_to_sle64(new_alloc_size);
-	if (NInoSparse(ni) || NInoCompressed(ni)) {
-		if (nr_freed) {
-			ni->itype.compressed.size -= nr_freed <<
-					vol->cluster_size_bits;
-			BUG_ON(ni->itype.compressed.size < 0);
-			a->data.non_resident.compressed_size = cpu_to_sle64(
-					ni->itype.compressed.size);
-			vi->i_blocks = ni->itype.compressed.size >> 9;
-		}
-	} else
-		vi->i_blocks = new_alloc_size >> 9;
-	write_unlock_irqrestore(&ni->size_lock, flags);
-	/*
-	 * We have shrunk the allocation.  If this is a shrinking truncate we
-	 * have already dealt with the initialized_size and the data_size above
-	 * and we are done.  If the truncate is only changing the allocation
-	 * and not the data_size, we are also done.  If this is an extending
-	 * truncate, need to extend the data_size now which is ensured by the
-	 * fact that @size_change is positive.
-	 */
-alloc_done:
-	/*
-	 * If the size is growing, need to update it now.  If it is shrinking,
-	 * we have already updated it above (before the allocation change).
-	 */
-	if (size_change > 0)
-		a->data.non_resident.data_size = cpu_to_sle64(new_size);
-	/* Ensure the modified mft record is written out. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-unm_done:
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-	up_write(&ni->runlist.lock);
-done:
-	/* Update the mtime and ctime on the base inode. */
-	/* normally ->truncate shouldn't update ctime or mtime,
-	 * but ntfs did before so it got a copy & paste version
-	 * of file_update_time.  one day someone should fix this
-	 * for real.
-	 */
-	if (!IS_NOCMTIME(VFS_I(base_ni)) && !IS_RDONLY(VFS_I(base_ni))) {
-		struct timespec64 now = current_time(VFS_I(base_ni));
-		struct timespec64 ctime = inode_get_ctime(VFS_I(base_ni));
-		struct timespec64 mtime = inode_get_mtime(VFS_I(base_ni));
-		int sync_it = 0;
-
-		if (!timespec64_equal(&mtime, &now) ||
-		    !timespec64_equal(&ctime, &now))
-			sync_it = 1;
-		inode_set_ctime_to_ts(VFS_I(base_ni), now);
-		inode_set_mtime_to_ts(VFS_I(base_ni), now);
-
-		if (sync_it)
-			mark_inode_dirty_sync(VFS_I(base_ni));
-	}
-
-	if (likely(!err)) {
-		NInoClearTruncateFailed(ni);
-		ntfs_debug("Done.");
-	}
-	return err;
-old_bad_out:
-	old_size = -1;
-bad_out:
-	if (err != -ENOMEM && err != -EOPNOTSUPP)
-		NVolSetErrors(vol);
-	if (err != -EOPNOTSUPP)
-		NInoSetTruncateFailed(ni);
-	else if (old_size >= 0)
-		i_size_write(vi, old_size);
-err_out:
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(base_ni);
-	up_write(&ni->runlist.lock);
-out:
-	ntfs_debug("Failed.  Returning error code %i.", err);
-	return err;
-conv_err_out:
-	if (err != -ENOMEM && err != -EOPNOTSUPP)
-		NVolSetErrors(vol);
-	if (err != -EOPNOTSUPP)
-		NInoSetTruncateFailed(ni);
-	else
-		i_size_write(vi, old_size);
-	goto out;
-}
-
-/**
- * ntfs_truncate_vfs - wrapper for ntfs_truncate() that has no return value
- * @vi:		inode for which the i_size was changed
- *
- * Wrapper for ntfs_truncate() that has no return value.
- *
- * See ntfs_truncate() description above for details.
- */
-#ifdef NTFS_RW
-void ntfs_truncate_vfs(struct inode *vi) {
-	ntfs_truncate(vi);
-}
-#endif
-
-/**
- * ntfs_setattr - called from notify_change() when an attribute is being changed
- * @idmap:	idmap of the mount the inode was found from
- * @dentry:	dentry whose attributes to change
- * @attr:	structure describing the attributes and the changes
- *
- * We have to trap VFS attempts to truncate the file described by @dentry as
- * soon as possible, because we do not implement changes in i_size yet.  So we
- * abort all i_size changes here.
- *
- * We also abort all changes of user, group, and mode as we do not implement
- * the NTFS ACLs yet.
- *
- * Called with ->i_mutex held.
- */
-int ntfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
-		 struct iattr *attr)
-{
-	struct inode *vi = d_inode(dentry);
-	int err;
-	unsigned int ia_valid = attr->ia_valid;
-
-	err = setattr_prepare(&nop_mnt_idmap, dentry, attr);
-	if (err)
-		goto out;
-	/* We do not support NTFS ACLs yet. */
-	if (ia_valid & (ATTR_UID | ATTR_GID | ATTR_MODE)) {
-		ntfs_warning(vi->i_sb, "Changes in user/group/mode are not "
-				"supported yet, ignoring.");
-		err = -EOPNOTSUPP;
-		goto out;
-	}
-	if (ia_valid & ATTR_SIZE) {
-		if (attr->ia_size != i_size_read(vi)) {
-			ntfs_inode *ni = NTFS_I(vi);
-			/*
-			 * FIXME: For now we do not support resizing of
-			 * compressed or encrypted files yet.
-			 */
-			if (NInoCompressed(ni) || NInoEncrypted(ni)) {
-				ntfs_warning(vi->i_sb, "Changes in inode size "
-						"are not supported yet for "
-						"%s files, ignoring.",
-						NInoCompressed(ni) ?
-						"compressed" : "encrypted");
-				err = -EOPNOTSUPP;
-			} else {
-				truncate_setsize(vi, attr->ia_size);
-				ntfs_truncate_vfs(vi);
-			}
-			if (err || ia_valid == ATTR_SIZE)
-				goto out;
-		} else {
-			/*
-			 * We skipped the truncate but must still update
-			 * timestamps.
-			 */
-			ia_valid |= ATTR_MTIME | ATTR_CTIME;
-		}
-	}
-	if (ia_valid & ATTR_ATIME)
-		inode_set_atime_to_ts(vi, attr->ia_atime);
-	if (ia_valid & ATTR_MTIME)
-		inode_set_mtime_to_ts(vi, attr->ia_mtime);
-	if (ia_valid & ATTR_CTIME)
-		inode_set_ctime_to_ts(vi, attr->ia_ctime);
-	mark_inode_dirty(vi);
-out:
-	return err;
-}
-
-/**
- * __ntfs_write_inode - write out a dirty inode
- * @vi:		inode to write out
- * @sync:	if true, write out synchronously
- *
- * Write out a dirty inode to disk including any extent inodes if present.
- *
- * If @sync is true, commit the inode to disk and wait for io completion.  This
- * is done using write_mft_record().
- *
- * If @sync is false, just schedule the write to happen but do not wait for i/o
- * completion.  In 2.6 kernels, scheduling usually happens just by virtue of
- * marking the page (and in this case mft record) dirty but we do not implement
- * this yet as write_mft_record() largely ignores the @sync parameter and
- * always performs synchronous writes.
- *
- * Return 0 on success and -errno on error.
- */
-int __ntfs_write_inode(struct inode *vi, int sync)
-{
-	sle64 nt;
-	ntfs_inode *ni = NTFS_I(vi);
-	ntfs_attr_search_ctx *ctx;
-	MFT_RECORD *m;
-	STANDARD_INFORMATION *si;
-	int err = 0;
-	bool modified = false;
-
-	ntfs_debug("Entering for %sinode 0x%lx.", NInoAttr(ni) ? "attr " : "",
-			vi->i_ino);
-	/*
-	 * Dirty attribute inodes are written via their real inodes so just
-	 * clean them here.  Access time updates are taken care off when the
-	 * real inode is written.
-	 */
-	if (NInoAttr(ni)) {
-		NInoClearDirty(ni);
-		ntfs_debug("Done.");
-		return 0;
-	}
-	/* Map, pin, and lock the mft record belonging to the inode. */
-	m = map_mft_record(ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		goto err_out;
-	}
-	/* Update the access times in the standard information attribute. */
-	ctx = ntfs_attr_get_search_ctx(ni, m);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto unm_err_out;
-	}
-	err = ntfs_attr_lookup(AT_STANDARD_INFORMATION, NULL, 0,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err)) {
-		ntfs_attr_put_search_ctx(ctx);
-		goto unm_err_out;
-	}
-	si = (STANDARD_INFORMATION*)((u8*)ctx->attr +
-			le16_to_cpu(ctx->attr->data.resident.value_offset));
-	/* Update the access times if they have changed. */
-	nt = utc2ntfs(inode_get_mtime(vi));
-	if (si->last_data_change_time != nt) {
-		ntfs_debug("Updating mtime for inode 0x%lx: old = 0x%llx, "
-				"new = 0x%llx", vi->i_ino, (long long)
-				sle64_to_cpu(si->last_data_change_time),
-				(long long)sle64_to_cpu(nt));
-		si->last_data_change_time = nt;
-		modified = true;
-	}
-	nt = utc2ntfs(inode_get_ctime(vi));
-	if (si->last_mft_change_time != nt) {
-		ntfs_debug("Updating ctime for inode 0x%lx: old = 0x%llx, "
-				"new = 0x%llx", vi->i_ino, (long long)
-				sle64_to_cpu(si->last_mft_change_time),
-				(long long)sle64_to_cpu(nt));
-		si->last_mft_change_time = nt;
-		modified = true;
-	}
-	nt = utc2ntfs(inode_get_atime(vi));
-	if (si->last_access_time != nt) {
-		ntfs_debug("Updating atime for inode 0x%lx: old = 0x%llx, "
-				"new = 0x%llx", vi->i_ino,
-				(long long)sle64_to_cpu(si->last_access_time),
-				(long long)sle64_to_cpu(nt));
-		si->last_access_time = nt;
-		modified = true;
-	}
-	/*
-	 * If we just modified the standard information attribute we need to
-	 * mark the mft record it is in dirty.  We do this manually so that
-	 * mark_inode_dirty() is not called which would redirty the inode and
-	 * hence result in an infinite loop of trying to write the inode.
-	 * There is no need to mark the base inode nor the base mft record
-	 * dirty, since we are going to write this mft record below in any case
-	 * and the base mft record may actually not have been modified so it
-	 * might not need to be written out.
-	 * NOTE: It is not a problem when the inode for $MFT itself is being
-	 * written out as mark_ntfs_record_dirty() will only set I_DIRTY_PAGES
-	 * on the $MFT inode and hence __ntfs_write_inode() will not be
-	 * re-invoked because of it which in turn is ok since the dirtied mft
-	 * record will be cleaned and written out to disk below, i.e. before
-	 * this function returns.
-	 */
-	if (modified) {
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
-		if (!NInoTestSetDirty(ctx->ntfs_ino))
-			mark_ntfs_record_dirty(ctx->ntfs_ino->page,
-					ctx->ntfs_ino->page_ofs);
-	}
-	ntfs_attr_put_search_ctx(ctx);
-	/* Now the access times are updated, write the base mft record. */
-	if (NInoDirty(ni))
-		err = write_mft_record(ni, m, sync);
-	/* Write all attached extent mft records. */
-	mutex_lock(&ni->extent_lock);
-	if (ni->nr_extents > 0) {
-		ntfs_inode **extent_nis = ni->ext.extent_ntfs_inos;
-		int i;
-
-		ntfs_debug("Writing %i extent inodes.", ni->nr_extents);
-		for (i = 0; i < ni->nr_extents; i++) {
-			ntfs_inode *tni = extent_nis[i];
-
-			if (NInoDirty(tni)) {
-				MFT_RECORD *tm = map_mft_record(tni);
-				int ret;
-
-				if (IS_ERR(tm)) {
-					if (!err || err == -ENOMEM)
-						err = PTR_ERR(tm);
-					continue;
-				}
-				ret = write_mft_record(tni, tm, sync);
-				unmap_mft_record(tni);
-				if (unlikely(ret)) {
-					if (!err || err == -ENOMEM)
-						err = ret;
-				}
-			}
-		}
-	}
-	mutex_unlock(&ni->extent_lock);
-	unmap_mft_record(ni);
-	if (unlikely(err))
-		goto err_out;
-	ntfs_debug("Done.");
-	return 0;
-unm_err_out:
-	unmap_mft_record(ni);
-err_out:
-	if (err == -ENOMEM) {
-		ntfs_warning(vi->i_sb, "Not enough memory to write inode.  "
-				"Marking the inode dirty again, so the VFS "
-				"retries later.");
-		mark_inode_dirty(vi);
-	} else {
-		ntfs_error(vi->i_sb, "Failed (error %i):  Run chkdsk.", -err);
-		NVolSetErrors(ni->vol);
-	}
-	return err;
-}
-
-#endif /* NTFS_RW */
diff --git a/fs/ntfs/inode.h b/fs/ntfs/inode.h
deleted file mode 100644
index 147ef4ddb691..000000000000
--- a/fs/ntfs/inode.h
+++ /dev/null
@@ -1,310 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * inode.h - Defines for inode structures NTFS Linux kernel driver. Part of
- *	     the Linux-NTFS project.
- *
- * Copyright (c) 2001-2007 Anton Altaparmakov
- * Copyright (c) 2002 Richard Russon
- */
-
-#ifndef _LINUX_NTFS_INODE_H
-#define _LINUX_NTFS_INODE_H
-
-#include <linux/atomic.h>
-
-#include <linux/fs.h>
-#include <linux/list.h>
-#include <linux/mm.h>
-#include <linux/mutex.h>
-#include <linux/seq_file.h>
-
-#include "layout.h"
-#include "volume.h"
-#include "types.h"
-#include "runlist.h"
-#include "debug.h"
-
-typedef struct _ntfs_inode ntfs_inode;
-
-/*
- * The NTFS in-memory inode structure. It is just used as an extension to the
- * fields already provided in the VFS inode.
- */
-struct _ntfs_inode {
-	rwlock_t size_lock;	/* Lock serializing access to inode sizes. */
-	s64 initialized_size;	/* Copy from the attribute record. */
-	s64 allocated_size;	/* Copy from the attribute record. */
-	unsigned long state;	/* NTFS specific flags describing this inode.
-				   See ntfs_inode_state_bits below. */
-	unsigned long mft_no;	/* Number of the mft record / inode. */
-	u16 seq_no;		/* Sequence number of the mft record. */
-	atomic_t count;		/* Inode reference count for book keeping. */
-	ntfs_volume *vol;	/* Pointer to the ntfs volume of this inode. */
-	/*
-	 * If NInoAttr() is true, the below fields describe the attribute which
-	 * this fake inode belongs to. The actual inode of this attribute is
-	 * pointed to by base_ntfs_ino and nr_extents is always set to -1 (see
-	 * below). For real inodes, we also set the type (AT_DATA for files and
-	 * AT_INDEX_ALLOCATION for directories), with the name = NULL and
-	 * name_len = 0 for files and name = I30 (global constant) and
-	 * name_len = 4 for directories.
-	 */
-	ATTR_TYPE type;	/* Attribute type of this fake inode. */
-	ntfschar *name;		/* Attribute name of this fake inode. */
-	u32 name_len;		/* Attribute name length of this fake inode. */
-	runlist runlist;	/* If state has the NI_NonResident bit set,
-				   the runlist of the unnamed data attribute
-				   (if a file) or of the index allocation
-				   attribute (directory) or of the attribute
-				   described by the fake inode (if NInoAttr()).
-				   If runlist.rl is NULL, the runlist has not
-				   been read in yet or has been unmapped. If
-				   NI_NonResident is clear, the attribute is
-				   resident (file and fake inode) or there is
-				   no $I30 index allocation attribute
-				   (small directory). In the latter case
-				   runlist.rl is always NULL.*/
-	/*
-	 * The following fields are only valid for real inodes and extent
-	 * inodes.
-	 */
-	struct mutex mrec_lock;	/* Lock for serializing access to the
-				   mft record belonging to this inode. */
-	struct page *page;	/* The page containing the mft record of the
-				   inode. This should only be touched by the
-				   (un)map_mft_record*() functions. */
-	int page_ofs;		/* Offset into the page at which the mft record
-				   begins. This should only be touched by the
-				   (un)map_mft_record*() functions. */
-	/*
-	 * Attribute list support (only for use by the attribute lookup
-	 * functions). Setup during read_inode for all inodes with attribute
-	 * lists. Only valid if NI_AttrList is set in state, and attr_list_rl is
-	 * further only valid if NI_AttrListNonResident is set.
-	 */
-	u32 attr_list_size;	/* Length of attribute list value in bytes. */
-	u8 *attr_list;		/* Attribute list value itself. */
-	runlist attr_list_rl;	/* Run list for the attribute list value. */
-	union {
-		struct { /* It is a directory, $MFT, or an index inode. */
-			u32 block_size;		/* Size of an index block. */
-			u32 vcn_size;		/* Size of a vcn in this
-						   index. */
-			COLLATION_RULE collation_rule; /* The collation rule
-						   for the index. */
-			u8 block_size_bits; 	/* Log2 of the above. */
-			u8 vcn_size_bits;	/* Log2 of the above. */
-		} index;
-		struct { /* It is a compressed/sparse file/attribute inode. */
-			s64 size;		/* Copy of compressed_size from
-						   $DATA. */
-			u32 block_size;		/* Size of a compression block
-						   (cb). */
-			u8 block_size_bits;	/* Log2 of the size of a cb. */
-			u8 block_clusters;	/* Number of clusters per cb. */
-		} compressed;
-	} itype;
-	struct mutex extent_lock;	/* Lock for accessing/modifying the
-					   below . */
-	s32 nr_extents;	/* For a base mft record, the number of attached extent
-			   inodes (0 if none), for extent records and for fake
-			   inodes describing an attribute this is -1. */
-	union {		/* This union is only used if nr_extents != 0. */
-		ntfs_inode **extent_ntfs_inos;	/* For nr_extents > 0, array of
-						   the ntfs inodes of the extent
-						   mft records belonging to
-						   this base inode which have
-						   been loaded. */
-		ntfs_inode *base_ntfs_ino;	/* For nr_extents == -1, the
-						   ntfs inode of the base mft
-						   record. For fake inodes, the
-						   real (base) inode to which
-						   the attribute belongs. */
-	} ext;
-};
-
-/*
- * Defined bits for the state field in the ntfs_inode structure.
- * (f) = files only, (d) = directories only, (a) = attributes/fake inodes only
- */
-typedef enum {
-	NI_Dirty,		/* 1: Mft record needs to be written to disk. */
-	NI_AttrList,		/* 1: Mft record contains an attribute list. */
-	NI_AttrListNonResident,	/* 1: Attribute list is non-resident. Implies
-				      NI_AttrList is set. */
-
-	NI_Attr,		/* 1: Fake inode for attribute i/o.
-				   0: Real inode or extent inode. */
-
-	NI_MstProtected,	/* 1: Attribute is protected by MST fixups.
-				   0: Attribute is not protected by fixups. */
-	NI_NonResident,		/* 1: Unnamed data attr is non-resident (f).
-				   1: Attribute is non-resident (a). */
-	NI_IndexAllocPresent = NI_NonResident,	/* 1: $I30 index alloc attr is
-						   present (d). */
-	NI_Compressed,		/* 1: Unnamed data attr is compressed (f).
-				   1: Create compressed files by default (d).
-				   1: Attribute is compressed (a). */
-	NI_Encrypted,		/* 1: Unnamed data attr is encrypted (f).
-				   1: Create encrypted files by default (d).
-				   1: Attribute is encrypted (a). */
-	NI_Sparse,		/* 1: Unnamed data attr is sparse (f).
-				   1: Create sparse files by default (d).
-				   1: Attribute is sparse (a). */
-	NI_SparseDisabled,	/* 1: May not create sparse regions. */
-	NI_TruncateFailed,	/* 1: Last ntfs_truncate() call failed. */
-} ntfs_inode_state_bits;
-
-/*
- * NOTE: We should be adding dirty mft records to a list somewhere and they
- * should be independent of the (ntfs/vfs) inode structure so that an inode can
- * be removed but the record can be left dirty for syncing later.
- */
-
-/*
- * Macro tricks to expand the NInoFoo(), NInoSetFoo(), and NInoClearFoo()
- * functions.
- */
-#define NINO_FNS(flag)					\
-static inline int NIno##flag(ntfs_inode *ni)		\
-{							\
-	return test_bit(NI_##flag, &(ni)->state);	\
-}							\
-static inline void NInoSet##flag(ntfs_inode *ni)	\
-{							\
-	set_bit(NI_##flag, &(ni)->state);		\
-}							\
-static inline void NInoClear##flag(ntfs_inode *ni)	\
-{							\
-	clear_bit(NI_##flag, &(ni)->state);		\
-}
-
-/*
- * As above for NInoTestSetFoo() and NInoTestClearFoo().
- */
-#define TAS_NINO_FNS(flag)					\
-static inline int NInoTestSet##flag(ntfs_inode *ni)		\
-{								\
-	return test_and_set_bit(NI_##flag, &(ni)->state);	\
-}								\
-static inline int NInoTestClear##flag(ntfs_inode *ni)		\
-{								\
-	return test_and_clear_bit(NI_##flag, &(ni)->state);	\
-}
-
-/* Emit the ntfs inode bitops functions. */
-NINO_FNS(Dirty)
-TAS_NINO_FNS(Dirty)
-NINO_FNS(AttrList)
-NINO_FNS(AttrListNonResident)
-NINO_FNS(Attr)
-NINO_FNS(MstProtected)
-NINO_FNS(NonResident)
-NINO_FNS(IndexAllocPresent)
-NINO_FNS(Compressed)
-NINO_FNS(Encrypted)
-NINO_FNS(Sparse)
-NINO_FNS(SparseDisabled)
-NINO_FNS(TruncateFailed)
-
-/*
- * The full structure containing a ntfs_inode and a vfs struct inode. Used for
- * all real and fake inodes but not for extent inodes which lack the vfs struct
- * inode.
- */
-typedef struct {
-	ntfs_inode ntfs_inode;
-	struct inode vfs_inode;		/* The vfs inode structure. */
-} big_ntfs_inode;
-
-/**
- * NTFS_I - return the ntfs inode given a vfs inode
- * @inode:	VFS inode
- *
- * NTFS_I() returns the ntfs inode associated with the VFS @inode.
- */
-static inline ntfs_inode *NTFS_I(struct inode *inode)
-{
-	return (ntfs_inode *)container_of(inode, big_ntfs_inode, vfs_inode);
-}
-
-static inline struct inode *VFS_I(ntfs_inode *ni)
-{
-	return &((big_ntfs_inode *)ni)->vfs_inode;
-}
-
-/**
- * ntfs_attr - ntfs in memory attribute structure
- * @mft_no:	mft record number of the base mft record of this attribute
- * @name:	Unicode name of the attribute (NULL if unnamed)
- * @name_len:	length of @name in Unicode characters (0 if unnamed)
- * @type:	attribute type (see layout.h)
- *
- * This structure exists only to provide a small structure for the
- * ntfs_{attr_}iget()/ntfs_test_inode()/ntfs_init_locked_inode() mechanism.
- *
- * NOTE: Elements are ordered by size to make the structure as compact as
- * possible on all architectures.
- */
-typedef struct {
-	unsigned long mft_no;
-	ntfschar *name;
-	u32 name_len;
-	ATTR_TYPE type;
-} ntfs_attr;
-
-extern int ntfs_test_inode(struct inode *vi, void *data);
-
-extern struct inode *ntfs_iget(struct super_block *sb, unsigned long mft_no);
-extern struct inode *ntfs_attr_iget(struct inode *base_vi, ATTR_TYPE type,
-		ntfschar *name, u32 name_len);
-extern struct inode *ntfs_index_iget(struct inode *base_vi, ntfschar *name,
-		u32 name_len);
-
-extern struct inode *ntfs_alloc_big_inode(struct super_block *sb);
-extern void ntfs_free_big_inode(struct inode *inode);
-extern void ntfs_evict_big_inode(struct inode *vi);
-
-extern void __ntfs_init_inode(struct super_block *sb, ntfs_inode *ni);
-
-static inline void ntfs_init_big_inode(struct inode *vi)
-{
-	ntfs_inode *ni = NTFS_I(vi);
-
-	ntfs_debug("Entering.");
-	__ntfs_init_inode(vi->i_sb, ni);
-	ni->mft_no = vi->i_ino;
-}
-
-extern ntfs_inode *ntfs_new_extent_inode(struct super_block *sb,
-		unsigned long mft_no);
-extern void ntfs_clear_extent_inode(ntfs_inode *ni);
-
-extern int ntfs_read_inode_mount(struct inode *vi);
-
-extern int ntfs_show_options(struct seq_file *sf, struct dentry *root);
-
-#ifdef NTFS_RW
-
-extern int ntfs_truncate(struct inode *vi);
-extern void ntfs_truncate_vfs(struct inode *vi);
-
-extern int ntfs_setattr(struct mnt_idmap *idmap,
-			struct dentry *dentry, struct iattr *attr);
-
-extern int __ntfs_write_inode(struct inode *vi, int sync);
-
-static inline void ntfs_commit_inode(struct inode *vi)
-{
-	if (!is_bad_inode(vi))
-		__ntfs_write_inode(vi, 1);
-	return;
-}
-
-#else
-
-static inline void ntfs_truncate_vfs(struct inode *vi) {}
-
-#endif /* NTFS_RW */
-
-#endif /* _LINUX_NTFS_INODE_H */
diff --git a/fs/ntfs/layout.h b/fs/ntfs/layout.h
deleted file mode 100644
index 5d4bf7a3259f..000000000000
--- a/fs/ntfs/layout.h
+++ /dev/null
@@ -1,2421 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * layout.h - All NTFS associated on-disk structures. Part of the Linux-NTFS
- *	      project.
- *
- * Copyright (c) 2001-2005 Anton Altaparmakov
- * Copyright (c) 2002 Richard Russon
- */
-
-#ifndef _LINUX_NTFS_LAYOUT_H
-#define _LINUX_NTFS_LAYOUT_H
-
-#include <linux/types.h>
-#include <linux/bitops.h>
-#include <linux/list.h>
-#include <asm/byteorder.h>
-
-#include "types.h"
-
-/* The NTFS oem_id "NTFS    " */
-#define magicNTFS	cpu_to_le64(0x202020205346544eULL)
-
-/*
- * Location of bootsector on partition:
- *	The standard NTFS_BOOT_SECTOR is on sector 0 of the partition.
- *	On NT4 and above there is one backup copy of the boot sector to
- *	be found on the last sector of the partition (not normally accessible
- *	from within Windows as the bootsector contained number of sectors
- *	value is one less than the actual value!).
- *	On versions of NT 3.51 and earlier, the backup copy was located at
- *	number of sectors/2 (integer divide), i.e. in the middle of the volume.
- */
-
-/*
- * BIOS parameter block (bpb) structure.
- */
-typedef struct {
-	le16 bytes_per_sector;		/* Size of a sector in bytes. */
-	u8  sectors_per_cluster;	/* Size of a cluster in sectors. */
-	le16 reserved_sectors;		/* zero */
-	u8  fats;			/* zero */
-	le16 root_entries;		/* zero */
-	le16 sectors;			/* zero */
-	u8  media_type;			/* 0xf8 = hard disk */
-	le16 sectors_per_fat;		/* zero */
-	le16 sectors_per_track;		/* irrelevant */
-	le16 heads;			/* irrelevant */
-	le32 hidden_sectors;		/* zero */
-	le32 large_sectors;		/* zero */
-} __attribute__ ((__packed__)) BIOS_PARAMETER_BLOCK;
-
-/*
- * NTFS boot sector structure.
- */
-typedef struct {
-	u8  jump[3];			/* Irrelevant (jump to boot up code).*/
-	le64 oem_id;			/* Magic "NTFS    ". */
-	BIOS_PARAMETER_BLOCK bpb;	/* See BIOS_PARAMETER_BLOCK. */
-	u8  unused[4];			/* zero, NTFS diskedit.exe states that
-					   this is actually:
-						__u8 physical_drive;	// 0x80
-						__u8 current_head;	// zero
-						__u8 extended_boot_signature;
-									// 0x80
-						__u8 unused;		// zero
-					 */
-/*0x28*/sle64 number_of_sectors;	/* Number of sectors in volume. Gives
-					   maximum volume size of 2^63 sectors.
-					   Assuming standard sector size of 512
-					   bytes, the maximum byte size is
-					   approx. 4.7x10^21 bytes. (-; */
-	sle64 mft_lcn;			/* Cluster location of mft data. */
-	sle64 mftmirr_lcn;		/* Cluster location of copy of mft. */
-	s8  clusters_per_mft_record;	/* Mft record size in clusters. */
-	u8  reserved0[3];		/* zero */
-	s8  clusters_per_index_record;	/* Index block size in clusters. */
-	u8  reserved1[3];		/* zero */
-	le64 volume_serial_number;	/* Irrelevant (serial number). */
-	le32 checksum;			/* Boot sector checksum. */
-/*0x54*/u8  bootstrap[426];		/* Irrelevant (boot up code). */
-	le16 end_of_sector_marker;	/* End of bootsector magic. Always is
-					   0xaa55 in little endian. */
-/* sizeof() = 512 (0x200) bytes */
-} __attribute__ ((__packed__)) NTFS_BOOT_SECTOR;
-
-/*
- * Magic identifiers present at the beginning of all ntfs record containing
- * records (like mft records for example).
- */
-enum {
-	/* Found in $MFT/$DATA. */
-	magic_FILE = cpu_to_le32(0x454c4946), /* Mft entry. */
-	magic_INDX = cpu_to_le32(0x58444e49), /* Index buffer. */
-	magic_HOLE = cpu_to_le32(0x454c4f48), /* ? (NTFS 3.0+?) */
-
-	/* Found in $LogFile/$DATA. */
-	magic_RSTR = cpu_to_le32(0x52545352), /* Restart page. */
-	magic_RCRD = cpu_to_le32(0x44524352), /* Log record page. */
-
-	/* Found in $LogFile/$DATA.  (May be found in $MFT/$DATA, also?) */
-	magic_CHKD = cpu_to_le32(0x444b4843), /* Modified by chkdsk. */
-
-	/* Found in all ntfs record containing records. */
-	magic_BAAD = cpu_to_le32(0x44414142), /* Failed multi sector
-						       transfer was detected. */
-	/*
-	 * Found in $LogFile/$DATA when a page is full of 0xff bytes and is
-	 * thus not initialized.  Page must be initialized before using it.
-	 */
-	magic_empty = cpu_to_le32(0xffffffff) /* Record is empty. */
-};
-
-typedef le32 NTFS_RECORD_TYPE;
-
-/*
- * Generic magic comparison macros. Finally found a use for the ## preprocessor
- * operator! (-8
- */
-
-static inline bool __ntfs_is_magic(le32 x, NTFS_RECORD_TYPE r)
-{
-	return (x == r);
-}
-#define ntfs_is_magic(x, m)	__ntfs_is_magic(x, magic_##m)
-
-static inline bool __ntfs_is_magicp(le32 *p, NTFS_RECORD_TYPE r)
-{
-	return (*p == r);
-}
-#define ntfs_is_magicp(p, m)	__ntfs_is_magicp(p, magic_##m)
-
-/*
- * Specialised magic comparison macros for the NTFS_RECORD_TYPEs defined above.
- */
-#define ntfs_is_file_record(x)		( ntfs_is_magic (x, FILE) )
-#define ntfs_is_file_recordp(p)		( ntfs_is_magicp(p, FILE) )
-#define ntfs_is_mft_record(x)		( ntfs_is_file_record (x) )
-#define ntfs_is_mft_recordp(p)		( ntfs_is_file_recordp(p) )
-#define ntfs_is_indx_record(x)		( ntfs_is_magic (x, INDX) )
-#define ntfs_is_indx_recordp(p)		( ntfs_is_magicp(p, INDX) )
-#define ntfs_is_hole_record(x)		( ntfs_is_magic (x, HOLE) )
-#define ntfs_is_hole_recordp(p)		( ntfs_is_magicp(p, HOLE) )
-
-#define ntfs_is_rstr_record(x)		( ntfs_is_magic (x, RSTR) )
-#define ntfs_is_rstr_recordp(p)		( ntfs_is_magicp(p, RSTR) )
-#define ntfs_is_rcrd_record(x)		( ntfs_is_magic (x, RCRD) )
-#define ntfs_is_rcrd_recordp(p)		( ntfs_is_magicp(p, RCRD) )
-
-#define ntfs_is_chkd_record(x)		( ntfs_is_magic (x, CHKD) )
-#define ntfs_is_chkd_recordp(p)		( ntfs_is_magicp(p, CHKD) )
-
-#define ntfs_is_baad_record(x)		( ntfs_is_magic (x, BAAD) )
-#define ntfs_is_baad_recordp(p)		( ntfs_is_magicp(p, BAAD) )
-
-#define ntfs_is_empty_record(x)		( ntfs_is_magic (x, empty) )
-#define ntfs_is_empty_recordp(p)	( ntfs_is_magicp(p, empty) )
-
-/*
- * The Update Sequence Array (usa) is an array of the le16 values which belong
- * to the end of each sector protected by the update sequence record in which
- * this array is contained. Note that the first entry is the Update Sequence
- * Number (usn), a cyclic counter of how many times the protected record has
- * been written to disk. The values 0 and -1 (ie. 0xffff) are not used. All
- * last le16's of each sector have to be equal to the usn (during reading) or
- * are set to it (during writing). If they are not, an incomplete multi sector
- * transfer has occurred when the data was written.
- * The maximum size for the update sequence array is fixed to:
- *	maximum size = usa_ofs + (usa_count * 2) = 510 bytes
- * The 510 bytes comes from the fact that the last le16 in the array has to
- * (obviously) finish before the last le16 of the first 512-byte sector.
- * This formula can be used as a consistency check in that usa_ofs +
- * (usa_count * 2) has to be less than or equal to 510.
- */
-typedef struct {
-	NTFS_RECORD_TYPE magic;	/* A four-byte magic identifying the record
-				   type and/or status. */
-	le16 usa_ofs;		/* Offset to the Update Sequence Array (usa)
-				   from the start of the ntfs record. */
-	le16 usa_count;		/* Number of le16 sized entries in the usa
-				   including the Update Sequence Number (usn),
-				   thus the number of fixups is the usa_count
-				   minus 1. */
-} __attribute__ ((__packed__)) NTFS_RECORD;
-
-/*
- * System files mft record numbers. All these files are always marked as used
- * in the bitmap attribute of the mft; presumably in order to avoid accidental
- * allocation for random other mft records. Also, the sequence number for each
- * of the system files is always equal to their mft record number and it is
- * never modified.
- */
-typedef enum {
-	FILE_MFT       = 0,	/* Master file table (mft). Data attribute
-				   contains the entries and bitmap attribute
-				   records which ones are in use (bit==1). */
-	FILE_MFTMirr   = 1,	/* Mft mirror: copy of first four mft records
-				   in data attribute. If cluster size > 4kiB,
-				   copy of first N mft records, with
-					N = cluster_size / mft_record_size. */
-	FILE_LogFile   = 2,	/* Journalling log in data attribute. */
-	FILE_Volume    = 3,	/* Volume name attribute and volume information
-				   attribute (flags and ntfs version). Windows
-				   refers to this file as volume DASD (Direct
-				   Access Storage Device). */
-	FILE_AttrDef   = 4,	/* Array of attribute definitions in data
-				   attribute. */
-	FILE_root      = 5,	/* Root directory. */
-	FILE_Bitmap    = 6,	/* Allocation bitmap of all clusters (lcns) in
-				   data attribute. */
-	FILE_Boot      = 7,	/* Boot sector (always at cluster 0) in data
-				   attribute. */
-	FILE_BadClus   = 8,	/* Contains all bad clusters in the non-resident
-				   data attribute. */
-	FILE_Secure    = 9,	/* Shared security descriptors in data attribute
-				   and two indexes into the descriptors.
-				   Appeared in Windows 2000. Before that, this
-				   file was named $Quota but was unused. */
-	FILE_UpCase    = 10,	/* Uppercase equivalents of all 65536 Unicode
-				   characters in data attribute. */
-	FILE_Extend    = 11,	/* Directory containing other system files (eg.
-				   $ObjId, $Quota, $Reparse and $UsnJrnl). This
-				   is new to NTFS3.0. */
-	FILE_reserved12 = 12,	/* Reserved for future use (records 12-15). */
-	FILE_reserved13 = 13,
-	FILE_reserved14 = 14,
-	FILE_reserved15 = 15,
-	FILE_first_user = 16,	/* First user file, used as test limit for
-				   whether to allow opening a file or not. */
-} NTFS_SYSTEM_FILES;
-
-/*
- * These are the so far known MFT_RECORD_* flags (16-bit) which contain
- * information about the mft record in which they are present.
- */
-enum {
-	MFT_RECORD_IN_USE	= cpu_to_le16(0x0001),
-	MFT_RECORD_IS_DIRECTORY = cpu_to_le16(0x0002),
-} __attribute__ ((__packed__));
-
-typedef le16 MFT_RECORD_FLAGS;
-
-/*
- * mft references (aka file references or file record segment references) are
- * used whenever a structure needs to refer to a record in the mft.
- *
- * A reference consists of a 48-bit index into the mft and a 16-bit sequence
- * number used to detect stale references.
- *
- * For error reporting purposes we treat the 48-bit index as a signed quantity.
- *
- * The sequence number is a circular counter (skipping 0) describing how many
- * times the referenced mft record has been (re)used. This has to match the
- * sequence number of the mft record being referenced, otherwise the reference
- * is considered stale and removed (FIXME: only ntfsck or the driver itself?).
- *
- * If the sequence number is zero it is assumed that no sequence number
- * consistency checking should be performed.
- *
- * FIXME: Since inodes are 32-bit as of now, the driver needs to always check
- * for high_part being 0 and if not either BUG(), cause a panic() or handle
- * the situation in some other way. This shouldn't be a problem as a volume has
- * to become HUGE in order to need more than 32-bits worth of mft records.
- * Assuming the standard mft record size of 1kb only the records (never mind
- * the non-resident attributes, etc.) would require 4Tb of space on their own
- * for the first 32 bits worth of records. This is only if some strange person
- * doesn't decide to foul play and make the mft sparse which would be a really
- * horrible thing to do as it would trash our current driver implementation. )-:
- * Do I hear screams "we want 64-bit inodes!" ?!? (-;
- *
- * FIXME: The mft zone is defined as the first 12% of the volume. This space is
- * reserved so that the mft can grow contiguously and hence doesn't become
- * fragmented. Volume free space includes the empty part of the mft zone and
- * when the volume's free 88% are used up, the mft zone is shrunk by a factor
- * of 2, thus making more space available for more files/data. This process is
- * repeated every time there is no more free space except for the mft zone until
- * there really is no more free space.
- */
-
-/*
- * Typedef the MFT_REF as a 64-bit value for easier handling.
- * Also define two unpacking macros to get to the reference (MREF) and
- * sequence number (MSEQNO) respectively.
- * The _LE versions are to be applied on little endian MFT_REFs.
- * Note: The _LE versions will return a CPU endian formatted value!
- */
-#define MFT_REF_MASK_CPU 0x0000ffffffffffffULL
-#define MFT_REF_MASK_LE cpu_to_le64(MFT_REF_MASK_CPU)
-
-typedef u64 MFT_REF;
-typedef le64 leMFT_REF;
-
-#define MK_MREF(m, s)	((MFT_REF)(((MFT_REF)(s) << 48) |		\
-					((MFT_REF)(m) & MFT_REF_MASK_CPU)))
-#define MK_LE_MREF(m, s) cpu_to_le64(MK_MREF(m, s))
-
-#define MREF(x)		((unsigned long)((x) & MFT_REF_MASK_CPU))
-#define MSEQNO(x)	((u16)(((x) >> 48) & 0xffff))
-#define MREF_LE(x)	((unsigned long)(le64_to_cpu(x) & MFT_REF_MASK_CPU))
-#define MSEQNO_LE(x)	((u16)((le64_to_cpu(x) >> 48) & 0xffff))
-
-#define IS_ERR_MREF(x)	(((x) & 0x0000800000000000ULL) ? true : false)
-#define ERR_MREF(x)	((u64)((s64)(x)))
-#define MREF_ERR(x)	((int)((s64)(x)))
-
-/*
- * The mft record header present at the beginning of every record in the mft.
- * This is followed by a sequence of variable length attribute records which
- * is terminated by an attribute of type AT_END which is a truncated attribute
- * in that it only consists of the attribute type code AT_END and none of the
- * other members of the attribute structure are present.
- */
-typedef struct {
-/*Ofs*/
-/*  0	NTFS_RECORD; -- Unfolded here as gcc doesn't like unnamed structs. */
-	NTFS_RECORD_TYPE magic;	/* Usually the magic is "FILE". */
-	le16 usa_ofs;		/* See NTFS_RECORD definition above. */
-	le16 usa_count;		/* See NTFS_RECORD definition above. */
-
-/*  8*/	le64 lsn;		/* $LogFile sequence number for this record.
-				   Changed every time the record is modified. */
-/* 16*/	le16 sequence_number;	/* Number of times this mft record has been
-				   reused. (See description for MFT_REF
-				   above.) NOTE: The increment (skipping zero)
-				   is done when the file is deleted. NOTE: If
-				   this is zero it is left zero. */
-/* 18*/	le16 link_count;	/* Number of hard links, i.e. the number of
-				   directory entries referencing this record.
-				   NOTE: Only used in mft base records.
-				   NOTE: When deleting a directory entry we
-				   check the link_count and if it is 1 we
-				   delete the file. Otherwise we delete the
-				   FILE_NAME_ATTR being referenced by the
-				   directory entry from the mft record and
-				   decrement the link_count.
-				   FIXME: Careful with Win32 + DOS names! */
-/* 20*/	le16 attrs_offset;	/* Byte offset to the first attribute in this
-				   mft record from the start of the mft record.
-				   NOTE: Must be aligned to 8-byte boundary. */
-/* 22*/	MFT_RECORD_FLAGS flags;	/* Bit array of MFT_RECORD_FLAGS. When a file
-				   is deleted, the MFT_RECORD_IN_USE flag is
-				   set to zero. */
-/* 24*/	le32 bytes_in_use;	/* Number of bytes used in this mft record.
-				   NOTE: Must be aligned to 8-byte boundary. */
-/* 28*/	le32 bytes_allocated;	/* Number of bytes allocated for this mft
-				   record. This should be equal to the mft
-				   record size. */
-/* 32*/	leMFT_REF base_mft_record;/* This is zero for base mft records.
-				   When it is not zero it is a mft reference
-				   pointing to the base mft record to which
-				   this record belongs (this is then used to
-				   locate the attribute list attribute present
-				   in the base record which describes this
-				   extension record and hence might need
-				   modification when the extension record
-				   itself is modified, also locating the
-				   attribute list also means finding the other
-				   potential extents, belonging to the non-base
-				   mft record). */
-/* 40*/	le16 next_attr_instance;/* The instance number that will be assigned to
-				   the next attribute added to this mft record.
-				   NOTE: Incremented each time after it is used.
-				   NOTE: Every time the mft record is reused
-				   this number is set to zero.  NOTE: The first
-				   instance number is always 0. */
-/* The below fields are specific to NTFS 3.1+ (Windows XP and above): */
-/* 42*/ le16 reserved;		/* Reserved/alignment. */
-/* 44*/ le32 mft_record_number;	/* Number of this mft record. */
-/* sizeof() = 48 bytes */
-/*
- * When (re)using the mft record, we place the update sequence array at this
- * offset, i.e. before we start with the attributes.  This also makes sense,
- * otherwise we could run into problems with the update sequence array
- * containing in itself the last two bytes of a sector which would mean that
- * multi sector transfer protection wouldn't work.  As you can't protect data
- * by overwriting it since you then can't get it back...
- * When reading we obviously use the data from the ntfs record header.
- */
-} __attribute__ ((__packed__)) MFT_RECORD;
-
-/* This is the version without the NTFS 3.1+ specific fields. */
-typedef struct {
-/*Ofs*/
-/*  0	NTFS_RECORD; -- Unfolded here as gcc doesn't like unnamed structs. */
-	NTFS_RECORD_TYPE magic;	/* Usually the magic is "FILE". */
-	le16 usa_ofs;		/* See NTFS_RECORD definition above. */
-	le16 usa_count;		/* See NTFS_RECORD definition above. */
-
-/*  8*/	le64 lsn;		/* $LogFile sequence number for this record.
-				   Changed every time the record is modified. */
-/* 16*/	le16 sequence_number;	/* Number of times this mft record has been
-				   reused. (See description for MFT_REF
-				   above.) NOTE: The increment (skipping zero)
-				   is done when the file is deleted. NOTE: If
-				   this is zero it is left zero. */
-/* 18*/	le16 link_count;	/* Number of hard links, i.e. the number of
-				   directory entries referencing this record.
-				   NOTE: Only used in mft base records.
-				   NOTE: When deleting a directory entry we
-				   check the link_count and if it is 1 we
-				   delete the file. Otherwise we delete the
-				   FILE_NAME_ATTR being referenced by the
-				   directory entry from the mft record and
-				   decrement the link_count.
-				   FIXME: Careful with Win32 + DOS names! */
-/* 20*/	le16 attrs_offset;	/* Byte offset to the first attribute in this
-				   mft record from the start of the mft record.
-				   NOTE: Must be aligned to 8-byte boundary. */
-/* 22*/	MFT_RECORD_FLAGS flags;	/* Bit array of MFT_RECORD_FLAGS. When a file
-				   is deleted, the MFT_RECORD_IN_USE flag is
-				   set to zero. */
-/* 24*/	le32 bytes_in_use;	/* Number of bytes used in this mft record.
-				   NOTE: Must be aligned to 8-byte boundary. */
-/* 28*/	le32 bytes_allocated;	/* Number of bytes allocated for this mft
-				   record. This should be equal to the mft
-				   record size. */
-/* 32*/	leMFT_REF base_mft_record;/* This is zero for base mft records.
-				   When it is not zero it is a mft reference
-				   pointing to the base mft record to which
-				   this record belongs (this is then used to
-				   locate the attribute list attribute present
-				   in the base record which describes this
-				   extension record and hence might need
-				   modification when the extension record
-				   itself is modified, also locating the
-				   attribute list also means finding the other
-				   potential extents, belonging to the non-base
-				   mft record). */
-/* 40*/	le16 next_attr_instance;/* The instance number that will be assigned to
-				   the next attribute added to this mft record.
-				   NOTE: Incremented each time after it is used.
-				   NOTE: Every time the mft record is reused
-				   this number is set to zero.  NOTE: The first
-				   instance number is always 0. */
-/* sizeof() = 42 bytes */
-/*
- * When (re)using the mft record, we place the update sequence array at this
- * offset, i.e. before we start with the attributes.  This also makes sense,
- * otherwise we could run into problems with the update sequence array
- * containing in itself the last two bytes of a sector which would mean that
- * multi sector transfer protection wouldn't work.  As you can't protect data
- * by overwriting it since you then can't get it back...
- * When reading we obviously use the data from the ntfs record header.
- */
-} __attribute__ ((__packed__)) MFT_RECORD_OLD;
-
-/*
- * System defined attributes (32-bit).  Each attribute type has a corresponding
- * attribute name (Unicode string of maximum 64 character length) as described
- * by the attribute definitions present in the data attribute of the $AttrDef
- * system file.  On NTFS 3.0 volumes the names are just as the types are named
- * in the below defines exchanging AT_ for the dollar sign ($).  If that is not
- * a revealing choice of symbol I do not know what is... (-;
- */
-enum {
-	AT_UNUSED			= cpu_to_le32(         0),
-	AT_STANDARD_INFORMATION		= cpu_to_le32(      0x10),
-	AT_ATTRIBUTE_LIST		= cpu_to_le32(      0x20),
-	AT_FILE_NAME			= cpu_to_le32(      0x30),
-	AT_OBJECT_ID			= cpu_to_le32(      0x40),
-	AT_SECURITY_DESCRIPTOR		= cpu_to_le32(      0x50),
-	AT_VOLUME_NAME			= cpu_to_le32(      0x60),
-	AT_VOLUME_INFORMATION		= cpu_to_le32(      0x70),
-	AT_DATA				= cpu_to_le32(      0x80),
-	AT_INDEX_ROOT			= cpu_to_le32(      0x90),
-	AT_INDEX_ALLOCATION		= cpu_to_le32(      0xa0),
-	AT_BITMAP			= cpu_to_le32(      0xb0),
-	AT_REPARSE_POINT		= cpu_to_le32(      0xc0),
-	AT_EA_INFORMATION		= cpu_to_le32(      0xd0),
-	AT_EA				= cpu_to_le32(      0xe0),
-	AT_PROPERTY_SET			= cpu_to_le32(      0xf0),
-	AT_LOGGED_UTILITY_STREAM	= cpu_to_le32(     0x100),
-	AT_FIRST_USER_DEFINED_ATTRIBUTE	= cpu_to_le32(    0x1000),
-	AT_END				= cpu_to_le32(0xffffffff)
-};
-
-typedef le32 ATTR_TYPE;
-
-/*
- * The collation rules for sorting views/indexes/etc (32-bit).
- *
- * COLLATION_BINARY - Collate by binary compare where the first byte is most
- *	significant.
- * COLLATION_UNICODE_STRING - Collate Unicode strings by comparing their binary
- *	Unicode values, except that when a character can be uppercased, the
- *	upper case value collates before the lower case one.
- * COLLATION_FILE_NAME - Collate file names as Unicode strings. The collation
- *	is done very much like COLLATION_UNICODE_STRING. In fact I have no idea
- *	what the difference is. Perhaps the difference is that file names
- *	would treat some special characters in an odd way (see
- *	unistr.c::ntfs_collate_names() and unistr.c::legal_ansi_char_array[]
- *	for what I mean but COLLATION_UNICODE_STRING would not give any special
- *	treatment to any characters at all, but this is speculation.
- * COLLATION_NTOFS_ULONG - Sorting is done according to ascending le32 key
- *	values. E.g. used for $SII index in FILE_Secure, which sorts by
- *	security_id (le32).
- * COLLATION_NTOFS_SID - Sorting is done according to ascending SID values.
- *	E.g. used for $O index in FILE_Extend/$Quota.
- * COLLATION_NTOFS_SECURITY_HASH - Sorting is done first by ascending hash
- *	values and second by ascending security_id values. E.g. used for $SDH
- *	index in FILE_Secure.
- * COLLATION_NTOFS_ULONGS - Sorting is done according to a sequence of ascending
- *	le32 key values. E.g. used for $O index in FILE_Extend/$ObjId, which
- *	sorts by object_id (16-byte), by splitting up the object_id in four
- *	le32 values and using them as individual keys. E.g. take the following
- *	two security_ids, stored as follows on disk:
- *		1st: a1 61 65 b7 65 7b d4 11 9e 3d 00 e0 81 10 42 59
- *		2nd: 38 14 37 d2 d2 f3 d4 11 a5 21 c8 6b 79 b1 97 45
- *	To compare them, they are split into four le32 values each, like so:
- *		1st: 0xb76561a1 0x11d47b65 0xe0003d9e 0x59421081
- *		2nd: 0xd2371438 0x11d4f3d2 0x6bc821a5 0x4597b179
- *	Now, it is apparent why the 2nd object_id collates after the 1st: the
- *	first le32 value of the 1st object_id is less than the first le32 of
- *	the 2nd object_id. If the first le32 values of both object_ids were
- *	equal then the second le32 values would be compared, etc.
- */
-enum {
-	COLLATION_BINARY		= cpu_to_le32(0x00),
-	COLLATION_FILE_NAME		= cpu_to_le32(0x01),
-	COLLATION_UNICODE_STRING	= cpu_to_le32(0x02),
-	COLLATION_NTOFS_ULONG		= cpu_to_le32(0x10),
-	COLLATION_NTOFS_SID		= cpu_to_le32(0x11),
-	COLLATION_NTOFS_SECURITY_HASH	= cpu_to_le32(0x12),
-	COLLATION_NTOFS_ULONGS		= cpu_to_le32(0x13),
-};
-
-typedef le32 COLLATION_RULE;
-
-/*
- * The flags (32-bit) describing attribute properties in the attribute
- * definition structure.  FIXME: This information is based on Regis's
- * information and, according to him, it is not certain and probably
- * incomplete.  The INDEXABLE flag is fairly certainly correct as only the file
- * name attribute has this flag set and this is the only attribute indexed in
- * NT4.
- */
-enum {
-	ATTR_DEF_INDEXABLE	= cpu_to_le32(0x02), /* Attribute can be
-					indexed. */
-	ATTR_DEF_MULTIPLE	= cpu_to_le32(0x04), /* Attribute type
-					can be present multiple times in the
-					mft records of an inode. */
-	ATTR_DEF_NOT_ZERO	= cpu_to_le32(0x08), /* Attribute value
-					must contain at least one non-zero
-					byte. */
-	ATTR_DEF_INDEXED_UNIQUE	= cpu_to_le32(0x10), /* Attribute must be
-					indexed and the attribute value must be
-					unique for the attribute type in all of
-					the mft records of an inode. */
-	ATTR_DEF_NAMED_UNIQUE	= cpu_to_le32(0x20), /* Attribute must be
-					named and the name must be unique for
-					the attribute type in all of the mft
-					records of an inode. */
-	ATTR_DEF_RESIDENT	= cpu_to_le32(0x40), /* Attribute must be
-					resident. */
-	ATTR_DEF_ALWAYS_LOG	= cpu_to_le32(0x80), /* Always log
-					modifications to this attribute,
-					regardless of whether it is resident or
-					non-resident.  Without this, only log
-					modifications if the attribute is
-					resident. */
-};
-
-typedef le32 ATTR_DEF_FLAGS;
-
-/*
- * The data attribute of FILE_AttrDef contains a sequence of attribute
- * definitions for the NTFS volume. With this, it is supposed to be safe for an
- * older NTFS driver to mount a volume containing a newer NTFS version without
- * damaging it (that's the theory. In practice it's: not damaging it too much).
- * Entries are sorted by attribute type. The flags describe whether the
- * attribute can be resident/non-resident and possibly other things, but the
- * actual bits are unknown.
- */
-typedef struct {
-/*hex ofs*/
-/*  0*/	ntfschar name[0x40];		/* Unicode name of the attribute. Zero
-					   terminated. */
-/* 80*/	ATTR_TYPE type;			/* Type of the attribute. */
-/* 84*/	le32 display_rule;		/* Default display rule.
-					   FIXME: What does it mean? (AIA) */
-/* 88*/ COLLATION_RULE collation_rule;	/* Default collation rule. */
-/* 8c*/	ATTR_DEF_FLAGS flags;		/* Flags describing the attribute. */
-/* 90*/	sle64 min_size;			/* Optional minimum attribute size. */
-/* 98*/	sle64 max_size;			/* Maximum size of attribute. */
-/* sizeof() = 0xa0 or 160 bytes */
-} __attribute__ ((__packed__)) ATTR_DEF;
-
-/*
- * Attribute flags (16-bit).
- */
-enum {
-	ATTR_IS_COMPRESSED    = cpu_to_le16(0x0001),
-	ATTR_COMPRESSION_MASK = cpu_to_le16(0x00ff), /* Compression method
-							      mask.  Also, first
-							      illegal value. */
-	ATTR_IS_ENCRYPTED     = cpu_to_le16(0x4000),
-	ATTR_IS_SPARSE	      = cpu_to_le16(0x8000),
-} __attribute__ ((__packed__));
-
-typedef le16 ATTR_FLAGS;
-
-/*
- * Attribute compression.
- *
- * Only the data attribute is ever compressed in the current ntfs driver in
- * Windows. Further, compression is only applied when the data attribute is
- * non-resident. Finally, to use compression, the maximum allowed cluster size
- * on a volume is 4kib.
- *
- * The compression method is based on independently compressing blocks of X
- * clusters, where X is determined from the compression_unit value found in the
- * non-resident attribute record header (more precisely: X = 2^compression_unit
- * clusters). On Windows NT/2k, X always is 16 clusters (compression_unit = 4).
- *
- * There are three different cases of how a compression block of X clusters
- * can be stored:
- *
- *   1) The data in the block is all zero (a sparse block):
- *	  This is stored as a sparse block in the runlist, i.e. the runlist
- *	  entry has length = X and lcn = -1. The mapping pairs array actually
- *	  uses a delta_lcn value length of 0, i.e. delta_lcn is not present at
- *	  all, which is then interpreted by the driver as lcn = -1.
- *	  NOTE: Even uncompressed files can be sparse on NTFS 3.0 volumes, then
- *	  the same principles apply as above, except that the length is not
- *	  restricted to being any particular value.
- *
- *   2) The data in the block is not compressed:
- *	  This happens when compression doesn't reduce the size of the block
- *	  in clusters. I.e. if compression has a small effect so that the
- *	  compressed data still occupies X clusters, then the uncompressed data
- *	  is stored in the block.
- *	  This case is recognised by the fact that the runlist entry has
- *	  length = X and lcn >= 0. The mapping pairs array stores this as
- *	  normal with a run length of X and some specific delta_lcn, i.e.
- *	  delta_lcn has to be present.
- *
- *   3) The data in the block is compressed:
- *	  The common case. This case is recognised by the fact that the run
- *	  list entry has length L < X and lcn >= 0. The mapping pairs array
- *	  stores this as normal with a run length of X and some specific
- *	  delta_lcn, i.e. delta_lcn has to be present. This runlist entry is
- *	  immediately followed by a sparse entry with length = X - L and
- *	  lcn = -1. The latter entry is to make up the vcn counting to the
- *	  full compression block size X.
- *
- * In fact, life is more complicated because adjacent entries of the same type
- * can be coalesced. This means that one has to keep track of the number of
- * clusters handled and work on a basis of X clusters at a time being one
- * block. An example: if length L > X this means that this particular runlist
- * entry contains a block of length X and part of one or more blocks of length
- * L - X. Another example: if length L < X, this does not necessarily mean that
- * the block is compressed as it might be that the lcn changes inside the block
- * and hence the following runlist entry describes the continuation of the
- * potentially compressed block. The block would be compressed if the
- * following runlist entry describes at least X - L sparse clusters, thus
- * making up the compression block length as described in point 3 above. (Of
- * course, there can be several runlist entries with small lengths so that the
- * sparse entry does not follow the first data containing entry with
- * length < X.)
- *
- * NOTE: At the end of the compressed attribute value, there most likely is not
- * just the right amount of data to make up a compression block, thus this data
- * is not even attempted to be compressed. It is just stored as is, unless
- * the number of clusters it occupies is reduced when compressed in which case
- * it is stored as a compressed compression block, complete with sparse
- * clusters at the end.
- */
-
-/*
- * Flags of resident attributes (8-bit).
- */
-enum {
-	RESIDENT_ATTR_IS_INDEXED = 0x01, /* Attribute is referenced in an index
-					    (has implications for deleting and
-					    modifying the attribute). */
-} __attribute__ ((__packed__));
-
-typedef u8 RESIDENT_ATTR_FLAGS;
-
-/*
- * Attribute record header. Always aligned to 8-byte boundary.
- */
-typedef struct {
-/*Ofs*/
-/*  0*/	ATTR_TYPE type;		/* The (32-bit) type of the attribute. */
-/*  4*/	le32 length;		/* Byte size of the resident part of the
-				   attribute (aligned to 8-byte boundary).
-				   Used to get to the next attribute. */
-/*  8*/	u8 non_resident;	/* If 0, attribute is resident.
-				   If 1, attribute is non-resident. */
-/*  9*/	u8 name_length;		/* Unicode character size of name of attribute.
-				   0 if unnamed. */
-/* 10*/	le16 name_offset;	/* If name_length != 0, the byte offset to the
-				   beginning of the name from the attribute
-				   record. Note that the name is stored as a
-				   Unicode string. When creating, place offset
-				   just at the end of the record header. Then,
-				   follow with attribute value or mapping pairs
-				   array, resident and non-resident attributes
-				   respectively, aligning to an 8-byte
-				   boundary. */
-/* 12*/	ATTR_FLAGS flags;	/* Flags describing the attribute. */
-/* 14*/	le16 instance;		/* The instance of this attribute record. This
-				   number is unique within this mft record (see
-				   MFT_RECORD/next_attribute_instance notes in
-				   mft.h for more details). */
-/* 16*/	union {
-		/* Resident attributes. */
-		struct {
-/* 16 */		le32 value_length;/* Byte size of attribute value. */
-/* 20 */		le16 value_offset;/* Byte offset of the attribute
-					     value from the start of the
-					     attribute record. When creating,
-					     align to 8-byte boundary if we
-					     have a name present as this might
-					     not have a length of a multiple
-					     of 8-bytes. */
-/* 22 */		RESIDENT_ATTR_FLAGS flags; /* See above. */
-/* 23 */		s8 reserved;	  /* Reserved/alignment to 8-byte
-					     boundary. */
-		} __attribute__ ((__packed__)) resident;
-		/* Non-resident attributes. */
-		struct {
-/* 16*/			leVCN lowest_vcn;/* Lowest valid virtual cluster number
-				for this portion of the attribute value or
-				0 if this is the only extent (usually the
-				case). - Only when an attribute list is used
-				does lowest_vcn != 0 ever occur. */
-/* 24*/			leVCN highest_vcn;/* Highest valid vcn of this extent of
-				the attribute value. - Usually there is only one
-				portion, so this usually equals the attribute
-				value size in clusters minus 1. Can be -1 for
-				zero length files. Can be 0 for "single extent"
-				attributes. */
-/* 32*/			le16 mapping_pairs_offset; /* Byte offset from the
-				beginning of the structure to the mapping pairs
-				array which contains the mappings between the
-				vcns and the logical cluster numbers (lcns).
-				When creating, place this at the end of this
-				record header aligned to 8-byte boundary. */
-/* 34*/			u8 compression_unit; /* The compression unit expressed
-				as the log to the base 2 of the number of
-				clusters in a compression unit.  0 means not
-				compressed.  (This effectively limits the
-				compression unit size to be a power of two
-				clusters.)  WinNT4 only uses a value of 4.
-				Sparse files have this set to 0 on XPSP2. */
-/* 35*/			u8 reserved[5];		/* Align to 8-byte boundary. */
-/* The sizes below are only used when lowest_vcn is zero, as otherwise it would
-   be difficult to keep them up-to-date.*/
-/* 40*/			sle64 allocated_size;	/* Byte size of disk space
-				allocated to hold the attribute value. Always
-				is a multiple of the cluster size. When a file
-				is compressed, this field is a multiple of the
-				compression block size (2^compression_unit) and
-				it represents the logically allocated space
-				rather than the actual on disk usage. For this
-				use the compressed_size (see below). */
-/* 48*/			sle64 data_size;	/* Byte size of the attribute
-				value. Can be larger than allocated_size if
-				attribute value is compressed or sparse. */
-/* 56*/			sle64 initialized_size;	/* Byte size of initialized
-				portion of the attribute value. Usually equals
-				data_size. */
-/* sizeof(uncompressed attr) = 64*/
-/* 64*/			sle64 compressed_size;	/* Byte size of the attribute
-				value after compression.  Only present when
-				compressed or sparse.  Always is a multiple of
-				the cluster size.  Represents the actual amount
-				of disk space being used on the disk. */
-/* sizeof(compressed attr) = 72*/
-		} __attribute__ ((__packed__)) non_resident;
-	} __attribute__ ((__packed__)) data;
-} __attribute__ ((__packed__)) ATTR_RECORD;
-
-typedef ATTR_RECORD ATTR_REC;
-
-/*
- * File attribute flags (32-bit) appearing in the file_attributes fields of the
- * STANDARD_INFORMATION attribute of MFT_RECORDs and the FILENAME_ATTR
- * attributes of MFT_RECORDs and directory index entries.
- *
- * All of the below flags appear in the directory index entries but only some
- * appear in the STANDARD_INFORMATION attribute whilst only some others appear
- * in the FILENAME_ATTR attribute of MFT_RECORDs.  Unless otherwise stated the
- * flags appear in all of the above.
- */
-enum {
-	FILE_ATTR_READONLY		= cpu_to_le32(0x00000001),
-	FILE_ATTR_HIDDEN		= cpu_to_le32(0x00000002),
-	FILE_ATTR_SYSTEM		= cpu_to_le32(0x00000004),
-	/* Old DOS volid. Unused in NT.	= cpu_to_le32(0x00000008), */
-
-	FILE_ATTR_DIRECTORY		= cpu_to_le32(0x00000010),
-	/* Note, FILE_ATTR_DIRECTORY is not considered valid in NT.  It is
-	   reserved for the DOS SUBDIRECTORY flag. */
-	FILE_ATTR_ARCHIVE		= cpu_to_le32(0x00000020),
-	FILE_ATTR_DEVICE		= cpu_to_le32(0x00000040),
-	FILE_ATTR_NORMAL		= cpu_to_le32(0x00000080),
-
-	FILE_ATTR_TEMPORARY		= cpu_to_le32(0x00000100),
-	FILE_ATTR_SPARSE_FILE		= cpu_to_le32(0x00000200),
-	FILE_ATTR_REPARSE_POINT		= cpu_to_le32(0x00000400),
-	FILE_ATTR_COMPRESSED		= cpu_to_le32(0x00000800),
-
-	FILE_ATTR_OFFLINE		= cpu_to_le32(0x00001000),
-	FILE_ATTR_NOT_CONTENT_INDEXED	= cpu_to_le32(0x00002000),
-	FILE_ATTR_ENCRYPTED		= cpu_to_le32(0x00004000),
-
-	FILE_ATTR_VALID_FLAGS		= cpu_to_le32(0x00007fb7),
-	/* Note, FILE_ATTR_VALID_FLAGS masks out the old DOS VolId and the
-	   FILE_ATTR_DEVICE and preserves everything else.  This mask is used
-	   to obtain all flags that are valid for reading. */
-	FILE_ATTR_VALID_SET_FLAGS	= cpu_to_le32(0x000031a7),
-	/* Note, FILE_ATTR_VALID_SET_FLAGS masks out the old DOS VolId, the
-	   F_A_DEVICE, F_A_DIRECTORY, F_A_SPARSE_FILE, F_A_REPARSE_POINT,
-	   F_A_COMPRESSED, and F_A_ENCRYPTED and preserves the rest.  This mask
-	   is used to obtain all flags that are valid for setting. */
-	/*
-	 * The flag FILE_ATTR_DUP_FILENAME_INDEX_PRESENT is present in all
-	 * FILENAME_ATTR attributes but not in the STANDARD_INFORMATION
-	 * attribute of an mft record.
-	 */
-	FILE_ATTR_DUP_FILE_NAME_INDEX_PRESENT	= cpu_to_le32(0x10000000),
-	/* Note, this is a copy of the corresponding bit from the mft record,
-	   telling us whether this is a directory or not, i.e. whether it has
-	   an index root attribute or not. */
-	FILE_ATTR_DUP_VIEW_INDEX_PRESENT	= cpu_to_le32(0x20000000),
-	/* Note, this is a copy of the corresponding bit from the mft record,
-	   telling us whether this file has a view index present (eg. object id
-	   index, quota index, one of the security indexes or the encrypting
-	   filesystem related indexes). */
-};
-
-typedef le32 FILE_ATTR_FLAGS;
-
-/*
- * NOTE on times in NTFS: All times are in MS standard time format, i.e. they
- * are the number of 100-nanosecond intervals since 1st January 1601, 00:00:00
- * universal coordinated time (UTC). (In Linux time starts 1st January 1970,
- * 00:00:00 UTC and is stored as the number of 1-second intervals since then.)
- */
-
-/*
- * Attribute: Standard information (0x10).
- *
- * NOTE: Always resident.
- * NOTE: Present in all base file records on a volume.
- * NOTE: There is conflicting information about the meaning of each of the time
- *	 fields but the meaning as defined below has been verified to be
- *	 correct by practical experimentation on Windows NT4 SP6a and is hence
- *	 assumed to be the one and only correct interpretation.
- */
-typedef struct {
-/*Ofs*/
-/*  0*/	sle64 creation_time;		/* Time file was created. Updated when
-					   a filename is changed(?). */
-/*  8*/	sle64 last_data_change_time;	/* Time the data attribute was last
-					   modified. */
-/* 16*/	sle64 last_mft_change_time;	/* Time this mft record was last
-					   modified. */
-/* 24*/	sle64 last_access_time;		/* Approximate time when the file was
-					   last accessed (obviously this is not
-					   updated on read-only volumes). In
-					   Windows this is only updated when
-					   accessed if some time delta has
-					   passed since the last update. Also,
-					   last access time updates can be
-					   disabled altogether for speed. */
-/* 32*/	FILE_ATTR_FLAGS file_attributes; /* Flags describing the file. */
-/* 36*/	union {
-	/* NTFS 1.2 */
-		struct {
-		/* 36*/	u8 reserved12[12];	/* Reserved/alignment to 8-byte
-						   boundary. */
-		} __attribute__ ((__packed__)) v1;
-	/* sizeof() = 48 bytes */
-	/* NTFS 3.x */
-		struct {
-/*
- * If a volume has been upgraded from a previous NTFS version, then these
- * fields are present only if the file has been accessed since the upgrade.
- * Recognize the difference by comparing the length of the resident attribute
- * value. If it is 48, then the following fields are missing. If it is 72 then
- * the fields are present. Maybe just check like this:
- *	if (resident.ValueLength < sizeof(STANDARD_INFORMATION)) {
- *		Assume NTFS 1.2- format.
- *		If (volume version is 3.x)
- *			Upgrade attribute to NTFS 3.x format.
- *		else
- *			Use NTFS 1.2- format for access.
- *	} else
- *		Use NTFS 3.x format for access.
- * Only problem is that it might be legal to set the length of the value to
- * arbitrarily large values thus spoiling this check. - But chkdsk probably
- * views that as a corruption, assuming that it behaves like this for all
- * attributes.
- */
-		/* 36*/	le32 maximum_versions;	/* Maximum allowed versions for
-				file. Zero if version numbering is disabled. */
-		/* 40*/	le32 version_number;	/* This file's version (if any).
-				Set to zero if maximum_versions is zero. */
-		/* 44*/	le32 class_id;		/* Class id from bidirectional
-				class id index (?). */
-		/* 48*/	le32 owner_id;		/* Owner_id of the user owning
-				the file. Translate via $Q index in FILE_Extend
-				/$Quota to the quota control entry for the user
-				owning the file. Zero if quotas are disabled. */
-		/* 52*/	le32 security_id;	/* Security_id for the file.
-				Translate via $SII index and $SDS data stream
-				in FILE_Secure to the security descriptor. */
-		/* 56*/	le64 quota_charged;	/* Byte size of the charge to
-				the quota for all streams of the file. Note: Is
-				zero if quotas are disabled. */
-		/* 64*/	leUSN usn;		/* Last update sequence number
-				of the file.  This is a direct index into the
-				transaction log file ($UsnJrnl).  It is zero if
-				the usn journal is disabled or this file has
-				not been subject to logging yet.  See usnjrnl.h
-				for details. */
-		} __attribute__ ((__packed__)) v3;
-	/* sizeof() = 72 bytes (NTFS 3.x) */
-	} __attribute__ ((__packed__)) ver;
-} __attribute__ ((__packed__)) STANDARD_INFORMATION;
-
-/*
- * Attribute: Attribute list (0x20).
- *
- * - Can be either resident or non-resident.
- * - Value consists of a sequence of variable length, 8-byte aligned,
- * ATTR_LIST_ENTRY records.
- * - The list is not terminated by anything at all! The only way to know when
- * the end is reached is to keep track of the current offset and compare it to
- * the attribute value size.
- * - The attribute list attribute contains one entry for each attribute of
- * the file in which the list is located, except for the list attribute
- * itself. The list is sorted: first by attribute type, second by attribute
- * name (if present), third by instance number. The extents of one
- * non-resident attribute (if present) immediately follow after the initial
- * extent. They are ordered by lowest_vcn and have their instace set to zero.
- * It is not allowed to have two attributes with all sorting keys equal.
- * - Further restrictions:
- *	- If not resident, the vcn to lcn mapping array has to fit inside the
- *	  base mft record.
- *	- The attribute list attribute value has a maximum size of 256kb. This
- *	  is imposed by the Windows cache manager.
- * - Attribute lists are only used when the attributes of mft record do not
- * fit inside the mft record despite all attributes (that can be made
- * non-resident) having been made non-resident. This can happen e.g. when:
- *	- File has a large number of hard links (lots of file name
- *	  attributes present).
- *	- The mapping pairs array of some non-resident attribute becomes so
- *	  large due to fragmentation that it overflows the mft record.
- *	- The security descriptor is very complex (not applicable to
- *	  NTFS 3.0 volumes).
- *	- There are many named streams.
- */
-typedef struct {
-/*Ofs*/
-/*  0*/	ATTR_TYPE type;		/* Type of referenced attribute. */
-/*  4*/	le16 length;		/* Byte size of this entry (8-byte aligned). */
-/*  6*/	u8 name_length;		/* Size in Unicode chars of the name of the
-				   attribute or 0 if unnamed. */
-/*  7*/	u8 name_offset;		/* Byte offset to beginning of attribute name
-				   (always set this to where the name would
-				   start even if unnamed). */
-/*  8*/	leVCN lowest_vcn;	/* Lowest virtual cluster number of this portion
-				   of the attribute value. This is usually 0. It
-				   is non-zero for the case where one attribute
-				   does not fit into one mft record and thus
-				   several mft records are allocated to hold
-				   this attribute. In the latter case, each mft
-				   record holds one extent of the attribute and
-				   there is one attribute list entry for each
-				   extent. NOTE: This is DEFINITELY a signed
-				   value! The windows driver uses cmp, followed
-				   by jg when comparing this, thus it treats it
-				   as signed. */
-/* 16*/	leMFT_REF mft_reference;/* The reference of the mft record holding
-				   the ATTR_RECORD for this portion of the
-				   attribute value. */
-/* 24*/	le16 instance;		/* If lowest_vcn = 0, the instance of the
-				   attribute being referenced; otherwise 0. */
-/* 26*/	ntfschar name[0];	/* Use when creating only. When reading use
-				   name_offset to determine the location of the
-				   name. */
-/* sizeof() = 26 + (attribute_name_length * 2) bytes */
-} __attribute__ ((__packed__)) ATTR_LIST_ENTRY;
-
-/*
- * The maximum allowed length for a file name.
- */
-#define MAXIMUM_FILE_NAME_LENGTH	255
-
-/*
- * Possible namespaces for filenames in ntfs (8-bit).
- */
-enum {
-	FILE_NAME_POSIX		= 0x00,
-	/* This is the largest namespace. It is case sensitive and allows all
-	   Unicode characters except for: '\0' and '/'.  Beware that in
-	   WinNT/2k/2003 by default files which eg have the same name except
-	   for their case will not be distinguished by the standard utilities
-	   and thus a "del filename" will delete both "filename" and "fileName"
-	   without warning.  However if for example Services For Unix (SFU) are
-	   installed and the case sensitive option was enabled at installation
-	   time, then you can create/access/delete such files.
-	   Note that even SFU places restrictions on the filenames beyond the
-	   '\0' and '/' and in particular the following set of characters is
-	   not allowed: '"', '/', '<', '>', '\'.  All other characters,
-	   including the ones no allowed in WIN32 namespace are allowed.
-	   Tested with SFU 3.5 (this is now free) running on Windows XP. */
-	FILE_NAME_WIN32		= 0x01,
-	/* The standard WinNT/2k NTFS long filenames. Case insensitive.  All
-	   Unicode chars except: '\0', '"', '*', '/', ':', '<', '>', '?', '\',
-	   and '|'.  Further, names cannot end with a '.' or a space. */
-	FILE_NAME_DOS		= 0x02,
-	/* The standard DOS filenames (8.3 format). Uppercase only.  All 8-bit
-	   characters greater space, except: '"', '*', '+', ',', '/', ':', ';',
-	   '<', '=', '>', '?', and '\'. */
-	FILE_NAME_WIN32_AND_DOS	= 0x03,
-	/* 3 means that both the Win32 and the DOS filenames are identical and
-	   hence have been saved in this single filename record. */
-} __attribute__ ((__packed__));
-
-typedef u8 FILE_NAME_TYPE_FLAGS;
-
-/*
- * Attribute: Filename (0x30).
- *
- * NOTE: Always resident.
- * NOTE: All fields, except the parent_directory, are only updated when the
- *	 filename is changed. Until then, they just become out of sync with
- *	 reality and the more up to date values are present in the standard
- *	 information attribute.
- * NOTE: There is conflicting information about the meaning of each of the time
- *	 fields but the meaning as defined below has been verified to be
- *	 correct by practical experimentation on Windows NT4 SP6a and is hence
- *	 assumed to be the one and only correct interpretation.
- */
-typedef struct {
-/*hex ofs*/
-/*  0*/	leMFT_REF parent_directory;	/* Directory this filename is
-					   referenced from. */
-/*  8*/	sle64 creation_time;		/* Time file was created. */
-/* 10*/	sle64 last_data_change_time;	/* Time the data attribute was last
-					   modified. */
-/* 18*/	sle64 last_mft_change_time;	/* Time this mft record was last
-					   modified. */
-/* 20*/	sle64 last_access_time;		/* Time this mft record was last
-					   accessed. */
-/* 28*/	sle64 allocated_size;		/* Byte size of on-disk allocated space
-					   for the unnamed data attribute.  So
-					   for normal $DATA, this is the
-					   allocated_size from the unnamed
-					   $DATA attribute and for compressed
-					   and/or sparse $DATA, this is the
-					   compressed_size from the unnamed
-					   $DATA attribute.  For a directory or
-					   other inode without an unnamed $DATA
-					   attribute, this is always 0.  NOTE:
-					   This is a multiple of the cluster
-					   size. */
-/* 30*/	sle64 data_size;		/* Byte size of actual data in unnamed
-					   data attribute.  For a directory or
-					   other inode without an unnamed $DATA
-					   attribute, this is always 0. */
-/* 38*/	FILE_ATTR_FLAGS file_attributes;	/* Flags describing the file. */
-/* 3c*/	union {
-	/* 3c*/	struct {
-		/* 3c*/	le16 packed_ea_size;	/* Size of the buffer needed to
-						   pack the extended attributes
-						   (EAs), if such are present.*/
-		/* 3e*/	le16 reserved;		/* Reserved for alignment. */
-		} __attribute__ ((__packed__)) ea;
-	/* 3c*/	struct {
-		/* 3c*/	le32 reparse_point_tag;	/* Type of reparse point,
-						   present only in reparse
-						   points and only if there are
-						   no EAs. */
-		} __attribute__ ((__packed__)) rp;
-	} __attribute__ ((__packed__)) type;
-/* 40*/	u8 file_name_length;			/* Length of file name in
-						   (Unicode) characters. */
-/* 41*/	FILE_NAME_TYPE_FLAGS file_name_type;	/* Namespace of the file name.*/
-/* 42*/	ntfschar file_name[0];			/* File name in Unicode. */
-} __attribute__ ((__packed__)) FILE_NAME_ATTR;
-
-/*
- * GUID structures store globally unique identifiers (GUID). A GUID is a
- * 128-bit value consisting of one group of eight hexadecimal digits, followed
- * by three groups of four hexadecimal digits each, followed by one group of
- * twelve hexadecimal digits. GUIDs are Microsoft's implementation of the
- * distributed computing environment (DCE) universally unique identifier (UUID).
- * Example of a GUID:
- *	1F010768-5A73-BC91-0010A52216A7
- */
-typedef struct {
-	le32 data1;	/* The first eight hexadecimal digits of the GUID. */
-	le16 data2;	/* The first group of four hexadecimal digits. */
-	le16 data3;	/* The second group of four hexadecimal digits. */
-	u8 data4[8];	/* The first two bytes are the third group of four
-			   hexadecimal digits. The remaining six bytes are the
-			   final 12 hexadecimal digits. */
-} __attribute__ ((__packed__)) GUID;
-
-/*
- * FILE_Extend/$ObjId contains an index named $O. This index contains all
- * object_ids present on the volume as the index keys and the corresponding
- * mft_record numbers as the index entry data parts. The data part (defined
- * below) also contains three other object_ids:
- *	birth_volume_id - object_id of FILE_Volume on which the file was first
- *			  created. Optional (i.e. can be zero).
- *	birth_object_id - object_id of file when it was first created. Usually
- *			  equals the object_id. Optional (i.e. can be zero).
- *	domain_id	- Reserved (always zero).
- */
-typedef struct {
-	leMFT_REF mft_reference;/* Mft record containing the object_id in
-				   the index entry key. */
-	union {
-		struct {
-			GUID birth_volume_id;
-			GUID birth_object_id;
-			GUID domain_id;
-		} __attribute__ ((__packed__)) origin;
-		u8 extended_info[48];
-	} __attribute__ ((__packed__)) opt;
-} __attribute__ ((__packed__)) OBJ_ID_INDEX_DATA;
-
-/*
- * Attribute: Object id (NTFS 3.0+) (0x40).
- *
- * NOTE: Always resident.
- */
-typedef struct {
-	GUID object_id;				/* Unique id assigned to the
-						   file.*/
-	/* The following fields are optional. The attribute value size is 16
-	   bytes, i.e. sizeof(GUID), if these are not present at all. Note,
-	   the entries can be present but one or more (or all) can be zero
-	   meaning that that particular value(s) is(are) not defined. */
-	union {
-		struct {
-			GUID birth_volume_id;	/* Unique id of volume on which
-						   the file was first created.*/
-			GUID birth_object_id;	/* Unique id of file when it was
-						   first created. */
-			GUID domain_id;		/* Reserved, zero. */
-		} __attribute__ ((__packed__)) origin;
-		u8 extended_info[48];
-	} __attribute__ ((__packed__)) opt;
-} __attribute__ ((__packed__)) OBJECT_ID_ATTR;
-
-/*
- * The pre-defined IDENTIFIER_AUTHORITIES used as SID_IDENTIFIER_AUTHORITY in
- * the SID structure (see below).
- */
-//typedef enum {					/* SID string prefix. */
-//	SECURITY_NULL_SID_AUTHORITY	= {0, 0, 0, 0, 0, 0},	/* S-1-0 */
-//	SECURITY_WORLD_SID_AUTHORITY	= {0, 0, 0, 0, 0, 1},	/* S-1-1 */
-//	SECURITY_LOCAL_SID_AUTHORITY	= {0, 0, 0, 0, 0, 2},	/* S-1-2 */
-//	SECURITY_CREATOR_SID_AUTHORITY	= {0, 0, 0, 0, 0, 3},	/* S-1-3 */
-//	SECURITY_NON_UNIQUE_AUTHORITY	= {0, 0, 0, 0, 0, 4},	/* S-1-4 */
-//	SECURITY_NT_SID_AUTHORITY	= {0, 0, 0, 0, 0, 5},	/* S-1-5 */
-//} IDENTIFIER_AUTHORITIES;
-
-/*
- * These relative identifiers (RIDs) are used with the above identifier
- * authorities to make up universal well-known SIDs.
- *
- * Note: The relative identifier (RID) refers to the portion of a SID, which
- * identifies a user or group in relation to the authority that issued the SID.
- * For example, the universal well-known SID Creator Owner ID (S-1-3-0) is
- * made up of the identifier authority SECURITY_CREATOR_SID_AUTHORITY (3) and
- * the relative identifier SECURITY_CREATOR_OWNER_RID (0).
- */
-typedef enum {					/* Identifier authority. */
-	SECURITY_NULL_RID		  = 0,	/* S-1-0 */
-	SECURITY_WORLD_RID		  = 0,	/* S-1-1 */
-	SECURITY_LOCAL_RID		  = 0,	/* S-1-2 */
-
-	SECURITY_CREATOR_OWNER_RID	  = 0,	/* S-1-3 */
-	SECURITY_CREATOR_GROUP_RID	  = 1,	/* S-1-3 */
-
-	SECURITY_CREATOR_OWNER_SERVER_RID = 2,	/* S-1-3 */
-	SECURITY_CREATOR_GROUP_SERVER_RID = 3,	/* S-1-3 */
-
-	SECURITY_DIALUP_RID		  = 1,
-	SECURITY_NETWORK_RID		  = 2,
-	SECURITY_BATCH_RID		  = 3,
-	SECURITY_INTERACTIVE_RID	  = 4,
-	SECURITY_SERVICE_RID		  = 6,
-	SECURITY_ANONYMOUS_LOGON_RID	  = 7,
-	SECURITY_PROXY_RID		  = 8,
-	SECURITY_ENTERPRISE_CONTROLLERS_RID=9,
-	SECURITY_SERVER_LOGON_RID	  = 9,
-	SECURITY_PRINCIPAL_SELF_RID	  = 0xa,
-	SECURITY_AUTHENTICATED_USER_RID	  = 0xb,
-	SECURITY_RESTRICTED_CODE_RID	  = 0xc,
-	SECURITY_TERMINAL_SERVER_RID	  = 0xd,
-
-	SECURITY_LOGON_IDS_RID		  = 5,
-	SECURITY_LOGON_IDS_RID_COUNT	  = 3,
-
-	SECURITY_LOCAL_SYSTEM_RID	  = 0x12,
-
-	SECURITY_NT_NON_UNIQUE		  = 0x15,
-
-	SECURITY_BUILTIN_DOMAIN_RID	  = 0x20,
-
-	/*
-	 * Well-known domain relative sub-authority values (RIDs).
-	 */
-
-	/* Users. */
-	DOMAIN_USER_RID_ADMIN		  = 0x1f4,
-	DOMAIN_USER_RID_GUEST		  = 0x1f5,
-	DOMAIN_USER_RID_KRBTGT		  = 0x1f6,
-
-	/* Groups. */
-	DOMAIN_GROUP_RID_ADMINS		  = 0x200,
-	DOMAIN_GROUP_RID_USERS		  = 0x201,
-	DOMAIN_GROUP_RID_GUESTS		  = 0x202,
-	DOMAIN_GROUP_RID_COMPUTERS	  = 0x203,
-	DOMAIN_GROUP_RID_CONTROLLERS	  = 0x204,
-	DOMAIN_GROUP_RID_CERT_ADMINS	  = 0x205,
-	DOMAIN_GROUP_RID_SCHEMA_ADMINS	  = 0x206,
-	DOMAIN_GROUP_RID_ENTERPRISE_ADMINS= 0x207,
-	DOMAIN_GROUP_RID_POLICY_ADMINS	  = 0x208,
-
-	/* Aliases. */
-	DOMAIN_ALIAS_RID_ADMINS		  = 0x220,
-	DOMAIN_ALIAS_RID_USERS		  = 0x221,
-	DOMAIN_ALIAS_RID_GUESTS		  = 0x222,
-	DOMAIN_ALIAS_RID_POWER_USERS	  = 0x223,
-
-	DOMAIN_ALIAS_RID_ACCOUNT_OPS	  = 0x224,
-	DOMAIN_ALIAS_RID_SYSTEM_OPS	  = 0x225,
-	DOMAIN_ALIAS_RID_PRINT_OPS	  = 0x226,
-	DOMAIN_ALIAS_RID_BACKUP_OPS	  = 0x227,
-
-	DOMAIN_ALIAS_RID_REPLICATOR	  = 0x228,
-	DOMAIN_ALIAS_RID_RAS_SERVERS	  = 0x229,
-	DOMAIN_ALIAS_RID_PREW2KCOMPACCESS = 0x22a,
-} RELATIVE_IDENTIFIERS;
-
-/*
- * The universal well-known SIDs:
- *
- *	NULL_SID			S-1-0-0
- *	WORLD_SID			S-1-1-0
- *	LOCAL_SID			S-1-2-0
- *	CREATOR_OWNER_SID		S-1-3-0
- *	CREATOR_GROUP_SID		S-1-3-1
- *	CREATOR_OWNER_SERVER_SID	S-1-3-2
- *	CREATOR_GROUP_SERVER_SID	S-1-3-3
- *
- *	(Non-unique IDs)		S-1-4
- *
- * NT well-known SIDs:
- *
- *	NT_AUTHORITY_SID	S-1-5
- *	DIALUP_SID		S-1-5-1
- *
- *	NETWORD_SID		S-1-5-2
- *	BATCH_SID		S-1-5-3
- *	INTERACTIVE_SID		S-1-5-4
- *	SERVICE_SID		S-1-5-6
- *	ANONYMOUS_LOGON_SID	S-1-5-7		(aka null logon session)
- *	PROXY_SID		S-1-5-8
- *	SERVER_LOGON_SID	S-1-5-9		(aka domain controller account)
- *	SELF_SID		S-1-5-10	(self RID)
- *	AUTHENTICATED_USER_SID	S-1-5-11
- *	RESTRICTED_CODE_SID	S-1-5-12	(running restricted code)
- *	TERMINAL_SERVER_SID	S-1-5-13	(running on terminal server)
- *
- *	(Logon IDs)		S-1-5-5-X-Y
- *
- *	(NT non-unique IDs)	S-1-5-0x15-...
- *
- *	(Built-in domain)	S-1-5-0x20
- */
-
-/*
- * The SID_IDENTIFIER_AUTHORITY is a 48-bit value used in the SID structure.
- *
- * NOTE: This is stored as a big endian number, hence the high_part comes
- * before the low_part.
- */
-typedef union {
-	struct {
-		u16 high_part;	/* High 16-bits. */
-		u32 low_part;	/* Low 32-bits. */
-	} __attribute__ ((__packed__)) parts;
-	u8 value[6];		/* Value as individual bytes. */
-} __attribute__ ((__packed__)) SID_IDENTIFIER_AUTHORITY;
-
-/*
- * The SID structure is a variable-length structure used to uniquely identify
- * users or groups. SID stands for security identifier.
- *
- * The standard textual representation of the SID is of the form:
- *	S-R-I-S-S...
- * Where:
- *    - The first "S" is the literal character 'S' identifying the following
- *	digits as a SID.
- *    - R is the revision level of the SID expressed as a sequence of digits
- *	either in decimal or hexadecimal (if the later, prefixed by "0x").
- *    - I is the 48-bit identifier_authority, expressed as digits as R above.
- *    - S... is one or more sub_authority values, expressed as digits as above.
- *
- * Example SID; the domain-relative SID of the local Administrators group on
- * Windows NT/2k:
- *	S-1-5-32-544
- * This translates to a SID with:
- *	revision = 1,
- *	sub_authority_count = 2,
- *	identifier_authority = {0,0,0,0,0,5},	// SECURITY_NT_AUTHORITY
- *	sub_authority[0] = 32,			// SECURITY_BUILTIN_DOMAIN_RID
- *	sub_authority[1] = 544			// DOMAIN_ALIAS_RID_ADMINS
- */
-typedef struct {
-	u8 revision;
-	u8 sub_authority_count;
-	SID_IDENTIFIER_AUTHORITY identifier_authority;
-	le32 sub_authority[1];		/* At least one sub_authority. */
-} __attribute__ ((__packed__)) SID;
-
-/*
- * Current constants for SIDs.
- */
-typedef enum {
-	SID_REVISION			=  1,	/* Current revision level. */
-	SID_MAX_SUB_AUTHORITIES		= 15,	/* Maximum number of those. */
-	SID_RECOMMENDED_SUB_AUTHORITIES	=  1,	/* Will change to around 6 in
-						   a future revision. */
-} SID_CONSTANTS;
-
-/*
- * The predefined ACE types (8-bit, see below).
- */
-enum {
-	ACCESS_MIN_MS_ACE_TYPE		= 0,
-	ACCESS_ALLOWED_ACE_TYPE		= 0,
-	ACCESS_DENIED_ACE_TYPE		= 1,
-	SYSTEM_AUDIT_ACE_TYPE		= 2,
-	SYSTEM_ALARM_ACE_TYPE		= 3, /* Not implemented as of Win2k. */
-	ACCESS_MAX_MS_V2_ACE_TYPE	= 3,
-
-	ACCESS_ALLOWED_COMPOUND_ACE_TYPE= 4,
-	ACCESS_MAX_MS_V3_ACE_TYPE	= 4,
-
-	/* The following are Win2k only. */
-	ACCESS_MIN_MS_OBJECT_ACE_TYPE	= 5,
-	ACCESS_ALLOWED_OBJECT_ACE_TYPE	= 5,
-	ACCESS_DENIED_OBJECT_ACE_TYPE	= 6,
-	SYSTEM_AUDIT_OBJECT_ACE_TYPE	= 7,
-	SYSTEM_ALARM_OBJECT_ACE_TYPE	= 8,
-	ACCESS_MAX_MS_OBJECT_ACE_TYPE	= 8,
-
-	ACCESS_MAX_MS_V4_ACE_TYPE	= 8,
-
-	/* This one is for WinNT/2k. */
-	ACCESS_MAX_MS_ACE_TYPE		= 8,
-} __attribute__ ((__packed__));
-
-typedef u8 ACE_TYPES;
-
-/*
- * The ACE flags (8-bit) for audit and inheritance (see below).
- *
- * SUCCESSFUL_ACCESS_ACE_FLAG is only used with system audit and alarm ACE
- * types to indicate that a message is generated (in Windows!) for successful
- * accesses.
- *
- * FAILED_ACCESS_ACE_FLAG is only used with system audit and alarm ACE types
- * to indicate that a message is generated (in Windows!) for failed accesses.
- */
-enum {
-	/* The inheritance flags. */
-	OBJECT_INHERIT_ACE		= 0x01,
-	CONTAINER_INHERIT_ACE		= 0x02,
-	NO_PROPAGATE_INHERIT_ACE	= 0x04,
-	INHERIT_ONLY_ACE		= 0x08,
-	INHERITED_ACE			= 0x10,	/* Win2k only. */
-	VALID_INHERIT_FLAGS		= 0x1f,
-
-	/* The audit flags. */
-	SUCCESSFUL_ACCESS_ACE_FLAG	= 0x40,
-	FAILED_ACCESS_ACE_FLAG		= 0x80,
-} __attribute__ ((__packed__));
-
-typedef u8 ACE_FLAGS;
-
-/*
- * An ACE is an access-control entry in an access-control list (ACL).
- * An ACE defines access to an object for a specific user or group or defines
- * the types of access that generate system-administration messages or alarms
- * for a specific user or group. The user or group is identified by a security
- * identifier (SID).
- *
- * Each ACE starts with an ACE_HEADER structure (aligned on 4-byte boundary),
- * which specifies the type and size of the ACE. The format of the subsequent
- * data depends on the ACE type.
- */
-typedef struct {
-/*Ofs*/
-/*  0*/	ACE_TYPES type;		/* Type of the ACE. */
-/*  1*/	ACE_FLAGS flags;	/* Flags describing the ACE. */
-/*  2*/	le16 size;		/* Size in bytes of the ACE. */
-} __attribute__ ((__packed__)) ACE_HEADER;
-
-/*
- * The access mask (32-bit). Defines the access rights.
- *
- * The specific rights (bits 0 to 15).  These depend on the type of the object
- * being secured by the ACE.
- */
-enum {
-	/* Specific rights for files and directories are as follows: */
-
-	/* Right to read data from the file. (FILE) */
-	FILE_READ_DATA			= cpu_to_le32(0x00000001),
-	/* Right to list contents of a directory. (DIRECTORY) */
-	FILE_LIST_DIRECTORY		= cpu_to_le32(0x00000001),
-
-	/* Right to write data to the file. (FILE) */
-	FILE_WRITE_DATA			= cpu_to_le32(0x00000002),
-	/* Right to create a file in the directory. (DIRECTORY) */
-	FILE_ADD_FILE			= cpu_to_le32(0x00000002),
-
-	/* Right to append data to the file. (FILE) */
-	FILE_APPEND_DATA		= cpu_to_le32(0x00000004),
-	/* Right to create a subdirectory. (DIRECTORY) */
-	FILE_ADD_SUBDIRECTORY		= cpu_to_le32(0x00000004),
-
-	/* Right to read extended attributes. (FILE/DIRECTORY) */
-	FILE_READ_EA			= cpu_to_le32(0x00000008),
-
-	/* Right to write extended attributes. (FILE/DIRECTORY) */
-	FILE_WRITE_EA			= cpu_to_le32(0x00000010),
-
-	/* Right to execute a file. (FILE) */
-	FILE_EXECUTE			= cpu_to_le32(0x00000020),
-	/* Right to traverse the directory. (DIRECTORY) */
-	FILE_TRAVERSE			= cpu_to_le32(0x00000020),
-
-	/*
-	 * Right to delete a directory and all the files it contains (its
-	 * children), even if the files are read-only. (DIRECTORY)
-	 */
-	FILE_DELETE_CHILD		= cpu_to_le32(0x00000040),
-
-	/* Right to read file attributes. (FILE/DIRECTORY) */
-	FILE_READ_ATTRIBUTES		= cpu_to_le32(0x00000080),
-
-	/* Right to change file attributes. (FILE/DIRECTORY) */
-	FILE_WRITE_ATTRIBUTES		= cpu_to_le32(0x00000100),
-
-	/*
-	 * The standard rights (bits 16 to 23).  These are independent of the
-	 * type of object being secured.
-	 */
-
-	/* Right to delete the object. */
-	DELETE				= cpu_to_le32(0x00010000),
-
-	/*
-	 * Right to read the information in the object's security descriptor,
-	 * not including the information in the SACL, i.e. right to read the
-	 * security descriptor and owner.
-	 */
-	READ_CONTROL			= cpu_to_le32(0x00020000),
-
-	/* Right to modify the DACL in the object's security descriptor. */
-	WRITE_DAC			= cpu_to_le32(0x00040000),
-
-	/* Right to change the owner in the object's security descriptor. */
-	WRITE_OWNER			= cpu_to_le32(0x00080000),
-
-	/*
-	 * Right to use the object for synchronization.  Enables a process to
-	 * wait until the object is in the signalled state.  Some object types
-	 * do not support this access right.
-	 */
-	SYNCHRONIZE			= cpu_to_le32(0x00100000),
-
-	/*
-	 * The following STANDARD_RIGHTS_* are combinations of the above for
-	 * convenience and are defined by the Win32 API.
-	 */
-
-	/* These are currently defined to READ_CONTROL. */
-	STANDARD_RIGHTS_READ		= cpu_to_le32(0x00020000),
-	STANDARD_RIGHTS_WRITE		= cpu_to_le32(0x00020000),
-	STANDARD_RIGHTS_EXECUTE		= cpu_to_le32(0x00020000),
-
-	/* Combines DELETE, READ_CONTROL, WRITE_DAC, and WRITE_OWNER access. */
-	STANDARD_RIGHTS_REQUIRED	= cpu_to_le32(0x000f0000),
-
-	/*
-	 * Combines DELETE, READ_CONTROL, WRITE_DAC, WRITE_OWNER, and
-	 * SYNCHRONIZE access.
-	 */
-	STANDARD_RIGHTS_ALL		= cpu_to_le32(0x001f0000),
-
-	/*
-	 * The access system ACL and maximum allowed access types (bits 24 to
-	 * 25, bits 26 to 27 are reserved).
-	 */
-	ACCESS_SYSTEM_SECURITY		= cpu_to_le32(0x01000000),
-	MAXIMUM_ALLOWED			= cpu_to_le32(0x02000000),
-
-	/*
-	 * The generic rights (bits 28 to 31).  These map onto the standard and
-	 * specific rights.
-	 */
-
-	/* Read, write, and execute access. */
-	GENERIC_ALL			= cpu_to_le32(0x10000000),
-
-	/* Execute access. */
-	GENERIC_EXECUTE			= cpu_to_le32(0x20000000),
-
-	/*
-	 * Write access.  For files, this maps onto:
-	 *	FILE_APPEND_DATA | FILE_WRITE_ATTRIBUTES | FILE_WRITE_DATA |
-	 *	FILE_WRITE_EA | STANDARD_RIGHTS_WRITE | SYNCHRONIZE
-	 * For directories, the mapping has the same numerical value.  See
-	 * above for the descriptions of the rights granted.
-	 */
-	GENERIC_WRITE			= cpu_to_le32(0x40000000),
-
-	/*
-	 * Read access.  For files, this maps onto:
-	 *	FILE_READ_ATTRIBUTES | FILE_READ_DATA | FILE_READ_EA |
-	 *	STANDARD_RIGHTS_READ | SYNCHRONIZE
-	 * For directories, the mapping has the same numberical value.  See
-	 * above for the descriptions of the rights granted.
-	 */
-	GENERIC_READ			= cpu_to_le32(0x80000000),
-};
-
-typedef le32 ACCESS_MASK;
-
-/*
- * The generic mapping array. Used to denote the mapping of each generic
- * access right to a specific access mask.
- *
- * FIXME: What exactly is this and what is it for? (AIA)
- */
-typedef struct {
-	ACCESS_MASK generic_read;
-	ACCESS_MASK generic_write;
-	ACCESS_MASK generic_execute;
-	ACCESS_MASK generic_all;
-} __attribute__ ((__packed__)) GENERIC_MAPPING;
-
-/*
- * The predefined ACE type structures are as defined below.
- */
-
-/*
- * ACCESS_ALLOWED_ACE, ACCESS_DENIED_ACE, SYSTEM_AUDIT_ACE, SYSTEM_ALARM_ACE
- */
-typedef struct {
-/*  0	ACE_HEADER; -- Unfolded here as gcc doesn't like unnamed structs. */
-	ACE_TYPES type;		/* Type of the ACE. */
-	ACE_FLAGS flags;	/* Flags describing the ACE. */
-	le16 size;		/* Size in bytes of the ACE. */
-/*  4*/	ACCESS_MASK mask;	/* Access mask associated with the ACE. */
-
-/*  8*/	SID sid;		/* The SID associated with the ACE. */
-} __attribute__ ((__packed__)) ACCESS_ALLOWED_ACE, ACCESS_DENIED_ACE,
-			       SYSTEM_AUDIT_ACE, SYSTEM_ALARM_ACE;
-
-/*
- * The object ACE flags (32-bit).
- */
-enum {
-	ACE_OBJECT_TYPE_PRESENT			= cpu_to_le32(1),
-	ACE_INHERITED_OBJECT_TYPE_PRESENT	= cpu_to_le32(2),
-};
-
-typedef le32 OBJECT_ACE_FLAGS;
-
-typedef struct {
-/*  0	ACE_HEADER; -- Unfolded here as gcc doesn't like unnamed structs. */
-	ACE_TYPES type;		/* Type of the ACE. */
-	ACE_FLAGS flags;	/* Flags describing the ACE. */
-	le16 size;		/* Size in bytes of the ACE. */
-/*  4*/	ACCESS_MASK mask;	/* Access mask associated with the ACE. */
-
-/*  8*/	OBJECT_ACE_FLAGS object_flags;	/* Flags describing the object ACE. */
-/* 12*/	GUID object_type;
-/* 28*/	GUID inherited_object_type;
-
-/* 44*/	SID sid;		/* The SID associated with the ACE. */
-} __attribute__ ((__packed__)) ACCESS_ALLOWED_OBJECT_ACE,
-			       ACCESS_DENIED_OBJECT_ACE,
-			       SYSTEM_AUDIT_OBJECT_ACE,
-			       SYSTEM_ALARM_OBJECT_ACE;
-
-/*
- * An ACL is an access-control list (ACL).
- * An ACL starts with an ACL header structure, which specifies the size of
- * the ACL and the number of ACEs it contains. The ACL header is followed by
- * zero or more access control entries (ACEs). The ACL as well as each ACE
- * are aligned on 4-byte boundaries.
- */
-typedef struct {
-	u8 revision;	/* Revision of this ACL. */
-	u8 alignment1;
-	le16 size;	/* Allocated space in bytes for ACL. Includes this
-			   header, the ACEs and the remaining free space. */
-	le16 ace_count;	/* Number of ACEs in the ACL. */
-	le16 alignment2;
-/* sizeof() = 8 bytes */
-} __attribute__ ((__packed__)) ACL;
-
-/*
- * Current constants for ACLs.
- */
-typedef enum {
-	/* Current revision. */
-	ACL_REVISION		= 2,
-	ACL_REVISION_DS		= 4,
-
-	/* History of revisions. */
-	ACL_REVISION1		= 1,
-	MIN_ACL_REVISION	= 2,
-	ACL_REVISION2		= 2,
-	ACL_REVISION3		= 3,
-	ACL_REVISION4		= 4,
-	MAX_ACL_REVISION	= 4,
-} ACL_CONSTANTS;
-
-/*
- * The security descriptor control flags (16-bit).
- *
- * SE_OWNER_DEFAULTED - This boolean flag, when set, indicates that the SID
- *	pointed to by the Owner field was provided by a defaulting mechanism
- *	rather than explicitly provided by the original provider of the
- *	security descriptor.  This may affect the treatment of the SID with
- *	respect to inheritance of an owner.
- *
- * SE_GROUP_DEFAULTED - This boolean flag, when set, indicates that the SID in
- *	the Group field was provided by a defaulting mechanism rather than
- *	explicitly provided by the original provider of the security
- *	descriptor.  This may affect the treatment of the SID with respect to
- *	inheritance of a primary group.
- *
- * SE_DACL_PRESENT - This boolean flag, when set, indicates that the security
- *	descriptor contains a discretionary ACL.  If this flag is set and the
- *	Dacl field of the SECURITY_DESCRIPTOR is null, then a null ACL is
- *	explicitly being specified.
- *
- * SE_DACL_DEFAULTED - This boolean flag, when set, indicates that the ACL
- *	pointed to by the Dacl field was provided by a defaulting mechanism
- *	rather than explicitly provided by the original provider of the
- *	security descriptor.  This may affect the treatment of the ACL with
- *	respect to inheritance of an ACL.  This flag is ignored if the
- *	DaclPresent flag is not set.
- *
- * SE_SACL_PRESENT - This boolean flag, when set,  indicates that the security
- *	descriptor contains a system ACL pointed to by the Sacl field.  If this
- *	flag is set and the Sacl field of the SECURITY_DESCRIPTOR is null, then
- *	an empty (but present) ACL is being specified.
- *
- * SE_SACL_DEFAULTED - This boolean flag, when set, indicates that the ACL
- *	pointed to by the Sacl field was provided by a defaulting mechanism
- *	rather than explicitly provided by the original provider of the
- *	security descriptor.  This may affect the treatment of the ACL with
- *	respect to inheritance of an ACL.  This flag is ignored if the
- *	SaclPresent flag is not set.
- *
- * SE_SELF_RELATIVE - This boolean flag, when set, indicates that the security
- *	descriptor is in self-relative form.  In this form, all fields of the
- *	security descriptor are contiguous in memory and all pointer fields are
- *	expressed as offsets from the beginning of the security descriptor.
- */
-enum {
-	SE_OWNER_DEFAULTED		= cpu_to_le16(0x0001),
-	SE_GROUP_DEFAULTED		= cpu_to_le16(0x0002),
-	SE_DACL_PRESENT			= cpu_to_le16(0x0004),
-	SE_DACL_DEFAULTED		= cpu_to_le16(0x0008),
-
-	SE_SACL_PRESENT			= cpu_to_le16(0x0010),
-	SE_SACL_DEFAULTED		= cpu_to_le16(0x0020),
-
-	SE_DACL_AUTO_INHERIT_REQ	= cpu_to_le16(0x0100),
-	SE_SACL_AUTO_INHERIT_REQ	= cpu_to_le16(0x0200),
-	SE_DACL_AUTO_INHERITED		= cpu_to_le16(0x0400),
-	SE_SACL_AUTO_INHERITED		= cpu_to_le16(0x0800),
-
-	SE_DACL_PROTECTED		= cpu_to_le16(0x1000),
-	SE_SACL_PROTECTED		= cpu_to_le16(0x2000),
-	SE_RM_CONTROL_VALID		= cpu_to_le16(0x4000),
-	SE_SELF_RELATIVE		= cpu_to_le16(0x8000)
-} __attribute__ ((__packed__));
-
-typedef le16 SECURITY_DESCRIPTOR_CONTROL;
-
-/*
- * Self-relative security descriptor. Contains the owner and group SIDs as well
- * as the sacl and dacl ACLs inside the security descriptor itself.
- */
-typedef struct {
-	u8 revision;	/* Revision level of the security descriptor. */
-	u8 alignment;
-	SECURITY_DESCRIPTOR_CONTROL control; /* Flags qualifying the type of
-			   the descriptor as well as the following fields. */
-	le32 owner;	/* Byte offset to a SID representing an object's
-			   owner. If this is NULL, no owner SID is present in
-			   the descriptor. */
-	le32 group;	/* Byte offset to a SID representing an object's
-			   primary group. If this is NULL, no primary group
-			   SID is present in the descriptor. */
-	le32 sacl;	/* Byte offset to a system ACL. Only valid, if
-			   SE_SACL_PRESENT is set in the control field. If
-			   SE_SACL_PRESENT is set but sacl is NULL, a NULL ACL
-			   is specified. */
-	le32 dacl;	/* Byte offset to a discretionary ACL. Only valid, if
-			   SE_DACL_PRESENT is set in the control field. If
-			   SE_DACL_PRESENT is set but dacl is NULL, a NULL ACL
-			   (unconditionally granting access) is specified. */
-/* sizeof() = 0x14 bytes */
-} __attribute__ ((__packed__)) SECURITY_DESCRIPTOR_RELATIVE;
-
-/*
- * Absolute security descriptor. Does not contain the owner and group SIDs, nor
- * the sacl and dacl ACLs inside the security descriptor. Instead, it contains
- * pointers to these structures in memory. Obviously, absolute security
- * descriptors are only useful for in memory representations of security
- * descriptors. On disk, a self-relative security descriptor is used.
- */
-typedef struct {
-	u8 revision;	/* Revision level of the security descriptor. */
-	u8 alignment;
-	SECURITY_DESCRIPTOR_CONTROL control;	/* Flags qualifying the type of
-			   the descriptor as well as the following fields. */
-	SID *owner;	/* Points to a SID representing an object's owner. If
-			   this is NULL, no owner SID is present in the
-			   descriptor. */
-	SID *group;	/* Points to a SID representing an object's primary
-			   group. If this is NULL, no primary group SID is
-			   present in the descriptor. */
-	ACL *sacl;	/* Points to a system ACL. Only valid, if
-			   SE_SACL_PRESENT is set in the control field. If
-			   SE_SACL_PRESENT is set but sacl is NULL, a NULL ACL
-			   is specified. */
-	ACL *dacl;	/* Points to a discretionary ACL. Only valid, if
-			   SE_DACL_PRESENT is set in the control field. If
-			   SE_DACL_PRESENT is set but dacl is NULL, a NULL ACL
-			   (unconditionally granting access) is specified. */
-} __attribute__ ((__packed__)) SECURITY_DESCRIPTOR;
-
-/*
- * Current constants for security descriptors.
- */
-typedef enum {
-	/* Current revision. */
-	SECURITY_DESCRIPTOR_REVISION	= 1,
-	SECURITY_DESCRIPTOR_REVISION1	= 1,
-
-	/* The sizes of both the absolute and relative security descriptors is
-	   the same as pointers, at least on ia32 architecture are 32-bit. */
-	SECURITY_DESCRIPTOR_MIN_LENGTH	= sizeof(SECURITY_DESCRIPTOR),
-} SECURITY_DESCRIPTOR_CONSTANTS;
-
-/*
- * Attribute: Security descriptor (0x50). A standard self-relative security
- * descriptor.
- *
- * NOTE: Can be resident or non-resident.
- * NOTE: Not used in NTFS 3.0+, as security descriptors are stored centrally
- * in FILE_Secure and the correct descriptor is found using the security_id
- * from the standard information attribute.
- */
-typedef SECURITY_DESCRIPTOR_RELATIVE SECURITY_DESCRIPTOR_ATTR;
-
-/*
- * On NTFS 3.0+, all security descriptors are stored in FILE_Secure. Only one
- * referenced instance of each unique security descriptor is stored.
- *
- * FILE_Secure contains no unnamed data attribute, i.e. it has zero length. It
- * does, however, contain two indexes ($SDH and $SII) as well as a named data
- * stream ($SDS).
- *
- * Every unique security descriptor is assigned a unique security identifier
- * (security_id, not to be confused with a SID). The security_id is unique for
- * the NTFS volume and is used as an index into the $SII index, which maps
- * security_ids to the security descriptor's storage location within the $SDS
- * data attribute. The $SII index is sorted by ascending security_id.
- *
- * A simple hash is computed from each security descriptor. This hash is used
- * as an index into the $SDH index, which maps security descriptor hashes to
- * the security descriptor's storage location within the $SDS data attribute.
- * The $SDH index is sorted by security descriptor hash and is stored in a B+
- * tree. When searching $SDH (with the intent of determining whether or not a
- * new security descriptor is already present in the $SDS data stream), if a
- * matching hash is found, but the security descriptors do not match, the
- * search in the $SDH index is continued, searching for a next matching hash.
- *
- * When a precise match is found, the security_id coresponding to the security
- * descriptor in the $SDS attribute is read from the found $SDH index entry and
- * is stored in the $STANDARD_INFORMATION attribute of the file/directory to
- * which the security descriptor is being applied. The $STANDARD_INFORMATION
- * attribute is present in all base mft records (i.e. in all files and
- * directories).
- *
- * If a match is not found, the security descriptor is assigned a new unique
- * security_id and is added to the $SDS data attribute. Then, entries
- * referencing the this security descriptor in the $SDS data attribute are
- * added to the $SDH and $SII indexes.
- *
- * Note: Entries are never deleted from FILE_Secure, even if nothing
- * references an entry any more.
- */
-
-/*
- * This header precedes each security descriptor in the $SDS data stream.
- * This is also the index entry data part of both the $SII and $SDH indexes.
- */
-typedef struct {
-	le32 hash;	  /* Hash of the security descriptor. */
-	le32 security_id; /* The security_id assigned to the descriptor. */
-	le64 offset;	  /* Byte offset of this entry in the $SDS stream. */
-	le32 length;	  /* Size in bytes of this entry in $SDS stream. */
-} __attribute__ ((__packed__)) SECURITY_DESCRIPTOR_HEADER;
-
-/*
- * The $SDS data stream contains the security descriptors, aligned on 16-byte
- * boundaries, sorted by security_id in a B+ tree. Security descriptors cannot
- * cross 256kib boundaries (this restriction is imposed by the Windows cache
- * manager). Each security descriptor is contained in a SDS_ENTRY structure.
- * Also, each security descriptor is stored twice in the $SDS stream with a
- * fixed offset of 0x40000 bytes (256kib, the Windows cache manager's max size)
- * between them; i.e. if a SDS_ENTRY specifies an offset of 0x51d0, then the
- * first copy of the security descriptor will be at offset 0x51d0 in the
- * $SDS data stream and the second copy will be at offset 0x451d0.
- */
-typedef struct {
-/*Ofs*/
-/*  0	SECURITY_DESCRIPTOR_HEADER; -- Unfolded here as gcc doesn't like
-				       unnamed structs. */
-	le32 hash;	  /* Hash of the security descriptor. */
-	le32 security_id; /* The security_id assigned to the descriptor. */
-	le64 offset;	  /* Byte offset of this entry in the $SDS stream. */
-	le32 length;	  /* Size in bytes of this entry in $SDS stream. */
-/* 20*/	SECURITY_DESCRIPTOR_RELATIVE sid; /* The self-relative security
-					     descriptor. */
-} __attribute__ ((__packed__)) SDS_ENTRY;
-
-/*
- * The index entry key used in the $SII index. The collation type is
- * COLLATION_NTOFS_ULONG.
- */
-typedef struct {
-	le32 security_id; /* The security_id assigned to the descriptor. */
-} __attribute__ ((__packed__)) SII_INDEX_KEY;
-
-/*
- * The index entry key used in the $SDH index. The keys are sorted first by
- * hash and then by security_id. The collation rule is
- * COLLATION_NTOFS_SECURITY_HASH.
- */
-typedef struct {
-	le32 hash;	  /* Hash of the security descriptor. */
-	le32 security_id; /* The security_id assigned to the descriptor. */
-} __attribute__ ((__packed__)) SDH_INDEX_KEY;
-
-/*
- * Attribute: Volume name (0x60).
- *
- * NOTE: Always resident.
- * NOTE: Present only in FILE_Volume.
- */
-typedef struct {
-	ntfschar name[0];	/* The name of the volume in Unicode. */
-} __attribute__ ((__packed__)) VOLUME_NAME;
-
-/*
- * Possible flags for the volume (16-bit).
- */
-enum {
-	VOLUME_IS_DIRTY			= cpu_to_le16(0x0001),
-	VOLUME_RESIZE_LOG_FILE		= cpu_to_le16(0x0002),
-	VOLUME_UPGRADE_ON_MOUNT		= cpu_to_le16(0x0004),
-	VOLUME_MOUNTED_ON_NT4		= cpu_to_le16(0x0008),
-
-	VOLUME_DELETE_USN_UNDERWAY	= cpu_to_le16(0x0010),
-	VOLUME_REPAIR_OBJECT_ID		= cpu_to_le16(0x0020),
-
-	VOLUME_CHKDSK_UNDERWAY		= cpu_to_le16(0x4000),
-	VOLUME_MODIFIED_BY_CHKDSK	= cpu_to_le16(0x8000),
-
-	VOLUME_FLAGS_MASK		= cpu_to_le16(0xc03f),
-
-	/* To make our life easier when checking if we must mount read-only. */
-	VOLUME_MUST_MOUNT_RO_MASK	= cpu_to_le16(0xc027),
-} __attribute__ ((__packed__));
-
-typedef le16 VOLUME_FLAGS;
-
-/*
- * Attribute: Volume information (0x70).
- *
- * NOTE: Always resident.
- * NOTE: Present only in FILE_Volume.
- * NOTE: Windows 2000 uses NTFS 3.0 while Windows NT4 service pack 6a uses
- *	 NTFS 1.2. I haven't personally seen other values yet.
- */
-typedef struct {
-	le64 reserved;		/* Not used (yet?). */
-	u8 major_ver;		/* Major version of the ntfs format. */
-	u8 minor_ver;		/* Minor version of the ntfs format. */
-	VOLUME_FLAGS flags;	/* Bit array of VOLUME_* flags. */
-} __attribute__ ((__packed__)) VOLUME_INFORMATION;
-
-/*
- * Attribute: Data attribute (0x80).
- *
- * NOTE: Can be resident or non-resident.
- *
- * Data contents of a file (i.e. the unnamed stream) or of a named stream.
- */
-typedef struct {
-	u8 data[0];		/* The file's data contents. */
-} __attribute__ ((__packed__)) DATA_ATTR;
-
-/*
- * Index header flags (8-bit).
- */
-enum {
-	/*
-	 * When index header is in an index root attribute:
-	 */
-	SMALL_INDEX = 0, /* The index is small enough to fit inside the index
-			    root attribute and there is no index allocation
-			    attribute present. */
-	LARGE_INDEX = 1, /* The index is too large to fit in the index root
-			    attribute and/or an index allocation attribute is
-			    present. */
-	/*
-	 * When index header is in an index block, i.e. is part of index
-	 * allocation attribute:
-	 */
-	LEAF_NODE  = 0, /* This is a leaf node, i.e. there are no more nodes
-			   branching off it. */
-	INDEX_NODE = 1, /* This node indexes other nodes, i.e. it is not a leaf
-			   node. */
-	NODE_MASK  = 1, /* Mask for accessing the *_NODE bits. */
-} __attribute__ ((__packed__));
-
-typedef u8 INDEX_HEADER_FLAGS;
-
-/*
- * This is the header for indexes, describing the INDEX_ENTRY records, which
- * follow the INDEX_HEADER. Together the index header and the index entries
- * make up a complete index.
- *
- * IMPORTANT NOTE: The offset, length and size structure members are counted
- * relative to the start of the index header structure and not relative to the
- * start of the index root or index allocation structures themselves.
- */
-typedef struct {
-	le32 entries_offset;		/* Byte offset to first INDEX_ENTRY
-					   aligned to 8-byte boundary. */
-	le32 index_length;		/* Data size of the index in bytes,
-					   i.e. bytes used from allocated
-					   size, aligned to 8-byte boundary. */
-	le32 allocated_size;		/* Byte size of this index (block),
-					   multiple of 8 bytes. */
-	/* NOTE: For the index root attribute, the above two numbers are always
-	   equal, as the attribute is resident and it is resized as needed. In
-	   the case of the index allocation attribute the attribute is not
-	   resident and hence the allocated_size is a fixed value and must
-	   equal the index_block_size specified by the INDEX_ROOT attribute
-	   corresponding to the INDEX_ALLOCATION attribute this INDEX_BLOCK
-	   belongs to. */
-	INDEX_HEADER_FLAGS flags;	/* Bit field of INDEX_HEADER_FLAGS. */
-	u8 reserved[3];			/* Reserved/align to 8-byte boundary. */
-} __attribute__ ((__packed__)) INDEX_HEADER;
-
-/*
- * Attribute: Index root (0x90).
- *
- * NOTE: Always resident.
- *
- * This is followed by a sequence of index entries (INDEX_ENTRY structures)
- * as described by the index header.
- *
- * When a directory is small enough to fit inside the index root then this
- * is the only attribute describing the directory. When the directory is too
- * large to fit in the index root, on the other hand, two additional attributes
- * are present: an index allocation attribute, containing sub-nodes of the B+
- * directory tree (see below), and a bitmap attribute, describing which virtual
- * cluster numbers (vcns) in the index allocation attribute are in use by an
- * index block.
- *
- * NOTE: The root directory (FILE_root) contains an entry for itself. Other
- * directories do not contain entries for themselves, though.
- */
-typedef struct {
-	ATTR_TYPE type;			/* Type of the indexed attribute. Is
-					   $FILE_NAME for directories, zero
-					   for view indexes. No other values
-					   allowed. */
-	COLLATION_RULE collation_rule;	/* Collation rule used to sort the
-					   index entries. If type is $FILE_NAME,
-					   this must be COLLATION_FILE_NAME. */
-	le32 index_block_size;		/* Size of each index block in bytes (in
-					   the index allocation attribute). */
-	u8 clusters_per_index_block;	/* Cluster size of each index block (in
-					   the index allocation attribute), when
-					   an index block is >= than a cluster,
-					   otherwise this will be the log of
-					   the size (like how the encoding of
-					   the mft record size and the index
-					   record size found in the boot sector
-					   work). Has to be a power of 2. */
-	u8 reserved[3];			/* Reserved/align to 8-byte boundary. */
-	INDEX_HEADER index;		/* Index header describing the
-					   following index entries. */
-} __attribute__ ((__packed__)) INDEX_ROOT;
-
-/*
- * Attribute: Index allocation (0xa0).
- *
- * NOTE: Always non-resident (doesn't make sense to be resident anyway!).
- *
- * This is an array of index blocks. Each index block starts with an
- * INDEX_BLOCK structure containing an index header, followed by a sequence of
- * index entries (INDEX_ENTRY structures), as described by the INDEX_HEADER.
- */
-typedef struct {
-/*  0	NTFS_RECORD; -- Unfolded here as gcc doesn't like unnamed structs. */
-	NTFS_RECORD_TYPE magic;	/* Magic is "INDX". */
-	le16 usa_ofs;		/* See NTFS_RECORD definition. */
-	le16 usa_count;		/* See NTFS_RECORD definition. */
-
-/*  8*/	sle64 lsn;		/* $LogFile sequence number of the last
-				   modification of this index block. */
-/* 16*/	leVCN index_block_vcn;	/* Virtual cluster number of the index block.
-				   If the cluster_size on the volume is <= the
-				   index_block_size of the directory,
-				   index_block_vcn counts in units of clusters,
-				   and in units of sectors otherwise. */
-/* 24*/	INDEX_HEADER index;	/* Describes the following index entries. */
-/* sizeof()= 40 (0x28) bytes */
-/*
- * When creating the index block, we place the update sequence array at this
- * offset, i.e. before we start with the index entries. This also makes sense,
- * otherwise we could run into problems with the update sequence array
- * containing in itself the last two bytes of a sector which would mean that
- * multi sector transfer protection wouldn't work. As you can't protect data
- * by overwriting it since you then can't get it back...
- * When reading use the data from the ntfs record header.
- */
-} __attribute__ ((__packed__)) INDEX_BLOCK;
-
-typedef INDEX_BLOCK INDEX_ALLOCATION;
-
-/*
- * The system file FILE_Extend/$Reparse contains an index named $R listing
- * all reparse points on the volume. The index entry keys are as defined
- * below. Note, that there is no index data associated with the index entries.
- *
- * The index entries are sorted by the index key file_id. The collation rule is
- * COLLATION_NTOFS_ULONGS. FIXME: Verify whether the reparse_tag is not the
- * primary key / is not a key at all. (AIA)
- */
-typedef struct {
-	le32 reparse_tag;	/* Reparse point type (inc. flags). */
-	leMFT_REF file_id;	/* Mft record of the file containing the
-				   reparse point attribute. */
-} __attribute__ ((__packed__)) REPARSE_INDEX_KEY;
-
-/*
- * Quota flags (32-bit).
- *
- * The user quota flags.  Names explain meaning.
- */
-enum {
-	QUOTA_FLAG_DEFAULT_LIMITS	= cpu_to_le32(0x00000001),
-	QUOTA_FLAG_LIMIT_REACHED	= cpu_to_le32(0x00000002),
-	QUOTA_FLAG_ID_DELETED		= cpu_to_le32(0x00000004),
-
-	QUOTA_FLAG_USER_MASK		= cpu_to_le32(0x00000007),
-	/* This is a bit mask for the user quota flags. */
-
-	/*
-	 * These flags are only present in the quota defaults index entry, i.e.
-	 * in the entry where owner_id = QUOTA_DEFAULTS_ID.
-	 */
-	QUOTA_FLAG_TRACKING_ENABLED	= cpu_to_le32(0x00000010),
-	QUOTA_FLAG_ENFORCEMENT_ENABLED	= cpu_to_le32(0x00000020),
-	QUOTA_FLAG_TRACKING_REQUESTED	= cpu_to_le32(0x00000040),
-	QUOTA_FLAG_LOG_THRESHOLD	= cpu_to_le32(0x00000080),
-
-	QUOTA_FLAG_LOG_LIMIT		= cpu_to_le32(0x00000100),
-	QUOTA_FLAG_OUT_OF_DATE		= cpu_to_le32(0x00000200),
-	QUOTA_FLAG_CORRUPT		= cpu_to_le32(0x00000400),
-	QUOTA_FLAG_PENDING_DELETES	= cpu_to_le32(0x00000800),
-};
-
-typedef le32 QUOTA_FLAGS;
-
-/*
- * The system file FILE_Extend/$Quota contains two indexes $O and $Q. Quotas
- * are on a per volume and per user basis.
- *
- * The $Q index contains one entry for each existing user_id on the volume. The
- * index key is the user_id of the user/group owning this quota control entry,
- * i.e. the key is the owner_id. The user_id of the owner of a file, i.e. the
- * owner_id, is found in the standard information attribute. The collation rule
- * for $Q is COLLATION_NTOFS_ULONG.
- *
- * The $O index contains one entry for each user/group who has been assigned
- * a quota on that volume. The index key holds the SID of the user_id the
- * entry belongs to, i.e. the owner_id. The collation rule for $O is
- * COLLATION_NTOFS_SID.
- *
- * The $O index entry data is the user_id of the user corresponding to the SID.
- * This user_id is used as an index into $Q to find the quota control entry
- * associated with the SID.
- *
- * The $Q index entry data is the quota control entry and is defined below.
- */
-typedef struct {
-	le32 version;		/* Currently equals 2. */
-	QUOTA_FLAGS flags;	/* Flags describing this quota entry. */
-	le64 bytes_used;	/* How many bytes of the quota are in use. */
-	sle64 change_time;	/* Last time this quota entry was changed. */
-	sle64 threshold;	/* Soft quota (-1 if not limited). */
-	sle64 limit;		/* Hard quota (-1 if not limited). */
-	sle64 exceeded_time;	/* How long the soft quota has been exceeded. */
-	SID sid;		/* The SID of the user/object associated with
-				   this quota entry.  Equals zero for the quota
-				   defaults entry (and in fact on a WinXP
-				   volume, it is not present at all). */
-} __attribute__ ((__packed__)) QUOTA_CONTROL_ENTRY;
-
-/*
- * Predefined owner_id values (32-bit).
- */
-enum {
-	QUOTA_INVALID_ID	= cpu_to_le32(0x00000000),
-	QUOTA_DEFAULTS_ID	= cpu_to_le32(0x00000001),
-	QUOTA_FIRST_USER_ID	= cpu_to_le32(0x00000100),
-};
-
-/*
- * Current constants for quota control entries.
- */
-typedef enum {
-	/* Current version. */
-	QUOTA_VERSION	= 2,
-} QUOTA_CONTROL_ENTRY_CONSTANTS;
-
-/*
- * Index entry flags (16-bit).
- */
-enum {
-	INDEX_ENTRY_NODE = cpu_to_le16(1), /* This entry contains a
-			sub-node, i.e. a reference to an index block in form of
-			a virtual cluster number (see below). */
-	INDEX_ENTRY_END  = cpu_to_le16(2), /* This signifies the last
-			entry in an index block.  The index entry does not
-			represent a file but it can point to a sub-node. */
-
-	INDEX_ENTRY_SPACE_FILLER = cpu_to_le16(0xffff), /* gcc: Force
-			enum bit width to 16-bit. */
-} __attribute__ ((__packed__));
-
-typedef le16 INDEX_ENTRY_FLAGS;
-
-/*
- * This the index entry header (see below).
- */
-typedef struct {
-/*  0*/	union {
-		struct { /* Only valid when INDEX_ENTRY_END is not set. */
-			leMFT_REF indexed_file;	/* The mft reference of the file
-						   described by this index
-						   entry. Used for directory
-						   indexes. */
-		} __attribute__ ((__packed__)) dir;
-		struct { /* Used for views/indexes to find the entry's data. */
-			le16 data_offset;	/* Data byte offset from this
-						   INDEX_ENTRY. Follows the
-						   index key. */
-			le16 data_length;	/* Data length in bytes. */
-			le32 reservedV;		/* Reserved (zero). */
-		} __attribute__ ((__packed__)) vi;
-	} __attribute__ ((__packed__)) data;
-/*  8*/	le16 length;		 /* Byte size of this index entry, multiple of
-				    8-bytes. */
-/* 10*/	le16 key_length;	 /* Byte size of the key value, which is in the
-				    index entry. It follows field reserved. Not
-				    multiple of 8-bytes. */
-/* 12*/	INDEX_ENTRY_FLAGS flags; /* Bit field of INDEX_ENTRY_* flags. */
-/* 14*/	le16 reserved;		 /* Reserved/align to 8-byte boundary. */
-/* sizeof() = 16 bytes */
-} __attribute__ ((__packed__)) INDEX_ENTRY_HEADER;
-
-/*
- * This is an index entry. A sequence of such entries follows each INDEX_HEADER
- * structure. Together they make up a complete index. The index follows either
- * an index root attribute or an index allocation attribute.
- *
- * NOTE: Before NTFS 3.0 only filename attributes were indexed.
- */
-typedef struct {
-/*Ofs*/
-/*  0	INDEX_ENTRY_HEADER; -- Unfolded here as gcc dislikes unnamed structs. */
-	union {
-		struct { /* Only valid when INDEX_ENTRY_END is not set. */
-			leMFT_REF indexed_file;	/* The mft reference of the file
-						   described by this index
-						   entry. Used for directory
-						   indexes. */
-		} __attribute__ ((__packed__)) dir;
-		struct { /* Used for views/indexes to find the entry's data. */
-			le16 data_offset;	/* Data byte offset from this
-						   INDEX_ENTRY. Follows the
-						   index key. */
-			le16 data_length;	/* Data length in bytes. */
-			le32 reservedV;		/* Reserved (zero). */
-		} __attribute__ ((__packed__)) vi;
-	} __attribute__ ((__packed__)) data;
-	le16 length;		 /* Byte size of this index entry, multiple of
-				    8-bytes. */
-	le16 key_length;	 /* Byte size of the key value, which is in the
-				    index entry. It follows field reserved. Not
-				    multiple of 8-bytes. */
-	INDEX_ENTRY_FLAGS flags; /* Bit field of INDEX_ENTRY_* flags. */
-	le16 reserved;		 /* Reserved/align to 8-byte boundary. */
-
-/* 16*/	union {		/* The key of the indexed attribute. NOTE: Only present
-			   if INDEX_ENTRY_END bit in flags is not set. NOTE: On
-			   NTFS versions before 3.0 the only valid key is the
-			   FILE_NAME_ATTR. On NTFS 3.0+ the following
-			   additional index keys are defined: */
-		FILE_NAME_ATTR file_name;/* $I30 index in directories. */
-		SII_INDEX_KEY sii;	/* $SII index in $Secure. */
-		SDH_INDEX_KEY sdh;	/* $SDH index in $Secure. */
-		GUID object_id;		/* $O index in FILE_Extend/$ObjId: The
-					   object_id of the mft record found in
-					   the data part of the index. */
-		REPARSE_INDEX_KEY reparse;	/* $R index in
-						   FILE_Extend/$Reparse. */
-		SID sid;		/* $O index in FILE_Extend/$Quota:
-					   SID of the owner of the user_id. */
-		le32 owner_id;		/* $Q index in FILE_Extend/$Quota:
-					   user_id of the owner of the quota
-					   control entry in the data part of
-					   the index. */
-	} __attribute__ ((__packed__)) key;
-	/* The (optional) index data is inserted here when creating. */
-	// leVCN vcn;	/* If INDEX_ENTRY_NODE bit in flags is set, the last
-	//		   eight bytes of this index entry contain the virtual
-	//		   cluster number of the index block that holds the
-	//		   entries immediately preceding the current entry (the
-	//		   vcn references the corresponding cluster in the data
-	//		   of the non-resident index allocation attribute). If
-	//		   the key_length is zero, then the vcn immediately
-	//		   follows the INDEX_ENTRY_HEADER. Regardless of
-	//		   key_length, the address of the 8-byte boundary
-	//		   aligned vcn of INDEX_ENTRY{_HEADER} *ie is given by
-	//		   (char*)ie + le16_to_cpu(ie*)->length) - sizeof(VCN),
-	//		   where sizeof(VCN) can be hardcoded as 8 if wanted. */
-} __attribute__ ((__packed__)) INDEX_ENTRY;
-
-/*
- * Attribute: Bitmap (0xb0).
- *
- * Contains an array of bits (aka a bitfield).
- *
- * When used in conjunction with the index allocation attribute, each bit
- * corresponds to one index block within the index allocation attribute. Thus
- * the number of bits in the bitmap * index block size / cluster size is the
- * number of clusters in the index allocation attribute.
- */
-typedef struct {
-	u8 bitmap[0];			/* Array of bits. */
-} __attribute__ ((__packed__)) BITMAP_ATTR;
-
-/*
- * The reparse point tag defines the type of the reparse point. It also
- * includes several flags, which further describe the reparse point.
- *
- * The reparse point tag is an unsigned 32-bit value divided in three parts:
- *
- * 1. The least significant 16 bits (i.e. bits 0 to 15) specifiy the type of
- *    the reparse point.
- * 2. The 13 bits after this (i.e. bits 16 to 28) are reserved for future use.
- * 3. The most significant three bits are flags describing the reparse point.
- *    They are defined as follows:
- *	bit 29: Name surrogate bit. If set, the filename is an alias for
- *		another object in the system.
- *	bit 30: High-latency bit. If set, accessing the first byte of data will
- *		be slow. (E.g. the data is stored on a tape drive.)
- *	bit 31: Microsoft bit. If set, the tag is owned by Microsoft. User
- *		defined tags have to use zero here.
- *
- * These are the predefined reparse point tags:
- */
-enum {
-	IO_REPARSE_TAG_IS_ALIAS		= cpu_to_le32(0x20000000),
-	IO_REPARSE_TAG_IS_HIGH_LATENCY	= cpu_to_le32(0x40000000),
-	IO_REPARSE_TAG_IS_MICROSOFT	= cpu_to_le32(0x80000000),
-
-	IO_REPARSE_TAG_RESERVED_ZERO	= cpu_to_le32(0x00000000),
-	IO_REPARSE_TAG_RESERVED_ONE	= cpu_to_le32(0x00000001),
-	IO_REPARSE_TAG_RESERVED_RANGE	= cpu_to_le32(0x00000001),
-
-	IO_REPARSE_TAG_NSS		= cpu_to_le32(0x68000005),
-	IO_REPARSE_TAG_NSS_RECOVER	= cpu_to_le32(0x68000006),
-	IO_REPARSE_TAG_SIS		= cpu_to_le32(0x68000007),
-	IO_REPARSE_TAG_DFS		= cpu_to_le32(0x68000008),
-
-	IO_REPARSE_TAG_MOUNT_POINT	= cpu_to_le32(0x88000003),
-
-	IO_REPARSE_TAG_HSM		= cpu_to_le32(0xa8000004),
-
-	IO_REPARSE_TAG_SYMBOLIC_LINK	= cpu_to_le32(0xe8000000),
-
-	IO_REPARSE_TAG_VALID_VALUES	= cpu_to_le32(0xe000ffff),
-};
-
-/*
- * Attribute: Reparse point (0xc0).
- *
- * NOTE: Can be resident or non-resident.
- */
-typedef struct {
-	le32 reparse_tag;		/* Reparse point type (inc. flags). */
-	le16 reparse_data_length;	/* Byte size of reparse data. */
-	le16 reserved;			/* Align to 8-byte boundary. */
-	u8 reparse_data[0];		/* Meaning depends on reparse_tag. */
-} __attribute__ ((__packed__)) REPARSE_POINT;
-
-/*
- * Attribute: Extended attribute (EA) information (0xd0).
- *
- * NOTE: Always resident. (Is this true???)
- */
-typedef struct {
-	le16 ea_length;		/* Byte size of the packed extended
-				   attributes. */
-	le16 need_ea_count;	/* The number of extended attributes which have
-				   the NEED_EA bit set. */
-	le32 ea_query_length;	/* Byte size of the buffer required to query
-				   the extended attributes when calling
-				   ZwQueryEaFile() in Windows NT/2k. I.e. the
-				   byte size of the unpacked extended
-				   attributes. */
-} __attribute__ ((__packed__)) EA_INFORMATION;
-
-/*
- * Extended attribute flags (8-bit).
- */
-enum {
-	NEED_EA	= 0x80		/* If set the file to which the EA belongs
-				   cannot be interpreted without understanding
-				   the associates extended attributes. */
-} __attribute__ ((__packed__));
-
-typedef u8 EA_FLAGS;
-
-/*
- * Attribute: Extended attribute (EA) (0xe0).
- *
- * NOTE: Can be resident or non-resident.
- *
- * Like the attribute list and the index buffer list, the EA attribute value is
- * a sequence of EA_ATTR variable length records.
- */
-typedef struct {
-	le32 next_entry_offset;	/* Offset to the next EA_ATTR. */
-	EA_FLAGS flags;		/* Flags describing the EA. */
-	u8 ea_name_length;	/* Length of the name of the EA in bytes
-				   excluding the '\0' byte terminator. */
-	le16 ea_value_length;	/* Byte size of the EA's value. */
-	u8 ea_name[0];		/* Name of the EA.  Note this is ASCII, not
-				   Unicode and it is zero terminated. */
-	u8 ea_value[0];		/* The value of the EA.  Immediately follows
-				   the name. */
-} __attribute__ ((__packed__)) EA_ATTR;
-
-/*
- * Attribute: Property set (0xf0).
- *
- * Intended to support Native Structure Storage (NSS) - a feature removed from
- * NTFS 3.0 during beta testing.
- */
-typedef struct {
-	/* Irrelevant as feature unused. */
-} __attribute__ ((__packed__)) PROPERTY_SET;
-
-/*
- * Attribute: Logged utility stream (0x100).
- *
- * NOTE: Can be resident or non-resident.
- *
- * Operations on this attribute are logged to the journal ($LogFile) like
- * normal metadata changes.
- *
- * Used by the Encrypting File System (EFS). All encrypted files have this
- * attribute with the name $EFS.
- */
-typedef struct {
-	/* Can be anything the creator chooses. */
-	/* EFS uses it as follows: */
-	// FIXME: Type this info, verifying it along the way. (AIA)
-} __attribute__ ((__packed__)) LOGGED_UTILITY_STREAM, EFS_ATTR;
-
-#endif /* _LINUX_NTFS_LAYOUT_H */
diff --git a/fs/ntfs/lcnalloc.c b/fs/ntfs/lcnalloc.c
deleted file mode 100644
index eda9972e6159..000000000000
--- a/fs/ntfs/lcnalloc.c
+++ /dev/null
@@ -1,1000 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * lcnalloc.c - Cluster (de)allocation code.  Part of the Linux-NTFS project.
- *
- * Copyright (c) 2004-2005 Anton Altaparmakov
- */
-
-#ifdef NTFS_RW
-
-#include <linux/pagemap.h>
-
-#include "lcnalloc.h"
-#include "debug.h"
-#include "bitmap.h"
-#include "inode.h"
-#include "volume.h"
-#include "attrib.h"
-#include "malloc.h"
-#include "aops.h"
-#include "ntfs.h"
-
-/**
- * ntfs_cluster_free_from_rl_nolock - free clusters from runlist
- * @vol:	mounted ntfs volume on which to free the clusters
- * @rl:		runlist describing the clusters to free
- *
- * Free all the clusters described by the runlist @rl on the volume @vol.  In
- * the case of an error being returned, at least some of the clusters were not
- * freed.
- *
- * Return 0 on success and -errno on error.
- *
- * Locking: - The volume lcn bitmap must be locked for writing on entry and is
- *	      left locked on return.
- */
-int ntfs_cluster_free_from_rl_nolock(ntfs_volume *vol,
-		const runlist_element *rl)
-{
-	struct inode *lcnbmp_vi = vol->lcnbmp_ino;
-	int ret = 0;
-
-	ntfs_debug("Entering.");
-	if (!rl)
-		return 0;
-	for (; rl->length; rl++) {
-		int err;
-
-		if (rl->lcn < 0)
-			continue;
-		err = ntfs_bitmap_clear_run(lcnbmp_vi, rl->lcn, rl->length);
-		if (unlikely(err && (!ret || ret == -ENOMEM) && ret != err))
-			ret = err;
-	}
-	ntfs_debug("Done.");
-	return ret;
-}
-
-/**
- * ntfs_cluster_alloc - allocate clusters on an ntfs volume
- * @vol:	mounted ntfs volume on which to allocate the clusters
- * @start_vcn:	vcn to use for the first allocated cluster
- * @count:	number of clusters to allocate
- * @start_lcn:	starting lcn at which to allocate the clusters (or -1 if none)
- * @zone:	zone from which to allocate the clusters
- * @is_extension:	if 'true', this is an attribute extension
- *
- * Allocate @count clusters preferably starting at cluster @start_lcn or at the
- * current allocator position if @start_lcn is -1, on the mounted ntfs volume
- * @vol. @zone is either DATA_ZONE for allocation of normal clusters or
- * MFT_ZONE for allocation of clusters for the master file table, i.e. the
- * $MFT/$DATA attribute.
- *
- * @start_vcn specifies the vcn of the first allocated cluster.  This makes
- * merging the resulting runlist with the old runlist easier.
- *
- * If @is_extension is 'true', the caller is allocating clusters to extend an
- * attribute and if it is 'false', the caller is allocating clusters to fill a
- * hole in an attribute.  Practically the difference is that if @is_extension
- * is 'true' the returned runlist will be terminated with LCN_ENOENT and if
- * @is_extension is 'false' the runlist will be terminated with
- * LCN_RL_NOT_MAPPED.
- *
- * You need to check the return value with IS_ERR().  If this is false, the
- * function was successful and the return value is a runlist describing the
- * allocated cluster(s).  If IS_ERR() is true, the function failed and
- * PTR_ERR() gives you the error code.
- *
- * Notes on the allocation algorithm
- * =================================
- *
- * There are two data zones.  First is the area between the end of the mft zone
- * and the end of the volume, and second is the area between the start of the
- * volume and the start of the mft zone.  On unmodified/standard NTFS 1.x
- * volumes, the second data zone does not exist due to the mft zone being
- * expanded to cover the start of the volume in order to reserve space for the
- * mft bitmap attribute.
- *
- * This is not the prettiest function but the complexity stems from the need of
- * implementing the mft vs data zoned approach and from the fact that we have
- * access to the lcn bitmap in portions of up to 8192 bytes at a time, so we
- * need to cope with crossing over boundaries of two buffers.  Further, the
- * fact that the allocator allows for caller supplied hints as to the location
- * of where allocation should begin and the fact that the allocator keeps track
- * of where in the data zones the next natural allocation should occur,
- * contribute to the complexity of the function.  But it should all be
- * worthwhile, because this allocator should: 1) be a full implementation of
- * the MFT zone approach used by Windows NT, 2) cause reduction in
- * fragmentation, and 3) be speedy in allocations (the code is not optimized
- * for speed, but the algorithm is, so further speed improvements are probably
- * possible).
- *
- * FIXME: We should be monitoring cluster allocation and increment the MFT zone
- * size dynamically but this is something for the future.  We will just cause
- * heavier fragmentation by not doing it and I am not even sure Windows would
- * grow the MFT zone dynamically, so it might even be correct not to do this.
- * The overhead in doing dynamic MFT zone expansion would be very large and
- * unlikely worth the effort. (AIA)
- *
- * TODO: I have added in double the required zone position pointer wrap around
- * logic which can be optimized to having only one of the two logic sets.
- * However, having the double logic will work fine, but if we have only one of
- * the sets and we get it wrong somewhere, then we get into trouble, so
- * removing the duplicate logic requires _very_ careful consideration of _all_
- * possible code paths.  So at least for now, I am leaving the double logic -
- * better safe than sorry... (AIA)
- *
- * Locking: - The volume lcn bitmap must be unlocked on entry and is unlocked
- *	      on return.
- *	    - This function takes the volume lcn bitmap lock for writing and
- *	      modifies the bitmap contents.
- */
-runlist_element *ntfs_cluster_alloc(ntfs_volume *vol, const VCN start_vcn,
-		const s64 count, const LCN start_lcn,
-		const NTFS_CLUSTER_ALLOCATION_ZONES zone,
-		const bool is_extension)
-{
-	LCN zone_start, zone_end, bmp_pos, bmp_initial_pos, last_read_pos, lcn;
-	LCN prev_lcn = 0, prev_run_len = 0, mft_zone_size;
-	s64 clusters;
-	loff_t i_size;
-	struct inode *lcnbmp_vi;
-	runlist_element *rl = NULL;
-	struct address_space *mapping;
-	struct page *page = NULL;
-	u8 *buf, *byte;
-	int err = 0, rlpos, rlsize, buf_size;
-	u8 pass, done_zones, search_zone, need_writeback = 0, bit;
-
-	ntfs_debug("Entering for start_vcn 0x%llx, count 0x%llx, start_lcn "
-			"0x%llx, zone %s_ZONE.", (unsigned long long)start_vcn,
-			(unsigned long long)count,
-			(unsigned long long)start_lcn,
-			zone == MFT_ZONE ? "MFT" : "DATA");
-	BUG_ON(!vol);
-	lcnbmp_vi = vol->lcnbmp_ino;
-	BUG_ON(!lcnbmp_vi);
-	BUG_ON(start_vcn < 0);
-	BUG_ON(count < 0);
-	BUG_ON(start_lcn < -1);
-	BUG_ON(zone < FIRST_ZONE);
-	BUG_ON(zone > LAST_ZONE);
-
-	/* Return NULL if @count is zero. */
-	if (!count)
-		return NULL;
-	/* Take the lcnbmp lock for writing. */
-	down_write(&vol->lcnbmp_lock);
-	/*
-	 * If no specific @start_lcn was requested, use the current data zone
-	 * position, otherwise use the requested @start_lcn but make sure it
-	 * lies outside the mft zone.  Also set done_zones to 0 (no zones done)
-	 * and pass depending on whether we are starting inside a zone (1) or
-	 * at the beginning of a zone (2).  If requesting from the MFT_ZONE,
-	 * we either start at the current position within the mft zone or at
-	 * the specified position.  If the latter is out of bounds then we start
-	 * at the beginning of the MFT_ZONE.
-	 */
-	done_zones = 0;
-	pass = 1;
-	/*
-	 * zone_start and zone_end are the current search range.  search_zone
-	 * is 1 for mft zone, 2 for data zone 1 (end of mft zone till end of
-	 * volume) and 4 for data zone 2 (start of volume till start of mft
-	 * zone).
-	 */
-	zone_start = start_lcn;
-	if (zone_start < 0) {
-		if (zone == DATA_ZONE)
-			zone_start = vol->data1_zone_pos;
-		else
-			zone_start = vol->mft_zone_pos;
-		if (!zone_start) {
-			/*
-			 * Zone starts at beginning of volume which means a
-			 * single pass is sufficient.
-			 */
-			pass = 2;
-		}
-	} else if (zone == DATA_ZONE && zone_start >= vol->mft_zone_start &&
-			zone_start < vol->mft_zone_end) {
-		zone_start = vol->mft_zone_end;
-		/*
-		 * Starting at beginning of data1_zone which means a single
-		 * pass in this zone is sufficient.
-		 */
-		pass = 2;
-	} else if (zone == MFT_ZONE && (zone_start < vol->mft_zone_start ||
-			zone_start >= vol->mft_zone_end)) {
-		zone_start = vol->mft_lcn;
-		if (!vol->mft_zone_end)
-			zone_start = 0;
-		/*
-		 * Starting at beginning of volume which means a single pass
-		 * is sufficient.
-		 */
-		pass = 2;
-	}
-	if (zone == MFT_ZONE) {
-		zone_end = vol->mft_zone_end;
-		search_zone = 1;
-	} else /* if (zone == DATA_ZONE) */ {
-		/* Skip searching the mft zone. */
-		done_zones |= 1;
-		if (zone_start >= vol->mft_zone_end) {
-			zone_end = vol->nr_clusters;
-			search_zone = 2;
-		} else {
-			zone_end = vol->mft_zone_start;
-			search_zone = 4;
-		}
-	}
-	/*
-	 * bmp_pos is the current bit position inside the bitmap.  We use
-	 * bmp_initial_pos to determine whether or not to do a zone switch.
-	 */
-	bmp_pos = bmp_initial_pos = zone_start;
-
-	/* Loop until all clusters are allocated, i.e. clusters == 0. */
-	clusters = count;
-	rlpos = rlsize = 0;
-	mapping = lcnbmp_vi->i_mapping;
-	i_size = i_size_read(lcnbmp_vi);
-	while (1) {
-		ntfs_debug("Start of outer while loop: done_zones 0x%x, "
-				"search_zone %i, pass %i, zone_start 0x%llx, "
-				"zone_end 0x%llx, bmp_initial_pos 0x%llx, "
-				"bmp_pos 0x%llx, rlpos %i, rlsize %i.",
-				done_zones, search_zone, pass,
-				(unsigned long long)zone_start,
-				(unsigned long long)zone_end,
-				(unsigned long long)bmp_initial_pos,
-				(unsigned long long)bmp_pos, rlpos, rlsize);
-		/* Loop until we run out of free clusters. */
-		last_read_pos = bmp_pos >> 3;
-		ntfs_debug("last_read_pos 0x%llx.",
-				(unsigned long long)last_read_pos);
-		if (last_read_pos > i_size) {
-			ntfs_debug("End of attribute reached.  "
-					"Skipping to zone_pass_done.");
-			goto zone_pass_done;
-		}
-		if (likely(page)) {
-			if (need_writeback) {
-				ntfs_debug("Marking page dirty.");
-				flush_dcache_page(page);
-				set_page_dirty(page);
-				need_writeback = 0;
-			}
-			ntfs_unmap_page(page);
-		}
-		page = ntfs_map_page(mapping, last_read_pos >>
-				PAGE_SHIFT);
-		if (IS_ERR(page)) {
-			err = PTR_ERR(page);
-			ntfs_error(vol->sb, "Failed to map page.");
-			goto out;
-		}
-		buf_size = last_read_pos & ~PAGE_MASK;
-		buf = page_address(page) + buf_size;
-		buf_size = PAGE_SIZE - buf_size;
-		if (unlikely(last_read_pos + buf_size > i_size))
-			buf_size = i_size - last_read_pos;
-		buf_size <<= 3;
-		lcn = bmp_pos & 7;
-		bmp_pos &= ~(LCN)7;
-		ntfs_debug("Before inner while loop: buf_size %i, lcn 0x%llx, "
-				"bmp_pos 0x%llx, need_writeback %i.", buf_size,
-				(unsigned long long)lcn,
-				(unsigned long long)bmp_pos, need_writeback);
-		while (lcn < buf_size && lcn + bmp_pos < zone_end) {
-			byte = buf + (lcn >> 3);
-			ntfs_debug("In inner while loop: buf_size %i, "
-					"lcn 0x%llx, bmp_pos 0x%llx, "
-					"need_writeback %i, byte ofs 0x%x, "
-					"*byte 0x%x.", buf_size,
-					(unsigned long long)lcn,
-					(unsigned long long)bmp_pos,
-					need_writeback,
-					(unsigned int)(lcn >> 3),
-					(unsigned int)*byte);
-			/* Skip full bytes. */
-			if (*byte == 0xff) {
-				lcn = (lcn + 8) & ~(LCN)7;
-				ntfs_debug("Continuing while loop 1.");
-				continue;
-			}
-			bit = 1 << (lcn & 7);
-			ntfs_debug("bit 0x%x.", bit);
-			/* If the bit is already set, go onto the next one. */
-			if (*byte & bit) {
-				lcn++;
-				ntfs_debug("Continuing while loop 2.");
-				continue;
-			}
-			/*
-			 * Allocate more memory if needed, including space for
-			 * the terminator element.
-			 * ntfs_malloc_nofs() operates on whole pages only.
-			 */
-			if ((rlpos + 2) * sizeof(*rl) > rlsize) {
-				runlist_element *rl2;
-
-				ntfs_debug("Reallocating memory.");
-				if (!rl)
-					ntfs_debug("First free bit is at LCN "
-							"0x%llx.",
-							(unsigned long long)
-							(lcn + bmp_pos));
-				rl2 = ntfs_malloc_nofs(rlsize + (int)PAGE_SIZE);
-				if (unlikely(!rl2)) {
-					err = -ENOMEM;
-					ntfs_error(vol->sb, "Failed to "
-							"allocate memory.");
-					goto out;
-				}
-				memcpy(rl2, rl, rlsize);
-				ntfs_free(rl);
-				rl = rl2;
-				rlsize += PAGE_SIZE;
-				ntfs_debug("Reallocated memory, rlsize 0x%x.",
-						rlsize);
-			}
-			/* Allocate the bitmap bit. */
-			*byte |= bit;
-			/* We need to write this bitmap page to disk. */
-			need_writeback = 1;
-			ntfs_debug("*byte 0x%x, need_writeback is set.",
-					(unsigned int)*byte);
-			/*
-			 * Coalesce with previous run if adjacent LCNs.
-			 * Otherwise, append a new run.
-			 */
-			ntfs_debug("Adding run (lcn 0x%llx, len 0x%llx), "
-					"prev_lcn 0x%llx, lcn 0x%llx, "
-					"bmp_pos 0x%llx, prev_run_len 0x%llx, "
-					"rlpos %i.",
-					(unsigned long long)(lcn + bmp_pos),
-					1ULL, (unsigned long long)prev_lcn,
-					(unsigned long long)lcn,
-					(unsigned long long)bmp_pos,
-					(unsigned long long)prev_run_len,
-					rlpos);
-			if (prev_lcn == lcn + bmp_pos - prev_run_len && rlpos) {
-				ntfs_debug("Coalescing to run (lcn 0x%llx, "
-						"len 0x%llx).",
-						(unsigned long long)
-						rl[rlpos - 1].lcn,
-						(unsigned long long)
-						rl[rlpos - 1].length);
-				rl[rlpos - 1].length = ++prev_run_len;
-				ntfs_debug("Run now (lcn 0x%llx, len 0x%llx), "
-						"prev_run_len 0x%llx.",
-						(unsigned long long)
-						rl[rlpos - 1].lcn,
-						(unsigned long long)
-						rl[rlpos - 1].length,
-						(unsigned long long)
-						prev_run_len);
-			} else {
-				if (likely(rlpos)) {
-					ntfs_debug("Adding new run, (previous "
-							"run lcn 0x%llx, "
-							"len 0x%llx).",
-							(unsigned long long)
-							rl[rlpos - 1].lcn,
-							(unsigned long long)
-							rl[rlpos - 1].length);
-					rl[rlpos].vcn = rl[rlpos - 1].vcn +
-							prev_run_len;
-				} else {
-					ntfs_debug("Adding new run, is first "
-							"run.");
-					rl[rlpos].vcn = start_vcn;
-				}
-				rl[rlpos].lcn = prev_lcn = lcn + bmp_pos;
-				rl[rlpos].length = prev_run_len = 1;
-				rlpos++;
-			}
-			/* Done? */
-			if (!--clusters) {
-				LCN tc;
-				/*
-				 * Update the current zone position.  Positions
-				 * of already scanned zones have been updated
-				 * during the respective zone switches.
-				 */
-				tc = lcn + bmp_pos + 1;
-				ntfs_debug("Done. Updating current zone "
-						"position, tc 0x%llx, "
-						"search_zone %i.",
-						(unsigned long long)tc,
-						search_zone);
-				switch (search_zone) {
-				case 1:
-					ntfs_debug("Before checks, "
-							"vol->mft_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->mft_zone_pos);
-					if (tc >= vol->mft_zone_end) {
-						vol->mft_zone_pos =
-								vol->mft_lcn;
-						if (!vol->mft_zone_end)
-							vol->mft_zone_pos = 0;
-					} else if ((bmp_initial_pos >=
-							vol->mft_zone_pos ||
-							tc > vol->mft_zone_pos)
-							&& tc >= vol->mft_lcn)
-						vol->mft_zone_pos = tc;
-					ntfs_debug("After checks, "
-							"vol->mft_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->mft_zone_pos);
-					break;
-				case 2:
-					ntfs_debug("Before checks, "
-							"vol->data1_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->data1_zone_pos);
-					if (tc >= vol->nr_clusters)
-						vol->data1_zone_pos =
-							     vol->mft_zone_end;
-					else if ((bmp_initial_pos >=
-						    vol->data1_zone_pos ||
-						    tc > vol->data1_zone_pos)
-						    && tc >= vol->mft_zone_end)
-						vol->data1_zone_pos = tc;
-					ntfs_debug("After checks, "
-							"vol->data1_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->data1_zone_pos);
-					break;
-				case 4:
-					ntfs_debug("Before checks, "
-							"vol->data2_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->data2_zone_pos);
-					if (tc >= vol->mft_zone_start)
-						vol->data2_zone_pos = 0;
-					else if (bmp_initial_pos >=
-						      vol->data2_zone_pos ||
-						      tc > vol->data2_zone_pos)
-						vol->data2_zone_pos = tc;
-					ntfs_debug("After checks, "
-							"vol->data2_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->data2_zone_pos);
-					break;
-				default:
-					BUG();
-				}
-				ntfs_debug("Finished.  Going to out.");
-				goto out;
-			}
-			lcn++;
-		}
-		bmp_pos += buf_size;
-		ntfs_debug("After inner while loop: buf_size 0x%x, lcn "
-				"0x%llx, bmp_pos 0x%llx, need_writeback %i.",
-				buf_size, (unsigned long long)lcn,
-				(unsigned long long)bmp_pos, need_writeback);
-		if (bmp_pos < zone_end) {
-			ntfs_debug("Continuing outer while loop, "
-					"bmp_pos 0x%llx, zone_end 0x%llx.",
-					(unsigned long long)bmp_pos,
-					(unsigned long long)zone_end);
-			continue;
-		}
-zone_pass_done:	/* Finished with the current zone pass. */
-		ntfs_debug("At zone_pass_done, pass %i.", pass);
-		if (pass == 1) {
-			/*
-			 * Now do pass 2, scanning the first part of the zone
-			 * we omitted in pass 1.
-			 */
-			pass = 2;
-			zone_end = zone_start;
-			switch (search_zone) {
-			case 1: /* mft_zone */
-				zone_start = vol->mft_zone_start;
-				break;
-			case 2: /* data1_zone */
-				zone_start = vol->mft_zone_end;
-				break;
-			case 4: /* data2_zone */
-				zone_start = 0;
-				break;
-			default:
-				BUG();
-			}
-			/* Sanity check. */
-			if (zone_end < zone_start)
-				zone_end = zone_start;
-			bmp_pos = zone_start;
-			ntfs_debug("Continuing outer while loop, pass 2, "
-					"zone_start 0x%llx, zone_end 0x%llx, "
-					"bmp_pos 0x%llx.",
-					(unsigned long long)zone_start,
-					(unsigned long long)zone_end,
-					(unsigned long long)bmp_pos);
-			continue;
-		} /* pass == 2 */
-done_zones_check:
-		ntfs_debug("At done_zones_check, search_zone %i, done_zones "
-				"before 0x%x, done_zones after 0x%x.",
-				search_zone, done_zones,
-				done_zones | search_zone);
-		done_zones |= search_zone;
-		if (done_zones < 7) {
-			ntfs_debug("Switching zone.");
-			/* Now switch to the next zone we haven't done yet. */
-			pass = 1;
-			switch (search_zone) {
-			case 1:
-				ntfs_debug("Switching from mft zone to data1 "
-						"zone.");
-				/* Update mft zone position. */
-				if (rlpos) {
-					LCN tc;
-
-					ntfs_debug("Before checks, "
-							"vol->mft_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->mft_zone_pos);
-					tc = rl[rlpos - 1].lcn +
-							rl[rlpos - 1].length;
-					if (tc >= vol->mft_zone_end) {
-						vol->mft_zone_pos =
-								vol->mft_lcn;
-						if (!vol->mft_zone_end)
-							vol->mft_zone_pos = 0;
-					} else if ((bmp_initial_pos >=
-							vol->mft_zone_pos ||
-							tc > vol->mft_zone_pos)
-							&& tc >= vol->mft_lcn)
-						vol->mft_zone_pos = tc;
-					ntfs_debug("After checks, "
-							"vol->mft_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->mft_zone_pos);
-				}
-				/* Switch from mft zone to data1 zone. */
-switch_to_data1_zone:		search_zone = 2;
-				zone_start = bmp_initial_pos =
-						vol->data1_zone_pos;
-				zone_end = vol->nr_clusters;
-				if (zone_start == vol->mft_zone_end)
-					pass = 2;
-				if (zone_start >= zone_end) {
-					vol->data1_zone_pos = zone_start =
-							vol->mft_zone_end;
-					pass = 2;
-				}
-				break;
-			case 2:
-				ntfs_debug("Switching from data1 zone to "
-						"data2 zone.");
-				/* Update data1 zone position. */
-				if (rlpos) {
-					LCN tc;
-
-					ntfs_debug("Before checks, "
-							"vol->data1_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->data1_zone_pos);
-					tc = rl[rlpos - 1].lcn +
-							rl[rlpos - 1].length;
-					if (tc >= vol->nr_clusters)
-						vol->data1_zone_pos =
-							     vol->mft_zone_end;
-					else if ((bmp_initial_pos >=
-						    vol->data1_zone_pos ||
-						    tc > vol->data1_zone_pos)
-						    && tc >= vol->mft_zone_end)
-						vol->data1_zone_pos = tc;
-					ntfs_debug("After checks, "
-							"vol->data1_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->data1_zone_pos);
-				}
-				/* Switch from data1 zone to data2 zone. */
-				search_zone = 4;
-				zone_start = bmp_initial_pos =
-						vol->data2_zone_pos;
-				zone_end = vol->mft_zone_start;
-				if (!zone_start)
-					pass = 2;
-				if (zone_start >= zone_end) {
-					vol->data2_zone_pos = zone_start =
-							bmp_initial_pos = 0;
-					pass = 2;
-				}
-				break;
-			case 4:
-				ntfs_debug("Switching from data2 zone to "
-						"data1 zone.");
-				/* Update data2 zone position. */
-				if (rlpos) {
-					LCN tc;
-
-					ntfs_debug("Before checks, "
-							"vol->data2_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->data2_zone_pos);
-					tc = rl[rlpos - 1].lcn +
-							rl[rlpos - 1].length;
-					if (tc >= vol->mft_zone_start)
-						vol->data2_zone_pos = 0;
-					else if (bmp_initial_pos >=
-						      vol->data2_zone_pos ||
-						      tc > vol->data2_zone_pos)
-						vol->data2_zone_pos = tc;
-					ntfs_debug("After checks, "
-							"vol->data2_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->data2_zone_pos);
-				}
-				/* Switch from data2 zone to data1 zone. */
-				goto switch_to_data1_zone;
-			default:
-				BUG();
-			}
-			ntfs_debug("After zone switch, search_zone %i, "
-					"pass %i, bmp_initial_pos 0x%llx, "
-					"zone_start 0x%llx, zone_end 0x%llx.",
-					search_zone, pass,
-					(unsigned long long)bmp_initial_pos,
-					(unsigned long long)zone_start,
-					(unsigned long long)zone_end);
-			bmp_pos = zone_start;
-			if (zone_start == zone_end) {
-				ntfs_debug("Empty zone, going to "
-						"done_zones_check.");
-				/* Empty zone. Don't bother searching it. */
-				goto done_zones_check;
-			}
-			ntfs_debug("Continuing outer while loop.");
-			continue;
-		} /* done_zones == 7 */
-		ntfs_debug("All zones are finished.");
-		/*
-		 * All zones are finished!  If DATA_ZONE, shrink mft zone.  If
-		 * MFT_ZONE, we have really run out of space.
-		 */
-		mft_zone_size = vol->mft_zone_end - vol->mft_zone_start;
-		ntfs_debug("vol->mft_zone_start 0x%llx, vol->mft_zone_end "
-				"0x%llx, mft_zone_size 0x%llx.",
-				(unsigned long long)vol->mft_zone_start,
-				(unsigned long long)vol->mft_zone_end,
-				(unsigned long long)mft_zone_size);
-		if (zone == MFT_ZONE || mft_zone_size <= 0) {
-			ntfs_debug("No free clusters left, going to out.");
-			/* Really no more space left on device. */
-			err = -ENOSPC;
-			goto out;
-		} /* zone == DATA_ZONE && mft_zone_size > 0 */
-		ntfs_debug("Shrinking mft zone.");
-		zone_end = vol->mft_zone_end;
-		mft_zone_size >>= 1;
-		if (mft_zone_size > 0)
-			vol->mft_zone_end = vol->mft_zone_start + mft_zone_size;
-		else /* mft zone and data2 zone no longer exist. */
-			vol->data2_zone_pos = vol->mft_zone_start =
-					vol->mft_zone_end = 0;
-		if (vol->mft_zone_pos >= vol->mft_zone_end) {
-			vol->mft_zone_pos = vol->mft_lcn;
-			if (!vol->mft_zone_end)
-				vol->mft_zone_pos = 0;
-		}
-		bmp_pos = zone_start = bmp_initial_pos =
-				vol->data1_zone_pos = vol->mft_zone_end;
-		search_zone = 2;
-		pass = 2;
-		done_zones &= ~2;
-		ntfs_debug("After shrinking mft zone, mft_zone_size 0x%llx, "
-				"vol->mft_zone_start 0x%llx, "
-				"vol->mft_zone_end 0x%llx, "
-				"vol->mft_zone_pos 0x%llx, search_zone 2, "
-				"pass 2, dones_zones 0x%x, zone_start 0x%llx, "
-				"zone_end 0x%llx, vol->data1_zone_pos 0x%llx, "
-				"continuing outer while loop.",
-				(unsigned long long)mft_zone_size,
-				(unsigned long long)vol->mft_zone_start,
-				(unsigned long long)vol->mft_zone_end,
-				(unsigned long long)vol->mft_zone_pos,
-				done_zones, (unsigned long long)zone_start,
-				(unsigned long long)zone_end,
-				(unsigned long long)vol->data1_zone_pos);
-	}
-	ntfs_debug("After outer while loop.");
-out:
-	ntfs_debug("At out.");
-	/* Add runlist terminator element. */
-	if (likely(rl)) {
-		rl[rlpos].vcn = rl[rlpos - 1].vcn + rl[rlpos - 1].length;
-		rl[rlpos].lcn = is_extension ? LCN_ENOENT : LCN_RL_NOT_MAPPED;
-		rl[rlpos].length = 0;
-	}
-	if (likely(page && !IS_ERR(page))) {
-		if (need_writeback) {
-			ntfs_debug("Marking page dirty.");
-			flush_dcache_page(page);
-			set_page_dirty(page);
-			need_writeback = 0;
-		}
-		ntfs_unmap_page(page);
-	}
-	if (likely(!err)) {
-		up_write(&vol->lcnbmp_lock);
-		ntfs_debug("Done.");
-		return rl;
-	}
-	ntfs_error(vol->sb, "Failed to allocate clusters, aborting "
-			"(error %i).", err);
-	if (rl) {
-		int err2;
-
-		if (err == -ENOSPC)
-			ntfs_debug("Not enough space to complete allocation, "
-					"err -ENOSPC, first free lcn 0x%llx, "
-					"could allocate up to 0x%llx "
-					"clusters.",
-					(unsigned long long)rl[0].lcn,
-					(unsigned long long)(count - clusters));
-		/* Deallocate all allocated clusters. */
-		ntfs_debug("Attempting rollback...");
-		err2 = ntfs_cluster_free_from_rl_nolock(vol, rl);
-		if (err2) {
-			ntfs_error(vol->sb, "Failed to rollback (error %i).  "
-					"Leaving inconsistent metadata!  "
-					"Unmount and run chkdsk.", err2);
-			NVolSetErrors(vol);
-		}
-		/* Free the runlist. */
-		ntfs_free(rl);
-	} else if (err == -ENOSPC)
-		ntfs_debug("No space left at all, err = -ENOSPC, first free "
-				"lcn = 0x%llx.",
-				(long long)vol->data1_zone_pos);
-	up_write(&vol->lcnbmp_lock);
-	return ERR_PTR(err);
-}
-
-/**
- * __ntfs_cluster_free - free clusters on an ntfs volume
- * @ni:		ntfs inode whose runlist describes the clusters to free
- * @start_vcn:	vcn in the runlist of @ni at which to start freeing clusters
- * @count:	number of clusters to free or -1 for all clusters
- * @ctx:	active attribute search context if present or NULL if not
- * @is_rollback:	true if this is a rollback operation
- *
- * Free @count clusters starting at the cluster @start_vcn in the runlist
- * described by the vfs inode @ni.
- *
- * If @count is -1, all clusters from @start_vcn to the end of the runlist are
- * deallocated.  Thus, to completely free all clusters in a runlist, use
- * @start_vcn = 0 and @count = -1.
- *
- * If @ctx is specified, it is an active search context of @ni and its base mft
- * record.  This is needed when __ntfs_cluster_free() encounters unmapped
- * runlist fragments and allows their mapping.  If you do not have the mft
- * record mapped, you can specify @ctx as NULL and __ntfs_cluster_free() will
- * perform the necessary mapping and unmapping.
- *
- * Note, __ntfs_cluster_free() saves the state of @ctx on entry and restores it
- * before returning.  Thus, @ctx will be left pointing to the same attribute on
- * return as on entry.  However, the actual pointers in @ctx may point to
- * different memory locations on return, so you must remember to reset any
- * cached pointers from the @ctx, i.e. after the call to __ntfs_cluster_free(),
- * you will probably want to do:
- *	m = ctx->mrec;
- *	a = ctx->attr;
- * Assuming you cache ctx->attr in a variable @a of type ATTR_RECORD * and that
- * you cache ctx->mrec in a variable @m of type MFT_RECORD *.
- *
- * @is_rollback should always be 'false', it is for internal use to rollback
- * errors.  You probably want to use ntfs_cluster_free() instead.
- *
- * Note, __ntfs_cluster_free() does not modify the runlist, so you have to
- * remove from the runlist or mark sparse the freed runs later.
- *
- * Return the number of deallocated clusters (not counting sparse ones) on
- * success and -errno on error.
- *
- * WARNING: If @ctx is supplied, regardless of whether success or failure is
- *	    returned, you need to check IS_ERR(@ctx->mrec) and if 'true' the @ctx
- *	    is no longer valid, i.e. you need to either call
- *	    ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it.
- *	    In that case PTR_ERR(@ctx->mrec) will give you the error code for
- *	    why the mapping of the old inode failed.
- *
- * Locking: - The runlist described by @ni must be locked for writing on entry
- *	      and is locked on return.  Note the runlist may be modified when
- *	      needed runlist fragments need to be mapped.
- *	    - The volume lcn bitmap must be unlocked on entry and is unlocked
- *	      on return.
- *	    - This function takes the volume lcn bitmap lock for writing and
- *	      modifies the bitmap contents.
- *	    - If @ctx is NULL, the base mft record of @ni must not be mapped on
- *	      entry and it will be left unmapped on return.
- *	    - If @ctx is not NULL, the base mft record must be mapped on entry
- *	      and it will be left mapped on return.
- */
-s64 __ntfs_cluster_free(ntfs_inode *ni, const VCN start_vcn, s64 count,
-		ntfs_attr_search_ctx *ctx, const bool is_rollback)
-{
-	s64 delta, to_free, total_freed, real_freed;
-	ntfs_volume *vol;
-	struct inode *lcnbmp_vi;
-	runlist_element *rl;
-	int err;
-
-	BUG_ON(!ni);
-	ntfs_debug("Entering for i_ino 0x%lx, start_vcn 0x%llx, count "
-			"0x%llx.%s", ni->mft_no, (unsigned long long)start_vcn,
-			(unsigned long long)count,
-			is_rollback ? " (rollback)" : "");
-	vol = ni->vol;
-	lcnbmp_vi = vol->lcnbmp_ino;
-	BUG_ON(!lcnbmp_vi);
-	BUG_ON(start_vcn < 0);
-	BUG_ON(count < -1);
-	/*
-	 * Lock the lcn bitmap for writing but only if not rolling back.  We
-	 * must hold the lock all the way including through rollback otherwise
-	 * rollback is not possible because once we have cleared a bit and
-	 * dropped the lock, anyone could have set the bit again, thus
-	 * allocating the cluster for another use.
-	 */
-	if (likely(!is_rollback))
-		down_write(&vol->lcnbmp_lock);
-
-	total_freed = real_freed = 0;
-
-	rl = ntfs_attr_find_vcn_nolock(ni, start_vcn, ctx);
-	if (IS_ERR(rl)) {
-		if (!is_rollback)
-			ntfs_error(vol->sb, "Failed to find first runlist "
-					"element (error %li), aborting.",
-					PTR_ERR(rl));
-		err = PTR_ERR(rl);
-		goto err_out;
-	}
-	if (unlikely(rl->lcn < LCN_HOLE)) {
-		if (!is_rollback)
-			ntfs_error(vol->sb, "First runlist element has "
-					"invalid lcn, aborting.");
-		err = -EIO;
-		goto err_out;
-	}
-	/* Find the starting cluster inside the run that needs freeing. */
-	delta = start_vcn - rl->vcn;
-
-	/* The number of clusters in this run that need freeing. */
-	to_free = rl->length - delta;
-	if (count >= 0 && to_free > count)
-		to_free = count;
-
-	if (likely(rl->lcn >= 0)) {
-		/* Do the actual freeing of the clusters in this run. */
-		err = ntfs_bitmap_set_bits_in_run(lcnbmp_vi, rl->lcn + delta,
-				to_free, likely(!is_rollback) ? 0 : 1);
-		if (unlikely(err)) {
-			if (!is_rollback)
-				ntfs_error(vol->sb, "Failed to clear first run "
-						"(error %i), aborting.", err);
-			goto err_out;
-		}
-		/* We have freed @to_free real clusters. */
-		real_freed = to_free;
-	};
-	/* Go to the next run and adjust the number of clusters left to free. */
-	++rl;
-	if (count >= 0)
-		count -= to_free;
-
-	/* Keep track of the total "freed" clusters, including sparse ones. */
-	total_freed = to_free;
-	/*
-	 * Loop over the remaining runs, using @count as a capping value, and
-	 * free them.
-	 */
-	for (; rl->length && count != 0; ++rl) {
-		if (unlikely(rl->lcn < LCN_HOLE)) {
-			VCN vcn;
-
-			/* Attempt to map runlist. */
-			vcn = rl->vcn;
-			rl = ntfs_attr_find_vcn_nolock(ni, vcn, ctx);
-			if (IS_ERR(rl)) {
-				err = PTR_ERR(rl);
-				if (!is_rollback)
-					ntfs_error(vol->sb, "Failed to map "
-							"runlist fragment or "
-							"failed to find "
-							"subsequent runlist "
-							"element.");
-				goto err_out;
-			}
-			if (unlikely(rl->lcn < LCN_HOLE)) {
-				if (!is_rollback)
-					ntfs_error(vol->sb, "Runlist element "
-							"has invalid lcn "
-							"(0x%llx).",
-							(unsigned long long)
-							rl->lcn);
-				err = -EIO;
-				goto err_out;
-			}
-		}
-		/* The number of clusters in this run that need freeing. */
-		to_free = rl->length;
-		if (count >= 0 && to_free > count)
-			to_free = count;
-
-		if (likely(rl->lcn >= 0)) {
-			/* Do the actual freeing of the clusters in the run. */
-			err = ntfs_bitmap_set_bits_in_run(lcnbmp_vi, rl->lcn,
-					to_free, likely(!is_rollback) ? 0 : 1);
-			if (unlikely(err)) {
-				if (!is_rollback)
-					ntfs_error(vol->sb, "Failed to clear "
-							"subsequent run.");
-				goto err_out;
-			}
-			/* We have freed @to_free real clusters. */
-			real_freed += to_free;
-		}
-		/* Adjust the number of clusters left to free. */
-		if (count >= 0)
-			count -= to_free;
-	
-		/* Update the total done clusters. */
-		total_freed += to_free;
-	}
-	if (likely(!is_rollback))
-		up_write(&vol->lcnbmp_lock);
-
-	BUG_ON(count > 0);
-
-	/* We are done.  Return the number of actually freed clusters. */
-	ntfs_debug("Done.");
-	return real_freed;
-err_out:
-	if (is_rollback)
-		return err;
-	/* If no real clusters were freed, no need to rollback. */
-	if (!real_freed) {
-		up_write(&vol->lcnbmp_lock);
-		return err;
-	}
-	/*
-	 * Attempt to rollback and if that succeeds just return the error code.
-	 * If rollback fails, set the volume errors flag, emit an error
-	 * message, and return the error code.
-	 */
-	delta = __ntfs_cluster_free(ni, start_vcn, total_freed, ctx, true);
-	if (delta < 0) {
-		ntfs_error(vol->sb, "Failed to rollback (error %i).  Leaving "
-				"inconsistent metadata!  Unmount and run "
-				"chkdsk.", (int)delta);
-		NVolSetErrors(vol);
-	}
-	up_write(&vol->lcnbmp_lock);
-	ntfs_error(vol->sb, "Aborting (error %i).", err);
-	return err;
-}
-
-#endif /* NTFS_RW */
diff --git a/fs/ntfs/lcnalloc.h b/fs/ntfs/lcnalloc.h
deleted file mode 100644
index 1589a6d8434b..000000000000
--- a/fs/ntfs/lcnalloc.h
+++ /dev/null
@@ -1,131 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * lcnalloc.h - Exports for NTFS kernel cluster (de)allocation.  Part of the
- *		Linux-NTFS project.
- *
- * Copyright (c) 2004-2005 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_LCNALLOC_H
-#define _LINUX_NTFS_LCNALLOC_H
-
-#ifdef NTFS_RW
-
-#include <linux/fs.h>
-
-#include "attrib.h"
-#include "types.h"
-#include "inode.h"
-#include "runlist.h"
-#include "volume.h"
-
-typedef enum {
-	FIRST_ZONE	= 0,	/* For sanity checking. */
-	MFT_ZONE	= 0,	/* Allocate from $MFT zone. */
-	DATA_ZONE	= 1,	/* Allocate from $DATA zone. */
-	LAST_ZONE	= 1,	/* For sanity checking. */
-} NTFS_CLUSTER_ALLOCATION_ZONES;
-
-extern runlist_element *ntfs_cluster_alloc(ntfs_volume *vol,
-		const VCN start_vcn, const s64 count, const LCN start_lcn,
-		const NTFS_CLUSTER_ALLOCATION_ZONES zone,
-		const bool is_extension);
-
-extern s64 __ntfs_cluster_free(ntfs_inode *ni, const VCN start_vcn,
-		s64 count, ntfs_attr_search_ctx *ctx, const bool is_rollback);
-
-/**
- * ntfs_cluster_free - free clusters on an ntfs volume
- * @ni:		ntfs inode whose runlist describes the clusters to free
- * @start_vcn:	vcn in the runlist of @ni at which to start freeing clusters
- * @count:	number of clusters to free or -1 for all clusters
- * @ctx:	active attribute search context if present or NULL if not
- *
- * Free @count clusters starting at the cluster @start_vcn in the runlist
- * described by the ntfs inode @ni.
- *
- * If @count is -1, all clusters from @start_vcn to the end of the runlist are
- * deallocated.  Thus, to completely free all clusters in a runlist, use
- * @start_vcn = 0 and @count = -1.
- *
- * If @ctx is specified, it is an active search context of @ni and its base mft
- * record.  This is needed when ntfs_cluster_free() encounters unmapped runlist
- * fragments and allows their mapping.  If you do not have the mft record
- * mapped, you can specify @ctx as NULL and ntfs_cluster_free() will perform
- * the necessary mapping and unmapping.
- *
- * Note, ntfs_cluster_free() saves the state of @ctx on entry and restores it
- * before returning.  Thus, @ctx will be left pointing to the same attribute on
- * return as on entry.  However, the actual pointers in @ctx may point to
- * different memory locations on return, so you must remember to reset any
- * cached pointers from the @ctx, i.e. after the call to ntfs_cluster_free(),
- * you will probably want to do:
- *	m = ctx->mrec;
- *	a = ctx->attr;
- * Assuming you cache ctx->attr in a variable @a of type ATTR_RECORD * and that
- * you cache ctx->mrec in a variable @m of type MFT_RECORD *.
- *
- * Note, ntfs_cluster_free() does not modify the runlist, so you have to remove
- * from the runlist or mark sparse the freed runs later.
- *
- * Return the number of deallocated clusters (not counting sparse ones) on
- * success and -errno on error.
- *
- * WARNING: If @ctx is supplied, regardless of whether success or failure is
- *	    returned, you need to check IS_ERR(@ctx->mrec) and if 'true' the @ctx
- *	    is no longer valid, i.e. you need to either call
- *	    ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it.
- *	    In that case PTR_ERR(@ctx->mrec) will give you the error code for
- *	    why the mapping of the old inode failed.
- *
- * Locking: - The runlist described by @ni must be locked for writing on entry
- *	      and is locked on return.  Note the runlist may be modified when
- *	      needed runlist fragments need to be mapped.
- *	    - The volume lcn bitmap must be unlocked on entry and is unlocked
- *	      on return.
- *	    - This function takes the volume lcn bitmap lock for writing and
- *	      modifies the bitmap contents.
- *	    - If @ctx is NULL, the base mft record of @ni must not be mapped on
- *	      entry and it will be left unmapped on return.
- *	    - If @ctx is not NULL, the base mft record must be mapped on entry
- *	      and it will be left mapped on return.
- */
-static inline s64 ntfs_cluster_free(ntfs_inode *ni, const VCN start_vcn,
-		s64 count, ntfs_attr_search_ctx *ctx)
-{
-	return __ntfs_cluster_free(ni, start_vcn, count, ctx, false);
-}
-
-extern int ntfs_cluster_free_from_rl_nolock(ntfs_volume *vol,
-		const runlist_element *rl);
-
-/**
- * ntfs_cluster_free_from_rl - free clusters from runlist
- * @vol:	mounted ntfs volume on which to free the clusters
- * @rl:		runlist describing the clusters to free
- *
- * Free all the clusters described by the runlist @rl on the volume @vol.  In
- * the case of an error being returned, at least some of the clusters were not
- * freed.
- *
- * Return 0 on success and -errno on error.
- *
- * Locking: - This function takes the volume lcn bitmap lock for writing and
- *	      modifies the bitmap contents.
- *	    - The caller must have locked the runlist @rl for reading or
- *	      writing.
- */
-static inline int ntfs_cluster_free_from_rl(ntfs_volume *vol,
-		const runlist_element *rl)
-{
-	int ret;
-
-	down_write(&vol->lcnbmp_lock);
-	ret = ntfs_cluster_free_from_rl_nolock(vol, rl);
-	up_write(&vol->lcnbmp_lock);
-	return ret;
-}
-
-#endif /* NTFS_RW */
-
-#endif /* defined _LINUX_NTFS_LCNALLOC_H */
diff --git a/fs/ntfs/logfile.c b/fs/ntfs/logfile.c
deleted file mode 100644
index 6ce60ffc6ac0..000000000000
--- a/fs/ntfs/logfile.c
+++ /dev/null
@@ -1,849 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * logfile.c - NTFS kernel journal handling. Part of the Linux-NTFS project.
- *
- * Copyright (c) 2002-2007 Anton Altaparmakov
- */
-
-#ifdef NTFS_RW
-
-#include <linux/types.h>
-#include <linux/fs.h>
-#include <linux/highmem.h>
-#include <linux/buffer_head.h>
-#include <linux/bitops.h>
-#include <linux/log2.h>
-#include <linux/bio.h>
-
-#include "attrib.h"
-#include "aops.h"
-#include "debug.h"
-#include "logfile.h"
-#include "malloc.h"
-#include "volume.h"
-#include "ntfs.h"
-
-/**
- * ntfs_check_restart_page_header - check the page header for consistency
- * @vi:		$LogFile inode to which the restart page header belongs
- * @rp:		restart page header to check
- * @pos:	position in @vi at which the restart page header resides
- *
- * Check the restart page header @rp for consistency and return 'true' if it is
- * consistent and 'false' otherwise.
- *
- * This function only needs NTFS_BLOCK_SIZE bytes in @rp, i.e. it does not
- * require the full restart page.
- */
-static bool ntfs_check_restart_page_header(struct inode *vi,
-		RESTART_PAGE_HEADER *rp, s64 pos)
-{
-	u32 logfile_system_page_size, logfile_log_page_size;
-	u16 ra_ofs, usa_count, usa_ofs, usa_end = 0;
-	bool have_usa = true;
-
-	ntfs_debug("Entering.");
-	/*
-	 * If the system or log page sizes are smaller than the ntfs block size
-	 * or either is not a power of 2 we cannot handle this log file.
-	 */
-	logfile_system_page_size = le32_to_cpu(rp->system_page_size);
-	logfile_log_page_size = le32_to_cpu(rp->log_page_size);
-	if (logfile_system_page_size < NTFS_BLOCK_SIZE ||
-			logfile_log_page_size < NTFS_BLOCK_SIZE ||
-			logfile_system_page_size &
-			(logfile_system_page_size - 1) ||
-			!is_power_of_2(logfile_log_page_size)) {
-		ntfs_error(vi->i_sb, "$LogFile uses unsupported page size.");
-		return false;
-	}
-	/*
-	 * We must be either at !pos (1st restart page) or at pos = system page
-	 * size (2nd restart page).
-	 */
-	if (pos && pos != logfile_system_page_size) {
-		ntfs_error(vi->i_sb, "Found restart area in incorrect "
-				"position in $LogFile.");
-		return false;
-	}
-	/* We only know how to handle version 1.1. */
-	if (sle16_to_cpu(rp->major_ver) != 1 ||
-			sle16_to_cpu(rp->minor_ver) != 1) {
-		ntfs_error(vi->i_sb, "$LogFile version %i.%i is not "
-				"supported.  (This driver supports version "
-				"1.1 only.)", (int)sle16_to_cpu(rp->major_ver),
-				(int)sle16_to_cpu(rp->minor_ver));
-		return false;
-	}
-	/*
-	 * If chkdsk has been run the restart page may not be protected by an
-	 * update sequence array.
-	 */
-	if (ntfs_is_chkd_record(rp->magic) && !le16_to_cpu(rp->usa_count)) {
-		have_usa = false;
-		goto skip_usa_checks;
-	}
-	/* Verify the size of the update sequence array. */
-	usa_count = 1 + (logfile_system_page_size >> NTFS_BLOCK_SIZE_BITS);
-	if (usa_count != le16_to_cpu(rp->usa_count)) {
-		ntfs_error(vi->i_sb, "$LogFile restart page specifies "
-				"inconsistent update sequence array count.");
-		return false;
-	}
-	/* Verify the position of the update sequence array. */
-	usa_ofs = le16_to_cpu(rp->usa_ofs);
-	usa_end = usa_ofs + usa_count * sizeof(u16);
-	if (usa_ofs < sizeof(RESTART_PAGE_HEADER) ||
-			usa_end > NTFS_BLOCK_SIZE - sizeof(u16)) {
-		ntfs_error(vi->i_sb, "$LogFile restart page specifies "
-				"inconsistent update sequence array offset.");
-		return false;
-	}
-skip_usa_checks:
-	/*
-	 * Verify the position of the restart area.  It must be:
-	 *	- aligned to 8-byte boundary,
-	 *	- after the update sequence array, and
-	 *	- within the system page size.
-	 */
-	ra_ofs = le16_to_cpu(rp->restart_area_offset);
-	if (ra_ofs & 7 || (have_usa ? ra_ofs < usa_end :
-			ra_ofs < sizeof(RESTART_PAGE_HEADER)) ||
-			ra_ofs > logfile_system_page_size) {
-		ntfs_error(vi->i_sb, "$LogFile restart page specifies "
-				"inconsistent restart area offset.");
-		return false;
-	}
-	/*
-	 * Only restart pages modified by chkdsk are allowed to have chkdsk_lsn
-	 * set.
-	 */
-	if (!ntfs_is_chkd_record(rp->magic) && sle64_to_cpu(rp->chkdsk_lsn)) {
-		ntfs_error(vi->i_sb, "$LogFile restart page is not modified "
-				"by chkdsk but a chkdsk LSN is specified.");
-		return false;
-	}
-	ntfs_debug("Done.");
-	return true;
-}
-
-/**
- * ntfs_check_restart_area - check the restart area for consistency
- * @vi:		$LogFile inode to which the restart page belongs
- * @rp:		restart page whose restart area to check
- *
- * Check the restart area of the restart page @rp for consistency and return
- * 'true' if it is consistent and 'false' otherwise.
- *
- * This function assumes that the restart page header has already been
- * consistency checked.
- *
- * This function only needs NTFS_BLOCK_SIZE bytes in @rp, i.e. it does not
- * require the full restart page.
- */
-static bool ntfs_check_restart_area(struct inode *vi, RESTART_PAGE_HEADER *rp)
-{
-	u64 file_size;
-	RESTART_AREA *ra;
-	u16 ra_ofs, ra_len, ca_ofs;
-	u8 fs_bits;
-
-	ntfs_debug("Entering.");
-	ra_ofs = le16_to_cpu(rp->restart_area_offset);
-	ra = (RESTART_AREA*)((u8*)rp + ra_ofs);
-	/*
-	 * Everything before ra->file_size must be before the first word
-	 * protected by an update sequence number.  This ensures that it is
-	 * safe to access ra->client_array_offset.
-	 */
-	if (ra_ofs + offsetof(RESTART_AREA, file_size) >
-			NTFS_BLOCK_SIZE - sizeof(u16)) {
-		ntfs_error(vi->i_sb, "$LogFile restart area specifies "
-				"inconsistent file offset.");
-		return false;
-	}
-	/*
-	 * Now that we can access ra->client_array_offset, make sure everything
-	 * up to the log client array is before the first word protected by an
-	 * update sequence number.  This ensures we can access all of the
-	 * restart area elements safely.  Also, the client array offset must be
-	 * aligned to an 8-byte boundary.
-	 */
-	ca_ofs = le16_to_cpu(ra->client_array_offset);
-	if (((ca_ofs + 7) & ~7) != ca_ofs ||
-			ra_ofs + ca_ofs > NTFS_BLOCK_SIZE - sizeof(u16)) {
-		ntfs_error(vi->i_sb, "$LogFile restart area specifies "
-				"inconsistent client array offset.");
-		return false;
-	}
-	/*
-	 * The restart area must end within the system page size both when
-	 * calculated manually and as specified by ra->restart_area_length.
-	 * Also, the calculated length must not exceed the specified length.
-	 */
-	ra_len = ca_ofs + le16_to_cpu(ra->log_clients) *
-			sizeof(LOG_CLIENT_RECORD);
-	if (ra_ofs + ra_len > le32_to_cpu(rp->system_page_size) ||
-			ra_ofs + le16_to_cpu(ra->restart_area_length) >
-			le32_to_cpu(rp->system_page_size) ||
-			ra_len > le16_to_cpu(ra->restart_area_length)) {
-		ntfs_error(vi->i_sb, "$LogFile restart area is out of bounds "
-				"of the system page size specified by the "
-				"restart page header and/or the specified "
-				"restart area length is inconsistent.");
-		return false;
-	}
-	/*
-	 * The ra->client_free_list and ra->client_in_use_list must be either
-	 * LOGFILE_NO_CLIENT or less than ra->log_clients or they are
-	 * overflowing the client array.
-	 */
-	if ((ra->client_free_list != LOGFILE_NO_CLIENT &&
-			le16_to_cpu(ra->client_free_list) >=
-			le16_to_cpu(ra->log_clients)) ||
-			(ra->client_in_use_list != LOGFILE_NO_CLIENT &&
-			le16_to_cpu(ra->client_in_use_list) >=
-			le16_to_cpu(ra->log_clients))) {
-		ntfs_error(vi->i_sb, "$LogFile restart area specifies "
-				"overflowing client free and/or in use lists.");
-		return false;
-	}
-	/*
-	 * Check ra->seq_number_bits against ra->file_size for consistency.
-	 * We cannot just use ffs() because the file size is not a power of 2.
-	 */
-	file_size = (u64)sle64_to_cpu(ra->file_size);
-	fs_bits = 0;
-	while (file_size) {
-		file_size >>= 1;
-		fs_bits++;
-	}
-	if (le32_to_cpu(ra->seq_number_bits) != 67 - fs_bits) {
-		ntfs_error(vi->i_sb, "$LogFile restart area specifies "
-				"inconsistent sequence number bits.");
-		return false;
-	}
-	/* The log record header length must be a multiple of 8. */
-	if (((le16_to_cpu(ra->log_record_header_length) + 7) & ~7) !=
-			le16_to_cpu(ra->log_record_header_length)) {
-		ntfs_error(vi->i_sb, "$LogFile restart area specifies "
-				"inconsistent log record header length.");
-		return false;
-	}
-	/* Dito for the log page data offset. */
-	if (((le16_to_cpu(ra->log_page_data_offset) + 7) & ~7) !=
-			le16_to_cpu(ra->log_page_data_offset)) {
-		ntfs_error(vi->i_sb, "$LogFile restart area specifies "
-				"inconsistent log page data offset.");
-		return false;
-	}
-	ntfs_debug("Done.");
-	return true;
-}
-
-/**
- * ntfs_check_log_client_array - check the log client array for consistency
- * @vi:		$LogFile inode to which the restart page belongs
- * @rp:		restart page whose log client array to check
- *
- * Check the log client array of the restart page @rp for consistency and
- * return 'true' if it is consistent and 'false' otherwise.
- *
- * This function assumes that the restart page header and the restart area have
- * already been consistency checked.
- *
- * Unlike ntfs_check_restart_page_header() and ntfs_check_restart_area(), this
- * function needs @rp->system_page_size bytes in @rp, i.e. it requires the full
- * restart page and the page must be multi sector transfer deprotected.
- */
-static bool ntfs_check_log_client_array(struct inode *vi,
-		RESTART_PAGE_HEADER *rp)
-{
-	RESTART_AREA *ra;
-	LOG_CLIENT_RECORD *ca, *cr;
-	u16 nr_clients, idx;
-	bool in_free_list, idx_is_first;
-
-	ntfs_debug("Entering.");
-	ra = (RESTART_AREA*)((u8*)rp + le16_to_cpu(rp->restart_area_offset));
-	ca = (LOG_CLIENT_RECORD*)((u8*)ra +
-			le16_to_cpu(ra->client_array_offset));
-	/*
-	 * Check the ra->client_free_list first and then check the
-	 * ra->client_in_use_list.  Check each of the log client records in
-	 * each of the lists and check that the array does not overflow the
-	 * ra->log_clients value.  Also keep track of the number of records
-	 * visited as there cannot be more than ra->log_clients records and
-	 * that way we detect eventual loops in within a list.
-	 */
-	nr_clients = le16_to_cpu(ra->log_clients);
-	idx = le16_to_cpu(ra->client_free_list);
-	in_free_list = true;
-check_list:
-	for (idx_is_first = true; idx != LOGFILE_NO_CLIENT_CPU; nr_clients--,
-			idx = le16_to_cpu(cr->next_client)) {
-		if (!nr_clients || idx >= le16_to_cpu(ra->log_clients))
-			goto err_out;
-		/* Set @cr to the current log client record. */
-		cr = ca + idx;
-		/* The first log client record must not have a prev_client. */
-		if (idx_is_first) {
-			if (cr->prev_client != LOGFILE_NO_CLIENT)
-				goto err_out;
-			idx_is_first = false;
-		}
-	}
-	/* Switch to and check the in use list if we just did the free list. */
-	if (in_free_list) {
-		in_free_list = false;
-		idx = le16_to_cpu(ra->client_in_use_list);
-		goto check_list;
-	}
-	ntfs_debug("Done.");
-	return true;
-err_out:
-	ntfs_error(vi->i_sb, "$LogFile log client array is corrupt.");
-	return false;
-}
-
-/**
- * ntfs_check_and_load_restart_page - check the restart page for consistency
- * @vi:		$LogFile inode to which the restart page belongs
- * @rp:		restart page to check
- * @pos:	position in @vi at which the restart page resides
- * @wrp:	[OUT] copy of the multi sector transfer deprotected restart page
- * @lsn:	[OUT] set to the current logfile lsn on success
- *
- * Check the restart page @rp for consistency and return 0 if it is consistent
- * and -errno otherwise.  The restart page may have been modified by chkdsk in
- * which case its magic is CHKD instead of RSTR.
- *
- * This function only needs NTFS_BLOCK_SIZE bytes in @rp, i.e. it does not
- * require the full restart page.
- *
- * If @wrp is not NULL, on success, *@wrp will point to a buffer containing a
- * copy of the complete multi sector transfer deprotected page.  On failure,
- * *@wrp is undefined.
- *
- * Simillarly, if @lsn is not NULL, on success *@lsn will be set to the current
- * logfile lsn according to this restart page.  On failure, *@lsn is undefined.
- *
- * The following error codes are defined:
- *	-EINVAL	- The restart page is inconsistent.
- *	-ENOMEM	- Not enough memory to load the restart page.
- *	-EIO	- Failed to reading from $LogFile.
- */
-static int ntfs_check_and_load_restart_page(struct inode *vi,
-		RESTART_PAGE_HEADER *rp, s64 pos, RESTART_PAGE_HEADER **wrp,
-		LSN *lsn)
-{
-	RESTART_AREA *ra;
-	RESTART_PAGE_HEADER *trp;
-	int size, err;
-
-	ntfs_debug("Entering.");
-	/* Check the restart page header for consistency. */
-	if (!ntfs_check_restart_page_header(vi, rp, pos)) {
-		/* Error output already done inside the function. */
-		return -EINVAL;
-	}
-	/* Check the restart area for consistency. */
-	if (!ntfs_check_restart_area(vi, rp)) {
-		/* Error output already done inside the function. */
-		return -EINVAL;
-	}
-	ra = (RESTART_AREA*)((u8*)rp + le16_to_cpu(rp->restart_area_offset));
-	/*
-	 * Allocate a buffer to store the whole restart page so we can multi
-	 * sector transfer deprotect it.
-	 */
-	trp = ntfs_malloc_nofs(le32_to_cpu(rp->system_page_size));
-	if (!trp) {
-		ntfs_error(vi->i_sb, "Failed to allocate memory for $LogFile "
-				"restart page buffer.");
-		return -ENOMEM;
-	}
-	/*
-	 * Read the whole of the restart page into the buffer.  If it fits
-	 * completely inside @rp, just copy it from there.  Otherwise map all
-	 * the required pages and copy the data from them.
-	 */
-	size = PAGE_SIZE - (pos & ~PAGE_MASK);
-	if (size >= le32_to_cpu(rp->system_page_size)) {
-		memcpy(trp, rp, le32_to_cpu(rp->system_page_size));
-	} else {
-		pgoff_t idx;
-		struct page *page;
-		int have_read, to_read;
-
-		/* First copy what we already have in @rp. */
-		memcpy(trp, rp, size);
-		/* Copy the remaining data one page at a time. */
-		have_read = size;
-		to_read = le32_to_cpu(rp->system_page_size) - size;
-		idx = (pos + size) >> PAGE_SHIFT;
-		BUG_ON((pos + size) & ~PAGE_MASK);
-		do {
-			page = ntfs_map_page(vi->i_mapping, idx);
-			if (IS_ERR(page)) {
-				ntfs_error(vi->i_sb, "Error mapping $LogFile "
-						"page (index %lu).", idx);
-				err = PTR_ERR(page);
-				if (err != -EIO && err != -ENOMEM)
-					err = -EIO;
-				goto err_out;
-			}
-			size = min_t(int, to_read, PAGE_SIZE);
-			memcpy((u8*)trp + have_read, page_address(page), size);
-			ntfs_unmap_page(page);
-			have_read += size;
-			to_read -= size;
-			idx++;
-		} while (to_read > 0);
-	}
-	/*
-	 * Perform the multi sector transfer deprotection on the buffer if the
-	 * restart page is protected.
-	 */
-	if ((!ntfs_is_chkd_record(trp->magic) || le16_to_cpu(trp->usa_count))
-			&& post_read_mst_fixup((NTFS_RECORD*)trp,
-			le32_to_cpu(rp->system_page_size))) {
-		/*
-		 * A multi sector tranfer error was detected.  We only need to
-		 * abort if the restart page contents exceed the multi sector
-		 * transfer fixup of the first sector.
-		 */
-		if (le16_to_cpu(rp->restart_area_offset) +
-				le16_to_cpu(ra->restart_area_length) >
-				NTFS_BLOCK_SIZE - sizeof(u16)) {
-			ntfs_error(vi->i_sb, "Multi sector transfer error "
-					"detected in $LogFile restart page.");
-			err = -EINVAL;
-			goto err_out;
-		}
-	}
-	/*
-	 * If the restart page is modified by chkdsk or there are no active
-	 * logfile clients, the logfile is consistent.  Otherwise, need to
-	 * check the log client records for consistency, too.
-	 */
-	err = 0;
-	if (ntfs_is_rstr_record(rp->magic) &&
-			ra->client_in_use_list != LOGFILE_NO_CLIENT) {
-		if (!ntfs_check_log_client_array(vi, trp)) {
-			err = -EINVAL;
-			goto err_out;
-		}
-	}
-	if (lsn) {
-		if (ntfs_is_rstr_record(rp->magic))
-			*lsn = sle64_to_cpu(ra->current_lsn);
-		else /* if (ntfs_is_chkd_record(rp->magic)) */
-			*lsn = sle64_to_cpu(rp->chkdsk_lsn);
-	}
-	ntfs_debug("Done.");
-	if (wrp)
-		*wrp = trp;
-	else {
-err_out:
-		ntfs_free(trp);
-	}
-	return err;
-}
-
-/**
- * ntfs_check_logfile - check the journal for consistency
- * @log_vi:	struct inode of loaded journal $LogFile to check
- * @rp:		[OUT] on success this is a copy of the current restart page
- *
- * Check the $LogFile journal for consistency and return 'true' if it is
- * consistent and 'false' if not.  On success, the current restart page is
- * returned in *@rp.  Caller must call ntfs_free(*@rp) when finished with it.
- *
- * At present we only check the two restart pages and ignore the log record
- * pages.
- *
- * Note that the MstProtected flag is not set on the $LogFile inode and hence
- * when reading pages they are not deprotected.  This is because we do not know
- * if the $LogFile was created on a system with a different page size to ours
- * yet and mst deprotection would fail if our page size is smaller.
- */
-bool ntfs_check_logfile(struct inode *log_vi, RESTART_PAGE_HEADER **rp)
-{
-	s64 size, pos;
-	LSN rstr1_lsn, rstr2_lsn;
-	ntfs_volume *vol = NTFS_SB(log_vi->i_sb);
-	struct address_space *mapping = log_vi->i_mapping;
-	struct page *page = NULL;
-	u8 *kaddr = NULL;
-	RESTART_PAGE_HEADER *rstr1_ph = NULL;
-	RESTART_PAGE_HEADER *rstr2_ph = NULL;
-	int log_page_size, err;
-	bool logfile_is_empty = true;
-	u8 log_page_bits;
-
-	ntfs_debug("Entering.");
-	/* An empty $LogFile must have been clean before it got emptied. */
-	if (NVolLogFileEmpty(vol))
-		goto is_empty;
-	size = i_size_read(log_vi);
-	/* Make sure the file doesn't exceed the maximum allowed size. */
-	if (size > MaxLogFileSize)
-		size = MaxLogFileSize;
-	/*
-	 * Truncate size to a multiple of the page cache size or the default
-	 * log page size if the page cache size is between the default log page
-	 * log page size if the page cache size is between the default log page
-	 * size and twice that.
-	 */
-	if (PAGE_SIZE >= DefaultLogPageSize && PAGE_SIZE <=
-			DefaultLogPageSize * 2)
-		log_page_size = DefaultLogPageSize;
-	else
-		log_page_size = PAGE_SIZE;
-	/*
-	 * Use ntfs_ffs() instead of ffs() to enable the compiler to
-	 * optimize log_page_size and log_page_bits into constants.
-	 */
-	log_page_bits = ntfs_ffs(log_page_size) - 1;
-	size &= ~(s64)(log_page_size - 1);
-	/*
-	 * Ensure the log file is big enough to store at least the two restart
-	 * pages and the minimum number of log record pages.
-	 */
-	if (size < log_page_size * 2 || (size - log_page_size * 2) >>
-			log_page_bits < MinLogRecordPages) {
-		ntfs_error(vol->sb, "$LogFile is too small.");
-		return false;
-	}
-	/*
-	 * Read through the file looking for a restart page.  Since the restart
-	 * page header is at the beginning of a page we only need to search at
-	 * what could be the beginning of a page (for each page size) rather
-	 * than scanning the whole file byte by byte.  If all potential places
-	 * contain empty and uninitialzed records, the log file can be assumed
-	 * to be empty.
-	 */
-	for (pos = 0; pos < size; pos <<= 1) {
-		pgoff_t idx = pos >> PAGE_SHIFT;
-		if (!page || page->index != idx) {
-			if (page)
-				ntfs_unmap_page(page);
-			page = ntfs_map_page(mapping, idx);
-			if (IS_ERR(page)) {
-				ntfs_error(vol->sb, "Error mapping $LogFile "
-						"page (index %lu).", idx);
-				goto err_out;
-			}
-		}
-		kaddr = (u8*)page_address(page) + (pos & ~PAGE_MASK);
-		/*
-		 * A non-empty block means the logfile is not empty while an
-		 * empty block after a non-empty block has been encountered
-		 * means we are done.
-		 */
-		if (!ntfs_is_empty_recordp((le32*)kaddr))
-			logfile_is_empty = false;
-		else if (!logfile_is_empty)
-			break;
-		/*
-		 * A log record page means there cannot be a restart page after
-		 * this so no need to continue searching.
-		 */
-		if (ntfs_is_rcrd_recordp((le32*)kaddr))
-			break;
-		/* If not a (modified by chkdsk) restart page, continue. */
-		if (!ntfs_is_rstr_recordp((le32*)kaddr) &&
-				!ntfs_is_chkd_recordp((le32*)kaddr)) {
-			if (!pos)
-				pos = NTFS_BLOCK_SIZE >> 1;
-			continue;
-		}
-		/*
-		 * Check the (modified by chkdsk) restart page for consistency
-		 * and get a copy of the complete multi sector transfer
-		 * deprotected restart page.
-		 */
-		err = ntfs_check_and_load_restart_page(log_vi,
-				(RESTART_PAGE_HEADER*)kaddr, pos,
-				!rstr1_ph ? &rstr1_ph : &rstr2_ph,
-				!rstr1_ph ? &rstr1_lsn : &rstr2_lsn);
-		if (!err) {
-			/*
-			 * If we have now found the first (modified by chkdsk)
-			 * restart page, continue looking for the second one.
-			 */
-			if (!pos) {
-				pos = NTFS_BLOCK_SIZE >> 1;
-				continue;
-			}
-			/*
-			 * We have now found the second (modified by chkdsk)
-			 * restart page, so we can stop looking.
-			 */
-			break;
-		}
-		/*
-		 * Error output already done inside the function.  Note, we do
-		 * not abort if the restart page was invalid as we might still
-		 * find a valid one further in the file.
-		 */
-		if (err != -EINVAL) {
-			ntfs_unmap_page(page);
-			goto err_out;
-		}
-		/* Continue looking. */
-		if (!pos)
-			pos = NTFS_BLOCK_SIZE >> 1;
-	}
-	if (page)
-		ntfs_unmap_page(page);
-	if (logfile_is_empty) {
-		NVolSetLogFileEmpty(vol);
-is_empty:
-		ntfs_debug("Done.  ($LogFile is empty.)");
-		return true;
-	}
-	if (!rstr1_ph) {
-		BUG_ON(rstr2_ph);
-		ntfs_error(vol->sb, "Did not find any restart pages in "
-				"$LogFile and it was not empty.");
-		return false;
-	}
-	/* If both restart pages were found, use the more recent one. */
-	if (rstr2_ph) {
-		/*
-		 * If the second restart area is more recent, switch to it.
-		 * Otherwise just throw it away.
-		 */
-		if (rstr2_lsn > rstr1_lsn) {
-			ntfs_debug("Using second restart page as it is more "
-					"recent.");
-			ntfs_free(rstr1_ph);
-			rstr1_ph = rstr2_ph;
-			/* rstr1_lsn = rstr2_lsn; */
-		} else {
-			ntfs_debug("Using first restart page as it is more "
-					"recent.");
-			ntfs_free(rstr2_ph);
-		}
-		rstr2_ph = NULL;
-	}
-	/* All consistency checks passed. */
-	if (rp)
-		*rp = rstr1_ph;
-	else
-		ntfs_free(rstr1_ph);
-	ntfs_debug("Done.");
-	return true;
-err_out:
-	if (rstr1_ph)
-		ntfs_free(rstr1_ph);
-	return false;
-}
-
-/**
- * ntfs_is_logfile_clean - check in the journal if the volume is clean
- * @log_vi:	struct inode of loaded journal $LogFile to check
- * @rp:		copy of the current restart page
- *
- * Analyze the $LogFile journal and return 'true' if it indicates the volume was
- * shutdown cleanly and 'false' if not.
- *
- * At present we only look at the two restart pages and ignore the log record
- * pages.  This is a little bit crude in that there will be a very small number
- * of cases where we think that a volume is dirty when in fact it is clean.
- * This should only affect volumes that have not been shutdown cleanly but did
- * not have any pending, non-check-pointed i/o, i.e. they were completely idle
- * at least for the five seconds preceding the unclean shutdown.
- *
- * This function assumes that the $LogFile journal has already been consistency
- * checked by a call to ntfs_check_logfile() and in particular if the $LogFile
- * is empty this function requires that NVolLogFileEmpty() is true otherwise an
- * empty volume will be reported as dirty.
- */
-bool ntfs_is_logfile_clean(struct inode *log_vi, const RESTART_PAGE_HEADER *rp)
-{
-	ntfs_volume *vol = NTFS_SB(log_vi->i_sb);
-	RESTART_AREA *ra;
-
-	ntfs_debug("Entering.");
-	/* An empty $LogFile must have been clean before it got emptied. */
-	if (NVolLogFileEmpty(vol)) {
-		ntfs_debug("Done.  ($LogFile is empty.)");
-		return true;
-	}
-	BUG_ON(!rp);
-	if (!ntfs_is_rstr_record(rp->magic) &&
-			!ntfs_is_chkd_record(rp->magic)) {
-		ntfs_error(vol->sb, "Restart page buffer is invalid.  This is "
-				"probably a bug in that the $LogFile should "
-				"have been consistency checked before calling "
-				"this function.");
-		return false;
-	}
-	ra = (RESTART_AREA*)((u8*)rp + le16_to_cpu(rp->restart_area_offset));
-	/*
-	 * If the $LogFile has active clients, i.e. it is open, and we do not
-	 * have the RESTART_VOLUME_IS_CLEAN bit set in the restart area flags,
-	 * we assume there was an unclean shutdown.
-	 */
-	if (ra->client_in_use_list != LOGFILE_NO_CLIENT &&
-			!(ra->flags & RESTART_VOLUME_IS_CLEAN)) {
-		ntfs_debug("Done.  $LogFile indicates a dirty shutdown.");
-		return false;
-	}
-	/* $LogFile indicates a clean shutdown. */
-	ntfs_debug("Done.  $LogFile indicates a clean shutdown.");
-	return true;
-}
-
-/**
- * ntfs_empty_logfile - empty the contents of the $LogFile journal
- * @log_vi:	struct inode of loaded journal $LogFile to empty
- *
- * Empty the contents of the $LogFile journal @log_vi and return 'true' on
- * success and 'false' on error.
- *
- * This function assumes that the $LogFile journal has already been consistency
- * checked by a call to ntfs_check_logfile() and that ntfs_is_logfile_clean()
- * has been used to ensure that the $LogFile is clean.
- */
-bool ntfs_empty_logfile(struct inode *log_vi)
-{
-	VCN vcn, end_vcn;
-	ntfs_inode *log_ni = NTFS_I(log_vi);
-	ntfs_volume *vol = log_ni->vol;
-	struct super_block *sb = vol->sb;
-	runlist_element *rl;
-	unsigned long flags;
-	unsigned block_size, block_size_bits;
-	int err;
-	bool should_wait = true;
-
-	ntfs_debug("Entering.");
-	if (NVolLogFileEmpty(vol)) {
-		ntfs_debug("Done.");
-		return true;
-	}
-	/*
-	 * We cannot use ntfs_attr_set() because we may be still in the middle
-	 * of a mount operation.  Thus we do the emptying by hand by first
-	 * zapping the page cache pages for the $LogFile/$DATA attribute and
-	 * then emptying each of the buffers in each of the clusters specified
-	 * by the runlist by hand.
-	 */
-	block_size = sb->s_blocksize;
-	block_size_bits = sb->s_blocksize_bits;
-	vcn = 0;
-	read_lock_irqsave(&log_ni->size_lock, flags);
-	end_vcn = (log_ni->initialized_size + vol->cluster_size_mask) >>
-			vol->cluster_size_bits;
-	read_unlock_irqrestore(&log_ni->size_lock, flags);
-	truncate_inode_pages(log_vi->i_mapping, 0);
-	down_write(&log_ni->runlist.lock);
-	rl = log_ni->runlist.rl;
-	if (unlikely(!rl || vcn < rl->vcn || !rl->length)) {
-map_vcn:
-		err = ntfs_map_runlist_nolock(log_ni, vcn, NULL);
-		if (err) {
-			ntfs_error(sb, "Failed to map runlist fragment (error "
-					"%d).", -err);
-			goto err;
-		}
-		rl = log_ni->runlist.rl;
-		BUG_ON(!rl || vcn < rl->vcn || !rl->length);
-	}
-	/* Seek to the runlist element containing @vcn. */
-	while (rl->length && vcn >= rl[1].vcn)
-		rl++;
-	do {
-		LCN lcn;
-		sector_t block, end_block;
-		s64 len;
-
-		/*
-		 * If this run is not mapped map it now and start again as the
-		 * runlist will have been updated.
-		 */
-		lcn = rl->lcn;
-		if (unlikely(lcn == LCN_RL_NOT_MAPPED)) {
-			vcn = rl->vcn;
-			goto map_vcn;
-		}
-		/* If this run is not valid abort with an error. */
-		if (unlikely(!rl->length || lcn < LCN_HOLE))
-			goto rl_err;
-		/* Skip holes. */
-		if (lcn == LCN_HOLE)
-			continue;
-		block = lcn << vol->cluster_size_bits >> block_size_bits;
-		len = rl->length;
-		if (rl[1].vcn > end_vcn)
-			len = end_vcn - rl->vcn;
-		end_block = (lcn + len) << vol->cluster_size_bits >>
-				block_size_bits;
-		/* Iterate over the blocks in the run and empty them. */
-		do {
-			struct buffer_head *bh;
-
-			/* Obtain the buffer, possibly not uptodate. */
-			bh = sb_getblk(sb, block);
-			BUG_ON(!bh);
-			/* Setup buffer i/o submission. */
-			lock_buffer(bh);
-			bh->b_end_io = end_buffer_write_sync;
-			get_bh(bh);
-			/* Set the entire contents of the buffer to 0xff. */
-			memset(bh->b_data, -1, block_size);
-			if (!buffer_uptodate(bh))
-				set_buffer_uptodate(bh);
-			if (buffer_dirty(bh))
-				clear_buffer_dirty(bh);
-			/*
-			 * Submit the buffer and wait for i/o to complete but
-			 * only for the first buffer so we do not miss really
-			 * serious i/o errors.  Once the first buffer has
-			 * completed ignore errors afterwards as we can assume
-			 * that if one buffer worked all of them will work.
-			 */
-			submit_bh(REQ_OP_WRITE, bh);
-			if (should_wait) {
-				should_wait = false;
-				wait_on_buffer(bh);
-				if (unlikely(!buffer_uptodate(bh)))
-					goto io_err;
-			}
-			brelse(bh);
-		} while (++block < end_block);
-	} while ((++rl)->vcn < end_vcn);
-	up_write(&log_ni->runlist.lock);
-	/*
-	 * Zap the pages again just in case any got instantiated whilst we were
-	 * emptying the blocks by hand.  FIXME: We may not have completed
-	 * writing to all the buffer heads yet so this may happen too early.
-	 * We really should use a kernel thread to do the emptying
-	 * asynchronously and then we can also set the volume dirty and output
-	 * an error message if emptying should fail.
-	 */
-	truncate_inode_pages(log_vi->i_mapping, 0);
-	/* Set the flag so we do not have to do it again on remount. */
-	NVolSetLogFileEmpty(vol);
-	ntfs_debug("Done.");
-	return true;
-io_err:
-	ntfs_error(sb, "Failed to write buffer.  Unmount and run chkdsk.");
-	goto dirty_err;
-rl_err:
-	ntfs_error(sb, "Runlist is corrupt.  Unmount and run chkdsk.");
-dirty_err:
-	NVolSetErrors(vol);
-	err = -EIO;
-err:
-	up_write(&log_ni->runlist.lock);
-	ntfs_error(sb, "Failed to fill $LogFile with 0xff bytes (error %d).",
-			-err);
-	return false;
-}
-
-#endif /* NTFS_RW */
diff --git a/fs/ntfs/logfile.h b/fs/ntfs/logfile.h
deleted file mode 100644
index 429d4909cc72..000000000000
--- a/fs/ntfs/logfile.h
+++ /dev/null
@@ -1,295 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * logfile.h - Defines for NTFS kernel journal ($LogFile) handling.  Part of
- *	       the Linux-NTFS project.
- *
- * Copyright (c) 2000-2005 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_LOGFILE_H
-#define _LINUX_NTFS_LOGFILE_H
-
-#ifdef NTFS_RW
-
-#include <linux/fs.h>
-
-#include "types.h"
-#include "endian.h"
-#include "layout.h"
-
-/*
- * Journal ($LogFile) organization:
- *
- * Two restart areas present in the first two pages (restart pages, one restart
- * area in each page).  When the volume is dismounted they should be identical,
- * except for the update sequence array which usually has a different update
- * sequence number.
- *
- * These are followed by log records organized in pages headed by a log record
- * header going up to log file size.  Not all pages contain log records when a
- * volume is first formatted, but as the volume ages, all records will be used.
- * When the log file fills up, the records at the beginning are purged (by
- * modifying the oldest_lsn to a higher value presumably) and writing begins
- * at the beginning of the file.  Effectively, the log file is viewed as a
- * circular entity.
- *
- * NOTE: Windows NT, 2000, and XP all use log file version 1.1 but they accept
- * versions <= 1.x, including 0.-1.  (Yes, that is a minus one in there!)  We
- * probably only want to support 1.1 as this seems to be the current version
- * and we don't know how that differs from the older versions.  The only
- * exception is if the journal is clean as marked by the two restart pages
- * then it doesn't matter whether we are on an earlier version.  We can just
- * reinitialize the logfile and start again with version 1.1.
- */
-
-/* Some $LogFile related constants. */
-#define MaxLogFileSize		0x100000000ULL
-#define DefaultLogPageSize	4096
-#define MinLogRecordPages	48
-
-/*
- * Log file restart page header (begins the restart area).
- */
-typedef struct {
-/*Ofs*/
-/*  0	NTFS_RECORD; -- Unfolded here as gcc doesn't like unnamed structs. */
-/*  0*/	NTFS_RECORD_TYPE magic;	/* The magic is "RSTR". */
-/*  4*/	le16 usa_ofs;		/* See NTFS_RECORD definition in layout.h.
-				   When creating, set this to be immediately
-				   after this header structure (without any
-				   alignment). */
-/*  6*/	le16 usa_count;		/* See NTFS_RECORD definition in layout.h. */
-
-/*  8*/	leLSN chkdsk_lsn;	/* The last log file sequence number found by
-				   chkdsk.  Only used when the magic is changed
-				   to "CHKD".  Otherwise this is zero. */
-/* 16*/	le32 system_page_size;	/* Byte size of system pages when the log file
-				   was created, has to be >= 512 and a power of
-				   2.  Use this to calculate the required size
-				   of the usa (usa_count) and add it to usa_ofs.
-				   Then verify that the result is less than the
-				   value of the restart_area_offset. */
-/* 20*/	le32 log_page_size;	/* Byte size of log file pages, has to be >=
-				   512 and a power of 2.  The default is 4096
-				   and is used when the system page size is
-				   between 4096 and 8192.  Otherwise this is
-				   set to the system page size instead. */
-/* 24*/	le16 restart_area_offset;/* Byte offset from the start of this header to
-				   the RESTART_AREA.  Value has to be aligned
-				   to 8-byte boundary.  When creating, set this
-				   to be after the usa. */
-/* 26*/	sle16 minor_ver;	/* Log file minor version.  Only check if major
-				   version is 1. */
-/* 28*/	sle16 major_ver;	/* Log file major version.  We only support
-				   version 1.1. */
-/* sizeof() = 30 (0x1e) bytes */
-} __attribute__ ((__packed__)) RESTART_PAGE_HEADER;
-
-/*
- * Constant for the log client indices meaning that there are no client records
- * in this particular client array.  Also inside the client records themselves,
- * this means that there are no client records preceding or following this one.
- */
-#define LOGFILE_NO_CLIENT	cpu_to_le16(0xffff)
-#define LOGFILE_NO_CLIENT_CPU	0xffff
-
-/*
- * These are the so far known RESTART_AREA_* flags (16-bit) which contain
- * information about the log file in which they are present.
- */
-enum {
-	RESTART_VOLUME_IS_CLEAN	= cpu_to_le16(0x0002),
-	RESTART_SPACE_FILLER	= cpu_to_le16(0xffff), /* gcc: Force enum bit width to 16. */
-} __attribute__ ((__packed__));
-
-typedef le16 RESTART_AREA_FLAGS;
-
-/*
- * Log file restart area record.  The offset of this record is found by adding
- * the offset of the RESTART_PAGE_HEADER to the restart_area_offset value found
- * in it.  See notes at restart_area_offset above.
- */
-typedef struct {
-/*Ofs*/
-/*  0*/	leLSN current_lsn;	/* The current, i.e. last LSN inside the log
-				   when the restart area was last written.
-				   This happens often but what is the interval?
-				   Is it just fixed time or is it every time a
-				   check point is written or somethine else?
-				   On create set to 0. */
-/*  8*/	le16 log_clients;	/* Number of log client records in the array of
-				   log client records which follows this
-				   restart area.  Must be 1.  */
-/* 10*/	le16 client_free_list;	/* The index of the first free log client record
-				   in the array of log client records.
-				   LOGFILE_NO_CLIENT means that there are no
-				   free log client records in the array.
-				   If != LOGFILE_NO_CLIENT, check that
-				   log_clients > client_free_list.  On Win2k
-				   and presumably earlier, on a clean volume
-				   this is != LOGFILE_NO_CLIENT, and it should
-				   be 0, i.e. the first (and only) client
-				   record is free and thus the logfile is
-				   closed and hence clean.  A dirty volume
-				   would have left the logfile open and hence
-				   this would be LOGFILE_NO_CLIENT.  On WinXP
-				   and presumably later, the logfile is always
-				   open, even on clean shutdown so this should
-				   always be LOGFILE_NO_CLIENT. */
-/* 12*/	le16 client_in_use_list;/* The index of the first in-use log client
-				   record in the array of log client records.
-				   LOGFILE_NO_CLIENT means that there are no
-				   in-use log client records in the array.  If
-				   != LOGFILE_NO_CLIENT check that log_clients
-				   > client_in_use_list.  On Win2k and
-				   presumably earlier, on a clean volume this
-				   is LOGFILE_NO_CLIENT, i.e. there are no
-				   client records in use and thus the logfile
-				   is closed and hence clean.  A dirty volume
-				   would have left the logfile open and hence
-				   this would be != LOGFILE_NO_CLIENT, and it
-				   should be 0, i.e. the first (and only)
-				   client record is in use.  On WinXP and
-				   presumably later, the logfile is always
-				   open, even on clean shutdown so this should
-				   always be 0. */
-/* 14*/	RESTART_AREA_FLAGS flags;/* Flags modifying LFS behaviour.  On Win2k
-				   and presumably earlier this is always 0.  On
-				   WinXP and presumably later, if the logfile
-				   was shutdown cleanly, the second bit,
-				   RESTART_VOLUME_IS_CLEAN, is set.  This bit
-				   is cleared when the volume is mounted by
-				   WinXP and set when the volume is dismounted,
-				   thus if the logfile is dirty, this bit is
-				   clear.  Thus we don't need to check the
-				   Windows version to determine if the logfile
-				   is clean.  Instead if the logfile is closed,
-				   we know it must be clean.  If it is open and
-				   this bit is set, we also know it must be
-				   clean.  If on the other hand the logfile is
-				   open and this bit is clear, we can be almost
-				   certain that the logfile is dirty. */
-/* 16*/	le32 seq_number_bits;	/* How many bits to use for the sequence
-				   number.  This is calculated as 67 - the
-				   number of bits required to store the logfile
-				   size in bytes and this can be used in with
-				   the specified file_size as a consistency
-				   check. */
-/* 20*/	le16 restart_area_length;/* Length of the restart area including the
-				   client array.  Following checks required if
-				   version matches.  Otherwise, skip them.
-				   restart_area_offset + restart_area_length
-				   has to be <= system_page_size.  Also,
-				   restart_area_length has to be >=
-				   client_array_offset + (log_clients *
-				   sizeof(log client record)). */
-/* 22*/	le16 client_array_offset;/* Offset from the start of this record to
-				   the first log client record if versions are
-				   matched.  When creating, set this to be
-				   after this restart area structure, aligned
-				   to 8-bytes boundary.  If the versions do not
-				   match, this is ignored and the offset is
-				   assumed to be (sizeof(RESTART_AREA) + 7) &
-				   ~7, i.e. rounded up to first 8-byte
-				   boundary.  Either way, client_array_offset
-				   has to be aligned to an 8-byte boundary.
-				   Also, restart_area_offset +
-				   client_array_offset has to be <= 510.
-				   Finally, client_array_offset + (log_clients
-				   * sizeof(log client record)) has to be <=
-				   system_page_size.  On Win2k and presumably
-				   earlier, this is 0x30, i.e. immediately
-				   following this record.  On WinXP and
-				   presumably later, this is 0x40, i.e. there
-				   are 16 extra bytes between this record and
-				   the client array.  This probably means that
-				   the RESTART_AREA record is actually bigger
-				   in WinXP and later. */
-/* 24*/	sle64 file_size;	/* Usable byte size of the log file.  If the
-				   restart_area_offset + the offset of the
-				   file_size are > 510 then corruption has
-				   occurred.  This is the very first check when
-				   starting with the restart_area as if it
-				   fails it means that some of the above values
-				   will be corrupted by the multi sector
-				   transfer protection.  The file_size has to
-				   be rounded down to be a multiple of the
-				   log_page_size in the RESTART_PAGE_HEADER and
-				   then it has to be at least big enough to
-				   store the two restart pages and 48 (0x30)
-				   log record pages. */
-/* 32*/	le32 last_lsn_data_length;/* Length of data of last LSN, not including
-				   the log record header.  On create set to
-				   0. */
-/* 36*/	le16 log_record_header_length;/* Byte size of the log record header.
-				   If the version matches then check that the
-				   value of log_record_header_length is a
-				   multiple of 8, i.e.
-				   (log_record_header_length + 7) & ~7 ==
-				   log_record_header_length.  When creating set
-				   it to sizeof(LOG_RECORD_HEADER), aligned to
-				   8 bytes. */
-/* 38*/	le16 log_page_data_offset;/* Offset to the start of data in a log record
-				   page.  Must be a multiple of 8.  On create
-				   set it to immediately after the update
-				   sequence array of the log record page. */
-/* 40*/	le32 restart_log_open_count;/* A counter that gets incremented every
-				   time the logfile is restarted which happens
-				   at mount time when the logfile is opened.
-				   When creating set to a random value.  Win2k
-				   sets it to the low 32 bits of the current
-				   system time in NTFS format (see time.h). */
-/* 44*/	le32 reserved;		/* Reserved/alignment to 8-byte boundary. */
-/* sizeof() = 48 (0x30) bytes */
-} __attribute__ ((__packed__)) RESTART_AREA;
-
-/*
- * Log client record.  The offset of this record is found by adding the offset
- * of the RESTART_AREA to the client_array_offset value found in it.
- */
-typedef struct {
-/*Ofs*/
-/*  0*/	leLSN oldest_lsn;	/* Oldest LSN needed by this client.  On create
-				   set to 0. */
-/*  8*/	leLSN client_restart_lsn;/* LSN at which this client needs to restart
-				   the volume, i.e. the current position within
-				   the log file.  At present, if clean this
-				   should = current_lsn in restart area but it
-				   probably also = current_lsn when dirty most
-				   of the time.  At create set to 0. */
-/* 16*/	le16 prev_client;	/* The offset to the previous log client record
-				   in the array of log client records.
-				   LOGFILE_NO_CLIENT means there is no previous
-				   client record, i.e. this is the first one.
-				   This is always LOGFILE_NO_CLIENT. */
-/* 18*/	le16 next_client;	/* The offset to the next log client record in
-				   the array of log client records.
-				   LOGFILE_NO_CLIENT means there are no next
-				   client records, i.e. this is the last one.
-				   This is always LOGFILE_NO_CLIENT. */
-/* 20*/	le16 seq_number;	/* On Win2k and presumably earlier, this is set
-				   to zero every time the logfile is restarted
-				   and it is incremented when the logfile is
-				   closed at dismount time.  Thus it is 0 when
-				   dirty and 1 when clean.  On WinXP and
-				   presumably later, this is always 0. */
-/* 22*/	u8 reserved[6];		/* Reserved/alignment. */
-/* 28*/	le32 client_name_length;/* Length of client name in bytes.  Should
-				   always be 8. */
-/* 32*/	ntfschar client_name[64];/* Name of the client in Unicode.  Should
-				   always be "NTFS" with the remaining bytes
-				   set to 0. */
-/* sizeof() = 160 (0xa0) bytes */
-} __attribute__ ((__packed__)) LOG_CLIENT_RECORD;
-
-extern bool ntfs_check_logfile(struct inode *log_vi,
-		RESTART_PAGE_HEADER **rp);
-
-extern bool ntfs_is_logfile_clean(struct inode *log_vi,
-		const RESTART_PAGE_HEADER *rp);
-
-extern bool ntfs_empty_logfile(struct inode *log_vi);
-
-#endif /* NTFS_RW */
-
-#endif /* _LINUX_NTFS_LOGFILE_H */
diff --git a/fs/ntfs/malloc.h b/fs/ntfs/malloc.h
deleted file mode 100644
index 7068425735f1..000000000000
--- a/fs/ntfs/malloc.h
+++ /dev/null
@@ -1,77 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * malloc.h - NTFS kernel memory handling. Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2005 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_MALLOC_H
-#define _LINUX_NTFS_MALLOC_H
-
-#include <linux/vmalloc.h>
-#include <linux/slab.h>
-#include <linux/highmem.h>
-
-/**
- * __ntfs_malloc - allocate memory in multiples of pages
- * @size:	number of bytes to allocate
- * @gfp_mask:	extra flags for the allocator
- *
- * Internal function.  You probably want ntfs_malloc_nofs()...
- *
- * Allocates @size bytes of memory, rounded up to multiples of PAGE_SIZE and
- * returns a pointer to the allocated memory.
- *
- * If there was insufficient memory to complete the request, return NULL.
- * Depending on @gfp_mask the allocation may be guaranteed to succeed.
- */
-static inline void *__ntfs_malloc(unsigned long size, gfp_t gfp_mask)
-{
-	if (likely(size <= PAGE_SIZE)) {
-		BUG_ON(!size);
-		/* kmalloc() has per-CPU caches so is faster for now. */
-		return kmalloc(PAGE_SIZE, gfp_mask & ~__GFP_HIGHMEM);
-		/* return (void *)__get_free_page(gfp_mask); */
-	}
-	if (likely((size >> PAGE_SHIFT) < totalram_pages()))
-		return __vmalloc(size, gfp_mask);
-	return NULL;
-}
-
-/**
- * ntfs_malloc_nofs - allocate memory in multiples of pages
- * @size:	number of bytes to allocate
- *
- * Allocates @size bytes of memory, rounded up to multiples of PAGE_SIZE and
- * returns a pointer to the allocated memory.
- *
- * If there was insufficient memory to complete the request, return NULL.
- */
-static inline void *ntfs_malloc_nofs(unsigned long size)
-{
-	return __ntfs_malloc(size, GFP_NOFS | __GFP_HIGHMEM);
-}
-
-/**
- * ntfs_malloc_nofs_nofail - allocate memory in multiples of pages
- * @size:	number of bytes to allocate
- *
- * Allocates @size bytes of memory, rounded up to multiples of PAGE_SIZE and
- * returns a pointer to the allocated memory.
- *
- * This function guarantees that the allocation will succeed.  It will sleep
- * for as long as it takes to complete the allocation.
- *
- * If there was insufficient memory to complete the request, return NULL.
- */
-static inline void *ntfs_malloc_nofs_nofail(unsigned long size)
-{
-	return __ntfs_malloc(size, GFP_NOFS | __GFP_HIGHMEM | __GFP_NOFAIL);
-}
-
-static inline void ntfs_free(void *addr)
-{
-	kvfree(addr);
-}
-
-#endif /* _LINUX_NTFS_MALLOC_H */
diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c
deleted file mode 100644
index 6fd1dc4b08c8..000000000000
--- a/fs/ntfs/mft.c
+++ /dev/null
@@ -1,2907 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * mft.c - NTFS kernel mft record operations. Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2012 Anton Altaparmakov and Tuxera Inc.
- * Copyright (c) 2002 Richard Russon
- */
-
-#include <linux/buffer_head.h>
-#include <linux/slab.h>
-#include <linux/swap.h>
-#include <linux/bio.h>
-
-#include "attrib.h"
-#include "aops.h"
-#include "bitmap.h"
-#include "debug.h"
-#include "dir.h"
-#include "lcnalloc.h"
-#include "malloc.h"
-#include "mft.h"
-#include "ntfs.h"
-
-#define MAX_BHS	(PAGE_SIZE / NTFS_BLOCK_SIZE)
-
-/**
- * map_mft_record_page - map the page in which a specific mft record resides
- * @ni:		ntfs inode whose mft record page to map
- *
- * This maps the page in which the mft record of the ntfs inode @ni is situated
- * and returns a pointer to the mft record within the mapped page.
- *
- * Return value needs to be checked with IS_ERR() and if that is true PTR_ERR()
- * contains the negative error code returned.
- */
-static inline MFT_RECORD *map_mft_record_page(ntfs_inode *ni)
-{
-	loff_t i_size;
-	ntfs_volume *vol = ni->vol;
-	struct inode *mft_vi = vol->mft_ino;
-	struct page *page;
-	unsigned long index, end_index;
-	unsigned ofs;
-
-	BUG_ON(ni->page);
-	/*
-	 * The index into the page cache and the offset within the page cache
-	 * page of the wanted mft record. FIXME: We need to check for
-	 * overflowing the unsigned long, but I don't think we would ever get
-	 * here if the volume was that big...
-	 */
-	index = (u64)ni->mft_no << vol->mft_record_size_bits >>
-			PAGE_SHIFT;
-	ofs = (ni->mft_no << vol->mft_record_size_bits) & ~PAGE_MASK;
-
-	i_size = i_size_read(mft_vi);
-	/* The maximum valid index into the page cache for $MFT's data. */
-	end_index = i_size >> PAGE_SHIFT;
-
-	/* If the wanted index is out of bounds the mft record doesn't exist. */
-	if (unlikely(index >= end_index)) {
-		if (index > end_index || (i_size & ~PAGE_MASK) < ofs +
-				vol->mft_record_size) {
-			page = ERR_PTR(-ENOENT);
-			ntfs_error(vol->sb, "Attempt to read mft record 0x%lx, "
-					"which is beyond the end of the mft.  "
-					"This is probably a bug in the ntfs "
-					"driver.", ni->mft_no);
-			goto err_out;
-		}
-	}
-	/* Read, map, and pin the page. */
-	page = ntfs_map_page(mft_vi->i_mapping, index);
-	if (!IS_ERR(page)) {
-		/* Catch multi sector transfer fixup errors. */
-		if (likely(ntfs_is_mft_recordp((le32*)(page_address(page) +
-				ofs)))) {
-			ni->page = page;
-			ni->page_ofs = ofs;
-			return page_address(page) + ofs;
-		}
-		ntfs_error(vol->sb, "Mft record 0x%lx is corrupt.  "
-				"Run chkdsk.", ni->mft_no);
-		ntfs_unmap_page(page);
-		page = ERR_PTR(-EIO);
-		NVolSetErrors(vol);
-	}
-err_out:
-	ni->page = NULL;
-	ni->page_ofs = 0;
-	return (void*)page;
-}
-
-/**
- * map_mft_record - map, pin and lock an mft record
- * @ni:		ntfs inode whose MFT record to map
- *
- * First, take the mrec_lock mutex.  We might now be sleeping, while waiting
- * for the mutex if it was already locked by someone else.
- *
- * The page of the record is mapped using map_mft_record_page() before being
- * returned to the caller.
- *
- * This in turn uses ntfs_map_page() to get the page containing the wanted mft
- * record (it in turn calls read_cache_page() which reads it in from disk if
- * necessary, increments the use count on the page so that it cannot disappear
- * under us and returns a reference to the page cache page).
- *
- * If read_cache_page() invokes ntfs_readpage() to load the page from disk, it
- * sets PG_locked and clears PG_uptodate on the page. Once I/O has completed
- * and the post-read mst fixups on each mft record in the page have been
- * performed, the page gets PG_uptodate set and PG_locked cleared (this is done
- * in our asynchronous I/O completion handler end_buffer_read_mft_async()).
- * ntfs_map_page() waits for PG_locked to become clear and checks if
- * PG_uptodate is set and returns an error code if not. This provides
- * sufficient protection against races when reading/using the page.
- *
- * However there is the write mapping to think about. Doing the above described
- * checking here will be fine, because when initiating the write we will set
- * PG_locked and clear PG_uptodate making sure nobody is touching the page
- * contents. Doing the locking this way means that the commit to disk code in
- * the page cache code paths is automatically sufficiently locked with us as
- * we will not touch a page that has been locked or is not uptodate. The only
- * locking problem then is them locking the page while we are accessing it.
- *
- * So that code will end up having to own the mrec_lock of all mft
- * records/inodes present in the page before I/O can proceed. In that case we
- * wouldn't need to bother with PG_locked and PG_uptodate as nobody will be
- * accessing anything without owning the mrec_lock mutex.  But we do need to
- * use them because of the read_cache_page() invocation and the code becomes so
- * much simpler this way that it is well worth it.
- *
- * The mft record is now ours and we return a pointer to it. You need to check
- * the returned pointer with IS_ERR() and if that is true, PTR_ERR() will return
- * the error code.
- *
- * NOTE: Caller is responsible for setting the mft record dirty before calling
- * unmap_mft_record(). This is obviously only necessary if the caller really
- * modified the mft record...
- * Q: Do we want to recycle one of the VFS inode state bits instead?
- * A: No, the inode ones mean we want to change the mft record, not we want to
- * write it out.
- */
-MFT_RECORD *map_mft_record(ntfs_inode *ni)
-{
-	MFT_RECORD *m;
-
-	ntfs_debug("Entering for mft_no 0x%lx.", ni->mft_no);
-
-	/* Make sure the ntfs inode doesn't go away. */
-	atomic_inc(&ni->count);
-
-	/* Serialize access to this mft record. */
-	mutex_lock(&ni->mrec_lock);
-
-	m = map_mft_record_page(ni);
-	if (!IS_ERR(m))
-		return m;
-
-	mutex_unlock(&ni->mrec_lock);
-	atomic_dec(&ni->count);
-	ntfs_error(ni->vol->sb, "Failed with error code %lu.", -PTR_ERR(m));
-	return m;
-}
-
-/**
- * unmap_mft_record_page - unmap the page in which a specific mft record resides
- * @ni:		ntfs inode whose mft record page to unmap
- *
- * This unmaps the page in which the mft record of the ntfs inode @ni is
- * situated and returns. This is a NOOP if highmem is not configured.
- *
- * The unmap happens via ntfs_unmap_page() which in turn decrements the use
- * count on the page thus releasing it from the pinned state.
- *
- * We do not actually unmap the page from memory of course, as that will be
- * done by the page cache code itself when memory pressure increases or
- * whatever.
- */
-static inline void unmap_mft_record_page(ntfs_inode *ni)
-{
-	BUG_ON(!ni->page);
-
-	// TODO: If dirty, blah...
-	ntfs_unmap_page(ni->page);
-	ni->page = NULL;
-	ni->page_ofs = 0;
-	return;
-}
-
-/**
- * unmap_mft_record - release a mapped mft record
- * @ni:		ntfs inode whose MFT record to unmap
- *
- * We release the page mapping and the mrec_lock mutex which unmaps the mft
- * record and releases it for others to get hold of. We also release the ntfs
- * inode by decrementing the ntfs inode reference count.
- *
- * NOTE: If caller has modified the mft record, it is imperative to set the mft
- * record dirty BEFORE calling unmap_mft_record().
- */
-void unmap_mft_record(ntfs_inode *ni)
-{
-	struct page *page = ni->page;
-
-	BUG_ON(!page);
-
-	ntfs_debug("Entering for mft_no 0x%lx.", ni->mft_no);
-
-	unmap_mft_record_page(ni);
-	mutex_unlock(&ni->mrec_lock);
-	atomic_dec(&ni->count);
-	/*
-	 * If pure ntfs_inode, i.e. no vfs inode attached, we leave it to
-	 * ntfs_clear_extent_inode() in the extent inode case, and to the
-	 * caller in the non-extent, yet pure ntfs inode case, to do the actual
-	 * tear down of all structures and freeing of all allocated memory.
-	 */
-	return;
-}
-
-/**
- * map_extent_mft_record - load an extent inode and attach it to its base
- * @base_ni:	base ntfs inode
- * @mref:	mft reference of the extent inode to load
- * @ntfs_ino:	on successful return, pointer to the ntfs_inode structure
- *
- * Load the extent mft record @mref and attach it to its base inode @base_ni.
- * Return the mapped extent mft record if IS_ERR(result) is false.  Otherwise
- * PTR_ERR(result) gives the negative error code.
- *
- * On successful return, @ntfs_ino contains a pointer to the ntfs_inode
- * structure of the mapped extent inode.
- */
-MFT_RECORD *map_extent_mft_record(ntfs_inode *base_ni, MFT_REF mref,
-		ntfs_inode **ntfs_ino)
-{
-	MFT_RECORD *m;
-	ntfs_inode *ni = NULL;
-	ntfs_inode **extent_nis = NULL;
-	int i;
-	unsigned long mft_no = MREF(mref);
-	u16 seq_no = MSEQNO(mref);
-	bool destroy_ni = false;
-
-	ntfs_debug("Mapping extent mft record 0x%lx (base mft record 0x%lx).",
-			mft_no, base_ni->mft_no);
-	/* Make sure the base ntfs inode doesn't go away. */
-	atomic_inc(&base_ni->count);
-	/*
-	 * Check if this extent inode has already been added to the base inode,
-	 * in which case just return it. If not found, add it to the base
-	 * inode before returning it.
-	 */
-	mutex_lock(&base_ni->extent_lock);
-	if (base_ni->nr_extents > 0) {
-		extent_nis = base_ni->ext.extent_ntfs_inos;
-		for (i = 0; i < base_ni->nr_extents; i++) {
-			if (mft_no != extent_nis[i]->mft_no)
-				continue;
-			ni = extent_nis[i];
-			/* Make sure the ntfs inode doesn't go away. */
-			atomic_inc(&ni->count);
-			break;
-		}
-	}
-	if (likely(ni != NULL)) {
-		mutex_unlock(&base_ni->extent_lock);
-		atomic_dec(&base_ni->count);
-		/* We found the record; just have to map and return it. */
-		m = map_mft_record(ni);
-		/* map_mft_record() has incremented this on success. */
-		atomic_dec(&ni->count);
-		if (!IS_ERR(m)) {
-			/* Verify the sequence number. */
-			if (likely(le16_to_cpu(m->sequence_number) == seq_no)) {
-				ntfs_debug("Done 1.");
-				*ntfs_ino = ni;
-				return m;
-			}
-			unmap_mft_record(ni);
-			ntfs_error(base_ni->vol->sb, "Found stale extent mft "
-					"reference! Corrupt filesystem. "
-					"Run chkdsk.");
-			return ERR_PTR(-EIO);
-		}
-map_err_out:
-		ntfs_error(base_ni->vol->sb, "Failed to map extent "
-				"mft record, error code %ld.", -PTR_ERR(m));
-		return m;
-	}
-	/* Record wasn't there. Get a new ntfs inode and initialize it. */
-	ni = ntfs_new_extent_inode(base_ni->vol->sb, mft_no);
-	if (unlikely(!ni)) {
-		mutex_unlock(&base_ni->extent_lock);
-		atomic_dec(&base_ni->count);
-		return ERR_PTR(-ENOMEM);
-	}
-	ni->vol = base_ni->vol;
-	ni->seq_no = seq_no;
-	ni->nr_extents = -1;
-	ni->ext.base_ntfs_ino = base_ni;
-	/* Now map the record. */
-	m = map_mft_record(ni);
-	if (IS_ERR(m)) {
-		mutex_unlock(&base_ni->extent_lock);
-		atomic_dec(&base_ni->count);
-		ntfs_clear_extent_inode(ni);
-		goto map_err_out;
-	}
-	/* Verify the sequence number if it is present. */
-	if (seq_no && (le16_to_cpu(m->sequence_number) != seq_no)) {
-		ntfs_error(base_ni->vol->sb, "Found stale extent mft "
-				"reference! Corrupt filesystem. Run chkdsk.");
-		destroy_ni = true;
-		m = ERR_PTR(-EIO);
-		goto unm_err_out;
-	}
-	/* Attach extent inode to base inode, reallocating memory if needed. */
-	if (!(base_ni->nr_extents & 3)) {
-		ntfs_inode **tmp;
-		int new_size = (base_ni->nr_extents + 4) * sizeof(ntfs_inode *);
-
-		tmp = kmalloc(new_size, GFP_NOFS);
-		if (unlikely(!tmp)) {
-			ntfs_error(base_ni->vol->sb, "Failed to allocate "
-					"internal buffer.");
-			destroy_ni = true;
-			m = ERR_PTR(-ENOMEM);
-			goto unm_err_out;
-		}
-		if (base_ni->nr_extents) {
-			BUG_ON(!base_ni->ext.extent_ntfs_inos);
-			memcpy(tmp, base_ni->ext.extent_ntfs_inos, new_size -
-					4 * sizeof(ntfs_inode *));
-			kfree(base_ni->ext.extent_ntfs_inos);
-		}
-		base_ni->ext.extent_ntfs_inos = tmp;
-	}
-	base_ni->ext.extent_ntfs_inos[base_ni->nr_extents++] = ni;
-	mutex_unlock(&base_ni->extent_lock);
-	atomic_dec(&base_ni->count);
-	ntfs_debug("Done 2.");
-	*ntfs_ino = ni;
-	return m;
-unm_err_out:
-	unmap_mft_record(ni);
-	mutex_unlock(&base_ni->extent_lock);
-	atomic_dec(&base_ni->count);
-	/*
-	 * If the extent inode was not attached to the base inode we need to
-	 * release it or we will leak memory.
-	 */
-	if (destroy_ni)
-		ntfs_clear_extent_inode(ni);
-	return m;
-}
-
-#ifdef NTFS_RW
-
-/**
- * __mark_mft_record_dirty - set the mft record and the page containing it dirty
- * @ni:		ntfs inode describing the mapped mft record
- *
- * Internal function.  Users should call mark_mft_record_dirty() instead.
- *
- * Set the mapped (extent) mft record of the (base or extent) ntfs inode @ni,
- * as well as the page containing the mft record, dirty.  Also, mark the base
- * vfs inode dirty.  This ensures that any changes to the mft record are
- * written out to disk.
- *
- * NOTE:  We only set I_DIRTY_DATASYNC (and not I_DIRTY_PAGES)
- * on the base vfs inode, because even though file data may have been modified,
- * it is dirty in the inode meta data rather than the data page cache of the
- * inode, and thus there are no data pages that need writing out.  Therefore, a
- * full mark_inode_dirty() is overkill.  A mark_inode_dirty_sync(), on the
- * other hand, is not sufficient, because ->write_inode needs to be called even
- * in case of fdatasync. This needs to happen or the file data would not
- * necessarily hit the device synchronously, even though the vfs inode has the
- * O_SYNC flag set.  Also, I_DIRTY_DATASYNC simply "feels" better than just
- * I_DIRTY_SYNC, since the file data has not actually hit the block device yet,
- * which is not what I_DIRTY_SYNC on its own would suggest.
- */
-void __mark_mft_record_dirty(ntfs_inode *ni)
-{
-	ntfs_inode *base_ni;
-
-	ntfs_debug("Entering for inode 0x%lx.", ni->mft_no);
-	BUG_ON(NInoAttr(ni));
-	mark_ntfs_record_dirty(ni->page, ni->page_ofs);
-	/* Determine the base vfs inode and mark it dirty, too. */
-	mutex_lock(&ni->extent_lock);
-	if (likely(ni->nr_extents >= 0))
-		base_ni = ni;
-	else
-		base_ni = ni->ext.base_ntfs_ino;
-	mutex_unlock(&ni->extent_lock);
-	__mark_inode_dirty(VFS_I(base_ni), I_DIRTY_DATASYNC);
-}
-
-static const char *ntfs_please_email = "Please email "
-		"linux-ntfs-dev@lists.sourceforge.net and say that you saw "
-		"this message.  Thank you.";
-
-/**
- * ntfs_sync_mft_mirror_umount - synchronise an mft record to the mft mirror
- * @vol:	ntfs volume on which the mft record to synchronize resides
- * @mft_no:	mft record number of mft record to synchronize
- * @m:		mapped, mst protected (extent) mft record to synchronize
- *
- * Write the mapped, mst protected (extent) mft record @m with mft record
- * number @mft_no to the mft mirror ($MFTMirr) of the ntfs volume @vol,
- * bypassing the page cache and the $MFTMirr inode itself.
- *
- * This function is only for use at umount time when the mft mirror inode has
- * already been disposed off.  We BUG() if we are called while the mft mirror
- * inode is still attached to the volume.
- *
- * On success return 0.  On error return -errno.
- *
- * NOTE:  This function is not implemented yet as I am not convinced it can
- * actually be triggered considering the sequence of commits we do in super.c::
- * ntfs_put_super().  But just in case we provide this place holder as the
- * alternative would be either to BUG() or to get a NULL pointer dereference
- * and Oops.
- */
-static int ntfs_sync_mft_mirror_umount(ntfs_volume *vol,
-		const unsigned long mft_no, MFT_RECORD *m)
-{
-	BUG_ON(vol->mftmirr_ino);
-	ntfs_error(vol->sb, "Umount time mft mirror syncing is not "
-			"implemented yet.  %s", ntfs_please_email);
-	return -EOPNOTSUPP;
-}
-
-/**
- * ntfs_sync_mft_mirror - synchronize an mft record to the mft mirror
- * @vol:	ntfs volume on which the mft record to synchronize resides
- * @mft_no:	mft record number of mft record to synchronize
- * @m:		mapped, mst protected (extent) mft record to synchronize
- * @sync:	if true, wait for i/o completion
- *
- * Write the mapped, mst protected (extent) mft record @m with mft record
- * number @mft_no to the mft mirror ($MFTMirr) of the ntfs volume @vol.
- *
- * On success return 0.  On error return -errno and set the volume errors flag
- * in the ntfs volume @vol.
- *
- * NOTE:  We always perform synchronous i/o and ignore the @sync parameter.
- *
- * TODO:  If @sync is false, want to do truly asynchronous i/o, i.e. just
- * schedule i/o via ->writepage or do it via kntfsd or whatever.
- */
-int ntfs_sync_mft_mirror(ntfs_volume *vol, const unsigned long mft_no,
-		MFT_RECORD *m, int sync)
-{
-	struct page *page;
-	unsigned int blocksize = vol->sb->s_blocksize;
-	int max_bhs = vol->mft_record_size / blocksize;
-	struct buffer_head *bhs[MAX_BHS];
-	struct buffer_head *bh, *head;
-	u8 *kmirr;
-	runlist_element *rl;
-	unsigned int block_start, block_end, m_start, m_end, page_ofs;
-	int i_bhs, nr_bhs, err = 0;
-	unsigned char blocksize_bits = vol->sb->s_blocksize_bits;
-
-	ntfs_debug("Entering for inode 0x%lx.", mft_no);
-	BUG_ON(!max_bhs);
-	if (WARN_ON(max_bhs > MAX_BHS))
-		return -EINVAL;
-	if (unlikely(!vol->mftmirr_ino)) {
-		/* This could happen during umount... */
-		err = ntfs_sync_mft_mirror_umount(vol, mft_no, m);
-		if (likely(!err))
-			return err;
-		goto err_out;
-	}
-	/* Get the page containing the mirror copy of the mft record @m. */
-	page = ntfs_map_page(vol->mftmirr_ino->i_mapping, mft_no >>
-			(PAGE_SHIFT - vol->mft_record_size_bits));
-	if (IS_ERR(page)) {
-		ntfs_error(vol->sb, "Failed to map mft mirror page.");
-		err = PTR_ERR(page);
-		goto err_out;
-	}
-	lock_page(page);
-	BUG_ON(!PageUptodate(page));
-	ClearPageUptodate(page);
-	/* Offset of the mft mirror record inside the page. */
-	page_ofs = (mft_no << vol->mft_record_size_bits) & ~PAGE_MASK;
-	/* The address in the page of the mirror copy of the mft record @m. */
-	kmirr = page_address(page) + page_ofs;
-	/* Copy the mst protected mft record to the mirror. */
-	memcpy(kmirr, m, vol->mft_record_size);
-	/* Create uptodate buffers if not present. */
-	if (unlikely(!page_has_buffers(page))) {
-		struct buffer_head *tail;
-
-		bh = head = alloc_page_buffers(page, blocksize, true);
-		do {
-			set_buffer_uptodate(bh);
-			tail = bh;
-			bh = bh->b_this_page;
-		} while (bh);
-		tail->b_this_page = head;
-		attach_page_private(page, head);
-	}
-	bh = head = page_buffers(page);
-	BUG_ON(!bh);
-	rl = NULL;
-	nr_bhs = 0;
-	block_start = 0;
-	m_start = kmirr - (u8*)page_address(page);
-	m_end = m_start + vol->mft_record_size;
-	do {
-		block_end = block_start + blocksize;
-		/* If the buffer is outside the mft record, skip it. */
-		if (block_end <= m_start)
-			continue;
-		if (unlikely(block_start >= m_end))
-			break;
-		/* Need to map the buffer if it is not mapped already. */
-		if (unlikely(!buffer_mapped(bh))) {
-			VCN vcn;
-			LCN lcn;
-			unsigned int vcn_ofs;
-
-			bh->b_bdev = vol->sb->s_bdev;
-			/* Obtain the vcn and offset of the current block. */
-			vcn = ((VCN)mft_no << vol->mft_record_size_bits) +
-					(block_start - m_start);
-			vcn_ofs = vcn & vol->cluster_size_mask;
-			vcn >>= vol->cluster_size_bits;
-			if (!rl) {
-				down_read(&NTFS_I(vol->mftmirr_ino)->
-						runlist.lock);
-				rl = NTFS_I(vol->mftmirr_ino)->runlist.rl;
-				/*
-				 * $MFTMirr always has the whole of its runlist
-				 * in memory.
-				 */
-				BUG_ON(!rl);
-			}
-			/* Seek to element containing target vcn. */
-			while (rl->length && rl[1].vcn <= vcn)
-				rl++;
-			lcn = ntfs_rl_vcn_to_lcn(rl, vcn);
-			/* For $MFTMirr, only lcn >= 0 is a successful remap. */
-			if (likely(lcn >= 0)) {
-				/* Setup buffer head to correct block. */
-				bh->b_blocknr = ((lcn <<
-						vol->cluster_size_bits) +
-						vcn_ofs) >> blocksize_bits;
-				set_buffer_mapped(bh);
-			} else {
-				bh->b_blocknr = -1;
-				ntfs_error(vol->sb, "Cannot write mft mirror "
-						"record 0x%lx because its "
-						"location on disk could not "
-						"be determined (error code "
-						"%lli).", mft_no,
-						(long long)lcn);
-				err = -EIO;
-			}
-		}
-		BUG_ON(!buffer_uptodate(bh));
-		BUG_ON(!nr_bhs && (m_start != block_start));
-		BUG_ON(nr_bhs >= max_bhs);
-		bhs[nr_bhs++] = bh;
-		BUG_ON((nr_bhs >= max_bhs) && (m_end != block_end));
-	} while (block_start = block_end, (bh = bh->b_this_page) != head);
-	if (unlikely(rl))
-		up_read(&NTFS_I(vol->mftmirr_ino)->runlist.lock);
-	if (likely(!err)) {
-		/* Lock buffers and start synchronous write i/o on them. */
-		for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++) {
-			struct buffer_head *tbh = bhs[i_bhs];
-
-			if (!trylock_buffer(tbh))
-				BUG();
-			BUG_ON(!buffer_uptodate(tbh));
-			clear_buffer_dirty(tbh);
-			get_bh(tbh);
-			tbh->b_end_io = end_buffer_write_sync;
-			submit_bh(REQ_OP_WRITE, tbh);
-		}
-		/* Wait on i/o completion of buffers. */
-		for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++) {
-			struct buffer_head *tbh = bhs[i_bhs];
-
-			wait_on_buffer(tbh);
-			if (unlikely(!buffer_uptodate(tbh))) {
-				err = -EIO;
-				/*
-				 * Set the buffer uptodate so the page and
-				 * buffer states do not become out of sync.
-				 */
-				set_buffer_uptodate(tbh);
-			}
-		}
-	} else /* if (unlikely(err)) */ {
-		/* Clean the buffers. */
-		for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++)
-			clear_buffer_dirty(bhs[i_bhs]);
-	}
-	/* Current state: all buffers are clean, unlocked, and uptodate. */
-	/* Remove the mst protection fixups again. */
-	post_write_mst_fixup((NTFS_RECORD*)kmirr);
-	flush_dcache_page(page);
-	SetPageUptodate(page);
-	unlock_page(page);
-	ntfs_unmap_page(page);
-	if (likely(!err)) {
-		ntfs_debug("Done.");
-	} else {
-		ntfs_error(vol->sb, "I/O error while writing mft mirror "
-				"record 0x%lx!", mft_no);
-err_out:
-		ntfs_error(vol->sb, "Failed to synchronize $MFTMirr (error "
-				"code %i).  Volume will be left marked dirty "
-				"on umount.  Run ntfsfix on the partition "
-				"after umounting to correct this.", -err);
-		NVolSetErrors(vol);
-	}
-	return err;
-}
-
-/**
- * write_mft_record_nolock - write out a mapped (extent) mft record
- * @ni:		ntfs inode describing the mapped (extent) mft record
- * @m:		mapped (extent) mft record to write
- * @sync:	if true, wait for i/o completion
- *
- * Write the mapped (extent) mft record @m described by the (regular or extent)
- * ntfs inode @ni to backing store.  If the mft record @m has a counterpart in
- * the mft mirror, that is also updated.
- *
- * We only write the mft record if the ntfs inode @ni is dirty and the first
- * buffer belonging to its mft record is dirty, too.  We ignore the dirty state
- * of subsequent buffers because we could have raced with
- * fs/ntfs/aops.c::mark_ntfs_record_dirty().
- *
- * On success, clean the mft record and return 0.  On error, leave the mft
- * record dirty and return -errno.
- *
- * NOTE:  We always perform synchronous i/o and ignore the @sync parameter.
- * However, if the mft record has a counterpart in the mft mirror and @sync is
- * true, we write the mft record, wait for i/o completion, and only then write
- * the mft mirror copy.  This ensures that if the system crashes either the mft
- * or the mft mirror will contain a self-consistent mft record @m.  If @sync is
- * false on the other hand, we start i/o on both and then wait for completion
- * on them.  This provides a speedup but no longer guarantees that you will end
- * up with a self-consistent mft record in the case of a crash but if you asked
- * for asynchronous writing you probably do not care about that anyway.
- *
- * TODO:  If @sync is false, want to do truly asynchronous i/o, i.e. just
- * schedule i/o via ->writepage or do it via kntfsd or whatever.
- */
-int write_mft_record_nolock(ntfs_inode *ni, MFT_RECORD *m, int sync)
-{
-	ntfs_volume *vol = ni->vol;
-	struct page *page = ni->page;
-	unsigned int blocksize = vol->sb->s_blocksize;
-	unsigned char blocksize_bits = vol->sb->s_blocksize_bits;
-	int max_bhs = vol->mft_record_size / blocksize;
-	struct buffer_head *bhs[MAX_BHS];
-	struct buffer_head *bh, *head;
-	runlist_element *rl;
-	unsigned int block_start, block_end, m_start, m_end;
-	int i_bhs, nr_bhs, err = 0;
-
-	ntfs_debug("Entering for inode 0x%lx.", ni->mft_no);
-	BUG_ON(NInoAttr(ni));
-	BUG_ON(!max_bhs);
-	BUG_ON(!PageLocked(page));
-	if (WARN_ON(max_bhs > MAX_BHS)) {
-		err = -EINVAL;
-		goto err_out;
-	}
-	/*
-	 * If the ntfs_inode is clean no need to do anything.  If it is dirty,
-	 * mark it as clean now so that it can be redirtied later on if needed.
-	 * There is no danger of races since the caller is holding the locks
-	 * for the mft record @m and the page it is in.
-	 */
-	if (!NInoTestClearDirty(ni))
-		goto done;
-	bh = head = page_buffers(page);
-	BUG_ON(!bh);
-	rl = NULL;
-	nr_bhs = 0;
-	block_start = 0;
-	m_start = ni->page_ofs;
-	m_end = m_start + vol->mft_record_size;
-	do {
-		block_end = block_start + blocksize;
-		/* If the buffer is outside the mft record, skip it. */
-		if (block_end <= m_start)
-			continue;
-		if (unlikely(block_start >= m_end))
-			break;
-		/*
-		 * If this block is not the first one in the record, we ignore
-		 * the buffer's dirty state because we could have raced with a
-		 * parallel mark_ntfs_record_dirty().
-		 */
-		if (block_start == m_start) {
-			/* This block is the first one in the record. */
-			if (!buffer_dirty(bh)) {
-				BUG_ON(nr_bhs);
-				/* Clean records are not written out. */
-				break;
-			}
-		}
-		/* Need to map the buffer if it is not mapped already. */
-		if (unlikely(!buffer_mapped(bh))) {
-			VCN vcn;
-			LCN lcn;
-			unsigned int vcn_ofs;
-
-			bh->b_bdev = vol->sb->s_bdev;
-			/* Obtain the vcn and offset of the current block. */
-			vcn = ((VCN)ni->mft_no << vol->mft_record_size_bits) +
-					(block_start - m_start);
-			vcn_ofs = vcn & vol->cluster_size_mask;
-			vcn >>= vol->cluster_size_bits;
-			if (!rl) {
-				down_read(&NTFS_I(vol->mft_ino)->runlist.lock);
-				rl = NTFS_I(vol->mft_ino)->runlist.rl;
-				BUG_ON(!rl);
-			}
-			/* Seek to element containing target vcn. */
-			while (rl->length && rl[1].vcn <= vcn)
-				rl++;
-			lcn = ntfs_rl_vcn_to_lcn(rl, vcn);
-			/* For $MFT, only lcn >= 0 is a successful remap. */
-			if (likely(lcn >= 0)) {
-				/* Setup buffer head to correct block. */
-				bh->b_blocknr = ((lcn <<
-						vol->cluster_size_bits) +
-						vcn_ofs) >> blocksize_bits;
-				set_buffer_mapped(bh);
-			} else {
-				bh->b_blocknr = -1;
-				ntfs_error(vol->sb, "Cannot write mft record "
-						"0x%lx because its location "
-						"on disk could not be "
-						"determined (error code %lli).",
-						ni->mft_no, (long long)lcn);
-				err = -EIO;
-			}
-		}
-		BUG_ON(!buffer_uptodate(bh));
-		BUG_ON(!nr_bhs && (m_start != block_start));
-		BUG_ON(nr_bhs >= max_bhs);
-		bhs[nr_bhs++] = bh;
-		BUG_ON((nr_bhs >= max_bhs) && (m_end != block_end));
-	} while (block_start = block_end, (bh = bh->b_this_page) != head);
-	if (unlikely(rl))
-		up_read(&NTFS_I(vol->mft_ino)->runlist.lock);
-	if (!nr_bhs)
-		goto done;
-	if (unlikely(err))
-		goto cleanup_out;
-	/* Apply the mst protection fixups. */
-	err = pre_write_mst_fixup((NTFS_RECORD*)m, vol->mft_record_size);
-	if (err) {
-		ntfs_error(vol->sb, "Failed to apply mst fixups!");
-		goto cleanup_out;
-	}
-	flush_dcache_mft_record_page(ni);
-	/* Lock buffers and start synchronous write i/o on them. */
-	for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++) {
-		struct buffer_head *tbh = bhs[i_bhs];
-
-		if (!trylock_buffer(tbh))
-			BUG();
-		BUG_ON(!buffer_uptodate(tbh));
-		clear_buffer_dirty(tbh);
-		get_bh(tbh);
-		tbh->b_end_io = end_buffer_write_sync;
-		submit_bh(REQ_OP_WRITE, tbh);
-	}
-	/* Synchronize the mft mirror now if not @sync. */
-	if (!sync && ni->mft_no < vol->mftmirr_size)
-		ntfs_sync_mft_mirror(vol, ni->mft_no, m, sync);
-	/* Wait on i/o completion of buffers. */
-	for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++) {
-		struct buffer_head *tbh = bhs[i_bhs];
-
-		wait_on_buffer(tbh);
-		if (unlikely(!buffer_uptodate(tbh))) {
-			err = -EIO;
-			/*
-			 * Set the buffer uptodate so the page and buffer
-			 * states do not become out of sync.
-			 */
-			if (PageUptodate(page))
-				set_buffer_uptodate(tbh);
-		}
-	}
-	/* If @sync, now synchronize the mft mirror. */
-	if (sync && ni->mft_no < vol->mftmirr_size)
-		ntfs_sync_mft_mirror(vol, ni->mft_no, m, sync);
-	/* Remove the mst protection fixups again. */
-	post_write_mst_fixup((NTFS_RECORD*)m);
-	flush_dcache_mft_record_page(ni);
-	if (unlikely(err)) {
-		/* I/O error during writing.  This is really bad! */
-		ntfs_error(vol->sb, "I/O error while writing mft record "
-				"0x%lx!  Marking base inode as bad.  You "
-				"should unmount the volume and run chkdsk.",
-				ni->mft_no);
-		goto err_out;
-	}
-done:
-	ntfs_debug("Done.");
-	return 0;
-cleanup_out:
-	/* Clean the buffers. */
-	for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++)
-		clear_buffer_dirty(bhs[i_bhs]);
-err_out:
-	/*
-	 * Current state: all buffers are clean, unlocked, and uptodate.
-	 * The caller should mark the base inode as bad so that no more i/o
-	 * happens.  ->clear_inode() will still be invoked so all extent inodes
-	 * and other allocated memory will be freed.
-	 */
-	if (err == -ENOMEM) {
-		ntfs_error(vol->sb, "Not enough memory to write mft record.  "
-				"Redirtying so the write is retried later.");
-		mark_mft_record_dirty(ni);
-		err = 0;
-	} else
-		NVolSetErrors(vol);
-	return err;
-}
-
-/**
- * ntfs_may_write_mft_record - check if an mft record may be written out
- * @vol:	[IN]  ntfs volume on which the mft record to check resides
- * @mft_no:	[IN]  mft record number of the mft record to check
- * @m:		[IN]  mapped mft record to check
- * @locked_ni:	[OUT] caller has to unlock this ntfs inode if one is returned
- *
- * Check if the mapped (base or extent) mft record @m with mft record number
- * @mft_no belonging to the ntfs volume @vol may be written out.  If necessary
- * and possible the ntfs inode of the mft record is locked and the base vfs
- * inode is pinned.  The locked ntfs inode is then returned in @locked_ni.  The
- * caller is responsible for unlocking the ntfs inode and unpinning the base
- * vfs inode.
- *
- * Return 'true' if the mft record may be written out and 'false' if not.
- *
- * The caller has locked the page and cleared the uptodate flag on it which
- * means that we can safely write out any dirty mft records that do not have
- * their inodes in icache as determined by ilookup5() as anyone
- * opening/creating such an inode would block when attempting to map the mft
- * record in read_cache_page() until we are finished with the write out.
- *
- * Here is a description of the tests we perform:
- *
- * If the inode is found in icache we know the mft record must be a base mft
- * record.  If it is dirty, we do not write it and return 'false' as the vfs
- * inode write paths will result in the access times being updated which would
- * cause the base mft record to be redirtied and written out again.  (We know
- * the access time update will modify the base mft record because Windows
- * chkdsk complains if the standard information attribute is not in the base
- * mft record.)
- *
- * If the inode is in icache and not dirty, we attempt to lock the mft record
- * and if we find the lock was already taken, it is not safe to write the mft
- * record and we return 'false'.
- *
- * If we manage to obtain the lock we have exclusive access to the mft record,
- * which also allows us safe writeout of the mft record.  We then set
- * @locked_ni to the locked ntfs inode and return 'true'.
- *
- * Note we cannot just lock the mft record and sleep while waiting for the lock
- * because this would deadlock due to lock reversal (normally the mft record is
- * locked before the page is locked but we already have the page locked here
- * when we try to lock the mft record).
- *
- * If the inode is not in icache we need to perform further checks.
- *
- * If the mft record is not a FILE record or it is a base mft record, we can
- * safely write it and return 'true'.
- *
- * We now know the mft record is an extent mft record.  We check if the inode
- * corresponding to its base mft record is in icache and obtain a reference to
- * it if it is.  If it is not, we can safely write it and return 'true'.
- *
- * We now have the base inode for the extent mft record.  We check if it has an
- * ntfs inode for the extent mft record attached and if not it is safe to write
- * the extent mft record and we return 'true'.
- *
- * The ntfs inode for the extent mft record is attached to the base inode so we
- * attempt to lock the extent mft record and if we find the lock was already
- * taken, it is not safe to write the extent mft record and we return 'false'.
- *
- * If we manage to obtain the lock we have exclusive access to the extent mft
- * record, which also allows us safe writeout of the extent mft record.  We
- * set the ntfs inode of the extent mft record clean and then set @locked_ni to
- * the now locked ntfs inode and return 'true'.
- *
- * Note, the reason for actually writing dirty mft records here and not just
- * relying on the vfs inode dirty code paths is that we can have mft records
- * modified without them ever having actual inodes in memory.  Also we can have
- * dirty mft records with clean ntfs inodes in memory.  None of the described
- * cases would result in the dirty mft records being written out if we only
- * relied on the vfs inode dirty code paths.  And these cases can really occur
- * during allocation of new mft records and in particular when the
- * initialized_size of the $MFT/$DATA attribute is extended and the new space
- * is initialized using ntfs_mft_record_format().  The clean inode can then
- * appear if the mft record is reused for a new inode before it got written
- * out.
- */
-bool ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no,
-		const MFT_RECORD *m, ntfs_inode **locked_ni)
-{
-	struct super_block *sb = vol->sb;
-	struct inode *mft_vi = vol->mft_ino;
-	struct inode *vi;
-	ntfs_inode *ni, *eni, **extent_nis;
-	int i;
-	ntfs_attr na;
-
-	ntfs_debug("Entering for inode 0x%lx.", mft_no);
-	/*
-	 * Normally we do not return a locked inode so set @locked_ni to NULL.
-	 */
-	BUG_ON(!locked_ni);
-	*locked_ni = NULL;
-	/*
-	 * Check if the inode corresponding to this mft record is in the VFS
-	 * inode cache and obtain a reference to it if it is.
-	 */
-	ntfs_debug("Looking for inode 0x%lx in icache.", mft_no);
-	na.mft_no = mft_no;
-	na.name = NULL;
-	na.name_len = 0;
-	na.type = AT_UNUSED;
-	/*
-	 * Optimize inode 0, i.e. $MFT itself, since we have it in memory and
-	 * we get here for it rather often.
-	 */
-	if (!mft_no) {
-		/* Balance the below iput(). */
-		vi = igrab(mft_vi);
-		BUG_ON(vi != mft_vi);
-	} else {
-		/*
-		 * Have to use ilookup5_nowait() since ilookup5() waits for the
-		 * inode lock which causes ntfs to deadlock when a concurrent
-		 * inode write via the inode dirty code paths and the page
-		 * dirty code path of the inode dirty code path when writing
-		 * $MFT occurs.
-		 */
-		vi = ilookup5_nowait(sb, mft_no, ntfs_test_inode, &na);
-	}
-	if (vi) {
-		ntfs_debug("Base inode 0x%lx is in icache.", mft_no);
-		/* The inode is in icache. */
-		ni = NTFS_I(vi);
-		/* Take a reference to the ntfs inode. */
-		atomic_inc(&ni->count);
-		/* If the inode is dirty, do not write this record. */
-		if (NInoDirty(ni)) {
-			ntfs_debug("Inode 0x%lx is dirty, do not write it.",
-					mft_no);
-			atomic_dec(&ni->count);
-			iput(vi);
-			return false;
-		}
-		ntfs_debug("Inode 0x%lx is not dirty.", mft_no);
-		/* The inode is not dirty, try to take the mft record lock. */
-		if (unlikely(!mutex_trylock(&ni->mrec_lock))) {
-			ntfs_debug("Mft record 0x%lx is already locked, do "
-					"not write it.", mft_no);
-			atomic_dec(&ni->count);
-			iput(vi);
-			return false;
-		}
-		ntfs_debug("Managed to lock mft record 0x%lx, write it.",
-				mft_no);
-		/*
-		 * The write has to occur while we hold the mft record lock so
-		 * return the locked ntfs inode.
-		 */
-		*locked_ni = ni;
-		return true;
-	}
-	ntfs_debug("Inode 0x%lx is not in icache.", mft_no);
-	/* The inode is not in icache. */
-	/* Write the record if it is not a mft record (type "FILE"). */
-	if (!ntfs_is_mft_record(m->magic)) {
-		ntfs_debug("Mft record 0x%lx is not a FILE record, write it.",
-				mft_no);
-		return true;
-	}
-	/* Write the mft record if it is a base inode. */
-	if (!m->base_mft_record) {
-		ntfs_debug("Mft record 0x%lx is a base record, write it.",
-				mft_no);
-		return true;
-	}
-	/*
-	 * This is an extent mft record.  Check if the inode corresponding to
-	 * its base mft record is in icache and obtain a reference to it if it
-	 * is.
-	 */
-	na.mft_no = MREF_LE(m->base_mft_record);
-	ntfs_debug("Mft record 0x%lx is an extent record.  Looking for base "
-			"inode 0x%lx in icache.", mft_no, na.mft_no);
-	if (!na.mft_no) {
-		/* Balance the below iput(). */
-		vi = igrab(mft_vi);
-		BUG_ON(vi != mft_vi);
-	} else
-		vi = ilookup5_nowait(sb, na.mft_no, ntfs_test_inode,
-				&na);
-	if (!vi) {
-		/*
-		 * The base inode is not in icache, write this extent mft
-		 * record.
-		 */
-		ntfs_debug("Base inode 0x%lx is not in icache, write the "
-				"extent record.", na.mft_no);
-		return true;
-	}
-	ntfs_debug("Base inode 0x%lx is in icache.", na.mft_no);
-	/*
-	 * The base inode is in icache.  Check if it has the extent inode
-	 * corresponding to this extent mft record attached.
-	 */
-	ni = NTFS_I(vi);
-	mutex_lock(&ni->extent_lock);
-	if (ni->nr_extents <= 0) {
-		/*
-		 * The base inode has no attached extent inodes, write this
-		 * extent mft record.
-		 */
-		mutex_unlock(&ni->extent_lock);
-		iput(vi);
-		ntfs_debug("Base inode 0x%lx has no attached extent inodes, "
-				"write the extent record.", na.mft_no);
-		return true;
-	}
-	/* Iterate over the attached extent inodes. */
-	extent_nis = ni->ext.extent_ntfs_inos;
-	for (eni = NULL, i = 0; i < ni->nr_extents; ++i) {
-		if (mft_no == extent_nis[i]->mft_no) {
-			/*
-			 * Found the extent inode corresponding to this extent
-			 * mft record.
-			 */
-			eni = extent_nis[i];
-			break;
-		}
-	}
-	/*
-	 * If the extent inode was not attached to the base inode, write this
-	 * extent mft record.
-	 */
-	if (!eni) {
-		mutex_unlock(&ni->extent_lock);
-		iput(vi);
-		ntfs_debug("Extent inode 0x%lx is not attached to its base "
-				"inode 0x%lx, write the extent record.",
-				mft_no, na.mft_no);
-		return true;
-	}
-	ntfs_debug("Extent inode 0x%lx is attached to its base inode 0x%lx.",
-			mft_no, na.mft_no);
-	/* Take a reference to the extent ntfs inode. */
-	atomic_inc(&eni->count);
-	mutex_unlock(&ni->extent_lock);
-	/*
-	 * Found the extent inode coresponding to this extent mft record.
-	 * Try to take the mft record lock.
-	 */
-	if (unlikely(!mutex_trylock(&eni->mrec_lock))) {
-		atomic_dec(&eni->count);
-		iput(vi);
-		ntfs_debug("Extent mft record 0x%lx is already locked, do "
-				"not write it.", mft_no);
-		return false;
-	}
-	ntfs_debug("Managed to lock extent mft record 0x%lx, write it.",
-			mft_no);
-	if (NInoTestClearDirty(eni))
-		ntfs_debug("Extent inode 0x%lx is dirty, marking it clean.",
-				mft_no);
-	/*
-	 * The write has to occur while we hold the mft record lock so return
-	 * the locked extent ntfs inode.
-	 */
-	*locked_ni = eni;
-	return true;
-}
-
-static const char *es = "  Leaving inconsistent metadata.  Unmount and run "
-		"chkdsk.";
-
-/**
- * ntfs_mft_bitmap_find_and_alloc_free_rec_nolock - see name
- * @vol:	volume on which to search for a free mft record
- * @base_ni:	open base inode if allocating an extent mft record or NULL
- *
- * Search for a free mft record in the mft bitmap attribute on the ntfs volume
- * @vol.
- *
- * If @base_ni is NULL start the search at the default allocator position.
- *
- * If @base_ni is not NULL start the search at the mft record after the base
- * mft record @base_ni.
- *
- * Return the free mft record on success and -errno on error.  An error code of
- * -ENOSPC means that there are no free mft records in the currently
- * initialized mft bitmap.
- *
- * Locking: Caller must hold vol->mftbmp_lock for writing.
- */
-static int ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(ntfs_volume *vol,
-		ntfs_inode *base_ni)
-{
-	s64 pass_end, ll, data_pos, pass_start, ofs, bit;
-	unsigned long flags;
-	struct address_space *mftbmp_mapping;
-	u8 *buf, *byte;
-	struct page *page;
-	unsigned int page_ofs, size;
-	u8 pass, b;
-
-	ntfs_debug("Searching for free mft record in the currently "
-			"initialized mft bitmap.");
-	mftbmp_mapping = vol->mftbmp_ino->i_mapping;
-	/*
-	 * Set the end of the pass making sure we do not overflow the mft
-	 * bitmap.
-	 */
-	read_lock_irqsave(&NTFS_I(vol->mft_ino)->size_lock, flags);
-	pass_end = NTFS_I(vol->mft_ino)->allocated_size >>
-			vol->mft_record_size_bits;
-	read_unlock_irqrestore(&NTFS_I(vol->mft_ino)->size_lock, flags);
-	read_lock_irqsave(&NTFS_I(vol->mftbmp_ino)->size_lock, flags);
-	ll = NTFS_I(vol->mftbmp_ino)->initialized_size << 3;
-	read_unlock_irqrestore(&NTFS_I(vol->mftbmp_ino)->size_lock, flags);
-	if (pass_end > ll)
-		pass_end = ll;
-	pass = 1;
-	if (!base_ni)
-		data_pos = vol->mft_data_pos;
-	else
-		data_pos = base_ni->mft_no + 1;
-	if (data_pos < 24)
-		data_pos = 24;
-	if (data_pos >= pass_end) {
-		data_pos = 24;
-		pass = 2;
-		/* This happens on a freshly formatted volume. */
-		if (data_pos >= pass_end)
-			return -ENOSPC;
-	}
-	pass_start = data_pos;
-	ntfs_debug("Starting bitmap search: pass %u, pass_start 0x%llx, "
-			"pass_end 0x%llx, data_pos 0x%llx.", pass,
-			(long long)pass_start, (long long)pass_end,
-			(long long)data_pos);
-	/* Loop until a free mft record is found. */
-	for (; pass <= 2;) {
-		/* Cap size to pass_end. */
-		ofs = data_pos >> 3;
-		page_ofs = ofs & ~PAGE_MASK;
-		size = PAGE_SIZE - page_ofs;
-		ll = ((pass_end + 7) >> 3) - ofs;
-		if (size > ll)
-			size = ll;
-		size <<= 3;
-		/*
-		 * If we are still within the active pass, search the next page
-		 * for a zero bit.
-		 */
-		if (size) {
-			page = ntfs_map_page(mftbmp_mapping,
-					ofs >> PAGE_SHIFT);
-			if (IS_ERR(page)) {
-				ntfs_error(vol->sb, "Failed to read mft "
-						"bitmap, aborting.");
-				return PTR_ERR(page);
-			}
-			buf = (u8*)page_address(page) + page_ofs;
-			bit = data_pos & 7;
-			data_pos &= ~7ull;
-			ntfs_debug("Before inner for loop: size 0x%x, "
-					"data_pos 0x%llx, bit 0x%llx", size,
-					(long long)data_pos, (long long)bit);
-			for (; bit < size && data_pos + bit < pass_end;
-					bit &= ~7ull, bit += 8) {
-				byte = buf + (bit >> 3);
-				if (*byte == 0xff)
-					continue;
-				b = ffz((unsigned long)*byte);
-				if (b < 8 && b >= (bit & 7)) {
-					ll = data_pos + (bit & ~7ull) + b;
-					if (unlikely(ll > (1ll << 32))) {
-						ntfs_unmap_page(page);
-						return -ENOSPC;
-					}
-					*byte |= 1 << b;
-					flush_dcache_page(page);
-					set_page_dirty(page);
-					ntfs_unmap_page(page);
-					ntfs_debug("Done.  (Found and "
-							"allocated mft record "
-							"0x%llx.)",
-							(long long)ll);
-					return ll;
-				}
-			}
-			ntfs_debug("After inner for loop: size 0x%x, "
-					"data_pos 0x%llx, bit 0x%llx", size,
-					(long long)data_pos, (long long)bit);
-			data_pos += size;
-			ntfs_unmap_page(page);
-			/*
-			 * If the end of the pass has not been reached yet,
-			 * continue searching the mft bitmap for a zero bit.
-			 */
-			if (data_pos < pass_end)
-				continue;
-		}
-		/* Do the next pass. */
-		if (++pass == 2) {
-			/*
-			 * Starting the second pass, in which we scan the first
-			 * part of the zone which we omitted earlier.
-			 */
-			pass_end = pass_start;
-			data_pos = pass_start = 24;
-			ntfs_debug("pass %i, pass_start 0x%llx, pass_end "
-					"0x%llx.", pass, (long long)pass_start,
-					(long long)pass_end);
-			if (data_pos >= pass_end)
-				break;
-		}
-	}
-	/* No free mft records in currently initialized mft bitmap. */
-	ntfs_debug("Done.  (No free mft records left in currently initialized "
-			"mft bitmap.)");
-	return -ENOSPC;
-}
-
-/**
- * ntfs_mft_bitmap_extend_allocation_nolock - extend mft bitmap by a cluster
- * @vol:	volume on which to extend the mft bitmap attribute
- *
- * Extend the mft bitmap attribute on the ntfs volume @vol by one cluster.
- *
- * Note: Only changes allocated_size, i.e. does not touch initialized_size or
- * data_size.
- *
- * Return 0 on success and -errno on error.
- *
- * Locking: - Caller must hold vol->mftbmp_lock for writing.
- *	    - This function takes NTFS_I(vol->mftbmp_ino)->runlist.lock for
- *	      writing and releases it before returning.
- *	    - This function takes vol->lcnbmp_lock for writing and releases it
- *	      before returning.
- */
-static int ntfs_mft_bitmap_extend_allocation_nolock(ntfs_volume *vol)
-{
-	LCN lcn;
-	s64 ll;
-	unsigned long flags;
-	struct page *page;
-	ntfs_inode *mft_ni, *mftbmp_ni;
-	runlist_element *rl, *rl2 = NULL;
-	ntfs_attr_search_ctx *ctx = NULL;
-	MFT_RECORD *mrec;
-	ATTR_RECORD *a = NULL;
-	int ret, mp_size;
-	u32 old_alen = 0;
-	u8 *b, tb;
-	struct {
-		u8 added_cluster:1;
-		u8 added_run:1;
-		u8 mp_rebuilt:1;
-	} status = { 0, 0, 0 };
-
-	ntfs_debug("Extending mft bitmap allocation.");
-	mft_ni = NTFS_I(vol->mft_ino);
-	mftbmp_ni = NTFS_I(vol->mftbmp_ino);
-	/*
-	 * Determine the last lcn of the mft bitmap.  The allocated size of the
-	 * mft bitmap cannot be zero so we are ok to do this.
-	 */
-	down_write(&mftbmp_ni->runlist.lock);
-	read_lock_irqsave(&mftbmp_ni->size_lock, flags);
-	ll = mftbmp_ni->allocated_size;
-	read_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-	rl = ntfs_attr_find_vcn_nolock(mftbmp_ni,
-			(ll - 1) >> vol->cluster_size_bits, NULL);
-	if (IS_ERR(rl) || unlikely(!rl->length || rl->lcn < 0)) {
-		up_write(&mftbmp_ni->runlist.lock);
-		ntfs_error(vol->sb, "Failed to determine last allocated "
-				"cluster of mft bitmap attribute.");
-		if (!IS_ERR(rl))
-			ret = -EIO;
-		else
-			ret = PTR_ERR(rl);
-		return ret;
-	}
-	lcn = rl->lcn + rl->length;
-	ntfs_debug("Last lcn of mft bitmap attribute is 0x%llx.",
-			(long long)lcn);
-	/*
-	 * Attempt to get the cluster following the last allocated cluster by
-	 * hand as it may be in the MFT zone so the allocator would not give it
-	 * to us.
-	 */
-	ll = lcn >> 3;
-	page = ntfs_map_page(vol->lcnbmp_ino->i_mapping,
-			ll >> PAGE_SHIFT);
-	if (IS_ERR(page)) {
-		up_write(&mftbmp_ni->runlist.lock);
-		ntfs_error(vol->sb, "Failed to read from lcn bitmap.");
-		return PTR_ERR(page);
-	}
-	b = (u8*)page_address(page) + (ll & ~PAGE_MASK);
-	tb = 1 << (lcn & 7ull);
-	down_write(&vol->lcnbmp_lock);
-	if (*b != 0xff && !(*b & tb)) {
-		/* Next cluster is free, allocate it. */
-		*b |= tb;
-		flush_dcache_page(page);
-		set_page_dirty(page);
-		up_write(&vol->lcnbmp_lock);
-		ntfs_unmap_page(page);
-		/* Update the mft bitmap runlist. */
-		rl->length++;
-		rl[1].vcn++;
-		status.added_cluster = 1;
-		ntfs_debug("Appending one cluster to mft bitmap.");
-	} else {
-		up_write(&vol->lcnbmp_lock);
-		ntfs_unmap_page(page);
-		/* Allocate a cluster from the DATA_ZONE. */
-		rl2 = ntfs_cluster_alloc(vol, rl[1].vcn, 1, lcn, DATA_ZONE,
-				true);
-		if (IS_ERR(rl2)) {
-			up_write(&mftbmp_ni->runlist.lock);
-			ntfs_error(vol->sb, "Failed to allocate a cluster for "
-					"the mft bitmap.");
-			return PTR_ERR(rl2);
-		}
-		rl = ntfs_runlists_merge(mftbmp_ni->runlist.rl, rl2);
-		if (IS_ERR(rl)) {
-			up_write(&mftbmp_ni->runlist.lock);
-			ntfs_error(vol->sb, "Failed to merge runlists for mft "
-					"bitmap.");
-			if (ntfs_cluster_free_from_rl(vol, rl2)) {
-				ntfs_error(vol->sb, "Failed to deallocate "
-						"allocated cluster.%s", es);
-				NVolSetErrors(vol);
-			}
-			ntfs_free(rl2);
-			return PTR_ERR(rl);
-		}
-		mftbmp_ni->runlist.rl = rl;
-		status.added_run = 1;
-		ntfs_debug("Adding one run to mft bitmap.");
-		/* Find the last run in the new runlist. */
-		for (; rl[1].length; rl++)
-			;
-	}
-	/*
-	 * Update the attribute record as well.  Note: @rl is the last
-	 * (non-terminator) runlist element of mft bitmap.
-	 */
-	mrec = map_mft_record(mft_ni);
-	if (IS_ERR(mrec)) {
-		ntfs_error(vol->sb, "Failed to map mft record.");
-		ret = PTR_ERR(mrec);
-		goto undo_alloc;
-	}
-	ctx = ntfs_attr_get_search_ctx(mft_ni, mrec);
-	if (unlikely(!ctx)) {
-		ntfs_error(vol->sb, "Failed to get search context.");
-		ret = -ENOMEM;
-		goto undo_alloc;
-	}
-	ret = ntfs_attr_lookup(mftbmp_ni->type, mftbmp_ni->name,
-			mftbmp_ni->name_len, CASE_SENSITIVE, rl[1].vcn, NULL,
-			0, ctx);
-	if (unlikely(ret)) {
-		ntfs_error(vol->sb, "Failed to find last attribute extent of "
-				"mft bitmap attribute.");
-		if (ret == -ENOENT)
-			ret = -EIO;
-		goto undo_alloc;
-	}
-	a = ctx->attr;
-	ll = sle64_to_cpu(a->data.non_resident.lowest_vcn);
-	/* Search back for the previous last allocated cluster of mft bitmap. */
-	for (rl2 = rl; rl2 > mftbmp_ni->runlist.rl; rl2--) {
-		if (ll >= rl2->vcn)
-			break;
-	}
-	BUG_ON(ll < rl2->vcn);
-	BUG_ON(ll >= rl2->vcn + rl2->length);
-	/* Get the size for the new mapping pairs array for this extent. */
-	mp_size = ntfs_get_size_for_mapping_pairs(vol, rl2, ll, -1);
-	if (unlikely(mp_size <= 0)) {
-		ntfs_error(vol->sb, "Get size for mapping pairs failed for "
-				"mft bitmap attribute extent.");
-		ret = mp_size;
-		if (!ret)
-			ret = -EIO;
-		goto undo_alloc;
-	}
-	/* Expand the attribute record if necessary. */
-	old_alen = le32_to_cpu(a->length);
-	ret = ntfs_attr_record_resize(ctx->mrec, a, mp_size +
-			le16_to_cpu(a->data.non_resident.mapping_pairs_offset));
-	if (unlikely(ret)) {
-		if (ret != -ENOSPC) {
-			ntfs_error(vol->sb, "Failed to resize attribute "
-					"record for mft bitmap attribute.");
-			goto undo_alloc;
-		}
-		// TODO: Deal with this by moving this extent to a new mft
-		// record or by starting a new extent in a new mft record or by
-		// moving other attributes out of this mft record.
-		// Note: It will need to be a special mft record and if none of
-		// those are available it gets rather complicated...
-		ntfs_error(vol->sb, "Not enough space in this mft record to "
-				"accommodate extended mft bitmap attribute "
-				"extent.  Cannot handle this yet.");
-		ret = -EOPNOTSUPP;
-		goto undo_alloc;
-	}
-	status.mp_rebuilt = 1;
-	/* Generate the mapping pairs array directly into the attr record. */
-	ret = ntfs_mapping_pairs_build(vol, (u8*)a +
-			le16_to_cpu(a->data.non_resident.mapping_pairs_offset),
-			mp_size, rl2, ll, -1, NULL);
-	if (unlikely(ret)) {
-		ntfs_error(vol->sb, "Failed to build mapping pairs array for "
-				"mft bitmap attribute.");
-		goto undo_alloc;
-	}
-	/* Update the highest_vcn. */
-	a->data.non_resident.highest_vcn = cpu_to_sle64(rl[1].vcn - 1);
-	/*
-	 * We now have extended the mft bitmap allocated_size by one cluster.
-	 * Reflect this in the ntfs_inode structure and the attribute record.
-	 */
-	if (a->data.non_resident.lowest_vcn) {
-		/*
-		 * We are not in the first attribute extent, switch to it, but
-		 * first ensure the changes will make it to disk later.
-		 */
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
-		mark_mft_record_dirty(ctx->ntfs_ino);
-		ntfs_attr_reinit_search_ctx(ctx);
-		ret = ntfs_attr_lookup(mftbmp_ni->type, mftbmp_ni->name,
-				mftbmp_ni->name_len, CASE_SENSITIVE, 0, NULL,
-				0, ctx);
-		if (unlikely(ret)) {
-			ntfs_error(vol->sb, "Failed to find first attribute "
-					"extent of mft bitmap attribute.");
-			goto restore_undo_alloc;
-		}
-		a = ctx->attr;
-	}
-	write_lock_irqsave(&mftbmp_ni->size_lock, flags);
-	mftbmp_ni->allocated_size += vol->cluster_size;
-	a->data.non_resident.allocated_size =
-			cpu_to_sle64(mftbmp_ni->allocated_size);
-	write_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-	/* Ensure the changes make it to disk. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(mft_ni);
-	up_write(&mftbmp_ni->runlist.lock);
-	ntfs_debug("Done.");
-	return 0;
-restore_undo_alloc:
-	ntfs_attr_reinit_search_ctx(ctx);
-	if (ntfs_attr_lookup(mftbmp_ni->type, mftbmp_ni->name,
-			mftbmp_ni->name_len, CASE_SENSITIVE, rl[1].vcn, NULL,
-			0, ctx)) {
-		ntfs_error(vol->sb, "Failed to find last attribute extent of "
-				"mft bitmap attribute.%s", es);
-		write_lock_irqsave(&mftbmp_ni->size_lock, flags);
-		mftbmp_ni->allocated_size += vol->cluster_size;
-		write_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(mft_ni);
-		up_write(&mftbmp_ni->runlist.lock);
-		/*
-		 * The only thing that is now wrong is ->allocated_size of the
-		 * base attribute extent which chkdsk should be able to fix.
-		 */
-		NVolSetErrors(vol);
-		return ret;
-	}
-	a = ctx->attr;
-	a->data.non_resident.highest_vcn = cpu_to_sle64(rl[1].vcn - 2);
-undo_alloc:
-	if (status.added_cluster) {
-		/* Truncate the last run in the runlist by one cluster. */
-		rl->length--;
-		rl[1].vcn--;
-	} else if (status.added_run) {
-		lcn = rl->lcn;
-		/* Remove the last run from the runlist. */
-		rl->lcn = rl[1].lcn;
-		rl->length = 0;
-	}
-	/* Deallocate the cluster. */
-	down_write(&vol->lcnbmp_lock);
-	if (ntfs_bitmap_clear_bit(vol->lcnbmp_ino, lcn)) {
-		ntfs_error(vol->sb, "Failed to free allocated cluster.%s", es);
-		NVolSetErrors(vol);
-	}
-	up_write(&vol->lcnbmp_lock);
-	if (status.mp_rebuilt) {
-		if (ntfs_mapping_pairs_build(vol, (u8*)a + le16_to_cpu(
-				a->data.non_resident.mapping_pairs_offset),
-				old_alen - le16_to_cpu(
-				a->data.non_resident.mapping_pairs_offset),
-				rl2, ll, -1, NULL)) {
-			ntfs_error(vol->sb, "Failed to restore mapping pairs "
-					"array.%s", es);
-			NVolSetErrors(vol);
-		}
-		if (ntfs_attr_record_resize(ctx->mrec, a, old_alen)) {
-			ntfs_error(vol->sb, "Failed to restore attribute "
-					"record.%s", es);
-			NVolSetErrors(vol);
-		}
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
-		mark_mft_record_dirty(ctx->ntfs_ino);
-	}
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (!IS_ERR(mrec))
-		unmap_mft_record(mft_ni);
-	up_write(&mftbmp_ni->runlist.lock);
-	return ret;
-}
-
-/**
- * ntfs_mft_bitmap_extend_initialized_nolock - extend mftbmp initialized data
- * @vol:	volume on which to extend the mft bitmap attribute
- *
- * Extend the initialized portion of the mft bitmap attribute on the ntfs
- * volume @vol by 8 bytes.
- *
- * Note:  Only changes initialized_size and data_size, i.e. requires that
- * allocated_size is big enough to fit the new initialized_size.
- *
- * Return 0 on success and -error on error.
- *
- * Locking: Caller must hold vol->mftbmp_lock for writing.
- */
-static int ntfs_mft_bitmap_extend_initialized_nolock(ntfs_volume *vol)
-{
-	s64 old_data_size, old_initialized_size;
-	unsigned long flags;
-	struct inode *mftbmp_vi;
-	ntfs_inode *mft_ni, *mftbmp_ni;
-	ntfs_attr_search_ctx *ctx;
-	MFT_RECORD *mrec;
-	ATTR_RECORD *a;
-	int ret;
-
-	ntfs_debug("Extending mft bitmap initiailized (and data) size.");
-	mft_ni = NTFS_I(vol->mft_ino);
-	mftbmp_vi = vol->mftbmp_ino;
-	mftbmp_ni = NTFS_I(mftbmp_vi);
-	/* Get the attribute record. */
-	mrec = map_mft_record(mft_ni);
-	if (IS_ERR(mrec)) {
-		ntfs_error(vol->sb, "Failed to map mft record.");
-		return PTR_ERR(mrec);
-	}
-	ctx = ntfs_attr_get_search_ctx(mft_ni, mrec);
-	if (unlikely(!ctx)) {
-		ntfs_error(vol->sb, "Failed to get search context.");
-		ret = -ENOMEM;
-		goto unm_err_out;
-	}
-	ret = ntfs_attr_lookup(mftbmp_ni->type, mftbmp_ni->name,
-			mftbmp_ni->name_len, CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(ret)) {
-		ntfs_error(vol->sb, "Failed to find first attribute extent of "
-				"mft bitmap attribute.");
-		if (ret == -ENOENT)
-			ret = -EIO;
-		goto put_err_out;
-	}
-	a = ctx->attr;
-	write_lock_irqsave(&mftbmp_ni->size_lock, flags);
-	old_data_size = i_size_read(mftbmp_vi);
-	old_initialized_size = mftbmp_ni->initialized_size;
-	/*
-	 * We can simply update the initialized_size before filling the space
-	 * with zeroes because the caller is holding the mft bitmap lock for
-	 * writing which ensures that no one else is trying to access the data.
-	 */
-	mftbmp_ni->initialized_size += 8;
-	a->data.non_resident.initialized_size =
-			cpu_to_sle64(mftbmp_ni->initialized_size);
-	if (mftbmp_ni->initialized_size > old_data_size) {
-		i_size_write(mftbmp_vi, mftbmp_ni->initialized_size);
-		a->data.non_resident.data_size =
-				cpu_to_sle64(mftbmp_ni->initialized_size);
-	}
-	write_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-	/* Ensure the changes make it to disk. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(mft_ni);
-	/* Initialize the mft bitmap attribute value with zeroes. */
-	ret = ntfs_attr_set(mftbmp_ni, old_initialized_size, 8, 0);
-	if (likely(!ret)) {
-		ntfs_debug("Done.  (Wrote eight initialized bytes to mft "
-				"bitmap.");
-		return 0;
-	}
-	ntfs_error(vol->sb, "Failed to write to mft bitmap.");
-	/* Try to recover from the error. */
-	mrec = map_mft_record(mft_ni);
-	if (IS_ERR(mrec)) {
-		ntfs_error(vol->sb, "Failed to map mft record.%s", es);
-		NVolSetErrors(vol);
-		return ret;
-	}
-	ctx = ntfs_attr_get_search_ctx(mft_ni, mrec);
-	if (unlikely(!ctx)) {
-		ntfs_error(vol->sb, "Failed to get search context.%s", es);
-		NVolSetErrors(vol);
-		goto unm_err_out;
-	}
-	if (ntfs_attr_lookup(mftbmp_ni->type, mftbmp_ni->name,
-			mftbmp_ni->name_len, CASE_SENSITIVE, 0, NULL, 0, ctx)) {
-		ntfs_error(vol->sb, "Failed to find first attribute extent of "
-				"mft bitmap attribute.%s", es);
-		NVolSetErrors(vol);
-put_err_out:
-		ntfs_attr_put_search_ctx(ctx);
-unm_err_out:
-		unmap_mft_record(mft_ni);
-		goto err_out;
-	}
-	a = ctx->attr;
-	write_lock_irqsave(&mftbmp_ni->size_lock, flags);
-	mftbmp_ni->initialized_size = old_initialized_size;
-	a->data.non_resident.initialized_size =
-			cpu_to_sle64(old_initialized_size);
-	if (i_size_read(mftbmp_vi) != old_data_size) {
-		i_size_write(mftbmp_vi, old_data_size);
-		a->data.non_resident.data_size = cpu_to_sle64(old_data_size);
-	}
-	write_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(mft_ni);
-#ifdef DEBUG
-	read_lock_irqsave(&mftbmp_ni->size_lock, flags);
-	ntfs_debug("Restored status of mftbmp: allocated_size 0x%llx, "
-			"data_size 0x%llx, initialized_size 0x%llx.",
-			(long long)mftbmp_ni->allocated_size,
-			(long long)i_size_read(mftbmp_vi),
-			(long long)mftbmp_ni->initialized_size);
-	read_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-#endif /* DEBUG */
-err_out:
-	return ret;
-}
-
-/**
- * ntfs_mft_data_extend_allocation_nolock - extend mft data attribute
- * @vol:	volume on which to extend the mft data attribute
- *
- * Extend the mft data attribute on the ntfs volume @vol by 16 mft records
- * worth of clusters or if not enough space for this by one mft record worth
- * of clusters.
- *
- * Note:  Only changes allocated_size, i.e. does not touch initialized_size or
- * data_size.
- *
- * Return 0 on success and -errno on error.
- *
- * Locking: - Caller must hold vol->mftbmp_lock for writing.
- *	    - This function takes NTFS_I(vol->mft_ino)->runlist.lock for
- *	      writing and releases it before returning.
- *	    - This function calls functions which take vol->lcnbmp_lock for
- *	      writing and release it before returning.
- */
-static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol)
-{
-	LCN lcn;
-	VCN old_last_vcn;
-	s64 min_nr, nr, ll;
-	unsigned long flags;
-	ntfs_inode *mft_ni;
-	runlist_element *rl, *rl2;
-	ntfs_attr_search_ctx *ctx = NULL;
-	MFT_RECORD *mrec;
-	ATTR_RECORD *a = NULL;
-	int ret, mp_size;
-	u32 old_alen = 0;
-	bool mp_rebuilt = false;
-
-	ntfs_debug("Extending mft data allocation.");
-	mft_ni = NTFS_I(vol->mft_ino);
-	/*
-	 * Determine the preferred allocation location, i.e. the last lcn of
-	 * the mft data attribute.  The allocated size of the mft data
-	 * attribute cannot be zero so we are ok to do this.
-	 */
-	down_write(&mft_ni->runlist.lock);
-	read_lock_irqsave(&mft_ni->size_lock, flags);
-	ll = mft_ni->allocated_size;
-	read_unlock_irqrestore(&mft_ni->size_lock, flags);
-	rl = ntfs_attr_find_vcn_nolock(mft_ni,
-			(ll - 1) >> vol->cluster_size_bits, NULL);
-	if (IS_ERR(rl) || unlikely(!rl->length || rl->lcn < 0)) {
-		up_write(&mft_ni->runlist.lock);
-		ntfs_error(vol->sb, "Failed to determine last allocated "
-				"cluster of mft data attribute.");
-		if (!IS_ERR(rl))
-			ret = -EIO;
-		else
-			ret = PTR_ERR(rl);
-		return ret;
-	}
-	lcn = rl->lcn + rl->length;
-	ntfs_debug("Last lcn of mft data attribute is 0x%llx.", (long long)lcn);
-	/* Minimum allocation is one mft record worth of clusters. */
-	min_nr = vol->mft_record_size >> vol->cluster_size_bits;
-	if (!min_nr)
-		min_nr = 1;
-	/* Want to allocate 16 mft records worth of clusters. */
-	nr = vol->mft_record_size << 4 >> vol->cluster_size_bits;
-	if (!nr)
-		nr = min_nr;
-	/* Ensure we do not go above 2^32-1 mft records. */
-	read_lock_irqsave(&mft_ni->size_lock, flags);
-	ll = mft_ni->allocated_size;
-	read_unlock_irqrestore(&mft_ni->size_lock, flags);
-	if (unlikely((ll + (nr << vol->cluster_size_bits)) >>
-			vol->mft_record_size_bits >= (1ll << 32))) {
-		nr = min_nr;
-		if (unlikely((ll + (nr << vol->cluster_size_bits)) >>
-				vol->mft_record_size_bits >= (1ll << 32))) {
-			ntfs_warning(vol->sb, "Cannot allocate mft record "
-					"because the maximum number of inodes "
-					"(2^32) has already been reached.");
-			up_write(&mft_ni->runlist.lock);
-			return -ENOSPC;
-		}
-	}
-	ntfs_debug("Trying mft data allocation with %s cluster count %lli.",
-			nr > min_nr ? "default" : "minimal", (long long)nr);
-	old_last_vcn = rl[1].vcn;
-	do {
-		rl2 = ntfs_cluster_alloc(vol, old_last_vcn, nr, lcn, MFT_ZONE,
-				true);
-		if (!IS_ERR(rl2))
-			break;
-		if (PTR_ERR(rl2) != -ENOSPC || nr == min_nr) {
-			ntfs_error(vol->sb, "Failed to allocate the minimal "
-					"number of clusters (%lli) for the "
-					"mft data attribute.", (long long)nr);
-			up_write(&mft_ni->runlist.lock);
-			return PTR_ERR(rl2);
-		}
-		/*
-		 * There is not enough space to do the allocation, but there
-		 * might be enough space to do a minimal allocation so try that
-		 * before failing.
-		 */
-		nr = min_nr;
-		ntfs_debug("Retrying mft data allocation with minimal cluster "
-				"count %lli.", (long long)nr);
-	} while (1);
-	rl = ntfs_runlists_merge(mft_ni->runlist.rl, rl2);
-	if (IS_ERR(rl)) {
-		up_write(&mft_ni->runlist.lock);
-		ntfs_error(vol->sb, "Failed to merge runlists for mft data "
-				"attribute.");
-		if (ntfs_cluster_free_from_rl(vol, rl2)) {
-			ntfs_error(vol->sb, "Failed to deallocate clusters "
-					"from the mft data attribute.%s", es);
-			NVolSetErrors(vol);
-		}
-		ntfs_free(rl2);
-		return PTR_ERR(rl);
-	}
-	mft_ni->runlist.rl = rl;
-	ntfs_debug("Allocated %lli clusters.", (long long)nr);
-	/* Find the last run in the new runlist. */
-	for (; rl[1].length; rl++)
-		;
-	/* Update the attribute record as well. */
-	mrec = map_mft_record(mft_ni);
-	if (IS_ERR(mrec)) {
-		ntfs_error(vol->sb, "Failed to map mft record.");
-		ret = PTR_ERR(mrec);
-		goto undo_alloc;
-	}
-	ctx = ntfs_attr_get_search_ctx(mft_ni, mrec);
-	if (unlikely(!ctx)) {
-		ntfs_error(vol->sb, "Failed to get search context.");
-		ret = -ENOMEM;
-		goto undo_alloc;
-	}
-	ret = ntfs_attr_lookup(mft_ni->type, mft_ni->name, mft_ni->name_len,
-			CASE_SENSITIVE, rl[1].vcn, NULL, 0, ctx);
-	if (unlikely(ret)) {
-		ntfs_error(vol->sb, "Failed to find last attribute extent of "
-				"mft data attribute.");
-		if (ret == -ENOENT)
-			ret = -EIO;
-		goto undo_alloc;
-	}
-	a = ctx->attr;
-	ll = sle64_to_cpu(a->data.non_resident.lowest_vcn);
-	/* Search back for the previous last allocated cluster of mft bitmap. */
-	for (rl2 = rl; rl2 > mft_ni->runlist.rl; rl2--) {
-		if (ll >= rl2->vcn)
-			break;
-	}
-	BUG_ON(ll < rl2->vcn);
-	BUG_ON(ll >= rl2->vcn + rl2->length);
-	/* Get the size for the new mapping pairs array for this extent. */
-	mp_size = ntfs_get_size_for_mapping_pairs(vol, rl2, ll, -1);
-	if (unlikely(mp_size <= 0)) {
-		ntfs_error(vol->sb, "Get size for mapping pairs failed for "
-				"mft data attribute extent.");
-		ret = mp_size;
-		if (!ret)
-			ret = -EIO;
-		goto undo_alloc;
-	}
-	/* Expand the attribute record if necessary. */
-	old_alen = le32_to_cpu(a->length);
-	ret = ntfs_attr_record_resize(ctx->mrec, a, mp_size +
-			le16_to_cpu(a->data.non_resident.mapping_pairs_offset));
-	if (unlikely(ret)) {
-		if (ret != -ENOSPC) {
-			ntfs_error(vol->sb, "Failed to resize attribute "
-					"record for mft data attribute.");
-			goto undo_alloc;
-		}
-		// TODO: Deal with this by moving this extent to a new mft
-		// record or by starting a new extent in a new mft record or by
-		// moving other attributes out of this mft record.
-		// Note: Use the special reserved mft records and ensure that
-		// this extent is not required to find the mft record in
-		// question.  If no free special records left we would need to
-		// move an existing record away, insert ours in its place, and
-		// then place the moved record into the newly allocated space
-		// and we would then need to update all references to this mft
-		// record appropriately.  This is rather complicated...
-		ntfs_error(vol->sb, "Not enough space in this mft record to "
-				"accommodate extended mft data attribute "
-				"extent.  Cannot handle this yet.");
-		ret = -EOPNOTSUPP;
-		goto undo_alloc;
-	}
-	mp_rebuilt = true;
-	/* Generate the mapping pairs array directly into the attr record. */
-	ret = ntfs_mapping_pairs_build(vol, (u8*)a +
-			le16_to_cpu(a->data.non_resident.mapping_pairs_offset),
-			mp_size, rl2, ll, -1, NULL);
-	if (unlikely(ret)) {
-		ntfs_error(vol->sb, "Failed to build mapping pairs array of "
-				"mft data attribute.");
-		goto undo_alloc;
-	}
-	/* Update the highest_vcn. */
-	a->data.non_resident.highest_vcn = cpu_to_sle64(rl[1].vcn - 1);
-	/*
-	 * We now have extended the mft data allocated_size by nr clusters.
-	 * Reflect this in the ntfs_inode structure and the attribute record.
-	 * @rl is the last (non-terminator) runlist element of mft data
-	 * attribute.
-	 */
-	if (a->data.non_resident.lowest_vcn) {
-		/*
-		 * We are not in the first attribute extent, switch to it, but
-		 * first ensure the changes will make it to disk later.
-		 */
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
-		mark_mft_record_dirty(ctx->ntfs_ino);
-		ntfs_attr_reinit_search_ctx(ctx);
-		ret = ntfs_attr_lookup(mft_ni->type, mft_ni->name,
-				mft_ni->name_len, CASE_SENSITIVE, 0, NULL, 0,
-				ctx);
-		if (unlikely(ret)) {
-			ntfs_error(vol->sb, "Failed to find first attribute "
-					"extent of mft data attribute.");
-			goto restore_undo_alloc;
-		}
-		a = ctx->attr;
-	}
-	write_lock_irqsave(&mft_ni->size_lock, flags);
-	mft_ni->allocated_size += nr << vol->cluster_size_bits;
-	a->data.non_resident.allocated_size =
-			cpu_to_sle64(mft_ni->allocated_size);
-	write_unlock_irqrestore(&mft_ni->size_lock, flags);
-	/* Ensure the changes make it to disk. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(mft_ni);
-	up_write(&mft_ni->runlist.lock);
-	ntfs_debug("Done.");
-	return 0;
-restore_undo_alloc:
-	ntfs_attr_reinit_search_ctx(ctx);
-	if (ntfs_attr_lookup(mft_ni->type, mft_ni->name, mft_ni->name_len,
-			CASE_SENSITIVE, rl[1].vcn, NULL, 0, ctx)) {
-		ntfs_error(vol->sb, "Failed to find last attribute extent of "
-				"mft data attribute.%s", es);
-		write_lock_irqsave(&mft_ni->size_lock, flags);
-		mft_ni->allocated_size += nr << vol->cluster_size_bits;
-		write_unlock_irqrestore(&mft_ni->size_lock, flags);
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(mft_ni);
-		up_write(&mft_ni->runlist.lock);
-		/*
-		 * The only thing that is now wrong is ->allocated_size of the
-		 * base attribute extent which chkdsk should be able to fix.
-		 */
-		NVolSetErrors(vol);
-		return ret;
-	}
-	ctx->attr->data.non_resident.highest_vcn =
-			cpu_to_sle64(old_last_vcn - 1);
-undo_alloc:
-	if (ntfs_cluster_free(mft_ni, old_last_vcn, -1, ctx) < 0) {
-		ntfs_error(vol->sb, "Failed to free clusters from mft data "
-				"attribute.%s", es);
-		NVolSetErrors(vol);
-	}
-
-	if (ntfs_rl_truncate_nolock(vol, &mft_ni->runlist, old_last_vcn)) {
-		ntfs_error(vol->sb, "Failed to truncate mft data attribute "
-				"runlist.%s", es);
-		NVolSetErrors(vol);
-	}
-	if (ctx) {
-		a = ctx->attr;
-		if (mp_rebuilt && !IS_ERR(ctx->mrec)) {
-			if (ntfs_mapping_pairs_build(vol, (u8 *)a + le16_to_cpu(
-				a->data.non_resident.mapping_pairs_offset),
-				old_alen - le16_to_cpu(
-					a->data.non_resident.mapping_pairs_offset),
-				rl2, ll, -1, NULL)) {
-				ntfs_error(vol->sb, "Failed to restore mapping pairs "
-					"array.%s", es);
-				NVolSetErrors(vol);
-			}
-			if (ntfs_attr_record_resize(ctx->mrec, a, old_alen)) {
-				ntfs_error(vol->sb, "Failed to restore attribute "
-					"record.%s", es);
-				NVolSetErrors(vol);
-			}
-			flush_dcache_mft_record_page(ctx->ntfs_ino);
-			mark_mft_record_dirty(ctx->ntfs_ino);
-		} else if (IS_ERR(ctx->mrec)) {
-			ntfs_error(vol->sb, "Failed to restore attribute search "
-				"context.%s", es);
-			NVolSetErrors(vol);
-		}
-		ntfs_attr_put_search_ctx(ctx);
-	}
-	if (!IS_ERR(mrec))
-		unmap_mft_record(mft_ni);
-	up_write(&mft_ni->runlist.lock);
-	return ret;
-}
-
-/**
- * ntfs_mft_record_layout - layout an mft record into a memory buffer
- * @vol:	volume to which the mft record will belong
- * @mft_no:	mft reference specifying the mft record number
- * @m:		destination buffer of size >= @vol->mft_record_size bytes
- *
- * Layout an empty, unused mft record with the mft record number @mft_no into
- * the buffer @m.  The volume @vol is needed because the mft record structure
- * was modified in NTFS 3.1 so we need to know which volume version this mft
- * record will be used on.
- *
- * Return 0 on success and -errno on error.
- */
-static int ntfs_mft_record_layout(const ntfs_volume *vol, const s64 mft_no,
-		MFT_RECORD *m)
-{
-	ATTR_RECORD *a;
-
-	ntfs_debug("Entering for mft record 0x%llx.", (long long)mft_no);
-	if (mft_no >= (1ll << 32)) {
-		ntfs_error(vol->sb, "Mft record number 0x%llx exceeds "
-				"maximum of 2^32.", (long long)mft_no);
-		return -ERANGE;
-	}
-	/* Start by clearing the whole mft record to gives us a clean slate. */
-	memset(m, 0, vol->mft_record_size);
-	/* Aligned to 2-byte boundary. */
-	if (vol->major_ver < 3 || (vol->major_ver == 3 && !vol->minor_ver))
-		m->usa_ofs = cpu_to_le16((sizeof(MFT_RECORD_OLD) + 1) & ~1);
-	else {
-		m->usa_ofs = cpu_to_le16((sizeof(MFT_RECORD) + 1) & ~1);
-		/*
-		 * Set the NTFS 3.1+ specific fields while we know that the
-		 * volume version is 3.1+.
-		 */
-		m->reserved = 0;
-		m->mft_record_number = cpu_to_le32((u32)mft_no);
-	}
-	m->magic = magic_FILE;
-	if (vol->mft_record_size >= NTFS_BLOCK_SIZE)
-		m->usa_count = cpu_to_le16(vol->mft_record_size /
-				NTFS_BLOCK_SIZE + 1);
-	else {
-		m->usa_count = cpu_to_le16(1);
-		ntfs_warning(vol->sb, "Sector size is bigger than mft record "
-				"size.  Setting usa_count to 1.  If chkdsk "
-				"reports this as corruption, please email "
-				"linux-ntfs-dev@lists.sourceforge.net stating "
-				"that you saw this message and that the "
-				"modified filesystem created was corrupt.  "
-				"Thank you.");
-	}
-	/* Set the update sequence number to 1. */
-	*(le16*)((u8*)m + le16_to_cpu(m->usa_ofs)) = cpu_to_le16(1);
-	m->lsn = 0;
-	m->sequence_number = cpu_to_le16(1);
-	m->link_count = 0;
-	/*
-	 * Place the attributes straight after the update sequence array,
-	 * aligned to 8-byte boundary.
-	 */
-	m->attrs_offset = cpu_to_le16((le16_to_cpu(m->usa_ofs) +
-			(le16_to_cpu(m->usa_count) << 1) + 7) & ~7);
-	m->flags = 0;
-	/*
-	 * Using attrs_offset plus eight bytes (for the termination attribute).
-	 * attrs_offset is already aligned to 8-byte boundary, so no need to
-	 * align again.
-	 */
-	m->bytes_in_use = cpu_to_le32(le16_to_cpu(m->attrs_offset) + 8);
-	m->bytes_allocated = cpu_to_le32(vol->mft_record_size);
-	m->base_mft_record = 0;
-	m->next_attr_instance = 0;
-	/* Add the termination attribute. */
-	a = (ATTR_RECORD*)((u8*)m + le16_to_cpu(m->attrs_offset));
-	a->type = AT_END;
-	a->length = 0;
-	ntfs_debug("Done.");
-	return 0;
-}
-
-/**
- * ntfs_mft_record_format - format an mft record on an ntfs volume
- * @vol:	volume on which to format the mft record
- * @mft_no:	mft record number to format
- *
- * Format the mft record @mft_no in $MFT/$DATA, i.e. lay out an empty, unused
- * mft record into the appropriate place of the mft data attribute.  This is
- * used when extending the mft data attribute.
- *
- * Return 0 on success and -errno on error.
- */
-static int ntfs_mft_record_format(const ntfs_volume *vol, const s64 mft_no)
-{
-	loff_t i_size;
-	struct inode *mft_vi = vol->mft_ino;
-	struct page *page;
-	MFT_RECORD *m;
-	pgoff_t index, end_index;
-	unsigned int ofs;
-	int err;
-
-	ntfs_debug("Entering for mft record 0x%llx.", (long long)mft_no);
-	/*
-	 * The index into the page cache and the offset within the page cache
-	 * page of the wanted mft record.
-	 */
-	index = mft_no << vol->mft_record_size_bits >> PAGE_SHIFT;
-	ofs = (mft_no << vol->mft_record_size_bits) & ~PAGE_MASK;
-	/* The maximum valid index into the page cache for $MFT's data. */
-	i_size = i_size_read(mft_vi);
-	end_index = i_size >> PAGE_SHIFT;
-	if (unlikely(index >= end_index)) {
-		if (unlikely(index > end_index || ofs + vol->mft_record_size >=
-				(i_size & ~PAGE_MASK))) {
-			ntfs_error(vol->sb, "Tried to format non-existing mft "
-					"record 0x%llx.", (long long)mft_no);
-			return -ENOENT;
-		}
-	}
-	/* Read, map, and pin the page containing the mft record. */
-	page = ntfs_map_page(mft_vi->i_mapping, index);
-	if (IS_ERR(page)) {
-		ntfs_error(vol->sb, "Failed to map page containing mft record "
-				"to format 0x%llx.", (long long)mft_no);
-		return PTR_ERR(page);
-	}
-	lock_page(page);
-	BUG_ON(!PageUptodate(page));
-	ClearPageUptodate(page);
-	m = (MFT_RECORD*)((u8*)page_address(page) + ofs);
-	err = ntfs_mft_record_layout(vol, mft_no, m);
-	if (unlikely(err)) {
-		ntfs_error(vol->sb, "Failed to layout mft record 0x%llx.",
-				(long long)mft_no);
-		SetPageUptodate(page);
-		unlock_page(page);
-		ntfs_unmap_page(page);
-		return err;
-	}
-	flush_dcache_page(page);
-	SetPageUptodate(page);
-	unlock_page(page);
-	/*
-	 * Make sure the mft record is written out to disk.  We could use
-	 * ilookup5() to check if an inode is in icache and so on but this is
-	 * unnecessary as ntfs_writepage() will write the dirty record anyway.
-	 */
-	mark_ntfs_record_dirty(page, ofs);
-	ntfs_unmap_page(page);
-	ntfs_debug("Done.");
-	return 0;
-}
-
-/**
- * ntfs_mft_record_alloc - allocate an mft record on an ntfs volume
- * @vol:	[IN]  volume on which to allocate the mft record
- * @mode:	[IN]  mode if want a file or directory, i.e. base inode or 0
- * @base_ni:	[IN]  open base inode if allocating an extent mft record or NULL
- * @mrec:	[OUT] on successful return this is the mapped mft record
- *
- * Allocate an mft record in $MFT/$DATA of an open ntfs volume @vol.
- *
- * If @base_ni is NULL make the mft record a base mft record, i.e. a file or
- * direvctory inode, and allocate it at the default allocator position.  In
- * this case @mode is the file mode as given to us by the caller.  We in
- * particular use @mode to distinguish whether a file or a directory is being
- * created (S_IFDIR(mode) and S_IFREG(mode), respectively).
- *
- * If @base_ni is not NULL make the allocated mft record an extent record,
- * allocate it starting at the mft record after the base mft record and attach
- * the allocated and opened ntfs inode to the base inode @base_ni.  In this
- * case @mode must be 0 as it is meaningless for extent inodes.
- *
- * You need to check the return value with IS_ERR().  If false, the function
- * was successful and the return value is the now opened ntfs inode of the
- * allocated mft record.  *@mrec is then set to the allocated, mapped, pinned,
- * and locked mft record.  If IS_ERR() is true, the function failed and the
- * error code is obtained from PTR_ERR(return value).  *@mrec is undefined in
- * this case.
- *
- * Allocation strategy:
- *
- * To find a free mft record, we scan the mft bitmap for a zero bit.  To
- * optimize this we start scanning at the place specified by @base_ni or if
- * @base_ni is NULL we start where we last stopped and we perform wrap around
- * when we reach the end.  Note, we do not try to allocate mft records below
- * number 24 because numbers 0 to 15 are the defined system files anyway and 16
- * to 24 are special in that they are used for storing extension mft records
- * for the $DATA attribute of $MFT.  This is required to avoid the possibility
- * of creating a runlist with a circular dependency which once written to disk
- * can never be read in again.  Windows will only use records 16 to 24 for
- * normal files if the volume is completely out of space.  We never use them
- * which means that when the volume is really out of space we cannot create any
- * more files while Windows can still create up to 8 small files.  We can start
- * doing this at some later time, it does not matter much for now.
- *
- * When scanning the mft bitmap, we only search up to the last allocated mft
- * record.  If there are no free records left in the range 24 to number of
- * allocated mft records, then we extend the $MFT/$DATA attribute in order to
- * create free mft records.  We extend the allocated size of $MFT/$DATA by 16
- * records at a time or one cluster, if cluster size is above 16kiB.  If there
- * is not sufficient space to do this, we try to extend by a single mft record
- * or one cluster, if cluster size is above the mft record size.
- *
- * No matter how many mft records we allocate, we initialize only the first
- * allocated mft record, incrementing mft data size and initialized size
- * accordingly, open an ntfs_inode for it and return it to the caller, unless
- * there are less than 24 mft records, in which case we allocate and initialize
- * mft records until we reach record 24 which we consider as the first free mft
- * record for use by normal files.
- *
- * If during any stage we overflow the initialized data in the mft bitmap, we
- * extend the initialized size (and data size) by 8 bytes, allocating another
- * cluster if required.  The bitmap data size has to be at least equal to the
- * number of mft records in the mft, but it can be bigger, in which case the
- * superflous bits are padded with zeroes.
- *
- * Thus, when we return successfully (IS_ERR() is false), we will have:
- *	- initialized / extended the mft bitmap if necessary,
- *	- initialized / extended the mft data if necessary,
- *	- set the bit corresponding to the mft record being allocated in the
- *	  mft bitmap,
- *	- opened an ntfs_inode for the allocated mft record, and we will have
- *	- returned the ntfs_inode as well as the allocated mapped, pinned, and
- *	  locked mft record.
- *
- * On error, the volume will be left in a consistent state and no record will
- * be allocated.  If rolling back a partial operation fails, we may leave some
- * inconsistent metadata in which case we set NVolErrors() so the volume is
- * left dirty when unmounted.
- *
- * Note, this function cannot make use of most of the normal functions, like
- * for example for attribute resizing, etc, because when the run list overflows
- * the base mft record and an attribute list is used, it is very important that
- * the extension mft records used to store the $DATA attribute of $MFT can be
- * reached without having to read the information contained inside them, as
- * this would make it impossible to find them in the first place after the
- * volume is unmounted.  $MFT/$BITMAP probably does not need to follow this
- * rule because the bitmap is not essential for finding the mft records, but on
- * the other hand, handling the bitmap in this special way would make life
- * easier because otherwise there might be circular invocations of functions
- * when reading the bitmap.
- */
-ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
-		ntfs_inode *base_ni, MFT_RECORD **mrec)
-{
-	s64 ll, bit, old_data_initialized, old_data_size;
-	unsigned long flags;
-	struct inode *vi;
-	struct page *page;
-	ntfs_inode *mft_ni, *mftbmp_ni, *ni;
-	ntfs_attr_search_ctx *ctx;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
-	pgoff_t index;
-	unsigned int ofs;
-	int err;
-	le16 seq_no, usn;
-	bool record_formatted = false;
-
-	if (base_ni) {
-		ntfs_debug("Entering (allocating an extent mft record for "
-				"base mft record 0x%llx).",
-				(long long)base_ni->mft_no);
-		/* @mode and @base_ni are mutually exclusive. */
-		BUG_ON(mode);
-	} else
-		ntfs_debug("Entering (allocating a base mft record).");
-	if (mode) {
-		/* @mode and @base_ni are mutually exclusive. */
-		BUG_ON(base_ni);
-		/* We only support creation of normal files and directories. */
-		if (!S_ISREG(mode) && !S_ISDIR(mode))
-			return ERR_PTR(-EOPNOTSUPP);
-	}
-	BUG_ON(!mrec);
-	mft_ni = NTFS_I(vol->mft_ino);
-	mftbmp_ni = NTFS_I(vol->mftbmp_ino);
-	down_write(&vol->mftbmp_lock);
-	bit = ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(vol, base_ni);
-	if (bit >= 0) {
-		ntfs_debug("Found and allocated free record (#1), bit 0x%llx.",
-				(long long)bit);
-		goto have_alloc_rec;
-	}
-	if (bit != -ENOSPC) {
-		up_write(&vol->mftbmp_lock);
-		return ERR_PTR(bit);
-	}
-	/*
-	 * No free mft records left.  If the mft bitmap already covers more
-	 * than the currently used mft records, the next records are all free,
-	 * so we can simply allocate the first unused mft record.
-	 * Note: We also have to make sure that the mft bitmap at least covers
-	 * the first 24 mft records as they are special and whilst they may not
-	 * be in use, we do not allocate from them.
-	 */
-	read_lock_irqsave(&mft_ni->size_lock, flags);
-	ll = mft_ni->initialized_size >> vol->mft_record_size_bits;
-	read_unlock_irqrestore(&mft_ni->size_lock, flags);
-	read_lock_irqsave(&mftbmp_ni->size_lock, flags);
-	old_data_initialized = mftbmp_ni->initialized_size;
-	read_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-	if (old_data_initialized << 3 > ll && old_data_initialized > 3) {
-		bit = ll;
-		if (bit < 24)
-			bit = 24;
-		if (unlikely(bit >= (1ll << 32)))
-			goto max_err_out;
-		ntfs_debug("Found free record (#2), bit 0x%llx.",
-				(long long)bit);
-		goto found_free_rec;
-	}
-	/*
-	 * The mft bitmap needs to be expanded until it covers the first unused
-	 * mft record that we can allocate.
-	 * Note: The smallest mft record we allocate is mft record 24.
-	 */
-	bit = old_data_initialized << 3;
-	if (unlikely(bit >= (1ll << 32)))
-		goto max_err_out;
-	read_lock_irqsave(&mftbmp_ni->size_lock, flags);
-	old_data_size = mftbmp_ni->allocated_size;
-	ntfs_debug("Status of mftbmp before extension: allocated_size 0x%llx, "
-			"data_size 0x%llx, initialized_size 0x%llx.",
-			(long long)old_data_size,
-			(long long)i_size_read(vol->mftbmp_ino),
-			(long long)old_data_initialized);
-	read_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-	if (old_data_initialized + 8 > old_data_size) {
-		/* Need to extend bitmap by one more cluster. */
-		ntfs_debug("mftbmp: initialized_size + 8 > allocated_size.");
-		err = ntfs_mft_bitmap_extend_allocation_nolock(vol);
-		if (unlikely(err)) {
-			up_write(&vol->mftbmp_lock);
-			goto err_out;
-		}
-#ifdef DEBUG
-		read_lock_irqsave(&mftbmp_ni->size_lock, flags);
-		ntfs_debug("Status of mftbmp after allocation extension: "
-				"allocated_size 0x%llx, data_size 0x%llx, "
-				"initialized_size 0x%llx.",
-				(long long)mftbmp_ni->allocated_size,
-				(long long)i_size_read(vol->mftbmp_ino),
-				(long long)mftbmp_ni->initialized_size);
-		read_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-#endif /* DEBUG */
-	}
-	/*
-	 * We now have sufficient allocated space, extend the initialized_size
-	 * as well as the data_size if necessary and fill the new space with
-	 * zeroes.
-	 */
-	err = ntfs_mft_bitmap_extend_initialized_nolock(vol);
-	if (unlikely(err)) {
-		up_write(&vol->mftbmp_lock);
-		goto err_out;
-	}
-#ifdef DEBUG
-	read_lock_irqsave(&mftbmp_ni->size_lock, flags);
-	ntfs_debug("Status of mftbmp after initialized extension: "
-			"allocated_size 0x%llx, data_size 0x%llx, "
-			"initialized_size 0x%llx.",
-			(long long)mftbmp_ni->allocated_size,
-			(long long)i_size_read(vol->mftbmp_ino),
-			(long long)mftbmp_ni->initialized_size);
-	read_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-#endif /* DEBUG */
-	ntfs_debug("Found free record (#3), bit 0x%llx.", (long long)bit);
-found_free_rec:
-	/* @bit is the found free mft record, allocate it in the mft bitmap. */
-	ntfs_debug("At found_free_rec.");
-	err = ntfs_bitmap_set_bit(vol->mftbmp_ino, bit);
-	if (unlikely(err)) {
-		ntfs_error(vol->sb, "Failed to allocate bit in mft bitmap.");
-		up_write(&vol->mftbmp_lock);
-		goto err_out;
-	}
-	ntfs_debug("Set bit 0x%llx in mft bitmap.", (long long)bit);
-have_alloc_rec:
-	/*
-	 * The mft bitmap is now uptodate.  Deal with mft data attribute now.
-	 * Note, we keep hold of the mft bitmap lock for writing until all
-	 * modifications to the mft data attribute are complete, too, as they
-	 * will impact decisions for mft bitmap and mft record allocation done
-	 * by a parallel allocation and if the lock is not maintained a
-	 * parallel allocation could allocate the same mft record as this one.
-	 */
-	ll = (bit + 1) << vol->mft_record_size_bits;
-	read_lock_irqsave(&mft_ni->size_lock, flags);
-	old_data_initialized = mft_ni->initialized_size;
-	read_unlock_irqrestore(&mft_ni->size_lock, flags);
-	if (ll <= old_data_initialized) {
-		ntfs_debug("Allocated mft record already initialized.");
-		goto mft_rec_already_initialized;
-	}
-	ntfs_debug("Initializing allocated mft record.");
-	/*
-	 * The mft record is outside the initialized data.  Extend the mft data
-	 * attribute until it covers the allocated record.  The loop is only
-	 * actually traversed more than once when a freshly formatted volume is
-	 * first written to so it optimizes away nicely in the common case.
-	 */
-	read_lock_irqsave(&mft_ni->size_lock, flags);
-	ntfs_debug("Status of mft data before extension: "
-			"allocated_size 0x%llx, data_size 0x%llx, "
-			"initialized_size 0x%llx.",
-			(long long)mft_ni->allocated_size,
-			(long long)i_size_read(vol->mft_ino),
-			(long long)mft_ni->initialized_size);
-	while (ll > mft_ni->allocated_size) {
-		read_unlock_irqrestore(&mft_ni->size_lock, flags);
-		err = ntfs_mft_data_extend_allocation_nolock(vol);
-		if (unlikely(err)) {
-			ntfs_error(vol->sb, "Failed to extend mft data "
-					"allocation.");
-			goto undo_mftbmp_alloc_nolock;
-		}
-		read_lock_irqsave(&mft_ni->size_lock, flags);
-		ntfs_debug("Status of mft data after allocation extension: "
-				"allocated_size 0x%llx, data_size 0x%llx, "
-				"initialized_size 0x%llx.",
-				(long long)mft_ni->allocated_size,
-				(long long)i_size_read(vol->mft_ino),
-				(long long)mft_ni->initialized_size);
-	}
-	read_unlock_irqrestore(&mft_ni->size_lock, flags);
-	/*
-	 * Extend mft data initialized size (and data size of course) to reach
-	 * the allocated mft record, formatting the mft records allong the way.
-	 * Note: We only modify the ntfs_inode structure as that is all that is
-	 * needed by ntfs_mft_record_format().  We will update the attribute
-	 * record itself in one fell swoop later on.
-	 */
-	write_lock_irqsave(&mft_ni->size_lock, flags);
-	old_data_initialized = mft_ni->initialized_size;
-	old_data_size = vol->mft_ino->i_size;
-	while (ll > mft_ni->initialized_size) {
-		s64 new_initialized_size, mft_no;
-		
-		new_initialized_size = mft_ni->initialized_size +
-				vol->mft_record_size;
-		mft_no = mft_ni->initialized_size >> vol->mft_record_size_bits;
-		if (new_initialized_size > i_size_read(vol->mft_ino))
-			i_size_write(vol->mft_ino, new_initialized_size);
-		write_unlock_irqrestore(&mft_ni->size_lock, flags);
-		ntfs_debug("Initializing mft record 0x%llx.",
-				(long long)mft_no);
-		err = ntfs_mft_record_format(vol, mft_no);
-		if (unlikely(err)) {
-			ntfs_error(vol->sb, "Failed to format mft record.");
-			goto undo_data_init;
-		}
-		write_lock_irqsave(&mft_ni->size_lock, flags);
-		mft_ni->initialized_size = new_initialized_size;
-	}
-	write_unlock_irqrestore(&mft_ni->size_lock, flags);
-	record_formatted = true;
-	/* Update the mft data attribute record to reflect the new sizes. */
-	m = map_mft_record(mft_ni);
-	if (IS_ERR(m)) {
-		ntfs_error(vol->sb, "Failed to map mft record.");
-		err = PTR_ERR(m);
-		goto undo_data_init;
-	}
-	ctx = ntfs_attr_get_search_ctx(mft_ni, m);
-	if (unlikely(!ctx)) {
-		ntfs_error(vol->sb, "Failed to get search context.");
-		err = -ENOMEM;
-		unmap_mft_record(mft_ni);
-		goto undo_data_init;
-	}
-	err = ntfs_attr_lookup(mft_ni->type, mft_ni->name, mft_ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err)) {
-		ntfs_error(vol->sb, "Failed to find first attribute extent of "
-				"mft data attribute.");
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(mft_ni);
-		goto undo_data_init;
-	}
-	a = ctx->attr;
-	read_lock_irqsave(&mft_ni->size_lock, flags);
-	a->data.non_resident.initialized_size =
-			cpu_to_sle64(mft_ni->initialized_size);
-	a->data.non_resident.data_size =
-			cpu_to_sle64(i_size_read(vol->mft_ino));
-	read_unlock_irqrestore(&mft_ni->size_lock, flags);
-	/* Ensure the changes make it to disk. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(mft_ni);
-	read_lock_irqsave(&mft_ni->size_lock, flags);
-	ntfs_debug("Status of mft data after mft record initialization: "
-			"allocated_size 0x%llx, data_size 0x%llx, "
-			"initialized_size 0x%llx.",
-			(long long)mft_ni->allocated_size,
-			(long long)i_size_read(vol->mft_ino),
-			(long long)mft_ni->initialized_size);
-	BUG_ON(i_size_read(vol->mft_ino) > mft_ni->allocated_size);
-	BUG_ON(mft_ni->initialized_size > i_size_read(vol->mft_ino));
-	read_unlock_irqrestore(&mft_ni->size_lock, flags);
-mft_rec_already_initialized:
-	/*
-	 * We can finally drop the mft bitmap lock as the mft data attribute
-	 * has been fully updated.  The only disparity left is that the
-	 * allocated mft record still needs to be marked as in use to match the
-	 * set bit in the mft bitmap but this is actually not a problem since
-	 * this mft record is not referenced from anywhere yet and the fact
-	 * that it is allocated in the mft bitmap means that no-one will try to
-	 * allocate it either.
-	 */
-	up_write(&vol->mftbmp_lock);
-	/*
-	 * We now have allocated and initialized the mft record.  Calculate the
-	 * index of and the offset within the page cache page the record is in.
-	 */
-	index = bit << vol->mft_record_size_bits >> PAGE_SHIFT;
-	ofs = (bit << vol->mft_record_size_bits) & ~PAGE_MASK;
-	/* Read, map, and pin the page containing the mft record. */
-	page = ntfs_map_page(vol->mft_ino->i_mapping, index);
-	if (IS_ERR(page)) {
-		ntfs_error(vol->sb, "Failed to map page containing allocated "
-				"mft record 0x%llx.", (long long)bit);
-		err = PTR_ERR(page);
-		goto undo_mftbmp_alloc;
-	}
-	lock_page(page);
-	BUG_ON(!PageUptodate(page));
-	ClearPageUptodate(page);
-	m = (MFT_RECORD*)((u8*)page_address(page) + ofs);
-	/* If we just formatted the mft record no need to do it again. */
-	if (!record_formatted) {
-		/* Sanity check that the mft record is really not in use. */
-		if (ntfs_is_file_record(m->magic) &&
-				(m->flags & MFT_RECORD_IN_USE)) {
-			ntfs_error(vol->sb, "Mft record 0x%llx was marked "
-					"free in mft bitmap but is marked "
-					"used itself.  Corrupt filesystem.  "
-					"Unmount and run chkdsk.",
-					(long long)bit);
-			err = -EIO;
-			SetPageUptodate(page);
-			unlock_page(page);
-			ntfs_unmap_page(page);
-			NVolSetErrors(vol);
-			goto undo_mftbmp_alloc;
-		}
-		/*
-		 * We need to (re-)format the mft record, preserving the
-		 * sequence number if it is not zero as well as the update
-		 * sequence number if it is not zero or -1 (0xffff).  This
-		 * means we do not need to care whether or not something went
-		 * wrong with the previous mft record.
-		 */
-		seq_no = m->sequence_number;
-		usn = *(le16*)((u8*)m + le16_to_cpu(m->usa_ofs));
-		err = ntfs_mft_record_layout(vol, bit, m);
-		if (unlikely(err)) {
-			ntfs_error(vol->sb, "Failed to layout allocated mft "
-					"record 0x%llx.", (long long)bit);
-			SetPageUptodate(page);
-			unlock_page(page);
-			ntfs_unmap_page(page);
-			goto undo_mftbmp_alloc;
-		}
-		if (seq_no)
-			m->sequence_number = seq_no;
-		if (usn && le16_to_cpu(usn) != 0xffff)
-			*(le16*)((u8*)m + le16_to_cpu(m->usa_ofs)) = usn;
-	}
-	/* Set the mft record itself in use. */
-	m->flags |= MFT_RECORD_IN_USE;
-	if (S_ISDIR(mode))
-		m->flags |= MFT_RECORD_IS_DIRECTORY;
-	flush_dcache_page(page);
-	SetPageUptodate(page);
-	if (base_ni) {
-		MFT_RECORD *m_tmp;
-
-		/*
-		 * Setup the base mft record in the extent mft record.  This
-		 * completes initialization of the allocated extent mft record
-		 * and we can simply use it with map_extent_mft_record().
-		 */
-		m->base_mft_record = MK_LE_MREF(base_ni->mft_no,
-				base_ni->seq_no);
-		/*
-		 * Allocate an extent inode structure for the new mft record,
-		 * attach it to the base inode @base_ni and map, pin, and lock
-		 * its, i.e. the allocated, mft record.
-		 */
-		m_tmp = map_extent_mft_record(base_ni, bit, &ni);
-		if (IS_ERR(m_tmp)) {
-			ntfs_error(vol->sb, "Failed to map allocated extent "
-					"mft record 0x%llx.", (long long)bit);
-			err = PTR_ERR(m_tmp);
-			/* Set the mft record itself not in use. */
-			m->flags &= cpu_to_le16(
-					~le16_to_cpu(MFT_RECORD_IN_USE));
-			flush_dcache_page(page);
-			/* Make sure the mft record is written out to disk. */
-			mark_ntfs_record_dirty(page, ofs);
-			unlock_page(page);
-			ntfs_unmap_page(page);
-			goto undo_mftbmp_alloc;
-		}
-		BUG_ON(m != m_tmp);
-		/*
-		 * Make sure the allocated mft record is written out to disk.
-		 * No need to set the inode dirty because the caller is going
-		 * to do that anyway after finishing with the new extent mft
-		 * record (e.g. at a minimum a new attribute will be added to
-		 * the mft record.
-		 */
-		mark_ntfs_record_dirty(page, ofs);
-		unlock_page(page);
-		/*
-		 * Need to unmap the page since map_extent_mft_record() mapped
-		 * it as well so we have it mapped twice at the moment.
-		 */
-		ntfs_unmap_page(page);
-	} else {
-		/*
-		 * Allocate a new VFS inode and set it up.  NOTE: @vi->i_nlink
-		 * is set to 1 but the mft record->link_count is 0.  The caller
-		 * needs to bear this in mind.
-		 */
-		vi = new_inode(vol->sb);
-		if (unlikely(!vi)) {
-			err = -ENOMEM;
-			/* Set the mft record itself not in use. */
-			m->flags &= cpu_to_le16(
-					~le16_to_cpu(MFT_RECORD_IN_USE));
-			flush_dcache_page(page);
-			/* Make sure the mft record is written out to disk. */
-			mark_ntfs_record_dirty(page, ofs);
-			unlock_page(page);
-			ntfs_unmap_page(page);
-			goto undo_mftbmp_alloc;
-		}
-		vi->i_ino = bit;
-
-		/* The owner and group come from the ntfs volume. */
-		vi->i_uid = vol->uid;
-		vi->i_gid = vol->gid;
-
-		/* Initialize the ntfs specific part of @vi. */
-		ntfs_init_big_inode(vi);
-		ni = NTFS_I(vi);
-		/*
-		 * Set the appropriate mode, attribute type, and name.  For
-		 * directories, also setup the index values to the defaults.
-		 */
-		if (S_ISDIR(mode)) {
-			vi->i_mode = S_IFDIR | S_IRWXUGO;
-			vi->i_mode &= ~vol->dmask;
-
-			NInoSetMstProtected(ni);
-			ni->type = AT_INDEX_ALLOCATION;
-			ni->name = I30;
-			ni->name_len = 4;
-
-			ni->itype.index.block_size = 4096;
-			ni->itype.index.block_size_bits = ntfs_ffs(4096) - 1;
-			ni->itype.index.collation_rule = COLLATION_FILE_NAME;
-			if (vol->cluster_size <= ni->itype.index.block_size) {
-				ni->itype.index.vcn_size = vol->cluster_size;
-				ni->itype.index.vcn_size_bits =
-						vol->cluster_size_bits;
-			} else {
-				ni->itype.index.vcn_size = vol->sector_size;
-				ni->itype.index.vcn_size_bits =
-						vol->sector_size_bits;
-			}
-		} else {
-			vi->i_mode = S_IFREG | S_IRWXUGO;
-			vi->i_mode &= ~vol->fmask;
-
-			ni->type = AT_DATA;
-			ni->name = NULL;
-			ni->name_len = 0;
-		}
-		if (IS_RDONLY(vi))
-			vi->i_mode &= ~S_IWUGO;
-
-		/* Set the inode times to the current time. */
-		simple_inode_init_ts(vi);
-		/*
-		 * Set the file size to 0, the ntfs inode sizes are set to 0 by
-		 * the call to ntfs_init_big_inode() below.
-		 */
-		vi->i_size = 0;
-		vi->i_blocks = 0;
-
-		/* Set the sequence number. */
-		vi->i_generation = ni->seq_no = le16_to_cpu(m->sequence_number);
-		/*
-		 * Manually map, pin, and lock the mft record as we already
-		 * have its page mapped and it is very easy to do.
-		 */
-		atomic_inc(&ni->count);
-		mutex_lock(&ni->mrec_lock);
-		ni->page = page;
-		ni->page_ofs = ofs;
-		/*
-		 * Make sure the allocated mft record is written out to disk.
-		 * NOTE: We do not set the ntfs inode dirty because this would
-		 * fail in ntfs_write_inode() because the inode does not have a
-		 * standard information attribute yet.  Also, there is no need
-		 * to set the inode dirty because the caller is going to do
-		 * that anyway after finishing with the new mft record (e.g. at
-		 * a minimum some new attributes will be added to the mft
-		 * record.
-		 */
-		mark_ntfs_record_dirty(page, ofs);
-		unlock_page(page);
-
-		/* Add the inode to the inode hash for the superblock. */
-		insert_inode_hash(vi);
-
-		/* Update the default mft allocation position. */
-		vol->mft_data_pos = bit + 1;
-	}
-	/*
-	 * Return the opened, allocated inode of the allocated mft record as
-	 * well as the mapped, pinned, and locked mft record.
-	 */
-	ntfs_debug("Returning opened, allocated %sinode 0x%llx.",
-			base_ni ? "extent " : "", (long long)bit);
-	*mrec = m;
-	return ni;
-undo_data_init:
-	write_lock_irqsave(&mft_ni->size_lock, flags);
-	mft_ni->initialized_size = old_data_initialized;
-	i_size_write(vol->mft_ino, old_data_size);
-	write_unlock_irqrestore(&mft_ni->size_lock, flags);
-	goto undo_mftbmp_alloc_nolock;
-undo_mftbmp_alloc:
-	down_write(&vol->mftbmp_lock);
-undo_mftbmp_alloc_nolock:
-	if (ntfs_bitmap_clear_bit(vol->mftbmp_ino, bit)) {
-		ntfs_error(vol->sb, "Failed to clear bit in mft bitmap.%s", es);
-		NVolSetErrors(vol);
-	}
-	up_write(&vol->mftbmp_lock);
-err_out:
-	return ERR_PTR(err);
-max_err_out:
-	ntfs_warning(vol->sb, "Cannot allocate mft record because the maximum "
-			"number of inodes (2^32) has already been reached.");
-	up_write(&vol->mftbmp_lock);
-	return ERR_PTR(-ENOSPC);
-}
-
-/**
- * ntfs_extent_mft_record_free - free an extent mft record on an ntfs volume
- * @ni:		ntfs inode of the mapped extent mft record to free
- * @m:		mapped extent mft record of the ntfs inode @ni
- *
- * Free the mapped extent mft record @m of the extent ntfs inode @ni.
- *
- * Note that this function unmaps the mft record and closes and destroys @ni
- * internally and hence you cannot use either @ni nor @m any more after this
- * function returns success.
- *
- * On success return 0 and on error return -errno.  @ni and @m are still valid
- * in this case and have not been freed.
- *
- * For some errors an error message is displayed and the success code 0 is
- * returned and the volume is then left dirty on umount.  This makes sense in
- * case we could not rollback the changes that were already done since the
- * caller no longer wants to reference this mft record so it does not matter to
- * the caller if something is wrong with it as long as it is properly detached
- * from the base inode.
- */
-int ntfs_extent_mft_record_free(ntfs_inode *ni, MFT_RECORD *m)
-{
-	unsigned long mft_no = ni->mft_no;
-	ntfs_volume *vol = ni->vol;
-	ntfs_inode *base_ni;
-	ntfs_inode **extent_nis;
-	int i, err;
-	le16 old_seq_no;
-	u16 seq_no;
-	
-	BUG_ON(NInoAttr(ni));
-	BUG_ON(ni->nr_extents != -1);
-
-	mutex_lock(&ni->extent_lock);
-	base_ni = ni->ext.base_ntfs_ino;
-	mutex_unlock(&ni->extent_lock);
-
-	BUG_ON(base_ni->nr_extents <= 0);
-
-	ntfs_debug("Entering for extent inode 0x%lx, base inode 0x%lx.\n",
-			mft_no, base_ni->mft_no);
-
-	mutex_lock(&base_ni->extent_lock);
-
-	/* Make sure we are holding the only reference to the extent inode. */
-	if (atomic_read(&ni->count) > 2) {
-		ntfs_error(vol->sb, "Tried to free busy extent inode 0x%lx, "
-				"not freeing.", base_ni->mft_no);
-		mutex_unlock(&base_ni->extent_lock);
-		return -EBUSY;
-	}
-
-	/* Dissociate the ntfs inode from the base inode. */
-	extent_nis = base_ni->ext.extent_ntfs_inos;
-	err = -ENOENT;
-	for (i = 0; i < base_ni->nr_extents; i++) {
-		if (ni != extent_nis[i])
-			continue;
-		extent_nis += i;
-		base_ni->nr_extents--;
-		memmove(extent_nis, extent_nis + 1, (base_ni->nr_extents - i) *
-				sizeof(ntfs_inode*));
-		err = 0;
-		break;
-	}
-
-	mutex_unlock(&base_ni->extent_lock);
-
-	if (unlikely(err)) {
-		ntfs_error(vol->sb, "Extent inode 0x%lx is not attached to "
-				"its base inode 0x%lx.", mft_no,
-				base_ni->mft_no);
-		BUG();
-	}
-
-	/*
-	 * The extent inode is no longer attached to the base inode so no one
-	 * can get a reference to it any more.
-	 */
-
-	/* Mark the mft record as not in use. */
-	m->flags &= ~MFT_RECORD_IN_USE;
-
-	/* Increment the sequence number, skipping zero, if it is not zero. */
-	old_seq_no = m->sequence_number;
-	seq_no = le16_to_cpu(old_seq_no);
-	if (seq_no == 0xffff)
-		seq_no = 1;
-	else if (seq_no)
-		seq_no++;
-	m->sequence_number = cpu_to_le16(seq_no);
-
-	/*
-	 * Set the ntfs inode dirty and write it out.  We do not need to worry
-	 * about the base inode here since whatever caused the extent mft
-	 * record to be freed is guaranteed to do it already.
-	 */
-	NInoSetDirty(ni);
-	err = write_mft_record(ni, m, 0);
-	if (unlikely(err)) {
-		ntfs_error(vol->sb, "Failed to write mft record 0x%lx, not "
-				"freeing.", mft_no);
-		goto rollback;
-	}
-rollback_error:
-	/* Unmap and throw away the now freed extent inode. */
-	unmap_extent_mft_record(ni);
-	ntfs_clear_extent_inode(ni);
-
-	/* Clear the bit in the $MFT/$BITMAP corresponding to this record. */
-	down_write(&vol->mftbmp_lock);
-	err = ntfs_bitmap_clear_bit(vol->mftbmp_ino, mft_no);
-	up_write(&vol->mftbmp_lock);
-	if (unlikely(err)) {
-		/*
-		 * The extent inode is gone but we failed to deallocate it in
-		 * the mft bitmap.  Just emit a warning and leave the volume
-		 * dirty on umount.
-		 */
-		ntfs_error(vol->sb, "Failed to clear bit in mft bitmap.%s", es);
-		NVolSetErrors(vol);
-	}
-	return 0;
-rollback:
-	/* Rollback what we did... */
-	mutex_lock(&base_ni->extent_lock);
-	extent_nis = base_ni->ext.extent_ntfs_inos;
-	if (!(base_ni->nr_extents & 3)) {
-		int new_size = (base_ni->nr_extents + 4) * sizeof(ntfs_inode*);
-
-		extent_nis = kmalloc(new_size, GFP_NOFS);
-		if (unlikely(!extent_nis)) {
-			ntfs_error(vol->sb, "Failed to allocate internal "
-					"buffer during rollback.%s", es);
-			mutex_unlock(&base_ni->extent_lock);
-			NVolSetErrors(vol);
-			goto rollback_error;
-		}
-		if (base_ni->nr_extents) {
-			BUG_ON(!base_ni->ext.extent_ntfs_inos);
-			memcpy(extent_nis, base_ni->ext.extent_ntfs_inos,
-					new_size - 4 * sizeof(ntfs_inode*));
-			kfree(base_ni->ext.extent_ntfs_inos);
-		}
-		base_ni->ext.extent_ntfs_inos = extent_nis;
-	}
-	m->flags |= MFT_RECORD_IN_USE;
-	m->sequence_number = old_seq_no;
-	extent_nis[base_ni->nr_extents++] = ni;
-	mutex_unlock(&base_ni->extent_lock);
-	mark_mft_record_dirty(ni);
-	return err;
-}
-#endif /* NTFS_RW */
diff --git a/fs/ntfs/mft.h b/fs/ntfs/mft.h
deleted file mode 100644
index 49c001af16ed..000000000000
--- a/fs/ntfs/mft.h
+++ /dev/null
@@ -1,110 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * mft.h - Defines for mft record handling in NTFS Linux kernel driver.
- *	   Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2004 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_MFT_H
-#define _LINUX_NTFS_MFT_H
-
-#include <linux/fs.h>
-#include <linux/highmem.h>
-#include <linux/pagemap.h>
-
-#include "inode.h"
-
-extern MFT_RECORD *map_mft_record(ntfs_inode *ni);
-extern void unmap_mft_record(ntfs_inode *ni);
-
-extern MFT_RECORD *map_extent_mft_record(ntfs_inode *base_ni, MFT_REF mref,
-		ntfs_inode **ntfs_ino);
-
-static inline void unmap_extent_mft_record(ntfs_inode *ni)
-{
-	unmap_mft_record(ni);
-	return;
-}
-
-#ifdef NTFS_RW
-
-/**
- * flush_dcache_mft_record_page - flush_dcache_page() for mft records
- * @ni:		ntfs inode structure of mft record
- *
- * Call flush_dcache_page() for the page in which an mft record resides.
- *
- * This must be called every time an mft record is modified, just after the
- * modification.
- */
-static inline void flush_dcache_mft_record_page(ntfs_inode *ni)
-{
-	flush_dcache_page(ni->page);
-}
-
-extern void __mark_mft_record_dirty(ntfs_inode *ni);
-
-/**
- * mark_mft_record_dirty - set the mft record and the page containing it dirty
- * @ni:		ntfs inode describing the mapped mft record
- *
- * Set the mapped (extent) mft record of the (base or extent) ntfs inode @ni,
- * as well as the page containing the mft record, dirty.  Also, mark the base
- * vfs inode dirty.  This ensures that any changes to the mft record are
- * written out to disk.
- *
- * NOTE:  Do not do anything if the mft record is already marked dirty.
- */
-static inline void mark_mft_record_dirty(ntfs_inode *ni)
-{
-	if (!NInoTestSetDirty(ni))
-		__mark_mft_record_dirty(ni);
-}
-
-extern int ntfs_sync_mft_mirror(ntfs_volume *vol, const unsigned long mft_no,
-		MFT_RECORD *m, int sync);
-
-extern int write_mft_record_nolock(ntfs_inode *ni, MFT_RECORD *m, int sync);
-
-/**
- * write_mft_record - write out a mapped (extent) mft record
- * @ni:		ntfs inode describing the mapped (extent) mft record
- * @m:		mapped (extent) mft record to write
- * @sync:	if true, wait for i/o completion
- *
- * This is just a wrapper for write_mft_record_nolock() (see mft.c), which
- * locks the page for the duration of the write.  This ensures that there are
- * no race conditions between writing the mft record via the dirty inode code
- * paths and via the page cache write back code paths or between writing
- * neighbouring mft records residing in the same page.
- *
- * Locking the page also serializes us against ->read_folio() if the page is not
- * uptodate.
- *
- * On success, clean the mft record and return 0.  On error, leave the mft
- * record dirty and return -errno.
- */
-static inline int write_mft_record(ntfs_inode *ni, MFT_RECORD *m, int sync)
-{
-	struct page *page = ni->page;
-	int err;
-
-	BUG_ON(!page);
-	lock_page(page);
-	err = write_mft_record_nolock(ni, m, sync);
-	unlock_page(page);
-	return err;
-}
-
-extern bool ntfs_may_write_mft_record(ntfs_volume *vol,
-		const unsigned long mft_no, const MFT_RECORD *m,
-		ntfs_inode **locked_ni);
-
-extern ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
-		ntfs_inode *base_ni, MFT_RECORD **mrec);
-extern int ntfs_extent_mft_record_free(ntfs_inode *ni, MFT_RECORD *m);
-
-#endif /* NTFS_RW */
-
-#endif /* _LINUX_NTFS_MFT_H */
diff --git a/fs/ntfs/mst.c b/fs/ntfs/mst.c
deleted file mode 100644
index 16b3c884abfc..000000000000
--- a/fs/ntfs/mst.c
+++ /dev/null
@@ -1,189 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * mst.c - NTFS multi sector transfer protection handling code. Part of the
- *	   Linux-NTFS project.
- *
- * Copyright (c) 2001-2004 Anton Altaparmakov
- */
-
-#include "ntfs.h"
-
-/**
- * post_read_mst_fixup - deprotect multi sector transfer protected data
- * @b:		pointer to the data to deprotect
- * @size:	size in bytes of @b
- *
- * Perform the necessary post read multi sector transfer fixup and detect the
- * presence of incomplete multi sector transfers. - In that case, overwrite the
- * magic of the ntfs record header being processed with "BAAD" (in memory only!)
- * and abort processing.
- *
- * Return 0 on success and -EINVAL on error ("BAAD" magic will be present).
- *
- * NOTE: We consider the absence / invalidity of an update sequence array to
- * mean that the structure is not protected at all and hence doesn't need to
- * be fixed up. Thus, we return success and not failure in this case. This is
- * in contrast to pre_write_mst_fixup(), see below.
- */
-int post_read_mst_fixup(NTFS_RECORD *b, const u32 size)
-{
-	u16 usa_ofs, usa_count, usn;
-	u16 *usa_pos, *data_pos;
-
-	/* Setup the variables. */
-	usa_ofs = le16_to_cpu(b->usa_ofs);
-	/* Decrement usa_count to get number of fixups. */
-	usa_count = le16_to_cpu(b->usa_count) - 1;
-	/* Size and alignment checks. */
-	if ( size & (NTFS_BLOCK_SIZE - 1)	||
-	     usa_ofs & 1			||
-	     usa_ofs + (usa_count * 2) > size	||
-	     (size >> NTFS_BLOCK_SIZE_BITS) != usa_count)
-		return 0;
-	/* Position of usn in update sequence array. */
-	usa_pos = (u16*)b + usa_ofs/sizeof(u16);
-	/*
-	 * The update sequence number which has to be equal to each of the
-	 * u16 values before they are fixed up. Note no need to care for
-	 * endianness since we are comparing and moving data for on disk
-	 * structures which means the data is consistent. - If it is
-	 * consistenty the wrong endianness it doesn't make any difference.
-	 */
-	usn = *usa_pos;
-	/*
-	 * Position in protected data of first u16 that needs fixing up.
-	 */
-	data_pos = (u16*)b + NTFS_BLOCK_SIZE/sizeof(u16) - 1;
-	/*
-	 * Check for incomplete multi sector transfer(s).
-	 */
-	while (usa_count--) {
-		if (*data_pos != usn) {
-			/*
-			 * Incomplete multi sector transfer detected! )-:
-			 * Set the magic to "BAAD" and return failure.
-			 * Note that magic_BAAD is already converted to le32.
-			 */
-			b->magic = magic_BAAD;
-			return -EINVAL;
-		}
-		data_pos += NTFS_BLOCK_SIZE/sizeof(u16);
-	}
-	/* Re-setup the variables. */
-	usa_count = le16_to_cpu(b->usa_count) - 1;
-	data_pos = (u16*)b + NTFS_BLOCK_SIZE/sizeof(u16) - 1;
-	/* Fixup all sectors. */
-	while (usa_count--) {
-		/*
-		 * Increment position in usa and restore original data from
-		 * the usa into the data buffer.
-		 */
-		*data_pos = *(++usa_pos);
-		/* Increment position in data as well. */
-		data_pos += NTFS_BLOCK_SIZE/sizeof(u16);
-	}
-	return 0;
-}
-
-/**
- * pre_write_mst_fixup - apply multi sector transfer protection
- * @b:		pointer to the data to protect
- * @size:	size in bytes of @b
- *
- * Perform the necessary pre write multi sector transfer fixup on the data
- * pointer to by @b of @size.
- *
- * Return 0 if fixup applied (success) or -EINVAL if no fixup was performed
- * (assumed not needed). This is in contrast to post_read_mst_fixup() above.
- *
- * NOTE: We consider the absence / invalidity of an update sequence array to
- * mean that the structure is not subject to protection and hence doesn't need
- * to be fixed up. This means that you have to create a valid update sequence
- * array header in the ntfs record before calling this function, otherwise it
- * will fail (the header needs to contain the position of the update sequence
- * array together with the number of elements in the array). You also need to
- * initialise the update sequence number before calling this function
- * otherwise a random word will be used (whatever was in the record at that
- * position at that time).
- */
-int pre_write_mst_fixup(NTFS_RECORD *b, const u32 size)
-{
-	le16 *usa_pos, *data_pos;
-	u16 usa_ofs, usa_count, usn;
-	le16 le_usn;
-
-	/* Sanity check + only fixup if it makes sense. */
-	if (!b || ntfs_is_baad_record(b->magic) ||
-			ntfs_is_hole_record(b->magic))
-		return -EINVAL;
-	/* Setup the variables. */
-	usa_ofs = le16_to_cpu(b->usa_ofs);
-	/* Decrement usa_count to get number of fixups. */
-	usa_count = le16_to_cpu(b->usa_count) - 1;
-	/* Size and alignment checks. */
-	if ( size & (NTFS_BLOCK_SIZE - 1)	||
-	     usa_ofs & 1			||
-	     usa_ofs + (usa_count * 2) > size	||
-	     (size >> NTFS_BLOCK_SIZE_BITS) != usa_count)
-		return -EINVAL;
-	/* Position of usn in update sequence array. */
-	usa_pos = (le16*)((u8*)b + usa_ofs);
-	/*
-	 * Cyclically increment the update sequence number
-	 * (skipping 0 and -1, i.e. 0xffff).
-	 */
-	usn = le16_to_cpup(usa_pos) + 1;
-	if (usn == 0xffff || !usn)
-		usn = 1;
-	le_usn = cpu_to_le16(usn);
-	*usa_pos = le_usn;
-	/* Position in data of first u16 that needs fixing up. */
-	data_pos = (le16*)b + NTFS_BLOCK_SIZE/sizeof(le16) - 1;
-	/* Fixup all sectors. */
-	while (usa_count--) {
-		/*
-		 * Increment the position in the usa and save the
-		 * original data from the data buffer into the usa.
-		 */
-		*(++usa_pos) = *data_pos;
-		/* Apply fixup to data. */
-		*data_pos = le_usn;
-		/* Increment position in data as well. */
-		data_pos += NTFS_BLOCK_SIZE/sizeof(le16);
-	}
-	return 0;
-}
-
-/**
- * post_write_mst_fixup - fast deprotect multi sector transfer protected data
- * @b:		pointer to the data to deprotect
- *
- * Perform the necessary post write multi sector transfer fixup, not checking
- * for any errors, because we assume we have just used pre_write_mst_fixup(),
- * thus the data will be fine or we would never have gotten here.
- */
-void post_write_mst_fixup(NTFS_RECORD *b)
-{
-	le16 *usa_pos, *data_pos;
-
-	u16 usa_ofs = le16_to_cpu(b->usa_ofs);
-	u16 usa_count = le16_to_cpu(b->usa_count) - 1;
-
-	/* Position of usn in update sequence array. */
-	usa_pos = (le16*)b + usa_ofs/sizeof(le16);
-
-	/* Position in protected data of first u16 that needs fixing up. */
-	data_pos = (le16*)b + NTFS_BLOCK_SIZE/sizeof(le16) - 1;
-
-	/* Fixup all sectors. */
-	while (usa_count--) {
-		/*
-		 * Increment position in usa and restore original data from
-		 * the usa into the data buffer.
-		 */
-		*data_pos = *(++usa_pos);
-
-		/* Increment position in data as well. */
-		data_pos += NTFS_BLOCK_SIZE/sizeof(le16);
-	}
-}
diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c
deleted file mode 100644
index d7498ddc4a72..000000000000
--- a/fs/ntfs/namei.c
+++ /dev/null
@@ -1,392 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * namei.c - NTFS kernel directory inode operations. Part of the Linux-NTFS
- *	     project.
- *
- * Copyright (c) 2001-2006 Anton Altaparmakov
- */
-
-#include <linux/dcache.h>
-#include <linux/exportfs.h>
-#include <linux/security.h>
-#include <linux/slab.h>
-
-#include "attrib.h"
-#include "debug.h"
-#include "dir.h"
-#include "mft.h"
-#include "ntfs.h"
-
-/**
- * ntfs_lookup - find the inode represented by a dentry in a directory inode
- * @dir_ino:	directory inode in which to look for the inode
- * @dent:	dentry representing the inode to look for
- * @flags:	lookup flags
- *
- * In short, ntfs_lookup() looks for the inode represented by the dentry @dent
- * in the directory inode @dir_ino and if found attaches the inode to the
- * dentry @dent.
- *
- * In more detail, the dentry @dent specifies which inode to look for by
- * supplying the name of the inode in @dent->d_name.name. ntfs_lookup()
- * converts the name to Unicode and walks the contents of the directory inode
- * @dir_ino looking for the converted Unicode name. If the name is found in the
- * directory, the corresponding inode is loaded by calling ntfs_iget() on its
- * inode number and the inode is associated with the dentry @dent via a call to
- * d_splice_alias().
- *
- * If the name is not found in the directory, a NULL inode is inserted into the
- * dentry @dent via a call to d_add(). The dentry is then termed a negative
- * dentry.
- *
- * Only if an actual error occurs, do we return an error via ERR_PTR().
- *
- * In order to handle the case insensitivity issues of NTFS with regards to the
- * dcache and the dcache requiring only one dentry per directory, we deal with
- * dentry aliases that only differ in case in ->ntfs_lookup() while maintaining
- * a case sensitive dcache. This means that we get the full benefit of dcache
- * speed when the file/directory is looked up with the same case as returned by
- * ->ntfs_readdir() but that a lookup for any other case (or for the short file
- * name) will not find anything in dcache and will enter ->ntfs_lookup()
- * instead, where we search the directory for a fully matching file name
- * (including case) and if that is not found, we search for a file name that
- * matches with different case and if that has non-POSIX semantics we return
- * that. We actually do only one search (case sensitive) and keep tabs on
- * whether we have found a case insensitive match in the process.
- *
- * To simplify matters for us, we do not treat the short vs long filenames as
- * two hard links but instead if the lookup matches a short filename, we
- * return the dentry for the corresponding long filename instead.
- *
- * There are three cases we need to distinguish here:
- *
- * 1) @dent perfectly matches (i.e. including case) a directory entry with a
- *    file name in the WIN32 or POSIX namespaces. In this case
- *    ntfs_lookup_inode_by_name() will return with name set to NULL and we
- *    just d_splice_alias() @dent.
- * 2) @dent matches (not including case) a directory entry with a file name in
- *    the WIN32 namespace. In this case ntfs_lookup_inode_by_name() will return
- *    with name set to point to a kmalloc()ed ntfs_name structure containing
- *    the properly cased little endian Unicode name. We convert the name to the
- *    current NLS code page, search if a dentry with this name already exists
- *    and if so return that instead of @dent.  At this point things are
- *    complicated by the possibility of 'disconnected' dentries due to NFS
- *    which we deal with appropriately (see the code comments).  The VFS will
- *    then destroy the old @dent and use the one we returned.  If a dentry is
- *    not found, we allocate a new one, d_splice_alias() it, and return it as
- *    above.
- * 3) @dent matches either perfectly or not (i.e. we don't care about case) a
- *    directory entry with a file name in the DOS namespace. In this case
- *    ntfs_lookup_inode_by_name() will return with name set to point to a
- *    kmalloc()ed ntfs_name structure containing the mft reference (cpu endian)
- *    of the inode. We use the mft reference to read the inode and to find the
- *    file name in the WIN32 namespace corresponding to the matched short file
- *    name. We then convert the name to the current NLS code page, and proceed
- *    searching for a dentry with this name, etc, as in case 2), above.
- *
- * Locking: Caller must hold i_mutex on the directory.
- */
-static struct dentry *ntfs_lookup(struct inode *dir_ino, struct dentry *dent,
-		unsigned int flags)
-{
-	ntfs_volume *vol = NTFS_SB(dir_ino->i_sb);
-	struct inode *dent_inode;
-	ntfschar *uname;
-	ntfs_name *name = NULL;
-	MFT_REF mref;
-	unsigned long dent_ino;
-	int uname_len;
-
-	ntfs_debug("Looking up %pd in directory inode 0x%lx.",
-			dent, dir_ino->i_ino);
-	/* Convert the name of the dentry to Unicode. */
-	uname_len = ntfs_nlstoucs(vol, dent->d_name.name, dent->d_name.len,
-			&uname);
-	if (uname_len < 0) {
-		if (uname_len != -ENAMETOOLONG)
-			ntfs_error(vol->sb, "Failed to convert name to "
-					"Unicode.");
-		return ERR_PTR(uname_len);
-	}
-	mref = ntfs_lookup_inode_by_name(NTFS_I(dir_ino), uname, uname_len,
-			&name);
-	kmem_cache_free(ntfs_name_cache, uname);
-	if (!IS_ERR_MREF(mref)) {
-		dent_ino = MREF(mref);
-		ntfs_debug("Found inode 0x%lx. Calling ntfs_iget.", dent_ino);
-		dent_inode = ntfs_iget(vol->sb, dent_ino);
-		if (!IS_ERR(dent_inode)) {
-			/* Consistency check. */
-			if (is_bad_inode(dent_inode) || MSEQNO(mref) ==
-					NTFS_I(dent_inode)->seq_no ||
-					dent_ino == FILE_MFT) {
-				/* Perfect WIN32/POSIX match. -- Case 1. */
-				if (!name) {
-					ntfs_debug("Done.  (Case 1.)");
-					return d_splice_alias(dent_inode, dent);
-				}
-				/*
-				 * We are too indented.  Handle imperfect
-				 * matches and short file names further below.
-				 */
-				goto handle_name;
-			}
-			ntfs_error(vol->sb, "Found stale reference to inode "
-					"0x%lx (reference sequence number = "
-					"0x%x, inode sequence number = 0x%x), "
-					"returning -EIO. Run chkdsk.",
-					dent_ino, MSEQNO(mref),
-					NTFS_I(dent_inode)->seq_no);
-			iput(dent_inode);
-			dent_inode = ERR_PTR(-EIO);
-		} else
-			ntfs_error(vol->sb, "ntfs_iget(0x%lx) failed with "
-					"error code %li.", dent_ino,
-					PTR_ERR(dent_inode));
-		kfree(name);
-		/* Return the error code. */
-		return ERR_CAST(dent_inode);
-	}
-	/* It is guaranteed that @name is no longer allocated at this point. */
-	if (MREF_ERR(mref) == -ENOENT) {
-		ntfs_debug("Entry was not found, adding negative dentry.");
-		/* The dcache will handle negative entries. */
-		d_add(dent, NULL);
-		ntfs_debug("Done.");
-		return NULL;
-	}
-	ntfs_error(vol->sb, "ntfs_lookup_ino_by_name() failed with error "
-			"code %i.", -MREF_ERR(mref));
-	return ERR_PTR(MREF_ERR(mref));
-	// TODO: Consider moving this lot to a separate function! (AIA)
-handle_name:
-   {
-	MFT_RECORD *m;
-	ntfs_attr_search_ctx *ctx;
-	ntfs_inode *ni = NTFS_I(dent_inode);
-	int err;
-	struct qstr nls_name;
-
-	nls_name.name = NULL;
-	if (name->type != FILE_NAME_DOS) {			/* Case 2. */
-		ntfs_debug("Case 2.");
-		nls_name.len = (unsigned)ntfs_ucstonls(vol,
-				(ntfschar*)&name->name, name->len,
-				(unsigned char**)&nls_name.name, 0);
-		kfree(name);
-	} else /* if (name->type == FILE_NAME_DOS) */ {		/* Case 3. */
-		FILE_NAME_ATTR *fn;
-
-		ntfs_debug("Case 3.");
-		kfree(name);
-
-		/* Find the WIN32 name corresponding to the matched DOS name. */
-		ni = NTFS_I(dent_inode);
-		m = map_mft_record(ni);
-		if (IS_ERR(m)) {
-			err = PTR_ERR(m);
-			m = NULL;
-			ctx = NULL;
-			goto err_out;
-		}
-		ctx = ntfs_attr_get_search_ctx(ni, m);
-		if (unlikely(!ctx)) {
-			err = -ENOMEM;
-			goto err_out;
-		}
-		do {
-			ATTR_RECORD *a;
-			u32 val_len;
-
-			err = ntfs_attr_lookup(AT_FILE_NAME, NULL, 0, 0, 0,
-					NULL, 0, ctx);
-			if (unlikely(err)) {
-				ntfs_error(vol->sb, "Inode corrupt: No WIN32 "
-						"namespace counterpart to DOS "
-						"file name. Run chkdsk.");
-				if (err == -ENOENT)
-					err = -EIO;
-				goto err_out;
-			}
-			/* Consistency checks. */
-			a = ctx->attr;
-			if (a->non_resident || a->flags)
-				goto eio_err_out;
-			val_len = le32_to_cpu(a->data.resident.value_length);
-			if (le16_to_cpu(a->data.resident.value_offset) +
-					val_len > le32_to_cpu(a->length))
-				goto eio_err_out;
-			fn = (FILE_NAME_ATTR*)((u8*)ctx->attr + le16_to_cpu(
-					ctx->attr->data.resident.value_offset));
-			if ((u32)(fn->file_name_length * sizeof(ntfschar) +
-					sizeof(FILE_NAME_ATTR)) > val_len)
-				goto eio_err_out;
-		} while (fn->file_name_type != FILE_NAME_WIN32);
-
-		/* Convert the found WIN32 name to current NLS code page. */
-		nls_name.len = (unsigned)ntfs_ucstonls(vol,
-				(ntfschar*)&fn->file_name, fn->file_name_length,
-				(unsigned char**)&nls_name.name, 0);
-
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(ni);
-	}
-	m = NULL;
-	ctx = NULL;
-
-	/* Check if a conversion error occurred. */
-	if ((signed)nls_name.len < 0) {
-		err = (signed)nls_name.len;
-		goto err_out;
-	}
-	nls_name.hash = full_name_hash(dent, nls_name.name, nls_name.len);
-
-	dent = d_add_ci(dent, dent_inode, &nls_name);
-	kfree(nls_name.name);
-	return dent;
-
-eio_err_out:
-	ntfs_error(vol->sb, "Illegal file name attribute. Run chkdsk.");
-	err = -EIO;
-err_out:
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(ni);
-	iput(dent_inode);
-	ntfs_error(vol->sb, "Failed, returning error code %i.", err);
-	return ERR_PTR(err);
-   }
-}
-
-/*
- * Inode operations for directories.
- */
-const struct inode_operations ntfs_dir_inode_ops = {
-	.lookup	= ntfs_lookup,	/* VFS: Lookup directory. */
-};
-
-/**
- * ntfs_get_parent - find the dentry of the parent of a given directory dentry
- * @child_dent:		dentry of the directory whose parent directory to find
- *
- * Find the dentry for the parent directory of the directory specified by the
- * dentry @child_dent.  This function is called from
- * fs/exportfs/expfs.c::find_exported_dentry() which in turn is called from the
- * default ->decode_fh() which is export_decode_fh() in the same file.
- *
- * The code is based on the ext3 ->get_parent() implementation found in
- * fs/ext3/namei.c::ext3_get_parent().
- *
- * Note: ntfs_get_parent() is called with @d_inode(child_dent)->i_mutex down.
- *
- * Return the dentry of the parent directory on success or the error code on
- * error (IS_ERR() is true).
- */
-static struct dentry *ntfs_get_parent(struct dentry *child_dent)
-{
-	struct inode *vi = d_inode(child_dent);
-	ntfs_inode *ni = NTFS_I(vi);
-	MFT_RECORD *mrec;
-	ntfs_attr_search_ctx *ctx;
-	ATTR_RECORD *attr;
-	FILE_NAME_ATTR *fn;
-	unsigned long parent_ino;
-	int err;
-
-	ntfs_debug("Entering for inode 0x%lx.", vi->i_ino);
-	/* Get the mft record of the inode belonging to the child dentry. */
-	mrec = map_mft_record(ni);
-	if (IS_ERR(mrec))
-		return ERR_CAST(mrec);
-	/* Find the first file name attribute in the mft record. */
-	ctx = ntfs_attr_get_search_ctx(ni, mrec);
-	if (unlikely(!ctx)) {
-		unmap_mft_record(ni);
-		return ERR_PTR(-ENOMEM);
-	}
-try_next:
-	err = ntfs_attr_lookup(AT_FILE_NAME, NULL, 0, CASE_SENSITIVE, 0, NULL,
-			0, ctx);
-	if (unlikely(err)) {
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(ni);
-		if (err == -ENOENT)
-			ntfs_error(vi->i_sb, "Inode 0x%lx does not have a "
-					"file name attribute.  Run chkdsk.",
-					vi->i_ino);
-		return ERR_PTR(err);
-	}
-	attr = ctx->attr;
-	if (unlikely(attr->non_resident))
-		goto try_next;
-	fn = (FILE_NAME_ATTR *)((u8 *)attr +
-			le16_to_cpu(attr->data.resident.value_offset));
-	if (unlikely((u8 *)fn + le32_to_cpu(attr->data.resident.value_length) >
-			(u8*)attr + le32_to_cpu(attr->length)))
-		goto try_next;
-	/* Get the inode number of the parent directory. */
-	parent_ino = MREF_LE(fn->parent_directory);
-	/* Release the search context and the mft record of the child. */
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(ni);
-
-	return d_obtain_alias(ntfs_iget(vi->i_sb, parent_ino));
-}
-
-static struct inode *ntfs_nfs_get_inode(struct super_block *sb,
-		u64 ino, u32 generation)
-{
-	struct inode *inode;
-
-	inode = ntfs_iget(sb, ino);
-	if (!IS_ERR(inode)) {
-		if (is_bad_inode(inode) || inode->i_generation != generation) {
-			iput(inode);
-			inode = ERR_PTR(-ESTALE);
-		}
-	}
-
-	return inode;
-}
-
-static struct dentry *ntfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
-		int fh_len, int fh_type)
-{
-	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
-				    ntfs_nfs_get_inode);
-}
-
-static struct dentry *ntfs_fh_to_parent(struct super_block *sb, struct fid *fid,
-		int fh_len, int fh_type)
-{
-	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
-				    ntfs_nfs_get_inode);
-}
-
-/*
- * Export operations allowing NFS exporting of mounted NTFS partitions.
- *
- * We use the default ->encode_fh() for now.  Note that they
- * use 32 bits to store the inode number which is an unsigned long so on 64-bit
- * architectures is usually 64 bits so it would all fail horribly on huge
- * volumes.  I guess we need to define our own encode and decode fh functions
- * that store 64-bit inode numbers at some point but for now we will ignore the
- * problem...
- *
- * We also use the default ->get_name() helper (used by ->decode_fh() via
- * fs/exportfs/expfs.c::find_exported_dentry()) as that is completely fs
- * independent.
- *
- * The default ->get_parent() just returns -EACCES so we have to provide our
- * own and the default ->get_dentry() is incompatible with NTFS due to not
- * allowing the inode number 0 which is used in NTFS for the system file $MFT
- * and due to using iget() whereas NTFS needs ntfs_iget().
- */
-const struct export_operations ntfs_export_ops = {
-	.encode_fh	= generic_encode_ino32_fh,
-	.get_parent	= ntfs_get_parent,	/* Find the parent of a given
-						   directory. */
-	.fh_to_dentry	= ntfs_fh_to_dentry,
-	.fh_to_parent	= ntfs_fh_to_parent,
-};
diff --git a/fs/ntfs/ntfs.h b/fs/ntfs/ntfs.h
deleted file mode 100644
index e81376ea9152..000000000000
--- a/fs/ntfs/ntfs.h
+++ /dev/null
@@ -1,150 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * ntfs.h - Defines for NTFS Linux kernel driver.
- *
- * Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc.
- * Copyright (C) 2002 Richard Russon
- */
-
-#ifndef _LINUX_NTFS_H
-#define _LINUX_NTFS_H
-
-#include <linux/stddef.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/compiler.h>
-#include <linux/fs.h>
-#include <linux/nls.h>
-#include <linux/smp.h>
-#include <linux/pagemap.h>
-
-#include "types.h"
-#include "volume.h"
-#include "layout.h"
-
-typedef enum {
-	NTFS_BLOCK_SIZE		= 512,
-	NTFS_BLOCK_SIZE_BITS	= 9,
-	NTFS_SB_MAGIC		= 0x5346544e,	/* 'NTFS' */
-	NTFS_MAX_NAME_LEN	= 255,
-	NTFS_MAX_ATTR_NAME_LEN	= 255,
-	NTFS_MAX_CLUSTER_SIZE	= 64 * 1024,	/* 64kiB */
-	NTFS_MAX_PAGES_PER_CLUSTER = NTFS_MAX_CLUSTER_SIZE / PAGE_SIZE,
-} NTFS_CONSTANTS;
-
-/* Global variables. */
-
-/* Slab caches (from super.c). */
-extern struct kmem_cache *ntfs_name_cache;
-extern struct kmem_cache *ntfs_inode_cache;
-extern struct kmem_cache *ntfs_big_inode_cache;
-extern struct kmem_cache *ntfs_attr_ctx_cache;
-extern struct kmem_cache *ntfs_index_ctx_cache;
-
-/* The various operations structs defined throughout the driver files. */
-extern const struct address_space_operations ntfs_normal_aops;
-extern const struct address_space_operations ntfs_compressed_aops;
-extern const struct address_space_operations ntfs_mst_aops;
-
-extern const struct  file_operations ntfs_file_ops;
-extern const struct inode_operations ntfs_file_inode_ops;
-
-extern const struct  file_operations ntfs_dir_ops;
-extern const struct inode_operations ntfs_dir_inode_ops;
-
-extern const struct  file_operations ntfs_empty_file_ops;
-extern const struct inode_operations ntfs_empty_inode_ops;
-
-extern const struct export_operations ntfs_export_ops;
-
-/**
- * NTFS_SB - return the ntfs volume given a vfs super block
- * @sb:		VFS super block
- *
- * NTFS_SB() returns the ntfs volume associated with the VFS super block @sb.
- */
-static inline ntfs_volume *NTFS_SB(struct super_block *sb)
-{
-	return sb->s_fs_info;
-}
-
-/* Declarations of functions and global variables. */
-
-/* From fs/ntfs/compress.c */
-extern int ntfs_read_compressed_block(struct page *page);
-extern int allocate_compression_buffers(void);
-extern void free_compression_buffers(void);
-
-/* From fs/ntfs/super.c */
-#define default_upcase_len 0x10000
-extern struct mutex ntfs_lock;
-
-typedef struct {
-	int val;
-	char *str;
-} option_t;
-extern const option_t on_errors_arr[];
-
-/* From fs/ntfs/mst.c */
-extern int post_read_mst_fixup(NTFS_RECORD *b, const u32 size);
-extern int pre_write_mst_fixup(NTFS_RECORD *b, const u32 size);
-extern void post_write_mst_fixup(NTFS_RECORD *b);
-
-/* From fs/ntfs/unistr.c */
-extern bool ntfs_are_names_equal(const ntfschar *s1, size_t s1_len,
-		const ntfschar *s2, size_t s2_len,
-		const IGNORE_CASE_BOOL ic,
-		const ntfschar *upcase, const u32 upcase_size);
-extern int ntfs_collate_names(const ntfschar *name1, const u32 name1_len,
-		const ntfschar *name2, const u32 name2_len,
-		const int err_val, const IGNORE_CASE_BOOL ic,
-		const ntfschar *upcase, const u32 upcase_len);
-extern int ntfs_ucsncmp(const ntfschar *s1, const ntfschar *s2, size_t n);
-extern int ntfs_ucsncasecmp(const ntfschar *s1, const ntfschar *s2, size_t n,
-		const ntfschar *upcase, const u32 upcase_size);
-extern void ntfs_upcase_name(ntfschar *name, u32 name_len,
-		const ntfschar *upcase, const u32 upcase_len);
-extern void ntfs_file_upcase_value(FILE_NAME_ATTR *file_name_attr,
-		const ntfschar *upcase, const u32 upcase_len);
-extern int ntfs_file_compare_values(FILE_NAME_ATTR *file_name_attr1,
-		FILE_NAME_ATTR *file_name_attr2,
-		const int err_val, const IGNORE_CASE_BOOL ic,
-		const ntfschar *upcase, const u32 upcase_len);
-extern int ntfs_nlstoucs(const ntfs_volume *vol, const char *ins,
-		const int ins_len, ntfschar **outs);
-extern int ntfs_ucstonls(const ntfs_volume *vol, const ntfschar *ins,
-		const int ins_len, unsigned char **outs, int outs_len);
-
-/* From fs/ntfs/upcase.c */
-extern ntfschar *generate_default_upcase(void);
-
-static inline int ntfs_ffs(int x)
-{
-	int r = 1;
-
-	if (!x)
-		return 0;
-	if (!(x & 0xffff)) {
-		x >>= 16;
-		r += 16;
-	}
-	if (!(x & 0xff)) {
-		x >>= 8;
-		r += 8;
-	}
-	if (!(x & 0xf)) {
-		x >>= 4;
-		r += 4;
-	}
-	if (!(x & 3)) {
-		x >>= 2;
-		r += 2;
-	}
-	if (!(x & 1)) {
-		x >>= 1;
-		r += 1;
-	}
-	return r;
-}
-
-#endif /* _LINUX_NTFS_H */
diff --git a/fs/ntfs/quota.c b/fs/ntfs/quota.c
deleted file mode 100644
index 9160480222fd..000000000000
--- a/fs/ntfs/quota.c
+++ /dev/null
@@ -1,103 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * quota.c - NTFS kernel quota ($Quota) handling.  Part of the Linux-NTFS
- *	     project.
- *
- * Copyright (c) 2004 Anton Altaparmakov
- */
-
-#ifdef NTFS_RW
-
-#include "index.h"
-#include "quota.h"
-#include "debug.h"
-#include "ntfs.h"
-
-/**
- * ntfs_mark_quotas_out_of_date - mark the quotas out of date on an ntfs volume
- * @vol:	ntfs volume on which to mark the quotas out of date
- *
- * Mark the quotas out of date on the ntfs volume @vol and return 'true' on
- * success and 'false' on error.
- */
-bool ntfs_mark_quotas_out_of_date(ntfs_volume *vol)
-{
-	ntfs_index_context *ictx;
-	QUOTA_CONTROL_ENTRY *qce;
-	const le32 qid = QUOTA_DEFAULTS_ID;
-	int err;
-
-	ntfs_debug("Entering.");
-	if (NVolQuotaOutOfDate(vol))
-		goto done;
-	if (!vol->quota_ino || !vol->quota_q_ino) {
-		ntfs_error(vol->sb, "Quota inodes are not open.");
-		return false;
-	}
-	inode_lock(vol->quota_q_ino);
-	ictx = ntfs_index_ctx_get(NTFS_I(vol->quota_q_ino));
-	if (!ictx) {
-		ntfs_error(vol->sb, "Failed to get index context.");
-		goto err_out;
-	}
-	err = ntfs_index_lookup(&qid, sizeof(qid), ictx);
-	if (err) {
-		if (err == -ENOENT)
-			ntfs_error(vol->sb, "Quota defaults entry is not "
-					"present.");
-		else
-			ntfs_error(vol->sb, "Lookup of quota defaults entry "
-					"failed.");
-		goto err_out;
-	}
-	if (ictx->data_len < offsetof(QUOTA_CONTROL_ENTRY, sid)) {
-		ntfs_error(vol->sb, "Quota defaults entry size is invalid.  "
-				"Run chkdsk.");
-		goto err_out;
-	}
-	qce = (QUOTA_CONTROL_ENTRY*)ictx->data;
-	if (le32_to_cpu(qce->version) != QUOTA_VERSION) {
-		ntfs_error(vol->sb, "Quota defaults entry version 0x%x is not "
-				"supported.", le32_to_cpu(qce->version));
-		goto err_out;
-	}
-	ntfs_debug("Quota defaults flags = 0x%x.", le32_to_cpu(qce->flags));
-	/* If quotas are already marked out of date, no need to do anything. */
-	if (qce->flags & QUOTA_FLAG_OUT_OF_DATE)
-		goto set_done;
-	/*
-	 * If quota tracking is neither requested, nor enabled and there are no
-	 * pending deletes, no need to mark the quotas out of date.
-	 */
-	if (!(qce->flags & (QUOTA_FLAG_TRACKING_ENABLED |
-			QUOTA_FLAG_TRACKING_REQUESTED |
-			QUOTA_FLAG_PENDING_DELETES)))
-		goto set_done;
-	/*
-	 * Set the QUOTA_FLAG_OUT_OF_DATE bit thus marking quotas out of date.
-	 * This is verified on WinXP to be sufficient to cause windows to
-	 * rescan the volume on boot and update all quota entries.
-	 */
-	qce->flags |= QUOTA_FLAG_OUT_OF_DATE;
-	/* Ensure the modified flags are written to disk. */
-	ntfs_index_entry_flush_dcache_page(ictx);
-	ntfs_index_entry_mark_dirty(ictx);
-set_done:
-	ntfs_index_ctx_put(ictx);
-	inode_unlock(vol->quota_q_ino);
-	/*
-	 * We set the flag so we do not try to mark the quotas out of date
-	 * again on remount.
-	 */
-	NVolSetQuotaOutOfDate(vol);
-done:
-	ntfs_debug("Done.");
-	return true;
-err_out:
-	if (ictx)
-		ntfs_index_ctx_put(ictx);
-	inode_unlock(vol->quota_q_ino);
-	return false;
-}
-
-#endif /* NTFS_RW */
diff --git a/fs/ntfs/quota.h b/fs/ntfs/quota.h
deleted file mode 100644
index fe3132a3d6d2..000000000000
--- a/fs/ntfs/quota.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * quota.h - Defines for NTFS kernel quota ($Quota) handling.  Part of the
- *	     Linux-NTFS project.
- *
- * Copyright (c) 2004 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_QUOTA_H
-#define _LINUX_NTFS_QUOTA_H
-
-#ifdef NTFS_RW
-
-#include "types.h"
-#include "volume.h"
-
-extern bool ntfs_mark_quotas_out_of_date(ntfs_volume *vol);
-
-#endif /* NTFS_RW */
-
-#endif /* _LINUX_NTFS_QUOTA_H */
diff --git a/fs/ntfs/runlist.c b/fs/ntfs/runlist.c
deleted file mode 100644
index 0d448e9881f7..000000000000
--- a/fs/ntfs/runlist.c
+++ /dev/null
@@ -1,1893 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * runlist.c - NTFS runlist handling code.  Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2007 Anton Altaparmakov
- * Copyright (c) 2002-2005 Richard Russon
- */
-
-#include "debug.h"
-#include "dir.h"
-#include "endian.h"
-#include "malloc.h"
-#include "ntfs.h"
-
-/**
- * ntfs_rl_mm - runlist memmove
- *
- * It is up to the caller to serialize access to the runlist @base.
- */
-static inline void ntfs_rl_mm(runlist_element *base, int dst, int src,
-		int size)
-{
-	if (likely((dst != src) && (size > 0)))
-		memmove(base + dst, base + src, size * sizeof(*base));
-}
-
-/**
- * ntfs_rl_mc - runlist memory copy
- *
- * It is up to the caller to serialize access to the runlists @dstbase and
- * @srcbase.
- */
-static inline void ntfs_rl_mc(runlist_element *dstbase, int dst,
-		runlist_element *srcbase, int src, int size)
-{
-	if (likely(size > 0))
-		memcpy(dstbase + dst, srcbase + src, size * sizeof(*dstbase));
-}
-
-/**
- * ntfs_rl_realloc - Reallocate memory for runlists
- * @rl:		original runlist
- * @old_size:	number of runlist elements in the original runlist @rl
- * @new_size:	number of runlist elements we need space for
- *
- * As the runlists grow, more memory will be required.  To prevent the
- * kernel having to allocate and reallocate large numbers of small bits of
- * memory, this function returns an entire page of memory.
- *
- * It is up to the caller to serialize access to the runlist @rl.
- *
- * N.B.  If the new allocation doesn't require a different number of pages in
- *       memory, the function will return the original pointer.
- *
- * On success, return a pointer to the newly allocated, or recycled, memory.
- * On error, return -errno. The following error codes are defined:
- *	-ENOMEM	- Not enough memory to allocate runlist array.
- *	-EINVAL	- Invalid parameters were passed in.
- */
-static inline runlist_element *ntfs_rl_realloc(runlist_element *rl,
-		int old_size, int new_size)
-{
-	runlist_element *new_rl;
-
-	old_size = PAGE_ALIGN(old_size * sizeof(*rl));
-	new_size = PAGE_ALIGN(new_size * sizeof(*rl));
-	if (old_size == new_size)
-		return rl;
-
-	new_rl = ntfs_malloc_nofs(new_size);
-	if (unlikely(!new_rl))
-		return ERR_PTR(-ENOMEM);
-
-	if (likely(rl != NULL)) {
-		if (unlikely(old_size > new_size))
-			old_size = new_size;
-		memcpy(new_rl, rl, old_size);
-		ntfs_free(rl);
-	}
-	return new_rl;
-}
-
-/**
- * ntfs_rl_realloc_nofail - Reallocate memory for runlists
- * @rl:		original runlist
- * @old_size:	number of runlist elements in the original runlist @rl
- * @new_size:	number of runlist elements we need space for
- *
- * As the runlists grow, more memory will be required.  To prevent the
- * kernel having to allocate and reallocate large numbers of small bits of
- * memory, this function returns an entire page of memory.
- *
- * This function guarantees that the allocation will succeed.  It will sleep
- * for as long as it takes to complete the allocation.
- *
- * It is up to the caller to serialize access to the runlist @rl.
- *
- * N.B.  If the new allocation doesn't require a different number of pages in
- *       memory, the function will return the original pointer.
- *
- * On success, return a pointer to the newly allocated, or recycled, memory.
- * On error, return -errno. The following error codes are defined:
- *	-ENOMEM	- Not enough memory to allocate runlist array.
- *	-EINVAL	- Invalid parameters were passed in.
- */
-static inline runlist_element *ntfs_rl_realloc_nofail(runlist_element *rl,
-		int old_size, int new_size)
-{
-	runlist_element *new_rl;
-
-	old_size = PAGE_ALIGN(old_size * sizeof(*rl));
-	new_size = PAGE_ALIGN(new_size * sizeof(*rl));
-	if (old_size == new_size)
-		return rl;
-
-	new_rl = ntfs_malloc_nofs_nofail(new_size);
-	BUG_ON(!new_rl);
-
-	if (likely(rl != NULL)) {
-		if (unlikely(old_size > new_size))
-			old_size = new_size;
-		memcpy(new_rl, rl, old_size);
-		ntfs_free(rl);
-	}
-	return new_rl;
-}
-
-/**
- * ntfs_are_rl_mergeable - test if two runlists can be joined together
- * @dst:	original runlist
- * @src:	new runlist to test for mergeability with @dst
- *
- * Test if two runlists can be joined together. For this, their VCNs and LCNs
- * must be adjacent.
- *
- * It is up to the caller to serialize access to the runlists @dst and @src.
- *
- * Return: true   Success, the runlists can be merged.
- *	   false  Failure, the runlists cannot be merged.
- */
-static inline bool ntfs_are_rl_mergeable(runlist_element *dst,
-		runlist_element *src)
-{
-	BUG_ON(!dst);
-	BUG_ON(!src);
-
-	/* We can merge unmapped regions even if they are misaligned. */
-	if ((dst->lcn == LCN_RL_NOT_MAPPED) && (src->lcn == LCN_RL_NOT_MAPPED))
-		return true;
-	/* If the runs are misaligned, we cannot merge them. */
-	if ((dst->vcn + dst->length) != src->vcn)
-		return false;
-	/* If both runs are non-sparse and contiguous, we can merge them. */
-	if ((dst->lcn >= 0) && (src->lcn >= 0) &&
-			((dst->lcn + dst->length) == src->lcn))
-		return true;
-	/* If we are merging two holes, we can merge them. */
-	if ((dst->lcn == LCN_HOLE) && (src->lcn == LCN_HOLE))
-		return true;
-	/* Cannot merge. */
-	return false;
-}
-
-/**
- * __ntfs_rl_merge - merge two runlists without testing if they can be merged
- * @dst:	original, destination runlist
- * @src:	new runlist to merge with @dst
- *
- * Merge the two runlists, writing into the destination runlist @dst. The
- * caller must make sure the runlists can be merged or this will corrupt the
- * destination runlist.
- *
- * It is up to the caller to serialize access to the runlists @dst and @src.
- */
-static inline void __ntfs_rl_merge(runlist_element *dst, runlist_element *src)
-{
-	dst->length += src->length;
-}
-
-/**
- * ntfs_rl_append - append a runlist after a given element
- * @dst:	original runlist to be worked on
- * @dsize:	number of elements in @dst (including end marker)
- * @src:	runlist to be inserted into @dst
- * @ssize:	number of elements in @src (excluding end marker)
- * @loc:	append the new runlist @src after this element in @dst
- *
- * Append the runlist @src after element @loc in @dst.  Merge the right end of
- * the new runlist, if necessary. Adjust the size of the hole before the
- * appended runlist.
- *
- * It is up to the caller to serialize access to the runlists @dst and @src.
- *
- * On success, return a pointer to the new, combined, runlist. Note, both
- * runlists @dst and @src are deallocated before returning so you cannot use
- * the pointers for anything any more. (Strictly speaking the returned runlist
- * may be the same as @dst but this is irrelevant.)
- *
- * On error, return -errno. Both runlists are left unmodified. The following
- * error codes are defined:
- *	-ENOMEM	- Not enough memory to allocate runlist array.
- *	-EINVAL	- Invalid parameters were passed in.
- */
-static inline runlist_element *ntfs_rl_append(runlist_element *dst,
-		int dsize, runlist_element *src, int ssize, int loc)
-{
-	bool right = false;	/* Right end of @src needs merging. */
-	int marker;		/* End of the inserted runs. */
-
-	BUG_ON(!dst);
-	BUG_ON(!src);
-
-	/* First, check if the right hand end needs merging. */
-	if ((loc + 1) < dsize)
-		right = ntfs_are_rl_mergeable(src + ssize - 1, dst + loc + 1);
-
-	/* Space required: @dst size + @src size, less one if we merged. */
-	dst = ntfs_rl_realloc(dst, dsize, dsize + ssize - right);
-	if (IS_ERR(dst))
-		return dst;
-	/*
-	 * We are guaranteed to succeed from here so can start modifying the
-	 * original runlists.
-	 */
-
-	/* First, merge the right hand end, if necessary. */
-	if (right)
-		__ntfs_rl_merge(src + ssize - 1, dst + loc + 1);
-
-	/* First run after the @src runs that have been inserted. */
-	marker = loc + ssize + 1;
-
-	/* Move the tail of @dst out of the way, then copy in @src. */
-	ntfs_rl_mm(dst, marker, loc + 1 + right, dsize - (loc + 1 + right));
-	ntfs_rl_mc(dst, loc + 1, src, 0, ssize);
-
-	/* Adjust the size of the preceding hole. */
-	dst[loc].length = dst[loc + 1].vcn - dst[loc].vcn;
-
-	/* We may have changed the length of the file, so fix the end marker */
-	if (dst[marker].lcn == LCN_ENOENT)
-		dst[marker].vcn = dst[marker - 1].vcn + dst[marker - 1].length;
-
-	return dst;
-}
-
-/**
- * ntfs_rl_insert - insert a runlist into another
- * @dst:	original runlist to be worked on
- * @dsize:	number of elements in @dst (including end marker)
- * @src:	new runlist to be inserted
- * @ssize:	number of elements in @src (excluding end marker)
- * @loc:	insert the new runlist @src before this element in @dst
- *
- * Insert the runlist @src before element @loc in the runlist @dst. Merge the
- * left end of the new runlist, if necessary. Adjust the size of the hole
- * after the inserted runlist.
- *
- * It is up to the caller to serialize access to the runlists @dst and @src.
- *
- * On success, return a pointer to the new, combined, runlist. Note, both
- * runlists @dst and @src are deallocated before returning so you cannot use
- * the pointers for anything any more. (Strictly speaking the returned runlist
- * may be the same as @dst but this is irrelevant.)
- *
- * On error, return -errno. Both runlists are left unmodified. The following
- * error codes are defined:
- *	-ENOMEM	- Not enough memory to allocate runlist array.
- *	-EINVAL	- Invalid parameters were passed in.
- */
-static inline runlist_element *ntfs_rl_insert(runlist_element *dst,
-		int dsize, runlist_element *src, int ssize, int loc)
-{
-	bool left = false;	/* Left end of @src needs merging. */
-	bool disc = false;	/* Discontinuity between @dst and @src. */
-	int marker;		/* End of the inserted runs. */
-
-	BUG_ON(!dst);
-	BUG_ON(!src);
-
-	/*
-	 * disc => Discontinuity between the end of @dst and the start of @src.
-	 *	   This means we might need to insert a "not mapped" run.
-	 */
-	if (loc == 0)
-		disc = (src[0].vcn > 0);
-	else {
-		s64 merged_length;
-
-		left = ntfs_are_rl_mergeable(dst + loc - 1, src);
-
-		merged_length = dst[loc - 1].length;
-		if (left)
-			merged_length += src->length;
-
-		disc = (src[0].vcn > dst[loc - 1].vcn + merged_length);
-	}
-	/*
-	 * Space required: @dst size + @src size, less one if we merged, plus
-	 * one if there was a discontinuity.
-	 */
-	dst = ntfs_rl_realloc(dst, dsize, dsize + ssize - left + disc);
-	if (IS_ERR(dst))
-		return dst;
-	/*
-	 * We are guaranteed to succeed from here so can start modifying the
-	 * original runlist.
-	 */
-	if (left)
-		__ntfs_rl_merge(dst + loc - 1, src);
-	/*
-	 * First run after the @src runs that have been inserted.
-	 * Nominally,  @marker equals @loc + @ssize, i.e. location + number of
-	 * runs in @src.  However, if @left, then the first run in @src has
-	 * been merged with one in @dst.  And if @disc, then @dst and @src do
-	 * not meet and we need an extra run to fill the gap.
-	 */
-	marker = loc + ssize - left + disc;
-
-	/* Move the tail of @dst out of the way, then copy in @src. */
-	ntfs_rl_mm(dst, marker, loc, dsize - loc);
-	ntfs_rl_mc(dst, loc + disc, src, left, ssize - left);
-
-	/* Adjust the VCN of the first run after the insertion... */
-	dst[marker].vcn = dst[marker - 1].vcn + dst[marker - 1].length;
-	/* ... and the length. */
-	if (dst[marker].lcn == LCN_HOLE || dst[marker].lcn == LCN_RL_NOT_MAPPED)
-		dst[marker].length = dst[marker + 1].vcn - dst[marker].vcn;
-
-	/* Writing beyond the end of the file and there is a discontinuity. */
-	if (disc) {
-		if (loc > 0) {
-			dst[loc].vcn = dst[loc - 1].vcn + dst[loc - 1].length;
-			dst[loc].length = dst[loc + 1].vcn - dst[loc].vcn;
-		} else {
-			dst[loc].vcn = 0;
-			dst[loc].length = dst[loc + 1].vcn;
-		}
-		dst[loc].lcn = LCN_RL_NOT_MAPPED;
-	}
-	return dst;
-}
-
-/**
- * ntfs_rl_replace - overwrite a runlist element with another runlist
- * @dst:	original runlist to be worked on
- * @dsize:	number of elements in @dst (including end marker)
- * @src:	new runlist to be inserted
- * @ssize:	number of elements in @src (excluding end marker)
- * @loc:	index in runlist @dst to overwrite with @src
- *
- * Replace the runlist element @dst at @loc with @src. Merge the left and
- * right ends of the inserted runlist, if necessary.
- *
- * It is up to the caller to serialize access to the runlists @dst and @src.
- *
- * On success, return a pointer to the new, combined, runlist. Note, both
- * runlists @dst and @src are deallocated before returning so you cannot use
- * the pointers for anything any more. (Strictly speaking the returned runlist
- * may be the same as @dst but this is irrelevant.)
- *
- * On error, return -errno. Both runlists are left unmodified. The following
- * error codes are defined:
- *	-ENOMEM	- Not enough memory to allocate runlist array.
- *	-EINVAL	- Invalid parameters were passed in.
- */
-static inline runlist_element *ntfs_rl_replace(runlist_element *dst,
-		int dsize, runlist_element *src, int ssize, int loc)
-{
-	signed delta;
-	bool left = false;	/* Left end of @src needs merging. */
-	bool right = false;	/* Right end of @src needs merging. */
-	int tail;		/* Start of tail of @dst. */
-	int marker;		/* End of the inserted runs. */
-
-	BUG_ON(!dst);
-	BUG_ON(!src);
-
-	/* First, see if the left and right ends need merging. */
-	if ((loc + 1) < dsize)
-		right = ntfs_are_rl_mergeable(src + ssize - 1, dst + loc + 1);
-	if (loc > 0)
-		left = ntfs_are_rl_mergeable(dst + loc - 1, src);
-	/*
-	 * Allocate some space.  We will need less if the left, right, or both
-	 * ends get merged.  The -1 accounts for the run being replaced.
-	 */
-	delta = ssize - 1 - left - right;
-	if (delta > 0) {
-		dst = ntfs_rl_realloc(dst, dsize, dsize + delta);
-		if (IS_ERR(dst))
-			return dst;
-	}
-	/*
-	 * We are guaranteed to succeed from here so can start modifying the
-	 * original runlists.
-	 */
-
-	/* First, merge the left and right ends, if necessary. */
-	if (right)
-		__ntfs_rl_merge(src + ssize - 1, dst + loc + 1);
-	if (left)
-		__ntfs_rl_merge(dst + loc - 1, src);
-	/*
-	 * Offset of the tail of @dst.  This needs to be moved out of the way
-	 * to make space for the runs to be copied from @src, i.e. the first
-	 * run of the tail of @dst.
-	 * Nominally, @tail equals @loc + 1, i.e. location, skipping the
-	 * replaced run.  However, if @right, then one of @dst's runs is
-	 * already merged into @src.
-	 */
-	tail = loc + right + 1;
-	/*
-	 * First run after the @src runs that have been inserted, i.e. where
-	 * the tail of @dst needs to be moved to.
-	 * Nominally, @marker equals @loc + @ssize, i.e. location + number of
-	 * runs in @src.  However, if @left, then the first run in @src has
-	 * been merged with one in @dst.
-	 */
-	marker = loc + ssize - left;
-
-	/* Move the tail of @dst out of the way, then copy in @src. */
-	ntfs_rl_mm(dst, marker, tail, dsize - tail);
-	ntfs_rl_mc(dst, loc, src, left, ssize - left);
-
-	/* We may have changed the length of the file, so fix the end marker. */
-	if (dsize - tail > 0 && dst[marker].lcn == LCN_ENOENT)
-		dst[marker].vcn = dst[marker - 1].vcn + dst[marker - 1].length;
-	return dst;
-}
-
-/**
- * ntfs_rl_split - insert a runlist into the centre of a hole
- * @dst:	original runlist to be worked on
- * @dsize:	number of elements in @dst (including end marker)
- * @src:	new runlist to be inserted
- * @ssize:	number of elements in @src (excluding end marker)
- * @loc:	index in runlist @dst at which to split and insert @src
- *
- * Split the runlist @dst at @loc into two and insert @new in between the two
- * fragments. No merging of runlists is necessary. Adjust the size of the
- * holes either side.
- *
- * It is up to the caller to serialize access to the runlists @dst and @src.
- *
- * On success, return a pointer to the new, combined, runlist. Note, both
- * runlists @dst and @src are deallocated before returning so you cannot use
- * the pointers for anything any more. (Strictly speaking the returned runlist
- * may be the same as @dst but this is irrelevant.)
- *
- * On error, return -errno. Both runlists are left unmodified. The following
- * error codes are defined:
- *	-ENOMEM	- Not enough memory to allocate runlist array.
- *	-EINVAL	- Invalid parameters were passed in.
- */
-static inline runlist_element *ntfs_rl_split(runlist_element *dst, int dsize,
-		runlist_element *src, int ssize, int loc)
-{
-	BUG_ON(!dst);
-	BUG_ON(!src);
-
-	/* Space required: @dst size + @src size + one new hole. */
-	dst = ntfs_rl_realloc(dst, dsize, dsize + ssize + 1);
-	if (IS_ERR(dst))
-		return dst;
-	/*
-	 * We are guaranteed to succeed from here so can start modifying the
-	 * original runlists.
-	 */
-
-	/* Move the tail of @dst out of the way, then copy in @src. */
-	ntfs_rl_mm(dst, loc + 1 + ssize, loc, dsize - loc);
-	ntfs_rl_mc(dst, loc + 1, src, 0, ssize);
-
-	/* Adjust the size of the holes either size of @src. */
-	dst[loc].length		= dst[loc+1].vcn       - dst[loc].vcn;
-	dst[loc+ssize+1].vcn    = dst[loc+ssize].vcn   + dst[loc+ssize].length;
-	dst[loc+ssize+1].length = dst[loc+ssize+2].vcn - dst[loc+ssize+1].vcn;
-
-	return dst;
-}
-
-/**
- * ntfs_runlists_merge - merge two runlists into one
- * @drl:	original runlist to be worked on
- * @srl:	new runlist to be merged into @drl
- *
- * First we sanity check the two runlists @srl and @drl to make sure that they
- * are sensible and can be merged. The runlist @srl must be either after the
- * runlist @drl or completely within a hole (or unmapped region) in @drl.
- *
- * It is up to the caller to serialize access to the runlists @drl and @srl.
- *
- * Merging of runlists is necessary in two cases:
- *   1. When attribute lists are used and a further extent is being mapped.
- *   2. When new clusters are allocated to fill a hole or extend a file.
- *
- * There are four possible ways @srl can be merged. It can:
- *	- be inserted at the beginning of a hole,
- *	- split the hole in two and be inserted between the two fragments,
- *	- be appended at the end of a hole, or it can
- *	- replace the whole hole.
- * It can also be appended to the end of the runlist, which is just a variant
- * of the insert case.
- *
- * On success, return a pointer to the new, combined, runlist. Note, both
- * runlists @drl and @srl are deallocated before returning so you cannot use
- * the pointers for anything any more. (Strictly speaking the returned runlist
- * may be the same as @dst but this is irrelevant.)
- *
- * On error, return -errno. Both runlists are left unmodified. The following
- * error codes are defined:
- *	-ENOMEM	- Not enough memory to allocate runlist array.
- *	-EINVAL	- Invalid parameters were passed in.
- *	-ERANGE	- The runlists overlap and cannot be merged.
- */
-runlist_element *ntfs_runlists_merge(runlist_element *drl,
-		runlist_element *srl)
-{
-	int di, si;		/* Current index into @[ds]rl. */
-	int sstart;		/* First index with lcn > LCN_RL_NOT_MAPPED. */
-	int dins;		/* Index into @drl at which to insert @srl. */
-	int dend, send;		/* Last index into @[ds]rl. */
-	int dfinal, sfinal;	/* The last index into @[ds]rl with
-				   lcn >= LCN_HOLE. */
-	int marker = 0;
-	VCN marker_vcn = 0;
-
-#ifdef DEBUG
-	ntfs_debug("dst:");
-	ntfs_debug_dump_runlist(drl);
-	ntfs_debug("src:");
-	ntfs_debug_dump_runlist(srl);
-#endif
-
-	/* Check for silly calling... */
-	if (unlikely(!srl))
-		return drl;
-	if (IS_ERR(srl) || IS_ERR(drl))
-		return ERR_PTR(-EINVAL);
-
-	/* Check for the case where the first mapping is being done now. */
-	if (unlikely(!drl)) {
-		drl = srl;
-		/* Complete the source runlist if necessary. */
-		if (unlikely(drl[0].vcn)) {
-			/* Scan to the end of the source runlist. */
-			for (dend = 0; likely(drl[dend].length); dend++)
-				;
-			dend++;
-			drl = ntfs_rl_realloc(drl, dend, dend + 1);
-			if (IS_ERR(drl))
-				return drl;
-			/* Insert start element at the front of the runlist. */
-			ntfs_rl_mm(drl, 1, 0, dend);
-			drl[0].vcn = 0;
-			drl[0].lcn = LCN_RL_NOT_MAPPED;
-			drl[0].length = drl[1].vcn;
-		}
-		goto finished;
-	}
-
-	si = di = 0;
-
-	/* Skip any unmapped start element(s) in the source runlist. */
-	while (srl[si].length && srl[si].lcn < LCN_HOLE)
-		si++;
-
-	/* Can't have an entirely unmapped source runlist. */
-	BUG_ON(!srl[si].length);
-
-	/* Record the starting points. */
-	sstart = si;
-
-	/*
-	 * Skip forward in @drl until we reach the position where @srl needs to
-	 * be inserted. If we reach the end of @drl, @srl just needs to be
-	 * appended to @drl.
-	 */
-	for (; drl[di].length; di++) {
-		if (drl[di].vcn + drl[di].length > srl[sstart].vcn)
-			break;
-	}
-	dins = di;
-
-	/* Sanity check for illegal overlaps. */
-	if ((drl[di].vcn == srl[si].vcn) && (drl[di].lcn >= 0) &&
-			(srl[si].lcn >= 0)) {
-		ntfs_error(NULL, "Run lists overlap. Cannot merge!");
-		return ERR_PTR(-ERANGE);
-	}
-
-	/* Scan to the end of both runlists in order to know their sizes. */
-	for (send = si; srl[send].length; send++)
-		;
-	for (dend = di; drl[dend].length; dend++)
-		;
-
-	if (srl[send].lcn == LCN_ENOENT)
-		marker_vcn = srl[marker = send].vcn;
-
-	/* Scan to the last element with lcn >= LCN_HOLE. */
-	for (sfinal = send; sfinal >= 0 && srl[sfinal].lcn < LCN_HOLE; sfinal--)
-		;
-	for (dfinal = dend; dfinal >= 0 && drl[dfinal].lcn < LCN_HOLE; dfinal--)
-		;
-
-	{
-	bool start;
-	bool finish;
-	int ds = dend + 1;		/* Number of elements in drl & srl */
-	int ss = sfinal - sstart + 1;
-
-	start  = ((drl[dins].lcn <  LCN_RL_NOT_MAPPED) ||    /* End of file   */
-		  (drl[dins].vcn == srl[sstart].vcn));	     /* Start of hole */
-	finish = ((drl[dins].lcn >= LCN_RL_NOT_MAPPED) &&    /* End of file   */
-		 ((drl[dins].vcn + drl[dins].length) <=      /* End of hole   */
-		  (srl[send - 1].vcn + srl[send - 1].length)));
-
-	/* Or we will lose an end marker. */
-	if (finish && !drl[dins].length)
-		ss++;
-	if (marker && (drl[dins].vcn + drl[dins].length > srl[send - 1].vcn))
-		finish = false;
-#if 0
-	ntfs_debug("dfinal = %i, dend = %i", dfinal, dend);
-	ntfs_debug("sstart = %i, sfinal = %i, send = %i", sstart, sfinal, send);
-	ntfs_debug("start = %i, finish = %i", start, finish);
-	ntfs_debug("ds = %i, ss = %i, dins = %i", ds, ss, dins);
-#endif
-	if (start) {
-		if (finish)
-			drl = ntfs_rl_replace(drl, ds, srl + sstart, ss, dins);
-		else
-			drl = ntfs_rl_insert(drl, ds, srl + sstart, ss, dins);
-	} else {
-		if (finish)
-			drl = ntfs_rl_append(drl, ds, srl + sstart, ss, dins);
-		else
-			drl = ntfs_rl_split(drl, ds, srl + sstart, ss, dins);
-	}
-	if (IS_ERR(drl)) {
-		ntfs_error(NULL, "Merge failed.");
-		return drl;
-	}
-	ntfs_free(srl);
-	if (marker) {
-		ntfs_debug("Triggering marker code.");
-		for (ds = dend; drl[ds].length; ds++)
-			;
-		/* We only need to care if @srl ended after @drl. */
-		if (drl[ds].vcn <= marker_vcn) {
-			int slots = 0;
-
-			if (drl[ds].vcn == marker_vcn) {
-				ntfs_debug("Old marker = 0x%llx, replacing "
-						"with LCN_ENOENT.",
-						(unsigned long long)
-						drl[ds].lcn);
-				drl[ds].lcn = LCN_ENOENT;
-				goto finished;
-			}
-			/*
-			 * We need to create an unmapped runlist element in
-			 * @drl or extend an existing one before adding the
-			 * ENOENT terminator.
-			 */
-			if (drl[ds].lcn == LCN_ENOENT) {
-				ds--;
-				slots = 1;
-			}
-			if (drl[ds].lcn != LCN_RL_NOT_MAPPED) {
-				/* Add an unmapped runlist element. */
-				if (!slots) {
-					drl = ntfs_rl_realloc_nofail(drl, ds,
-							ds + 2);
-					slots = 2;
-				}
-				ds++;
-				/* Need to set vcn if it isn't set already. */
-				if (slots != 1)
-					drl[ds].vcn = drl[ds - 1].vcn +
-							drl[ds - 1].length;
-				drl[ds].lcn = LCN_RL_NOT_MAPPED;
-				/* We now used up a slot. */
-				slots--;
-			}
-			drl[ds].length = marker_vcn - drl[ds].vcn;
-			/* Finally add the ENOENT terminator. */
-			ds++;
-			if (!slots)
-				drl = ntfs_rl_realloc_nofail(drl, ds, ds + 1);
-			drl[ds].vcn = marker_vcn;
-			drl[ds].lcn = LCN_ENOENT;
-			drl[ds].length = (s64)0;
-		}
-	}
-	}
-
-finished:
-	/* The merge was completed successfully. */
-	ntfs_debug("Merged runlist:");
-	ntfs_debug_dump_runlist(drl);
-	return drl;
-}
-
-/**
- * ntfs_mapping_pairs_decompress - convert mapping pairs array to runlist
- * @vol:	ntfs volume on which the attribute resides
- * @attr:	attribute record whose mapping pairs array to decompress
- * @old_rl:	optional runlist in which to insert @attr's runlist
- *
- * It is up to the caller to serialize access to the runlist @old_rl.
- *
- * Decompress the attribute @attr's mapping pairs array into a runlist. On
- * success, return the decompressed runlist.
- *
- * If @old_rl is not NULL, decompressed runlist is inserted into the
- * appropriate place in @old_rl and the resultant, combined runlist is
- * returned. The original @old_rl is deallocated.
- *
- * On error, return -errno. @old_rl is left unmodified in that case.
- *
- * The following error codes are defined:
- *	-ENOMEM	- Not enough memory to allocate runlist array.
- *	-EIO	- Corrupt runlist.
- *	-EINVAL	- Invalid parameters were passed in.
- *	-ERANGE	- The two runlists overlap.
- *
- * FIXME: For now we take the conceptionally simplest approach of creating the
- * new runlist disregarding the already existing one and then splicing the
- * two into one, if that is possible (we check for overlap and discard the new
- * runlist if overlap present before returning ERR_PTR(-ERANGE)).
- */
-runlist_element *ntfs_mapping_pairs_decompress(const ntfs_volume *vol,
-		const ATTR_RECORD *attr, runlist_element *old_rl)
-{
-	VCN vcn;		/* Current vcn. */
-	LCN lcn;		/* Current lcn. */
-	s64 deltaxcn;		/* Change in [vl]cn. */
-	runlist_element *rl;	/* The output runlist. */
-	u8 *buf;		/* Current position in mapping pairs array. */
-	u8 *attr_end;		/* End of attribute. */
-	int rlsize;		/* Size of runlist buffer. */
-	u16 rlpos;		/* Current runlist position in units of
-				   runlist_elements. */
-	u8 b;			/* Current byte offset in buf. */
-
-#ifdef DEBUG
-	/* Make sure attr exists and is non-resident. */
-	if (!attr || !attr->non_resident || sle64_to_cpu(
-			attr->data.non_resident.lowest_vcn) < (VCN)0) {
-		ntfs_error(vol->sb, "Invalid arguments.");
-		return ERR_PTR(-EINVAL);
-	}
-#endif
-	/* Start at vcn = lowest_vcn and lcn 0. */
-	vcn = sle64_to_cpu(attr->data.non_resident.lowest_vcn);
-	lcn = 0;
-	/* Get start of the mapping pairs array. */
-	buf = (u8*)attr + le16_to_cpu(
-			attr->data.non_resident.mapping_pairs_offset);
-	attr_end = (u8*)attr + le32_to_cpu(attr->length);
-	if (unlikely(buf < (u8*)attr || buf > attr_end)) {
-		ntfs_error(vol->sb, "Corrupt attribute.");
-		return ERR_PTR(-EIO);
-	}
-	/* If the mapping pairs array is valid but empty, nothing to do. */
-	if (!vcn && !*buf)
-		return old_rl;
-	/* Current position in runlist array. */
-	rlpos = 0;
-	/* Allocate first page and set current runlist size to one page. */
-	rl = ntfs_malloc_nofs(rlsize = PAGE_SIZE);
-	if (unlikely(!rl))
-		return ERR_PTR(-ENOMEM);
-	/* Insert unmapped starting element if necessary. */
-	if (vcn) {
-		rl->vcn = 0;
-		rl->lcn = LCN_RL_NOT_MAPPED;
-		rl->length = vcn;
-		rlpos++;
-	}
-	while (buf < attr_end && *buf) {
-		/*
-		 * Allocate more memory if needed, including space for the
-		 * not-mapped and terminator elements. ntfs_malloc_nofs()
-		 * operates on whole pages only.
-		 */
-		if (((rlpos + 3) * sizeof(*old_rl)) > rlsize) {
-			runlist_element *rl2;
-
-			rl2 = ntfs_malloc_nofs(rlsize + (int)PAGE_SIZE);
-			if (unlikely(!rl2)) {
-				ntfs_free(rl);
-				return ERR_PTR(-ENOMEM);
-			}
-			memcpy(rl2, rl, rlsize);
-			ntfs_free(rl);
-			rl = rl2;
-			rlsize += PAGE_SIZE;
-		}
-		/* Enter the current vcn into the current runlist element. */
-		rl[rlpos].vcn = vcn;
-		/*
-		 * Get the change in vcn, i.e. the run length in clusters.
-		 * Doing it this way ensures that we signextend negative values.
-		 * A negative run length doesn't make any sense, but hey, I
-		 * didn't make up the NTFS specs and Windows NT4 treats the run
-		 * length as a signed value so that's how it is...
-		 */
-		b = *buf & 0xf;
-		if (b) {
-			if (unlikely(buf + b > attr_end))
-				goto io_error;
-			for (deltaxcn = (s8)buf[b--]; b; b--)
-				deltaxcn = (deltaxcn << 8) + buf[b];
-		} else { /* The length entry is compulsory. */
-			ntfs_error(vol->sb, "Missing length entry in mapping "
-					"pairs array.");
-			deltaxcn = (s64)-1;
-		}
-		/*
-		 * Assume a negative length to indicate data corruption and
-		 * hence clean-up and return NULL.
-		 */
-		if (unlikely(deltaxcn < 0)) {
-			ntfs_error(vol->sb, "Invalid length in mapping pairs "
-					"array.");
-			goto err_out;
-		}
-		/*
-		 * Enter the current run length into the current runlist
-		 * element.
-		 */
-		rl[rlpos].length = deltaxcn;
-		/* Increment the current vcn by the current run length. */
-		vcn += deltaxcn;
-		/*
-		 * There might be no lcn change at all, as is the case for
-		 * sparse clusters on NTFS 3.0+, in which case we set the lcn
-		 * to LCN_HOLE.
-		 */
-		if (!(*buf & 0xf0))
-			rl[rlpos].lcn = LCN_HOLE;
-		else {
-			/* Get the lcn change which really can be negative. */
-			u8 b2 = *buf & 0xf;
-			b = b2 + ((*buf >> 4) & 0xf);
-			if (buf + b > attr_end)
-				goto io_error;
-			for (deltaxcn = (s8)buf[b--]; b > b2; b--)
-				deltaxcn = (deltaxcn << 8) + buf[b];
-			/* Change the current lcn to its new value. */
-			lcn += deltaxcn;
-#ifdef DEBUG
-			/*
-			 * On NTFS 1.2-, apparently can have lcn == -1 to
-			 * indicate a hole. But we haven't verified ourselves
-			 * whether it is really the lcn or the deltaxcn that is
-			 * -1. So if either is found give us a message so we
-			 * can investigate it further!
-			 */
-			if (vol->major_ver < 3) {
-				if (unlikely(deltaxcn == (LCN)-1))
-					ntfs_error(vol->sb, "lcn delta == -1");
-				if (unlikely(lcn == (LCN)-1))
-					ntfs_error(vol->sb, "lcn == -1");
-			}
-#endif
-			/* Check lcn is not below -1. */
-			if (unlikely(lcn < (LCN)-1)) {
-				ntfs_error(vol->sb, "Invalid LCN < -1 in "
-						"mapping pairs array.");
-				goto err_out;
-			}
-			/* Enter the current lcn into the runlist element. */
-			rl[rlpos].lcn = lcn;
-		}
-		/* Get to the next runlist element. */
-		rlpos++;
-		/* Increment the buffer position to the next mapping pair. */
-		buf += (*buf & 0xf) + ((*buf >> 4) & 0xf) + 1;
-	}
-	if (unlikely(buf >= attr_end))
-		goto io_error;
-	/*
-	 * If there is a highest_vcn specified, it must be equal to the final
-	 * vcn in the runlist - 1, or something has gone badly wrong.
-	 */
-	deltaxcn = sle64_to_cpu(attr->data.non_resident.highest_vcn);
-	if (unlikely(deltaxcn && vcn - 1 != deltaxcn)) {
-mpa_err:
-		ntfs_error(vol->sb, "Corrupt mapping pairs array in "
-				"non-resident attribute.");
-		goto err_out;
-	}
-	/* Setup not mapped runlist element if this is the base extent. */
-	if (!attr->data.non_resident.lowest_vcn) {
-		VCN max_cluster;
-
-		max_cluster = ((sle64_to_cpu(
-				attr->data.non_resident.allocated_size) +
-				vol->cluster_size - 1) >>
-				vol->cluster_size_bits) - 1;
-		/*
-		 * A highest_vcn of zero means this is a single extent
-		 * attribute so simply terminate the runlist with LCN_ENOENT).
-		 */
-		if (deltaxcn) {
-			/*
-			 * If there is a difference between the highest_vcn and
-			 * the highest cluster, the runlist is either corrupt
-			 * or, more likely, there are more extents following
-			 * this one.
-			 */
-			if (deltaxcn < max_cluster) {
-				ntfs_debug("More extents to follow; deltaxcn "
-						"= 0x%llx, max_cluster = "
-						"0x%llx",
-						(unsigned long long)deltaxcn,
-						(unsigned long long)
-						max_cluster);
-				rl[rlpos].vcn = vcn;
-				vcn += rl[rlpos].length = max_cluster -
-						deltaxcn;
-				rl[rlpos].lcn = LCN_RL_NOT_MAPPED;
-				rlpos++;
-			} else if (unlikely(deltaxcn > max_cluster)) {
-				ntfs_error(vol->sb, "Corrupt attribute.  "
-						"deltaxcn = 0x%llx, "
-						"max_cluster = 0x%llx",
-						(unsigned long long)deltaxcn,
-						(unsigned long long)
-						max_cluster);
-				goto mpa_err;
-			}
-		}
-		rl[rlpos].lcn = LCN_ENOENT;
-	} else /* Not the base extent. There may be more extents to follow. */
-		rl[rlpos].lcn = LCN_RL_NOT_MAPPED;
-
-	/* Setup terminating runlist element. */
-	rl[rlpos].vcn = vcn;
-	rl[rlpos].length = (s64)0;
-	/* If no existing runlist was specified, we are done. */
-	if (!old_rl) {
-		ntfs_debug("Mapping pairs array successfully decompressed:");
-		ntfs_debug_dump_runlist(rl);
-		return rl;
-	}
-	/* Now combine the new and old runlists checking for overlaps. */
-	old_rl = ntfs_runlists_merge(old_rl, rl);
-	if (!IS_ERR(old_rl))
-		return old_rl;
-	ntfs_free(rl);
-	ntfs_error(vol->sb, "Failed to merge runlists.");
-	return old_rl;
-io_error:
-	ntfs_error(vol->sb, "Corrupt attribute.");
-err_out:
-	ntfs_free(rl);
-	return ERR_PTR(-EIO);
-}
-
-/**
- * ntfs_rl_vcn_to_lcn - convert a vcn into a lcn given a runlist
- * @rl:		runlist to use for conversion
- * @vcn:	vcn to convert
- *
- * Convert the virtual cluster number @vcn of an attribute into a logical
- * cluster number (lcn) of a device using the runlist @rl to map vcns to their
- * corresponding lcns.
- *
- * It is up to the caller to serialize access to the runlist @rl.
- *
- * Since lcns must be >= 0, we use negative return codes with special meaning:
- *
- * Return code		Meaning / Description
- * ==================================================
- *  LCN_HOLE		Hole / not allocated on disk.
- *  LCN_RL_NOT_MAPPED	This is part of the runlist which has not been
- *			inserted into the runlist yet.
- *  LCN_ENOENT		There is no such vcn in the attribute.
- *
- * Locking: - The caller must have locked the runlist (for reading or writing).
- *	    - This function does not touch the lock, nor does it modify the
- *	      runlist.
- */
-LCN ntfs_rl_vcn_to_lcn(const runlist_element *rl, const VCN vcn)
-{
-	int i;
-
-	BUG_ON(vcn < 0);
-	/*
-	 * If rl is NULL, assume that we have found an unmapped runlist. The
-	 * caller can then attempt to map it and fail appropriately if
-	 * necessary.
-	 */
-	if (unlikely(!rl))
-		return LCN_RL_NOT_MAPPED;
-
-	/* Catch out of lower bounds vcn. */
-	if (unlikely(vcn < rl[0].vcn))
-		return LCN_ENOENT;
-
-	for (i = 0; likely(rl[i].length); i++) {
-		if (unlikely(vcn < rl[i+1].vcn)) {
-			if (likely(rl[i].lcn >= (LCN)0))
-				return rl[i].lcn + (vcn - rl[i].vcn);
-			return rl[i].lcn;
-		}
-	}
-	/*
-	 * The terminator element is setup to the correct value, i.e. one of
-	 * LCN_HOLE, LCN_RL_NOT_MAPPED, or LCN_ENOENT.
-	 */
-	if (likely(rl[i].lcn < (LCN)0))
-		return rl[i].lcn;
-	/* Just in case... We could replace this with BUG() some day. */
-	return LCN_ENOENT;
-}
-
-#ifdef NTFS_RW
-
-/**
- * ntfs_rl_find_vcn_nolock - find a vcn in a runlist
- * @rl:		runlist to search
- * @vcn:	vcn to find
- *
- * Find the virtual cluster number @vcn in the runlist @rl and return the
- * address of the runlist element containing the @vcn on success.
- *
- * Return NULL if @rl is NULL or @vcn is in an unmapped part/out of bounds of
- * the runlist.
- *
- * Locking: The runlist must be locked on entry.
- */
-runlist_element *ntfs_rl_find_vcn_nolock(runlist_element *rl, const VCN vcn)
-{
-	BUG_ON(vcn < 0);
-	if (unlikely(!rl || vcn < rl[0].vcn))
-		return NULL;
-	while (likely(rl->length)) {
-		if (unlikely(vcn < rl[1].vcn)) {
-			if (likely(rl->lcn >= LCN_HOLE))
-				return rl;
-			return NULL;
-		}
-		rl++;
-	}
-	if (likely(rl->lcn == LCN_ENOENT))
-		return rl;
-	return NULL;
-}
-
-/**
- * ntfs_get_nr_significant_bytes - get number of bytes needed to store a number
- * @n:		number for which to get the number of bytes for
- *
- * Return the number of bytes required to store @n unambiguously as
- * a signed number.
- *
- * This is used in the context of the mapping pairs array to determine how
- * many bytes will be needed in the array to store a given logical cluster
- * number (lcn) or a specific run length.
- *
- * Return the number of bytes written.  This function cannot fail.
- */
-static inline int ntfs_get_nr_significant_bytes(const s64 n)
-{
-	s64 l = n;
-	int i;
-	s8 j;
-
-	i = 0;
-	do {
-		l >>= 8;
-		i++;
-	} while (l != 0 && l != -1);
-	j = (n >> 8 * (i - 1)) & 0xff;
-	/* If the sign bit is wrong, we need an extra byte. */
-	if ((n < 0 && j >= 0) || (n > 0 && j < 0))
-		i++;
-	return i;
-}
-
-/**
- * ntfs_get_size_for_mapping_pairs - get bytes needed for mapping pairs array
- * @vol:	ntfs volume (needed for the ntfs version)
- * @rl:		locked runlist to determine the size of the mapping pairs of
- * @first_vcn:	first vcn which to include in the mapping pairs array
- * @last_vcn:	last vcn which to include in the mapping pairs array
- *
- * Walk the locked runlist @rl and calculate the size in bytes of the mapping
- * pairs array corresponding to the runlist @rl, starting at vcn @first_vcn and
- * finishing with vcn @last_vcn.
- *
- * A @last_vcn of -1 means end of runlist and in that case the size of the
- * mapping pairs array corresponding to the runlist starting at vcn @first_vcn
- * and finishing at the end of the runlist is determined.
- *
- * This for example allows us to allocate a buffer of the right size when
- * building the mapping pairs array.
- *
- * If @rl is NULL, just return 1 (for the single terminator byte).
- *
- * Return the calculated size in bytes on success.  On error, return -errno.
- * The following error codes are defined:
- *	-EINVAL	- Run list contains unmapped elements.  Make sure to only pass
- *		  fully mapped runlists to this function.
- *	-EIO	- The runlist is corrupt.
- *
- * Locking: @rl must be locked on entry (either for reading or writing), it
- *	    remains locked throughout, and is left locked upon return.
- */
-int ntfs_get_size_for_mapping_pairs(const ntfs_volume *vol,
-		const runlist_element *rl, const VCN first_vcn,
-		const VCN last_vcn)
-{
-	LCN prev_lcn;
-	int rls;
-	bool the_end = false;
-
-	BUG_ON(first_vcn < 0);
-	BUG_ON(last_vcn < -1);
-	BUG_ON(last_vcn >= 0 && first_vcn > last_vcn);
-	if (!rl) {
-		BUG_ON(first_vcn);
-		BUG_ON(last_vcn > 0);
-		return 1;
-	}
-	/* Skip to runlist element containing @first_vcn. */
-	while (rl->length && first_vcn >= rl[1].vcn)
-		rl++;
-	if (unlikely((!rl->length && first_vcn > rl->vcn) ||
-			first_vcn < rl->vcn))
-		return -EINVAL;
-	prev_lcn = 0;
-	/* Always need the termining zero byte. */
-	rls = 1;
-	/* Do the first partial run if present. */
-	if (first_vcn > rl->vcn) {
-		s64 delta, length = rl->length;
-
-		/* We know rl->length != 0 already. */
-		if (unlikely(length < 0 || rl->lcn < LCN_HOLE))
-			goto err_out;
-		/*
-		 * If @stop_vcn is given and finishes inside this run, cap the
-		 * run length.
-		 */
-		if (unlikely(last_vcn >= 0 && rl[1].vcn > last_vcn)) {
-			s64 s1 = last_vcn + 1;
-			if (unlikely(rl[1].vcn > s1))
-				length = s1 - rl->vcn;
-			the_end = true;
-		}
-		delta = first_vcn - rl->vcn;
-		/* Header byte + length. */
-		rls += 1 + ntfs_get_nr_significant_bytes(length - delta);
-		/*
-		 * If the logical cluster number (lcn) denotes a hole and we
-		 * are on NTFS 3.0+, we don't store it at all, i.e. we need
-		 * zero space.  On earlier NTFS versions we just store the lcn.
-		 * Note: this assumes that on NTFS 1.2-, holes are stored with
-		 * an lcn of -1 and not a delta_lcn of -1 (unless both are -1).
-		 */
-		if (likely(rl->lcn >= 0 || vol->major_ver < 3)) {
-			prev_lcn = rl->lcn;
-			if (likely(rl->lcn >= 0))
-				prev_lcn += delta;
-			/* Change in lcn. */
-			rls += ntfs_get_nr_significant_bytes(prev_lcn);
-		}
-		/* Go to next runlist element. */
-		rl++;
-	}
-	/* Do the full runs. */
-	for (; rl->length && !the_end; rl++) {
-		s64 length = rl->length;
-
-		if (unlikely(length < 0 || rl->lcn < LCN_HOLE))
-			goto err_out;
-		/*
-		 * If @stop_vcn is given and finishes inside this run, cap the
-		 * run length.
-		 */
-		if (unlikely(last_vcn >= 0 && rl[1].vcn > last_vcn)) {
-			s64 s1 = last_vcn + 1;
-			if (unlikely(rl[1].vcn > s1))
-				length = s1 - rl->vcn;
-			the_end = true;
-		}
-		/* Header byte + length. */
-		rls += 1 + ntfs_get_nr_significant_bytes(length);
-		/*
-		 * If the logical cluster number (lcn) denotes a hole and we
-		 * are on NTFS 3.0+, we don't store it at all, i.e. we need
-		 * zero space.  On earlier NTFS versions we just store the lcn.
-		 * Note: this assumes that on NTFS 1.2-, holes are stored with
-		 * an lcn of -1 and not a delta_lcn of -1 (unless both are -1).
-		 */
-		if (likely(rl->lcn >= 0 || vol->major_ver < 3)) {
-			/* Change in lcn. */
-			rls += ntfs_get_nr_significant_bytes(rl->lcn -
-					prev_lcn);
-			prev_lcn = rl->lcn;
-		}
-	}
-	return rls;
-err_out:
-	if (rl->lcn == LCN_RL_NOT_MAPPED)
-		rls = -EINVAL;
-	else
-		rls = -EIO;
-	return rls;
-}
-
-/**
- * ntfs_write_significant_bytes - write the significant bytes of a number
- * @dst:	destination buffer to write to
- * @dst_max:	pointer to last byte of destination buffer for bounds checking
- * @n:		number whose significant bytes to write
- *
- * Store in @dst, the minimum bytes of the number @n which are required to
- * identify @n unambiguously as a signed number, taking care not to exceed
- * @dest_max, the maximum position within @dst to which we are allowed to
- * write.
- *
- * This is used when building the mapping pairs array of a runlist to compress
- * a given logical cluster number (lcn) or a specific run length to the minimum
- * size possible.
- *
- * Return the number of bytes written on success.  On error, i.e. the
- * destination buffer @dst is too small, return -ENOSPC.
- */
-static inline int ntfs_write_significant_bytes(s8 *dst, const s8 *dst_max,
-		const s64 n)
-{
-	s64 l = n;
-	int i;
-	s8 j;
-
-	i = 0;
-	do {
-		if (unlikely(dst > dst_max))
-			goto err_out;
-		*dst++ = l & 0xffll;
-		l >>= 8;
-		i++;
-	} while (l != 0 && l != -1);
-	j = (n >> 8 * (i - 1)) & 0xff;
-	/* If the sign bit is wrong, we need an extra byte. */
-	if (n < 0 && j >= 0) {
-		if (unlikely(dst > dst_max))
-			goto err_out;
-		i++;
-		*dst = (s8)-1;
-	} else if (n > 0 && j < 0) {
-		if (unlikely(dst > dst_max))
-			goto err_out;
-		i++;
-		*dst = (s8)0;
-	}
-	return i;
-err_out:
-	return -ENOSPC;
-}
-
-/**
- * ntfs_mapping_pairs_build - build the mapping pairs array from a runlist
- * @vol:	ntfs volume (needed for the ntfs version)
- * @dst:	destination buffer to which to write the mapping pairs array
- * @dst_len:	size of destination buffer @dst in bytes
- * @rl:		locked runlist for which to build the mapping pairs array
- * @first_vcn:	first vcn which to include in the mapping pairs array
- * @last_vcn:	last vcn which to include in the mapping pairs array
- * @stop_vcn:	first vcn outside destination buffer on success or -ENOSPC
- *
- * Create the mapping pairs array from the locked runlist @rl, starting at vcn
- * @first_vcn and finishing with vcn @last_vcn and save the array in @dst.
- * @dst_len is the size of @dst in bytes and it should be at least equal to the
- * value obtained by calling ntfs_get_size_for_mapping_pairs().
- *
- * A @last_vcn of -1 means end of runlist and in that case the mapping pairs
- * array corresponding to the runlist starting at vcn @first_vcn and finishing
- * at the end of the runlist is created.
- *
- * If @rl is NULL, just write a single terminator byte to @dst.
- *
- * On success or -ENOSPC error, if @stop_vcn is not NULL, *@stop_vcn is set to
- * the first vcn outside the destination buffer.  Note that on error, @dst has
- * been filled with all the mapping pairs that will fit, thus it can be treated
- * as partial success, in that a new attribute extent needs to be created or
- * the next extent has to be used and the mapping pairs build has to be
- * continued with @first_vcn set to *@stop_vcn.
- *
- * Return 0 on success and -errno on error.  The following error codes are
- * defined:
- *	-EINVAL	- Run list contains unmapped elements.  Make sure to only pass
- *		  fully mapped runlists to this function.
- *	-EIO	- The runlist is corrupt.
- *	-ENOSPC	- The destination buffer is too small.
- *
- * Locking: @rl must be locked on entry (either for reading or writing), it
- *	    remains locked throughout, and is left locked upon return.
- */
-int ntfs_mapping_pairs_build(const ntfs_volume *vol, s8 *dst,
-		const int dst_len, const runlist_element *rl,
-		const VCN first_vcn, const VCN last_vcn, VCN *const stop_vcn)
-{
-	LCN prev_lcn;
-	s8 *dst_max, *dst_next;
-	int err = -ENOSPC;
-	bool the_end = false;
-	s8 len_len, lcn_len;
-
-	BUG_ON(first_vcn < 0);
-	BUG_ON(last_vcn < -1);
-	BUG_ON(last_vcn >= 0 && first_vcn > last_vcn);
-	BUG_ON(dst_len < 1);
-	if (!rl) {
-		BUG_ON(first_vcn);
-		BUG_ON(last_vcn > 0);
-		if (stop_vcn)
-			*stop_vcn = 0;
-		/* Terminator byte. */
-		*dst = 0;
-		return 0;
-	}
-	/* Skip to runlist element containing @first_vcn. */
-	while (rl->length && first_vcn >= rl[1].vcn)
-		rl++;
-	if (unlikely((!rl->length && first_vcn > rl->vcn) ||
-			first_vcn < rl->vcn))
-		return -EINVAL;
-	/*
-	 * @dst_max is used for bounds checking in
-	 * ntfs_write_significant_bytes().
-	 */
-	dst_max = dst + dst_len - 1;
-	prev_lcn = 0;
-	/* Do the first partial run if present. */
-	if (first_vcn > rl->vcn) {
-		s64 delta, length = rl->length;
-
-		/* We know rl->length != 0 already. */
-		if (unlikely(length < 0 || rl->lcn < LCN_HOLE))
-			goto err_out;
-		/*
-		 * If @stop_vcn is given and finishes inside this run, cap the
-		 * run length.
-		 */
-		if (unlikely(last_vcn >= 0 && rl[1].vcn > last_vcn)) {
-			s64 s1 = last_vcn + 1;
-			if (unlikely(rl[1].vcn > s1))
-				length = s1 - rl->vcn;
-			the_end = true;
-		}
-		delta = first_vcn - rl->vcn;
-		/* Write length. */
-		len_len = ntfs_write_significant_bytes(dst + 1, dst_max,
-				length - delta);
-		if (unlikely(len_len < 0))
-			goto size_err;
-		/*
-		 * If the logical cluster number (lcn) denotes a hole and we
-		 * are on NTFS 3.0+, we don't store it at all, i.e. we need
-		 * zero space.  On earlier NTFS versions we just write the lcn
-		 * change.  FIXME: Do we need to write the lcn change or just
-		 * the lcn in that case?  Not sure as I have never seen this
-		 * case on NT4. - We assume that we just need to write the lcn
-		 * change until someone tells us otherwise... (AIA)
-		 */
-		if (likely(rl->lcn >= 0 || vol->major_ver < 3)) {
-			prev_lcn = rl->lcn;
-			if (likely(rl->lcn >= 0))
-				prev_lcn += delta;
-			/* Write change in lcn. */
-			lcn_len = ntfs_write_significant_bytes(dst + 1 +
-					len_len, dst_max, prev_lcn);
-			if (unlikely(lcn_len < 0))
-				goto size_err;
-		} else
-			lcn_len = 0;
-		dst_next = dst + len_len + lcn_len + 1;
-		if (unlikely(dst_next > dst_max))
-			goto size_err;
-		/* Update header byte. */
-		*dst = lcn_len << 4 | len_len;
-		/* Position at next mapping pairs array element. */
-		dst = dst_next;
-		/* Go to next runlist element. */
-		rl++;
-	}
-	/* Do the full runs. */
-	for (; rl->length && !the_end; rl++) {
-		s64 length = rl->length;
-
-		if (unlikely(length < 0 || rl->lcn < LCN_HOLE))
-			goto err_out;
-		/*
-		 * If @stop_vcn is given and finishes inside this run, cap the
-		 * run length.
-		 */
-		if (unlikely(last_vcn >= 0 && rl[1].vcn > last_vcn)) {
-			s64 s1 = last_vcn + 1;
-			if (unlikely(rl[1].vcn > s1))
-				length = s1 - rl->vcn;
-			the_end = true;
-		}
-		/* Write length. */
-		len_len = ntfs_write_significant_bytes(dst + 1, dst_max,
-				length);
-		if (unlikely(len_len < 0))
-			goto size_err;
-		/*
-		 * If the logical cluster number (lcn) denotes a hole and we
-		 * are on NTFS 3.0+, we don't store it at all, i.e. we need
-		 * zero space.  On earlier NTFS versions we just write the lcn
-		 * change.  FIXME: Do we need to write the lcn change or just
-		 * the lcn in that case?  Not sure as I have never seen this
-		 * case on NT4. - We assume that we just need to write the lcn
-		 * change until someone tells us otherwise... (AIA)
-		 */
-		if (likely(rl->lcn >= 0 || vol->major_ver < 3)) {
-			/* Write change in lcn. */
-			lcn_len = ntfs_write_significant_bytes(dst + 1 +
-					len_len, dst_max, rl->lcn - prev_lcn);
-			if (unlikely(lcn_len < 0))
-				goto size_err;
-			prev_lcn = rl->lcn;
-		} else
-			lcn_len = 0;
-		dst_next = dst + len_len + lcn_len + 1;
-		if (unlikely(dst_next > dst_max))
-			goto size_err;
-		/* Update header byte. */
-		*dst = lcn_len << 4 | len_len;
-		/* Position at next mapping pairs array element. */
-		dst = dst_next;
-	}
-	/* Success. */
-	err = 0;
-size_err:
-	/* Set stop vcn. */
-	if (stop_vcn)
-		*stop_vcn = rl->vcn;
-	/* Add terminator byte. */
-	*dst = 0;
-	return err;
-err_out:
-	if (rl->lcn == LCN_RL_NOT_MAPPED)
-		err = -EINVAL;
-	else
-		err = -EIO;
-	return err;
-}
-
-/**
- * ntfs_rl_truncate_nolock - truncate a runlist starting at a specified vcn
- * @vol:	ntfs volume (needed for error output)
- * @runlist:	runlist to truncate
- * @new_length:	the new length of the runlist in VCNs
- *
- * Truncate the runlist described by @runlist as well as the memory buffer
- * holding the runlist elements to a length of @new_length VCNs.
- *
- * If @new_length lies within the runlist, the runlist elements with VCNs of
- * @new_length and above are discarded.  As a special case if @new_length is
- * zero, the runlist is discarded and set to NULL.
- *
- * If @new_length lies beyond the runlist, a sparse runlist element is added to
- * the end of the runlist @runlist or if the last runlist element is a sparse
- * one already, this is extended.
- *
- * Note, no checking is done for unmapped runlist elements.  It is assumed that
- * the caller has mapped any elements that need to be mapped already.
- *
- * Return 0 on success and -errno on error.
- *
- * Locking: The caller must hold @runlist->lock for writing.
- */
-int ntfs_rl_truncate_nolock(const ntfs_volume *vol, runlist *const runlist,
-		const s64 new_length)
-{
-	runlist_element *rl;
-	int old_size;
-
-	ntfs_debug("Entering for new_length 0x%llx.", (long long)new_length);
-	BUG_ON(!runlist);
-	BUG_ON(new_length < 0);
-	rl = runlist->rl;
-	if (!new_length) {
-		ntfs_debug("Freeing runlist.");
-		runlist->rl = NULL;
-		if (rl)
-			ntfs_free(rl);
-		return 0;
-	}
-	if (unlikely(!rl)) {
-		/*
-		 * Create a runlist consisting of a sparse runlist element of
-		 * length @new_length followed by a terminator runlist element.
-		 */
-		rl = ntfs_malloc_nofs(PAGE_SIZE);
-		if (unlikely(!rl)) {
-			ntfs_error(vol->sb, "Not enough memory to allocate "
-					"runlist element buffer.");
-			return -ENOMEM;
-		}
-		runlist->rl = rl;
-		rl[1].length = rl->vcn = 0;
-		rl->lcn = LCN_HOLE;
-		rl[1].vcn = rl->length = new_length;
-		rl[1].lcn = LCN_ENOENT;
-		return 0;
-	}
-	BUG_ON(new_length < rl->vcn);
-	/* Find @new_length in the runlist. */
-	while (likely(rl->length && new_length >= rl[1].vcn))
-		rl++;
-	/*
-	 * If not at the end of the runlist we need to shrink it.
-	 * If at the end of the runlist we need to expand it.
-	 */
-	if (rl->length) {
-		runlist_element *trl;
-		bool is_end;
-
-		ntfs_debug("Shrinking runlist.");
-		/* Determine the runlist size. */
-		trl = rl + 1;
-		while (likely(trl->length))
-			trl++;
-		old_size = trl - runlist->rl + 1;
-		/* Truncate the run. */
-		rl->length = new_length - rl->vcn;
-		/*
-		 * If a run was partially truncated, make the following runlist
-		 * element a terminator.
-		 */
-		is_end = false;
-		if (rl->length) {
-			rl++;
-			if (!rl->length)
-				is_end = true;
-			rl->vcn = new_length;
-			rl->length = 0;
-		}
-		rl->lcn = LCN_ENOENT;
-		/* Reallocate memory if necessary. */
-		if (!is_end) {
-			int new_size = rl - runlist->rl + 1;
-			rl = ntfs_rl_realloc(runlist->rl, old_size, new_size);
-			if (IS_ERR(rl))
-				ntfs_warning(vol->sb, "Failed to shrink "
-						"runlist buffer.  This just "
-						"wastes a bit of memory "
-						"temporarily so we ignore it "
-						"and return success.");
-			else
-				runlist->rl = rl;
-		}
-	} else if (likely(/* !rl->length && */ new_length > rl->vcn)) {
-		ntfs_debug("Expanding runlist.");
-		/*
-		 * If there is a previous runlist element and it is a sparse
-		 * one, extend it.  Otherwise need to add a new, sparse runlist
-		 * element.
-		 */
-		if ((rl > runlist->rl) && ((rl - 1)->lcn == LCN_HOLE))
-			(rl - 1)->length = new_length - (rl - 1)->vcn;
-		else {
-			/* Determine the runlist size. */
-			old_size = rl - runlist->rl + 1;
-			/* Reallocate memory if necessary. */
-			rl = ntfs_rl_realloc(runlist->rl, old_size,
-					old_size + 1);
-			if (IS_ERR(rl)) {
-				ntfs_error(vol->sb, "Failed to expand runlist "
-						"buffer, aborting.");
-				return PTR_ERR(rl);
-			}
-			runlist->rl = rl;
-			/*
-			 * Set @rl to the same runlist element in the new
-			 * runlist as before in the old runlist.
-			 */
-			rl += old_size - 1;
-			/* Add a new, sparse runlist element. */
-			rl->lcn = LCN_HOLE;
-			rl->length = new_length - rl->vcn;
-			/* Add a new terminator runlist element. */
-			rl++;
-			rl->length = 0;
-		}
-		rl->vcn = new_length;
-		rl->lcn = LCN_ENOENT;
-	} else /* if (unlikely(!rl->length && new_length == rl->vcn)) */ {
-		/* Runlist already has same size as requested. */
-		rl->lcn = LCN_ENOENT;
-	}
-	ntfs_debug("Done.");
-	return 0;
-}
-
-/**
- * ntfs_rl_punch_nolock - punch a hole into a runlist
- * @vol:	ntfs volume (needed for error output)
- * @runlist:	runlist to punch a hole into
- * @start:	starting VCN of the hole to be created
- * @length:	size of the hole to be created in units of clusters
- *
- * Punch a hole into the runlist @runlist starting at VCN @start and of size
- * @length clusters.
- *
- * Return 0 on success and -errno on error, in which case @runlist has not been
- * modified.
- *
- * If @start and/or @start + @length are outside the runlist return error code
- * -ENOENT.
- *
- * If the runlist contains unmapped or error elements between @start and @start
- * + @length return error code -EINVAL.
- *
- * Locking: The caller must hold @runlist->lock for writing.
- */
-int ntfs_rl_punch_nolock(const ntfs_volume *vol, runlist *const runlist,
-		const VCN start, const s64 length)
-{
-	const VCN end = start + length;
-	s64 delta;
-	runlist_element *rl, *rl_end, *rl_real_end, *trl;
-	int old_size;
-	bool lcn_fixup = false;
-
-	ntfs_debug("Entering for start 0x%llx, length 0x%llx.",
-			(long long)start, (long long)length);
-	BUG_ON(!runlist);
-	BUG_ON(start < 0);
-	BUG_ON(length < 0);
-	BUG_ON(end < 0);
-	rl = runlist->rl;
-	if (unlikely(!rl)) {
-		if (likely(!start && !length))
-			return 0;
-		return -ENOENT;
-	}
-	/* Find @start in the runlist. */
-	while (likely(rl->length && start >= rl[1].vcn))
-		rl++;
-	rl_end = rl;
-	/* Find @end in the runlist. */
-	while (likely(rl_end->length && end >= rl_end[1].vcn)) {
-		/* Verify there are no unmapped or error elements. */
-		if (unlikely(rl_end->lcn < LCN_HOLE))
-			return -EINVAL;
-		rl_end++;
-	}
-	/* Check the last element. */
-	if (unlikely(rl_end->length && rl_end->lcn < LCN_HOLE))
-		return -EINVAL;
-	/* This covers @start being out of bounds, too. */
-	if (!rl_end->length && end > rl_end->vcn)
-		return -ENOENT;
-	if (!length)
-		return 0;
-	if (!rl->length)
-		return -ENOENT;
-	rl_real_end = rl_end;
-	/* Determine the runlist size. */
-	while (likely(rl_real_end->length))
-		rl_real_end++;
-	old_size = rl_real_end - runlist->rl + 1;
-	/* If @start is in a hole simply extend the hole. */
-	if (rl->lcn == LCN_HOLE) {
-		/*
-		 * If both @start and @end are in the same sparse run, we are
-		 * done.
-		 */
-		if (end <= rl[1].vcn) {
-			ntfs_debug("Done (requested hole is already sparse).");
-			return 0;
-		}
-extend_hole:
-		/* Extend the hole. */
-		rl->length = end - rl->vcn;
-		/* If @end is in a hole, merge it with the current one. */
-		if (rl_end->lcn == LCN_HOLE) {
-			rl_end++;
-			rl->length = rl_end->vcn - rl->vcn;
-		}
-		/* We have done the hole.  Now deal with the remaining tail. */
-		rl++;
-		/* Cut out all runlist elements up to @end. */
-		if (rl < rl_end)
-			memmove(rl, rl_end, (rl_real_end - rl_end + 1) *
-					sizeof(*rl));
-		/* Adjust the beginning of the tail if necessary. */
-		if (end > rl->vcn) {
-			delta = end - rl->vcn;
-			rl->vcn = end;
-			rl->length -= delta;
-			/* Only adjust the lcn if it is real. */
-			if (rl->lcn >= 0)
-				rl->lcn += delta;
-		}
-shrink_allocation:
-		/* Reallocate memory if the allocation changed. */
-		if (rl < rl_end) {
-			rl = ntfs_rl_realloc(runlist->rl, old_size,
-					old_size - (rl_end - rl));
-			if (IS_ERR(rl))
-				ntfs_warning(vol->sb, "Failed to shrink "
-						"runlist buffer.  This just "
-						"wastes a bit of memory "
-						"temporarily so we ignore it "
-						"and return success.");
-			else
-				runlist->rl = rl;
-		}
-		ntfs_debug("Done (extend hole).");
-		return 0;
-	}
-	/*
-	 * If @start is at the beginning of a run things are easier as there is
-	 * no need to split the first run.
-	 */
-	if (start == rl->vcn) {
-		/*
-		 * @start is at the beginning of a run.
-		 *
-		 * If the previous run is sparse, extend its hole.
-		 *
-		 * If @end is not in the same run, switch the run to be sparse
-		 * and extend the newly created hole.
-		 *
-		 * Thus both of these cases reduce the problem to the above
-		 * case of "@start is in a hole".
-		 */
-		if (rl > runlist->rl && (rl - 1)->lcn == LCN_HOLE) {
-			rl--;
-			goto extend_hole;
-		}
-		if (end >= rl[1].vcn) {
-			rl->lcn = LCN_HOLE;
-			goto extend_hole;
-		}
-		/*
-		 * The final case is when @end is in the same run as @start.
-		 * For this need to split the run into two.  One run for the
-		 * sparse region between the beginning of the old run, i.e.
-		 * @start, and @end and one for the remaining non-sparse
-		 * region, i.e. between @end and the end of the old run.
-		 */
-		trl = ntfs_rl_realloc(runlist->rl, old_size, old_size + 1);
-		if (IS_ERR(trl))
-			goto enomem_out;
-		old_size++;
-		if (runlist->rl != trl) {
-			rl = trl + (rl - runlist->rl);
-			rl_end = trl + (rl_end - runlist->rl);
-			rl_real_end = trl + (rl_real_end - runlist->rl);
-			runlist->rl = trl;
-		}
-split_end:
-		/* Shift all the runs up by one. */
-		memmove(rl + 1, rl, (rl_real_end - rl + 1) * sizeof(*rl));
-		/* Finally, setup the two split runs. */
-		rl->lcn = LCN_HOLE;
-		rl->length = length;
-		rl++;
-		rl->vcn += length;
-		/* Only adjust the lcn if it is real. */
-		if (rl->lcn >= 0 || lcn_fixup)
-			rl->lcn += length;
-		rl->length -= length;
-		ntfs_debug("Done (split one).");
-		return 0;
-	}
-	/*
-	 * @start is neither in a hole nor at the beginning of a run.
-	 *
-	 * If @end is in a hole, things are easier as simply truncating the run
-	 * @start is in to end at @start - 1, deleting all runs after that up
-	 * to @end, and finally extending the beginning of the run @end is in
-	 * to be @start is all that is needed.
-	 */
-	if (rl_end->lcn == LCN_HOLE) {
-		/* Truncate the run containing @start. */
-		rl->length = start - rl->vcn;
-		rl++;
-		/* Cut out all runlist elements up to @end. */
-		if (rl < rl_end)
-			memmove(rl, rl_end, (rl_real_end - rl_end + 1) *
-					sizeof(*rl));
-		/* Extend the beginning of the run @end is in to be @start. */
-		rl->vcn = start;
-		rl->length = rl[1].vcn - start;
-		goto shrink_allocation;
-	}
-	/* 
-	 * If @end is not in a hole there are still two cases to distinguish.
-	 * Either @end is or is not in the same run as @start.
-	 *
-	 * The second case is easier as it can be reduced to an already solved
-	 * problem by truncating the run @start is in to end at @start - 1.
-	 * Then, if @end is in the next run need to split the run into a sparse
-	 * run followed by a non-sparse run (already covered above) and if @end
-	 * is not in the next run switching it to be sparse, again reduces the
-	 * problem to the already covered case of "@start is in a hole".
-	 */
-	if (end >= rl[1].vcn) {
-		/*
-		 * If @end is not in the next run, reduce the problem to the
-		 * case of "@start is in a hole".
-		 */
-		if (rl[1].length && end >= rl[2].vcn) {
-			/* Truncate the run containing @start. */
-			rl->length = start - rl->vcn;
-			rl++;
-			rl->vcn = start;
-			rl->lcn = LCN_HOLE;
-			goto extend_hole;
-		}
-		trl = ntfs_rl_realloc(runlist->rl, old_size, old_size + 1);
-		if (IS_ERR(trl))
-			goto enomem_out;
-		old_size++;
-		if (runlist->rl != trl) {
-			rl = trl + (rl - runlist->rl);
-			rl_end = trl + (rl_end - runlist->rl);
-			rl_real_end = trl + (rl_real_end - runlist->rl);
-			runlist->rl = trl;
-		}
-		/* Truncate the run containing @start. */
-		rl->length = start - rl->vcn;
-		rl++;
-		/*
-		 * @end is in the next run, reduce the problem to the case
-		 * where "@start is at the beginning of a run and @end is in
-		 * the same run as @start".
-		 */
-		delta = rl->vcn - start;
-		rl->vcn = start;
-		if (rl->lcn >= 0) {
-			rl->lcn -= delta;
-			/* Need this in case the lcn just became negative. */
-			lcn_fixup = true;
-		}
-		rl->length += delta;
-		goto split_end;
-	}
-	/*
-	 * The first case from above, i.e. @end is in the same run as @start.
-	 * We need to split the run into three.  One run for the non-sparse
-	 * region between the beginning of the old run and @start, one for the
-	 * sparse region between @start and @end, and one for the remaining
-	 * non-sparse region, i.e. between @end and the end of the old run.
-	 */
-	trl = ntfs_rl_realloc(runlist->rl, old_size, old_size + 2);
-	if (IS_ERR(trl))
-		goto enomem_out;
-	old_size += 2;
-	if (runlist->rl != trl) {
-		rl = trl + (rl - runlist->rl);
-		rl_end = trl + (rl_end - runlist->rl);
-		rl_real_end = trl + (rl_real_end - runlist->rl);
-		runlist->rl = trl;
-	}
-	/* Shift all the runs up by two. */
-	memmove(rl + 2, rl, (rl_real_end - rl + 1) * sizeof(*rl));
-	/* Finally, setup the three split runs. */
-	rl->length = start - rl->vcn;
-	rl++;
-	rl->vcn = start;
-	rl->lcn = LCN_HOLE;
-	rl->length = length;
-	rl++;
-	delta = end - rl->vcn;
-	rl->vcn = end;
-	rl->lcn += delta;
-	rl->length -= delta;
-	ntfs_debug("Done (split both).");
-	return 0;
-enomem_out:
-	ntfs_error(vol->sb, "Not enough memory to extend runlist buffer.");
-	return -ENOMEM;
-}
-
-#endif /* NTFS_RW */
diff --git a/fs/ntfs/runlist.h b/fs/ntfs/runlist.h
deleted file mode 100644
index 38de0a375f59..000000000000
--- a/fs/ntfs/runlist.h
+++ /dev/null
@@ -1,88 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * runlist.h - Defines for runlist handling in NTFS Linux kernel driver.
- *	       Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2005 Anton Altaparmakov
- * Copyright (c) 2002 Richard Russon
- */
-
-#ifndef _LINUX_NTFS_RUNLIST_H
-#define _LINUX_NTFS_RUNLIST_H
-
-#include "types.h"
-#include "layout.h"
-#include "volume.h"
-
-/**
- * runlist_element - in memory vcn to lcn mapping array element
- * @vcn:	starting vcn of the current array element
- * @lcn:	starting lcn of the current array element
- * @length:	length in clusters of the current array element
- *
- * The last vcn (in fact the last vcn + 1) is reached when length == 0.
- *
- * When lcn == -1 this means that the count vcns starting at vcn are not
- * physically allocated (i.e. this is a hole / data is sparse).
- */
-typedef struct {	/* In memory vcn to lcn mapping structure element. */
-	VCN vcn;	/* vcn = Starting virtual cluster number. */
-	LCN lcn;	/* lcn = Starting logical cluster number. */
-	s64 length;	/* Run length in clusters. */
-} runlist_element;
-
-/**
- * runlist - in memory vcn to lcn mapping array including a read/write lock
- * @rl:		pointer to an array of runlist elements
- * @lock:	read/write spinlock for serializing access to @rl
- *
- */
-typedef struct {
-	runlist_element *rl;
-	struct rw_semaphore lock;
-} runlist;
-
-static inline void ntfs_init_runlist(runlist *rl)
-{
-	rl->rl = NULL;
-	init_rwsem(&rl->lock);
-}
-
-typedef enum {
-	LCN_HOLE		= -1,	/* Keep this as highest value or die! */
-	LCN_RL_NOT_MAPPED	= -2,
-	LCN_ENOENT		= -3,
-	LCN_ENOMEM		= -4,
-	LCN_EIO			= -5,
-} LCN_SPECIAL_VALUES;
-
-extern runlist_element *ntfs_runlists_merge(runlist_element *drl,
-		runlist_element *srl);
-
-extern runlist_element *ntfs_mapping_pairs_decompress(const ntfs_volume *vol,
-		const ATTR_RECORD *attr, runlist_element *old_rl);
-
-extern LCN ntfs_rl_vcn_to_lcn(const runlist_element *rl, const VCN vcn);
-
-#ifdef NTFS_RW
-
-extern runlist_element *ntfs_rl_find_vcn_nolock(runlist_element *rl,
-		const VCN vcn);
-
-extern int ntfs_get_size_for_mapping_pairs(const ntfs_volume *vol,
-		const runlist_element *rl, const VCN first_vcn,
-		const VCN last_vcn);
-
-extern int ntfs_mapping_pairs_build(const ntfs_volume *vol, s8 *dst,
-		const int dst_len, const runlist_element *rl,
-		const VCN first_vcn, const VCN last_vcn, VCN *const stop_vcn);
-
-extern int ntfs_rl_truncate_nolock(const ntfs_volume *vol,
-		runlist *const runlist, const s64 new_length);
-
-int ntfs_rl_punch_nolock(const ntfs_volume *vol, runlist *const runlist,
-		const VCN start, const s64 length);
-
-#endif /* NTFS_RW */
-
-#endif /* _LINUX_NTFS_RUNLIST_H */
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
deleted file mode 100644
index 56a7d5bd33e4..000000000000
--- a/fs/ntfs/super.c
+++ /dev/null
@@ -1,3202 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * super.c - NTFS kernel super block handling. Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2012 Anton Altaparmakov and Tuxera Inc.
- * Copyright (c) 2001,2002 Richard Russon
- */
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/stddef.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/spinlock.h>
-#include <linux/blkdev.h>	/* For bdev_logical_block_size(). */
-#include <linux/backing-dev.h>
-#include <linux/buffer_head.h>
-#include <linux/vfs.h>
-#include <linux/moduleparam.h>
-#include <linux/bitmap.h>
-
-#include "sysctl.h"
-#include "logfile.h"
-#include "quota.h"
-#include "usnjrnl.h"
-#include "dir.h"
-#include "debug.h"
-#include "index.h"
-#include "inode.h"
-#include "aops.h"
-#include "layout.h"
-#include "malloc.h"
-#include "ntfs.h"
-
-/* Number of mounted filesystems which have compression enabled. */
-static unsigned long ntfs_nr_compression_users;
-
-/* A global default upcase table and a corresponding reference count. */
-static ntfschar *default_upcase;
-static unsigned long ntfs_nr_upcase_users;
-
-/* Error constants/strings used in inode.c::ntfs_show_options(). */
-typedef enum {
-	/* One of these must be present, default is ON_ERRORS_CONTINUE. */
-	ON_ERRORS_PANIC			= 0x01,
-	ON_ERRORS_REMOUNT_RO		= 0x02,
-	ON_ERRORS_CONTINUE		= 0x04,
-	/* Optional, can be combined with any of the above. */
-	ON_ERRORS_RECOVER		= 0x10,
-} ON_ERRORS_ACTIONS;
-
-const option_t on_errors_arr[] = {
-	{ ON_ERRORS_PANIC,	"panic" },
-	{ ON_ERRORS_REMOUNT_RO,	"remount-ro", },
-	{ ON_ERRORS_CONTINUE,	"continue", },
-	{ ON_ERRORS_RECOVER,	"recover" },
-	{ 0,			NULL }
-};
-
-/**
- * simple_getbool - convert input string to a boolean value
- * @s: input string to convert
- * @setval: where to store the output boolean value
- *
- * Copied from old ntfs driver (which copied from vfat driver).
- *
- * "1", "yes", "true", or an empty string are converted to %true.
- * "0", "no", and "false" are converted to %false.
- *
- * Return: %1 if the string is converted or was empty and *setval contains it;
- *	   %0 if the string was not valid.
- */
-static int simple_getbool(char *s, bool *setval)
-{
-	if (s) {
-		if (!strcmp(s, "1") || !strcmp(s, "yes") || !strcmp(s, "true"))
-			*setval = true;
-		else if (!strcmp(s, "0") || !strcmp(s, "no") ||
-							!strcmp(s, "false"))
-			*setval = false;
-		else
-			return 0;
-	} else
-		*setval = true;
-	return 1;
-}
-
-/**
- * parse_options - parse the (re)mount options
- * @vol:	ntfs volume
- * @opt:	string containing the (re)mount options
- *
- * Parse the recognized options in @opt for the ntfs volume described by @vol.
- */
-static bool parse_options(ntfs_volume *vol, char *opt)
-{
-	char *p, *v, *ov;
-	static char *utf8 = "utf8";
-	int errors = 0, sloppy = 0;
-	kuid_t uid = INVALID_UID;
-	kgid_t gid = INVALID_GID;
-	umode_t fmask = (umode_t)-1, dmask = (umode_t)-1;
-	int mft_zone_multiplier = -1, on_errors = -1;
-	int show_sys_files = -1, case_sensitive = -1, disable_sparse = -1;
-	struct nls_table *nls_map = NULL, *old_nls;
-
-	/* I am lazy... (-8 */
-#define NTFS_GETOPT_WITH_DEFAULT(option, variable, default_value)	\
-	if (!strcmp(p, option)) {					\
-		if (!v || !*v)						\
-			variable = default_value;			\
-		else {							\
-			variable = simple_strtoul(ov = v, &v, 0);	\
-			if (*v)						\
-				goto needs_val;				\
-		}							\
-	}
-#define NTFS_GETOPT(option, variable)					\
-	if (!strcmp(p, option)) {					\
-		if (!v || !*v)						\
-			goto needs_arg;					\
-		variable = simple_strtoul(ov = v, &v, 0);		\
-		if (*v)							\
-			goto needs_val;					\
-	}
-#define NTFS_GETOPT_UID(option, variable)				\
-	if (!strcmp(p, option)) {					\
-		uid_t uid_value;					\
-		if (!v || !*v)						\
-			goto needs_arg;					\
-		uid_value = simple_strtoul(ov = v, &v, 0);		\
-		if (*v)							\
-			goto needs_val;					\
-		variable = make_kuid(current_user_ns(), uid_value);	\
-		if (!uid_valid(variable))				\
-			goto needs_val;					\
-	}
-#define NTFS_GETOPT_GID(option, variable)				\
-	if (!strcmp(p, option)) {					\
-		gid_t gid_value;					\
-		if (!v || !*v)						\
-			goto needs_arg;					\
-		gid_value = simple_strtoul(ov = v, &v, 0);		\
-		if (*v)							\
-			goto needs_val;					\
-		variable = make_kgid(current_user_ns(), gid_value);	\
-		if (!gid_valid(variable))				\
-			goto needs_val;					\
-	}
-#define NTFS_GETOPT_OCTAL(option, variable)				\
-	if (!strcmp(p, option)) {					\
-		if (!v || !*v)						\
-			goto needs_arg;					\
-		variable = simple_strtoul(ov = v, &v, 8);		\
-		if (*v)							\
-			goto needs_val;					\
-	}
-#define NTFS_GETOPT_BOOL(option, variable)				\
-	if (!strcmp(p, option)) {					\
-		bool val;						\
-		if (!simple_getbool(v, &val))				\
-			goto needs_bool;				\
-		variable = val;						\
-	}
-#define NTFS_GETOPT_OPTIONS_ARRAY(option, variable, opt_array)		\
-	if (!strcmp(p, option)) {					\
-		int _i;							\
-		if (!v || !*v)						\
-			goto needs_arg;					\
-		ov = v;							\
-		if (variable == -1)					\
-			variable = 0;					\
-		for (_i = 0; opt_array[_i].str && *opt_array[_i].str; _i++) \
-			if (!strcmp(opt_array[_i].str, v)) {		\
-				variable |= opt_array[_i].val;		\
-				break;					\
-			}						\
-		if (!opt_array[_i].str || !*opt_array[_i].str)		\
-			goto needs_val;					\
-	}
-	if (!opt || !*opt)
-		goto no_mount_options;
-	ntfs_debug("Entering with mount options string: %s", opt);
-	while ((p = strsep(&opt, ","))) {
-		if ((v = strchr(p, '=')))
-			*v++ = 0;
-		NTFS_GETOPT_UID("uid", uid)
-		else NTFS_GETOPT_GID("gid", gid)
-		else NTFS_GETOPT_OCTAL("umask", fmask = dmask)
-		else NTFS_GETOPT_OCTAL("fmask", fmask)
-		else NTFS_GETOPT_OCTAL("dmask", dmask)
-		else NTFS_GETOPT("mft_zone_multiplier", mft_zone_multiplier)
-		else NTFS_GETOPT_WITH_DEFAULT("sloppy", sloppy, true)
-		else NTFS_GETOPT_BOOL("show_sys_files", show_sys_files)
-		else NTFS_GETOPT_BOOL("case_sensitive", case_sensitive)
-		else NTFS_GETOPT_BOOL("disable_sparse", disable_sparse)
-		else NTFS_GETOPT_OPTIONS_ARRAY("errors", on_errors,
-				on_errors_arr)
-		else if (!strcmp(p, "posix") || !strcmp(p, "show_inodes"))
-			ntfs_warning(vol->sb, "Ignoring obsolete option %s.",
-					p);
-		else if (!strcmp(p, "nls") || !strcmp(p, "iocharset")) {
-			if (!strcmp(p, "iocharset"))
-				ntfs_warning(vol->sb, "Option iocharset is "
-						"deprecated. Please use "
-						"option nls=<charsetname> in "
-						"the future.");
-			if (!v || !*v)
-				goto needs_arg;
-use_utf8:
-			old_nls = nls_map;
-			nls_map = load_nls(v);
-			if (!nls_map) {
-				if (!old_nls) {
-					ntfs_error(vol->sb, "NLS character set "
-							"%s not found.", v);
-					return false;
-				}
-				ntfs_error(vol->sb, "NLS character set %s not "
-						"found. Using previous one %s.",
-						v, old_nls->charset);
-				nls_map = old_nls;
-			} else /* nls_map */ {
-				unload_nls(old_nls);
-			}
-		} else if (!strcmp(p, "utf8")) {
-			bool val = false;
-			ntfs_warning(vol->sb, "Option utf8 is no longer "
-				   "supported, using option nls=utf8. Please "
-				   "use option nls=utf8 in the future and "
-				   "make sure utf8 is compiled either as a "
-				   "module or into the kernel.");
-			if (!v || !*v)
-				val = true;
-			else if (!simple_getbool(v, &val))
-				goto needs_bool;
-			if (val) {
-				v = utf8;
-				goto use_utf8;
-			}
-		} else {
-			ntfs_error(vol->sb, "Unrecognized mount option %s.", p);
-			if (errors < INT_MAX)
-				errors++;
-		}
-#undef NTFS_GETOPT_OPTIONS_ARRAY
-#undef NTFS_GETOPT_BOOL
-#undef NTFS_GETOPT
-#undef NTFS_GETOPT_WITH_DEFAULT
-	}
-no_mount_options:
-	if (errors && !sloppy)
-		return false;
-	if (sloppy)
-		ntfs_warning(vol->sb, "Sloppy option given. Ignoring "
-				"unrecognized mount option(s) and continuing.");
-	/* Keep this first! */
-	if (on_errors != -1) {
-		if (!on_errors) {
-			ntfs_error(vol->sb, "Invalid errors option argument "
-					"or bug in options parser.");
-			return false;
-		}
-	}
-	if (nls_map) {
-		if (vol->nls_map && vol->nls_map != nls_map) {
-			ntfs_error(vol->sb, "Cannot change NLS character set "
-					"on remount.");
-			return false;
-		} /* else (!vol->nls_map) */
-		ntfs_debug("Using NLS character set %s.", nls_map->charset);
-		vol->nls_map = nls_map;
-	} else /* (!nls_map) */ {
-		if (!vol->nls_map) {
-			vol->nls_map = load_nls_default();
-			if (!vol->nls_map) {
-				ntfs_error(vol->sb, "Failed to load default "
-						"NLS character set.");
-				return false;
-			}
-			ntfs_debug("Using default NLS character set (%s).",
-					vol->nls_map->charset);
-		}
-	}
-	if (mft_zone_multiplier != -1) {
-		if (vol->mft_zone_multiplier && vol->mft_zone_multiplier !=
-				mft_zone_multiplier) {
-			ntfs_error(vol->sb, "Cannot change mft_zone_multiplier "
-					"on remount.");
-			return false;
-		}
-		if (mft_zone_multiplier < 1 || mft_zone_multiplier > 4) {
-			ntfs_error(vol->sb, "Invalid mft_zone_multiplier. "
-					"Using default value, i.e. 1.");
-			mft_zone_multiplier = 1;
-		}
-		vol->mft_zone_multiplier = mft_zone_multiplier;
-	}
-	if (!vol->mft_zone_multiplier)
-		vol->mft_zone_multiplier = 1;
-	if (on_errors != -1)
-		vol->on_errors = on_errors;
-	if (!vol->on_errors || vol->on_errors == ON_ERRORS_RECOVER)
-		vol->on_errors |= ON_ERRORS_CONTINUE;
-	if (uid_valid(uid))
-		vol->uid = uid;
-	if (gid_valid(gid))
-		vol->gid = gid;
-	if (fmask != (umode_t)-1)
-		vol->fmask = fmask;
-	if (dmask != (umode_t)-1)
-		vol->dmask = dmask;
-	if (show_sys_files != -1) {
-		if (show_sys_files)
-			NVolSetShowSystemFiles(vol);
-		else
-			NVolClearShowSystemFiles(vol);
-	}
-	if (case_sensitive != -1) {
-		if (case_sensitive)
-			NVolSetCaseSensitive(vol);
-		else
-			NVolClearCaseSensitive(vol);
-	}
-	if (disable_sparse != -1) {
-		if (disable_sparse)
-			NVolClearSparseEnabled(vol);
-		else {
-			if (!NVolSparseEnabled(vol) &&
-					vol->major_ver && vol->major_ver < 3)
-				ntfs_warning(vol->sb, "Not enabling sparse "
-						"support due to NTFS volume "
-						"version %i.%i (need at least "
-						"version 3.0).", vol->major_ver,
-						vol->minor_ver);
-			else
-				NVolSetSparseEnabled(vol);
-		}
-	}
-	return true;
-needs_arg:
-	ntfs_error(vol->sb, "The %s option requires an argument.", p);
-	return false;
-needs_bool:
-	ntfs_error(vol->sb, "The %s option requires a boolean argument.", p);
-	return false;
-needs_val:
-	ntfs_error(vol->sb, "Invalid %s option argument: %s", p, ov);
-	return false;
-}
-
-#ifdef NTFS_RW
-
-/**
- * ntfs_write_volume_flags - write new flags to the volume information flags
- * @vol:	ntfs volume on which to modify the flags
- * @flags:	new flags value for the volume information flags
- *
- * Internal function.  You probably want to use ntfs_{set,clear}_volume_flags()
- * instead (see below).
- *
- * Replace the volume information flags on the volume @vol with the value
- * supplied in @flags.  Note, this overwrites the volume information flags, so
- * make sure to combine the flags you want to modify with the old flags and use
- * the result when calling ntfs_write_volume_flags().
- *
- * Return 0 on success and -errno on error.
- */
-static int ntfs_write_volume_flags(ntfs_volume *vol, const VOLUME_FLAGS flags)
-{
-	ntfs_inode *ni = NTFS_I(vol->vol_ino);
-	MFT_RECORD *m;
-	VOLUME_INFORMATION *vi;
-	ntfs_attr_search_ctx *ctx;
-	int err;
-
-	ntfs_debug("Entering, old flags = 0x%x, new flags = 0x%x.",
-			le16_to_cpu(vol->vol_flags), le16_to_cpu(flags));
-	if (vol->vol_flags == flags)
-		goto done;
-	BUG_ON(!ni);
-	m = map_mft_record(ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		goto err_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(ni, m);
-	if (!ctx) {
-		err = -ENOMEM;
-		goto put_unm_err_out;
-	}
-	err = ntfs_attr_lookup(AT_VOLUME_INFORMATION, NULL, 0, 0, 0, NULL, 0,
-			ctx);
-	if (err)
-		goto put_unm_err_out;
-	vi = (VOLUME_INFORMATION*)((u8*)ctx->attr +
-			le16_to_cpu(ctx->attr->data.resident.value_offset));
-	vol->vol_flags = vi->flags = flags;
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(ni);
-done:
-	ntfs_debug("Done.");
-	return 0;
-put_unm_err_out:
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(ni);
-err_out:
-	ntfs_error(vol->sb, "Failed with error code %i.", -err);
-	return err;
-}
-
-/**
- * ntfs_set_volume_flags - set bits in the volume information flags
- * @vol:	ntfs volume on which to modify the flags
- * @flags:	flags to set on the volume
- *
- * Set the bits in @flags in the volume information flags on the volume @vol.
- *
- * Return 0 on success and -errno on error.
- */
-static inline int ntfs_set_volume_flags(ntfs_volume *vol, VOLUME_FLAGS flags)
-{
-	flags &= VOLUME_FLAGS_MASK;
-	return ntfs_write_volume_flags(vol, vol->vol_flags | flags);
-}
-
-/**
- * ntfs_clear_volume_flags - clear bits in the volume information flags
- * @vol:	ntfs volume on which to modify the flags
- * @flags:	flags to clear on the volume
- *
- * Clear the bits in @flags in the volume information flags on the volume @vol.
- *
- * Return 0 on success and -errno on error.
- */
-static inline int ntfs_clear_volume_flags(ntfs_volume *vol, VOLUME_FLAGS flags)
-{
-	flags &= VOLUME_FLAGS_MASK;
-	flags = vol->vol_flags & cpu_to_le16(~le16_to_cpu(flags));
-	return ntfs_write_volume_flags(vol, flags);
-}
-
-#endif /* NTFS_RW */
-
-/**
- * ntfs_remount - change the mount options of a mounted ntfs filesystem
- * @sb:		superblock of mounted ntfs filesystem
- * @flags:	remount flags
- * @opt:	remount options string
- *
- * Change the mount options of an already mounted ntfs filesystem.
- *
- * NOTE:  The VFS sets the @sb->s_flags remount flags to @flags after
- * ntfs_remount() returns successfully (i.e. returns 0).  Otherwise,
- * @sb->s_flags are not changed.
- */
-static int ntfs_remount(struct super_block *sb, int *flags, char *opt)
-{
-	ntfs_volume *vol = NTFS_SB(sb);
-
-	ntfs_debug("Entering with remount options string: %s", opt);
-
-	sync_filesystem(sb);
-
-#ifndef NTFS_RW
-	/* For read-only compiled driver, enforce read-only flag. */
-	*flags |= SB_RDONLY;
-#else /* NTFS_RW */
-	/*
-	 * For the read-write compiled driver, if we are remounting read-write,
-	 * make sure there are no volume errors and that no unsupported volume
-	 * flags are set.  Also, empty the logfile journal as it would become
-	 * stale as soon as something is written to the volume and mark the
-	 * volume dirty so that chkdsk is run if the volume is not umounted
-	 * cleanly.  Finally, mark the quotas out of date so Windows rescans
-	 * the volume on boot and updates them.
-	 *
-	 * When remounting read-only, mark the volume clean if no volume errors
-	 * have occurred.
-	 */
-	if (sb_rdonly(sb) && !(*flags & SB_RDONLY)) {
-		static const char *es = ".  Cannot remount read-write.";
-
-		/* Remounting read-write. */
-		if (NVolErrors(vol)) {
-			ntfs_error(sb, "Volume has errors and is read-only%s",
-					es);
-			return -EROFS;
-		}
-		if (vol->vol_flags & VOLUME_IS_DIRTY) {
-			ntfs_error(sb, "Volume is dirty and read-only%s", es);
-			return -EROFS;
-		}
-		if (vol->vol_flags & VOLUME_MODIFIED_BY_CHKDSK) {
-			ntfs_error(sb, "Volume has been modified by chkdsk "
-					"and is read-only%s", es);
-			return -EROFS;
-		}
-		if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) {
-			ntfs_error(sb, "Volume has unsupported flags set "
-					"(0x%x) and is read-only%s",
-					(unsigned)le16_to_cpu(vol->vol_flags),
-					es);
-			return -EROFS;
-		}
-		if (ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY)) {
-			ntfs_error(sb, "Failed to set dirty bit in volume "
-					"information flags%s", es);
-			return -EROFS;
-		}
-#if 0
-		// TODO: Enable this code once we start modifying anything that
-		//	 is different between NTFS 1.2 and 3.x...
-		/* Set NT4 compatibility flag on newer NTFS version volumes. */
-		if ((vol->major_ver > 1)) {
-			if (ntfs_set_volume_flags(vol, VOLUME_MOUNTED_ON_NT4)) {
-				ntfs_error(sb, "Failed to set NT4 "
-						"compatibility flag%s", es);
-				NVolSetErrors(vol);
-				return -EROFS;
-			}
-		}
-#endif
-		if (!ntfs_empty_logfile(vol->logfile_ino)) {
-			ntfs_error(sb, "Failed to empty journal $LogFile%s",
-					es);
-			NVolSetErrors(vol);
-			return -EROFS;
-		}
-		if (!ntfs_mark_quotas_out_of_date(vol)) {
-			ntfs_error(sb, "Failed to mark quotas out of date%s",
-					es);
-			NVolSetErrors(vol);
-			return -EROFS;
-		}
-		if (!ntfs_stamp_usnjrnl(vol)) {
-			ntfs_error(sb, "Failed to stamp transaction log "
-					"($UsnJrnl)%s", es);
-			NVolSetErrors(vol);
-			return -EROFS;
-		}
-	} else if (!sb_rdonly(sb) && (*flags & SB_RDONLY)) {
-		/* Remounting read-only. */
-		if (!NVolErrors(vol)) {
-			if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY))
-				ntfs_warning(sb, "Failed to clear dirty bit "
-						"in volume information "
-						"flags.  Run chkdsk.");
-		}
-	}
-#endif /* NTFS_RW */
-
-	// TODO: Deal with *flags.
-
-	if (!parse_options(vol, opt))
-		return -EINVAL;
-
-	ntfs_debug("Done.");
-	return 0;
-}
-
-/**
- * is_boot_sector_ntfs - check whether a boot sector is a valid NTFS boot sector
- * @sb:		Super block of the device to which @b belongs.
- * @b:		Boot sector of device @sb to check.
- * @silent:	If 'true', all output will be silenced.
- *
- * is_boot_sector_ntfs() checks whether the boot sector @b is a valid NTFS boot
- * sector. Returns 'true' if it is valid and 'false' if not.
- *
- * @sb is only needed for warning/error output, i.e. it can be NULL when silent
- * is 'true'.
- */
-static bool is_boot_sector_ntfs(const struct super_block *sb,
-		const NTFS_BOOT_SECTOR *b, const bool silent)
-{
-	/*
-	 * Check that checksum == sum of u32 values from b to the checksum
-	 * field.  If checksum is zero, no checking is done.  We will work when
-	 * the checksum test fails, since some utilities update the boot sector
-	 * ignoring the checksum which leaves the checksum out-of-date.  We
-	 * report a warning if this is the case.
-	 */
-	if ((void*)b < (void*)&b->checksum && b->checksum && !silent) {
-		le32 *u;
-		u32 i;
-
-		for (i = 0, u = (le32*)b; u < (le32*)(&b->checksum); ++u)
-			i += le32_to_cpup(u);
-		if (le32_to_cpu(b->checksum) != i)
-			ntfs_warning(sb, "Invalid boot sector checksum.");
-	}
-	/* Check OEMidentifier is "NTFS    " */
-	if (b->oem_id != magicNTFS)
-		goto not_ntfs;
-	/* Check bytes per sector value is between 256 and 4096. */
-	if (le16_to_cpu(b->bpb.bytes_per_sector) < 0x100 ||
-			le16_to_cpu(b->bpb.bytes_per_sector) > 0x1000)
-		goto not_ntfs;
-	/* Check sectors per cluster value is valid. */
-	switch (b->bpb.sectors_per_cluster) {
-	case 1: case 2: case 4: case 8: case 16: case 32: case 64: case 128:
-		break;
-	default:
-		goto not_ntfs;
-	}
-	/* Check the cluster size is not above the maximum (64kiB). */
-	if ((u32)le16_to_cpu(b->bpb.bytes_per_sector) *
-			b->bpb.sectors_per_cluster > NTFS_MAX_CLUSTER_SIZE)
-		goto not_ntfs;
-	/* Check reserved/unused fields are really zero. */
-	if (le16_to_cpu(b->bpb.reserved_sectors) ||
-			le16_to_cpu(b->bpb.root_entries) ||
-			le16_to_cpu(b->bpb.sectors) ||
-			le16_to_cpu(b->bpb.sectors_per_fat) ||
-			le32_to_cpu(b->bpb.large_sectors) || b->bpb.fats)
-		goto not_ntfs;
-	/* Check clusters per file mft record value is valid. */
-	if ((u8)b->clusters_per_mft_record < 0xe1 ||
-			(u8)b->clusters_per_mft_record > 0xf7)
-		switch (b->clusters_per_mft_record) {
-		case 1: case 2: case 4: case 8: case 16: case 32: case 64:
-			break;
-		default:
-			goto not_ntfs;
-		}
-	/* Check clusters per index block value is valid. */
-	if ((u8)b->clusters_per_index_record < 0xe1 ||
-			(u8)b->clusters_per_index_record > 0xf7)
-		switch (b->clusters_per_index_record) {
-		case 1: case 2: case 4: case 8: case 16: case 32: case 64:
-			break;
-		default:
-			goto not_ntfs;
-		}
-	/*
-	 * Check for valid end of sector marker. We will work without it, but
-	 * many BIOSes will refuse to boot from a bootsector if the magic is
-	 * incorrect, so we emit a warning.
-	 */
-	if (!silent && b->end_of_sector_marker != cpu_to_le16(0xaa55))
-		ntfs_warning(sb, "Invalid end of sector marker.");
-	return true;
-not_ntfs:
-	return false;
-}
-
-/**
- * read_ntfs_boot_sector - read the NTFS boot sector of a device
- * @sb:		super block of device to read the boot sector from
- * @silent:	if true, suppress all output
- *
- * Reads the boot sector from the device and validates it. If that fails, tries
- * to read the backup boot sector, first from the end of the device a-la NT4 and
- * later and then from the middle of the device a-la NT3.51 and before.
- *
- * If a valid boot sector is found but it is not the primary boot sector, we
- * repair the primary boot sector silently (unless the device is read-only or
- * the primary boot sector is not accessible).
- *
- * NOTE: To call this function, @sb must have the fields s_dev, the ntfs super
- * block (u.ntfs_sb), nr_blocks and the device flags (s_flags) initialized
- * to their respective values.
- *
- * Return the unlocked buffer head containing the boot sector or NULL on error.
- */
-static struct buffer_head *read_ntfs_boot_sector(struct super_block *sb,
-		const int silent)
-{
-	const char *read_err_str = "Unable to read %s boot sector.";
-	struct buffer_head *bh_primary, *bh_backup;
-	sector_t nr_blocks = NTFS_SB(sb)->nr_blocks;
-
-	/* Try to read primary boot sector. */
-	if ((bh_primary = sb_bread(sb, 0))) {
-		if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*)
-				bh_primary->b_data, silent))
-			return bh_primary;
-		if (!silent)
-			ntfs_error(sb, "Primary boot sector is invalid.");
-	} else if (!silent)
-		ntfs_error(sb, read_err_str, "primary");
-	if (!(NTFS_SB(sb)->on_errors & ON_ERRORS_RECOVER)) {
-		if (bh_primary)
-			brelse(bh_primary);
-		if (!silent)
-			ntfs_error(sb, "Mount option errors=recover not used. "
-					"Aborting without trying to recover.");
-		return NULL;
-	}
-	/* Try to read NT4+ backup boot sector. */
-	if ((bh_backup = sb_bread(sb, nr_blocks - 1))) {
-		if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*)
-				bh_backup->b_data, silent))
-			goto hotfix_primary_boot_sector;
-		brelse(bh_backup);
-	} else if (!silent)
-		ntfs_error(sb, read_err_str, "backup");
-	/* Try to read NT3.51- backup boot sector. */
-	if ((bh_backup = sb_bread(sb, nr_blocks >> 1))) {
-		if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*)
-				bh_backup->b_data, silent))
-			goto hotfix_primary_boot_sector;
-		if (!silent)
-			ntfs_error(sb, "Could not find a valid backup boot "
-					"sector.");
-		brelse(bh_backup);
-	} else if (!silent)
-		ntfs_error(sb, read_err_str, "backup");
-	/* We failed. Cleanup and return. */
-	if (bh_primary)
-		brelse(bh_primary);
-	return NULL;
-hotfix_primary_boot_sector:
-	if (bh_primary) {
-		/*
-		 * If we managed to read sector zero and the volume is not
-		 * read-only, copy the found, valid backup boot sector to the
-		 * primary boot sector.  Note we only copy the actual boot
-		 * sector structure, not the actual whole device sector as that
-		 * may be bigger and would potentially damage the $Boot system
-		 * file (FIXME: Would be nice to know if the backup boot sector
-		 * on a large sector device contains the whole boot loader or
-		 * just the first 512 bytes).
-		 */
-		if (!sb_rdonly(sb)) {
-			ntfs_warning(sb, "Hot-fix: Recovering invalid primary "
-					"boot sector from backup copy.");
-			memcpy(bh_primary->b_data, bh_backup->b_data,
-					NTFS_BLOCK_SIZE);
-			mark_buffer_dirty(bh_primary);
-			sync_dirty_buffer(bh_primary);
-			if (buffer_uptodate(bh_primary)) {
-				brelse(bh_backup);
-				return bh_primary;
-			}
-			ntfs_error(sb, "Hot-fix: Device write error while "
-					"recovering primary boot sector.");
-		} else {
-			ntfs_warning(sb, "Hot-fix: Recovery of primary boot "
-					"sector failed: Read-only mount.");
-		}
-		brelse(bh_primary);
-	}
-	ntfs_warning(sb, "Using backup boot sector.");
-	return bh_backup;
-}
-
-/**
- * parse_ntfs_boot_sector - parse the boot sector and store the data in @vol
- * @vol:	volume structure to initialise with data from boot sector
- * @b:		boot sector to parse
- *
- * Parse the ntfs boot sector @b and store all imporant information therein in
- * the ntfs super block @vol.  Return 'true' on success and 'false' on error.
- */
-static bool parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
-{
-	unsigned int sectors_per_cluster_bits, nr_hidden_sects;
-	int clusters_per_mft_record, clusters_per_index_record;
-	s64 ll;
-
-	vol->sector_size = le16_to_cpu(b->bpb.bytes_per_sector);
-	vol->sector_size_bits = ffs(vol->sector_size) - 1;
-	ntfs_debug("vol->sector_size = %i (0x%x)", vol->sector_size,
-			vol->sector_size);
-	ntfs_debug("vol->sector_size_bits = %i (0x%x)", vol->sector_size_bits,
-			vol->sector_size_bits);
-	if (vol->sector_size < vol->sb->s_blocksize) {
-		ntfs_error(vol->sb, "Sector size (%i) is smaller than the "
-				"device block size (%lu).  This is not "
-				"supported.  Sorry.", vol->sector_size,
-				vol->sb->s_blocksize);
-		return false;
-	}
-	ntfs_debug("sectors_per_cluster = 0x%x", b->bpb.sectors_per_cluster);
-	sectors_per_cluster_bits = ffs(b->bpb.sectors_per_cluster) - 1;
-	ntfs_debug("sectors_per_cluster_bits = 0x%x",
-			sectors_per_cluster_bits);
-	nr_hidden_sects = le32_to_cpu(b->bpb.hidden_sectors);
-	ntfs_debug("number of hidden sectors = 0x%x", nr_hidden_sects);
-	vol->cluster_size = vol->sector_size << sectors_per_cluster_bits;
-	vol->cluster_size_mask = vol->cluster_size - 1;
-	vol->cluster_size_bits = ffs(vol->cluster_size) - 1;
-	ntfs_debug("vol->cluster_size = %i (0x%x)", vol->cluster_size,
-			vol->cluster_size);
-	ntfs_debug("vol->cluster_size_mask = 0x%x", vol->cluster_size_mask);
-	ntfs_debug("vol->cluster_size_bits = %i", vol->cluster_size_bits);
-	if (vol->cluster_size < vol->sector_size) {
-		ntfs_error(vol->sb, "Cluster size (%i) is smaller than the "
-				"sector size (%i).  This is not supported.  "
-				"Sorry.", vol->cluster_size, vol->sector_size);
-		return false;
-	}
-	clusters_per_mft_record = b->clusters_per_mft_record;
-	ntfs_debug("clusters_per_mft_record = %i (0x%x)",
-			clusters_per_mft_record, clusters_per_mft_record);
-	if (clusters_per_mft_record > 0)
-		vol->mft_record_size = vol->cluster_size <<
-				(ffs(clusters_per_mft_record) - 1);
-	else
-		/*
-		 * When mft_record_size < cluster_size, clusters_per_mft_record
-		 * = -log2(mft_record_size) bytes. mft_record_size normaly is
-		 * 1024 bytes, which is encoded as 0xF6 (-10 in decimal).
-		 */
-		vol->mft_record_size = 1 << -clusters_per_mft_record;
-	vol->mft_record_size_mask = vol->mft_record_size - 1;
-	vol->mft_record_size_bits = ffs(vol->mft_record_size) - 1;
-	ntfs_debug("vol->mft_record_size = %i (0x%x)", vol->mft_record_size,
-			vol->mft_record_size);
-	ntfs_debug("vol->mft_record_size_mask = 0x%x",
-			vol->mft_record_size_mask);
-	ntfs_debug("vol->mft_record_size_bits = %i (0x%x)",
-			vol->mft_record_size_bits, vol->mft_record_size_bits);
-	/*
-	 * We cannot support mft record sizes above the PAGE_SIZE since
-	 * we store $MFT/$DATA, the table of mft records in the page cache.
-	 */
-	if (vol->mft_record_size > PAGE_SIZE) {
-		ntfs_error(vol->sb, "Mft record size (%i) exceeds the "
-				"PAGE_SIZE on your system (%lu).  "
-				"This is not supported.  Sorry.",
-				vol->mft_record_size, PAGE_SIZE);
-		return false;
-	}
-	/* We cannot support mft record sizes below the sector size. */
-	if (vol->mft_record_size < vol->sector_size) {
-		ntfs_error(vol->sb, "Mft record size (%i) is smaller than the "
-				"sector size (%i).  This is not supported.  "
-				"Sorry.", vol->mft_record_size,
-				vol->sector_size);
-		return false;
-	}
-	clusters_per_index_record = b->clusters_per_index_record;
-	ntfs_debug("clusters_per_index_record = %i (0x%x)",
-			clusters_per_index_record, clusters_per_index_record);
-	if (clusters_per_index_record > 0)
-		vol->index_record_size = vol->cluster_size <<
-				(ffs(clusters_per_index_record) - 1);
-	else
-		/*
-		 * When index_record_size < cluster_size,
-		 * clusters_per_index_record = -log2(index_record_size) bytes.
-		 * index_record_size normaly equals 4096 bytes, which is
-		 * encoded as 0xF4 (-12 in decimal).
-		 */
-		vol->index_record_size = 1 << -clusters_per_index_record;
-	vol->index_record_size_mask = vol->index_record_size - 1;
-	vol->index_record_size_bits = ffs(vol->index_record_size) - 1;
-	ntfs_debug("vol->index_record_size = %i (0x%x)",
-			vol->index_record_size, vol->index_record_size);
-	ntfs_debug("vol->index_record_size_mask = 0x%x",
-			vol->index_record_size_mask);
-	ntfs_debug("vol->index_record_size_bits = %i (0x%x)",
-			vol->index_record_size_bits,
-			vol->index_record_size_bits);
-	/* We cannot support index record sizes below the sector size. */
-	if (vol->index_record_size < vol->sector_size) {
-		ntfs_error(vol->sb, "Index record size (%i) is smaller than "
-				"the sector size (%i).  This is not "
-				"supported.  Sorry.", vol->index_record_size,
-				vol->sector_size);
-		return false;
-	}
-	/*
-	 * Get the size of the volume in clusters and check for 64-bit-ness.
-	 * Windows currently only uses 32 bits to save the clusters so we do
-	 * the same as it is much faster on 32-bit CPUs.
-	 */
-	ll = sle64_to_cpu(b->number_of_sectors) >> sectors_per_cluster_bits;
-	if ((u64)ll >= 1ULL << 32) {
-		ntfs_error(vol->sb, "Cannot handle 64-bit clusters.  Sorry.");
-		return false;
-	}
-	vol->nr_clusters = ll;
-	ntfs_debug("vol->nr_clusters = 0x%llx", (long long)vol->nr_clusters);
-	/*
-	 * On an architecture where unsigned long is 32-bits, we restrict the
-	 * volume size to 2TiB (2^41). On a 64-bit architecture, the compiler
-	 * will hopefully optimize the whole check away.
-	 */
-	if (sizeof(unsigned long) < 8) {
-		if ((ll << vol->cluster_size_bits) >= (1ULL << 41)) {
-			ntfs_error(vol->sb, "Volume size (%lluTiB) is too "
-					"large for this architecture.  "
-					"Maximum supported is 2TiB.  Sorry.",
-					(unsigned long long)ll >> (40 -
-					vol->cluster_size_bits));
-			return false;
-		}
-	}
-	ll = sle64_to_cpu(b->mft_lcn);
-	if (ll >= vol->nr_clusters) {
-		ntfs_error(vol->sb, "MFT LCN (%lli, 0x%llx) is beyond end of "
-				"volume.  Weird.", (unsigned long long)ll,
-				(unsigned long long)ll);
-		return false;
-	}
-	vol->mft_lcn = ll;
-	ntfs_debug("vol->mft_lcn = 0x%llx", (long long)vol->mft_lcn);
-	ll = sle64_to_cpu(b->mftmirr_lcn);
-	if (ll >= vol->nr_clusters) {
-		ntfs_error(vol->sb, "MFTMirr LCN (%lli, 0x%llx) is beyond end "
-				"of volume.  Weird.", (unsigned long long)ll,
-				(unsigned long long)ll);
-		return false;
-	}
-	vol->mftmirr_lcn = ll;
-	ntfs_debug("vol->mftmirr_lcn = 0x%llx", (long long)vol->mftmirr_lcn);
-#ifdef NTFS_RW
-	/*
-	 * Work out the size of the mft mirror in number of mft records. If the
-	 * cluster size is less than or equal to the size taken by four mft
-	 * records, the mft mirror stores the first four mft records. If the
-	 * cluster size is bigger than the size taken by four mft records, the
-	 * mft mirror contains as many mft records as will fit into one
-	 * cluster.
-	 */
-	if (vol->cluster_size <= (4 << vol->mft_record_size_bits))
-		vol->mftmirr_size = 4;
-	else
-		vol->mftmirr_size = vol->cluster_size >>
-				vol->mft_record_size_bits;
-	ntfs_debug("vol->mftmirr_size = %i", vol->mftmirr_size);
-#endif /* NTFS_RW */
-	vol->serial_no = le64_to_cpu(b->volume_serial_number);
-	ntfs_debug("vol->serial_no = 0x%llx",
-			(unsigned long long)vol->serial_no);
-	return true;
-}
-
-/**
- * ntfs_setup_allocators - initialize the cluster and mft allocators
- * @vol:	volume structure for which to setup the allocators
- *
- * Setup the cluster (lcn) and mft allocators to the starting values.
- */
-static void ntfs_setup_allocators(ntfs_volume *vol)
-{
-#ifdef NTFS_RW
-	LCN mft_zone_size, mft_lcn;
-#endif /* NTFS_RW */
-
-	ntfs_debug("vol->mft_zone_multiplier = 0x%x",
-			vol->mft_zone_multiplier);
-#ifdef NTFS_RW
-	/* Determine the size of the MFT zone. */
-	mft_zone_size = vol->nr_clusters;
-	switch (vol->mft_zone_multiplier) {  /* % of volume size in clusters */
-	case 4:
-		mft_zone_size >>= 1;			/* 50%   */
-		break;
-	case 3:
-		mft_zone_size = (mft_zone_size +
-				(mft_zone_size >> 1)) >> 2;	/* 37.5% */
-		break;
-	case 2:
-		mft_zone_size >>= 2;			/* 25%   */
-		break;
-	/* case 1: */
-	default:
-		mft_zone_size >>= 3;			/* 12.5% */
-		break;
-	}
-	/* Setup the mft zone. */
-	vol->mft_zone_start = vol->mft_zone_pos = vol->mft_lcn;
-	ntfs_debug("vol->mft_zone_pos = 0x%llx",
-			(unsigned long long)vol->mft_zone_pos);
-	/*
-	 * Calculate the mft_lcn for an unmodified NTFS volume (see mkntfs
-	 * source) and if the actual mft_lcn is in the expected place or even
-	 * further to the front of the volume, extend the mft_zone to cover the
-	 * beginning of the volume as well.  This is in order to protect the
-	 * area reserved for the mft bitmap as well within the mft_zone itself.
-	 * On non-standard volumes we do not protect it as the overhead would
-	 * be higher than the speed increase we would get by doing it.
-	 */
-	mft_lcn = (8192 + 2 * vol->cluster_size - 1) / vol->cluster_size;
-	if (mft_lcn * vol->cluster_size < 16 * 1024)
-		mft_lcn = (16 * 1024 + vol->cluster_size - 1) /
-				vol->cluster_size;
-	if (vol->mft_zone_start <= mft_lcn)
-		vol->mft_zone_start = 0;
-	ntfs_debug("vol->mft_zone_start = 0x%llx",
-			(unsigned long long)vol->mft_zone_start);
-	/*
-	 * Need to cap the mft zone on non-standard volumes so that it does
-	 * not point outside the boundaries of the volume.  We do this by
-	 * halving the zone size until we are inside the volume.
-	 */
-	vol->mft_zone_end = vol->mft_lcn + mft_zone_size;
-	while (vol->mft_zone_end >= vol->nr_clusters) {
-		mft_zone_size >>= 1;
-		vol->mft_zone_end = vol->mft_lcn + mft_zone_size;
-	}
-	ntfs_debug("vol->mft_zone_end = 0x%llx",
-			(unsigned long long)vol->mft_zone_end);
-	/*
-	 * Set the current position within each data zone to the start of the
-	 * respective zone.
-	 */
-	vol->data1_zone_pos = vol->mft_zone_end;
-	ntfs_debug("vol->data1_zone_pos = 0x%llx",
-			(unsigned long long)vol->data1_zone_pos);
-	vol->data2_zone_pos = 0;
-	ntfs_debug("vol->data2_zone_pos = 0x%llx",
-			(unsigned long long)vol->data2_zone_pos);
-
-	/* Set the mft data allocation position to mft record 24. */
-	vol->mft_data_pos = 24;
-	ntfs_debug("vol->mft_data_pos = 0x%llx",
-			(unsigned long long)vol->mft_data_pos);
-#endif /* NTFS_RW */
-}
-
-#ifdef NTFS_RW
-
-/**
- * load_and_init_mft_mirror - load and setup the mft mirror inode for a volume
- * @vol:	ntfs super block describing device whose mft mirror to load
- *
- * Return 'true' on success or 'false' on error.
- */
-static bool load_and_init_mft_mirror(ntfs_volume *vol)
-{
-	struct inode *tmp_ino;
-	ntfs_inode *tmp_ni;
-
-	ntfs_debug("Entering.");
-	/* Get mft mirror inode. */
-	tmp_ino = ntfs_iget(vol->sb, FILE_MFTMirr);
-	if (IS_ERR(tmp_ino) || is_bad_inode(tmp_ino)) {
-		if (!IS_ERR(tmp_ino))
-			iput(tmp_ino);
-		/* Caller will display error message. */
-		return false;
-	}
-	/*
-	 * Re-initialize some specifics about $MFTMirr's inode as
-	 * ntfs_read_inode() will have set up the default ones.
-	 */
-	/* Set uid and gid to root. */
-	tmp_ino->i_uid = GLOBAL_ROOT_UID;
-	tmp_ino->i_gid = GLOBAL_ROOT_GID;
-	/* Regular file.  No access for anyone. */
-	tmp_ino->i_mode = S_IFREG;
-	/* No VFS initiated operations allowed for $MFTMirr. */
-	tmp_ino->i_op = &ntfs_empty_inode_ops;
-	tmp_ino->i_fop = &ntfs_empty_file_ops;
-	/* Put in our special address space operations. */
-	tmp_ino->i_mapping->a_ops = &ntfs_mst_aops;
-	tmp_ni = NTFS_I(tmp_ino);
-	/* The $MFTMirr, like the $MFT is multi sector transfer protected. */
-	NInoSetMstProtected(tmp_ni);
-	NInoSetSparseDisabled(tmp_ni);
-	/*
-	 * Set up our little cheat allowing us to reuse the async read io
-	 * completion handler for directories.
-	 */
-	tmp_ni->itype.index.block_size = vol->mft_record_size;
-	tmp_ni->itype.index.block_size_bits = vol->mft_record_size_bits;
-	vol->mftmirr_ino = tmp_ino;
-	ntfs_debug("Done.");
-	return true;
-}
-
-/**
- * check_mft_mirror - compare contents of the mft mirror with the mft
- * @vol:	ntfs super block describing device whose mft mirror to check
- *
- * Return 'true' on success or 'false' on error.
- *
- * Note, this function also results in the mft mirror runlist being completely
- * mapped into memory.  The mft mirror write code requires this and will BUG()
- * should it find an unmapped runlist element.
- */
-static bool check_mft_mirror(ntfs_volume *vol)
-{
-	struct super_block *sb = vol->sb;
-	ntfs_inode *mirr_ni;
-	struct page *mft_page, *mirr_page;
-	u8 *kmft, *kmirr;
-	runlist_element *rl, rl2[2];
-	pgoff_t index;
-	int mrecs_per_page, i;
-
-	ntfs_debug("Entering.");
-	/* Compare contents of $MFT and $MFTMirr. */
-	mrecs_per_page = PAGE_SIZE / vol->mft_record_size;
-	BUG_ON(!mrecs_per_page);
-	BUG_ON(!vol->mftmirr_size);
-	mft_page = mirr_page = NULL;
-	kmft = kmirr = NULL;
-	index = i = 0;
-	do {
-		u32 bytes;
-
-		/* Switch pages if necessary. */
-		if (!(i % mrecs_per_page)) {
-			if (index) {
-				ntfs_unmap_page(mft_page);
-				ntfs_unmap_page(mirr_page);
-			}
-			/* Get the $MFT page. */
-			mft_page = ntfs_map_page(vol->mft_ino->i_mapping,
-					index);
-			if (IS_ERR(mft_page)) {
-				ntfs_error(sb, "Failed to read $MFT.");
-				return false;
-			}
-			kmft = page_address(mft_page);
-			/* Get the $MFTMirr page. */
-			mirr_page = ntfs_map_page(vol->mftmirr_ino->i_mapping,
-					index);
-			if (IS_ERR(mirr_page)) {
-				ntfs_error(sb, "Failed to read $MFTMirr.");
-				goto mft_unmap_out;
-			}
-			kmirr = page_address(mirr_page);
-			++index;
-		}
-		/* Do not check the record if it is not in use. */
-		if (((MFT_RECORD*)kmft)->flags & MFT_RECORD_IN_USE) {
-			/* Make sure the record is ok. */
-			if (ntfs_is_baad_recordp((le32*)kmft)) {
-				ntfs_error(sb, "Incomplete multi sector "
-						"transfer detected in mft "
-						"record %i.", i);
-mm_unmap_out:
-				ntfs_unmap_page(mirr_page);
-mft_unmap_out:
-				ntfs_unmap_page(mft_page);
-				return false;
-			}
-		}
-		/* Do not check the mirror record if it is not in use. */
-		if (((MFT_RECORD*)kmirr)->flags & MFT_RECORD_IN_USE) {
-			if (ntfs_is_baad_recordp((le32*)kmirr)) {
-				ntfs_error(sb, "Incomplete multi sector "
-						"transfer detected in mft "
-						"mirror record %i.", i);
-				goto mm_unmap_out;
-			}
-		}
-		/* Get the amount of data in the current record. */
-		bytes = le32_to_cpu(((MFT_RECORD*)kmft)->bytes_in_use);
-		if (bytes < sizeof(MFT_RECORD_OLD) ||
-				bytes > vol->mft_record_size ||
-				ntfs_is_baad_recordp((le32*)kmft)) {
-			bytes = le32_to_cpu(((MFT_RECORD*)kmirr)->bytes_in_use);
-			if (bytes < sizeof(MFT_RECORD_OLD) ||
-					bytes > vol->mft_record_size ||
-					ntfs_is_baad_recordp((le32*)kmirr))
-				bytes = vol->mft_record_size;
-		}
-		/* Compare the two records. */
-		if (memcmp(kmft, kmirr, bytes)) {
-			ntfs_error(sb, "$MFT and $MFTMirr (record %i) do not "
-					"match.  Run ntfsfix or chkdsk.", i);
-			goto mm_unmap_out;
-		}
-		kmft += vol->mft_record_size;
-		kmirr += vol->mft_record_size;
-	} while (++i < vol->mftmirr_size);
-	/* Release the last pages. */
-	ntfs_unmap_page(mft_page);
-	ntfs_unmap_page(mirr_page);
-
-	/* Construct the mft mirror runlist by hand. */
-	rl2[0].vcn = 0;
-	rl2[0].lcn = vol->mftmirr_lcn;
-	rl2[0].length = (vol->mftmirr_size * vol->mft_record_size +
-			vol->cluster_size - 1) / vol->cluster_size;
-	rl2[1].vcn = rl2[0].length;
-	rl2[1].lcn = LCN_ENOENT;
-	rl2[1].length = 0;
-	/*
-	 * Because we have just read all of the mft mirror, we know we have
-	 * mapped the full runlist for it.
-	 */
-	mirr_ni = NTFS_I(vol->mftmirr_ino);
-	down_read(&mirr_ni->runlist.lock);
-	rl = mirr_ni->runlist.rl;
-	/* Compare the two runlists.  They must be identical. */
-	i = 0;
-	do {
-		if (rl2[i].vcn != rl[i].vcn || rl2[i].lcn != rl[i].lcn ||
-				rl2[i].length != rl[i].length) {
-			ntfs_error(sb, "$MFTMirr location mismatch.  "
-					"Run chkdsk.");
-			up_read(&mirr_ni->runlist.lock);
-			return false;
-		}
-	} while (rl2[i++].length);
-	up_read(&mirr_ni->runlist.lock);
-	ntfs_debug("Done.");
-	return true;
-}
-
-/**
- * load_and_check_logfile - load and check the logfile inode for a volume
- * @vol:	ntfs super block describing device whose logfile to load
- *
- * Return 'true' on success or 'false' on error.
- */
-static bool load_and_check_logfile(ntfs_volume *vol,
-		RESTART_PAGE_HEADER **rp)
-{
-	struct inode *tmp_ino;
-
-	ntfs_debug("Entering.");
-	tmp_ino = ntfs_iget(vol->sb, FILE_LogFile);
-	if (IS_ERR(tmp_ino) || is_bad_inode(tmp_ino)) {
-		if (!IS_ERR(tmp_ino))
-			iput(tmp_ino);
-		/* Caller will display error message. */
-		return false;
-	}
-	if (!ntfs_check_logfile(tmp_ino, rp)) {
-		iput(tmp_ino);
-		/* ntfs_check_logfile() will have displayed error output. */
-		return false;
-	}
-	NInoSetSparseDisabled(NTFS_I(tmp_ino));
-	vol->logfile_ino = tmp_ino;
-	ntfs_debug("Done.");
-	return true;
-}
-
-#define NTFS_HIBERFIL_HEADER_SIZE	4096
-
-/**
- * check_windows_hibernation_status - check if Windows is suspended on a volume
- * @vol:	ntfs super block of device to check
- *
- * Check if Windows is hibernated on the ntfs volume @vol.  This is done by
- * looking for the file hiberfil.sys in the root directory of the volume.  If
- * the file is not present Windows is definitely not suspended.
- *
- * If hiberfil.sys exists and is less than 4kiB in size it means Windows is
- * definitely suspended (this volume is not the system volume).  Caveat:  on a
- * system with many volumes it is possible that the < 4kiB check is bogus but
- * for now this should do fine.
- *
- * If hiberfil.sys exists and is larger than 4kiB in size, we need to read the
- * hiberfil header (which is the first 4kiB).  If this begins with "hibr",
- * Windows is definitely suspended.  If it is completely full of zeroes,
- * Windows is definitely not hibernated.  Any other case is treated as if
- * Windows is suspended.  This caters for the above mentioned caveat of a
- * system with many volumes where no "hibr" magic would be present and there is
- * no zero header.
- *
- * Return 0 if Windows is not hibernated on the volume, >0 if Windows is
- * hibernated on the volume, and -errno on error.
- */
-static int check_windows_hibernation_status(ntfs_volume *vol)
-{
-	MFT_REF mref;
-	struct inode *vi;
-	struct page *page;
-	u32 *kaddr, *kend;
-	ntfs_name *name = NULL;
-	int ret = 1;
-	static const ntfschar hiberfil[13] = { cpu_to_le16('h'),
-			cpu_to_le16('i'), cpu_to_le16('b'),
-			cpu_to_le16('e'), cpu_to_le16('r'),
-			cpu_to_le16('f'), cpu_to_le16('i'),
-			cpu_to_le16('l'), cpu_to_le16('.'),
-			cpu_to_le16('s'), cpu_to_le16('y'),
-			cpu_to_le16('s'), 0 };
-
-	ntfs_debug("Entering.");
-	/*
-	 * Find the inode number for the hibernation file by looking up the
-	 * filename hiberfil.sys in the root directory.
-	 */
-	inode_lock(vol->root_ino);
-	mref = ntfs_lookup_inode_by_name(NTFS_I(vol->root_ino), hiberfil, 12,
-			&name);
-	inode_unlock(vol->root_ino);
-	if (IS_ERR_MREF(mref)) {
-		ret = MREF_ERR(mref);
-		/* If the file does not exist, Windows is not hibernated. */
-		if (ret == -ENOENT) {
-			ntfs_debug("hiberfil.sys not present.  Windows is not "
-					"hibernated on the volume.");
-			return 0;
-		}
-		/* A real error occurred. */
-		ntfs_error(vol->sb, "Failed to find inode number for "
-				"hiberfil.sys.");
-		return ret;
-	}
-	/* We do not care for the type of match that was found. */
-	kfree(name);
-	/* Get the inode. */
-	vi = ntfs_iget(vol->sb, MREF(mref));
-	if (IS_ERR(vi) || is_bad_inode(vi)) {
-		if (!IS_ERR(vi))
-			iput(vi);
-		ntfs_error(vol->sb, "Failed to load hiberfil.sys.");
-		return IS_ERR(vi) ? PTR_ERR(vi) : -EIO;
-	}
-	if (unlikely(i_size_read(vi) < NTFS_HIBERFIL_HEADER_SIZE)) {
-		ntfs_debug("hiberfil.sys is smaller than 4kiB (0x%llx).  "
-				"Windows is hibernated on the volume.  This "
-				"is not the system volume.", i_size_read(vi));
-		goto iput_out;
-	}
-	page = ntfs_map_page(vi->i_mapping, 0);
-	if (IS_ERR(page)) {
-		ntfs_error(vol->sb, "Failed to read from hiberfil.sys.");
-		ret = PTR_ERR(page);
-		goto iput_out;
-	}
-	kaddr = (u32*)page_address(page);
-	if (*(le32*)kaddr == cpu_to_le32(0x72626968)/*'hibr'*/) {
-		ntfs_debug("Magic \"hibr\" found in hiberfil.sys.  Windows is "
-				"hibernated on the volume.  This is the "
-				"system volume.");
-		goto unm_iput_out;
-	}
-	kend = kaddr + NTFS_HIBERFIL_HEADER_SIZE/sizeof(*kaddr);
-	do {
-		if (unlikely(*kaddr)) {
-			ntfs_debug("hiberfil.sys is larger than 4kiB "
-					"(0x%llx), does not contain the "
-					"\"hibr\" magic, and does not have a "
-					"zero header.  Windows is hibernated "
-					"on the volume.  This is not the "
-					"system volume.", i_size_read(vi));
-			goto unm_iput_out;
-		}
-	} while (++kaddr < kend);
-	ntfs_debug("hiberfil.sys contains a zero header.  Windows is not "
-			"hibernated on the volume.  This is the system "
-			"volume.");
-	ret = 0;
-unm_iput_out:
-	ntfs_unmap_page(page);
-iput_out:
-	iput(vi);
-	return ret;
-}
-
-/**
- * load_and_init_quota - load and setup the quota file for a volume if present
- * @vol:	ntfs super block describing device whose quota file to load
- *
- * Return 'true' on success or 'false' on error.  If $Quota is not present, we
- * leave vol->quota_ino as NULL and return success.
- */
-static bool load_and_init_quota(ntfs_volume *vol)
-{
-	MFT_REF mref;
-	struct inode *tmp_ino;
-	ntfs_name *name = NULL;
-	static const ntfschar Quota[7] = { cpu_to_le16('$'),
-			cpu_to_le16('Q'), cpu_to_le16('u'),
-			cpu_to_le16('o'), cpu_to_le16('t'),
-			cpu_to_le16('a'), 0 };
-	static ntfschar Q[3] = { cpu_to_le16('$'),
-			cpu_to_le16('Q'), 0 };
-
-	ntfs_debug("Entering.");
-	/*
-	 * Find the inode number for the quota file by looking up the filename
-	 * $Quota in the extended system files directory $Extend.
-	 */
-	inode_lock(vol->extend_ino);
-	mref = ntfs_lookup_inode_by_name(NTFS_I(vol->extend_ino), Quota, 6,
-			&name);
-	inode_unlock(vol->extend_ino);
-	if (IS_ERR_MREF(mref)) {
-		/*
-		 * If the file does not exist, quotas are disabled and have
-		 * never been enabled on this volume, just return success.
-		 */
-		if (MREF_ERR(mref) == -ENOENT) {
-			ntfs_debug("$Quota not present.  Volume does not have "
-					"quotas enabled.");
-			/*
-			 * No need to try to set quotas out of date if they are
-			 * not enabled.
-			 */
-			NVolSetQuotaOutOfDate(vol);
-			return true;
-		}
-		/* A real error occurred. */
-		ntfs_error(vol->sb, "Failed to find inode number for $Quota.");
-		return false;
-	}
-	/* We do not care for the type of match that was found. */
-	kfree(name);
-	/* Get the inode. */
-	tmp_ino = ntfs_iget(vol->sb, MREF(mref));
-	if (IS_ERR(tmp_ino) || is_bad_inode(tmp_ino)) {
-		if (!IS_ERR(tmp_ino))
-			iput(tmp_ino);
-		ntfs_error(vol->sb, "Failed to load $Quota.");
-		return false;
-	}
-	vol->quota_ino = tmp_ino;
-	/* Get the $Q index allocation attribute. */
-	tmp_ino = ntfs_index_iget(vol->quota_ino, Q, 2);
-	if (IS_ERR(tmp_ino)) {
-		ntfs_error(vol->sb, "Failed to load $Quota/$Q index.");
-		return false;
-	}
-	vol->quota_q_ino = tmp_ino;
-	ntfs_debug("Done.");
-	return true;
-}
-
-/**
- * load_and_init_usnjrnl - load and setup the transaction log if present
- * @vol:	ntfs super block describing device whose usnjrnl file to load
- *
- * Return 'true' on success or 'false' on error.
- *
- * If $UsnJrnl is not present or in the process of being disabled, we set
- * NVolUsnJrnlStamped() and return success.
- *
- * If the $UsnJrnl $DATA/$J attribute has a size equal to the lowest valid usn,
- * i.e. transaction logging has only just been enabled or the journal has been
- * stamped and nothing has been logged since, we also set NVolUsnJrnlStamped()
- * and return success.
- */
-static bool load_and_init_usnjrnl(ntfs_volume *vol)
-{
-	MFT_REF mref;
-	struct inode *tmp_ino;
-	ntfs_inode *tmp_ni;
-	struct page *page;
-	ntfs_name *name = NULL;
-	USN_HEADER *uh;
-	static const ntfschar UsnJrnl[9] = { cpu_to_le16('$'),
-			cpu_to_le16('U'), cpu_to_le16('s'),
-			cpu_to_le16('n'), cpu_to_le16('J'),
-			cpu_to_le16('r'), cpu_to_le16('n'),
-			cpu_to_le16('l'), 0 };
-	static ntfschar Max[5] = { cpu_to_le16('$'),
-			cpu_to_le16('M'), cpu_to_le16('a'),
-			cpu_to_le16('x'), 0 };
-	static ntfschar J[3] = { cpu_to_le16('$'),
-			cpu_to_le16('J'), 0 };
-
-	ntfs_debug("Entering.");
-	/*
-	 * Find the inode number for the transaction log file by looking up the
-	 * filename $UsnJrnl in the extended system files directory $Extend.
-	 */
-	inode_lock(vol->extend_ino);
-	mref = ntfs_lookup_inode_by_name(NTFS_I(vol->extend_ino), UsnJrnl, 8,
-			&name);
-	inode_unlock(vol->extend_ino);
-	if (IS_ERR_MREF(mref)) {
-		/*
-		 * If the file does not exist, transaction logging is disabled,
-		 * just return success.
-		 */
-		if (MREF_ERR(mref) == -ENOENT) {
-			ntfs_debug("$UsnJrnl not present.  Volume does not "
-					"have transaction logging enabled.");
-not_enabled:
-			/*
-			 * No need to try to stamp the transaction log if
-			 * transaction logging is not enabled.
-			 */
-			NVolSetUsnJrnlStamped(vol);
-			return true;
-		}
-		/* A real error occurred. */
-		ntfs_error(vol->sb, "Failed to find inode number for "
-				"$UsnJrnl.");
-		return false;
-	}
-	/* We do not care for the type of match that was found. */
-	kfree(name);
-	/* Get the inode. */
-	tmp_ino = ntfs_iget(vol->sb, MREF(mref));
-	if (IS_ERR(tmp_ino) || unlikely(is_bad_inode(tmp_ino))) {
-		if (!IS_ERR(tmp_ino))
-			iput(tmp_ino);
-		ntfs_error(vol->sb, "Failed to load $UsnJrnl.");
-		return false;
-	}
-	vol->usnjrnl_ino = tmp_ino;
-	/*
-	 * If the transaction log is in the process of being deleted, we can
-	 * ignore it.
-	 */
-	if (unlikely(vol->vol_flags & VOLUME_DELETE_USN_UNDERWAY)) {
-		ntfs_debug("$UsnJrnl in the process of being disabled.  "
-				"Volume does not have transaction logging "
-				"enabled.");
-		goto not_enabled;
-	}
-	/* Get the $DATA/$Max attribute. */
-	tmp_ino = ntfs_attr_iget(vol->usnjrnl_ino, AT_DATA, Max, 4);
-	if (IS_ERR(tmp_ino)) {
-		ntfs_error(vol->sb, "Failed to load $UsnJrnl/$DATA/$Max "
-				"attribute.");
-		return false;
-	}
-	vol->usnjrnl_max_ino = tmp_ino;
-	if (unlikely(i_size_read(tmp_ino) < sizeof(USN_HEADER))) {
-		ntfs_error(vol->sb, "Found corrupt $UsnJrnl/$DATA/$Max "
-				"attribute (size is 0x%llx but should be at "
-				"least 0x%zx bytes).", i_size_read(tmp_ino),
-				sizeof(USN_HEADER));
-		return false;
-	}
-	/* Get the $DATA/$J attribute. */
-	tmp_ino = ntfs_attr_iget(vol->usnjrnl_ino, AT_DATA, J, 2);
-	if (IS_ERR(tmp_ino)) {
-		ntfs_error(vol->sb, "Failed to load $UsnJrnl/$DATA/$J "
-				"attribute.");
-		return false;
-	}
-	vol->usnjrnl_j_ino = tmp_ino;
-	/* Verify $J is non-resident and sparse. */
-	tmp_ni = NTFS_I(vol->usnjrnl_j_ino);
-	if (unlikely(!NInoNonResident(tmp_ni) || !NInoSparse(tmp_ni))) {
-		ntfs_error(vol->sb, "$UsnJrnl/$DATA/$J attribute is resident "
-				"and/or not sparse.");
-		return false;
-	}
-	/* Read the USN_HEADER from $DATA/$Max. */
-	page = ntfs_map_page(vol->usnjrnl_max_ino->i_mapping, 0);
-	if (IS_ERR(page)) {
-		ntfs_error(vol->sb, "Failed to read from $UsnJrnl/$DATA/$Max "
-				"attribute.");
-		return false;
-	}
-	uh = (USN_HEADER*)page_address(page);
-	/* Sanity check the $Max. */
-	if (unlikely(sle64_to_cpu(uh->allocation_delta) >
-			sle64_to_cpu(uh->maximum_size))) {
-		ntfs_error(vol->sb, "Allocation delta (0x%llx) exceeds "
-				"maximum size (0x%llx).  $UsnJrnl is corrupt.",
-				(long long)sle64_to_cpu(uh->allocation_delta),
-				(long long)sle64_to_cpu(uh->maximum_size));
-		ntfs_unmap_page(page);
-		return false;
-	}
-	/*
-	 * If the transaction log has been stamped and nothing has been written
-	 * to it since, we do not need to stamp it.
-	 */
-	if (unlikely(sle64_to_cpu(uh->lowest_valid_usn) >=
-			i_size_read(vol->usnjrnl_j_ino))) {
-		if (likely(sle64_to_cpu(uh->lowest_valid_usn) ==
-				i_size_read(vol->usnjrnl_j_ino))) {
-			ntfs_unmap_page(page);
-			ntfs_debug("$UsnJrnl is enabled but nothing has been "
-					"logged since it was last stamped.  "
-					"Treating this as if the volume does "
-					"not have transaction logging "
-					"enabled.");
-			goto not_enabled;
-		}
-		ntfs_error(vol->sb, "$UsnJrnl has lowest valid usn (0x%llx) "
-				"which is out of bounds (0x%llx).  $UsnJrnl "
-				"is corrupt.",
-				(long long)sle64_to_cpu(uh->lowest_valid_usn),
-				i_size_read(vol->usnjrnl_j_ino));
-		ntfs_unmap_page(page);
-		return false;
-	}
-	ntfs_unmap_page(page);
-	ntfs_debug("Done.");
-	return true;
-}
-
-/**
- * load_and_init_attrdef - load the attribute definitions table for a volume
- * @vol:	ntfs super block describing device whose attrdef to load
- *
- * Return 'true' on success or 'false' on error.
- */
-static bool load_and_init_attrdef(ntfs_volume *vol)
-{
-	loff_t i_size;
-	struct super_block *sb = vol->sb;
-	struct inode *ino;
-	struct page *page;
-	pgoff_t index, max_index;
-	unsigned int size;
-
-	ntfs_debug("Entering.");
-	/* Read attrdef table and setup vol->attrdef and vol->attrdef_size. */
-	ino = ntfs_iget(sb, FILE_AttrDef);
-	if (IS_ERR(ino) || is_bad_inode(ino)) {
-		if (!IS_ERR(ino))
-			iput(ino);
-		goto failed;
-	}
-	NInoSetSparseDisabled(NTFS_I(ino));
-	/* The size of FILE_AttrDef must be above 0 and fit inside 31 bits. */
-	i_size = i_size_read(ino);
-	if (i_size <= 0 || i_size > 0x7fffffff)
-		goto iput_failed;
-	vol->attrdef = (ATTR_DEF*)ntfs_malloc_nofs(i_size);
-	if (!vol->attrdef)
-		goto iput_failed;
-	index = 0;
-	max_index = i_size >> PAGE_SHIFT;
-	size = PAGE_SIZE;
-	while (index < max_index) {
-		/* Read the attrdef table and copy it into the linear buffer. */
-read_partial_attrdef_page:
-		page = ntfs_map_page(ino->i_mapping, index);
-		if (IS_ERR(page))
-			goto free_iput_failed;
-		memcpy((u8*)vol->attrdef + (index++ << PAGE_SHIFT),
-				page_address(page), size);
-		ntfs_unmap_page(page);
-	}
-	if (size == PAGE_SIZE) {
-		size = i_size & ~PAGE_MASK;
-		if (size)
-			goto read_partial_attrdef_page;
-	}
-	vol->attrdef_size = i_size;
-	ntfs_debug("Read %llu bytes from $AttrDef.", i_size);
-	iput(ino);
-	return true;
-free_iput_failed:
-	ntfs_free(vol->attrdef);
-	vol->attrdef = NULL;
-iput_failed:
-	iput(ino);
-failed:
-	ntfs_error(sb, "Failed to initialize attribute definition table.");
-	return false;
-}
-
-#endif /* NTFS_RW */
-
-/**
- * load_and_init_upcase - load the upcase table for an ntfs volume
- * @vol:	ntfs super block describing device whose upcase to load
- *
- * Return 'true' on success or 'false' on error.
- */
-static bool load_and_init_upcase(ntfs_volume *vol)
-{
-	loff_t i_size;
-	struct super_block *sb = vol->sb;
-	struct inode *ino;
-	struct page *page;
-	pgoff_t index, max_index;
-	unsigned int size;
-	int i, max;
-
-	ntfs_debug("Entering.");
-	/* Read upcase table and setup vol->upcase and vol->upcase_len. */
-	ino = ntfs_iget(sb, FILE_UpCase);
-	if (IS_ERR(ino) || is_bad_inode(ino)) {
-		if (!IS_ERR(ino))
-			iput(ino);
-		goto upcase_failed;
-	}
-	/*
-	 * The upcase size must not be above 64k Unicode characters, must not
-	 * be zero and must be a multiple of sizeof(ntfschar).
-	 */
-	i_size = i_size_read(ino);
-	if (!i_size || i_size & (sizeof(ntfschar) - 1) ||
-			i_size > 64ULL * 1024 * sizeof(ntfschar))
-		goto iput_upcase_failed;
-	vol->upcase = (ntfschar*)ntfs_malloc_nofs(i_size);
-	if (!vol->upcase)
-		goto iput_upcase_failed;
-	index = 0;
-	max_index = i_size >> PAGE_SHIFT;
-	size = PAGE_SIZE;
-	while (index < max_index) {
-		/* Read the upcase table and copy it into the linear buffer. */
-read_partial_upcase_page:
-		page = ntfs_map_page(ino->i_mapping, index);
-		if (IS_ERR(page))
-			goto iput_upcase_failed;
-		memcpy((char*)vol->upcase + (index++ << PAGE_SHIFT),
-				page_address(page), size);
-		ntfs_unmap_page(page);
-	}
-	if (size == PAGE_SIZE) {
-		size = i_size & ~PAGE_MASK;
-		if (size)
-			goto read_partial_upcase_page;
-	}
-	vol->upcase_len = i_size >> UCHAR_T_SIZE_BITS;
-	ntfs_debug("Read %llu bytes from $UpCase (expected %zu bytes).",
-			i_size, 64 * 1024 * sizeof(ntfschar));
-	iput(ino);
-	mutex_lock(&ntfs_lock);
-	if (!default_upcase) {
-		ntfs_debug("Using volume specified $UpCase since default is "
-				"not present.");
-		mutex_unlock(&ntfs_lock);
-		return true;
-	}
-	max = default_upcase_len;
-	if (max > vol->upcase_len)
-		max = vol->upcase_len;
-	for (i = 0; i < max; i++)
-		if (vol->upcase[i] != default_upcase[i])
-			break;
-	if (i == max) {
-		ntfs_free(vol->upcase);
-		vol->upcase = default_upcase;
-		vol->upcase_len = max;
-		ntfs_nr_upcase_users++;
-		mutex_unlock(&ntfs_lock);
-		ntfs_debug("Volume specified $UpCase matches default. Using "
-				"default.");
-		return true;
-	}
-	mutex_unlock(&ntfs_lock);
-	ntfs_debug("Using volume specified $UpCase since it does not match "
-			"the default.");
-	return true;
-iput_upcase_failed:
-	iput(ino);
-	ntfs_free(vol->upcase);
-	vol->upcase = NULL;
-upcase_failed:
-	mutex_lock(&ntfs_lock);
-	if (default_upcase) {
-		vol->upcase = default_upcase;
-		vol->upcase_len = default_upcase_len;
-		ntfs_nr_upcase_users++;
-		mutex_unlock(&ntfs_lock);
-		ntfs_error(sb, "Failed to load $UpCase from the volume. Using "
-				"default.");
-		return true;
-	}
-	mutex_unlock(&ntfs_lock);
-	ntfs_error(sb, "Failed to initialize upcase table.");
-	return false;
-}
-
-/*
- * The lcn and mft bitmap inodes are NTFS-internal inodes with
- * their own special locking rules:
- */
-static struct lock_class_key
-	lcnbmp_runlist_lock_key, lcnbmp_mrec_lock_key,
-	mftbmp_runlist_lock_key, mftbmp_mrec_lock_key;
-
-/**
- * load_system_files - open the system files using normal functions
- * @vol:	ntfs super block describing device whose system files to load
- *
- * Open the system files with normal access functions and complete setting up
- * the ntfs super block @vol.
- *
- * Return 'true' on success or 'false' on error.
- */
-static bool load_system_files(ntfs_volume *vol)
-{
-	struct super_block *sb = vol->sb;
-	MFT_RECORD *m;
-	VOLUME_INFORMATION *vi;
-	ntfs_attr_search_ctx *ctx;
-#ifdef NTFS_RW
-	RESTART_PAGE_HEADER *rp;
-	int err;
-#endif /* NTFS_RW */
-
-	ntfs_debug("Entering.");
-#ifdef NTFS_RW
-	/* Get mft mirror inode compare the contents of $MFT and $MFTMirr. */
-	if (!load_and_init_mft_mirror(vol) || !check_mft_mirror(vol)) {
-		static const char *es1 = "Failed to load $MFTMirr";
-		static const char *es2 = "$MFTMirr does not match $MFT";
-		static const char *es3 = ".  Run ntfsfix and/or chkdsk.";
-
-		/* If a read-write mount, convert it to a read-only mount. */
-		if (!sb_rdonly(sb)) {
-			if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-					ON_ERRORS_CONTINUE))) {
-				ntfs_error(sb, "%s and neither on_errors="
-						"continue nor on_errors="
-						"remount-ro was specified%s",
-						!vol->mftmirr_ino ? es1 : es2,
-						es3);
-				goto iput_mirr_err_out;
-			}
-			sb->s_flags |= SB_RDONLY;
-			ntfs_error(sb, "%s.  Mounting read-only%s",
-					!vol->mftmirr_ino ? es1 : es2, es3);
-		} else
-			ntfs_warning(sb, "%s.  Will not be able to remount "
-					"read-write%s",
-					!vol->mftmirr_ino ? es1 : es2, es3);
-		/* This will prevent a read-write remount. */
-		NVolSetErrors(vol);
-	}
-#endif /* NTFS_RW */
-	/* Get mft bitmap attribute inode. */
-	vol->mftbmp_ino = ntfs_attr_iget(vol->mft_ino, AT_BITMAP, NULL, 0);
-	if (IS_ERR(vol->mftbmp_ino)) {
-		ntfs_error(sb, "Failed to load $MFT/$BITMAP attribute.");
-		goto iput_mirr_err_out;
-	}
-	lockdep_set_class(&NTFS_I(vol->mftbmp_ino)->runlist.lock,
-			   &mftbmp_runlist_lock_key);
-	lockdep_set_class(&NTFS_I(vol->mftbmp_ino)->mrec_lock,
-			   &mftbmp_mrec_lock_key);
-	/* Read upcase table and setup @vol->upcase and @vol->upcase_len. */
-	if (!load_and_init_upcase(vol))
-		goto iput_mftbmp_err_out;
-#ifdef NTFS_RW
-	/*
-	 * Read attribute definitions table and setup @vol->attrdef and
-	 * @vol->attrdef_size.
-	 */
-	if (!load_and_init_attrdef(vol))
-		goto iput_upcase_err_out;
-#endif /* NTFS_RW */
-	/*
-	 * Get the cluster allocation bitmap inode and verify the size, no
-	 * need for any locking at this stage as we are already running
-	 * exclusively as we are mount in progress task.
-	 */
-	vol->lcnbmp_ino = ntfs_iget(sb, FILE_Bitmap);
-	if (IS_ERR(vol->lcnbmp_ino) || is_bad_inode(vol->lcnbmp_ino)) {
-		if (!IS_ERR(vol->lcnbmp_ino))
-			iput(vol->lcnbmp_ino);
-		goto bitmap_failed;
-	}
-	lockdep_set_class(&NTFS_I(vol->lcnbmp_ino)->runlist.lock,
-			   &lcnbmp_runlist_lock_key);
-	lockdep_set_class(&NTFS_I(vol->lcnbmp_ino)->mrec_lock,
-			   &lcnbmp_mrec_lock_key);
-
-	NInoSetSparseDisabled(NTFS_I(vol->lcnbmp_ino));
-	if ((vol->nr_clusters + 7) >> 3 > i_size_read(vol->lcnbmp_ino)) {
-		iput(vol->lcnbmp_ino);
-bitmap_failed:
-		ntfs_error(sb, "Failed to load $Bitmap.");
-		goto iput_attrdef_err_out;
-	}
-	/*
-	 * Get the volume inode and setup our cache of the volume flags and
-	 * version.
-	 */
-	vol->vol_ino = ntfs_iget(sb, FILE_Volume);
-	if (IS_ERR(vol->vol_ino) || is_bad_inode(vol->vol_ino)) {
-		if (!IS_ERR(vol->vol_ino))
-			iput(vol->vol_ino);
-volume_failed:
-		ntfs_error(sb, "Failed to load $Volume.");
-		goto iput_lcnbmp_err_out;
-	}
-	m = map_mft_record(NTFS_I(vol->vol_ino));
-	if (IS_ERR(m)) {
-iput_volume_failed:
-		iput(vol->vol_ino);
-		goto volume_failed;
-	}
-	if (!(ctx = ntfs_attr_get_search_ctx(NTFS_I(vol->vol_ino), m))) {
-		ntfs_error(sb, "Failed to get attribute search context.");
-		goto get_ctx_vol_failed;
-	}
-	if (ntfs_attr_lookup(AT_VOLUME_INFORMATION, NULL, 0, 0, 0, NULL, 0,
-			ctx) || ctx->attr->non_resident || ctx->attr->flags) {
-err_put_vol:
-		ntfs_attr_put_search_ctx(ctx);
-get_ctx_vol_failed:
-		unmap_mft_record(NTFS_I(vol->vol_ino));
-		goto iput_volume_failed;
-	}
-	vi = (VOLUME_INFORMATION*)((char*)ctx->attr +
-			le16_to_cpu(ctx->attr->data.resident.value_offset));
-	/* Some bounds checks. */
-	if ((u8*)vi < (u8*)ctx->attr || (u8*)vi +
-			le32_to_cpu(ctx->attr->data.resident.value_length) >
-			(u8*)ctx->attr + le32_to_cpu(ctx->attr->length))
-		goto err_put_vol;
-	/* Copy the volume flags and version to the ntfs_volume structure. */
-	vol->vol_flags = vi->flags;
-	vol->major_ver = vi->major_ver;
-	vol->minor_ver = vi->minor_ver;
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(NTFS_I(vol->vol_ino));
-	pr_info("volume version %i.%i.\n", vol->major_ver,
-			vol->minor_ver);
-	if (vol->major_ver < 3 && NVolSparseEnabled(vol)) {
-		ntfs_warning(vol->sb, "Disabling sparse support due to NTFS "
-				"volume version %i.%i (need at least version "
-				"3.0).", vol->major_ver, vol->minor_ver);
-		NVolClearSparseEnabled(vol);
-	}
-#ifdef NTFS_RW
-	/* Make sure that no unsupported volume flags are set. */
-	if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) {
-		static const char *es1a = "Volume is dirty";
-		static const char *es1b = "Volume has been modified by chkdsk";
-		static const char *es1c = "Volume has unsupported flags set";
-		static const char *es2a = ".  Run chkdsk and mount in Windows.";
-		static const char *es2b = ".  Mount in Windows.";
-		const char *es1, *es2;
-
-		es2 = es2a;
-		if (vol->vol_flags & VOLUME_IS_DIRTY)
-			es1 = es1a;
-		else if (vol->vol_flags & VOLUME_MODIFIED_BY_CHKDSK) {
-			es1 = es1b;
-			es2 = es2b;
-		} else {
-			es1 = es1c;
-			ntfs_warning(sb, "Unsupported volume flags 0x%x "
-					"encountered.",
-					(unsigned)le16_to_cpu(vol->vol_flags));
-		}
-		/* If a read-write mount, convert it to a read-only mount. */
-		if (!sb_rdonly(sb)) {
-			if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-					ON_ERRORS_CONTINUE))) {
-				ntfs_error(sb, "%s and neither on_errors="
-						"continue nor on_errors="
-						"remount-ro was specified%s",
-						es1, es2);
-				goto iput_vol_err_out;
-			}
-			sb->s_flags |= SB_RDONLY;
-			ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
-		} else
-			ntfs_warning(sb, "%s.  Will not be able to remount "
-					"read-write%s", es1, es2);
-		/*
-		 * Do not set NVolErrors() because ntfs_remount() re-checks the
-		 * flags which we need to do in case any flags have changed.
-		 */
-	}
-	/*
-	 * Get the inode for the logfile, check it and determine if the volume
-	 * was shutdown cleanly.
-	 */
-	rp = NULL;
-	if (!load_and_check_logfile(vol, &rp) ||
-			!ntfs_is_logfile_clean(vol->logfile_ino, rp)) {
-		static const char *es1a = "Failed to load $LogFile";
-		static const char *es1b = "$LogFile is not clean";
-		static const char *es2 = ".  Mount in Windows.";
-		const char *es1;
-
-		es1 = !vol->logfile_ino ? es1a : es1b;
-		/* If a read-write mount, convert it to a read-only mount. */
-		if (!sb_rdonly(sb)) {
-			if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-					ON_ERRORS_CONTINUE))) {
-				ntfs_error(sb, "%s and neither on_errors="
-						"continue nor on_errors="
-						"remount-ro was specified%s",
-						es1, es2);
-				if (vol->logfile_ino) {
-					BUG_ON(!rp);
-					ntfs_free(rp);
-				}
-				goto iput_logfile_err_out;
-			}
-			sb->s_flags |= SB_RDONLY;
-			ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
-		} else
-			ntfs_warning(sb, "%s.  Will not be able to remount "
-					"read-write%s", es1, es2);
-		/* This will prevent a read-write remount. */
-		NVolSetErrors(vol);
-	}
-	ntfs_free(rp);
-#endif /* NTFS_RW */
-	/* Get the root directory inode so we can do path lookups. */
-	vol->root_ino = ntfs_iget(sb, FILE_root);
-	if (IS_ERR(vol->root_ino) || is_bad_inode(vol->root_ino)) {
-		if (!IS_ERR(vol->root_ino))
-			iput(vol->root_ino);
-		ntfs_error(sb, "Failed to load root directory.");
-		goto iput_logfile_err_out;
-	}
-#ifdef NTFS_RW
-	/*
-	 * Check if Windows is suspended to disk on the target volume.  If it
-	 * is hibernated, we must not write *anything* to the disk so set
-	 * NVolErrors() without setting the dirty volume flag and mount
-	 * read-only.  This will prevent read-write remounting and it will also
-	 * prevent all writes.
-	 */
-	err = check_windows_hibernation_status(vol);
-	if (unlikely(err)) {
-		static const char *es1a = "Failed to determine if Windows is "
-				"hibernated";
-		static const char *es1b = "Windows is hibernated";
-		static const char *es2 = ".  Run chkdsk.";
-		const char *es1;
-
-		es1 = err < 0 ? es1a : es1b;
-		/* If a read-write mount, convert it to a read-only mount. */
-		if (!sb_rdonly(sb)) {
-			if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-					ON_ERRORS_CONTINUE))) {
-				ntfs_error(sb, "%s and neither on_errors="
-						"continue nor on_errors="
-						"remount-ro was specified%s",
-						es1, es2);
-				goto iput_root_err_out;
-			}
-			sb->s_flags |= SB_RDONLY;
-			ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
-		} else
-			ntfs_warning(sb, "%s.  Will not be able to remount "
-					"read-write%s", es1, es2);
-		/* This will prevent a read-write remount. */
-		NVolSetErrors(vol);
-	}
-	/* If (still) a read-write mount, mark the volume dirty. */
-	if (!sb_rdonly(sb) && ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY)) {
-		static const char *es1 = "Failed to set dirty bit in volume "
-				"information flags";
-		static const char *es2 = ".  Run chkdsk.";
-
-		/* Convert to a read-only mount. */
-		if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-				ON_ERRORS_CONTINUE))) {
-			ntfs_error(sb, "%s and neither on_errors=continue nor "
-					"on_errors=remount-ro was specified%s",
-					es1, es2);
-			goto iput_root_err_out;
-		}
-		ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
-		sb->s_flags |= SB_RDONLY;
-		/*
-		 * Do not set NVolErrors() because ntfs_remount() might manage
-		 * to set the dirty flag in which case all would be well.
-		 */
-	}
-#if 0
-	// TODO: Enable this code once we start modifying anything that is
-	//	 different between NTFS 1.2 and 3.x...
-	/*
-	 * If (still) a read-write mount, set the NT4 compatibility flag on
-	 * newer NTFS version volumes.
-	 */
-	if (!(sb->s_flags & SB_RDONLY) && (vol->major_ver > 1) &&
-			ntfs_set_volume_flags(vol, VOLUME_MOUNTED_ON_NT4)) {
-		static const char *es1 = "Failed to set NT4 compatibility flag";
-		static const char *es2 = ".  Run chkdsk.";
-
-		/* Convert to a read-only mount. */
-		if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-				ON_ERRORS_CONTINUE))) {
-			ntfs_error(sb, "%s and neither on_errors=continue nor "
-					"on_errors=remount-ro was specified%s",
-					es1, es2);
-			goto iput_root_err_out;
-		}
-		ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
-		sb->s_flags |= SB_RDONLY;
-		NVolSetErrors(vol);
-	}
-#endif
-	/* If (still) a read-write mount, empty the logfile. */
-	if (!sb_rdonly(sb) && !ntfs_empty_logfile(vol->logfile_ino)) {
-		static const char *es1 = "Failed to empty $LogFile";
-		static const char *es2 = ".  Mount in Windows.";
-
-		/* Convert to a read-only mount. */
-		if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-				ON_ERRORS_CONTINUE))) {
-			ntfs_error(sb, "%s and neither on_errors=continue nor "
-					"on_errors=remount-ro was specified%s",
-					es1, es2);
-			goto iput_root_err_out;
-		}
-		ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
-		sb->s_flags |= SB_RDONLY;
-		NVolSetErrors(vol);
-	}
-#endif /* NTFS_RW */
-	/* If on NTFS versions before 3.0, we are done. */
-	if (unlikely(vol->major_ver < 3))
-		return true;
-	/* NTFS 3.0+ specific initialization. */
-	/* Get the security descriptors inode. */
-	vol->secure_ino = ntfs_iget(sb, FILE_Secure);
-	if (IS_ERR(vol->secure_ino) || is_bad_inode(vol->secure_ino)) {
-		if (!IS_ERR(vol->secure_ino))
-			iput(vol->secure_ino);
-		ntfs_error(sb, "Failed to load $Secure.");
-		goto iput_root_err_out;
-	}
-	// TODO: Initialize security.
-	/* Get the extended system files' directory inode. */
-	vol->extend_ino = ntfs_iget(sb, FILE_Extend);
-	if (IS_ERR(vol->extend_ino) || is_bad_inode(vol->extend_ino) ||
-	    !S_ISDIR(vol->extend_ino->i_mode)) {
-		if (!IS_ERR(vol->extend_ino))
-			iput(vol->extend_ino);
-		ntfs_error(sb, "Failed to load $Extend.");
-		goto iput_sec_err_out;
-	}
-#ifdef NTFS_RW
-	/* Find the quota file, load it if present, and set it up. */
-	if (!load_and_init_quota(vol)) {
-		static const char *es1 = "Failed to load $Quota";
-		static const char *es2 = ".  Run chkdsk.";
-
-		/* If a read-write mount, convert it to a read-only mount. */
-		if (!sb_rdonly(sb)) {
-			if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-					ON_ERRORS_CONTINUE))) {
-				ntfs_error(sb, "%s and neither on_errors="
-						"continue nor on_errors="
-						"remount-ro was specified%s",
-						es1, es2);
-				goto iput_quota_err_out;
-			}
-			sb->s_flags |= SB_RDONLY;
-			ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
-		} else
-			ntfs_warning(sb, "%s.  Will not be able to remount "
-					"read-write%s", es1, es2);
-		/* This will prevent a read-write remount. */
-		NVolSetErrors(vol);
-	}
-	/* If (still) a read-write mount, mark the quotas out of date. */
-	if (!sb_rdonly(sb) && !ntfs_mark_quotas_out_of_date(vol)) {
-		static const char *es1 = "Failed to mark quotas out of date";
-		static const char *es2 = ".  Run chkdsk.";
-
-		/* Convert to a read-only mount. */
-		if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-				ON_ERRORS_CONTINUE))) {
-			ntfs_error(sb, "%s and neither on_errors=continue nor "
-					"on_errors=remount-ro was specified%s",
-					es1, es2);
-			goto iput_quota_err_out;
-		}
-		ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
-		sb->s_flags |= SB_RDONLY;
-		NVolSetErrors(vol);
-	}
-	/*
-	 * Find the transaction log file ($UsnJrnl), load it if present, check
-	 * it, and set it up.
-	 */
-	if (!load_and_init_usnjrnl(vol)) {
-		static const char *es1 = "Failed to load $UsnJrnl";
-		static const char *es2 = ".  Run chkdsk.";
-
-		/* If a read-write mount, convert it to a read-only mount. */
-		if (!sb_rdonly(sb)) {
-			if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-					ON_ERRORS_CONTINUE))) {
-				ntfs_error(sb, "%s and neither on_errors="
-						"continue nor on_errors="
-						"remount-ro was specified%s",
-						es1, es2);
-				goto iput_usnjrnl_err_out;
-			}
-			sb->s_flags |= SB_RDONLY;
-			ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
-		} else
-			ntfs_warning(sb, "%s.  Will not be able to remount "
-					"read-write%s", es1, es2);
-		/* This will prevent a read-write remount. */
-		NVolSetErrors(vol);
-	}
-	/* If (still) a read-write mount, stamp the transaction log. */
-	if (!sb_rdonly(sb) && !ntfs_stamp_usnjrnl(vol)) {
-		static const char *es1 = "Failed to stamp transaction log "
-				"($UsnJrnl)";
-		static const char *es2 = ".  Run chkdsk.";
-
-		/* Convert to a read-only mount. */
-		if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-				ON_ERRORS_CONTINUE))) {
-			ntfs_error(sb, "%s and neither on_errors=continue nor "
-					"on_errors=remount-ro was specified%s",
-					es1, es2);
-			goto iput_usnjrnl_err_out;
-		}
-		ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
-		sb->s_flags |= SB_RDONLY;
-		NVolSetErrors(vol);
-	}
-#endif /* NTFS_RW */
-	return true;
-#ifdef NTFS_RW
-iput_usnjrnl_err_out:
-	iput(vol->usnjrnl_j_ino);
-	iput(vol->usnjrnl_max_ino);
-	iput(vol->usnjrnl_ino);
-iput_quota_err_out:
-	iput(vol->quota_q_ino);
-	iput(vol->quota_ino);
-	iput(vol->extend_ino);
-#endif /* NTFS_RW */
-iput_sec_err_out:
-	iput(vol->secure_ino);
-iput_root_err_out:
-	iput(vol->root_ino);
-iput_logfile_err_out:
-#ifdef NTFS_RW
-	iput(vol->logfile_ino);
-iput_vol_err_out:
-#endif /* NTFS_RW */
-	iput(vol->vol_ino);
-iput_lcnbmp_err_out:
-	iput(vol->lcnbmp_ino);
-iput_attrdef_err_out:
-	vol->attrdef_size = 0;
-	if (vol->attrdef) {
-		ntfs_free(vol->attrdef);
-		vol->attrdef = NULL;
-	}
-#ifdef NTFS_RW
-iput_upcase_err_out:
-#endif /* NTFS_RW */
-	vol->upcase_len = 0;
-	mutex_lock(&ntfs_lock);
-	if (vol->upcase == default_upcase) {
-		ntfs_nr_upcase_users--;
-		vol->upcase = NULL;
-	}
-	mutex_unlock(&ntfs_lock);
-	if (vol->upcase) {
-		ntfs_free(vol->upcase);
-		vol->upcase = NULL;
-	}
-iput_mftbmp_err_out:
-	iput(vol->mftbmp_ino);
-iput_mirr_err_out:
-#ifdef NTFS_RW
-	iput(vol->mftmirr_ino);
-#endif /* NTFS_RW */
-	return false;
-}
-
-/**
- * ntfs_put_super - called by the vfs to unmount a volume
- * @sb:		vfs superblock of volume to unmount
- *
- * ntfs_put_super() is called by the VFS (from fs/super.c::do_umount()) when
- * the volume is being unmounted (umount system call has been invoked) and it
- * releases all inodes and memory belonging to the NTFS specific part of the
- * super block.
- */
-static void ntfs_put_super(struct super_block *sb)
-{
-	ntfs_volume *vol = NTFS_SB(sb);
-
-	ntfs_debug("Entering.");
-
-#ifdef NTFS_RW
-	/*
-	 * Commit all inodes while they are still open in case some of them
-	 * cause others to be dirtied.
-	 */
-	ntfs_commit_inode(vol->vol_ino);
-
-	/* NTFS 3.0+ specific. */
-	if (vol->major_ver >= 3) {
-		if (vol->usnjrnl_j_ino)
-			ntfs_commit_inode(vol->usnjrnl_j_ino);
-		if (vol->usnjrnl_max_ino)
-			ntfs_commit_inode(vol->usnjrnl_max_ino);
-		if (vol->usnjrnl_ino)
-			ntfs_commit_inode(vol->usnjrnl_ino);
-		if (vol->quota_q_ino)
-			ntfs_commit_inode(vol->quota_q_ino);
-		if (vol->quota_ino)
-			ntfs_commit_inode(vol->quota_ino);
-		if (vol->extend_ino)
-			ntfs_commit_inode(vol->extend_ino);
-		if (vol->secure_ino)
-			ntfs_commit_inode(vol->secure_ino);
-	}
-
-	ntfs_commit_inode(vol->root_ino);
-
-	down_write(&vol->lcnbmp_lock);
-	ntfs_commit_inode(vol->lcnbmp_ino);
-	up_write(&vol->lcnbmp_lock);
-
-	down_write(&vol->mftbmp_lock);
-	ntfs_commit_inode(vol->mftbmp_ino);
-	up_write(&vol->mftbmp_lock);
-
-	if (vol->logfile_ino)
-		ntfs_commit_inode(vol->logfile_ino);
-
-	if (vol->mftmirr_ino)
-		ntfs_commit_inode(vol->mftmirr_ino);
-	ntfs_commit_inode(vol->mft_ino);
-
-	/*
-	 * If a read-write mount and no volume errors have occurred, mark the
-	 * volume clean.  Also, re-commit all affected inodes.
-	 */
-	if (!sb_rdonly(sb)) {
-		if (!NVolErrors(vol)) {
-			if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY))
-				ntfs_warning(sb, "Failed to clear dirty bit "
-						"in volume information "
-						"flags.  Run chkdsk.");
-			ntfs_commit_inode(vol->vol_ino);
-			ntfs_commit_inode(vol->root_ino);
-			if (vol->mftmirr_ino)
-				ntfs_commit_inode(vol->mftmirr_ino);
-			ntfs_commit_inode(vol->mft_ino);
-		} else {
-			ntfs_warning(sb, "Volume has errors.  Leaving volume "
-					"marked dirty.  Run chkdsk.");
-		}
-	}
-#endif /* NTFS_RW */
-
-	iput(vol->vol_ino);
-	vol->vol_ino = NULL;
-
-	/* NTFS 3.0+ specific clean up. */
-	if (vol->major_ver >= 3) {
-#ifdef NTFS_RW
-		if (vol->usnjrnl_j_ino) {
-			iput(vol->usnjrnl_j_ino);
-			vol->usnjrnl_j_ino = NULL;
-		}
-		if (vol->usnjrnl_max_ino) {
-			iput(vol->usnjrnl_max_ino);
-			vol->usnjrnl_max_ino = NULL;
-		}
-		if (vol->usnjrnl_ino) {
-			iput(vol->usnjrnl_ino);
-			vol->usnjrnl_ino = NULL;
-		}
-		if (vol->quota_q_ino) {
-			iput(vol->quota_q_ino);
-			vol->quota_q_ino = NULL;
-		}
-		if (vol->quota_ino) {
-			iput(vol->quota_ino);
-			vol->quota_ino = NULL;
-		}
-#endif /* NTFS_RW */
-		if (vol->extend_ino) {
-			iput(vol->extend_ino);
-			vol->extend_ino = NULL;
-		}
-		if (vol->secure_ino) {
-			iput(vol->secure_ino);
-			vol->secure_ino = NULL;
-		}
-	}
-
-	iput(vol->root_ino);
-	vol->root_ino = NULL;
-
-	down_write(&vol->lcnbmp_lock);
-	iput(vol->lcnbmp_ino);
-	vol->lcnbmp_ino = NULL;
-	up_write(&vol->lcnbmp_lock);
-
-	down_write(&vol->mftbmp_lock);
-	iput(vol->mftbmp_ino);
-	vol->mftbmp_ino = NULL;
-	up_write(&vol->mftbmp_lock);
-
-#ifdef NTFS_RW
-	if (vol->logfile_ino) {
-		iput(vol->logfile_ino);
-		vol->logfile_ino = NULL;
-	}
-	if (vol->mftmirr_ino) {
-		/* Re-commit the mft mirror and mft just in case. */
-		ntfs_commit_inode(vol->mftmirr_ino);
-		ntfs_commit_inode(vol->mft_ino);
-		iput(vol->mftmirr_ino);
-		vol->mftmirr_ino = NULL;
-	}
-	/*
-	 * We should have no dirty inodes left, due to
-	 * mft.c::ntfs_mft_writepage() cleaning all the dirty pages as
-	 * the underlying mft records are written out and cleaned.
-	 */
-	ntfs_commit_inode(vol->mft_ino);
-	write_inode_now(vol->mft_ino, 1);
-#endif /* NTFS_RW */
-
-	iput(vol->mft_ino);
-	vol->mft_ino = NULL;
-
-	/* Throw away the table of attribute definitions. */
-	vol->attrdef_size = 0;
-	if (vol->attrdef) {
-		ntfs_free(vol->attrdef);
-		vol->attrdef = NULL;
-	}
-	vol->upcase_len = 0;
-	/*
-	 * Destroy the global default upcase table if necessary.  Also decrease
-	 * the number of upcase users if we are a user.
-	 */
-	mutex_lock(&ntfs_lock);
-	if (vol->upcase == default_upcase) {
-		ntfs_nr_upcase_users--;
-		vol->upcase = NULL;
-	}
-	if (!ntfs_nr_upcase_users && default_upcase) {
-		ntfs_free(default_upcase);
-		default_upcase = NULL;
-	}
-	if (vol->cluster_size <= 4096 && !--ntfs_nr_compression_users)
-		free_compression_buffers();
-	mutex_unlock(&ntfs_lock);
-	if (vol->upcase) {
-		ntfs_free(vol->upcase);
-		vol->upcase = NULL;
-	}
-
-	unload_nls(vol->nls_map);
-
-	sb->s_fs_info = NULL;
-	kfree(vol);
-}
-
-/**
- * get_nr_free_clusters - return the number of free clusters on a volume
- * @vol:	ntfs volume for which to obtain free cluster count
- *
- * Calculate the number of free clusters on the mounted NTFS volume @vol. We
- * actually calculate the number of clusters in use instead because this
- * allows us to not care about partial pages as these will be just zero filled
- * and hence not be counted as allocated clusters.
- *
- * The only particularity is that clusters beyond the end of the logical ntfs
- * volume will be marked as allocated to prevent errors which means we have to
- * discount those at the end. This is important as the cluster bitmap always
- * has a size in multiples of 8 bytes, i.e. up to 63 clusters could be outside
- * the logical volume and marked in use when they are not as they do not exist.
- *
- * If any pages cannot be read we assume all clusters in the erroring pages are
- * in use. This means we return an underestimate on errors which is better than
- * an overestimate.
- */
-static s64 get_nr_free_clusters(ntfs_volume *vol)
-{
-	s64 nr_free = vol->nr_clusters;
-	struct address_space *mapping = vol->lcnbmp_ino->i_mapping;
-	struct page *page;
-	pgoff_t index, max_index;
-
-	ntfs_debug("Entering.");
-	/* Serialize accesses to the cluster bitmap. */
-	down_read(&vol->lcnbmp_lock);
-	/*
-	 * Convert the number of bits into bytes rounded up, then convert into
-	 * multiples of PAGE_SIZE, rounding up so that if we have one
-	 * full and one partial page max_index = 2.
-	 */
-	max_index = (((vol->nr_clusters + 7) >> 3) + PAGE_SIZE - 1) >>
-			PAGE_SHIFT;
-	/* Use multiples of 4 bytes, thus max_size is PAGE_SIZE / 4. */
-	ntfs_debug("Reading $Bitmap, max_index = 0x%lx, max_size = 0x%lx.",
-			max_index, PAGE_SIZE / 4);
-	for (index = 0; index < max_index; index++) {
-		unsigned long *kaddr;
-
-		/*
-		 * Read the page from page cache, getting it from backing store
-		 * if necessary, and increment the use count.
-		 */
-		page = read_mapping_page(mapping, index, NULL);
-		/* Ignore pages which errored synchronously. */
-		if (IS_ERR(page)) {
-			ntfs_debug("read_mapping_page() error. Skipping "
-					"page (index 0x%lx).", index);
-			nr_free -= PAGE_SIZE * 8;
-			continue;
-		}
-		kaddr = kmap_atomic(page);
-		/*
-		 * Subtract the number of set bits. If this
-		 * is the last page and it is partial we don't really care as
-		 * it just means we do a little extra work but it won't affect
-		 * the result as all out of range bytes are set to zero by
-		 * ntfs_readpage().
-		 */
-		nr_free -= bitmap_weight(kaddr,
-					PAGE_SIZE * BITS_PER_BYTE);
-		kunmap_atomic(kaddr);
-		put_page(page);
-	}
-	ntfs_debug("Finished reading $Bitmap, last index = 0x%lx.", index - 1);
-	/*
-	 * Fixup for eventual bits outside logical ntfs volume (see function
-	 * description above).
-	 */
-	if (vol->nr_clusters & 63)
-		nr_free += 64 - (vol->nr_clusters & 63);
-	up_read(&vol->lcnbmp_lock);
-	/* If errors occurred we may well have gone below zero, fix this. */
-	if (nr_free < 0)
-		nr_free = 0;
-	ntfs_debug("Exiting.");
-	return nr_free;
-}
-
-/**
- * __get_nr_free_mft_records - return the number of free inodes on a volume
- * @vol:	ntfs volume for which to obtain free inode count
- * @nr_free:	number of mft records in filesystem
- * @max_index:	maximum number of pages containing set bits
- *
- * Calculate the number of free mft records (inodes) on the mounted NTFS
- * volume @vol. We actually calculate the number of mft records in use instead
- * because this allows us to not care about partial pages as these will be just
- * zero filled and hence not be counted as allocated mft record.
- *
- * If any pages cannot be read we assume all mft records in the erroring pages
- * are in use. This means we return an underestimate on errors which is better
- * than an overestimate.
- *
- * NOTE: Caller must hold mftbmp_lock rw_semaphore for reading or writing.
- */
-static unsigned long __get_nr_free_mft_records(ntfs_volume *vol,
-		s64 nr_free, const pgoff_t max_index)
-{
-	struct address_space *mapping = vol->mftbmp_ino->i_mapping;
-	struct page *page;
-	pgoff_t index;
-
-	ntfs_debug("Entering.");
-	/* Use multiples of 4 bytes, thus max_size is PAGE_SIZE / 4. */
-	ntfs_debug("Reading $MFT/$BITMAP, max_index = 0x%lx, max_size = "
-			"0x%lx.", max_index, PAGE_SIZE / 4);
-	for (index = 0; index < max_index; index++) {
-		unsigned long *kaddr;
-
-		/*
-		 * Read the page from page cache, getting it from backing store
-		 * if necessary, and increment the use count.
-		 */
-		page = read_mapping_page(mapping, index, NULL);
-		/* Ignore pages which errored synchronously. */
-		if (IS_ERR(page)) {
-			ntfs_debug("read_mapping_page() error. Skipping "
-					"page (index 0x%lx).", index);
-			nr_free -= PAGE_SIZE * 8;
-			continue;
-		}
-		kaddr = kmap_atomic(page);
-		/*
-		 * Subtract the number of set bits. If this
-		 * is the last page and it is partial we don't really care as
-		 * it just means we do a little extra work but it won't affect
-		 * the result as all out of range bytes are set to zero by
-		 * ntfs_readpage().
-		 */
-		nr_free -= bitmap_weight(kaddr,
-					PAGE_SIZE * BITS_PER_BYTE);
-		kunmap_atomic(kaddr);
-		put_page(page);
-	}
-	ntfs_debug("Finished reading $MFT/$BITMAP, last index = 0x%lx.",
-			index - 1);
-	/* If errors occurred we may well have gone below zero, fix this. */
-	if (nr_free < 0)
-		nr_free = 0;
-	ntfs_debug("Exiting.");
-	return nr_free;
-}
-
-/**
- * ntfs_statfs - return information about mounted NTFS volume
- * @dentry:	dentry from mounted volume
- * @sfs:	statfs structure in which to return the information
- *
- * Return information about the mounted NTFS volume @dentry in the statfs structure
- * pointed to by @sfs (this is initialized with zeros before ntfs_statfs is
- * called). We interpret the values to be correct of the moment in time at
- * which we are called. Most values are variable otherwise and this isn't just
- * the free values but the totals as well. For example we can increase the
- * total number of file nodes if we run out and we can keep doing this until
- * there is no more space on the volume left at all.
- *
- * Called from vfs_statfs which is used to handle the statfs, fstatfs, and
- * ustat system calls.
- *
- * Return 0 on success or -errno on error.
- */
-static int ntfs_statfs(struct dentry *dentry, struct kstatfs *sfs)
-{
-	struct super_block *sb = dentry->d_sb;
-	s64 size;
-	ntfs_volume *vol = NTFS_SB(sb);
-	ntfs_inode *mft_ni = NTFS_I(vol->mft_ino);
-	pgoff_t max_index;
-	unsigned long flags;
-
-	ntfs_debug("Entering.");
-	/* Type of filesystem. */
-	sfs->f_type   = NTFS_SB_MAGIC;
-	/* Optimal transfer block size. */
-	sfs->f_bsize  = PAGE_SIZE;
-	/*
-	 * Total data blocks in filesystem in units of f_bsize and since
-	 * inodes are also stored in data blocs ($MFT is a file) this is just
-	 * the total clusters.
-	 */
-	sfs->f_blocks = vol->nr_clusters << vol->cluster_size_bits >>
-				PAGE_SHIFT;
-	/* Free data blocks in filesystem in units of f_bsize. */
-	size	      = get_nr_free_clusters(vol) << vol->cluster_size_bits >>
-				PAGE_SHIFT;
-	if (size < 0LL)
-		size = 0LL;
-	/* Free blocks avail to non-superuser, same as above on NTFS. */
-	sfs->f_bavail = sfs->f_bfree = size;
-	/* Serialize accesses to the inode bitmap. */
-	down_read(&vol->mftbmp_lock);
-	read_lock_irqsave(&mft_ni->size_lock, flags);
-	size = i_size_read(vol->mft_ino) >> vol->mft_record_size_bits;
-	/*
-	 * Convert the maximum number of set bits into bytes rounded up, then
-	 * convert into multiples of PAGE_SIZE, rounding up so that if we
-	 * have one full and one partial page max_index = 2.
-	 */
-	max_index = ((((mft_ni->initialized_size >> vol->mft_record_size_bits)
-			+ 7) >> 3) + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	read_unlock_irqrestore(&mft_ni->size_lock, flags);
-	/* Number of inodes in filesystem (at this point in time). */
-	sfs->f_files = size;
-	/* Free inodes in fs (based on current total count). */
-	sfs->f_ffree = __get_nr_free_mft_records(vol, size, max_index);
-	up_read(&vol->mftbmp_lock);
-	/*
-	 * File system id. This is extremely *nix flavour dependent and even
-	 * within Linux itself all fs do their own thing. I interpret this to
-	 * mean a unique id associated with the mounted fs and not the id
-	 * associated with the filesystem driver, the latter is already given
-	 * by the filesystem type in sfs->f_type. Thus we use the 64-bit
-	 * volume serial number splitting it into two 32-bit parts. We enter
-	 * the least significant 32-bits in f_fsid[0] and the most significant
-	 * 32-bits in f_fsid[1].
-	 */
-	sfs->f_fsid = u64_to_fsid(vol->serial_no);
-	/* Maximum length of filenames. */
-	sfs->f_namelen	   = NTFS_MAX_NAME_LEN;
-	return 0;
-}
-
-#ifdef NTFS_RW
-static int ntfs_write_inode(struct inode *vi, struct writeback_control *wbc)
-{
-	return __ntfs_write_inode(vi, wbc->sync_mode == WB_SYNC_ALL);
-}
-#endif
-
-/*
- * The complete super operations.
- */
-static const struct super_operations ntfs_sops = {
-	.alloc_inode	= ntfs_alloc_big_inode,	  /* VFS: Allocate new inode. */
-	.free_inode	= ntfs_free_big_inode, /* VFS: Deallocate inode. */
-#ifdef NTFS_RW
-	.write_inode	= ntfs_write_inode,	/* VFS: Write dirty inode to
-						   disk. */
-#endif /* NTFS_RW */
-	.put_super	= ntfs_put_super,	/* Syscall: umount. */
-	.statfs		= ntfs_statfs,		/* Syscall: statfs */
-	.remount_fs	= ntfs_remount,		/* Syscall: mount -o remount. */
-	.evict_inode	= ntfs_evict_big_inode,	/* VFS: Called when an inode is
-						   removed from memory. */
-	.show_options	= ntfs_show_options,	/* Show mount options in
-						   proc. */
-};
-
-/**
- * ntfs_fill_super - mount an ntfs filesystem
- * @sb:		super block of ntfs filesystem to mount
- * @opt:	string containing the mount options
- * @silent:	silence error output
- *
- * ntfs_fill_super() is called by the VFS to mount the device described by @sb
- * with the mount otions in @data with the NTFS filesystem.
- *
- * If @silent is true, remain silent even if errors are detected. This is used
- * during bootup, when the kernel tries to mount the root filesystem with all
- * registered filesystems one after the other until one succeeds. This implies
- * that all filesystems except the correct one will quite correctly and
- * expectedly return an error, but nobody wants to see error messages when in
- * fact this is what is supposed to happen.
- *
- * NOTE: @sb->s_flags contains the mount options flags.
- */
-static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent)
-{
-	ntfs_volume *vol;
-	struct buffer_head *bh;
-	struct inode *tmp_ino;
-	int blocksize, result;
-
-	/*
-	 * We do a pretty difficult piece of bootstrap by reading the
-	 * MFT (and other metadata) from disk into memory. We'll only
-	 * release this metadata during umount, so the locking patterns
-	 * observed during bootstrap do not count. So turn off the
-	 * observation of locking patterns (strictly for this context
-	 * only) while mounting NTFS. [The validator is still active
-	 * otherwise, even for this context: it will for example record
-	 * lock class registrations.]
-	 */
-	lockdep_off();
-	ntfs_debug("Entering.");
-#ifndef NTFS_RW
-	sb->s_flags |= SB_RDONLY;
-#endif /* ! NTFS_RW */
-	/* Allocate a new ntfs_volume and place it in sb->s_fs_info. */
-	sb->s_fs_info = kmalloc(sizeof(ntfs_volume), GFP_NOFS);
-	vol = NTFS_SB(sb);
-	if (!vol) {
-		if (!silent)
-			ntfs_error(sb, "Allocation of NTFS volume structure "
-					"failed. Aborting mount...");
-		lockdep_on();
-		return -ENOMEM;
-	}
-	/* Initialize ntfs_volume structure. */
-	*vol = (ntfs_volume) {
-		.sb = sb,
-		/*
-		 * Default is group and other don't have any access to files or
-		 * directories while owner has full access. Further, files by
-		 * default are not executable but directories are of course
-		 * browseable.
-		 */
-		.fmask = 0177,
-		.dmask = 0077,
-	};
-	init_rwsem(&vol->mftbmp_lock);
-	init_rwsem(&vol->lcnbmp_lock);
-
-	/* By default, enable sparse support. */
-	NVolSetSparseEnabled(vol);
-
-	/* Important to get the mount options dealt with now. */
-	if (!parse_options(vol, (char*)opt))
-		goto err_out_now;
-
-	/* We support sector sizes up to the PAGE_SIZE. */
-	if (bdev_logical_block_size(sb->s_bdev) > PAGE_SIZE) {
-		if (!silent)
-			ntfs_error(sb, "Device has unsupported sector size "
-					"(%i).  The maximum supported sector "
-					"size on this architecture is %lu "
-					"bytes.",
-					bdev_logical_block_size(sb->s_bdev),
-					PAGE_SIZE);
-		goto err_out_now;
-	}
-	/*
-	 * Setup the device access block size to NTFS_BLOCK_SIZE or the hard
-	 * sector size, whichever is bigger.
-	 */
-	blocksize = sb_min_blocksize(sb, NTFS_BLOCK_SIZE);
-	if (blocksize < NTFS_BLOCK_SIZE) {
-		if (!silent)
-			ntfs_error(sb, "Unable to set device block size.");
-		goto err_out_now;
-	}
-	BUG_ON(blocksize != sb->s_blocksize);
-	ntfs_debug("Set device block size to %i bytes (block size bits %i).",
-			blocksize, sb->s_blocksize_bits);
-	/* Determine the size of the device in units of block_size bytes. */
-	vol->nr_blocks = sb_bdev_nr_blocks(sb);
-	if (!vol->nr_blocks) {
-		if (!silent)
-			ntfs_error(sb, "Unable to determine device size.");
-		goto err_out_now;
-	}
-	/* Read the boot sector and return unlocked buffer head to it. */
-	if (!(bh = read_ntfs_boot_sector(sb, silent))) {
-		if (!silent)
-			ntfs_error(sb, "Not an NTFS volume.");
-		goto err_out_now;
-	}
-	/*
-	 * Extract the data from the boot sector and setup the ntfs volume
-	 * using it.
-	 */
-	result = parse_ntfs_boot_sector(vol, (NTFS_BOOT_SECTOR*)bh->b_data);
-	brelse(bh);
-	if (!result) {
-		if (!silent)
-			ntfs_error(sb, "Unsupported NTFS filesystem.");
-		goto err_out_now;
-	}
-	/*
-	 * If the boot sector indicates a sector size bigger than the current
-	 * device block size, switch the device block size to the sector size.
-	 * TODO: It may be possible to support this case even when the set
-	 * below fails, we would just be breaking up the i/o for each sector
-	 * into multiple blocks for i/o purposes but otherwise it should just
-	 * work.  However it is safer to leave disabled until someone hits this
-	 * error message and then we can get them to try it without the setting
-	 * so we know for sure that it works.
-	 */
-	if (vol->sector_size > blocksize) {
-		blocksize = sb_set_blocksize(sb, vol->sector_size);
-		if (blocksize != vol->sector_size) {
-			if (!silent)
-				ntfs_error(sb, "Unable to set device block "
-						"size to sector size (%i).",
-						vol->sector_size);
-			goto err_out_now;
-		}
-		BUG_ON(blocksize != sb->s_blocksize);
-		vol->nr_blocks = sb_bdev_nr_blocks(sb);
-		ntfs_debug("Changed device block size to %i bytes (block size "
-				"bits %i) to match volume sector size.",
-				blocksize, sb->s_blocksize_bits);
-	}
-	/* Initialize the cluster and mft allocators. */
-	ntfs_setup_allocators(vol);
-	/* Setup remaining fields in the super block. */
-	sb->s_magic = NTFS_SB_MAGIC;
-	/*
-	 * Ntfs allows 63 bits for the file size, i.e. correct would be:
-	 *	sb->s_maxbytes = ~0ULL >> 1;
-	 * But the kernel uses a long as the page cache page index which on
-	 * 32-bit architectures is only 32-bits. MAX_LFS_FILESIZE is kernel
-	 * defined to the maximum the page cache page index can cope with
-	 * without overflowing the index or to 2^63 - 1, whichever is smaller.
-	 */
-	sb->s_maxbytes = MAX_LFS_FILESIZE;
-	/* Ntfs measures time in 100ns intervals. */
-	sb->s_time_gran = 100;
-	/*
-	 * Now load the metadata required for the page cache and our address
-	 * space operations to function. We do this by setting up a specialised
-	 * read_inode method and then just calling the normal iget() to obtain
-	 * the inode for $MFT which is sufficient to allow our normal inode
-	 * operations and associated address space operations to function.
-	 */
-	sb->s_op = &ntfs_sops;
-	tmp_ino = new_inode(sb);
-	if (!tmp_ino) {
-		if (!silent)
-			ntfs_error(sb, "Failed to load essential metadata.");
-		goto err_out_now;
-	}
-	tmp_ino->i_ino = FILE_MFT;
-	insert_inode_hash(tmp_ino);
-	if (ntfs_read_inode_mount(tmp_ino) < 0) {
-		if (!silent)
-			ntfs_error(sb, "Failed to load essential metadata.");
-		goto iput_tmp_ino_err_out_now;
-	}
-	mutex_lock(&ntfs_lock);
-	/*
-	 * The current mount is a compression user if the cluster size is
-	 * less than or equal 4kiB.
-	 */
-	if (vol->cluster_size <= 4096 && !ntfs_nr_compression_users++) {
-		result = allocate_compression_buffers();
-		if (result) {
-			ntfs_error(NULL, "Failed to allocate buffers "
-					"for compression engine.");
-			ntfs_nr_compression_users--;
-			mutex_unlock(&ntfs_lock);
-			goto iput_tmp_ino_err_out_now;
-		}
-	}
-	/*
-	 * Generate the global default upcase table if necessary.  Also
-	 * temporarily increment the number of upcase users to avoid race
-	 * conditions with concurrent (u)mounts.
-	 */
-	if (!default_upcase)
-		default_upcase = generate_default_upcase();
-	ntfs_nr_upcase_users++;
-	mutex_unlock(&ntfs_lock);
-	/*
-	 * From now on, ignore @silent parameter. If we fail below this line,
-	 * it will be due to a corrupt fs or a system error, so we report it.
-	 */
-	/*
-	 * Open the system files with normal access functions and complete
-	 * setting up the ntfs super block.
-	 */
-	if (!load_system_files(vol)) {
-		ntfs_error(sb, "Failed to load system files.");
-		goto unl_upcase_iput_tmp_ino_err_out_now;
-	}
-
-	/* We grab a reference, simulating an ntfs_iget(). */
-	ihold(vol->root_ino);
-	if ((sb->s_root = d_make_root(vol->root_ino))) {
-		ntfs_debug("Exiting, status successful.");
-		/* Release the default upcase if it has no users. */
-		mutex_lock(&ntfs_lock);
-		if (!--ntfs_nr_upcase_users && default_upcase) {
-			ntfs_free(default_upcase);
-			default_upcase = NULL;
-		}
-		mutex_unlock(&ntfs_lock);
-		sb->s_export_op = &ntfs_export_ops;
-		lockdep_on();
-		return 0;
-	}
-	ntfs_error(sb, "Failed to allocate root directory.");
-	/* Clean up after the successful load_system_files() call from above. */
-	// TODO: Use ntfs_put_super() instead of repeating all this code...
-	// FIXME: Should mark the volume clean as the error is most likely
-	// 	  -ENOMEM.
-	iput(vol->vol_ino);
-	vol->vol_ino = NULL;
-	/* NTFS 3.0+ specific clean up. */
-	if (vol->major_ver >= 3) {
-#ifdef NTFS_RW
-		if (vol->usnjrnl_j_ino) {
-			iput(vol->usnjrnl_j_ino);
-			vol->usnjrnl_j_ino = NULL;
-		}
-		if (vol->usnjrnl_max_ino) {
-			iput(vol->usnjrnl_max_ino);
-			vol->usnjrnl_max_ino = NULL;
-		}
-		if (vol->usnjrnl_ino) {
-			iput(vol->usnjrnl_ino);
-			vol->usnjrnl_ino = NULL;
-		}
-		if (vol->quota_q_ino) {
-			iput(vol->quota_q_ino);
-			vol->quota_q_ino = NULL;
-		}
-		if (vol->quota_ino) {
-			iput(vol->quota_ino);
-			vol->quota_ino = NULL;
-		}
-#endif /* NTFS_RW */
-		if (vol->extend_ino) {
-			iput(vol->extend_ino);
-			vol->extend_ino = NULL;
-		}
-		if (vol->secure_ino) {
-			iput(vol->secure_ino);
-			vol->secure_ino = NULL;
-		}
-	}
-	iput(vol->root_ino);
-	vol->root_ino = NULL;
-	iput(vol->lcnbmp_ino);
-	vol->lcnbmp_ino = NULL;
-	iput(vol->mftbmp_ino);
-	vol->mftbmp_ino = NULL;
-#ifdef NTFS_RW
-	if (vol->logfile_ino) {
-		iput(vol->logfile_ino);
-		vol->logfile_ino = NULL;
-	}
-	if (vol->mftmirr_ino) {
-		iput(vol->mftmirr_ino);
-		vol->mftmirr_ino = NULL;
-	}
-#endif /* NTFS_RW */
-	/* Throw away the table of attribute definitions. */
-	vol->attrdef_size = 0;
-	if (vol->attrdef) {
-		ntfs_free(vol->attrdef);
-		vol->attrdef = NULL;
-	}
-	vol->upcase_len = 0;
-	mutex_lock(&ntfs_lock);
-	if (vol->upcase == default_upcase) {
-		ntfs_nr_upcase_users--;
-		vol->upcase = NULL;
-	}
-	mutex_unlock(&ntfs_lock);
-	if (vol->upcase) {
-		ntfs_free(vol->upcase);
-		vol->upcase = NULL;
-	}
-	if (vol->nls_map) {
-		unload_nls(vol->nls_map);
-		vol->nls_map = NULL;
-	}
-	/* Error exit code path. */
-unl_upcase_iput_tmp_ino_err_out_now:
-	/*
-	 * Decrease the number of upcase users and destroy the global default
-	 * upcase table if necessary.
-	 */
-	mutex_lock(&ntfs_lock);
-	if (!--ntfs_nr_upcase_users && default_upcase) {
-		ntfs_free(default_upcase);
-		default_upcase = NULL;
-	}
-	if (vol->cluster_size <= 4096 && !--ntfs_nr_compression_users)
-		free_compression_buffers();
-	mutex_unlock(&ntfs_lock);
-iput_tmp_ino_err_out_now:
-	iput(tmp_ino);
-	if (vol->mft_ino && vol->mft_ino != tmp_ino)
-		iput(vol->mft_ino);
-	vol->mft_ino = NULL;
-	/* Errors at this stage are irrelevant. */
-err_out_now:
-	sb->s_fs_info = NULL;
-	kfree(vol);
-	ntfs_debug("Failed, returning -EINVAL.");
-	lockdep_on();
-	return -EINVAL;
-}
-
-/*
- * This is a slab cache to optimize allocations and deallocations of Unicode
- * strings of the maximum length allowed by NTFS, which is NTFS_MAX_NAME_LEN
- * (255) Unicode characters + a terminating NULL Unicode character.
- */
-struct kmem_cache *ntfs_name_cache;
-
-/* Slab caches for efficient allocation/deallocation of inodes. */
-struct kmem_cache *ntfs_inode_cache;
-struct kmem_cache *ntfs_big_inode_cache;
-
-/* Init once constructor for the inode slab cache. */
-static void ntfs_big_inode_init_once(void *foo)
-{
-	ntfs_inode *ni = (ntfs_inode *)foo;
-
-	inode_init_once(VFS_I(ni));
-}
-
-/*
- * Slab caches to optimize allocations and deallocations of attribute search
- * contexts and index contexts, respectively.
- */
-struct kmem_cache *ntfs_attr_ctx_cache;
-struct kmem_cache *ntfs_index_ctx_cache;
-
-/* Driver wide mutex. */
-DEFINE_MUTEX(ntfs_lock);
-
-static struct dentry *ntfs_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
-{
-	return mount_bdev(fs_type, flags, dev_name, data, ntfs_fill_super);
-}
-
-static struct file_system_type ntfs_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "ntfs",
-	.mount		= ntfs_mount,
-	.kill_sb	= kill_block_super,
-	.fs_flags	= FS_REQUIRES_DEV,
-};
-MODULE_ALIAS_FS("ntfs");
-
-/* Stable names for the slab caches. */
-static const char ntfs_index_ctx_cache_name[] = "ntfs_index_ctx_cache";
-static const char ntfs_attr_ctx_cache_name[] = "ntfs_attr_ctx_cache";
-static const char ntfs_name_cache_name[] = "ntfs_name_cache";
-static const char ntfs_inode_cache_name[] = "ntfs_inode_cache";
-static const char ntfs_big_inode_cache_name[] = "ntfs_big_inode_cache";
-
-static int __init init_ntfs_fs(void)
-{
-	int err = 0;
-
-	/* This may be ugly but it results in pretty output so who cares. (-8 */
-	pr_info("driver " NTFS_VERSION " [Flags: R/"
-#ifdef NTFS_RW
-			"W"
-#else
-			"O"
-#endif
-#ifdef DEBUG
-			" DEBUG"
-#endif
-#ifdef MODULE
-			" MODULE"
-#endif
-			"].\n");
-
-	ntfs_debug("Debug messages are enabled.");
-
-	ntfs_index_ctx_cache = kmem_cache_create(ntfs_index_ctx_cache_name,
-			sizeof(ntfs_index_context), 0 /* offset */,
-			SLAB_HWCACHE_ALIGN, NULL /* ctor */);
-	if (!ntfs_index_ctx_cache) {
-		pr_crit("Failed to create %s!\n", ntfs_index_ctx_cache_name);
-		goto ictx_err_out;
-	}
-	ntfs_attr_ctx_cache = kmem_cache_create(ntfs_attr_ctx_cache_name,
-			sizeof(ntfs_attr_search_ctx), 0 /* offset */,
-			SLAB_HWCACHE_ALIGN, NULL /* ctor */);
-	if (!ntfs_attr_ctx_cache) {
-		pr_crit("NTFS: Failed to create %s!\n",
-			ntfs_attr_ctx_cache_name);
-		goto actx_err_out;
-	}
-
-	ntfs_name_cache = kmem_cache_create(ntfs_name_cache_name,
-			(NTFS_MAX_NAME_LEN+1) * sizeof(ntfschar), 0,
-			SLAB_HWCACHE_ALIGN, NULL);
-	if (!ntfs_name_cache) {
-		pr_crit("Failed to create %s!\n", ntfs_name_cache_name);
-		goto name_err_out;
-	}
-
-	ntfs_inode_cache = kmem_cache_create(ntfs_inode_cache_name,
-			sizeof(ntfs_inode), 0,
-			SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
-	if (!ntfs_inode_cache) {
-		pr_crit("Failed to create %s!\n", ntfs_inode_cache_name);
-		goto inode_err_out;
-	}
-
-	ntfs_big_inode_cache = kmem_cache_create(ntfs_big_inode_cache_name,
-			sizeof(big_ntfs_inode), 0,
-			SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|
-			SLAB_ACCOUNT, ntfs_big_inode_init_once);
-	if (!ntfs_big_inode_cache) {
-		pr_crit("Failed to create %s!\n", ntfs_big_inode_cache_name);
-		goto big_inode_err_out;
-	}
-
-	/* Register the ntfs sysctls. */
-	err = ntfs_sysctl(1);
-	if (err) {
-		pr_crit("Failed to register NTFS sysctls!\n");
-		goto sysctl_err_out;
-	}
-
-	err = register_filesystem(&ntfs_fs_type);
-	if (!err) {
-		ntfs_debug("NTFS driver registered successfully.");
-		return 0; /* Success! */
-	}
-	pr_crit("Failed to register NTFS filesystem driver!\n");
-
-	/* Unregister the ntfs sysctls. */
-	ntfs_sysctl(0);
-sysctl_err_out:
-	kmem_cache_destroy(ntfs_big_inode_cache);
-big_inode_err_out:
-	kmem_cache_destroy(ntfs_inode_cache);
-inode_err_out:
-	kmem_cache_destroy(ntfs_name_cache);
-name_err_out:
-	kmem_cache_destroy(ntfs_attr_ctx_cache);
-actx_err_out:
-	kmem_cache_destroy(ntfs_index_ctx_cache);
-ictx_err_out:
-	if (!err) {
-		pr_crit("Aborting NTFS filesystem driver registration...\n");
-		err = -ENOMEM;
-	}
-	return err;
-}
-
-static void __exit exit_ntfs_fs(void)
-{
-	ntfs_debug("Unregistering NTFS driver.");
-
-	unregister_filesystem(&ntfs_fs_type);
-
-	/*
-	 * Make sure all delayed rcu free inodes are flushed before we
-	 * destroy cache.
-	 */
-	rcu_barrier();
-	kmem_cache_destroy(ntfs_big_inode_cache);
-	kmem_cache_destroy(ntfs_inode_cache);
-	kmem_cache_destroy(ntfs_name_cache);
-	kmem_cache_destroy(ntfs_attr_ctx_cache);
-	kmem_cache_destroy(ntfs_index_ctx_cache);
-	/* Unregister the ntfs sysctls. */
-	ntfs_sysctl(0);
-}
-
-MODULE_AUTHOR("Anton Altaparmakov <anton@tuxera.com>");
-MODULE_DESCRIPTION("NTFS 1.2/3.x driver - Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc.");
-MODULE_VERSION(NTFS_VERSION);
-MODULE_LICENSE("GPL");
-#ifdef DEBUG
-module_param(debug_msgs, bint, 0);
-MODULE_PARM_DESC(debug_msgs, "Enable debug messages.");
-#endif
-
-module_init(init_ntfs_fs)
-module_exit(exit_ntfs_fs)
diff --git a/fs/ntfs/sysctl.c b/fs/ntfs/sysctl.c
deleted file mode 100644
index 4e980170d86a..000000000000
--- a/fs/ntfs/sysctl.c
+++ /dev/null
@@ -1,58 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * sysctl.c - Code for sysctl handling in NTFS Linux kernel driver. Part of
- *	      the Linux-NTFS project. Adapted from the old NTFS driver,
- *	      Copyright (C) 1997 Martin von Löwis, Régis Duchesne
- *
- * Copyright (c) 2002-2005 Anton Altaparmakov
- */
-
-#ifdef DEBUG
-
-#include <linux/module.h>
-
-#ifdef CONFIG_SYSCTL
-
-#include <linux/proc_fs.h>
-#include <linux/sysctl.h>
-
-#include "sysctl.h"
-#include "debug.h"
-
-/* Definition of the ntfs sysctl. */
-static struct ctl_table ntfs_sysctls[] = {
-	{
-		.procname	= "ntfs-debug",
-		.data		= &debug_msgs,		/* Data pointer and size. */
-		.maxlen		= sizeof(debug_msgs),
-		.mode		= 0644,			/* Mode, proc handler. */
-		.proc_handler	= proc_dointvec
-	},
-};
-
-/* Storage for the sysctls header. */
-static struct ctl_table_header *sysctls_root_table;
-
-/**
- * ntfs_sysctl - add or remove the debug sysctl
- * @add:	add (1) or remove (0) the sysctl
- *
- * Add or remove the debug sysctl. Return 0 on success or -errno on error.
- */
-int ntfs_sysctl(int add)
-{
-	if (add) {
-		BUG_ON(sysctls_root_table);
-		sysctls_root_table = register_sysctl("fs", ntfs_sysctls);
-		if (!sysctls_root_table)
-			return -ENOMEM;
-	} else {
-		BUG_ON(!sysctls_root_table);
-		unregister_sysctl_table(sysctls_root_table);
-		sysctls_root_table = NULL;
-	}
-	return 0;
-}
-
-#endif /* CONFIG_SYSCTL */
-#endif /* DEBUG */
diff --git a/fs/ntfs/sysctl.h b/fs/ntfs/sysctl.h
deleted file mode 100644
index 96bb2299d2d5..000000000000
--- a/fs/ntfs/sysctl.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * sysctl.h - Defines for sysctl handling in NTFS Linux kernel driver. Part of
- *	      the Linux-NTFS project. Adapted from the old NTFS driver,
- *	      Copyright (C) 1997 Martin von Löwis, Régis Duchesne
- *
- * Copyright (c) 2002-2004 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_SYSCTL_H
-#define _LINUX_NTFS_SYSCTL_H
-
-
-#if defined(DEBUG) && defined(CONFIG_SYSCTL)
-
-extern int ntfs_sysctl(int add);
-
-#else
-
-/* Just return success. */
-static inline int ntfs_sysctl(int add)
-{
-	return 0;
-}
-
-#endif /* DEBUG && CONFIG_SYSCTL */
-#endif /* _LINUX_NTFS_SYSCTL_H */
diff --git a/fs/ntfs/time.h b/fs/ntfs/time.h
deleted file mode 100644
index 6b63261300cc..000000000000
--- a/fs/ntfs/time.h
+++ /dev/null
@@ -1,89 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * time.h - NTFS time conversion functions.  Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2005 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_TIME_H
-#define _LINUX_NTFS_TIME_H
-
-#include <linux/time.h>		/* For current_kernel_time(). */
-#include <asm/div64.h>		/* For do_div(). */
-
-#include "endian.h"
-
-#define NTFS_TIME_OFFSET ((s64)(369 * 365 + 89) * 24 * 3600 * 10000000)
-
-/**
- * utc2ntfs - convert Linux UTC time to NTFS time
- * @ts:		Linux UTC time to convert to NTFS time
- *
- * Convert the Linux UTC time @ts to its corresponding NTFS time and return
- * that in little endian format.
- *
- * Linux stores time in a struct timespec64 consisting of a time64_t tv_sec
- * and a long tv_nsec where tv_sec is the number of 1-second intervals since
- * 1st January 1970, 00:00:00 UTC and tv_nsec is the number of 1-nano-second
- * intervals since the value of tv_sec.
- *
- * NTFS uses Microsoft's standard time format which is stored in a s64 and is
- * measured as the number of 100-nano-second intervals since 1st January 1601,
- * 00:00:00 UTC.
- */
-static inline sle64 utc2ntfs(const struct timespec64 ts)
-{
-	/*
-	 * Convert the seconds to 100ns intervals, add the nano-seconds
-	 * converted to 100ns intervals, and then add the NTFS time offset.
-	 */
-	return cpu_to_sle64((s64)ts.tv_sec * 10000000 + ts.tv_nsec / 100 +
-			NTFS_TIME_OFFSET);
-}
-
-/**
- * get_current_ntfs_time - get the current time in little endian NTFS format
- *
- * Get the current time from the Linux kernel, convert it to its corresponding
- * NTFS time and return that in little endian format.
- */
-static inline sle64 get_current_ntfs_time(void)
-{
-	struct timespec64 ts;
-
-	ktime_get_coarse_real_ts64(&ts);
-	return utc2ntfs(ts);
-}
-
-/**
- * ntfs2utc - convert NTFS time to Linux time
- * @time:	NTFS time (little endian) to convert to Linux UTC
- *
- * Convert the little endian NTFS time @time to its corresponding Linux UTC
- * time and return that in cpu format.
- *
- * Linux stores time in a struct timespec64 consisting of a time64_t tv_sec
- * and a long tv_nsec where tv_sec is the number of 1-second intervals since
- * 1st January 1970, 00:00:00 UTC and tv_nsec is the number of 1-nano-second
- * intervals since the value of tv_sec.
- *
- * NTFS uses Microsoft's standard time format which is stored in a s64 and is
- * measured as the number of 100 nano-second intervals since 1st January 1601,
- * 00:00:00 UTC.
- */
-static inline struct timespec64 ntfs2utc(const sle64 time)
-{
-	struct timespec64 ts;
-
-	/* Subtract the NTFS time offset. */
-	u64 t = (u64)(sle64_to_cpu(time) - NTFS_TIME_OFFSET);
-	/*
-	 * Convert the time to 1-second intervals and the remainder to
-	 * 1-nano-second intervals.
-	 */
-	ts.tv_nsec = do_div(t, 10000000) * 100;
-	ts.tv_sec = t;
-	return ts;
-}
-
-#endif /* _LINUX_NTFS_TIME_H */
diff --git a/fs/ntfs/types.h b/fs/ntfs/types.h
deleted file mode 100644
index 9a47859e7a06..000000000000
--- a/fs/ntfs/types.h
+++ /dev/null
@@ -1,55 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * types.h - Defines for NTFS Linux kernel driver specific types.
- *	     Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2005 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_TYPES_H
-#define _LINUX_NTFS_TYPES_H
-
-#include <linux/types.h>
-
-typedef __le16 le16;
-typedef __le32 le32;
-typedef __le64 le64;
-typedef __u16 __bitwise sle16;
-typedef __u32 __bitwise sle32;
-typedef __u64 __bitwise sle64;
-
-/* 2-byte Unicode character type. */
-typedef le16 ntfschar;
-#define UCHAR_T_SIZE_BITS 1
-
-/*
- * Clusters are signed 64-bit values on NTFS volumes. We define two types, LCN
- * and VCN, to allow for type checking and better code readability.
- */
-typedef s64 VCN;
-typedef sle64 leVCN;
-typedef s64 LCN;
-typedef sle64 leLCN;
-
-/*
- * The NTFS journal $LogFile uses log sequence numbers which are signed 64-bit
- * values.  We define our own type LSN, to allow for type checking and better
- * code readability.
- */
-typedef s64 LSN;
-typedef sle64 leLSN;
-
-/*
- * The NTFS transaction log $UsnJrnl uses usn which are signed 64-bit values.
- * We define our own type USN, to allow for type checking and better code
- * readability.
- */
-typedef s64 USN;
-typedef sle64 leUSN;
-
-typedef enum {
-	CASE_SENSITIVE = 0,
-	IGNORE_CASE = 1,
-} IGNORE_CASE_BOOL;
-
-#endif /* _LINUX_NTFS_TYPES_H */
diff --git a/fs/ntfs/unistr.c b/fs/ntfs/unistr.c
deleted file mode 100644
index a6b6c64f14a9..000000000000
--- a/fs/ntfs/unistr.c
+++ /dev/null
@@ -1,384 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * unistr.c - NTFS Unicode string handling. Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2006 Anton Altaparmakov
- */
-
-#include <linux/slab.h>
-
-#include "types.h"
-#include "debug.h"
-#include "ntfs.h"
-
-/*
- * IMPORTANT
- * =========
- *
- * All these routines assume that the Unicode characters are in little endian
- * encoding inside the strings!!!
- */
-
-/*
- * This is used by the name collation functions to quickly determine what
- * characters are (in)valid.
- */
-static const u8 legal_ansi_char_array[0x40] = {
-	0x00, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
-	0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
-
-	0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
-	0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
-
-	0x17, 0x07, 0x18, 0x17, 0x17, 0x17, 0x17, 0x17,
-	0x17, 0x17, 0x18, 0x16, 0x16, 0x17, 0x07, 0x00,
-
-	0x17, 0x17, 0x17, 0x17, 0x17, 0x17, 0x17, 0x17,
-	0x17, 0x17, 0x04, 0x16, 0x18, 0x16, 0x18, 0x18,
-};
-
-/**
- * ntfs_are_names_equal - compare two Unicode names for equality
- * @s1:			name to compare to @s2
- * @s1_len:		length in Unicode characters of @s1
- * @s2:			name to compare to @s1
- * @s2_len:		length in Unicode characters of @s2
- * @ic:			ignore case bool
- * @upcase:		upcase table (only if @ic == IGNORE_CASE)
- * @upcase_size:	length in Unicode characters of @upcase (if present)
- *
- * Compare the names @s1 and @s2 and return 'true' (1) if the names are
- * identical, or 'false' (0) if they are not identical. If @ic is IGNORE_CASE,
- * the @upcase table is used to performa a case insensitive comparison.
- */
-bool ntfs_are_names_equal(const ntfschar *s1, size_t s1_len,
-		const ntfschar *s2, size_t s2_len, const IGNORE_CASE_BOOL ic,
-		const ntfschar *upcase, const u32 upcase_size)
-{
-	if (s1_len != s2_len)
-		return false;
-	if (ic == CASE_SENSITIVE)
-		return !ntfs_ucsncmp(s1, s2, s1_len);
-	return !ntfs_ucsncasecmp(s1, s2, s1_len, upcase, upcase_size);
-}
-
-/**
- * ntfs_collate_names - collate two Unicode names
- * @name1:	first Unicode name to compare
- * @name2:	second Unicode name to compare
- * @err_val:	if @name1 contains an invalid character return this value
- * @ic:		either CASE_SENSITIVE or IGNORE_CASE
- * @upcase:	upcase table (ignored if @ic is CASE_SENSITIVE)
- * @upcase_len:	upcase table size (ignored if @ic is CASE_SENSITIVE)
- *
- * ntfs_collate_names collates two Unicode names and returns:
- *
- *  -1 if the first name collates before the second one,
- *   0 if the names match,
- *   1 if the second name collates before the first one, or
- * @err_val if an invalid character is found in @name1 during the comparison.
- *
- * The following characters are considered invalid: '"', '*', '<', '>' and '?'.
- */
-int ntfs_collate_names(const ntfschar *name1, const u32 name1_len,
-		const ntfschar *name2, const u32 name2_len,
-		const int err_val, const IGNORE_CASE_BOOL ic,
-		const ntfschar *upcase, const u32 upcase_len)
-{
-	u32 cnt, min_len;
-	u16 c1, c2;
-
-	min_len = name1_len;
-	if (name1_len > name2_len)
-		min_len = name2_len;
-	for (cnt = 0; cnt < min_len; ++cnt) {
-		c1 = le16_to_cpu(*name1++);
-		c2 = le16_to_cpu(*name2++);
-		if (ic) {
-			if (c1 < upcase_len)
-				c1 = le16_to_cpu(upcase[c1]);
-			if (c2 < upcase_len)
-				c2 = le16_to_cpu(upcase[c2]);
-		}
-		if (c1 < 64 && legal_ansi_char_array[c1] & 8)
-			return err_val;
-		if (c1 < c2)
-			return -1;
-		if (c1 > c2)
-			return 1;
-	}
-	if (name1_len < name2_len)
-		return -1;
-	if (name1_len == name2_len)
-		return 0;
-	/* name1_len > name2_len */
-	c1 = le16_to_cpu(*name1);
-	if (c1 < 64 && legal_ansi_char_array[c1] & 8)
-		return err_val;
-	return 1;
-}
-
-/**
- * ntfs_ucsncmp - compare two little endian Unicode strings
- * @s1:		first string
- * @s2:		second string
- * @n:		maximum unicode characters to compare
- *
- * Compare the first @n characters of the Unicode strings @s1 and @s2,
- * The strings in little endian format and appropriate le16_to_cpu()
- * conversion is performed on non-little endian machines.
- *
- * The function returns an integer less than, equal to, or greater than zero
- * if @s1 (or the first @n Unicode characters thereof) is found, respectively,
- * to be less than, to match, or be greater than @s2.
- */
-int ntfs_ucsncmp(const ntfschar *s1, const ntfschar *s2, size_t n)
-{
-	u16 c1, c2;
-	size_t i;
-
-	for (i = 0; i < n; ++i) {
-		c1 = le16_to_cpu(s1[i]);
-		c2 = le16_to_cpu(s2[i]);
-		if (c1 < c2)
-			return -1;
-		if (c1 > c2)
-			return 1;
-		if (!c1)
-			break;
-	}
-	return 0;
-}
-
-/**
- * ntfs_ucsncasecmp - compare two little endian Unicode strings, ignoring case
- * @s1:			first string
- * @s2:			second string
- * @n:			maximum unicode characters to compare
- * @upcase:		upcase table
- * @upcase_size:	upcase table size in Unicode characters
- *
- * Compare the first @n characters of the Unicode strings @s1 and @s2,
- * ignoring case. The strings in little endian format and appropriate
- * le16_to_cpu() conversion is performed on non-little endian machines.
- *
- * Each character is uppercased using the @upcase table before the comparison.
- *
- * The function returns an integer less than, equal to, or greater than zero
- * if @s1 (or the first @n Unicode characters thereof) is found, respectively,
- * to be less than, to match, or be greater than @s2.
- */
-int ntfs_ucsncasecmp(const ntfschar *s1, const ntfschar *s2, size_t n,
-		const ntfschar *upcase, const u32 upcase_size)
-{
-	size_t i;
-	u16 c1, c2;
-
-	for (i = 0; i < n; ++i) {
-		if ((c1 = le16_to_cpu(s1[i])) < upcase_size)
-			c1 = le16_to_cpu(upcase[c1]);
-		if ((c2 = le16_to_cpu(s2[i])) < upcase_size)
-			c2 = le16_to_cpu(upcase[c2]);
-		if (c1 < c2)
-			return -1;
-		if (c1 > c2)
-			return 1;
-		if (!c1)
-			break;
-	}
-	return 0;
-}
-
-void ntfs_upcase_name(ntfschar *name, u32 name_len, const ntfschar *upcase,
-		const u32 upcase_len)
-{
-	u32 i;
-	u16 u;
-
-	for (i = 0; i < name_len; i++)
-		if ((u = le16_to_cpu(name[i])) < upcase_len)
-			name[i] = upcase[u];
-}
-
-void ntfs_file_upcase_value(FILE_NAME_ATTR *file_name_attr,
-		const ntfschar *upcase, const u32 upcase_len)
-{
-	ntfs_upcase_name((ntfschar*)&file_name_attr->file_name,
-			file_name_attr->file_name_length, upcase, upcase_len);
-}
-
-int ntfs_file_compare_values(FILE_NAME_ATTR *file_name_attr1,
-		FILE_NAME_ATTR *file_name_attr2,
-		const int err_val, const IGNORE_CASE_BOOL ic,
-		const ntfschar *upcase, const u32 upcase_len)
-{
-	return ntfs_collate_names((ntfschar*)&file_name_attr1->file_name,
-			file_name_attr1->file_name_length,
-			(ntfschar*)&file_name_attr2->file_name,
-			file_name_attr2->file_name_length,
-			err_val, ic, upcase, upcase_len);
-}
-
-/**
- * ntfs_nlstoucs - convert NLS string to little endian Unicode string
- * @vol:	ntfs volume which we are working with
- * @ins:	input NLS string buffer
- * @ins_len:	length of input string in bytes
- * @outs:	on return contains the allocated output Unicode string buffer
- *
- * Convert the input string @ins, which is in whatever format the loaded NLS
- * map dictates, into a little endian, 2-byte Unicode string.
- *
- * This function allocates the string and the caller is responsible for
- * calling kmem_cache_free(ntfs_name_cache, *@outs); when finished with it.
- *
- * On success the function returns the number of Unicode characters written to
- * the output string *@outs (>= 0), not counting the terminating Unicode NULL
- * character. *@outs is set to the allocated output string buffer.
- *
- * On error, a negative number corresponding to the error code is returned. In
- * that case the output string is not allocated. Both *@outs and *@outs_len
- * are then undefined.
- *
- * This might look a bit odd due to fast path optimization...
- */
-int ntfs_nlstoucs(const ntfs_volume *vol, const char *ins,
-		const int ins_len, ntfschar **outs)
-{
-	struct nls_table *nls = vol->nls_map;
-	ntfschar *ucs;
-	wchar_t wc;
-	int i, o, wc_len;
-
-	/* We do not trust outside sources. */
-	if (likely(ins)) {
-		ucs = kmem_cache_alloc(ntfs_name_cache, GFP_NOFS);
-		if (likely(ucs)) {
-			for (i = o = 0; i < ins_len; i += wc_len) {
-				wc_len = nls->char2uni(ins + i, ins_len - i,
-						&wc);
-				if (likely(wc_len >= 0 &&
-						o < NTFS_MAX_NAME_LEN)) {
-					if (likely(wc)) {
-						ucs[o++] = cpu_to_le16(wc);
-						continue;
-					} /* else if (!wc) */
-					break;
-				} /* else if (wc_len < 0 ||
-						o >= NTFS_MAX_NAME_LEN) */
-				goto name_err;
-			}
-			ucs[o] = 0;
-			*outs = ucs;
-			return o;
-		} /* else if (!ucs) */
-		ntfs_error(vol->sb, "Failed to allocate buffer for converted "
-				"name from ntfs_name_cache.");
-		return -ENOMEM;
-	} /* else if (!ins) */
-	ntfs_error(vol->sb, "Received NULL pointer.");
-	return -EINVAL;
-name_err:
-	kmem_cache_free(ntfs_name_cache, ucs);
-	if (wc_len < 0) {
-		ntfs_error(vol->sb, "Name using character set %s contains "
-				"characters that cannot be converted to "
-				"Unicode.", nls->charset);
-		i = -EILSEQ;
-	} else /* if (o >= NTFS_MAX_NAME_LEN) */ {
-		ntfs_error(vol->sb, "Name is too long (maximum length for a "
-				"name on NTFS is %d Unicode characters.",
-				NTFS_MAX_NAME_LEN);
-		i = -ENAMETOOLONG;
-	}
-	return i;
-}
-
-/**
- * ntfs_ucstonls - convert little endian Unicode string to NLS string
- * @vol:	ntfs volume which we are working with
- * @ins:	input Unicode string buffer
- * @ins_len:	length of input string in Unicode characters
- * @outs:	on return contains the (allocated) output NLS string buffer
- * @outs_len:	length of output string buffer in bytes
- *
- * Convert the input little endian, 2-byte Unicode string @ins, of length
- * @ins_len into the string format dictated by the loaded NLS.
- *
- * If *@outs is NULL, this function allocates the string and the caller is
- * responsible for calling kfree(*@outs); when finished with it. In this case
- * @outs_len is ignored and can be 0.
- *
- * On success the function returns the number of bytes written to the output
- * string *@outs (>= 0), not counting the terminating NULL byte. If the output
- * string buffer was allocated, *@outs is set to it.
- *
- * On error, a negative number corresponding to the error code is returned. In
- * that case the output string is not allocated. The contents of *@outs are
- * then undefined.
- *
- * This might look a bit odd due to fast path optimization...
- */
-int ntfs_ucstonls(const ntfs_volume *vol, const ntfschar *ins,
-		const int ins_len, unsigned char **outs, int outs_len)
-{
-	struct nls_table *nls = vol->nls_map;
-	unsigned char *ns;
-	int i, o, ns_len, wc;
-
-	/* We don't trust outside sources. */
-	if (ins) {
-		ns = *outs;
-		ns_len = outs_len;
-		if (ns && !ns_len) {
-			wc = -ENAMETOOLONG;
-			goto conversion_err;
-		}
-		if (!ns) {
-			ns_len = ins_len * NLS_MAX_CHARSET_SIZE;
-			ns = kmalloc(ns_len + 1, GFP_NOFS);
-			if (!ns)
-				goto mem_err_out;
-		}
-		for (i = o = 0; i < ins_len; i++) {
-retry:			wc = nls->uni2char(le16_to_cpu(ins[i]), ns + o,
-					ns_len - o);
-			if (wc > 0) {
-				o += wc;
-				continue;
-			} else if (!wc)
-				break;
-			else if (wc == -ENAMETOOLONG && ns != *outs) {
-				unsigned char *tc;
-				/* Grow in multiples of 64 bytes. */
-				tc = kmalloc((ns_len + 64) &
-						~63, GFP_NOFS);
-				if (tc) {
-					memcpy(tc, ns, ns_len);
-					ns_len = ((ns_len + 64) & ~63) - 1;
-					kfree(ns);
-					ns = tc;
-					goto retry;
-				} /* No memory so goto conversion_error; */
-			} /* wc < 0, real error. */
-			goto conversion_err;
-		}
-		ns[o] = 0;
-		*outs = ns;
-		return o;
-	} /* else (!ins) */
-	ntfs_error(vol->sb, "Received NULL pointer.");
-	return -EINVAL;
-conversion_err:
-	ntfs_error(vol->sb, "Unicode name contains characters that cannot be "
-			"converted to character set %s.  You might want to "
-			"try to use the mount option nls=utf8.", nls->charset);
-	if (ns != *outs)
-		kfree(ns);
-	if (wc != -ENAMETOOLONG)
-		wc = -EILSEQ;
-	return wc;
-mem_err_out:
-	ntfs_error(vol->sb, "Failed to allocate name!");
-	return -ENOMEM;
-}
diff --git a/fs/ntfs/upcase.c b/fs/ntfs/upcase.c
deleted file mode 100644
index 4ebe84a78dea..000000000000
--- a/fs/ntfs/upcase.c
+++ /dev/null
@@ -1,73 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * upcase.c - Generate the full NTFS Unicode upcase table in little endian.
- *	      Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001 Richard Russon <ntfs@flatcap.org>
- * Copyright (c) 2001-2006 Anton Altaparmakov
- */
-
-#include "malloc.h"
-#include "ntfs.h"
-
-ntfschar *generate_default_upcase(void)
-{
-	static const int uc_run_table[][3] = { /* Start, End, Add */
-	{0x0061, 0x007B,  -32}, {0x0451, 0x045D, -80}, {0x1F70, 0x1F72,  74},
-	{0x00E0, 0x00F7,  -32}, {0x045E, 0x0460, -80}, {0x1F72, 0x1F76,  86},
-	{0x00F8, 0x00FF,  -32}, {0x0561, 0x0587, -48}, {0x1F76, 0x1F78, 100},
-	{0x0256, 0x0258, -205}, {0x1F00, 0x1F08,   8}, {0x1F78, 0x1F7A, 128},
-	{0x028A, 0x028C, -217}, {0x1F10, 0x1F16,   8}, {0x1F7A, 0x1F7C, 112},
-	{0x03AC, 0x03AD,  -38}, {0x1F20, 0x1F28,   8}, {0x1F7C, 0x1F7E, 126},
-	{0x03AD, 0x03B0,  -37}, {0x1F30, 0x1F38,   8}, {0x1FB0, 0x1FB2,   8},
-	{0x03B1, 0x03C2,  -32}, {0x1F40, 0x1F46,   8}, {0x1FD0, 0x1FD2,   8},
-	{0x03C2, 0x03C3,  -31}, {0x1F51, 0x1F52,   8}, {0x1FE0, 0x1FE2,   8},
-	{0x03C3, 0x03CC,  -32}, {0x1F53, 0x1F54,   8}, {0x1FE5, 0x1FE6,   7},
-	{0x03CC, 0x03CD,  -64}, {0x1F55, 0x1F56,   8}, {0x2170, 0x2180, -16},
-	{0x03CD, 0x03CF,  -63}, {0x1F57, 0x1F58,   8}, {0x24D0, 0x24EA, -26},
-	{0x0430, 0x0450,  -32}, {0x1F60, 0x1F68,   8}, {0xFF41, 0xFF5B, -32},
-	{0}
-	};
-
-	static const int uc_dup_table[][2] = { /* Start, End */
-	{0x0100, 0x012F}, {0x01A0, 0x01A6}, {0x03E2, 0x03EF}, {0x04CB, 0x04CC},
-	{0x0132, 0x0137}, {0x01B3, 0x01B7}, {0x0460, 0x0481}, {0x04D0, 0x04EB},
-	{0x0139, 0x0149}, {0x01CD, 0x01DD}, {0x0490, 0x04BF}, {0x04EE, 0x04F5},
-	{0x014A, 0x0178}, {0x01DE, 0x01EF}, {0x04BF, 0x04BF}, {0x04F8, 0x04F9},
-	{0x0179, 0x017E}, {0x01F4, 0x01F5}, {0x04C1, 0x04C4}, {0x1E00, 0x1E95},
-	{0x018B, 0x018B}, {0x01FA, 0x0218}, {0x04C7, 0x04C8}, {0x1EA0, 0x1EF9},
-	{0}
-	};
-
-	static const int uc_word_table[][2] = { /* Offset, Value */
-	{0x00FF, 0x0178}, {0x01AD, 0x01AC}, {0x01F3, 0x01F1}, {0x0269, 0x0196},
-	{0x0183, 0x0182}, {0x01B0, 0x01AF}, {0x0253, 0x0181}, {0x026F, 0x019C},
-	{0x0185, 0x0184}, {0x01B9, 0x01B8}, {0x0254, 0x0186}, {0x0272, 0x019D},
-	{0x0188, 0x0187}, {0x01BD, 0x01BC}, {0x0259, 0x018F}, {0x0275, 0x019F},
-	{0x018C, 0x018B}, {0x01C6, 0x01C4}, {0x025B, 0x0190}, {0x0283, 0x01A9},
-	{0x0192, 0x0191}, {0x01C9, 0x01C7}, {0x0260, 0x0193}, {0x0288, 0x01AE},
-	{0x0199, 0x0198}, {0x01CC, 0x01CA}, {0x0263, 0x0194}, {0x0292, 0x01B7},
-	{0x01A8, 0x01A7}, {0x01DD, 0x018E}, {0x0268, 0x0197},
-	{0}
-	};
-
-	int i, r;
-	ntfschar *uc;
-
-	uc = ntfs_malloc_nofs(default_upcase_len * sizeof(ntfschar));
-	if (!uc)
-		return uc;
-	memset(uc, 0, default_upcase_len * sizeof(ntfschar));
-	/* Generate the little endian Unicode upcase table used by ntfs. */
-	for (i = 0; i < default_upcase_len; i++)
-		uc[i] = cpu_to_le16(i);
-	for (r = 0; uc_run_table[r][0]; r++)
-		for (i = uc_run_table[r][0]; i < uc_run_table[r][1]; i++)
-			le16_add_cpu(&uc[i], uc_run_table[r][2]);
-	for (r = 0; uc_dup_table[r][0]; r++)
-		for (i = uc_dup_table[r][0]; i < uc_dup_table[r][1]; i += 2)
-			le16_add_cpu(&uc[i + 1], -1);
-	for (r = 0; uc_word_table[r][0]; r++)
-		uc[uc_word_table[r][0]] = cpu_to_le16(uc_word_table[r][1]);
-	return uc;
-}
diff --git a/fs/ntfs/usnjrnl.c b/fs/ntfs/usnjrnl.c
deleted file mode 100644
index 9097a0b4ef25..000000000000
--- a/fs/ntfs/usnjrnl.c
+++ /dev/null
@@ -1,70 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * usnjrnl.h - NTFS kernel transaction log ($UsnJrnl) handling.  Part of the
- *	       Linux-NTFS project.
- *
- * Copyright (c) 2005 Anton Altaparmakov
- */
-
-#ifdef NTFS_RW
-
-#include <linux/fs.h>
-#include <linux/highmem.h>
-#include <linux/mm.h>
-
-#include "aops.h"
-#include "debug.h"
-#include "endian.h"
-#include "time.h"
-#include "types.h"
-#include "usnjrnl.h"
-#include "volume.h"
-
-/**
- * ntfs_stamp_usnjrnl - stamp the transaction log ($UsnJrnl) on an ntfs volume
- * @vol:	ntfs volume on which to stamp the transaction log
- *
- * Stamp the transaction log ($UsnJrnl) on the ntfs volume @vol and return
- * 'true' on success and 'false' on error.
- *
- * This function assumes that the transaction log has already been loaded and
- * consistency checked by a call to fs/ntfs/super.c::load_and_init_usnjrnl().
- */
-bool ntfs_stamp_usnjrnl(ntfs_volume *vol)
-{
-	ntfs_debug("Entering.");
-	if (likely(!NVolUsnJrnlStamped(vol))) {
-		sle64 stamp;
-		struct page *page;
-		USN_HEADER *uh;
-
-		page = ntfs_map_page(vol->usnjrnl_max_ino->i_mapping, 0);
-		if (IS_ERR(page)) {
-			ntfs_error(vol->sb, "Failed to read from "
-					"$UsnJrnl/$DATA/$Max attribute.");
-			return false;
-		}
-		uh = (USN_HEADER*)page_address(page);
-		stamp = get_current_ntfs_time();
-		ntfs_debug("Stamping transaction log ($UsnJrnl): old "
-				"journal_id 0x%llx, old lowest_valid_usn "
-				"0x%llx, new journal_id 0x%llx, new "
-				"lowest_valid_usn 0x%llx.",
-				(long long)sle64_to_cpu(uh->journal_id),
-				(long long)sle64_to_cpu(uh->lowest_valid_usn),
-				(long long)sle64_to_cpu(stamp),
-				i_size_read(vol->usnjrnl_j_ino));
-		uh->lowest_valid_usn =
-				cpu_to_sle64(i_size_read(vol->usnjrnl_j_ino));
-		uh->journal_id = stamp;
-		flush_dcache_page(page);
-		set_page_dirty(page);
-		ntfs_unmap_page(page);
-		/* Set the flag so we do not have to do it again on remount. */
-		NVolSetUsnJrnlStamped(vol);
-	}
-	ntfs_debug("Done.");
-	return true;
-}
-
-#endif /* NTFS_RW */
diff --git a/fs/ntfs/usnjrnl.h b/fs/ntfs/usnjrnl.h
deleted file mode 100644
index 85f531b59395..000000000000
--- a/fs/ntfs/usnjrnl.h
+++ /dev/null
@@ -1,191 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * usnjrnl.h - Defines for NTFS kernel transaction log ($UsnJrnl) handling.
- *	       Part of the Linux-NTFS project.
- *
- * Copyright (c) 2005 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_USNJRNL_H
-#define _LINUX_NTFS_USNJRNL_H
-
-#ifdef NTFS_RW
-
-#include "types.h"
-#include "endian.h"
-#include "layout.h"
-#include "volume.h"
-
-/*
- * Transaction log ($UsnJrnl) organization:
- *
- * The transaction log records whenever a file is modified in any way.  So for
- * example it will record that file "blah" was written to at a particular time
- * but not what was written.  If will record that a file was deleted or
- * created, that a file was truncated, etc.  See below for all the reason
- * codes used.
- *
- * The transaction log is in the $Extend directory which is in the root
- * directory of each volume.  If it is not present it means transaction
- * logging is disabled.  If it is present it means transaction logging is
- * either enabled or in the process of being disabled in which case we can
- * ignore it as it will go away as soon as Windows gets its hands on it.
- *
- * To determine whether the transaction logging is enabled or in the process
- * of being disabled, need to check the volume flags in the
- * $VOLUME_INFORMATION attribute in the $Volume system file (which is present
- * in the root directory and has a fixed mft record number, see layout.h).
- * If the flag VOLUME_DELETE_USN_UNDERWAY is set it means the transaction log
- * is in the process of being disabled and if this flag is clear it means the
- * transaction log is enabled.
- *
- * The transaction log consists of two parts; the $DATA/$Max attribute as well
- * as the $DATA/$J attribute.  $Max is a header describing the transaction
- * log whilst $J is the transaction log data itself as a sequence of variable
- * sized USN_RECORDs (see below for all the structures).
- *
- * We do not care about transaction logging at this point in time but we still
- * need to let windows know that the transaction log is out of date.  To do
- * this we need to stamp the transaction log.  This involves setting the
- * lowest_valid_usn field in the $DATA/$Max attribute to the usn to be used
- * for the next added USN_RECORD to the $DATA/$J attribute as well as
- * generating a new journal_id in $DATA/$Max.
- *
- * The journal_id is as of the current version (2.0) of the transaction log
- * simply the 64-bit timestamp of when the journal was either created or last
- * stamped.
- *
- * To determine the next usn there are two ways.  The first is to parse
- * $DATA/$J and to find the last USN_RECORD in it and to add its record_length
- * to its usn (which is the byte offset in the $DATA/$J attribute).  The
- * second is simply to take the data size of the attribute.  Since the usns
- * are simply byte offsets into $DATA/$J, this is exactly the next usn.  For
- * obvious reasons we use the second method as it is much simpler and faster.
- *
- * As an aside, note that to actually disable the transaction log, one would
- * need to set the VOLUME_DELETE_USN_UNDERWAY flag (see above), then go
- * through all the mft records on the volume and set the usn field in their
- * $STANDARD_INFORMATION attribute to zero.  Once that is done, one would need
- * to delete the transaction log file, i.e. \$Extent\$UsnJrnl, and finally,
- * one would need to clear the VOLUME_DELETE_USN_UNDERWAY flag.
- *
- * Note that if a volume is unmounted whilst the transaction log is being
- * disabled, the process will continue the next time the volume is mounted.
- * This is why we can safely mount read-write when we see a transaction log
- * in the process of being deleted.
- */
-
-/* Some $UsnJrnl related constants. */
-#define UsnJrnlMajorVer		2
-#define UsnJrnlMinorVer		0
-
-/*
- * $DATA/$Max attribute.  This is (always?) resident and has a fixed size of
- * 32 bytes.  It contains the header describing the transaction log.
- */
-typedef struct {
-/*Ofs*/
-/*   0*/sle64 maximum_size;	/* The maximum on-disk size of the $DATA/$J
-				   attribute. */
-/*   8*/sle64 allocation_delta;	/* Number of bytes by which to increase the
-				   size of the $DATA/$J attribute. */
-/*0x10*/sle64 journal_id;	/* Current id of the transaction log. */
-/*0x18*/leUSN lowest_valid_usn;	/* Lowest valid usn in $DATA/$J for the
-				   current journal_id. */
-/* sizeof() = 32 (0x20) bytes */
-} __attribute__ ((__packed__)) USN_HEADER;
-
-/*
- * Reason flags (32-bit).  Cumulative flags describing the change(s) to the
- * file since it was last opened.  I think the names speak for themselves but
- * if you disagree check out the descriptions in the Linux NTFS project NTFS
- * documentation: http://www.linux-ntfs.org/
- */
-enum {
-	USN_REASON_DATA_OVERWRITE	= cpu_to_le32(0x00000001),
-	USN_REASON_DATA_EXTEND		= cpu_to_le32(0x00000002),
-	USN_REASON_DATA_TRUNCATION	= cpu_to_le32(0x00000004),
-	USN_REASON_NAMED_DATA_OVERWRITE	= cpu_to_le32(0x00000010),
-	USN_REASON_NAMED_DATA_EXTEND	= cpu_to_le32(0x00000020),
-	USN_REASON_NAMED_DATA_TRUNCATION= cpu_to_le32(0x00000040),
-	USN_REASON_FILE_CREATE		= cpu_to_le32(0x00000100),
-	USN_REASON_FILE_DELETE		= cpu_to_le32(0x00000200),
-	USN_REASON_EA_CHANGE		= cpu_to_le32(0x00000400),
-	USN_REASON_SECURITY_CHANGE	= cpu_to_le32(0x00000800),
-	USN_REASON_RENAME_OLD_NAME	= cpu_to_le32(0x00001000),
-	USN_REASON_RENAME_NEW_NAME	= cpu_to_le32(0x00002000),
-	USN_REASON_INDEXABLE_CHANGE	= cpu_to_le32(0x00004000),
-	USN_REASON_BASIC_INFO_CHANGE	= cpu_to_le32(0x00008000),
-	USN_REASON_HARD_LINK_CHANGE	= cpu_to_le32(0x00010000),
-	USN_REASON_COMPRESSION_CHANGE	= cpu_to_le32(0x00020000),
-	USN_REASON_ENCRYPTION_CHANGE	= cpu_to_le32(0x00040000),
-	USN_REASON_OBJECT_ID_CHANGE	= cpu_to_le32(0x00080000),
-	USN_REASON_REPARSE_POINT_CHANGE	= cpu_to_le32(0x00100000),
-	USN_REASON_STREAM_CHANGE	= cpu_to_le32(0x00200000),
-	USN_REASON_CLOSE		= cpu_to_le32(0x80000000),
-};
-
-typedef le32 USN_REASON_FLAGS;
-
-/*
- * Source info flags (32-bit).  Information about the source of the change(s)
- * to the file.  For detailed descriptions of what these mean, see the Linux
- * NTFS project NTFS documentation:
- *	http://www.linux-ntfs.org/
- */
-enum {
-	USN_SOURCE_DATA_MANAGEMENT	  = cpu_to_le32(0x00000001),
-	USN_SOURCE_AUXILIARY_DATA	  = cpu_to_le32(0x00000002),
-	USN_SOURCE_REPLICATION_MANAGEMENT = cpu_to_le32(0x00000004),
-};
-
-typedef le32 USN_SOURCE_INFO_FLAGS;
-
-/*
- * $DATA/$J attribute.  This is always non-resident, is marked as sparse, and
- * is of variabled size.  It consists of a sequence of variable size
- * USN_RECORDS.  The minimum allocated_size is allocation_delta as
- * specified in $DATA/$Max.  When the maximum_size specified in $DATA/$Max is
- * exceeded by more than allocation_delta bytes, allocation_delta bytes are
- * allocated and appended to the $DATA/$J attribute and an equal number of
- * bytes at the beginning of the attribute are freed and made sparse.  Note the
- * making sparse only happens at volume checkpoints and hence the actual
- * $DATA/$J size can exceed maximum_size + allocation_delta temporarily.
- */
-typedef struct {
-/*Ofs*/
-/*   0*/le32 length;		/* Byte size of this record (8-byte
-				   aligned). */
-/*   4*/le16 major_ver;		/* Major version of the transaction log used
-				   for this record. */
-/*   6*/le16 minor_ver;		/* Minor version of the transaction log used
-				   for this record. */
-/*   8*/leMFT_REF mft_reference;/* The mft reference of the file (or
-				   directory) described by this record. */
-/*0x10*/leMFT_REF parent_directory;/* The mft reference of the parent
-				   directory of the file described by this
-				   record. */
-/*0x18*/leUSN usn;		/* The usn of this record.  Equals the offset
-				   within the $DATA/$J attribute. */
-/*0x20*/sle64 time;		/* Time when this record was created. */
-/*0x28*/USN_REASON_FLAGS reason;/* Reason flags (see above). */
-/*0x2c*/USN_SOURCE_INFO_FLAGS source_info;/* Source info flags (see above). */
-/*0x30*/le32 security_id;	/* File security_id copied from
-				   $STANDARD_INFORMATION. */
-/*0x34*/FILE_ATTR_FLAGS file_attributes;	/* File attributes copied from
-				   $STANDARD_INFORMATION or $FILE_NAME (not
-				   sure which). */
-/*0x38*/le16 file_name_size;	/* Size of the file name in bytes. */
-/*0x3a*/le16 file_name_offset;	/* Offset to the file name in bytes from the
-				   start of this record. */
-/*0x3c*/ntfschar file_name[0];	/* Use when creating only.  When reading use
-				   file_name_offset to determine the location
-				   of the name. */
-/* sizeof() = 60 (0x3c) bytes */
-} __attribute__ ((__packed__)) USN_RECORD;
-
-extern bool ntfs_stamp_usnjrnl(ntfs_volume *vol);
-
-#endif /* NTFS_RW */
-
-#endif /* _LINUX_NTFS_USNJRNL_H */
diff --git a/fs/ntfs/volume.h b/fs/ntfs/volume.h
deleted file mode 100644
index 930a9ae8a053..000000000000
--- a/fs/ntfs/volume.h
+++ /dev/null
@@ -1,164 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * volume.h - Defines for volume structures in NTFS Linux kernel driver. Part
- *	      of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2006 Anton Altaparmakov
- * Copyright (c) 2002 Richard Russon
- */
-
-#ifndef _LINUX_NTFS_VOLUME_H
-#define _LINUX_NTFS_VOLUME_H
-
-#include <linux/rwsem.h>
-#include <linux/uidgid.h>
-
-#include "types.h"
-#include "layout.h"
-
-/*
- * The NTFS in memory super block structure.
- */
-typedef struct {
-	/*
-	 * FIXME: Reorder to have commonly used together element within the
-	 * same cache line, aiming at a cache line size of 32 bytes. Aim for
-	 * 64 bytes for less commonly used together elements. Put most commonly
-	 * used elements to front of structure. Obviously do this only when the
-	 * structure has stabilized... (AIA)
-	 */
-	/* Device specifics. */
-	struct super_block *sb;		/* Pointer back to the super_block. */
-	LCN nr_blocks;			/* Number of sb->s_blocksize bytes
-					   sized blocks on the device. */
-	/* Configuration provided by user at mount time. */
-	unsigned long flags;		/* Miscellaneous flags, see below. */
-	kuid_t uid;			/* uid that files will be mounted as. */
-	kgid_t gid;			/* gid that files will be mounted as. */
-	umode_t fmask;			/* The mask for file permissions. */
-	umode_t dmask;			/* The mask for directory
-					   permissions. */
-	u8 mft_zone_multiplier;		/* Initial mft zone multiplier. */
-	u8 on_errors;			/* What to do on filesystem errors. */
-	/* NTFS bootsector provided information. */
-	u16 sector_size;		/* in bytes */
-	u8 sector_size_bits;		/* log2(sector_size) */
-	u32 cluster_size;		/* in bytes */
-	u32 cluster_size_mask;		/* cluster_size - 1 */
-	u8 cluster_size_bits;		/* log2(cluster_size) */
-	u32 mft_record_size;		/* in bytes */
-	u32 mft_record_size_mask;	/* mft_record_size - 1 */
-	u8 mft_record_size_bits;	/* log2(mft_record_size) */
-	u32 index_record_size;		/* in bytes */
-	u32 index_record_size_mask;	/* index_record_size - 1 */
-	u8 index_record_size_bits;	/* log2(index_record_size) */
-	LCN nr_clusters;		/* Volume size in clusters == number of
-					   bits in lcn bitmap. */
-	LCN mft_lcn;			/* Cluster location of mft data. */
-	LCN mftmirr_lcn;		/* Cluster location of copy of mft. */
-	u64 serial_no;			/* The volume serial number. */
-	/* Mount specific NTFS information. */
-	u32 upcase_len;			/* Number of entries in upcase[]. */
-	ntfschar *upcase;		/* The upcase table. */
-
-	s32 attrdef_size;		/* Size of the attribute definition
-					   table in bytes. */
-	ATTR_DEF *attrdef;		/* Table of attribute definitions.
-					   Obtained from FILE_AttrDef. */
-
-#ifdef NTFS_RW
-	/* Variables used by the cluster and mft allocators. */
-	s64 mft_data_pos;		/* Mft record number at which to
-					   allocate the next mft record. */
-	LCN mft_zone_start;		/* First cluster of the mft zone. */
-	LCN mft_zone_end;		/* First cluster beyond the mft zone. */
-	LCN mft_zone_pos;		/* Current position in the mft zone. */
-	LCN data1_zone_pos;		/* Current position in the first data
-					   zone. */
-	LCN data2_zone_pos;		/* Current position in the second data
-					   zone. */
-#endif /* NTFS_RW */
-
-	struct inode *mft_ino;		/* The VFS inode of $MFT. */
-
-	struct inode *mftbmp_ino;	/* Attribute inode for $MFT/$BITMAP. */
-	struct rw_semaphore mftbmp_lock; /* Lock for serializing accesses to the
-					    mft record bitmap ($MFT/$BITMAP). */
-#ifdef NTFS_RW
-	struct inode *mftmirr_ino;	/* The VFS inode of $MFTMirr. */
-	int mftmirr_size;		/* Size of mft mirror in mft records. */
-
-	struct inode *logfile_ino;	/* The VFS inode of $LogFile. */
-#endif /* NTFS_RW */
-
-	struct inode *lcnbmp_ino;	/* The VFS inode of $Bitmap. */
-	struct rw_semaphore lcnbmp_lock; /* Lock for serializing accesses to the
-					    cluster bitmap ($Bitmap/$DATA). */
-
-	struct inode *vol_ino;		/* The VFS inode of $Volume. */
-	VOLUME_FLAGS vol_flags;		/* Volume flags. */
-	u8 major_ver;			/* Ntfs major version of volume. */
-	u8 minor_ver;			/* Ntfs minor version of volume. */
-
-	struct inode *root_ino;		/* The VFS inode of the root
-					   directory. */
-	struct inode *secure_ino;	/* The VFS inode of $Secure (NTFS3.0+
-					   only, otherwise NULL). */
-	struct inode *extend_ino;	/* The VFS inode of $Extend (NTFS3.0+
-					   only, otherwise NULL). */
-#ifdef NTFS_RW
-	/* $Quota stuff is NTFS3.0+ specific.  Unused/NULL otherwise. */
-	struct inode *quota_ino;	/* The VFS inode of $Quota. */
-	struct inode *quota_q_ino;	/* Attribute inode for $Quota/$Q. */
-	/* $UsnJrnl stuff is NTFS3.0+ specific.  Unused/NULL otherwise. */
-	struct inode *usnjrnl_ino;	/* The VFS inode of $UsnJrnl. */
-	struct inode *usnjrnl_max_ino;	/* Attribute inode for $UsnJrnl/$Max. */
-	struct inode *usnjrnl_j_ino;	/* Attribute inode for $UsnJrnl/$J. */
-#endif /* NTFS_RW */
-	struct nls_table *nls_map;
-} ntfs_volume;
-
-/*
- * Defined bits for the flags field in the ntfs_volume structure.
- */
-typedef enum {
-	NV_Errors,		/* 1: Volume has errors, prevent remount rw. */
-	NV_ShowSystemFiles,	/* 1: Return system files in ntfs_readdir(). */
-	NV_CaseSensitive,	/* 1: Treat file names as case sensitive and
-				      create filenames in the POSIX namespace.
-				      Otherwise be case insensitive but still
-				      create file names in POSIX namespace. */
-	NV_LogFileEmpty,	/* 1: $LogFile journal is empty. */
-	NV_QuotaOutOfDate,	/* 1: $Quota is out of date. */
-	NV_UsnJrnlStamped,	/* 1: $UsnJrnl has been stamped. */
-	NV_SparseEnabled,	/* 1: May create sparse files. */
-} ntfs_volume_flags;
-
-/*
- * Macro tricks to expand the NVolFoo(), NVolSetFoo(), and NVolClearFoo()
- * functions.
- */
-#define DEFINE_NVOL_BIT_OPS(flag)					\
-static inline int NVol##flag(ntfs_volume *vol)		\
-{							\
-	return test_bit(NV_##flag, &(vol)->flags);	\
-}							\
-static inline void NVolSet##flag(ntfs_volume *vol)	\
-{							\
-	set_bit(NV_##flag, &(vol)->flags);		\
-}							\
-static inline void NVolClear##flag(ntfs_volume *vol)	\
-{							\
-	clear_bit(NV_##flag, &(vol)->flags);		\
-}
-
-/* Emit the ntfs volume bitops functions. */
-DEFINE_NVOL_BIT_OPS(Errors)
-DEFINE_NVOL_BIT_OPS(ShowSystemFiles)
-DEFINE_NVOL_BIT_OPS(CaseSensitive)
-DEFINE_NVOL_BIT_OPS(LogFileEmpty)
-DEFINE_NVOL_BIT_OPS(QuotaOutOfDate)
-DEFINE_NVOL_BIT_OPS(UsnJrnlStamped)
-DEFINE_NVOL_BIT_OPS(SparseEnabled)
-
-#endif /* _LINUX_NTFS_VOLUME_H */
diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c
index 63f70259edc0..7aadf5010999 100644
--- a/fs/ntfs3/attrib.c
+++ b/fs/ntfs3/attrib.c
@@ -886,7 +886,7 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
 	struct runs_tree *run = &ni->file.run;
 	struct ntfs_sb_info *sbi;
 	u8 cluster_bits;
-	struct ATTRIB *attr = NULL, *attr_b;
+	struct ATTRIB *attr, *attr_b;
 	struct ATTR_LIST_ENTRY *le, *le_b;
 	struct mft_inode *mi, *mi_b;
 	CLST hint, svcn, to_alloc, evcn1, next_svcn, asize, end, vcn0, alen;
@@ -904,12 +904,8 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
 		*len = 0;
 	up_read(&ni->file.run_lock);
 
-	if (*len) {
-		if (*lcn != SPARSE_LCN || !new)
-			return 0; /* Fast normal way without allocation. */
-		else if (clen > *len)
-			clen = *len;
-	}
+	if (*len && (*lcn != SPARSE_LCN || !new))
+		return 0; /* Fast normal way without allocation. */
 
 	/* No cluster in cache or we need to allocate cluster in hole. */
 	sbi = ni->mi.sbi;
@@ -918,6 +914,17 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
 	ni_lock(ni);
 	down_write(&ni->file.run_lock);
 
+	/* Repeat the code above (under write lock). */
+	if (!run_lookup_entry(run, vcn, lcn, len, NULL))
+		*len = 0;
+
+	if (*len) {
+		if (*lcn != SPARSE_LCN || !new)
+			goto out; /* normal way without allocation. */
+		if (clen > *len)
+			clen = *len;
+	}
+
 	le_b = NULL;
 	attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b);
 	if (!attr_b) {
@@ -1736,8 +1743,10 @@ repack:
 			le_b = NULL;
 			attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL,
 					      0, NULL, &mi_b);
-			if (!attr_b)
-				return -ENOENT;
+			if (!attr_b) {
+				err = -ENOENT;
+				goto out;
+			}
 
 			attr = attr_b;
 			le = le_b;
@@ -1818,13 +1827,15 @@ ins_ext:
 ok:
 	run_truncate_around(run, vcn);
 out:
-	if (new_valid > data_size)
-		new_valid = data_size;
+	if (attr_b) {
+		if (new_valid > data_size)
+			new_valid = data_size;
 
-	valid_size = le64_to_cpu(attr_b->nres.valid_size);
-	if (new_valid != valid_size) {
-		attr_b->nres.valid_size = cpu_to_le64(valid_size);
-		mi_b->dirty = true;
+		valid_size = le64_to_cpu(attr_b->nres.valid_size);
+		if (new_valid != valid_size) {
+			attr_b->nres.valid_size = cpu_to_le64(valid_size);
+			mi_b->dirty = true;
+		}
 	}
 
 	return err;
@@ -2073,7 +2084,7 @@ next_attr:
 
 	/* Update inode size. */
 	ni->i_valid = valid_size;
-	ni->vfs_inode.i_size = data_size;
+	i_size_write(&ni->vfs_inode, data_size);
 	inode_set_bytes(&ni->vfs_inode, total_size);
 	ni->ni_flags |= NI_FLAG_UPDATE_PARENT;
 	mark_inode_dirty(&ni->vfs_inode);
@@ -2488,7 +2499,7 @@ int attr_insert_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 	mi_b->dirty = true;
 
 done:
-	ni->vfs_inode.i_size += bytes;
+	i_size_write(&ni->vfs_inode, ni->vfs_inode.i_size + bytes);
 	ni->ni_flags |= NI_FLAG_UPDATE_PARENT;
 	mark_inode_dirty(&ni->vfs_inode);
 
diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c
index 7c01735d1219..9f4bd8d26090 100644
--- a/fs/ntfs3/attrlist.c
+++ b/fs/ntfs3/attrlist.c
@@ -29,7 +29,7 @@ static inline bool al_is_valid_le(const struct ntfs_inode *ni,
 void al_destroy(struct ntfs_inode *ni)
 {
 	run_close(&ni->attr_list.run);
-	kfree(ni->attr_list.le);
+	kvfree(ni->attr_list.le);
 	ni->attr_list.le = NULL;
 	ni->attr_list.size = 0;
 	ni->attr_list.dirty = false;
@@ -127,12 +127,13 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni,
 {
 	size_t off;
 	u16 sz;
+	const unsigned le_min_size = le_size(0);
 
 	if (!le) {
 		le = ni->attr_list.le;
 	} else {
 		sz = le16_to_cpu(le->size);
-		if (sz < sizeof(struct ATTR_LIST_ENTRY)) {
+		if (sz < le_min_size) {
 			/* Impossible 'cause we should not return such le. */
 			return NULL;
 		}
@@ -141,7 +142,7 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni,
 
 	/* Check boundary. */
 	off = PtrOffset(ni->attr_list.le, le);
-	if (off + sizeof(struct ATTR_LIST_ENTRY) > ni->attr_list.size) {
+	if (off + le_min_size > ni->attr_list.size) {
 		/* The regular end of list. */
 		return NULL;
 	}
@@ -149,8 +150,7 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni,
 	sz = le16_to_cpu(le->size);
 
 	/* Check le for errors. */
-	if (sz < sizeof(struct ATTR_LIST_ENTRY) ||
-	    off + sz > ni->attr_list.size ||
+	if (sz < le_min_size || off + sz > ni->attr_list.size ||
 	    sz < le->name_off + le->name_len * sizeof(short)) {
 		return NULL;
 	}
@@ -318,7 +318,7 @@ int al_add_le(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name,
 		memcpy(ptr, al->le, off);
 		memcpy(Add2Ptr(ptr, off + sz), le, old_size - off);
 		le = Add2Ptr(ptr, off);
-		kfree(al->le);
+		kvfree(al->le);
 		al->le = ptr;
 	} else {
 		memmove(Add2Ptr(le, sz), le, old_size - off);
diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c
index 63f14a0232f6..845f9b22deef 100644
--- a/fs/ntfs3/bitmap.c
+++ b/fs/ntfs3/bitmap.c
@@ -124,7 +124,7 @@ void wnd_close(struct wnd_bitmap *wnd)
 {
 	struct rb_node *node, *next;
 
-	kfree(wnd->free_bits);
+	kvfree(wnd->free_bits);
 	wnd->free_bits = NULL;
 	run_close(&wnd->run);
 
@@ -1360,7 +1360,7 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits)
 		memcpy(new_free, wnd->free_bits, wnd->nwnd * sizeof(short));
 		memset(new_free + wnd->nwnd, 0,
 		       (new_wnd - wnd->nwnd) * sizeof(short));
-		kfree(wnd->free_bits);
+		kvfree(wnd->free_bits);
 		wnd->free_bits = new_free;
 	}
 
diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
index ec0566b322d5..5cf3d9decf64 100644
--- a/fs/ntfs3/dir.c
+++ b/fs/ntfs3/dir.c
@@ -309,11 +309,31 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
 		return 0;
 	}
 
-	/* NTFS: symlinks are "dir + reparse" or "file + reparse" */
-	if (fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT)
-		dt_type = DT_LNK;
-	else
-		dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG;
+	/*
+	 * NTFS: symlinks are "dir + reparse" or "file + reparse"
+	 * Unfortunately reparse attribute is used for many purposes (several dozens).
+	 * It is not possible here to know is this name symlink or not.
+	 * To get exactly the type of name we should to open inode (read mft).
+	 * getattr for opened file (fstat) correctly returns symlink.
+	 */
+	dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG;
+
+	/*
+	 * It is not reliable to detect the type of name using duplicated information
+	 * stored in parent directory.
+	 * The only correct way to get the type of name - read MFT record and find ATTR_STD.
+	 * The code below is not good idea.
+	 * It does additional locks/reads just to get the type of name.
+	 * Should we use additional mount option to enable branch below?
+	 */
+	if ((fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT) &&
+	    ino != ni->mi.rno) {
+		struct inode *inode = ntfs_iget5(sbi->sb, &e->ref, NULL);
+		if (!IS_ERR_OR_NULL(inode)) {
+			dt_type = fs_umode_to_dtype(inode->i_mode);
+			iput(inode);
+		}
+	}
 
 	return !dir_emit(ctx, (s8 *)name, name_len, ino, dt_type);
 }
@@ -495,11 +515,9 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
 	struct INDEX_HDR *hdr;
 	const struct ATTR_FILE_NAME *fname;
 	u32 e_size, off, end;
-	u64 vbo = 0;
 	size_t drs = 0, fles = 0, bit = 0;
-	loff_t i_size = ni->vfs_inode.i_size;
 	struct indx_node *node = NULL;
-	u8 index_bits = ni->dir.index_bits;
+	size_t max_indx = i_size_read(&ni->vfs_inode) >> ni->dir.index_bits;
 
 	if (is_empty)
 		*is_empty = true;
@@ -518,8 +536,10 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
 			e = Add2Ptr(hdr, off);
 			e_size = le16_to_cpu(e->size);
 			if (e_size < sizeof(struct NTFS_DE) ||
-			    off + e_size > end)
+			    off + e_size > end) {
+				/* Looks like corruption. */
 				break;
+			}
 
 			if (de_is_last(e))
 				break;
@@ -543,7 +563,7 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
 				fles += 1;
 		}
 
-		if (vbo >= i_size)
+		if (bit >= max_indx)
 			goto out;
 
 		err = indx_used_bit(&ni->dir, ni, &bit);
@@ -553,8 +573,7 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
 		if (bit == MINUS_ONE_T)
 			goto out;
 
-		vbo = (u64)bit << index_bits;
-		if (vbo >= i_size)
+		if (bit >= max_indx)
 			goto out;
 
 		err = indx_read(&ni->dir, ni, bit << ni->dir.idx2vbn_bits,
@@ -564,7 +583,6 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
 
 		hdr = &node->index->ihdr;
 		bit += 1;
-		vbo = (u64)bit << ni->dir.idx2vbn_bits;
 	}
 
 out:
@@ -593,5 +611,9 @@ const struct file_operations ntfs_dir_operations = {
 	.iterate_shared	= ntfs_readdir,
 	.fsync		= generic_file_fsync,
 	.open		= ntfs_file_open,
+	.unlocked_ioctl = ntfs_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl   = ntfs_compat_ioctl,
+#endif
 };
 // clang-format on
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index a5a30a24ce5d..5418662c80d8 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -48,7 +48,7 @@ static int ntfs_ioctl_fitrim(struct ntfs_sb_info *sbi, unsigned long arg)
 	return 0;
 }
 
-static long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg)
+long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
 	struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info;
@@ -61,7 +61,7 @@ static long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg)
 }
 
 #ifdef CONFIG_COMPAT
-static long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg)
+long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg)
 
 {
 	return ntfs_ioctl(filp, cmd, (unsigned long)compat_ptr(arg));
@@ -188,6 +188,7 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to)
 	u32 bh_next, bh_off, to;
 	sector_t iblock;
 	struct folio *folio;
+	bool dirty = false;
 
 	for (; idx < idx_end; idx += 1, from = 0) {
 		page_off = (loff_t)idx << PAGE_SHIFT;
@@ -223,29 +224,27 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to)
 			/* Ok, it's mapped. Make sure it's up-to-date. */
 			if (folio_test_uptodate(folio))
 				set_buffer_uptodate(bh);
-
-			if (!buffer_uptodate(bh)) {
-				err = bh_read(bh, 0);
-				if (err < 0) {
-					folio_unlock(folio);
-					folio_put(folio);
-					goto out;
-				}
+			else if (bh_read(bh, 0) < 0) {
+				err = -EIO;
+				folio_unlock(folio);
+				folio_put(folio);
+				goto out;
 			}
 
 			mark_buffer_dirty(bh);
-
 		} while (bh_off = bh_next, iblock += 1,
 			 head != (bh = bh->b_this_page));
 
 		folio_zero_segment(folio, from, to);
+		dirty = true;
 
 		folio_unlock(folio);
 		folio_put(folio);
 		cond_resched();
 	}
 out:
-	mark_inode_dirty(inode);
+	if (dirty)
+		mark_inode_dirty(inode);
 	return err;
 }
 
@@ -261,6 +260,9 @@ static int ntfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	bool rw = vma->vm_flags & VM_WRITE;
 	int err;
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	if (is_encrypted(ni)) {
 		ntfs_inode_warn(inode, "mmap encrypted not supported");
 		return -EOPNOTSUPP;
@@ -499,10 +501,14 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 		ni_lock(ni);
 		err = attr_punch_hole(ni, vbo, len, &frame_size);
 		ni_unlock(ni);
+		if (!err)
+			goto ok;
+
 		if (err != E_NTFS_NOTALIGNED)
 			goto out;
 
 		/* Process not aligned punch. */
+		err = 0;
 		mask = frame_size - 1;
 		vbo_a = (vbo + mask) & ~mask;
 		end_a = end & ~mask;
@@ -525,6 +531,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 			ni_lock(ni);
 			err = attr_punch_hole(ni, vbo_a, end_a - vbo_a, NULL);
 			ni_unlock(ni);
+			if (err)
+				goto out;
 		}
 	} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
 		/*
@@ -564,6 +572,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 		ni_lock(ni);
 		err = attr_insert_range(ni, vbo, len);
 		ni_unlock(ni);
+		if (err)
+			goto out;
 	} else {
 		/* Check new size. */
 		u8 cluster_bits = sbi->cluster_bits;
@@ -633,11 +643,18 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 					    &ni->file.run, i_size, &ni->i_valid,
 					    true, NULL);
 			ni_unlock(ni);
+			if (err)
+				goto out;
 		} else if (new_size > i_size) {
-			inode->i_size = new_size;
+			i_size_write(inode, new_size);
 		}
 	}
 
+ok:
+	err = file_modified(file);
+	if (err)
+		goto out;
+
 out:
 	if (map_locked)
 		filemap_invalidate_unlock(mapping);
@@ -663,6 +680,9 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	umode_t mode = inode->i_mode;
 	int err;
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	err = setattr_prepare(idmap, dentry, attr);
 	if (err)
 		goto out;
@@ -676,7 +696,7 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 			goto out;
 		}
 		inode_dio_wait(inode);
-		oldsize = inode->i_size;
+		oldsize = i_size_read(inode);
 		newsize = attr->ia_size;
 
 		if (newsize <= oldsize)
@@ -688,7 +708,7 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 			goto out;
 
 		ni->ni_flags |= NI_FLAG_UPDATE_PARENT;
-		inode->i_size = newsize;
+		i_size_write(inode, newsize);
 	}
 
 	setattr_copy(idmap, inode, attr);
@@ -718,6 +738,9 @@ static ssize_t ntfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 	struct inode *inode = file->f_mapping->host;
 	struct ntfs_inode *ni = ntfs_i(inode);
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	if (is_encrypted(ni)) {
 		ntfs_inode_warn(inode, "encrypted i/o not supported");
 		return -EOPNOTSUPP;
@@ -752,6 +775,9 @@ static ssize_t ntfs_file_splice_read(struct file *in, loff_t *ppos,
 	struct inode *inode = in->f_mapping->host;
 	struct ntfs_inode *ni = ntfs_i(inode);
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	if (is_encrypted(ni)) {
 		ntfs_inode_warn(inode, "encrypted i/o not supported");
 		return -EOPNOTSUPP;
@@ -821,7 +847,7 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 	size_t count = iov_iter_count(from);
 	loff_t pos = iocb->ki_pos;
 	struct inode *inode = file_inode(file);
-	loff_t i_size = inode->i_size;
+	loff_t i_size = i_size_read(inode);
 	struct address_space *mapping = inode->i_mapping;
 	struct ntfs_inode *ni = ntfs_i(inode);
 	u64 valid = ni->i_valid;
@@ -1028,6 +1054,8 @@ out:
 	iocb->ki_pos += written;
 	if (iocb->ki_pos > ni->i_valid)
 		ni->i_valid = iocb->ki_pos;
+	if (iocb->ki_pos > i_size)
+		i_size_write(inode, iocb->ki_pos);
 
 	return written;
 }
@@ -1041,8 +1069,12 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
 	ssize_t ret;
+	int err;
 	struct ntfs_inode *ni = ntfs_i(inode);
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	if (is_encrypted(ni)) {
 		ntfs_inode_warn(inode, "encrypted i/o not supported");
 		return -EOPNOTSUPP;
@@ -1068,6 +1100,12 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (ret <= 0)
 		goto out;
 
+	err = file_modified(iocb->ki_filp);
+	if (err) {
+		ret = err;
+		goto out;
+	}
+
 	if (WARN_ON(ni->ni_flags & NI_FLAG_COMPRESSED_MASK)) {
 		/* Should never be here, see ntfs_file_open(). */
 		ret = -EOPNOTSUPP;
@@ -1097,6 +1135,9 @@ int ntfs_file_open(struct inode *inode, struct file *file)
 {
 	struct ntfs_inode *ni = ntfs_i(inode);
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	if (unlikely((is_compressed(ni) || is_encrypted(ni)) &&
 		     (file->f_flags & O_DIRECT))) {
 		return -EOPNOTSUPP;
@@ -1138,7 +1179,8 @@ static int ntfs_file_release(struct inode *inode, struct file *file)
 		down_write(&ni->file.run_lock);
 
 		err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run,
-				    inode->i_size, &ni->i_valid, false, NULL);
+				    i_size_read(inode), &ni->i_valid, false,
+				    NULL);
 
 		up_write(&ni->file.run_lock);
 		ni_unlock(ni);
diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
index 3df2d9e34b91..7f27382e0ce2 100644
--- a/fs/ntfs3/frecord.c
+++ b/fs/ntfs3/frecord.c
@@ -778,7 +778,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni)
 	run_deallocate(sbi, &ni->attr_list.run, true);
 	run_close(&ni->attr_list.run);
 	ni->attr_list.size = 0;
-	kfree(ni->attr_list.le);
+	kvfree(ni->attr_list.le);
 	ni->attr_list.le = NULL;
 	ni->attr_list.dirty = false;
 
@@ -927,7 +927,7 @@ int ni_create_attr_list(struct ntfs_inode *ni)
 	return 0;
 
 out:
-	kfree(ni->attr_list.le);
+	kvfree(ni->attr_list.le);
 	ni->attr_list.le = NULL;
 	ni->attr_list.size = 0;
 	return err;
@@ -2099,7 +2099,7 @@ int ni_readpage_cmpr(struct ntfs_inode *ni, struct page *page)
 	gfp_t gfp_mask;
 	struct page *pg;
 
-	if (vbo >= ni->vfs_inode.i_size) {
+	if (vbo >= i_size_read(&ni->vfs_inode)) {
 		SetPageUptodate(page);
 		err = 0;
 		goto out;
@@ -2173,7 +2173,7 @@ int ni_decompress_file(struct ntfs_inode *ni)
 {
 	struct ntfs_sb_info *sbi = ni->mi.sbi;
 	struct inode *inode = &ni->vfs_inode;
-	loff_t i_size = inode->i_size;
+	loff_t i_size = i_size_read(inode);
 	struct address_space *mapping = inode->i_mapping;
 	gfp_t gfp_mask = mapping_gfp_mask(mapping);
 	struct page **pages = NULL;
@@ -2508,6 +2508,7 @@ int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages,
 		err = -EOPNOTSUPP;
 		goto out1;
 #else
+		loff_t i_size = i_size_read(&ni->vfs_inode);
 		u32 frame_bits = ni_ext_compress_bits(ni);
 		u64 frame64 = frame_vbo >> frame_bits;
 		u64 frames, vbo_data;
@@ -2548,7 +2549,7 @@ int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages,
 			}
 		}
 
-		frames = (ni->vfs_inode.i_size - 1) >> frame_bits;
+		frames = (i_size - 1) >> frame_bits;
 
 		err = attr_wof_frame_info(ni, attr, run, frame64, frames,
 					  frame_bits, &ondisk_size, &vbo_data);
@@ -2556,8 +2557,7 @@ int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages,
 			goto out2;
 
 		if (frame64 == frames) {
-			unc_size = 1 + ((ni->vfs_inode.i_size - 1) &
-					(frame_size - 1));
+			unc_size = 1 + ((i_size - 1) & (frame_size - 1));
 			ondisk_size = attr_size(attr) - vbo_data;
 		} else {
 			unc_size = frame_size;
@@ -3259,6 +3259,9 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint)
 	if (is_bad_inode(inode) || sb_rdonly(sb))
 		return 0;
 
+	if (unlikely(ntfs3_forced_shutdown(sb)))
+		return -EIO;
+
 	if (!ni_trylock(ni)) {
 		/* 'ni' is under modification, skip for now. */
 		mark_inode_dirty_sync(inode);
@@ -3288,7 +3291,7 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint)
 			modified = true;
 		}
 
-		ts = inode_get_mtime(inode);
+		ts = inode_get_ctime(inode);
 		dup.c_time = kernel2nt(&ts);
 		if (std->c_time != dup.c_time) {
 			std->c_time = dup.c_time;
diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c
index 98ccb6650858..855519713bf7 100644
--- a/fs/ntfs3/fslog.c
+++ b/fs/ntfs3/fslog.c
@@ -465,7 +465,7 @@ static inline bool is_rst_area_valid(const struct RESTART_HDR *rhdr)
 {
 	const struct RESTART_AREA *ra;
 	u16 cl, fl, ul;
-	u32 off, l_size, file_dat_bits, file_size_round;
+	u32 off, l_size, seq_bits;
 	u16 ro = le16_to_cpu(rhdr->ra_off);
 	u32 sys_page = le32_to_cpu(rhdr->sys_page_size);
 
@@ -511,13 +511,15 @@ static inline bool is_rst_area_valid(const struct RESTART_HDR *rhdr)
 	/* Make sure the sequence number bits match the log file size. */
 	l_size = le64_to_cpu(ra->l_size);
 
-	file_dat_bits = sizeof(u64) * 8 - le32_to_cpu(ra->seq_num_bits);
-	file_size_round = 1u << (file_dat_bits + 3);
-	if (file_size_round != l_size &&
-	    (file_size_round < l_size || (file_size_round / 2) > l_size)) {
-		return false;
+	seq_bits = sizeof(u64) * 8 + 3;
+	while (l_size) {
+		l_size >>= 1;
+		seq_bits -= 1;
 	}
 
+	if (seq_bits != ra->seq_num_bits)
+		return false;
+
 	/* The log page data offset and record header length must be quad-aligned. */
 	if (!IS_ALIGNED(le16_to_cpu(ra->data_off), 8) ||
 	    !IS_ALIGNED(le16_to_cpu(ra->rec_hdr_len), 8))
@@ -974,6 +976,16 @@ skip_looking:
 	return e;
 }
 
+struct restart_info {
+	u64 last_lsn;
+	struct RESTART_HDR *r_page;
+	u32 vbo;
+	bool chkdsk_was_run;
+	bool valid_page;
+	bool initialized;
+	bool restart;
+};
+
 #define RESTART_SINGLE_PAGE_IO cpu_to_le16(0x0001)
 
 #define NTFSLOG_WRAPPED 0x00000001
@@ -987,6 +999,7 @@ struct ntfs_log {
 	struct ntfs_inode *ni;
 
 	u32 l_size;
+	u32 orig_file_size;
 	u32 sys_page_size;
 	u32 sys_page_mask;
 	u32 page_size;
@@ -1040,6 +1053,8 @@ struct ntfs_log {
 
 	struct CLIENT_ID client_id;
 	u32 client_undo_commit;
+
+	struct restart_info rst_info, rst_info2;
 };
 
 static inline u32 lsn_to_vbo(struct ntfs_log *log, const u64 lsn)
@@ -1105,16 +1120,6 @@ static inline bool verify_client_lsn(struct ntfs_log *log,
 	       lsn <= le64_to_cpu(log->ra->current_lsn) && lsn;
 }
 
-struct restart_info {
-	u64 last_lsn;
-	struct RESTART_HDR *r_page;
-	u32 vbo;
-	bool chkdsk_was_run;
-	bool valid_page;
-	bool initialized;
-	bool restart;
-};
-
 static int read_log_page(struct ntfs_log *log, u32 vbo,
 			 struct RECORD_PAGE_HDR **buffer, bool *usa_error)
 {
@@ -1176,7 +1181,7 @@ out:
  * restart page header. It will stop the first time we find a
  * valid page header.
  */
-static int log_read_rst(struct ntfs_log *log, u32 l_size, bool first,
+static int log_read_rst(struct ntfs_log *log, bool first,
 			struct restart_info *info)
 {
 	u32 skip, vbo;
@@ -1192,7 +1197,7 @@ static int log_read_rst(struct ntfs_log *log, u32 l_size, bool first,
 	}
 
 	/* Loop continuously until we succeed. */
-	for (; vbo < l_size; vbo = 2 * vbo + skip, skip = 0) {
+	for (; vbo < log->l_size; vbo = 2 * vbo + skip, skip = 0) {
 		bool usa_error;
 		bool brst, bchk;
 		struct RESTART_AREA *ra;
@@ -1285,22 +1290,17 @@ check_result:
 /*
  * Ilog_init_pg_hdr - Init @log from restart page header.
  */
-static void log_init_pg_hdr(struct ntfs_log *log, u32 sys_page_size,
-			    u32 page_size, u16 major_ver, u16 minor_ver)
+static void log_init_pg_hdr(struct ntfs_log *log, u16 major_ver, u16 minor_ver)
 {
-	log->sys_page_size = sys_page_size;
-	log->sys_page_mask = sys_page_size - 1;
-	log->page_size = page_size;
-	log->page_mask = page_size - 1;
-	log->page_bits = blksize_bits(page_size);
+	log->sys_page_size = log->page_size;
+	log->sys_page_mask = log->page_mask;
 
 	log->clst_per_page = log->page_size >> log->ni->mi.sbi->cluster_bits;
 	if (!log->clst_per_page)
 		log->clst_per_page = 1;
 
-	log->first_page = major_ver >= 2 ?
-				  0x22 * page_size :
-				  ((sys_page_size << 1) + (page_size << 1));
+	log->first_page = major_ver >= 2 ? 0x22 * log->page_size :
+					   4 * log->page_size;
 	log->major_ver = major_ver;
 	log->minor_ver = minor_ver;
 }
@@ -1308,12 +1308,11 @@ static void log_init_pg_hdr(struct ntfs_log *log, u32 sys_page_size,
 /*
  * log_create - Init @log in cases when we don't have a restart area to use.
  */
-static void log_create(struct ntfs_log *log, u32 l_size, const u64 last_lsn,
+static void log_create(struct ntfs_log *log, const u64 last_lsn,
 		       u32 open_log_count, bool wrapped, bool use_multi_page)
 {
-	log->l_size = l_size;
 	/* All file offsets must be quadword aligned. */
-	log->file_data_bits = blksize_bits(l_size) - 3;
+	log->file_data_bits = blksize_bits(log->l_size) - 3;
 	log->seq_num_mask = (8 << log->file_data_bits) - 1;
 	log->seq_num_bits = sizeof(u64) * 8 - log->file_data_bits;
 	log->seq_num = (last_lsn >> log->file_data_bits) + 2;
@@ -3720,10 +3719,8 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
 	struct ntfs_sb_info *sbi = ni->mi.sbi;
 	struct ntfs_log *log;
 
-	struct restart_info rst_info, rst_info2;
-	u64 rec_lsn, ra_lsn, checkpt_lsn = 0, rlsn = 0;
+	u64 rec_lsn, checkpt_lsn = 0, rlsn = 0;
 	struct ATTR_NAME_ENTRY *attr_names = NULL;
-	struct ATTR_NAME_ENTRY *ane;
 	struct RESTART_TABLE *dptbl = NULL;
 	struct RESTART_TABLE *trtbl = NULL;
 	const struct RESTART_TABLE *rt;
@@ -3741,9 +3738,7 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
 	struct TRANSACTION_ENTRY *tr;
 	struct DIR_PAGE_ENTRY *dp;
 	u32 i, bytes_per_attr_entry;
-	u32 l_size = ni->vfs_inode.i_size;
-	u32 orig_file_size = l_size;
-	u32 page_size, vbo, tail, off, dlen;
+	u32 vbo, tail, off, dlen;
 	u32 saved_len, rec_len, transact_id;
 	bool use_second_page;
 	struct RESTART_AREA *ra2, *ra = NULL;
@@ -3758,52 +3753,50 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
 	u16 t16;
 	u32 t32;
 
-	/* Get the size of page. NOTE: To replay we can use default page. */
-#if PAGE_SIZE >= DefaultLogPageSize && PAGE_SIZE <= DefaultLogPageSize * 2
-	page_size = norm_file_page(PAGE_SIZE, &l_size, true);
-#else
-	page_size = norm_file_page(PAGE_SIZE, &l_size, false);
-#endif
-	if (!page_size)
-		return -EINVAL;
-
 	log = kzalloc(sizeof(struct ntfs_log), GFP_NOFS);
 	if (!log)
 		return -ENOMEM;
 
 	log->ni = ni;
-	log->l_size = l_size;
-	log->one_page_buf = kmalloc(page_size, GFP_NOFS);
+	log->l_size = log->orig_file_size = ni->vfs_inode.i_size;
 
+	/* Get the size of page. NOTE: To replay we can use default page. */
+#if PAGE_SIZE >= DefaultLogPageSize && PAGE_SIZE <= DefaultLogPageSize * 2
+	log->page_size = norm_file_page(PAGE_SIZE, &log->l_size, true);
+#else
+	log->page_size = norm_file_page(PAGE_SIZE, &log->l_size, false);
+#endif
+	if (!log->page_size) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	log->one_page_buf = kmalloc(log->page_size, GFP_NOFS);
 	if (!log->one_page_buf) {
 		err = -ENOMEM;
 		goto out;
 	}
 
-	log->page_size = page_size;
-	log->page_mask = page_size - 1;
-	log->page_bits = blksize_bits(page_size);
+	log->page_mask = log->page_size - 1;
+	log->page_bits = blksize_bits(log->page_size);
 
 	/* Look for a restart area on the disk. */
-	memset(&rst_info, 0, sizeof(struct restart_info));
-	err = log_read_rst(log, l_size, true, &rst_info);
+	err = log_read_rst(log, true, &log->rst_info);
 	if (err)
 		goto out;
 
 	/* remember 'initialized' */
-	*initialized = rst_info.initialized;
+	*initialized = log->rst_info.initialized;
 
-	if (!rst_info.restart) {
-		if (rst_info.initialized) {
+	if (!log->rst_info.restart) {
+		if (log->rst_info.initialized) {
 			/* No restart area but the file is not initialized. */
 			err = -EINVAL;
 			goto out;
 		}
 
-		log_init_pg_hdr(log, page_size, page_size, 1, 1);
-		log_create(log, l_size, 0, get_random_u32(), false, false);
-
-		log->ra = ra;
+		log_init_pg_hdr(log, 1, 1);
+		log_create(log, 0, get_random_u32(), false, false);
 
 		ra = log_create_ra(log);
 		if (!ra) {
@@ -3820,25 +3813,26 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
 	 * If the restart offset above wasn't zero then we won't
 	 * look for a second restart.
 	 */
-	if (rst_info.vbo)
+	if (log->rst_info.vbo)
 		goto check_restart_area;
 
-	memset(&rst_info2, 0, sizeof(struct restart_info));
-	err = log_read_rst(log, l_size, false, &rst_info2);
+	err = log_read_rst(log, false, &log->rst_info2);
 	if (err)
 		goto out;
 
 	/* Determine which restart area to use. */
-	if (!rst_info2.restart || rst_info2.last_lsn <= rst_info.last_lsn)
+	if (!log->rst_info2.restart ||
+	    log->rst_info2.last_lsn <= log->rst_info.last_lsn)
 		goto use_first_page;
 
 	use_second_page = true;
 
-	if (rst_info.chkdsk_was_run && page_size != rst_info.vbo) {
+	if (log->rst_info.chkdsk_was_run &&
+	    log->page_size != log->rst_info.vbo) {
 		struct RECORD_PAGE_HDR *sp = NULL;
 		bool usa_error;
 
-		if (!read_log_page(log, page_size, &sp, &usa_error) &&
+		if (!read_log_page(log, log->page_size, &sp, &usa_error) &&
 		    sp->rhdr.sign == NTFS_CHKD_SIGNATURE) {
 			use_second_page = false;
 		}
@@ -3846,52 +3840,43 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
 	}
 
 	if (use_second_page) {
-		kfree(rst_info.r_page);
-		memcpy(&rst_info, &rst_info2, sizeof(struct restart_info));
-		rst_info2.r_page = NULL;
+		kfree(log->rst_info.r_page);
+		memcpy(&log->rst_info, &log->rst_info2,
+		       sizeof(struct restart_info));
+		log->rst_info2.r_page = NULL;
 	}
 
 use_first_page:
-	kfree(rst_info2.r_page);
+	kfree(log->rst_info2.r_page);
 
 check_restart_area:
 	/*
 	 * If the restart area is at offset 0, we want
 	 * to write the second restart area first.
 	 */
-	log->init_ra = !!rst_info.vbo;
+	log->init_ra = !!log->rst_info.vbo;
 
 	/* If we have a valid page then grab a pointer to the restart area. */
-	ra2 = rst_info.valid_page ?
-		      Add2Ptr(rst_info.r_page,
-			      le16_to_cpu(rst_info.r_page->ra_off)) :
+	ra2 = log->rst_info.valid_page ?
+		      Add2Ptr(log->rst_info.r_page,
+			      le16_to_cpu(log->rst_info.r_page->ra_off)) :
 		      NULL;
 
-	if (rst_info.chkdsk_was_run ||
+	if (log->rst_info.chkdsk_was_run ||
 	    (ra2 && ra2->client_idx[1] == LFS_NO_CLIENT_LE)) {
 		bool wrapped = false;
 		bool use_multi_page = false;
 		u32 open_log_count;
 
 		/* Do some checks based on whether we have a valid log page. */
-		if (!rst_info.valid_page) {
-			open_log_count = get_random_u32();
-			goto init_log_instance;
-		}
-		open_log_count = le32_to_cpu(ra2->open_log_count);
-
-		/*
-		 * If the restart page size isn't changing then we want to
-		 * check how much work we need to do.
-		 */
-		if (page_size != le32_to_cpu(rst_info.r_page->sys_page_size))
-			goto init_log_instance;
+		open_log_count = log->rst_info.valid_page ?
+					 le32_to_cpu(ra2->open_log_count) :
+					 get_random_u32();
 
-init_log_instance:
-		log_init_pg_hdr(log, page_size, page_size, 1, 1);
+		log_init_pg_hdr(log, 1, 1);
 
-		log_create(log, l_size, rst_info.last_lsn, open_log_count,
-			   wrapped, use_multi_page);
+		log_create(log, log->rst_info.last_lsn, open_log_count, wrapped,
+			   use_multi_page);
 
 		ra = log_create_ra(log);
 		if (!ra) {
@@ -3916,28 +3901,27 @@ init_log_instance:
 	 * use the log file. We must use the system page size instead of the
 	 * default size if there is not a clean shutdown.
 	 */
-	t32 = le32_to_cpu(rst_info.r_page->sys_page_size);
-	if (page_size != t32) {
-		l_size = orig_file_size;
-		page_size =
-			norm_file_page(t32, &l_size, t32 == DefaultLogPageSize);
+	t32 = le32_to_cpu(log->rst_info.r_page->sys_page_size);
+	if (log->page_size != t32) {
+		log->l_size = log->orig_file_size;
+		log->page_size = norm_file_page(t32, &log->l_size,
+						t32 == DefaultLogPageSize);
 	}
 
-	if (page_size != t32 ||
-	    page_size != le32_to_cpu(rst_info.r_page->page_size)) {
+	if (log->page_size != t32 ||
+	    log->page_size != le32_to_cpu(log->rst_info.r_page->page_size)) {
 		err = -EINVAL;
 		goto out;
 	}
 
 	/* If the file size has shrunk then we won't mount it. */
-	if (l_size < le64_to_cpu(ra2->l_size)) {
+	if (log->l_size < le64_to_cpu(ra2->l_size)) {
 		err = -EINVAL;
 		goto out;
 	}
 
-	log_init_pg_hdr(log, page_size, page_size,
-			le16_to_cpu(rst_info.r_page->major_ver),
-			le16_to_cpu(rst_info.r_page->minor_ver));
+	log_init_pg_hdr(log, le16_to_cpu(log->rst_info.r_page->major_ver),
+			le16_to_cpu(log->rst_info.r_page->minor_ver));
 
 	log->l_size = le64_to_cpu(ra2->l_size);
 	log->seq_num_bits = le32_to_cpu(ra2->seq_num_bits);
@@ -3945,7 +3929,7 @@ init_log_instance:
 	log->seq_num_mask = (8 << log->file_data_bits) - 1;
 	log->last_lsn = le64_to_cpu(ra2->current_lsn);
 	log->seq_num = log->last_lsn >> log->file_data_bits;
-	log->ra_off = le16_to_cpu(rst_info.r_page->ra_off);
+	log->ra_off = le16_to_cpu(log->rst_info.r_page->ra_off);
 	log->restart_size = log->sys_page_size - log->ra_off;
 	log->record_header_len = le16_to_cpu(ra2->rec_hdr_len);
 	log->ra_size = le16_to_cpu(ra2->ra_len);
@@ -4045,7 +4029,7 @@ find_oldest:
 	log->current_avail = current_log_avail(log);
 
 	/* Remember which restart area to write first. */
-	log->init_ra = rst_info.vbo;
+	log->init_ra = log->rst_info.vbo;
 
 process_log:
 	/* 1.0, 1.1, 2.0 log->major_ver/minor_ver - short values. */
@@ -4105,7 +4089,7 @@ process_log:
 	log->client_id.seq_num = cr->seq_num;
 	log->client_id.client_idx = client;
 
-	err = read_rst_area(log, &rst, &ra_lsn);
+	err = read_rst_area(log, &rst, &checkpt_lsn);
 	if (err)
 		goto out;
 
@@ -4114,9 +4098,8 @@ process_log:
 
 	bytes_per_attr_entry = !rst->major_ver ? 0x2C : 0x28;
 
-	checkpt_lsn = le64_to_cpu(rst->check_point_start);
-	if (!checkpt_lsn)
-		checkpt_lsn = ra_lsn;
+	if (rst->check_point_start)
+		checkpt_lsn = le64_to_cpu(rst->check_point_start);
 
 	/* Allocate and Read the Transaction Table. */
 	if (!rst->transact_table_len)
@@ -4330,23 +4313,20 @@ check_attr_table:
 	lcb = NULL;
 
 check_attribute_names2:
-	if (!rst->attr_names_len)
-		goto trace_attribute_table;
-
-	ane = attr_names;
-	if (!oatbl)
-		goto trace_attribute_table;
-	while (ane->off) {
-		/* TODO: Clear table on exit! */
-		oe = Add2Ptr(oatbl, le16_to_cpu(ane->off));
-		t16 = le16_to_cpu(ane->name_bytes);
-		oe->name_len = t16 / sizeof(short);
-		oe->ptr = ane->name;
-		oe->is_attr_name = 2;
-		ane = Add2Ptr(ane, sizeof(struct ATTR_NAME_ENTRY) + t16);
-	}
-
-trace_attribute_table:
+	if (rst->attr_names_len && oatbl) {
+		struct ATTR_NAME_ENTRY *ane = attr_names;
+		while (ane->off) {
+			/* TODO: Clear table on exit! */
+			oe = Add2Ptr(oatbl, le16_to_cpu(ane->off));
+			t16 = le16_to_cpu(ane->name_bytes);
+			oe->name_len = t16 / sizeof(short);
+			oe->ptr = ane->name;
+			oe->is_attr_name = 2;
+			ane = Add2Ptr(ane,
+				      sizeof(struct ATTR_NAME_ENTRY) + t16);
+		}
+	}
+
 	/*
 	 * If the checkpt_lsn is zero, then this is a freshly
 	 * formatted disk and we have no work to do.
@@ -5189,7 +5169,7 @@ out:
 	kfree(oatbl);
 	kfree(dptbl);
 	kfree(attr_names);
-	kfree(rst_info.r_page);
+	kfree(log->rst_info.r_page);
 
 	kfree(ra);
 	kfree(log->one_page_buf);
diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c
index fbfe21dbb425..ae2ef5c11868 100644
--- a/fs/ntfs3/fsntfs.c
+++ b/fs/ntfs3/fsntfs.c
@@ -853,7 +853,8 @@ void ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait)
 	/*
 	 * sb can be NULL here. In this case sbi->flags should be 0 too.
 	 */
-	if (!sb || !(sbi->flags & NTFS_FLAGS_MFTMIRR))
+	if (!sb || !(sbi->flags & NTFS_FLAGS_MFTMIRR) ||
+	    unlikely(ntfs3_forced_shutdown(sb)))
 		return;
 
 	blocksize = sb->s_blocksize;
@@ -1006,6 +1007,30 @@ static inline __le32 security_hash(const void *sd, size_t bytes)
 	return cpu_to_le32(hash);
 }
 
+/*
+ * simple wrapper for sb_bread_unmovable.
+ */
+struct buffer_head *ntfs_bread(struct super_block *sb, sector_t block)
+{
+	struct ntfs_sb_info *sbi = sb->s_fs_info;
+	struct buffer_head *bh;
+
+	if (unlikely(block >= sbi->volume.blocks)) {
+		/* prevent generic message "attempt to access beyond end of device" */
+		ntfs_err(sb, "try to read out of volume at offset 0x%llx",
+			 (u64)block << sb->s_blocksize_bits);
+		return NULL;
+	}
+
+	bh = sb_bread_unmovable(sb, block);
+	if (bh)
+		return bh;
+
+	ntfs_err(sb, "failed to read volume at offset 0x%llx",
+		 (u64)block << sb->s_blocksize_bits);
+	return NULL;
+}
+
 int ntfs_sb_read(struct super_block *sb, u64 lbo, size_t bytes, void *buffer)
 {
 	struct block_device *bdev = sb->s_bdev;
@@ -2128,8 +2153,8 @@ int ntfs_insert_security(struct ntfs_sb_info *sbi,
 			if (le32_to_cpu(d_security->size) == new_sec_size &&
 			    d_security->key.hash == hash_key.hash &&
 			    !memcmp(d_security + 1, sd, size_sd)) {
-				*security_id = d_security->key.sec_id;
 				/* Such security already exists. */
+				*security_id = d_security->key.sec_id;
 				err = 0;
 				goto out;
 			}
diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c
index cf92b2433f7a..daabaad63aaf 100644
--- a/fs/ntfs3/index.c
+++ b/fs/ntfs3/index.c
@@ -1462,7 +1462,7 @@ static int indx_create_allocate(struct ntfs_index *indx, struct ntfs_inode *ni,
 		goto out2;
 
 	if (in->name == I30_NAME) {
-		ni->vfs_inode.i_size = data_size;
+		i_size_write(&ni->vfs_inode, data_size);
 		inode_set_bytes(&ni->vfs_inode, alloc_size);
 	}
 
@@ -1544,7 +1544,7 @@ static int indx_add_allocate(struct ntfs_index *indx, struct ntfs_inode *ni,
 	}
 
 	if (in->name == I30_NAME)
-		ni->vfs_inode.i_size = data_size;
+		i_size_write(&ni->vfs_inode, data_size);
 
 	*vbn = bit << indx->idx2vbn_bits;
 
@@ -2090,7 +2090,7 @@ static int indx_shrink(struct ntfs_index *indx, struct ntfs_inode *ni,
 		return err;
 
 	if (in->name == I30_NAME)
-		ni->vfs_inode.i_size = new_data;
+		i_size_write(&ni->vfs_inode, new_data);
 
 	bpb = bitmap_size(bit);
 	if (bpb * 8 == nbits)
@@ -2576,7 +2576,7 @@ int indx_delete_entry(struct ntfs_index *indx, struct ntfs_inode *ni,
 		err = attr_set_size(ni, ATTR_ALLOC, in->name, in->name_len,
 				    &indx->alloc_run, 0, NULL, false, NULL);
 		if (in->name == I30_NAME)
-			ni->vfs_inode.i_size = 0;
+			i_size_write(&ni->vfs_inode, 0);
 
 		err = ni_remove_attr(ni, ATTR_ALLOC, in->name, in->name_len,
 				     false, NULL);
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index 5e3d71374918..eb7a8c9fba01 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -345,9 +345,7 @@ next_attr:
 			inode->i_size = le16_to_cpu(rp.SymbolicLinkReparseBuffer
 							    .PrintNameLength) /
 					sizeof(u16);
-
 			ni->i_valid = inode->i_size;
-
 			/* Clear directory bit. */
 			if (ni->ni_flags & NI_FLAG_DIR) {
 				indx_clear(&ni->dir);
@@ -412,7 +410,6 @@ end_enum:
 		goto out;
 
 	if (!is_match && name) {
-		/* Reuse rec as buffer for ascii name. */
 		err = -ENOENT;
 		goto out;
 	}
@@ -427,6 +424,7 @@ end_enum:
 
 	if (names != le16_to_cpu(rec->hard_links)) {
 		/* Correct minor error on the fly. Do not mark inode as dirty. */
+		ntfs_inode_warn(inode, "Correct links count -> %u.", names);
 		rec->hard_links = cpu_to_le16(names);
 		ni->mi.dirty = true;
 	}
@@ -653,9 +651,10 @@ static noinline int ntfs_get_block_vbo(struct inode *inode, u64 vbo,
 			off = vbo & (PAGE_SIZE - 1);
 			folio_set_bh(bh, folio, off);
 
-			err = bh_read(bh, 0);
-			if (err < 0)
+			if (bh_read(bh, 0) < 0) {
+				err = -EIO;
 				goto out;
+			}
 			folio_zero_segment(folio, off + voff, off + block_size);
 		}
 	}
@@ -853,9 +852,13 @@ static int ntfs_resident_writepage(struct folio *folio,
 				   struct writeback_control *wbc, void *data)
 {
 	struct address_space *mapping = data;
-	struct ntfs_inode *ni = ntfs_i(mapping->host);
+	struct inode *inode = mapping->host;
+	struct ntfs_inode *ni = ntfs_i(inode);
 	int ret;
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	ni_lock(ni);
 	ret = attr_data_write_resident(ni, &folio->page);
 	ni_unlock(ni);
@@ -869,7 +872,12 @@ static int ntfs_resident_writepage(struct folio *folio,
 static int ntfs_writepages(struct address_space *mapping,
 			   struct writeback_control *wbc)
 {
-	if (is_resident(ntfs_i(mapping->host)))
+	struct inode *inode = mapping->host;
+
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
+	if (is_resident(ntfs_i(inode)))
 		return write_cache_pages(mapping, wbc, ntfs_resident_writepage,
 					 mapping);
 	return mpage_writepages(mapping, wbc, ntfs_get_block);
@@ -889,6 +897,9 @@ int ntfs_write_begin(struct file *file, struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	struct ntfs_inode *ni = ntfs_i(inode);
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	*pagep = NULL;
 	if (is_resident(ni)) {
 		struct page *page =
@@ -974,7 +985,7 @@ int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos,
 		}
 
 		if (pos + err > inode->i_size) {
-			inode->i_size = pos + err;
+			i_size_write(inode, pos + err);
 			dirty = true;
 		}
 
@@ -1306,6 +1317,11 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir,
 		goto out1;
 	}
 
+	if (unlikely(ntfs3_forced_shutdown(sb))) {
+		err = -EIO;
+		goto out2;
+	}
+
 	/* Mark rw ntfs as dirty. it will be cleared at umount. */
 	ntfs_set_state(sbi, NTFS_DIRTY_DIRTY);
 
diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c
index ee3093be5170..084d19d78397 100644
--- a/fs/ntfs3/namei.c
+++ b/fs/ntfs3/namei.c
@@ -181,6 +181,9 @@ static int ntfs_unlink(struct inode *dir, struct dentry *dentry)
 	struct ntfs_inode *ni = ntfs_i(dir);
 	int err;
 
+	if (unlikely(ntfs3_forced_shutdown(dir->i_sb)))
+		return -EIO;
+
 	ni_lock_dir(ni);
 
 	err = ntfs_unlink_inode(dir, dentry);
@@ -199,6 +202,9 @@ static int ntfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 	u32 size = strlen(symname);
 	struct inode *inode;
 
+	if (unlikely(ntfs3_forced_shutdown(dir->i_sb)))
+		return -EIO;
+
 	inode = ntfs_create_inode(idmap, dir, dentry, NULL, S_IFLNK | 0777, 0,
 				  symname, size, NULL);
 
@@ -227,6 +233,9 @@ static int ntfs_rmdir(struct inode *dir, struct dentry *dentry)
 	struct ntfs_inode *ni = ntfs_i(dir);
 	int err;
 
+	if (unlikely(ntfs3_forced_shutdown(dir->i_sb)))
+		return -EIO;
+
 	ni_lock_dir(ni);
 
 	err = ntfs_unlink_inode(dir, dentry);
@@ -264,6 +273,9 @@ static int ntfs_rename(struct mnt_idmap *idmap, struct inode *dir,
 		      1024);
 	static_assert(PATH_MAX >= 4 * 1024);
 
+	if (unlikely(ntfs3_forced_shutdown(sb)))
+		return -EIO;
+
 	if (flags & ~RENAME_NOREPLACE)
 		return -EINVAL;
 
@@ -419,7 +431,7 @@ static int ntfs_atomic_open(struct inode *dir, struct dentry *dentry,
 	 * fnd contains tree's path to insert to.
 	 * If fnd is not NULL then dir is locked.
 	 */
-	inode = ntfs_create_inode(mnt_idmap(file->f_path.mnt), dir, dentry, uni,
+	inode = ntfs_create_inode(file_mnt_idmap(file), dir, dentry, uni,
 				  mode, 0, NULL, 0, fnd);
 	err = IS_ERR(inode) ? PTR_ERR(inode) :
 			      finish_open(file, dentry, ntfs_file_open);
diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h
index 86aecbb01a92..9c7478150a03 100644
--- a/fs/ntfs3/ntfs.h
+++ b/fs/ntfs3/ntfs.h
@@ -523,12 +523,10 @@ struct ATTR_LIST_ENTRY {
 	__le64 vcn;		// 0x08: Starting VCN of this attribute.
 	struct MFT_REF ref;	// 0x10: MFT record number with attribute.
 	__le16 id;		// 0x18: struct ATTRIB ID.
-	__le16 name[3];		// 0x1A: Just to align. To get real name can use bNameOffset.
+	__le16 name[];		// 0x1A: To get real name use name_off.
 
 }; // sizeof(0x20)
 
-static_assert(sizeof(struct ATTR_LIST_ENTRY) == 0x20);
-
 static inline u32 le_size(u8 name_len)
 {
 	return ALIGN(offsetof(struct ATTR_LIST_ENTRY, name) +
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index f6706143d14b..79356fd29a14 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -61,6 +61,8 @@ enum utf16_endian;
 
 /* sbi->flags */
 #define NTFS_FLAGS_NODISCARD		0x00000001
+/* ntfs in shutdown state. */
+#define NTFS_FLAGS_SHUTDOWN_BIT		0x00000002  /* == 4*/
 /* Set when LogFile is replaying. */
 #define NTFS_FLAGS_LOG_REPLAYING	0x00000008
 /* Set when we changed first MFT's which copy must be updated in $MftMirr. */
@@ -226,7 +228,7 @@ struct ntfs_sb_info {
 	u64 maxbytes; // Maximum size for normal files.
 	u64 maxbytes_sparse; // Maximum size for sparse file.
 
-	u32 flags; // See NTFS_FLAGS_XXX.
+	unsigned long flags; // See NTFS_FLAGS_
 
 	CLST zone_max; // Maximum MFT zone length in clusters
 	CLST bad_clusters; // The count of marked bad clusters.
@@ -473,7 +475,7 @@ bool al_delete_le(struct ntfs_inode *ni, enum ATTR_TYPE type, CLST vcn,
 int al_update(struct ntfs_inode *ni, int sync);
 static inline size_t al_aligned(size_t size)
 {
-	return (size + 1023) & ~(size_t)1023;
+	return size_add(size, 1023) & ~(size_t)1023;
 }
 
 /* Globals from bitfunc.c */
@@ -500,6 +502,8 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 int ntfs_file_open(struct inode *inode, struct file *file);
 int ntfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		__u64 start, __u64 len);
+long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg);
+long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg);
 extern const struct inode_operations ntfs_special_inode_operations;
 extern const struct inode_operations ntfs_file_inode_operations;
 extern const struct file_operations ntfs_file_operations;
@@ -584,6 +588,7 @@ bool check_index_header(const struct INDEX_HDR *hdr, size_t bytes);
 int log_replay(struct ntfs_inode *ni, bool *initialized);
 
 /* Globals from fsntfs.c */
+struct buffer_head *ntfs_bread(struct super_block *sb, sector_t block);
 bool ntfs_fix_pre_write(struct NTFS_RECORD_HEADER *rhdr, size_t bytes);
 int ntfs_fix_post_read(struct NTFS_RECORD_HEADER *rhdr, size_t bytes,
 		       bool simple);
@@ -872,7 +877,7 @@ int ntfs_init_acl(struct mnt_idmap *idmap, struct inode *inode,
 
 int ntfs_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry);
 ssize_t ntfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
-extern const struct xattr_handler * const ntfs_xattr_handlers[];
+extern const struct xattr_handler *const ntfs_xattr_handlers[];
 
 int ntfs_save_wsl_perm(struct inode *inode, __le16 *ea_size);
 void ntfs_get_wsl_perm(struct inode *inode);
@@ -999,6 +1004,11 @@ static inline struct ntfs_sb_info *ntfs_sb(struct super_block *sb)
 	return sb->s_fs_info;
 }
 
+static inline int ntfs3_forced_shutdown(struct super_block *sb)
+{
+	return test_bit(NTFS_FLAGS_SHUTDOWN_BIT, &ntfs_sb(sb)->flags);
+}
+
 /*
  * ntfs_up_cluster - Align up on cluster boundary.
  */
@@ -1025,19 +1035,6 @@ static inline u64 bytes_to_block(const struct super_block *sb, u64 size)
 	return (size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
 }
 
-static inline struct buffer_head *ntfs_bread(struct super_block *sb,
-					     sector_t block)
-{
-	struct buffer_head *bh = sb_bread(sb, block);
-
-	if (bh)
-		return bh;
-
-	ntfs_err(sb, "failed to read volume at offset 0x%llx",
-		 (u64)block << sb->s_blocksize_bits);
-	return NULL;
-}
-
 static inline struct ntfs_inode *ntfs_i(struct inode *inode)
 {
 	return container_of(inode, struct ntfs_inode, vfs_inode);
diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c
index 53629b1f65e9..6aa3a9d44df1 100644
--- a/fs/ntfs3/record.c
+++ b/fs/ntfs3/record.c
@@ -279,7 +279,7 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
 		if (t16 > asize)
 			return NULL;
 
-		if (t16 + le32_to_cpu(attr->res.data_size) > asize)
+		if (le32_to_cpu(attr->res.data_size) > asize - t16)
 			return NULL;
 
 		t32 = sizeof(short) * attr->name_len;
@@ -535,8 +535,20 @@ bool mi_remove_attr(struct ntfs_inode *ni, struct mft_inode *mi,
 		return false;
 
 	if (ni && is_attr_indexed(attr)) {
-		le16_add_cpu(&ni->mi.mrec->hard_links, -1);
-		ni->mi.dirty = true;
+		u16 links = le16_to_cpu(ni->mi.mrec->hard_links);
+		struct ATTR_FILE_NAME *fname =
+			attr->type != ATTR_NAME ?
+				NULL :
+				resident_data_ex(attr,
+						 SIZEOF_ATTRIBUTE_FILENAME);
+		if (fname && fname->type == FILE_NAME_DOS) {
+			/* Do not decrease links count deleting DOS name. */
+		} else if (!links) {
+			/* minor error. Not critical. */
+		} else {
+			ni->mi.mrec->hard_links = cpu_to_le16(links - 1);
+			ni->mi.dirty = true;
+		}
 	}
 
 	used -= asize;
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index 9153dffde950..cef5467fd928 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -122,13 +122,12 @@ void ntfs_inode_printk(struct inode *inode, const char *fmt, ...)
 
 	if (name) {
 		struct dentry *de = d_find_alias(inode);
-		const u32 name_len = ARRAY_SIZE(s_name_buf) - 1;
 
 		if (de) {
 			spin_lock(&de->d_lock);
-			snprintf(name, name_len, " \"%s\"", de->d_name.name);
+			snprintf(name, sizeof(s_name_buf), " \"%s\"",
+				 de->d_name.name);
 			spin_unlock(&de->d_lock);
-			name[name_len] = 0; /* To be sure. */
 		} else {
 			name[0] = 0;
 		}
@@ -625,7 +624,7 @@ static void ntfs3_free_sbi(struct ntfs_sb_info *sbi)
 {
 	kfree(sbi->new_rec);
 	kvfree(ntfs_put_shared(sbi->upcase));
-	kfree(sbi->def_table);
+	kvfree(sbi->def_table);
 	kfree(sbi->compress.lznt);
 #ifdef CONFIG_NTFS3_LZX_XPRESS
 	xpress_free_decompressor(sbi->compress.xpress);
@@ -715,6 +714,14 @@ static int ntfs_show_options(struct seq_file *m, struct dentry *root)
 }
 
 /*
+ * ntfs_shutdown - super_operations::shutdown
+ */
+static void ntfs_shutdown(struct super_block *sb)
+{
+	set_bit(NTFS_FLAGS_SHUTDOWN_BIT, &ntfs_sb(sb)->flags);
+}
+
+/*
  * ntfs_sync_fs - super_operations::sync_fs
  */
 static int ntfs_sync_fs(struct super_block *sb, int wait)
@@ -724,6 +731,9 @@ static int ntfs_sync_fs(struct super_block *sb, int wait)
 	struct ntfs_inode *ni;
 	struct inode *inode;
 
+	if (unlikely(ntfs3_forced_shutdown(sb)))
+		return -EIO;
+
 	ni = sbi->security.ni;
 	if (ni) {
 		inode = &ni->vfs_inode;
@@ -763,6 +773,7 @@ static const struct super_operations ntfs_sops = {
 	.put_super = ntfs_put_super,
 	.statfs = ntfs_statfs,
 	.show_options = ntfs_show_options,
+	.shutdown = ntfs_shutdown,
 	.sync_fs = ntfs_sync_fs,
 	.write_inode = ntfs3_write_inode,
 };
@@ -866,6 +877,7 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size,
 	u16 fn, ao;
 	u8 cluster_bits;
 	u32 boot_off = 0;
+	sector_t boot_block = 0;
 	const char *hint = "Primary boot";
 
 	/* Save original dev_size. Used with alternative boot. */
@@ -873,11 +885,11 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size,
 
 	sbi->volume.blocks = dev_size >> PAGE_SHIFT;
 
-	bh = ntfs_bread(sb, 0);
+read_boot:
+	bh = ntfs_bread(sb, boot_block);
 	if (!bh)
-		return -EIO;
+		return boot_block ? -EINVAL : -EIO;
 
-check_boot:
 	err = -EINVAL;
 
 	/* Corrupted image; do not read OOB */
@@ -1108,26 +1120,24 @@ check_boot:
 	}
 
 out:
-	if (err == -EINVAL && !bh->b_blocknr && dev_size0 > PAGE_SHIFT) {
+	brelse(bh);
+
+	if (err == -EINVAL && !boot_block && dev_size0 > PAGE_SHIFT) {
 		u32 block_size = min_t(u32, sector_size, PAGE_SIZE);
 		u64 lbo = dev_size0 - sizeof(*boot);
 
-		/*
-	 	 * Try alternative boot (last sector)
-		 */
-		brelse(bh);
-
-		sb_set_blocksize(sb, block_size);
-		bh = ntfs_bread(sb, lbo >> blksize_bits(block_size));
-		if (!bh)
-			return -EINVAL;
-
+		boot_block = lbo >> blksize_bits(block_size);
 		boot_off = lbo & (block_size - 1);
-		hint = "Alternative boot";
-		dev_size = dev_size0; /* restore original size. */
-		goto check_boot;
+		if (boot_block && block_size >= boot_off + sizeof(*boot)) {
+			/*
+			 * Try alternative boot (last sector)
+			 */
+			sb_set_blocksize(sb, block_size);
+			hint = "Alternative boot";
+			dev_size = dev_size0; /* restore original size. */
+			goto read_boot;
+		}
 	}
-	brelse(bh);
 
 	return err;
 }
diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c
index 4274b6f31cfa..53e7d1fa036a 100644
--- a/fs/ntfs3/xattr.c
+++ b/fs/ntfs3/xattr.c
@@ -219,6 +219,9 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer,
 		if (!ea->name_len)
 			break;
 
+		if (ea->name_len > ea_size)
+			break;
+
 		if (buffer) {
 			/* Check if we can use field ea->name */
 			if (off + ea_size > size)
@@ -744,6 +747,9 @@ static int ntfs_getxattr(const struct xattr_handler *handler, struct dentry *de,
 	int err;
 	struct ntfs_inode *ni = ntfs_i(inode);
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	/* Dispatch request. */
 	if (!strcmp(name, SYSTEM_DOS_ATTRIB)) {
 		/* system.dos_attrib */
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 4d7efefa98c5..1bde1281d514 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -213,7 +213,7 @@ struct o2hb_region {
 	unsigned int		hr_num_pages;
 
 	struct page             **hr_slot_data;
-	struct bdev_handle	*hr_bdev_handle;
+	struct file		*hr_bdev_file;
 	struct o2hb_disk_slot	*hr_slots;
 
 	/* live node map of this region */
@@ -263,7 +263,7 @@ struct o2hb_region {
 
 static inline struct block_device *reg_bdev(struct o2hb_region *reg)
 {
-	return reg->hr_bdev_handle ? reg->hr_bdev_handle->bdev : NULL;
+	return reg->hr_bdev_file ? file_bdev(reg->hr_bdev_file) : NULL;
 }
 
 struct o2hb_bio_wait_ctxt {
@@ -1509,8 +1509,8 @@ static void o2hb_region_release(struct config_item *item)
 		kfree(reg->hr_slot_data);
 	}
 
-	if (reg->hr_bdev_handle)
-		bdev_release(reg->hr_bdev_handle);
+	if (reg->hr_bdev_file)
+		fput(reg->hr_bdev_file);
 
 	kfree(reg->hr_slots);
 
@@ -1569,7 +1569,7 @@ static ssize_t o2hb_region_block_bytes_store(struct config_item *item,
 	unsigned long block_bytes;
 	unsigned int block_bits;
 
-	if (reg->hr_bdev_handle)
+	if (reg->hr_bdev_file)
 		return -EINVAL;
 
 	status = o2hb_read_block_input(reg, page, &block_bytes,
@@ -1598,7 +1598,7 @@ static ssize_t o2hb_region_start_block_store(struct config_item *item,
 	char *p = (char *)page;
 	ssize_t ret;
 
-	if (reg->hr_bdev_handle)
+	if (reg->hr_bdev_file)
 		return -EINVAL;
 
 	ret = kstrtoull(p, 0, &tmp);
@@ -1623,7 +1623,7 @@ static ssize_t o2hb_region_blocks_store(struct config_item *item,
 	unsigned long tmp;
 	char *p = (char *)page;
 
-	if (reg->hr_bdev_handle)
+	if (reg->hr_bdev_file)
 		return -EINVAL;
 
 	tmp = simple_strtoul(p, &p, 0);
@@ -1642,7 +1642,7 @@ static ssize_t o2hb_region_dev_show(struct config_item *item, char *page)
 {
 	unsigned int ret = 0;
 
-	if (to_o2hb_region(item)->hr_bdev_handle)
+	if (to_o2hb_region(item)->hr_bdev_file)
 		ret = sprintf(page, "%pg\n", reg_bdev(to_o2hb_region(item)));
 
 	return ret;
@@ -1753,7 +1753,7 @@ out:
 }
 
 /*
- * this is acting as commit; we set up all of hr_bdev_handle and hr_task or
+ * this is acting as commit; we set up all of hr_bdev_file and hr_task or
  * nothing
  */
 static ssize_t o2hb_region_dev_store(struct config_item *item,
@@ -1769,7 +1769,7 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
 	ssize_t ret = -EINVAL;
 	int live_threshold;
 
-	if (reg->hr_bdev_handle)
+	if (reg->hr_bdev_file)
 		goto out;
 
 	/* We can't heartbeat without having had our node number
@@ -1795,11 +1795,11 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
 	if (!S_ISBLK(f.file->f_mapping->host->i_mode))
 		goto out2;
 
-	reg->hr_bdev_handle = bdev_open_by_dev(f.file->f_mapping->host->i_rdev,
+	reg->hr_bdev_file = bdev_file_open_by_dev(f.file->f_mapping->host->i_rdev,
 			BLK_OPEN_WRITE | BLK_OPEN_READ, NULL, NULL);
-	if (IS_ERR(reg->hr_bdev_handle)) {
-		ret = PTR_ERR(reg->hr_bdev_handle);
-		reg->hr_bdev_handle = NULL;
+	if (IS_ERR(reg->hr_bdev_file)) {
+		ret = PTR_ERR(reg->hr_bdev_file);
+		reg->hr_bdev_file = NULL;
 		goto out2;
 	}
 
@@ -1903,8 +1903,8 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
 
 out3:
 	if (ret < 0) {
-		bdev_release(reg->hr_bdev_handle);
-		reg->hr_bdev_handle = NULL;
+		fput(reg->hr_bdev_file);
+		reg->hr_bdev_file = NULL;
 	}
 out2:
 	fdput(f);
diff --git a/fs/ocfs2/locks.c b/fs/ocfs2/locks.c
index f37174e79fad..6de944818c56 100644
--- a/fs/ocfs2/locks.c
+++ b/fs/ocfs2/locks.c
@@ -27,7 +27,7 @@ static int ocfs2_do_flock(struct file *file, struct inode *inode,
 	struct ocfs2_file_private *fp = file->private_data;
 	struct ocfs2_lock_res *lockres = &fp->fp_flock;
 
-	if (fl->fl_type == F_WRLCK)
+	if (lock_is_write(fl))
 		level = 1;
 	if (!IS_SETLKW(cmd))
 		trylock = 1;
@@ -53,8 +53,8 @@ static int ocfs2_do_flock(struct file *file, struct inode *inode,
 		 */
 
 		locks_init_lock(&request);
-		request.fl_type = F_UNLCK;
-		request.fl_flags = FL_FLOCK;
+		request.c.flc_type = F_UNLCK;
+		request.c.flc_flags = FL_FLOCK;
 		locks_lock_file_wait(file, &request);
 
 		ocfs2_file_unlock(file);
@@ -100,14 +100,14 @@ int ocfs2_flock(struct file *file, int cmd, struct file_lock *fl)
 	struct inode *inode = file->f_mapping->host;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
-	if (!(fl->fl_flags & FL_FLOCK))
+	if (!(fl->c.flc_flags & FL_FLOCK))
 		return -ENOLCK;
 
 	if ((osb->s_mount_opt & OCFS2_MOUNT_LOCALFLOCKS) ||
 	    ocfs2_mount_local(osb))
 		return locks_lock_file_wait(file, fl);
 
-	if (fl->fl_type == F_UNLCK)
+	if (lock_is_unlock(fl))
 		return ocfs2_do_funlock(file, cmd, fl);
 	else
 		return ocfs2_do_flock(file, inode, cmd, fl);
@@ -118,7 +118,7 @@ int ocfs2_lock(struct file *file, int cmd, struct file_lock *fl)
 	struct inode *inode = file->f_mapping->host;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
-	if (!(fl->fl_flags & FL_POSIX))
+	if (!(fl->c.flc_flags & FL_POSIX))
 		return -ENOLCK;
 
 	return ocfs2_plock(osb->cconn, OCFS2_I(inode)->ip_blkno, file, cmd, fl);
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index 9b76ee66aeb2..c11406cd87a8 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -744,7 +744,7 @@ static int user_plock(struct ocfs2_cluster_connection *conn,
 		return dlm_posix_cancel(conn->cc_lockspace, ino, file, fl);
 	else if (IS_GETLK(cmd))
 		return dlm_posix_get(conn->cc_lockspace, ino, file, fl);
-	else if (fl->fl_type == F_UNLCK)
+	else if (lock_is_unlock(fl))
 		return dlm_posix_unlock(conn->cc_lockspace, ino, file, fl);
 	else
 		return dlm_posix_lock(conn->cc_lockspace, ino, file, cmd, fl);
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 6b906424902b..a70aff17d455 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -2027,8 +2027,8 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	cbits = le32_to_cpu(di->id2.i_super.s_clustersize_bits);
 	bbits = le32_to_cpu(di->id2.i_super.s_blocksize_bits);
 	sb->s_maxbytes = ocfs2_max_file_offset(bbits, cbits);
-	memcpy(&sb->s_uuid, di->id2.i_super.s_uuid,
-	       sizeof(di->id2.i_super.s_uuid));
+	super_set_uuid(sb, di->id2.i_super.s_uuid,
+		       sizeof(di->id2.i_super.s_uuid));
 
 	osb->osb_dx_mask = (1 << (cbits - bbits)) - 1;
 
diff --git a/fs/open.c b/fs/open.c
index a84d21e55c39..a7d4bb2c725f 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -154,49 +154,52 @@ COMPAT_SYSCALL_DEFINE2(truncate, const char __user *, path, compat_off_t, length
 }
 #endif
 
-long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
+long do_ftruncate(struct file *file, loff_t length, int small)
 {
 	struct inode *inode;
 	struct dentry *dentry;
-	struct fd f;
 	int error;
 
-	error = -EINVAL;
-	if (length < 0)
-		goto out;
-	error = -EBADF;
-	f = fdget(fd);
-	if (!f.file)
-		goto out;
-
 	/* explicitly opened as large or we are on 64-bit box */
-	if (f.file->f_flags & O_LARGEFILE)
+	if (file->f_flags & O_LARGEFILE)
 		small = 0;
 
-	dentry = f.file->f_path.dentry;
+	dentry = file->f_path.dentry;
 	inode = dentry->d_inode;
-	error = -EINVAL;
-	if (!S_ISREG(inode->i_mode) || !(f.file->f_mode & FMODE_WRITE))
-		goto out_putf;
+	if (!S_ISREG(inode->i_mode) || !(file->f_mode & FMODE_WRITE))
+		return -EINVAL;
 
-	error = -EINVAL;
 	/* Cannot ftruncate over 2^31 bytes without large file support */
 	if (small && length > MAX_NON_LFS)
-		goto out_putf;
+		return -EINVAL;
 
-	error = -EPERM;
 	/* Check IS_APPEND on real upper inode */
-	if (IS_APPEND(file_inode(f.file)))
-		goto out_putf;
+	if (IS_APPEND(file_inode(file)))
+		return -EPERM;
 	sb_start_write(inode->i_sb);
-	error = security_file_truncate(f.file);
+	error = security_file_truncate(file);
 	if (!error)
-		error = do_truncate(file_mnt_idmap(f.file), dentry, length,
-				    ATTR_MTIME | ATTR_CTIME, f.file);
+		error = do_truncate(file_mnt_idmap(file), dentry, length,
+				    ATTR_MTIME | ATTR_CTIME, file);
 	sb_end_write(inode->i_sb);
-out_putf:
+
+	return error;
+}
+
+long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
+{
+	struct fd f;
+	int error;
+
+	if (length < 0)
+		return -EINVAL;
+	f = fdget(fd);
+	if (!f.file)
+		return -EBADF;
+
+	error = do_ftruncate(f.file, length, small);
+
 	fdput(f);
-out:
 	return error;
 }
 
@@ -1364,7 +1367,7 @@ struct file *filp_open(const char *filename, int flags, umode_t mode)
 {
 	struct filename *name = getname_kernel(filename);
 	struct file *file = ERR_CAST(name);
-	
+
 	if (!IS_ERR(name)) {
 		file = file_open_name(name, flags, mode);
 		putname(name);
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index c4b65a6d41cc..4a0779e3ef79 100644
--- a/fs/openpromfs/inode.c
+++ b/fs/openpromfs/inode.c
@@ -446,7 +446,7 @@ static int __init init_openprom_fs(void)
 					    sizeof(struct op_inode_info),
 					    0,
 					    (SLAB_RECLAIM_ACCOUNT |
-					     SLAB_MEM_SPREAD | SLAB_ACCOUNT),
+					     SLAB_ACCOUNT),
 					    op_inode_init_once);
 	if (!op_inode_cachep)
 		return -ENOMEM;
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index b8e25ca51016..8586e2f5d243 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -265,20 +265,18 @@ static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry,
 	if (IS_ERR(old_file))
 		return PTR_ERR(old_file);
 
+	/* Try to use clone_file_range to clone up within the same fs */
+	cloned = vfs_clone_file_range(old_file, 0, new_file, 0, len, 0);
+	if (cloned == len)
+		goto out_fput;
+
+	/* Couldn't clone, so now we try to copy the data */
 	error = rw_verify_area(READ, old_file, &old_pos, len);
 	if (!error)
 		error = rw_verify_area(WRITE, new_file, &new_pos, len);
 	if (error)
 		goto out_fput;
 
-	/* Try to use clone_file_range to clone up within the same fs */
-	ovl_start_write(dentry);
-	cloned = do_clone_file_range(old_file, 0, new_file, 0, len, 0);
-	ovl_end_write(dentry);
-	if (cloned == len)
-		goto out_fput;
-	/* Couldn't clone, so now we try to copy the data */
-
 	/* Check if lower fs supports seek operation */
 	if (old_file->f_mode & FMODE_LSEEK)
 		skip_hole = true;
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index 984ffdaeed6c..5764f91d283e 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -18,10 +18,11 @@
 
 struct ovl_lookup_data {
 	struct super_block *sb;
-	struct vfsmount *mnt;
+	const struct ovl_layer *layer;
 	struct qstr name;
 	bool is_dir;
 	bool opaque;
+	bool xwhiteouts;
 	bool stop;
 	bool last;
 	char *redirect;
@@ -201,17 +202,13 @@ struct dentry *ovl_decode_real_fh(struct ovl_fs *ofs, struct ovl_fh *fh,
 	return real;
 }
 
-static bool ovl_is_opaquedir(struct ovl_fs *ofs, const struct path *path)
-{
-	return ovl_path_check_dir_xattr(ofs, path, OVL_XATTR_OPAQUE);
-}
-
 static struct dentry *ovl_lookup_positive_unlocked(struct ovl_lookup_data *d,
 						   const char *name,
 						   struct dentry *base, int len,
 						   bool drop_negative)
 {
-	struct dentry *ret = lookup_one_unlocked(mnt_idmap(d->mnt), name, base, len);
+	struct dentry *ret = lookup_one_unlocked(mnt_idmap(d->layer->mnt), name,
+						 base, len);
 
 	if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) {
 		if (drop_negative && ret->d_lockref.count == 1) {
@@ -232,10 +229,13 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d,
 			     size_t prelen, const char *post,
 			     struct dentry **ret, bool drop_negative)
 {
+	struct ovl_fs *ofs = OVL_FS(d->sb);
 	struct dentry *this;
 	struct path path;
 	int err;
 	bool last_element = !post[0];
+	bool is_upper = d->layer->idx == 0;
+	char val;
 
 	this = ovl_lookup_positive_unlocked(d, name, base, namelen, drop_negative);
 	if (IS_ERR(this)) {
@@ -253,8 +253,8 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d,
 	}
 
 	path.dentry = this;
-	path.mnt = d->mnt;
-	if (ovl_path_is_whiteout(OVL_FS(d->sb), &path)) {
+	path.mnt = d->layer->mnt;
+	if (ovl_path_is_whiteout(ofs, &path)) {
 		d->stop = d->opaque = true;
 		goto put_and_out;
 	}
@@ -272,7 +272,7 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d,
 			d->stop = true;
 			goto put_and_out;
 		}
-		err = ovl_check_metacopy_xattr(OVL_FS(d->sb), &path, NULL);
+		err = ovl_check_metacopy_xattr(ofs, &path, NULL);
 		if (err < 0)
 			goto out_err;
 
@@ -292,7 +292,12 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d,
 		if (d->last)
 			goto out;
 
-		if (ovl_is_opaquedir(OVL_FS(d->sb), &path)) {
+		/* overlay.opaque=x means xwhiteouts directory */
+		val = ovl_get_opaquedir_val(ofs, &path);
+		if (last_element && !is_upper && val == 'x') {
+			d->xwhiteouts = true;
+			ovl_layer_set_xwhiteouts(ofs, d->layer);
+		} else if (val == 'y') {
 			d->stop = true;
 			if (last_element)
 				d->opaque = true;
@@ -863,7 +868,8 @@ fail:
  * Returns next layer in stack starting from top.
  * Returns -1 if this is the last layer.
  */
-int ovl_path_next(int idx, struct dentry *dentry, struct path *path)
+int ovl_path_next(int idx, struct dentry *dentry, struct path *path,
+		  const struct ovl_layer **layer)
 {
 	struct ovl_entry *oe = OVL_E(dentry);
 	struct ovl_path *lowerstack = ovl_lowerstack(oe);
@@ -871,13 +877,16 @@ int ovl_path_next(int idx, struct dentry *dentry, struct path *path)
 	BUG_ON(idx < 0);
 	if (idx == 0) {
 		ovl_path_upper(dentry, path);
-		if (path->dentry)
+		if (path->dentry) {
+			*layer = &OVL_FS(dentry->d_sb)->layers[0];
 			return ovl_numlower(oe) ? 1 : -1;
+		}
 		idx++;
 	}
 	BUG_ON(idx > ovl_numlower(oe));
 	path->dentry = lowerstack[idx - 1].dentry;
-	path->mnt = lowerstack[idx - 1].layer->mnt;
+	*layer = lowerstack[idx - 1].layer;
+	path->mnt = (*layer)->mnt;
 
 	return (idx < ovl_numlower(oe)) ? idx + 1 : -1;
 }
@@ -1055,7 +1064,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 	old_cred = ovl_override_creds(dentry->d_sb);
 	upperdir = ovl_dentry_upper(dentry->d_parent);
 	if (upperdir) {
-		d.mnt = ovl_upper_mnt(ofs);
+		d.layer = &ofs->layers[0];
 		err = ovl_lookup_layer(upperdir, &d, &upperdentry, true);
 		if (err)
 			goto out;
@@ -1111,7 +1120,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 		else if (d.is_dir || !ofs->numdatalayer)
 			d.last = lower.layer->idx == ovl_numlower(roe);
 
-		d.mnt = lower.layer->mnt;
+		d.layer = lower.layer;
 		err = ovl_lookup_layer(lower.dentry, &d, &this, false);
 		if (err)
 			goto out_put;
@@ -1278,6 +1287,8 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 
 	if (upperopaque)
 		ovl_dentry_set_opaque(dentry);
+	if (d.xwhiteouts)
+		ovl_dentry_set_xwhiteouts(dentry);
 
 	if (upperdentry)
 		ovl_dentry_set_upper_alias(dentry);
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 5ba11eb43767..ee949f3e7c77 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -50,7 +50,6 @@ enum ovl_xattr {
 	OVL_XATTR_METACOPY,
 	OVL_XATTR_PROTATTR,
 	OVL_XATTR_XWHITEOUT,
-	OVL_XATTR_XWHITEOUTS,
 };
 
 enum ovl_inode_flag {
@@ -70,6 +69,8 @@ enum ovl_entry_flag {
 	OVL_E_UPPER_ALIAS,
 	OVL_E_OPAQUE,
 	OVL_E_CONNECTED,
+	/* Lower stack may contain xwhiteout entries */
+	OVL_E_XWHITEOUTS,
 };
 
 enum {
@@ -477,6 +478,10 @@ bool ovl_dentry_test_flag(unsigned long flag, struct dentry *dentry);
 bool ovl_dentry_is_opaque(struct dentry *dentry);
 bool ovl_dentry_is_whiteout(struct dentry *dentry);
 void ovl_dentry_set_opaque(struct dentry *dentry);
+bool ovl_dentry_has_xwhiteouts(struct dentry *dentry);
+void ovl_dentry_set_xwhiteouts(struct dentry *dentry);
+void ovl_layer_set_xwhiteouts(struct ovl_fs *ofs,
+			      const struct ovl_layer *layer);
 bool ovl_dentry_has_upper_alias(struct dentry *dentry);
 void ovl_dentry_set_upper_alias(struct dentry *dentry);
 bool ovl_dentry_needs_data_copy_up(struct dentry *dentry, int flags);
@@ -494,11 +499,10 @@ struct file *ovl_path_open(const struct path *path, int flags);
 int ovl_copy_up_start(struct dentry *dentry, int flags);
 void ovl_copy_up_end(struct dentry *dentry);
 bool ovl_already_copied_up(struct dentry *dentry, int flags);
-bool ovl_path_check_dir_xattr(struct ovl_fs *ofs, const struct path *path,
-			      enum ovl_xattr ox);
+char ovl_get_dir_xattr_val(struct ovl_fs *ofs, const struct path *path,
+			   enum ovl_xattr ox);
 bool ovl_path_check_origin_xattr(struct ovl_fs *ofs, const struct path *path);
 bool ovl_path_check_xwhiteout_xattr(struct ovl_fs *ofs, const struct path *path);
-bool ovl_path_check_xwhiteouts_xattr(struct ovl_fs *ofs, const struct path *path);
 bool ovl_init_uuid_xattr(struct super_block *sb, struct ovl_fs *ofs,
 			 const struct path *upperpath);
 
@@ -573,7 +577,13 @@ static inline bool ovl_is_impuredir(struct super_block *sb,
 		.mnt = ovl_upper_mnt(ofs),
 	};
 
-	return ovl_path_check_dir_xattr(ofs, &upperpath, OVL_XATTR_IMPURE);
+	return ovl_get_dir_xattr_val(ofs, &upperpath, OVL_XATTR_IMPURE) == 'y';
+}
+
+static inline char ovl_get_opaquedir_val(struct ovl_fs *ofs,
+					 const struct path *path)
+{
+	return ovl_get_dir_xattr_val(ofs, path, OVL_XATTR_OPAQUE);
 }
 
 static inline bool ovl_redirect_follow(struct ovl_fs *ofs)
@@ -680,7 +690,8 @@ int ovl_get_index_name(struct ovl_fs *ofs, struct dentry *origin,
 struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh);
 struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper,
 				struct dentry *origin, bool verify);
-int ovl_path_next(int idx, struct dentry *dentry, struct path *path);
+int ovl_path_next(int idx, struct dentry *dentry, struct path *path,
+		  const struct ovl_layer **layer);
 int ovl_verify_lowerdata(struct dentry *dentry);
 struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			  unsigned int flags);
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index 5fa9c58af65f..cb449ab310a7 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -40,6 +40,8 @@ struct ovl_layer {
 	int idx;
 	/* One fsid per unique underlying sb (upper fsid == 0) */
 	int fsid;
+	/* xwhiteouts were found on this layer */
+	bool has_xwhiteouts;
 };
 
 struct ovl_path {
@@ -59,7 +61,7 @@ struct ovl_fs {
 	unsigned int numfs;
 	/* Number of data-only lower layers */
 	unsigned int numdatalayer;
-	const struct ovl_layer *layers;
+	struct ovl_layer *layers;
 	struct ovl_sb *fs;
 	/* workbasedir is the path at workdir= mount option */
 	struct dentry *workbasedir;
diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c
index 112b4b12f825..36dcc530ac28 100644
--- a/fs/overlayfs/params.c
+++ b/fs/overlayfs/params.c
@@ -280,12 +280,20 @@ static int ovl_mount_dir_check(struct fs_context *fc, const struct path *path,
 {
 	struct ovl_fs_context *ctx = fc->fs_private;
 
-	if (ovl_dentry_weird(path->dentry))
-		return invalfc(fc, "filesystem on %s not supported", name);
-
 	if (!d_is_dir(path->dentry))
 		return invalfc(fc, "%s is not a directory", name);
 
+	/*
+	 * Root dentries of case-insensitive capable filesystems might
+	 * not have the dentry operations set, but still be incompatible
+	 * with overlayfs.  Check explicitly to prevent post-mount
+	 * failures.
+	 */
+	if (sb_has_encoding(path->mnt->mnt_sb))
+		return invalfc(fc, "case-insensitive capable filesystem on %s not supported", name);
+
+	if (ovl_dentry_weird(path->dentry))
+		return invalfc(fc, "filesystem on %s not supported", name);
 
 	/*
 	 * Check whether upper path is read-only here to report failures
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index e71156baa7bc..0ca8af060b0c 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -305,8 +305,6 @@ static inline int ovl_dir_read(const struct path *realpath,
 	if (IS_ERR(realfile))
 		return PTR_ERR(realfile);
 
-	rdd->in_xwhiteouts_dir = rdd->dentry &&
-		ovl_path_check_xwhiteouts_xattr(OVL_FS(rdd->dentry->d_sb), realpath);
 	rdd->first_maybe_whiteout = NULL;
 	rdd->ctx.pos = 0;
 	do {
@@ -359,10 +357,13 @@ static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list,
 		.is_lowest = false,
 	};
 	int idx, next;
+	const struct ovl_layer *layer;
 
 	for (idx = 0; idx != -1; idx = next) {
-		next = ovl_path_next(idx, dentry, &realpath);
+		next = ovl_path_next(idx, dentry, &realpath, &layer);
 		rdd.is_upper = ovl_dentry_upper(dentry) == realpath.dentry;
+		rdd.in_xwhiteouts_dir = layer->has_xwhiteouts &&
+					ovl_dentry_has_xwhiteouts(dentry);
 
 		if (next != -1) {
 			err = ovl_dir_read(&realpath, &rdd);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 4ab66e3d4cff..36d4b8b1f784 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -28,41 +28,38 @@ MODULE_LICENSE("GPL");
 
 struct ovl_dir_cache;
 
-static struct dentry *ovl_d_real(struct dentry *dentry,
-				 const struct inode *inode)
+static struct dentry *ovl_d_real(struct dentry *dentry, enum d_real_type type)
 {
-	struct dentry *real = NULL, *lower;
+	struct dentry *upper, *lower;
 	int err;
 
-	/*
-	 * vfs is only expected to call d_real() with NULL from d_real_inode()
-	 * and with overlay inode from file_dentry() on an overlay file.
-	 *
-	 * TODO: remove @inode argument from d_real() API, remove code in this
-	 * function that deals with non-NULL @inode and remove d_real() call
-	 * from file_dentry().
-	 */
-	if (inode && d_inode(dentry) == inode)
-		return dentry;
-	else if (inode)
+	switch (type) {
+	case D_REAL_DATA:
+	case D_REAL_METADATA:
+		break;
+	default:
 		goto bug;
+	}
 
 	if (!d_is_reg(dentry)) {
 		/* d_real_inode() is only relevant for regular files */
 		return dentry;
 	}
 
-	real = ovl_dentry_upper(dentry);
-	if (real && (inode == d_inode(real)))
-		return real;
+	upper = ovl_dentry_upper(dentry);
+	if (upper && (type == D_REAL_METADATA ||
+		      ovl_has_upperdata(d_inode(dentry))))
+		return upper;
 
-	if (real && !inode && ovl_has_upperdata(d_inode(dentry)))
-		return real;
+	if (type == D_REAL_METADATA) {
+		lower = ovl_dentry_lower(dentry);
+		goto real_lower;
+	}
 
 	/*
-	 * Best effort lazy lookup of lowerdata for !inode case to return
+	 * Best effort lazy lookup of lowerdata for D_REAL_DATA case to return
 	 * the real lowerdata dentry.  The only current caller of d_real() with
-	 * NULL inode is d_real_inode() from trace_uprobe and this caller is
+	 * D_REAL_DATA is d_real_inode() from trace_uprobe and this caller is
 	 * likely going to be followed reading from the file, before placing
 	 * uprobes on offset within the file, so lowerdata should be available
 	 * when setting the uprobe.
@@ -73,18 +70,13 @@ static struct dentry *ovl_d_real(struct dentry *dentry,
 	lower = ovl_dentry_lowerdata(dentry);
 	if (!lower)
 		goto bug;
-	real = lower;
 
-	/* Handle recursion */
-	real = d_real(real, inode);
+real_lower:
+	/* Handle recursion into stacked lower fs */
+	return d_real(lower, type);
 
-	if (!inode || inode == d_inode(real))
-		return real;
 bug:
-	WARN(1, "%s(%pd4, %s:%lu): real dentry (%p/%lu) not found\n",
-	     __func__, dentry, inode ? inode->i_sb->s_id : "NULL",
-	     inode ? inode->i_ino : 0, real,
-	     real && d_inode(real) ? d_inode(real)->i_ino : 0);
+	WARN(1, "%s(%pd4, %d): real dentry not found\n", __func__, dentry, type);
 	return dentry;
 }
 
@@ -1249,6 +1241,7 @@ static struct dentry *ovl_get_root(struct super_block *sb,
 				   struct ovl_entry *oe)
 {
 	struct dentry *root;
+	struct ovl_fs *ofs = OVL_FS(sb);
 	struct ovl_path *lowerpath = ovl_lowerstack(oe);
 	unsigned long ino = d_inode(lowerpath->dentry)->i_ino;
 	int fsid = lowerpath->layer->fsid;
@@ -1270,6 +1263,20 @@ static struct dentry *ovl_get_root(struct super_block *sb,
 			ovl_set_flag(OVL_IMPURE, d_inode(root));
 	}
 
+	/* Look for xwhiteouts marker except in the lowermost layer */
+	for (int i = 0; i < ovl_numlower(oe) - 1; i++, lowerpath++) {
+		struct path path = {
+			.mnt = lowerpath->layer->mnt,
+			.dentry = lowerpath->dentry,
+		};
+
+		/* overlay.opaque=x means xwhiteouts directory */
+		if (ovl_get_opaquedir_val(ofs, &path) == 'x') {
+			ovl_layer_set_xwhiteouts(ofs, lowerpath->layer);
+			ovl_dentry_set_xwhiteouts(root);
+		}
+	}
+
 	/* Root is always merge -> can have whiteouts */
 	ovl_set_flag(OVL_WHITEOUTS, d_inode(root));
 	ovl_dentry_set_flag(OVL_E_CONNECTED, root);
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 0217094c23ea..d285d1d7baad 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -461,6 +461,33 @@ void ovl_dentry_set_opaque(struct dentry *dentry)
 	ovl_dentry_set_flag(OVL_E_OPAQUE, dentry);
 }
 
+bool ovl_dentry_has_xwhiteouts(struct dentry *dentry)
+{
+	return ovl_dentry_test_flag(OVL_E_XWHITEOUTS, dentry);
+}
+
+void ovl_dentry_set_xwhiteouts(struct dentry *dentry)
+{
+	ovl_dentry_set_flag(OVL_E_XWHITEOUTS, dentry);
+}
+
+/*
+ * ovl_layer_set_xwhiteouts() is called before adding the overlay dir
+ * dentry to dcache, while readdir of that same directory happens after
+ * the overlay dir dentry is in dcache, so if some cpu observes that
+ * ovl_dentry_is_xwhiteouts(), it will also observe layer->has_xwhiteouts
+ * for the layers where xwhiteouts marker was found in that merge dir.
+ */
+void ovl_layer_set_xwhiteouts(struct ovl_fs *ofs,
+			      const struct ovl_layer *layer)
+{
+	if (layer->has_xwhiteouts)
+		return;
+
+	/* Write once to read-mostly layer properties */
+	ofs->layers[layer->idx].has_xwhiteouts = true;
+}
+
 /*
  * For hard links and decoded file handles, it's possible for ovl_dentry_upper()
  * to return positive, while there's no actual upper alias for the inode.
@@ -739,19 +766,6 @@ bool ovl_path_check_xwhiteout_xattr(struct ovl_fs *ofs, const struct path *path)
 	return res >= 0;
 }
 
-bool ovl_path_check_xwhiteouts_xattr(struct ovl_fs *ofs, const struct path *path)
-{
-	struct dentry *dentry = path->dentry;
-	int res;
-
-	/* xattr.whiteouts must be a directory */
-	if (!d_is_dir(dentry))
-		return false;
-
-	res = ovl_path_getxattr(ofs, path, OVL_XATTR_XWHITEOUTS, NULL, 0);
-	return res >= 0;
-}
-
 /*
  * Load persistent uuid from xattr into s_uuid if found, or store a new
  * random generated value in s_uuid and in xattr.
@@ -760,13 +774,14 @@ bool ovl_init_uuid_xattr(struct super_block *sb, struct ovl_fs *ofs,
 			 const struct path *upperpath)
 {
 	bool set = false;
+	uuid_t uuid;
 	int res;
 
 	/* Try to load existing persistent uuid */
-	res = ovl_path_getxattr(ofs, upperpath, OVL_XATTR_UUID, sb->s_uuid.b,
+	res = ovl_path_getxattr(ofs, upperpath, OVL_XATTR_UUID, uuid.b,
 				UUID_SIZE);
 	if (res == UUID_SIZE)
-		return true;
+		goto set_uuid;
 
 	if (res != -ENODATA)
 		goto fail;
@@ -794,37 +809,37 @@ bool ovl_init_uuid_xattr(struct super_block *sb, struct ovl_fs *ofs,
 	}
 
 	/* Generate overlay instance uuid */
-	uuid_gen(&sb->s_uuid);
+	uuid_gen(&uuid);
 
 	/* Try to store persistent uuid */
 	set = true;
-	res = ovl_setxattr(ofs, upperpath->dentry, OVL_XATTR_UUID, sb->s_uuid.b,
+	res = ovl_setxattr(ofs, upperpath->dentry, OVL_XATTR_UUID, uuid.b,
 			   UUID_SIZE);
-	if (res == 0)
-		return true;
+	if (res)
+		goto fail;
+
+set_uuid:
+	super_set_uuid(sb, uuid.b, sizeof(uuid));
+	return true;
 
 fail:
-	memset(sb->s_uuid.b, 0, UUID_SIZE);
 	ofs->config.uuid = OVL_UUID_NULL;
 	pr_warn("failed to %s uuid (%pd2, err=%i); falling back to uuid=null.\n",
 		set ? "set" : "get", upperpath->dentry, res);
 	return false;
 }
 
-bool ovl_path_check_dir_xattr(struct ovl_fs *ofs, const struct path *path,
-			       enum ovl_xattr ox)
+char ovl_get_dir_xattr_val(struct ovl_fs *ofs, const struct path *path,
+			   enum ovl_xattr ox)
 {
 	int res;
 	char val;
 
 	if (!d_is_dir(path->dentry))
-		return false;
+		return 0;
 
 	res = ovl_path_getxattr(ofs, path, ox, &val, 1);
-	if (res == 1 && val == 'y')
-		return true;
-
-	return false;
+	return res == 1 ? val : 0;
 }
 
 #define OVL_XATTR_OPAQUE_POSTFIX	"opaque"
@@ -837,7 +852,6 @@ bool ovl_path_check_dir_xattr(struct ovl_fs *ofs, const struct path *path,
 #define OVL_XATTR_METACOPY_POSTFIX	"metacopy"
 #define OVL_XATTR_PROTATTR_POSTFIX	"protattr"
 #define OVL_XATTR_XWHITEOUT_POSTFIX	"whiteout"
-#define OVL_XATTR_XWHITEOUTS_POSTFIX	"whiteouts"
 
 #define OVL_XATTR_TAB_ENTRY(x) \
 	[x] = { [false] = OVL_XATTR_TRUSTED_PREFIX x ## _POSTFIX, \
@@ -854,7 +868,6 @@ const char *const ovl_xattr_table[][2] = {
 	OVL_XATTR_TAB_ENTRY(OVL_XATTR_METACOPY),
 	OVL_XATTR_TAB_ENTRY(OVL_XATTR_PROTATTR),
 	OVL_XATTR_TAB_ENTRY(OVL_XATTR_XWHITEOUT),
-	OVL_XATTR_TAB_ENTRY(OVL_XATTR_XWHITEOUTS),
 };
 
 int ovl_check_setxattr(struct ovl_fs *ofs, struct dentry *upperdentry,
diff --git a/fs/pidfs.c b/fs/pidfs.c
new file mode 100644
index 000000000000..8fd71a00be9c
--- /dev/null
+++ b/fs/pidfs.c
@@ -0,0 +1,290 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/anon_inodes.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/magic.h>
+#include <linux/mount.h>
+#include <linux/pid.h>
+#include <linux/pidfs.h>
+#include <linux/pid_namespace.h>
+#include <linux/poll.h>
+#include <linux/proc_fs.h>
+#include <linux/proc_ns.h>
+#include <linux/pseudo_fs.h>
+#include <linux/seq_file.h>
+#include <uapi/linux/pidfd.h>
+
+#include "internal.h"
+
+static int pidfd_release(struct inode *inode, struct file *file)
+{
+#ifndef CONFIG_FS_PID
+	struct pid *pid = file->private_data;
+
+	file->private_data = NULL;
+	put_pid(pid);
+#endif
+	return 0;
+}
+
+#ifdef CONFIG_PROC_FS
+/**
+ * pidfd_show_fdinfo - print information about a pidfd
+ * @m: proc fdinfo file
+ * @f: file referencing a pidfd
+ *
+ * Pid:
+ * This function will print the pid that a given pidfd refers to in the
+ * pid namespace of the procfs instance.
+ * If the pid namespace of the process is not a descendant of the pid
+ * namespace of the procfs instance 0 will be shown as its pid. This is
+ * similar to calling getppid() on a process whose parent is outside of
+ * its pid namespace.
+ *
+ * NSpid:
+ * If pid namespaces are supported then this function will also print
+ * the pid of a given pidfd refers to for all descendant pid namespaces
+ * starting from the current pid namespace of the instance, i.e. the
+ * Pid field and the first entry in the NSpid field will be identical.
+ * If the pid namespace of the process is not a descendant of the pid
+ * namespace of the procfs instance 0 will be shown as its first NSpid
+ * entry and no others will be shown.
+ * Note that this differs from the Pid and NSpid fields in
+ * /proc/<pid>/status where Pid and NSpid are always shown relative to
+ * the  pid namespace of the procfs instance. The difference becomes
+ * obvious when sending around a pidfd between pid namespaces from a
+ * different branch of the tree, i.e. where no ancestral relation is
+ * present between the pid namespaces:
+ * - create two new pid namespaces ns1 and ns2 in the initial pid
+ *   namespace (also take care to create new mount namespaces in the
+ *   new pid namespace and mount procfs)
+ * - create a process with a pidfd in ns1
+ * - send pidfd from ns1 to ns2
+ * - read /proc/self/fdinfo/<pidfd> and observe that both Pid and NSpid
+ *   have exactly one entry, which is 0
+ */
+static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
+{
+	struct pid *pid = pidfd_pid(f);
+	struct pid_namespace *ns;
+	pid_t nr = -1;
+
+	if (likely(pid_has_task(pid, PIDTYPE_PID))) {
+		ns = proc_pid_ns(file_inode(m->file)->i_sb);
+		nr = pid_nr_ns(pid, ns);
+	}
+
+	seq_put_decimal_ll(m, "Pid:\t", nr);
+
+#ifdef CONFIG_PID_NS
+	seq_put_decimal_ll(m, "\nNSpid:\t", nr);
+	if (nr > 0) {
+		int i;
+
+		/* If nr is non-zero it means that 'pid' is valid and that
+		 * ns, i.e. the pid namespace associated with the procfs
+		 * instance, is in the pid namespace hierarchy of pid.
+		 * Start at one below the already printed level.
+		 */
+		for (i = ns->level + 1; i <= pid->level; i++)
+			seq_put_decimal_ll(m, "\t", pid->numbers[i].nr);
+	}
+#endif
+	seq_putc(m, '\n');
+}
+#endif
+
+/*
+ * Poll support for process exit notification.
+ */
+static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts)
+{
+	struct pid *pid = pidfd_pid(file);
+	bool thread = file->f_flags & PIDFD_THREAD;
+	struct task_struct *task;
+	__poll_t poll_flags = 0;
+
+	poll_wait(file, &pid->wait_pidfd, pts);
+	/*
+	 * Depending on PIDFD_THREAD, inform pollers when the thread
+	 * or the whole thread-group exits.
+	 */
+	guard(rcu)();
+	task = pid_task(pid, PIDTYPE_PID);
+	if (!task)
+		poll_flags = EPOLLIN | EPOLLRDNORM | EPOLLHUP;
+	else if (task->exit_state && (thread || thread_group_empty(task)))
+		poll_flags = EPOLLIN | EPOLLRDNORM;
+
+	return poll_flags;
+}
+
+static const struct file_operations pidfs_file_operations = {
+	.release	= pidfd_release,
+	.poll		= pidfd_poll,
+#ifdef CONFIG_PROC_FS
+	.show_fdinfo	= pidfd_show_fdinfo,
+#endif
+};
+
+struct pid *pidfd_pid(const struct file *file)
+{
+	if (file->f_op != &pidfs_file_operations)
+		return ERR_PTR(-EBADF);
+#ifdef CONFIG_FS_PID
+	return file_inode(file)->i_private;
+#else
+	return file->private_data;
+#endif
+}
+
+#ifdef CONFIG_FS_PID
+static struct vfsmount *pidfs_mnt __ro_after_init;
+
+/*
+ * The vfs falls back to simple_setattr() if i_op->setattr() isn't
+ * implemented. Let's reject it completely until we have a clean
+ * permission concept for pidfds.
+ */
+static int pidfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+			 struct iattr *attr)
+{
+	return -EOPNOTSUPP;
+}
+
+static int pidfs_getattr(struct mnt_idmap *idmap, const struct path *path,
+			 struct kstat *stat, u32 request_mask,
+			 unsigned int query_flags)
+{
+	struct inode *inode = d_inode(path->dentry);
+
+	generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat);
+	return 0;
+}
+
+static const struct inode_operations pidfs_inode_operations = {
+	.getattr = pidfs_getattr,
+	.setattr = pidfs_setattr,
+};
+
+static void pidfs_evict_inode(struct inode *inode)
+{
+	struct pid *pid = inode->i_private;
+
+	clear_inode(inode);
+	put_pid(pid);
+}
+
+static const struct super_operations pidfs_sops = {
+	.drop_inode	= generic_delete_inode,
+	.evict_inode	= pidfs_evict_inode,
+	.statfs		= simple_statfs,
+};
+
+static char *pidfs_dname(struct dentry *dentry, char *buffer, int buflen)
+{
+	return dynamic_dname(buffer, buflen, "pidfd:[%lu]",
+			     d_inode(dentry)->i_ino);
+}
+
+static const struct dentry_operations pidfs_dentry_operations = {
+	.d_delete	= always_delete_dentry,
+	.d_dname	= pidfs_dname,
+	.d_prune	= stashed_dentry_prune,
+};
+
+static void pidfs_init_inode(struct inode *inode, void *data)
+{
+	inode->i_private = data;
+	inode->i_flags |= S_PRIVATE;
+	inode->i_mode |= S_IRWXU;
+	inode->i_op = &pidfs_inode_operations;
+	inode->i_fop = &pidfs_file_operations;
+}
+
+static void pidfs_put_data(void *data)
+{
+	struct pid *pid = data;
+	put_pid(pid);
+}
+
+static const struct stashed_operations pidfs_stashed_ops = {
+	.init_inode = pidfs_init_inode,
+	.put_data = pidfs_put_data,
+};
+
+static int pidfs_init_fs_context(struct fs_context *fc)
+{
+	struct pseudo_fs_context *ctx;
+
+	ctx = init_pseudo(fc, PID_FS_MAGIC);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->ops = &pidfs_sops;
+	ctx->dops = &pidfs_dentry_operations;
+	fc->s_fs_info = (void *)&pidfs_stashed_ops;
+	return 0;
+}
+
+static struct file_system_type pidfs_type = {
+	.name			= "pidfs",
+	.init_fs_context	= pidfs_init_fs_context,
+	.kill_sb		= kill_anon_super,
+};
+
+struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags)
+{
+
+	struct file *pidfd_file;
+	struct path path;
+	int ret;
+
+	/*
+	* Inode numbering for pidfs start at RESERVED_PIDS + 1.
+	* This avoids collisions with the root inode which is 1
+	* for pseudo filesystems.
+	 */
+	ret = path_from_stashed(&pid->stashed, pid->ino, pidfs_mnt,
+				get_pid(pid), &path);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	pidfd_file = dentry_open(&path, flags, current_cred());
+	path_put(&path);
+	return pidfd_file;
+}
+
+void __init pidfs_init(void)
+{
+	pidfs_mnt = kern_mount(&pidfs_type);
+	if (IS_ERR(pidfs_mnt))
+		panic("Failed to mount pidfs pseudo filesystem");
+}
+
+bool is_pidfs_sb(const struct super_block *sb)
+{
+	return sb == pidfs_mnt->mnt_sb;
+}
+
+#else /* !CONFIG_FS_PID */
+
+struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags)
+{
+	struct file *pidfd_file;
+
+	pidfd_file = anon_inode_getfile("[pidfd]", &pidfs_file_operations, pid,
+					flags | O_RDWR);
+	if (IS_ERR(pidfd_file))
+		return pidfd_file;
+
+	get_pid(pid);
+	return pidfd_file;
+}
+
+void __init pidfs_init(void) { }
+bool is_pidfs_sb(const struct super_block *sb)
+{
+	return false;
+}
+#endif
diff --git a/fs/pipe.c b/fs/pipe.c
index f1adbfe743d4..50c8a8596b52 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -76,18 +76,20 @@ static unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR;
  * -- Manfred Spraul <manfred@colorfullife.com> 2002-05-09
  */
 
-static void pipe_lock_nested(struct pipe_inode_info *pipe, int subclass)
+#define cmp_int(l, r)		((l > r) - (l < r))
+
+#ifdef CONFIG_PROVE_LOCKING
+static int pipe_lock_cmp_fn(const struct lockdep_map *a,
+			    const struct lockdep_map *b)
 {
-	if (pipe->files)
-		mutex_lock_nested(&pipe->mutex, subclass);
+	return cmp_int((unsigned long) a, (unsigned long) b);
 }
+#endif
 
 void pipe_lock(struct pipe_inode_info *pipe)
 {
-	/*
-	 * pipe_lock() nests non-pipe inode locks (for writing to a file)
-	 */
-	pipe_lock_nested(pipe, I_MUTEX_PARENT);
+	if (pipe->files)
+		mutex_lock(&pipe->mutex);
 }
 EXPORT_SYMBOL(pipe_lock);
 
@@ -98,28 +100,16 @@ void pipe_unlock(struct pipe_inode_info *pipe)
 }
 EXPORT_SYMBOL(pipe_unlock);
 
-static inline void __pipe_lock(struct pipe_inode_info *pipe)
-{
-	mutex_lock_nested(&pipe->mutex, I_MUTEX_PARENT);
-}
-
-static inline void __pipe_unlock(struct pipe_inode_info *pipe)
-{
-	mutex_unlock(&pipe->mutex);
-}
-
 void pipe_double_lock(struct pipe_inode_info *pipe1,
 		      struct pipe_inode_info *pipe2)
 {
 	BUG_ON(pipe1 == pipe2);
 
-	if (pipe1 < pipe2) {
-		pipe_lock_nested(pipe1, I_MUTEX_PARENT);
-		pipe_lock_nested(pipe2, I_MUTEX_CHILD);
-	} else {
-		pipe_lock_nested(pipe2, I_MUTEX_PARENT);
-		pipe_lock_nested(pipe1, I_MUTEX_CHILD);
-	}
+	if (pipe1 > pipe2)
+		swap(pipe1, pipe2);
+
+	pipe_lock(pipe1);
+	pipe_lock(pipe2);
 }
 
 static void anon_pipe_buf_release(struct pipe_inode_info *pipe,
@@ -271,7 +261,7 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to)
 		return 0;
 
 	ret = 0;
-	__pipe_lock(pipe);
+	mutex_lock(&pipe->mutex);
 
 	/*
 	 * We only wake up writers if the pipe was full when we started
@@ -368,7 +358,7 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to)
 			ret = -EAGAIN;
 			break;
 		}
-		__pipe_unlock(pipe);
+		mutex_unlock(&pipe->mutex);
 
 		/*
 		 * We only get here if we didn't actually read anything.
@@ -400,13 +390,13 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to)
 		if (wait_event_interruptible_exclusive(pipe->rd_wait, pipe_readable(pipe)) < 0)
 			return -ERESTARTSYS;
 
-		__pipe_lock(pipe);
+		mutex_lock(&pipe->mutex);
 		was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage);
 		wake_next_reader = true;
 	}
 	if (pipe_empty(pipe->head, pipe->tail))
 		wake_next_reader = false;
-	__pipe_unlock(pipe);
+	mutex_unlock(&pipe->mutex);
 
 	if (was_full)
 		wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM);
@@ -462,7 +452,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
 	if (unlikely(total_len == 0))
 		return 0;
 
-	__pipe_lock(pipe);
+	mutex_lock(&pipe->mutex);
 
 	if (!pipe->readers) {
 		send_sig(SIGPIPE, current, 0);
@@ -582,19 +572,19 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
 		 * after waiting we need to re-check whether the pipe
 		 * become empty while we dropped the lock.
 		 */
-		__pipe_unlock(pipe);
+		mutex_unlock(&pipe->mutex);
 		if (was_empty)
 			wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM);
 		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
 		wait_event_interruptible_exclusive(pipe->wr_wait, pipe_writable(pipe));
-		__pipe_lock(pipe);
+		mutex_lock(&pipe->mutex);
 		was_empty = pipe_empty(pipe->head, pipe->tail);
 		wake_next_writer = true;
 	}
 out:
 	if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
 		wake_next_writer = false;
-	__pipe_unlock(pipe);
+	mutex_unlock(&pipe->mutex);
 
 	/*
 	 * If we do do a wakeup event, we do a 'sync' wakeup, because we
@@ -629,7 +619,7 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 
 	switch (cmd) {
 	case FIONREAD:
-		__pipe_lock(pipe);
+		mutex_lock(&pipe->mutex);
 		count = 0;
 		head = pipe->head;
 		tail = pipe->tail;
@@ -639,16 +629,16 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 			count += pipe->bufs[tail & mask].len;
 			tail++;
 		}
-		__pipe_unlock(pipe);
+		mutex_unlock(&pipe->mutex);
 
 		return put_user(count, (int __user *)arg);
 
 #ifdef CONFIG_WATCH_QUEUE
 	case IOC_WATCH_QUEUE_SET_SIZE: {
 		int ret;
-		__pipe_lock(pipe);
+		mutex_lock(&pipe->mutex);
 		ret = watch_queue_set_size(pipe, arg);
-		__pipe_unlock(pipe);
+		mutex_unlock(&pipe->mutex);
 		return ret;
 	}
 
@@ -734,7 +724,7 @@ pipe_release(struct inode *inode, struct file *file)
 {
 	struct pipe_inode_info *pipe = file->private_data;
 
-	__pipe_lock(pipe);
+	mutex_lock(&pipe->mutex);
 	if (file->f_mode & FMODE_READ)
 		pipe->readers--;
 	if (file->f_mode & FMODE_WRITE)
@@ -747,7 +737,7 @@ pipe_release(struct inode *inode, struct file *file)
 		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
 		kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
 	}
-	__pipe_unlock(pipe);
+	mutex_unlock(&pipe->mutex);
 
 	put_pipe_info(inode, pipe);
 	return 0;
@@ -759,7 +749,7 @@ pipe_fasync(int fd, struct file *filp, int on)
 	struct pipe_inode_info *pipe = filp->private_data;
 	int retval = 0;
 
-	__pipe_lock(pipe);
+	mutex_lock(&pipe->mutex);
 	if (filp->f_mode & FMODE_READ)
 		retval = fasync_helper(fd, filp, on, &pipe->fasync_readers);
 	if ((filp->f_mode & FMODE_WRITE) && retval >= 0) {
@@ -768,7 +758,7 @@ pipe_fasync(int fd, struct file *filp, int on)
 			/* this can happen only if on == T */
 			fasync_helper(-1, filp, 0, &pipe->fasync_readers);
 	}
-	__pipe_unlock(pipe);
+	mutex_unlock(&pipe->mutex);
 	return retval;
 }
 
@@ -834,6 +824,7 @@ struct pipe_inode_info *alloc_pipe_info(void)
 		pipe->nr_accounted = pipe_bufs;
 		pipe->user = user;
 		mutex_init(&pipe->mutex);
+		lock_set_cmp_fn(&pipe->mutex, pipe_lock_cmp_fn, NULL);
 		return pipe;
 	}
 
@@ -1144,7 +1135,7 @@ static int fifo_open(struct inode *inode, struct file *filp)
 	filp->private_data = pipe;
 	/* OK, we have a pipe and it's pinned down */
 
-	__pipe_lock(pipe);
+	mutex_lock(&pipe->mutex);
 
 	/* We can only do regular read/write on fifos */
 	stream_open(inode, filp);
@@ -1214,7 +1205,7 @@ static int fifo_open(struct inode *inode, struct file *filp)
 	}
 
 	/* Ok! */
-	__pipe_unlock(pipe);
+	mutex_unlock(&pipe->mutex);
 	return 0;
 
 err_rd:
@@ -1230,7 +1221,7 @@ err_wr:
 	goto err;
 
 err:
-	__pipe_unlock(pipe);
+	mutex_unlock(&pipe->mutex);
 
 	put_pipe_info(inode, pipe);
 	return ret;
@@ -1411,7 +1402,7 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned int arg)
 	if (!pipe)
 		return -EBADF;
 
-	__pipe_lock(pipe);
+	mutex_lock(&pipe->mutex);
 
 	switch (cmd) {
 	case F_SETPIPE_SZ:
@@ -1425,7 +1416,7 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned int arg)
 		break;
 	}
 
-	__pipe_unlock(pipe);
+	mutex_unlock(&pipe->mutex);
 	return ret;
 }
 
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index e1af20893ebe..6bf587d1a9b8 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -786,12 +786,12 @@ struct posix_acl *posix_acl_from_xattr(struct user_namespace *userns,
 		return ERR_PTR(count);
 	if (count == 0)
 		return NULL;
-	
+
 	acl = posix_acl_alloc(count, GFP_NOFS);
 	if (!acl)
 		return ERR_PTR(-ENOMEM);
 	acl_e = acl->a_entries;
-	
+
 	for (end = entry + count; entry != end; acl_e++, entry++) {
 		acl_e->e_tag  = le16_to_cpu(entry->e_tag);
 		acl_e->e_perm = le16_to_cpu(entry->e_perm);
diff --git a/fs/proc/array.c b/fs/proc/array.c
index ff08a8957552..34a47fb0c57f 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -477,13 +477,13 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	int permitted;
 	struct mm_struct *mm;
 	unsigned long long start_time;
-	unsigned long cmin_flt = 0, cmaj_flt = 0;
-	unsigned long  min_flt = 0,  maj_flt = 0;
-	u64 cutime, cstime, utime, stime;
-	u64 cgtime, gtime;
+	unsigned long cmin_flt, cmaj_flt, min_flt, maj_flt;
+	u64 cutime, cstime, cgtime, utime, stime, gtime;
 	unsigned long rsslim = 0;
 	unsigned long flags;
 	int exit_code = task->exit_code;
+	struct signal_struct *sig = task->signal;
+	unsigned int seq = 1;
 
 	state = *get_task_state(task);
 	vsize = eip = esp = 0;
@@ -511,12 +511,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
 	sigemptyset(&sigign);
 	sigemptyset(&sigcatch);
-	cutime = cstime = utime = stime = 0;
-	cgtime = gtime = 0;
 
 	if (lock_task_sighand(task, &flags)) {
-		struct signal_struct *sig = task->signal;
-
 		if (sig->tty) {
 			struct pid *pgrp = tty_get_pgrp(sig->tty);
 			tty_pgrp = pid_nr_ns(pgrp, ns);
@@ -527,28 +523,9 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 		num_threads = get_nr_threads(task);
 		collect_sigign_sigcatch(task, &sigign, &sigcatch);
 
-		cmin_flt = sig->cmin_flt;
-		cmaj_flt = sig->cmaj_flt;
-		cutime = sig->cutime;
-		cstime = sig->cstime;
-		cgtime = sig->cgtime;
 		rsslim = READ_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur);
 
-		/* add up live thread stats at the group level */
 		if (whole) {
-			struct task_struct *t;
-
-			__for_each_thread(sig, t) {
-				min_flt += t->min_flt;
-				maj_flt += t->maj_flt;
-				gtime += task_gtime(t);
-			}
-
-			min_flt += sig->min_flt;
-			maj_flt += sig->maj_flt;
-			thread_group_cputime_adjusted(task, &utime, &stime);
-			gtime += sig->gtime;
-
 			if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED))
 				exit_code = sig->group_exit_code;
 		}
@@ -562,10 +539,41 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
 	if (permitted && (!whole || num_threads < 2))
 		wchan = !task_is_running(task);
-	if (!whole) {
+
+	do {
+		seq++; /* 2 on the 1st/lockless path, otherwise odd */
+		flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
+
+		cmin_flt = sig->cmin_flt;
+		cmaj_flt = sig->cmaj_flt;
+		cutime = sig->cutime;
+		cstime = sig->cstime;
+		cgtime = sig->cgtime;
+
+		if (whole) {
+			struct task_struct *t;
+
+			min_flt = sig->min_flt;
+			maj_flt = sig->maj_flt;
+			gtime = sig->gtime;
+
+			rcu_read_lock();
+			__for_each_thread(sig, t) {
+				min_flt += t->min_flt;
+				maj_flt += t->maj_flt;
+				gtime += task_gtime(t);
+			}
+			rcu_read_unlock();
+		}
+	} while (need_seqretry(&sig->stats_lock, seq));
+	done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
+
+	if (whole) {
+		thread_group_cputime_adjusted(task, &utime, &stime);
+	} else {
+		task_cputime_adjusted(task, &utime, &stime);
 		min_flt = task->min_flt;
 		maj_flt = task->maj_flt;
-		task_cputime_adjusted(task, &utime, &stime);
 		gtime = task_gtime(task);
 	}
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 98a031ac2648..18550c071d71 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1878,8 +1878,6 @@ void proc_pid_evict_inode(struct proc_inode *ei)
 		hlist_del_init_rcu(&ei->sibling_inodes);
 		spin_unlock(&pid->lock);
 	}
-
-	put_pid(pid);
 }
 
 struct inode *proc_pid_make_inode(struct super_block *sb,
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index b33e490e3fd9..dcd513dccf55 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -30,7 +30,6 @@
 
 static void proc_evict_inode(struct inode *inode)
 {
-	struct proc_dir_entry *de;
 	struct ctl_table_header *head;
 	struct proc_inode *ei = PROC_I(inode);
 
@@ -38,17 +37,8 @@ static void proc_evict_inode(struct inode *inode)
 	clear_inode(inode);
 
 	/* Stop tracking associated processes */
-	if (ei->pid) {
+	if (ei->pid)
 		proc_pid_evict_inode(ei);
-		ei->pid = NULL;
-	}
-
-	/* Let go of any associated proc directory entry */
-	de = ei->pde;
-	if (de) {
-		pde_put(de);
-		ei->pde = NULL;
-	}
 
 	head = ei->sysctl;
 	if (head) {
@@ -80,6 +70,13 @@ static struct inode *proc_alloc_inode(struct super_block *sb)
 
 static void proc_free_inode(struct inode *inode)
 {
+	struct proc_inode *ei = PROC_I(inode);
+
+	if (ei->pid)
+		put_pid(ei->pid);
+	/* Let go of any associated proc directory entry */
+	if (ei->pde)
+		pde_put(ei->pde);
 	kmem_cache_free(proc_inode_cachep, PROC_I(inode));
 }
 
@@ -95,7 +92,7 @@ void __init proc_init_kmemcache(void)
 	proc_inode_cachep = kmem_cache_create("proc_inode_cache",
 					     sizeof(struct proc_inode),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD|SLAB_ACCOUNT|
+						SLAB_ACCOUNT|
 						SLAB_PANIC),
 					     init_once);
 	pde_opener_cache =
diff --git a/fs/proc/root.c b/fs/proc/root.c
index b55dbc70287b..06a297a27ba3 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -271,7 +271,7 @@ static void proc_kill_sb(struct super_block *sb)
 
 	kill_anon_super(sb);
 	put_pid_ns(fs_info->pid_ns);
-	kfree(fs_info);
+	kfree_rcu(fs_info, rcu);
 }
 
 static struct file_system_type proc_fs_type = {
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 62b16f42d5d2..3f78ebbb795f 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -2432,7 +2432,6 @@ static long pagemap_scan_flush_buffer(struct pagemap_scan_private *p)
 
 static long do_pagemap_scan(struct mm_struct *mm, unsigned long uarg)
 {
-	struct mmu_notifier_range range;
 	struct pagemap_scan_private p = {0};
 	unsigned long walk_start;
 	size_t n_ranges_out = 0;
@@ -2448,15 +2447,9 @@ static long do_pagemap_scan(struct mm_struct *mm, unsigned long uarg)
 	if (ret)
 		return ret;
 
-	/* Protection change for the range is going to happen. */
-	if (p.arg.flags & PM_SCAN_WP_MATCHING) {
-		mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, 0,
-					mm, p.arg.start, p.arg.end);
-		mmu_notifier_invalidate_range_start(&range);
-	}
-
 	for (walk_start = p.arg.start; walk_start < p.arg.end;
 			walk_start = p.arg.walk_end) {
+		struct mmu_notifier_range range;
 		long n_out;
 
 		if (fatal_signal_pending(current)) {
@@ -2467,8 +2460,20 @@ static long do_pagemap_scan(struct mm_struct *mm, unsigned long uarg)
 		ret = mmap_read_lock_killable(mm);
 		if (ret)
 			break;
+
+		/* Protection change for the range is going to happen. */
+		if (p.arg.flags & PM_SCAN_WP_MATCHING) {
+			mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, 0,
+						mm, walk_start, p.arg.end);
+			mmu_notifier_invalidate_range_start(&range);
+		}
+
 		ret = walk_page_range(mm, walk_start, p.arg.end,
 				      &pagemap_scan_ops, &p);
+
+		if (p.arg.flags & PM_SCAN_WP_MATCHING)
+			mmu_notifier_invalidate_range_end(&range);
+
 		mmap_read_unlock(mm);
 
 		n_out = pagemap_scan_flush_buffer(&p);
@@ -2494,9 +2499,6 @@ static long do_pagemap_scan(struct mm_struct *mm, unsigned long uarg)
 	if (pagemap_scan_writeback_args(&p.arg, uarg))
 		ret = -EFAULT;
 
-	if (p.arg.flags & PM_SCAN_WP_MATCHING)
-		mmu_notifier_invalidate_range_end(&range);
-
 	kfree(p.vec_buf);
 	return ret;
 }
diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c
index 6eb9bb369b57..7b5711f76709 100644
--- a/fs/qnx4/inode.c
+++ b/fs/qnx4/inode.c
@@ -21,6 +21,7 @@
 #include <linux/buffer_head.h>
 #include <linux/writeback.h>
 #include <linux/statfs.h>
+#include <linux/fs_context.h>
 #include "qnx4.h"
 
 #define QNX4_VERSION  4
@@ -30,28 +31,33 @@ static const struct super_operations qnx4_sops;
 
 static struct inode *qnx4_alloc_inode(struct super_block *sb);
 static void qnx4_free_inode(struct inode *inode);
-static int qnx4_remount(struct super_block *sb, int *flags, char *data);
 static int qnx4_statfs(struct dentry *, struct kstatfs *);
+static int qnx4_get_tree(struct fs_context *fc);
 
 static const struct super_operations qnx4_sops =
 {
 	.alloc_inode	= qnx4_alloc_inode,
 	.free_inode	= qnx4_free_inode,
 	.statfs		= qnx4_statfs,
-	.remount_fs	= qnx4_remount,
 };
 
-static int qnx4_remount(struct super_block *sb, int *flags, char *data)
+static int qnx4_reconfigure(struct fs_context *fc)
 {
+	struct super_block *sb = fc->root->d_sb;
 	struct qnx4_sb_info *qs;
 
 	sync_filesystem(sb);
 	qs = qnx4_sb(sb);
 	qs->Version = QNX4_VERSION;
-	*flags |= SB_RDONLY;
+	fc->sb_flags |= SB_RDONLY;
 	return 0;
 }
 
+static const struct fs_context_operations qnx4_context_opts = {
+	.get_tree	= qnx4_get_tree,
+	.reconfigure	= qnx4_reconfigure,
+};
+
 static int qnx4_get_block( struct inode *inode, sector_t iblock, struct buffer_head *bh, int create )
 {
 	unsigned long phys;
@@ -183,12 +189,13 @@ static const char *qnx4_checkroot(struct super_block *sb,
 	return "bitmap file not found.";
 }
 
-static int qnx4_fill_super(struct super_block *s, void *data, int silent)
+static int qnx4_fill_super(struct super_block *s, struct fs_context *fc)
 {
 	struct buffer_head *bh;
 	struct inode *root;
 	const char *errmsg;
 	struct qnx4_sb_info *qs;
+	int silent = fc->sb_flags & SB_SILENT;
 
 	qs = kzalloc(sizeof(struct qnx4_sb_info), GFP_KERNEL);
 	if (!qs)
@@ -216,7 +223,7 @@ static int qnx4_fill_super(struct super_block *s, void *data, int silent)
 	errmsg = qnx4_checkroot(s, (struct qnx4_super_block *) bh->b_data);
 	brelse(bh);
 	if (errmsg != NULL) {
- 		if (!silent)
+		if (!silent)
 			printk(KERN_ERR "qnx4: %s\n", errmsg);
 		return -EINVAL;
 	}
@@ -235,6 +242,18 @@ static int qnx4_fill_super(struct super_block *s, void *data, int silent)
 	return 0;
 }
 
+static int qnx4_get_tree(struct fs_context *fc)
+{
+	return get_tree_bdev(fc, qnx4_fill_super);
+}
+
+static int qnx4_init_fs_context(struct fs_context *fc)
+{
+	fc->ops = &qnx4_context_opts;
+
+	return 0;
+}
+
 static void qnx4_kill_sb(struct super_block *sb)
 {
 	struct qnx4_sb_info *qs = qnx4_sb(sb);
@@ -376,18 +395,12 @@ static void destroy_inodecache(void)
 	kmem_cache_destroy(qnx4_inode_cachep);
 }
 
-static struct dentry *qnx4_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
-{
-	return mount_bdev(fs_type, flags, dev_name, data, qnx4_fill_super);
-}
-
 static struct file_system_type qnx4_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "qnx4",
-	.mount		= qnx4_mount,
-	.kill_sb	= qnx4_kill_sb,
-	.fs_flags	= FS_REQUIRES_DEV,
+	.owner			= THIS_MODULE,
+	.name			= "qnx4",
+	.kill_sb		= qnx4_kill_sb,
+	.fs_flags		= FS_REQUIRES_DEV,
+	.init_fs_context	= qnx4_init_fs_context,
 };
 MODULE_ALIAS_FS("qnx4");
 
diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c
index a286c545717f..405913f4faff 100644
--- a/fs/qnx6/inode.c
+++ b/fs/qnx6/inode.c
@@ -615,7 +615,7 @@ static int init_inodecache(void)
 	qnx6_inode_cachep = kmem_cache_create("qnx6_inode_cache",
 					     sizeof(struct qnx6_inode_info),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
+						SLAB_ACCOUNT),
 					     init_once);
 	if (!qnx6_inode_cachep)
 		return -ENOMEM;
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 171c912af50f..6474529c4253 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -2386,7 +2386,7 @@ static int journal_read(struct super_block *sb)
 
 	cur_dblock = SB_ONDISK_JOURNAL_1st_BLOCK(sb);
 	reiserfs_info(sb, "checking transaction log (%pg)\n",
-		      journal->j_bdev_handle->bdev);
+		      file_bdev(journal->j_bdev_file));
 	start = ktime_get_seconds();
 
 	/*
@@ -2447,7 +2447,7 @@ static int journal_read(struct super_block *sb)
 		 * device and journal device to be the same
 		 */
 		d_bh =
-		    reiserfs_breada(journal->j_bdev_handle->bdev, cur_dblock,
+		    reiserfs_breada(file_bdev(journal->j_bdev_file), cur_dblock,
 				    sb->s_blocksize,
 				    SB_ONDISK_JOURNAL_1st_BLOCK(sb) +
 				    SB_ONDISK_JOURNAL_SIZE(sb));
@@ -2588,9 +2588,9 @@ static void journal_list_init(struct super_block *sb)
 
 static void release_journal_dev(struct reiserfs_journal *journal)
 {
-	if (journal->j_bdev_handle) {
-		bdev_release(journal->j_bdev_handle);
-		journal->j_bdev_handle = NULL;
+	if (journal->j_bdev_file) {
+		fput(journal->j_bdev_file);
+		journal->j_bdev_file = NULL;
 	}
 }
 
@@ -2605,7 +2605,7 @@ static int journal_init_dev(struct super_block *super,
 
 	result = 0;
 
-	journal->j_bdev_handle = NULL;
+	journal->j_bdev_file = NULL;
 	jdev = SB_ONDISK_JOURNAL_DEVICE(super) ?
 	    new_decode_dev(SB_ONDISK_JOURNAL_DEVICE(super)) : super->s_dev;
 
@@ -2616,37 +2616,37 @@ static int journal_init_dev(struct super_block *super,
 	if ((!jdev_name || !jdev_name[0])) {
 		if (jdev == super->s_dev)
 			holder = NULL;
-		journal->j_bdev_handle = bdev_open_by_dev(jdev, blkdev_mode,
+		journal->j_bdev_file = bdev_file_open_by_dev(jdev, blkdev_mode,
 							  holder, NULL);
-		if (IS_ERR(journal->j_bdev_handle)) {
-			result = PTR_ERR(journal->j_bdev_handle);
-			journal->j_bdev_handle = NULL;
+		if (IS_ERR(journal->j_bdev_file)) {
+			result = PTR_ERR(journal->j_bdev_file);
+			journal->j_bdev_file = NULL;
 			reiserfs_warning(super, "sh-458",
 					 "cannot init journal device unknown-block(%u,%u): %i",
 					 MAJOR(jdev), MINOR(jdev), result);
 			return result;
 		} else if (jdev != super->s_dev)
-			set_blocksize(journal->j_bdev_handle->bdev,
+			set_blocksize(file_bdev(journal->j_bdev_file),
 				      super->s_blocksize);
 
 		return 0;
 	}
 
-	journal->j_bdev_handle = bdev_open_by_path(jdev_name, blkdev_mode,
+	journal->j_bdev_file = bdev_file_open_by_path(jdev_name, blkdev_mode,
 						   holder, NULL);
-	if (IS_ERR(journal->j_bdev_handle)) {
-		result = PTR_ERR(journal->j_bdev_handle);
-		journal->j_bdev_handle = NULL;
+	if (IS_ERR(journal->j_bdev_file)) {
+		result = PTR_ERR(journal->j_bdev_file);
+		journal->j_bdev_file = NULL;
 		reiserfs_warning(super, "sh-457",
 				 "journal_init_dev: Cannot open '%s': %i",
 				 jdev_name, result);
 		return result;
 	}
 
-	set_blocksize(journal->j_bdev_handle->bdev, super->s_blocksize);
+	set_blocksize(file_bdev(journal->j_bdev_file), super->s_blocksize);
 	reiserfs_info(super,
 		      "journal_init_dev: journal device: %pg\n",
-		      journal->j_bdev_handle->bdev);
+		      file_bdev(journal->j_bdev_file));
 	return 0;
 }
 
@@ -2804,7 +2804,7 @@ int journal_init(struct super_block *sb, const char *j_dev_name,
 				 "journal header magic %x (device %pg) does "
 				 "not match to magic found in super block %x",
 				 jh->jh_journal.jp_journal_magic,
-				 journal->j_bdev_handle->bdev,
+				 file_bdev(journal->j_bdev_file),
 				 sb_jp_journal_magic(rs));
 		brelse(bhjh);
 		goto free_and_return;
@@ -2828,7 +2828,7 @@ int journal_init(struct super_block *sb, const char *j_dev_name,
 	reiserfs_info(sb, "journal params: device %pg, size %u, "
 		      "journal first block %u, max trans len %u, max batch %u, "
 		      "max commit age %u, max trans age %u\n",
-		      journal->j_bdev_handle->bdev,
+		      file_bdev(journal->j_bdev_file),
 		      SB_ONDISK_JOURNAL_SIZE(sb),
 		      SB_ONDISK_JOURNAL_1st_BLOCK(sb),
 		      journal->j_trans_max,
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index 83cb9402e0f9..5c68a4a52d78 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -354,7 +354,7 @@ static int show_journal(struct seq_file *m, void *unused)
 		   "prepare: \t%12lu\n"
 		   "prepare_retry: \t%12lu\n",
 		   DJP(jp_journal_1st_block),
-		   SB_JOURNAL(sb)->j_bdev_handle->bdev,
+		   file_bdev(SB_JOURNAL(sb)->j_bdev_file),
 		   DJP(jp_journal_dev),
 		   DJP(jp_journal_size),
 		   DJP(jp_journal_trans_max),
diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h
index 725667880e62..0554903f42a9 100644
--- a/fs/reiserfs/reiserfs.h
+++ b/fs/reiserfs/reiserfs.h
@@ -299,7 +299,7 @@ struct reiserfs_journal {
 	/* oldest journal block.  start here for traverse */
 	struct reiserfs_journal_cnode *j_first;
 
-	struct bdev_handle *j_bdev_handle;
+	struct file *j_bdev_file;
 
 	/* first block on s_dev of reserved area journal */
 	int j_1st_reserved_block;
@@ -2810,10 +2810,10 @@ struct reiserfs_journal_header {
 
 /* We need these to make journal.c code more readable */
 #define journal_find_get_block(s, block) __find_get_block(\
-		SB_JOURNAL(s)->j_bdev_handle->bdev, block, s->s_blocksize)
-#define journal_getblk(s, block) __getblk(SB_JOURNAL(s)->j_bdev_handle->bdev,\
+		file_bdev(SB_JOURNAL(s)->j_bdev_file), block, s->s_blocksize)
+#define journal_getblk(s, block) __getblk(file_bdev(SB_JOURNAL(s)->j_bdev_file),\
 		block, s->s_blocksize)
-#define journal_bread(s, block) __bread(SB_JOURNAL(s)->j_bdev_handle->bdev,\
+#define journal_bread(s, block) __bread(file_bdev(SB_JOURNAL(s)->j_bdev_file),\
 		block, s->s_blocksize)
 
 enum reiserfs_bh_state_bits {
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 67b5510beded..2cc469d481a2 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -670,7 +670,6 @@ static int __init init_inodecache(void)
 						  sizeof(struct
 							 reiserfs_inode_info),
 						  0, (SLAB_RECLAIM_ACCOUNT|
-						      SLAB_MEM_SPREAD|
 						      SLAB_ACCOUNT),
 						  init_once);
 	if (reiserfs_inode_cachep == NULL)
diff --git a/fs/remap_range.c b/fs/remap_range.c
index f8c1120b8311..de07f978ce3e 100644
--- a/fs/remap_range.c
+++ b/fs/remap_range.c
@@ -373,9 +373,9 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 }
 EXPORT_SYMBOL(generic_remap_file_range_prep);
 
-loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
-			   struct file *file_out, loff_t pos_out,
-			   loff_t len, unsigned int remap_flags)
+loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
+			    struct file *file_out, loff_t pos_out,
+			    loff_t len, unsigned int remap_flags)
 {
 	loff_t ret;
 
@@ -391,23 +391,6 @@ loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
 	if (!file_in->f_op->remap_file_range)
 		return -EOPNOTSUPP;
 
-	ret = file_in->f_op->remap_file_range(file_in, pos_in,
-			file_out, pos_out, len, remap_flags);
-	if (ret < 0)
-		return ret;
-
-	fsnotify_access(file_in);
-	fsnotify_modify(file_out);
-	return ret;
-}
-EXPORT_SYMBOL(do_clone_file_range);
-
-loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
-			    struct file *file_out, loff_t pos_out,
-			    loff_t len, unsigned int remap_flags)
-{
-	loff_t ret;
-
 	ret = remap_verify_area(file_in, pos_in, len, false);
 	if (ret)
 		return ret;
@@ -417,10 +400,14 @@ loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 		return ret;
 
 	file_start_write(file_out);
-	ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len,
-				  remap_flags);
+	ret = file_in->f_op->remap_file_range(file_in, pos_in,
+			file_out, pos_out, len, remap_flags);
 	file_end_write(file_out);
+	if (ret < 0)
+		return ret;
 
+	fsnotify_access(file_in);
+	fsnotify_modify(file_out);
 	return ret;
 }
 EXPORT_SYMBOL(vfs_clone_file_range);
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index 545ad44f96b8..2be227532f39 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -594,7 +594,7 @@ static void romfs_kill_sb(struct super_block *sb)
 #ifdef CONFIG_ROMFS_ON_BLOCK
 	if (sb->s_bdev) {
 		sync_blockdev(sb->s_bdev);
-		bdev_release(sb->s_bdev_handle);
+		fput(sb->s_bdev_file);
 	}
 #endif
 }
@@ -630,8 +630,8 @@ static int __init init_romfs_fs(void)
 	romfs_inode_cachep =
 		kmem_cache_create("romfs_i",
 				  sizeof(struct romfs_inode_info), 0,
-				  SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD |
-				  SLAB_ACCOUNT, romfs_i_init_once);
+				  SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT,
+				  romfs_i_init_once);
 
 	if (!romfs_inode_cachep) {
 		pr_err("Failed to initialise inode cache\n");
diff --git a/fs/select.c b/fs/select.c
index 0ee55af1a55c..9515c3fa1a03 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -476,7 +476,7 @@ static inline void wait_key_set(poll_table *wait, unsigned long in,
 		wait->_key |= POLLOUT_SET;
 }
 
-static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
+static noinline_for_stack int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
 {
 	ktime_t expire, *to = NULL;
 	struct poll_wqueues table;
@@ -839,7 +839,7 @@ SYSCALL_DEFINE1(old_select, struct sel_arg_struct __user *, arg)
 
 struct poll_list {
 	struct poll_list *next;
-	int len;
+	unsigned int len;
 	struct pollfd entries[];
 };
 
@@ -975,14 +975,15 @@ static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
 		struct timespec64 *end_time)
 {
 	struct poll_wqueues table;
-	int err = -EFAULT, fdcount, len;
+	int err = -EFAULT, fdcount;
 	/* Allocate small arguments on the stack to save memory and be
 	   faster - use long to make sure the buffer is aligned properly
 	   on 64 bit archs to avoid unaligned access */
 	long stack_pps[POLL_STACK_ALLOC/sizeof(long)];
 	struct poll_list *const head = (struct poll_list *)stack_pps;
  	struct poll_list *walk = head;
- 	unsigned long todo = nfds;
+	unsigned int todo = nfds;
+	unsigned int len;
 
 	if (nfds > rlimit(RLIMIT_NOFILE))
 		return -EINVAL;
@@ -998,9 +999,9 @@ static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
 					sizeof(struct pollfd) * walk->len))
 			goto out_fds;
 
-		todo -= walk->len;
-		if (!todo)
+		if (walk->len >= todo)
 			break;
+		todo -= walk->len;
 
 		len = min(todo, POLLFD_PER_PAGE);
 		walk = walk->next = kmalloc(struct_size(walk, entries, len),
@@ -1020,7 +1021,7 @@ static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
 
 	for (walk = head; walk; walk = walk->next) {
 		struct pollfd *fds = walk->entries;
-		int j;
+		unsigned int j;
 
 		for (j = walk->len; j; fds++, ufds++, j--)
 			unsafe_put_user(fds->revents, &ufds->revents, Efault);
diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index d64a306a414b..3de5047a7ff9 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -145,21 +145,27 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
 	struct cached_fid *cfid;
 	struct cached_fids *cfids;
 	const char *npath;
+	int retries = 0, cur_sleep = 1;
 
 	if (tcon == NULL || tcon->cfids == NULL || tcon->nohandlecache ||
 	    is_smb1_server(tcon->ses->server) || (dir_cache_timeout == 0))
 		return -EOPNOTSUPP;
 
 	ses = tcon->ses;
-	server = ses->server;
 	cfids = tcon->cfids;
 
-	if (!server->ops->new_lease_key)
-		return -EIO;
-
 	if (cifs_sb->root == NULL)
 		return -ENOENT;
 
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	oplock = SMB2_OPLOCK_LEVEL_II;
+	server = cifs_pick_channel(ses);
+
+	if (!server->ops->new_lease_key)
+		return -EIO;
+
 	utf16_path = cifs_convert_path_to_utf16(path, cifs_sb);
 	if (!utf16_path)
 		return -ENOMEM;
@@ -236,6 +242,7 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
 		.desired_access =  FILE_READ_DATA | FILE_READ_ATTRIBUTES,
 		.disposition = FILE_OPEN,
 		.fid = pfid,
+		.replay = !!(retries),
 	};
 
 	rc = SMB2_open_init(tcon, server,
@@ -268,6 +275,11 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
 	 */
 	cfid->has_lease = true;
 
+	if (retries) {
+		smb2_set_replay(server, &rqst[0]);
+		smb2_set_replay(server, &rqst[1]);
+	}
+
 	rc = compound_send_recv(xid, ses, server,
 				flags, 2, rqst,
 				resp_buftype, rsp_iov);
@@ -367,6 +379,11 @@ out:
 		atomic_inc(&tcon->num_remote_opens);
 	}
 	kfree(utf16_path);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c
index 60027f5aebe8..3e4209f41c18 100644
--- a/fs/smb/client/cifs_debug.c
+++ b/fs/smb/client/cifs_debug.c
@@ -659,6 +659,7 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 					spin_lock(&tcon->stat_lock);
 					tcon->bytes_read = 0;
 					tcon->bytes_written = 0;
+					tcon->stats_from_time = ktime_get_real_seconds();
 					spin_unlock(&tcon->stat_lock);
 					if (server->ops->clear_stats)
 						server->ops->clear_stats(tcon);
@@ -737,8 +738,9 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v)
 				seq_printf(m, "\n%d) %s", i, tcon->tree_name);
 				if (tcon->need_reconnect)
 					seq_puts(m, "\tDISCONNECTED ");
-				seq_printf(m, "\nSMBs: %d",
-					   atomic_read(&tcon->num_smbs_sent));
+				seq_printf(m, "\nSMBs: %d since %ptTs UTC",
+					   atomic_read(&tcon->num_smbs_sent),
+					   &tcon->stats_from_time);
 				if (server->ops->print_stats)
 					server->ops->print_stats(m, tcon);
 			}
diff --git a/fs/smb/client/cifsencrypt.c b/fs/smb/client/cifsencrypt.c
index ef4c2e3c9fa6..6322f0f68a17 100644
--- a/fs/smb/client/cifsencrypt.c
+++ b/fs/smb/client/cifsencrypt.c
@@ -572,7 +572,7 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash,
 		len = cifs_strtoUTF16(user, ses->user_name, len, nls_cp);
 		UniStrupr(user);
 	} else {
-		memset(user, '\0', 2);
+		*(u16 *)user = 0;
 	}
 
 	rc = crypto_shash_update(ses->server->secmech.hmacmd5,
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 99b0ade833aa..fb368b191eef 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -396,7 +396,7 @@ cifs_alloc_inode(struct super_block *sb)
 	spin_lock_init(&cifs_inode->writers_lock);
 	cifs_inode->writers = 0;
 	cifs_inode->netfs.inode.i_blkbits = 14;  /* 2**14 = CIFS_MAX_MSGSIZE */
-	cifs_inode->server_eof = 0;
+	cifs_inode->netfs.remote_i_size = 0;
 	cifs_inode->uniqueid = 0;
 	cifs_inode->createtime = 0;
 	cifs_inode->epoch = 0;
@@ -430,7 +430,7 @@ static void
 cifs_evict_inode(struct inode *inode)
 {
 	truncate_inode_pages_final(&inode->i_data);
-	if (inode->i_state & I_PINNING_FSCACHE_WB)
+	if (inode->i_state & I_PINNING_NETFS_WB)
 		cifs_fscache_unuse_inode_cookie(inode, true);
 	cifs_fscache_release_inode_cookie(inode);
 	clear_inode(inode);
@@ -681,6 +681,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 		seq_printf(s, ",rasize=%u", cifs_sb->ctx->rasize);
 	if (tcon->ses->server->min_offload)
 		seq_printf(s, ",esize=%u", tcon->ses->server->min_offload);
+	if (tcon->ses->server->retrans)
+		seq_printf(s, ",retrans=%u", tcon->ses->server->retrans);
 	seq_printf(s, ",echo_interval=%lu",
 			tcon->ses->server->echo_interval / HZ);
 
@@ -793,8 +795,7 @@ static int cifs_show_stats(struct seq_file *s, struct dentry *root)
 
 static int cifs_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
-	fscache_unpin_writeback(wbc, cifs_inode_cookie(inode));
-	return 0;
+	return netfs_unpin_writeback(inode, wbc);
 }
 
 static int cifs_drop_inode(struct inode *inode)
@@ -1084,7 +1085,7 @@ static loff_t cifs_llseek(struct file *file, loff_t offset, int whence)
 }
 
 static int
-cifs_setlease(struct file *file, int arg, struct file_lock **lease, void **priv)
+cifs_setlease(struct file *file, int arg, struct file_lease **lease, void **priv)
 {
 	/*
 	 * Note that this is called by vfs setlease with i_lock held to
@@ -1093,9 +1094,6 @@ cifs_setlease(struct file *file, int arg, struct file_lock **lease, void **priv)
 	struct inode *inode = file_inode(file);
 	struct cifsFileInfo *cfile = file->private_data;
 
-	if (!(S_ISREG(inode->i_mode)))
-		return -EINVAL;
-
 	/* Check if file is oplocked if this is request for new lease */
 	if (arg == F_UNLCK ||
 	    ((arg == F_RDLCK) && CIFS_CACHE_READ(CIFS_I(inode))) ||
@@ -1171,6 +1169,9 @@ const char *cifs_get_link(struct dentry *dentry, struct inode *inode,
 {
 	char *target_path;
 
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
 	target_path = kmalloc(PATH_MAX, GFP_KERNEL);
 	if (!target_path)
 		return ERR_PTR(-ENOMEM);
@@ -1222,7 +1223,7 @@ static int cifs_precopy_set_eof(struct inode *src_inode, struct cifsInodeInfo *s
 	if (rc < 0)
 		goto set_failed;
 
-	netfs_resize_file(&src_cifsi->netfs, src_end);
+	netfs_resize_file(&src_cifsi->netfs, src_end, true);
 	fscache_resize_cookie(cifs_inode_cookie(src_inode), src_end);
 	return 0;
 
@@ -1353,7 +1354,7 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
 			smb_file_src, smb_file_target, off, len, destoff);
 		if (rc == 0 && new_size > i_size_read(target_inode)) {
 			truncate_setsize(target_inode, new_size);
-			netfs_resize_file(&target_cifsi->netfs, new_size);
+			netfs_resize_file(&target_cifsi->netfs, new_size, true);
 			fscache_resize_cookie(cifs_inode_cookie(target_inode),
 					      new_size);
 		}
@@ -1379,6 +1380,7 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
 	struct inode *src_inode = file_inode(src_file);
 	struct inode *target_inode = file_inode(dst_file);
 	struct cifsInodeInfo *src_cifsi = CIFS_I(src_inode);
+	struct cifsInodeInfo *target_cifsi = CIFS_I(target_inode);
 	struct cifsFileInfo *smb_file_src;
 	struct cifsFileInfo *smb_file_target;
 	struct cifs_tcon *src_tcon;
@@ -1427,7 +1429,7 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
 	 * Advance the EOF marker after the flush above to the end of the range
 	 * if it's short of that.
 	 */
-	if (src_cifsi->server_eof < off + len) {
+	if (src_cifsi->netfs.remote_i_size < off + len) {
 		rc = cifs_precopy_set_eof(src_inode, src_cifsi, src_tcon, xid, off + len);
 		if (rc < 0)
 			goto unlock;
@@ -1451,12 +1453,22 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
 	/* Discard all the folios that overlap the destination region. */
 	truncate_inode_pages_range(&target_inode->i_data, fstart, fend);
 
+	fscache_invalidate(cifs_inode_cookie(target_inode), NULL,
+			   i_size_read(target_inode), 0);
+
 	rc = file_modified(dst_file);
 	if (!rc) {
 		rc = target_tcon->ses->server->ops->copychunk_range(xid,
 			smb_file_src, smb_file_target, off, len, destoff);
-		if (rc > 0 && destoff + rc > i_size_read(target_inode))
+		if (rc > 0 && destoff + rc > i_size_read(target_inode)) {
 			truncate_setsize(target_inode, destoff + rc);
+			netfs_resize_file(&target_cifsi->netfs,
+					  i_size_read(target_inode), true);
+			fscache_resize_cookie(cifs_inode_cookie(target_inode),
+					      i_size_read(target_inode));
+		}
+		if (rc > 0 && destoff + rc > target_cifsi->netfs.zero_point)
+			target_cifsi->netfs.zero_point = destoff + rc;
 	}
 
 	file_accessed(src_file);
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 879d5ef8a66e..53c75cfb33ab 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -50,6 +50,11 @@
 #define CIFS_DEF_ACTIMEO (1 * HZ)
 
 /*
+ * max sleep time before retry to server
+ */
+#define CIFS_MAX_SLEEP 2000
+
+/*
  * max attribute cache timeout (jiffies) - 2^30
  */
 #define CIFS_MAX_ACTIMEO (1 << 30)
@@ -82,7 +87,7 @@
 #define SMB_INTERFACE_POLL_INTERVAL	600
 
 /* maximum number of PDUs in one compound */
-#define MAX_COMPOUND 5
+#define MAX_COMPOUND 7
 
 /*
  * Default number of credits to keep available for SMB3.
@@ -204,6 +209,8 @@ struct cifs_open_info_data {
 		};
 	} reparse;
 	char *symlink_target;
+	struct cifs_sid posix_owner;
+	struct cifs_sid posix_group;
 	union {
 		struct smb2_file_all_info fi;
 		struct smb311_posix_qinfo posix_fi;
@@ -751,6 +758,7 @@ struct TCP_Server_Info {
 	unsigned int	max_read;
 	unsigned int	max_write;
 	unsigned int	min_offload;
+	unsigned int	retrans;
 	__le16	compress_algorithm;
 	__u16	signing_algorithm;
 	__le16	cipher_type;
@@ -1024,6 +1032,8 @@ struct cifs_chan {
 	__u8 signkey[SMB3_SIGN_KEY_SIZE];
 };
 
+#define CIFS_SES_FLAG_SCALE_CHANNELS (0x1)
+
 /*
  * Session structure.  One of these for each uid session with a particular host
  */
@@ -1056,6 +1066,7 @@ struct cifs_ses {
 	enum securityEnum sectype; /* what security flavor was specified? */
 	bool sign;		/* is signing required? */
 	bool domainAuto:1;
+	unsigned int flags;
 	__u16 session_flags;
 	__u8 smb3signingkey[SMB3_SIGN_KEY_SIZE];
 	__u8 smb3encryptionkey[SMB3_ENC_DEC_KEY_SIZE];
@@ -1207,6 +1218,7 @@ struct cifs_tcon {
 	__u64    bytes_read;
 	__u64    bytes_written;
 	spinlock_t stat_lock;  /* protects the two fields above */
+	time64_t stats_from_time;
 	FILE_SYSTEM_DEVICE_INFO fsDevInfo;
 	FILE_SYSTEM_ATTRIBUTE_INFO fsAttrInfo; /* ok if fs name truncated */
 	FILE_SYSTEM_UNIX_INFO fsUnixInfo;
@@ -1366,6 +1378,7 @@ struct cifs_open_parms {
 	struct cifs_fid *fid;
 	umode_t mode;
 	bool reconnect:1;
+	bool replay:1; /* indicates that this open is for a replay */
 };
 
 struct cifs_fid {
@@ -1497,6 +1510,7 @@ struct cifs_writedata {
 	struct smbd_mr			*mr;
 #endif
 	struct cifs_credits		credits;
+	bool				replay;
 };
 
 /*
@@ -1557,7 +1571,6 @@ struct cifsInodeInfo {
 	spinlock_t writers_lock;
 	unsigned int writers;		/* Number of writers on this inode */
 	unsigned long time;		/* jiffies of last update of inode */
-	u64  server_eof;		/* current file size on server -- protected by i_lock */
 	u64  uniqueid;			/* server inode number */
 	u64  createtime;		/* creation time on server */
 	__u8 lease_key[SMB2_LEASE_KEY_SIZE];	/* lease key for this inode */
@@ -1827,6 +1840,13 @@ static inline bool is_retryable_error(int error)
 	return false;
 }
 
+static inline bool is_replayable_error(int error)
+{
+	if (error == -EAGAIN || error == -ECONNABORTED)
+		return true;
+	return false;
+}
+
 
 /* cifs_get_writable_file() flags */
 #define FIND_WR_ANY         0
diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index 01e89070df5a..5eb83bafc7fd 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -2066,20 +2066,20 @@ CIFSSMBPosixLock(const unsigned int xid, struct cifs_tcon *tcon,
 		parm_data = (struct cifs_posix_lock *)
 			((char *)&pSMBr->hdr.Protocol + data_offset);
 		if (parm_data->lock_type == cpu_to_le16(CIFS_UNLCK))
-			pLockData->fl_type = F_UNLCK;
+			pLockData->c.flc_type = F_UNLCK;
 		else {
 			if (parm_data->lock_type ==
 					cpu_to_le16(CIFS_RDLCK))
-				pLockData->fl_type = F_RDLCK;
+				pLockData->c.flc_type = F_RDLCK;
 			else if (parm_data->lock_type ==
 					cpu_to_le16(CIFS_WRLCK))
-				pLockData->fl_type = F_WRLCK;
+				pLockData->c.flc_type = F_WRLCK;
 
 			pLockData->fl_start = le64_to_cpu(parm_data->start);
 			pLockData->fl_end = pLockData->fl_start +
 				(le64_to_cpu(parm_data->length) ?
 				 le64_to_cpu(parm_data->length) - 1 : 0);
-			pLockData->fl_pid = -le32_to_cpu(parm_data->pid);
+			pLockData->c.flc_pid = -le32_to_cpu(parm_data->pid);
 		}
 	}
 
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 3052a208c6ca..ac9595504f4b 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -233,6 +233,12 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server,
 	list_for_each_entry_safe(ses, nses, &pserver->smb_ses_list, smb_ses_list) {
 		/* check if iface is still active */
 		spin_lock(&ses->chan_lock);
+		if (cifs_ses_get_chan_index(ses, server) ==
+		    CIFS_INVAL_CHAN_INDEX) {
+			spin_unlock(&ses->chan_lock);
+			continue;
+		}
+
 		if (!cifs_chan_is_iface_active(ses, server)) {
 			spin_unlock(&ses->chan_lock);
 			cifs_chan_update_iface(ses, server);
@@ -1574,6 +1580,9 @@ static int match_server(struct TCP_Server_Info *server,
 	if (server->min_offload != ctx->min_offload)
 		return 0;
 
+	if (server->retrans != ctx->retrans)
+		return 0;
+
 	return 1;
 }
 
@@ -1798,6 +1807,7 @@ smbd_connected:
 		goto out_err_crypto_release;
 	}
 	tcp_ses->min_offload = ctx->min_offload;
+	tcp_ses->retrans = ctx->retrans;
 	/*
 	 * at this point we are the only ones with the pointer
 	 * to the struct since the kernel thread not created yet
@@ -3434,8 +3444,18 @@ int cifs_mount_get_tcon(struct cifs_mount_ctx *mnt_ctx)
 	 * the user on mount
 	 */
 	if ((cifs_sb->ctx->wsize == 0) ||
-	    (cifs_sb->ctx->wsize > server->ops->negotiate_wsize(tcon, ctx)))
-		cifs_sb->ctx->wsize = server->ops->negotiate_wsize(tcon, ctx);
+	    (cifs_sb->ctx->wsize > server->ops->negotiate_wsize(tcon, ctx))) {
+		cifs_sb->ctx->wsize =
+			round_down(server->ops->negotiate_wsize(tcon, ctx), PAGE_SIZE);
+		/*
+		 * in the very unlikely event that the server sent a max write size under PAGE_SIZE,
+		 * (which would get rounded down to 0) then reset wsize to absolute minimum eg 4096
+		 */
+		if (cifs_sb->ctx->wsize == 0) {
+			cifs_sb->ctx->wsize = PAGE_SIZE;
+			cifs_dbg(VFS, "wsize too small, reset to minimum ie PAGE_SIZE, usually 4096\n");
+		}
+	}
 	if ((cifs_sb->ctx->rsize == 0) ||
 	    (cifs_sb->ctx->rsize > server->ops->negotiate_rsize(tcon, ctx)))
 		cifs_sb->ctx->rsize = server->ops->negotiate_rsize(tcon, ctx);
@@ -4224,6 +4244,11 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru
 
 	/* only send once per connect */
 	spin_lock(&tcon->tc_lock);
+
+	/* if tcon is marked for needing reconnect, update state */
+	if (tcon->need_reconnect)
+		tcon->status = TID_NEED_TCON;
+
 	if (tcon->status == TID_GOOD) {
 		spin_unlock(&tcon->tc_lock);
 		return 0;
diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c
index a8a1d386da65..449c59830039 100644
--- a/fs/smb/client/dfs.c
+++ b/fs/smb/client/dfs.c
@@ -565,6 +565,11 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru
 
 	/* only send once per connect */
 	spin_lock(&tcon->tc_lock);
+
+	/* if tcon is marked for needing reconnect, update state */
+	if (tcon->need_reconnect)
+		tcon->status = TID_NEED_TCON;
+
 	if (tcon->status == TID_GOOD) {
 		spin_unlock(&tcon->tc_lock);
 		return 0;
@@ -625,8 +630,8 @@ out:
 		spin_lock(&tcon->tc_lock);
 		if (tcon->status == TID_IN_TCON)
 			tcon->status = TID_GOOD;
-		spin_unlock(&tcon->tc_lock);
 		tcon->need_reconnect = false;
+		spin_unlock(&tcon->tc_lock);
 	}
 
 	return rc;
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 1b4262aff8fa..c3b8e7091a4d 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -87,7 +87,7 @@ void cifs_pages_written_back(struct inode *inode, loff_t start, unsigned int len
 			continue;
 		if (!folio_test_writeback(folio)) {
 			WARN_ONCE(1, "bad %x @%llx page %lx %lx\n",
-				  len, start, folio_index(folio), end);
+				  len, start, folio->index, end);
 			continue;
 		}
 
@@ -120,7 +120,7 @@ void cifs_pages_write_failed(struct inode *inode, loff_t start, unsigned int len
 			continue;
 		if (!folio_test_writeback(folio)) {
 			WARN_ONCE(1, "bad %x @%llx page %lx %lx\n",
-				  len, start, folio_index(folio), end);
+				  len, start, folio->index, end);
 			continue;
 		}
 
@@ -151,7 +151,7 @@ void cifs_pages_write_redirty(struct inode *inode, loff_t start, unsigned int le
 	xas_for_each(&xas, folio, end) {
 		if (!folio_test_writeback(folio)) {
 			WARN_ONCE(1, "bad %x @%llx page %lx %lx\n",
-				  len, start, folio_index(folio), end);
+				  len, start, folio->index, end);
 			continue;
 		}
 
@@ -175,6 +175,9 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon)
 
 	/* only send once per connect */
 	spin_lock(&tcon->tc_lock);
+	if (tcon->need_reconnect)
+		tcon->status = TID_NEED_RECON;
+
 	if (tcon->status != TID_NEED_RECON) {
 		spin_unlock(&tcon->tc_lock);
 		return;
@@ -1312,20 +1315,20 @@ cifs_lock_test(struct cifsFileInfo *cfile, __u64 offset, __u64 length,
 	down_read(&cinode->lock_sem);
 
 	exist = cifs_find_lock_conflict(cfile, offset, length, type,
-					flock->fl_flags, &conf_lock,
+					flock->c.flc_flags, &conf_lock,
 					CIFS_LOCK_OP);
 	if (exist) {
 		flock->fl_start = conf_lock->offset;
 		flock->fl_end = conf_lock->offset + conf_lock->length - 1;
-		flock->fl_pid = conf_lock->pid;
+		flock->c.flc_pid = conf_lock->pid;
 		if (conf_lock->type & server->vals->shared_lock_type)
-			flock->fl_type = F_RDLCK;
+			flock->c.flc_type = F_RDLCK;
 		else
-			flock->fl_type = F_WRLCK;
+			flock->c.flc_type = F_WRLCK;
 	} else if (!cinode->can_cache_brlcks)
 		rc = 1;
 	else
-		flock->fl_type = F_UNLCK;
+		flock->c.flc_type = F_UNLCK;
 
 	up_read(&cinode->lock_sem);
 	return rc;
@@ -1401,16 +1404,16 @@ cifs_posix_lock_test(struct file *file, struct file_lock *flock)
 {
 	int rc = 0;
 	struct cifsInodeInfo *cinode = CIFS_I(file_inode(file));
-	unsigned char saved_type = flock->fl_type;
+	unsigned char saved_type = flock->c.flc_type;
 
-	if ((flock->fl_flags & FL_POSIX) == 0)
+	if ((flock->c.flc_flags & FL_POSIX) == 0)
 		return 1;
 
 	down_read(&cinode->lock_sem);
 	posix_test_lock(file, flock);
 
-	if (flock->fl_type == F_UNLCK && !cinode->can_cache_brlcks) {
-		flock->fl_type = saved_type;
+	if (lock_is_unlock(flock) && !cinode->can_cache_brlcks) {
+		flock->c.flc_type = saved_type;
 		rc = 1;
 	}
 
@@ -1431,7 +1434,7 @@ cifs_posix_lock_set(struct file *file, struct file_lock *flock)
 	struct cifsInodeInfo *cinode = CIFS_I(file_inode(file));
 	int rc = FILE_LOCK_DEFERRED + 1;
 
-	if ((flock->fl_flags & FL_POSIX) == 0)
+	if ((flock->c.flc_flags & FL_POSIX) == 0)
 		return rc;
 
 	cifs_down_write(&cinode->lock_sem);
@@ -1581,7 +1584,9 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 
 	el = locks_to_send.next;
 	spin_lock(&flctx->flc_lock);
-	list_for_each_entry(flock, &flctx->flc_posix, fl_list) {
+	for_each_file_lock(flock, &flctx->flc_posix) {
+		unsigned char ftype = flock->c.flc_type;
+
 		if (el == &locks_to_send) {
 			/*
 			 * The list ended. We don't have enough allocated
@@ -1591,12 +1596,12 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 			break;
 		}
 		length = cifs_flock_len(flock);
-		if (flock->fl_type == F_RDLCK || flock->fl_type == F_SHLCK)
+		if (ftype == F_RDLCK || ftype == F_SHLCK)
 			type = CIFS_RDLCK;
 		else
 			type = CIFS_WRLCK;
 		lck = list_entry(el, struct lock_to_push, llist);
-		lck->pid = hash_lockowner(flock->fl_owner);
+		lck->pid = hash_lockowner(flock->c.flc_owner);
 		lck->netfid = cfile->fid.netfid;
 		lck->length = length;
 		lck->type = type;
@@ -1663,42 +1668,43 @@ static void
 cifs_read_flock(struct file_lock *flock, __u32 *type, int *lock, int *unlock,
 		bool *wait_flag, struct TCP_Server_Info *server)
 {
-	if (flock->fl_flags & FL_POSIX)
+	if (flock->c.flc_flags & FL_POSIX)
 		cifs_dbg(FYI, "Posix\n");
-	if (flock->fl_flags & FL_FLOCK)
+	if (flock->c.flc_flags & FL_FLOCK)
 		cifs_dbg(FYI, "Flock\n");
-	if (flock->fl_flags & FL_SLEEP) {
+	if (flock->c.flc_flags & FL_SLEEP) {
 		cifs_dbg(FYI, "Blocking lock\n");
 		*wait_flag = true;
 	}
-	if (flock->fl_flags & FL_ACCESS)
+	if (flock->c.flc_flags & FL_ACCESS)
 		cifs_dbg(FYI, "Process suspended by mandatory locking - not implemented yet\n");
-	if (flock->fl_flags & FL_LEASE)
+	if (flock->c.flc_flags & FL_LEASE)
 		cifs_dbg(FYI, "Lease on file - not implemented yet\n");
-	if (flock->fl_flags &
+	if (flock->c.flc_flags &
 	    (~(FL_POSIX | FL_FLOCK | FL_SLEEP |
 	       FL_ACCESS | FL_LEASE | FL_CLOSE | FL_OFDLCK)))
-		cifs_dbg(FYI, "Unknown lock flags 0x%x\n", flock->fl_flags);
+		cifs_dbg(FYI, "Unknown lock flags 0x%x\n",
+		         flock->c.flc_flags);
 
 	*type = server->vals->large_lock_type;
-	if (flock->fl_type == F_WRLCK) {
+	if (lock_is_write(flock)) {
 		cifs_dbg(FYI, "F_WRLCK\n");
 		*type |= server->vals->exclusive_lock_type;
 		*lock = 1;
-	} else if (flock->fl_type == F_UNLCK) {
+	} else if (lock_is_unlock(flock)) {
 		cifs_dbg(FYI, "F_UNLCK\n");
 		*type |= server->vals->unlock_lock_type;
 		*unlock = 1;
 		/* Check if unlock includes more than one lock range */
-	} else if (flock->fl_type == F_RDLCK) {
+	} else if (lock_is_read(flock)) {
 		cifs_dbg(FYI, "F_RDLCK\n");
 		*type |= server->vals->shared_lock_type;
 		*lock = 1;
-	} else if (flock->fl_type == F_EXLCK) {
+	} else if (flock->c.flc_type == F_EXLCK) {
 		cifs_dbg(FYI, "F_EXLCK\n");
 		*type |= server->vals->exclusive_lock_type;
 		*lock = 1;
-	} else if (flock->fl_type == F_SHLCK) {
+	} else if (flock->c.flc_type == F_SHLCK) {
 		cifs_dbg(FYI, "F_SHLCK\n");
 		*type |= server->vals->shared_lock_type;
 		*lock = 1;
@@ -1730,7 +1736,7 @@ cifs_getlk(struct file *file, struct file_lock *flock, __u32 type,
 		else
 			posix_lock_type = CIFS_WRLCK;
 		rc = CIFSSMBPosixLock(xid, tcon, netfid,
-				      hash_lockowner(flock->fl_owner),
+				      hash_lockowner(flock->c.flc_owner),
 				      flock->fl_start, length, flock,
 				      posix_lock_type, wait_flag);
 		return rc;
@@ -1747,7 +1753,7 @@ cifs_getlk(struct file *file, struct file_lock *flock, __u32 type,
 	if (rc == 0) {
 		rc = server->ops->mand_lock(xid, cfile, flock->fl_start, length,
 					    type, 0, 1, false);
-		flock->fl_type = F_UNLCK;
+		flock->c.flc_type = F_UNLCK;
 		if (rc != 0)
 			cifs_dbg(VFS, "Error unlocking previously locked range %d during test of lock\n",
 				 rc);
@@ -1755,7 +1761,7 @@ cifs_getlk(struct file *file, struct file_lock *flock, __u32 type,
 	}
 
 	if (type & server->vals->shared_lock_type) {
-		flock->fl_type = F_WRLCK;
+		flock->c.flc_type = F_WRLCK;
 		return 0;
 	}
 
@@ -1767,12 +1773,12 @@ cifs_getlk(struct file *file, struct file_lock *flock, __u32 type,
 	if (rc == 0) {
 		rc = server->ops->mand_lock(xid, cfile, flock->fl_start, length,
 			type | server->vals->shared_lock_type, 0, 1, false);
-		flock->fl_type = F_RDLCK;
+		flock->c.flc_type = F_RDLCK;
 		if (rc != 0)
 			cifs_dbg(VFS, "Error unlocking previously locked range %d during test of lock\n",
 				 rc);
 	} else
-		flock->fl_type = F_WRLCK;
+		flock->c.flc_type = F_WRLCK;
 
 	return 0;
 }
@@ -1940,7 +1946,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type,
 			posix_lock_type = CIFS_UNLCK;
 
 		rc = CIFSSMBPosixLock(xid, tcon, cfile->fid.netfid,
-				      hash_lockowner(flock->fl_owner),
+				      hash_lockowner(flock->c.flc_owner),
 				      flock->fl_start, length,
 				      NULL, posix_lock_type, wait_flag);
 		goto out;
@@ -1950,7 +1956,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type,
 		struct cifsLockInfo *lock;
 
 		lock = cifs_lock_init(flock->fl_start, length, type,
-				      flock->fl_flags);
+				      flock->c.flc_flags);
 		if (!lock)
 			return -ENOMEM;
 
@@ -1989,7 +1995,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type,
 		rc = server->ops->mand_unlock_range(cfile, flock, xid);
 
 out:
-	if ((flock->fl_flags & FL_POSIX) || (flock->fl_flags & FL_FLOCK)) {
+	if ((flock->c.flc_flags & FL_POSIX) || (flock->c.flc_flags & FL_FLOCK)) {
 		/*
 		 * If this is a request to remove all locks because we
 		 * are closing the file, it doesn't matter if the
@@ -1998,7 +2004,7 @@ out:
 		 */
 		if (rc) {
 			cifs_dbg(VFS, "%s failed rc=%d\n", __func__, rc);
-			if (!(flock->fl_flags & FL_CLOSE))
+			if (!(flock->c.flc_flags & FL_CLOSE))
 				return rc;
 		}
 		rc = locks_lock_file_wait(file, flock);
@@ -2019,7 +2025,7 @@ int cifs_flock(struct file *file, int cmd, struct file_lock *fl)
 
 	xid = get_xid();
 
-	if (!(fl->fl_flags & FL_FLOCK)) {
+	if (!(fl->c.flc_flags & FL_FLOCK)) {
 		rc = -ENOLCK;
 		free_xid(xid);
 		return rc;
@@ -2070,7 +2076,8 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *flock)
 	xid = get_xid();
 
 	cifs_dbg(FYI, "%s: %pD2 cmd=0x%x type=0x%x flags=0x%x r=%lld:%lld\n", __func__, file, cmd,
-		 flock->fl_flags, flock->fl_type, (long long)flock->fl_start,
+		 flock->c.flc_flags, flock->c.flc_type,
+		 (long long)flock->fl_start,
 		 (long long)flock->fl_end);
 
 	cfile = (struct cifsFileInfo *)file->private_data;
@@ -2120,8 +2127,8 @@ cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset,
 {
 	loff_t end_of_write = offset + bytes_written;
 
-	if (end_of_write > cifsi->server_eof)
-		cifsi->server_eof = end_of_write;
+	if (end_of_write > cifsi->netfs.remote_i_size)
+		netfs_resize_file(&cifsi->netfs, end_of_write, true);
 }
 
 static ssize_t
@@ -2651,7 +2658,7 @@ static void cifs_extend_writeback(struct address_space *mapping,
 				continue;
 			if (xa_is_value(folio))
 				break;
-			if (folio_index(folio) != index)
+			if (folio->index != index)
 				break;
 			if (!folio_try_get_rcu(folio)) {
 				xas_reset(&xas);
@@ -2899,7 +2906,7 @@ redo_folio:
 					goto skip_write;
 			}
 
-			if (folio_mapping(folio) != mapping ||
+			if (folio->mapping != mapping ||
 			    !folio_test_dirty(folio)) {
 				start += folio_size(folio);
 				folio_unlock(folio);
@@ -2951,7 +2958,7 @@ skip_write:
 			continue;
 		}
 
-		folio_batch_release(&fbatch);		
+		folio_batch_release(&fbatch);
 		cond_resched();
 	} while (wbc->nr_to_write > 0);
 
@@ -3247,8 +3254,8 @@ cifs_uncached_writev_complete(struct work_struct *work)
 
 	spin_lock(&inode->i_lock);
 	cifs_update_eof(cifsi, wdata->offset, wdata->bytes);
-	if (cifsi->server_eof > inode->i_size)
-		i_size_write(inode, cifsi->server_eof);
+	if (cifsi->netfs.remote_i_size > inode->i_size)
+		i_size_write(inode, cifsi->netfs.remote_i_size);
 	spin_unlock(&inode->i_lock);
 
 	complete(&wdata->done);
@@ -3300,6 +3307,7 @@ cifs_resend_wdata(struct cifs_writedata *wdata, struct list_head *wdata_list,
 			if (wdata->cfile->invalidHandle)
 				rc = -EAGAIN;
 			else {
+				wdata->replay = true;
 #ifdef CONFIG_CIFS_SMB_DIRECT
 				if (wdata->mr) {
 					wdata->mr->need_invalidate = true;
@@ -5043,27 +5051,13 @@ static void cifs_swap_deactivate(struct file *file)
 	/* do we need to unpin (or unlock) the file */
 }
 
-/*
- * Mark a page as having been made dirty and thus needing writeback.  We also
- * need to pin the cache object to write back to.
- */
-#ifdef CONFIG_CIFS_FSCACHE
-static bool cifs_dirty_folio(struct address_space *mapping, struct folio *folio)
-{
-	return fscache_dirty_folio(mapping, folio,
-					cifs_inode_cookie(mapping->host));
-}
-#else
-#define cifs_dirty_folio filemap_dirty_folio
-#endif
-
 const struct address_space_operations cifs_addr_ops = {
 	.read_folio = cifs_read_folio,
 	.readahead = cifs_readahead,
 	.writepages = cifs_writepages,
 	.write_begin = cifs_write_begin,
 	.write_end = cifs_write_end,
-	.dirty_folio = cifs_dirty_folio,
+	.dirty_folio = netfs_dirty_folio,
 	.release_folio = cifs_release_folio,
 	.direct_IO = cifs_direct_io,
 	.invalidate_folio = cifs_invalidate_folio,
@@ -5087,7 +5081,7 @@ const struct address_space_operations cifs_addr_ops_smallbuf = {
 	.writepages = cifs_writepages,
 	.write_begin = cifs_write_begin,
 	.write_end = cifs_write_end,
-	.dirty_folio = cifs_dirty_folio,
+	.dirty_folio = netfs_dirty_folio,
 	.release_folio = cifs_release_folio,
 	.invalidate_folio = cifs_invalidate_folio,
 	.launder_folio = cifs_launder_folio,
diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index a3493da12ad1..4b2f5aa2ea0e 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -139,6 +139,7 @@ const struct fs_parameter_spec smb3_fs_parameters[] = {
 	fsparam_u32("dir_mode", Opt_dirmode),
 	fsparam_u32("port", Opt_port),
 	fsparam_u32("min_enc_offload", Opt_min_enc_offload),
+	fsparam_u32("retrans", Opt_retrans),
 	fsparam_u32("esize", Opt_min_enc_offload),
 	fsparam_u32("bsize", Opt_blocksize),
 	fsparam_u32("rasize", Opt_rasize),
@@ -210,7 +211,7 @@ cifs_parse_security_flavors(struct fs_context *fc, char *value, struct smb3_fs_c
 
 	switch (match_token(value, cifs_secflavor_tokens, args)) {
 	case Opt_sec_krb5p:
-		cifs_errorf(fc, "sec=krb5p is not supported!\n");
+		cifs_errorf(fc, "sec=krb5p is not supported. Use sec=krb5,seal instead\n");
 		return 1;
 	case Opt_sec_krb5i:
 		ctx->sign = true;
@@ -1064,6 +1065,9 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 	case Opt_min_enc_offload:
 		ctx->min_offload = result.uint_32;
 		break;
+	case Opt_retrans:
+		ctx->retrans = result.uint_32;
+		break;
 	case Opt_blocksize:
 		/*
 		 * inode blocksize realistically should never need to be
@@ -1107,6 +1111,17 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 	case Opt_wsize:
 		ctx->wsize = result.uint_32;
 		ctx->got_wsize = true;
+		if (ctx->wsize % PAGE_SIZE != 0) {
+			ctx->wsize = round_down(ctx->wsize, PAGE_SIZE);
+			if (ctx->wsize == 0) {
+				ctx->wsize = PAGE_SIZE;
+				cifs_dbg(VFS, "wsize too small, reset to minimum %ld\n", PAGE_SIZE);
+			} else {
+				cifs_dbg(VFS,
+					 "wsize rounded down to %d to multiple of PAGE_SIZE %ld\n",
+					 ctx->wsize, PAGE_SIZE);
+			}
+		}
 		break;
 	case Opt_acregmax:
 		ctx->acregmax = HZ * result.uint_32;
@@ -1619,6 +1634,8 @@ int smb3_init_fs_context(struct fs_context *fc)
 	ctx->backupuid_specified = false; /* no backup intent for a user */
 	ctx->backupgid_specified = false; /* no backup intent for a group */
 
+	ctx->retrans = 1;
+
 /*
  *	short int override_uid = -1;
  *	short int override_gid = -1;
diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h
index cf46916286d0..182ce11cbe93 100644
--- a/fs/smb/client/fs_context.h
+++ b/fs/smb/client/fs_context.h
@@ -118,6 +118,7 @@ enum cifs_param {
 	Opt_file_mode,
 	Opt_dirmode,
 	Opt_min_enc_offload,
+	Opt_retrans,
 	Opt_blocksize,
 	Opt_rasize,
 	Opt_rsize,
@@ -245,6 +246,7 @@ struct smb3_fs_context {
 	unsigned int rsize;
 	unsigned int wsize;
 	unsigned int min_offload;
+	unsigned int retrans;
 	bool sockopt_tcp_nodelay:1;
 	/* attribute cache timemout for files and directories in jiffies */
 	unsigned long acregmax;
diff --git a/fs/smb/client/fscache.c b/fs/smb/client/fscache.c
index e5cad149f5a2..c4a3cb736881 100644
--- a/fs/smb/client/fscache.c
+++ b/fs/smb/client/fscache.c
@@ -180,7 +180,7 @@ static int fscache_fallback_write_pages(struct inode *inode, loff_t start, size_
 	if (ret < 0)
 		return ret;
 
-	ret = cres.ops->prepare_write(&cres, &start, &len, i_size_read(inode),
+	ret = cres.ops->prepare_write(&cres, &start, &len, len, i_size_read(inode),
 				      no_space_allocated_yet);
 	if (ret == 0)
 		ret = fscache_write(&cres, start, &iter, NULL, NULL);
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index 9f37c1758f73..d02f8ba29cb5 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -104,7 +104,7 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr)
 	fattr->cf_mtime = timestamp_truncate(fattr->cf_mtime, inode);
 	mtime = inode_get_mtime(inode);
 	if (timespec64_equal(&mtime, &fattr->cf_mtime) &&
-	    cifs_i->server_eof == fattr->cf_eof) {
+	    cifs_i->netfs.remote_i_size == fattr->cf_eof) {
 		cifs_dbg(FYI, "%s: inode %llu is unchanged\n",
 			 __func__, cifs_i->uniqueid);
 		return;
@@ -194,7 +194,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
 	else
 		clear_bit(CIFS_INO_DELETE_PENDING, &cifs_i->flags);
 
-	cifs_i->server_eof = fattr->cf_eof;
+	cifs_i->netfs.remote_i_size = fattr->cf_eof;
 	/*
 	 * Can't safely change the file size here if the client is writing to
 	 * it due to potential races.
@@ -665,8 +665,6 @@ static int cifs_sfu_mode(struct cifs_fattr *fattr, const unsigned char *path,
 /* Fill a cifs_fattr struct with info from POSIX info struct */
 static void smb311_posix_info_to_fattr(struct cifs_fattr *fattr,
 				       struct cifs_open_info_data *data,
-				       struct cifs_sid *owner,
-				       struct cifs_sid *group,
 				       struct super_block *sb)
 {
 	struct smb311_posix_qinfo *info = &data->posix_fi;
@@ -722,8 +720,8 @@ out_reparse:
 		fattr->cf_symlink_target = data->symlink_target;
 		data->symlink_target = NULL;
 	}
-	sid_to_id(cifs_sb, owner, fattr, SIDOWNER);
-	sid_to_id(cifs_sb, group, fattr, SIDGROUP);
+	sid_to_id(cifs_sb, &data->posix_owner, fattr, SIDOWNER);
+	sid_to_id(cifs_sb, &data->posix_group, fattr, SIDGROUP);
 
 	cifs_dbg(FYI, "POSIX query info: mode 0x%x uniqueid 0x%llx nlink %d\n",
 		fattr->cf_mode, fattr->cf_uniqueid, fattr->cf_nlink);
@@ -1070,9 +1068,7 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data,
 				 const unsigned int xid,
 				 struct cifs_tcon *tcon,
 				 const char *full_path,
-				 struct cifs_fattr *fattr,
-				 struct cifs_sid *owner,
-				 struct cifs_sid *group)
+				 struct cifs_fattr *fattr)
 {
 	struct TCP_Server_Info *server = tcon->ses->server;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
@@ -1117,7 +1113,7 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data,
 	}
 
 	if (tcon->posix_extensions)
-		smb311_posix_info_to_fattr(fattr, data, owner, group, sb);
+		smb311_posix_info_to_fattr(fattr, data, sb);
 	else
 		cifs_open_info_to_fattr(fattr, data, sb);
 out:
@@ -1171,8 +1167,7 @@ static int cifs_get_fattr(struct cifs_open_info_data *data,
 		 */
 		if (cifs_open_data_reparse(data)) {
 			rc = reparse_info_to_fattr(data, sb, xid, tcon,
-						   full_path, fattr,
-						   NULL, NULL);
+						   full_path, fattr);
 		} else {
 			cifs_open_info_to_fattr(fattr, data, sb);
 		}
@@ -1317,10 +1312,10 @@ static int smb311_posix_get_fattr(struct cifs_open_info_data *data,
 				  const unsigned int xid)
 {
 	struct cifs_open_info_data tmp_data = {};
+	struct TCP_Server_Info *server;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 	struct cifs_tcon *tcon;
 	struct tcon_link *tlink;
-	struct cifs_sid owner, group;
 	int tmprc;
 	int rc = 0;
 
@@ -1328,14 +1323,14 @@ static int smb311_posix_get_fattr(struct cifs_open_info_data *data,
 	if (IS_ERR(tlink))
 		return PTR_ERR(tlink);
 	tcon = tlink_tcon(tlink);
+	server = tcon->ses->server;
 
 	/*
 	 * 1. Fetch file metadata if not provided (data)
 	 */
 	if (!data) {
-		rc = smb311_posix_query_path_info(xid, tcon, cifs_sb,
-						  full_path, &tmp_data,
-						  &owner, &group);
+		rc = server->ops->query_path_info(xid, tcon, cifs_sb,
+						  full_path, &tmp_data);
 		data = &tmp_data;
 	}
 
@@ -1347,11 +1342,9 @@ static int smb311_posix_get_fattr(struct cifs_open_info_data *data,
 	case 0:
 		if (cifs_open_data_reparse(data)) {
 			rc = reparse_info_to_fattr(data, sb, xid, tcon,
-						   full_path, fattr,
-						   &owner, &group);
+						   full_path, fattr);
 		} else {
-			smb311_posix_info_to_fattr(fattr, data,
-						   &owner, &group, sb);
+			smb311_posix_info_to_fattr(fattr, data, sb);
 		}
 		break;
 	case -EREMOTE:
@@ -2865,7 +2858,7 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs,
 
 set_size_out:
 	if (rc == 0) {
-		cifsInode->server_eof = attrs->ia_size;
+		netfs_resize_file(&cifsInode->netfs, attrs->ia_size, true);
 		cifs_setsize(inode, attrs->ia_size);
 		/*
 		 * i_blocks is not related to (i_size / i_blksize), but instead
@@ -3018,6 +3011,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 	if ((attrs->ia_valid & ATTR_SIZE) &&
 	    attrs->ia_size != i_size_read(inode)) {
 		truncate_setsize(inode, attrs->ia_size);
+		netfs_resize_file(&cifsInode->netfs, attrs->ia_size, true);
 		fscache_resize_cookie(cifs_inode_cookie(inode), attrs->ia_size);
 	}
 
@@ -3217,6 +3211,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 	if ((attrs->ia_valid & ATTR_SIZE) &&
 	    attrs->ia_size != i_size_read(inode)) {
 		truncate_setsize(inode, attrs->ia_size);
+		netfs_resize_file(&cifsInode->netfs, attrs->ia_size, true);
 		fscache_resize_cookie(cifs_inode_cookie(inode), attrs->ia_size);
 	}
 
diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c
index c2137ea3c253..0748d7b757b9 100644
--- a/fs/smb/client/misc.c
+++ b/fs/smb/client/misc.c
@@ -140,6 +140,7 @@ tcon_info_alloc(bool dir_leases_enabled)
 	spin_lock_init(&ret_buf->stat_lock);
 	atomic_set(&ret_buf->num_local_opens, 0);
 	atomic_set(&ret_buf->num_remote_opens, 0);
+	ret_buf->stats_from_time = ktime_get_real_seconds();
 #ifdef CONFIG_CIFS_DFS_UPCALL
 	INIT_LIST_HEAD(&ret_buf->dfs_ses_list);
 #endif
diff --git a/fs/smb/client/namespace.c b/fs/smb/client/namespace.c
index a6968573b775..4a517b280f2b 100644
--- a/fs/smb/client/namespace.c
+++ b/fs/smb/client/namespace.c
@@ -168,6 +168,21 @@ static char *automount_fullpath(struct dentry *dentry, void *page)
 	return s;
 }
 
+static void fs_context_set_ids(struct smb3_fs_context *ctx)
+{
+	kuid_t uid = current_fsuid();
+	kgid_t gid = current_fsgid();
+
+	if (ctx->multiuser) {
+		if (!ctx->uid_specified)
+			ctx->linux_uid = uid;
+		if (!ctx->gid_specified)
+			ctx->linux_gid = gid;
+	}
+	if (!ctx->cruid_specified)
+		ctx->cred_uid = uid;
+}
+
 /*
  * Create a vfsmount that we can automount
  */
@@ -205,6 +220,7 @@ static struct vfsmount *cifs_do_automount(struct path *path)
 	tmp.leaf_fullpath = NULL;
 	tmp.UNC = tmp.prepath = NULL;
 	tmp.dfs_root_ses = NULL;
+	fs_context_set_ids(&tmp);
 
 	rc = smb3_fs_context_dup(ctx, &tmp);
 	if (rc) {
diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c
index 056cae1ddcce..b520eea7bfce 100644
--- a/fs/smb/client/readdir.c
+++ b/fs/smb/client/readdir.c
@@ -133,15 +133,15 @@ retry:
 				 * Query dir responses don't provide enough
 				 * information about reparse points other than
 				 * their reparse tags.  Save an invalidation by
-				 * not clobbering the existing mode, size and
-				 * symlink target (if any) when reparse tag and
-				 * ctime haven't changed.
+				 * not clobbering some existing attributes when
+				 * reparse tag and ctime haven't changed.
 				 */
 				rc = 0;
 				if (fattr->cf_cifsattrs & ATTR_REPARSE) {
 					if (likely(reparse_inode_match(inode, fattr))) {
 						fattr->cf_mode = inode->i_mode;
-						fattr->cf_eof = CIFS_I(inode)->server_eof;
+						fattr->cf_rdev = inode->i_rdev;
+						fattr->cf_eof = CIFS_I(inode)->netfs.remote_i_size;
 						fattr->cf_symlink_target = NULL;
 					} else {
 						CIFS_I(inode)->time = 0;
@@ -307,14 +307,16 @@ cifs_dir_info_to_fattr(struct cifs_fattr *fattr, FILE_DIRECTORY_INFO *info,
 }
 
 static void cifs_fulldir_info_to_fattr(struct cifs_fattr *fattr,
-				       SEARCH_ID_FULL_DIR_INFO *info,
+				       const void *info,
 				       struct cifs_sb_info *cifs_sb)
 {
+	const FILE_FULL_DIRECTORY_INFO *di = info;
+
 	__dir_info_to_fattr(fattr, info);
 
-	/* See MS-FSCC 2.4.19 FileIdFullDirectoryInformation */
+	/* See MS-FSCC 2.4.14, 2.4.19 */
 	if (fattr->cf_cifsattrs & ATTR_REPARSE)
-		fattr->cf_cifstag = le32_to_cpu(info->EaSize);
+		fattr->cf_cifstag = le32_to_cpu(di->EaSize);
 	cifs_fill_common_info(fattr, cifs_sb);
 }
 
@@ -396,7 +398,7 @@ ffirst_retry:
 	} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) {
 		cifsFile->srch_inf.info_level = SMB_FIND_FILE_ID_FULL_DIR_INFO;
 	} else /* not srvinos - BB fixme add check for backlevel? */ {
-		cifsFile->srch_inf.info_level = SMB_FIND_FILE_DIRECTORY_INFO;
+		cifsFile->srch_inf.info_level = SMB_FIND_FILE_FULL_DIRECTORY_INFO;
 	}
 
 	search_flags = CIFS_SEARCH_CLOSE_AT_END | CIFS_SEARCH_RETURN_RESUME;
@@ -645,10 +647,10 @@ static int cifs_entry_is_dot(struct cifs_dirent *de, bool is_unicode)
 static int is_dir_changed(struct file *file)
 {
 	struct inode *inode = file_inode(file);
-	struct cifsInodeInfo *cifsInfo = CIFS_I(inode);
+	struct cifsInodeInfo *cifs_inode_info = CIFS_I(inode);
 
-	if (cifsInfo->time == 0)
-		return 1; /* directory was changed, perhaps due to unlink */
+	if (cifs_inode_info->time == 0)
+		return 1; /* directory was changed, e.g. unlink or new file */
 	else
 		return 0;
 
@@ -987,10 +989,9 @@ static int cifs_filldir(char *find_entry, struct file *file,
 				       (FIND_FILE_STANDARD_INFO *)find_entry,
 				       cifs_sb);
 		break;
+	case SMB_FIND_FILE_FULL_DIRECTORY_INFO:
 	case SMB_FIND_FILE_ID_FULL_DIR_INFO:
-		cifs_fulldir_info_to_fattr(&fattr,
-					   (SEARCH_ID_FULL_DIR_INFO *)find_entry,
-					   cifs_sb);
+		cifs_fulldir_info_to_fattr(&fattr, find_entry, cifs_sb);
 		break;
 	default:
 		cifs_dir_info_to_fattr(&fattr,
diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c
index cde81042bebd..8f37373fd333 100644
--- a/fs/smb/client/sess.c
+++ b/fs/smb/client/sess.c
@@ -75,6 +75,10 @@ cifs_ses_get_chan_index(struct cifs_ses *ses,
 {
 	unsigned int i;
 
+	/* if the channel is waiting for termination */
+	if (server && server->terminate)
+		return CIFS_INVAL_CHAN_INDEX;
+
 	for (i = 0; i < ses->chan_count; i++) {
 		if (ses->chans[i].server == server)
 			return i;
@@ -84,7 +88,6 @@ cifs_ses_get_chan_index(struct cifs_ses *ses,
 	if (server)
 		cifs_dbg(VFS, "unable to get chan index for server: 0x%llx",
 			 server->conn_id);
-	WARN_ON(1);
 	return CIFS_INVAL_CHAN_INDEX;
 }
 
@@ -269,6 +272,8 @@ int cifs_try_adding_channels(struct cifs_ses *ses)
 					 &iface->sockaddr,
 					 rc);
 				kref_put(&iface->refcount, release_iface);
+				/* failure to add chan should increase weight */
+				iface->weight_fulfilled++;
 				continue;
 			}
 
diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c
index e0ee96d69d49..c23478ab1cf8 100644
--- a/fs/smb/client/smb2file.c
+++ b/fs/smb/client/smb2file.c
@@ -228,7 +228,7 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
 			 * flock and OFD lock are associated with an open
 			 * file description, not the process.
 			 */
-			if (!(flock->fl_flags & (FL_FLOCK | FL_OFDLCK)))
+			if (!(flock->c.flc_flags & (FL_FLOCK | FL_OFDLCK)))
 				continue;
 		if (cinode->can_cache_brlcks) {
 			/*
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 5053a5550abe..05818cd6d932 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -56,6 +56,35 @@ static inline __u32 file_create_options(struct dentry *dentry)
 	return 0;
 }
 
+/* Parse owner and group from SMB3.1.1 POSIX query info */
+static int parse_posix_sids(struct cifs_open_info_data *data,
+			    struct kvec *rsp_iov)
+{
+	struct smb2_query_info_rsp *qi = rsp_iov->iov_base;
+	unsigned int out_len = le32_to_cpu(qi->OutputBufferLength);
+	unsigned int qi_len = sizeof(data->posix_fi);
+	int owner_len, group_len;
+	u8 *sidsbuf, *sidsbuf_end;
+
+	if (out_len <= qi_len)
+		return -EINVAL;
+
+	sidsbuf = (u8 *)qi + le16_to_cpu(qi->OutputBufferOffset) + qi_len;
+	sidsbuf_end = sidsbuf + out_len - qi_len;
+
+	owner_len = posix_info_sid_size(sidsbuf, sidsbuf_end);
+	if (owner_len == -1)
+		return -EINVAL;
+
+	memcpy(&data->posix_owner, sidsbuf, owner_len);
+	group_len = posix_info_sid_size(sidsbuf + owner_len, sidsbuf_end);
+	if (group_len == -1)
+		return -EINVAL;
+
+	memcpy(&data->posix_group, sidsbuf + owner_len, group_len);
+	return 0;
+}
+
 /*
  * note: If cfile is passed, the reference to it is dropped here.
  * So make sure that you do not reuse cfile after return from this func.
@@ -69,7 +98,6 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
 			    __u32 desired_access, __u32 create_disposition,
 			    __u32 create_options, umode_t mode, struct kvec *in_iov,
 			    int *cmds, int num_cmds, struct cifsFileInfo *cfile,
-			    __u8 **extbuf, size_t *extbuflen,
 			    struct kvec *out_iov, int *out_buftype)
 {
 
@@ -92,6 +120,14 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
 	unsigned int size[2];
 	void *data[2];
 	int len;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	oplock = SMB2_OPLOCK_LEVEL_NONE;
+	num_rqst = 0;
+	server = cifs_pick_channel(ses);
 
 	vars = kzalloc(sizeof(*vars), GFP_ATOMIC);
 	if (vars == NULL)
@@ -99,8 +135,6 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
 	rqst = &vars->rqst[0];
 	rsp_iov = &vars->rsp_iov[0];
 
-	server = cifs_pick_channel(ses);
-
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
@@ -435,15 +469,24 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
 	num_rqst++;
 
 	if (cfile) {
+		if (retries)
+			for (i = 1; i < num_rqst - 2; i++)
+				smb2_set_replay(server, &rqst[i]);
+
 		rc = compound_send_recv(xid, ses, server,
 					flags, num_rqst - 2,
 					&rqst[1], &resp_buftype[1],
 					&rsp_iov[1]);
-	} else
+	} else {
+		if (retries)
+			for (i = 0; i < num_rqst; i++)
+				smb2_set_replay(server, &rqst[i]);
+
 		rc = compound_send_recv(xid, ses, server,
 					flags, num_rqst,
 					rqst, resp_buftype,
 					rsp_iov);
+	}
 
 finished:
 	num_rqst = 0;
@@ -494,21 +537,9 @@ finished:
 					&rsp_iov[i + 1], sizeof(idata->posix_fi) /* add SIDs */,
 					(char *)&idata->posix_fi);
 			}
-			if (rc == 0) {
-				unsigned int length = le32_to_cpu(qi_rsp->OutputBufferLength);
-
-				if (length > sizeof(idata->posix_fi)) {
-					char *base = (char *)rsp_iov[i + 1].iov_base +
-						le16_to_cpu(qi_rsp->OutputBufferOffset) +
-						sizeof(idata->posix_fi);
-					*extbuflen = length - sizeof(idata->posix_fi);
-					*extbuf = kmemdup(base, *extbuflen, GFP_KERNEL);
-					if (!*extbuf)
-						rc = -ENOMEM;
-				} else {
-					rc = -EINVAL;
-				}
-			}
+			if (rc == 0)
+				rc = parse_posix_sids(idata, &rsp_iov[i + 1]);
+
 			SMB2_query_info_free(&rqst[num_rqst++]);
 			if (rc)
 				trace_smb3_posix_query_info_compound_err(xid,  ses->Suid,
@@ -604,9 +635,6 @@ finished:
 	}
 	SMB2_close_free(&rqst[num_rqst]);
 
-	if (cfile)
-		cifsFileInfo_put(cfile);
-
 	num_cmds += 2;
 	if (out_iov && out_buftype) {
 		memcpy(out_iov, rsp_iov, num_cmds * sizeof(*out_iov));
@@ -616,7 +644,16 @@ finished:
 		for (i = 0; i < num_cmds; i++)
 			free_rsp_buf(resp_buftype[i], rsp_iov[i].iov_base);
 	}
+	num_cmds -= 2; /* correct num_cmds as there could be a retry */
 	kfree(vars);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
+	if (cfile)
+		cifsFileInfo_put(cfile);
+
 	return rc;
 }
 
@@ -662,7 +699,7 @@ int smb2_query_path_info(const unsigned int xid,
 	struct smb2_hdr *hdr;
 	struct kvec in_iov[2], out_iov[3] = {};
 	int out_buftype[3] = {};
-	int cmds[2] = { SMB2_OP_QUERY_INFO,  };
+	int cmds[2];
 	bool islink;
 	int i, num_cmds;
 	int rc, rc2;
@@ -670,20 +707,36 @@ int smb2_query_path_info(const unsigned int xid,
 	data->adjust_tz = false;
 	data->reparse_point = false;
 
-	if (strcmp(full_path, ""))
-		rc = -ENOENT;
-	else
-		rc = open_cached_dir(xid, tcon, full_path, cifs_sb, false, &cfid);
-	/* If it is a root and its handle is cached then use it */
-	if (!rc) {
-		if (cfid->file_all_info_is_valid) {
-			memcpy(&data->fi, &cfid->file_all_info, sizeof(data->fi));
+	/*
+	 * BB TODO: Add support for using cached root handle in SMB3.1.1 POSIX.
+	 * Create SMB2_query_posix_info worker function to do non-compounded
+	 * query when we already have an open file handle for this. For now this
+	 * is fast enough (always using the compounded version).
+	 */
+	if (!tcon->posix_extensions) {
+		if (*full_path) {
+			rc = -ENOENT;
 		} else {
-			rc = SMB2_query_info(xid, tcon, cfid->fid.persistent_fid,
-					     cfid->fid.volatile_fid, &data->fi);
+			rc = open_cached_dir(xid, tcon, full_path,
+					     cifs_sb, false, &cfid);
+		}
+		/* If it is a root and its handle is cached then use it */
+		if (!rc) {
+			if (cfid->file_all_info_is_valid) {
+				memcpy(&data->fi, &cfid->file_all_info,
+				       sizeof(data->fi));
+			} else {
+				rc = SMB2_query_info(xid, tcon,
+						     cfid->fid.persistent_fid,
+						     cfid->fid.volatile_fid,
+						     &data->fi);
+			}
+			close_cached_dir(cfid);
+			return rc;
 		}
-		close_cached_dir(cfid);
-		return rc;
+		cmds[0] = SMB2_OP_QUERY_INFO;
+	} else {
+		cmds[0] = SMB2_OP_POSIX_QUERY_INFO;
 	}
 
 	in_iov[0].iov_base = data;
@@ -693,9 +746,8 @@ int smb2_query_path_info(const unsigned int xid,
 	cifs_get_readable_path(tcon, full_path, &cfile);
 	rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
 			      FILE_READ_ATTRIBUTES, FILE_OPEN,
-			      create_options, ACL_NO_MODE,
-			      in_iov, cmds, 1, cfile,
-			      NULL, NULL, out_iov, out_buftype);
+			      create_options, ACL_NO_MODE, in_iov,
+			      cmds, 1, cfile, out_iov, out_buftype);
 	hdr = out_iov[0].iov_base;
 	/*
 	 * If first iov is unset, then SMB session was dropped or we've got a
@@ -707,6 +759,10 @@ int smb2_query_path_info(const unsigned int xid,
 	switch (rc) {
 	case 0:
 	case -EOPNOTSUPP:
+		/*
+		 * BB TODO: When support for special files added to Samba
+		 * re-verify this path.
+		 */
 		rc = parse_create_response(data, cifs_sb, &out_iov[0]);
 		if (rc || !data->reparse_point)
 			goto out;
@@ -722,8 +778,8 @@ int smb2_query_path_info(const unsigned int xid,
 		cifs_get_readable_path(tcon, full_path, &cfile);
 		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
 				      FILE_READ_ATTRIBUTES, FILE_OPEN,
-				      create_options, ACL_NO_MODE, in_iov, cmds,
-				      num_cmds, cfile, NULL, NULL, NULL, NULL);
+				      create_options, ACL_NO_MODE, in_iov,
+				      cmds, num_cmds, cfile, NULL, NULL);
 		break;
 	case -EREMOTE:
 		break;
@@ -746,101 +802,6 @@ out:
 	return rc;
 }
 
-int smb311_posix_query_path_info(const unsigned int xid,
-				 struct cifs_tcon *tcon,
-				 struct cifs_sb_info *cifs_sb,
-				 const char *full_path,
-				 struct cifs_open_info_data *data,
-				 struct cifs_sid *owner,
-				 struct cifs_sid *group)
-{
-	int rc;
-	__u32 create_options = 0;
-	struct cifsFileInfo *cfile;
-	struct kvec in_iov[2], out_iov[3] = {};
-	int out_buftype[3] = {};
-	__u8 *sidsbuf = NULL;
-	__u8 *sidsbuf_end = NULL;
-	size_t sidsbuflen = 0;
-	size_t owner_len, group_len;
-	int cmds[2] = { SMB2_OP_POSIX_QUERY_INFO,  };
-	int i, num_cmds;
-
-	data->adjust_tz = false;
-	data->reparse_point = false;
-
-	/*
-	 * BB TODO: Add support for using the cached root handle.
-	 * Create SMB2_query_posix_info worker function to do non-compounded query
-	 * when we already have an open file handle for this. For now this is fast enough
-	 * (always using the compounded version).
-	 */
-	in_iov[0].iov_base = data;
-	in_iov[0].iov_len = sizeof(*data);
-	in_iov[1] = in_iov[0];
-
-	cifs_get_readable_path(tcon, full_path, &cfile);
-	rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
-			      FILE_READ_ATTRIBUTES, FILE_OPEN,
-			      create_options, ACL_NO_MODE, in_iov, cmds, 1,
-			      cfile, &sidsbuf, &sidsbuflen, out_iov, out_buftype);
-	/*
-	 * If first iov is unset, then SMB session was dropped or we've got a
-	 * cached open file (@cfile).
-	 */
-	if (!out_iov[0].iov_base || out_buftype[0] == CIFS_NO_BUFFER)
-		goto out;
-
-	switch (rc) {
-	case 0:
-	case -EOPNOTSUPP:
-		/* BB TODO: When support for special files added to Samba re-verify this path */
-		rc = parse_create_response(data, cifs_sb, &out_iov[0]);
-		if (rc || !data->reparse_point)
-			goto out;
-
-		if (data->reparse.tag == IO_REPARSE_TAG_SYMLINK) {
-			/* symlink already parsed in create response */
-			num_cmds = 1;
-		} else {
-			cmds[1] = SMB2_OP_GET_REPARSE;
-			num_cmds = 2;
-		}
-		create_options |= OPEN_REPARSE_POINT;
-		cifs_get_readable_path(tcon, full_path, &cfile);
-		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
-				      FILE_READ_ATTRIBUTES, FILE_OPEN,
-				      create_options, ACL_NO_MODE, in_iov, cmds,
-				      num_cmds, cfile, &sidsbuf, &sidsbuflen, NULL, NULL);
-		break;
-	}
-
-out:
-	if (rc == 0) {
-		sidsbuf_end = sidsbuf + sidsbuflen;
-
-		owner_len = posix_info_sid_size(sidsbuf, sidsbuf_end);
-		if (owner_len == -1) {
-			rc = -EINVAL;
-			goto out;
-		}
-		memcpy(owner, sidsbuf, owner_len);
-
-		group_len = posix_info_sid_size(
-			sidsbuf + owner_len, sidsbuf_end);
-		if (group_len == -1) {
-			rc = -EINVAL;
-			goto out;
-		}
-		memcpy(group, sidsbuf + owner_len, group_len);
-	}
-
-	kfree(sidsbuf);
-	for (i = 0; i < ARRAY_SIZE(out_buftype); i++)
-		free_rsp_buf(out_buftype[i], out_iov[i].iov_base);
-	return rc;
-}
-
 int
 smb2_mkdir(const unsigned int xid, struct inode *parent_inode, umode_t mode,
 	   struct cifs_tcon *tcon, const char *name,
@@ -848,9 +809,9 @@ smb2_mkdir(const unsigned int xid, struct inode *parent_inode, umode_t mode,
 {
 	return smb2_compound_op(xid, tcon, cifs_sb, name,
 				FILE_WRITE_ATTRIBUTES, FILE_CREATE,
-				CREATE_NOT_FILE, mode, NULL,
-				&(int){SMB2_OP_MKDIR}, 1,
-				NULL, NULL, NULL, NULL, NULL);
+				CREATE_NOT_FILE, mode,
+				NULL, &(int){SMB2_OP_MKDIR}, 1,
+				NULL, NULL, NULL);
 }
 
 void
@@ -875,7 +836,7 @@ smb2_mkdir_setinfo(struct inode *inode, const char *name,
 				 FILE_WRITE_ATTRIBUTES, FILE_CREATE,
 				 CREATE_NOT_FILE, ACL_NO_MODE, &in_iov,
 				 &(int){SMB2_OP_SET_INFO}, 1,
-				 cfile, NULL, NULL, NULL, NULL);
+				 cfile, NULL, NULL);
 	if (tmprc == 0)
 		cifs_i->cifsAttrs = dosattrs;
 }
@@ -887,8 +848,9 @@ smb2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, const char *name,
 	drop_cached_dir_by_name(xid, tcon, name, cifs_sb);
 	return smb2_compound_op(xid, tcon, cifs_sb, name,
 				DELETE, FILE_OPEN, CREATE_NOT_FILE,
-				ACL_NO_MODE, NULL, &(int){SMB2_OP_RMDIR}, 1,
-				NULL, NULL, NULL, NULL, NULL);
+				ACL_NO_MODE, NULL,
+				&(int){SMB2_OP_RMDIR}, 1,
+				NULL, NULL, NULL);
 }
 
 int
@@ -897,8 +859,9 @@ smb2_unlink(const unsigned int xid, struct cifs_tcon *tcon, const char *name,
 {
 	return smb2_compound_op(xid, tcon, cifs_sb, name, DELETE, FILE_OPEN,
 				CREATE_DELETE_ON_CLOSE | OPEN_REPARSE_POINT,
-				ACL_NO_MODE, NULL, &(int){SMB2_OP_DELETE}, 1,
-				NULL, NULL, NULL, NULL, NULL);
+				ACL_NO_MODE, NULL,
+				&(int){SMB2_OP_DELETE}, 1,
+				NULL, NULL, NULL);
 }
 
 static int smb2_set_path_attr(const unsigned int xid, struct cifs_tcon *tcon,
@@ -919,8 +882,8 @@ static int smb2_set_path_attr(const unsigned int xid, struct cifs_tcon *tcon,
 	in_iov.iov_base = smb2_to_name;
 	in_iov.iov_len = 2 * UniStrnlen((wchar_t *)smb2_to_name, PATH_MAX);
 	rc = smb2_compound_op(xid, tcon, cifs_sb, from_name, access,
-			      FILE_OPEN, create_options, ACL_NO_MODE, &in_iov,
-			      &command, 1, cfile, NULL, NULL, NULL, NULL);
+			      FILE_OPEN, create_options, ACL_NO_MODE,
+			      &in_iov, &command, 1, cfile, NULL, NULL);
 smb2_rename_path:
 	kfree(smb2_to_name);
 	return rc;
@@ -971,7 +934,7 @@ smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon,
 				FILE_WRITE_DATA, FILE_OPEN,
 				0, ACL_NO_MODE, &in_iov,
 				&(int){SMB2_OP_SET_EOF}, 1,
-				cfile, NULL, NULL, NULL, NULL);
+				cfile, NULL, NULL);
 }
 
 int
@@ -999,8 +962,8 @@ smb2_set_file_info(struct inode *inode, const char *full_path,
 	rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
 			      FILE_WRITE_ATTRIBUTES, FILE_OPEN,
 			      0, ACL_NO_MODE, &in_iov,
-			      &(int){SMB2_OP_SET_INFO}, 1, cfile,
-			      NULL, NULL, NULL, NULL);
+			      &(int){SMB2_OP_SET_INFO}, 1,
+			      cfile, NULL, NULL);
 	cifs_put_tlink(tlink);
 	return rc;
 }
@@ -1035,7 +998,7 @@ struct inode *smb2_get_reparse_inode(struct cifs_open_info_data *data,
 		cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
 		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
 				      da, cd, co, ACL_NO_MODE, in_iov,
-				      cmds, 2, cfile, NULL, NULL, NULL, NULL);
+				      cmds, 2, cfile, NULL, NULL);
 		if (!rc) {
 			rc = smb311_posix_get_inode_info(&new, full_path,
 							 data, sb, xid);
@@ -1045,7 +1008,7 @@ struct inode *smb2_get_reparse_inode(struct cifs_open_info_data *data,
 		cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
 		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
 				      da, cd, co, ACL_NO_MODE, in_iov,
-				      cmds, 2, cfile, NULL, NULL, NULL, NULL);
+				      cmds, 2, cfile, NULL, NULL);
 		if (!rc) {
 			rc = cifs_get_inode_info(&new, full_path,
 						 data, sb, xid, NULL);
@@ -1072,8 +1035,8 @@ int smb2_query_reparse_point(const unsigned int xid,
 	rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
 			      FILE_READ_ATTRIBUTES, FILE_OPEN,
 			      OPEN_REPARSE_POINT, ACL_NO_MODE, &in_iov,
-			      &(int){SMB2_OP_GET_REPARSE}, 1, cfile,
-			      NULL, NULL, NULL, NULL);
+			      &(int){SMB2_OP_GET_REPARSE}, 1,
+			      cfile, NULL, NULL);
 	if (rc)
 		goto out;
 
diff --git a/fs/smb/client/smb2maperror.c b/fs/smb/client/smb2maperror.c
index 1a90dd78b238..ac1895358908 100644
--- a/fs/smb/client/smb2maperror.c
+++ b/fs/smb/client/smb2maperror.c
@@ -1210,6 +1210,8 @@ static const struct status_to_posix_error smb2_error_map_table[] = {
 	{STATUS_INVALID_TASK_INDEX, -EIO, "STATUS_INVALID_TASK_INDEX"},
 	{STATUS_THREAD_ALREADY_IN_TASK, -EIO, "STATUS_THREAD_ALREADY_IN_TASK"},
 	{STATUS_CALLBACK_BYPASS, -EIO, "STATUS_CALLBACK_BYPASS"},
+	{STATUS_SERVER_UNAVAILABLE, -EAGAIN, "STATUS_SERVER_UNAVAILABLE"},
+	{STATUS_FILE_NOT_AVAILABLE, -EAGAIN, "STATUS_FILE_NOT_AVAILABLE"},
 	{STATUS_PORT_CLOSED, -EIO, "STATUS_PORT_CLOSED"},
 	{STATUS_MESSAGE_LOST, -EIO, "STATUS_MESSAGE_LOST"},
 	{STATUS_INVALID_MESSAGE, -EIO, "STATUS_INVALID_MESSAGE"},
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 01a5bd7e6a30..4695433fcf39 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -614,11 +614,12 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
 				 "multichannel not available\n"
 				 "Empty network interface list returned by server %s\n",
 				 ses->server->hostname);
-		rc = -EINVAL;
+		rc = -EOPNOTSUPP;
+		ses->iface_last_update = jiffies;
 		goto out;
 	}
 
-	while (bytes_left >= sizeof(*p)) {
+	while (bytes_left >= (ssize_t)sizeof(*p)) {
 		memset(&tmp_iface, 0, sizeof(tmp_iface));
 		tmp_iface.speed = le64_to_cpu(p->LinkSpeed);
 		tmp_iface.rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE) ? 1 : 0;
@@ -712,7 +713,6 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
 
 		ses->iface_count++;
 		spin_unlock(&ses->iface_lock);
-		ses->iface_last_update = jiffies;
 next_iface:
 		nb_iface++;
 		next = le32_to_cpu(p->Next);
@@ -734,11 +734,7 @@ next_iface:
 	if ((bytes_left > 8) || p->Next)
 		cifs_dbg(VFS, "%s: incomplete interface info\n", __func__);
 
-
-	if (!ses->iface_count) {
-		rc = -EINVAL;
-		goto out;
-	}
+	ses->iface_last_update = jiffies;
 
 out:
 	/*
@@ -1112,7 +1108,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
 {
 	struct smb2_compound_vars *vars;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	struct smb_rqst *rqst;
 	struct kvec *rsp_iov;
 	__le16 *utf16_path = NULL;
@@ -1128,6 +1124,13 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
 	struct smb2_file_full_ea_info *ea = NULL;
 	struct smb2_query_info_rsp *rsp;
 	int rc, used_len = 0;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = CIFS_CP_CREATE_CLOSE_OP;
+	oplock = SMB2_OPLOCK_LEVEL_NONE;
+	server = cifs_pick_channel(ses);
 
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
@@ -1201,6 +1204,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
 		.disposition = FILE_OPEN,
 		.create_options = cifs_create_options(cifs_sb, 0),
 		.fid = &fid,
+		.replay = !!(retries),
 	};
 
 	rc = SMB2_open_init(tcon, server,
@@ -1248,6 +1252,12 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
 		goto sea_exit;
 	smb2_set_related(&rqst[2]);
 
+	if (retries) {
+		smb2_set_replay(server, &rqst[0]);
+		smb2_set_replay(server, &rqst[1]);
+		smb2_set_replay(server, &rqst[2]);
+	}
+
 	rc = compound_send_recv(xid, ses, server,
 				flags, 3, rqst,
 				resp_buftype, rsp_iov);
@@ -1264,6 +1274,11 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
 	kfree(vars);
 out_free_path:
 	kfree(utf16_path);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 #endif
@@ -1488,7 +1503,7 @@ smb2_ioctl_query_info(const unsigned int xid,
 	struct smb_rqst *rqst;
 	struct kvec *rsp_iov;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	char __user *arg = (char __user *)p;
 	struct smb_query_info qi;
 	struct smb_query_info __user *pqi;
@@ -1505,6 +1520,13 @@ smb2_ioctl_query_info(const unsigned int xid,
 	void *data[2];
 	int create_options = is_dir ? CREATE_NOT_FILE : CREATE_NOT_DIR;
 	void (*free_req1_func)(struct smb_rqst *r);
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = CIFS_CP_CREATE_CLOSE_OP;
+	oplock = SMB2_OPLOCK_LEVEL_NONE;
+	server = cifs_pick_channel(ses);
 
 	vars = kzalloc(sizeof(*vars), GFP_ATOMIC);
 	if (vars == NULL)
@@ -1548,6 +1570,7 @@ smb2_ioctl_query_info(const unsigned int xid,
 		.disposition = FILE_OPEN,
 		.create_options = cifs_create_options(cifs_sb, create_options),
 		.fid = &fid,
+		.replay = !!(retries),
 	};
 
 	if (qi.flags & PASSTHRU_FSCTL) {
@@ -1645,6 +1668,12 @@ smb2_ioctl_query_info(const unsigned int xid,
 		goto free_req_1;
 	smb2_set_related(&rqst[2]);
 
+	if (retries) {
+		smb2_set_replay(server, &rqst[0]);
+		smb2_set_replay(server, &rqst[1]);
+		smb2_set_replay(server, &rqst[2]);
+	}
+
 	rc = compound_send_recv(xid, ses, server,
 				flags, 3, rqst,
 				resp_buftype, rsp_iov);
@@ -1705,6 +1734,11 @@ free_output_buffer:
 	kfree(buffer);
 free_vars:
 	kfree(vars);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -2231,8 +2265,14 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon,
 	struct cifs_open_parms oparms;
 	struct smb2_query_directory_rsp *qd_rsp = NULL;
 	struct smb2_create_rsp *op_rsp = NULL;
-	struct TCP_Server_Info *server = cifs_pick_channel(tcon->ses);
-	int retry_count = 0;
+	struct TCP_Server_Info *server;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	oplock = SMB2_OPLOCK_LEVEL_NONE;
+	server = cifs_pick_channel(tcon->ses);
 
 	utf16_path = cifs_convert_path_to_utf16(path, cifs_sb);
 	if (!utf16_path)
@@ -2257,6 +2297,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon,
 		.disposition = FILE_OPEN,
 		.create_options = cifs_create_options(cifs_sb, 0),
 		.fid = fid,
+		.replay = !!(retries),
 	};
 
 	rc = SMB2_open_init(tcon, server,
@@ -2282,14 +2323,15 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon,
 
 	smb2_set_related(&rqst[1]);
 
-again:
+	if (retries) {
+		smb2_set_replay(server, &rqst[0]);
+		smb2_set_replay(server, &rqst[1]);
+	}
+
 	rc = compound_send_recv(xid, tcon->ses, server,
 				flags, 2, rqst,
 				resp_buftype, rsp_iov);
 
-	if (rc == -EAGAIN && retry_count++ < 10)
-		goto again;
-
 	/* If the open failed there is nothing to do */
 	op_rsp = (struct smb2_create_rsp *)rsp_iov[0].iov_base;
 	if (op_rsp == NULL || op_rsp->hdr.Status != STATUS_SUCCESS) {
@@ -2337,6 +2379,11 @@ again:
 	SMB2_query_directory_free(&rqst[1]);
 	free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base);
 	free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -2462,6 +2509,22 @@ smb2_oplock_response(struct cifs_tcon *tcon, __u64 persistent_fid,
 }
 
 void
+smb2_set_replay(struct TCP_Server_Info *server, struct smb_rqst *rqst)
+{
+	struct smb2_hdr *shdr;
+
+	if (server->dialect < SMB30_PROT_ID)
+		return;
+
+	shdr = (struct smb2_hdr *)(rqst->rq_iov[0].iov_base);
+	if (shdr == NULL) {
+		cifs_dbg(FYI, "shdr NULL in smb2_set_related\n");
+		return;
+	}
+	shdr->Flags |= SMB2_FLAGS_REPLAY_OPERATION;
+}
+
+void
 smb2_set_related(struct smb_rqst *rqst)
 {
 	struct smb2_hdr *shdr;
@@ -2534,6 +2597,27 @@ smb2_set_next_command(struct cifs_tcon *tcon, struct smb_rqst *rqst)
 }
 
 /*
+ * helper function for exponential backoff and check if replayable
+ */
+bool smb2_should_replay(struct cifs_tcon *tcon,
+				int *pretries,
+				int *pcur_sleep)
+{
+	if (!pretries || !pcur_sleep)
+		return false;
+
+	if (tcon->retry || (*pretries)++ < tcon->ses->server->retrans) {
+		msleep(*pcur_sleep);
+		(*pcur_sleep) = ((*pcur_sleep) << 1);
+		if ((*pcur_sleep) > CIFS_MAX_SLEEP)
+			(*pcur_sleep) = CIFS_MAX_SLEEP;
+		return true;
+	}
+
+	return false;
+}
+
+/*
  * Passes the query info response back to the caller on success.
  * Caller need to free this with free_rsp_buf().
  */
@@ -2546,7 +2630,7 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon,
 {
 	struct smb2_compound_vars *vars;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	int flags = CIFS_CP_CREATE_CLOSE_OP;
 	struct smb_rqst *rqst;
 	int resp_buftype[3];
@@ -2557,6 +2641,13 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc;
 	__le16 *utf16_path;
 	struct cached_fid *cfid = NULL;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = CIFS_CP_CREATE_CLOSE_OP;
+	oplock = SMB2_OPLOCK_LEVEL_NONE;
+	server = cifs_pick_channel(ses);
 
 	if (!path)
 		path = "";
@@ -2593,6 +2684,7 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon,
 		.disposition = FILE_OPEN,
 		.create_options = cifs_create_options(cifs_sb, 0),
 		.fid = &fid,
+		.replay = !!(retries),
 	};
 
 	rc = SMB2_open_init(tcon, server,
@@ -2637,6 +2729,14 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon,
 		goto qic_exit;
 	smb2_set_related(&rqst[2]);
 
+	if (retries) {
+		if (!cfid) {
+			smb2_set_replay(server, &rqst[0]);
+			smb2_set_replay(server, &rqst[2]);
+		}
+		smb2_set_replay(server, &rqst[1]);
+	}
+
 	if (cfid) {
 		rc = compound_send_recv(xid, ses, server,
 					flags, 1, &rqst[1],
@@ -2669,6 +2769,11 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon,
 	kfree(vars);
 out_free_path:
 	kfree(utf16_path);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -3217,6 +3322,9 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 				  cfile->fid.volatile_fid, cfile->pid, new_size);
 		if (rc >= 0) {
 			truncate_setsize(inode, new_size);
+			netfs_resize_file(&cifsi->netfs, new_size, true);
+			if (offset < cifsi->netfs.zero_point)
+				cifsi->netfs.zero_point = offset;
 			fscache_resize_cookie(cifs_inode_cookie(inode), new_size);
 		}
 	}
@@ -3440,7 +3548,7 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
 		rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
 				  cfile->fid.volatile_fid, cfile->pid, new_eof);
 		if (rc == 0) {
-			cifsi->server_eof = new_eof;
+			netfs_resize_file(&cifsi->netfs, new_eof, true);
 			cifs_setsize(inode, new_eof);
 			cifs_truncate_page(inode->i_mapping, inode->i_size);
 			truncate_setsize(inode, new_eof);
@@ -3532,8 +3640,9 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon,
 	int rc;
 	unsigned int xid;
 	struct inode *inode = file_inode(file);
-	struct cifsFileInfo *cfile = file->private_data;
 	struct cifsInodeInfo *cifsi = CIFS_I(inode);
+	struct cifsFileInfo *cfile = file->private_data;
+	struct netfs_inode *ictx = &cifsi->netfs;
 	loff_t old_eof, new_eof;
 
 	xid = get_xid();
@@ -3553,6 +3662,7 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon,
 		goto out_2;
 
 	truncate_pagecache_range(inode, off, old_eof);
+	ictx->zero_point = old_eof;
 
 	rc = smb2_copychunk_range(xid, cfile, cfile, off + len,
 				  old_eof - off - len, off);
@@ -3567,9 +3677,10 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon,
 
 	rc = 0;
 
-	cifsi->server_eof = i_size_read(inode) - len;
-	truncate_setsize(inode, cifsi->server_eof);
-	fscache_resize_cookie(cifs_inode_cookie(inode), cifsi->server_eof);
+	truncate_setsize(inode, new_eof);
+	netfs_resize_file(&cifsi->netfs, new_eof, true);
+	ictx->zero_point = new_eof;
+	fscache_resize_cookie(cifs_inode_cookie(inode), new_eof);
 out_2:
 	filemap_invalidate_unlock(inode->i_mapping);
  out:
@@ -3585,6 +3696,7 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon,
 	unsigned int xid;
 	struct cifsFileInfo *cfile = file->private_data;
 	struct inode *inode = file_inode(file);
+	struct cifsInodeInfo *cifsi = CIFS_I(inode);
 	__u64 count, old_eof, new_eof;
 
 	xid = get_xid();
@@ -3612,6 +3724,7 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon,
 		goto out_2;
 
 	truncate_setsize(inode, new_eof);
+	netfs_resize_file(&cifsi->netfs, i_size_read(inode), true);
 	fscache_resize_cookie(cifs_inode_cookie(inode), i_size_read(inode));
 
 	rc = smb2_copychunk_range(xid, cfile, cfile, off, count, off + len);
@@ -5104,7 +5217,7 @@ static int smb2_create_reparse_symlink(const unsigned int xid,
 	struct inode *new;
 	struct kvec iov;
 	__le16 *path;
-	char *sym;
+	char *sym, sep = CIFS_DIR_SEP(cifs_sb);
 	u16 len, plen;
 	int rc = 0;
 
@@ -5118,7 +5231,8 @@ static int smb2_create_reparse_symlink(const unsigned int xid,
 		.symlink_target = sym,
 	};
 
-	path = cifs_convert_path_to_utf16(symname, cifs_sb);
+	convert_delimiter(sym, sep);
+	path = cifs_convert_path_to_utf16(sym, cifs_sb);
 	if (!path) {
 		rc = -ENOMEM;
 		goto out;
@@ -5141,7 +5255,10 @@ static int smb2_create_reparse_symlink(const unsigned int xid,
 	buf->PrintNameLength = cpu_to_le16(plen);
 	memcpy(buf->PathBuffer, path, plen);
 	buf->Flags = cpu_to_le32(*symname != '/' ? SYMLINK_FLAG_RELATIVE : 0);
+	if (*sym != sep)
+		buf->Flags = cpu_to_le32(SYMLINK_FLAG_RELATIVE);
 
+	convert_delimiter(sym, '/');
 	iov.iov_base = buf;
 	iov.iov_len = len;
 	new = smb2_get_reparse_inode(&data, inode->i_sb, xid,
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index bd25c34dc398..608ee05491e2 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -156,6 +156,56 @@ out:
 	return;
 }
 
+/* helper function for code reuse */
+static int
+cifs_chan_skip_or_disable(struct cifs_ses *ses,
+			  struct TCP_Server_Info *server,
+			  bool from_reconnect)
+{
+	struct TCP_Server_Info *pserver;
+	unsigned int chan_index;
+
+	if (SERVER_IS_CHAN(server)) {
+		cifs_dbg(VFS,
+			"server %s does not support multichannel anymore. Skip secondary channel\n",
+			 ses->server->hostname);
+
+		spin_lock(&ses->chan_lock);
+		chan_index = cifs_ses_get_chan_index(ses, server);
+		if (chan_index == CIFS_INVAL_CHAN_INDEX) {
+			spin_unlock(&ses->chan_lock);
+			goto skip_terminate;
+		}
+
+		ses->chans[chan_index].server = NULL;
+		server->terminate = true;
+		spin_unlock(&ses->chan_lock);
+
+		/*
+		 * the above reference of server by channel
+		 * needs to be dropped without holding chan_lock
+		 * as cifs_put_tcp_session takes a higher lock
+		 * i.e. cifs_tcp_ses_lock
+		 */
+		cifs_put_tcp_session(server, from_reconnect);
+
+		cifs_signal_cifsd_for_reconnect(server, false);
+
+		/* mark primary server as needing reconnect */
+		pserver = server->primary_server;
+		cifs_signal_cifsd_for_reconnect(pserver, false);
+skip_terminate:
+		return -EHOSTDOWN;
+	}
+
+	cifs_server_dbg(VFS,
+		"server does not support multichannel anymore. Disable all other channels\n");
+	cifs_disable_secondary_channels(ses);
+
+
+	return 0;
+}
+
 static int
 smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon,
 	       struct TCP_Server_Info *server, bool from_reconnect)
@@ -164,8 +214,6 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon,
 	struct nls_table *nls_codepage = NULL;
 	struct cifs_ses *ses;
 	int xid;
-	struct TCP_Server_Info *pserver;
-	unsigned int chan_index;
 
 	/*
 	 * SMB2s NegProt, SessSetup, Logoff do not have tcon yet so
@@ -310,44 +358,11 @@ again:
 		 */
 		if (ses->chan_count > 1 &&
 		    !(server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) {
-			if (SERVER_IS_CHAN(server)) {
-				cifs_dbg(VFS, "server %s does not support " \
-					 "multichannel anymore. skipping secondary channel\n",
-					 ses->server->hostname);
-
-				spin_lock(&ses->chan_lock);
-				chan_index = cifs_ses_get_chan_index(ses, server);
-				if (chan_index == CIFS_INVAL_CHAN_INDEX) {
-					spin_unlock(&ses->chan_lock);
-					goto skip_terminate;
-				}
-
-				ses->chans[chan_index].server = NULL;
-				spin_unlock(&ses->chan_lock);
-
-				/*
-				 * the above reference of server by channel
-				 * needs to be dropped without holding chan_lock
-				 * as cifs_put_tcp_session takes a higher lock
-				 * i.e. cifs_tcp_ses_lock
-				 */
-				cifs_put_tcp_session(server, from_reconnect);
-
-				server->terminate = true;
-				cifs_signal_cifsd_for_reconnect(server, false);
-
-				/* mark primary server as needing reconnect */
-				pserver = server->primary_server;
-				cifs_signal_cifsd_for_reconnect(pserver, false);
-
-skip_terminate:
+			rc = cifs_chan_skip_or_disable(ses, server,
+						       from_reconnect);
+			if (rc) {
 				mutex_unlock(&ses->session_mutex);
-				rc = -EHOSTDOWN;
 				goto out;
-			} else {
-				cifs_server_dbg(VFS, "does not support " \
-					 "multichannel anymore. disabling all other channels\n");
-				cifs_disable_secondary_channels(ses);
 			}
 		}
 
@@ -384,6 +399,15 @@ skip_sess_setup:
 		goto out;
 	}
 
+	spin_lock(&ses->ses_lock);
+	if (ses->flags & CIFS_SES_FLAG_SCALE_CHANNELS) {
+		spin_unlock(&ses->ses_lock);
+		mutex_unlock(&ses->session_mutex);
+		goto skip_add_channels;
+	}
+	ses->flags |= CIFS_SES_FLAG_SCALE_CHANNELS;
+	spin_unlock(&ses->ses_lock);
+
 	if (!rc &&
 	    (server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) {
 		mutex_unlock(&ses->session_mutex);
@@ -395,14 +419,29 @@ skip_sess_setup:
 		rc = SMB3_request_interfaces(xid, tcon, false);
 		free_xid(xid);
 
-		if (rc)
+		if (rc == -EOPNOTSUPP && ses->chan_count > 1) {
+			/*
+			 * some servers like Azure SMB server do not advertise
+			 * that multichannel has been disabled with server
+			 * capabilities, rather return STATUS_NOT_IMPLEMENTED.
+			 * treat this as server not supporting multichannel
+			 */
+
+			rc = cifs_chan_skip_or_disable(ses, server,
+						       from_reconnect);
+			goto skip_add_channels;
+		} else if (rc)
 			cifs_dbg(FYI, "%s: failed to query server interfaces: %d\n",
 				 __func__, rc);
 
 		if (ses->chan_max > ses->chan_count &&
+		    ses->iface_count &&
 		    !SERVER_IS_CHAN(server)) {
-			if (ses->chan_count == 1)
+			if (ses->chan_count == 1) {
 				cifs_server_dbg(VFS, "supports multichannel now\n");
+				queue_delayed_work(cifsiod_wq, &tcon->query_interfaces,
+						 (SMB_INTERFACE_POLL_INTERVAL * HZ));
+			}
 
 			cifs_try_adding_channels(ses);
 		}
@@ -410,6 +449,11 @@ skip_sess_setup:
 		mutex_unlock(&ses->session_mutex);
 	}
 
+skip_add_channels:
+	spin_lock(&ses->ses_lock);
+	ses->flags &= ~CIFS_SES_FLAG_SCALE_CHANNELS;
+	spin_unlock(&ses->ses_lock);
+
 	if (smb2_command != SMB2_INTERNAL_CMD)
 		mod_delayed_work(cifsiod_wq, &server->reconnect, 0);
 
@@ -1958,10 +2002,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	__le16 *unc_path = NULL;
 	int flags = 0;
 	unsigned int total_len;
-	struct TCP_Server_Info *server;
-
-	/* always use master channel */
-	server = ses->server;
+	struct TCP_Server_Info *server = cifs_pick_channel(ses);
 
 	cifs_dbg(FYI, "TCON\n");
 
@@ -2094,6 +2135,7 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon)
 	struct smb2_tree_disconnect_req *req; /* response is trivial */
 	int rc = 0;
 	struct cifs_ses *ses = tcon->ses;
+	struct TCP_Server_Info *server = cifs_pick_channel(ses);
 	int flags = 0;
 	unsigned int total_len;
 	struct kvec iov[1];
@@ -2116,7 +2158,7 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon)
 
 	invalidate_all_cached_dirs(tcon);
 
-	rc = smb2_plain_req_init(SMB2_TREE_DISCONNECT, tcon, ses->server,
+	rc = smb2_plain_req_init(SMB2_TREE_DISCONNECT, tcon, server,
 				 (void **) &req,
 				 &total_len);
 	if (rc)
@@ -2134,7 +2176,7 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon)
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = 1;
 
-	rc = cifs_send_recv(xid, ses, ses->server,
+	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buf_type, flags, &rsp_iov);
 	cifs_small_buf_release(req);
 	if (rc) {
@@ -2279,7 +2321,7 @@ int smb2_parse_contexts(struct TCP_Server_Info *server,
 
 		noff = le16_to_cpu(cc->NameOffset);
 		nlen = le16_to_cpu(cc->NameLength);
-		if (noff + nlen >= doff)
+		if (noff + nlen > doff)
 			return -EINVAL;
 
 		name = (char *)cc + noff;
@@ -2362,8 +2404,13 @@ create_durable_v2_buf(struct cifs_open_parms *oparms)
 	 */
 	buf->dcontext.Timeout = cpu_to_le32(oparms->tcon->handle_timeout);
 	buf->dcontext.Flags = cpu_to_le32(SMB2_DHANDLE_FLAG_PERSISTENT);
-	generate_random_uuid(buf->dcontext.CreateGuid);
-	memcpy(pfid->create_guid, buf->dcontext.CreateGuid, 16);
+
+	/* for replay, we should not overwrite the existing create guid */
+	if (!oparms->replay) {
+		generate_random_uuid(buf->dcontext.CreateGuid);
+		memcpy(pfid->create_guid, buf->dcontext.CreateGuid, 16);
+	} else
+		memcpy(buf->dcontext.CreateGuid, pfid->create_guid, 16);
 
 	/* SMB2_CREATE_DURABLE_HANDLE_REQUEST is "DH2Q" */
 	buf->Name[0] = 'D';
@@ -2736,7 +2783,14 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
 	int flags = 0;
 	unsigned int total_len;
 	__le16 *utf16_path = NULL;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	n_iov = 2;
+	server = cifs_pick_channel(ses);
 
 	cifs_dbg(FYI, "mkdir\n");
 
@@ -2840,6 +2894,10 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
 	/* no need to inc num_remote_opens because we close it just below */
 	trace_smb3_posix_mkdir_enter(xid, tcon->tid, ses->Suid, full_path, CREATE_NOT_FILE,
 				    FILE_WRITE_ATTRIBUTES);
+
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	/* resource #4: response buffer */
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
@@ -2877,6 +2935,11 @@ err_free_req:
 	cifs_small_buf_release(req);
 err_free_path:
 	kfree(utf16_path);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -3072,12 +3135,19 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	struct smb2_create_rsp *rsp = NULL;
 	struct cifs_tcon *tcon = oparms->tcon;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	struct kvec iov[SMB2_CREATE_IOV_SIZE];
 	struct kvec rsp_iov = {NULL, 0};
 	int resp_buftype = CIFS_NO_BUFFER;
 	int rc = 0;
 	int flags = 0;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	server = cifs_pick_channel(ses);
+	oparms->replay = !!(retries);
 
 	cifs_dbg(FYI, "create/open\n");
 	if (!ses || !server)
@@ -3099,6 +3169,9 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	trace_smb3_open_enter(xid, tcon->tid, tcon->ses->Suid, oparms->path,
 		oparms->create_options, oparms->desired_access);
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags,
 			    &rsp_iov);
@@ -3152,6 +3225,11 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 creat_exit:
 	SMB2_open_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -3276,15 +3354,7 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	int resp_buftype = CIFS_NO_BUFFER;
 	int rc = 0;
 	int flags = 0;
-
-	cifs_dbg(FYI, "SMB2 IOCTL\n");
-
-	if (out_data != NULL)
-		*out_data = NULL;
-
-	/* zero out returned data len, in case of error */
-	if (plen)
-		*plen = 0;
+	int retries = 0, cur_sleep = 1;
 
 	if (!tcon)
 		return -EIO;
@@ -3293,10 +3363,23 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	if (!ses)
 		return -EIO;
 
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
 	server = cifs_pick_channel(ses);
+
 	if (!server)
 		return -EIO;
 
+	cifs_dbg(FYI, "SMB2 IOCTL\n");
+
+	if (out_data != NULL)
+		*out_data = NULL;
+
+	/* zero out returned data len, in case of error */
+	if (plen)
+		*plen = 0;
+
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
@@ -3311,6 +3394,9 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	if (rc)
 		goto ioctl_exit;
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags,
 			    &rsp_iov);
@@ -3380,6 +3466,11 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 ioctl_exit:
 	SMB2_ioctl_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -3451,13 +3542,20 @@ __SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 	struct smb_rqst rqst;
 	struct smb2_close_rsp *rsp = NULL;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	struct kvec iov[1];
 	struct kvec rsp_iov;
 	int resp_buftype = CIFS_NO_BUFFER;
 	int rc = 0;
 	int flags = 0;
 	bool query_attrs = false;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	query_attrs = false;
+	server = cifs_pick_channel(ses);
 
 	cifs_dbg(FYI, "Close\n");
 
@@ -3483,6 +3581,9 @@ __SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		goto close_exit;
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
 	rsp = (struct smb2_close_rsp *)rsp_iov.iov_base;
@@ -3516,6 +3617,11 @@ close_exit:
 			cifs_dbg(VFS, "handle cancelled close fid 0x%llx returned error %d\n",
 				 persistent_fid, tmp_rc);
 	}
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -3646,12 +3752,19 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
 	struct TCP_Server_Info *server;
 	int flags = 0;
 	bool allocated = false;
+	int retries = 0, cur_sleep = 1;
 
 	cifs_dbg(FYI, "Query Info\n");
 
 	if (!ses)
 		return -EIO;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	allocated = false;
 	server = cifs_pick_channel(ses);
+
 	if (!server)
 		return -EIO;
 
@@ -3673,6 +3786,9 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
 	trace_smb3_query_info_enter(xid, persistent_fid, tcon->tid,
 				    ses->Suid, info_class, (__u32)info_type);
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
 	rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base;
@@ -3715,6 +3831,11 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
 qinf_exit:
 	SMB2_query_info_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -3815,7 +3936,7 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon,
 		u32 *plen /* returned data len */)
 {
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	struct smb_rqst rqst;
 	struct smb2_change_notify_rsp *smb_rsp;
 	struct kvec iov[1];
@@ -3823,6 +3944,12 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon,
 	int resp_buftype = CIFS_NO_BUFFER;
 	int flags = 0;
 	int rc = 0;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	server = cifs_pick_channel(ses);
 
 	cifs_dbg(FYI, "change notify\n");
 	if (!ses || !server)
@@ -3847,6 +3974,10 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon,
 
 	trace_smb3_notify_enter(xid, persistent_fid, tcon->tid, ses->Suid,
 				(u8)watch_tree, completion_filter);
+
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
 
@@ -3881,6 +4012,11 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rqst.rq_iov)
 		cifs_small_buf_release(rqst.rq_iov[0].iov_base); /* request */
 	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -3918,7 +4054,7 @@ void smb2_reconnect_server(struct work_struct *work)
 	struct cifs_ses *ses, *ses2;
 	struct cifs_tcon *tcon, *tcon2;
 	struct list_head tmp_list, tmp_ses_list;
-	bool tcon_exist = false, ses_exist = false;
+	bool ses_exist = false;
 	bool tcon_selected = false;
 	int rc;
 	bool resched = false;
@@ -3964,7 +4100,7 @@ void smb2_reconnect_server(struct work_struct *work)
 			if (tcon->need_reconnect || tcon->need_reopen_files) {
 				tcon->tc_count++;
 				list_add_tail(&tcon->rlist, &tmp_list);
-				tcon_selected = tcon_exist = true;
+				tcon_selected = true;
 			}
 		}
 		/*
@@ -3973,7 +4109,7 @@ void smb2_reconnect_server(struct work_struct *work)
 		 */
 		if (ses->tcon_ipc && ses->tcon_ipc->need_reconnect) {
 			list_add_tail(&ses->tcon_ipc->rlist, &tmp_list);
-			tcon_selected = tcon_exist = true;
+			tcon_selected = true;
 			cifs_smb_ses_inc_refcount(ses);
 		}
 		/*
@@ -4123,10 +4259,16 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	struct smb_rqst rqst;
 	struct kvec iov[1];
 	struct kvec rsp_iov = {NULL, 0};
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	int resp_buftype = CIFS_NO_BUFFER;
 	int flags = 0;
 	int rc = 0;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	server = cifs_pick_channel(ses);
 
 	cifs_dbg(FYI, "flush\n");
 	if (!ses || !(ses->server))
@@ -4146,6 +4288,10 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 		goto flush_exit;
 
 	trace_smb3_flush_enter(xid, persistent_fid, tcon->tid, ses->Suid);
+
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
 
@@ -4160,6 +4306,11 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
  flush_exit:
 	SMB2_flush_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -4639,7 +4790,7 @@ smb2_async_writev(struct cifs_writedata *wdata,
 	struct cifs_io_parms *io_parms = NULL;
 	int credit_request;
 
-	if (!wdata->server)
+	if (!wdata->server || wdata->replay)
 		server = wdata->server = cifs_pick_channel(tcon->ses);
 
 	/*
@@ -4724,6 +4875,8 @@ smb2_async_writev(struct cifs_writedata *wdata,
 	rqst.rq_nvec = 1;
 	rqst.rq_iter = wdata->iter;
 	rqst.rq_iter_size = iov_iter_count(&rqst.rq_iter);
+	if (wdata->replay)
+		smb2_set_replay(server, &rqst);
 #ifdef CONFIG_CIFS_SMB_DIRECT
 	if (wdata->mr)
 		iov[0].iov_len += sizeof(struct smbd_buffer_descriptor_v1);
@@ -4797,18 +4950,21 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
 	int flags = 0;
 	unsigned int total_len;
 	struct TCP_Server_Info *server;
+	int retries = 0, cur_sleep = 1;
 
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
 	*nbytes = 0;
-
-	if (n_vec < 1)
-		return rc;
-
 	if (!io_parms->server)
 		io_parms->server = cifs_pick_channel(io_parms->tcon->ses);
 	server = io_parms->server;
 	if (server == NULL)
 		return -ECONNABORTED;
 
+	if (n_vec < 1)
+		return rc;
+
 	rc = smb2_plain_req_init(SMB2_WRITE, io_parms->tcon, server,
 				 (void **) &req, &total_len);
 	if (rc)
@@ -4842,6 +4998,9 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = n_vec + 1;
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, io_parms->tcon->ses, server,
 			    &rqst,
 			    &resp_buftype, flags, &rsp_iov);
@@ -4866,6 +5025,11 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
 
 	cifs_small_buf_release(req);
 	free_rsp_buf(resp_buftype, rsp);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(io_parms->tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -5048,6 +5212,9 @@ int SMB2_query_directory_init(const unsigned int xid,
 	case SMB_FIND_FILE_POSIX_INFO:
 		req->FileInformationClass = SMB_FIND_FILE_POSIX_INFO;
 		break;
+	case SMB_FIND_FILE_FULL_DIRECTORY_INFO:
+		req->FileInformationClass = FILE_FULL_DIRECTORY_INFORMATION;
+		break;
 	default:
 		cifs_tcon_dbg(VFS, "info level %u isn't supported\n",
 			info_level);
@@ -5117,6 +5284,9 @@ smb2_parse_query_directory(struct cifs_tcon *tcon,
 		/* note that posix payload are variable size */
 		info_buf_size = sizeof(struct smb2_posix_info);
 		break;
+	case SMB_FIND_FILE_FULL_DIRECTORY_INFO:
+		info_buf_size = sizeof(FILE_FULL_DIRECTORY_INFO);
+		break;
 	default:
 		cifs_tcon_dbg(VFS, "info level %u isn't supported\n",
 			 srch_inf->info_level);
@@ -5177,8 +5347,14 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 	struct kvec rsp_iov;
 	int rc = 0;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	int flags = 0;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	server = cifs_pick_channel(ses);
 
 	if (!ses || !(ses->server))
 		return -EIO;
@@ -5198,6 +5374,9 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		goto qdir_exit;
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
 	rsp = (struct smb2_query_directory_rsp *)rsp_iov.iov_base;
@@ -5232,6 +5411,11 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 qdir_exit:
 	SMB2_query_directory_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -5298,8 +5482,14 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc = 0;
 	int resp_buftype;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	int flags = 0;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	server = cifs_pick_channel(ses);
 
 	if (!ses || !server)
 		return -EIO;
@@ -5327,6 +5517,8 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
 		return rc;
 	}
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
 
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags,
@@ -5342,6 +5534,11 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 	free_rsp_buf(resp_buftype, rsp);
 	kfree(iov);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -5394,12 +5591,18 @@ SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc;
 	struct smb2_oplock_break *req = NULL;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	int flags = CIFS_OBREAK_OP;
 	unsigned int total_len;
 	struct kvec iov[1];
 	struct kvec rsp_iov;
 	int resp_buf_type;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = CIFS_OBREAK_OP;
+	server = cifs_pick_channel(ses);
 
 	cifs_dbg(FYI, "SMB2_oplock_break\n");
 	rc = smb2_plain_req_init(SMB2_OPLOCK_BREAK, tcon, server,
@@ -5424,15 +5627,21 @@ SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = 1;
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buf_type, flags, &rsp_iov);
 	cifs_small_buf_release(req);
-
 	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_OPLOCK_BREAK_HE);
 		cifs_dbg(FYI, "Send error in Oplock Break = %d\n", rc);
 	}
 
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -5518,9 +5727,15 @@ SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc = 0;
 	int resp_buftype;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	FILE_SYSTEM_POSIX_INFO *info = NULL;
 	int flags = 0;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	server = cifs_pick_channel(ses);
 
 	rc = build_qfs_info_req(&iov, tcon, server,
 				FS_POSIX_INFORMATION,
@@ -5536,6 +5751,9 @@ SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon,
 	rqst.rq_iov = &iov;
 	rqst.rq_nvec = 1;
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
 	free_qfs_info_req(&iov);
@@ -5555,6 +5773,11 @@ SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 posix_qfsinf_exit:
 	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -5569,9 +5792,15 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc = 0;
 	int resp_buftype;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	struct smb2_fs_full_size_info *info = NULL;
 	int flags = 0;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	server = cifs_pick_channel(ses);
 
 	rc = build_qfs_info_req(&iov, tcon, server,
 				FS_FULL_SIZE_INFORMATION,
@@ -5587,6 +5816,9 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 	rqst.rq_iov = &iov;
 	rqst.rq_nvec = 1;
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
 	free_qfs_info_req(&iov);
@@ -5606,6 +5838,11 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 qfsinf_exit:
 	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -5620,9 +5857,15 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc = 0;
 	int resp_buftype, max_len, min_len;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	unsigned int rsp_len, offset;
 	int flags = 0;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	server = cifs_pick_channel(ses);
 
 	if (level == FS_DEVICE_INFORMATION) {
 		max_len = sizeof(FILE_SYSTEM_DEVICE_INFO);
@@ -5654,6 +5897,9 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 	rqst.rq_iov = &iov;
 	rqst.rq_nvec = 1;
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
 	free_qfs_info_req(&iov);
@@ -5691,6 +5937,11 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 
 qfsattr_exit:
 	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -5708,7 +5959,13 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon,
 	unsigned int count;
 	int flags = CIFS_NO_RSP_BUF;
 	unsigned int total_len;
-	struct TCP_Server_Info *server = cifs_pick_channel(tcon->ses);
+	struct TCP_Server_Info *server;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = CIFS_NO_RSP_BUF;
+	server = cifs_pick_channel(tcon->ses);
 
 	cifs_dbg(FYI, "smb2_lockv num lock %d\n", num_lock);
 
@@ -5739,6 +5996,9 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon,
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = 2;
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, tcon->ses, server,
 			    &rqst, &resp_buf_type, flags,
 			    &rsp_iov);
@@ -5750,6 +6010,10 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon,
 				    tcon->ses->Suid, rc);
 	}
 
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h
index 343ada691e76..b3069911e9dd 100644
--- a/fs/smb/client/smb2proto.h
+++ b/fs/smb/client/smb2proto.h
@@ -122,6 +122,11 @@ extern unsigned long smb_rqst_len(struct TCP_Server_Info *server,
 extern void smb2_set_next_command(struct cifs_tcon *tcon,
 				  struct smb_rqst *rqst);
 extern void smb2_set_related(struct smb_rqst *rqst);
+extern void smb2_set_replay(struct TCP_Server_Info *server,
+			    struct smb_rqst *rqst);
+extern bool smb2_should_replay(struct cifs_tcon *tcon,
+			  int *pretries,
+			  int *pcur_sleep);
 
 /*
  * SMB2 Worker functions - most of protocol specific implementation details
@@ -299,9 +304,7 @@ int smb311_posix_query_path_info(const unsigned int xid,
 				 struct cifs_tcon *tcon,
 				 struct cifs_sb_info *cifs_sb,
 				 const char *full_path,
-				 struct cifs_open_info_data *data,
-				 struct cifs_sid *owner,
-				 struct cifs_sid *group);
+				 struct cifs_open_info_data *data);
 int posix_info_parse(const void *beg, const void *end,
 		     struct smb2_posix_info_parsed *out);
 int posix_info_sid_size(const void *beg, const void *end);
diff --git a/fs/smb/client/smb2status.h b/fs/smb/client/smb2status.h
index a9e958166fc5..9c6d79b0bd49 100644
--- a/fs/smb/client/smb2status.h
+++ b/fs/smb/client/smb2status.h
@@ -982,6 +982,8 @@ struct ntstatus {
 #define STATUS_INVALID_TASK_INDEX cpu_to_le32(0xC0000501)
 #define STATUS_THREAD_ALREADY_IN_TASK cpu_to_le32(0xC0000502)
 #define STATUS_CALLBACK_BYPASS cpu_to_le32(0xC0000503)
+#define STATUS_SERVER_UNAVAILABLE cpu_to_le32(0xC0000466)
+#define STATUS_FILE_NOT_AVAILABLE cpu_to_le32(0xC0000467)
 #define STATUS_PORT_CLOSED cpu_to_le32(0xC0000700)
 #define STATUS_MESSAGE_LOST cpu_to_le32(0xC0000701)
 #define STATUS_INVALID_MESSAGE cpu_to_le32(0xC0000702)
diff --git a/fs/smb/client/smbencrypt.c b/fs/smb/client/smbencrypt.c
index f0ce26414f17..1d1ee9f18f37 100644
--- a/fs/smb/client/smbencrypt.c
+++ b/fs/smb/client/smbencrypt.c
@@ -26,13 +26,6 @@
 #include "cifsproto.h"
 #include "../common/md4.h"
 
-#ifndef false
-#define false 0
-#endif
-#ifndef true
-#define true 1
-#endif
-
 /* following came from the other byteorder.h to avoid include conflicts */
 #define CVAL(buf,pos) (((unsigned char *)(buf))[pos])
 #define SSVALX(buf,pos,val) (CVAL(buf,pos)=(val)&0xFF,CVAL(buf,pos+1)=(val)>>8)
diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c
index 4f717ad7c21b..994d70193432 100644
--- a/fs/smb/client/transport.c
+++ b/fs/smb/client/transport.c
@@ -400,10 +400,17 @@ unmask:
 						  server->conn_id, server->hostname);
 	}
 smbd_done:
-	if (rc < 0 && rc != -EINTR)
+	/*
+	 * there's hardly any use for the layers above to know the
+	 * actual error code here. All they should do at this point is
+	 * to retry the connection and hope it goes away.
+	 */
+	if (rc < 0 && rc != -EINTR && rc != -EAGAIN) {
 		cifs_server_dbg(VFS, "Error %d sending data on socket to server\n",
 			 rc);
-	else if (rc > 0)
+		rc = -ECONNABORTED;
+		cifs_signal_cifsd_for_reconnect(server, false);
+	} else if (rc > 0)
 		rc = 0;
 out:
 	cifs_in_send_dec(server);
@@ -428,8 +435,8 @@ smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
 	if (!(flags & CIFS_TRANSFORM_REQ))
 		return __smb_send_rqst(server, num_rqst, rqst);
 
-	if (num_rqst > MAX_COMPOUND - 1)
-		return -ENOMEM;
+	if (WARN_ON_ONCE(num_rqst > MAX_COMPOUND - 1))
+		return -EIO;
 
 	if (!server->ops->init_transform_rq) {
 		cifs_server_dbg(VFS, "Encryption requested but transform callback is missing\n");
@@ -1026,6 +1033,9 @@ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses)
 		if (!server || server->terminate)
 			continue;
 
+		if (CIFS_CHAN_NEEDS_RECONNECT(ses, i))
+			continue;
+
 		/*
 		 * strictly speaking, we should pick up req_lock to read
 		 * server->in_flight. But it shouldn't matter much here if we
diff --git a/fs/smb/server/asn1.c b/fs/smb/server/asn1.c
index 4a4b2b03ff33..b931a99ab9c8 100644
--- a/fs/smb/server/asn1.c
+++ b/fs/smb/server/asn1.c
@@ -214,10 +214,15 @@ static int ksmbd_neg_token_alloc(void *context, size_t hdrlen,
 {
 	struct ksmbd_conn *conn = context;
 
+	if (!vlen)
+		return -EINVAL;
+
 	conn->mechToken = kmemdup_nul(value, vlen, GFP_KERNEL);
 	if (!conn->mechToken)
 		return -ENOMEM;
 
+	conn->mechTokenLen = (unsigned int)vlen;
+
 	return 0;
 }
 
diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c
index d311c2ee10bd..09e1e7771592 100644
--- a/fs/smb/server/connection.c
+++ b/fs/smb/server/connection.c
@@ -416,13 +416,7 @@ static void stop_sessions(void)
 again:
 	down_read(&conn_list_lock);
 	list_for_each_entry(conn, &conn_list, conns_list) {
-		struct task_struct *task;
-
 		t = conn->transport;
-		task = t->handler;
-		if (task)
-			ksmbd_debug(CONN, "Stop session handler %s/%d\n",
-				    task->comm, task_pid_nr(task));
 		ksmbd_conn_set_exiting(conn);
 		if (t->ops->shutdown) {
 			up_read(&conn_list_lock);
diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h
index 3c005246a32e..0e04cf8b1d89 100644
--- a/fs/smb/server/connection.h
+++ b/fs/smb/server/connection.h
@@ -88,6 +88,7 @@ struct ksmbd_conn {
 	__u16				dialect;
 
 	char				*mechToken;
+	unsigned int			mechTokenLen;
 
 	struct ksmbd_conn_ops	*conn_ops;
 
@@ -134,7 +135,6 @@ struct ksmbd_transport_ops {
 struct ksmbd_transport {
 	struct ksmbd_conn		*conn;
 	struct ksmbd_transport_ops	*ops;
-	struct task_struct		*handler;
 };
 
 #define KSMBD_TCP_RECV_TIMEOUT	(7 * HZ)
diff --git a/fs/smb/server/ksmbd_netlink.h b/fs/smb/server/ksmbd_netlink.h
index b7521e41402e..0ebf91ffa236 100644
--- a/fs/smb/server/ksmbd_netlink.h
+++ b/fs/smb/server/ksmbd_netlink.h
@@ -304,7 +304,8 @@ enum ksmbd_event {
 	KSMBD_EVENT_SPNEGO_AUTHEN_REQUEST,
 	KSMBD_EVENT_SPNEGO_AUTHEN_RESPONSE	= 15,
 
-	KSMBD_EVENT_MAX
+	__KSMBD_EVENT_MAX,
+	KSMBD_EVENT_MAX = __KSMBD_EVENT_MAX - 1
 };
 
 /*
diff --git a/fs/smb/server/misc.c b/fs/smb/server/misc.c
index 9e8afaa686e3..1a5faa6f6e7b 100644
--- a/fs/smb/server/misc.c
+++ b/fs/smb/server/misc.c
@@ -261,6 +261,7 @@ out_ascii:
 
 /**
  * ksmbd_extract_sharename() - get share name from tree connect request
+ * @um: pointer to a unicode_map structure for character encoding handling
  * @treename:	buffer containing tree name and share name
  *
  * Return:      share name on success, otherwise error
diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c
index 001926d3b348..53dfaac425c6 100644
--- a/fs/smb/server/oplock.c
+++ b/fs/smb/server/oplock.c
@@ -1197,6 +1197,12 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid,
 	bool prev_op_has_lease;
 	__le32 prev_op_state = 0;
 
+	/* Only v2 leases handle the directory */
+	if (S_ISDIR(file_inode(fp->filp)->i_mode)) {
+		if (!lctx || lctx->version != 2)
+			return 0;
+	}
+
 	opinfo = alloc_opinfo(work, pid, tid);
 	if (!opinfo)
 		return -ENOMEM;
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 3143819935dc..089527a8b4ff 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -1414,7 +1414,10 @@ static struct ksmbd_user *session_user(struct ksmbd_conn *conn,
 	char *name;
 	unsigned int name_off, name_len, secbuf_len;
 
-	secbuf_len = le16_to_cpu(req->SecurityBufferLength);
+	if (conn->use_spnego && conn->mechToken)
+		secbuf_len = conn->mechTokenLen;
+	else
+		secbuf_len = le16_to_cpu(req->SecurityBufferLength);
 	if (secbuf_len < sizeof(struct authenticate_message)) {
 		ksmbd_debug(SMB, "blob len %d too small\n", secbuf_len);
 		return NULL;
@@ -1505,7 +1508,10 @@ static int ntlm_authenticate(struct ksmbd_work *work,
 		struct authenticate_message *authblob;
 
 		authblob = user_authblob(conn, req);
-		sz = le16_to_cpu(req->SecurityBufferLength);
+		if (conn->use_spnego && conn->mechToken)
+			sz = conn->mechTokenLen;
+		else
+			sz = le16_to_cpu(req->SecurityBufferLength);
 		rc = ksmbd_decode_ntlmssp_auth_blob(authblob, sz, conn, sess);
 		if (rc) {
 			set_user_flag(sess->user, KSMBD_USER_FLAG_BAD_PASSWORD);
@@ -1778,8 +1784,7 @@ int smb2_sess_setup(struct ksmbd_work *work)
 
 	negblob_off = le16_to_cpu(req->SecurityBufferOffset);
 	negblob_len = le16_to_cpu(req->SecurityBufferLength);
-	if (negblob_off < offsetof(struct smb2_sess_setup_req, Buffer) ||
-	    negblob_len < offsetof(struct negotiate_message, NegotiateFlags)) {
+	if (negblob_off < offsetof(struct smb2_sess_setup_req, Buffer)) {
 		rc = -EINVAL;
 		goto out_err;
 	}
@@ -1788,8 +1793,15 @@ int smb2_sess_setup(struct ksmbd_work *work)
 			negblob_off);
 
 	if (decode_negotiation_token(conn, negblob, negblob_len) == 0) {
-		if (conn->mechToken)
+		if (conn->mechToken) {
 			negblob = (struct negotiate_message *)conn->mechToken;
+			negblob_len = conn->mechTokenLen;
+		}
+	}
+
+	if (negblob_len < offsetof(struct negotiate_message, NegotiateFlags)) {
+		rc = -EINVAL;
+		goto out_err;
 	}
 
 	if (server_conf.auth_mechs & conn->auth_mechs) {
@@ -6161,8 +6173,10 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work)
 		err = ksmbd_iov_pin_rsp_read(work, (void *)rsp,
 					     offsetof(struct smb2_read_rsp, Buffer),
 					     aux_payload_buf, nbytes);
-		if (err)
+		if (err) {
+			kvfree(aux_payload_buf);
 			goto out;
+		}
 		kvfree(rpc_resp);
 	} else {
 		err = ksmbd_iov_pin_rsp(work, (void *)rsp,
@@ -6372,8 +6386,10 @@ int smb2_read(struct ksmbd_work *work)
 	err = ksmbd_iov_pin_rsp_read(work, (void *)rsp,
 				     offsetof(struct smb2_read_rsp, Buffer),
 				     aux_payload_buf, nbytes);
-	if (err)
+	if (err) {
+		kvfree(aux_payload_buf);
 		goto out;
+	}
 	ksmbd_fd_put(work, fp);
 	return 0;
 
@@ -6748,10 +6764,10 @@ struct file_lock *smb_flock_init(struct file *f)
 
 	locks_init_lock(fl);
 
-	fl->fl_owner = f;
-	fl->fl_pid = current->tgid;
-	fl->fl_file = f;
-	fl->fl_flags = FL_POSIX;
+	fl->c.flc_owner = f;
+	fl->c.flc_pid = current->tgid;
+	fl->c.flc_file = f;
+	fl->c.flc_flags = FL_POSIX;
 	fl->fl_ops = NULL;
 	fl->fl_lmops = NULL;
 
@@ -6768,30 +6784,30 @@ static int smb2_set_flock_flags(struct file_lock *flock, int flags)
 	case SMB2_LOCKFLAG_SHARED:
 		ksmbd_debug(SMB, "received shared request\n");
 		cmd = F_SETLKW;
-		flock->fl_type = F_RDLCK;
-		flock->fl_flags |= FL_SLEEP;
+		flock->c.flc_type = F_RDLCK;
+		flock->c.flc_flags |= FL_SLEEP;
 		break;
 	case SMB2_LOCKFLAG_EXCLUSIVE:
 		ksmbd_debug(SMB, "received exclusive request\n");
 		cmd = F_SETLKW;
-		flock->fl_type = F_WRLCK;
-		flock->fl_flags |= FL_SLEEP;
+		flock->c.flc_type = F_WRLCK;
+		flock->c.flc_flags |= FL_SLEEP;
 		break;
 	case SMB2_LOCKFLAG_SHARED | SMB2_LOCKFLAG_FAIL_IMMEDIATELY:
 		ksmbd_debug(SMB,
 			    "received shared & fail immediately request\n");
 		cmd = F_SETLK;
-		flock->fl_type = F_RDLCK;
+		flock->c.flc_type = F_RDLCK;
 		break;
 	case SMB2_LOCKFLAG_EXCLUSIVE | SMB2_LOCKFLAG_FAIL_IMMEDIATELY:
 		ksmbd_debug(SMB,
 			    "received exclusive & fail immediately request\n");
 		cmd = F_SETLK;
-		flock->fl_type = F_WRLCK;
+		flock->c.flc_type = F_WRLCK;
 		break;
 	case SMB2_LOCKFLAG_UNLOCK:
 		ksmbd_debug(SMB, "received unlock request\n");
-		flock->fl_type = F_UNLCK;
+		flock->c.flc_type = F_UNLCK;
 		cmd = F_SETLK;
 		break;
 	}
@@ -6829,13 +6845,13 @@ static void smb2_remove_blocked_lock(void **argv)
 	struct file_lock *flock = (struct file_lock *)argv[0];
 
 	ksmbd_vfs_posix_lock_unblock(flock);
-	wake_up(&flock->fl_wait);
+	locks_wake_up(flock);
 }
 
 static inline bool lock_defer_pending(struct file_lock *fl)
 {
 	/* check pending lock waiters */
-	return waitqueue_active(&fl->fl_wait);
+	return waitqueue_active(&fl->c.flc_wait);
 }
 
 /**
@@ -6926,8 +6942,8 @@ int smb2_lock(struct ksmbd_work *work)
 		list_for_each_entry(cmp_lock, &lock_list, llist) {
 			if (cmp_lock->fl->fl_start <= flock->fl_start &&
 			    cmp_lock->fl->fl_end >= flock->fl_end) {
-				if (cmp_lock->fl->fl_type != F_UNLCK &&
-				    flock->fl_type != F_UNLCK) {
+				if (cmp_lock->fl->c.flc_type != F_UNLCK &&
+				    flock->c.flc_type != F_UNLCK) {
 					pr_err("conflict two locks in one request\n");
 					err = -EINVAL;
 					locks_free_lock(flock);
@@ -6975,12 +6991,12 @@ int smb2_lock(struct ksmbd_work *work)
 		list_for_each_entry(conn, &conn_list, conns_list) {
 			spin_lock(&conn->llist_lock);
 			list_for_each_entry_safe(cmp_lock, tmp2, &conn->lock_list, clist) {
-				if (file_inode(cmp_lock->fl->fl_file) !=
-				    file_inode(smb_lock->fl->fl_file))
+				if (file_inode(cmp_lock->fl->c.flc_file) !=
+				    file_inode(smb_lock->fl->c.flc_file))
 					continue;
 
-				if (smb_lock->fl->fl_type == F_UNLCK) {
-					if (cmp_lock->fl->fl_file == smb_lock->fl->fl_file &&
+				if (lock_is_unlock(smb_lock->fl)) {
+					if (cmp_lock->fl->c.flc_file == smb_lock->fl->c.flc_file &&
 					    cmp_lock->start == smb_lock->start &&
 					    cmp_lock->end == smb_lock->end &&
 					    !lock_defer_pending(cmp_lock->fl)) {
@@ -6997,7 +7013,7 @@ int smb2_lock(struct ksmbd_work *work)
 					continue;
 				}
 
-				if (cmp_lock->fl->fl_file == smb_lock->fl->fl_file) {
+				if (cmp_lock->fl->c.flc_file == smb_lock->fl->c.flc_file) {
 					if (smb_lock->flags & SMB2_LOCKFLAG_SHARED)
 						continue;
 				} else {
@@ -7039,7 +7055,7 @@ int smb2_lock(struct ksmbd_work *work)
 		}
 		up_read(&conn_list_lock);
 out_check_cl:
-		if (smb_lock->fl->fl_type == F_UNLCK && nolock) {
+		if (lock_is_unlock(smb_lock->fl) && nolock) {
 			pr_err("Try to unlock nolocked range\n");
 			rsp->hdr.Status = STATUS_RANGE_NOT_LOCKED;
 			goto out;
@@ -7163,7 +7179,7 @@ out:
 		struct file_lock *rlock = NULL;
 
 		rlock = smb_flock_init(filp);
-		rlock->fl_type = F_UNLCK;
+		rlock->c.flc_type = F_UNLCK;
 		rlock->fl_start = smb_lock->start;
 		rlock->fl_end = smb_lock->end;
 
diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c
index b49d47bdafc9..f29bb03f0dc4 100644
--- a/fs/smb/server/transport_ipc.c
+++ b/fs/smb/server/transport_ipc.c
@@ -74,7 +74,7 @@ static int handle_unsupported_event(struct sk_buff *skb, struct genl_info *info)
 static int handle_generic_event(struct sk_buff *skb, struct genl_info *info);
 static int ksmbd_ipc_heartbeat_request(void);
 
-static const struct nla_policy ksmbd_nl_policy[KSMBD_EVENT_MAX] = {
+static const struct nla_policy ksmbd_nl_policy[KSMBD_EVENT_MAX + 1] = {
 	[KSMBD_EVENT_UNSPEC] = {
 		.len = 0,
 	},
@@ -403,7 +403,7 @@ static int handle_generic_event(struct sk_buff *skb, struct genl_info *info)
 		return -EPERM;
 #endif
 
-	if (type >= KSMBD_EVENT_MAX) {
+	if (type > KSMBD_EVENT_MAX) {
 		WARN_ON(1);
 		return -EINVAL;
 	}
diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c
index c5629a68c8b7..8faa25c6e129 100644
--- a/fs/smb/server/transport_rdma.c
+++ b/fs/smb/server/transport_rdma.c
@@ -2039,6 +2039,7 @@ static bool rdma_frwr_is_supported(struct ib_device_attr *attrs)
 static int smb_direct_handle_connect_request(struct rdma_cm_id *new_cm_id)
 {
 	struct smb_direct_transport *t;
+	struct task_struct *handler;
 	int ret;
 
 	if (!rdma_frwr_is_supported(&new_cm_id->device->attrs)) {
@@ -2056,11 +2057,11 @@ static int smb_direct_handle_connect_request(struct rdma_cm_id *new_cm_id)
 	if (ret)
 		goto out_err;
 
-	KSMBD_TRANS(t)->handler = kthread_run(ksmbd_conn_handler_loop,
-					      KSMBD_TRANS(t)->conn, "ksmbd:r%u",
-					      smb_direct_port);
-	if (IS_ERR(KSMBD_TRANS(t)->handler)) {
-		ret = PTR_ERR(KSMBD_TRANS(t)->handler);
+	handler = kthread_run(ksmbd_conn_handler_loop,
+			      KSMBD_TRANS(t)->conn, "ksmbd:r%u",
+			      smb_direct_port);
+	if (IS_ERR(handler)) {
+		ret = PTR_ERR(handler);
 		pr_err("Can't start thread\n");
 		goto out_err;
 	}
diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c
index eff7a1d793f0..002a3f0dc7c5 100644
--- a/fs/smb/server/transport_tcp.c
+++ b/fs/smb/server/transport_tcp.c
@@ -185,6 +185,7 @@ static int ksmbd_tcp_new_connection(struct socket *client_sk)
 	struct sockaddr *csin;
 	int rc = 0;
 	struct tcp_transport *t;
+	struct task_struct *handler;
 
 	t = alloc_transport(client_sk);
 	if (!t) {
@@ -199,13 +200,13 @@ static int ksmbd_tcp_new_connection(struct socket *client_sk)
 		goto out_error;
 	}
 
-	KSMBD_TRANS(t)->handler = kthread_run(ksmbd_conn_handler_loop,
-					      KSMBD_TRANS(t)->conn,
-					      "ksmbd:%u",
-					      ksmbd_tcp_get_port(csin));
-	if (IS_ERR(KSMBD_TRANS(t)->handler)) {
+	handler = kthread_run(ksmbd_conn_handler_loop,
+			      KSMBD_TRANS(t)->conn,
+			      "ksmbd:%u",
+			      ksmbd_tcp_get_port(csin));
+	if (IS_ERR(handler)) {
 		pr_err("cannot start conn thread\n");
-		rc = PTR_ERR(KSMBD_TRANS(t)->handler);
+		rc = PTR_ERR(handler);
 		free_transport(t);
 	}
 	return rc;
@@ -364,6 +365,7 @@ static int ksmbd_tcp_readv(struct tcp_transport *t, struct kvec *iov_orig,
  * @t:		TCP transport instance
  * @buf:	buffer to store read data from socket
  * @to_read:	number of bytes to read from socket
+ * @max_retries: number of retries if reading from socket fails
  *
  * Return:	on success return number of bytes read from socket,
  *		otherwise return error number
@@ -415,6 +417,7 @@ static void tcp_destroy_socket(struct socket *ksmbd_socket)
 
 /**
  * create_socket - create socket for ksmbd/0
+ * @iface:      interface to bind the created socket to
  *
  * Return:	0 on success, error number otherwise
  */
diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c
index a6961bfe3e13..c487e834331a 100644
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c
@@ -337,18 +337,18 @@ static int check_lock_range(struct file *filp, loff_t start, loff_t end,
 		return 0;
 
 	spin_lock(&ctx->flc_lock);
-	list_for_each_entry(flock, &ctx->flc_posix, fl_list) {
+	for_each_file_lock(flock, &ctx->flc_posix) {
 		/* check conflict locks */
 		if (flock->fl_end >= start && end >= flock->fl_start) {
-			if (flock->fl_type == F_RDLCK) {
+			if (lock_is_read(flock)) {
 				if (type == WRITE) {
 					pr_err("not allow write by shared lock\n");
 					error = 1;
 					goto out;
 				}
-			} else if (flock->fl_type == F_WRLCK) {
+			} else if (lock_is_write(flock)) {
 				/* check owner in lock */
-				if (flock->fl_file != filp) {
+				if (flock->c.flc_file != filp) {
 					error = 1;
 					pr_err("not allow rw access by exclusive lock from other opens\n");
 					goto out;
@@ -1837,13 +1837,13 @@ int ksmbd_vfs_copy_file_ranges(struct ksmbd_work *work,
 
 void ksmbd_vfs_posix_lock_wait(struct file_lock *flock)
 {
-	wait_event(flock->fl_wait, !flock->fl_blocker);
+	wait_event(flock->c.flc_wait, !flock->c.flc_blocker);
 }
 
 int ksmbd_vfs_posix_lock_wait_timeout(struct file_lock *flock, long timeout)
 {
-	return wait_event_interruptible_timeout(flock->fl_wait,
-						!flock->fl_blocker,
+	return wait_event_interruptible_timeout(flock->c.flc_wait,
+						!flock->c.flc_blocker,
 						timeout);
 }
 
diff --git a/fs/super.c b/fs/super.c
index d35e85295489..ee05ab6b37e7 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -274,9 +274,10 @@ static void destroy_super_work(struct work_struct *work)
 {
 	struct super_block *s = container_of(work, struct super_block,
 							destroy_work);
-	int i;
-
-	for (i = 0; i < SB_FREEZE_LEVELS; i++)
+	security_sb_free(s);
+	put_user_ns(s->s_user_ns);
+	kfree(s->s_subtype);
+	for (int i = 0; i < SB_FREEZE_LEVELS; i++)
 		percpu_free_rwsem(&s->s_writers.rw_sem[i]);
 	kfree(s);
 }
@@ -296,9 +297,6 @@ static void destroy_unused_super(struct super_block *s)
 	super_unlock_excl(s);
 	list_lru_destroy(&s->s_dentry_lru);
 	list_lru_destroy(&s->s_inode_lru);
-	security_sb_free(s);
-	put_user_ns(s->s_user_ns);
-	kfree(s->s_subtype);
 	shrinker_free(s->s_shrink);
 	/* no delays needed */
 	destroy_super_work(&s->destroy_work);
@@ -409,9 +407,6 @@ static void __put_super(struct super_block *s)
 		WARN_ON(s->s_dentry_lru.node);
 		WARN_ON(s->s_inode_lru.node);
 		WARN_ON(!list_empty(&s->s_mounts));
-		security_sb_free(s);
-		put_user_ns(s->s_user_ns);
-		kfree(s->s_subtype);
 		call_rcu(&s->rcu, destroy_super_rcu);
 	}
 }
@@ -1532,16 +1527,16 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
 		struct fs_context *fc)
 {
 	blk_mode_t mode = sb_open_mode(sb_flags);
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct block_device *bdev;
 
-	bdev_handle = bdev_open_by_dev(sb->s_dev, mode, sb, &fs_holder_ops);
-	if (IS_ERR(bdev_handle)) {
+	bdev_file = bdev_file_open_by_dev(sb->s_dev, mode, sb, &fs_holder_ops);
+	if (IS_ERR(bdev_file)) {
 		if (fc)
 			errorf(fc, "%s: Can't open blockdev", fc->source);
-		return PTR_ERR(bdev_handle);
+		return PTR_ERR(bdev_file);
 	}
-	bdev = bdev_handle->bdev;
+	bdev = file_bdev(bdev_file);
 
 	/*
 	 * This really should be in blkdev_get_by_dev, but right now can't due
@@ -1549,7 +1544,7 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
 	 * writable from userspace even for a read-only block device.
 	 */
 	if ((mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) {
-		bdev_release(bdev_handle);
+		fput(bdev_file);
 		return -EACCES;
 	}
 
@@ -1560,11 +1555,11 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
 	if (atomic_read(&bdev->bd_fsfreeze_count) > 0) {
 		if (fc)
 			warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev);
-		bdev_release(bdev_handle);
+		fput(bdev_file);
 		return -EBUSY;
 	}
 	spin_lock(&sb_lock);
-	sb->s_bdev_handle = bdev_handle;
+	sb->s_bdev_file = bdev_file;
 	sb->s_bdev = bdev;
 	sb->s_bdi = bdi_get(bdev->bd_disk->bdi);
 	if (bdev_stable_writes(bdev))
@@ -1680,7 +1675,7 @@ void kill_block_super(struct super_block *sb)
 	generic_shutdown_super(sb);
 	if (bdev) {
 		sync_blockdev(bdev);
-		bdev_release(sb->s_bdev_handle);
+		fput(sb->s_bdev_file);
 	}
 }
 
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index b6b6796e1616..4df2afa551dc 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -81,7 +81,7 @@ void sysfs_remove_dir(struct kobject *kobj)
 	struct kernfs_node *kn = kobj->sd;
 
 	/*
-	 * In general, kboject owner is responsible for ensuring removal
+	 * In general, kobject owner is responsible for ensuring removal
 	 * doesn't race with other operations and sysfs doesn't provide any
 	 * protection; however, when @kobj is used as a symlink target, the
 	 * symlinking entity usually doesn't own @kobj and thus has no
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index 5a915b2e68f5..76bc2d5e75a9 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -336,7 +336,7 @@ int __init sysv_init_icache(void)
 {
 	sysv_inode_cachep = kmem_cache_create("sysv_inode_cache",
 			sizeof(struct sysv_inode_info), 0,
-			SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT,
+			SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT,
 			init_once);
 	if (!sysv_inode_cachep)
 		return -ENOMEM;
diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c
index 410ab2a44d2f..19bcb51a2203 100644
--- a/fs/sysv/itree.c
+++ b/fs/sysv/itree.c
@@ -83,9 +83,6 @@ static inline sysv_zone_t *block_end(struct buffer_head *bh)
 	return (sysv_zone_t*)((char*)bh->b_data + bh->b_size);
 }
 
-/*
- * Requires read_lock(&pointers_lock) or write_lock(&pointers_lock)
- */
 static Indirect *get_branch(struct inode *inode,
 			    int depth,
 			    int offsets[],
@@ -105,15 +102,18 @@ static Indirect *get_branch(struct inode *inode,
 		bh = sb_bread(sb, block);
 		if (!bh)
 			goto failure;
+		read_lock(&pointers_lock);
 		if (!verify_chain(chain, p))
 			goto changed;
 		add_chain(++p, bh, (sysv_zone_t*)bh->b_data + *++offsets);
+		read_unlock(&pointers_lock);
 		if (!p->key)
 			goto no_block;
 	}
 	return NULL;
 
 changed:
+	read_unlock(&pointers_lock);
 	brelse(bh);
 	*err = -EAGAIN;
 	goto no_block;
@@ -219,9 +219,7 @@ static int get_block(struct inode *inode, sector_t iblock, struct buffer_head *b
 		goto out;
 
 reread:
-	read_lock(&pointers_lock);
 	partial = get_branch(inode, depth, offsets, chain, &err);
-	read_unlock(&pointers_lock);
 
 	/* Simplest case - block found, no allocation needed */
 	if (!partial) {
@@ -291,9 +289,9 @@ static Indirect *find_shared(struct inode *inode,
 	*top = 0;
 	for (k = depth; k > 1 && !offsets[k-1]; k--)
 		;
+	partial = get_branch(inode, k, offsets, chain, &err);
 
 	write_lock(&pointers_lock);
-	partial = get_branch(inode, k, offsets, chain, &err);
 	if (!partial)
 		partial = chain + k-1;
 	/*
diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index f0677ea0ec24..110e8a272189 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -32,6 +32,18 @@
  */
 static DEFINE_MUTEX(eventfs_mutex);
 
+/* Choose something "unique" ;-) */
+#define EVENTFS_FILE_INODE_INO		0x12c4e37
+
+/* Just try to make something consistent and unique */
+static int eventfs_dir_ino(struct eventfs_inode *ei)
+{
+	if (!ei->ino)
+		ei->ino = get_next_ino();
+
+	return ei->ino;
+}
+
 /*
  * The eventfs_inode (ei) itself is protected by SRCU. It is released from
  * its parent's list and will have is_freed set (under eventfs_mutex).
@@ -45,16 +57,55 @@ enum {
 	EVENTFS_SAVE_MODE	= BIT(16),
 	EVENTFS_SAVE_UID	= BIT(17),
 	EVENTFS_SAVE_GID	= BIT(18),
+	EVENTFS_TOPLEVEL	= BIT(19),
 };
 
 #define EVENTFS_MODE_MASK	(EVENTFS_SAVE_MODE - 1)
 
+/*
+ * eventfs_inode reference count management.
+ *
+ * NOTE! We count only references from dentries, in the
+ * form 'dentry->d_fsdata'. There are also references from
+ * directory inodes ('ti->private'), but the dentry reference
+ * count is always a superset of the inode reference count.
+ */
+static void release_ei(struct kref *ref)
+{
+	struct eventfs_inode *ei = container_of(ref, struct eventfs_inode, kref);
+
+	WARN_ON_ONCE(!ei->is_freed);
+
+	kfree(ei->entry_attrs);
+	kfree_const(ei->name);
+	kfree_rcu(ei, rcu);
+}
+
+static inline void put_ei(struct eventfs_inode *ei)
+{
+	if (ei)
+		kref_put(&ei->kref, release_ei);
+}
+
+static inline void free_ei(struct eventfs_inode *ei)
+{
+	if (ei) {
+		ei->is_freed = 1;
+		put_ei(ei);
+	}
+}
+
+static inline struct eventfs_inode *get_ei(struct eventfs_inode *ei)
+{
+	if (ei)
+		kref_get(&ei->kref);
+	return ei;
+}
+
 static struct dentry *eventfs_root_lookup(struct inode *dir,
 					  struct dentry *dentry,
 					  unsigned int flags);
-static int dcache_dir_open_wrapper(struct inode *inode, struct file *file);
-static int dcache_readdir_wrapper(struct file *file, struct dir_context *ctx);
-static int eventfs_release(struct inode *inode, struct file *file);
+static int eventfs_iterate(struct file *file, struct dir_context *ctx);
 
 static void update_attr(struct eventfs_attr *attr, struct iattr *iattr)
 {
@@ -94,7 +145,7 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry,
 	/* Preallocate the children mode array if necessary */
 	if (!(dentry->d_inode->i_mode & S_IFDIR)) {
 		if (!ei->entry_attrs) {
-			ei->entry_attrs = kzalloc(sizeof(*ei->entry_attrs) * ei->nr_entries,
+			ei->entry_attrs = kcalloc(ei->nr_entries, sizeof(*ei->entry_attrs),
 						  GFP_NOFS);
 			if (!ei->entry_attrs) {
 				ret = -ENOMEM;
@@ -117,10 +168,17 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry,
 		 * The events directory dentry is never freed, unless its
 		 * part of an instance that is deleted. It's attr is the
 		 * default for its child files and directories.
-		 * Do not update it. It's not used for its own mode or ownership
+		 * Do not update it. It's not used for its own mode or ownership.
 		 */
-		if (!ei->is_events)
+		if (ei->is_events) {
+			/* But it still needs to know if it was modified */
+			if (iattr->ia_valid & ATTR_UID)
+				ei->attr.mode |= EVENTFS_SAVE_UID;
+			if (iattr->ia_valid & ATTR_GID)
+				ei->attr.mode |= EVENTFS_SAVE_GID;
+		} else {
 			update_attr(&ei->attr, iattr);
+		}
 
 	} else {
 		name = dentry->d_name.name;
@@ -138,9 +196,63 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry,
 	return ret;
 }
 
+static void update_top_events_attr(struct eventfs_inode *ei, struct super_block *sb)
+{
+	struct inode *root;
+
+	/* Only update if the "events" was on the top level */
+	if (!ei || !(ei->attr.mode & EVENTFS_TOPLEVEL))
+		return;
+
+	/* Get the tracefs root inode. */
+	root = d_inode(sb->s_root);
+	ei->attr.uid = root->i_uid;
+	ei->attr.gid = root->i_gid;
+}
+
+static void set_top_events_ownership(struct inode *inode)
+{
+	struct tracefs_inode *ti = get_tracefs(inode);
+	struct eventfs_inode *ei = ti->private;
+
+	/* The top events directory doesn't get automatically updated */
+	if (!ei || !ei->is_events || !(ei->attr.mode & EVENTFS_TOPLEVEL))
+		return;
+
+	update_top_events_attr(ei, inode->i_sb);
+
+	if (!(ei->attr.mode & EVENTFS_SAVE_UID))
+		inode->i_uid = ei->attr.uid;
+
+	if (!(ei->attr.mode & EVENTFS_SAVE_GID))
+		inode->i_gid = ei->attr.gid;
+}
+
+static int eventfs_get_attr(struct mnt_idmap *idmap,
+			    const struct path *path, struct kstat *stat,
+			    u32 request_mask, unsigned int flags)
+{
+	struct dentry *dentry = path->dentry;
+	struct inode *inode = d_backing_inode(dentry);
+
+	set_top_events_ownership(inode);
+
+	generic_fillattr(idmap, request_mask, inode, stat);
+	return 0;
+}
+
+static int eventfs_permission(struct mnt_idmap *idmap,
+			      struct inode *inode, int mask)
+{
+	set_top_events_ownership(inode);
+	return generic_permission(idmap, inode, mask);
+}
+
 static const struct inode_operations eventfs_root_dir_inode_operations = {
 	.lookup		= eventfs_root_lookup,
 	.setattr	= eventfs_set_attr,
+	.getattr	= eventfs_get_attr,
+	.permission	= eventfs_permission,
 };
 
 static const struct inode_operations eventfs_file_inode_operations = {
@@ -148,11 +260,9 @@ static const struct inode_operations eventfs_file_inode_operations = {
 };
 
 static const struct file_operations eventfs_file_operations = {
-	.open		= dcache_dir_open_wrapper,
 	.read		= generic_read_dir,
-	.iterate_shared	= dcache_readdir_wrapper,
+	.iterate_shared	= eventfs_iterate,
 	.llseek		= generic_file_llseek,
-	.release	= eventfs_release,
 };
 
 /* Return the evenfs_inode of the "events" directory */
@@ -160,10 +270,11 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry)
 {
 	struct eventfs_inode *ei;
 
-	mutex_lock(&eventfs_mutex);
 	do {
-		/* The parent always has an ei, except for events itself */
-		ei = dentry->d_parent->d_fsdata;
+		// The parent is stable because we do not do renames
+		dentry = dentry->d_parent;
+		// ... and directories always have d_fsdata
+		ei = dentry->d_fsdata;
 
 		/*
 		 * If the ei is being freed, the ownership of the children
@@ -173,10 +284,10 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry)
 			ei = NULL;
 			break;
 		}
-
-		dentry = ei->dentry;
+		// Walk upwards until you find the events inode
 	} while (!ei->is_events);
-	mutex_unlock(&eventfs_mutex);
+
+	update_top_events_attr(ei, dentry->d_sb);
 
 	return ei;
 }
@@ -206,50 +317,11 @@ static void update_inode_attr(struct dentry *dentry, struct inode *inode,
 		inode->i_gid = attr->gid;
 }
 
-static void update_gid(struct eventfs_inode *ei, kgid_t gid, int level)
-{
-	struct eventfs_inode *ei_child;
-
-	/* at most we have events/system/event */
-	if (WARN_ON_ONCE(level > 3))
-		return;
-
-	ei->attr.gid = gid;
-
-	if (ei->entry_attrs) {
-		for (int i = 0; i < ei->nr_entries; i++) {
-			ei->entry_attrs[i].gid = gid;
-		}
-	}
-
-	/*
-	 * Only eventfs_inode with dentries are updated, make sure
-	 * all eventfs_inodes are updated. If one of the children
-	 * do not have a dentry, this function must traverse it.
-	 */
-	list_for_each_entry_srcu(ei_child, &ei->children, list,
-				 srcu_read_lock_held(&eventfs_srcu)) {
-		if (!ei_child->dentry)
-			update_gid(ei_child, gid, level + 1);
-	}
-}
-
-void eventfs_update_gid(struct dentry *dentry, kgid_t gid)
-{
-	struct eventfs_inode *ei = dentry->d_fsdata;
-	int idx;
-
-	idx = srcu_read_lock(&eventfs_srcu);
-	update_gid(ei, gid, 0);
-	srcu_read_unlock(&eventfs_srcu, idx);
-}
-
 /**
- * create_file - create a file in the tracefs filesystem
- * @name: the name of the file to create.
+ * lookup_file - look up a file in the tracefs filesystem
+ * @dentry: the dentry to look up
  * @mode: the permission that the file should have.
  * @attr: saved attributes changed by user
- * @parent: parent dentry for this file.
  * @data: something that the caller will want to get to later on.
  * @fop: struct file_operations that should be used for this file.
  *
@@ -257,30 +329,25 @@ void eventfs_update_gid(struct dentry *dentry, kgid_t gid)
  * directory. The inode.i_private pointer will point to @data in the open()
  * call.
  */
-static struct dentry *create_file(const char *name, umode_t mode,
+static struct dentry *lookup_file(struct eventfs_inode *parent_ei,
+				  struct dentry *dentry,
+				  umode_t mode,
 				  struct eventfs_attr *attr,
-				  struct dentry *parent, void *data,
+				  void *data,
 				  const struct file_operations *fop)
 {
 	struct tracefs_inode *ti;
-	struct dentry *dentry;
 	struct inode *inode;
 
 	if (!(mode & S_IFMT))
 		mode |= S_IFREG;
 
 	if (WARN_ON_ONCE(!S_ISREG(mode)))
-		return NULL;
-
-	WARN_ON_ONCE(!parent);
-	dentry = eventfs_start_creating(name, parent);
-
-	if (IS_ERR(dentry))
-		return dentry;
+		return ERR_PTR(-EIO);
 
 	inode = tracefs_get_inode(dentry->d_sb);
 	if (unlikely(!inode))
-		return eventfs_failed_creating(dentry);
+		return ERR_PTR(-ENOMEM);
 
 	/* If the user updated the directory's attributes, use them */
 	update_inode_attr(dentry, inode, attr, mode);
@@ -289,34 +356,36 @@ static struct dentry *create_file(const char *name, umode_t mode,
 	inode->i_fop = fop;
 	inode->i_private = data;
 
+	/* All files will have the same inode number */
+	inode->i_ino = EVENTFS_FILE_INODE_INO;
+
 	ti = get_tracefs(inode);
 	ti->flags |= TRACEFS_EVENT_INODE;
-	d_instantiate(dentry, inode);
-	fsnotify_create(dentry->d_parent->d_inode, dentry);
-	return eventfs_end_creating(dentry);
+
+	// Files have their parent's ei as their fsdata
+	dentry->d_fsdata = get_ei(parent_ei);
+
+	d_add(dentry, inode);
+	return NULL;
 };
 
 /**
- * create_dir - create a dir in the tracefs filesystem
+ * lookup_dir_entry - look up a dir in the tracefs filesystem
+ * @dentry: the directory to look up
  * @ei: the eventfs_inode that represents the directory to create
- * @parent: parent dentry for this file.
  *
- * This function will create a dentry for a directory represented by
+ * This function will look up a dentry for a directory represented by
  * a eventfs_inode.
  */
-static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent)
+static struct dentry *lookup_dir_entry(struct dentry *dentry,
+	struct eventfs_inode *pei, struct eventfs_inode *ei)
 {
 	struct tracefs_inode *ti;
-	struct dentry *dentry;
 	struct inode *inode;
 
-	dentry = eventfs_start_creating(ei->name, parent);
-	if (IS_ERR(dentry))
-		return dentry;
-
 	inode = tracefs_get_inode(dentry->d_sb);
 	if (unlikely(!inode))
-		return eventfs_failed_creating(dentry);
+		return ERR_PTR(-ENOMEM);
 
 	/* If the user updated the directory's attributes, use them */
 	update_inode_attr(dentry, inode, &ei->attr,
@@ -325,247 +394,72 @@ static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent
 	inode->i_op = &eventfs_root_dir_inode_operations;
 	inode->i_fop = &eventfs_file_operations;
 
+	/* All directories will have the same inode number */
+	inode->i_ino = eventfs_dir_ino(ei);
+
 	ti = get_tracefs(inode);
 	ti->flags |= TRACEFS_EVENT_INODE;
+	/* Only directories have ti->private set to an ei, not files */
+	ti->private = ei;
 
-	inc_nlink(inode);
-	d_instantiate(dentry, inode);
-	inc_nlink(dentry->d_parent->d_inode);
-	fsnotify_mkdir(dentry->d_parent->d_inode, dentry);
-	return eventfs_end_creating(dentry);
+	dentry->d_fsdata = get_ei(ei);
+
+	d_add(dentry, inode);
+	return NULL;
 }
 
-static void free_ei(struct eventfs_inode *ei)
+static inline struct eventfs_inode *alloc_ei(const char *name)
 {
-	kfree_const(ei->name);
-	kfree(ei->d_children);
-	kfree(ei->entry_attrs);
-	kfree(ei);
+	struct eventfs_inode *ei = kzalloc(sizeof(*ei), GFP_KERNEL);
+
+	if (!ei)
+		return NULL;
+
+	ei->name = kstrdup_const(name, GFP_KERNEL);
+	if (!ei->name) {
+		kfree(ei);
+		return NULL;
+	}
+	kref_init(&ei->kref);
+	return ei;
 }
 
 /**
- * eventfs_set_ei_status_free - remove the dentry reference from an eventfs_inode
- * @ti: the tracefs_inode of the dentry
+ * eventfs_d_release - dentry is going away
  * @dentry: dentry which has the reference to remove.
  *
  * Remove the association between a dentry from an eventfs_inode.
  */
-void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry)
+void eventfs_d_release(struct dentry *dentry)
 {
-	struct eventfs_inode *ei;
-	int i;
-
-	mutex_lock(&eventfs_mutex);
-
-	ei = dentry->d_fsdata;
-	if (!ei)
-		goto out;
-
-	/* This could belong to one of the files of the ei */
-	if (ei->dentry != dentry) {
-		for (i = 0; i < ei->nr_entries; i++) {
-			if (ei->d_children[i] == dentry)
-				break;
-		}
-		if (WARN_ON_ONCE(i == ei->nr_entries))
-			goto out;
-		ei->d_children[i] = NULL;
-	} else if (ei->is_freed) {
-		free_ei(ei);
-	} else {
-		ei->dentry = NULL;
-	}
-
-	dentry->d_fsdata = NULL;
- out:
-	mutex_unlock(&eventfs_mutex);
+	put_ei(dentry->d_fsdata);
 }
 
 /**
- * create_file_dentry - create a dentry for a file of an eventfs_inode
+ * lookup_file_dentry - create a dentry for a file of an eventfs_inode
  * @ei: the eventfs_inode that the file will be created under
- * @idx: the index into the d_children[] of the @ei
+ * @idx: the index into the entry_attrs[] of the @ei
  * @parent: The parent dentry of the created file.
  * @name: The name of the file to create
  * @mode: The mode of the file.
  * @data: The data to use to set the inode of the file with on open()
  * @fops: The fops of the file to be created.
- * @lookup: If called by the lookup routine, in which case, dput() the created dentry.
  *
  * Create a dentry for a file of an eventfs_inode @ei and place it into the
- * address located at @e_dentry. If the @e_dentry already has a dentry, then
- * just do a dget() on it and return. Otherwise create the dentry and attach it.
+ * address located at @e_dentry.
  */
 static struct dentry *
-create_file_dentry(struct eventfs_inode *ei, int idx,
-		   struct dentry *parent, const char *name, umode_t mode, void *data,
-		   const struct file_operations *fops, bool lookup)
+lookup_file_dentry(struct dentry *dentry,
+		   struct eventfs_inode *ei, int idx,
+		   umode_t mode, void *data,
+		   const struct file_operations *fops)
 {
 	struct eventfs_attr *attr = NULL;
-	struct dentry **e_dentry = &ei->d_children[idx];
-	struct dentry *dentry;
-
-	WARN_ON_ONCE(!inode_is_locked(parent->d_inode));
 
-	mutex_lock(&eventfs_mutex);
-	if (ei->is_freed) {
-		mutex_unlock(&eventfs_mutex);
-		return NULL;
-	}
-	/* If the e_dentry already has a dentry, use it */
-	if (*e_dentry) {
-		/* lookup does not need to up the ref count */
-		if (!lookup)
-			dget(*e_dentry);
-		mutex_unlock(&eventfs_mutex);
-		return *e_dentry;
-	}
-
-	/* ei->entry_attrs are protected by SRCU */
 	if (ei->entry_attrs)
 		attr = &ei->entry_attrs[idx];
 
-	mutex_unlock(&eventfs_mutex);
-
-	dentry = create_file(name, mode, attr, parent, data, fops);
-
-	mutex_lock(&eventfs_mutex);
-
-	if (IS_ERR_OR_NULL(dentry)) {
-		/*
-		 * When the mutex was released, something else could have
-		 * created the dentry for this e_dentry. In which case
-		 * use that one.
-		 *
-		 * If ei->is_freed is set, the e_dentry is currently on its
-		 * way to being freed, don't return it. If e_dentry is NULL
-		 * it means it was already freed.
-		 */
-		if (ei->is_freed)
-			dentry = NULL;
-		else
-			dentry = *e_dentry;
-		/* The lookup does not need to up the dentry refcount */
-		if (dentry && !lookup)
-			dget(dentry);
-		mutex_unlock(&eventfs_mutex);
-		return dentry;
-	}
-
-	if (!*e_dentry && !ei->is_freed) {
-		*e_dentry = dentry;
-		dentry->d_fsdata = ei;
-	} else {
-		/*
-		 * Should never happen unless we get here due to being freed.
-		 * Otherwise it means two dentries exist with the same name.
-		 */
-		WARN_ON_ONCE(!ei->is_freed);
-		dentry = NULL;
-	}
-	mutex_unlock(&eventfs_mutex);
-
-	if (lookup)
-		dput(dentry);
-
-	return dentry;
-}
-
-/**
- * eventfs_post_create_dir - post create dir routine
- * @ei: eventfs_inode of recently created dir
- *
- * Map the meta-data of files within an eventfs dir to their parent dentry
- */
-static void eventfs_post_create_dir(struct eventfs_inode *ei)
-{
-	struct eventfs_inode *ei_child;
-	struct tracefs_inode *ti;
-
-	lockdep_assert_held(&eventfs_mutex);
-
-	/* srcu lock already held */
-	/* fill parent-child relation */
-	list_for_each_entry_srcu(ei_child, &ei->children, list,
-				 srcu_read_lock_held(&eventfs_srcu)) {
-		ei_child->d_parent = ei->dentry;
-	}
-
-	ti = get_tracefs(ei->dentry->d_inode);
-	ti->private = ei;
-}
-
-/**
- * create_dir_dentry - Create a directory dentry for the eventfs_inode
- * @pei: The eventfs_inode parent of ei.
- * @ei: The eventfs_inode to create the directory for
- * @parent: The dentry of the parent of this directory
- * @lookup: True if this is called by the lookup code
- *
- * This creates and attaches a directory dentry to the eventfs_inode @ei.
- */
-static struct dentry *
-create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei,
-		  struct dentry *parent, bool lookup)
-{
-	struct dentry *dentry = NULL;
-
-	WARN_ON_ONCE(!inode_is_locked(parent->d_inode));
-
-	mutex_lock(&eventfs_mutex);
-	if (pei->is_freed || ei->is_freed) {
-		mutex_unlock(&eventfs_mutex);
-		return NULL;
-	}
-	if (ei->dentry) {
-		/* If the dentry already has a dentry, use it */
-		dentry = ei->dentry;
-		/* lookup does not need to up the ref count */
-		if (!lookup)
-			dget(dentry);
-		mutex_unlock(&eventfs_mutex);
-		return dentry;
-	}
-	mutex_unlock(&eventfs_mutex);
-
-	dentry = create_dir(ei, parent);
-
-	mutex_lock(&eventfs_mutex);
-
-	if (IS_ERR_OR_NULL(dentry) && !ei->is_freed) {
-		/*
-		 * When the mutex was released, something else could have
-		 * created the dentry for this e_dentry. In which case
-		 * use that one.
-		 *
-		 * If ei->is_freed is set, the e_dentry is currently on its
-		 * way to being freed.
-		 */
-		dentry = ei->dentry;
-		if (dentry && !lookup)
-			dget(dentry);
-		mutex_unlock(&eventfs_mutex);
-		return dentry;
-	}
-
-	if (!ei->dentry && !ei->is_freed) {
-		ei->dentry = dentry;
-		eventfs_post_create_dir(ei);
-		dentry->d_fsdata = ei;
-	} else {
-		/*
-		 * Should never happen unless we get here due to being freed.
-		 * Otherwise it means two dentries exist with the same name.
-		 */
-		WARN_ON_ONCE(!ei->is_freed);
-		dentry = NULL;
-	}
-	mutex_unlock(&eventfs_mutex);
-
-	if (lookup)
-		dput(dentry);
-
-	return dentry;
+	return lookup_file(ei, dentry, mode, attr, data, fops);
 }
 
 /**
@@ -582,250 +476,153 @@ static struct dentry *eventfs_root_lookup(struct inode *dir,
 					  struct dentry *dentry,
 					  unsigned int flags)
 {
-	const struct file_operations *fops;
-	const struct eventfs_entry *entry;
 	struct eventfs_inode *ei_child;
 	struct tracefs_inode *ti;
 	struct eventfs_inode *ei;
-	struct dentry *ei_dentry = NULL;
-	struct dentry *ret = NULL;
 	const char *name = dentry->d_name.name;
-	bool created = false;
-	umode_t mode;
-	void *data;
-	int idx;
-	int i;
-	int r;
+	struct dentry *result = NULL;
 
 	ti = get_tracefs(dir);
 	if (!(ti->flags & TRACEFS_EVENT_INODE))
-		return NULL;
-
-	/* Grab srcu to prevent the ei from going away */
-	idx = srcu_read_lock(&eventfs_srcu);
+		return ERR_PTR(-EIO);
 
-	/*
-	 * Grab the eventfs_mutex to consistent value from ti->private.
-	 * This s
-	 */
 	mutex_lock(&eventfs_mutex);
-	ei = READ_ONCE(ti->private);
-	if (ei && !ei->is_freed)
-		ei_dentry = READ_ONCE(ei->dentry);
-	mutex_unlock(&eventfs_mutex);
 
-	if (!ei || !ei_dentry)
+	ei = ti->private;
+	if (!ei || ei->is_freed)
 		goto out;
 
-	data = ei->data;
-
-	list_for_each_entry_srcu(ei_child, &ei->children, list,
-				 srcu_read_lock_held(&eventfs_srcu)) {
+	list_for_each_entry(ei_child, &ei->children, list) {
 		if (strcmp(ei_child->name, name) != 0)
 			continue;
-		ret = simple_lookup(dir, dentry, flags);
-		if (IS_ERR(ret))
+		if (ei_child->is_freed)
 			goto out;
-		create_dir_dentry(ei, ei_child, ei_dentry, true);
-		created = true;
-		break;
-	}
-
-	if (created)
+		result = lookup_dir_entry(dentry, ei, ei_child);
 		goto out;
-
-	for (i = 0; i < ei->nr_entries; i++) {
-		entry = &ei->entries[i];
-		if (strcmp(name, entry->name) == 0) {
-			void *cdata = data;
-			mutex_lock(&eventfs_mutex);
-			/* If ei->is_freed, then the event itself may be too */
-			if (!ei->is_freed)
-				r = entry->callback(name, &mode, &cdata, &fops);
-			else
-				r = -1;
-			mutex_unlock(&eventfs_mutex);
-			if (r <= 0)
-				continue;
-			ret = simple_lookup(dir, dentry, flags);
-			if (IS_ERR(ret))
-				goto out;
-			create_file_dentry(ei, i, ei_dentry, name, mode, cdata,
-					   fops, true);
-			break;
-		}
 	}
- out:
-	srcu_read_unlock(&eventfs_srcu, idx);
-	return ret;
-}
-
-struct dentry_list {
-	void			*cursor;
-	struct dentry		**dentries;
-};
 
-/**
- * eventfs_release - called to release eventfs file/dir
- * @inode: inode to be released
- * @file: file to be released (not used)
- */
-static int eventfs_release(struct inode *inode, struct file *file)
-{
-	struct tracefs_inode *ti;
-	struct dentry_list *dlist = file->private_data;
-	void *cursor;
-	int i;
+	for (int i = 0; i < ei->nr_entries; i++) {
+		void *data;
+		umode_t mode;
+		const struct file_operations *fops;
+		const struct eventfs_entry *entry = &ei->entries[i];
 
-	ti = get_tracefs(inode);
-	if (!(ti->flags & TRACEFS_EVENT_INODE))
-		return -EINVAL;
+		if (strcmp(name, entry->name) != 0)
+			continue;
 
-	if (WARN_ON_ONCE(!dlist))
-		return -EINVAL;
+		data = ei->data;
+		if (entry->callback(name, &mode, &data, &fops) <= 0)
+			goto out;
 
-	for (i = 0; dlist->dentries && dlist->dentries[i]; i++) {
-		dput(dlist->dentries[i]);
+		result = lookup_file_dentry(dentry, ei, i, mode, data, fops);
+		goto out;
 	}
-
-	cursor = dlist->cursor;
-	kfree(dlist->dentries);
-	kfree(dlist);
-	file->private_data = cursor;
-	return dcache_dir_close(inode, file);
-}
-
-static int add_dentries(struct dentry ***dentries, struct dentry *d, int cnt)
-{
-	struct dentry **tmp;
-
-	tmp = krealloc(*dentries, sizeof(d) * (cnt + 2), GFP_NOFS);
-	if (!tmp)
-		return -1;
-	tmp[cnt] = d;
-	tmp[cnt + 1] = NULL;
-	*dentries = tmp;
-	return 0;
+ out:
+	mutex_unlock(&eventfs_mutex);
+	return result;
 }
 
-/**
- * dcache_dir_open_wrapper - eventfs open wrapper
- * @inode: not used
- * @file: dir to be opened (to create it's children)
- *
- * Used to dynamic create file/dir with-in @file, all the
- * file/dir will be created. If already created then references
- * will be increased
+/*
+ * Walk the children of a eventfs_inode to fill in getdents().
  */
-static int dcache_dir_open_wrapper(struct inode *inode, struct file *file)
+static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 {
 	const struct file_operations *fops;
+	struct inode *f_inode = file_inode(file);
 	const struct eventfs_entry *entry;
 	struct eventfs_inode *ei_child;
 	struct tracefs_inode *ti;
 	struct eventfs_inode *ei;
-	struct dentry_list *dlist;
-	struct dentry **dentries = NULL;
-	struct dentry *parent = file_dentry(file);
-	struct dentry *d;
-	struct inode *f_inode = file_inode(file);
-	const char *name = parent->d_name.name;
+	const char *name;
 	umode_t mode;
-	void *data;
-	int cnt = 0;
 	int idx;
-	int ret;
-	int i;
-	int r;
+	int ret = -EINVAL;
+	int ino;
+	int i, r, c;
+
+	if (!dir_emit_dots(file, ctx))
+		return 0;
 
 	ti = get_tracefs(f_inode);
 	if (!(ti->flags & TRACEFS_EVENT_INODE))
 		return -EINVAL;
 
-	if (WARN_ON_ONCE(file->private_data))
-		return -EINVAL;
+	c = ctx->pos - 2;
 
 	idx = srcu_read_lock(&eventfs_srcu);
 
 	mutex_lock(&eventfs_mutex);
 	ei = READ_ONCE(ti->private);
+	if (ei && ei->is_freed)
+		ei = NULL;
 	mutex_unlock(&eventfs_mutex);
 
-	if (!ei) {
-		srcu_read_unlock(&eventfs_srcu, idx);
-		return -EINVAL;
-	}
-
+	if (!ei)
+		goto out;
 
-	data = ei->data;
+	/*
+	 * Need to create the dentries and inodes to have a consistent
+	 * inode number.
+	 */
+	ret = 0;
 
-	dlist = kmalloc(sizeof(*dlist), GFP_KERNEL);
-	if (!dlist) {
-		srcu_read_unlock(&eventfs_srcu, idx);
-		return -ENOMEM;
-	}
+	/* Start at 'c' to jump over already read entries */
+	for (i = c; i < ei->nr_entries; i++, ctx->pos++) {
+		void *cdata = ei->data;
 
-	inode_lock(parent->d_inode);
-	list_for_each_entry_srcu(ei_child, &ei->children, list,
-				 srcu_read_lock_held(&eventfs_srcu)) {
-		d = create_dir_dentry(ei, ei_child, parent, false);
-		if (d) {
-			ret = add_dentries(&dentries, d, cnt);
-			if (ret < 0)
-				break;
-			cnt++;
-		}
-	}
-
-	for (i = 0; i < ei->nr_entries; i++) {
-		void *cdata = data;
 		entry = &ei->entries[i];
 		name = entry->name;
+
 		mutex_lock(&eventfs_mutex);
-		/* If ei->is_freed, then the event itself may be too */
-		if (!ei->is_freed)
-			r = entry->callback(name, &mode, &cdata, &fops);
-		else
-			r = -1;
+		/* If ei->is_freed then just bail here, nothing more to do */
+		if (ei->is_freed) {
+			mutex_unlock(&eventfs_mutex);
+			goto out;
+		}
+		r = entry->callback(name, &mode, &cdata, &fops);
 		mutex_unlock(&eventfs_mutex);
 		if (r <= 0)
 			continue;
-		d = create_file_dentry(ei, i, parent, name, mode, cdata, fops, false);
-		if (d) {
-			ret = add_dentries(&dentries, d, cnt);
-			if (ret < 0)
-				break;
-			cnt++;
+
+		ino = EVENTFS_FILE_INODE_INO;
+
+		if (!dir_emit(ctx, name, strlen(name), ino, DT_REG))
+			goto out;
+	}
+
+	/* Subtract the skipped entries above */
+	c -= min((unsigned int)c, (unsigned int)ei->nr_entries);
+
+	list_for_each_entry_srcu(ei_child, &ei->children, list,
+				 srcu_read_lock_held(&eventfs_srcu)) {
+
+		if (c > 0) {
+			c--;
+			continue;
 		}
+
+		ctx->pos++;
+
+		if (ei_child->is_freed)
+			continue;
+
+		name = ei_child->name;
+
+		ino = eventfs_dir_ino(ei_child);
+
+		if (!dir_emit(ctx, name, strlen(name), ino, DT_DIR))
+			goto out_dec;
 	}
-	inode_unlock(parent->d_inode);
+	ret = 1;
+ out:
 	srcu_read_unlock(&eventfs_srcu, idx);
-	ret = dcache_dir_open(inode, file);
 
-	/*
-	 * dcache_dir_open() sets file->private_data to a dentry cursor.
-	 * Need to save that but also save all the dentries that were
-	 * opened by this function.
-	 */
-	dlist->cursor = file->private_data;
-	dlist->dentries = dentries;
-	file->private_data = dlist;
 	return ret;
-}
-
-/*
- * This just sets the file->private_data back to the cursor and back.
- */
-static int dcache_readdir_wrapper(struct file *file, struct dir_context *ctx)
-{
-	struct dentry_list *dlist = file->private_data;
-	int ret;
 
-	file->private_data = dlist->cursor;
-	ret = dcache_readdir(file, ctx);
-	dlist->cursor = file->private_data;
-	file->private_data = dlist;
-	return ret;
+ out_dec:
+	/* Incremented ctx->pos without adding something, reset it */
+	ctx->pos--;
+	goto out;
 }
 
 /**
@@ -872,25 +669,10 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode
 	if (!parent)
 		return ERR_PTR(-EINVAL);
 
-	ei = kzalloc(sizeof(*ei), GFP_KERNEL);
+	ei = alloc_ei(name);
 	if (!ei)
 		return ERR_PTR(-ENOMEM);
 
-	ei->name = kstrdup_const(name, GFP_KERNEL);
-	if (!ei->name) {
-		kfree(ei);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	if (size) {
-		ei->d_children = kzalloc(sizeof(*ei->d_children) * size, GFP_KERNEL);
-		if (!ei->d_children) {
-			kfree_const(ei->name);
-			kfree(ei);
-			return ERR_PTR(-ENOMEM);
-		}
-	}
-
 	ei->entries = entries;
 	ei->nr_entries = size;
 	ei->data = data;
@@ -898,10 +680,8 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode
 	INIT_LIST_HEAD(&ei->list);
 
 	mutex_lock(&eventfs_mutex);
-	if (!parent->is_freed) {
+	if (!parent->is_freed)
 		list_add_tail(&ei->list, &parent->children);
-		ei->d_parent = parent->dentry;
-	}
 	mutex_unlock(&eventfs_mutex);
 
 	/* Was the parent freed? */
@@ -941,33 +721,33 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 	if (IS_ERR(dentry))
 		return ERR_CAST(dentry);
 
-	ei = kzalloc(sizeof(*ei), GFP_KERNEL);
+	ei = alloc_ei(name);
 	if (!ei)
-		goto fail_ei;
+		goto fail;
 
 	inode = tracefs_get_inode(dentry->d_sb);
 	if (unlikely(!inode))
 		goto fail;
 
-	if (size) {
-		ei->d_children = kzalloc(sizeof(*ei->d_children) * size, GFP_KERNEL);
-		if (!ei->d_children)
-			goto fail;
-	}
-
-	ei->dentry = dentry;
+	// Note: we have a ref to the dentry from tracefs_start_creating()
+	ei->events_dir = dentry;
 	ei->entries = entries;
 	ei->nr_entries = size;
 	ei->is_events = 1;
 	ei->data = data;
-	ei->name = kstrdup_const(name, GFP_KERNEL);
-	if (!ei->name)
-		goto fail;
 
 	/* Save the ownership of this directory */
 	uid = d_inode(dentry->d_parent)->i_uid;
 	gid = d_inode(dentry->d_parent)->i_gid;
 
+	/*
+	 * If the events directory is of the top instance, then parent
+	 * is NULL. Set the attr.mode to reflect this and its permissions will
+	 * default to the tracefs root dentry.
+	 */
+	if (!parent)
+		ei->attr.mode = EVENTFS_TOPLEVEL;
+
 	/* This is used as the default ownership of the files and directories */
 	ei->attr.uid = uid;
 	ei->attr.gid = gid;
@@ -985,11 +765,19 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 	inode->i_op = &eventfs_root_dir_inode_operations;
 	inode->i_fop = &eventfs_file_operations;
 
-	dentry->d_fsdata = ei;
+	dentry->d_fsdata = get_ei(ei);
 
-	/* directory inodes start off with i_nlink == 2 (for "." entry) */
-	inc_nlink(inode);
+	/*
+	 * Keep all eventfs directories with i_nlink == 1.
+	 * Due to the dynamic nature of the dentry creations and not
+	 * wanting to add a pointer to the parent eventfs_inode in the
+	 * eventfs_inode structure, keeping the i_nlink in sync with the
+	 * number of directories would cause too much complexity for
+	 * something not worth much. Keeping directory links at 1
+	 * tells userspace not to trust the link number.
+	 */
 	d_instantiate(dentry, inode);
+	/* The dentry of the "events" parent does keep track though */
 	inc_nlink(dentry->d_parent->d_inode);
 	fsnotify_mkdir(dentry->d_parent->d_inode, dentry);
 	tracefs_end_creating(dentry);
@@ -997,72 +785,11 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 	return ei;
 
  fail:
-	kfree(ei->d_children);
-	kfree(ei);
- fail_ei:
+	free_ei(ei);
 	tracefs_failed_creating(dentry);
 	return ERR_PTR(-ENOMEM);
 }
 
-static LLIST_HEAD(free_list);
-
-static void eventfs_workfn(struct work_struct *work)
-{
-        struct eventfs_inode *ei, *tmp;
-        struct llist_node *llnode;
-
-	llnode = llist_del_all(&free_list);
-        llist_for_each_entry_safe(ei, tmp, llnode, llist) {
-		/* This dput() matches the dget() from unhook_dentry() */
-		for (int i = 0; i < ei->nr_entries; i++) {
-			if (ei->d_children[i])
-				dput(ei->d_children[i]);
-		}
-		/* This should only get here if it had a dentry */
-		if (!WARN_ON_ONCE(!ei->dentry))
-			dput(ei->dentry);
-        }
-}
-
-static DECLARE_WORK(eventfs_work, eventfs_workfn);
-
-static void free_rcu_ei(struct rcu_head *head)
-{
-	struct eventfs_inode *ei = container_of(head, struct eventfs_inode, rcu);
-
-	if (ei->dentry) {
-		/* Do not free the ei until all references of dentry are gone */
-		if (llist_add(&ei->llist, &free_list))
-			queue_work(system_unbound_wq, &eventfs_work);
-		return;
-	}
-
-	/* If the ei doesn't have a dentry, neither should its children */
-	for (int i = 0; i < ei->nr_entries; i++) {
-		WARN_ON_ONCE(ei->d_children[i]);
-	}
-
-	free_ei(ei);
-}
-
-static void unhook_dentry(struct dentry *dentry)
-{
-	if (!dentry)
-		return;
-	/*
-	 * Need to add a reference to the dentry that is expected by
-	 * simple_recursive_removal(), which will include a dput().
-	 */
-	dget(dentry);
-
-	/*
-	 * Also add a reference for the dput() in eventfs_workfn().
-	 * That is required as that dput() will free the ei after
-	 * the SRCU grace period is over.
-	 */
-	dget(dentry);
-}
-
 /**
  * eventfs_remove_rec - remove eventfs dir or file from list
  * @ei: eventfs_inode to be removed.
@@ -1075,8 +802,6 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level)
 {
 	struct eventfs_inode *ei_child;
 
-	if (!ei)
-		return;
 	/*
 	 * Check recursion depth. It should never be greater than 3:
 	 * 0 - events/
@@ -1088,28 +813,11 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level)
 		return;
 
 	/* search for nested folders or files */
-	list_for_each_entry_srcu(ei_child, &ei->children, list,
-				 lockdep_is_held(&eventfs_mutex)) {
-		/* Children only have dentry if parent does */
-		WARN_ON_ONCE(ei_child->dentry && !ei->dentry);
+	list_for_each_entry(ei_child, &ei->children, list)
 		eventfs_remove_rec(ei_child, level + 1);
-	}
-
-
-	ei->is_freed = 1;
 
-	for (int i = 0; i < ei->nr_entries; i++) {
-		if (ei->d_children[i]) {
-			/* Children only have dentry if parent does */
-			WARN_ON_ONCE(!ei->dentry);
-			unhook_dentry(ei->d_children[i]);
-		}
-	}
-
-	unhook_dentry(ei->dentry);
-
-	list_del_rcu(&ei->list);
-	call_srcu(&eventfs_srcu, &ei->rcu, free_rcu_ei);
+	list_del(&ei->list);
+	free_ei(ei);
 }
 
 /**
@@ -1120,22 +828,12 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level)
  */
 void eventfs_remove_dir(struct eventfs_inode *ei)
 {
-	struct dentry *dentry;
-
 	if (!ei)
 		return;
 
 	mutex_lock(&eventfs_mutex);
-	dentry = ei->dentry;
 	eventfs_remove_rec(ei, 0);
 	mutex_unlock(&eventfs_mutex);
-
-	/*
-	 * If any of the ei children has a dentry, then the ei itself
-	 * must have a dentry.
-	 */
-	if (dentry)
-		simple_recursive_removal(dentry, NULL);
 }
 
 /**
@@ -1148,7 +846,11 @@ void eventfs_remove_events_dir(struct eventfs_inode *ei)
 {
 	struct dentry *dentry;
 
-	dentry = ei->dentry;
+	dentry = ei->events_dir;
+	if (!dentry)
+		return;
+
+	ei->events_dir = NULL;
 	eventfs_remove_dir(ei);
 
 	/*
@@ -1158,5 +860,6 @@ void eventfs_remove_events_dir(struct eventfs_inode *ei)
 	 * sticks around while the other ei->dentry are created
 	 * and destroyed dynamically.
 	 */
+	d_invalidate(dentry);
 	dput(dentry);
 }
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index ad20e6af938d..d65ffad4c327 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -38,8 +38,6 @@ static struct inode *tracefs_alloc_inode(struct super_block *sb)
 	if (!ti)
 		return NULL;
 
-	ti->flags = 0;
-
 	return &ti->vfs_inode;
 }
 
@@ -91,6 +89,7 @@ static int tracefs_syscall_mkdir(struct mnt_idmap *idmap,
 				 struct inode *inode, struct dentry *dentry,
 				 umode_t mode)
 {
+	struct tracefs_inode *ti;
 	char *name;
 	int ret;
 
@@ -99,6 +98,15 @@ static int tracefs_syscall_mkdir(struct mnt_idmap *idmap,
 		return -ENOMEM;
 
 	/*
+	 * This is a new directory that does not take the default of
+	 * the rootfs. It becomes the default permissions for all the
+	 * files and directories underneath it.
+	 */
+	ti = get_tracefs(inode);
+	ti->flags |= TRACEFS_INSTANCE_INODE;
+	ti->private = inode;
+
+	/*
 	 * The mkdir call can call the generic functions that create
 	 * the files within the tracefs system. It is up to the individual
 	 * mkdir routine to handle races.
@@ -141,10 +149,76 @@ static int tracefs_syscall_rmdir(struct inode *inode, struct dentry *dentry)
 	return ret;
 }
 
-static const struct inode_operations tracefs_dir_inode_operations = {
+static void set_tracefs_inode_owner(struct inode *inode)
+{
+	struct tracefs_inode *ti = get_tracefs(inode);
+	struct inode *root_inode = ti->private;
+
+	/*
+	 * If this inode has never been referenced, then update
+	 * the permissions to the superblock.
+	 */
+	if (!(ti->flags & TRACEFS_UID_PERM_SET))
+		inode->i_uid = root_inode->i_uid;
+
+	if (!(ti->flags & TRACEFS_GID_PERM_SET))
+		inode->i_gid = root_inode->i_gid;
+}
+
+static int tracefs_permission(struct mnt_idmap *idmap,
+			      struct inode *inode, int mask)
+{
+	set_tracefs_inode_owner(inode);
+	return generic_permission(idmap, inode, mask);
+}
+
+static int tracefs_getattr(struct mnt_idmap *idmap,
+			   const struct path *path, struct kstat *stat,
+			   u32 request_mask, unsigned int flags)
+{
+	struct inode *inode = d_backing_inode(path->dentry);
+
+	set_tracefs_inode_owner(inode);
+	generic_fillattr(idmap, request_mask, inode, stat);
+	return 0;
+}
+
+static int tracefs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+			   struct iattr *attr)
+{
+	unsigned int ia_valid = attr->ia_valid;
+	struct inode *inode = d_inode(dentry);
+	struct tracefs_inode *ti = get_tracefs(inode);
+
+	if (ia_valid & ATTR_UID)
+		ti->flags |= TRACEFS_UID_PERM_SET;
+
+	if (ia_valid & ATTR_GID)
+		ti->flags |= TRACEFS_GID_PERM_SET;
+
+	return simple_setattr(idmap, dentry, attr);
+}
+
+static const struct inode_operations tracefs_instance_dir_inode_operations = {
 	.lookup		= simple_lookup,
 	.mkdir		= tracefs_syscall_mkdir,
 	.rmdir		= tracefs_syscall_rmdir,
+	.permission	= tracefs_permission,
+	.getattr	= tracefs_getattr,
+	.setattr	= tracefs_setattr,
+};
+
+static const struct inode_operations tracefs_dir_inode_operations = {
+	.lookup		= simple_lookup,
+	.permission	= tracefs_permission,
+	.getattr	= tracefs_getattr,
+	.setattr	= tracefs_setattr,
+};
+
+static const struct inode_operations tracefs_file_inode_operations = {
+	.permission	= tracefs_permission,
+	.getattr	= tracefs_getattr,
+	.setattr	= tracefs_setattr,
 };
 
 struct inode *tracefs_get_inode(struct super_block *sb)
@@ -183,82 +257,6 @@ struct tracefs_fs_info {
 	struct tracefs_mount_opts mount_opts;
 };
 
-static void change_gid(struct dentry *dentry, kgid_t gid)
-{
-	if (!dentry->d_inode)
-		return;
-	dentry->d_inode->i_gid = gid;
-}
-
-/*
- * Taken from d_walk, but without he need for handling renames.
- * Nothing can be renamed while walking the list, as tracefs
- * does not support renames. This is only called when mounting
- * or remounting the file system, to set all the files to
- * the given gid.
- */
-static void set_gid(struct dentry *parent, kgid_t gid)
-{
-	struct dentry *this_parent, *dentry;
-
-	this_parent = parent;
-	spin_lock(&this_parent->d_lock);
-
-	change_gid(this_parent, gid);
-repeat:
-	dentry = d_first_child(this_parent);
-resume:
-	hlist_for_each_entry_from(dentry, d_sib) {
-		struct tracefs_inode *ti;
-
-		/* Note, getdents() can add a cursor dentry with no inode */
-		if (!dentry->d_inode)
-			continue;
-
-		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
-
-		change_gid(dentry, gid);
-
-		/* If this is the events directory, update that too */
-		ti = get_tracefs(dentry->d_inode);
-		if (ti && (ti->flags & TRACEFS_EVENT_INODE))
-			eventfs_update_gid(dentry, gid);
-
-		if (!hlist_empty(&dentry->d_children)) {
-			spin_unlock(&this_parent->d_lock);
-			spin_release(&dentry->d_lock.dep_map, _RET_IP_);
-			this_parent = dentry;
-			spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_);
-			goto repeat;
-		}
-		spin_unlock(&dentry->d_lock);
-	}
-	/*
-	 * All done at this level ... ascend and resume the search.
-	 */
-	rcu_read_lock();
-ascend:
-	if (this_parent != parent) {
-		dentry = this_parent;
-		this_parent = dentry->d_parent;
-
-		spin_unlock(&dentry->d_lock);
-		spin_lock(&this_parent->d_lock);
-
-		/* go into the first sibling still alive */
-		hlist_for_each_entry_continue(dentry, d_sib) {
-			if (likely(!(dentry->d_flags & DCACHE_DENTRY_KILLED))) {
-				rcu_read_unlock();
-				goto resume;
-			}
-		}
-		goto ascend;
-	}
-	rcu_read_unlock();
-	spin_unlock(&this_parent->d_lock);
-	return;
-}
-
 static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts)
 {
 	substring_t args[MAX_OPT_ARGS];
@@ -331,10 +329,8 @@ static int tracefs_apply_options(struct super_block *sb, bool remount)
 	if (!remount || opts->opts & BIT(Opt_uid))
 		inode->i_uid = opts->uid;
 
-	if (!remount || opts->opts & BIT(Opt_gid)) {
-		/* Set all the group ids to the mount option */
-		set_gid(sb->s_root, opts->gid);
-	}
+	if (!remount || opts->opts & BIT(Opt_gid))
+		inode->i_gid = opts->gid;
 
 	return 0;
 }
@@ -381,21 +377,30 @@ static const struct super_operations tracefs_super_operations = {
 	.show_options	= tracefs_show_options,
 };
 
-static void tracefs_dentry_iput(struct dentry *dentry, struct inode *inode)
+/*
+ * It would be cleaner if eventfs had its own dentry ops.
+ *
+ * Note that d_revalidate is called potentially under RCU,
+ * so it can't take the eventfs mutex etc. It's fine - if
+ * we open a file just as it's marked dead, things will
+ * still work just fine, and just see the old stale case.
+ */
+static void tracefs_d_release(struct dentry *dentry)
 {
-	struct tracefs_inode *ti;
+	if (dentry->d_fsdata)
+		eventfs_d_release(dentry);
+}
 
-	if (!dentry || !inode)
-		return;
+static int tracefs_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct eventfs_inode *ei = dentry->d_fsdata;
 
-	ti = get_tracefs(inode);
-	if (ti && ti->flags & TRACEFS_EVENT_INODE)
-		eventfs_set_ei_status_free(ti, dentry);
-	iput(inode);
+	return !(ei && ei->is_freed);
 }
 
 static const struct dentry_operations tracefs_dentry_operations = {
-	.d_iput = tracefs_dentry_iput,
+	.d_revalidate = tracefs_d_revalidate,
+	.d_release = tracefs_d_release,
 };
 
 static int trace_fill_super(struct super_block *sb, void *data, int silent)
@@ -499,73 +504,24 @@ struct dentry *tracefs_end_creating(struct dentry *dentry)
 	return dentry;
 }
 
-/**
- * eventfs_start_creating - start the process of creating a dentry
- * @name: Name of the file created for the dentry
- * @parent: The parent dentry where this dentry will be created
- *
- * This is a simple helper function for the dynamically created eventfs
- * files. When the directory of the eventfs files are accessed, their
- * dentries are created on the fly. This function is used to start that
- * process.
- */
-struct dentry *eventfs_start_creating(const char *name, struct dentry *parent)
+/* Find the inode that this will use for default */
+static struct inode *instance_inode(struct dentry *parent, struct inode *inode)
 {
-	struct dentry *dentry;
-	int error;
-
-	/* Must always have a parent. */
-	if (WARN_ON_ONCE(!parent))
-		return ERR_PTR(-EINVAL);
-
-	error = simple_pin_fs(&trace_fs_type, &tracefs_mount,
-			      &tracefs_mount_count);
-	if (error)
-		return ERR_PTR(error);
+	struct tracefs_inode *ti;
 
-	if (unlikely(IS_DEADDIR(parent->d_inode)))
-		dentry = ERR_PTR(-ENOENT);
-	else
-		dentry = lookup_one_len(name, parent, strlen(name));
+	/* If parent is NULL then use root inode */
+	if (!parent)
+		return d_inode(inode->i_sb->s_root);
 
-	if (!IS_ERR(dentry) && dentry->d_inode) {
-		dput(dentry);
-		dentry = ERR_PTR(-EEXIST);
+	/* Find the inode that is flagged as an instance or the root inode */
+	while (!IS_ROOT(parent)) {
+		ti = get_tracefs(d_inode(parent));
+		if (ti->flags & TRACEFS_INSTANCE_INODE)
+			break;
+		parent = parent->d_parent;
 	}
 
-	if (IS_ERR(dentry))
-		simple_release_fs(&tracefs_mount, &tracefs_mount_count);
-
-	return dentry;
-}
-
-/**
- * eventfs_failed_creating - clean up a failed eventfs dentry creation
- * @dentry: The dentry to clean up
- *
- * If after calling eventfs_start_creating(), a failure is detected, the
- * resources created by eventfs_start_creating() needs to be cleaned up. In
- * that case, this function should be called to perform that clean up.
- */
-struct dentry *eventfs_failed_creating(struct dentry *dentry)
-{
-	dput(dentry);
-	simple_release_fs(&tracefs_mount, &tracefs_mount_count);
-	return NULL;
-}
-
-/**
- * eventfs_end_creating - Finish the process of creating a eventfs dentry
- * @dentry: The dentry that has successfully been created.
- *
- * This function is currently just a place holder to match
- * eventfs_start_creating(). In case any synchronization needs to be added,
- * this function will be used to implement that without having to modify
- * the callers of eventfs_start_creating().
- */
-struct dentry *eventfs_end_creating(struct dentry *dentry)
-{
-	return dentry;
+	return d_inode(parent);
 }
 
 /**
@@ -598,6 +554,7 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode,
 				   struct dentry *parent, void *data,
 				   const struct file_operations *fops)
 {
+	struct tracefs_inode *ti;
 	struct dentry *dentry;
 	struct inode *inode;
 
@@ -616,7 +573,11 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode,
 	if (unlikely(!inode))
 		return tracefs_failed_creating(dentry);
 
+	ti = get_tracefs(inode);
+	ti->private = instance_inode(parent, inode);
+
 	inode->i_mode = mode;
+	inode->i_op = &tracefs_file_inode_operations;
 	inode->i_fop = fops ? fops : &tracefs_file_operations;
 	inode->i_private = data;
 	inode->i_uid = d_inode(dentry->d_parent)->i_uid;
@@ -629,6 +590,7 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode,
 static struct dentry *__create_dir(const char *name, struct dentry *parent,
 				   const struct inode_operations *ops)
 {
+	struct tracefs_inode *ti;
 	struct dentry *dentry = tracefs_start_creating(name, parent);
 	struct inode *inode;
 
@@ -646,6 +608,9 @@ static struct dentry *__create_dir(const char *name, struct dentry *parent,
 	inode->i_uid = d_inode(dentry->d_parent)->i_uid;
 	inode->i_gid = d_inode(dentry->d_parent)->i_gid;
 
+	ti = get_tracefs(inode);
+	ti->private = instance_inode(parent, inode);
+
 	/* directory inodes start off with i_nlink == 2 (for "." entry) */
 	inc_nlink(inode);
 	d_instantiate(dentry, inode);
@@ -676,7 +641,7 @@ struct dentry *tracefs_create_dir(const char *name, struct dentry *parent)
 	if (security_locked_down(LOCKDOWN_TRACEFS))
 		return NULL;
 
-	return __create_dir(name, parent, &simple_dir_inode_operations);
+	return __create_dir(name, parent, &tracefs_dir_inode_operations);
 }
 
 /**
@@ -707,7 +672,7 @@ __init struct dentry *tracefs_create_instance_dir(const char *name,
 	if (WARN_ON(tracefs_ops.mkdir || tracefs_ops.rmdir))
 		return NULL;
 
-	dentry = __create_dir(name, parent, &tracefs_dir_inode_operations);
+	dentry = __create_dir(name, parent, &tracefs_instance_dir_inode_operations);
 	if (!dentry)
 		return NULL;
 
@@ -752,7 +717,11 @@ static void init_once(void *foo)
 {
 	struct tracefs_inode *ti = (struct tracefs_inode *) foo;
 
+	/* inode_init_once() calls memset() on the vfs_inode portion */
 	inode_init_once(&ti->vfs_inode);
+
+	/* Zero out the rest */
+	memset_after(ti, 0, vfs_inode);
 }
 
 static int __init tracefs_init(void)
diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
index 42bdeb471a07..beb3dcd0e434 100644
--- a/fs/tracefs/internal.h
+++ b/fs/tracefs/internal.h
@@ -5,12 +5,16 @@
 enum {
 	TRACEFS_EVENT_INODE		= BIT(1),
 	TRACEFS_EVENT_TOP_INODE		= BIT(2),
+	TRACEFS_GID_PERM_SET		= BIT(3),
+	TRACEFS_UID_PERM_SET		= BIT(4),
+	TRACEFS_INSTANCE_INODE		= BIT(5),
 };
 
 struct tracefs_inode {
+	struct inode            vfs_inode;
+	/* The below gets initialized with memset_after(ti, 0, vfs_inode) */
 	unsigned long           flags;
 	void                    *private;
-	struct inode            vfs_inode;
 };
 
 /*
@@ -28,42 +32,37 @@ struct eventfs_attr {
 /*
  * struct eventfs_inode - hold the properties of the eventfs directories.
  * @list:	link list into the parent directory
+ * @rcu:	Union with @list for freeing
+ * @children:	link list into the child eventfs_inode
  * @entries:	the array of entries representing the files in the directory
  * @name:	the name of the directory to create
- * @children:	link list into the child eventfs_inode
- * @dentry:     the dentry of the directory
- * @d_parent:   pointer to the parent's dentry
- * @d_children: The array of dentries to represent the files when created
+ * @events_dir: the dentry of the events directory
  * @entry_attrs: Saved mode and ownership of the @d_children
- * @attr:	Saved mode and ownership of eventfs_inode itself
  * @data:	The private data to pass to the callbacks
+ * @attr:	Saved mode and ownership of eventfs_inode itself
  * @is_freed:	Flag set if the eventfs is on its way to be freed
  *                Note if is_freed is set, then dentry is corrupted.
+ * @is_events:	Flag set for only the top level "events" directory
  * @nr_entries: The number of items in @entries
+ * @ino:	The saved inode number
  */
 struct eventfs_inode {
-	struct list_head		list;
+	union {
+		struct list_head	list;
+		struct rcu_head		rcu;
+	};
+	struct list_head		children;
 	const struct eventfs_entry	*entries;
 	const char			*name;
-	struct list_head		children;
-	struct dentry			*dentry; /* Check is_freed to access */
-	struct dentry			*d_parent;
-	struct dentry			**d_children;
+	struct dentry			*events_dir;
 	struct eventfs_attr		*entry_attrs;
-	struct eventfs_attr		attr;
 	void				*data;
-	/*
-	 * Union - used for deletion
-	 * @llist:	for calling dput() if needed after RCU
-	 * @rcu:	eventfs_inode to delete in RCU
-	 */
-	union {
-		struct llist_node	llist;
-		struct rcu_head		rcu;
-	};
+	struct eventfs_attr		attr;
+	struct kref			kref;
 	unsigned int			is_freed:1;
 	unsigned int			is_events:1;
 	unsigned int			nr_entries:30;
+	unsigned int			ino;
 };
 
 static inline struct tracefs_inode *get_tracefs(const struct inode *inode)
@@ -75,10 +74,7 @@ struct dentry *tracefs_start_creating(const char *name, struct dentry *parent);
 struct dentry *tracefs_end_creating(struct dentry *dentry);
 struct dentry *tracefs_failed_creating(struct dentry *dentry);
 struct inode *tracefs_get_inode(struct super_block *sb);
-struct dentry *eventfs_start_creating(const char *name, struct dentry *parent);
-struct dentry *eventfs_failed_creating(struct dentry *dentry);
-struct dentry *eventfs_end_creating(struct dentry *dentry);
-void eventfs_update_gid(struct dentry *dentry, kgid_t gid);
-void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry);
+
+void eventfs_d_release(struct dentry *dentry);
 
 #endif /* _TRACEFS_INTERNAL_H */
diff --git a/fs/ubifs/auth.c b/fs/ubifs/auth.c
index 0d561ecb6869..a4a0158f712d 100644
--- a/fs/ubifs/auth.c
+++ b/fs/ubifs/auth.c
@@ -18,7 +18,7 @@
 #include "ubifs.h"
 
 /**
- * ubifs_node_calc_hash - calculate the hash of a UBIFS node
+ * __ubifs_node_calc_hash - calculate the hash of a UBIFS node
  * @c: UBIFS file-system description object
  * @node: the node to calculate a hash for
  * @hash: the returned hash
@@ -507,28 +507,13 @@ out:
  */
 int ubifs_hmac_wkm(struct ubifs_info *c, u8 *hmac)
 {
-	SHASH_DESC_ON_STACK(shash, c->hmac_tfm);
-	int err;
 	const char well_known_message[] = "UBIFS";
 
 	if (!ubifs_authenticated(c))
 		return 0;
 
-	shash->tfm = c->hmac_tfm;
-
-	err = crypto_shash_init(shash);
-	if (err)
-		return err;
-
-	err = crypto_shash_update(shash, well_known_message,
-				  sizeof(well_known_message) - 1);
-	if (err < 0)
-		return err;
-
-	err = crypto_shash_final(shash, hmac);
-	if (err)
-		return err;
-	return 0;
+	return crypto_shash_tfm_digest(c->hmac_tfm, well_known_message,
+				       sizeof(well_known_message) - 1, hmac);
 }
 
 /*
diff --git a/fs/ubifs/commit.c b/fs/ubifs/commit.c
index c4fc1047fc07..5b3a840098b0 100644
--- a/fs/ubifs/commit.c
+++ b/fs/ubifs/commit.c
@@ -70,18 +70,29 @@ static int nothing_to_commit(struct ubifs_info *c)
 		return 0;
 
 	/*
+	 * Increasing @c->dirty_pn_cnt/@c->dirty_nn_cnt and marking
+	 * nnodes/pnodes as dirty in run_gc() could race with following
+	 * checking, which leads inconsistent states between @c->nroot
+	 * and @c->dirty_pn_cnt/@c->dirty_nn_cnt, holding @c->lp_mutex
+	 * to avoid that.
+	 */
+	mutex_lock(&c->lp_mutex);
+	/*
 	 * Even though the TNC is clean, the LPT tree may have dirty nodes. For
 	 * example, this may happen if the budgeting subsystem invoked GC to
 	 * make some free space, and the GC found an LEB with only dirty and
 	 * free space. In this case GC would just change the lprops of this
 	 * LEB (by turning all space into free space) and unmap it.
 	 */
-	if (c->nroot && test_bit(DIRTY_CNODE, &c->nroot->flags))
+	if (c->nroot && test_bit(DIRTY_CNODE, &c->nroot->flags)) {
+		mutex_unlock(&c->lp_mutex);
 		return 0;
+	}
 
 	ubifs_assert(c, atomic_long_read(&c->dirty_zn_cnt) == 0);
 	ubifs_assert(c, c->dirty_pn_cnt == 0);
 	ubifs_assert(c, c->dirty_nn_cnt == 0);
+	mutex_unlock(&c->lp_mutex);
 
 	return 1;
 }
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 3b13c648d490..551148de66cd 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -205,7 +205,6 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
 	dbg_gen("'%pd' in dir ino %lu", dentry, dir->i_ino);
 
 	err = fscrypt_prepare_lookup(dir, dentry, &nm);
-	generic_set_encrypted_ci_d_ops(dentry);
 	if (err == -ENOENT)
 		return d_splice_alias(NULL, dentry);
 	if (err)
@@ -1234,6 +1233,8 @@ out_cancel:
 	dir_ui->ui_size = dir->i_size;
 	mutex_unlock(&dir_ui->ui_mutex);
 out_inode:
+	/* Free inode->i_link before inode is marked as bad. */
+	fscrypt_free_inode(inode);
 	make_bad_inode(inode);
 	iput(inode);
 out_fname:
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 2d2b39f843ce..5029eb3390a5 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -318,8 +318,9 @@ static int write_begin_slow(struct address_space *mapping,
  * This is a helper function for 'ubifs_write_begin()' which allocates budget
  * for the operation. The budget is allocated differently depending on whether
  * this is appending, whether the page is dirty or not, and so on. This
- * function leaves the @ui->ui_mutex locked in case of appending. Returns zero
- * in case of success and %-ENOSPC in case of failure.
+ * function leaves the @ui->ui_mutex locked in case of appending.
+ *
+ * Returns: %0 in case of success and %-ENOSPC in case of failure.
  */
 static int allocate_budget(struct ubifs_info *c, struct page *page,
 			   struct ubifs_inode *ui, int appending)
@@ -600,7 +601,7 @@ out:
  * @bu: bulk-read information
  * @n: next zbranch slot
  *
- * This function returns %0 on success and a negative error code on failure.
+ * Returns: %0 on success and a negative error code on failure.
  */
 static int populate_page(struct ubifs_info *c, struct page *page,
 			 struct bu_info *bu, int *n)
@@ -711,7 +712,7 @@ out_err:
  * @bu: bulk-read information
  * @page1: first page to read
  *
- * This function returns %1 if the bulk-read is done, otherwise %0 is returned.
+ * Returns: %1 if the bulk-read is done, otherwise %0 is returned.
  */
 static int ubifs_do_bulk_read(struct ubifs_info *c, struct bu_info *bu,
 			      struct page *page1)
@@ -821,7 +822,9 @@ out_bu_off:
  * Some flash media are capable of reading sequentially at faster rates. UBIFS
  * bulk-read facility is designed to take advantage of that, by reading in one
  * go consecutive data nodes that are also located consecutively in the same
- * LEB. This function returns %1 if a bulk-read is done and %0 otherwise.
+ * LEB.
+ *
+ * Returns: %1 if a bulk-read is done and %0 otherwise.
  */
 static int ubifs_bulk_read(struct page *page)
 {
@@ -1109,7 +1112,9 @@ static void do_attr_changes(struct inode *inode, const struct iattr *attr)
  * @attr: inode attribute changes description
  *
  * This function implements VFS '->setattr()' call when the inode is truncated
- * to a smaller size. Returns zero in case of success and a negative error code
+ * to a smaller size.
+ *
+ * Returns: %0 in case of success and a negative error code
  * in case of failure.
  */
 static int do_truncation(struct ubifs_info *c, struct inode *inode,
@@ -1215,7 +1220,9 @@ out_budg:
  * @attr: inode attribute changes description
  *
  * This function implements VFS '->setattr()' call for all cases except
- * truncations to smaller size. Returns zero in case of success and a negative
+ * truncations to smaller size.
+ *
+ * Returns: %0 in case of success and a negative
  * error code in case of failure.
  */
 static int do_setattr(struct ubifs_info *c, struct inode *inode,
@@ -1360,6 +1367,8 @@ out:
  * This helper function checks if the inode mtime/ctime should be updated or
  * not. If current values of the time-stamps are within the UBIFS inode time
  * granularity, they are not updated. This is an optimization.
+ *
+ * Returns: %1 if time update is needed, %0 if not
  */
 static inline int mctime_update_needed(const struct inode *inode,
 				       const struct timespec64 *now)
@@ -1375,11 +1384,12 @@ static inline int mctime_update_needed(const struct inode *inode,
 /**
  * ubifs_update_time - update time of inode.
  * @inode: inode to update
- * @time:  timespec structure to hold the current time value
  * @flags: time updating control flag determines updating
  *	    which time fields of @inode
  *
  * This function updates time of the inode.
+ *
+ * Returns: %0 for success or a negative error code otherwise.
  */
 int ubifs_update_time(struct inode *inode, int flags)
 {
@@ -1413,7 +1423,9 @@ int ubifs_update_time(struct inode *inode, int flags)
  * @inode: inode to update
  *
  * This function updates mtime and ctime of the inode if it is not equivalent to
- * current time. Returns zero in case of success and a negative error code in
+ * current time.
+ *
+ * Returns: %0 in case of success and a negative error code in
  * case of failure.
  */
 static int update_mctime(struct inode *inode)
diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c
index c59d47fe7939..17da28d6247a 100644
--- a/fs/ubifs/replay.c
+++ b/fs/ubifs/replay.c
@@ -365,6 +365,7 @@ static void destroy_replay_list(struct ubifs_info *c)
  * @lnum: node logical eraseblock number
  * @offs: node offset
  * @len: node length
+ * @hash: node hash
  * @key: node key
  * @sqnum: sequence number
  * @deletion: non-zero if this is a deletion
@@ -417,6 +418,7 @@ static int insert_node(struct ubifs_info *c, int lnum, int offs, int len,
  * @lnum: node logical eraseblock number
  * @offs: node offset
  * @len: node length
+ * @hash: node hash
  * @key: node key
  * @name: directory entry name
  * @nlen: directory entry name length
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 09e270d6ed02..d2881041b393 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -2239,13 +2239,14 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
 		goto out_umount;
 	}
 
+	generic_set_sb_d_ops(sb);
 	sb->s_root = d_make_root(root);
 	if (!sb->s_root) {
 		err = -ENOMEM;
 		goto out_umount;
 	}
 
-	import_uuid(&sb->s_uuid, c->uuid);
+	super_set_uuid(sb, c->uuid, sizeof(c->uuid));
 
 	mutex_unlock(&c->umount_mutex);
 	return 0;
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 4fcefe5ef7cb..959551ff9a95 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1032,7 +1032,7 @@ static int resolve_userfault_fork(struct userfaultfd_ctx *new,
 {
 	int fd;
 
-	fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, new,
+	fd = anon_inode_create_getfd("[userfaultfd]", &userfaultfd_fops, new,
 			O_RDONLY | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode);
 	if (fd < 0)
 		return fd;
@@ -2260,7 +2260,8 @@ static int new_userfaultfd(int flags)
 	/* prevent the mm struct to be freed */
 	mmgrab(ctx->mm);
 
-	fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, ctx,
+	/* Create a new inode so that the LSM can block the creation.  */
+	fd = anon_inode_create_getfd("[userfaultfd]", &userfaultfd_fops, ctx,
 			O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL);
 	if (fd < 0) {
 		mmdrop(ctx->mm);
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 9976a00a73f9..e965a48e7db9 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -421,10 +421,10 @@ xfs_attr_complete_op(
 	bool			do_replace = args->op_flags & XFS_DA_OP_REPLACE;
 
 	args->op_flags &= ~XFS_DA_OP_REPLACE;
-	if (do_replace) {
-		args->attr_filter &= ~XFS_ATTR_INCOMPLETE;
+	args->attr_filter &= ~XFS_ATTR_INCOMPLETE;
+	if (do_replace)
 		return replace_state;
-	}
+
 	return XFS_DAS_DONE;
 }
 
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 98aaca933bdd..f362345467fa 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3277,7 +3277,7 @@ xfs_bmap_alloc_account(
 	struct xfs_bmalloca	*ap)
 {
 	bool			isrt = XFS_IS_REALTIME_INODE(ap->ip) &&
-					(ap->flags & XFS_BMAPI_ATTRFORK);
+					!(ap->flags & XFS_BMAPI_ATTRFORK);
 	uint			fld;
 
 	if (ap->flags & XFS_BMAPI_COWFORK) {
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 31100120b2c5..e31663cb7b43 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -1119,20 +1119,6 @@ xfs_rtbitmap_blockcount(
 }
 
 /*
- * Compute the maximum level number of the realtime summary file, as defined by
- * mkfs.  The historic use of highbit32 on a 64-bit quantity prohibited correct
- * use of rt volumes with more than 2^32 extents.
- */
-uint8_t
-xfs_compute_rextslog(
-	xfs_rtbxlen_t		rtextents)
-{
-	if (!rtextents)
-		return 0;
-	return xfs_highbit64(rtextents);
-}
-
-/*
  * Compute the number of rtbitmap words needed to populate every block of a
  * bitmap that is large enough to track the given number of rt extents.
  */
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h
index 274dc7dae1fa..152a66750af5 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.h
+++ b/fs/xfs/libxfs/xfs_rtbitmap.h
@@ -351,20 +351,6 @@ xfs_rtfree_extent(
 int xfs_rtfree_blocks(struct xfs_trans *tp, xfs_fsblock_t rtbno,
 		xfs_filblks_t rtlen);
 
-uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents);
-
-/* Do we support an rt volume having this number of rtextents? */
-static inline bool
-xfs_validate_rtextents(
-	xfs_rtbxlen_t		rtextents)
-{
-	/* No runt rt volumes */
-	if (rtextents == 0)
-		return false;
-
-	return true;
-}
-
 xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t
 		rtextents);
 unsigned long long xfs_rtbitmap_wordcount(struct xfs_mount *mp,
@@ -383,8 +369,6 @@ unsigned long long xfs_rtsummary_wordcount(struct xfs_mount *mp,
 # define xfs_rtsummary_read_buf(a,b)			(-ENOSYS)
 # define xfs_rtbuf_cache_relse(a)			(0)
 # define xfs_rtalloc_extent_is_free(m,t,s,l,i)		(-ENOSYS)
-# define xfs_compute_rextslog(rtx)			(0)
-# define xfs_validate_rtextents(rtx)			(false)
 static inline xfs_filblks_t
 xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t rtextents)
 {
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 4a9e8588f4c9..5bb6e2bd6dee 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -1377,3 +1377,17 @@ xfs_validate_stripe_geometry(
 	}
 	return true;
 }
+
+/*
+ * Compute the maximum level number of the realtime summary file, as defined by
+ * mkfs.  The historic use of highbit32 on a 64-bit quantity prohibited correct
+ * use of rt volumes with more than 2^32 extents.
+ */
+uint8_t
+xfs_compute_rextslog(
+	xfs_rtbxlen_t		rtextents)
+{
+	if (!rtextents)
+		return 0;
+	return xfs_highbit64(rtextents);
+}
diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h
index 19134b23c10b..2e8e8d63d4eb 100644
--- a/fs/xfs/libxfs/xfs_sb.h
+++ b/fs/xfs/libxfs/xfs_sb.h
@@ -38,4 +38,6 @@ extern int	xfs_sb_get_secondary(struct xfs_mount *mp,
 extern bool	xfs_validate_stripe_geometry(struct xfs_mount *mp,
 		__s64 sunit, __s64 swidth, int sectorsize, bool silent);
 
+uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents);
+
 #endif	/* __XFS_SB_H__ */
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index 20b5375f2d9c..62e02d5380ad 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -251,4 +251,16 @@ bool xfs_verify_fileoff(struct xfs_mount *mp, xfs_fileoff_t off);
 bool xfs_verify_fileext(struct xfs_mount *mp, xfs_fileoff_t off,
 		xfs_fileoff_t len);
 
+/* Do we support an rt volume having this number of rtextents? */
+static inline bool
+xfs_validate_rtextents(
+	xfs_rtbxlen_t		rtextents)
+{
+	/* No runt rt volumes */
+	if (rtextents == 0)
+		return false;
+
+	return true;
+}
+
 #endif	/* __XFS_TYPES_H__ */
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index 441ca9977652..46583517377f 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -15,6 +15,7 @@
 #include "xfs_inode.h"
 #include "xfs_bmap.h"
 #include "xfs_bit.h"
+#include "xfs_sb.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/repair.h"
diff --git a/fs/xfs/scrub/rtsummary.c b/fs/xfs/scrub/rtsummary.c
index fabd0ed9dfa6..b1ff4f33324a 100644
--- a/fs/xfs/scrub/rtsummary.c
+++ b/fs/xfs/scrub/rtsummary.c
@@ -16,6 +16,7 @@
 #include "xfs_rtbitmap.h"
 #include "xfs_bit.h"
 #include "xfs_bmap.h"
+#include "xfs_sb.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 813f85156b0c..1698507d1ac7 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -112,7 +112,7 @@ xfs_end_ioend(
 	 * longer dirty. If we don't remove delalloc blocks here, they become
 	 * stale and can corrupt free space accounting on unmount.
 	 */
-	error = blk_status_to_errno(ioend->io_bio->bi_status);
+	error = blk_status_to_errno(ioend->io_bio.bi_status);
 	if (unlikely(error)) {
 		if (ioend->io_flags & IOMAP_F_SHARED) {
 			xfs_reflink_cancel_cow_range(ip, offset, size, true);
@@ -179,7 +179,7 @@ STATIC void
 xfs_end_bio(
 	struct bio		*bio)
 {
-	struct iomap_ioend	*ioend = bio->bi_private;
+	struct iomap_ioend	*ioend = iomap_ioend_from_bio(bio);
 	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
 	unsigned long		flags;
 
@@ -276,7 +276,8 @@ static int
 xfs_map_blocks(
 	struct iomap_writepage_ctx *wpc,
 	struct inode		*inode,
-	loff_t			offset)
+	loff_t			offset,
+	unsigned int		len)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
@@ -444,7 +445,7 @@ xfs_prepare_ioend(
 	/* send ioends that might require a transaction to the completion wq */
 	if (xfs_ioend_is_append(ioend) || ioend->io_type == IOMAP_UNWRITTEN ||
 	    (ioend->io_flags & IOMAP_F_SHARED))
-		ioend->io_bio->bi_end_io = xfs_end_bio;
+		ioend->io_bio.bi_end_io = xfs_end_bio;
 	return status;
 }
 
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 8e5bd50d29fe..01b41fabbe3c 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1951,7 +1951,7 @@ xfs_free_buftarg(
 	fs_put_dax(btp->bt_daxdev, btp->bt_mount);
 	/* the main block device is closed by kill_block_super */
 	if (btp->bt_bdev != btp->bt_mount->m_super->s_bdev)
-		bdev_release(btp->bt_bdev_handle);
+		fput(btp->bt_bdev_file);
 
 	kmem_free(btp);
 }
@@ -1994,7 +1994,7 @@ xfs_setsize_buftarg_early(
 struct xfs_buftarg *
 xfs_alloc_buftarg(
 	struct xfs_mount	*mp,
-	struct bdev_handle	*bdev_handle)
+	struct file		*bdev_file)
 {
 	xfs_buftarg_t		*btp;
 	const struct dax_holder_operations *ops = NULL;
@@ -2005,9 +2005,9 @@ xfs_alloc_buftarg(
 	btp = kmem_zalloc(sizeof(*btp), KM_NOFS);
 
 	btp->bt_mount = mp;
-	btp->bt_bdev_handle = bdev_handle;
-	btp->bt_dev = bdev_handle->bdev->bd_dev;
-	btp->bt_bdev = bdev_handle->bdev;
+	btp->bt_bdev_file = bdev_file;
+	btp->bt_bdev = file_bdev(bdev_file);
+	btp->bt_dev = btp->bt_bdev->bd_dev;
 	btp->bt_daxdev = fs_dax_get_by_bdev(btp->bt_bdev, &btp->bt_dax_part_off,
 					    mp, ops);
 
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index b470de08a46c..304e858d04fb 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -98,7 +98,7 @@ typedef unsigned int xfs_buf_flags_t;
  */
 typedef struct xfs_buftarg {
 	dev_t			bt_dev;
-	struct bdev_handle	*bt_bdev_handle;
+	struct file		*bt_bdev_file;
 	struct block_device	*bt_bdev;
 	struct dax_device	*bt_daxdev;
 	u64			bt_dax_part_off;
@@ -366,7 +366,7 @@ xfs_buf_update_cksum(struct xfs_buf *bp, unsigned long cksum_offset)
  *	Handling of buftargs.
  */
 struct xfs_buftarg *xfs_alloc_buftarg(struct xfs_mount *mp,
-		struct bdev_handle *bdev_handle);
+		struct file *bdev_file);
 extern void xfs_free_buftarg(struct xfs_buftarg *);
 extern void xfs_buftarg_wait(struct xfs_buftarg *);
 extern void xfs_buftarg_drain(struct xfs_buftarg *);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index aabb25dc3efa..57fa21ad7912 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -62,7 +62,7 @@ xfs_uuid_mount(
 	int			hole, i;
 
 	/* Publish UUID in struct super_block */
-	uuid_copy(&mp->m_super->s_uuid, uuid);
+	super_set_uuid(mp->m_super, uuid->b, sizeof(*uuid));
 
 	if (xfs_has_nouuid(mp))
 		return 0;
@@ -706,6 +706,8 @@ xfs_mountfs(
 	/* enable fail_at_unmount as default */
 	mp->m_fail_unmount = true;
 
+	super_set_sysfs_name_id(mp->m_super);
+
 	error = xfs_sysfs_init(&mp->m_kobj, &xfs_mp_ktype,
 			       NULL, mp->m_super->s_id);
 	if (error)
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index aff20ddd4a9f..00fbd5b6e582 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -350,7 +350,6 @@ xfs_setup_dax_always(
 		return -EINVAL;
 	}
 
-	xfs_warn(mp, "DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
 	return 0;
 
 disable_dax:
@@ -362,16 +361,16 @@ STATIC int
 xfs_blkdev_get(
 	xfs_mount_t		*mp,
 	const char		*name,
-	struct bdev_handle	**handlep)
+	struct file		**bdev_filep)
 {
 	int			error = 0;
 
-	*handlep = bdev_open_by_path(name,
+	*bdev_filep = bdev_file_open_by_path(name,
 		BLK_OPEN_READ | BLK_OPEN_WRITE | BLK_OPEN_RESTRICT_WRITES,
 		mp->m_super, &fs_holder_ops);
-	if (IS_ERR(*handlep)) {
-		error = PTR_ERR(*handlep);
-		*handlep = NULL;
+	if (IS_ERR(*bdev_filep)) {
+		error = PTR_ERR(*bdev_filep);
+		*bdev_filep = NULL;
 		xfs_warn(mp, "Invalid device [%s], error=%d", name, error);
 	}
 
@@ -436,26 +435,26 @@ xfs_open_devices(
 {
 	struct super_block	*sb = mp->m_super;
 	struct block_device	*ddev = sb->s_bdev;
-	struct bdev_handle	*logdev_handle = NULL, *rtdev_handle = NULL;
+	struct file		*logdev_file = NULL, *rtdev_file = NULL;
 	int			error;
 
 	/*
 	 * Open real time and log devices - order is important.
 	 */
 	if (mp->m_logname) {
-		error = xfs_blkdev_get(mp, mp->m_logname, &logdev_handle);
+		error = xfs_blkdev_get(mp, mp->m_logname, &logdev_file);
 		if (error)
 			return error;
 	}
 
 	if (mp->m_rtname) {
-		error = xfs_blkdev_get(mp, mp->m_rtname, &rtdev_handle);
+		error = xfs_blkdev_get(mp, mp->m_rtname, &rtdev_file);
 		if (error)
 			goto out_close_logdev;
 
-		if (rtdev_handle->bdev == ddev ||
-		    (logdev_handle &&
-		     rtdev_handle->bdev == logdev_handle->bdev)) {
+		if (file_bdev(rtdev_file) == ddev ||
+		    (logdev_file &&
+		     file_bdev(rtdev_file) == file_bdev(logdev_file))) {
 			xfs_warn(mp,
 	"Cannot mount filesystem with identical rtdev and ddev/logdev.");
 			error = -EINVAL;
@@ -467,25 +466,25 @@ xfs_open_devices(
 	 * Setup xfs_mount buffer target pointers
 	 */
 	error = -ENOMEM;
-	mp->m_ddev_targp = xfs_alloc_buftarg(mp, sb->s_bdev_handle);
+	mp->m_ddev_targp = xfs_alloc_buftarg(mp, sb->s_bdev_file);
 	if (!mp->m_ddev_targp)
 		goto out_close_rtdev;
 
-	if (rtdev_handle) {
-		mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev_handle);
+	if (rtdev_file) {
+		mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev_file);
 		if (!mp->m_rtdev_targp)
 			goto out_free_ddev_targ;
 	}
 
-	if (logdev_handle && logdev_handle->bdev != ddev) {
-		mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev_handle);
+	if (logdev_file && file_bdev(logdev_file) != ddev) {
+		mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev_file);
 		if (!mp->m_logdev_targp)
 			goto out_free_rtdev_targ;
 	} else {
 		mp->m_logdev_targp = mp->m_ddev_targp;
 		/* Handle won't be used, drop it */
-		if (logdev_handle)
-			bdev_release(logdev_handle);
+		if (logdev_file)
+			fput(logdev_file);
 	}
 
 	return 0;
@@ -496,11 +495,11 @@ xfs_open_devices(
  out_free_ddev_targ:
 	xfs_free_buftarg(mp->m_ddev_targp);
  out_close_rtdev:
-	 if (rtdev_handle)
-		bdev_release(rtdev_handle);
+	 if (rtdev_file)
+		fput(rtdev_file);
  out_close_logdev:
-	if (logdev_handle)
-		bdev_release(logdev_handle);
+	if (logdev_file)
+		fput(logdev_file);
 	return error;
 }
 
@@ -1496,6 +1495,18 @@ xfs_fs_fill_super(
 
 	mp->m_super = sb;
 
+	/*
+	 * Copy VFS mount flags from the context now that all parameter parsing
+	 * is guaranteed to have been completed by either the old mount API or
+	 * the newer fsopen/fsconfig API.
+	 */
+	if (fc->sb_flags & SB_RDONLY)
+		set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate);
+	if (fc->sb_flags & SB_DIRSYNC)
+		mp->m_features |= XFS_FEAT_DIRSYNC;
+	if (fc->sb_flags & SB_SYNCHRONOUS)
+		mp->m_features |= XFS_FEAT_WSYNC;
+
 	error = xfs_fs_validate_params(mp);
 	if (error)
 		return error;
@@ -1965,6 +1976,11 @@ static const struct fs_context_operations xfs_context_ops = {
 	.free        = xfs_fs_free,
 };
 
+/*
+ * WARNING: do not initialise any parameters in this function that depend on
+ * mount option parsing having already been performed as this can be called from
+ * fsopen() before any parameters have been set.
+ */
 static int xfs_init_fs_context(
 	struct fs_context	*fc)
 {
@@ -1996,16 +2012,6 @@ static int xfs_init_fs_context(
 	mp->m_logbsize = -1;
 	mp->m_allocsize_log = 16; /* 64k */
 
-	/*
-	 * Copy binary VFS mount flags we are interested in.
-	 */
-	if (fc->sb_flags & SB_RDONLY)
-		set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate);
-	if (fc->sb_flags & SB_DIRSYNC)
-		mp->m_features |= XFS_FEAT_DIRSYNC;
-	if (fc->sb_flags & SB_SYNCHRONOUS)
-		mp->m_features |= XFS_FEAT_WSYNC;
-
 	fc->s_fs_info = mp;
 	fc->ops = &xfs_context_ops;
 
diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c
index 6ab2318a9c8e..3b103715acc9 100644
--- a/fs/zonefs/file.c
+++ b/fs/zonefs/file.c
@@ -125,7 +125,8 @@ static void zonefs_readahead(struct readahead_control *rac)
  * which implies that the page range can only be within the fixed inode size.
  */
 static int zonefs_write_map_blocks(struct iomap_writepage_ctx *wpc,
-				   struct inode *inode, loff_t offset)
+				   struct inode *inode, loff_t offset,
+				   unsigned int len)
 {
 	struct zonefs_zone *z = zonefs_inode_zone(inode);
 
@@ -348,7 +349,12 @@ static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size,
 	struct zonefs_inode_info *zi = ZONEFS_I(inode);
 
 	if (error) {
-		zonefs_io_error(inode, true);
+		/*
+		 * For Sync IOs, error recovery is called from
+		 * zonefs_file_dio_write().
+		 */
+		if (!is_sync_kiocb(iocb))
+			zonefs_io_error(inode, true);
 		return error;
 	}
 
@@ -491,6 +497,14 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 			ret = -EINVAL;
 			goto inode_unlock;
 		}
+		/*
+		 * Advance the zone write pointer offset. This assumes that the
+		 * IO will succeed, which is OK to do because we do not allow
+		 * partial writes (IOMAP_DIO_PARTIAL is not set) and if the IO
+		 * fails, the error path will correct the write pointer offset.
+		 */
+		z->z_wpoffset += count;
+		zonefs_inode_account_active(inode);
 		mutex_unlock(&zi->i_truncate_mutex);
 	}
 
@@ -504,20 +518,19 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 	if (ret == -ENOTBLK)
 		ret = -EBUSY;
 
-	if (zonefs_zone_is_seq(z) &&
-	    (ret > 0 || ret == -EIOCBQUEUED)) {
-		if (ret > 0)
-			count = ret;
-
-		/*
-		 * Update the zone write pointer offset assuming the write
-		 * operation succeeded. If it did not, the error recovery path
-		 * will correct it. Also do active seq file accounting.
-		 */
-		mutex_lock(&zi->i_truncate_mutex);
-		z->z_wpoffset += count;
-		zonefs_inode_account_active(inode);
-		mutex_unlock(&zi->i_truncate_mutex);
+	/*
+	 * For a failed IO or partial completion, trigger error recovery
+	 * to update the zone write pointer offset to a correct value.
+	 * For asynchronous IOs, zonefs_file_write_dio_end_io() may already
+	 * have executed error recovery if the IO already completed when we
+	 * reach here. However, we cannot know that and execute error recovery
+	 * again (that will not change anything).
+	 */
+	if (zonefs_zone_is_seq(z)) {
+		if (ret > 0 && ret != count)
+			ret = -EIO;
+		if (ret < 0 && ret != -EIOCBQUEUED)
+			zonefs_io_error(inode, true);
 	}
 
 inode_unlock:
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 93971742613a..aadad16738df 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -113,7 +113,7 @@ static int zonefs_zone_mgmt(struct super_block *sb,
 
 	trace_zonefs_zone_mgmt(sb, z, op);
 	ret = blkdev_zone_mgmt(sb->s_bdev, op, z->z_sector,
-			       z->z_size >> SECTOR_SHIFT, GFP_NOFS);
+			       z->z_size >> SECTOR_SHIFT);
 	if (ret) {
 		zonefs_err(sb,
 			   "Zone management operation %s at %llu failed %d\n",
@@ -246,16 +246,18 @@ static void zonefs_inode_update_mode(struct inode *inode)
 	z->z_mode = inode->i_mode;
 }
 
-struct zonefs_ioerr_data {
-	struct inode	*inode;
-	bool		write;
-};
-
 static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 			      void *data)
 {
-	struct zonefs_ioerr_data *err = data;
-	struct inode *inode = err->inode;
+	struct blk_zone *z = data;
+
+	*z = *zone;
+	return 0;
+}
+
+static void zonefs_handle_io_error(struct inode *inode, struct blk_zone *zone,
+				   bool write)
+{
 	struct zonefs_zone *z = zonefs_inode_zone(inode);
 	struct super_block *sb = inode->i_sb;
 	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
@@ -270,8 +272,8 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 	data_size = zonefs_check_zone_condition(sb, z, zone);
 	isize = i_size_read(inode);
 	if (!(z->z_flags & (ZONEFS_ZONE_READONLY | ZONEFS_ZONE_OFFLINE)) &&
-	    !err->write && isize == data_size)
-		return 0;
+	    !write && isize == data_size)
+		return;
 
 	/*
 	 * At this point, we detected either a bad zone or an inconsistency
@@ -292,7 +294,7 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 	 * In all cases, warn about inode size inconsistency and handle the
 	 * IO error according to the zone condition and to the mount options.
 	 */
-	if (zonefs_zone_is_seq(z) && isize != data_size)
+	if (isize != data_size)
 		zonefs_warn(sb,
 			    "inode %lu: invalid size %lld (should be %lld)\n",
 			    inode->i_ino, isize, data_size);
@@ -352,8 +354,6 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 	zonefs_i_size_write(inode, data_size);
 	z->z_wpoffset = data_size;
 	zonefs_inode_account_active(inode);
-
-	return 0;
 }
 
 /*
@@ -367,23 +367,25 @@ void __zonefs_io_error(struct inode *inode, bool write)
 {
 	struct zonefs_zone *z = zonefs_inode_zone(inode);
 	struct super_block *sb = inode->i_sb;
-	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
 	unsigned int noio_flag;
-	unsigned int nr_zones = 1;
-	struct zonefs_ioerr_data err = {
-		.inode = inode,
-		.write = write,
-	};
+	struct blk_zone zone;
 	int ret;
 
 	/*
-	 * The only files that have more than one zone are conventional zone
-	 * files with aggregated conventional zones, for which the inode zone
-	 * size is always larger than the device zone size.
+	 * Conventional zone have no write pointer and cannot become read-only
+	 * or offline. So simply fake a report for a single or aggregated zone
+	 * and let zonefs_handle_io_error() correct the zone inode information
+	 * according to the mount options.
 	 */
-	if (z->z_size > bdev_zone_sectors(sb->s_bdev))
-		nr_zones = z->z_size >>
-			(sbi->s_zone_sectors_shift + SECTOR_SHIFT);
+	if (!zonefs_zone_is_seq(z)) {
+		zone.start = z->z_sector;
+		zone.len = z->z_size >> SECTOR_SHIFT;
+		zone.wp = zone.start + zone.len;
+		zone.type = BLK_ZONE_TYPE_CONVENTIONAL;
+		zone.cond = BLK_ZONE_COND_NOT_WP;
+		zone.capacity = zone.len;
+		goto handle_io_error;
+	}
 
 	/*
 	 * Memory allocations in blkdev_report_zones() can trigger a memory
@@ -394,12 +396,20 @@ void __zonefs_io_error(struct inode *inode, bool write)
 	 * the GFP_NOIO context avoids both problems.
 	 */
 	noio_flag = memalloc_noio_save();
-	ret = blkdev_report_zones(sb->s_bdev, z->z_sector, nr_zones,
-				  zonefs_io_error_cb, &err);
-	if (ret != nr_zones)
+	ret = blkdev_report_zones(sb->s_bdev, z->z_sector, 1,
+				  zonefs_io_error_cb, &zone);
+	memalloc_noio_restore(noio_flag);
+
+	if (ret != 1) {
 		zonefs_err(sb, "Get inode %lu zone information failed %d\n",
 			   inode->i_ino, ret);
-	memalloc_noio_restore(noio_flag);
+		zonefs_warn(sb, "remounting filesystem read-only\n");
+		sb->s_flags |= SB_RDONLY;
+		return;
+	}
+
+handle_io_error:
+	zonefs_handle_io_error(inode, &zone, write);
 }
 
 static struct kmem_cache *zonefs_inode_cachep;
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 2b3ae51f950d..e4d24d3f9abb 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -719,6 +719,8 @@ struct acpi_pci_root {
 
 /* helper */
 
+struct iommu_ops;
+
 bool acpi_dma_supported(const struct acpi_device *adev);
 enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev);
 int acpi_iommu_fwspec_init(struct device *dev, u32 id,
diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h
index 3751ae69432f..9775384d61c6 100644
--- a/include/acpi/actbl2.h
+++ b/include/acpi/actbl2.h
@@ -1046,6 +1046,8 @@ struct acpi_madt_generic_interrupt {
 /* ACPI_MADT_ENABLED                    (1)      Processor is usable if set */
 #define ACPI_MADT_PERFORMANCE_IRQ_MODE  (1<<1)	/* 01: Performance Interrupt Mode */
 #define ACPI_MADT_VGIC_IRQ_MODE         (1<<2)	/* 02: VGIC Maintenance Interrupt mode */
+#define ACPI_MADT_GICC_ONLINE_CAPABLE   (1<<3)	/* 03: Processor is online capable  */
+#define ACPI_MADT_GICC_NON_COHERENT     (1<<4)	/* 04: GIC redistributor is not coherent */
 
 /* 12: Generic Distributor (ACPI 5.0 + ACPI 6.0 changes) */
 
@@ -1090,21 +1092,27 @@ struct acpi_madt_generic_msi_frame {
 
 struct acpi_madt_generic_redistributor {
 	struct acpi_subtable_header header;
-	u16 reserved;		/* reserved - must be zero */
+	u8 flags;
+	u8 reserved;		/* reserved - must be zero */
 	u64 base_address;
 	u32 length;
 };
 
+#define ACPI_MADT_GICR_NON_COHERENT     (1)
+
 /* 15: Generic Translator (ACPI 6.0) */
 
 struct acpi_madt_generic_translator {
 	struct acpi_subtable_header header;
-	u16 reserved;		/* reserved - must be zero */
+	u8 flags;
+	u8 reserved;		/* reserved - must be zero */
 	u32 translation_id;
 	u64 base_address;
 	u32 reserved2;
 };
 
+#define ACPI_MADT_ITS_NON_COHERENT      (1)
+
 /* 16: Multiprocessor wakeup (ACPI 6.4) */
 
 struct acpi_madt_multiproc_wakeup {
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 961f4d88f9ef..0c0695763bea 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -193,7 +193,6 @@ do {									\
 #ifndef smp_store_release
 #define smp_store_release(p, v)						\
 do {									\
-	compiletime_assert_atomic_type(*p);				\
 	barrier();							\
 	WRITE_ONCE(*p, v);						\
 } while (0)
@@ -203,7 +202,6 @@ do {									\
 #define smp_load_acquire(p)						\
 ({									\
 	__unqual_scalar_typeof(*p) ___p1 = READ_ONCE(*p);		\
-	compiletime_assert_atomic_type(*p);				\
 	barrier();							\
 	(typeof(*p))___p1;						\
 })
diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h
index 84ec53ccc450..7ee8a179d103 100644
--- a/include/asm-generic/cacheflush.h
+++ b/include/asm-generic/cacheflush.h
@@ -91,6 +91,12 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 }
 #endif
 
+#ifndef flush_cache_vmap_early
+static inline void flush_cache_vmap_early(unsigned long start, unsigned long end)
+{
+}
+#endif
+
 #ifndef flush_cache_vunmap
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
 {
diff --git a/include/asm-generic/checksum.h b/include/asm-generic/checksum.h
index 43e18db89c14..ad928cce268b 100644
--- a/include/asm-generic/checksum.h
+++ b/include/asm-generic/checksum.h
@@ -2,6 +2,8 @@
 #ifndef __ASM_GENERIC_CHECKSUM_H
 #define __ASM_GENERIC_CHECKSUM_H
 
+#include <linux/bitops.h>
+
 /*
  * computes the checksum of a memory block at buff, length len,
  * and adds in "sum" (32-bit)
@@ -31,9 +33,7 @@ extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
 static inline __sum16 csum_fold(__wsum csum)
 {
 	u32 sum = (__force u32)csum;
-	sum = (sum & 0xffff) + (sum >> 16);
-	sum = (sum & 0xffff) + (sum >> 16);
-	return (__force __sum16)~sum;
+	return (__force __sum16)((~sum - ror32(sum, 16)) >> 16);
 }
 #endif
 
diff --git a/include/drm/bridge/aux-bridge.h b/include/drm/bridge/aux-bridge.h
index c4c423e97f06..4453906105ca 100644
--- a/include/drm/bridge/aux-bridge.h
+++ b/include/drm/bridge/aux-bridge.h
@@ -9,6 +9,8 @@
 
 #include <drm/drm_connector.h>
 
+struct auxiliary_device;
+
 #if IS_ENABLED(CONFIG_DRM_AUX_BRIDGE)
 int drm_aux_bridge_register(struct device *parent);
 #else
@@ -19,10 +21,23 @@ static inline int drm_aux_bridge_register(struct device *parent)
 #endif
 
 #if IS_ENABLED(CONFIG_DRM_AUX_HPD_BRIDGE)
+struct auxiliary_device *devm_drm_dp_hpd_bridge_alloc(struct device *parent, struct device_node *np);
+int devm_drm_dp_hpd_bridge_add(struct device *dev, struct auxiliary_device *adev);
 struct device *drm_dp_hpd_bridge_register(struct device *parent,
 					  struct device_node *np);
 void drm_aux_hpd_bridge_notify(struct device *dev, enum drm_connector_status status);
 #else
+static inline struct auxiliary_device *devm_drm_dp_hpd_bridge_alloc(struct device *parent,
+								    struct device_node *np)
+{
+	return NULL;
+}
+
+static inline int devm_drm_dp_hpd_bridge_add(struct auxiliary_device *adev)
+{
+	return 0;
+}
+
 static inline struct device *drm_dp_hpd_bridge_register(struct device *parent,
 							struct device_node *np)
 {
diff --git a/include/dt-bindings/dma/fsl-edma.h b/include/dt-bindings/dma/fsl-edma.h
new file mode 100644
index 000000000000..fd11478cfe9c
--- /dev/null
+++ b/include/dt-bindings/dma/fsl-edma.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause */
+
+#ifndef _FSL_EDMA_DT_BINDING_H_
+#define _FSL_EDMA_DT_BINDING_H_
+
+/* Receive Channel */
+#define FSL_EDMA_RX		0x1
+
+/* iMX8 audio remote DMA */
+#define FSL_EDMA_REMOTE		0x2
+
+/* FIFO is continue memory region */
+#define FSL_EDMA_MULTI_FIFO	0x4
+
+/* Channel need stick to even channel */
+#define FSL_EDMA_EVEN_CH	0x8
+
+/* Channel need stick to odd channel */
+#define FSL_EDMA_ODD_CH		0x10
+
+#endif
diff --git a/include/kunit/test.h b/include/kunit/test.h
index fcb4a4940ace..61637ef32302 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -579,12 +579,12 @@ void __printf(2, 3) kunit_log_append(struct string_stream *log, const char *fmt,
 
 void __noreturn __kunit_abort(struct kunit *test);
 
-void __kunit_do_failed_assertion(struct kunit *test,
-			       const struct kunit_loc *loc,
-			       enum kunit_assert_type type,
-			       const struct kunit_assert *assert,
-			       assert_format_t assert_format,
-			       const char *fmt, ...);
+void __printf(6, 7) __kunit_do_failed_assertion(struct kunit *test,
+						const struct kunit_loc *loc,
+						enum kunit_assert_type type,
+						const struct kunit_assert *assert,
+						assert_format_t assert_format,
+						const char *fmt, ...);
 
 #define _KUNIT_FAILED(test, assert_type, assert_class, assert_format, INITIALIZER, fmt, ...) do { \
 	static const struct kunit_loc __loc = KUNIT_CURRENT_LOC;	       \
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 118a18b7ff84..b7165e52b3c6 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -15,6 +15,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/property.h>
 #include <linux/uuid.h>
+#include <linux/node.h>
 
 struct irq_domain;
 struct irq_domain_ops;
@@ -431,6 +432,16 @@ int thermal_acpi_hot_trip_temp(struct acpi_device *adev, int *ret_temp);
 int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp);
 #endif
 
+#ifdef CONFIG_ACPI_HMAT
+int acpi_get_genport_coordinates(u32 uid, struct access_coordinate *coord);
+#else
+static inline int acpi_get_genport_coordinates(u32 uid,
+					       struct access_coordinate *coord)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
 #ifdef CONFIG_ACPI_NUMA
 int acpi_map_pxm_to_node(int pxm);
 int acpi_get_node(acpi_handle handle);
diff --git a/include/linux/aer.h b/include/linux/aer.h
index f6ea2f57d808..ae0fae70d4bd 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -19,10 +19,10 @@
 struct pci_dev;
 
 struct aer_header_log_regs {
-	unsigned int dw0;
-	unsigned int dw1;
-	unsigned int dw2;
-	unsigned int dw3;
+	u32 dw0;
+	u32 dw1;
+	u32 dw2;
+	u32 dw3;
 };
 
 struct aer_capability_regs {
diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h
index a1307b58cc2c..9120de05ead0 100644
--- a/include/linux/amba/serial.h
+++ b/include/linux/amba/serial.h
@@ -10,6 +10,11 @@
 #ifndef ASM_ARM_HARDWARE_SERIAL_AMBA_H
 #define ASM_ARM_HARDWARE_SERIAL_AMBA_H
 
+#ifndef __ASSEMBLY__
+#include <linux/bitfield.h>
+#include <linux/bits.h>
+#endif
+
 #include <linux/types.h>
 
 /* -------------------------------------------------------------------------------
@@ -70,141 +75,145 @@
 #define ZX_UART011_ICR		0x4c
 #define ZX_UART011_DMACR	0x50
 
-#define UART011_DR_OE		(1 << 11)
-#define UART011_DR_BE		(1 << 10)
-#define UART011_DR_PE		(1 << 9)
-#define UART011_DR_FE		(1 << 8)
-
-#define UART01x_RSR_OE 		0x08
-#define UART01x_RSR_BE 		0x04
-#define UART01x_RSR_PE 		0x02
-#define UART01x_RSR_FE 		0x01
-
-#define UART011_FR_RI		0x100
-#define UART011_FR_TXFE		0x080
-#define UART011_FR_RXFF		0x040
-#define UART01x_FR_TXFF		0x020
-#define UART01x_FR_RXFE		0x010
-#define UART01x_FR_BUSY		0x008
-#define UART01x_FR_DCD 		0x004
-#define UART01x_FR_DSR 		0x002
-#define UART01x_FR_CTS 		0x001
+#define UART011_DR_OE		BIT(11)
+#define UART011_DR_BE		BIT(10)
+#define UART011_DR_PE		BIT(9)
+#define UART011_DR_FE		BIT(8)
+
+#define UART01x_RSR_OE		BIT(3)
+#define UART01x_RSR_BE		BIT(2)
+#define UART01x_RSR_PE		BIT(1)
+#define UART01x_RSR_FE		BIT(0)
+
+#define UART011_FR_RI		BIT(8)
+#define UART011_FR_TXFE		BIT(7)
+#define UART011_FR_RXFF		BIT(6)
+#define UART01x_FR_TXFF		(1 << 5)	/* used in ASM */
+#define UART01x_FR_RXFE		BIT(4)
+#define UART01x_FR_BUSY		(1 << 3)	/* used in ASM */
+#define UART01x_FR_DCD		BIT(2)
+#define UART01x_FR_DSR		BIT(1)
+#define UART01x_FR_CTS		BIT(0)
 #define UART01x_FR_TMSK		(UART01x_FR_TXFF + UART01x_FR_BUSY)
 
 /*
  * Some bits of Flag Register on ZTE device have different position from
  * standard ones.
  */
-#define ZX_UART01x_FR_BUSY	0x100
-#define ZX_UART01x_FR_DSR	0x008
-#define ZX_UART01x_FR_CTS	0x002
-#define ZX_UART011_FR_RI	0x001
-
-#define UART011_CR_CTSEN	0x8000	/* CTS hardware flow control */
-#define UART011_CR_RTSEN	0x4000	/* RTS hardware flow control */
-#define UART011_CR_OUT2		0x2000	/* OUT2 */
-#define UART011_CR_OUT1		0x1000	/* OUT1 */
-#define UART011_CR_RTS		0x0800	/* RTS */
-#define UART011_CR_DTR		0x0400	/* DTR */
-#define UART011_CR_RXE		0x0200	/* receive enable */
-#define UART011_CR_TXE		0x0100	/* transmit enable */
-#define UART011_CR_LBE		0x0080	/* loopback enable */
-#define UART010_CR_RTIE		0x0040
-#define UART010_CR_TIE 		0x0020
-#define UART010_CR_RIE 		0x0010
-#define UART010_CR_MSIE		0x0008
-#define ST_UART011_CR_OVSFACT	0x0008	/* Oversampling factor */
-#define UART01x_CR_IIRLP	0x0004	/* SIR low power mode */
-#define UART01x_CR_SIREN	0x0002	/* SIR enable */
-#define UART01x_CR_UARTEN	0x0001	/* UART enable */
- 
-#define UART011_LCRH_SPS	0x80
+#define ZX_UART01x_FR_BUSY	BIT(8)
+#define ZX_UART01x_FR_DSR	BIT(3)
+#define ZX_UART01x_FR_CTS	BIT(1)
+#define ZX_UART011_FR_RI	BIT(0)
+
+#define UART011_CR_CTSEN	BIT(15)	/* CTS hardware flow control */
+#define UART011_CR_RTSEN	BIT(14)	/* RTS hardware flow control */
+#define UART011_CR_OUT2		BIT(13)	/* OUT2 */
+#define UART011_CR_OUT1		BIT(12)	/* OUT1 */
+#define UART011_CR_RTS		BIT(11)	/* RTS */
+#define UART011_CR_DTR		BIT(10)	/* DTR */
+#define UART011_CR_RXE		BIT(9)	/* receive enable */
+#define UART011_CR_TXE		BIT(8)	/* transmit enable */
+#define UART011_CR_LBE		BIT(7)	/* loopback enable */
+#define UART010_CR_RTIE		BIT(6)
+#define UART010_CR_TIE		BIT(5)
+#define UART010_CR_RIE		BIT(4)
+#define UART010_CR_MSIE		BIT(3)
+#define ST_UART011_CR_OVSFACT	BIT(3)	/* Oversampling factor */
+#define UART01x_CR_IIRLP	BIT(2)	/* SIR low power mode */
+#define UART01x_CR_SIREN	BIT(1)	/* SIR enable */
+#define UART01x_CR_UARTEN	BIT(0)	/* UART enable */
+
+#define UART011_LCRH_SPS	BIT(7)
 #define UART01x_LCRH_WLEN_8	0x60
 #define UART01x_LCRH_WLEN_7	0x40
 #define UART01x_LCRH_WLEN_6	0x20
 #define UART01x_LCRH_WLEN_5	0x00
-#define UART01x_LCRH_FEN	0x10
-#define UART01x_LCRH_STP2	0x08
-#define UART01x_LCRH_EPS	0x04
-#define UART01x_LCRH_PEN	0x02
-#define UART01x_LCRH_BRK	0x01
-
-#define ST_UART011_DMAWM_RX_1	(0 << 3)
-#define ST_UART011_DMAWM_RX_2	(1 << 3)
-#define ST_UART011_DMAWM_RX_4	(2 << 3)
-#define ST_UART011_DMAWM_RX_8	(3 << 3)
-#define ST_UART011_DMAWM_RX_16	(4 << 3)
-#define ST_UART011_DMAWM_RX_32	(5 << 3)
-#define ST_UART011_DMAWM_RX_48	(6 << 3)
-#define ST_UART011_DMAWM_TX_1	0
-#define ST_UART011_DMAWM_TX_2	1
-#define ST_UART011_DMAWM_TX_4	2
-#define ST_UART011_DMAWM_TX_8	3
-#define ST_UART011_DMAWM_TX_16	4
-#define ST_UART011_DMAWM_TX_32	5
-#define ST_UART011_DMAWM_TX_48	6
-
-#define UART010_IIR_RTIS	0x08
-#define UART010_IIR_TIS		0x04
-#define UART010_IIR_RIS		0x02
-#define UART010_IIR_MIS		0x01
-
-#define UART011_IFLS_RX1_8	(0 << 3)
-#define UART011_IFLS_RX2_8	(1 << 3)
-#define UART011_IFLS_RX4_8	(2 << 3)
-#define UART011_IFLS_RX6_8	(3 << 3)
-#define UART011_IFLS_RX7_8	(4 << 3)
-#define UART011_IFLS_TX1_8	(0 << 0)
-#define UART011_IFLS_TX2_8	(1 << 0)
-#define UART011_IFLS_TX4_8	(2 << 0)
-#define UART011_IFLS_TX6_8	(3 << 0)
-#define UART011_IFLS_TX7_8	(4 << 0)
+#define UART01x_LCRH_FEN	BIT(4)
+#define UART01x_LCRH_STP2	BIT(3)
+#define UART01x_LCRH_EPS	BIT(2)
+#define UART01x_LCRH_PEN	BIT(1)
+#define UART01x_LCRH_BRK	BIT(0)
+
+#define ST_UART011_DMAWM_RX	GENMASK(5, 3)
+#define ST_UART011_DMAWM_RX_1	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 0)
+#define ST_UART011_DMAWM_RX_2	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 1)
+#define ST_UART011_DMAWM_RX_4	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 2)
+#define ST_UART011_DMAWM_RX_8	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 3)
+#define ST_UART011_DMAWM_RX_16	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 4)
+#define ST_UART011_DMAWM_RX_32	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 5)
+#define ST_UART011_DMAWM_RX_48	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 6)
+#define ST_UART011_DMAWM_TX	GENMASK(2, 0)
+#define ST_UART011_DMAWM_TX_1	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 0)
+#define ST_UART011_DMAWM_TX_2	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 1)
+#define ST_UART011_DMAWM_TX_4	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 2)
+#define ST_UART011_DMAWM_TX_8	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 3)
+#define ST_UART011_DMAWM_TX_16	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 4)
+#define ST_UART011_DMAWM_TX_32	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 5)
+#define ST_UART011_DMAWM_TX_48	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 6)
+
+#define UART010_IIR_RTIS	BIT(3)
+#define UART010_IIR_TIS		BIT(2)
+#define UART010_IIR_RIS		BIT(1)
+#define UART010_IIR_MIS		BIT(0)
+
+#define UART011_IFLS_RXIFLSEL	GENMASK(5, 3)
+#define UART011_IFLS_RX1_8	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 0)
+#define UART011_IFLS_RX2_8	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 1)
+#define UART011_IFLS_RX4_8	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 2)
+#define UART011_IFLS_RX6_8	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 3)
+#define UART011_IFLS_RX7_8	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 4)
+#define UART011_IFLS_TXIFLSEL	GENMASK(2, 0)
+#define UART011_IFLS_TX1_8	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 0)
+#define UART011_IFLS_TX2_8	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 1)
+#define UART011_IFLS_TX4_8	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 2)
+#define UART011_IFLS_TX6_8	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 3)
+#define UART011_IFLS_TX7_8	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 4)
 /* special values for ST vendor with deeper fifo */
-#define UART011_IFLS_RX_HALF	(5 << 3)
-#define UART011_IFLS_TX_HALF	(5 << 0)
-
-#define UART011_OEIM		(1 << 10)	/* overrun error interrupt mask */
-#define UART011_BEIM		(1 << 9)	/* break error interrupt mask */
-#define UART011_PEIM		(1 << 8)	/* parity error interrupt mask */
-#define UART011_FEIM		(1 << 7)	/* framing error interrupt mask */
-#define UART011_RTIM		(1 << 6)	/* receive timeout interrupt mask */
-#define UART011_TXIM		(1 << 5)	/* transmit interrupt mask */
-#define UART011_RXIM		(1 << 4)	/* receive interrupt mask */
-#define UART011_DSRMIM		(1 << 3)	/* DSR interrupt mask */
-#define UART011_DCDMIM		(1 << 2)	/* DCD interrupt mask */
-#define UART011_CTSMIM		(1 << 1)	/* CTS interrupt mask */
-#define UART011_RIMIM		(1 << 0)	/* RI interrupt mask */
-
-#define UART011_OEIS		(1 << 10)	/* overrun error interrupt status */
-#define UART011_BEIS		(1 << 9)	/* break error interrupt status */
-#define UART011_PEIS		(1 << 8)	/* parity error interrupt status */
-#define UART011_FEIS		(1 << 7)	/* framing error interrupt status */
-#define UART011_RTIS		(1 << 6)	/* receive timeout interrupt status */
-#define UART011_TXIS		(1 << 5)	/* transmit interrupt status */
-#define UART011_RXIS		(1 << 4)	/* receive interrupt status */
-#define UART011_DSRMIS		(1 << 3)	/* DSR interrupt status */
-#define UART011_DCDMIS		(1 << 2)	/* DCD interrupt status */
-#define UART011_CTSMIS		(1 << 1)	/* CTS interrupt status */
-#define UART011_RIMIS		(1 << 0)	/* RI interrupt status */
-
-#define UART011_OEIC		(1 << 10)	/* overrun error interrupt clear */
-#define UART011_BEIC		(1 << 9)	/* break error interrupt clear */
-#define UART011_PEIC		(1 << 8)	/* parity error interrupt clear */
-#define UART011_FEIC		(1 << 7)	/* framing error interrupt clear */
-#define UART011_RTIC		(1 << 6)	/* receive timeout interrupt clear */
-#define UART011_TXIC		(1 << 5)	/* transmit interrupt clear */
-#define UART011_RXIC		(1 << 4)	/* receive interrupt clear */
-#define UART011_DSRMIC		(1 << 3)	/* DSR interrupt clear */
-#define UART011_DCDMIC		(1 << 2)	/* DCD interrupt clear */
-#define UART011_CTSMIC		(1 << 1)	/* CTS interrupt clear */
-#define UART011_RIMIC		(1 << 0)	/* RI interrupt clear */
-
-#define UART011_DMAONERR	(1 << 2)	/* disable dma on error */
-#define UART011_TXDMAE		(1 << 1)	/* enable transmit dma */
-#define UART011_RXDMAE		(1 << 0)	/* enable receive dma */
-
-#define UART01x_RSR_ANY		(UART01x_RSR_OE|UART01x_RSR_BE|UART01x_RSR_PE|UART01x_RSR_FE)
-#define UART01x_FR_MODEM_ANY	(UART01x_FR_DCD|UART01x_FR_DSR|UART01x_FR_CTS)
+#define UART011_IFLS_RX_HALF	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 5)
+#define UART011_IFLS_TX_HALF	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 5)
+
+#define UART011_OEIM		BIT(10)	/* overrun error interrupt mask */
+#define UART011_BEIM		BIT(9)	/* break error interrupt mask */
+#define UART011_PEIM		BIT(8)	/* parity error interrupt mask */
+#define UART011_FEIM		BIT(7)	/* framing error interrupt mask */
+#define UART011_RTIM		BIT(6)	/* receive timeout interrupt mask */
+#define UART011_TXIM		BIT(5)	/* transmit interrupt mask */
+#define UART011_RXIM		BIT(4)	/* receive interrupt mask */
+#define UART011_DSRMIM		BIT(3)	/* DSR interrupt mask */
+#define UART011_DCDMIM		BIT(2)	/* DCD interrupt mask */
+#define UART011_CTSMIM		BIT(1)	/* CTS interrupt mask */
+#define UART011_RIMIM		BIT(0)	/* RI interrupt mask */
+
+#define UART011_OEIS		BIT(10)	/* overrun error interrupt status */
+#define UART011_BEIS		BIT(9)	/* break error interrupt status */
+#define UART011_PEIS		BIT(8)	/* parity error interrupt status */
+#define UART011_FEIS		BIT(7)	/* framing error interrupt status */
+#define UART011_RTIS		BIT(6)	/* receive timeout interrupt status */
+#define UART011_TXIS		BIT(5)	/* transmit interrupt status */
+#define UART011_RXIS		BIT(4)	/* receive interrupt status */
+#define UART011_DSRMIS		BIT(3)	/* DSR interrupt status */
+#define UART011_DCDMIS		BIT(2)	/* DCD interrupt status */
+#define UART011_CTSMIS		BIT(1)	/* CTS interrupt status */
+#define UART011_RIMIS		BIT(0)	/* RI interrupt status */
+
+#define UART011_OEIC		BIT(10)	/* overrun error interrupt clear */
+#define UART011_BEIC		BIT(9)	/* break error interrupt clear */
+#define UART011_PEIC		BIT(8)	/* parity error interrupt clear */
+#define UART011_FEIC		BIT(7)	/* framing error interrupt clear */
+#define UART011_RTIC		BIT(6)	/* receive timeout interrupt clear */
+#define UART011_TXIC		BIT(5)	/* transmit interrupt clear */
+#define UART011_RXIC		BIT(4)	/* receive interrupt clear */
+#define UART011_DSRMIC		BIT(3)	/* DSR interrupt clear */
+#define UART011_DCDMIC		BIT(2)	/* DCD interrupt clear */
+#define UART011_CTSMIC		BIT(1)	/* CTS interrupt clear */
+#define UART011_RIMIC		BIT(0)	/* RI interrupt clear */
+
+#define UART011_DMAONERR	BIT(2)	/* disable dma on error */
+#define UART011_TXDMAE		BIT(1)	/* enable transmit dma */
+#define UART011_RXDMAE		BIT(0)	/* enable receive dma */
+
+#define UART01x_RSR_ANY		(UART01x_RSR_OE | UART01x_RSR_BE | UART01x_RSR_PE | UART01x_RSR_FE)
+#define UART01x_FR_MODEM_ANY	(UART01x_FR_DCD | UART01x_FR_DSR | UART01x_FR_CTS)
 
 #ifndef __ASSEMBLY__
 struct amba_device; /* in uncompress this is included but amba/bus.h is not */
@@ -220,8 +229,8 @@ struct amba_pl011_data {
 	bool dma_rx_poll_enable;
 	unsigned int dma_rx_poll_rate;
 	unsigned int dma_rx_poll_timeout;
-        void (*init) (void);
-	void (*exit) (void);
+	void (*init)(void);
+	void (*exit)(void);
 };
 #endif
 
diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h
index 5deaddbd7927..93a5f16d03f3 100644
--- a/include/linux/anon_inodes.h
+++ b/include/linux/anon_inodes.h
@@ -15,13 +15,13 @@ struct inode;
 struct file *anon_inode_getfile(const char *name,
 				const struct file_operations *fops,
 				void *priv, int flags);
-struct file *anon_inode_getfile_secure(const char *name,
+struct file *anon_inode_create_getfile(const char *name,
 				       const struct file_operations *fops,
 				       void *priv, int flags,
 				       const struct inode *context_inode);
 int anon_inode_getfd(const char *name, const struct file_operations *fops,
 		     void *priv, int flags);
-int anon_inode_getfd_secure(const char *name,
+int anon_inode_create_getfd(const char *name,
 			    const struct file_operations *fops,
 			    void *priv, int flags,
 			    const struct inode *context_inode);
diff --git a/include/linux/async.h b/include/linux/async.h
index 33c9ff4afb49..19b778d08600 100644
--- a/include/linux/async.h
+++ b/include/linux/async.h
@@ -120,4 +120,5 @@ extern void async_synchronize_cookie(async_cookie_t cookie);
 extern void async_synchronize_cookie_domain(async_cookie_t cookie,
 					    struct async_domain *domain);
 extern bool current_is_async(void);
+extern void async_init(void);
 #endif
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index ae12696ec492..2ad261082bba 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -141,8 +141,6 @@ struct bdi_writeback {
 	struct delayed_work dwork;	/* work item used for writeback */
 	struct delayed_work bw_dwork;	/* work item used for bandwidth estimate */
 
-	unsigned long dirty_sleep;	/* last wait */
-
 	struct list_head bdi_node;	/* anchored at bdi->wb_list */
 
 #ifdef CONFIG_CGROUP_WRITEBACK
@@ -179,6 +177,11 @@ struct backing_dev_info {
 	 * any dirty wbs, which is depended upon by bdi_has_dirty().
 	 */
 	atomic_long_t tot_write_bandwidth;
+	/*
+	 * Jiffies when last process was dirty throttled on this bdi. Used by
+	 * blk-wbt.
+	 */
+	unsigned long last_bdp_sleep;
 
 	struct bdi_writeback wb;  /* the root writeback info for this bdi */
 	struct list_head wb_list; /* list of all wbs */
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 1a97277f99b1..8e7af9a03b41 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -38,7 +38,6 @@ struct backing_dev_info *bdi_alloc(int node_id);
 
 void wb_start_background_writeback(struct bdi_writeback *wb);
 void wb_workfn(struct work_struct *work);
-void wb_wakeup_delayed(struct bdi_writeback *wb);
 
 void wb_wait_for_completion(struct wb_completion *done);
 
diff --git a/include/linux/bio.h b/include/linux/bio.h
index ec4db73e5f4e..875d792bffff 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -286,6 +286,11 @@ static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio,
 {
 	struct bio_vec *bvec = bio_first_bvec_all(bio) + i;
 
+	if (unlikely(i >= bio->bi_vcnt)) {
+		fi->folio = NULL;
+		return;
+	}
+
 	fi->folio = page_folio(bvec->bv_page);
 	fi->offset = bvec->bv_offset +
 			PAGE_SIZE * (bvec->bv_page - &fi->folio->page);
@@ -303,10 +308,8 @@ static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio)
 		fi->offset = 0;
 		fi->length = min(folio_size(fi->folio), fi->_seg_count);
 		fi->_next = folio_next(fi->folio);
-	} else if (fi->_i + 1 < bio->bi_vcnt) {
-		bio_first_folio(fi, bio, fi->_i + 1);
 	} else {
-		fi->folio = NULL;
+		bio_first_folio(fi, bio, fi->_i + 1);
 	}
 }
 
diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h
index 378b2459efe2..e253e7bd0d17 100644
--- a/include/linux/blk-integrity.h
+++ b/include/linux/blk-integrity.h
@@ -20,6 +20,7 @@ struct blk_integrity_iter {
 	unsigned int		data_size;
 	unsigned short		interval;
 	unsigned char		tuple_size;
+	unsigned char		pi_offset;
 	const char		*disk_name;
 };
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index a676e116085f..d3d8fd8e229b 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -8,6 +8,7 @@
 #include <linux/scatterlist.h>
 #include <linux/prefetch.h>
 #include <linux/srcu.h>
+#include <linux/rw_hint.h>
 
 struct blk_mq_tags;
 struct blk_flush_queue;
@@ -135,6 +136,7 @@ struct request {
 	struct blk_crypto_keyslot *crypt_keyslot;
 #endif
 
+	enum rw_hint write_hint;
 	unsigned short ioprio;
 
 	enum mq_rq_state state;
@@ -391,9 +393,6 @@ struct blk_mq_hw_ctx {
 	 */
 	struct blk_mq_tags	*sched_tags;
 
-	/** @run: Number of dispatched requests. */
-	unsigned long		run;
-
 	/** @numa_node: NUMA node the storage adapter has been connected to. */
 	unsigned int		numa_node;
 	/** @queue_num: Index of this hardware queue. */
@@ -685,17 +684,19 @@ enum {
 
 #define BLK_MQ_NO_HCTX_IDX	(-1U)
 
-struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata,
+struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set,
+		struct queue_limits *lim, void *queuedata,
 		struct lock_class_key *lkclass);
-#define blk_mq_alloc_disk(set, queuedata)				\
+#define blk_mq_alloc_disk(set, lim, queuedata)				\
 ({									\
 	static struct lock_class_key __key;				\
 									\
-	__blk_mq_alloc_disk(set, queuedata, &__key);			\
+	__blk_mq_alloc_disk(set, lim, queuedata, &__key);		\
 })
 struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q,
 		struct lock_class_key *lkclass);
-struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *);
+struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set,
+		struct queue_limits *lim, void *queuedata);
 int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 		struct request_queue *q);
 void blk_mq_destroy_queue(struct request_queue *);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index f288c94374b3..cb1526ec44b5 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -10,6 +10,7 @@
 #include <linux/bvec.h>
 #include <linux/device.h>
 #include <linux/ktime.h>
+#include <linux/rw_hint.h>
 
 struct bio_set;
 struct bio;
@@ -206,52 +207,10 @@ static inline bool blk_path_error(blk_status_t error)
 	return true;
 }
 
-/*
- * From most significant bit:
- * 1 bit: reserved for other usage, see below
- * 12 bits: original size of bio
- * 51 bits: issue time of bio
- */
-#define BIO_ISSUE_RES_BITS      1
-#define BIO_ISSUE_SIZE_BITS     12
-#define BIO_ISSUE_RES_SHIFT     (64 - BIO_ISSUE_RES_BITS)
-#define BIO_ISSUE_SIZE_SHIFT    (BIO_ISSUE_RES_SHIFT - BIO_ISSUE_SIZE_BITS)
-#define BIO_ISSUE_TIME_MASK     ((1ULL << BIO_ISSUE_SIZE_SHIFT) - 1)
-#define BIO_ISSUE_SIZE_MASK     \
-	(((1ULL << BIO_ISSUE_SIZE_BITS) - 1) << BIO_ISSUE_SIZE_SHIFT)
-#define BIO_ISSUE_RES_MASK      (~((1ULL << BIO_ISSUE_RES_SHIFT) - 1))
-
-/* Reserved bit for blk-throtl */
-#define BIO_ISSUE_THROTL_SKIP_LATENCY (1ULL << 63)
-
 struct bio_issue {
 	u64 value;
 };
 
-static inline u64 __bio_issue_time(u64 time)
-{
-	return time & BIO_ISSUE_TIME_MASK;
-}
-
-static inline u64 bio_issue_time(struct bio_issue *issue)
-{
-	return __bio_issue_time(issue->value);
-}
-
-static inline sector_t bio_issue_size(struct bio_issue *issue)
-{
-	return ((issue->value & BIO_ISSUE_SIZE_MASK) >> BIO_ISSUE_SIZE_SHIFT);
-}
-
-static inline void bio_issue_init(struct bio_issue *issue,
-				       sector_t size)
-{
-	size &= (1ULL << BIO_ISSUE_SIZE_BITS) - 1;
-	issue->value = ((issue->value & BIO_ISSUE_RES_MASK) |
-			(ktime_get_ns() & BIO_ISSUE_TIME_MASK) |
-			((u64)size << BIO_ISSUE_SIZE_SHIFT));
-}
-
 typedef __u32 __bitwise blk_opf_t;
 
 typedef unsigned int blk_qc_t;
@@ -269,6 +228,7 @@ struct bio {
 						 */
 	unsigned short		bi_flags;	/* BIO_* below */
 	unsigned short		bi_ioprio;
+	enum rw_hint		bi_write_hint;
 	blk_status_t		bi_status;
 	atomic_t		__bi_remaining;
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 99e4f5e72213..f9b87c39cab0 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -24,6 +24,7 @@
 #include <linux/sbitmap.h>
 #include <linux/uuid.h>
 #include <linux/xarray.h>
+#include <linux/file.h>
 
 struct module;
 struct request_queue;
@@ -42,7 +43,7 @@ struct blk_crypto_profile;
 
 extern const struct device_type disk_type;
 extern const struct device_type part_type;
-extern struct class block_class;
+extern const struct class block_class;
 
 /*
  * Maximum number of blkcg policies allowed to be registered concurrently.
@@ -108,6 +109,7 @@ struct blk_integrity {
 	const struct blk_integrity_profile	*profile;
 	unsigned char				flags;
 	unsigned char				tuple_size;
+	unsigned char				pi_offset;
 	unsigned char				interval_exp;
 	unsigned char				tag_size;
 };
@@ -189,8 +191,6 @@ struct gendisk {
 	 * blk_mq_unfreeze_queue().
 	 */
 	unsigned int		nr_zones;
-	unsigned int		max_open_zones;
-	unsigned int		max_active_zones;
 	unsigned long		*conv_zones_bitmap;
 	unsigned long		*seq_zones_wlock;
 #endif /* CONFIG_BLK_DEV_ZONED */
@@ -292,6 +292,7 @@ struct queue_limits {
 	unsigned int		io_opt;
 	unsigned int		max_discard_sectors;
 	unsigned int		max_hw_discard_sectors;
+	unsigned int		max_user_discard_sectors;
 	unsigned int		max_secure_erase_sectors;
 	unsigned int		max_write_zeroes_sectors;
 	unsigned int		max_zone_append_sectors;
@@ -307,6 +308,8 @@ struct queue_limits {
 	unsigned char		discard_misaligned;
 	unsigned char		raid_partial_stripes_expensive;
 	bool			zoned;
+	unsigned int		max_open_zones;
+	unsigned int		max_active_zones;
 
 	/*
 	 * Drivers that set dma_alignment to less than 511 must be prepared to
@@ -325,7 +328,7 @@ void disk_set_zoned(struct gendisk *disk);
 int blkdev_report_zones(struct block_device *bdev, sector_t sector,
 		unsigned int nr_zones, report_zones_cb cb, void *data);
 int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
-		sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask);
+		sector_t sectors, sector_t nr_sectors);
 int blk_revalidate_disk_zones(struct gendisk *disk,
 		void (*update_driver_data)(struct gendisk *disk));
 
@@ -473,6 +476,7 @@ struct request_queue {
 
 	struct mutex		sysfs_lock;
 	struct mutex		sysfs_dir_lock;
+	struct mutex		limits_lock;
 
 	/*
 	 * for reusing dead hctx instance in case of updating
@@ -639,23 +643,23 @@ static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector)
 static inline void disk_set_max_open_zones(struct gendisk *disk,
 		unsigned int max_open_zones)
 {
-	disk->max_open_zones = max_open_zones;
+	disk->queue->limits.max_open_zones = max_open_zones;
 }
 
 static inline void disk_set_max_active_zones(struct gendisk *disk,
 		unsigned int max_active_zones)
 {
-	disk->max_active_zones = max_active_zones;
+	disk->queue->limits.max_active_zones = max_active_zones;
 }
 
 static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
 {
-	return bdev->bd_disk->max_open_zones;
+	return bdev->bd_disk->queue->limits.max_open_zones;
 }
 
 static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
 {
-	return bdev->bd_disk->max_active_zones;
+	return bdev->bd_disk->queue->limits.max_active_zones;
 }
 
 #else /* CONFIG_BLK_DEV_ZONED */
@@ -763,22 +767,26 @@ static inline u64 sb_bdev_nr_blocks(struct super_block *sb)
 int bdev_disk_changed(struct gendisk *disk, bool invalidate);
 
 void put_disk(struct gendisk *disk);
-struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass);
+struct gendisk *__blk_alloc_disk(struct queue_limits *lim, int node,
+		struct lock_class_key *lkclass);
 
 /**
  * blk_alloc_disk - allocate a gendisk structure
+ * @lim: queue limits to be used for this disk.
  * @node_id: numa node to allocate on
  *
  * Allocate and pre-initialize a gendisk structure for use with BIO based
  * drivers.
  *
+ * Returns an ERR_PTR on error, else the allocated disk.
+ *
  * Context: can sleep
  */
-#define blk_alloc_disk(node_id)						\
+#define blk_alloc_disk(lim, node_id)					\
 ({									\
 	static struct lock_class_key __key;				\
 									\
-	__blk_alloc_disk(node_id, &__key);				\
+	__blk_alloc_disk(lim, node_id, &__key);				\
 })
 
 int __register_blkdev(unsigned int major, const char *name,
@@ -861,6 +869,29 @@ static inline unsigned int blk_chunk_sectors_left(sector_t offset,
 	return chunk_sectors - (offset & (chunk_sectors - 1));
 }
 
+/**
+ * queue_limits_start_update - start an atomic update of queue limits
+ * @q:		queue to update
+ *
+ * This functions starts an atomic update of the queue limits.  It takes a lock
+ * to prevent other updates and returns a snapshot of the current limits that
+ * the caller can modify.  The caller must call queue_limits_commit_update()
+ * to finish the update.
+ *
+ * Context: process context.  The caller must have frozen the queue or ensured
+ * that there is outstanding I/O by other means.
+ */
+static inline struct queue_limits
+queue_limits_start_update(struct request_queue *q)
+	__acquires(q->limits_lock)
+{
+	mutex_lock(&q->limits_lock);
+	return q->limits;
+}
+int queue_limits_commit_update(struct request_queue *q,
+		struct queue_limits *lim);
+int queue_limits_set(struct request_queue *q, struct queue_limits *lim);
+
 /*
  * Access functions for manipulating queue properties
  */
@@ -894,8 +925,8 @@ extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth);
 extern void blk_set_stacking_limits(struct queue_limits *lim);
 extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 			    sector_t offset);
-extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
-			      sector_t offset);
+void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev,
+		sector_t offset, const char *pfx);
 extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
 extern void blk_queue_segment_boundary(struct request_queue *, unsigned long);
 extern void blk_queue_virt_boundary(struct request_queue *, unsigned long);
@@ -942,6 +973,7 @@ struct blk_plug {
 
 	/* if ios_left is > 1, we can batch tag/rq allocations */
 	struct request *cached_rq;
+	u64 cur_ktime;
 	unsigned short nr_ios;
 
 	unsigned short rq_count;
@@ -972,6 +1004,18 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async)
 		__blk_flush_plug(plug, async);
 }
 
+/*
+ * tsk == current here
+ */
+static inline void blk_plug_invalidate_ts(struct task_struct *tsk)
+{
+	struct blk_plug *plug = tsk->plug;
+
+	if (plug)
+		plug->cur_ktime = 0;
+	current->flags &= ~PF_BLOCK_TS;
+}
+
 int blkdev_issue_flush(struct block_device *bdev);
 long nr_blockdev_pages(void);
 #else /* CONFIG_BLOCK */
@@ -995,6 +1039,10 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async)
 {
 }
 
+static inline void blk_plug_invalidate_ts(struct task_struct *tsk)
+{
+}
+
 static inline int blkdev_issue_flush(struct block_device *bdev)
 {
 	return 0;
@@ -1474,26 +1522,20 @@ extern const struct blk_holder_ops fs_holder_ops;
 	(BLK_OPEN_READ | BLK_OPEN_RESTRICT_WRITES | \
 	 (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE))
 
-struct bdev_handle {
-	struct block_device *bdev;
-	void *holder;
-	blk_mode_t mode;
-};
-
-struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
+struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
 		const struct blk_holder_ops *hops);
-struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode,
+struct file *bdev_file_open_by_path(const char *path, blk_mode_t mode,
 		void *holder, const struct blk_holder_ops *hops);
 int bd_prepare_to_claim(struct block_device *bdev, void *holder,
 		const struct blk_holder_ops *hops);
 void bd_abort_claiming(struct block_device *bdev, void *holder);
-void bdev_release(struct bdev_handle *handle);
 
 /* just for blk-cgroup, don't use elsewhere */
 struct block_device *blkdev_get_no_open(dev_t dev);
 void blkdev_put_no_open(struct block_device *bdev);
 
 struct block_device *I_BDEV(struct inode *inode);
+struct block_device *file_bdev(struct file *bdev_file);
 
 #ifdef CONFIG_BLOCK
 void invalidate_bdev(struct block_device *bdev);
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 59d404e22814..cf5c6ff48981 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -512,7 +512,7 @@ s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id);
 int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt,
 				struct module *owner);
 struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id);
-const struct btf_member *
+const struct btf_type *
 btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
 		      const struct btf_type *t, enum bpf_prog_type prog_type,
 		      int arg);
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index 555aae5448ae..bd1e361b351c 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -83,7 +83,7 @@ struct bvec_iter {
 
 	unsigned int            bi_bvec_done;	/* number of bytes completed in
 						   current bvec */
-} __packed;
+} __packed __aligned(4);
 
 struct bvec_iter_all {
 	struct bio_vec	bv;
diff --git a/include/linux/cdx/cdx_bus.h b/include/linux/cdx/cdx_bus.h
index 94ad2c9017c9..6355a36a3f81 100644
--- a/include/linux/cdx/cdx_bus.h
+++ b/include/linux/cdx/cdx_bus.h
@@ -113,6 +113,7 @@ struct cdx_controller {
  * @dev_num: Device number for this device
  * @res: array of MMIO region entries
  * @res_attr: resource binary attribute
+ * @debugfs_dir: debugfs directory for this device
  * @res_count: number of valid MMIO regions
  * @dma_mask: Default DMA mask
  * @flags: CDX device flags
@@ -135,6 +136,8 @@ struct cdx_device {
 	u8 bus_num;
 	u8 dev_num;
 	struct resource res[MAX_CDX_DEV_RESOURCES];
+	struct bin_attribute *res_attr[MAX_CDX_DEV_RESOURCES];
+	struct dentry *debugfs_dir;
 	u8 res_count;
 	u64 dma_mask;
 	u16 flags;
@@ -147,6 +150,15 @@ struct cdx_device {
 #define to_cdx_device(_dev) \
 	container_of(_dev, struct cdx_device, dev)
 
+#define cdx_resource_start(dev, num)	((dev)->res[(num)].start)
+#define cdx_resource_end(dev, num)	((dev)->res[(num)].end)
+#define cdx_resource_flags(dev, num)	((dev)->res[(num)].flags)
+#define cdx_resource_len(dev, num) \
+	((cdx_resource_start((dev), (num)) == 0 &&	\
+	  cdx_resource_end((dev), (num)) ==		\
+	  cdx_resource_start((dev), (num))) ? 0 :	\
+	 (cdx_resource_end((dev), (num)) -		\
+	  cdx_resource_start((dev), (num)) + 1))
 /**
  * struct cdx_driver - CDX device driver
  * @driver: Generic device driver
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 2eaaabbe98cb..1717cc57cdac 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -283,7 +283,7 @@ struct ceph_msg {
 	struct kref kref;
 	bool more_to_follow;
 	bool needs_out_seq;
-	bool sparse_read;
+	u64 sparse_read_total;
 	int front_alloc_len;
 
 	struct ceph_msgpool *pool;
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index b8610e9d2471..f66f6aac74f6 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -45,6 +45,7 @@ enum ceph_sparse_read_state {
 	CEPH_SPARSE_READ_HDR	= 0,
 	CEPH_SPARSE_READ_EXTENTS,
 	CEPH_SPARSE_READ_DATA_LEN,
+	CEPH_SPARSE_READ_DATA_PRE,
 	CEPH_SPARSE_READ_DATA,
 };
 
@@ -64,7 +65,7 @@ struct ceph_sparse_read {
 	u64				sr_req_len;  /* orig request length */
 	u64				sr_pos;      /* current pos in buffer */
 	int				sr_index;    /* current extent index */
-	__le32				sr_datalen;  /* length of actual data */
+	u32				sr_datalen;  /* length of actual data */
 	u32				sr_count;    /* extent count in reply */
 	int				sr_ext_len;  /* length of extent array */
 	struct ceph_sparse_extent	*sr_extent;  /* extent array */
@@ -572,9 +573,12 @@ int __ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt);
  */
 #define CEPH_SPARSE_EXT_ARRAY_INITIAL  16
 
-static inline int ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op)
+static inline int ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt)
 {
-	return __ceph_alloc_sparse_ext_map(op, CEPH_SPARSE_EXT_ARRAY_INITIAL);
+	if (!cnt)
+		cnt = CEPH_SPARSE_EXT_ARRAY_INITIAL;
+
+	return __ceph_alloc_sparse_ext_map(op, cnt);
 }
 
 extern void ceph_osdc_get_request(struct ceph_osd_request *req);
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index aebb65bf95a7..75bd1692d2e3 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -64,6 +64,26 @@
 		__builtin_unreachable();	\
 	} while (0)
 
+/*
+ * GCC 'asm goto' with outputs miscompiles certain code sequences:
+ *
+ *   https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921
+ *
+ * Work around it via the same compiler barrier quirk that we used
+ * to use for the old 'asm goto' workaround.
+ *
+ * Also, always mark such 'asm goto' statements as volatile: all
+ * asm goto statements are supposed to be volatile as per the
+ * documentation, but some versions of gcc didn't actually do
+ * that for asms with outputs:
+ *
+ *    https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619
+ */
+#ifdef CONFIG_GCC_ASM_GOTO_OUTPUT_WORKAROUND
+#define asm_goto_output(x...) \
+	do { asm volatile goto(x); asm (""); } while (0)
+#endif
+
 #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP)
 #define __HAVE_BUILTIN_BSWAP32__
 #define __HAVE_BUILTIN_BSWAP64__
diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index 28566624f008..289810685fc5 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -95,11 +95,11 @@
 #endif
 
 /*
- * Optional: only supported since gcc >= 14
+ * Optional: only supported since gcc >= 15
  * Optional: only supported since clang >= 18
  *
  *   gcc: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108896
- * clang: https://reviews.llvm.org/D148381
+ * clang: https://github.com/llvm/llvm-project/pull/76348
  */
 #if __has_attribute(__counted_by__)
 # define __counted_by(member)		__attribute__((__counted_by__(member)))
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 6f1ca49306d2..0caf354cb94b 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -362,8 +362,15 @@ struct ftrace_likely_data {
 #define __member_size(p)	__builtin_object_size(p, 1)
 #endif
 
-#ifndef asm_volatile_goto
-#define asm_volatile_goto(x...) asm goto(x)
+/*
+ * Some versions of gcc do not mark 'asm goto' volatile:
+ *
+ *  https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103979
+ *
+ * We do it here by hand, because it doesn't hurt.
+ */
+#ifndef asm_goto_output
+#define asm_goto_output(x...) asm volatile goto(x)
 #endif
 
 #ifdef CONFIG_CC_HAS_ASM_INLINE
diff --git a/include/linux/container.h b/include/linux/container.h
index 2566a1baa736..dd00cc918a92 100644
--- a/include/linux/container.h
+++ b/include/linux/container.h
@@ -12,7 +12,7 @@
 #include <linux/device.h>
 
 /* drivers/base/power/container.c */
-extern struct bus_type container_subsys;
+extern const struct bus_type container_subsys;
 
 struct container_dev {
 	struct device dev;
diff --git a/include/linux/coresight.h b/include/linux/coresight.h
index a269fffaf991..a4cb7dd6ca23 100644
--- a/include/linux/coresight.h
+++ b/include/linux/coresight.h
@@ -64,6 +64,7 @@ enum coresight_dev_subtype_source {
 	CORESIGHT_DEV_SUBTYPE_SOURCE_PROC,
 	CORESIGHT_DEV_SUBTYPE_SOURCE_BUS,
 	CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE,
+	CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM,
 	CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS,
 };
 
diff --git a/include/linux/cper.h b/include/linux/cper.h
index c1a7dc325121..265b0f8fc0b3 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -90,6 +90,29 @@ enum {
 	GUID_INIT(0x667DD791, 0xC6B3, 0x4c27, 0x8A, 0x6B, 0x0F, 0x8E,	\
 		  0x72, 0x2D, 0xEB, 0x41)
 
+/* CXL Event record UUIDs are formatted as GUIDs and reported in section type */
+/*
+ * General Media Event Record
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ */
+#define CPER_SEC_CXL_GEN_MEDIA_GUID					\
+	GUID_INIT(0xfbcd0a77, 0xc260, 0x417f,				\
+		  0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6)
+/*
+ * DRAM Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
+ */
+#define CPER_SEC_CXL_DRAM_GUID						\
+	GUID_INIT(0x601dcbb3, 0x9c06, 0x4eab,				\
+		  0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24)
+/*
+ * Memory Module Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+#define CPER_SEC_CXL_MEM_MODULE_GUID					\
+	GUID_INIT(0xfe927475, 0xdd59, 0x4339,				\
+		  0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74)
+
 /*
  * Flags bits definitions for flags in struct cper_record_header
  * If set, the error has been recovered
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index fc8094419084..dcb89c987164 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -80,6 +80,7 @@ extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,
 				 const struct attribute_group **groups,
 				 const char *fmt, ...);
+extern bool arch_cpu_is_hotpluggable(int cpu);
 extern int arch_register_cpu(int cpu);
 extern void arch_unregister_cpu(int cpu);
 #ifdef CONFIG_HOTPLUG_CPU
@@ -88,6 +89,10 @@ extern ssize_t arch_cpu_probe(const char *, size_t);
 extern ssize_t arch_cpu_release(const char *, size_t);
 #endif
 
+#ifdef CONFIG_GENERIC_CPU_DEVICES
+DECLARE_PER_CPU(struct cpu, cpu_devices);
+#endif
+
 /*
  * These states are not related to the core CPU hotplug mechanism. They are
  * used by various (sub)architectures to track internal state
diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h
new file mode 100644
index 000000000000..03fa6d50d46f
--- /dev/null
+++ b/include/linux/cxl-event.h
@@ -0,0 +1,143 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2023 Intel Corporation. */
+#ifndef _LINUX_CXL_EVENT_H
+#define _LINUX_CXL_EVENT_H
+
+/*
+ * Common Event Record Format
+ * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
+ */
+struct cxl_event_record_hdr {
+	u8 length;
+	u8 flags[3];
+	__le16 handle;
+	__le16 related_handle;
+	__le64 timestamp;
+	u8 maint_op_class;
+	u8 reserved[15];
+} __packed;
+
+#define CXL_EVENT_RECORD_DATA_LENGTH 0x50
+struct cxl_event_generic {
+	struct cxl_event_record_hdr hdr;
+	u8 data[CXL_EVENT_RECORD_DATA_LENGTH];
+} __packed;
+
+/*
+ * General Media Event Record
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ */
+#define CXL_EVENT_GEN_MED_COMP_ID_SIZE	0x10
+struct cxl_event_gen_media {
+	struct cxl_event_record_hdr hdr;
+	__le64 phys_addr;
+	u8 descriptor;
+	u8 type;
+	u8 transaction_type;
+	u8 validity_flags[2];
+	u8 channel;
+	u8 rank;
+	u8 device[3];
+	u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
+	u8 reserved[46];
+} __packed;
+
+/*
+ * DRAM Event Record - DER
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 3-44
+ */
+#define CXL_EVENT_DER_CORRECTION_MASK_SIZE	0x20
+struct cxl_event_dram {
+	struct cxl_event_record_hdr hdr;
+	__le64 phys_addr;
+	u8 descriptor;
+	u8 type;
+	u8 transaction_type;
+	u8 validity_flags[2];
+	u8 channel;
+	u8 rank;
+	u8 nibble_mask[3];
+	u8 bank_group;
+	u8 bank;
+	u8 row[3];
+	u8 column[2];
+	u8 correction_mask[CXL_EVENT_DER_CORRECTION_MASK_SIZE];
+	u8 reserved[0x17];
+} __packed;
+
+/*
+ * Get Health Info Record
+ * CXL rev 3.0 section 8.2.9.8.3.1; Table 8-100
+ */
+struct cxl_get_health_info {
+	u8 health_status;
+	u8 media_status;
+	u8 add_status;
+	u8 life_used;
+	u8 device_temp[2];
+	u8 dirty_shutdown_cnt[4];
+	u8 cor_vol_err_cnt[4];
+	u8 cor_per_err_cnt[4];
+} __packed;
+
+/*
+ * Memory Module Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+struct cxl_event_mem_module {
+	struct cxl_event_record_hdr hdr;
+	u8 event_type;
+	struct cxl_get_health_info info;
+	u8 reserved[0x3d];
+} __packed;
+
+union cxl_event {
+	struct cxl_event_generic generic;
+	struct cxl_event_gen_media gen_media;
+	struct cxl_event_dram dram;
+	struct cxl_event_mem_module mem_module;
+} __packed;
+
+/*
+ * Common Event Record Format; in event logs
+ * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
+ */
+struct cxl_event_record_raw {
+	uuid_t id;
+	union cxl_event event;
+} __packed;
+
+enum cxl_event_type {
+	CXL_CPER_EVENT_GENERIC,
+	CXL_CPER_EVENT_GEN_MEDIA,
+	CXL_CPER_EVENT_DRAM,
+	CXL_CPER_EVENT_MEM_MODULE,
+};
+
+#define CPER_CXL_DEVICE_ID_VALID		BIT(0)
+#define CPER_CXL_DEVICE_SN_VALID		BIT(1)
+#define CPER_CXL_COMP_EVENT_LOG_VALID		BIT(2)
+struct cxl_cper_event_rec {
+	struct {
+		u32 length;
+		u64 validation_bits;
+		struct cper_cxl_event_devid {
+			u16 vendor_id;
+			u16 device_id;
+			u8 func_num;
+			u8 device_num;
+			u8 bus_num;
+			u16 segment_num;
+			u16 slot_num; /* bits 2:0 reserved */
+			u8 reserved;
+		} __packed device_id;
+		struct cper_cxl_event_sn {
+			u32 lower_dw;
+			u32 upper_dw;
+		} __packed dev_serial_num;
+	} __packed hdr;
+
+	union cxl_event event;
+} __packed;
+
+#endif /* _LINUX_CXL_EVENT_H */
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 1666c387861f..bf53e3894aae 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -125,6 +125,11 @@ enum dentry_d_lock_class
 	DENTRY_D_LOCK_NESTED
 };
 
+enum d_real_type {
+	D_REAL_DATA,
+	D_REAL_METADATA,
+};
+
 struct dentry_operations {
 	int (*d_revalidate)(struct dentry *, unsigned int);
 	int (*d_weak_revalidate)(struct dentry *, unsigned int);
@@ -139,7 +144,7 @@ struct dentry_operations {
 	char *(*d_dname)(struct dentry *, char *, int);
 	struct vfsmount *(*d_automount)(struct path *);
 	int (*d_manage)(const struct path *, bool);
-	struct dentry *(*d_real)(struct dentry *, const struct inode *);
+	struct dentry *(*d_real)(struct dentry *, enum d_real_type type);
 } ____cacheline_aligned;
 
 /*
@@ -173,6 +178,7 @@ struct dentry_operations {
 #define DCACHE_DONTCACHE		BIT(7) /* Purge from memory on final dput() */
 
 #define DCACHE_CANT_MOUNT		BIT(8)
+#define DCACHE_GENOCIDE			BIT(9)
 #define DCACHE_SHRINK_LIST		BIT(10)
 
 #define DCACHE_OP_WEAK_REVALIDATE	BIT(11)
@@ -546,24 +552,23 @@ static inline struct inode *d_backing_inode(const struct dentry *upper)
 /**
  * d_real - Return the real dentry
  * @dentry: the dentry to query
- * @inode: inode to select the dentry from multiple layers (can be NULL)
+ * @type: the type of real dentry (data or metadata)
  *
  * If dentry is on a union/overlay, then return the underlying, real dentry.
  * Otherwise return the dentry itself.
  *
  * See also: Documentation/filesystems/vfs.rst
  */
-static inline struct dentry *d_real(struct dentry *dentry,
-				    const struct inode *inode)
+static inline struct dentry *d_real(struct dentry *dentry, enum d_real_type type)
 {
 	if (unlikely(dentry->d_flags & DCACHE_OP_REAL))
-		return dentry->d_op->d_real(dentry, inode);
+		return dentry->d_op->d_real(dentry, type);
 	else
 		return dentry;
 }
 
 /**
- * d_real_inode - Return the real inode
+ * d_real_inode - Return the real inode hosting the data
  * @dentry: The dentry to query
  *
  * If dentry is on a union/overlay, then return the underlying, real inode.
@@ -572,7 +577,7 @@ static inline struct dentry *d_real(struct dentry *dentry,
 static inline struct inode *d_real_inode(const struct dentry *dentry)
 {
 	/* This usage of d_real() results in const dentry */
-	return d_backing_inode(d_real((struct dentry *) dentry, NULL));
+	return d_inode(d_real((struct dentry *) dentry, D_REAL_DATA));
 }
 
 struct name_snapshot {
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 772ab4d74d94..82b2195efaca 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -165,7 +165,7 @@ void dm_error(const char *message);
 
 struct dm_dev {
 	struct block_device *bdev;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct dax_device *dax_dev;
 	blk_mode_t mode;
 	char name[16];
diff --git a/include/linux/device.h b/include/linux/device.h
index 6c83294395ac..97c4b046c09d 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -42,7 +42,6 @@ struct class;
 struct subsys_private;
 struct device_node;
 struct fwnode_handle;
-struct iommu_ops;
 struct iommu_group;
 struct dev_pin_info;
 struct dev_iommu;
@@ -63,7 +62,7 @@ struct msi_device_data;
  */
 struct subsys_interface {
 	const char *name;
-	struct bus_type *subsys;
+	const struct bus_type *subsys;
 	struct list_head node;
 	int (*add_dev)(struct device *dev, struct subsys_interface *sif);
 	void (*remove_dev)(struct device *dev, struct subsys_interface *sif);
@@ -72,9 +71,9 @@ struct subsys_interface {
 int subsys_interface_register(struct subsys_interface *sif);
 void subsys_interface_unregister(struct subsys_interface *sif);
 
-int subsys_system_register(struct bus_type *subsys,
+int subsys_system_register(const struct bus_type *subsys,
 			   const struct attribute_group **groups);
-int subsys_virtual_register(struct bus_type *subsys,
+int subsys_virtual_register(const struct bus_type *subsys,
 			    const struct attribute_group **groups);
 
 /*
@@ -662,7 +661,6 @@ struct device_physical_location {
  * @id:		device instance
  * @devres_lock: Spinlock to protect the resource of the device.
  * @devres_head: The resources list of the device.
- * @knode_class: The node used to add the device to the class list.
  * @class:	The class of the device.
  * @groups:	Optional attribute groups.
  * @release:	Callback to free the device after all references have
@@ -1073,7 +1071,6 @@ int device_rename(struct device *dev, const char *new_name);
 int device_move(struct device *dev, struct device *new_parent,
 		enum dpm_order dpm_order);
 int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid);
-int device_is_dependent(struct device *dev, void *target);
 
 static inline bool device_supports_offline(struct device *dev)
 {
diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h
index ae10c4322754..5ef4ec1c36c3 100644
--- a/include/linux/device/bus.h
+++ b/include/linux/device/bus.h
@@ -62,9 +62,6 @@ struct fwnode_handle;
  *			this bus.
  * @pm:		Power management operations of this bus, callback the specific
  *		device driver's pm-ops.
- * @iommu_ops:  IOMMU specific operations for this bus, used to attach IOMMU
- *              driver implementations to a bus and allow the driver to do
- *              bus-specific setup
  * @need_parent_lock:	When probing or removing a device on this bus, the
  *			device core should lock the device's parent.
  *
@@ -104,8 +101,6 @@ struct bus_type {
 
 	const struct dev_pm_ops *pm;
 
-	const struct iommu_ops *iommu_ops;
-
 	bool need_parent_lock;
 };
 
@@ -232,7 +227,7 @@ bus_find_device_by_acpi_dev(const struct bus_type *bus, const void *adev)
 
 int bus_for_each_drv(const struct bus_type *bus, struct device_driver *start,
 		     void *data, int (*fn)(struct device_driver *, void *));
-void bus_sort_breadthfirst(struct bus_type *bus,
+void bus_sort_breadthfirst(const struct bus_type *bus,
 			   int (*compare)(const struct device *a,
 					  const struct device *b));
 /*
diff --git a/include/linux/device/class.h b/include/linux/device/class.h
index abf3d3bfb6fe..c576b49c55c2 100644
--- a/include/linux/device/class.h
+++ b/include/linux/device/class.h
@@ -40,8 +40,6 @@ struct fwnode_handle;
  *		for the devices belonging to the class. Usually tied to
  *		device's namespace.
  * @pm:		The default device power management operations of this class.
- * @p:		The private data of the driver core, no one other than the
- *		driver core can touch this.
  *
  * A class is a higher-level view of a device that abstracts out low-level
  * implementation details. Drivers may see a SCSI disk or an ATA disk, but,
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index f2fc203fb8a1..4abc60f04209 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -11,6 +11,7 @@
 #include <linux/slab.h>
 
 struct cma;
+struct iommu_ops;
 
 /*
  * Values for struct dma_map_ops.flags:
@@ -426,10 +427,10 @@ bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg,
 
 #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-		const struct iommu_ops *iommu, bool coherent);
+		bool coherent);
 #else
 static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base,
-		u64 size, const struct iommu_ops *iommu, bool coherent)
+		u64 size, bool coherent)
 {
 }
 #endif /* CONFIG_ARCH_HAS_SETUP_DMA_OPS */
@@ -443,10 +444,10 @@ static inline void arch_teardown_dma_ops(struct device *dev)
 #endif /* CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS */
 
 #ifdef CONFIG_DMA_API_DEBUG
-void dma_debug_add_bus(struct bus_type *bus);
+void dma_debug_add_bus(const struct bus_type *bus);
 void debug_dma_dump_mappings(struct device *dev);
 #else
-static inline void dma_debug_add_bus(struct bus_type *bus)
+static inline void dma_debug_add_bus(const struct bus_type *bus)
 {
 }
 static inline void debug_dma_dump_mappings(struct device *dev)
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 3df70d6131c8..752dbde4cec1 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -953,7 +953,8 @@ static inline int dmaengine_slave_config(struct dma_chan *chan,
 
 static inline bool is_slave_direction(enum dma_transfer_direction direction)
 {
-	return (direction == DMA_MEM_TO_DEV) || (direction == DMA_DEV_TO_MEM);
+	return (direction == DMA_MEM_TO_DEV) || (direction == DMA_DEV_TO_MEM) ||
+	       (direction == DMA_DEV_TO_DEV);
 }
 
 static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_single(
diff --git a/include/linux/dpll.h b/include/linux/dpll.h
index 9cf896ea1d41..e37344f6a231 100644
--- a/include/linux/dpll.h
+++ b/include/linux/dpll.h
@@ -10,6 +10,8 @@
 #include <uapi/linux/dpll.h>
 #include <linux/device.h>
 #include <linux/netlink.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
 
 struct dpll_device;
 struct dpll_pin;
@@ -120,15 +122,24 @@ struct dpll_pin_properties {
 };
 
 #if IS_ENABLED(CONFIG_DPLL)
-size_t dpll_msg_pin_handle_size(struct dpll_pin *pin);
-int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin);
+void dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin);
+void dpll_netdev_pin_clear(struct net_device *dev);
+
+size_t dpll_netdev_pin_handle_size(const struct net_device *dev);
+int dpll_netdev_add_pin_handle(struct sk_buff *msg,
+			       const struct net_device *dev);
 #else
-static inline size_t dpll_msg_pin_handle_size(struct dpll_pin *pin)
+static inline void
+dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin) { }
+static inline void dpll_netdev_pin_clear(struct net_device *dev) { }
+
+static inline size_t dpll_netdev_pin_handle_size(const struct net_device *dev)
 {
 	return 0;
 }
 
-static inline int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin)
+static inline int
+dpll_netdev_add_pin_handle(struct sk_buff *msg, const struct net_device *dev)
 {
 	return 0;
 }
diff --git a/include/linux/edac.h b/include/linux/edac.h
index 1174beb94ab6..b4ee8961e623 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -30,7 +30,7 @@ struct device;
 
 extern int edac_op_state;
 
-struct bus_type *edac_get_sysfs_subsys(void);
+const struct bus_type *edac_get_sysfs_subsys(void);
 
 static inline void opstate_init(void)
 {
@@ -495,7 +495,7 @@ struct edac_raw_error_desc {
  */
 struct mem_ctl_info {
 	struct device			dev;
-	struct bus_type			*bus;
+	const struct bus_type		*bus;
 
 	struct list_head link;	/* for global list of mem_ctl_info structs */
 
diff --git a/include/linux/export.h b/include/linux/export.h
index 9911508a9604..0bbd02fd351d 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -7,15 +7,6 @@
 #include <linux/stringify.h>
 
 /*
- * Export symbols from the kernel to modules.  Forked from module.h
- * to reduce the amount of pointless cruft we feed to gcc when only
- * exporting a simple symbol or two.
- *
- * Try not to add #includes here.  It slows compilation and makes kernel
- * hackers place grumpy comments in header files.
- */
-
-/*
  * This comment block is used by fixdep. Please do not remove.
  *
  * When CONFIG_MODVERSIONS is changed from n to y, all source files having
@@ -23,15 +14,6 @@
  * side effect of the *.o build rule.
  */
 
-#ifndef __ASSEMBLY__
-#ifdef MODULE
-extern struct module __this_module;
-#define THIS_MODULE (&__this_module)
-#else
-#define THIS_MODULE ((struct module *)0)
-#endif
-#endif /* __ASSEMBLY__ */
-
 #ifdef CONFIG_64BIT
 #define __EXPORT_SYMBOL_REF(sym)			\
 	.balign 8				ASM_NL	\
diff --git a/include/linux/file.h b/include/linux/file.h
index 6834a29338c4..169692cb1906 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -24,6 +24,8 @@ struct inode;
 struct path;
 extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *,
 	const char *, int flags, const struct file_operations *);
+extern struct file *alloc_file_pseudo_noaccount(struct inode *, struct vfsmount *,
+	const char *, int flags, const struct file_operations *);
 extern struct file *alloc_file_clone(struct file *, int flags,
 	const struct file_operations *);
 
diff --git a/include/linux/filelock.h b/include/linux/filelock.h
index 95e868e09e29..daee999d05f3 100644
--- a/include/linux/filelock.h
+++ b/include/linux/filelock.h
@@ -27,6 +27,7 @@
 #define FILE_LOCK_DEFERRED 1
 
 struct file_lock;
+struct file_lease;
 
 struct file_lock_operations {
 	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
@@ -39,14 +40,17 @@ struct lock_manager_operations {
 	void (*lm_put_owner)(fl_owner_t);
 	void (*lm_notify)(struct file_lock *);	/* unblock callback */
 	int (*lm_grant)(struct file_lock *, int);
-	bool (*lm_break)(struct file_lock *);
-	int (*lm_change)(struct file_lock *, int, struct list_head *);
-	void (*lm_setup)(struct file_lock *, void **);
-	bool (*lm_breaker_owns_lease)(struct file_lock *);
 	bool (*lm_lock_expirable)(struct file_lock *cfl);
 	void (*lm_expire_lock)(void);
 };
 
+struct lease_manager_operations {
+	bool (*lm_break)(struct file_lease *);
+	int (*lm_change)(struct file_lease *, int, struct list_head *);
+	void (*lm_setup)(struct file_lease *, void **);
+	bool (*lm_breaker_owns_lease)(struct file_lease *);
+};
+
 struct lock_manager {
 	struct list_head list;
 	/*
@@ -85,31 +89,31 @@ bool opens_in_grace(struct net *);
  *
  * Obviously, the last two criteria only matter for POSIX locks.
  */
-struct file_lock {
-	struct file_lock *fl_blocker;	/* The lock, that is blocking us */
-	struct list_head fl_list;	/* link into file_lock_context */
-	struct hlist_node fl_link;	/* node in global lists */
-	struct list_head fl_blocked_requests;	/* list of requests with
+
+struct file_lock_core {
+	struct file_lock_core *flc_blocker;	/* The lock that is blocking us */
+	struct list_head flc_list;	/* link into file_lock_context */
+	struct hlist_node flc_link;	/* node in global lists */
+	struct list_head flc_blocked_requests;	/* list of requests with
 						 * ->fl_blocker pointing here
 						 */
-	struct list_head fl_blocked_member;	/* node in
+	struct list_head flc_blocked_member;	/* node in
 						 * ->fl_blocker->fl_blocked_requests
 						 */
-	fl_owner_t fl_owner;
-	unsigned int fl_flags;
-	unsigned char fl_type;
-	unsigned int fl_pid;
-	int fl_link_cpu;		/* what cpu's list is this on? */
-	wait_queue_head_t fl_wait;
-	struct file *fl_file;
+	fl_owner_t flc_owner;
+	unsigned int flc_flags;
+	unsigned char flc_type;
+	pid_t flc_pid;
+	int flc_link_cpu;		/* what cpu's list is this on? */
+	wait_queue_head_t flc_wait;
+	struct file *flc_file;
+};
+
+struct file_lock {
+	struct file_lock_core c;
 	loff_t fl_start;
 	loff_t fl_end;
 
-	struct fasync_struct *	fl_fasync; /* for lease break notifications */
-	/* for lease breaks: */
-	unsigned long fl_break_time;
-	unsigned long fl_downgrade_time;
-
 	const struct file_lock_operations *fl_ops;	/* Callbacks for filesystems */
 	const struct lock_manager_operations *fl_lmops;	/* Callbacks for lockmanagers */
 	union {
@@ -126,6 +130,15 @@ struct file_lock {
 	} fl_u;
 } __randomize_layout;
 
+struct file_lease {
+	struct file_lock_core c;
+	struct fasync_struct *	fl_fasync; /* for lease break notifications */
+	/* for lease breaks: */
+	unsigned long fl_break_time;
+	unsigned long fl_downgrade_time;
+	const struct lease_manager_operations *fl_lmops; /* Callbacks for lease managers */
+} __randomize_layout;
+
 struct file_lock_context {
 	spinlock_t		flc_lock;
 	struct list_head	flc_flock;
@@ -147,11 +160,31 @@ int fcntl_setlk64(unsigned int, struct file *, unsigned int,
 int fcntl_setlease(unsigned int fd, struct file *filp, int arg);
 int fcntl_getlease(struct file *filp);
 
+static inline bool lock_is_unlock(struct file_lock *fl)
+{
+	return fl->c.flc_type == F_UNLCK;
+}
+
+static inline bool lock_is_read(struct file_lock *fl)
+{
+	return fl->c.flc_type == F_RDLCK;
+}
+
+static inline bool lock_is_write(struct file_lock *fl)
+{
+	return fl->c.flc_type == F_WRLCK;
+}
+
+static inline void locks_wake_up(struct file_lock *fl)
+{
+	wake_up(&fl->c.flc_wait);
+}
+
 /* fs/locks.c */
 void locks_free_lock_context(struct inode *inode);
 void locks_free_lock(struct file_lock *fl);
 void locks_init_lock(struct file_lock *);
-struct file_lock * locks_alloc_lock(void);
+struct file_lock *locks_alloc_lock(void);
 void locks_copy_lock(struct file_lock *, struct file_lock *);
 void locks_copy_conflock(struct file_lock *, struct file_lock *);
 void locks_remove_posix(struct file *, fl_owner_t);
@@ -165,11 +198,16 @@ int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_l
 int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
 bool vfs_inode_has_locks(struct inode *inode);
 int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl);
+
+void locks_init_lease(struct file_lease *);
+void locks_free_lease(struct file_lease *fl);
+struct file_lease *locks_alloc_lease(void);
 int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
 void lease_get_mtime(struct inode *, struct timespec64 *time);
-int generic_setlease(struct file *, int, struct file_lock **, void **priv);
-int vfs_setlease(struct file *, int, struct file_lock **, void **);
-int lease_modify(struct file_lock *, int, struct list_head *);
+int generic_setlease(struct file *, int, struct file_lease **, void **priv);
+int kernel_setlease(struct file *, int, struct file_lease **, void **);
+int vfs_setlease(struct file *, int, struct file_lease **, void **);
+int lease_modify(struct file_lease *, int, struct list_head *);
 
 struct notifier_block;
 int lease_register_notifier(struct notifier_block *);
@@ -223,6 +261,25 @@ static inline int fcntl_getlease(struct file *filp)
 	return F_UNLCK;
 }
 
+static inline bool lock_is_unlock(struct file_lock *fl)
+{
+	return false;
+}
+
+static inline bool lock_is_read(struct file_lock *fl)
+{
+	return false;
+}
+
+static inline bool lock_is_write(struct file_lock *fl)
+{
+	return false;
+}
+
+static inline void locks_wake_up(struct file_lock *fl)
+{
+}
+
 static inline void
 locks_free_lock_context(struct inode *inode)
 {
@@ -233,6 +290,11 @@ static inline void locks_init_lock(struct file_lock *fl)
 	return;
 }
 
+static inline void locks_init_lease(struct file_lease *fl)
+{
+	return;
+}
+
 static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
 {
 	return;
@@ -307,18 +369,24 @@ static inline void lease_get_mtime(struct inode *inode,
 }
 
 static inline int generic_setlease(struct file *filp, int arg,
-				    struct file_lock **flp, void **priv)
+				    struct file_lease **flp, void **priv)
+{
+	return -EINVAL;
+}
+
+static inline int kernel_setlease(struct file *filp, int arg,
+			       struct file_lease **lease, void **priv)
 {
 	return -EINVAL;
 }
 
 static inline int vfs_setlease(struct file *filp, int arg,
-			       struct file_lock **lease, void **priv)
+			       struct file_lease **lease, void **priv)
 {
 	return -EINVAL;
 }
 
-static inline int lease_modify(struct file_lock *fl, int arg,
+static inline int lease_modify(struct file_lease *fl, int arg,
 			       struct list_head *dispose)
 {
 	return -EINVAL;
@@ -341,6 +409,9 @@ locks_inode_context(const struct inode *inode)
 
 #endif /* !CONFIG_FILE_LOCKING */
 
+/* for walking lists of file_locks linked by fl_list */
+#define for_each_file_lock(_fl, _head)	list_for_each_entry(_fl, _head, c.flc_list)
+
 static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl)
 {
 	return locks_lock_inode_wait(file_inode(filp), fl);
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index d1ea3898564c..9a7e52739251 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -32,6 +32,7 @@
 #define PM_SIP_SVC			0xC2000000
 
 /* PM API versions */
+#define PM_API_VERSION_1	1
 #define PM_API_VERSION_2	2
 
 #define PM_PINCTRL_PARAM_SET_VERSION	2
@@ -47,6 +48,9 @@
 #define FAMILY_CODE_MASK	GENMASK(27, 21)
 #define SUB_FAMILY_CODE_MASK	GENMASK(20, 19)
 
+#define API_ID_MASK		GENMASK(7, 0)
+#define MODULE_ID_MASK		GENMASK(11, 8)
+
 /* ATF only commands */
 #define TF_A_PM_REGISTER_SGI		0xa04
 #define PM_GET_TRUSTZONE_VERSION	0xa03
@@ -91,10 +95,18 @@
 /*
  * Node IDs for the Error Events.
  */
-#define EVENT_ERROR_PMC_ERR1	(0x28100000U)
-#define EVENT_ERROR_PMC_ERR2	(0x28104000U)
-#define EVENT_ERROR_PSM_ERR1	(0x28108000U)
-#define EVENT_ERROR_PSM_ERR2	(0x2810C000U)
+#define VERSAL_EVENT_ERROR_PMC_ERR1	(0x28100000U)
+#define VERSAL_EVENT_ERROR_PMC_ERR2	(0x28104000U)
+#define VERSAL_EVENT_ERROR_PSM_ERR1	(0x28108000U)
+#define VERSAL_EVENT_ERROR_PSM_ERR2	(0x2810C000U)
+
+#define VERSAL_NET_EVENT_ERROR_PMC_ERR1	(0x28100000U)
+#define VERSAL_NET_EVENT_ERROR_PMC_ERR2	(0x28104000U)
+#define VERSAL_NET_EVENT_ERROR_PMC_ERR3	(0x28108000U)
+#define VERSAL_NET_EVENT_ERROR_PSM_ERR1	(0x2810C000U)
+#define VERSAL_NET_EVENT_ERROR_PSM_ERR2	(0x28110000U)
+#define VERSAL_NET_EVENT_ERROR_PSM_ERR3	(0x28114000U)
+#define VERSAL_NET_EVENT_ERROR_PSM_ERR4	(0x28118000U)
 
 /* ZynqMP SD tap delay tuning */
 #define SD_ITAPDLY	0xFF180314
@@ -112,6 +124,12 @@
 #define XPM_EVENT_ERROR_MASK_NOC_NCR		BIT(13)
 #define XPM_EVENT_ERROR_MASK_NOC_CR		BIT(12)
 
+enum pm_module_id {
+	PM_MODULE_ID = 0x0,
+	XSEM_MODULE_ID = 0x3,
+	TF_A_MODULE_ID = 0xa,
+};
+
 enum pm_api_cb_id {
 	PM_INIT_SUSPEND_CB = 30,
 	PM_ACKNOWLEDGE_CB = 31,
@@ -119,6 +137,7 @@ enum pm_api_cb_id {
 };
 
 enum pm_api_id {
+	PM_API_FEATURES = 0,
 	PM_GET_API_VERSION = 1,
 	PM_REGISTER_NOTIFIER = 5,
 	PM_FORCE_POWERDOWN = 8,
@@ -138,7 +157,6 @@ enum pm_api_id {
 	PM_SECURE_SHA = 26,
 	PM_PINCTRL_REQUEST = 28,
 	PM_PINCTRL_RELEASE = 29,
-	PM_PINCTRL_GET_FUNCTION = 30,
 	PM_PINCTRL_SET_FUNCTION = 31,
 	PM_PINCTRL_CONFIG_PARAM_GET = 32,
 	PM_PINCTRL_CONFIG_PARAM_SET = 33,
@@ -149,8 +167,6 @@ enum pm_api_id {
 	PM_CLOCK_GETSTATE = 38,
 	PM_CLOCK_SETDIVIDER = 39,
 	PM_CLOCK_GETDIVIDER = 40,
-	PM_CLOCK_SETRATE = 41,
-	PM_CLOCK_GETRATE = 42,
 	PM_CLOCK_SETPARENT = 43,
 	PM_CLOCK_GETPARENT = 44,
 	PM_FPGA_READ = 46,
@@ -161,7 +177,9 @@ enum pm_api_id {
 /* PMU-FW return status codes */
 enum pm_ret_status {
 	XST_PM_SUCCESS = 0,
+	XST_PM_INVALID_VERSION = 4,
 	XST_PM_NO_FEATURE = 19,
+	XST_PM_INVALID_CRC = 301,
 	XST_PM_INTERNAL = 2000,
 	XST_PM_CONFLICT = 2001,
 	XST_PM_NO_ACCESS = 2002,
@@ -509,20 +527,18 @@ struct zynqmp_pm_query_data {
 	u32 arg3;
 };
 
-int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1,
-			u32 arg2, u32 arg3, u32 *ret_payload);
+int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 *ret_payload, u32 num_args, ...);
 
 #if IS_REACHABLE(CONFIG_ZYNQMP_FIRMWARE)
 int zynqmp_pm_get_api_version(u32 *version);
 int zynqmp_pm_get_chipid(u32 *idcode, u32 *version);
+int zynqmp_pm_get_family_info(u32 *family, u32 *subfamily);
 int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out);
 int zynqmp_pm_clock_enable(u32 clock_id);
 int zynqmp_pm_clock_disable(u32 clock_id);
 int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state);
 int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider);
 int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider);
-int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate);
-int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate);
 int zynqmp_pm_clock_setparent(u32 clock_id, u32 parent_id);
 int zynqmp_pm_clock_getparent(u32 clock_id, u32 *parent_id);
 int zynqmp_pm_set_pll_frac_mode(u32 clk_id, u32 mode);
@@ -559,7 +575,6 @@ int zynqmp_pm_system_shutdown(const u32 type, const u32 subtype);
 int zynqmp_pm_set_boot_health_status(u32 value);
 int zynqmp_pm_pinctrl_request(const u32 pin);
 int zynqmp_pm_pinctrl_release(const u32 pin);
-int zynqmp_pm_pinctrl_get_function(const u32 pin, u32 *id);
 int zynqmp_pm_pinctrl_set_function(const u32 pin, const u32 id);
 int zynqmp_pm_pinctrl_get_config(const u32 pin, const u32 param,
 				 u32 *value);
@@ -596,6 +611,11 @@ static inline int zynqmp_pm_get_chipid(u32 *idcode, u32 *version)
 	return -ENODEV;
 }
 
+static inline int zynqmp_pm_get_family_info(u32 *family, u32 *subfamily)
+{
+	return -ENODEV;
+}
+
 static inline int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata,
 				       u32 *out)
 {
@@ -627,16 +647,6 @@ static inline int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider)
 	return -ENODEV;
 }
 
-static inline int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate)
-{
-	return -ENODEV;
-}
-
-static inline int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate)
-{
-	return -ENODEV;
-}
-
 static inline int zynqmp_pm_clock_setparent(u32 clock_id, u32 parent_id)
 {
 	return -ENODEV;
@@ -806,11 +816,6 @@ static inline int zynqmp_pm_pinctrl_release(const u32 pin)
 	return -ENODEV;
 }
 
-static inline int zynqmp_pm_pinctrl_get_function(const u32 pin, u32 *id)
-{
-	return -ENODEV;
-}
-
 static inline int zynqmp_pm_is_function_supported(const u32 api_id, const u32 id)
 {
 	return -ENODEV;
diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h
index 79ef6ac4c021..89a6888f2f9e 100644
--- a/include/linux/fortify-string.h
+++ b/include/linux/fortify-string.h
@@ -214,51 +214,6 @@ __kernel_size_t __fortify_strlen(const char * const POS p)
 	return ret;
 }
 
-/* Defined after fortified strlen() to reuse it. */
-extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy);
-/**
- * strlcpy - Copy a string into another string buffer
- *
- * @p: pointer to destination of copy
- * @q: pointer to NUL-terminated source string to copy
- * @size: maximum number of bytes to write at @p
- *
- * If strlen(@q) >= @size, the copy of @q will be truncated at
- * @size - 1 bytes. @p will always be NUL-terminated.
- *
- * Do not use this function. While FORTIFY_SOURCE tries to avoid
- * over-reads when calculating strlen(@q), it is still possible.
- * Prefer strscpy(), though note its different return values for
- * detecting truncation.
- *
- * Returns total number of bytes written to @p, including terminating NUL.
- *
- */
-__FORTIFY_INLINE size_t strlcpy(char * const POS p, const char * const POS q, size_t size)
-{
-	const size_t p_size = __member_size(p);
-	const size_t q_size = __member_size(q);
-	size_t q_len;	/* Full count of source string length. */
-	size_t len;	/* Count of characters going into destination. */
-
-	if (p_size == SIZE_MAX && q_size == SIZE_MAX)
-		return __real_strlcpy(p, q, size);
-	q_len = strlen(q);
-	len = (q_len >= size) ? size - 1 : q_len;
-	if (__builtin_constant_p(size) && __builtin_constant_p(q_len) && size) {
-		/* Write size is always larger than destination. */
-		if (len >= p_size)
-			__write_overflow();
-	}
-	if (size) {
-		if (len >= p_size)
-			fortify_panic(__func__);
-		__underlying_memcpy(p, q, len);
-		p[len] = '\0';
-	}
-	return q_len;
-}
-
 /* Defined after fortified strnlen() to reuse it. */
 extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy);
 /**
@@ -272,12 +227,6 @@ extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy);
  * @p buffer. The behavior is undefined if the string buffers overlap. The
  * destination @p buffer is always NUL terminated, unless it's zero-sized.
  *
- * Preferred to strlcpy() since the API doesn't require reading memory
- * from the source @q string beyond the specified @size bytes, and since
- * the return value is easier to error-check than strlcpy()'s.
- * In addition, the implementation is robust to the string changing out
- * from underneath it, unlike the current strlcpy() implementation.
- *
  * Preferred to strncpy() since it always returns a valid string, and
  * doesn't unnecessarily force the tail of the destination buffer to be
  * zero padded. If padding is desired please use strscpy_pad().
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e6ba0cc6f2ee..0a22b7245982 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -43,6 +43,8 @@
 #include <linux/cred.h>
 #include <linux/mnt_idmapping.h>
 #include <linux/slab.h>
+#include <linux/maple_tree.h>
+#include <linux/rw_hint.h>
 
 #include <asm/byteorder.h>
 #include <uapi/linux/fs.h>
@@ -309,19 +311,6 @@ struct address_space;
 struct writeback_control;
 struct readahead_control;
 
-/*
- * Write life time hint values.
- * Stored in struct inode as u8.
- */
-enum rw_hint {
-	WRITE_LIFE_NOT_SET	= 0,
-	WRITE_LIFE_NONE		= RWH_WRITE_LIFE_NONE,
-	WRITE_LIFE_SHORT	= RWH_WRITE_LIFE_SHORT,
-	WRITE_LIFE_MEDIUM	= RWH_WRITE_LIFE_MEDIUM,
-	WRITE_LIFE_LONG		= RWH_WRITE_LIFE_LONG,
-	WRITE_LIFE_EXTREME	= RWH_WRITE_LIFE_EXTREME,
-};
-
 /* Match RWF_* bits to IOCB bits */
 #define IOCB_HIPRI		(__force int) RWF_HIPRI
 #define IOCB_DSYNC		(__force int) RWF_DSYNC
@@ -352,6 +341,8 @@ enum rw_hint {
  * unrelated IO (like cache flushing, new IO generation, etc).
  */
 #define IOCB_DIO_CALLER_COMP	(1 << 22)
+/* kiocb is a read or write operation submitted by fs/aio.c. */
+#define IOCB_AIO_RW		(1 << 23)
 
 /* for use in trace events */
 #define TRACE_IOCB_STRINGS \
@@ -482,10 +473,10 @@ struct address_space {
 	pgoff_t			writeback_index;
 	const struct address_space_operations *a_ops;
 	unsigned long		flags;
-	struct rw_semaphore	i_mmap_rwsem;
 	errseq_t		wb_err;
 	spinlock_t		i_private_lock;
 	struct list_head	i_private_list;
+	struct rw_semaphore	i_mmap_rwsem;
 	void *			i_private_data;
 } __attribute__((aligned(sizeof(long)))) __randomize_layout;
 	/*
@@ -677,7 +668,7 @@ struct inode {
 	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
 	unsigned short          i_bytes;
 	u8			i_blkbits;
-	u8			i_write_hint;
+	enum rw_hint		i_write_hint;
 	blkcnt_t		i_blocks;
 
 #ifdef __NEED_I_SIZE_ORDERED
@@ -907,7 +898,8 @@ static inline loff_t i_size_read(const struct inode *inode)
 	preempt_enable();
 	return i_size;
 #else
-	return inode->i_size;
+	/* Pairs with smp_store_release() in i_size_write() */
+	return smp_load_acquire(&inode->i_size);
 #endif
 }
 
@@ -929,7 +921,12 @@ static inline void i_size_write(struct inode *inode, loff_t i_size)
 	inode->i_size = i_size;
 	preempt_enable();
 #else
-	inode->i_size = i_size;
+	/*
+	 * Pairs with smp_load_acquire() in i_size_read() to ensure
+	 * changes related to inode size (such as page contents) are
+	 * visible before we see the changed inode size.
+	 */
+	smp_store_release(&inode->i_size, i_size);
 #endif
 }
 
@@ -1064,6 +1061,7 @@ struct file *get_file_active(struct file **f);
 typedef void *fl_owner_t;
 
 struct file_lock;
+struct file_lease;
 
 /* The following constant reflects the upper bound of the file/locking space */
 #ifndef OFFSET_MAX
@@ -1078,9 +1076,20 @@ static inline struct inode *file_inode(const struct file *f)
 	return f->f_inode;
 }
 
+/*
+ * file_dentry() is a relic from the days that overlayfs was using files with a
+ * "fake" path, meaning, f_path on overlayfs and f_inode on underlying fs.
+ * In those days, file_dentry() was needed to get the underlying fs dentry that
+ * matches f_inode.
+ * Files with "fake" path should not exist nowadays, so use an assertion to make
+ * sure that file_dentry() was not papering over filesystem bugs.
+ */
 static inline struct dentry *file_dentry(const struct file *file)
 {
-	return d_real(file->f_path.dentry, file_inode(file));
+	struct dentry *dentry = file->f_path.dentry;
+
+	WARN_ON_ONCE(d_inode(dentry) != file_inode(file));
+	return dentry;
 }
 
 struct fasync_struct {
@@ -1228,8 +1237,8 @@ struct super_block {
 #endif
 	struct hlist_bl_head	s_roots;	/* alternate root dentries for NFS */
 	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
-	struct block_device	*s_bdev;
-	struct bdev_handle	*s_bdev_handle;
+	struct block_device	*s_bdev;	/* can go away once we use an accessor for @s_bdev_file */
+	struct file		*s_bdev_file;
 	struct backing_dev_info *s_bdi;
 	struct mtd_info		*s_mtd;
 	struct hlist_node	s_instances;
@@ -1255,8 +1264,22 @@ struct super_block {
 	struct fsnotify_mark_connector __rcu	*s_fsnotify_marks;
 #endif
 
+	/*
+	 * q: why are s_id and s_sysfs_name not the same? both are human
+	 * readable strings that identify the filesystem
+	 * a: s_id is allowed to change at runtime; it's used in log messages,
+	 * and we want to when a device starts out as single device (s_id is dev
+	 * name) but then a device is hot added and we have to switch to
+	 * identifying it by UUID
+	 * but s_sysfs_name is a handle for programmatic access, and can't
+	 * change at runtime
+	 */
 	char			s_id[32];	/* Informational name */
 	uuid_t			s_uuid;		/* UUID */
+	u8			s_uuid_len;	/* Default 16, possibly smaller for weird filesystems */
+
+	/* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */
+	char			s_sysfs_name[UUID_STRING_LEN + 1];
 
 	unsigned int		s_max_links;
 
@@ -2005,7 +2028,7 @@ struct file_operations {
 	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
 	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
 	void (*splice_eof)(struct file *file);
-	int (*setlease)(struct file *, int, struct file_lock **, void **);
+	int (*setlease)(struct file *, int, struct file_lease **, void **);
 	long (*fallocate)(struct file *file, int mode, loff_t offset,
 			  loff_t len);
 	void (*show_fdinfo)(struct seq_file *m, struct file *f);
@@ -2101,9 +2124,6 @@ int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 				  struct file *file_out, loff_t pos_out,
 				  loff_t *count, unsigned int remap_flags);
-extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
-				  struct file *file_out, loff_t pos_out,
-				  loff_t len, unsigned int remap_flags);
 extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 				   struct file *file_out, loff_t pos_out,
 				   loff_t len, unsigned int remap_flags);
@@ -2371,7 +2391,7 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
 #define I_CREATING		(1 << 15)
 #define I_DONTCACHE		(1 << 16)
 #define I_SYNC_QUEUED		(1 << 17)
-#define I_PINNING_FSCACHE_WB	(1 << 18)
+#define I_PINNING_NETFS_WB	(1 << 18)
 
 #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
 #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
@@ -2532,6 +2552,44 @@ extern __printf(2, 3)
 int super_setup_bdi_name(struct super_block *sb, char *fmt, ...);
 extern int super_setup_bdi(struct super_block *sb);
 
+static inline void super_set_uuid(struct super_block *sb, const u8 *uuid, unsigned len)
+{
+	if (WARN_ON(len > sizeof(sb->s_uuid)))
+		len = sizeof(sb->s_uuid);
+	sb->s_uuid_len = len;
+	memcpy(&sb->s_uuid, uuid, len);
+}
+
+/* set sb sysfs name based on sb->s_bdev */
+static inline void super_set_sysfs_name_bdev(struct super_block *sb)
+{
+	snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pg", sb->s_bdev);
+}
+
+/* set sb sysfs name based on sb->s_uuid */
+static inline void super_set_sysfs_name_uuid(struct super_block *sb)
+{
+	WARN_ON(sb->s_uuid_len != sizeof(sb->s_uuid));
+	snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pU", sb->s_uuid.b);
+}
+
+/* set sb sysfs name based on sb->s_id */
+static inline void super_set_sysfs_name_id(struct super_block *sb)
+{
+	strscpy(sb->s_sysfs_name, sb->s_id, sizeof(sb->s_sysfs_name));
+}
+
+/* try to use something standard before you use this */
+__printf(2, 3)
+static inline void super_set_sysfs_name_generic(struct super_block *sb, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	vsnprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), fmt, args);
+	va_end(args);
+}
+
 extern int current_umask(void);
 
 extern void ihold(struct inode * inode);
@@ -2928,6 +2986,17 @@ extern bool path_is_under(const struct path *, const struct path *);
 
 extern char *file_path(struct file *, char *, int);
 
+/**
+ * is_dot_dotdot - returns true only if @name is "." or ".."
+ * @name: file name to check
+ * @len: length of file name, in bytes
+ */
+static inline bool is_dot_dotdot(const char *name, size_t len)
+{
+	return len && unlikely(name[0] == '.') &&
+		(len == 1 || (len == 2 && name[1] == '.'));
+}
+
 #include <linux/err.h>
 
 /* needed for stackable file system support */
@@ -3238,7 +3307,7 @@ extern int simple_write_begin(struct file *file, struct address_space *mapping,
 extern const struct address_space_operations ram_aops;
 extern int always_delete_dentry(const struct dentry *);
 extern struct inode *alloc_anon_inode(struct super_block *);
-extern int simple_nosetlease(struct file *, int, struct file_lock **, void **);
+extern int simple_nosetlease(struct file *, int, struct file_lease **, void **);
 extern const struct dentry_operations simple_dentry_operations;
 
 extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
@@ -3260,13 +3329,14 @@ extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
 		const void __user *from, size_t count);
 
 struct offset_ctx {
-	struct xarray		xa;
-	u32			next_offset;
+	struct maple_tree	mt;
+	unsigned long		next_offset;
 };
 
 void simple_offset_init(struct offset_ctx *octx);
 int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry);
 void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry);
+int simple_offset_empty(struct dentry *dentry);
 int simple_offset_rename_exchange(struct inode *old_dir,
 				  struct dentry *old_dentry,
 				  struct inode *new_dir,
@@ -3280,7 +3350,16 @@ extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
 
 extern int generic_check_addressable(unsigned, u64);
 
-extern void generic_set_encrypted_ci_d_ops(struct dentry *dentry);
+extern void generic_set_sb_d_ops(struct super_block *sb);
+
+static inline bool sb_has_encoding(const struct super_block *sb)
+{
+#if IS_ENABLED(CONFIG_UNICODE)
+	return !!sb->s_encoding;
+#else
+	return false;
+#endif
+}
 
 int may_setattr(struct mnt_idmap *idmap, struct inode *inode,
 		unsigned int ia_valid);
@@ -3335,6 +3414,8 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
 		return 0;
 	if (unlikely(flags & ~RWF_SUPPORTED))
 		return -EOPNOTSUPP;
+	if (unlikely((flags & RWF_APPEND) && (flags & RWF_NOAPPEND)))
+		return -EINVAL;
 
 	if (flags & RWF_NOWAIT) {
 		if (!(ki->ki_filp->f_mode & FMODE_NOWAIT))
@@ -3345,6 +3426,12 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
 	if (flags & RWF_SYNC)
 		kiocb_flags |= IOCB_DSYNC;
 
+	if ((flags & RWF_NOAPPEND) && (ki->ki_flags & IOCB_APPEND)) {
+		if (IS_APPEND(file_inode(ki->ki_filp)))
+			return -EPERM;
+		ki->ki_flags &= ~IOCB_APPEND;
+	}
+
 	ki->ki_flags |= kiocb_flags;
 	return 0;
 }
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index a174cedf4d90..bdf7f3eddf0a 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -189,17 +189,20 @@ extern atomic_t fscache_n_write;
 extern atomic_t fscache_n_no_write_space;
 extern atomic_t fscache_n_no_create_space;
 extern atomic_t fscache_n_culled;
+extern atomic_t fscache_n_dio_misfit;
 #define fscache_count_read() atomic_inc(&fscache_n_read)
 #define fscache_count_write() atomic_inc(&fscache_n_write)
 #define fscache_count_no_write_space() atomic_inc(&fscache_n_no_write_space)
 #define fscache_count_no_create_space() atomic_inc(&fscache_n_no_create_space)
 #define fscache_count_culled() atomic_inc(&fscache_n_culled)
+#define fscache_count_dio_misfit() atomic_inc(&fscache_n_dio_misfit)
 #else
 #define fscache_count_read() do {} while(0)
 #define fscache_count_write() do {} while(0)
 #define fscache_count_no_write_space() do {} while(0)
 #define fscache_count_no_create_space() do {} while(0)
 #define fscache_count_culled() do {} while(0)
+#define fscache_count_dio_misfit() do {} while(0)
 #endif
 
 #endif /* _LINUX_FSCACHE_CACHE_H */
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
index 8e312c8323a8..6e8562cbcc43 100644
--- a/include/linux/fscache.h
+++ b/include/linux/fscache.h
@@ -437,9 +437,6 @@ const struct netfs_cache_ops *fscache_operation_valid(const struct netfs_cache_r
  * indicates the cache resources to which the operation state should be
  * attached; @cookie indicates the cache object that will be accessed.
  *
- * This is intended to be called from the ->begin_cache_operation() netfs lib
- * operation as implemented by the network filesystem.
- *
  * @cres->inval_counter is set from @cookie->inval_counter for comparison at
  * the end of the operation.  This allows invalidation during the operation to
  * be detected by the caller.
@@ -629,48 +626,6 @@ static inline void fscache_write_to_cache(struct fscache_cookie *cookie,
 
 }
 
-#if __fscache_available
-bool fscache_dirty_folio(struct address_space *mapping, struct folio *folio,
-		struct fscache_cookie *cookie);
-#else
-#define fscache_dirty_folio(MAPPING, FOLIO, COOKIE) \
-		filemap_dirty_folio(MAPPING, FOLIO)
-#endif
-
-/**
- * fscache_unpin_writeback - Unpin writeback resources
- * @wbc: The writeback control
- * @cookie: The cookie referring to the cache object
- *
- * Unpin the writeback resources pinned by fscache_dirty_folio().  This is
- * intended to be called by the netfs's ->write_inode() method.
- */
-static inline void fscache_unpin_writeback(struct writeback_control *wbc,
-					   struct fscache_cookie *cookie)
-{
-	if (wbc->unpinned_fscache_wb)
-		fscache_unuse_cookie(cookie, NULL, NULL);
-}
-
-/**
- * fscache_clear_inode_writeback - Clear writeback resources pinned by an inode
- * @cookie: The cookie referring to the cache object
- * @inode: The inode to clean up
- * @aux: Auxiliary data to apply to the inode
- *
- * Clear any writeback resources held by an inode when the inode is evicted.
- * This must be called before clear_inode() is called.
- */
-static inline void fscache_clear_inode_writeback(struct fscache_cookie *cookie,
-						 struct inode *inode,
-						 const void *aux)
-{
-	if (inode->i_state & I_PINNING_FSCACHE_WB) {
-		loff_t i_size = i_size_read(inode);
-		fscache_unuse_cookie(cookie, aux, &i_size);
-	}
-}
-
 /**
  * fscache_note_page_release - Note that a netfs page got released
  * @cookie: The cookie corresponding to the file
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 12f9e455d569..772f822dc6b8 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -192,6 +192,8 @@ struct fscrypt_operations {
 					     unsigned int *num_devs);
 };
 
+int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags);
+
 static inline struct fscrypt_inode_info *
 fscrypt_get_inode_info(const struct inode *inode)
 {
@@ -221,15 +223,29 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode)
 }
 
 /*
- * When d_splice_alias() moves a directory's no-key alias to its plaintext alias
- * as a result of the encryption key being added, DCACHE_NOKEY_NAME must be
- * cleared.  Note that we don't have to support arbitrary moves of this flag
- * because fscrypt doesn't allow no-key names to be the source or target of a
- * rename().
+ * When d_splice_alias() moves a directory's no-key alias to its
+ * plaintext alias as a result of the encryption key being added,
+ * DCACHE_NOKEY_NAME must be cleared and there might be an opportunity
+ * to disable d_revalidate.  Note that we don't have to support the
+ * inverse operation because fscrypt doesn't allow no-key names to be
+ * the source or target of a rename().
  */
 static inline void fscrypt_handle_d_move(struct dentry *dentry)
 {
-	dentry->d_flags &= ~DCACHE_NOKEY_NAME;
+	/*
+	 * VFS calls fscrypt_handle_d_move even for non-fscrypt
+	 * filesystems.
+	 */
+	if (dentry->d_flags & DCACHE_NOKEY_NAME) {
+		dentry->d_flags &= ~DCACHE_NOKEY_NAME;
+
+		/*
+		 * Other filesystem features might be handling dentry
+		 * revalidation, in which case it cannot be disabled.
+		 */
+		if (dentry->d_op->d_revalidate == fscrypt_d_revalidate)
+			dentry->d_flags &= ~DCACHE_OP_REVALIDATE;
+	}
 }
 
 /**
@@ -261,6 +277,35 @@ static inline bool fscrypt_is_nokey_name(const struct dentry *dentry)
 	return dentry->d_flags & DCACHE_NOKEY_NAME;
 }
 
+static inline void fscrypt_prepare_dentry(struct dentry *dentry,
+					  bool is_nokey_name)
+{
+	/*
+	 * This code tries to only take ->d_lock when necessary to write
+	 * to ->d_flags.  We shouldn't be peeking on d_flags for
+	 * DCACHE_OP_REVALIDATE unlocked, but in the unlikely case
+	 * there is a race, the worst it can happen is that we fail to
+	 * unset DCACHE_OP_REVALIDATE and pay the cost of an extra
+	 * d_revalidate.
+	 */
+	if (is_nokey_name) {
+		spin_lock(&dentry->d_lock);
+		dentry->d_flags |= DCACHE_NOKEY_NAME;
+		spin_unlock(&dentry->d_lock);
+	} else if (dentry->d_flags & DCACHE_OP_REVALIDATE &&
+		   dentry->d_op->d_revalidate == fscrypt_d_revalidate) {
+		/*
+		 * Unencrypted dentries and encrypted dentries where the
+		 * key is available are always valid from fscrypt
+		 * perspective. Avoid the cost of calling
+		 * fscrypt_d_revalidate unnecessarily.
+		 */
+		spin_lock(&dentry->d_lock);
+		dentry->d_flags &= ~DCACHE_OP_REVALIDATE;
+		spin_unlock(&dentry->d_lock);
+	}
+}
+
 /* crypto.c */
 void fscrypt_enqueue_decrypt_work(struct work_struct *);
 
@@ -368,7 +413,6 @@ int fscrypt_fname_disk_to_usr(const struct inode *inode,
 bool fscrypt_match_name(const struct fscrypt_name *fname,
 			const u8 *de_name, u32 de_name_len);
 u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name);
-int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags);
 
 /* bio.c */
 bool fscrypt_decrypt_bio(struct bio *bio);
@@ -425,6 +469,11 @@ static inline bool fscrypt_is_nokey_name(const struct dentry *dentry)
 	return false;
 }
 
+static inline void fscrypt_prepare_dentry(struct dentry *dentry,
+					  bool is_nokey_name)
+{
+}
+
 /* crypto.c */
 static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work)
 {
@@ -982,6 +1031,9 @@ static inline int fscrypt_prepare_lookup(struct inode *dir,
 	fname->usr_fname = &dentry->d_name;
 	fname->disk_name.name = (unsigned char *)dentry->d_name.name;
 	fname->disk_name.len = dentry->d_name.len;
+
+	fscrypt_prepare_dentry(dentry, false);
+
 	return 0;
 }
 
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 11e6434b8e71..8300a5286988 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -100,6 +100,7 @@ static inline int fsnotify_file(struct file *file, __u32 mask)
 	return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH);
 }
 
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
 /*
  * fsnotify_file_area_perm - permission hook before access to file range
  */
@@ -145,6 +146,24 @@ static inline int fsnotify_open_perm(struct file *file)
 	return fsnotify_file(file, FS_OPEN_PERM);
 }
 
+#else
+static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
+					  const loff_t *ppos, size_t count)
+{
+	return 0;
+}
+
+static inline int fsnotify_file_perm(struct file *file, int perm_mask)
+{
+	return 0;
+}
+
+static inline int fsnotify_open_perm(struct file *file)
+{
+	return 0;
+}
+#endif
+
 /*
  * fsnotify_link_count - inode's link count changed
  */
diff --git a/include/linux/fw_table.h b/include/linux/fw_table.h
index ca49947f0a77..95421860397a 100644
--- a/include/linux/fw_table.h
+++ b/include/linux/fw_table.h
@@ -25,16 +25,35 @@ struct acpi_subtable_proc {
 	int count;
 };
 
+union fw_table_header {
+	struct acpi_table_header acpi;
+	struct acpi_table_cdat cdat;
+};
+
 union acpi_subtable_headers {
 	struct acpi_subtable_header common;
 	struct acpi_hmat_structure hmat;
 	struct acpi_prmt_module_header prmt;
 	struct acpi_cedt_header cedt;
+	struct acpi_cdat_header cdat;
 };
 
 int acpi_parse_entries_array(char *id, unsigned long table_size,
-			     struct acpi_table_header *table_header,
+			     union fw_table_header *table_header,
 			     struct acpi_subtable_proc *proc,
 			     int proc_num, unsigned int max_entries);
 
+int cdat_table_parse(enum acpi_cdat_type type,
+		     acpi_tbl_entry_handler_arg handler_arg, void *arg,
+		     struct acpi_table_cdat *table_header);
+
+/* CXL is the only non-ACPI consumer of the FIRMWARE_TABLE library */
+#if IS_ENABLED(CONFIG_ACPI) && !IS_ENABLED(CONFIG_CXL_BUS)
+#define EXPORT_SYMBOL_FWTBL_LIB(x) EXPORT_SYMBOL_ACPI_LIB(x)
+#define __init_or_fwtbl_lib __init_or_acpilib
+#else
+#define EXPORT_SYMBOL_FWTBL_LIB(x) EXPORT_SYMBOL_NS_GPL(x, CXL)
+#define __init_or_fwtbl_lib
+#endif
+
 #endif
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index de292a007138..e2a916cf29c4 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -353,6 +353,15 @@ static inline bool gfp_has_io_fs(gfp_t gfp)
 	return (gfp & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS);
 }
 
+/*
+ * Check if the gfp flags allow compaction - GFP_NOIO is a really
+ * tricky context because the migration might require IO.
+ */
+static inline bool gfp_compaction_allowed(gfp_t gfp_mask)
+{
+	return IS_ENABLED(CONFIG_COMPACTION) && (gfp_mask & __GFP_IO);
+}
+
 extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma);
 
 #ifdef CONFIG_CONTIG_ALLOC
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index e846bd4e7559..7f75c9a51874 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -635,7 +635,7 @@ struct gpio_device *gpio_device_get(struct gpio_device *gdev);
 void gpio_device_put(struct gpio_device *gdev);
 
 DEFINE_FREE(gpio_device_put, struct gpio_device *,
-	    if (IS_ERR_OR_NULL(_T)) gpio_device_put(_T));
+	    if (!IS_ERR_OR_NULL(_T)) gpio_device_put(_T))
 
 struct device *gpio_device_to_device(struct gpio_device *gdev);
 
@@ -819,6 +819,24 @@ static inline struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc)
 	return ERR_PTR(-ENODEV);
 }
 
+static inline struct gpio_device *gpiod_to_gpio_device(struct gpio_desc *desc)
+{
+	WARN_ON(1);
+	return ERR_PTR(-ENODEV);
+}
+
+static inline int gpio_device_get_base(struct gpio_device *gdev)
+{
+	WARN_ON(1);
+	return -ENODEV;
+}
+
+static inline const char *gpio_device_get_label(struct gpio_device *gdev)
+{
+	WARN_ON(1);
+	return NULL;
+}
+
 static inline int gpiochip_lock_as_irq(struct gpio_chip *gc,
 				       unsigned int offset)
 {
diff --git a/include/linux/gpio_keys.h b/include/linux/gpio_keys.h
index 3f84aeb81e48..80fa930b04c6 100644
--- a/include/linux/gpio_keys.h
+++ b/include/linux/gpio_keys.h
@@ -21,6 +21,7 @@ struct device;
  *			disable button via sysfs
  * @value:		axis value for %EV_ABS
  * @irq:		Irq number in case of interrupt keys
+ * @wakeirq:		Optional dedicated wake-up interrupt
  */
 struct gpio_keys_button {
 	unsigned int code;
@@ -34,6 +35,7 @@ struct gpio_keys_button {
 	bool can_disable;
 	int value;
 	unsigned int irq;
+	unsigned int wakeirq;
 };
 
 /**
diff --git a/include/linux/hid_bpf.h b/include/linux/hid_bpf.h
index 840cd254172d..7118ac28d468 100644
--- a/include/linux/hid_bpf.h
+++ b/include/linux/hid_bpf.h
@@ -77,17 +77,6 @@ enum hid_bpf_attach_flags {
 int hid_bpf_device_event(struct hid_bpf_ctx *ctx);
 int hid_bpf_rdesc_fixup(struct hid_bpf_ctx *ctx);
 
-/* Following functions are kfunc that we export to BPF programs */
-/* available everywhere in HID-BPF */
-__u8 *hid_bpf_get_data(struct hid_bpf_ctx *ctx, unsigned int offset, const size_t __sz);
-
-/* only available in syscall */
-int hid_bpf_attach_prog(unsigned int hid_id, int prog_fd, __u32 flags);
-int hid_bpf_hw_request(struct hid_bpf_ctx *ctx, __u8 *buf, size_t buf__sz,
-		       enum hid_report_type rtype, enum hid_class_request reqtype);
-struct hid_bpf_ctx *hid_bpf_allocate_context(unsigned int hid_id);
-void hid_bpf_release_context(struct hid_bpf_ctx *ctx);
-
 /*
  * Below is HID internal
  */
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 87e3bedf8eb0..641c4567cfa7 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -157,6 +157,7 @@ enum  hrtimer_base_type {
  * @max_hang_time:	Maximum time spent in hrtimer_interrupt
  * @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are
  *			 expired
+ * @online:		CPU is online from an hrtimers point of view
  * @timer_waiters:	A hrtimer_cancel() invocation waits for the timer
  *			callback to finish.
  * @expires_next:	absolute time of the next event, is required for remote
@@ -179,7 +180,8 @@ struct hrtimer_cpu_base {
 	unsigned int			hres_active		: 1,
 					in_hrtirq		: 1,
 					hang_detected		: 1,
-					softirq_activated       : 1;
+					softirq_activated       : 1,
+					online			: 1;
 #ifdef CONFIG_HIGH_RES_TIMERS
 	unsigned int			nr_events;
 	unsigned short			nr_retries;
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 2b00faf98017..6ef0557b4bff 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -164,8 +164,28 @@ struct hv_ring_buffer {
 	u8 buffer[];
 } __packed;
 
+
+/*
+ * If the requested ring buffer size is at least 8 times the size of the
+ * header, steal space from the ring buffer for the header. Otherwise, add
+ * space for the header so that is doesn't take too much of the ring buffer
+ * space.
+ *
+ * The factor of 8 is somewhat arbitrary. The goal is to prevent adding a
+ * relatively small header (4 Kbytes on x86) to a large-ish power-of-2 ring
+ * buffer size (such as 128 Kbytes) and so end up making a nearly twice as
+ * large allocation that will be almost half wasted. As a contrasting example,
+ * on ARM64 with 64 Kbyte page size, we don't want to take 64 Kbytes for the
+ * header from a 128 Kbyte allocation, leaving only 64 Kbytes for the ring.
+ * In this latter case, we must add 64 Kbytes for the header and not worry
+ * about what's wasted.
+ */
+#define VMBUS_HEADER_ADJ(payload_sz) \
+	((payload_sz) >=  8 * sizeof(struct hv_ring_buffer) ? \
+	0 : sizeof(struct hv_ring_buffer))
+
 /* Calculate the proper size of a ringbuffer, it must be page-aligned */
-#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(sizeof(struct hv_ring_buffer) + \
+#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(VMBUS_HEADER_ADJ(payload_sz) + \
 					       (payload_sz))
 
 struct hv_ring_buffer_info {
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 0dae9db27538..652ecb7abeda 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -23,7 +23,7 @@
 #include <linux/swab.h>		/* for swab16 */
 #include <uapi/linux/i2c.h>
 
-extern struct bus_type i2c_bus_type;
+extern const struct bus_type i2c_bus_type;
 extern struct device_type i2c_adapter_type;
 extern struct device_type i2c_client_type;
 
@@ -746,6 +746,8 @@ struct i2c_adapter {
 
 	struct irq_domain *host_notify_domain;
 	struct regulator *bus_regulator;
+
+	struct dentry *debugfs;
 };
 #define to_i2c_adapter(d) container_of(d, struct i2c_adapter, dev)
 
@@ -850,7 +852,6 @@ static inline void i2c_mark_adapter_resumed(struct i2c_adapter *adap)
 
 /* i2c adapter classes (bitmask) */
 #define I2C_CLASS_HWMON		(1<<0)	/* lm_sensors, ... */
-#define I2C_CLASS_DDC		(1<<3)	/* DDC bus on graphics adapters */
 #define I2C_CLASS_SPD		(1<<7)	/* Memory modules */
 /* Warn users that the adapter doesn't support classes anymore */
 #define I2C_CLASS_DEPRECATED	(1<<8)
diff --git a/include/linux/i3c/device.h b/include/linux/i3c/device.h
index 84ed77c04940..e119f11948ef 100644
--- a/include/linux/i3c/device.h
+++ b/include/linux/i3c/device.h
@@ -54,6 +54,7 @@ enum i3c_hdr_mode {
  * struct i3c_priv_xfer - I3C SDR private transfer
  * @rnw: encodes the transfer direction. true for a read, false for a write
  * @len: transfer length in bytes of the transfer
+ * @actual_len: actual length in bytes are transferred by the controller
  * @data: input/output buffer
  * @data.in: input buffer. Must point to a DMA-able buffer
  * @data.out: output buffer. Must point to a DMA-able buffer
@@ -62,6 +63,7 @@ enum i3c_hdr_mode {
 struct i3c_priv_xfer {
 	u8 rnw;
 	u16 len;
+	u16 actual_len;
 	union {
 		void *in;
 		const void *out;
diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h
index 24c1863b86e2..0ca27dd86956 100644
--- a/include/linux/i3c/master.h
+++ b/include/linux/i3c/master.h
@@ -76,7 +76,6 @@ struct i2c_dev_boardinfo {
 /**
  * struct i2c_dev_desc - I2C device descriptor
  * @common: common part of the I2C device descriptor
- * @boardinfo: pointer to the boardinfo attached to this I2C device
  * @dev: I2C device object registered to the I2C framework
  * @addr: I2C device address
  * @lvr: LVR (Legacy Virtual Register) needed by the I3C core to know about
@@ -434,6 +433,8 @@ struct i3c_bus {
  *		      for a future IBI
  *		      This method is mandatory only if ->request_ibi is not
  *		      NULL.
+ * @enable_hotjoin: enable hot join event detect.
+ * @disable_hotjoin: disable hot join event detect.
  */
 struct i3c_master_controller_ops {
 	int (*bus_init)(struct i3c_master_controller *master);
@@ -460,6 +461,8 @@ struct i3c_master_controller_ops {
 	int (*disable_ibi)(struct i3c_dev_desc *dev);
 	void (*recycle_ibi_slot)(struct i3c_dev_desc *dev,
 				 struct i3c_ibi_slot *slot);
+	int (*enable_hotjoin)(struct i3c_master_controller *master);
+	int (*disable_hotjoin)(struct i3c_master_controller *master);
 };
 
 /**
@@ -473,6 +476,7 @@ struct i3c_master_controller_ops {
  * @ops: master operations. See &struct i3c_master_controller_ops
  * @secondary: true if the master is a secondary master
  * @init_done: true when the bus initialization is done
+ * @hotjoin: true if the master support hotjoin
  * @boardinfo.i3c: list of I3C  boardinfo objects
  * @boardinfo.i2c: list of I2C boardinfo objects
  * @boardinfo: board-level information attached to devices connected on the bus
@@ -495,6 +499,7 @@ struct i3c_master_controller {
 	const struct i3c_master_controller_ops *ops;
 	unsigned int secondary : 1;
 	unsigned int init_done : 1;
+	unsigned int hotjoin: 1;
 	struct {
 		struct list_head i3c;
 		struct list_head i2c;
@@ -551,6 +556,8 @@ int i3c_master_register(struct i3c_master_controller *master,
 			const struct i3c_master_controller_ops *ops,
 			bool secondary);
 void i3c_master_unregister(struct i3c_master_controller *master);
+int i3c_master_enable_hotjoin(struct i3c_master_controller *master);
+int i3c_master_disable_hotjoin(struct i3c_master_controller *master);
 
 /**
  * i3c_dev_get_master_data() - get master private data attached to an I3C
diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h
index 7852f6c9a714..719cf9cc6e1a 100644
--- a/include/linux/iio/adc/ad_sigma_delta.h
+++ b/include/linux/iio/adc/ad_sigma_delta.h
@@ -8,6 +8,8 @@
 #ifndef __AD_SIGMA_DELTA_H__
 #define __AD_SIGMA_DELTA_H__
 
+#include <linux/iio/iio.h>
+
 enum ad_sigma_delta_mode {
 	AD_SD_MODE_CONTINUOUS = 0,
 	AD_SD_MODE_SINGLE = 1,
@@ -99,7 +101,7 @@ struct ad_sigma_delta {
 	 * 'rx_buf' is up to 32 bits per sample + 64 bit timestamp,
 	 * rounded to 16 bytes to take into account padding.
 	 */
-	uint8_t				tx_buf[4] ____cacheline_aligned;
+	uint8_t				tx_buf[4] __aligned(IIO_DMA_MINALIGN);
 	uint8_t				rx_buf[16] __aligned(8);
 };
 
diff --git a/include/linux/iio/adc/adi-axi-adc.h b/include/linux/iio/adc/adi-axi-adc.h
index 52620e5b8052..b7904992d561 100644
--- a/include/linux/iio/adc/adi-axi-adc.h
+++ b/include/linux/iio/adc/adi-axi-adc.h
@@ -41,6 +41,7 @@ struct adi_axi_adc_chip_info {
  * @reg_access		IIO debugfs_reg_access hook for the client ADC
  * @read_raw		IIO read_raw hook for the client ADC
  * @write_raw		IIO write_raw hook for the client ADC
+ * @read_avail		IIO read_avail hook for the client ADC
  */
 struct adi_axi_adc_conv {
 	const struct adi_axi_adc_chip_info		*chip_info;
@@ -54,6 +55,9 @@ struct adi_axi_adc_conv {
 	int (*write_raw)(struct adi_axi_adc_conv *conv,
 			 struct iio_chan_spec const *chan,
 			 int val, int val2, long mask);
+	int (*read_avail)(struct adi_axi_adc_conv *conv,
+			  struct iio_chan_spec const *chan,
+			  const int **val, int *type, int *length, long mask);
 };
 
 struct adi_axi_adc_conv *devm_adi_axi_adc_conv_register(struct device *dev,
diff --git a/include/linux/iio/buffer-dma.h b/include/linux/iio/buffer-dma.h
index 6564bdcdac66..18d3702fa95d 100644
--- a/include/linux/iio/buffer-dma.h
+++ b/include/linux/iio/buffer-dma.h
@@ -19,14 +19,12 @@ struct device;
 
 /**
  * enum iio_block_state - State of a struct iio_dma_buffer_block
- * @IIO_BLOCK_STATE_DEQUEUED: Block is not queued
  * @IIO_BLOCK_STATE_QUEUED: Block is on the incoming queue
  * @IIO_BLOCK_STATE_ACTIVE: Block is currently being processed by the DMA
  * @IIO_BLOCK_STATE_DONE: Block is on the outgoing queue
  * @IIO_BLOCK_STATE_DEAD: Block has been marked as to be freed
  */
 enum iio_block_state {
-	IIO_BLOCK_STATE_DEQUEUED,
 	IIO_BLOCK_STATE_QUEUED,
 	IIO_BLOCK_STATE_ACTIVE,
 	IIO_BLOCK_STATE_DONE,
@@ -73,12 +71,15 @@ struct iio_dma_buffer_block {
  * @active_block: Block being used in read()
  * @pos: Read offset in the active block
  * @block_size: Size of each block
+ * @next_dequeue: index of next block that will be dequeued
  */
 struct iio_dma_buffer_queue_fileio {
 	struct iio_dma_buffer_block *blocks[2];
 	struct iio_dma_buffer_block *active_block;
 	size_t pos;
 	size_t block_size;
+
+	unsigned int next_dequeue;
 };
 
 /**
@@ -93,7 +94,6 @@ struct iio_dma_buffer_queue_fileio {
  *   list and typically also a list of active blocks in the part that handles
  *   the DMA controller
  * @incoming: List of buffers on the incoming queue
- * @outgoing: List of buffers on the outgoing queue
  * @active: Whether the buffer is currently active
  * @fileio: FileIO state
  */
@@ -105,7 +105,6 @@ struct iio_dma_buffer_queue {
 	struct mutex lock;
 	spinlock_t list_lock;
 	struct list_head incoming;
-	struct list_head outgoing;
 
 	bool active;
 
diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h
index 607c3a89a647..f9ae5cdd884f 100644
--- a/include/linux/iio/common/st_sensors.h
+++ b/include/linux/iio/common/st_sensors.h
@@ -258,9 +258,9 @@ struct st_sensor_data {
 	bool hw_irq_trigger;
 	s64 hw_timestamp;
 
-	char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] ____cacheline_aligned;
-
 	struct mutex odr_lock;
+
+	char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] __aligned(IIO_DMA_MINALIGN);
 };
 
 #ifdef CONFIG_IIO_BUFFER
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index d0ce3b71106a..c5b36d2c1e73 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -434,13 +434,7 @@ struct iio_trigger; /* forward declaration */
  * @update_scan_mode:	function to configure device and scan buffer when
  *			channels have changed
  * @debugfs_reg_access:	function to read or write register value of device
- * @of_xlate:		function pointer to obtain channel specifier index.
- *			When #iio-cells is greater than '0', the driver could
- *			provide a custom of_xlate function that reads the
- *			*args* and returns the appropriate index in registered
- *			IIO channels array.
  * @fwnode_xlate:	fwnode based function pointer to obtain channel specifier index.
- *			Functionally the same as @of_xlate.
  * @hwfifo_set_watermark: function pointer to set the current hardware
  *			fifo watermark level; see hwfifo_* entries in
  *			Documentation/ABI/testing/sysfs-bus-iio for details on
diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h
index dc9ea299e088..8898966bc0f0 100644
--- a/include/linux/iio/imu/adis.h
+++ b/include/linux/iio/imu/adis.h
@@ -11,6 +11,7 @@
 
 #include <linux/spi/spi.h>
 #include <linux/interrupt.h>
+#include <linux/iio/iio.h>
 #include <linux/iio/types.h>
 
 #define ADIS_WRITE_REG(reg) ((0x80 | (reg)))
@@ -131,7 +132,7 @@ struct adis {
 	unsigned long		irq_flag;
 	void			*buffer;
 
-	u8			tx[10] ____cacheline_aligned;
+	u8			tx[10] __aligned(IIO_DMA_MINALIGN);
 	u8			rx[4];
 };
 
diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h
index 117bde7d6ad7..d89982c98368 100644
--- a/include/linux/iio/types.h
+++ b/include/linux/iio/types.h
@@ -68,6 +68,7 @@ enum iio_chan_info_enum {
 	IIO_CHAN_INFO_THERMOCOUPLE_TYPE,
 	IIO_CHAN_INFO_CALIBAMBIENT,
 	IIO_CHAN_INFO_ZEROPOINT,
+	IIO_CHAN_INFO_TROUGH,
 };
 
 #endif /* _IIO_TYPES_H_ */
diff --git a/include/linux/init.h b/include/linux/init.h
index 01b52c9c7526..3fa3f6241350 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -179,6 +179,13 @@ extern void (*late_time_init)(void);
 
 extern bool initcall_debug;
 
+#ifdef MODULE
+extern struct module __this_module;
+#define THIS_MODULE (&__this_module)
+#else
+#define THIS_MODULE ((struct module *)0)
+#endif
+
 #endif
   
 #ifndef MODULE
diff --git a/include/linux/input/as5011.h b/include/linux/input/as5011.h
index 5fba52a56cd6..5705d5de3aea 100644
--- a/include/linux/input/as5011.h
+++ b/include/linux/input/as5011.h
@@ -7,7 +7,6 @@
  */
 
 struct as5011_platform_data {
-	unsigned int button_gpio;
 	unsigned int axis_irq; /* irq number */
 	unsigned long axis_irqflags;
 	char xp, xn; /* threshold for x axis */
diff --git a/include/linux/input/navpoint.h b/include/linux/input/navpoint.h
index d464ffb4db52..5192ae3f5ec1 100644
--- a/include/linux/input/navpoint.h
+++ b/include/linux/input/navpoint.h
@@ -5,5 +5,4 @@
 
 struct navpoint_platform_data {
 	int		port;		/* PXA SSP port for pxa_ssp_request() */
-	int		gpio;		/* GPIO for power on/off */
 };
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 25142a0e2fc2..86cf1f7ae389 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -100,6 +100,30 @@ struct io_pgtable_cfg {
 	const struct iommu_flush_ops	*tlb;
 	struct device			*iommu_dev;
 
+	/**
+	 * @alloc: Custom page allocator.
+	 *
+	 * Optional hook used to allocate page tables. If this function is NULL,
+	 * @free must be NULL too.
+	 *
+	 * Memory returned should be zeroed and suitable for dma_map_single() and
+	 * virt_to_phys().
+	 *
+	 * Not all formats support custom page allocators. Before considering
+	 * passing a non-NULL value, make sure the chosen page format supports
+	 * this feature.
+	 */
+	void *(*alloc)(void *cookie, size_t size, gfp_t gfp);
+
+	/**
+	 * @free: Custom page de-allocator.
+	 *
+	 * Optional hook used to free page tables allocated with the @alloc
+	 * hook. Must be non-NULL if @alloc is not NULL, must be NULL
+	 * otherwise.
+	 */
+	void (*free)(void *cookie, void *pages, size_t size);
+
 	/* Low-level data specific to the table format */
 	union {
 		struct {
@@ -242,15 +266,25 @@ io_pgtable_tlb_add_page(struct io_pgtable *iop,
 }
 
 /**
+ * enum io_pgtable_caps - IO page table backend capabilities.
+ */
+enum io_pgtable_caps {
+	/** @IO_PGTABLE_CAP_CUSTOM_ALLOCATOR: Backend accepts custom page table allocators. */
+	IO_PGTABLE_CAP_CUSTOM_ALLOCATOR = BIT(0),
+};
+
+/**
  * struct io_pgtable_init_fns - Alloc/free a set of page tables for a
  *                              particular format.
  *
  * @alloc: Allocate a set of page tables described by cfg.
  * @free:  Free the page tables associated with iop.
+ * @caps:  Combination of @io_pgtable_caps flags encoding the backend capabilities.
  */
 struct io_pgtable_init_fns {
 	struct io_pgtable *(*alloc)(struct io_pgtable_cfg *cfg, void *cookie);
 	void (*free)(struct io_pgtable *iop);
+	u32 caps;
 };
 
 extern struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s1_init_fns;
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 854ad67a5f70..e24893625085 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -2,6 +2,7 @@
 #define IO_URING_TYPES_H
 
 #include <linux/blkdev.h>
+#include <linux/hashtable.h>
 #include <linux/task_work.h>
 #include <linux/bitmap.h>
 #include <linux/llist.h>
@@ -240,12 +241,14 @@ struct io_ring_ctx {
 		unsigned int		poll_activated: 1;
 		unsigned int		drain_disabled: 1;
 		unsigned int		compat: 1;
+		unsigned int		iowq_limits_set : 1;
 
 		struct task_struct	*submitter_task;
 		struct io_rings		*rings;
 		struct percpu_ref	refs;
 
 		enum task_work_notify_mode	notify_method;
+		unsigned			sq_thread_idle;
 	} ____cacheline_aligned_in_smp;
 
 	/* submission data */
@@ -274,10 +277,20 @@ struct io_ring_ctx {
 		 */
 		struct io_rsrc_node	*rsrc_node;
 		atomic_t		cancel_seq;
+
+		/*
+		 * ->iopoll_list is protected by the ctx->uring_lock for
+		 * io_uring instances that don't use IORING_SETUP_SQPOLL.
+		 * For SQPOLL, only the single threaded io_sq_thread() will
+		 * manipulate the list, hence no extra locking is needed there.
+		 */
+		bool			poll_multi_queue;
+		struct io_wq_work_list	iopoll_list;
+
 		struct io_file_table	file_table;
+		struct io_mapped_ubuf	**user_bufs;
 		unsigned		nr_user_files;
 		unsigned		nr_user_bufs;
-		struct io_mapped_ubuf	**user_bufs;
 
 		struct io_submit_state	submit_state;
 
@@ -289,15 +302,6 @@ struct io_ring_ctx {
 		struct io_alloc_cache	netmsg_cache;
 
 		/*
-		 * ->iopoll_list is protected by the ctx->uring_lock for
-		 * io_uring instances that don't use IORING_SETUP_SQPOLL.
-		 * For SQPOLL, only the single threaded io_sq_thread() will
-		 * manipulate the list, hence no extra locking is needed there.
-		 */
-		struct io_wq_work_list	iopoll_list;
-		bool			poll_multi_queue;
-
-		/*
 		 * Any cancelable uring_cmd is added to this list in
 		 * ->uring_cmd() by io_uring_cmd_insert_cancelable()
 		 */
@@ -343,8 +347,8 @@ struct io_ring_ctx {
 	spinlock_t		completion_lock;
 
 	/* IRQ completion list, under ->completion_lock */
-	struct io_wq_work_list	locked_free_list;
 	unsigned int		locked_free_nr;
+	struct io_wq_work_list	locked_free_list;
 
 	struct list_head	io_buffers_comp;
 	struct list_head	cq_overflow_list;
@@ -366,9 +370,6 @@ struct io_ring_ctx {
 	unsigned int		file_alloc_start;
 	unsigned int		file_alloc_end;
 
-	struct xarray		personalities;
-	u32			pers_next;
-
 	struct list_head	io_buffers_cache;
 
 	/* deferred free list, protected by ->uring_lock */
@@ -389,6 +390,9 @@ struct io_ring_ctx {
 	struct wait_queue_head		rsrc_quiesce_wq;
 	unsigned			rsrc_quiesce;
 
+	u32			pers_next;
+	struct xarray		personalities;
+
 	/* hashed buffered write serialization */
 	struct io_wq_hash		*hash_map;
 
@@ -405,11 +409,22 @@ struct io_ring_ctx {
 
 	/* io-wq management, e.g. thread count */
 	u32				iowq_limits[2];
-	bool				iowq_limits_set;
 
 	struct callback_head		poll_wq_task_work;
 	struct list_head		defer_list;
-	unsigned			sq_thread_idle;
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	struct list_head	napi_list;	/* track busy poll napi_id */
+	spinlock_t		napi_lock;	/* napi_list lock */
+
+	/* napi busy poll default timeout */
+	unsigned int		napi_busy_poll_to;
+	bool			napi_prefer_busy_poll;
+	bool			napi_enabled;
+
+	DECLARE_HASHTABLE(napi_ht, 4);
+#endif
+
 	/* protected by ->completion_lock */
 	unsigned			evfd_last_cq_tail;
 
@@ -455,7 +470,6 @@ enum {
 	REQ_F_SKIP_LINK_CQES_BIT,
 	REQ_F_SINGLE_POLL_BIT,
 	REQ_F_DOUBLE_POLL_BIT,
-	REQ_F_PARTIAL_IO_BIT,
 	REQ_F_APOLL_MULTISHOT_BIT,
 	REQ_F_CLEAR_POLLIN_BIT,
 	REQ_F_HASH_LOCKED_BIT,
@@ -463,75 +477,88 @@ enum {
 	REQ_F_SUPPORT_NOWAIT_BIT,
 	REQ_F_ISREG_BIT,
 	REQ_F_POLL_NO_LAZY_BIT,
+	REQ_F_CANCEL_SEQ_BIT,
+	REQ_F_CAN_POLL_BIT,
+	REQ_F_BL_EMPTY_BIT,
+	REQ_F_BL_NO_RECYCLE_BIT,
 
 	/* not a real bit, just to check we're not overflowing the space */
 	__REQ_F_LAST_BIT,
 };
 
+typedef u64 __bitwise io_req_flags_t;
+#define IO_REQ_FLAG(bitno)	((__force io_req_flags_t) BIT_ULL((bitno)))
+
 enum {
 	/* ctx owns file */
-	REQ_F_FIXED_FILE	= BIT(REQ_F_FIXED_FILE_BIT),
+	REQ_F_FIXED_FILE	= IO_REQ_FLAG(REQ_F_FIXED_FILE_BIT),
 	/* drain existing IO first */
-	REQ_F_IO_DRAIN		= BIT(REQ_F_IO_DRAIN_BIT),
+	REQ_F_IO_DRAIN		= IO_REQ_FLAG(REQ_F_IO_DRAIN_BIT),
 	/* linked sqes */
-	REQ_F_LINK		= BIT(REQ_F_LINK_BIT),
+	REQ_F_LINK		= IO_REQ_FLAG(REQ_F_LINK_BIT),
 	/* doesn't sever on completion < 0 */
-	REQ_F_HARDLINK		= BIT(REQ_F_HARDLINK_BIT),
+	REQ_F_HARDLINK		= IO_REQ_FLAG(REQ_F_HARDLINK_BIT),
 	/* IOSQE_ASYNC */
-	REQ_F_FORCE_ASYNC	= BIT(REQ_F_FORCE_ASYNC_BIT),
+	REQ_F_FORCE_ASYNC	= IO_REQ_FLAG(REQ_F_FORCE_ASYNC_BIT),
 	/* IOSQE_BUFFER_SELECT */
-	REQ_F_BUFFER_SELECT	= BIT(REQ_F_BUFFER_SELECT_BIT),
+	REQ_F_BUFFER_SELECT	= IO_REQ_FLAG(REQ_F_BUFFER_SELECT_BIT),
 	/* IOSQE_CQE_SKIP_SUCCESS */
-	REQ_F_CQE_SKIP		= BIT(REQ_F_CQE_SKIP_BIT),
+	REQ_F_CQE_SKIP		= IO_REQ_FLAG(REQ_F_CQE_SKIP_BIT),
 
 	/* fail rest of links */
-	REQ_F_FAIL		= BIT(REQ_F_FAIL_BIT),
+	REQ_F_FAIL		= IO_REQ_FLAG(REQ_F_FAIL_BIT),
 	/* on inflight list, should be cancelled and waited on exit reliably */
-	REQ_F_INFLIGHT		= BIT(REQ_F_INFLIGHT_BIT),
+	REQ_F_INFLIGHT		= IO_REQ_FLAG(REQ_F_INFLIGHT_BIT),
 	/* read/write uses file position */
-	REQ_F_CUR_POS		= BIT(REQ_F_CUR_POS_BIT),
+	REQ_F_CUR_POS		= IO_REQ_FLAG(REQ_F_CUR_POS_BIT),
 	/* must not punt to workers */
-	REQ_F_NOWAIT		= BIT(REQ_F_NOWAIT_BIT),
+	REQ_F_NOWAIT		= IO_REQ_FLAG(REQ_F_NOWAIT_BIT),
 	/* has or had linked timeout */
-	REQ_F_LINK_TIMEOUT	= BIT(REQ_F_LINK_TIMEOUT_BIT),
+	REQ_F_LINK_TIMEOUT	= IO_REQ_FLAG(REQ_F_LINK_TIMEOUT_BIT),
 	/* needs cleanup */
-	REQ_F_NEED_CLEANUP	= BIT(REQ_F_NEED_CLEANUP_BIT),
+	REQ_F_NEED_CLEANUP	= IO_REQ_FLAG(REQ_F_NEED_CLEANUP_BIT),
 	/* already went through poll handler */
-	REQ_F_POLLED		= BIT(REQ_F_POLLED_BIT),
+	REQ_F_POLLED		= IO_REQ_FLAG(REQ_F_POLLED_BIT),
 	/* buffer already selected */
-	REQ_F_BUFFER_SELECTED	= BIT(REQ_F_BUFFER_SELECTED_BIT),
+	REQ_F_BUFFER_SELECTED	= IO_REQ_FLAG(REQ_F_BUFFER_SELECTED_BIT),
 	/* buffer selected from ring, needs commit */
-	REQ_F_BUFFER_RING	= BIT(REQ_F_BUFFER_RING_BIT),
+	REQ_F_BUFFER_RING	= IO_REQ_FLAG(REQ_F_BUFFER_RING_BIT),
 	/* caller should reissue async */
-	REQ_F_REISSUE		= BIT(REQ_F_REISSUE_BIT),
+	REQ_F_REISSUE		= IO_REQ_FLAG(REQ_F_REISSUE_BIT),
 	/* supports async reads/writes */
-	REQ_F_SUPPORT_NOWAIT	= BIT(REQ_F_SUPPORT_NOWAIT_BIT),
+	REQ_F_SUPPORT_NOWAIT	= IO_REQ_FLAG(REQ_F_SUPPORT_NOWAIT_BIT),
 	/* regular file */
-	REQ_F_ISREG		= BIT(REQ_F_ISREG_BIT),
+	REQ_F_ISREG		= IO_REQ_FLAG(REQ_F_ISREG_BIT),
 	/* has creds assigned */
-	REQ_F_CREDS		= BIT(REQ_F_CREDS_BIT),
+	REQ_F_CREDS		= IO_REQ_FLAG(REQ_F_CREDS_BIT),
 	/* skip refcounting if not set */
-	REQ_F_REFCOUNT		= BIT(REQ_F_REFCOUNT_BIT),
+	REQ_F_REFCOUNT		= IO_REQ_FLAG(REQ_F_REFCOUNT_BIT),
 	/* there is a linked timeout that has to be armed */
-	REQ_F_ARM_LTIMEOUT	= BIT(REQ_F_ARM_LTIMEOUT_BIT),
+	REQ_F_ARM_LTIMEOUT	= IO_REQ_FLAG(REQ_F_ARM_LTIMEOUT_BIT),
 	/* ->async_data allocated */
-	REQ_F_ASYNC_DATA	= BIT(REQ_F_ASYNC_DATA_BIT),
+	REQ_F_ASYNC_DATA	= IO_REQ_FLAG(REQ_F_ASYNC_DATA_BIT),
 	/* don't post CQEs while failing linked requests */
-	REQ_F_SKIP_LINK_CQES	= BIT(REQ_F_SKIP_LINK_CQES_BIT),
+	REQ_F_SKIP_LINK_CQES	= IO_REQ_FLAG(REQ_F_SKIP_LINK_CQES_BIT),
 	/* single poll may be active */
-	REQ_F_SINGLE_POLL	= BIT(REQ_F_SINGLE_POLL_BIT),
+	REQ_F_SINGLE_POLL	= IO_REQ_FLAG(REQ_F_SINGLE_POLL_BIT),
 	/* double poll may active */
-	REQ_F_DOUBLE_POLL	= BIT(REQ_F_DOUBLE_POLL_BIT),
-	/* request has already done partial IO */
-	REQ_F_PARTIAL_IO	= BIT(REQ_F_PARTIAL_IO_BIT),
+	REQ_F_DOUBLE_POLL	= IO_REQ_FLAG(REQ_F_DOUBLE_POLL_BIT),
 	/* fast poll multishot mode */
-	REQ_F_APOLL_MULTISHOT	= BIT(REQ_F_APOLL_MULTISHOT_BIT),
+	REQ_F_APOLL_MULTISHOT	= IO_REQ_FLAG(REQ_F_APOLL_MULTISHOT_BIT),
 	/* recvmsg special flag, clear EPOLLIN */
-	REQ_F_CLEAR_POLLIN	= BIT(REQ_F_CLEAR_POLLIN_BIT),
+	REQ_F_CLEAR_POLLIN	= IO_REQ_FLAG(REQ_F_CLEAR_POLLIN_BIT),
 	/* hashed into ->cancel_hash_locked, protected by ->uring_lock */
-	REQ_F_HASH_LOCKED	= BIT(REQ_F_HASH_LOCKED_BIT),
+	REQ_F_HASH_LOCKED	= IO_REQ_FLAG(REQ_F_HASH_LOCKED_BIT),
 	/* don't use lazy poll wake for this request */
-	REQ_F_POLL_NO_LAZY	= BIT(REQ_F_POLL_NO_LAZY_BIT),
+	REQ_F_POLL_NO_LAZY	= IO_REQ_FLAG(REQ_F_POLL_NO_LAZY_BIT),
+	/* cancel sequence is set and valid */
+	REQ_F_CANCEL_SEQ	= IO_REQ_FLAG(REQ_F_CANCEL_SEQ_BIT),
+	/* file is pollable */
+	REQ_F_CAN_POLL		= IO_REQ_FLAG(REQ_F_CAN_POLL_BIT),
+	/* buffer list was empty after selection of buffer */
+	REQ_F_BL_EMPTY		= IO_REQ_FLAG(REQ_F_BL_EMPTY_BIT),
+	/* don't recycle provided buffers for this request */
+	REQ_F_BL_NO_RECYCLE	= IO_REQ_FLAG(REQ_F_BL_NO_RECYCLE_BIT),
 };
 
 typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts);
@@ -592,15 +619,17 @@ struct io_kiocb {
 	 * and after selection it points to the buffer ID itself.
 	 */
 	u16				buf_index;
-	unsigned int			flags;
+
+	unsigned			nr_tw;
+
+	/* REQ_F_* flags */
+	io_req_flags_t			flags;
 
 	struct io_cqe			cqe;
 
 	struct io_ring_ctx		*ctx;
 	struct task_struct		*task;
 
-	struct io_rsrc_node		*rsrc_node;
-
 	union {
 		/* store used ubuf, so we can prevent reloading */
 		struct io_mapped_ubuf	*imu;
@@ -621,10 +650,12 @@ struct io_kiocb {
 		/* cache ->apoll->events */
 		__poll_t apoll_events;
 	};
+
+	struct io_rsrc_node		*rsrc_node;
+
 	atomic_t			refs;
 	atomic_t			poll_refs;
 	struct io_task_work		io_task_work;
-	unsigned			nr_tw;
 	/* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */
 	struct hlist_node		hash_node;
 	/* internal polling, see IORING_FEAT_FAST_POLL */
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 96dd0acbba44..6fc1c858013d 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -293,22 +293,32 @@ struct iomap_ioend {
 	struct list_head	io_list;	/* next ioend in chain */
 	u16			io_type;
 	u16			io_flags;	/* IOMAP_F_* */
-	u32			io_folios;	/* folios added to ioend */
 	struct inode		*io_inode;	/* file being written to */
 	size_t			io_size;	/* size of the extent */
 	loff_t			io_offset;	/* offset in the file */
 	sector_t		io_sector;	/* start sector of ioend */
-	struct bio		*io_bio;	/* bio being built */
-	struct bio		io_inline_bio;	/* MUST BE LAST! */
+	struct bio		io_bio;		/* MUST BE LAST! */
 };
 
+static inline struct iomap_ioend *iomap_ioend_from_bio(struct bio *bio)
+{
+	return container_of(bio, struct iomap_ioend, io_bio);
+}
+
 struct iomap_writeback_ops {
 	/*
 	 * Required, maps the blocks so that writeback can be performed on
 	 * the range starting at offset.
+	 *
+	 * Can return arbitrarily large regions, but we need to call into it at
+	 * least once per folio to allow the file systems to synchronize with
+	 * the write path that could be invalidating mappings.
+	 *
+	 * An existing mapping from a previous call to this method can be reused
+	 * by the file system if it is still valid.
 	 */
 	int (*map_blocks)(struct iomap_writepage_ctx *wpc, struct inode *inode,
-				loff_t offset);
+			  loff_t offset, unsigned len);
 
 	/*
 	 * Optional, allows the file systems to perform actions just before
@@ -329,6 +339,7 @@ struct iomap_writepage_ctx {
 	struct iomap		iomap;
 	struct iomap_ioend	*ioend;
 	const struct iomap_writeback_ops *ops;
+	u32			nr_folios;	/* folios added to the ioend */
 };
 
 void iomap_finish_ioends(struct iomap_ioend *ioend, int error);
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 6291aa7b079b..5e27cb3a3be9 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -106,7 +106,7 @@ struct iommu_domain {
 	unsigned type;
 	const struct iommu_domain_ops *ops;
 	const struct iommu_dirty_ops *dirty_ops;
-
+	const struct iommu_ops *owner; /* Whose domain_alloc we came from */
 	unsigned long pgsize_bitmap;	/* Bitmap of page sizes in use */
 	struct iommu_domain_geometry geometry;
 	struct iommu_dma_cookie *iova_cookie;
@@ -121,6 +121,11 @@ struct iommu_domain {
 		struct {	/* IOMMU_DOMAIN_SVA */
 			struct mm_struct *mm;
 			int users;
+			/*
+			 * Next iommu_domain in mm->iommu_mm->sva-domains list
+			 * protected by iommu_sva_lock.
+			 */
+			struct list_head next;
 		};
 	};
 };
@@ -285,6 +290,23 @@ struct iommu_user_data {
 };
 
 /**
+ * struct iommu_user_data_array - iommu driver specific user space data array
+ * @type: The data type of all the entries in the user buffer array
+ * @uptr: Pointer to the user buffer array
+ * @entry_len: The fixed-width length of an entry in the array, in bytes
+ * @entry_num: The number of total entries in the array
+ *
+ * The user buffer includes an array of requests with format defined in
+ * include/uapi/linux/iommufd.h
+ */
+struct iommu_user_data_array {
+	unsigned int type;
+	void __user *uptr;
+	size_t entry_len;
+	u32 entry_num;
+};
+
+/**
  * __iommu_copy_struct_from_user - Copy iommu driver specific user space data
  * @dst_data: Pointer to an iommu driver specific user data that is defined in
  *            include/uapi/linux/iommufd.h
@@ -325,6 +347,57 @@ static inline int __iommu_copy_struct_from_user(
 				      offsetofend(typeof(*kdst), min_last))
 
 /**
+ * __iommu_copy_struct_from_user_array - Copy iommu driver specific user space
+ *                                       data from an iommu_user_data_array
+ * @dst_data: Pointer to an iommu driver specific user data that is defined in
+ *            include/uapi/linux/iommufd.h
+ * @src_array: Pointer to a struct iommu_user_data_array for a user space array
+ * @data_type: The data type of the @dst_data. Must match with @src_array.type
+ * @index: Index to the location in the array to copy user data from
+ * @data_len: Length of current user data structure, i.e. sizeof(struct _dst)
+ * @min_len: Initial length of user data structure for backward compatibility.
+ *           This should be offsetofend using the last member in the user data
+ *           struct that was initially added to include/uapi/linux/iommufd.h
+ */
+static inline int __iommu_copy_struct_from_user_array(
+	void *dst_data, const struct iommu_user_data_array *src_array,
+	unsigned int data_type, unsigned int index, size_t data_len,
+	size_t min_len)
+{
+	struct iommu_user_data src_data;
+
+	if (WARN_ON(!src_array || index >= src_array->entry_num))
+		return -EINVAL;
+	if (!src_array->entry_num)
+		return -EINVAL;
+	src_data.uptr = src_array->uptr + src_array->entry_len * index;
+	src_data.len = src_array->entry_len;
+	src_data.type = src_array->type;
+
+	return __iommu_copy_struct_from_user(dst_data, &src_data, data_type,
+					     data_len, min_len);
+}
+
+/**
+ * iommu_copy_struct_from_user_array - Copy iommu driver specific user space
+ *                                     data from an iommu_user_data_array
+ * @kdst: Pointer to an iommu driver specific user data that is defined in
+ *        include/uapi/linux/iommufd.h
+ * @user_array: Pointer to a struct iommu_user_data_array for a user space
+ *              array
+ * @data_type: The data type of the @kdst. Must match with @user_array->type
+ * @index: Index to the location in the array to copy user data from
+ * @min_last: The last member of the data structure @kdst points in the
+ *            initial version.
+ * Return 0 for success, otherwise -error.
+ */
+#define iommu_copy_struct_from_user_array(kdst, user_array, data_type, index, \
+					  min_last)                           \
+	__iommu_copy_struct_from_user_array(                                  \
+		kdst, user_array, data_type, index, sizeof(*(kdst)),          \
+		offsetofend(typeof(*(kdst)), min_last))
+
+/**
  * struct iommu_ops - iommu ops and capabilities
  * @capable: check capability
  * @hw_info: report iommu hardware information. The data buffer returned by this
@@ -440,6 +513,13 @@ struct iommu_ops {
  * @iotlb_sync_map: Sync mappings created recently using @map to the hardware
  * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush
  *            queue
+ * @cache_invalidate_user: Flush hardware cache for user space IO page table.
+ *                         The @domain must be IOMMU_DOMAIN_NESTED. The @array
+ *                         passes in the cache invalidation requests, in form
+ *                         of a driver data structure. The driver must update
+ *                         array->entry_num to report the number of handled
+ *                         invalidation requests. The driver data structure
+ *                         must be defined in include/uapi/linux/iommufd.h
  * @iova_to_phys: translate iova to physical address
  * @enforce_cache_coherency: Prevent any kind of DMA from bypassing IOMMU_CACHE,
  *                           including no-snoop TLPs on PCIe or other platform
@@ -465,6 +545,8 @@ struct iommu_domain_ops {
 			      size_t size);
 	void (*iotlb_sync)(struct iommu_domain *domain,
 			   struct iommu_iotlb_gather *iotlb_gather);
+	int (*cache_invalidate_user)(struct iommu_domain *domain,
+				     struct iommu_user_data_array *array);
 
 	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain,
 				    dma_addr_t iova);
@@ -810,6 +892,14 @@ struct iommu_fwspec {
 struct iommu_sva {
 	struct device			*dev;
 	struct iommu_domain		*domain;
+	struct list_head		handle_item;
+	refcount_t			users;
+};
+
+struct iommu_mm_data {
+	u32			pasid;
+	struct list_head	sva_domains;
+	struct list_head	sva_handles;
 };
 
 int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode,
@@ -840,10 +930,7 @@ static inline void *dev_iommu_priv_get(struct device *dev)
 		return NULL;
 }
 
-static inline void dev_iommu_priv_set(struct device *dev, void *priv)
-{
-	dev->iommu->priv = priv;
-}
+void dev_iommu_priv_set(struct device *dev, void *priv);
 
 extern struct mutex iommu_probe_device_lock;
 int iommu_probe_device(struct device *dev);
@@ -1337,15 +1424,33 @@ static inline bool tegra_dev_iommu_get_stream_id(struct device *dev, u32 *stream
 	return false;
 }
 
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_IOMMU_MM_DATA
 static inline void mm_pasid_init(struct mm_struct *mm)
 {
-	mm->pasid = IOMMU_PASID_INVALID;
+	/*
+	 * During dup_mm(), a new mm will be memcpy'd from an old one and that makes
+	 * the new mm and the old one point to a same iommu_mm instance. When either
+	 * one of the two mms gets released, the iommu_mm instance is freed, leaving
+	 * the other mm running into a use-after-free/double-free problem. To avoid
+	 * the problem, zeroing the iommu_mm pointer of a new mm is needed here.
+	 */
+	mm->iommu_mm = NULL;
 }
+
 static inline bool mm_valid_pasid(struct mm_struct *mm)
 {
-	return mm->pasid != IOMMU_PASID_INVALID;
+	return READ_ONCE(mm->iommu_mm);
+}
+
+static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm)
+{
+	struct iommu_mm_data *iommu_mm = READ_ONCE(mm->iommu_mm);
+
+	if (!iommu_mm)
+		return IOMMU_PASID_INVALID;
+	return iommu_mm->pasid;
 }
+
 void mm_pasid_drop(struct mm_struct *mm);
 struct iommu_sva *iommu_sva_bind_device(struct device *dev,
 					struct mm_struct *mm);
@@ -1368,6 +1473,12 @@ static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle)
 }
 static inline void mm_pasid_init(struct mm_struct *mm) {}
 static inline bool mm_valid_pasid(struct mm_struct *mm) { return false; }
+
+static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm)
+{
+	return IOMMU_PASID_INVALID;
+}
+
 static inline void mm_pasid_drop(struct mm_struct *mm) {}
 #endif /* CONFIG_IOMMU_SVA */
 
diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h
index 7578d4f6a969..db1249cd9692 100644
--- a/include/linux/ioprio.h
+++ b/include/linux/ioprio.h
@@ -47,7 +47,30 @@ static inline int task_nice_ioclass(struct task_struct *task)
 }
 
 #ifdef CONFIG_BLOCK
-int __get_task_ioprio(struct task_struct *p);
+/*
+ * If the task has set an I/O priority, use that. Otherwise, return
+ * the default I/O priority.
+ *
+ * Expected to be called for current task or with task_lock() held to keep
+ * io_context stable.
+ */
+static inline int __get_task_ioprio(struct task_struct *p)
+{
+	struct io_context *ioc = p->io_context;
+	int prio;
+
+	if (!ioc)
+		return IOPRIO_DEFAULT;
+
+	if (p != current)
+		lockdep_assert_held(&p->alloc_lock);
+
+	prio = ioc->ioprio;
+	if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE)
+		prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p),
+					 task_nice_ioprio(p));
+	return prio;
+}
 #else
 static inline int __get_task_ioprio(struct task_struct *p)
 {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 4944136efaa2..179df96b20f8 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -80,8 +80,8 @@
 /* Two fragments for cross MMIO pages. */
 #define KVM_MAX_MMIO_FRAGMENTS	2
 
-#ifndef KVM_ADDRESS_SPACE_NUM
-#define KVM_ADDRESS_SPACE_NUM	1
+#ifndef KVM_MAX_NR_ADDRESS_SPACES
+#define KVM_MAX_NR_ADDRESS_SPACES	1
 #endif
 
 /*
@@ -253,9 +253,10 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
 
-#ifdef KVM_ARCH_WANT_MMU_NOTIFIER
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 union kvm_mmu_notifier_arg {
 	pte_t pte;
+	unsigned long attributes;
 };
 
 struct kvm_gfn_range {
@@ -588,8 +589,20 @@ struct kvm_memory_slot {
 	u32 flags;
 	short id;
 	u16 as_id;
+
+#ifdef CONFIG_KVM_PRIVATE_MEM
+	struct {
+		struct file __rcu *file;
+		pgoff_t pgoff;
+	} gmem;
+#endif
 };
 
+static inline bool kvm_slot_can_be_private(const struct kvm_memory_slot *slot)
+{
+	return slot && (slot->flags & KVM_MEM_GUEST_MEMFD);
+}
+
 static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot)
 {
 	return slot->flags & KVM_MEM_LOG_DIRTY_PAGES;
@@ -677,13 +690,29 @@ bool kvm_arch_irqchip_in_kernel(struct kvm *kvm);
 #define KVM_MEM_SLOTS_NUM SHRT_MAX
 #define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS)
 
-#ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
+#if KVM_MAX_NR_ADDRESS_SPACES == 1
+static inline int kvm_arch_nr_memslot_as_ids(struct kvm *kvm)
+{
+	return KVM_MAX_NR_ADDRESS_SPACES;
+}
+
 static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
 {
 	return 0;
 }
 #endif
 
+/*
+ * Arch code must define kvm_arch_has_private_mem if support for private memory
+ * is enabled.
+ */
+#if !defined(kvm_arch_has_private_mem) && !IS_ENABLED(CONFIG_KVM_PRIVATE_MEM)
+static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
+{
+	return false;
+}
+#endif
+
 struct kvm_memslots {
 	u64 generation;
 	atomic_long_t last_used_slot;
@@ -721,9 +750,9 @@ struct kvm {
 	struct mm_struct *mm; /* userspace tied to this vm */
 	unsigned long nr_memslot_pages;
 	/* The two memslot sets - active and inactive (per address space) */
-	struct kvm_memslots __memslots[KVM_ADDRESS_SPACE_NUM][2];
+	struct kvm_memslots __memslots[KVM_MAX_NR_ADDRESS_SPACES][2];
 	/* The current active memslot set for each address space */
-	struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM];
+	struct kvm_memslots __rcu *memslots[KVM_MAX_NR_ADDRESS_SPACES];
 	struct xarray vcpu_array;
 	/*
 	 * Protected by slots_lock, but can be read outside if an
@@ -753,7 +782,7 @@ struct kvm {
 	struct list_head vm_list;
 	struct mutex lock;
 	struct kvm_io_bus __rcu *buses[KVM_NR_BUSES];
-#ifdef CONFIG_HAVE_KVM_EVENTFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 	struct {
 		spinlock_t        lock;
 		struct list_head  items;
@@ -761,8 +790,8 @@ struct kvm {
 		struct list_head  resampler_list;
 		struct mutex      resampler_lock;
 	} irqfds;
-	struct list_head ioeventfds;
 #endif
+	struct list_head ioeventfds;
 	struct kvm_vm_stat stat;
 	struct kvm_arch arch;
 	refcount_t users_count;
@@ -778,17 +807,16 @@ struct kvm {
 	 * Update side is protected by irq_lock.
 	 */
 	struct kvm_irq_routing_table __rcu *irq_routing;
-#endif
-#ifdef CONFIG_HAVE_KVM_IRQFD
+
 	struct hlist_head irq_ack_notifier_list;
 #endif
 
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 	struct mmu_notifier mmu_notifier;
 	unsigned long mmu_invalidate_seq;
 	long mmu_invalidate_in_progress;
-	unsigned long mmu_invalidate_range_start;
-	unsigned long mmu_invalidate_range_end;
+	gfn_t mmu_invalidate_range_start;
+	gfn_t mmu_invalidate_range_end;
 #endif
 	struct list_head devices;
 	u64 manual_dirty_log_protect;
@@ -807,6 +835,10 @@ struct kvm {
 #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
 	struct notifier_block pm_notifier;
 #endif
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	/* Protected by slots_locks (for writes) and RCU (for reads) */
+	struct xarray mem_attr_array;
+#endif
 	char stats_id[KVM_STATS_NAME_SIZE];
 };
 
@@ -965,7 +997,7 @@ static inline void kvm_arch_post_irq_routing_update(struct kvm *kvm)
 }
 #endif
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 int kvm_irqfd_init(void);
 void kvm_irqfd_exit(void);
 #else
@@ -989,7 +1021,7 @@ void kvm_put_kvm_no_destroy(struct kvm *kvm);
 
 static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id)
 {
-	as_id = array_index_nospec(as_id, KVM_ADDRESS_SPACE_NUM);
+	as_id = array_index_nospec(as_id, KVM_MAX_NR_ADDRESS_SPACES);
 	return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu,
 			lockdep_is_held(&kvm->slots_lock) ||
 			!refcount_read(&kvm->users_count));
@@ -1146,9 +1178,9 @@ enum kvm_mr_change {
 };
 
 int kvm_set_memory_region(struct kvm *kvm,
-			  const struct kvm_userspace_memory_region *mem);
+			  const struct kvm_userspace_memory_region2 *mem);
 int __kvm_set_memory_region(struct kvm *kvm,
-			    const struct kvm_userspace_memory_region *mem);
+			    const struct kvm_userspace_memory_region2 *mem);
 void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot);
 void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen);
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
@@ -1392,10 +1424,10 @@ void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc);
 void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
 #endif
 
-void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
-			      unsigned long end);
-void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
-			    unsigned long end);
+void kvm_mmu_invalidate_begin(struct kvm *kvm);
+void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end);
+void kvm_mmu_invalidate_end(struct kvm *kvm);
+bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
 
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
@@ -1947,7 +1979,7 @@ extern const struct _kvm_stats_desc kvm_vm_stats_desc[];
 extern const struct kvm_stats_header kvm_vcpu_stats_header;
 extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[];
 
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
 {
 	if (unlikely(kvm->mmu_invalidate_in_progress))
@@ -1970,9 +2002,9 @@ static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
 	return 0;
 }
 
-static inline int mmu_invalidate_retry_hva(struct kvm *kvm,
+static inline int mmu_invalidate_retry_gfn(struct kvm *kvm,
 					   unsigned long mmu_seq,
-					   unsigned long hva)
+					   gfn_t gfn)
 {
 	lockdep_assert_held(&kvm->mmu_lock);
 	/*
@@ -1981,14 +2013,50 @@ static inline int mmu_invalidate_retry_hva(struct kvm *kvm,
 	 * that might be being invalidated. Note that it may include some false
 	 * positives, due to shortcuts when handing concurrent invalidations.
 	 */
-	if (unlikely(kvm->mmu_invalidate_in_progress) &&
-	    hva >= kvm->mmu_invalidate_range_start &&
-	    hva < kvm->mmu_invalidate_range_end)
-		return 1;
+	if (unlikely(kvm->mmu_invalidate_in_progress)) {
+		/*
+		 * Dropping mmu_lock after bumping mmu_invalidate_in_progress
+		 * but before updating the range is a KVM bug.
+		 */
+		if (WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA ||
+				 kvm->mmu_invalidate_range_end == INVALID_GPA))
+			return 1;
+
+		if (gfn >= kvm->mmu_invalidate_range_start &&
+		    gfn < kvm->mmu_invalidate_range_end)
+			return 1;
+	}
+
 	if (kvm->mmu_invalidate_seq != mmu_seq)
 		return 1;
 	return 0;
 }
+
+/*
+ * This lockless version of the range-based retry check *must* be paired with a
+ * call to the locked version after acquiring mmu_lock, i.e. this is safe to
+ * use only as a pre-check to avoid contending mmu_lock.  This version *will*
+ * get false negatives and false positives.
+ */
+static inline bool mmu_invalidate_retry_gfn_unsafe(struct kvm *kvm,
+						   unsigned long mmu_seq,
+						   gfn_t gfn)
+{
+	/*
+	 * Use READ_ONCE() to ensure the in-progress flag and sequence counter
+	 * are always read from memory, e.g. so that checking for retry in a
+	 * loop won't result in an infinite retry loop.  Don't force loads for
+	 * start+end, as the key to avoiding infinite retry loops is observing
+	 * the 1=>0 transition of in-progress, i.e. getting false negatives
+	 * due to stale start+end values is acceptable.
+	 */
+	if (unlikely(READ_ONCE(kvm->mmu_invalidate_in_progress)) &&
+	    gfn >= kvm->mmu_invalidate_range_start &&
+	    gfn < kvm->mmu_invalidate_range_end)
+		return true;
+
+	return READ_ONCE(kvm->mmu_invalidate_seq) != mmu_seq;
+}
 #endif
 
 #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
@@ -2013,12 +2081,10 @@ static inline void kvm_free_irq_routing(struct kvm *kvm) {}
 
 int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
 
-#ifdef CONFIG_HAVE_KVM_EVENTFD
-
 void kvm_eventfd_init(struct kvm *kvm);
 int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args);
 void kvm_irqfd_release(struct kvm *kvm);
 bool kvm_notify_irqfd_resampler(struct kvm *kvm,
@@ -2039,31 +2105,7 @@ static inline bool kvm_notify_irqfd_resampler(struct kvm *kvm,
 {
 	return false;
 }
-#endif
-
-#else
-
-static inline void kvm_eventfd_init(struct kvm *kvm) {}
-
-static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
-{
-	return -EINVAL;
-}
-
-static inline void kvm_irqfd_release(struct kvm *kvm) {}
-
-#ifdef CONFIG_HAVE_KVM_IRQCHIP
-static inline void kvm_irq_routing_update(struct kvm *kvm)
-{
-}
-#endif
-
-static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
-{
-	return -ENOSYS;
-}
-
-#endif /* CONFIG_HAVE_KVM_EVENTFD */
+#endif /* CONFIG_HAVE_KVM_IRQCHIP */
 
 void kvm_arch_irq_routing_update(struct kvm *kvm);
 
@@ -2318,4 +2360,57 @@ static inline void kvm_account_pgtable_pages(void *virt, int nr)
 /* Max number of entries allowed for each kvm dirty ring */
 #define  KVM_DIRTY_RING_MAX_ENTRIES  65536
 
+static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
+						 gpa_t gpa, gpa_t size,
+						 bool is_write, bool is_exec,
+						 bool is_private)
+{
+	vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
+	vcpu->run->memory_fault.gpa = gpa;
+	vcpu->run->memory_fault.size = size;
+
+	/* RWX flags are not (yet) defined or communicated to userspace. */
+	vcpu->run->memory_fault.flags = 0;
+	if (is_private)
+		vcpu->run->memory_fault.flags |= KVM_MEMORY_EXIT_FLAG_PRIVATE;
+}
+
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn)
+{
+	return xa_to_value(xa_load(&kvm->mem_attr_array, gfn));
+}
+
+bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
+				     unsigned long attrs);
+bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
+					struct kvm_gfn_range *range);
+bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
+					 struct kvm_gfn_range *range);
+
+static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
+{
+	return IS_ENABLED(CONFIG_KVM_PRIVATE_MEM) &&
+	       kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE;
+}
+#else
+static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
+{
+	return false;
+}
+#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
+
+#ifdef CONFIG_KVM_PRIVATE_MEM
+int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+		     gfn_t gfn, kvm_pfn_t *pfn, int *max_order);
+#else
+static inline int kvm_gmem_get_pfn(struct kvm *kvm,
+				   struct kvm_memory_slot *slot, gfn_t gfn,
+				   kvm_pfn_t *pfn, int *max_order)
+{
+	KVM_BUG_ON(1, kvm);
+	return -EIO;
+}
+#endif /* CONFIG_KVM_PRIVATE_MEM */
+
 #endif
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index 6f4737d5046a..9d1f7835d8c1 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -6,6 +6,7 @@
 struct kvm;
 struct kvm_async_pf;
 struct kvm_device_ops;
+struct kvm_gfn_range;
 struct kvm_interrupt;
 struct kvm_irq_routing_table;
 struct kvm_memory_slot;
diff --git a/include/linux/leds.h b/include/linux/leds.h
index aa16dc2a8230..4754b02d3a2c 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -527,23 +527,6 @@ static inline void *led_get_trigger_data(struct led_classdev *led_cdev)
 	return led_cdev->trigger_data;
 }
 
-/**
- * led_trigger_rename_static - rename a trigger
- * @name: the new trigger name
- * @trig: the LED trigger to rename
- *
- * Change a LED trigger name by copying the string passed in
- * name into current trigger name, which MUST be large
- * enough for the new string.
- *
- * Note that name must NOT point to the same string used
- * during LED registration, as that could lead to races.
- *
- * This is meant to be used on triggers with statically
- * allocated name.
- */
-void led_trigger_rename_static(const char *name, struct led_trigger *trig);
-
 #define module_led_trigger(__led_trigger) \
 	module_driver(__led_trigger, led_trigger_register, \
 		      led_trigger_unregister)
@@ -588,6 +571,9 @@ enum led_trigger_netdev_modes {
 	TRIGGER_NETDEV_LINK_10,
 	TRIGGER_NETDEV_LINK_100,
 	TRIGGER_NETDEV_LINK_1000,
+	TRIGGER_NETDEV_LINK_2500,
+	TRIGGER_NETDEV_LINK_5000,
+	TRIGGER_NETDEV_LINK_10000,
 	TRIGGER_NETDEV_HALF_DUPLEX,
 	TRIGGER_NETDEV_FULL_DUPLEX,
 	TRIGGER_NETDEV_TX,
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 1dbb14daccfa..26d68115afb8 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -471,7 +471,7 @@ enum ata_completion_errors {
 
 /*
  * Link power management policy: If you alter this, you also need to
- * alter libata-scsi.c (for the ascii descriptions)
+ * alter libata-sata.c (for the ascii descriptions)
  */
 enum ata_lpm_policy {
 	ATA_LPM_UNKNOWN,
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index 9f565416d186..1b95fe31051f 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -375,12 +375,12 @@ static inline int nlm_privileged_requester(const struct svc_rqst *rqstp)
 static inline int nlm_compare_locks(const struct file_lock *fl1,
 				    const struct file_lock *fl2)
 {
-	return file_inode(fl1->fl_file) == file_inode(fl2->fl_file)
-	     && fl1->fl_pid   == fl2->fl_pid
-	     && fl1->fl_owner == fl2->fl_owner
+	return file_inode(fl1->c.flc_file) == file_inode(fl2->c.flc_file)
+	     && fl1->c.flc_pid   == fl2->c.flc_pid
+	     && fl1->c.flc_owner == fl2->c.flc_owner
 	     && fl1->fl_start == fl2->fl_start
 	     && fl1->fl_end   == fl2->fl_end
-	     &&(fl1->fl_type  == fl2->fl_type || fl2->fl_type == F_UNLCK);
+	     &&(fl1->c.flc_type  == fl2->c.flc_type || fl2->c.flc_type == F_UNLCK);
 }
 
 extern const struct lock_manager_operations nlmsvc_lock_operations;
diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h
index b60fbcd8cdfa..80cca9426761 100644
--- a/include/linux/lockd/xdr.h
+++ b/include/linux/lockd/xdr.h
@@ -52,7 +52,7 @@ struct nlm_lock {
  *	FreeBSD uses 16, Apple Mac OS X 10.3 uses 20. Therefore we set it to
  *	32 bytes.
  */
- 
+
 struct nlm_cookie
 {
 	unsigned char data[NLM_MAXCOOKIELEN];
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 185924c56378..76458b6d53da 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -315,9 +315,9 @@ LSM_HOOK(int, 0, socket_getsockopt, struct socket *sock, int level, int optname)
 LSM_HOOK(int, 0, socket_setsockopt, struct socket *sock, int level, int optname)
 LSM_HOOK(int, 0, socket_shutdown, struct socket *sock, int how)
 LSM_HOOK(int, 0, socket_sock_rcv_skb, struct sock *sk, struct sk_buff *skb)
-LSM_HOOK(int, 0, socket_getpeersec_stream, struct socket *sock,
+LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_stream, struct socket *sock,
 	 sockptr_t optval, sockptr_t optlen, unsigned int len)
-LSM_HOOK(int, 0, socket_getpeersec_dgram, struct socket *sock,
+LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_dgram, struct socket *sock,
 	 struct sk_buff *skb, u32 *secid)
 LSM_HOOK(int, 0, sk_alloc_security, struct sock *sk, int family, gfp_t priority)
 LSM_HOOK(void, LSM_RET_VOID, sk_free_security, struct sock *sk)
diff --git a/include/linux/maple.h b/include/linux/maple.h
index 9b140272ee16..9aae44efcfd4 100644
--- a/include/linux/maple.h
+++ b/include/linux/maple.h
@@ -5,7 +5,6 @@
 #include <mach/maple.h>
 
 struct device;
-extern struct bus_type maple_bus_type;
 
 /* Maple Bus command and response codes */
 enum maple_code {
diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h
index b3d63123b945..a53ad4dabd7e 100644
--- a/include/linux/maple_tree.h
+++ b/include/linux/maple_tree.h
@@ -171,6 +171,7 @@ enum maple_type {
 #define MT_FLAGS_LOCK_IRQ	0x100
 #define MT_FLAGS_LOCK_BH	0x200
 #define MT_FLAGS_LOCK_EXTERN	0x300
+#define MT_FLAGS_ALLOC_WRAPPED	0x0800
 
 #define MAPLE_HEIGHT_MAX	31
 
@@ -319,6 +320,9 @@ int mtree_insert_range(struct maple_tree *mt, unsigned long first,
 int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp,
 		void *entry, unsigned long size, unsigned long min,
 		unsigned long max, gfp_t gfp);
+int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp,
+		void *entry, unsigned long range_lo, unsigned long range_hi,
+		unsigned long *next, gfp_t gfp);
 int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp,
 		void *entry, unsigned long size, unsigned long min,
 		unsigned long max, gfp_t gfp);
@@ -499,6 +503,9 @@ void *mas_find_range(struct ma_state *mas, unsigned long max);
 void *mas_find_rev(struct ma_state *mas, unsigned long min);
 void *mas_find_range_rev(struct ma_state *mas, unsigned long max);
 int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp);
+int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp,
+		void *entry, unsigned long range_lo, unsigned long range_hi,
+		unsigned long *next, gfp_t gfp);
 
 bool mas_nomem(struct ma_state *mas, gfp_t gfp);
 void mas_pause(struct ma_state *mas);
diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h
index b0da04fe087b..34dfcc77f505 100644
--- a/include/linux/mc146818rtc.h
+++ b/include/linux/mc146818rtc.h
@@ -126,10 +126,11 @@ struct cmos_rtc_board_info {
 #endif /* ARCH_RTC_LOCATION */
 
 bool mc146818_does_rtc_work(void);
-int mc146818_get_time(struct rtc_time *time);
+int mc146818_get_time(struct rtc_time *time, int timeout);
 int mc146818_set_time(struct rtc_time *time);
 
 bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param),
+			int timeout,
 			void *param);
 
 #endif /* _MC146818RTC_H */
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index b695f9e946da..e2082240586d 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -121,6 +121,8 @@ int memblock_reserve(phys_addr_t base, phys_addr_t size);
 int memblock_physmem_add(phys_addr_t base, phys_addr_t size);
 #endif
 void memblock_trim_memory(phys_addr_t align);
+unsigned long memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
+				     phys_addr_t base2, phys_addr_t size2);
 bool memblock_overlaps_region(struct memblock_type *type,
 			      phys_addr_t base, phys_addr_t size);
 bool memblock_validate_numa_coverage(unsigned long threshold_bytes);
diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 1e39d27bee41..69e781900082 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -33,7 +33,7 @@ struct memory_dev_type {
 	struct kref kref;
 };
 
-struct node_hmem_attrs;
+struct access_coordinate;
 
 #ifdef CONFIG_NUMA
 extern bool numa_demotion_enabled;
@@ -45,9 +45,9 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype);
 int register_mt_adistance_algorithm(struct notifier_block *nb);
 int unregister_mt_adistance_algorithm(struct notifier_block *nb);
 int mt_calc_adistance(int node, int *adist);
-int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf,
+int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
 			     const char *source);
-int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist);
+int mt_perf_to_adistance(struct access_coordinate *perf, int *adist);
 #ifdef CONFIG_MIGRATION
 int next_demotion_node(int node);
 void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
@@ -126,13 +126,13 @@ static inline int mt_calc_adistance(int node, int *adist)
 	return NOTIFY_DONE;
 }
 
-static inline int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf,
+static inline int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
 					   const char *source)
 {
 	return -EIO;
 }
 
-static inline int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist)
+static inline int mt_perf_to_adistance(struct access_coordinate *perf, int *adist)
 {
 	return -EIO;
 }
diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h
index 311f7d3d2323..54444ff2a5de 100644
--- a/include/linux/mfd/max77693-private.h
+++ b/include/linux/mfd/max77693-private.h
@@ -405,7 +405,7 @@ enum max77693_haptic_reg {
 	MAX77693_HAPTIC_REG_END,
 };
 
-/* max77693-pmic LSCNFG configuraton register */
+/* max77693-pmic LSCNFG configuration register */
 #define MAX77693_PMIC_LOW_SYS_MASK      0x80
 #define MAX77693_PMIC_LOW_SYS_SHIFT     7
 
diff --git a/include/linux/mfd/max77843-private.h b/include/linux/mfd/max77843-private.h
index 0bc7454c4dbe..2fb4db67f110 100644
--- a/include/linux/mfd/max77843-private.h
+++ b/include/linux/mfd/max77843-private.h
@@ -198,7 +198,7 @@ enum max77843_irq_muic {
 #define MAX77843_MCONFIG_MEN_MASK		BIT(MCONFIG_MEN_SHIFT)
 #define MAX77843_MCONFIG_PDIV_MASK		(0x3 << MCONFIG_PDIV_SHIFT)
 
-/* Max77843 charger insterrupts */
+/* Max77843 charger interrupts */
 #define MAX77843_CHG_BYP_I			BIT(0)
 #define MAX77843_CHG_BATP_I			BIT(2)
 #define MAX77843_CHG_BAT_I			BIT(3)
diff --git a/include/linux/mfd/si476x-platform.h b/include/linux/mfd/si476x-platform.h
index 18363b773d07..cb99e16ca947 100644
--- a/include/linux/mfd/si476x-platform.h
+++ b/include/linux/mfd/si476x-platform.h
@@ -10,7 +10,7 @@
 #ifndef __SI476X_PLATFORM_H__
 #define __SI476X_PLATFORM_H__
 
-/* It is possible to select one of the four adresses using pins A0
+/* It is possible to select one of the four addresses using pins A0
  * and A1 on SI476x */
 #define SI476X_I2C_ADDR_1	0x60
 #define SI476X_I2C_ADDR_2	0x61
diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h
index 701925db75b3..f67ef0a4e041 100644
--- a/include/linux/mfd/tps65910.h
+++ b/include/linux/mfd/tps65910.h
@@ -749,7 +749,7 @@
 #define VDDCTRL_ST_SHIFT                                 0
 
 
-/*Register VDDCTRL_OP  (0x28) bit definitios */
+/*Register VDDCTRL_OP  (0x28) bit definitions */
 #define VDDCTRL_OP_CMD_MASK                              0x80
 #define VDDCTRL_OP_CMD_SHIFT                             7
 #define VDDCTRL_OP_SEL_MASK                              0x7F
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index 039943ec4d4e..d0f9b522f328 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -266,6 +266,7 @@ struct mhi_event_config {
  * struct mhi_controller_config - Root MHI controller configuration
  * @max_channels: Maximum number of channels supported
  * @timeout_ms: Timeout value for operations. 0 means use default
+ * @ready_timeout_ms: Timeout value for waiting device to be ready (optional)
  * @buf_len: Size of automatically allocated buffers. 0 means use default
  * @num_channels: Number of channels defined in @ch_cfg
  * @ch_cfg: Array of defined channels
@@ -277,6 +278,7 @@ struct mhi_event_config {
 struct mhi_controller_config {
 	u32 max_channels;
 	u32 timeout_ms;
+	u32 ready_timeout_ms;
 	u32 buf_len;
 	u32 num_channels;
 	const struct mhi_channel_config *ch_cfg;
@@ -330,6 +332,7 @@ struct mhi_controller_config {
  * @pm_mutex: Mutex for suspend/resume operation
  * @pm_lock: Lock for protecting MHI power management state
  * @timeout_ms: Timeout in ms for state transitions
+ * @ready_timeout_ms: Timeout in ms for waiting device to be ready (optional)
  * @pm_state: MHI power management state
  * @db_access: DB access states
  * @ee: MHI device execution environment
@@ -419,6 +422,7 @@ struct mhi_controller {
 	struct mutex pm_mutex;
 	rwlock_t pm_lock;
 	u32 timeout_ms;
+	u32 ready_timeout_ms;
 	u32 pm_state;
 	u32 db_access;
 	enum mhi_ee_type ee;
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index f198a8ac7ee7..11bf3212f782 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -50,6 +50,27 @@ struct mhi_ep_db_info {
 };
 
 /**
+ * struct mhi_ep_buf_info - MHI Endpoint transfer buffer info
+ * @mhi_dev: MHI device associated with this buffer
+ * @dev_addr: Address of the buffer in endpoint
+ * @host_addr: Address of the bufffer in host
+ * @size: Size of the buffer
+ * @code: Transfer completion code
+ * @cb: Callback to be executed by controller drivers after transfer completion (async)
+ * @cb_buf: Opaque buffer to be passed to the callback
+ */
+struct mhi_ep_buf_info {
+	struct mhi_ep_device *mhi_dev;
+	void *dev_addr;
+	u64 host_addr;
+	size_t size;
+	int code;
+
+	void (*cb)(struct mhi_ep_buf_info *buf_info);
+	void *cb_buf;
+};
+
+/**
  * struct mhi_ep_cntrl - MHI Endpoint controller structure
  * @cntrl_dev: Pointer to the struct device of physical bus acting as the MHI
  *             Endpoint controller
@@ -82,8 +103,10 @@ struct mhi_ep_db_info {
  * @raise_irq: CB function for raising IRQ to the host
  * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it
  * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context
- * @read_from_host: CB function for reading from host memory from endpoint
- * @write_to_host: CB function for writing to host memory from endpoint
+ * @read_sync: CB function for reading from host memory synchronously
+ * @write_sync: CB function for writing to host memory synchronously
+ * @read_async: CB function for reading from host memory asynchronously
+ * @write_async: CB function for writing to host memory asynchronously
  * @mhi_state: MHI Endpoint state
  * @max_chan: Maximum channels supported by the endpoint controller
  * @mru: MRU (Maximum Receive Unit) value of the endpoint controller
@@ -128,14 +151,19 @@ struct mhi_ep_cntrl {
 	struct work_struct reset_work;
 	struct work_struct cmd_ring_work;
 	struct work_struct ch_ring_work;
+	struct kmem_cache *ring_item_cache;
+	struct kmem_cache *ev_ring_el_cache;
+	struct kmem_cache *tre_buf_cache;
 
 	void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector);
 	int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr,
 			 void __iomem **virt, size_t size);
 	void (*unmap_free)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t phys,
 			   void __iomem *virt, size_t size);
-	int (*read_from_host)(struct mhi_ep_cntrl *mhi_cntrl, u64 from, void *to, size_t size);
-	int (*write_to_host)(struct mhi_ep_cntrl *mhi_cntrl, void *from, u64 to, size_t size);
+	int (*read_sync)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
+	int (*write_sync)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
+	int (*read_async)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
+	int (*write_async)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
 
 	enum mhi_state mhi_state;
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 8c55ff351e5f..41f03b352401 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -681,6 +681,7 @@ struct mlx5e_resources {
 		struct mlx5_sq_bfreg       bfreg;
 #define MLX5_MAX_NUM_TC 8
 		u32                        tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC];
+		bool			   tisn_valid;
 	} hw_objs;
 	struct net_device *uplink_netdev;
 	struct mutex uplink_netdev_lock;
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 6f7725238abc..3fb428ce7d1c 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -132,6 +132,7 @@ struct mlx5_flow_handle;
 
 enum {
 	FLOW_CONTEXT_HAS_TAG = BIT(0),
+	FLOW_CONTEXT_UPLINK_HAIRPIN_EN = BIT(1),
 };
 
 struct mlx5_flow_context {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 7235f3eaed8b..486b7492050c 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1103,7 +1103,7 @@ struct mlx5_ifc_roce_cap_bits {
 	u8         sw_r_roce_src_udp_port[0x1];
 	u8         fl_rc_qp_when_roce_disabled[0x1];
 	u8         fl_rc_qp_when_roce_enabled[0x1];
-	u8         reserved_at_7[0x1];
+	u8         roce_cc_general[0x1];
 	u8	   qp_ooo_transmit_default[0x1];
 	u8         reserved_at_9[0x15];
 	u8	   qp_ts_format[0x2];
@@ -1241,7 +1241,8 @@ struct mlx5_ifc_virtio_emulation_cap_bits {
 
 	u8	   reserved_at_c0[0x13];
 	u8         desc_group_mkey_supported[0x1];
-	u8         reserved_at_d4[0xc];
+	u8         freeze_to_rdy_supported[0x1];
+	u8         reserved_at_d5[0xb];
 
 	u8         reserved_at_e0[0x20];
 
@@ -3575,7 +3576,7 @@ struct mlx5_ifc_flow_context_bits {
 	u8         action[0x10];
 
 	u8         extended_destination[0x1];
-	u8         reserved_at_81[0x1];
+	u8         uplink_hairpin_en[0x1];
 	u8         flow_source[0x2];
 	u8         encrypt_decrypt_type[0x4];
 	u8         destination_list_size[0x18];
@@ -4035,8 +4036,13 @@ struct mlx5_ifc_nic_vport_context_bits {
 	u8	   affiliation_criteria[0x4];
 	u8	   affiliated_vhca_id[0x10];
 
-	u8	   reserved_at_60[0xd0];
+	u8	   reserved_at_60[0xa0];
 
+	u8	   reserved_at_100[0x1];
+	u8         sd_group[0x3];
+	u8	   reserved_at_104[0x1c];
+
+	u8	   reserved_at_120[0x10];
 	u8         mtu[0x10];
 
 	u8         system_image_guid[0x40];
@@ -10121,8 +10127,7 @@ struct mlx5_ifc_mpir_reg_bits {
 	u8         reserved_at_20[0x20];
 
 	u8         local_port[0x8];
-	u8         reserved_at_28[0x15];
-	u8         sd_group[0x3];
+	u8         reserved_at_28[0x18];
 
 	u8         reserved_at_60[0x20];
 };
@@ -10256,7 +10261,9 @@ struct mlx5_ifc_mcam_access_reg_bits {
 
 	u8         regs_63_to_46[0x12];
 	u8         mrtc[0x1];
-	u8         regs_44_to_32[0xd];
+	u8         regs_44_to_41[0x4];
+	u8         mfrl[0x1];
+	u8         regs_39_to_32[0x8];
 
 	u8         regs_31_to_10[0x16];
 	u8         mtmp[0x1];
diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h
index b86d51a855f6..40371c916cf9 100644
--- a/include/linux/mlx5/mlx5_ifc_vdpa.h
+++ b/include/linux/mlx5/mlx5_ifc_vdpa.h
@@ -145,6 +145,10 @@ enum {
 	MLX5_VIRTQ_MODIFY_MASK_STATE                    = (u64)1 << 0,
 	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_PARAMS      = (u64)1 << 3,
 	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_DUMP_ENABLE = (u64)1 << 4,
+	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_ADDRS           = (u64)1 << 6,
+	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_AVAIL_IDX       = (u64)1 << 7,
+	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX        = (u64)1 << 8,
+	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY            = (u64)1 << 11,
 	MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY          = (u64)1 << 14,
 };
 
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index bd53cf4be7bd..f0e55bf3ec8b 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -269,7 +269,10 @@ struct mlx5_wqe_eth_seg {
 	union {
 		struct {
 			__be16 sz;
-			u8     start[2];
+			union {
+				u8     start[2];
+				DECLARE_FLEX_ARRAY(u8, data);
+			};
 		} inline_hdr;
 		struct {
 			__be16 type;
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index fbb9bf447889..c36cc6d82926 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -72,6 +72,7 @@ int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu);
 int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu);
 int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev,
 					   u64 *system_image_guid);
+int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group);
 int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid);
 int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 				    u16 vport, u64 node_guid);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index b2d3a88a34d1..8b611e13153e 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -730,6 +730,7 @@ struct mm_cid {
 #endif
 
 struct kioctx_table;
+struct iommu_mm_data;
 struct mm_struct {
 	struct {
 		/*
@@ -941,8 +942,8 @@ struct mm_struct {
 #endif
 		struct work_struct async_put_work;
 
-#ifdef CONFIG_IOMMU_SVA
-		u32 pasid;
+#ifdef CONFIG_IOMMU_MM_DATA
+		struct iommu_mm_data *iommu_mm;
 #endif
 #ifdef CONFIG_KSM
 		/*
diff --git a/include/linux/mman.h b/include/linux/mman.h
index 40d94411d492..dc7048824be8 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -156,6 +156,7 @@ calc_vm_flag_bits(unsigned long flags)
 	return _calc_vm_trans(flags, MAP_GROWSDOWN,  VM_GROWSDOWN ) |
 	       _calc_vm_trans(flags, MAP_LOCKED,     VM_LOCKED    ) |
 	       _calc_vm_trans(flags, MAP_SYNC,	     VM_SYNC      ) |
+	       _calc_vm_trans(flags, MAP_STACK,	     VM_NOHUGEPAGE) |
 	       arch_calc_vm_flag_bits(flags);
 }
 
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 4ed33b127821..a497f189d988 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -2013,9 +2013,9 @@ static inline int pfn_valid(unsigned long pfn)
 	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
 		return 0;
 	ms = __pfn_to_section(pfn);
-	rcu_read_lock();
+	rcu_read_lock_sched();
 	if (!valid_section(ms)) {
-		rcu_read_unlock();
+		rcu_read_unlock_sched();
 		return 0;
 	}
 	/*
@@ -2023,7 +2023,7 @@ static inline int pfn_valid(unsigned long pfn)
 	 * the entire section-sized span.
 	 */
 	ret = early_section(ms) || pfn_section_valid(ms, pfn);
-	rcu_read_unlock();
+	rcu_read_unlock_sched();
 
 	return ret;
 }
diff --git a/include/linux/moxtet.h b/include/linux/moxtet.h
index 79184948fab4..ac577699edfd 100644
--- a/include/linux/moxtet.h
+++ b/include/linux/moxtet.h
@@ -35,8 +35,6 @@ enum turris_mox_module_id {
 
 #define MOXTET_NIRQS	16
 
-extern struct bus_type moxtet_type;
-
 struct moxtet {
 	struct device			*dev;
 	struct mutex			lock;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 118c40258d07..78a09af89e39 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -79,8 +79,6 @@ struct xdp_buff;
 struct xdp_frame;
 struct xdp_metadata_ops;
 struct xdp_md;
-/* DPLL specific */
-struct dpll_pin;
 
 typedef u32 xdp_features_t;
 
@@ -2141,6 +2139,11 @@ struct net_device {
 
 	/* TXRX read-mostly hotpath */
 	__cacheline_group_begin(net_device_read_txrx);
+	union {
+		struct pcpu_lstats __percpu		*lstats;
+		struct pcpu_sw_netstats __percpu	*tstats;
+		struct pcpu_dstats __percpu		*dstats;
+	};
 	unsigned int		flags;
 	unsigned short		hard_header_len;
 	netdev_features_t	features;
@@ -2395,11 +2398,6 @@ struct net_device {
 	enum netdev_ml_priv_type	ml_priv_type;
 
 	enum netdev_stat_type		pcpu_stat_type:8;
-	union {
-		struct pcpu_lstats __percpu		*lstats;
-		struct pcpu_sw_netstats __percpu	*tstats;
-		struct pcpu_dstats __percpu		*dstats;
-	};
 
 #if IS_ENABLED(CONFIG_GARP)
 	struct garp_port __rcu	*garp_port;
@@ -2469,7 +2467,7 @@ struct net_device {
 	struct devlink_port	*devlink_port;
 
 #if IS_ENABLED(CONFIG_DPLL)
-	struct dpll_pin		*dpll_pin;
+	struct dpll_pin	__rcu	*dpll_pin;
 #endif
 #if IS_ENABLED(CONFIG_PAGE_POOL)
 	/** @page_pools: page pools created for this netdevice */
@@ -3499,6 +3497,16 @@ static inline void netdev_queue_set_dql_min_limit(struct netdev_queue *dev_queue
 #endif
 }
 
+static inline int netdev_queue_dql_avail(const struct netdev_queue *txq)
+{
+#ifdef CONFIG_BQL
+	/* Non-BQL migrated drivers will return 0, too. */
+	return dql_avail(&txq->dql);
+#else
+	return 0;
+#endif
+}
+
 /**
  *	netdev_txq_bql_enqueue_prefetchw - prefetch bql data for write
  *	@dev_queue: pointer to transmit queue
@@ -4032,17 +4040,6 @@ int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name);
 int dev_get_port_parent_id(struct net_device *dev,
 			   struct netdev_phys_item_id *ppid, bool recurse);
 bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b);
-void netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin);
-void netdev_dpll_pin_clear(struct net_device *dev);
-
-static inline struct dpll_pin *netdev_dpll_pin(const struct net_device *dev)
-{
-#if IS_ENABLED(CONFIG_DPLL)
-	return dev->dpll_pin;
-#else
-	return NULL;
-#endif
-}
 
 struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again);
 struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 80900d910992..ce660d51549b 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -474,6 +474,7 @@ struct nf_ct_hook {
 			      const struct sk_buff *);
 	void (*attach)(struct sk_buff *nskb, const struct sk_buff *skb);
 	void (*set_closing)(struct nf_conntrack *nfct);
+	int (*confirm)(struct sk_buff *skb);
 };
 extern const struct nf_ct_hook __rcu *nf_ct_hook;
 
diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index e8c350a3ade1..e9f4f845d760 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -186,6 +186,8 @@ struct ip_set_type_variant {
 	/* Return true if "b" set is the same as "a"
 	 * according to the create set parameters */
 	bool (*same_set)(const struct ip_set *a, const struct ip_set *b);
+	/* Cancel ongoing garbage collectors before destroying the set*/
+	void (*cancel_gc)(struct ip_set *set);
 	/* Region-locking is used */
 	bool region_lock;
 };
@@ -242,6 +244,8 @@ extern void ip_set_type_unregister(struct ip_set_type *set_type);
 
 /* A generic IP set */
 struct ip_set {
+	/* For call_cru in destroy */
+	struct rcu_head rcu;
 	/* The name of the set */
 	char name[IPSET_MAXNAMELEN];
 	/* Lock protecting the set data */
diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h
index f980edfdd278..743475ca7e9d 100644
--- a/include/linux/netfilter_bridge.h
+++ b/include/linux/netfilter_bridge.h
@@ -42,7 +42,7 @@ static inline int nf_bridge_get_physinif(const struct sk_buff *skb)
 	if (!nf_bridge)
 		return 0;
 
-	return nf_bridge->physindev ? nf_bridge->physindev->ifindex : 0;
+	return nf_bridge->physinif;
 }
 
 static inline int nf_bridge_get_physoutif(const struct sk_buff *skb)
@@ -56,11 +56,11 @@ static inline int nf_bridge_get_physoutif(const struct sk_buff *skb)
 }
 
 static inline struct net_device *
-nf_bridge_get_physindev(const struct sk_buff *skb)
+nf_bridge_get_physindev(const struct sk_buff *skb, struct net *net)
 {
 	const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 
-	return nf_bridge ? nf_bridge->physindev : NULL;
+	return nf_bridge ? dev_get_by_index_rcu(net, nf_bridge->physinif) : NULL;
 }
 
 static inline struct net_device *
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index b11a84f6c32b..100cbb261269 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -109,11 +109,18 @@ static inline int wait_on_page_fscache_killable(struct page *page)
 	return folio_wait_private_2_killable(page_folio(page));
 }
 
+/* Marks used on xarray-based buffers */
+#define NETFS_BUF_PUT_MARK	XA_MARK_0	/* - Page needs putting  */
+#define NETFS_BUF_PAGECACHE_MARK XA_MARK_1	/* - Page needs wb/dirty flag wrangling */
+
 enum netfs_io_source {
 	NETFS_FILL_WITH_ZEROES,
 	NETFS_DOWNLOAD_FROM_SERVER,
 	NETFS_READ_FROM_CACHE,
 	NETFS_INVALID_READ,
+	NETFS_UPLOAD_TO_SERVER,
+	NETFS_WRITE_TO_CACHE,
+	NETFS_INVALID_WRITE,
 } __mode(byte);
 
 typedef void (*netfs_io_terminated_t)(void *priv, ssize_t transferred_or_error,
@@ -129,9 +136,57 @@ struct netfs_inode {
 	struct fscache_cookie	*cache;
 #endif
 	loff_t			remote_i_size;	/* Size of the remote file */
+	loff_t			zero_point;	/* Size after which we assume there's no data
+						 * on the server */
+	unsigned long		flags;
+#define NETFS_ICTX_ODIRECT	0		/* The file has DIO in progress */
+#define NETFS_ICTX_UNBUFFERED	1		/* I/O should not use the pagecache */
+#define NETFS_ICTX_WRITETHROUGH	2		/* Write-through caching */
+#define NETFS_ICTX_NO_WRITE_STREAMING	3	/* Don't engage in write-streaming */
+};
+
+/*
+ * A netfs group - for instance a ceph snap.  This is marked on dirty pages and
+ * pages marked with a group must be flushed before they can be written under
+ * the domain of another group.
+ */
+struct netfs_group {
+	refcount_t		ref;
+	void (*free)(struct netfs_group *netfs_group);
 };
 
 /*
+ * Information about a dirty page (attached only if necessary).
+ * folio->private
+ */
+struct netfs_folio {
+	struct netfs_group	*netfs_group;	/* Filesystem's grouping marker (or NULL). */
+	unsigned int		dirty_offset;	/* Write-streaming dirty data offset */
+	unsigned int		dirty_len;	/* Write-streaming dirty data length */
+};
+#define NETFS_FOLIO_INFO	0x1UL	/* OR'd with folio->private. */
+
+static inline struct netfs_folio *netfs_folio_info(struct folio *folio)
+{
+	void *priv = folio_get_private(folio);
+
+	if ((unsigned long)priv & NETFS_FOLIO_INFO)
+		return (struct netfs_folio *)((unsigned long)priv & ~NETFS_FOLIO_INFO);
+	return NULL;
+}
+
+static inline struct netfs_group *netfs_folio_group(struct folio *folio)
+{
+	struct netfs_folio *finfo;
+	void *priv = folio_get_private(folio);
+
+	finfo = netfs_folio_info(folio);
+	if (finfo)
+		return finfo->netfs_group;
+	return priv;
+}
+
+/*
  * Resources required to do operations on a cache.
  */
 struct netfs_cache_resources {
@@ -143,17 +198,24 @@ struct netfs_cache_resources {
 };
 
 /*
- * Descriptor for a single component subrequest.
+ * Descriptor for a single component subrequest.  Each operation represents an
+ * individual read/write from/to a server, a cache, a journal, etc..
+ *
+ * The buffer iterator is persistent for the life of the subrequest struct and
+ * the pages it points to can be relied on to exist for the duration.
  */
 struct netfs_io_subrequest {
 	struct netfs_io_request *rreq;		/* Supervising I/O request */
+	struct work_struct	work;
 	struct list_head	rreq_link;	/* Link in rreq->subrequests */
+	struct iov_iter		io_iter;	/* Iterator for this subrequest */
 	loff_t			start;		/* Where to start the I/O */
 	size_t			len;		/* Size of the I/O */
 	size_t			transferred;	/* Amount of data transferred */
 	refcount_t		ref;
 	short			error;		/* 0 or error that occurred */
 	unsigned short		debug_index;	/* Index in list (for debugging output) */
+	unsigned int		max_nr_segs;	/* 0 or max number of segments in an iterator */
 	enum netfs_io_source	source;		/* Where to read from/write to */
 	unsigned long		flags;
 #define NETFS_SREQ_COPY_TO_CACHE	0	/* Set if should copy the data to the cache */
@@ -168,6 +230,13 @@ enum netfs_io_origin {
 	NETFS_READAHEAD,		/* This read was triggered by readahead */
 	NETFS_READPAGE,			/* This read is a synchronous read */
 	NETFS_READ_FOR_WRITE,		/* This read is to prepare a write */
+	NETFS_WRITEBACK,		/* This write was triggered by writepages */
+	NETFS_WRITETHROUGH,		/* This write was made by netfs_perform_write() */
+	NETFS_LAUNDER_WRITE,		/* This is triggered by ->launder_folio() */
+	NETFS_UNBUFFERED_WRITE,		/* This is an unbuffered write */
+	NETFS_DIO_READ,			/* This is a direct I/O read */
+	NETFS_DIO_WRITE,		/* This is a direct I/O write */
+	nr__netfs_io_origin
 } __mode(byte);
 
 /*
@@ -175,19 +244,34 @@ enum netfs_io_origin {
  * operations to a variety of data stores and then stitch the result together.
  */
 struct netfs_io_request {
-	struct work_struct	work;
+	union {
+		struct work_struct work;
+		struct rcu_head rcu;
+	};
 	struct inode		*inode;		/* The file being accessed */
 	struct address_space	*mapping;	/* The mapping being accessed */
+	struct kiocb		*iocb;		/* AIO completion vector */
 	struct netfs_cache_resources cache_resources;
+	struct list_head	proc_link;	/* Link in netfs_iorequests */
 	struct list_head	subrequests;	/* Contributory I/O operations */
+	struct iov_iter		iter;		/* Unencrypted-side iterator */
+	struct iov_iter		io_iter;	/* I/O (Encrypted-side) iterator */
 	void			*netfs_priv;	/* Private data for the netfs */
+	struct bio_vec		*direct_bv;	/* DIO buffer list (when handling iovec-iter) */
+	unsigned int		direct_bv_count; /* Number of elements in direct_bv[] */
 	unsigned int		debug_id;
+	unsigned int		rsize;		/* Maximum read size (0 for none) */
+	unsigned int		wsize;		/* Maximum write size (0 for none) */
+	unsigned int		subreq_counter;	/* Next subreq->debug_index */
 	atomic_t		nr_outstanding;	/* Number of ops in progress */
 	atomic_t		nr_copy_ops;	/* Number of copy-to-cache ops in progress */
 	size_t			submitted;	/* Amount submitted for I/O so far */
 	size_t			len;		/* Length of the request */
+	size_t			upper_len;	/* Length can be extended to here */
+	size_t			transferred;	/* Amount to be indicated as transferred */
 	short			error;		/* 0 or error that occurred */
 	enum netfs_io_origin	origin;		/* Origin of the request */
+	bool			direct_bv_unpin; /* T if direct_bv[] must be unpinned */
 	loff_t			i_size;		/* Size of the file */
 	loff_t			start;		/* Start position */
 	pgoff_t			no_unlock_folio; /* Don't unlock this folio after read */
@@ -199,17 +283,25 @@ struct netfs_io_request {
 #define NETFS_RREQ_DONT_UNLOCK_FOLIOS	3	/* Don't unlock the folios on completion */
 #define NETFS_RREQ_FAILED		4	/* The request failed */
 #define NETFS_RREQ_IN_PROGRESS		5	/* Unlocked when the request completes */
+#define NETFS_RREQ_WRITE_TO_CACHE	7	/* Need to write to the cache */
+#define NETFS_RREQ_UPLOAD_TO_SERVER	8	/* Need to write to the server */
+#define NETFS_RREQ_NONBLOCK		9	/* Don't block if possible (O_NONBLOCK) */
+#define NETFS_RREQ_BLOCKED		10	/* We blocked */
 	const struct netfs_request_ops *netfs_ops;
+	void (*cleanup)(struct netfs_io_request *req);
 };
 
 /*
  * Operations the network filesystem can/must provide to the helpers.
  */
 struct netfs_request_ops {
+	unsigned int	io_request_size;	/* Alloc size for netfs_io_request struct */
+	unsigned int	io_subrequest_size;	/* Alloc size for netfs_io_subrequest struct */
 	int (*init_request)(struct netfs_io_request *rreq, struct file *file);
 	void (*free_request)(struct netfs_io_request *rreq);
-	int (*begin_cache_operation)(struct netfs_io_request *rreq);
+	void (*free_subrequest)(struct netfs_io_subrequest *rreq);
 
+	/* Read request handling */
 	void (*expand_readahead)(struct netfs_io_request *rreq);
 	bool (*clamp_length)(struct netfs_io_subrequest *subreq);
 	void (*issue_read)(struct netfs_io_subrequest *subreq);
@@ -217,6 +309,14 @@ struct netfs_request_ops {
 	int (*check_write_begin)(struct file *file, loff_t pos, unsigned len,
 				 struct folio **foliop, void **_fsdata);
 	void (*done)(struct netfs_io_request *rreq);
+
+	/* Modification handling */
+	void (*update_i_size)(struct inode *inode, loff_t i_size);
+
+	/* Write request handling */
+	void (*create_write_requests)(struct netfs_io_request *wreq,
+				      loff_t start, size_t len);
+	void (*invalidate_cache)(struct netfs_io_request *wreq);
 };
 
 /*
@@ -229,8 +329,7 @@ enum netfs_read_from_hole {
 };
 
 /*
- * Table of operations for access to a cache.  This is obtained by
- * rreq->ops->begin_cache_operation().
+ * Table of operations for access to a cache.
  */
 struct netfs_cache_ops {
 	/* End an operation */
@@ -265,8 +364,8 @@ struct netfs_cache_ops {
 	 * actually do.
 	 */
 	int (*prepare_write)(struct netfs_cache_resources *cres,
-			     loff_t *_start, size_t *_len, loff_t i_size,
-			     bool no_space_allocated_yet);
+			     loff_t *_start, size_t *_len, size_t upper_len,
+			     loff_t i_size, bool no_space_allocated_yet);
 
 	/* Prepare an on-demand read operation, shortening it to a cached/uncached
 	 * boundary as appropriate.
@@ -284,22 +383,62 @@ struct netfs_cache_ops {
 			       loff_t *_data_start, size_t *_data_len);
 };
 
+/* High-level read API. */
+ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter);
+ssize_t netfs_buffered_read_iter(struct kiocb *iocb, struct iov_iter *iter);
+ssize_t netfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter);
+
+/* High-level write API */
+ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
+			    struct netfs_group *netfs_group);
+ssize_t netfs_buffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *from,
+					 struct netfs_group *netfs_group);
+ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from);
+ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from);
+
+/* Address operations API */
 struct readahead_control;
 void netfs_readahead(struct readahead_control *);
 int netfs_read_folio(struct file *, struct folio *);
 int netfs_write_begin(struct netfs_inode *, struct file *,
-		struct address_space *, loff_t pos, unsigned int len,
-		struct folio **, void **fsdata);
-
+		      struct address_space *, loff_t pos, unsigned int len,
+		      struct folio **, void **fsdata);
+int netfs_writepages(struct address_space *mapping,
+		     struct writeback_control *wbc);
+bool netfs_dirty_folio(struct address_space *mapping, struct folio *folio);
+int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc);
+void netfs_clear_inode_writeback(struct inode *inode, const void *aux);
+void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length);
+bool netfs_release_folio(struct folio *folio, gfp_t gfp);
+int netfs_launder_folio(struct folio *folio);
+
+/* VMA operations API. */
+vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group);
+
+/* (Sub)request management API. */
 void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool);
 void netfs_get_subrequest(struct netfs_io_subrequest *subreq,
 			  enum netfs_sreq_ref_trace what);
 void netfs_put_subrequest(struct netfs_io_subrequest *subreq,
 			  bool was_async, enum netfs_sreq_ref_trace what);
-void netfs_stats_show(struct seq_file *);
 ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
 				struct iov_iter *new,
 				iov_iter_extraction_t extraction_flags);
+size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset,
+			size_t max_size, size_t max_segs);
+struct netfs_io_subrequest *netfs_create_write_request(
+	struct netfs_io_request *wreq, enum netfs_io_source dest,
+	loff_t start, size_t len, work_func_t worker);
+void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error,
+				       bool was_async);
+void netfs_queue_write_request(struct netfs_io_subrequest *subreq);
+
+int netfs_start_io_read(struct inode *inode);
+void netfs_end_io_read(struct inode *inode);
+int netfs_start_io_write(struct inode *inode);
+void netfs_end_io_write(struct inode *inode);
+int netfs_start_io_direct(struct inode *inode);
+void netfs_end_io_direct(struct inode *inode);
 
 /**
  * netfs_inode - Get the netfs inode context from the inode
@@ -317,30 +456,44 @@ static inline struct netfs_inode *netfs_inode(struct inode *inode)
  * netfs_inode_init - Initialise a netfslib inode context
  * @ctx: The netfs inode to initialise
  * @ops: The netfs's operations list
+ * @use_zero_point: True to use the zero_point read optimisation
  *
  * Initialise the netfs library context struct.  This is expected to follow on
  * directly from the VFS inode struct.
  */
 static inline void netfs_inode_init(struct netfs_inode *ctx,
-				    const struct netfs_request_ops *ops)
+				    const struct netfs_request_ops *ops,
+				    bool use_zero_point)
 {
 	ctx->ops = ops;
 	ctx->remote_i_size = i_size_read(&ctx->inode);
+	ctx->zero_point = LLONG_MAX;
+	ctx->flags = 0;
 #if IS_ENABLED(CONFIG_FSCACHE)
 	ctx->cache = NULL;
 #endif
+	/* ->releasepage() drives zero_point */
+	if (use_zero_point) {
+		ctx->zero_point = ctx->remote_i_size;
+		mapping_set_release_always(ctx->inode.i_mapping);
+	}
 }
 
 /**
  * netfs_resize_file - Note that a file got resized
  * @ctx: The netfs inode being resized
  * @new_i_size: The new file size
+ * @changed_on_server: The change was applied to the server
  *
  * Inform the netfs lib that a file got resized so that it can adjust its state.
  */
-static inline void netfs_resize_file(struct netfs_inode *ctx, loff_t new_i_size)
+static inline void netfs_resize_file(struct netfs_inode *ctx, loff_t new_i_size,
+				     bool changed_on_server)
 {
-	ctx->remote_i_size = new_i_size;
+	if (changed_on_server)
+		ctx->remote_i_size = new_i_size;
+	if (new_i_size < ctx->zero_point)
+		ctx->zero_point = new_i_size;
 }
 
 /**
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index cd797e00fe35..92de074e63b9 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -124,6 +124,7 @@ struct nfs_client {
 	char			cl_ipaddr[48];
 	struct net		*cl_net;
 	struct list_head	pending_cb_stateids;
+	struct rcu_head		rcu;
 };
 
 /*
@@ -265,6 +266,7 @@ struct nfs_server {
 	const struct cred	*cred;
 	bool			has_sec_mnt_opts;
 	struct kobject		kobj;
+	struct rcu_head		rcu;
 };
 
 /* Server capabilities */
diff --git a/include/linux/node.h b/include/linux/node.h
index 427a5975cf40..25b66d705ee2 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -20,14 +20,14 @@
 #include <linux/list.h>
 
 /**
- * struct node_hmem_attrs - heterogeneous memory performance attributes
+ * struct access_coordinate - generic performance coordinates container
  *
  * @read_bandwidth:	Read bandwidth in MB/s
  * @write_bandwidth:	Write bandwidth in MB/s
  * @read_latency:	Read latency in nanoseconds
  * @write_latency:	Write latency in nanoseconds
  */
-struct node_hmem_attrs {
+struct access_coordinate {
 	unsigned int read_bandwidth;
 	unsigned int write_bandwidth;
 	unsigned int read_latency;
@@ -65,7 +65,7 @@ struct node_cache_attrs {
 
 #ifdef CONFIG_HMEM_REPORTING
 void node_add_cache(unsigned int nid, struct node_cache_attrs *cache_attrs);
-void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs,
+void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord,
 			 unsigned access);
 #else
 static inline void node_add_cache(unsigned int nid,
@@ -74,7 +74,7 @@ static inline void node_add_cache(unsigned int nid,
 }
 
 static inline void node_set_perf_attrs(unsigned int nid,
-				       struct node_hmem_attrs *hmem_attrs,
+				       struct access_coordinate *coord,
 				       unsigned access)
 {
 }
diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h
index 0f1d024bd958..7d22ea50b098 100644
--- a/include/linux/ns_common.h
+++ b/include/linux/ns_common.h
@@ -7,7 +7,7 @@
 struct proc_ns_operations;
 
 struct ns_common {
-	atomic_long_t stashed;
+	struct dentry *stashed;
 	const struct proc_ns_operations *ops;
 	unsigned int inum;
 	refcount_t count;
diff --git a/include/linux/nvme-rdma.h b/include/linux/nvme-rdma.h
index 4dd7e6fe92fb..eb2f04d636c8 100644
--- a/include/linux/nvme-rdma.h
+++ b/include/linux/nvme-rdma.h
@@ -6,7 +6,11 @@
 #ifndef _LINUX_NVME_RDMA_H
 #define _LINUX_NVME_RDMA_H
 
-#define NVME_RDMA_MAX_QUEUE_SIZE	128
+#define NVME_RDMA_IP_PORT		4420
+
+#define NVME_RDMA_MAX_QUEUE_SIZE 256
+#define NVME_RDMA_MAX_METADATA_QUEUE_SIZE 128
+#define NVME_RDMA_DEFAULT_QUEUE_SIZE 128
 
 enum nvme_rdma_cm_fmt {
 	NVME_RDMA_CM_FMT_1_0 = 0x0,
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 44325c068b6a..425573202295 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -20,12 +20,9 @@
 #define NVMF_TRSVCID_SIZE	32
 #define NVMF_TRADDR_SIZE	256
 #define NVMF_TSAS_SIZE		256
-#define NVMF_AUTH_HASH_LEN	64
 
 #define NVME_DISC_SUBSYS_NAME	"nqn.2014-08.org.nvmexpress.discovery"
 
-#define NVME_RDMA_IP_PORT	4420
-
 #define NVME_NSID_ALL		0xffffffff
 
 enum nvme_subsys_type {
@@ -647,6 +644,7 @@ enum {
 	NVME_CMD_EFFECTS_NCC		= 1 << 2,
 	NVME_CMD_EFFECTS_NIC		= 1 << 3,
 	NVME_CMD_EFFECTS_CCC		= 1 << 4,
+	NVME_CMD_EFFECTS_CSER_MASK	= GENMASK(15, 14),
 	NVME_CMD_EFFECTS_CSE_MASK	= GENMASK(18, 16),
 	NVME_CMD_EFFECTS_UUID_SEL	= 1 << 19,
 	NVME_CMD_EFFECTS_SCOPE_MASK	= GENMASK(31, 20),
@@ -817,12 +815,6 @@ struct nvme_reservation_status_ext {
 	struct nvme_registered_ctrl_ext regctl_eds[];
 };
 
-enum nvme_async_event_type {
-	NVME_AER_TYPE_ERROR	= 0,
-	NVME_AER_TYPE_SMART	= 1,
-	NVME_AER_TYPE_NOTICE	= 2,
-};
-
 /* I/O commands */
 
 enum nvme_opcode {
@@ -1819,7 +1811,7 @@ struct nvme_command {
 	};
 };
 
-static inline bool nvme_is_fabrics(struct nvme_command *cmd)
+static inline bool nvme_is_fabrics(const struct nvme_command *cmd)
 {
 	return cmd->common.opcode == nvme_fabrics_command;
 }
@@ -1838,7 +1830,7 @@ struct nvme_error_slot {
 	__u8		resv2[24];
 };
 
-static inline bool nvme_is_write(struct nvme_command *cmd)
+static inline bool nvme_is_write(const struct nvme_command *cmd)
 {
 	/*
 	 * What a mess...
diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h
index 6ec4b9743e25..34c0e58dfa26 100644
--- a/include/linux/nvmem-consumer.h
+++ b/include/linux/nvmem-consumer.h
@@ -81,6 +81,7 @@ int nvmem_device_cell_write(struct nvmem_device *nvmem,
 			    struct nvmem_cell_info *info, void *buf);
 
 const char *nvmem_dev_name(struct nvmem_device *nvmem);
+size_t nvmem_dev_size(struct nvmem_device *nvmem);
 
 void nvmem_add_cell_lookups(struct nvmem_cell_lookup *entries,
 			    size_t nentries);
@@ -247,7 +248,6 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np,
 				     const char *id);
 struct nvmem_device *of_nvmem_device_get(struct device_node *np,
 					 const char *name);
-struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem);
 #else
 static inline struct nvmem_cell *of_nvmem_cell_get(struct device_node *np,
 						   const char *id)
@@ -260,12 +260,6 @@ static inline struct nvmem_device *of_nvmem_device_get(struct device_node *np,
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
-
-static inline struct device_node *
-of_nvmem_layout_get_container(struct nvmem_device *nvmem)
-{
-	return NULL;
-}
 #endif /* CONFIG_NVMEM && CONFIG_OF */
 
 #endif  /* ifndef _LINUX_NVMEM_CONSUMER_H */
diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h
index e3930835235b..f0ba0e03218f 100644
--- a/include/linux/nvmem-provider.h
+++ b/include/linux/nvmem-provider.h
@@ -9,6 +9,7 @@
 #ifndef _LINUX_NVMEM_PROVIDER_H
 #define _LINUX_NVMEM_PROVIDER_H
 
+#include <linux/device.h>
 #include <linux/device/driver.h>
 #include <linux/err.h>
 #include <linux/errno.h>
@@ -83,6 +84,8 @@ struct nvmem_cell_info {
  * @cells:	Optional array of pre-defined NVMEM cells.
  * @ncells:	Number of elements in cells.
  * @add_legacy_fixed_of_cells:	Read fixed NVMEM cells from old OF syntax.
+ * @fixup_dt_cell_info: Will be called before a cell is added. Can be
+ *		used to modify the nvmem_cell_info.
  * @keepout:	Optional array of keepout ranges (sorted ascending by start).
  * @nkeepout:	Number of elements in the keepout array.
  * @type:	Type of the nvmem storage
@@ -113,6 +116,8 @@ struct nvmem_config {
 	const struct nvmem_cell_info	*cells;
 	int			ncells;
 	bool			add_legacy_fixed_of_cells;
+	void (*fixup_dt_cell_info)(struct nvmem_device *nvmem,
+				   struct nvmem_cell_info *cell);
 	const struct nvmem_keepout *keepout;
 	unsigned int		nkeepout;
 	enum nvmem_type		type;
@@ -154,15 +159,11 @@ struct nvmem_cell_table {
 /**
  * struct nvmem_layout - NVMEM layout definitions
  *
- * @name:		Layout name.
- * @of_match_table:	Open firmware match table.
+ * @dev:		Device-model layout device.
+ * @nvmem:		The underlying NVMEM device
  * @add_cells:		Will be called if a nvmem device is found which
  *			has this layout. The function will add layout
  *			specific cells with nvmem_add_one_cell().
- * @fixup_cell_info:	Will be called before a cell is added. Can be
- *			used to modify the nvmem_cell_info.
- * @owner:		Pointer to struct module.
- * @node:		List node.
  *
  * A nvmem device can hold a well defined structure which can just be
  * evaluated during runtime. For example a TLV list, or a list of "name=val"
@@ -170,17 +171,15 @@ struct nvmem_cell_table {
  * cells.
  */
 struct nvmem_layout {
-	const char *name;
-	const struct of_device_id *of_match_table;
-	int (*add_cells)(struct device *dev, struct nvmem_device *nvmem,
-			 struct nvmem_layout *layout);
-	void (*fixup_cell_info)(struct nvmem_device *nvmem,
-				struct nvmem_layout *layout,
-				struct nvmem_cell_info *cell);
-
-	/* private */
-	struct module *owner;
-	struct list_head node;
+	struct device dev;
+	struct nvmem_device *nvmem;
+	int (*add_cells)(struct nvmem_layout *layout);
+};
+
+struct nvmem_layout_driver {
+	struct device_driver driver;
+	int (*probe)(struct nvmem_layout *layout);
+	void (*remove)(struct nvmem_layout *layout);
 };
 
 #if IS_ENABLED(CONFIG_NVMEM)
@@ -197,13 +196,14 @@ void nvmem_del_cell_table(struct nvmem_cell_table *table);
 int nvmem_add_one_cell(struct nvmem_device *nvmem,
 		       const struct nvmem_cell_info *info);
 
-int __nvmem_layout_register(struct nvmem_layout *layout, struct module *owner);
-#define nvmem_layout_register(layout) \
-	__nvmem_layout_register(layout, THIS_MODULE)
+int nvmem_layout_register(struct nvmem_layout *layout);
 void nvmem_layout_unregister(struct nvmem_layout *layout);
 
-const void *nvmem_layout_get_match_data(struct nvmem_device *nvmem,
-					struct nvmem_layout *layout);
+int nvmem_layout_driver_register(struct nvmem_layout_driver *drv);
+void nvmem_layout_driver_unregister(struct nvmem_layout_driver *drv);
+#define module_nvmem_layout_driver(__nvmem_layout_driver)		\
+	module_driver(__nvmem_layout_driver, nvmem_layout_driver_register, \
+		      nvmem_layout_driver_unregister)
 
 #else
 
@@ -235,17 +235,27 @@ static inline int nvmem_layout_register(struct nvmem_layout *layout)
 
 static inline void nvmem_layout_unregister(struct nvmem_layout *layout) {}
 
-static inline const void *
-nvmem_layout_get_match_data(struct nvmem_device *nvmem,
-			    struct nvmem_layout *layout)
+#endif /* CONFIG_NVMEM */
+
+#if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF)
+
+/**
+ * of_nvmem_layout_get_container() - Get OF node of layout container
+ *
+ * @nvmem: nvmem device
+ *
+ * Return: a node pointer with refcount incremented or NULL if no
+ * container exists. Use of_node_put() on it when done.
+ */
+struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem);
+
+#else  /* CONFIG_NVMEM && CONFIG_OF */
+
+static inline struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem)
 {
 	return NULL;
 }
 
-#endif /* CONFIG_NVMEM */
-
-#define module_nvmem_layout_driver(__layout_driver)		\
-	module_driver(__layout_driver, nvmem_layout_register,	\
-		      nvmem_layout_unregister)
+#endif /* CONFIG_NVMEM && CONFIG_OF */
 
 #endif  /* ifndef _LINUX_NVMEM_PROVIDER_H */
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 2c7a3d4bc775..9042bca5bb84 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -2,10 +2,7 @@
 #ifndef _LINUX_OF_DEVICE_H
 #define _LINUX_OF_DEVICE_H
 
-#include <linux/platform_device.h>
-#include <linux/of_platform.h> /* temporary until merge */
-
-#include <linux/of.h>
+#include <linux/device/driver.h>
 
 struct device;
 struct of_device_id;
@@ -40,6 +37,9 @@ static inline int of_dma_configure(struct device *dev,
 {
 	return of_dma_configure_id(dev, np, force_dma, NULL);
 }
+
+void of_device_make_bus_id(struct device *dev);
+
 #else /* CONFIG_OF */
 
 static inline int of_driver_match_device(struct device *dev,
@@ -82,6 +82,9 @@ static inline int of_dma_configure(struct device *dev,
 {
 	return 0;
 }
+
+static inline void of_device_make_bus_id(struct device *dev) {}
+
 #endif /* CONFIG_OF */
 
 #endif /* _LINUX_OF_DEVICE_H */
diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h
index 9a5e6b410dd2..e61cbbe12dac 100644
--- a/include/linux/of_iommu.h
+++ b/include/linux/of_iommu.h
@@ -8,20 +8,19 @@ struct iommu_ops;
 
 #ifdef CONFIG_OF_IOMMU
 
-extern const struct iommu_ops *of_iommu_configure(struct device *dev,
-					struct device_node *master_np,
-					const u32 *id);
+extern int of_iommu_configure(struct device *dev, struct device_node *master_np,
+			      const u32 *id);
 
 extern void of_iommu_get_resv_regions(struct device *dev,
 				      struct list_head *list);
 
 #else
 
-static inline const struct iommu_ops *of_iommu_configure(struct device *dev,
-					 struct device_node *master_np,
-					 const u32 *id)
+static inline int of_iommu_configure(struct device *dev,
+				     struct device_node *master_np,
+				     const u32 *id)
 {
-	return NULL;
+	return -ENODEV;
 }
 
 static inline void of_iommu_get_resv_regions(struct device *dev,
diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h
index fadfea575485..a2ff1ad48f7f 100644
--- a/include/linux/of_platform.h
+++ b/include/linux/of_platform.h
@@ -7,11 +7,11 @@
  */
 
 #include <linux/mod_devicetable.h>
-#include <linux/of_device.h>
-#include <linux/platform_device.h>
 
 struct device;
+struct device_node;
 struct of_device_id;
+struct platform_device;
 
 /**
  * struct of_dev_auxdata - lookup table entry for device names & platform_data
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 06142ff7f9ce..2df35e65557d 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -206,6 +206,7 @@ enum mapping_flags {
 	AS_RELEASE_ALWAYS,	/* Call ->release_folio(), even if no private data */
 	AS_STABLE_WRITES,	/* must wait for writeback before modifying
 				   folio contents */
+	AS_UNMOVABLE,		/* The mapping cannot be moved, ever */
 };
 
 /**
@@ -306,6 +307,22 @@ static inline void mapping_clear_stable_writes(struct address_space *mapping)
 	clear_bit(AS_STABLE_WRITES, &mapping->flags);
 }
 
+static inline void mapping_set_unmovable(struct address_space *mapping)
+{
+	/*
+	 * It's expected unmovable mappings are also unevictable. Compaction
+	 * migrate scanner (isolate_migratepages_block()) relies on this to
+	 * reduce page locking.
+	 */
+	set_bit(AS_UNEVICTABLE, &mapping->flags);
+	set_bit(AS_UNMOVABLE, &mapping->flags);
+}
+
+static inline bool mapping_unmovable(struct address_space *mapping)
+{
+	return test_bit(AS_UNMOVABLE, &mapping->flags);
+}
+
 static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
 {
 	return mapping->gfp_mask;
diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h
index 6b1301e2498e..3a4860bd2758 100644
--- a/include/linux/pci-ecam.h
+++ b/include/linux/pci-ecam.h
@@ -93,6 +93,6 @@ extern const struct pci_ecam_ops loongson_pci_ecam_ops; /* Loongson PCIe */
 #if IS_ENABLED(CONFIG_PCI_HOST_COMMON)
 /* for DT-based PCI controllers that support ECAM */
 int pci_host_common_probe(struct platform_device *pdev);
-int pci_host_common_remove(struct platform_device *pdev);
+void pci_host_common_remove(struct platform_device *pdev);
 #endif
 #endif
diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h
index 5cb694031072..40ea18f5aa02 100644
--- a/include/linux/pci-epc.h
+++ b/include/linux/pci-epc.h
@@ -19,13 +19,6 @@ enum pci_epc_interface_type {
 	SECONDARY_INTERFACE,
 };
 
-enum pci_epc_irq_type {
-	PCI_EPC_IRQ_UNKNOWN,
-	PCI_EPC_IRQ_LEGACY,
-	PCI_EPC_IRQ_MSI,
-	PCI_EPC_IRQ_MSIX,
-};
-
 static inline const char *
 pci_epc_interface_string(enum pci_epc_interface_type type)
 {
@@ -79,7 +72,7 @@ struct pci_epc_ops {
 			    u16 interrupts, enum pci_barno, u32 offset);
 	int	(*get_msix)(struct pci_epc *epc, u8 func_no, u8 vfunc_no);
 	int	(*raise_irq)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-			     enum pci_epc_irq_type type, u16 interrupt_num);
+			     unsigned int type, u16 interrupt_num);
 	int	(*map_msi_irq)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			       phys_addr_t phys_addr, u8 interrupt_num,
 			       u32 entry_size, u32 *msi_data,
@@ -122,7 +115,7 @@ struct pci_epc_mem {
  * struct pci_epc - represents the PCI EPC device
  * @dev: PCI EPC device
  * @pci_epf: list of endpoint functions present in this EPC device
- * list_lock: Mutex for protecting pci_epf list
+ * @list_lock: Mutex for protecting pci_epf list
  * @ops: function pointers for performing endpoint operations
  * @windows: array of address space of the endpoint controller
  * @mem: first window of the endpoint controller, which corresponds to
@@ -229,7 +222,7 @@ int pci_epc_map_msi_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			phys_addr_t phys_addr, u8 interrupt_num,
 			u32 entry_size, u32 *msi_data, u32 *msi_addr_offset);
 int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-		      enum pci_epc_irq_type type, u16 interrupt_num);
+		      unsigned int type, u16 interrupt_num);
 int pci_epc_start(struct pci_epc *epc);
 void pci_epc_stop(struct pci_epc *epc);
 const struct pci_epc_features *pci_epc_get_features(struct pci_epc *epc,
diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h
index 3f44b6aec477..77b146e0f672 100644
--- a/include/linux/pci-epf.h
+++ b/include/linux/pci-epf.h
@@ -68,7 +68,7 @@ struct pci_epf_ops {
 };
 
 /**
- * struct pci_epf_event_ops - Callbacks for capturing the EPC events
+ * struct pci_epc_event_ops - Callbacks for capturing the EPC events
  * @core_init: Callback for the EPC initialization complete event
  * @link_up: Callback for the EPC link up event
  * @link_down: Callback for the EPC link down event
@@ -98,7 +98,7 @@ struct pci_epf_driver {
 	void	(*remove)(struct pci_epf *epf);
 
 	struct device_driver	driver;
-	struct pci_epf_ops	*ops;
+	const struct pci_epf_ops *ops;
 	struct module		*owner;
 	struct list_head	epf_group;
 	const struct pci_epf_device_id	*id_table;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 58a4c976c39b..7ab0d13672da 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -715,6 +715,7 @@ static inline bool pci_is_bridge(struct pci_dev *dev)
 
 /**
  * pci_is_vga - check if the PCI device is a VGA device
+ * @pdev: PCI device
  *
  * The PCI Code and ID Assignment spec, r1.15, secs 1.4 and 1.1, define
  * VGA Base Class and Sub-Classes:
@@ -885,7 +886,6 @@ struct module;
 
 /**
  * struct pci_driver - PCI driver structure
- * @node:	List of driver structures.
  * @name:	Driver name.
  * @id_table:	Pointer to table of device IDs the driver is
  *		interested in.  Most drivers should export this
@@ -940,7 +940,6 @@ struct module;
  *		own I/O address space.
  */
 struct pci_driver {
-	struct list_head	node;
 	const char		*name;
 	const struct pci_device_id *id_table;	/* Must be non-NULL for probe to be called */
 	int  (*probe)(struct pci_dev *dev, const struct pci_device_id *id);	/* New device inserted */
@@ -1073,11 +1072,13 @@ enum {
 	PCI_SCAN_ALL_PCIE_DEVS	= 0x00000040,	/* Scan all, not just dev 0 */
 };
 
-#define PCI_IRQ_LEGACY		(1 << 0) /* Allow legacy interrupts */
+#define PCI_IRQ_INTX		(1 << 0) /* Allow INTx interrupts */
 #define PCI_IRQ_MSI		(1 << 1) /* Allow MSI interrupts */
 #define PCI_IRQ_MSIX		(1 << 2) /* Allow MSI-X interrupts */
 #define PCI_IRQ_AFFINITY	(1 << 3) /* Auto-assign affinity */
 
+#define PCI_IRQ_LEGACY		PCI_IRQ_INTX /* Deprecated! Use PCI_IRQ_INTX */
+
 /* These external functions are only available when PCI support is enabled */
 #ifdef CONFIG_PCI
 
@@ -1170,6 +1171,7 @@ int pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge);
 u8 pci_common_swizzle(struct pci_dev *dev, u8 *pinp);
 struct pci_dev *pci_dev_get(struct pci_dev *dev);
 void pci_dev_put(struct pci_dev *dev);
+DEFINE_FREE(pci_dev_put, struct pci_dev *, if (_T) pci_dev_put(_T))
 void pci_remove_bus(struct pci_bus *b);
 void pci_stop_and_remove_bus_device(struct pci_dev *dev);
 void pci_stop_and_remove_bus_device_locked(struct pci_dev *dev);
@@ -1366,6 +1368,7 @@ int pcie_set_mps(struct pci_dev *dev, int mps);
 u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev,
 			     enum pci_bus_speed *speed,
 			     enum pcie_link_width *width);
+int pcie_link_speed_mbps(struct pci_dev *pdev);
 void pcie_print_link_status(struct pci_dev *dev);
 int pcie_reset_flr(struct pci_dev *dev, bool probe);
 int pcie_flr(struct pci_dev *dev);
@@ -1419,6 +1422,7 @@ int pci_load_and_free_saved_state(struct pci_dev *dev,
 				  struct pci_saved_state **state);
 int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state);
 int pci_set_power_state(struct pci_dev *dev, pci_power_t state);
+int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state);
 pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state);
 bool pci_pme_capable(struct pci_dev *dev, pci_power_t state);
 void pci_pme_active(struct pci_dev *dev, bool enable);
@@ -1622,6 +1626,8 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max,
 
 void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
 		  void *userdata);
+void pci_walk_bus_locked(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
+			 void *userdata);
 int pci_cfg_space_size(struct pci_dev *dev);
 unsigned char pci_bus_max_busnr(struct pci_bus *bus);
 void pci_setup_bridge(struct pci_bus *bus);
@@ -1876,6 +1882,7 @@ void pci_cfg_access_unlock(struct pci_dev *dev);
 void pci_dev_lock(struct pci_dev *dev);
 int pci_dev_trylock(struct pci_dev *dev);
 void pci_dev_unlock(struct pci_dev *dev);
+DEFINE_GUARD(pci_dev, struct pci_dev *, pci_dev_lock(_T), pci_dev_unlock(_T))
 
 /*
  * PCI domain support.  Sometimes called PCI segment (eg by ACPI),
@@ -2021,6 +2028,8 @@ static inline int pci_save_state(struct pci_dev *dev) { return 0; }
 static inline void pci_restore_state(struct pci_dev *dev) { }
 static inline int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 { return 0; }
+static inline int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state)
+{ return 0; }
 static inline int pci_wake_from_d3(struct pci_dev *dev, bool enable)
 { return 0; }
 static inline pci_power_t pci_choose_state(struct pci_dev *dev,
@@ -2132,14 +2141,14 @@ int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma);
 	(pci_resource_end((dev), (bar)) ? 				\
 	 resource_size(pci_resource_n((dev), (bar))) : 0)
 
-#define __pci_dev_for_each_res0(dev, res, ...)				\
-	for (unsigned int __b = 0;					\
-	     res = pci_resource_n(dev, __b), __b < PCI_NUM_RESOURCES;	\
+#define __pci_dev_for_each_res0(dev, res, ...)				  \
+	for (unsigned int __b = 0;					  \
+	     __b < PCI_NUM_RESOURCES && (res = pci_resource_n(dev, __b)); \
 	     __b++)
 
-#define __pci_dev_for_each_res1(dev, res, __b)				\
-	for (__b = 0;							\
-	     res = pci_resource_n(dev, __b), __b < PCI_NUM_RESOURCES;	\
+#define __pci_dev_for_each_res1(dev, res, __b)				  \
+	for (__b = 0;							  \
+	     __b < PCI_NUM_RESOURCES && (res = pci_resource_n(dev, __b)); \
 	     __b++)
 
 #define pci_dev_for_each_resource(dev, res, ...)			\
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 466cf477551a..f6d0e3513948 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -299,6 +299,27 @@ static inline pmd_t pmdp_get(pmd_t *pmdp)
 }
 #endif
 
+#ifndef pudp_get
+static inline pud_t pudp_get(pud_t *pudp)
+{
+	return READ_ONCE(*pudp);
+}
+#endif
+
+#ifndef p4dp_get
+static inline p4d_t p4dp_get(p4d_t *p4dp)
+{
+	return READ_ONCE(*p4dp);
+}
+#endif
+
+#ifndef pgdp_get
+static inline pgd_t pgdp_get(pgd_t *pgdp)
+{
+	return READ_ONCE(*pgdp);
+}
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long address,
diff --git a/include/linux/pid.h b/include/linux/pid.h
index 395cacce1179..c79a0efd0258 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -55,6 +55,10 @@ struct pid
 	refcount_t count;
 	unsigned int level;
 	spinlock_t lock;
+#ifdef CONFIG_FS_PID
+	struct dentry *stashed;
+	unsigned long ino;
+#endif
 	/* lists of tasks that use this pid */
 	struct hlist_head tasks[PIDTYPE_MAX];
 	struct hlist_head inodes;
@@ -66,15 +70,13 @@ struct pid
 
 extern struct pid init_struct_pid;
 
-extern const struct file_operations pidfd_fops;
-
 struct file;
 
-extern struct pid *pidfd_pid(const struct file *file);
+struct pid *pidfd_pid(const struct file *file);
 struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags);
 struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags);
-int pidfd_create(struct pid *pid, unsigned int flags);
 int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret);
+void do_notify_pidfd(struct task_struct *task);
 
 static inline struct pid *get_pid(struct pid *pid)
 {
diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h
new file mode 100644
index 000000000000..40dd325a32a6
--- /dev/null
+++ b/include/linux/pidfs.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_PID_FS_H
+#define _LINUX_PID_FS_H
+
+struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags);
+void __init pidfs_init(void);
+bool is_pidfs_sb(const struct super_block *sb);
+
+#endif /* _LINUX_PID_FS_H */
diff --git a/include/linux/pinctrl/machine.h b/include/linux/pinctrl/machine.h
index ee8803f6ad07..673e96df453b 100644
--- a/include/linux/pinctrl/machine.h
+++ b/include/linux/pinctrl/machine.h
@@ -47,7 +47,7 @@ struct pinctrl_map_mux {
 struct pinctrl_map_configs {
 	const char *group_or_pin;
 	unsigned long *configs;
-	unsigned num_configs;
+	unsigned int num_configs;
 };
 
 /**
@@ -154,13 +154,13 @@ struct pinctrl_map;
 #ifdef CONFIG_PINCTRL
 
 extern int pinctrl_register_mappings(const struct pinctrl_map *map,
-				     unsigned num_maps);
+				     unsigned int num_maps);
 extern void pinctrl_unregister_mappings(const struct pinctrl_map *map);
 extern void pinctrl_provide_dummies(void);
 #else
 
 static inline int pinctrl_register_mappings(const struct pinctrl_map *map,
-					    unsigned num_maps)
+					    unsigned int num_maps)
 {
 	return 0;
 }
diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h
index d74b7a4ea154..a65d3d078e58 100644
--- a/include/linux/pinctrl/pinconf-generic.h
+++ b/include/linux/pinctrl/pinconf-generic.h
@@ -193,17 +193,17 @@ struct pinconf_generic_params {
 
 int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev,
 		struct device_node *np, struct pinctrl_map **map,
-		unsigned *reserved_maps, unsigned *num_maps,
+		unsigned int *reserved_maps, unsigned int *num_maps,
 		enum pinctrl_map_type type);
 int pinconf_generic_dt_node_to_map(struct pinctrl_dev *pctldev,
 		struct device_node *np_config, struct pinctrl_map **map,
-		unsigned *num_maps, enum pinctrl_map_type type);
+		unsigned int *num_maps, enum pinctrl_map_type type);
 void pinconf_generic_dt_free_map(struct pinctrl_dev *pctldev,
-		struct pinctrl_map *map, unsigned num_maps);
+		struct pinctrl_map *map, unsigned int num_maps);
 
 static inline int pinconf_generic_dt_node_to_map_group(struct pinctrl_dev *pctldev,
 		struct device_node *np_config, struct pinctrl_map **map,
-		unsigned *num_maps)
+		unsigned int *num_maps)
 {
 	return pinconf_generic_dt_node_to_map(pctldev, np_config, map, num_maps,
 			PIN_MAP_TYPE_CONFIGS_GROUP);
@@ -211,7 +211,7 @@ static inline int pinconf_generic_dt_node_to_map_group(struct pinctrl_dev *pctld
 
 static inline int pinconf_generic_dt_node_to_map_pin(struct pinctrl_dev *pctldev,
 		struct device_node *np_config, struct pinctrl_map **map,
-		unsigned *num_maps)
+		unsigned int *num_maps)
 {
 	return pinconf_generic_dt_node_to_map(pctldev, np_config, map, num_maps,
 			PIN_MAP_TYPE_CONFIGS_PIN);
diff --git a/include/linux/pinctrl/pinconf.h b/include/linux/pinctrl/pinconf.h
index f8a8215e9021..770ec2221156 100644
--- a/include/linux/pinctrl/pinconf.h
+++ b/include/linux/pinctrl/pinconf.h
@@ -40,25 +40,25 @@ struct pinconf_ops {
 	bool is_generic;
 #endif
 	int (*pin_config_get) (struct pinctrl_dev *pctldev,
-			       unsigned pin,
+			       unsigned int pin,
 			       unsigned long *config);
 	int (*pin_config_set) (struct pinctrl_dev *pctldev,
-			       unsigned pin,
+			       unsigned int pin,
 			       unsigned long *configs,
-			       unsigned num_configs);
+			       unsigned int num_configs);
 	int (*pin_config_group_get) (struct pinctrl_dev *pctldev,
-				     unsigned selector,
+				     unsigned int selector,
 				     unsigned long *config);
 	int (*pin_config_group_set) (struct pinctrl_dev *pctldev,
-				     unsigned selector,
+				     unsigned int selector,
 				     unsigned long *configs,
-				     unsigned num_configs);
+				     unsigned int num_configs);
 	void (*pin_config_dbg_show) (struct pinctrl_dev *pctldev,
 				     struct seq_file *s,
-				     unsigned offset);
+				     unsigned int offset);
 	void (*pin_config_group_dbg_show) (struct pinctrl_dev *pctldev,
 					   struct seq_file *s,
-					   unsigned selector);
+					   unsigned int selector);
 	void (*pin_config_config_dbg_show) (struct pinctrl_dev *pctldev,
 					    struct seq_file *s,
 					    unsigned long config);
diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h
index 4d252ea00ed1..9a8189ffd0f2 100644
--- a/include/linux/pinctrl/pinctrl.h
+++ b/include/linux/pinctrl/pinctrl.h
@@ -54,7 +54,7 @@ struct pingroup {
  * @drv_data: driver-defined per-pin data. pinctrl core does not touch this
  */
 struct pinctrl_pin_desc {
-	unsigned number;
+	unsigned int number;
 	const char *name;
 	void *drv_data;
 };
@@ -82,7 +82,7 @@ struct pinctrl_gpio_range {
 	unsigned int base;
 	unsigned int pin_base;
 	unsigned int npins;
-	unsigned const *pins;
+	unsigned int const *pins;
 	struct gpio_chip *gc;
 };
 
@@ -108,18 +108,18 @@ struct pinctrl_gpio_range {
 struct pinctrl_ops {
 	int (*get_groups_count) (struct pinctrl_dev *pctldev);
 	const char *(*get_group_name) (struct pinctrl_dev *pctldev,
-				       unsigned selector);
+				       unsigned int selector);
 	int (*get_group_pins) (struct pinctrl_dev *pctldev,
-			       unsigned selector,
-			       const unsigned **pins,
-			       unsigned *num_pins);
+			       unsigned int selector,
+			       const unsigned int **pins,
+			       unsigned int *num_pins);
 	void (*pin_dbg_show) (struct pinctrl_dev *pctldev, struct seq_file *s,
-			  unsigned offset);
+			      unsigned int offset);
 	int (*dt_node_to_map) (struct pinctrl_dev *pctldev,
 			       struct device_node *np_config,
-			       struct pinctrl_map **map, unsigned *num_maps);
+			       struct pinctrl_map **map, unsigned int *num_maps);
 	void (*dt_free_map) (struct pinctrl_dev *pctldev,
-			     struct pinctrl_map *map, unsigned num_maps);
+			     struct pinctrl_map *map, unsigned int num_maps);
 };
 
 /**
@@ -193,7 +193,7 @@ extern void pinctrl_add_gpio_range(struct pinctrl_dev *pctldev,
 				struct pinctrl_gpio_range *range);
 extern void pinctrl_add_gpio_ranges(struct pinctrl_dev *pctldev,
 				struct pinctrl_gpio_range *ranges,
-				unsigned nranges);
+				unsigned int nranges);
 extern void pinctrl_remove_gpio_range(struct pinctrl_dev *pctldev,
 				struct pinctrl_gpio_range *range);
 
@@ -203,8 +203,8 @@ extern struct pinctrl_gpio_range *
 pinctrl_find_gpio_range_from_pin(struct pinctrl_dev *pctldev,
 				 unsigned int pin);
 extern int pinctrl_get_group_pins(struct pinctrl_dev *pctldev,
-				const char *pin_group, const unsigned **pins,
-				unsigned *num_pins);
+				  const char *pin_group, const unsigned int **pins,
+				  unsigned int *num_pins);
 
 /**
  * struct pinfunction - Description about a function
diff --git a/include/linux/pinctrl/pinmux.h b/include/linux/pinctrl/pinmux.h
index a7e370965c53..d6f7b58d6ad0 100644
--- a/include/linux/pinctrl/pinmux.h
+++ b/include/linux/pinctrl/pinmux.h
@@ -57,26 +57,26 @@ struct pinctrl_gpio_range;
  *	the pin request.
  */
 struct pinmux_ops {
-	int (*request) (struct pinctrl_dev *pctldev, unsigned offset);
-	int (*free) (struct pinctrl_dev *pctldev, unsigned offset);
+	int (*request) (struct pinctrl_dev *pctldev, unsigned int offset);
+	int (*free) (struct pinctrl_dev *pctldev, unsigned int offset);
 	int (*get_functions_count) (struct pinctrl_dev *pctldev);
 	const char *(*get_function_name) (struct pinctrl_dev *pctldev,
-					  unsigned selector);
+					  unsigned int selector);
 	int (*get_function_groups) (struct pinctrl_dev *pctldev,
-				  unsigned selector,
-				  const char * const **groups,
-				  unsigned *num_groups);
-	int (*set_mux) (struct pinctrl_dev *pctldev, unsigned func_selector,
-			unsigned group_selector);
+				    unsigned int selector,
+				    const char * const **groups,
+				    unsigned int *num_groups);
+	int (*set_mux) (struct pinctrl_dev *pctldev, unsigned int func_selector,
+			unsigned int group_selector);
 	int (*gpio_request_enable) (struct pinctrl_dev *pctldev,
 				    struct pinctrl_gpio_range *range,
-				    unsigned offset);
+				    unsigned int offset);
 	void (*gpio_disable_free) (struct pinctrl_dev *pctldev,
 				   struct pinctrl_gpio_range *range,
-				   unsigned offset);
+				   unsigned int offset);
 	int (*gpio_set_direction) (struct pinctrl_dev *pctldev,
 				   struct pinctrl_gpio_range *range,
-				   unsigned offset,
+				   unsigned int offset,
 				   bool input);
 	bool strict;
 };
diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h
index 79594aeb160d..2f1b952d596a 100644
--- a/include/linux/pktcdvd.h
+++ b/include/linux/pktcdvd.h
@@ -154,9 +154,9 @@ struct packet_stacked_data
 
 struct pktcdvd_device
 {
-	struct bdev_handle	*bdev_handle;	/* dev attached */
+	struct file		*bdev_file;	/* dev attached */
 	/* handle acquired for bdev during pkt_open_dev() */
-	struct bdev_handle	*open_bdev_handle;
+	struct file		*f_open_bdev;
 	dev_t			pkt_dev;	/* our dev */
 	struct packet_settings	settings;
 	struct packet_stats	stats;
diff --git a/include/linux/platform_data/i2c-mux-reg.h b/include/linux/platform_data/i2c-mux-reg.h
index 2543c2a1c9ae..e2e895768311 100644
--- a/include/linux/platform_data/i2c-mux-reg.h
+++ b/include/linux/platform_data/i2c-mux-reg.h
@@ -17,7 +17,6 @@
  * @n_values: Number of multiplexer channels
  * @little_endian: Indicating if the register is in little endian
  * @write_only: Reading the register is not allowed by hardware
- * @classes: Optional I2C auto-detection classes
  * @idle: Value to write to mux when idle
  * @idle_in_use: indicate if idle value is in use
  * @reg: Virtual address of the register to switch channel
@@ -30,7 +29,6 @@ struct i2c_mux_reg_platform_data {
 	int n_values;
 	bool little_endian;
 	bool write_only;
-	const unsigned int *classes;
 	u32 idle;
 	bool idle_in_use;
 	void __iomem *reg;
diff --git a/include/linux/platform_data/keypad-omap.h b/include/linux/platform_data/keypad-omap.h
index 3e7c64c854f4..f3f1311cdf3a 100644
--- a/include/linux/platform_data/keypad-omap.h
+++ b/include/linux/platform_data/keypad-omap.h
@@ -19,9 +19,6 @@ struct omap_kp_platform_data {
 	bool rep;
 	unsigned long delay;
 	bool dbounce;
-	/* specific to OMAP242x*/
-	unsigned int *row_gpios;
-	unsigned int *col_gpios;
 };
 
 /* Group (0..3) -- when multiple keys are pressed, only the
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 92a4f69de0e8..a2f3e53a8196 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -681,6 +681,7 @@ struct dev_pm_info {
 	bool			wakeup_path:1;
 	bool			syscore:1;
 	bool			no_pm_callbacks:1;	/* Owned by the PM core */
+	bool			async_in_progress:1;	/* Owned by the PM core */
 	unsigned int		must_resume:1;	/* Owned by the PM core */
 	unsigned int		may_skip_resume:1;	/* Set by subsystems */
 #else
diff --git a/include/linux/pm_clock.h b/include/linux/pm_clock.h
index ada3a0ab10bf..68669ce18720 100644
--- a/include/linux/pm_clock.h
+++ b/include/linux/pm_clock.h
@@ -91,10 +91,10 @@ static inline int devm_pm_clk_create(struct device *dev)
 #endif
 
 #ifdef CONFIG_HAVE_CLK
-extern void pm_clk_add_notifier(struct bus_type *bus,
+extern void pm_clk_add_notifier(const struct bus_type *bus,
 					struct pm_clk_notifier_block *clknb);
 #else
-static inline void pm_clk_add_notifier(struct bus_type *bus,
+static inline void pm_clk_add_notifier(const struct bus_type *bus,
 					struct pm_clk_notifier_block *clknb)
 {
 }
diff --git a/include/linux/pnp.h b/include/linux/pnp.h
index 267fb8a4fb6e..ddbe7c3ca4ce 100644
--- a/include/linux/pnp.h
+++ b/include/linux/pnp.h
@@ -435,7 +435,7 @@ struct pnp_protocol {
 #define protocol_for_each_dev(protocol, dev)	\
 	list_for_each_entry(dev, &(protocol)->devices, protocol_list)
 
-extern struct bus_type pnp_bus_type;
+extern const struct bus_type pnp_bus_type;
 
 #if defined(CONFIG_PNP)
 
diff --git a/include/linux/poison.h b/include/linux/poison.h
index 27a7dad17eef..1f0ee2459f2a 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -92,4 +92,7 @@
 /********** VFS **********/
 #define VFS_PTR_POISON ((void *)(0xF5 + POISON_POINTER_DELTA))
 
+/********** lib/stackdepot.c **********/
+#define STACK_DEPOT_POISON ((void *)(0xD390 + POISON_POINTER_DELTA))
+
 #endif
diff --git a/include/linux/poll.h b/include/linux/poll.h
index a9e0e1c2d1f2..d1ea4f3714a8 100644
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -14,11 +14,7 @@
 
 /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating
    additional memory. */
-#ifdef __clang__
-#define MAX_STACK_ALLOC 768
-#else
 #define MAX_STACK_ALLOC 832
-#endif
 #define FRONTEND_STACK_ALLOC	256
 #define SELECT_STACK_ALLOC	FRONTEND_STACK_ALLOC
 #define POLL_STACK_ALLOC	FRONTEND_STACK_ALLOC
diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h
index 7c8d65414a70..7d8025fb74b7 100644
--- a/include/linux/power/bq27xxx_battery.h
+++ b/include/linux/power/bq27xxx_battery.h
@@ -83,5 +83,6 @@ struct bq27xxx_device_info {
 void bq27xxx_battery_update(struct bq27xxx_device_info *di);
 int bq27xxx_battery_setup(struct bq27xxx_device_info *di);
 void bq27xxx_battery_teardown(struct bq27xxx_device_info *di);
+extern const struct dev_pm_ops bq27xxx_battery_battery_pm_ops;
 
 #endif
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index de407e7c3b55..0b2a89854440 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -65,6 +65,7 @@ struct proc_fs_info {
 	kgid_t pid_gid;
 	enum proc_hidepid hide_pid;
 	enum proc_pidonly pidonly;
+	struct rcu_head rcu;
 };
 
 static inline struct proc_fs_info *proc_sb_info(struct super_block *sb)
diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h
index 49539bc416ce..5ea470eb4d76 100644
--- a/include/linux/proc_ns.h
+++ b/include/linux/proc_ns.h
@@ -66,7 +66,7 @@ static inline void proc_free_inum(unsigned int inum) {}
 
 static inline int ns_alloc_inum(struct ns_common *ns)
 {
-	atomic_long_set(&ns->stashed, 0);
+	WRITE_ONCE(ns->stashed, NULL);
 	return proc_alloc_inum(&ns->inum);
 }
 
diff --git a/include/linux/property.h b/include/linux/property.h
index 60e35bd97398..e6516d0b7d52 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -124,6 +124,18 @@ static inline bool device_is_compatible(const struct device *dev, const char *co
 	return fwnode_device_is_compatible(dev_fwnode(dev), compat);
 }
 
+int fwnode_property_match_property_string(const struct fwnode_handle *fwnode,
+					  const char *propname,
+					  const char * const *array, size_t n);
+
+static inline
+int device_property_match_property_string(const struct device *dev,
+					  const char *propname,
+					  const char * const *array, size_t n)
+{
+	return fwnode_property_match_property_string(dev_fwnode(dev), propname, array, n);
+}
+
 int fwnode_property_get_reference_args(const struct fwnode_handle *fwnode,
 				       const char *prop, const char *nargs_prop,
 				       unsigned int nargs, unsigned int index,
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index eaaef3ffec22..90507d4afcd6 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -393,6 +393,10 @@ static inline void user_single_step_report(struct pt_regs *regs)
 #define current_user_stack_pointer() user_stack_pointer(current_pt_regs())
 #endif
 
+#ifndef exception_ip
+#define exception_ip(x) instruction_pointer(x)
+#endif
+
 extern int task_current_syscall(struct task_struct *target, struct syscall_info *info);
 
 extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact);
diff --git a/include/linux/rcu_sync.h b/include/linux/rcu_sync.h
index 0027d4c8087c..3860dbb9107a 100644
--- a/include/linux/rcu_sync.h
+++ b/include/linux/rcu_sync.h
@@ -37,7 +37,6 @@ static inline bool rcu_sync_is_idle(struct rcu_sync *rsp)
 }
 
 extern void rcu_sync_init(struct rcu_sync *);
-extern void rcu_sync_enter_start(struct rcu_sync *);
 extern void rcu_sync_enter(struct rcu_sync *);
 extern void rcu_sync_exit(struct rcu_sync *);
 extern void rcu_sync_dtor(struct rcu_sync *);
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 0746b1b0b663..16f519914415 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -184,9 +184,9 @@ void rcu_tasks_trace_qs_blkd(struct task_struct *t);
 	do {									\
 		int ___rttq_nesting = READ_ONCE((t)->trc_reader_nesting);	\
 										\
-		if (likely(!READ_ONCE((t)->trc_reader_special.b.need_qs)) &&	\
+		if (unlikely(READ_ONCE((t)->trc_reader_special.b.need_qs) == TRC_NEED_QS) &&	\
 		    likely(!___rttq_nesting)) {					\
-			rcu_trc_cmpxchg_need_qs((t), 0,	TRC_NEED_QS_CHECKED);	\
+			rcu_trc_cmpxchg_need_qs((t), TRC_NEED_QS, TRC_NEED_QS_CHECKED);	\
 		} else if (___rttq_nesting && ___rttq_nesting != INT_MIN &&	\
 			   !READ_ONCE((t)->trc_reader_special.b.blocked)) {	\
 			rcu_tasks_trace_qs_blkd(t);				\
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 782e14f62201..fa802db216f9 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -141,6 +141,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter);
 bool ring_buffer_iter_dropped(struct ring_buffer_iter *iter);
 
 unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu);
+unsigned long ring_buffer_max_event_size(struct trace_buffer *buffer);
 
 void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu);
 void ring_buffer_reset_online_cpus(struct trace_buffer *buffer);
@@ -191,15 +192,24 @@ bool ring_buffer_time_stamp_abs(struct trace_buffer *buffer);
 size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu);
 size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu);
 
-void *ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu);
-void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data);
-int ring_buffer_read_page(struct trace_buffer *buffer, void **data_page,
+struct buffer_data_read_page;
+struct buffer_data_read_page *
+ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu);
+void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu,
+				struct buffer_data_read_page *page);
+int ring_buffer_read_page(struct trace_buffer *buffer,
+			  struct buffer_data_read_page *data_page,
 			  size_t len, int cpu, int full);
+void *ring_buffer_read_page_data(struct buffer_data_read_page *page);
 
 struct trace_seq;
 
 int ring_buffer_print_entry_header(struct trace_seq *s);
-int ring_buffer_print_page_header(struct trace_seq *s);
+int ring_buffer_print_page_header(struct trace_buffer *buffer, struct trace_seq *s);
+
+int ring_buffer_subbuf_order_get(struct trace_buffer *buffer);
+int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order);
+int ring_buffer_subbuf_size_get(struct trace_buffer *buffer);
 
 enum ring_buffer_flags {
 	RB_FL_OVERWRITE		= 1 << 0,
diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h
index 534038d962e4..4612ef09a0c7 100644
--- a/include/linux/rtsx_pci.h
+++ b/include/linux/rtsx_pci.h
@@ -60,6 +60,7 @@
 #define   SD_EXIST			(1 << 16)
 #define   DELINK_INT			GPIO0_INT
 #define   MS_OC_INT			(1 << 23)
+#define   SD_OVP_INT		(1 << 23)
 #define   SD_OC_INT			(1 << 22)
 
 #define CARD_INT		(XD_INT | MS_INT | SD_INT)
@@ -80,6 +81,7 @@
 #define   OC_INT_EN			(1 << 23)
 #define   DELINK_INT_EN			GPIO0_INT_EN
 #define   MS_OC_INT_EN			(1 << 23)
+#define   SD_OVP_INT_EN			(1 << 23)
 #define   SD_OC_INT_EN			(1 << 22)
 
 #define RTSX_DUM_REG			0x1C
@@ -583,6 +585,7 @@
 #define   OBFF_DISABLE			0x00
 
 #define CDRESUMECTL			0xFE52
+#define CDGW				0xFE53
 #define WAKE_SEL_CTL			0xFE54
 #define PCLK_CTL			0xFE55
 #define   PCLK_MODE_SEL			0x20
@@ -764,6 +767,9 @@
 #define   SD_VIO_LDO_1V8		0x40
 #define   SD_VIO_LDO_3V3		0x70
 
+#define RTS5264_AUTOLOAD_CFG2		0xFF7D
+#define RTS5264_CHIP_RST_N_SEL		(1 << 6)
+
 #define RTS5260_AUTOLOAD_CFG4		0xFF7F
 #define   RTS5260_MIMO_DISABLE		0x8A
 /*RTS5261*/
@@ -1261,6 +1267,7 @@ struct rtsx_pcr {
 	u8				dma_error_count;
 	u8			ocp_stat;
 	u8			ocp_stat2;
+	u8			ovp_stat;
 	u8			rtd3_en;
 };
 
@@ -1271,6 +1278,7 @@ struct rtsx_pcr {
 #define PID_5260	0x5260
 #define PID_5261	0x5261
 #define PID_5228	0x5228
+#define PID_5264	0x5264
 
 #define CHK_PCI_PID(pcr, pid)		((pcr)->pci->device == (pid))
 #define PCI_VID(pcr)			((pcr)->pci->vendor)
diff --git a/include/linux/rw_hint.h b/include/linux/rw_hint.h
new file mode 100644
index 000000000000..309ca72f2dfb
--- /dev/null
+++ b/include/linux/rw_hint.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_RW_HINT_H
+#define _LINUX_RW_HINT_H
+
+#include <linux/build_bug.h>
+#include <linux/compiler_attributes.h>
+#include <uapi/linux/fcntl.h>
+
+/* Block storage write lifetime hint values. */
+enum rw_hint {
+	WRITE_LIFE_NOT_SET	= RWH_WRITE_LIFE_NOT_SET,
+	WRITE_LIFE_NONE		= RWH_WRITE_LIFE_NONE,
+	WRITE_LIFE_SHORT	= RWH_WRITE_LIFE_SHORT,
+	WRITE_LIFE_MEDIUM	= RWH_WRITE_LIFE_MEDIUM,
+	WRITE_LIFE_LONG		= RWH_WRITE_LIFE_LONG,
+	WRITE_LIFE_EXTREME	= RWH_WRITE_LIFE_EXTREME,
+} __packed;
+
+/* Sparse ignores __packed annotations on enums, hence the #ifndef below. */
+#ifndef __CHECKER__
+static_assert(sizeof(enum rw_hint) == 1);
+#endif
+
+#endif /* _LINUX_RW_HINT_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9a66147915b2..17cb0761ff65 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -858,6 +858,8 @@ struct task_struct {
 	u8				rcu_tasks_idx;
 	int				rcu_tasks_idle_cpu;
 	struct list_head		rcu_tasks_holdout_list;
+	int				rcu_tasks_exit_cpu;
+	struct list_head		rcu_tasks_exit_list;
 #endif /* #ifdef CONFIG_TASKS_RCU */
 
 #ifdef CONFIG_TASKS_TRACE_RCU
@@ -920,7 +922,7 @@ struct task_struct {
 	unsigned			sched_rt_mutex:1;
 #endif
 
-	/* Bit to tell LSMs we're in execve(): */
+	/* Bit to tell TOMOYO we're in execve(): */
 	unsigned			in_execve:1;
 	unsigned			in_iowait:1;
 #ifndef TIF_RESTORE_SIGMASK
@@ -957,7 +959,7 @@ struct task_struct {
 	/* Recursion prevention for eventfd_signal() */
 	unsigned			in_eventfd:1;
 #endif
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_ARCH_HAS_CPU_PASID
 	unsigned			pasid_activated:1;
 #endif
 #ifdef	CONFIG_CPU_SUP_INTEL
@@ -1642,7 +1644,7 @@ extern struct pid *cad_pid;
 #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
 #define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
 #define PF_MEMALLOC_PIN		0x10000000	/* Allocation context constrained to zones which allow long term pinning. */
-#define PF__HOLE__20000000	0x20000000
+#define PF_BLOCK_TS		0x20000000	/* plug has ts that needs updating */
 #define PF__HOLE__40000000	0x40000000
 #define PF_SUSPEND_TASK		0x80000000      /* This thread called freeze_processes() and should not be frozen */
 
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 4b7664c56208..0a0e23c45406 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -735,8 +735,6 @@ static inline int thread_group_empty(struct task_struct *p)
 #define delay_group_leader(p) \
 		(thread_group_leader(p) && !thread_group_empty(p))
 
-extern bool thread_group_exited(struct pid *pid);
-
 extern struct sighand_struct *__lock_task_sighand(struct task_struct *task,
 							unsigned long *flags);
 
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index a6e04b4a21d7..11e0e00e0bb9 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -176,6 +176,7 @@ extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
 void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
 
+bool cpus_equal_capacity(int this_cpu, int that_cpu);
 bool cpus_share_cache(int this_cpu, int that_cpu);
 bool cpus_share_resources(int this_cpu, int that_cpu);
 
@@ -226,6 +227,11 @@ partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 {
 }
 
+static inline bool cpus_equal_capacity(int this_cpu, int that_cpu)
+{
+	return true;
+}
+
 static inline bool cpus_share_cache(int this_cpu, int that_cpu)
 {
 	return true;
diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h
index 5fb1f12c33f9..fe41da005970 100644
--- a/include/linux/seq_buf.h
+++ b/include/linux/seq_buf.h
@@ -2,7 +2,10 @@
 #ifndef _LINUX_SEQ_BUF_H
 #define _LINUX_SEQ_BUF_H
 
-#include <linux/fs.h>
+#include <linux/bug.h>
+#include <linux/minmax.h>
+#include <linux/seq_file.h>
+#include <linux/types.h>
 
 /*
  * Trace sequences are used to allow a function to call several other functions
@@ -10,7 +13,7 @@
  */
 
 /**
- * seq_buf - seq buffer structure
+ * struct seq_buf - seq buffer structure
  * @buffer:	pointer to the buffer
  * @size:	size of the buffer
  * @len:	the amount of data inside the buffer
@@ -22,9 +25,8 @@ struct seq_buf {
 };
 
 #define DECLARE_SEQ_BUF(NAME, SIZE)			\
-	char __ ## NAME ## _buffer[SIZE] = "";		\
 	struct seq_buf NAME = {				\
-		.buffer = &__ ## NAME ## _buffer,	\
+		.buffer = (char[SIZE]) { 0 },		\
 		.size = SIZE,				\
 	}
 
@@ -78,10 +80,10 @@ static inline unsigned int seq_buf_used(struct seq_buf *s)
 }
 
 /**
- * seq_buf_str - get %NUL-terminated C string from seq_buf
+ * seq_buf_str - get NUL-terminated C string from seq_buf
  * @s: the seq_buf handle
  *
- * This makes sure that the buffer in @s is nul terminated and
+ * This makes sure that the buffer in @s is NUL-terminated and
  * safe to read as a string.
  *
  * Note, if this is called when the buffer has overflowed, then
@@ -91,7 +93,7 @@ static inline unsigned int seq_buf_used(struct seq_buf *s)
  * After this function is called, s->buffer is safe to use
  * in string operations.
  *
- * Returns @s->buf after making sure it is terminated.
+ * Returns: @s->buf after making sure it is terminated.
  */
 static inline const char *seq_buf_str(struct seq_buf *s)
 {
@@ -111,7 +113,7 @@ static inline const char *seq_buf_str(struct seq_buf *s)
  * @s: the seq_buf handle
  * @bufp: the beginning of the buffer is stored here
  *
- * Return the number of bytes available in the buffer, or zero if
+ * Returns: the number of bytes available in the buffer, or zero if
  * there's no space.
  */
 static inline size_t seq_buf_get_buf(struct seq_buf *s, char **bufp)
@@ -133,7 +135,7 @@ static inline size_t seq_buf_get_buf(struct seq_buf *s, char **bufp)
  * @num: the number of bytes to commit
  *
  * Commit @num bytes of data written to a buffer previously acquired
- * by seq_buf_get.  To signal an error condition, or that the data
+ * by seq_buf_get_buf(). To signal an error condition, or that the data
  * didn't fit in the available space, pass a negative @num value.
  */
 static inline void seq_buf_commit(struct seq_buf *s, int num)
diff --git a/include/linux/serdev.h b/include/linux/serdev.h
index f5f97fa25e8a..3fab88ba265e 100644
--- a/include/linux/serdev.h
+++ b/include/linux/serdev.h
@@ -27,7 +27,7 @@ struct serdev_device;
  *			not sleep.
  */
 struct serdev_device_ops {
-	int (*receive_buf)(struct serdev_device *, const unsigned char *, size_t);
+	ssize_t (*receive_buf)(struct serdev_device *, const u8 *, size_t);
 	void (*write_wakeup)(struct serdev_device *);
 };
 
@@ -82,7 +82,7 @@ enum serdev_parity {
  * serdev controller structures
  */
 struct serdev_controller_ops {
-	int (*write_buf)(struct serdev_controller *, const unsigned char *, size_t);
+	ssize_t (*write_buf)(struct serdev_controller *, const u8 *, size_t);
 	void (*write_flush)(struct serdev_controller *);
 	int (*write_room)(struct serdev_controller *);
 	int (*open)(struct serdev_controller *);
@@ -99,12 +99,14 @@ struct serdev_controller_ops {
 /**
  * struct serdev_controller - interface to the serdev controller
  * @dev:	Driver model representation of the device.
+ * @host:	Serial port hardware controller device
  * @nr:		number identifier for this controller/bus.
  * @serdev:	Pointer to slave device for this controller.
  * @ops:	Controller operations.
  */
 struct serdev_controller {
 	struct device		dev;
+	struct device		*host;
 	unsigned int		nr;
 	struct serdev_device	*serdev;
 	const struct serdev_controller_ops *ops;
@@ -167,7 +169,9 @@ struct serdev_device *serdev_device_alloc(struct serdev_controller *);
 int serdev_device_add(struct serdev_device *);
 void serdev_device_remove(struct serdev_device *);
 
-struct serdev_controller *serdev_controller_alloc(struct device *, size_t);
+struct serdev_controller *serdev_controller_alloc(struct device *host,
+						  struct device *parent,
+						  size_t size);
 int serdev_controller_add(struct serdev_controller *);
 void serdev_controller_remove(struct serdev_controller *);
 
@@ -181,9 +185,9 @@ static inline void serdev_controller_write_wakeup(struct serdev_controller *ctrl
 	serdev->ops->write_wakeup(serdev);
 }
 
-static inline int serdev_controller_receive_buf(struct serdev_controller *ctrl,
-					      const unsigned char *data,
-					      size_t count)
+static inline ssize_t serdev_controller_receive_buf(struct serdev_controller *ctrl,
+						    const u8 *data,
+						    size_t count)
 {
 	struct serdev_device *serdev = ctrl->serdev;
 
@@ -200,13 +204,13 @@ void serdev_device_close(struct serdev_device *);
 int devm_serdev_device_open(struct device *, struct serdev_device *);
 unsigned int serdev_device_set_baudrate(struct serdev_device *, unsigned int);
 void serdev_device_set_flow_control(struct serdev_device *, bool);
-int serdev_device_write_buf(struct serdev_device *, const unsigned char *, size_t);
+int serdev_device_write_buf(struct serdev_device *, const u8 *, size_t);
 void serdev_device_wait_until_sent(struct serdev_device *, long);
 int serdev_device_get_tiocm(struct serdev_device *);
 int serdev_device_set_tiocm(struct serdev_device *, int, int);
 int serdev_device_break_ctl(struct serdev_device *serdev, int break_state);
 void serdev_device_write_wakeup(struct serdev_device *);
-int serdev_device_write(struct serdev_device *, const unsigned char *, size_t, long);
+ssize_t serdev_device_write(struct serdev_device *, const u8 *, size_t, long);
 void serdev_device_write_flush(struct serdev_device *);
 int serdev_device_write_room(struct serdev_device *);
 
@@ -244,7 +248,7 @@ static inline unsigned int serdev_device_set_baudrate(struct serdev_device *sdev
 }
 static inline void serdev_device_set_flow_control(struct serdev_device *sdev, bool enable) {}
 static inline int serdev_device_write_buf(struct serdev_device *serdev,
-					  const unsigned char *buf,
+					  const u8 *buf,
 					  size_t count)
 {
 	return -ENODEV;
@@ -262,8 +266,9 @@ static inline int serdev_device_break_ctl(struct serdev_device *serdev, int brea
 {
 	return -EOPNOTSUPP;
 }
-static inline int serdev_device_write(struct serdev_device *sdev, const unsigned char *buf,
-				      size_t count, unsigned long timeout)
+static inline ssize_t serdev_device_write(struct serdev_device *sdev,
+					  const u8 *buf, size_t count,
+					  unsigned long timeout)
 {
 	return -ENODEV;
 }
@@ -311,11 +316,13 @@ struct tty_driver;
 
 #ifdef CONFIG_SERIAL_DEV_CTRL_TTYPORT
 struct device *serdev_tty_port_register(struct tty_port *port,
+					struct device *host,
 					struct device *parent,
 					struct tty_driver *drv, int idx);
 int serdev_tty_port_unregister(struct tty_port *port);
 #else
 static inline struct device *serdev_tty_port_register(struct tty_port *port,
+					   struct device *host,
 					   struct device *parent,
 					   struct tty_driver *drv, int idx)
 {
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 89f7b6c63598..55b1f3ba48ac 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -748,8 +748,17 @@ struct uart_driver {
 
 void uart_write_wakeup(struct uart_port *port);
 
-#define __uart_port_tx(uport, ch, tx_ready, put_char, tx_done, for_test,      \
-		for_post)						      \
+/**
+ * enum UART_TX_FLAGS -- flags for uart_port_tx_flags()
+ *
+ * @UART_TX_NOSTOP: don't call port->ops->stop_tx() on empty buffer
+ */
+enum UART_TX_FLAGS {
+	UART_TX_NOSTOP = BIT(0),
+};
+
+#define __uart_port_tx(uport, ch, flags, tx_ready, put_char, tx_done,	      \
+		       for_test, for_post)				      \
 ({									      \
 	struct uart_port *__port = (uport);				      \
 	struct circ_buf *xmit = &__port->state->xmit;			      \
@@ -777,7 +786,7 @@ void uart_write_wakeup(struct uart_port *port);
 	if (pending < WAKEUP_CHARS) {					      \
 		uart_write_wakeup(__port);				      \
 									      \
-		if (pending == 0)					      \
+		if (!((flags) & UART_TX_NOSTOP) && pending == 0)	      \
 			__port->ops->stop_tx(__port);			      \
 	}								      \
 									      \
@@ -812,7 +821,7 @@ void uart_write_wakeup(struct uart_port *port);
  */
 #define uart_port_tx_limited(port, ch, count, tx_ready, put_char, tx_done) ({ \
 	unsigned int __count = (count);					      \
-	__uart_port_tx(port, ch, tx_ready, put_char, tx_done, __count,	      \
+	__uart_port_tx(port, ch, 0, tx_ready, put_char, tx_done, __count,     \
 			__count--);					      \
 })
 
@@ -826,8 +835,21 @@ void uart_write_wakeup(struct uart_port *port);
  * See uart_port_tx_limited() for more details.
  */
 #define uart_port_tx(port, ch, tx_ready, put_char)			\
-	__uart_port_tx(port, ch, tx_ready, put_char, ({}), true, ({}))
+	__uart_port_tx(port, ch, 0, tx_ready, put_char, ({}), true, ({}))
+
 
+/**
+ * uart_port_tx_flags -- transmit helper for uart_port with flags
+ * @port: uart port
+ * @ch: variable to store a character to be written to the HW
+ * @flags: %UART_TX_NOSTOP or similar
+ * @tx_ready: can HW accept more data function
+ * @put_char: function to write a character
+ *
+ * See uart_port_tx_limited() for more details.
+ */
+#define uart_port_tx_flags(port, ch, flags, tx_ready, put_char)		\
+	__uart_port_tx(port, ch, flags, tx_ready, put_char, ({}), true, ({}))
 /*
  * Baud rate helpers.
  */
@@ -852,9 +874,9 @@ static inline unsigned long uart_fifo_timeout(struct uart_port *port)
 }
 
 /* Base timer interval for polling */
-static inline int uart_poll_timeout(struct uart_port *port)
+static inline unsigned long uart_poll_timeout(struct uart_port *port)
 {
-	int timeout = uart_fifo_timeout(port);
+	unsigned long timeout = uart_fifo_timeout(port);
 
 	return timeout > 6 ? (timeout / 2 - 2) : 1;
 }
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index a5ae952454c8..2dde34c29203 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -295,7 +295,7 @@ struct nf_bridge_info {
 	u8			bridged_dnat:1;
 	u8			sabotage_in_done:1;
 	__u16			frag_max_size;
-	struct net_device	*physindev;
+	int			physinif;
 
 	/* always valid & non-NULL from FORWARD on, for physdev match */
 	struct net_device	*physoutdev;
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 888a4b217829..e65ec3fd2799 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -505,12 +505,6 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock)
 	return !!psock->saved_data_ready;
 }
 
-static inline bool sk_is_udp(const struct sock *sk)
-{
-	return sk->sk_type == SOCK_DGRAM &&
-	       sk->sk_protocol == IPPROTO_UDP;
-}
-
 #if IS_ENABLED(CONFIG_NET_SOCK_MSG)
 
 #define BPF_F_STRPARSER	(1UL << 1)
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 4f3d14bb1538..66f814b63a43 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -886,7 +886,8 @@ struct sdw_master_ops {
  * struct sdw_bus - SoundWire bus
  * @dev: Shortcut to &bus->md->dev to avoid changing the entire code.
  * @md: Master device
- * @link_id: Link id number, can be 0 to N, unique for each Master
+ * @controller_id: system-unique controller ID. If set to -1, the bus @id will be used.
+ * @link_id: Link id number, can be 0 to N, unique for each Controller
  * @id: bus system-wide unique id
  * @slaves: list of Slaves on this bus
  * @assigned: Bitmap for Slave device numbers.
@@ -918,6 +919,7 @@ struct sdw_master_ops {
 struct sdw_bus {
 	struct device *dev;
 	struct sdw_master_device *md;
+	int controller_id;
 	unsigned int link_id;
 	int id;
 	struct list_head slaves;
@@ -1040,7 +1042,7 @@ int sdw_compute_params(struct sdw_bus *bus);
 
 int sdw_stream_add_master(struct sdw_bus *bus,
 		struct sdw_stream_config *stream_config,
-		struct sdw_port_config *port_config,
+		const struct sdw_port_config *port_config,
 		unsigned int num_ports,
 		struct sdw_stream_runtime *stream);
 int sdw_stream_remove_master(struct sdw_bus *bus,
@@ -1062,7 +1064,7 @@ void sdw_extract_slave_id(struct sdw_bus *bus, u64 addr, struct sdw_slave_id *id
 
 int sdw_stream_add_slave(struct sdw_slave *slave,
 			 struct sdw_stream_config *stream_config,
-			 struct sdw_port_config *port_config,
+			 const struct sdw_port_config *port_config,
 			 unsigned int num_ports,
 			 struct sdw_stream_runtime *stream);
 int sdw_stream_remove_slave(struct sdw_slave *slave,
@@ -1084,7 +1086,7 @@ int sdw_update_no_pm(struct sdw_slave *slave, u32 addr, u8 mask, u8 val);
 
 static inline int sdw_stream_add_slave(struct sdw_slave *slave,
 				       struct sdw_stream_config *stream_config,
-				       struct sdw_port_config *port_config,
+				       const struct sdw_port_config *port_config,
 				       unsigned int num_ports,
 				       struct sdw_stream_runtime *stream)
 {
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 471fe2ff9066..600fbd5daf68 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -21,7 +21,7 @@
 #include <uapi/linux/spi/spi.h>
 
 /* Max no. of CS supported per spi device */
-#define SPI_CS_CNT_MAX 4
+#define SPI_CS_CNT_MAX 16
 
 struct dma_chan;
 struct software_node;
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index eaac8b0da25b..3fcd20de6ca8 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -449,6 +449,12 @@ static __always_inline int spin_is_contended(spinlock_t *lock)
 	return raw_spin_is_contended(&lock->rlock);
 }
 
+#define assert_spin_locked(lock)	assert_raw_spin_locked(&(lock)->rlock)
+
+#else  /* !CONFIG_PREEMPT_RT */
+# include <linux/spinlock_rt.h>
+#endif /* CONFIG_PREEMPT_RT */
+
 /*
  * Does a critical section need to be broken due to another
  * task waiting?: (technically does not depend on CONFIG_PREEMPTION,
@@ -480,12 +486,6 @@ static inline int rwlock_needbreak(rwlock_t *lock)
 #endif
 }
 
-#define assert_spin_locked(lock)	assert_raw_spin_locked(&(lock)->rlock)
-
-#else  /* !CONFIG_PREEMPT_RT */
-# include <linux/spinlock_rt.h>
-#endif /* CONFIG_PREEMPT_RT */
-
 /*
  * Pull the atomic_t declaration:
  * (asm-mips/atomic.h needs above definitions)
diff --git a/include/linux/spmi.h b/include/linux/spmi.h
index 2a4ce4144f9f..28e8c8bd3944 100644
--- a/include/linux/spmi.h
+++ b/include/linux/spmi.h
@@ -120,6 +120,9 @@ static inline void spmi_controller_put(struct spmi_controller *ctrl)
 int spmi_controller_add(struct spmi_controller *ctrl);
 void spmi_controller_remove(struct spmi_controller *ctrl);
 
+struct spmi_controller *devm_spmi_controller_alloc(struct device *parent, size_t size);
+int devm_spmi_controller_add(struct device *parent, struct spmi_controller *ctrl);
+
 /**
  * struct spmi_driver - SPMI slave device driver
  * @driver:	SPMI device drivers should initialize name and owner field of
diff --git a/include/linux/string.h b/include/linux/string.h
index ce137830a0b9..ab148d8dbfc1 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -66,9 +66,6 @@ extern char * strcpy(char *,const char *);
 #ifndef __HAVE_ARCH_STRNCPY
 extern char * strncpy(char *,const char *, __kernel_size_t);
 #endif
-#ifndef __HAVE_ARCH_STRLCPY
-size_t strlcpy(char *, const char *, size_t);
-#endif
 #ifndef __HAVE_ARCH_STRSCPY
 ssize_t strscpy(char *, const char *, size_t);
 #endif
diff --git a/include/linux/surface_aggregator/device.h b/include/linux/surface_aggregator/device.h
index 42b249b4c24b..8cd8c38cf3f3 100644
--- a/include/linux/surface_aggregator/device.h
+++ b/include/linux/surface_aggregator/device.h
@@ -193,7 +193,6 @@ struct ssam_device_driver {
 
 #ifdef CONFIG_SURFACE_AGGREGATOR_BUS
 
-extern struct bus_type ssam_bus_type;
 extern const struct device_type ssam_device_type;
 
 /**
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 4db00ddad261..378ab1cd23bd 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -298,7 +298,7 @@ struct swap_info_struct {
 	unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */
 	struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */
 	struct rb_root swap_extent_root;/* root of the swap extent rbtree */
-	struct bdev_handle *bdev_handle;/* open handle of the bdev */
+	struct file *bdev_file;		/* open handle of the bdev */
 	struct block_device *bdev;	/* swap device or bdev of swap file */
 	struct file *swap_file;		/* seldom referenced */
 	unsigned int old_block_size;	/* seldom referenced */
@@ -549,6 +549,11 @@ static inline int swap_duplicate(swp_entry_t swp)
 	return 0;
 }
 
+static inline int swapcache_prepare(swp_entry_t swp)
+{
+	return 0;
+}
+
 static inline void swap_free(swp_entry_t swp)
 {
 }
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 5c0dbef55792..77eb9b0e7685 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -128,6 +128,7 @@ struct mnt_id_req;
 #define __TYPE_IS_LL(t) (__TYPE_AS(t, 0LL) || __TYPE_AS(t, 0ULL))
 #define __SC_LONG(t, a) __typeof(__builtin_choose_expr(__TYPE_IS_LL(t), 0LL, 0L)) a
 #define __SC_CAST(t, a)	(__force t) a
+#define __SC_TYPE(t, a)	t
 #define __SC_ARGS(t, a)	a
 #define __SC_TEST(t, a) (void)BUILD_BUG_ON_ZERO(!__TYPE_IS_LL(t) && sizeof(t) > sizeof(long))
 
@@ -414,7 +415,7 @@ asmlinkage long sys_statmount(const struct mnt_id_req __user *req,
 			      struct statmount __user *buf, size_t bufsize,
 			      unsigned int flags);
 asmlinkage long sys_listmount(const struct mnt_id_req __user *req,
-			      u64 __user *buf, size_t bufsize,
+			      u64 __user *mnt_ids, size_t nr_mnt_ids,
 			      unsigned int flags);
 asmlinkage long sys_truncate(const char __user *path, long length);
 asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length);
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 89b290d8c8dc..a1c47a6d69b0 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -221,8 +221,10 @@ struct tcp_sock {
 	u32	lost_out;	/* Lost packets			*/
 	u32	sacked_out;	/* SACK'd packets			*/
 	u16	tcp_header_len;	/* Bytes of tcp header to send		*/
+	u8	scaling_ratio;	/* see tcp_win_from_space() */
 	u8	chrono_type : 2,	/* current chronograph type */
 		repair      : 1,
+		tcp_usec_ts : 1, /* TSval values in usec */
 		is_sack_reneg:1,    /* in recovery from loss with SACK reneg? */
 		is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */
 	__cacheline_group_end(tcp_sock_read_txrx);
@@ -352,7 +354,6 @@ struct tcp_sock {
 	u32	compressed_ack_rcv_nxt;
 	struct list_head tsq_node; /* anchor in tsq_tasklet.head list */
 
-	u8	scaling_ratio;	/* see tcp_win_from_space() */
 	/* Information of the most recently (s)acked skb */
 	struct tcp_rack {
 		u64 mstamp; /* (Re)sent time of the skb */
@@ -368,8 +369,7 @@ struct tcp_sock {
 	u8	compressed_ack;
 	u8	dup_ack_counter:2,
 		tlp_retrans:1,	/* TLP is a retransmission */
-		tcp_usec_ts:1, /* TSval values in usec */
-		unused:4;
+		unused:5;
 	u8	thin_lto    : 1,/* Use linear timeouts for thin streams */
 		recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */
 		fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index bf84595a4e86..b7a3deb372fd 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -32,6 +32,7 @@
 struct thermal_zone_device;
 struct thermal_cooling_device;
 struct thermal_instance;
+struct thermal_debugfs;
 struct thermal_attr;
 
 enum thermal_trend {
@@ -102,7 +103,7 @@ struct thermal_cooling_device_ops {
 
 struct thermal_cooling_device {
 	int id;
-	char *type;
+	const char *type;
 	unsigned long max_state;
 	struct device device;
 	struct device_node *np;
@@ -113,6 +114,9 @@ struct thermal_cooling_device {
 	struct mutex lock; /* protect thermal_instances list */
 	struct list_head thermal_instances;
 	struct list_head node;
+#ifdef CONFIG_THERMAL_DEBUGFS
+	struct thermal_debugfs *debugfs;
+#endif
 };
 
 /**
@@ -189,6 +193,9 @@ struct thermal_zone_device {
 	struct list_head node;
 	struct delayed_work poll_queue;
 	enum thermal_notify_event notify_event;
+#ifdef CONFIG_THERMAL_DEBUGFS
+	struct thermal_debugfs *debugfs;
+#endif
 	bool suspended;
 };
 
diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h
index 6151c210d987..2c835e5c41f6 100644
--- a/include/linux/thunderbolt.h
+++ b/include/linux/thunderbolt.h
@@ -86,7 +86,7 @@ struct tb {
 	unsigned long privdata[];
 };
 
-extern struct bus_type tb_bus_type;
+extern const struct bus_type tb_bus_type;
 extern struct device_type tb_service_type;
 extern struct device_type tb_xdomain_type;
 
diff --git a/include/linux/trace.h b/include/linux/trace.h
index 2a70a447184c..fdcd76b7be83 100644
--- a/include/linux/trace.h
+++ b/include/linux/trace.h
@@ -51,7 +51,7 @@ int trace_array_printk(struct trace_array *tr, unsigned long ip,
 		       const char *fmt, ...);
 int trace_array_init_printk(struct trace_array *tr);
 void trace_array_put(struct trace_array *tr);
-struct trace_array *trace_array_get_by_name(const char *name);
+struct trace_array *trace_array_get_by_name(const char *name, const char *systems);
 int trace_array_destroy(struct trace_array *tr);
 
 /* For osnoise tracer */
@@ -84,7 +84,7 @@ static inline int trace_array_init_printk(struct trace_array *tr)
 static inline void trace_array_put(struct trace_array *tr)
 {
 }
-static inline struct trace_array *trace_array_get_by_name(const char *name)
+static inline struct trace_array *trace_array_get_by_name(const char *name, const char *systems)
 {
 	return NULL;
 }
diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h
index 3691e0e76a1a..1ef95c0287f0 100644
--- a/include/linux/trace_seq.h
+++ b/include/linux/trace_seq.h
@@ -8,11 +8,20 @@
 
 /*
  * Trace sequences are used to allow a function to call several other functions
- * to create a string of data to use (up to a max of PAGE_SIZE).
+ * to create a string of data to use.
+ *
+ * Have the trace seq to be 8K which is typically PAGE_SIZE * 2 on
+ * most architectures. The TRACE_SEQ_BUFFER_SIZE (which is
+ * TRACE_SEQ_SIZE minus the other fields of trace_seq), is the
+ * max size the output of a trace event may be.
  */
 
+#define TRACE_SEQ_SIZE		8192
+#define TRACE_SEQ_BUFFER_SIZE	(TRACE_SEQ_SIZE - \
+	(sizeof(struct seq_buf) + sizeof(size_t) + sizeof(int)))
+
 struct trace_seq {
-	char			buffer[PAGE_SIZE];
+	char			buffer[TRACE_SEQ_BUFFER_SIZE];
 	struct seq_buf		seq;
 	size_t			readpos;
 	int			full;
@@ -21,7 +30,7 @@ struct trace_seq {
 static inline void
 trace_seq_init(struct trace_seq *s)
 {
-	seq_buf_init(&s->seq, s->buffer, PAGE_SIZE);
+	seq_buf_init(&s->seq, s->buffer, TRACE_SEQ_BUFFER_SIZE);
 	s->full = 0;
 	s->readpos = 0;
 }
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 4b6340ac2af2..8c76fd97d4ad 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -242,7 +242,7 @@ struct tty_struct {
 	void *driver_data;
 	spinlock_t files_lock;
 	int write_cnt;
-	unsigned char *write_buf;
+	u8 *write_buf;
 
 	struct list_head tty_files;
 
@@ -393,8 +393,10 @@ extern const struct class tty_class;
  * tty_kref_get - get a tty reference
  * @tty: tty device
  *
- * Returns: a new reference to a tty object. The caller must hold sufficient
- * locks/counts to ensure that their existing reference cannot go away
+ * Returns: a new reference to a tty object
+ *
+ * Locking: The caller must hold sufficient locks/counts to ensure that their
+ * existing reference cannot go away.
  */
 static inline struct tty_struct *tty_kref_get(struct tty_struct *tty)
 {
@@ -408,8 +410,8 @@ void tty_wait_until_sent(struct tty_struct *tty, long timeout);
 void stop_tty(struct tty_struct *tty);
 void start_tty(struct tty_struct *tty);
 void tty_write_message(struct tty_struct *tty, char *msg);
-int tty_send_xchar(struct tty_struct *tty, char ch);
-int tty_put_char(struct tty_struct *tty, unsigned char c);
+int tty_send_xchar(struct tty_struct *tty, u8 ch);
+int tty_put_char(struct tty_struct *tty, u8 c);
 unsigned int tty_chars_in_buffer(struct tty_struct *tty);
 unsigned int tty_write_room(struct tty_struct *tty);
 void tty_driver_flush_buffer(struct tty_struct *tty);
@@ -419,6 +421,7 @@ bool tty_unthrottle_safe(struct tty_struct *tty);
 int tty_do_resize(struct tty_struct *tty, struct winsize *ws);
 int tty_get_icount(struct tty_struct *tty,
 		struct serial_icounter_struct *icount);
+int tty_get_tiocm(struct tty_struct *tty);
 int is_current_pgrp_orphaned(void);
 void tty_hangup(struct tty_struct *tty);
 void tty_vhangup(struct tty_struct *tty);
@@ -436,12 +439,11 @@ void tty_encode_baud_rate(struct tty_struct *tty, speed_t ibaud,
  * tty_get_baud_rate - get tty bit rates
  * @tty: tty to query
  *
- * Returns: the baud rate as an integer for this terminal. The termios lock
- * must be held by the caller and the terminal bit flags may be updated.
+ * Returns: the baud rate as an integer for this terminal
  *
- * Locking: none
+ * Locking: The termios lock must be held by the caller.
  */
-static inline speed_t tty_get_baud_rate(struct tty_struct *tty)
+static inline speed_t tty_get_baud_rate(const struct tty_struct *tty)
 {
 	return tty_termios_baud_rate(&tty->termios);
 }
diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h
index 18beff0cec1a..7372124fbf90 100644
--- a/include/linux/tty_driver.h
+++ b/include/linux/tty_driver.h
@@ -72,8 +72,7 @@ struct serial_struct;
  *	is closed for the last time freeing up the resources. This is
  *	actually the second part of shutdown for routines that might sleep.
  *
- * @write: ``ssize_t ()(struct tty_struct *tty, const unsigned char *buf,
- *		    size_t count)``
+ * @write: ``ssize_t ()(struct tty_struct *tty, const u8 *buf, size_t count)``
  *
  *	This routine is called by the kernel to write a series (@count) of
  *	characters (@buf) to the @tty device. The characters may come from
@@ -85,7 +84,7 @@ struct serial_struct;
  *
  *	Optional: Required for writable devices. May not sleep.
  *
- * @put_char: ``int ()(struct tty_struct *tty, unsigned char ch)``
+ * @put_char: ``int ()(struct tty_struct *tty, u8 ch)``
  *
  *	This routine is called by the kernel to write a single character @ch to
  *	the @tty device. If the kernel uses this routine, it must call the
@@ -243,7 +242,7 @@ struct serial_struct;
  *	Optional: If not provided, the device is assumed to have no FIFO.
  *	Usually correct to invoke via tty_wait_until_sent(). May sleep.
  *
- * @send_xchar: ``void ()(struct tty_struct *tty, char ch)``
+ * @send_xchar: ``void ()(struct tty_struct *tty, u8 ch)``
  *
  *	This routine is used to send a high-priority XON/XOFF character (@ch)
  *	to the @tty device.
@@ -375,7 +374,7 @@ struct tty_operations {
 	void (*flush_buffer)(struct tty_struct *tty);
 	void (*set_ldisc)(struct tty_struct *tty);
 	void (*wait_until_sent)(struct tty_struct *tty, int timeout);
-	void (*send_xchar)(struct tty_struct *tty, char ch);
+	void (*send_xchar)(struct tty_struct *tty, u8 ch);
 	int (*tiocmget)(struct tty_struct *tty);
 	int (*tiocmset)(struct tty_struct *tty,
 			unsigned int set, unsigned int clear);
diff --git a/include/linux/tty_port.h b/include/linux/tty_port.h
index 6b367eb17979..1b861f2100b6 100644
--- a/include/linux/tty_port.h
+++ b/include/linux/tty_port.h
@@ -114,8 +114,8 @@ struct tty_port {
 	unsigned char		console:1;
 	struct mutex		mutex;
 	struct mutex		buf_mutex;
-	unsigned char		*xmit_buf;
-	DECLARE_KFIFO_PTR(xmit_fifo, unsigned char);
+	u8			*xmit_buf;
+	DECLARE_KFIFO_PTR(xmit_fifo, u8);
 	unsigned int		close_delay;
 	unsigned int		closing_wait;
 	int			drain_delay;
@@ -149,10 +149,10 @@ struct device *tty_port_register_device_attr(struct tty_port *port,
 		const struct attribute_group **attr_grp);
 struct device *tty_port_register_device_serdev(struct tty_port *port,
 		struct tty_driver *driver, unsigned index,
-		struct device *device);
+		struct device *host, struct device *parent);
 struct device *tty_port_register_device_attr_serdev(struct tty_port *port,
 		struct tty_driver *driver, unsigned index,
-		struct device *device, void *drvdata,
+		struct device *host, struct device *parent, void *drvdata,
 		const struct attribute_group **attr_grp);
 void tty_port_unregister_device(struct tty_port *port,
 		struct tty_driver *driver, unsigned index);
diff --git a/include/linux/uio.h b/include/linux/uio.h
index bea9c89922d9..00cebe2b70de 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -40,7 +40,6 @@ struct iov_iter_state {
 
 struct iov_iter {
 	u8 iter_type;
-	bool copy_mc;
 	bool nofault;
 	bool data_source;
 	size_t iov_offset;
@@ -248,22 +247,8 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i);
 
 #ifdef CONFIG_ARCH_HAS_COPY_MC
 size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
-static inline void iov_iter_set_copy_mc(struct iov_iter *i)
-{
-	i->copy_mc = true;
-}
-
-static inline bool iov_iter_is_copy_mc(const struct iov_iter *i)
-{
-	return i->copy_mc;
-}
 #else
 #define _copy_mc_to_iter _copy_to_iter
-static inline void iov_iter_set_copy_mc(struct iov_iter *i) { }
-static inline bool iov_iter_is_copy_mc(const struct iov_iter *i)
-{
-	return false;
-}
 #endif
 
 size_t iov_iter_zero(size_t bytes, struct iov_iter *);
@@ -355,7 +340,6 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction,
 	WARN_ON(direction & ~(READ | WRITE));
 	*i = (struct iov_iter) {
 		.iter_type = ITER_UBUF,
-		.copy_mc = false,
 		.data_source = direction,
 		.ubuf = buf,
 		.count = count,
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 8c61643acd49..9e52179872a5 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -632,7 +632,6 @@ struct usb3_lpm_parameters {
  * @reset_resume: needs reset instead of resume
  * @port_is_suspended: the upstream port is suspended (L2 or U3)
  * @slot_id: Slot ID assigned by xHCI
- * @removable: Device can be physically removed from this port
  * @l1_params: best effor service latency for USB2 L1 LPM state, and L1 timeout.
  * @u1_params: exit latencies for USB3 U1 LPM state, and hub-initiated timeout.
  * @u2_params: exit latencies for USB3 U2 LPM state, and hub-initiated timeout.
@@ -1145,16 +1144,6 @@ extern ssize_t usb_store_new_id(struct usb_dynids *dynids,
 extern ssize_t usb_show_dynids(struct usb_dynids *dynids, char *buf);
 
 /**
- * struct usbdrv_wrap - wrapper for driver-model structure
- * @driver: The driver-model core driver structure.
- * @for_devices: Non-zero for device drivers, 0 for interface drivers.
- */
-struct usbdrv_wrap {
-	struct device_driver driver;
-	int for_devices;
-};
-
-/**
  * struct usb_driver - identifies USB interface driver to usbcore
  * @name: The driver name should be unique among USB drivers,
  *	and should normally be the same as the module name.
@@ -1194,7 +1183,7 @@ struct usbdrv_wrap {
  *	is bound to the driver.
  * @dynids: used internally to hold the list of dynamically added device
  *	ids for this driver.
- * @drvwrap: Driver-model core structure wrapper.
+ * @driver: The driver-model core driver structure.
  * @no_dynamic_id: if set to 1, the USB core will not allow dynamic ids to be
  *	added to this driver by preventing the sysfs file from being created.
  * @supports_autosuspend: if set to 0, the USB core will not allow autosuspend
@@ -1242,13 +1231,13 @@ struct usb_driver {
 	const struct attribute_group **dev_groups;
 
 	struct usb_dynids dynids;
-	struct usbdrv_wrap drvwrap;
+	struct device_driver driver;
 	unsigned int no_dynamic_id:1;
 	unsigned int supports_autosuspend:1;
 	unsigned int disable_hub_initiated_lpm:1;
 	unsigned int soft_unbind:1;
 };
-#define	to_usb_driver(d) container_of(d, struct usb_driver, drvwrap.driver)
+#define	to_usb_driver(d) container_of(d, struct usb_driver, driver)
 
 /**
  * struct usb_device_driver - identifies USB device driver to usbcore
@@ -1264,9 +1253,12 @@ struct usb_driver {
  *	module is being unloaded.
  * @suspend: Called when the device is going to be suspended by the system.
  * @resume: Called when the device is being resumed by the system.
+ * @choose_configuration: If non-NULL, called instead of the default
+ *	usb_choose_configuration(). If this returns an error then we'll go
+ *	on to call the normal usb_choose_configuration().
  * @dev_groups: Attributes attached to the device that will be created once it
  *	is bound to the driver.
- * @drvwrap: Driver-model core structure wrapper.
+ * @driver: The driver-model core driver structure.
  * @id_table: used with @match() to select better matching driver at
  * 	probe() time.
  * @supports_autosuspend: if set to 0, the USB core will not allow autosuspend
@@ -1275,7 +1267,7 @@ struct usb_driver {
  *	resume and suspend functions will be called in addition to the driver's
  *	own, so this part of the setup does not need to be replicated.
  *
- * USB drivers must provide all the fields listed above except drvwrap,
+ * USB drivers must provide all the fields listed above except driver,
  * match, and id_table.
  */
 struct usb_device_driver {
@@ -1287,14 +1279,17 @@ struct usb_device_driver {
 
 	int (*suspend) (struct usb_device *udev, pm_message_t message);
 	int (*resume) (struct usb_device *udev, pm_message_t message);
+
+	int (*choose_configuration) (struct usb_device *udev);
+
 	const struct attribute_group **dev_groups;
-	struct usbdrv_wrap drvwrap;
+	struct device_driver driver;
 	const struct usb_device_id *id_table;
 	unsigned int supports_autosuspend:1;
 	unsigned int generic_subclass:1;
 };
 #define	to_usb_device_driver(d) container_of(d, struct usb_device_driver, \
-		drvwrap.driver)
+		driver)
 
 /**
  * struct usb_class_driver - identifies a USB driver that wants to use the USB major number
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index f698aac71de3..ac95e7c89df5 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -372,8 +372,9 @@ struct hc_driver {
 		 * or bandwidth constraints.
 		 */
 	void	(*reset_bandwidth)(struct usb_hcd *, struct usb_device *);
-		/* Returns the hardware-chosen device address */
-	int	(*address_device)(struct usb_hcd *, struct usb_device *udev);
+		/* Set the hardware-chosen device address */
+	int	(*address_device)(struct usb_hcd *, struct usb_device *udev,
+				  unsigned int timeout_ms);
 		/* prepares the hardware to send commands to the device */
 	int	(*enable_device)(struct usb_hcd *, struct usb_device *udev);
 		/* Notifies the HCD after a hub descriptor is fetched.
diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h
index eeb7c2157c72..59409c1fc3de 100644
--- a/include/linux/usb/quirks.h
+++ b/include/linux/usb/quirks.h
@@ -72,4 +72,7 @@
 /* device has endpoints that should be ignored */
 #define USB_QUIRK_ENDPOINT_IGNORE		BIT(15)
 
+/* short SET_ADDRESS request timeout */
+#define USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT	BIT(16)
+
 #endif /* __LINUX_USB_QUIRKS_H */
diff --git a/include/linux/usb/tcpci.h b/include/linux/usb/tcpci.h
index 83376473ac76..467e8045e9f8 100644
--- a/include/linux/usb/tcpci.h
+++ b/include/linux/usb/tcpci.h
@@ -36,7 +36,9 @@
 
 #define TCPC_ALERT_MASK			0x12
 #define TCPC_POWER_STATUS_MASK		0x14
-#define TCPC_FAULT_STATUS_MASK		0x15
+
+#define TCPC_FAULT_STATUS_MASK			0x15
+#define TCPC_FAULT_STATUS_MASK_VCONN_OC		BIT(1)
 
 #define TCPC_EXTENDED_STATUS_MASK		0x16
 #define TCPC_EXTENDED_STATUS_MASK_VSAFE0V	BIT(0)
@@ -104,6 +106,7 @@
 
 #define TCPC_FAULT_STATUS		0x1f
 #define TCPC_FAULT_STATUS_ALL_REG_RST_TO_DEFAULT BIT(7)
+#define TCPC_FAULT_STATUS_VCONN_OC	BIT(1)
 
 #define TCPC_ALERT_EXTENDED		0x21
 
diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h
index ab7ca872950b..65fac5e1f317 100644
--- a/include/linux/usb/tcpm.h
+++ b/include/linux/usb/tcpm.h
@@ -173,5 +173,6 @@ void tcpm_pd_hard_reset(struct tcpm_port *port);
 void tcpm_tcpc_reset(struct tcpm_port *port);
 void tcpm_port_clean(struct tcpm_port *port);
 bool tcpm_port_is_toggling(struct tcpm_port *port);
+void tcpm_port_error_recovery(struct tcpm_port *port);
 
 #endif /* __LINUX_USB_TCPM_H */
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index a65b2513f8cd..89b265bc6ec3 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -69,6 +69,13 @@ struct vfio_device {
 	u8 iommufd_attached:1;
 #endif
 	u8 cdev_opened:1;
+#ifdef CONFIG_DEBUG_FS
+	/*
+	 * debug_root is a static property of the vfio_device
+	 * which must be set prior to registering the vfio_device.
+	 */
+	struct dentry *debug_root;
+#endif
 };
 
 /**
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index 562e8754869d..85e84b92751b 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -127,7 +127,27 @@ int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf);
 int vfio_pci_core_enable(struct vfio_pci_core_device *vdev);
 void vfio_pci_core_disable(struct vfio_pci_core_device *vdev);
 void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev);
+int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar);
 pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev,
 						pci_channel_state_t state);
 
+#define VFIO_IOWRITE_DECLATION(size) \
+int vfio_pci_core_iowrite##size(struct vfio_pci_core_device *vdev,	\
+			bool test_mem, u##size val, void __iomem *io);
+
+VFIO_IOWRITE_DECLATION(8)
+VFIO_IOWRITE_DECLATION(16)
+VFIO_IOWRITE_DECLATION(32)
+#ifdef iowrite64
+VFIO_IOWRITE_DECLATION(64)
+#endif
+
+#define VFIO_IOREAD_DECLATION(size) \
+int vfio_pci_core_ioread##size(struct vfio_pci_core_device *vdev,	\
+			bool test_mem, u##size *val, void __iomem *io);
+
+VFIO_IOREAD_DECLATION(8)
+VFIO_IOREAD_DECLATION(16)
+VFIO_IOREAD_DECLATION(32)
+
 #endif /* VFIO_PCI_CORE_H */
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 4cc614a38376..b0201747a263 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -103,6 +103,14 @@ int virtqueue_resize(struct virtqueue *vq, u32 num,
 int virtqueue_reset(struct virtqueue *vq,
 		    void (*recycle)(struct virtqueue *vq, void *buf));
 
+struct virtio_admin_cmd {
+	__le16 opcode;
+	__le16 group_type;
+	__le64 group_member_id;
+	struct scatterlist *data_sg;
+	struct scatterlist *result_sg;
+};
+
 /**
  * struct virtio_device - representation of a device using virtio
  * @index: unique position on the virtio bus
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 2b3438de2c4d..da9b271b54db 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -93,6 +93,8 @@ typedef void vq_callback_t(struct virtqueue *);
  *	Returns 0 on success or error status
  *	If disable_vq_and_reset is set, then enable_vq_after_reset must also be
  *	set.
+ * @create_avq: create admin virtqueue resource.
+ * @destroy_avq: destroy admin virtqueue resource.
  */
 struct virtio_config_ops {
 	void (*get)(struct virtio_device *vdev, unsigned offset,
@@ -120,6 +122,8 @@ struct virtio_config_ops {
 			       struct virtio_shm_region *region, u8 id);
 	int (*disable_vq_and_reset)(struct virtqueue *vq);
 	int (*enable_vq_after_reset)(struct virtqueue *vq);
+	int (*create_avq)(struct virtio_device *vdev);
+	void (*destroy_avq)(struct virtio_device *vdev);
 };
 
 /* If driver didn't advertise the feature, it will never appear. */
diff --git a/include/linux/virtio_console.h b/include/linux/virtio_console.h
deleted file mode 100644
index d2e2785af602..000000000000
--- a/include/linux/virtio_console.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/*
- * This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so
- * anyone can use the definitions to implement compatible drivers/servers:
- *
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the name of IBM nor the names of its contributors
- *    may be used to endorse or promote products derived from this software
- *    without specific prior written permission.
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
- * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
- * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
- * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
- * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
- * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
- * SUCH DAMAGE.
- *
- * Copyright (C) Red Hat, Inc., 2009, 2010, 2011
- * Copyright (C) Amit Shah <amit.shah@redhat.com>, 2009, 2010, 2011
- */
-#ifndef _LINUX_VIRTIO_CONSOLE_H
-#define _LINUX_VIRTIO_CONSOLE_H
-
-#include <uapi/linux/virtio_console.h>
-
-int __init virtio_cons_early_init(int (*put_chars)(u32, const char *, int));
-#endif /* _LINUX_VIRTIO_CONSOLE_H */
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 27cc1d464321..4dfa9b69ca8d 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -3,6 +3,8 @@
 #define _LINUX_VIRTIO_NET_H
 
 #include <linux/if_vlan.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
 #include <linux/udp.h>
 #include <uapi/linux/tcp.h>
 #include <uapi/linux/virtio_net.h>
@@ -49,6 +51,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 					const struct virtio_net_hdr *hdr,
 					bool little_endian)
 {
+	unsigned int nh_min_len = sizeof(struct iphdr);
 	unsigned int gso_type = 0;
 	unsigned int thlen = 0;
 	unsigned int p_off = 0;
@@ -65,6 +68,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 			gso_type = SKB_GSO_TCPV6;
 			ip_proto = IPPROTO_TCP;
 			thlen = sizeof(struct tcphdr);
+			nh_min_len = sizeof(struct ipv6hdr);
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
 			gso_type = SKB_GSO_UDP;
@@ -100,7 +104,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 		if (!skb_partial_csum_set(skb, start, off))
 			return -EINVAL;
 
-		p_off = skb_transport_offset(skb) + thlen;
+		nh_min_len = max_t(u32, nh_min_len, skb_transport_offset(skb));
+		p_off = nh_min_len + thlen;
 		if (!pskb_may_pull(skb, p_off))
 			return -EINVAL;
 	} else {
@@ -140,7 +145,7 @@ retry:
 
 			skb_set_transport_header(skb, keys.control.thoff);
 		} else if (gso_type) {
-			p_off = thlen;
+			p_off = nh_min_len + thlen;
 			if (!pskb_may_pull(skb, p_off))
 				return -EINVAL;
 		}
diff --git a/include/linux/virtio_pci_admin.h b/include/linux/virtio_pci_admin.h
new file mode 100644
index 000000000000..f4a100a0fe2e
--- /dev/null
+++ b/include/linux/virtio_pci_admin.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_VIRTIO_PCI_ADMIN_H
+#define _LINUX_VIRTIO_PCI_ADMIN_H
+
+#include <linux/types.h>
+#include <linux/pci.h>
+
+#ifdef CONFIG_VIRTIO_PCI_ADMIN_LEGACY
+bool virtio_pci_admin_has_legacy_io(struct pci_dev *pdev);
+int virtio_pci_admin_legacy_common_io_write(struct pci_dev *pdev, u8 offset,
+					    u8 size, u8 *buf);
+int virtio_pci_admin_legacy_common_io_read(struct pci_dev *pdev, u8 offset,
+					   u8 size, u8 *buf);
+int virtio_pci_admin_legacy_device_io_write(struct pci_dev *pdev, u8 offset,
+					    u8 size, u8 *buf);
+int virtio_pci_admin_legacy_device_io_read(struct pci_dev *pdev, u8 offset,
+					   u8 size, u8 *buf);
+int virtio_pci_admin_legacy_io_notify_info(struct pci_dev *pdev,
+					   u8 req_bar_flags, u8 *bar,
+					   u64 *bar_offset);
+#endif
+
+#endif /* _LINUX_VIRTIO_PCI_ADMIN_H */
diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h
index a09e13a577a9..c0b1b1ca1163 100644
--- a/include/linux/virtio_pci_modern.h
+++ b/include/linux/virtio_pci_modern.h
@@ -125,4 +125,6 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev);
 void vp_modern_remove(struct virtio_pci_modern_device *mdev);
 int vp_modern_get_queue_reset(struct virtio_pci_modern_device *mdev, u16 index);
 void vp_modern_set_queue_reset(struct virtio_pci_modern_device *mdev, u16 index);
+u16 vp_modern_avq_num(struct virtio_pci_modern_device *mdev);
+u16 vp_modern_avq_index(struct virtio_pci_modern_device *mdev);
 #endif
diff --git a/include/linux/w1-gpio.h b/include/linux/w1-gpio.h
deleted file mode 100644
index 3495fd0dc790..000000000000
--- a/include/linux/w1-gpio.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * w1-gpio interface to platform code
- *
- * Copyright (C) 2007 Ville Syrjala <syrjala@sci.fi>
- */
-#ifndef _LINUX_W1_GPIO_H
-#define _LINUX_W1_GPIO_H
-
-struct gpio_desc;
-
-/**
- * struct w1_gpio_platform_data - Platform-dependent data for w1-gpio
- */
-struct w1_gpio_platform_data {
-	struct gpio_desc *gpiod;
-	struct gpio_desc *pullup_gpiod;
-	void (*enable_external_pullup)(int enable);
-	unsigned int pullup_duration;
-};
-
-#endif /* _LINUX_W1_GPIO_H */
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 283d7891b4c4..158784dd189a 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -24,41 +24,49 @@
 
 enum work_bits {
 	WORK_STRUCT_PENDING_BIT	= 0,	/* work item is pending execution */
-	WORK_STRUCT_INACTIVE_BIT= 1,	/* work item is inactive */
-	WORK_STRUCT_PWQ_BIT	= 2,	/* data points to pwq */
-	WORK_STRUCT_LINKED_BIT	= 3,	/* next work is linked to this one */
+	WORK_STRUCT_INACTIVE_BIT,	/* work item is inactive */
+	WORK_STRUCT_PWQ_BIT,		/* data points to pwq */
+	WORK_STRUCT_LINKED_BIT,		/* next work is linked to this one */
 #ifdef CONFIG_DEBUG_OBJECTS_WORK
-	WORK_STRUCT_STATIC_BIT	= 4,	/* static initializer (debugobjects) */
-	WORK_STRUCT_COLOR_SHIFT	= 5,	/* color for workqueue flushing */
-#else
-	WORK_STRUCT_COLOR_SHIFT	= 4,	/* color for workqueue flushing */
+	WORK_STRUCT_STATIC_BIT,		/* static initializer (debugobjects) */
 #endif
+	WORK_STRUCT_FLAG_BITS,
 
+	/* color for workqueue flushing */
+	WORK_STRUCT_COLOR_SHIFT	= WORK_STRUCT_FLAG_BITS,
 	WORK_STRUCT_COLOR_BITS	= 4,
 
 	/*
-	 * Reserve 8 bits off of pwq pointer w/ debugobjects turned off.
-	 * This makes pwqs aligned to 256 bytes and allows 16 workqueue
-	 * flush colors.
+	 * When WORK_STRUCT_PWQ is set, reserve 8 bits off of pwq pointer w/
+	 * debugobjects turned off. This makes pwqs aligned to 256 bytes (512
+	 * bytes w/ DEBUG_OBJECTS_WORK) and allows 16 workqueue flush colors.
+	 *
+	 * MSB
+	 * [ pwq pointer ] [ flush color ] [ STRUCT flags ]
+	 *                     4 bits        4 or 5 bits
 	 */
-	WORK_STRUCT_FLAG_BITS	= WORK_STRUCT_COLOR_SHIFT +
-				  WORK_STRUCT_COLOR_BITS,
-
-	/* data contains off-queue information when !WORK_STRUCT_PWQ */
-	WORK_OFFQ_FLAG_BASE	= WORK_STRUCT_COLOR_SHIFT,
+	WORK_STRUCT_PWQ_SHIFT	= WORK_STRUCT_COLOR_SHIFT + WORK_STRUCT_COLOR_BITS,
 
-	__WORK_OFFQ_CANCELING	= WORK_OFFQ_FLAG_BASE,
+	/*
+	 * data contains off-queue information when !WORK_STRUCT_PWQ.
+	 *
+	 * MSB
+	 * [ pool ID ] [ OFFQ flags ] [ STRUCT flags ]
+	 *                 1 bit        4 or 5 bits
+	 */
+	WORK_OFFQ_FLAG_SHIFT	= WORK_STRUCT_FLAG_BITS,
+	WORK_OFFQ_CANCELING_BIT = WORK_OFFQ_FLAG_SHIFT,
+	WORK_OFFQ_FLAG_END,
+	WORK_OFFQ_FLAG_BITS	= WORK_OFFQ_FLAG_END - WORK_OFFQ_FLAG_SHIFT,
 
 	/*
-	 * When a work item is off queue, its high bits point to the last
-	 * pool it was on.  Cap at 31 bits and use the highest number to
-	 * indicate that no pool is associated.
+	 * When a work item is off queue, the high bits encode off-queue flags
+	 * and the last pool it was on. Cap pool ID to 31 bits and use the
+	 * highest number to indicate that no pool is associated.
 	 */
-	WORK_OFFQ_FLAG_BITS	= 1,
-	WORK_OFFQ_POOL_SHIFT	= WORK_OFFQ_FLAG_BASE + WORK_OFFQ_FLAG_BITS,
+	WORK_OFFQ_POOL_SHIFT	= WORK_OFFQ_FLAG_SHIFT + WORK_OFFQ_FLAG_BITS,
 	WORK_OFFQ_LEFT		= BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT,
 	WORK_OFFQ_POOL_BITS	= WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31,
-
 };
 
 enum work_flags {
@@ -88,12 +96,10 @@ enum wq_misc_consts {
 };
 
 /* Convenience constants - of type 'unsigned long', not 'enum'! */
-#define WORK_OFFQ_CANCELING	(1ul << __WORK_OFFQ_CANCELING)
+#define WORK_OFFQ_CANCELING	(1ul << WORK_OFFQ_CANCELING_BIT)
 #define WORK_OFFQ_POOL_NONE	((1ul << WORK_OFFQ_POOL_BITS) - 1)
 #define WORK_STRUCT_NO_POOL	(WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT)
-
-#define WORK_STRUCT_FLAG_MASK    ((1ul << WORK_STRUCT_FLAG_BITS) - 1)
-#define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK)
+#define WORK_STRUCT_PWQ_MASK	(~((1ul << WORK_STRUCT_PWQ_SHIFT) - 1))
 
 #define WORK_DATA_INIT()	ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL)
 #define WORK_DATA_STATIC_INIT()	\
@@ -392,7 +398,6 @@ enum wq_flags {
 	__WQ_DRAINING		= 1 << 16, /* internal: workqueue is draining */
 	__WQ_ORDERED		= 1 << 17, /* internal: workqueue is ordered */
 	__WQ_LEGACY		= 1 << 18, /* internal: create*_workqueue() */
-	__WQ_ORDERED_EXPLICIT	= 1 << 19, /* internal: alloc_ordered_workqueue() */
 
 	/* BH wq only allows the following flags */
 	__WQ_BH_ALLOWS		= WQ_BH | WQ_HIGHPRI,
@@ -453,6 +458,7 @@ extern struct workqueue_struct *system_bh_wq;
 extern struct workqueue_struct *system_bh_highpri_wq;
 
 void workqueue_softirq_action(bool highpri);
+void workqueue_softirq_dead(unsigned int cpu);
 
 /**
  * alloc_workqueue - allocate a workqueue
@@ -507,8 +513,7 @@ alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...);
  * Pointer to the allocated workqueue on success, %NULL on failure.
  */
 #define alloc_ordered_workqueue(fmt, flags, args...)			\
-	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED |		\
-			__WQ_ORDERED_EXPLICIT | (flags), 1, ##args)
+	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
 
 #define create_workqueue(name)						\
 	alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name))
@@ -518,6 +523,9 @@ alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...);
 #define create_singlethread_workqueue(name)				\
 	alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name)
 
+#define from_work(var, callback_work, work_fieldname)	\
+	container_of(callback_work, typeof(*var), work_fieldname)
+
 extern void destroy_workqueue(struct workqueue_struct *wq);
 
 struct workqueue_attrs *alloc_workqueue_attrs(void);
@@ -555,6 +563,8 @@ extern bool flush_rcu_work(struct rcu_work *rwork);
 
 extern void workqueue_set_max_active(struct workqueue_struct *wq,
 				     int max_active);
+extern void workqueue_set_min_active(struct workqueue_struct *wq,
+				     int min_active);
 extern struct work_struct *current_work(void);
 extern bool current_is_workqueue_rescuer(void);
 extern bool workqueue_congested(int cpu, struct workqueue_struct *wq);
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 6d0a14f7019d..453736fd1d23 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -60,7 +60,7 @@ struct writeback_control {
 	unsigned for_reclaim:1;		/* Invoked from the page allocator */
 	unsigned range_cyclic:1;	/* range_start is cyclic */
 	unsigned for_sync:1;		/* sync(2) WB_SYNC_ALL writeback */
-	unsigned unpinned_fscache_wb:1;	/* Cleared I_PINNING_FSCACHE_WB */
+	unsigned unpinned_netfs_wb:1;	/* Cleared I_PINNING_NETFS_WB */
 
 	/*
 	 * When writeback IOs are bounced through async layers, only the
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 49c4640027d8..afd40dce40f3 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -46,12 +46,6 @@ struct scm_stat {
 
 #define UNIXCB(skb)	(*(struct unix_skb_parms *)&((skb)->cb))
 
-#define unix_state_lock(s)	spin_lock(&unix_sk(s)->lock)
-#define unix_state_unlock(s)	spin_unlock(&unix_sk(s)->lock)
-#define unix_state_lock_nested(s) \
-				spin_lock_nested(&unix_sk(s)->lock, \
-				SINGLE_DEPTH_NESTING)
-
 /* The AF_UNIX socket */
 struct unix_sock {
 	/* WARNING: sk has to be the first member */
@@ -77,6 +71,20 @@ struct unix_sock {
 #define unix_sk(ptr) container_of_const(ptr, struct unix_sock, sk)
 #define unix_peer(sk) (unix_sk(sk)->peer)
 
+#define unix_state_lock(s)	spin_lock(&unix_sk(s)->lock)
+#define unix_state_unlock(s)	spin_unlock(&unix_sk(s)->lock)
+enum unix_socket_lock_class {
+	U_LOCK_NORMAL,
+	U_LOCK_SECOND,	/* for double locking, see unix_state_double_lock(). */
+	U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */
+};
+
+static inline void unix_state_lock_nested(struct sock *sk,
+				   enum unix_socket_lock_class subclass)
+{
+	spin_lock_nested(&unix_sk(sk)->lock, subclass);
+}
+
 #define peer_wait peer_wq.wait
 
 long unix_inq_len(struct sock *sk);
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 4dabeb6c76d3..9b09acac538e 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -48,6 +48,10 @@ void napi_busy_loop(unsigned int napi_id,
 		    bool (*loop_end)(void *, unsigned long),
 		    void *loop_end_arg, bool prefer_busy_poll, u16 budget);
 
+void napi_busy_loop_rcu(unsigned int napi_id,
+			bool (*loop_end)(void *, unsigned long),
+			void *loop_end_arg, bool prefer_busy_poll, u16 budget);
+
 #else /* CONFIG_NET_RX_BUSY_POLL */
 static inline unsigned long net_busy_loop_on(void)
 {
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index cf79656ce09c..2b54fdd8ca15 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2910,6 +2910,8 @@ struct cfg80211_bss_ies {
  *	own the beacon_ies, but they're just pointers to the ones from the
  *	@hidden_beacon_bss struct)
  * @proberesp_ies: the information elements from the last Probe Response frame
+ * @proberesp_ecsa_stuck: ECSA element is stuck in the Probe Response frame,
+ *	cannot rely on it having valid data
  * @hidden_beacon_bss: in case this BSS struct represents a probe response from
  *	a BSS that hides the SSID in its beacon, this points to the BSS struct
  *	that holds the beacon data. @beacon_ies is still valid, of course, and
@@ -2950,6 +2952,8 @@ struct cfg80211_bss {
 	u8 chains;
 	s8 chain_signal[IEEE80211_MAX_CHAINS];
 
+	u8 proberesp_ecsa_stuck:1;
+
 	u8 bssid_index;
 	u8 max_bssid_indicator;
 
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index d0a2f827d5f2..9ab4bf704e86 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -357,4 +357,12 @@ static inline bool inet_csk_has_ulp(const struct sock *sk)
 	return inet_test_bit(IS_ICSK, sk) && !!inet_csk(sk)->icsk_ulp_ops;
 }
 
+static inline void inet_init_csk_locks(struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	spin_lock_init(&icsk->icsk_accept_queue.rskq_lock);
+	spin_lock_init(&icsk->icsk_accept_queue.fastopenq.lock);
+}
+
 #endif /* _INET_CONNECTION_SOCK_H */
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index aa86453f6b9b..d94c242eb3ed 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -307,11 +307,6 @@ static inline unsigned long inet_cmsg_flags(const struct inet_sock *inet)
 #define inet_assign_bit(nr, sk, val)		\
 	assign_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags, val)
 
-static inline bool sk_is_inet(struct sock *sk)
-{
-	return sk->sk_family == AF_INET || sk->sk_family == AF_INET6;
-}
-
 /**
  * sk_to_full_sk - Access to a full socket
  * @sk: pointer to a socket
diff --git a/include/net/ip.h b/include/net/ip.h
index de0c69c57e3c..25cb688bdc62 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -767,7 +767,7 @@ int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev);
  *	Functions provided by ip_sockglue.c
  */
 
-void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb);
+void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb, bool drop_dst);
 void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk,
 			 struct sk_buff *skb, int tlen, int offset);
 int ip_cmsg_send(struct sock *sk, struct msghdr *msg,
diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h
index 7e73f8e5e497..1d55ba7c45be 100644
--- a/include/net/llc_pdu.h
+++ b/include/net/llc_pdu.h
@@ -262,8 +262,7 @@ static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type,
  */
 static inline void llc_pdu_decode_sa(struct sk_buff *skb, u8 *sa)
 {
-	if (skb->protocol == htons(ETH_P_802_2))
-		memcpy(sa, eth_hdr(skb)->h_source, ETH_ALEN);
+	memcpy(sa, eth_hdr(skb)->h_source, ETH_ALEN);
 }
 
 /**
@@ -275,8 +274,7 @@ static inline void llc_pdu_decode_sa(struct sk_buff *skb, u8 *sa)
  */
 static inline void llc_pdu_decode_da(struct sk_buff *skb, u8 *da)
 {
-	if (skb->protocol == htons(ETH_P_802_2))
-		memcpy(da, eth_hdr(skb)->h_dest, ETH_ALEN);
+	memcpy(da, eth_hdr(skb)->h_dest, ETH_ALEN);
 }
 
 /**
diff --git a/include/net/mctp.h b/include/net/mctp.h
index da86e106c91d..2bff5f47ce82 100644
--- a/include/net/mctp.h
+++ b/include/net/mctp.h
@@ -249,6 +249,7 @@ struct mctp_route {
 struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet,
 				     mctp_eid_t daddr);
 
+/* always takes ownership of skb */
 int mctp_local_output(struct sock *sk, struct mctp_route *rt,
 		      struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag);
 
diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index d68b0a483431..8b8ed4e13d74 100644
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -128,7 +128,7 @@ netdev_txq_completed_mb(struct netdev_queue *dev_queue,
 		netdev_txq_completed_mb(txq, pkts, bytes);		\
 									\
 		_res = -1;						\
-		if (pkts && likely(get_desc > start_thrs)) {		\
+		if (pkts && likely(get_desc >= start_thrs)) {		\
 			_res = 1;					\
 			if (unlikely(netif_tx_queue_stopped(txq)) &&	\
 			    !(down_cond)) {				\
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 956c752ceb31..a763dd327c6e 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -276,7 +276,7 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table,
 }
 
 void flow_offload_route_init(struct flow_offload *flow,
-			     const struct nf_flow_route *route);
+			     struct nf_flow_route *route);
 
 int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow);
 void flow_offload_refresh(struct nf_flowtable *flow_table,
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index b157c5cafd14..510244cc0f8f 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -205,6 +205,7 @@ static inline void nft_data_copy(u32 *dst, const struct nft_data *src,
  *	@nla: netlink attributes
  *	@portid: netlink portID of the original message
  *	@seq: netlink sequence number
+ *	@flags: modifiers to new request
  *	@family: protocol family
  *	@level: depth of the chains
  *	@report: notify via unicast netlink message
@@ -282,6 +283,7 @@ struct nft_elem_priv { };
  *
  *	@key: element key
  *	@key_end: closing element key
+ *	@data: element data
  *	@priv: element private data and extensions
  */
 struct nft_set_elem {
@@ -325,10 +327,10 @@ struct nft_set_iter {
  *	@dtype: data type
  *	@dlen: data length
  *	@objtype: object type
- *	@flags: flags
  *	@size: number of set elements
  *	@policy: set policy
  *	@gc_int: garbage collector interval
+ *	@timeout: element timeout
  *	@field_len: length of each field in concatenation, bytes
  *	@field_count: number of concatenated fields in element
  *	@expr: set must support for expressions
@@ -351,9 +353,9 @@ struct nft_set_desc {
 /**
  *	enum nft_set_class - performance class
  *
- *	@NFT_LOOKUP_O_1: constant, O(1)
- *	@NFT_LOOKUP_O_LOG_N: logarithmic, O(log N)
- *	@NFT_LOOKUP_O_N: linear, O(N)
+ *	@NFT_SET_CLASS_O_1: constant, O(1)
+ *	@NFT_SET_CLASS_O_LOG_N: logarithmic, O(log N)
+ *	@NFT_SET_CLASS_O_N: linear, O(N)
  */
 enum nft_set_class {
 	NFT_SET_CLASS_O_1,
@@ -422,9 +424,13 @@ struct nft_set_ext;
  *	@remove: remove element from set
  *	@walk: iterate over all set elements
  *	@get: get set elements
+ *	@commit: commit set elements
+ *	@abort: abort set elements
  *	@privsize: function to return size of set private data
+ *	@estimate: estimate the required memory size and the lookup complexity class
  *	@init: initialize private data of new set instance
  *	@destroy: destroy private data of set instance
+ *	@gc_init: initialize garbage collection
  *	@elemsize: element private size
  *
  *	Operations lookup, update and delete have simpler interfaces, are faster
@@ -540,13 +546,16 @@ struct nft_set_elem_expr {
  *	@policy: set parameterization (see enum nft_set_policies)
  *	@udlen: user data length
  *	@udata: user data
- *	@expr: stateful expression
+ *	@pending_update: list of pending update set element
  * 	@ops: set ops
  * 	@flags: set flags
  *	@dead: set will be freed, never cleared
  *	@genmask: generation mask
  * 	@klen: key length
  * 	@dlen: data length
+ *	@num_exprs: numbers of exprs
+ *	@exprs: stateful expression
+ *	@catchall_list: list of catch-all set element
  * 	@data: private set data
  */
 struct nft_set {
@@ -692,6 +701,7 @@ extern const struct nft_set_ext_type nft_set_ext_types[];
  *
  *	@len: length of extension area
  *	@offset: offsets of individual extension types
+ *	@ext_len: length of the expected extension(used to sanity check)
  */
 struct nft_set_ext_tmpl {
 	u16	len;
@@ -798,10 +808,16 @@ static inline struct nft_set_elem_expr *nft_set_ext_expr(const struct nft_set_ex
 	return nft_set_ext(ext, NFT_SET_EXT_EXPRESSIONS);
 }
 
-static inline bool nft_set_elem_expired(const struct nft_set_ext *ext)
+static inline bool __nft_set_elem_expired(const struct nft_set_ext *ext,
+					  u64 tstamp)
 {
 	return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) &&
-	       time_is_before_eq_jiffies64(*nft_set_ext_expiration(ext));
+	       time_after_eq64(tstamp, *nft_set_ext_expiration(ext));
+}
+
+static inline bool nft_set_elem_expired(const struct nft_set_ext *ext)
+{
+	return __nft_set_elem_expired(ext, get_jiffies_64());
 }
 
 static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set,
@@ -840,6 +856,7 @@ struct nft_expr_ops;
  *	@select_ops: function to select nft_expr_ops
  *	@release_ops: release nft_expr_ops
  *	@ops: default ops, used when no select_ops functions is present
+ *	@inner_ops: inner ops, used for inner packet operation
  *	@list: used internally
  *	@name: Identifier
  *	@owner: module reference
@@ -881,14 +898,22 @@ struct nft_offload_ctx;
  *	struct nft_expr_ops - nf_tables expression operations
  *
  *	@eval: Expression evaluation function
+ *	@clone: Expression clone function
  *	@size: full expression size, including private data size
  *	@init: initialization function
  *	@activate: activate expression in the next generation
  *	@deactivate: deactivate expression in next generation
  *	@destroy: destruction function, called after synchronize_rcu
+ *	@destroy_clone: destruction clone function
  *	@dump: function to dump parameters
- *	@type: expression type
  *	@validate: validate expression, called during loop detection
+ *	@reduce: reduce expression
+ *	@gc: garbage collection expression
+ *	@offload: hardware offload expression
+ *	@offload_action: function to report true/false to allocate one slot or not in the flow
+ *			 offload array
+ *	@offload_stats: function to synchronize hardware stats via updating the counter expression
+ *	@type: expression type
  *	@data: extra data to attach to this expression operation
  */
 struct nft_expr_ops {
@@ -1041,14 +1066,21 @@ struct nft_rule_blob {
 /**
  *	struct nft_chain - nf_tables chain
  *
+ *	@blob_gen_0: rule blob pointer to the current generation
+ *	@blob_gen_1: rule blob pointer to the future generation
  *	@rules: list of rules in the chain
  *	@list: used internally
  *	@rhlhead: used internally
  *	@table: table that this chain belongs to
  *	@handle: chain handle
  *	@use: number of jump references to this chain
- *	@flags: bitmask of enum nft_chain_flags
+ *	@flags: bitmask of enum NFTA_CHAIN_FLAGS
+ *	@bound: bind or not
+ *	@genmask: generation mask
  *	@name: name of the chain
+ *	@udlen: user data length
+ *	@udata: user data in the chain
+ *	@blob_next: rule blob pointer to the next in the chain
  */
 struct nft_chain {
 	struct nft_rule_blob		__rcu *blob_gen_0;
@@ -1146,6 +1178,7 @@ struct nft_hook {
  *	@hook_list: list of netfilter hooks (for NFPROTO_NETDEV family)
  *	@type: chain type
  *	@policy: default policy
+ *	@flags: indicate the base chain disabled or not
  *	@stats: per-cpu chain stats
  *	@chain: the chain
  *	@flow_block: flow block (for hardware offload)
@@ -1274,11 +1307,13 @@ struct nft_object_hash_key {
  *	struct nft_object - nf_tables stateful object
  *
  *	@list: table stateful object list node
- *	@key:  keys that identify this object
  *	@rhlhead: nft_objname_ht node
+ *	@key: keys that identify this object
  *	@genmask: generation mask
  *	@use: number of references to this stateful object
  *	@handle: unique object handle
+ *	@udlen: length of user data
+ *	@udata: user data
  *	@ops: object operations
  *	@data: object data, layout depends on type
  */
@@ -1322,6 +1357,7 @@ void nft_obj_notify(struct net *net, const struct nft_table *table,
  *	@type: stateful object numeric type
  *	@owner: module owner
  *	@maxattr: maximum netlink attribute
+ *	@family: address family for AF-specific object types
  *	@policy: netlink attribute policy
  */
 struct nft_object_type {
@@ -1331,6 +1367,7 @@ struct nft_object_type {
 	struct list_head		list;
 	u32				type;
 	unsigned int                    maxattr;
+	u8				family;
 	struct module			*owner;
 	const struct nla_policy		*policy;
 };
@@ -1344,6 +1381,7 @@ struct nft_object_type {
  *	@destroy: release existing stateful object
  *	@dump: netlink dump stateful object
  *	@update: update stateful object
+ *	@type: pointer to object type
  */
 struct nft_object_ops {
 	void				(*eval)(struct nft_object *obj,
@@ -1379,9 +1417,8 @@ void nft_unregister_obj(struct nft_object_type *obj_type);
  *	@genmask: generation mask
  *	@use: number of references to this flow table
  * 	@handle: unique object handle
- *	@dev_name: array of device names
+ *	@hook_list: hook list for hooks per net_device in flowtables
  *	@data: rhashtable and garbage collector
- * 	@ops: array of hooks
  */
 struct nft_flowtable {
 	struct list_head		list;
@@ -1748,6 +1785,7 @@ struct nftables_pernet {
 	struct list_head	notify_list;
 	struct mutex		commit_mutex;
 	u64			table_handle;
+	u64			tstamp;
 	unsigned int		base_seq;
 	unsigned int		gc_seq;
 	u8			validate_state;
@@ -1760,6 +1798,11 @@ static inline struct nftables_pernet *nft_pernet(const struct net *net)
 	return net_generic(net, nf_tables_net_id);
 }
 
+static inline u64 nft_net_tstamp(const struct net *net)
+{
+	return nft_pernet(net)->tstamp;
+}
+
 #define __NFT_REDUCE_READONLY	1UL
 #define NFT_REDUCE_READONLY	(void *)__NFT_REDUCE_READONLY
 
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index ba3e1b315de8..cefe0c4bdae3 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -238,12 +238,7 @@ static inline bool qdisc_may_bulk(const struct Qdisc *qdisc)
 
 static inline int qdisc_avail_bulklimit(const struct netdev_queue *txq)
 {
-#ifdef CONFIG_BQL
-	/* Non-BQL migrated drivers will return 0, too. */
-	return dql_avail(&txq->dql);
-#else
-	return 0;
-#endif
+	return netdev_queue_dql_avail(txq);
 }
 
 struct Qdisc_class_ops {
@@ -375,6 +370,10 @@ struct tcf_proto_ops {
 						struct nlattr **tca,
 						struct netlink_ext_ack *extack);
 	void			(*tmplt_destroy)(void *tmplt_priv);
+	void			(*tmplt_reoffload)(struct tcf_chain *chain,
+						   bool add,
+						   flow_setup_cb_t *cb,
+						   void *cb_priv);
 	struct tcf_exts *	(*get_exts)(const struct tcf_proto *tp,
 					    u32 handle);
 
diff --git a/include/net/sock.h b/include/net/sock.h
index a7f815c7cfdf..54ca8dcbfb43 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2765,9 +2765,25 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags)
 			   &skb_shinfo(skb)->tskey);
 }
 
+static inline bool sk_is_inet(const struct sock *sk)
+{
+	int family = READ_ONCE(sk->sk_family);
+
+	return family == AF_INET || family == AF_INET6;
+}
+
 static inline bool sk_is_tcp(const struct sock *sk)
 {
-	return sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP;
+	return sk_is_inet(sk) &&
+	       sk->sk_type == SOCK_STREAM &&
+	       sk->sk_protocol == IPPROTO_TCP;
+}
+
+static inline bool sk_is_udp(const struct sock *sk)
+{
+	return sk_is_inet(sk) &&
+	       sk->sk_type == SOCK_DGRAM &&
+	       sk->sk_protocol == IPPROTO_UDP;
 }
 
 static inline bool sk_is_stream_unix(const struct sock *sk)
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index a43062d4c734..8346b0d29542 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -308,6 +308,9 @@ void switchdev_deferred_process(void);
 int switchdev_port_attr_set(struct net_device *dev,
 			    const struct switchdev_attr *attr,
 			    struct netlink_ext_ack *extack);
+bool switchdev_port_obj_act_is_deferred(struct net_device *dev,
+					enum switchdev_notifier_type nt,
+					const struct switchdev_obj *obj);
 int switchdev_port_obj_add(struct net_device *dev,
 			   const struct switchdev_obj *obj,
 			   struct netlink_ext_ack *extack);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index dd78a1181031..f6eba9652d01 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2506,7 +2506,7 @@ struct tcp_ulp_ops {
 	/* cleanup ulp */
 	void (*release)(struct sock *sk);
 	/* diagnostic */
-	int (*get_info)(const struct sock *sk, struct sk_buff *skb);
+	int (*get_info)(struct sock *sk, struct sk_buff *skb);
 	size_t (*get_info_size)(const struct sock *sk);
 	/* clone ulp */
 	void (*clone)(const struct request_sock *req, struct sock *newsk,
diff --git a/include/net/tls.h b/include/net/tls.h
index 962f0c501111..340ad43971e4 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -97,9 +97,6 @@ struct tls_sw_context_tx {
 	struct tls_rec *open_rec;
 	struct list_head tx_list;
 	atomic_t encrypt_pending;
-	/* protect crypto_wait with encrypt_pending */
-	spinlock_t encrypt_compl_lock;
-	int async_notify;
 	u8 async_capable:1;
 
 #define BIT_TX_SCHEDULED	0
@@ -136,8 +133,6 @@ struct tls_sw_context_rx {
 	struct tls_strparser strp;
 
 	atomic_t decrypt_pending;
-	/* protect crypto_wait with decrypt_pending*/
-	spinlock_t decrypt_compl_lock;
 	struct sk_buff_head async_hold;
 	struct wait_queue_head wq;
 };
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 526c1e7f505e..c9aec9ab6191 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -159,11 +159,29 @@ static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first)
 	return ret;
 }
 
+static inline void xsk_buff_del_tail(struct xdp_buff *tail)
+{
+	struct xdp_buff_xsk *xskb = container_of(tail, struct xdp_buff_xsk, xdp);
+
+	list_del(&xskb->xskb_list_node);
+}
+
+static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first)
+{
+	struct xdp_buff_xsk *xskb = container_of(first, struct xdp_buff_xsk, xdp);
+	struct xdp_buff_xsk *frag;
+
+	frag = list_last_entry(&xskb->pool->xskb_list, struct xdp_buff_xsk,
+			       xskb_list_node);
+	return &frag->xdp;
+}
+
 static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size)
 {
 	xdp->data = xdp->data_hard_start + XDP_PACKET_HEADROOM;
 	xdp->data_meta = xdp->data;
 	xdp->data_end = xdp->data + size;
+	xdp->flags = 0;
 }
 
 static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool,
@@ -350,6 +368,15 @@ static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first)
 	return NULL;
 }
 
+static inline void xsk_buff_del_tail(struct xdp_buff *tail)
+{
+}
+
+static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first)
+{
+	return NULL;
+}
+
 static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size)
 {
 }
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 5ec1e71a09de..c38f4fe5e64c 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -100,10 +100,6 @@ struct scsi_vpd {
 	unsigned char	data[];
 };
 
-enum scsi_vpd_parameters {
-	SCSI_VPD_HEADER_SIZE = 4,
-};
-
 struct scsi_device {
 	struct Scsi_Host *host;
 	struct request_queue *request_queue;
@@ -208,6 +204,7 @@ struct scsi_device {
 	unsigned use_10_for_rw:1; /* first try 10-byte read / write */
 	unsigned use_10_for_ms:1; /* first try 10-byte mode sense/select */
 	unsigned set_dbd_for_ms:1; /* Set "DBD" field in mode sense */
+	unsigned read_before_ms:1;	/* perform a READ before MODE SENSE */
 	unsigned no_report_opcodes:1;	/* no REPORT SUPPORTED OPERATION CODES */
 	unsigned no_write_same:1;	/* no WRITE SAME command */
 	unsigned use_16_for_rw:1; /* Use read/write(16) over read/write(10) */
diff --git a/include/soc/qcom/qcom-spmi-pmic.h b/include/soc/qcom/qcom-spmi-pmic.h
index c47cc71a999e..17a0a8c3d656 100644
--- a/include/soc/qcom/qcom-spmi-pmic.h
+++ b/include/soc/qcom/qcom-spmi-pmic.h
@@ -31,6 +31,7 @@
 #define PM8998_SUBTYPE		0x14
 #define PMI8998_SUBTYPE		0x15
 #define PM8005_SUBTYPE		0x18
+#define PM8937_SUBTYPE		0x19
 #define PM660L_SUBTYPE		0x1a
 #define PM660_SUBTYPE		0x1b
 #define PM8150_SUBTYPE		0x1e
diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h
index 8c18e8b6d27d..b24716ab2750 100644
--- a/include/sound/cs35l56.h
+++ b/include/sound/cs35l56.h
@@ -75,6 +75,7 @@
 #define CS35L56_DSP1_AHBM_WINDOW_DEBUG_0		0x25E2040
 #define CS35L56_DSP1_AHBM_WINDOW_DEBUG_1		0x25E2044
 #define CS35L56_DSP1_XMEM_UNPACKED24_0			0x2800000
+#define CS35L56_DSP1_FW_VER				0x2800010
 #define CS35L56_DSP1_HALO_STATE_A1			0x2801E58
 #define CS35L56_DSP1_HALO_STATE				0x28021E0
 #define CS35L56_DSP1_PM_CUR_STATE_A1			0x2804000
@@ -241,7 +242,7 @@
 
 #define CS35L56_CONTROL_PORT_READY_US			2200
 #define CS35L56_HALO_STATE_POLL_US			1000
-#define CS35L56_HALO_STATE_TIMEOUT_US			50000
+#define CS35L56_HALO_STATE_TIMEOUT_US			250000
 #define CS35L56_RESET_PULSE_MIN_US			1100
 #define CS35L56_WAKE_HOLD_TIME_US			1000
 
@@ -272,6 +273,7 @@ extern const char * const cs35l56_tx_input_texts[CS35L56_NUM_INPUT_SRC];
 extern const unsigned int cs35l56_tx_input_values[CS35L56_NUM_INPUT_SRC];
 
 int cs35l56_set_patch(struct cs35l56_base *cs35l56_base);
+int cs35l56_force_sync_asp1_registers_from_cache(struct cs35l56_base *cs35l56_base);
 int cs35l56_mbox_send(struct cs35l56_base *cs35l56_base, unsigned int command);
 int cs35l56_firmware_shutdown(struct cs35l56_base *cs35l56_base);
 int cs35l56_wait_for_firmware_boot(struct cs35l56_base *cs35l56_base);
@@ -284,7 +286,10 @@ int cs35l56_is_fw_reload_needed(struct cs35l56_base *cs35l56_base);
 int cs35l56_runtime_suspend_common(struct cs35l56_base *cs35l56_base);
 int cs35l56_runtime_resume_common(struct cs35l56_base *cs35l56_base, bool is_soundwire);
 void cs35l56_init_cs_dsp(struct cs35l56_base *cs35l56_base, struct cs_dsp *cs_dsp);
+int cs35l56_read_prot_status(struct cs35l56_base *cs35l56_base,
+			     bool *fw_missing, unsigned int *fw_version);
 int cs35l56_hw_init(struct cs35l56_base *cs35l56_base);
+int cs35l56_get_speaker_id(struct cs35l56_base *cs35l56_base);
 int cs35l56_get_bclk_freq_id(unsigned int freq);
 void cs35l56_fill_supply_names(struct regulator_bulk_data *data);
 
diff --git a/include/sound/soc-card.h b/include/sound/soc-card.h
index ecc02e955279..1f4c39922d82 100644
--- a/include/sound/soc-card.h
+++ b/include/sound/soc-card.h
@@ -30,6 +30,8 @@ static inline void snd_soc_card_mutex_unlock(struct snd_soc_card *card)
 
 struct snd_kcontrol *snd_soc_card_get_kcontrol(struct snd_soc_card *soc_card,
 					       const char *name);
+struct snd_kcontrol *snd_soc_card_get_kcontrol_locked(struct snd_soc_card *soc_card,
+						      const char *name);
 int snd_soc_card_jack_new(struct snd_soc_card *card, const char *id, int type,
 			  struct snd_soc_jack *jack);
 int snd_soc_card_jack_new_pins(struct snd_soc_card *card, const char *id,
diff --git a/include/sound/tas2781.h b/include/sound/tas2781.h
index 0a86ab8d47b9..9aff384941de 100644
--- a/include/sound/tas2781.h
+++ b/include/sound/tas2781.h
@@ -1,13 +1,13 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 //
-// ALSA SoC Texas Instruments TAS2781 Audio Smart Amplifier
+// ALSA SoC Texas Instruments TAS2563/TAS2781 Audio Smart Amplifier
 //
 // Copyright (C) 2022 - 2023 Texas Instruments Incorporated
 // https://www.ti.com
 //
-// The TAS2781 driver implements a flexible and configurable
+// The TAS2563/TAS2781 driver implements a flexible and configurable
 // algo coefficient setting for one, two, or even multiple
-// TAS2781 chips.
+// TAS2563/TAS2781 chips.
 //
 // Author: Shenghao Ding <shenghao-ding@ti.com>
 // Author: Kevin Lu <kevin-lu@ti.com>
@@ -60,7 +60,8 @@
 #define TASDEVICE_CMD_FIELD_W		0x4
 
 enum audio_device {
-	TAS2781	= 0,
+	TAS2563,
+	TAS2781,
 };
 
 enum device_catlog_id {
@@ -141,6 +142,7 @@ struct tasdevice_priv {
 
 void tas2781_reset(struct tasdevice_priv *tas_dev);
 int tascodec_init(struct tasdevice_priv *tas_priv, void *codec,
+	struct module *module,
 	void (*cont)(const struct firmware *fw, void *context));
 struct tasdevice_priv *tasdevice_kzalloc(struct i2c_client *i2c);
 int tasdevice_init(struct tasdevice_priv *tas_priv);
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 5194b7e6dc8d..450c44c83a5d 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -902,37 +902,6 @@ TRACE_EVENT(afs_dir_check_failed,
 		      __entry->vnode, __entry->off, __entry->i_size)
 	    );
 
-TRACE_EVENT(afs_folio_dirty,
-	    TP_PROTO(struct afs_vnode *vnode, const char *where, struct folio *folio),
-
-	    TP_ARGS(vnode, where, folio),
-
-	    TP_STRUCT__entry(
-		    __field(struct afs_vnode *,		vnode)
-		    __field(const char *,		where)
-		    __field(pgoff_t,			index)
-		    __field(unsigned long,		from)
-		    __field(unsigned long,		to)
-			     ),
-
-	    TP_fast_assign(
-		    unsigned long priv = (unsigned long)folio_get_private(folio);
-		    __entry->vnode = vnode;
-		    __entry->where = where;
-		    __entry->index = folio_index(folio);
-		    __entry->from  = afs_folio_dirty_from(folio, priv);
-		    __entry->to    = afs_folio_dirty_to(folio, priv);
-		    __entry->to   |= (afs_is_folio_dirty_mmapped(priv) ?
-				      (1UL << (BITS_PER_LONG - 1)) : 0);
-			   ),
-
-	    TP_printk("vn=%p %lx %s %lx-%lx%s",
-		      __entry->vnode, __entry->index, __entry->where,
-		      __entry->from,
-		      __entry->to & ~(1UL << (BITS_PER_LONG - 1)),
-		      __entry->to & (1UL << (BITS_PER_LONG - 1)) ? " M" : "")
-	    );
-
 TRACE_EVENT(afs_call_state,
 	    TP_PROTO(struct afs_call *call,
 		     enum afs_call_state from,
@@ -1102,6 +1071,31 @@ TRACE_EVENT(afs_file_error,
 		      __print_symbolic(__entry->where, afs_file_errors))
 	    );
 
+TRACE_EVENT(afs_bulkstat_error,
+	    TP_PROTO(struct afs_operation *op, struct afs_fid *fid, unsigned int index, s32 abort),
+
+	    TP_ARGS(op, fid, index, abort),
+
+	    TP_STRUCT__entry(
+		    __field_struct(struct afs_fid,	fid)
+		    __field(unsigned int,		op)
+		    __field(unsigned int,		index)
+		    __field(s32,			abort)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->op = op->debug_id;
+		    __entry->fid = *fid;
+		    __entry->index = index;
+		    __entry->abort = abort;
+			   ),
+
+	    TP_printk("OP=%08x[%02x] %llx:%llx:%x a=%d",
+		      __entry->op, __entry->index,
+		      __entry->fid.vid, __entry->fid.vnode, __entry->fid.unique,
+		      __entry->abort)
+	    );
+
 TRACE_EVENT(afs_cm_no_server,
 	    TP_PROTO(struct afs_call *call, struct sockaddr_rxrpc *srx),
 
@@ -1195,8 +1189,8 @@ TRACE_EVENT(afs_flock_op,
 		    __entry->from = fl->fl_start;
 		    __entry->len = fl->fl_end - fl->fl_start + 1;
 		    __entry->op = op;
-		    __entry->type = fl->fl_type;
-		    __entry->flags = fl->fl_flags;
+		    __entry->type = fl->c.flc_type;
+		    __entry->flags = fl->c.flc_flags;
 		    __entry->debug_id = fl->fl_u.afs.debug_id;
 			   ),
 
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 65029dfb92fb..a697f4b77162 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -772,15 +772,14 @@ TRACE_EVENT(ext4_mb_release_group_pa,
 );
 
 TRACE_EVENT(ext4_discard_preallocations,
-	TP_PROTO(struct inode *inode, unsigned int len, unsigned int needed),
+	TP_PROTO(struct inode *inode, unsigned int len),
 
-	TP_ARGS(inode, len, needed),
+	TP_ARGS(inode, len),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,		dev		)
 		__field(	ino_t,		ino		)
 		__field(	unsigned int,	len		)
-		__field(	unsigned int,	needed		)
 
 	),
 
@@ -788,13 +787,11 @@ TRACE_EVENT(ext4_discard_preallocations,
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
 		__entry->len	= len;
-		__entry->needed	= needed;
 	),
 
-	TP_printk("dev %d,%d ino %lu len: %u needed %u",
+	TP_printk("dev %d,%d ino %lu len: %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  (unsigned long) __entry->ino, __entry->len,
-		  __entry->needed)
+		  (unsigned long) __entry->ino, __entry->len)
 );
 
 TRACE_EVENT(ext4_mb_discard_preallocations,
diff --git a/include/trace/events/filelock.h b/include/trace/events/filelock.h
index 1646dadd7f37..b8d1e00a7982 100644
--- a/include/trace/events/filelock.h
+++ b/include/trace/events/filelock.h
@@ -68,11 +68,11 @@ DECLARE_EVENT_CLASS(filelock_lock,
 		__field(struct file_lock *, fl)
 		__field(unsigned long, i_ino)
 		__field(dev_t, s_dev)
-		__field(struct file_lock *, fl_blocker)
-		__field(fl_owner_t, fl_owner)
-		__field(unsigned int, fl_pid)
-		__field(unsigned int, fl_flags)
-		__field(unsigned char, fl_type)
+		__field(struct file_lock_core *, blocker)
+		__field(fl_owner_t, owner)
+		__field(unsigned int, pid)
+		__field(unsigned int, flags)
+		__field(unsigned char, type)
 		__field(loff_t, fl_start)
 		__field(loff_t, fl_end)
 		__field(int, ret)
@@ -82,11 +82,11 @@ DECLARE_EVENT_CLASS(filelock_lock,
 		__entry->fl = fl ? fl : NULL;
 		__entry->s_dev = inode->i_sb->s_dev;
 		__entry->i_ino = inode->i_ino;
-		__entry->fl_blocker = fl ? fl->fl_blocker : NULL;
-		__entry->fl_owner = fl ? fl->fl_owner : NULL;
-		__entry->fl_pid = fl ? fl->fl_pid : 0;
-		__entry->fl_flags = fl ? fl->fl_flags : 0;
-		__entry->fl_type = fl ? fl->fl_type : 0;
+		__entry->blocker = fl ? fl->c.flc_blocker : NULL;
+		__entry->owner = fl ? fl->c.flc_owner : NULL;
+		__entry->pid = fl ? fl->c.flc_pid : 0;
+		__entry->flags = fl ? fl->c.flc_flags : 0;
+		__entry->type = fl ? fl->c.flc_type : 0;
 		__entry->fl_start = fl ? fl->fl_start : 0;
 		__entry->fl_end = fl ? fl->fl_end : 0;
 		__entry->ret = ret;
@@ -94,9 +94,9 @@ DECLARE_EVENT_CLASS(filelock_lock,
 
 	TP_printk("fl=%p dev=0x%x:0x%x ino=0x%lx fl_blocker=%p fl_owner=%p fl_pid=%u fl_flags=%s fl_type=%s fl_start=%lld fl_end=%lld ret=%d",
 		__entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
-		__entry->i_ino, __entry->fl_blocker, __entry->fl_owner,
-		__entry->fl_pid, show_fl_flags(__entry->fl_flags),
-		show_fl_type(__entry->fl_type),
+		__entry->i_ino, __entry->blocker, __entry->owner,
+		__entry->pid, show_fl_flags(__entry->flags),
+		show_fl_type(__entry->type),
 		__entry->fl_start, __entry->fl_end, __entry->ret)
 );
 
@@ -117,59 +117,59 @@ DEFINE_EVENT(filelock_lock, flock_lock_inode,
 		TP_ARGS(inode, fl, ret));
 
 DECLARE_EVENT_CLASS(filelock_lease,
-	TP_PROTO(struct inode *inode, struct file_lock *fl),
+	TP_PROTO(struct inode *inode, struct file_lease *fl),
 
 	TP_ARGS(inode, fl),
 
 	TP_STRUCT__entry(
-		__field(struct file_lock *, fl)
+		__field(struct file_lease *, fl)
 		__field(unsigned long, i_ino)
 		__field(dev_t, s_dev)
-		__field(struct file_lock *, fl_blocker)
-		__field(fl_owner_t, fl_owner)
-		__field(unsigned int, fl_flags)
-		__field(unsigned char, fl_type)
-		__field(unsigned long, fl_break_time)
-		__field(unsigned long, fl_downgrade_time)
+		__field(struct file_lock_core *, blocker)
+		__field(fl_owner_t, owner)
+		__field(unsigned int, flags)
+		__field(unsigned char, type)
+		__field(unsigned long, break_time)
+		__field(unsigned long, downgrade_time)
 	),
 
 	TP_fast_assign(
 		__entry->fl = fl ? fl : NULL;
 		__entry->s_dev = inode->i_sb->s_dev;
 		__entry->i_ino = inode->i_ino;
-		__entry->fl_blocker = fl ? fl->fl_blocker : NULL;
-		__entry->fl_owner = fl ? fl->fl_owner : NULL;
-		__entry->fl_flags = fl ? fl->fl_flags : 0;
-		__entry->fl_type = fl ? fl->fl_type : 0;
-		__entry->fl_break_time = fl ? fl->fl_break_time : 0;
-		__entry->fl_downgrade_time = fl ? fl->fl_downgrade_time : 0;
+		__entry->blocker = fl ? fl->c.flc_blocker : NULL;
+		__entry->owner = fl ? fl->c.flc_owner : NULL;
+		__entry->flags = fl ? fl->c.flc_flags : 0;
+		__entry->type = fl ? fl->c.flc_type : 0;
+		__entry->break_time = fl ? fl->fl_break_time : 0;
+		__entry->downgrade_time = fl ? fl->fl_downgrade_time : 0;
 	),
 
 	TP_printk("fl=%p dev=0x%x:0x%x ino=0x%lx fl_blocker=%p fl_owner=%p fl_flags=%s fl_type=%s fl_break_time=%lu fl_downgrade_time=%lu",
 		__entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
-		__entry->i_ino, __entry->fl_blocker, __entry->fl_owner,
-		show_fl_flags(__entry->fl_flags),
-		show_fl_type(__entry->fl_type),
-		__entry->fl_break_time, __entry->fl_downgrade_time)
+		__entry->i_ino, __entry->blocker, __entry->owner,
+		show_fl_flags(__entry->flags),
+		show_fl_type(__entry->type),
+		__entry->break_time, __entry->downgrade_time)
 );
 
-DEFINE_EVENT(filelock_lease, break_lease_noblock, TP_PROTO(struct inode *inode, struct file_lock *fl),
+DEFINE_EVENT(filelock_lease, break_lease_noblock, TP_PROTO(struct inode *inode, struct file_lease *fl),
 		TP_ARGS(inode, fl));
 
-DEFINE_EVENT(filelock_lease, break_lease_block, TP_PROTO(struct inode *inode, struct file_lock *fl),
+DEFINE_EVENT(filelock_lease, break_lease_block, TP_PROTO(struct inode *inode, struct file_lease *fl),
 		TP_ARGS(inode, fl));
 
-DEFINE_EVENT(filelock_lease, break_lease_unblock, TP_PROTO(struct inode *inode, struct file_lock *fl),
+DEFINE_EVENT(filelock_lease, break_lease_unblock, TP_PROTO(struct inode *inode, struct file_lease *fl),
 		TP_ARGS(inode, fl));
 
-DEFINE_EVENT(filelock_lease, generic_delete_lease, TP_PROTO(struct inode *inode, struct file_lock *fl),
+DEFINE_EVENT(filelock_lease, generic_delete_lease, TP_PROTO(struct inode *inode, struct file_lease *fl),
 		TP_ARGS(inode, fl));
 
-DEFINE_EVENT(filelock_lease, time_out_leases, TP_PROTO(struct inode *inode, struct file_lock *fl),
+DEFINE_EVENT(filelock_lease, time_out_leases, TP_PROTO(struct inode *inode, struct file_lease *fl),
 		TP_ARGS(inode, fl));
 
 TRACE_EVENT(generic_add_lease,
-	TP_PROTO(struct inode *inode, struct file_lock *fl),
+	TP_PROTO(struct inode *inode, struct file_lease *fl),
 
 	TP_ARGS(inode, fl),
 
@@ -179,9 +179,9 @@ TRACE_EVENT(generic_add_lease,
 		__field(int, rcount)
 		__field(int, icount)
 		__field(dev_t, s_dev)
-		__field(fl_owner_t, fl_owner)
-		__field(unsigned int, fl_flags)
-		__field(unsigned char, fl_type)
+		__field(fl_owner_t, owner)
+		__field(unsigned int, flags)
+		__field(unsigned char, type)
 	),
 
 	TP_fast_assign(
@@ -190,21 +190,21 @@ TRACE_EVENT(generic_add_lease,
 		__entry->wcount = atomic_read(&inode->i_writecount);
 		__entry->rcount = atomic_read(&inode->i_readcount);
 		__entry->icount = atomic_read(&inode->i_count);
-		__entry->fl_owner = fl->fl_owner;
-		__entry->fl_flags = fl->fl_flags;
-		__entry->fl_type = fl->fl_type;
+		__entry->owner = fl->c.flc_owner;
+		__entry->flags = fl->c.flc_flags;
+		__entry->type = fl->c.flc_type;
 	),
 
 	TP_printk("dev=0x%x:0x%x ino=0x%lx wcount=%d rcount=%d icount=%d fl_owner=%p fl_flags=%s fl_type=%s",
 		MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
 		__entry->i_ino, __entry->wcount, __entry->rcount,
-		__entry->icount, __entry->fl_owner,
-		show_fl_flags(__entry->fl_flags),
-		show_fl_type(__entry->fl_type))
+		__entry->icount, __entry->owner,
+		show_fl_flags(__entry->flags),
+		show_fl_type(__entry->type))
 );
 
 TRACE_EVENT(leases_conflict,
-	TP_PROTO(bool conflict, struct file_lock *lease, struct file_lock *breaker),
+	TP_PROTO(bool conflict, struct file_lease *lease, struct file_lease *breaker),
 
 	TP_ARGS(conflict, lease, breaker),
 
@@ -220,11 +220,11 @@ TRACE_EVENT(leases_conflict,
 
 	TP_fast_assign(
 		__entry->lease = lease;
-		__entry->l_fl_flags = lease->fl_flags;
-		__entry->l_fl_type = lease->fl_type;
+		__entry->l_fl_flags = lease->c.flc_flags;
+		__entry->l_fl_type = lease->c.flc_type;
 		__entry->breaker = breaker;
-		__entry->b_fl_flags = breaker->fl_flags;
-		__entry->b_fl_type = breaker->fl_type;
+		__entry->b_fl_flags = breaker->c.flc_flags;
+		__entry->b_fl_type = breaker->c.flc_type;
 		__entry->conflict = conflict;
 	),
 
diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h
index 69454f1f98b0..e948df7ce625 100644
--- a/include/trace/events/io_uring.h
+++ b/include/trace/events/io_uring.h
@@ -148,7 +148,7 @@ TRACE_EVENT(io_uring_queue_async_work,
 		__field(  void *,			req		)
 		__field(  u64,				user_data	)
 		__field(  u8,				opcode		)
-		__field(  unsigned int,			flags		)
+		__field(  unsigned long long,		flags		)
 		__field(  struct io_wq_work *,		work		)
 		__field(  int,				rw		)
 
@@ -159,7 +159,7 @@ TRACE_EVENT(io_uring_queue_async_work,
 		__entry->ctx		= req->ctx;
 		__entry->req		= req;
 		__entry->user_data	= req->cqe.user_data;
-		__entry->flags		= req->flags;
+		__entry->flags		= (__force unsigned long long) req->flags;
 		__entry->opcode		= req->opcode;
 		__entry->work		= &req->work;
 		__entry->rw		= rw;
@@ -167,10 +167,10 @@ TRACE_EVENT(io_uring_queue_async_work,
 		__assign_str(op_str, io_uring_get_opcode(req->opcode));
 	),
 
-	TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, flags 0x%x, %s queue, work %p",
+	TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, flags 0x%llx, %s queue, work %p",
 		__entry->ctx, __entry->req, __entry->user_data,
-		__get_str(op_str),
-		__entry->flags, __entry->rw ? "hashed" : "normal", __entry->work)
+		__get_str(op_str), __entry->flags,
+		__entry->rw ? "hashed" : "normal", __entry->work)
 );
 
 /**
@@ -378,7 +378,7 @@ TRACE_EVENT(io_uring_submit_req,
 		__field(  void *,		req		)
 		__field(  unsigned long long,	user_data	)
 		__field(  u8,			opcode		)
-		__field(  u32,			flags		)
+		__field(  unsigned long long,	flags		)
 		__field(  bool,			sq_thread	)
 
 		__string( op_str, io_uring_get_opcode(req->opcode) )
@@ -389,16 +389,16 @@ TRACE_EVENT(io_uring_submit_req,
 		__entry->req		= req;
 		__entry->user_data	= req->cqe.user_data;
 		__entry->opcode		= req->opcode;
-		__entry->flags		= req->flags;
+		__entry->flags		= (__force unsigned long long) req->flags;
 		__entry->sq_thread	= req->ctx->flags & IORING_SETUP_SQPOLL;
 
 		__assign_str(op_str, io_uring_get_opcode(req->opcode));
 	),
 
-	TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, flags 0x%x, "
+	TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, flags 0x%llx, "
 		  "sq_thread %d", __entry->ctx, __entry->req,
-		  __entry->user_data, __get_str(op_str),
-		  __entry->flags, __entry->sq_thread)
+		  __entry->user_data, __get_str(op_str), __entry->flags,
+		  __entry->sq_thread)
 );
 
 /*
@@ -602,29 +602,25 @@ TRACE_EVENT(io_uring_cqe_overflow,
  *
  * @tctx:		pointer to a io_uring_task
  * @count:		how many functions it ran
- * @loops:		how many loops it ran
  *
  */
 TRACE_EVENT(io_uring_task_work_run,
 
-	TP_PROTO(void *tctx, unsigned int count, unsigned int loops),
+	TP_PROTO(void *tctx, unsigned int count),
 
-	TP_ARGS(tctx, count, loops),
+	TP_ARGS(tctx, count),
 
 	TP_STRUCT__entry (
 		__field(  void *,		tctx		)
 		__field(  unsigned int,		count		)
-		__field(  unsigned int,		loops		)
 	),
 
 	TP_fast_assign(
 		__entry->tctx		= tctx;
 		__entry->count		= count;
-		__entry->loops		= loops;
 	),
 
-	TP_printk("tctx %p, count %u, loops %u",
-		 __entry->tctx, __entry->count, __entry->loops)
+	TP_printk("tctx %p, count %u", __entry->tctx, __entry->count)
 );
 
 TRACE_EVENT(io_uring_short_write,
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 3bd31ea23fee..011fba6b5552 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -62,7 +62,7 @@ TRACE_EVENT(kvm_vcpu_wakeup,
 		  __entry->valid ? "valid" : "invalid")
 );
 
-#if defined(CONFIG_HAVE_KVM_IRQFD)
+#if defined(CONFIG_HAVE_KVM_IRQCHIP)
 TRACE_EVENT(kvm_set_irq,
 	TP_PROTO(unsigned int gsi, int level, int irq_source_id),
 	TP_ARGS(gsi, level, irq_source_id),
@@ -82,7 +82,7 @@ TRACE_EVENT(kvm_set_irq,
 	TP_printk("gsi %u level %d source %d",
 		  __entry->gsi, __entry->level, __entry->irq_source_id)
 );
-#endif /* defined(CONFIG_HAVE_KVM_IRQFD) */
+#endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */
 
 #if defined(__KVM_HAVE_IOAPIC)
 #define kvm_deliver_mode		\
@@ -170,7 +170,7 @@ TRACE_EVENT(kvm_msi_set_irq,
 
 #endif /* defined(__KVM_HAVE_IOAPIC) */
 
-#if defined(CONFIG_HAVE_KVM_IRQFD)
+#if defined(CONFIG_HAVE_KVM_IRQCHIP)
 
 #ifdef kvm_irqchips
 #define kvm_ack_irq_string "irqchip %s pin %u"
@@ -197,7 +197,7 @@ TRACE_EVENT(kvm_ack_irq,
 	TP_printk(kvm_ack_irq_string, kvm_ack_irq_parm)
 );
 
-#endif /* defined(CONFIG_HAVE_KVM_IRQFD) */
+#endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */
 
 
 
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index beec534cbaab..447a8c21cf57 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -16,34 +16,57 @@
  * Define enums for tracing information.
  */
 #define netfs_read_traces					\
+	EM(netfs_read_trace_dio_read,		"DIO-READ ")	\
 	EM(netfs_read_trace_expanded,		"EXPANDED ")	\
 	EM(netfs_read_trace_readahead,		"READAHEAD")	\
 	EM(netfs_read_trace_readpage,		"READPAGE ")	\
+	EM(netfs_read_trace_prefetch_for_write,	"PREFETCHW")	\
 	E_(netfs_read_trace_write_begin,	"WRITEBEGN")
 
+#define netfs_write_traces					\
+	EM(netfs_write_trace_dio_write,		"DIO-WRITE")	\
+	EM(netfs_write_trace_launder,		"LAUNDER  ")	\
+	EM(netfs_write_trace_unbuffered_write,	"UNB-WRITE")	\
+	EM(netfs_write_trace_writeback,		"WRITEBACK")	\
+	E_(netfs_write_trace_writethrough,	"WRITETHRU")
+
 #define netfs_rreq_origins					\
 	EM(NETFS_READAHEAD,			"RA")		\
 	EM(NETFS_READPAGE,			"RP")		\
-	E_(NETFS_READ_FOR_WRITE,		"RW")
+	EM(NETFS_READ_FOR_WRITE,		"RW")		\
+	EM(NETFS_WRITEBACK,			"WB")		\
+	EM(NETFS_WRITETHROUGH,			"WT")		\
+	EM(NETFS_LAUNDER_WRITE,			"LW")		\
+	EM(NETFS_UNBUFFERED_WRITE,		"UW")		\
+	EM(NETFS_DIO_READ,			"DR")		\
+	E_(NETFS_DIO_WRITE,			"DW")
 
 #define netfs_rreq_traces					\
 	EM(netfs_rreq_trace_assess,		"ASSESS ")	\
 	EM(netfs_rreq_trace_copy,		"COPY   ")	\
 	EM(netfs_rreq_trace_done,		"DONE   ")	\
 	EM(netfs_rreq_trace_free,		"FREE   ")	\
+	EM(netfs_rreq_trace_redirty,		"REDIRTY")	\
 	EM(netfs_rreq_trace_resubmit,		"RESUBMT")	\
 	EM(netfs_rreq_trace_unlock,		"UNLOCK ")	\
-	E_(netfs_rreq_trace_unmark,		"UNMARK ")
+	EM(netfs_rreq_trace_unmark,		"UNMARK ")	\
+	EM(netfs_rreq_trace_wait_ip,		"WAIT-IP")	\
+	EM(netfs_rreq_trace_wake_ip,		"WAKE-IP")	\
+	E_(netfs_rreq_trace_write_done,		"WR-DONE")
 
 #define netfs_sreq_sources					\
 	EM(NETFS_FILL_WITH_ZEROES,		"ZERO")		\
 	EM(NETFS_DOWNLOAD_FROM_SERVER,		"DOWN")		\
 	EM(NETFS_READ_FROM_CACHE,		"READ")		\
-	E_(NETFS_INVALID_READ,			"INVL")		\
+	EM(NETFS_INVALID_READ,			"INVL")		\
+	EM(NETFS_UPLOAD_TO_SERVER,		"UPLD")		\
+	EM(NETFS_WRITE_TO_CACHE,		"WRIT")		\
+	E_(NETFS_INVALID_WRITE,			"INVL")
 
 #define netfs_sreq_traces					\
 	EM(netfs_sreq_trace_download_instead,	"RDOWN")	\
 	EM(netfs_sreq_trace_free,		"FREE ")	\
+	EM(netfs_sreq_trace_limited,		"LIMIT")	\
 	EM(netfs_sreq_trace_prepare,		"PREP ")	\
 	EM(netfs_sreq_trace_resubmit_short,	"SHORT")	\
 	EM(netfs_sreq_trace_submit,		"SUBMT")	\
@@ -55,19 +78,24 @@
 #define netfs_failures							\
 	EM(netfs_fail_check_write_begin,	"check-write-begin")	\
 	EM(netfs_fail_copy_to_cache,		"copy-to-cache")	\
+	EM(netfs_fail_dio_read_short,		"dio-read-short")	\
+	EM(netfs_fail_dio_read_zero,		"dio-read-zero")	\
 	EM(netfs_fail_read,			"read")			\
 	EM(netfs_fail_short_read,		"short-read")		\
-	E_(netfs_fail_prepare_write,		"prep-write")
+	EM(netfs_fail_prepare_write,		"prep-write")		\
+	E_(netfs_fail_write,			"write")
 
 #define netfs_rreq_ref_traces					\
-	EM(netfs_rreq_trace_get_hold,		"GET HOLD   ")	\
+	EM(netfs_rreq_trace_get_for_outstanding,"GET OUTSTND")	\
 	EM(netfs_rreq_trace_get_subreq,		"GET SUBREQ ")	\
 	EM(netfs_rreq_trace_put_complete,	"PUT COMPLT ")	\
 	EM(netfs_rreq_trace_put_discard,	"PUT DISCARD")	\
 	EM(netfs_rreq_trace_put_failed,		"PUT FAILED ")	\
-	EM(netfs_rreq_trace_put_hold,		"PUT HOLD   ")	\
+	EM(netfs_rreq_trace_put_no_submit,	"PUT NO-SUBM")	\
+	EM(netfs_rreq_trace_put_return,		"PUT RETURN ")	\
 	EM(netfs_rreq_trace_put_subreq,		"PUT SUBREQ ")	\
-	EM(netfs_rreq_trace_put_zero_len,	"PUT ZEROLEN")	\
+	EM(netfs_rreq_trace_put_work,		"PUT WORK   ")	\
+	EM(netfs_rreq_trace_see_work,		"SEE WORK   ")	\
 	E_(netfs_rreq_trace_new,		"NEW        ")
 
 #define netfs_sreq_ref_traces					\
@@ -76,11 +104,44 @@
 	EM(netfs_sreq_trace_get_short_read,	"GET SHORTRD")	\
 	EM(netfs_sreq_trace_new,		"NEW        ")	\
 	EM(netfs_sreq_trace_put_clear,		"PUT CLEAR  ")	\
+	EM(netfs_sreq_trace_put_discard,	"PUT DISCARD")	\
 	EM(netfs_sreq_trace_put_failed,		"PUT FAILED ")	\
 	EM(netfs_sreq_trace_put_merged,		"PUT MERGED ")	\
 	EM(netfs_sreq_trace_put_no_copy,	"PUT NO COPY")	\
+	EM(netfs_sreq_trace_put_wip,		"PUT WIP    ")	\
+	EM(netfs_sreq_trace_put_work,		"PUT WORK   ")	\
 	E_(netfs_sreq_trace_put_terminated,	"PUT TERM   ")
 
+#define netfs_folio_traces					\
+	/* The first few correspond to enum netfs_how_to_modify */	\
+	EM(netfs_folio_is_uptodate,		"mod-uptodate")	\
+	EM(netfs_just_prefetch,			"mod-prefetch")	\
+	EM(netfs_whole_folio_modify,		"mod-whole-f")	\
+	EM(netfs_modify_and_clear,		"mod-n-clear")	\
+	EM(netfs_streaming_write,		"mod-streamw")	\
+	EM(netfs_streaming_write_cont,		"mod-streamw+")	\
+	EM(netfs_flush_content,			"flush")	\
+	EM(netfs_streaming_filled_page,		"mod-streamw-f") \
+	EM(netfs_streaming_cont_filled_page,	"mod-streamw-f+") \
+	/* The rest are for writeback */			\
+	EM(netfs_folio_trace_clear,		"clear")	\
+	EM(netfs_folio_trace_clear_s,		"clear-s")	\
+	EM(netfs_folio_trace_clear_g,		"clear-g")	\
+	EM(netfs_folio_trace_copy_to_cache,	"copy")		\
+	EM(netfs_folio_trace_end_copy,		"end-copy")	\
+	EM(netfs_folio_trace_filled_gaps,	"filled-gaps")	\
+	EM(netfs_folio_trace_kill,		"kill")		\
+	EM(netfs_folio_trace_launder,		"launder")	\
+	EM(netfs_folio_trace_mkwrite,		"mkwrite")	\
+	EM(netfs_folio_trace_mkwrite_plus,	"mkwrite+")	\
+	EM(netfs_folio_trace_read_gaps,		"read-gaps")	\
+	EM(netfs_folio_trace_redirty,		"redirty")	\
+	EM(netfs_folio_trace_redirtied,		"redirtied")	\
+	EM(netfs_folio_trace_store,		"store")	\
+	EM(netfs_folio_trace_store_plus,	"store+")	\
+	EM(netfs_folio_trace_wthru,		"wthru")	\
+	E_(netfs_folio_trace_wthru_plus,	"wthru+")
+
 #ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY
 #define __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY
 
@@ -90,11 +151,13 @@
 #define E_(a, b) a
 
 enum netfs_read_trace { netfs_read_traces } __mode(byte);
+enum netfs_write_trace { netfs_write_traces } __mode(byte);
 enum netfs_rreq_trace { netfs_rreq_traces } __mode(byte);
 enum netfs_sreq_trace { netfs_sreq_traces } __mode(byte);
 enum netfs_failure { netfs_failures } __mode(byte);
 enum netfs_rreq_ref_trace { netfs_rreq_ref_traces } __mode(byte);
 enum netfs_sreq_ref_trace { netfs_sreq_ref_traces } __mode(byte);
+enum netfs_folio_trace { netfs_folio_traces } __mode(byte);
 
 #endif
 
@@ -107,6 +170,7 @@ enum netfs_sreq_ref_trace { netfs_sreq_ref_traces } __mode(byte);
 #define E_(a, b) TRACE_DEFINE_ENUM(a);
 
 netfs_read_traces;
+netfs_write_traces;
 netfs_rreq_origins;
 netfs_rreq_traces;
 netfs_sreq_sources;
@@ -114,6 +178,7 @@ netfs_sreq_traces;
 netfs_failures;
 netfs_rreq_ref_traces;
 netfs_sreq_ref_traces;
+netfs_folio_traces;
 
 /*
  * Now redefine the EM() and E_() macros to map the enums to the strings that
@@ -314,6 +379,82 @@ TRACE_EVENT(netfs_sreq_ref,
 		      __entry->ref)
 	    );
 
+TRACE_EVENT(netfs_folio,
+	    TP_PROTO(struct folio *folio, enum netfs_folio_trace why),
+
+	    TP_ARGS(folio, why),
+
+	    TP_STRUCT__entry(
+		    __field(ino_t,			ino)
+		    __field(pgoff_t,			index)
+		    __field(unsigned int,		nr)
+		    __field(enum netfs_folio_trace,	why)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->ino = folio->mapping->host->i_ino;
+		    __entry->why = why;
+		    __entry->index = folio_index(folio);
+		    __entry->nr = folio_nr_pages(folio);
+			   ),
+
+	    TP_printk("i=%05lx ix=%05lx-%05lx %s",
+		      __entry->ino, __entry->index, __entry->index + __entry->nr - 1,
+		      __print_symbolic(__entry->why, netfs_folio_traces))
+	    );
+
+TRACE_EVENT(netfs_write_iter,
+	    TP_PROTO(const struct kiocb *iocb, const struct iov_iter *from),
+
+	    TP_ARGS(iocb, from),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned long long,		start		)
+		    __field(size_t,			len		)
+		    __field(unsigned int,		flags		)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->start	= iocb->ki_pos;
+		    __entry->len	= iov_iter_count(from);
+		    __entry->flags	= iocb->ki_flags;
+			   ),
+
+	    TP_printk("WRITE-ITER s=%llx l=%zx f=%x",
+		      __entry->start, __entry->len, __entry->flags)
+	    );
+
+TRACE_EVENT(netfs_write,
+	    TP_PROTO(const struct netfs_io_request *wreq,
+		     enum netfs_write_trace what),
+
+	    TP_ARGS(wreq, what),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		wreq		)
+		    __field(unsigned int,		cookie		)
+		    __field(enum netfs_write_trace,	what		)
+		    __field(unsigned long long,		start		)
+		    __field(size_t,			len		)
+			     ),
+
+	    TP_fast_assign(
+		    struct netfs_inode *__ctx = netfs_inode(wreq->inode);
+		    struct fscache_cookie *__cookie = netfs_i_cookie(__ctx);
+		    __entry->wreq	= wreq->debug_id;
+		    __entry->cookie	= __cookie ? __cookie->debug_id : 0;
+		    __entry->what	= what;
+		    __entry->start	= wreq->start;
+		    __entry->len	= wreq->len;
+			   ),
+
+	    TP_printk("R=%08x %s c=%08x by=%llx-%llx",
+		      __entry->wreq,
+		      __print_symbolic(__entry->what, netfs_write_traces),
+		      __entry->cookie,
+		      __entry->start, __entry->start + __entry->len - 1)
+	    );
+
 #undef EM
 #undef E_
 #endif /* _TRACE_NETFS_H */
diff --git a/include/trace/events/qdisc.h b/include/trace/events/qdisc.h
index a3995925cb05..1f4258308b96 100644
--- a/include/trace/events/qdisc.h
+++ b/include/trace/events/qdisc.h
@@ -81,14 +81,14 @@ TRACE_EVENT(qdisc_reset,
 	TP_ARGS(q),
 
 	TP_STRUCT__entry(
-		__string(	dev,		qdisc_dev(q)	)
-		__string(	kind,		q->ops->id	)
-		__field(	u32,		parent		)
-		__field(	u32,		handle		)
+		__string(	dev,		qdisc_dev(q)->name	)
+		__string(	kind,		q->ops->id		)
+		__field(	u32,		parent			)
+		__field(	u32,		handle			)
 	),
 
 	TP_fast_assign(
-		__assign_str(dev, qdisc_dev(q));
+		__assign_str(dev, qdisc_dev(q)->name);
 		__assign_str(kind, q->ops->id);
 		__entry->parent = q->parent;
 		__entry->handle = q->handle;
@@ -106,14 +106,14 @@ TRACE_EVENT(qdisc_destroy,
 	TP_ARGS(q),
 
 	TP_STRUCT__entry(
-		__string(	dev,		qdisc_dev(q)	)
-		__string(	kind,		q->ops->id	)
-		__field(	u32,		parent		)
-		__field(	u32,		handle		)
+		__string(	dev,		qdisc_dev(q)->name	)
+		__string(	kind,		q->ops->id		)
+		__field(	u32,		parent			)
+		__field(	u32,		handle			)
 	),
 
 	TP_fast_assign(
-		__assign_str(dev, qdisc_dev(q));
+		__assign_str(dev, qdisc_dev(q)->name);
 		__assign_str(kind, q->ops->id);
 		__entry->parent = q->parent;
 		__entry->handle = q->handle;
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 4c1ef7b3705c..87b8de9b6c1c 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -128,6 +128,7 @@
 	EM(rxrpc_skb_eaten_by_unshare_nomem,	"ETN unshar-nm") \
 	EM(rxrpc_skb_get_conn_secured,		"GET conn-secd") \
 	EM(rxrpc_skb_get_conn_work,		"GET conn-work") \
+	EM(rxrpc_skb_get_last_nack,		"GET last-nack") \
 	EM(rxrpc_skb_get_local_work,		"GET locl-work") \
 	EM(rxrpc_skb_get_reject_work,		"GET rej-work ") \
 	EM(rxrpc_skb_get_to_recvmsg,		"GET to-recv  ") \
@@ -141,6 +142,7 @@
 	EM(rxrpc_skb_put_error_report,		"PUT error-rep") \
 	EM(rxrpc_skb_put_input,			"PUT input    ") \
 	EM(rxrpc_skb_put_jumbo_subpacket,	"PUT jumbo-sub") \
+	EM(rxrpc_skb_put_last_nack,		"PUT last-nack") \
 	EM(rxrpc_skb_put_purge,			"PUT purge    ") \
 	EM(rxrpc_skb_put_rotate,		"PUT rotate   ") \
 	EM(rxrpc_skb_put_unknown,		"PUT unknown  ") \
@@ -1552,7 +1554,7 @@ TRACE_EVENT(rxrpc_congest,
 		    memcpy(&__entry->sum, summary, sizeof(__entry->sum));
 			   ),
 
-	    TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u nA=%u,%u+%u r=%u b=%u u=%u d=%u l=%x%s%s%s",
+	    TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u nA=%u,%u+%u,%u b=%u u=%u d=%u l=%x%s%s%s",
 		      __entry->call,
 		      __entry->ack_serial,
 		      __print_symbolic(__entry->sum.ack_reason, rxrpc_ack_names),
@@ -1560,9 +1562,9 @@ TRACE_EVENT(rxrpc_congest,
 		      __print_symbolic(__entry->sum.mode, rxrpc_congest_modes),
 		      __entry->sum.cwnd,
 		      __entry->sum.ssthresh,
-		      __entry->sum.nr_acks, __entry->sum.saw_nacks,
+		      __entry->sum.nr_acks, __entry->sum.nr_retained_nacks,
 		      __entry->sum.nr_new_acks,
-		      __entry->sum.nr_rot_new_acks,
+		      __entry->sum.nr_new_nacks,
 		      __entry->top - __entry->hard_ack,
 		      __entry->sum.cumulative_acks,
 		      __entry->sum.dup_acks,
diff --git a/include/uapi/drm/ivpu_accel.h b/include/uapi/drm/ivpu_accel.h
index de1944e42c65..19a13468eca5 100644
--- a/include/uapi/drm/ivpu_accel.h
+++ b/include/uapi/drm/ivpu_accel.h
@@ -53,7 +53,7 @@ extern "C" {
 #define DRM_IVPU_PARAM_CORE_CLOCK_RATE	    3
 #define DRM_IVPU_PARAM_NUM_CONTEXTS	    4
 #define DRM_IVPU_PARAM_CONTEXT_BASE_ADDRESS 5
-#define DRM_IVPU_PARAM_CONTEXT_PRIORITY	    6
+#define DRM_IVPU_PARAM_CONTEXT_PRIORITY	    6 /* Deprecated */
 #define DRM_IVPU_PARAM_CONTEXT_ID	    7
 #define DRM_IVPU_PARAM_FW_API_VERSION	    8
 #define DRM_IVPU_PARAM_ENGINE_HEARTBEAT	    9
@@ -64,11 +64,18 @@ extern "C" {
 
 #define DRM_IVPU_PLATFORM_TYPE_SILICON	    0
 
+/* Deprecated, use DRM_IVPU_JOB_PRIORITY */
 #define DRM_IVPU_CONTEXT_PRIORITY_IDLE	    0
 #define DRM_IVPU_CONTEXT_PRIORITY_NORMAL    1
 #define DRM_IVPU_CONTEXT_PRIORITY_FOCUS	    2
 #define DRM_IVPU_CONTEXT_PRIORITY_REALTIME  3
 
+#define DRM_IVPU_JOB_PRIORITY_DEFAULT  0
+#define DRM_IVPU_JOB_PRIORITY_IDLE     1
+#define DRM_IVPU_JOB_PRIORITY_NORMAL   2
+#define DRM_IVPU_JOB_PRIORITY_FOCUS    3
+#define DRM_IVPU_JOB_PRIORITY_REALTIME 4
+
 /**
  * DRM_IVPU_CAP_METRIC_STREAMER
  *
@@ -112,10 +119,6 @@ struct drm_ivpu_param {
 	 * %DRM_IVPU_PARAM_CONTEXT_BASE_ADDRESS:
 	 * Lowest VPU virtual address available in the current context (read-only)
 	 *
-	 * %DRM_IVPU_PARAM_CONTEXT_PRIORITY:
-	 * Value of current context scheduling priority (read-write).
-	 * See DRM_IVPU_CONTEXT_PRIORITY_* for possible values.
-	 *
 	 * %DRM_IVPU_PARAM_CONTEXT_ID:
 	 * Current context ID, always greater than 0 (read-only)
 	 *
@@ -286,10 +289,23 @@ struct drm_ivpu_submit {
 	 * to be executed. The offset has to be 8-byte aligned.
 	 */
 	__u32 commands_offset;
+
+	/**
+	 * @priority:
+	 *
+	 * Priority to be set for related job command queue, can be one of the following:
+	 * %DRM_IVPU_JOB_PRIORITY_DEFAULT
+	 * %DRM_IVPU_JOB_PRIORITY_IDLE
+	 * %DRM_IVPU_JOB_PRIORITY_NORMAL
+	 * %DRM_IVPU_JOB_PRIORITY_FOCUS
+	 * %DRM_IVPU_JOB_PRIORITY_REALTIME
+	 */
+	__u32 priority;
 };
 
 /* drm_ivpu_bo_wait job status codes */
 #define DRM_IVPU_JOB_STATUS_SUCCESS 0
+#define DRM_IVPU_JOB_STATUS_ABORTED 256
 
 /**
  * struct drm_ivpu_bo_wait - Wait for BO to become inactive
diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h
index 0bade1592f34..77d7ff0d5b11 100644
--- a/include/uapi/drm/nouveau_drm.h
+++ b/include/uapi/drm/nouveau_drm.h
@@ -54,6 +54,20 @@ extern "C" {
  */
 #define NOUVEAU_GETPARAM_EXEC_PUSH_MAX   17
 
+/*
+ * NOUVEAU_GETPARAM_VRAM_BAR_SIZE - query bar size
+ *
+ * Query the VRAM BAR size.
+ */
+#define NOUVEAU_GETPARAM_VRAM_BAR_SIZE 18
+
+/*
+ * NOUVEAU_GETPARAM_VRAM_USED
+ *
+ * Get remaining VRAM size.
+ */
+#define NOUVEAU_GETPARAM_VRAM_USED 19
+
 struct drm_nouveau_getparam {
 	__u64 param;
 	__u64 value;
diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
index 9fa3ae324731..bb0c8a994116 100644
--- a/include/uapi/drm/xe_drm.h
+++ b/include/uapi/drm/xe_drm.h
@@ -831,11 +831,6 @@ struct drm_xe_vm_destroy {
  *  - %DRM_XE_VM_BIND_OP_PREFETCH
  *
  * and the @flags can be:
- *  - %DRM_XE_VM_BIND_FLAG_READONLY
- *  - %DRM_XE_VM_BIND_FLAG_ASYNC
- *  - %DRM_XE_VM_BIND_FLAG_IMMEDIATE - Valid on a faulting VM only, do the
- *    MAP operation immediately rather than deferring the MAP to the page
- *    fault handler.
  *  - %DRM_XE_VM_BIND_FLAG_NULL - When the NULL flag is set, the page
  *    tables are setup with a special bit which indicates writes are
  *    dropped and all reads return zero. In the future, the NULL flags
@@ -928,9 +923,8 @@ struct drm_xe_vm_bind_op {
 	/** @op: Bind operation to perform */
 	__u32 op;
 
-#define DRM_XE_VM_BIND_FLAG_READONLY	(1 << 0)
-#define DRM_XE_VM_BIND_FLAG_IMMEDIATE	(1 << 1)
 #define DRM_XE_VM_BIND_FLAG_NULL	(1 << 2)
+#define DRM_XE_VM_BIND_FLAG_DUMPABLE	(1 << 3)
 	/** @flags: Bind flags */
 	__u32 flags;
 
@@ -1045,20 +1039,6 @@ struct drm_xe_exec_queue_create {
 #define DRM_XE_EXEC_QUEUE_EXTENSION_SET_PROPERTY		0
 #define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY		0
 #define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE		1
-#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_PREEMPTION_TIMEOUT	2
-#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_PERSISTENCE		3
-#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_JOB_TIMEOUT		4
-#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_TRIGGER		5
-#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_NOTIFY		6
-#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_GRANULARITY	7
-/* Monitor 128KB contiguous region with 4K sub-granularity */
-#define     DRM_XE_ACC_GRANULARITY_128K				0
-/* Monitor 2MB contiguous region with 64KB sub-granularity */
-#define     DRM_XE_ACC_GRANULARITY_2M				1
-/* Monitor 16MB contiguous region with 512KB sub-granularity */
-#define     DRM_XE_ACC_GRANULARITY_16M				2
-/* Monitor 64MB contiguous region with 2M sub-granularity */
-#define     DRM_XE_ACC_GRANULARITY_64M				3
 
 	/** @extensions: Pointer to the first extension struct, if any */
 	__u64 extensions;
diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h
index 5f636b5afcd7..d44a8118b2ed 100644
--- a/include/uapi/linux/android/binder.h
+++ b/include/uapi/linux/android/binder.h
@@ -251,20 +251,22 @@ struct binder_extended_error {
 	__s32	param;
 };
 
-#define BINDER_WRITE_READ		_IOWR('b', 1, struct binder_write_read)
-#define BINDER_SET_IDLE_TIMEOUT		_IOW('b', 3, __s64)
-#define BINDER_SET_MAX_THREADS		_IOW('b', 5, __u32)
-#define BINDER_SET_IDLE_PRIORITY	_IOW('b', 6, __s32)
-#define BINDER_SET_CONTEXT_MGR		_IOW('b', 7, __s32)
-#define BINDER_THREAD_EXIT		_IOW('b', 8, __s32)
-#define BINDER_VERSION			_IOWR('b', 9, struct binder_version)
-#define BINDER_GET_NODE_DEBUG_INFO	_IOWR('b', 11, struct binder_node_debug_info)
-#define BINDER_GET_NODE_INFO_FOR_REF	_IOWR('b', 12, struct binder_node_info_for_ref)
-#define BINDER_SET_CONTEXT_MGR_EXT	_IOW('b', 13, struct flat_binder_object)
-#define BINDER_FREEZE			_IOW('b', 14, struct binder_freeze_info)
-#define BINDER_GET_FROZEN_INFO		_IOWR('b', 15, struct binder_frozen_status_info)
-#define BINDER_ENABLE_ONEWAY_SPAM_DETECTION	_IOW('b', 16, __u32)
-#define BINDER_GET_EXTENDED_ERROR	_IOWR('b', 17, struct binder_extended_error)
+enum {
+	BINDER_WRITE_READ		= _IOWR('b', 1, struct binder_write_read),
+	BINDER_SET_IDLE_TIMEOUT		= _IOW('b', 3, __s64),
+	BINDER_SET_MAX_THREADS		= _IOW('b', 5, __u32),
+	BINDER_SET_IDLE_PRIORITY	= _IOW('b', 6, __s32),
+	BINDER_SET_CONTEXT_MGR		= _IOW('b', 7, __s32),
+	BINDER_THREAD_EXIT		= _IOW('b', 8, __s32),
+	BINDER_VERSION			= _IOWR('b', 9, struct binder_version),
+	BINDER_GET_NODE_DEBUG_INFO	= _IOWR('b', 11, struct binder_node_debug_info),
+	BINDER_GET_NODE_INFO_FOR_REF	= _IOWR('b', 12, struct binder_node_info_for_ref),
+	BINDER_SET_CONTEXT_MGR_EXT	= _IOW('b', 13, struct flat_binder_object),
+	BINDER_FREEZE			= _IOW('b', 14, struct binder_freeze_info),
+	BINDER_GET_FROZEN_INFO		= _IOWR('b', 15, struct binder_frozen_status_info),
+	BINDER_ENABLE_ONEWAY_SPAM_DETECTION	= _IOW('b', 16, __u32),
+	BINDER_GET_EXTENDED_ERROR	= _IOWR('b', 17, struct binder_extended_error),
+};
 
 /*
  * NOTE: Two special error codes you should check for when calling
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index 7c29d82db9ee..f8bc34a6bcfa 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -614,6 +614,9 @@ struct btrfs_ioctl_clone_range_args {
  */
 #define BTRFS_DEFRAG_RANGE_COMPRESS 1
 #define BTRFS_DEFRAG_RANGE_START_IO 2
+#define BTRFS_DEFRAG_RANGE_FLAGS_SUPP	(BTRFS_DEFRAG_RANGE_COMPRESS |		\
+					 BTRFS_DEFRAG_RANGE_START_IO)
+
 struct btrfs_ioctl_defrag_range_args {
 	/* start of the defrag operation */
 	__u64 start;
diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h
index 14bc6e742148..42066f4eb890 100644
--- a/include/uapi/linux/cxl_mem.h
+++ b/include/uapi/linux/cxl_mem.h
@@ -46,6 +46,7 @@
 	___C(GET_SCAN_MEDIA_CAPS, "Get Scan Media Capabilities"),         \
 	___DEPRECATED(SCAN_MEDIA, "Scan Media"),                          \
 	___DEPRECATED(GET_SCAN_MEDIA, "Get Scan Media Results"),          \
+	___C(GET_TIMESTAMP, "Get Timestamp"),                             \
 	___C(MAX, "invalid / last command")
 
 #define ___C(a, b) CXL_MEM_COMMAND_ID_##a
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 48ad69f7722e..45e4e64fd664 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -64,6 +64,24 @@ struct fstrim_range {
 	__u64 minlen;
 };
 
+/*
+ * We include a length field because some filesystems (vfat) have an identifier
+ * that we do want to expose as a UUID, but doesn't have the standard length.
+ *
+ * We use a fixed size buffer beacuse this interface will, by fiat, never
+ * support "UUIDs" longer than 16 bytes; we don't want to force all downstream
+ * users to have to deal with that.
+ */
+struct fsuuid2 {
+	__u8	len;
+	__u8	uuid[16];
+};
+
+struct fs_sysfs_path {
+	__u8			len;
+	__u8			name[128];
+};
+
 /* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
 #define FILE_DEDUPE_RANGE_SAME		0
 #define FILE_DEDUPE_RANGE_DIFFERS	1
@@ -215,6 +233,13 @@ struct fsxattr {
 #define FS_IOC_FSSETXATTR		_IOW('X', 32, struct fsxattr)
 #define FS_IOC_GETFSLABEL		_IOR(0x94, 49, char[FSLABEL_MAX])
 #define FS_IOC_SETFSLABEL		_IOW(0x94, 50, char[FSLABEL_MAX])
+/* Returns the external filesystem UUID, the same one blkid returns */
+#define FS_IOC_GETFSUUID		_IOR(0x15, 0, struct fsuuid2)
+/*
+ * Returns the path component under /sys/fs/ that refers to this filesystem;
+ * also /sys/kernel/debug/ for filesystems with debugfs exports
+ */
+#define FS_IOC_GETFSSYSFSPATH		_IOR(0x15, 1, struct fs_sysfs_path)
 
 /*
  * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
@@ -301,9 +326,12 @@ typedef int __bitwise __kernel_rwf_t;
 /* per-IO O_APPEND */
 #define RWF_APPEND	((__force __kernel_rwf_t)0x00000010)
 
+/* per-IO negation of O_APPEND */
+#define RWF_NOAPPEND	((__force __kernel_rwf_t)0x00000020)
+
 /* mask of flags supported by the kernel */
 #define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
-			 RWF_APPEND)
+			 RWF_APPEND | RWF_NOAPPEND)
 
 /* Pagemap ioctl */
 #define PAGEMAP_SCAN	_IOWR('f', 16, struct pm_scan_arg)
diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h
index 9c2ffdcd6623..f2e0b2d50e6b 100644
--- a/include/uapi/linux/iio/types.h
+++ b/include/uapi/linux/iio/types.h
@@ -105,6 +105,8 @@ enum iio_modifier {
 	IIO_MOD_PITCH,
 	IIO_MOD_YAW,
 	IIO_MOD_ROLL,
+	IIO_MOD_LIGHT_UVA,
+	IIO_MOD_LIGHT_UVB,
 };
 
 enum iio_event_type {
diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
index c4c53a9ab959..ff8d21f9e95b 100644
--- a/include/uapi/linux/in6.h
+++ b/include/uapi/linux/in6.h
@@ -145,7 +145,7 @@ struct in6_flowlabel_req {
 #define IPV6_TLV_PADN		1
 #define IPV6_TLV_ROUTERALERT	5
 #define IPV6_TLV_CALIPSO	7	/* RFC 5570 */
-#define IPV6_TLV_IOAM		49	/* TEMPORARY IANA allocation for IOAM */
+#define IPV6_TLV_IOAM		49	/* RFC 9486 */
 #define IPV6_TLV_JUMBO		194
 #define IPV6_TLV_HAO		201	/* home address option */
 
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 7a673b52827b..7bd10201a02b 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -255,6 +255,7 @@ enum io_uring_op {
 	IORING_OP_FUTEX_WAKE,
 	IORING_OP_FUTEX_WAITV,
 	IORING_OP_FIXED_FD_INSTALL,
+	IORING_OP_FTRUNCATE,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
@@ -570,6 +571,10 @@ enum {
 	/* return status information for a buffer group */
 	IORING_REGISTER_PBUF_STATUS		= 26,
 
+	/* set/clear busy poll settings */
+	IORING_REGISTER_NAPI			= 27,
+	IORING_UNREGISTER_NAPI			= 28,
+
 	/* this goes last */
 	IORING_REGISTER_LAST,
 
@@ -703,6 +708,14 @@ struct io_uring_buf_status {
 	__u32	resv[8];
 };
 
+/* argument for IORING_(UN)REGISTER_NAPI */
+struct io_uring_napi {
+	__u32	busy_poll_to;
+	__u8	prefer_busy_poll;
+	__u8	pad[3];
+	__u64	resv;
+};
+
 /*
  * io_uring_restriction->opcode values
  */
diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
index 0b2bc6252e2c..1dfeaa2e649e 100644
--- a/include/uapi/linux/iommufd.h
+++ b/include/uapi/linux/iommufd.h
@@ -49,6 +49,7 @@ enum {
 	IOMMUFD_CMD_GET_HW_INFO,
 	IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING,
 	IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP,
+	IOMMUFD_CMD_HWPT_INVALIDATE,
 };
 
 /**
@@ -613,4 +614,82 @@ struct iommu_hwpt_get_dirty_bitmap {
 #define IOMMU_HWPT_GET_DIRTY_BITMAP _IO(IOMMUFD_TYPE, \
 					IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP)
 
+/**
+ * enum iommu_hwpt_invalidate_data_type - IOMMU HWPT Cache Invalidation
+ *                                        Data Type
+ * @IOMMU_HWPT_INVALIDATE_DATA_VTD_S1: Invalidation data for VTD_S1
+ */
+enum iommu_hwpt_invalidate_data_type {
+	IOMMU_HWPT_INVALIDATE_DATA_VTD_S1,
+};
+
+/**
+ * enum iommu_hwpt_vtd_s1_invalidate_flags - Flags for Intel VT-d
+ *                                           stage-1 cache invalidation
+ * @IOMMU_VTD_INV_FLAGS_LEAF: Indicates whether the invalidation applies
+ *                            to all-levels page structure cache or just
+ *                            the leaf PTE cache.
+ */
+enum iommu_hwpt_vtd_s1_invalidate_flags {
+	IOMMU_VTD_INV_FLAGS_LEAF = 1 << 0,
+};
+
+/**
+ * struct iommu_hwpt_vtd_s1_invalidate - Intel VT-d cache invalidation
+ *                                       (IOMMU_HWPT_INVALIDATE_DATA_VTD_S1)
+ * @addr: The start address of the range to be invalidated. It needs to
+ *        be 4KB aligned.
+ * @npages: Number of contiguous 4K pages to be invalidated.
+ * @flags: Combination of enum iommu_hwpt_vtd_s1_invalidate_flags
+ * @__reserved: Must be 0
+ *
+ * The Intel VT-d specific invalidation data for user-managed stage-1 cache
+ * invalidation in nested translation. Userspace uses this structure to
+ * tell the impacted cache scope after modifying the stage-1 page table.
+ *
+ * Invalidating all the caches related to the page table by setting @addr
+ * to be 0 and @npages to be U64_MAX.
+ *
+ * The device TLB will be invalidated automatically if ATS is enabled.
+ */
+struct iommu_hwpt_vtd_s1_invalidate {
+	__aligned_u64 addr;
+	__aligned_u64 npages;
+	__u32 flags;
+	__u32 __reserved;
+};
+
+/**
+ * struct iommu_hwpt_invalidate - ioctl(IOMMU_HWPT_INVALIDATE)
+ * @size: sizeof(struct iommu_hwpt_invalidate)
+ * @hwpt_id: ID of a nested HWPT for cache invalidation
+ * @data_uptr: User pointer to an array of driver-specific cache invalidation
+ *             data.
+ * @data_type: One of enum iommu_hwpt_invalidate_data_type, defining the data
+ *             type of all the entries in the invalidation request array. It
+ *             should be a type supported by the hwpt pointed by @hwpt_id.
+ * @entry_len: Length (in bytes) of a request entry in the request array
+ * @entry_num: Input the number of cache invalidation requests in the array.
+ *             Output the number of requests successfully handled by kernel.
+ * @__reserved: Must be 0.
+ *
+ * Invalidate the iommu cache for user-managed page table. Modifications on a
+ * user-managed page table should be followed by this operation to sync cache.
+ * Each ioctl can support one or more cache invalidation requests in the array
+ * that has a total size of @entry_len * @entry_num.
+ *
+ * An empty invalidation request array by setting @entry_num==0 is allowed, and
+ * @entry_len and @data_uptr would be ignored in this case. This can be used to
+ * check if the given @data_type is supported or not by kernel.
+ */
+struct iommu_hwpt_invalidate {
+	__u32 size;
+	__u32 hwpt_id;
+	__aligned_u64 data_uptr;
+	__u32 data_type;
+	__u32 entry_len;
+	__u32 entry_num;
+	__u32 __reserved;
+};
+#define IOMMU_HWPT_INVALIDATE _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_INVALIDATE)
 #endif
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 211b86de35ac..c3308536482b 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -16,76 +16,6 @@
 
 #define KVM_API_VERSION 12
 
-/* *** Deprecated interfaces *** */
-
-#define KVM_TRC_SHIFT           16
-
-#define KVM_TRC_ENTRYEXIT       (1 << KVM_TRC_SHIFT)
-#define KVM_TRC_HANDLER         (1 << (KVM_TRC_SHIFT + 1))
-
-#define KVM_TRC_VMENTRY         (KVM_TRC_ENTRYEXIT + 0x01)
-#define KVM_TRC_VMEXIT          (KVM_TRC_ENTRYEXIT + 0x02)
-#define KVM_TRC_PAGE_FAULT      (KVM_TRC_HANDLER + 0x01)
-
-#define KVM_TRC_HEAD_SIZE       12
-#define KVM_TRC_CYCLE_SIZE      8
-#define KVM_TRC_EXTRA_MAX       7
-
-#define KVM_TRC_INJ_VIRQ         (KVM_TRC_HANDLER + 0x02)
-#define KVM_TRC_REDELIVER_EVT    (KVM_TRC_HANDLER + 0x03)
-#define KVM_TRC_PEND_INTR        (KVM_TRC_HANDLER + 0x04)
-#define KVM_TRC_IO_READ          (KVM_TRC_HANDLER + 0x05)
-#define KVM_TRC_IO_WRITE         (KVM_TRC_HANDLER + 0x06)
-#define KVM_TRC_CR_READ          (KVM_TRC_HANDLER + 0x07)
-#define KVM_TRC_CR_WRITE         (KVM_TRC_HANDLER + 0x08)
-#define KVM_TRC_DR_READ          (KVM_TRC_HANDLER + 0x09)
-#define KVM_TRC_DR_WRITE         (KVM_TRC_HANDLER + 0x0A)
-#define KVM_TRC_MSR_READ         (KVM_TRC_HANDLER + 0x0B)
-#define KVM_TRC_MSR_WRITE        (KVM_TRC_HANDLER + 0x0C)
-#define KVM_TRC_CPUID            (KVM_TRC_HANDLER + 0x0D)
-#define KVM_TRC_INTR             (KVM_TRC_HANDLER + 0x0E)
-#define KVM_TRC_NMI              (KVM_TRC_HANDLER + 0x0F)
-#define KVM_TRC_VMMCALL          (KVM_TRC_HANDLER + 0x10)
-#define KVM_TRC_HLT              (KVM_TRC_HANDLER + 0x11)
-#define KVM_TRC_CLTS             (KVM_TRC_HANDLER + 0x12)
-#define KVM_TRC_LMSW             (KVM_TRC_HANDLER + 0x13)
-#define KVM_TRC_APIC_ACCESS      (KVM_TRC_HANDLER + 0x14)
-#define KVM_TRC_TDP_FAULT        (KVM_TRC_HANDLER + 0x15)
-#define KVM_TRC_GTLB_WRITE       (KVM_TRC_HANDLER + 0x16)
-#define KVM_TRC_STLB_WRITE       (KVM_TRC_HANDLER + 0x17)
-#define KVM_TRC_STLB_INVAL       (KVM_TRC_HANDLER + 0x18)
-#define KVM_TRC_PPC_INSTR        (KVM_TRC_HANDLER + 0x19)
-
-struct kvm_user_trace_setup {
-	__u32 buf_size;
-	__u32 buf_nr;
-};
-
-#define __KVM_DEPRECATED_MAIN_W_0x06 \
-	_IOW(KVMIO, 0x06, struct kvm_user_trace_setup)
-#define __KVM_DEPRECATED_MAIN_0x07 _IO(KVMIO, 0x07)
-#define __KVM_DEPRECATED_MAIN_0x08 _IO(KVMIO, 0x08)
-
-#define __KVM_DEPRECATED_VM_R_0x70 _IOR(KVMIO, 0x70, struct kvm_assigned_irq)
-
-struct kvm_breakpoint {
-	__u32 enabled;
-	__u32 padding;
-	__u64 address;
-};
-
-struct kvm_debug_guest {
-	__u32 enabled;
-	__u32 pad;
-	struct kvm_breakpoint breakpoints[4];
-	__u32 singlestep;
-};
-
-#define __KVM_DEPRECATED_VCPU_W_0x87 _IOW(KVMIO, 0x87, struct kvm_debug_guest)
-
-/* *** End of deprecated interfaces *** */
-
-
 /* for KVM_SET_USER_MEMORY_REGION */
 struct kvm_userspace_memory_region {
 	__u32 slot;
@@ -95,6 +25,19 @@ struct kvm_userspace_memory_region {
 	__u64 userspace_addr; /* start of the userspace allocated memory */
 };
 
+/* for KVM_SET_USER_MEMORY_REGION2 */
+struct kvm_userspace_memory_region2 {
+	__u32 slot;
+	__u32 flags;
+	__u64 guest_phys_addr;
+	__u64 memory_size;
+	__u64 userspace_addr;
+	__u64 guest_memfd_offset;
+	__u32 guest_memfd;
+	__u32 pad1;
+	__u64 pad2[14];
+};
+
 /*
  * The bit 0 ~ bit 15 of kvm_userspace_memory_region::flags are visible for
  * userspace, other bits are reserved for kvm internal use which are defined
@@ -102,6 +45,7 @@ struct kvm_userspace_memory_region {
  */
 #define KVM_MEM_LOG_DIRTY_PAGES	(1UL << 0)
 #define KVM_MEM_READONLY	(1UL << 1)
+#define KVM_MEM_GUEST_MEMFD	(1UL << 2)
 
 /* for KVM_IRQ_LINE */
 struct kvm_irq_level {
@@ -265,6 +209,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_RISCV_CSR        36
 #define KVM_EXIT_NOTIFY           37
 #define KVM_EXIT_LOONGARCH_IOCSR  38
+#define KVM_EXIT_MEMORY_FAULT     39
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -518,6 +463,13 @@ struct kvm_run {
 #define KVM_NOTIFY_CONTEXT_INVALID	(1 << 0)
 			__u32 flags;
 		} notify;
+		/* KVM_EXIT_MEMORY_FAULT */
+		struct {
+#define KVM_MEMORY_EXIT_FLAG_PRIVATE	(1ULL << 3)
+			__u64 flags;
+			__u64 gpa;
+			__u64 size;
+		} memory_fault;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -945,9 +897,6 @@ struct kvm_ppc_resize_hpt {
  */
 #define KVM_GET_VCPU_MMAP_SIZE    _IO(KVMIO,   0x04) /* in bytes */
 #define KVM_GET_SUPPORTED_CPUID   _IOWR(KVMIO, 0x05, struct kvm_cpuid2)
-#define KVM_TRACE_ENABLE          __KVM_DEPRECATED_MAIN_W_0x06
-#define KVM_TRACE_PAUSE           __KVM_DEPRECATED_MAIN_0x07
-#define KVM_TRACE_DISABLE         __KVM_DEPRECATED_MAIN_0x08
 #define KVM_GET_EMULATED_CPUID	  _IOWR(KVMIO, 0x09, struct kvm_cpuid2)
 #define KVM_GET_MSR_FEATURE_INDEX_LIST    _IOWR(KVMIO, 0x0a, struct kvm_msr_list)
 
@@ -1201,6 +1150,11 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
 #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
 #define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230
+#define KVM_CAP_USER_MEMORY2 231
+#define KVM_CAP_MEMORY_FAULT_INFO 232
+#define KVM_CAP_MEMORY_ATTRIBUTES 233
+#define KVM_CAP_GUEST_MEMFD 234
+#define KVM_CAP_VM_TYPES 235
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1291,6 +1245,7 @@ struct kvm_x86_mce {
 #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL	(1 << 4)
 #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND		(1 << 5)
 #define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG	(1 << 6)
+#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE	(1 << 7)
 
 struct kvm_xen_hvm_config {
 	__u32 flags;
@@ -1483,6 +1438,8 @@ struct kvm_vfio_spapr_tce {
 					struct kvm_userspace_memory_region)
 #define KVM_SET_TSS_ADDR          _IO(KVMIO,   0x47)
 #define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO,  0x48, __u64)
+#define KVM_SET_USER_MEMORY_REGION2 _IOW(KVMIO, 0x49, \
+					 struct kvm_userspace_memory_region2)
 
 /* enable ucontrol for s390 */
 struct kvm_s390_ucas_mapping {
@@ -1507,20 +1464,8 @@ struct kvm_s390_ucas_mapping {
 			_IOW(KVMIO,  0x67, struct kvm_coalesced_mmio_zone)
 #define KVM_UNREGISTER_COALESCED_MMIO \
 			_IOW(KVMIO,  0x68, struct kvm_coalesced_mmio_zone)
-#define KVM_ASSIGN_PCI_DEVICE     _IOR(KVMIO,  0x69, \
-				       struct kvm_assigned_pci_dev)
 #define KVM_SET_GSI_ROUTING       _IOW(KVMIO,  0x6a, struct kvm_irq_routing)
-/* deprecated, replaced by KVM_ASSIGN_DEV_IRQ */
-#define KVM_ASSIGN_IRQ            __KVM_DEPRECATED_VM_R_0x70
-#define KVM_ASSIGN_DEV_IRQ        _IOW(KVMIO,  0x70, struct kvm_assigned_irq)
 #define KVM_REINJECT_CONTROL      _IO(KVMIO,   0x71)
-#define KVM_DEASSIGN_PCI_DEVICE   _IOW(KVMIO,  0x72, \
-				       struct kvm_assigned_pci_dev)
-#define KVM_ASSIGN_SET_MSIX_NR    _IOW(KVMIO,  0x73, \
-				       struct kvm_assigned_msix_nr)
-#define KVM_ASSIGN_SET_MSIX_ENTRY _IOW(KVMIO,  0x74, \
-				       struct kvm_assigned_msix_entry)
-#define KVM_DEASSIGN_DEV_IRQ      _IOW(KVMIO,  0x75, struct kvm_assigned_irq)
 #define KVM_IRQFD                 _IOW(KVMIO,  0x76, struct kvm_irqfd)
 #define KVM_CREATE_PIT2		  _IOW(KVMIO,  0x77, struct kvm_pit_config)
 #define KVM_SET_BOOT_CPU_ID       _IO(KVMIO,   0x78)
@@ -1537,9 +1482,6 @@ struct kvm_s390_ucas_mapping {
 *  KVM_CAP_VM_TSC_CONTROL to set defaults for a VM */
 #define KVM_SET_TSC_KHZ           _IO(KVMIO,  0xa2)
 #define KVM_GET_TSC_KHZ           _IO(KVMIO,  0xa3)
-/* Available with KVM_CAP_PCI_2_3 */
-#define KVM_ASSIGN_SET_INTX_MASK  _IOW(KVMIO,  0xa4, \
-				       struct kvm_assigned_pci_dev)
 /* Available with KVM_CAP_SIGNAL_MSI */
 #define KVM_SIGNAL_MSI            _IOW(KVMIO,  0xa5, struct kvm_msi)
 /* Available with KVM_CAP_PPC_GET_SMMU_INFO */
@@ -1592,8 +1534,6 @@ struct kvm_s390_ucas_mapping {
 #define KVM_SET_SREGS             _IOW(KVMIO,  0x84, struct kvm_sregs)
 #define KVM_TRANSLATE             _IOWR(KVMIO, 0x85, struct kvm_translation)
 #define KVM_INTERRUPT             _IOW(KVMIO,  0x86, struct kvm_interrupt)
-/* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */
-#define KVM_DEBUG_GUEST           __KVM_DEPRECATED_VCPU_W_0x87
 #define KVM_GET_MSRS              _IOWR(KVMIO, 0x88, struct kvm_msrs)
 #define KVM_SET_MSRS              _IOW(KVMIO,  0x89, struct kvm_msrs)
 #define KVM_SET_CPUID             _IOW(KVMIO,  0x8a, struct kvm_cpuid)
@@ -2267,4 +2207,24 @@ struct kvm_s390_zpci_op {
 /* flags for kvm_s390_zpci_op->u.reg_aen.flags */
 #define KVM_S390_ZPCIOP_REGAEN_HOST    (1 << 0)
 
+/* Available with KVM_CAP_MEMORY_ATTRIBUTES */
+#define KVM_SET_MEMORY_ATTRIBUTES              _IOW(KVMIO,  0xd2, struct kvm_memory_attributes)
+
+struct kvm_memory_attributes {
+	__u64 address;
+	__u64 size;
+	__u64 attributes;
+	__u64 flags;
+};
+
+#define KVM_MEMORY_ATTRIBUTE_PRIVATE           (1ULL << 3)
+
+#define KVM_CREATE_GUEST_MEMFD	_IOWR(KVMIO,  0xd4, struct kvm_create_guest_memfd)
+
+struct kvm_create_guest_memfd {
+	__u64 size;
+	__u64 flags;
+	__u64 reserved[6];
+};
+
 #endif /* __LINUX_KVM_H */
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index 6325d1d0e90f..1b40a968ba91 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -101,5 +101,6 @@
 #define DMA_BUF_MAGIC		0x444d4142	/* "DMAB" */
 #define DEVMEM_MAGIC		0x454d444d	/* "DMEM" */
 #define SECRETMEM_MAGIC		0x5345434d	/* "SECM" */
+#define PID_FS_MAGIC		0x50494446	/* "PIDF" */
 
 #endif /* __LINUX_MAGIC_H__ */
diff --git a/include/uapi/linux/mei.h b/include/uapi/linux/mei.h
index 171c5cce3641..68a0272e99b7 100644
--- a/include/uapi/linux/mei.h
+++ b/include/uapi/linux/mei.h
@@ -100,14 +100,14 @@ struct mei_connect_client_data_vtag {
  * a FW client on a tagged channel. From this point on, every read
  * and write will communicate with the associated FW client
  * on the tagged channel.
- * Upone close() the communication is terminated.
+ * Upon close() the communication is terminated.
  *
  * The IOCTL argument is a struct with a union that contains
  * the input parameter and the output parameter for this IOCTL.
  *
  * The input parameter is UUID of the FW Client, a vtag [0,255].
  * The output parameter is the properties of the FW client
- * (FW protocool version and max message size).
+ * (FW protocol version and max message size).
  *
  * Clients that do not support tagged connection
  * will respond with -EOPNOTSUPP.
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index ca30232b7bc8..117c6a9b845b 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -285,9 +285,11 @@ enum nft_rule_attributes {
 /**
  * enum nft_rule_compat_flags - nf_tables rule compat flags
  *
+ * @NFT_RULE_COMPAT_F_UNUSED: unused
  * @NFT_RULE_COMPAT_F_INV: invert the check result
  */
 enum nft_rule_compat_flags {
+	NFT_RULE_COMPAT_F_UNUSED = (1 << 0),
 	NFT_RULE_COMPAT_F_INV	= (1 << 1),
 	NFT_RULE_COMPAT_F_MASK	= NFT_RULE_COMPAT_F_INV,
 };
diff --git a/include/uapi/linux/nsm.h b/include/uapi/linux/nsm.h
new file mode 100644
index 000000000000..e529f232f6c0
--- /dev/null
+++ b/include/uapi/linux/nsm.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ */
+
+#ifndef __UAPI_LINUX_NSM_H
+#define __UAPI_LINUX_NSM_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+#define NSM_MAGIC		0x0A
+
+#define NSM_REQUEST_MAX_SIZE	0x1000
+#define NSM_RESPONSE_MAX_SIZE	0x3000
+
+struct nsm_iovec {
+	__u64 addr; /* Virtual address of target buffer */
+	__u64 len;  /* Length of target buffer */
+};
+
+/* Raw NSM message. Only available with CAP_SYS_ADMIN. */
+struct nsm_raw {
+	/* Request from user */
+	struct nsm_iovec request;
+	/* Response to user */
+	struct nsm_iovec response;
+};
+#define NSM_IOCTL_RAW		_IOWR(NSM_MAGIC, 0x0, struct nsm_raw)
+
+#endif /* __UAPI_LINUX_NSM_H */
diff --git a/include/uapi/linux/pcitest.h b/include/uapi/linux/pcitest.h
index f9c1af8d141b..94b46b043b53 100644
--- a/include/uapi/linux/pcitest.h
+++ b/include/uapi/linux/pcitest.h
@@ -11,7 +11,8 @@
 #define __UAPI_LINUX_PCITEST_H
 
 #define PCITEST_BAR		_IO('P', 0x1)
-#define PCITEST_LEGACY_IRQ	_IO('P', 0x2)
+#define PCITEST_INTX_IRQ	_IO('P', 0x2)
+#define PCITEST_LEGACY_IRQ	PCITEST_INTX_IRQ
 #define PCITEST_MSI		_IOW('P', 0x3, int)
 #define PCITEST_WRITE		_IOW('P', 0x4, unsigned long)
 #define PCITEST_READ		_IOW('P', 0x5, unsigned long)
diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h
index 5406fbc13074..72ec000a97cd 100644
--- a/include/uapi/linux/pidfd.h
+++ b/include/uapi/linux/pidfd.h
@@ -7,6 +7,12 @@
 #include <linux/fcntl.h>
 
 /* Flags for pidfd_open().  */
-#define PIDFD_NONBLOCK O_NONBLOCK
+#define PIDFD_NONBLOCK	O_NONBLOCK
+#define PIDFD_THREAD	O_EXCL
+
+/* Flags for pidfd_send_signal(). */
+#define PIDFD_SIGNAL_THREAD		(1UL << 0)
+#define PIDFD_SIGNAL_THREAD_GROUP	(1UL << 1)
+#define PIDFD_SIGNAL_PROCESS_GROUP	(1UL << 2)
 
 #endif /* _UAPI_LINUX_PIDFD_H */
diff --git a/include/uapi/linux/serial.h b/include/uapi/linux/serial.h
index 53bc1af67a41..de9b4733607e 100644
--- a/include/uapi/linux/serial.h
+++ b/include/uapi/linux/serial.h
@@ -11,6 +11,7 @@
 #ifndef _UAPI_LINUX_SERIAL_H
 #define _UAPI_LINUX_SERIAL_H
 
+#include <linux/const.h>
 #include <linux/types.h>
 
 #include <linux/tty_flags.h>
@@ -137,17 +138,20 @@ struct serial_icounter_struct {
  * * %SER_RS485_ADDRB		- Enable RS485 addressing mode.
  * * %SER_RS485_ADDR_RECV - Receive address filter (enables @addr_recv). Requires %SER_RS485_ADDRB.
  * * %SER_RS485_ADDR_DEST - Destination address (enables @addr_dest). Requires %SER_RS485_ADDRB.
+ * * %SER_RS485_MODE_RS422	- Enable RS422. Requires %SER_RS485_ENABLED.
  */
 struct serial_rs485 {
 	__u32	flags;
-#define SER_RS485_ENABLED		(1 << 0)
-#define SER_RS485_RTS_ON_SEND		(1 << 1)
-#define SER_RS485_RTS_AFTER_SEND	(1 << 2)
-#define SER_RS485_RX_DURING_TX		(1 << 4)
-#define SER_RS485_TERMINATE_BUS		(1 << 5)
-#define SER_RS485_ADDRB			(1 << 6)
-#define SER_RS485_ADDR_RECV		(1 << 7)
-#define SER_RS485_ADDR_DEST		(1 << 8)
+#define SER_RS485_ENABLED		_BITUL(0)
+#define SER_RS485_RTS_ON_SEND		_BITUL(1)
+#define SER_RS485_RTS_AFTER_SEND	_BITUL(2)
+/* Placeholder for bit 3: SER_RS485_RTS_BEFORE_SEND, which isn't used anymore */
+#define SER_RS485_RX_DURING_TX		_BITUL(4)
+#define SER_RS485_TERMINATE_BUS		_BITUL(5)
+#define SER_RS485_ADDRB			_BITUL(6)
+#define SER_RS485_ADDR_RECV		_BITUL(7)
+#define SER_RS485_ADDR_DEST		_BITUL(8)
+#define SER_RS485_MODE_RS422		_BITUL(9)
 
 	__u32	delay_rts_before_send;
 	__u32	delay_rts_after_send;
diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h
index b9cfc5c96268..c8dc5f8ea699 100644
--- a/include/uapi/linux/ublk_cmd.h
+++ b/include/uapi/linux/ublk_cmd.h
@@ -49,6 +49,8 @@
 	_IOR('u', UBLK_CMD_GET_DEV_INFO2, struct ublksrv_ctrl_cmd)
 #define UBLK_U_CMD_GET_FEATURES	\
 	_IOR('u', 0x13, struct ublksrv_ctrl_cmd)
+#define UBLK_U_CMD_DEL_DEV_ASYNC	\
+	_IOR('u', 0x14, struct ublksrv_ctrl_cmd)
 
 /*
  * 64bits are enough now, and it should be easy to extend in case of
diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h
index d77ee6b65328..078098e73fd3 100644
--- a/include/uapi/linux/usb/functionfs.h
+++ b/include/uapi/linux/usb/functionfs.h
@@ -73,8 +73,10 @@ struct usb_os_desc_header {
 struct usb_ext_compat_desc {
 	__u8	bFirstInterfaceNumber;
 	__u8	Reserved1;
-	__u8	CompatibleID[8];
-	__u8	SubCompatibleID[8];
+	__struct_group(/* no tag */, IDs, /* no attrs */,
+		__u8	CompatibleID[8];
+		__u8	SubCompatibleID[8];
+	);
 	__u8	Reserved2[6];
 };
 
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 7f5fb010226d..2b68e6cdf190 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -1219,6 +1219,7 @@ enum vfio_device_mig_state {
 	VFIO_DEVICE_STATE_RUNNING_P2P = 5,
 	VFIO_DEVICE_STATE_PRE_COPY = 6,
 	VFIO_DEVICE_STATE_PRE_COPY_P2P = 7,
+	VFIO_DEVICE_STATE_NR,
 };
 
 /**
diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h
index 8881aea60f6f..2445f365bce7 100644
--- a/include/uapi/linux/virtio_config.h
+++ b/include/uapi/linux/virtio_config.h
@@ -52,7 +52,7 @@
  * rest are per-device feature bits.
  */
 #define VIRTIO_TRANSPORT_F_START	28
-#define VIRTIO_TRANSPORT_F_END		41
+#define VIRTIO_TRANSPORT_F_END		42
 
 #ifndef VIRTIO_CONFIG_NO_LEGACY
 /* Do we get callbacks when the ring is completely used, even if we've
@@ -114,4 +114,10 @@
  * This feature indicates that the driver can reset a queue individually.
  */
 #define VIRTIO_F_RING_RESET		40
+
+/*
+ * This feature indicates that the device support administration virtqueues.
+ */
+#define VIRTIO_F_ADMIN_VQ		41
+
 #endif /* _UAPI_LINUX_VIRTIO_CONFIG_H */
diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 44f4dd2add18..ef3810dee7ef 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -175,6 +175,9 @@ struct virtio_pci_modern_common_cfg {
 
 	__le16 queue_notify_data;	/* read-write */
 	__le16 queue_reset;		/* read-write */
+
+	__le16 admin_queue_index;	/* read-only */
+	__le16 admin_queue_num;		/* read-only */
 };
 
 /* Fields in VIRTIO_PCI_CAP_PCI_CFG: */
@@ -215,7 +218,72 @@ struct virtio_pci_cfg_cap {
 #define VIRTIO_PCI_COMMON_Q_USEDHI	52
 #define VIRTIO_PCI_COMMON_Q_NDATA	56
 #define VIRTIO_PCI_COMMON_Q_RESET	58
+#define VIRTIO_PCI_COMMON_ADM_Q_IDX	60
+#define VIRTIO_PCI_COMMON_ADM_Q_NUM	62
 
 #endif /* VIRTIO_PCI_NO_MODERN */
 
+/* Admin command status. */
+#define VIRTIO_ADMIN_STATUS_OK		0
+
+/* Admin command opcode. */
+#define VIRTIO_ADMIN_CMD_LIST_QUERY	0x0
+#define VIRTIO_ADMIN_CMD_LIST_USE	0x1
+
+/* Admin command group type. */
+#define VIRTIO_ADMIN_GROUP_TYPE_SRIOV	0x1
+
+/* Transitional device admin command. */
+#define VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_WRITE	0x2
+#define VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_READ		0x3
+#define VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_WRITE		0x4
+#define VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ		0x5
+#define VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO		0x6
+
+struct __packed virtio_admin_cmd_hdr {
+	__le16 opcode;
+	/*
+	 * 1 - SR-IOV
+	 * 2-65535 - reserved
+	 */
+	__le16 group_type;
+	/* Unused, reserved for future extensions. */
+	__u8 reserved1[12];
+	__le64 group_member_id;
+};
+
+struct __packed virtio_admin_cmd_status {
+	__le16 status;
+	__le16 status_qualifier;
+	/* Unused, reserved for future extensions. */
+	__u8 reserved2[4];
+};
+
+struct __packed virtio_admin_cmd_legacy_wr_data {
+	__u8 offset; /* Starting offset of the register(s) to write. */
+	__u8 reserved[7];
+	__u8 registers[];
+};
+
+struct __packed virtio_admin_cmd_legacy_rd_data {
+	__u8 offset; /* Starting offset of the register(s) to read. */
+};
+
+#define VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_END 0
+#define VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_OWNER_DEV 0x1
+#define VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_OWNER_MEM 0x2
+
+#define VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO 4
+
+struct __packed virtio_admin_cmd_notify_info_data {
+	__u8 flags; /* 0 = end of list, 1 = owner device, 2 = member device */
+	__u8 bar; /* BAR of the member or the owner device */
+	__u8 padding[6];
+	__le64 offset; /* Offset within bar. */
+};
+
+struct virtio_admin_cmd_notify_info_result {
+	struct virtio_admin_cmd_notify_info_data entries[VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO];
+};
+
 #endif
diff --git a/include/uapi/linux/virtio_pmem.h b/include/uapi/linux/virtio_pmem.h
index d676b3620383..ede4f3564977 100644
--- a/include/uapi/linux/virtio_pmem.h
+++ b/include/uapi/linux/virtio_pmem.h
@@ -14,6 +14,13 @@
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
 
+/* Feature bits */
+/* guest physical address range will be indicated as shared memory region 0 */
+#define VIRTIO_PMEM_F_SHMEM_REGION 0
+
+/* shmid of the shared memory region corresponding to the pmem */
+#define VIRTIO_PMEM_SHMEM_REGION_ID 0
+
 struct virtio_pmem_config {
 	__le64 start;
 	__le64 size;
diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h
index d5b9cfbd9cea..628d46a0da92 100644
--- a/include/uapi/sound/asound.h
+++ b/include/uapi/sound/asound.h
@@ -142,7 +142,7 @@ struct snd_hwdep_dsp_image {
  *                                                                           *
  *****************************************************************************/
 
-#define SNDRV_PCM_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 16)
+#define SNDRV_PCM_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 17)
 
 typedef unsigned long snd_pcm_uframes_t;
 typedef signed long snd_pcm_sframes_t;
@@ -416,7 +416,7 @@ struct snd_pcm_hw_params {
 	unsigned int rmask;		/* W: requested masks */
 	unsigned int cmask;		/* R: changed masks */
 	unsigned int info;		/* R: Info flags for returned setup */
-	unsigned int msbits;		/* R: used most significant bits */
+	unsigned int msbits;		/* R: used most significant bits (in sample bit-width) */
 	unsigned int rate_num;		/* R: rate numerator */
 	unsigned int rate_den;		/* R: rate denominator */
 	snd_pcm_uframes_t fifo_size;	/* R: chip FIFO size in frames */
diff --git a/include/uapi/xen/gntalloc.h b/include/uapi/xen/gntalloc.h
index 48d2790ef928..3109282672f3 100644
--- a/include/uapi/xen/gntalloc.h
+++ b/include/uapi/xen/gntalloc.h
@@ -31,7 +31,10 @@ struct ioctl_gntalloc_alloc_gref {
 	__u64 index;
 	/* The grant references of the newly created grant, one per page */
 	/* Variable size, depending on count */
-	__u32 gref_ids[1];
+	union {
+		__u32 gref_ids[1];
+		__DECLARE_FLEX_ARRAY(__u32, gref_ids_flex);
+	};
 };
 
 #define GNTALLOC_FLAG_WRITABLE 1
diff --git a/include/xen/interface/io/displif.h b/include/xen/interface/io/displif.h
index 18417b017869..60e42d3b760e 100644
--- a/include/xen/interface/io/displif.h
+++ b/include/xen/interface/io/displif.h
@@ -537,7 +537,7 @@ struct xendispl_dbuf_create_req {
 
 struct xendispl_page_directory {
 	grant_ref_t gref_dir_next_page;
-	grant_ref_t gref[1]; /* Variable length */
+	grant_ref_t gref[];
 };
 
 /*
diff --git a/include/xen/interface/io/ring.h b/include/xen/interface/io/ring.h
index ba4c4274b714..4fef1efcdcab 100644
--- a/include/xen/interface/io/ring.h
+++ b/include/xen/interface/io/ring.h
@@ -95,7 +95,7 @@ struct __name##_sring {                                                 \
     RING_IDX req_prod, req_event;                                       \
     RING_IDX rsp_prod, rsp_event;                                       \
     uint8_t __pad[48];                                                  \
-    union __name##_sring_entry ring[1]; /* variable-length */           \
+    union __name##_sring_entry ring[];                                  \
 };                                                                      \
                                                                         \
 /* "Front" end's private variables */                                   \
diff --git a/include/xen/interface/io/sndif.h b/include/xen/interface/io/sndif.h
index 445657cdb1de..b818517588b5 100644
--- a/include/xen/interface/io/sndif.h
+++ b/include/xen/interface/io/sndif.h
@@ -659,7 +659,7 @@ struct xensnd_open_req {
 
 struct xensnd_page_directory {
 	grant_ref_t gref_dir_next_page;
-	grant_ref_t gref[1]; /* Variable length */
+	grant_ref_t gref[];
 };
 
 /*
diff --git a/init/Kconfig b/init/Kconfig
index 8df18f3a9748..7c5df7b0b576 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -89,6 +89,15 @@ config CC_HAS_ASM_GOTO_TIED_OUTPUT
 	# Detect buggy gcc and clang, fixed in gcc-11 clang-14.
 	def_bool $(success,echo 'int foo(int *x) { asm goto (".long (%l[bar]) - .": "+m"(*x) ::: bar); return *x; bar: return 0; }' | $CC -x c - -c -o /dev/null)
 
+config GCC_ASM_GOTO_OUTPUT_WORKAROUND
+	bool
+	depends on CC_IS_GCC && CC_HAS_ASM_GOTO_OUTPUT
+	# Fixed in GCC 14, 13.3, 12.4 and 11.5
+	# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921
+	default y if GCC_VERSION < 110500
+	default y if GCC_VERSION >= 120000 && GCC_VERSION < 120400
+	default y if GCC_VERSION >= 130000 && GCC_VERSION < 130300
+
 config TOOLS_SUPPORT_RELR
 	def_bool $(success,env "CC=$(CC)" "LD=$(LD)" "NM=$(NM)" "OBJCOPY=$(OBJCOPY)" $(srctree)/scripts/tools-support-relr.sh)
 
@@ -106,7 +115,7 @@ config CONSTRUCTORS
 	bool
 
 config IRQ_WORK
-	bool
+	def_bool y if SMP
 
 config BUILDTIME_TABLE_SORT
 	bool
@@ -867,14 +876,26 @@ config CC_IMPLICIT_FALLTHROUGH
 	default "-Wimplicit-fallthrough=5" if CC_IS_GCC && $(cc-option,-Wimplicit-fallthrough=5)
 	default "-Wimplicit-fallthrough" if CC_IS_CLANG && $(cc-option,-Wunreachable-code-fallthrough)
 
-# Currently, disable gcc-11+ array-bounds globally.
+# Currently, disable gcc-10+ array-bounds globally.
 # It's still broken in gcc-13, so no upper bound yet.
-config GCC11_NO_ARRAY_BOUNDS
+config GCC10_NO_ARRAY_BOUNDS
 	def_bool y
 
 config CC_NO_ARRAY_BOUNDS
 	bool
-	default y if CC_IS_GCC && GCC_VERSION >= 110000 && GCC11_NO_ARRAY_BOUNDS
+	default y if CC_IS_GCC && GCC_VERSION >= 100000 && GCC10_NO_ARRAY_BOUNDS
+
+# Currently, disable -Wstringop-overflow for GCC globally.
+config GCC_NO_STRINGOP_OVERFLOW
+	def_bool y
+
+config CC_NO_STRINGOP_OVERFLOW
+	bool
+	default y if CC_IS_GCC && GCC_NO_STRINGOP_OVERFLOW
+
+config CC_STRINGOP_OVERFLOW
+	bool
+	default y if CC_IS_GCC && !CC_NO_STRINGOP_OVERFLOW
 
 #
 # For architectures that know their GCC __int128 support is sound
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 5fdef94f0864..3c5fd993bc7e 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -208,6 +208,9 @@ retry:
 				goto out;
 			case -EACCES:
 			case -EINVAL:
+#ifdef CONFIG_BLOCK
+				init_flush_fput();
+#endif
 				continue;
 		}
 	        /*
@@ -510,7 +513,10 @@ struct file_system_type rootfs_fs_type = {
 
 void __init init_rootfs(void)
 {
-	if (IS_ENABLED(CONFIG_TMPFS) && !saved_root_name[0] &&
-		(!root_fs_names || strstr(root_fs_names, "tmpfs")))
-		is_tmpfs = true;
+	if (IS_ENABLED(CONFIG_TMPFS)) {
+		if (!saved_root_name[0] && !root_fs_names)
+			is_tmpfs = true;
+		else if (root_fs_names && !!strstr(root_fs_names, "tmpfs"))
+			is_tmpfs = true;
+	}
 }
diff --git a/init/do_mounts.h b/init/do_mounts.h
index 15e372b00ce7..6069ea3eb80d 100644
--- a/init/do_mounts.h
+++ b/init/do_mounts.h
@@ -9,6 +9,8 @@
 #include <linux/major.h>
 #include <linux/root_dev.h>
 #include <linux/init_syscalls.h>
+#include <linux/task_work.h>
+#include <linux/file.h>
 
 void  mount_root_generic(char *name, char *pretty_name, int flags);
 void  mount_root(char *root_device_name);
@@ -41,3 +43,10 @@ static inline bool initrd_load(char *root_device_name)
 	}
 
 #endif
+
+/* Ensure that async file closing finished to prevent spurious errors. */
+static inline void init_flush_fput(void)
+{
+	flush_delayed_fput();
+	task_work_run();
+}
diff --git a/init/init_task.c b/init/init_task.c
index 7ecb458eb3da..4daee6d761c8 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -147,6 +147,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
 	.rcu_tasks_holdout = false,
 	.rcu_tasks_holdout_list = LIST_HEAD_INIT(init_task.rcu_tasks_holdout_list),
 	.rcu_tasks_idle_cpu = -1,
+	.rcu_tasks_exit_list = LIST_HEAD_INIT(init_task.rcu_tasks_exit_list),
 #endif
 #ifdef CONFIG_TASKS_TRACE_RCU
 	.trc_reader_nesting = 0,
diff --git a/init/initramfs.c b/init/initramfs.c
index 8d0fd946cdd2..01dbd0e81501 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -16,9 +16,10 @@
 #include <linux/mm.h>
 #include <linux/namei.h>
 #include <linux/init_syscalls.h>
-#include <linux/task_work.h>
 #include <linux/umh.h>
 
+#include "do_mounts.h"
+
 static __initdata bool csum_present;
 static __initdata u32 io_csum;
 
@@ -574,6 +575,16 @@ extern unsigned long __initramfs_size;
 #include <linux/initrd.h>
 #include <linux/kexec.h>
 
+static ssize_t raw_read(struct file *file, struct kobject *kobj,
+			struct bin_attribute *attr, char *buf,
+			loff_t pos, size_t count)
+{
+	memcpy(buf, attr->private + pos, count);
+	return count;
+}
+
+static BIN_ATTR(initrd, 0440, raw_read, NULL, 0);
+
 void __init reserve_initrd_mem(void)
 {
 	phys_addr_t start;
@@ -669,8 +680,6 @@ static void __init populate_initrd_image(char *err)
 	struct file *file;
 	loff_t pos = 0;
 
-	unpack_to_rootfs(__initramfs_start, __initramfs_size);
-
 	printk(KERN_INFO "rootfs image is not initramfs (%s); looks like an initrd\n",
 			err);
 	file = filp_open("/initrd.image", O_WRONLY | O_CREAT, 0700);
@@ -715,13 +724,18 @@ done:
 	 * If the initrd region is overlapped with crashkernel reserved region,
 	 * free only memory that is not part of crashkernel region.
 	 */
-	if (!do_retain_initrd && initrd_start && !kexec_free_initrd())
+	if (!do_retain_initrd && initrd_start && !kexec_free_initrd()) {
 		free_initrd_mem(initrd_start, initrd_end);
+	} else if (do_retain_initrd && initrd_start) {
+		bin_attr_initrd.size = initrd_end - initrd_start;
+		bin_attr_initrd.private = (void *)initrd_start;
+		if (sysfs_create_bin_file(firmware_kobj, &bin_attr_initrd))
+			pr_err("Failed to create initrd sysfs file");
+	}
 	initrd_start = 0;
 	initrd_end = 0;
 
-	flush_delayed_fput();
-	task_work_run();
+	init_flush_fput();
 }
 
 static ASYNC_DOMAIN_EXCLUSIVE(initramfs_domain);
diff --git a/init/main.c b/init/main.c
index e24b0780fdff..f7ff31f878b8 100644
--- a/init/main.c
+++ b/init/main.c
@@ -99,6 +99,7 @@
 #include <linux/init_syscalls.h>
 #include <linux/stackdepot.h>
 #include <linux/randomize_kstack.h>
+#include <linux/pidfs.h>
 #include <net/net_namespace.h>
 
 #include <asm/io.h>
@@ -1059,6 +1060,7 @@ void start_kernel(void)
 	seq_file_init();
 	proc_root_init();
 	nsfs_init();
+	pidfs_init();
 	cpuset_init();
 	cgroup_init();
 	taskstats_init_early();
@@ -1545,6 +1547,7 @@ static noinline void __init kernel_init_freeable(void)
 	sched_init_smp();
 
 	workqueue_init_topology();
+	async_init();
 	padata_init();
 	page_alloc_init_late();
 
diff --git a/io_uring/Makefile b/io_uring/Makefile
index 2cdc51825405..2e1d4e03799c 100644
--- a/io_uring/Makefile
+++ b/io_uring/Makefile
@@ -8,6 +8,7 @@ obj-$(CONFIG_IO_URING)		+= io_uring.o xattr.o nop.o fs.o splice.o \
 					statx.o net.o msg_ring.o timeout.o \
 					sqpoll.o fdinfo.o tctx.o poll.o \
 					cancel.o kbuf.o rsrc.o rw.o opdef.o \
-					notif.o waitid.o register.o
+					notif.o waitid.o register.o truncate.o
 obj-$(CONFIG_IO_WQ)		+= io-wq.o
 obj-$(CONFIG_FUTEX)		+= futex.o
+obj-$(CONFIG_NET_RX_BUSY_POLL) += napi.o
diff --git a/io_uring/cancel.c b/io_uring/cancel.c
index 8a8b07dfc444..acfcdd7f059a 100644
--- a/io_uring/cancel.c
+++ b/io_uring/cancel.c
@@ -58,9 +58,8 @@ bool io_cancel_req_match(struct io_kiocb *req, struct io_cancel_data *cd)
 		return false;
 	if (cd->flags & IORING_ASYNC_CANCEL_ALL) {
 check_seq:
-		if (cd->seq == req->work.cancel_seq)
+		if (io_cancel_match_sequence(req, cd->seq))
 			return false;
-		req->work.cancel_seq = cd->seq;
 	}
 
 	return true;
diff --git a/io_uring/cancel.h b/io_uring/cancel.h
index c0a8e7c520b6..76b32e65c03c 100644
--- a/io_uring/cancel.h
+++ b/io_uring/cancel.h
@@ -25,4 +25,14 @@ void init_hash_table(struct io_hash_table *table, unsigned size);
 int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg);
 bool io_cancel_req_match(struct io_kiocb *req, struct io_cancel_data *cd);
 
+static inline bool io_cancel_match_sequence(struct io_kiocb *req, int sequence)
+{
+	if ((req->flags & REQ_F_CANCEL_SEQ) && sequence == req->work.cancel_seq)
+		return true;
+
+	req->flags |= REQ_F_CANCEL_SEQ;
+	req->work.cancel_seq = sequence;
+	return false;
+}
+
 #endif
diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
index 976e9500f651..8d444dd1b0a7 100644
--- a/io_uring/fdinfo.c
+++ b/io_uring/fdinfo.c
@@ -55,6 +55,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
 	struct io_ring_ctx *ctx = f->private_data;
 	struct io_overflow_cqe *ocqe;
 	struct io_rings *r = ctx->rings;
+	struct rusage sq_usage;
 	unsigned int sq_mask = ctx->sq_entries - 1, cq_mask = ctx->cq_entries - 1;
 	unsigned int sq_head = READ_ONCE(r->sq.head);
 	unsigned int sq_tail = READ_ONCE(r->sq.tail);
@@ -64,6 +65,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
 	unsigned int sq_shift = 0;
 	unsigned int sq_entries, cq_entries;
 	int sq_pid = -1, sq_cpu = -1;
+	u64 sq_total_time = 0, sq_work_time = 0;
 	bool has_lock;
 	unsigned int i;
 
@@ -145,12 +147,24 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
 	if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) {
 		struct io_sq_data *sq = ctx->sq_data;
 
-		sq_pid = sq->task_pid;
-		sq_cpu = sq->sq_cpu;
+		/*
+		 * sq->thread might be NULL if we raced with the sqpoll
+		 * thread termination.
+		 */
+		if (sq->thread) {
+			sq_pid = sq->task_pid;
+			sq_cpu = sq->sq_cpu;
+			getrusage(sq->thread, RUSAGE_SELF, &sq_usage);
+			sq_total_time = (sq_usage.ru_stime.tv_sec * 1000000
+					 + sq_usage.ru_stime.tv_usec);
+			sq_work_time = sq->work_time;
+		}
 	}
 
 	seq_printf(m, "SqThread:\t%d\n", sq_pid);
 	seq_printf(m, "SqThreadCpu:\t%d\n", sq_cpu);
+	seq_printf(m, "SqTotalTime:\t%llu\n", sq_total_time);
+	seq_printf(m, "SqWorkTime:\t%llu\n", sq_work_time);
 	seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files);
 	for (i = 0; has_lock && i < ctx->nr_user_files; i++) {
 		struct file *f = io_file_from_index(&ctx->file_table, i);
diff --git a/io_uring/filetable.h b/io_uring/filetable.h
index b47adf170c31..b2435c4dca1f 100644
--- a/io_uring/filetable.h
+++ b/io_uring/filetable.h
@@ -17,7 +17,7 @@ int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset);
 int io_register_file_alloc_range(struct io_ring_ctx *ctx,
 				 struct io_uring_file_index_range __user *arg);
 
-unsigned int io_file_get_flags(struct file *file);
+io_req_flags_t io_file_get_flags(struct file *file);
 
 static inline void io_file_bitmap_clear(struct io_file_table *table, int bit)
 {
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 09b6d860deba..cf348c33f485 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -59,7 +59,6 @@
 #include <linux/bvec.h>
 #include <linux/net.h>
 #include <net/sock.h>
-#include <net/af_unix.h>
 #include <linux/anon_inodes.h>
 #include <linux/sched/mm.h>
 #include <linux/uaccess.h>
@@ -95,6 +94,7 @@
 #include "notif.h"
 #include "waitid.h"
 #include "futex.h"
+#include "napi.h"
 
 #include "timeout.h"
 #include "poll.h"
@@ -122,11 +122,6 @@
 #define IO_COMPL_BATCH			32
 #define IO_REQ_ALLOC_BATCH		8
 
-enum {
-	IO_CHECK_CQ_OVERFLOW_BIT,
-	IO_CHECK_CQ_DROPPED_BIT,
-};
-
 struct io_defer_entry {
 	struct list_head	list;
 	struct io_kiocb		*req;
@@ -137,6 +132,14 @@ struct io_defer_entry {
 #define IO_DISARM_MASK (REQ_F_ARM_LTIMEOUT | REQ_F_LINK_TIMEOUT | REQ_F_FAIL)
 #define IO_REQ_LINK_FLAGS (REQ_F_LINK | REQ_F_HARDLINK)
 
+/*
+ * No waiters. It's larger than any valid value of the tw counter
+ * so that tests against ->cq_wait_nr would fail and skip wake_up().
+ */
+#define IO_CQ_WAKE_INIT		(-1U)
+/* Forced wake up if there is a waiter regardless of ->cq_wait_nr */
+#define IO_CQ_WAKE_FORCE	(IO_CQ_WAKE_INIT >> 1)
+
 static bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
 					 struct task_struct *task,
 					 bool cancel_all);
@@ -303,6 +306,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 		goto err;
 
 	ctx->flags = p->flags;
+	atomic_set(&ctx->cq_wait_nr, IO_CQ_WAKE_INIT);
 	init_waitqueue_head(&ctx->sqo_sq_wait);
 	INIT_LIST_HEAD(&ctx->sqd_list);
 	INIT_LIST_HEAD(&ctx->cq_overflow_list);
@@ -340,6 +344,8 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func);
 	INIT_WQ_LIST(&ctx->submit_state.compl_reqs);
 	INIT_HLIST_HEAD(&ctx->cancelable_uring_cmd);
+	io_napi_init(ctx);
+
 	return ctx;
 err:
 	kfree(ctx->cancel_table.hbs);
@@ -454,7 +460,6 @@ static void io_prep_async_work(struct io_kiocb *req)
 
 	req->work.list.next = NULL;
 	req->work.flags = 0;
-	req->work.cancel_seq = atomic_read(&ctx->cancel_seq);
 	if (req->flags & REQ_F_FORCE_ASYNC)
 		req->work.flags |= IO_WQ_WORK_CONCURRENT;
 
@@ -661,7 +666,6 @@ static void io_cq_unlock_post(struct io_ring_ctx *ctx)
 	io_commit_cqring_flush(ctx);
 }
 
-/* Returns true if there are no backlogged entries after the flush */
 static void io_cqring_overflow_kill(struct io_ring_ctx *ctx)
 {
 	struct io_overflow_cqe *ocqe;
@@ -940,6 +944,8 @@ bool io_fill_cqe_req_aux(struct io_kiocb *req, bool defer, s32 res, u32 cflags)
 	u64 user_data = req->cqe.user_data;
 	struct io_uring_cqe *cqe;
 
+	lockdep_assert(!io_wq_current_is_worker());
+
 	if (!defer)
 		return __io_post_aux_cqe(ctx, user_data, res, cflags, false);
 
@@ -1016,15 +1022,15 @@ static void __io_req_complete_post(struct io_kiocb *req, unsigned issue_flags)
 
 void io_req_complete_post(struct io_kiocb *req, unsigned issue_flags)
 {
-	if (req->ctx->task_complete && req->ctx->submitter_task != current) {
+	struct io_ring_ctx *ctx = req->ctx;
+
+	if (ctx->task_complete && ctx->submitter_task != current) {
 		req->io_task_work.func = io_req_task_complete;
 		io_req_task_work_add(req);
 	} else if (!(issue_flags & IO_URING_F_UNLOCKED) ||
-		   !(req->ctx->flags & IORING_SETUP_IOPOLL)) {
+		   !(ctx->flags & IORING_SETUP_IOPOLL)) {
 		__io_req_complete_post(req, issue_flags);
 	} else {
-		struct io_ring_ctx *ctx = req->ctx;
-
 		mutex_lock(&ctx->uring_lock);
 		__io_req_complete_post(req, issue_flags & ~IO_URING_F_UNLOCKED);
 		mutex_unlock(&ctx->uring_lock);
@@ -1165,40 +1171,44 @@ static void ctx_flush_and_put(struct io_ring_ctx *ctx, struct io_tw_state *ts)
 	percpu_ref_put(&ctx->refs);
 }
 
-static unsigned int handle_tw_list(struct llist_node *node,
-				   struct io_ring_ctx **ctx,
-				   struct io_tw_state *ts,
-				   struct llist_node *last)
+/*
+ * Run queued task_work, returning the number of entries processed in *count.
+ * If more entries than max_entries are available, stop processing once this
+ * is reached and return the rest of the list.
+ */
+struct llist_node *io_handle_tw_list(struct llist_node *node,
+				     unsigned int *count,
+				     unsigned int max_entries)
 {
-	unsigned int count = 0;
+	struct io_ring_ctx *ctx = NULL;
+	struct io_tw_state ts = { };
 
-	while (node && node != last) {
+	do {
 		struct llist_node *next = node->next;
 		struct io_kiocb *req = container_of(node, struct io_kiocb,
 						    io_task_work.node);
 
-		prefetch(container_of(next, struct io_kiocb, io_task_work.node));
-
-		if (req->ctx != *ctx) {
-			ctx_flush_and_put(*ctx, ts);
-			*ctx = req->ctx;
+		if (req->ctx != ctx) {
+			ctx_flush_and_put(ctx, &ts);
+			ctx = req->ctx;
 			/* if not contended, grab and improve batching */
-			ts->locked = mutex_trylock(&(*ctx)->uring_lock);
-			percpu_ref_get(&(*ctx)->refs);
+			ts.locked = mutex_trylock(&ctx->uring_lock);
+			percpu_ref_get(&ctx->refs);
 		}
 		INDIRECT_CALL_2(req->io_task_work.func,
 				io_poll_task_func, io_req_rw_complete,
-				req, ts);
+				req, &ts);
 		node = next;
-		count++;
+		(*count)++;
 		if (unlikely(need_resched())) {
-			ctx_flush_and_put(*ctx, ts);
-			*ctx = NULL;
+			ctx_flush_and_put(ctx, &ts);
+			ctx = NULL;
 			cond_resched();
 		}
-	}
+	} while (node && *count < max_entries);
 
-	return count;
+	ctx_flush_and_put(ctx, &ts);
+	return node;
 }
 
 /**
@@ -1215,22 +1225,6 @@ static inline struct llist_node *io_llist_xchg(struct llist_head *head,
 	return xchg(&head->first, new);
 }
 
-/**
- * io_llist_cmpxchg - possibly swap all entries in a lock-less list
- * @head:	the head of lock-less list to delete all entries
- * @old:	expected old value of the first entry of the list
- * @new:	new entry as the head of the list
- *
- * perform a cmpxchg on the first entry of the list.
- */
-
-static inline struct llist_node *io_llist_cmpxchg(struct llist_head *head,
-						  struct llist_node *old,
-						  struct llist_node *new)
-{
-	return cmpxchg(&head->first, old, new);
-}
-
 static __cold void io_fallback_tw(struct io_uring_task *tctx, bool sync)
 {
 	struct llist_node *node = llist_del_all(&tctx->task_list);
@@ -1259,61 +1253,64 @@ static __cold void io_fallback_tw(struct io_uring_task *tctx, bool sync)
 	}
 }
 
-void tctx_task_work(struct callback_head *cb)
+struct llist_node *tctx_task_work_run(struct io_uring_task *tctx,
+				      unsigned int max_entries,
+				      unsigned int *count)
 {
-	struct io_tw_state ts = {};
-	struct io_ring_ctx *ctx = NULL;
-	struct io_uring_task *tctx = container_of(cb, struct io_uring_task,
-						  task_work);
-	struct llist_node fake = {};
 	struct llist_node *node;
-	unsigned int loops = 0;
-	unsigned int count = 0;
 
 	if (unlikely(current->flags & PF_EXITING)) {
 		io_fallback_tw(tctx, true);
-		return;
+		return NULL;
 	}
 
-	do {
-		loops++;
-		node = io_llist_xchg(&tctx->task_list, &fake);
-		count += handle_tw_list(node, &ctx, &ts, &fake);
-
-		/* skip expensive cmpxchg if there are items in the list */
-		if (READ_ONCE(tctx->task_list.first) != &fake)
-			continue;
-		if (ts.locked && !wq_list_empty(&ctx->submit_state.compl_reqs)) {
-			io_submit_flush_completions(ctx);
-			if (READ_ONCE(tctx->task_list.first) != &fake)
-				continue;
-		}
-		node = io_llist_cmpxchg(&tctx->task_list, &fake, NULL);
-	} while (node != &fake);
-
-	ctx_flush_and_put(ctx, &ts);
+	node = llist_del_all(&tctx->task_list);
+	if (node) {
+		node = llist_reverse_order(node);
+		node = io_handle_tw_list(node, count, max_entries);
+	}
 
 	/* relaxed read is enough as only the task itself sets ->in_cancel */
 	if (unlikely(atomic_read(&tctx->in_cancel)))
 		io_uring_drop_tctx_refs(current);
 
-	trace_io_uring_task_work_run(tctx, count, loops);
+	trace_io_uring_task_work_run(tctx, *count);
+	return node;
+}
+
+void tctx_task_work(struct callback_head *cb)
+{
+	struct io_uring_task *tctx;
+	struct llist_node *ret;
+	unsigned int count = 0;
+
+	tctx = container_of(cb, struct io_uring_task, task_work);
+	ret = tctx_task_work_run(tctx, UINT_MAX, &count);
+	/* can't happen */
+	WARN_ON_ONCE(ret);
 }
 
 static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 	unsigned nr_wait, nr_tw, nr_tw_prev;
-	struct llist_node *first;
+	struct llist_node *head;
 
+	/* See comment above IO_CQ_WAKE_INIT */
+	BUILD_BUG_ON(IO_CQ_WAKE_FORCE <= IORING_MAX_CQ_ENTRIES);
+
+	/*
+	 * We don't know how many reuqests is there in the link and whether
+	 * they can even be queued lazily, fall back to non-lazy.
+	 */
 	if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK))
 		flags &= ~IOU_F_TWQ_LAZY_WAKE;
 
-	first = READ_ONCE(ctx->work_llist.first);
+	head = READ_ONCE(ctx->work_llist.first);
 	do {
 		nr_tw_prev = 0;
-		if (first) {
-			struct io_kiocb *first_req = container_of(first,
+		if (head) {
+			struct io_kiocb *first_req = container_of(head,
 							struct io_kiocb,
 							io_task_work.node);
 			/*
@@ -1322,17 +1319,29 @@ static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 			 */
 			nr_tw_prev = READ_ONCE(first_req->nr_tw);
 		}
+
+		/*
+		 * Theoretically, it can overflow, but that's fine as one of
+		 * previous adds should've tried to wake the task.
+		 */
 		nr_tw = nr_tw_prev + 1;
-		/* Large enough to fail the nr_wait comparison below */
 		if (!(flags & IOU_F_TWQ_LAZY_WAKE))
-			nr_tw = -1U;
+			nr_tw = IO_CQ_WAKE_FORCE;
 
 		req->nr_tw = nr_tw;
-		req->io_task_work.node.next = first;
-	} while (!try_cmpxchg(&ctx->work_llist.first, &first,
+		req->io_task_work.node.next = head;
+	} while (!try_cmpxchg(&ctx->work_llist.first, &head,
 			      &req->io_task_work.node));
 
-	if (!first) {
+	/*
+	 * cmpxchg implies a full barrier, which pairs with the barrier
+	 * in set_current_state() on the io_cqring_wait() side. It's used
+	 * to ensure that either we see updated ->cq_wait_nr, or waiters
+	 * going to sleep will observe the work added to the list, which
+	 * is similar to the wait/wawke task state sync.
+	 */
+
+	if (!head) {
 		if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
 			atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
 		if (ctx->has_evfd)
@@ -1340,14 +1349,12 @@ static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 	}
 
 	nr_wait = atomic_read(&ctx->cq_wait_nr);
-	/* no one is waiting */
-	if (!nr_wait)
+	/* not enough or no one is waiting */
+	if (nr_tw < nr_wait)
 		return;
-	/* either not enough or the previous add has already woken it up */
-	if (nr_wait > nr_tw || nr_tw_prev >= nr_wait)
+	/* the previous add has already woken it up */
+	if (nr_tw_prev >= nr_wait)
 		return;
-	/* pairs with set_current_state() in io_cqring_wait() */
-	smp_mb__after_atomic();
 	wake_up_state(ctx->submitter_task, TASK_INTERRUPTIBLE);
 }
 
@@ -1363,6 +1370,15 @@ static void io_req_normal_work_add(struct io_kiocb *req)
 	if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
 		atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
 
+	/* SQPOLL doesn't need the task_work added, it'll run it itself */
+	if (ctx->flags & IORING_SETUP_SQPOLL) {
+		struct io_sq_data *sqd = ctx->sq_data;
+
+		if (wq_has_sleeper(&sqd->wait))
+			wake_up(&sqd->wait);
+		return;
+	}
+
 	if (likely(!task_work_add(req->task, &tctx->task_work, ctx->notify_method)))
 		return;
 
@@ -1394,7 +1410,20 @@ static void __cold io_move_task_work_from_local(struct io_ring_ctx *ctx)
 	}
 }
 
-static int __io_run_local_work(struct io_ring_ctx *ctx, struct io_tw_state *ts)
+static bool io_run_local_work_continue(struct io_ring_ctx *ctx, int events,
+				       int min_events)
+{
+	if (llist_empty(&ctx->work_llist))
+		return false;
+	if (events < min_events)
+		return true;
+	if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
+		atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
+	return false;
+}
+
+static int __io_run_local_work(struct io_ring_ctx *ctx, struct io_tw_state *ts,
+			       int min_events)
 {
 	struct llist_node *node;
 	unsigned int loops = 0;
@@ -1414,7 +1443,6 @@ again:
 		struct llist_node *next = node->next;
 		struct io_kiocb *req = container_of(node, struct io_kiocb,
 						    io_task_work.node);
-		prefetch(container_of(next, struct io_kiocb, io_task_work.node));
 		INDIRECT_CALL_2(req->io_task_work.func,
 				io_poll_task_func, io_req_rw_complete,
 				req, ts);
@@ -1423,18 +1451,20 @@ again:
 	}
 	loops++;
 
-	if (!llist_empty(&ctx->work_llist))
+	if (io_run_local_work_continue(ctx, ret, min_events))
 		goto again;
 	if (ts->locked) {
 		io_submit_flush_completions(ctx);
-		if (!llist_empty(&ctx->work_llist))
+		if (io_run_local_work_continue(ctx, ret, min_events))
 			goto again;
 	}
+
 	trace_io_uring_local_work_run(ctx, ret, loops);
 	return ret;
 }
 
-static inline int io_run_local_work_locked(struct io_ring_ctx *ctx)
+static inline int io_run_local_work_locked(struct io_ring_ctx *ctx,
+					   int min_events)
 {
 	struct io_tw_state ts = { .locked = true, };
 	int ret;
@@ -1442,20 +1472,20 @@ static inline int io_run_local_work_locked(struct io_ring_ctx *ctx)
 	if (llist_empty(&ctx->work_llist))
 		return 0;
 
-	ret = __io_run_local_work(ctx, &ts);
+	ret = __io_run_local_work(ctx, &ts, min_events);
 	/* shouldn't happen! */
 	if (WARN_ON_ONCE(!ts.locked))
 		mutex_lock(&ctx->uring_lock);
 	return ret;
 }
 
-static int io_run_local_work(struct io_ring_ctx *ctx)
+static int io_run_local_work(struct io_ring_ctx *ctx, int min_events)
 {
 	struct io_tw_state ts = {};
 	int ret;
 
 	ts.locked = mutex_trylock(&ctx->uring_lock);
-	ret = __io_run_local_work(ctx, &ts);
+	ret = __io_run_local_work(ctx, &ts, min_events);
 	if (ts.locked)
 		mutex_unlock(&ctx->uring_lock);
 
@@ -1651,7 +1681,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
 		    io_task_work_pending(ctx)) {
 			u32 tail = ctx->cached_cq_tail;
 
-			(void) io_run_local_work_locked(ctx);
+			(void) io_run_local_work_locked(ctx, min);
 
 			if (task_work_pending(current) ||
 			    wq_list_empty(&ctx->iopoll_list)) {
@@ -1742,9 +1772,9 @@ static void io_iopoll_req_issued(struct io_kiocb *req, unsigned int issue_flags)
 	}
 }
 
-unsigned int io_file_get_flags(struct file *file)
+io_req_flags_t io_file_get_flags(struct file *file)
 {
-	unsigned int res = 0;
+	io_req_flags_t res = 0;
 
 	if (S_ISREG(file_inode(file)->i_mode))
 		res |= REQ_F_ISREG;
@@ -1940,10 +1970,28 @@ fail:
 		goto fail;
 	}
 
+	/*
+	 * If DEFER_TASKRUN is set, it's only allowed to post CQEs from the
+	 * submitter task context. Final request completions are handed to the
+	 * right context, however this is not the case of auxiliary CQEs,
+	 * which is the main mean of operation for multishot requests.
+	 * Don't allow any multishot execution from io-wq. It's more restrictive
+	 * than necessary and also cleaner.
+	 */
+	if (req->flags & REQ_F_APOLL_MULTISHOT) {
+		err = -EBADFD;
+		if (!io_file_can_poll(req))
+			goto fail;
+		err = -ECANCELED;
+		if (io_arm_poll_handler(req, issue_flags) != IO_APOLL_OK)
+			goto fail;
+		return;
+	}
+
 	if (req->flags & REQ_F_FORCE_ASYNC) {
 		bool opcode_poll = def->pollin || def->pollout;
 
-		if (opcode_poll && file_can_poll(req->file)) {
+		if (opcode_poll && io_file_can_poll(req)) {
 			needs_poll = true;
 			issue_flags |= IO_URING_F_NONBLOCK;
 		}
@@ -2000,9 +2048,10 @@ inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
 		goto out;
 	fd = array_index_nospec(fd, ctx->nr_user_files);
 	slot = io_fixed_file_slot(&ctx->file_table, fd);
-	file = io_slot_file(slot);
+	if (!req->rsrc_node)
+		__io_req_set_rsrc_node(req, ctx);
 	req->flags |= io_slot_flags(slot);
-	io_req_set_rsrc_node(req, ctx, 0);
+	file = io_slot_file(slot);
 out:
 	io_ring_submit_unlock(ctx, issue_flags);
 	return file;
@@ -2144,7 +2193,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	/* req is partially pre-initialised, see io_preinit_req() */
 	req->opcode = opcode = READ_ONCE(sqe->opcode);
 	/* same numerical values with corresponding REQ_F_*, safe to copy */
-	req->flags = sqe_flags = READ_ONCE(sqe->flags);
+	sqe_flags = READ_ONCE(sqe->flags);
+	req->flags = (io_req_flags_t) sqe_flags;
 	req->cqe.user_data = READ_ONCE(sqe->user_data);
 	req->file = NULL;
 	req->rsrc_node = NULL;
@@ -2448,33 +2498,6 @@ int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
 	return ret;
 }
 
-struct io_wait_queue {
-	struct wait_queue_entry wq;
-	struct io_ring_ctx *ctx;
-	unsigned cq_tail;
-	unsigned nr_timeouts;
-	ktime_t timeout;
-};
-
-static inline bool io_has_work(struct io_ring_ctx *ctx)
-{
-	return test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq) ||
-	       !llist_empty(&ctx->work_llist);
-}
-
-static inline bool io_should_wake(struct io_wait_queue *iowq)
-{
-	struct io_ring_ctx *ctx = iowq->ctx;
-	int dist = READ_ONCE(ctx->rings->cq.tail) - (int) iowq->cq_tail;
-
-	/*
-	 * Wake up if we have enough events, or if a timeout occurred since we
-	 * started waiting. For timeouts, we always want to return to userspace,
-	 * regardless of event count.
-	 */
-	return dist >= 0 || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts;
-}
-
 static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode,
 			    int wake_flags, void *key)
 {
@@ -2493,7 +2516,7 @@ int io_run_task_work_sig(struct io_ring_ctx *ctx)
 {
 	if (!llist_empty(&ctx->work_llist)) {
 		__set_current_state(TASK_RUNNING);
-		if (io_run_local_work(ctx) > 0)
+		if (io_run_local_work(ctx, INT_MAX) > 0)
 			return 0;
 	}
 	if (io_run_task_work() > 0)
@@ -2561,7 +2584,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 	if (!io_allowed_run_tw(ctx))
 		return -EEXIST;
 	if (!llist_empty(&ctx->work_llist))
-		io_run_local_work(ctx);
+		io_run_local_work(ctx, min_events);
 	io_run_task_work();
 	io_cqring_overflow_flush(ctx);
 	/* if user messes with these they will just get an early return */
@@ -2594,16 +2617,19 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 
 		if (get_timespec64(&ts, uts))
 			return -EFAULT;
+
 		iowq.timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns());
+		io_napi_adjust_timeout(ctx, &iowq, &ts);
 	}
 
+	io_napi_busy_loop(ctx, &iowq);
+
 	trace_io_uring_cqring_wait(ctx, min_events);
 	do {
+		int nr_wait = (int) iowq.cq_tail - READ_ONCE(ctx->rings->cq.tail);
 		unsigned long check_cq;
 
 		if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) {
-			int nr_wait = (int) iowq.cq_tail - READ_ONCE(ctx->rings->cq.tail);
-
 			atomic_set(&ctx->cq_wait_nr, nr_wait);
 			set_current_state(TASK_INTERRUPTIBLE);
 		} else {
@@ -2613,7 +2639,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 
 		ret = io_cqring_wait_schedule(ctx, &iowq);
 		__set_current_state(TASK_RUNNING);
-		atomic_set(&ctx->cq_wait_nr, 0);
+		atomic_set(&ctx->cq_wait_nr, IO_CQ_WAKE_INIT);
 
 		/*
 		 * Run task_work after scheduling and before io_should_wake().
@@ -2622,7 +2648,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 		 */
 		io_run_task_work();
 		if (!llist_empty(&ctx->work_llist))
-			io_run_local_work(ctx);
+			io_run_local_work(ctx, nr_wait);
 
 		/*
 		 * Non-local task_work will be run on exit to userspace, but
@@ -2890,6 +2916,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
 	io_req_caches_free(ctx);
 	if (ctx->hash_map)
 		io_wq_put_hash(ctx->hash_map);
+	io_napi_free(ctx);
 	kfree(ctx->cancel_table.hbs);
 	kfree(ctx->cancel_table_locked.hbs);
 	kfree(ctx->io_bl);
@@ -3277,7 +3304,7 @@ static __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
 
 	if ((ctx->flags & IORING_SETUP_DEFER_TASKRUN) &&
 	    io_allowed_defer_tw_run(ctx))
-		ret |= io_run_local_work(ctx) > 0;
+		ret |= io_run_local_work(ctx, INT_MAX) > 0;
 	ret |= io_cancel_defer_files(ctx, task, cancel_all);
 	mutex_lock(&ctx->uring_lock);
 	ret |= io_poll_remove_all(ctx, task, cancel_all);
@@ -3639,7 +3666,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 			 * it should handle ownership problems if any.
 			 */
 			if (ctx->flags & IORING_SETUP_DEFER_TASKRUN)
-				(void)io_run_local_work_locked(ctx);
+				(void)io_run_local_work_locked(ctx, min_complete);
 		}
 		mutex_unlock(&ctx->uring_lock);
 	}
@@ -3787,7 +3814,8 @@ static int io_uring_install_fd(struct file *file)
  */
 static struct file *io_uring_get_file(struct io_ring_ctx *ctx)
 {
-	return anon_inode_getfile_secure("[io_uring]", &io_uring_fops, ctx,
+	/* Create a new inode so that the LSM can block the creation.  */
+	return anon_inode_create_getfile("[io_uring]", &io_uring_fops, ctx,
 					 O_RDWR | O_CLOEXEC, NULL);
 }
 
@@ -4125,7 +4153,7 @@ static int __init io_uring_init(void)
 	BUILD_BUG_ON(SQE_COMMON_FLAGS >= (1 << 8));
 	BUILD_BUG_ON((SQE_VALID_FLAGS | SQE_COMMON_FLAGS) != SQE_VALID_FLAGS);
 
-	BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof(int));
+	BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof_field(struct io_kiocb, flags));
 
 	BUILD_BUG_ON(sizeof(atomic_t) != sizeof(u32));
 
@@ -4147,9 +4175,8 @@ static int __init io_uring_init(void)
 				SLAB_ACCOUNT | SLAB_TYPESAFE_BY_RCU,
 				offsetof(struct io_kiocb, cmd.data),
 				sizeof_field(struct io_kiocb, cmd.data), NULL);
-	io_buf_cachep = kmem_cache_create("io_buffer", sizeof(struct io_buffer), 0,
-					  SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT,
-					  NULL);
+	io_buf_cachep = KMEM_CACHE(io_buffer,
+					  SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT);
 
 #ifdef CONFIG_SYSCTL
 	register_sysctl_init("kernel", kernel_io_uring_disabled_table);
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index 04e33f25919c..6426ee382276 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -5,6 +5,7 @@
 #include <linux/lockdep.h>
 #include <linux/resume_user_mode.h>
 #include <linux/kasan.h>
+#include <linux/poll.h>
 #include <linux/io_uring_types.h>
 #include <uapi/linux/eventpoll.h>
 #include "io-wq.h"
@@ -15,12 +16,18 @@
 #include <trace/events/io_uring.h>
 #endif
 
-
 enum {
 	IOU_OK			= 0,
 	IOU_ISSUE_SKIP_COMPLETE	= -EIOCBQUEUED,
 
 	/*
+	 * Requeue the task_work to restart operations on this request. The
+	 * actual value isn't important, should just be not an otherwise
+	 * valid error code, yet less than -MAX_ERRNO and valid internally.
+	 */
+	IOU_REQUEUE		= -3072,
+
+	/*
 	 * Intended only when both IO_URING_F_MULTISHOT is passed
 	 * to indicate to the poll runner that multishot should be
 	 * removed and the result is set on req->cqe.res.
@@ -28,6 +35,32 @@ enum {
 	IOU_STOP_MULTISHOT	= -ECANCELED,
 };
 
+struct io_wait_queue {
+	struct wait_queue_entry wq;
+	struct io_ring_ctx *ctx;
+	unsigned cq_tail;
+	unsigned nr_timeouts;
+	ktime_t timeout;
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	unsigned int napi_busy_poll_to;
+	bool napi_prefer_busy_poll;
+#endif
+};
+
+static inline bool io_should_wake(struct io_wait_queue *iowq)
+{
+	struct io_ring_ctx *ctx = iowq->ctx;
+	int dist = READ_ONCE(ctx->rings->cq.tail) - (int) iowq->cq_tail;
+
+	/*
+	 * Wake up if we have enough events, or if a timeout occurred since we
+	 * started waiting. For timeouts, we always want to return to userspace,
+	 * regardless of event count.
+	 */
+	return dist >= 0 || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts;
+}
+
 bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow);
 void io_req_cqe_overflow(struct io_kiocb *req);
 int io_run_task_work_sig(struct io_ring_ctx *ctx);
@@ -50,6 +83,8 @@ void io_queue_iowq(struct io_kiocb *req, struct io_tw_state *ts_dont_use);
 void io_req_task_complete(struct io_kiocb *req, struct io_tw_state *ts);
 void io_req_task_queue_fail(struct io_kiocb *req, int ret);
 void io_req_task_submit(struct io_kiocb *req, struct io_tw_state *ts);
+struct llist_node *io_handle_tw_list(struct llist_node *node, unsigned int *count, unsigned int max_entries);
+struct llist_node *tctx_task_work_run(struct io_uring_task *tctx, unsigned int max_entries, unsigned int *count);
 void tctx_task_work(struct callback_head *cb);
 __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd);
 int io_uring_alloc_task_context(struct task_struct *task,
@@ -201,7 +236,7 @@ static inline void io_ring_submit_unlock(struct io_ring_ctx *ctx,
 					 unsigned issue_flags)
 {
 	lockdep_assert_held(&ctx->uring_lock);
-	if (issue_flags & IO_URING_F_UNLOCKED)
+	if (unlikely(issue_flags & IO_URING_F_UNLOCKED))
 		mutex_unlock(&ctx->uring_lock);
 }
 
@@ -214,7 +249,7 @@ static inline void io_ring_submit_lock(struct io_ring_ctx *ctx,
 	 * The only exception is when we've detached the request and issue it
 	 * from an async worker thread, grab the lock for that case.
 	 */
-	if (issue_flags & IO_URING_F_UNLOCKED)
+	if (unlikely(issue_flags & IO_URING_F_UNLOCKED))
 		mutex_lock(&ctx->uring_lock);
 	lockdep_assert_held(&ctx->uring_lock);
 }
@@ -268,6 +303,8 @@ static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
 
 static inline int io_run_task_work(void)
 {
+	bool ret = false;
+
 	/*
 	 * Always check-and-clear the task_work notification signal. With how
 	 * signaling works for task_work, we can find it set with nothing to
@@ -279,18 +316,26 @@ static inline int io_run_task_work(void)
 	 * PF_IO_WORKER never returns to userspace, so check here if we have
 	 * notify work that needs processing.
 	 */
-	if (current->flags & PF_IO_WORKER &&
-	    test_thread_flag(TIF_NOTIFY_RESUME)) {
-		__set_current_state(TASK_RUNNING);
-		resume_user_mode_work(NULL);
+	if (current->flags & PF_IO_WORKER) {
+		if (test_thread_flag(TIF_NOTIFY_RESUME)) {
+			__set_current_state(TASK_RUNNING);
+			resume_user_mode_work(NULL);
+		}
+		if (current->io_uring) {
+			unsigned int count = 0;
+
+			tctx_task_work_run(current->io_uring, UINT_MAX, &count);
+			if (count)
+				ret = true;
+		}
 	}
 	if (task_work_pending(current)) {
 		__set_current_state(TASK_RUNNING);
 		task_work_run();
-		return 1;
+		ret = true;
 	}
 
-	return 0;
+	return ret;
 }
 
 static inline bool io_task_work_pending(struct io_ring_ctx *ctx)
@@ -392,4 +437,26 @@ static inline size_t uring_sqe_size(struct io_ring_ctx *ctx)
 		return 2 * sizeof(struct io_uring_sqe);
 	return sizeof(struct io_uring_sqe);
 }
+
+static inline bool io_file_can_poll(struct io_kiocb *req)
+{
+	if (req->flags & REQ_F_CAN_POLL)
+		return true;
+	if (file_can_poll(req->file)) {
+		req->flags |= REQ_F_CAN_POLL;
+		return true;
+	}
+	return false;
+}
+
+enum {
+	IO_CHECK_CQ_OVERFLOW_BIT,
+	IO_CHECK_CQ_DROPPED_BIT,
+};
+
+static inline bool io_has_work(struct io_ring_ctx *ctx)
+{
+	return test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq) ||
+	       !llist_empty(&ctx->work_llist);
+}
 #endif
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index 18df5a9d2f5e..9be42bff936b 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -81,15 +81,6 @@ bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags)
 	struct io_buffer_list *bl;
 	struct io_buffer *buf;
 
-	/*
-	 * For legacy provided buffer mode, don't recycle if we already did
-	 * IO to this buffer. For ring-mapped provided buffer mode, we should
-	 * increment ring->head to explicitly monopolize the buffer to avoid
-	 * multiple use.
-	 */
-	if (req->flags & REQ_F_PARTIAL_IO)
-		return false;
-
 	io_ring_submit_lock(ctx, issue_flags);
 
 	buf = req->kbuf;
@@ -102,10 +93,8 @@ bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags)
 	return true;
 }
 
-unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags)
+void __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags)
 {
-	unsigned int cflags;
-
 	/*
 	 * We can add this buffer back to two lists:
 	 *
@@ -118,21 +107,17 @@ unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags)
 	 * We migrate buffers from the comp_list to the issue cache list
 	 * when we need one.
 	 */
-	if (req->flags & REQ_F_BUFFER_RING) {
-		/* no buffers to recycle for this case */
-		cflags = __io_put_kbuf_list(req, NULL);
-	} else if (issue_flags & IO_URING_F_UNLOCKED) {
+	if (issue_flags & IO_URING_F_UNLOCKED) {
 		struct io_ring_ctx *ctx = req->ctx;
 
 		spin_lock(&ctx->completion_lock);
-		cflags = __io_put_kbuf_list(req, &ctx->io_buffers_comp);
+		__io_put_kbuf_list(req, &ctx->io_buffers_comp);
 		spin_unlock(&ctx->completion_lock);
 	} else {
 		lockdep_assert_held(&req->ctx->uring_lock);
 
-		cflags = __io_put_kbuf_list(req, &req->ctx->io_buffers_cache);
+		__io_put_kbuf_list(req, &req->ctx->io_buffers_cache);
 	}
-	return cflags;
 }
 
 static void __user *io_provided_buffer_select(struct io_kiocb *req, size_t *len,
@@ -145,6 +130,8 @@ static void __user *io_provided_buffer_select(struct io_kiocb *req, size_t *len,
 		list_del(&kbuf->list);
 		if (*len == 0 || *len > kbuf->len)
 			*len = kbuf->len;
+		if (list_empty(&bl->buf_list))
+			req->flags |= REQ_F_BL_EMPTY;
 		req->flags |= REQ_F_BUFFER_SELECTED;
 		req->kbuf = kbuf;
 		req->buf_index = kbuf->bid;
@@ -158,12 +145,16 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len,
 					  unsigned int issue_flags)
 {
 	struct io_uring_buf_ring *br = bl->buf_ring;
+	__u16 tail, head = bl->head;
 	struct io_uring_buf *buf;
-	__u16 head = bl->head;
 
-	if (unlikely(smp_load_acquire(&br->tail) == head))
+	tail = smp_load_acquire(&br->tail);
+	if (unlikely(tail == head))
 		return NULL;
 
+	if (head + 1 == tail)
+		req->flags |= REQ_F_BL_EMPTY;
+
 	head &= bl->mask;
 	/* mmaped buffers are always contig */
 	if (bl->is_mmap || head < IO_BUFFER_LIST_BUF_PER_PAGE) {
@@ -180,7 +171,7 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len,
 	req->buf_list = bl;
 	req->buf_index = buf->bid;
 
-	if (issue_flags & IO_URING_F_UNLOCKED || !file_can_poll(req->file)) {
+	if (issue_flags & IO_URING_F_UNLOCKED || !io_file_can_poll(req)) {
 		/*
 		 * If we came in unlocked, we have no choice but to consume the
 		 * buffer here, otherwise nothing ensures that the buffer won't
diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h
index 53dfaa71a397..5218bfd79e87 100644
--- a/io_uring/kbuf.h
+++ b/io_uring/kbuf.h
@@ -57,7 +57,7 @@ int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg);
 
 void io_kbuf_mmap_list_free(struct io_ring_ctx *ctx);
 
-unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags);
+void __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags);
 
 bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags);
 
@@ -73,21 +73,9 @@ static inline bool io_kbuf_recycle_ring(struct io_kiocb *req)
 	 * to monopolize the buffer.
 	 */
 	if (req->buf_list) {
-		if (req->flags & REQ_F_PARTIAL_IO) {
-			/*
-			 * If we end up here, then the io_uring_lock has
-			 * been kept held since we retrieved the buffer.
-			 * For the io-wq case, we already cleared
-			 * req->buf_list when the buffer was retrieved,
-			 * hence it cannot be set here for that case.
-			 */
-			req->buf_list->head++;
-			req->buf_list = NULL;
-		} else {
-			req->buf_index = req->buf_list->bgid;
-			req->flags &= ~REQ_F_BUFFER_RING;
-			return true;
-		}
+		req->buf_index = req->buf_list->bgid;
+		req->flags &= ~REQ_F_BUFFER_RING;
+		return true;
 	}
 	return false;
 }
@@ -101,6 +89,8 @@ static inline bool io_do_buffer_select(struct io_kiocb *req)
 
 static inline bool io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags)
 {
+	if (req->flags & REQ_F_BL_NO_RECYCLE)
+		return false;
 	if (req->flags & REQ_F_BUFFER_SELECTED)
 		return io_kbuf_recycle_legacy(req, issue_flags);
 	if (req->flags & REQ_F_BUFFER_RING)
@@ -108,41 +98,54 @@ static inline bool io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags)
 	return false;
 }
 
-static inline unsigned int __io_put_kbuf_list(struct io_kiocb *req,
-					      struct list_head *list)
+static inline void __io_put_kbuf_ring(struct io_kiocb *req)
 {
-	unsigned int ret = IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT);
+	if (req->buf_list) {
+		req->buf_index = req->buf_list->bgid;
+		req->buf_list->head++;
+	}
+	req->flags &= ~REQ_F_BUFFER_RING;
+}
 
+static inline void __io_put_kbuf_list(struct io_kiocb *req,
+				      struct list_head *list)
+{
 	if (req->flags & REQ_F_BUFFER_RING) {
-		if (req->buf_list) {
-			req->buf_index = req->buf_list->bgid;
-			req->buf_list->head++;
-		}
-		req->flags &= ~REQ_F_BUFFER_RING;
+		__io_put_kbuf_ring(req);
 	} else {
 		req->buf_index = req->kbuf->bgid;
 		list_add(&req->kbuf->list, list);
 		req->flags &= ~REQ_F_BUFFER_SELECTED;
 	}
-
-	return ret;
 }
 
 static inline unsigned int io_put_kbuf_comp(struct io_kiocb *req)
 {
+	unsigned int ret;
+
 	lockdep_assert_held(&req->ctx->completion_lock);
 
 	if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)))
 		return 0;
-	return __io_put_kbuf_list(req, &req->ctx->io_buffers_comp);
+
+	ret = IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT);
+	__io_put_kbuf_list(req, &req->ctx->io_buffers_comp);
+	return ret;
 }
 
 static inline unsigned int io_put_kbuf(struct io_kiocb *req,
 				       unsigned issue_flags)
 {
+	unsigned int ret;
 
-	if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)))
+	if (!(req->flags & (REQ_F_BUFFER_RING | REQ_F_BUFFER_SELECTED)))
 		return 0;
-	return __io_put_kbuf(req, issue_flags);
+
+	ret = IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT);
+	if (req->flags & REQ_F_BUFFER_RING)
+		__io_put_kbuf_ring(req);
+	else
+		__io_put_kbuf(req, issue_flags);
+	return ret;
 }
 #endif
diff --git a/io_uring/napi.c b/io_uring/napi.c
new file mode 100644
index 000000000000..883a1a665907
--- /dev/null
+++ b/io_uring/napi.c
@@ -0,0 +1,332 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "io_uring.h"
+#include "napi.h"
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+
+/* Timeout for cleanout of stale entries. */
+#define NAPI_TIMEOUT		(60 * SEC_CONVERSION)
+
+struct io_napi_entry {
+	unsigned int		napi_id;
+	struct list_head	list;
+
+	unsigned long		timeout;
+	struct hlist_node	node;
+
+	struct rcu_head		rcu;
+};
+
+static struct io_napi_entry *io_napi_hash_find(struct hlist_head *hash_list,
+					       unsigned int napi_id)
+{
+	struct io_napi_entry *e;
+
+	hlist_for_each_entry_rcu(e, hash_list, node) {
+		if (e->napi_id != napi_id)
+			continue;
+		e->timeout = jiffies + NAPI_TIMEOUT;
+		return e;
+	}
+
+	return NULL;
+}
+
+void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock)
+{
+	struct hlist_head *hash_list;
+	unsigned int napi_id;
+	struct sock *sk;
+	struct io_napi_entry *e;
+
+	sk = sock->sk;
+	if (!sk)
+		return;
+
+	napi_id = READ_ONCE(sk->sk_napi_id);
+
+	/* Non-NAPI IDs can be rejected. */
+	if (napi_id < MIN_NAPI_ID)
+		return;
+
+	hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx->napi_ht))];
+
+	rcu_read_lock();
+	e = io_napi_hash_find(hash_list, napi_id);
+	if (e) {
+		e->timeout = jiffies + NAPI_TIMEOUT;
+		rcu_read_unlock();
+		return;
+	}
+	rcu_read_unlock();
+
+	e = kmalloc(sizeof(*e), GFP_NOWAIT);
+	if (!e)
+		return;
+
+	e->napi_id = napi_id;
+	e->timeout = jiffies + NAPI_TIMEOUT;
+
+	spin_lock(&ctx->napi_lock);
+	if (unlikely(io_napi_hash_find(hash_list, napi_id))) {
+		spin_unlock(&ctx->napi_lock);
+		kfree(e);
+		return;
+	}
+
+	hlist_add_tail_rcu(&e->node, hash_list);
+	list_add_tail(&e->list, &ctx->napi_list);
+	spin_unlock(&ctx->napi_lock);
+}
+
+static void __io_napi_remove_stale(struct io_ring_ctx *ctx)
+{
+	struct io_napi_entry *e;
+	unsigned int i;
+
+	spin_lock(&ctx->napi_lock);
+	hash_for_each(ctx->napi_ht, i, e, node) {
+		if (time_after(jiffies, e->timeout)) {
+			list_del(&e->list);
+			hash_del_rcu(&e->node);
+			kfree_rcu(e, rcu);
+		}
+	}
+	spin_unlock(&ctx->napi_lock);
+}
+
+static inline void io_napi_remove_stale(struct io_ring_ctx *ctx, bool is_stale)
+{
+	if (is_stale)
+		__io_napi_remove_stale(ctx);
+}
+
+static inline bool io_napi_busy_loop_timeout(unsigned long start_time,
+					     unsigned long bp_usec)
+{
+	if (bp_usec) {
+		unsigned long end_time = start_time + bp_usec;
+		unsigned long now = busy_loop_current_time();
+
+		return time_after(now, end_time);
+	}
+
+	return true;
+}
+
+static bool io_napi_busy_loop_should_end(void *data,
+					 unsigned long start_time)
+{
+	struct io_wait_queue *iowq = data;
+
+	if (signal_pending(current))
+		return true;
+	if (io_should_wake(iowq) || io_has_work(iowq->ctx))
+		return true;
+	if (io_napi_busy_loop_timeout(start_time, iowq->napi_busy_poll_to))
+		return true;
+
+	return false;
+}
+
+static bool __io_napi_do_busy_loop(struct io_ring_ctx *ctx,
+				   void *loop_end_arg)
+{
+	struct io_napi_entry *e;
+	bool (*loop_end)(void *, unsigned long) = NULL;
+	bool is_stale = false;
+
+	if (loop_end_arg)
+		loop_end = io_napi_busy_loop_should_end;
+
+	list_for_each_entry_rcu(e, &ctx->napi_list, list) {
+		napi_busy_loop_rcu(e->napi_id, loop_end, loop_end_arg,
+				   ctx->napi_prefer_busy_poll, BUSY_POLL_BUDGET);
+
+		if (time_after(jiffies, e->timeout))
+			is_stale = true;
+	}
+
+	return is_stale;
+}
+
+static void io_napi_blocking_busy_loop(struct io_ring_ctx *ctx,
+				       struct io_wait_queue *iowq)
+{
+	unsigned long start_time = busy_loop_current_time();
+	void *loop_end_arg = NULL;
+	bool is_stale = false;
+
+	/* Singular lists use a different napi loop end check function and are
+	 * only executed once.
+	 */
+	if (list_is_singular(&ctx->napi_list))
+		loop_end_arg = iowq;
+
+	rcu_read_lock();
+	do {
+		is_stale = __io_napi_do_busy_loop(ctx, loop_end_arg);
+	} while (!io_napi_busy_loop_should_end(iowq, start_time) && !loop_end_arg);
+	rcu_read_unlock();
+
+	io_napi_remove_stale(ctx, is_stale);
+}
+
+/*
+ * io_napi_init() - Init napi settings
+ * @ctx: pointer to io-uring context structure
+ *
+ * Init napi settings in the io-uring context.
+ */
+void io_napi_init(struct io_ring_ctx *ctx)
+{
+	INIT_LIST_HEAD(&ctx->napi_list);
+	spin_lock_init(&ctx->napi_lock);
+	ctx->napi_prefer_busy_poll = false;
+	ctx->napi_busy_poll_to = READ_ONCE(sysctl_net_busy_poll);
+}
+
+/*
+ * io_napi_free() - Deallocate napi
+ * @ctx: pointer to io-uring context structure
+ *
+ * Free the napi list and the hash table in the io-uring context.
+ */
+void io_napi_free(struct io_ring_ctx *ctx)
+{
+	struct io_napi_entry *e;
+	LIST_HEAD(napi_list);
+	unsigned int i;
+
+	spin_lock(&ctx->napi_lock);
+	hash_for_each(ctx->napi_ht, i, e, node) {
+		hash_del_rcu(&e->node);
+		kfree_rcu(e, rcu);
+	}
+	spin_unlock(&ctx->napi_lock);
+}
+
+/*
+ * io_napi_register() - Register napi with io-uring
+ * @ctx: pointer to io-uring context structure
+ * @arg: pointer to io_uring_napi structure
+ *
+ * Register napi in the io-uring context.
+ */
+int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
+{
+	const struct io_uring_napi curr = {
+		.busy_poll_to 	  = ctx->napi_busy_poll_to,
+		.prefer_busy_poll = ctx->napi_prefer_busy_poll
+	};
+	struct io_uring_napi napi;
+
+	if (copy_from_user(&napi, arg, sizeof(napi)))
+		return -EFAULT;
+	if (napi.pad[0] || napi.pad[1] || napi.pad[2] || napi.resv)
+		return -EINVAL;
+
+	if (copy_to_user(arg, &curr, sizeof(curr)))
+		return -EFAULT;
+
+	WRITE_ONCE(ctx->napi_busy_poll_to, napi.busy_poll_to);
+	WRITE_ONCE(ctx->napi_prefer_busy_poll, !!napi.prefer_busy_poll);
+	WRITE_ONCE(ctx->napi_enabled, true);
+	return 0;
+}
+
+/*
+ * io_napi_unregister() - Unregister napi with io-uring
+ * @ctx: pointer to io-uring context structure
+ * @arg: pointer to io_uring_napi structure
+ *
+ * Unregister napi. If arg has been specified copy the busy poll timeout and
+ * prefer busy poll setting to the passed in structure.
+ */
+int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg)
+{
+	const struct io_uring_napi curr = {
+		.busy_poll_to 	  = ctx->napi_busy_poll_to,
+		.prefer_busy_poll = ctx->napi_prefer_busy_poll
+	};
+
+	if (arg && copy_to_user(arg, &curr, sizeof(curr)))
+		return -EFAULT;
+
+	WRITE_ONCE(ctx->napi_busy_poll_to, 0);
+	WRITE_ONCE(ctx->napi_prefer_busy_poll, false);
+	WRITE_ONCE(ctx->napi_enabled, false);
+	return 0;
+}
+
+/*
+ * __io_napi_adjust_timeout() - Add napi id to the busy poll list
+ * @ctx: pointer to io-uring context structure
+ * @iowq: pointer to io wait queue
+ * @ts: pointer to timespec or NULL
+ *
+ * Adjust the busy loop timeout according to timespec and busy poll timeout.
+ */
+void __io_napi_adjust_timeout(struct io_ring_ctx *ctx, struct io_wait_queue *iowq,
+			      struct timespec64 *ts)
+{
+	unsigned int poll_to = READ_ONCE(ctx->napi_busy_poll_to);
+
+	if (ts) {
+		struct timespec64 poll_to_ts = ns_to_timespec64(1000 * (s64)poll_to);
+
+		if (timespec64_compare(ts, &poll_to_ts) > 0) {
+			*ts = timespec64_sub(*ts, poll_to_ts);
+		} else {
+			u64 to = timespec64_to_ns(ts);
+
+			do_div(to, 1000);
+			ts->tv_sec = 0;
+			ts->tv_nsec = 0;
+		}
+	}
+
+	iowq->napi_busy_poll_to = poll_to;
+}
+
+/*
+ * __io_napi_busy_loop() - execute busy poll loop
+ * @ctx: pointer to io-uring context structure
+ * @iowq: pointer to io wait queue
+ *
+ * Execute the busy poll loop and merge the spliced off list.
+ */
+void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq)
+{
+	iowq->napi_prefer_busy_poll = READ_ONCE(ctx->napi_prefer_busy_poll);
+
+	if (!(ctx->flags & IORING_SETUP_SQPOLL) && ctx->napi_enabled)
+		io_napi_blocking_busy_loop(ctx, iowq);
+}
+
+/*
+ * io_napi_sqpoll_busy_poll() - busy poll loop for sqpoll
+ * @ctx: pointer to io-uring context structure
+ *
+ * Splice of the napi list and execute the napi busy poll loop.
+ */
+int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx)
+{
+	LIST_HEAD(napi_list);
+	bool is_stale = false;
+
+	if (!READ_ONCE(ctx->napi_busy_poll_to))
+		return 0;
+	if (list_empty_careful(&ctx->napi_list))
+		return 0;
+
+	rcu_read_lock();
+	is_stale = __io_napi_do_busy_loop(ctx, NULL);
+	rcu_read_unlock();
+
+	io_napi_remove_stale(ctx, is_stale);
+	return 1;
+}
+
+#endif
diff --git a/io_uring/napi.h b/io_uring/napi.h
new file mode 100644
index 000000000000..6fc0393d0dbe
--- /dev/null
+++ b/io_uring/napi.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef IOU_NAPI_H
+#define IOU_NAPI_H
+
+#include <linux/kernel.h>
+#include <linux/io_uring.h>
+#include <net/busy_poll.h>
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+
+void io_napi_init(struct io_ring_ctx *ctx);
+void io_napi_free(struct io_ring_ctx *ctx);
+
+int io_register_napi(struct io_ring_ctx *ctx, void __user *arg);
+int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg);
+
+void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock);
+
+void __io_napi_adjust_timeout(struct io_ring_ctx *ctx,
+		struct io_wait_queue *iowq, struct timespec64 *ts);
+void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq);
+int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx);
+
+static inline bool io_napi(struct io_ring_ctx *ctx)
+{
+	return !list_empty(&ctx->napi_list);
+}
+
+static inline void io_napi_adjust_timeout(struct io_ring_ctx *ctx,
+					  struct io_wait_queue *iowq,
+					  struct timespec64 *ts)
+{
+	if (!io_napi(ctx))
+		return;
+	__io_napi_adjust_timeout(ctx, iowq, ts);
+}
+
+static inline void io_napi_busy_loop(struct io_ring_ctx *ctx,
+				     struct io_wait_queue *iowq)
+{
+	if (!io_napi(ctx))
+		return;
+	__io_napi_busy_loop(ctx, iowq);
+}
+
+/*
+ * io_napi_add() - Add napi id to the busy poll list
+ * @req: pointer to io_kiocb request
+ *
+ * Add the napi id of the socket to the napi busy poll list and hash table.
+ */
+static inline void io_napi_add(struct io_kiocb *req)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+	struct socket *sock;
+
+	if (!READ_ONCE(ctx->napi_busy_poll_to))
+		return;
+
+	sock = sock_from_file(req->file);
+	if (sock)
+		__io_napi_add(ctx, sock);
+}
+
+#else
+
+static inline void io_napi_init(struct io_ring_ctx *ctx)
+{
+}
+static inline void io_napi_free(struct io_ring_ctx *ctx)
+{
+}
+static inline int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
+{
+	return -EOPNOTSUPP;
+}
+static inline int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg)
+{
+	return -EOPNOTSUPP;
+}
+static inline bool io_napi(struct io_ring_ctx *ctx)
+{
+	return false;
+}
+static inline void io_napi_add(struct io_kiocb *req)
+{
+}
+static inline void io_napi_adjust_timeout(struct io_ring_ctx *ctx,
+					  struct io_wait_queue *iowq,
+					  struct timespec64 *ts)
+{
+}
+static inline void io_napi_busy_loop(struct io_ring_ctx *ctx,
+				     struct io_wait_queue *iowq)
+{
+}
+static inline int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx)
+{
+	return 0;
+}
+#endif /* CONFIG_NET_RX_BUSY_POLL */
+
+#endif
diff --git a/io_uring/net.c b/io_uring/net.c
index 75d494dad7e2..19451f0dbf81 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -60,6 +60,7 @@ struct io_sr_msg {
 	unsigned			len;
 	unsigned			done_io;
 	unsigned			msg_flags;
+	unsigned			nr_multishot_loops;
 	u16				flags;
 	/* initialised and used only by !msg send variants */
 	u16				addr_len;
@@ -70,18 +71,12 @@ struct io_sr_msg {
 	struct io_kiocb 		*notif;
 };
 
-static inline bool io_check_multishot(struct io_kiocb *req,
-				      unsigned int issue_flags)
-{
-	/*
-	 * When ->locked_cq is set we only allow to post CQEs from the original
-	 * task context. Usual request completions will be handled in other
-	 * generic paths but multipoll may decide to post extra cqes.
-	 */
-	return !(issue_flags & IO_URING_F_IOWQ) ||
-		!(issue_flags & IO_URING_F_MULTISHOT) ||
-		!req->ctx->task_complete;
-}
+/*
+ * Number of times we'll try and do receives if there's more data. If we
+ * exceed this limit, then add us to the back of the queue and retry from
+ * there. This helps fairness between flooding clients.
+ */
+#define MULTISHOT_MAX_RETRY	32
 
 int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
@@ -196,16 +191,130 @@ static int io_setup_async_msg(struct io_kiocb *req,
 	return -EAGAIN;
 }
 
+#ifdef CONFIG_COMPAT
+static int io_compat_msg_copy_hdr(struct io_kiocb *req,
+				  struct io_async_msghdr *iomsg,
+				  struct compat_msghdr *msg, int ddir)
+{
+	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
+	struct compat_iovec __user *uiov;
+	int ret;
+
+	if (copy_from_user(msg, sr->umsg_compat, sizeof(*msg)))
+		return -EFAULT;
+
+	uiov = compat_ptr(msg->msg_iov);
+	if (req->flags & REQ_F_BUFFER_SELECT) {
+		compat_ssize_t clen;
+
+		iomsg->free_iov = NULL;
+		if (msg->msg_iovlen == 0) {
+			sr->len = 0;
+		} else if (msg->msg_iovlen > 1) {
+			return -EINVAL;
+		} else {
+			if (!access_ok(uiov, sizeof(*uiov)))
+				return -EFAULT;
+			if (__get_user(clen, &uiov->iov_len))
+				return -EFAULT;
+			if (clen < 0)
+				return -EINVAL;
+			sr->len = clen;
+		}
+
+		return 0;
+	}
+
+	iomsg->free_iov = iomsg->fast_iov;
+	ret = __import_iovec(ddir, (struct iovec __user *)uiov, msg->msg_iovlen,
+				UIO_FASTIOV, &iomsg->free_iov,
+				&iomsg->msg.msg_iter, true);
+	if (unlikely(ret < 0))
+		return ret;
+
+	return 0;
+}
+#endif
+
+static int io_msg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg,
+			   struct user_msghdr *msg, int ddir)
+{
+	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
+	int ret;
+
+	if (!user_access_begin(sr->umsg, sizeof(*sr->umsg)))
+		return -EFAULT;
+
+	ret = -EFAULT;
+	unsafe_get_user(msg->msg_name, &sr->umsg->msg_name, ua_end);
+	unsafe_get_user(msg->msg_namelen, &sr->umsg->msg_namelen, ua_end);
+	unsafe_get_user(msg->msg_iov, &sr->umsg->msg_iov, ua_end);
+	unsafe_get_user(msg->msg_iovlen, &sr->umsg->msg_iovlen, ua_end);
+	unsafe_get_user(msg->msg_control, &sr->umsg->msg_control, ua_end);
+	unsafe_get_user(msg->msg_controllen, &sr->umsg->msg_controllen, ua_end);
+	msg->msg_flags = 0;
+
+	if (req->flags & REQ_F_BUFFER_SELECT) {
+		if (msg->msg_iovlen == 0) {
+			sr->len = iomsg->fast_iov[0].iov_len = 0;
+			iomsg->fast_iov[0].iov_base = NULL;
+			iomsg->free_iov = NULL;
+		} else if (msg->msg_iovlen > 1) {
+			ret = -EINVAL;
+			goto ua_end;
+		} else {
+			/* we only need the length for provided buffers */
+			if (!access_ok(&msg->msg_iov[0].iov_len, sizeof(__kernel_size_t)))
+				goto ua_end;
+			unsafe_get_user(iomsg->fast_iov[0].iov_len,
+					&msg->msg_iov[0].iov_len, ua_end);
+			sr->len = iomsg->fast_iov[0].iov_len;
+			iomsg->free_iov = NULL;
+		}
+		ret = 0;
+ua_end:
+		user_access_end();
+		return ret;
+	}
+
+	user_access_end();
+	iomsg->free_iov = iomsg->fast_iov;
+	ret = __import_iovec(ddir, msg->msg_iov, msg->msg_iovlen, UIO_FASTIOV,
+				&iomsg->free_iov, &iomsg->msg.msg_iter, false);
+	if (unlikely(ret < 0))
+		return ret;
+
+	return 0;
+}
+
 static int io_sendmsg_copy_hdr(struct io_kiocb *req,
 			       struct io_async_msghdr *iomsg)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
+	struct user_msghdr msg;
 	int ret;
 
 	iomsg->msg.msg_name = &iomsg->addr;
-	iomsg->free_iov = iomsg->fast_iov;
-	ret = sendmsg_copy_msghdr(&iomsg->msg, sr->umsg, sr->msg_flags,
-					&iomsg->free_iov);
+	iomsg->msg.msg_iter.nr_segs = 0;
+
+#ifdef CONFIG_COMPAT
+	if (unlikely(req->ctx->compat)) {
+		struct compat_msghdr cmsg;
+
+		ret = io_compat_msg_copy_hdr(req, iomsg, &cmsg, ITER_SOURCE);
+		if (unlikely(ret))
+			return ret;
+
+		return __get_compat_msghdr(&iomsg->msg, &cmsg, NULL);
+	}
+#endif
+
+	ret = io_msg_copy_hdr(req, iomsg, &msg, ITER_SOURCE);
+	if (unlikely(ret))
+		return ret;
+
+	ret = __copy_msghdr(&iomsg->msg, &msg, NULL);
+
 	/* save msg_control as sys_sendmsg() overwrites it */
 	sr->msg_control = iomsg->msg.msg_control_user;
 	return ret;
@@ -265,6 +374,8 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
 
+	sr->done_io = 0;
+
 	if (req->opcode == IORING_OP_SEND) {
 		if (READ_ONCE(sqe->__pad3[0]))
 			return -EINVAL;
@@ -287,10 +398,20 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	if (req->ctx->compat)
 		sr->msg_flags |= MSG_CMSG_COMPAT;
 #endif
-	sr->done_io = 0;
 	return 0;
 }
 
+static void io_req_msg_cleanup(struct io_kiocb *req,
+			       struct io_async_msghdr *kmsg,
+			       unsigned int issue_flags)
+{
+	req->flags &= ~REQ_F_NEED_CLEANUP;
+	/* fast path, check for non-NULL to avoid function call */
+	if (kmsg->free_iov)
+		kfree(kmsg->free_iov);
+	io_netmsg_recycle(req, issue_flags);
+}
+
 int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
@@ -333,18 +454,14 @@ int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
 			kmsg->msg.msg_controllen = 0;
 			kmsg->msg.msg_control = NULL;
 			sr->done_io += ret;
-			req->flags |= REQ_F_PARTIAL_IO;
+			req->flags |= REQ_F_BL_NO_RECYCLE;
 			return io_setup_async_msg(req, kmsg, issue_flags);
 		}
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;
 		req_set_fail(req);
 	}
-	/* fast path, check for non-NULL to avoid function call */
-	if (kmsg->free_iov)
-		kfree(kmsg->free_iov);
-	req->flags &= ~REQ_F_NEED_CLEANUP;
-	io_netmsg_recycle(req, issue_flags);
+	io_req_msg_cleanup(req, kmsg, issue_flags);
 	if (ret >= 0)
 		ret += sr->done_io;
 	else if (sr->done_io)
@@ -412,7 +529,7 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags)
 			sr->len -= ret;
 			sr->buf += ret;
 			sr->done_io += ret;
-			req->flags |= REQ_F_PARTIAL_IO;
+			req->flags |= REQ_F_BL_NO_RECYCLE;
 			return io_setup_async_addr(req, &__address, issue_flags);
 		}
 		if (ret == -ERESTARTSYS)
@@ -427,142 +544,77 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags)
 	return IOU_OK;
 }
 
-static bool io_recvmsg_multishot_overflow(struct io_async_msghdr *iomsg)
+static int io_recvmsg_mshot_prep(struct io_kiocb *req,
+				 struct io_async_msghdr *iomsg,
+				 int namelen, size_t controllen)
 {
-	int hdr;
-
-	if (iomsg->namelen < 0)
-		return true;
-	if (check_add_overflow((int)sizeof(struct io_uring_recvmsg_out),
-			       iomsg->namelen, &hdr))
-		return true;
-	if (check_add_overflow(hdr, (int)iomsg->controllen, &hdr))
-		return true;
+	if ((req->flags & (REQ_F_APOLL_MULTISHOT|REQ_F_BUFFER_SELECT)) ==
+			  (REQ_F_APOLL_MULTISHOT|REQ_F_BUFFER_SELECT)) {
+		int hdr;
+
+		if (unlikely(namelen < 0))
+			return -EOVERFLOW;
+		if (check_add_overflow(sizeof(struct io_uring_recvmsg_out),
+					namelen, &hdr))
+			return -EOVERFLOW;
+		if (check_add_overflow(hdr, controllen, &hdr))
+			return -EOVERFLOW;
+
+		iomsg->namelen = namelen;
+		iomsg->controllen = controllen;
+		return 0;
+	}
 
-	return false;
+	return 0;
 }
 
-static int __io_recvmsg_copy_hdr(struct io_kiocb *req,
-				 struct io_async_msghdr *iomsg)
+static int io_recvmsg_copy_hdr(struct io_kiocb *req,
+			       struct io_async_msghdr *iomsg)
 {
-	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
 	struct user_msghdr msg;
 	int ret;
 
-	if (copy_from_user(&msg, sr->umsg, sizeof(*sr->umsg)))
-		return -EFAULT;
-
-	ret = __copy_msghdr(&iomsg->msg, &msg, &iomsg->uaddr);
-	if (ret)
-		return ret;
-
-	if (req->flags & REQ_F_BUFFER_SELECT) {
-		if (msg.msg_iovlen == 0) {
-			sr->len = iomsg->fast_iov[0].iov_len = 0;
-			iomsg->fast_iov[0].iov_base = NULL;
-			iomsg->free_iov = NULL;
-		} else if (msg.msg_iovlen > 1) {
-			return -EINVAL;
-		} else {
-			if (copy_from_user(iomsg->fast_iov, msg.msg_iov, sizeof(*msg.msg_iov)))
-				return -EFAULT;
-			sr->len = iomsg->fast_iov[0].iov_len;
-			iomsg->free_iov = NULL;
-		}
-
-		if (req->flags & REQ_F_APOLL_MULTISHOT) {
-			iomsg->namelen = msg.msg_namelen;
-			iomsg->controllen = msg.msg_controllen;
-			if (io_recvmsg_multishot_overflow(iomsg))
-				return -EOVERFLOW;
-		}
-	} else {
-		iomsg->free_iov = iomsg->fast_iov;
-		ret = __import_iovec(ITER_DEST, msg.msg_iov, msg.msg_iovlen, UIO_FASTIOV,
-				     &iomsg->free_iov, &iomsg->msg.msg_iter,
-				     false);
-		if (ret > 0)
-			ret = 0;
-	}
-
-	return ret;
-}
+	iomsg->msg.msg_name = &iomsg->addr;
+	iomsg->msg.msg_iter.nr_segs = 0;
 
 #ifdef CONFIG_COMPAT
-static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req,
-					struct io_async_msghdr *iomsg)
-{
-	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
-	struct compat_msghdr msg;
-	struct compat_iovec __user *uiov;
-	int ret;
+	if (unlikely(req->ctx->compat)) {
+		struct compat_msghdr cmsg;
 
-	if (copy_from_user(&msg, sr->umsg_compat, sizeof(msg)))
-		return -EFAULT;
-
-	ret = __get_compat_msghdr(&iomsg->msg, &msg, &iomsg->uaddr);
-	if (ret)
-		return ret;
-
-	uiov = compat_ptr(msg.msg_iov);
-	if (req->flags & REQ_F_BUFFER_SELECT) {
-		compat_ssize_t clen;
-
-		iomsg->free_iov = NULL;
-		if (msg.msg_iovlen == 0) {
-			sr->len = 0;
-		} else if (msg.msg_iovlen > 1) {
-			return -EINVAL;
-		} else {
-			if (!access_ok(uiov, sizeof(*uiov)))
-				return -EFAULT;
-			if (__get_user(clen, &uiov->iov_len))
-				return -EFAULT;
-			if (clen < 0)
-				return -EINVAL;
-			sr->len = clen;
-		}
+		ret = io_compat_msg_copy_hdr(req, iomsg, &cmsg, ITER_DEST);
+		if (unlikely(ret))
+			return ret;
 
-		if (req->flags & REQ_F_APOLL_MULTISHOT) {
-			iomsg->namelen = msg.msg_namelen;
-			iomsg->controllen = msg.msg_controllen;
-			if (io_recvmsg_multishot_overflow(iomsg))
-				return -EOVERFLOW;
-		}
-	} else {
-		iomsg->free_iov = iomsg->fast_iov;
-		ret = __import_iovec(ITER_DEST, (struct iovec __user *)uiov, msg.msg_iovlen,
-				   UIO_FASTIOV, &iomsg->free_iov,
-				   &iomsg->msg.msg_iter, true);
-		if (ret < 0)
+		ret = __get_compat_msghdr(&iomsg->msg, &cmsg, &iomsg->uaddr);
+		if (unlikely(ret))
 			return ret;
-	}
 
-	return 0;
-}
+		return io_recvmsg_mshot_prep(req, iomsg, cmsg.msg_namelen,
+						cmsg.msg_controllen);
+	}
 #endif
 
-static int io_recvmsg_copy_hdr(struct io_kiocb *req,
-			       struct io_async_msghdr *iomsg)
-{
-	iomsg->msg.msg_name = &iomsg->addr;
-	iomsg->msg.msg_iter.nr_segs = 0;
+	ret = io_msg_copy_hdr(req, iomsg, &msg, ITER_DEST);
+	if (unlikely(ret))
+		return ret;
 
-#ifdef CONFIG_COMPAT
-	if (req->ctx->compat)
-		return __io_compat_recvmsg_copy_hdr(req, iomsg);
-#endif
+	ret = __copy_msghdr(&iomsg->msg, &msg, &iomsg->uaddr);
+	if (unlikely(ret))
+		return ret;
 
-	return __io_recvmsg_copy_hdr(req, iomsg);
+	return io_recvmsg_mshot_prep(req, iomsg, msg.msg_namelen,
+					msg.msg_controllen);
 }
 
 int io_recvmsg_prep_async(struct io_kiocb *req)
 {
+	struct io_async_msghdr *iomsg;
 	int ret;
 
 	if (!io_msg_alloc_async_prep(req))
 		return -ENOMEM;
-	ret = io_recvmsg_copy_hdr(req, req->async_data);
+	iomsg = req->async_data;
+	ret = io_recvmsg_copy_hdr(req, iomsg);
 	if (!ret)
 		req->flags |= REQ_F_NEED_CLEANUP;
 	return ret;
@@ -574,6 +626,8 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
 
+	sr->done_io = 0;
+
 	if (unlikely(sqe->file_index || sqe->addr2))
 		return -EINVAL;
 
@@ -610,7 +664,7 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	if (req->ctx->compat)
 		sr->msg_flags |= MSG_CMSG_COMPAT;
 #endif
-	sr->done_io = 0;
+	sr->nr_multishot_loops = 0;
 	return 0;
 }
 
@@ -618,6 +672,7 @@ static inline void io_recv_prep_retry(struct io_kiocb *req)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
 
+	req->flags &= ~REQ_F_BL_EMPTY;
 	sr->done_io = 0;
 	sr->len = 0; /* get from the provided buffer */
 	req->buf_index = sr->buf_group;
@@ -636,32 +691,36 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret,
 	unsigned int cflags;
 
 	cflags = io_put_kbuf(req, issue_flags);
-	if (msg->msg_inq && msg->msg_inq != -1)
+	if (msg->msg_inq > 0)
 		cflags |= IORING_CQE_F_SOCK_NONEMPTY;
 
-	if (!(req->flags & REQ_F_APOLL_MULTISHOT)) {
-		io_req_set_res(req, *ret, cflags);
-		*ret = IOU_OK;
-		return true;
-	}
-
-	if (!mshot_finished) {
-		if (io_fill_cqe_req_aux(req, issue_flags & IO_URING_F_COMPLETE_DEFER,
-					*ret, cflags | IORING_CQE_F_MORE)) {
-			io_recv_prep_retry(req);
-			/* Known not-empty or unknown state, retry */
-			if (cflags & IORING_CQE_F_SOCK_NONEMPTY ||
-			    msg->msg_inq == -1)
+	/*
+	 * Fill CQE for this receive and see if we should keep trying to
+	 * receive from this socket.
+	 */
+	if ((req->flags & REQ_F_APOLL_MULTISHOT) && !mshot_finished &&
+	    io_fill_cqe_req_aux(req, issue_flags & IO_URING_F_COMPLETE_DEFER,
+				*ret, cflags | IORING_CQE_F_MORE)) {
+		struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
+		int mshot_retry_ret = IOU_ISSUE_SKIP_COMPLETE;
+
+		io_recv_prep_retry(req);
+		/* Known not-empty or unknown state, retry */
+		if (cflags & IORING_CQE_F_SOCK_NONEMPTY || msg->msg_inq < 0) {
+			if (sr->nr_multishot_loops++ < MULTISHOT_MAX_RETRY)
 				return false;
-			if (issue_flags & IO_URING_F_MULTISHOT)
-				*ret = IOU_ISSUE_SKIP_COMPLETE;
-			else
-				*ret = -EAGAIN;
-			return true;
+			/* mshot retries exceeded, force a requeue */
+			sr->nr_multishot_loops = 0;
+			mshot_retry_ret = IOU_REQUEUE;
 		}
-		/* Otherwise stop multishot but use the current result. */
+		if (issue_flags & IO_URING_F_MULTISHOT)
+			*ret = mshot_retry_ret;
+		else
+			*ret = -EAGAIN;
+		return true;
 	}
 
+	/* Finish the request / stop multishot. */
 	io_req_set_res(req, *ret, cflags);
 
 	if (issue_flags & IO_URING_F_MULTISHOT)
@@ -782,8 +841,9 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 	    (sr->flags & IORING_RECVSEND_POLL_FIRST))
 		return io_setup_async_msg(req, kmsg, issue_flags);
 
-	if (!io_check_multishot(req, issue_flags))
-		return io_setup_async_msg(req, kmsg, issue_flags);
+	flags = sr->msg_flags;
+	if (force_nonblock)
+		flags |= MSG_DONTWAIT;
 
 retry_multishot:
 	if (io_do_buffer_select(req)) {
@@ -805,10 +865,6 @@ retry_multishot:
 		iov_iter_ubuf(&kmsg->msg.msg_iter, ITER_DEST, buf, len);
 	}
 
-	flags = sr->msg_flags;
-	if (force_nonblock)
-		flags |= MSG_DONTWAIT;
-
 	kmsg->msg.msg_get_inq = 1;
 	kmsg->msg.msg_inq = -1;
 	if (req->flags & REQ_F_APOLL_MULTISHOT) {
@@ -834,7 +890,7 @@ retry_multishot:
 		}
 		if (ret > 0 && io_net_retry(sock, flags)) {
 			sr->done_io += ret;
-			req->flags |= REQ_F_PARTIAL_IO;
+			req->flags |= REQ_F_BL_NO_RECYCLE;
 			return io_setup_async_msg(req, kmsg, issue_flags);
 		}
 		if (ret == -ERESTARTSYS)
@@ -854,13 +910,10 @@ retry_multishot:
 	if (!io_recv_finish(req, &ret, &kmsg->msg, mshot_finished, issue_flags))
 		goto retry_multishot;
 
-	if (mshot_finished) {
-		/* fast path, check for non-NULL to avoid function call */
-		if (kmsg->free_iov)
-			kfree(kmsg->free_iov);
-		io_netmsg_recycle(req, issue_flags);
-		req->flags &= ~REQ_F_NEED_CLEANUP;
-	}
+	if (mshot_finished)
+		io_req_msg_cleanup(req, kmsg, issue_flags);
+	else if (ret == -EAGAIN)
+		return io_setup_async_msg(req, kmsg, issue_flags);
 
 	return ret;
 }
@@ -879,9 +932,6 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 	    (sr->flags & IORING_RECVSEND_POLL_FIRST))
 		return -EAGAIN;
 
-	if (!io_check_multishot(req, issue_flags))
-		return -EAGAIN;
-
 	sock = sock_from_file(req->file);
 	if (unlikely(!sock))
 		return -ENOTSOCK;
@@ -894,6 +944,10 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 	msg.msg_iocb = NULL;
 	msg.msg_ubuf = NULL;
 
+	flags = sr->msg_flags;
+	if (force_nonblock)
+		flags |= MSG_DONTWAIT;
+
 retry_multishot:
 	if (io_do_buffer_select(req)) {
 		void __user *buf;
@@ -902,6 +956,7 @@ retry_multishot:
 		if (!buf)
 			return -ENOBUFS;
 		sr->buf = buf;
+		sr->len = len;
 	}
 
 	ret = import_ubuf(ITER_DEST, sr->buf, len, &msg.msg_iter);
@@ -911,9 +966,6 @@ retry_multishot:
 	msg.msg_inq = -1;
 	msg.msg_flags = 0;
 
-	flags = sr->msg_flags;
-	if (force_nonblock)
-		flags |= MSG_DONTWAIT;
 	if (flags & MSG_WAITALL)
 		min_ret = iov_iter_count(&msg.msg_iter);
 
@@ -931,7 +983,7 @@ retry_multishot:
 			sr->len -= ret;
 			sr->buf += ret;
 			sr->done_io += ret;
-			req->flags |= REQ_F_PARTIAL_IO;
+			req->flags |= REQ_F_BL_NO_RECYCLE;
 			return -EAGAIN;
 		}
 		if (ret == -ERESTARTSYS)
@@ -981,6 +1033,8 @@ int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	struct io_ring_ctx *ctx = req->ctx;
 	struct io_kiocb *notif;
 
+	zc->done_io = 0;
+
 	if (unlikely(READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3)))
 		return -EINVAL;
 	/* we don't support IOSQE_CQE_SKIP_SUCCESS just yet */
@@ -1033,8 +1087,6 @@ int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	if (zc->msg_flags & MSG_DONTWAIT)
 		req->flags |= REQ_F_NOWAIT;
 
-	zc->done_io = 0;
-
 #ifdef CONFIG_COMPAT
 	if (req->ctx->compat)
 		zc->msg_flags |= MSG_CMSG_COMPAT;
@@ -1174,7 +1226,7 @@ int io_send_zc(struct io_kiocb *req, unsigned int issue_flags)
 			zc->len -= ret;
 			zc->buf += ret;
 			zc->done_io += ret;
-			req->flags |= REQ_F_PARTIAL_IO;
+			req->flags |= REQ_F_BL_NO_RECYCLE;
 			return io_setup_async_addr(req, &__address, issue_flags);
 		}
 		if (ret == -ERESTARTSYS)
@@ -1244,7 +1296,7 @@ int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags)
 
 		if (ret > 0 && io_net_retry(sock, flags)) {
 			sr->done_io += ret;
-			req->flags |= REQ_F_PARTIAL_IO;
+			req->flags |= REQ_F_BL_NO_RECYCLE;
 			return io_setup_async_msg(req, kmsg, issue_flags);
 		}
 		if (ret == -ERESTARTSYS)
@@ -1279,7 +1331,7 @@ void io_sendrecv_fail(struct io_kiocb *req)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
 
-	if (req->flags & REQ_F_PARTIAL_IO)
+	if (sr->done_io)
 		req->cqe.res = sr->done_io;
 
 	if ((req->flags & REQ_F_NEED_CLEANUP) &&
@@ -1329,8 +1381,6 @@ int io_accept(struct io_kiocb *req, unsigned int issue_flags)
 	struct file *file;
 	int ret, fd;
 
-	if (!io_check_multishot(req, issue_flags))
-		return -EAGAIN;
 retry:
 	if (!fixed) {
 		fd = __get_unused_fd_flags(accept->flags, accept->nofile);
@@ -1350,7 +1400,7 @@ retry:
 			 * has already been done
 			 */
 			if (issue_flags & IO_URING_F_MULTISHOT)
-				ret = IOU_ISSUE_SKIP_COMPLETE;
+				return IOU_ISSUE_SKIP_COMPLETE;
 			return ret;
 		}
 		if (ret == -ERESTARTSYS)
@@ -1375,7 +1425,8 @@ retry:
 				ret, IORING_CQE_F_MORE))
 		goto retry;
 
-	return -ECANCELED;
+	io_req_set_res(req, ret, 0);
+	return IOU_STOP_MULTISHOT;
 }
 
 int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
diff --git a/io_uring/opdef.c b/io_uring/opdef.c
index 6705634e5f52..9c080aadc5a6 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -35,6 +35,7 @@
 #include "rw.h"
 #include "waitid.h"
 #include "futex.h"
+#include "truncate.h"
 
 static int io_no_issue(struct io_kiocb *req, unsigned int issue_flags)
 {
@@ -471,10 +472,15 @@ const struct io_issue_def io_issue_defs[] = {
 	},
 	[IORING_OP_FIXED_FD_INSTALL] = {
 		.needs_file		= 1,
-		.audit_skip		= 1,
 		.prep			= io_install_fixed_fd_prep,
 		.issue			= io_install_fixed_fd,
 	},
+	[IORING_OP_FTRUNCATE] = {
+		.needs_file		= 1,
+		.hash_reg_file		= 1,
+		.prep			= io_ftruncate_prep,
+		.issue			= io_ftruncate,
+	},
 };
 
 const struct io_cold_def io_cold_defs[] = {
@@ -713,6 +719,9 @@ const struct io_cold_def io_cold_defs[] = {
 	[IORING_OP_FIXED_FD_INSTALL] = {
 		.name			= "FIXED_FD_INSTALL",
 	},
+	[IORING_OP_FTRUNCATE] = {
+		.name			= "FTRUNCATE",
+	},
 };
 
 const char *io_uring_get_opcode(u8 opcode)
diff --git a/io_uring/openclose.c b/io_uring/openclose.c
index 0fe0dd305546..e3357dfa14ca 100644
--- a/io_uring/openclose.c
+++ b/io_uring/openclose.c
@@ -277,6 +277,10 @@ int io_install_fixed_fd_prep(struct io_kiocb *req, const struct io_uring_sqe *sq
 	if (flags & ~IORING_FIXED_FD_NO_CLOEXEC)
 		return -EINVAL;
 
+	/* ensure the task's creds are used when installing/receiving fds */
+	if (req->flags & REQ_F_CREDS)
+		return -EPERM;
+
 	/* default to O_CLOEXEC, disable if IORING_FIXED_FD_NO_CLOEXEC is set */
 	ifi = io_kiocb_to_cmd(req, struct io_fixed_install);
 	ifi->o_flags = O_CLOEXEC;
diff --git a/io_uring/poll.c b/io_uring/poll.c
index d59b74a99d4e..5f779139cae1 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -15,6 +15,7 @@
 
 #include "io_uring.h"
 #include "refs.h"
+#include "napi.h"
 #include "opdef.h"
 #include "kbuf.h"
 #include "poll.h"
@@ -226,8 +227,29 @@ enum {
 	IOU_POLL_NO_ACTION = 1,
 	IOU_POLL_REMOVE_POLL_USE_RES = 2,
 	IOU_POLL_REISSUE = 3,
+	IOU_POLL_REQUEUE = 4,
 };
 
+static void __io_poll_execute(struct io_kiocb *req, int mask)
+{
+	unsigned flags = 0;
+
+	io_req_set_res(req, mask, 0);
+	req->io_task_work.func = io_poll_task_func;
+
+	trace_io_uring_task_add(req, mask);
+
+	if (!(req->flags & REQ_F_POLL_NO_LAZY))
+		flags = IOU_F_TWQ_LAZY_WAKE;
+	__io_req_task_work_add(req, flags);
+}
+
+static inline void io_poll_execute(struct io_kiocb *req, int res)
+{
+	if (io_poll_get_ownership(req))
+		__io_poll_execute(req, res);
+}
+
 /*
  * All poll tw should go through this. Checks for poll events, manages
  * references, does rewait, etc.
@@ -309,6 +331,8 @@ static int io_poll_check_events(struct io_kiocb *req, struct io_tw_state *ts)
 			int ret = io_poll_issue(req, ts);
 			if (ret == IOU_STOP_MULTISHOT)
 				return IOU_POLL_REMOVE_POLL_USE_RES;
+			else if (ret == IOU_REQUEUE)
+				return IOU_POLL_REQUEUE;
 			if (ret < 0)
 				return ret;
 		}
@@ -320,8 +344,8 @@ static int io_poll_check_events(struct io_kiocb *req, struct io_tw_state *ts)
 		 * Release all references, retry if someone tried to restart
 		 * task_work while we were executing it.
 		 */
-	} while (atomic_sub_return(v & IO_POLL_REF_MASK, &req->poll_refs) &
-					IO_POLL_REF_MASK);
+		v &= IO_POLL_REF_MASK;
+	} while (atomic_sub_return(v, &req->poll_refs) & IO_POLL_REF_MASK);
 
 	return IOU_POLL_NO_ACTION;
 }
@@ -331,8 +355,12 @@ void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts)
 	int ret;
 
 	ret = io_poll_check_events(req, ts);
-	if (ret == IOU_POLL_NO_ACTION)
+	if (ret == IOU_POLL_NO_ACTION) {
 		return;
+	} else if (ret == IOU_POLL_REQUEUE) {
+		__io_poll_execute(req, 0);
+		return;
+	}
 	io_poll_remove_entries(req);
 	io_poll_tw_hash_eject(req, ts);
 
@@ -364,26 +392,6 @@ void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts)
 	}
 }
 
-static void __io_poll_execute(struct io_kiocb *req, int mask)
-{
-	unsigned flags = 0;
-
-	io_req_set_res(req, mask, 0);
-	req->io_task_work.func = io_poll_task_func;
-
-	trace_io_uring_task_add(req, mask);
-
-	if (!(req->flags & REQ_F_POLL_NO_LAZY))
-		flags = IOU_F_TWQ_LAZY_WAKE;
-	__io_req_task_work_add(req, flags);
-}
-
-static inline void io_poll_execute(struct io_kiocb *req, int res)
-{
-	if (io_poll_get_ownership(req))
-		__io_poll_execute(req, res);
-}
-
 static void io_poll_cancel_req(struct io_kiocb *req)
 {
 	io_poll_mark_cancelled(req);
@@ -532,14 +540,6 @@ static void __io_queue_proc(struct io_poll *poll, struct io_poll_table *pt,
 	poll->wait.private = (void *) wqe_private;
 
 	if (poll->events & EPOLLEXCLUSIVE) {
-		/*
-		 * Exclusive waits may only wake a limited amount of entries
-		 * rather than all of them, this may interfere with lazy
-		 * wake if someone does wait(events > 1). Ensure we don't do
-		 * lazy wake for those, as we need to process each one as they
-		 * come in.
-		 */
-		req->flags |= REQ_F_POLL_NO_LAZY;
 		add_wait_queue_exclusive(head, &poll->wait);
 	} else {
 		add_wait_queue(head, &poll->wait);
@@ -581,10 +581,7 @@ static int __io_arm_poll_handler(struct io_kiocb *req,
 				 struct io_poll_table *ipt, __poll_t mask,
 				 unsigned issue_flags)
 {
-	struct io_ring_ctx *ctx = req->ctx;
-
 	INIT_HLIST_NODE(&req->hash_node);
-	req->work.cancel_seq = atomic_read(&ctx->cancel_seq);
 	io_init_poll_iocb(poll, mask);
 	poll->file = req->file;
 	req->apoll_events = poll->events;
@@ -611,6 +608,17 @@ static int __io_arm_poll_handler(struct io_kiocb *req,
 	if (issue_flags & IO_URING_F_UNLOCKED)
 		req->flags &= ~REQ_F_HASH_LOCKED;
 
+
+	/*
+	 * Exclusive waits may only wake a limited amount of entries
+	 * rather than all of them, this may interfere with lazy
+	 * wake if someone does wait(events > 1). Ensure we don't do
+	 * lazy wake for those, as we need to process each one as they
+	 * come in.
+	 */
+	if (poll->events & EPOLLEXCLUSIVE)
+		req->flags |= REQ_F_POLL_NO_LAZY;
+
 	mask = vfs_poll(req->file, &ipt->pt) & poll->events;
 
 	if (unlikely(ipt->error || !ipt->nr_entries)) {
@@ -645,6 +653,7 @@ static int __io_arm_poll_handler(struct io_kiocb *req,
 		__io_poll_execute(req, mask);
 		return 0;
 	}
+	io_napi_add(req);
 
 	if (ipt->owning) {
 		/*
@@ -720,7 +729,7 @@ int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags)
 
 	if (!def->pollin && !def->pollout)
 		return IO_APOLL_ABORTED;
-	if (!file_can_poll(req->file))
+	if (!io_file_can_poll(req))
 		return IO_APOLL_ABORTED;
 	if (!(req->flags & REQ_F_APOLL_MULTISHOT))
 		mask |= EPOLLONESHOT;
@@ -811,9 +820,8 @@ static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, bool poll_only,
 		if (poll_only && req->opcode != IORING_OP_POLL_ADD)
 			continue;
 		if (cd->flags & IORING_ASYNC_CANCEL_ALL) {
-			if (cd->seq == req->work.cancel_seq)
+			if (io_cancel_match_sequence(req, cd->seq))
 				continue;
-			req->work.cancel_seq = cd->seq;
 		}
 		*out_bucket = hb;
 		return req;
diff --git a/io_uring/poll.h b/io_uring/poll.h
index ff4d5d753387..1dacae9e816c 100644
--- a/io_uring/poll.h
+++ b/io_uring/poll.h
@@ -24,6 +24,15 @@ struct async_poll {
 	struct io_poll		*double_poll;
 };
 
+/*
+ * Must only be called inside issue_flags & IO_URING_F_MULTISHOT, or
+ * potentially other cases where we already "own" this poll request.
+ */
+static inline void io_poll_multishot_retry(struct io_kiocb *req)
+{
+	atomic_inc(&req->poll_refs);
+}
+
 int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
 int io_poll_add(struct io_kiocb *req, unsigned int issue_flags);
 
diff --git a/io_uring/register.c b/io_uring/register.c
index 708dd1d89add..99c37775f974 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 #include <linux/nospec.h>
+#include <linux/compat.h>
 #include <linux/io_uring.h>
 #include <linux/io_uring_types.h>
 
@@ -25,6 +26,7 @@
 #include "register.h"
 #include "cancel.h"
 #include "kbuf.h"
+#include "napi.h"
 
 #define IORING_MAX_RESTRICTIONS	(IORING_RESTRICTION_LAST + \
 				 IORING_REGISTER_LAST + IORING_OP_LAST)
@@ -278,13 +280,14 @@ static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx,
 	if (len > cpumask_size())
 		len = cpumask_size();
 
-	if (in_compat_syscall()) {
+#ifdef CONFIG_COMPAT
+	if (in_compat_syscall())
 		ret = compat_get_bitmap(cpumask_bits(new_mask),
 					(const compat_ulong_t __user *)arg,
 					len * 8 /* CHAR_BIT */);
-	} else {
+	else
+#endif
 		ret = copy_from_user(new_mask, arg, len);
-	}
 
 	if (ret) {
 		free_cpumask_var(new_mask);
@@ -548,6 +551,18 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 			break;
 		ret = io_register_pbuf_status(ctx, arg);
 		break;
+	case IORING_REGISTER_NAPI:
+		ret = -EINVAL;
+		if (!arg || nr_args != 1)
+			break;
+		ret = io_register_napi(ctx, arg);
+		break;
+	case IORING_UNREGISTER_NAPI:
+		ret = -EINVAL;
+		if (nr_args != 1)
+			break;
+		ret = io_unregister_napi(ctx, arg);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index 7238b9cfe33b..e21000238954 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -2,8 +2,6 @@
 #ifndef IOU_RSRC_H
 #define IOU_RSRC_H
 
-#include <net/af_unix.h>
-
 #include "alloc_cache.h"
 
 #define IO_NODE_ALLOC_CACHE_MAX 32
@@ -102,17 +100,21 @@ static inline void io_charge_rsrc_node(struct io_ring_ctx *ctx,
 	node->refs++;
 }
 
+static inline void __io_req_set_rsrc_node(struct io_kiocb *req,
+					  struct io_ring_ctx *ctx)
+{
+	lockdep_assert_held(&ctx->uring_lock);
+	req->rsrc_node = ctx->rsrc_node;
+	io_charge_rsrc_node(ctx, ctx->rsrc_node);
+}
+
 static inline void io_req_set_rsrc_node(struct io_kiocb *req,
 					struct io_ring_ctx *ctx,
 					unsigned int issue_flags)
 {
 	if (!req->rsrc_node) {
 		io_ring_submit_lock(ctx, issue_flags);
-
-		lockdep_assert_held(&ctx->uring_lock);
-
-		req->rsrc_node = ctx->rsrc_node;
-		io_charge_rsrc_node(ctx, ctx->rsrc_node);
+		__io_req_set_rsrc_node(req, ctx);
 		io_ring_submit_unlock(ctx, issue_flags);
 	}
 }
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 0c856726b15d..47e097ab5d7e 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -11,6 +11,7 @@
 #include <linux/nospec.h>
 #include <linux/compat.h>
 #include <linux/io_uring/cmd.h>
+#include <linux/indirect_call_wrapper.h>
 
 #include <uapi/linux/io_uring.h>
 
@@ -18,6 +19,7 @@
 #include "opdef.h"
 #include "kbuf.h"
 #include "rsrc.h"
+#include "poll.h"
 #include "rw.h"
 
 struct io_rw {
@@ -168,27 +170,6 @@ void io_readv_writev_cleanup(struct io_kiocb *req)
 	kfree(io->free_iovec);
 }
 
-static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
-{
-	switch (ret) {
-	case -EIOCBQUEUED:
-		break;
-	case -ERESTARTSYS:
-	case -ERESTARTNOINTR:
-	case -ERESTARTNOHAND:
-	case -ERESTART_RESTARTBLOCK:
-		/*
-		 * We can't just restart the syscall, since previously
-		 * submitted sqes may already be in progress. Just fail this
-		 * IO with EINTR.
-		 */
-		ret = -EINTR;
-		fallthrough;
-	default:
-		kiocb->ki_complete(kiocb, ret);
-	}
-}
-
 static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req)
 {
 	struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
@@ -294,7 +275,7 @@ static bool __io_complete_rw_common(struct io_kiocb *req, long res)
 			 * current cycle.
 			 */
 			io_req_io_end(req);
-			req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO;
+			req->flags |= REQ_F_REISSUE | REQ_F_BL_NO_RECYCLE;
 			return true;
 		}
 		req_set_fail(req);
@@ -361,7 +342,7 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
 		io_req_end_write(req);
 	if (unlikely(res != req->cqe.res)) {
 		if (res == -EAGAIN && io_rw_should_reissue(req)) {
-			req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO;
+			req->flags |= REQ_F_REISSUE | REQ_F_BL_NO_RECYCLE;
 			return;
 		}
 		req->cqe.res = res;
@@ -371,6 +352,33 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
 	smp_store_release(&req->iopoll_completed, 1);
 }
 
+static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
+{
+	/* IO was queued async, completion will happen later */
+	if (ret == -EIOCBQUEUED)
+		return;
+
+	/* transform internal restart error codes */
+	if (unlikely(ret < 0)) {
+		switch (ret) {
+		case -ERESTARTSYS:
+		case -ERESTARTNOINTR:
+		case -ERESTARTNOHAND:
+		case -ERESTART_RESTARTBLOCK:
+			/*
+			 * We can't just restart the syscall, since previously
+			 * submitted sqes may already be in progress. Just fail
+			 * this IO with EINTR.
+			 */
+			ret = -EINTR;
+			break;
+		}
+	}
+
+	INDIRECT_CALL_2(kiocb->ki_complete, io_complete_rw_iopoll,
+			io_complete_rw, kiocb, ret);
+}
+
 static int kiocb_done(struct io_kiocb *req, ssize_t ret,
 		       unsigned int issue_flags)
 {
@@ -675,7 +683,7 @@ static bool io_rw_should_retry(struct io_kiocb *req)
 	 * just use poll if we can, and don't attempt if the fs doesn't
 	 * support callback based unlocks
 	 */
-	if (file_can_poll(req->file) || !(req->file->f_mode & FMODE_BUF_RASYNC))
+	if (io_file_can_poll(req) || !(req->file->f_mode & FMODE_BUF_RASYNC))
 		return false;
 
 	wait->wait.func = io_async_buf_func;
@@ -714,7 +722,7 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode)
 	struct file *file = req->file;
 	int ret;
 
-	if (unlikely(!file || !(file->f_mode & mode)))
+	if (unlikely(!(file->f_mode & mode)))
 		return -EBADF;
 
 	if (!(req->flags & REQ_F_FIXED_FILE))
@@ -824,7 +832,7 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags)
 		 * If we can poll, just do that. For a vectored read, we'll
 		 * need to copy state first.
 		 */
-		if (file_can_poll(req->file) && !io_issue_defs[req->opcode].vectored)
+		if (io_file_can_poll(req) && !io_issue_defs[req->opcode].vectored)
 			return -EAGAIN;
 		/* IOPOLL retry should happen for io-wq threads */
 		if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL))
@@ -923,7 +931,7 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
 	/*
 	 * Multishot MUST be used on a pollable file
 	 */
-	if (!file_can_poll(req->file))
+	if (!io_file_can_poll(req))
 		return -EBADFD;
 
 	ret = __io_read(req, issue_flags);
@@ -956,8 +964,15 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
 		if (io_fill_cqe_req_aux(req,
 					issue_flags & IO_URING_F_COMPLETE_DEFER,
 					ret, cflags | IORING_CQE_F_MORE)) {
-			if (issue_flags & IO_URING_F_MULTISHOT)
+			if (issue_flags & IO_URING_F_MULTISHOT) {
+				/*
+				 * Force retry, as we might have more data to
+				 * be read and otherwise it won't get retried
+				 * until (if ever) another poll is triggered.
+				 */
+				io_poll_multishot_retry(req);
 				return IOU_ISSUE_SKIP_COMPLETE;
+			}
 			return -EAGAIN;
 		}
 	}
diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index 65b5dbe3c850..363052b4ea76 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -15,9 +15,11 @@
 #include <uapi/linux/io_uring.h>
 
 #include "io_uring.h"
+#include "napi.h"
 #include "sqpoll.h"
 
 #define IORING_SQPOLL_CAP_ENTRIES_VALUE 8
+#define IORING_TW_CAP_ENTRIES_VALUE	8
 
 enum {
 	IO_SQ_THREAD_SHOULD_STOP = 0,
@@ -193,6 +195,9 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
 			ret = io_submit_sqes(ctx, to_submit);
 		mutex_unlock(&ctx->uring_lock);
 
+		if (io_napi(ctx))
+			ret += io_napi_sqpoll_busy_poll(ctx);
+
 		if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait))
 			wake_up(&ctx->sqo_sq_wait);
 		if (creds)
@@ -219,10 +224,52 @@ static bool io_sqd_handle_event(struct io_sq_data *sqd)
 	return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
 }
 
+/*
+ * Run task_work, processing the retry_list first. The retry_list holds
+ * entries that we passed on in the previous run, if we had more task_work
+ * than we were asked to process. Newly queued task_work isn't run until the
+ * retry list has been fully processed.
+ */
+static unsigned int io_sq_tw(struct llist_node **retry_list, int max_entries)
+{
+	struct io_uring_task *tctx = current->io_uring;
+	unsigned int count = 0;
+
+	if (*retry_list) {
+		*retry_list = io_handle_tw_list(*retry_list, &count, max_entries);
+		if (count >= max_entries)
+			return count;
+		max_entries -= count;
+	}
+
+	*retry_list = tctx_task_work_run(tctx, max_entries, &count);
+	return count;
+}
+
+static bool io_sq_tw_pending(struct llist_node *retry_list)
+{
+	struct io_uring_task *tctx = current->io_uring;
+
+	return retry_list || !llist_empty(&tctx->task_list);
+}
+
+static void io_sq_update_worktime(struct io_sq_data *sqd, struct rusage *start)
+{
+	struct rusage end;
+
+	getrusage(current, RUSAGE_SELF, &end);
+	end.ru_stime.tv_sec -= start->ru_stime.tv_sec;
+	end.ru_stime.tv_usec -= start->ru_stime.tv_usec;
+
+	sqd->work_time += end.ru_stime.tv_usec + end.ru_stime.tv_sec * 1000000;
+}
+
 static int io_sq_thread(void *data)
 {
+	struct llist_node *retry_list = NULL;
 	struct io_sq_data *sqd = data;
 	struct io_ring_ctx *ctx;
+	struct rusage start;
 	unsigned long timeout = 0;
 	char buf[TASK_COMM_LEN];
 	DEFINE_WAIT(wait);
@@ -251,18 +298,21 @@ static int io_sq_thread(void *data)
 		}
 
 		cap_entries = !list_is_singular(&sqd->ctx_list);
+		getrusage(current, RUSAGE_SELF, &start);
 		list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
 			int ret = __io_sq_thread(ctx, cap_entries);
 
 			if (!sqt_spin && (ret > 0 || !wq_list_empty(&ctx->iopoll_list)))
 				sqt_spin = true;
 		}
-		if (io_run_task_work())
+		if (io_sq_tw(&retry_list, IORING_TW_CAP_ENTRIES_VALUE))
 			sqt_spin = true;
 
 		if (sqt_spin || !time_after(jiffies, timeout)) {
-			if (sqt_spin)
+			if (sqt_spin) {
+				io_sq_update_worktime(sqd, &start);
 				timeout = jiffies + sqd->sq_thread_idle;
+			}
 			if (unlikely(need_resched())) {
 				mutex_unlock(&sqd->lock);
 				cond_resched();
@@ -273,7 +323,7 @@ static int io_sq_thread(void *data)
 		}
 
 		prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE);
-		if (!io_sqd_events_pending(sqd) && !task_work_pending(current)) {
+		if (!io_sqd_events_pending(sqd) && !io_sq_tw_pending(retry_list)) {
 			bool needs_sched = true;
 
 			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
@@ -312,6 +362,9 @@ static int io_sq_thread(void *data)
 		timeout = jiffies + sqd->sq_thread_idle;
 	}
 
+	if (retry_list)
+		io_sq_tw(&retry_list, UINT_MAX);
+
 	io_uring_cancel_generic(true, sqd);
 	sqd->thread = NULL;
 	list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
diff --git a/io_uring/sqpoll.h b/io_uring/sqpoll.h
index 8df37e8c9149..4171666b1cf4 100644
--- a/io_uring/sqpoll.h
+++ b/io_uring/sqpoll.h
@@ -16,6 +16,7 @@ struct io_sq_data {
 	pid_t			task_pid;
 	pid_t			task_tgid;
 
+	u64			work_time;
 	unsigned long		state;
 	struct completion	exited;
 };
diff --git a/io_uring/truncate.c b/io_uring/truncate.c
new file mode 100644
index 000000000000..62ee73d34d72
--- /dev/null
+++ b/io_uring/truncate.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/io_uring.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "../fs/internal.h"
+
+#include "io_uring.h"
+#include "truncate.h"
+
+struct io_ftrunc {
+	struct file			*file;
+	loff_t				len;
+};
+
+int io_ftruncate_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_ftrunc *ft = io_kiocb_to_cmd(req, struct io_ftrunc);
+
+	if (sqe->rw_flags || sqe->addr || sqe->len || sqe->buf_index ||
+	    sqe->splice_fd_in || sqe->addr3)
+		return -EINVAL;
+
+	ft->len = READ_ONCE(sqe->off);
+
+	req->flags |= REQ_F_FORCE_ASYNC;
+	return 0;
+}
+
+int io_ftruncate(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_ftrunc *ft = io_kiocb_to_cmd(req, struct io_ftrunc);
+	int ret;
+
+	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
+
+	ret = do_ftruncate(req->file, ft->len, 1);
+
+	io_req_set_res(req, ret, 0);
+	return IOU_OK;
+}
diff --git a/io_uring/truncate.h b/io_uring/truncate.h
new file mode 100644
index 000000000000..ec088293a478
--- /dev/null
+++ b/io_uring/truncate.h
@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
+
+int io_ftruncate_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_ftruncate(struct io_kiocb *req, unsigned int issue_flags);
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index c33fca585dde..42f63adfa54a 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -5,6 +5,7 @@
 #include <linux/io_uring/cmd.h>
 #include <linux/security.h>
 #include <linux/nospec.h>
+#include <net/sock.h>
 
 #include <uapi/linux/io_uring.h>
 #include <asm/ioctls.h>
diff --git a/io_uring/xattr.c b/io_uring/xattr.c
index e1c810e0b85a..44905b82eea8 100644
--- a/io_uring/xattr.c
+++ b/io_uring/xattr.c
@@ -112,7 +112,7 @@ int io_fgetxattr(struct io_kiocb *req, unsigned int issue_flags)
 
 	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
 
-	ret = do_getxattr(mnt_idmap(req->file->f_path.mnt),
+	ret = do_getxattr(file_mnt_idmap(req->file),
 			req->file->f_path.dentry,
 			&ix->ctx);
 
diff --git a/kernel/async.c b/kernel/async.c
index 97f224a5257b..4c3e6a44595f 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -64,6 +64,7 @@ static async_cookie_t next_cookie = 1;
 static LIST_HEAD(async_global_pending);	/* pending from all registered doms */
 static ASYNC_DOMAIN(async_dfl_domain);
 static DEFINE_SPINLOCK(async_lock);
+static struct workqueue_struct *async_wq;
 
 struct async_entry {
 	struct list_head	domain_list;
@@ -174,7 +175,7 @@ static async_cookie_t __async_schedule_node_domain(async_func_t func,
 	spin_unlock_irqrestore(&async_lock, flags);
 
 	/* schedule for execution */
-	queue_work_node(node, system_unbound_wq, &entry->work);
+	queue_work_node(node, async_wq, &entry->work);
 
 	return newcookie;
 }
@@ -345,3 +346,17 @@ bool current_is_async(void)
 	return worker && worker->current_func == async_run_entry_fn;
 }
 EXPORT_SYMBOL_GPL(current_is_async);
+
+void __init async_init(void)
+{
+	/*
+	 * Async can schedule a number of interdependent work items. However,
+	 * unbound workqueues can handle only upto min_active interdependent
+	 * work items. The default min_active of 8 isn't sufficient for async
+	 * and can lead to stalls. Let's use a dedicated workqueue with raised
+	 * min_active.
+	 */
+	async_wq = alloc_workqueue("async", WQ_UNBOUND, 0);
+	BUG_ON(!async_wq);
+	workqueue_set_min_active(async_wq, WQ_DFL_ACTIVE);
+}
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 51e8b4bee0c8..596471189176 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -5615,21 +5615,46 @@ static u8 bpf_ctx_convert_map[] = {
 #undef BPF_MAP_TYPE
 #undef BPF_LINK_TYPE
 
-const struct btf_member *
-btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
-		      const struct btf_type *t, enum bpf_prog_type prog_type,
-		      int arg)
+static const struct btf_type *find_canonical_prog_ctx_type(enum bpf_prog_type prog_type)
 {
 	const struct btf_type *conv_struct;
-	const struct btf_type *ctx_struct;
 	const struct btf_member *ctx_type;
-	const char *tname, *ctx_tname;
 
 	conv_struct = bpf_ctx_convert.t;
-	if (!conv_struct) {
-		bpf_log(log, "btf_vmlinux is malformed\n");
+	if (!conv_struct)
 		return NULL;
-	}
+	/* prog_type is valid bpf program type. No need for bounds check. */
+	ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2;
+	/* ctx_type is a pointer to prog_ctx_type in vmlinux.
+	 * Like 'struct __sk_buff'
+	 */
+	return btf_type_by_id(btf_vmlinux, ctx_type->type);
+}
+
+static int find_kern_ctx_type_id(enum bpf_prog_type prog_type)
+{
+	const struct btf_type *conv_struct;
+	const struct btf_member *ctx_type;
+
+	conv_struct = bpf_ctx_convert.t;
+	if (!conv_struct)
+		return -EFAULT;
+	/* prog_type is valid bpf program type. No need for bounds check. */
+	ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2 + 1;
+	/* ctx_type is a pointer to prog_ctx_type in vmlinux.
+	 * Like 'struct sk_buff'
+	 */
+	return ctx_type->type;
+}
+
+const struct btf_type *
+btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
+		      const struct btf_type *t, enum bpf_prog_type prog_type,
+		      int arg)
+{
+	const struct btf_type *ctx_type;
+	const char *tname, *ctx_tname;
+
 	t = btf_type_by_id(btf, t->type);
 	while (btf_type_is_modifier(t))
 		t = btf_type_by_id(btf, t->type);
@@ -5646,17 +5671,15 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
 		bpf_log(log, "arg#%d struct doesn't have a name\n", arg);
 		return NULL;
 	}
-	/* prog_type is valid bpf program type. No need for bounds check. */
-	ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2;
-	/* ctx_struct is a pointer to prog_ctx_type in vmlinux.
-	 * Like 'struct __sk_buff'
-	 */
-	ctx_struct = btf_type_by_id(btf_vmlinux, ctx_type->type);
-	if (!ctx_struct)
+
+	ctx_type = find_canonical_prog_ctx_type(prog_type);
+	if (!ctx_type) {
+		bpf_log(log, "btf_vmlinux is malformed\n");
 		/* should not happen */
 		return NULL;
+	}
 again:
-	ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_struct->name_off);
+	ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off);
 	if (!ctx_tname) {
 		/* should not happen */
 		bpf_log(log, "Please fix kernel include/linux/bpf_types.h\n");
@@ -5677,28 +5700,167 @@ again:
 		/* bpf_user_pt_regs_t is a typedef, so resolve it to
 		 * underlying struct and check name again
 		 */
-		if (!btf_type_is_modifier(ctx_struct))
+		if (!btf_type_is_modifier(ctx_type))
 			return NULL;
-		while (btf_type_is_modifier(ctx_struct))
-			ctx_struct = btf_type_by_id(btf_vmlinux, ctx_struct->type);
+		while (btf_type_is_modifier(ctx_type))
+			ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type);
 		goto again;
 	}
 	return ctx_type;
 }
 
+/* forward declarations for arch-specific underlying types of
+ * bpf_user_pt_regs_t; this avoids the need for arch-specific #ifdef
+ * compilation guards below for BPF_PROG_TYPE_PERF_EVENT checks, but still
+ * works correctly with __builtin_types_compatible_p() on respective
+ * architectures
+ */
+struct user_regs_struct;
+struct user_pt_regs;
+
+static int btf_validate_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
+				      const struct btf_type *t, int arg,
+				      enum bpf_prog_type prog_type,
+				      enum bpf_attach_type attach_type)
+{
+	const struct btf_type *ctx_type;
+	const char *tname, *ctx_tname;
+
+	if (!btf_is_ptr(t)) {
+		bpf_log(log, "arg#%d type isn't a pointer\n", arg);
+		return -EINVAL;
+	}
+	t = btf_type_by_id(btf, t->type);
+
+	/* KPROBE and PERF_EVENT programs allow bpf_user_pt_regs_t typedef */
+	if (prog_type == BPF_PROG_TYPE_KPROBE || prog_type == BPF_PROG_TYPE_PERF_EVENT) {
+		while (btf_type_is_modifier(t) && !btf_type_is_typedef(t))
+			t = btf_type_by_id(btf, t->type);
+
+		if (btf_type_is_typedef(t)) {
+			tname = btf_name_by_offset(btf, t->name_off);
+			if (tname && strcmp(tname, "bpf_user_pt_regs_t") == 0)
+				return 0;
+		}
+	}
+
+	/* all other program types don't use typedefs for context type */
+	while (btf_type_is_modifier(t))
+		t = btf_type_by_id(btf, t->type);
+
+	/* `void *ctx __arg_ctx` is always valid */
+	if (btf_type_is_void(t))
+		return 0;
+
+	tname = btf_name_by_offset(btf, t->name_off);
+	if (str_is_empty(tname)) {
+		bpf_log(log, "arg#%d type doesn't have a name\n", arg);
+		return -EINVAL;
+	}
+
+	/* special cases */
+	switch (prog_type) {
+	case BPF_PROG_TYPE_KPROBE:
+		if (__btf_type_is_struct(t) && strcmp(tname, "pt_regs") == 0)
+			return 0;
+		break;
+	case BPF_PROG_TYPE_PERF_EVENT:
+		if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct pt_regs) &&
+		    __btf_type_is_struct(t) && strcmp(tname, "pt_regs") == 0)
+			return 0;
+		if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_pt_regs) &&
+		    __btf_type_is_struct(t) && strcmp(tname, "user_pt_regs") == 0)
+			return 0;
+		if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_regs_struct) &&
+		    __btf_type_is_struct(t) && strcmp(tname, "user_regs_struct") == 0)
+			return 0;
+		break;
+	case BPF_PROG_TYPE_RAW_TRACEPOINT:
+	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
+		/* allow u64* as ctx */
+		if (btf_is_int(t) && t->size == 8)
+			return 0;
+		break;
+	case BPF_PROG_TYPE_TRACING:
+		switch (attach_type) {
+		case BPF_TRACE_RAW_TP:
+			/* tp_btf program is TRACING, so need special case here */
+			if (__btf_type_is_struct(t) &&
+			    strcmp(tname, "bpf_raw_tracepoint_args") == 0)
+				return 0;
+			/* allow u64* as ctx */
+			if (btf_is_int(t) && t->size == 8)
+				return 0;
+			break;
+		case BPF_TRACE_ITER:
+			/* allow struct bpf_iter__xxx types only */
+			if (__btf_type_is_struct(t) &&
+			    strncmp(tname, "bpf_iter__", sizeof("bpf_iter__") - 1) == 0)
+				return 0;
+			break;
+		case BPF_TRACE_FENTRY:
+		case BPF_TRACE_FEXIT:
+		case BPF_MODIFY_RETURN:
+			/* allow u64* as ctx */
+			if (btf_is_int(t) && t->size == 8)
+				return 0;
+			break;
+		default:
+			break;
+		}
+		break;
+	case BPF_PROG_TYPE_LSM:
+	case BPF_PROG_TYPE_STRUCT_OPS:
+		/* allow u64* as ctx */
+		if (btf_is_int(t) && t->size == 8)
+			return 0;
+		break;
+	case BPF_PROG_TYPE_TRACEPOINT:
+	case BPF_PROG_TYPE_SYSCALL:
+	case BPF_PROG_TYPE_EXT:
+		return 0; /* anything goes */
+	default:
+		break;
+	}
+
+	ctx_type = find_canonical_prog_ctx_type(prog_type);
+	if (!ctx_type) {
+		/* should not happen */
+		bpf_log(log, "btf_vmlinux is malformed\n");
+		return -EINVAL;
+	}
+
+	/* resolve typedefs and check that underlying structs are matching as well */
+	while (btf_type_is_modifier(ctx_type))
+		ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type);
+
+	/* if program type doesn't have distinctly named struct type for
+	 * context, then __arg_ctx argument can only be `void *`, which we
+	 * already checked above
+	 */
+	if (!__btf_type_is_struct(ctx_type)) {
+		bpf_log(log, "arg#%d should be void pointer\n", arg);
+		return -EINVAL;
+	}
+
+	ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off);
+	if (!__btf_type_is_struct(t) || strcmp(ctx_tname, tname) != 0) {
+		bpf_log(log, "arg#%d should be `struct %s *`\n", arg, ctx_tname);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int btf_translate_to_vmlinux(struct bpf_verifier_log *log,
 				     struct btf *btf,
 				     const struct btf_type *t,
 				     enum bpf_prog_type prog_type,
 				     int arg)
 {
-	const struct btf_member *prog_ctx_type, *kern_ctx_type;
-
-	prog_ctx_type = btf_get_prog_ctx_type(log, btf, t, prog_type, arg);
-	if (!prog_ctx_type)
+	if (!btf_get_prog_ctx_type(log, btf, t, prog_type, arg))
 		return -ENOENT;
-	kern_ctx_type = prog_ctx_type + 1;
-	return kern_ctx_type->type;
+	return find_kern_ctx_type_id(prog_type);
 }
 
 int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type)
@@ -6934,6 +7096,23 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog)
 		return -EINVAL;
 	}
 
+	for (i = 0; i < nargs; i++) {
+		const char *tag;
+
+		if (sub->args[i].arg_type != ARG_PTR_TO_CTX)
+			continue;
+
+		/* check if arg has "arg:ctx" tag */
+		t = btf_type_by_id(btf, args[i].type);
+		tag = btf_find_decl_tag_value(btf, fn_t, i, "arg:");
+		if (IS_ERR_OR_NULL(tag) || strcmp(tag, "ctx") != 0)
+			continue;
+
+		if (btf_validate_prog_ctx_type(log, btf, t, i, prog_type,
+					       prog->expected_attach_type))
+			return -EINVAL;
+	}
+
 	sub->arg_cnt = nargs;
 	sub->args_cached = true;
 
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 8a0bb80fe48a..ef82ffc90cbe 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -178,7 +178,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 				    void **frames, int n,
 				    struct xdp_cpumap_stats *stats)
 {
-	struct xdp_rxq_info rxq;
+	struct xdp_rxq_info rxq = {};
 	struct xdp_buff xdp;
 	int i, nframes = 0;
 
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index be72824f32b2..d19cd863d294 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1101,6 +1101,7 @@ struct bpf_hrtimer {
 	struct bpf_prog *prog;
 	void __rcu *callback_fn;
 	void *value;
+	struct rcu_head rcu;
 };
 
 /* the actual struct hidden inside uapi struct bpf_timer */
@@ -1332,6 +1333,7 @@ BPF_CALL_1(bpf_timer_cancel, struct bpf_timer_kern *, timer)
 
 	if (in_nmi())
 		return -EOPNOTSUPP;
+	rcu_read_lock();
 	__bpf_spin_lock_irqsave(&timer->lock);
 	t = timer->timer;
 	if (!t) {
@@ -1353,6 +1355,7 @@ out:
 	 * if it was running.
 	 */
 	ret = ret ?: hrtimer_cancel(&t->timer);
+	rcu_read_unlock();
 	return ret;
 }
 
@@ -1407,7 +1410,7 @@ out:
 	 */
 	if (this_cpu_read(hrtimer_running) != t)
 		hrtimer_cancel(&t->timer);
-	kfree(t);
+	kfree_rcu(t, rcu);
 }
 
 BPF_CALL_2(bpf_kptr_xchg, void *, map_value, void *, ptr)
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index e5c3500443c6..ec4e97c61eef 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -978,6 +978,8 @@ __bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it,
 	BUILD_BUG_ON(__alignof__(struct bpf_iter_task_kern) !=
 					__alignof__(struct bpf_iter_task));
 
+	kit->pos = NULL;
+
 	switch (flags) {
 	case BPF_TASK_ITER_ALL_THREADS:
 	case BPF_TASK_ITER_ALL_PROCS:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index adbf330d364b..ddea9567f755 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5227,7 +5227,9 @@ BTF_ID(struct, prog_test_ref_kfunc)
 #ifdef CONFIG_CGROUPS
 BTF_ID(struct, cgroup)
 #endif
+#ifdef CONFIG_BPF_JIT
 BTF_ID(struct, bpf_cpumask)
+#endif
 BTF_ID(struct, task_struct)
 BTF_SET_END(rcu_protected_types)
 
@@ -12826,6 +12828,10 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	}
 
 	switch (base_type(ptr_reg->type)) {
+	case PTR_TO_FLOW_KEYS:
+		if (known)
+			break;
+		fallthrough;
 	case CONST_PTR_TO_MAP:
 		/* smin_val represents the known value */
 		if (known && smin_val == 0 && opcode == BPF_ADD)
@@ -16596,6 +16602,9 @@ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_stat
 {
 	int i;
 
+	if (old->callback_depth > cur->callback_depth)
+		return false;
+
 	for (i = 0; i < MAX_BPF_REG; i++)
 		if (!regsafe(env, &old->regs[i], &cur->regs[i],
 			     &env->idmap_scratch, exact))
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 04d11a7dd95f..520a11cb12f4 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -802,7 +802,7 @@ void cgroup1_release_agent(struct work_struct *work)
 		goto out_free;
 
 	ret = cgroup_path_ns(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns);
-	if (ret < 0 || ret >= PATH_MAX)
+	if (ret < 0)
 		goto out_free;
 
 	argv[0] = agentbuf;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 8f3cef1a4d8a..a66c088c851c 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1906,7 +1906,7 @@ int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
 	len = kernfs_path_from_node(kf_node, ns_cgroup->kn, buf, PATH_MAX);
 	spin_unlock_irq(&css_set_lock);
 
-	if (len >= PATH_MAX)
+	if (len == -E2BIG)
 		len = -ERANGE;
 	else if (len > 0) {
 		seq_escape(sf, buf, " \t\n\\");
@@ -4182,20 +4182,6 @@ static struct kernfs_ops cgroup_kf_ops = {
 	.seq_show		= cgroup_seqfile_show,
 };
 
-/* set uid and gid of cgroup dirs and files to that of the creator */
-static int cgroup_kn_set_ugid(struct kernfs_node *kn)
-{
-	struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID,
-			       .ia_uid = current_fsuid(),
-			       .ia_gid = current_fsgid(), };
-
-	if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) &&
-	    gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID))
-		return 0;
-
-	return kernfs_setattr(kn, &iattr);
-}
-
 static void cgroup_file_notify_timer(struct timer_list *timer)
 {
 	cgroup_file_notify(container_of(timer, struct cgroup_file,
@@ -4208,25 +4194,18 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp,
 	char name[CGROUP_FILE_NAME_MAX];
 	struct kernfs_node *kn;
 	struct lock_class_key *key = NULL;
-	int ret;
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	key = &cft->lockdep_key;
 #endif
 	kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name),
 				  cgroup_file_mode(cft),
-				  GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
+				  current_fsuid(), current_fsgid(),
 				  0, cft->kf_ops, cft,
 				  NULL, key);
 	if (IS_ERR(kn))
 		return PTR_ERR(kn);
 
-	ret = cgroup_kn_set_ugid(kn);
-	if (ret) {
-		kernfs_remove(kn);
-		return ret;
-	}
-
 	if (cft->file_offset) {
 		struct cgroup_file *cfile = (void *)css + cft->file_offset;
 
@@ -5629,7 +5608,9 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 		goto out_cancel_ref;
 
 	/* create the directory */
-	kn = kernfs_create_dir(parent->kn, name, mode, cgrp);
+	kn = kernfs_create_dir_ns(parent->kn, name, mode,
+				  current_fsuid(), current_fsgid(),
+				  cgrp, NULL);
 	if (IS_ERR(kn)) {
 		ret = PTR_ERR(kn);
 		goto out_stat_exit;
@@ -5774,10 +5755,6 @@ int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode)
 	 */
 	kernfs_get(cgrp->kn);
 
-	ret = cgroup_kn_set_ugid(cgrp->kn);
-	if (ret)
-		goto out_destroy;
-
 	ret = css_populate_dir(&cgrp->self);
 	if (ret)
 		goto out_destroy;
@@ -6316,7 +6293,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 		if (cgroup_on_dfl(cgrp) || !(tsk->flags & PF_EXITING)) {
 			retval = cgroup_path_ns_locked(cgrp, buf, PATH_MAX,
 						current->nsproxy->cgroup_ns);
-			if (retval >= PATH_MAX)
+			if (retval == -E2BIG)
 				retval = -ENAMETOOLONG;
 			if (retval < 0)
 				goto out_unlock;
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index dfbb16aca9f4..927bef3a598a 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2562,7 +2562,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 		update_partition_sd_lb(cs, old_prs);
 out_free:
 	free_cpumasks(NULL, &tmp);
-	return 0;
+	return retval;
 }
 
 /**
@@ -2598,9 +2598,6 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	if (cpumask_equal(cs->exclusive_cpus, trialcs->exclusive_cpus))
 		return 0;
 
-	if (alloc_cpumasks(NULL, &tmp))
-		return -ENOMEM;
-
 	if (*buf)
 		compute_effective_exclusive_cpumask(trialcs, NULL);
 
@@ -2615,6 +2612,9 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	if (retval)
 		return retval;
 
+	if (alloc_cpumasks(NULL, &tmp))
+		return -ENOMEM;
+
 	if (old_prs) {
 		if (cpumask_empty(trialcs->effective_xcpus)) {
 			invalidate = true;
@@ -5092,7 +5092,7 @@ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
 	retval = cgroup_path_ns(css->cgroup, buf, PATH_MAX,
 				current->nsproxy->cgroup_ns);
 	css_put(css);
-	if (retval >= PATH_MAX)
+	if (retval == -E2BIG)
 		retval = -ENAMETOOLONG;
 	if (retval < 0)
 		goto out_free;
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 6ef0b35fc28c..70ae70d03823 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -458,6 +458,8 @@ static __always_inline void context_tracking_recursion_exit(void)
  * __ct_user_enter - Inform the context tracking that the CPU is going
  *		     to enter user or guest space mode.
  *
+ * @state: userspace context-tracking state to enter.
+ *
  * This function must be called right before we switch from the kernel
  * to user or guest space, when it's guaranteed the remaining kernel
  * instructions to execute won't use any RCU read side critical section
@@ -595,6 +597,8 @@ NOKPROBE_SYMBOL(user_enter_callable);
  * __ct_user_exit - Inform the context tracking that the CPU is
  *		    exiting user or guest mode and entering the kernel.
  *
+ * @state: userspace context-tracking state being exited from.
+ *
  * This function must be called after we entered the kernel from user or
  * guest space before any use of RCU read side critical section. This
  * potentially include any high level kernel code like syscalls, exceptions,
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index d48315667752..75cd6a736d03 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -376,7 +376,6 @@ static int __init reserve_crashkernel_low(unsigned long long low_size)
 
 	crashk_low_res.start = low_base;
 	crashk_low_res.end   = low_base + low_size - 1;
-	insert_resource(&iomem_resource, &crashk_low_res);
 #endif
 	return 0;
 }
@@ -458,8 +457,19 @@ retry:
 
 	crashk_res.start = crash_base;
 	crashk_res.end = crash_base + crash_size - 1;
-	insert_resource(&iomem_resource, &crashk_res);
 }
+
+static __init int insert_crashkernel_resources(void)
+{
+	if (crashk_res.start < crashk_res.end)
+		insert_resource(&iomem_resource, &crashk_res);
+
+	if (crashk_low_res.start < crashk_low_res.end)
+		insert_resource(&iomem_resource, &crashk_low_res);
+
+	return 0;
+}
+early_initcall(insert_crashkernel_resources);
 #endif
 
 int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map,
@@ -867,7 +877,7 @@ subsys_initcall(crash_notes_memory_init);
  * regions are online. So mutex lock  __crash_hotplug_lock is used to
  * serialize the crash hotplug handling specifically.
  */
-DEFINE_MUTEX(__crash_hotplug_lock);
+static DEFINE_MUTEX(__crash_hotplug_lock);
 #define crash_hotplug_lock() mutex_lock(&__crash_hotplug_lock)
 #define crash_hotplug_unlock() mutex_unlock(&__crash_hotplug_lock)
 
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 6b213c8252d6..d05066cb40b2 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -1348,8 +1348,6 @@ do_full_getstr:
 		/* PROMPT can only be set if we have MEM_READ permission. */
 		snprintf(kdb_prompt_str, CMD_BUFLEN, kdbgetenv("PROMPT"),
 			 raw_smp_processor_id());
-		if (defcmd_in_progress)
-			strncat(kdb_prompt_str, "[defcmd]", CMD_BUFLEN);
 
 		/*
 		 * Fetch command from keyboard
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 3de494375b7b..a6e3792b15f8 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -62,7 +62,8 @@ enum map_err_types {
  * @pfn: page frame of the start address
  * @offset: offset of mapping relative to pfn
  * @map_err_type: track whether dma_mapping_error() was checked
- * @stacktrace: support backtraces when a violation is detected
+ * @stack_len: number of backtrace entries in @stack_entries
+ * @stack_entries: stack of backtrace history
  */
 struct dma_debug_entry {
 	struct list_head list;
@@ -876,7 +877,7 @@ static int dma_debug_device_change(struct notifier_block *nb, unsigned long acti
 	return 0;
 }
 
-void dma_debug_add_bus(struct bus_type *bus)
+void dma_debug_add_bus(const struct bus_type *bus)
 {
 	struct notifier_block *nb;
 
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 97c298b210bc..b079a9a8e087 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -1136,6 +1136,9 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
 	int cpu, i;
 	int index;
 
+	if (alloc_size > IO_TLB_SEGSIZE * IO_TLB_SIZE)
+		return -1;
+
 	cpu = raw_smp_processor_id();
 	for (i = 0; i < default_nareas; ++i) {
 		index = swiotlb_search_area(dev, cpu, i, orig_addr, alloc_size,
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 485bb0389b48..929e98c62965 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -537,7 +537,7 @@ retry:
 		}
 	}
 
-	ret = __replace_page(vma, vaddr, old_page, new_page);
+	ret = __replace_page(vma, vaddr & PAGE_MASK, old_page, new_page);
 	if (new_page)
 		put_page(new_page);
 put_old:
diff --git a/kernel/exit.c b/kernel/exit.c
index 3988a02efaef..41a12630cbbc 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -739,6 +739,13 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
 		kill_orphaned_pgrp(tsk->group_leader, NULL);
 
 	tsk->exit_state = EXIT_ZOMBIE;
+	/*
+	 * sub-thread or delay_group_leader(), wake up the
+	 * PIDFD_THREAD waiters.
+	 */
+	if (!thread_group_empty(tsk))
+		do_notify_pidfd(tsk);
+
 	if (unlikely(tsk->ptrace)) {
 		int sig = thread_group_leader(tsk) &&
 				thread_group_empty(tsk) &&
@@ -1127,17 +1134,14 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		 * and nobody can change them.
 		 *
 		 * psig->stats_lock also protects us from our sub-threads
-		 * which can reap other children at the same time. Until
-		 * we change k_getrusage()-like users to rely on this lock
-		 * we have to take ->siglock as well.
+		 * which can reap other children at the same time.
 		 *
 		 * We use thread_group_cputime_adjusted() to get times for
 		 * the thread group, which consolidates times for all threads
 		 * in the group including the group leader.
 		 */
 		thread_group_cputime_adjusted(p, &tgutime, &tgstime);
-		spin_lock_irq(&current->sighand->siglock);
-		write_seqlock(&psig->stats_lock);
+		write_seqlock_irq(&psig->stats_lock);
 		psig->cutime += tgutime + sig->cutime;
 		psig->cstime += tgstime + sig->cstime;
 		psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime;
@@ -1160,8 +1164,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 			psig->cmaxrss = maxrss;
 		task_io_accounting_add(&psig->ioac, &p->ioac);
 		task_io_accounting_add(&psig->ioac, &sig->ioac);
-		write_sequnlock(&psig->stats_lock);
-		spin_unlock_irq(&current->sighand->siglock);
+		write_sequnlock_irq(&psig->stats_lock);
 	}
 
 	if (wo->wo_rusage)
@@ -1893,30 +1896,6 @@ Efault:
 }
 #endif
 
-/**
- * thread_group_exited - check that a thread group has exited
- * @pid: tgid of thread group to be checked.
- *
- * Test if the thread group represented by tgid has exited (all
- * threads are zombies, dead or completely gone).
- *
- * Return: true if the thread group has exited. false otherwise.
- */
-bool thread_group_exited(struct pid *pid)
-{
-	struct task_struct *task;
-	bool exited;
-
-	rcu_read_lock();
-	task = pid_task(pid, PIDTYPE_PID);
-	exited = !task ||
-		(READ_ONCE(task->exit_state) && thread_group_empty(task));
-	rcu_read_unlock();
-
-	return exited;
-}
-EXPORT_SYMBOL(thread_group_exited);
-
 /*
  * This needs to be __function_aligned as GCC implicitly makes any
  * implementation of abort() cold and drops alignment specified by
diff --git a/kernel/fork.c b/kernel/fork.c
index c981fa6171c1..39a5046c2f0b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -101,6 +101,8 @@
 #include <linux/user_events.h>
 #include <linux/iommu.h>
 #include <linux/rseq.h>
+#include <uapi/linux/pidfd.h>
+#include <linux/pidfs.h>
 
 #include <asm/pgalloc.h>
 #include <linux/uaccess.h>
@@ -1173,7 +1175,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	tsk->use_memdelay = 0;
 #endif
 
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_ARCH_HAS_CPU_PASID
 	tsk->pasid_activated = 0;
 #endif
 
@@ -1748,6 +1750,7 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
 	if (clone_flags & CLONE_FS) {
 		/* tsk->fs is already what we want */
 		spin_lock(&fs->lock);
+		/* "users" and "in_exec" locked for check_unsafe_exec() */
 		if (fs->in_exec) {
 			spin_unlock(&fs->lock);
 			return -EAGAIN;
@@ -1975,6 +1978,7 @@ static inline void rcu_copy_process(struct task_struct *p)
 	p->rcu_tasks_holdout = false;
 	INIT_LIST_HEAD(&p->rcu_tasks_holdout_list);
 	p->rcu_tasks_idle_cpu = -1;
+	INIT_LIST_HEAD(&p->rcu_tasks_exit_list);
 #endif /* #ifdef CONFIG_TASKS_RCU */
 #ifdef CONFIG_TASKS_TRACE_RCU
 	p->trc_reader_nesting = 0;
@@ -1984,119 +1988,6 @@ static inline void rcu_copy_process(struct task_struct *p)
 #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
 }
 
-struct pid *pidfd_pid(const struct file *file)
-{
-	if (file->f_op == &pidfd_fops)
-		return file->private_data;
-
-	return ERR_PTR(-EBADF);
-}
-
-static int pidfd_release(struct inode *inode, struct file *file)
-{
-	struct pid *pid = file->private_data;
-
-	file->private_data = NULL;
-	put_pid(pid);
-	return 0;
-}
-
-#ifdef CONFIG_PROC_FS
-/**
- * pidfd_show_fdinfo - print information about a pidfd
- * @m: proc fdinfo file
- * @f: file referencing a pidfd
- *
- * Pid:
- * This function will print the pid that a given pidfd refers to in the
- * pid namespace of the procfs instance.
- * If the pid namespace of the process is not a descendant of the pid
- * namespace of the procfs instance 0 will be shown as its pid. This is
- * similar to calling getppid() on a process whose parent is outside of
- * its pid namespace.
- *
- * NSpid:
- * If pid namespaces are supported then this function will also print
- * the pid of a given pidfd refers to for all descendant pid namespaces
- * starting from the current pid namespace of the instance, i.e. the
- * Pid field and the first entry in the NSpid field will be identical.
- * If the pid namespace of the process is not a descendant of the pid
- * namespace of the procfs instance 0 will be shown as its first NSpid
- * entry and no others will be shown.
- * Note that this differs from the Pid and NSpid fields in
- * /proc/<pid>/status where Pid and NSpid are always shown relative to
- * the  pid namespace of the procfs instance. The difference becomes
- * obvious when sending around a pidfd between pid namespaces from a
- * different branch of the tree, i.e. where no ancestral relation is
- * present between the pid namespaces:
- * - create two new pid namespaces ns1 and ns2 in the initial pid
- *   namespace (also take care to create new mount namespaces in the
- *   new pid namespace and mount procfs)
- * - create a process with a pidfd in ns1
- * - send pidfd from ns1 to ns2
- * - read /proc/self/fdinfo/<pidfd> and observe that both Pid and NSpid
- *   have exactly one entry, which is 0
- */
-static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
-{
-	struct pid *pid = f->private_data;
-	struct pid_namespace *ns;
-	pid_t nr = -1;
-
-	if (likely(pid_has_task(pid, PIDTYPE_PID))) {
-		ns = proc_pid_ns(file_inode(m->file)->i_sb);
-		nr = pid_nr_ns(pid, ns);
-	}
-
-	seq_put_decimal_ll(m, "Pid:\t", nr);
-
-#ifdef CONFIG_PID_NS
-	seq_put_decimal_ll(m, "\nNSpid:\t", nr);
-	if (nr > 0) {
-		int i;
-
-		/* If nr is non-zero it means that 'pid' is valid and that
-		 * ns, i.e. the pid namespace associated with the procfs
-		 * instance, is in the pid namespace hierarchy of pid.
-		 * Start at one below the already printed level.
-		 */
-		for (i = ns->level + 1; i <= pid->level; i++)
-			seq_put_decimal_ll(m, "\t", pid->numbers[i].nr);
-	}
-#endif
-	seq_putc(m, '\n');
-}
-#endif
-
-/*
- * Poll support for process exit notification.
- */
-static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts)
-{
-	struct pid *pid = file->private_data;
-	__poll_t poll_flags = 0;
-
-	poll_wait(file, &pid->wait_pidfd, pts);
-
-	/*
-	 * Inform pollers only when the whole thread group exits.
-	 * If the thread group leader exits before all other threads in the
-	 * group, then poll(2) should block, similar to the wait(2) family.
-	 */
-	if (thread_group_exited(pid))
-		poll_flags = EPOLLIN | EPOLLRDNORM;
-
-	return poll_flags;
-}
-
-const struct file_operations pidfd_fops = {
-	.release = pidfd_release,
-	.poll = pidfd_poll,
-#ifdef CONFIG_PROC_FS
-	.show_fdinfo = pidfd_show_fdinfo,
-#endif
-};
-
 /**
  * __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd
  * @pid:   the struct pid for which to create a pidfd
@@ -2130,20 +2021,20 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re
 	int pidfd;
 	struct file *pidfd_file;
 
-	if (flags & ~(O_NONBLOCK | O_RDWR | O_CLOEXEC))
-		return -EINVAL;
-
-	pidfd = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
+	pidfd = get_unused_fd_flags(O_CLOEXEC);
 	if (pidfd < 0)
 		return pidfd;
 
-	pidfd_file = anon_inode_getfile("[pidfd]", &pidfd_fops, pid,
-					flags | O_RDWR | O_CLOEXEC);
+	pidfd_file = pidfs_alloc_file(pid, flags | O_RDWR);
 	if (IS_ERR(pidfd_file)) {
 		put_unused_fd(pidfd);
 		return PTR_ERR(pidfd_file);
 	}
-	get_pid(pid); /* held by pidfd_file now */
+	/*
+	 * anon_inode_getfile() ignores everything outside of the
+	 * O_ACCMODE | O_NONBLOCK mask, set PIDFD_THREAD manually.
+	 */
+	pidfd_file->f_flags |= (flags & PIDFD_THREAD);
 	*ret = pidfd_file;
 	return pidfd;
 }
@@ -2157,7 +2048,8 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re
  * Allocate a new file that stashes @pid and reserve a new pidfd number in the
  * caller's file descriptor table. The pidfd is reserved but not installed yet.
  *
- * The helper verifies that @pid is used as a thread group leader.
+ * The helper verifies that @pid is still in use, without PIDFD_THREAD the
+ * task identified by @pid must be a thread-group leader.
  *
  * If this function returns successfully the caller is responsible to either
  * call fd_install() passing the returned pidfd and pidfd file as arguments in
@@ -2176,7 +2068,9 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re
  */
 int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret)
 {
-	if (!pid || !pid_has_task(pid, PIDTYPE_TGID))
+	bool thread = flags & PIDFD_THREAD;
+
+	if (!pid || !pid_has_task(pid, thread ? PIDTYPE_PID : PIDTYPE_TGID))
 		return -EINVAL;
 
 	return __pidfd_prepare(pid, flags, ret);
@@ -2298,9 +2192,8 @@ __latent_entropy struct task_struct *copy_process(
 		/*
 		 * - CLONE_DETACHED is blocked so that we can potentially
 		 *   reuse it later for CLONE_PIDFD.
-		 * - CLONE_THREAD is blocked until someone really needs it.
 		 */
-		if (clone_flags & (CLONE_DETACHED | CLONE_THREAD))
+		if (clone_flags & CLONE_DETACHED)
 			return ERR_PTR(-EINVAL);
 	}
 
@@ -2523,8 +2416,10 @@ __latent_entropy struct task_struct *copy_process(
 	 * if the fd table isn't shared).
 	 */
 	if (clone_flags & CLONE_PIDFD) {
+		int flags = (clone_flags & CLONE_THREAD) ? PIDFD_THREAD : 0;
+
 		/* Note that no task has been attached to @pid yet. */
-		retval = __pidfd_prepare(pid, O_RDWR | O_CLOEXEC, &pidfile);
+		retval = __pidfd_prepare(pid, flags, &pidfile);
 		if (retval < 0)
 			goto bad_fork_free_pid;
 		pidfd = retval;
@@ -2875,8 +2770,8 @@ pid_t kernel_clone(struct kernel_clone_args *args)
 	 * here has the advantage that we don't need to have a separate helper
 	 * to check for legacy clone().
 	 */
-	if ((args->flags & CLONE_PIDFD) &&
-	    (args->flags & CLONE_PARENT_SETTID) &&
+	if ((clone_flags & CLONE_PIDFD) &&
+	    (clone_flags & CLONE_PARENT_SETTID) &&
 	    (args->pidfd == args->parent_tid))
 		return -EINVAL;
 
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index e0e853412c15..1e78ef24321e 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -627,12 +627,21 @@ retry:
 }
 
 /*
- * PI futexes can not be requeued and must remove themselves from the
- * hash bucket. The hash bucket lock (i.e. lock_ptr) is held.
+ * PI futexes can not be requeued and must remove themselves from the hash
+ * bucket. The hash bucket lock (i.e. lock_ptr) is held.
  */
 void futex_unqueue_pi(struct futex_q *q)
 {
-	__futex_unqueue(q);
+	/*
+	 * If the lock was not acquired (due to timeout or signal) then the
+	 * rt_waiter is removed before futex_q is. If this is observed by
+	 * an unlocker after dropping the rtmutex wait lock and before
+	 * acquiring the hash bucket lock, then the unlocker dequeues the
+	 * futex_q from the hash bucket list to guarantee consistent state
+	 * vs. userspace. Therefore the dequeue here must be conditional.
+	 */
+	if (!plist_node_empty(&q->list))
+		__futex_unqueue(q);
 
 	BUG_ON(!q->pi_state);
 	put_pi_state(q->pi_state);
diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c
index 90e5197f4e56..5722467f2737 100644
--- a/kernel/futex/pi.c
+++ b/kernel/futex/pi.c
@@ -1135,6 +1135,7 @@ retry:
 
 	hb = futex_hash(&key);
 	spin_lock(&hb->lock);
+retry_hb:
 
 	/*
 	 * Check waiters first. We do not trust user space values at
@@ -1177,12 +1178,17 @@ retry:
 		/*
 		 * Futex vs rt_mutex waiter state -- if there are no rt_mutex
 		 * waiters even though futex thinks there are, then the waiter
-		 * is leaving and the uncontended path is safe to take.
+		 * is leaving. The entry needs to be removed from the list so a
+		 * new futex_lock_pi() is not using this stale PI-state while
+		 * the futex is available in user space again.
+		 * There can be more than one task on its way out so it needs
+		 * to retry.
 		 */
 		rt_waiter = rt_mutex_top_waiter(&pi_state->pi_mutex);
 		if (!rt_waiter) {
+			__futex_unqueue(top_waiter);
 			raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
-			goto do_uncontended;
+			goto retry_hb;
 		}
 
 		get_pi_state(pi_state);
@@ -1217,7 +1223,6 @@ retry:
 		return ret;
 	}
 
-do_uncontended:
 	/*
 	 * We have no kernel internal state, i.e. no waiters in the
 	 * kernel. Waiters which are about to queue themselves are stuck
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 27ca1c866f29..371eb1711d34 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -600,7 +600,7 @@ int __init early_irq_init(void)
 		mutex_init(&desc[i].request_mutex);
 		init_waitqueue_head(&desc[i].wait_for_threads);
 		desc_set_defaults(i, &desc[i], node, NULL, NULL);
-		irq_resend_init(desc);
+		irq_resend_init(&desc[i]);
 	}
 	return arch_early_irq_init();
 }
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index a08031b57a61..d08fc7b5db97 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -1257,6 +1257,7 @@ int kernel_kexec(void)
 		kexec_in_progress = true;
 		kernel_restart_prepare("kexec reboot");
 		migrate_to_reboot_cpu();
+		syscore_shutdown();
 
 		/*
 		 * migrate_to_reboot_cpu() disables CPU hotplug assuming that
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index d5a0ee40bf66..9d9095e81792 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1993,7 +1993,7 @@ NOKPROBE_SYMBOL(__kretprobe_find_ret_addr);
 unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp,
 				      struct llist_node **cur)
 {
-	struct kretprobe_instance *ri = NULL;
+	struct kretprobe_instance *ri;
 	kprobe_opcode_t *ret;
 
 	if (WARN_ON_ONCE(!cur))
@@ -2802,7 +2802,7 @@ static int show_kprobe_addr(struct seq_file *pi, void *v)
 {
 	struct hlist_head *head;
 	struct kprobe *p, *kp;
-	const char *sym = NULL;
+	const char *sym;
 	unsigned int i = *(loff_t *) v;
 	unsigned long offset = 0;
 	char *modname, namebuf[KSYM_NAME_LEN];
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 15781acaac1c..6ec3deec68c2 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -573,7 +573,7 @@ SYSCALL_DEFINE2(setns, int, fd, int, flags)
 	if (proc_ns_file(f.file))
 		err = validate_ns(&nsset, ns);
 	else
-		err = validate_nsset(&nsset, f.file->private_data);
+		err = validate_nsset(&nsset, pidfd_pid(f.file));
 	if (!err) {
 		commit_nsset(&nsset);
 		perf_event_namespaces(current);
diff --git a/kernel/pid.c b/kernel/pid.c
index b52b10865454..99a0c5eb24b8 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -42,6 +42,7 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/task.h>
 #include <linux/idr.h>
+#include <linux/pidfs.h>
 #include <net/sock.h>
 #include <uapi/linux/pidfd.h>
 
@@ -65,6 +66,13 @@ int pid_max = PID_MAX_DEFAULT;
 
 int pid_max_min = RESERVED_PIDS + 1;
 int pid_max_max = PID_MAX_LIMIT;
+#ifdef CONFIG_FS_PID
+/*
+ * Pseudo filesystems start inode numbering after one. We use Reserved
+ * PIDs as a natural offset.
+ */
+static u64 pidfs_ino = RESERVED_PIDS;
+#endif
 
 /*
  * PID-map pages start out as NULL, they get allocated upon
@@ -272,6 +280,10 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 	spin_lock_irq(&pidmap_lock);
 	if (!(ns->pid_allocated & PIDNS_ADDING))
 		goto out_unlock;
+#ifdef CONFIG_FS_PID
+	pid->stashed = NULL;
+	pid->ino = ++pidfs_ino;
+#endif
 	for ( ; upid >= pid->numbers; --upid) {
 		/* Make the PID visible to find_pid_ns. */
 		idr_replace(&upid->ns->idr, pid, upid->nr);
@@ -349,6 +361,11 @@ static void __change_pid(struct task_struct *task, enum pid_type type,
 	hlist_del_rcu(&task->pid_links[type]);
 	*pid_ptr = new;
 
+	if (type == PIDTYPE_PID) {
+		WARN_ON_ONCE(pid_has_task(pid, PIDTYPE_PID));
+		wake_up_all(&pid->wait_pidfd);
+	}
+
 	for (tmp = PIDTYPE_MAX; --tmp >= 0; )
 		if (pid_has_task(pid, tmp))
 			return;
@@ -391,8 +408,7 @@ void exchange_tids(struct task_struct *left, struct task_struct *right)
 void transfer_pid(struct task_struct *old, struct task_struct *new,
 			   enum pid_type type)
 {
-	if (type == PIDTYPE_PID)
-		new->thread_pid = old->thread_pid;
+	WARN_ON_ONCE(type == PIDTYPE_PID);
 	hlist_replace_rcu(&old->pid_links[type], &new->pid_links[type]);
 }
 
@@ -552,11 +568,6 @@ struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags)
  * Return the task associated with @pidfd. The function takes a reference on
  * the returned task. The caller is responsible for releasing that reference.
  *
- * Currently, the process identified by @pidfd is always a thread-group leader.
- * This restriction currently exists for all aspects of pidfds including pidfd
- * creation (CLONE_PIDFD cannot be used with CLONE_THREAD) and pidfd polling
- * (only supports thread group leaders).
- *
  * Return: On success, the task_struct associated with the pidfd.
  *	   On error, a negative errno number will be returned.
  */
@@ -595,7 +606,7 @@ struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags)
  * Return: On success, a cloexec pidfd is returned.
  *         On error, a negative errno number will be returned.
  */
-int pidfd_create(struct pid *pid, unsigned int flags)
+static int pidfd_create(struct pid *pid, unsigned int flags)
 {
 	int pidfd;
 	struct file *pidfd_file;
@@ -615,11 +626,8 @@ int pidfd_create(struct pid *pid, unsigned int flags)
  * @flags: flags to pass
  *
  * This creates a new pid file descriptor with the O_CLOEXEC flag set for
- * the process identified by @pid. Currently, the process identified by
- * @pid must be a thread-group leader. This restriction currently exists
- * for all aspects of pidfds including pidfd creation (CLONE_PIDFD cannot
- * be used with CLONE_THREAD) and pidfd polling (only supports thread group
- * leaders).
+ * the task identified by @pid. Without PIDFD_THREAD flag the target task
+ * must be a thread-group leader.
  *
  * Return: On success, a cloexec pidfd is returned.
  *         On error, a negative errno number will be returned.
@@ -629,7 +637,7 @@ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
 	int fd;
 	struct pid *p;
 
-	if (flags & ~PIDFD_NONBLOCK)
+	if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD))
 		return -EINVAL;
 
 	if (pid <= 0)
@@ -682,7 +690,26 @@ static struct file *__pidfd_fget(struct task_struct *task, int fd)
 
 	up_read(&task->signal->exec_update_lock);
 
-	return file ?: ERR_PTR(-EBADF);
+	if (!file) {
+		/*
+		 * It is possible that the target thread is exiting; it can be
+		 * either:
+		 * 1. before exit_signals(), which gives a real fd
+		 * 2. before exit_files() takes the task_lock() gives a real fd
+		 * 3. after exit_files() releases task_lock(), ->files is NULL;
+		 *    this has PF_EXITING, since it was set in exit_signals(),
+		 *    __pidfd_fget() returns EBADF.
+		 * In case 3 we get EBADF, but that really means ESRCH, since
+		 * the task is currently exiting and has freed its files
+		 * struct, so we fix it up.
+		 */
+		if (task->flags & PF_EXITING)
+			file = ERR_PTR(-ESRCH);
+		else
+			file = ERR_PTR(-EBADF);
+	}
+
+	return file;
 }
 
 static int pidfd_getfd(struct pid *pid, int fd)
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 6053ddddaf65..692f12fe60c1 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -222,7 +222,7 @@ int swsusp_swap_in_use(void)
  */
 
 static unsigned short root_swap = 0xffff;
-static struct bdev_handle *hib_resume_bdev_handle;
+static struct file *hib_resume_bdev_file;
 
 struct hib_bio_batch {
 	atomic_t		count;
@@ -276,7 +276,7 @@ static int hib_submit_io(blk_opf_t opf, pgoff_t page_off, void *addr,
 	struct bio *bio;
 	int error = 0;
 
-	bio = bio_alloc(hib_resume_bdev_handle->bdev, 1, opf,
+	bio = bio_alloc(file_bdev(hib_resume_bdev_file), 1, opf,
 			GFP_NOIO | __GFP_HIGH);
 	bio->bi_iter.bi_sector = page_off * (PAGE_SIZE >> 9);
 
@@ -357,14 +357,14 @@ static int swsusp_swap_check(void)
 		return res;
 	root_swap = res;
 
-	hib_resume_bdev_handle = bdev_open_by_dev(swsusp_resume_device,
+	hib_resume_bdev_file = bdev_file_open_by_dev(swsusp_resume_device,
 			BLK_OPEN_WRITE, NULL, NULL);
-	if (IS_ERR(hib_resume_bdev_handle))
-		return PTR_ERR(hib_resume_bdev_handle);
+	if (IS_ERR(hib_resume_bdev_file))
+		return PTR_ERR(hib_resume_bdev_file);
 
-	res = set_blocksize(hib_resume_bdev_handle->bdev, PAGE_SIZE);
+	res = set_blocksize(file_bdev(hib_resume_bdev_file), PAGE_SIZE);
 	if (res < 0)
-		bdev_release(hib_resume_bdev_handle);
+		fput(hib_resume_bdev_file);
 
 	return res;
 }
@@ -1523,10 +1523,10 @@ int swsusp_check(bool exclusive)
 	void *holder = exclusive ? &swsusp_holder : NULL;
 	int error;
 
-	hib_resume_bdev_handle = bdev_open_by_dev(swsusp_resume_device,
+	hib_resume_bdev_file = bdev_file_open_by_dev(swsusp_resume_device,
 				BLK_OPEN_READ, holder, NULL);
-	if (!IS_ERR(hib_resume_bdev_handle)) {
-		set_blocksize(hib_resume_bdev_handle->bdev, PAGE_SIZE);
+	if (!IS_ERR(hib_resume_bdev_file)) {
+		set_blocksize(file_bdev(hib_resume_bdev_file), PAGE_SIZE);
 		clear_page(swsusp_header);
 		error = hib_submit_io(REQ_OP_READ, swsusp_resume_block,
 					swsusp_header, NULL);
@@ -1551,11 +1551,11 @@ int swsusp_check(bool exclusive)
 
 put:
 		if (error)
-			bdev_release(hib_resume_bdev_handle);
+			fput(hib_resume_bdev_file);
 		else
 			pr_debug("Image signature found, resuming\n");
 	} else {
-		error = PTR_ERR(hib_resume_bdev_handle);
+		error = PTR_ERR(hib_resume_bdev_file);
 	}
 
 	if (error)
@@ -1570,12 +1570,12 @@ put:
 
 void swsusp_close(void)
 {
-	if (IS_ERR(hib_resume_bdev_handle)) {
+	if (IS_ERR(hib_resume_bdev_file)) {
 		pr_debug("Image device not initialised\n");
 		return;
 	}
 
-	bdev_release(hib_resume_bdev_handle);
+	fput(hib_resume_bdev_file);
 }
 
 /**
diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index bdd7eadb33d8..e7d2dd267593 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -314,6 +314,19 @@ config RCU_LAZY
 	  To save power, batch RCU callbacks and flush after delay, memory
 	  pressure, or callback list growing too big.
 
+	  Requires rcu_nocbs=all to be set.
+
+	  Use rcutree.enable_rcu_lazy=0 to turn it off at boot time.
+
+config RCU_LAZY_DEFAULT_OFF
+	bool "Turn RCU lazy invocation off by default"
+	depends on RCU_LAZY
+	default n
+	help
+	  Allows building the kernel with CONFIG_RCU_LAZY=y yet keep it default
+	  off. Boot time param rcutree.enable_rcu_lazy=1 can be used to switch
+	  it back on.
+
 config RCU_DOUBLE_CHECK_CB_TIME
 	bool "RCU callback-batch backup time check"
 	depends on RCU_EXPERT
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index f94f65877f2b..86fce206560e 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -528,6 +528,12 @@ struct task_struct *get_rcu_tasks_gp_kthread(void);
 struct task_struct *get_rcu_tasks_rude_gp_kthread(void);
 #endif // # ifdef CONFIG_TASKS_RUDE_RCU
 
+#ifdef CONFIG_TASKS_RCU_GENERIC
+void tasks_cblist_init_generic(void);
+#else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
+static inline void tasks_cblist_init_generic(void) { }
+#endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */
+
 #define RCU_SCHEDULER_INACTIVE	0
 #define RCU_SCHEDULER_INIT	1
 #define RCU_SCHEDULER_RUNNING	2
@@ -543,11 +549,11 @@ enum rcutorture_type {
 };
 
 #if defined(CONFIG_RCU_LAZY)
-unsigned long rcu_lazy_get_jiffies_till_flush(void);
-void rcu_lazy_set_jiffies_till_flush(unsigned long j);
+unsigned long rcu_get_jiffies_lazy_flush(void);
+void rcu_set_jiffies_lazy_flush(unsigned long j);
 #else
-static inline unsigned long rcu_lazy_get_jiffies_till_flush(void) { return 0; }
-static inline void rcu_lazy_set_jiffies_till_flush(unsigned long j) { }
+static inline unsigned long rcu_get_jiffies_lazy_flush(void) { return 0; }
+static inline void rcu_set_jiffies_lazy_flush(unsigned long j) { }
 #endif
 
 #if defined(CONFIG_TREE_RCU)
@@ -623,12 +629,7 @@ int rcu_get_gp_kthreads_prio(void);
 void rcu_fwd_progress_check(unsigned long j);
 void rcu_force_quiescent_state(void);
 extern struct workqueue_struct *rcu_gp_wq;
-#ifdef CONFIG_RCU_EXP_KTHREAD
 extern struct kthread_worker *rcu_exp_gp_kworker;
-extern struct kthread_worker *rcu_exp_par_gp_kworker;
-#else /* !CONFIG_RCU_EXP_KTHREAD */
-extern struct workqueue_struct *rcu_par_gp_wq;
-#endif /* CONFIG_RCU_EXP_KTHREAD */
 void rcu_gp_slow_register(atomic_t *rgssp);
 void rcu_gp_slow_unregister(atomic_t *rgssp);
 #endif /* #else #ifdef CONFIG_TINY_RCU */
diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
index ffdb30495e3c..8db4fedaaa1e 100644
--- a/kernel/rcu/rcuscale.c
+++ b/kernel/rcu/rcuscale.c
@@ -764,9 +764,9 @@ kfree_scale_init(void)
 
 	if (kfree_by_call_rcu) {
 		/* do a test to check the timeout. */
-		orig_jif = rcu_lazy_get_jiffies_till_flush();
+		orig_jif = rcu_get_jiffies_lazy_flush();
 
-		rcu_lazy_set_jiffies_till_flush(2 * HZ);
+		rcu_set_jiffies_lazy_flush(2 * HZ);
 		rcu_barrier();
 
 		jif_start = jiffies;
@@ -775,7 +775,7 @@ kfree_scale_init(void)
 
 		smp_cond_load_relaxed(&rcu_lazy_test1_cb_called, VAL == 1);
 
-		rcu_lazy_set_jiffies_till_flush(orig_jif);
+		rcu_set_jiffies_lazy_flush(orig_jif);
 
 		if (WARN_ON_ONCE(jiffies_at_lazy_cb - jif_start < 2 * HZ)) {
 			pr_alert("ERROR: call_rcu() CBs are not being lazy as expected!\n");
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 7567ca8e743c..45d6b4c3d199 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1368,9 +1368,13 @@ rcu_torture_writer(void *arg)
 	struct rcu_torture *rp;
 	struct rcu_torture *old_rp;
 	static DEFINE_TORTURE_RANDOM(rand);
+	unsigned long stallsdone = jiffies;
 	bool stutter_waited;
 	unsigned long ulo[NUM_ACTIVE_RCU_POLL_OLDSTATE];
 
+	// If a new stall test is added, this must be adjusted.
+	if (stall_cpu_holdoff + stall_gp_kthread + stall_cpu)
+		stallsdone += (stall_cpu_holdoff + stall_gp_kthread + stall_cpu + 60) * HZ;
 	VERBOSE_TOROUT_STRING("rcu_torture_writer task started");
 	if (!can_expedite)
 		pr_alert("%s" TORTURE_FLAG
@@ -1576,11 +1580,11 @@ rcu_torture_writer(void *arg)
 		    !atomic_read(&rcu_fwd_cb_nodelay) &&
 		    !cur_ops->slow_gps &&
 		    !torture_must_stop() &&
-		    boot_ended)
+		    boot_ended &&
+		    time_after(jiffies, stallsdone))
 			for (i = 0; i < ARRAY_SIZE(rcu_tortures); i++)
 				if (list_empty(&rcu_tortures[i].rtort_free) &&
-				    rcu_access_pointer(rcu_torture_current) !=
-				    &rcu_tortures[i]) {
+				    rcu_access_pointer(rcu_torture_current) != &rcu_tortures[i]) {
 					tracing_off();
 					show_rcu_gp_kthreads();
 					WARN(1, "%s: rtort_pipe_count: %d\n", __func__, rcu_tortures[i].rtort_pipe_count);
@@ -2441,7 +2445,8 @@ static struct notifier_block rcu_torture_stall_block = {
 
 /*
  * CPU-stall kthread.  It waits as specified by stall_cpu_holdoff, then
- * induces a CPU stall for the time specified by stall_cpu.
+ * induces a CPU stall for the time specified by stall_cpu.  If a new
+ * stall test is added, stallsdone in rcu_torture_writer() must be adjusted.
  */
 static int rcu_torture_stall(void *args)
 {
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 0351a4e83529..e4d673fc30f4 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -1234,11 +1234,20 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp,
 	if (rhp)
 		rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp);
 	/*
-	 * The snapshot for acceleration must be taken _before_ the read of the
-	 * current gp sequence used for advancing, otherwise advancing may fail
-	 * and acceleration may then fail too.
+	 * It's crucial to capture the snapshot 's' for acceleration before
+	 * reading the current gp_seq that is used for advancing. This is
+	 * essential because if the acceleration snapshot is taken after a
+	 * failed advancement attempt, there's a risk that a grace period may
+	 * conclude and a new one may start in the interim. If the snapshot is
+	 * captured after this sequence of events, the acceleration snapshot 's'
+	 * could be excessively advanced, leading to acceleration failure.
+	 * In such a scenario, an 'acceleration leak' can occur, where new
+	 * callbacks become indefinitely stuck in the RCU_NEXT_TAIL segment.
+	 * Also note that encountering advancing failures is a normal
+	 * occurrence when the grace period for RCU_WAIT_TAIL is in progress.
 	 *
-	 * This could happen if:
+	 * To see this, consider the following events which occur if
+	 * rcu_seq_snap() were to be called after advance:
 	 *
 	 *  1) The RCU_WAIT_TAIL segment has callbacks (gp_num = X + 4) and the
 	 *     RCU_NEXT_READY_TAIL also has callbacks (gp_num = X + 8).
@@ -1264,6 +1273,13 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp,
 	if (rhp) {
 		rcu_segcblist_advance(&sdp->srcu_cblist,
 				      rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
+		/*
+		 * Acceleration can never fail because the base current gp_seq
+		 * used for acceleration is <= the value of gp_seq used for
+		 * advancing. This means that RCU_NEXT_TAIL segment will
+		 * always be able to be emptied by the acceleration into the
+		 * RCU_NEXT_READY_TAIL or RCU_WAIT_TAIL segments.
+		 */
 		WARN_ON_ONCE(!rcu_segcblist_accelerate(&sdp->srcu_cblist, s));
 	}
 	if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {
diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c
index e550f97779b8..86df878a2fee 100644
--- a/kernel/rcu/sync.c
+++ b/kernel/rcu/sync.c
@@ -24,22 +24,6 @@ void rcu_sync_init(struct rcu_sync *rsp)
 	init_waitqueue_head(&rsp->gp_wait);
 }
 
-/**
- * rcu_sync_enter_start - Force readers onto slow path for multiple updates
- * @rsp: Pointer to rcu_sync structure to use for synchronization
- *
- * Must be called after rcu_sync_init() and before first use.
- *
- * Ensures rcu_sync_is_idle() returns false and rcu_sync_{enter,exit}()
- * pairs turn into NO-OPs.
- */
-void rcu_sync_enter_start(struct rcu_sync *rsp)
-{
-	rsp->gp_count++;
-	rsp->gp_state = GP_PASSED;
-}
-
-
 static void rcu_sync_func(struct rcu_head *rhp);
 
 static void rcu_sync_call(struct rcu_sync *rsp)
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 732ad5b39946..147b5945d67a 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -32,6 +32,7 @@ typedef void (*postgp_func_t)(struct rcu_tasks *rtp);
  * @rtp_irq_work: IRQ work queue for deferred wakeups.
  * @barrier_q_head: RCU callback for barrier operation.
  * @rtp_blkd_tasks: List of tasks blocked as readers.
+ * @rtp_exit_list: List of tasks in the latter portion of do_exit().
  * @cpu: CPU number corresponding to this entry.
  * @rtpp: Pointer to the rcu_tasks structure.
  */
@@ -46,6 +47,7 @@ struct rcu_tasks_percpu {
 	struct irq_work rtp_irq_work;
 	struct rcu_head barrier_q_head;
 	struct list_head rtp_blkd_tasks;
+	struct list_head rtp_exit_list;
 	int cpu;
 	struct rcu_tasks *rtpp;
 };
@@ -144,8 +146,6 @@ static struct rcu_tasks rt_name =							\
 }
 
 #ifdef CONFIG_TASKS_RCU
-/* Track exiting tasks in order to allow them to be waited for. */
-DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu);
 
 /* Report delay in synchronize_srcu() completion in rcu_tasks_postscan(). */
 static void tasks_rcu_exit_srcu_stall(struct timer_list *unused);
@@ -240,7 +240,6 @@ static const char *tasks_gp_state_getname(struct rcu_tasks *rtp)
 static void cblist_init_generic(struct rcu_tasks *rtp)
 {
 	int cpu;
-	unsigned long flags;
 	int lim;
 	int shift;
 
@@ -266,15 +265,15 @@ static void cblist_init_generic(struct rcu_tasks *rtp)
 		WARN_ON_ONCE(!rtpcp);
 		if (cpu)
 			raw_spin_lock_init(&ACCESS_PRIVATE(rtpcp, lock));
-		local_irq_save(flags);  // serialize initialization
 		if (rcu_segcblist_empty(&rtpcp->cblist))
 			rcu_segcblist_init(&rtpcp->cblist);
-		local_irq_restore(flags);
 		INIT_WORK(&rtpcp->rtp_work, rcu_tasks_invoke_cbs_wq);
 		rtpcp->cpu = cpu;
 		rtpcp->rtpp = rtp;
 		if (!rtpcp->rtp_blkd_tasks.next)
 			INIT_LIST_HEAD(&rtpcp->rtp_blkd_tasks);
+		if (!rtpcp->rtp_exit_list.next)
+			INIT_LIST_HEAD(&rtpcp->rtp_exit_list);
 	}
 
 	pr_info("%s: Setting shift to %d and lim to %d rcu_task_cb_adjust=%d.\n", rtp->name,
@@ -851,10 +850,12 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
 //	number of voluntary context switches, and add that task to the
 //	holdout list.
 // rcu_tasks_postscan():
-//	Invoke synchronize_srcu() to ensure that all tasks that were
-//	in the process of exiting (and which thus might not know to
-//	synchronize with this RCU Tasks grace period) have completed
-//	exiting.
+//	Gather per-CPU lists of tasks in do_exit() to ensure that all
+//	tasks that were in the process of exiting (and which thus might
+//	not know to synchronize with this RCU Tasks grace period) have
+//	completed exiting.  The synchronize_rcu() in rcu_tasks_postgp()
+//	will take care of any tasks stuck in the non-preemptible region
+//	of do_exit() following its call to exit_tasks_rcu_stop().
 // check_all_holdout_tasks(), repeatedly until holdout list is empty:
 //	Scans the holdout list, attempting to identify a quiescent state
 //	for each task on the list.  If there is a quiescent state, the
@@ -867,8 +868,10 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
 //	with interrupts disabled.
 //
 // For each exiting task, the exit_tasks_rcu_start() and
-// exit_tasks_rcu_finish() functions begin and end, respectively, the SRCU
-// read-side critical sections waited for by rcu_tasks_postscan().
+// exit_tasks_rcu_finish() functions add and remove, respectively, the
+// current task to a per-CPU list of tasks that rcu_tasks_postscan() must
+// wait on.  This is necessary because rcu_tasks_postscan() must wait on
+// tasks that have already been removed from the global list of tasks.
 //
 // Pre-grace-period update-side code is ordered before the grace
 // via the raw_spin_lock.*rcu_node().  Pre-grace-period read-side code
@@ -932,9 +935,13 @@ static void rcu_tasks_pertask(struct task_struct *t, struct list_head *hop)
 	}
 }
 
+void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func);
+DEFINE_RCU_TASKS(rcu_tasks, rcu_tasks_wait_gp, call_rcu_tasks, "RCU Tasks");
+
 /* Processing between scanning taskslist and draining the holdout list. */
 static void rcu_tasks_postscan(struct list_head *hop)
 {
+	int cpu;
 	int rtsi = READ_ONCE(rcu_task_stall_info);
 
 	if (!IS_ENABLED(CONFIG_TINY_RCU)) {
@@ -948,9 +955,9 @@ static void rcu_tasks_postscan(struct list_head *hop)
 	 * this, divide the fragile exit path part in two intersecting
 	 * read side critical sections:
 	 *
-	 * 1) An _SRCU_ read side starting before calling exit_notify(),
-	 *    which may remove the task from the tasklist, and ending after
-	 *    the final preempt_disable() call in do_exit().
+	 * 1) A task_struct list addition before calling exit_notify(),
+	 *    which may remove the task from the tasklist, with the
+	 *    removal after the final preempt_disable() call in do_exit().
 	 *
 	 * 2) An _RCU_ read side starting with the final preempt_disable()
 	 *    call in do_exit() and ending with the final call to schedule()
@@ -959,7 +966,37 @@ static void rcu_tasks_postscan(struct list_head *hop)
 	 * This handles the part 1). And postgp will handle part 2) with a
 	 * call to synchronize_rcu().
 	 */
-	synchronize_srcu(&tasks_rcu_exit_srcu);
+
+	for_each_possible_cpu(cpu) {
+		unsigned long j = jiffies + 1;
+		struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rcu_tasks.rtpcpu, cpu);
+		struct task_struct *t;
+		struct task_struct *t1;
+		struct list_head tmp;
+
+		raw_spin_lock_irq_rcu_node(rtpcp);
+		list_for_each_entry_safe(t, t1, &rtpcp->rtp_exit_list, rcu_tasks_exit_list) {
+			if (list_empty(&t->rcu_tasks_holdout_list))
+				rcu_tasks_pertask(t, hop);
+
+			// RT kernels need frequent pauses, otherwise
+			// pause at least once per pair of jiffies.
+			if (!IS_ENABLED(CONFIG_PREEMPT_RT) && time_before(jiffies, j))
+				continue;
+
+			// Keep our place in the list while pausing.
+			// Nothing else traverses this list, so adding a
+			// bare list_head is OK.
+			list_add(&tmp, &t->rcu_tasks_exit_list);
+			raw_spin_unlock_irq_rcu_node(rtpcp);
+			cond_resched(); // For CONFIG_PREEMPT=n kernels
+			raw_spin_lock_irq_rcu_node(rtpcp);
+			t1 = list_entry(tmp.next, struct task_struct, rcu_tasks_exit_list);
+			list_del(&tmp);
+			j = jiffies + 1;
+		}
+		raw_spin_unlock_irq_rcu_node(rtpcp);
+	}
 
 	if (!IS_ENABLED(CONFIG_TINY_RCU))
 		del_timer_sync(&tasks_rcu_exit_srcu_stall_timer);
@@ -1027,7 +1064,6 @@ static void rcu_tasks_postgp(struct rcu_tasks *rtp)
 	 *
 	 * In addition, this synchronize_rcu() waits for exiting tasks
 	 * to complete their final preempt_disable() region of execution,
-	 * cleaning up after synchronize_srcu(&tasks_rcu_exit_srcu),
 	 * enforcing the whole region before tasklist removal until
 	 * the final schedule() with TASK_DEAD state to be an RCU TASKS
 	 * read side critical section.
@@ -1035,9 +1071,6 @@ static void rcu_tasks_postgp(struct rcu_tasks *rtp)
 	synchronize_rcu();
 }
 
-void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func);
-DEFINE_RCU_TASKS(rcu_tasks, rcu_tasks_wait_gp, call_rcu_tasks, "RCU Tasks");
-
 static void tasks_rcu_exit_srcu_stall(struct timer_list *unused)
 {
 #ifndef CONFIG_TINY_RCU
@@ -1118,7 +1151,6 @@ module_param(rcu_tasks_lazy_ms, int, 0444);
 
 static int __init rcu_spawn_tasks_kthread(void)
 {
-	cblist_init_generic(&rcu_tasks);
 	rcu_tasks.gp_sleep = HZ / 10;
 	rcu_tasks.init_fract = HZ / 10;
 	if (rcu_tasks_lazy_ms >= 0)
@@ -1147,25 +1179,48 @@ struct task_struct *get_rcu_tasks_gp_kthread(void)
 EXPORT_SYMBOL_GPL(get_rcu_tasks_gp_kthread);
 
 /*
- * Contribute to protect against tasklist scan blind spot while the
- * task is exiting and may be removed from the tasklist. See
- * corresponding synchronize_srcu() for further details.
+ * Protect against tasklist scan blind spot while the task is exiting and
+ * may be removed from the tasklist.  Do this by adding the task to yet
+ * another list.
+ *
+ * Note that the task will remove itself from this list, so there is no
+ * need for get_task_struct(), except in the case where rcu_tasks_pertask()
+ * adds it to the holdout list, in which case rcu_tasks_pertask() supplies
+ * the needed get_task_struct().
  */
-void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu)
+void exit_tasks_rcu_start(void)
 {
-	current->rcu_tasks_idx = __srcu_read_lock(&tasks_rcu_exit_srcu);
+	unsigned long flags;
+	struct rcu_tasks_percpu *rtpcp;
+	struct task_struct *t = current;
+
+	WARN_ON_ONCE(!list_empty(&t->rcu_tasks_exit_list));
+	preempt_disable();
+	rtpcp = this_cpu_ptr(rcu_tasks.rtpcpu);
+	t->rcu_tasks_exit_cpu = smp_processor_id();
+	raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
+	if (!rtpcp->rtp_exit_list.next)
+		INIT_LIST_HEAD(&rtpcp->rtp_exit_list);
+	list_add(&t->rcu_tasks_exit_list, &rtpcp->rtp_exit_list);
+	raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
+	preempt_enable();
 }
 
 /*
- * Contribute to protect against tasklist scan blind spot while the
- * task is exiting and may be removed from the tasklist. See
- * corresponding synchronize_srcu() for further details.
+ * Remove the task from the "yet another list" because do_exit() is now
+ * non-preemptible, allowing synchronize_rcu() to wait beyond this point.
  */
-void exit_tasks_rcu_stop(void) __releases(&tasks_rcu_exit_srcu)
+void exit_tasks_rcu_stop(void)
 {
+	unsigned long flags;
+	struct rcu_tasks_percpu *rtpcp;
 	struct task_struct *t = current;
 
-	__srcu_read_unlock(&tasks_rcu_exit_srcu, t->rcu_tasks_idx);
+	WARN_ON_ONCE(list_empty(&t->rcu_tasks_exit_list));
+	rtpcp = per_cpu_ptr(rcu_tasks.rtpcpu, t->rcu_tasks_exit_cpu);
+	raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
+	list_del_init(&t->rcu_tasks_exit_list);
+	raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
 }
 
 /*
@@ -1282,7 +1337,6 @@ module_param(rcu_tasks_rude_lazy_ms, int, 0444);
 
 static int __init rcu_spawn_tasks_rude_kthread(void)
 {
-	cblist_init_generic(&rcu_tasks_rude);
 	rcu_tasks_rude.gp_sleep = HZ / 10;
 	if (rcu_tasks_rude_lazy_ms >= 0)
 		rcu_tasks_rude.lazy_jiffies = msecs_to_jiffies(rcu_tasks_rude_lazy_ms);
@@ -1914,7 +1968,6 @@ module_param(rcu_tasks_trace_lazy_ms, int, 0444);
 
 static int __init rcu_spawn_tasks_trace_kthread(void)
 {
-	cblist_init_generic(&rcu_tasks_trace);
 	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) {
 		rcu_tasks_trace.gp_sleep = HZ / 10;
 		rcu_tasks_trace.init_fract = HZ / 10;
@@ -2086,6 +2139,24 @@ late_initcall(rcu_tasks_verify_schedule_work);
 static void rcu_tasks_initiate_self_tests(void) { }
 #endif /* #else #ifdef CONFIG_PROVE_RCU */
 
+void __init tasks_cblist_init_generic(void)
+{
+	lockdep_assert_irqs_disabled();
+	WARN_ON(num_online_cpus() > 1);
+
+#ifdef CONFIG_TASKS_RCU
+	cblist_init_generic(&rcu_tasks);
+#endif
+
+#ifdef CONFIG_TASKS_RUDE_RCU
+	cblist_init_generic(&rcu_tasks_rude);
+#endif
+
+#ifdef CONFIG_TASKS_TRACE_RCU
+	cblist_init_generic(&rcu_tasks_trace);
+#endif
+}
+
 void __init rcu_init_tasks_generic(void)
 {
 #ifdef CONFIG_TASKS_RCU
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index fec804b79080..705c0d16850a 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -261,4 +261,5 @@ void __init rcu_init(void)
 {
 	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 	rcu_early_boot_tests();
+	tasks_cblist_init_generic();
 }
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 1ae851777806..d9642dd06c25 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -145,7 +145,7 @@ static int rcu_scheduler_fully_active __read_mostly;
 
 static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp,
 			      unsigned long gps, unsigned long flags);
-static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
+static struct task_struct *rcu_boost_task(struct rcu_node *rnp);
 static void invoke_rcu_core(void);
 static void rcu_report_exp_rdp(struct rcu_data *rdp);
 static void sync_sched_exp_online_cleanup(int cpu);
@@ -1013,6 +1013,38 @@ static bool rcu_future_gp_cleanup(struct rcu_node *rnp)
 	return needmore;
 }
 
+static void swake_up_one_online_ipi(void *arg)
+{
+	struct swait_queue_head *wqh = arg;
+
+	swake_up_one(wqh);
+}
+
+static void swake_up_one_online(struct swait_queue_head *wqh)
+{
+	int cpu = get_cpu();
+
+	/*
+	 * If called from rcutree_report_cpu_starting(), wake up
+	 * is dangerous that late in the CPU-down hotplug process. The
+	 * scheduler might queue an ignored hrtimer. Defer the wake up
+	 * to an online CPU instead.
+	 */
+	if (unlikely(cpu_is_offline(cpu))) {
+		int target;
+
+		target = cpumask_any_and(housekeeping_cpumask(HK_TYPE_RCU),
+					 cpu_online_mask);
+
+		smp_call_function_single(target, swake_up_one_online_ipi,
+					 wqh, 0);
+		put_cpu();
+	} else {
+		put_cpu();
+		swake_up_one(wqh);
+	}
+}
+
 /*
  * Awaken the grace-period kthread.  Don't do a self-awaken (unless in an
  * interrupt or softirq handler, in which case we just might immediately
@@ -1037,7 +1069,7 @@ static void rcu_gp_kthread_wake(void)
 		return;
 	WRITE_ONCE(rcu_state.gp_wake_time, jiffies);
 	WRITE_ONCE(rcu_state.gp_wake_seq, READ_ONCE(rcu_state.gp_seq));
-	swake_up_one(&rcu_state.gp_wq);
+	swake_up_one_online(&rcu_state.gp_wq);
 }
 
 /*
@@ -2113,6 +2145,12 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	 * Extract the list of ready callbacks, disabling IRQs to prevent
 	 * races with call_rcu() from interrupt handlers.  Leave the
 	 * callback counts, as rcu_barrier() needs to be conservative.
+	 *
+	 * Callbacks execution is fully ordered against preceding grace period
+	 * completion (materialized by rnp->gp_seq update) thanks to the
+	 * smp_mb__after_unlock_lock() upon node locking required for callbacks
+	 * advancing. In NOCB mode this ordering is then further relayed through
+	 * the nocb locking that protects both callbacks advancing and extraction.
 	 */
 	rcu_nocb_lock_irqsave(rdp, flags);
 	WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
@@ -2559,12 +2597,26 @@ static int __init rcu_spawn_core_kthreads(void)
 	return 0;
 }
 
+static void rcutree_enqueue(struct rcu_data *rdp, struct rcu_head *head, rcu_callback_t func)
+{
+	rcu_segcblist_enqueue(&rdp->cblist, head);
+	if (__is_kvfree_rcu_offset((unsigned long)func))
+		trace_rcu_kvfree_callback(rcu_state.name, head,
+					 (unsigned long)func,
+					 rcu_segcblist_n_cbs(&rdp->cblist));
+	else
+		trace_rcu_callback(rcu_state.name, head,
+				   rcu_segcblist_n_cbs(&rdp->cblist));
+	trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCBQueued"));
+}
+
 /*
  * Handle any core-RCU processing required by a call_rcu() invocation.
  */
-static void __call_rcu_core(struct rcu_data *rdp, struct rcu_head *head,
-			    unsigned long flags)
+static void call_rcu_core(struct rcu_data *rdp, struct rcu_head *head,
+			  rcu_callback_t func, unsigned long flags)
 {
+	rcutree_enqueue(rdp, head, func);
 	/*
 	 * If called from an extended quiescent state, invoke the RCU
 	 * core in order to force a re-evaluation of RCU's idleness.
@@ -2660,7 +2712,6 @@ __call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy_in)
 	unsigned long flags;
 	bool lazy;
 	struct rcu_data *rdp;
-	bool was_alldone;
 
 	/* Misaligned rcu_head! */
 	WARN_ON_ONCE((unsigned long)head & (sizeof(void *) - 1));
@@ -2697,30 +2748,18 @@ __call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy_in)
 	}
 
 	check_cb_ovld(rdp);
-	if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags, lazy))
-		return; // Enqueued onto ->nocb_bypass, so just leave.
-	// If no-CBs CPU gets here, rcu_nocb_try_bypass() acquired ->nocb_lock.
-	rcu_segcblist_enqueue(&rdp->cblist, head);
-	if (__is_kvfree_rcu_offset((unsigned long)func))
-		trace_rcu_kvfree_callback(rcu_state.name, head,
-					 (unsigned long)func,
-					 rcu_segcblist_n_cbs(&rdp->cblist));
-	else
-		trace_rcu_callback(rcu_state.name, head,
-				   rcu_segcblist_n_cbs(&rdp->cblist));
 
-	trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCBQueued"));
-
-	/* Go handle any RCU core processing required. */
-	if (unlikely(rcu_rdp_is_offloaded(rdp))) {
-		__call_rcu_nocb_wake(rdp, was_alldone, flags); /* unlocks */
-	} else {
-		__call_rcu_core(rdp, head, flags);
-		local_irq_restore(flags);
-	}
+	if (unlikely(rcu_rdp_is_offloaded(rdp)))
+		call_rcu_nocb(rdp, head, func, flags, lazy);
+	else
+		call_rcu_core(rdp, head, func, flags);
+	local_irq_restore(flags);
 }
 
 #ifdef CONFIG_RCU_LAZY
+static bool enable_rcu_lazy __read_mostly = !IS_ENABLED(CONFIG_RCU_LAZY_DEFAULT_OFF);
+module_param(enable_rcu_lazy, bool, 0444);
+
 /**
  * call_rcu_hurry() - Queue RCU callback for invocation after grace period, and
  * flush all lazy callbacks (including the new one) to the main ->cblist while
@@ -2746,6 +2785,8 @@ void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func)
 	__call_rcu_common(head, func, false);
 }
 EXPORT_SYMBOL_GPL(call_rcu_hurry);
+#else
+#define enable_rcu_lazy		false
 #endif
 
 /**
@@ -2794,7 +2835,7 @@ EXPORT_SYMBOL_GPL(call_rcu_hurry);
  */
 void call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
-	__call_rcu_common(head, func, IS_ENABLED(CONFIG_RCU_LAZY));
+	__call_rcu_common(head, func, enable_rcu_lazy);
 }
 EXPORT_SYMBOL_GPL(call_rcu);
 
@@ -4362,6 +4403,66 @@ rcu_boot_init_percpu_data(int cpu)
 	rcu_boot_init_nocb_percpu_data(rdp);
 }
 
+struct kthread_worker *rcu_exp_gp_kworker;
+
+static void rcu_spawn_exp_par_gp_kworker(struct rcu_node *rnp)
+{
+	struct kthread_worker *kworker;
+	const char *name = "rcu_exp_par_gp_kthread_worker/%d";
+	struct sched_param param = { .sched_priority = kthread_prio };
+	int rnp_index = rnp - rcu_get_root();
+
+	if (rnp->exp_kworker)
+		return;
+
+	kworker = kthread_create_worker(0, name, rnp_index);
+	if (IS_ERR_OR_NULL(kworker)) {
+		pr_err("Failed to create par gp kworker on %d/%d\n",
+		       rnp->grplo, rnp->grphi);
+		return;
+	}
+	WRITE_ONCE(rnp->exp_kworker, kworker);
+
+	if (IS_ENABLED(CONFIG_RCU_EXP_KTHREAD))
+		sched_setscheduler_nocheck(kworker->task, SCHED_FIFO, &param);
+}
+
+static struct task_struct *rcu_exp_par_gp_task(struct rcu_node *rnp)
+{
+	struct kthread_worker *kworker = READ_ONCE(rnp->exp_kworker);
+
+	if (!kworker)
+		return NULL;
+
+	return kworker->task;
+}
+
+static void __init rcu_start_exp_gp_kworker(void)
+{
+	const char *name = "rcu_exp_gp_kthread_worker";
+	struct sched_param param = { .sched_priority = kthread_prio };
+
+	rcu_exp_gp_kworker = kthread_create_worker(0, name);
+	if (IS_ERR_OR_NULL(rcu_exp_gp_kworker)) {
+		pr_err("Failed to create %s!\n", name);
+		rcu_exp_gp_kworker = NULL;
+		return;
+	}
+
+	if (IS_ENABLED(CONFIG_RCU_EXP_KTHREAD))
+		sched_setscheduler_nocheck(rcu_exp_gp_kworker->task, SCHED_FIFO, &param);
+}
+
+static void rcu_spawn_rnp_kthreads(struct rcu_node *rnp)
+{
+	if (rcu_scheduler_fully_active) {
+		mutex_lock(&rnp->kthread_mutex);
+		rcu_spawn_one_boost_kthread(rnp);
+		rcu_spawn_exp_par_gp_kworker(rnp);
+		mutex_unlock(&rnp->kthread_mutex);
+	}
+}
+
 /*
  * Invoked early in the CPU-online process, when pretty much all services
  * are available.  The incoming CPU is not present.
@@ -4410,7 +4511,7 @@ int rcutree_prepare_cpu(unsigned int cpu)
 	rdp->rcu_iw_gp_seq = rdp->gp_seq - 1;
 	trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuonl"));
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-	rcu_spawn_one_boost_kthread(rnp);
+	rcu_spawn_rnp_kthreads(rnp);
 	rcu_spawn_cpu_nocb_kthread(cpu);
 	WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus + 1);
 
@@ -4418,13 +4519,64 @@ int rcutree_prepare_cpu(unsigned int cpu)
 }
 
 /*
- * Update RCU priority boot kthread affinity for CPU-hotplug changes.
+ * Update kthreads affinity during CPU-hotplug changes.
+ *
+ * Set the per-rcu_node kthread's affinity to cover all CPUs that are
+ * served by the rcu_node in question.  The CPU hotplug lock is still
+ * held, so the value of rnp->qsmaskinit will be stable.
+ *
+ * We don't include outgoingcpu in the affinity set, use -1 if there is
+ * no outgoing CPU.  If there are no CPUs left in the affinity set,
+ * this function allows the kthread to execute on any CPU.
+ *
+ * Any future concurrent calls are serialized via ->kthread_mutex.
  */
-static void rcutree_affinity_setting(unsigned int cpu, int outgoing)
+static void rcutree_affinity_setting(unsigned int cpu, int outgoingcpu)
 {
-	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+	cpumask_var_t cm;
+	unsigned long mask;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
+	struct task_struct *task_boost, *task_exp;
+
+	rdp = per_cpu_ptr(&rcu_data, cpu);
+	rnp = rdp->mynode;
+
+	task_boost = rcu_boost_task(rnp);
+	task_exp = rcu_exp_par_gp_task(rnp);
 
-	rcu_boost_kthread_setaffinity(rdp->mynode, outgoing);
+	/*
+	 * If CPU is the boot one, those tasks are created later from early
+	 * initcall since kthreadd must be created first.
+	 */
+	if (!task_boost && !task_exp)
+		return;
+
+	if (!zalloc_cpumask_var(&cm, GFP_KERNEL))
+		return;
+
+	mutex_lock(&rnp->kthread_mutex);
+	mask = rcu_rnp_online_cpus(rnp);
+	for_each_leaf_node_possible_cpu(rnp, cpu)
+		if ((mask & leaf_node_cpu_bit(rnp, cpu)) &&
+		    cpu != outgoingcpu)
+			cpumask_set_cpu(cpu, cm);
+	cpumask_and(cm, cm, housekeeping_cpumask(HK_TYPE_RCU));
+	if (cpumask_empty(cm)) {
+		cpumask_copy(cm, housekeeping_cpumask(HK_TYPE_RCU));
+		if (outgoingcpu >= 0)
+			cpumask_clear_cpu(outgoingcpu, cm);
+	}
+
+	if (task_exp)
+		set_cpus_allowed_ptr(task_exp, cm);
+
+	if (task_boost)
+		set_cpus_allowed_ptr(task_boost, cm);
+
+	mutex_unlock(&rnp->kthread_mutex);
+
+	free_cpumask_var(cm);
 }
 
 /*
@@ -4608,8 +4760,9 @@ void rcutree_migrate_callbacks(int cpu)
 		__call_rcu_nocb_wake(my_rdp, true, flags);
 	} else {
 		rcu_nocb_unlock(my_rdp); /* irqs remain disabled. */
-		raw_spin_unlock_irqrestore_rcu_node(my_rnp, flags);
+		raw_spin_unlock_rcu_node(my_rnp); /* irqs remain disabled. */
 	}
+	local_irq_restore(flags);
 	if (needwake)
 		rcu_gp_kthread_wake();
 	lockdep_assert_irqs_enabled();
@@ -4698,51 +4851,6 @@ static int rcu_pm_notify(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
-#ifdef CONFIG_RCU_EXP_KTHREAD
-struct kthread_worker *rcu_exp_gp_kworker;
-struct kthread_worker *rcu_exp_par_gp_kworker;
-
-static void __init rcu_start_exp_gp_kworkers(void)
-{
-	const char *par_gp_kworker_name = "rcu_exp_par_gp_kthread_worker";
-	const char *gp_kworker_name = "rcu_exp_gp_kthread_worker";
-	struct sched_param param = { .sched_priority = kthread_prio };
-
-	rcu_exp_gp_kworker = kthread_create_worker(0, gp_kworker_name);
-	if (IS_ERR_OR_NULL(rcu_exp_gp_kworker)) {
-		pr_err("Failed to create %s!\n", gp_kworker_name);
-		return;
-	}
-
-	rcu_exp_par_gp_kworker = kthread_create_worker(0, par_gp_kworker_name);
-	if (IS_ERR_OR_NULL(rcu_exp_par_gp_kworker)) {
-		pr_err("Failed to create %s!\n", par_gp_kworker_name);
-		kthread_destroy_worker(rcu_exp_gp_kworker);
-		return;
-	}
-
-	sched_setscheduler_nocheck(rcu_exp_gp_kworker->task, SCHED_FIFO, &param);
-	sched_setscheduler_nocheck(rcu_exp_par_gp_kworker->task, SCHED_FIFO,
-				   &param);
-}
-
-static inline void rcu_alloc_par_gp_wq(void)
-{
-}
-#else /* !CONFIG_RCU_EXP_KTHREAD */
-struct workqueue_struct *rcu_par_gp_wq;
-
-static void __init rcu_start_exp_gp_kworkers(void)
-{
-}
-
-static inline void rcu_alloc_par_gp_wq(void)
-{
-	rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0);
-	WARN_ON(!rcu_par_gp_wq);
-}
-#endif /* CONFIG_RCU_EXP_KTHREAD */
-
 /*
  * Spawn the kthreads that handle RCU's grace periods.
  */
@@ -4777,10 +4885,10 @@ static int __init rcu_spawn_gp_kthread(void)
 	 * due to rcu_scheduler_fully_active.
 	 */
 	rcu_spawn_cpu_nocb_kthread(smp_processor_id());
-	rcu_spawn_one_boost_kthread(rdp->mynode);
+	rcu_spawn_rnp_kthreads(rdp->mynode);
 	rcu_spawn_core_kthreads();
 	/* Create kthread worker for expedited GPs */
-	rcu_start_exp_gp_kworkers();
+	rcu_start_exp_gp_kworker();
 	return 0;
 }
 early_initcall(rcu_spawn_gp_kthread);
@@ -4883,7 +4991,7 @@ static void __init rcu_init_one(void)
 			init_waitqueue_head(&rnp->exp_wq[2]);
 			init_waitqueue_head(&rnp->exp_wq[3]);
 			spin_lock_init(&rnp->exp_lock);
-			mutex_init(&rnp->boost_kthread_mutex);
+			mutex_init(&rnp->kthread_mutex);
 			raw_spin_lock_init(&rnp->exp_poll_lock);
 			rnp->exp_seq_poll_rq = RCU_GET_STATE_COMPLETED;
 			INIT_WORK(&rnp->exp_poll_wq, sync_rcu_do_polled_gp);
@@ -5120,7 +5228,6 @@ void __init rcu_init(void)
 	/* Create workqueue for Tree SRCU and for expedited GPs. */
 	rcu_gp_wq = alloc_workqueue("rcu_gp", WQ_MEM_RECLAIM, 0);
 	WARN_ON(!rcu_gp_wq);
-	rcu_alloc_par_gp_wq();
 
 	/* Fill in default value for rcutree.qovld boot parameter. */
 	/* -After- the rcu_node ->lock fields are initialized! */
@@ -5133,6 +5240,8 @@ void __init rcu_init(void)
 	(void)start_poll_synchronize_rcu_expedited();
 
 	rcu_test_sync_prims();
+
+	tasks_cblist_init_generic();
 }
 
 #include "tree_stall.h"
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index e9821a8422db..df48160b3136 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -21,14 +21,10 @@
 
 #include "rcu_segcblist.h"
 
-/* Communicate arguments to a workqueue handler. */
+/* Communicate arguments to a kthread worker handler. */
 struct rcu_exp_work {
 	unsigned long rew_s;
-#ifdef CONFIG_RCU_EXP_KTHREAD
 	struct kthread_work rew_work;
-#else
-	struct work_struct rew_work;
-#endif /* CONFIG_RCU_EXP_KTHREAD */
 };
 
 /* RCU's kthread states for tracing. */
@@ -72,6 +68,9 @@ struct rcu_node {
 				/* Online CPUs for next expedited GP. */
 				/*  Any CPU that has ever been online will */
 				/*  have its bit set. */
+	struct kthread_worker *exp_kworker;
+				/* Workers performing per node expedited GP */
+				/* initialization. */
 	unsigned long cbovldmask;
 				/* CPUs experiencing callback overload. */
 	unsigned long ffmask;	/* Fully functional CPUs. */
@@ -113,7 +112,7 @@ struct rcu_node {
 				/*  side effect, not as a lock. */
 	unsigned long boost_time;
 				/* When to start boosting (jiffies). */
-	struct mutex boost_kthread_mutex;
+	struct mutex kthread_mutex;
 				/* Exclusion for thread spawning and affinity */
 				/*  manipulation. */
 	struct task_struct *boost_kthread_task;
@@ -467,11 +466,10 @@ static void rcu_init_one_nocb(struct rcu_node *rnp);
 static bool wake_nocb_gp(struct rcu_data *rdp, bool force);
 static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 				  unsigned long j, bool lazy);
-static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
-				bool *was_alldone, unsigned long flags,
-				bool lazy);
-static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_empty,
-				 unsigned long flags);
+static void call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *head,
+			  rcu_callback_t func, unsigned long flags, bool lazy);
+static void __maybe_unused __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_empty,
+						unsigned long flags);
 static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp, int level);
 static bool do_nocb_deferred_wakeup(struct rcu_data *rdp);
 static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 6d7cea5d591f..6b83537480b1 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -173,7 +173,6 @@ static bool sync_rcu_exp_done_unlocked(struct rcu_node *rnp)
 	return ret;
 }
 
-
 /*
  * Report the exit from RCU read-side critical section for the last task
  * that queued itself during or before the current expedited preemptible-RCU
@@ -199,10 +198,9 @@ static void __rcu_report_exp_rnp(struct rcu_node *rnp,
 		}
 		if (rnp->parent == NULL) {
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-			if (wake) {
-				smp_mb(); /* EGP done before wake_up(). */
-				swake_up_one(&rcu_state.expedited_wq);
-			}
+			if (wake)
+				swake_up_one_online(&rcu_state.expedited_wq);
+
 			break;
 		}
 		mask = rnp->grpmask;
@@ -420,7 +418,6 @@ retry_ipi:
 
 static void rcu_exp_sel_wait_wake(unsigned long s);
 
-#ifdef CONFIG_RCU_EXP_KTHREAD
 static void sync_rcu_exp_select_node_cpus(struct kthread_work *wp)
 {
 	struct rcu_exp_work *rewp =
@@ -429,9 +426,14 @@ static void sync_rcu_exp_select_node_cpus(struct kthread_work *wp)
 	__sync_rcu_exp_select_node_cpus(rewp);
 }
 
-static inline bool rcu_gp_par_worker_started(void)
+static inline bool rcu_exp_worker_started(void)
+{
+	return !!READ_ONCE(rcu_exp_gp_kworker);
+}
+
+static inline bool rcu_exp_par_worker_started(struct rcu_node *rnp)
 {
-	return !!READ_ONCE(rcu_exp_par_gp_kworker);
+	return !!READ_ONCE(rnp->exp_kworker);
 }
 
 static inline void sync_rcu_exp_select_cpus_queue_work(struct rcu_node *rnp)
@@ -442,7 +444,7 @@ static inline void sync_rcu_exp_select_cpus_queue_work(struct rcu_node *rnp)
 	 * another work item on the same kthread worker can result in
 	 * deadlock.
 	 */
-	kthread_queue_work(rcu_exp_par_gp_kworker, &rnp->rew.rew_work);
+	kthread_queue_work(READ_ONCE(rnp->exp_kworker), &rnp->rew.rew_work);
 }
 
 static inline void sync_rcu_exp_select_cpus_flush_work(struct rcu_node *rnp)
@@ -467,64 +469,6 @@ static inline void synchronize_rcu_expedited_queue_work(struct rcu_exp_work *rew
 	kthread_queue_work(rcu_exp_gp_kworker, &rew->rew_work);
 }
 
-static inline void synchronize_rcu_expedited_destroy_work(struct rcu_exp_work *rew)
-{
-}
-#else /* !CONFIG_RCU_EXP_KTHREAD */
-static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
-{
-	struct rcu_exp_work *rewp =
-		container_of(wp, struct rcu_exp_work, rew_work);
-
-	__sync_rcu_exp_select_node_cpus(rewp);
-}
-
-static inline bool rcu_gp_par_worker_started(void)
-{
-	return !!READ_ONCE(rcu_par_gp_wq);
-}
-
-static inline void sync_rcu_exp_select_cpus_queue_work(struct rcu_node *rnp)
-{
-	int cpu = find_next_bit(&rnp->ffmask, BITS_PER_LONG, -1);
-
-	INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
-	/* If all offline, queue the work on an unbound CPU. */
-	if (unlikely(cpu > rnp->grphi - rnp->grplo))
-		cpu = WORK_CPU_UNBOUND;
-	else
-		cpu += rnp->grplo;
-	queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work);
-}
-
-static inline void sync_rcu_exp_select_cpus_flush_work(struct rcu_node *rnp)
-{
-	flush_work(&rnp->rew.rew_work);
-}
-
-/*
- * Work-queue handler to drive an expedited grace period forward.
- */
-static void wait_rcu_exp_gp(struct work_struct *wp)
-{
-	struct rcu_exp_work *rewp;
-
-	rewp = container_of(wp, struct rcu_exp_work, rew_work);
-	rcu_exp_sel_wait_wake(rewp->rew_s);
-}
-
-static inline void synchronize_rcu_expedited_queue_work(struct rcu_exp_work *rew)
-{
-	INIT_WORK_ONSTACK(&rew->rew_work, wait_rcu_exp_gp);
-	queue_work(rcu_gp_wq, &rew->rew_work);
-}
-
-static inline void synchronize_rcu_expedited_destroy_work(struct rcu_exp_work *rew)
-{
-	destroy_work_on_stack(&rew->rew_work);
-}
-#endif /* CONFIG_RCU_EXP_KTHREAD */
-
 /*
  * Select the nodes that the upcoming expedited grace period needs
  * to wait for.
@@ -542,7 +486,7 @@ static void sync_rcu_exp_select_cpus(void)
 		rnp->exp_need_flush = false;
 		if (!READ_ONCE(rnp->expmask))
 			continue; /* Avoid early boot non-existent wq. */
-		if (!rcu_gp_par_worker_started() ||
+		if (!rcu_exp_par_worker_started(rnp) ||
 		    rcu_scheduler_active != RCU_SCHEDULER_RUNNING ||
 		    rcu_is_last_leaf_node(rnp)) {
 			/* No worker started yet or last leaf, do direct call. */
@@ -957,7 +901,6 @@ static void rcu_exp_print_detail_task_stall_rnp(struct rcu_node *rnp)
  */
 void synchronize_rcu_expedited(void)
 {
-	bool boottime = (rcu_scheduler_active == RCU_SCHEDULER_INIT);
 	unsigned long flags;
 	struct rcu_exp_work rew;
 	struct rcu_node *rnp;
@@ -997,7 +940,7 @@ void synchronize_rcu_expedited(void)
 		return;  /* Someone else did our work for us. */
 
 	/* Ensure that load happens before action based on it. */
-	if (unlikely(boottime)) {
+	if (unlikely((rcu_scheduler_active == RCU_SCHEDULER_INIT) || !rcu_exp_worker_started())) {
 		/* Direct call during scheduler init and early_initcalls(). */
 		rcu_exp_sel_wait_wake(s);
 	} else {
@@ -1014,9 +957,6 @@ void synchronize_rcu_expedited(void)
 
 	/* Let the next expedited grace period start. */
 	mutex_unlock(&rcu_state.exp_mutex);
-
-	if (likely(!boottime))
-		synchronize_rcu_expedited_destroy_work(&rew);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
 
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index 4efbf7333d4e..3f85577bddd4 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -256,6 +256,7 @@ static bool wake_nocb_gp(struct rcu_data *rdp, bool force)
 	return __wake_nocb_gp(rdp_gp, rdp, force, flags);
 }
 
+#ifdef CONFIG_RCU_LAZY
 /*
  * LAZY_FLUSH_JIFFIES decides the maximum amount of time that
  * can elapse before lazy callbacks are flushed. Lazy callbacks
@@ -264,21 +265,20 @@ static bool wake_nocb_gp(struct rcu_data *rdp, bool force)
  * left unsubmitted to RCU after those many jiffies.
  */
 #define LAZY_FLUSH_JIFFIES (10 * HZ)
-static unsigned long jiffies_till_flush = LAZY_FLUSH_JIFFIES;
+static unsigned long jiffies_lazy_flush = LAZY_FLUSH_JIFFIES;
 
-#ifdef CONFIG_RCU_LAZY
 // To be called only from test code.
-void rcu_lazy_set_jiffies_till_flush(unsigned long jif)
+void rcu_set_jiffies_lazy_flush(unsigned long jif)
 {
-	jiffies_till_flush = jif;
+	jiffies_lazy_flush = jif;
 }
-EXPORT_SYMBOL(rcu_lazy_set_jiffies_till_flush);
+EXPORT_SYMBOL(rcu_set_jiffies_lazy_flush);
 
-unsigned long rcu_lazy_get_jiffies_till_flush(void)
+unsigned long rcu_get_jiffies_lazy_flush(void)
 {
-	return jiffies_till_flush;
+	return jiffies_lazy_flush;
 }
-EXPORT_SYMBOL(rcu_lazy_get_jiffies_till_flush);
+EXPORT_SYMBOL(rcu_get_jiffies_lazy_flush);
 #endif
 
 /*
@@ -299,7 +299,7 @@ static void wake_nocb_gp_defer(struct rcu_data *rdp, int waketype,
 	 */
 	if (waketype == RCU_NOCB_WAKE_LAZY &&
 	    rdp->nocb_defer_wakeup == RCU_NOCB_WAKE_NOT) {
-		mod_timer(&rdp_gp->nocb_timer, jiffies + jiffies_till_flush);
+		mod_timer(&rdp_gp->nocb_timer, jiffies + rcu_get_jiffies_lazy_flush());
 		WRITE_ONCE(rdp_gp->nocb_defer_wakeup, waketype);
 	} else if (waketype == RCU_NOCB_WAKE_BYPASS) {
 		mod_timer(&rdp_gp->nocb_timer, jiffies + 2);
@@ -482,7 +482,7 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 	// flush ->nocb_bypass to ->cblist.
 	if ((ncbs && !bypass_is_lazy && j != READ_ONCE(rdp->nocb_bypass_first)) ||
 	    (ncbs &&  bypass_is_lazy &&
-	     (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + jiffies_till_flush))) ||
+	     (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + rcu_get_jiffies_lazy_flush()))) ||
 	    ncbs >= qhimark) {
 		rcu_nocb_lock(rdp);
 		*was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist);
@@ -532,9 +532,7 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 	// 2. Both of these conditions are met:
 	//    a. The bypass list previously had only lazy CBs, and:
 	//    b. The new CB is non-lazy.
-	if (ncbs && (!bypass_is_lazy || lazy)) {
-		local_irq_restore(flags);
-	} else {
+	if (!ncbs || (bypass_is_lazy && !lazy)) {
 		// No-CBs GP kthread might be indefinitely asleep, if so, wake.
 		rcu_nocb_lock(rdp); // Rare during call_rcu() flood.
 		if (!rcu_segcblist_pend_cbs(&rdp->cblist)) {
@@ -544,7 +542,7 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 		} else {
 			trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
 					    TPS("FirstBQnoWake"));
-			rcu_nocb_unlock_irqrestore(rdp, flags);
+			rcu_nocb_unlock(rdp);
 		}
 	}
 	return true; // Callback already enqueued.
@@ -566,11 +564,12 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
 	long lazy_len;
 	long len;
 	struct task_struct *t;
+	struct rcu_data *rdp_gp = rdp->nocb_gp_rdp;
 
 	// If we are being polled or there is no kthread, just leave.
 	t = READ_ONCE(rdp->nocb_gp_kthread);
 	if (rcu_nocb_poll || !t) {
-		rcu_nocb_unlock_irqrestore(rdp, flags);
+		rcu_nocb_unlock(rdp);
 		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
 				    TPS("WakeNotPoll"));
 		return;
@@ -583,17 +582,17 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
 		rdp->qlen_last_fqs_check = len;
 		// Only lazy CBs in bypass list
 		if (lazy_len && bypass_len == lazy_len) {
-			rcu_nocb_unlock_irqrestore(rdp, flags);
+			rcu_nocb_unlock(rdp);
 			wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE_LAZY,
 					   TPS("WakeLazy"));
 		} else if (!irqs_disabled_flags(flags)) {
 			/* ... if queue was empty ... */
-			rcu_nocb_unlock_irqrestore(rdp, flags);
+			rcu_nocb_unlock(rdp);
 			wake_nocb_gp(rdp, false);
 			trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
 					    TPS("WakeEmpty"));
 		} else {
-			rcu_nocb_unlock_irqrestore(rdp, flags);
+			rcu_nocb_unlock(rdp);
 			wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE,
 					   TPS("WakeEmptyIsDeferred"));
 		}
@@ -610,20 +609,32 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
 		smp_mb(); /* Enqueue before timer_pending(). */
 		if ((rdp->nocb_cb_sleep ||
 		     !rcu_segcblist_ready_cbs(&rdp->cblist)) &&
-		    !timer_pending(&rdp->nocb_timer)) {
-			rcu_nocb_unlock_irqrestore(rdp, flags);
+		    !timer_pending(&rdp_gp->nocb_timer)) {
+			rcu_nocb_unlock(rdp);
 			wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE_FORCE,
 					   TPS("WakeOvfIsDeferred"));
 		} else {
-			rcu_nocb_unlock_irqrestore(rdp, flags);
+			rcu_nocb_unlock(rdp);
 			trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNot"));
 		}
 	} else {
-		rcu_nocb_unlock_irqrestore(rdp, flags);
+		rcu_nocb_unlock(rdp);
 		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNot"));
 	}
 }
 
+static void call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *head,
+			  rcu_callback_t func, unsigned long flags, bool lazy)
+{
+	bool was_alldone;
+
+	if (!rcu_nocb_try_bypass(rdp, head, &was_alldone, flags, lazy)) {
+		/* Not enqueued on bypass but locked, do regular enqueue */
+		rcutree_enqueue(rdp, head, func);
+		__call_rcu_nocb_wake(rdp, was_alldone, flags); /* unlocks */
+	}
+}
+
 static int nocb_gp_toggle_rdp(struct rcu_data *rdp,
 			       bool *wake_state)
 {
@@ -723,7 +734,7 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 		lazy_ncbs = READ_ONCE(rdp->lazy_len);
 
 		if (bypass_ncbs && (lazy_ncbs == bypass_ncbs) &&
-		    (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + jiffies_till_flush) ||
+		    (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + rcu_get_jiffies_lazy_flush()) ||
 		     bypass_ncbs > 2 * qhimark)) {
 			flush_bypass = true;
 		} else if (bypass_ncbs && (lazy_ncbs != bypass_ncbs) &&
@@ -779,7 +790,6 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 		if (rcu_segcblist_ready_cbs(&rdp->cblist)) {
 			needwake = rdp->nocb_cb_sleep;
 			WRITE_ONCE(rdp->nocb_cb_sleep, false);
-			smp_mb(); /* CB invocation -after- GP end. */
 		} else {
 			needwake = false;
 		}
@@ -933,8 +943,7 @@ static void nocb_cb_wait(struct rcu_data *rdp)
 		swait_event_interruptible_exclusive(rdp->nocb_cb_wq,
 						    nocb_cb_wait_cond(rdp));
 
-		// VVV Ensure CB invocation follows _sleep test.
-		if (smp_load_acquire(&rdp->nocb_cb_sleep)) { // ^^^
+		if (READ_ONCE(rdp->nocb_cb_sleep)) {
 			WARN_ON(signal_pending(current));
 			trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WokeEmpty"));
 		}
@@ -1383,7 +1392,7 @@ lazy_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 			rcu_nocb_unlock_irqrestore(rdp, flags);
 			continue;
 		}
-		WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies, false));
+		rcu_nocb_try_flush_bypass(rdp, jiffies);
 		rcu_nocb_unlock_irqrestore(rdp, flags);
 		wake_nocb_gp(rdp, false);
 		sc->nr_to_scan -= _count;
@@ -1768,10 +1777,10 @@ static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 	return true;
 }
 
-static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
-				bool *was_alldone, unsigned long flags, bool lazy)
+static void call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *head,
+			  rcu_callback_t func, unsigned long flags, bool lazy)
 {
-	return false;
+	WARN_ON_ONCE(1);  /* Should be dead code! */
 }
 
 static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_empty,
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 41021080ad25..36a8b5dbf5b5 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1195,14 +1195,13 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
 	struct sched_param sp;
 	struct task_struct *t;
 
-	mutex_lock(&rnp->boost_kthread_mutex);
-	if (rnp->boost_kthread_task || !rcu_scheduler_fully_active)
-		goto out;
+	if (rnp->boost_kthread_task)
+		return;
 
 	t = kthread_create(rcu_boost_kthread, (void *)rnp,
 			   "rcub/%d", rnp_index);
 	if (WARN_ON_ONCE(IS_ERR(t)))
-		goto out;
+		return;
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	rnp->boost_kthread_task = t;
@@ -1210,48 +1209,11 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
 	sp.sched_priority = kthread_prio;
 	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
 	wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
-
- out:
-	mutex_unlock(&rnp->boost_kthread_mutex);
 }
 
-/*
- * Set the per-rcu_node kthread's affinity to cover all CPUs that are
- * served by the rcu_node in question.  The CPU hotplug lock is still
- * held, so the value of rnp->qsmaskinit will be stable.
- *
- * We don't include outgoingcpu in the affinity set, use -1 if there is
- * no outgoing CPU.  If there are no CPUs left in the affinity set,
- * this function allows the kthread to execute on any CPU.
- *
- * Any future concurrent calls are serialized via ->boost_kthread_mutex.
- */
-static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
+static struct task_struct *rcu_boost_task(struct rcu_node *rnp)
 {
-	struct task_struct *t = rnp->boost_kthread_task;
-	unsigned long mask;
-	cpumask_var_t cm;
-	int cpu;
-
-	if (!t)
-		return;
-	if (!zalloc_cpumask_var(&cm, GFP_KERNEL))
-		return;
-	mutex_lock(&rnp->boost_kthread_mutex);
-	mask = rcu_rnp_online_cpus(rnp);
-	for_each_leaf_node_possible_cpu(rnp, cpu)
-		if ((mask & leaf_node_cpu_bit(rnp, cpu)) &&
-		    cpu != outgoingcpu)
-			cpumask_set_cpu(cpu, cm);
-	cpumask_and(cm, cm, housekeeping_cpumask(HK_TYPE_RCU));
-	if (cpumask_empty(cm)) {
-		cpumask_copy(cm, housekeeping_cpumask(HK_TYPE_RCU));
-		if (outgoingcpu >= 0)
-			cpumask_clear_cpu(outgoingcpu, cm);
-	}
-	set_cpus_allowed_ptr(t, cm);
-	mutex_unlock(&rnp->boost_kthread_mutex);
-	free_cpumask_var(cm);
+	return READ_ONCE(rnp->boost_kthread_task);
 }
 
 #else /* #ifdef CONFIG_RCU_BOOST */
@@ -1270,10 +1232,10 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
 {
 }
 
-static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
+static struct task_struct *rcu_boost_task(struct rcu_node *rnp)
 {
+	return NULL;
 }
-
 #endif /* #else #ifdef CONFIG_RCU_BOOST */
 
 /*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9116bcc90346..540f229700b6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3955,6 +3955,17 @@ void wake_up_if_idle(int cpu)
 	}
 }
 
+bool cpus_equal_capacity(int this_cpu, int that_cpu)
+{
+	if (!sched_asym_cpucap_active())
+		return true;
+
+	if (this_cpu == that_cpu)
+		return true;
+
+	return arch_scale_cpu_capacity(this_cpu) == arch_scale_cpu_capacity(that_cpu);
+}
+
 bool cpus_share_cache(int this_cpu, int that_cpu)
 {
 	if (this_cpu == that_cpu)
@@ -6787,10 +6798,12 @@ static inline void sched_submit_work(struct task_struct *tsk)
 
 static void sched_update_worker(struct task_struct *tsk)
 {
-	if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
+	if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER | PF_BLOCK_TS)) {
+		if (tsk->flags & PF_BLOCK_TS)
+			blk_plug_invalidate_ts(tsk);
 		if (tsk->flags & PF_WQ_WORKER)
 			wq_worker_running(tsk);
-		else
+		else if (tsk->flags & PF_IO_WORKER)
 			io_wq_worker_running(tsk);
 	}
 }
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 95c3c097083e..eece6244f9d2 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -133,7 +133,11 @@ unsigned long get_capacity_ref_freq(struct cpufreq_policy *policy)
 	if (arch_scale_freq_invariant())
 		return policy->cpuinfo.max_freq;
 
-	return policy->cur;
+	/*
+	 * Apply a 25% margin so that we select a higher frequency than
+	 * the current one before the CPU is fully busy:
+	 */
+	return policy->cur + (policy->cur >> 2);
 }
 
 /**
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index 2ad881d07752..4e715b9b278e 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -162,6 +162,9 @@
 	| MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK			\
 	| MEMBARRIER_CMD_GET_REGISTRATIONS)
 
+static DEFINE_MUTEX(membarrier_ipi_mutex);
+#define SERIALIZE_IPI() guard(mutex)(&membarrier_ipi_mutex)
+
 static void ipi_mb(void *info)
 {
 	smp_mb();	/* IPIs should be serializing but paranoid. */
@@ -259,6 +262,7 @@ static int membarrier_global_expedited(void)
 	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
 		return -ENOMEM;
 
+	SERIALIZE_IPI();
 	cpus_read_lock();
 	rcu_read_lock();
 	for_each_online_cpu(cpu) {
@@ -347,6 +351,7 @@ static int membarrier_private_expedited(int flags, int cpu_id)
 	if (cpu_id < 0 && !zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
 		return -ENOMEM;
 
+	SERIALIZE_IPI();
 	cpus_read_lock();
 
 	if (cpu_id >= 0) {
@@ -460,6 +465,7 @@ static int sync_runqueues_membarrier_state(struct mm_struct *mm)
 	 * between threads which are users of @mm has its membarrier state
 	 * updated.
 	 */
+	SERIALIZE_IPI();
 	cpus_read_lock();
 	rcu_read_lock();
 	for_each_online_cpu(cpu) {
diff --git a/kernel/signal.c b/kernel/signal.c
index c9c57d053ce4..bdca529f0f7b 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -47,6 +47,7 @@
 #include <linux/cgroup.h>
 #include <linux/audit.h>
 #include <linux/sysctl.h>
+#include <uapi/linux/pidfd.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/signal.h>
@@ -1436,7 +1437,8 @@ void lockdep_assert_task_sighand_held(struct task_struct *task)
 #endif
 
 /*
- * send signal info to all the members of a group
+ * send signal info to all the members of a thread group or to the
+ * individual thread if type == PIDTYPE_PID.
  */
 int group_send_sig_info(int sig, struct kernel_siginfo *info,
 			struct task_struct *p, enum pid_type type)
@@ -1478,7 +1480,8 @@ int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp)
 	return ret;
 }
 
-int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid)
+static int kill_pid_info_type(int sig, struct kernel_siginfo *info,
+				struct pid *pid, enum pid_type type)
 {
 	int error = -ESRCH;
 	struct task_struct *p;
@@ -1487,11 +1490,10 @@ int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid)
 		rcu_read_lock();
 		p = pid_task(pid, PIDTYPE_PID);
 		if (p)
-			error = group_send_sig_info(sig, info, p, PIDTYPE_TGID);
+			error = group_send_sig_info(sig, info, p, type);
 		rcu_read_unlock();
 		if (likely(!p || error != -ESRCH))
 			return error;
-
 		/*
 		 * The task was unhashed in between, try again.  If it
 		 * is dead, pid_task() will return NULL, if we race with
@@ -1500,6 +1502,11 @@ int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid)
 	}
 }
 
+int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid)
+{
+	return kill_pid_info_type(sig, info, pid, PIDTYPE_TGID);
+}
+
 static int kill_proc_info(int sig, struct kernel_siginfo *info, pid_t pid)
 {
 	int error;
@@ -1898,16 +1905,19 @@ int send_sig_fault_trapno(int sig, int code, void __user *addr, int trapno,
 	return send_sig_info(info.si_signo, &info, t);
 }
 
-int kill_pgrp(struct pid *pid, int sig, int priv)
+static int kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp)
 {
 	int ret;
-
 	read_lock(&tasklist_lock);
-	ret = __kill_pgrp_info(sig, __si_special(priv), pid);
+	ret = __kill_pgrp_info(sig, info, pgrp);
 	read_unlock(&tasklist_lock);
-
 	return ret;
 }
+
+int kill_pgrp(struct pid *pid, int sig, int priv)
+{
+	return kill_pgrp_info(sig, __si_special(priv), pid);
+}
 EXPORT_SYMBOL(kill_pgrp);
 
 int kill_pid(struct pid *pid, int sig, int priv)
@@ -2019,13 +2029,14 @@ ret:
 	return ret;
 }
 
-static void do_notify_pidfd(struct task_struct *task)
+void do_notify_pidfd(struct task_struct *task)
 {
-	struct pid *pid;
+	struct pid *pid = task_pid(task);
 
 	WARN_ON(task->exit_state == 0);
-	pid = task_pid(task);
-	wake_up_all(&pid->wait_pidfd);
+
+	__wake_up(&pid->wait_pidfd, TASK_NORMAL, 0,
+			poll_to_key(EPOLLIN | EPOLLRDNORM));
 }
 
 /*
@@ -2050,9 +2061,12 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
 
 	WARN_ON_ONCE(!tsk->ptrace &&
 	       (tsk->group_leader != tsk || !thread_group_empty(tsk)));
-
-	/* Wake up all pidfd waiters */
-	do_notify_pidfd(tsk);
+	/*
+	 * tsk is a group leader and has no threads, wake up the
+	 * non-PIDFD_THREAD waiters.
+	 */
+	if (thread_group_empty(tsk))
+		do_notify_pidfd(tsk);
 
 	if (sig != SIGCHLD) {
 		/*
@@ -3789,12 +3803,13 @@ COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait_time32, compat_sigset_t __user *, uthese,
 #endif
 #endif
 
-static inline void prepare_kill_siginfo(int sig, struct kernel_siginfo *info)
+static void prepare_kill_siginfo(int sig, struct kernel_siginfo *info,
+				 enum pid_type type)
 {
 	clear_siginfo(info);
 	info->si_signo = sig;
 	info->si_errno = 0;
-	info->si_code = SI_USER;
+	info->si_code = (type == PIDTYPE_PID) ? SI_TKILL : SI_USER;
 	info->si_pid = task_tgid_vnr(current);
 	info->si_uid = from_kuid_munged(current_user_ns(), current_uid());
 }
@@ -3808,7 +3823,7 @@ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig)
 {
 	struct kernel_siginfo info;
 
-	prepare_kill_siginfo(sig, &info);
+	prepare_kill_siginfo(sig, &info, PIDTYPE_TGID);
 
 	return kill_something_info(sig, &info, pid);
 }
@@ -3861,6 +3876,10 @@ static struct pid *pidfd_to_pid(const struct file *file)
 	return tgid_pidfd_to_pid(file);
 }
 
+#define PIDFD_SEND_SIGNAL_FLAGS                            \
+	(PIDFD_SIGNAL_THREAD | PIDFD_SIGNAL_THREAD_GROUP | \
+	 PIDFD_SIGNAL_PROCESS_GROUP)
+
 /**
  * sys_pidfd_send_signal - Signal a process through a pidfd
  * @pidfd:  file descriptor of the process
@@ -3868,14 +3887,10 @@ static struct pid *pidfd_to_pid(const struct file *file)
  * @info:   signal info
  * @flags:  future flags
  *
- * The syscall currently only signals via PIDTYPE_PID which covers
- * kill(<positive-pid>, <signal>. It does not signal threads or process
- * groups.
- * In order to extend the syscall to threads and process groups the @flags
- * argument should be used. In essence, the @flags argument will determine
- * what is signaled and not the file descriptor itself. Put in other words,
- * grouping is a property of the flags argument not a property of the file
- * descriptor.
+ * Send the signal to the thread group or to the individual thread depending
+ * on PIDFD_THREAD.
+ * In the future extension to @flags may be used to override the default scope
+ * of @pidfd.
  *
  * Return: 0 on success, negative errno on failure
  */
@@ -3886,9 +3901,14 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
 	struct fd f;
 	struct pid *pid;
 	kernel_siginfo_t kinfo;
+	enum pid_type type;
 
 	/* Enforce flags be set to 0 until we add an extension. */
-	if (flags)
+	if (flags & ~PIDFD_SEND_SIGNAL_FLAGS)
+		return -EINVAL;
+
+	/* Ensure that only a single signal scope determining flag is set. */
+	if (hweight32(flags & PIDFD_SEND_SIGNAL_FLAGS) > 1)
 		return -EINVAL;
 
 	f = fdget(pidfd);
@@ -3906,6 +3926,25 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
 	if (!access_pidfd_pidns(pid))
 		goto err;
 
+	switch (flags) {
+	case 0:
+		/* Infer scope from the type of pidfd. */
+		if (f.file->f_flags & PIDFD_THREAD)
+			type = PIDTYPE_PID;
+		else
+			type = PIDTYPE_TGID;
+		break;
+	case PIDFD_SIGNAL_THREAD:
+		type = PIDTYPE_PID;
+		break;
+	case PIDFD_SIGNAL_THREAD_GROUP:
+		type = PIDTYPE_TGID;
+		break;
+	case PIDFD_SIGNAL_PROCESS_GROUP:
+		type = PIDTYPE_PGID;
+		break;
+	}
+
 	if (info) {
 		ret = copy_siginfo_from_user_any(&kinfo, info);
 		if (unlikely(ret))
@@ -3917,15 +3956,17 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
 
 		/* Only allow sending arbitrary signals to yourself. */
 		ret = -EPERM;
-		if ((task_pid(current) != pid) &&
+		if ((task_pid(current) != pid || type > PIDTYPE_TGID) &&
 		    (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL))
 			goto err;
 	} else {
-		prepare_kill_siginfo(sig, &kinfo);
+		prepare_kill_siginfo(sig, &kinfo, type);
 	}
 
-	ret = kill_pid_info(sig, &kinfo, pid);
-
+	if (type == PIDTYPE_PGID)
+		ret = kill_pgrp_info(sig, &kinfo, pid);
+	else
+		ret = kill_pid_info_type(sig, &kinfo, pid, type);
 err:
 	fdput(f);
 	return ret;
@@ -3965,12 +4006,7 @@ static int do_tkill(pid_t tgid, pid_t pid, int sig)
 {
 	struct kernel_siginfo info;
 
-	clear_siginfo(&info);
-	info.si_signo = sig;
-	info.si_errno = 0;
-	info.si_code = SI_TKILL;
-	info.si_pid = task_tgid_vnr(current);
-	info.si_uid = from_kuid_munged(current_user_ns(), current_uid());
+	prepare_kill_siginfo(sig, &info, PIDTYPE_PID);
 
 	return do_send_specific(tgid, pid, sig, &info);
 }
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 547d282548a8..b315b21fb28c 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -932,6 +932,8 @@ static void run_ksoftirqd(unsigned int cpu)
 #ifdef CONFIG_HOTPLUG_CPU
 static int takeover_tasklets(unsigned int cpu)
 {
+	workqueue_softirq_dead(cpu);
+
 	/* CPU is dead, so no lock needed. */
 	local_irq_disable();
 
diff --git a/kernel/sys.c b/kernel/sys.c
index e219fcfa112d..f8e543f1e38a 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1785,21 +1785,24 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
 	struct task_struct *t;
 	unsigned long flags;
 	u64 tgutime, tgstime, utime, stime;
-	unsigned long maxrss = 0;
+	unsigned long maxrss;
+	struct mm_struct *mm;
 	struct signal_struct *sig = p->signal;
+	unsigned int seq = 0;
 
-	memset((char *)r, 0, sizeof (*r));
+retry:
+	memset(r, 0, sizeof(*r));
 	utime = stime = 0;
+	maxrss = 0;
 
 	if (who == RUSAGE_THREAD) {
 		task_cputime_adjusted(current, &utime, &stime);
 		accumulate_thread_rusage(p, r);
 		maxrss = sig->maxrss;
-		goto out;
+		goto out_thread;
 	}
 
-	if (!lock_task_sighand(p, &flags))
-		return;
+	flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
 
 	switch (who) {
 	case RUSAGE_BOTH:
@@ -1819,9 +1822,6 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
 		fallthrough;
 
 	case RUSAGE_SELF:
-		thread_group_cputime_adjusted(p, &tgutime, &tgstime);
-		utime += tgutime;
-		stime += tgstime;
 		r->ru_nvcsw += sig->nvcsw;
 		r->ru_nivcsw += sig->nivcsw;
 		r->ru_minflt += sig->min_flt;
@@ -1830,28 +1830,42 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
 		r->ru_oublock += sig->oublock;
 		if (maxrss < sig->maxrss)
 			maxrss = sig->maxrss;
+
+		rcu_read_lock();
 		__for_each_thread(sig, t)
 			accumulate_thread_rusage(t, r);
+		rcu_read_unlock();
+
 		break;
 
 	default:
 		BUG();
 	}
-	unlock_task_sighand(p, &flags);
 
-out:
-	r->ru_utime = ns_to_kernel_old_timeval(utime);
-	r->ru_stime = ns_to_kernel_old_timeval(stime);
+	if (need_seqretry(&sig->stats_lock, seq)) {
+		seq = 1;
+		goto retry;
+	}
+	done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
 
-	if (who != RUSAGE_CHILDREN) {
-		struct mm_struct *mm = get_task_mm(p);
+	if (who == RUSAGE_CHILDREN)
+		goto out_children;
 
-		if (mm) {
-			setmax_mm_hiwater_rss(&maxrss, mm);
-			mmput(mm);
-		}
+	thread_group_cputime_adjusted(p, &tgutime, &tgstime);
+	utime += tgutime;
+	stime += tgstime;
+
+out_thread:
+	mm = get_task_mm(p);
+	if (mm) {
+		setmax_mm_hiwater_rss(&maxrss, mm);
+		mmput(mm);
 	}
+
+out_children:
 	r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */
+	r->ru_utime = ns_to_kernel_old_timeval(utime);
+	r->ru_stime = ns_to_kernel_old_timeval(stime);
 }
 
 SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru)
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index c108ed8a9804..3052b1f1168e 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -99,6 +99,7 @@ static u64 suspend_start;
  * Interval: 0.5sec.
  */
 #define WATCHDOG_INTERVAL (HZ >> 1)
+#define WATCHDOG_INTERVAL_MAX_NS ((2 * WATCHDOG_INTERVAL) * (NSEC_PER_SEC / HZ))
 
 /*
  * Threshold: 0.0312s, when doubled: 0.0625s.
@@ -134,6 +135,7 @@ static DECLARE_WORK(watchdog_work, clocksource_watchdog_work);
 static DEFINE_SPINLOCK(watchdog_lock);
 static int watchdog_running;
 static atomic_t watchdog_reset_pending;
+static int64_t watchdog_max_interval;
 
 static inline void clocksource_watchdog_lock(unsigned long *flags)
 {
@@ -399,8 +401,8 @@ static inline void clocksource_reset_watchdog(void)
 static void clocksource_watchdog(struct timer_list *unused)
 {
 	u64 csnow, wdnow, cslast, wdlast, delta;
+	int64_t wd_nsec, cs_nsec, interval;
 	int next_cpu, reset_pending;
-	int64_t wd_nsec, cs_nsec;
 	struct clocksource *cs;
 	enum wd_read_status read_ret;
 	unsigned long extra_wait = 0;
@@ -470,6 +472,27 @@ static void clocksource_watchdog(struct timer_list *unused)
 		if (atomic_read(&watchdog_reset_pending))
 			continue;
 
+		/*
+		 * The processing of timer softirqs can get delayed (usually
+		 * on account of ksoftirqd not getting to run in a timely
+		 * manner), which causes the watchdog interval to stretch.
+		 * Skew detection may fail for longer watchdog intervals
+		 * on account of fixed margins being used.
+		 * Some clocksources, e.g. acpi_pm, cannot tolerate
+		 * watchdog intervals longer than a few seconds.
+		 */
+		interval = max(cs_nsec, wd_nsec);
+		if (unlikely(interval > WATCHDOG_INTERVAL_MAX_NS)) {
+			if (system_state > SYSTEM_SCHEDULING &&
+			    interval > 2 * watchdog_max_interval) {
+				watchdog_max_interval = interval;
+				pr_warn("Long readout interval, skipping watchdog check: cs_nsec: %lld wd_nsec: %lld\n",
+					cs_nsec, wd_nsec);
+			}
+			watchdog_timer.expires = jiffies;
+			continue;
+		}
+
 		/* Check the deviation from the watchdog clocksource. */
 		md = cs->uncertainty_margin + watchdog->uncertainty_margin;
 		if (abs(cs_nsec - wd_nsec) > md) {
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 760793998cdd..edb0f821dcea 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1085,6 +1085,7 @@ static int enqueue_hrtimer(struct hrtimer *timer,
 			   enum hrtimer_mode mode)
 {
 	debug_activate(timer, mode);
+	WARN_ON_ONCE(!base->cpu_base->online);
 
 	base->cpu_base->active_bases |= 1 << base->index;
 
@@ -2183,6 +2184,7 @@ int hrtimers_prepare_cpu(unsigned int cpu)
 	cpu_base->softirq_next_timer = NULL;
 	cpu_base->expires_next = KTIME_MAX;
 	cpu_base->softirq_expires_next = KTIME_MAX;
+	cpu_base->online = 1;
 	hrtimer_cpu_base_init_expiry_lock(cpu_base);
 	return 0;
 }
@@ -2250,6 +2252,7 @@ int hrtimers_cpu_dying(unsigned int dying_cpu)
 	smp_call_function_single(ncpu, retrigger_next_event, NULL, 0);
 
 	raw_spin_unlock(&new_base->lock);
+	old_base->online = 0;
 	raw_spin_unlock(&old_base->lock);
 
 	return 0;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index a17d26002831..01fb50c1b17e 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1576,13 +1576,23 @@ void tick_setup_sched_timer(void)
 void tick_cancel_sched_timer(int cpu)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+	ktime_t idle_sleeptime, iowait_sleeptime;
+	unsigned long idle_calls, idle_sleeps;
 
 # ifdef CONFIG_HIGH_RES_TIMERS
 	if (ts->sched_timer.base)
 		hrtimer_cancel(&ts->sched_timer);
 # endif
 
+	idle_sleeptime = ts->idle_sleeptime;
+	iowait_sleeptime = ts->iowait_sleeptime;
+	idle_calls = ts->idle_calls;
+	idle_sleeps = ts->idle_sleeps;
 	memset(ts, 0, sizeof(*ts));
+	ts->idle_sleeptime = idle_sleeptime;
+	ts->iowait_sleeptime = iowait_sleeptime;
+	ts->idle_calls = idle_calls;
+	ts->idle_sleeps = idle_sleeps;
 }
 #endif
 
diff --git a/kernel/time/time_test.c b/kernel/time/time_test.c
index ca058c8af6ba..3e5d422dd15c 100644
--- a/kernel/time/time_test.c
+++ b/kernel/time/time_test.c
@@ -73,7 +73,7 @@ static void time64_to_tm_test_date_range(struct kunit *test)
 
 		days = div_s64(secs, 86400);
 
-		#define FAIL_MSG "%05ld/%02d/%02d (%2d) : %ld", \
+		#define FAIL_MSG "%05ld/%02d/%02d (%2d) : %lld", \
 			year, month, mdday, yday, days
 
 		KUNIT_ASSERT_EQ_MSG(test, year - 1900, result.tm_year, FAIL_MSG);
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 6cd2a4e3afb8..9ff018245840 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -189,9 +189,6 @@ static int fprobe_init_rethook(struct fprobe *fp, int num)
 {
 	int size;
 
-	if (num <= 0)
-		return -EINVAL;
-
 	if (!fp->exit_handler) {
 		fp->rethook = NULL;
 		return 0;
@@ -199,15 +196,16 @@ static int fprobe_init_rethook(struct fprobe *fp, int num)
 
 	/* Initialize rethook if needed */
 	if (fp->nr_maxactive)
-		size = fp->nr_maxactive;
+		num = fp->nr_maxactive;
 	else
-		size = num * num_possible_cpus() * 2;
-	if (size <= 0)
+		num *= num_possible_cpus() * 2;
+	if (num <= 0)
 		return -EINVAL;
 
+	size = sizeof(struct fprobe_rethook_node) + fp->entry_data_size;
+
 	/* Initialize rethook */
-	fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler,
-				sizeof(struct fprobe_rethook_node), size);
+	fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler, size, num);
 	if (IS_ERR(fp->rethook))
 		return PTR_ERR(fp->rethook);
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index b01ae7d36021..83ba342aef31 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5325,7 +5325,17 @@ static LIST_HEAD(ftrace_direct_funcs);
 
 static int register_ftrace_function_nolock(struct ftrace_ops *ops);
 
+/*
+ * If there are multiple ftrace_ops, use SAVE_REGS by default, so that direct
+ * call will be jumped from ftrace_regs_caller. Only if the architecture does
+ * not support ftrace_regs_caller but direct_call, use SAVE_ARGS so that it
+ * jumps from ftrace_caller for multiple ftrace_ops.
+ */
+#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_REGS
 #define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_ARGS)
+#else
+#define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS)
+#endif
 
 static int check_direct_multi(struct ftrace_ops *ops)
 {
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 9286f88fcd32..aa332ace108b 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -27,6 +27,7 @@
 #include <linux/cpu.h>
 #include <linux/oom.h>
 
+#include <asm/local64.h>
 #include <asm/local.h>
 
 /*
@@ -317,6 +318,11 @@ struct buffer_data_page {
 	unsigned char	 data[] RB_ALIGN_DATA;	/* data of buffer page */
 };
 
+struct buffer_data_read_page {
+	unsigned		order;	/* order of the page */
+	struct buffer_data_page	*data;	/* actual data, stored in this page */
+};
+
 /*
  * Note, the buffer_page list must be first. The buffer pages
  * are allocated in cache lines, which means that each buffer
@@ -331,6 +337,7 @@ struct buffer_page {
 	unsigned	 read;		/* index for next read */
 	local_t		 entries;	/* entries on this page */
 	unsigned long	 real_end;	/* real end of data */
+	unsigned	 order;		/* order of the page */
 	struct buffer_data_page *page;	/* Actual data page */
 };
 
@@ -361,7 +368,7 @@ static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage)
 
 static void free_buffer_page(struct buffer_page *bpage)
 {
-	free_page((unsigned long)bpage->page);
+	free_pages((unsigned long)bpage->page, bpage->order);
 	kfree(bpage);
 }
 
@@ -373,46 +380,10 @@ static inline bool test_time_stamp(u64 delta)
 	return !!(delta & TS_DELTA_TEST);
 }
 
-#define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE)
-
-/* Max payload is BUF_PAGE_SIZE - header (8bytes) */
-#define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2))
-
-int ring_buffer_print_page_header(struct trace_seq *s)
-{
-	struct buffer_data_page field;
-
-	trace_seq_printf(s, "\tfield: u64 timestamp;\t"
-			 "offset:0;\tsize:%u;\tsigned:%u;\n",
-			 (unsigned int)sizeof(field.time_stamp),
-			 (unsigned int)is_signed_type(u64));
-
-	trace_seq_printf(s, "\tfield: local_t commit;\t"
-			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
-			 (unsigned int)offsetof(typeof(field), commit),
-			 (unsigned int)sizeof(field.commit),
-			 (unsigned int)is_signed_type(long));
-
-	trace_seq_printf(s, "\tfield: int overwrite;\t"
-			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
-			 (unsigned int)offsetof(typeof(field), commit),
-			 1,
-			 (unsigned int)is_signed_type(long));
-
-	trace_seq_printf(s, "\tfield: char data;\t"
-			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
-			 (unsigned int)offsetof(typeof(field), data),
-			 (unsigned int)BUF_PAGE_SIZE,
-			 (unsigned int)is_signed_type(char));
-
-	return !trace_seq_has_overflowed(s);
-}
-
 struct rb_irq_work {
 	struct irq_work			work;
 	wait_queue_head_t		waiters;
 	wait_queue_head_t		full_waiters;
-	long				wait_index;
 	bool				waiters_pending;
 	bool				full_waiters_pending;
 	bool				wakeup_full;
@@ -463,27 +434,9 @@ enum {
 	RB_CTX_MAX
 };
 
-#if BITS_PER_LONG == 32
-#define RB_TIME_32
-#endif
-
-/* To test on 64 bit machines */
-//#define RB_TIME_32
-
-#ifdef RB_TIME_32
-
-struct rb_time_struct {
-	local_t		cnt;
-	local_t		top;
-	local_t		bottom;
-	local_t		msb;
-};
-#else
-#include <asm/local64.h>
 struct rb_time_struct {
 	local64_t	time;
 };
-#endif
 typedef struct rb_time_struct rb_time_t;
 
 #define MAX_NEST	5
@@ -557,6 +510,10 @@ struct trace_buffer {
 
 	struct rb_irq_work		irq_work;
 	bool				time_stamp_abs;
+
+	unsigned int			subbuf_size;
+	unsigned int			subbuf_order;
+	unsigned int			max_data_size;
 };
 
 struct ring_buffer_iter {
@@ -570,150 +527,48 @@ struct ring_buffer_iter {
 	u64				read_stamp;
 	u64				page_stamp;
 	struct ring_buffer_event	*event;
+	size_t				event_size;
 	int				missed_events;
 };
 
-#ifdef RB_TIME_32
-
-/*
- * On 32 bit machines, local64_t is very expensive. As the ring
- * buffer doesn't need all the features of a true 64 bit atomic,
- * on 32 bit, it uses these functions (64 still uses local64_t).
- *
- * For the ring buffer, 64 bit required operations for the time is
- * the following:
- *
- *  - Reads may fail if it interrupted a modification of the time stamp.
- *      It will succeed if it did not interrupt another write even if
- *      the read itself is interrupted by a write.
- *      It returns whether it was successful or not.
- *
- *  - Writes always succeed and will overwrite other writes and writes
- *      that were done by events interrupting the current write.
- *
- *  - A write followed by a read of the same time stamp will always succeed,
- *      but may not contain the same value.
- *
- *  - A cmpxchg will fail if it interrupted another write or cmpxchg.
- *      Other than that, it acts like a normal cmpxchg.
- *
- * The 60 bit time stamp is broken up by 30 bits in a top and bottom half
- *  (bottom being the least significant 30 bits of the 60 bit time stamp).
- *
- * The two most significant bits of each half holds a 2 bit counter (0-3).
- * Each update will increment this counter by one.
- * When reading the top and bottom, if the two counter bits match then the
- *  top and bottom together make a valid 60 bit number.
- */
-#define RB_TIME_SHIFT	30
-#define RB_TIME_VAL_MASK ((1 << RB_TIME_SHIFT) - 1)
-#define RB_TIME_MSB_SHIFT	 60
-
-static inline int rb_time_cnt(unsigned long val)
-{
-	return (val >> RB_TIME_SHIFT) & 3;
-}
-
-static inline u64 rb_time_val(unsigned long top, unsigned long bottom)
-{
-	u64 val;
-
-	val = top & RB_TIME_VAL_MASK;
-	val <<= RB_TIME_SHIFT;
-	val |= bottom & RB_TIME_VAL_MASK;
-
-	return val;
-}
-
-static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt)
-{
-	unsigned long top, bottom, msb;
-	unsigned long c;
-
-	/*
-	 * If the read is interrupted by a write, then the cnt will
-	 * be different. Loop until both top and bottom have been read
-	 * without interruption.
-	 */
-	do {
-		c = local_read(&t->cnt);
-		top = local_read(&t->top);
-		bottom = local_read(&t->bottom);
-		msb = local_read(&t->msb);
-	} while (c != local_read(&t->cnt));
-
-	*cnt = rb_time_cnt(top);
-
-	/* If top, msb or bottom counts don't match, this interrupted a write */
-	if (*cnt != rb_time_cnt(msb) || *cnt != rb_time_cnt(bottom))
-		return false;
-
-	/* The shift to msb will lose its cnt bits */
-	*ret = rb_time_val(top, bottom) | ((u64)msb << RB_TIME_MSB_SHIFT);
-	return true;
-}
-
-static bool rb_time_read(rb_time_t *t, u64 *ret)
-{
-	unsigned long cnt;
-
-	return __rb_time_read(t, ret, &cnt);
-}
-
-static inline unsigned long rb_time_val_cnt(unsigned long val, unsigned long cnt)
-{
-	return (val & RB_TIME_VAL_MASK) | ((cnt & 3) << RB_TIME_SHIFT);
-}
-
-static inline void rb_time_split(u64 val, unsigned long *top, unsigned long *bottom,
-				 unsigned long *msb)
+int ring_buffer_print_page_header(struct trace_buffer *buffer, struct trace_seq *s)
 {
-	*top = (unsigned long)((val >> RB_TIME_SHIFT) & RB_TIME_VAL_MASK);
-	*bottom = (unsigned long)(val & RB_TIME_VAL_MASK);
-	*msb = (unsigned long)(val >> RB_TIME_MSB_SHIFT);
-}
+	struct buffer_data_page field;
 
-static inline void rb_time_val_set(local_t *t, unsigned long val, unsigned long cnt)
-{
-	val = rb_time_val_cnt(val, cnt);
-	local_set(t, val);
-}
+	trace_seq_printf(s, "\tfield: u64 timestamp;\t"
+			 "offset:0;\tsize:%u;\tsigned:%u;\n",
+			 (unsigned int)sizeof(field.time_stamp),
+			 (unsigned int)is_signed_type(u64));
 
-static void rb_time_set(rb_time_t *t, u64 val)
-{
-	unsigned long cnt, top, bottom, msb;
+	trace_seq_printf(s, "\tfield: local_t commit;\t"
+			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
+			 (unsigned int)offsetof(typeof(field), commit),
+			 (unsigned int)sizeof(field.commit),
+			 (unsigned int)is_signed_type(long));
 
-	rb_time_split(val, &top, &bottom, &msb);
+	trace_seq_printf(s, "\tfield: int overwrite;\t"
+			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
+			 (unsigned int)offsetof(typeof(field), commit),
+			 1,
+			 (unsigned int)is_signed_type(long));
 
-	/* Writes always succeed with a valid number even if it gets interrupted. */
-	do {
-		cnt = local_inc_return(&t->cnt);
-		rb_time_val_set(&t->top, top, cnt);
-		rb_time_val_set(&t->bottom, bottom, cnt);
-		rb_time_val_set(&t->msb, val >> RB_TIME_MSB_SHIFT, cnt);
-	} while (cnt != local_read(&t->cnt));
-}
+	trace_seq_printf(s, "\tfield: char data;\t"
+			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
+			 (unsigned int)offsetof(typeof(field), data),
+			 (unsigned int)buffer->subbuf_size,
+			 (unsigned int)is_signed_type(char));
 
-static inline bool
-rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set)
-{
-	return local_try_cmpxchg(l, &expect, set);
+	return !trace_seq_has_overflowed(s);
 }
 
-#else /* 64 bits */
-
-/* local64_t always succeeds */
-
-static inline bool rb_time_read(rb_time_t *t, u64 *ret)
+static inline void rb_time_read(rb_time_t *t, u64 *ret)
 {
 	*ret = local64_read(&t->time);
-	return true;
 }
 static void rb_time_set(rb_time_t *t, u64 val)
 {
 	local64_set(&t->time, val);
 }
-#endif
 
 /*
  * Enable this to make sure that the event passed to
@@ -820,10 +675,7 @@ u64 ring_buffer_event_time_stamp(struct trace_buffer *buffer,
 	WARN_ONCE(1, "nest (%d) greater than max", nest);
 
  fail:
-	/* Can only fail on 32 bit */
-	if (!rb_time_read(&cpu_buffer->write_stamp, &ts))
-		/* Screw it, just read the current time */
-		ts = rb_time_stamp(cpu_buffer->buffer);
+	rb_time_read(&cpu_buffer->write_stamp, &ts);
 
 	return ts;
 }
@@ -903,8 +755,19 @@ static void rb_wake_up_waiters(struct irq_work *work)
 
 	wake_up_all(&rbwork->waiters);
 	if (rbwork->full_waiters_pending || rbwork->wakeup_full) {
+		/* Only cpu_buffer sets the above flags */
+		struct ring_buffer_per_cpu *cpu_buffer =
+			container_of(rbwork, struct ring_buffer_per_cpu, irq_work);
+
+		/* Called from interrupt context */
+		raw_spin_lock(&cpu_buffer->reader_lock);
 		rbwork->wakeup_full = false;
 		rbwork->full_waiters_pending = false;
+
+		/* Waking up all waiters, they will reset the shortest full */
+		cpu_buffer->shortest_full = 0;
+		raw_spin_unlock(&cpu_buffer->reader_lock);
+
 		wake_up_all(&rbwork->full_waiters);
 	}
 }
@@ -945,14 +808,40 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu)
 		rbwork = &cpu_buffer->irq_work;
 	}
 
-	rbwork->wait_index++;
-	/* make sure the waiters see the new index */
-	smp_wmb();
-
 	/* This can be called in any context */
 	irq_work_queue(&rbwork->work);
 }
 
+static bool rb_watermark_hit(struct trace_buffer *buffer, int cpu, int full)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	bool ret = false;
+
+	/* Reads of all CPUs always waits for any data */
+	if (cpu == RING_BUFFER_ALL_CPUS)
+		return !ring_buffer_empty(buffer);
+
+	cpu_buffer = buffer->buffers[cpu];
+
+	if (!ring_buffer_empty_cpu(buffer, cpu)) {
+		unsigned long flags;
+		bool pagebusy;
+
+		if (!full)
+			return true;
+
+		raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+		pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;
+		ret = !pagebusy && full_hit(buffer, cpu, full);
+
+		if (!cpu_buffer->shortest_full ||
+		    cpu_buffer->shortest_full > full)
+			cpu_buffer->shortest_full = full;
+		raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	}
+	return ret;
+}
+
 /**
  * ring_buffer_wait - wait for input to the ring buffer
  * @buffer: buffer to wait on
@@ -968,7 +857,6 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
 	struct ring_buffer_per_cpu *cpu_buffer;
 	DEFINE_WAIT(wait);
 	struct rb_irq_work *work;
-	long wait_index;
 	int ret = 0;
 
 	/*
@@ -987,81 +875,54 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
 		work = &cpu_buffer->irq_work;
 	}
 
-	wait_index = READ_ONCE(work->wait_index);
-
-	while (true) {
-		if (full)
-			prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE);
-		else
-			prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE);
-
-		/*
-		 * The events can happen in critical sections where
-		 * checking a work queue can cause deadlocks.
-		 * After adding a task to the queue, this flag is set
-		 * only to notify events to try to wake up the queue
-		 * using irq_work.
-		 *
-		 * We don't clear it even if the buffer is no longer
-		 * empty. The flag only causes the next event to run
-		 * irq_work to do the work queue wake up. The worse
-		 * that can happen if we race with !trace_empty() is that
-		 * an event will cause an irq_work to try to wake up
-		 * an empty queue.
-		 *
-		 * There's no reason to protect this flag either, as
-		 * the work queue and irq_work logic will do the necessary
-		 * synchronization for the wake ups. The only thing
-		 * that is necessary is that the wake up happens after
-		 * a task has been queued. It's OK for spurious wake ups.
-		 */
-		if (full)
-			work->full_waiters_pending = true;
-		else
-			work->waiters_pending = true;
-
-		if (signal_pending(current)) {
-			ret = -EINTR;
-			break;
-		}
-
-		if (cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer))
-			break;
-
-		if (cpu != RING_BUFFER_ALL_CPUS &&
-		    !ring_buffer_empty_cpu(buffer, cpu)) {
-			unsigned long flags;
-			bool pagebusy;
-			bool done;
-
-			if (!full)
-				break;
-
-			raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
-			pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;
-			done = !pagebusy && full_hit(buffer, cpu, full);
+	if (full)
+		prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE);
+	else
+		prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE);
 
-			if (!cpu_buffer->shortest_full ||
-			    cpu_buffer->shortest_full > full)
-				cpu_buffer->shortest_full = full;
-			raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
-			if (done)
-				break;
-		}
+	/*
+	 * The events can happen in critical sections where
+	 * checking a work queue can cause deadlocks.
+	 * After adding a task to the queue, this flag is set
+	 * only to notify events to try to wake up the queue
+	 * using irq_work.
+	 *
+	 * We don't clear it even if the buffer is no longer
+	 * empty. The flag only causes the next event to run
+	 * irq_work to do the work queue wake up. The worse
+	 * that can happen if we race with !trace_empty() is that
+	 * an event will cause an irq_work to try to wake up
+	 * an empty queue.
+	 *
+	 * There's no reason to protect this flag either, as
+	 * the work queue and irq_work logic will do the necessary
+	 * synchronization for the wake ups. The only thing
+	 * that is necessary is that the wake up happens after
+	 * a task has been queued. It's OK for spurious wake ups.
+	 */
+	if (full)
+		work->full_waiters_pending = true;
+	else
+		work->waiters_pending = true;
 
-		schedule();
+	if (rb_watermark_hit(buffer, cpu, full))
+		goto out;
 
-		/* Make sure to see the new wait index */
-		smp_rmb();
-		if (wait_index != work->wait_index)
-			break;
+	if (signal_pending(current)) {
+		ret = -EINTR;
+		goto out;
 	}
 
+	schedule();
+ out:
 	if (full)
 		finish_wait(&work->full_waiters, &wait);
 	else
 		finish_wait(&work->waiters, &wait);
 
+	if (!ret && !rb_watermark_hit(buffer, cpu, full) && signal_pending(current))
+		ret = -EINTR;
+
 	return ret;
 }
 
@@ -1084,28 +945,33 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
 			  struct file *filp, poll_table *poll_table, int full)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	struct rb_irq_work *work;
+	struct rb_irq_work *rbwork;
 
 	if (cpu == RING_BUFFER_ALL_CPUS) {
-		work = &buffer->irq_work;
+		rbwork = &buffer->irq_work;
 		full = 0;
 	} else {
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
-			return -EINVAL;
+			return EPOLLERR;
 
 		cpu_buffer = buffer->buffers[cpu];
-		work = &cpu_buffer->irq_work;
+		rbwork = &cpu_buffer->irq_work;
 	}
 
 	if (full) {
-		poll_wait(filp, &work->full_waiters, poll_table);
-		work->full_waiters_pending = true;
+		unsigned long flags;
+
+		poll_wait(filp, &rbwork->full_waiters, poll_table);
+
+		raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+		rbwork->full_waiters_pending = true;
 		if (!cpu_buffer->shortest_full ||
 		    cpu_buffer->shortest_full > full)
 			cpu_buffer->shortest_full = full;
+		raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 	} else {
-		poll_wait(filp, &work->waiters, poll_table);
-		work->waiters_pending = true;
+		poll_wait(filp, &rbwork->waiters, poll_table);
+		rbwork->waiters_pending = true;
 	}
 
 	/*
@@ -1619,10 +1485,12 @@ static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 
 		list_add(&bpage->list, pages);
 
-		page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), mflags, 0);
+		page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), mflags,
+					cpu_buffer->buffer->subbuf_order);
 		if (!page)
 			goto free_pages;
 		bpage->page = page_address(page);
+		bpage->order = cpu_buffer->buffer->subbuf_order;
 		rb_init_page(bpage->page);
 
 		if (user_thread && fatal_signal_pending(current))
@@ -1701,7 +1569,8 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu)
 	rb_check_bpage(cpu_buffer, bpage);
 
 	cpu_buffer->reader_page = bpage;
-	page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, 0);
+
+	page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, cpu_buffer->buffer->subbuf_order);
 	if (!page)
 		goto fail_free_reader;
 	bpage->page = page_address(page);
@@ -1784,7 +1653,14 @@ struct trace_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	if (!zalloc_cpumask_var(&buffer->cpumask, GFP_KERNEL))
 		goto fail_free_buffer;
 
-	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+	/* Default buffer page size - one system page */
+	buffer->subbuf_order = 0;
+	buffer->subbuf_size = PAGE_SIZE - BUF_PAGE_HDR_SIZE;
+
+	/* Max payload is buffer page size - header (8bytes) */
+	buffer->max_data_size = buffer->subbuf_size - (sizeof(u32) * 2);
+
+	nr_pages = DIV_ROUND_UP(size, buffer->subbuf_size);
 	buffer->flags = flags;
 	buffer->clock = trace_clock_local;
 	buffer->reader_lock_key = key;
@@ -2103,7 +1979,7 @@ static void update_pages_handler(struct work_struct *work)
  * @size: the new size.
  * @cpu_id: the cpu buffer to resize
  *
- * Minimum size is 2 * BUF_PAGE_SIZE.
+ * Minimum size is 2 * buffer->subbuf_size.
  *
  * Returns 0 on success and < 0 on failure.
  */
@@ -2125,7 +2001,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 	    !cpumask_test_cpu(cpu_id, buffer->cpumask))
 		return 0;
 
-	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+	nr_pages = DIV_ROUND_UP(size, buffer->subbuf_size);
 
 	/* we need a minimum of two pages */
 	if (nr_pages < 2)
@@ -2372,7 +2248,7 @@ rb_iter_head_event(struct ring_buffer_iter *iter)
 	 */
 	barrier();
 
-	if ((iter->head + length) > commit || length > BUF_PAGE_SIZE)
+	if ((iter->head + length) > commit || length > iter->event_size)
 		/* Writer corrupted the read? */
 		goto reset;
 
@@ -2412,11 +2288,13 @@ rb_commit_index(struct ring_buffer_per_cpu *cpu_buffer)
 }
 
 static __always_inline unsigned
-rb_event_index(struct ring_buffer_event *event)
+rb_event_index(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event)
 {
 	unsigned long addr = (unsigned long)event;
 
-	return (addr & ~PAGE_MASK) - BUF_PAGE_HDR_SIZE;
+	addr &= (PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1;
+
+	return addr - BUF_PAGE_HDR_SIZE;
 }
 
 static void rb_inc_iter(struct ring_buffer_iter *iter)
@@ -2605,6 +2483,7 @@ static inline void
 rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	      unsigned long tail, struct rb_event_info *info)
 {
+	unsigned long bsize = READ_ONCE(cpu_buffer->buffer->subbuf_size);
 	struct buffer_page *tail_page = info->tail_page;
 	struct ring_buffer_event *event;
 	unsigned long length = info->length;
@@ -2613,13 +2492,13 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	 * Only the event that crossed the page boundary
 	 * must fill the old tail_page with padding.
 	 */
-	if (tail >= BUF_PAGE_SIZE) {
+	if (tail >= bsize) {
 		/*
 		 * If the page was filled, then we still need
 		 * to update the real_end. Reset it to zero
 		 * and the reader will ignore it.
 		 */
-		if (tail == BUF_PAGE_SIZE)
+		if (tail == bsize)
 			tail_page->real_end = 0;
 
 		local_sub(length, &tail_page->write);
@@ -2647,7 +2526,7 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	 * If we are less than the minimum size, we don't need to
 	 * worry about it.
 	 */
-	if (tail > (BUF_PAGE_SIZE - RB_EVNT_MIN_SIZE)) {
+	if (tail > (bsize - RB_EVNT_MIN_SIZE)) {
 		/* No room for any events */
 
 		/* Mark the rest of the page with padding */
@@ -2662,19 +2541,19 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	}
 
 	/* Put in a discarded event */
-	event->array[0] = (BUF_PAGE_SIZE - tail) - RB_EVNT_HDR_SIZE;
+	event->array[0] = (bsize - tail) - RB_EVNT_HDR_SIZE;
 	event->type_len = RINGBUF_TYPE_PADDING;
 	/* time delta must be non zero */
 	event->time_delta = 1;
 
 	/* account for padding bytes */
-	local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes);
+	local_add(bsize - tail, &cpu_buffer->entries_bytes);
 
 	/* Make sure the padding is visible before the tail_page->write update */
 	smp_wmb();
 
 	/* Set write to end of buffer */
-	length = (tail + length) - BUF_PAGE_SIZE;
+	length = (tail + length) - bsize;
 	local_sub(length, &tail_page->write);
 }
 
@@ -2788,7 +2667,8 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
 
 /* Slow path */
 static struct ring_buffer_event *
-rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs)
+rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
+		  struct ring_buffer_event *event, u64 delta, bool abs)
 {
 	if (abs)
 		event->type_len = RINGBUF_TYPE_TIME_STAMP;
@@ -2796,7 +2676,7 @@ rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs)
 		event->type_len = RINGBUF_TYPE_TIME_EXTEND;
 
 	/* Not the first event on the page, or not delta? */
-	if (abs || rb_event_index(event)) {
+	if (abs || rb_event_index(cpu_buffer, event)) {
 		event->time_delta = delta & TS_MASK;
 		event->array[0] = delta >> TS_SHIFT;
 	} else {
@@ -2826,7 +2706,7 @@ rb_check_timestamp(struct ring_buffer_per_cpu *cpu_buffer,
 		  (unsigned long long)info->ts,
 		  (unsigned long long)info->before,
 		  (unsigned long long)info->after,
-		  (unsigned long long)(rb_time_read(&cpu_buffer->write_stamp, &write_stamp) ? write_stamp : 0),
+		  (unsigned long long)({rb_time_read(&cpu_buffer->write_stamp, &write_stamp); write_stamp;}),
 		  sched_clock_stable() ? "" :
 		  "If you just came from a suspend/resume,\n"
 		  "please switch to the trace global clock:\n"
@@ -2870,7 +2750,7 @@ static void rb_add_timestamp(struct ring_buffer_per_cpu *cpu_buffer,
 		if (!abs)
 			info->delta = 0;
 	}
-	*event = rb_add_time_stamp(*event, info->delta, abs);
+	*event = rb_add_time_stamp(cpu_buffer, *event, info->delta, abs);
 	*length -= RB_LEN_TIME_EXTEND;
 	*delta = 0;
 }
@@ -2954,10 +2834,10 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 	struct buffer_page *bpage;
 	unsigned long addr;
 
-	new_index = rb_event_index(event);
+	new_index = rb_event_index(cpu_buffer, event);
 	old_index = new_index + rb_event_ts_length(event);
 	addr = (unsigned long)event;
-	addr &= PAGE_MASK;
+	addr &= ~((PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1);
 
 	bpage = READ_ONCE(cpu_buffer->tail_page);
 
@@ -3344,6 +3224,76 @@ EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit);
 #define CHECK_FULL_PAGE		1L
 
 #ifdef CONFIG_RING_BUFFER_VALIDATE_TIME_DELTAS
+
+static const char *show_irq_str(int bits)
+{
+	const char *type[] = {
+		".",	// 0
+		"s",	// 1
+		"h",	// 2
+		"Hs",	// 3
+		"n",	// 4
+		"Ns",	// 5
+		"Nh",	// 6
+		"NHs",	// 7
+	};
+
+	return type[bits];
+}
+
+/* Assume this is an trace event */
+static const char *show_flags(struct ring_buffer_event *event)
+{
+	struct trace_entry *entry;
+	int bits = 0;
+
+	if (rb_event_data_length(event) - RB_EVNT_HDR_SIZE < sizeof(*entry))
+		return "X";
+
+	entry = ring_buffer_event_data(event);
+
+	if (entry->flags & TRACE_FLAG_SOFTIRQ)
+		bits |= 1;
+
+	if (entry->flags & TRACE_FLAG_HARDIRQ)
+		bits |= 2;
+
+	if (entry->flags & TRACE_FLAG_NMI)
+		bits |= 4;
+
+	return show_irq_str(bits);
+}
+
+static const char *show_irq(struct ring_buffer_event *event)
+{
+	struct trace_entry *entry;
+
+	if (rb_event_data_length(event) - RB_EVNT_HDR_SIZE < sizeof(*entry))
+		return "";
+
+	entry = ring_buffer_event_data(event);
+	if (entry->flags & TRACE_FLAG_IRQS_OFF)
+		return "d";
+	return "";
+}
+
+static const char *show_interrupt_level(void)
+{
+	unsigned long pc = preempt_count();
+	unsigned char level = 0;
+
+	if (pc & SOFTIRQ_OFFSET)
+		level |= 1;
+
+	if (pc & HARDIRQ_MASK)
+		level |= 2;
+
+	if (pc & NMI_MASK)
+		level |= 4;
+
+	return show_irq_str(level);
+}
+
 static void dump_buffer_page(struct buffer_data_page *bpage,
 			     struct rb_event_info *info,
 			     unsigned long tail)
@@ -3364,34 +3314,57 @@ static void dump_buffer_page(struct buffer_data_page *bpage,
 		case RINGBUF_TYPE_TIME_EXTEND:
 			delta = rb_event_time_stamp(event);
 			ts += delta;
-			pr_warn("  [%lld] delta:%lld TIME EXTEND\n", ts, delta);
+			pr_warn(" 0x%x: [%lld] delta:%lld TIME EXTEND\n",
+				e, ts, delta);
 			break;
 
 		case RINGBUF_TYPE_TIME_STAMP:
 			delta = rb_event_time_stamp(event);
 			ts = rb_fix_abs_ts(delta, ts);
-			pr_warn("  [%lld] absolute:%lld TIME STAMP\n", ts, delta);
+			pr_warn(" 0x%x:  [%lld] absolute:%lld TIME STAMP\n",
+				e, ts, delta);
 			break;
 
 		case RINGBUF_TYPE_PADDING:
 			ts += event->time_delta;
-			pr_warn("  [%lld] delta:%d PADDING\n", ts, event->time_delta);
+			pr_warn(" 0x%x:  [%lld] delta:%d PADDING\n",
+				e, ts, event->time_delta);
 			break;
 
 		case RINGBUF_TYPE_DATA:
 			ts += event->time_delta;
-			pr_warn("  [%lld] delta:%d\n", ts, event->time_delta);
+			pr_warn(" 0x%x:  [%lld] delta:%d %s%s\n",
+				e, ts, event->time_delta,
+				show_flags(event), show_irq(event));
 			break;
 
 		default:
 			break;
 		}
 	}
+	pr_warn("expected end:0x%lx last event actually ended at:0x%x\n", tail, e);
 }
 
 static DEFINE_PER_CPU(atomic_t, checking);
 static atomic_t ts_dump;
 
+#define buffer_warn_return(fmt, ...)					\
+	do {								\
+		/* If another report is happening, ignore this one */	\
+		if (atomic_inc_return(&ts_dump) != 1) {			\
+			atomic_dec(&ts_dump);				\
+			goto out;					\
+		}							\
+		atomic_inc(&cpu_buffer->record_disabled);		\
+		pr_warn(fmt, ##__VA_ARGS__);				\
+		dump_buffer_page(bpage, info, tail);			\
+		atomic_dec(&ts_dump);					\
+		/* There's some cases in boot up that this can happen */ \
+		if (WARN_ON_ONCE(system_state != SYSTEM_BOOTING))	\
+			/* Do not re-enable checking */			\
+			return;						\
+	} while (0)
+
 /*
  * Check if the current event time stamp matches the deltas on
  * the buffer page.
@@ -3445,7 +3418,12 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer,
 
 		case RINGBUF_TYPE_TIME_STAMP:
 			delta = rb_event_time_stamp(event);
-			ts = rb_fix_abs_ts(delta, ts);
+			delta = rb_fix_abs_ts(delta, ts);
+			if (delta < ts) {
+				buffer_warn_return("[CPU: %d]ABSOLUTE TIME WENT BACKWARDS: last ts: %lld absolute ts: %lld\n",
+						   cpu_buffer->cpu, ts, delta);
+			}
+			ts = delta;
 			break;
 
 		case RINGBUF_TYPE_PADDING:
@@ -3462,23 +3440,11 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer,
 	}
 	if ((full && ts > info->ts) ||
 	    (!full && ts + info->delta != info->ts)) {
-		/* If another report is happening, ignore this one */
-		if (atomic_inc_return(&ts_dump) != 1) {
-			atomic_dec(&ts_dump);
-			goto out;
-		}
-		atomic_inc(&cpu_buffer->record_disabled);
-		/* There's some cases in boot up that this can happen */
-		WARN_ON_ONCE(system_state != SYSTEM_BOOTING);
-		pr_warn("[CPU: %d]TIME DOES NOT MATCH expected:%lld actual:%lld delta:%lld before:%lld after:%lld%s\n",
-			cpu_buffer->cpu,
-			ts + info->delta, info->ts, info->delta,
-			info->before, info->after,
-			full ? " (full)" : "");
-		dump_buffer_page(bpage, info, tail);
-		atomic_dec(&ts_dump);
-		/* Do not re-enable checking */
-		return;
+		buffer_warn_return("[CPU: %d]TIME DOES NOT MATCH expected:%lld actual:%lld delta:%lld before:%lld after:%lld%s context:%s\n",
+				   cpu_buffer->cpu,
+				   ts + info->delta, info->ts, info->delta,
+				   info->before, info->after,
+				   full ? " (full)" : "", show_interrupt_level());
 	}
 out:
 	atomic_dec(this_cpu_ptr(&checking));
@@ -3498,16 +3464,14 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	struct ring_buffer_event *event;
 	struct buffer_page *tail_page;
 	unsigned long tail, write, w;
-	bool a_ok;
-	bool b_ok;
 
 	/* Don't let the compiler play games with cpu_buffer->tail_page */
 	tail_page = info->tail_page = READ_ONCE(cpu_buffer->tail_page);
 
  /*A*/	w = local_read(&tail_page->write) & RB_WRITE_MASK;
 	barrier();
-	b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
-	a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
+	rb_time_read(&cpu_buffer->before_stamp, &info->before);
+	rb_time_read(&cpu_buffer->write_stamp, &info->after);
 	barrier();
 	info->ts = rb_time_stamp(cpu_buffer->buffer);
 
@@ -3522,7 +3486,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		if (!w) {
 			/* Use the sub-buffer timestamp */
 			info->delta = 0;
-		} else if (unlikely(!a_ok || !b_ok || info->before != info->after)) {
+		} else if (unlikely(info->before != info->after)) {
 			info->add_timestamp |= RB_ADD_STAMP_FORCE | RB_ADD_STAMP_EXTEND;
 			info->length += RB_LEN_TIME_EXTEND;
 		} else {
@@ -3544,7 +3508,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	tail = write - info->length;
 
 	/* See if we shot pass the end of this buffer page */
-	if (unlikely(write > BUF_PAGE_SIZE)) {
+	if (unlikely(write > cpu_buffer->buffer->subbuf_size)) {
 		check_buffer(cpu_buffer, info, CHECK_FULL_PAGE);
 		return rb_move_tail(cpu_buffer, tail, info);
 	}
@@ -3571,8 +3535,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		/* SLOW PATH - Interrupted between A and C */
 
 		/* Save the old before_stamp */
-		a_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
-		RB_WARN_ON(cpu_buffer, !a_ok);
+		rb_time_read(&cpu_buffer->before_stamp, &info->before);
 
 		/*
 		 * Read a new timestamp and update the before_stamp to make
@@ -3584,9 +3547,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		rb_time_set(&cpu_buffer->before_stamp, ts);
 
 		barrier();
- /*E*/		a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
-		/* Was interrupted before here, write_stamp must be valid */
-		RB_WARN_ON(cpu_buffer, !a_ok);
+ /*E*/		rb_time_read(&cpu_buffer->write_stamp, &info->after);
 		barrier();
  /*F*/		if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) &&
 		    info->after == info->before && info->after < ts) {
@@ -3678,7 +3639,7 @@ rb_reserve_next_event(struct trace_buffer *buffer,
 	if (ring_buffer_time_stamp_abs(cpu_buffer->buffer)) {
 		add_ts_default = RB_ADD_STAMP_ABSOLUTE;
 		info.length += RB_LEN_TIME_EXTEND;
-		if (info.length > BUF_MAX_DATA_SIZE)
+		if (info.length > cpu_buffer->buffer->max_data_size)
 			goto out_fail;
 	} else {
 		add_ts_default = RB_ADD_STAMP_NONE;
@@ -3753,7 +3714,7 @@ ring_buffer_lock_reserve(struct trace_buffer *buffer, unsigned long length)
 	if (unlikely(atomic_read(&cpu_buffer->record_disabled)))
 		goto out;
 
-	if (unlikely(length > BUF_MAX_DATA_SIZE))
+	if (unlikely(length > buffer->max_data_size))
 		goto out;
 
 	if (unlikely(trace_recursive_lock(cpu_buffer)))
@@ -3787,7 +3748,7 @@ rb_decrement_entry(struct ring_buffer_per_cpu *cpu_buffer,
 	struct buffer_page *bpage = cpu_buffer->commit_page;
 	struct buffer_page *start;
 
-	addr &= PAGE_MASK;
+	addr &= ~((PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1);
 
 	/* Do the likely case first */
 	if (likely(bpage->page == (void *)addr)) {
@@ -3903,7 +3864,7 @@ int ring_buffer_write(struct trace_buffer *buffer,
 	if (atomic_read(&cpu_buffer->record_disabled))
 		goto out;
 
-	if (length > BUF_MAX_DATA_SIZE)
+	if (length > buffer->max_data_size)
 		goto out;
 
 	if (unlikely(trace_recursive_lock(cpu_buffer)))
@@ -4483,6 +4444,7 @@ static struct buffer_page *
 rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	struct buffer_page *reader = NULL;
+	unsigned long bsize = READ_ONCE(cpu_buffer->buffer->subbuf_size);
 	unsigned long overwrite;
 	unsigned long flags;
 	int nr_loops = 0;
@@ -4618,7 +4580,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 #define USECS_WAIT	1000000
         for (nr_loops = 0; nr_loops < USECS_WAIT; nr_loops++) {
 		/* If the write is past the end of page, a writer is still updating it */
-		if (likely(!reader || rb_page_write(reader) <= BUF_PAGE_SIZE))
+		if (likely(!reader || rb_page_write(reader) <= bsize))
 			break;
 
 		udelay(1);
@@ -5062,7 +5024,8 @@ ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags)
 		return NULL;
 
 	/* Holds the entire event: data and meta data */
-	iter->event = kmalloc(BUF_PAGE_SIZE, flags);
+	iter->event_size = buffer->subbuf_size;
+	iter->event = kmalloc(iter->event_size, flags);
 	if (!iter->event) {
 		kfree(iter);
 		return NULL;
@@ -5178,19 +5141,28 @@ EXPORT_SYMBOL_GPL(ring_buffer_iter_advance);
  */
 unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu)
 {
-	/*
-	 * Earlier, this method returned
-	 *	BUF_PAGE_SIZE * buffer->nr_pages
-	 * Since the nr_pages field is now removed, we have converted this to
-	 * return the per cpu buffer value.
-	 */
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return 0;
 
-	return BUF_PAGE_SIZE * buffer->buffers[cpu]->nr_pages;
+	return buffer->subbuf_size * buffer->buffers[cpu]->nr_pages;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_size);
 
+/**
+ * ring_buffer_max_event_size - return the max data size of an event
+ * @buffer: The ring buffer.
+ *
+ * Returns the maximum size an event can be.
+ */
+unsigned long ring_buffer_max_event_size(struct trace_buffer *buffer)
+{
+	/* If abs timestamp is requested, events have a timestamp too */
+	if (ring_buffer_time_stamp_abs(buffer))
+		return buffer->max_data_size - RB_LEN_TIME_EXTEND;
+	return buffer->max_data_size;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_max_event_size);
+
 static void rb_clear_buffer_page(struct buffer_page *page)
 {
 	local_set(&page->write, 0);
@@ -5461,6 +5433,9 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a,
 	if (cpu_buffer_a->nr_pages != cpu_buffer_b->nr_pages)
 		goto out;
 
+	if (buffer_a->subbuf_order != buffer_b->subbuf_order)
+		goto out;
+
 	ret = -EAGAIN;
 
 	if (atomic_read(&buffer_a->record_disabled))
@@ -5532,40 +5507,48 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
  * Returns:
  *  The page allocated, or ERR_PTR
  */
-void *ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu)
+struct buffer_data_read_page *
+ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	struct buffer_data_page *bpage = NULL;
+	struct buffer_data_read_page *bpage = NULL;
 	unsigned long flags;
 	struct page *page;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return ERR_PTR(-ENODEV);
 
+	bpage = kzalloc(sizeof(*bpage), GFP_KERNEL);
+	if (!bpage)
+		return ERR_PTR(-ENOMEM);
+
+	bpage->order = buffer->subbuf_order;
 	cpu_buffer = buffer->buffers[cpu];
 	local_irq_save(flags);
 	arch_spin_lock(&cpu_buffer->lock);
 
 	if (cpu_buffer->free_page) {
-		bpage = cpu_buffer->free_page;
+		bpage->data = cpu_buffer->free_page;
 		cpu_buffer->free_page = NULL;
 	}
 
 	arch_spin_unlock(&cpu_buffer->lock);
 	local_irq_restore(flags);
 
-	if (bpage)
+	if (bpage->data)
 		goto out;
 
-	page = alloc_pages_node(cpu_to_node(cpu),
-				GFP_KERNEL | __GFP_NORETRY, 0);
-	if (!page)
+	page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY,
+				cpu_buffer->buffer->subbuf_order);
+	if (!page) {
+		kfree(bpage);
 		return ERR_PTR(-ENOMEM);
+	}
 
-	bpage = page_address(page);
+	bpage->data = page_address(page);
 
  out:
-	rb_init_page(bpage);
+	rb_init_page(bpage->data);
 
 	return bpage;
 }
@@ -5575,14 +5558,15 @@ EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page);
  * ring_buffer_free_read_page - free an allocated read page
  * @buffer: the buffer the page was allocate for
  * @cpu: the cpu buffer the page came from
- * @data: the page to free
+ * @data_page: the page to free
  *
  * Free a page allocated from ring_buffer_alloc_read_page.
  */
-void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data)
+void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu,
+				struct buffer_data_read_page *data_page)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	struct buffer_data_page *bpage = data;
+	struct buffer_data_page *bpage = data_page->data;
 	struct page *page = virt_to_page(bpage);
 	unsigned long flags;
 
@@ -5591,8 +5575,12 @@ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data
 
 	cpu_buffer = buffer->buffers[cpu];
 
-	/* If the page is still in use someplace else, we can't reuse it */
-	if (page_ref_count(page) > 1)
+	/*
+	 * If the page is still in use someplace else, or order of the page
+	 * is different from the subbuffer order of the buffer -
+	 * we can't reuse it
+	 */
+	if (page_ref_count(page) > 1 || data_page->order != buffer->subbuf_order)
 		goto out;
 
 	local_irq_save(flags);
@@ -5607,7 +5595,8 @@ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data
 	local_irq_restore(flags);
 
  out:
-	free_page((unsigned long)bpage);
+	free_pages((unsigned long)bpage, data_page->order);
+	kfree(data_page);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
 
@@ -5628,9 +5617,10 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
  *	rpage = ring_buffer_alloc_read_page(buffer, cpu);
  *	if (IS_ERR(rpage))
  *		return PTR_ERR(rpage);
- *	ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0);
+ *	ret = ring_buffer_read_page(buffer, rpage, len, cpu, 0);
  *	if (ret >= 0)
- *		process_page(rpage, ret);
+ *		process_page(ring_buffer_read_page_data(rpage), ret);
+ *	ring_buffer_free_read_page(buffer, cpu, rpage);
  *
  * When @full is set, the function will not return true unless
  * the writer is off the reader page.
@@ -5645,7 +5635,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
  *  <0 if no data has been transferred.
  */
 int ring_buffer_read_page(struct trace_buffer *buffer,
-			  void **data_page, size_t len, int cpu, int full)
+			  struct buffer_data_read_page *data_page,
+			  size_t len, int cpu, int full)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
 	struct ring_buffer_event *event;
@@ -5670,10 +5661,12 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 
 	len -= BUF_PAGE_HDR_SIZE;
 
-	if (!data_page)
+	if (!data_page || !data_page->data)
+		goto out;
+	if (data_page->order != buffer->subbuf_order)
 		goto out;
 
-	bpage = *data_page;
+	bpage = data_page->data;
 	if (!bpage)
 		goto out;
 
@@ -5767,11 +5760,11 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 		/* swap the pages */
 		rb_init_page(bpage);
 		bpage = reader->page;
-		reader->page = *data_page;
+		reader->page = data_page->data;
 		local_set(&reader->write, 0);
 		local_set(&reader->entries, 0);
 		reader->read = 0;
-		*data_page = bpage;
+		data_page->data = bpage;
 
 		/*
 		 * Use the real_end for the data size,
@@ -5793,7 +5786,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 		/* If there is room at the end of the page to save the
 		 * missed events, then record it there.
 		 */
-		if (BUF_PAGE_SIZE - commit >= sizeof(missed_events)) {
+		if (buffer->subbuf_size - commit >= sizeof(missed_events)) {
 			memcpy(&bpage->data[commit], &missed_events,
 			       sizeof(missed_events));
 			local_add(RB_MISSED_STORED, &bpage->commit);
@@ -5805,8 +5798,8 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 	/*
 	 * This page may be off to user land. Zero it out here.
 	 */
-	if (commit < BUF_PAGE_SIZE)
-		memset(&bpage->data[commit], 0, BUF_PAGE_SIZE - commit);
+	if (commit < buffer->subbuf_size)
+		memset(&bpage->data[commit], 0, buffer->subbuf_size - commit);
 
  out_unlock:
 	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
@@ -5816,6 +5809,213 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_page);
 
+/**
+ * ring_buffer_read_page_data - get pointer to the data in the page.
+ * @page:  the page to get the data from
+ *
+ * Returns pointer to the actual data in this page.
+ */
+void *ring_buffer_read_page_data(struct buffer_data_read_page *page)
+{
+	return page->data;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_read_page_data);
+
+/**
+ * ring_buffer_subbuf_size_get - get size of the sub buffer.
+ * @buffer: the buffer to get the sub buffer size from
+ *
+ * Returns size of the sub buffer, in bytes.
+ */
+int ring_buffer_subbuf_size_get(struct trace_buffer *buffer)
+{
+	return buffer->subbuf_size + BUF_PAGE_HDR_SIZE;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_subbuf_size_get);
+
+/**
+ * ring_buffer_subbuf_order_get - get order of system sub pages in one buffer page.
+ * @buffer: The ring_buffer to get the system sub page order from
+ *
+ * By default, one ring buffer sub page equals to one system page. This parameter
+ * is configurable, per ring buffer. The size of the ring buffer sub page can be
+ * extended, but must be an order of system page size.
+ *
+ * Returns the order of buffer sub page size, in system pages:
+ * 0 means the sub buffer size is 1 system page and so forth.
+ * In case of an error < 0 is returned.
+ */
+int ring_buffer_subbuf_order_get(struct trace_buffer *buffer)
+{
+	if (!buffer)
+		return -EINVAL;
+
+	return buffer->subbuf_order;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_subbuf_order_get);
+
+/**
+ * ring_buffer_subbuf_order_set - set the size of ring buffer sub page.
+ * @buffer: The ring_buffer to set the new page size.
+ * @order: Order of the system pages in one sub buffer page
+ *
+ * By default, one ring buffer pages equals to one system page. This API can be
+ * used to set new size of the ring buffer page. The size must be order of
+ * system page size, that's why the input parameter @order is the order of
+ * system pages that are allocated for one ring buffer page:
+ *  0 - 1 system page
+ *  1 - 2 system pages
+ *  3 - 4 system pages
+ *  ...
+ *
+ * Returns 0 on success or < 0 in case of an error.
+ */
+int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	struct buffer_page *bpage, *tmp;
+	int old_order, old_size;
+	int nr_pages;
+	int psize;
+	int err;
+	int cpu;
+
+	if (!buffer || order < 0)
+		return -EINVAL;
+
+	if (buffer->subbuf_order == order)
+		return 0;
+
+	psize = (1 << order) * PAGE_SIZE;
+	if (psize <= BUF_PAGE_HDR_SIZE)
+		return -EINVAL;
+
+	/* Size of a subbuf cannot be greater than the write counter */
+	if (psize > RB_WRITE_MASK + 1)
+		return -EINVAL;
+
+	old_order = buffer->subbuf_order;
+	old_size = buffer->subbuf_size;
+
+	/* prevent another thread from changing buffer sizes */
+	mutex_lock(&buffer->mutex);
+	atomic_inc(&buffer->record_disabled);
+
+	/* Make sure all commits have finished */
+	synchronize_rcu();
+
+	buffer->subbuf_order = order;
+	buffer->subbuf_size = psize - BUF_PAGE_HDR_SIZE;
+
+	/* Make sure all new buffers are allocated, before deleting the old ones */
+	for_each_buffer_cpu(buffer, cpu) {
+
+		if (!cpumask_test_cpu(cpu, buffer->cpumask))
+			continue;
+
+		cpu_buffer = buffer->buffers[cpu];
+
+		/* Update the number of pages to match the new size */
+		nr_pages = old_size * buffer->buffers[cpu]->nr_pages;
+		nr_pages = DIV_ROUND_UP(nr_pages, buffer->subbuf_size);
+
+		/* we need a minimum of two pages */
+		if (nr_pages < 2)
+			nr_pages = 2;
+
+		cpu_buffer->nr_pages_to_update = nr_pages;
+
+		/* Include the reader page */
+		nr_pages++;
+
+		/* Allocate the new size buffer */
+		INIT_LIST_HEAD(&cpu_buffer->new_pages);
+		if (__rb_allocate_pages(cpu_buffer, nr_pages,
+					&cpu_buffer->new_pages)) {
+			/* not enough memory for new pages */
+			err = -ENOMEM;
+			goto error;
+		}
+	}
+
+	for_each_buffer_cpu(buffer, cpu) {
+
+		if (!cpumask_test_cpu(cpu, buffer->cpumask))
+			continue;
+
+		cpu_buffer = buffer->buffers[cpu];
+
+		/* Clear the head bit to make the link list normal to read */
+		rb_head_page_deactivate(cpu_buffer);
+
+		/* Now walk the list and free all the old sub buffers */
+		list_for_each_entry_safe(bpage, tmp, cpu_buffer->pages, list) {
+			list_del_init(&bpage->list);
+			free_buffer_page(bpage);
+		}
+		/* The above loop stopped an the last page needing to be freed */
+		bpage = list_entry(cpu_buffer->pages, struct buffer_page, list);
+		free_buffer_page(bpage);
+
+		/* Free the current reader page */
+		free_buffer_page(cpu_buffer->reader_page);
+
+		/* One page was allocated for the reader page */
+		cpu_buffer->reader_page = list_entry(cpu_buffer->new_pages.next,
+						     struct buffer_page, list);
+		list_del_init(&cpu_buffer->reader_page->list);
+
+		/* The cpu_buffer pages are a link list with no head */
+		cpu_buffer->pages = cpu_buffer->new_pages.next;
+		cpu_buffer->new_pages.next->prev = cpu_buffer->new_pages.prev;
+		cpu_buffer->new_pages.prev->next = cpu_buffer->new_pages.next;
+
+		/* Clear the new_pages list */
+		INIT_LIST_HEAD(&cpu_buffer->new_pages);
+
+		cpu_buffer->head_page
+			= list_entry(cpu_buffer->pages, struct buffer_page, list);
+		cpu_buffer->tail_page = cpu_buffer->commit_page = cpu_buffer->head_page;
+
+		cpu_buffer->nr_pages = cpu_buffer->nr_pages_to_update;
+		cpu_buffer->nr_pages_to_update = 0;
+
+		free_pages((unsigned long)cpu_buffer->free_page, old_order);
+		cpu_buffer->free_page = NULL;
+
+		rb_head_page_activate(cpu_buffer);
+
+		rb_check_pages(cpu_buffer);
+	}
+
+	atomic_dec(&buffer->record_disabled);
+	mutex_unlock(&buffer->mutex);
+
+	return 0;
+
+error:
+	buffer->subbuf_order = old_order;
+	buffer->subbuf_size = old_size;
+
+	atomic_dec(&buffer->record_disabled);
+	mutex_unlock(&buffer->mutex);
+
+	for_each_buffer_cpu(buffer, cpu) {
+		cpu_buffer = buffer->buffers[cpu];
+
+		if (!cpu_buffer->nr_pages_to_update)
+			continue;
+
+		list_for_each_entry_safe(bpage, tmp, &cpu_buffer->new_pages, list) {
+			list_del_init(&bpage->list);
+			free_buffer_page(bpage);
+		}
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_subbuf_order_set);
+
 /*
  * We only allocate new buffers, never free them if the CPU goes down.
  * If we were to free the buffer, then the user would lose any trace that was in
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index aef34673d79d..008187ebd7fe 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -104,10 +104,11 @@ static enum event_status read_event(int cpu)
 
 static enum event_status read_page(int cpu)
 {
+	struct buffer_data_read_page *bpage;
 	struct ring_buffer_event *event;
 	struct rb_page *rpage;
 	unsigned long commit;
-	void *bpage;
+	int page_size;
 	int *entry;
 	int ret;
 	int inc;
@@ -117,14 +118,15 @@ static enum event_status read_page(int cpu)
 	if (IS_ERR(bpage))
 		return EVENT_DROPPED;
 
-	ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1);
+	page_size = ring_buffer_subbuf_size_get(buffer);
+	ret = ring_buffer_read_page(buffer, bpage, page_size, cpu, 1);
 	if (ret >= 0) {
-		rpage = bpage;
+		rpage = ring_buffer_read_page_data(bpage);
 		/* The commit may have missed event flags set, clear them */
 		commit = local_read(&rpage->commit) & 0xfffff;
 		for (i = 0; i < commit && !test_error ; i += inc) {
 
-			if (i >= (PAGE_SIZE - offsetof(struct rb_page, data))) {
+			if (i >= (page_size - offsetof(struct rb_page, data))) {
 				TEST_ERROR();
 				break;
 			}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a0defe156b57..c9c898307348 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -39,6 +39,7 @@
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/panic_notifier.h>
+#include <linux/kmemleak.h>
 #include <linux/poll.h>
 #include <linux/nmi.h>
 #include <linux/fs.h>
@@ -1263,10 +1264,17 @@ static void set_buffer_entries(struct array_buffer *buf, unsigned long val);
 
 int tracing_alloc_snapshot_instance(struct trace_array *tr)
 {
+	int order;
 	int ret;
 
 	if (!tr->allocated_snapshot) {
 
+		/* Make the snapshot buffer have the same order as main buffer */
+		order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer);
+		ret = ring_buffer_subbuf_order_set(tr->max_buffer.buffer, order);
+		if (ret < 0)
+			return ret;
+
 		/* allocate spare buffer */
 		ret = resize_buffer_duplicate_size(&tr->max_buffer,
 				   &tr->array_buffer, RING_BUFFER_ALL_CPUS);
@@ -1286,6 +1294,7 @@ static void free_snapshot(struct trace_array *tr)
 	 * The max_tr ring buffer has some state (e.g. ring->clock) and
 	 * we want preserve it.
 	 */
+	ring_buffer_subbuf_order_set(tr->max_buffer.buffer, 0);
 	ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS);
 	set_buffer_entries(&tr->max_buffer, 1);
 	tracing_reset_online_cpus(&tr->max_buffer);
@@ -1524,7 +1533,7 @@ void disable_trace_on_warning(void)
 bool tracer_tracing_is_on(struct trace_array *tr)
 {
 	if (tr->array_buffer.buffer)
-		return ring_buffer_record_is_on(tr->array_buffer.buffer);
+		return ring_buffer_record_is_set_on(tr->array_buffer.buffer);
 	return !tr->buffer_disabled;
 }
 
@@ -2312,7 +2321,7 @@ struct saved_cmdlines_buffer {
 	unsigned *map_cmdline_to_pid;
 	unsigned cmdline_num;
 	int cmdline_idx;
-	char *saved_cmdlines;
+	char saved_cmdlines[];
 };
 static struct saved_cmdlines_buffer *savedcmd;
 
@@ -2326,47 +2335,60 @@ static inline void set_cmdline(int idx, const char *cmdline)
 	strncpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN);
 }
 
-static int allocate_cmdlines_buffer(unsigned int val,
-				    struct saved_cmdlines_buffer *s)
+static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
+{
+	int order = get_order(sizeof(*s) + s->cmdline_num * TASK_COMM_LEN);
+
+	kfree(s->map_cmdline_to_pid);
+	kmemleak_free(s);
+	free_pages((unsigned long)s, order);
+}
+
+static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val)
 {
+	struct saved_cmdlines_buffer *s;
+	struct page *page;
+	int orig_size, size;
+	int order;
+
+	/* Figure out how much is needed to hold the given number of cmdlines */
+	orig_size = sizeof(*s) + val * TASK_COMM_LEN;
+	order = get_order(orig_size);
+	size = 1 << (order + PAGE_SHIFT);
+	page = alloc_pages(GFP_KERNEL, order);
+	if (!page)
+		return NULL;
+
+	s = page_address(page);
+	kmemleak_alloc(s, size, 1, GFP_KERNEL);
+	memset(s, 0, sizeof(*s));
+
+	/* Round up to actual allocation */
+	val = (size - sizeof(*s)) / TASK_COMM_LEN;
+	s->cmdline_num = val;
+
 	s->map_cmdline_to_pid = kmalloc_array(val,
 					      sizeof(*s->map_cmdline_to_pid),
 					      GFP_KERNEL);
-	if (!s->map_cmdline_to_pid)
-		return -ENOMEM;
-
-	s->saved_cmdlines = kmalloc_array(TASK_COMM_LEN, val, GFP_KERNEL);
-	if (!s->saved_cmdlines) {
-		kfree(s->map_cmdline_to_pid);
-		return -ENOMEM;
+	if (!s->map_cmdline_to_pid) {
+		free_saved_cmdlines_buffer(s);
+		return NULL;
 	}
 
 	s->cmdline_idx = 0;
-	s->cmdline_num = val;
 	memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,
 	       sizeof(s->map_pid_to_cmdline));
 	memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP,
 	       val * sizeof(*s->map_cmdline_to_pid));
 
-	return 0;
+	return s;
 }
 
 static int trace_create_savedcmd(void)
 {
-	int ret;
-
-	savedcmd = kmalloc(sizeof(*savedcmd), GFP_KERNEL);
-	if (!savedcmd)
-		return -ENOMEM;
-
-	ret = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT, savedcmd);
-	if (ret < 0) {
-		kfree(savedcmd);
-		savedcmd = NULL;
-		return -ENOMEM;
-	}
+	savedcmd = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT);
 
-	return 0;
+	return savedcmd ? 0 : -ENOMEM;
 }
 
 int is_tracing_stopped(void)
@@ -3767,7 +3789,7 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str,
 
 	/* OK if part of the temp seq buffer */
 	if ((addr >= (unsigned long)iter->tmp_seq.buffer) &&
-	    (addr < (unsigned long)iter->tmp_seq.buffer + PAGE_SIZE))
+	    (addr < (unsigned long)iter->tmp_seq.buffer + TRACE_SEQ_BUFFER_SIZE))
 		return true;
 
 	/* Core rodata can not be freed */
@@ -5032,7 +5054,7 @@ static int tracing_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static int tracing_release_generic_tr(struct inode *inode, struct file *file)
+int tracing_release_generic_tr(struct inode *inode, struct file *file)
 {
 	struct trace_array *tr = inode->i_private;
 
@@ -6048,26 +6070,14 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf,
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
 
-static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
-{
-	kfree(s->saved_cmdlines);
-	kfree(s->map_cmdline_to_pid);
-	kfree(s);
-}
-
 static int tracing_resize_saved_cmdlines(unsigned int val)
 {
 	struct saved_cmdlines_buffer *s, *savedcmd_temp;
 
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	s = allocate_cmdlines_buffer(val);
 	if (!s)
 		return -ENOMEM;
 
-	if (allocate_cmdlines_buffer(val, s) < 0) {
-		kfree(s);
-		return -ENOMEM;
-	}
-
 	preempt_disable();
 	arch_spin_lock(&trace_cmdline_lock);
 	savedcmd_temp = savedcmd;
@@ -6946,8 +6956,8 @@ waitagain:
 		goto out;
 	}
 
-	if (cnt >= PAGE_SIZE)
-		cnt = PAGE_SIZE - 1;
+	if (cnt >= TRACE_SEQ_BUFFER_SIZE)
+		cnt = TRACE_SEQ_BUFFER_SIZE - 1;
 
 	/* reset all but tr, trace, and overruns */
 	trace_iterator_reset(iter);
@@ -7283,6 +7293,8 @@ tracing_free_buffer_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+#define TRACE_MARKER_MAX_SIZE		4096
+
 static ssize_t
 tracing_mark_write(struct file *filp, const char __user *ubuf,
 					size_t cnt, loff_t *fpos)
@@ -7292,8 +7304,9 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	enum event_trigger_type tt = ETT_NONE;
 	struct trace_buffer *buffer;
 	struct print_entry *entry;
+	int meta_size;
 	ssize_t written;
-	int size;
+	size_t size;
 	int len;
 
 /* Used in tracing_mark_raw_write() as well */
@@ -7306,12 +7319,15 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	if (!(tr->trace_flags & TRACE_ITER_MARKERS))
 		return -EINVAL;
 
-	if (cnt > TRACE_BUF_SIZE)
-		cnt = TRACE_BUF_SIZE;
+	if ((ssize_t)cnt < 0)
+		return -EINVAL;
 
-	BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE);
+	if (cnt > TRACE_MARKER_MAX_SIZE)
+		cnt = TRACE_MARKER_MAX_SIZE;
 
-	size = sizeof(*entry) + cnt + 2; /* add '\0' and possible '\n' */
+	meta_size = sizeof(*entry) + 2;  /* add '\0' and possible '\n' */
+ again:
+	size = cnt + meta_size;
 
 	/* If less than "<faulted>", then make sure we can still add that */
 	if (cnt < FAULTED_SIZE)
@@ -7320,9 +7336,25 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	buffer = tr->array_buffer.buffer;
 	event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
 					    tracing_gen_ctx());
-	if (unlikely(!event))
+	if (unlikely(!event)) {
+		/*
+		 * If the size was greater than what was allowed, then
+		 * make it smaller and try again.
+		 */
+		if (size > ring_buffer_max_event_size(buffer)) {
+			/* cnt < FAULTED size should never be bigger than max */
+			if (WARN_ON_ONCE(cnt < FAULTED_SIZE))
+				return -EBADF;
+			cnt = ring_buffer_max_event_size(buffer) - meta_size;
+			/* The above should only happen once */
+			if (WARN_ON_ONCE(cnt + meta_size == size))
+				return -EBADF;
+			goto again;
+		}
+
 		/* Ring buffer disabled, return as if not open for write */
 		return -EBADF;
+	}
 
 	entry = ring_buffer_event_data(event);
 	entry->ip = _THIS_IP_;
@@ -7357,9 +7389,6 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	return written;
 }
 
-/* Limit it for now to 3K (including tag) */
-#define RAW_DATA_MAX_SIZE (1024*3)
-
 static ssize_t
 tracing_mark_raw_write(struct file *filp, const char __user *ubuf,
 					size_t cnt, loff_t *fpos)
@@ -7381,19 +7410,18 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf,
 		return -EINVAL;
 
 	/* The marker must at least have a tag id */
-	if (cnt < sizeof(unsigned int) || cnt > RAW_DATA_MAX_SIZE)
+	if (cnt < sizeof(unsigned int))
 		return -EINVAL;
 
-	if (cnt > TRACE_BUF_SIZE)
-		cnt = TRACE_BUF_SIZE;
-
-	BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE);
-
 	size = sizeof(*entry) + cnt;
 	if (cnt < FAULT_SIZE_ID)
 		size += FAULT_SIZE_ID - cnt;
 
 	buffer = tr->array_buffer.buffer;
+
+	if (size > ring_buffer_max_event_size(buffer))
+		return -EINVAL;
+
 	event = __trace_buffer_lock_reserve(buffer, TRACE_RAW_DATA, size,
 					    tracing_gen_ctx());
 	if (!event)
@@ -7578,6 +7606,7 @@ struct ftrace_buffer_info {
 	struct trace_iterator	iter;
 	void			*spare;
 	unsigned int		spare_cpu;
+	unsigned int		spare_size;
 	unsigned int		read;
 };
 
@@ -8282,6 +8311,8 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 {
 	struct ftrace_buffer_info *info = filp->private_data;
 	struct trace_iterator *iter = &info->iter;
+	void *trace_data;
+	int page_size;
 	ssize_t ret = 0;
 	ssize_t size;
 
@@ -8293,6 +8324,17 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 		return -EBUSY;
 #endif
 
+	page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer);
+
+	/* Make sure the spare matches the current sub buffer size */
+	if (info->spare) {
+		if (page_size != info->spare_size) {
+			ring_buffer_free_read_page(iter->array_buffer->buffer,
+						   info->spare_cpu, info->spare);
+			info->spare = NULL;
+		}
+	}
+
 	if (!info->spare) {
 		info->spare = ring_buffer_alloc_read_page(iter->array_buffer->buffer,
 							  iter->cpu_file);
@@ -8301,19 +8343,20 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 			info->spare = NULL;
 		} else {
 			info->spare_cpu = iter->cpu_file;
+			info->spare_size = page_size;
 		}
 	}
 	if (!info->spare)
 		return ret;
 
 	/* Do we have previous read data to read? */
-	if (info->read < PAGE_SIZE)
+	if (info->read < page_size)
 		goto read;
 
  again:
 	trace_access_lock(iter->cpu_file);
 	ret = ring_buffer_read_page(iter->array_buffer->buffer,
-				    &info->spare,
+				    info->spare,
 				    count,
 				    iter->cpu_file, 0);
 	trace_access_unlock(iter->cpu_file);
@@ -8334,11 +8377,11 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 
 	info->read = 0;
  read:
-	size = PAGE_SIZE - info->read;
+	size = page_size - info->read;
 	if (size > count)
 		size = count;
-
-	ret = copy_to_user(ubuf, info->spare + info->read, size);
+	trace_data = ring_buffer_read_page_data(info->spare);
+	ret = copy_to_user(ubuf, trace_data + info->read, size);
 	if (ret == size)
 		return -EFAULT;
 
@@ -8350,6 +8393,20 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 	return size;
 }
 
+static int tracing_buffers_flush(struct file *file, fl_owner_t id)
+{
+	struct ftrace_buffer_info *info = file->private_data;
+	struct trace_iterator *iter = &info->iter;
+
+	iter->wait_index++;
+	/* Make sure the waiters see the new wait_index */
+	smp_wmb();
+
+	ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file);
+
+	return 0;
+}
+
 static int tracing_buffers_release(struct inode *inode, struct file *file)
 {
 	struct ftrace_buffer_info *info = file->private_data;
@@ -8361,12 +8418,6 @@ static int tracing_buffers_release(struct inode *inode, struct file *file)
 
 	__trace_array_put(iter->tr);
 
-	iter->wait_index++;
-	/* Make sure the waiters see the new wait_index */
-	smp_wmb();
-
-	ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file);
-
 	if (info->spare)
 		ring_buffer_free_read_page(iter->array_buffer->buffer,
 					   info->spare_cpu, info->spare);
@@ -8449,6 +8500,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		.spd_release	= buffer_spd_release,
 	};
 	struct buffer_ref *ref;
+	int page_size;
 	int entries, i;
 	ssize_t ret = 0;
 
@@ -8457,13 +8509,14 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		return -EBUSY;
 #endif
 
-	if (*ppos & (PAGE_SIZE - 1))
+	page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer);
+	if (*ppos & (page_size - 1))
 		return -EINVAL;
 
-	if (len & (PAGE_SIZE - 1)) {
-		if (len < PAGE_SIZE)
+	if (len & (page_size - 1)) {
+		if (len < page_size)
 			return -EINVAL;
-		len &= PAGE_MASK;
+		len &= (~(page_size - 1));
 	}
 
 	if (splice_grow_spd(pipe, &spd))
@@ -8473,7 +8526,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 	trace_access_lock(iter->cpu_file);
 	entries = ring_buffer_entries_cpu(iter->array_buffer->buffer, iter->cpu_file);
 
-	for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= PAGE_SIZE) {
+	for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= page_size) {
 		struct page *page;
 		int r;
 
@@ -8494,7 +8547,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		}
 		ref->cpu = iter->cpu_file;
 
-		r = ring_buffer_read_page(ref->buffer, &ref->page,
+		r = ring_buffer_read_page(ref->buffer, ref->page,
 					  len, iter->cpu_file, 1);
 		if (r < 0) {
 			ring_buffer_free_read_page(ref->buffer, ref->cpu,
@@ -8503,14 +8556,14 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 			break;
 		}
 
-		page = virt_to_page(ref->page);
+		page = virt_to_page(ring_buffer_read_page_data(ref->page));
 
 		spd.pages[i] = page;
-		spd.partial[i].len = PAGE_SIZE;
+		spd.partial[i].len = page_size;
 		spd.partial[i].offset = 0;
 		spd.partial[i].private = (unsigned long)ref;
 		spd.nr_pages++;
-		*ppos += PAGE_SIZE;
+		*ppos += page_size;
 
 		entries = ring_buffer_entries_cpu(iter->array_buffer->buffer, iter->cpu_file);
 	}
@@ -8580,6 +8633,7 @@ static const struct file_operations tracing_buffers_fops = {
 	.read		= tracing_buffers_read,
 	.poll		= tracing_buffers_poll,
 	.release	= tracing_buffers_release,
+	.flush		= tracing_buffers_flush,
 	.splice_read	= tracing_buffers_splice_read,
 	.unlocked_ioctl = tracing_buffers_ioctl,
 	.llseek		= no_llseek,
@@ -9354,6 +9408,103 @@ static const struct file_operations buffer_percent_fops = {
 	.llseek		= default_llseek,
 };
 
+static ssize_t
+buffer_subbuf_size_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+	struct trace_array *tr = filp->private_data;
+	size_t size;
+	char buf[64];
+	int order;
+	int r;
+
+	order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer);
+	size = (PAGE_SIZE << order) / 1024;
+
+	r = sprintf(buf, "%zd\n", size);
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+buffer_subbuf_size_write(struct file *filp, const char __user *ubuf,
+			 size_t cnt, loff_t *ppos)
+{
+	struct trace_array *tr = filp->private_data;
+	unsigned long val;
+	int old_order;
+	int order;
+	int pages;
+	int ret;
+
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
+		return ret;
+
+	val *= 1024; /* value passed in is in KB */
+
+	pages = DIV_ROUND_UP(val, PAGE_SIZE);
+	order = fls(pages - 1);
+
+	/* limit between 1 and 128 system pages */
+	if (order < 0 || order > 7)
+		return -EINVAL;
+
+	/* Do not allow tracing while changing the order of the ring buffer */
+	tracing_stop_tr(tr);
+
+	old_order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer);
+	if (old_order == order)
+		goto out;
+
+	ret = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, order);
+	if (ret)
+		goto out;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+
+	if (!tr->allocated_snapshot)
+		goto out_max;
+
+	ret = ring_buffer_subbuf_order_set(tr->max_buffer.buffer, order);
+	if (ret) {
+		/* Put back the old order */
+		cnt = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, old_order);
+		if (WARN_ON_ONCE(cnt)) {
+			/*
+			 * AARGH! We are left with different orders!
+			 * The max buffer is our "snapshot" buffer.
+			 * When a tracer needs a snapshot (one of the
+			 * latency tracers), it swaps the max buffer
+			 * with the saved snap shot. We succeeded to
+			 * update the order of the main buffer, but failed to
+			 * update the order of the max buffer. But when we tried
+			 * to reset the main buffer to the original size, we
+			 * failed there too. This is very unlikely to
+			 * happen, but if it does, warn and kill all
+			 * tracing.
+			 */
+			tracing_disabled = 1;
+		}
+		goto out;
+	}
+ out_max:
+#endif
+	(*ppos)++;
+ out:
+	if (ret)
+		cnt = ret;
+	tracing_start_tr(tr);
+	return cnt;
+}
+
+static const struct file_operations buffer_subbuf_size_fops = {
+	.open		= tracing_open_generic_tr,
+	.read		= buffer_subbuf_size_read,
+	.write		= buffer_subbuf_size_write,
+	.release	= tracing_release_generic_tr,
+	.llseek		= default_llseek,
+};
+
 static struct dentry *trace_instance_dir;
 
 static void
@@ -9504,7 +9655,8 @@ static int trace_array_create_dir(struct trace_array *tr)
 	return ret;
 }
 
-static struct trace_array *trace_array_create(const char *name)
+static struct trace_array *
+trace_array_create_systems(const char *name, const char *systems)
 {
 	struct trace_array *tr;
 	int ret;
@@ -9524,6 +9676,12 @@ static struct trace_array *trace_array_create(const char *name)
 	if (!zalloc_cpumask_var(&tr->pipe_cpumask, GFP_KERNEL))
 		goto out_free_tr;
 
+	if (systems) {
+		tr->system_names = kstrdup_const(systems, GFP_KERNEL);
+		if (!tr->system_names)
+			goto out_free_tr;
+	}
+
 	tr->trace_flags = global_trace.trace_flags & ~ZEROED_TRACE_FLAGS;
 
 	cpumask_copy(tr->tracing_cpumask, cpu_all_mask);
@@ -9570,12 +9728,18 @@ static struct trace_array *trace_array_create(const char *name)
 	free_trace_buffers(tr);
 	free_cpumask_var(tr->pipe_cpumask);
 	free_cpumask_var(tr->tracing_cpumask);
+	kfree_const(tr->system_names);
 	kfree(tr->name);
 	kfree(tr);
 
 	return ERR_PTR(ret);
 }
 
+static struct trace_array *trace_array_create(const char *name)
+{
+	return trace_array_create_systems(name, NULL);
+}
+
 static int instance_mkdir(const char *name)
 {
 	struct trace_array *tr;
@@ -9601,6 +9765,7 @@ out_unlock:
 /**
  * trace_array_get_by_name - Create/Lookup a trace array, given its name.
  * @name: The name of the trace array to be looked up/created.
+ * @systems: A list of systems to create event directories for (NULL for all)
  *
  * Returns pointer to trace array with given name.
  * NULL, if it cannot be created.
@@ -9614,7 +9779,7 @@ out_unlock:
  * trace_array_put() is called, user space can not delete it.
  *
  */
-struct trace_array *trace_array_get_by_name(const char *name)
+struct trace_array *trace_array_get_by_name(const char *name, const char *systems)
 {
 	struct trace_array *tr;
 
@@ -9626,7 +9791,7 @@ struct trace_array *trace_array_get_by_name(const char *name)
 			goto out_unlock;
 	}
 
-	tr = trace_array_create(name);
+	tr = trace_array_create_systems(name, systems);
 
 	if (IS_ERR(tr))
 		tr = NULL;
@@ -9673,6 +9838,7 @@ static int __remove_instance(struct trace_array *tr)
 
 	free_cpumask_var(tr->pipe_cpumask);
 	free_cpumask_var(tr->tracing_cpumask);
+	kfree_const(tr->system_names);
 	kfree(tr->name);
 	kfree(tr);
 
@@ -9805,6 +9971,9 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 	trace_create_file("buffer_percent", TRACE_MODE_WRITE, d_tracer,
 			tr, &buffer_percent_fops);
 
+	trace_create_file("buffer_subbuf_size_kb", TRACE_MODE_WRITE, d_tracer,
+			  tr, &buffer_subbuf_size_fops);
+
 	create_trace_options_dir(tr);
 
 #ifdef CONFIG_TRACER_MAX_TRACE
@@ -10391,7 +10560,7 @@ __init static void enable_instances(void)
 		if (IS_ENABLED(CONFIG_TRACER_MAX_TRACE))
 			do_allocate_snapshot(tok);
 
-		tr = trace_array_get_by_name(tok);
+		tr = trace_array_get_by_name(tok, NULL);
 		if (!tr) {
 			pr_warn("Failed to create instance buffer %s\n", curr_str);
 			continue;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 0489e72c8169..00f873910c5d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -377,6 +377,7 @@ struct trace_array {
 	unsigned char		trace_flags_index[TRACE_FLAGS_MAX_SIZE];
 	unsigned int		flags;
 	raw_spinlock_t		start_lock;
+	const char		*system_names;
 	struct list_head	err_log;
 	struct dentry		*dir;
 	struct dentry		*options;
@@ -615,6 +616,7 @@ void tracing_reset_all_online_cpus(void);
 void tracing_reset_all_online_cpus_unlocked(void);
 int tracing_open_generic(struct inode *inode, struct file *filp);
 int tracing_open_generic_tr(struct inode *inode, struct file *filp);
+int tracing_release_generic_tr(struct inode *inode, struct file *file);
 int tracing_open_file_tr(struct inode *inode, struct file *filp);
 int tracing_release_file_tr(struct inode *inode, struct file *filp);
 int tracing_single_release_file_tr(struct inode *inode, struct file *filp);
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 7ccc7a8e155b..dbe29b4c6a7a 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -633,7 +633,7 @@ trace_boot_init_instances(struct xbc_node *node)
 		if (!p || *p == '\0')
 			continue;
 
-		tr = trace_array_get_by_name(p);
+		tr = trace_array_get_by_name(p, NULL);
 		if (!tr) {
 			pr_err("Failed to get trace instance %s\n", p);
 			continue;
diff --git a/kernel/trace/trace_btf.c b/kernel/trace/trace_btf.c
index ca224d53bfdc..5bbdbcbbde3c 100644
--- a/kernel/trace/trace_btf.c
+++ b/kernel/trace/trace_btf.c
@@ -91,8 +91,8 @@ retry:
 	for_each_member(i, type, member) {
 		if (!member->name_off) {
 			/* Anonymous union/struct: push it for later use */
-			type = btf_type_skip_modifiers(btf, member->type, &tid);
-			if (type && top < BTF_ANON_STACK_MAX) {
+			if (btf_type_skip_modifiers(btf, member->type, &tid) &&
+			    top < BTF_ANON_STACK_MAX) {
 				anon_stack[top].tid = tid;
 				anon_stack[top++].offset =
 					cur_offset + member->offset;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f29e815ca5b2..7c364b87352e 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1893,9 +1893,9 @@ subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 }
 
 static ssize_t
-show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+show_header_page_file(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
 {
-	int (*func)(struct trace_seq *s) = filp->private_data;
+	struct trace_array *tr = filp->private_data;
 	struct trace_seq *s;
 	int r;
 
@@ -1908,7 +1908,31 @@ show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
 
 	trace_seq_init(s);
 
-	func(s);
+	ring_buffer_print_page_header(tr->array_buffer.buffer, s);
+	r = simple_read_from_buffer(ubuf, cnt, ppos,
+				    s->buffer, trace_seq_used(s));
+
+	kfree(s);
+
+	return r;
+}
+
+static ssize_t
+show_header_event_file(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+	struct trace_seq *s;
+	int r;
+
+	if (*ppos)
+		return 0;
+
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	trace_seq_init(s);
+
+	ring_buffer_print_entry_header(s);
 	r = simple_read_from_buffer(ubuf, cnt, ppos,
 				    s->buffer, trace_seq_used(s));
 
@@ -2165,10 +2189,18 @@ static const struct file_operations ftrace_tr_enable_fops = {
 	.release = subsystem_release,
 };
 
-static const struct file_operations ftrace_show_header_fops = {
-	.open = tracing_open_generic,
-	.read = show_header,
+static const struct file_operations ftrace_show_header_page_fops = {
+	.open = tracing_open_generic_tr,
+	.read = show_header_page_file,
+	.llseek = default_llseek,
+	.release = tracing_release_generic_tr,
+};
+
+static const struct file_operations ftrace_show_header_event_fops = {
+	.open = tracing_open_generic_tr,
+	.read = show_header_event_file,
 	.llseek = default_llseek,
+	.release = tracing_release_generic_tr,
 };
 
 static int
@@ -2896,6 +2928,27 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
 	up_write(&trace_event_sem);
 }
 
+static bool event_in_systems(struct trace_event_call *call,
+			     const char *systems)
+{
+	const char *system;
+	const char *p;
+
+	if (!systems)
+		return true;
+
+	system = call->class->system;
+	p = strstr(systems, system);
+	if (!p)
+		return false;
+
+	if (p != systems && !isspace(*(p - 1)) && *(p - 1) != ',')
+		return false;
+
+	p += strlen(system);
+	return !*p || isspace(*p) || *p == ',';
+}
+
 static struct trace_event_file *
 trace_create_new_event(struct trace_event_call *call,
 		       struct trace_array *tr)
@@ -2905,9 +2958,12 @@ trace_create_new_event(struct trace_event_call *call,
 	struct trace_event_file *file;
 	unsigned int first;
 
+	if (!event_in_systems(call, tr->system_names))
+		return NULL;
+
 	file = kmem_cache_alloc(file_cachep, GFP_TRACE);
 	if (!file)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	pid_list = rcu_dereference_protected(tr->filtered_pids,
 					     lockdep_is_held(&event_mutex));
@@ -2972,8 +3028,17 @@ __trace_add_new_event(struct trace_event_call *call, struct trace_array *tr)
 	struct trace_event_file *file;
 
 	file = trace_create_new_event(call, tr);
+	/*
+	 * trace_create_new_event() returns ERR_PTR(-ENOMEM) if failed
+	 * allocation, or NULL if the event is not part of the tr->system_names.
+	 * When the event is not part of the tr->system_names, return zero, not
+	 * an error.
+	 */
 	if (!file)
-		return -ENOMEM;
+		return 0;
+
+	if (IS_ERR(file))
+		return PTR_ERR(file);
 
 	if (eventdir_initialized)
 		return event_create_dir(tr->event_dir, file);
@@ -3012,8 +3077,17 @@ __trace_early_add_new_event(struct trace_event_call *call,
 	int ret;
 
 	file = trace_create_new_event(call, tr);
+	/*
+	 * trace_create_new_event() returns ERR_PTR(-ENOMEM) if failed
+	 * allocation, or NULL if the event is not part of the tr->system_names.
+	 * When the event is not part of the tr->system_names, return zero, not
+	 * an error.
+	 */
 	if (!file)
-		return -ENOMEM;
+		return 0;
+
+	if (IS_ERR(file))
+		return PTR_ERR(file);
 
 	ret = event_define_fields(call);
 	if (ret)
@@ -3752,17 +3826,16 @@ static int events_callback(const char *name, umode_t *mode, void **data,
 		return 1;
 	}
 
-	if (strcmp(name, "header_page") == 0)
-		*data = ring_buffer_print_page_header;
-
-	else if (strcmp(name, "header_event") == 0)
-		*data = ring_buffer_print_entry_header;
+	if (strcmp(name, "header_page") == 0) {
+		*mode = TRACE_MODE_READ;
+		*fops = &ftrace_show_header_page_fops;
 
-	else
+	} else if (strcmp(name, "header_event") == 0) {
+		*mode = TRACE_MODE_READ;
+		*fops = &ftrace_show_header_event_fops;
+	} else
 		return 0;
 
-	*mode = TRACE_MODE_READ;
-	*fops = &ftrace_show_header_fops;
 	return 1;
 }
 
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 5ecf3c8bde20..6ece1308d36a 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -4805,36 +4805,35 @@ static int parse_actions(struct hist_trigger_data *hist_data)
 	int len;
 
 	for (i = 0; i < hist_data->attrs->n_actions; i++) {
+		enum handler_id hid = 0;
+		char *action_str;
+
 		str = hist_data->attrs->action_str[i];
 
-		if ((len = str_has_prefix(str, "onmatch("))) {
-			char *action_str = str + len;
+		if ((len = str_has_prefix(str, "onmatch(")))
+			hid = HANDLER_ONMATCH;
+		else if ((len = str_has_prefix(str, "onmax(")))
+			hid = HANDLER_ONMAX;
+		else if ((len = str_has_prefix(str, "onchange(")))
+			hid = HANDLER_ONCHANGE;
 
-			data = onmatch_parse(tr, action_str);
-			if (IS_ERR(data)) {
-				ret = PTR_ERR(data);
-				break;
-			}
-		} else if ((len = str_has_prefix(str, "onmax("))) {
-			char *action_str = str + len;
+		action_str = str + len;
 
-			data = track_data_parse(hist_data, action_str,
-						HANDLER_ONMAX);
-			if (IS_ERR(data)) {
-				ret = PTR_ERR(data);
-				break;
-			}
-		} else if ((len = str_has_prefix(str, "onchange("))) {
-			char *action_str = str + len;
+		switch (hid) {
+		case HANDLER_ONMATCH:
+			data = onmatch_parse(tr, action_str);
+			break;
+		case HANDLER_ONMAX:
+		case HANDLER_ONCHANGE:
+			data = track_data_parse(hist_data, action_str, hid);
+			break;
+		default:
+			data = ERR_PTR(-EINVAL);
+			break;
+		}
 
-			data = track_data_parse(hist_data, action_str,
-						HANDLER_ONCHANGE);
-			if (IS_ERR(data)) {
-				ret = PTR_ERR(data);
-				break;
-			}
-		} else {
-			ret = -EINVAL;
+		if (IS_ERR(data)) {
+			ret = PTR_ERR(data);
 			break;
 		}
 
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index e7af286af4f1..c82b401a294d 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -441,8 +441,9 @@ static unsigned int trace_string(struct synth_trace_event *entry,
 	if (is_dynamic) {
 		union trace_synth_field *data = &entry->fields[*n_u64];
 
+		len = fetch_store_strlen((unsigned long)str_val);
 		data->as_dynamic.offset = struct_size(entry, fields, event->n_u64) + data_size;
-		data->as_dynamic.len = fetch_store_strlen((unsigned long)str_val);
+		data->as_dynamic.len = len;
 
 		ret = fetch_store_string((unsigned long)str_val, &entry->fields[*n_u64], entry);
 
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 46439e3bcec4..b33c3861fbbb 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -1470,8 +1470,10 @@ register_snapshot_trigger(char *glob,
 			  struct event_trigger_data *data,
 			  struct trace_event_file *file)
 {
-	if (tracing_alloc_snapshot_instance(file->tr) != 0)
-		return 0;
+	int ret = tracing_alloc_snapshot_instance(file->tr);
+
+	if (ret < 0)
+		return ret;
 
 	return register_trigger(glob, data, file);
 }
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 52f8b537dd0a..c4c6e0e0068b 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -487,8 +487,8 @@ static int __register_trace_kprobe(struct trace_kprobe *tk)
 		return -EINVAL;
 
 	if (within_notrace_func(tk)) {
-		pr_warn("Could not probe notrace function %s\n",
-			trace_kprobe_symbol(tk));
+		pr_warn("Could not probe notrace function %ps\n",
+			(void *)trace_kprobe_address(tk));
 		return -EINVAL;
 	}
 
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index bd0d01d00fb9..a8e28f9b9271 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -2444,6 +2444,9 @@ static int timerlat_fd_open(struct inode *inode, struct file *file)
 	tlat = this_cpu_tmr_var();
 	tlat->count = 0;
 
+	hrtimer_init(&tlat->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
+	tlat->timer.function = timerlat_irq;
+
 	migrate_enable();
 	return 0;
 };
@@ -2526,9 +2529,6 @@ timerlat_fd_read(struct file *file, char __user *ubuf, size_t count,
 		tlat->tracing_thread = false;
 		tlat->kthread = current;
 
-		hrtimer_init(&tlat->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
-		tlat->timer.function = timerlat_irq;
-
 		/* Annotate now to drift new period */
 		tlat->abs_period = hrtimer_cb_get_time(&tlat->timer);
 
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 3e7fa44dc2b2..d8b302d01083 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1587,12 +1587,11 @@ static enum print_line_t trace_print_print(struct trace_iterator *iter,
 {
 	struct print_entry *field;
 	struct trace_seq *s = &iter->seq;
-	int max = iter->ent_size - offsetof(struct print_entry, buf);
 
 	trace_assign_type(field, iter->ent);
 
 	seq_print_ip_sym(s, field->ip, flags);
-	trace_seq_printf(s, ": %.*s", max, field->buf);
+	trace_seq_printf(s, ": %s", field->buf);
 
 	return trace_handle_return(s);
 }
@@ -1601,11 +1600,10 @@ static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags,
 					 struct trace_event *event)
 {
 	struct print_entry *field;
-	int max = iter->ent_size - offsetof(struct print_entry, buf);
 
 	trace_assign_type(field, iter->ent);
 
-	trace_seq_printf(&iter->seq, "# %lx %.*s", field->ip, max, field->buf);
+	trace_seq_printf(&iter->seq, "# %lx %s", field->ip, field->buf);
 
 	return trace_handle_return(&iter->seq);
 }
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 4dc74d73fc1d..34289f9c6707 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -1159,9 +1159,12 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
 	if (!(ctx->flags & TPARG_FL_TEVENT) &&
 	    (strcmp(arg, "$comm") == 0 || strcmp(arg, "$COMM") == 0 ||
 	     strncmp(arg, "\\\"", 2) == 0)) {
-		/* The type of $comm must be "string", and not an array. */
-		if (parg->count || (t && strcmp(t, "string")))
+		/* The type of $comm must be "string", and not an array type. */
+		if (parg->count || (t && strcmp(t, "string"))) {
+			trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0),
+					NEED_STRING_TYPE);
 			goto out;
+		}
 		parg->type = find_fetch_type("string", ctx->flags);
 	} else
 		parg->type = find_fetch_type(t, ctx->flags);
@@ -1169,18 +1172,6 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
 		trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0), BAD_TYPE);
 		goto out;
 	}
-	parg->offset = *size;
-	*size += parg->type->size * (parg->count ?: 1);
-
-	ret = -ENOMEM;
-	if (parg->count) {
-		len = strlen(parg->type->fmttype) + 6;
-		parg->fmt = kmalloc(len, GFP_KERNEL);
-		if (!parg->fmt)
-			goto out;
-		snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype,
-			 parg->count);
-	}
 
 	code = tmp = kcalloc(FETCH_INSN_MAX, sizeof(*code), GFP_KERNEL);
 	if (!code)
@@ -1204,6 +1195,19 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
 				goto fail;
 		}
 	}
+	parg->offset = *size;
+	*size += parg->type->size * (parg->count ?: 1);
+
+	if (parg->count) {
+		len = strlen(parg->type->fmttype) + 6;
+		parg->fmt = kmalloc(len, GFP_KERNEL);
+		if (!parg->fmt) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype,
+			 parg->count);
+	}
 
 	ret = -EINVAL;
 	/* Store operation */
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 850d9ecb6765..c1877d018269 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -515,7 +515,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
 	C(BAD_HYPHEN,		"Failed to parse single hyphen. Forgot '>'?"),	\
 	C(NO_BTF_FIELD,		"This field is not found."),	\
 	C(BAD_BTF_TID,		"Failed to get BTF type info."),\
-	C(BAD_TYPE4STR,		"This type does not fit for string."),
+	C(BAD_TYPE4STR,		"This type does not fit for string."),\
+	C(NEED_STRING_TYPE,	"$comm and immediate-string only accepts string type"),
 
 #undef C
 #define C(a, b)		TP_ERR_##a
diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c
index 7be97229ddf8..c158d65a8a88 100644
--- a/kernel/trace/trace_seq.c
+++ b/kernel/trace/trace_seq.c
@@ -13,9 +13,6 @@
  * trace_seq_init() more than once to reset the trace_seq to start
  * from scratch.
  * 
- * The buffer size is currently PAGE_SIZE, although it may become dynamic
- * in the future.
- *
  * A write to the buffer will either succeed or fail. That is, unlike
  * sprintf() there will not be a partial write (well it may write into
  * the buffer but it wont update the pointers). This allows users to
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index c774e560f2f9..a4dcf0f24352 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -574,7 +574,12 @@ __tracing_map_insert(struct tracing_map *map, void *key, bool lookup_only)
 				}
 
 				memcpy(elt->key, key, map->key_size);
-				entry->val = elt;
+				/*
+				 * Ensure the initialization is visible and
+				 * publish the elt.
+				 */
+				smp_wmb();
+				WRITE_ONCE(entry->val, elt);
 				atomic64_inc(&map->hits);
 
 				return entry->val;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 68c48489eab3..a60eb65955e7 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -54,6 +54,7 @@
 #include <linux/nmi.h>
 #include <linux/kvm_para.h>
 #include <linux/delay.h>
+#include <linux/irq_work.h>
 
 #include "workqueue_internal.h"
 
@@ -80,6 +81,7 @@ enum worker_pool_flags {
 	POOL_BH			= 1 << 0,	/* is a BH pool */
 	POOL_MANAGER_ACTIVE	= 1 << 1,	/* being managed */
 	POOL_DISASSOCIATED	= 1 << 2,	/* cpu can't serve workers */
+	POOL_BH_DRAINING	= 1 << 3,	/* draining after CPU offline */
 };
 
 enum worker_flags {
@@ -95,6 +97,10 @@ enum worker_flags {
 				  WORKER_UNBOUND | WORKER_REBOUND,
 };
 
+enum work_cancel_flags {
+	WORK_CANCEL_DELAYED	= 1 << 0,	/* canceling a delayed_work */
+};
+
 enum wq_internal_consts {
 	NR_STD_WORKER_POOLS	= 2,		/* # standard pools per cpu */
 
@@ -242,7 +248,7 @@ enum pool_workqueue_stats {
 };
 
 /*
- * The per-pool workqueue.  While queued, the lower WORK_STRUCT_FLAG_BITS
+ * The per-pool workqueue.  While queued, bits below WORK_PWQ_SHIFT
  * of work_struct->data are used for flags and the remaining high bits
  * point to the pwq; thus, pwqs need to be aligned at two's power of the
  * number of flag bits.
@@ -255,6 +261,7 @@ struct pool_workqueue {
 	int			refcnt;		/* L: reference count */
 	int			nr_in_flight[WORK_NR_COLORS];
 						/* L: nr of in_flight works */
+	bool			plugged;	/* L: execution suspended */
 
 	/*
 	 * nr_active management and WORK_STRUCT_INACTIVE:
@@ -288,7 +295,7 @@ struct pool_workqueue {
 	 */
 	struct kthread_work	release_work;
 	struct rcu_head		rcu;
-} __aligned(1 << WORK_STRUCT_FLAG_BITS);
+} __aligned(1 << WORK_STRUCT_PWQ_SHIFT);
 
 /*
  * Structure used to wait for workqueue flush.
@@ -374,8 +381,6 @@ struct workqueue_struct {
 	struct wq_node_nr_active *node_nr_active[]; /* I: per-node nr_active */
 };
 
-static struct kmem_cache *pwq_cache;
-
 /*
  * Each pod type describes how CPUs should be grouped for unbound workqueues.
  * See the comment above workqueue_attrs->affn_scope.
@@ -387,20 +392,15 @@ struct wq_pod_type {
 	int			*cpu_pod;	/* cpu -> pod */
 };
 
-static struct wq_pod_type wq_pod_types[WQ_AFFN_NR_TYPES];
-static enum wq_affn_scope wq_affn_dfl = WQ_AFFN_CACHE;
-
 static const char *wq_affn_names[WQ_AFFN_NR_TYPES] = {
-	[WQ_AFFN_DFL]			= "default",
-	[WQ_AFFN_CPU]			= "cpu",
-	[WQ_AFFN_SMT]			= "smt",
-	[WQ_AFFN_CACHE]			= "cache",
-	[WQ_AFFN_NUMA]			= "numa",
-	[WQ_AFFN_SYSTEM]		= "system",
+	[WQ_AFFN_DFL]		= "default",
+	[WQ_AFFN_CPU]		= "cpu",
+	[WQ_AFFN_SMT]		= "smt",
+	[WQ_AFFN_CACHE]		= "cache",
+	[WQ_AFFN_NUMA]		= "numa",
+	[WQ_AFFN_SYSTEM]	= "system",
 };
 
-static bool wq_topo_initialized __read_mostly = false;
-
 /*
  * Per-cpu work items which run for longer than the following threshold are
  * automatically considered CPU intensive and excluded from concurrency
@@ -410,12 +410,22 @@ static bool wq_topo_initialized __read_mostly = false;
  */
 static unsigned long wq_cpu_intensive_thresh_us = ULONG_MAX;
 module_param_named(cpu_intensive_thresh_us, wq_cpu_intensive_thresh_us, ulong, 0644);
+#ifdef CONFIG_WQ_CPU_INTENSIVE_REPORT
+static unsigned int wq_cpu_intensive_warning_thresh = 4;
+module_param_named(cpu_intensive_warning_thresh, wq_cpu_intensive_warning_thresh, uint, 0644);
+#endif
 
 /* see the comment above the definition of WQ_POWER_EFFICIENT */
 static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT);
 module_param_named(power_efficient, wq_power_efficient, bool, 0444);
 
 static bool wq_online;			/* can kworkers be created yet? */
+static bool wq_topo_initialized __read_mostly = false;
+
+static struct kmem_cache *pwq_cache;
+
+static struct wq_pod_type wq_pod_types[WQ_AFFN_NR_TYPES];
+static enum wq_affn_scope wq_affn_dfl = WQ_AFFN_CACHE;
 
 /* buf for wq_update_unbound_pod_attrs(), protected by CPU hotplug exclusion */
 static struct workqueue_attrs *wq_update_pod_attrs_buf;
@@ -456,6 +466,10 @@ static bool wq_debug_force_rr_cpu = false;
 #endif
 module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644);
 
+/* to raise softirq for the BH worker pools on other CPUs */
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_work [NR_STD_WORKER_POOLS],
+				     bh_pool_irq_works);
+
 /* the BH worker pools */
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS],
 				     bh_worker_pools);
@@ -476,6 +490,12 @@ static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS];
 static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS];
 
 /*
+ * Used to synchronize multiple cancel_sync attempts on the same work item. See
+ * work_grab_pending() and __cancel_work_sync().
+ */
+static DECLARE_WAIT_QUEUE_HEAD(wq_cancel_waitq);
+
+/*
  * I: kthread_worker to release pwq's. pwq release needs to be bounced to a
  * process context while holding a pool lock. Bounce to a dedicated kthread
  * worker to avoid A-A deadlocks.
@@ -510,12 +530,12 @@ static void show_one_worker_pool(struct worker_pool *pool);
 #include <trace/events/workqueue.h>
 
 #define assert_rcu_or_pool_mutex()					\
-	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
+	RCU_LOCKDEP_WARN(!rcu_read_lock_any_held() &&			\
 			 !lockdep_is_held(&wq_pool_mutex),		\
 			 "RCU or wq_pool_mutex should be held")
 
 #define assert_rcu_or_wq_mutex_or_pool_mutex(wq)			\
-	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
+	RCU_LOCKDEP_WARN(!rcu_read_lock_any_held() &&			\
 			 !lockdep_is_held(&wq->mutex) &&		\
 			 !lockdep_is_held(&wq_pool_mutex),		\
 			 "RCU, wq->mutex or wq_pool_mutex should be held")
@@ -748,10 +768,9 @@ static int work_next_color(int color)
  * contain the pointer to the queued pwq.  Once execution starts, the flag
  * is cleared and the high bits contain OFFQ flags and pool ID.
  *
- * set_work_pwq(), set_work_pool_and_clear_pending(), mark_work_canceling()
- * and clear_work_data() can be used to set the pwq, pool or clear
- * work->data.  These functions should only be called while the work is
- * owned - ie. while the PENDING bit is set.
+ * set_work_pwq(), set_work_pool_and_clear_pending() and mark_work_canceling()
+ * can be used to set the pwq, pool or clear work->data. These functions should
+ * only be called while the work is owned - ie. while the PENDING bit is set.
  *
  * get_work_pool() and get_work_pwq() can be used to obtain the pool or pwq
  * corresponding to a work.  Pool is available once the work has been
@@ -763,29 +782,28 @@ static int work_next_color(int color)
  * but stay off timer and worklist for arbitrarily long and nobody should
  * try to steal the PENDING bit.
  */
-static inline void set_work_data(struct work_struct *work, unsigned long data,
-				 unsigned long flags)
+static inline void set_work_data(struct work_struct *work, unsigned long data)
 {
 	WARN_ON_ONCE(!work_pending(work));
-	atomic_long_set(&work->data, data | flags | work_static(work));
+	atomic_long_set(&work->data, data | work_static(work));
 }
 
 static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq,
-			 unsigned long extra_flags)
+			 unsigned long flags)
 {
-	set_work_data(work, (unsigned long)pwq,
-		      WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | extra_flags);
+	set_work_data(work, (unsigned long)pwq | WORK_STRUCT_PENDING |
+		      WORK_STRUCT_PWQ | flags);
 }
 
 static void set_work_pool_and_keep_pending(struct work_struct *work,
-					   int pool_id)
+					   int pool_id, unsigned long flags)
 {
-	set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT,
-		      WORK_STRUCT_PENDING);
+	set_work_data(work, ((unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT) |
+		      WORK_STRUCT_PENDING | flags);
 }
 
 static void set_work_pool_and_clear_pending(struct work_struct *work,
-					    int pool_id)
+					    int pool_id, unsigned long flags)
 {
 	/*
 	 * The following wmb is paired with the implied mb in
@@ -794,7 +812,8 @@ static void set_work_pool_and_clear_pending(struct work_struct *work,
 	 * owner.
 	 */
 	smp_wmb();
-	set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, 0);
+	set_work_data(work, ((unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT) |
+		      flags);
 	/*
 	 * The following mb guarantees that previous clear of a PENDING bit
 	 * will not be reordered with any speculative LOADS or STORES from
@@ -826,15 +845,9 @@ static void set_work_pool_and_clear_pending(struct work_struct *work,
 	smp_mb();
 }
 
-static void clear_work_data(struct work_struct *work)
-{
-	smp_wmb();	/* see set_work_pool_and_clear_pending() */
-	set_work_data(work, WORK_STRUCT_NO_POOL, 0);
-}
-
 static inline struct pool_workqueue *work_struct_pwq(unsigned long data)
 {
-	return (struct pool_workqueue *)(data & WORK_STRUCT_WQ_DATA_MASK);
+	return (struct pool_workqueue *)(data & WORK_STRUCT_PWQ_MASK);
 }
 
 static struct pool_workqueue *get_work_pwq(struct work_struct *work)
@@ -901,7 +914,7 @@ static void mark_work_canceling(struct work_struct *work)
 	unsigned long pool_id = get_work_pool_id(work);
 
 	pool_id <<= WORK_OFFQ_POOL_SHIFT;
-	set_work_data(work, pool_id | WORK_OFFQ_CANCELING, WORK_STRUCT_PENDING);
+	set_work_data(work, pool_id | WORK_STRUCT_PENDING | WORK_OFFQ_CANCELING);
 }
 
 static bool work_is_canceling(struct work_struct *work)
@@ -1196,6 +1209,29 @@ static bool assign_work(struct work_struct *work, struct worker *worker,
 	return true;
 }
 
+static struct irq_work *bh_pool_irq_work(struct worker_pool *pool)
+{
+	int high = pool->attrs->nice == HIGHPRI_NICE_LEVEL ? 1 : 0;
+
+	return &per_cpu(bh_pool_irq_works, pool->cpu)[high];
+}
+
+static void kick_bh_pool(struct worker_pool *pool)
+{
+#ifdef CONFIG_SMP
+	/* see drain_dead_softirq_workfn() for BH_DRAINING */
+	if (unlikely(pool->cpu != smp_processor_id() &&
+		     !(pool->flags & POOL_BH_DRAINING))) {
+		irq_work_queue_on(bh_pool_irq_work(pool), pool->cpu);
+		return;
+	}
+#endif
+	if (pool->attrs->nice == HIGHPRI_NICE_LEVEL)
+		raise_softirq_irqoff(HI_SOFTIRQ);
+	else
+		raise_softirq_irqoff(TASKLET_SOFTIRQ);
+}
+
 /**
  * kick_pool - wake up an idle worker if necessary
  * @pool: pool to kick
@@ -1214,10 +1250,7 @@ static bool kick_pool(struct worker_pool *pool)
 		return false;
 
 	if (pool->flags & POOL_BH) {
-		if (pool->attrs->nice == HIGHPRI_NICE_LEVEL)
-			raise_softirq_irqoff(HI_SOFTIRQ);
-		else
-			raise_softirq_irqoff(TASKLET_SOFTIRQ);
+		kick_bh_pool(pool);
 		return true;
 	}
 
@@ -1301,11 +1334,13 @@ restart:
 		u64 cnt;
 
 		/*
-		 * Start reporting from the fourth time and back off
+		 * Start reporting from the warning_thresh and back off
 		 * exponentially.
 		 */
 		cnt = atomic64_inc_return_relaxed(&ent->cnt);
-		if (cnt >= 4 && is_power_of_2(cnt))
+		if (wq_cpu_intensive_warning_thresh &&
+		    cnt >= wq_cpu_intensive_warning_thresh &&
+		    is_power_of_2(cnt + 1 - wq_cpu_intensive_warning_thresh))
 			printk_deferred(KERN_WARNING "workqueue: %ps hogged CPU for >%luus %llu times, consider switching to WQ_UNBOUND\n",
 					ent->func, wq_cpu_intensive_thresh_us,
 					atomic64_read(&ent->cnt));
@@ -1334,10 +1369,12 @@ restart:
 
 	ent = &wci_ents[wci_nr_ents++];
 	ent->func = func;
-	atomic64_set(&ent->cnt, 1);
+	atomic64_set(&ent->cnt, 0);
 	hash_add_rcu(wci_hash, &ent->hash_node, (unsigned long)func);
 
 	raw_spin_unlock(&wci_lock);
+
+	goto restart;
 }
 
 #else	/* CONFIG_WQ_CPU_INTENSIVE_REPORT */
@@ -1708,6 +1745,9 @@ static bool pwq_tryinc_nr_active(struct pool_workqueue *pwq, bool fill)
 		goto out;
 	}
 
+	if (unlikely(pwq->plugged))
+		return false;
+
 	/*
 	 * Unbound workqueue uses per-node shared nr_active $nna. If @pwq is
 	 * already waiting on $nna, pwq_dec_nr_active() will maintain the
@@ -1783,6 +1823,46 @@ static bool pwq_activate_first_inactive(struct pool_workqueue *pwq, bool fill)
 }
 
 /**
+ * unplug_oldest_pwq - unplug the oldest pool_workqueue
+ * @wq: workqueue_struct where its oldest pwq is to be unplugged
+ *
+ * This function should only be called for ordered workqueues where only the
+ * oldest pwq is unplugged, the others are plugged to suspend execution to
+ * ensure proper work item ordering::
+ *
+ *    dfl_pwq --------------+     [P] - plugged
+ *                          |
+ *                          v
+ *    pwqs -> A -> B [P] -> C [P] (newest)
+ *            |    |        |
+ *            1    3        5
+ *            |    |        |
+ *            2    4        6
+ *
+ * When the oldest pwq is drained and removed, this function should be called
+ * to unplug the next oldest one to start its work item execution. Note that
+ * pwq's are linked into wq->pwqs with the oldest first, so the first one in
+ * the list is the oldest.
+ */
+static void unplug_oldest_pwq(struct workqueue_struct *wq)
+{
+	struct pool_workqueue *pwq;
+
+	lockdep_assert_held(&wq->mutex);
+
+	/* Caller should make sure that pwqs isn't empty before calling */
+	pwq = list_first_entry_or_null(&wq->pwqs, struct pool_workqueue,
+				       pwqs_node);
+	raw_spin_lock_irq(&pwq->pool->lock);
+	if (pwq->plugged) {
+		pwq->plugged = false;
+		if (pwq_activate_first_inactive(pwq, true))
+			kick_pool(pwq->pool);
+	}
+	raw_spin_unlock_irq(&pwq->pool->lock);
+}
+
+/**
  * node_activate_pending_pwq - Activate a pending pwq on a wq_node_nr_active
  * @nna: wq_node_nr_active to activate a pending pwq for
  * @caller_pool: worker_pool the caller is locking
@@ -1962,8 +2042,8 @@ out_put:
 /**
  * try_to_grab_pending - steal work item from worklist and disable irq
  * @work: work item to steal
- * @is_dwork: @work is a delayed_work
- * @flags: place to store irq state
+ * @cflags: %WORK_CANCEL_ flags
+ * @irq_flags: place to store irq state
  *
  * Try to grab PENDING bit of @work.  This function can handle @work in any
  * stable state - idle, on timer or on worklist.
@@ -1985,20 +2065,20 @@ out_put:
  * irqsafe, ensures that we return -EAGAIN for finite short period of time.
  *
  * On successful return, >= 0, irq is disabled and the caller is
- * responsible for releasing it using local_irq_restore(*@flags).
+ * responsible for releasing it using local_irq_restore(*@irq_flags).
  *
  * This function is safe to call from any context including IRQ handler.
  */
-static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
-			       unsigned long *flags)
+static int try_to_grab_pending(struct work_struct *work, u32 cflags,
+			       unsigned long *irq_flags)
 {
 	struct worker_pool *pool;
 	struct pool_workqueue *pwq;
 
-	local_irq_save(*flags);
+	local_irq_save(*irq_flags);
 
 	/* try to steal the timer if it exists */
-	if (is_dwork) {
+	if (cflags & WORK_CANCEL_DELAYED) {
 		struct delayed_work *dwork = to_delayed_work(work);
 
 		/*
@@ -2058,7 +2138,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
 		 * this destroys work->data needed by the next step, stash it.
 		 */
 		work_data = *work_data_bits(work);
-		set_work_pool_and_keep_pending(work, pool->id);
+		set_work_pool_and_keep_pending(work, pool->id, 0);
 
 		/* must be the last step, see the function comment */
 		pwq_dec_nr_in_flight(pwq, work_data);
@@ -2070,13 +2150,82 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
 	raw_spin_unlock(&pool->lock);
 fail:
 	rcu_read_unlock();
-	local_irq_restore(*flags);
+	local_irq_restore(*irq_flags);
 	if (work_is_canceling(work))
 		return -ENOENT;
 	cpu_relax();
 	return -EAGAIN;
 }
 
+struct cwt_wait {
+	wait_queue_entry_t	wait;
+	struct work_struct	*work;
+};
+
+static int cwt_wakefn(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
+{
+	struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait);
+
+	if (cwait->work != key)
+		return 0;
+	return autoremove_wake_function(wait, mode, sync, key);
+}
+
+/**
+ * work_grab_pending - steal work item from worklist and disable irq
+ * @work: work item to steal
+ * @cflags: %WORK_CANCEL_ flags
+ * @irq_flags: place to store IRQ state
+ *
+ * Grab PENDING bit of @work. @work can be in any stable state - idle, on timer
+ * or on worklist.
+ *
+ * Must be called in process context. IRQ is disabled on return with IRQ state
+ * stored in *@irq_flags. The caller is responsible for re-enabling it using
+ * local_irq_restore().
+ *
+ * Returns %true if @work was pending. %false if idle.
+ */
+static bool work_grab_pending(struct work_struct *work, u32 cflags,
+			      unsigned long *irq_flags)
+{
+	struct cwt_wait cwait;
+	int ret;
+
+	might_sleep();
+repeat:
+	ret = try_to_grab_pending(work, cflags, irq_flags);
+	if (likely(ret >= 0))
+		return ret;
+	if (ret != -ENOENT)
+		goto repeat;
+
+	/*
+	 * Someone is already canceling. Wait for it to finish. flush_work()
+	 * doesn't work for PREEMPT_NONE because we may get woken up between
+	 * @work's completion and the other canceling task resuming and clearing
+	 * CANCELING - flush_work() will return false immediately as @work is no
+	 * longer busy, try_to_grab_pending() will return -ENOENT as @work is
+	 * still being canceled and the other canceling task won't be able to
+	 * clear CANCELING as we're hogging the CPU.
+	 *
+	 * Let's wait for completion using a waitqueue. As this may lead to the
+	 * thundering herd problem, use a custom wake function which matches
+	 * @work along with exclusive wait and wakeup.
+	 */
+	init_wait(&cwait.wait);
+	cwait.wait.func = cwt_wakefn;
+	cwait.work = work;
+
+	prepare_to_wait_exclusive(&wq_cancel_waitq, &cwait.wait,
+				  TASK_UNINTERRUPTIBLE);
+	if (work_is_canceling(work))
+		schedule();
+	finish_wait(&wq_cancel_waitq, &cwait.wait);
+
+	goto repeat;
+}
+
 /**
  * insert_work - insert a work into a pool
  * @pwq: pwq @work belongs to
@@ -2164,7 +2313,6 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 	 */
 	lockdep_assert_irqs_disabled();
 
-
 	/*
 	 * For a draining wq, only works from the same workqueue are
 	 * allowed. The __WQ_DESTROYING helps to spot the issue that
@@ -2279,16 +2427,16 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq,
 		   struct work_struct *work)
 {
 	bool ret = false;
-	unsigned long flags;
+	unsigned long irq_flags;
 
-	local_irq_save(flags);
+	local_irq_save(irq_flags);
 
 	if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
 		__queue_work(cpu, wq, work);
 		ret = true;
 	}
 
-	local_irq_restore(flags);
+	local_irq_restore(irq_flags);
 	return ret;
 }
 EXPORT_SYMBOL(queue_work_on);
@@ -2345,7 +2493,7 @@ static int select_numa_node_cpu(int node)
 bool queue_work_node(int node, struct workqueue_struct *wq,
 		     struct work_struct *work)
 {
-	unsigned long flags;
+	unsigned long irq_flags;
 	bool ret = false;
 
 	/*
@@ -2359,7 +2507,7 @@ bool queue_work_node(int node, struct workqueue_struct *wq,
 	 */
 	WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND));
 
-	local_irq_save(flags);
+	local_irq_save(irq_flags);
 
 	if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
 		int cpu = select_numa_node_cpu(node);
@@ -2368,7 +2516,7 @@ bool queue_work_node(int node, struct workqueue_struct *wq,
 		ret = true;
 	}
 
-	local_irq_restore(flags);
+	local_irq_restore(irq_flags);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(queue_work_node);
@@ -2438,17 +2586,17 @@ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
 {
 	struct work_struct *work = &dwork->work;
 	bool ret = false;
-	unsigned long flags;
+	unsigned long irq_flags;
 
 	/* read the comment in __queue_work() */
-	local_irq_save(flags);
+	local_irq_save(irq_flags);
 
 	if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
 		__queue_delayed_work(cpu, wq, dwork, delay);
 		ret = true;
 	}
 
-	local_irq_restore(flags);
+	local_irq_restore(irq_flags);
 	return ret;
 }
 EXPORT_SYMBOL(queue_delayed_work_on);
@@ -2474,16 +2622,17 @@ EXPORT_SYMBOL(queue_delayed_work_on);
 bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq,
 			 struct delayed_work *dwork, unsigned long delay)
 {
-	unsigned long flags;
+	unsigned long irq_flags;
 	int ret;
 
 	do {
-		ret = try_to_grab_pending(&dwork->work, true, &flags);
+		ret = try_to_grab_pending(&dwork->work, WORK_CANCEL_DELAYED,
+					  &irq_flags);
 	} while (unlikely(ret == -EAGAIN));
 
 	if (likely(ret >= 0)) {
 		__queue_delayed_work(cpu, wq, dwork, delay);
-		local_irq_restore(flags);
+		local_irq_restore(irq_flags);
 	}
 
 	/* -ENOENT from try_to_grab_pending() becomes %true */
@@ -3009,6 +3158,7 @@ __acquires(&pool->lock)
 	struct worker_pool *pool = worker->pool;
 	unsigned long work_data;
 	int lockdep_start_depth, rcu_start_depth;
+	bool bh_draining = pool->flags & POOL_BH_DRAINING;
 #ifdef CONFIG_LOCKDEP
 	/*
 	 * It is permissible to free the struct work_struct from
@@ -3067,14 +3217,16 @@ __acquires(&pool->lock)
 	 * PENDING and queued state changes happen together while IRQ is
 	 * disabled.
 	 */
-	set_work_pool_and_clear_pending(work, pool->id);
+	set_work_pool_and_clear_pending(work, pool->id, 0);
 
 	pwq->stats[PWQ_STAT_STARTED]++;
 	raw_spin_unlock_irq(&pool->lock);
 
 	rcu_start_depth = rcu_preempt_depth();
 	lockdep_start_depth = lockdep_depth(current);
-	lock_map_acquire(&pwq->wq->lockdep_map);
+	/* see drain_dead_softirq_workfn() */
+	if (!bh_draining)
+		lock_map_acquire(&pwq->wq->lockdep_map);
 	lock_map_acquire(&lockdep_map);
 	/*
 	 * Strictly speaking we should mark the invariant state without holding
@@ -3107,7 +3259,8 @@ __acquires(&pool->lock)
 	trace_workqueue_execute_end(work, worker->current_func);
 	pwq->stats[PWQ_STAT_COMPLETED]++;
 	lock_map_release(&lockdep_map);
-	lock_map_release(&pwq->wq->lockdep_map);
+	if (!bh_draining)
+		lock_map_release(&pwq->wq->lockdep_map);
 
 	if (unlikely((worker->task && in_atomic()) ||
 		     lockdep_depth(current) != lockdep_start_depth ||
@@ -3469,6 +3622,84 @@ void workqueue_softirq_action(bool highpri)
 		bh_worker(list_first_entry(&pool->workers, struct worker, node));
 }
 
+struct wq_drain_dead_softirq_work {
+	struct work_struct	work;
+	struct worker_pool	*pool;
+	struct completion	done;
+};
+
+static void drain_dead_softirq_workfn(struct work_struct *work)
+{
+	struct wq_drain_dead_softirq_work *dead_work =
+		container_of(work, struct wq_drain_dead_softirq_work, work);
+	struct worker_pool *pool = dead_work->pool;
+	bool repeat;
+
+	/*
+	 * @pool's CPU is dead and we want to execute its still pending work
+	 * items from this BH work item which is running on a different CPU. As
+	 * its CPU is dead, @pool can't be kicked and, as work execution path
+	 * will be nested, a lockdep annotation needs to be suppressed. Mark
+	 * @pool with %POOL_BH_DRAINING for the special treatments.
+	 */
+	raw_spin_lock_irq(&pool->lock);
+	pool->flags |= POOL_BH_DRAINING;
+	raw_spin_unlock_irq(&pool->lock);
+
+	bh_worker(list_first_entry(&pool->workers, struct worker, node));
+
+	raw_spin_lock_irq(&pool->lock);
+	pool->flags &= ~POOL_BH_DRAINING;
+	repeat = need_more_worker(pool);
+	raw_spin_unlock_irq(&pool->lock);
+
+	/*
+	 * bh_worker() might hit consecutive execution limit and bail. If there
+	 * still are pending work items, reschedule self and return so that we
+	 * don't hog this CPU's BH.
+	 */
+	if (repeat) {
+		if (pool->attrs->nice == HIGHPRI_NICE_LEVEL)
+			queue_work(system_bh_highpri_wq, work);
+		else
+			queue_work(system_bh_wq, work);
+	} else {
+		complete(&dead_work->done);
+	}
+}
+
+/*
+ * @cpu is dead. Drain the remaining BH work items on the current CPU. It's
+ * possible to allocate dead_work per CPU and avoid flushing. However, then we
+ * have to worry about draining overlapping with CPU coming back online or
+ * nesting (one CPU's dead_work queued on another CPU which is also dead and so
+ * on). Let's keep it simple and drain them synchronously. These are BH work
+ * items which shouldn't be requeued on the same pool. Shouldn't take long.
+ */
+void workqueue_softirq_dead(unsigned int cpu)
+{
+	int i;
+
+	for (i = 0; i < NR_STD_WORKER_POOLS; i++) {
+		struct worker_pool *pool = &per_cpu(bh_worker_pools, cpu)[i];
+		struct wq_drain_dead_softirq_work dead_work;
+
+		if (!need_more_worker(pool))
+			continue;
+
+		INIT_WORK(&dead_work.work, drain_dead_softirq_workfn);
+		dead_work.pool = pool;
+		init_completion(&dead_work.done);
+
+		if (pool->attrs->nice == HIGHPRI_NICE_LEVEL)
+			queue_work(system_bh_highpri_wq, &dead_work.work);
+		else
+			queue_work(system_bh_wq, &dead_work.work);
+
+		wait_for_completion(&dead_work.done);
+	}
+}
+
 /**
  * check_flush_dependency - check for flush dependency sanity
  * @target_wq: workqueue being flushed
@@ -3996,108 +4227,6 @@ bool flush_work(struct work_struct *work)
 }
 EXPORT_SYMBOL_GPL(flush_work);
 
-struct cwt_wait {
-	wait_queue_entry_t		wait;
-	struct work_struct	*work;
-};
-
-static int cwt_wakefn(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
-{
-	struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait);
-
-	if (cwait->work != key)
-		return 0;
-	return autoremove_wake_function(wait, mode, sync, key);
-}
-
-static bool __cancel_work_timer(struct work_struct *work, bool is_dwork)
-{
-	static DECLARE_WAIT_QUEUE_HEAD(cancel_waitq);
-	unsigned long flags;
-	int ret;
-
-	do {
-		ret = try_to_grab_pending(work, is_dwork, &flags);
-		/*
-		 * If someone else is already canceling, wait for it to
-		 * finish.  flush_work() doesn't work for PREEMPT_NONE
-		 * because we may get scheduled between @work's completion
-		 * and the other canceling task resuming and clearing
-		 * CANCELING - flush_work() will return false immediately
-		 * as @work is no longer busy, try_to_grab_pending() will
-		 * return -ENOENT as @work is still being canceled and the
-		 * other canceling task won't be able to clear CANCELING as
-		 * we're hogging the CPU.
-		 *
-		 * Let's wait for completion using a waitqueue.  As this
-		 * may lead to the thundering herd problem, use a custom
-		 * wake function which matches @work along with exclusive
-		 * wait and wakeup.
-		 */
-		if (unlikely(ret == -ENOENT)) {
-			struct cwt_wait cwait;
-
-			init_wait(&cwait.wait);
-			cwait.wait.func = cwt_wakefn;
-			cwait.work = work;
-
-			prepare_to_wait_exclusive(&cancel_waitq, &cwait.wait,
-						  TASK_UNINTERRUPTIBLE);
-			if (work_is_canceling(work))
-				schedule();
-			finish_wait(&cancel_waitq, &cwait.wait);
-		}
-	} while (unlikely(ret < 0));
-
-	/* tell other tasks trying to grab @work to back off */
-	mark_work_canceling(work);
-	local_irq_restore(flags);
-
-	/*
-	 * This allows canceling during early boot.  We know that @work
-	 * isn't executing.
-	 */
-	if (wq_online)
-		__flush_work(work, true);
-
-	clear_work_data(work);
-
-	/*
-	 * Paired with prepare_to_wait() above so that either
-	 * waitqueue_active() is visible here or !work_is_canceling() is
-	 * visible there.
-	 */
-	smp_mb();
-	if (waitqueue_active(&cancel_waitq))
-		__wake_up(&cancel_waitq, TASK_NORMAL, 1, work);
-
-	return ret;
-}
-
-/**
- * cancel_work_sync - cancel a work and wait for it to finish
- * @work: the work to cancel
- *
- * Cancel @work and wait for its execution to finish.  This function
- * can be used even if the work re-queues itself or migrates to
- * another workqueue.  On return from this function, @work is
- * guaranteed to be not pending or executing on any CPU.
- *
- * cancel_work_sync(&delayed_work->work) must not be used for
- * delayed_work's.  Use cancel_delayed_work_sync() instead.
- *
- * The caller must ensure that the workqueue on which @work was last
- * queued can't be destroyed before this function returns.
- *
- * Return:
- * %true if @work was pending, %false otherwise.
- */
-bool cancel_work_sync(struct work_struct *work)
-{
-	return __cancel_work_timer(work, false);
-}
-EXPORT_SYMBOL_GPL(cancel_work_sync);
-
 /**
  * flush_delayed_work - wait for a dwork to finish executing the last queueing
  * @dwork: the delayed work to flush
@@ -4140,20 +4269,50 @@ bool flush_rcu_work(struct rcu_work *rwork)
 }
 EXPORT_SYMBOL(flush_rcu_work);
 
-static bool __cancel_work(struct work_struct *work, bool is_dwork)
+static bool __cancel_work(struct work_struct *work, u32 cflags)
 {
-	unsigned long flags;
+	unsigned long irq_flags;
 	int ret;
 
 	do {
-		ret = try_to_grab_pending(work, is_dwork, &flags);
+		ret = try_to_grab_pending(work, cflags, &irq_flags);
 	} while (unlikely(ret == -EAGAIN));
 
 	if (unlikely(ret < 0))
 		return false;
 
-	set_work_pool_and_clear_pending(work, get_work_pool_id(work));
-	local_irq_restore(flags);
+	set_work_pool_and_clear_pending(work, get_work_pool_id(work), 0);
+	local_irq_restore(irq_flags);
+	return ret;
+}
+
+static bool __cancel_work_sync(struct work_struct *work, u32 cflags)
+{
+	unsigned long irq_flags;
+	bool ret;
+
+	/* claim @work and tell other tasks trying to grab @work to back off */
+	ret = work_grab_pending(work, cflags, &irq_flags);
+	mark_work_canceling(work);
+	local_irq_restore(irq_flags);
+
+	/*
+	 * Skip __flush_work() during early boot when we know that @work isn't
+	 * executing. This allows canceling during early boot.
+	 */
+	if (wq_online)
+		__flush_work(work, true);
+
+	/*
+	 * smp_mb() at the end of set_work_pool_and_clear_pending() is paired
+	 * with prepare_to_wait() above so that either waitqueue_active() is
+	 * visible here or !work_is_canceling() is visible there.
+	 */
+	set_work_pool_and_clear_pending(work, WORK_OFFQ_POOL_NONE, 0);
+
+	if (waitqueue_active(&wq_cancel_waitq))
+		__wake_up(&wq_cancel_waitq, TASK_NORMAL, 1, work);
+
 	return ret;
 }
 
@@ -4162,11 +4321,35 @@ static bool __cancel_work(struct work_struct *work, bool is_dwork)
  */
 bool cancel_work(struct work_struct *work)
 {
-	return __cancel_work(work, false);
+	return __cancel_work(work, 0);
 }
 EXPORT_SYMBOL(cancel_work);
 
 /**
+ * cancel_work_sync - cancel a work and wait for it to finish
+ * @work: the work to cancel
+ *
+ * Cancel @work and wait for its execution to finish.  This function
+ * can be used even if the work re-queues itself or migrates to
+ * another workqueue.  On return from this function, @work is
+ * guaranteed to be not pending or executing on any CPU.
+ *
+ * cancel_work_sync(&delayed_work->work) must not be used for
+ * delayed_work's.  Use cancel_delayed_work_sync() instead.
+ *
+ * The caller must ensure that the workqueue on which @work was last
+ * queued can't be destroyed before this function returns.
+ *
+ * Return:
+ * %true if @work was pending, %false otherwise.
+ */
+bool cancel_work_sync(struct work_struct *work)
+{
+	return __cancel_work_sync(work, 0);
+}
+EXPORT_SYMBOL_GPL(cancel_work_sync);
+
+/**
  * cancel_delayed_work - cancel a delayed work
  * @dwork: delayed_work to cancel
  *
@@ -4184,7 +4367,7 @@ EXPORT_SYMBOL(cancel_work);
  */
 bool cancel_delayed_work(struct delayed_work *dwork)
 {
-	return __cancel_work(&dwork->work, true);
+	return __cancel_work(&dwork->work, WORK_CANCEL_DELAYED);
 }
 EXPORT_SYMBOL(cancel_delayed_work);
 
@@ -4199,7 +4382,7 @@ EXPORT_SYMBOL(cancel_delayed_work);
  */
 bool cancel_delayed_work_sync(struct delayed_work *dwork)
 {
-	return __cancel_work_timer(&dwork->work, true);
+	return __cancel_work_sync(&dwork->work, WORK_CANCEL_DELAYED);
 }
 EXPORT_SYMBOL(cancel_delayed_work_sync);
 
@@ -4740,6 +4923,13 @@ static void pwq_release_workfn(struct kthread_work *work)
 		mutex_lock(&wq->mutex);
 		list_del_rcu(&pwq->pwqs_node);
 		is_last = list_empty(&wq->pwqs);
+
+		/*
+		 * For ordered workqueue with a plugged dfl_pwq, restart it now.
+		 */
+		if (!is_last && (wq->flags & __WQ_ORDERED))
+			unplug_oldest_pwq(wq);
+
 		mutex_unlock(&wq->mutex);
 	}
 
@@ -4774,7 +4964,7 @@ static void pwq_release_workfn(struct kthread_work *work)
 static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq,
 		     struct worker_pool *pool)
 {
-	BUG_ON((unsigned long)pwq & WORK_STRUCT_FLAG_MASK);
+	BUG_ON((unsigned long)pwq & ~WORK_STRUCT_PWQ_MASK);
 
 	memset(pwq, 0, sizeof(*pwq));
 
@@ -4804,7 +4994,7 @@ static void link_pwq(struct pool_workqueue *pwq)
 	pwq->work_color = wq->work_color;
 
 	/* link in @pwq */
-	list_add_rcu(&pwq->pwqs_node, &wq->pwqs);
+	list_add_tail_rcu(&pwq->pwqs_node, &wq->pwqs);
 }
 
 /* obtain a pool matching @attr and create a pwq associating the pool and @wq */
@@ -4966,6 +5156,15 @@ apply_wqattrs_prepare(struct workqueue_struct *wq,
 	cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask);
 	ctx->attrs = new_attrs;
 
+	/*
+	 * For initialized ordered workqueues, there should only be one pwq
+	 * (dfl_pwq). Set the plugged flag of ctx->dfl_pwq to suspend execution
+	 * of newly queued work items until execution of older work items in
+	 * the old pwq's have completed.
+	 */
+	if ((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs))
+		ctx->dfl_pwq->plugged = true;
+
 	ctx->wq = wq;
 	return ctx;
 
@@ -4994,6 +5193,11 @@ static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx)
 	/* update node_nr_active->max */
 	wq_update_node_max_active(ctx->wq, -1);
 
+	/* rescuer needs to respect wq cpumask changes */
+	if (ctx->wq->rescuer)
+		set_cpus_allowed_ptr(ctx->wq->rescuer->task,
+				     unbound_effective_cpumask(ctx->wq));
+
 	mutex_unlock(&ctx->wq->mutex);
 }
 
@@ -5006,14 +5210,6 @@ static int apply_workqueue_attrs_locked(struct workqueue_struct *wq,
 	if (WARN_ON(!(wq->flags & WQ_UNBOUND)))
 		return -EINVAL;
 
-	/* creating multiple pwqs breaks ordering guarantee */
-	if (!list_empty(&wq->pwqs)) {
-		if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
-			return -EINVAL;
-
-		wq->flags &= ~__WQ_ORDERED;
-	}
-
 	ctx = apply_wqattrs_prepare(wq, attrs, wq_unbound_cpumask);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
@@ -5245,7 +5441,7 @@ static int init_rescuer(struct workqueue_struct *wq)
 
 	wq->rescuer = rescuer;
 	if (wq->flags & WQ_UNBOUND)
-		kthread_bind_mask(rescuer->task, wq->unbound_attrs->cpumask);
+		kthread_bind_mask(rescuer->task, wq_unbound_cpumask);
 	else
 		kthread_bind_mask(rescuer->task, cpu_possible_mask);
 	wake_up_process(rescuer->task);
@@ -5303,15 +5499,15 @@ static void wq_adjust_max_active(struct workqueue_struct *wq)
 
 		activated = false;
 		for_each_pwq(pwq, wq) {
-			unsigned long flags;
+			unsigned long irq_flags;
 
 			/* can be called during early boot w/ irq disabled */
-			raw_spin_lock_irqsave(&pwq->pool->lock, flags);
+			raw_spin_lock_irqsave(&pwq->pool->lock, irq_flags);
 			if (pwq_activate_first_inactive(pwq, true)) {
 				activated = true;
 				kick_pool(pwq->pool);
 			}
-			raw_spin_unlock_irqrestore(&pwq->pool->lock, flags);
+			raw_spin_unlock_irqrestore(&pwq->pool->lock, irq_flags);
 		}
 	} while (activated);
 }
@@ -5333,15 +5529,6 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
 			return NULL;
 	}
 
-	/*
-	 * Unbound && max_active == 1 used to imply ordered, which is no longer
-	 * the case on many machines due to per-pod pools. While
-	 * alloc_ordered_workqueue() is the right way to create an ordered
-	 * workqueue, keep the previous behavior to avoid subtle breakages.
-	 */
-	if ((flags & WQ_UNBOUND) && max_active == 1)
-		flags |= __WQ_ORDERED;
-
 	/* see the comment above the definition of WQ_POWER_EFFICIENT */
 	if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
 		flags |= WQ_UNBOUND;
@@ -5564,14 +5751,13 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
 	if (WARN_ON(wq->flags & WQ_BH))
 		return;
 	/* disallow meddling with max_active for ordered workqueues */
-	if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
+	if (WARN_ON(wq->flags & __WQ_ORDERED))
 		return;
 
 	max_active = wq_clamp_max_active(max_active, wq->flags, wq->name);
 
 	mutex_lock(&wq->mutex);
 
-	wq->flags &= ~__WQ_ORDERED;
 	wq->saved_max_active = max_active;
 	if (wq->flags & WQ_UNBOUND)
 		wq->saved_min_active = min(wq->saved_min_active, max_active);
@@ -5583,6 +5769,33 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
 EXPORT_SYMBOL_GPL(workqueue_set_max_active);
 
 /**
+ * workqueue_set_min_active - adjust min_active of an unbound workqueue
+ * @wq: target unbound workqueue
+ * @min_active: new min_active value
+ *
+ * Set min_active of an unbound workqueue. Unlike other types of workqueues, an
+ * unbound workqueue is not guaranteed to be able to process max_active
+ * interdependent work items. Instead, an unbound workqueue is guaranteed to be
+ * able to process min_active number of interdependent work items which is
+ * %WQ_DFL_MIN_ACTIVE by default.
+ *
+ * Use this function to adjust the min_active value between 0 and the current
+ * max_active.
+ */
+void workqueue_set_min_active(struct workqueue_struct *wq, int min_active)
+{
+	/* min_active is only meaningful for non-ordered unbound workqueues */
+	if (WARN_ON((wq->flags & (WQ_BH | WQ_UNBOUND | __WQ_ORDERED)) !=
+		    WQ_UNBOUND))
+		return;
+
+	mutex_lock(&wq->mutex);
+	wq->saved_min_active = clamp(min_active, 0, wq->saved_max_active);
+	wq_adjust_max_active(wq);
+	mutex_unlock(&wq->mutex);
+}
+
+/**
  * current_work - retrieve %current task's work struct
  *
  * Determine if %current task is a workqueue worker and what it's working on.
@@ -5667,7 +5880,7 @@ EXPORT_SYMBOL_GPL(workqueue_congested);
 unsigned int work_busy(struct work_struct *work)
 {
 	struct worker_pool *pool;
-	unsigned long flags;
+	unsigned long irq_flags;
 	unsigned int ret = 0;
 
 	if (work_pending(work))
@@ -5676,10 +5889,10 @@ unsigned int work_busy(struct work_struct *work)
 	rcu_read_lock();
 	pool = get_work_pool(work);
 	if (pool) {
-		raw_spin_lock_irqsave(&pool->lock, flags);
+		raw_spin_lock_irqsave(&pool->lock, irq_flags);
 		if (find_worker_executing_work(pool, work))
 			ret |= WORK_BUSY_RUNNING;
-		raw_spin_unlock_irqrestore(&pool->lock, flags);
+		raw_spin_unlock_irqrestore(&pool->lock, irq_flags);
 	}
 	rcu_read_unlock();
 
@@ -5911,7 +6124,7 @@ void show_one_workqueue(struct workqueue_struct *wq)
 {
 	struct pool_workqueue *pwq;
 	bool idle = true;
-	unsigned long flags;
+	unsigned long irq_flags;
 
 	for_each_pwq(pwq, wq) {
 		if (!pwq_is_empty(pwq)) {
@@ -5925,7 +6138,7 @@ void show_one_workqueue(struct workqueue_struct *wq)
 	pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags);
 
 	for_each_pwq(pwq, wq) {
-		raw_spin_lock_irqsave(&pwq->pool->lock, flags);
+		raw_spin_lock_irqsave(&pwq->pool->lock, irq_flags);
 		if (!pwq_is_empty(pwq)) {
 			/*
 			 * Defer printing to avoid deadlocks in console
@@ -5936,7 +6149,7 @@ void show_one_workqueue(struct workqueue_struct *wq)
 			show_pwq(pwq);
 			printk_deferred_exit();
 		}
-		raw_spin_unlock_irqrestore(&pwq->pool->lock, flags);
+		raw_spin_unlock_irqrestore(&pwq->pool->lock, irq_flags);
 		/*
 		 * We could be printing a lot from atomic context, e.g.
 		 * sysrq-t -> show_all_workqueues(). Avoid triggering
@@ -5955,10 +6168,10 @@ static void show_one_worker_pool(struct worker_pool *pool)
 {
 	struct worker *worker;
 	bool first = true;
-	unsigned long flags;
+	unsigned long irq_flags;
 	unsigned long hung = 0;
 
-	raw_spin_lock_irqsave(&pool->lock, flags);
+	raw_spin_lock_irqsave(&pool->lock, irq_flags);
 	if (pool->nr_workers == pool->nr_idle)
 		goto next_pool;
 
@@ -5986,7 +6199,7 @@ static void show_one_worker_pool(struct worker_pool *pool)
 	pr_cont("\n");
 	printk_deferred_exit();
 next_pool:
-	raw_spin_unlock_irqrestore(&pool->lock, flags);
+	raw_spin_unlock_irqrestore(&pool->lock, irq_flags);
 	/*
 	 * We could be printing a lot from atomic context, e.g.
 	 * sysrq-t -> show_all_workqueues(). Avoid triggering
@@ -6504,13 +6717,6 @@ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask)
 		if (!(wq->flags & WQ_UNBOUND) || (wq->flags & __WQ_DESTROYING))
 			continue;
 
-		/* creating multiple pwqs breaks ordering guarantee */
-		if (!list_empty(&wq->pwqs)) {
-			if (wq->flags & __WQ_ORDERED_EXPLICIT)
-				continue;
-			wq->flags &= ~__WQ_ORDERED;
-		}
-
 		ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs, unbound_cpumask);
 		if (IS_ERR(ctx)) {
 			ret = PTR_ERR(ctx);
@@ -7024,11 +7230,10 @@ int workqueue_sysfs_register(struct workqueue_struct *wq)
 	int ret;
 
 	/*
-	 * Adjusting max_active or creating new pwqs by applying
-	 * attributes breaks ordering guarantee.  Disallow exposing ordered
-	 * workqueues.
+	 * Adjusting max_active breaks ordering guarantee.  Disallow exposing
+	 * ordered workqueues.
 	 */
-	if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
+	if (WARN_ON(wq->flags & __WQ_ORDERED))
 		return -EINVAL;
 
 	wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL);
@@ -7125,10 +7330,10 @@ static DEFINE_PER_CPU(unsigned long, wq_watchdog_touched_cpu) = INITIAL_JIFFIES;
 static void show_cpu_pool_hog(struct worker_pool *pool)
 {
 	struct worker *worker;
-	unsigned long flags;
+	unsigned long irq_flags;
 	int bkt;
 
-	raw_spin_lock_irqsave(&pool->lock, flags);
+	raw_spin_lock_irqsave(&pool->lock, irq_flags);
 
 	hash_for_each(pool->busy_hash, bkt, worker, hentry) {
 		if (task_is_running(worker->task)) {
@@ -7146,7 +7351,7 @@ static void show_cpu_pool_hog(struct worker_pool *pool)
 		}
 	}
 
-	raw_spin_unlock_irqrestore(&pool->lock, flags);
+	raw_spin_unlock_irqrestore(&pool->lock, irq_flags);
 }
 
 static void show_cpu_pools_hogs(void)
@@ -7301,6 +7506,16 @@ static inline void wq_watchdog_init(void) { }
 
 #endif	/* CONFIG_WQ_WATCHDOG */
 
+static void bh_pool_kick_normal(struct irq_work *irq_work)
+{
+	raise_softirq_irqoff(TASKLET_SOFTIRQ);
+}
+
+static void bh_pool_kick_highpri(struct irq_work *irq_work)
+{
+	raise_softirq_irqoff(HI_SOFTIRQ);
+}
+
 static void __init restrict_unbound_cpumask(const char *name, const struct cpumask *mask)
 {
 	if (!cpumask_intersects(wq_unbound_cpumask, mask)) {
@@ -7342,6 +7557,8 @@ void __init workqueue_init_early(void)
 {
 	struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_SYSTEM];
 	int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL };
+	void (*irq_work_fns[2])(struct irq_work *) = { bh_pool_kick_normal,
+						       bh_pool_kick_highpri };
 	int i, cpu;
 
 	BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long));
@@ -7389,8 +7606,10 @@ void __init workqueue_init_early(void)
 
 		i = 0;
 		for_each_bh_worker_pool(pool, cpu) {
-			init_cpu_worker_pool(pool, cpu, std_nice[i++]);
+			init_cpu_worker_pool(pool, cpu, std_nice[i]);
 			pool->flags |= POOL_BH;
+			init_irq_work(bh_pool_irq_work(pool), irq_work_fns[i]);
+			i++;
 		}
 
 		i = 0;
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 97ce28f4d154..f3b50b47b7ea 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -231,9 +231,10 @@ config DEBUG_INFO
 	  in the "Debug information" choice below, indicating that debug
 	  information will be generated for build targets.
 
-# Clang is known to generate .{s,u}leb128 with symbol deltas with DWARF5, which
-# some targets may not support: https://sourceware.org/bugzilla/show_bug.cgi?id=27215
-config AS_HAS_NON_CONST_LEB128
+# Clang generates .uleb128 with label differences for DWARF v5, a feature that
+# older binutils ports do not support when utilizing RISC-V style linker
+# relaxation: https://sourceware.org/bugzilla/show_bug.cgi?id=27215
+config AS_HAS_NON_CONST_ULEB128
 	def_bool $(as-instr,.uleb128 .Lexpr_end4 - .Lexpr_start3\n.Lexpr_start3:\n.Lexpr_end4:)
 
 choice
@@ -258,7 +259,7 @@ config DEBUG_INFO_NONE
 config DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT
 	bool "Rely on the toolchain's implicit default DWARF version"
 	select DEBUG_INFO
-	depends on !CC_IS_CLANG || AS_IS_LLVM || CLANG_VERSION < 140000 || (AS_IS_GNU && AS_VERSION >= 23502 && AS_HAS_NON_CONST_LEB128)
+	depends on !CC_IS_CLANG || AS_IS_LLVM || CLANG_VERSION < 140000 || (AS_IS_GNU && AS_VERSION >= 23502 && AS_HAS_NON_CONST_ULEB128)
 	help
 	  The implicit default version of DWARF debug info produced by a
 	  toolchain changes over time.
@@ -282,7 +283,8 @@ config DEBUG_INFO_DWARF4
 config DEBUG_INFO_DWARF5
 	bool "Generate DWARF Version 5 debuginfo"
 	select DEBUG_INFO
-	depends on !CC_IS_CLANG || AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502 && AS_HAS_NON_CONST_LEB128)
+	depends on !ARCH_HAS_BROKEN_DWARF5
+	depends on !CC_IS_CLANG || AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502 && AS_HAS_NON_CONST_ULEB128)
 	help
 	  Generate DWARF v5 debug info. Requires binutils 2.35.2, gcc 5.0+ (gcc
 	  5.0+ accepts the -gdwarf-5 flag but only had partial support for some
@@ -378,6 +380,8 @@ config DEBUG_INFO_BTF
 	depends on !GCC_PLUGIN_RANDSTRUCT || COMPILE_TEST
 	depends on BPF_SYSCALL
 	depends on !DEBUG_INFO_DWARF5 || PAHOLE_VERSION >= 121
+	# pahole uses elfutils, which does not have support for Hexagon relocations
+	depends on !HEXAGON
 	help
 	  Generate deduplicated BTF type information from DWARF debug info.
 	  Turning this on expects presence of pahole tool, which will convert
@@ -2231,6 +2235,7 @@ config TEST_DIV64
 config TEST_IOV_ITER
 	tristate "Test iov_iter operation" if !KUNIT_ALL_TESTS
 	depends on KUNIT
+	depends on MMU
 	default KUNIT_ALL_TESTS
 	help
 	  Enable this to turn on testing of the operation of the I/O iterator
@@ -2853,28 +2858,6 @@ config TEST_MEMCAT_P
 
 	  If unsure, say N.
 
-config TEST_LIVEPATCH
-	tristate "Test livepatching"
-	default n
-	depends on DYNAMIC_DEBUG
-	depends on LIVEPATCH
-	depends on m
-	help
-	  Test kernel livepatching features for correctness.  The tests will
-	  load test modules that will be livepatched in various scenarios.
-
-	  To run all the livepatching tests:
-
-	  make -C tools/testing/selftests TARGETS=livepatch run_tests
-
-	  Alternatively, individual tests may be invoked:
-
-	  tools/testing/selftests/livepatch/test-callbacks.sh
-	  tools/testing/selftests/livepatch/test-livepatch.sh
-	  tools/testing/selftests/livepatch/test-shadow-vars.sh
-
-	  If unsure, say N.
-
 config TEST_OBJAGG
 	tristate "Perform selftest on object aggreration manager"
 	default n
diff --git a/lib/Makefile b/lib/Makefile
index 6b09731d8e61..95ed57f377fd 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -134,8 +134,6 @@ endif
 obj-$(CONFIG_TEST_FPU) += test_fpu.o
 CFLAGS_test_fpu.o += $(FPU_CFLAGS)
 
-obj-$(CONFIG_TEST_LIVEPATCH) += livepatch/
-
 # Some KUnit files (hooks.o) need to be built-in even when KUnit is a module,
 # so we can't just use obj-$(CONFIG_KUNIT).
 ifdef CONFIG_KUNIT
diff --git a/lib/checksum_kunit.c b/lib/checksum_kunit.c
index 0eed92b77ba3..bf70850035c7 100644
--- a/lib/checksum_kunit.c
+++ b/lib/checksum_kunit.c
@@ -1,15 +1,21 @@
 // SPDX-License-Identifier: GPL-2.0+
 /*
- * Test cases csum_partial and csum_fold
+ * Test cases csum_partial, csum_fold, ip_fast_csum, csum_ipv6_magic
  */
 
 #include <kunit/test.h>
 #include <asm/checksum.h>
+#include <net/ip6_checksum.h>
 
 #define MAX_LEN 512
 #define MAX_ALIGN 64
 #define TEST_BUFLEN (MAX_LEN + MAX_ALIGN)
 
+#define IPv4_MIN_WORDS 5
+#define IPv4_MAX_WORDS 15
+#define NUM_IPv6_TESTS 200
+#define NUM_IP_FAST_CSUM_TESTS 181
+
 /* Values for a little endian CPU. Byte swap each half on big endian CPU. */
 static const u32 random_init_sum = 0x2847aab;
 static const u8 random_buf[] = {
@@ -209,6 +215,237 @@ static const u32 init_sums_no_overflow[] = {
 	0xffff0000, 0xfffffffb,
 };
 
+static const u16 expected_csum_ipv6_magic[] = {
+	0x18d4, 0x3085, 0x2e4b, 0xd9f4, 0xbdc8, 0x78f,	0x1034, 0x8422, 0x6fc0,
+	0xd2f6, 0xbeb5, 0x9d3,	0x7e2a, 0x312e, 0x778e, 0xc1bb, 0x7cf2, 0x9d1e,
+	0xca21, 0xf3ff, 0x7569, 0xb02e, 0xca86, 0x7e76, 0x4539, 0x45e3, 0xf28d,
+	0xdf81, 0x8fd5, 0x3b5d, 0x8324, 0xf471, 0x83be, 0x1daf, 0x8c46, 0xe682,
+	0xd1fb, 0x6b2e, 0xe687, 0x2a33, 0x4833, 0x2d67, 0x660f, 0x2e79, 0xd65e,
+	0x6b62, 0x6672, 0x5dbd, 0x8680, 0xbaa5, 0x2229, 0x2125, 0x2d01, 0x1cc0,
+	0x6d36, 0x33c0, 0xee36, 0xd832, 0x9820, 0x8a31, 0x53c5, 0x2e2,	0xdb0e,
+	0x49ed, 0x17a7, 0x77a0, 0xd72e, 0x3d72, 0x7dc8, 0x5b17, 0xf55d, 0xa4d9,
+	0x1446, 0x5d56, 0x6b2e, 0x69a5, 0xadb6, 0xff2a, 0x92e,	0xe044, 0x3402,
+	0xbb60, 0xec7f, 0xe7e6, 0x1986, 0x32f4, 0x8f8,	0x5e00, 0x47c6, 0x3059,
+	0x3969, 0xe957, 0x4388, 0x2854, 0x3334, 0xea71, 0xa6de, 0x33f9, 0x83fc,
+	0x37b4, 0x5531, 0x3404, 0x1010, 0xed30, 0x610a, 0xc95,	0x9aed, 0x6ff,
+	0x5136, 0x2741, 0x660e, 0x8b80, 0xf71,	0xa263, 0x88af, 0x7a73, 0x3c37,
+	0x1908, 0x6db5, 0x2e92, 0x1cd2, 0x70c8, 0xee16, 0xe80,	0xcd55, 0x6e6,
+	0x6434, 0x127,	0x655d, 0x2ea0, 0xb4f4, 0xdc20, 0x5671, 0xe462, 0xe52b,
+	0xdb44, 0x3589, 0xc48f, 0xe60b, 0xd2d2, 0x66ad, 0x498,	0x436,	0xb917,
+	0xf0ca, 0x1a6e, 0x1cb7, 0xbf61, 0x2870, 0xc7e8, 0x5b30, 0xe4a5, 0x168,
+	0xadfc, 0xd035, 0xe690, 0xe283, 0xfb27, 0xe4ad, 0xb1a5, 0xf2d5, 0xc4b6,
+	0x8a30, 0xd7d5, 0x7df9, 0x91d5, 0x63ed, 0x2d21, 0x312b, 0xab19, 0xa632,
+	0x8d2e, 0xef06, 0x57b9, 0xc373, 0xbd1f, 0xa41f, 0x8444, 0x9975, 0x90cb,
+	0xc49c, 0xe965, 0x4eff, 0x5a,	0xef6d, 0xe81a, 0xe260, 0x853a, 0xff7a,
+	0x99aa, 0xb06b, 0xee19, 0xcc2c, 0xf34c, 0x7c49, 0xdac3, 0xa71e, 0xc988,
+	0x3845, 0x1014
+};
+
+static const u16 expected_fast_csum[] = {
+	0xda83, 0x45da, 0x4f46, 0x4e4f, 0x34e,	0xe902, 0xa5e9, 0x87a5, 0x7187,
+	0x5671, 0xf556, 0x6df5, 0x816d, 0x8f81, 0xbb8f, 0xfbba, 0x5afb, 0xbe5a,
+	0xedbe, 0xabee, 0x6aac, 0xe6b,	0xea0d, 0x67ea, 0x7e68, 0x8a7e, 0x6f8a,
+	0x3a70, 0x9f3a, 0xe89e, 0x75e8, 0x7976, 0xfa79, 0x2cfa, 0x3c2c, 0x463c,
+	0x7146, 0x7a71, 0x547a, 0xfd53, 0x99fc, 0xb699, 0x92b6, 0xdb91, 0xe8da,
+	0x5fe9, 0x1e60, 0xae1d, 0x39ae, 0xf439, 0xa1f4, 0xdda1, 0xede,	0x790f,
+	0x579,	0x1206, 0x9012, 0x2490, 0xd224, 0x5cd2, 0xa65d, 0xca7,	0x220d,
+	0xf922, 0xbf9,	0x920b, 0x1b92, 0x361c, 0x2e36, 0x4d2e, 0x24d,	0x2,
+	0xcfff, 0x90cf, 0xa591, 0x93a5, 0x7993, 0x9579, 0xc894, 0x50c8, 0x5f50,
+	0xd55e, 0xcad5, 0xf3c9, 0x8f4,	0x4409, 0x5043, 0x5b50, 0x55b,	0x2205,
+	0x1e22, 0x801e, 0x3780, 0xe137, 0x7ee0, 0xf67d, 0x3cf6, 0xa53c, 0x2ea5,
+	0x472e, 0x5147, 0xcf51, 0x1bcf, 0x951c, 0x1e95, 0xc71e, 0xe4c7, 0xc3e4,
+	0x3dc3, 0xee3d, 0xa4ed, 0xf9a4, 0xcbf8, 0x75cb, 0xb375, 0x50b4, 0x3551,
+	0xf835, 0x19f8, 0x8c1a, 0x538c, 0xad52, 0xa3ac, 0xb0a3, 0x5cb0, 0x6c5c,
+	0x5b6c, 0xc05a, 0x92c0, 0x4792, 0xbe47, 0x53be, 0x1554, 0x5715, 0x4b57,
+	0xe54a, 0x20e5, 0x21,	0xd500, 0xa1d4, 0xa8a1, 0x57a9, 0xca57, 0x5ca,
+	0x1c06, 0x4f1c, 0xe24e, 0xd9e2, 0xf0d9, 0x4af1, 0x474b, 0x8146, 0xe81,
+	0xfd0e, 0x84fd, 0x7c85, 0xba7c, 0x17ba, 0x4a17, 0x964a, 0xf595, 0xff5,
+	0x5310, 0x3253, 0x6432, 0x4263, 0x2242, 0xe121, 0x32e1, 0xf632, 0xc5f5,
+	0x21c6, 0x7d22, 0x8e7c, 0x418e, 0x5641, 0x3156, 0x7c31, 0x737c, 0x373,
+	0x2503, 0xc22a, 0x3c2,	0x4a04, 0x8549, 0x5285, 0xa352, 0xe8a3, 0x6fe8,
+	0x1a6f, 0x211a, 0xe021, 0x38e0, 0x7638, 0xf575, 0x9df5, 0x169e, 0xf116,
+	0x23f1, 0xcd23, 0xece,	0x660f, 0x4866, 0x6a48, 0x716a, 0xee71, 0xa2ee,
+	0xb8a2, 0x61b9, 0xa361, 0xf7a2, 0x26f7, 0x1127, 0x6611, 0xe065, 0x36e0,
+	0x1837, 0x3018, 0x1c30, 0x721b, 0x3e71, 0xe43d, 0x99e4, 0x9e9a, 0xb79d,
+	0xa9b7, 0xcaa,	0xeb0c, 0x4eb,	0x1305, 0x8813, 0xb687, 0xa9b6, 0xfba9,
+	0xd7fb, 0xccd8, 0x2ecd, 0x652f, 0xae65, 0x3fae, 0x3a40, 0x563a, 0x7556,
+	0x2776, 0x1228, 0xef12, 0xf9ee, 0xcef9, 0x56cf, 0xa956, 0x24a9, 0xba24,
+	0x5fba, 0x665f, 0xf465, 0x8ff4, 0x6d8f, 0x346d, 0x5f34, 0x385f, 0xd137,
+	0xb8d0, 0xacb8, 0x55ac, 0x7455, 0xe874, 0x89e8, 0xd189, 0xa0d1, 0xb2a0,
+	0xb8b2, 0x36b8, 0x5636, 0xd355, 0x8d3,	0x1908, 0x2118, 0xc21,	0x990c,
+	0x8b99, 0x158c, 0x7815, 0x9e78, 0x6f9e, 0x4470, 0x1d44, 0x341d, 0x2634,
+	0x3f26, 0x793e, 0xc79,	0xcc0b, 0x26cc, 0xd126, 0x1fd1, 0xb41f, 0xb6b4,
+	0x22b7, 0xa122, 0xa1,	0x7f01, 0x837e, 0x3b83, 0xaf3b, 0x6fae, 0x916f,
+	0xb490, 0xffb3, 0xceff, 0x50cf, 0x7550, 0x7275, 0x1272, 0x2613, 0xaa26,
+	0xd5aa, 0x7d5,	0x9607, 0x96,	0xb100, 0xf8b0, 0x4bf8, 0xdd4c, 0xeddd,
+	0x98ed, 0x2599, 0x9325, 0xeb92, 0x8feb, 0xcc8f, 0x2acd, 0x392b, 0x3b39,
+	0xcb3b, 0x6acb, 0xd46a, 0xb8d4, 0x6ab8, 0x106a, 0x2f10, 0x892f, 0x789,
+	0xc806, 0x45c8, 0x7445, 0x3c74, 0x3a3c, 0xcf39, 0xd7ce, 0x58d8, 0x6e58,
+	0x336e, 0x1034, 0xee10, 0xe9ed, 0xc2e9, 0x3fc2, 0xd53e, 0xd2d4, 0xead2,
+	0x8fea, 0x2190, 0x1162, 0xbe11, 0x8cbe, 0x6d8c, 0xfb6c, 0x6dfb, 0xd36e,
+	0x3ad3, 0xf3a,	0x870e, 0xc287, 0x53c3, 0xc54,	0x5b0c, 0x7d5a, 0x797d,
+	0xec79, 0x5dec, 0x4d5e, 0x184e, 0xd618, 0x60d6, 0xb360, 0x98b3, 0xf298,
+	0xb1f2, 0x69b1, 0xf969, 0xef9,	0xab0e, 0x21ab, 0xe321, 0x24e3, 0x8224,
+	0x5481, 0x5954, 0x7a59, 0xff7a, 0x7dff, 0x1a7d, 0xa51a, 0x46a5, 0x6b47,
+	0xe6b,	0x830e, 0xa083, 0xff9f, 0xd0ff, 0xffd0, 0xe6ff, 0x7de7, 0xc67d,
+	0xd0c6, 0x61d1, 0x3a62, 0xc3b,	0x150c, 0x1715, 0x4517, 0x5345, 0x3954,
+	0xdd39, 0xdadd, 0x32db, 0x6a33, 0xd169, 0x86d1, 0xb687, 0x3fb6, 0x883f,
+	0xa487, 0x39a4, 0x2139, 0xbe20, 0xffbe, 0xedfe, 0x8ded, 0x368e, 0xc335,
+	0x51c3, 0x9851, 0xf297, 0xd6f2, 0xb9d6, 0x95ba, 0x2096, 0xea1f, 0x76e9,
+	0x4e76, 0xe04d, 0xd0df, 0x80d0, 0xa280, 0xfca2, 0x75fc, 0xef75, 0x32ef,
+	0x6833, 0xdf68, 0xc4df, 0x76c4, 0xb77,	0xb10a, 0xbfb1, 0x58bf, 0x5258,
+	0x4d52, 0x6c4d, 0x7e6c, 0xb67e, 0xccb5, 0x8ccc, 0xbe8c, 0xc8bd, 0x9ac8,
+	0xa99b, 0x52a9, 0x2f53, 0xc30,	0x3e0c, 0xb83d, 0x83b7, 0x5383, 0x7e53,
+	0x4f7e, 0xe24e, 0xb3e1, 0x8db3, 0x618e, 0xc861, 0xfcc8, 0x34fc, 0x9b35,
+	0xaa9b, 0xb1aa, 0x5eb1, 0x395e, 0x8639, 0xd486, 0x8bd4, 0x558b, 0x2156,
+	0xf721, 0x4ef6, 0x14f,	0x7301, 0xdd72, 0x49de, 0x894a, 0x9889, 0x8898,
+	0x7788, 0x7b77, 0x637b, 0xb963, 0xabb9, 0x7cab, 0xc87b, 0x21c8, 0xcb21,
+	0xdfca, 0xbfdf, 0xf2bf, 0x6af2, 0x626b, 0xb261, 0x3cb2, 0xc63c, 0xc9c6,
+	0xc9c9, 0xb4c9, 0xf9b4, 0x91f9, 0x4091, 0x3a40, 0xcc39, 0xd1cb, 0x7ed1,
+	0x537f, 0x6753, 0xa167, 0xba49, 0x88ba, 0x7789, 0x3877, 0xf037, 0xd3ef,
+	0xb5d4, 0x55b6, 0xa555, 0xeca4, 0xa1ec, 0xb6a2, 0x7b7,	0x9507, 0xfd94,
+	0x82fd, 0x5c83, 0x765c, 0x9676, 0x3f97, 0xda3f, 0x6fda, 0x646f, 0x3064,
+	0x5e30, 0x655e, 0x6465, 0xcb64, 0xcdca, 0x4ccd, 0x3f4c, 0x243f, 0x6f24,
+	0x656f, 0x6065, 0x3560, 0x3b36, 0xac3b, 0x4aac, 0x714a, 0x7e71, 0xda7e,
+	0x7fda, 0xda7f, 0x6fda, 0xff6f, 0xc6ff, 0xedc6, 0xd4ed, 0x70d5, 0xeb70,
+	0xa3eb, 0x80a3, 0xca80, 0x3fcb, 0x2540, 0xf825, 0x7ef8, 0xf87e, 0x73f8,
+	0xb474, 0xb4b4, 0x92b5, 0x9293, 0x93,	0x3500, 0x7134, 0x9071, 0xfa8f,
+	0x51fa, 0x1452, 0xba13, 0x7ab9, 0x957a, 0x8a95, 0x6e8a, 0x6d6e, 0x7c6d,
+	0x447c, 0x9744, 0x4597, 0x8945, 0xef88, 0x8fee, 0x3190, 0x4831, 0x8447,
+	0xa183, 0x1da1, 0xd41d, 0x2dd4, 0x4f2e, 0xc94e, 0xcbc9, 0xc9cb, 0x9ec9,
+	0x319e, 0xd531, 0x20d5, 0x4021, 0xb23f, 0x29b2, 0xd828, 0xecd8, 0x5ded,
+	0xfc5d, 0x4dfc, 0xd24d, 0x6bd2, 0x5f6b, 0xb35e, 0x7fb3, 0xee7e, 0x56ee,
+	0xa657, 0x68a6, 0x8768, 0x7787, 0xb077, 0x4cb1, 0x764c, 0xb175, 0x7b1,
+	0x3d07, 0x603d, 0x3560, 0x3e35, 0xb03d, 0xd6b0, 0xc8d6, 0xd8c8, 0x8bd8,
+	0x3e8c, 0x303f, 0xd530, 0xf1d4, 0x42f1, 0xca42, 0xddca, 0x41dd, 0x3141,
+	0x132,	0xe901, 0x8e9,	0xbe09, 0xe0bd, 0x2ce0, 0x862d, 0x3986, 0x9139,
+	0x6d91, 0x6a6d, 0x8d6a, 0x1b8d, 0xac1b, 0xedab, 0x54ed, 0xc054, 0xcebf,
+	0xc1ce, 0x5c2,	0x3805, 0x6038, 0x5960, 0xd359, 0xdd3,	0xbe0d, 0xafbd,
+	0x6daf, 0x206d, 0x2c20, 0x862c, 0x8e86, 0xec8d, 0xa2ec, 0xa3a2, 0x51a3,
+	0x8051, 0xfd7f, 0x91fd, 0xa292, 0xaf14, 0xeeae, 0x59ef, 0x535a, 0x8653,
+	0x3986, 0x9539, 0xb895, 0xa0b8, 0x26a0, 0x2227, 0xc022, 0x77c0, 0xad77,
+	0x46ad, 0xaa46, 0x60aa, 0x8560, 0x4785, 0xd747, 0x45d7, 0x2346, 0x5f23,
+	0x25f,	0x1d02, 0x71d,	0x8206, 0xc82,	0x180c, 0x3018, 0x4b30, 0x4b,
+	0x3001, 0x1230, 0x2d12, 0x8c2d, 0x148d, 0x4015, 0x5f3f, 0x3d5f, 0x6b3d,
+	0x396b, 0x473a, 0xf746, 0x44f7, 0x8945, 0x3489, 0xcb34, 0x84ca, 0xd984,
+	0xf0d9, 0xbcf0, 0x63bd, 0x3264, 0xf332, 0x45f3, 0x7346, 0x5673, 0xb056,
+	0xd3b0, 0x4ad4, 0x184b, 0x7d18, 0x6c7d, 0xbb6c, 0xfeba, 0xe0fe, 0x10e1,
+	0x5410, 0x2954, 0x9f28, 0x3a9f, 0x5a3a, 0xdb59, 0xbdc,	0xb40b, 0x1ab4,
+	0x131b, 0x5d12, 0x6d5c, 0xe16c, 0xb0e0, 0x89b0, 0xba88, 0xbb,	0x3c01,
+	0xe13b, 0x6fe1, 0x446f, 0xa344, 0x81a3, 0xfe81, 0xc7fd, 0x38c8, 0xb38,
+	0x1a0b, 0x6d19, 0xf36c, 0x47f3, 0x6d48, 0xb76d, 0xd3b7, 0xd8d2, 0x52d9,
+	0x4b53, 0xa54a, 0x34a5, 0xc534, 0x9bc4, 0xed9b, 0xbeed, 0x3ebe, 0x233e,
+	0x9f22, 0x4a9f, 0x774b, 0x4577, 0xa545, 0x64a5, 0xb65,	0x870b, 0x487,
+	0x9204, 0x5f91, 0xd55f, 0x35d5, 0x1a35, 0x71a,	0x7a07, 0x4e7a, 0xfc4e,
+	0x1efc, 0x481f, 0x7448, 0xde74, 0xa7dd, 0x1ea7, 0xaa1e, 0xcfaa, 0xfbcf,
+	0xedfb, 0x6eee, 0x386f, 0x4538, 0x6e45, 0xd96d, 0x11d9, 0x7912, 0x4b79,
+	0x494b, 0x6049, 0xac5f, 0x65ac, 0x1366, 0x5913, 0xe458, 0x7ae4, 0x387a,
+	0x3c38, 0xb03c, 0x76b0, 0x9376, 0xe193, 0x42e1, 0x7742, 0x6476, 0x3564,
+	0x3c35, 0x6a3c, 0xcc69, 0x94cc, 0x5d95, 0xe5e,	0xee0d, 0x4ced, 0xce4c,
+	0x52ce, 0xaa52, 0xdaaa, 0xe4da, 0x1de5, 0x4530, 0x5445, 0x3954, 0xb639,
+	0x81b6, 0x7381, 0x1574, 0xc215, 0x10c2, 0x3f10, 0x6b3f, 0xe76b, 0x7be7,
+	0xbc7b, 0xf7bb, 0x41f7, 0xcc41, 0x38cc, 0x4239, 0xa942, 0x4a9,	0xc504,
+	0x7cc4, 0x437c, 0x6743, 0xea67, 0x8dea, 0xe88d, 0xd8e8, 0xdcd8, 0x17dd,
+	0x5718, 0x958,	0xa609, 0x41a5, 0x5842, 0x159,	0x9f01, 0x269f, 0x5a26,
+	0x405a, 0xc340, 0xb4c3, 0xd4b4, 0xf4d3, 0xf1f4, 0x39f2, 0xe439, 0x67e4,
+	0x4168, 0xa441, 0xdda3, 0xdedd, 0x9df,	0xab0a, 0xa5ab, 0x9a6,	0xba09,
+	0x9ab9, 0xad9a, 0x5ae,	0xe205, 0xece2, 0xecec, 0x14ed, 0xd614, 0x6bd5,
+	0x916c, 0x3391, 0x6f33, 0x206f, 0x8020, 0x780,	0x7207, 0x2472, 0x8a23,
+	0xb689, 0x3ab6, 0xf739, 0x97f6, 0xb097, 0xa4b0, 0xe6a4, 0x88e6, 0x2789,
+	0xb28,	0x350b, 0x1f35, 0x431e, 0x1043, 0xc30f, 0x79c3, 0x379,	0x5703,
+	0x3256, 0x4732, 0x7247, 0x9d72, 0x489d, 0xd348, 0xa4d3, 0x7ca4, 0xbf7b,
+	0x45c0, 0x7b45, 0x337b, 0x4034, 0x843f, 0xd083, 0x35d0, 0x6335, 0x4d63,
+	0xe14c, 0xcce0, 0xfecc, 0x35ff, 0x5636, 0xf856, 0xeef8, 0x2def, 0xfc2d,
+	0x4fc,	0x6e04, 0xb66d, 0x78b6, 0xbb78, 0x3dbb, 0x9a3d, 0x839a, 0x9283,
+	0x593,	0xd504, 0x23d5, 0x5424, 0xd054, 0x61d0, 0xdb61, 0x17db, 0x1f18,
+	0x381f, 0x9e37, 0x679e, 0x1d68, 0x381d, 0x8038, 0x917f, 0x491,	0xbb04,
+	0x23bb, 0x4124, 0xd41,	0xa30c, 0x8ba3, 0x8b8b, 0xc68b, 0xd2c6, 0xebd2,
+	0x93eb, 0xbd93, 0x99bd, 0x1a99, 0xea19, 0x58ea, 0xcf58, 0x73cf, 0x1073,
+	0x9e10, 0x139e, 0xea13, 0xcde9, 0x3ecd, 0x883f, 0xf89,	0x180f, 0x2a18,
+	0x212a, 0xce20, 0x73ce, 0xf373, 0x60f3, 0xad60, 0x4093, 0x8e40, 0xb98e,
+	0xbfb9, 0xf1bf, 0x8bf1, 0x5e8c, 0xe95e, 0x14e9, 0x4e14, 0x1c4e, 0x7f1c,
+	0xe77e, 0x6fe7, 0xf26f, 0x13f2, 0x8b13, 0xda8a, 0x5fda, 0xea5f, 0x4eea,
+	0xa84f, 0x88a8, 0x1f88, 0x2820, 0x9728, 0x5a97, 0x3f5b, 0xb23f, 0x70b2,
+	0x2c70, 0x232d, 0xf623, 0x4f6,	0x905,	0x7509, 0xd675, 0x28d7, 0x9428,
+	0x3794, 0xf036, 0x2bf0, 0xba2c, 0xedb9, 0xd7ed, 0x59d8, 0xed59, 0x4ed,
+	0xe304, 0x18e3, 0x5c19, 0x3d5c, 0x753d, 0x6d75, 0x956d, 0x7f95, 0xc47f,
+	0x83c4, 0xa84,	0x2e0a, 0x5f2e, 0xb95f, 0x77b9, 0x6d78, 0xf46d, 0x1bf4,
+	0xed1b, 0xd6ed, 0xe0d6, 0x5e1,	0x3905, 0x5638, 0xa355, 0x99a2, 0xbe99,
+	0xb4bd, 0x85b4, 0x2e86, 0x542e, 0x6654, 0xd765, 0x73d7, 0x3a74, 0x383a,
+	0x2638, 0x7826, 0x7677, 0x9a76, 0x7e99, 0x2e7e, 0xea2d, 0xa6ea, 0x8a7,
+	0x109,	0x3300, 0xad32, 0x5fad, 0x465f, 0x2f46, 0xc62f, 0xd4c5, 0xad5,
+	0xcb0a, 0x4cb,	0xb004, 0x7baf, 0xe47b, 0x92e4, 0x8e92, 0x638e, 0x1763,
+	0xc17,	0xf20b, 0x1ff2, 0x8920, 0x5889, 0xcb58, 0xf8cb, 0xcaf8, 0x84cb,
+	0x9f84, 0x8a9f, 0x918a, 0x4991, 0x8249, 0xff81, 0x46ff, 0x5046, 0x5f50,
+	0x725f, 0xf772, 0x8ef7, 0xe08f, 0xc1e0, 0x1fc2, 0x9e1f, 0x8b9d, 0x108b,
+	0x411,	0x2b04, 0xb02a, 0x1fb0, 0x1020, 0x7a0f, 0x587a, 0x8958, 0xb188,
+	0xb1b1, 0x49b2, 0xb949, 0x7ab9, 0x917a, 0xfc91, 0xe6fc, 0x47e7, 0xbc47,
+	0x8fbb, 0xea8e, 0x34ea, 0x2635, 0x1726, 0x9616, 0xc196, 0xa6c1, 0xf3a6,
+	0x11f3, 0x4811, 0x3e48, 0xeb3e, 0xf7ea, 0x1bf8, 0xdb1c, 0x8adb, 0xe18a,
+	0x42e1, 0x9d42, 0x5d9c, 0x6e5d, 0x286e, 0x4928, 0x9a49, 0xb09c, 0xa6b0,
+	0x2a7,	0xe702, 0xf5e6, 0x9af5, 0xf9b,	0x810f, 0x8080, 0x180,	0x1702,
+	0x5117, 0xa650, 0x11a6, 0x1011, 0x550f, 0xd554, 0xbdd5, 0x6bbe, 0xc66b,
+	0xfc7,	0x5510, 0x5555, 0x7655, 0x177,	0x2b02, 0x6f2a, 0xb70,	0x9f0b,
+	0xcf9e, 0xf3cf, 0x3ff4, 0xcb40, 0x8ecb, 0x768e, 0x5277, 0x8652, 0x9186,
+	0x9991, 0x5099, 0xd350, 0x93d3, 0x6d94, 0xe6d,	0x530e, 0x3153, 0xa531,
+	0x64a5, 0x7964, 0x7c79, 0x467c, 0x1746, 0x3017, 0x3730, 0x538,	0x5,
+	0x1e00, 0x5b1e, 0x955a, 0xae95, 0x3eaf, 0xff3e, 0xf8ff, 0xb2f9, 0xa1b3,
+	0xb2a1, 0x5b2,	0xad05, 0x7cac, 0x2d7c, 0xd32c, 0x80d2, 0x7280, 0x8d72,
+	0x1b8e, 0x831b, 0xac82, 0xfdac, 0xa7fd, 0x15a8, 0xd614, 0xe0d5, 0x7be0,
+	0xb37b, 0x61b3, 0x9661, 0x9d95, 0xc79d, 0x83c7, 0xd883, 0xead7, 0xceb,
+	0xf60c, 0xa9f5, 0x19a9, 0xa019, 0x8f9f, 0xd48f, 0x3ad5, 0x853a, 0x985,
+	0x5309, 0x6f52, 0x1370, 0x6e13, 0xa96d, 0x98a9, 0x5198, 0x9f51, 0xb69f,
+	0xa1b6, 0x2ea1, 0x672e, 0x2067, 0x6520, 0xaf65, 0x6eaf, 0x7e6f, 0xee7e,
+	0x17ef, 0xa917, 0xcea8, 0x9ace, 0xff99, 0x5dff, 0xdf5d, 0x38df, 0xa39,
+	0x1c0b, 0xe01b, 0x46e0, 0xcb46, 0x90cb, 0xba90, 0x4bb,	0x9104, 0x9d90,
+	0xc89c, 0xf6c8, 0x6cf6, 0x886c, 0x1789, 0xbd17, 0x70bc, 0x7e71, 0x17e,
+	0x1f01, 0xa01f, 0xbaa0, 0x14bb, 0xfc14, 0x7afb, 0xa07a, 0x3da0, 0xbf3d,
+	0x48bf, 0x8c48, 0x968b, 0x9d96, 0xfd9d, 0x96fd, 0x9796, 0x6b97, 0xd16b,
+	0xf4d1, 0x3bf4, 0x253c, 0x9125, 0x6691, 0xc166, 0x34c1, 0x5735, 0x1a57,
+	0xdc19, 0x77db, 0x8577, 0x4a85, 0x824a, 0x9182, 0x7f91, 0xfd7f, 0xb4c3,
+	0xb5b4, 0xb3b5, 0x7eb3, 0x617e, 0x4e61, 0xa4f,	0x530a, 0x3f52, 0xa33e,
+	0x34a3, 0x9234, 0xf091, 0xf4f0, 0x1bf5, 0x311b, 0x9631, 0x6a96, 0x386b,
+	0x1d39, 0xe91d, 0xe8e9, 0x69e8, 0x426a, 0xee42, 0x89ee, 0x368a, 0x2837,
+	0x7428, 0x5974, 0x6159, 0x1d62, 0x7b1d, 0xf77a, 0x7bf7, 0x6b7c, 0x696c,
+	0xf969, 0x4cf9, 0x714c, 0x4e71, 0x6b4e, 0x256c, 0x6e25, 0xe96d, 0x94e9,
+	0x8f94, 0x3e8f, 0x343e, 0x4634, 0xb646, 0x97b5, 0x8997, 0xe8a,	0x900e,
+	0x8090, 0xfd80, 0xa0fd, 0x16a1, 0xf416, 0xebf4, 0x95ec, 0x1196, 0x8911,
+	0x3d89, 0xda3c, 0x9fd9, 0xd79f, 0x4bd7, 0x214c, 0x3021, 0x4f30, 0x994e,
+	0x5c99, 0x6f5d, 0x326f, 0xab31, 0x6aab, 0xe969, 0x90e9, 0x1190, 0xff10,
+	0xa2fe, 0xe0a2, 0x66e1, 0x4067, 0x9e3f, 0x2d9e, 0x712d, 0x8170, 0xd180,
+	0xffd1, 0x25ff, 0x3826, 0x2538, 0x5f24, 0xc45e, 0x1cc4, 0xdf1c, 0x93df,
+	0xc793, 0x80c7, 0x2380, 0xd223, 0x7ed2, 0xfc7e, 0x22fd, 0x7422, 0x1474,
+	0xb714, 0x7db6, 0x857d, 0xa85,	0xa60a, 0x88a6, 0x4289, 0x7842, 0xc278,
+	0xf7c2, 0xcdf7, 0x84cd, 0xae84, 0x8cae, 0xb98c, 0x1aba, 0x4d1a, 0x884c,
+	0x4688, 0xcc46, 0xd8cb, 0x2bd9, 0xbe2b, 0xa2be, 0x72a2, 0xf772, 0xd2f6,
+	0x75d2, 0xc075, 0xa3c0, 0x63a3, 0xae63, 0x8fae, 0x2a90, 0x5f2a, 0xef5f,
+	0x5cef, 0xa05c, 0x89a0, 0x5e89, 0x6b5e, 0x736b, 0x773,	0x9d07, 0xe99c,
+	0x27ea, 0x2028, 0xc20,	0x980b, 0x4797, 0x2848, 0x9828, 0xc197, 0x48c2,
+	0x2449, 0x7024, 0x570,	0x3e05, 0xd3e,	0xf60c, 0xbbf5, 0x69bb, 0x3f6a,
+	0x740,	0xf006, 0xe0ef, 0xbbe0, 0xadbb, 0x56ad, 0xcf56, 0xbfce, 0xa9bf,
+	0x205b, 0x6920, 0xae69, 0x50ae, 0x2050, 0xf01f, 0x27f0, 0x9427, 0x8993,
+	0x8689, 0x4087, 0x6e40, 0xb16e, 0xa1b1, 0xe8a1, 0x87e8, 0x6f88, 0xfe6f,
+	0x4cfe, 0xe94d, 0xd5e9, 0x47d6, 0x3148, 0x5f31, 0xc35f, 0x13c4, 0xa413,
+	0x5a5,	0x2405, 0xc223, 0x66c2, 0x3667, 0x5e37, 0x5f5e, 0x2f5f, 0x8c2f,
+	0xe48c, 0xd0e4, 0x4d1,	0xd104, 0xe4d0, 0xcee4, 0xfcf,	0x480f, 0xa447,
+	0x5ea4, 0xff5e, 0xbefe, 0x8dbe, 0x1d8e, 0x411d, 0x1841, 0x6918, 0x5469,
+	0x1155, 0xc611, 0xaac6, 0x37ab, 0x2f37, 0xca2e, 0x87ca, 0xbd87, 0xabbd,
+	0xb3ab, 0xcb4,	0xce0c, 0xfccd, 0xa5fd, 0x72a5, 0xf072, 0x83f0, 0xfe83,
+	0x97fd, 0xc997, 0xb0c9, 0xadb0, 0xe6ac, 0x88e6, 0x1088, 0xbe10, 0x16be,
+	0xa916, 0xa3a8, 0x46a3, 0x5447, 0xe953, 0x84e8, 0x2085, 0xa11f, 0xfa1,
+	0xdd0f, 0xbedc, 0x5abe, 0x805a, 0xc97f, 0x6dc9, 0x826d, 0x4a82, 0x934a,
+	0x5293, 0xd852, 0xd3d8, 0xadd3, 0xf4ad, 0xf3f4, 0xfcf3, 0xfefc, 0xcafe,
+	0xb7ca, 0x3cb8, 0xa13c, 0x18a1, 0x1418, 0xea13, 0x91ea, 0xf891, 0x53f8,
+	0xa254, 0xe9a2, 0x87ea, 0x4188, 0x1c41, 0xdc1b, 0xf5db, 0xcaf5, 0x45ca,
+	0x6d45, 0x396d, 0xde39, 0x90dd, 0x1e91, 0x1e,	0x7b00, 0x6a7b, 0xa46a,
+	0xc9a3, 0x9bc9, 0x389b, 0x1139, 0x5211, 0x1f52, 0xeb1f, 0xabeb, 0x48ab,
+	0x9348, 0xb392, 0x17b3, 0x1618, 0x5b16, 0x175b, 0xdc17, 0xdedb, 0x1cdf,
+	0xeb1c, 0xd1ea, 0x4ad2, 0xd4b,	0xc20c, 0x24c2, 0x7b25, 0x137b, 0x8b13,
+	0x618b, 0xa061, 0xff9f, 0xfffe, 0x72ff, 0xf572, 0xe2f5, 0xcfe2, 0xd2cf,
+	0x75d3, 0x6a76, 0xc469, 0x1ec4, 0xfc1d, 0x59fb, 0x455a, 0x7a45, 0xa479,
+	0xb7a4
+};
+
 static u8 tmp_buf[TEST_BUFLEN];
 
 #define full_csum(buff, len, sum) csum_fold(csum_partial(buff, len, sum))
@@ -338,10 +575,58 @@ static void test_csum_no_carry_inputs(struct kunit *test)
 	}
 }
 
+static void test_ip_fast_csum(struct kunit *test)
+{
+	__sum16 csum_result;
+	u16 expected;
+
+	for (int len = IPv4_MIN_WORDS; len < IPv4_MAX_WORDS; len++) {
+		for (int index = 0; index < NUM_IP_FAST_CSUM_TESTS; index++) {
+			csum_result = ip_fast_csum(random_buf + index, len);
+			expected =
+				expected_fast_csum[(len - IPv4_MIN_WORDS) *
+						   NUM_IP_FAST_CSUM_TESTS +
+						   index];
+			CHECK_EQ(to_sum16(expected), csum_result);
+		}
+	}
+}
+
+static void test_csum_ipv6_magic(struct kunit *test)
+{
+#if defined(CONFIG_NET)
+	const struct in6_addr *saddr;
+	const struct in6_addr *daddr;
+	unsigned int len;
+	unsigned char proto;
+	__wsum csum;
+
+	const int daddr_offset = sizeof(struct in6_addr);
+	const int len_offset = sizeof(struct in6_addr) + sizeof(struct in6_addr);
+	const int proto_offset = sizeof(struct in6_addr) + sizeof(struct in6_addr) +
+			     sizeof(int);
+	const int csum_offset = sizeof(struct in6_addr) + sizeof(struct in6_addr) +
+			    sizeof(int) + sizeof(char);
+
+	for (int i = 0; i < NUM_IPv6_TESTS; i++) {
+		saddr = (const struct in6_addr *)(random_buf + i);
+		daddr = (const struct in6_addr *)(random_buf + i +
+						  daddr_offset);
+		len = le32_to_cpu(*(__le32 *)(random_buf + i + len_offset));
+		proto = *(random_buf + i + proto_offset);
+		csum = *(__wsum *)(random_buf + i + csum_offset);
+		CHECK_EQ(to_sum16(expected_csum_ipv6_magic[i]),
+			 csum_ipv6_magic(saddr, daddr, len, proto, csum));
+	}
+#endif /* !CONFIG_NET */
+}
+
 static struct kunit_case __refdata checksum_test_cases[] = {
 	KUNIT_CASE(test_csum_fixed_random_inputs),
 	KUNIT_CASE(test_csum_all_carry_inputs),
 	KUNIT_CASE(test_csum_no_carry_inputs),
+	KUNIT_CASE(test_ip_fast_csum),
+	KUNIT_CASE(test_csum_ipv6_magic),
 	{}
 };
 
diff --git a/lib/cmdline_kunit.c b/lib/cmdline_kunit.c
index d4572dbc9145..705b82736be0 100644
--- a/lib/cmdline_kunit.c
+++ b/lib/cmdline_kunit.c
@@ -124,7 +124,7 @@ static void cmdline_do_one_range_test(struct kunit *test, const char *in,
 			    n, e[0], r[0]);
 
 	p = memchr_inv(&r[1], 0, sizeof(r) - sizeof(r[0]));
-	KUNIT_EXPECT_PTR_EQ_MSG(test, p, NULL, "in test %u at %u out of bound", n, p - r);
+	KUNIT_EXPECT_PTR_EQ_MSG(test, p, NULL, "in test %u at %td out of bound", n, p - r);
 }
 
 static void cmdline_test_range(struct kunit *test)
diff --git a/lib/fw_table.c b/lib/fw_table.c
index c49a09ee3853..c3569d2ba503 100644
--- a/lib/fw_table.c
+++ b/lib/fw_table.c
@@ -12,12 +12,14 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/types.h>
+#include <linux/fw_table.h>
 
 enum acpi_subtable_type {
 	ACPI_SUBTABLE_COMMON,
 	ACPI_SUBTABLE_HMAT,
 	ACPI_SUBTABLE_PRMT,
 	ACPI_SUBTABLE_CEDT,
+	CDAT_SUBTABLE,
 };
 
 struct acpi_subtable_entry {
@@ -25,7 +27,7 @@ struct acpi_subtable_entry {
 	enum acpi_subtable_type type;
 };
 
-static unsigned long __init_or_acpilib
+static unsigned long __init_or_fwtbl_lib
 acpi_get_entry_type(struct acpi_subtable_entry *entry)
 {
 	switch (entry->type) {
@@ -37,11 +39,13 @@ acpi_get_entry_type(struct acpi_subtable_entry *entry)
 		return 0;
 	case ACPI_SUBTABLE_CEDT:
 		return entry->hdr->cedt.type;
+	case CDAT_SUBTABLE:
+		return entry->hdr->cdat.type;
 	}
 	return 0;
 }
 
-static unsigned long __init_or_acpilib
+static unsigned long __init_or_fwtbl_lib
 acpi_get_entry_length(struct acpi_subtable_entry *entry)
 {
 	switch (entry->type) {
@@ -53,11 +57,16 @@ acpi_get_entry_length(struct acpi_subtable_entry *entry)
 		return entry->hdr->prmt.length;
 	case ACPI_SUBTABLE_CEDT:
 		return entry->hdr->cedt.length;
+	case CDAT_SUBTABLE: {
+		__le16 length = (__force __le16)entry->hdr->cdat.length;
+
+		return le16_to_cpu(length);
+	}
 	}
 	return 0;
 }
 
-static unsigned long __init_or_acpilib
+static unsigned long __init_or_fwtbl_lib
 acpi_get_subtable_header_length(struct acpi_subtable_entry *entry)
 {
 	switch (entry->type) {
@@ -69,11 +78,13 @@ acpi_get_subtable_header_length(struct acpi_subtable_entry *entry)
 		return sizeof(entry->hdr->prmt);
 	case ACPI_SUBTABLE_CEDT:
 		return sizeof(entry->hdr->cedt);
+	case CDAT_SUBTABLE:
+		return sizeof(entry->hdr->cdat);
 	}
 	return 0;
 }
 
-static enum acpi_subtable_type __init_or_acpilib
+static enum acpi_subtable_type __init_or_fwtbl_lib
 acpi_get_subtable_type(char *id)
 {
 	if (strncmp(id, ACPI_SIG_HMAT, 4) == 0)
@@ -82,12 +93,27 @@ acpi_get_subtable_type(char *id)
 		return ACPI_SUBTABLE_PRMT;
 	if (strncmp(id, ACPI_SIG_CEDT, 4) == 0)
 		return ACPI_SUBTABLE_CEDT;
+	if (strncmp(id, ACPI_SIG_CDAT, 4) == 0)
+		return CDAT_SUBTABLE;
 	return ACPI_SUBTABLE_COMMON;
 }
 
-static __init_or_acpilib int call_handler(struct acpi_subtable_proc *proc,
-					  union acpi_subtable_headers *hdr,
-					  unsigned long end)
+static unsigned long __init_or_fwtbl_lib
+acpi_table_get_length(enum acpi_subtable_type type,
+		      union fw_table_header *header)
+{
+	if (type == CDAT_SUBTABLE) {
+		__le32 length = (__force __le32)header->cdat.length;
+
+		return le32_to_cpu(length);
+	}
+
+	return header->acpi.length;
+}
+
+static __init_or_fwtbl_lib int call_handler(struct acpi_subtable_proc *proc,
+					    union acpi_subtable_headers *hdr,
+					    unsigned long end)
 {
 	if (proc->handler)
 		return proc->handler(hdr, end);
@@ -119,22 +145,25 @@ static __init_or_acpilib int call_handler(struct acpi_subtable_proc *proc,
  * On success returns sum of all matching entries for all proc handlers.
  * Otherwise, -ENODEV or -EINVAL is returned.
  */
-int __init_or_acpilib
+int __init_or_fwtbl_lib
 acpi_parse_entries_array(char *id, unsigned long table_size,
-			 struct acpi_table_header *table_header,
+			 union fw_table_header *table_header,
 			 struct acpi_subtable_proc *proc,
 			 int proc_num, unsigned int max_entries)
 {
 	unsigned long table_end, subtable_len, entry_len;
 	struct acpi_subtable_entry entry;
+	enum acpi_subtable_type type;
 	int count = 0;
 	int i;
 
-	table_end = (unsigned long)table_header + table_header->length;
+	type = acpi_get_subtable_type(id);
+	table_end = (unsigned long)table_header +
+		    acpi_table_get_length(type, table_header);
 
 	/* Parse all entries looking for a match. */
 
-	entry.type = acpi_get_subtable_type(id);
+	entry.type = type;
 	entry.hdr = (union acpi_subtable_headers *)
 	    ((unsigned long)table_header + table_size);
 	subtable_len = acpi_get_subtable_header_length(&entry);
@@ -174,3 +203,25 @@ acpi_parse_entries_array(char *id, unsigned long table_size,
 
 	return count;
 }
+
+int __init_or_fwtbl_lib
+cdat_table_parse(enum acpi_cdat_type type,
+		 acpi_tbl_entry_handler_arg handler_arg,
+		 void *arg,
+		 struct acpi_table_cdat *table_header)
+{
+	struct acpi_subtable_proc proc = {
+		.id		= type,
+		.handler_arg	= handler_arg,
+		.arg		= arg,
+	};
+
+	if (!table_header)
+		return -EINVAL;
+
+	return acpi_parse_entries_array(ACPI_SIG_CDAT,
+					sizeof(struct acpi_table_cdat),
+					(union fw_table_header *)table_header,
+					&proc, 1, 0);
+}
+EXPORT_SYMBOL_FWTBL_LIB(cdat_table_parse);
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index e0aa6b440ca5..4a6a9f419bd7 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -166,7 +166,6 @@ void iov_iter_init(struct iov_iter *i, unsigned int direction,
 	WARN_ON(direction & ~(READ | WRITE));
 	*i = (struct iov_iter) {
 		.iter_type = ITER_IOVEC,
-		.copy_mc = false,
 		.nofault = false,
 		.data_source = direction,
 		.__iov = iov,
@@ -245,26 +244,8 @@ EXPORT_SYMBOL_GPL(_copy_mc_to_iter);
 #endif /* CONFIG_ARCH_HAS_COPY_MC */
 
 static __always_inline
-size_t memcpy_from_iter_mc(void *iter_from, size_t progress,
-			   size_t len, void *to, void *priv2)
-{
-	return copy_mc_to_kernel(to + progress, iter_from, len);
-}
-
-static size_t __copy_from_iter_mc(void *addr, size_t bytes, struct iov_iter *i)
-{
-	if (unlikely(i->count < bytes))
-		bytes = i->count;
-	if (unlikely(!bytes))
-		return 0;
-	return iterate_bvec(i, bytes, addr, NULL, memcpy_from_iter_mc);
-}
-
-static __always_inline
 size_t __copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
 {
-	if (unlikely(iov_iter_is_copy_mc(i)))
-		return __copy_from_iter_mc(addr, bytes, i);
 	return iterate_and_advance(i, bytes, addr,
 				   copy_from_user_iter, memcpy_from_iter);
 }
@@ -633,7 +614,6 @@ void iov_iter_kvec(struct iov_iter *i, unsigned int direction,
 	WARN_ON(direction & ~(READ | WRITE));
 	*i = (struct iov_iter){
 		.iter_type = ITER_KVEC,
-		.copy_mc = false,
 		.data_source = direction,
 		.kvec = kvec,
 		.nr_segs = nr_segs,
@@ -650,7 +630,6 @@ void iov_iter_bvec(struct iov_iter *i, unsigned int direction,
 	WARN_ON(direction & ~(READ | WRITE));
 	*i = (struct iov_iter){
 		.iter_type = ITER_BVEC,
-		.copy_mc = false,
 		.data_source = direction,
 		.bvec = bvec,
 		.nr_segs = nr_segs,
@@ -679,7 +658,6 @@ void iov_iter_xarray(struct iov_iter *i, unsigned int direction,
 	BUG_ON(direction & ~1);
 	*i = (struct iov_iter) {
 		.iter_type = ITER_XARRAY,
-		.copy_mc = false,
 		.data_source = direction,
 		.xarray = xarray,
 		.xarray_start = start,
@@ -703,7 +681,6 @@ void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count)
 	BUG_ON(direction != READ);
 	*i = (struct iov_iter){
 		.iter_type = ITER_DISCARD,
-		.copy_mc = false,
 		.data_source = false,
 		.count = count,
 		.iov_offset = 0
@@ -714,12 +691,11 @@ EXPORT_SYMBOL(iov_iter_discard);
 static bool iov_iter_aligned_iovec(const struct iov_iter *i, unsigned addr_mask,
 				   unsigned len_mask)
 {
+	const struct iovec *iov = iter_iov(i);
 	size_t size = i->count;
 	size_t skip = i->iov_offset;
-	unsigned k;
 
-	for (k = 0; k < i->nr_segs; k++, skip = 0) {
-		const struct iovec *iov = iter_iov(i) + k;
+	do {
 		size_t len = iov->iov_len - skip;
 
 		if (len > size)
@@ -729,34 +705,36 @@ static bool iov_iter_aligned_iovec(const struct iov_iter *i, unsigned addr_mask,
 		if ((unsigned long)(iov->iov_base + skip) & addr_mask)
 			return false;
 
+		iov++;
 		size -= len;
-		if (!size)
-			break;
-	}
+		skip = 0;
+	} while (size);
+
 	return true;
 }
 
 static bool iov_iter_aligned_bvec(const struct iov_iter *i, unsigned addr_mask,
 				  unsigned len_mask)
 {
-	size_t size = i->count;
+	const struct bio_vec *bvec = i->bvec;
 	unsigned skip = i->iov_offset;
-	unsigned k;
+	size_t size = i->count;
 
-	for (k = 0; k < i->nr_segs; k++, skip = 0) {
-		size_t len = i->bvec[k].bv_len - skip;
+	do {
+		size_t len = bvec->bv_len;
 
 		if (len > size)
 			len = size;
 		if (len & len_mask)
 			return false;
-		if ((unsigned long)(i->bvec[k].bv_offset + skip) & addr_mask)
+		if ((unsigned long)(bvec->bv_offset + skip) & addr_mask)
 			return false;
 
+		bvec++;
 		size -= len;
-		if (!size)
-			break;
-	}
+		skip = 0;
+	} while (size);
+
 	return true;
 }
 
@@ -800,13 +778,12 @@ EXPORT_SYMBOL_GPL(iov_iter_is_aligned);
 
 static unsigned long iov_iter_alignment_iovec(const struct iov_iter *i)
 {
+	const struct iovec *iov = iter_iov(i);
 	unsigned long res = 0;
 	size_t size = i->count;
 	size_t skip = i->iov_offset;
-	unsigned k;
 
-	for (k = 0; k < i->nr_segs; k++, skip = 0) {
-		const struct iovec *iov = iter_iov(i) + k;
+	do {
 		size_t len = iov->iov_len - skip;
 		if (len) {
 			res |= (unsigned long)iov->iov_base + skip;
@@ -814,30 +791,31 @@ static unsigned long iov_iter_alignment_iovec(const struct iov_iter *i)
 				len = size;
 			res |= len;
 			size -= len;
-			if (!size)
-				break;
 		}
-	}
+		iov++;
+		skip = 0;
+	} while (size);
 	return res;
 }
 
 static unsigned long iov_iter_alignment_bvec(const struct iov_iter *i)
 {
+	const struct bio_vec *bvec = i->bvec;
 	unsigned res = 0;
 	size_t size = i->count;
 	unsigned skip = i->iov_offset;
-	unsigned k;
 
-	for (k = 0; k < i->nr_segs; k++, skip = 0) {
-		size_t len = i->bvec[k].bv_len - skip;
-		res |= (unsigned long)i->bvec[k].bv_offset + skip;
+	do {
+		size_t len = bvec->bv_len - skip;
+		res |= (unsigned long)bvec->bv_offset + skip;
 		if (len > size)
 			len = size;
 		res |= len;
+		bvec++;
 		size -= len;
-		if (!size)
-			break;
-	}
+		skip = 0;
+	} while (size);
+
 	return res;
 }
 
@@ -1166,11 +1144,12 @@ const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags)
 EXPORT_SYMBOL(dup_iter);
 
 static __noclone int copy_compat_iovec_from_user(struct iovec *iov,
-		const struct iovec __user *uvec, unsigned long nr_segs)
+		const struct iovec __user *uvec, u32 nr_segs)
 {
 	const struct compat_iovec __user *uiov =
 		(const struct compat_iovec __user *)uvec;
-	int ret = -EFAULT, i;
+	int ret = -EFAULT;
+	u32 i;
 
 	if (!user_access_begin(uiov, nr_segs * sizeof(*uiov)))
 		return -EFAULT;
diff --git a/lib/kobject.c b/lib/kobject.c
index 59dbcbdb1c91..72fa20f405f1 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -74,10 +74,12 @@ static int create_dir(struct kobject *kobj)
 	if (error)
 		return error;
 
-	error = sysfs_create_groups(kobj, ktype->default_groups);
-	if (error) {
-		sysfs_remove_dir(kobj);
-		return error;
+	if (ktype) {
+		error = sysfs_create_groups(kobj, ktype->default_groups);
+		if (error) {
+			sysfs_remove_dir(kobj);
+			return error;
+		}
 	}
 
 	/*
@@ -589,7 +591,8 @@ static void __kobject_del(struct kobject *kobj)
 	sd = kobj->sd;
 	ktype = get_ktype(kobj);
 
-	sysfs_remove_groups(kobj, ktype->default_groups);
+	if (ktype)
+		sysfs_remove_groups(kobj, ktype->default_groups);
 
 	/* send "remove" if the caller did not do it but sent "add" */
 	if (kobj->state_add_uevent_sent && !kobj->state_remove_uevent_sent) {
@@ -666,6 +669,10 @@ static void kobject_cleanup(struct kobject *kobj)
 	pr_debug("'%s' (%p): %s, parent %p\n",
 		 kobject_name(kobj), kobj, __func__, kobj->parent);
 
+	if (t && !t->release)
+		pr_debug("'%s' (%p): does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n",
+			 kobject_name(kobj), kobj);
+
 	/* remove from sysfs if the caller did not do it */
 	if (kobj->state_in_sysfs) {
 		pr_debug("'%s' (%p): auto cleanup kobject_del\n",
@@ -676,13 +683,10 @@ static void kobject_cleanup(struct kobject *kobj)
 		parent = NULL;
 	}
 
-	if (t->release) {
+	if (t && t->release) {
 		pr_debug("'%s' (%p): calling ktype release\n",
 			 kobject_name(kobj), kobj);
 		t->release(kobj);
-	} else {
-		pr_debug("'%s' (%p): does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n",
-			 kobject_name(kobj), kobj);
 	}
 
 	/* free name if we allocated it */
@@ -1056,7 +1060,7 @@ const struct kobj_ns_type_operations *kobj_child_ns_ops(const struct kobject *pa
 {
 	const struct kobj_ns_type_operations *ops = NULL;
 
-	if (parent && parent->ktype->child_ns_type)
+	if (parent && parent->ktype && parent->ktype->child_ns_type)
 		ops = parent->ktype->child_ns_type(parent);
 
 	return ops;
diff --git a/lib/kunit/device-impl.h b/lib/kunit/device-impl.h
index 54bd55836405..5fcd48ff0f36 100644
--- a/lib/kunit/device-impl.h
+++ b/lib/kunit/device-impl.h
@@ -13,5 +13,7 @@
 
 // For internal use only -- registers the kunit_bus.
 int kunit_bus_init(void);
+// For internal use only -- unregisters the kunit_bus.
+void kunit_bus_shutdown(void);
 
 #endif //_KUNIT_DEVICE_IMPL_H
diff --git a/lib/kunit/device.c b/lib/kunit/device.c
index f5371287b375..abc603730b8e 100644
--- a/lib/kunit/device.c
+++ b/lib/kunit/device.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/device.h>
+#include <linux/dma-mapping.h>
 
 #include <kunit/test.h>
 #include <kunit/device.h>
@@ -35,7 +36,7 @@ struct kunit_device {
 
 #define to_kunit_device(d) container_of_const(d, struct kunit_device, dev)
 
-static struct bus_type kunit_bus_type = {
+static const struct bus_type kunit_bus_type = {
 	.name		= "kunit",
 };
 
@@ -45,8 +46,8 @@ int kunit_bus_init(void)
 	int error;
 
 	kunit_bus_device = root_device_register("kunit");
-	if (!kunit_bus_device)
-		return -ENOMEM;
+	if (IS_ERR(kunit_bus_device))
+		return PTR_ERR(kunit_bus_device);
 
 	error = bus_register(&kunit_bus_type);
 	if (error)
@@ -54,6 +55,20 @@ int kunit_bus_init(void)
 	return error;
 }
 
+/* Unregister the 'kunit_bus' in case the KUnit module is unloaded. */
+void kunit_bus_shutdown(void)
+{
+	/* Make sure the bus exists before we unregister it. */
+	if (IS_ERR_OR_NULL(kunit_bus_device))
+		return;
+
+	bus_unregister(&kunit_bus_type);
+
+	root_device_unregister(kunit_bus_device);
+
+	kunit_bus_device = NULL;
+}
+
 /* Release a 'fake' KUnit device. */
 static void kunit_device_release(struct device *d)
 {
@@ -119,6 +134,9 @@ static struct kunit_device *kunit_device_register_internal(struct kunit *test,
 		return ERR_PTR(err);
 	}
 
+	kunit_dev->dev.dma_mask = &kunit_dev->dev.coherent_dma_mask;
+	kunit_dev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
+
 	kunit_add_action(test, device_unregister_wrapper, &kunit_dev->dev);
 
 	return kunit_dev;
diff --git a/lib/kunit/executor.c b/lib/kunit/executor.c
index 717b9599036b..70b9a43cd257 100644
--- a/lib/kunit/executor.c
+++ b/lib/kunit/executor.c
@@ -33,13 +33,13 @@ static char *filter_glob_param;
 static char *filter_param;
 static char *filter_action_param;
 
-module_param_named(filter_glob, filter_glob_param, charp, 0400);
+module_param_named(filter_glob, filter_glob_param, charp, 0600);
 MODULE_PARM_DESC(filter_glob,
 		"Filter which KUnit test suites/tests run at boot-time, e.g. list* or list*.*del_test");
-module_param_named(filter, filter_param, charp, 0400);
+module_param_named(filter, filter_param, charp, 0600);
 MODULE_PARM_DESC(filter,
 		"Filter which KUnit test suites/tests run at boot-time using attributes, e.g. speed>slow");
-module_param_named(filter_action, filter_action_param, charp, 0400);
+module_param_named(filter_action, filter_action_param, charp, 0600);
 MODULE_PARM_DESC(filter_action,
 		"Changes behavior of filtered tests using attributes, valid values are:\n"
 		"<none>: do not run filtered tests as normal\n"
@@ -146,6 +146,10 @@ void kunit_free_suite_set(struct kunit_suite_set suite_set)
 	kfree(suite_set.start);
 }
 
+/*
+ * Filter and reallocate test suites. Must return the filtered test suites set
+ * allocated at a valid virtual address or NULL in case of error.
+ */
 struct kunit_suite_set
 kunit_filter_suites(const struct kunit_suite_set *suite_set,
 		    const char *filter_glob,
diff --git a/lib/kunit/executor_test.c b/lib/kunit/executor_test.c
index 22d4ee86dbed..3f7f967e3688 100644
--- a/lib/kunit/executor_test.c
+++ b/lib/kunit/executor_test.c
@@ -129,7 +129,7 @@ static void parse_filter_attr_test(struct kunit *test)
 			GFP_KERNEL);
 	for (j = 0; j < filter_count; j++) {
 		parsed_filters[j] = kunit_next_attr_filter(&filter, &err);
-		KUNIT_ASSERT_EQ_MSG(test, err, 0, "failed to parse filter '%s'", filters[j]);
+		KUNIT_ASSERT_EQ_MSG(test, err, 0, "failed to parse filter from '%s'", filters);
 	}
 
 	KUNIT_EXPECT_STREQ(test, kunit_attr_filter_name(parsed_filters[0]), "speed");
diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c
index c4259d910356..f7980ef236a3 100644
--- a/lib/kunit/kunit-test.c
+++ b/lib/kunit/kunit-test.c
@@ -720,7 +720,7 @@ static void kunit_device_cleanup_test(struct kunit *test)
 	long action_was_run = 0;
 
 	test_device = kunit_device_register(test, "my_device");
-	KUNIT_ASSERT_NOT_NULL(test, test_device);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, test_device);
 
 	/* Add an action to verify cleanup. */
 	devm_add_action(test_device, test_dev_action, &action_was_run);
diff --git a/lib/kunit/test.c b/lib/kunit/test.c
index f95d2093a0aa..1d1475578515 100644
--- a/lib/kunit/test.c
+++ b/lib/kunit/test.c
@@ -17,6 +17,7 @@
 #include <linux/panic.h>
 #include <linux/sched/debug.h>
 #include <linux/sched.h>
+#include <linux/mm.h>
 
 #include "debugfs.h"
 #include "device-impl.h"
@@ -801,12 +802,19 @@ static void kunit_module_exit(struct module *mod)
 	};
 	const char *action = kunit_action();
 
+	/*
+	 * Check if the start address is a valid virtual address to detect
+	 * if the module load sequence has failed and the suite set has not
+	 * been initialized and filtered.
+	 */
+	if (!suite_set.start || !virt_addr_valid(suite_set.start))
+		return;
+
 	if (!action)
 		__kunit_test_suites_exit(mod->kunit_suites,
 					 mod->num_kunit_suites);
 
-	if (suite_set.start)
-		kunit_free_suite_set(suite_set);
+	kunit_free_suite_set(suite_set);
 }
 
 static int kunit_module_notify(struct notifier_block *nb, unsigned long val,
@@ -816,12 +824,12 @@ static int kunit_module_notify(struct notifier_block *nb, unsigned long val,
 
 	switch (val) {
 	case MODULE_STATE_LIVE:
+		kunit_module_init(mod);
 		break;
 	case MODULE_STATE_GOING:
 		kunit_module_exit(mod);
 		break;
 	case MODULE_STATE_COMING:
-		kunit_module_init(mod);
 		break;
 	case MODULE_STATE_UNFORMED:
 		break;
@@ -920,6 +928,9 @@ static void __exit kunit_exit(void)
 #ifdef CONFIG_MODULES
 	unregister_module_notifier(&kunit_mod_nb);
 #endif
+
+	kunit_bus_shutdown();
+
 	kunit_debugfs_cleanup();
 }
 module_exit(kunit_exit);
diff --git a/lib/livepatch/Makefile b/lib/livepatch/Makefile
deleted file mode 100644
index dcc912b3478f..000000000000
--- a/lib/livepatch/Makefile
+++ /dev/null
@@ -1,14 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile for livepatch test code.
-
-obj-$(CONFIG_TEST_LIVEPATCH) += test_klp_atomic_replace.o \
-				test_klp_callbacks_demo.o \
-				test_klp_callbacks_demo2.o \
-				test_klp_callbacks_busy.o \
-				test_klp_callbacks_mod.o \
-				test_klp_livepatch.o \
-				test_klp_shadow_vars.o \
-				test_klp_state.o \
-				test_klp_state2.o \
-				test_klp_state3.o
diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index 6f241bb38799..af0970288727 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -4290,6 +4290,56 @@ exists:
 
 }
 
+/**
+ * mas_alloc_cyclic() - Internal call to find somewhere to store an entry
+ * @mas: The maple state.
+ * @startp: Pointer to ID.
+ * @range_lo: Lower bound of range to search.
+ * @range_hi: Upper bound of range to search.
+ * @entry: The entry to store.
+ * @next: Pointer to next ID to allocate.
+ * @gfp: The GFP_FLAGS to use for allocations.
+ *
+ * Return: 0 if the allocation succeeded without wrapping, 1 if the
+ * allocation succeeded after wrapping, or -EBUSY if there are no
+ * free entries.
+ */
+int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp,
+		void *entry, unsigned long range_lo, unsigned long range_hi,
+		unsigned long *next, gfp_t gfp)
+{
+	unsigned long min = range_lo;
+	int ret = 0;
+
+	range_lo = max(min, *next);
+	ret = mas_empty_area(mas, range_lo, range_hi, 1);
+	if ((mas->tree->ma_flags & MT_FLAGS_ALLOC_WRAPPED) && ret == 0) {
+		mas->tree->ma_flags &= ~MT_FLAGS_ALLOC_WRAPPED;
+		ret = 1;
+	}
+	if (ret < 0 && range_lo > min) {
+		ret = mas_empty_area(mas, min, range_hi, 1);
+		if (ret == 0)
+			ret = 1;
+	}
+	if (ret < 0)
+		return ret;
+
+	do {
+		mas_insert(mas, entry);
+	} while (mas_nomem(mas, gfp));
+	if (mas_is_err(mas))
+		return xa_err(mas->node);
+
+	*startp = mas->index;
+	*next = *startp + 1;
+	if (*next == 0)
+		mas->tree->ma_flags |= MT_FLAGS_ALLOC_WRAPPED;
+
+	return ret;
+}
+EXPORT_SYMBOL(mas_alloc_cyclic);
+
 static __always_inline void mas_rewalk(struct ma_state *mas, unsigned long index)
 {
 retry:
@@ -6443,6 +6493,49 @@ unlock:
 }
 EXPORT_SYMBOL(mtree_alloc_range);
 
+/**
+ * mtree_alloc_cyclic() - Find somewhere to store this entry in the tree.
+ * @mt: The maple tree.
+ * @startp: Pointer to ID.
+ * @range_lo: Lower bound of range to search.
+ * @range_hi: Upper bound of range to search.
+ * @entry: The entry to store.
+ * @next: Pointer to next ID to allocate.
+ * @gfp: The GFP_FLAGS to use for allocations.
+ *
+ * Finds an empty entry in @mt after @next, stores the new index into
+ * the @id pointer, stores the entry at that index, then updates @next.
+ *
+ * @mt must be initialized with the MT_FLAGS_ALLOC_RANGE flag.
+ *
+ * Context: Any context.  Takes and releases the mt.lock.  May sleep if
+ * the @gfp flags permit.
+ *
+ * Return: 0 if the allocation succeeded without wrapping, 1 if the
+ * allocation succeeded after wrapping, -ENOMEM if memory could not be
+ * allocated, -EINVAL if @mt cannot be used, or -EBUSY if there are no
+ * free entries.
+ */
+int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp,
+		void *entry, unsigned long range_lo, unsigned long range_hi,
+		unsigned long *next, gfp_t gfp)
+{
+	int ret;
+
+	MA_STATE(mas, mt, 0, 0);
+
+	if (!mt_is_alloc(mt))
+		return -EINVAL;
+	if (WARN_ON_ONCE(mt_is_reserved(entry)))
+		return -EINVAL;
+	mtree_lock(mt);
+	ret = mas_alloc_cyclic(&mas, startp, entry, range_lo, range_hi,
+			       next, gfp);
+	mtree_unlock(mt);
+	return ret;
+}
+EXPORT_SYMBOL(mtree_alloc_cyclic);
+
 int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp,
 		void *entry, unsigned long size, unsigned long min,
 		unsigned long max, gfp_t gfp)
diff --git a/lib/memcpy_kunit.c b/lib/memcpy_kunit.c
index 440aee705ccc..30e00ef0bf2e 100644
--- a/lib/memcpy_kunit.c
+++ b/lib/memcpy_kunit.c
@@ -32,7 +32,7 @@ struct some_bytes {
 	BUILD_BUG_ON(sizeof(instance.data) != 32);	\
 	for (size_t i = 0; i < sizeof(instance.data); i++) {	\
 		KUNIT_ASSERT_EQ_MSG(test, instance.data[i], v, \
-			"line %d: '%s' not initialized to 0x%02x @ %d (saw 0x%02x)\n", \
+			"line %d: '%s' not initialized to 0x%02x @ %zu (saw 0x%02x)\n", \
 			__LINE__, #instance, v, i, instance.data[i]);	\
 	}	\
 } while (0)
@@ -41,7 +41,7 @@ struct some_bytes {
 	BUILD_BUG_ON(sizeof(one) != sizeof(two)); \
 	for (size_t i = 0; i < sizeof(one); i++) {	\
 		KUNIT_EXPECT_EQ_MSG(test, one.data[i], two.data[i], \
-			"line %d: %s.data[%d] (0x%02x) != %s.data[%d] (0x%02x)\n", \
+			"line %d: %s.data[%zu] (0x%02x) != %s.data[%zu] (0x%02x)\n", \
 			__LINE__, #one, i, one.data[i], #two, i, two.data[i]); \
 	}	\
 	kunit_info(test, "ok: " TEST_OP "() " name "\n");	\
diff --git a/lib/nlattr.c b/lib/nlattr.c
index dc15e7888fc1..be9c576b6e2d 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -30,6 +30,8 @@ static const u8 nla_attr_len[NLA_TYPE_MAX+1] = {
 	[NLA_S16]	= sizeof(s16),
 	[NLA_S32]	= sizeof(s32),
 	[NLA_S64]	= sizeof(s64),
+	[NLA_BE16]	= sizeof(__be16),
+	[NLA_BE32]	= sizeof(__be32),
 };
 
 static const u8 nla_attr_minlen[NLA_TYPE_MAX+1] = {
@@ -43,6 +45,8 @@ static const u8 nla_attr_minlen[NLA_TYPE_MAX+1] = {
 	[NLA_S16]	= sizeof(s16),
 	[NLA_S32]	= sizeof(s32),
 	[NLA_S64]	= sizeof(s64),
+	[NLA_BE16]	= sizeof(__be16),
+	[NLA_BE32]	= sizeof(__be32),
 };
 
 /*
@@ -758,7 +762,7 @@ EXPORT_SYMBOL(nla_find);
  * @dstsize: Size of destination buffer.
  *
  * Copies at most dstsize - 1 bytes into the destination buffer.
- * Unlike strlcpy the destination buffer is always padded out.
+ * Unlike strscpy() the destination buffer is always padded out.
  *
  * Return:
  * * srclen - Returns @nla length (not including the trailing %NUL).
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index d0a5081dfd12..92c6b1fd8989 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -388,11 +388,6 @@ static unsigned int sbq_calc_wake_batch(struct sbitmap_queue *sbq,
 	unsigned int shallow_depth;
 
 	/*
-	 * For each batch, we wake up one queue. We need to make sure that our
-	 * batch size is small enough that the full depth of the bitmap,
-	 * potentially limited by a shallow depth, is enough to wake up all of
-	 * the queues.
-	 *
 	 * Each full word of the bitmap has bits_per_word bits, and there might
 	 * be a partial word. There are depth / bits_per_word full words and
 	 * depth % bits_per_word bits left over. In bitwise arithmetic:
diff --git a/lib/seq_buf.c b/lib/seq_buf.c
index 010c730ca7fc..f3f3436d60a9 100644
--- a/lib/seq_buf.c
+++ b/lib/seq_buf.c
@@ -13,16 +13,26 @@
  * seq_buf_init() more than once to reset the seq_buf to start
  * from scratch.
  */
-#include <linux/uaccess.h>
-#include <linux/seq_file.h>
+
+#include <linux/bug.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/hex.h>
+#include <linux/minmax.h>
+#include <linux/printk.h>
 #include <linux/seq_buf.h>
+#include <linux/seq_file.h>
+#include <linux/sprintf.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
 
 /**
  * seq_buf_can_fit - can the new data fit in the current buffer?
  * @s: the seq_buf descriptor
  * @len: The length to see if it can fit in the current buffer
  *
- * Returns true if there's enough unused space in the seq_buf buffer
+ * Returns: true if there's enough unused space in the seq_buf buffer
  * to fit the amount of new data according to @len.
  */
 static bool seq_buf_can_fit(struct seq_buf *s, size_t len)
@@ -35,7 +45,7 @@ static bool seq_buf_can_fit(struct seq_buf *s, size_t len)
  * @m: the seq_file descriptor that is the destination
  * @s: the seq_buf descriptor that is the source.
  *
- * Returns zero on success, non zero otherwise
+ * Returns: zero on success, non-zero otherwise.
  */
 int seq_buf_print_seq(struct seq_file *m, struct seq_buf *s)
 {
@@ -50,9 +60,9 @@ int seq_buf_print_seq(struct seq_file *m, struct seq_buf *s)
  * @fmt: printf format string
  * @args: va_list of arguments from a printf() type function
  *
- * Writes a vnprintf() format into the sequencce buffer.
+ * Writes a vnprintf() format into the sequence buffer.
  *
- * Returns zero on success, -1 on overflow.
+ * Returns: zero on success, -1 on overflow.
  */
 int seq_buf_vprintf(struct seq_buf *s, const char *fmt, va_list args)
 {
@@ -78,7 +88,7 @@ int seq_buf_vprintf(struct seq_buf *s, const char *fmt, va_list args)
  *
  * Writes a printf() format into the sequence buffer.
  *
- * Returns zero on success, -1 on overflow.
+ * Returns: zero on success, -1 on overflow.
  */
 int seq_buf_printf(struct seq_buf *s, const char *fmt, ...)
 {
@@ -94,12 +104,12 @@ int seq_buf_printf(struct seq_buf *s, const char *fmt, ...)
 EXPORT_SYMBOL_GPL(seq_buf_printf);
 
 /**
- * seq_buf_do_printk - printk seq_buf line by line
+ * seq_buf_do_printk - printk() seq_buf line by line
  * @s: seq_buf descriptor
  * @lvl: printk level
  *
  * printk()-s a multi-line sequential buffer line by line. The function
- * makes sure that the buffer in @s is nul terminated and safe to read
+ * makes sure that the buffer in @s is NUL-terminated and safe to read
  * as a string.
  */
 void seq_buf_do_printk(struct seq_buf *s, const char *lvl)
@@ -139,7 +149,7 @@ EXPORT_SYMBOL_GPL(seq_buf_do_printk);
  * This function will take the format and the binary array and finish
  * the conversion into the ASCII string within the buffer.
  *
- * Returns zero on success, -1 on overflow.
+ * Returns: zero on success, -1 on overflow.
  */
 int seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary)
 {
@@ -167,7 +177,7 @@ int seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary)
  *
  * Copy a simple string into the sequence buffer.
  *
- * Returns zero on success, -1 on overflow
+ * Returns: zero on success, -1 on overflow.
  */
 int seq_buf_puts(struct seq_buf *s, const char *str)
 {
@@ -196,7 +206,7 @@ EXPORT_SYMBOL_GPL(seq_buf_puts);
  *
  * Copy a single character into the sequence buffer.
  *
- * Returns zero on success, -1 on overflow
+ * Returns: zero on success, -1 on overflow.
  */
 int seq_buf_putc(struct seq_buf *s, unsigned char c)
 {
@@ -212,7 +222,7 @@ int seq_buf_putc(struct seq_buf *s, unsigned char c)
 EXPORT_SYMBOL_GPL(seq_buf_putc);
 
 /**
- * seq_buf_putmem - write raw data into the sequenc buffer
+ * seq_buf_putmem - write raw data into the sequence buffer
  * @s: seq_buf descriptor
  * @mem: The raw memory to copy into the buffer
  * @len: The length of the raw memory to copy (in bytes)
@@ -221,7 +231,7 @@ EXPORT_SYMBOL_GPL(seq_buf_putc);
  * buffer and a strcpy() would not work. Using this function allows
  * for such cases.
  *
- * Returns zero on success, -1 on overflow
+ * Returns: zero on success, -1 on overflow.
  */
 int seq_buf_putmem(struct seq_buf *s, const void *mem, unsigned int len)
 {
@@ -249,7 +259,7 @@ int seq_buf_putmem(struct seq_buf *s, const void *mem, unsigned int len)
  * raw memory into the buffer it writes its ASCII representation of it
  * in hex characters.
  *
- * Returns zero on success, -1 on overflow
+ * Returns: zero on success, -1 on overflow.
  */
 int seq_buf_putmem_hex(struct seq_buf *s, const void *mem,
 		       unsigned int len)
@@ -297,7 +307,7 @@ int seq_buf_putmem_hex(struct seq_buf *s, const void *mem,
  *
  * Write a path name into the sequence buffer.
  *
- * Returns the number of written bytes on success, -1 on overflow
+ * Returns: the number of written bytes on success, -1 on overflow.
  */
 int seq_buf_path(struct seq_buf *s, const struct path *path, const char *esc)
 {
@@ -332,6 +342,7 @@ int seq_buf_path(struct seq_buf *s, const struct path *path, const char *esc)
  * or until it reaches the end of the content in the buffer (@s->len),
  * whichever comes first.
  *
+ * Returns:
  * On success, it returns a positive number of the number of bytes
  * it copied.
  *
@@ -382,11 +393,11 @@ int seq_buf_to_user(struct seq_buf *s, char __user *ubuf, size_t start, int cnt)
  * linebuf size is maximal length for one line.
  * 32 * 3 - maximum bytes per line, each printed into 2 chars + 1 for
  *	separating space
- * 2 - spaces separating hex dump and ascii representation
- * 32 - ascii representation
+ * 2 - spaces separating hex dump and ASCII representation
+ * 32 - ASCII representation
  * 1 - terminating '\0'
  *
- * Returns zero on success, -1 on overflow
+ * Returns: zero on success, -1 on overflow.
  */
 int seq_buf_hex_dump(struct seq_buf *s, const char *prefix_str, int prefix_type,
 		     int rowsize, int groupsize,
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index a0be5d05c7f0..4a7055a63d9f 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -14,6 +14,7 @@
 
 #define pr_fmt(fmt) "stackdepot: " fmt
 
+#include <linux/debugfs.h>
 #include <linux/gfp.h>
 #include <linux/jhash.h>
 #include <linux/kernel.h>
@@ -21,8 +22,10 @@
 #include <linux/list.h>
 #include <linux/mm.h>
 #include <linux/mutex.h>
-#include <linux/percpu.h>
+#include <linux/poison.h>
 #include <linux/printk.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
 #include <linux/refcount.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -41,17 +44,7 @@
 #define DEPOT_OFFSET_BITS (DEPOT_POOL_ORDER + PAGE_SHIFT - DEPOT_STACK_ALIGN)
 #define DEPOT_POOL_INDEX_BITS (DEPOT_HANDLE_BITS - DEPOT_OFFSET_BITS - \
 			       STACK_DEPOT_EXTRA_BITS)
-#if IS_ENABLED(CONFIG_KMSAN) && CONFIG_STACKDEPOT_MAX_FRAMES >= 32
-/*
- * KMSAN is frequently used in fuzzing scenarios and thus saves a lot of stack
- * traces. As KMSAN does not support evicting stack traces from the stack
- * depot, the stack depot capacity might be reached quickly with large stack
- * records. Adjust the maximum number of stack depot pools for this case.
- */
-#define DEPOT_POOLS_CAP (8192 * (CONFIG_STACKDEPOT_MAX_FRAMES / 16))
-#else
 #define DEPOT_POOLS_CAP 8192
-#endif
 #define DEPOT_MAX_POOLS \
 	(((1LL << (DEPOT_POOL_INDEX_BITS)) < DEPOT_POOLS_CAP) ? \
 	 (1LL << (DEPOT_POOL_INDEX_BITS)) : DEPOT_POOLS_CAP)
@@ -67,17 +60,30 @@ union handle_parts {
 };
 
 struct stack_record {
-	struct list_head list;		/* Links in hash table or freelist */
+	struct list_head hash_list;	/* Links in the hash table */
 	u32 hash;			/* Hash in hash table */
 	u32 size;			/* Number of stored frames */
-	union handle_parts handle;
+	union handle_parts handle;	/* Constant after initialization */
 	refcount_t count;
-	unsigned long entries[CONFIG_STACKDEPOT_MAX_FRAMES];	/* Frames */
+	union {
+		unsigned long entries[CONFIG_STACKDEPOT_MAX_FRAMES];	/* Frames */
+		struct {
+			/*
+			 * An important invariant of the implementation is to
+			 * only place a stack record onto the freelist iff its
+			 * refcount is zero. Because stack records with a zero
+			 * refcount are never considered as valid, it is safe to
+			 * union @entries and freelist management state below.
+			 * Conversely, as soon as an entry is off the freelist
+			 * and its refcount becomes non-zero, the below must not
+			 * be accessed until being placed back on the freelist.
+			 */
+			struct list_head free_list;	/* Links in the freelist */
+			unsigned long rcu_state;	/* RCU cookie */
+		};
+	};
 };
 
-#define DEPOT_STACK_RECORD_SIZE \
-	ALIGN(sizeof(struct stack_record), 1 << DEPOT_STACK_ALIGN)
-
 static bool stack_depot_disabled;
 static bool __stack_depot_early_init_requested __initdata = IS_ENABLED(CONFIG_STACKDEPOT_ALWAYS_INIT);
 static bool __stack_depot_early_init_passed __initdata;
@@ -103,17 +109,33 @@ static void *stack_pools[DEPOT_MAX_POOLS];
 static void *new_pool;
 /* Number of pools in stack_pools. */
 static int pools_num;
+/* Offset to the unused space in the currently used pool. */
+static size_t pool_offset = DEPOT_POOL_SIZE;
 /* Freelist of stack records within stack_pools. */
 static LIST_HEAD(free_stacks);
-/*
- * Stack depot tries to keep an extra pool allocated even before it runs out
- * of space in the currently used pool. This flag marks whether this extra pool
- * needs to be allocated. It has the value 0 when either an extra pool is not
- * yet allocated or if the limit on the number of pools is reached.
- */
-static bool new_pool_required = true;
-/* Lock that protects the variables above. */
-static DEFINE_RWLOCK(pool_rwlock);
+/* The lock must be held when performing pool or freelist modifications. */
+static DEFINE_RAW_SPINLOCK(pool_lock);
+
+/* Statistics counters for debugfs. */
+enum depot_counter_id {
+	DEPOT_COUNTER_REFD_ALLOCS,
+	DEPOT_COUNTER_REFD_FREES,
+	DEPOT_COUNTER_REFD_INUSE,
+	DEPOT_COUNTER_FREELIST_SIZE,
+	DEPOT_COUNTER_PERSIST_COUNT,
+	DEPOT_COUNTER_PERSIST_BYTES,
+	DEPOT_COUNTER_COUNT,
+};
+static long counters[DEPOT_COUNTER_COUNT];
+static const char *const counter_names[] = {
+	[DEPOT_COUNTER_REFD_ALLOCS]	= "refcounted_allocations",
+	[DEPOT_COUNTER_REFD_FREES]	= "refcounted_frees",
+	[DEPOT_COUNTER_REFD_INUSE]	= "refcounted_in_use",
+	[DEPOT_COUNTER_FREELIST_SIZE]	= "freelist_size",
+	[DEPOT_COUNTER_PERSIST_COUNT]	= "persistent_count",
+	[DEPOT_COUNTER_PERSIST_BYTES]	= "persistent_bytes",
+};
+static_assert(ARRAY_SIZE(counter_names) == DEPOT_COUNTER_COUNT);
 
 static int __init disable_stack_depot(char *str)
 {
@@ -258,174 +280,273 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(stack_depot_init);
 
-/* Initializes a stack depol pool. */
-static void depot_init_pool(void *pool)
+/*
+ * Initializes new stack pool, and updates the list of pools.
+ */
+static bool depot_init_pool(void **prealloc)
 {
-	int offset;
+	lockdep_assert_held(&pool_lock);
 
-	lockdep_assert_held_write(&pool_rwlock);
+	if (unlikely(pools_num >= DEPOT_MAX_POOLS)) {
+		/* Bail out if we reached the pool limit. */
+		WARN_ON_ONCE(pools_num > DEPOT_MAX_POOLS); /* should never happen */
+		WARN_ON_ONCE(!new_pool); /* to avoid unnecessary pre-allocation */
+		WARN_ONCE(1, "Stack depot reached limit capacity");
+		return false;
+	}
 
-	WARN_ON(!list_empty(&free_stacks));
+	if (!new_pool && *prealloc) {
+		/* We have preallocated memory, use it. */
+		WRITE_ONCE(new_pool, *prealloc);
+		*prealloc = NULL;
+	}
 
-	/* Initialize handles and link stack records into the freelist. */
-	for (offset = 0; offset <= DEPOT_POOL_SIZE - DEPOT_STACK_RECORD_SIZE;
-	     offset += DEPOT_STACK_RECORD_SIZE) {
-		struct stack_record *stack = pool + offset;
+	if (!new_pool)
+		return false; /* new_pool and *prealloc are NULL */
 
-		stack->handle.pool_index = pools_num;
-		stack->handle.offset = offset >> DEPOT_STACK_ALIGN;
-		stack->handle.extra = 0;
+	/* Save reference to the pool to be used by depot_fetch_stack(). */
+	stack_pools[pools_num] = new_pool;
 
-		list_add(&stack->list, &free_stacks);
-	}
+	/*
+	 * Stack depot tries to keep an extra pool allocated even before it runs
+	 * out of space in the currently used pool.
+	 *
+	 * To indicate that a new preallocation is needed new_pool is reset to
+	 * NULL; do not reset to NULL if we have reached the maximum number of
+	 * pools.
+	 */
+	if (pools_num < DEPOT_MAX_POOLS)
+		WRITE_ONCE(new_pool, NULL);
+	else
+		WRITE_ONCE(new_pool, STACK_DEPOT_POISON);
 
-	/* Save reference to the pool to be used by depot_fetch_stack(). */
-	stack_pools[pools_num] = pool;
-	pools_num++;
+	/* Pairs with concurrent READ_ONCE() in depot_fetch_stack(). */
+	WRITE_ONCE(pools_num, pools_num + 1);
+	ASSERT_EXCLUSIVE_WRITER(pools_num);
+
+	pool_offset = 0;
+
+	return true;
 }
 
 /* Keeps the preallocated memory to be used for a new stack depot pool. */
 static void depot_keep_new_pool(void **prealloc)
 {
-	lockdep_assert_held_write(&pool_rwlock);
+	lockdep_assert_held(&pool_lock);
 
 	/*
 	 * If a new pool is already saved or the maximum number of
 	 * pools is reached, do not use the preallocated memory.
 	 */
-	if (!new_pool_required)
+	if (new_pool)
 		return;
 
-	/*
-	 * Use the preallocated memory for the new pool
-	 * as long as we do not exceed the maximum number of pools.
-	 */
-	if (pools_num < DEPOT_MAX_POOLS) {
-		new_pool = *prealloc;
-		*prealloc = NULL;
+	WRITE_ONCE(new_pool, *prealloc);
+	*prealloc = NULL;
+}
+
+/*
+ * Try to initialize a new stack record from the current pool, a cached pool, or
+ * the current pre-allocation.
+ */
+static struct stack_record *depot_pop_free_pool(void **prealloc, size_t size)
+{
+	struct stack_record *stack;
+	void *current_pool;
+	u32 pool_index;
+
+	lockdep_assert_held(&pool_lock);
+
+	if (pool_offset + size > DEPOT_POOL_SIZE) {
+		if (!depot_init_pool(prealloc))
+			return NULL;
 	}
 
-	/*
-	 * At this point, either a new pool is kept or the maximum
-	 * number of pools is reached. In either case, take note that
-	 * keeping another pool is not required.
-	 */
-	new_pool_required = false;
+	if (WARN_ON_ONCE(pools_num < 1))
+		return NULL;
+	pool_index = pools_num - 1;
+	current_pool = stack_pools[pool_index];
+	if (WARN_ON_ONCE(!current_pool))
+		return NULL;
+
+	stack = current_pool + pool_offset;
+
+	/* Pre-initialize handle once. */
+	stack->handle.pool_index = pool_index;
+	stack->handle.offset = pool_offset >> DEPOT_STACK_ALIGN;
+	stack->handle.extra = 0;
+	INIT_LIST_HEAD(&stack->hash_list);
+
+	pool_offset += size;
+
+	return stack;
 }
 
-/* Updates references to the current and the next stack depot pools. */
-static bool depot_update_pools(void **prealloc)
+/* Try to find next free usable entry from the freelist. */
+static struct stack_record *depot_pop_free(void)
 {
-	lockdep_assert_held_write(&pool_rwlock);
+	struct stack_record *stack;
 
-	/* Check if we still have objects in the freelist. */
-	if (!list_empty(&free_stacks))
-		goto out_keep_prealloc;
+	lockdep_assert_held(&pool_lock);
 
-	/* Check if we have a new pool saved and use it. */
-	if (new_pool) {
-		depot_init_pool(new_pool);
-		new_pool = NULL;
+	if (list_empty(&free_stacks))
+		return NULL;
 
-		/* Take note that we might need a new new_pool. */
-		if (pools_num < DEPOT_MAX_POOLS)
-			new_pool_required = true;
+	/*
+	 * We maintain the invariant that the elements in front are least
+	 * recently used, and are therefore more likely to be associated with an
+	 * RCU grace period in the past. Consequently it is sufficient to only
+	 * check the first entry.
+	 */
+	stack = list_first_entry(&free_stacks, struct stack_record, free_list);
+	if (!poll_state_synchronize_rcu(stack->rcu_state))
+		return NULL;
 
-		/* Try keeping the preallocated memory for new_pool. */
-		goto out_keep_prealloc;
-	}
+	list_del(&stack->free_list);
+	counters[DEPOT_COUNTER_FREELIST_SIZE]--;
 
-	/* Bail out if we reached the pool limit. */
-	if (unlikely(pools_num >= DEPOT_MAX_POOLS)) {
-		WARN_ONCE(1, "Stack depot reached limit capacity");
-		return false;
-	}
+	return stack;
+}
 
-	/* Check if we have preallocated memory and use it. */
-	if (*prealloc) {
-		depot_init_pool(*prealloc);
-		*prealloc = NULL;
-		return true;
-	}
+static inline size_t depot_stack_record_size(struct stack_record *s, unsigned int nr_entries)
+{
+	const size_t used = flex_array_size(s, entries, nr_entries);
+	const size_t unused = sizeof(s->entries) - used;
 
-	return false;
+	WARN_ON_ONCE(sizeof(s->entries) < used);
 
-out_keep_prealloc:
-	/* Keep the preallocated memory for a new pool if required. */
-	if (*prealloc)
-		depot_keep_new_pool(prealloc);
-	return true;
+	return ALIGN(sizeof(struct stack_record) - unused, 1 << DEPOT_STACK_ALIGN);
 }
 
 /* Allocates a new stack in a stack depot pool. */
 static struct stack_record *
-depot_alloc_stack(unsigned long *entries, int size, u32 hash, void **prealloc)
+depot_alloc_stack(unsigned long *entries, unsigned int nr_entries, u32 hash, depot_flags_t flags, void **prealloc)
 {
-	struct stack_record *stack;
+	struct stack_record *stack = NULL;
+	size_t record_size;
 
-	lockdep_assert_held_write(&pool_rwlock);
+	lockdep_assert_held(&pool_lock);
 
-	/* Update current and new pools if required and possible. */
-	if (!depot_update_pools(prealloc))
+	/* This should already be checked by public API entry points. */
+	if (WARN_ON_ONCE(!nr_entries))
 		return NULL;
 
-	/* Check if we have a stack record to save the stack trace. */
-	if (list_empty(&free_stacks))
-		return NULL;
+	/* Limit number of saved frames to CONFIG_STACKDEPOT_MAX_FRAMES. */
+	if (nr_entries > CONFIG_STACKDEPOT_MAX_FRAMES)
+		nr_entries = CONFIG_STACKDEPOT_MAX_FRAMES;
 
-	/* Get and unlink the first entry from the freelist. */
-	stack = list_first_entry(&free_stacks, struct stack_record, list);
-	list_del(&stack->list);
+	if (flags & STACK_DEPOT_FLAG_GET) {
+		/*
+		 * Evictable entries have to allocate the max. size so they may
+		 * safely be re-used by differently sized allocations.
+		 */
+		record_size = depot_stack_record_size(stack, CONFIG_STACKDEPOT_MAX_FRAMES);
+		stack = depot_pop_free();
+	} else {
+		record_size = depot_stack_record_size(stack, nr_entries);
+	}
 
-	/* Limit number of saved frames to CONFIG_STACKDEPOT_MAX_FRAMES. */
-	if (size > CONFIG_STACKDEPOT_MAX_FRAMES)
-		size = CONFIG_STACKDEPOT_MAX_FRAMES;
+	if (!stack) {
+		stack = depot_pop_free_pool(prealloc, record_size);
+		if (!stack)
+			return NULL;
+	}
 
 	/* Save the stack trace. */
 	stack->hash = hash;
-	stack->size = size;
-	/* stack->handle is already filled in by depot_init_pool(). */
-	refcount_set(&stack->count, 1);
-	memcpy(stack->entries, entries, flex_array_size(stack, entries, size));
+	stack->size = nr_entries;
+	/* stack->handle is already filled in by depot_pop_free_pool(). */
+	memcpy(stack->entries, entries, flex_array_size(stack, entries, nr_entries));
+
+	if (flags & STACK_DEPOT_FLAG_GET) {
+		refcount_set(&stack->count, 1);
+		counters[DEPOT_COUNTER_REFD_ALLOCS]++;
+		counters[DEPOT_COUNTER_REFD_INUSE]++;
+	} else {
+		/* Warn on attempts to switch to refcounting this entry. */
+		refcount_set(&stack->count, REFCOUNT_SATURATED);
+		counters[DEPOT_COUNTER_PERSIST_COUNT]++;
+		counters[DEPOT_COUNTER_PERSIST_BYTES] += record_size;
+	}
 
 	/*
 	 * Let KMSAN know the stored stack record is initialized. This shall
 	 * prevent false positive reports if instrumented code accesses it.
 	 */
-	kmsan_unpoison_memory(stack, DEPOT_STACK_RECORD_SIZE);
+	kmsan_unpoison_memory(stack, record_size);
 
 	return stack;
 }
 
 static struct stack_record *depot_fetch_stack(depot_stack_handle_t handle)
 {
+	const int pools_num_cached = READ_ONCE(pools_num);
 	union handle_parts parts = { .handle = handle };
 	void *pool;
 	size_t offset = parts.offset << DEPOT_STACK_ALIGN;
 	struct stack_record *stack;
 
-	lockdep_assert_held(&pool_rwlock);
+	lockdep_assert_not_held(&pool_lock);
 
-	if (parts.pool_index > pools_num) {
+	if (parts.pool_index > pools_num_cached) {
 		WARN(1, "pool index %d out of bounds (%d) for stack id %08x\n",
-		     parts.pool_index, pools_num, handle);
+		     parts.pool_index, pools_num_cached, handle);
 		return NULL;
 	}
 
 	pool = stack_pools[parts.pool_index];
-	if (!pool)
+	if (WARN_ON(!pool))
 		return NULL;
 
 	stack = pool + offset;
+	if (WARN_ON(!refcount_read(&stack->count)))
+		return NULL;
+
 	return stack;
 }
 
 /* Links stack into the freelist. */
 static void depot_free_stack(struct stack_record *stack)
 {
-	lockdep_assert_held_write(&pool_rwlock);
+	unsigned long flags;
+
+	lockdep_assert_not_held(&pool_lock);
+
+	raw_spin_lock_irqsave(&pool_lock, flags);
+	printk_deferred_enter();
 
-	list_add(&stack->list, &free_stacks);
+	/*
+	 * Remove the entry from the hash list. Concurrent list traversal may
+	 * still observe the entry, but since the refcount is zero, this entry
+	 * will no longer be considered as valid.
+	 */
+	list_del_rcu(&stack->hash_list);
+
+	/*
+	 * Due to being used from constrained contexts such as the allocators,
+	 * NMI, or even RCU itself, stack depot cannot rely on primitives that
+	 * would sleep (such as synchronize_rcu()) or recursively call into
+	 * stack depot again (such as call_rcu()).
+	 *
+	 * Instead, get an RCU cookie, so that we can ensure this entry isn't
+	 * moved onto another list until the next grace period, and concurrent
+	 * RCU list traversal remains safe.
+	 */
+	stack->rcu_state = get_state_synchronize_rcu();
+
+	/*
+	 * Add the entry to the freelist tail, so that older entries are
+	 * considered first - their RCU cookie is more likely to no longer be
+	 * associated with the current grace period.
+	 */
+	list_add_tail(&stack->free_list, &free_stacks);
+
+	counters[DEPOT_COUNTER_FREELIST_SIZE]++;
+	counters[DEPOT_COUNTER_REFD_FREES]++;
+	counters[DEPOT_COUNTER_REFD_INUSE]--;
+
+	printk_deferred_exit();
+	raw_spin_unlock_irqrestore(&pool_lock, flags);
 }
 
 /* Calculates the hash for a stack. */
@@ -453,22 +574,52 @@ int stackdepot_memcmp(const unsigned long *u1, const unsigned long *u2,
 
 /* Finds a stack in a bucket of the hash table. */
 static inline struct stack_record *find_stack(struct list_head *bucket,
-					     unsigned long *entries, int size,
-					     u32 hash)
+					      unsigned long *entries, int size,
+					      u32 hash, depot_flags_t flags)
 {
-	struct list_head *pos;
-	struct stack_record *found;
+	struct stack_record *stack, *ret = NULL;
 
-	lockdep_assert_held(&pool_rwlock);
+	/*
+	 * Stack depot may be used from instrumentation that instruments RCU or
+	 * tracing itself; use variant that does not call into RCU and cannot be
+	 * traced.
+	 *
+	 * Note: Such use cases must take care when using refcounting to evict
+	 * unused entries, because the stack record free-then-reuse code paths
+	 * do call into RCU.
+	 */
+	rcu_read_lock_sched_notrace();
+
+	list_for_each_entry_rcu(stack, bucket, hash_list) {
+		if (stack->hash != hash || stack->size != size)
+			continue;
+
+		/*
+		 * This may race with depot_free_stack() accessing the freelist
+		 * management state unioned with @entries. The refcount is zero
+		 * in that case and the below refcount_inc_not_zero() will fail.
+		 */
+		if (data_race(stackdepot_memcmp(entries, stack->entries, size)))
+			continue;
+
+		/*
+		 * Try to increment refcount. If this succeeds, the stack record
+		 * is valid and has not yet been freed.
+		 *
+		 * If STACK_DEPOT_FLAG_GET is not used, it is undefined behavior
+		 * to then call stack_depot_put() later, and we can assume that
+		 * a stack record is never placed back on the freelist.
+		 */
+		if ((flags & STACK_DEPOT_FLAG_GET) && !refcount_inc_not_zero(&stack->count))
+			continue;
 
-	list_for_each(pos, bucket) {
-		found = list_entry(pos, struct stack_record, list);
-		if (found->hash == hash &&
-		    found->size == size &&
-		    !stackdepot_memcmp(entries, found->entries, size))
-			return found;
+		ret = stack;
+		break;
 	}
-	return NULL;
+
+	rcu_read_unlock_sched_notrace();
+
+	return ret;
 }
 
 depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
@@ -482,7 +633,6 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
 	struct page *page = NULL;
 	void *prealloc = NULL;
 	bool can_alloc = depot_flags & STACK_DEPOT_FLAG_CAN_ALLOC;
-	bool need_alloc = false;
 	unsigned long flags;
 	u32 hash;
 
@@ -505,31 +655,16 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
 	hash = hash_stack(entries, nr_entries);
 	bucket = &stack_table[hash & stack_hash_mask];
 
-	read_lock_irqsave(&pool_rwlock, flags);
-	printk_deferred_enter();
-
-	/* Fast path: look the stack trace up without full locking. */
-	found = find_stack(bucket, entries, nr_entries, hash);
-	if (found) {
-		if (depot_flags & STACK_DEPOT_FLAG_GET)
-			refcount_inc(&found->count);
-		printk_deferred_exit();
-		read_unlock_irqrestore(&pool_rwlock, flags);
+	/* Fast path: look the stack trace up without locking. */
+	found = find_stack(bucket, entries, nr_entries, hash, depot_flags);
+	if (found)
 		goto exit;
-	}
-
-	/* Take note if another stack pool needs to be allocated. */
-	if (new_pool_required)
-		need_alloc = true;
-
-	printk_deferred_exit();
-	read_unlock_irqrestore(&pool_rwlock, flags);
 
 	/*
 	 * Allocate memory for a new pool if required now:
 	 * we won't be able to do that under the lock.
 	 */
-	if (unlikely(can_alloc && need_alloc)) {
+	if (unlikely(can_alloc && !READ_ONCE(new_pool))) {
 		/*
 		 * Zero out zone modifiers, as we don't have specific zone
 		 * requirements. Keep the flags related to allocation in atomic
@@ -543,31 +678,36 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
 			prealloc = page_address(page);
 	}
 
-	write_lock_irqsave(&pool_rwlock, flags);
+	raw_spin_lock_irqsave(&pool_lock, flags);
 	printk_deferred_enter();
 
-	found = find_stack(bucket, entries, nr_entries, hash);
+	/* Try to find again, to avoid concurrently inserting duplicates. */
+	found = find_stack(bucket, entries, nr_entries, hash, depot_flags);
 	if (!found) {
 		struct stack_record *new =
-			depot_alloc_stack(entries, nr_entries, hash, &prealloc);
+			depot_alloc_stack(entries, nr_entries, hash, depot_flags, &prealloc);
 
 		if (new) {
-			list_add(&new->list, bucket);
+			/*
+			 * This releases the stack record into the bucket and
+			 * makes it visible to readers in find_stack().
+			 */
+			list_add_rcu(&new->hash_list, bucket);
 			found = new;
 		}
-	} else {
-		if (depot_flags & STACK_DEPOT_FLAG_GET)
-			refcount_inc(&found->count);
+	}
+
+	if (prealloc) {
 		/*
-		 * Stack depot already contains this stack trace, but let's
-		 * keep the preallocated memory for future.
+		 * Either stack depot already contains this stack trace, or
+		 * depot_alloc_stack() did not consume the preallocated memory.
+		 * Try to keep the preallocated memory for future.
 		 */
-		if (prealloc)
-			depot_keep_new_pool(&prealloc);
+		depot_keep_new_pool(&prealloc);
 	}
 
 	printk_deferred_exit();
-	write_unlock_irqrestore(&pool_rwlock, flags);
+	raw_spin_unlock_irqrestore(&pool_lock, flags);
 exit:
 	if (prealloc) {
 		/* Stack depot didn't use this memory, free it. */
@@ -592,7 +732,6 @@ unsigned int stack_depot_fetch(depot_stack_handle_t handle,
 			       unsigned long **entries)
 {
 	struct stack_record *stack;
-	unsigned long flags;
 
 	*entries = NULL;
 	/*
@@ -604,13 +743,13 @@ unsigned int stack_depot_fetch(depot_stack_handle_t handle,
 	if (!handle || stack_depot_disabled)
 		return 0;
 
-	read_lock_irqsave(&pool_rwlock, flags);
-	printk_deferred_enter();
-
 	stack = depot_fetch_stack(handle);
-
-	printk_deferred_exit();
-	read_unlock_irqrestore(&pool_rwlock, flags);
+	/*
+	 * Should never be NULL, otherwise this is a use-after-put (or just a
+	 * corrupt handle).
+	 */
+	if (WARN(!stack, "corrupt handle or use after stack_depot_put()"))
+		return 0;
 
 	*entries = stack->entries;
 	return stack->size;
@@ -620,29 +759,20 @@ EXPORT_SYMBOL_GPL(stack_depot_fetch);
 void stack_depot_put(depot_stack_handle_t handle)
 {
 	struct stack_record *stack;
-	unsigned long flags;
 
 	if (!handle || stack_depot_disabled)
 		return;
 
-	write_lock_irqsave(&pool_rwlock, flags);
-	printk_deferred_enter();
-
 	stack = depot_fetch_stack(handle);
-	if (WARN_ON(!stack))
-		goto out;
-
-	if (refcount_dec_and_test(&stack->count)) {
-		/* Unlink stack from the hash table. */
-		list_del(&stack->list);
+	/*
+	 * Should always be able to find the stack record, otherwise this is an
+	 * unbalanced put attempt (or corrupt handle).
+	 */
+	if (WARN(!stack, "corrupt handle or unbalanced stack_depot_put()"))
+		return;
 
-		/* Free stack. */
+	if (refcount_dec_and_test(&stack->count))
 		depot_free_stack(stack);
-	}
-
-out:
-	printk_deferred_exit();
-	write_unlock_irqrestore(&pool_rwlock, flags);
 }
 EXPORT_SYMBOL_GPL(stack_depot_put);
 
@@ -690,3 +820,30 @@ unsigned int stack_depot_get_extra_bits(depot_stack_handle_t handle)
 	return parts.extra;
 }
 EXPORT_SYMBOL(stack_depot_get_extra_bits);
+
+static int stats_show(struct seq_file *seq, void *v)
+{
+	/*
+	 * data race ok: These are just statistics counters, and approximate
+	 * statistics are ok for debugging.
+	 */
+	seq_printf(seq, "pools: %d\n", data_race(pools_num));
+	for (int i = 0; i < DEPOT_COUNTER_COUNT; i++)
+		seq_printf(seq, "%s: %ld\n", counter_names[i], data_race(counters[i]));
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(stats);
+
+static int depot_debugfs_init(void)
+{
+	struct dentry *dir;
+
+	if (stack_depot_disabled)
+		return 0;
+
+	dir = debugfs_create_dir("stackdepot", NULL);
+	debugfs_create_file("stats", 0444, dir, NULL, &stats_fops);
+	return 0;
+}
+late_initcall(depot_debugfs_init);
diff --git a/lib/string.c b/lib/string.c
index be26623953d2..6891d15ce991 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -103,21 +103,6 @@ char *strncpy(char *dest, const char *src, size_t count)
 EXPORT_SYMBOL(strncpy);
 #endif
 
-#ifndef __HAVE_ARCH_STRLCPY
-size_t strlcpy(char *dest, const char *src, size_t size)
-{
-	size_t ret = strlen(src);
-
-	if (size) {
-		size_t len = (ret >= size) ? size - 1 : ret;
-		__builtin_memcpy(dest, src, len);
-		dest[len] = '\0';
-	}
-	return ret;
-}
-EXPORT_SYMBOL(strlcpy);
-#endif
-
 #ifndef __HAVE_ARCH_STRSCPY
 ssize_t strscpy(char *dest, const char *src, size_t count)
 {
diff --git a/lib/test_fortify/write_overflow-strlcpy-src.c b/lib/test_fortify/write_overflow-strlcpy-src.c
deleted file mode 100644
index 91bf83ebd34a..000000000000
--- a/lib/test_fortify/write_overflow-strlcpy-src.c
+++ /dev/null
@@ -1,5 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-#define TEST	\
-	strlcpy(small, large_src, sizeof(small) + 1)
-
-#include "test_fortify.h"
diff --git a/lib/test_fortify/write_overflow-strlcpy.c b/lib/test_fortify/write_overflow-strlcpy.c
deleted file mode 100644
index 1883db7c0cd6..000000000000
--- a/lib/test_fortify/write_overflow-strlcpy.c
+++ /dev/null
@@ -1,5 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-#define TEST	\
-	strlcpy(instance.buf, large_src, sizeof(instance.buf) + 1)
-
-#include "test_fortify.h"
diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c
index 29185ac5c727..399380db449c 100644
--- a/lib/test_maple_tree.c
+++ b/lib/test_maple_tree.c
@@ -3599,6 +3599,45 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	mas_unlock(&mas);
 }
 
+static noinline void __init alloc_cyclic_testing(struct maple_tree *mt)
+{
+	unsigned long location;
+	unsigned long next;
+	int ret = 0;
+	MA_STATE(mas, mt, 0, 0);
+
+	next = 0;
+	mtree_lock(mt);
+	for (int i = 0; i < 100; i++) {
+		mas_alloc_cyclic(&mas, &location, mt, 2, ULONG_MAX, &next, GFP_KERNEL);
+		MAS_BUG_ON(&mas, i != location - 2);
+		MAS_BUG_ON(&mas, mas.index != location);
+		MAS_BUG_ON(&mas, mas.last != location);
+		MAS_BUG_ON(&mas, i != next - 3);
+	}
+
+	mtree_unlock(mt);
+	mtree_destroy(mt);
+	next = 0;
+	mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE);
+	for (int i = 0; i < 100; i++) {
+		mtree_alloc_cyclic(mt, &location, mt, 2, ULONG_MAX, &next, GFP_KERNEL);
+		MT_BUG_ON(mt, i != location - 2);
+		MT_BUG_ON(mt, i != next - 3);
+		MT_BUG_ON(mt, mtree_load(mt, location) != mt);
+	}
+
+	mtree_destroy(mt);
+	/* Overflow test */
+	next = ULONG_MAX - 1;
+	ret = mtree_alloc_cyclic(mt, &location, mt, 2, ULONG_MAX, &next, GFP_KERNEL);
+	MT_BUG_ON(mt, ret != 0);
+	ret = mtree_alloc_cyclic(mt, &location, mt, 2, ULONG_MAX, &next, GFP_KERNEL);
+	MT_BUG_ON(mt, ret != 0);
+	ret = mtree_alloc_cyclic(mt, &location, mt, 2, ULONG_MAX, &next, GFP_KERNEL);
+	MT_BUG_ON(mt, ret != 1);
+}
+
 static DEFINE_MTREE(tree);
 static int __init maple_tree_seed(void)
 {
@@ -3880,6 +3919,11 @@ static int __init maple_tree_seed(void)
 	check_state_handling(&tree);
 	mtree_destroy(&tree);
 
+	mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE);
+	alloc_cyclic_testing(&tree);
+	mtree_destroy(&tree);
+
+
 #if defined(BENCH)
 skip:
 #endif
diff --git a/mm/Kconfig b/mm/Kconfig
index 1902cfe4cc4f..ffc3a2ba3a8c 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1258,6 +1258,9 @@ config LOCK_MM_AND_FIND_VMA
 	bool
 	depends on !STACK_GROWSUP
 
+config IOMMU_MM_DATA
+	bool
+
 source "mm/damon/Kconfig"
 
 endmenu
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 1e3447bccdb1..5f2be8c8df11 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -372,31 +372,6 @@ static int __init default_bdi_init(void)
 }
 subsys_initcall(default_bdi_init);
 
-/*
- * This function is used when the first inode for this wb is marked dirty. It
- * wakes-up the corresponding bdi thread which should then take care of the
- * periodic background write-out of dirty inodes. Since the write-out would
- * starts only 'dirty_writeback_interval' centisecs from now anyway, we just
- * set up a timer which wakes the bdi thread up later.
- *
- * Note, we wouldn't bother setting up the timer, but this function is on the
- * fast-path (used by '__mark_inode_dirty()'), so we save few context switches
- * by delaying the wake-up.
- *
- * We have to be careful not to postpone flush work if it is scheduled for
- * earlier. Thus we use queue_delayed_work().
- */
-void wb_wakeup_delayed(struct bdi_writeback *wb)
-{
-	unsigned long timeout;
-
-	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
-	spin_lock_irq(&wb->work_lock);
-	if (test_bit(WB_registered, &wb->state))
-		queue_delayed_work(bdi_wq, &wb->dwork, timeout);
-	spin_unlock_irq(&wb->work_lock);
-}
-
 static void wb_update_bandwidth_workfn(struct work_struct *work)
 {
 	struct bdi_writeback *wb = container_of(to_delayed_work(work),
@@ -436,7 +411,6 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
 	INIT_LIST_HEAD(&wb->work_list);
 	INIT_DELAYED_WORK(&wb->dwork, wb_workfn);
 	INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn);
-	wb->dirty_sleep = jiffies;
 
 	err = fprop_local_init_percpu(&wb->completions, gfp);
 	if (err)
@@ -921,6 +895,7 @@ int bdi_init(struct backing_dev_info *bdi)
 	INIT_LIST_HEAD(&bdi->bdi_list);
 	INIT_LIST_HEAD(&bdi->wb_list);
 	init_waitqueue_head(&bdi->wb_waitq);
+	bdi->last_bdp_sleep = jiffies;
 
 	return cgwb_bdi_init(bdi);
 }
diff --git a/mm/compaction.c b/mm/compaction.c
index 27ada42924d5..b961db601df4 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -882,6 +882,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 	/* Time to isolate some pages for migration */
 	for (; low_pfn < end_pfn; low_pfn++) {
+		bool is_dirty, is_unevictable;
 
 		if (skip_on_failure && low_pfn >= next_skip_pfn) {
 			/*
@@ -1079,8 +1080,10 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if (!folio_test_lru(folio))
 			goto isolate_fail_put;
 
+		is_unevictable = folio_test_unevictable(folio);
+
 		/* Compaction might skip unevictable pages but CMA takes them */
-		if (!(mode & ISOLATE_UNEVICTABLE) && folio_test_unevictable(folio))
+		if (!(mode & ISOLATE_UNEVICTABLE) && is_unevictable)
 			goto isolate_fail_put;
 
 		/*
@@ -1092,26 +1095,42 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if ((mode & ISOLATE_ASYNC_MIGRATE) && folio_test_writeback(folio))
 			goto isolate_fail_put;
 
-		if ((mode & ISOLATE_ASYNC_MIGRATE) && folio_test_dirty(folio)) {
-			bool migrate_dirty;
+		is_dirty = folio_test_dirty(folio);
+
+		if (((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) ||
+		    (mapping && is_unevictable)) {
+			bool migrate_dirty = true;
+			bool is_unmovable;
 
 			/*
 			 * Only folios without mappings or that have
-			 * a ->migrate_folio callback are possible to
-			 * migrate without blocking.  However, we may
-			 * be racing with truncation, which can free
-			 * the mapping.  Truncation holds the folio lock
-			 * until after the folio is removed from the page
-			 * cache so holding it ourselves is sufficient.
+			 * a ->migrate_folio callback are possible to migrate
+			 * without blocking.
+			 *
+			 * Folios from unmovable mappings are not migratable.
+			 *
+			 * However, we can be racing with truncation, which can
+			 * free the mapping that we need to check. Truncation
+			 * holds the folio lock until after the folio is removed
+			 * from the page so holding it ourselves is sufficient.
+			 *
+			 * To avoid locking the folio just to check unmovable,
+			 * assume every unmovable folio is also unevictable,
+			 * which is a cheaper test.  If our assumption goes
+			 * wrong, it's not a correctness bug, just potentially
+			 * wasted cycles.
 			 */
 			if (!folio_trylock(folio))
 				goto isolate_fail_put;
 
 			mapping = folio_mapping(folio);
-			migrate_dirty = !mapping ||
-					mapping->a_ops->migrate_folio;
+			if ((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) {
+				migrate_dirty = !mapping ||
+						mapping->a_ops->migrate_folio;
+			}
+			is_unmovable = mapping && mapping_unmovable(mapping);
 			folio_unlock(folio);
-			if (!migrate_dirty)
+			if (!migrate_dirty || is_unmovable)
 				goto isolate_fail_put;
 		}
 
@@ -2704,16 +2723,11 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
 		unsigned int alloc_flags, const struct alloc_context *ac,
 		enum compact_priority prio, struct page **capture)
 {
-	int may_perform_io = (__force int)(gfp_mask & __GFP_IO);
 	struct zoneref *z;
 	struct zone *zone;
 	enum compact_result rc = COMPACT_SKIPPED;
 
-	/*
-	 * Check if the GFP flags allow compaction - GFP_NOIO is really
-	 * tricky context because the migration might require IO
-	 */
-	if (!may_perform_io)
+	if (!gfp_compaction_allowed(gfp_mask))
 		return COMPACT_SKIPPED;
 
 	trace_mm_compaction_try_to_compact_pages(order, gfp_mask, prio);
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 36f6f1d21ff0..5b325749fc12 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -1026,6 +1026,9 @@ static void damon_do_apply_schemes(struct damon_ctx *c,
 	damon_for_each_scheme(s, c) {
 		struct damos_quota *quota = &s->quota;
 
+		if (c->passed_sample_intervals != s->next_apply_sis)
+			continue;
+
 		if (!s->wmarks.activated)
 			continue;
 
@@ -1176,10 +1179,6 @@ static void kdamond_apply_schemes(struct damon_ctx *c)
 		if (c->passed_sample_intervals != s->next_apply_sis)
 			continue;
 
-		s->next_apply_sis +=
-			(s->apply_interval_us ? s->apply_interval_us :
-			 c->attrs.aggr_interval) / sample_interval;
-
 		if (!s->wmarks.activated)
 			continue;
 
@@ -1195,6 +1194,14 @@ static void kdamond_apply_schemes(struct damon_ctx *c)
 		damon_for_each_region_safe(r, next_r, t)
 			damon_do_apply_schemes(c, t, r);
 	}
+
+	damon_for_each_scheme(s, c) {
+		if (c->passed_sample_intervals != s->next_apply_sis)
+			continue;
+		s->next_apply_sis +=
+			(s->apply_interval_us ? s->apply_interval_us :
+			 c->attrs.aggr_interval) / sample_interval;
+	}
 }
 
 /*
diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c
index f2e5f9431892..3de2916a65c3 100644
--- a/mm/damon/lru_sort.c
+++ b/mm/damon/lru_sort.c
@@ -185,9 +185,21 @@ static struct damos *damon_lru_sort_new_cold_scheme(unsigned int cold_thres)
 	return damon_lru_sort_new_scheme(&pattern, DAMOS_LRU_DEPRIO);
 }
 
+static void damon_lru_sort_copy_quota_status(struct damos_quota *dst,
+		struct damos_quota *src)
+{
+	dst->total_charged_sz = src->total_charged_sz;
+	dst->total_charged_ns = src->total_charged_ns;
+	dst->charged_sz = src->charged_sz;
+	dst->charged_from = src->charged_from;
+	dst->charge_target_from = src->charge_target_from;
+	dst->charge_addr_from = src->charge_addr_from;
+}
+
 static int damon_lru_sort_apply_parameters(void)
 {
-	struct damos *scheme;
+	struct damos *scheme, *hot_scheme, *cold_scheme;
+	struct damos *old_hot_scheme = NULL, *old_cold_scheme = NULL;
 	unsigned int hot_thres, cold_thres;
 	int err = 0;
 
@@ -195,18 +207,35 @@ static int damon_lru_sort_apply_parameters(void)
 	if (err)
 		return err;
 
+	damon_for_each_scheme(scheme, ctx) {
+		if (!old_hot_scheme) {
+			old_hot_scheme = scheme;
+			continue;
+		}
+		old_cold_scheme = scheme;
+	}
+
 	hot_thres = damon_max_nr_accesses(&damon_lru_sort_mon_attrs) *
 		hot_thres_access_freq / 1000;
-	scheme = damon_lru_sort_new_hot_scheme(hot_thres);
-	if (!scheme)
+	hot_scheme = damon_lru_sort_new_hot_scheme(hot_thres);
+	if (!hot_scheme)
 		return -ENOMEM;
-	damon_set_schemes(ctx, &scheme, 1);
+	if (old_hot_scheme)
+		damon_lru_sort_copy_quota_status(&hot_scheme->quota,
+				&old_hot_scheme->quota);
 
 	cold_thres = cold_min_age / damon_lru_sort_mon_attrs.aggr_interval;
-	scheme = damon_lru_sort_new_cold_scheme(cold_thres);
-	if (!scheme)
+	cold_scheme = damon_lru_sort_new_cold_scheme(cold_thres);
+	if (!cold_scheme) {
+		damon_destroy_scheme(hot_scheme);
 		return -ENOMEM;
-	damon_add_scheme(ctx, scheme);
+	}
+	if (old_cold_scheme)
+		damon_lru_sort_copy_quota_status(&cold_scheme->quota,
+				&old_cold_scheme->quota);
+
+	damon_set_schemes(ctx, &hot_scheme, 1);
+	damon_add_scheme(ctx, cold_scheme);
 
 	return damon_set_region_biggest_system_ram_default(target,
 					&monitor_region_start,
diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c
index ab974e477d2f..66e190f0374a 100644
--- a/mm/damon/reclaim.c
+++ b/mm/damon/reclaim.c
@@ -150,9 +150,20 @@ static struct damos *damon_reclaim_new_scheme(void)
 			&damon_reclaim_wmarks);
 }
 
+static void damon_reclaim_copy_quota_status(struct damos_quota *dst,
+		struct damos_quota *src)
+{
+	dst->total_charged_sz = src->total_charged_sz;
+	dst->total_charged_ns = src->total_charged_ns;
+	dst->charged_sz = src->charged_sz;
+	dst->charged_from = src->charged_from;
+	dst->charge_target_from = src->charge_target_from;
+	dst->charge_addr_from = src->charge_addr_from;
+}
+
 static int damon_reclaim_apply_parameters(void)
 {
-	struct damos *scheme;
+	struct damos *scheme, *old_scheme;
 	struct damos_filter *filter;
 	int err = 0;
 
@@ -164,6 +175,11 @@ static int damon_reclaim_apply_parameters(void)
 	scheme = damon_reclaim_new_scheme();
 	if (!scheme)
 		return -ENOMEM;
+	if (!list_empty(&ctx->schemes)) {
+		damon_for_each_scheme(old_scheme, ctx)
+			damon_reclaim_copy_quota_status(&scheme->quota,
+					&old_scheme->quota);
+	}
 	if (skip_anon) {
 		filter = damos_new_filter(DAMOS_FILTER_TYPE_ANON, true);
 		if (!filter) {
diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c
index 8dbaac6e5c2d..ae0f0b314f3a 100644
--- a/mm/damon/sysfs-schemes.c
+++ b/mm/damon/sysfs-schemes.c
@@ -1905,6 +1905,10 @@ void damos_sysfs_set_quota_scores(struct damon_sysfs_schemes *sysfs_schemes,
 	damon_for_each_scheme(scheme, ctx) {
 		struct damon_sysfs_scheme *sysfs_scheme;
 
+		/* user could have removed the scheme sysfs dir */
+		if (i >= sysfs_schemes->nr)
+			break;
+
 		sysfs_scheme = sysfs_schemes->schemes_arr[i];
 		damos_sysfs_set_quota_score(sysfs_scheme->quotas->goals,
 				&scheme->quota);
@@ -2194,7 +2198,7 @@ static void damos_tried_regions_init_upd_status(
 		sysfs_regions->upd_timeout_jiffies = jiffies +
 			2 * usecs_to_jiffies(scheme->apply_interval_us ?
 					scheme->apply_interval_us :
-					ctx->attrs.sample_interval);
+					ctx->attrs.aggr_interval);
 	}
 }
 
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index 5662e29fe253..65c19025da3d 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -362,6 +362,12 @@ static void __init pud_advanced_tests(struct pgtable_debug_args *args)
 	vaddr &= HPAGE_PUD_MASK;
 
 	pud = pfn_pud(args->pud_pfn, args->page_prot);
+	/*
+	 * Some architectures have debug checks to make sure
+	 * huge pud mapping are only found with devmap entries
+	 * For now test with only devmap entries.
+	 */
+	pud = pud_mkdevmap(pud);
 	set_pud_at(args->mm, vaddr, args->pudp, pud);
 	flush_dcache_page(page);
 	pudp_set_wrprotect(args->mm, vaddr, args->pudp);
@@ -374,6 +380,7 @@ static void __init pud_advanced_tests(struct pgtable_debug_args *args)
 	WARN_ON(!pud_none(pud));
 #endif /* __PAGETABLE_PMD_FOLDED */
 	pud = pfn_pud(args->pud_pfn, args->page_prot);
+	pud = pud_mkdevmap(pud);
 	pud = pud_wrprotect(pud);
 	pud = pud_mkclean(pud);
 	set_pud_at(args->mm, vaddr, args->pudp, pud);
@@ -391,6 +398,7 @@ static void __init pud_advanced_tests(struct pgtable_debug_args *args)
 #endif /* __PAGETABLE_PMD_FOLDED */
 
 	pud = pfn_pud(args->pud_pfn, args->page_prot);
+	pud = pud_mkdevmap(pud);
 	pud = pud_mkyoung(pud);
 	set_pud_at(args->mm, vaddr, args->pudp, pud);
 	flush_dcache_page(page);
diff --git a/mm/filemap.c b/mm/filemap.c
index ea49677c6338..8df4797c5287 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2609,15 +2609,6 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter,
 		end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count);
 
 		/*
-		 * Pairs with a barrier in
-		 * block_write_end()->mark_buffer_dirty() or other page
-		 * dirtying routines like iomap_write_end() to ensure
-		 * changes to page contents are visible before we see
-		 * increased inode size.
-		 */
-		smp_rmb();
-
-		/*
 		 * Once we start copying data, we don't want to be touching any
 		 * cachelines that might be contended:
 		 */
@@ -2688,6 +2679,7 @@ int kiocb_write_and_wait(struct kiocb *iocb, size_t count)
 
 	return filemap_write_and_wait_range(mapping, pos, end);
 }
+EXPORT_SYMBOL_GPL(kiocb_write_and_wait);
 
 int kiocb_invalidate_pages(struct kiocb *iocb, size_t count)
 {
@@ -2715,6 +2707,7 @@ int kiocb_invalidate_pages(struct kiocb *iocb, size_t count)
 	return invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT,
 					     end >> PAGE_SHIFT);
 }
+EXPORT_SYMBOL_GPL(kiocb_invalidate_pages);
 
 /**
  * generic_file_read_iter - generic filesystem read routine
@@ -4109,28 +4102,40 @@ static void filemap_cachestat(struct address_space *mapping,
 
 	rcu_read_lock();
 	xas_for_each(&xas, folio, last_index) {
+		int order;
 		unsigned long nr_pages;
 		pgoff_t folio_first_index, folio_last_index;
 
+		/*
+		 * Don't deref the folio. It is not pinned, and might
+		 * get freed (and reused) underneath us.
+		 *
+		 * We *could* pin it, but that would be expensive for
+		 * what should be a fast and lightweight syscall.
+		 *
+		 * Instead, derive all information of interest from
+		 * the rcu-protected xarray.
+		 */
+
 		if (xas_retry(&xas, folio))
 			continue;
 
+		order = xa_get_order(xas.xa, xas.xa_index);
+		nr_pages = 1 << order;
+		folio_first_index = round_down(xas.xa_index, 1 << order);
+		folio_last_index = folio_first_index + nr_pages - 1;
+
+		/* Folios might straddle the range boundaries, only count covered pages */
+		if (folio_first_index < first_index)
+			nr_pages -= first_index - folio_first_index;
+
+		if (folio_last_index > last_index)
+			nr_pages -= folio_last_index - last_index;
+
 		if (xa_is_value(folio)) {
 			/* page is evicted */
 			void *shadow = (void *)folio;
 			bool workingset; /* not used */
-			int order = xa_get_order(xas.xa, xas.xa_index);
-
-			nr_pages = 1 << order;
-			folio_first_index = round_down(xas.xa_index, 1 << order);
-			folio_last_index = folio_first_index + nr_pages - 1;
-
-			/* Folios might straddle the range boundaries, only count covered pages */
-			if (folio_first_index < first_index)
-				nr_pages -= first_index - folio_first_index;
-
-			if (folio_last_index > last_index)
-				nr_pages -= folio_last_index - last_index;
 
 			cs->nr_evicted += nr_pages;
 
@@ -4148,24 +4153,13 @@ static void filemap_cachestat(struct address_space *mapping,
 			goto resched;
 		}
 
-		nr_pages = folio_nr_pages(folio);
-		folio_first_index = folio_pgoff(folio);
-		folio_last_index = folio_first_index + nr_pages - 1;
-
-		/* Folios might straddle the range boundaries, only count covered pages */
-		if (folio_first_index < first_index)
-			nr_pages -= first_index - folio_first_index;
-
-		if (folio_last_index > last_index)
-			nr_pages -= folio_last_index - last_index;
-
 		/* page is in cache */
 		cs->nr_cache += nr_pages;
 
-		if (folio_test_dirty(folio))
+		if (xas_get_mark(&xas, PAGECACHE_TAG_DIRTY))
 			cs->nr_dirty += nr_pages;
 
-		if (folio_test_writeback(folio))
+		if (xas_get_mark(&xas, PAGECACHE_TAG_WRITEBACK))
 			cs->nr_writeback += nr_pages;
 
 resched:
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 94ef5c02b459..94c958f7ebb5 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -37,6 +37,7 @@
 #include <linux/page_owner.h>
 #include <linux/sched/sysctl.h>
 #include <linux/memory-tiers.h>
+#include <linux/compat.h>
 
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
@@ -809,7 +810,10 @@ static unsigned long __thp_get_unmapped_area(struct file *filp,
 {
 	loff_t off_end = off + len;
 	loff_t off_align = round_up(off, size);
-	unsigned long len_pad, ret;
+	unsigned long len_pad, ret, off_sub;
+
+	if (IS_ENABLED(CONFIG_32BIT) || in_compat_syscall())
+		return 0;
 
 	if (off_end <= off_align || (off_end - off_align) < size)
 		return 0;
@@ -835,7 +839,13 @@ static unsigned long __thp_get_unmapped_area(struct file *filp,
 	if (ret == addr)
 		return addr;
 
-	ret += (off - ret) & (size - 1);
+	off_sub = (off - ret) & (size - 1);
+
+	if (current->mm->get_unmapped_area == arch_get_unmapped_area_topdown &&
+	    !off_sub)
+		return ret + size;
+
+	ret += off_sub;
 	return ret;
 }
 
@@ -2437,7 +2447,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 			page = pmd_page(old_pmd);
 			folio = page_folio(page);
 			if (!folio_test_dirty(folio) && pmd_dirty(old_pmd))
-				folio_set_dirty(folio);
+				folio_mark_dirty(folio);
 			if (!folio_test_referenced(folio) && pmd_young(old_pmd))
 				folio_set_referenced(folio);
 			folio_remove_rmap_pmd(folio, page, vma);
@@ -3563,7 +3573,7 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 	}
 
 	if (pmd_dirty(pmdval))
-		folio_set_dirty(folio);
+		folio_mark_dirty(folio);
 	if (pmd_write(pmdval))
 		entry = make_writable_migration_entry(page_to_pfn(page));
 	else if (anon_exclusive)
diff --git a/mm/init-mm.c b/mm/init-mm.c
index cfd367822cdd..24c809379274 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -44,9 +44,6 @@ struct mm_struct init_mm = {
 #endif
 	.user_ns	= &init_user_ns,
 	.cpu_bitmap	= CPU_BITS_NONE,
-#ifdef CONFIG_IOMMU_SVA
-	.pasid		= IOMMU_PASID_INVALID,
-#endif
 	INIT_MM_CONTEXT(init_mm)
 };
 
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 610efae91220..6ca63e8dda74 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -65,8 +65,7 @@ void kasan_save_track(struct kasan_track *track, gfp_t flags)
 {
 	depot_stack_handle_t stack;
 
-	stack = kasan_save_stack(flags,
-			STACK_DEPOT_FLAG_CAN_ALLOC | STACK_DEPOT_FLAG_GET);
+	stack = kasan_save_stack(flags, STACK_DEPOT_FLAG_CAN_ALLOC);
 	kasan_set_track(track, stack);
 }
 
@@ -266,10 +265,9 @@ bool __kasan_slab_free(struct kmem_cache *cache, void *object,
 		return true;
 
 	/*
-	 * If the object is not put into quarantine, it will likely be quickly
-	 * reallocated. Thus, release its metadata now.
+	 * Note: Keep per-object metadata to allow KASAN print stack traces for
+	 * use-after-free-before-realloc bugs.
 	 */
-	kasan_release_object_meta(cache, object);
 
 	/* Let slab put the object onto the freelist. */
 	return false;
diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c
index 24c13dfb1e94..1900f8576034 100644
--- a/mm/kasan/generic.c
+++ b/mm/kasan/generic.c
@@ -485,15 +485,6 @@ void kasan_init_object_meta(struct kmem_cache *cache, const void *object)
 	if (alloc_meta) {
 		/* Zero out alloc meta to mark it as invalid. */
 		__memset(alloc_meta, 0, sizeof(*alloc_meta));
-
-		/*
-		 * Temporarily disable KASAN bug reporting to allow instrumented
-		 * raw_spin_lock_init to access aux_lock, which resides inside
-		 * of a redzone.
-		 */
-		kasan_disable_current();
-		raw_spin_lock_init(&alloc_meta->aux_lock);
-		kasan_enable_current();
 	}
 
 	/*
@@ -505,42 +496,23 @@ void kasan_init_object_meta(struct kmem_cache *cache, const void *object)
 
 static void release_alloc_meta(struct kasan_alloc_meta *meta)
 {
-	/* Evict the stack traces from stack depot. */
-	stack_depot_put(meta->alloc_track.stack);
-	stack_depot_put(meta->aux_stack[0]);
-	stack_depot_put(meta->aux_stack[1]);
-
 	/* Zero out alloc meta to mark it as invalid. */
 	__memset(meta, 0, sizeof(*meta));
 }
 
 static void release_free_meta(const void *object, struct kasan_free_meta *meta)
 {
+	if (!kasan_arch_is_ready())
+		return;
+
 	/* Check if free meta is valid. */
 	if (*(u8 *)kasan_mem_to_shadow(object) != KASAN_SLAB_FREE_META)
 		return;
 
-	/* Evict the stack trace from the stack depot. */
-	stack_depot_put(meta->free_track.stack);
-
 	/* Mark free meta as invalid. */
 	*(u8 *)kasan_mem_to_shadow(object) = KASAN_SLAB_FREE;
 }
 
-void kasan_release_object_meta(struct kmem_cache *cache, const void *object)
-{
-	struct kasan_alloc_meta *alloc_meta;
-	struct kasan_free_meta *free_meta;
-
-	alloc_meta = kasan_get_alloc_meta(cache, object);
-	if (alloc_meta)
-		release_alloc_meta(alloc_meta);
-
-	free_meta = kasan_get_free_meta(cache, object);
-	if (free_meta)
-		release_free_meta(object, free_meta);
-}
-
 size_t kasan_metadata_size(struct kmem_cache *cache, bool in_object)
 {
 	struct kasan_cache *info = &cache->kasan_info;
@@ -565,8 +537,6 @@ static void __kasan_record_aux_stack(void *addr, depot_flags_t depot_flags)
 	struct kmem_cache *cache;
 	struct kasan_alloc_meta *alloc_meta;
 	void *object;
-	depot_stack_handle_t new_handle, old_handle;
-	unsigned long flags;
 
 	if (is_kfence_address(addr) || !slab)
 		return;
@@ -577,33 +547,18 @@ static void __kasan_record_aux_stack(void *addr, depot_flags_t depot_flags)
 	if (!alloc_meta)
 		return;
 
-	new_handle = kasan_save_stack(0, depot_flags);
-
-	/*
-	 * Temporarily disable KASAN bug reporting to allow instrumented
-	 * spinlock functions to access aux_lock, which resides inside of a
-	 * redzone.
-	 */
-	kasan_disable_current();
-	raw_spin_lock_irqsave(&alloc_meta->aux_lock, flags);
-	old_handle = alloc_meta->aux_stack[1];
 	alloc_meta->aux_stack[1] = alloc_meta->aux_stack[0];
-	alloc_meta->aux_stack[0] = new_handle;
-	raw_spin_unlock_irqrestore(&alloc_meta->aux_lock, flags);
-	kasan_enable_current();
-
-	stack_depot_put(old_handle);
+	alloc_meta->aux_stack[0] = kasan_save_stack(0, depot_flags);
 }
 
 void kasan_record_aux_stack(void *addr)
 {
-	return __kasan_record_aux_stack(addr,
-			STACK_DEPOT_FLAG_CAN_ALLOC | STACK_DEPOT_FLAG_GET);
+	return __kasan_record_aux_stack(addr, STACK_DEPOT_FLAG_CAN_ALLOC);
 }
 
 void kasan_record_aux_stack_noalloc(void *addr)
 {
-	return __kasan_record_aux_stack(addr, STACK_DEPOT_FLAG_GET);
+	return __kasan_record_aux_stack(addr, 0);
 }
 
 void kasan_save_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags)
@@ -614,7 +569,7 @@ void kasan_save_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags)
 	if (!alloc_meta)
 		return;
 
-	/* Evict previous stack traces (might exist for krealloc or mempool). */
+	/* Invalidate previous stack traces (might exist for krealloc or mempool). */
 	release_alloc_meta(alloc_meta);
 
 	kasan_save_track(&alloc_meta->alloc_track, flags);
@@ -628,7 +583,7 @@ void kasan_save_free_info(struct kmem_cache *cache, void *object)
 	if (!free_meta)
 		return;
 
-	/* Evict previous stack trace (might exist for mempool). */
+	/* Invalidate previous stack trace (might exist for mempool). */
 	release_free_meta(object, free_meta);
 
 	kasan_save_track(&free_meta->free_track, 0);
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index d0f172f2b978..fb2b9ac0659a 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -6,7 +6,6 @@
 #include <linux/kasan.h>
 #include <linux/kasan-tags.h>
 #include <linux/kfence.h>
-#include <linux/spinlock.h>
 #include <linux/stackdepot.h>
 
 #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
@@ -265,13 +264,6 @@ struct kasan_global {
 struct kasan_alloc_meta {
 	struct kasan_track alloc_track;
 	/* Free track is stored in kasan_free_meta. */
-	/*
-	 * aux_lock protects aux_stack from accesses from concurrent
-	 * kasan_record_aux_stack calls. It is a raw spinlock to avoid sleeping
-	 * on RT kernels, as kasan_record_aux_stack_noalloc can be called from
-	 * non-sleepable contexts.
-	 */
-	raw_spinlock_t aux_lock;
 	depot_stack_handle_t aux_stack[2];
 };
 
@@ -398,10 +390,8 @@ struct kasan_alloc_meta *kasan_get_alloc_meta(struct kmem_cache *cache,
 struct kasan_free_meta *kasan_get_free_meta(struct kmem_cache *cache,
 						const void *object);
 void kasan_init_object_meta(struct kmem_cache *cache, const void *object);
-void kasan_release_object_meta(struct kmem_cache *cache, const void *object);
 #else
 static inline void kasan_init_object_meta(struct kmem_cache *cache, const void *object) { }
-static inline void kasan_release_object_meta(struct kmem_cache *cache, const void *object) { }
 #endif
 
 depot_stack_handle_t kasan_save_stack(gfp_t flags, depot_flags_t depot_flags);
diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
index 3ba02efb952a..6958aa713c67 100644
--- a/mm/kasan/quarantine.c
+++ b/mm/kasan/quarantine.c
@@ -145,7 +145,10 @@ static void qlink_free(struct qlist_node *qlink, struct kmem_cache *cache)
 	void *object = qlink_to_object(qlink, cache);
 	struct kasan_free_meta *free_meta = kasan_get_free_meta(cache, object);
 
-	kasan_release_object_meta(cache, object);
+	/*
+	 * Note: Keep per-object metadata to allow KASAN print stack traces for
+	 * use-after-free-before-realloc bugs.
+	 */
 
 	/*
 	 * If init_on_free is enabled and KASAN's free metadata is stored in
diff --git a/mm/madvise.c b/mm/madvise.c
index 912155a94ed5..cfa5e7288261 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -429,6 +429,7 @@ restart:
 		if (++batch_count == SWAP_CLUSTER_MAX) {
 			batch_count = 0;
 			if (need_resched()) {
+				arch_leave_lazy_mmu_mode();
 				pte_unmap_unlock(start_pte, ptl);
 				cond_resched();
 				goto restart;
diff --git a/mm/memblock.c b/mm/memblock.c
index 8c194d8afeec..d09136e040d3 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -180,8 +180,9 @@ static inline phys_addr_t memblock_cap_size(phys_addr_t base, phys_addr_t *size)
 /*
  * Address comparison utilities
  */
-static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
-				       phys_addr_t base2, phys_addr_t size2)
+unsigned long __init_memblock
+memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, phys_addr_t base2,
+		       phys_addr_t size2)
 {
 	return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
 }
@@ -1885,7 +1886,7 @@ int __init_memblock memblock_search_pfn_nid(unsigned long pfn,
 	int mid = memblock_search(type, PFN_PHYS(pfn));
 
 	if (mid == -1)
-		return -1;
+		return NUMA_NO_NODE;
 
 	*start_pfn = PFN_DOWN(type->regions[mid].base);
 	*end_pfn = PFN_DOWN(type->regions[mid].base + type->regions[mid].size);
@@ -2176,6 +2177,9 @@ static void __init memmap_init_reserved_pages(void)
 			start = region->base;
 			end = start + region->size;
 
+			if (nid == NUMA_NO_NODE || nid >= MAX_NUMNODES)
+				nid = early_pfn_to_nid(PFN_DOWN(start));
+
 			reserve_bootmem_region(start, end, nid);
 		}
 	}
@@ -2246,6 +2250,7 @@ static const char * const flagname[] = {
 	[ilog2(MEMBLOCK_MIRROR)] = "MIRROR",
 	[ilog2(MEMBLOCK_NOMAP)] = "NOMAP",
 	[ilog2(MEMBLOCK_DRIVER_MANAGED)] = "DRV_MNG",
+	[ilog2(MEMBLOCK_RSRV_NOINIT)] = "RSV_NIT",
 };
 
 static int memblock_debug_show(struct seq_file *m, void *private)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e4c8735e7c85..61932c9215e7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -621,6 +621,15 @@ static inline int memcg_events_index(enum vm_event_item idx)
 }
 
 struct memcg_vmstats_percpu {
+	/* Stats updates since the last flush */
+	unsigned int			stats_updates;
+
+	/* Cached pointers for fast iteration in memcg_rstat_updated() */
+	struct memcg_vmstats_percpu	*parent;
+	struct memcg_vmstats		*vmstats;
+
+	/* The above should fit a single cacheline for memcg_rstat_updated() */
+
 	/* Local (CPU and cgroup) page state & events */
 	long			state[MEMCG_NR_STAT];
 	unsigned long		events[NR_MEMCG_EVENTS];
@@ -632,10 +641,7 @@ struct memcg_vmstats_percpu {
 	/* Cgroup1: threshold notifications & softlimit tree updates */
 	unsigned long		nr_page_events;
 	unsigned long		targets[MEM_CGROUP_NTARGETS];
-
-	/* Stats updates since the last flush */
-	unsigned int		stats_updates;
-};
+} ____cacheline_aligned;
 
 struct memcg_vmstats {
 	/* Aggregated (CPU and subtree) page state & events */
@@ -698,36 +704,35 @@ static void memcg_stats_unlock(void)
 }
 
 
-static bool memcg_should_flush_stats(struct mem_cgroup *memcg)
+static bool memcg_vmstats_needs_flush(struct memcg_vmstats *vmstats)
 {
-	return atomic64_read(&memcg->vmstats->stats_updates) >
+	return atomic64_read(&vmstats->stats_updates) >
 		MEMCG_CHARGE_BATCH * num_online_cpus();
 }
 
 static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
 {
+	struct memcg_vmstats_percpu *statc;
 	int cpu = smp_processor_id();
-	unsigned int x;
 
 	if (!val)
 		return;
 
 	cgroup_rstat_updated(memcg->css.cgroup, cpu);
-
-	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
-		x = __this_cpu_add_return(memcg->vmstats_percpu->stats_updates,
-					  abs(val));
-
-		if (x < MEMCG_CHARGE_BATCH)
+	statc = this_cpu_ptr(memcg->vmstats_percpu);
+	for (; statc; statc = statc->parent) {
+		statc->stats_updates += abs(val);
+		if (statc->stats_updates < MEMCG_CHARGE_BATCH)
 			continue;
 
 		/*
 		 * If @memcg is already flush-able, increasing stats_updates is
 		 * redundant. Avoid the overhead of the atomic update.
 		 */
-		if (!memcg_should_flush_stats(memcg))
-			atomic64_add(x, &memcg->vmstats->stats_updates);
-		__this_cpu_write(memcg->vmstats_percpu->stats_updates, 0);
+		if (!memcg_vmstats_needs_flush(statc->vmstats))
+			atomic64_add(statc->stats_updates,
+				     &statc->vmstats->stats_updates);
+		statc->stats_updates = 0;
 	}
 }
 
@@ -756,7 +761,7 @@ void mem_cgroup_flush_stats(struct mem_cgroup *memcg)
 	if (!memcg)
 		memcg = root_mem_cgroup;
 
-	if (memcg_should_flush_stats(memcg))
+	if (memcg_vmstats_needs_flush(memcg->vmstats))
 		do_flush_stats(memcg);
 }
 
@@ -770,7 +775,7 @@ void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg)
 static void flush_memcg_stats_dwork(struct work_struct *w)
 {
 	/*
-	 * Deliberately ignore memcg_should_flush_stats() here so that flushing
+	 * Deliberately ignore memcg_vmstats_needs_flush() here so that flushing
 	 * in latency-sensitive paths is as cheap as possible.
 	 */
 	do_flush_stats(root_mem_cgroup);
@@ -2623,8 +2628,9 @@ static unsigned long calculate_high_delay(struct mem_cgroup *memcg,
 }
 
 /*
- * Scheduled by try_charge() to be executed from the userland return path
- * and reclaims memory over the high limit.
+ * Reclaims memory over the high limit. Called directly from
+ * try_charge() (context permitting), as well as from the userland
+ * return path where reclaim is always able to block.
  */
 void mem_cgroup_handle_over_high(gfp_t gfp_mask)
 {
@@ -2644,6 +2650,17 @@ void mem_cgroup_handle_over_high(gfp_t gfp_mask)
 
 retry_reclaim:
 	/*
+	 * Bail if the task is already exiting. Unlike memory.max,
+	 * memory.high enforcement isn't as strict, and there is no
+	 * OOM killer involved, which means the excess could already
+	 * be much bigger (and still growing) than it could for
+	 * memory.max; the dying task could get stuck in fruitless
+	 * reclaim for a long time, which isn't desirable.
+	 */
+	if (task_is_dying())
+		goto out;
+
+	/*
 	 * The allocating task should reclaim at least the batch size, but for
 	 * subsequent retries we only want to do what's necessary to prevent oom
 	 * or breaching resource isolation.
@@ -2693,6 +2710,9 @@ retry_reclaim:
 	}
 
 	/*
+	 * Reclaim didn't manage to push usage below the limit, slow
+	 * this allocating task down.
+	 *
 	 * If we exit early, we're guaranteed to die (since
 	 * schedule_timeout_killable sets TASK_KILLABLE). This means we don't
 	 * need to account for any ill-begotten jiffies to pay them off later.
@@ -2887,11 +2907,17 @@ done_restock:
 		}
 	} while ((memcg = parent_mem_cgroup(memcg)));
 
+	/*
+	 * Reclaim is set up above to be called from the userland
+	 * return path. But also attempt synchronous reclaim to avoid
+	 * excessive overrun while the task is still inside the
+	 * kernel. If this is successful, the return path will see it
+	 * when it rechecks the overage and simply bail out.
+	 */
 	if (current->memcg_nr_pages_over_high > MEMCG_CHARGE_BATCH &&
 	    !(current->flags & PF_MEMALLOC) &&
-	    gfpflags_allow_blocking(gfp_mask)) {
+	    gfpflags_allow_blocking(gfp_mask))
 		mem_cgroup_handle_over_high(gfp_mask);
-	}
 	return 0;
 }
 
@@ -5456,10 +5482,11 @@ static void mem_cgroup_free(struct mem_cgroup *memcg)
 	__mem_cgroup_free(memcg);
 }
 
-static struct mem_cgroup *mem_cgroup_alloc(void)
+static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent)
 {
+	struct memcg_vmstats_percpu *statc, *pstatc;
 	struct mem_cgroup *memcg;
-	int node;
+	int node, cpu;
 	int __maybe_unused i;
 	long error = -ENOMEM;
 
@@ -5483,6 +5510,14 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	if (!memcg->vmstats_percpu)
 		goto fail;
 
+	for_each_possible_cpu(cpu) {
+		if (parent)
+			pstatc = per_cpu_ptr(parent->vmstats_percpu, cpu);
+		statc = per_cpu_ptr(memcg->vmstats_percpu, cpu);
+		statc->parent = parent ? pstatc : NULL;
+		statc->vmstats = memcg->vmstats;
+	}
+
 	for_each_node(node)
 		if (alloc_mem_cgroup_per_node_info(memcg, node))
 			goto fail;
@@ -5528,7 +5563,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	struct mem_cgroup *memcg, *old_memcg;
 
 	old_memcg = set_active_memcg(parent);
-	memcg = mem_cgroup_alloc();
+	memcg = mem_cgroup_alloc(parent);
 	set_active_memcg(old_memcg);
 	if (IS_ERR(memcg))
 		return ERR_CAST(memcg);
@@ -7936,9 +7971,13 @@ bool mem_cgroup_swap_full(struct folio *folio)
 
 static int __init setup_swap_account(char *s)
 {
-	pr_warn_once("The swapaccount= commandline option is deprecated. "
-		     "Please report your usecase to linux-mm@kvack.org if you "
-		     "depend on this functionality.\n");
+	bool res;
+
+	if (!kstrtobool(s, &res) && !res)
+		pr_warn_once("The swapaccount=0 commandline option is deprecated "
+			     "in favor of configuring swap control via cgroupfs. "
+			     "Please report your usecase to linux-mm@kvack.org if you "
+			     "depend on this functionality.\n");
 	return 1;
 }
 __setup("swapaccount=", setup_swap_account);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 4f9b61f4a668..9349948f1abf 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -982,7 +982,7 @@ static bool has_extra_refcount(struct page_state *ps, struct page *p,
 	int count = page_count(p) - 1;
 
 	if (extra_pins)
-		count -= 1;
+		count -= folio_nr_pages(page_folio(p));
 
 	if (count > 0) {
 		pr_err("%#lx: %s still referenced by %d users\n",
@@ -1377,6 +1377,9 @@ void ClearPageHWPoisonTakenOff(struct page *page)
  */
 static inline bool HWPoisonHandlable(struct page *page, unsigned long flags)
 {
+	if (PageSlab(page))
+		return false;
+
 	/* Soft offline could migrate non-LRU movable pages */
 	if ((flags & MF_SOFT_OFFLINE) && __PageMovable(page))
 		return true;
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 8d5291add2bc..5462d9e3c84c 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -109,7 +109,7 @@ static struct demotion_nodes *node_demotion __read_mostly;
 static BLOCKING_NOTIFIER_HEAD(mt_adistance_algorithms);
 
 static bool default_dram_perf_error;
-static struct node_hmem_attrs default_dram_perf;
+static struct access_coordinate default_dram_perf;
 static int default_dram_perf_ref_nid = NUMA_NO_NODE;
 static const char *default_dram_perf_ref_source;
 
@@ -601,15 +601,15 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype)
 }
 EXPORT_SYMBOL_GPL(clear_node_memory_type);
 
-static void dump_hmem_attrs(struct node_hmem_attrs *attrs, const char *prefix)
+static void dump_hmem_attrs(struct access_coordinate *coord, const char *prefix)
 {
 	pr_info(
 "%sread_latency: %u, write_latency: %u, read_bandwidth: %u, write_bandwidth: %u\n",
-		prefix, attrs->read_latency, attrs->write_latency,
-		attrs->read_bandwidth, attrs->write_bandwidth);
+		prefix, coord->read_latency, coord->write_latency,
+		coord->read_bandwidth, coord->write_bandwidth);
 }
 
-int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf,
+int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
 			     const char *source)
 {
 	int rc = 0;
@@ -666,7 +666,7 @@ out:
 	return rc;
 }
 
-int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist)
+int mt_perf_to_adistance(struct access_coordinate *perf, int *adist)
 {
 	if (default_dram_perf_error)
 		return -EIO;
diff --git a/mm/memory.c b/mm/memory.c
index 7e1f4849463a..0bfc8b007c01 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1464,7 +1464,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 			delay_rmap = 0;
 			if (!folio_test_anon(folio)) {
 				if (pte_dirty(ptent)) {
-					folio_set_dirty(folio);
+					folio_mark_dirty(folio);
 					if (tlb_delay_rmap(tlb)) {
 						delay_rmap = 1;
 						force_flush = 1;
@@ -3799,6 +3799,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	struct page *page;
 	struct swap_info_struct *si = NULL;
 	rmap_t rmap_flags = RMAP_NONE;
+	bool need_clear_cache = false;
 	bool exclusive = false;
 	swp_entry_t entry;
 	pte_t pte;
@@ -3867,6 +3868,20 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	if (!folio) {
 		if (data_race(si->flags & SWP_SYNCHRONOUS_IO) &&
 		    __swap_count(entry) == 1) {
+			/*
+			 * Prevent parallel swapin from proceeding with
+			 * the cache flag. Otherwise, another thread may
+			 * finish swapin first, free the entry, and swapout
+			 * reusing the same entry. It's undetectable as
+			 * pte_same() returns true due to entry reuse.
+			 */
+			if (swapcache_prepare(entry)) {
+				/* Relax a bit to prevent rapid repeated page faults */
+				schedule_timeout_uninterruptible(1);
+				goto out;
+			}
+			need_clear_cache = true;
+
 			/* skip swapcache */
 			folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0,
 						vma, vmf->address, false);
@@ -4117,6 +4132,9 @@ unlock:
 	if (vmf->pte)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 out:
+	/* Clear the swap cache pin for direct swapin after PTL unlock */
+	if (need_clear_cache)
+		swapcache_clear(si, entry);
 	if (si)
 		put_swap_device(si);
 	return ret;
@@ -4131,6 +4149,8 @@ out_release:
 		folio_unlock(swapcache);
 		folio_put(swapcache);
 	}
+	if (need_clear_cache)
+		swapcache_clear(si, entry);
 	if (si)
 		put_swap_device(si);
 	return ret;
@@ -5478,7 +5498,7 @@ static inline bool get_mmap_lock_carefully(struct mm_struct *mm, struct pt_regs
 		return true;
 
 	if (regs && !user_mode(regs)) {
-		unsigned long ip = instruction_pointer(regs);
+		unsigned long ip = exception_ip(regs);
 		if (!search_exception_tables(ip))
 			return false;
 	}
@@ -5503,7 +5523,7 @@ static inline bool upgrade_mmap_lock_carefully(struct mm_struct *mm, struct pt_r
 {
 	mmap_read_unlock(mm);
 	if (regs && !user_mode(regs)) {
-		unsigned long ip = instruction_pointer(regs);
+		unsigned long ip = exception_ip(regs);
 		if (!search_exception_tables(ip))
 			return false;
 	}
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b3c0ff52bb72..21890994c1d3 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -101,9 +101,11 @@ static int set_memmap_mode(const char *val, const struct kernel_param *kp)
 
 static int get_memmap_mode(char *buffer, const struct kernel_param *kp)
 {
-	if (*((int *)kp->arg) == MEMMAP_ON_MEMORY_FORCE)
-		return sprintf(buffer,  "force\n");
-	return param_get_bool(buffer, kp);
+	int mode = *((int *)kp->arg);
+
+	if (mode == MEMMAP_ON_MEMORY_FORCE)
+		return sprintf(buffer, "force\n");
+	return sprintf(buffer, "%c\n", mode ? 'Y' : 'N');
 }
 
 static const struct kernel_param_ops memmap_mode_ops = {
diff --git a/mm/migrate.c b/mm/migrate.c
index bde8273cf15b..c27b1f8097d4 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -962,6 +962,8 @@ static int move_to_new_folio(struct folio *dst, struct folio *src,
 
 		if (!mapping)
 			rc = migrate_folio(mapping, dst, src, mode);
+		else if (mapping_unmovable(mapping))
+			rc = -EOPNOTSUPP;
 		else if (mapping->a_ops->migrate_folio)
 			/*
 			 * Most folios have a mapping and most filesystems
@@ -2517,6 +2519,14 @@ static int numamigrate_isolate_folio(pg_data_t *pgdat, struct folio *folio)
 			if (managed_zone(pgdat->node_zones + z))
 				break;
 		}
+
+		/*
+		 * If there are no managed zones, it should not proceed
+		 * further.
+		 */
+		if (z < 0)
+			return 0;
+
 		wakeup_kswapd(pgdat->node_zones + z, 0,
 			      folio_order(folio), ZONE_MOVABLE);
 		return 0;
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 89dc29f1e6c6..2c19f5515e36 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -26,6 +26,7 @@
 #include <linux/pgtable.h>
 #include <linux/swap.h>
 #include <linux/cma.h>
+#include <linux/crash_dump.h>
 #include "internal.h"
 #include "slab.h"
 #include "shuffle.h"
@@ -381,6 +382,11 @@ static void __init find_zone_movable_pfns_for_nodes(void)
 			goto out;
 		}
 
+		if (is_kdump_kernel()) {
+			pr_warn("The system is under kdump, ignore kernelcore=mirror.\n");
+			goto out;
+		}
+
 		for_each_mem_region(r) {
 			if (memblock_is_mirror(r))
 				continue;
diff --git a/mm/mmap.c b/mm/mmap.c
index b78e83d351d2..3281287771c9 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -954,13 +954,21 @@ static struct vm_area_struct
 	} else if (merge_prev) {			/* case 2 */
 		if (curr) {
 			vma_start_write(curr);
-			err = dup_anon_vma(prev, curr, &anon_dup);
 			if (end == curr->vm_end) {	/* case 7 */
+				/*
+				 * can_vma_merge_after() assumed we would not be
+				 * removing prev vma, so it skipped the check
+				 * for vm_ops->close, but we are removing curr
+				 */
+				if (curr->vm_ops && curr->vm_ops->close)
+					err = -EINVAL;
 				remove = curr;
 			} else {			/* case 5 */
 				adjust = curr;
 				adj_start = (end - curr->vm_start);
 			}
+			if (!err)
+				err = dup_anon_vma(prev, curr, &anon_dup);
 		}
 	} else { /* merge_next */
 		vma_start_write(next);
@@ -1825,15 +1833,17 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 		/*
 		 * mmap_region() will call shmem_zero_setup() to create a file,
 		 * so use shmem's get_unmapped_area in case it can be huge.
-		 * do_mmap() will clear pgoff, so match alignment.
 		 */
-		pgoff = 0;
 		get_area = shmem_get_unmapped_area;
 	} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
 		/* Ensures that larger anonymous mappings are THP aligned. */
 		get_area = thp_get_unmapped_area;
 	}
 
+	/* Always treat pgoff as zero for anonymous memory. */
+	if (!file)
+		pgoff = 0;
+
 	addr = get_area(file, addr, len, pgoff, flags);
 	if (IS_ERR_VALUE(addr))
 		return addr;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index cd4e4ae77c40..3f255534986a 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1638,7 +1638,7 @@ static inline void wb_dirty_limits(struct dirty_throttle_control *dtc)
 	 */
 	dtc->wb_thresh = __wb_calc_thresh(dtc);
 	dtc->wb_bg_thresh = dtc->thresh ?
-		div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0;
+		div64_u64(dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0;
 
 	/*
 	 * In order to avoid the stacked BDI deadlock we need
@@ -1921,7 +1921,7 @@ pause:
 			break;
 		}
 		__set_current_state(TASK_KILLABLE);
-		wb->dirty_sleep = now;
+		bdi->last_bdp_sleep = jiffies;
 		io_schedule_timeout(pause);
 
 		current->dirty_paused_when = now + pause;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 150d4f23b010..a663202045dc 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4041,6 +4041,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 						struct alloc_context *ac)
 {
 	bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM;
+	bool can_compact = gfp_compaction_allowed(gfp_mask);
 	const bool costly_order = order > PAGE_ALLOC_COSTLY_ORDER;
 	struct page *page = NULL;
 	unsigned int alloc_flags;
@@ -4111,7 +4112,7 @@ restart:
 	 * Don't try this for allocations that are allowed to ignore
 	 * watermarks, as the ALLOC_NO_WATERMARKS attempt didn't yet happen.
 	 */
-	if (can_direct_reclaim &&
+	if (can_direct_reclaim && can_compact &&
 			(costly_order ||
 			   (order > 0 && ac->migratetype != MIGRATE_MOVABLE))
 			&& !gfp_pfmemalloc_allowed(gfp_mask)) {
@@ -4209,9 +4210,10 @@ retry:
 
 	/*
 	 * Do not retry costly high order allocations unless they are
-	 * __GFP_RETRY_MAYFAIL
+	 * __GFP_RETRY_MAYFAIL and we can compact
 	 */
-	if (costly_order && !(gfp_mask & __GFP_RETRY_MAYFAIL))
+	if (costly_order && (!can_compact ||
+			     !(gfp_mask & __GFP_RETRY_MAYFAIL)))
 		goto nopage;
 
 	if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags,
@@ -4224,7 +4226,7 @@ retry:
 	 * implementation of the compaction depends on the sufficient amount
 	 * of free memory (see __compaction_suitable)
 	 */
-	if (did_some_progress > 0 &&
+	if (did_some_progress > 0 && can_compact &&
 			should_compact_retry(ac, order, alloc_flags,
 				compact_result, &compact_priority,
 				&compaction_retries))
diff --git a/mm/percpu.c b/mm/percpu.c
index 7b97d31df767..4e11fc1e6def 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -3333,13 +3333,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t
 		if (rc < 0)
 			panic("failed to map percpu area, err=%d\n", rc);
 
-		/*
-		 * FIXME: Archs with virtual cache should flush local
-		 * cache for the linear mapping here - something
-		 * equivalent to flush_cache_vmap() on the local cpu.
-		 * flush_cache_vmap() can't be used as most supporting
-		 * data structures are not set up yet.
-		 */
+		flush_cache_vmap_early(unit_addr, unit_addr + ai->unit_size);
 
 		/* copy static data */
 		memcpy((void *)unit_addr, __per_cpu_load, ai->static_size);
diff --git a/mm/readahead.c b/mm/readahead.c
index 23620c57c122..2648ec4f0494 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -469,7 +469,7 @@ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index,
 
 	if (!folio)
 		return -ENOMEM;
-	mark = round_up(mark, 1UL << order);
+	mark = round_down(mark, 1UL << order);
 	if (index == mark)
 		folio_set_readahead(folio);
 	err = filemap_add_folio(ractl->mapping, folio, index, gfp);
@@ -575,7 +575,7 @@ static void ondemand_readahead(struct readahead_control *ractl,
 	 * It's the expected callback index, assume sequential access.
 	 * Ramp up sizes, and push forward the readahead window.
 	 */
-	expected = round_up(ra->start + ra->size - ra->async_size,
+	expected = round_down(ra->start + ra->size - ra->async_size,
 			1UL << order);
 	if (index == expected || index == (ra->start + ra->size)) {
 		ra->start += ra->size;
diff --git a/mm/shmem.c b/mm/shmem.c
index d7c84ff62186..29d5a024df48 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3374,7 +3374,7 @@ static int shmem_unlink(struct inode *dir, struct dentry *dentry)
 
 static int shmem_rmdir(struct inode *dir, struct dentry *dentry)
 {
-	if (!simple_empty(dentry))
+	if (!simple_offset_empty(dentry))
 		return -ENOTEMPTY;
 
 	drop_nlink(d_inode(dentry));
@@ -3431,7 +3431,7 @@ static int shmem_rename2(struct mnt_idmap *idmap,
 		return simple_offset_rename_exchange(old_dir, old_dentry,
 						     new_dir, new_dentry);
 
-	if (!simple_empty(new_dentry))
+	if (!simple_offset_empty(new_dentry))
 		return -ENOTEMPTY;
 
 	if (flags & RENAME_WHITEOUT) {
@@ -4355,7 +4355,9 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
 #ifdef CONFIG_TMPFS_POSIX_ACL
 	sb->s_flags |= SB_POSIXACL;
 #endif
-	uuid_gen(&sb->s_uuid);
+	uuid_t uuid;
+	uuid_gen(&uuid);
+	super_set_uuid(sb, uuid.b, sizeof(uuid));
 
 #ifdef CONFIG_TMPFS_QUOTA
 	if (ctx->seen & SHMEM_SEEN_QUOTA) {
diff --git a/mm/swap.h b/mm/swap.h
index 758c46ca671e..fc2f6ade7f80 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -41,6 +41,7 @@ void __delete_from_swap_cache(struct folio *folio,
 void delete_from_swap_cache(struct folio *folio);
 void clear_shadow_from_swap_cache(int type, unsigned long begin,
 				  unsigned long end);
+void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry);
 struct folio *swap_cache_get_folio(swp_entry_t entry,
 		struct vm_area_struct *vma, unsigned long addr);
 struct folio *filemap_get_incore_folio(struct address_space *mapping,
@@ -97,6 +98,10 @@ static inline int swap_writepage(struct page *p, struct writeback_control *wbc)
 	return 0;
 }
 
+static inline void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry)
+{
+}
+
 static inline struct folio *swap_cache_get_folio(swp_entry_t entry,
 		struct vm_area_struct *vma, unsigned long addr)
 {
diff --git a/mm/swap_state.c b/mm/swap_state.c
index e671266ad772..7255c01a1e4e 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -680,9 +680,10 @@ skip:
 	/* The page was likely read above, so no need for plugging here */
 	folio = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
 					&page_allocated, false);
-	if (unlikely(page_allocated))
+	if (unlikely(page_allocated)) {
+		zswap_folio_swapin(folio);
 		swap_read_folio(folio, false, NULL);
-	zswap_folio_swapin(folio);
+	}
 	return folio;
 }
 
@@ -855,9 +856,10 @@ skip:
 	/* The folio was likely read above, so no need for plugging here */
 	folio = __read_swap_cache_async(targ_entry, gfp_mask, mpol, targ_ilx,
 					&page_allocated, false);
-	if (unlikely(page_allocated))
+	if (unlikely(page_allocated)) {
+		zswap_folio_swapin(folio);
 		swap_read_folio(folio, false, NULL);
-	zswap_folio_swapin(folio);
+	}
 	return folio;
 }
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 556ff7347d5f..573843d9cc91 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2532,10 +2532,10 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	exit_swap_address_space(p->type);
 
 	inode = mapping->host;
-	if (p->bdev_handle) {
+	if (p->bdev_file) {
 		set_blocksize(p->bdev, old_block_size);
-		bdev_release(p->bdev_handle);
-		p->bdev_handle = NULL;
+		fput(p->bdev_file);
+		p->bdev_file = NULL;
 	}
 
 	inode_lock(inode);
@@ -2765,14 +2765,14 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode)
 	int error;
 
 	if (S_ISBLK(inode->i_mode)) {
-		p->bdev_handle = bdev_open_by_dev(inode->i_rdev,
+		p->bdev_file = bdev_file_open_by_dev(inode->i_rdev,
 				BLK_OPEN_READ | BLK_OPEN_WRITE, p, NULL);
-		if (IS_ERR(p->bdev_handle)) {
-			error = PTR_ERR(p->bdev_handle);
-			p->bdev_handle = NULL;
+		if (IS_ERR(p->bdev_file)) {
+			error = PTR_ERR(p->bdev_file);
+			p->bdev_file = NULL;
 			return error;
 		}
-		p->bdev = p->bdev_handle->bdev;
+		p->bdev = file_bdev(p->bdev_file);
 		p->old_block_size = block_size(p->bdev);
 		error = set_blocksize(p->bdev, PAGE_SIZE);
 		if (error < 0)
@@ -3208,10 +3208,10 @@ bad_swap:
 	p->percpu_cluster = NULL;
 	free_percpu(p->cluster_next_cpu);
 	p->cluster_next_cpu = NULL;
-	if (p->bdev_handle) {
+	if (p->bdev_file) {
 		set_blocksize(p->bdev, p->old_block_size);
-		bdev_release(p->bdev_handle);
-		p->bdev_handle = NULL;
+		fput(p->bdev_file);
+		p->bdev_file = NULL;
 	}
 	inode = NULL;
 	destroy_swap_extents(p);
@@ -3365,6 +3365,19 @@ int swapcache_prepare(swp_entry_t entry)
 	return __swap_duplicate(entry, SWAP_HAS_CACHE);
 }
 
+void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry)
+{
+	struct swap_cluster_info *ci;
+	unsigned long offset = swp_offset(entry);
+	unsigned char usage;
+
+	ci = lock_cluster_or_swap_info(si, offset);
+	usage = __swap_entry_free_locked(si, offset, SWAP_HAS_CACHE);
+	unlock_cluster_or_swap_info(si, ci);
+	if (!usage)
+		free_swap_slot(entry);
+}
+
 struct swap_info_struct *swp_swap_info(swp_entry_t entry)
 {
 	return swap_type_to_swap_info(swp_type(entry));
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 216ab4c8621f..313f1c42768a 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -357,6 +357,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
 					      unsigned long dst_start,
 					      unsigned long src_start,
 					      unsigned long len,
+					      atomic_t *mmap_changing,
 					      uffd_flags_t flags)
 {
 	struct mm_struct *dst_mm = dst_vma->vm_mm;
@@ -472,6 +473,15 @@ retry:
 				goto out;
 			}
 			mmap_read_lock(dst_mm);
+			/*
+			 * If memory mappings are changing because of non-cooperative
+			 * operation (e.g. mremap) running in parallel, bail out and
+			 * request the user to retry later
+			 */
+			if (mmap_changing && atomic_read(mmap_changing)) {
+				err = -EAGAIN;
+				break;
+			}
 
 			dst_vma = NULL;
 			goto retry;
@@ -506,6 +516,7 @@ extern ssize_t mfill_atomic_hugetlb(struct vm_area_struct *dst_vma,
 				    unsigned long dst_start,
 				    unsigned long src_start,
 				    unsigned long len,
+				    atomic_t *mmap_changing,
 				    uffd_flags_t flags);
 #endif /* CONFIG_HUGETLB_PAGE */
 
@@ -622,8 +633,8 @@ retry:
 	 * If this is a HUGETLB vma, pass off to appropriate routine
 	 */
 	if (is_vm_hugetlb_page(dst_vma))
-		return  mfill_atomic_hugetlb(dst_vma, dst_start,
-					     src_start, len, flags);
+		return  mfill_atomic_hugetlb(dst_vma, dst_start, src_start,
+					     len, mmap_changing, flags);
 
 	if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma))
 		goto out_unlock;
@@ -891,8 +902,8 @@ static int move_present_pte(struct mm_struct *mm,
 
 	double_pt_lock(dst_ptl, src_ptl);
 
-	if (!pte_same(*src_pte, orig_src_pte) ||
-	    !pte_same(*dst_pte, orig_dst_pte)) {
+	if (!pte_same(ptep_get(src_pte), orig_src_pte) ||
+	    !pte_same(ptep_get(dst_pte), orig_dst_pte)) {
 		err = -EAGAIN;
 		goto out;
 	}
@@ -903,9 +914,6 @@ static int move_present_pte(struct mm_struct *mm,
 		goto out;
 	}
 
-	folio_move_anon_rmap(src_folio, dst_vma);
-	WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr));
-
 	orig_src_pte = ptep_clear_flush(src_vma, src_addr, src_pte);
 	/* Folio got pinned from under us. Put it back and fail the move. */
 	if (folio_maybe_dma_pinned(src_folio)) {
@@ -914,6 +922,9 @@ static int move_present_pte(struct mm_struct *mm,
 		goto out;
 	}
 
+	folio_move_anon_rmap(src_folio, dst_vma);
+	WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr));
+
 	orig_dst_pte = mk_pte(&src_folio->page, dst_vma->vm_page_prot);
 	/* Follow mremap() behavior and treat the entry dirty after the move */
 	orig_dst_pte = pte_mkwrite(pte_mkdirty(orig_dst_pte), dst_vma);
@@ -935,8 +946,8 @@ static int move_swap_pte(struct mm_struct *mm,
 
 	double_pt_lock(dst_ptl, src_ptl);
 
-	if (!pte_same(*src_pte, orig_src_pte) ||
-	    !pte_same(*dst_pte, orig_dst_pte)) {
+	if (!pte_same(ptep_get(src_pte), orig_src_pte) ||
+	    !pte_same(ptep_get(dst_pte), orig_dst_pte)) {
 		double_pt_unlock(dst_ptl, src_ptl);
 		return -EAGAIN;
 	}
@@ -1005,7 +1016,7 @@ retry:
 	}
 
 	spin_lock(dst_ptl);
-	orig_dst_pte = *dst_pte;
+	orig_dst_pte = ptep_get(dst_pte);
 	spin_unlock(dst_ptl);
 	if (!pte_none(orig_dst_pte)) {
 		err = -EEXIST;
@@ -1013,7 +1024,7 @@ retry:
 	}
 
 	spin_lock(src_ptl);
-	orig_src_pte = *src_pte;
+	orig_src_pte = ptep_get(src_pte);
 	spin_unlock(src_ptl);
 	if (pte_none(orig_src_pte)) {
 		if (!(mode & UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES))
@@ -1043,7 +1054,7 @@ retry:
 			 * page isn't freed under us
 			 */
 			spin_lock(src_ptl);
-			if (!pte_same(orig_src_pte, *src_pte)) {
+			if (!pte_same(orig_src_pte, ptep_get(src_pte))) {
 				spin_unlock(src_ptl);
 				err = -EAGAIN;
 				goto out;
@@ -1393,6 +1404,12 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
 				err = -ENOENT;
 				break;
 			}
+			/* Avoid moving zeropages for now */
+			if (is_huge_zero_pmd(*src_pmd)) {
+				spin_unlock(ptl);
+				err = -EBUSY;
+				break;
+			}
 
 			/* Check if we can move the pmd without splitting it. */
 			if (move_splits_huge_pmd(dst_addr, src_addr, src_start + len) ||
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 4f9c854ce6cc..4255619a1a31 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -5753,7 +5753,7 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 /* Use reclaim/compaction for costly allocs or under memory pressure */
 static bool in_reclaim_compaction(struct scan_control *sc)
 {
-	if (IS_ENABLED(CONFIG_COMPACTION) && sc->order &&
+	if (gfp_compaction_allowed(sc->gfp_mask) && sc->order &&
 			(sc->order > PAGE_ALLOC_COSTLY_ORDER ||
 			 sc->priority < DEF_PRIORITY - 2))
 		return true;
@@ -5998,6 +5998,9 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
 {
 	unsigned long watermark;
 
+	if (!gfp_compaction_allowed(sc->gfp_mask))
+		return false;
+
 	/* Allocation can already succeed, nothing to do */
 	if (zone_watermark_ok(zone, sc->order, min_wmark_pages(zone),
 			      sc->reclaim_idx, 0))
diff --git a/mm/zswap.c b/mm/zswap.c
index ca25b676048e..db4625af65fb 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -377,10 +377,9 @@ void zswap_folio_swapin(struct folio *folio)
 {
 	struct lruvec *lruvec;
 
-	if (folio) {
-		lruvec = folio_lruvec(folio);
-		atomic_long_inc(&lruvec->zswap_lruvec_state.nr_zswap_protected);
-	}
+	VM_WARN_ON_ONCE(!folio_test_locked(folio));
+	lruvec = folio_lruvec(folio);
+	atomic_long_inc(&lruvec->zswap_lruvec_state.nr_zswap_protected);
 }
 
 /*********************************
@@ -536,10 +535,6 @@ static struct zpool *zswap_find_zpool(struct zswap_entry *entry)
  */
 static void zswap_free_entry(struct zswap_entry *entry)
 {
-	if (entry->objcg) {
-		obj_cgroup_uncharge_zswap(entry->objcg, entry->length);
-		obj_cgroup_put(entry->objcg);
-	}
 	if (!entry->length)
 		atomic_dec(&zswap_same_filled_pages);
 	else {
@@ -548,6 +543,10 @@ static void zswap_free_entry(struct zswap_entry *entry)
 		atomic_dec(&entry->pool->nr_stored);
 		zswap_pool_put(entry->pool);
 	}
+	if (entry->objcg) {
+		obj_cgroup_uncharge_zswap(entry->objcg, entry->length);
+		obj_cgroup_put(entry->objcg);
+	}
 	zswap_entry_cache_free(entry);
 	atomic_dec(&zswap_stored_pages);
 	zswap_update_total_size();
@@ -895,10 +894,8 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o
 		 * into the warmer region. We should terminate shrinking (if we're in the dynamic
 		 * shrinker context).
 		 */
-		if (writeback_result == -EEXIST && encountered_page_in_swapcache) {
-			ret = LRU_SKIP;
+		if (writeback_result == -EEXIST && encountered_page_in_swapcache)
 			*encountered_page_in_swapcache = true;
-		}
 
 		goto put_unlock;
 	}
@@ -1442,6 +1439,8 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 	if (zswap_rb_search(&tree->rbroot, swp_offset(entry->swpentry)) != entry) {
 		spin_unlock(&tree->lock);
 		delete_from_swap_cache(folio);
+		folio_unlock(folio);
+		folio_put(folio);
 		return -ENOMEM;
 	}
 	spin_unlock(&tree->lock);
@@ -1519,7 +1518,7 @@ bool zswap_store(struct folio *folio)
 	if (folio_test_large(folio))
 		return false;
 
-	if (!zswap_enabled || !tree)
+	if (!tree)
 		return false;
 
 	/*
@@ -1534,6 +1533,10 @@ bool zswap_store(struct folio *folio)
 		zswap_invalidate_entry(tree, dupentry);
 	}
 	spin_unlock(&tree->lock);
+
+	if (!zswap_enabled)
+		return false;
+
 	objcg = get_obj_cgroup_from_folio(folio);
 	if (objcg && !obj_cgroup_may_zswap(objcg)) {
 		memcg = get_mem_cgroup_from_objcg(objcg);
diff --git a/net/6lowpan/core.c b/net/6lowpan/core.c
index 7b3341cef926..850d4a185f55 100644
--- a/net/6lowpan/core.c
+++ b/net/6lowpan/core.c
@@ -179,4 +179,5 @@ static void __exit lowpan_module_exit(void)
 module_init(lowpan_module_init);
 module_exit(lowpan_module_exit);
 
+MODULE_DESCRIPTION("IPv6 over Low-Power Wireless Personal Area Network core module");
 MODULE_LICENSE("GPL");
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index 214532173536..a3b68243fd4b 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -118,12 +118,16 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	}
 	if (data[IFLA_VLAN_INGRESS_QOS]) {
 		nla_for_each_nested(attr, data[IFLA_VLAN_INGRESS_QOS], rem) {
+			if (nla_type(attr) != IFLA_VLAN_QOS_MAPPING)
+				continue;
 			m = nla_data(attr);
 			vlan_dev_set_ingress_priority(dev, m->to, m->from);
 		}
 	}
 	if (data[IFLA_VLAN_EGRESS_QOS]) {
 		nla_for_each_nested(attr, data[IFLA_VLAN_EGRESS_QOS], rem) {
+			if (nla_type(attr) != IFLA_VLAN_QOS_MAPPING)
+				continue;
 			m = nla_data(attr);
 			err = vlan_dev_set_egress_priority(dev, m->from, m->to);
 			if (err)
diff --git a/net/atm/mpc.c b/net/atm/mpc.c
index 033871e718a3..324e3ab96bb3 100644
--- a/net/atm/mpc.c
+++ b/net/atm/mpc.c
@@ -1532,4 +1532,5 @@ static void __exit atm_mpoa_cleanup(void)
 module_init(atm_mpoa_init);
 module_exit(atm_mpoa_cleanup);
 
+MODULE_DESCRIPTION("Multi-Protocol Over ATM (MPOA) driver");
 MODULE_LICENSE("GPL");
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index d982daea8329..14088c4ff2f6 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -2175,6 +2175,7 @@ void batadv_mcast_free(struct batadv_priv *bat_priv)
 	cancel_delayed_work_sync(&bat_priv->mcast.work);
 
 	batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_MCAST, 2);
+	batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_MCAST_TRACKER, 1);
 	batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_MCAST, 2);
 
 	/* safely calling outside of worker, as worker was canceled above */
@@ -2198,6 +2199,8 @@ void batadv_mcast_purge_orig(struct batadv_orig_node *orig)
 				      BATADV_MCAST_WANT_NO_RTR4);
 	batadv_mcast_want_rtr6_update(bat_priv, orig,
 				      BATADV_MCAST_WANT_NO_RTR6);
+	batadv_mcast_have_mc_ptype_update(bat_priv, orig,
+					  BATADV_MCAST_HAVE_MC_PTYPE_CAPA);
 
 	spin_unlock_bh(&orig->mcast_handler_lock);
 }
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 65601aa52e0d..2821a42cefdc 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1049,6 +1049,7 @@ static void hci_error_reset(struct work_struct *work)
 {
 	struct hci_dev *hdev = container_of(work, struct hci_dev, error_reset);
 
+	hci_dev_hold(hdev);
 	BT_DBG("%s", hdev->name);
 
 	if (hdev->hw_error)
@@ -1056,10 +1057,10 @@ static void hci_error_reset(struct work_struct *work)
 	else
 		bt_dev_err(hdev, "hardware error 0x%2.2x", hdev->hw_error_code);
 
-	if (hci_dev_do_close(hdev))
-		return;
+	if (!hci_dev_do_close(hdev))
+		hci_dev_do_open(hdev);
 
-	hci_dev_do_open(hdev);
+	hci_dev_put(hdev);
 }
 
 void hci_uuids_clear(struct hci_dev *hdev)
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index ef8c3bed7361..2a5f5a7d2412 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -5329,9 +5329,12 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, void *data,
 	hci_dev_lock(hdev);
 
 	conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr);
-	if (!conn || !hci_conn_ssp_enabled(conn))
+	if (!conn || !hci_dev_test_flag(hdev, HCI_SSP_ENABLED))
 		goto unlock;
 
+	/* Assume remote supports SSP since it has triggered this event */
+	set_bit(HCI_CONN_SSP_ENABLED, &conn->flags);
+
 	hci_conn_hold(conn);
 
 	if (!hci_dev_test_flag(hdev, HCI_MGMT))
@@ -6794,6 +6797,10 @@ static void hci_le_remote_conn_param_req_evt(struct hci_dev *hdev, void *data,
 		return send_conn_param_neg_reply(hdev, handle,
 						 HCI_ERROR_UNKNOWN_CONN_ID);
 
+	if (max > hcon->le_conn_max_interval)
+		return send_conn_param_neg_reply(hdev, handle,
+						 HCI_ERROR_INVALID_LL_PARAMS);
+
 	if (hci_check_conn_params(min, max, latency, timeout))
 		return send_conn_param_neg_reply(hdev, handle,
 						 HCI_ERROR_INVALID_LL_PARAMS);
@@ -7420,10 +7427,10 @@ static void hci_store_wake_reason(struct hci_dev *hdev, u8 event,
 	 * keep track of the bdaddr of the connection event that woke us up.
 	 */
 	if (event == HCI_EV_CONN_REQUEST) {
-		bacpy(&hdev->wake_addr, &conn_complete->bdaddr);
+		bacpy(&hdev->wake_addr, &conn_request->bdaddr);
 		hdev->wake_addr_type = BDADDR_BREDR;
 	} else if (event == HCI_EV_CONN_COMPLETE) {
-		bacpy(&hdev->wake_addr, &conn_request->bdaddr);
+		bacpy(&hdev->wake_addr, &conn_complete->bdaddr);
 		hdev->wake_addr_type = BDADDR_BREDR;
 	} else if (event == HCI_EV_LE_META) {
 		struct hci_ev_le_meta *le_ev = (void *)skb->data;
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index a6fc8a2a5c67..5716345a26df 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -2206,8 +2206,11 @@ static int hci_le_add_accept_list_sync(struct hci_dev *hdev,
 
 	/* During suspend, only wakeable devices can be in acceptlist */
 	if (hdev->suspended &&
-	    !(params->flags & HCI_CONN_FLAG_REMOTE_WAKEUP))
+	    !(params->flags & HCI_CONN_FLAG_REMOTE_WAKEUP)) {
+		hci_le_del_accept_list_sync(hdev, &params->addr,
+					    params->addr_type);
 		return 0;
+	}
 
 	/* Select filter policy to accept all advertising */
 	if (*num_entries >= hdev->le_accept_list_size)
@@ -5559,7 +5562,7 @@ static int hci_inquiry_sync(struct hci_dev *hdev, u8 length)
 
 	bt_dev_dbg(hdev, "");
 
-	if (hci_dev_test_flag(hdev, HCI_INQUIRY))
+	if (test_bit(HCI_INQUIRY, &hdev->flags))
 		return 0;
 
 	hci_dev_lock(hdev);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 60298975d5c4..656f49b299d2 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -5613,7 +5613,13 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn,
 
 	memset(&rsp, 0, sizeof(rsp));
 
-	err = hci_check_conn_params(min, max, latency, to_multiplier);
+	if (max > hcon->le_conn_max_interval) {
+		BT_DBG("requested connection interval exceeds current bounds.");
+		err = -EINVAL;
+	} else {
+		err = hci_check_conn_params(min, max, latency, to_multiplier);
+	}
+
 	if (err)
 		rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_REJECTED);
 	else
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index bb72ff6eb22f..ee3b4aad8bd8 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1045,6 +1045,8 @@ static void rpa_expired(struct work_struct *work)
 	hci_cmd_sync_queue(hdev, rpa_expired_sync, NULL, NULL);
 }
 
+static int set_discoverable_sync(struct hci_dev *hdev, void *data);
+
 static void discov_off(struct work_struct *work)
 {
 	struct hci_dev *hdev = container_of(work, struct hci_dev,
@@ -1063,7 +1065,7 @@ static void discov_off(struct work_struct *work)
 	hci_dev_clear_flag(hdev, HCI_DISCOVERABLE);
 	hdev->discov_timeout = 0;
 
-	hci_update_discoverable(hdev);
+	hci_cmd_sync_queue(hdev, set_discoverable_sync, NULL, NULL);
 
 	mgmt_new_settings(hdev);
 
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index 053ef8f25fae..1d34d8497033 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -1941,7 +1941,7 @@ static struct rfcomm_session *rfcomm_process_rx(struct rfcomm_session *s)
 	/* Get data directly from socket receive queue without copying it. */
 	while ((skb = skb_dequeue(&sk->sk_receive_queue))) {
 		skb_orphan(skb);
-		if (!skb_linearize(skb)) {
+		if (!skb_linearize(skb) && sk->sk_state != BT_CLOSED) {
 			s = rfcomm_recv_frame(s, skb);
 			if (!s)
 				break;
diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c
index 94ec913dfb76..69c75c041fe1 100644
--- a/net/bluetooth/rfcomm/tty.c
+++ b/net/bluetooth/rfcomm/tty.c
@@ -1041,7 +1041,7 @@ static void rfcomm_tty_flush_buffer(struct tty_struct *tty)
 	tty_wakeup(tty);
 }
 
-static void rfcomm_tty_send_xchar(struct tty_struct *tty, char ch)
+static void rfcomm_tty_send_xchar(struct tty_struct *tty, u8 ch)
 {
 	BT_DBG("tty %p ch %c", tty, ch);
 }
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index d7d021af1029..2d7b73242958 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1762,6 +1762,10 @@ static void br_ip6_multicast_querier_expired(struct timer_list *t)
 }
 #endif
 
+static void br_multicast_query_delay_expired(struct timer_list *t)
+{
+}
+
 static void br_multicast_select_own_querier(struct net_bridge_mcast *brmctx,
 					    struct br_ip *ip,
 					    struct sk_buff *skb)
@@ -3198,7 +3202,7 @@ br_multicast_update_query_timer(struct net_bridge_mcast *brmctx,
 				unsigned long max_delay)
 {
 	if (!timer_pending(&query->timer))
-		query->delay_time = jiffies + max_delay;
+		mod_timer(&query->delay_timer, jiffies + max_delay);
 
 	mod_timer(&query->timer, jiffies + brmctx->multicast_querier_interval);
 }
@@ -4041,13 +4045,11 @@ void br_multicast_ctx_init(struct net_bridge *br,
 	brmctx->multicast_querier_interval = 255 * HZ;
 	brmctx->multicast_membership_interval = 260 * HZ;
 
-	brmctx->ip4_other_query.delay_time = 0;
 	brmctx->ip4_querier.port_ifidx = 0;
 	seqcount_spinlock_init(&brmctx->ip4_querier.seq, &br->multicast_lock);
 	brmctx->multicast_igmp_version = 2;
 #if IS_ENABLED(CONFIG_IPV6)
 	brmctx->multicast_mld_version = 1;
-	brmctx->ip6_other_query.delay_time = 0;
 	brmctx->ip6_querier.port_ifidx = 0;
 	seqcount_spinlock_init(&brmctx->ip6_querier.seq, &br->multicast_lock);
 #endif
@@ -4056,6 +4058,8 @@ void br_multicast_ctx_init(struct net_bridge *br,
 		    br_ip4_multicast_local_router_expired, 0);
 	timer_setup(&brmctx->ip4_other_query.timer,
 		    br_ip4_multicast_querier_expired, 0);
+	timer_setup(&brmctx->ip4_other_query.delay_timer,
+		    br_multicast_query_delay_expired, 0);
 	timer_setup(&brmctx->ip4_own_query.timer,
 		    br_ip4_multicast_query_expired, 0);
 #if IS_ENABLED(CONFIG_IPV6)
@@ -4063,6 +4067,8 @@ void br_multicast_ctx_init(struct net_bridge *br,
 		    br_ip6_multicast_local_router_expired, 0);
 	timer_setup(&brmctx->ip6_other_query.timer,
 		    br_ip6_multicast_querier_expired, 0);
+	timer_setup(&brmctx->ip6_other_query.delay_timer,
+		    br_multicast_query_delay_expired, 0);
 	timer_setup(&brmctx->ip6_own_query.timer,
 		    br_ip6_multicast_query_expired, 0);
 #endif
@@ -4197,10 +4203,12 @@ static void __br_multicast_stop(struct net_bridge_mcast *brmctx)
 {
 	del_timer_sync(&brmctx->ip4_mc_router_timer);
 	del_timer_sync(&brmctx->ip4_other_query.timer);
+	del_timer_sync(&brmctx->ip4_other_query.delay_timer);
 	del_timer_sync(&brmctx->ip4_own_query.timer);
 #if IS_ENABLED(CONFIG_IPV6)
 	del_timer_sync(&brmctx->ip6_mc_router_timer);
 	del_timer_sync(&brmctx->ip6_other_query.timer);
+	del_timer_sync(&brmctx->ip6_other_query.delay_timer);
 	del_timer_sync(&brmctx->ip6_own_query.timer);
 #endif
 }
@@ -4643,13 +4651,15 @@ int br_multicast_set_querier(struct net_bridge_mcast *brmctx, unsigned long val)
 	max_delay = brmctx->multicast_query_response_interval;
 
 	if (!timer_pending(&brmctx->ip4_other_query.timer))
-		brmctx->ip4_other_query.delay_time = jiffies + max_delay;
+		mod_timer(&brmctx->ip4_other_query.delay_timer,
+			  jiffies + max_delay);
 
 	br_multicast_start_querier(brmctx, &brmctx->ip4_own_query);
 
 #if IS_ENABLED(CONFIG_IPV6)
 	if (!timer_pending(&brmctx->ip6_other_query.timer))
-		brmctx->ip6_other_query.delay_time = jiffies + max_delay;
+		mod_timer(&brmctx->ip6_other_query.delay_timer,
+			  jiffies + max_delay);
 
 	br_multicast_start_querier(brmctx, &brmctx->ip6_own_query);
 #endif
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 6adcb45bca75..35e10c5a766d 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -43,6 +43,10 @@
 #include <linux/sysctl.h>
 #endif
 
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+#include <net/netfilter/nf_conntrack_core.h>
+#endif
+
 static unsigned int brnf_net_id __read_mostly;
 
 struct brnf_net {
@@ -279,8 +283,17 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_
 
 		if ((READ_ONCE(neigh->nud_state) & NUD_CONNECTED) &&
 		    READ_ONCE(neigh->hh.hh_len)) {
+			struct net_device *br_indev;
+
+			br_indev = nf_bridge_get_physindev(skb, net);
+			if (!br_indev) {
+				neigh_release(neigh);
+				goto free_skb;
+			}
+
 			neigh_hh_bridge(&neigh->hh, skb);
-			skb->dev = nf_bridge->physindev;
+			skb->dev = br_indev;
+
 			ret = br_handle_frame_finish(net, sk, skb);
 		} else {
 			/* the neighbour function below overwrites the complete
@@ -352,12 +365,18 @@ br_nf_ipv4_daddr_was_changed(const struct sk_buff *skb,
  */
 static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	struct net_device *dev = skb->dev;
+	struct net_device *dev = skb->dev, *br_indev;
 	struct iphdr *iph = ip_hdr(skb);
 	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 	struct rtable *rt;
 	int err;
 
+	br_indev = nf_bridge_get_physindev(skb, net);
+	if (!br_indev) {
+		kfree_skb(skb);
+		return 0;
+	}
+
 	nf_bridge->frag_max_size = IPCB(skb)->frag_max_size;
 
 	if (nf_bridge->pkt_otherhost) {
@@ -397,7 +416,7 @@ free_skb:
 		} else {
 			if (skb_dst(skb)->dev == dev) {
 bridged_dnat:
-				skb->dev = nf_bridge->physindev;
+				skb->dev = br_indev;
 				nf_bridge_update_protocol(skb);
 				nf_bridge_push_encap_header(skb);
 				br_nf_hook_thresh(NF_BR_PRE_ROUTING,
@@ -410,7 +429,7 @@ bridged_dnat:
 			skb->pkt_type = PACKET_HOST;
 		}
 	} else {
-		rt = bridge_parent_rtable(nf_bridge->physindev);
+		rt = bridge_parent_rtable(br_indev);
 		if (!rt) {
 			kfree_skb(skb);
 			return 0;
@@ -419,7 +438,7 @@ bridged_dnat:
 		skb_dst_set_noref(skb, &rt->dst);
 	}
 
-	skb->dev = nf_bridge->physindev;
+	skb->dev = br_indev;
 	nf_bridge_update_protocol(skb);
 	nf_bridge_push_encap_header(skb);
 	br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL,
@@ -456,7 +475,7 @@ struct net_device *setup_pre_routing(struct sk_buff *skb, const struct net *net)
 	}
 
 	nf_bridge->in_prerouting = 1;
-	nf_bridge->physindev = skb->dev;
+	nf_bridge->physinif = skb->dev->ifindex;
 	skb->dev = brnf_get_logical_dev(skb, skb->dev, net);
 
 	if (skb->protocol == htons(ETH_P_8021Q))
@@ -538,6 +557,90 @@ static unsigned int br_nf_pre_routing(void *priv,
 	return NF_STOLEN;
 }
 
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+/* conntracks' nf_confirm logic cannot handle cloned skbs referencing
+ * the same nf_conn entry, which will happen for multicast (broadcast)
+ * Frames on bridges.
+ *
+ * Example:
+ *      macvlan0
+ *      br0
+ *  ethX  ethY
+ *
+ * ethX (or Y) receives multicast or broadcast packet containing
+ * an IP packet, not yet in conntrack table.
+ *
+ * 1. skb passes through bridge and fake-ip (br_netfilter)Prerouting.
+ *    -> skb->_nfct now references a unconfirmed entry
+ * 2. skb is broad/mcast packet. bridge now passes clones out on each bridge
+ *    interface.
+ * 3. skb gets passed up the stack.
+ * 4. In macvlan case, macvlan driver retains clone(s) of the mcast skb
+ *    and schedules a work queue to send them out on the lower devices.
+ *
+ *    The clone skb->_nfct is not a copy, it is the same entry as the
+ *    original skb.  The macvlan rx handler then returns RX_HANDLER_PASS.
+ * 5. Normal conntrack hooks (in NF_INET_LOCAL_IN) confirm the orig skb.
+ *
+ * The Macvlan broadcast worker and normal confirm path will race.
+ *
+ * This race will not happen if step 2 already confirmed a clone. In that
+ * case later steps perform skb_clone() with skb->_nfct already confirmed (in
+ * hash table).  This works fine.
+ *
+ * But such confirmation won't happen when eb/ip/nftables rules dropped the
+ * packets before they reached the nf_confirm step in postrouting.
+ *
+ * Work around this problem by explicit confirmation of the entry at
+ * LOCAL_IN time, before upper layer has a chance to clone the unconfirmed
+ * entry.
+ *
+ */
+static unsigned int br_nf_local_in(void *priv,
+				   struct sk_buff *skb,
+				   const struct nf_hook_state *state)
+{
+	struct nf_conntrack *nfct = skb_nfct(skb);
+	const struct nf_ct_hook *ct_hook;
+	struct nf_conn *ct;
+	int ret;
+
+	if (!nfct || skb->pkt_type == PACKET_HOST)
+		return NF_ACCEPT;
+
+	ct = container_of(nfct, struct nf_conn, ct_general);
+	if (likely(nf_ct_is_confirmed(ct)))
+		return NF_ACCEPT;
+
+	WARN_ON_ONCE(skb_shared(skb));
+	WARN_ON_ONCE(refcount_read(&nfct->use) != 1);
+
+	/* We can't call nf_confirm here, it would create a dependency
+	 * on nf_conntrack module.
+	 */
+	ct_hook = rcu_dereference(nf_ct_hook);
+	if (!ct_hook) {
+		skb->_nfct = 0ul;
+		nf_conntrack_put(nfct);
+		return NF_ACCEPT;
+	}
+
+	nf_bridge_pull_encap_header(skb);
+	ret = ct_hook->confirm(skb);
+	switch (ret & NF_VERDICT_MASK) {
+	case NF_STOLEN:
+		return NF_STOLEN;
+	default:
+		nf_bridge_push_encap_header(skb);
+		break;
+	}
+
+	ct = container_of(nfct, struct nf_conn, ct_general);
+	WARN_ON_ONCE(!nf_ct_is_confirmed(ct));
+
+	return ret;
+}
+#endif
 
 /* PF_BRIDGE/FORWARD *************************************************/
 static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
@@ -553,7 +656,11 @@ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff
 		if (skb->protocol == htons(ETH_P_IPV6))
 			nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size;
 
-		in = nf_bridge->physindev;
+		in = nf_bridge_get_physindev(skb, net);
+		if (!in) {
+			kfree_skb(skb);
+			return 0;
+		}
 		if (nf_bridge->pkt_otherhost) {
 			skb->pkt_type = PACKET_OTHERHOST;
 			nf_bridge->pkt_otherhost = false;
@@ -899,6 +1006,13 @@ static unsigned int ip_sabotage_in(void *priv,
 static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb)
 {
 	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
+	struct net_device *br_indev;
+
+	br_indev = nf_bridge_get_physindev(skb, dev_net(skb->dev));
+	if (!br_indev) {
+		kfree_skb(skb);
+		return;
+	}
 
 	skb_pull(skb, ETH_HLEN);
 	nf_bridge->bridged_dnat = 0;
@@ -908,7 +1022,7 @@ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb)
 	skb_copy_to_linear_data_offset(skb, -(ETH_HLEN - ETH_ALEN),
 				       nf_bridge->neigh_header,
 				       ETH_HLEN - ETH_ALEN);
-	skb->dev = nf_bridge->physindev;
+	skb->dev = br_indev;
 
 	nf_bridge->physoutdev = NULL;
 	br_handle_frame_finish(dev_net(skb->dev), NULL, skb);
@@ -938,6 +1052,14 @@ static const struct nf_hook_ops br_nf_ops[] = {
 		.hooknum = NF_BR_PRE_ROUTING,
 		.priority = NF_BR_PRI_BRNF,
 	},
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+	{
+		.hook = br_nf_local_in,
+		.pf = NFPROTO_BRIDGE,
+		.hooknum = NF_BR_LOCAL_IN,
+		.priority = NF_BR_PRI_LAST,
+	},
+#endif
 	{
 		.hook = br_nf_forward,
 		.pf = NFPROTO_BRIDGE,
diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c
index 2e24a743f917..e0421eaa3abc 100644
--- a/net/bridge/br_netfilter_ipv6.c
+++ b/net/bridge/br_netfilter_ipv6.c
@@ -102,9 +102,15 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
 {
 	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 	struct rtable *rt;
-	struct net_device *dev = skb->dev;
+	struct net_device *dev = skb->dev, *br_indev;
 	const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
 
+	br_indev = nf_bridge_get_physindev(skb, net);
+	if (!br_indev) {
+		kfree_skb(skb);
+		return 0;
+	}
+
 	nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size;
 
 	if (nf_bridge->pkt_otherhost) {
@@ -122,7 +128,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
 		}
 
 		if (skb_dst(skb)->dev == dev) {
-			skb->dev = nf_bridge->physindev;
+			skb->dev = br_indev;
 			nf_bridge_update_protocol(skb);
 			nf_bridge_push_encap_header(skb);
 			br_nf_hook_thresh(NF_BR_PRE_ROUTING,
@@ -133,7 +139,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
 		ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr);
 		skb->pkt_type = PACKET_HOST;
 	} else {
-		rt = bridge_parent_rtable(nf_bridge->physindev);
+		rt = bridge_parent_rtable(br_indev);
 		if (!rt) {
 			kfree_skb(skb);
 			return 0;
@@ -142,7 +148,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
 		skb_dst_set_noref(skb, &rt->dst);
 	}
 
-	skb->dev = nf_bridge->physindev;
+	skb->dev = br_indev;
 	nf_bridge_update_protocol(skb);
 	nf_bridge_push_encap_header(skb);
 	br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb,
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index b0a92c344722..86ea5e6689b5 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -78,7 +78,7 @@ struct bridge_mcast_own_query {
 /* other querier */
 struct bridge_mcast_other_query {
 	struct timer_list		timer;
-	unsigned long			delay_time;
+	struct timer_list		delay_timer;
 };
 
 /* selected querier */
@@ -1159,7 +1159,7 @@ __br_multicast_querier_exists(struct net_bridge_mcast *brmctx,
 		own_querier_enabled = false;
 	}
 
-	return time_is_before_jiffies(querier->delay_time) &&
+	return !timer_pending(&querier->delay_timer) &&
 	       (own_querier_enabled || timer_pending(&querier->timer));
 }
 
diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index ee84e783e1df..7b41ee8740cb 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -595,21 +595,40 @@ br_switchdev_mdb_replay_one(struct notifier_block *nb, struct net_device *dev,
 }
 
 static int br_switchdev_mdb_queue_one(struct list_head *mdb_list,
+				      struct net_device *dev,
+				      unsigned long action,
 				      enum switchdev_obj_id id,
 				      const struct net_bridge_mdb_entry *mp,
 				      struct net_device *orig_dev)
 {
-	struct switchdev_obj_port_mdb *mdb;
+	struct switchdev_obj_port_mdb mdb = {
+		.obj = {
+			.id = id,
+			.orig_dev = orig_dev,
+		},
+	};
+	struct switchdev_obj_port_mdb *pmdb;
 
-	mdb = kzalloc(sizeof(*mdb), GFP_ATOMIC);
-	if (!mdb)
-		return -ENOMEM;
+	br_switchdev_mdb_populate(&mdb, mp);
+
+	if (action == SWITCHDEV_PORT_OBJ_ADD &&
+	    switchdev_port_obj_act_is_deferred(dev, action, &mdb.obj)) {
+		/* This event is already in the deferred queue of
+		 * events, so this replay must be elided, lest the
+		 * driver receives duplicate events for it. This can
+		 * only happen when replaying additions, since
+		 * modifications are always immediately visible in
+		 * br->mdb_list, whereas actual event delivery may be
+		 * delayed.
+		 */
+		return 0;
+	}
 
-	mdb->obj.id = id;
-	mdb->obj.orig_dev = orig_dev;
-	br_switchdev_mdb_populate(mdb, mp);
-	list_add_tail(&mdb->obj.list, mdb_list);
+	pmdb = kmemdup(&mdb, sizeof(mdb), GFP_ATOMIC);
+	if (!pmdb)
+		return -ENOMEM;
 
+	list_add_tail(&pmdb->obj.list, mdb_list);
 	return 0;
 }
 
@@ -677,51 +696,50 @@ br_switchdev_mdb_replay(struct net_device *br_dev, struct net_device *dev,
 	if (!br_opt_get(br, BROPT_MULTICAST_ENABLED))
 		return 0;
 
-	/* We cannot walk over br->mdb_list protected just by the rtnl_mutex,
-	 * because the write-side protection is br->multicast_lock. But we
-	 * need to emulate the [ blocking ] calling context of a regular
-	 * switchdev event, so since both br->multicast_lock and RCU read side
-	 * critical sections are atomic, we have no choice but to pick the RCU
-	 * read side lock, queue up all our events, leave the critical section
-	 * and notify switchdev from blocking context.
+	if (adding)
+		action = SWITCHDEV_PORT_OBJ_ADD;
+	else
+		action = SWITCHDEV_PORT_OBJ_DEL;
+
+	/* br_switchdev_mdb_queue_one() will take care to not queue a
+	 * replay of an event that is already pending in the switchdev
+	 * deferred queue. In order to safely determine that, there
+	 * must be no new deferred MDB notifications enqueued for the
+	 * duration of the MDB scan. Therefore, grab the write-side
+	 * lock to avoid racing with any concurrent IGMP/MLD snooping.
 	 */
-	rcu_read_lock();
+	spin_lock_bh(&br->multicast_lock);
 
-	hlist_for_each_entry_rcu(mp, &br->mdb_list, mdb_node) {
+	hlist_for_each_entry(mp, &br->mdb_list, mdb_node) {
 		struct net_bridge_port_group __rcu * const *pp;
 		const struct net_bridge_port_group *p;
 
 		if (mp->host_joined) {
-			err = br_switchdev_mdb_queue_one(&mdb_list,
+			err = br_switchdev_mdb_queue_one(&mdb_list, dev, action,
 							 SWITCHDEV_OBJ_ID_HOST_MDB,
 							 mp, br_dev);
 			if (err) {
-				rcu_read_unlock();
+				spin_unlock_bh(&br->multicast_lock);
 				goto out_free_mdb;
 			}
 		}
 
-		for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL;
+		for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL;
 		     pp = &p->next) {
 			if (p->key.port->dev != dev)
 				continue;
 
-			err = br_switchdev_mdb_queue_one(&mdb_list,
+			err = br_switchdev_mdb_queue_one(&mdb_list, dev, action,
 							 SWITCHDEV_OBJ_ID_PORT_MDB,
 							 mp, dev);
 			if (err) {
-				rcu_read_unlock();
+				spin_unlock_bh(&br->multicast_lock);
 				goto out_free_mdb;
 			}
 		}
 	}
 
-	rcu_read_unlock();
-
-	if (adding)
-		action = SWITCHDEV_PORT_OBJ_ADD;
-	else
-		action = SWITCHDEV_PORT_OBJ_DEL;
+	spin_unlock_bh(&br->multicast_lock);
 
 	list_for_each_entry(obj, &mdb_list, list) {
 		err = br_switchdev_mdb_replay_one(nb, dev,
@@ -786,6 +804,16 @@ static void nbp_switchdev_unsync_objs(struct net_bridge_port *p,
 	br_switchdev_mdb_replay(br_dev, dev, ctx, false, blocking_nb, NULL);
 
 	br_switchdev_vlan_replay(br_dev, ctx, false, blocking_nb, NULL);
+
+	/* Make sure that the device leaving this bridge has seen all
+	 * relevant events before it is disassociated. In the normal
+	 * case, when the device is directly attached to the bridge,
+	 * this is covered by del_nbp(). If the association was indirect
+	 * however, e.g. via a team or bond, and the device is leaving
+	 * that intermediate device, then the bridge port remains in
+	 * place.
+	 */
+	switchdev_deferred_process();
 }
 
 /* Let the bridge know that this port is offloaded, so that it can assign a
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index abb090f94ed2..6f877e31709b 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -291,6 +291,30 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb,
 	return nf_conntrack_in(skb, &bridge_state);
 }
 
+static unsigned int nf_ct_bridge_in(void *priv, struct sk_buff *skb,
+				    const struct nf_hook_state *state)
+{
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct;
+
+	if (skb->pkt_type == PACKET_HOST)
+		return NF_ACCEPT;
+
+	/* nf_conntrack_confirm() cannot handle concurrent clones,
+	 * this happens for broad/multicast frames with e.g. macvlan on top
+	 * of the bridge device.
+	 */
+	ct = nf_ct_get(skb, &ctinfo);
+	if (!ct || nf_ct_is_confirmed(ct) || nf_ct_is_template(ct))
+		return NF_ACCEPT;
+
+	/* let inet prerouting call conntrack again */
+	skb->_nfct = 0;
+	nf_ct_put(ct);
+
+	return NF_ACCEPT;
+}
+
 static void nf_ct_bridge_frag_save(struct sk_buff *skb,
 				   struct nf_bridge_frag_data *data)
 {
@@ -386,6 +410,12 @@ static struct nf_hook_ops nf_ct_bridge_hook_ops[] __read_mostly = {
 		.priority	= NF_IP_PRI_CONNTRACK,
 	},
 	{
+		.hook		= nf_ct_bridge_in,
+		.pf		= NFPROTO_BRIDGE,
+		.hooknum	= NF_BR_LOCAL_IN,
+		.priority	= NF_IP_PRI_CONNTRACK_CONFIRM,
+	},
+	{
 		.hook		= nf_ct_bridge_post,
 		.pf		= NFPROTO_BRIDGE,
 		.hooknum	= NF_BR_POST_ROUTING,
diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h
index 16af1a7f80f6..31a93cae5111 100644
--- a/net/can/j1939/j1939-priv.h
+++ b/net/can/j1939/j1939-priv.h
@@ -86,7 +86,7 @@ struct j1939_priv {
 	unsigned int tp_max_packet_size;
 
 	/* lock for j1939_socks list */
-	spinlock_t j1939_socks_lock;
+	rwlock_t j1939_socks_lock;
 	struct list_head j1939_socks;
 
 	struct kref rx_kref;
@@ -301,6 +301,7 @@ struct j1939_sock {
 
 	int ifindex;
 	struct j1939_addr addr;
+	spinlock_t filters_lock;
 	struct j1939_filter *filters;
 	int nfilters;
 	pgn_t pgn_rx_filter;
diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c
index ecff1c947d68..a6fb89fa6278 100644
--- a/net/can/j1939/main.c
+++ b/net/can/j1939/main.c
@@ -274,7 +274,7 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev)
 		return ERR_PTR(-ENOMEM);
 
 	j1939_tp_init(priv);
-	spin_lock_init(&priv->j1939_socks_lock);
+	rwlock_init(&priv->j1939_socks_lock);
 	INIT_LIST_HEAD(&priv->j1939_socks);
 
 	mutex_lock(&j1939_netdev_lock);
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index 14c431663233..305dd72c844c 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -80,16 +80,16 @@ static void j1939_jsk_add(struct j1939_priv *priv, struct j1939_sock *jsk)
 	jsk->state |= J1939_SOCK_BOUND;
 	j1939_priv_get(priv);
 
-	spin_lock_bh(&priv->j1939_socks_lock);
+	write_lock_bh(&priv->j1939_socks_lock);
 	list_add_tail(&jsk->list, &priv->j1939_socks);
-	spin_unlock_bh(&priv->j1939_socks_lock);
+	write_unlock_bh(&priv->j1939_socks_lock);
 }
 
 static void j1939_jsk_del(struct j1939_priv *priv, struct j1939_sock *jsk)
 {
-	spin_lock_bh(&priv->j1939_socks_lock);
+	write_lock_bh(&priv->j1939_socks_lock);
 	list_del_init(&jsk->list);
-	spin_unlock_bh(&priv->j1939_socks_lock);
+	write_unlock_bh(&priv->j1939_socks_lock);
 
 	j1939_priv_put(priv);
 	jsk->state &= ~J1939_SOCK_BOUND;
@@ -262,12 +262,17 @@ static bool j1939_sk_match_dst(struct j1939_sock *jsk,
 static bool j1939_sk_match_filter(struct j1939_sock *jsk,
 				  const struct j1939_sk_buff_cb *skcb)
 {
-	const struct j1939_filter *f = jsk->filters;
-	int nfilter = jsk->nfilters;
+	const struct j1939_filter *f;
+	int nfilter;
+
+	spin_lock_bh(&jsk->filters_lock);
+
+	f = jsk->filters;
+	nfilter = jsk->nfilters;
 
 	if (!nfilter)
 		/* receive all when no filters are assigned */
-		return true;
+		goto filter_match_found;
 
 	for (; nfilter; ++f, --nfilter) {
 		if ((skcb->addr.pgn & f->pgn_mask) != f->pgn)
@@ -276,9 +281,15 @@ static bool j1939_sk_match_filter(struct j1939_sock *jsk,
 			continue;
 		if ((skcb->addr.src_name & f->name_mask) != f->name)
 			continue;
-		return true;
+		goto filter_match_found;
 	}
+
+	spin_unlock_bh(&jsk->filters_lock);
 	return false;
+
+filter_match_found:
+	spin_unlock_bh(&jsk->filters_lock);
+	return true;
 }
 
 static bool j1939_sk_recv_match_one(struct j1939_sock *jsk,
@@ -329,13 +340,13 @@ bool j1939_sk_recv_match(struct j1939_priv *priv, struct j1939_sk_buff_cb *skcb)
 	struct j1939_sock *jsk;
 	bool match = false;
 
-	spin_lock_bh(&priv->j1939_socks_lock);
+	read_lock_bh(&priv->j1939_socks_lock);
 	list_for_each_entry(jsk, &priv->j1939_socks, list) {
 		match = j1939_sk_recv_match_one(jsk, skcb);
 		if (match)
 			break;
 	}
-	spin_unlock_bh(&priv->j1939_socks_lock);
+	read_unlock_bh(&priv->j1939_socks_lock);
 
 	return match;
 }
@@ -344,11 +355,11 @@ void j1939_sk_recv(struct j1939_priv *priv, struct sk_buff *skb)
 {
 	struct j1939_sock *jsk;
 
-	spin_lock_bh(&priv->j1939_socks_lock);
+	read_lock_bh(&priv->j1939_socks_lock);
 	list_for_each_entry(jsk, &priv->j1939_socks, list) {
 		j1939_sk_recv_one(jsk, skb);
 	}
-	spin_unlock_bh(&priv->j1939_socks_lock);
+	read_unlock_bh(&priv->j1939_socks_lock);
 }
 
 static void j1939_sk_sock_destruct(struct sock *sk)
@@ -401,6 +412,7 @@ static int j1939_sk_init(struct sock *sk)
 	atomic_set(&jsk->skb_pending, 0);
 	spin_lock_init(&jsk->sk_session_queue_lock);
 	INIT_LIST_HEAD(&jsk->sk_session_queue);
+	spin_lock_init(&jsk->filters_lock);
 
 	/* j1939_sk_sock_destruct() depends on SOCK_RCU_FREE flag */
 	sock_set_flag(sk, SOCK_RCU_FREE);
@@ -703,9 +715,11 @@ static int j1939_sk_setsockopt(struct socket *sock, int level, int optname,
 		}
 
 		lock_sock(&jsk->sk);
+		spin_lock_bh(&jsk->filters_lock);
 		ofilters = jsk->filters;
 		jsk->filters = filters;
 		jsk->nfilters = count;
+		spin_unlock_bh(&jsk->filters_lock);
 		release_sock(&jsk->sk);
 		kfree(ofilters);
 		return 0;
@@ -1080,12 +1094,12 @@ void j1939_sk_errqueue(struct j1939_session *session,
 	}
 
 	/* spread RX notifications to all sockets subscribed to this session */
-	spin_lock_bh(&priv->j1939_socks_lock);
+	read_lock_bh(&priv->j1939_socks_lock);
 	list_for_each_entry(jsk, &priv->j1939_socks, list) {
 		if (j1939_sk_recv_match_one(jsk, &session->skcb))
 			__j1939_sk_errqueue(session, &jsk->sk, type);
 	}
-	spin_unlock_bh(&priv->j1939_socks_lock);
+	read_unlock_bh(&priv->j1939_socks_lock);
 };
 
 void j1939_sk_send_loop_abort(struct sock *sk, int err)
@@ -1273,7 +1287,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv)
 	struct j1939_sock *jsk;
 	int error_code = ENETDOWN;
 
-	spin_lock_bh(&priv->j1939_socks_lock);
+	read_lock_bh(&priv->j1939_socks_lock);
 	list_for_each_entry(jsk, &priv->j1939_socks, list) {
 		jsk->sk.sk_err = error_code;
 		if (!sock_flag(&jsk->sk, SOCK_DEAD))
@@ -1281,7 +1295,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv)
 
 		j1939_sk_queue_drop_all(priv, jsk, error_code);
 	}
-	spin_unlock_bh(&priv->j1939_socks_lock);
+	read_unlock_bh(&priv->j1939_socks_lock);
 }
 
 static int j1939_sk_no_ioctlcmd(struct socket *sock, unsigned int cmd,
diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c
index f9a50d7f0d20..0cb61c76b9b8 100644
--- a/net/ceph/messenger_v1.c
+++ b/net/ceph/messenger_v1.c
@@ -160,8 +160,9 @@ static size_t sizeof_footer(struct ceph_connection *con)
 static void prepare_message_data(struct ceph_msg *msg, u32 data_len)
 {
 	/* Initialize data cursor if it's not a sparse read */
-	if (!msg->sparse_read)
-		ceph_msg_data_cursor_init(&msg->cursor, msg, data_len);
+	u64 len = msg->sparse_read_total ? : data_len;
+
+	ceph_msg_data_cursor_init(&msg->cursor, msg, len);
 }
 
 /*
@@ -991,7 +992,7 @@ static inline int read_partial_message_section(struct ceph_connection *con,
 	return read_partial_message_chunk(con, section, sec_len, crc);
 }
 
-static int read_sparse_msg_extent(struct ceph_connection *con, u32 *crc)
+static int read_partial_sparse_msg_extent(struct ceph_connection *con, u32 *crc)
 {
 	struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor;
 	bool do_bounce = ceph_test_opt(from_msgr(con->msgr), RXBOUNCE);
@@ -1026,7 +1027,7 @@ static int read_sparse_msg_extent(struct ceph_connection *con, u32 *crc)
 	return 1;
 }
 
-static int read_sparse_msg_data(struct ceph_connection *con)
+static int read_partial_sparse_msg_data(struct ceph_connection *con)
 {
 	struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor;
 	bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
@@ -1036,31 +1037,31 @@ static int read_sparse_msg_data(struct ceph_connection *con)
 	if (do_datacrc)
 		crc = con->in_data_crc;
 
-	do {
+	while (cursor->total_resid) {
 		if (con->v1.in_sr_kvec.iov_base)
 			ret = read_partial_message_chunk(con,
 							 &con->v1.in_sr_kvec,
 							 con->v1.in_sr_len,
 							 &crc);
 		else if (cursor->sr_resid > 0)
-			ret = read_sparse_msg_extent(con, &crc);
-
-		if (ret <= 0) {
-			if (do_datacrc)
-				con->in_data_crc = crc;
-			return ret;
-		}
+			ret = read_partial_sparse_msg_extent(con, &crc);
+		if (ret <= 0)
+			break;
 
 		memset(&con->v1.in_sr_kvec, 0, sizeof(con->v1.in_sr_kvec));
 		ret = con->ops->sparse_read(con, cursor,
 				(char **)&con->v1.in_sr_kvec.iov_base);
+		if (ret <= 0) {
+			ret = ret ? ret : 1;  /* must return > 0 to indicate success */
+			break;
+		}
 		con->v1.in_sr_len = ret;
-	} while (ret > 0);
+	}
 
 	if (do_datacrc)
 		con->in_data_crc = crc;
 
-	return ret < 0 ? ret : 1;  /* must return > 0 to indicate success */
+	return ret;
 }
 
 static int read_partial_msg_data(struct ceph_connection *con)
@@ -1253,8 +1254,8 @@ static int read_partial_message(struct ceph_connection *con)
 		if (!m->num_data_items)
 			return -EIO;
 
-		if (m->sparse_read)
-			ret = read_sparse_msg_data(con);
+		if (m->sparse_read_total)
+			ret = read_partial_sparse_msg_data(con);
 		else if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE))
 			ret = read_partial_msg_data_bounce(con);
 		else
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index f8ec60e1aba3..bd608ffa0627 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -1128,7 +1128,7 @@ static int decrypt_tail(struct ceph_connection *con)
 	struct sg_table enc_sgt = {};
 	struct sg_table sgt = {};
 	struct page **pages = NULL;
-	bool sparse = con->in_msg->sparse_read;
+	bool sparse = !!con->in_msg->sparse_read_total;
 	int dpos = 0;
 	int tail_len;
 	int ret;
@@ -2034,6 +2034,9 @@ static int prepare_sparse_read_data(struct ceph_connection *con)
 	if (!con_secure(con))
 		con->in_data_crc = -1;
 
+	ceph_msg_data_cursor_init(&con->v2.in_cursor, msg,
+				  msg->sparse_read_total);
+
 	reset_in_kvecs(con);
 	con->v2.in_state = IN_S_PREPARE_SPARSE_DATA_CONT;
 	con->v2.data_len_remain = data_len(msg);
@@ -2060,7 +2063,7 @@ static int prepare_read_tail_plain(struct ceph_connection *con)
 	}
 
 	if (data_len(msg)) {
-		if (msg->sparse_read)
+		if (msg->sparse_read_total)
 			con->v2.in_state = IN_S_PREPARE_SPARSE_DATA;
 		else
 			con->v2.in_state = IN_S_PREPARE_READ_DATA;
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index d3a759e052c8..9d078b37fe0b 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -5510,7 +5510,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
 	}
 
 	m = ceph_msg_get(req->r_reply);
-	m->sparse_read = (bool)srlen;
+	m->sparse_read_total = srlen;
 
 	dout("get_reply tid %lld %p\n", tid, m);
 
@@ -5777,11 +5777,8 @@ static int prep_next_sparse_read(struct ceph_connection *con,
 	}
 
 	if (o->o_sparse_op_idx < 0) {
-		u64 srlen = sparse_data_requested(req);
-
-		dout("%s: [%d] starting new sparse read req. srlen=0x%llx\n",
-		     __func__, o->o_osd, srlen);
-		ceph_msg_data_cursor_init(cursor, con->in_msg, srlen);
+		dout("%s: [%d] starting new sparse read req\n",
+		     __func__, o->o_osd);
 	} else {
 		u64 end;
 
@@ -5850,8 +5847,6 @@ static inline void convert_extent_map(struct ceph_sparse_read *sr)
 }
 #endif
 
-#define MAX_EXTENTS 4096
-
 static int osd_sparse_read(struct ceph_connection *con,
 			   struct ceph_msg_data_cursor *cursor,
 			   char **pbuf)
@@ -5859,8 +5854,8 @@ static int osd_sparse_read(struct ceph_connection *con,
 	struct ceph_osd *o = con->private;
 	struct ceph_sparse_read *sr = &o->o_sparse_read;
 	u32 count = sr->sr_count;
-	u64 eoff, elen;
-	int ret;
+	u64 eoff, elen, len = 0;
+	int i, ret;
 
 	switch (sr->sr_state) {
 	case CEPH_SPARSE_READ_HDR:
@@ -5882,23 +5877,16 @@ next_op:
 
 		if (count > 0) {
 			if (!sr->sr_extent || count > sr->sr_ext_len) {
-				/*
-				 * Apply a hard cap to the number of extents.
-				 * If we have more, assume something is wrong.
-				 */
-				if (count > MAX_EXTENTS) {
-					dout("%s: OSD returned 0x%x extents in a single reply!\n",
-					     __func__, count);
-					return -EREMOTEIO;
-				}
-
 				/* no extent array provided, or too short */
 				kfree(sr->sr_extent);
 				sr->sr_extent = kmalloc_array(count,
 							      sizeof(*sr->sr_extent),
 							      GFP_NOIO);
-				if (!sr->sr_extent)
+				if (!sr->sr_extent) {
+					pr_err("%s: failed to allocate %u extents\n",
+					       __func__, count);
 					return -ENOMEM;
+				}
 				sr->sr_ext_len = count;
 			}
 			ret = count * sizeof(*sr->sr_extent);
@@ -5912,8 +5900,20 @@ next_op:
 		convert_extent_map(sr);
 		ret = sizeof(sr->sr_datalen);
 		*pbuf = (char *)&sr->sr_datalen;
-		sr->sr_state = CEPH_SPARSE_READ_DATA;
+		sr->sr_state = CEPH_SPARSE_READ_DATA_PRE;
 		break;
+	case CEPH_SPARSE_READ_DATA_PRE:
+		/* Convert sr_datalen to host-endian */
+		sr->sr_datalen = le32_to_cpu((__force __le32)sr->sr_datalen);
+		for (i = 0; i < count; i++)
+			len += sr->sr_extent[i].len;
+		if (sr->sr_datalen != len) {
+			pr_warn_ratelimited("data len %u != extent len %llu\n",
+					    sr->sr_datalen, len);
+			return -EREMOTEIO;
+		}
+		sr->sr_state = CEPH_SPARSE_READ_DATA;
+		fallthrough;
 	case CEPH_SPARSE_READ_DATA:
 		if (sr->sr_index >= count) {
 			sr->sr_state = CEPH_SPARSE_READ_HDR;
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 103d46fa0eeb..a8b625abe242 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -751,7 +751,7 @@ size_t memcpy_to_iter_csum(void *iter_to, size_t progress,
 			   size_t len, void *from, void *priv2)
 {
 	__wsum *csum = priv2;
-	__wsum next = csum_partial_copy_nocheck(from, iter_to, len);
+	__wsum next = csum_partial_copy_nocheck(from + progress, iter_to, len);
 
 	*csum = csum_block_add(*csum, next, progress);
 	return 0;
diff --git a/net/core/dev.c b/net/core/dev.c
index f01a9b858347..a892f7265189 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -336,7 +336,7 @@ int netdev_name_node_alt_create(struct net_device *dev, const char *name)
 		return -ENOMEM;
 	netdev_name_node_add(net, name_node);
 	/* The node that holds dev->name acts as a head of per-device list. */
-	list_add_tail(&name_node->list, &dev->name_node->list);
+	list_add_tail_rcu(&name_node->list, &dev->name_node->list);
 
 	return 0;
 }
@@ -6177,8 +6177,13 @@ static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
 	clear_bit(NAPI_STATE_SCHED, &napi->state);
 }
 
-static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool prefer_busy_poll,
-			   u16 budget)
+enum {
+	NAPI_F_PREFER_BUSY_POLL	= 1,
+	NAPI_F_END_ON_RESCHED	= 2,
+};
+
+static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
+			   unsigned flags, u16 budget)
 {
 	bool skip_schedule = false;
 	unsigned long timeout;
@@ -6198,7 +6203,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool
 
 	local_bh_disable();
 
-	if (prefer_busy_poll) {
+	if (flags & NAPI_F_PREFER_BUSY_POLL) {
 		napi->defer_hard_irqs_count = READ_ONCE(napi->dev->napi_defer_hard_irqs);
 		timeout = READ_ONCE(napi->dev->gro_flush_timeout);
 		if (napi->defer_hard_irqs_count && timeout) {
@@ -6222,23 +6227,23 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool
 	local_bh_enable();
 }
 
-void napi_busy_loop(unsigned int napi_id,
-		    bool (*loop_end)(void *, unsigned long),
-		    void *loop_end_arg, bool prefer_busy_poll, u16 budget)
+static void __napi_busy_loop(unsigned int napi_id,
+		      bool (*loop_end)(void *, unsigned long),
+		      void *loop_end_arg, unsigned flags, u16 budget)
 {
 	unsigned long start_time = loop_end ? busy_loop_current_time() : 0;
 	int (*napi_poll)(struct napi_struct *napi, int budget);
 	void *have_poll_lock = NULL;
 	struct napi_struct *napi;
 
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
 restart:
 	napi_poll = NULL;
 
-	rcu_read_lock();
-
 	napi = napi_by_id(napi_id);
 	if (!napi)
-		goto out;
+		return;
 
 	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
 		preempt_disable();
@@ -6254,14 +6259,14 @@ restart:
 			 */
 			if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED |
 				   NAPIF_STATE_IN_BUSY_POLL)) {
-				if (prefer_busy_poll)
+				if (flags & NAPI_F_PREFER_BUSY_POLL)
 					set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
 				goto count;
 			}
 			if (cmpxchg(&napi->state, val,
 				    val | NAPIF_STATE_IN_BUSY_POLL |
 					  NAPIF_STATE_SCHED) != val) {
-				if (prefer_busy_poll)
+				if (flags & NAPI_F_PREFER_BUSY_POLL)
 					set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
 				goto count;
 			}
@@ -6281,12 +6286,15 @@ count:
 			break;
 
 		if (unlikely(need_resched())) {
+			if (flags & NAPI_F_END_ON_RESCHED)
+				break;
 			if (napi_poll)
-				busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
+				busy_poll_stop(napi, have_poll_lock, flags, budget);
 			if (!IS_ENABLED(CONFIG_PREEMPT_RT))
 				preempt_enable();
 			rcu_read_unlock();
 			cond_resched();
+			rcu_read_lock();
 			if (loop_end(loop_end_arg, start_time))
 				return;
 			goto restart;
@@ -6294,10 +6302,31 @@ count:
 		cpu_relax();
 	}
 	if (napi_poll)
-		busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
+		busy_poll_stop(napi, have_poll_lock, flags, budget);
 	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
 		preempt_enable();
-out:
+}
+
+void napi_busy_loop_rcu(unsigned int napi_id,
+			bool (*loop_end)(void *, unsigned long),
+			void *loop_end_arg, bool prefer_busy_poll, u16 budget)
+{
+	unsigned flags = NAPI_F_END_ON_RESCHED;
+
+	if (prefer_busy_poll)
+		flags |= NAPI_F_PREFER_BUSY_POLL;
+
+	__napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget);
+}
+
+void napi_busy_loop(unsigned int napi_id,
+		    bool (*loop_end)(void *, unsigned long),
+		    void *loop_end_arg, bool prefer_busy_poll, u16 budget)
+{
+	unsigned flags = prefer_busy_poll ? NAPI_F_PREFER_BUSY_POLL : 0;
+
+	rcu_read_lock();
+	__napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget);
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL(napi_busy_loop);
@@ -9074,28 +9103,6 @@ bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b)
 }
 EXPORT_SYMBOL(netdev_port_same_parent_id);
 
-static void netdev_dpll_pin_assign(struct net_device *dev, struct dpll_pin *dpll_pin)
-{
-#if IS_ENABLED(CONFIG_DPLL)
-	rtnl_lock();
-	dev->dpll_pin = dpll_pin;
-	rtnl_unlock();
-#endif
-}
-
-void netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin)
-{
-	WARN_ON(!dpll_pin);
-	netdev_dpll_pin_assign(dev, dpll_pin);
-}
-EXPORT_SYMBOL(netdev_dpll_pin_set);
-
-void netdev_dpll_pin_clear(struct net_device *dev)
-{
-	netdev_dpll_pin_assign(dev, NULL);
-}
-EXPORT_SYMBOL(netdev_dpll_pin_clear);
-
 /**
  *	dev_change_proto_down - set carrier according to proto_down.
  *
@@ -11551,6 +11558,7 @@ static struct pernet_operations __net_initdata netdev_net_ops = {
 
 static void __net_exit default_device_exit_net(struct net *net)
 {
+	struct netdev_name_node *name_node, *tmp;
 	struct net_device *dev, *aux;
 	/*
 	 * Push all migratable network devices back to the
@@ -11573,6 +11581,14 @@ static void __net_exit default_device_exit_net(struct net *net)
 		snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex);
 		if (netdev_name_in_use(&init_net, fb_name))
 			snprintf(fb_name, IFNAMSIZ, "dev%%d");
+
+		netdev_for_each_altname_safe(dev, name_node, tmp)
+			if (netdev_name_in_use(&init_net, name_node->name)) {
+				netdev_name_node_del(name_node);
+				synchronize_rcu();
+				__netdev_name_node_alt_destroy(name_node);
+			}
+
 		err = dev_change_net_namespace(dev, &init_net, fb_name);
 		if (err) {
 			pr_emerg("%s: failed to move %s to init_net: %d\n",
@@ -11643,11 +11659,12 @@ static void __init net_dev_struct_check(void)
 	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 160);
 
 	/* TXRX read-mostly hotpath */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, lstats);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr);
-	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 30);
+	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 38);
 
 	/* RX read-mostly hotpath */
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific);
diff --git a/net/core/dev.h b/net/core/dev.h
index cf93e188785b..7480b4c84298 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -63,6 +63,9 @@ int dev_change_name(struct net_device *dev, const char *newname);
 
 #define netdev_for_each_altname(dev, namenode)				\
 	list_for_each_entry((namenode), &(dev)->name_node->list, list)
+#define netdev_for_each_altname_safe(dev, namenode, next)		\
+	list_for_each_entry_safe((namenode), (next), &(dev)->name_node->list, \
+				 list)
 
 int netdev_name_node_alt_create(struct net_device *dev, const char *name);
 int netdev_name_node_alt_destroy(struct net_device *dev, const char *name);
diff --git a/net/core/filter.c b/net/core/filter.c
index 24061f29c9dd..ef3e78b6a39c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -83,6 +83,7 @@
 #include <net/netfilter/nf_conntrack_bpf.h>
 #include <net/netkit.h>
 #include <linux/un.h>
+#include <net/xdp_sock_drv.h>
 
 #include "dev.h"
 
@@ -4092,10 +4093,46 @@ static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset)
 	memset(skb_frag_address(frag) + skb_frag_size(frag), 0, offset);
 	skb_frag_size_add(frag, offset);
 	sinfo->xdp_frags_size += offset;
+	if (rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL)
+		xsk_buff_get_tail(xdp)->data_end += offset;
 
 	return 0;
 }
 
+static void bpf_xdp_shrink_data_zc(struct xdp_buff *xdp, int shrink,
+				   struct xdp_mem_info *mem_info, bool release)
+{
+	struct xdp_buff *zc_frag = xsk_buff_get_tail(xdp);
+
+	if (release) {
+		xsk_buff_del_tail(zc_frag);
+		__xdp_return(NULL, mem_info, false, zc_frag);
+	} else {
+		zc_frag->data_end -= shrink;
+	}
+}
+
+static bool bpf_xdp_shrink_data(struct xdp_buff *xdp, skb_frag_t *frag,
+				int shrink)
+{
+	struct xdp_mem_info *mem_info = &xdp->rxq->mem;
+	bool release = skb_frag_size(frag) == shrink;
+
+	if (mem_info->type == MEM_TYPE_XSK_BUFF_POOL) {
+		bpf_xdp_shrink_data_zc(xdp, shrink, mem_info, release);
+		goto out;
+	}
+
+	if (release) {
+		struct page *page = skb_frag_page(frag);
+
+		__xdp_return(page_address(page), mem_info, false, NULL);
+	}
+
+out:
+	return release;
+}
+
 static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset)
 {
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
@@ -4110,12 +4147,7 @@ static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset)
 
 		len_free += shrink;
 		offset -= shrink;
-
-		if (skb_frag_size(frag) == shrink) {
-			struct page *page = skb_frag_page(frag);
-
-			__xdp_return(page_address(page), &xdp->rxq->mem,
-				     false, NULL);
+		if (bpf_xdp_shrink_data(xdp, frag, shrink)) {
 			n_frags_free++;
 		} else {
 			skb_frag_size_sub(frag, shrink);
diff --git a/net/core/gso_test.c b/net/core/gso_test.c
index 4c2e77bd12f4..358c44680d91 100644
--- a/net/core/gso_test.c
+++ b/net/core/gso_test.c
@@ -225,7 +225,7 @@ static void gso_test_func(struct kunit *test)
 
 	segs = skb_segment(skb, features);
 	if (IS_ERR(segs)) {
-		KUNIT_FAIL(test, "segs error %lld", PTR_ERR(segs));
+		KUNIT_FAIL(test, "segs error %pe", segs);
 		goto free_gso_skb;
 	} else if (!segs) {
 		KUNIT_FAIL(test, "no segments");
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index ffe5244e5597..278294aca66a 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -94,11 +94,12 @@ netdev_nl_page_pool_get_dump(struct sk_buff *skb, struct netlink_callback *cb,
 			state->pp_id = pool->user.id;
 			err = fill(skb, pool, info);
 			if (err)
-				break;
+				goto out;
 		}
 
 		state->pp_id = 0;
 	}
+out:
 	mutex_unlock(&page_pools_lock);
 	rtnl_unlock();
 
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index f35c2e998406..63de5c635842 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -33,9 +33,6 @@
 
 void reqsk_queue_alloc(struct request_sock_queue *queue)
 {
-	spin_lock_init(&queue->rskq_lock);
-
-	spin_lock_init(&queue->fastopenq.lock);
 	queue->fastopenq.rskq_rst_head = NULL;
 	queue->fastopenq.rskq_rst_tail = NULL;
 	queue->fastopenq.qlen = 0;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 5f6ed6da3cfc..bd50e9fe3234 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1020,14 +1020,17 @@ static size_t rtnl_xdp_size(void)
 static size_t rtnl_prop_list_size(const struct net_device *dev)
 {
 	struct netdev_name_node *name_node;
-	size_t size;
+	unsigned int cnt = 0;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(name_node, &dev->name_node->list, list)
+		cnt++;
+	rcu_read_unlock();
 
-	if (list_empty(&dev->name_node->list))
+	if (!cnt)
 		return 0;
-	size = nla_total_size(0);
-	list_for_each_entry(name_node, &dev->name_node->list, list)
-		size += nla_total_size(ALTIFNAMSIZ);
-	return size;
+
+	return nla_total_size(0) + cnt * nla_total_size(ALTIFNAMSIZ);
 }
 
 static size_t rtnl_proto_down_size(const struct net_device *dev)
@@ -1054,7 +1057,7 @@ static size_t rtnl_dpll_pin_size(const struct net_device *dev)
 {
 	size_t size = nla_total_size(0); /* nest IFLA_DPLL_PIN */
 
-	size += dpll_msg_pin_handle_size(netdev_dpll_pin(dev));
+	size += dpll_netdev_pin_handle_size(dev);
 
 	return size;
 }
@@ -1789,7 +1792,7 @@ static int rtnl_fill_dpll_pin(struct sk_buff *skb,
 	if (!dpll_pin_nest)
 		return -EMSGSIZE;
 
-	ret = dpll_msg_add_pin_handle(skb, netdev_dpll_pin(dev));
+	ret = dpll_netdev_add_pin_handle(skb, dev);
 	if (ret < 0)
 		goto nest_cancel;
 
@@ -2899,13 +2902,6 @@ static int do_setlink(const struct sk_buff *skb,
 		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
 	}
 
-	if (tb[IFLA_MASTER]) {
-		err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack);
-		if (err)
-			goto errout;
-		status |= DO_SETLINK_MODIFIED;
-	}
-
 	if (ifm->ifi_flags || ifm->ifi_change) {
 		err = dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm),
 				       extack);
@@ -2913,6 +2909,13 @@ static int do_setlink(const struct sk_buff *skb,
 			goto errout;
 	}
 
+	if (tb[IFLA_MASTER]) {
+		err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack);
+		if (err)
+			goto errout;
+		status |= DO_SETLINK_MODIFIED;
+	}
+
 	if (tb[IFLA_CARRIER]) {
 		err = dev_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER]));
 		if (err)
@@ -5166,10 +5169,9 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net *net = sock_net(skb->sk);
 	struct ifinfomsg *ifm;
 	struct net_device *dev;
-	struct nlattr *br_spec, *attr = NULL;
+	struct nlattr *br_spec, *attr, *br_flags_attr = NULL;
 	int rem, err = -EOPNOTSUPP;
 	u16 flags = 0;
-	bool have_flags = false;
 
 	if (nlmsg_len(nlh) < sizeof(*ifm))
 		return -EINVAL;
@@ -5187,11 +5189,11 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
 	if (br_spec) {
 		nla_for_each_nested(attr, br_spec, rem) {
-			if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !have_flags) {
+			if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !br_flags_attr) {
 				if (nla_len(attr) < sizeof(flags))
 					return -EINVAL;
 
-				have_flags = true;
+				br_flags_attr = attr;
 				flags = nla_get_u16(attr);
 			}
 
@@ -5235,8 +5237,8 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		}
 	}
 
-	if (have_flags)
-		memcpy(nla_data(attr), &flags, sizeof(flags));
+	if (br_flags_attr)
+		memcpy(nla_data(br_flags_attr), &flags, sizeof(flags));
 out:
 	return err;
 }
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 93ecfceac1bc..4d75ef9d24bf 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -1226,8 +1226,11 @@ static void sk_psock_verdict_data_ready(struct sock *sk)
 
 		rcu_read_lock();
 		psock = sk_psock(sk);
-		if (psock)
-			psock->saved_data_ready(sk);
+		if (psock) {
+			read_lock_bh(&sk->sk_callback_lock);
+			sk_psock_data_ready(sk, psock);
+			read_unlock_bh(&sk->sk_callback_lock);
+		}
 		rcu_read_unlock();
 	}
 }
diff --git a/net/core/sock.c b/net/core/sock.c
index 158dbdebce6a..5e78798456fd 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -107,6 +107,7 @@
 #include <linux/interrupt.h>
 #include <linux/poll.h>
 #include <linux/tcp.h>
+#include <linux/udp.h>
 #include <linux/init.h>
 #include <linux/highmem.h>
 #include <linux/user_namespace.h>
@@ -1187,6 +1188,17 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 		 */
 		WRITE_ONCE(sk->sk_txrehash, (u8)val);
 		return 0;
+	case SO_PEEK_OFF:
+		{
+		int (*set_peek_off)(struct sock *sk, int val);
+
+		set_peek_off = READ_ONCE(sock->ops)->set_peek_off;
+		if (set_peek_off)
+			ret = set_peek_off(sk, val);
+		else
+			ret = -EOPNOTSUPP;
+		return ret;
+		}
 	}
 
 	sockopt_lock_sock(sk);
@@ -1429,18 +1441,6 @@ set_sndbuf:
 		sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool);
 		break;
 
-	case SO_PEEK_OFF:
-		{
-		int (*set_peek_off)(struct sock *sk, int val);
-
-		set_peek_off = READ_ONCE(sock->ops)->set_peek_off;
-		if (set_peek_off)
-			ret = set_peek_off(sk, val);
-		else
-			ret = -EOPNOTSUPP;
-		break;
-		}
-
 	case SO_NOFCS:
 		sock_valbool_flag(sk, SOCK_NOFCS, valbool);
 		break;
@@ -4144,8 +4144,14 @@ bool sk_busy_loop_end(void *p, unsigned long start_time)
 {
 	struct sock *sk = p;
 
-	return !skb_queue_empty_lockless(&sk->sk_receive_queue) ||
-	       sk_busy_loop_timeout(sk, start_time);
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
+		return true;
+
+	if (sk_is_udp(sk) &&
+	    !skb_queue_empty_lockless(&udp_sk(sk)->reader_queue))
+		return true;
+
+	return sk_busy_loop_timeout(sk, start_time);
 }
 EXPORT_SYMBOL(sk_busy_loop_end);
 #endif /* CONFIG_NET_RX_BUSY_POLL */
diff --git a/net/devlink/core.c b/net/devlink/core.c
index 4275a2bc6d8e..7f0b093208d7 100644
--- a/net/devlink/core.c
+++ b/net/devlink/core.c
@@ -46,7 +46,7 @@ struct devlink_rel {
 		u32 obj_index;
 		devlink_rel_notify_cb_t *notify_cb;
 		devlink_rel_cleanup_cb_t *cleanup_cb;
-		struct work_struct notify_work;
+		struct delayed_work notify_work;
 	} nested_in;
 };
 
@@ -70,7 +70,7 @@ static void __devlink_rel_put(struct devlink_rel *rel)
 static void devlink_rel_nested_in_notify_work(struct work_struct *work)
 {
 	struct devlink_rel *rel = container_of(work, struct devlink_rel,
-					       nested_in.notify_work);
+					       nested_in.notify_work.work);
 	struct devlink *devlink;
 
 	devlink = devlinks_xa_get(rel->nested_in.devlink_index);
@@ -96,13 +96,13 @@ rel_put:
 	return;
 
 reschedule_work:
-	schedule_work(&rel->nested_in.notify_work);
+	schedule_delayed_work(&rel->nested_in.notify_work, 1);
 }
 
 static void devlink_rel_nested_in_notify_work_schedule(struct devlink_rel *rel)
 {
 	__devlink_rel_get(rel);
-	schedule_work(&rel->nested_in.notify_work);
+	schedule_delayed_work(&rel->nested_in.notify_work, 0);
 }
 
 static struct devlink_rel *devlink_rel_alloc(void)
@@ -123,8 +123,8 @@ static struct devlink_rel *devlink_rel_alloc(void)
 	}
 
 	refcount_set(&rel->refcount, 1);
-	INIT_WORK(&rel->nested_in.notify_work,
-		  &devlink_rel_nested_in_notify_work);
+	INIT_DELAYED_WORK(&rel->nested_in.notify_work,
+			  &devlink_rel_nested_in_notify_work);
 	return rel;
 }
 
@@ -529,14 +529,20 @@ static int __init devlink_init(void)
 {
 	int err;
 
-	err = genl_register_family(&devlink_nl_family);
-	if (err)
-		goto out;
 	err = register_pernet_subsys(&devlink_pernet_ops);
 	if (err)
 		goto out;
+	err = genl_register_family(&devlink_nl_family);
+	if (err)
+		goto out_unreg_pernet_subsys;
 	err = register_netdevice_notifier(&devlink_port_netdevice_nb);
+	if (!err)
+		return 0;
+
+	genl_unregister_family(&devlink_nl_family);
 
+out_unreg_pernet_subsys:
+	unregister_pernet_subsys(&devlink_pernet_ops);
 out:
 	WARN_ON(err);
 	return err;
diff --git a/net/devlink/port.c b/net/devlink/port.c
index 62e54e152ecf..4b2d46ccfe48 100644
--- a/net/devlink/port.c
+++ b/net/devlink/port.c
@@ -583,7 +583,7 @@ devlink_nl_port_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
 
 	xa_for_each_start(&devlink->ports, port_index, devlink_port, state->idx) {
 		err = devlink_nl_port_fill(msg, devlink_port,
-					   DEVLINK_CMD_NEW,
+					   DEVLINK_CMD_PORT_NEW,
 					   NETLINK_CB(cb->skb).portid,
 					   cb->nlh->nlmsg_seq, flags,
 					   cb->extack);
@@ -674,7 +674,7 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port,
 		return -EOPNOTSUPP;
 	}
 	if (tb[DEVLINK_PORT_FN_ATTR_STATE] && !ops->port_fn_state_set) {
-		NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR],
+		NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FN_ATTR_STATE],
 				    "Function does not support state setting");
 		return -EOPNOTSUPP;
 	}
diff --git a/net/dsa/user.c b/net/dsa/user.c
index b738a466e2dc..b15e71cc342c 100644
--- a/net/dsa/user.c
+++ b/net/dsa/user.c
@@ -2806,13 +2806,14 @@ EXPORT_SYMBOL_GPL(dsa_user_dev_check);
 static int dsa_user_changeupper(struct net_device *dev,
 				struct netdev_notifier_changeupper_info *info)
 {
-	struct dsa_port *dp = dsa_user_to_port(dev);
 	struct netlink_ext_ack *extack;
 	int err = NOTIFY_DONE;
+	struct dsa_port *dp;
 
 	if (!dsa_user_dev_check(dev))
 		return err;
 
+	dp = dsa_user_to_port(dev);
 	extack = netdev_notifier_info_to_extack(&info->info);
 
 	if (netif_is_bridge_master(info->upper_dev)) {
@@ -2865,11 +2866,13 @@ static int dsa_user_changeupper(struct net_device *dev,
 static int dsa_user_prechangeupper(struct net_device *dev,
 				   struct netdev_notifier_changeupper_info *info)
 {
-	struct dsa_port *dp = dsa_user_to_port(dev);
+	struct dsa_port *dp;
 
 	if (!dsa_user_dev_check(dev))
 		return NOTIFY_DONE;
 
+	dp = dsa_user_to_port(dev);
+
 	if (netif_is_bridge_master(info->upper_dev) && !info->linking)
 		dsa_port_pre_bridge_leave(dp, info->upper_dev);
 	else if (netif_is_lag_master(info->upper_dev) && !info->linking)
diff --git a/net/ethtool/features.c b/net/ethtool/features.c
index a79af8c25a07..b6cb101d7f19 100644
--- a/net/ethtool/features.c
+++ b/net/ethtool/features.c
@@ -234,17 +234,20 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 	dev = req_info.dev;
 
 	rtnl_lock();
+	ret = ethnl_ops_begin(dev);
+	if (ret < 0)
+		goto out_rtnl;
 	ethnl_features_to_bitmap(old_active, dev->features);
 	ethnl_features_to_bitmap(old_wanted, dev->wanted_features);
 	ret = ethnl_parse_bitset(req_wanted, req_mask, NETDEV_FEATURE_COUNT,
 				 tb[ETHTOOL_A_FEATURES_WANTED],
 				 netdev_features_strings, info->extack);
 	if (ret < 0)
-		goto out_rtnl;
+		goto out_ops;
 	if (ethnl_bitmap_to_features(req_mask) & ~NETIF_F_ETHTOOL_BITS) {
 		GENL_SET_ERR_MSG(info, "attempt to change non-ethtool features");
 		ret = -EINVAL;
-		goto out_rtnl;
+		goto out_ops;
 	}
 
 	/* set req_wanted bits not in req_mask from old_wanted */
@@ -281,6 +284,8 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 	if (mod)
 		netdev_features_change(dev);
 
+out_ops:
+	ethnl_ops_complete(dev);
 out_rtnl:
 	rtnl_unlock();
 	ethnl_parse_header_dev_put(&req_info);
diff --git a/net/handshake/handshake-test.c b/net/handshake/handshake-test.c
index 16ed7bfd29e4..34fd1d9b2db8 100644
--- a/net/handshake/handshake-test.c
+++ b/net/handshake/handshake-test.c
@@ -471,7 +471,10 @@ static void handshake_req_destroy_test1(struct kunit *test)
 	handshake_req_cancel(sock->sk);
 
 	/* Act */
-	fput(filp);
+	/* Ensure the close/release/put process has run to
+	 * completion before checking the result.
+	 */
+	__fput_sync(filp);
 
 	/* Assert */
 	KUNIT_EXPECT_PTR_EQ(test, handshake_req_destroy_test, req);
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 7ceb9ac6e730..9d71b66183da 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -308,7 +308,7 @@ static void send_hsr_supervision_frame(struct hsr_port *master,
 
 	skb = hsr_init_skb(master);
 	if (!skb) {
-		WARN_ONCE(1, "HSR: Could not send supervision frame\n");
+		netdev_warn_once(master->dev, "HSR: Could not send supervision frame\n");
 		return;
 	}
 
@@ -355,7 +355,7 @@ static void send_prp_supervision_frame(struct hsr_port *master,
 
 	skb = hsr_init_skb(master);
 	if (!skb) {
-		WARN_ONCE(1, "PRP: Could not send supervision frame\n");
+		netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n");
 		return;
 	}
 
diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c
index 80cdc6f6b34c..5d68cb181695 100644
--- a/net/hsr/hsr_forward.c
+++ b/net/hsr/hsr_forward.c
@@ -83,7 +83,7 @@ static bool is_supervision_frame(struct hsr_priv *hsr, struct sk_buff *skb)
 		return false;
 
 	/* Get next tlv */
-	total_length += sizeof(struct hsr_sup_tlv) + hsr_sup_tag->tlv.HSR_TLV_length;
+	total_length += hsr_sup_tag->tlv.HSR_TLV_length;
 	if (!pskb_may_pull(skb, total_length))
 		return false;
 	skb_pull(skb, total_length);
@@ -435,7 +435,7 @@ static void hsr_forward_do(struct hsr_frame_info *frame)
 			continue;
 
 		/* Don't send frame over port where it has been sent before.
-		 * Also fro SAN, this shouldn't be done.
+		 * Also for SAN, this shouldn't be done.
 		 */
 		if (!frame->is_from_san &&
 		    hsr_register_frame_out(port, frame->node_src,
diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c
index b099c3150150..cb83c8feb746 100644
--- a/net/hsr/hsr_main.c
+++ b/net/hsr/hsr_main.c
@@ -167,4 +167,5 @@ static void __exit hsr_exit(void)
 
 module_init(hsr_init);
 module_exit(hsr_exit);
+MODULE_DESCRIPTION("High-availability Seamless Redundancy (HSR) driver");
 MODULE_LICENSE("GPL");
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 835f4f9d98d2..a5a820ee2026 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -330,6 +330,9 @@ lookup_protocol:
 	if (INET_PROTOSW_REUSE & answer_flags)
 		sk->sk_reuse = SK_CAN_REUSE;
 
+	if (INET_PROTOSW_ICSK & answer_flags)
+		inet_init_csk_locks(sk);
+
 	inet = inet_sk(sk);
 	inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags);
 
@@ -1625,10 +1628,12 @@ EXPORT_SYMBOL(inet_current_timestamp);
 
 int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 {
-	if (sk->sk_family == AF_INET)
+	unsigned int family = READ_ONCE(sk->sk_family);
+
+	if (family == AF_INET)
 		return ip_recv_error(sk, msg, len, addr_len);
 #if IS_ENABLED(CONFIG_IPV6)
-	if (sk->sk_family == AF_INET6)
+	if (family == AF_INET6)
 		return pingv6_ops.ipv6_recv_error(sk, msg, len, addr_len);
 #endif
 	return -EINVAL;
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index a2e6e1fdf82b..64aec3dff8ec 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -597,5 +597,6 @@ static void __exit ah4_fini(void)
 
 module_init(ah4_init);
 module_exit(ah4_fini);
+MODULE_DESCRIPTION("IPv4 AH transformation library");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_AH);
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 9456f5bb35e5..0d0d725b46ad 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1125,7 +1125,8 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev)
 	if (neigh) {
 		if (!(READ_ONCE(neigh->nud_state) & NUD_NOARP)) {
 			read_lock_bh(&neigh->lock);
-			memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len);
+			memcpy(r->arp_ha.sa_data, neigh->ha,
+			       min(dev->addr_len, sizeof(r->arp_ha.sa_data_min)));
 			r->arp_flags = arp_state_to_flags(neigh);
 			read_unlock_bh(&neigh->lock);
 			r->arp_ha.sa_family = dev->type;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index ca0ff15dc8fa..bc74f131fe4d 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1825,6 +1825,21 @@ done:
 	return err;
 }
 
+/* Combine dev_addr_genid and dev_base_seq to detect changes.
+ */
+static u32 inet_base_seq(const struct net *net)
+{
+	u32 res = atomic_read(&net->ipv4.dev_addr_genid) +
+		  net->dev_base_seq;
+
+	/* Must not return 0 (see nl_dump_check_consistent()).
+	 * Chose a value far away from 0.
+	 */
+	if (!res)
+		res = 0x80000000;
+	return res;
+}
+
 static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	const struct nlmsghdr *nlh = cb->nlh;
@@ -1876,8 +1891,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
 		idx = 0;
 		head = &tgt_net->dev_index_head[h];
 		rcu_read_lock();
-		cb->seq = atomic_read(&tgt_net->ipv4.dev_addr_genid) ^
-			  tgt_net->dev_base_seq;
+		cb->seq = inet_base_seq(tgt_net);
 		hlist_for_each_entry_rcu(dev, head, index_hlist) {
 			if (idx < s_idx)
 				goto cont;
@@ -2278,8 +2292,7 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb,
 		idx = 0;
 		head = &net->dev_index_head[h];
 		rcu_read_lock();
-		cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^
-			  net->dev_base_seq;
+		cb->seq = inet_base_seq(net);
 		hlist_for_each_entry_rcu(dev, head, index_hlist) {
 			if (idx < s_idx)
 				goto cont;
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 4ccfc104f13a..4dd9e5040672 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -1247,5 +1247,6 @@ static void __exit esp4_fini(void)
 
 module_init(esp4_init);
 module_exit(esp4_fini);
+MODULE_DESCRIPTION("IPv4 ESP transformation library");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_ESP);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 8e2eb1793685..459af1f89739 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -727,6 +727,10 @@ out:
 	}
 	if (req)
 		reqsk_put(req);
+
+	if (newsk)
+		inet_init_csk_locks(newsk);
+
 	return newsk;
 out_err:
 	newsk = NULL;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 93e9193df544..308ff34002ea 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -1130,10 +1130,33 @@ ok:
 	return 0;
 
 error:
+	if (sk_hashed(sk)) {
+		spinlock_t *lock = inet_ehash_lockp(hinfo, sk->sk_hash);
+
+		sock_prot_inuse_add(net, sk->sk_prot, -1);
+
+		spin_lock(lock);
+		sk_nulls_del_node_init_rcu(sk);
+		spin_unlock(lock);
+
+		sk->sk_hash = 0;
+		inet_sk(sk)->inet_sport = 0;
+		inet_sk(sk)->inet_num = 0;
+
+		if (tw)
+			inet_twsk_bind_unhash(tw, hinfo);
+	}
+
 	spin_unlock(&head2->lock);
 	if (tb_created)
 		inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb);
-	spin_unlock_bh(&head->lock);
+	spin_unlock(&head->lock);
+
+	if (tw)
+		inet_twsk_deschedule_put(tw);
+
+	local_bh_enable();
+
 	return -ENOMEM;
 }
 
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 5169c3c72cff..6b9cf5a24c19 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1793,6 +1793,7 @@ static void __exit ipgre_fini(void)
 
 module_init(ipgre_init);
 module_exit(ipgre_fini);
+MODULE_DESCRIPTION("IPv4 GRE tunnels over IP library");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_RTNL_LINK("gre");
 MODULE_ALIAS_RTNL_LINK("gretap");
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b06f678b03a1..67d846622365 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -972,8 +972,8 @@ static int __ip_append_data(struct sock *sk,
 	unsigned int maxfraglen, fragheaderlen, maxnonfragsize;
 	int csummode = CHECKSUM_NONE;
 	struct rtable *rt = (struct rtable *)cork->dst;
+	bool paged, hold_tskey, extra_uref = false;
 	unsigned int wmem_alloc_delta = 0;
-	bool paged, extra_uref = false;
 	u32 tskey = 0;
 
 	skb = skb_peek_tail(queue);
@@ -982,10 +982,6 @@ static int __ip_append_data(struct sock *sk,
 	mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize;
 	paged = !!cork->gso_size;
 
-	if (cork->tx_flags & SKBTX_ANY_TSTAMP &&
-	    READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID)
-		tskey = atomic_inc_return(&sk->sk_tskey) - 1;
-
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
 
 	fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
@@ -1052,6 +1048,11 @@ static int __ip_append_data(struct sock *sk,
 
 	cork->length += length;
 
+	hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP &&
+		     READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID;
+	if (hold_tskey)
+		tskey = atomic_inc_return(&sk->sk_tskey) - 1;
+
 	/* So, what's going on in the loop below?
 	 *
 	 * We use calculated fragment length to generate chained skb,
@@ -1274,6 +1275,8 @@ error:
 	cork->length -= length;
 	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
 	refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
+	if (hold_tskey)
+		atomic_dec(&sk->sk_tskey);
 	return err;
 }
 
@@ -1287,6 +1290,12 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 	if (unlikely(!rt))
 		return -EFAULT;
 
+	cork->fragsize = ip_sk_use_pmtu(sk) ?
+			 dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu);
+
+	if (!inetdev_valid_mtu(cork->fragsize))
+		return -ENETUNREACH;
+
 	/*
 	 * setup for corking.
 	 */
@@ -1303,12 +1312,6 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 		cork->addr = ipc->addr;
 	}
 
-	cork->fragsize = ip_sk_use_pmtu(sk) ?
-			 dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu);
-
-	if (!inetdev_valid_mtu(cork->fragsize))
-		return -ENETUNREACH;
-
 	cork->gso_size = ipc->gso_size;
 
 	cork->dst = &rt->dst;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 7aa9dc0e6760..21d2ffa919e9 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1363,12 +1363,13 @@ e_inval:
  * ipv4_pktinfo_prepare - transfer some info from rtable to skb
  * @sk: socket
  * @skb: buffer
+ * @drop_dst: if true, drops skb dst
  *
  * To support IP_CMSG_PKTINFO option, we store rt_iif and specific
  * destination in skb->cb[] before dst drop.
  * This way, receiver doesn't make cache line misses to read rtable.
  */
-void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
+void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb, bool drop_dst)
 {
 	struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb);
 	bool prepare = inet_test_bit(PKTINFO, sk) ||
@@ -1397,7 +1398,8 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
 		pktinfo->ipi_ifindex = 0;
 		pktinfo->ipi_spec_dst.s_addr = 0;
 	}
-	skb_dst_drop(skb);
+	if (drop_dst)
+		skb_dst_drop(skb);
 }
 
 int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index beeae624c412..1b6981de3f29 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -554,6 +554,20 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 	return 0;
 }
 
+static void ip_tunnel_adj_headroom(struct net_device *dev, unsigned int headroom)
+{
+	/* we must cap headroom to some upperlimit, else pskb_expand_head
+	 * will overflow header offsets in skb_headers_offset_update().
+	 */
+	static const unsigned int max_allowed = 512;
+
+	if (headroom > max_allowed)
+		headroom = max_allowed;
+
+	if (headroom > READ_ONCE(dev->needed_headroom))
+		WRITE_ONCE(dev->needed_headroom, headroom);
+}
+
 void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		       u8 proto, int tunnel_hlen)
 {
@@ -632,13 +646,13 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len;
-	if (headroom > READ_ONCE(dev->needed_headroom))
-		WRITE_ONCE(dev->needed_headroom, headroom);
-
-	if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) {
+	if (skb_cow_head(skb, headroom)) {
 		ip_rt_put(rt);
 		goto tx_dropped;
 	}
+
+	ip_tunnel_adj_headroom(dev, headroom);
+
 	iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, tos, ttl,
 		      df, !net_eq(tunnel->net, dev_net(dev)));
 	return;
@@ -818,16 +832,16 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
 			+ rt->dst.header_len + ip_encap_hlen(&tunnel->encap);
-	if (max_headroom > READ_ONCE(dev->needed_headroom))
-		WRITE_ONCE(dev->needed_headroom, max_headroom);
 
-	if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) {
+	if (skb_cow_head(skb, max_headroom)) {
 		ip_rt_put(rt);
 		DEV_STATS_INC(dev, tx_dropped);
 		kfree_skb(skb);
 		return;
 	}
 
+	ip_tunnel_adj_headroom(dev, max_headroom);
+
 	iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl,
 		      df, !net_eq(tunnel->net, dev_net(dev)));
 	return;
@@ -1298,4 +1312,5 @@ void ip_tunnel_setup(struct net_device *dev, unsigned int net_id)
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_setup);
 
+MODULE_DESCRIPTION("IPv4 tunnel implementation library");
 MODULE_LICENSE("GPL");
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 586b1b3e35b8..80ccd6661aa3 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -332,7 +332,7 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu)
 	};
 	skb_reset_network_header(skb);
 
-	csum = csum_partial(icmp6h, len, 0);
+	csum = skb_checksum(skb, skb_transport_offset(skb), len, 0);
 	icmp6h->icmp6_cksum = csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr, len,
 					      IPPROTO_ICMPV6, csum);
 
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 9ab9b3ebe0cd..d1d6bb28ed6e 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -721,6 +721,7 @@ static void __exit vti_fini(void)
 
 module_init(vti_init);
 module_exit(vti_fini);
+MODULE_DESCRIPTION("Virtual (secure) IP tunneling library");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_RTNL_LINK("vti");
 MODULE_ALIAS_NETDEV("ip_vti0");
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 27b8f83c6ea2..03afa3871efc 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -658,6 +658,7 @@ static void __exit ipip_fini(void)
 
 module_init(ipip_init);
 module_exit(ipip_fini);
+MODULE_DESCRIPTION("IP/IP protocol decoder library");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_RTNL_LINK("ipip");
 MODULE_ALIAS_NETDEV("tunl0");
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 9d6f59531b3a..362229836510 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1073,7 +1073,7 @@ static int ipmr_cache_report(const struct mr_table *mrt,
 		msg = (struct igmpmsg *)skb_network_header(skb);
 		msg->im_vif = vifi;
 		msg->im_vif_hi = vifi >> 8;
-		ipv4_pktinfo_prepare(mroute_sk, pkt);
+		ipv4_pktinfo_prepare(mroute_sk, pkt, false);
 		memcpy(skb->cb, pkt->cb, sizeof(skb->cb));
 		/* Add our header */
 		igmp = skb_put(skb, sizeof(struct igmphdr));
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index f01b038fc1cd..04504b2b51df 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -239,7 +239,6 @@ static int nf_reject_fill_skb_dst(struct sk_buff *skb_in)
 void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 		   int hook)
 {
-	struct net_device *br_indev __maybe_unused;
 	struct sk_buff *nskb;
 	struct iphdr *niph;
 	const struct tcphdr *oth;
@@ -289,9 +288,13 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	 * build the eth header using the original destination's MAC as the
 	 * source, and send the RST packet directly.
 	 */
-	br_indev = nf_bridge_get_physindev(oldskb);
-	if (br_indev) {
+	if (nf_bridge_info_exists(oldskb)) {
 		struct ethhdr *oeth = eth_hdr(oldskb);
+		struct net_device *br_indev;
+
+		br_indev = nf_bridge_get_physindev(oldskb, net);
+		if (!br_indev)
+			goto free_nskb;
 
 		nskb->dev = br_indev;
 		niph->tot_len = htons(nskb->len);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 27da9d7294c0..aea89326c697 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -292,7 +292,7 @@ static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 	/* Charge it to the socket. */
 
-	ipv4_pktinfo_prepare(sk, skb);
+	ipv4_pktinfo_prepare(sk, skb, true);
 	if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) {
 		kfree_skb_reason(skb, reason);
 		return NET_RX_DROP;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 1baa484d2190..c82dc42f57c6 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -722,6 +722,7 @@ void tcp_push(struct sock *sk, int flags, int mss_now,
 		if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) {
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING);
 			set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags);
+			smp_mb__after_atomic();
 		}
 		/* It is possible TX completion already happened
 		 * before we set TSQ_THROTTLED.
@@ -1785,7 +1786,17 @@ static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb,
 
 static bool can_map_frag(const skb_frag_t *frag)
 {
-	return skb_frag_size(frag) == PAGE_SIZE && !skb_frag_off(frag);
+	struct page *page;
+
+	if (skb_frag_size(frag) != PAGE_SIZE || skb_frag_off(frag))
+		return false;
+
+	page = skb_frag_page(frag);
+
+	if (PageCompound(page) || page->mapping)
+		return false;
+
+	return true;
 }
 
 static int find_next_mappable_frag(const skb_frag_t *frag,
@@ -4604,7 +4615,8 @@ static void __init tcp_struct_check(void)
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, prr_out);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, lost_out);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, sacked_out);
-	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 31);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, scaling_ratio);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 32);
 
 	/* RX read-mostly hotpath cache lines */
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, copied_seq);
diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c
index 5048c47c79b2..4c1f836aae38 100644
--- a/net/ipv4/tunnel4.c
+++ b/net/ipv4/tunnel4.c
@@ -294,4 +294,5 @@ static void __exit tunnel4_fini(void)
 
 module_init(tunnel4_init);
 module_exit(tunnel4_fini);
+MODULE_DESCRIPTION("IPv4 XFRM tunnel library");
 MODULE_LICENSE("GPL");
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 89e5a806b82e..e474b201900f 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -805,7 +805,7 @@ void udp_flush_pending_frames(struct sock *sk)
 
 	if (up->pending) {
 		up->len = 0;
-		up->pending = 0;
+		WRITE_ONCE(up->pending, 0);
 		ip_flush_pending_frames(sk);
 	}
 }
@@ -993,7 +993,7 @@ int udp_push_pending_frames(struct sock *sk)
 
 out:
 	up->len = 0;
-	up->pending = 0;
+	WRITE_ONCE(up->pending, 0);
 	return err;
 }
 EXPORT_SYMBOL(udp_push_pending_frames);
@@ -1070,7 +1070,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
 
 	fl4 = &inet->cork.fl.u.ip4;
-	if (up->pending) {
+	if (READ_ONCE(up->pending)) {
 		/*
 		 * There are pending frames.
 		 * The socket lock must be held while it's corked.
@@ -1269,7 +1269,7 @@ back_from_confirm:
 	fl4->saddr = saddr;
 	fl4->fl4_dport = dport;
 	fl4->fl4_sport = inet->inet_sport;
-	up->pending = AF_INET;
+	WRITE_ONCE(up->pending, AF_INET);
 
 do_append_data:
 	up->len += ulen;
@@ -1281,7 +1281,7 @@ do_append_data:
 	else if (!corkreq)
 		err = udp_push_pending_frames(sk);
 	else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
-		up->pending = 0;
+		WRITE_ONCE(up->pending, 0);
 	release_sock(sk);
 
 out:
@@ -1319,7 +1319,7 @@ void udp_splice_eof(struct socket *sock)
 	struct sock *sk = sock->sk;
 	struct udp_sock *up = udp_sk(sk);
 
-	if (!up->pending || udp_test_bit(CORK, sk))
+	if (!READ_ONCE(up->pending) || udp_test_bit(CORK, sk))
 		return;
 
 	lock_sock(sk);
@@ -1589,12 +1589,7 @@ int udp_init_sock(struct sock *sk)
 
 void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len)
 {
-	if (unlikely(READ_ONCE(sk->sk_peek_off) >= 0)) {
-		bool slow = lock_sock_fast(sk);
-
-		sk_peek_offset_bwd(sk, len);
-		unlock_sock_fast(sk, slow);
-	}
+	sk_peek_offset_bwd(sk, len);
 
 	if (!skb_unref(skb))
 		return;
@@ -2169,7 +2164,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 
 	udp_csum_pull_header(skb);
 
-	ipv4_pktinfo_prepare(sk, skb);
+	ipv4_pktinfo_prepare(sk, skb, true);
 	return __udp_queue_rcv_skb(sk, skb);
 
 csum_error:
@@ -3137,16 +3132,18 @@ static struct sock *bpf_iter_udp_batch(struct seq_file *seq)
 	struct bpf_udp_iter_state *iter = seq->private;
 	struct udp_iter_state *state = &iter->state;
 	struct net *net = seq_file_net(seq);
+	int resume_bucket, resume_offset;
 	struct udp_table *udptable;
 	unsigned int batch_sks = 0;
 	bool resized = false;
 	struct sock *sk;
 
+	resume_bucket = state->bucket;
+	resume_offset = iter->offset;
+
 	/* The current batch is done, so advance the bucket. */
-	if (iter->st_bucket_done) {
+	if (iter->st_bucket_done)
 		state->bucket++;
-		iter->offset = 0;
-	}
 
 	udptable = udp_get_table_seq(seq, net);
 
@@ -3166,19 +3163,19 @@ again:
 	for (; state->bucket <= udptable->mask; state->bucket++) {
 		struct udp_hslot *hslot2 = &udptable->hash2[state->bucket];
 
-		if (hlist_empty(&hslot2->head)) {
-			iter->offset = 0;
+		if (hlist_empty(&hslot2->head))
 			continue;
-		}
 
+		iter->offset = 0;
 		spin_lock_bh(&hslot2->lock);
 		udp_portaddr_for_each_entry(sk, &hslot2->head) {
 			if (seq_sk_match(seq, sk)) {
 				/* Resume from the last iterated socket at the
 				 * offset in the bucket before iterator was stopped.
 				 */
-				if (iter->offset) {
-					--iter->offset;
+				if (state->bucket == resume_bucket &&
+				    iter->offset < resume_offset) {
+					++iter->offset;
 					continue;
 				}
 				if (iter->end_sk < iter->max_sk) {
@@ -3192,9 +3189,6 @@ again:
 
 		if (iter->end_sk)
 			break;
-
-		/* Reset the current bucket's offset before moving to the next bucket. */
-		iter->offset = 0;
 	}
 
 	/* All done: no batch made. */
@@ -3213,7 +3207,6 @@ again:
 		/* After allocating a larger batch, retry one more time to grab
 		 * the whole bucket.
 		 */
-		state->bucket--;
 		goto again;
 	}
 done:
diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
index a87defb2b167..860aff5f8599 100644
--- a/net/ipv4/udp_tunnel_core.c
+++ b/net/ipv4/udp_tunnel_core.c
@@ -253,4 +253,5 @@ struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb,
 }
 EXPORT_SYMBOL_GPL(udp_tunnel_dst_lookup);
 
+MODULE_DESCRIPTION("IPv4 Foo over UDP tunnel driver");
 MODULE_LICENSE("GPL");
diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c
index 8489fa106583..8cb266af1393 100644
--- a/net/ipv4/xfrm4_tunnel.c
+++ b/net/ipv4/xfrm4_tunnel.c
@@ -114,5 +114,6 @@ static void __exit ipip_fini(void)
 
 module_init(ipip_init);
 module_exit(ipip_fini);
+MODULE_DESCRIPTION("IPv4 XFRM tunnel driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_IPIP);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 733ace18806c..055230b669cf 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -708,6 +708,22 @@ errout:
 	return err;
 }
 
+/* Combine dev_addr_genid and dev_base_seq to detect changes.
+ */
+static u32 inet6_base_seq(const struct net *net)
+{
+	u32 res = atomic_read(&net->ipv6.dev_addr_genid) +
+		  net->dev_base_seq;
+
+	/* Must not return 0 (see nl_dump_check_consistent()).
+	 * Chose a value far away from 0.
+	 */
+	if (!res)
+		res = 0x80000000;
+	return res;
+}
+
+
 static int inet6_netconf_dump_devconf(struct sk_buff *skb,
 				      struct netlink_callback *cb)
 {
@@ -741,8 +757,7 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb,
 		idx = 0;
 		head = &net->dev_index_head[h];
 		rcu_read_lock();
-		cb->seq = atomic_read(&net->ipv6.dev_addr_genid) ^
-			  net->dev_base_seq;
+		cb->seq = inet6_base_seq(net);
 		hlist_for_each_entry_rcu(dev, head, index_hlist) {
 			if (idx < s_idx)
 				goto cont;
@@ -5362,7 +5377,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
 	}
 
 	rcu_read_lock();
-	cb->seq = atomic_read(&tgt_net->ipv6.dev_addr_genid) ^ tgt_net->dev_base_seq;
+	cb->seq = inet6_base_seq(tgt_net);
 	for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
 		idx = 0;
 		head = &tgt_net->dev_index_head[h];
@@ -5494,9 +5509,10 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	}
 
 	addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer);
-	if (!addr)
-		return -EINVAL;
-
+	if (!addr) {
+		err = -EINVAL;
+		goto errout;
+	}
 	ifm = nlmsg_data(nlh);
 	if (ifm->ifa_index)
 		dev = dev_get_by_index(tgt_net, ifm->ifa_index);
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 507a8353a6bd..c008d21925d7 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -220,19 +220,26 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
 EXPORT_SYMBOL_GPL(ipv6_stub);
 
 /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */
-const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT;
+const struct in6_addr in6addr_loopback __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_LOOPBACK_INIT;
 EXPORT_SYMBOL(in6addr_loopback);
-const struct in6_addr in6addr_any = IN6ADDR_ANY_INIT;
+const struct in6_addr in6addr_any __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_ANY_INIT;
 EXPORT_SYMBOL(in6addr_any);
-const struct in6_addr in6addr_linklocal_allnodes = IN6ADDR_LINKLOCAL_ALLNODES_INIT;
+const struct in6_addr in6addr_linklocal_allnodes __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_LINKLOCAL_ALLNODES_INIT;
 EXPORT_SYMBOL(in6addr_linklocal_allnodes);
-const struct in6_addr in6addr_linklocal_allrouters = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT;
+const struct in6_addr in6addr_linklocal_allrouters __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_LINKLOCAL_ALLROUTERS_INIT;
 EXPORT_SYMBOL(in6addr_linklocal_allrouters);
-const struct in6_addr in6addr_interfacelocal_allnodes = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT;
+const struct in6_addr in6addr_interfacelocal_allnodes __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_INTERFACELOCAL_ALLNODES_INIT;
 EXPORT_SYMBOL(in6addr_interfacelocal_allnodes);
-const struct in6_addr in6addr_interfacelocal_allrouters = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT;
+const struct in6_addr in6addr_interfacelocal_allrouters __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT;
 EXPORT_SYMBOL(in6addr_interfacelocal_allrouters);
-const struct in6_addr in6addr_sitelocal_allrouters = IN6ADDR_SITELOCAL_ALLROUTERS_INIT;
+const struct in6_addr in6addr_sitelocal_allrouters __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_SITELOCAL_ALLROUTERS_INIT;
 EXPORT_SYMBOL(in6addr_sitelocal_allrouters);
 
 static void snmp6_free_dev(struct inet6_dev *idev)
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 13a1833a4df5..959bfd9f6344 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -199,6 +199,9 @@ lookup_protocol:
 	if (INET_PROTOSW_REUSE & answer_flags)
 		sk->sk_reuse = SK_CAN_REUSE;
 
+	if (INET_PROTOSW_ICSK & answer_flags)
+		inet_init_csk_locks(sk);
+
 	inet = inet_sk(sk);
 	inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags);
 
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 2016e90e6e1d..eb474f0987ae 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -800,5 +800,6 @@ static void __exit ah6_fini(void)
 module_init(ah6_init);
 module_exit(ah6_fini);
 
+MODULE_DESCRIPTION("IPv6 AH transformation helpers");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_AH);
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 2cc1a45742d8..6e6efe026cdc 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -1301,5 +1301,6 @@ static void __exit esp6_fini(void)
 module_init(esp6_init);
 module_exit(esp6_fini);
 
+MODULE_DESCRIPTION("IPv6 ESP transformation helpers");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_ESP);
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 4952ae792450..02e9ffb63af1 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -177,6 +177,8 @@ static bool ip6_parse_tlv(bool hopbyhop,
 				case IPV6_TLV_IOAM:
 					if (!ipv6_hop_ioam(skb, off))
 						return false;
+
+					nh = skb_network_header(skb);
 					break;
 				case IPV6_TLV_JUMBO:
 					if (!ipv6_hop_jumbo(skb, off))
@@ -943,6 +945,14 @@ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff)
 		if (!skb_valid_dst(skb))
 			ip6_route_input(skb);
 
+		/* About to mangle packet header */
+		if (skb_ensure_writable(skb, optoff + 2 + hdr->opt_len))
+			goto drop;
+
+		/* Trace pointer may have changed */
+		trace = (struct ioam6_trace_hdr *)(skb_network_header(skb)
+						   + optoff + sizeof(*hdr));
+
 		ioam6_fill_trace_data(skb, ns, trace, true);
 		break;
 	default:
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a722a43dd668..31b86fe661aa 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1424,11 +1424,11 @@ static int __ip6_append_data(struct sock *sk,
 	bool zc = false;
 	u32 tskey = 0;
 	struct rt6_info *rt = (struct rt6_info *)cork->dst;
+	bool paged, hold_tskey, extra_uref = false;
 	struct ipv6_txoptions *opt = v6_cork->opt;
 	int csummode = CHECKSUM_NONE;
 	unsigned int maxnonfragsize, headersize;
 	unsigned int wmem_alloc_delta = 0;
-	bool paged, extra_uref = false;
 
 	skb = skb_peek_tail(queue);
 	if (!skb) {
@@ -1440,10 +1440,6 @@ static int __ip6_append_data(struct sock *sk,
 	mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize;
 	orig_mtu = mtu;
 
-	if (cork->tx_flags & SKBTX_ANY_TSTAMP &&
-	    READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID)
-		tskey = atomic_inc_return(&sk->sk_tskey) - 1;
-
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
 
 	fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
@@ -1538,6 +1534,11 @@ emsgsize:
 			flags &= ~MSG_SPLICE_PAGES;
 	}
 
+	hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP &&
+		     READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID;
+	if (hold_tskey)
+		tskey = atomic_inc_return(&sk->sk_tskey) - 1;
+
 	/*
 	 * Let's try using as much space as possible.
 	 * Use MTU if total length of the message fits into the MTU.
@@ -1794,6 +1795,8 @@ error:
 	cork->length -= length;
 	IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
 	refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
+	if (hold_tskey)
+		atomic_dec(&sk->sk_tskey);
 	return err;
 }
 
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 46c19bd48990..9bbabf750a21 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -796,8 +796,8 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb,
 						struct sk_buff *skb),
 			 bool log_ecn_err)
 {
-	const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
-	int err;
+	const struct ipv6hdr *ipv6h;
+	int nh, err;
 
 	if ((!(tpi->flags & TUNNEL_CSUM) &&
 	     (tunnel->parms.i_flags & TUNNEL_CSUM)) ||
@@ -829,7 +829,6 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb,
 			goto drop;
 		}
 
-		ipv6h = ipv6_hdr(skb);
 		skb->protocol = eth_type_trans(skb, tunnel->dev);
 		skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
 	} else {
@@ -837,7 +836,23 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb,
 		skb_reset_mac_header(skb);
 	}
 
+	/* Save offset of outer header relative to skb->head,
+	 * because we are going to reset the network header to the inner header
+	 * and might change skb->head.
+	 */
+	nh = skb_network_header(skb) - skb->head;
+
 	skb_reset_network_header(skb);
+
+	if (!pskb_inet_may_pull(skb)) {
+		DEV_STATS_INC(tunnel->dev, rx_length_errors);
+		DEV_STATS_INC(tunnel->dev, rx_errors);
+		goto drop;
+	}
+
+	/* Get the outer header. */
+	ipv6h = (struct ipv6hdr *)(skb->head + nh);
+
 	memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
 
 	__skb_tunnel_rx(skb, tunnel->dev, tunnel->net);
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index a7bf0327b380..c99053189ea8 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -182,4 +182,5 @@ struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb,
 }
 EXPORT_SYMBOL_GPL(udp_tunnel6_dst_lookup);
 
+MODULE_DESCRIPTION("IPv6 Foo over UDP tunnel driver");
 MODULE_LICENSE("GPL");
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index b75d3c9d41bb..bc6e0a0bad3c 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2722,8 +2722,12 @@ void ipv6_mc_down(struct inet6_dev *idev)
 	synchronize_net();
 	mld_query_stop_work(idev);
 	mld_report_stop_work(idev);
+
+	mutex_lock(&idev->mc_lock);
 	mld_ifc_stop_work(idev);
 	mld_gq_stop_work(idev);
+	mutex_unlock(&idev->mc_lock);
+
 	mld_dad_stop_work(idev);
 }
 
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index 83d2a8be263f..6a16a5bd0d91 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -405,6 +405,7 @@ static void __exit mip6_fini(void)
 module_init(mip6_init);
 module_exit(mip6_fini);
 
+MODULE_DESCRIPTION("IPv6 Mobility driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_DSTOPTS);
 MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_ROUTING);
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index d45bc54b7ea5..196dd4ecb5e2 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -278,7 +278,6 @@ static int nf_reject6_fill_skb_dst(struct sk_buff *skb_in)
 void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 		    int hook)
 {
-	struct net_device *br_indev __maybe_unused;
 	struct sk_buff *nskb;
 	struct tcphdr _otcph;
 	const struct tcphdr *otcph;
@@ -354,9 +353,15 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	 * build the eth header using the original destination's MAC as the
 	 * source, and send the RST packet directly.
 	 */
-	br_indev = nf_bridge_get_physindev(oldskb);
-	if (br_indev) {
+	if (nf_bridge_info_exists(oldskb)) {
 		struct ethhdr *oeth = eth_hdr(oldskb);
+		struct net_device *br_indev;
+
+		br_indev = nf_bridge_get_physindev(oldskb, net);
+		if (!br_indev) {
+			kfree_skb(nskb);
+			return;
+		}
 
 		nskb->dev = br_indev;
 		nskb->protocol = htons(ETH_P_IPV6);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ea1dec8448fc..ef815ba583a8 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -5332,19 +5332,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 	err_nh = NULL;
 	list_for_each_entry(nh, &rt6_nh_list, next) {
 		err = __ip6_ins_rt(nh->fib6_info, info, extack);
-		fib6_info_release(nh->fib6_info);
-
-		if (!err) {
-			/* save reference to last route successfully inserted */
-			rt_last = nh->fib6_info;
-
-			/* save reference to first route for notification */
-			if (!rt_notif)
-				rt_notif = nh->fib6_info;
-		}
 
-		/* nh->fib6_info is used or freed at this point, reset to NULL*/
-		nh->fib6_info = NULL;
 		if (err) {
 			if (replace && nhn)
 				NL_SET_ERR_MSG_MOD(extack,
@@ -5352,6 +5340,12 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 			err_nh = nh;
 			goto add_errout;
 		}
+		/* save reference to last route successfully inserted */
+		rt_last = nh->fib6_info;
+
+		/* save reference to first route for notification */
+		if (!rt_notif)
+			rt_notif = nh->fib6_info;
 
 		/* Because each route is added like a single route we remove
 		 * these flags after the first nexthop: if there is a collision,
@@ -5412,8 +5406,7 @@ add_errout:
 
 cleanup:
 	list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) {
-		if (nh->fib6_info)
-			fib6_info_release(nh->fib6_info);
+		fib6_info_release(nh->fib6_info);
 		list_del(&nh->next);
 		kfree(nh);
 	}
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index 29346a6eec9f..35508abd76f4 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -512,22 +512,24 @@ int __init seg6_init(void)
 {
 	int err;
 
-	err = genl_register_family(&seg6_genl_family);
+	err = register_pernet_subsys(&ip6_segments_ops);
 	if (err)
 		goto out;
 
-	err = register_pernet_subsys(&ip6_segments_ops);
+	err = genl_register_family(&seg6_genl_family);
 	if (err)
-		goto out_unregister_genl;
+		goto out_unregister_pernet;
 
 #ifdef CONFIG_IPV6_SEG6_LWTUNNEL
 	err = seg6_iptunnel_init();
 	if (err)
-		goto out_unregister_pernet;
+		goto out_unregister_genl;
 
 	err = seg6_local_init();
-	if (err)
-		goto out_unregister_pernet;
+	if (err) {
+		seg6_iptunnel_exit();
+		goto out_unregister_genl;
+	}
 #endif
 
 #ifdef CONFIG_IPV6_SEG6_HMAC
@@ -548,11 +550,11 @@ out_unregister_iptun:
 #endif
 #endif
 #ifdef CONFIG_IPV6_SEG6_LWTUNNEL
-out_unregister_pernet:
-	unregister_pernet_subsys(&ip6_segments_ops);
-#endif
 out_unregister_genl:
 	genl_unregister_family(&seg6_genl_family);
+#endif
+out_unregister_pernet:
+	unregister_pernet_subsys(&ip6_segments_ops);
 	goto out;
 }
 
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index cc24cefdb85c..5e9f625b76e3 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1956,6 +1956,7 @@ xfrm_tunnel_failed:
 
 module_init(sit_init);
 module_exit(sit_cleanup);
+MODULE_DESCRIPTION("IPv6-in-IPv4 tunnel SIT driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_RTNL_LINK("sit");
 MODULE_ALIAS_NETDEV("sit0");
diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c
index 00e8d8b1c9a7..dc4ea9b11794 100644
--- a/net/ipv6/tunnel6.c
+++ b/net/ipv6/tunnel6.c
@@ -302,4 +302,5 @@ static void __exit tunnel6_fini(void)
 
 module_init(tunnel6_init);
 module_exit(tunnel6_fini);
+MODULE_DESCRIPTION("IP-in-IPv6 tunnel driver");
 MODULE_LICENSE("GPL");
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 594e3f23c129..3f2249b4cd5f 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1135,7 +1135,7 @@ static void udp_v6_flush_pending_frames(struct sock *sk)
 		udp_flush_pending_frames(sk);
 	else if (up->pending) {
 		up->len = 0;
-		up->pending = 0;
+		WRITE_ONCE(up->pending, 0);
 		ip6_flush_pending_frames(sk);
 	}
 }
@@ -1313,7 +1313,7 @@ static int udp_v6_push_pending_frames(struct sock *sk)
 			      &inet_sk(sk)->cork.base);
 out:
 	up->len = 0;
-	up->pending = 0;
+	WRITE_ONCE(up->pending, 0);
 	return err;
 }
 
@@ -1370,7 +1370,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		default:
 			return -EINVAL;
 		}
-	} else if (!up->pending) {
+	} else if (!READ_ONCE(up->pending)) {
 		if (sk->sk_state != TCP_ESTABLISHED)
 			return -EDESTADDRREQ;
 		daddr = &sk->sk_v6_daddr;
@@ -1401,8 +1401,8 @@ do_udp_sendmsg:
 		return -EMSGSIZE;
 
 	getfrag  =  is_udplite ?  udplite_getfrag : ip_generic_getfrag;
-	if (up->pending) {
-		if (up->pending == AF_INET)
+	if (READ_ONCE(up->pending)) {
+		if (READ_ONCE(up->pending) == AF_INET)
 			return udp_sendmsg(sk, msg, len);
 		/*
 		 * There are pending frames.
@@ -1593,7 +1593,7 @@ back_from_confirm:
 		goto out;
 	}
 
-	up->pending = AF_INET6;
+	WRITE_ONCE(up->pending, AF_INET6);
 
 do_append_data:
 	if (ipc6.dontfrag < 0)
@@ -1607,7 +1607,7 @@ do_append_data:
 	else if (!corkreq)
 		err = udp_v6_push_pending_frames(sk);
 	else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
-		up->pending = 0;
+		WRITE_ONCE(up->pending, 0);
 
 	if (err > 0)
 		err = inet6_test_bit(RECVERR6, sk) ? net_xmit_errno(err) : 0;
@@ -1648,7 +1648,7 @@ static void udpv6_splice_eof(struct socket *sock)
 	struct sock *sk = sock->sk;
 	struct udp_sock *up = udp_sk(sk);
 
-	if (!up->pending || udp_test_bit(CORK, sk))
+	if (!READ_ONCE(up->pending) || udp_test_bit(CORK, sk))
 		return;
 
 	lock_sock(sk);
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index 1323f2f6928e..f6cb94f82cc3 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -401,5 +401,6 @@ static void __exit xfrm6_tunnel_fini(void)
 
 module_init(xfrm6_tunnel_init);
 module_exit(xfrm6_tunnel_fini);
+MODULE_DESCRIPTION("IPv6 XFRM tunnel driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_IPV6);
diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
index 6334f64f04d5..b0b3e9c5af44 100644
--- a/net/iucv/iucv.c
+++ b/net/iucv/iucv.c
@@ -156,7 +156,7 @@ static char iucv_error_pathid[16] = "INVALID PATHID";
 static LIST_HEAD(iucv_handler_list);
 
 /*
- * iucv_path_table: an array of iucv_path structures.
+ * iucv_path_table: array of pointers to iucv_path structures.
  */
 static struct iucv_path **iucv_path_table;
 static unsigned long iucv_max_pathid;
@@ -544,7 +544,7 @@ static int iucv_enable(void)
 
 	cpus_read_lock();
 	rc = -ENOMEM;
-	alloc_size = iucv_max_pathid * sizeof(struct iucv_path);
+	alloc_size = iucv_max_pathid * sizeof(*iucv_path_table);
 	iucv_path_table = kzalloc(alloc_size, GFP_KERNEL);
 	if (!iucv_path_table)
 		goto out;
diff --git a/net/key/af_key.c b/net/key/af_key.c
index d68d01804dc7..f79fb99271ed 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3924,5 +3924,6 @@ out_unregister_key_proto:
 
 module_init(ipsec_pfkey_init);
 module_exit(ipsec_pfkey_exit);
+MODULE_DESCRIPTION("PF_KEY socket helpers");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_NETPROTO(PF_KEY);
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index dd3153966173..7bf14cf9ffaa 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -627,7 +627,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 back_from_confirm:
 	lock_sock(sk);
-	ulen = len + skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0;
+	ulen = len + (skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0);
 	err = ip6_append_data(sk, ip_generic_getfrag, msg,
 			      ulen, transhdrlen, &ipc6,
 			      &fl6, (struct rt6_info *)dst,
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 9b06c380866b..fde1140d899e 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -226,6 +226,8 @@ static int llc_ui_release(struct socket *sock)
 	}
 	netdev_put(llc->dev, &llc->dev_tracker);
 	sock_put(sk);
+	sock_orphan(sk);
+	sock->sk = NULL;
 	llc_sk_free(sk);
 out:
 	return 0;
@@ -928,14 +930,15 @@ copy_uaddr:
  */
 static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
+	DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name);
 	struct sock *sk = sock->sk;
 	struct llc_sock *llc = llc_sk(sk);
-	DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name);
 	int flags = msg->msg_flags;
 	int noblock = flags & MSG_DONTWAIT;
+	int rc = -EINVAL, copied = 0, hdrlen, hh_len;
 	struct sk_buff *skb = NULL;
+	struct net_device *dev;
 	size_t size = 0;
-	int rc = -EINVAL, copied = 0, hdrlen;
 
 	dprintk("%s: sending from %02X to %02X\n", __func__,
 		llc->laddr.lsap, llc->daddr.lsap);
@@ -955,22 +958,29 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 		if (rc)
 			goto out;
 	}
-	hdrlen = llc->dev->hard_header_len + llc_ui_header_len(sk, addr);
+	dev = llc->dev;
+	hh_len = LL_RESERVED_SPACE(dev);
+	hdrlen = llc_ui_header_len(sk, addr);
 	size = hdrlen + len;
-	if (size > llc->dev->mtu)
-		size = llc->dev->mtu;
+	size = min_t(size_t, size, READ_ONCE(dev->mtu));
 	copied = size - hdrlen;
 	rc = -EINVAL;
 	if (copied < 0)
 		goto out;
 	release_sock(sk);
-	skb = sock_alloc_send_skb(sk, size, noblock, &rc);
+	skb = sock_alloc_send_skb(sk, hh_len + size, noblock, &rc);
 	lock_sock(sk);
 	if (!skb)
 		goto out;
-	skb->dev      = llc->dev;
+	if (sock_flag(sk, SOCK_ZAPPED) ||
+	    llc->dev != dev ||
+	    hdrlen != llc_ui_header_len(sk, addr) ||
+	    hh_len != LL_RESERVED_SPACE(dev) ||
+	    size > READ_ONCE(dev->mtu))
+		goto out;
+	skb->dev      = dev;
 	skb->protocol = llc_proto_type(addr->sllc_arphrd);
-	skb_reserve(skb, hdrlen);
+	skb_reserve(skb, hh_len + hdrlen);
 	rc = memcpy_from_msg(skb_put(skb, copied), msg, copied);
 	if (rc)
 		goto out;
diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c
index 6e387aadffce..4f16d9c88350 100644
--- a/net/llc/llc_core.c
+++ b/net/llc/llc_core.c
@@ -135,22 +135,15 @@ static struct packet_type llc_packet_type __read_mostly = {
 	.func = llc_rcv,
 };
 
-static struct packet_type llc_tr_packet_type __read_mostly = {
-	.type = cpu_to_be16(ETH_P_TR_802_2),
-	.func = llc_rcv,
-};
-
 static int __init llc_init(void)
 {
 	dev_add_pack(&llc_packet_type);
-	dev_add_pack(&llc_tr_packet_type);
 	return 0;
 }
 
 static void __exit llc_exit(void)
 {
 	dev_remove_pack(&llc_packet_type);
-	dev_remove_pack(&llc_tr_packet_type);
 }
 
 module_init(llc_init);
diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig
index cb0291decf2e..13438cc0a6b1 100644
--- a/net/mac80211/Kconfig
+++ b/net/mac80211/Kconfig
@@ -62,7 +62,6 @@ config MAC80211_KUNIT_TEST
 	depends on KUNIT
 	depends on MAC80211
 	default KUNIT_ALL_TESTS
-	depends on !KERNEL_6_2
 	help
 	  Enable this option to test mac80211 internals with kunit.
 
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 489dd97f5172..327682995c92 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -5,7 +5,7 @@
  * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2015  Intel Mobile Communications GmbH
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2022 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
  */
 
 #include <linux/ieee80211.h>
@@ -987,7 +987,8 @@ static int
 ieee80211_set_unsol_bcast_probe_resp(struct ieee80211_sub_if_data *sdata,
 				     struct cfg80211_unsol_bcast_probe_resp *params,
 				     struct ieee80211_link_data *link,
-				     struct ieee80211_bss_conf *link_conf)
+				     struct ieee80211_bss_conf *link_conf,
+				     u64 *changed)
 {
 	struct unsol_bcast_probe_resp_data *new, *old = NULL;
 
@@ -1011,7 +1012,8 @@ ieee80211_set_unsol_bcast_probe_resp(struct ieee80211_sub_if_data *sdata,
 		RCU_INIT_POINTER(link->u.ap.unsol_bcast_probe_resp, NULL);
 	}
 
-	return BSS_CHANGED_UNSOL_BCAST_PROBE_RESP;
+	*changed |= BSS_CHANGED_UNSOL_BCAST_PROBE_RESP;
+	return 0;
 }
 
 static int ieee80211_set_ftm_responder_params(
@@ -1450,10 +1452,9 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 
 	err = ieee80211_set_unsol_bcast_probe_resp(sdata,
 						   &params->unsol_bcast_probe_resp,
-						   link, link_conf);
+						   link, link_conf, &changed);
 	if (err < 0)
 		goto error;
-	changed |= err;
 
 	err = drv_start_ap(sdata->local, sdata, link_conf);
 	if (err) {
@@ -1525,10 +1526,9 @@ static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev,
 
 	err = ieee80211_set_unsol_bcast_probe_resp(sdata,
 						   &params->unsol_bcast_probe_resp,
-						   link, link_conf);
+						   link, link_conf, &changed);
 	if (err < 0)
 		return err;
-	changed |= err;
 
 	if (beacon->he_bss_color_valid &&
 	    beacon->he_bss_color.enabled != link_conf->he_bss_color.enabled) {
@@ -1869,6 +1869,8 @@ static int sta_link_apply_parameters(struct ieee80211_local *local,
 					      sband->band);
 	}
 
+	ieee80211_sta_set_rx_nss(link_sta);
+
 	return ret;
 }
 
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index dce5606ed66d..68596ef78b15 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -997,8 +997,8 @@ static void add_link_files(struct ieee80211_link_data *link,
 	}
 }
 
-void ieee80211_debugfs_add_netdev(struct ieee80211_sub_if_data *sdata,
-				  bool mld_vif)
+static void ieee80211_debugfs_add_netdev(struct ieee80211_sub_if_data *sdata,
+					 bool mld_vif)
 {
 	char buf[10+IFNAMSIZ];
 
diff --git a/net/mac80211/debugfs_netdev.h b/net/mac80211/debugfs_netdev.h
index b226b1aae88a..a02ec0a413f6 100644
--- a/net/mac80211/debugfs_netdev.h
+++ b/net/mac80211/debugfs_netdev.h
@@ -11,8 +11,6 @@
 #include "ieee80211_i.h"
 
 #ifdef CONFIG_MAC80211_DEBUGFS
-void ieee80211_debugfs_add_netdev(struct ieee80211_sub_if_data *sdata,
-				  bool mld_vif);
 void ieee80211_debugfs_remove_netdev(struct ieee80211_sub_if_data *sdata);
 void ieee80211_debugfs_rename_netdev(struct ieee80211_sub_if_data *sdata);
 void ieee80211_debugfs_recreate_netdev(struct ieee80211_sub_if_data *sdata,
@@ -24,9 +22,6 @@ void ieee80211_link_debugfs_remove(struct ieee80211_link_data *link);
 void ieee80211_link_debugfs_drv_add(struct ieee80211_link_data *link);
 void ieee80211_link_debugfs_drv_remove(struct ieee80211_link_data *link);
 #else
-static inline void ieee80211_debugfs_add_netdev(
-	struct ieee80211_sub_if_data *sdata, bool mld_vif)
-{}
 static inline void ieee80211_debugfs_remove_netdev(
 	struct ieee80211_sub_if_data *sdata)
 {}
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index e4e7c0b38cb6..11c4caa4748e 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1783,7 +1783,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
 	/* need to do this after the switch so vif.type is correct */
 	ieee80211_link_setup(&sdata->deflink);
 
-	ieee80211_debugfs_add_netdev(sdata, false);
+	ieee80211_debugfs_recreate_netdev(sdata, false);
 }
 
 static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata,
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 073105deb424..2022a26eb881 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -8,7 +8,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright (C) 2015 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2023 Intel Corporation
+ * Copyright (C) 2018 - 2024 Intel Corporation
  */
 
 #include <linux/delay.h>
@@ -2918,6 +2918,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 
 	/* other links will be destroyed */
 	sdata->deflink.u.mgd.bss = NULL;
+	sdata->deflink.smps_mode = IEEE80211_SMPS_OFF;
 
 	netif_carrier_off(sdata->dev);
 
@@ -5045,9 +5046,6 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	if (!link)
 		return 0;
 
-	/* will change later if needed */
-	link->smps_mode = IEEE80211_SMPS_OFF;
-
 	/*
 	 * If this fails (possibly due to channel context sharing
 	 * on incompatible channels, e.g. 80+80 and 160 sharing the
@@ -7096,6 +7094,7 @@ void ieee80211_mgd_setup_link(struct ieee80211_link_data *link)
 	link->u.mgd.p2p_noa_index = -1;
 	link->u.mgd.conn_flags = 0;
 	link->conf->bssid = link->u.mgd.bssid;
+	link->smps_mode = IEEE80211_SMPS_OFF;
 
 	wiphy_work_init(&link->u.mgd.request_smps_work,
 			ieee80211_request_smps_mgd_work);
@@ -7309,6 +7308,75 @@ out_err:
 	return err;
 }
 
+static bool ieee80211_mgd_csa_present(struct ieee80211_sub_if_data *sdata,
+				      const struct cfg80211_bss_ies *ies,
+				      u8 cur_channel, bool ignore_ecsa)
+{
+	const struct element *csa_elem, *ecsa_elem;
+	struct ieee80211_channel_sw_ie *csa = NULL;
+	struct ieee80211_ext_chansw_ie *ecsa = NULL;
+
+	if (!ies)
+		return false;
+
+	csa_elem = cfg80211_find_elem(WLAN_EID_CHANNEL_SWITCH,
+				      ies->data, ies->len);
+	if (csa_elem && csa_elem->datalen == sizeof(*csa))
+		csa = (void *)csa_elem->data;
+
+	ecsa_elem = cfg80211_find_elem(WLAN_EID_EXT_CHANSWITCH_ANN,
+				       ies->data, ies->len);
+	if (ecsa_elem && ecsa_elem->datalen == sizeof(*ecsa))
+		ecsa = (void *)ecsa_elem->data;
+
+	if (csa && csa->count == 0)
+		csa = NULL;
+	if (csa && !csa->mode && csa->new_ch_num == cur_channel)
+		csa = NULL;
+
+	if (ecsa && ecsa->count == 0)
+		ecsa = NULL;
+	if (ecsa && !ecsa->mode && ecsa->new_ch_num == cur_channel)
+		ecsa = NULL;
+
+	if (ignore_ecsa && ecsa) {
+		sdata_info(sdata,
+			   "Ignoring ECSA in probe response - was considered stuck!\n");
+		return csa;
+	}
+
+	return csa || ecsa;
+}
+
+static bool ieee80211_mgd_csa_in_process(struct ieee80211_sub_if_data *sdata,
+					 struct cfg80211_bss *bss)
+{
+	u8 cur_channel;
+	bool ret;
+
+	cur_channel = ieee80211_frequency_to_channel(bss->channel->center_freq);
+
+	rcu_read_lock();
+	if (ieee80211_mgd_csa_present(sdata,
+				      rcu_dereference(bss->beacon_ies),
+				      cur_channel, false)) {
+		ret = true;
+		goto out;
+	}
+
+	if (ieee80211_mgd_csa_present(sdata,
+				      rcu_dereference(bss->proberesp_ies),
+				      cur_channel, bss->proberesp_ecsa_stuck)) {
+		ret = true;
+		goto out;
+	}
+
+	ret = false;
+out:
+	rcu_read_unlock();
+	return ret;
+}
+
 /* config hooks */
 int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata,
 		       struct cfg80211_auth_request *req)
@@ -7317,7 +7385,6 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	struct ieee80211_mgd_auth_data *auth_data;
 	struct ieee80211_link_data *link;
-	const struct element *csa_elem, *ecsa_elem;
 	u16 auth_alg;
 	int err;
 	bool cont_auth;
@@ -7360,21 +7427,10 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata,
 	if (ifmgd->assoc_data)
 		return -EBUSY;
 
-	rcu_read_lock();
-	csa_elem = ieee80211_bss_get_elem(req->bss, WLAN_EID_CHANNEL_SWITCH);
-	ecsa_elem = ieee80211_bss_get_elem(req->bss,
-					   WLAN_EID_EXT_CHANSWITCH_ANN);
-	if ((csa_elem &&
-	     csa_elem->datalen == sizeof(struct ieee80211_channel_sw_ie) &&
-	     ((struct ieee80211_channel_sw_ie *)csa_elem->data)->count != 0) ||
-	    (ecsa_elem &&
-	     ecsa_elem->datalen == sizeof(struct ieee80211_ext_chansw_ie) &&
-	     ((struct ieee80211_ext_chansw_ie *)ecsa_elem->data)->count != 0)) {
-		rcu_read_unlock();
+	if (ieee80211_mgd_csa_in_process(sdata, req->bss)) {
 		sdata_info(sdata, "AP is in CSA process, reject auth\n");
 		return -EINVAL;
 	}
-	rcu_read_unlock();
 
 	auth_data = kzalloc(sizeof(*auth_data) + req->auth_data_len +
 			    req->ie_len, GFP_KERNEL);
@@ -7684,7 +7740,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	struct ieee80211_mgd_assoc_data *assoc_data;
-	const struct element *ssid_elem, *csa_elem, *ecsa_elem;
+	const struct element *ssid_elem;
 	struct ieee80211_vif_cfg *vif_cfg = &sdata->vif.cfg;
 	ieee80211_conn_flags_t conn_flags = 0;
 	struct ieee80211_link_data *link;
@@ -7707,23 +7763,15 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 
 	cbss = req->link_id < 0 ? req->bss : req->links[req->link_id].bss;
 
-	rcu_read_lock();
-	ssid_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_SSID);
-	if (!ssid_elem || ssid_elem->datalen > sizeof(assoc_data->ssid)) {
-		rcu_read_unlock();
+	if (ieee80211_mgd_csa_in_process(sdata, cbss)) {
+		sdata_info(sdata, "AP is in CSA process, reject assoc\n");
 		kfree(assoc_data);
 		return -EINVAL;
 	}
 
-	csa_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_CHANNEL_SWITCH);
-	ecsa_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_EXT_CHANSWITCH_ANN);
-	if ((csa_elem &&
-	     csa_elem->datalen == sizeof(struct ieee80211_channel_sw_ie) &&
-	     ((struct ieee80211_channel_sw_ie *)csa_elem->data)->count != 0) ||
-	    (ecsa_elem &&
-	     ecsa_elem->datalen == sizeof(struct ieee80211_ext_chansw_ie) &&
-	     ((struct ieee80211_ext_chansw_ie *)ecsa_elem->data)->count != 0)) {
-		sdata_info(sdata, "AP is in CSA process, reject assoc\n");
+	rcu_read_lock();
+	ssid_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_SSID);
+	if (!ssid_elem || ssid_elem->datalen > sizeof(assoc_data->ssid)) {
 		rcu_read_unlock();
 		kfree(assoc_data);
 		return -EINVAL;
@@ -7998,8 +8046,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 
 		rcu_read_lock();
 		beacon_ies = rcu_dereference(req->bss->beacon_ies);
-
-		if (beacon_ies) {
+		if (!beacon_ies) {
 			/*
 			 * Wait up to one beacon interval ...
 			 * should this be more if we miss one?
@@ -8080,6 +8127,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata,
 		ieee80211_report_disconnect(sdata, frame_buf,
 					    sizeof(frame_buf), true,
 					    req->reason_code, false);
+		drv_mgd_complete_tx(sdata->local, sdata, &info);
 		return 0;
 	}
 
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index d5ea5f5bcf3a..9d33fd2377c8 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -119,7 +119,8 @@ void rate_control_rate_update(struct ieee80211_local *local,
 		rcu_read_unlock();
 	}
 
-	drv_sta_rc_update(local, sta->sdata, &sta->sta, changed);
+	if (sta->uploaded)
+		drv_sta_rc_update(local, sta->sdata, &sta->sta, changed);
 }
 
 int ieee80211_rate_control_register(const struct rate_control_ops *ops)
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 645355e5f1bc..f9d5842601fa 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -9,7 +9,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2013-2015  Intel Mobile Communications GmbH
  * Copyright 2016-2017  Intel Deutschland GmbH
- * Copyright (C) 2018-2023 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
  */
 
 #include <linux/if_arp.h>
@@ -237,14 +237,18 @@ ieee80211_bss_info_update(struct ieee80211_local *local,
 }
 
 static bool ieee80211_scan_accept_presp(struct ieee80211_sub_if_data *sdata,
+					struct ieee80211_channel *channel,
 					u32 scan_flags, const u8 *da)
 {
 	if (!sdata)
 		return false;
-	/* accept broadcast for OCE */
-	if (scan_flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP &&
-	    is_broadcast_ether_addr(da))
+
+	/* accept broadcast on 6 GHz and for OCE */
+	if (is_broadcast_ether_addr(da) &&
+	    (channel->band == NL80211_BAND_6GHZ ||
+	     scan_flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP))
 		return true;
+
 	if (scan_flags & NL80211_SCAN_FLAG_RANDOM_ADDR)
 		return true;
 	return ether_addr_equal(da, sdata->vif.addr);
@@ -293,6 +297,12 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb)
 		wiphy_delayed_work_queue(local->hw.wiphy, &local->scan_work, 0);
 	}
 
+	channel = ieee80211_get_channel_khz(local->hw.wiphy,
+					    ieee80211_rx_status_to_khz(rx_status));
+
+	if (!channel || channel->flags & IEEE80211_CHAN_DISABLED)
+		return;
+
 	if (ieee80211_is_probe_resp(mgmt->frame_control)) {
 		struct cfg80211_scan_request *scan_req;
 		struct cfg80211_sched_scan_request *sched_scan_req;
@@ -310,19 +320,15 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb)
 		/* ignore ProbeResp to foreign address or non-bcast (OCE)
 		 * unless scanning with randomised address
 		 */
-		if (!ieee80211_scan_accept_presp(sdata1, scan_req_flags,
+		if (!ieee80211_scan_accept_presp(sdata1, channel,
+						 scan_req_flags,
 						 mgmt->da) &&
-		    !ieee80211_scan_accept_presp(sdata2, sched_scan_req_flags,
+		    !ieee80211_scan_accept_presp(sdata2, channel,
+						 sched_scan_req_flags,
 						 mgmt->da))
 			return;
 	}
 
-	channel = ieee80211_get_channel_khz(local->hw.wiphy,
-					ieee80211_rx_status_to_khz(rx_status));
-
-	if (!channel || channel->flags & IEEE80211_CHAN_DISABLED)
-		return;
-
 	bss = ieee80211_bss_info_update(local, rx_status,
 					mgmt, skb->len,
 					channel);
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index bf1adcd96b41..4391d8dd634b 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -404,7 +404,10 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(sta->link); i++) {
-		if (!(sta->sta.valid_links & BIT(i)))
+		struct link_sta_info *link_sta;
+
+		link_sta = rcu_access_pointer(sta->link[i]);
+		if (!link_sta)
 			continue;
 
 		sta_remove_link(sta, i, false);
@@ -910,6 +913,8 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
 	if (ieee80211_vif_is_mesh(&sdata->vif))
 		mesh_accept_plinks_update(sdata);
 
+	ieee80211_check_fast_xmit(sta);
+
 	return 0;
  out_remove:
 	if (sta->sta.valid_links)
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 314998fdb1a5..6fbb15b65902 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -5,7 +5,7 @@
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
- * Copyright (C) 2018-2022 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
  *
  * Transmit and frame generation functions.
  */
@@ -3048,7 +3048,7 @@ void ieee80211_check_fast_xmit(struct sta_info *sta)
 	    sdata->vif.type == NL80211_IFTYPE_STATION)
 		goto out;
 
-	if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED))
+	if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED) || !sta->uploaded)
 		goto out;
 
 	if (test_sta_flag(sta, WLAN_STA_PS_STA) ||
@@ -3100,10 +3100,11 @@ void ieee80211_check_fast_xmit(struct sta_info *sta)
 			/* DA SA BSSID */
 			build.da_offs = offsetof(struct ieee80211_hdr, addr1);
 			build.sa_offs = offsetof(struct ieee80211_hdr, addr2);
+			rcu_read_lock();
 			link = rcu_dereference(sdata->link[tdls_link_id]);
-			if (WARN_ON_ONCE(!link))
-				break;
-			memcpy(hdr->addr3, link->u.mgd.bssid, ETH_ALEN);
+			if (!WARN_ON_ONCE(!link))
+				memcpy(hdr->addr3, link->u.mgd.bssid, ETH_ALEN);
+			rcu_read_unlock();
 			build.hdr_len = 24;
 			break;
 		}
@@ -3926,6 +3927,7 @@ begin:
 			goto begin;
 
 		skb = __skb_dequeue(&tx.skbs);
+		info = IEEE80211_SKB_CB(skb);
 
 		if (!skb_queue_empty(&tx.skbs)) {
 			spin_lock_bh(&fq->lock);
@@ -3970,7 +3972,7 @@ begin:
 	}
 
 encap_out:
-	IEEE80211_SKB_CB(skb)->control.vif = vif;
+	info->control.vif = vif;
 
 	if (tx.sta &&
 	    wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) {
diff --git a/net/mac80211/wbrf.c b/net/mac80211/wbrf.c
index a05c5b971789..3a8612309137 100644
--- a/net/mac80211/wbrf.c
+++ b/net/mac80211/wbrf.c
@@ -23,8 +23,6 @@ void ieee80211_check_wbrf_support(struct ieee80211_local *local)
 		return;
 
 	local->wbrf_supported = acpi_amd_wbrf_supported_producer(dev);
-	dev_dbg(dev, "WBRF is %s supported\n",
-		local->wbrf_supported ? "" : "not");
 }
 
 static void get_chan_freq_boundary(u32 center_freq, u32 bandwidth, u64 *start, u64 *end)
diff --git a/net/mctp/route.c b/net/mctp/route.c
index 7a47a58aa54b..ceee44ea09d9 100644
--- a/net/mctp/route.c
+++ b/net/mctp/route.c
@@ -663,7 +663,7 @@ struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk,
 	spin_unlock_irqrestore(&mns->keys_lock, flags);
 
 	if (!tagbits) {
-		kfree(key);
+		mctp_key_unref(key);
 		return ERR_PTR(-EBUSY);
 	}
 
@@ -888,7 +888,7 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt,
 		dev = dev_get_by_index_rcu(sock_net(sk), cb->ifindex);
 		if (!dev) {
 			rcu_read_unlock();
-			return rc;
+			goto out_free;
 		}
 		rt->dev = __mctp_dev_get(dev);
 		rcu_read_unlock();
@@ -903,7 +903,8 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt,
 		rt->mtu = 0;
 
 	} else {
-		return -EINVAL;
+		rc = -EINVAL;
+		goto out_free;
 	}
 
 	spin_lock_irqsave(&rt->dev->addrs_lock, flags);
@@ -966,12 +967,17 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt,
 		rc = mctp_do_fragment_route(rt, skb, mtu, tag);
 	}
 
+	/* route output functions consume the skb, even on error */
+	skb = NULL;
+
 out_release:
 	if (!ext_rt)
 		mctp_route_release(rt);
 
 	mctp_dev_put(tmp_rt.dev);
 
+out_free:
+	kfree_skb(skb);
 	return rc;
 }
 
diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c
index a536586742f2..7017dd60659d 100644
--- a/net/mptcp/diag.c
+++ b/net/mptcp/diag.c
@@ -13,17 +13,22 @@
 #include <uapi/linux/mptcp.h>
 #include "protocol.h"
 
-static int subflow_get_info(const struct sock *sk, struct sk_buff *skb)
+static int subflow_get_info(struct sock *sk, struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *sf;
 	struct nlattr *start;
 	u32 flags = 0;
+	bool slow;
 	int err;
 
+	if (inet_sk_state_load(sk) == TCP_LISTEN)
+		return 0;
+
 	start = nla_nest_start_noflag(skb, INET_ULP_INFO_MPTCP);
 	if (!start)
 		return -EMSGSIZE;
 
+	slow = lock_sock_fast(sk);
 	rcu_read_lock();
 	sf = rcu_dereference(inet_csk(sk)->icsk_ulp_data);
 	if (!sf) {
@@ -63,17 +68,19 @@ static int subflow_get_info(const struct sock *sk, struct sk_buff *skb)
 			sf->map_data_len) ||
 	    nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_FLAGS, flags) ||
 	    nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_REM, sf->remote_id) ||
-	    nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, sf->local_id)) {
+	    nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, subflow_get_local_id(sf))) {
 		err = -EMSGSIZE;
 		goto nla_failure;
 	}
 
 	rcu_read_unlock();
+	unlock_sock_fast(sk, slow);
 	nla_nest_end(skb, start);
 	return 0;
 
 nla_failure:
 	rcu_read_unlock();
+	unlock_sock_fast(sk, slow);
 	nla_nest_cancel(skb, start);
 	return err;
 }
diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c
index 74698582a285..ad28da655f8b 100644
--- a/net/mptcp/fastopen.c
+++ b/net/mptcp/fastopen.c
@@ -59,13 +59,12 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf
 	mptcp_data_unlock(sk);
 }
 
-void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
-				   const struct mptcp_options_received *mp_opt)
+void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
+				     const struct mptcp_options_received *mp_opt)
 {
 	struct sock *sk = (struct sock *)msk;
 	struct sk_buff *skb;
 
-	mptcp_data_lock(sk);
 	skb = skb_peek_tail(&sk->sk_receive_queue);
 	if (skb) {
 		WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq);
@@ -77,5 +76,4 @@ void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_
 	}
 
 	pr_debug("msk=%p ack_seq=%llx", msk, msk->ack_seq);
-	mptcp_data_unlock(sk);
 }
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index c53914012d01..63fc0758c22d 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -123,8 +123,8 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		break;
 
 	case MPTCPOPT_MP_JOIN:
-		mp_opt->suboptions |= OPTIONS_MPTCP_MPJ;
 		if (opsize == TCPOLEN_MPTCP_MPJ_SYN) {
+			mp_opt->suboptions |= OPTION_MPTCP_MPJ_SYN;
 			mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP;
 			mp_opt->join_id = *ptr++;
 			mp_opt->token = get_unaligned_be32(ptr);
@@ -135,6 +135,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 				 mp_opt->backup, mp_opt->join_id,
 				 mp_opt->token, mp_opt->nonce);
 		} else if (opsize == TCPOLEN_MPTCP_MPJ_SYNACK) {
+			mp_opt->suboptions |= OPTION_MPTCP_MPJ_SYNACK;
 			mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP;
 			mp_opt->join_id = *ptr++;
 			mp_opt->thmac = get_unaligned_be64(ptr);
@@ -145,11 +146,10 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 				 mp_opt->backup, mp_opt->join_id,
 				 mp_opt->thmac, mp_opt->nonce);
 		} else if (opsize == TCPOLEN_MPTCP_MPJ_ACK) {
+			mp_opt->suboptions |= OPTION_MPTCP_MPJ_ACK;
 			ptr += 2;
 			memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN);
 			pr_debug("MP_JOIN hmac");
-		} else {
-			mp_opt->suboptions &= ~OPTIONS_MPTCP_MPJ;
 		}
 		break;
 
@@ -962,9 +962,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 		/* subflows are fully established as soon as we get any
 		 * additional ack, including ADD_ADDR.
 		 */
-		subflow->fully_established = 1;
-		WRITE_ONCE(msk->fully_established, true);
-		goto check_notify;
+		goto set_fully_established;
 	}
 
 	/* If the first established packet does not contain MP_CAPABLE + data
@@ -983,10 +981,13 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 	if (mp_opt->deny_join_id0)
 		WRITE_ONCE(msk->pm.remote_deny_join_id0, true);
 
-set_fully_established:
 	if (unlikely(!READ_ONCE(msk->pm.server_side)))
 		pr_warn_once("bogus mpc option on established client sk");
-	mptcp_subflow_fully_established(subflow, mp_opt);
+
+set_fully_established:
+	mptcp_data_lock((struct sock *)msk);
+	__mptcp_subflow_fully_established(msk, subflow, mp_opt);
+	mptcp_data_unlock((struct sock *)msk);
 
 check_notify:
 	/* if the subflow is not already linked into the conn_list, we can't
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 287a60381eae..58d17d9604e7 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -396,19 +396,6 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk)
 	}
 }
 
-static bool lookup_address_in_vec(const struct mptcp_addr_info *addrs, unsigned int nr,
-				  const struct mptcp_addr_info *addr)
-{
-	int i;
-
-	for (i = 0; i < nr; i++) {
-		if (addrs[i].id == addr->id)
-			return true;
-	}
-
-	return false;
-}
-
 /* Fill all the remote addresses into the array addrs[],
  * and return the array size.
  */
@@ -440,18 +427,34 @@ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk,
 		msk->pm.subflows++;
 		addrs[i++] = remote;
 	} else {
+		DECLARE_BITMAP(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1);
+
+		/* Forbid creation of new subflows matching existing
+		 * ones, possibly already created by incoming ADD_ADDR
+		 */
+		bitmap_zero(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1);
+		mptcp_for_each_subflow(msk, subflow)
+			if (READ_ONCE(subflow->local_id) == local->id)
+				__set_bit(subflow->remote_id, unavail_id);
+
 		mptcp_for_each_subflow(msk, subflow) {
 			ssk = mptcp_subflow_tcp_sock(subflow);
 			remote_address((struct sock_common *)ssk, &addrs[i]);
-			addrs[i].id = subflow->remote_id;
+			addrs[i].id = READ_ONCE(subflow->remote_id);
 			if (deny_id0 && !addrs[i].id)
 				continue;
 
+			if (test_bit(addrs[i].id, unavail_id))
+				continue;
+
 			if (!mptcp_pm_addr_families_match(sk, local, &addrs[i]))
 				continue;
 
-			if (!lookup_address_in_vec(addrs, i, &addrs[i]) &&
-			    msk->pm.subflows < subflows_max) {
+			if (msk->pm.subflows < subflows_max) {
+				/* forbid creating multiple address towards
+				 * this id
+				 */
+				__set_bit(addrs[i].id, unavail_id);
 				msk->pm.subflows++;
 				i++;
 			}
@@ -799,18 +802,18 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 
 		mptcp_for_each_subflow_safe(msk, subflow, tmp) {
 			struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+			u8 remote_id = READ_ONCE(subflow->remote_id);
 			int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
-			u8 id = subflow->local_id;
+			u8 id = subflow_get_local_id(subflow);
 
-			if (rm_type == MPTCP_MIB_RMADDR && subflow->remote_id != rm_id)
+			if (rm_type == MPTCP_MIB_RMADDR && remote_id != rm_id)
 				continue;
 			if (rm_type == MPTCP_MIB_RMSUBFLOW && !mptcp_local_id_match(msk, id, rm_id))
 				continue;
 
 			pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u",
 				 rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow",
-				 i, rm_id, subflow->local_id, subflow->remote_id,
-				 msk->mpc_endpoint_id);
+				 i, rm_id, id, remote_id, msk->mpc_endpoint_id);
 			spin_unlock_bh(&msk->pm.lock);
 			mptcp_subflow_shutdown(sk, ssk, how);
 
@@ -901,7 +904,8 @@ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry)
 }
 
 static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
-					     struct mptcp_pm_addr_entry *entry)
+					     struct mptcp_pm_addr_entry *entry,
+					     bool needs_id)
 {
 	struct mptcp_pm_addr_entry *cur, *del_entry = NULL;
 	unsigned int addr_max;
@@ -949,7 +953,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
 		}
 	}
 
-	if (!entry->addr.id) {
+	if (!entry->addr.id && needs_id) {
 find_next:
 		entry->addr.id = find_next_zero_bit(pernet->id_bitmap,
 						    MPTCP_PM_MAX_ADDR_ID + 1,
@@ -960,7 +964,7 @@ find_next:
 		}
 	}
 
-	if (!entry->addr.id)
+	if (!entry->addr.id && needs_id)
 		goto out;
 
 	__set_bit(entry->addr.id, pernet->id_bitmap);
@@ -1092,7 +1096,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc
 	entry->ifindex = 0;
 	entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT;
 	entry->lsk = NULL;
-	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry);
+	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true);
 	if (ret < 0)
 		kfree(entry);
 
@@ -1285,6 +1289,18 @@ next:
 	return 0;
 }
 
+static bool mptcp_pm_has_addr_attr_id(const struct nlattr *attr,
+				      struct genl_info *info)
+{
+	struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1];
+
+	if (!nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr,
+					 mptcp_pm_address_nl_policy, info->extack) &&
+	    tb[MPTCP_PM_ADDR_ATTR_ID])
+		return true;
+	return false;
+}
+
 int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
@@ -1326,7 +1342,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
 			goto out_free;
 		}
 	}
-	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry);
+	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry,
+						!mptcp_pm_has_addr_attr_id(attr, info));
 	if (ret < 0) {
 		GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret);
 		goto out_free;
@@ -1980,7 +1997,7 @@ static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk)
 	if (WARN_ON_ONCE(!sf))
 		return -EINVAL;
 
-	if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, sf->local_id))
+	if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, subflow_get_local_id(sf)))
 		return -EMSGSIZE;
 
 	if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, sf->remote_id))
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index efecbe3cf415..bc97cc30f013 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -26,7 +26,8 @@ void mptcp_free_local_addr_list(struct mptcp_sock *msk)
 }
 
 static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
-						    struct mptcp_pm_addr_entry *entry)
+						    struct mptcp_pm_addr_entry *entry,
+						    bool needs_id)
 {
 	DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
 	struct mptcp_pm_addr_entry *match = NULL;
@@ -41,7 +42,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
 	spin_lock_bh(&msk->pm.lock);
 	list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) {
 		addr_match = mptcp_addresses_equal(&e->addr, &entry->addr, true);
-		if (addr_match && entry->addr.id == 0)
+		if (addr_match && entry->addr.id == 0 && needs_id)
 			entry->addr.id = e->addr.id;
 		id_match = (e->addr.id == entry->addr.id);
 		if (addr_match && id_match) {
@@ -64,7 +65,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
 		}
 
 		*e = *entry;
-		if (!e->addr.id)
+		if (!e->addr.id && needs_id)
 			e->addr.id = find_next_zero_bit(id_bitmap,
 							MPTCP_PM_MAX_ADDR_ID + 1,
 							1);
@@ -130,10 +131,21 @@ int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
 int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
 				    struct mptcp_addr_info *skc)
 {
-	struct mptcp_pm_addr_entry new_entry;
+	struct mptcp_pm_addr_entry *entry = NULL, *e, new_entry;
 	__be16 msk_sport =  ((struct inet_sock *)
 			     inet_sk((struct sock *)msk))->inet_sport;
 
+	spin_lock_bh(&msk->pm.lock);
+	list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) {
+		if (mptcp_addresses_equal(&e->addr, skc, false)) {
+			entry = e;
+			break;
+		}
+	}
+	spin_unlock_bh(&msk->pm.lock);
+	if (entry)
+		return entry->addr.id;
+
 	memset(&new_entry, 0, sizeof(struct mptcp_pm_addr_entry));
 	new_entry.addr = *skc;
 	new_entry.addr.id = 0;
@@ -142,7 +154,7 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
 	if (new_entry.addr.port == msk_sport)
 		new_entry.addr.port = 0;
 
-	return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry);
+	return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true);
 }
 
 int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
@@ -187,7 +199,7 @@ int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
 		goto announce_err;
 	}
 
-	err = mptcp_userspace_pm_append_new_local_addr(msk, &addr_val);
+	err = mptcp_userspace_pm_append_new_local_addr(msk, &addr_val, false);
 	if (err < 0) {
 		GENL_SET_ERR_MSG(info, "did not match address and id");
 		goto announce_err;
@@ -222,7 +234,7 @@ static int mptcp_userspace_pm_remove_id_zero_address(struct mptcp_sock *msk,
 
 	lock_sock(sk);
 	mptcp_for_each_subflow(msk, subflow) {
-		if (subflow->local_id == 0) {
+		if (READ_ONCE(subflow->local_id) == 0) {
 			has_id_0 = true;
 			break;
 		}
@@ -367,7 +379,7 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	local.addr = addr_l;
-	err = mptcp_userspace_pm_append_new_local_addr(msk, &local);
+	err = mptcp_userspace_pm_append_new_local_addr(msk, &local, false);
 	if (err < 0) {
 		GENL_SET_ERR_MSG(info, "did not match address and id");
 		goto create_err;
@@ -483,6 +495,16 @@ int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, struct genl_info *info
 		goto destroy_err;
 	}
 
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	if (addr_l.family == AF_INET && ipv6_addr_v4mapped(&addr_r.addr6)) {
+		ipv6_addr_set_v4mapped(addr_l.addr.s_addr, &addr_l.addr6);
+		addr_l.family = AF_INET6;
+	}
+	if (addr_r.family == AF_INET && ipv6_addr_v4mapped(&addr_l.addr6)) {
+		ipv6_addr_set_v4mapped(addr_r.addr.s_addr, &addr_r.addr6);
+		addr_r.family = AF_INET6;
+	}
+#endif
 	if (addr_l.family != addr_r.family) {
 		GENL_SET_ERR_MSG(info, "address families do not match");
 		err = -EINVAL;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 3ed4709a7509..7833a49f6214 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -85,7 +85,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
 	subflow->subflow_id = msk->subflow_id++;
 
 	/* This is the first subflow, always with id 0 */
-	subflow->local_id_valid = 1;
+	WRITE_ONCE(subflow->local_id, 0);
 	mptcp_sock_graft(msk->first, sk->sk_socket);
 	iput(SOCK_INODE(ssock));
 
@@ -1260,6 +1260,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 		mpext = mptcp_get_ext(skb);
 		if (!mptcp_skb_can_collapse_to(data_seq, skb, mpext)) {
 			TCP_SKB_CB(skb)->eor = 1;
+			tcp_mark_push(tcp_sk(ssk), skb);
 			goto alloc_skb;
 		}
 
@@ -1505,8 +1506,11 @@ static void mptcp_update_post_push(struct mptcp_sock *msk,
 
 void mptcp_check_and_set_pending(struct sock *sk)
 {
-	if (mptcp_send_head(sk))
-		mptcp_sk(sk)->push_pending |= BIT(MPTCP_PUSH_PENDING);
+	if (mptcp_send_head(sk)) {
+		mptcp_data_lock(sk);
+		mptcp_sk(sk)->cb_flags |= BIT(MPTCP_PUSH_PENDING);
+		mptcp_data_unlock(sk);
+	}
 }
 
 static int __subflow_push_pending(struct sock *sk, struct sock *ssk,
@@ -1960,6 +1964,9 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 	if (copied <= 0)
 		return;
 
+	if (!msk->rcvspace_init)
+		mptcp_rcv_space_init(msk, msk->first);
+
 	msk->rcvq_space.copied += copied;
 
 	mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC);
@@ -2314,9 +2321,6 @@ bool __mptcp_retransmit_pending_data(struct sock *sk)
 	if (__mptcp_check_fallback(msk))
 		return false;
 
-	if (tcp_rtx_and_write_queues_empty(sk))
-		return false;
-
 	/* the closing socket has some data untransmitted and/or unacked:
 	 * some data in the mptcp rtx queue has not really xmitted yet.
 	 * keep it simple and re-inject the whole mptcp level rtx queue
@@ -3145,7 +3149,6 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 	mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE);
 	WRITE_ONCE(msk->flags, 0);
 	msk->cb_flags = 0;
-	msk->push_pending = 0;
 	msk->recovery = false;
 	msk->can_ack = false;
 	msk->fully_established = false;
@@ -3161,6 +3164,7 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 	msk->bytes_received = 0;
 	msk->bytes_sent = 0;
 	msk->bytes_retrans = 0;
+	msk->rcvspace_init = 0;
 
 	WRITE_ONCE(sk->sk_shutdown, 0);
 	sk_error_report(sk);
@@ -3174,8 +3178,50 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk)
 
 	return (struct ipv6_pinfo *)(((u8 *)sk) + offset);
 }
+
+static void mptcp_copy_ip6_options(struct sock *newsk, const struct sock *sk)
+{
+	const struct ipv6_pinfo *np = inet6_sk(sk);
+	struct ipv6_txoptions *opt;
+	struct ipv6_pinfo *newnp;
+
+	newnp = inet6_sk(newsk);
+
+	rcu_read_lock();
+	opt = rcu_dereference(np->opt);
+	if (opt) {
+		opt = ipv6_dup_options(newsk, opt);
+		if (!opt)
+			net_warn_ratelimited("%s: Failed to copy ip6 options\n", __func__);
+	}
+	RCU_INIT_POINTER(newnp->opt, opt);
+	rcu_read_unlock();
+}
 #endif
 
+static void mptcp_copy_ip_options(struct sock *newsk, const struct sock *sk)
+{
+	struct ip_options_rcu *inet_opt, *newopt = NULL;
+	const struct inet_sock *inet = inet_sk(sk);
+	struct inet_sock *newinet;
+
+	newinet = inet_sk(newsk);
+
+	rcu_read_lock();
+	inet_opt = rcu_dereference(inet->inet_opt);
+	if (inet_opt) {
+		newopt = sock_kmalloc(newsk, sizeof(*inet_opt) +
+				      inet_opt->opt.optlen, GFP_ATOMIC);
+		if (newopt)
+			memcpy(newopt, inet_opt, sizeof(*inet_opt) +
+			       inet_opt->opt.optlen);
+		else
+			net_warn_ratelimited("%s: Failed to copy ip options\n", __func__);
+	}
+	RCU_INIT_POINTER(newinet->inet_opt, newopt);
+	rcu_read_unlock();
+}
+
 struct sock *mptcp_sk_clone_init(const struct sock *sk,
 				 const struct mptcp_options_received *mp_opt,
 				 struct sock *ssk,
@@ -3183,6 +3229,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 {
 	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
 	struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC);
+	struct mptcp_subflow_context *subflow;
 	struct mptcp_sock *msk;
 
 	if (!nsk)
@@ -3195,6 +3242,13 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 
 	__mptcp_init_sock(nsk);
 
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	if (nsk->sk_family == AF_INET6)
+		mptcp_copy_ip6_options(nsk, sk);
+	else
+#endif
+		mptcp_copy_ip_options(nsk, sk);
+
 	msk = mptcp_sk(nsk);
 	msk->local_key = subflow_req->local_key;
 	msk->token = subflow_req->token;
@@ -3206,7 +3260,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 	msk->write_seq = subflow_req->idsn + 1;
 	msk->snd_nxt = msk->write_seq;
 	msk->snd_una = msk->write_seq;
-	msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd;
+	msk->wnd_end = msk->snd_nxt + tcp_sk(ssk)->snd_wnd;
 	msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;
 	mptcp_init_sched(msk, mptcp_sk(sk)->sched);
 
@@ -3223,7 +3277,8 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 
 	/* The msk maintain a ref to each subflow in the connections list */
 	WRITE_ONCE(msk->first, ssk);
-	list_add(&mptcp_subflow_ctx(ssk)->node, &msk->conn_list);
+	subflow = mptcp_subflow_ctx(ssk);
+	list_add(&subflow->node, &msk->conn_list);
 	sock_hold(ssk);
 
 	/* new mpc subflow takes ownership of the newly
@@ -3238,6 +3293,9 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 	__mptcp_propagate_sndbuf(nsk, ssk);
 
 	mptcp_rcv_space_init(msk, ssk);
+
+	if (mp_opt->suboptions & OPTION_MPTCP_MPC_ACK)
+		__mptcp_subflow_fully_established(msk, subflow, mp_opt);
 	bh_unlock_sock(nsk);
 
 	/* note: the newly allocated socket refcount is 2 now */
@@ -3248,6 +3306,7 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
 {
 	const struct tcp_sock *tp = tcp_sk(ssk);
 
+	msk->rcvspace_init = 1;
 	msk->rcvq_space.copied = 0;
 	msk->rcvq_space.rtt_us = 0;
 
@@ -3258,8 +3317,6 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
 				      TCP_INIT_CWND * tp->advmss);
 	if (msk->rcvq_space.space == 0)
 		msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT;
-
-	WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd);
 }
 
 void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags)
@@ -3333,8 +3390,7 @@ static void mptcp_release_cb(struct sock *sk)
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
 	for (;;) {
-		unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED) |
-				      msk->push_pending;
+		unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED);
 		struct list_head join_list;
 
 		if (!flags)
@@ -3350,7 +3406,6 @@ static void mptcp_release_cb(struct sock *sk)
 		 *    datapath acquires the msk socket spinlock while helding
 		 *    the subflow socket lock
 		 */
-		msk->push_pending = 0;
 		msk->cb_flags &= ~flags;
 		spin_unlock_bh(&sk->sk_lock.slock);
 
@@ -3478,13 +3533,8 @@ void mptcp_finish_connect(struct sock *ssk)
 	 * accessing the field below
 	 */
 	WRITE_ONCE(msk->local_key, subflow->local_key);
-	WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
-	WRITE_ONCE(msk->snd_nxt, msk->write_seq);
-	WRITE_ONCE(msk->snd_una, msk->write_seq);
 
 	mptcp_pm_new_connection(msk, ssk, 0);
-
-	mptcp_rcv_space_init(msk, ssk);
 }
 
 void mptcp_sock_graft(struct sock *sk, struct socket *parent)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 3517f2d24a22..07f6242afc1a 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -286,7 +286,6 @@ struct mptcp_sock {
 	int		rmem_released;
 	unsigned long	flags;
 	unsigned long	cb_flags;
-	unsigned long	push_pending;
 	bool		recovery;		/* closing subflow write queue reinjected */
 	bool		can_ack;
 	bool		fully_established;
@@ -305,7 +304,8 @@ struct mptcp_sock {
 			nodelay:1,
 			fastopening:1,
 			in_accept_queue:1,
-			free_first:1;
+			free_first:1,
+			rcvspace_init:1;
 	struct work_struct work;
 	struct sk_buff  *ooo_last_skb;
 	struct rb_root  out_of_order_queue;
@@ -491,10 +491,9 @@ struct mptcp_subflow_context {
 		remote_key_valid : 1,        /* received the peer key from */
 		disposable : 1,	    /* ctx can be free at ulp release time */
 		stale : 1,	    /* unable to snd/rcv data, do not use for xmit */
-		local_id_valid : 1, /* local_id is correctly initialized */
 		valid_csum_seen : 1,        /* at least one csum validated */
 		is_mptfo : 1,	    /* subflow is doing TFO */
-		__unused : 9;
+		__unused : 10;
 	bool	data_avail;
 	bool	scheduled;
 	u32	remote_nonce;
@@ -505,7 +504,7 @@ struct mptcp_subflow_context {
 		u8	hmac[MPTCPOPT_HMAC_LEN]; /* MPJ subflow only */
 		u64	iasn;	    /* initial ack sequence number, MPC subflows only */
 	};
-	u8	local_id;
+	s16	local_id;	    /* if negative not initialized yet */
 	u8	remote_id;
 	u8	reset_seen:1;
 	u8	reset_transient:1;
@@ -556,6 +555,7 @@ mptcp_subflow_ctx_reset(struct mptcp_subflow_context *subflow)
 {
 	memset(&subflow->reset, 0, sizeof(subflow->reset));
 	subflow->request_mptcp = 1;
+	WRITE_ONCE(subflow->local_id, -1);
 }
 
 static inline u64
@@ -622,8 +622,9 @@ unsigned int mptcp_stale_loss_cnt(const struct net *net);
 unsigned int mptcp_close_timeout(const struct sock *sk);
 int mptcp_get_pm_type(const struct net *net);
 const char *mptcp_get_scheduler(const struct net *net);
-void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
-				     const struct mptcp_options_received *mp_opt);
+void __mptcp_subflow_fully_established(struct mptcp_sock *msk,
+				       struct mptcp_subflow_context *subflow,
+				       const struct mptcp_options_received *mp_opt);
 bool __mptcp_retransmit_pending_data(struct sock *sk);
 void mptcp_check_and_set_pending(struct sock *sk);
 void __mptcp_push_pending(struct sock *sk, unsigned int flags);
@@ -789,6 +790,16 @@ static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk)
 	       READ_ONCE(msk->write_seq) == READ_ONCE(msk->snd_nxt);
 }
 
+static inline void mptcp_write_space(struct sock *sk)
+{
+	if (sk_stream_is_writeable(sk)) {
+		/* pairs with memory barrier in mptcp_poll */
+		smp_mb();
+		if (test_and_clear_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags))
+			sk_stream_write_space(sk);
+	}
+}
+
 static inline void __mptcp_sync_sndbuf(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow;
@@ -807,6 +818,7 @@ static inline void __mptcp_sync_sndbuf(struct sock *sk)
 
 	/* the msk max wmem limit is <nr_subflows> * tcp wmem[2] */
 	WRITE_ONCE(sk->sk_sndbuf, new_sndbuf);
+	mptcp_write_space(sk);
 }
 
 /* The called held both the msk socket and the subflow socket locks,
@@ -837,16 +849,6 @@ static inline void mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk)
 	local_bh_enable();
 }
 
-static inline void mptcp_write_space(struct sock *sk)
-{
-	if (sk_stream_is_writeable(sk)) {
-		/* pairs with memory barrier in mptcp_poll */
-		smp_mb();
-		if (test_and_clear_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags))
-			sk_stream_write_space(sk);
-	}
-}
-
 void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags);
 
 #define MPTCP_TOKEN_MAX_RETRIES	4
@@ -952,8 +954,8 @@ void mptcp_event_pm_listener(const struct sock *ssk,
 			     enum mptcp_event_type event);
 bool mptcp_userspace_pm_active(const struct mptcp_sock *msk);
 
-void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
-				   const struct mptcp_options_received *mp_opt);
+void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
+				     const struct mptcp_options_received *mp_opt);
 void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow,
 					      struct request_sock *req);
 
@@ -1021,6 +1023,15 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
 int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
 int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
 
+static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflow)
+{
+	int local_id = READ_ONCE(subflow->local_id);
+
+	if (local_id < 0)
+		return 0;
+	return local_id;
+}
+
 void __init mptcp_pm_nl_init(void);
 void mptcp_pm_nl_work(struct mptcp_sock *msk);
 void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
@@ -1128,7 +1139,8 @@ static inline bool subflow_simultaneous_connect(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 
-	return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1) &&
+	return (1 << sk->sk_state) &
+	       (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSING) &&
 	       is_active_ssk(subflow) &&
 	       !subflow->conn_finished;
 }
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 3eacd04e7099..71ba86246ff8 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -157,8 +157,8 @@ static int subflow_check_req(struct request_sock *req,
 
 	mptcp_get_options(skb, &mp_opt);
 
-	opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC);
-	opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ);
+	opt_mp_capable = !!(mp_opt.suboptions & OPTION_MPTCP_MPC_SYN);
+	opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_SYN);
 	if (opt_mp_capable) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
 
@@ -254,8 +254,8 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req,
 	subflow_init_req(req, sk_listener);
 	mptcp_get_options(skb, &mp_opt);
 
-	opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC);
-	opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ);
+	opt_mp_capable = !!(mp_opt.suboptions & OPTION_MPTCP_MPC_ACK);
+	opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK);
 	if (opt_mp_capable && opt_mp_join)
 		return -EINVAL;
 
@@ -421,29 +421,26 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc
 
 void __mptcp_sync_state(struct sock *sk, int state)
 {
+	struct mptcp_subflow_context *subflow;
 	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct sock *ssk = msk->first;
+
+	subflow = mptcp_subflow_ctx(ssk);
+	__mptcp_propagate_sndbuf(sk, ssk);
+	if (!msk->rcvspace_init)
+		mptcp_rcv_space_init(msk, ssk);
 
-	__mptcp_propagate_sndbuf(sk, msk->first);
 	if (sk->sk_state == TCP_SYN_SENT) {
+		/* subflow->idsn is always available is TCP_SYN_SENT state,
+		 * even for the FASTOPEN scenarios
+		 */
+		WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
+		WRITE_ONCE(msk->snd_nxt, msk->write_seq);
 		mptcp_set_state(sk, state);
 		sk->sk_state_change(sk);
 	}
 }
 
-static void mptcp_propagate_state(struct sock *sk, struct sock *ssk)
-{
-	struct mptcp_sock *msk = mptcp_sk(sk);
-
-	mptcp_data_lock(sk);
-	if (!sock_owned_by_user(sk)) {
-		__mptcp_sync_state(sk, ssk->sk_state);
-	} else {
-		msk->pending_state = ssk->sk_state;
-		__set_bit(MPTCP_SYNC_STATE, &msk->cb_flags);
-	}
-	mptcp_data_unlock(sk);
-}
-
 static void subflow_set_remote_key(struct mptcp_sock *msk,
 				   struct mptcp_subflow_context *subflow,
 				   const struct mptcp_options_received *mp_opt)
@@ -465,6 +462,31 @@ static void subflow_set_remote_key(struct mptcp_sock *msk,
 	atomic64_set(&msk->rcv_wnd_sent, subflow->iasn);
 }
 
+static void mptcp_propagate_state(struct sock *sk, struct sock *ssk,
+				  struct mptcp_subflow_context *subflow,
+				  const struct mptcp_options_received *mp_opt)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	mptcp_data_lock(sk);
+	if (mp_opt) {
+		/* Options are available only in the non fallback cases
+		 * avoid updating rx path fields otherwise
+		 */
+		WRITE_ONCE(msk->snd_una, subflow->idsn + 1);
+		WRITE_ONCE(msk->wnd_end, subflow->idsn + 1 + tcp_sk(ssk)->snd_wnd);
+		subflow_set_remote_key(msk, subflow, mp_opt);
+	}
+
+	if (!sock_owned_by_user(sk)) {
+		__mptcp_sync_state(sk, ssk->sk_state);
+	} else {
+		msk->pending_state = ssk->sk_state;
+		__set_bit(MPTCP_SYNC_STATE, &msk->cb_flags);
+	}
+	mptcp_data_unlock(sk);
+}
+
 static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
@@ -486,7 +508,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 
 	mptcp_get_options(skb, &mp_opt);
 	if (subflow->request_mptcp) {
-		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) {
+		if (!(mp_opt.suboptions & OPTION_MPTCP_MPC_SYNACK)) {
 			MPTCP_INC_STATS(sock_net(sk),
 					MPTCP_MIB_MPCAPABLEACTIVEFALLBACK);
 			mptcp_do_fallback(sk);
@@ -499,14 +521,13 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		if (mp_opt.deny_join_id0)
 			WRITE_ONCE(msk->pm.remote_deny_join_id0, true);
 		subflow->mp_capable = 1;
-		subflow_set_remote_key(msk, subflow, &mp_opt);
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK);
 		mptcp_finish_connect(sk);
-		mptcp_propagate_state(parent, sk);
+		mptcp_propagate_state(parent, sk, subflow, &mp_opt);
 	} else if (subflow->request_join) {
 		u8 hmac[SHA256_DIGEST_SIZE];
 
-		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ)) {
+		if (!(mp_opt.suboptions & OPTION_MPTCP_MPJ_SYNACK)) {
 			subflow->reset_reason = MPTCP_RST_EMPTCP;
 			goto do_reset;
 		}
@@ -514,7 +535,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		subflow->backup = mp_opt.backup;
 		subflow->thmac = mp_opt.thmac;
 		subflow->remote_nonce = mp_opt.nonce;
-		subflow->remote_id = mp_opt.join_id;
+		WRITE_ONCE(subflow->remote_id, mp_opt.join_id);
 		pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d",
 			 subflow, subflow->thmac, subflow->remote_nonce,
 			 subflow->backup);
@@ -545,8 +566,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		}
 	} else if (mptcp_check_fallback(sk)) {
 fallback:
-		mptcp_rcv_space_init(msk, sk);
-		mptcp_propagate_state(parent, sk);
+		mptcp_propagate_state(parent, sk, subflow, NULL);
 	}
 	return;
 
@@ -557,8 +577,8 @@ do_reset:
 
 static void subflow_set_local_id(struct mptcp_subflow_context *subflow, int local_id)
 {
-	subflow->local_id = local_id;
-	subflow->local_id_valid = 1;
+	WARN_ON_ONCE(local_id < 0 || local_id > 255);
+	WRITE_ONCE(subflow->local_id, local_id);
 }
 
 static int subflow_chk_local_id(struct sock *sk)
@@ -567,7 +587,7 @@ static int subflow_chk_local_id(struct sock *sk)
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
 	int err;
 
-	if (likely(subflow->local_id_valid))
+	if (likely(subflow->local_id >= 0))
 		return 0;
 
 	err = mptcp_pm_get_local_id(msk, (struct sock_common *)sk);
@@ -731,17 +751,16 @@ void mptcp_subflow_drop_ctx(struct sock *ssk)
 	kfree_rcu(ctx, rcu);
 }
 
-void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
-				     const struct mptcp_options_received *mp_opt)
+void __mptcp_subflow_fully_established(struct mptcp_sock *msk,
+				       struct mptcp_subflow_context *subflow,
+				       const struct mptcp_options_received *mp_opt)
 {
-	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
-
 	subflow_set_remote_key(msk, subflow, mp_opt);
 	subflow->fully_established = 1;
 	WRITE_ONCE(msk->fully_established, true);
 
 	if (subflow->is_mptfo)
-		mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt);
+		__mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt);
 }
 
 static struct sock *subflow_syn_recv_sock(const struct sock *sk,
@@ -783,12 +802,13 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 		 * options.
 		 */
 		mptcp_get_options(skb, &mp_opt);
-		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC))
+		if (!(mp_opt.suboptions &
+		      (OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_ACK)))
 			fallback = true;
 
 	} else if (subflow_req->mp_join) {
 		mptcp_get_options(skb, &mp_opt);
-		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ) ||
+		if (!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK) ||
 		    !subflow_hmac_valid(req, &mp_opt) ||
 		    !mptcp_can_accept_new_subflow(subflow_req->msk)) {
 			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
@@ -833,7 +853,6 @@ create_child:
 			 * mpc option
 			 */
 			if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) {
-				mptcp_subflow_fully_established(ctx, &mp_opt);
 				mptcp_pm_fully_established(owner, child);
 				ctx->pm_notified = 1;
 			}
@@ -1548,7 +1567,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 	pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk,
 		 remote_token, local_id, remote_id);
 	subflow->remote_token = remote_token;
-	subflow->remote_id = remote_id;
+	WRITE_ONCE(subflow->remote_id, remote_id);
 	subflow->request_join = 1;
 	subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP);
 	subflow->subflow_id = msk->subflow_id++;
@@ -1712,6 +1731,7 @@ static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk,
 	pr_debug("subflow=%p", ctx);
 
 	ctx->tcp_sock = sk;
+	WRITE_ONCE(ctx->local_id, -1);
 
 	return ctx;
 }
@@ -1743,10 +1763,9 @@ static void subflow_state_change(struct sock *sk)
 	msk = mptcp_sk(parent);
 	if (subflow_simultaneous_connect(sk)) {
 		mptcp_do_fallback(sk);
-		mptcp_rcv_space_init(msk, sk);
 		pr_fallback(msk);
 		subflow->conn_finished = 1;
-		mptcp_propagate_state(parent, sk);
+		mptcp_propagate_state(parent, sk, subflow, NULL);
 	}
 
 	/* as recvmsg() does not acquire the subflow socket for ssk selection
@@ -1948,14 +1967,14 @@ static void subflow_ulp_clone(const struct request_sock *req,
 		new_ctx->idsn = subflow_req->idsn;
 
 		/* this is the first subflow, id is always 0 */
-		new_ctx->local_id_valid = 1;
+		subflow_set_local_id(new_ctx, 0);
 	} else if (subflow_req->mp_join) {
 		new_ctx->ssn_offset = subflow_req->ssn_offset;
 		new_ctx->mp_join = 1;
 		new_ctx->fully_established = 1;
 		new_ctx->remote_key_valid = 1;
 		new_ctx->backup = subflow_req->backup;
-		new_ctx->remote_id = subflow_req->remote_id;
+		WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id);
 		new_ctx->token = subflow_req->token;
 		new_ctx->thmac = subflow_req->thmac;
 
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index 21f7860e8fa1..cb48a2b9cb9f 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -30,6 +30,7 @@
 #define mtype_del		IPSET_TOKEN(MTYPE, _del)
 #define mtype_list		IPSET_TOKEN(MTYPE, _list)
 #define mtype_gc		IPSET_TOKEN(MTYPE, _gc)
+#define mtype_cancel_gc		IPSET_TOKEN(MTYPE, _cancel_gc)
 #define mtype			MTYPE
 
 #define get_ext(set, map, id)	((map)->extensions + ((set)->dsize * (id)))
@@ -59,9 +60,6 @@ mtype_destroy(struct ip_set *set)
 {
 	struct mtype *map = set->data;
 
-	if (SET_WITH_TIMEOUT(set))
-		del_timer_sync(&map->gc);
-
 	if (set->dsize && set->extensions & IPSET_EXT_DESTROY)
 		mtype_ext_cleanup(set);
 	ip_set_free(map->members);
@@ -290,6 +288,15 @@ mtype_gc(struct timer_list *t)
 	add_timer(&map->gc);
 }
 
+static void
+mtype_cancel_gc(struct ip_set *set)
+{
+	struct mtype *map = set->data;
+
+	if (SET_WITH_TIMEOUT(set))
+		del_timer_sync(&map->gc);
+}
+
 static const struct ip_set_type_variant mtype = {
 	.kadt	= mtype_kadt,
 	.uadt	= mtype_uadt,
@@ -303,6 +310,7 @@ static const struct ip_set_type_variant mtype = {
 	.head	= mtype_head,
 	.list	= mtype_list,
 	.same_set = mtype_same_set,
+	.cancel_gc = mtype_cancel_gc,
 };
 
 #endif /* __IP_SET_BITMAP_IP_GEN_H */
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 4c133e06be1d..3184cc6be4c9 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1154,6 +1154,7 @@ static int ip_set_create(struct sk_buff *skb, const struct nfnl_info *info,
 	return ret;
 
 cleanup:
+	set->variant->cancel_gc(set);
 	set->variant->destroy(set);
 put_out:
 	module_put(set->type->me);
@@ -1182,6 +1183,14 @@ ip_set_destroy_set(struct ip_set *set)
 	kfree(set);
 }
 
+static void
+ip_set_destroy_set_rcu(struct rcu_head *head)
+{
+	struct ip_set *set = container_of(head, struct ip_set, rcu);
+
+	ip_set_destroy_set(set);
+}
+
 static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 			  const struct nlattr * const attr[])
 {
@@ -1193,8 +1202,6 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 	if (unlikely(protocol_min_failed(attr)))
 		return -IPSET_ERR_PROTOCOL;
 
-	/* Must wait for flush to be really finished in list:set */
-	rcu_barrier();
 
 	/* Commands are serialized and references are
 	 * protected by the ip_set_ref_lock.
@@ -1206,8 +1213,10 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 	 * counter, so if it's already zero, we can proceed
 	 * without holding the lock.
 	 */
-	read_lock_bh(&ip_set_ref_lock);
 	if (!attr[IPSET_ATTR_SETNAME]) {
+		/* Must wait for flush to be really finished in list:set */
+		rcu_barrier();
+		read_lock_bh(&ip_set_ref_lock);
 		for (i = 0; i < inst->ip_set_max; i++) {
 			s = ip_set(inst, i);
 			if (s && (s->ref || s->ref_netlink)) {
@@ -1221,6 +1230,8 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 			s = ip_set(inst, i);
 			if (s) {
 				ip_set(inst, i) = NULL;
+				/* Must cancel garbage collectors */
+				s->variant->cancel_gc(s);
 				ip_set_destroy_set(s);
 			}
 		}
@@ -1228,6 +1239,9 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 		inst->is_destroyed = false;
 	} else {
 		u32 flags = flag_exist(info->nlh);
+		u16 features = 0;
+
+		read_lock_bh(&ip_set_ref_lock);
 		s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]),
 				    &i);
 		if (!s) {
@@ -1238,10 +1252,16 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 			ret = -IPSET_ERR_BUSY;
 			goto out;
 		}
+		features = s->type->features;
 		ip_set(inst, i) = NULL;
 		read_unlock_bh(&ip_set_ref_lock);
-
-		ip_set_destroy_set(s);
+		if (features & IPSET_TYPE_NAME) {
+			/* Must wait for flush to be really finished  */
+			rcu_barrier();
+		}
+		/* Must cancel garbage collectors */
+		s->variant->cancel_gc(s);
+		call_rcu(&s->rcu, ip_set_destroy_set_rcu);
 	}
 	return 0;
 out:
@@ -1394,9 +1414,6 @@ static int ip_set_swap(struct sk_buff *skb, const struct nfnl_info *info,
 	ip_set(inst, to_id) = from;
 	write_unlock_bh(&ip_set_ref_lock);
 
-	/* Make sure all readers of the old set pointers are completed. */
-	synchronize_rcu();
-
 	return 0;
 }
 
@@ -2362,6 +2379,7 @@ ip_set_net_exit(struct net *net)
 		set = ip_set(inst, i);
 		if (set) {
 			ip_set(inst, i) = NULL;
+			set->variant->cancel_gc(set);
 			ip_set_destroy_set(set);
 		}
 	}
@@ -2409,8 +2427,11 @@ ip_set_fini(void)
 {
 	nf_unregister_sockopt(&so_set);
 	nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
-
 	unregister_pernet_subsys(&ip_set_net_ops);
+
+	/* Wait for call_rcu() in destroy */
+	rcu_barrier();
+
 	pr_debug("these are the famous last words\n");
 }
 
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index cbf80da9a01c..cf3ce72c3de6 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -222,6 +222,7 @@ static const union nf_inet_addr zeromask = {};
 #undef mtype_gc_do
 #undef mtype_gc
 #undef mtype_gc_init
+#undef mtype_cancel_gc
 #undef mtype_variant
 #undef mtype_data_match
 
@@ -266,6 +267,7 @@ static const union nf_inet_addr zeromask = {};
 #define mtype_gc_do		IPSET_TOKEN(MTYPE, _gc_do)
 #define mtype_gc		IPSET_TOKEN(MTYPE, _gc)
 #define mtype_gc_init		IPSET_TOKEN(MTYPE, _gc_init)
+#define mtype_cancel_gc		IPSET_TOKEN(MTYPE, _cancel_gc)
 #define mtype_variant		IPSET_TOKEN(MTYPE, _variant)
 #define mtype_data_match	IPSET_TOKEN(MTYPE, _data_match)
 
@@ -430,7 +432,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy)
 	u32 i;
 
 	for (i = 0; i < jhash_size(t->htable_bits); i++) {
-		n = __ipset_dereference(hbucket(t, i));
+		n = (__force struct hbucket *)hbucket(t, i);
 		if (!n)
 			continue;
 		if (set->extensions & IPSET_EXT_DESTROY && ext_destroy)
@@ -450,10 +452,7 @@ mtype_destroy(struct ip_set *set)
 	struct htype *h = set->data;
 	struct list_head *l, *lt;
 
-	if (SET_WITH_TIMEOUT(set))
-		cancel_delayed_work_sync(&h->gc.dwork);
-
-	mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true);
+	mtype_ahash_destroy(set, (__force struct htable *)h->table, true);
 	list_for_each_safe(l, lt, &h->ad) {
 		list_del(l);
 		kfree(l);
@@ -599,6 +598,15 @@ mtype_gc_init(struct htable_gc *gc)
 	queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ);
 }
 
+static void
+mtype_cancel_gc(struct ip_set *set)
+{
+	struct htype *h = set->data;
+
+	if (SET_WITH_TIMEOUT(set))
+		cancel_delayed_work_sync(&h->gc.dwork);
+}
+
 static int
 mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	  struct ip_set_ext *mext, u32 flags);
@@ -1441,6 +1449,7 @@ static const struct ip_set_type_variant mtype_variant = {
 	.uref	= mtype_uref,
 	.resize	= mtype_resize,
 	.same_set = mtype_same_set,
+	.cancel_gc = mtype_cancel_gc,
 	.region_lock = true,
 };
 
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 95aeb31c60e0..30a655e5c4fd 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -138,9 +138,9 @@ hash_netiface4_data_next(struct hash_netiface4_elem *next,
 #include "ip_set_hash_gen.h"
 
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-static const char *get_physindev_name(const struct sk_buff *skb)
+static const char *get_physindev_name(const struct sk_buff *skb, struct net *net)
 {
-	struct net_device *dev = nf_bridge_get_physindev(skb);
+	struct net_device *dev = nf_bridge_get_physindev(skb, net);
 
 	return dev ? dev->name : NULL;
 }
@@ -177,7 +177,7 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb,
 
 	if (opt->cmdflags & IPSET_FLAG_PHYSDEV) {
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-		const char *eiface = SRCDIR ? get_physindev_name(skb) :
+		const char *eiface = SRCDIR ? get_physindev_name(skb, xt_net(par)) :
 					      get_physoutdev_name(skb);
 
 		if (!eiface)
@@ -395,7 +395,7 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb,
 
 	if (opt->cmdflags & IPSET_FLAG_PHYSDEV) {
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-		const char *eiface = SRCDIR ? get_physindev_name(skb) :
+		const char *eiface = SRCDIR ? get_physindev_name(skb, xt_net(par)) :
 					      get_physoutdev_name(skb);
 
 		if (!eiface)
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index e162636525cf..6c3f28bc59b3 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -426,9 +426,6 @@ list_set_destroy(struct ip_set *set)
 	struct list_set *map = set->data;
 	struct set_elem *e, *n;
 
-	if (SET_WITH_TIMEOUT(set))
-		timer_shutdown_sync(&map->gc);
-
 	list_for_each_entry_safe(e, n, &map->members, list) {
 		list_del(&e->list);
 		ip_set_put_byindex(map->net, e->id);
@@ -545,6 +542,15 @@ list_set_same_set(const struct ip_set *a, const struct ip_set *b)
 	       a->extensions == b->extensions;
 }
 
+static void
+list_set_cancel_gc(struct ip_set *set)
+{
+	struct list_set *map = set->data;
+
+	if (SET_WITH_TIMEOUT(set))
+		timer_shutdown_sync(&map->gc);
+}
+
 static const struct ip_set_type_variant set_variant = {
 	.kadt	= list_set_kadt,
 	.uadt	= list_set_uadt,
@@ -558,6 +564,7 @@ static const struct ip_set_type_variant set_variant = {
 	.head	= list_set_head,
 	.list	= list_set_list,
 	.same_set = list_set_same_set,
+	.cancel_gc = list_set_cancel_gc,
 };
 
 static void
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 9193e109e6b3..65e0259178da 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -271,7 +271,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs,
 			skb->dev = dst->dev;
 			icmpv6_send(skb, ICMPV6_TIME_EXCEED,
 				    ICMPV6_EXC_HOPLIMIT, 0);
-			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
+			IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
 
 			return false;
 		}
@@ -286,7 +286,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs,
 	{
 		if (ip_hdr(skb)->ttl <= 1) {
 			/* Tell the sender its packet died... */
-			__IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS);
+			IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS);
 			icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
 			return false;
 		}
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 2e5f3864d353..5b876fa7f9af 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -2756,6 +2756,7 @@ static const struct nf_ct_hook nf_conntrack_hook = {
 	.get_tuple_skb  = nf_conntrack_get_tuple_skb,
 	.attach		= nf_conntrack_attach,
 	.set_closing	= nf_conntrack_set_closing,
+	.confirm	= __nf_conntrack_confirm,
 };
 
 void nf_conntrack_init_end(void)
diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c
index e697a824b001..540d97715bd2 100644
--- a/net/netfilter/nf_conntrack_h323_asn1.c
+++ b/net/netfilter/nf_conntrack_h323_asn1.c
@@ -533,6 +533,8 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f,
 	/* Get fields bitmap */
 	if (nf_h323_error_boundary(bs, 0, f->sz))
 		return H323_ERROR_BOUND;
+	if (f->sz > 32)
+		return H323_ERROR_RANGE;
 	bmp = get_bitmap(bs, f->sz);
 	if (base)
 		*(unsigned int *)base = bmp;
@@ -589,6 +591,8 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f,
 	bmp2_len = get_bits(bs, 7) + 1;
 	if (nf_h323_error_boundary(bs, 0, bmp2_len))
 		return H323_ERROR_BOUND;
+	if (bmp2_len > 32)
+		return H323_ERROR_RANGE;
 	bmp2 = get_bitmap(bs, bmp2_len);
 	bmp |= bmp2 >> f->sz;
 	if (base)
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 0c22a02c2035..3b846cbdc050 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -876,6 +876,7 @@ struct ctnetlink_filter_u32 {
 
 struct ctnetlink_filter {
 	u8 family;
+	bool zone_filter;
 
 	u_int32_t orig_flags;
 	u_int32_t reply_flags;
@@ -992,9 +993,12 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family)
 	if (err)
 		goto err_filter;
 
-	err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone);
-	if (err < 0)
-		goto err_filter;
+	if (cda[CTA_ZONE]) {
+		err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone);
+		if (err < 0)
+			goto err_filter;
+		filter->zone_filter = true;
+	}
 
 	if (!cda[CTA_FILTER])
 		return filter;
@@ -1148,7 +1152,7 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data)
 	if (filter->family && nf_ct_l3num(ct) != filter->family)
 		goto ignore_entry;
 
-	if (filter->zone.id != NF_CT_DEFAULT_ZONE_ID &&
+	if (filter->zone_filter &&
 	    !nf_ct_zone_equal_any(ct, &filter->zone))
 		goto ignore_entry;
 
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index c6bd533983c1..4cc97f971264 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -283,7 +283,7 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb,
 			pr_debug("Setting vtag %x for secondary conntrack\n",
 				 sh->vtag);
 			ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = sh->vtag;
-		} else {
+		} else if (sch->type == SCTP_CID_SHUTDOWN_ACK) {
 		/* If it is a shutdown ack OOTB packet, we expect a return
 		   shutdown complete, otherwise an ABORT Sec 8.4 (5) and (8) */
 			pr_debug("Setting vtag %x for new conn OOTB\n",
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index e573be5afde7..ae493599a3ef 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -457,7 +457,8 @@ static void tcp_init_sender(struct ip_ct_tcp_state *sender,
 			    const struct sk_buff *skb,
 			    unsigned int dataoff,
 			    const struct tcphdr *tcph,
-			    u32 end, u32 win)
+			    u32 end, u32 win,
+			    enum ip_conntrack_dir dir)
 {
 	/* SYN-ACK in reply to a SYN
 	 * or SYN from reply direction in simultaneous open.
@@ -471,7 +472,8 @@ static void tcp_init_sender(struct ip_ct_tcp_state *sender,
 	 * Both sides must send the Window Scale option
 	 * to enable window scaling in either direction.
 	 */
-	if (!(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE &&
+	if (dir == IP_CT_DIR_REPLY &&
+	    !(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE &&
 	      receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE)) {
 		sender->td_scale = 0;
 		receiver->td_scale = 0;
@@ -542,7 +544,7 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir,
 		if (tcph->syn) {
 			tcp_init_sender(sender, receiver,
 					skb, dataoff, tcph,
-					end, win);
+					end, win, dir);
 			if (!tcph->ack)
 				/* Simultaneous open */
 				return NFCT_TCP_ACCEPT;
@@ -585,7 +587,7 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir,
 		 */
 		tcp_init_sender(sender, receiver,
 				skb, dataoff, tcph,
-				end, win);
+				end, win, dir);
 
 		if (dir == IP_CT_DIR_REPLY && !tcph->ack)
 			return NFCT_TCP_ACCEPT;
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 920a5a29ae1d..a0571339239c 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -87,12 +87,22 @@ static u32 flow_offload_dst_cookie(struct flow_offload_tuple *flow_tuple)
 	return 0;
 }
 
+static struct dst_entry *nft_route_dst_fetch(struct nf_flow_route *route,
+					     enum flow_offload_tuple_dir dir)
+{
+	struct dst_entry *dst = route->tuple[dir].dst;
+
+	route->tuple[dir].dst = NULL;
+
+	return dst;
+}
+
 static int flow_offload_fill_route(struct flow_offload *flow,
-				   const struct nf_flow_route *route,
+				   struct nf_flow_route *route,
 				   enum flow_offload_tuple_dir dir)
 {
 	struct flow_offload_tuple *flow_tuple = &flow->tuplehash[dir].tuple;
-	struct dst_entry *dst = route->tuple[dir].dst;
+	struct dst_entry *dst = nft_route_dst_fetch(route, dir);
 	int i, j = 0;
 
 	switch (flow_tuple->l3proto) {
@@ -122,6 +132,7 @@ static int flow_offload_fill_route(struct flow_offload *flow,
 		       ETH_ALEN);
 		flow_tuple->out.ifidx = route->tuple[dir].out.ifindex;
 		flow_tuple->out.hw_ifidx = route->tuple[dir].out.hw_ifindex;
+		dst_release(dst);
 		break;
 	case FLOW_OFFLOAD_XMIT_XFRM:
 	case FLOW_OFFLOAD_XMIT_NEIGH:
@@ -146,7 +157,7 @@ static void nft_flow_dst_release(struct flow_offload *flow,
 }
 
 void flow_offload_route_init(struct flow_offload *flow,
-			    const struct nf_flow_route *route)
+			     struct nf_flow_route *route)
 {
 	flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL);
 	flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY);
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 8cc52d2bd31b..e16f158388bb 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -193,11 +193,12 @@ void nf_logger_put(int pf, enum nf_log_type type)
 		return;
 	}
 
-	BUG_ON(loggers[pf][type] == NULL);
-
 	rcu_read_lock();
 	logger = rcu_dereference(loggers[pf][type]);
-	module_put(logger->me);
+	if (!logger)
+		WARN_ON_ONCE(1);
+	else
+		module_put(logger->me);
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(nf_logger_put);
diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c
index c66689ad2b49..58402226045e 100644
--- a/net/netfilter/nf_log_syslog.c
+++ b/net/netfilter/nf_log_syslog.c
@@ -111,7 +111,8 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u8 pf,
 			  unsigned int hooknum, const struct sk_buff *skb,
 			  const struct net_device *in,
 			  const struct net_device *out,
-			  const struct nf_loginfo *loginfo, const char *prefix)
+			  const struct nf_loginfo *loginfo, const char *prefix,
+			  struct net *net)
 {
 	const struct net_device *physoutdev __maybe_unused;
 	const struct net_device *physindev __maybe_unused;
@@ -121,7 +122,7 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u8 pf,
 			in ? in->name : "",
 			out ? out->name : "");
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	physindev = nf_bridge_get_physindev(skb);
+	physindev = nf_bridge_get_physindev(skb, net);
 	if (physindev && in != physindev)
 		nf_log_buf_add(m, "PHYSIN=%s ", physindev->name);
 	physoutdev = nf_bridge_get_physoutdev(skb);
@@ -148,7 +149,7 @@ static void nf_log_arp_packet(struct net *net, u_int8_t pf,
 		loginfo = &default_loginfo;
 
 	nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo,
-				  prefix);
+				  prefix, net);
 	dump_arp_packet(m, loginfo, skb, skb_network_offset(skb));
 
 	nf_log_buf_close(m);
@@ -845,7 +846,7 @@ static void nf_log_ip_packet(struct net *net, u_int8_t pf,
 		loginfo = &default_loginfo;
 
 	nf_log_dump_packet_common(m, pf, hooknum, skb, in,
-				  out, loginfo, prefix);
+				  out, loginfo, prefix, net);
 
 	if (in)
 		dump_mac_header(m, loginfo, skb);
@@ -880,7 +881,7 @@ static void nf_log_ip6_packet(struct net *net, u_int8_t pf,
 		loginfo = &default_loginfo;
 
 	nf_log_dump_packet_common(m, pf, hooknum, skb, in, out,
-				  loginfo, prefix);
+				  loginfo, prefix, net);
 
 	if (in)
 		dump_mac_header(m, loginfo, skb);
@@ -916,7 +917,7 @@ static void nf_log_unknown_packet(struct net *net, u_int8_t pf,
 		loginfo = &default_loginfo;
 
 	nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo,
-				  prefix);
+				  prefix, net);
 
 	dump_mac_header(m, loginfo, skb);
 
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index c3d7ecbc777c..016c816d91cb 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -551,8 +551,11 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple,
 find_free_id:
 	if (range->flags & NF_NAT_RANGE_PROTO_OFFSET)
 		off = (ntohs(*keyptr) - ntohs(range->base_proto.all));
-	else
+	else if ((range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL) ||
+		 maniptype != NF_NAT_MANIP_DST)
 		off = get_random_u16();
+	else
+		off = 0;
 
 	attempts = range_size;
 	if (attempts > NF_NAT_MAX_ATTEMPTS)
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 63d1516816b1..e2f334f70281 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -82,11 +82,9 @@ static void __nf_queue_entry_init_physdevs(struct nf_queue_entry *entry)
 {
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	const struct sk_buff *skb = entry->skb;
-	struct nf_bridge_info *nf_bridge;
 
-	nf_bridge = nf_bridge_info_get(skb);
-	if (nf_bridge) {
-		entry->physin = nf_bridge_get_physindev(skb);
+	if (nf_bridge_info_exists(skb)) {
+		entry->physin = nf_bridge_get_physindev(skb, entry->state.net);
 		entry->physout = nf_bridge_get_physoutdev(skb);
 	} else {
 		entry->physin = NULL;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 8438a8922e4a..1683dc196b59 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -24,6 +24,7 @@
 #include <net/sock.h>
 
 #define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-"))
+#define NFT_SET_MAX_ANONLEN 16
 
 unsigned int nf_tables_net_id __read_mostly;
 
@@ -683,15 +684,16 @@ static int nft_delobj(struct nft_ctx *ctx, struct nft_object *obj)
 	return err;
 }
 
-static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type,
-				   struct nft_flowtable *flowtable)
+static struct nft_trans *
+nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type,
+		        struct nft_flowtable *flowtable)
 {
 	struct nft_trans *trans;
 
 	trans = nft_trans_alloc(ctx, msg_type,
 				sizeof(struct nft_trans_flowtable));
 	if (trans == NULL)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	if (msg_type == NFT_MSG_NEWFLOWTABLE)
 		nft_activate_next(ctx->net, flowtable);
@@ -700,22 +702,22 @@ static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type,
 	nft_trans_flowtable(trans) = flowtable;
 	nft_trans_commit_list_add_tail(ctx->net, trans);
 
-	return 0;
+	return trans;
 }
 
 static int nft_delflowtable(struct nft_ctx *ctx,
 			    struct nft_flowtable *flowtable)
 {
-	int err;
+	struct nft_trans *trans;
 
-	err = nft_trans_flowtable_add(ctx, NFT_MSG_DELFLOWTABLE, flowtable);
-	if (err < 0)
-		return err;
+	trans = nft_trans_flowtable_add(ctx, NFT_MSG_DELFLOWTABLE, flowtable);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
 
 	nft_deactivate_next(ctx->net, flowtable);
 	nft_use_dec(&ctx->table->use);
 
-	return err;
+	return 0;
 }
 
 static void __nft_reg_track_clobber(struct nft_regs_track *track, u8 dreg)
@@ -1250,6 +1252,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx)
 	return 0;
 
 err_register_hooks:
+	ctx->table->flags |= NFT_TABLE_F_DORMANT;
 	nft_trans_destroy(trans);
 	return ret;
 }
@@ -2079,7 +2082,7 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net,
 	struct nft_hook *hook;
 	int err;
 
-	hook = kmalloc(sizeof(struct nft_hook), GFP_KERNEL_ACCOUNT);
+	hook = kzalloc(sizeof(struct nft_hook), GFP_KERNEL_ACCOUNT);
 	if (!hook) {
 		err = -ENOMEM;
 		goto err_hook_alloc;
@@ -2502,19 +2505,15 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 	RCU_INIT_POINTER(chain->blob_gen_0, blob);
 	RCU_INIT_POINTER(chain->blob_gen_1, blob);
 
-	err = nf_tables_register_hook(net, table, chain);
-	if (err < 0)
-		goto err_destroy_chain;
-
 	if (!nft_use_inc(&table->use)) {
 		err = -EMFILE;
-		goto err_use;
+		goto err_destroy_chain;
 	}
 
 	trans = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN);
 	if (IS_ERR(trans)) {
 		err = PTR_ERR(trans);
-		goto err_unregister_hook;
+		goto err_trans;
 	}
 
 	nft_trans_chain_policy(trans) = NFT_CHAIN_POLICY_UNSET;
@@ -2522,17 +2521,22 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 		nft_trans_chain_policy(trans) = policy;
 
 	err = nft_chain_add(table, chain);
-	if (err < 0) {
-		nft_trans_destroy(trans);
-		goto err_unregister_hook;
-	}
+	if (err < 0)
+		goto err_chain_add;
+
+	/* This must be LAST to ensure no packets are walking over this chain. */
+	err = nf_tables_register_hook(net, table, chain);
+	if (err < 0)
+		goto err_register_hook;
 
 	return 0;
 
-err_unregister_hook:
+err_register_hook:
+	nft_chain_del(chain);
+err_chain_add:
+	nft_trans_destroy(trans);
+err_trans:
 	nft_use_dec_restore(&table->use);
-err_use:
-	nf_tables_unregister_hook(net, table, chain);
 err_destroy_chain:
 	nf_tables_chain_destroy(ctx);
 
@@ -2977,6 +2981,9 @@ static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info,
  */
 int nft_register_expr(struct nft_expr_type *type)
 {
+	if (WARN_ON_ONCE(type->maxattr > NFT_EXPR_MAXATTR))
+		return -ENOMEM;
+
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
 	if (type->family == NFPROTO_UNSPEC)
 		list_add_tail_rcu(&type->list, &nf_tables_expressions);
@@ -3271,14 +3278,13 @@ int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src)
 {
 	int err;
 
-	if (src->ops->clone) {
-		dst->ops = src->ops;
-		err = src->ops->clone(dst, src);
-		if (err < 0)
-			return err;
-	} else {
-		memcpy(dst, src, src->ops->size);
-	}
+	if (WARN_ON_ONCE(!src->ops->clone))
+		return -EINVAL;
+
+	dst->ops = src->ops;
+	err = src->ops->clone(dst, src);
+	if (err < 0)
+		return err;
 
 	__module_get(src->ops->type->owner);
 
@@ -4411,6 +4417,9 @@ static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set,
 		if (p[1] != 'd' || strchr(p + 2, '%'))
 			return -EINVAL;
 
+		if (strnlen(name, NFT_SET_MAX_ANONLEN) >= NFT_SET_MAX_ANONLEN)
+			return -EINVAL;
+
 		inuse = (unsigned long *)get_zeroed_page(GFP_KERNEL);
 		if (inuse == NULL)
 			return -ENOMEM;
@@ -4811,8 +4820,8 @@ static int nft_set_desc_concat_parse(const struct nlattr *attr,
 static int nft_set_desc_concat(struct nft_set_desc *desc,
 			       const struct nlattr *nla)
 {
+	u32 num_regs = 0, key_num_regs = 0;
 	struct nlattr *attr;
-	u32 num_regs = 0;
 	int rem, err, i;
 
 	nla_for_each_nested(attr, nla, rem) {
@@ -4827,6 +4836,10 @@ static int nft_set_desc_concat(struct nft_set_desc *desc,
 	for (i = 0; i < desc->field_count; i++)
 		num_regs += DIV_ROUND_UP(desc->field_len[i], sizeof(u32));
 
+	key_num_regs = DIV_ROUND_UP(desc->klen, sizeof(u32));
+	if (key_num_regs != num_regs)
+		return -EINVAL;
+
 	if (num_regs > NFT_REG32_COUNT)
 		return -E2BIG;
 
@@ -4988,6 +5001,12 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
 		if ((flags & (NFT_SET_EVAL | NFT_SET_OBJECT)) ==
 			     (NFT_SET_EVAL | NFT_SET_OBJECT))
 			return -EOPNOTSUPP;
+		if ((flags & (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT | NFT_SET_EVAL)) ==
+			     (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT))
+			return -EOPNOTSUPP;
+		if ((flags & (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) ==
+			     (NFT_SET_CONSTANT | NFT_SET_TIMEOUT))
+			return -EOPNOTSUPP;
 	}
 
 	desc.dtype = 0;
@@ -5048,16 +5067,28 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
 	}
 
 	desc.policy = NFT_SET_POL_PERFORMANCE;
-	if (nla[NFTA_SET_POLICY] != NULL)
+	if (nla[NFTA_SET_POLICY] != NULL) {
 		desc.policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY]));
+		switch (desc.policy) {
+		case NFT_SET_POL_PERFORMANCE:
+		case NFT_SET_POL_MEMORY:
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+	}
 
 	if (nla[NFTA_SET_DESC] != NULL) {
 		err = nf_tables_set_desc_parse(&desc, nla[NFTA_SET_DESC]);
 		if (err < 0)
 			return err;
 
-		if (desc.field_count > 1 && !(flags & NFT_SET_CONCAT))
+		if (desc.field_count > 1) {
+			if (!(flags & NFT_SET_CONCAT))
+				return -EINVAL;
+		} else if (flags & NFT_SET_CONCAT) {
 			return -EINVAL;
+		}
 	} else if (flags & NFT_SET_CONCAT) {
 		return -EINVAL;
 	}
@@ -5399,6 +5430,7 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
 
 	if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) {
 		list_del_rcu(&set->list);
+		set->dead = 1;
 		if (event)
 			nf_tables_set_notify(ctx, set, NFT_MSG_DELSET,
 					     GFP_KERNEL);
@@ -5704,7 +5736,7 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx,
 	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv);
 	struct nft_set_dump_args *args;
 
-	if (nft_set_elem_expired(ext))
+	if (nft_set_elem_expired(ext) || nft_set_elem_is_dead(ext))
 		return 0;
 
 	args = container_of(iter, struct nft_set_dump_args, iter);
@@ -6568,7 +6600,7 @@ static int nft_setelem_catchall_deactivate(const struct net *net,
 
 	list_for_each_entry(catchall, &set->catchall_list, list) {
 		ext = nft_set_elem_ext(set, catchall->elem);
-		if (!nft_is_active(net, ext))
+		if (!nft_is_active_next(net, ext))
 			continue;
 
 		kfree(elem->priv);
@@ -7529,11 +7561,15 @@ nla_put_failure:
 	return -1;
 }
 
-static const struct nft_object_type *__nft_obj_type_get(u32 objtype)
+static const struct nft_object_type *__nft_obj_type_get(u32 objtype, u8 family)
 {
 	const struct nft_object_type *type;
 
 	list_for_each_entry(type, &nf_tables_objects, list) {
+		if (type->family != NFPROTO_UNSPEC &&
+		    type->family != family)
+			continue;
+
 		if (objtype == type->type)
 			return type;
 	}
@@ -7541,11 +7577,11 @@ static const struct nft_object_type *__nft_obj_type_get(u32 objtype)
 }
 
 static const struct nft_object_type *
-nft_obj_type_get(struct net *net, u32 objtype)
+nft_obj_type_get(struct net *net, u32 objtype, u8 family)
 {
 	const struct nft_object_type *type;
 
-	type = __nft_obj_type_get(objtype);
+	type = __nft_obj_type_get(objtype, family);
 	if (type != NULL && try_module_get(type->owner))
 		return type;
 
@@ -7638,7 +7674,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info,
 		if (info->nlh->nlmsg_flags & NLM_F_REPLACE)
 			return -EOPNOTSUPP;
 
-		type = __nft_obj_type_get(objtype);
+		type = __nft_obj_type_get(objtype, family);
 		if (WARN_ON_ONCE(!type))
 			return -ENOENT;
 
@@ -7652,7 +7688,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info,
 	if (!nft_use_inc(&table->use))
 		return -EMFILE;
 
-	type = nft_obj_type_get(net, objtype);
+	type = nft_obj_type_get(net, objtype, family);
 	if (IS_ERR(type)) {
 		err = PTR_ERR(type);
 		goto err_type;
@@ -8429,9 +8465,9 @@ static int nf_tables_newflowtable(struct sk_buff *skb,
 	u8 family = info->nfmsg->nfgen_family;
 	const struct nf_flowtable_type *type;
 	struct nft_flowtable *flowtable;
-	struct nft_hook *hook, *next;
 	struct net *net = info->net;
 	struct nft_table *table;
+	struct nft_trans *trans;
 	struct nft_ctx ctx;
 	int err;
 
@@ -8511,34 +8547,34 @@ static int nf_tables_newflowtable(struct sk_buff *skb,
 	err = nft_flowtable_parse_hook(&ctx, nla, &flowtable_hook, flowtable,
 				       extack, true);
 	if (err < 0)
-		goto err4;
+		goto err_flowtable_parse_hooks;
 
 	list_splice(&flowtable_hook.list, &flowtable->hook_list);
 	flowtable->data.priority = flowtable_hook.priority;
 	flowtable->hooknum = flowtable_hook.num;
 
+	trans = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable);
+	if (IS_ERR(trans)) {
+		err = PTR_ERR(trans);
+		goto err_flowtable_trans;
+	}
+
+	/* This must be LAST to ensure no packets are walking over this flowtable. */
 	err = nft_register_flowtable_net_hooks(ctx.net, table,
 					       &flowtable->hook_list,
 					       flowtable);
-	if (err < 0) {
-		nft_hooks_destroy(&flowtable->hook_list);
-		goto err4;
-	}
-
-	err = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable);
 	if (err < 0)
-		goto err5;
+		goto err_flowtable_hooks;
 
 	list_add_tail_rcu(&flowtable->list, &table->flowtables);
 
 	return 0;
-err5:
-	list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) {
-		nft_unregister_flowtable_hook(net, flowtable, hook);
-		list_del_rcu(&hook->list);
-		kfree_rcu(hook, rcu);
-	}
-err4:
+
+err_flowtable_hooks:
+	nft_trans_destroy(trans);
+err_flowtable_trans:
+	nft_hooks_destroy(&flowtable->hook_list);
+err_flowtable_parse_hooks:
 	flowtable->data.type->free(&flowtable->data);
 err3:
 	module_put(type->owner);
@@ -9801,6 +9837,7 @@ dead_elem:
 struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc)
 {
 	struct nft_set_elem_catchall *catchall, *next;
+	u64 tstamp = nft_net_tstamp(gc->net);
 	const struct nft_set *set = gc->set;
 	struct nft_elem_priv *elem_priv;
 	struct nft_set_ext *ext;
@@ -9810,7 +9847,7 @@ struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc)
 	list_for_each_entry_safe(catchall, next, &set->catchall_list, list) {
 		ext = nft_set_elem_ext(set, catchall->elem);
 
-		if (!nft_set_elem_expired(ext))
+		if (!__nft_set_elem_expired(ext, tstamp))
 			continue;
 
 		gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
@@ -10596,6 +10633,7 @@ static bool nf_tables_valid_genid(struct net *net, u32 genid)
 	bool genid_ok;
 
 	mutex_lock(&nft_net->commit_mutex);
+	nft_net->tstamp = get_jiffies_64();
 
 	genid_ok = genid == 0 || nft_net->base_seq == genid;
 	if (!genid_ok)
@@ -10970,16 +11008,10 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 	data->verdict.code = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE]));
 
 	switch (data->verdict.code) {
-	default:
-		switch (data->verdict.code & NF_VERDICT_MASK) {
-		case NF_ACCEPT:
-		case NF_DROP:
-		case NF_QUEUE:
-			break;
-		default:
-			return -EINVAL;
-		}
-		fallthrough;
+	case NF_ACCEPT:
+	case NF_DROP:
+	case NF_QUEUE:
+		break;
 	case NFT_CONTINUE:
 	case NFT_BREAK:
 	case NFT_RETURN:
@@ -11014,6 +11046,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 
 		data->verdict.chain = chain;
 		break;
+	default:
+		return -EINVAL;
 	}
 
 	desc->len = sizeof(data->verdict);
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index f03f4d4d7d88..134e05d31061 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -508,7 +508,7 @@ __build_packet_message(struct nfnl_log_net *log,
 					 htonl(br_port_get_rcu(indev)->br->dev->ifindex)))
 				goto nla_put_failure;
 		} else {
-			struct net_device *physindev;
+			int physinif;
 
 			/* Case 2: indev is bridge group, we need to look for
 			 * physical device (when called from ipv4) */
@@ -516,10 +516,10 @@ __build_packet_message(struct nfnl_log_net *log,
 					 htonl(indev->ifindex)))
 				goto nla_put_failure;
 
-			physindev = nf_bridge_get_physindev(skb);
-			if (physindev &&
+			physinif = nf_bridge_get_physinif(skb);
+			if (physinif &&
 			    nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSINDEV,
-					 htonl(physindev->ifindex)))
+					 htonl(physinif)))
 				goto nla_put_failure;
 		}
 #endif
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 171d1f52d3dd..5cf38fc0a366 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -232,18 +232,25 @@ static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict)
 	if (verdict == NF_ACCEPT ||
 	    verdict == NF_REPEAT ||
 	    verdict == NF_STOP) {
+		unsigned int ct_verdict = verdict;
+
 		rcu_read_lock();
 		ct_hook = rcu_dereference(nf_ct_hook);
 		if (ct_hook)
-			verdict = ct_hook->update(entry->state.net, entry->skb);
+			ct_verdict = ct_hook->update(entry->state.net, entry->skb);
 		rcu_read_unlock();
 
-		switch (verdict & NF_VERDICT_MASK) {
+		switch (ct_verdict & NF_VERDICT_MASK) {
+		case NF_ACCEPT:
+			/* follow userspace verdict, could be REPEAT */
+			break;
 		case NF_STOLEN:
 			nf_queue_entry_free(entry);
 			return;
+		default:
+			verdict = ct_verdict & NF_VERDICT_MASK;
+			break;
 		}
-
 	}
 	nf_reinject(entry, verdict);
 }
diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c
index 680fe557686e..274b6f7e6bb5 100644
--- a/net/netfilter/nft_chain_filter.c
+++ b/net/netfilter/nft_chain_filter.c
@@ -357,9 +357,10 @@ static int nf_tables_netdev_event(struct notifier_block *this,
 				  unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct nft_base_chain *basechain;
 	struct nftables_pernet *nft_net;
-	struct nft_table *table;
 	struct nft_chain *chain, *nr;
+	struct nft_table *table;
 	struct nft_ctx ctx = {
 		.net	= dev_net(dev),
 	};
@@ -371,7 +372,8 @@ static int nf_tables_netdev_event(struct notifier_block *this,
 	nft_net = nft_pernet(ctx.net);
 	mutex_lock(&nft_net->commit_mutex);
 	list_for_each_entry(table, &nft_net->tables, list) {
-		if (table->family != NFPROTO_NETDEV)
+		if (table->family != NFPROTO_NETDEV &&
+		    table->family != NFPROTO_INET)
 			continue;
 
 		ctx.family = table->family;
@@ -380,6 +382,11 @@ static int nf_tables_netdev_event(struct notifier_block *this,
 			if (!nft_is_base_chain(chain))
 				continue;
 
+			basechain = nft_base_chain(chain);
+			if (table->family == NFPROTO_INET &&
+			    basechain->ops.hooknum != NF_INET_INGRESS)
+				continue;
+
 			ctx.chain = chain;
 			nft_netdev_event(event, dev, &ctx);
 		}
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 5284cd2ad532..d3d11dede545 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -135,7 +135,7 @@ static void nft_target_eval_bridge(const struct nft_expr *expr,
 
 static const struct nla_policy nft_target_policy[NFTA_TARGET_MAX + 1] = {
 	[NFTA_TARGET_NAME]	= { .type = NLA_NUL_STRING },
-	[NFTA_TARGET_REV]	= { .type = NLA_U32 },
+	[NFTA_TARGET_REV]	= NLA_POLICY_MAX(NLA_BE32, 255),
 	[NFTA_TARGET_INFO]	= { .type = NLA_BINARY },
 };
 
@@ -200,6 +200,7 @@ static const struct nla_policy nft_rule_compat_policy[NFTA_RULE_COMPAT_MAX + 1]
 static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv)
 {
 	struct nlattr *tb[NFTA_RULE_COMPAT_MAX+1];
+	u32 l4proto;
 	u32 flags;
 	int err;
 
@@ -212,12 +213,18 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv)
 		return -EINVAL;
 
 	flags = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_FLAGS]));
-	if (flags & ~NFT_RULE_COMPAT_F_MASK)
+	if (flags & NFT_RULE_COMPAT_F_UNUSED ||
+	    flags & ~NFT_RULE_COMPAT_F_MASK)
 		return -EINVAL;
 	if (flags & NFT_RULE_COMPAT_F_INV)
 		*inv = true;
 
-	*proto = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO]));
+	l4proto = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO]));
+	if (l4proto > U16_MAX)
+		return -EINVAL;
+
+	*proto = l4proto;
+
 	return 0;
 }
 
@@ -350,6 +357,22 @@ static int nft_target_validate(const struct nft_ctx *ctx,
 	unsigned int hook_mask = 0;
 	int ret;
 
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET &&
+	    ctx->family != NFPROTO_BRIDGE &&
+	    ctx->family != NFPROTO_ARP)
+		return -EOPNOTSUPP;
+
+	ret = nft_chain_validate_hooks(ctx->chain,
+				       (1 << NF_INET_PRE_ROUTING) |
+				       (1 << NF_INET_LOCAL_IN) |
+				       (1 << NF_INET_FORWARD) |
+				       (1 << NF_INET_LOCAL_OUT) |
+				       (1 << NF_INET_POST_ROUTING));
+	if (ret)
+		return ret;
+
 	if (nft_is_base_chain(ctx->chain)) {
 		const struct nft_base_chain *basechain =
 						nft_base_chain(ctx->chain);
@@ -413,7 +436,7 @@ static void nft_match_eval(const struct nft_expr *expr,
 
 static const struct nla_policy nft_match_policy[NFTA_MATCH_MAX + 1] = {
 	[NFTA_MATCH_NAME]	= { .type = NLA_NUL_STRING },
-	[NFTA_MATCH_REV]	= { .type = NLA_U32 },
+	[NFTA_MATCH_REV]	= NLA_POLICY_MAX(NLA_BE32, 255),
 	[NFTA_MATCH_INFO]	= { .type = NLA_BINARY },
 };
 
@@ -595,6 +618,22 @@ static int nft_match_validate(const struct nft_ctx *ctx,
 	unsigned int hook_mask = 0;
 	int ret;
 
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET &&
+	    ctx->family != NFPROTO_BRIDGE &&
+	    ctx->family != NFPROTO_ARP)
+		return -EOPNOTSUPP;
+
+	ret = nft_chain_validate_hooks(ctx->chain,
+				       (1 << NF_INET_PRE_ROUTING) |
+				       (1 << NF_INET_LOCAL_IN) |
+				       (1 << NF_INET_FORWARD) |
+				       (1 << NF_INET_LOCAL_OUT) |
+				       (1 << NF_INET_POST_ROUTING));
+	if (ret)
+		return ret;
+
 	if (nft_is_base_chain(ctx->chain)) {
 		const struct nft_base_chain *basechain =
 						nft_base_chain(ctx->chain);
@@ -712,7 +751,7 @@ out_put:
 static const struct nla_policy nfnl_compat_policy_get[NFTA_COMPAT_MAX+1] = {
 	[NFTA_COMPAT_NAME]	= { .type = NLA_NUL_STRING,
 				    .len = NFT_COMPAT_NAME_MAX-1 },
-	[NFTA_COMPAT_REV]	= { .type = NLA_U32 },
+	[NFTA_COMPAT_REV]	= NLA_POLICY_MAX(NLA_BE32, 255),
 	[NFTA_COMPAT_TYPE]	= { .type = NLA_U32 },
 };
 
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 86bb9d7797d9..255640013ab8 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -476,6 +476,9 @@ static int nft_ct_get_init(const struct nft_ctx *ctx,
 		break;
 #endif
 	case NFT_CT_ID:
+		if (tb[NFTA_CT_DIRECTION])
+			return -EINVAL;
+
 		len = sizeof(u32);
 		break;
 	default:
@@ -1250,7 +1253,30 @@ static int nft_ct_expect_obj_init(const struct nft_ctx *ctx,
 	if (tb[NFTA_CT_EXPECT_L3PROTO])
 		priv->l3num = ntohs(nla_get_be16(tb[NFTA_CT_EXPECT_L3PROTO]));
 
+	switch (priv->l3num) {
+	case NFPROTO_IPV4:
+	case NFPROTO_IPV6:
+		if (priv->l3num == ctx->family || ctx->family == NFPROTO_INET)
+			break;
+
+		return -EINVAL;
+	case NFPROTO_INET: /* tuple.src.l3num supports NFPROTO_IPV4/6 only */
+	default:
+		return -EAFNOSUPPORT;
+	}
+
 	priv->l4proto = nla_get_u8(tb[NFTA_CT_EXPECT_L4PROTO]);
+	switch (priv->l4proto) {
+	case IPPROTO_TCP:
+	case IPPROTO_UDP:
+	case IPPROTO_UDPLITE:
+	case IPPROTO_DCCP:
+	case IPPROTO_SCTP:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
 	priv->dport = nla_get_be16(tb[NFTA_CT_EXPECT_DPORT]);
 	priv->timeout = nla_get_u32(tb[NFTA_CT_EXPECT_TIMEOUT]);
 	priv->size = nla_get_u8(tb[NFTA_CT_EXPECT_SIZE]);
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index ab3362c483b4..ab9576098701 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -361,6 +361,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
 		ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
 	}
 
+	__set_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags);
 	ret = flow_offload_add(flowtable, flow);
 	if (ret < 0)
 		goto err_flow_add;
@@ -384,6 +385,11 @@ static int nft_flow_offload_validate(const struct nft_ctx *ctx,
 {
 	unsigned int hook_mask = (1 << NF_INET_FORWARD);
 
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	return nft_chain_validate_hooks(ctx->chain, hook_mask);
 }
 
diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c
index 145dc62c6247..cefa25e0dbb0 100644
--- a/net/netfilter/nft_limit.c
+++ b/net/netfilter/nft_limit.c
@@ -58,16 +58,19 @@ static inline bool nft_limit_eval(struct nft_limit_priv *priv, u64 cost)
 static int nft_limit_init(struct nft_limit_priv *priv,
 			  const struct nlattr * const tb[], bool pkts)
 {
-	u64 unit, tokens;
+	u64 unit, tokens, rate_with_burst;
+	bool invert = false;
 
 	if (tb[NFTA_LIMIT_RATE] == NULL ||
 	    tb[NFTA_LIMIT_UNIT] == NULL)
 		return -EINVAL;
 
 	priv->rate = be64_to_cpu(nla_get_be64(tb[NFTA_LIMIT_RATE]));
+	if (priv->rate == 0)
+		return -EINVAL;
+
 	unit = be64_to_cpu(nla_get_be64(tb[NFTA_LIMIT_UNIT]));
-	priv->nsecs = unit * NSEC_PER_SEC;
-	if (priv->rate == 0 || priv->nsecs < unit)
+	if (check_mul_overflow(unit, NSEC_PER_SEC, &priv->nsecs))
 		return -EOVERFLOW;
 
 	if (tb[NFTA_LIMIT_BURST])
@@ -76,18 +79,35 @@ static int nft_limit_init(struct nft_limit_priv *priv,
 	if (pkts && priv->burst == 0)
 		priv->burst = NFT_LIMIT_PKT_BURST_DEFAULT;
 
-	if (priv->rate + priv->burst < priv->rate)
+	if (check_add_overflow(priv->rate, priv->burst, &rate_with_burst))
 		return -EOVERFLOW;
 
 	if (pkts) {
-		tokens = div64_u64(priv->nsecs, priv->rate) * priv->burst;
+		u64 tmp = div64_u64(priv->nsecs, priv->rate);
+
+		if (check_mul_overflow(tmp, priv->burst, &tokens))
+			return -EOVERFLOW;
 	} else {
+		u64 tmp;
+
 		/* The token bucket size limits the number of tokens can be
 		 * accumulated. tokens_max specifies the bucket size.
 		 * tokens_max = unit * (rate + burst) / rate.
 		 */
-		tokens = div64_u64(priv->nsecs * (priv->rate + priv->burst),
-				 priv->rate);
+		if (check_mul_overflow(priv->nsecs, rate_with_burst, &tmp))
+			return -EOVERFLOW;
+
+		tokens = div64_u64(tmp, priv->rate);
+	}
+
+	if (tb[NFTA_LIMIT_FLAGS]) {
+		u32 flags = ntohl(nla_get_be32(tb[NFTA_LIMIT_FLAGS]));
+
+		if (flags & ~NFT_LIMIT_F_INV)
+			return -EOPNOTSUPP;
+
+		if (flags & NFT_LIMIT_F_INV)
+			invert = true;
 	}
 
 	priv->limit = kmalloc(sizeof(*priv->limit), GFP_KERNEL_ACCOUNT);
@@ -96,13 +116,7 @@ static int nft_limit_init(struct nft_limit_priv *priv,
 
 	priv->limit->tokens = tokens;
 	priv->tokens_max = priv->limit->tokens;
-
-	if (tb[NFTA_LIMIT_FLAGS]) {
-		u32 flags = ntohl(nla_get_be32(tb[NFTA_LIMIT_FLAGS]));
-
-		if (flags & NFT_LIMIT_F_INV)
-			priv->invert = true;
-	}
+	priv->invert = invert;
 	priv->limit->last = ktime_get_ns();
 	spin_lock_init(&priv->limit->lock);
 
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index 583885ce7232..808f5802c270 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -143,6 +143,11 @@ static int nft_nat_validate(const struct nft_ctx *ctx,
 	struct nft_nat *priv = nft_expr_priv(expr);
 	int err;
 
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
 	if (err < 0)
 		return err;
diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c
index 35a2c28caa60..24d977138572 100644
--- a/net/netfilter/nft_rt.c
+++ b/net/netfilter/nft_rt.c
@@ -166,6 +166,11 @@ static int nft_rt_validate(const struct nft_ctx *ctx, const struct nft_expr *exp
 	const struct nft_rt *priv = nft_expr_priv(expr);
 	unsigned int hooks;
 
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	switch (priv->key) {
 	case NFT_RT_NEXTHOP4:
 	case NFT_RT_NEXTHOP6:
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 6c2061bfdae6..6968a3b34236 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -36,6 +36,7 @@ struct nft_rhash_cmp_arg {
 	const struct nft_set		*set;
 	const u32			*key;
 	u8				genmask;
+	u64				tstamp;
 };
 
 static inline u32 nft_rhash_key(const void *data, u32 len, u32 seed)
@@ -62,7 +63,7 @@ static inline int nft_rhash_cmp(struct rhashtable_compare_arg *arg,
 		return 1;
 	if (nft_set_elem_is_dead(&he->ext))
 		return 1;
-	if (nft_set_elem_expired(&he->ext))
+	if (__nft_set_elem_expired(&he->ext, x->tstamp))
 		return 1;
 	if (!nft_set_elem_active(&he->ext, x->genmask))
 		return 1;
@@ -87,6 +88,7 @@ bool nft_rhash_lookup(const struct net *net, const struct nft_set *set,
 		.genmask = nft_genmask_cur(net),
 		.set	 = set,
 		.key	 = key,
+		.tstamp  = get_jiffies_64(),
 	};
 
 	he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params);
@@ -106,6 +108,7 @@ nft_rhash_get(const struct net *net, const struct nft_set *set,
 		.genmask = nft_genmask_cur(net),
 		.set	 = set,
 		.key	 = elem->key.val.data,
+		.tstamp  = get_jiffies_64(),
 	};
 
 	he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params);
@@ -131,6 +134,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key,
 		.genmask = NFT_GENMASK_ANY,
 		.set	 = set,
 		.key	 = key,
+		.tstamp  = get_jiffies_64(),
 	};
 
 	he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params);
@@ -175,6 +179,7 @@ static int nft_rhash_insert(const struct net *net, const struct nft_set *set,
 		.genmask = nft_genmask_next(net),
 		.set	 = set,
 		.key	 = elem->key.val.data,
+		.tstamp	 = nft_net_tstamp(net),
 	};
 	struct nft_rhash_elem *prev;
 
@@ -216,6 +221,7 @@ nft_rhash_deactivate(const struct net *net, const struct nft_set *set,
 		.genmask = nft_genmask_next(net),
 		.set	 = set,
 		.key	 = elem->key.val.data,
+		.tstamp	 = nft_net_tstamp(net),
 	};
 
 	rcu_read_lock();
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index efd523496be4..aa1d9e93a9a0 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -342,9 +342,6 @@
 #include "nft_set_pipapo_avx2.h"
 #include "nft_set_pipapo.h"
 
-/* Current working bitmap index, toggled between field matches */
-static DEFINE_PER_CPU(bool, nft_pipapo_scratch_index);
-
 /**
  * pipapo_refill() - For each set bit, set bits from selected mapping table item
  * @map:	Bitmap to be scanned for set bits
@@ -412,6 +409,7 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 		       const u32 *key, const struct nft_set_ext **ext)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
+	struct nft_pipapo_scratch *scratch;
 	unsigned long *res_map, *fill_map;
 	u8 genmask = nft_genmask_cur(net);
 	const u8 *rp = (const u8 *)key;
@@ -422,15 +420,17 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 
 	local_bh_disable();
 
-	map_index = raw_cpu_read(nft_pipapo_scratch_index);
-
 	m = rcu_dereference(priv->match);
 
 	if (unlikely(!m || !*raw_cpu_ptr(m->scratch)))
 		goto out;
 
-	res_map  = *raw_cpu_ptr(m->scratch) + (map_index ? m->bsize_max : 0);
-	fill_map = *raw_cpu_ptr(m->scratch) + (map_index ? 0 : m->bsize_max);
+	scratch = *raw_cpu_ptr(m->scratch);
+
+	map_index = scratch->map_index;
+
+	res_map  = scratch->map + (map_index ? m->bsize_max : 0);
+	fill_map = scratch->map + (map_index ? 0 : m->bsize_max);
 
 	memset(res_map, 0xff, m->bsize_max * sizeof(*res_map));
 
@@ -460,7 +460,7 @@ next_match:
 		b = pipapo_refill(res_map, f->bsize, f->rules, fill_map, f->mt,
 				  last);
 		if (b < 0) {
-			raw_cpu_write(nft_pipapo_scratch_index, map_index);
+			scratch->map_index = map_index;
 			local_bh_enable();
 
 			return false;
@@ -477,7 +477,7 @@ next_match:
 			 * current inactive bitmap is clean and can be reused as
 			 * *next* bitmap (not initial) for the next packet.
 			 */
-			raw_cpu_write(nft_pipapo_scratch_index, map_index);
+			scratch->map_index = map_index;
 			local_bh_enable();
 
 			return true;
@@ -504,6 +504,7 @@ out:
  * @set:	nftables API set representation
  * @data:	Key data to be matched against existing elements
  * @genmask:	If set, check that element is active in given genmask
+ * @tstamp:	timestamp to check for expired elements
  *
  * This is essentially the same as the lookup function, except that it matches
  * key data against the uncommitted copy and doesn't use preallocated maps for
@@ -513,7 +514,8 @@ out:
  */
 static struct nft_pipapo_elem *pipapo_get(const struct net *net,
 					  const struct nft_set *set,
-					  const u8 *data, u8 genmask)
+					  const u8 *data, u8 genmask,
+					  u64 tstamp)
 {
 	struct nft_pipapo_elem *ret = ERR_PTR(-ENOENT);
 	struct nft_pipapo *priv = nft_set_priv(set);
@@ -566,7 +568,7 @@ next_match:
 			goto out;
 
 		if (last) {
-			if (nft_set_elem_expired(&f->mt[b].e->ext))
+			if (__nft_set_elem_expired(&f->mt[b].e->ext, tstamp))
 				goto next_match;
 			if ((genmask &&
 			     !nft_set_elem_active(&f->mt[b].e->ext, genmask)))
@@ -603,10 +605,10 @@ static struct nft_elem_priv *
 nft_pipapo_get(const struct net *net, const struct nft_set *set,
 	       const struct nft_set_elem *elem, unsigned int flags)
 {
-	static struct nft_pipapo_elem *e;
+	struct nft_pipapo_elem *e;
 
 	e = pipapo_get(net, set, (const u8 *)elem->key.val.data,
-		       nft_genmask_cur(net));
+		       nft_genmask_cur(net), get_jiffies_64());
 	if (IS_ERR(e))
 		return ERR_CAST(e);
 
@@ -1109,6 +1111,25 @@ static void pipapo_map(struct nft_pipapo_match *m,
 }
 
 /**
+ * pipapo_free_scratch() - Free per-CPU map at original (not aligned) address
+ * @m:		Matching data
+ * @cpu:	CPU number
+ */
+static void pipapo_free_scratch(const struct nft_pipapo_match *m, unsigned int cpu)
+{
+	struct nft_pipapo_scratch *s;
+	void *mem;
+
+	s = *per_cpu_ptr(m->scratch, cpu);
+	if (!s)
+		return;
+
+	mem = s;
+	mem -= s->align_off;
+	kfree(mem);
+}
+
+/**
  * pipapo_realloc_scratch() - Reallocate scratch maps for partial match results
  * @clone:	Copy of matching data with pending insertions and deletions
  * @bsize_max:	Maximum bucket size, scratch maps cover two buckets
@@ -1121,12 +1142,13 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
 	int i;
 
 	for_each_possible_cpu(i) {
-		unsigned long *scratch;
+		struct nft_pipapo_scratch *scratch;
 #ifdef NFT_PIPAPO_ALIGN
-		unsigned long *scratch_aligned;
+		void *scratch_aligned;
+		u32 align_off;
 #endif
-
-		scratch = kzalloc_node(bsize_max * sizeof(*scratch) * 2 +
+		scratch = kzalloc_node(struct_size(scratch, map,
+						   bsize_max * 2) +
 				       NFT_PIPAPO_ALIGN_HEADROOM,
 				       GFP_KERNEL, cpu_to_node(i));
 		if (!scratch) {
@@ -1140,14 +1162,25 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
 			return -ENOMEM;
 		}
 
-		kfree(*per_cpu_ptr(clone->scratch, i));
-
-		*per_cpu_ptr(clone->scratch, i) = scratch;
+		pipapo_free_scratch(clone, i);
 
 #ifdef NFT_PIPAPO_ALIGN
-		scratch_aligned = NFT_PIPAPO_LT_ALIGN(scratch);
-		*per_cpu_ptr(clone->scratch_aligned, i) = scratch_aligned;
+		/* Align &scratch->map (not the struct itself): the extra
+		 * %NFT_PIPAPO_ALIGN_HEADROOM bytes passed to kzalloc_node()
+		 * above guarantee we can waste up to those bytes in order
+		 * to align the map field regardless of its offset within
+		 * the struct.
+		 */
+		BUILD_BUG_ON(offsetof(struct nft_pipapo_scratch, map) > NFT_PIPAPO_ALIGN_HEADROOM);
+
+		scratch_aligned = NFT_PIPAPO_LT_ALIGN(&scratch->map);
+		scratch_aligned -= offsetof(struct nft_pipapo_scratch, map);
+		align_off = scratch_aligned - (void *)scratch;
+
+		scratch = scratch_aligned;
+		scratch->align_off = align_off;
 #endif
+		*per_cpu_ptr(clone->scratch, i) = scratch;
 	}
 
 	return 0;
@@ -1173,6 +1206,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 	struct nft_pipapo_match *m = priv->clone;
 	u8 genmask = nft_genmask_next(net);
 	struct nft_pipapo_elem *e, *dup;
+	u64 tstamp = nft_net_tstamp(net);
 	struct nft_pipapo_field *f;
 	const u8 *start_p, *end_p;
 	int i, bsize_max, err = 0;
@@ -1182,7 +1216,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 	else
 		end = start;
 
-	dup = pipapo_get(net, set, start, genmask);
+	dup = pipapo_get(net, set, start, genmask, tstamp);
 	if (!IS_ERR(dup)) {
 		/* Check if we already have the same exact entry */
 		const struct nft_data *dup_key, *dup_end;
@@ -1204,7 +1238,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 
 	if (PTR_ERR(dup) == -ENOENT) {
 		/* Look for partially overlapping entries */
-		dup = pipapo_get(net, set, end, nft_genmask_next(net));
+		dup = pipapo_get(net, set, end, nft_genmask_next(net), tstamp);
 	}
 
 	if (PTR_ERR(dup) != -ENOENT) {
@@ -1301,11 +1335,6 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old)
 	if (!new->scratch)
 		goto out_scratch;
 
-#ifdef NFT_PIPAPO_ALIGN
-	new->scratch_aligned = alloc_percpu(*new->scratch_aligned);
-	if (!new->scratch_aligned)
-		goto out_scratch;
-#endif
 	for_each_possible_cpu(i)
 		*per_cpu_ptr(new->scratch, i) = NULL;
 
@@ -1357,10 +1386,7 @@ out_lt:
 	}
 out_scratch_realloc:
 	for_each_possible_cpu(i)
-		kfree(*per_cpu_ptr(new->scratch, i));
-#ifdef NFT_PIPAPO_ALIGN
-	free_percpu(new->scratch_aligned);
-#endif
+		pipapo_free_scratch(new, i);
 out_scratch:
 	free_percpu(new->scratch);
 	kfree(new);
@@ -1560,6 +1586,7 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
 	struct net *net = read_pnet(&set->net);
+	u64 tstamp = nft_net_tstamp(net);
 	int rules_f0, first_rule = 0;
 	struct nft_pipapo_elem *e;
 	struct nft_trans_gc *gc;
@@ -1594,7 +1621,7 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m)
 		/* synchronous gc never fails, there is no need to set on
 		 * NFT_SET_ELEM_DEAD_BIT.
 		 */
-		if (nft_set_elem_expired(&e->ext)) {
+		if (__nft_set_elem_expired(&e->ext, tstamp)) {
 			priv->dirty = true;
 
 			gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
@@ -1640,13 +1667,9 @@ static void pipapo_free_match(struct nft_pipapo_match *m)
 	int i;
 
 	for_each_possible_cpu(i)
-		kfree(*per_cpu_ptr(m->scratch, i));
+		pipapo_free_scratch(m, i);
 
-#ifdef NFT_PIPAPO_ALIGN
-	free_percpu(m->scratch_aligned);
-#endif
 	free_percpu(m->scratch);
-
 	pipapo_free_fields(m);
 
 	kfree(m);
@@ -1769,7 +1792,7 @@ static void *pipapo_deactivate(const struct net *net, const struct nft_set *set,
 {
 	struct nft_pipapo_elem *e;
 
-	e = pipapo_get(net, set, data, nft_genmask_next(net));
+	e = pipapo_get(net, set, data, nft_genmask_next(net), nft_net_tstamp(net));
 	if (IS_ERR(e))
 		return NULL;
 
@@ -2132,7 +2155,7 @@ static int nft_pipapo_init(const struct nft_set *set,
 	m->field_count = field_count;
 	m->bsize_max = 0;
 
-	m->scratch = alloc_percpu(unsigned long *);
+	m->scratch = alloc_percpu(struct nft_pipapo_scratch *);
 	if (!m->scratch) {
 		err = -ENOMEM;
 		goto out_scratch;
@@ -2140,16 +2163,6 @@ static int nft_pipapo_init(const struct nft_set *set,
 	for_each_possible_cpu(i)
 		*per_cpu_ptr(m->scratch, i) = NULL;
 
-#ifdef NFT_PIPAPO_ALIGN
-	m->scratch_aligned = alloc_percpu(unsigned long *);
-	if (!m->scratch_aligned) {
-		err = -ENOMEM;
-		goto out_free;
-	}
-	for_each_possible_cpu(i)
-		*per_cpu_ptr(m->scratch_aligned, i) = NULL;
-#endif
-
 	rcu_head_init(&m->rcu);
 
 	nft_pipapo_for_each_field(f, i, m) {
@@ -2180,9 +2193,6 @@ static int nft_pipapo_init(const struct nft_set *set,
 	return 0;
 
 out_free:
-#ifdef NFT_PIPAPO_ALIGN
-	free_percpu(m->scratch_aligned);
-#endif
 	free_percpu(m->scratch);
 out_scratch:
 	kfree(m);
@@ -2236,11 +2246,8 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx,
 
 		nft_set_pipapo_match_destroy(ctx, set, m);
 
-#ifdef NFT_PIPAPO_ALIGN
-		free_percpu(m->scratch_aligned);
-#endif
 		for_each_possible_cpu(cpu)
-			kfree(*per_cpu_ptr(m->scratch, cpu));
+			pipapo_free_scratch(m, cpu);
 		free_percpu(m->scratch);
 		pipapo_free_fields(m);
 		kfree(m);
@@ -2253,11 +2260,8 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx,
 		if (priv->dirty)
 			nft_set_pipapo_match_destroy(ctx, set, m);
 
-#ifdef NFT_PIPAPO_ALIGN
-		free_percpu(priv->clone->scratch_aligned);
-#endif
 		for_each_possible_cpu(cpu)
-			kfree(*per_cpu_ptr(priv->clone->scratch, cpu));
+			pipapo_free_scratch(priv->clone, cpu);
 		free_percpu(priv->clone->scratch);
 
 		pipapo_free_fields(priv->clone);
diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h
index 1040223da5fa..3842c7341a9f 100644
--- a/net/netfilter/nft_set_pipapo.h
+++ b/net/netfilter/nft_set_pipapo.h
@@ -131,20 +131,28 @@ struct nft_pipapo_field {
 };
 
 /**
+ * struct nft_pipapo_scratch - percpu data used for lookup and matching
+ * @map_index:	Current working bitmap index, toggled between field matches
+ * @align_off:	Offset to get the originally allocated address
+ * @map:	store partial matching results during lookup
+ */
+struct nft_pipapo_scratch {
+	u8 map_index;
+	u32 align_off;
+	unsigned long map[];
+};
+
+/**
  * struct nft_pipapo_match - Data used for lookup and matching
- * @field_count		Amount of fields in set
+ * @field_count:	Amount of fields in set
  * @scratch:		Preallocated per-CPU maps for partial matching results
- * @scratch_aligned:	Version of @scratch aligned to NFT_PIPAPO_ALIGN bytes
  * @bsize_max:		Maximum lookup table bucket size of all fields, in longs
- * @rcu			Matching data is swapped on commits
+ * @rcu:		Matching data is swapped on commits
  * @f:			Fields, with lookup and mapping tables
  */
 struct nft_pipapo_match {
 	int field_count;
-#ifdef NFT_PIPAPO_ALIGN
-	unsigned long * __percpu *scratch_aligned;
-#endif
-	unsigned long * __percpu *scratch;
+	struct nft_pipapo_scratch * __percpu *scratch;
 	size_t bsize_max;
 	struct rcu_head rcu;
 	struct nft_pipapo_field f[] __counted_by(field_count);
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index 52e0d026d30a..a3a8ddca9918 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -57,7 +57,7 @@
 
 /* Jump to label if @reg is zero */
 #define NFT_PIPAPO_AVX2_NOMATCH_GOTO(reg, label)			\
-	asm_volatile_goto("vptest %%ymm" #reg ", %%ymm" #reg ";"	\
+	asm goto("vptest %%ymm" #reg ", %%ymm" #reg ";"	\
 			  "je %l[" #label "]" : : : : label)
 
 /* Store 256 bits from YMM register into memory. Contrary to bucket load
@@ -71,9 +71,6 @@
 #define NFT_PIPAPO_AVX2_ZERO(reg)					\
 	asm volatile("vpxor %ymm" #reg ", %ymm" #reg ", %ymm" #reg)
 
-/* Current working bitmap index, toggled between field matches */
-static DEFINE_PER_CPU(bool, nft_pipapo_avx2_scratch_index);
-
 /**
  * nft_pipapo_avx2_prepare() - Prepare before main algorithm body
  *
@@ -1120,11 +1117,12 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 			    const u32 *key, const struct nft_set_ext **ext)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
-	unsigned long *res, *fill, *scratch;
+	struct nft_pipapo_scratch *scratch;
 	u8 genmask = nft_genmask_cur(net);
 	const u8 *rp = (const u8 *)key;
 	struct nft_pipapo_match *m;
 	struct nft_pipapo_field *f;
+	unsigned long *res, *fill;
 	bool map_index;
 	int i, ret = 0;
 
@@ -1141,15 +1139,16 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 	 */
 	kernel_fpu_begin_mask(0);
 
-	scratch = *raw_cpu_ptr(m->scratch_aligned);
+	scratch = *raw_cpu_ptr(m->scratch);
 	if (unlikely(!scratch)) {
 		kernel_fpu_end();
 		return false;
 	}
-	map_index = raw_cpu_read(nft_pipapo_avx2_scratch_index);
 
-	res  = scratch + (map_index ? m->bsize_max : 0);
-	fill = scratch + (map_index ? 0 : m->bsize_max);
+	map_index = scratch->map_index;
+
+	res  = scratch->map + (map_index ? m->bsize_max : 0);
+	fill = scratch->map + (map_index ? 0 : m->bsize_max);
 
 	/* Starting map doesn't need to be set for this implementation */
 
@@ -1221,7 +1220,7 @@ next_match:
 
 out:
 	if (i % 2)
-		raw_cpu_write(nft_pipapo_avx2_scratch_index, !map_index);
+		scratch->map_index = !map_index;
 	kernel_fpu_end();
 
 	return ret >= 0;
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index baa3fea4fe65..9944fe479e53 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -234,7 +234,7 @@ static void nft_rbtree_gc_elem_remove(struct net *net, struct nft_set *set,
 
 static const struct nft_rbtree_elem *
 nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv,
-		   struct nft_rbtree_elem *rbe, u8 genmask)
+		   struct nft_rbtree_elem *rbe)
 {
 	struct nft_set *set = (struct nft_set *)__set;
 	struct rb_node *prev = rb_prev(&rbe->node);
@@ -253,7 +253,7 @@ nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv,
 	while (prev) {
 		rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node);
 		if (nft_rbtree_interval_end(rbe_prev) &&
-		    nft_set_elem_active(&rbe_prev->ext, genmask))
+		    nft_set_elem_active(&rbe_prev->ext, NFT_GENMASK_ANY))
 			break;
 
 		prev = rb_prev(prev);
@@ -313,6 +313,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 	struct nft_rbtree *priv = nft_set_priv(set);
 	u8 cur_genmask = nft_genmask_cur(net);
 	u8 genmask = nft_genmask_next(net);
+	u64 tstamp = nft_net_tstamp(net);
 	int d;
 
 	/* Descend the tree to search for an existing element greater than the
@@ -360,11 +361,11 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 		/* perform garbage collection to avoid bogus overlap reports
 		 * but skip new elements in this transaction.
 		 */
-		if (nft_set_elem_expired(&rbe->ext) &&
+		if (__nft_set_elem_expired(&rbe->ext, tstamp) &&
 		    nft_set_elem_active(&rbe->ext, cur_genmask)) {
 			const struct nft_rbtree_elem *removed_end;
 
-			removed_end = nft_rbtree_gc_elem(set, priv, rbe, genmask);
+			removed_end = nft_rbtree_gc_elem(set, priv, rbe);
 			if (IS_ERR(removed_end))
 				return PTR_ERR(removed_end);
 
@@ -551,6 +552,7 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set,
 	const struct nft_rbtree *priv = nft_set_priv(set);
 	const struct rb_node *parent = priv->root.rb_node;
 	u8 genmask = nft_genmask_next(net);
+	u64 tstamp = nft_net_tstamp(net);
 	int d;
 
 	while (parent != NULL) {
@@ -571,7 +573,7 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set,
 				   nft_rbtree_interval_end(this)) {
 				parent = parent->rb_right;
 				continue;
-			} else if (nft_set_elem_expired(&rbe->ext)) {
+			} else if (__nft_set_elem_expired(&rbe->ext, tstamp)) {
 				break;
 			} else if (!nft_set_elem_active(&rbe->ext, genmask)) {
 				parent = parent->rb_left;
@@ -624,9 +626,10 @@ static void nft_rbtree_gc(struct nft_set *set)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe, *rbe_end = NULL;
+	struct net *net = read_pnet(&set->net);
+	u64 tstamp = nft_net_tstamp(net);
 	struct rb_node *node, *next;
 	struct nft_trans_gc *gc;
-	struct net *net;
 
 	set  = nft_set_container_of(priv);
 	net  = read_pnet(&set->net);
@@ -648,7 +651,7 @@ static void nft_rbtree_gc(struct nft_set *set)
 			rbe_end = rbe;
 			continue;
 		}
-		if (!nft_set_elem_expired(&rbe->ext))
+		if (!__nft_set_elem_expired(&rbe->ext, tstamp))
 			continue;
 
 		gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
index 9ed85be79452..f30163e2ca62 100644
--- a/net/netfilter/nft_socket.c
+++ b/net/netfilter/nft_socket.c
@@ -242,6 +242,11 @@ static int nft_socket_validate(const struct nft_ctx *ctx,
 			       const struct nft_expr *expr,
 			       const struct nft_data **data)
 {
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	return nft_chain_validate_hooks(ctx->chain,
 					(1 << NF_INET_PRE_ROUTING) |
 					(1 << NF_INET_LOCAL_IN) |
diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c
index 13da882669a4..1d737f89dfc1 100644
--- a/net/netfilter/nft_synproxy.c
+++ b/net/netfilter/nft_synproxy.c
@@ -186,7 +186,6 @@ static int nft_synproxy_do_init(const struct nft_ctx *ctx,
 		break;
 #endif
 	case NFPROTO_INET:
-	case NFPROTO_BRIDGE:
 		err = nf_synproxy_ipv4_init(snet, ctx->net);
 		if (err)
 			goto nf_ct_failure;
@@ -219,7 +218,6 @@ static void nft_synproxy_do_destroy(const struct nft_ctx *ctx)
 		break;
 #endif
 	case NFPROTO_INET:
-	case NFPROTO_BRIDGE:
 		nf_synproxy_ipv4_fini(snet, ctx->net);
 		nf_synproxy_ipv6_fini(snet, ctx->net);
 		break;
@@ -253,6 +251,11 @@ static int nft_synproxy_validate(const struct nft_ctx *ctx,
 				 const struct nft_expr *expr,
 				 const struct nft_data **data)
 {
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) |
 						    (1 << NF_INET_FORWARD));
 }
diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c
index ae15cd693f0e..71412adb73d4 100644
--- a/net/netfilter/nft_tproxy.c
+++ b/net/netfilter/nft_tproxy.c
@@ -316,6 +316,11 @@ static int nft_tproxy_validate(const struct nft_ctx *ctx,
 			       const struct nft_expr *expr,
 			       const struct nft_data **data)
 {
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	return nft_chain_validate_hooks(ctx->chain, 1 << NF_INET_PRE_ROUTING);
 }
 
diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index 9f21953c7433..f735d79d8be5 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -713,6 +713,7 @@ static const struct nft_object_ops nft_tunnel_obj_ops = {
 
 static struct nft_object_type nft_tunnel_obj_type __read_mostly = {
 	.type		= NFT_OBJECT_TUNNEL,
+	.family		= NFPROTO_NETDEV,
 	.ops		= &nft_tunnel_obj_ops,
 	.maxattr	= NFTA_TUNNEL_KEY_MAX,
 	.policy		= nft_tunnel_key_policy,
diff --git a/net/netfilter/nft_xfrm.c b/net/netfilter/nft_xfrm.c
index 452f8587adda..1c866757db55 100644
--- a/net/netfilter/nft_xfrm.c
+++ b/net/netfilter/nft_xfrm.c
@@ -235,6 +235,11 @@ static int nft_xfrm_validate(const struct nft_ctx *ctx, const struct nft_expr *e
 	const struct nft_xfrm *priv = nft_expr_priv(expr);
 	unsigned int hooks;
 
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	switch (priv->dir) {
 	case XFRM_POLICY_IN:
 		hooks = (1 << NF_INET_FORWARD) |
diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c
index ec6ed6fda96c..343e65f377d4 100644
--- a/net/netfilter/xt_physdev.c
+++ b/net/netfilter/xt_physdev.c
@@ -59,7 +59,7 @@ physdev_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	    (!!outdev ^ !(info->invert & XT_PHYSDEV_OP_BRIDGED)))
 		return false;
 
-	physdev = nf_bridge_get_physindev(skb);
+	physdev = nf_bridge_get_physindev(skb, xt_net(par));
 	indev = physdev ? physdev->name : NULL;
 
 	if ((info->bitmask & XT_PHYSDEV_OP_ISIN &&
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 4ed8ffd58ff3..ff315351269f 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -167,7 +167,7 @@ static inline u32 netlink_group_mask(u32 group)
 static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb,
 					   gfp_t gfp_mask)
 {
-	unsigned int len = skb_end_offset(skb);
+	unsigned int len = skb->len;
 	struct sk_buff *new;
 
 	new = alloc_skb(len, gfp_mask);
@@ -374,7 +374,7 @@ static void netlink_skb_destructor(struct sk_buff *skb)
 	if (is_vmalloc_addr(skb->head)) {
 		if (!skb->cloned ||
 		    !atomic_dec_return(&(skb_shinfo(skb)->dataref)))
-			vfree(skb->head);
+			vfree_atomic(skb->head);
 
 		skb->head = NULL;
 	}
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 0eed00184adf..104a80b75477 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -453,16 +453,16 @@ static int nr_create(struct net *net, struct socket *sock, int protocol,
 	nr_init_timers(sk);
 
 	nr->t1     =
-		msecs_to_jiffies(sysctl_netrom_transport_timeout);
+		msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_timeout));
 	nr->t2     =
-		msecs_to_jiffies(sysctl_netrom_transport_acknowledge_delay);
+		msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_acknowledge_delay));
 	nr->n2     =
-		msecs_to_jiffies(sysctl_netrom_transport_maximum_tries);
+		msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_maximum_tries));
 	nr->t4     =
-		msecs_to_jiffies(sysctl_netrom_transport_busy_delay);
+		msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_busy_delay));
 	nr->idle   =
-		msecs_to_jiffies(sysctl_netrom_transport_no_activity_timeout);
-	nr->window = sysctl_netrom_transport_requested_window_size;
+		msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_no_activity_timeout));
+	nr->window = READ_ONCE(sysctl_netrom_transport_requested_window_size);
 
 	nr->bpqext = 1;
 	nr->state  = NR_STATE_0;
@@ -954,7 +954,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 		 * G8PZT's Xrouter which is sending packets with command type 7
 		 * as an extension of the protocol.
 		 */
-		if (sysctl_netrom_reset_circuit &&
+		if (READ_ONCE(sysctl_netrom_reset_circuit) &&
 		    (frametype != NR_RESET || flags != 0))
 			nr_transmit_reset(skb, 1);
 
diff --git a/net/netrom/nr_dev.c b/net/netrom/nr_dev.c
index 3aaac4a22b38..2c34389c3ce6 100644
--- a/net/netrom/nr_dev.c
+++ b/net/netrom/nr_dev.c
@@ -81,7 +81,7 @@ static int nr_header(struct sk_buff *skb, struct net_device *dev,
 	buff[6] |= AX25_SSSID_SPARE;
 	buff    += AX25_ADDR_LEN;
 
-	*buff++ = sysctl_netrom_network_ttl_initialiser;
+	*buff++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser);
 
 	*buff++ = NR_PROTO_IP;
 	*buff++ = NR_PROTO_IP;
diff --git a/net/netrom/nr_in.c b/net/netrom/nr_in.c
index 2f084b6f69d7..97944db6b5ac 100644
--- a/net/netrom/nr_in.c
+++ b/net/netrom/nr_in.c
@@ -97,7 +97,7 @@ static int nr_state1_machine(struct sock *sk, struct sk_buff *skb,
 		break;
 
 	case NR_RESET:
-		if (sysctl_netrom_reset_circuit)
+		if (READ_ONCE(sysctl_netrom_reset_circuit))
 			nr_disconnect(sk, ECONNRESET);
 		break;
 
@@ -128,7 +128,7 @@ static int nr_state2_machine(struct sock *sk, struct sk_buff *skb,
 		break;
 
 	case NR_RESET:
-		if (sysctl_netrom_reset_circuit)
+		if (READ_ONCE(sysctl_netrom_reset_circuit))
 			nr_disconnect(sk, ECONNRESET);
 		break;
 
@@ -262,7 +262,7 @@ static int nr_state3_machine(struct sock *sk, struct sk_buff *skb, int frametype
 		break;
 
 	case NR_RESET:
-		if (sysctl_netrom_reset_circuit)
+		if (READ_ONCE(sysctl_netrom_reset_circuit))
 			nr_disconnect(sk, ECONNRESET);
 		break;
 
diff --git a/net/netrom/nr_out.c b/net/netrom/nr_out.c
index 44929657f5b7..5e531394a724 100644
--- a/net/netrom/nr_out.c
+++ b/net/netrom/nr_out.c
@@ -204,7 +204,7 @@ void nr_transmit_buffer(struct sock *sk, struct sk_buff *skb)
 	dptr[6] |= AX25_SSSID_SPARE;
 	dptr += AX25_ADDR_LEN;
 
-	*dptr++ = sysctl_netrom_network_ttl_initialiser;
+	*dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser);
 
 	if (!nr_route_frame(skb, NULL)) {
 		kfree_skb(skb);
diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c
index baea3cbd76ca..70480869ad1c 100644
--- a/net/netrom/nr_route.c
+++ b/net/netrom/nr_route.c
@@ -153,7 +153,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic,
 		nr_neigh->digipeat = NULL;
 		nr_neigh->ax25     = NULL;
 		nr_neigh->dev      = dev;
-		nr_neigh->quality  = sysctl_netrom_default_path_quality;
+		nr_neigh->quality  = READ_ONCE(sysctl_netrom_default_path_quality);
 		nr_neigh->locked   = 0;
 		nr_neigh->count    = 0;
 		nr_neigh->number   = nr_neigh_no++;
@@ -728,7 +728,7 @@ void nr_link_failed(ax25_cb *ax25, int reason)
 	nr_neigh->ax25 = NULL;
 	ax25_cb_put(ax25);
 
-	if (++nr_neigh->failed < sysctl_netrom_link_fails_count) {
+	if (++nr_neigh->failed < READ_ONCE(sysctl_netrom_link_fails_count)) {
 		nr_neigh_put(nr_neigh);
 		return;
 	}
@@ -766,7 +766,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25)
 	if (ax25 != NULL) {
 		ret = nr_add_node(nr_src, "", &ax25->dest_addr, ax25->digipeat,
 				  ax25->ax25_dev->dev, 0,
-				  sysctl_netrom_obsolescence_count_initialiser);
+				  READ_ONCE(sysctl_netrom_obsolescence_count_initialiser));
 		if (ret)
 			return ret;
 	}
@@ -780,7 +780,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25)
 		return ret;
 	}
 
-	if (!sysctl_netrom_routing_control && ax25 != NULL)
+	if (!READ_ONCE(sysctl_netrom_routing_control) && ax25 != NULL)
 		return 0;
 
 	/* Its Time-To-Live has expired */
diff --git a/net/netrom/nr_subr.c b/net/netrom/nr_subr.c
index e2d2af924cff..c3bbd5880850 100644
--- a/net/netrom/nr_subr.c
+++ b/net/netrom/nr_subr.c
@@ -182,7 +182,8 @@ void nr_write_internal(struct sock *sk, int frametype)
 		*dptr++ = nr->my_id;
 		*dptr++ = frametype;
 		*dptr++ = nr->window;
-		if (nr->bpqext) *dptr++ = sysctl_netrom_network_ttl_initialiser;
+		if (nr->bpqext)
+			*dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser);
 		break;
 
 	case NR_DISCREQ:
@@ -236,7 +237,7 @@ void __nr_transmit_reply(struct sk_buff *skb, int mine, unsigned char cmdflags)
 	dptr[6] |= AX25_SSSID_SPARE;
 	dptr += AX25_ADDR_LEN;
 
-	*dptr++ = sysctl_netrom_network_ttl_initialiser;
+	*dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser);
 
 	if (mine) {
 		*dptr++ = 0;
diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c
index d63d2e5dc60c..dae378f1d52b 100644
--- a/net/nfc/digital_core.c
+++ b/net/nfc/digital_core.c
@@ -858,4 +858,5 @@ void nfc_digital_unregister_device(struct nfc_digital_dev *ddev)
 }
 EXPORT_SYMBOL(nfc_digital_unregister_device);
 
+MODULE_DESCRIPTION("NFC Digital protocol stack");
 MODULE_LICENSE("GPL");
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 6c9592d05120..cdad47b140fa 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -1208,6 +1208,10 @@ void nci_free_device(struct nci_dev *ndev)
 {
 	nfc_free_device(ndev->nfc_dev);
 	nci_hci_deallocate(ndev);
+
+	/* drop partial rx data packet if present */
+	if (ndev->rx_data_reassembly)
+		kfree_skb(ndev->rx_data_reassembly);
 	kfree(ndev);
 }
 EXPORT_SYMBOL(nci_free_device);
@@ -1577,4 +1581,5 @@ static void nci_cmd_work(struct work_struct *work)
 	}
 }
 
+MODULE_DESCRIPTION("NFC Controller Interface");
 MODULE_LICENSE("GPL");
diff --git a/net/nfc/nci/spi.c b/net/nfc/nci/spi.c
index b68150c971d0..6a93533c480e 100644
--- a/net/nfc/nci/spi.c
+++ b/net/nfc/nci/spi.c
@@ -319,4 +319,5 @@ done:
 }
 EXPORT_SYMBOL_GPL(nci_spi_read);
 
+MODULE_DESCRIPTION("NFC Controller Interface (NCI) SPI link layer");
 MODULE_LICENSE("GPL");
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 88965e2068ac..ebc5728aab4e 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -48,6 +48,7 @@ struct ovs_len_tbl {
 
 #define OVS_ATTR_NESTED -1
 #define OVS_ATTR_VARIABLE -2
+#define OVS_COPY_ACTIONS_MAX_DEPTH 16
 
 static bool actions_may_change_flow(const struct nlattr *actions)
 {
@@ -2545,13 +2546,15 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 				  const struct sw_flow_key *key,
 				  struct sw_flow_actions **sfa,
 				  __be16 eth_type, __be16 vlan_tci,
-				  u32 mpls_label_count, bool log);
+				  u32 mpls_label_count, bool log,
+				  u32 depth);
 
 static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
 				    const struct sw_flow_key *key,
 				    struct sw_flow_actions **sfa,
 				    __be16 eth_type, __be16 vlan_tci,
-				    u32 mpls_label_count, bool log, bool last)
+				    u32 mpls_label_count, bool log, bool last,
+				    u32 depth)
 {
 	const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
 	const struct nlattr *probability, *actions;
@@ -2602,7 +2605,8 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
 		return err;
 
 	err = __ovs_nla_copy_actions(net, actions, key, sfa,
-				     eth_type, vlan_tci, mpls_label_count, log);
+				     eth_type, vlan_tci, mpls_label_count, log,
+				     depth + 1);
 
 	if (err)
 		return err;
@@ -2617,7 +2621,8 @@ static int validate_and_copy_dec_ttl(struct net *net,
 				     const struct sw_flow_key *key,
 				     struct sw_flow_actions **sfa,
 				     __be16 eth_type, __be16 vlan_tci,
-				     u32 mpls_label_count, bool log)
+				     u32 mpls_label_count, bool log,
+				     u32 depth)
 {
 	const struct nlattr *attrs[OVS_DEC_TTL_ATTR_MAX + 1];
 	int start, action_start, err, rem;
@@ -2660,7 +2665,8 @@ static int validate_and_copy_dec_ttl(struct net *net,
 		return action_start;
 
 	err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type,
-				     vlan_tci, mpls_label_count, log);
+				     vlan_tci, mpls_label_count, log,
+				     depth + 1);
 	if (err)
 		return err;
 
@@ -2674,7 +2680,8 @@ static int validate_and_copy_clone(struct net *net,
 				   const struct sw_flow_key *key,
 				   struct sw_flow_actions **sfa,
 				   __be16 eth_type, __be16 vlan_tci,
-				   u32 mpls_label_count, bool log, bool last)
+				   u32 mpls_label_count, bool log, bool last,
+				   u32 depth)
 {
 	int start, err;
 	u32 exec;
@@ -2694,7 +2701,8 @@ static int validate_and_copy_clone(struct net *net,
 		return err;
 
 	err = __ovs_nla_copy_actions(net, attr, key, sfa,
-				     eth_type, vlan_tci, mpls_label_count, log);
+				     eth_type, vlan_tci, mpls_label_count, log,
+				     depth + 1);
 	if (err)
 		return err;
 
@@ -3063,7 +3071,7 @@ static int validate_and_copy_check_pkt_len(struct net *net,
 					   struct sw_flow_actions **sfa,
 					   __be16 eth_type, __be16 vlan_tci,
 					   u32 mpls_label_count,
-					   bool log, bool last)
+					   bool log, bool last, u32 depth)
 {
 	const struct nlattr *acts_if_greater, *acts_if_lesser_eq;
 	struct nlattr *a[OVS_CHECK_PKT_LEN_ATTR_MAX + 1];
@@ -3111,7 +3119,8 @@ static int validate_and_copy_check_pkt_len(struct net *net,
 		return nested_acts_start;
 
 	err = __ovs_nla_copy_actions(net, acts_if_lesser_eq, key, sfa,
-				     eth_type, vlan_tci, mpls_label_count, log);
+				     eth_type, vlan_tci, mpls_label_count, log,
+				     depth + 1);
 
 	if (err)
 		return err;
@@ -3124,7 +3133,8 @@ static int validate_and_copy_check_pkt_len(struct net *net,
 		return nested_acts_start;
 
 	err = __ovs_nla_copy_actions(net, acts_if_greater, key, sfa,
-				     eth_type, vlan_tci, mpls_label_count, log);
+				     eth_type, vlan_tci, mpls_label_count, log,
+				     depth + 1);
 
 	if (err)
 		return err;
@@ -3152,12 +3162,16 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 				  const struct sw_flow_key *key,
 				  struct sw_flow_actions **sfa,
 				  __be16 eth_type, __be16 vlan_tci,
-				  u32 mpls_label_count, bool log)
+				  u32 mpls_label_count, bool log,
+				  u32 depth)
 {
 	u8 mac_proto = ovs_key_mac_proto(key);
 	const struct nlattr *a;
 	int rem, err;
 
+	if (depth > OVS_COPY_ACTIONS_MAX_DEPTH)
+		return -EOVERFLOW;
+
 	nla_for_each_nested(a, attr, rem) {
 		/* Expected argument lengths, (u32)-1 for variable length. */
 		static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = {
@@ -3355,7 +3369,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			err = validate_and_copy_sample(net, a, key, sfa,
 						       eth_type, vlan_tci,
 						       mpls_label_count,
-						       log, last);
+						       log, last, depth);
 			if (err)
 				return err;
 			skip_copy = true;
@@ -3426,7 +3440,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			err = validate_and_copy_clone(net, a, key, sfa,
 						      eth_type, vlan_tci,
 						      mpls_label_count,
-						      log, last);
+						      log, last, depth);
 			if (err)
 				return err;
 			skip_copy = true;
@@ -3440,7 +3454,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 							      eth_type,
 							      vlan_tci,
 							      mpls_label_count,
-							      log, last);
+							      log, last,
+							      depth);
 			if (err)
 				return err;
 			skip_copy = true;
@@ -3450,7 +3465,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 		case OVS_ACTION_ATTR_DEC_TTL:
 			err = validate_and_copy_dec_ttl(net, a, key, sfa,
 							eth_type, vlan_tci,
-							mpls_label_count, log);
+							mpls_label_count, log,
+							depth);
 			if (err)
 				return err;
 			skip_copy = true;
@@ -3495,7 +3511,8 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 
 	(*sfa)->orig_len = nla_len(attr);
 	err = __ovs_nla_copy_actions(net, attr, key, sfa, key->eth.type,
-				     key->eth.vlan.tci, mpls_label_count, log);
+				     key->eth.vlan.tci, mpls_label_count, log,
+				     0);
 	if (err)
 		ovs_nla_free_flow_actions(*sfa);
 
diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c
index 3aa50dc7535b..976fe250b509 100644
--- a/net/phonet/datagram.c
+++ b/net/phonet/datagram.c
@@ -34,10 +34,10 @@ static int pn_ioctl(struct sock *sk, int cmd, int *karg)
 
 	switch (cmd) {
 	case SIOCINQ:
-		lock_sock(sk);
+		spin_lock_bh(&sk->sk_receive_queue.lock);
 		skb = skb_peek(&sk->sk_receive_queue);
 		*karg = skb ? skb->len : 0;
-		release_sock(sk);
+		spin_unlock_bh(&sk->sk_receive_queue.lock);
 		return 0;
 
 	case SIOCPNADDRESOURCE:
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index faba31f2eff2..3dd5f52bc1b5 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -917,6 +917,37 @@ static int pep_sock_enable(struct sock *sk, struct sockaddr *addr, int len)
 	return 0;
 }
 
+static unsigned int pep_first_packet_length(struct sock *sk)
+{
+	struct pep_sock *pn = pep_sk(sk);
+	struct sk_buff_head *q;
+	struct sk_buff *skb;
+	unsigned int len = 0;
+	bool found = false;
+
+	if (sock_flag(sk, SOCK_URGINLINE)) {
+		q = &pn->ctrlreq_queue;
+		spin_lock_bh(&q->lock);
+		skb = skb_peek(q);
+		if (skb) {
+			len = skb->len;
+			found = true;
+		}
+		spin_unlock_bh(&q->lock);
+	}
+
+	if (likely(!found)) {
+		q = &sk->sk_receive_queue;
+		spin_lock_bh(&q->lock);
+		skb = skb_peek(q);
+		if (skb)
+			len = skb->len;
+		spin_unlock_bh(&q->lock);
+	}
+
+	return len;
+}
+
 static int pep_ioctl(struct sock *sk, int cmd, int *karg)
 {
 	struct pep_sock *pn = pep_sk(sk);
@@ -929,15 +960,7 @@ static int pep_ioctl(struct sock *sk, int cmd, int *karg)
 			break;
 		}
 
-		lock_sock(sk);
-		if (sock_flag(sk, SOCK_URGINLINE) &&
-		    !skb_queue_empty(&pn->ctrlreq_queue))
-			*karg = skb_peek(&pn->ctrlreq_queue)->len;
-		else if (!skb_queue_empty(&sk->sk_receive_queue))
-			*karg = skb_peek(&sk->sk_receive_queue)->len;
-		else
-			*karg = 0;
-		release_sock(sk);
+		*karg = pep_first_packet_length(sk);
 		ret = 0;
 		break;
 
diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index 01c4cdfef45d..8435a20968ef 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -419,7 +419,7 @@ static int rds_recv_track_latency(struct rds_sock *rs, sockptr_t optval,
 
 	rs->rs_rx_traces = trace.rx_traces;
 	for (i = 0; i < rs->rs_rx_traces; i++) {
-		if (trace.rx_trace_pos[i] > RDS_MSG_RX_DGRAM_TRACE_MAX) {
+		if (trace.rx_trace_pos[i] >= RDS_MSG_RX_DGRAM_TRACE_MAX) {
 			rs->rs_rx_traces = 0;
 			return -EFAULT;
 		}
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index fba82d36593a..a4e3c5de998b 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -301,6 +301,9 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
 			kfree(sg);
 		}
 		ret = PTR_ERR(trans_private);
+		/* Trigger connection so that its ready for the next retry */
+		if (ret == -ENODEV)
+			rds_conn_connect_if_down(cp->cp_conn);
 		goto out;
 	}
 
diff --git a/net/rds/recv.c b/net/rds/recv.c
index c71b923764fd..5627f80013f8 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -425,6 +425,7 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc,
 	struct sock *sk = rds_rs_to_sk(rs);
 	int ret = 0;
 	unsigned long flags;
+	struct rds_incoming *to_drop = NULL;
 
 	write_lock_irqsave(&rs->rs_recv_lock, flags);
 	if (!list_empty(&inc->i_item)) {
@@ -435,11 +436,14 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc,
 					      -be32_to_cpu(inc->i_hdr.h_len),
 					      inc->i_hdr.h_dport);
 			list_del_init(&inc->i_item);
-			rds_inc_put(inc);
+			to_drop = inc;
 		}
 	}
 	write_unlock_irqrestore(&rs->rs_recv_lock, flags);
 
+	if (to_drop)
+		rds_inc_put(to_drop);
+
 	rdsdebug("inc %p rs %p still %d dropped %d\n", inc, rs, ret, drop);
 	return ret;
 }
@@ -758,16 +762,21 @@ void rds_clear_recv_queue(struct rds_sock *rs)
 	struct sock *sk = rds_rs_to_sk(rs);
 	struct rds_incoming *inc, *tmp;
 	unsigned long flags;
+	LIST_HEAD(to_drop);
 
 	write_lock_irqsave(&rs->rs_recv_lock, flags);
 	list_for_each_entry_safe(inc, tmp, &rs->rs_recv_queue, i_item) {
 		rds_recv_rcvbuf_delta(rs, sk, inc->i_conn->c_lcong,
 				      -be32_to_cpu(inc->i_hdr.h_len),
 				      inc->i_hdr.h_dport);
+		list_move(&inc->i_item, &to_drop);
+	}
+	write_unlock_irqrestore(&rs->rs_recv_lock, flags);
+
+	list_for_each_entry_safe(inc, tmp, &to_drop, i_item) {
 		list_del_init(&inc->i_item);
 		rds_inc_put(inc);
 	}
-	write_unlock_irqrestore(&rs->rs_recv_lock, flags);
 }
 
 /*
diff --git a/net/rds/send.c b/net/rds/send.c
index 5e57a1581dc6..2899def23865 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1313,12 +1313,8 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 
 	/* Parse any control messages the user may have included. */
 	ret = rds_cmsg_send(rs, rm, msg, &allocated_mr, &vct);
-	if (ret) {
-		/* Trigger connection so that its ready for the next retry */
-		if (ret ==  -EAGAIN)
-			rds_conn_connect_if_down(conn);
+	if (ret)
 		goto out;
-	}
 
 	if (rm->rdma.op_active && !conn->c_trans->xmit_rdma) {
 		printk_ratelimited(KERN_NOTICE "rdma_op %p conn xmit_rdma %p\n",
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 2f8b39a614c3..7818aae1be8e 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -199,11 +199,19 @@ struct rxrpc_host_header {
  */
 struct rxrpc_skb_priv {
 	struct rxrpc_connection *conn;	/* Connection referred to (poke packet) */
-	u16		offset;		/* Offset of data */
-	u16		len;		/* Length of data */
-	u8		flags;
+	union {
+		struct {
+			u16		offset;		/* Offset of data */
+			u16		len;		/* Length of data */
+			u8		flags;
 #define RXRPC_RX_VERIFIED	0x01
-
+		};
+		struct {
+			rxrpc_seq_t	first_ack;	/* First packet in acks table */
+			u8		nr_acks;	/* Number of acks+nacks */
+			u8		nr_nacks;	/* Number of nacks */
+		};
+	};
 	struct rxrpc_host_header hdr;	/* RxRPC packet header from this packet */
 };
 
@@ -510,7 +518,7 @@ struct rxrpc_connection {
 	enum rxrpc_call_completion completion;	/* Completion condition */
 	s32			abort_code;	/* Abort code of connection abort */
 	int			debug_id;	/* debug ID for printks */
-	atomic_t		serial;		/* packet serial number counter */
+	rxrpc_serial_t		tx_serial;	/* Outgoing packet serial number counter */
 	unsigned int		hi_serial;	/* highest serial number received */
 	u32			service_id;	/* Service ID, possibly upgraded */
 	u32			security_level;	/* Security level selected */
@@ -692,11 +700,11 @@ struct rxrpc_call {
 	u8			cong_dup_acks;	/* Count of ACKs showing missing packets */
 	u8			cong_cumul_acks; /* Cumulative ACK count */
 	ktime_t			cong_tstamp;	/* Last time cwnd was changed */
+	struct sk_buff		*cong_last_nack; /* Last ACK with nacks received */
 
 	/* Receive-phase ACK management (ACKs we send). */
 	u8			ackr_reason;	/* reason to ACK */
 	u16			ackr_sack_base;	/* Starting slot in SACK table ring */
-	rxrpc_serial_t		ackr_serial;	/* serial of packet being ACK'd */
 	rxrpc_seq_t		ackr_window;	/* Base of SACK window */
 	rxrpc_seq_t		ackr_wtop;	/* Base of SACK window */
 	unsigned int		ackr_nr_unacked; /* Number of unacked packets */
@@ -730,7 +738,8 @@ struct rxrpc_call {
 struct rxrpc_ack_summary {
 	u16			nr_acks;		/* Number of ACKs in packet */
 	u16			nr_new_acks;		/* Number of new ACKs in packet */
-	u16			nr_rot_new_acks;	/* Number of rotated new ACKs */
+	u16			nr_new_nacks;		/* Number of new nacks in packet */
+	u16			nr_retained_nacks;	/* Number of nacks retained between ACKs */
 	u8			ack_reason;
 	bool			saw_nacks;		/* Saw NACKs in packet */
 	bool			new_low_nack;		/* T if new low NACK found */
@@ -823,6 +832,20 @@ static inline bool rxrpc_sending_to_client(const struct rxrpc_txbuf *txb)
 #include <trace/events/rxrpc.h>
 
 /*
+ * Allocate the next serial number on a connection.  0 must be skipped.
+ */
+static inline rxrpc_serial_t rxrpc_get_next_serial(struct rxrpc_connection *conn)
+{
+	rxrpc_serial_t serial;
+
+	serial = conn->tx_serial;
+	if (serial == 0)
+		serial = 1;
+	conn->tx_serial = serial + 1;
+	return serial;
+}
+
+/*
  * af_rxrpc.c
  */
 extern atomic_t rxrpc_n_rx_skbs;
@@ -1079,6 +1102,7 @@ void rxrpc_send_version_request(struct rxrpc_local *local,
 /*
  * local_object.c
  */
+void rxrpc_local_dont_fragment(const struct rxrpc_local *local, bool set);
 struct rxrpc_local *rxrpc_lookup_local(struct net *, const struct sockaddr_rxrpc *);
 struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *, enum rxrpc_local_trace);
 struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *, enum rxrpc_local_trace);
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index e363f21a2014..0f78544d043b 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -43,8 +43,6 @@ void rxrpc_propose_delay_ACK(struct rxrpc_call *call, rxrpc_serial_t serial,
 	unsigned long expiry = rxrpc_soft_ack_delay;
 	unsigned long now = jiffies, ack_at;
 
-	call->ackr_serial = serial;
-
 	if (rxrpc_soft_ack_delay < expiry)
 		expiry = rxrpc_soft_ack_delay;
 	if (call->peer->srtt_us != 0)
@@ -114,6 +112,7 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call)
 void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb)
 {
 	struct rxrpc_ackpacket *ack = NULL;
+	struct rxrpc_skb_priv *sp;
 	struct rxrpc_txbuf *txb;
 	unsigned long resend_at;
 	rxrpc_seq_t transmitted = READ_ONCE(call->tx_transmitted);
@@ -141,14 +140,15 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb)
 	 * explicitly NAK'd packets.
 	 */
 	if (ack_skb) {
+		sp = rxrpc_skb(ack_skb);
 		ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header);
 
-		for (i = 0; i < ack->nAcks; i++) {
+		for (i = 0; i < sp->nr_acks; i++) {
 			rxrpc_seq_t seq;
 
 			if (ack->acks[i] & 1)
 				continue;
-			seq = ntohl(ack->firstPacket) + i;
+			seq = sp->first_ack + i;
 			if (after(txb->seq, transmitted))
 				break;
 			if (after(txb->seq, seq))
@@ -373,7 +373,6 @@ static void rxrpc_send_initial_ping(struct rxrpc_call *call)
 bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
 {
 	unsigned long now, next, t;
-	rxrpc_serial_t ackr_serial;
 	bool resend = false, expired = false;
 	s32 abort_code;
 
@@ -423,8 +422,7 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
 	if (time_after_eq(now, t)) {
 		trace_rxrpc_timer(call, rxrpc_timer_exp_ack, now);
 		cmpxchg(&call->delay_ack_at, t, now + MAX_JIFFY_OFFSET);
-		ackr_serial = xchg(&call->ackr_serial, 0);
-		rxrpc_send_ACK(call, RXRPC_ACK_DELAY, ackr_serial,
+		rxrpc_send_ACK(call, RXRPC_ACK_DELAY, 0,
 			       rxrpc_propose_ack_ping_for_lost_ack);
 	}
 
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 0943e54370ba..9fc9a6c3f685 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -686,6 +686,7 @@ static void rxrpc_destroy_call(struct work_struct *work)
 
 	del_timer_sync(&call->timer);
 
+	rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack);
 	rxrpc_cleanup_ring(call);
 	while ((txb = list_first_entry_or_null(&call->tx_sendmsg,
 					       struct rxrpc_txbuf, call_link))) {
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 95f4bc206b3d..1f251d758cb9 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -95,6 +95,14 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
 
 	_enter("%d", conn->debug_id);
 
+	if (sp && sp->hdr.type == RXRPC_PACKET_TYPE_ACK) {
+		if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
+				  &pkt.ack, sizeof(pkt.ack)) < 0)
+			return;
+		if (pkt.ack.reason == RXRPC_ACK_PING_RESPONSE)
+			return;
+	}
+
 	chan = &conn->channels[channel];
 
 	/* If the last call got moved on whilst we were waiting to run, just
@@ -117,7 +125,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
 	iov[2].iov_base	= &ack_info;
 	iov[2].iov_len	= sizeof(ack_info);
 
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 
 	pkt.whdr.epoch		= htonl(conn->proto.epoch);
 	pkt.whdr.cid		= htonl(conn->proto.cid | channel);
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 92495e73b869..9691de00ade7 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -45,11 +45,9 @@ static void rxrpc_congestion_management(struct rxrpc_call *call,
 	}
 
 	cumulative_acks += summary->nr_new_acks;
-	cumulative_acks += summary->nr_rot_new_acks;
 	if (cumulative_acks > 255)
 		cumulative_acks = 255;
 
-	summary->mode = call->cong_mode;
 	summary->cwnd = call->cong_cwnd;
 	summary->ssthresh = call->cong_ssthresh;
 	summary->cumulative_acks = cumulative_acks;
@@ -151,6 +149,7 @@ out_no_clear_ca:
 		cwnd = RXRPC_TX_MAX_WINDOW;
 	call->cong_cwnd = cwnd;
 	call->cong_cumul_acks = cumulative_acks;
+	summary->mode = call->cong_mode;
 	trace_rxrpc_congest(call, summary, acked_serial, change);
 	if (resend)
 		rxrpc_resend(call, skb);
@@ -213,7 +212,6 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
 	list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) {
 		if (before_eq(txb->seq, call->acks_hard_ack))
 			continue;
-		summary->nr_rot_new_acks++;
 		if (test_bit(RXRPC_TXBUF_LAST, &txb->flags)) {
 			set_bit(RXRPC_CALL_TX_LAST, &call->flags);
 			rot_last = true;
@@ -254,6 +252,11 @@ static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
 {
 	ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags));
 
+	if (unlikely(call->cong_last_nack)) {
+		rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack);
+		call->cong_last_nack = NULL;
+	}
+
 	switch (__rxrpc_call_state(call)) {
 	case RXRPC_CALL_CLIENT_SEND_REQUEST:
 	case RXRPC_CALL_CLIENT_AWAIT_REPLY:
@@ -703,6 +706,43 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
 }
 
 /*
+ * Determine how many nacks from the previous ACK have now been satisfied.
+ */
+static rxrpc_seq_t rxrpc_input_check_prev_ack(struct rxrpc_call *call,
+					      struct rxrpc_ack_summary *summary,
+					      rxrpc_seq_t seq)
+{
+	struct sk_buff *skb = call->cong_last_nack;
+	struct rxrpc_ackpacket ack;
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	unsigned int i, new_acks = 0, retained_nacks = 0;
+	rxrpc_seq_t old_seq = sp->first_ack;
+	u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(ack);
+
+	if (after_eq(seq, old_seq + sp->nr_acks)) {
+		summary->nr_new_acks += sp->nr_nacks;
+		summary->nr_new_acks += seq - (old_seq + sp->nr_acks);
+		summary->nr_retained_nacks = 0;
+	} else if (seq == old_seq) {
+		summary->nr_retained_nacks = sp->nr_nacks;
+	} else {
+		for (i = 0; i < sp->nr_acks; i++) {
+			if (acks[i] == RXRPC_ACK_TYPE_NACK) {
+				if (before(old_seq + i, seq))
+					new_acks++;
+				else
+					retained_nacks++;
+			}
+		}
+
+		summary->nr_new_acks += new_acks;
+		summary->nr_retained_nacks = retained_nacks;
+	}
+
+	return old_seq + sp->nr_acks;
+}
+
+/*
  * Process individual soft ACKs.
  *
  * Each ACK in the array corresponds to one packet and can be either an ACK or
@@ -711,25 +751,51 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
  * the timer on the basis that the peer might just not have processed them at
  * the time the ACK was sent.
  */
-static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks,
-				  rxrpc_seq_t seq, int nr_acks,
-				  struct rxrpc_ack_summary *summary)
+static void rxrpc_input_soft_acks(struct rxrpc_call *call,
+				  struct rxrpc_ack_summary *summary,
+				  struct sk_buff *skb,
+				  rxrpc_seq_t seq,
+				  rxrpc_seq_t since)
 {
-	unsigned int i;
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	unsigned int i, old_nacks = 0;
+	rxrpc_seq_t lowest_nak = seq + sp->nr_acks;
+	u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket);
 
-	for (i = 0; i < nr_acks; i++) {
+	for (i = 0; i < sp->nr_acks; i++) {
 		if (acks[i] == RXRPC_ACK_TYPE_ACK) {
 			summary->nr_acks++;
-			summary->nr_new_acks++;
+			if (after_eq(seq, since))
+				summary->nr_new_acks++;
 		} else {
-			if (!summary->saw_nacks &&
-			    call->acks_lowest_nak != seq + i) {
-				call->acks_lowest_nak = seq + i;
-				summary->new_low_nack = true;
-			}
 			summary->saw_nacks = true;
+			if (before(seq, since)) {
+				/* Overlap with previous ACK */
+				old_nacks++;
+			} else {
+				summary->nr_new_nacks++;
+				sp->nr_nacks++;
+			}
+
+			if (before(seq, lowest_nak))
+				lowest_nak = seq;
 		}
+		seq++;
+	}
+
+	if (lowest_nak != call->acks_lowest_nak) {
+		call->acks_lowest_nak = lowest_nak;
+		summary->new_low_nack = true;
 	}
+
+	/* We *can* have more nacks than we did - the peer is permitted to drop
+	 * packets it has soft-acked and re-request them.  Further, it is
+	 * possible for the nack distribution to change whilst the number of
+	 * nacks stays the same or goes down.
+	 */
+	if (old_nacks < summary->nr_retained_nacks)
+		summary->nr_new_acks += summary->nr_retained_nacks - old_nacks;
+	summary->nr_retained_nacks = old_nacks;
 }
 
 /*
@@ -773,7 +839,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	struct rxrpc_ackinfo info;
 	rxrpc_serial_t ack_serial, acked_serial;
-	rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt;
+	rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt, since;
 	int nr_acks, offset, ioffset;
 
 	_enter("");
@@ -789,6 +855,8 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	prev_pkt = ntohl(ack.previousPacket);
 	hard_ack = first_soft_ack - 1;
 	nr_acks = ack.nAcks;
+	sp->first_ack = first_soft_ack;
+	sp->nr_acks = nr_acks;
 	summary.ack_reason = (ack.reason < RXRPC_ACK__INVALID ?
 			      ack.reason : RXRPC_ACK__INVALID);
 
@@ -858,6 +926,16 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	if (nr_acks > 0)
 		skb_condense(skb);
 
+	if (call->cong_last_nack) {
+		since = rxrpc_input_check_prev_ack(call, &summary, first_soft_ack);
+		rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack);
+		call->cong_last_nack = NULL;
+	} else {
+		summary.nr_new_acks = first_soft_ack - call->acks_first_seq;
+		call->acks_lowest_nak = first_soft_ack + nr_acks;
+		since = first_soft_ack;
+	}
+
 	call->acks_latest_ts = skb->tstamp;
 	call->acks_first_seq = first_soft_ack;
 	call->acks_prev_seq = prev_pkt;
@@ -866,7 +944,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	case RXRPC_ACK_PING:
 		break;
 	default:
-		if (after(acked_serial, call->acks_highest_serial))
+		if (acked_serial && after(acked_serial, call->acks_highest_serial))
 			call->acks_highest_serial = acked_serial;
 		break;
 	}
@@ -905,8 +983,9 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	if (nr_acks > 0) {
 		if (offset > (int)skb->len - nr_acks)
 			return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_short_sack);
-		rxrpc_input_soft_acks(call, skb->data + offset, first_soft_ack,
-				      nr_acks, &summary);
+		rxrpc_input_soft_acks(call, &summary, skb, first_soft_ack, since);
+		rxrpc_get_skb(skb, rxrpc_skb_get_last_nack);
+		call->cong_last_nack = skb;
 	}
 
 	if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) &&
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index c553a30e9c83..34d307368135 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -37,6 +37,17 @@ static void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, int err,
 }
 
 /*
+ * Set or clear the Don't Fragment flag on a socket.
+ */
+void rxrpc_local_dont_fragment(const struct rxrpc_local *local, bool set)
+{
+	if (set)
+		ip_sock_set_mtu_discover(local->socket->sk, IP_PMTUDISC_DO);
+	else
+		ip_sock_set_mtu_discover(local->socket->sk, IP_PMTUDISC_DONT);
+}
+
+/*
  * Compare a local to an address.  Return -ve, 0 or +ve to indicate less than,
  * same or greater than.
  *
@@ -203,7 +214,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 		ip_sock_set_recverr(usk);
 
 		/* we want to set the don't fragment bit */
-		ip_sock_set_mtu_discover(usk, IP_PMTUDISC_DO);
+		rxrpc_local_dont_fragment(local, true);
 
 		/* We want receive timestamps. */
 		sock_enable_timestamps(usk);
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 5e53429c6922..4a292f860ae3 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -216,7 +216,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb)
 	iov[0].iov_len	= sizeof(txb->wire) + sizeof(txb->ack) + n;
 	len = iov[0].iov_len;
 
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 	txb->wire.serial = htonl(serial);
 	trace_rxrpc_tx_ack(call->debug_id, serial,
 			   ntohl(txb->ack.firstPacket),
@@ -302,7 +302,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 	iov[0].iov_base	= &pkt;
 	iov[0].iov_len	= sizeof(pkt);
 
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 	pkt.whdr.serial = htonl(serial);
 
 	iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, sizeof(pkt));
@@ -334,7 +334,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb)
 	_enter("%x,{%d}", txb->seq, txb->len);
 
 	/* Each transmission of a Tx packet needs a new serial number */
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 	txb->wire.serial = htonl(serial);
 
 	if (test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags) &&
@@ -494,14 +494,12 @@ send_fragmentable:
 	switch (conn->local->srx.transport.family) {
 	case AF_INET6:
 	case AF_INET:
-		ip_sock_set_mtu_discover(conn->local->socket->sk,
-					 IP_PMTUDISC_DONT);
+		rxrpc_local_dont_fragment(conn->local, false);
 		rxrpc_inc_stat(call->rxnet, stat_tx_data_send_frag);
 		ret = do_udp_sendmsg(conn->local->socket, &msg, len);
 		conn->peer->last_tx_at = ktime_get_seconds();
 
-		ip_sock_set_mtu_discover(conn->local->socket->sk,
-					 IP_PMTUDISC_DO);
+		rxrpc_local_dont_fragment(conn->local, true);
 		break;
 
 	default:
@@ -560,7 +558,7 @@ void rxrpc_send_conn_abort(struct rxrpc_connection *conn)
 
 	len = iov[0].iov_len + iov[1].iov_len;
 
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 	whdr.serial = htonl(serial);
 
 	iov_iter_kvec(&msg.msg_iter, WRITE, iov, 2, len);
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index 6c86cbb98d1d..26dc2f26d92d 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -181,7 +181,7 @@ print:
 		   atomic_read(&conn->active),
 		   state,
 		   key_serial(conn->key),
-		   atomic_read(&conn->serial),
+		   conn->tx_serial,
 		   conn->hi_serial,
 		   conn->channels[0].call_id,
 		   conn->channels[1].call_id,
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 1bf571a66e02..6b32d61d4cdc 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -664,7 +664,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn)
 
 	len = iov[0].iov_len + iov[1].iov_len;
 
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 	whdr.serial = htonl(serial);
 
 	ret = kernel_sendmsg(conn->local->socket, &msg, iov, 2, len);
@@ -721,10 +721,12 @@ static int rxkad_send_response(struct rxrpc_connection *conn,
 
 	len = iov[0].iov_len + iov[1].iov_len + iov[2].iov_len;
 
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 	whdr.serial = htonl(serial);
 
+	rxrpc_local_dont_fragment(conn->local, false);
 	ret = kernel_sendmsg(conn->local->socket, &msg, iov, 3, len);
+	rxrpc_local_dont_fragment(conn->local, true);
 	if (ret < 0) {
 		trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
 				    rxrpc_tx_point_rxkad_response);
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 12386f590b0f..6faa7d00da09 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -232,18 +232,14 @@ release_idr:
 	return err;
 }
 
-static bool is_mirred_nested(void)
-{
-	return unlikely(__this_cpu_read(mirred_nest_level) > 1);
-}
-
-static int tcf_mirred_forward(bool want_ingress, struct sk_buff *skb)
+static int
+tcf_mirred_forward(bool at_ingress, bool want_ingress, struct sk_buff *skb)
 {
 	int err;
 
 	if (!want_ingress)
 		err = tcf_dev_queue_xmit(skb, dev_queue_xmit);
-	else if (is_mirred_nested())
+	else if (!at_ingress)
 		err = netif_rx(skb);
 	else
 		err = netif_receive_skb(skb);
@@ -270,8 +266,7 @@ static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m,
 	if (unlikely(!(dev->flags & IFF_UP)) || !netif_carrier_ok(dev)) {
 		net_notice_ratelimited("tc mirred to Houston: device %s is down\n",
 				       dev->name);
-		err = -ENODEV;
-		goto out;
+		goto err_cant_do;
 	}
 
 	/* we could easily avoid the clone only if called by ingress and clsact;
@@ -283,10 +278,8 @@ static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m,
 		tcf_mirred_can_reinsert(retval);
 	if (!dont_clone) {
 		skb_to_send = skb_clone(skb, GFP_ATOMIC);
-		if (!skb_to_send) {
-			err =  -ENOMEM;
-			goto out;
-		}
+		if (!skb_to_send)
+			goto err_cant_do;
 	}
 
 	want_ingress = tcf_mirred_act_wants_ingress(m_eaction);
@@ -319,19 +312,20 @@ static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m,
 
 		skb_set_redirected(skb_to_send, skb_to_send->tc_at_ingress);
 
-		err = tcf_mirred_forward(want_ingress, skb_to_send);
+		err = tcf_mirred_forward(at_ingress, want_ingress, skb_to_send);
 	} else {
-		err = tcf_mirred_forward(want_ingress, skb_to_send);
+		err = tcf_mirred_forward(at_ingress, want_ingress, skb_to_send);
 	}
-
-	if (err) {
-out:
+	if (err)
 		tcf_action_inc_overlimit_qstats(&m->common);
-		if (is_redirect)
-			retval = TC_ACT_SHOT;
-	}
 
 	return retval;
+
+err_cant_do:
+	if (is_redirect)
+		retval = TC_ACT_SHOT;
+	tcf_action_inc_overlimit_qstats(&m->common);
+	return retval;
 }
 
 static int tcf_blockcast_redir(struct sk_buff *skb, struct tcf_mirred *m,
@@ -533,8 +527,6 @@ static int mirred_device_event(struct notifier_block *unused,
 				 * net_device are already rcu protected.
 				 */
 				RCU_INIT_POINTER(m->tcfm_dev, NULL);
-			} else if (m->tcfm_blockid) {
-				m->tcfm_blockid = 0;
 			}
 			spin_unlock_bh(&m->tcf_lock);
 		}
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index e3236a3169c3..ff3d396a65aa 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1424,6 +1424,14 @@ static void tcf_block_owner_del(struct tcf_block *block,
 	WARN_ON(1);
 }
 
+static bool tcf_block_tracks_dev(struct tcf_block *block,
+				 struct tcf_block_ext_info *ei)
+{
+	return tcf_block_shared(block) &&
+	       (ei->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS ||
+		ei->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS);
+}
+
 int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
 		      struct tcf_block_ext_info *ei,
 		      struct netlink_ext_ack *extack)
@@ -1462,7 +1470,7 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
 	if (err)
 		goto err_block_offload_bind;
 
-	if (tcf_block_shared(block)) {
+	if (tcf_block_tracks_dev(block, ei)) {
 		err = xa_insert(&block->ports, dev->ifindex, dev, GFP_KERNEL);
 		if (err) {
 			NL_SET_ERR_MSG(extack, "block dev insert failed");
@@ -1516,7 +1524,7 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
 
 	if (!block)
 		return;
-	if (tcf_block_shared(block))
+	if (tcf_block_tracks_dev(block, ei))
 		xa_erase(&block->ports, dev->ifindex);
 	tcf_chain0_head_change_cb_del(block, ei);
 	tcf_block_owner_del(block, q, ei->binder_type);
@@ -1552,6 +1560,9 @@ tcf_block_playback_offloads(struct tcf_block *block, flow_setup_cb_t *cb,
 	     chain_prev = chain,
 		     chain = __tcf_get_next_chain(block, chain),
 		     tcf_chain_put(chain_prev)) {
+		if (chain->tmplt_ops && add)
+			chain->tmplt_ops->tmplt_reoffload(chain, true, cb,
+							  cb_priv);
 		for (tp = __tcf_get_next_proto(chain, NULL); tp;
 		     tp_prev = tp,
 			     tp = __tcf_get_next_proto(chain, tp),
@@ -1567,6 +1578,9 @@ tcf_block_playback_offloads(struct tcf_block *block, flow_setup_cb_t *cb,
 				goto err_playback_remove;
 			}
 		}
+		if (chain->tmplt_ops && !add)
+			chain->tmplt_ops->tmplt_reoffload(chain, false, cb,
+							  cb_priv);
 	}
 
 	return 0;
@@ -2992,7 +3006,8 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net,
 	ops = tcf_proto_lookup_ops(name, true, extack);
 	if (IS_ERR(ops))
 		return PTR_ERR(ops);
-	if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) {
+	if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump ||
+	    !ops->tmplt_reoffload) {
 		NL_SET_ERR_MSG(extack, "Chain templates are not supported with specified classifier");
 		module_put(ops->owner);
 		return -EOPNOTSUPP;
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index e5314a31f75a..6ee7064c82fc 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -2460,8 +2460,11 @@ unbind_filter:
 	}
 
 errout_idr:
-	if (!fold)
+	if (!fold) {
+		spin_lock(&tp->lock);
 		idr_remove(&head->handle_idr, fnew->handle);
+		spin_unlock(&tp->lock);
+	}
 	__fl_put(fnew);
 errout_tb:
 	kfree(tb);
@@ -2721,6 +2724,28 @@ static void fl_tmplt_destroy(void *tmplt_priv)
 	kfree(tmplt);
 }
 
+static void fl_tmplt_reoffload(struct tcf_chain *chain, bool add,
+			       flow_setup_cb_t *cb, void *cb_priv)
+{
+	struct fl_flow_tmplt *tmplt = chain->tmplt_priv;
+	struct flow_cls_offload cls_flower = {};
+
+	cls_flower.rule = flow_rule_alloc(0);
+	if (!cls_flower.rule)
+		return;
+
+	cls_flower.common.chain_index = chain->index;
+	cls_flower.command = add ? FLOW_CLS_TMPLT_CREATE :
+				   FLOW_CLS_TMPLT_DESTROY;
+	cls_flower.cookie = (unsigned long) tmplt;
+	cls_flower.rule->match.dissector = &tmplt->dissector;
+	cls_flower.rule->match.mask = &tmplt->mask;
+	cls_flower.rule->match.key = &tmplt->dummy_key;
+
+	cb(TC_SETUP_CLSFLOWER, &cls_flower, cb_priv);
+	kfree(cls_flower.rule);
+}
+
 static int fl_dump_key_val(struct sk_buff *skb,
 			   void *val, int val_type,
 			   void *mask, int mask_type, int len)
@@ -3628,6 +3653,7 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = {
 	.bind_class	= fl_bind_class,
 	.tmplt_create	= fl_tmplt_create,
 	.tmplt_destroy	= fl_tmplt_destroy,
+	.tmplt_reoffload = fl_tmplt_reoffload,
 	.tmplt_dump	= fl_tmplt_dump,
 	.get_exts	= fl_get_exts,
 	.owner		= THIS_MODULE,
diff --git a/net/sched/em_canid.c b/net/sched/em_canid.c
index 5ea84decec19..5337bc462755 100644
--- a/net/sched/em_canid.c
+++ b/net/sched/em_canid.c
@@ -222,6 +222,7 @@ static void __exit exit_em_canid(void)
 	tcf_em_unregister(&em_canid_ops);
 }
 
+MODULE_DESCRIPTION("ematch classifier to match CAN IDs embedded in skb CAN frames");
 MODULE_LICENSE("GPL");
 
 module_init(init_em_canid);
diff --git a/net/sched/em_cmp.c b/net/sched/em_cmp.c
index f17b049ea530..c90ad7ea26b4 100644
--- a/net/sched/em_cmp.c
+++ b/net/sched/em_cmp.c
@@ -87,6 +87,7 @@ static void __exit exit_em_cmp(void)
 	tcf_em_unregister(&em_cmp_ops);
 }
 
+MODULE_DESCRIPTION("ematch classifier for basic data types(8/16/32 bit) against skb data");
 MODULE_LICENSE("GPL");
 
 module_init(init_em_cmp);
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 09d8afd04a2a..8996c73c9779 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -1006,6 +1006,7 @@ static void __exit exit_em_meta(void)
 	tcf_em_unregister(&em_meta_ops);
 }
 
+MODULE_DESCRIPTION("ematch classifier for various internal kernel metadata, skb metadata and sk metadata");
 MODULE_LICENSE("GPL");
 
 module_init(init_em_meta);
diff --git a/net/sched/em_nbyte.c b/net/sched/em_nbyte.c
index a83b237cbeb0..4f9f21a05d5e 100644
--- a/net/sched/em_nbyte.c
+++ b/net/sched/em_nbyte.c
@@ -68,6 +68,7 @@ static void __exit exit_em_nbyte(void)
 	tcf_em_unregister(&em_nbyte_ops);
 }
 
+MODULE_DESCRIPTION("ematch classifier for arbitrary skb multi-bytes");
 MODULE_LICENSE("GPL");
 
 module_init(init_em_nbyte);
diff --git a/net/sched/em_text.c b/net/sched/em_text.c
index f176afb70559..420c66203b17 100644
--- a/net/sched/em_text.c
+++ b/net/sched/em_text.c
@@ -147,6 +147,7 @@ static void __exit exit_em_text(void)
 	tcf_em_unregister(&em_text_ops);
 }
 
+MODULE_DESCRIPTION("ematch classifier for embedded text in skbs");
 MODULE_LICENSE("GPL");
 
 module_init(init_em_text);
diff --git a/net/sched/em_u32.c b/net/sched/em_u32.c
index 71b070da0437..fdec4db5ec89 100644
--- a/net/sched/em_u32.c
+++ b/net/sched/em_u32.c
@@ -52,6 +52,7 @@ static void __exit exit_em_u32(void)
 	tcf_em_unregister(&em_u32_ops);
 }
 
+MODULE_DESCRIPTION("ematch skb classifier using 32 bit chunks of data");
 MODULE_LICENSE("GPL");
 
 module_init(init_em_u32);
diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c
index 7182c5a450fb..5c1652181805 100644
--- a/net/sctp/inqueue.c
+++ b/net/sctp/inqueue.c
@@ -38,6 +38,14 @@ void sctp_inq_init(struct sctp_inq *queue)
 	INIT_WORK(&queue->immediate, NULL);
 }
 
+/* Properly release the chunk which is being worked on. */
+static inline void sctp_inq_chunk_free(struct sctp_chunk *chunk)
+{
+	if (chunk->head_skb)
+		chunk->skb = chunk->head_skb;
+	sctp_chunk_free(chunk);
+}
+
 /* Release the memory associated with an SCTP inqueue.  */
 void sctp_inq_free(struct sctp_inq *queue)
 {
@@ -53,7 +61,7 @@ void sctp_inq_free(struct sctp_inq *queue)
 	 * free it as well.
 	 */
 	if (queue->in_progress) {
-		sctp_chunk_free(queue->in_progress);
+		sctp_inq_chunk_free(queue->in_progress);
 		queue->in_progress = NULL;
 	}
 }
@@ -130,9 +138,7 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue)
 				goto new_skb;
 			}
 
-			if (chunk->head_skb)
-				chunk->skb = chunk->head_skb;
-			sctp_chunk_free(chunk);
+			sctp_inq_chunk_free(chunk);
 			chunk = queue->in_progress = NULL;
 		} else {
 			/* Nothing to do. Next chunk in the packet, please. */
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index a2cb30af46cb..0f53a5c6fd9d 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -924,6 +924,7 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
 		smc->clcsock->file->private_data = smc->clcsock;
 		smc->clcsock->wq.fasync_list =
 			smc->sk.sk_socket->wq.fasync_list;
+		smc->sk.sk_socket->wq.fasync_list = NULL;
 
 		/* There might be some wait entries remaining
 		 * in smc sk->sk_wq and they should be woken up
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 95cc95458e2d..e4c858411207 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1877,9 +1877,15 @@ static bool smcd_lgr_match(struct smc_link_group *lgr,
 			   struct smcd_dev *smcismdev,
 			   struct smcd_gid *peer_gid)
 {
-	return lgr->peer_gid.gid == peer_gid->gid && lgr->smcd == smcismdev &&
-		smc_ism_is_virtual(smcismdev) ?
-		(lgr->peer_gid.gid_ext == peer_gid->gid_ext) : 1;
+	if (lgr->peer_gid.gid != peer_gid->gid ||
+	    lgr->smcd != smcismdev)
+		return false;
+
+	if (smc_ism_is_virtual(smcismdev) &&
+	    lgr->peer_gid.gid_ext != peer_gid->gid_ext)
+		return false;
+
+	return true;
 }
 
 /* create a new SMC connection (and a new link group if necessary) */
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index 52f7c4f1e767..5a33908015f3 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -164,7 +164,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 	}
 	if (smc_conn_lgr_valid(&smc->conn) && smc->conn.lgr->is_smcd &&
 	    (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) &&
-	    !list_empty(&smc->conn.lgr->list)) {
+	    !list_empty(&smc->conn.lgr->list) && smc->conn.rmb_desc) {
 		struct smc_connection *conn = &smc->conn;
 		struct smcd_diag_dmbinfo dinfo;
 		struct smcd_dev *smcd = conn->lgr->smcd;
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 1af71fbb0d80..c7af0220f82f 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -2280,6 +2280,7 @@ static void __exit exit_rpcsec_gss(void)
 }
 
 MODULE_ALIAS("rpc-auth-6");
+MODULE_DESCRIPTION("Sun RPC Kerberos RPCSEC_GSS client authentication");
 MODULE_LICENSE("GPL");
 module_param_named(expired_cred_retry_delay,
 		   gss_expired_cred_retry_delay,
diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c
index e31cfdf7eadc..64cff717c3d9 100644
--- a/net/sunrpc/auth_gss/gss_krb5_mech.c
+++ b/net/sunrpc/auth_gss/gss_krb5_mech.c
@@ -650,6 +650,7 @@ static void __exit cleanup_kerberos_module(void)
 	gss_mech_unregister(&gss_kerberos_mech);
 }
 
+MODULE_DESCRIPTION("Sun RPC Kerberos 5 module");
 MODULE_LICENSE("GPL");
 module_init(init_kerberos_module);
 module_exit(cleanup_kerberos_module);
diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c
index 691c0000e9ea..bab6cab29405 100644
--- a/net/sunrpc/sunrpc_syms.c
+++ b/net/sunrpc/sunrpc_syms.c
@@ -148,6 +148,7 @@ cleanup_sunrpc(void)
 #endif
 	rcu_barrier(); /* Wait for completion of call_rcu()'s */
 }
+MODULE_DESCRIPTION("Sun RPC core");
 MODULE_LICENSE("GPL");
 fs_initcall(init_sunrpc); /* Ensure we're initialised before nfs */
 module_exit(cleanup_sunrpc);
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index f60c93e5a25d..b969e505c7b7 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1598,10 +1598,10 @@ void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp)
 	/* Finally, send the reply synchronously */
 	if (rqstp->bc_to_initval > 0) {
 		timeout.to_initval = rqstp->bc_to_initval;
-		timeout.to_retries = rqstp->bc_to_initval;
+		timeout.to_retries = rqstp->bc_to_retries;
 	} else {
 		timeout.to_initval = req->rq_xprt->timeout->to_initval;
-		timeout.to_initval = req->rq_xprt->timeout->to_retries;
+		timeout.to_retries = req->rq_xprt->timeout->to_retries;
 	}
 	memcpy(&req->rq_snd_buf, &rqstp->rq_res, sizeof(req->rq_snd_buf));
 	task = rpc_run_bc_task(req, &timeout);
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index bfb2f78523a8..545017a3daa4 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -717,12 +717,12 @@ static int svc_udp_sendto(struct svc_rqst *rqstp)
 				ARRAY_SIZE(rqstp->rq_bvec), xdr);
 
 	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec,
-		      count, 0);
+		      count, rqstp->rq_res.len);
 	err = sock_sendmsg(svsk->sk_sock, &msg);
 	if (err == -ECONNREFUSED) {
 		/* ICMP error on earlier request. */
 		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec,
-			      count, 0);
+			      count, rqstp->rq_res.len);
 		err = sock_sendmsg(svsk->sk_sock, &msg);
 	}
 
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 5b045284849e..c9189a970eec 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -19,6 +19,35 @@
 #include <linux/rtnetlink.h>
 #include <net/switchdev.h>
 
+static bool switchdev_obj_eq(const struct switchdev_obj *a,
+			     const struct switchdev_obj *b)
+{
+	const struct switchdev_obj_port_vlan *va, *vb;
+	const struct switchdev_obj_port_mdb *ma, *mb;
+
+	if (a->id != b->id || a->orig_dev != b->orig_dev)
+		return false;
+
+	switch (a->id) {
+	case SWITCHDEV_OBJ_ID_PORT_VLAN:
+		va = SWITCHDEV_OBJ_PORT_VLAN(a);
+		vb = SWITCHDEV_OBJ_PORT_VLAN(b);
+		return va->flags == vb->flags &&
+			va->vid == vb->vid &&
+			va->changed == vb->changed;
+	case SWITCHDEV_OBJ_ID_PORT_MDB:
+	case SWITCHDEV_OBJ_ID_HOST_MDB:
+		ma = SWITCHDEV_OBJ_PORT_MDB(a);
+		mb = SWITCHDEV_OBJ_PORT_MDB(b);
+		return ma->vid == mb->vid &&
+			ether_addr_equal(ma->addr, mb->addr);
+	default:
+		break;
+	}
+
+	BUG();
+}
+
 static LIST_HEAD(deferred);
 static DEFINE_SPINLOCK(deferred_lock);
 
@@ -307,6 +336,50 @@ int switchdev_port_obj_del(struct net_device *dev,
 }
 EXPORT_SYMBOL_GPL(switchdev_port_obj_del);
 
+/**
+ *	switchdev_port_obj_act_is_deferred - Is object action pending?
+ *
+ *	@dev: port device
+ *	@nt: type of action; add or delete
+ *	@obj: object to test
+ *
+ *	Returns true if a deferred item is pending, which is
+ *	equivalent to the action @nt on an object @obj.
+ *
+ *	rtnl_lock must be held.
+ */
+bool switchdev_port_obj_act_is_deferred(struct net_device *dev,
+					enum switchdev_notifier_type nt,
+					const struct switchdev_obj *obj)
+{
+	struct switchdev_deferred_item *dfitem;
+	bool found = false;
+
+	ASSERT_RTNL();
+
+	spin_lock_bh(&deferred_lock);
+
+	list_for_each_entry(dfitem, &deferred, list) {
+		if (dfitem->dev != dev)
+			continue;
+
+		if ((dfitem->func == switchdev_port_obj_add_deferred &&
+		     nt == SWITCHDEV_PORT_OBJ_ADD) ||
+		    (dfitem->func == switchdev_port_obj_del_deferred &&
+		     nt == SWITCHDEV_PORT_OBJ_DEL)) {
+			if (switchdev_obj_eq((const void *)dfitem->data, obj)) {
+				found = true;
+				break;
+			}
+		}
+	}
+
+	spin_unlock_bh(&deferred_lock);
+
+	return found;
+}
+EXPORT_SYMBOL_GPL(switchdev_port_obj_act_is_deferred);
+
 static ATOMIC_NOTIFIER_HEAD(switchdev_notif_chain);
 static BLOCKING_NOTIFIER_HEAD(switchdev_blocking_notif_chain);
 
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 2cde375477e3..878415c43527 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -1086,6 +1086,12 @@ int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info)
 
 #ifdef CONFIG_TIPC_MEDIA_UDP
 	if (attrs[TIPC_NLA_BEARER_UDP_OPTS]) {
+		if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) {
+			rtnl_unlock();
+			NL_SET_ERR_MSG(info->extack, "UDP option is unsupported");
+			return -EINVAL;
+		}
+
 		err = tipc_udp_nl_bearer_add(b,
 					     attrs[TIPC_NLA_BEARER_UDP_OPTS]);
 		if (err) {
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 1c2c6800949d..b4674f03d71a 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -1003,7 +1003,7 @@ static u16 tls_user_config(struct tls_context *ctx, bool tx)
 	return 0;
 }
 
-static int tls_get_info(const struct sock *sk, struct sk_buff *skb)
+static int tls_get_info(struct sock *sk, struct sk_buff *skb)
 {
 	u16 version, cipher_type;
 	struct tls_context *ctx;
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index e37b4d2e2acd..211f57164cb6 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -52,6 +52,7 @@ struct tls_decrypt_arg {
 	struct_group(inargs,
 	bool zc;
 	bool async;
+	bool async_done;
 	u8 tail;
 	);
 
@@ -63,6 +64,7 @@ struct tls_decrypt_ctx {
 	u8 iv[TLS_MAX_IV_SIZE];
 	u8 aad[TLS_MAX_AAD_SIZE];
 	u8 tail;
+	bool free_sgout;
 	struct scatterlist sg[];
 };
 
@@ -187,7 +189,6 @@ static void tls_decrypt_done(void *data, int err)
 	struct aead_request *aead_req = data;
 	struct crypto_aead *aead = crypto_aead_reqtfm(aead_req);
 	struct scatterlist *sgout = aead_req->dst;
-	struct scatterlist *sgin = aead_req->src;
 	struct tls_sw_context_rx *ctx;
 	struct tls_decrypt_ctx *dctx;
 	struct tls_context *tls_ctx;
@@ -196,6 +197,17 @@ static void tls_decrypt_done(void *data, int err)
 	struct sock *sk;
 	int aead_size;
 
+	/* If requests get too backlogged crypto API returns -EBUSY and calls
+	 * ->complete(-EINPROGRESS) immediately followed by ->complete(0)
+	 * to make waiting for backlog to flush with crypto_wait_req() easier.
+	 * First wait converts -EBUSY -> -EINPROGRESS, and the second one
+	 * -EINPROGRESS -> 0.
+	 * We have a single struct crypto_async_request per direction, this
+	 * scheme doesn't help us, so just ignore the first ->complete().
+	 */
+	if (err == -EINPROGRESS)
+		return;
+
 	aead_size = sizeof(*aead_req) + crypto_aead_reqsize(aead);
 	aead_size = ALIGN(aead_size, __alignof__(*dctx));
 	dctx = (void *)((u8 *)aead_req + aead_size);
@@ -213,7 +225,7 @@ static void tls_decrypt_done(void *data, int err)
 	}
 
 	/* Free the destination pages if skb was not decrypted inplace */
-	if (sgout != sgin) {
+	if (dctx->free_sgout) {
 		/* Skip the first S/G entry as it points to AAD */
 		for_each_sg(sg_next(sgout), sg, UINT_MAX, pages) {
 			if (!sg)
@@ -224,10 +236,17 @@ static void tls_decrypt_done(void *data, int err)
 
 	kfree(aead_req);
 
-	spin_lock_bh(&ctx->decrypt_compl_lock);
-	if (!atomic_dec_return(&ctx->decrypt_pending))
+	if (atomic_dec_and_test(&ctx->decrypt_pending))
 		complete(&ctx->async_wait.completion);
-	spin_unlock_bh(&ctx->decrypt_compl_lock);
+}
+
+static int tls_decrypt_async_wait(struct tls_sw_context_rx *ctx)
+{
+	if (!atomic_dec_and_test(&ctx->decrypt_pending))
+		crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+	atomic_inc(&ctx->decrypt_pending);
+
+	return ctx->async_wait.err;
 }
 
 static int tls_do_decryption(struct sock *sk,
@@ -253,20 +272,33 @@ static int tls_do_decryption(struct sock *sk,
 		aead_request_set_callback(aead_req,
 					  CRYPTO_TFM_REQ_MAY_BACKLOG,
 					  tls_decrypt_done, aead_req);
+		DEBUG_NET_WARN_ON_ONCE(atomic_read(&ctx->decrypt_pending) < 1);
 		atomic_inc(&ctx->decrypt_pending);
 	} else {
+		DECLARE_CRYPTO_WAIT(wait);
+
 		aead_request_set_callback(aead_req,
 					  CRYPTO_TFM_REQ_MAY_BACKLOG,
-					  crypto_req_done, &ctx->async_wait);
+					  crypto_req_done, &wait);
+		ret = crypto_aead_decrypt(aead_req);
+		if (ret == -EINPROGRESS || ret == -EBUSY)
+			ret = crypto_wait_req(ret, &wait);
+		return ret;
 	}
 
 	ret = crypto_aead_decrypt(aead_req);
-	if (ret == -EINPROGRESS) {
-		if (darg->async)
-			return 0;
+	if (ret == -EINPROGRESS)
+		return 0;
 
-		ret = crypto_wait_req(ret, &ctx->async_wait);
+	if (ret == -EBUSY) {
+		ret = tls_decrypt_async_wait(ctx);
+		darg->async_done = true;
+		/* all completions have run, we're not doing async anymore */
+		darg->async = false;
+		return ret;
 	}
+
+	atomic_dec(&ctx->decrypt_pending);
 	darg->async = false;
 
 	return ret;
@@ -439,9 +471,10 @@ static void tls_encrypt_done(void *data, int err)
 	struct tls_rec *rec = data;
 	struct scatterlist *sge;
 	struct sk_msg *msg_en;
-	bool ready = false;
 	struct sock *sk;
-	int pending;
+
+	if (err == -EINPROGRESS) /* see the comment in tls_decrypt_done() */
+		return;
 
 	msg_en = &rec->msg_encrypted;
 
@@ -476,23 +509,25 @@ static void tls_encrypt_done(void *data, int err)
 		/* If received record is at head of tx_list, schedule tx */
 		first_rec = list_first_entry(&ctx->tx_list,
 					     struct tls_rec, list);
-		if (rec == first_rec)
-			ready = true;
+		if (rec == first_rec) {
+			/* Schedule the transmission */
+			if (!test_and_set_bit(BIT_TX_SCHEDULED,
+					      &ctx->tx_bitmask))
+				schedule_delayed_work(&ctx->tx_work.work, 1);
+		}
 	}
 
-	spin_lock_bh(&ctx->encrypt_compl_lock);
-	pending = atomic_dec_return(&ctx->encrypt_pending);
-
-	if (!pending && ctx->async_notify)
+	if (atomic_dec_and_test(&ctx->encrypt_pending))
 		complete(&ctx->async_wait.completion);
-	spin_unlock_bh(&ctx->encrypt_compl_lock);
+}
 
-	if (!ready)
-		return;
+static int tls_encrypt_async_wait(struct tls_sw_context_tx *ctx)
+{
+	if (!atomic_dec_and_test(&ctx->encrypt_pending))
+		crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+	atomic_inc(&ctx->encrypt_pending);
 
-	/* Schedule the transmission */
-	if (!test_and_set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask))
-		schedule_delayed_work(&ctx->tx_work.work, 1);
+	return ctx->async_wait.err;
 }
 
 static int tls_do_encryption(struct sock *sk,
@@ -541,9 +576,14 @@ static int tls_do_encryption(struct sock *sk,
 
 	/* Add the record in tx_list */
 	list_add_tail((struct list_head *)&rec->list, &ctx->tx_list);
+	DEBUG_NET_WARN_ON_ONCE(atomic_read(&ctx->encrypt_pending) < 1);
 	atomic_inc(&ctx->encrypt_pending);
 
 	rc = crypto_aead_encrypt(aead_req);
+	if (rc == -EBUSY) {
+		rc = tls_encrypt_async_wait(ctx);
+		rc = rc ?: -EINPROGRESS;
+	}
 	if (!rc || rc != -EINPROGRESS) {
 		atomic_dec(&ctx->encrypt_pending);
 		sge->offset -= prot->prepend_size;
@@ -984,7 +1024,6 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg,
 	int num_zc = 0;
 	int orig_size;
 	int ret = 0;
-	int pending;
 
 	if (!eor && (msg->msg_flags & MSG_EOR))
 		return -EINVAL;
@@ -1052,7 +1091,11 @@ alloc_encrypted:
 			if (ret < 0)
 				goto send_end;
 			tls_ctx->pending_open_record_frags = true;
-			if (full_record || eor || sk_msg_full(msg_pl))
+
+			if (sk_msg_full(msg_pl))
+				full_record = true;
+
+			if (full_record || eor)
 				goto copied;
 			continue;
 		}
@@ -1159,24 +1202,12 @@ trim_sgl:
 	if (!num_async) {
 		goto send_end;
 	} else if (num_zc) {
-		/* Wait for pending encryptions to get completed */
-		spin_lock_bh(&ctx->encrypt_compl_lock);
-		ctx->async_notify = true;
-
-		pending = atomic_read(&ctx->encrypt_pending);
-		spin_unlock_bh(&ctx->encrypt_compl_lock);
-		if (pending)
-			crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
-		else
-			reinit_completion(&ctx->async_wait.completion);
-
-		/* There can be no concurrent accesses, since we have no
-		 * pending encrypt operations
-		 */
-		WRITE_ONCE(ctx->async_notify, false);
+		int err;
 
-		if (ctx->async_wait.err) {
-			ret = ctx->async_wait.err;
+		/* Wait for pending encryptions to get completed */
+		err = tls_encrypt_async_wait(ctx);
+		if (err) {
+			ret = err;
 			copied = 0;
 		}
 	}
@@ -1225,7 +1256,6 @@ void tls_sw_splice_eof(struct socket *sock)
 	ssize_t copied = 0;
 	bool retrying = false;
 	int ret = 0;
-	int pending;
 
 	if (!ctx->open_rec)
 		return;
@@ -1260,22 +1290,7 @@ retry:
 	}
 
 	/* Wait for pending encryptions to get completed */
-	spin_lock_bh(&ctx->encrypt_compl_lock);
-	ctx->async_notify = true;
-
-	pending = atomic_read(&ctx->encrypt_pending);
-	spin_unlock_bh(&ctx->encrypt_compl_lock);
-	if (pending)
-		crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
-	else
-		reinit_completion(&ctx->async_wait.completion);
-
-	/* There can be no concurrent accesses, since we have no pending
-	 * encrypt operations
-	 */
-	WRITE_ONCE(ctx->async_notify, false);
-
-	if (ctx->async_wait.err)
+	if (tls_encrypt_async_wait(ctx))
 		goto unlock;
 
 	/* Transmit if any encryptions have completed */
@@ -1577,12 +1592,16 @@ static int tls_decrypt_sg(struct sock *sk, struct iov_iter *out_iov,
 	} else if (out_sg) {
 		memcpy(sgout, out_sg, n_sgout * sizeof(*sgout));
 	}
+	dctx->free_sgout = !!pages;
 
 	/* Prepare and submit AEAD request */
 	err = tls_do_decryption(sk, sgin, sgout, dctx->iv,
 				data_len + prot->tail_size, aead_req, darg);
-	if (err)
+	if (err) {
+		if (darg->async_done)
+			goto exit_free_skb;
 		goto exit_free_pages;
+	}
 
 	darg->skb = clear_skb ?: tls_strp_msg(ctx);
 	clear_skb = NULL;
@@ -1594,6 +1613,9 @@ static int tls_decrypt_sg(struct sock *sk, struct iov_iter *out_iov,
 		return err;
 	}
 
+	if (unlikely(darg->async_done))
+		return 0;
+
 	if (prot->tail_size)
 		darg->tail = dctx->tail;
 
@@ -1765,7 +1787,8 @@ static int process_rx_list(struct tls_sw_context_rx *ctx,
 			   u8 *control,
 			   size_t skip,
 			   size_t len,
-			   bool is_peek)
+			   bool is_peek,
+			   bool *more)
 {
 	struct sk_buff *skb = skb_peek(&ctx->rx_list);
 	struct tls_msg *tlm;
@@ -1778,7 +1801,7 @@ static int process_rx_list(struct tls_sw_context_rx *ctx,
 
 		err = tls_record_content_type(msg, tlm, control);
 		if (err <= 0)
-			goto out;
+			goto more;
 
 		if (skip < rxm->full_len)
 			break;
@@ -1796,12 +1819,12 @@ static int process_rx_list(struct tls_sw_context_rx *ctx,
 
 		err = tls_record_content_type(msg, tlm, control);
 		if (err <= 0)
-			goto out;
+			goto more;
 
 		err = skb_copy_datagram_msg(skb, rxm->offset + skip,
 					    msg, chunk);
 		if (err < 0)
-			goto out;
+			goto more;
 
 		len = len - chunk;
 		copied = copied + chunk;
@@ -1837,6 +1860,10 @@ static int process_rx_list(struct tls_sw_context_rx *ctx,
 
 out:
 	return copied ? : err;
+more:
+	if (more)
+		*more = true;
+	goto out;
 }
 
 static bool
@@ -1936,10 +1963,12 @@ int tls_sw_recvmsg(struct sock *sk,
 	struct strp_msg *rxm;
 	struct tls_msg *tlm;
 	ssize_t copied = 0;
+	ssize_t peeked = 0;
 	bool async = false;
 	int target, err;
 	bool is_kvec = iov_iter_is_kvec(&msg->msg_iter);
 	bool is_peek = flags & MSG_PEEK;
+	bool rx_more = false;
 	bool released = true;
 	bool bpf_strp_enabled;
 	bool zc_capable;
@@ -1959,12 +1988,12 @@ int tls_sw_recvmsg(struct sock *sk,
 		goto end;
 
 	/* Process pending decrypted records. It must be non-zero-copy */
-	err = process_rx_list(ctx, msg, &control, 0, len, is_peek);
+	err = process_rx_list(ctx, msg, &control, 0, len, is_peek, &rx_more);
 	if (err < 0)
 		goto end;
 
 	copied = err;
-	if (len <= copied)
+	if (len <= copied || (copied && control != TLS_RECORD_TYPE_DATA) || rx_more)
 		goto end;
 
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
@@ -2057,6 +2086,8 @@ put_on_rx_list:
 				decrypted += chunk;
 				len -= chunk;
 				__skb_queue_tail(&ctx->rx_list, skb);
+				if (unlikely(control != TLS_RECORD_TYPE_DATA))
+					break;
 				continue;
 			}
 
@@ -2080,8 +2111,10 @@ put_on_rx_list:
 			if (err < 0)
 				goto put_on_rx_list_err;
 
-			if (is_peek)
+			if (is_peek) {
+				peeked += chunk;
 				goto put_on_rx_list;
+			}
 
 			if (partially_consumed) {
 				rxm->offset += chunk;
@@ -2105,16 +2138,10 @@ put_on_rx_list:
 
 recv_end:
 	if (async) {
-		int ret, pending;
+		int ret;
 
 		/* Wait for all previously submitted records to be decrypted */
-		spin_lock_bh(&ctx->decrypt_compl_lock);
-		reinit_completion(&ctx->async_wait.completion);
-		pending = atomic_read(&ctx->decrypt_pending);
-		spin_unlock_bh(&ctx->decrypt_compl_lock);
-		ret = 0;
-		if (pending)
-			ret = crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+		ret = tls_decrypt_async_wait(ctx);
 		__skb_queue_purge(&ctx->async_hold);
 
 		if (ret) {
@@ -2126,12 +2153,11 @@ recv_end:
 
 		/* Drain records from the rx_list & copy if required */
 		if (is_peek || is_kvec)
-			err = process_rx_list(ctx, msg, &control, copied,
-					      decrypted, is_peek);
+			err = process_rx_list(ctx, msg, &control, copied + peeked,
+					      decrypted - peeked, is_peek, NULL);
 		else
 			err = process_rx_list(ctx, msg, &control, 0,
-					      async_copy_bytes, is_peek);
-		decrypted += max(err, 0);
+					      async_copy_bytes, is_peek, NULL);
 	}
 
 	copied += decrypted;
@@ -2431,16 +2457,9 @@ void tls_sw_release_resources_tx(struct sock *sk)
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
 	struct tls_rec *rec, *tmp;
-	int pending;
 
 	/* Wait for any pending async encryptions to complete */
-	spin_lock_bh(&ctx->encrypt_compl_lock);
-	ctx->async_notify = true;
-	pending = atomic_read(&ctx->encrypt_pending);
-	spin_unlock_bh(&ctx->encrypt_compl_lock);
-
-	if (pending)
-		crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+	tls_encrypt_async_wait(ctx);
 
 	tls_tx_records(sk, -1);
 
@@ -2603,7 +2622,7 @@ static struct tls_sw_context_tx *init_ctx_tx(struct tls_context *ctx, struct soc
 	}
 
 	crypto_init_wait(&sw_ctx_tx->async_wait);
-	spin_lock_init(&sw_ctx_tx->encrypt_compl_lock);
+	atomic_set(&sw_ctx_tx->encrypt_pending, 1);
 	INIT_LIST_HEAD(&sw_ctx_tx->tx_list);
 	INIT_DELAYED_WORK(&sw_ctx_tx->tx_work.work, tx_work_handler);
 	sw_ctx_tx->tx_work.sk = sk;
@@ -2624,7 +2643,7 @@ static struct tls_sw_context_rx *init_ctx_rx(struct tls_context *ctx)
 	}
 
 	crypto_init_wait(&sw_ctx_rx->async_wait);
-	spin_lock_init(&sw_ctx_rx->decrypt_compl_lock);
+	atomic_set(&sw_ctx_rx->decrypt_pending, 1);
 	init_waitqueue_head(&sw_ctx_rx->wq);
 	skb_queue_head_init(&sw_ctx_rx->rx_list);
 	skb_queue_head_init(&sw_ctx_rx->async_hold);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index ac1f2bc18fc9..0748e7ea5210 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -782,19 +782,6 @@ static int unix_seqpacket_sendmsg(struct socket *, struct msghdr *, size_t);
 static int unix_seqpacket_recvmsg(struct socket *, struct msghdr *, size_t,
 				  int);
 
-static int unix_set_peek_off(struct sock *sk, int val)
-{
-	struct unix_sock *u = unix_sk(sk);
-
-	if (mutex_lock_interruptible(&u->iolock))
-		return -EINTR;
-
-	WRITE_ONCE(sk->sk_peek_off, val);
-	mutex_unlock(&u->iolock);
-
-	return 0;
-}
-
 #ifdef CONFIG_PROC_FS
 static int unix_count_nr_fds(struct sock *sk)
 {
@@ -862,7 +849,7 @@ static const struct proto_ops unix_stream_ops = {
 	.read_skb =	unix_stream_read_skb,
 	.mmap =		sock_no_mmap,
 	.splice_read =	unix_stream_splice_read,
-	.set_peek_off =	unix_set_peek_off,
+	.set_peek_off =	sk_set_peek_off,
 	.show_fdinfo =	unix_show_fdinfo,
 };
 
@@ -886,7 +873,7 @@ static const struct proto_ops unix_dgram_ops = {
 	.read_skb =	unix_read_skb,
 	.recvmsg =	unix_dgram_recvmsg,
 	.mmap =		sock_no_mmap,
-	.set_peek_off =	unix_set_peek_off,
+	.set_peek_off =	sk_set_peek_off,
 	.show_fdinfo =	unix_show_fdinfo,
 };
 
@@ -909,7 +896,7 @@ static const struct proto_ops unix_seqpacket_ops = {
 	.sendmsg =	unix_seqpacket_sendmsg,
 	.recvmsg =	unix_seqpacket_recvmsg,
 	.mmap =		sock_no_mmap,
-	.set_peek_off =	unix_set_peek_off,
+	.set_peek_off =	sk_set_peek_off,
 	.show_fdinfo =	unix_show_fdinfo,
 };
 
@@ -1344,13 +1331,11 @@ static void unix_state_double_lock(struct sock *sk1, struct sock *sk2)
 		unix_state_lock(sk1);
 		return;
 	}
-	if (sk1 < sk2) {
-		unix_state_lock(sk1);
-		unix_state_lock_nested(sk2);
-	} else {
-		unix_state_lock(sk2);
-		unix_state_lock_nested(sk1);
-	}
+	if (sk1 > sk2)
+		swap(sk1, sk2);
+
+	unix_state_lock(sk1);
+	unix_state_lock_nested(sk2, U_LOCK_SECOND);
 }
 
 static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2)
@@ -1591,7 +1576,7 @@ restart:
 		goto out_unlock;
 	}
 
-	unix_state_lock_nested(sk);
+	unix_state_lock_nested(sk, U_LOCK_SECOND);
 
 	if (sk->sk_state != st) {
 		unix_state_unlock(sk);
diff --git a/net/unix/diag.c b/net/unix/diag.c
index bec09a3a1d44..be19827eca36 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -84,7 +84,7 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb)
 			 * queue lock. With the other's queue locked it's
 			 * OK to lock the state.
 			 */
-			unix_state_lock_nested(req);
+			unix_state_lock_nested(req, U_LOCK_DIAG);
 			peer = unix_sk(req)->peer;
 			buf[i++] = (peer ? sock_i_ino(peer) : 0);
 			unix_state_unlock(req);
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 2405f0f9af31..2a81880dac7b 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -284,9 +284,17 @@ void unix_gc(void)
 	 * which are creating the cycle(s).
 	 */
 	skb_queue_head_init(&hitlist);
-	list_for_each_entry(u, &gc_candidates, link)
+	list_for_each_entry(u, &gc_candidates, link) {
 		scan_children(&u->sk, inc_inflight, &hitlist);
 
+#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
+		if (u->oob_skb) {
+			kfree_skb(u->oob_skb);
+			u->oob_skb = NULL;
+		}
+#endif
+	}
+
 	/* not_cycle_list contains those sockets which do not make up a
 	 * cycle.  Restore these to the inflight list.
 	 */
diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig
index a9ac85e09af3..10345388ad13 100644
--- a/net/wireless/Kconfig
+++ b/net/wireless/Kconfig
@@ -206,7 +206,6 @@ config CFG80211_KUNIT_TEST
 	depends on KUNIT
 	depends on CFG80211
 	default KUNIT_ALL_TESTS
-	depends on !KERNEL_6_2
 	help
 	  Enable this option to test cfg80211 functions with kunit.
 
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 409d74c57ca0..3fb1b637352a 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -5,7 +5,7 @@
  * Copyright 2006-2010		Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright 2015-2017	Intel Deutschland GmbH
- * Copyright (C) 2018-2023 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -1661,6 +1661,7 @@ void wiphy_delayed_work_queue(struct wiphy *wiphy,
 			      unsigned long delay)
 {
 	if (!delay) {
+		del_timer(&dwork->timer);
 		wiphy_work_queue(wiphy, &dwork->work);
 		return;
 	}
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 60877b532993..bd54a928bab4 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4020,6 +4020,7 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback *
 		}
 		wiphy_unlock(&rdev->wiphy);
 
+		if_start = 0;
 		wp_idx++;
 	}
  out:
@@ -4196,6 +4197,8 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info)
 
 		if (ntype != NL80211_IFTYPE_MESH_POINT)
 			return -EINVAL;
+		if (otype != NL80211_IFTYPE_MESH_POINT)
+			return -EINVAL;
 		if (netif_running(dev))
 			return -EBUSY;
 
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 2249b1a89d1c..389a52c29bfc 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -1731,6 +1731,61 @@ static void cfg80211_update_hidden_bsses(struct cfg80211_internal_bss *known,
 	}
 }
 
+static void cfg80211_check_stuck_ecsa(struct cfg80211_registered_device *rdev,
+				      struct cfg80211_internal_bss *known,
+				      const struct cfg80211_bss_ies *old)
+{
+	const struct ieee80211_ext_chansw_ie *ecsa;
+	const struct element *elem_new, *elem_old;
+	const struct cfg80211_bss_ies *new, *bcn;
+
+	if (known->pub.proberesp_ecsa_stuck)
+		return;
+
+	new = rcu_dereference_protected(known->pub.proberesp_ies,
+					lockdep_is_held(&rdev->bss_lock));
+	if (WARN_ON(!new))
+		return;
+
+	if (new->tsf - old->tsf < USEC_PER_SEC)
+		return;
+
+	elem_old = cfg80211_find_elem(WLAN_EID_EXT_CHANSWITCH_ANN,
+				      old->data, old->len);
+	if (!elem_old)
+		return;
+
+	elem_new = cfg80211_find_elem(WLAN_EID_EXT_CHANSWITCH_ANN,
+				      new->data, new->len);
+	if (!elem_new)
+		return;
+
+	bcn = rcu_dereference_protected(known->pub.beacon_ies,
+					lockdep_is_held(&rdev->bss_lock));
+	if (bcn &&
+	    cfg80211_find_elem(WLAN_EID_EXT_CHANSWITCH_ANN,
+			       bcn->data, bcn->len))
+		return;
+
+	if (elem_new->datalen != elem_old->datalen)
+		return;
+	if (elem_new->datalen < sizeof(struct ieee80211_ext_chansw_ie))
+		return;
+	if (memcmp(elem_new->data, elem_old->data, elem_new->datalen))
+		return;
+
+	ecsa = (void *)elem_new->data;
+
+	if (!ecsa->mode)
+		return;
+
+	if (ecsa->new_ch_num !=
+	    ieee80211_frequency_to_channel(known->pub.channel->center_freq))
+		return;
+
+	known->pub.proberesp_ecsa_stuck = 1;
+}
+
 static bool
 cfg80211_update_known_bss(struct cfg80211_registered_device *rdev,
 			  struct cfg80211_internal_bss *known,
@@ -1750,8 +1805,10 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev,
 		/* Override possible earlier Beacon frame IEs */
 		rcu_assign_pointer(known->pub.ies,
 				   new->pub.proberesp_ies);
-		if (old)
+		if (old) {
+			cfg80211_check_stuck_ecsa(rdev, known, old);
 			kfree_rcu((struct cfg80211_bss_ies *)old, rcu_head);
+		}
 	}
 
 	if (rcu_access_pointer(new->pub.beacon_ies)) {
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 9f13aa3353e3..b78c0e095e22 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -167,8 +167,10 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 		contd = XDP_PKT_CONTD;
 
 	err = __xsk_rcv_zc(xs, xskb, len, contd);
-	if (err || likely(!frags))
-		goto out;
+	if (err)
+		goto err;
+	if (likely(!frags))
+		return 0;
 
 	xskb_list = &xskb->pool->xskb_list;
 	list_for_each_entry_safe(pos, tmp, xskb_list, xskb_list_node) {
@@ -177,11 +179,13 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 		len = pos->xdp.data_end - pos->xdp.data;
 		err = __xsk_rcv_zc(xs, pos, len, contd);
 		if (err)
-			return err;
+			goto err;
 		list_del(&pos->xskb_list_node);
 	}
 
-out:
+	return 0;
+err:
+	xsk_buff_free(xdp);
 	return err;
 }
 
@@ -718,7 +722,8 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 			memcpy(vaddr, buffer, len);
 			kunmap_local(vaddr);
 
-			skb_add_rx_frag(skb, nr_frags, page, 0, len, 0);
+			skb_add_rx_frag(skb, nr_frags, page, 0, len, PAGE_SIZE);
+			refcount_add(PAGE_SIZE, &xs->sk.sk_wmem_alloc);
 		}
 
 		if (first_frag && desc->options & XDP_TX_METADATA) {
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 28711cc44ced..ce60ecd48a4d 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -555,6 +555,7 @@ struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool)
 
 	xskb->xdp.data = xskb->xdp.data_hard_start + XDP_PACKET_HEADROOM;
 	xskb->xdp.data_meta = xskb->xdp.data;
+	xskb->xdp.flags = 0;
 
 	if (pool->dma_need_sync) {
 		dma_sync_single_range_for_device(pool->dev, xskb->dma, 0,
diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c
index 41533c631431..e6da7e8495c9 100644
--- a/net/xfrm/xfrm_algo.c
+++ b/net/xfrm/xfrm_algo.c
@@ -858,4 +858,5 @@ int xfrm_count_pfkey_enc_supported(void)
 }
 EXPORT_SYMBOL_GPL(xfrm_count_pfkey_enc_supported);
 
+MODULE_DESCRIPTION("XFRM Algorithm interface");
 MODULE_LICENSE("GPL");
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 3784534c9185..653e51ae3964 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -407,7 +407,7 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 	struct net_device *dev = x->xso.dev;
 
-	if (!x->type_offload || x->encap)
+	if (!x->type_offload)
 		return false;
 
 	if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET ||
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 662c83beb345..e5722c95b8bb 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -704,9 +704,13 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb_dst(skb)->dev);
 	struct xfrm_state *x = skb_dst(skb)->xfrm;
+	int family;
 	int err;
 
-	switch (x->outer_mode.family) {
+	family = (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) ? x->outer_mode.family
+		: skb_dst(skb)->ops->family;
+
+	switch (family) {
 	case AF_INET:
 		memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 		IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 1b7e75159727..da6ecc6b3e15 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2694,7 +2694,9 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 			if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m)
 				mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]);
 
-			family = xfrm[i]->props.family;
+			if (xfrm[i]->xso.type != XFRM_DEV_OFFLOAD_PACKET)
+				family = xfrm[i]->props.family;
+
 			oif = fl->flowi_oif ? : fl->flowi_l3mdev;
 			dst = xfrm_dst_lookup(xfrm[i], tos, oif,
 					      &saddr, &daddr, family, mark);
@@ -3416,7 +3418,7 @@ decode_session4(const struct xfrm_flow_keys *flkeys, struct flowi *fl, bool reve
 	}
 
 	fl4->flowi4_proto = flkeys->basic.ip_proto;
-	fl4->flowi4_tos = flkeys->ip.tos;
+	fl4->flowi4_tos = flkeys->ip.tos & ~INET_ECN_MASK;
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index ad01997c3aa9..912c1189ba41 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -2017,6 +2017,9 @@ static int copy_to_user_tmpl(struct xfrm_policy *xp, struct sk_buff *skb)
 	if (xp->xfrm_nr == 0)
 		return 0;
 
+	if (xp->xfrm_nr > XFRM_MAX_DEPTH)
+		return -ENOBUFS;
+
 	for (i = 0; i < xp->xfrm_nr; i++) {
 		struct xfrm_user_tmpl *up = &vec[i];
 		struct xfrm_tmpl *kp = &xp->xfrm_vec[i];
@@ -3888,5 +3891,6 @@ static void __exit xfrm_user_exit(void)
 
 module_init(xfrm_user_init);
 module_exit(xfrm_user_exit);
+MODULE_DESCRIPTION("XFRM User interface");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_XFRM);
diff --git a/rust/Makefile b/rust/Makefile
index 9d2a16cc91cb..a78fcf4004b0 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -40,7 +40,7 @@ obj-$(CONFIG_RUST_KERNEL_DOCTESTS) += doctests_kernel_generated_kunit.o
 ifdef CONFIG_RUST
 
 # `$(rust_flags)` is passed in case the user added `--sysroot`.
-rustc_sysroot := $(shell $(RUSTC) $(rust_flags) --print sysroot)
+rustc_sysroot := $(shell MAKEFLAGS= $(RUSTC) $(rust_flags) --print sysroot)
 rustc_host_target := $(shell $(RUSTC) --version --verbose | grep -F 'host: ' | cut -d' ' -f2)
 RUST_LIB_SRC ?= $(rustc_sysroot)/lib/rustlib/src/rust/library
 
@@ -108,14 +108,14 @@ rustdoc-macros: private rustdoc_host = yes
 rustdoc-macros: private rustc_target_flags = --crate-type proc-macro \
     --extern proc_macro
 rustdoc-macros: $(src)/macros/lib.rs FORCE
-	$(call if_changed,rustdoc)
+	+$(call if_changed,rustdoc)
 
 rustdoc-core: private rustc_target_flags = $(core-cfgs)
 rustdoc-core: $(RUST_LIB_SRC)/core/src/lib.rs FORCE
-	$(call if_changed,rustdoc)
+	+$(call if_changed,rustdoc)
 
 rustdoc-compiler_builtins: $(src)/compiler_builtins.rs rustdoc-core FORCE
-	$(call if_changed,rustdoc)
+	+$(call if_changed,rustdoc)
 
 # We need to allow `rustdoc::broken_intra_doc_links` because some
 # `no_global_oom_handling` functions refer to non-`no_global_oom_handling`
@@ -124,7 +124,7 @@ rustdoc-compiler_builtins: $(src)/compiler_builtins.rs rustdoc-core FORCE
 rustdoc-alloc: private rustc_target_flags = $(alloc-cfgs) \
     -Arustdoc::broken_intra_doc_links
 rustdoc-alloc: $(src)/alloc/lib.rs rustdoc-core rustdoc-compiler_builtins FORCE
-	$(call if_changed,rustdoc)
+	+$(call if_changed,rustdoc)
 
 rustdoc-kernel: private rustc_target_flags = --extern alloc \
     --extern build_error --extern macros=$(objtree)/$(obj)/libmacros.so \
@@ -132,7 +132,7 @@ rustdoc-kernel: private rustc_target_flags = --extern alloc \
 rustdoc-kernel: $(src)/kernel/lib.rs rustdoc-core rustdoc-macros \
     rustdoc-compiler_builtins rustdoc-alloc $(obj)/libmacros.so \
     $(obj)/bindings.o FORCE
-	$(call if_changed,rustdoc)
+	+$(call if_changed,rustdoc)
 
 quiet_cmd_rustc_test_library = RUSTC TL $<
       cmd_rustc_test_library = \
@@ -146,18 +146,18 @@ quiet_cmd_rustc_test_library = RUSTC TL $<
 		--crate-name $(subst rusttest-,,$(subst rusttestlib-,,$@)) $<
 
 rusttestlib-build_error: $(src)/build_error.rs rusttest-prepare FORCE
-	$(call if_changed,rustc_test_library)
+	+$(call if_changed,rustc_test_library)
 
 rusttestlib-macros: private rustc_target_flags = --extern proc_macro
 rusttestlib-macros: private rustc_test_library_proc = yes
 rusttestlib-macros: $(src)/macros/lib.rs rusttest-prepare FORCE
-	$(call if_changed,rustc_test_library)
+	+$(call if_changed,rustc_test_library)
 
 rusttestlib-bindings: $(src)/bindings/lib.rs rusttest-prepare FORCE
-	$(call if_changed,rustc_test_library)
+	+$(call if_changed,rustc_test_library)
 
 rusttestlib-uapi: $(src)/uapi/lib.rs rusttest-prepare FORCE
-	$(call if_changed,rustc_test_library)
+	+$(call if_changed,rustc_test_library)
 
 quiet_cmd_rustdoc_test = RUSTDOC T $<
       cmd_rustdoc_test = \
@@ -189,7 +189,7 @@ quiet_cmd_rustdoc_test_kernel = RUSTDOC TK $<
     $(src)/kernel/lib.rs $(obj)/kernel.o \
     $(objtree)/scripts/rustdoc_test_builder \
     $(objtree)/scripts/rustdoc_test_gen FORCE
-	$(call if_changed,rustdoc_test_kernel)
+	+$(call if_changed,rustdoc_test_kernel)
 
 # We cannot use `-Zpanic-abort-tests` because some tests are dynamic,
 # so for the moment we skip `-Cpanic=abort`.
@@ -254,21 +254,21 @@ quiet_cmd_rustsysroot = RUSTSYSROOT
 		$(objtree)/$(obj)/test/sysroot/lib/rustlib/$(rustc_host_target)/lib
 
 rusttest-prepare: FORCE
-	$(call if_changed,rustsysroot)
+	+$(call if_changed,rustsysroot)
 
 rusttest-macros: private rustc_target_flags = --extern proc_macro
 rusttest-macros: private rustdoc_test_target_flags = --crate-type proc-macro
 rusttest-macros: $(src)/macros/lib.rs rusttest-prepare FORCE
-	$(call if_changed,rustc_test)
-	$(call if_changed,rustdoc_test)
+	+$(call if_changed,rustc_test)
+	+$(call if_changed,rustdoc_test)
 
 rusttest-kernel: private rustc_target_flags = --extern alloc \
     --extern build_error --extern macros --extern bindings --extern uapi
 rusttest-kernel: $(src)/kernel/lib.rs rusttest-prepare \
     rusttestlib-build_error rusttestlib-macros rusttestlib-bindings \
     rusttestlib-uapi FORCE
-	$(call if_changed,rustc_test)
-	$(call if_changed,rustc_test_library)
+	+$(call if_changed,rustc_test)
+	+$(call if_changed,rustc_test_library)
 
 ifdef CONFIG_CC_IS_CLANG
 bindgen_c_flags = $(c_flags)
@@ -396,7 +396,7 @@ quiet_cmd_rustc_procmacro = $(RUSTC_OR_CLIPPY_QUIET) P $@
 # Therefore, to get `libmacros.so` automatically recompiled when the compiler
 # version changes, we add `core.o` as a dependency (even if it is not needed).
 $(obj)/libmacros.so: $(src)/macros/lib.rs $(obj)/core.o FORCE
-	$(call if_changed_dep,rustc_procmacro)
+	+$(call if_changed_dep,rustc_procmacro)
 
 quiet_cmd_rustc_library = $(if $(skip_clippy),RUSTC,$(RUSTC_OR_CLIPPY_QUIET)) L $@
       cmd_rustc_library = \
@@ -435,36 +435,36 @@ $(obj)/core.o: private skip_flags = -Dunreachable_pub
 $(obj)/core.o: private rustc_objcopy = $(foreach sym,$(redirect-intrinsics),--redefine-sym $(sym)=__rust$(sym))
 $(obj)/core.o: private rustc_target_flags = $(core-cfgs)
 $(obj)/core.o: $(RUST_LIB_SRC)/core/src/lib.rs scripts/target.json FORCE
-	$(call if_changed_dep,rustc_library)
+	+$(call if_changed_dep,rustc_library)
 
 $(obj)/compiler_builtins.o: private rustc_objcopy = -w -W '__*'
 $(obj)/compiler_builtins.o: $(src)/compiler_builtins.rs $(obj)/core.o FORCE
-	$(call if_changed_dep,rustc_library)
+	+$(call if_changed_dep,rustc_library)
 
 $(obj)/alloc.o: private skip_clippy = 1
 $(obj)/alloc.o: private skip_flags = -Dunreachable_pub
 $(obj)/alloc.o: private rustc_target_flags = $(alloc-cfgs)
 $(obj)/alloc.o: $(src)/alloc/lib.rs $(obj)/compiler_builtins.o FORCE
-	$(call if_changed_dep,rustc_library)
+	+$(call if_changed_dep,rustc_library)
 
 $(obj)/build_error.o: $(src)/build_error.rs $(obj)/compiler_builtins.o FORCE
-	$(call if_changed_dep,rustc_library)
+	+$(call if_changed_dep,rustc_library)
 
 $(obj)/bindings.o: $(src)/bindings/lib.rs \
     $(obj)/compiler_builtins.o \
     $(obj)/bindings/bindings_generated.rs \
     $(obj)/bindings/bindings_helpers_generated.rs FORCE
-	$(call if_changed_dep,rustc_library)
+	+$(call if_changed_dep,rustc_library)
 
 $(obj)/uapi.o: $(src)/uapi/lib.rs \
     $(obj)/compiler_builtins.o \
     $(obj)/uapi/uapi_generated.rs FORCE
-	$(call if_changed_dep,rustc_library)
+	+$(call if_changed_dep,rustc_library)
 
 $(obj)/kernel.o: private rustc_target_flags = --extern alloc \
     --extern build_error --extern macros --extern bindings --extern uapi
 $(obj)/kernel.o: $(src)/kernel/lib.rs $(obj)/alloc.o $(obj)/build_error.o \
     $(obj)/libmacros.so $(obj)/bindings.o $(obj)/uapi.o FORCE
-	$(call if_changed_dep,rustc_library)
+	+$(call if_changed_dep,rustc_library)
 
 endif # CONFIG_RUST
diff --git a/rust/alloc/alloc.rs b/rust/alloc/alloc.rs
index 150e13750ff7..abb791cc2371 100644
--- a/rust/alloc/alloc.rs
+++ b/rust/alloc/alloc.rs
@@ -379,13 +379,20 @@ pub const fn handle_alloc_error(layout: Layout) -> ! {
         panic!("allocation failed");
     }
 
+    #[inline]
     fn rt_error(layout: Layout) -> ! {
         unsafe {
             __rust_alloc_error_handler(layout.size(), layout.align());
         }
     }
 
-    unsafe { core::intrinsics::const_eval_select((layout,), ct_error, rt_error) }
+    #[cfg(not(feature = "panic_immediate_abort"))]
+    unsafe {
+        core::intrinsics::const_eval_select((layout,), ct_error, rt_error)
+    }
+
+    #[cfg(feature = "panic_immediate_abort")]
+    ct_error(layout)
 }
 
 // For alloc test `std::alloc::handle_alloc_error` can be used directly.
@@ -418,12 +425,14 @@ pub mod __alloc_error_handler {
     }
 }
 
+#[cfg(not(no_global_oom_handling))]
 /// Specialize clones into pre-allocated, uninitialized memory.
 /// Used by `Box::clone` and `Rc`/`Arc::make_mut`.
 pub(crate) trait WriteCloneIntoRaw: Sized {
     unsafe fn write_clone_into_raw(&self, target: *mut Self);
 }
 
+#[cfg(not(no_global_oom_handling))]
 impl<T: Clone> WriteCloneIntoRaw for T {
     #[inline]
     default unsafe fn write_clone_into_raw(&self, target: *mut Self) {
@@ -433,6 +442,7 @@ impl<T: Clone> WriteCloneIntoRaw for T {
     }
 }
 
+#[cfg(not(no_global_oom_handling))]
 impl<T: Copy> WriteCloneIntoRaw for T {
     #[inline]
     unsafe fn write_clone_into_raw(&self, target: *mut Self) {
diff --git a/rust/alloc/boxed.rs b/rust/alloc/boxed.rs
index 9620eba17268..c93a22a5c97f 100644
--- a/rust/alloc/boxed.rs
+++ b/rust/alloc/boxed.rs
@@ -161,7 +161,7 @@ use core::marker::Tuple;
 use core::marker::Unsize;
 use core::mem::{self, SizedTypeProperties};
 use core::ops::{
-    CoerceUnsized, Deref, DerefMut, DispatchFromDyn, Generator, GeneratorState, Receiver,
+    CoerceUnsized, Coroutine, CoroutineState, Deref, DerefMut, DispatchFromDyn, Receiver,
 };
 use core::pin::Pin;
 use core::ptr::{self, NonNull, Unique};
@@ -211,7 +211,7 @@ impl<T> Box<T> {
     /// ```
     /// let five = Box::new(5);
     /// ```
-    #[cfg(all(not(no_global_oom_handling)))]
+    #[cfg(not(no_global_oom_handling))]
     #[inline(always)]
     #[stable(feature = "rust1", since = "1.0.0")]
     #[must_use]
@@ -1042,10 +1042,18 @@ impl<T: ?Sized, A: Allocator> Box<T, A> {
     /// use std::ptr;
     ///
     /// let x = Box::new(String::from("Hello"));
-    /// let p = Box::into_raw(x);
+    /// let ptr = Box::into_raw(x);
     /// unsafe {
-    ///     ptr::drop_in_place(p);
-    ///     dealloc(p as *mut u8, Layout::new::<String>());
+    ///     ptr::drop_in_place(ptr);
+    ///     dealloc(ptr as *mut u8, Layout::new::<String>());
+    /// }
+    /// ```
+    /// Note: This is equivalent to the following:
+    /// ```
+    /// let x = Box::new(String::from("Hello"));
+    /// let ptr = Box::into_raw(x);
+    /// unsafe {
+    ///     drop(Box::from_raw(ptr));
     /// }
     /// ```
     ///
@@ -2110,28 +2118,28 @@ impl<T: ?Sized, A: Allocator> AsMut<T> for Box<T, A> {
 #[stable(feature = "pin", since = "1.33.0")]
 impl<T: ?Sized, A: Allocator> Unpin for Box<T, A> where A: 'static {}
 
-#[unstable(feature = "generator_trait", issue = "43122")]
-impl<G: ?Sized + Generator<R> + Unpin, R, A: Allocator> Generator<R> for Box<G, A>
+#[unstable(feature = "coroutine_trait", issue = "43122")]
+impl<G: ?Sized + Coroutine<R> + Unpin, R, A: Allocator> Coroutine<R> for Box<G, A>
 where
     A: 'static,
 {
     type Yield = G::Yield;
     type Return = G::Return;
 
-    fn resume(mut self: Pin<&mut Self>, arg: R) -> GeneratorState<Self::Yield, Self::Return> {
+    fn resume(mut self: Pin<&mut Self>, arg: R) -> CoroutineState<Self::Yield, Self::Return> {
         G::resume(Pin::new(&mut *self), arg)
     }
 }
 
-#[unstable(feature = "generator_trait", issue = "43122")]
-impl<G: ?Sized + Generator<R>, R, A: Allocator> Generator<R> for Pin<Box<G, A>>
+#[unstable(feature = "coroutine_trait", issue = "43122")]
+impl<G: ?Sized + Coroutine<R>, R, A: Allocator> Coroutine<R> for Pin<Box<G, A>>
 where
     A: 'static,
 {
     type Yield = G::Yield;
     type Return = G::Return;
 
-    fn resume(mut self: Pin<&mut Self>, arg: R) -> GeneratorState<Self::Yield, Self::Return> {
+    fn resume(mut self: Pin<&mut Self>, arg: R) -> CoroutineState<Self::Yield, Self::Return> {
         G::resume((*self).as_mut(), arg)
     }
 }
@@ -2448,4 +2456,8 @@ impl<T: core::error::Error> core::error::Error for Box<T> {
     fn source(&self) -> Option<&(dyn core::error::Error + 'static)> {
         core::error::Error::source(&**self)
     }
+
+    fn provide<'b>(&'b self, request: &mut core::error::Request<'b>) {
+        core::error::Error::provide(&**self, request);
+    }
 }
diff --git a/rust/alloc/collections/mod.rs b/rust/alloc/collections/mod.rs
index 2506065d158a..00ffb3b97365 100644
--- a/rust/alloc/collections/mod.rs
+++ b/rust/alloc/collections/mod.rs
@@ -150,6 +150,7 @@ impl Display for TryReserveError {
 
 /// An intermediate trait for specialization of `Extend`.
 #[doc(hidden)]
+#[cfg(not(no_global_oom_handling))]
 trait SpecExtend<I: IntoIterator> {
     /// Extends `self` with the contents of the given iterator.
     fn spec_extend(&mut self, iter: I);
diff --git a/rust/alloc/lib.rs b/rust/alloc/lib.rs
index 9c7ea73da108..36f79c075593 100644
--- a/rust/alloc/lib.rs
+++ b/rust/alloc/lib.rs
@@ -80,6 +80,8 @@
     not(no_sync),
     target_has_atomic = "ptr"
 ))]
+#![doc(rust_logo)]
+#![feature(rustdoc_internals)]
 #![no_std]
 #![needs_allocator]
 // Lints:
@@ -115,7 +117,6 @@
 #![feature(const_eval_select)]
 #![feature(const_maybe_uninit_as_mut_ptr)]
 #![feature(const_maybe_uninit_write)]
-#![feature(const_maybe_uninit_zeroed)]
 #![feature(const_pin)]
 #![feature(const_refs_to_cell)]
 #![feature(const_size_of_val)]
@@ -141,7 +142,6 @@
 #![feature(maybe_uninit_uninit_array)]
 #![feature(maybe_uninit_uninit_array_transpose)]
 #![feature(pattern)]
-#![feature(pointer_byte_offsets)]
 #![feature(ptr_internals)]
 #![feature(ptr_metadata)]
 #![feature(ptr_sub_ptr)]
@@ -156,6 +156,7 @@
 #![feature(std_internals)]
 #![feature(str_internals)]
 #![feature(strict_provenance)]
+#![feature(trusted_fused)]
 #![feature(trusted_len)]
 #![feature(trusted_random_access)]
 #![feature(try_trait_v2)]
@@ -168,7 +169,7 @@
 //
 // Language features:
 // tidy-alphabetical-start
-#![cfg_attr(not(test), feature(generator_trait))]
+#![cfg_attr(not(test), feature(coroutine_trait))]
 #![cfg_attr(test, feature(panic_update_hook))]
 #![cfg_attr(test, feature(test))]
 #![feature(allocator_internals)]
@@ -276,7 +277,7 @@ pub(crate) mod test_helpers {
     /// seed not being the same for every RNG invocation too.
     pub(crate) fn test_rng() -> rand_xorshift::XorShiftRng {
         use std::hash::{BuildHasher, Hash, Hasher};
-        let mut hasher = std::collections::hash_map::RandomState::new().build_hasher();
+        let mut hasher = std::hash::RandomState::new().build_hasher();
         std::panic::Location::caller().hash(&mut hasher);
         let hc64 = hasher.finish();
         let seed_vec =
diff --git a/rust/alloc/raw_vec.rs b/rust/alloc/raw_vec.rs
index a7425582a323..98b6abf30af6 100644
--- a/rust/alloc/raw_vec.rs
+++ b/rust/alloc/raw_vec.rs
@@ -27,6 +27,16 @@ enum AllocInit {
     Zeroed,
 }
 
+#[repr(transparent)]
+#[cfg_attr(target_pointer_width = "16", rustc_layout_scalar_valid_range_end(0x7fff))]
+#[cfg_attr(target_pointer_width = "32", rustc_layout_scalar_valid_range_end(0x7fff_ffff))]
+#[cfg_attr(target_pointer_width = "64", rustc_layout_scalar_valid_range_end(0x7fff_ffff_ffff_ffff))]
+struct Cap(usize);
+
+impl Cap {
+    const ZERO: Cap = unsafe { Cap(0) };
+}
+
 /// A low-level utility for more ergonomically allocating, reallocating, and deallocating
 /// a buffer of memory on the heap without having to worry about all the corner cases
 /// involved. This type is excellent for building your own data structures like Vec and VecDeque.
@@ -52,7 +62,12 @@ enum AllocInit {
 #[allow(missing_debug_implementations)]
 pub(crate) struct RawVec<T, A: Allocator = Global> {
     ptr: Unique<T>,
-    cap: usize,
+    /// Never used for ZSTs; it's `capacity()`'s responsibility to return usize::MAX in that case.
+    ///
+    /// # Safety
+    ///
+    /// `cap` must be in the `0..=isize::MAX` range.
+    cap: Cap,
     alloc: A,
 }
 
@@ -121,7 +136,7 @@ impl<T, A: Allocator> RawVec<T, A> {
     /// the returned `RawVec`.
     pub const fn new_in(alloc: A) -> Self {
         // `cap: 0` means "unallocated". zero-sized types are ignored.
-        Self { ptr: Unique::dangling(), cap: 0, alloc }
+        Self { ptr: Unique::dangling(), cap: Cap::ZERO, alloc }
     }
 
     /// Like `with_capacity`, but parameterized over the choice of
@@ -203,7 +218,7 @@ impl<T, A: Allocator> RawVec<T, A> {
             // here should change to `ptr.len() / mem::size_of::<T>()`.
             Self {
                 ptr: unsafe { Unique::new_unchecked(ptr.cast().as_ptr()) },
-                cap: capacity,
+                cap: unsafe { Cap(capacity) },
                 alloc,
             }
         }
@@ -228,7 +243,7 @@ impl<T, A: Allocator> RawVec<T, A> {
         // here should change to `ptr.len() / mem::size_of::<T>()`.
         Ok(Self {
             ptr: unsafe { Unique::new_unchecked(ptr.cast().as_ptr()) },
-            cap: capacity,
+            cap: unsafe { Cap(capacity) },
             alloc,
         })
     }
@@ -240,12 +255,13 @@ impl<T, A: Allocator> RawVec<T, A> {
     /// The `ptr` must be allocated (via the given allocator `alloc`), and with the given
     /// `capacity`.
     /// The `capacity` cannot exceed `isize::MAX` for sized types. (only a concern on 32-bit
-    /// systems). ZST vectors may have a capacity up to `usize::MAX`.
+    /// systems). For ZSTs capacity is ignored.
     /// If the `ptr` and `capacity` come from a `RawVec` created via `alloc`, then this is
     /// guaranteed.
     #[inline]
     pub unsafe fn from_raw_parts_in(ptr: *mut T, capacity: usize, alloc: A) -> Self {
-        Self { ptr: unsafe { Unique::new_unchecked(ptr) }, cap: capacity, alloc }
+        let cap = if T::IS_ZST { Cap::ZERO } else { unsafe { Cap(capacity) } };
+        Self { ptr: unsafe { Unique::new_unchecked(ptr) }, cap, alloc }
     }
 
     /// Gets a raw pointer to the start of the allocation. Note that this is
@@ -261,7 +277,7 @@ impl<T, A: Allocator> RawVec<T, A> {
     /// This will always be `usize::MAX` if `T` is zero-sized.
     #[inline(always)]
     pub fn capacity(&self) -> usize {
-        if T::IS_ZST { usize::MAX } else { self.cap }
+        if T::IS_ZST { usize::MAX } else { self.cap.0 }
     }
 
     /// Returns a shared reference to the allocator backing this `RawVec`.
@@ -270,7 +286,7 @@ impl<T, A: Allocator> RawVec<T, A> {
     }
 
     fn current_memory(&self) -> Option<(NonNull<u8>, Layout)> {
-        if T::IS_ZST || self.cap == 0 {
+        if T::IS_ZST || self.cap.0 == 0 {
             None
         } else {
             // We could use Layout::array here which ensures the absence of isize and usize overflows
@@ -280,7 +296,7 @@ impl<T, A: Allocator> RawVec<T, A> {
             let _: () = const { assert!(mem::size_of::<T>() % mem::align_of::<T>() == 0) };
             unsafe {
                 let align = mem::align_of::<T>();
-                let size = mem::size_of::<T>().unchecked_mul(self.cap);
+                let size = mem::size_of::<T>().unchecked_mul(self.cap.0);
                 let layout = Layout::from_size_align_unchecked(size, align);
                 Some((self.ptr.cast().into(), layout))
             }
@@ -338,10 +354,13 @@ impl<T, A: Allocator> RawVec<T, A> {
     /// The same as `reserve`, but returns on errors instead of panicking or aborting.
     pub fn try_reserve(&mut self, len: usize, additional: usize) -> Result<(), TryReserveError> {
         if self.needs_to_grow(len, additional) {
-            self.grow_amortized(len, additional)
-        } else {
-            Ok(())
+            self.grow_amortized(len, additional)?;
         }
+        unsafe {
+            // Inform the optimizer that the reservation has succeeded or wasn't needed
+            core::intrinsics::assume(!self.needs_to_grow(len, additional));
+        }
+        Ok(())
     }
 
     /// The same as `reserve_for_push`, but returns on errors instead of panicking or aborting.
@@ -378,7 +397,14 @@ impl<T, A: Allocator> RawVec<T, A> {
         len: usize,
         additional: usize,
     ) -> Result<(), TryReserveError> {
-        if self.needs_to_grow(len, additional) { self.grow_exact(len, additional) } else { Ok(()) }
+        if self.needs_to_grow(len, additional) {
+            self.grow_exact(len, additional)?;
+        }
+        unsafe {
+            // Inform the optimizer that the reservation has succeeded or wasn't needed
+            core::intrinsics::assume(!self.needs_to_grow(len, additional));
+        }
+        Ok(())
     }
 
     /// Shrinks the buffer down to the specified capacity. If the given amount
@@ -404,12 +430,15 @@ impl<T, A: Allocator> RawVec<T, A> {
         additional > self.capacity().wrapping_sub(len)
     }
 
-    fn set_ptr_and_cap(&mut self, ptr: NonNull<[u8]>, cap: usize) {
+    /// # Safety:
+    ///
+    /// `cap` must not exceed `isize::MAX`.
+    unsafe fn set_ptr_and_cap(&mut self, ptr: NonNull<[u8]>, cap: usize) {
         // Allocators currently return a `NonNull<[u8]>` whose length matches
         // the size requested. If that ever changes, the capacity here should
         // change to `ptr.len() / mem::size_of::<T>()`.
         self.ptr = unsafe { Unique::new_unchecked(ptr.cast().as_ptr()) };
-        self.cap = cap;
+        self.cap = unsafe { Cap(cap) };
     }
 
     // This method is usually instantiated many times. So we want it to be as
@@ -434,14 +463,15 @@ impl<T, A: Allocator> RawVec<T, A> {
 
         // This guarantees exponential growth. The doubling cannot overflow
         // because `cap <= isize::MAX` and the type of `cap` is `usize`.
-        let cap = cmp::max(self.cap * 2, required_cap);
+        let cap = cmp::max(self.cap.0 * 2, required_cap);
         let cap = cmp::max(Self::MIN_NON_ZERO_CAP, cap);
 
         let new_layout = Layout::array::<T>(cap);
 
         // `finish_grow` is non-generic over `T`.
         let ptr = finish_grow(new_layout, self.current_memory(), &mut self.alloc)?;
-        self.set_ptr_and_cap(ptr, cap);
+        // SAFETY: finish_grow would have resulted in a capacity overflow if we tried to allocate more than isize::MAX items
+        unsafe { self.set_ptr_and_cap(ptr, cap) };
         Ok(())
     }
 
@@ -460,7 +490,10 @@ impl<T, A: Allocator> RawVec<T, A> {
 
         // `finish_grow` is non-generic over `T`.
         let ptr = finish_grow(new_layout, self.current_memory(), &mut self.alloc)?;
-        self.set_ptr_and_cap(ptr, cap);
+        // SAFETY: finish_grow would have resulted in a capacity overflow if we tried to allocate more than isize::MAX items
+        unsafe {
+            self.set_ptr_and_cap(ptr, cap);
+        }
         Ok(())
     }
 
@@ -478,7 +511,7 @@ impl<T, A: Allocator> RawVec<T, A> {
         if cap == 0 {
             unsafe { self.alloc.deallocate(ptr, layout) };
             self.ptr = Unique::dangling();
-            self.cap = 0;
+            self.cap = Cap::ZERO;
         } else {
             let ptr = unsafe {
                 // `Layout::array` cannot overflow here because it would have
@@ -489,7 +522,10 @@ impl<T, A: Allocator> RawVec<T, A> {
                     .shrink(ptr, layout, new_layout)
                     .map_err(|_| AllocError { layout: new_layout, non_exhaustive: () })?
             };
-            self.set_ptr_and_cap(ptr, cap);
+            // SAFETY: if the allocation is valid, then the capacity is too
+            unsafe {
+                self.set_ptr_and_cap(ptr, cap);
+            }
         }
         Ok(())
     }
@@ -569,6 +605,7 @@ fn alloc_guard(alloc_size: usize) -> Result<(), TryReserveError> {
 // ensure that the code generation related to these panics is minimal as there's
 // only one location which panics rather than a bunch throughout the module.
 #[cfg(not(no_global_oom_handling))]
+#[cfg_attr(not(feature = "panic_immediate_abort"), inline(never))]
 fn capacity_overflow() -> ! {
     panic!("capacity overflow");
 }
diff --git a/rust/alloc/vec/into_iter.rs b/rust/alloc/vec/into_iter.rs
index aac0ec16aef1..136bfe94af6c 100644
--- a/rust/alloc/vec/into_iter.rs
+++ b/rust/alloc/vec/into_iter.rs
@@ -9,7 +9,8 @@ use crate::raw_vec::RawVec;
 use core::array;
 use core::fmt;
 use core::iter::{
-    FusedIterator, InPlaceIterable, SourceIter, TrustedLen, TrustedRandomAccessNoCoerce,
+    FusedIterator, InPlaceIterable, SourceIter, TrustedFused, TrustedLen,
+    TrustedRandomAccessNoCoerce,
 };
 use core::marker::PhantomData;
 use core::mem::{self, ManuallyDrop, MaybeUninit, SizedTypeProperties};
@@ -287,9 +288,7 @@ impl<T, A: Allocator> Iterator for IntoIter<T, A> {
         // Also note the implementation of `Self: TrustedRandomAccess` requires
         // that `T: Copy` so reading elements from the buffer doesn't invalidate
         // them for `Drop`.
-        unsafe {
-            if T::IS_ZST { mem::zeroed() } else { ptr::read(self.ptr.add(i)) }
-        }
+        unsafe { if T::IS_ZST { mem::zeroed() } else { ptr::read(self.ptr.add(i)) } }
     }
 }
 
@@ -341,6 +340,10 @@ impl<T, A: Allocator> ExactSizeIterator for IntoIter<T, A> {
 #[stable(feature = "fused", since = "1.26.0")]
 impl<T, A: Allocator> FusedIterator for IntoIter<T, A> {}
 
+#[doc(hidden)]
+#[unstable(issue = "none", feature = "trusted_fused")]
+unsafe impl<T, A: Allocator> TrustedFused for IntoIter<T, A> {}
+
 #[unstable(feature = "trusted_len", issue = "37572")]
 unsafe impl<T, A: Allocator> TrustedLen for IntoIter<T, A> {}
 
@@ -425,7 +428,10 @@ unsafe impl<#[may_dangle] T, A: Allocator> Drop for IntoIter<T, A> {
 // also refer to the vec::in_place_collect module documentation to get an overview
 #[unstable(issue = "none", feature = "inplace_iteration")]
 #[doc(hidden)]
-unsafe impl<T, A: Allocator> InPlaceIterable for IntoIter<T, A> {}
+unsafe impl<T, A: Allocator> InPlaceIterable for IntoIter<T, A> {
+    const EXPAND_BY: Option<NonZeroUsize> = NonZeroUsize::new(1);
+    const MERGE_BY: Option<NonZeroUsize> = NonZeroUsize::new(1);
+}
 
 #[unstable(issue = "none", feature = "inplace_iteration")]
 #[doc(hidden)]
diff --git a/rust/alloc/vec/mod.rs b/rust/alloc/vec/mod.rs
index 41ca71805ef0..220fb9d6f45b 100644
--- a/rust/alloc/vec/mod.rs
+++ b/rust/alloc/vec/mod.rs
@@ -105,6 +105,7 @@ mod into_iter;
 #[cfg(not(no_global_oom_handling))]
 use self::is_zero::IsZero;
 
+#[cfg(not(no_global_oom_handling))]
 mod is_zero;
 
 #[cfg(not(no_global_oom_handling))]
@@ -123,7 +124,7 @@ use self::set_len_on_drop::SetLenOnDrop;
 mod set_len_on_drop;
 
 #[cfg(not(no_global_oom_handling))]
-use self::in_place_drop::{InPlaceDrop, InPlaceDstBufDrop};
+use self::in_place_drop::{InPlaceDrop, InPlaceDstDataSrcBufDrop};
 
 #[cfg(not(no_global_oom_handling))]
 mod in_place_drop;
@@ -1376,7 +1377,7 @@ impl<T, A: Allocator> Vec<T, A> {
     /// [`as_mut_ptr`]: Vec::as_mut_ptr
     /// [`as_ptr`]: Vec::as_ptr
     #[stable(feature = "vec_as_ptr", since = "1.37.0")]
-    #[cfg_attr(not(bootstrap), rustc_never_returns_null_ptr)]
+    #[rustc_never_returns_null_ptr]
     #[inline]
     pub fn as_ptr(&self) -> *const T {
         // We shadow the slice method of the same name to avoid going through
@@ -1436,7 +1437,7 @@ impl<T, A: Allocator> Vec<T, A> {
     /// [`as_mut_ptr`]: Vec::as_mut_ptr
     /// [`as_ptr`]: Vec::as_ptr
     #[stable(feature = "vec_as_ptr", since = "1.37.0")]
-    #[cfg_attr(not(bootstrap), rustc_never_returns_null_ptr)]
+    #[rustc_never_returns_null_ptr]
     #[inline]
     pub fn as_mut_ptr(&mut self) -> *mut T {
         // We shadow the slice method of the same name to avoid going through
@@ -1565,7 +1566,8 @@ impl<T, A: Allocator> Vec<T, A> {
     #[stable(feature = "rust1", since = "1.0.0")]
     pub fn swap_remove(&mut self, index: usize) -> T {
         #[cold]
-        #[inline(never)]
+        #[cfg_attr(not(feature = "panic_immediate_abort"), inline(never))]
+        #[track_caller]
         fn assert_failed(index: usize, len: usize) -> ! {
             panic!("swap_remove index (is {index}) should be < len (is {len})");
         }
@@ -1606,7 +1608,8 @@ impl<T, A: Allocator> Vec<T, A> {
     #[stable(feature = "rust1", since = "1.0.0")]
     pub fn insert(&mut self, index: usize, element: T) {
         #[cold]
-        #[inline(never)]
+        #[cfg_attr(not(feature = "panic_immediate_abort"), inline(never))]
+        #[track_caller]
         fn assert_failed(index: usize, len: usize) -> ! {
             panic!("insertion index (is {index}) should be <= len (is {len})");
         }
@@ -1667,7 +1670,7 @@ impl<T, A: Allocator> Vec<T, A> {
     #[track_caller]
     pub fn remove(&mut self, index: usize) -> T {
         #[cold]
-        #[inline(never)]
+        #[cfg_attr(not(feature = "panic_immediate_abort"), inline(never))]
         #[track_caller]
         fn assert_failed(index: usize, len: usize) -> ! {
             panic!("removal index (is {index}) should be < len (is {len})");
@@ -1891,7 +1894,32 @@ impl<T, A: Allocator> Vec<T, A> {
             return;
         }
 
-        /* INVARIANT: vec.len() > read >= write > write-1 >= 0 */
+        // Check if we ever want to remove anything.
+        // This allows to use copy_non_overlapping in next cycle.
+        // And avoids any memory writes if we don't need to remove anything.
+        let mut first_duplicate_idx: usize = 1;
+        let start = self.as_mut_ptr();
+        while first_duplicate_idx != len {
+            let found_duplicate = unsafe {
+                // SAFETY: first_duplicate always in range [1..len)
+                // Note that we start iteration from 1 so we never overflow.
+                let prev = start.add(first_duplicate_idx.wrapping_sub(1));
+                let current = start.add(first_duplicate_idx);
+                // We explicitly say in docs that references are reversed.
+                same_bucket(&mut *current, &mut *prev)
+            };
+            if found_duplicate {
+                break;
+            }
+            first_duplicate_idx += 1;
+        }
+        // Don't need to remove anything.
+        // We cannot get bigger than len.
+        if first_duplicate_idx == len {
+            return;
+        }
+
+        /* INVARIANT: vec.len() > read > write > write-1 >= 0 */
         struct FillGapOnDrop<'a, T, A: core::alloc::Allocator> {
             /* Offset of the element we want to check if it is duplicate */
             read: usize,
@@ -1937,31 +1965,39 @@ impl<T, A: Allocator> Vec<T, A> {
             }
         }
 
-        let mut gap = FillGapOnDrop { read: 1, write: 1, vec: self };
-        let ptr = gap.vec.as_mut_ptr();
-
         /* Drop items while going through Vec, it should be more efficient than
          * doing slice partition_dedup + truncate */
 
+        // Construct gap first and then drop item to avoid memory corruption if `T::drop` panics.
+        let mut gap =
+            FillGapOnDrop { read: first_duplicate_idx + 1, write: first_duplicate_idx, vec: self };
+        unsafe {
+            // SAFETY: we checked that first_duplicate_idx in bounds before.
+            // If drop panics, `gap` would remove this item without drop.
+            ptr::drop_in_place(start.add(first_duplicate_idx));
+        }
+
         /* SAFETY: Because of the invariant, read_ptr, prev_ptr and write_ptr
          * are always in-bounds and read_ptr never aliases prev_ptr */
         unsafe {
             while gap.read < len {
-                let read_ptr = ptr.add(gap.read);
-                let prev_ptr = ptr.add(gap.write.wrapping_sub(1));
+                let read_ptr = start.add(gap.read);
+                let prev_ptr = start.add(gap.write.wrapping_sub(1));
 
-                if same_bucket(&mut *read_ptr, &mut *prev_ptr) {
+                // We explicitly say in docs that references are reversed.
+                let found_duplicate = same_bucket(&mut *read_ptr, &mut *prev_ptr);
+                if found_duplicate {
                     // Increase `gap.read` now since the drop may panic.
                     gap.read += 1;
                     /* We have found duplicate, drop it in-place */
                     ptr::drop_in_place(read_ptr);
                 } else {
-                    let write_ptr = ptr.add(gap.write);
+                    let write_ptr = start.add(gap.write);
 
-                    /* Because `read_ptr` can be equal to `write_ptr`, we either
-                     * have to use `copy` or conditional `copy_nonoverlapping`.
-                     * Looks like the first option is faster. */
-                    ptr::copy(read_ptr, write_ptr, 1);
+                    /* read_ptr cannot be equal to write_ptr because at this point
+                     * we guaranteed to skip at least one element (before loop starts).
+                     */
+                    ptr::copy_nonoverlapping(read_ptr, write_ptr, 1);
 
                     /* We have filled that place, so go further */
                     gap.write += 1;
@@ -2097,6 +2133,7 @@ impl<T, A: Allocator> Vec<T, A> {
         } else {
             unsafe {
                 self.len -= 1;
+                core::intrinsics::assume(self.len < self.capacity());
                 Some(ptr::read(self.as_ptr().add(self.len())))
             }
         }
@@ -2299,7 +2336,8 @@ impl<T, A: Allocator> Vec<T, A> {
         A: Clone,
     {
         #[cold]
-        #[inline(never)]
+        #[cfg_attr(not(feature = "panic_immediate_abort"), inline(never))]
+        #[track_caller]
         fn assert_failed(at: usize, len: usize) -> ! {
             panic!("`at` split index (is {at}) should be <= len (is {len})");
         }
@@ -2840,6 +2878,7 @@ pub fn from_elem_in<T: Clone, A: Allocator>(elem: T, n: usize, alloc: A) -> Vec<
     <T as SpecFromElem>::from_elem(elem, n, alloc)
 }
 
+#[cfg(not(no_global_oom_handling))]
 trait ExtendFromWithinSpec {
     /// # Safety
     ///
@@ -2848,6 +2887,7 @@ trait ExtendFromWithinSpec {
     unsafe fn spec_extend_from_within(&mut self, src: Range<usize>);
 }
 
+#[cfg(not(no_global_oom_handling))]
 impl<T: Clone, A: Allocator> ExtendFromWithinSpec for Vec<T, A> {
     default unsafe fn spec_extend_from_within(&mut self, src: Range<usize>) {
         // SAFETY:
@@ -2867,6 +2907,7 @@ impl<T: Clone, A: Allocator> ExtendFromWithinSpec for Vec<T, A> {
     }
 }
 
+#[cfg(not(no_global_oom_handling))]
 impl<T: Copy, A: Allocator> ExtendFromWithinSpec for Vec<T, A> {
     unsafe fn spec_extend_from_within(&mut self, src: Range<usize>) {
         let count = src.len();
@@ -2947,7 +2988,7 @@ impl<T: Clone, A: Allocator + Clone> Clone for Vec<T, A> {
 /// ```
 /// use std::hash::BuildHasher;
 ///
-/// let b = std::collections::hash_map::RandomState::new();
+/// let b = std::hash::RandomState::new();
 /// let v: Vec<u8> = vec![0xa8, 0x3c, 0x09];
 /// let s: &[u8] = &[0xa8, 0x3c, 0x09];
 /// assert_eq!(b.hash_one(v), b.hash_one(s));
diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h
index c0cb4b05b918..65b98831b975 100644
--- a/rust/bindings/bindings_helper.h
+++ b/rust/bindings/bindings_helper.h
@@ -9,12 +9,13 @@
 #include <kunit/test.h>
 #include <linux/errname.h>
 #include <linux/ethtool.h>
+#include <linux/jiffies.h>
 #include <linux/mdio.h>
 #include <linux/phy.h>
-#include <linux/slab.h>
 #include <linux/refcount.h>
-#include <linux/wait.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
 #include <linux/workqueue.h>
 
 /* `bindgen` gets confused at certain things. */
diff --git a/rust/kernel/allocator.rs b/rust/kernel/allocator.rs
index 4b057e837358..01ad139e19bc 100644
--- a/rust/kernel/allocator.rs
+++ b/rust/kernel/allocator.rs
@@ -35,7 +35,7 @@ unsafe fn krealloc_aligned(ptr: *mut u8, new_layout: Layout, flags: bindings::gf
     // - `ptr` is either null or a pointer returned from a previous `k{re}alloc()` by the
     //   function safety requirement.
     // - `size` is greater than 0 since it's either a `layout.size()` (which cannot be zero
-    //    according to the function safety requirement) or a result from `next_power_of_two()`.
+    //   according to the function safety requirement) or a result from `next_power_of_two()`.
     unsafe { bindings::krealloc(ptr as *const core::ffi::c_void, size, flags) as *mut u8 }
 }
 
diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs
index 4f0c1edd63b7..4786d3ee1e92 100644
--- a/rust/kernel/error.rs
+++ b/rust/kernel/error.rs
@@ -264,13 +264,9 @@ pub fn to_result(err: core::ffi::c_int) -> Result {
 ///     pdev: &mut PlatformDevice,
 ///     index: u32,
 /// ) -> Result<*mut core::ffi::c_void> {
-///     // SAFETY: FFI call.
-///     unsafe {
-///         from_err_ptr(bindings::devm_platform_ioremap_resource(
-///             pdev.to_ptr(),
-///             index,
-///         ))
-///     }
+///     // SAFETY: `pdev` points to a valid platform device. There are no safety requirements
+///     // on `index`.
+///     from_err_ptr(unsafe { bindings::devm_platform_ioremap_resource(pdev.to_ptr(), index) })
 /// }
 /// ```
 // TODO: Remove `dead_code` marker once an in-kernel client is available.
diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs
index 65be9ae57b80..424257284d16 100644
--- a/rust/kernel/init.rs
+++ b/rust/kernel/init.rs
@@ -36,7 +36,7 @@
 //!
 //! ```rust
 //! # #![allow(clippy::disallowed_names)]
-//! use kernel::{prelude::*, sync::Mutex, new_mutex};
+//! use kernel::sync::{new_mutex, Mutex};
 //! # use core::pin::Pin;
 //! #[pin_data]
 //! struct Foo {
@@ -56,7 +56,7 @@
 //!
 //! ```rust
 //! # #![allow(clippy::disallowed_names)]
-//! # use kernel::{prelude::*, sync::Mutex, new_mutex};
+//! # use kernel::sync::{new_mutex, Mutex};
 //! # use core::pin::Pin;
 //! # #[pin_data]
 //! # struct Foo {
@@ -79,7 +79,7 @@
 //! above method only works for types where you can access the fields.
 //!
 //! ```rust
-//! # use kernel::{new_mutex, sync::{Arc, Mutex}};
+//! # use kernel::sync::{new_mutex, Arc, Mutex};
 //! let mtx: Result<Arc<Mutex<usize>>> = Arc::pin_init(new_mutex!(42, "example::mtx"));
 //! ```
 //!
@@ -751,10 +751,10 @@ macro_rules! try_init {
 ///
 /// # Safety
 ///
-/// When implementing this type you will need to take great care. Also there are probably very few
+/// When implementing this trait you will need to take great care. Also there are probably very few
 /// cases where a manual implementation is necessary. Use [`pin_init_from_closure`] where possible.
 ///
-/// The [`PinInit::__pinned_init`] function
+/// The [`PinInit::__pinned_init`] function:
 /// - returns `Ok(())` if it initialized every field of `slot`,
 /// - returns `Err(err)` if it encountered an error and then cleaned `slot`, this means:
 ///     - `slot` can be deallocated without UB occurring,
@@ -861,10 +861,10 @@ where
 ///
 /// # Safety
 ///
-/// When implementing this type you will need to take great care. Also there are probably very few
+/// When implementing this trait you will need to take great care. Also there are probably very few
 /// cases where a manual implementation is necessary. Use [`init_from_closure`] where possible.
 ///
-/// The [`Init::__init`] function
+/// The [`Init::__init`] function:
 /// - returns `Ok(())` if it initialized every field of `slot`,
 /// - returns `Err(err)` if it encountered an error and then cleaned `slot`, this means:
 ///     - `slot` can be deallocated without UB occurring,
@@ -1013,7 +1013,7 @@ pub fn uninit<T, E>() -> impl Init<MaybeUninit<T>, E> {
 ///
 /// ```rust
 /// use kernel::{error::Error, init::init_array_from_fn};
-/// let array: Box<[usize; 1_000]>= Box::init::<Error>(init_array_from_fn(|i| i)).unwrap();
+/// let array: Box<[usize; 1_000]> = Box::init::<Error>(init_array_from_fn(|i| i)).unwrap();
 /// assert_eq!(array.len(), 1_000);
 /// ```
 pub fn init_array_from_fn<I, const N: usize, T, E>(
@@ -1027,7 +1027,7 @@ where
         // Counts the number of initialized elements and when dropped drops that many elements from
         // `slot`.
         let mut init_count = ScopeGuard::new_with_data(0, |i| {
-            // We now free every element that has been initialized before:
+            // We now free every element that has been initialized before.
             // SAFETY: The loop initialized exactly the values from 0..i and since we
             // return `Err` below, the caller will consider the memory at `slot` as
             // uninitialized.
@@ -1056,7 +1056,7 @@ where
 ///
 /// ```rust
 /// use kernel::{sync::{Arc, Mutex}, init::pin_init_array_from_fn, new_mutex};
-/// let array: Arc<[Mutex<usize>; 1_000]>=
+/// let array: Arc<[Mutex<usize>; 1_000]> =
 ///     Arc::pin_init(pin_init_array_from_fn(|i| new_mutex!(i))).unwrap();
 /// assert_eq!(array.len(), 1_000);
 /// ```
@@ -1071,7 +1071,7 @@ where
         // Counts the number of initialized elements and when dropped drops that many elements from
         // `slot`.
         let mut init_count = ScopeGuard::new_with_data(0, |i| {
-            // We now free every element that has been initialized before:
+            // We now free every element that has been initialized before.
             // SAFETY: The loop initialized exactly the values from 0..i and since we
             // return `Err` below, the caller will consider the memory at `slot` as
             // uninitialized.
diff --git a/rust/kernel/ioctl.rs b/rust/kernel/ioctl.rs
index f1d42ab69972..cfa7d080b531 100644
--- a/rust/kernel/ioctl.rs
+++ b/rust/kernel/ioctl.rs
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
-//! ioctl() number definitions
+//! `ioctl()` number definitions.
 //!
 //! C header: [`include/asm-generic/ioctl.h`](srctree/include/asm-generic/ioctl.h)
 
@@ -28,13 +28,13 @@ pub const fn _IO(ty: u32, nr: u32) -> u32 {
     _IOC(uapi::_IOC_NONE, ty, nr, 0)
 }
 
-/// Build an ioctl number for an read-only ioctl.
+/// Build an ioctl number for a read-only ioctl.
 #[inline(always)]
 pub const fn _IOR<T>(ty: u32, nr: u32) -> u32 {
     _IOC(uapi::_IOC_READ, ty, nr, core::mem::size_of::<T>())
 }
 
-/// Build an ioctl number for an write-only ioctl.
+/// Build an ioctl number for a write-only ioctl.
 #[inline(always)]
 pub const fn _IOW<T>(ty: u32, nr: u32) -> u32 {
     _IOC(uapi::_IOC_WRITE, ty, nr, core::mem::size_of::<T>())
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 7ac39874aeac..be68d5e567b1 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -14,11 +14,9 @@
 #![no_std]
 #![feature(allocator_api)]
 #![feature(coerce_unsized)]
-#![feature(const_maybe_uninit_zeroed)]
 #![feature(dispatch_from_dyn)]
 #![feature(new_uninit)]
 #![feature(offset_of)]
-#![feature(ptr_metadata)]
 #![feature(receiver_trait)]
 #![feature(unsize)]
 
@@ -49,6 +47,7 @@ pub mod std_vendor;
 pub mod str;
 pub mod sync;
 pub mod task;
+pub mod time;
 pub mod types;
 pub mod workqueue;
 
@@ -78,7 +77,7 @@ pub trait Module: Sized + Sync {
 
 /// Equivalent to `THIS_MODULE` in the C API.
 ///
-/// C header: `include/linux/export.h`
+/// C header: [`include/linux/export.h`](srctree/include/linux/export.h)
 pub struct ThisModule(*mut bindings::module);
 
 // SAFETY: `THIS_MODULE` may be used from all threads within a module.
@@ -102,3 +101,35 @@ fn panic(info: &core::panic::PanicInfo<'_>) -> ! {
     // SAFETY: FFI call.
     unsafe { bindings::BUG() };
 }
+
+/// Produces a pointer to an object from a pointer to one of its fields.
+///
+/// # Safety
+///
+/// The pointer passed to this macro, and the pointer returned by this macro, must both be in
+/// bounds of the same allocation.
+///
+/// # Examples
+///
+/// ```
+/// # use kernel::container_of;
+/// struct Test {
+///     a: u64,
+///     b: u32,
+/// }
+///
+/// let test = Test { a: 10, b: 20 };
+/// let b_ptr = &test.b;
+/// // SAFETY: The pointer points at the `b` field of a `Test`, so the resulting pointer will be
+/// // in-bounds of the same allocation as `b_ptr`.
+/// let test_alias = unsafe { container_of!(b_ptr, Test, b) };
+/// assert!(core::ptr::eq(&test, test_alias));
+/// ```
+#[macro_export]
+macro_rules! container_of {
+    ($ptr:expr, $type:ty, $($f:tt)*) => {{
+        let ptr = $ptr as *const _ as *const u8;
+        let offset: usize = ::core::mem::offset_of!($type, $($f)*);
+        ptr.sub(offset) as *const $type
+    }}
+}
diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs
index 7d848b83add4..925ced8fdc61 100644
--- a/rust/kernel/str.rs
+++ b/rust/kernel/str.rs
@@ -13,9 +13,102 @@ use crate::{
 };
 
 /// Byte string without UTF-8 validity guarantee.
-///
-/// `BStr` is simply an alias to `[u8]`, but has a more evident semantical meaning.
-pub type BStr = [u8];
+#[repr(transparent)]
+pub struct BStr([u8]);
+
+impl BStr {
+    /// Returns the length of this string.
+    #[inline]
+    pub const fn len(&self) -> usize {
+        self.0.len()
+    }
+
+    /// Returns `true` if the string is empty.
+    #[inline]
+    pub const fn is_empty(&self) -> bool {
+        self.len() == 0
+    }
+
+    /// Creates a [`BStr`] from a `[u8]`.
+    #[inline]
+    pub const fn from_bytes(bytes: &[u8]) -> &Self {
+        // SAFETY: `BStr` is transparent to `[u8]`.
+        unsafe { &*(bytes as *const [u8] as *const BStr) }
+    }
+}
+
+impl fmt::Display for BStr {
+    /// Formats printable ASCII characters, escaping the rest.
+    ///
+    /// ```
+    /// # use kernel::{fmt, b_str, str::{BStr, CString}};
+    /// let ascii = b_str!("Hello, BStr!");
+    /// let s = CString::try_from_fmt(fmt!("{}", ascii)).unwrap();
+    /// assert_eq!(s.as_bytes(), "Hello, BStr!".as_bytes());
+    ///
+    /// let non_ascii = b_str!("🦀");
+    /// let s = CString::try_from_fmt(fmt!("{}", non_ascii)).unwrap();
+    /// assert_eq!(s.as_bytes(), "\\xf0\\x9f\\xa6\\x80".as_bytes());
+    /// ```
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        for &b in &self.0 {
+            match b {
+                // Common escape codes.
+                b'\t' => f.write_str("\\t")?,
+                b'\n' => f.write_str("\\n")?,
+                b'\r' => f.write_str("\\r")?,
+                // Printable characters.
+                0x20..=0x7e => f.write_char(b as char)?,
+                _ => write!(f, "\\x{:02x}", b)?,
+            }
+        }
+        Ok(())
+    }
+}
+
+impl fmt::Debug for BStr {
+    /// Formats printable ASCII characters with a double quote on either end,
+    /// escaping the rest.
+    ///
+    /// ```
+    /// # use kernel::{fmt, b_str, str::{BStr, CString}};
+    /// // Embedded double quotes are escaped.
+    /// let ascii = b_str!("Hello, \"BStr\"!");
+    /// let s = CString::try_from_fmt(fmt!("{:?}", ascii)).unwrap();
+    /// assert_eq!(s.as_bytes(), "\"Hello, \\\"BStr\\\"!\"".as_bytes());
+    ///
+    /// let non_ascii = b_str!("😺");
+    /// let s = CString::try_from_fmt(fmt!("{:?}", non_ascii)).unwrap();
+    /// assert_eq!(s.as_bytes(), "\"\\xf0\\x9f\\x98\\xba\"".as_bytes());
+    /// ```
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        f.write_char('"')?;
+        for &b in &self.0 {
+            match b {
+                // Common escape codes.
+                b'\t' => f.write_str("\\t")?,
+                b'\n' => f.write_str("\\n")?,
+                b'\r' => f.write_str("\\r")?,
+                // String escape characters.
+                b'\"' => f.write_str("\\\"")?,
+                b'\\' => f.write_str("\\\\")?,
+                // Printable characters.
+                0x20..=0x7e => f.write_char(b as char)?,
+                _ => write!(f, "\\x{:02x}", b)?,
+            }
+        }
+        f.write_char('"')
+    }
+}
+
+impl Deref for BStr {
+    type Target = [u8];
+
+    #[inline]
+    fn deref(&self) -> &Self::Target {
+        &self.0
+    }
+}
 
 /// Creates a new [`BStr`] from a string literal.
 ///
@@ -33,7 +126,7 @@ pub type BStr = [u8];
 macro_rules! b_str {
     ($str:literal) => {{
         const S: &'static str = $str;
-        const C: &'static $crate::str::BStr = S.as_bytes();
+        const C: &'static $crate::str::BStr = $crate::str::BStr::from_bytes(S.as_bytes());
         C
     }};
 }
@@ -149,13 +242,13 @@ impl CStr {
         self.0.as_ptr() as _
     }
 
-    /// Convert the string to a byte slice without the trailing 0 byte.
+    /// Convert the string to a byte slice without the trailing `NUL` byte.
     #[inline]
     pub fn as_bytes(&self) -> &[u8] {
         &self.0[..self.len()]
     }
 
-    /// Convert the string to a byte slice containing the trailing 0 byte.
+    /// Convert the string to a byte slice containing the trailing `NUL` byte.
     #[inline]
     pub const fn as_bytes_with_nul(&self) -> &[u8] {
         &self.0
@@ -191,9 +284,9 @@ impl CStr {
     /// ```
     /// # use kernel::c_str;
     /// # use kernel::str::CStr;
+    /// let bar = c_str!("ツ");
     /// // SAFETY: String literals are guaranteed to be valid UTF-8
     /// // by the Rust compiler.
-    /// let bar = c_str!("ツ");
     /// assert_eq!(unsafe { bar.as_str_unchecked() }, "ツ");
     /// ```
     #[inline]
@@ -271,7 +364,7 @@ impl fmt::Debug for CStr {
 impl AsRef<BStr> for CStr {
     #[inline]
     fn as_ref(&self) -> &BStr {
-        self.as_bytes()
+        BStr::from_bytes(self.as_bytes())
     }
 }
 
@@ -280,7 +373,7 @@ impl Deref for CStr {
 
     #[inline]
     fn deref(&self) -> &Self::Target {
-        self.as_bytes()
+        self.as_ref()
     }
 }
 
@@ -327,7 +420,7 @@ where
 
     #[inline]
     fn index(&self, index: Idx) -> &Self::Output {
-        &self.as_bytes()[index]
+        &self.as_ref()[index]
     }
 }
 
@@ -357,6 +450,21 @@ macro_rules! c_str {
 #[cfg(test)]
 mod tests {
     use super::*;
+    use alloc::format;
+
+    const ALL_ASCII_CHARS: &'static str =
+        "\\x01\\x02\\x03\\x04\\x05\\x06\\x07\\x08\\x09\\x0a\\x0b\\x0c\\x0d\\x0e\\x0f\
+        \\x10\\x11\\x12\\x13\\x14\\x15\\x16\\x17\\x18\\x19\\x1a\\x1b\\x1c\\x1d\\x1e\\x1f \
+        !\"#$%&'()*+,-./0123456789:;<=>?@\
+        ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\\x7f\
+        \\x80\\x81\\x82\\x83\\x84\\x85\\x86\\x87\\x88\\x89\\x8a\\x8b\\x8c\\x8d\\x8e\\x8f\
+        \\x90\\x91\\x92\\x93\\x94\\x95\\x96\\x97\\x98\\x99\\x9a\\x9b\\x9c\\x9d\\x9e\\x9f\
+        \\xa0\\xa1\\xa2\\xa3\\xa4\\xa5\\xa6\\xa7\\xa8\\xa9\\xaa\\xab\\xac\\xad\\xae\\xaf\
+        \\xb0\\xb1\\xb2\\xb3\\xb4\\xb5\\xb6\\xb7\\xb8\\xb9\\xba\\xbb\\xbc\\xbd\\xbe\\xbf\
+        \\xc0\\xc1\\xc2\\xc3\\xc4\\xc5\\xc6\\xc7\\xc8\\xc9\\xca\\xcb\\xcc\\xcd\\xce\\xcf\
+        \\xd0\\xd1\\xd2\\xd3\\xd4\\xd5\\xd6\\xd7\\xd8\\xd9\\xda\\xdb\\xdc\\xdd\\xde\\xdf\
+        \\xe0\\xe1\\xe2\\xe3\\xe4\\xe5\\xe6\\xe7\\xe8\\xe9\\xea\\xeb\\xec\\xed\\xee\\xef\
+        \\xf0\\xf1\\xf2\\xf3\\xf4\\xf5\\xf6\\xf7\\xf8\\xf9\\xfa\\xfb\\xfc\\xfd\\xfe\\xff";
 
     #[test]
     fn test_cstr_to_str() {
@@ -381,6 +489,69 @@ mod tests {
         let unchecked_str = unsafe { checked_cstr.as_str_unchecked() };
         assert_eq!(unchecked_str, "🐧");
     }
+
+    #[test]
+    fn test_cstr_display() {
+        let hello_world = CStr::from_bytes_with_nul(b"hello, world!\0").unwrap();
+        assert_eq!(format!("{}", hello_world), "hello, world!");
+        let non_printables = CStr::from_bytes_with_nul(b"\x01\x09\x0a\0").unwrap();
+        assert_eq!(format!("{}", non_printables), "\\x01\\x09\\x0a");
+        let non_ascii = CStr::from_bytes_with_nul(b"d\xe9j\xe0 vu\0").unwrap();
+        assert_eq!(format!("{}", non_ascii), "d\\xe9j\\xe0 vu");
+        let good_bytes = CStr::from_bytes_with_nul(b"\xf0\x9f\xa6\x80\0").unwrap();
+        assert_eq!(format!("{}", good_bytes), "\\xf0\\x9f\\xa6\\x80");
+    }
+
+    #[test]
+    fn test_cstr_display_all_bytes() {
+        let mut bytes: [u8; 256] = [0; 256];
+        // fill `bytes` with [1..=255] + [0]
+        for i in u8::MIN..=u8::MAX {
+            bytes[i as usize] = i.wrapping_add(1);
+        }
+        let cstr = CStr::from_bytes_with_nul(&bytes).unwrap();
+        assert_eq!(format!("{}", cstr), ALL_ASCII_CHARS);
+    }
+
+    #[test]
+    fn test_cstr_debug() {
+        let hello_world = CStr::from_bytes_with_nul(b"hello, world!\0").unwrap();
+        assert_eq!(format!("{:?}", hello_world), "\"hello, world!\"");
+        let non_printables = CStr::from_bytes_with_nul(b"\x01\x09\x0a\0").unwrap();
+        assert_eq!(format!("{:?}", non_printables), "\"\\x01\\x09\\x0a\"");
+        let non_ascii = CStr::from_bytes_with_nul(b"d\xe9j\xe0 vu\0").unwrap();
+        assert_eq!(format!("{:?}", non_ascii), "\"d\\xe9j\\xe0 vu\"");
+        let good_bytes = CStr::from_bytes_with_nul(b"\xf0\x9f\xa6\x80\0").unwrap();
+        assert_eq!(format!("{:?}", good_bytes), "\"\\xf0\\x9f\\xa6\\x80\"");
+    }
+
+    #[test]
+    fn test_bstr_display() {
+        let hello_world = BStr::from_bytes(b"hello, world!");
+        assert_eq!(format!("{}", hello_world), "hello, world!");
+        let escapes = BStr::from_bytes(b"_\t_\n_\r_\\_\'_\"_");
+        assert_eq!(format!("{}", escapes), "_\\t_\\n_\\r_\\_'_\"_");
+        let others = BStr::from_bytes(b"\x01");
+        assert_eq!(format!("{}", others), "\\x01");
+        let non_ascii = BStr::from_bytes(b"d\xe9j\xe0 vu");
+        assert_eq!(format!("{}", non_ascii), "d\\xe9j\\xe0 vu");
+        let good_bytes = BStr::from_bytes(b"\xf0\x9f\xa6\x80");
+        assert_eq!(format!("{}", good_bytes), "\\xf0\\x9f\\xa6\\x80");
+    }
+
+    #[test]
+    fn test_bstr_debug() {
+        let hello_world = BStr::from_bytes(b"hello, world!");
+        assert_eq!(format!("{:?}", hello_world), "\"hello, world!\"");
+        let escapes = BStr::from_bytes(b"_\t_\n_\r_\\_\'_\"_");
+        assert_eq!(format!("{:?}", escapes), "\"_\\t_\\n_\\r_\\\\_'_\\\"_\"");
+        let others = BStr::from_bytes(b"\x01");
+        assert_eq!(format!("{:?}", others), "\"\\x01\"");
+        let non_ascii = BStr::from_bytes(b"d\xe9j\xe0 vu");
+        assert_eq!(format!("{:?}", non_ascii), "\"d\\xe9j\\xe0 vu\"");
+        let good_bytes = BStr::from_bytes(b"\xf0\x9f\xa6\x80");
+        assert_eq!(format!("{:?}", good_bytes), "\"\\xf0\\x9f\\xa6\\x80\"");
+    }
 }
 
 /// Allows formatting of [`fmt::Arguments`] into a raw buffer.
@@ -449,7 +620,7 @@ impl RawFormatter {
         self.pos as _
     }
 
-    /// Return the number of bytes written to the formatter.
+    /// Returns the number of bytes written to the formatter.
     pub(crate) fn bytes_written(&self) -> usize {
         self.pos - self.beg
     }
diff --git a/rust/kernel/sync.rs b/rust/kernel/sync.rs
index d219ee518eff..c983f63fd56e 100644
--- a/rust/kernel/sync.rs
+++ b/rust/kernel/sync.rs
@@ -13,8 +13,9 @@ pub mod lock;
 mod locked_by;
 
 pub use arc::{Arc, ArcBorrow, UniqueArc};
-pub use condvar::CondVar;
-pub use lock::{mutex::Mutex, spinlock::SpinLock};
+pub use condvar::{new_condvar, CondVar, CondVarTimeoutResult};
+pub use lock::mutex::{new_mutex, Mutex};
+pub use lock::spinlock::{new_spinlock, SpinLock};
 pub use locked_by::LockedBy;
 
 /// Represents a lockdep class. It's a wrapper around C's `lock_class_key`.
diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs
index 77cdbcf7bd2e..7d4c4bf58388 100644
--- a/rust/kernel/sync/arc.rs
+++ b/rust/kernel/sync/arc.rs
@@ -30,7 +30,7 @@ use core::{
     mem::{ManuallyDrop, MaybeUninit},
     ops::{Deref, DerefMut},
     pin::Pin,
-    ptr::{NonNull, Pointee},
+    ptr::NonNull,
 };
 use macros::pin_data;
 
@@ -56,7 +56,7 @@ mod std_vendor;
 ///     b: u32,
 /// }
 ///
-/// // Create a ref-counted instance of `Example`.
+/// // Create a refcounted instance of `Example`.
 /// let obj = Arc::try_new(Example { a: 10, b: 20 })?;
 ///
 /// // Get a new pointer to `obj` and increment the refcount.
@@ -239,22 +239,20 @@ impl<T: ?Sized> Arc<T> {
         // binary, so its layout is not so large that it can trigger arithmetic overflow.
         let val_offset = unsafe { refcount_layout.extend(val_layout).unwrap_unchecked().1 };
 
-        let metadata: <T as Pointee>::Metadata = core::ptr::metadata(ptr);
-        // SAFETY: The metadata of `T` and `ArcInner<T>` is the same because `ArcInner` is a struct
-        // with `T` as its last field.
+        // Pointer casts leave the metadata unchanged. This is okay because the metadata of `T` and
+        // `ArcInner<T>` is the same since `ArcInner` is a struct with `T` as its last field.
         //
         // This is documented at:
         // <https://doc.rust-lang.org/std/ptr/trait.Pointee.html>.
-        let metadata: <ArcInner<T> as Pointee>::Metadata =
-            unsafe { core::mem::transmute_copy(&metadata) };
+        let ptr = ptr as *const ArcInner<T>;
+
         // SAFETY: The pointer is in-bounds of an allocation both before and after offsetting the
         // pointer, since it originates from a previous call to `Arc::into_raw` and is still valid.
-        let ptr = unsafe { (ptr as *mut u8).sub(val_offset) as *mut () };
-        let ptr = core::ptr::from_raw_parts_mut(ptr, metadata);
+        let ptr = unsafe { ptr.byte_sub(val_offset) };
 
         // SAFETY: By the safety requirements we know that `ptr` came from `Arc::into_raw`, so the
         // reference count held then will be owned by the new `Arc` object.
-        unsafe { Self::from_inner(NonNull::new_unchecked(ptr)) }
+        unsafe { Self::from_inner(NonNull::new_unchecked(ptr.cast_mut())) }
     }
 
     /// Returns an [`ArcBorrow`] from the given [`Arc`].
@@ -365,12 +363,12 @@ impl<T: ?Sized> From<Pin<UniqueArc<T>>> for Arc<T> {
 /// A borrowed reference to an [`Arc`] instance.
 ///
 /// For cases when one doesn't ever need to increment the refcount on the allocation, it is simpler
-/// to use just `&T`, which we can trivially get from an `Arc<T>` instance.
+/// to use just `&T`, which we can trivially get from an [`Arc<T>`] instance.
 ///
 /// However, when one may need to increment the refcount, it is preferable to use an `ArcBorrow<T>`
 /// over `&Arc<T>` because the latter results in a double-indirection: a pointer (shared reference)
-/// to a pointer (`Arc<T>`) to the object (`T`). An [`ArcBorrow`] eliminates this double
-/// indirection while still allowing one to increment the refcount and getting an `Arc<T>` when/if
+/// to a pointer ([`Arc<T>`]) to the object (`T`). An [`ArcBorrow`] eliminates this double
+/// indirection while still allowing one to increment the refcount and getting an [`Arc<T>`] when/if
 /// needed.
 ///
 /// # Invariants
@@ -510,7 +508,7 @@ impl<T: ?Sized> Deref for ArcBorrow<'_, T> {
 /// # test().unwrap();
 /// ```
 ///
-/// In the following example we first allocate memory for a ref-counted `Example` but we don't
+/// In the following example we first allocate memory for a refcounted `Example` but we don't
 /// initialise it on allocation. We do initialise it later with a call to [`UniqueArc::write`],
 /// followed by a conversion to `Arc<Example>`. This is particularly useful when allocation happens
 /// in one context (e.g., sleepable) and initialisation in another (e.g., atomic):
@@ -560,7 +558,7 @@ impl<T> UniqueArc<T> {
     /// Tries to allocate a new [`UniqueArc`] instance.
     pub fn try_new(value: T) -> Result<Self, AllocError> {
         Ok(Self {
-            // INVARIANT: The newly-created object has a ref-count of 1.
+            // INVARIANT: The newly-created object has a refcount of 1.
             inner: Arc::try_new(value)?,
         })
     }
@@ -574,7 +572,7 @@ impl<T> UniqueArc<T> {
             data <- init::uninit::<T, AllocError>(),
         }? AllocError))?;
         Ok(UniqueArc {
-            // INVARIANT: The newly-created object has a ref-count of 1.
+            // INVARIANT: The newly-created object has a refcount of 1.
             // SAFETY: The pointer from the `Box` is valid.
             inner: unsafe { Arc::from_inner(Box::leak(inner).into()) },
         })
diff --git a/rust/kernel/sync/condvar.rs b/rust/kernel/sync/condvar.rs
index f65e19d5a37c..0c3671caffeb 100644
--- a/rust/kernel/sync/condvar.rs
+++ b/rust/kernel/sync/condvar.rs
@@ -6,8 +6,18 @@
 //! variable.
 
 use super::{lock::Backend, lock::Guard, LockClassKey};
-use crate::{bindings, init::PinInit, pin_init, str::CStr, types::Opaque};
+use crate::{
+    bindings,
+    init::PinInit,
+    pin_init,
+    str::CStr,
+    task::{MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE, TASK_NORMAL, TASK_UNINTERRUPTIBLE},
+    time::Jiffies,
+    types::Opaque,
+};
+use core::ffi::{c_int, c_long};
 use core::marker::PhantomPinned;
+use core::ptr;
 use macros::pin_data;
 
 /// Creates a [`CondVar`] initialiser with the given name and a newly-created lock class.
@@ -17,6 +27,7 @@ macro_rules! new_condvar {
         $crate::sync::CondVar::new($crate::optional_name!($($name)?), $crate::static_lock_class!())
     };
 }
+pub use new_condvar;
 
 /// A conditional variable.
 ///
@@ -34,8 +45,7 @@ macro_rules! new_condvar {
 /// The following is an example of using a condvar with a mutex:
 ///
 /// ```
-/// use kernel::sync::{CondVar, Mutex};
-/// use kernel::{new_condvar, new_mutex};
+/// use kernel::sync::{new_condvar, new_mutex, CondVar, Mutex};
 ///
 /// #[pin_data]
 /// pub struct Example {
@@ -73,10 +83,12 @@ macro_rules! new_condvar {
 #[pin_data]
 pub struct CondVar {
     #[pin]
-    pub(crate) wait_list: Opaque<bindings::wait_queue_head>,
+    pub(crate) wait_queue_head: Opaque<bindings::wait_queue_head>,
 
     /// A condvar needs to be pinned because it contains a [`struct list_head`] that is
     /// self-referential, so it cannot be safely moved once it is initialised.
+    ///
+    /// [`struct list_head`]: srctree/include/linux/types.h
     #[pin]
     _pin: PhantomPinned,
 }
@@ -96,28 +108,35 @@ impl CondVar {
             _pin: PhantomPinned,
             // SAFETY: `slot` is valid while the closure is called and both `name` and `key` have
             // static lifetimes so they live indefinitely.
-            wait_list <- Opaque::ffi_init(|slot| unsafe {
+            wait_queue_head <- Opaque::ffi_init(|slot| unsafe {
                 bindings::__init_waitqueue_head(slot, name.as_char_ptr(), key.as_ptr())
             }),
         })
     }
 
-    fn wait_internal<T: ?Sized, B: Backend>(&self, wait_state: u32, guard: &mut Guard<'_, T, B>) {
+    fn wait_internal<T: ?Sized, B: Backend>(
+        &self,
+        wait_state: c_int,
+        guard: &mut Guard<'_, T, B>,
+        timeout_in_jiffies: c_long,
+    ) -> c_long {
         let wait = Opaque::<bindings::wait_queue_entry>::uninit();
 
         // SAFETY: `wait` points to valid memory.
         unsafe { bindings::init_wait(wait.get()) };
 
-        // SAFETY: Both `wait` and `wait_list` point to valid memory.
+        // SAFETY: Both `wait` and `wait_queue_head` point to valid memory.
         unsafe {
-            bindings::prepare_to_wait_exclusive(self.wait_list.get(), wait.get(), wait_state as _)
+            bindings::prepare_to_wait_exclusive(self.wait_queue_head.get(), wait.get(), wait_state)
         };
 
-        // SAFETY: No arguments, switches to another thread.
-        guard.do_unlocked(|| unsafe { bindings::schedule() });
+        // SAFETY: Switches to another thread. The timeout can be any number.
+        let ret = guard.do_unlocked(|| unsafe { bindings::schedule_timeout(timeout_in_jiffies) });
+
+        // SAFETY: Both `wait` and `wait_queue_head` point to valid memory.
+        unsafe { bindings::finish_wait(self.wait_queue_head.get(), wait.get()) };
 
-        // SAFETY: Both `wait` and `wait_list` point to valid memory.
-        unsafe { bindings::finish_wait(self.wait_list.get(), wait.get()) };
+        ret
     }
 
     /// Releases the lock and waits for a notification in uninterruptible mode.
@@ -127,7 +146,7 @@ impl CondVar {
     /// [`CondVar::notify_one`] or [`CondVar::notify_all`]. Note that it may also wake up
     /// spuriously.
     pub fn wait<T: ?Sized, B: Backend>(&self, guard: &mut Guard<'_, T, B>) {
-        self.wait_internal(bindings::TASK_UNINTERRUPTIBLE, guard);
+        self.wait_internal(TASK_UNINTERRUPTIBLE, guard, MAX_SCHEDULE_TIMEOUT);
     }
 
     /// Releases the lock and waits for a notification in interruptible mode.
@@ -138,29 +157,60 @@ impl CondVar {
     /// Returns whether there is a signal pending.
     #[must_use = "wait_interruptible returns if a signal is pending, so the caller must check the return value"]
     pub fn wait_interruptible<T: ?Sized, B: Backend>(&self, guard: &mut Guard<'_, T, B>) -> bool {
-        self.wait_internal(bindings::TASK_INTERRUPTIBLE, guard);
+        self.wait_internal(TASK_INTERRUPTIBLE, guard, MAX_SCHEDULE_TIMEOUT);
         crate::current!().signal_pending()
     }
 
-    /// Calls the kernel function to notify the appropriate number of threads with the given flags.
-    fn notify(&self, count: i32, flags: u32) {
-        // SAFETY: `wait_list` points to valid memory.
+    /// Releases the lock and waits for a notification in interruptible mode.
+    ///
+    /// Atomically releases the given lock (whose ownership is proven by the guard) and puts the
+    /// thread to sleep. It wakes up when notified by [`CondVar::notify_one`] or
+    /// [`CondVar::notify_all`], or when a timeout occurs, or when the thread receives a signal.
+    #[must_use = "wait_interruptible_timeout returns if a signal is pending, so the caller must check the return value"]
+    pub fn wait_interruptible_timeout<T: ?Sized, B: Backend>(
+        &self,
+        guard: &mut Guard<'_, T, B>,
+        jiffies: Jiffies,
+    ) -> CondVarTimeoutResult {
+        let jiffies = jiffies.try_into().unwrap_or(MAX_SCHEDULE_TIMEOUT);
+        let res = self.wait_internal(TASK_INTERRUPTIBLE, guard, jiffies);
+
+        match (res as Jiffies, crate::current!().signal_pending()) {
+            (jiffies, true) => CondVarTimeoutResult::Signal { jiffies },
+            (0, false) => CondVarTimeoutResult::Timeout,
+            (jiffies, false) => CondVarTimeoutResult::Woken { jiffies },
+        }
+    }
+
+    /// Calls the kernel function to notify the appropriate number of threads.
+    fn notify(&self, count: c_int) {
+        // SAFETY: `wait_queue_head` points to valid memory.
         unsafe {
             bindings::__wake_up(
-                self.wait_list.get(),
-                bindings::TASK_NORMAL,
+                self.wait_queue_head.get(),
+                TASK_NORMAL,
                 count,
-                flags as _,
+                ptr::null_mut(),
             )
         };
     }
 
+    /// Calls the kernel function to notify one thread synchronously.
+    ///
+    /// This method behaves like `notify_one`, except that it hints to the scheduler that the
+    /// current thread is about to go to sleep, so it should schedule the target thread on the same
+    /// CPU.
+    pub fn notify_sync(&self) {
+        // SAFETY: `wait_queue_head` points to valid memory.
+        unsafe { bindings::__wake_up_sync(self.wait_queue_head.get(), TASK_NORMAL) };
+    }
+
     /// Wakes a single waiter up, if any.
     ///
     /// This is not 'sticky' in the sense that if no thread is waiting, the notification is lost
     /// completely (as opposed to automatically waking up the next waiter).
     pub fn notify_one(&self) {
-        self.notify(1, 0);
+        self.notify(1);
     }
 
     /// Wakes all waiters up, if any.
@@ -168,6 +218,22 @@ impl CondVar {
     /// This is not 'sticky' in the sense that if no thread is waiting, the notification is lost
     /// completely (as opposed to automatically waking up the next waiter).
     pub fn notify_all(&self) {
-        self.notify(0, 0);
+        self.notify(0);
     }
 }
+
+/// The return type of `wait_timeout`.
+pub enum CondVarTimeoutResult {
+    /// The timeout was reached.
+    Timeout,
+    /// Somebody woke us up.
+    Woken {
+        /// Remaining sleep duration.
+        jiffies: Jiffies,
+    },
+    /// A signal occurred.
+    Signal {
+        /// Remaining sleep duration.
+        jiffies: Jiffies,
+    },
+}
diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs
index f12a684bc957..5b5c8efe427a 100644
--- a/rust/kernel/sync/lock.rs
+++ b/rust/kernel/sync/lock.rs
@@ -21,14 +21,21 @@ pub mod spinlock;
 /// # Safety
 ///
 /// - Implementers must ensure that only one thread/CPU may access the protected data once the lock
-/// is owned, that is, between calls to `lock` and `unlock`.
-/// - Implementers must also ensure that `relock` uses the same locking method as the original
-/// lock operation.
+///   is owned, that is, between calls to [`lock`] and [`unlock`].
+/// - Implementers must also ensure that [`relock`] uses the same locking method as the original
+///   lock operation.
+///
+/// [`lock`]: Backend::lock
+/// [`unlock`]: Backend::unlock
+/// [`relock`]: Backend::relock
 pub unsafe trait Backend {
     /// The state required by the lock.
     type State;
 
-    /// The state required to be kept between lock and unlock.
+    /// The state required to be kept between [`lock`] and [`unlock`].
+    ///
+    /// [`lock`]: Backend::lock
+    /// [`unlock`]: Backend::unlock
     type GuardState;
 
     /// Initialises the lock.
@@ -139,7 +146,7 @@ pub struct Guard<'a, T: ?Sized, B: Backend> {
 unsafe impl<T: Sync + ?Sized, B: Backend> Sync for Guard<'_, T, B> {}
 
 impl<T: ?Sized, B: Backend> Guard<'_, T, B> {
-    pub(crate) fn do_unlocked(&mut self, cb: impl FnOnce()) {
+    pub(crate) fn do_unlocked<U>(&mut self, cb: impl FnOnce() -> U) -> U {
         // SAFETY: The caller owns the lock, so it is safe to unlock it.
         unsafe { B::unlock(self.lock.state.get(), &self.state) };
 
@@ -147,7 +154,7 @@ impl<T: ?Sized, B: Backend> Guard<'_, T, B> {
         let _relock =
             ScopeGuard::new(|| unsafe { B::relock(self.lock.state.get(), &mut self.state) });
 
-        cb();
+        cb()
     }
 }
 
diff --git a/rust/kernel/sync/lock/mutex.rs b/rust/kernel/sync/lock/mutex.rs
index 8c524a3ec45a..ef4c4634d294 100644
--- a/rust/kernel/sync/lock/mutex.rs
+++ b/rust/kernel/sync/lock/mutex.rs
@@ -17,6 +17,7 @@ macro_rules! new_mutex {
             $inner, $crate::optional_name!($($name)?), $crate::static_lock_class!())
     };
 }
+pub use new_mutex;
 
 /// A mutual exclusion primitive.
 ///
@@ -35,7 +36,7 @@ macro_rules! new_mutex {
 /// contains an inner struct (`Inner`) that is protected by a mutex.
 ///
 /// ```
-/// use kernel::{init::InPlaceInit, init::PinInit, new_mutex, pin_init, sync::Mutex};
+/// use kernel::sync::{new_mutex, Mutex};
 ///
 /// struct Inner {
 ///     a: u32,
diff --git a/rust/kernel/sync/lock/spinlock.rs b/rust/kernel/sync/lock/spinlock.rs
index 068535ce1b29..0b22c635634f 100644
--- a/rust/kernel/sync/lock/spinlock.rs
+++ b/rust/kernel/sync/lock/spinlock.rs
@@ -17,6 +17,7 @@ macro_rules! new_spinlock {
             $inner, $crate::optional_name!($($name)?), $crate::static_lock_class!())
     };
 }
+pub use new_spinlock;
 
 /// A spinlock.
 ///
@@ -33,7 +34,7 @@ macro_rules! new_spinlock {
 /// contains an inner struct (`Inner`) that is protected by a spinlock.
 ///
 /// ```
-/// use kernel::{init::InPlaceInit, init::PinInit, new_spinlock, pin_init, sync::SpinLock};
+/// use kernel::sync::{new_spinlock, SpinLock};
 ///
 /// struct Inner {
 ///     a: u32,
@@ -112,7 +113,7 @@ unsafe impl super::Backend for SpinLockBackend {
 
     unsafe fn unlock(ptr: *mut Self::State, _guard_state: &Self::GuardState) {
         // SAFETY: The safety requirements of this function ensure that `ptr` is valid and that the
-        // caller is the owner of the mutex.
+        // caller is the owner of the spinlock.
         unsafe { bindings::spin_unlock(ptr) }
     }
 }
diff --git a/rust/kernel/sync/locked_by.rs b/rust/kernel/sync/locked_by.rs
index b17ee5cd98f3..babc731bd5f6 100644
--- a/rust/kernel/sync/locked_by.rs
+++ b/rust/kernel/sync/locked_by.rs
@@ -9,14 +9,17 @@ use core::{cell::UnsafeCell, mem::size_of, ptr};
 /// Allows access to some data to be serialised by a lock that does not wrap it.
 ///
 /// In most cases, data protected by a lock is wrapped by the appropriate lock type, e.g.,
-/// [`super::Mutex`] or [`super::SpinLock`]. [`LockedBy`] is meant for cases when this is not
-/// possible. For example, if a container has a lock and some data in the contained elements needs
+/// [`Mutex`] or [`SpinLock`]. [`LockedBy`] is meant for cases when this is not possible.
+/// For example, if a container has a lock and some data in the contained elements needs
 /// to be protected by the same lock.
 ///
 /// [`LockedBy`] wraps the data in lieu of another locking primitive, and only allows access to it
 /// when the caller shows evidence that the 'external' lock is locked. It panics if the evidence
 /// refers to the wrong instance of the lock.
 ///
+/// [`Mutex`]: super::Mutex
+/// [`SpinLock`]: super::SpinLock
+///
 /// # Examples
 ///
 /// The following is an example for illustrative purposes: `InnerDirectory::bytes_used` is an
diff --git a/rust/kernel/task.rs b/rust/kernel/task.rs
index 9451932d5d86..ca6e7e31d71c 100644
--- a/rust/kernel/task.rs
+++ b/rust/kernel/task.rs
@@ -5,7 +5,23 @@
 //! C header: [`include/linux/sched.h`](srctree/include/linux/sched.h).
 
 use crate::{bindings, types::Opaque};
-use core::{marker::PhantomData, ops::Deref, ptr};
+use core::{
+    ffi::{c_int, c_long, c_uint},
+    marker::PhantomData,
+    ops::Deref,
+    ptr,
+};
+
+/// A sentinel value used for infinite timeouts.
+pub const MAX_SCHEDULE_TIMEOUT: c_long = c_long::MAX;
+
+/// Bitmask for tasks that are sleeping in an interruptible state.
+pub const TASK_INTERRUPTIBLE: c_int = bindings::TASK_INTERRUPTIBLE as c_int;
+/// Bitmask for tasks that are sleeping in an uninterruptible state.
+pub const TASK_UNINTERRUPTIBLE: c_int = bindings::TASK_UNINTERRUPTIBLE as c_int;
+/// Convenience constant for waking up tasks regardless of whether they are in interruptible or
+/// uninterruptible sleep.
+pub const TASK_NORMAL: c_uint = bindings::TASK_NORMAL as c_uint;
 
 /// Returns the currently running task.
 #[macro_export]
@@ -23,7 +39,7 @@ macro_rules! current {
 ///
 /// All instances are valid tasks created by the C portion of the kernel.
 ///
-/// Instances of this type are always ref-counted, that is, a call to `get_task_struct` ensures
+/// Instances of this type are always refcounted, that is, a call to `get_task_struct` ensures
 /// that the allocation remains valid at least until the matching call to `put_task_struct`.
 ///
 /// # Examples
@@ -116,7 +132,7 @@ impl Task {
     /// Returns the group leader of the given task.
     pub fn group_leader(&self) -> &Task {
         // SAFETY: By the type invariant, we know that `self.0` is a valid task. Valid tasks always
-        // have a valid group_leader.
+        // have a valid `group_leader`.
         let ptr = unsafe { *ptr::addr_of!((*self.0.get()).group_leader) };
 
         // SAFETY: The lifetime of the returned task reference is tied to the lifetime of `self`,
@@ -147,7 +163,7 @@ impl Task {
     }
 }
 
-// SAFETY: The type invariants guarantee that `Task` is always ref-counted.
+// SAFETY: The type invariants guarantee that `Task` is always refcounted.
 unsafe impl crate::types::AlwaysRefCounted for Task {
     fn inc_ref(&self) {
         // SAFETY: The existence of a shared reference means that the refcount is nonzero.
diff --git a/rust/kernel/time.rs b/rust/kernel/time.rs
new file mode 100644
index 000000000000..25a896eed468
--- /dev/null
+++ b/rust/kernel/time.rs
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Time related primitives.
+//!
+//! This module contains the kernel APIs related to time and timers that
+//! have been ported or wrapped for usage by Rust code in the kernel.
+
+/// The time unit of Linux kernel. One jiffy equals (1/HZ) second.
+pub type Jiffies = core::ffi::c_ulong;
+
+/// The millisecond time unit.
+pub type Msecs = core::ffi::c_uint;
+
+/// Converts milliseconds to jiffies.
+#[inline]
+pub fn msecs_to_jiffies(msecs: Msecs) -> Jiffies {
+    // SAFETY: The `__msecs_to_jiffies` function is always safe to call no
+    // matter what the argument is.
+    unsafe { bindings::__msecs_to_jiffies(msecs) }
+}
diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs
index fdb778e65d79..aa77bad9bce4 100644
--- a/rust/kernel/types.rs
+++ b/rust/kernel/types.rs
@@ -46,6 +46,25 @@ pub trait ForeignOwnable: Sized {
     /// Additionally, all instances (if any) of values returned by [`ForeignOwnable::borrow`] for
     /// this object must have been dropped.
     unsafe fn from_foreign(ptr: *const core::ffi::c_void) -> Self;
+
+    /// Tries to convert a foreign-owned object back to a Rust-owned one.
+    ///
+    /// A convenience wrapper over [`ForeignOwnable::from_foreign`] that returns [`None`] if `ptr`
+    /// is null.
+    ///
+    /// # Safety
+    ///
+    /// `ptr` must either be null or satisfy the safety requirements for
+    /// [`ForeignOwnable::from_foreign`].
+    unsafe fn try_from_foreign(ptr: *const core::ffi::c_void) -> Option<Self> {
+        if ptr.is_null() {
+            None
+        } else {
+            // SAFETY: Since `ptr` is not null here, then `ptr` satisfies the safety requirements
+            // of `from_foreign` given the safety requirements of this function.
+            unsafe { Some(Self::from_foreign(ptr)) }
+        }
+    }
 }
 
 impl<T: 'static> ForeignOwnable for Box<T> {
@@ -90,6 +109,7 @@ impl ForeignOwnable for () {
 ///
 /// In the example below, we have multiple exit paths and we want to log regardless of which one is
 /// taken:
+///
 /// ```
 /// # use kernel::types::ScopeGuard;
 /// fn example1(arg: bool) {
@@ -108,6 +128,7 @@ impl ForeignOwnable for () {
 ///
 /// In the example below, we want to log the same message on all early exits but a different one on
 /// the main exit path:
+///
 /// ```
 /// # use kernel::types::ScopeGuard;
 /// fn example2(arg: bool) {
@@ -129,6 +150,7 @@ impl ForeignOwnable for () {
 ///
 /// In the example below, we need a mutable object (the vector) to be accessible within the log
 /// function, so we wrap it in the [`ScopeGuard`]:
+///
 /// ```
 /// # use kernel::types::ScopeGuard;
 /// fn example3(arg: bool) -> Result {
diff --git a/rust/kernel/workqueue.rs b/rust/kernel/workqueue.rs
index d00231e18007..480cb292e7c2 100644
--- a/rust/kernel/workqueue.rs
+++ b/rust/kernel/workqueue.rs
@@ -12,19 +12,19 @@
 //!
 //! # The raw API
 //!
-//! The raw API consists of the `RawWorkItem` trait, where the work item needs to provide an
+//! The raw API consists of the [`RawWorkItem`] trait, where the work item needs to provide an
 //! arbitrary function that knows how to enqueue the work item. It should usually not be used
 //! directly, but if you want to, you can use it without using the pieces from the safe API.
 //!
 //! # The safe API
 //!
-//! The safe API is used via the `Work` struct and `WorkItem` traits. Furthermore, it also includes
-//! a trait called `WorkItemPointer`, which is usually not used directly by the user.
+//! The safe API is used via the [`Work`] struct and [`WorkItem`] traits. Furthermore, it also
+//! includes a trait called [`WorkItemPointer`], which is usually not used directly by the user.
 //!
-//!  * The `Work` struct is the Rust wrapper for the C `work_struct` type.
-//!  * The `WorkItem` trait is implemented for structs that can be enqueued to a workqueue.
-//!  * The `WorkItemPointer` trait is implemented for the pointer type that points at a something
-//!    that implements `WorkItem`.
+//!  * The [`Work`] struct is the Rust wrapper for the C `work_struct` type.
+//!  * The [`WorkItem`] trait is implemented for structs that can be enqueued to a workqueue.
+//!  * The [`WorkItemPointer`] trait is implemented for the pointer type that points at a something
+//!    that implements [`WorkItem`].
 //!
 //! ## Example
 //!
@@ -35,8 +35,7 @@
 //! ```
 //! use kernel::prelude::*;
 //! use kernel::sync::Arc;
-//! use kernel::workqueue::{self, Work, WorkItem};
-//! use kernel::{impl_has_work, new_work};
+//! use kernel::workqueue::{self, impl_has_work, new_work, Work, WorkItem};
 //!
 //! #[pin_data]
 //! struct MyStruct {
@@ -78,8 +77,7 @@
 //! ```
 //! use kernel::prelude::*;
 //! use kernel::sync::Arc;
-//! use kernel::workqueue::{self, Work, WorkItem};
-//! use kernel::{impl_has_work, new_work};
+//! use kernel::workqueue::{self, impl_has_work, new_work, Work, WorkItem};
 //!
 //! #[pin_data]
 //! struct MyStruct {
@@ -147,6 +145,7 @@ macro_rules! new_work {
         $crate::workqueue::Work::new($crate::optional_name!($($name)?), $crate::static_lock_class!())
     };
 }
+pub use new_work;
 
 /// A kernel work queue.
 ///
@@ -168,7 +167,7 @@ impl Queue {
     /// # Safety
     ///
     /// The caller must ensure that the provided raw pointer is not dangling, that it points at a
-    /// valid workqueue, and that it remains valid until the end of 'a.
+    /// valid workqueue, and that it remains valid until the end of `'a`.
     pub unsafe fn from_raw<'a>(ptr: *const bindings::workqueue_struct) -> &'a Queue {
         // SAFETY: The `Queue` type is `#[repr(transparent)]`, so the pointer cast is valid. The
         // caller promises that the pointer is not dangling.
@@ -222,7 +221,9 @@ impl Queue {
     }
 }
 
-/// A helper type used in `try_spawn`.
+/// A helper type used in [`try_spawn`].
+///
+/// [`try_spawn`]: Queue::try_spawn
 #[pin_data]
 struct ClosureWork<T> {
     #[pin]
@@ -257,14 +258,16 @@ impl<T: FnOnce()> WorkItem for ClosureWork<T> {
 /// actual value of the id is not important as long as you use different ids for different fields
 /// of the same struct. (Fields of different structs need not use different ids.)
 ///
-/// Note that the id is used only to select the right method to call during compilation. It wont be
+/// Note that the id is used only to select the right method to call during compilation. It won't be
 /// part of the final executable.
 ///
 /// # Safety
 ///
-/// Implementers must ensure that any pointers passed to a `queue_work_on` closure by `__enqueue`
+/// Implementers must ensure that any pointers passed to a `queue_work_on` closure by [`__enqueue`]
 /// remain valid for the duration specified in the guarantees section of the documentation for
-/// `__enqueue`.
+/// [`__enqueue`].
+///
+/// [`__enqueue`]: RawWorkItem::__enqueue
 pub unsafe trait RawWorkItem<const ID: u64> {
     /// The return type of [`Queue::enqueue`].
     type EnqueueOutput;
@@ -294,10 +297,11 @@ pub unsafe trait RawWorkItem<const ID: u64> {
 
 /// Defines the method that should be called directly when a work item is executed.
 ///
-/// This trait is implemented by `Pin<Box<T>>` and `Arc<T>`, and is mainly intended to be
+/// This trait is implemented by `Pin<Box<T>>` and [`Arc<T>`], and is mainly intended to be
 /// implemented for smart pointer types. For your own structs, you would implement [`WorkItem`]
-/// instead. The `run` method on this trait will usually just perform the appropriate
-/// `container_of` translation and then call into the `run` method from the [`WorkItem`] trait.
+/// instead. The [`run`] method on this trait will usually just perform the appropriate
+/// `container_of` translation and then call into the [`run`][WorkItem::run] method from the
+/// [`WorkItem`] trait.
 ///
 /// This trait is used when the `work_struct` field is defined using the [`Work`] helper.
 ///
@@ -313,8 +317,10 @@ pub unsafe trait WorkItemPointer<const ID: u64>: RawWorkItem<ID> {
     ///
     /// # Safety
     ///
-    /// The provided `work_struct` pointer must originate from a previous call to `__enqueue` where
-    /// the `queue_work_on` closure returned true, and the pointer must still be valid.
+    /// The provided `work_struct` pointer must originate from a previous call to [`__enqueue`]
+    /// where the `queue_work_on` closure returned true, and the pointer must still be valid.
+    ///
+    /// [`__enqueue`]: RawWorkItem::__enqueue
     unsafe extern "C" fn run(ptr: *mut bindings::work_struct);
 }
 
@@ -332,12 +338,14 @@ pub trait WorkItem<const ID: u64 = 0> {
 
 /// Links for a work item.
 ///
-/// This struct contains a function pointer to the `run` function from the [`WorkItemPointer`]
+/// This struct contains a function pointer to the [`run`] function from the [`WorkItemPointer`]
 /// trait, and defines the linked list pointers necessary to enqueue a work item in a workqueue.
 ///
 /// Wraps the kernel's C `struct work_struct`.
 ///
 /// This is a helper type used to associate a `work_struct` with the [`WorkItem`] that uses it.
+///
+/// [`run`]: WorkItemPointer::run
 #[repr(transparent)]
 pub struct Work<T: ?Sized, const ID: u64 = 0> {
     work: Opaque<bindings::work_struct>,
@@ -400,9 +408,8 @@ impl<T: ?Sized, const ID: u64> Work<T, ID> {
 /// like this:
 ///
 /// ```no_run
-/// use kernel::impl_has_work;
 /// use kernel::prelude::*;
-/// use kernel::workqueue::Work;
+/// use kernel::workqueue::{impl_has_work, Work};
 ///
 /// struct MyWorkItem {
 ///     work_field: Work<MyWorkItem, 1>,
@@ -413,28 +420,25 @@ impl<T: ?Sized, const ID: u64> Work<T, ID> {
 /// }
 /// ```
 ///
-/// Note that since the `Work` type is annotated with an id, you can have several `work_struct`
+/// Note that since the [`Work`] type is annotated with an id, you can have several `work_struct`
 /// fields by using a different id for each one.
 ///
 /// # Safety
 ///
-/// The [`OFFSET`] constant must be the offset of a field in Self of type [`Work<T, ID>`]. The methods on
-/// this trait must have exactly the behavior that the definitions given below have.
+/// The [`OFFSET`] constant must be the offset of a field in `Self` of type [`Work<T, ID>`]. The
+/// methods on this trait must have exactly the behavior that the definitions given below have.
 ///
-/// [`Work<T, ID>`]: Work
 /// [`impl_has_work!`]: crate::impl_has_work
 /// [`OFFSET`]: HasWork::OFFSET
 pub unsafe trait HasWork<T, const ID: u64 = 0> {
     /// The offset of the [`Work<T, ID>`] field.
-    ///
-    /// [`Work<T, ID>`]: Work
     const OFFSET: usize;
 
     /// Returns the offset of the [`Work<T, ID>`] field.
     ///
-    /// This method exists because the [`OFFSET`] constant cannot be accessed if the type is not Sized.
+    /// This method exists because the [`OFFSET`] constant cannot be accessed if the type is not
+    /// [`Sized`].
     ///
-    /// [`Work<T, ID>`]: Work
     /// [`OFFSET`]: HasWork::OFFSET
     #[inline]
     fn get_work_offset(&self) -> usize {
@@ -446,8 +450,6 @@ pub unsafe trait HasWork<T, const ID: u64 = 0> {
     /// # Safety
     ///
     /// The provided pointer must point at a valid struct of type `Self`.
-    ///
-    /// [`Work<T, ID>`]: Work
     #[inline]
     unsafe fn raw_get_work(ptr: *mut Self) -> *mut Work<T, ID> {
         // SAFETY: The caller promises that the pointer is valid.
@@ -459,8 +461,6 @@ pub unsafe trait HasWork<T, const ID: u64 = 0> {
     /// # Safety
     ///
     /// The pointer must point at a [`Work<T, ID>`] field in a struct of type `Self`.
-    ///
-    /// [`Work<T, ID>`]: Work
     #[inline]
     unsafe fn work_container_of(ptr: *mut Work<T, ID>) -> *mut Self
     where
@@ -477,9 +477,8 @@ pub unsafe trait HasWork<T, const ID: u64 = 0> {
 /// # Examples
 ///
 /// ```
-/// use kernel::impl_has_work;
 /// use kernel::sync::Arc;
-/// use kernel::workqueue::{self, Work};
+/// use kernel::workqueue::{self, impl_has_work, Work};
 ///
 /// struct MyStruct {
 ///     work_field: Work<MyStruct, 17>,
@@ -489,8 +488,6 @@ pub unsafe trait HasWork<T, const ID: u64 = 0> {
 ///     impl HasWork<MyStruct, 17> for MyStruct { self.work_field }
 /// }
 /// ```
-///
-/// [`HasWork<T, ID>`]: HasWork
 #[macro_export]
 macro_rules! impl_has_work {
     ($(impl$(<$($implarg:ident),*>)?
@@ -513,6 +510,7 @@ macro_rules! impl_has_work {
         }
     )*};
 }
+pub use impl_has_work;
 
 impl_has_work! {
     impl<T> HasWork<Self> for ClosureWork<T> { self.work }
diff --git a/rust/macros/module.rs b/rust/macros/module.rs
index d62d8710d77a..27979e582e4b 100644
--- a/rust/macros/module.rs
+++ b/rust/macros/module.rs
@@ -222,10 +222,15 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream {
             }};
 
             // Loadable modules need to export the `{{init,cleanup}}_module` identifiers.
+            /// # Safety
+            ///
+            /// This function must not be called after module initialization, because it may be
+            /// freed after that completes.
             #[cfg(MODULE)]
             #[doc(hidden)]
             #[no_mangle]
-            pub extern \"C\" fn init_module() -> core::ffi::c_int {{
+            #[link_section = \".init.text\"]
+            pub unsafe extern \"C\" fn init_module() -> core::ffi::c_int {{
                 __init()
             }}
 
diff --git a/samples/bpf/asm_goto_workaround.h b/samples/bpf/asm_goto_workaround.h
index 7048bb3594d6..634e81d83efd 100644
--- a/samples/bpf/asm_goto_workaround.h
+++ b/samples/bpf/asm_goto_workaround.h
@@ -4,14 +4,14 @@
 #define __ASM_GOTO_WORKAROUND_H
 
 /*
- * This will bring in asm_volatile_goto and asm_inline macro definitions
+ * This will bring in asm_goto_output and asm_inline macro definitions
  * if enabled by compiler and config options.
  */
 #include <linux/types.h>
 
-#ifdef asm_volatile_goto
-#undef asm_volatile_goto
-#define asm_volatile_goto(x...) asm volatile("invalid use of asm_volatile_goto")
+#ifdef asm_goto_output
+#undef asm_goto_output
+#define asm_goto_output(x...) asm volatile("invalid use of asm_goto_output")
 #endif
 
 /*
diff --git a/samples/cgroup/.gitignore b/samples/cgroup/.gitignore
new file mode 100644
index 000000000000..3a0161194cce
--- /dev/null
+++ b/samples/cgroup/.gitignore
@@ -0,0 +1,3 @@
+/cgroup_event_listener
+/memcg_event_listener
+
diff --git a/samples/ftrace/ftrace-direct-modify.c b/samples/ftrace/ftrace-direct-modify.c
index e2a6a69352df..81220390851a 100644
--- a/samples/ftrace/ftrace-direct-modify.c
+++ b/samples/ftrace/ftrace-direct-modify.c
@@ -24,6 +24,41 @@ extern void my_tramp2(void *);
 
 static unsigned long my_ip = (unsigned long)schedule;
 
+#ifdef CONFIG_RISCV
+#include <asm/asm.h>
+
+asm (
+"	.pushsection    .text, \"ax\", @progbits\n"
+"	.type		my_tramp1, @function\n"
+"	.globl		my_tramp1\n"
+"   my_tramp1:\n"
+"	addi	sp,sp,-2*"SZREG"\n"
+"	"REG_S"	t0,0*"SZREG"(sp)\n"
+"	"REG_S"	ra,1*"SZREG"(sp)\n"
+"	call	my_direct_func1\n"
+"	"REG_L"	t0,0*"SZREG"(sp)\n"
+"	"REG_L"	ra,1*"SZREG"(sp)\n"
+"	addi	sp,sp,2*"SZREG"\n"
+"	jr	t0\n"
+"	.size		my_tramp1, .-my_tramp1\n"
+"	.type		my_tramp2, @function\n"
+"	.globl		my_tramp2\n"
+
+"   my_tramp2:\n"
+"	addi	sp,sp,-2*"SZREG"\n"
+"	"REG_S"	t0,0*"SZREG"(sp)\n"
+"	"REG_S"	ra,1*"SZREG"(sp)\n"
+"	call	my_direct_func2\n"
+"	"REG_L"	t0,0*"SZREG"(sp)\n"
+"	"REG_L"	ra,1*"SZREG"(sp)\n"
+"	addi	sp,sp,2*"SZREG"\n"
+"	jr	t0\n"
+"	.size		my_tramp2, .-my_tramp2\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_RISCV */
+
 #ifdef CONFIG_X86_64
 
 #include <asm/ibt.h>
diff --git a/samples/ftrace/ftrace-direct-multi-modify.c b/samples/ftrace/ftrace-direct-multi-modify.c
index 2e349834d63c..f943e40d57fd 100644
--- a/samples/ftrace/ftrace-direct-multi-modify.c
+++ b/samples/ftrace/ftrace-direct-multi-modify.c
@@ -22,6 +22,47 @@ void my_direct_func2(unsigned long ip)
 extern void my_tramp1(void *);
 extern void my_tramp2(void *);
 
+#ifdef CONFIG_RISCV
+#include <asm/asm.h>
+
+asm (
+"	.pushsection    .text, \"ax\", @progbits\n"
+"	.type		my_tramp1, @function\n"
+"	.globl		my_tramp1\n"
+"   my_tramp1:\n"
+"       addi	sp,sp,-3*"SZREG"\n"
+"       "REG_S"	a0,0*"SZREG"(sp)\n"
+"       "REG_S"	t0,1*"SZREG"(sp)\n"
+"       "REG_S"	ra,2*"SZREG"(sp)\n"
+"       mv	a0,t0\n"
+"       call	my_direct_func1\n"
+"       "REG_L"	a0,0*"SZREG"(sp)\n"
+"       "REG_L"	t0,1*"SZREG"(sp)\n"
+"       "REG_L"	ra,2*"SZREG"(sp)\n"
+"       addi	sp,sp,3*"SZREG"\n"
+"	jr	t0\n"
+"	.size		my_tramp1, .-my_tramp1\n"
+
+"	.type		my_tramp2, @function\n"
+"	.globl		my_tramp2\n"
+"   my_tramp2:\n"
+"       addi	sp,sp,-3*"SZREG"\n"
+"       "REG_S"	a0,0*"SZREG"(sp)\n"
+"       "REG_S"	t0,1*"SZREG"(sp)\n"
+"       "REG_S"	ra,2*"SZREG"(sp)\n"
+"       mv	a0,t0\n"
+"       call	my_direct_func2\n"
+"       "REG_L"	a0,0*"SZREG"(sp)\n"
+"       "REG_L"	t0,1*"SZREG"(sp)\n"
+"       "REG_L"	ra,2*"SZREG"(sp)\n"
+"       addi	sp,sp,3*"SZREG"\n"
+"	jr	t0\n"
+"	.size		my_tramp2, .-my_tramp2\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_RISCV */
+
 #ifdef CONFIG_X86_64
 
 #include <asm/ibt.h>
diff --git a/samples/ftrace/ftrace-direct-multi.c b/samples/ftrace/ftrace-direct-multi.c
index 9243dbfe4d0c..aed6df2927ce 100644
--- a/samples/ftrace/ftrace-direct-multi.c
+++ b/samples/ftrace/ftrace-direct-multi.c
@@ -17,6 +17,31 @@ void my_direct_func(unsigned long ip)
 
 extern void my_tramp(void *);
 
+#ifdef CONFIG_RISCV
+#include <asm/asm.h>
+
+asm (
+"       .pushsection    .text, \"ax\", @progbits\n"
+"       .type           my_tramp, @function\n"
+"       .globl          my_tramp\n"
+"   my_tramp:\n"
+"       addi	sp,sp,-3*"SZREG"\n"
+"       "REG_S"	a0,0*"SZREG"(sp)\n"
+"       "REG_S"	t0,1*"SZREG"(sp)\n"
+"       "REG_S"	ra,2*"SZREG"(sp)\n"
+"       mv	a0,t0\n"
+"       call	my_direct_func\n"
+"       "REG_L"	a0,0*"SZREG"(sp)\n"
+"       "REG_L"	t0,1*"SZREG"(sp)\n"
+"       "REG_L"	ra,2*"SZREG"(sp)\n"
+"       addi	sp,sp,3*"SZREG"\n"
+"       jr	t0\n"
+"       .size           my_tramp, .-my_tramp\n"
+"       .popsection\n"
+);
+
+#endif /* CONFIG_RISCV */
+
 #ifdef CONFIG_X86_64
 
 #include <asm/ibt.h>
diff --git a/samples/ftrace/ftrace-direct-too.c b/samples/ftrace/ftrace-direct-too.c
index e39c3563ae4e..6ff546a5d7eb 100644
--- a/samples/ftrace/ftrace-direct-too.c
+++ b/samples/ftrace/ftrace-direct-too.c
@@ -19,6 +19,34 @@ void my_direct_func(struct vm_area_struct *vma, unsigned long address,
 
 extern void my_tramp(void *);
 
+#ifdef CONFIG_RISCV
+#include <asm/asm.h>
+
+asm (
+"       .pushsection    .text, \"ax\", @progbits\n"
+"       .type           my_tramp, @function\n"
+"       .globl          my_tramp\n"
+"   my_tramp:\n"
+"       addi	sp,sp,-5*"SZREG"\n"
+"       "REG_S"	a0,0*"SZREG"(sp)\n"
+"       "REG_S"	a1,1*"SZREG"(sp)\n"
+"       "REG_S"	a2,2*"SZREG"(sp)\n"
+"       "REG_S"	t0,3*"SZREG"(sp)\n"
+"       "REG_S"	ra,4*"SZREG"(sp)\n"
+"       call	my_direct_func\n"
+"       "REG_L"	a0,0*"SZREG"(sp)\n"
+"       "REG_L"	a1,1*"SZREG"(sp)\n"
+"       "REG_L"	a2,2*"SZREG"(sp)\n"
+"       "REG_L"	t0,3*"SZREG"(sp)\n"
+"       "REG_L"	ra,4*"SZREG"(sp)\n"
+"       addi	sp,sp,5*"SZREG"\n"
+"       jr	t0\n"
+"       .size           my_tramp, .-my_tramp\n"
+"       .popsection\n"
+);
+
+#endif /* CONFIG_RISCV */
+
 #ifdef CONFIG_X86_64
 
 #include <asm/ibt.h>
diff --git a/samples/ftrace/ftrace-direct.c b/samples/ftrace/ftrace-direct.c
index 32c477da1e9a..ef0945670e1e 100644
--- a/samples/ftrace/ftrace-direct.c
+++ b/samples/ftrace/ftrace-direct.c
@@ -16,6 +16,30 @@ void my_direct_func(struct task_struct *p)
 
 extern void my_tramp(void *);
 
+#ifdef CONFIG_RISCV
+#include <asm/asm.h>
+
+asm (
+"       .pushsection    .text, \"ax\", @progbits\n"
+"       .type           my_tramp, @function\n"
+"       .globl          my_tramp\n"
+"   my_tramp:\n"
+"       addi	sp,sp,-3*"SZREG"\n"
+"       "REG_S"	a0,0*"SZREG"(sp)\n"
+"       "REG_S"	t0,1*"SZREG"(sp)\n"
+"       "REG_S"	ra,2*"SZREG"(sp)\n"
+"       call	my_direct_func\n"
+"       "REG_L"	a0,0*"SZREG"(sp)\n"
+"       "REG_L"	t0,1*"SZREG"(sp)\n"
+"       "REG_L"	ra,2*"SZREG"(sp)\n"
+"       addi	sp,sp,3*"SZREG"\n"
+"       jr	t0\n"
+"       .size           my_tramp, .-my_tramp\n"
+"       .popsection\n"
+);
+
+#endif /* CONFIG_RISCV */
+
 #ifdef CONFIG_X86_64
 
 #include <asm/ibt.h>
diff --git a/samples/ftrace/sample-trace-array.c b/samples/ftrace/sample-trace-array.c
index 6aba02a31c96..d0ee9001c7b3 100644
--- a/samples/ftrace/sample-trace-array.c
+++ b/samples/ftrace/sample-trace-array.c
@@ -105,7 +105,7 @@ static int __init sample_trace_array_init(void)
 	 * NOTE: This function increments the reference counter
 	 * associated with the trace array - "tr".
 	 */
-	tr = trace_array_get_by_name("sample-instance");
+	tr = trace_array_get_by_name("sample-instance", "sched,timer,kprobes");
 
 	if (!tr)
 		return -1;
diff --git a/scripts/Kconfig.include b/scripts/Kconfig.include
index 5a84b6443875..3ee8ecfb8c04 100644
--- a/scripts/Kconfig.include
+++ b/scripts/Kconfig.include
@@ -33,7 +33,7 @@ ld-option = $(success,$(LD) -v $(1))
 
 # $(as-instr,<instr>)
 # Return y if the assembler supports <instr>, n otherwise
-as-instr = $(success,printf "%b\n" "$(1)" | $(CC) $(CLANG_FLAGS) -c -x assembler-with-cpp -o /dev/null -)
+as-instr = $(success,printf "%b\n" "$(1)" | $(CC) $(CLANG_FLAGS) -Wa$(comma)--fatal-warnings -c -x assembler-with-cpp -o /dev/null -)
 
 # check if $(CC) and $(LD) exist
 $(error-if,$(failure,command -v $(CC)),C compiler '$(CC)' not found)
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index dae447a1ad30..0fb7a785594c 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -290,7 +290,7 @@ quiet_cmd_rustc_o_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@
       cmd_rustc_o_rs = $(rust_common_cmd) --emit=obj=$@ $<
 
 $(obj)/%.o: $(src)/%.rs FORCE
-	$(call if_changed_dep,rustc_o_rs)
+	+$(call if_changed_dep,rustc_o_rs)
 
 quiet_cmd_rustc_rsi_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@
       cmd_rustc_rsi_rs = \
@@ -298,19 +298,19 @@ quiet_cmd_rustc_rsi_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@
 	command -v $(RUSTFMT) >/dev/null && $(RUSTFMT) $@
 
 $(obj)/%.rsi: $(src)/%.rs FORCE
-	$(call if_changed_dep,rustc_rsi_rs)
+	+$(call if_changed_dep,rustc_rsi_rs)
 
 quiet_cmd_rustc_s_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@
       cmd_rustc_s_rs = $(rust_common_cmd) --emit=asm=$@ $<
 
 $(obj)/%.s: $(src)/%.rs FORCE
-	$(call if_changed_dep,rustc_s_rs)
+	+$(call if_changed_dep,rustc_s_rs)
 
 quiet_cmd_rustc_ll_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@
       cmd_rustc_ll_rs = $(rust_common_cmd) --emit=llvm-ir=$@ $<
 
 $(obj)/%.ll: $(src)/%.rs FORCE
-	$(call if_changed_dep,rustc_ll_rs)
+	+$(call if_changed_dep,rustc_ll_rs)
 
 # Compile assembler sources (.S)
 # ---------------------------------------------------------------------------
diff --git a/scripts/Makefile.compiler b/scripts/Makefile.compiler
index 8fcb427405a6..92be0c9a13ee 100644
--- a/scripts/Makefile.compiler
+++ b/scripts/Makefile.compiler
@@ -38,7 +38,7 @@ as-option = $(call try-run,\
 # Usage: aflags-y += $(call as-instr,instr,option1,option2)
 
 as-instr = $(call try-run,\
-	printf "%b\n" "$(1)" | $(CC) -Werror $(CLANG_FLAGS) $(KBUILD_AFLAGS) -c -x assembler-with-cpp -o "$$TMP" -,$(2),$(3))
+	printf "%b\n" "$(1)" | $(CC) -Werror $(CLANG_FLAGS) $(KBUILD_AFLAGS) -Wa$(comma)--fatal-warnings -c -x assembler-with-cpp -o "$$TMP" -,$(2),$(3))
 
 # __cc-option
 # Usage: MY_CFLAGS += $(call __cc-option,$(CC),$(MY_CFLAGS),-march=winchip-c6,-march=i586)
diff --git a/scripts/Makefile.defconf b/scripts/Makefile.defconf
index ab271b2051a2..226ea3df3b4b 100644
--- a/scripts/Makefile.defconf
+++ b/scripts/Makefile.defconf
@@ -9,8 +9,8 @@
 # Input config fragments without '.config' suffix
 define merge_into_defconfig
 	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \
-		-m -O $(objtree) $(srctree)/arch/$(ARCH)/configs/$(1) \
-		$(foreach config,$(2),$(srctree)/arch/$(ARCH)/configs/$(config).config)
+		-m -O $(objtree) $(srctree)/arch/$(SRCARCH)/configs/$(1) \
+		$(foreach config,$(2),$(srctree)/arch/$(SRCARCH)/configs/$(config).config)
 	+$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig
 endef
 
@@ -23,7 +23,7 @@ endef
 # Input config fragments without '.config' suffix
 define merge_into_defconfig_override
 	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \
-		-Q -m -O $(objtree) $(srctree)/arch/$(ARCH)/configs/$(1) \
-		$(foreach config,$(2),$(srctree)/arch/$(ARCH)/configs/$(config).config)
+		-Q -m -O $(objtree) $(srctree)/arch/$(SRCARCH)/configs/$(1) \
+		$(foreach config,$(2),$(srctree)/arch/$(SRCARCH)/configs/$(config).config)
 	+$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig
 endef
diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn
index c9725685aa76..a9e552a1e910 100644
--- a/scripts/Makefile.extrawarn
+++ b/scripts/Makefile.extrawarn
@@ -82,15 +82,6 @@ KBUILD_CFLAGS += $(call cc-option,-Werror=designated-init)
 # Warn if there is an enum types mismatch
 KBUILD_CFLAGS += $(call cc-option,-Wenum-conversion)
 
-# backward compatibility
-KBUILD_EXTRA_WARN ?= $(KBUILD_ENABLE_EXTRA_GCC_CHECKS)
-
-ifeq ("$(origin W)", "command line")
-  KBUILD_EXTRA_WARN := $(W)
-endif
-
-export KBUILD_EXTRA_WARN
-
 #
 # W=1 - warnings which may be relevant and do not occur too often
 #
@@ -106,7 +97,6 @@ KBUILD_CFLAGS += $(call cc-option, -Wunused-const-variable)
 KBUILD_CFLAGS += $(call cc-option, -Wpacked-not-aligned)
 KBUILD_CFLAGS += $(call cc-option, -Wformat-overflow)
 KBUILD_CFLAGS += $(call cc-option, -Wformat-truncation)
-KBUILD_CFLAGS += $(call cc-option, -Wstringop-overflow)
 KBUILD_CFLAGS += $(call cc-option, -Wstringop-truncation)
 
 KBUILD_CPPFLAGS += -Wundef
@@ -122,7 +112,6 @@ KBUILD_CFLAGS += $(call cc-disable-warning, restrict)
 KBUILD_CFLAGS += $(call cc-disable-warning, packed-not-aligned)
 KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow)
 KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation)
-KBUILD_CFLAGS += $(call cc-disable-warning, stringop-overflow)
 KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation)
 
 ifdef CONFIG_CC_IS_CLANG
diff --git a/scripts/Makefile.host b/scripts/Makefile.host
index 08d83d9db31a..3c17e6ba421c 100644
--- a/scripts/Makefile.host
+++ b/scripts/Makefile.host
@@ -156,7 +156,7 @@ quiet_cmd_host-rust	= HOSTRUSTC $@
       cmd_host-rust	= \
 	$(HOSTRUSTC) $(hostrust_flags) --emit=link=$@ $<
 $(host-rust): $(obj)/%: $(src)/%.rs FORCE
-	$(call if_changed_dep,host-rust)
+	+$(call if_changed_dep,host-rust)
 
 targets += $(host-csingle) $(host-cmulti) $(host-cobjs) \
 	   $(host-cxxmulti) $(host-cxxobjs) $(host-rust)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 1a965fe68e01..cd5b181060f1 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -83,8 +83,8 @@ dtb-$(CONFIG_OF_ALL_DTBS)       += $(dtb-)
 multi-dtb-y := $(call multi-search, $(dtb-y), .dtb, -dtbs)
 # Primitive DTB compiled from *.dts
 real-dtb-y := $(call real-search, $(dtb-y), .dtb, -dtbs)
-# Base DTB that overlay is applied onto (each first word of $(*-dtbs) expansion)
-base-dtb-y := $(foreach m, $(multi-dtb-y), $(firstword $(call suffix-search, $m, .dtb, -dtbs)))
+# Base DTB that overlay is applied onto
+base-dtb-y := $(filter %.dtb, $(call real-search, $(multi-dtb-y), .dtb, -dtbs))
 
 always-y			+= $(dtb-y)
 
diff --git a/scripts/Makefile.package b/scripts/Makefile.package
index 3addd1c0b989..a81dfb1f5181 100644
--- a/scripts/Makefile.package
+++ b/scripts/Makefile.package
@@ -4,27 +4,6 @@
 include $(srctree)/scripts/Kbuild.include
 include $(srctree)/scripts/Makefile.lib
 
-KERNELPATH := kernel-$(subst -,_,$(KERNELRELEASE))
-# Include only those top-level files that are needed by make, plus the GPL copy
-TAR_CONTENT := Documentation LICENSES arch block certs crypto drivers fs \
-               include init io_uring ipc kernel lib mm net rust \
-               samples scripts security sound tools usr virt \
-               .config Makefile \
-               Kbuild Kconfig COPYING $(wildcard localversion*)
-
-quiet_cmd_src_tar = TAR     $(2).tar.gz
-      cmd_src_tar = \
-if test "$(objtree)" != "$(srctree)"; then \
-	echo >&2; \
-	echo >&2 "  ERROR:"; \
-	echo >&2 "  Building source tarball is not possible outside the"; \
-	echo >&2 "  kernel source tree. Don't set KBUILD_OUTPUT"; \
-	echo >&2; \
-	false; \
-fi ; \
-tar -I $(KGZIP) -c $(RCS_TAR_IGNORE) -f $(2).tar.gz \
-	--transform 's:^:$(2)/:S' $(TAR_CONTENT) $(3)
-
 # Git
 # ---------------------------------------------------------------------------
 
@@ -130,8 +109,6 @@ debian-orig: linux.tar$(debian-orig-suffix) debian
 		cp $< ../$(orig-name); \
 	fi
 
-KBUILD_PKG_ROOTCMD ?= 'fakeroot -u'
-
 PHONY += deb-pkg srcdeb-pkg bindeb-pkg
 
 deb-pkg:    private build-type := source,binary
@@ -146,7 +123,7 @@ deb-pkg srcdeb-pkg bindeb-pkg:
 	$(if $(findstring source, $(build-type)), \
 		--unsigned-source --compression=$(KDEB_SOURCE_COMPRESS)) \
 	$(if $(findstring binary, $(build-type)), \
-		--rules-file='$(MAKE) -f debian/rules' --jobs=1 -r$(KBUILD_PKG_ROOTCMD) -a$$(cat debian/arch), \
+		-R'$(MAKE) -f debian/rules' -j1 -a$$(cat debian/arch), \
 		--no-check-builddeps) \
 	$(DPKG_FLAGS))
 
@@ -157,9 +134,8 @@ snap-pkg:
 	rm -rf $(objtree)/snap
 	mkdir $(objtree)/snap
 	$(MAKE) clean
-	$(call cmd,src_tar,$(KERNELPATH))
 	sed "s@KERNELRELEASE@$(KERNELRELEASE)@; \
-		s@SRCTREE@$(shell realpath $(KERNELPATH).tar.gz)@" \
+		s@SRCTREE@$(abs_srctree)@" \
 		$(srctree)/scripts/package/snapcraft.template > \
 		$(objtree)/snap/snapcraft.yaml
 	cd $(objtree)/snap && \
diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py
index 61b7dddedc46..0669bac5e900 100755
--- a/scripts/bpf_doc.py
+++ b/scripts/bpf_doc.py
@@ -513,7 +513,7 @@ eBPF programs can have an associated license, passed along with the bytecode
 instructions to the kernel when the programs are loaded. The format for that
 string is identical to the one in use for kernel modules (Dual licenses, such
 as "Dual BSD/GPL", may be used). Some helper functions are only accessible to
-programs that are compatible with the GNU Privacy License (GPL).
+programs that are compatible with the GNU General Public License (GNU GPL).
 
 In order to use such helpers, the eBPF program must be loaded with the correct
 license string passed (via **attr**) to the **bpf**\\ () system call, and this
diff --git a/scripts/check-uapi.sh b/scripts/check-uapi.sh
new file mode 100755
index 000000000000..955581735cb3
--- /dev/null
+++ b/scripts/check-uapi.sh
@@ -0,0 +1,573 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+# Script to check commits for UAPI backwards compatibility
+
+set -o errexit
+set -o pipefail
+
+print_usage() {
+	name=$(basename "$0")
+	cat << EOF
+$name - check for UAPI header stability across Git commits
+
+By default, the script will check to make sure the latest commit (or current
+dirty changes) did not introduce ABI changes when compared to HEAD^1. You can
+check against additional commit ranges with the -b and -p options.
+
+The script will not check UAPI headers for architectures other than the one
+defined in ARCH.
+
+Usage: $name [-b BASE_REF] [-p PAST_REF] [-j N] [-l ERROR_LOG] [-i] [-q] [-v]
+
+Options:
+    -b BASE_REF    Base git reference to use for comparison. If unspecified or empty,
+                   will use any dirty changes in tree to UAPI files. If there are no
+                   dirty changes, HEAD will be used.
+    -p PAST_REF    Compare BASE_REF to PAST_REF (e.g. -p v6.1). If unspecified or empty,
+                   will use BASE_REF^1. Must be an ancestor of BASE_REF. Only headers
+                   that exist on PAST_REF will be checked for compatibility.
+    -j JOBS        Number of checks to run in parallel (default: number of CPU cores).
+    -l ERROR_LOG   Write error log to file (default: no error log is generated).
+    -i             Ignore ambiguous changes that may or may not break UAPI compatibility.
+    -q             Quiet operation.
+    -v             Verbose operation (print more information about each header being checked).
+
+Environmental args:
+    ABIDIFF  Custom path to abidiff binary
+    CC       C compiler (default is "gcc")
+    ARCH     Target architecture for the UAPI check (default is host arch)
+
+Exit codes:
+    $SUCCESS) Success
+    $FAIL_ABI) ABI difference detected
+    $FAIL_PREREQ) Prerequisite not met
+EOF
+}
+
+readonly SUCCESS=0
+readonly FAIL_ABI=1
+readonly FAIL_PREREQ=2
+
+# Print to stderr
+eprintf() {
+	# shellcheck disable=SC2059
+	printf "$@" >&2
+}
+
+# Expand an array with a specific character (similar to Python string.join())
+join() {
+	local IFS="$1"
+	shift
+	printf "%s" "$*"
+}
+
+# Create abidiff suppressions
+gen_suppressions() {
+	# Common enum variant names which we don't want to worry about
+	# being shifted when new variants are added.
+	local -a enum_regex=(
+		".*_AFTER_LAST$"
+		".*_CNT$"
+		".*_COUNT$"
+		".*_END$"
+		".*_LAST$"
+		".*_MASK$"
+		".*_MAX$"
+		".*_MAX_BIT$"
+		".*_MAX_BPF_ATTACH_TYPE$"
+		".*_MAX_ID$"
+		".*_MAX_SHIFT$"
+		".*_NBITS$"
+		".*_NETDEV_NUMHOOKS$"
+		".*_NFT_META_IIFTYPE$"
+		".*_NL80211_ATTR$"
+		".*_NLDEV_NUM_OPS$"
+		".*_NUM$"
+		".*_NUM_ELEMS$"
+		".*_NUM_IRQS$"
+		".*_SIZE$"
+		".*_TLSMAX$"
+		"^MAX_.*"
+		"^NUM_.*"
+	)
+
+	# Common padding field names which can be expanded into
+	# without worrying about users.
+	local -a padding_regex=(
+		".*end$"
+		".*pad$"
+		".*pad[0-9]?$"
+		".*pad_[0-9]?$"
+		".*padding$"
+		".*padding[0-9]?$"
+		".*padding_[0-9]?$"
+		".*res$"
+		".*resv$"
+		".*resv[0-9]?$"
+		".*resv_[0-9]?$"
+		".*reserved$"
+		".*reserved[0-9]?$"
+		".*reserved_[0-9]?$"
+		".*rsvd[0-9]?$"
+		".*unused$"
+	)
+
+	cat << EOF
+[suppress_type]
+  type_kind = enum
+  changed_enumerators_regexp = $(join , "${enum_regex[@]}")
+EOF
+
+	for p in "${padding_regex[@]}"; do
+		cat << EOF
+[suppress_type]
+  type_kind = struct
+  has_data_member_inserted_at = offset_of_first_data_member_regexp(${p})
+EOF
+	done
+
+if [ "$IGNORE_AMBIGUOUS_CHANGES" = "true" ]; then
+	cat << EOF
+[suppress_type]
+  type_kind = struct
+  has_data_member_inserted_at = end
+  has_size_change = yes
+EOF
+fi
+}
+
+# Check if git tree is dirty
+tree_is_dirty() {
+	! git diff --quiet
+}
+
+# Get list of files installed in $ref
+get_file_list() {
+	local -r ref="$1"
+	local -r tree="$(get_header_tree "$ref")"
+
+	# Print all installed headers, filtering out ones that can't be compiled
+	find "$tree" -type f -name '*.h' -printf '%P\n' | grep -v -f "$INCOMPAT_LIST"
+}
+
+# Add to the list of incompatible headers
+add_to_incompat_list() {
+	local -r ref="$1"
+
+	# Start with the usr/include/Makefile to get a list of the headers
+	# that don't compile using this method.
+	if [ ! -f usr/include/Makefile ]; then
+		eprintf "error - no usr/include/Makefile present at %s\n" "$ref"
+		eprintf "Note: usr/include/Makefile was added in the v5.3 kernel release\n"
+		exit "$FAIL_PREREQ"
+	fi
+	{
+		# shellcheck disable=SC2016
+		printf 'all: ; @echo $(no-header-test)\n'
+		cat usr/include/Makefile
+	} | SRCARCH="$ARCH" make --always-make -f - | tr " " "\n" \
+	  | grep -v "asm-generic" >> "$INCOMPAT_LIST"
+
+	# The makefile also skips all asm-generic files, but prints "asm-generic/%"
+	# which won't work for our grep match. Instead, print something grep will match.
+	printf "asm-generic/.*\.h\n" >> "$INCOMPAT_LIST"
+}
+
+# Compile the simple test app
+do_compile() {
+	local -r inc_dir="$1"
+	local -r header="$2"
+	local -r out="$3"
+	printf "int main(void) { return 0; }\n" | \
+		"$CC" -c \
+		  -o "$out" \
+		  -x c \
+		  -O0 \
+		  -std=c90 \
+		  -fno-eliminate-unused-debug-types \
+		  -g \
+		  "-I${inc_dir}" \
+		  -include "$header" \
+		  -
+}
+
+# Run make headers_install
+run_make_headers_install() {
+	local -r ref="$1"
+	local -r install_dir="$(get_header_tree "$ref")"
+	make -j "$MAX_THREADS" ARCH="$ARCH" INSTALL_HDR_PATH="$install_dir" \
+		headers_install > /dev/null
+}
+
+# Install headers for both git refs
+install_headers() {
+	local -r base_ref="$1"
+	local -r past_ref="$2"
+
+	for ref in "$base_ref" "$past_ref"; do
+		printf "Installing user-facing UAPI headers from %s... " "${ref:-dirty tree}"
+		if [ -n "$ref" ]; then
+			git archive --format=tar --prefix="${ref}-archive/" "$ref" \
+				| (cd "$TMP_DIR" && tar xf -)
+			(
+				cd "${TMP_DIR}/${ref}-archive"
+				run_make_headers_install "$ref"
+				add_to_incompat_list "$ref" "$INCOMPAT_LIST"
+			)
+		else
+			run_make_headers_install "$ref"
+			add_to_incompat_list "$ref" "$INCOMPAT_LIST"
+		fi
+		printf "OK\n"
+	done
+	sort -u -o "$INCOMPAT_LIST" "$INCOMPAT_LIST"
+	sed -i -e '/^$/d' "$INCOMPAT_LIST"
+}
+
+# Print the path to the headers_install tree for a given ref
+get_header_tree() {
+	local -r ref="$1"
+	printf "%s" "${TMP_DIR}/${ref}/usr"
+}
+
+# Check file list for UAPI compatibility
+check_uapi_files() {
+	local -r base_ref="$1"
+	local -r past_ref="$2"
+	local -r abi_error_log="$3"
+
+	local passed=0;
+	local failed=0;
+	local -a threads=()
+	set -o errexit
+
+	printf "Checking changes to UAPI headers between %s and %s...\n" "$past_ref" "${base_ref:-dirty tree}"
+	# Loop over all UAPI headers that were installed by $past_ref (if they only exist on $base_ref,
+	# there's no way they're broken and no way to compare anyway)
+	while read -r file; do
+		if [ "${#threads[@]}" -ge "$MAX_THREADS" ]; then
+			if wait "${threads[0]}"; then
+				passed=$((passed + 1))
+			else
+				failed=$((failed + 1))
+			fi
+			threads=("${threads[@]:1}")
+		fi
+
+		check_individual_file "$base_ref" "$past_ref" "$file" &
+		threads+=("$!")
+	done < <(get_file_list "$past_ref")
+
+	for t in "${threads[@]}"; do
+		if wait "$t"; then
+			passed=$((passed + 1))
+		else
+			failed=$((failed + 1))
+		fi
+	done
+
+	if [ -n "$abi_error_log" ]; then
+		printf 'Generated by "%s %s" from git ref %s\n\n' \
+			"$0" "$*" "$(git rev-parse HEAD)" > "$abi_error_log"
+	fi
+
+	while read -r error_file; do
+		{
+			cat "$error_file"
+			printf "\n\n"
+		} | tee -a "${abi_error_log:-/dev/null}" >&2
+	done < <(find "$TMP_DIR" -type f -name '*.error' | sort)
+
+	total="$((passed + failed))"
+	if [ "$failed" -gt 0 ]; then
+		eprintf "error - %d/%d UAPI headers compatible with %s appear _not_ to be backwards compatible\n" \
+			"$failed" "$total" "$ARCH"
+		if [ -n "$abi_error_log" ]; then
+			eprintf "Failure summary saved to %s\n" "$abi_error_log"
+		fi
+	else
+		printf "All %d UAPI headers compatible with %s appear to be backwards compatible\n" \
+			"$total" "$ARCH"
+	fi
+
+	return "$failed"
+}
+
+# Check an individual file for UAPI compatibility
+check_individual_file() {
+	local -r base_ref="$1"
+	local -r past_ref="$2"
+	local -r file="$3"
+
+	local -r base_header="$(get_header_tree "$base_ref")/${file}"
+	local -r past_header="$(get_header_tree "$past_ref")/${file}"
+
+	if [ ! -f "$base_header" ]; then
+		mkdir -p "$(dirname "$base_header")"
+		printf "==== UAPI header %s was removed between %s and %s ====" \
+			"$file" "$past_ref" "$base_ref" \
+				> "${base_header}.error"
+		return 1
+	fi
+
+	compare_abi "$file" "$base_header" "$past_header" "$base_ref" "$past_ref"
+}
+
+# Perform the A/B compilation and compare output ABI
+compare_abi() {
+	local -r file="$1"
+	local -r base_header="$2"
+	local -r past_header="$3"
+	local -r base_ref="$4"
+	local -r past_ref="$5"
+	local -r log="${TMP_DIR}/log/${file}.log"
+	local -r error_log="${TMP_DIR}/log/${file}.error"
+
+	mkdir -p "$(dirname "$log")"
+
+	if ! do_compile "$(get_header_tree "$base_ref")/include" "$base_header" "${base_header}.bin" 2> "$log"; then
+		{
+			warn_str=$(printf "==== Could not compile version of UAPI header %s at %s ====\n" \
+				"$file" "$base_ref")
+			printf "%s\n" "$warn_str"
+			cat "$log"
+			printf -- "=%.0s" $(seq 0 ${#warn_str})
+		} > "$error_log"
+		return 1
+	fi
+
+	if ! do_compile "$(get_header_tree "$past_ref")/include" "$past_header" "${past_header}.bin" 2> "$log"; then
+		{
+			warn_str=$(printf "==== Could not compile version of UAPI header %s at %s ====\n" \
+				"$file" "$past_ref")
+			printf "%s\n" "$warn_str"
+			cat "$log"
+			printf -- "=%.0s" $(seq 0 ${#warn_str})
+		} > "$error_log"
+		return 1
+	fi
+
+	local ret=0
+	"$ABIDIFF" --non-reachable-types \
+		--suppressions "$SUPPRESSIONS" \
+		"${past_header}.bin" "${base_header}.bin" > "$log" || ret="$?"
+	if [ "$ret" -eq 0 ]; then
+		if [ "$VERBOSE" = "true" ]; then
+			printf "No ABI differences detected in %s from %s -> %s\n" \
+				"$file" "$past_ref" "$base_ref"
+		fi
+	else
+		# Bits in abidiff's return code can be used to determine the type of error
+		if [ $((ret & 0x2)) -gt 0 ]; then
+			eprintf "error - abidiff did not run properly\n"
+			exit 1
+		fi
+
+		if [ "$IGNORE_AMBIGUOUS_CHANGES" = "true" ] && [ "$ret" -eq 4 ]; then
+			return 0
+		fi
+
+		# If the only changes were additions (not modifications to existing APIs), then
+		# there's no problem. Ignore these diffs.
+		if grep "Unreachable types summary" "$log" | grep -q "0 removed" &&
+		   grep "Unreachable types summary" "$log" | grep -q "0 changed"; then
+			return 0
+		fi
+
+		{
+			warn_str=$(printf "==== ABI differences detected in %s from %s -> %s ====" \
+				"$file" "$past_ref" "$base_ref")
+			printf "%s\n" "$warn_str"
+			sed  -e '/summary:/d' -e '/changed type/d' -e '/^$/d' -e 's/^/  /g' "$log"
+			printf -- "=%.0s" $(seq 0 ${#warn_str})
+			if cmp "$past_header" "$base_header" > /dev/null 2>&1; then
+				printf "\n%s did not change between %s and %s...\n" "$file" "$past_ref" "${base_ref:-dirty tree}"
+				printf "It's possible a change to one of the headers it includes caused this error:\n"
+				grep '^#include' "$base_header"
+				printf "\n"
+			fi
+		} > "$error_log"
+
+		return 1
+	fi
+}
+
+# Check that a minimum software version number is satisfied
+min_version_is_satisfied() {
+	local -r min_version="$1"
+	local -r version_installed="$2"
+
+	printf "%s\n%s\n" "$min_version" "$version_installed" \
+		| sort -Vc > /dev/null 2>&1
+}
+
+# Make sure we have the tools we need and the arguments make sense
+check_deps() {
+	ABIDIFF="${ABIDIFF:-abidiff}"
+	CC="${CC:-gcc}"
+	ARCH="${ARCH:-$(uname -m)}"
+	if [ "$ARCH" = "x86_64" ]; then
+		ARCH="x86"
+	fi
+
+	local -r abidiff_min_version="2.4"
+	local -r libdw_min_version_if_clang="0.171"
+
+	if ! command -v "$ABIDIFF" > /dev/null 2>&1; then
+		eprintf "error - abidiff not found!\n"
+		eprintf "Please install abigail-tools version %s or greater\n" "$abidiff_min_version"
+		eprintf "See: https://sourceware.org/libabigail/manual/libabigail-overview.html\n"
+		return 1
+	fi
+
+	local -r abidiff_version="$("$ABIDIFF" --version | cut -d ' ' -f 2)"
+	if ! min_version_is_satisfied "$abidiff_min_version" "$abidiff_version"; then
+		eprintf "error - abidiff version too old: %s\n" "$abidiff_version"
+		eprintf "Please install abigail-tools version %s or greater\n" "$abidiff_min_version"
+		eprintf "See: https://sourceware.org/libabigail/manual/libabigail-overview.html\n"
+		return 1
+	fi
+
+	if ! command -v "$CC" > /dev/null 2>&1; then
+		eprintf 'error - %s not found\n' "$CC"
+		return 1
+	fi
+
+	if "$CC" --version | grep -q clang; then
+		local -r libdw_version="$(ldconfig -v 2>/dev/null | grep -v SKIPPED | grep -m 1 -o 'libdw-[0-9]\+.[0-9]\+' | cut -c 7-)"
+		if ! min_version_is_satisfied "$libdw_min_version_if_clang" "$libdw_version"; then
+			eprintf "error - libdw version too old for use with clang: %s\n" "$libdw_version"
+			eprintf "Please install libdw from elfutils version %s or greater\n" "$libdw_min_version_if_clang"
+			eprintf "See: https://sourceware.org/elfutils/\n"
+			return 1
+		fi
+	fi
+
+	if [ ! -d "arch/${ARCH}" ]; then
+		eprintf 'error - ARCH "%s" is not a subdirectory under arch/\n' "$ARCH"
+		eprintf "Please set ARCH to one of:\n%s\n" "$(find arch -maxdepth 1 -mindepth 1 -type d -printf '%f ' | fmt)"
+		return 1
+	fi
+
+	if ! git rev-parse --is-inside-work-tree > /dev/null 2>&1; then
+		eprintf "error - this script requires the kernel tree to be initialized with Git\n"
+		return 1
+	fi
+
+	if ! git rev-parse --verify "$past_ref" > /dev/null 2>&1; then
+		printf 'error - invalid git reference "%s"\n' "$past_ref"
+		return 1
+	fi
+
+	if [ -n "$base_ref" ]; then
+		if ! git merge-base --is-ancestor "$past_ref" "$base_ref" > /dev/null 2>&1; then
+			printf 'error - "%s" is not an ancestor of base ref "%s"\n' "$past_ref" "$base_ref"
+			return 1
+		fi
+		if [ "$(git rev-parse "$base_ref")" = "$(git rev-parse "$past_ref")" ]; then
+			printf 'error - "%s" and "%s" are the same reference\n' "$past_ref" "$base_ref"
+			return 1
+		fi
+	fi
+}
+
+run() {
+	local base_ref="$1"
+	local past_ref="$2"
+	local abi_error_log="$3"
+	shift 3
+
+	if [ -z "$KERNEL_SRC" ]; then
+		KERNEL_SRC="$(realpath "$(dirname "$0")"/..)"
+	fi
+
+	cd "$KERNEL_SRC"
+
+	if [ -z "$base_ref" ] && ! tree_is_dirty; then
+		base_ref=HEAD
+	fi
+
+	if [ -z "$past_ref" ]; then
+		if [ -n "$base_ref" ]; then
+			past_ref="${base_ref}^1"
+		else
+			past_ref=HEAD
+		fi
+	fi
+
+	if ! check_deps; then
+		exit "$FAIL_PREREQ"
+	fi
+
+	TMP_DIR=$(mktemp -d)
+	readonly TMP_DIR
+	trap 'rm -rf "$TMP_DIR"' EXIT
+
+	readonly INCOMPAT_LIST="${TMP_DIR}/incompat_list.txt"
+	touch "$INCOMPAT_LIST"
+
+	readonly SUPPRESSIONS="${TMP_DIR}/suppressions.txt"
+	gen_suppressions > "$SUPPRESSIONS"
+
+	# Run make install_headers for both refs
+	install_headers "$base_ref" "$past_ref"
+
+	# Check for any differences in the installed header trees
+	if diff -r -q "$(get_header_tree "$base_ref")" "$(get_header_tree "$past_ref")" > /dev/null 2>&1; then
+		printf "No changes to UAPI headers were applied between %s and %s\n" "$past_ref" "${base_ref:-dirty tree}"
+		exit "$SUCCESS"
+	fi
+
+	if ! check_uapi_files "$base_ref" "$past_ref" "$abi_error_log"; then
+		exit "$FAIL_ABI"
+	fi
+}
+
+main() {
+	MAX_THREADS=$(nproc)
+	VERBOSE="false"
+	IGNORE_AMBIGUOUS_CHANGES="false"
+	quiet="false"
+	local base_ref=""
+	while getopts "hb:p:j:l:iqv" opt; do
+		case $opt in
+		h)
+			print_usage
+			exit "$SUCCESS"
+			;;
+		b)
+			base_ref="$OPTARG"
+			;;
+		p)
+			past_ref="$OPTARG"
+			;;
+		j)
+			MAX_THREADS="$OPTARG"
+			;;
+		l)
+			abi_error_log="$OPTARG"
+			;;
+		i)
+			IGNORE_AMBIGUOUS_CHANGES="true"
+			;;
+		q)
+			quiet="true"
+			VERBOSE="false"
+			;;
+		v)
+			VERBOSE="true"
+			quiet="false"
+			;;
+		*)
+			exit "$FAIL_PREREQ"
+		esac
+	done
+
+	if [ "$quiet" = "true" ]; then
+		exec > /dev/null 2>&1
+	fi
+
+	run "$base_ref" "$past_ref" "$abi_error_log" "$@"
+}
+
+main "$@"
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index f8343b34a28b..9c4c4a61bc83 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -512,6 +512,7 @@ our $Attribute	= qr{
 			__ro_after_init|
 			__kprobes|
 			$InitAttribute|
+			__aligned\s*\(.*\)|
 			____cacheline_aligned|
 			____cacheline_aligned_in_smp|
 			____cacheline_internodealigned_in_smp|
diff --git a/scripts/clang-tools/gen_compile_commands.py b/scripts/clang-tools/gen_compile_commands.py
index 5dea4479240b..e4fb686dfaa9 100755
--- a/scripts/clang-tools/gen_compile_commands.py
+++ b/scripts/clang-tools/gen_compile_commands.py
@@ -170,7 +170,7 @@ def process_line(root_directory, command_prefix, file_path):
     # escape the pound sign '#', either as '\#' or '$(pound)' (depending on the
     # kernel version). The compile_commands.json file is not interepreted
     # by Make, so this code replaces the escaped version with '#'.
-    prefix = command_prefix.replace('\#', '#').replace('$(pound)', '#')
+    prefix = command_prefix.replace(r'\#', '#').replace('$(pound)', '#')
 
     # Return the canonical path, eliminating any symbolic links encountered in the path.
     abs_path = os.path.realpath(os.path.join(root_directory, file_path))
diff --git a/scripts/coccinelle/api/device_attr_show.cocci b/scripts/coccinelle/api/device_attr_show.cocci
index a28dc061653a..550d1d2fc02a 100644
--- a/scripts/coccinelle/api/device_attr_show.cocci
+++ b/scripts/coccinelle/api/device_attr_show.cocci
@@ -1,10 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0-only
 ///
 /// From Documentation/filesystems/sysfs.rst:
-///  show() must not use snprintf() when formatting the value to be
-///  returned to user space. If you can guarantee that an overflow
-///  will never happen you can use sprintf() otherwise you must use
-///  scnprintf().
+///  show() should only use sysfs_emit() or sysfs_emit_at() when formatting
+///  the value to be returned to user space.
 ///
 // Confidence: High
 // Copyright: (C) 2020 Denis Efremov ISPRAS
@@ -30,15 +28,16 @@ ssize_t show(struct device *dev, struct device_attribute *attr, char *buf)
 
 @rp depends on patch@
 identifier show, dev, attr, buf;
+expression BUF, SZ, FORMAT, STR;
 @@
 
 ssize_t show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	<...
 	return
--		snprintf
-+		scnprintf
-			(...);
+-		snprintf(BUF, SZ, FORMAT
++		sysfs_emit(BUF, FORMAT
+				,...);
 	...>
 }
 
@@ -46,10 +45,10 @@ ssize_t show(struct device *dev, struct device_attribute *attr, char *buf)
 p << r.p;
 @@
 
-coccilib.report.print_report(p[0], "WARNING: use scnprintf or sprintf")
+coccilib.report.print_report(p[0], "WARNING: please use sysfs_emit or sysfs_emit_at")
 
 @script: python depends on org@
 p << r.p;
 @@
 
-coccilib.org.print_todo(p[0], "WARNING: use scnprintf or sprintf")
+coccilib.org.print_todo(p[0], "WARNING: please use sysfs_emit or sysfs_emit_at")
diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh
index cb980b144ca1..fa5be6f57b00 100755
--- a/scripts/decode_stacktrace.sh
+++ b/scripts/decode_stacktrace.sh
@@ -16,6 +16,21 @@ elif type c++filt >/dev/null 2>&1 ; then
 	cppfilt_opts=-i
 fi
 
+UTIL_SUFFIX=
+if [[ -z ${LLVM:-} ]]; then
+	UTIL_PREFIX=${CROSS_COMPILE:-}
+else
+	UTIL_PREFIX=llvm-
+	if [[ ${LLVM} == */ ]]; then
+		UTIL_PREFIX=${LLVM}${UTIL_PREFIX}
+	elif [[ ${LLVM} == -* ]]; then
+		UTIL_SUFFIX=${LLVM}
+	fi
+fi
+
+READELF=${UTIL_PREFIX}readelf${UTIL_SUFFIX}
+ADDR2LINE=${UTIL_PREFIX}addr2line${UTIL_SUFFIX}
+
 if [[ $1 == "-r" ]] ; then
 	vmlinux=""
 	basepath="auto"
@@ -75,7 +90,7 @@ find_module() {
 
 	if [[ "$modpath" != "" ]] ; then
 		for fn in $(find "$modpath" -name "${module//_/[-_]}.ko*") ; do
-			if readelf -WS "$fn" | grep -qwF .debug_line ; then
+			if ${READELF} -WS "$fn" | grep -qwF .debug_line ; then
 				echo $fn
 				return
 			fi
@@ -169,7 +184,7 @@ parse_symbol() {
 	if [[ $aarray_support == true && "${cache[$module,$address]+isset}" == "isset" ]]; then
 		local code=${cache[$module,$address]}
 	else
-		local code=$(${CROSS_COMPILE}addr2line -i -e "$objfile" "$address" 2>/dev/null)
+		local code=$(${ADDR2LINE} -i -e "$objfile" "$address" 2>/dev/null)
 		if [[ $aarray_support == true ]]; then
 			cache[$module,$address]=$code
 		fi
diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py
index c8047f4441e6..e8316beb17a7 100644
--- a/scripts/gdb/linux/symbols.py
+++ b/scripts/gdb/linux/symbols.py
@@ -82,7 +82,7 @@ lx-symbols command."""
         self.module_files_updated = True
 
     def _get_module_file(self, module_name):
-        module_pattern = ".*/{0}\.ko(?:.debug)?$".format(
+        module_pattern = r".*/{0}\.ko(?:.debug)?$".format(
             module_name.replace("_", r"[_\-]"))
         for name in self.module_files:
             if re.match(module_pattern, name) and os.path.exists(name):
diff --git a/scripts/gdb/linux/tasks.py b/scripts/gdb/linux/tasks.py
index aa5ab6251f76..6793d6e86e77 100644
--- a/scripts/gdb/linux/tasks.py
+++ b/scripts/gdb/linux/tasks.py
@@ -82,21 +82,12 @@ LxPs()
 
 thread_info_type = utils.CachedType("struct thread_info")
 
-ia64_task_size = None
-
 
 def get_thread_info(task):
     thread_info_ptr_type = thread_info_type.get_type().pointer()
-    if utils.is_target_arch("ia64"):
-        global ia64_task_size
-        if ia64_task_size is None:
-            ia64_task_size = gdb.parse_and_eval("sizeof(struct task_struct)")
-        thread_info_addr = task.address + ia64_task_size
-        thread_info = thread_info_addr.cast(thread_info_ptr_type)
-    else:
-        if task.type.fields()[0].type == thread_info_type.get_type():
-            return task['thread_info']
-        thread_info = task['stack'].cast(thread_info_ptr_type)
+    if task.type.fields()[0].type == thread_info_type.get_type():
+        return task['thread_info']
+    thread_info = task['stack'].cast(thread_info_ptr_type)
     return thread_info.dereference()
 
 
diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs
index 3c6cbe2b278d..0da52b548ba5 100644
--- a/scripts/generate_rust_target.rs
+++ b/scripts/generate_rust_target.rs
@@ -161,6 +161,13 @@ fn main() {
         ts.push("features", features);
         ts.push("llvm-target", "x86_64-linux-gnu");
         ts.push("target-pointer-width", "64");
+    } else if cfg.has("LOONGARCH") {
+        ts.push("arch", "loongarch64");
+        ts.push("data-layout", "e-m:e-p:64:64-i64:64-i128:128-n64-S128");
+        ts.push("features", "-f,-d");
+        ts.push("llvm-target", "loongarch64-linux-gnusf");
+        ts.push("llvm-abiname", "lp64s");
+        ts.push("target-pointer-width", "64");
     } else {
         panic!("Unsupported architecture");
     }
diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c
index f5dfdb9d80e9..f3901c55df23 100644
--- a/scripts/genksyms/genksyms.c
+++ b/scripts/genksyms/genksyms.c
@@ -16,9 +16,7 @@
 #include <unistd.h>
 #include <assert.h>
 #include <stdarg.h>
-#ifdef __GNU_LIBRARY__
 #include <getopt.h>
-#endif				/* __GNU_LIBRARY__ */
 
 #include "genksyms.h"
 /*----------------------------------------------------------------------*/
@@ -718,8 +716,6 @@ void error_with_pos(const char *fmt, ...)
 static void genksyms_usage(void)
 {
 	fputs("Usage:\n" "genksyms [-adDTwqhVR] > /path/to/.tmp_obj.ver\n" "\n"
-#ifdef __GNU_LIBRARY__
-	      "  -s, --symbol-prefix   Select symbol prefix\n"
 	      "  -d, --debug           Increment the debug level (repeatable)\n"
 	      "  -D, --dump            Dump expanded symbol defs (for debugging only)\n"
 	      "  -r, --reference file  Read reference symbols from a file\n"
@@ -729,18 +725,6 @@ static void genksyms_usage(void)
 	      "  -q, --quiet           Disable warnings (default)\n"
 	      "  -h, --help            Print this message\n"
 	      "  -V, --version         Print the release version\n"
-#else				/* __GNU_LIBRARY__ */
-	      "  -s                    Select symbol prefix\n"
-	      "  -d                    Increment the debug level (repeatable)\n"
-	      "  -D                    Dump expanded symbol defs (for debugging only)\n"
-	      "  -r file               Read reference symbols from a file\n"
-	      "  -T file               Dump expanded types into file\n"
-	      "  -p                    Preserve reference modversions or fail\n"
-	      "  -w                    Enable warnings\n"
-	      "  -q                    Disable warnings (default)\n"
-	      "  -h                    Print this message\n"
-	      "  -V                    Print the release version\n"
-#endif				/* __GNU_LIBRARY__ */
 	      , stderr);
 }
 
@@ -749,7 +733,6 @@ int main(int argc, char **argv)
 	FILE *dumpfile = NULL, *ref_file = NULL;
 	int o;
 
-#ifdef __GNU_LIBRARY__
 	struct option long_opts[] = {
 		{"debug", 0, 0, 'd'},
 		{"warnings", 0, 0, 'w'},
@@ -763,11 +746,8 @@ int main(int argc, char **argv)
 		{0, 0, 0, 0}
 	};
 
-	while ((o = getopt_long(argc, argv, "s:dwqVDr:T:ph",
+	while ((o = getopt_long(argc, argv, "dwqVDr:T:ph",
 				&long_opts[0], NULL)) != EOF)
-#else				/* __GNU_LIBRARY__ */
-	while ((o = getopt(argc, argv, "s:dwqVDr:T:ph")) != EOF)
-#endif				/* __GNU_LIBRARY__ */
 		switch (o) {
 		case 'd':
 			flag_debug++;
diff --git a/scripts/git.orderFile b/scripts/git.orderFile
new file mode 100644
index 000000000000..5102ba73357f
--- /dev/null
+++ b/scripts/git.orderFile
@@ -0,0 +1,42 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# order file for git, to produce patches which are easier to review
+# by diffing the important stuff like header changes first.
+#
+# one-off usage:
+#   git diff -O scripts/git.orderFile ...
+#
+# add to git config:
+#   git config diff.orderFile scripts/git.orderFile
+#
+
+MAINTAINERS
+
+# Documentation
+Documentation/*
+*.rst
+
+# git-specific
+.gitignore
+scripts/git.orderFile
+
+# build system
+Kconfig*
+*/Kconfig*
+Kbuild*
+*/Kbuild*
+Makefile*
+*/Makefile*
+*.mak
+*.mk
+scripts/*
+
+# semantic patches
+*.cocci
+
+# headers
+*types.h
+*.h
+
+# code
+*.c
diff --git a/scripts/head-object-list.txt b/scripts/head-object-list.txt
index 26359968744e..890f69005bab 100644
--- a/scripts/head-object-list.txt
+++ b/scripts/head-object-list.txt
@@ -17,7 +17,6 @@ arch/arm/kernel/head-nommu.o
 arch/arm/kernel/head.o
 arch/csky/kernel/head.o
 arch/hexagon/kernel/head.o
-arch/ia64/kernel/head.o
 arch/loongarch/kernel/head.o
 arch/m68k/68000/head.o
 arch/m68k/coldfire/head.o
diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile
index 4eee155121a8..ea1bf3b3dbde 100644
--- a/scripts/kconfig/Makefile
+++ b/scripts/kconfig/Makefile
@@ -27,6 +27,14 @@ KCONFIG_DEFCONFIG_LIST += \
 endif
 KCONFIG_DEFCONFIG_LIST += arch/$(SRCARCH)/configs/$(KBUILD_DEFCONFIG)
 
+ifneq ($(findstring c, $(KBUILD_EXTRA_WARN)),)
+export KCONFIG_WARN_UNKNOWN_SYMBOLS=1
+endif
+
+ifneq ($(findstring e, $(KBUILD_EXTRA_WARN)),)
+export KCONFIG_WERROR=1
+endif
+
 # We need this, in case the user has it in its environment
 unexport CONFIG_
 
@@ -99,7 +107,7 @@ config-fragments = $(call configfiles,$@)
 
 %.config: $(obj)/conf
 	$(if $(config-fragments),, $(error $@ fragment does not exists on this architecture))
-	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh -m .config $(config-fragments)
+	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh -m $(KCONFIG_CONFIG) $(config-fragments)
 	$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig
 
 PHONY += tinyconfig
@@ -166,7 +174,7 @@ conf-objs	:= conf.o $(common-objs)
 
 # nconf: Used for the nconfig target based on ncurses
 hostprogs	+= nconf
-nconf-objs	:= nconf.o nconf.gui.o $(common-objs)
+nconf-objs	:= nconf.o nconf.gui.o mnconf-common.o $(common-objs)
 
 HOSTLDLIBS_nconf       = $(call read-file, $(obj)/nconf-libs)
 HOSTCFLAGS_nconf.o     = $(call read-file, $(obj)/nconf-cflags)
@@ -179,7 +187,7 @@ $(obj)/nconf.o $(obj)/nconf.gui.o: | $(obj)/nconf-cflags
 hostprogs	+= mconf
 lxdialog	:= $(addprefix lxdialog/, \
 		     checklist.o inputbox.o menubox.o textbox.o util.o yesno.o)
-mconf-objs	:= mconf.o $(lxdialog) $(common-objs)
+mconf-objs	:= mconf.o $(lxdialog) mnconf-common.o $(common-objs)
 
 HOSTLDLIBS_mconf = $(call read-file, $(obj)/mconf-libs)
 $(foreach f, mconf.o $(lxdialog), \
diff --git a/scripts/kconfig/conf.c b/scripts/kconfig/conf.c
index 33d19e419908..662a5e7c37c2 100644
--- a/scripts/kconfig/conf.c
+++ b/scripts/kconfig/conf.c
@@ -827,6 +827,9 @@ int main(int ac, char **av)
 		break;
 	}
 
+	if (conf_errors())
+		exit(1);
+
 	if (sync_kconfig) {
 		name = getenv("KCONFIG_NOSILENTUPDATE");
 		if (name && *name) {
@@ -890,6 +893,9 @@ int main(int ac, char **av)
 		break;
 	}
 
+	if (sym_dep_errors())
+		exit(1);
+
 	if (input_mode == savedefconfig) {
 		if (conf_write_defconfig(defconfig_file)) {
 			fprintf(stderr, "n*** Error while saving defconfig to: %s\n\n",
diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index 4a6811d77d18..f53dcdd44597 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -155,6 +155,13 @@ static void conf_message(const char *fmt, ...)
 static const char *conf_filename;
 static int conf_lineno, conf_warnings;
 
+bool conf_errors(void)
+{
+	if (conf_warnings)
+		return getenv("KCONFIG_WERROR");
+	return false;
+}
+
 static void conf_warning(const char *fmt, ...)
 {
 	va_list ap;
@@ -289,16 +296,12 @@ static int conf_set_sym_val(struct symbol *sym, int def, int def_flags, char *p)
 #define LINE_GROWTH 16
 static int add_byte(int c, char **lineptr, size_t slen, size_t *n)
 {
-	char *nline;
 	size_t new_size = slen + 1;
+
 	if (new_size > *n) {
 		new_size += LINE_GROWTH - 1;
 		new_size *= 2;
-		nline = xrealloc(*lineptr, new_size);
-		if (!nline)
-			return -1;
-
-		*lineptr = nline;
+		*lineptr = xrealloc(*lineptr, new_size);
 		*n = new_size;
 	}
 
@@ -341,19 +344,37 @@ e_out:
 	return -1;
 }
 
+/* like getline(), but the newline character is stripped away */
+static ssize_t getline_stripped(char **lineptr, size_t *n, FILE *stream)
+{
+	ssize_t len;
+
+	len = compat_getline(lineptr, n, stream);
+
+	if (len > 0 && (*lineptr)[len - 1] == '\n') {
+		len--;
+		(*lineptr)[len] = '\0';
+
+		if (len > 0 && (*lineptr)[len - 1] == '\r') {
+			len--;
+			(*lineptr)[len] = '\0';
+		}
+	}
+
+	return len;
+}
+
 int conf_read_simple(const char *name, int def)
 {
 	FILE *in = NULL;
 	char   *line = NULL;
 	size_t  line_asize = 0;
-	char *p, *p2;
+	char *p, *val;
 	struct symbol *sym;
 	int i, def_flags;
-	const char *warn_unknown;
-	const char *werror;
+	const char *warn_unknown, *sym_name;
 
 	warn_unknown = getenv("KCONFIG_WARN_UNKNOWN_SYMBOLS");
-	werror = getenv("KCONFIG_WERROR");
 	if (name) {
 		in = zconf_fopen(name);
 	} else {
@@ -417,8 +438,7 @@ load:
 		case S_INT:
 		case S_HEX:
 		case S_STRING:
-			if (sym->def[def].val)
-				free(sym->def[def].val);
+			free(sym->def[def].val);
 			/* fall through */
 		default:
 			sym->def[def].val = NULL;
@@ -426,90 +446,68 @@ load:
 		}
 	}
 
-	while (compat_getline(&line, &line_asize, in) != -1) {
+	while (getline_stripped(&line, &line_asize, in) != -1) {
 		conf_lineno++;
-		sym = NULL;
+
+		if (!line[0]) /* blank line */
+			continue;
+
 		if (line[0] == '#') {
-			if (memcmp(line + 2, CONFIG_, strlen(CONFIG_)))
+			if (line[1] != ' ')
+				continue;
+			p = line + 2;
+			if (memcmp(p, CONFIG_, strlen(CONFIG_)))
 				continue;
-			p = strchr(line + 2 + strlen(CONFIG_), ' ');
+			sym_name = p + strlen(CONFIG_);
+			p = strchr(sym_name, ' ');
 			if (!p)
 				continue;
 			*p++ = 0;
-			if (strncmp(p, "is not set", 10))
+			if (strcmp(p, "is not set"))
 				continue;
-			if (def == S_DEF_USER) {
-				sym = sym_find(line + 2 + strlen(CONFIG_));
-				if (!sym) {
-					if (warn_unknown)
-						conf_warning("unknown symbol: %s",
-							     line + 2 + strlen(CONFIG_));
-
-					conf_set_changed(true);
-					continue;
-				}
-			} else {
-				sym = sym_lookup(line + 2 + strlen(CONFIG_), 0);
-				if (sym->type == S_UNKNOWN)
-					sym->type = S_BOOLEAN;
-			}
-			if (sym->flags & def_flags) {
-				conf_warning("override: reassigning to symbol %s", sym->name);
-			}
-			switch (sym->type) {
-			case S_BOOLEAN:
-			case S_TRISTATE:
-				sym->def[def].tri = no;
-				sym->flags |= def_flags;
-				break;
-			default:
-				;
-			}
-		} else if (memcmp(line, CONFIG_, strlen(CONFIG_)) == 0) {
-			p = strchr(line + strlen(CONFIG_), '=');
-			if (!p)
+
+			val = "n";
+		} else {
+			if (memcmp(line, CONFIG_, strlen(CONFIG_))) {
+				conf_warning("unexpected data: %s", line);
 				continue;
-			*p++ = 0;
-			p2 = strchr(p, '\n');
-			if (p2) {
-				*p2-- = 0;
-				if (*p2 == '\r')
-					*p2 = 0;
 			}
 
-			sym = sym_find(line + strlen(CONFIG_));
-			if (!sym) {
-				if (def == S_DEF_AUTO) {
-					/*
-					 * Reading from include/config/auto.conf
-					 * If CONFIG_FOO previously existed in
-					 * auto.conf but it is missing now,
-					 * include/config/FOO must be touched.
-					 */
-					conf_touch_dep(line + strlen(CONFIG_));
-				} else {
-					if (warn_unknown)
-						conf_warning("unknown symbol: %s",
-							     line + strlen(CONFIG_));
-
-					conf_set_changed(true);
-				}
+			sym_name = line + strlen(CONFIG_);
+			p = strchr(sym_name, '=');
+			if (!p) {
+				conf_warning("unexpected data: %s", line);
 				continue;
 			}
+			*p = 0;
+			val = p + 1;
+		}
 
-			if (sym->flags & def_flags) {
-				conf_warning("override: reassigning to symbol %s", sym->name);
-			}
-			if (conf_set_sym_val(sym, def, def_flags, p))
-				continue;
-		} else {
-			if (line[0] != '\r' && line[0] != '\n')
-				conf_warning("unexpected data: %.*s",
-					     (int)strcspn(line, "\r\n"), line);
+		sym = sym_find(sym_name);
+		if (!sym) {
+			if (def == S_DEF_AUTO) {
+				/*
+				 * Reading from include/config/auto.conf.
+				 * If CONFIG_FOO previously existed in auto.conf
+				 * but it is missing now, include/config/FOO
+				 * must be touched.
+				 */
+				conf_touch_dep(sym_name);
+			} else {
+				if (warn_unknown)
+					conf_warning("unknown symbol: %s", sym_name);
 
+				conf_set_changed(true);
+			}
 			continue;
 		}
 
+		if (sym->flags & def_flags)
+			conf_warning("override: reassigning to symbol %s", sym->name);
+
+		if (conf_set_sym_val(sym, def, def_flags, val))
+			continue;
+
 		if (sym && sym_is_choice_value(sym)) {
 			struct symbol *cs = prop_get_symbol(sym_get_choice_prop(sym));
 			switch (sym->def[def].tri) {
@@ -533,9 +531,6 @@ load:
 	free(line);
 	fclose(in);
 
-	if (conf_warnings && werror)
-		exit(1);
-
 	return 0;
 }
 
@@ -594,7 +589,7 @@ int conf_read(const char *name)
 				/* Reset a string value if it's out of range */
 				if (sym_string_within_range(sym, sym->def[S_DEF_USER].val))
 					break;
-				sym->flags &= ~(SYMBOL_VALID|SYMBOL_DEF_USER);
+				sym->flags &= ~SYMBOL_VALID;
 				conf_unsaved++;
 				break;
 			default:
diff --git a/scripts/kconfig/expr.c b/scripts/kconfig/expr.c
index 81ebf8108ca7..a290de36307b 100644
--- a/scripts/kconfig/expr.c
+++ b/scripts/kconfig/expr.c
@@ -1131,7 +1131,6 @@ static int expr_compare_type(enum expr_type t1, enum expr_type t2)
 	default:
 		return -1;
 	}
-	printf("[%dgt%d?]", t1, t2);
 	return 0;
 }
 
diff --git a/scripts/kconfig/lkc.h b/scripts/kconfig/lkc.h
index 471a59acecec..5cdc8f5e6446 100644
--- a/scripts/kconfig/lkc.h
+++ b/scripts/kconfig/lkc.h
@@ -99,8 +99,6 @@ bool menu_is_visible(struct menu *menu);
 bool menu_has_prompt(struct menu *menu);
 const char *menu_get_prompt(struct menu *menu);
 struct menu *menu_get_parent_menu(struct menu *menu);
-bool menu_has_help(struct menu *menu);
-const char *menu_get_help(struct menu *menu);
 int get_jump_key_char(void);
 struct gstr get_relations_str(struct symbol **sym_arr, struct list_head *head);
 void menu_get_ext_help(struct menu *menu, struct gstr *help);
diff --git a/scripts/kconfig/lkc_proto.h b/scripts/kconfig/lkc_proto.h
index edd1e617b25c..a4ae5e9eadad 100644
--- a/scripts/kconfig/lkc_proto.h
+++ b/scripts/kconfig/lkc_proto.h
@@ -1,4 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#ifndef LKC_PROTO_H
+#define LKC_PROTO_H
+
 #include <stdarg.h>
 
 /* confdata.c */
@@ -12,6 +15,7 @@ void conf_set_changed(bool val);
 bool conf_get_changed(void);
 void conf_set_changed_callback(void (*fn)(void));
 void conf_set_message_callback(void (*fn)(const char *s));
+bool conf_errors(void);
 
 /* symbol.c */
 extern struct symbol * symbol_hash[SYMBOL_HASHSIZE];
@@ -22,6 +26,7 @@ void print_symbol_for_listconfig(struct symbol *sym);
 struct symbol ** sym_re_search(const char *pattern);
 const char * sym_type_name(enum symbol_type type);
 void sym_calc_value(struct symbol *sym);
+bool sym_dep_errors(void);
 enum symbol_type sym_get_type(struct symbol *sym);
 bool sym_tristate_within_range(struct symbol *sym,tristate tri);
 bool sym_set_tristate_value(struct symbol *sym,tristate tri);
@@ -50,3 +55,5 @@ char *expand_one_token(const char **str);
 
 /* expr.c */
 void expr_print(struct expr *e, void (*fn)(void *, struct symbol *, const char *), void *data, int prevtoken);
+
+#endif /* LKC_PROTO_H */
diff --git a/scripts/kconfig/mconf.c b/scripts/kconfig/mconf.c
index eccc87a441e7..5df32148a869 100644
--- a/scripts/kconfig/mconf.c
+++ b/scripts/kconfig/mconf.c
@@ -21,6 +21,7 @@
 
 #include "lkc.h"
 #include "lxdialog/dialog.h"
+#include "mnconf-common.h"
 
 static const char mconf_readme[] =
 "Overview\n"
@@ -247,7 +248,7 @@ search_help[] =
 	"      -> PCI support (PCI [=y])\n"
 	"(1)     -> PCI access mode (<choice> [=y])\n"
 	"  Defined at drivers/pci/Kconfig:47\n"
-	"  Depends on: X86_LOCAL_APIC && X86_IO_APIC || IA64\n"
+	"  Depends on: X86_LOCAL_APIC && X86_IO_APIC\n"
 	"  Selects: LIBCRC32\n"
 	"  Selected by: BAR [=n]\n"
 	"-----------------------------------------------------------------\n"
@@ -286,7 +287,6 @@ static int single_menu_mode;
 static int show_all_options;
 static int save_and_exit;
 static int silent;
-static int jump_key_char;
 
 static void conf(struct menu *menu, struct menu *active_menu);
 
@@ -378,58 +378,6 @@ static void show_help(struct menu *menu)
 	str_free(&help);
 }
 
-struct search_data {
-	struct list_head *head;
-	struct menu *target;
-};
-
-static int next_jump_key(int key)
-{
-	if (key < '1' || key > '9')
-		return '1';
-
-	key++;
-
-	if (key > '9')
-		key = '1';
-
-	return key;
-}
-
-static int handle_search_keys(int key, size_t start, size_t end, void *_data)
-{
-	struct search_data *data = _data;
-	struct jump_key *pos;
-	int index = 0;
-
-	if (key < '1' || key > '9')
-		return 0;
-
-	list_for_each_entry(pos, data->head, entries) {
-		index = next_jump_key(index);
-
-		if (pos->offset < start)
-			continue;
-
-		if (pos->offset >= end)
-			break;
-
-		if (key == index) {
-			data->target = pos->target;
-			return 1;
-		}
-	}
-
-	return 0;
-}
-
-int get_jump_key_char(void)
-{
-	jump_key_char = next_jump_key(jump_key_char);
-
-	return jump_key_char;
-}
-
 static void search_conf(void)
 {
 	struct symbol **sym_arr;
diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c
index 61c442d84aef..2cce8b651f61 100644
--- a/scripts/kconfig/menu.c
+++ b/scripts/kconfig/menu.c
@@ -673,19 +673,6 @@ struct menu *menu_get_parent_menu(struct menu *menu)
 	return menu;
 }
 
-bool menu_has_help(struct menu *menu)
-{
-	return menu->help != NULL;
-}
-
-const char *menu_get_help(struct menu *menu)
-{
-	if (menu->help)
-		return menu->help;
-	else
-		return "";
-}
-
 static void get_def_str(struct gstr *r, struct menu *menu)
 {
 	str_printf(r, "Defined at %s:%d\n",
@@ -856,10 +843,10 @@ void menu_get_ext_help(struct menu *menu, struct gstr *help)
 	struct symbol *sym = menu->sym;
 	const char *help_text = nohelp_text;
 
-	if (menu_has_help(menu)) {
+	if (menu->help) {
 		if (sym->name)
 			str_printf(help, "%s%s:\n\n", CONFIG_, sym->name);
-		help_text = menu_get_help(menu);
+		help_text = menu->help;
 	}
 	str_printf(help, "%s\n", help_text);
 	if (sym)
diff --git a/scripts/kconfig/mnconf-common.c b/scripts/kconfig/mnconf-common.c
new file mode 100644
index 000000000000..18cb9a6c5aaa
--- /dev/null
+++ b/scripts/kconfig/mnconf-common.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "expr.h"
+#include "list.h"
+#include "mnconf-common.h"
+
+int jump_key_char;
+
+int next_jump_key(int key)
+{
+	if (key < '1' || key > '9')
+		return '1';
+
+	key++;
+
+	if (key > '9')
+		key = '1';
+
+	return key;
+}
+
+int handle_search_keys(int key, size_t start, size_t end, void *_data)
+{
+	struct search_data *data = _data;
+	struct jump_key *pos;
+	int index = 0;
+
+	if (key < '1' || key > '9')
+		return 0;
+
+	list_for_each_entry(pos, data->head, entries) {
+		index = next_jump_key(index);
+
+		if (pos->offset < start)
+			continue;
+
+		if (pos->offset >= end)
+			break;
+
+		if (key == index) {
+			data->target = pos->target;
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+int get_jump_key_char(void)
+{
+	jump_key_char = next_jump_key(jump_key_char);
+
+	return jump_key_char;
+}
diff --git a/scripts/kconfig/mnconf-common.h b/scripts/kconfig/mnconf-common.h
new file mode 100644
index 000000000000..ab6292cc4bf2
--- /dev/null
+++ b/scripts/kconfig/mnconf-common.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef MNCONF_COMMON_H
+#define MNCONF_COMMON_H
+
+#include <stddef.h>
+
+struct search_data {
+	struct list_head *head;
+	struct menu *target;
+};
+
+extern int jump_key_char;
+
+int next_jump_key(int key);
+int handle_search_keys(int key, size_t start, size_t end, void *_data);
+int get_jump_key_char(void);
+
+#endif /* MNCONF_COMMON_H */
diff --git a/scripts/kconfig/nconf.c b/scripts/kconfig/nconf.c
index 143a2c351d57..1148163cfa7e 100644
--- a/scripts/kconfig/nconf.c
+++ b/scripts/kconfig/nconf.c
@@ -12,6 +12,7 @@
 #include <stdlib.h>
 
 #include "lkc.h"
+#include "mnconf-common.h"
 #include "nconf.h"
 #include <ctype.h>
 
@@ -216,7 +217,7 @@ search_help[] =
 "Symbol: FOO [ = m]\n"
 "Prompt: Foo bus is used to drive the bar HW\n"
 "Defined at drivers/pci/Kconfig:47\n"
-"Depends on: X86_LOCAL_APIC && X86_IO_APIC || IA64\n"
+"Depends on: X86_LOCAL_APIC && X86_IO_APIC\n"
 "Location:\n"
 "  -> Bus options (PCI, PCMCIA, EISA, ISA)\n"
 "    -> PCI support (PCI [ = y])\n"
@@ -279,7 +280,6 @@ static const char *current_instructions = menu_instructions;
 
 static char *dialog_input_result;
 static int dialog_input_result_len;
-static int jump_key_char;
 
 static void selected_conf(struct menu *menu, struct menu *active_menu);
 static void conf(struct menu *menu);
@@ -691,57 +691,6 @@ static int do_exit(void)
 	return 0;
 }
 
-struct search_data {
-	struct list_head *head;
-	struct menu *target;
-};
-
-static int next_jump_key(int key)
-{
-	if (key < '1' || key > '9')
-		return '1';
-
-	key++;
-
-	if (key > '9')
-		key = '1';
-
-	return key;
-}
-
-static int handle_search_keys(int key, size_t start, size_t end, void *_data)
-{
-	struct search_data *data = _data;
-	struct jump_key *pos;
-	int index = 0;
-
-	if (key < '1' || key > '9')
-		return 0;
-
-	list_for_each_entry(pos, data->head, entries) {
-		index = next_jump_key(index);
-
-		if (pos->offset < start)
-			continue;
-
-		if (pos->offset >= end)
-			break;
-
-		if (key == index) {
-			data->target = pos->target;
-			return 1;
-		}
-	}
-
-	return 0;
-}
-
-int get_jump_key_char(void)
-{
-	jump_key_char = next_jump_key(jump_key_char);
-
-	return jump_key_char;
-}
 
 static void search_conf(void)
 {
diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index a76925b46ce6..e9e9fb8d8674 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -29,14 +29,9 @@ struct symbol symbol_no = {
 	.flags = SYMBOL_CONST|SYMBOL_VALID,
 };
 
-static struct symbol symbol_empty = {
-	.name = "",
-	.curr = { "", no },
-	.flags = SYMBOL_VALID,
-};
-
 struct symbol *modules_sym;
 static tristate modules_val;
+static int sym_warnings;
 
 enum symbol_type sym_get_type(struct symbol *sym)
 {
@@ -317,6 +312,14 @@ static void sym_warn_unmet_dep(struct symbol *sym)
 			       "  Selected by [m]:\n");
 
 	fputs(str_get(&gs), stderr);
+	sym_warnings++;
+}
+
+bool sym_dep_errors(void)
+{
+	if (sym_warnings)
+		return getenv("KCONFIG_WERROR");
+	return false;
 }
 
 void sym_calc_value(struct symbol *sym)
@@ -342,15 +345,21 @@ void sym_calc_value(struct symbol *sym)
 
 	oldval = sym->curr;
 
+	newval.tri = no;
+
 	switch (sym->type) {
 	case S_INT:
+		newval.val = "0";
+		break;
 	case S_HEX:
+		newval.val = "0x0";
+		break;
 	case S_STRING:
-		newval = symbol_empty.curr;
+		newval.val = "";
 		break;
 	case S_BOOLEAN:
 	case S_TRISTATE:
-		newval = symbol_no.curr;
+		newval.val = "n";
 		break;
 	default:
 		sym->curr.val = sym->name;
@@ -697,13 +706,12 @@ const char *sym_get_string_default(struct symbol *sym)
 {
 	struct property *prop;
 	struct symbol *ds;
-	const char *str;
+	const char *str = "";
 	tristate val;
 
 	sym_calc_visibility(sym);
 	sym_calc_value(modules_sym);
 	val = symbol_no.curr.tri;
-	str = symbol_empty.curr.val;
 
 	/* If symbol has a default value look it up */
 	prop = sym_get_default_prop(sym);
@@ -753,14 +761,17 @@ const char *sym_get_string_default(struct symbol *sym)
 		case yes: return "y";
 		}
 	case S_INT:
+		if (!str[0])
+			str = "0";
+		break;
 	case S_HEX:
-		return str;
-	case S_STRING:
-		return str;
-	case S_UNKNOWN:
+		if (!str[0])
+			str = "0x0";
+		break;
+	default:
 		break;
 	}
-	return "";
+	return str;
 }
 
 const char *sym_get_string_value(struct symbol *sym)
diff --git a/scripts/kconfig/util.c b/scripts/kconfig/util.c
index b78f114ad48c..92e5b2b9761d 100644
--- a/scripts/kconfig/util.c
+++ b/scripts/kconfig/util.c
@@ -42,8 +42,7 @@ struct gstr str_new(void)
 /* Free storage for growable string */
 void str_free(struct gstr *gs)
 {
-	if (gs->s)
-		free(gs->s);
+	free(gs->s);
 	gs->s = NULL;
 	gs->len = 0;
 }
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index a432b171be82..7862a8101747 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -135,8 +135,13 @@ gen_btf()
 	${OBJCOPY} --only-section=.BTF --set-section-flags .BTF=alloc,readonly \
 		--strip-all ${1} ${2} 2>/dev/null
 	# Change e_type to ET_REL so that it can be used to link final vmlinux.
-	# Unlike GNU ld, lld does not allow an ET_EXEC input.
-	printf '\1' | dd of=${2} conv=notrunc bs=1 seek=16 status=none
+	# GNU ld 2.35+ and lld do not allow an ET_EXEC input.
+	if is_enabled CONFIG_CPU_BIG_ENDIAN; then
+		et_rel='\0\1'
+	else
+		et_rel='\1\0'
+	fi
+	printf "${et_rel}" | dd of=${2} conv=notrunc bs=1 seek=16 status=none
 }
 
 # Create ${2} .S file with all symbols from the ${1} object file
diff --git a/scripts/min-tool-version.sh b/scripts/min-tool-version.sh
index c62066825f53..e217683b10d6 100755
--- a/scripts/min-tool-version.sh
+++ b/scripts/min-tool-version.sh
@@ -26,12 +26,14 @@ gcc)
 llvm)
 	if [ "$SRCARCH" = s390 ]; then
 		echo 15.0.0
+	elif [ "$SRCARCH" = loongarch ]; then
+		echo 18.0.0
 	else
 		echo 11.0.0
 	fi
 	;;
 rustc)
-	echo 1.74.1
+	echo 1.76.0
 	;;
 bindgen)
 	echo 0.65.1
diff --git a/scripts/mksysmap b/scripts/mksysmap
index 9ba1c9da0a40..57ff5656d566 100755
--- a/scripts/mksysmap
+++ b/scripts/mksysmap
@@ -48,17 +48,8 @@ ${NM} -n ${1} | sed >${2} -e "
 / __kvm_nvhe_\\$/d
 / __kvm_nvhe_\.L/d
 
-# arm64 lld
-/ __AArch64ADRPThunk_/d
-
-# arm lld
-/ __ARMV5PILongThunk_/d
-/ __ARMV7PILongThunk_/d
-/ __ThumbV7PILongThunk_/d
-
-# mips lld
-/ __LA25Thunk_/d
-/ __microLA25Thunk_/d
+# lld arm/aarch64/mips thunks
+/ __[[:alnum:]]*Thunk_/d
 
 # CFI type identifiers
 / __kcfi_typeid_/d
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index cb6406f485a9..267b9a0a3abc 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -60,8 +60,7 @@ static unsigned int nr_unresolved;
 
 #define MODULE_NAME_LEN (64 - sizeof(Elf_Addr))
 
-void __attribute__((format(printf, 2, 3)))
-modpost_log(enum loglevel loglevel, const char *fmt, ...)
+void modpost_log(enum loglevel loglevel, const char *fmt, ...)
 {
 	va_list arglist;
 
@@ -71,9 +70,7 @@ modpost_log(enum loglevel loglevel, const char *fmt, ...)
 		break;
 	case LOG_ERROR:
 		fprintf(stderr, "ERROR: ");
-		break;
-	case LOG_FATAL:
-		fprintf(stderr, "FATAL: ");
+		error_occurred = true;
 		break;
 	default: /* invalid loglevel, ignore */
 		break;
@@ -84,11 +81,6 @@ modpost_log(enum loglevel loglevel, const char *fmt, ...)
 	va_start(arglist, fmt);
 	vfprintf(stderr, fmt, arglist);
 	va_end(arglist);
-
-	if (loglevel == LOG_FATAL)
-		exit(1);
-	if (loglevel == LOG_ERROR)
-		error_occurred = true;
 }
 
 static inline bool strends(const char *str, const char *postfix)
@@ -474,11 +466,9 @@ static int parse_elf(struct elf_info *info, const char *filename)
 		fatal("%s: not relocatable object.", filename);
 
 	/* Check if file offset is correct */
-	if (hdr->e_shoff > info->size) {
+	if (hdr->e_shoff > info->size)
 		fatal("section header offset=%lu in file '%s' is bigger than filesize=%zu\n",
 		      (unsigned long)hdr->e_shoff, filename, info->size);
-		return 0;
-	}
 
 	if (hdr->e_shnum == SHN_UNDEF) {
 		/*
@@ -516,12 +506,11 @@ static int parse_elf(struct elf_info *info, const char *filename)
 		const char *secname;
 		int nobits = sechdrs[i].sh_type == SHT_NOBITS;
 
-		if (!nobits && sechdrs[i].sh_offset > info->size) {
+		if (!nobits && sechdrs[i].sh_offset > info->size)
 			fatal("%s is truncated. sechdrs[i].sh_offset=%lu > sizeof(*hrd)=%zu\n",
 			      filename, (unsigned long)sechdrs[i].sh_offset,
 			      sizeof(*hdr));
-			return 0;
-		}
+
 		secname = secstrings + sechdrs[i].sh_name;
 		if (strcmp(secname, ".modinfo") == 0) {
 			if (nobits)
@@ -807,7 +796,8 @@ static void check_section(const char *modname, struct elf_info *elf,
 
 #define DATA_SECTIONS ".data", ".data.rel"
 #define TEXT_SECTIONS ".text", ".text.*", ".sched.text", \
-		".kprobes.text", ".cpuidle.text", ".noinstr.text"
+		".kprobes.text", ".cpuidle.text", ".noinstr.text", \
+		".ltext", ".ltext.*"
 #define OTHER_TEXT_SECTIONS ".ref.text", ".head.text", ".spinlock.text", \
 		".fixup", ".entry.text", ".exception.text", \
 		".coldtext", ".softirqentry.text"
@@ -1346,6 +1336,14 @@ static Elf_Addr addend_mips_rel(uint32_t *location, unsigned int r_type)
 #define R_LARCH_SUB32		55
 #endif
 
+#ifndef R_LARCH_RELAX
+#define R_LARCH_RELAX		100
+#endif
+
+#ifndef R_LARCH_ALIGN
+#define R_LARCH_ALIGN		102
+#endif
+
 static void get_rel_type_and_sym(struct elf_info *elf, uint64_t r_info,
 				 unsigned int *r_type, unsigned int *r_sym)
 {
@@ -1400,9 +1398,16 @@ static void section_rela(struct module *mod, struct elf_info *elf,
 				continue;
 			break;
 		case EM_LOONGARCH:
-			if (!strcmp("__ex_table", fromsec) &&
-			    r_type == R_LARCH_SUB32)
+			switch (r_type) {
+			case R_LARCH_SUB32:
+				if (!strcmp("__ex_table", fromsec))
+					continue;
+				break;
+			case R_LARCH_RELAX:
+			case R_LARCH_ALIGN:
+				/* These relocs do not refer to symbols */
 				continue;
+			}
 			break;
 		}
 
@@ -1419,7 +1424,7 @@ static void section_rel(struct module *mod, struct elf_info *elf,
 
 	for (rel = start; rel < stop; rel++) {
 		Elf_Sym *tsym;
-		Elf_Addr taddr = 0, r_offset;
+		Elf_Addr taddr, r_offset;
 		unsigned int r_type, r_sym;
 		void *loc;
 
diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h
index 69baf014da4f..ee43c7950636 100644
--- a/scripts/mod/modpost.h
+++ b/scripts/mod/modpost.h
@@ -194,10 +194,10 @@ void *sym_get_data(const struct elf_info *info, const Elf_Sym *sym);
 enum loglevel {
 	LOG_WARN,
 	LOG_ERROR,
-	LOG_FATAL
 };
 
-void modpost_log(enum loglevel loglevel, const char *fmt, ...);
+void __attribute__((format(printf, 2, 3)))
+modpost_log(enum loglevel loglevel, const char *fmt, ...);
 
 /*
  * warn - show the given message, then let modpost continue running, still
@@ -214,4 +214,4 @@ void modpost_log(enum loglevel loglevel, const char *fmt, ...);
  */
 #define warn(fmt, args...)	modpost_log(LOG_WARN, fmt, ##args)
 #define error(fmt, args...)	modpost_log(LOG_ERROR, fmt, ##args)
-#define fatal(fmt, args...)	modpost_log(LOG_FATAL, fmt, ##args)
+#define fatal(fmt, args...)	do { error(fmt, ##args); exit(1); } while (1)
diff --git a/scripts/mod/sumversion.c b/scripts/mod/sumversion.c
index 31066bfdba04..dc4878502276 100644
--- a/scripts/mod/sumversion.c
+++ b/scripts/mod/sumversion.c
@@ -326,7 +326,12 @@ static int parse_source_files(const char *objfile, struct md4_ctx *md)
 
 	/* Sum all files in the same dir or subdirs. */
 	while ((line = get_line(&pos))) {
-		char* p = line;
+		char* p;
+
+		/* trim the leading spaces away */
+		while (isspace(*line))
+			line++;
+		p = line;
 
 		if (strncmp(line, "source_", sizeof("source_")-1) == 0) {
 			p = strrchr(line, ' ');
diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index d7dd0d04c70c..bf96a3c24608 100755
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -25,35 +25,20 @@ if_enabled_echo() {
 }
 
 create_package() {
-	local pname="$1" pdir="$2"
-	local dpkg_deb_opts
-
-	mkdir -m 755 -p "$pdir/DEBIAN"
-	mkdir -p "$pdir/usr/share/doc/$pname"
-	cp debian/copyright "$pdir/usr/share/doc/$pname/"
-	cp debian/changelog "$pdir/usr/share/doc/$pname/changelog.Debian"
-	gzip -n -9 "$pdir/usr/share/doc/$pname/changelog.Debian"
-	sh -c "cd '$pdir'; find . -type f ! -path './DEBIAN/*' -printf '%P\0' \
-		| xargs -r0 md5sum > DEBIAN/md5sums"
-
-	# Fix ownership and permissions
-	if [ "$DEB_RULES_REQUIRES_ROOT" = "no" ]; then
-		dpkg_deb_opts="--root-owner-group"
-	else
-		chown -R root:root "$pdir"
-	fi
-	# a+rX in case we are in a restrictive umask environment like 0077
-	# ug-s in case we build in a setuid/setgid directory
-	chmod -R go-w,a+rX,ug-s "$pdir"
-
-	# Create the package
-	dpkg-gencontrol -p$pname -P"$pdir"
-	dpkg-deb $dpkg_deb_opts ${KDEB_COMPRESS:+-Z$KDEB_COMPRESS} --build "$pdir" ..
+	export DH_OPTIONS="-p${1}"
+
+	dh_installdocs
+	dh_installchangelogs
+	dh_compress
+	dh_fixperms
+	dh_gencontrol
+	dh_md5sums
+	dh_builddeb -- ${KDEB_COMPRESS:+-Z$KDEB_COMPRESS}
 }
 
 install_linux_image () {
-	pdir=$1
-	pname=$2
+	pname=$1
+	pdir=debian/$1
 
 	rm -rf ${pdir}
 
@@ -62,7 +47,7 @@ install_linux_image () {
 		${MAKE} -f ${srctree}/Makefile INSTALL_DTBS_PATH="${pdir}/usr/lib/linux-image-${KERNELRELEASE}" dtbs_install
 	fi
 
-	${MAKE} -f ${srctree}/Makefile INSTALL_MOD_PATH="${pdir}" modules_install
+	${MAKE} -f ${srctree}/Makefile INSTALL_MOD_PATH="${pdir}" INSTALL_MOD_STRIP=1 modules_install
 	rm -f "${pdir}/lib/modules/${KERNELRELEASE}/build"
 
 	# Install the kernel
@@ -122,26 +107,22 @@ install_linux_image () {
 }
 
 install_linux_image_dbg () {
-	pdir=$1
-	image_pdir=$2
+	pdir=debian/$1
 
 	rm -rf ${pdir}
 
-	for module in $(find ${image_pdir}/lib/modules/ -name *.ko -printf '%P\n'); do
-		module=lib/modules/${module}
-		mkdir -p $(dirname ${pdir}/usr/lib/debug/${module})
-		# only keep debug symbols in the debug file
-		${OBJCOPY} --only-keep-debug ${image_pdir}/${module} ${pdir}/usr/lib/debug/${module}
-		# strip original module from debug symbols
-		${OBJCOPY} --strip-debug ${image_pdir}/${module}
-		# then add a link to those
-		${OBJCOPY} --add-gnu-debuglink=${pdir}/usr/lib/debug/${module} ${image_pdir}/${module}
-	done
+	# Parse modules.order directly because 'make modules_install' may sign,
+	# compress modules, and then run unneeded depmod.
+	while read -r mod; do
+		mod="${mod%.o}.ko"
+		dbg="${pdir}/usr/lib/debug/lib/modules/${KERNELRELEASE}/kernel/${mod}"
+		buildid=$("${READELF}" -n "${mod}" | sed -n 's@^.*Build ID: \(..\)\(.*\)@\1/\2@p')
+		link="${pdir}/usr/lib/debug/.build-id/${buildid}.debug"
 
-	# re-sign stripped modules
-	if is_enabled CONFIG_MODULE_SIG_ALL; then
-		${MAKE} -f ${srctree}/Makefile INSTALL_MOD_PATH="${image_pdir}" modules_sign
-	fi
+		mkdir -p "${dbg%/*}" "${link%/*}"
+		"${OBJCOPY}" --only-keep-debug "${mod}" "${dbg}"
+		ln -sf --relative "${dbg}" "${link}"
+	done < modules.order
 
 	# Build debug package
 	# Different tools want the image in different locations
@@ -156,8 +137,8 @@ install_linux_image_dbg () {
 }
 
 install_kernel_headers () {
-	pdir=$1
-	version=$2
+	pdir=debian/$1
+	version=${1#linux-headers-}
 
 	rm -rf $pdir
 
@@ -168,18 +149,16 @@ install_kernel_headers () {
 }
 
 install_libc_headers () {
-	pdir=$1
+	pdir=debian/$1
 
 	rm -rf $pdir
 
-	$MAKE -f $srctree/Makefile headers
 	$MAKE -f $srctree/Makefile headers_install INSTALL_HDR_PATH=$pdir/usr
 
 	# move asm headers to /usr/include/<libc-machine>/asm to match the structure
 	# used by Debian-based distros (to support multi-arch)
-	host_arch=$(dpkg-architecture -a$DEB_HOST_ARCH -qDEB_HOST_MULTIARCH)
-	mkdir $pdir/usr/include/$host_arch
-	mv $pdir/usr/include/asm $pdir/usr/include/$host_arch/
+	mkdir "$pdir/usr/include/${DEB_HOST_MULTIARCH}"
+	mv "$pdir/usr/include/asm" "$pdir/usr/include/${DEB_HOST_MULTIARCH}"
 }
 
 rm -f debian/files
@@ -190,30 +169,13 @@ for package in ${packages_enabled}
 do
 	case ${package} in
 	*-dbg)
-		# This must be done after linux-image, that is, we expect the
-		# debug package appears after linux-image in debian/control.
-		install_linux_image_dbg debian/linux-image-dbg debian/linux-image;;
-	linux-image-*|user-mode-linux-*)
-		install_linux_image debian/linux-image ${package};;
-	linux-libc-dev)
-		install_libc_headers debian/linux-libc-dev;;
-	linux-headers-*)
-		install_kernel_headers debian/linux-headers ${package#linux-headers-};;
-	esac
-done
-
-for package in ${packages_enabled}
-do
-	case ${package} in
-	*-dbg)
-		create_package ${package} debian/linux-image-dbg;;
+		install_linux_image_dbg "${package}";;
 	linux-image-*|user-mode-linux-*)
-		create_package ${package} debian/linux-image;;
+		install_linux_image "${package}";;
 	linux-libc-dev)
-		create_package ${package} debian/linux-libc-dev;;
+		install_libc_headers "${package}";;
 	linux-headers-*)
-		create_package ${package} debian/linux-headers;;
+		install_kernel_headers "${package}";;
 	esac
+	create_package "${package}"
 done
-
-exit 0
diff --git a/scripts/package/buildtar b/scripts/package/buildtar
index 65b4ea502962..72c91a1b832f 100755
--- a/scripts/package/buildtar
+++ b/scripts/package/buildtar
@@ -23,7 +23,6 @@ tmpdir=$1
 #
 rm -rf -- "${tmpdir}"
 mkdir -p -- "${tmpdir}/boot"
-dirs=boot
 
 
 #
@@ -38,12 +37,9 @@ fi
 
 
 #
-# Try to install modules
+# Install modules
 #
-if grep -q '^CONFIG_MODULES=y' include/config/auto.conf; then
-	make ARCH="${ARCH}" -f ${srctree}/Makefile INSTALL_MOD_PATH="${tmpdir}" modules_install
-	dirs="$dirs lib"
-fi
+make ARCH="${ARCH}" -f ${srctree}/Makefile INSTALL_MOD_PATH="${tmpdir}" modules_install
 
 
 #
diff --git a/scripts/package/deb-build-option b/scripts/package/deb-build-option
deleted file mode 100755
index 7950eff01781..000000000000
--- a/scripts/package/deb-build-option
+++ /dev/null
@@ -1,14 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0-only
-
-# Set up CROSS_COMPILE if not defined yet
-if [ "${CROSS_COMPILE+set}" != "set" -a "${DEB_HOST_ARCH}" != "${DEB_BUILD_ARCH}" ]; then
-	echo CROSS_COMPILE=${DEB_HOST_GNU_TYPE}-
-fi
-
-version=$(dpkg-parsechangelog -S Version)
-debian_revision="${version##*-}"
-
-if [ "${version}" != "${debian_revision}" ]; then
-	echo KBUILD_BUILD_VERSION=${debian_revision}
-fi
diff --git a/scripts/package/debian/copyright b/scripts/package/debian/copyright
new file mode 100644
index 000000000000..4f1f06221f09
--- /dev/null
+++ b/scripts/package/debian/copyright
@@ -0,0 +1,16 @@
+This is a packaged upstream version of the Linux kernel.
+
+The sources may be found at most Linux archive sites, including:
+https://www.kernel.org/pub/linux/kernel
+
+Copyright: 1991 - 2023 Linus Torvalds and others.
+
+The git repository for mainline kernel development is at:
+git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; version 2 dated June, 1991.
+
+On Debian GNU/Linux systems, the complete text of the GNU General Public
+License version 2 can be found in `/usr/share/common-licenses/GPL-2'.
diff --git a/scripts/package/debian/rules b/scripts/package/debian/rules
index 3dafa9496c63..098307780062 100755
--- a/scripts/package/debian/rules
+++ b/scripts/package/debian/rules
@@ -1,33 +1,46 @@
 #!/usr/bin/make -f
 # SPDX-License-Identifier: GPL-2.0-only
 
-include debian/rules.vars
+# in case debian/rules is executed directly
+export DEB_RULES_REQUIRES_ROOT := no
 
-srctree ?= .
+include debian/rules.vars
 
 ifneq (,$(filter-out parallel=1,$(filter parallel=%,$(DEB_BUILD_OPTIONS))))
     NUMJOBS = $(patsubst parallel=%,%,$(filter parallel=%,$(DEB_BUILD_OPTIONS)))
     MAKEFLAGS += -j$(NUMJOBS)
 endif
 
+revision = $(lastword $(subst -, ,$(shell dpkg-parsechangelog -S Version)))
+CROSS_COMPILE ?= $(filter-out $(DEB_BUILD_GNU_TYPE)-, $(DEB_HOST_GNU_TYPE)-)
+make-opts = ARCH=$(ARCH) KERNELRELEASE=$(KERNELRELEASE) KBUILD_BUILD_VERSION=$(revision) $(addprefix CROSS_COMPILE=,$(CROSS_COMPILE))
+
 .PHONY: binary binary-indep binary-arch
 binary: binary-arch binary-indep
 binary-indep: build-indep
 binary-arch: build-arch
-	$(MAKE) -f $(srctree)/Makefile ARCH=$(ARCH) \
-	KERNELRELEASE=$(KERNELRELEASE) \
-	run-command KBUILD_RUN_COMMAND=+$(srctree)/scripts/package/builddeb
+	$(MAKE) $(make-opts) \
+	run-command KBUILD_RUN_COMMAND='+$$(srctree)/scripts/package/builddeb'
 
 .PHONY: build build-indep build-arch
 build: build-arch build-indep
 build-indep:
 build-arch:
-	$(MAKE) -f $(srctree)/Makefile ARCH=$(ARCH) \
-	KERNELRELEASE=$(KERNELRELEASE) \
-	$(shell $(srctree)/scripts/package/deb-build-option) \
-	olddefconfig all
+	$(MAKE) $(make-opts) olddefconfig
+	$(MAKE) $(make-opts) $(if $(filter um,$(ARCH)),,headers) all
 
 .PHONY: clean
 clean:
-	rm -rf debian/files debian/linux-*
-	$(MAKE) -f $(srctree)/Makefile ARCH=$(ARCH) clean
+	rm -rf debian/files debian/linux-* debian/deb-env.vars*
+	$(MAKE) ARCH=$(ARCH) clean
+
+# If DEB_HOST_ARCH is empty, it is likely that debian/rules was executed
+# directly. Run 'dpkg-architecture --print-set --print-format=make' to
+# generate a makefile construct that exports all DEB_* variables.
+ifndef DEB_HOST_ARCH
+include debian/deb-env.vars
+
+debian/deb-env.vars:
+	dpkg-architecture -a$$(cat debian/arch) --print-set --print-format=make > $@.tmp
+	mv $@.tmp $@
+endif
diff --git a/scripts/package/install-extmod-build b/scripts/package/install-extmod-build
index 8a7051fad087..76e0765dfcd6 100755
--- a/scripts/package/install-extmod-build
+++ b/scripts/package/install-extmod-build
@@ -20,7 +20,7 @@ mkdir -p "${destdir}"
 	find "arch/${SRCARCH}" -maxdepth 1 -name 'Makefile*'
 	find include scripts -type f -o -type l
 	find "arch/${SRCARCH}" -name Kbuild.platforms -o -name Platform
-	find "arch/${SRCARCH}" -name include -o -name scripts -type d
+	find "arch/${SRCARCH}" -name include -type d
 ) | tar -c -f - -C "${srctree}" -T - | tar -xf - -C "${destdir}"
 
 {
diff --git a/scripts/package/kernel.spec b/scripts/package/kernel.spec
index 3eee0143e0c5..f58726671fb3 100644
--- a/scripts/package/kernel.spec
+++ b/scripts/package/kernel.spec
@@ -55,18 +55,12 @@ patch -p1 < %{SOURCE2}
 %{make} %{makeflags} KERNELRELEASE=%{KERNELRELEASE} KBUILD_BUILD_VERSION=%{release}
 
 %install
-mkdir -p %{buildroot}/boot
-%ifarch ia64
-mkdir -p %{buildroot}/boot/efi
-cp $(%{make} %{makeflags} -s image_name) %{buildroot}/boot/efi/vmlinuz-%{KERNELRELEASE}
-ln -s efi/vmlinuz-%{KERNELRELEASE} %{buildroot}/boot/
-%else
-cp $(%{make} %{makeflags} -s image_name) %{buildroot}/boot/vmlinuz-%{KERNELRELEASE}
-%endif
+mkdir -p %{buildroot}/lib/modules/%{KERNELRELEASE}
+cp $(%{make} %{makeflags} -s image_name) %{buildroot}/lib/modules/%{KERNELRELEASE}/vmlinuz
 %{make} %{makeflags} INSTALL_MOD_PATH=%{buildroot} modules_install
 %{make} %{makeflags} INSTALL_HDR_PATH=%{buildroot}/usr headers_install
-cp System.map %{buildroot}/boot/System.map-%{KERNELRELEASE}
-cp .config %{buildroot}/boot/config-%{KERNELRELEASE}
+cp System.map %{buildroot}/lib/modules/%{KERNELRELEASE}
+cp .config %{buildroot}/lib/modules/%{KERNELRELEASE}/config
 ln -fns /usr/src/kernels/%{KERNELRELEASE} %{buildroot}/lib/modules/%{KERNELRELEASE}/build
 %if %{with_devel}
 %{make} %{makeflags} run-command KBUILD_RUN_COMMAND='${srctree}/scripts/package/install-extmod-build %{buildroot}/usr/src/kernels/%{KERNELRELEASE}'
@@ -76,13 +70,14 @@ ln -fns /usr/src/kernels/%{KERNELRELEASE} %{buildroot}/lib/modules/%{KERNELRELEA
 rm -rf %{buildroot}
 
 %post
-if [ -x /sbin/installkernel -a -r /boot/vmlinuz-%{KERNELRELEASE} -a -r /boot/System.map-%{KERNELRELEASE} ]; then
-cp /boot/vmlinuz-%{KERNELRELEASE} /boot/.vmlinuz-%{KERNELRELEASE}-rpm
-cp /boot/System.map-%{KERNELRELEASE} /boot/.System.map-%{KERNELRELEASE}-rpm
-rm -f /boot/vmlinuz-%{KERNELRELEASE} /boot/System.map-%{KERNELRELEASE}
-/sbin/installkernel %{KERNELRELEASE} /boot/.vmlinuz-%{KERNELRELEASE}-rpm /boot/.System.map-%{KERNELRELEASE}-rpm
-rm -f /boot/.vmlinuz-%{KERNELRELEASE}-rpm /boot/.System.map-%{KERNELRELEASE}-rpm
+if [ -x /usr/bin/kernel-install ]; then
+	/usr/bin/kernel-install add %{KERNELRELEASE} /lib/modules/%{KERNELRELEASE}/vmlinuz
 fi
+for file in vmlinuz System.map config; do
+	if ! cmp --silent "/lib/modules/%{KERNELRELEASE}/${file}" "/boot/${file}-%{KERNELRELEASE}"; then
+		cp "/lib/modules/%{KERNELRELEASE}/${file}" "/boot/${file}-%{KERNELRELEASE}"
+	fi
+done
 
 %preun
 if [ -x /sbin/new-kernel-pkg ]; then
@@ -100,7 +95,6 @@ fi
 %defattr (-, root, root)
 /lib/modules/%{KERNELRELEASE}
 %exclude /lib/modules/%{KERNELRELEASE}/build
-/boot/*
 
 %files headers
 %defattr (-, root, root)
diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index 5044224cf671..070149c985fe 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -26,7 +26,7 @@ set_debarch() {
 
 	# Attempt to find the correct Debian architecture
 	case "$UTS_MACHINE" in
-	i386|ia64|alpha|m68k|riscv*)
+	i386|alpha|m68k|riscv*)
 		debarch="$UTS_MACHINE" ;;
 	x86_64)
 		debarch=amd64 ;;
@@ -176,8 +176,6 @@ else
 fi
 
 echo $debarch > debian/arch
-extra_build_depends=", $(if_enabled_echo CONFIG_UNWINDER_ORC libelf-dev:native)"
-extra_build_depends="$extra_build_depends, $(if_enabled_echo CONFIG_SYSTEM_TRUSTED_KEYRING libssl-dev:native)"
 
 # Generate a simple changelog template
 cat <<EOF > debian/changelog
@@ -188,26 +186,6 @@ $sourcename ($packageversion) $distribution; urgency=low
  -- $maintainer  $(date -R)
 EOF
 
-# Generate copyright file
-cat <<EOF > debian/copyright
-This is a packaged upstream version of the Linux kernel.
-
-The sources may be found at most Linux archive sites, including:
-https://www.kernel.org/pub/linux/kernel
-
-Copyright: 1991 - 2018 Linus Torvalds and others.
-
-The git repository for mainline kernel development is at:
-git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
-
-    This program is free software; you can redistribute it and/or modify
-    it under the terms of the GNU General Public License as published by
-    the Free Software Foundation; version 2 dated June, 1991.
-
-On Debian GNU/Linux systems, the complete text of the GNU General Public
-License version 2 can be found in \`/usr/share/common-licenses/GPL-2'.
-EOF
-
 # Generate a control file
 cat <<EOF > debian/control
 Source: $sourcename
@@ -215,7 +193,8 @@ Section: kernel
 Priority: optional
 Maintainer: $maintainer
 Rules-Requires-Root: no
-Build-Depends: bc, debhelper, rsync, kmod, cpio, bison, flex $extra_build_depends
+Build-Depends: debhelper-compat (= 12)
+Build-Depends-Arch: bc, bison, cpio, flex, kmod, libelf-dev:native, libssl-dev:native, rsync
 Homepage: https://www.kernel.org/
 
 Package: $packagename-$version
@@ -268,6 +247,7 @@ ARCH := ${ARCH}
 KERNELRELEASE := ${KERNELRELEASE}
 EOF
 
+cp "${srctree}/scripts/package/debian/copyright" debian/
 cp "${srctree}/scripts/package/debian/rules" debian/
 
 exit 0
diff --git a/scripts/package/snapcraft.template b/scripts/package/snapcraft.template
index 626d278e4a5a..85d5e07d1b40 100644
--- a/scripts/package/snapcraft.template
+++ b/scripts/package/snapcraft.template
@@ -10,5 +10,5 @@ parts:
   kernel:
     plugin: kernel
     source: SRCTREE
-    source-type: tar
+    source-type: local
     kernel-with-firmware: false
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index 40ae6b2c7a6d..3e4f54799cc0 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -590,7 +590,6 @@ static int do_file(char const *const fname)
 		ideal_nop = ideal_nop4_arm64;
 		is_fake_mcount64 = arm64_is_fake_mcount;
 		break;
-	case EM_IA_64:	reltype = R_IA64_IMM64; break;
 	case EM_MIPS:	/* reltype: e_class    */ break;
 	case EM_LOONGARCH:	/* reltype: e_class    */ break;
 	case EM_PPC:	reltype = R_PPC_ADDR32; break;
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 6a4645a57976..f84df9e383fd 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -275,13 +275,6 @@ if ($arch eq "x86_64") {
     $section_type = '%progbits';
     $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_AARCH64_CALL26\\s+_mcount\$";
     $type = ".quad";
-} elsif ($arch eq "ia64") {
-    $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s_mcount\$";
-    $type = "data8";
-
-    if ($is_module eq "0") {
-	$cc .= " -mconstant-gp";
-    }
 } elsif ($arch eq "sparc64") {
     # In the objdump output there are giblets like:
     # 0000000000000000 <igmp_net_exit-0x18>:
diff --git a/scripts/tags.sh b/scripts/tags.sh
index a70d43723146..191e0461d6d5 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -3,7 +3,7 @@
 # Generate tags or cscope files
 # Usage tags.sh <mode>
 #
-# mode may be any of: tags, TAGS, cscope
+# mode may be any of: tags, gtags, TAGS, cscope
 #
 # Uses the following environment variables:
 # SUBARCH, SRCARCH, srctree
@@ -50,7 +50,7 @@ fi
 find_arch_sources()
 {
 	for i in $archincludedir; do
-		prune="$prune -wholename $i -prune -o"
+		local prune="$prune ( -path $i ) -prune -o"
 	done
 	find ${tree}arch/$1 $ignore $prune -name "$2" -not -type l -print;
 }
@@ -58,7 +58,7 @@ find_arch_sources()
 # find sources in arch/$1/include
 find_arch_include_sources()
 {
-	include=$(find ${tree}arch/$1/ -name include -type d -print);
+	local include=$(find ${tree}arch/$1/ -name include -type d -print);
 	if [ -n "$include" ]; then
 		archincludedir="$archincludedir $include"
 		find $include $ignore -name "$2" -not -type l -print;
@@ -81,21 +81,16 @@ find_other_sources()
 	       -name "$1" -not -type l -print;
 }
 
-find_sources()
-{
-	find_arch_sources $1 "$2"
-}
-
 all_sources()
 {
 	find_arch_include_sources ${SRCARCH} '*.[chS]'
-	if [ ! -z "$archinclude" ]; then
+	if [ -n "$archinclude" ]; then
 		find_arch_include_sources $archinclude '*.[chS]'
 	fi
 	find_include_sources '*.[chS]'
 	for arch in $ALLSOURCE_ARCHS
 	do
-		find_sources $arch '*.[chS]'
+		find_arch_sources $arch '*.[chS]'
 	done
 	find_other_sources '*.[chS]'
 }
@@ -125,7 +120,7 @@ all_kconfigs()
 	find ${tree}arch/ -maxdepth 1 $ignore \
 	       -name "Kconfig*" -not -type l -print;
 	for arch in $ALLSOURCE_ARCHS; do
-		find_sources $arch 'Kconfig*'
+		find_arch_sources $arch 'Kconfig*'
 	done
 	find_other_sources 'Kconfig*'
 }
diff --git a/scripts/xz_wrap.sh b/scripts/xz_wrap.sh
index 76e9cbcfbeab..d06baf626abe 100755
--- a/scripts/xz_wrap.sh
+++ b/scripts/xz_wrap.sh
@@ -15,7 +15,6 @@ LZMA2OPTS=
 case $SRCARCH in
 	x86)            BCJ=--x86 ;;
 	powerpc)        BCJ=--powerpc ;;
-	ia64)           BCJ=--ia64; LZMA2OPTS=pb=4 ;;
 	arm)            BCJ=--arm ;;
 	sparc)          BCJ=--sparc ;;
 esac
diff --git a/security/apparmor/Kconfig b/security/apparmor/Kconfig
index e0d1dd0a192a..64cc3044a42c 100644
--- a/security/apparmor/Kconfig
+++ b/security/apparmor/Kconfig
@@ -57,10 +57,10 @@ config SECURITY_APPARMOR_INTROSPECT_POLICY
 	  cpu is paramount.
 
 config SECURITY_APPARMOR_HASH
-	bool "Enable introspection of sha1 hashes for loaded profiles"
+	bool "Enable introspection of sha256 hashes for loaded profiles"
 	depends on SECURITY_APPARMOR_INTROSPECT_POLICY
 	select CRYPTO
-	select CRYPTO_SHA1
+	select CRYPTO_SHA256
 	default y
 	help
 	  This option selects whether introspection of loaded policy
@@ -74,10 +74,10 @@ config SECURITY_APPARMOR_HASH_DEFAULT
        depends on SECURITY_APPARMOR_HASH
        default y
        help
-         This option selects whether sha1 hashing of loaded policy
-	 is enabled by default. The generation of sha1 hashes for
-	 loaded policy provide system administrators a quick way
-	 to verify that policy in the kernel matches what is expected,
+	 This option selects whether sha256 hashing of loaded policy
+	 is enabled by default. The generation of sha256 hashes for
+	 loaded policy provide system administrators a quick way to
+	 verify that policy in the kernel matches what is expected,
 	 however it can slow down policy load on some devices. In
 	 these cases policy hashing can be disabled by default and
 	 enabled only if needed.
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index f3c77825aa75..bcfea073e3f2 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -1474,7 +1474,7 @@ int __aa_fs_create_rawdata(struct aa_ns *ns, struct aa_loaddata *rawdata)
 	rawdata->dents[AAFS_LOADDATA_REVISION] = dent;
 
 	if (aa_g_hash_policy) {
-		dent = aafs_create_file("sha1", S_IFREG | 0444, dir,
+		dent = aafs_create_file("sha256", S_IFREG | 0444, dir,
 					      rawdata, &seq_rawdata_hash_fops);
 		if (IS_ERR(dent))
 			goto fail;
@@ -1643,11 +1643,11 @@ static const char *rawdata_get_link_base(struct dentry *dentry,
 	return target;
 }
 
-static const char *rawdata_get_link_sha1(struct dentry *dentry,
+static const char *rawdata_get_link_sha256(struct dentry *dentry,
 					 struct inode *inode,
 					 struct delayed_call *done)
 {
-	return rawdata_get_link_base(dentry, inode, done, "sha1");
+	return rawdata_get_link_base(dentry, inode, done, "sha256");
 }
 
 static const char *rawdata_get_link_abi(struct dentry *dentry,
@@ -1664,8 +1664,8 @@ static const char *rawdata_get_link_data(struct dentry *dentry,
 	return rawdata_get_link_base(dentry, inode, done, "raw_data");
 }
 
-static const struct inode_operations rawdata_link_sha1_iops = {
-	.get_link	= rawdata_get_link_sha1,
+static const struct inode_operations rawdata_link_sha256_iops = {
+	.get_link	= rawdata_get_link_sha256,
 };
 
 static const struct inode_operations rawdata_link_abi_iops = {
@@ -1738,7 +1738,7 @@ int __aafs_profile_mkdir(struct aa_profile *profile, struct dentry *parent)
 	profile->dents[AAFS_PROF_ATTACH] = dent;
 
 	if (profile->hash) {
-		dent = create_profile_file(dir, "sha1", profile,
+		dent = create_profile_file(dir, "sha256", profile,
 					   &seq_profile_hash_fops);
 		if (IS_ERR(dent))
 			goto fail;
@@ -1748,9 +1748,9 @@ int __aafs_profile_mkdir(struct aa_profile *profile, struct dentry *parent)
 #ifdef CONFIG_SECURITY_APPARMOR_EXPORT_BINARY
 	if (profile->rawdata) {
 		if (aa_g_hash_policy) {
-			dent = aafs_create("raw_sha1", S_IFLNK | 0444, dir,
+			dent = aafs_create("raw_sha256", S_IFLNK | 0444, dir,
 					   profile->label.proxy, NULL, NULL,
-					   &rawdata_link_sha1_iops);
+					   &rawdata_link_sha256_iops);
 			if (IS_ERR(dent))
 				goto fail;
 			aa_get_proxy(profile->label.proxy);
diff --git a/security/apparmor/crypto.c b/security/apparmor/crypto.c
index 6724e2ff6da8..aad486b2fca6 100644
--- a/security/apparmor/crypto.c
+++ b/security/apparmor/crypto.c
@@ -106,16 +106,16 @@ static int __init init_profile_hash(void)
 	if (!apparmor_initialized)
 		return 0;
 
-	tfm = crypto_alloc_shash("sha1", 0, 0);
+	tfm = crypto_alloc_shash("sha256", 0, 0);
 	if (IS_ERR(tfm)) {
 		int error = PTR_ERR(tfm);
-		AA_ERROR("failed to setup profile sha1 hashing: %d\n", error);
+		AA_ERROR("failed to setup profile sha256 hashing: %d\n", error);
 		return error;
 	}
 	apparmor_tfm = tfm;
 	apparmor_hash_size = crypto_shash_digestsize(apparmor_tfm);
 
-	aa_info_message("AppArmor sha1 policy hashing enabled");
+	aa_info_message("AppArmor sha256 policy hashing enabled");
 
 	return 0;
 }
diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index 89fbeab4b33b..571158ec6188 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -1311,7 +1311,7 @@ static int change_profile_perms_wrapper(const char *op, const char *name,
 	return error;
 }
 
-const char *stack_msg = "change_profile unprivileged unconfined converted to stacking";
+static const char *stack_msg = "change_profile unprivileged unconfined converted to stacking";
 
 /**
  * aa_change_profile - perform a one-way profile transition
diff --git a/security/apparmor/lib.c b/security/apparmor/lib.c
index 4c198d273f09..cd569fbbfe36 100644
--- a/security/apparmor/lib.c
+++ b/security/apparmor/lib.c
@@ -41,6 +41,7 @@ void aa_free_str_table(struct aa_str_table *t)
 			kfree_sensitive(t->table[i]);
 		kfree_sensitive(t->table);
 		t->table = NULL;
+		t->size = 0;
 	}
 }
 
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index e490a7000408..9a3dcaafb5b1 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -469,8 +469,10 @@ static int apparmor_file_open(struct file *file)
 	 * Cache permissions granted by the previous exec check, with
 	 * implicit read and executable mmap which are required to
 	 * actually execute the image.
+	 *
+	 * Illogically, FMODE_EXEC is in f_flags, not f_mode.
 	 */
-	if (current->in_execve) {
+	if (file->f_flags & __FMODE_EXEC) {
 		fctx->allow = MAY_EXEC | MAY_READ | AA_EXEC_MMAP;
 		return 0;
 	}
@@ -782,7 +784,7 @@ static int apparmor_getselfattr(unsigned int attr, struct lsm_ctx __user *lx,
 	int error = -ENOENT;
 	struct aa_task_ctx *ctx = task_ctx(current);
 	struct aa_label *label = NULL;
-	char *value;
+	char *value = NULL;
 
 	switch (attr) {
 	case LSM_ATTR_CURRENT:
@@ -1023,7 +1025,6 @@ static int apparmor_task_kill(struct task_struct *target, struct kernel_siginfo
 		cl = aa_get_newest_cred_label(cred);
 		error = aa_may_signal(cred, cl, tc, tl, sig);
 		aa_put_label(cl);
-		return error;
 	} else {
 		cl = __begin_current_label_crit_section();
 		error = aa_may_signal(current_cred(), cl, tc, tl, sig);
@@ -1056,9 +1057,6 @@ static int apparmor_userns_create(const struct cred *cred)
 	return error;
 }
 
-/**
- * apparmor_sk_alloc_security - allocate and attach the sk_security field
- */
 static int apparmor_sk_alloc_security(struct sock *sk, int family, gfp_t flags)
 {
 	struct aa_sk_ctx *ctx;
@@ -1072,9 +1070,6 @@ static int apparmor_sk_alloc_security(struct sock *sk, int family, gfp_t flags)
 	return 0;
 }
 
-/**
- * apparmor_sk_free_security - free the sk_security field
- */
 static void apparmor_sk_free_security(struct sock *sk)
 {
 	struct aa_sk_ctx *ctx = aa_sock(sk);
@@ -1087,6 +1082,8 @@ static void apparmor_sk_free_security(struct sock *sk)
 
 /**
  * apparmor_sk_clone_security - clone the sk_security field
+ * @sk: sock to have security cloned
+ * @newsk: sock getting clone
  */
 static void apparmor_sk_clone_security(const struct sock *sk,
 				       struct sock *newsk)
@@ -1103,9 +1100,6 @@ static void apparmor_sk_clone_security(const struct sock *sk,
 	new->peer = aa_get_label(ctx->peer);
 }
 
-/**
- * apparmor_socket_create - check perms before creating a new socket
- */
 static int apparmor_socket_create(int family, int type, int protocol, int kern)
 {
 	struct aa_label *label;
@@ -1127,10 +1121,14 @@ static int apparmor_socket_create(int family, int type, int protocol, int kern)
 
 /**
  * apparmor_socket_post_create - setup the per-socket security struct
+ * @sock: socket that is being setup
+ * @family: family of socket being created
+ * @type: type of the socket
+ * @ptotocol: protocol of the socket
+ * @kern: socket is a special kernel socket
  *
  * Note:
- * -   kernel sockets currently labeled unconfined but we may want to
- *     move to a special kernel label
+ * -   kernel sockets labeled kernel_t used to use unconfined
  * -   socket may not have sk here if created with sock_create_lite or
  *     sock_alloc. These should be accept cases which will be handled in
  *     sock_graft.
@@ -1156,9 +1154,6 @@ static int apparmor_socket_post_create(struct socket *sock, int family,
 	return 0;
 }
 
-/**
- * apparmor_socket_bind - check perms before bind addr to socket
- */
 static int apparmor_socket_bind(struct socket *sock,
 				struct sockaddr *address, int addrlen)
 {
@@ -1172,9 +1167,6 @@ static int apparmor_socket_bind(struct socket *sock,
 			 aa_sk_perm(OP_BIND, AA_MAY_BIND, sock->sk));
 }
 
-/**
- * apparmor_socket_connect - check perms before connecting @sock to @address
- */
 static int apparmor_socket_connect(struct socket *sock,
 				   struct sockaddr *address, int addrlen)
 {
@@ -1188,9 +1180,6 @@ static int apparmor_socket_connect(struct socket *sock,
 			 aa_sk_perm(OP_CONNECT, AA_MAY_CONNECT, sock->sk));
 }
 
-/**
- * apparmor_socket_listen - check perms before allowing listen
- */
 static int apparmor_socket_listen(struct socket *sock, int backlog)
 {
 	AA_BUG(!sock);
@@ -1202,9 +1191,7 @@ static int apparmor_socket_listen(struct socket *sock, int backlog)
 			 aa_sk_perm(OP_LISTEN, AA_MAY_LISTEN, sock->sk));
 }
 
-/**
- * apparmor_socket_accept - check perms before accepting a new connection.
- *
+/*
  * Note: while @newsock is created and has some information, the accept
  *       has not been done.
  */
@@ -1233,18 +1220,12 @@ static int aa_sock_msg_perm(const char *op, u32 request, struct socket *sock,
 			 aa_sk_perm(op, request, sock->sk));
 }
 
-/**
- * apparmor_socket_sendmsg - check perms before sending msg to another socket
- */
 static int apparmor_socket_sendmsg(struct socket *sock,
 				   struct msghdr *msg, int size)
 {
 	return aa_sock_msg_perm(OP_SENDMSG, AA_MAY_SEND, sock, msg, size);
 }
 
-/**
- * apparmor_socket_recvmsg - check perms before receiving a message
- */
 static int apparmor_socket_recvmsg(struct socket *sock,
 				   struct msghdr *msg, int size, int flags)
 {
@@ -1263,17 +1244,11 @@ static int aa_sock_perm(const char *op, u32 request, struct socket *sock)
 			 aa_sk_perm(op, request, sock->sk));
 }
 
-/**
- * apparmor_socket_getsockname - check perms before getting the local address
- */
 static int apparmor_socket_getsockname(struct socket *sock)
 {
 	return aa_sock_perm(OP_GETSOCKNAME, AA_MAY_GETATTR, sock);
 }
 
-/**
- * apparmor_socket_getpeername - check perms before getting remote address
- */
 static int apparmor_socket_getpeername(struct socket *sock)
 {
 	return aa_sock_perm(OP_GETPEERNAME, AA_MAY_GETATTR, sock);
@@ -1292,9 +1267,6 @@ static int aa_sock_opt_perm(const char *op, u32 request, struct socket *sock,
 			 aa_sk_perm(op, request, sock->sk));
 }
 
-/**
- * apparmor_socket_getsockopt - check perms before getting socket options
- */
 static int apparmor_socket_getsockopt(struct socket *sock, int level,
 				      int optname)
 {
@@ -1302,9 +1274,6 @@ static int apparmor_socket_getsockopt(struct socket *sock, int level,
 				level, optname);
 }
 
-/**
- * apparmor_socket_setsockopt - check perms before setting socket options
- */
 static int apparmor_socket_setsockopt(struct socket *sock, int level,
 				      int optname)
 {
@@ -1312,9 +1281,6 @@ static int apparmor_socket_setsockopt(struct socket *sock, int level,
 				level, optname);
 }
 
-/**
- * apparmor_socket_shutdown - check perms before shutting down @sock conn
- */
 static int apparmor_socket_shutdown(struct socket *sock, int how)
 {
 	return aa_sock_perm(OP_SHUTDOWN, AA_MAY_SHUTDOWN, sock);
@@ -1323,6 +1289,8 @@ static int apparmor_socket_shutdown(struct socket *sock, int how)
 #ifdef CONFIG_NETWORK_SECMARK
 /**
  * apparmor_socket_sock_rcv_skb - check perms before associating skb to sk
+ * @sk: sk to associate @skb with
+ * @skb: skb to check for perms
  *
  * Note: can not sleep may be called with locks held
  *
@@ -1354,6 +1322,11 @@ static struct aa_label *sk_peer_label(struct sock *sk)
 
 /**
  * apparmor_socket_getpeersec_stream - get security context of peer
+ * @sock: socket that we are trying to get the peer context of
+ * @optval: output - buffer to copy peer name to
+ * @optlen: output - size of copied name in @optval
+ * @len: size of @optval buffer
+ * Returns: 0 on success, -errno of failure
  *
  * Note: for tcp only valid if using ipsec or cipso on lan
  */
@@ -2182,7 +2155,7 @@ __initcall(apparmor_nf_ip_init);
 static char nulldfa_src[] = {
 	#include "nulldfa.in"
 };
-struct aa_dfa *nulldfa;
+static struct aa_dfa *nulldfa;
 
 static char stacksplitdfa_src[] = {
 	#include "stacksplitdfa.in"
diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
index ed4c9803c8fa..957654d253dd 100644
--- a/security/apparmor/policy.c
+++ b/security/apparmor/policy.c
@@ -99,13 +99,14 @@ const char *const aa_profile_mode_names[] = {
 };
 
 
-static void aa_free_pdb(struct aa_policydb *policy)
+static void aa_free_pdb(struct aa_policydb *pdb)
 {
-	if (policy) {
-		aa_put_dfa(policy->dfa);
-		if (policy->perms)
-			kvfree(policy->perms);
-		aa_free_str_table(&policy->trans);
+	if (pdb) {
+		aa_put_dfa(pdb->dfa);
+		if (pdb->perms)
+			kvfree(pdb->perms);
+		aa_free_str_table(&pdb->trans);
+		kfree(pdb);
 	}
 }
 
diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
index 47ec097d6741..5e578ef0ddff 100644
--- a/security/apparmor/policy_unpack.c
+++ b/security/apparmor/policy_unpack.c
@@ -478,6 +478,8 @@ static bool unpack_trans_table(struct aa_ext *e, struct aa_str_table *strs)
 		if (!table)
 			goto fail;
 
+		strs->table = table;
+		strs->size = size;
 		for (i = 0; i < size; i++) {
 			char *str;
 			int c, j, pos, size2 = aa_unpack_strdup(e, &str, NULL);
@@ -520,14 +522,11 @@ static bool unpack_trans_table(struct aa_ext *e, struct aa_str_table *strs)
 			goto fail;
 		if (!aa_unpack_nameX(e, AA_STRUCTEND, NULL))
 			goto fail;
-
-		strs->table = table;
-		strs->size = size;
 	}
 	return true;
 
 fail:
-	kfree_sensitive(table);
+	aa_free_str_table(strs);
 	e->pos = saved_pos;
 	return false;
 }
@@ -833,6 +832,10 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name)
 
 	tmpname = aa_splitn_fqname(name, strlen(name), &tmpns, &ns_len);
 	if (tmpns) {
+		if (!tmpname) {
+			info = "empty profile name";
+			goto fail;
+		}
 		*ns_name = kstrndup(tmpns, ns_len, GFP_KERNEL);
 		if (!*ns_name) {
 			info = "out of memory";
@@ -1022,8 +1025,10 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name)
 		}
 	} else if (rules->policy->dfa &&
 		   rules->policy->start[AA_CLASS_FILE]) {
+		aa_put_pdb(rules->file);
 		rules->file = aa_get_pdb(rules->policy);
 	} else {
+		aa_put_pdb(rules->file);
 		rules->file = aa_get_pdb(nullpdb);
 	}
 	error = -EPROTO;
diff --git a/security/apparmor/task.c b/security/apparmor/task.c
index f29a2e80e6bf..c87fb9f4ac18 100644
--- a/security/apparmor/task.c
+++ b/security/apparmor/task.c
@@ -278,7 +278,9 @@ static int profile_tracer_perm(const struct cred *cred,
 
 /**
  * aa_may_ptrace - test if tracer task can trace the tracee
+ * @tracer_cred: cred of task doing the tracing  (NOT NULL)
  * @tracer: label of the task doing the tracing  (NOT NULL)
+ * @tracee_cred: cred of task to be traced
  * @tracee: task label to be traced
  * @request: permission request
  *
diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c
index df387de29bfa..45c3e5dda355 100644
--- a/security/integrity/digsig.c
+++ b/security/integrity/digsig.c
@@ -179,7 +179,8 @@ static int __init integrity_add_key(const unsigned int id, const void *data,
 				   KEY_ALLOC_NOT_IN_QUOTA);
 	if (IS_ERR(key)) {
 		rc = PTR_ERR(key);
-		pr_err("Problem loading X.509 certificate %d\n", rc);
+		if (id != INTEGRITY_KEYRING_MACHINE)
+			pr_err("Problem loading X.509 certificate %d\n", rc);
 	} else {
 		pr_notice("Loaded X.509 cert '%s'\n",
 			  key_ref_to_ptr(key)->description);
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index 76f55dd13cb8..8af2136069d2 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -237,10 +237,6 @@ static int datablob_parse(char *datablob, const char **format,
 			break;
 		}
 		*decrypted_data = strsep(&datablob, " \t");
-		if (!*decrypted_data) {
-			pr_info("encrypted_key: decrypted_data is missing\n");
-			break;
-		}
 		ret = 0;
 		break;
 	case Opt_load:
diff --git a/security/landlock/fs.c b/security/landlock/fs.c
index fc520a06f9af..0171f7eb6ee1 100644
--- a/security/landlock/fs.c
+++ b/security/landlock/fs.c
@@ -737,8 +737,8 @@ static int current_check_refer_path(struct dentry *const old_dentry,
 	bool allow_parent1, allow_parent2;
 	access_mask_t access_request_parent1, access_request_parent2;
 	struct path mnt_dir;
-	layer_mask_t layer_masks_parent1[LANDLOCK_NUM_ACCESS_FS],
-		layer_masks_parent2[LANDLOCK_NUM_ACCESS_FS];
+	layer_mask_t layer_masks_parent1[LANDLOCK_NUM_ACCESS_FS] = {},
+		     layer_masks_parent2[LANDLOCK_NUM_ACCESS_FS] = {};
 
 	if (!dom)
 		return 0;
diff --git a/security/security.c b/security/security.c
index 0144a98d3712..7035ee35a393 100644
--- a/security/security.c
+++ b/security/security.c
@@ -29,6 +29,7 @@
 #include <linux/backing-dev.h>
 #include <linux/string.h>
 #include <linux/msg.h>
+#include <linux/overflow.h>
 #include <net/flow.h>
 
 /* How many LSMs were built into the kernel? */
@@ -4015,6 +4016,7 @@ int security_setselfattr(unsigned int attr, struct lsm_ctx __user *uctx,
 	struct security_hook_list *hp;
 	struct lsm_ctx *lctx;
 	int rc = LSM_RET_DEFAULT(setselfattr);
+	u64 required_len;
 
 	if (flags)
 		return -EINVAL;
@@ -4027,8 +4029,9 @@ int security_setselfattr(unsigned int attr, struct lsm_ctx __user *uctx,
 	if (IS_ERR(lctx))
 		return PTR_ERR(lctx);
 
-	if (size < lctx->len || size < lctx->ctx_len + sizeof(*lctx) ||
-	    lctx->len < lctx->ctx_len + sizeof(*lctx)) {
+	if (size < lctx->len ||
+	    check_add_overflow(sizeof(*lctx), lctx->ctx_len, &required_len) ||
+	    lctx->len < required_len) {
 		rc = -EINVAL;
 		goto free_out;
 	}
@@ -4255,7 +4258,19 @@ EXPORT_SYMBOL(security_inode_setsecctx);
  */
 int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen)
 {
-	return call_int_hook(inode_getsecctx, -EOPNOTSUPP, inode, ctx, ctxlen);
+	struct security_hook_list *hp;
+	int rc;
+
+	/*
+	 * Only one module will provide a security context.
+	 */
+	hlist_for_each_entry(hp, &security_hook_heads.inode_getsecctx, list) {
+		rc = hp->hook.inode_getsecctx(inode, ctx, ctxlen);
+		if (rc != LSM_RET_DEFAULT(inode_getsecctx))
+			return rc;
+	}
+
+	return LSM_RET_DEFAULT(inode_getsecctx);
 }
 EXPORT_SYMBOL(security_inode_getsecctx);
 
@@ -4612,8 +4627,20 @@ EXPORT_SYMBOL(security_sock_rcv_skb);
 int security_socket_getpeersec_stream(struct socket *sock, sockptr_t optval,
 				      sockptr_t optlen, unsigned int len)
 {
-	return call_int_hook(socket_getpeersec_stream, -ENOPROTOOPT, sock,
-			     optval, optlen, len);
+	struct security_hook_list *hp;
+	int rc;
+
+	/*
+	 * Only one module will provide a security context.
+	 */
+	hlist_for_each_entry(hp, &security_hook_heads.socket_getpeersec_stream,
+			     list) {
+		rc = hp->hook.socket_getpeersec_stream(sock, optval, optlen,
+						       len);
+		if (rc != LSM_RET_DEFAULT(socket_getpeersec_stream))
+			return rc;
+	}
+	return LSM_RET_DEFAULT(socket_getpeersec_stream);
 }
 
 /**
@@ -4633,8 +4660,19 @@ int security_socket_getpeersec_stream(struct socket *sock, sockptr_t optval,
 int security_socket_getpeersec_dgram(struct socket *sock,
 				     struct sk_buff *skb, u32 *secid)
 {
-	return call_int_hook(socket_getpeersec_dgram, -ENOPROTOOPT, sock,
-			     skb, secid);
+	struct security_hook_list *hp;
+	int rc;
+
+	/*
+	 * Only one module will provide a security context.
+	 */
+	hlist_for_each_entry(hp, &security_hook_heads.socket_getpeersec_dgram,
+			     list) {
+		rc = hp->hook.socket_getpeersec_dgram(sock, skb, secid);
+		if (rc != LSM_RET_DEFAULT(socket_getpeersec_dgram))
+			return rc;
+	}
+	return LSM_RET_DEFAULT(socket_getpeersec_dgram);
 }
 EXPORT_SYMBOL(security_socket_getpeersec_dgram);
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index a6bf90ace84c..338b023a8c3e 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -6559,7 +6559,7 @@ static int selinux_getselfattr(unsigned int attr, struct lsm_ctx __user *ctx,
 			       size_t *size, u32 flags)
 {
 	int rc;
-	char *val;
+	char *val = NULL;
 	int val_len;
 
 	val_len = selinux_lsm_getattr(attr, current, &val);
diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c
index 57ee70ae50f2..ea3140d510ec 100644
--- a/security/tomoyo/common.c
+++ b/security/tomoyo/common.c
@@ -2649,13 +2649,14 @@ ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head,
 {
 	int error = buffer_len;
 	size_t avail_len = buffer_len;
-	char *cp0 = head->write_buf;
+	char *cp0;
 	int idx;
 
 	if (!head->write)
 		return -EINVAL;
 	if (mutex_lock_interruptible(&head->io_sem))
 		return -EINTR;
+	cp0 = head->write_buf;
 	head->read_user_buf_avail = 0;
 	idx = tomoyo_read_lock();
 	/* Read a line and dispatch it to the policy handler. */
diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c
index 3c3af149bf1c..04a92c3d65d4 100644
--- a/security/tomoyo/tomoyo.c
+++ b/security/tomoyo/tomoyo.c
@@ -328,7 +328,8 @@ static int tomoyo_file_fcntl(struct file *file, unsigned int cmd,
 static int tomoyo_file_open(struct file *f)
 {
 	/* Don't check read permission here if called from execve(). */
-	if (current->in_execve)
+	/* Illogically, FMODE_EXEC is in f_flags, not f_mode. */
+	if (f->f_flags & __FMODE_EXEC)
 		return 0;
 	return tomoyo_check_open_permission(tomoyo_domain(), &f->f_path,
 					    f->f_flags);
diff --git a/sound/core/Makefile b/sound/core/Makefile
index a6b444ee2832..f6526b337137 100644
--- a/sound/core/Makefile
+++ b/sound/core/Makefile
@@ -32,7 +32,6 @@ snd-ump-objs      := ump.o
 snd-ump-$(CONFIG_SND_UMP_LEGACY_RAWMIDI) += ump_convert.o
 snd-timer-objs    := timer.o
 snd-hrtimer-objs  := hrtimer.o
-snd-rtctimer-objs := rtctimer.o
 snd-hwdep-objs    := hwdep.o
 snd-seq-device-objs := seq_device.o
 
diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index a09f0154e6a7..d0788126cbab 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -211,6 +211,10 @@ static const char * const snd_pcm_format_names[] = {
 	FORMAT(DSD_U32_LE),
 	FORMAT(DSD_U16_BE),
 	FORMAT(DSD_U32_BE),
+	FORMAT(S20_LE),
+	FORMAT(S20_BE),
+	FORMAT(U20_LE),
+	FORMAT(U20_BE),
 };
 
 /**
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index f5ff00f99788..21baf6bf7e25 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -486,6 +486,11 @@ static int fixup_unreferenced_params(struct snd_pcm_substream *substream,
 		i = hw_param_interval_c(params, SNDRV_PCM_HW_PARAM_SAMPLE_BITS);
 		if (snd_interval_single(i))
 			params->msbits = snd_interval_value(i);
+		m = hw_param_mask_c(params, SNDRV_PCM_HW_PARAM_FORMAT);
+		if (snd_mask_single(m)) {
+			snd_pcm_format_t format = (__force snd_pcm_format_t)snd_mask_min(m);
+			params->msbits = snd_pcm_format_width(format);
+		}
 	}
 
 	if (params->msbits) {
diff --git a/sound/core/ump.c b/sound/core/ump.c
index 3bef1944e955..fe7911498cc4 100644
--- a/sound/core/ump.c
+++ b/sound/core/ump.c
@@ -985,7 +985,7 @@ static int snd_ump_legacy_open(struct snd_rawmidi_substream *substream)
 	struct snd_ump_endpoint *ump = substream->rmidi->private_data;
 	int dir = substream->stream;
 	int group = ump->legacy_mapping[substream->number];
-	int err;
+	int err = 0;
 
 	mutex_lock(&ump->open_mutex);
 	if (ump->legacy_substreams[dir][group]) {
@@ -1009,7 +1009,7 @@ static int snd_ump_legacy_open(struct snd_rawmidi_substream *substream)
 	spin_unlock_irq(&ump->legacy_locks[dir]);
  unlock:
 	mutex_unlock(&ump->open_mutex);
-	return 0;
+	return err;
 }
 
 static int snd_ump_legacy_close(struct snd_rawmidi_substream *substream)
diff --git a/sound/drivers/aloop.c b/sound/drivers/aloop.c
index e87dc67f33c6..1c65e0a3b13c 100644
--- a/sound/drivers/aloop.c
+++ b/sound/drivers/aloop.c
@@ -322,6 +322,17 @@ static int loopback_snd_timer_close_cable(struct loopback_pcm *dpcm)
 	return 0;
 }
 
+static bool is_access_interleaved(snd_pcm_access_t access)
+{
+	switch (access) {
+	case SNDRV_PCM_ACCESS_MMAP_INTERLEAVED:
+	case SNDRV_PCM_ACCESS_RW_INTERLEAVED:
+		return true;
+	default:
+		return false;
+	}
+};
+
 static int loopback_check_format(struct loopback_cable *cable, int stream)
 {
 	struct snd_pcm_runtime *runtime, *cruntime;
@@ -341,7 +352,8 @@ static int loopback_check_format(struct loopback_cable *cable, int stream)
 	check = runtime->format != cruntime->format ||
 		runtime->rate != cruntime->rate ||
 		runtime->channels != cruntime->channels ||
-		runtime->access != cruntime->access;
+		is_access_interleaved(runtime->access) !=
+		is_access_interleaved(cruntime->access);
 	if (!check)
 		return 0;
 	if (stream == SNDRV_PCM_STREAM_CAPTURE) {
@@ -369,7 +381,8 @@ static int loopback_check_format(struct loopback_cable *cable, int stream)
 							&setup->channels_id);
 			setup->channels = runtime->channels;
 		}
-		if (setup->access != runtime->access) {
+		if (is_access_interleaved(setup->access) !=
+		    is_access_interleaved(runtime->access)) {
 			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE,
 							&setup->access_id);
 			setup->access = runtime->access;
@@ -584,8 +597,7 @@ static void copy_play_buf(struct loopback_pcm *play,
 			size = play->pcm_buffer_size - src_off;
 		if (dst_off + size > capt->pcm_buffer_size)
 			size = capt->pcm_buffer_size - dst_off;
-		if (runtime->access == SNDRV_PCM_ACCESS_RW_NONINTERLEAVED ||
-		    runtime->access == SNDRV_PCM_ACCESS_MMAP_NONINTERLEAVED)
+		if (!is_access_interleaved(runtime->access))
 			copy_play_buf_part_n(play, capt, size, src_off, dst_off);
 		else
 			memcpy(dst + dst_off, src + src_off, size);
@@ -1544,8 +1556,7 @@ static int loopback_access_get(struct snd_kcontrol *kcontrol,
 	mutex_lock(&loopback->cable_lock);
 	access = loopback->setup[kcontrol->id.subdevice][kcontrol->id.device].access;
 
-	ucontrol->value.enumerated.item[0] = access == SNDRV_PCM_ACCESS_RW_NONINTERLEAVED ||
-					     access == SNDRV_PCM_ACCESS_MMAP_NONINTERLEAVED;
+	ucontrol->value.enumerated.item[0] = !is_access_interleaved(access);
 
 	mutex_unlock(&loopback->cable_lock);
 	return 0;
diff --git a/sound/drivers/serial-generic.c b/sound/drivers/serial-generic.c
index c8db6c75d133..d6e5aafd697c 100644
--- a/sound/drivers/serial-generic.c
+++ b/sound/drivers/serial-generic.c
@@ -100,8 +100,8 @@ static void snd_serial_generic_write_wakeup(struct serdev_device *serdev)
 	snd_serial_generic_tx_wakeup(drvdata);
 }
 
-static int snd_serial_generic_receive_buf(struct serdev_device *serdev,
-				const unsigned char *buf, size_t count)
+static ssize_t snd_serial_generic_receive_buf(struct serdev_device *serdev,
+					      const u8 *buf, size_t count)
 {
 	int ret;
 	struct snd_serial_generic *drvdata = serdev_device_get_drvdata(serdev);
diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c
index a13c0b408aad..7be17bca257f 100644
--- a/sound/firewire/amdtp-stream.c
+++ b/sound/firewire/amdtp-stream.c
@@ -951,7 +951,7 @@ static int generate_tx_packet_descs(struct amdtp_stream *s, struct pkt_desc *des
 				// to the reason.
 				unsigned int safe_cycle = increment_ohci_cycle_count(next_cycle,
 								IR_JUMBO_PAYLOAD_MAX_SKIP_CYCLES);
-				lost = (compare_ohci_cycle_count(safe_cycle, cycle) > 0);
+				lost = (compare_ohci_cycle_count(safe_cycle, cycle) < 0);
 			}
 			if (lost) {
 				dev_err(&s->unit->device, "Detect discontinuity of cycle: %d %d\n",
diff --git a/sound/pci/hda/Kconfig b/sound/pci/hda/Kconfig
index 21a90b3c4cc7..8e0ff70fb610 100644
--- a/sound/pci/hda/Kconfig
+++ b/sound/pci/hda/Kconfig
@@ -156,7 +156,7 @@ config SND_HDA_SCODEC_CS35L56_I2C
 	depends on I2C
 	depends on ACPI || COMPILE_TEST
 	depends on SND_SOC
-	select CS_DSP
+	select FW_CS_DSP
 	select SND_HDA_GENERIC
 	select SND_SOC_CS35L56_SHARED
 	select SND_HDA_SCODEC_CS35L56
@@ -171,7 +171,7 @@ config SND_HDA_SCODEC_CS35L56_SPI
 	depends on SPI_MASTER
 	depends on ACPI || COMPILE_TEST
 	depends on SND_SOC
-	select CS_DSP
+	select FW_CS_DSP
 	select SND_HDA_GENERIC
 	select SND_SOC_CS35L56_SHARED
 	select SND_HDA_SCODEC_CS35L56
diff --git a/sound/pci/hda/cs35l41_hda_property.c b/sound/pci/hda/cs35l41_hda_property.c
index 35277ce890a4..e436d4dab317 100644
--- a/sound/pci/hda/cs35l41_hda_property.c
+++ b/sound/pci/hda/cs35l41_hda_property.c
@@ -76,11 +76,14 @@ static const struct cs35l41_config cs35l41_config_table[] = {
 	{ "10431533", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
 	{ "10431573", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
 	{ "10431663", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 1000, 4500, 24 },
+	{ "10431683", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
+	{ "104316A3", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
 	{ "104316D3", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
 	{ "104316F3", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
 	{ "104317F3", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
 	{ "10431863", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
 	{ "104318D3", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
+	{ "10431A83", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
 	{ "10431C9F", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
 	{ "10431CAF", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
 	{ "10431CCF", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
@@ -89,10 +92,14 @@ static const struct cs35l41_config cs35l41_config_table[] = {
 	{ "10431D1F", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
 	{ "10431DA2", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
 	{ "10431E02", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
+	{ "10431E12", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
 	{ "10431EE2", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, -1, -1, 0, 0, 0 },
 	{ "10431F12", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
 	{ "10431F1F", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 0, 0, 0 },
 	{ "10431F62", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
+	{ "17AA386F", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, -1, -1, 0, 0, 0 },
+	{ "17AA38A9", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 2, -1, 0, 0, 0 },
+	{ "17AA38AB", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 2, -1, 0, 0, 0 },
 	{ "17AA38B4", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
 	{ "17AA38B5", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
 	{ "17AA38B6", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
@@ -410,11 +417,14 @@ static const struct cs35l41_prop_model cs35l41_prop_model_table[] = {
 	{ "CSC3551", "10431533", generic_dsd_config },
 	{ "CSC3551", "10431573", generic_dsd_config },
 	{ "CSC3551", "10431663", generic_dsd_config },
+	{ "CSC3551", "10431683", generic_dsd_config },
+	{ "CSC3551", "104316A3", generic_dsd_config },
 	{ "CSC3551", "104316D3", generic_dsd_config },
 	{ "CSC3551", "104316F3", generic_dsd_config },
 	{ "CSC3551", "104317F3", generic_dsd_config },
 	{ "CSC3551", "10431863", generic_dsd_config },
 	{ "CSC3551", "104318D3", generic_dsd_config },
+	{ "CSC3551", "10431A83", generic_dsd_config },
 	{ "CSC3551", "10431C9F", generic_dsd_config },
 	{ "CSC3551", "10431CAF", generic_dsd_config },
 	{ "CSC3551", "10431CCF", generic_dsd_config },
@@ -423,10 +433,14 @@ static const struct cs35l41_prop_model cs35l41_prop_model_table[] = {
 	{ "CSC3551", "10431D1F", generic_dsd_config },
 	{ "CSC3551", "10431DA2", generic_dsd_config },
 	{ "CSC3551", "10431E02", generic_dsd_config },
+	{ "CSC3551", "10431E12", generic_dsd_config },
 	{ "CSC3551", "10431EE2", generic_dsd_config },
 	{ "CSC3551", "10431F12", generic_dsd_config },
 	{ "CSC3551", "10431F1F", generic_dsd_config },
 	{ "CSC3551", "10431F62", generic_dsd_config },
+	{ "CSC3551", "17AA386F", generic_dsd_config },
+	{ "CSC3551", "17AA38A9", generic_dsd_config },
+	{ "CSC3551", "17AA38AB", generic_dsd_config },
 	{ "CSC3551", "17AA38B4", generic_dsd_config },
 	{ "CSC3551", "17AA38B5", generic_dsd_config },
 	{ "CSC3551", "17AA38B6", generic_dsd_config },
diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c
index b61e1de8c4bf..75a14ba54fcd 100644
--- a/sound/pci/hda/cs35l56_hda.c
+++ b/sound/pci/hda/cs35l56_hda.c
@@ -30,14 +30,23 @@
   *  ASP1_RX_WL = 24 bits per sample
   *  ASP1_TX_WL = 24 bits per sample
   *  ASP1_RXn_EN 1..3 and ASP1_TXn_EN 1..4 disabled
+  *
+  * Override any Windows-specific mixer settings applied by the firmware.
   */
 static const struct reg_sequence cs35l56_hda_dai_config[] = {
 	{ CS35L56_ASP1_CONTROL1,	0x00000021 },
 	{ CS35L56_ASP1_CONTROL2,	0x20200200 },
 	{ CS35L56_ASP1_CONTROL3,	0x00000003 },
+	{ CS35L56_ASP1_FRAME_CONTROL1,	0x03020100 },
+	{ CS35L56_ASP1_FRAME_CONTROL5,	0x00020100 },
 	{ CS35L56_ASP1_DATA_CONTROL5,	0x00000018 },
 	{ CS35L56_ASP1_DATA_CONTROL1,	0x00000018 },
 	{ CS35L56_ASP1_ENABLES1,	0x00000000 },
+	{ CS35L56_ASP1TX1_INPUT,	0x00000018 },
+	{ CS35L56_ASP1TX2_INPUT,	0x00000019 },
+	{ CS35L56_ASP1TX3_INPUT,	0x00000020 },
+	{ CS35L56_ASP1TX4_INPUT,	0x00000028 },
+
 };
 
 static void cs35l56_hda_play(struct cs35l56_hda *cs35l56)
@@ -133,6 +142,10 @@ static int cs35l56_hda_runtime_resume(struct device *dev)
 		}
 	}
 
+	ret = cs35l56_force_sync_asp1_registers_from_cache(&cs35l56->base);
+	if (ret)
+		goto err;
+
 	return 0;
 
 err:
@@ -384,7 +397,7 @@ static const struct cs_dsp_client_ops cs35l56_hda_client_ops = {
 
 static int cs35l56_hda_request_firmware_file(struct cs35l56_hda *cs35l56,
 					     const struct firmware **firmware, char **filename,
-					     const char *dir, const char *system_name,
+					     const char *base_name, const char *system_name,
 					     const char *amp_name,
 					     const char *filetype)
 {
@@ -392,17 +405,13 @@ static int cs35l56_hda_request_firmware_file(struct cs35l56_hda *cs35l56,
 	int ret = 0;
 
 	if (system_name && amp_name)
-		*filename = kasprintf(GFP_KERNEL, "%scs35l56%s-%02x-dsp1-misc-%s-%s.%s", dir,
-				      cs35l56->base.secured ? "s" : "", cs35l56->base.rev,
+		*filename = kasprintf(GFP_KERNEL, "%s-%s-%s.%s", base_name,
 				      system_name, amp_name, filetype);
 	else if (system_name)
-		*filename = kasprintf(GFP_KERNEL, "%scs35l56%s-%02x-dsp1-misc-%s.%s", dir,
-				      cs35l56->base.secured ? "s" : "", cs35l56->base.rev,
+		*filename = kasprintf(GFP_KERNEL, "%s-%s.%s", base_name,
 				      system_name, filetype);
 	else
-		*filename = kasprintf(GFP_KERNEL, "%scs35l56%s-%02x-dsp1-misc.%s", dir,
-				      cs35l56->base.secured ? "s" : "", cs35l56->base.rev,
-				      filetype);
+		*filename = kasprintf(GFP_KERNEL, "%s.%s", base_name, filetype);
 
 	if (!*filename)
 		return -ENOMEM;
@@ -435,8 +444,8 @@ static int cs35l56_hda_request_firmware_file(struct cs35l56_hda *cs35l56,
 	return 0;
 }
 
-static const char cirrus_dir[] = "cirrus/";
 static void cs35l56_hda_request_firmware_files(struct cs35l56_hda *cs35l56,
+					       unsigned int preloaded_fw_ver,
 					       const struct firmware **wmfw_firmware,
 					       char **wmfw_filename,
 					       const struct firmware **coeff_firmware,
@@ -444,55 +453,73 @@ static void cs35l56_hda_request_firmware_files(struct cs35l56_hda *cs35l56,
 {
 	const char *system_name = cs35l56->system_name;
 	const char *amp_name = cs35l56->amp_name;
+	char base_name[37];
 	int ret;
 
+	if (preloaded_fw_ver) {
+		snprintf(base_name, sizeof(base_name),
+			 "cirrus/cs35l56-%02x%s-%06x-dsp1-misc",
+			 cs35l56->base.rev,
+			 cs35l56->base.secured ? "-s" : "",
+			 preloaded_fw_ver & 0xffffff);
+	} else {
+		snprintf(base_name, sizeof(base_name),
+			 "cirrus/cs35l56-%02x%s-dsp1-misc",
+			 cs35l56->base.rev,
+			 cs35l56->base.secured ? "-s" : "");
+	}
+
 	if (system_name && amp_name) {
 		if (!cs35l56_hda_request_firmware_file(cs35l56, wmfw_firmware, wmfw_filename,
-						       cirrus_dir, system_name, amp_name, "wmfw")) {
+						       base_name, system_name, amp_name, "wmfw")) {
 			cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
-							  cirrus_dir, system_name, amp_name, "bin");
+							  base_name, system_name, amp_name, "bin");
 			return;
 		}
 	}
 
 	if (system_name) {
 		if (!cs35l56_hda_request_firmware_file(cs35l56, wmfw_firmware, wmfw_filename,
-						       cirrus_dir, system_name, NULL, "wmfw")) {
+						       base_name, system_name, NULL, "wmfw")) {
 			if (amp_name)
 				cs35l56_hda_request_firmware_file(cs35l56,
 								  coeff_firmware, coeff_filename,
-								  cirrus_dir, system_name,
+								  base_name, system_name,
 								  amp_name, "bin");
 			if (!*coeff_firmware)
 				cs35l56_hda_request_firmware_file(cs35l56,
 								  coeff_firmware, coeff_filename,
-								  cirrus_dir, system_name,
+								  base_name, system_name,
 								  NULL, "bin");
 			return;
 		}
+
+		/*
+		 * Check for system-specific bin files without wmfw before
+		 * falling back to generic firmware
+		 */
+		if (amp_name)
+			cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
+							  base_name, system_name, amp_name, "bin");
+		if (!*coeff_firmware)
+			cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
+							  base_name, system_name, NULL, "bin");
+
+		if (*coeff_firmware)
+			return;
 	}
 
 	ret = cs35l56_hda_request_firmware_file(cs35l56, wmfw_firmware, wmfw_filename,
-						cirrus_dir, NULL, NULL, "wmfw");
+						base_name, NULL, NULL, "wmfw");
 	if (!ret) {
 		cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
-						  cirrus_dir, NULL, NULL, "bin");
+						  base_name, NULL, NULL, "bin");
 		return;
 	}
 
-	/* When a firmware file is not found must still search for the coeff files */
-	if (system_name) {
-		if (amp_name)
-			cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
-							  cirrus_dir, system_name, amp_name, "bin");
-		if (!*coeff_firmware)
-			cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
-							  cirrus_dir, system_name, NULL, "bin");
-	}
-
 	if (!*coeff_firmware)
 		cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
-						  cirrus_dir, NULL, NULL, "bin");
+						  base_name, NULL, NULL, "bin");
 }
 
 static void cs35l56_hda_release_firmware_files(const struct firmware *wmfw_firmware,
@@ -526,7 +553,8 @@ static int cs35l56_hda_fw_load(struct cs35l56_hda *cs35l56)
 	const struct firmware *wmfw_firmware = NULL;
 	char *coeff_filename = NULL;
 	char *wmfw_filename = NULL;
-	unsigned int firmware_missing;
+	unsigned int preloaded_fw_ver;
+	bool firmware_missing;
 	int ret = 0;
 
 	/* Prepare for a new DSP power-up */
@@ -537,24 +565,21 @@ static int cs35l56_hda_fw_load(struct cs35l56_hda *cs35l56)
 
 	pm_runtime_get_sync(cs35l56->base.dev);
 
-	ret = regmap_read(cs35l56->base.regmap, CS35L56_PROTECTION_STATUS, &firmware_missing);
-	if (ret) {
-		dev_err(cs35l56->base.dev, "Failed to read PROTECTION_STATUS: %d\n", ret);
+	/*
+	 * The firmware can only be upgraded if it is currently running
+	 * from the built-in ROM. If not, the wmfw/bin must be for the
+	 * version of firmware that is running on the chip.
+	 */
+	ret = cs35l56_read_prot_status(&cs35l56->base, &firmware_missing, &preloaded_fw_ver);
+	if (ret)
 		goto err_pm_put;
-	}
 
-	firmware_missing &= CS35L56_FIRMWARE_MISSING;
+	if (firmware_missing)
+		preloaded_fw_ver = 0;
 
-	/*
-	 * Firmware can only be downloaded if the CS35L56 is secured or is
-	 * running from the built-in ROM. If it is secured the BIOS will have
-	 * downloaded firmware, and the wmfw/bin files will only contain
-	 * tunings that are safe to download with the firmware running.
-	 */
-	if (cs35l56->base.secured || firmware_missing) {
-		cs35l56_hda_request_firmware_files(cs35l56, &wmfw_firmware, &wmfw_filename,
-						   &coeff_firmware, &coeff_filename);
-	}
+	cs35l56_hda_request_firmware_files(cs35l56, preloaded_fw_ver,
+					   &wmfw_firmware, &wmfw_filename,
+					   &coeff_firmware, &coeff_filename);
 
 	/*
 	 * If the BIOS didn't patch the firmware a bin file is mandatory to
@@ -569,12 +594,12 @@ static int cs35l56_hda_fw_load(struct cs35l56_hda *cs35l56)
 	mutex_lock(&cs35l56->base.irq_lock);
 
 	/*
-	 * When the device is running in secure mode the firmware files can
-	 * only contain insecure tunings and therefore we do not need to
-	 * shutdown the firmware to apply them and can use the lower cost
-	 * reinit sequence instead.
+	 * If the firmware hasn't been patched it must be shutdown before
+	 * doing a full patch and reset afterwards. If it is already
+	 * running a patched version the firmware files only contain
+	 * tunings and we can use the lower cost reinit sequence instead.
 	 */
-	if (!cs35l56->base.secured && (wmfw_firmware || coeff_firmware)) {
+	if (firmware_missing && (wmfw_firmware || coeff_firmware)) {
 		ret = cs35l56_firmware_shutdown(&cs35l56->base);
 		if (ret)
 			goto err;
@@ -593,7 +618,7 @@ static int cs35l56_hda_fw_load(struct cs35l56_hda *cs35l56)
 	if (coeff_filename)
 		dev_dbg(cs35l56->base.dev, "Loaded Coefficients: %s\n", coeff_filename);
 
-	if (cs35l56->base.secured) {
+	if (!firmware_missing) {
 		ret = cs35l56_mbox_send(&cs35l56->base, CS35L56_MBOX_CMD_AUDIO_REINIT);
 		if (ret)
 			goto err_powered_up;
@@ -976,6 +1001,9 @@ int cs35l56_hda_common_probe(struct cs35l56_hda *cs35l56, int id)
 
 	regmap_multi_reg_write(cs35l56->base.regmap, cs35l56_hda_dai_config,
 			       ARRAY_SIZE(cs35l56_hda_dai_config));
+	ret = cs35l56_force_sync_asp1_registers_from_cache(&cs35l56->base);
+	if (ret)
+		goto err;
 
 	/*
 	 * By default only enable one ASP1TXn, where n=amplifier index,
@@ -1035,16 +1063,6 @@ const struct dev_pm_ops cs35l56_hda_pm_ops = {
 };
 EXPORT_SYMBOL_NS_GPL(cs35l56_hda_pm_ops, SND_HDA_SCODEC_CS35L56);
 
-#if IS_ENABLED(CONFIG_SND_HDA_SCODEC_CS35L56_KUNIT_TEST)
-/* Hooks to export static function to KUnit test */
-
-int cs35l56_hda_test_hook_get_speaker_id(struct device *dev, int amp_index, int num_amps)
-{
-	return cs35l56_hda_get_speaker_id(dev, amp_index, num_amps);
-}
-EXPORT_SYMBOL_NS_GPL(cs35l56_hda_test_hook_get_speaker_id, SND_HDA_SCODEC_CS35L56);
-#endif
-
 MODULE_DESCRIPTION("CS35L56 HDA Driver");
 MODULE_IMPORT_NS(SND_HDA_CIRRUS_SCODEC);
 MODULE_IMPORT_NS(SND_HDA_CS_DSP_CONTROLS);
diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c
index 3e7bfeee84fd..efe98f6f19a3 100644
--- a/sound/pci/hda/hda_controller.c
+++ b/sound/pci/hda/hda_controller.c
@@ -1207,6 +1207,9 @@ int azx_probe_codecs(struct azx *chip, unsigned int max_slots)
 				dev_warn(chip->card->dev,
 					 "Codec #%d probe error; disabling it...\n", c);
 				bus->codec_mask &= ~(1 << c);
+				/* no codecs */
+				if (bus->codec_mask == 0)
+					break;
 				/* More badly, accessing to a non-existing
 				 * codec often screws up the controller chip,
 				 * and disturbs the further communications.
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index bf685d01259d..de2a3d08c73c 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -3946,7 +3946,6 @@ static int create_mute_led_cdev(struct hda_codec *codec,
 	cdev->max_brightness = 1;
 	cdev->default_trigger = micmute ? "audio-micmute" : "audio-mute";
 	cdev->brightness_set_blocking = callback;
-	cdev->brightness = ledtrig_audio_get(idx);
 	cdev->flags = LED_CORE_SUSPENDRESUME;
 
 	err = led_classdev_register(&codec->core.dev, cdev);
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 2276adc84478..1b550c42db09 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1729,9 +1729,11 @@ static int default_bdl_pos_adj(struct azx *chip)
 	/* some exceptions: Atoms seem problematic with value 1 */
 	if (chip->pci->vendor == PCI_VENDOR_ID_INTEL) {
 		switch (chip->pci->device) {
-		case 0x0f04: /* Baytrail */
-		case 0x2284: /* Braswell */
+		case PCI_DEVICE_ID_INTEL_HDA_BYT:
+		case PCI_DEVICE_ID_INTEL_HDA_BSW:
 			return 32;
+		case PCI_DEVICE_ID_INTEL_HDA_APL:
+			return 64;
 		}
 	}
 
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index e8819e8a9876..e8209178d87b 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -344,6 +344,7 @@ enum {
 	CXT_FIXUP_HP_ZBOOK_MUTE_LED,
 	CXT_FIXUP_HEADSET_MIC,
 	CXT_FIXUP_HP_MIC_NO_PRESENCE,
+	CXT_PINCFG_SWS_JS201D,
 };
 
 /* for hda_fixup_thinkpad_acpi() */
@@ -841,6 +842,17 @@ static const struct hda_pintbl cxt_pincfg_lemote[] = {
 	{}
 };
 
+/* SuoWoSi/South-holding JS201D with sn6140 */
+static const struct hda_pintbl cxt_pincfg_sws_js201d[] = {
+	{ 0x16, 0x03211040 }, /* hp out */
+	{ 0x17, 0x91170110 }, /* SPK/Class_D */
+	{ 0x18, 0x95a70130 }, /* Internal mic */
+	{ 0x19, 0x03a11020 }, /* Headset Mic */
+	{ 0x1a, 0x40f001f0 }, /* Not used */
+	{ 0x21, 0x40f001f0 }, /* Not used */
+	{}
+};
+
 static const struct hda_fixup cxt_fixups[] = {
 	[CXT_PINCFG_LENOVO_X200] = {
 		.type = HDA_FIXUP_PINS,
@@ -996,6 +1008,10 @@ static const struct hda_fixup cxt_fixups[] = {
 		.chained = true,
 		.chain_id = CXT_FIXUP_HEADSET_MIC,
 	},
+	[CXT_PINCFG_SWS_JS201D] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = cxt_pincfg_sws_js201d,
+	},
 };
 
 static const struct snd_pci_quirk cxt5045_fixups[] = {
@@ -1069,6 +1085,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = {
 	SND_PCI_QUIRK(0x103c, 0x8457, "HP Z2 G4 mini", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x8458, "HP Z2 G4 mini premium", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN),
+	SND_PCI_QUIRK(0x14f1, 0x0265, "SWS JS201D", CXT_PINCFG_SWS_JS201D),
 	SND_PCI_QUIRK(0x152d, 0x0833, "OLPC XO-1.5", CXT_FIXUP_OLPC_XO),
 	SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410),
 	SND_PCI_QUIRK(0x17aa, 0x215e, "Lenovo T410", CXT_PINCFG_LENOVO_TP410),
@@ -1109,6 +1126,7 @@ static const struct hda_model_fixup cxt5066_fixup_models[] = {
 	{ .id = CXT_FIXUP_HP_ZBOOK_MUTE_LED, .name = "hp-zbook-mute-led" },
 	{ .id = CXT_FIXUP_HP_MIC_NO_PRESENCE, .name = "hp-mic-fix" },
 	{ .id = CXT_PINCFG_LENOVO_NOTEBOOK, .name = "lenovo-20149" },
+	{ .id = CXT_PINCFG_SWS_JS201D, .name = "sws-js201d" },
 	{}
 };
 
diff --git a/sound/pci/hda/patch_cs8409.c b/sound/pci/hda/patch_cs8409.c
index 627899959ffe..e41316e2e983 100644
--- a/sound/pci/hda/patch_cs8409.c
+++ b/sound/pci/hda/patch_cs8409.c
@@ -1371,6 +1371,7 @@ void dolphin_fixups(struct hda_codec *codec, const struct hda_fixup *fix, int ac
 		spec->scodecs[CS8409_CODEC1] = &dolphin_cs42l42_1;
 		spec->scodecs[CS8409_CODEC1]->codec = codec;
 		spec->num_scodecs = 2;
+		spec->gen.suppress_vmaster = 1;
 
 		codec->patch_ops = cs8409_dolphin_patch_ops;
 
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 200779296a1b..495d63101186 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -2301,6 +2301,7 @@ static int generic_hdmi_build_pcms(struct hda_codec *codec)
 	codec_dbg(codec, "hdmi: pcm_num set to %d\n", pcm_num);
 
 	for (idx = 0; idx < pcm_num; idx++) {
+		struct hdmi_spec_per_cvt *per_cvt;
 		struct hda_pcm *info;
 		struct hda_pcm_stream *pstr;
 
@@ -2316,6 +2317,11 @@ static int generic_hdmi_build_pcms(struct hda_codec *codec)
 		pstr = &info->stream[SNDRV_PCM_STREAM_PLAYBACK];
 		pstr->substreams = 1;
 		pstr->ops = generic_ops;
+
+		per_cvt = get_cvt(spec, 0);
+		pstr->channels_min = per_cvt->channels_min;
+		pstr->channels_max = per_cvt->channels_max;
+
 		/* pcm number is less than pcm_rec array size */
 		if (spec->pcm_used >= ARRAY_SIZE(spec->pcm_rec))
 			break;
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index b68c94757051..a1facdb98d9a 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -439,6 +439,10 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 		alc_update_coef_idx(codec, 0x67, 0xf000, 0x3000);
 		fallthrough;
 	case 0x10ec0215:
+	case 0x10ec0285:
+	case 0x10ec0289:
+		alc_update_coef_idx(codec, 0x36, 1<<13, 0);
+		fallthrough;
 	case 0x10ec0230:
 	case 0x10ec0233:
 	case 0x10ec0235:
@@ -452,9 +456,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 	case 0x10ec0283:
 	case 0x10ec0286:
 	case 0x10ec0288:
-	case 0x10ec0285:
 	case 0x10ec0298:
-	case 0x10ec0289:
 	case 0x10ec0300:
 		alc_update_coef_idx(codec, 0x10, 1<<9, 0);
 		break;
@@ -3682,6 +3684,7 @@ static void alc285_hp_init(struct hda_codec *codec)
 	int i, val;
 	int coef38, coef0d, coef36;
 
+	alc_write_coefex_idx(codec, 0x58, 0x00, 0x1888); /* write default value */
 	alc_update_coef_idx(codec, 0x4a, 1<<15, 1<<15); /* Reset HP JD */
 	coef38 = alc_read_coef_idx(codec, 0x38); /* Amp control */
 	coef0d = alc_read_coef_idx(codec, 0x0d); /* Digital Misc control */
@@ -7442,6 +7445,7 @@ enum {
 	ALC287_FIXUP_LEGION_15IMHG05_AUTOMUTE,
 	ALC287_FIXUP_YOGA7_14ITL_SPEAKERS,
 	ALC298_FIXUP_LENOVO_C940_DUET7,
+	ALC287_FIXUP_LENOVO_14IRP8_DUETITL,
 	ALC287_FIXUP_13S_GEN2_SPEAKERS,
 	ALC256_FIXUP_SET_COEF_DEFAULTS,
 	ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE,
@@ -7493,6 +7497,26 @@ static void alc298_fixup_lenovo_c940_duet7(struct hda_codec *codec,
 	__snd_hda_apply_fixup(codec, id, action, 0);
 }
 
+/* A special fixup for Lenovo Slim/Yoga Pro 9 14IRP8 and Yoga DuetITL 2021;
+ * 14IRP8 PCI SSID will mistakenly be matched with the DuetITL codec SSID,
+ * so we need to apply a different fixup in this case. The only DuetITL codec
+ * SSID reported so far is the 17aa:3802 while the 14IRP8 has the 17aa:38be
+ * and 17aa:38bf. If it weren't for the PCI SSID, the 14IRP8 models would
+ * have matched correctly by their codecs.
+ */
+static void alc287_fixup_lenovo_14irp8_duetitl(struct hda_codec *codec,
+					      const struct hda_fixup *fix,
+					      int action)
+{
+	int id;
+
+	if (codec->core.subsystem_id == 0x17aa3802)
+		id = ALC287_FIXUP_YOGA7_14ITL_SPEAKERS; /* DuetITL */
+	else
+		id = ALC287_FIXUP_TAS2781_I2C; /* 14IRP8 */
+	__snd_hda_apply_fixup(codec, id, action, 0);
+}
+
 static const struct hda_fixup alc269_fixups[] = {
 	[ALC269_FIXUP_GPIO2] = {
 		.type = HDA_FIXUP_FUNC,
@@ -9377,6 +9401,10 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc298_fixup_lenovo_c940_duet7,
 	},
+	[ALC287_FIXUP_LENOVO_14IRP8_DUETITL] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc287_fixup_lenovo_14irp8_duetitl,
+	},
 	[ALC287_FIXUP_13S_GEN2_SPEAKERS] = {
 		.type = HDA_FIXUP_VERBS,
 		.v.verbs = (const struct hda_verb[]) {
@@ -9577,13 +9605,13 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = cs35l41_fixup_i2c_two,
 		.chained = true,
-		.chain_id = ALC269_FIXUP_THINKPAD_ACPI,
+		.chain_id = ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK,
 	},
 	[ALC287_FIXUP_TAS2781_I2C] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = tas2781_fixup_i2c,
 		.chained = true,
-		.chain_id = ALC269_FIXUP_THINKPAD_ACPI,
+		.chain_id = ALC285_FIXUP_THINKPAD_HEADSET_JACK,
 	},
 	[ALC287_FIXUP_YOGA7_14ARB7_I2C] = {
 		.type = HDA_FIXUP_FUNC,
@@ -9604,6 +9632,8 @@ static const struct hda_fixup alc269_fixups[] = {
 	[ALC287_FIXUP_THINKPAD_I2S_SPK] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc287_fixup_bind_dacs,
+		.chained = true,
+		.chain_id = ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK,
 	},
 	[ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD] = {
 		.type = HDA_FIXUP_FUNC,
@@ -9653,6 +9683,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x1247, "Acer vCopperbox", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS),
 	SND_PCI_QUIRK(0x1025, 0x1248, "Acer Veriton N4660G", ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1025, 0x1269, "Acer SWIFT SF314-54", ALC256_FIXUP_ACER_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1025, 0x126a, "Acer Swift SF114-32", ALC256_FIXUP_ACER_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1025, 0x128f, "Acer Veriton Z6860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x1290, "Acer Veriton Z4860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x1291, "Acer Veriton Z4660G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
@@ -9732,12 +9763,16 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x0b71, "Dell Inspiron 16 Plus 7620", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS),
 	SND_PCI_QUIRK(0x1028, 0x0beb, "Dell XPS 15 9530 (2023)", ALC289_FIXUP_DELL_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1028, 0x0c03, "Dell Precision 5340", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x0c0b, "Dell Oasis 14 RPL-P", ALC289_FIXUP_RTK_AMP_DUAL_SPK),
+	SND_PCI_QUIRK(0x1028, 0x0c0d, "Dell Oasis", ALC289_FIXUP_RTK_AMP_DUAL_SPK),
+	SND_PCI_QUIRK(0x1028, 0x0c0e, "Dell Oasis 16", ALC289_FIXUP_RTK_AMP_DUAL_SPK),
 	SND_PCI_QUIRK(0x1028, 0x0c19, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
 	SND_PCI_QUIRK(0x1028, 0x0c1a, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
 	SND_PCI_QUIRK(0x1028, 0x0c1b, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS),
 	SND_PCI_QUIRK(0x1028, 0x0c1c, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS),
 	SND_PCI_QUIRK(0x1028, 0x0c1d, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS),
 	SND_PCI_QUIRK(0x1028, 0x0c1e, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS),
+	SND_PCI_QUIRK(0x1028, 0x0c28, "Dell Inspiron 16 Plus 7630", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS),
 	SND_PCI_QUIRK(0x1028, 0x0c4d, "Dell", ALC287_FIXUP_CS35L41_I2C_4),
 	SND_PCI_QUIRK(0x1028, 0x0cbd, "Dell Oasis 13 CS MTL-U", ALC289_FIXUP_DELL_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1028, 0x0cbe, "Dell Oasis 13 2-IN-1 MTL-U", ALC289_FIXUP_DELL_CS35L41_SPI_2),
@@ -9852,6 +9887,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8786, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x8787, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x8788, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED),
+	SND_PCI_QUIRK(0x103c, 0x87b7, "HP Laptop 14-fq0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87e5, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87e7, "HP ProBook 450 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED),
@@ -9861,6 +9897,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87f6, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP),
 	SND_PCI_QUIRK(0x103c, 0x87f7, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP),
+	SND_PCI_QUIRK(0x103c, 0x87fe, "HP Laptop 15s-fq2xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x8805, "HP ProBook 650 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x880d, "HP EliteBook 830 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8811, "HP Spectre x360 15-eb1xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1),
@@ -9892,6 +9929,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8973, "HP EliteBook 860 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8974, "HP EliteBook 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8975, "HP EliteBook x360 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x897d, "HP mt440 Mobile Thin Client U74", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8981, "HP Elite Dragonfly G3", ALC245_FIXUP_CS35L41_SPI_4),
 	SND_PCI_QUIRK(0x103c, 0x898e, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x898f, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2),
@@ -9917,16 +9955,20 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8aa3, "HP ProBook 450 G9 (MB 8AA1)", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8aa8, "HP EliteBook 640 G9 (MB 8AA6)", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8aab, "HP EliteBook 650 G9 (MB 8AA9)", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8ab9, "HP EliteBook 840 G8 (MB 8AB8)", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8b0f, "HP Elite mt645 G7 Mobile Thin Client U81", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8b2f, "HP 255 15.6 inch G10 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
+	SND_PCI_QUIRK(0x103c, 0x8b3f, "HP mt440 Mobile Thin Client U91", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8b43, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8b44, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8b45, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8b46, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8b47, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8b59, "HP Elite mt645 G7 Mobile Thin Client U89", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8b5d, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8b5e, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8b63, "HP Elite Dragonfly 13.5 inch G4", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED),
@@ -9954,7 +9996,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8c70, "HP EliteBook 835 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8c71, "HP EliteBook 845 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8c8a, "HP EliteBook 630", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8c8c, "HP EliteBook 660", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8c90, "HP EliteBook 640", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8c91, "HP EliteBook 660", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8c96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
+	SND_PCI_QUIRK(0x103c, 0x8c97, "HP ZBook", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
+	SND_PCI_QUIRK(0x103c, 0x8ca1, "HP ZBook Power", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8ca2, "HP ZBook Power", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED),
@@ -9992,6 +10041,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK),
 	SND_PCI_QUIRK(0x1043, 0x1663, "ASUS GU603ZI/ZJ/ZQ/ZU/ZV", ALC285_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1683, "ASUS UM3402YAR", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x16a3, "ASUS UX3402VA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x16b2, "ASUS GU603", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x16d3, "ASUS UX5304VA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC),
@@ -10035,14 +10085,12 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE),
 	SND_PCI_QUIRK(0x1043, 0x1da2, "ASUS UP6502ZA/ZD", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1e02, "ASUS UX3402ZA", ALC245_FIXUP_CS35L41_SPI_2),
-	SND_PCI_QUIRK(0x1043, 0x16a3, "ASUS UX3402VA", ALC245_FIXUP_CS35L41_SPI_2),
-	SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502),
-	SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM6702RA/RC", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS),
 	SND_PCI_QUIRK(0x1043, 0x1e5e, "ASUS ROG Strix G513", ALC294_FIXUP_ASUS_G513_PINS),
 	SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401),
-	SND_PCI_QUIRK(0x1043, 0x1ee2, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x1ee2, "ASUS UM6702RA/RC", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1c52, "ASUS Zephyrus G15 2022", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1f12, "ASUS UM5302", ALC287_FIXUP_CS35L41_I2C_2),
@@ -10231,8 +10279,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x3176, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x3178, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x31af, "ThinkCentre Station", ALC623_FIXUP_LENOVO_THINKSTATION_P340),
+	SND_PCI_QUIRK(0x17aa, 0x334b, "Lenovo ThinkCentre M70 Gen5", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x3801, "Lenovo Yoga9 14IAP7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
-	SND_PCI_QUIRK(0x17aa, 0x3802, "Lenovo Yoga DuetITL 2021", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS),
+	SND_PCI_QUIRK(0x17aa, 0x3802, "Lenovo Yoga Pro 9 14IRP8 / DuetITL 2021", ALC287_FIXUP_LENOVO_14IRP8_DUETITL),
 	SND_PCI_QUIRK(0x17aa, 0x3813, "Legion 7i 15IMHG05", ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS),
 	SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940 / Yoga Duet 7", ALC298_FIXUP_LENOVO_C940_DUET7),
 	SND_PCI_QUIRK(0x17aa, 0x3819, "Lenovo 13s Gen2 ITL", ALC287_FIXUP_13S_GEN2_SPEAKERS),
@@ -10248,6 +10297,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x3853, "Lenovo Yoga 7 15ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS),
 	SND_PCI_QUIRK(0x17aa, 0x3855, "Legion 7 16ITHG6", ALC287_FIXUP_LEGION_16ITHG6),
 	SND_PCI_QUIRK(0x17aa, 0x3869, "Lenovo Yoga7 14IAL7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
+	SND_PCI_QUIRK(0x17aa, 0x386f, "Legion 7i 16IAX7", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x17aa, 0x3870, "Lenovo Yoga 7 14ARB7", ALC287_FIXUP_YOGA7_14ARB7_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x387d, "Yoga S780-16 pro Quad AAC", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x387e, "Yoga S780-16 pro Quad YC", ALC287_FIXUP_TAS2781_I2C),
@@ -10257,6 +10307,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x3886, "Y780 VECO DUAL", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x38a7, "Y780P AMD YG dual", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x38a8, "Y780P AMD VECO dual", ALC287_FIXUP_TAS2781_I2C),
+	SND_PCI_QUIRK(0x17aa, 0x38a9, "Thinkbook 16P", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x17aa, 0x38ab, "Thinkbook 16P", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x17aa, 0x38b4, "Legion Slim 7 16IRH8", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x17aa, 0x38b5, "Legion Slim 7 16IRH8", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x17aa, 0x38b6, "Legion Slim 7 16APH8", ALC287_FIXUP_CS35L41_I2C_2),
@@ -10319,6 +10371,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
 	SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO),
+	SND_PCI_QUIRK(0x2782, 0x1707, "Vaio VJFE-ADL", ALC298_FIXUP_SPK_VOLUME),
 	SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC),
 	SND_PCI_QUIRK(0x8086, 0x2080, "Intel NUC 8 Rugged", ALC256_FIXUP_INTEL_NUC8_RUGGED),
 	SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10),
@@ -10948,6 +11001,8 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
  *   at most one tbl is allowed to define for the same vendor and same codec
  */
 static const struct snd_hda_pin_quirk alc269_fallback_pin_fixup_tbl[] = {
+	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1025, "Acer", ALC2XX_FIXUP_HEADSET_MIC,
+		{0x19, 0x40000000}),
 	SND_HDA_PIN_QUIRK(0x10ec0289, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
 		{0x19, 0x40000000},
 		{0x1b, 0x40000000}),
@@ -11637,8 +11692,7 @@ static void alc897_hp_automute_hook(struct hda_codec *codec,
 
 	snd_hda_gen_hp_automute(codec, jack);
 	vref = spec->gen.hp_jack_present ? (PIN_HP | AC_PINCTL_VREF_100) : PIN_HP;
-	snd_hda_codec_write(codec, 0x1b, 0, AC_VERB_SET_PIN_WIDGET_CONTROL,
-			    vref);
+	snd_hda_set_pin_ctl(codec, 0x1b, vref);
 }
 
 static void alc897_fixup_lenovo_headset_mic(struct hda_codec *codec,
@@ -11647,6 +11701,10 @@ static void alc897_fixup_lenovo_headset_mic(struct hda_codec *codec,
 	struct alc_spec *spec = codec->spec;
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		spec->gen.hp_automute_hook = alc897_hp_automute_hook;
+		spec->no_shutup_pins = 1;
+	}
+	if (action == HDA_FIXUP_ACT_PROBE) {
+		snd_hda_set_pin_ctl_cache(codec, 0x1a, PIN_IN | AC_PINCTL_VREF_100);
 	}
 }
 
diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c
index 2dd809de62e5..1bfb00102a77 100644
--- a/sound/pci/hda/tas2781_hda_i2c.c
+++ b/sound/pci/hda/tas2781_hda_i2c.c
@@ -710,7 +710,7 @@ static int tas2781_hda_bind(struct device *dev, struct device *master,
 
 	strscpy(comps->name, dev_name(dev), sizeof(comps->name));
 
-	ret = tascodec_init(tas_hda->priv, codec, tasdev_fw_ready);
+	ret = tascodec_init(tas_hda->priv, codec, THIS_MODULE, tasdev_fw_ready);
 	if (!ret)
 		comps->playback_hook = tas2781_hda_playback_hook;
 
diff --git a/sound/pci/oxygen/oxygen_mixer.c b/sound/pci/oxygen/oxygen_mixer.c
index 46705ec77b48..eb3aca16359c 100644
--- a/sound/pci/oxygen/oxygen_mixer.c
+++ b/sound/pci/oxygen/oxygen_mixer.c
@@ -718,7 +718,7 @@ static int ac97_fp_rec_volume_put(struct snd_kcontrol *ctl,
 	oldreg = oxygen_read_ac97(chip, 1, AC97_REC_GAIN);
 	newreg = oldreg & ~0x0707;
 	newreg = newreg | (value->value.integer.value[0] & 7);
-	newreg = newreg | ((value->value.integer.value[0] & 7) << 8);
+	newreg = newreg | ((value->value.integer.value[1] & 7) << 8);
 	change = newreg != oldreg;
 	if (change)
 		oxygen_write_ac97(chip, 1, AC97_REC_GAIN, newreg);
diff --git a/sound/soc/amd/acp/acp-mach-common.c b/sound/soc/amd/acp/acp-mach-common.c
index c90ec3419247..504d1b8c4cbb 100644
--- a/sound/soc/amd/acp/acp-mach-common.c
+++ b/sound/soc/amd/acp/acp-mach-common.c
@@ -505,6 +505,13 @@ static int acp_card_rt5682s_hw_params(struct snd_pcm_substream *substream,
 
 	clk_set_rate(drvdata->wclk, srate);
 	clk_set_rate(drvdata->bclk, srate * ch * format);
+	if (!drvdata->soc_mclk) {
+		ret = acp_clk_enable(drvdata, srate, ch * format);
+		if (ret < 0) {
+			dev_err(rtd->card->dev, "Failed to enable HS clk: %d\n", ret);
+			return ret;
+		}
+	}
 
 	return 0;
 }
@@ -1464,8 +1471,13 @@ int acp_sofdsp_dai_links_create(struct snd_soc_card *card)
 	if (drv_data->amp_cpu_id == I2S_SP) {
 		links[i].name = "acp-amp-codec";
 		links[i].id = AMP_BE_ID;
-		links[i].cpus = sof_sp_virtual;
-		links[i].num_cpus = ARRAY_SIZE(sof_sp_virtual);
+		if (drv_data->platform == RENOIR) {
+			links[i].cpus = sof_sp;
+			links[i].num_cpus = ARRAY_SIZE(sof_sp);
+		} else {
+			links[i].cpus = sof_sp_virtual;
+			links[i].num_cpus = ARRAY_SIZE(sof_sp_virtual);
+		}
 		links[i].platforms = sof_component;
 		links[i].num_platforms = ARRAY_SIZE(sof_component);
 		links[i].dpcm_playback = 1;
diff --git a/sound/soc/amd/acp/acp-sof-mach.c b/sound/soc/amd/acp/acp-sof-mach.c
index 2a9fd3275e42..20b94814a046 100644
--- a/sound/soc/amd/acp/acp-sof-mach.c
+++ b/sound/soc/amd/acp/acp-sof-mach.c
@@ -48,6 +48,7 @@ static struct acp_card_drvdata sof_rt5682s_rt1019_data = {
 	.hs_codec_id = RT5682S,
 	.amp_codec_id = RT1019,
 	.dmic_codec_id = DMIC,
+	.platform = RENOIR,
 	.tdm_mode = false,
 };
 
@@ -58,6 +59,7 @@ static struct acp_card_drvdata sof_rt5682s_max_data = {
 	.hs_codec_id = RT5682S,
 	.amp_codec_id = MAX98360A,
 	.dmic_codec_id = DMIC,
+	.platform = RENOIR,
 	.tdm_mode = false,
 };
 
@@ -68,6 +70,7 @@ static struct acp_card_drvdata sof_nau8825_data = {
 	.hs_codec_id = NAU8825,
 	.amp_codec_id = MAX98360A,
 	.dmic_codec_id = DMIC,
+	.platform = REMBRANDT,
 	.soc_mclk = true,
 	.tdm_mode = false,
 };
@@ -79,6 +82,7 @@ static struct acp_card_drvdata sof_rt5682s_hs_rt1019_data = {
 	.hs_codec_id = RT5682S,
 	.amp_codec_id = RT1019,
 	.dmic_codec_id = DMIC,
+	.platform = REMBRANDT,
 	.soc_mclk = true,
 	.tdm_mode = false,
 };
diff --git a/sound/soc/amd/acp/acp3x-es83xx/acp3x-es83xx.c b/sound/soc/amd/acp/acp3x-es83xx/acp3x-es83xx.c
index f85b85ea4be9..2b0aa270a3e9 100644
--- a/sound/soc/amd/acp/acp3x-es83xx/acp3x-es83xx.c
+++ b/sound/soc/amd/acp/acp3x-es83xx/acp3x-es83xx.c
@@ -358,6 +358,14 @@ static const struct dmi_system_id acp3x_es83xx_dmi_table[] = {
 		.matches = {
 			DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "HUAWEI"),
 			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "HVY-WXX9"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "M1010"),
+		},
+		.driver_data = (void *)(ES83XX_ENABLE_DMIC),
+	},
+	{
+		.matches = {
+			DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "HUAWEI"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "HVY-WXX9"),
 			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "M1020"),
 		},
 		.driver_data = (void *)(ES83XX_ENABLE_DMIC),
diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index d83cb6e4c62a..90360f8b3e81 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -203,6 +203,20 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 		.driver_data = &acp6x_card,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21J2"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21J0"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "21J5"),
 		}
 	},
@@ -238,6 +252,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 		.driver_data = &acp6x_card,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "82UU"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "82V2"),
 		}
 	},
@@ -251,6 +272,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 	{
 		.driver_data = &acp6x_card,
 		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "83AS"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "UM5302TA"),
 		}
@@ -300,6 +328,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 	{
 		.driver_data = &acp6x_card,
 		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Bravo 15 C7VF"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "Alienware"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m17 R5 AMD"),
 		}
@@ -384,6 +419,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 	{
 		.driver_data = &acp6x_card,
 		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "HP"),
+			DMI_MATCH(DMI_BOARD_NAME, "8BD6"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "MECHREVO"),
 			DMI_MATCH(DMI_BOARD_NAME, "MRID6"),
 		}
diff --git a/sound/soc/amd/yc/pci-acp6x.c b/sound/soc/amd/yc/pci-acp6x.c
index 7af6a349b1d4..694b8e313902 100644
--- a/sound/soc/amd/yc/pci-acp6x.c
+++ b/sound/soc/amd/yc/pci-acp6x.c
@@ -162,6 +162,7 @@ static int snd_acp6x_probe(struct pci_dev *pci,
 	/* Yellow Carp device check */
 	switch (pci->revision) {
 	case 0x60:
+	case 0x63:
 	case 0x6f:
 		break;
 	default:
diff --git a/sound/soc/codecs/cs35l45.c b/sound/soc/codecs/cs35l45.c
index 44c221745c3b..2392c6effed8 100644
--- a/sound/soc/codecs/cs35l45.c
+++ b/sound/soc/codecs/cs35l45.c
@@ -184,7 +184,7 @@ static int cs35l45_activate_ctl(struct snd_soc_component *component,
 	else
 		snprintf(name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, "%s", ctl_name);
 
-	kcontrol = snd_soc_card_get_kcontrol(component->card, name);
+	kcontrol = snd_soc_card_get_kcontrol_locked(component->card, name);
 	if (!kcontrol) {
 		dev_err(component->dev, "Can't find kcontrol %s\n", name);
 		return -EINVAL;
diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
index 953ba066bab1..cb4e83126b08 100644
--- a/sound/soc/codecs/cs35l56-shared.c
+++ b/sound/soc/codecs/cs35l56-shared.c
@@ -5,6 +5,7 @@
 // Copyright (C) 2023 Cirrus Logic, Inc. and
 //                    Cirrus Logic International Semiconductor Ltd.
 
+#include <linux/gpio/consumer.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
 #include <linux/types.h>
@@ -12,6 +13,15 @@
 #include "cs35l56.h"
 
 static const struct reg_sequence cs35l56_patch[] = {
+	/*
+	 * Firmware can change these to non-defaults to satisfy SDCA.
+	 * Ensure that they are at known defaults.
+	 */
+	{ CS35L56_SWIRE_DP3_CH1_INPUT,		0x00000018 },
+	{ CS35L56_SWIRE_DP3_CH2_INPUT,		0x00000019 },
+	{ CS35L56_SWIRE_DP3_CH3_INPUT,		0x00000029 },
+	{ CS35L56_SWIRE_DP3_CH4_INPUT,		0x00000028 },
+
 	/* These are not reset by a soft-reset, so patch to defaults. */
 	{ CS35L56_MAIN_RENDER_USER_MUTE,	0x00000000 },
 	{ CS35L56_MAIN_RENDER_USER_VOLUME,	0x00000000 },
@@ -34,15 +44,13 @@ static const struct reg_default cs35l56_reg_defaults[] = {
 	{ CS35L56_ASP1_FRAME_CONTROL5,		0x00020100 },
 	{ CS35L56_ASP1_DATA_CONTROL1,		0x00000018 },
 	{ CS35L56_ASP1_DATA_CONTROL5,		0x00000018 },
-	{ CS35L56_ASP1TX1_INPUT,		0x00000018 },
-	{ CS35L56_ASP1TX2_INPUT,		0x00000019 },
-	{ CS35L56_ASP1TX3_INPUT,		0x00000020 },
-	{ CS35L56_ASP1TX4_INPUT,		0x00000028 },
+
+	/* no defaults for ASP1TX mixer */
+
 	{ CS35L56_SWIRE_DP3_CH1_INPUT,		0x00000018 },
 	{ CS35L56_SWIRE_DP3_CH2_INPUT,		0x00000019 },
 	{ CS35L56_SWIRE_DP3_CH3_INPUT,		0x00000029 },
 	{ CS35L56_SWIRE_DP3_CH4_INPUT,		0x00000028 },
-	{ CS35L56_IRQ1_CFG,			0x00000000 },
 	{ CS35L56_IRQ1_MASK_1,			0x83ffffff },
 	{ CS35L56_IRQ1_MASK_2,			0xffff7fff },
 	{ CS35L56_IRQ1_MASK_4,			0xe0ffffff },
@@ -195,6 +203,47 @@ static bool cs35l56_volatile_reg(struct device *dev, unsigned int reg)
 	}
 }
 
+/*
+ * The firmware boot sequence can overwrite the ASP1 config registers so that
+ * they don't match regmap's view of their values. Rewrite the values from the
+ * regmap cache into the hardware registers.
+ */
+int cs35l56_force_sync_asp1_registers_from_cache(struct cs35l56_base *cs35l56_base)
+{
+	struct reg_sequence asp1_regs[] = {
+		{ .reg = CS35L56_ASP1_ENABLES1 },
+		{ .reg = CS35L56_ASP1_CONTROL1 },
+		{ .reg = CS35L56_ASP1_CONTROL2 },
+		{ .reg = CS35L56_ASP1_CONTROL3 },
+		{ .reg = CS35L56_ASP1_FRAME_CONTROL1 },
+		{ .reg = CS35L56_ASP1_FRAME_CONTROL5 },
+		{ .reg = CS35L56_ASP1_DATA_CONTROL1 },
+		{ .reg = CS35L56_ASP1_DATA_CONTROL5 },
+	};
+	int i, ret;
+
+	/* Read values from regmap cache into a write sequence */
+	for (i = 0; i < ARRAY_SIZE(asp1_regs); ++i) {
+		ret = regmap_read(cs35l56_base->regmap, asp1_regs[i].reg, &asp1_regs[i].def);
+		if (ret)
+			goto err;
+	}
+
+	/* Write the values cache-bypassed so that they will be written to silicon */
+	ret = regmap_multi_reg_write_bypassed(cs35l56_base->regmap, asp1_regs,
+					      ARRAY_SIZE(asp1_regs));
+	if (ret)
+		goto err;
+
+	return 0;
+
+err:
+	dev_err(cs35l56_base->dev, "Failed to sync ASP1 registers: %d\n", ret);
+
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(cs35l56_force_sync_asp1_registers_from_cache, SND_SOC_CS35L56_SHARED);
+
 int cs35l56_mbox_send(struct cs35l56_base *cs35l56_base, unsigned int command)
 {
 	unsigned int val;
@@ -286,6 +335,7 @@ void cs35l56_wait_min_reset_pulse(void)
 EXPORT_SYMBOL_NS_GPL(cs35l56_wait_min_reset_pulse, SND_SOC_CS35L56_SHARED);
 
 static const struct reg_sequence cs35l56_system_reset_seq[] = {
+	REG_SEQ0(CS35L56_DSP1_HALO_STATE, 0),
 	REG_SEQ0(CS35L56_DSP_VIRTUAL1_MBOX_1, CS35L56_MBOX_CMD_SYSTEM_RESET),
 };
 
@@ -400,17 +450,6 @@ int cs35l56_is_fw_reload_needed(struct cs35l56_base *cs35l56_base)
 	unsigned int val;
 	int ret;
 
-	/* Nothing to re-patch if we haven't done any patching yet. */
-	if (!cs35l56_base->fw_patched)
-		return false;
-
-	/*
-	 * If we have control of RESET we will have asserted it so the firmware
-	 * will need re-patching.
-	 */
-	if (cs35l56_base->reset_gpio)
-		return true;
-
 	/*
 	 * In secure mode FIRMWARE_MISSING is cleared by the BIOS loader so
 	 * can't be used here to test for memory retention.
@@ -590,10 +629,35 @@ void cs35l56_init_cs_dsp(struct cs35l56_base *cs35l56_base, struct cs_dsp *cs_ds
 }
 EXPORT_SYMBOL_NS_GPL(cs35l56_init_cs_dsp, SND_SOC_CS35L56_SHARED);
 
+int cs35l56_read_prot_status(struct cs35l56_base *cs35l56_base,
+			     bool *fw_missing, unsigned int *fw_version)
+{
+	unsigned int prot_status;
+	int ret;
+
+	ret = regmap_read(cs35l56_base->regmap, CS35L56_PROTECTION_STATUS, &prot_status);
+	if (ret) {
+		dev_err(cs35l56_base->dev, "Get PROTECTION_STATUS failed: %d\n", ret);
+		return ret;
+	}
+
+	*fw_missing = !!(prot_status & CS35L56_FIRMWARE_MISSING);
+
+	ret = regmap_read(cs35l56_base->regmap, CS35L56_DSP1_FW_VER, fw_version);
+	if (ret) {
+		dev_err(cs35l56_base->dev, "Get FW VER failed: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cs35l56_read_prot_status, SND_SOC_CS35L56_SHARED);
+
 int cs35l56_hw_init(struct cs35l56_base *cs35l56_base)
 {
 	int ret;
-	unsigned int devid, revid, otpid, secured;
+	unsigned int devid, revid, otpid, secured, fw_ver;
+	bool fw_missing;
 
 	/*
 	 * When the system is not using a reset_gpio ensure the device is
@@ -652,8 +716,13 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base)
 		return ret;
 	}
 
-	dev_info(cs35l56_base->dev, "Cirrus Logic CS35L56%s Rev %02X OTP%d\n",
-		 cs35l56_base->secured ? "s" : "", cs35l56_base->rev, otpid);
+	ret = cs35l56_read_prot_status(cs35l56_base, &fw_missing, &fw_ver);
+	if (ret)
+		return ret;
+
+	dev_info(cs35l56_base->dev, "Cirrus Logic CS35L56%s Rev %02X OTP%d fw:%d.%d.%d (patched=%u)\n",
+		 cs35l56_base->secured ? "s" : "", cs35l56_base->rev, otpid,
+		 fw_ver >> 16, (fw_ver >> 8) & 0xff, fw_ver & 0xff, !fw_missing);
 
 	/* Wake source and *_BLOCKED interrupts default to unmasked, so mask them */
 	regmap_write(cs35l56_base->regmap, CS35L56_IRQ1_MASK_20, 0xffffffff);
@@ -668,6 +737,41 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base)
 }
 EXPORT_SYMBOL_NS_GPL(cs35l56_hw_init, SND_SOC_CS35L56_SHARED);
 
+int cs35l56_get_speaker_id(struct cs35l56_base *cs35l56_base)
+{
+	struct gpio_descs *descs;
+	int speaker_id;
+	int i, ret;
+
+	/* Read the speaker type qualifier from the motherboard GPIOs */
+	descs = gpiod_get_array_optional(cs35l56_base->dev, "spk-id", GPIOD_IN);
+	if (!descs) {
+		return -ENOENT;
+	} else if (IS_ERR(descs)) {
+		ret = PTR_ERR(descs);
+		return dev_err_probe(cs35l56_base->dev, ret, "Failed to get spk-id-gpios\n");
+	}
+
+	speaker_id = 0;
+	for (i = 0; i < descs->ndescs; i++) {
+		ret = gpiod_get_value_cansleep(descs->desc[i]);
+		if (ret < 0) {
+			dev_err_probe(cs35l56_base->dev, ret, "Failed to read spk-id[%d]\n", i);
+			goto err;
+		}
+
+		speaker_id |= (ret << i);
+	}
+
+	dev_dbg(cs35l56_base->dev, "Speaker ID = %d\n", speaker_id);
+	ret = speaker_id;
+err:
+	gpiod_put_array(descs);
+
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(cs35l56_get_speaker_id, SND_SOC_CS35L56_SHARED);
+
 static const u32 cs35l56_bclk_valid_for_pll_freq_table[] = {
 	[0x0C] = 128000,
 	[0x0F] = 256000,
diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index 45b4de3eff94..6dd0319bc843 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -5,6 +5,7 @@
 // Copyright (C) 2023 Cirrus Logic, Inc. and
 //                    Cirrus Logic International Semiconductor Ltd.
 
+#include <linux/acpi.h>
 #include <linux/completion.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
@@ -15,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
+#include <linux/property.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
 #include <linux/slab.h>
@@ -59,6 +61,131 @@ static int cs35l56_dspwait_put_volsw(struct snd_kcontrol *kcontrol,
 	return snd_soc_put_volsw(kcontrol, ucontrol);
 }
 
+static const unsigned short cs35l56_asp1_mixer_regs[] = {
+	CS35L56_ASP1TX1_INPUT, CS35L56_ASP1TX2_INPUT,
+	CS35L56_ASP1TX3_INPUT, CS35L56_ASP1TX4_INPUT,
+};
+
+static const char * const cs35l56_asp1_mux_control_names[] = {
+	"ASP1 TX1 Source", "ASP1 TX2 Source", "ASP1 TX3 Source", "ASP1 TX4 Source"
+};
+
+static int cs35l56_sync_asp1_mixer_widgets_with_firmware(struct cs35l56_private *cs35l56)
+{
+	struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(cs35l56->component);
+	const char *prefix = cs35l56->component->name_prefix;
+	char full_name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
+	const char *name;
+	struct snd_kcontrol *kcontrol;
+	struct soc_enum *e;
+	unsigned int val[4];
+	int i, item, ret;
+
+	if (cs35l56->asp1_mixer_widgets_initialized)
+		return 0;
+
+	/*
+	 * Resume so we can read the registers from silicon if the regmap
+	 * cache has not yet been populated.
+	 */
+	ret = pm_runtime_resume_and_get(cs35l56->base.dev);
+	if (ret < 0)
+		return ret;
+
+	/* Wait for firmware download and reboot */
+	cs35l56_wait_dsp_ready(cs35l56);
+
+	ret = regmap_bulk_read(cs35l56->base.regmap, CS35L56_ASP1TX1_INPUT,
+			       val, ARRAY_SIZE(val));
+
+	pm_runtime_mark_last_busy(cs35l56->base.dev);
+	pm_runtime_put_autosuspend(cs35l56->base.dev);
+
+	if (ret) {
+		dev_err(cs35l56->base.dev, "Failed to read ASP1 mixer regs: %d\n", ret);
+		return ret;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(cs35l56_asp1_mux_control_names); ++i) {
+		name = cs35l56_asp1_mux_control_names[i];
+
+		if (prefix) {
+			snprintf(full_name, sizeof(full_name), "%s %s", prefix, name);
+			name = full_name;
+		}
+
+		kcontrol = snd_soc_card_get_kcontrol_locked(dapm->card, name);
+		if (!kcontrol) {
+			dev_warn(cs35l56->base.dev, "Could not find control %s\n", name);
+			continue;
+		}
+
+		e = (struct soc_enum *)kcontrol->private_value;
+		item = snd_soc_enum_val_to_item(e, val[i] & CS35L56_ASP_TXn_SRC_MASK);
+		snd_soc_dapm_mux_update_power(dapm, kcontrol, item, e, NULL);
+	}
+
+	cs35l56->asp1_mixer_widgets_initialized = true;
+
+	return 0;
+}
+
+static int cs35l56_dspwait_asp1tx_get(struct snd_kcontrol *kcontrol,
+				      struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_soc_dapm_kcontrol_component(kcontrol);
+	struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(component);
+	struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
+	int index = e->shift_l;
+	unsigned int addr, val;
+	int ret;
+
+	ret = cs35l56_sync_asp1_mixer_widgets_with_firmware(cs35l56);
+	if (ret)
+		return ret;
+
+	addr = cs35l56_asp1_mixer_regs[index];
+	ret = regmap_read(cs35l56->base.regmap, addr, &val);
+	if (ret)
+		return ret;
+
+	val &= CS35L56_ASP_TXn_SRC_MASK;
+	ucontrol->value.enumerated.item[0] = snd_soc_enum_val_to_item(e, val);
+
+	return 0;
+}
+
+static int cs35l56_dspwait_asp1tx_put(struct snd_kcontrol *kcontrol,
+				      struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_soc_dapm_kcontrol_component(kcontrol);
+	struct snd_soc_dapm_context *dapm = snd_soc_dapm_kcontrol_dapm(kcontrol);
+	struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(component);
+	struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
+	int item = ucontrol->value.enumerated.item[0];
+	int index = e->shift_l;
+	unsigned int addr, val;
+	bool changed;
+	int ret;
+
+	ret = cs35l56_sync_asp1_mixer_widgets_with_firmware(cs35l56);
+	if (ret)
+		return ret;
+
+	addr = cs35l56_asp1_mixer_regs[index];
+	val = snd_soc_enum_item_to_val(e, item);
+
+	ret = regmap_update_bits_check(cs35l56->base.regmap, addr,
+				       CS35L56_ASP_TXn_SRC_MASK, val, &changed);
+	if (ret)
+		return ret;
+
+	if (changed)
+		snd_soc_dapm_mux_update_power(dapm, kcontrol, item, e, NULL);
+
+	return changed;
+}
+
 static DECLARE_TLV_DB_SCALE(vol_tlv, -10000, 25, 0);
 
 static const struct snd_kcontrol_new cs35l56_controls[] = {
@@ -77,40 +204,44 @@ static const struct snd_kcontrol_new cs35l56_controls[] = {
 };
 
 static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_asp1tx1_enum,
-				  CS35L56_ASP1TX1_INPUT,
-				  0, CS35L56_ASP_TXn_SRC_MASK,
+				  SND_SOC_NOPM,
+				  0, 0,
 				  cs35l56_tx_input_texts,
 				  cs35l56_tx_input_values);
 
 static const struct snd_kcontrol_new asp1_tx1_mux =
-	SOC_DAPM_ENUM("ASP1TX1 SRC", cs35l56_asp1tx1_enum);
+	SOC_DAPM_ENUM_EXT("ASP1TX1 SRC", cs35l56_asp1tx1_enum,
+			  cs35l56_dspwait_asp1tx_get, cs35l56_dspwait_asp1tx_put);
 
 static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_asp1tx2_enum,
-				  CS35L56_ASP1TX2_INPUT,
-				  0, CS35L56_ASP_TXn_SRC_MASK,
+				  SND_SOC_NOPM,
+				  1, 0,
 				  cs35l56_tx_input_texts,
 				  cs35l56_tx_input_values);
 
 static const struct snd_kcontrol_new asp1_tx2_mux =
-	SOC_DAPM_ENUM("ASP1TX2 SRC", cs35l56_asp1tx2_enum);
+	SOC_DAPM_ENUM_EXT("ASP1TX2 SRC", cs35l56_asp1tx2_enum,
+			  cs35l56_dspwait_asp1tx_get, cs35l56_dspwait_asp1tx_put);
 
 static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_asp1tx3_enum,
-				  CS35L56_ASP1TX3_INPUT,
-				  0, CS35L56_ASP_TXn_SRC_MASK,
+				  SND_SOC_NOPM,
+				  2, 0,
 				  cs35l56_tx_input_texts,
 				  cs35l56_tx_input_values);
 
 static const struct snd_kcontrol_new asp1_tx3_mux =
-	SOC_DAPM_ENUM("ASP1TX3 SRC", cs35l56_asp1tx3_enum);
+	SOC_DAPM_ENUM_EXT("ASP1TX3 SRC", cs35l56_asp1tx3_enum,
+			  cs35l56_dspwait_asp1tx_get, cs35l56_dspwait_asp1tx_put);
 
 static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_asp1tx4_enum,
-				  CS35L56_ASP1TX4_INPUT,
-				  0, CS35L56_ASP_TXn_SRC_MASK,
+				  SND_SOC_NOPM,
+				  3, 0,
 				  cs35l56_tx_input_texts,
 				  cs35l56_tx_input_values);
 
 static const struct snd_kcontrol_new asp1_tx4_mux =
-	SOC_DAPM_ENUM("ASP1TX4 SRC", cs35l56_asp1tx4_enum);
+	SOC_DAPM_ENUM_EXT("ASP1TX4 SRC", cs35l56_asp1tx4_enum,
+			  cs35l56_dspwait_asp1tx_get, cs35l56_dspwait_asp1tx_put);
 
 static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_sdw1tx1_enum,
 				CS35L56_SWIRE_DP3_CH1_INPUT,
@@ -148,6 +279,21 @@ static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_sdw1tx4_enum,
 static const struct snd_kcontrol_new sdw1_tx4_mux =
 	SOC_DAPM_ENUM("SDW1TX4 SRC", cs35l56_sdw1tx4_enum);
 
+static int cs35l56_asp1_cfg_event(struct snd_soc_dapm_widget *w,
+				  struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
+	struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(component);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		/* Override register values set by firmware boot */
+		return cs35l56_force_sync_asp1_registers_from_cache(&cs35l56->base);
+	default:
+		return 0;
+	}
+}
+
 static int cs35l56_play_event(struct snd_soc_dapm_widget *w,
 			      struct snd_kcontrol *kcontrol, int event)
 {
@@ -184,6 +330,9 @@ static const struct snd_soc_dapm_widget cs35l56_dapm_widgets[] = {
 	SND_SOC_DAPM_REGULATOR_SUPPLY("VDD_B", 0, 0),
 	SND_SOC_DAPM_REGULATOR_SUPPLY("VDD_AMP", 0, 0),
 
+	SND_SOC_DAPM_SUPPLY("ASP1 CFG", SND_SOC_NOPM, 0, 0, cs35l56_asp1_cfg_event,
+			    SND_SOC_DAPM_PRE_PMU),
+
 	SND_SOC_DAPM_SUPPLY("PLAY", SND_SOC_NOPM, 0, 0, cs35l56_play_event,
 			    SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_POST_PMD),
 
@@ -251,6 +400,9 @@ static const struct snd_soc_dapm_route cs35l56_audio_map[] = {
 	{ "AMP", NULL, "VDD_B" },
 	{ "AMP", NULL, "VDD_AMP" },
 
+	{ "ASP1 Playback", NULL, "ASP1 CFG" },
+	{ "ASP1 Capture", NULL, "ASP1 CFG" },
+
 	{ "ASP1 Playback", NULL, "PLAY" },
 	{ "SDW1 Playback", NULL, "PLAY" },
 
@@ -650,7 +802,7 @@ static struct snd_soc_dai_driver cs35l56_dai[] = {
 	}
 };
 
-static void cs35l56_secure_patch(struct cs35l56_private *cs35l56)
+static void cs35l56_reinit_patch(struct cs35l56_private *cs35l56)
 {
 	int ret;
 
@@ -662,19 +814,10 @@ static void cs35l56_secure_patch(struct cs35l56_private *cs35l56)
 		cs35l56_mbox_send(&cs35l56->base, CS35L56_MBOX_CMD_AUDIO_REINIT);
 }
 
-static void cs35l56_patch(struct cs35l56_private *cs35l56)
+static void cs35l56_patch(struct cs35l56_private *cs35l56, bool firmware_missing)
 {
-	unsigned int firmware_missing;
 	int ret;
 
-	ret = regmap_read(cs35l56->base.regmap, CS35L56_PROTECTION_STATUS, &firmware_missing);
-	if (ret) {
-		dev_err(cs35l56->base.dev, "Failed to read PROTECTION_STATUS: %d\n", ret);
-		return;
-	}
-
-	firmware_missing &= CS35L56_FIRMWARE_MISSING;
-
 	/*
 	 * Disable SoundWire interrupts to prevent race with IRQ work.
 	 * Setting sdw_irq_no_unmask prevents the handler re-enabling
@@ -747,23 +890,51 @@ static void cs35l56_dsp_work(struct work_struct *work)
 	struct cs35l56_private *cs35l56 = container_of(work,
 						       struct cs35l56_private,
 						       dsp_work);
+	unsigned int firmware_version;
+	bool firmware_missing;
+	int ret;
 
 	if (!cs35l56->base.init_done)
 		return;
 
 	pm_runtime_get_sync(cs35l56->base.dev);
 
+	ret = cs35l56_read_prot_status(&cs35l56->base, &firmware_missing, &firmware_version);
+	if (ret)
+		goto err;
+
+	/* Populate fw file qualifier with the revision and security state */
+	kfree(cs35l56->dsp.fwf_name);
+	if (firmware_missing) {
+		cs35l56->dsp.fwf_name = kasprintf(GFP_KERNEL, "%02x-dsp1", cs35l56->base.rev);
+	} else {
+		/* Firmware files must match the running firmware version */
+		cs35l56->dsp.fwf_name = kasprintf(GFP_KERNEL,
+						  "%02x%s-%06x-dsp1",
+						  cs35l56->base.rev,
+						  cs35l56->base.secured ? "-s" : "",
+						  firmware_version);
+	}
+
+	if (!cs35l56->dsp.fwf_name)
+		goto err;
+
+	dev_dbg(cs35l56->base.dev, "DSP fwf name: '%s' system name: '%s'\n",
+		cs35l56->dsp.fwf_name, cs35l56->dsp.system_name);
+
 	/*
-	 * When the device is running in secure mode the firmware files can
-	 * only contain insecure tunings and therefore we do not need to
-	 * shutdown the firmware to apply them and can use the lower cost
-	 * reinit sequence instead.
+	 * The firmware cannot be patched if it is already running from
+	 * patch RAM. In this case the firmware files are versioned to
+	 * match the running firmware version and will only contain
+	 * tunings. We do not need to shutdown the firmware to apply
+	 * tunings so can use the lower cost reinit sequence instead.
 	 */
-	if (cs35l56->base.secured)
-		cs35l56_secure_patch(cs35l56);
+	if (!firmware_missing)
+		cs35l56_reinit_patch(cs35l56);
 	else
-		cs35l56_patch(cs35l56);
+		cs35l56_patch(cs35l56, firmware_missing);
 
+err:
 	pm_runtime_mark_last_busy(cs35l56->base.dev);
 	pm_runtime_put_autosuspend(cs35l56->base.dev);
 }
@@ -778,10 +949,19 @@ static int cs35l56_component_probe(struct snd_soc_component *component)
 
 	if (!cs35l56->dsp.system_name &&
 	    (snd_soc_card_get_pci_ssid(component->card, &vendor, &device) == 0)) {
-		cs35l56->dsp.system_name = devm_kasprintf(cs35l56->base.dev,
-							  GFP_KERNEL,
-							  "%04x%04x",
-							  vendor, device);
+		/* Append a speaker qualifier if there is a speaker ID */
+		if (cs35l56->speaker_id >= 0) {
+			cs35l56->dsp.system_name = devm_kasprintf(cs35l56->base.dev,
+								  GFP_KERNEL,
+								  "%04x%04x-spkid%d",
+								  vendor, device,
+								  cs35l56->speaker_id);
+		} else {
+			cs35l56->dsp.system_name = devm_kasprintf(cs35l56->base.dev,
+								  GFP_KERNEL,
+								  "%04x%04x",
+								  vendor, device);
+		}
 		if (!cs35l56->dsp.system_name)
 			return -ENOMEM;
 	}
@@ -799,6 +979,13 @@ static int cs35l56_component_probe(struct snd_soc_component *component)
 	debugfs_create_bool("can_hibernate", 0444, debugfs_root, &cs35l56->base.can_hibernate);
 	debugfs_create_bool("fw_patched", 0444, debugfs_root, &cs35l56->base.fw_patched);
 
+	/*
+	 * The widgets for the ASP1TX mixer can't be initialized
+	 * until the firmware has been downloaded and rebooted.
+	 */
+	regcache_drop_region(cs35l56->base.regmap, CS35L56_ASP1TX1_INPUT, CS35L56_ASP1TX4_INPUT);
+	cs35l56->asp1_mixer_widgets_initialized = false;
+
 	queue_work(cs35l56->dsp_wq, &cs35l56->dsp_work);
 
 	return 0;
@@ -809,6 +996,16 @@ static void cs35l56_component_remove(struct snd_soc_component *component)
 	struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(component);
 
 	cancel_work_sync(&cs35l56->dsp_work);
+
+	if (cs35l56->dsp.cs_dsp.booted)
+		wm_adsp_power_down(&cs35l56->dsp);
+
+	wm_adsp2_component_remove(&cs35l56->dsp, component);
+
+	kfree(cs35l56->dsp.fwf_name);
+	cs35l56->dsp.fwf_name = NULL;
+
+	cs35l56->component = NULL;
 }
 
 static int cs35l56_set_bias_level(struct snd_soc_component *component,
@@ -1050,7 +1247,13 @@ static int cs35l56_get_firmware_uid(struct cs35l56_private *cs35l56)
 	if (ret < 0)
 		return 0;
 
-	cs35l56->dsp.system_name = devm_kstrdup(dev, prop, GFP_KERNEL);
+	/* Append a speaker qualifier if there is a speaker ID */
+	if (cs35l56->speaker_id >= 0)
+		cs35l56->dsp.system_name = devm_kasprintf(dev, GFP_KERNEL, "%s-spkid%d",
+							  prop, cs35l56->speaker_id);
+	else
+		cs35l56->dsp.system_name = devm_kstrdup(dev, prop, GFP_KERNEL);
+
 	if (cs35l56->dsp.system_name == NULL)
 		return -ENOMEM;
 
@@ -1059,12 +1262,101 @@ static int cs35l56_get_firmware_uid(struct cs35l56_private *cs35l56)
 	return 0;
 }
 
+/*
+ * Some SoundWire laptops have a spk-id-gpios property but it points to
+ * the wrong ACPI Device node so can't be used to get the GPIO. Try to
+ * find the SDCA node containing the GpioIo resource and add a GPIO
+ * mapping to it.
+ */
+static const struct acpi_gpio_params cs35l56_af01_first_gpio = { 0, 0, false };
+static const struct acpi_gpio_mapping cs35l56_af01_spkid_gpios_mapping[] = {
+	{ "spk-id-gpios", &cs35l56_af01_first_gpio, 1 },
+	{ }
+};
+
+static void cs35l56_acpi_dev_release_driver_gpios(void *adev)
+{
+	acpi_dev_remove_driver_gpios(adev);
+}
+
+static int cs35l56_try_get_broken_sdca_spkid_gpio(struct cs35l56_private *cs35l56)
+{
+	struct fwnode_handle *af01_fwnode;
+	const union acpi_object *obj;
+	struct gpio_desc *desc;
+	int ret;
+
+	/* Find the SDCA node containing the GpioIo */
+	af01_fwnode = device_get_named_child_node(cs35l56->base.dev, "AF01");
+	if (!af01_fwnode) {
+		dev_dbg(cs35l56->base.dev, "No AF01 node\n");
+		return -ENOENT;
+	}
+
+	ret = acpi_dev_get_property(ACPI_COMPANION(cs35l56->base.dev),
+				    "spk-id-gpios", ACPI_TYPE_PACKAGE, &obj);
+	if (ret) {
+		dev_dbg(cs35l56->base.dev, "Could not get spk-id-gpios package: %d\n", ret);
+		return -ENOENT;
+	}
+
+	/* The broken properties we can handle are a 4-element package (one GPIO) */
+	if (obj->package.count != 4) {
+		dev_warn(cs35l56->base.dev, "Unexpected spk-id element count %d\n",
+			 obj->package.count);
+		return -ENOENT;
+	}
+
+	/* Add a GPIO mapping if it doesn't already have one */
+	if (!fwnode_property_present(af01_fwnode, "spk-id-gpios")) {
+		struct acpi_device *adev = to_acpi_device_node(af01_fwnode);
+
+		/*
+		 * Can't use devm_acpi_dev_add_driver_gpios() because the
+		 * mapping isn't being added to the node pointed to by
+		 * ACPI_COMPANION().
+		 */
+		ret = acpi_dev_add_driver_gpios(adev, cs35l56_af01_spkid_gpios_mapping);
+		if (ret) {
+			return dev_err_probe(cs35l56->base.dev, ret,
+					     "Failed to add gpio mapping to AF01\n");
+		}
+
+		ret = devm_add_action_or_reset(cs35l56->base.dev,
+					       cs35l56_acpi_dev_release_driver_gpios,
+					       adev);
+		if (ret)
+			return ret;
+
+		dev_dbg(cs35l56->base.dev, "Added spk-id-gpios mapping to AF01\n");
+	}
+
+	desc = fwnode_gpiod_get_index(af01_fwnode, "spk-id", 0, GPIOD_IN, NULL);
+	if (IS_ERR(desc)) {
+		ret = PTR_ERR(desc);
+		return dev_err_probe(cs35l56->base.dev, ret, "Get GPIO from AF01 failed\n");
+	}
+
+	ret = gpiod_get_value_cansleep(desc);
+	gpiod_put(desc);
+
+	if (ret < 0) {
+		dev_err_probe(cs35l56->base.dev, ret, "Error reading spk-id GPIO\n");
+		return ret;
+		}
+
+	dev_info(cs35l56->base.dev, "Got spk-id from AF01\n");
+
+	return ret;
+}
+
 int cs35l56_common_probe(struct cs35l56_private *cs35l56)
 {
 	int ret;
 
 	init_completion(&cs35l56->init_completion);
 	mutex_init(&cs35l56->base.irq_lock);
+	cs35l56->speaker_id = -ENOENT;
 
 	dev_set_drvdata(cs35l56->base.dev, cs35l56);
 
@@ -1101,6 +1393,15 @@ int cs35l56_common_probe(struct cs35l56_private *cs35l56)
 		gpiod_set_value_cansleep(cs35l56->base.reset_gpio, 1);
 	}
 
+	ret = cs35l56_get_speaker_id(&cs35l56->base);
+	if (ACPI_COMPANION(cs35l56->base.dev) && cs35l56->sdw_peripheral && (ret == -ENOENT))
+		ret = cs35l56_try_get_broken_sdca_spkid_gpio(cs35l56);
+
+	if ((ret < 0) && (ret != -ENOENT))
+		goto err;
+
+	cs35l56->speaker_id = ret;
+
 	ret = cs35l56_get_firmware_uid(cs35l56);
 	if (ret != 0)
 		goto err;
@@ -1152,11 +1453,9 @@ int cs35l56_init(struct cs35l56_private *cs35l56)
 	if (ret < 0)
 		return ret;
 
-	/* Populate the DSP information with the revision and security state */
-	cs35l56->dsp.part = devm_kasprintf(cs35l56->base.dev, GFP_KERNEL, "cs35l56%s-%02x",
-					   cs35l56->base.secured ? "s" : "", cs35l56->base.rev);
-	if (!cs35l56->dsp.part)
-		return -ENOMEM;
+	ret = cs35l56_set_patch(&cs35l56->base);
+	if (ret)
+		return ret;
 
 	if (!cs35l56->base.reset_gpio) {
 		dev_dbg(cs35l56->base.dev, "No reset gpio: using soft reset\n");
@@ -1190,10 +1489,6 @@ post_soft_reset:
 	if (ret)
 		return ret;
 
-	ret = cs35l56_set_patch(&cs35l56->base);
-	if (ret)
-		return ret;
-
 	/* Registers could be dirty after soft reset or SoundWire enumeration */
 	regcache_sync(cs35l56->base.regmap);
 
diff --git a/sound/soc/codecs/cs35l56.h b/sound/soc/codecs/cs35l56.h
index 8159c3e217d9..b000e7365e40 100644
--- a/sound/soc/codecs/cs35l56.h
+++ b/sound/soc/codecs/cs35l56.h
@@ -44,12 +44,14 @@ struct cs35l56_private {
 	bool sdw_attached;
 	struct completion init_completion;
 
+	int speaker_id;
 	u32 rx_mask;
 	u32 tx_mask;
 	u8 asp_slot_width;
 	u8 asp_slot_count;
 	bool tdm_mode;
 	bool sysclk_set;
+	bool asp1_mixer_widgets_initialized;
 	u8 old_sdw_clock_scale;
 };
 
diff --git a/sound/soc/codecs/cs42l43.c b/sound/soc/codecs/cs42l43.c
index 6a64681767de..a97ccb512deb 100644
--- a/sound/soc/codecs/cs42l43.c
+++ b/sound/soc/codecs/cs42l43.c
@@ -2257,7 +2257,10 @@ static int cs42l43_codec_probe(struct platform_device *pdev)
 	pm_runtime_use_autosuspend(priv->dev);
 	pm_runtime_set_active(priv->dev);
 	pm_runtime_get_noresume(priv->dev);
-	devm_pm_runtime_enable(priv->dev);
+
+	ret = devm_pm_runtime_enable(priv->dev);
+	if (ret)
+		goto err_pm;
 
 	for (i = 0; i < ARRAY_SIZE(cs42l43_irqs); i++) {
 		ret = cs42l43_request_irq(priv, dom, cs42l43_irqs[i].name,
@@ -2333,8 +2336,47 @@ static int cs42l43_codec_runtime_resume(struct device *dev)
 	return 0;
 }
 
-static DEFINE_RUNTIME_DEV_PM_OPS(cs42l43_codec_pm_ops, NULL,
-				 cs42l43_codec_runtime_resume, NULL);
+static int cs42l43_codec_suspend(struct device *dev)
+{
+	struct cs42l43 *cs42l43 = dev_get_drvdata(dev);
+
+	disable_irq(cs42l43->irq);
+
+	return 0;
+}
+
+static int cs42l43_codec_suspend_noirq(struct device *dev)
+{
+	struct cs42l43 *cs42l43 = dev_get_drvdata(dev);
+
+	enable_irq(cs42l43->irq);
+
+	return 0;
+}
+
+static int cs42l43_codec_resume(struct device *dev)
+{
+	struct cs42l43 *cs42l43 = dev_get_drvdata(dev);
+
+	enable_irq(cs42l43->irq);
+
+	return 0;
+}
+
+static int cs42l43_codec_resume_noirq(struct device *dev)
+{
+	struct cs42l43 *cs42l43 = dev_get_drvdata(dev);
+
+	disable_irq(cs42l43->irq);
+
+	return 0;
+}
+
+static const struct dev_pm_ops cs42l43_codec_pm_ops = {
+	SYSTEM_SLEEP_PM_OPS(cs42l43_codec_suspend, cs42l43_codec_resume)
+	NOIRQ_SYSTEM_SLEEP_PM_OPS(cs42l43_codec_suspend_noirq, cs42l43_codec_resume_noirq)
+	RUNTIME_PM_OPS(NULL, cs42l43_codec_runtime_resume, NULL)
+};
 
 static const struct platform_device_id cs42l43_codec_id_table[] = {
 	{ "cs42l43-codec", },
diff --git a/sound/soc/codecs/es8326.c b/sound/soc/codecs/es8326.c
index fa890f6205e2..cbcd02ec6ba4 100755..100644
--- a/sound/soc/codecs/es8326.c
+++ b/sound/soc/codecs/es8326.c
@@ -45,6 +45,82 @@ struct es8326_priv {
 	int jack_remove_retry;
 };
 
+static int es8326_crosstalk1_get(struct snd_kcontrol *kcontrol,
+		struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+	struct es8326_priv *es8326 = snd_soc_component_get_drvdata(component);
+	unsigned int crosstalk_h, crosstalk_l;
+	unsigned int crosstalk;
+
+	regmap_read(es8326->regmap, ES8326_DAC_RAMPRATE, &crosstalk_h);
+	regmap_read(es8326->regmap, ES8326_DAC_CROSSTALK, &crosstalk_l);
+	crosstalk_h &= 0x20;
+	crosstalk_l &= 0xf0;
+	crosstalk = crosstalk_h >> 1 | crosstalk_l >> 4;
+	ucontrol->value.integer.value[0] = crosstalk;
+
+	return 0;
+}
+
+static int es8326_crosstalk1_set(struct snd_kcontrol *kcontrol,
+		struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+	struct es8326_priv *es8326 = snd_soc_component_get_drvdata(component);
+	unsigned int crosstalk_h, crosstalk_l;
+	unsigned int crosstalk;
+
+	crosstalk = ucontrol->value.integer.value[0];
+	regmap_read(es8326->regmap, ES8326_DAC_CROSSTALK, &crosstalk_l);
+	crosstalk_h = (crosstalk & 0x10) << 1;
+	crosstalk_l &= 0x0f;
+	crosstalk_l |= (crosstalk & 0x0f) << 4;
+	regmap_update_bits(es8326->regmap, ES8326_DAC_RAMPRATE,
+			0x20, crosstalk_h);
+	regmap_write(es8326->regmap, ES8326_DAC_CROSSTALK, crosstalk_l);
+
+	return 0;
+}
+
+static int es8326_crosstalk2_get(struct snd_kcontrol *kcontrol,
+		struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+	struct es8326_priv *es8326 = snd_soc_component_get_drvdata(component);
+	unsigned int crosstalk_h, crosstalk_l;
+	unsigned int crosstalk;
+
+	regmap_read(es8326->regmap, ES8326_DAC_RAMPRATE, &crosstalk_h);
+	regmap_read(es8326->regmap, ES8326_DAC_CROSSTALK, &crosstalk_l);
+	crosstalk_h &= 0x10;
+	crosstalk_l &= 0x0f;
+	crosstalk = crosstalk_h  | crosstalk_l;
+	ucontrol->value.integer.value[0] = crosstalk;
+
+	return 0;
+}
+
+static int es8326_crosstalk2_set(struct snd_kcontrol *kcontrol,
+		struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+	struct es8326_priv *es8326 = snd_soc_component_get_drvdata(component);
+	unsigned int crosstalk_h, crosstalk_l;
+	unsigned int crosstalk;
+
+	crosstalk = ucontrol->value.integer.value[0];
+	regmap_read(es8326->regmap, ES8326_DAC_CROSSTALK, &crosstalk_l);
+	crosstalk_h = crosstalk & 0x10;
+	crosstalk_l &= 0xf0;
+	crosstalk_l |= crosstalk & 0x0f;
+	regmap_update_bits(es8326->regmap, ES8326_DAC_RAMPRATE,
+			0x10, crosstalk_h);
+	regmap_write(es8326->regmap, ES8326_DAC_CROSSTALK, crosstalk_l);
+
+	return 0;
+}
+
 static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(dac_vol_tlv, -9550, 50, 0);
 static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(adc_vol_tlv, -9550, 50, 0);
 static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(adc_analog_pga_tlv, 0, 300, 0);
@@ -102,6 +178,10 @@ static const struct snd_kcontrol_new es8326_snd_controls[] = {
 	SOC_SINGLE_TLV("ALC Capture Target Level", ES8326_ALC_LEVEL,
 			0, 0x0f, 0, drc_target_tlv),
 
+	SOC_SINGLE_EXT("CROSSTALK1", SND_SOC_NOPM, 0, 31, 0,
+			es8326_crosstalk1_get, es8326_crosstalk1_set),
+	SOC_SINGLE_EXT("CROSSTALK2", SND_SOC_NOPM, 0, 31, 0,
+			es8326_crosstalk2_get, es8326_crosstalk2_set),
 };
 
 static const struct snd_soc_dapm_widget es8326_dapm_widgets[] = {
@@ -117,12 +197,6 @@ static const struct snd_soc_dapm_widget es8326_dapm_widgets[] = {
 	SND_SOC_DAPM_AIF_OUT("I2S OUT", "I2S1 Capture", 0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("I2S IN", "I2S1 Playback", 0, SND_SOC_NOPM, 0, 0),
 
-	/* ADC Digital Mute */
-	SND_SOC_DAPM_PGA("ADC L1", ES8326_ADC_MUTE, 0, 1, NULL, 0),
-	SND_SOC_DAPM_PGA("ADC R1", ES8326_ADC_MUTE, 1, 1, NULL, 0),
-	SND_SOC_DAPM_PGA("ADC L2", ES8326_ADC_MUTE, 2, 1, NULL, 0),
-	SND_SOC_DAPM_PGA("ADC R2", ES8326_ADC_MUTE, 3, 1, NULL, 0),
-
 	/* Analog Power Supply*/
 	SND_SOC_DAPM_DAC("Right DAC", NULL, ES8326_ANA_PDN, 0, 1),
 	SND_SOC_DAPM_DAC("Left DAC", NULL, ES8326_ANA_PDN, 1, 1),
@@ -142,15 +216,10 @@ static const struct snd_soc_dapm_widget es8326_dapm_widgets[] = {
 };
 
 static const struct snd_soc_dapm_route es8326_dapm_routes[] = {
-	{"ADC L1", NULL, "MIC1"},
-	{"ADC R1", NULL, "MIC2"},
-	{"ADC L2", NULL, "MIC3"},
-	{"ADC R2", NULL, "MIC4"},
-
-	{"ADC L", NULL, "ADC L1"},
-	{"ADC R", NULL, "ADC R1"},
-	{"ADC L", NULL, "ADC L2"},
-	{"ADC R", NULL, "ADC R2"},
+	{"ADC L", NULL, "MIC1"},
+	{"ADC R", NULL, "MIC2"},
+	{"ADC L", NULL, "MIC3"},
+	{"ADC R", NULL, "MIC4"},
 
 	{"I2S OUT", NULL, "ADC L"},
 	{"I2S OUT", NULL, "ADC R"},
@@ -440,10 +509,16 @@ static int es8326_mute(struct snd_soc_dai *dai, int mute, int direction)
 	unsigned int offset_l, offset_r;
 
 	if (mute) {
-		regmap_write(es8326->regmap, ES8326_HP_CAL, ES8326_HP_OFF);
-		regmap_update_bits(es8326->regmap, ES8326_DAC_MUTE,
-				ES8326_MUTE_MASK, ES8326_MUTE);
-		regmap_write(es8326->regmap, ES8326_HP_DRIVER, 0xf0);
+		if (direction == SNDRV_PCM_STREAM_PLAYBACK) {
+			regmap_write(es8326->regmap, ES8326_HP_CAL, ES8326_HP_OFF);
+			regmap_update_bits(es8326->regmap, ES8326_DAC_MUTE,
+					ES8326_MUTE_MASK, ES8326_MUTE);
+			regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF,
+					0x30, 0x00);
+		} else {
+			regmap_update_bits(es8326->regmap,  ES8326_ADC_MUTE,
+					0x0F, 0x0F);
+		}
 	} else {
 		if (!es8326->calibrated) {
 			regmap_write(es8326->regmap, ES8326_HP_CAL, ES8326_HP_FORCE_CAL);
@@ -456,11 +531,22 @@ static int es8326_mute(struct snd_soc_dai *dai, int mute, int direction)
 			regmap_write(es8326->regmap, ES8326_HPR_OFFSET_INI, offset_r);
 			es8326->calibrated = true;
 		}
-		regmap_write(es8326->regmap, ES8326_HP_DRIVER, 0xa1);
-		regmap_write(es8326->regmap, ES8326_HP_VOL, 0x91);
-		regmap_write(es8326->regmap, ES8326_HP_CAL, ES8326_HP_ON);
-		regmap_update_bits(es8326->regmap, ES8326_DAC_MUTE,
-				ES8326_MUTE_MASK, ~(ES8326_MUTE));
+		if (direction == SNDRV_PCM_STREAM_PLAYBACK) {
+			regmap_update_bits(es8326->regmap, ES8326_DAC_DSM, 0x01, 0x01);
+			usleep_range(1000, 5000);
+			regmap_update_bits(es8326->regmap, ES8326_DAC_DSM, 0x01, 0x00);
+			usleep_range(1000, 5000);
+			regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x30, 0x20);
+			regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x30, 0x30);
+			regmap_write(es8326->regmap, ES8326_HP_DRIVER, 0xa1);
+			regmap_write(es8326->regmap, ES8326_HP_CAL, ES8326_HP_ON);
+			regmap_update_bits(es8326->regmap, ES8326_DAC_MUTE,
+					ES8326_MUTE_MASK, ~(ES8326_MUTE));
+		} else {
+			msleep(300);
+			regmap_update_bits(es8326->regmap,  ES8326_ADC_MUTE,
+					0x0F, 0x00);
+		}
 	}
 	return 0;
 }
@@ -477,23 +563,20 @@ static int es8326_set_bias_level(struct snd_soc_component *codec,
 		if (ret)
 			return ret;
 
-		regmap_update_bits(es8326->regmap, ES8326_DAC_DSM, 0x01, 0x00);
+		regmap_update_bits(es8326->regmap, ES8326_RESET, 0x02, 0x02);
+		usleep_range(5000, 10000);
 		regmap_write(es8326->regmap, ES8326_INTOUT_IO, es8326->interrupt_clk);
 		regmap_write(es8326->regmap, ES8326_SDINOUT1_IO,
 			    (ES8326_IO_DMIC_CLK << ES8326_SDINOUT1_SHIFT));
-		regmap_write(es8326->regmap, ES8326_VMIDSEL, 0x0E);
 		regmap_write(es8326->regmap, ES8326_PGA_PDN, 0x40);
 		regmap_write(es8326->regmap, ES8326_ANA_PDN, 0x00);
 		regmap_update_bits(es8326->regmap,  ES8326_CLK_CTL, 0x20, 0x20);
-
-		regmap_update_bits(es8326->regmap, ES8326_RESET,
-				ES8326_CSM_ON, ES8326_CSM_ON);
+		regmap_update_bits(es8326->regmap, ES8326_RESET, 0x02, 0x00);
 		break;
 	case SND_SOC_BIAS_PREPARE:
 		break;
 	case SND_SOC_BIAS_STANDBY:
 		regmap_write(es8326->regmap, ES8326_ANA_PDN, 0x3b);
-		regmap_write(es8326->regmap, ES8326_VMIDSEL, 0x00);
 		regmap_update_bits(es8326->regmap, ES8326_CLK_CTL, 0x20, 0x00);
 		regmap_write(es8326->regmap, ES8326_SDINOUT1_IO, ES8326_IO_INPUT);
 		break;
@@ -513,7 +596,7 @@ static const struct snd_soc_dai_ops es8326_ops = {
 	.set_fmt = es8326_set_dai_fmt,
 	.set_sysclk = es8326_set_dai_sysclk,
 	.mute_stream = es8326_mute,
-	.no_capture_mute = 1,
+	.no_capture_mute = 0,
 };
 
 static struct snd_soc_dai_driver es8326_dai = {
@@ -672,6 +755,8 @@ static void es8326_jack_detect_handler(struct work_struct *work)
 			es8326->hp = 0;
 		}
 		regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x01);
+		regmap_write(es8326->regmap, ES8326_SYS_BIAS, 0x0a);
+		regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x0f, 0x03);
 		/*
 		 * Inverted HPJACK_POL bit to trigger one IRQ to double check HP Removal event
 		 */
@@ -695,8 +780,11 @@ static void es8326_jack_detect_handler(struct work_struct *work)
 			 * Don't report jack status.
 			 */
 			regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x01);
+			es8326_enable_micbias(es8326->component);
 			usleep_range(50000, 70000);
 			regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x00);
+			regmap_write(es8326->regmap, ES8326_SYS_BIAS, 0x1f);
+			regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x0f, 0x08);
 			queue_delayed_work(system_wq, &es8326->jack_detect_work,
 					msecs_to_jiffies(400));
 			es8326->hp = 1;
@@ -736,13 +824,10 @@ exit:
 static irqreturn_t es8326_irq(int irq, void *dev_id)
 {
 	struct es8326_priv *es8326 = dev_id;
-	struct snd_soc_component *comp = es8326->component;
 
 	if (!es8326->jack)
 		goto out;
 
-	es8326_enable_micbias(comp);
-
 	if (es8326->jack->status & SND_JACK_HEADSET)
 		queue_delayed_work(system_wq, &es8326->jack_detect_work,
 				   msecs_to_jiffies(10));
@@ -766,14 +851,14 @@ static int es8326_calibrate(struct snd_soc_component *component)
 	if ((es8326->version == ES8326_VERSION_B) && (es8326->calibrated == false)) {
 		dev_dbg(component->dev, "ES8326_VERSION_B, calibrating\n");
 		regmap_write(es8326->regmap, ES8326_CLK_INV, 0xc0);
-		regmap_write(es8326->regmap, ES8326_CLK_DIV1, 0x01);
+		regmap_write(es8326->regmap, ES8326_CLK_DIV1, 0x03);
 		regmap_write(es8326->regmap, ES8326_CLK_DLL, 0x30);
 		regmap_write(es8326->regmap, ES8326_CLK_MUX, 0xed);
 		regmap_write(es8326->regmap, ES8326_CLK_DAC_SEL, 0x08);
 		regmap_write(es8326->regmap, ES8326_CLK_TRI, 0xc1);
 		regmap_write(es8326->regmap, ES8326_DAC_MUTE, 0x03);
 		regmap_write(es8326->regmap, ES8326_ANA_VSEL, 0x7f);
-		regmap_write(es8326->regmap, ES8326_VMIDLOW, 0x03);
+		regmap_write(es8326->regmap, ES8326_VMIDLOW, 0x23);
 		regmap_write(es8326->regmap, ES8326_DAC2HPMIX, 0x88);
 		usleep_range(15000, 20000);
 		regmap_write(es8326->regmap, ES8326_HP_OFFSET_CAL, 0x8c);
@@ -814,13 +899,13 @@ static int es8326_resume(struct snd_soc_component *component)
 	/* reset internal clock state */
 	regmap_write(es8326->regmap, ES8326_RESET, 0x1f);
 	regmap_write(es8326->regmap, ES8326_VMIDSEL, 0x0E);
+	regmap_write(es8326->regmap, ES8326_ANA_LP, 0xf0);
 	usleep_range(10000, 15000);
 	regmap_write(es8326->regmap, ES8326_HPJACK_TIMER, 0xe9);
-	regmap_write(es8326->regmap, ES8326_ANA_MICBIAS, 0x4b);
+	regmap_write(es8326->regmap, ES8326_ANA_MICBIAS, 0xcb);
 	/* set headphone default type and detect pin */
 	regmap_write(es8326->regmap, ES8326_HPDET_TYPE, 0x83);
 	regmap_write(es8326->regmap, ES8326_CLK_RESAMPLE, 0x05);
-	regmap_write(es8326->regmap, ES8326_HP_MISC, 0x30);
 
 	/* set internal oscillator as clock source of headpone cp */
 	regmap_write(es8326->regmap, ES8326_CLK_DIV_CPC, 0x89);
@@ -828,14 +913,15 @@ static int es8326_resume(struct snd_soc_component *component)
 	/* clock manager reset release */
 	regmap_write(es8326->regmap, ES8326_RESET, 0x17);
 	/* set headphone detection as half scan mode */
-	regmap_write(es8326->regmap, ES8326_HP_MISC, 0x30);
+	regmap_write(es8326->regmap, ES8326_HP_MISC, 0x3d);
 	regmap_write(es8326->regmap, ES8326_PULLUP_CTL, 0x00);
 
 	/* enable headphone driver */
+	regmap_write(es8326->regmap, ES8326_HP_VOL, 0xc4);
 	regmap_write(es8326->regmap, ES8326_HP_DRIVER, 0xa7);
 	usleep_range(2000, 5000);
-	regmap_write(es8326->regmap, ES8326_HP_DRIVER_REF, 0xa3);
-	regmap_write(es8326->regmap, ES8326_HP_DRIVER_REF, 0xb3);
+	regmap_write(es8326->regmap, ES8326_HP_DRIVER_REF, 0x23);
+	regmap_write(es8326->regmap, ES8326_HP_DRIVER_REF, 0x33);
 	regmap_write(es8326->regmap, ES8326_HP_DRIVER, 0xa1);
 
 	regmap_write(es8326->regmap, ES8326_CLK_INV, 0x00);
@@ -844,6 +930,8 @@ static int es8326_resume(struct snd_soc_component *component)
 	regmap_write(es8326->regmap, ES8326_CLK_CAL_TIME, 0x00);
 	/* calibrate for B version */
 	es8326_calibrate(component);
+	regmap_write(es8326->regmap, ES8326_DAC_CROSSTALK, 0xaa);
+	regmap_write(es8326->regmap, ES8326_DAC_RAMPRATE, 0x00);
 	/* turn off headphone out */
 	regmap_write(es8326->regmap, ES8326_HP_CAL, 0x00);
 	/* set ADC and DAC in low power mode */
@@ -856,6 +944,14 @@ static int es8326_resume(struct snd_soc_component *component)
 	regmap_write(es8326->regmap, ES8326_DAC_DSM, 0x08);
 	regmap_write(es8326->regmap, ES8326_DAC_VPPSCALE, 0x15);
 
+	regmap_write(es8326->regmap, ES8326_HPDET_TYPE, 0x80 |
+			((es8326->version == ES8326_VERSION_B) ?
+			(ES8326_HP_DET_SRC_PIN9 | es8326->jack_pol) :
+			(ES8326_HP_DET_SRC_PIN9 | es8326->jack_pol | 0x04)));
+	usleep_range(5000, 10000);
+	es8326_enable_micbias(es8326->component);
+	usleep_range(50000, 70000);
+	regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x00);
 	regmap_write(es8326->regmap, ES8326_INT_SOURCE,
 		    (ES8326_INT_SRC_PIN9 | ES8326_INT_SRC_BUTTON));
 	regmap_write(es8326->regmap, ES8326_INTOUT_IO,
@@ -864,7 +960,7 @@ static int es8326_resume(struct snd_soc_component *component)
 		    (ES8326_IO_DMIC_CLK << ES8326_SDINOUT1_SHIFT));
 	regmap_write(es8326->regmap, ES8326_SDINOUT23_IO, ES8326_IO_INPUT);
 
-	regmap_write(es8326->regmap, ES8326_ANA_PDN, 0x3b);
+	regmap_write(es8326->regmap, ES8326_ANA_PDN, 0x00);
 	regmap_write(es8326->regmap, ES8326_RESET, ES8326_CSM_ON);
 	regmap_update_bits(es8326->regmap, ES8326_PGAGAIN, ES8326_MIC_SEL_MASK,
 			   ES8326_MIC1_SEL);
@@ -872,11 +968,7 @@ static int es8326_resume(struct snd_soc_component *component)
 	regmap_update_bits(es8326->regmap, ES8326_DAC_MUTE, ES8326_MUTE_MASK,
 			   ES8326_MUTE);
 
-	regmap_write(es8326->regmap, ES8326_HPDET_TYPE, 0x80 |
-			((es8326->version == ES8326_VERSION_B) ?
-			(ES8326_HP_DET_SRC_PIN9 | es8326->jack_pol) :
-			(ES8326_HP_DET_SRC_PIN9 | es8326->jack_pol | 0x04)));
-	regmap_write(es8326->regmap, ES8326_HP_VOL, 0x11);
+	regmap_write(es8326->regmap, ES8326_ADC_MUTE, 0x0f);
 
 	es8326->jack_remove_retry = 0;
 	es8326->hp = 0;
diff --git a/sound/soc/codecs/es8326.h b/sound/soc/codecs/es8326.h
index 90a08351d6ac..4234bbb900c4 100644
--- a/sound/soc/codecs/es8326.h
+++ b/sound/soc/codecs/es8326.h
@@ -72,6 +72,7 @@
 #define ES8326_DAC_VOL		0x50
 #define ES8326_DRC_RECOVERY	0x53
 #define ES8326_DRC_WINSIZE	0x54
+#define ES8326_DAC_CROSSTALK	0x55
 #define ES8326_HPJACK_TIMER	0x56
 #define ES8326_HPDET_TYPE	0x57
 #define ES8326_INT_SOURCE	0x58
@@ -100,7 +101,7 @@
 #define ES8326_MUTE (3 << 0)
 
 /* ES8326_CLK_CTL */
-#define ES8326_CLK_ON (0x7f << 0)
+#define ES8326_CLK_ON (0x7e << 0)
 #define ES8326_CLK_OFF (0 << 0)
 
 /* ES8326_CLK_INV */
diff --git a/sound/soc/codecs/lpass-wsa-macro.c b/sound/soc/codecs/lpass-wsa-macro.c
index 7e21cec3c2fb..6ce309980cd1 100644
--- a/sound/soc/codecs/lpass-wsa-macro.c
+++ b/sound/soc/codecs/lpass-wsa-macro.c
@@ -1584,7 +1584,6 @@ static int wsa_macro_enable_interpolator(struct snd_soc_dapm_widget *w,
 	u16 gain_reg;
 	u16 reg;
 	int val;
-	int offset_val = 0;
 	struct wsa_macro *wsa = snd_soc_component_get_drvdata(component);
 
 	if (w->shift == WSA_MACRO_COMP1) {
@@ -1623,10 +1622,8 @@ static int wsa_macro_enable_interpolator(struct snd_soc_dapm_widget *w,
 					CDC_WSA_RX1_RX_PATH_MIX_SEC0,
 					CDC_WSA_RX_PGA_HALF_DB_MASK,
 					CDC_WSA_RX_PGA_HALF_DB_ENABLE);
-			offset_val = -2;
 		}
 		val = snd_soc_component_read(component, gain_reg);
-		val += offset_val;
 		snd_soc_component_write(component, gain_reg, val);
 		wsa_macro_config_ear_spkr_gain(component, wsa,
 						event, gain_reg);
@@ -1654,10 +1651,6 @@ static int wsa_macro_enable_interpolator(struct snd_soc_dapm_widget *w,
 					CDC_WSA_RX1_RX_PATH_MIX_SEC0,
 					CDC_WSA_RX_PGA_HALF_DB_MASK,
 					CDC_WSA_RX_PGA_HALF_DB_DISABLE);
-			offset_val = 2;
-			val = snd_soc_component_read(component, gain_reg);
-			val += offset_val;
-			snd_soc_component_write(component, gain_reg, val);
 		}
 		wsa_macro_config_ear_spkr_gain(component, wsa,
 						event, gain_reg);
diff --git a/sound/soc/codecs/madera.c b/sound/soc/codecs/madera.c
index b9f19fbd2911..b24d6472ad5f 100644
--- a/sound/soc/codecs/madera.c
+++ b/sound/soc/codecs/madera.c
@@ -3884,7 +3884,7 @@ static inline int madera_set_fll_clks(struct madera_fll *fll, int base, bool ena
 	return madera_set_fll_clks_reg(fll, ena,
 				       base + MADERA_FLL_CONTROL_6_OFFS,
 				       MADERA_FLL1_REFCLK_SRC_MASK,
-				       MADERA_FLL1_REFCLK_DIV_SHIFT);
+				       MADERA_FLL1_REFCLK_SRC_SHIFT);
 }
 
 static inline int madera_set_fllao_clks(struct madera_fll *fll, int base, bool ena)
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index 5150d6ee3748..20191a4473c2 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -3317,6 +3317,7 @@ static void rt5645_jack_detect_work(struct work_struct *work)
 				    report, SND_JACK_HEADPHONE);
 		snd_soc_jack_report(rt5645->mic_jack,
 				    report, SND_JACK_MICROPHONE);
+		mutex_unlock(&rt5645->jd_mutex);
 		return;
 	case 4:
 		val = snd_soc_component_read(rt5645->component, RT5645_A_JD_CTRL1) & 0x0020;
@@ -3692,6 +3693,11 @@ static const struct rt5645_platform_data jd_mode3_monospk_platform_data = {
 	.mono_speaker = true,
 };
 
+static const struct rt5645_platform_data jd_mode3_inv_data = {
+	.jd_mode = 3,
+	.inv_jd1_1 = true,
+};
+
 static const struct rt5645_platform_data jd_mode3_platform_data = {
 	.jd_mode = 3,
 };
@@ -3837,6 +3843,16 @@ static const struct dmi_system_id dmi_platform_data[] = {
 		  DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
 		  DMI_EXACT_MATCH(DMI_BOARD_NAME, "Cherry Trail CR"),
 		  DMI_EXACT_MATCH(DMI_BOARD_VERSION, "Default string"),
+		  /*
+		   * Above strings are too generic, LattePanda BIOS versions for
+		   * all 4 hw revisions are:
+		   * DF-BI-7-S70CR100-*
+		   * DF-BI-7-S70CR110-*
+		   * DF-BI-7-S70CR200-*
+		   * LP-BS-7-S70CR700-*
+		   * Do a partial match for S70CR to avoid false positive matches.
+		   */
+		  DMI_MATCH(DMI_BIOS_VERSION, "S70CR"),
 		},
 		.driver_data = (void *)&lattepanda_board_platform_data,
 	},
@@ -3871,6 +3887,16 @@ static const struct dmi_system_id dmi_platform_data[] = {
 		},
 		.driver_data = (void *)&intel_braswell_platform_data,
 	},
+	{
+		.ident = "Meegopad T08",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Default string"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Default string"),
+			DMI_MATCH(DMI_BOARD_NAME, "T3 MRD"),
+			DMI_MATCH(DMI_BOARD_VERSION, "V1.1"),
+		},
+		.driver_data = (void *)&jd_mode3_inv_data,
+	},
 	{ }
 };
 
diff --git a/sound/soc/codecs/rtq9128.c b/sound/soc/codecs/rtq9128.c
index c22b047115cc..aa3eadecd974 100644
--- a/sound/soc/codecs/rtq9128.c
+++ b/sound/soc/codecs/rtq9128.c
@@ -59,6 +59,7 @@
 
 struct rtq9128_data {
 	struct gpio_desc *enable;
+	unsigned int daifmt;
 	int tdm_slots;
 	int tdm_slot_width;
 	bool tdm_input_data2_select;
@@ -391,7 +392,11 @@ static int rtq9128_component_probe(struct snd_soc_component *comp)
 	unsigned int val;
 	int i, ret;
 
-	pm_runtime_resume_and_get(comp->dev);
+	ret = pm_runtime_resume_and_get(comp->dev);
+	if (ret < 0) {
+		dev_err(comp->dev, "Failed to resume device (%d)\n", ret);
+		return ret;
+	}
 
 	val = snd_soc_component_read(comp, RTQ9128_REG_EFUSE_DATA);
 
@@ -437,10 +442,7 @@ static const struct snd_soc_component_driver rtq9128_comp_driver = {
 static int rtq9128_dai_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 {
 	struct rtq9128_data *data = snd_soc_dai_get_drvdata(dai);
-	struct snd_soc_component *comp = dai->component;
 	struct device *dev = dai->dev;
-	unsigned int audfmt, fmtval;
-	int ret;
 
 	dev_dbg(dev, "%s: fmt 0x%8x\n", __func__, fmt);
 
@@ -450,35 +452,10 @@ static int rtq9128_dai_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 		return -EINVAL;
 	}
 
-	fmtval = fmt & SND_SOC_DAIFMT_FORMAT_MASK;
-	if (data->tdm_slots && fmtval != SND_SOC_DAIFMT_DSP_A && fmtval != SND_SOC_DAIFMT_DSP_B) {
-		dev_err(dev, "TDM is used, format only support DSP_A or DSP_B\n");
-		return -EINVAL;
-	}
+	/* Store here and will be used in runtime hw_params for DAI format setting */
+	data->daifmt = fmt;
 
-	switch (fmtval) {
-	case SND_SOC_DAIFMT_I2S:
-		audfmt = 8;
-		break;
-	case SND_SOC_DAIFMT_LEFT_J:
-		audfmt = 9;
-		break;
-	case SND_SOC_DAIFMT_RIGHT_J:
-		audfmt = 10;
-		break;
-	case SND_SOC_DAIFMT_DSP_A:
-		audfmt = data->tdm_slots ? 12 : 11;
-		break;
-	case SND_SOC_DAIFMT_DSP_B:
-		audfmt = data->tdm_slots ? 4 : 3;
-		break;
-	default:
-		dev_err(dev, "Unsupported format 0x%8x\n", fmt);
-		return -EINVAL;
-	}
-
-	ret = snd_soc_component_write_field(comp, RTQ9128_REG_I2S_OPT, RTQ9128_AUDFMT_MASK, audfmt);
-	return ret < 0 ? ret : 0;
+	return 0;
 }
 
 static int rtq9128_dai_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
@@ -554,10 +531,38 @@ static int rtq9128_dai_hw_params(struct snd_pcm_substream *stream, struct snd_pc
 	unsigned int width, slot_width, bitrate, audbit, dolen;
 	struct snd_soc_component *comp = dai->component;
 	struct device *dev = dai->dev;
+	unsigned int fmtval, audfmt;
 	int ret;
 
 	dev_dbg(dev, "%s: width %d\n", __func__, params_width(param));
 
+	fmtval = FIELD_GET(SND_SOC_DAIFMT_FORMAT_MASK, data->daifmt);
+	if (data->tdm_slots && fmtval != SND_SOC_DAIFMT_DSP_A && fmtval != SND_SOC_DAIFMT_DSP_B) {
+		dev_err(dev, "TDM is used, format only support DSP_A or DSP_B\n");
+		return -EINVAL;
+	}
+
+	switch (fmtval) {
+	case SND_SOC_DAIFMT_I2S:
+		audfmt = 8;
+		break;
+	case SND_SOC_DAIFMT_LEFT_J:
+		audfmt = 9;
+		break;
+	case SND_SOC_DAIFMT_RIGHT_J:
+		audfmt = 10;
+		break;
+	case SND_SOC_DAIFMT_DSP_A:
+		audfmt = data->tdm_slots ? 12 : 11;
+		break;
+	case SND_SOC_DAIFMT_DSP_B:
+		audfmt = data->tdm_slots ? 4 : 3;
+		break;
+	default:
+		dev_err(dev, "Unsupported format 0x%8x\n", fmtval);
+		return -EINVAL;
+	}
+
 	switch (width = params_width(param)) {
 	case 16:
 		audbit = 0;
@@ -611,6 +616,10 @@ static int rtq9128_dai_hw_params(struct snd_pcm_substream *stream, struct snd_pc
 		return -EINVAL;
 	}
 
+	ret = snd_soc_component_write_field(comp, RTQ9128_REG_I2S_OPT, RTQ9128_AUDFMT_MASK, audfmt);
+	if (ret < 0)
+		return ret;
+
 	ret = snd_soc_component_write_field(comp, RTQ9128_REG_I2S_OPT, RTQ9128_AUDBIT_MASK, audbit);
 	if (ret < 0)
 		return ret;
diff --git a/sound/soc/codecs/tas2562.c b/sound/soc/codecs/tas2562.c
index 962c2cdfa017..54561ae598b8 100644
--- a/sound/soc/codecs/tas2562.c
+++ b/sound/soc/codecs/tas2562.c
@@ -59,7 +59,6 @@ struct tas2562_data {
 
 enum tas256x_model {
 	TAS2562,
-	TAS2563,
 	TAS2564,
 	TAS2110,
 };
@@ -721,7 +720,6 @@ static int tas2562_parse_dt(struct tas2562_data *tas2562)
 
 static const struct i2c_device_id tas2562_id[] = {
 	{ "tas2562", TAS2562 },
-	{ "tas2563", TAS2563 },
 	{ "tas2564", TAS2564 },
 	{ "tas2110", TAS2110 },
 	{ }
@@ -770,7 +768,6 @@ static int tas2562_probe(struct i2c_client *client)
 #ifdef CONFIG_OF
 static const struct of_device_id tas2562_of_match[] = {
 	{ .compatible = "ti,tas2562", },
-	{ .compatible = "ti,tas2563", },
 	{ .compatible = "ti,tas2564", },
 	{ .compatible = "ti,tas2110", },
 	{ },
diff --git a/sound/soc/codecs/tas2781-comlib.c b/sound/soc/codecs/tas2781-comlib.c
index b7e56ceb1acf..5d0e5348b361 100644
--- a/sound/soc/codecs/tas2781-comlib.c
+++ b/sound/soc/codecs/tas2781-comlib.c
@@ -267,6 +267,7 @@ void tas2781_reset(struct tasdevice_priv *tas_dev)
 EXPORT_SYMBOL_GPL(tas2781_reset);
 
 int tascodec_init(struct tasdevice_priv *tas_priv, void *codec,
+	struct module *module,
 	void (*cont)(const struct firmware *fw, void *context))
 {
 	int ret = 0;
@@ -280,7 +281,7 @@ int tascodec_init(struct tasdevice_priv *tas_priv, void *codec,
 		tas_priv->dev_name, tas_priv->ndev);
 	crc8_populate_msb(tas_priv->crc8_lkp_tbl, TASDEVICE_CRC8_POLYNOMIAL);
 	tas_priv->codec = codec;
-	ret = request_firmware_nowait(THIS_MODULE, FW_ACTION_UEVENT,
+	ret = request_firmware_nowait(module, FW_ACTION_UEVENT,
 		tas_priv->rca_binaryname, tas_priv->dev, GFP_KERNEL, tas_priv,
 		cont);
 	if (ret)
diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c
index 917b1c15f71d..b5abff230e43 100644
--- a/sound/soc/codecs/tas2781-i2c.c
+++ b/sound/soc/codecs/tas2781-i2c.c
@@ -1,13 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
 //
-// ALSA SoC Texas Instruments TAS2781 Audio Smart Amplifier
+// ALSA SoC Texas Instruments TAS2563/TAS2781 Audio Smart Amplifier
 //
 // Copyright (C) 2022 - 2023 Texas Instruments Incorporated
 // https://www.ti.com
 //
-// The TAS2781 driver implements a flexible and configurable
+// The TAS2563/TAS2781 driver implements a flexible and configurable
 // algo coefficient setting for one, two, or even multiple
-// TAS2781 chips.
+// TAS2563/TAS2781 chips.
 //
 // Author: Shenghao Ding <shenghao-ding@ti.com>
 // Author: Kevin Lu <kevin-lu@ti.com>
@@ -32,6 +32,7 @@
 #include <sound/tas2781-tlv.h>
 
 static const struct i2c_device_id tasdevice_id[] = {
+	{ "tas2563", TAS2563 },
 	{ "tas2781", TAS2781 },
 	{}
 };
@@ -39,6 +40,7 @@ MODULE_DEVICE_TABLE(i2c, tasdevice_id);
 
 #ifdef CONFIG_OF
 static const struct of_device_id tasdevice_of_match[] = {
+	{ .compatible = "ti,tas2563" },
 	{ .compatible = "ti,tas2781" },
 	{},
 };
@@ -564,7 +566,7 @@ static int tasdevice_codec_probe(struct snd_soc_component *codec)
 {
 	struct tasdevice_priv *tas_priv = snd_soc_component_get_drvdata(codec);
 
-	return tascodec_init(tas_priv, codec, tasdevice_fw_ready);
+	return tascodec_init(tas_priv, codec, THIS_MODULE, tasdevice_fw_ready);
 }
 
 static void tasdevice_deinit(void *context)
diff --git a/sound/soc/codecs/wcd9335.c b/sound/soc/codecs/wcd9335.c
index 43c648efd0d9..deb15b95992d 100644
--- a/sound/soc/codecs/wcd9335.c
+++ b/sound/soc/codecs/wcd9335.c
@@ -3033,7 +3033,6 @@ static int wcd9335_codec_enable_mix_path(struct snd_soc_dapm_widget *w,
 {
 	struct snd_soc_component *comp = snd_soc_dapm_to_component(w->dapm);
 	u16 gain_reg;
-	int offset_val = 0;
 	int val = 0;
 
 	switch (w->reg) {
@@ -3073,7 +3072,6 @@ static int wcd9335_codec_enable_mix_path(struct snd_soc_dapm_widget *w,
 	switch (event) {
 	case SND_SOC_DAPM_POST_PMU:
 		val = snd_soc_component_read(comp, gain_reg);
-		val += offset_val;
 		snd_soc_component_write(comp, gain_reg, val);
 		break;
 	case SND_SOC_DAPM_POST_PMD:
@@ -3294,7 +3292,6 @@ static int wcd9335_codec_enable_interpolator(struct snd_soc_dapm_widget *w,
 	u16 gain_reg;
 	u16 reg;
 	int val;
-	int offset_val = 0;
 
 	if (!(snd_soc_dapm_widget_name_cmp(w, "RX INT0 INTERP"))) {
 		reg = WCD9335_CDC_RX0_RX_PATH_CTL;
@@ -3337,7 +3334,6 @@ static int wcd9335_codec_enable_interpolator(struct snd_soc_dapm_widget *w,
 	case SND_SOC_DAPM_POST_PMU:
 		wcd9335_config_compander(comp, w->shift, event);
 		val = snd_soc_component_read(comp, gain_reg);
-		val += offset_val;
 		snd_soc_component_write(comp, gain_reg, val);
 		break;
 	case SND_SOC_DAPM_POST_PMD:
diff --git a/sound/soc/codecs/wcd934x.c b/sound/soc/codecs/wcd934x.c
index 1b6e376f3833..6813268e6a19 100644
--- a/sound/soc/codecs/wcd934x.c
+++ b/sound/soc/codecs/wcd934x.c
@@ -13,7 +13,6 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
-#include <linux/regulator/consumer.h>
 #include <linux/slab.h>
 #include <linux/slimbus.h>
 #include <sound/pcm_params.h>
diff --git a/sound/soc/codecs/wcd938x.c b/sound/soc/codecs/wcd938x.c
index faf8d3f9b3c5..6021aa5a5689 100644
--- a/sound/soc/codecs/wcd938x.c
+++ b/sound/soc/codecs/wcd938x.c
@@ -210,7 +210,7 @@ struct wcd938x_priv {
 };
 
 static const SNDRV_CTL_TLVD_DECLARE_DB_MINMAX(ear_pa_gain, 600, -1800);
-static const DECLARE_TLV_DB_SCALE(line_gain, -3000, 150, -3000);
+static const DECLARE_TLV_DB_SCALE(line_gain, -3000, 150, 0);
 static const SNDRV_CTL_TLVD_DECLARE_DB_MINMAX(analog_gain, 0, 3000);
 
 struct wcd938x_mbhc_zdet_param {
@@ -3587,10 +3587,8 @@ static int wcd938x_probe(struct platform_device *pdev)
 	mutex_init(&wcd938x->micb_lock);
 
 	ret = wcd938x_populate_dt_data(wcd938x, dev);
-	if (ret) {
-		dev_err(dev, "%s: Fail to obtain platform data\n", __func__);
-		return -EINVAL;
-	}
+	if (ret)
+		return ret;
 
 	ret = wcd938x_add_slave_components(wcd938x, dev, &match);
 	if (ret)
diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index fb90ae6a8a34..7c6ed2983128 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -2229,6 +2229,9 @@ SND_SOC_DAPM_PGA_E("HPOUT", SND_SOC_NOPM, 0, 0, NULL, 0, hp_event,
 
 SND_SOC_DAPM_OUTPUT("HPOUTL"),
 SND_SOC_DAPM_OUTPUT("HPOUTR"),
+
+SND_SOC_DAPM_PGA("SPKOUTL Output", WM8962_CLASS_D_CONTROL_1, 6, 0, NULL, 0),
+SND_SOC_DAPM_PGA("SPKOUTR Output", WM8962_CLASS_D_CONTROL_1, 7, 0, NULL, 0),
 };
 
 static const struct snd_soc_dapm_widget wm8962_dapm_spk_mono_widgets[] = {
@@ -2236,7 +2239,6 @@ SND_SOC_DAPM_MIXER("Speaker Mixer", WM8962_MIXER_ENABLES, 1, 0,
 		   spkmixl, ARRAY_SIZE(spkmixl)),
 SND_SOC_DAPM_MUX_E("Speaker PGA", WM8962_PWR_MGMT_2, 4, 0, &spkoutl_mux,
 		   out_pga_event, SND_SOC_DAPM_POST_PMU),
-SND_SOC_DAPM_PGA("Speaker Output", WM8962_CLASS_D_CONTROL_1, 7, 0, NULL, 0),
 SND_SOC_DAPM_OUTPUT("SPKOUT"),
 };
 
@@ -2251,9 +2253,6 @@ SND_SOC_DAPM_MUX_E("SPKOUTL PGA", WM8962_PWR_MGMT_2, 4, 0, &spkoutl_mux,
 SND_SOC_DAPM_MUX_E("SPKOUTR PGA", WM8962_PWR_MGMT_2, 3, 0, &spkoutr_mux,
 		   out_pga_event, SND_SOC_DAPM_POST_PMU),
 
-SND_SOC_DAPM_PGA("SPKOUTR Output", WM8962_CLASS_D_CONTROL_1, 7, 0, NULL, 0),
-SND_SOC_DAPM_PGA("SPKOUTL Output", WM8962_CLASS_D_CONTROL_1, 6, 0, NULL, 0),
-
 SND_SOC_DAPM_OUTPUT("SPKOUTL"),
 SND_SOC_DAPM_OUTPUT("SPKOUTR"),
 };
@@ -2366,12 +2365,18 @@ static const struct snd_soc_dapm_route wm8962_spk_mono_intercon[] = {
 	{ "Speaker PGA", "Mixer", "Speaker Mixer" },
 	{ "Speaker PGA", "DAC", "DACL" },
 
-	{ "Speaker Output", NULL, "Speaker PGA" },
-	{ "Speaker Output", NULL, "SYSCLK" },
-	{ "Speaker Output", NULL, "TOCLK" },
-	{ "Speaker Output", NULL, "TEMP_SPK" },
+	{ "SPKOUTL Output", NULL, "Speaker PGA" },
+	{ "SPKOUTL Output", NULL, "SYSCLK" },
+	{ "SPKOUTL Output", NULL, "TOCLK" },
+	{ "SPKOUTL Output", NULL, "TEMP_SPK" },
 
-	{ "SPKOUT", NULL, "Speaker Output" },
+	{ "SPKOUTR Output", NULL, "Speaker PGA" },
+	{ "SPKOUTR Output", NULL, "SYSCLK" },
+	{ "SPKOUTR Output", NULL, "TOCLK" },
+	{ "SPKOUTR Output", NULL, "TEMP_SPK" },
+
+	{ "SPKOUT", NULL, "SPKOUTL Output" },
+	{ "SPKOUT", NULL, "SPKOUTR Output" },
 };
 
 static const struct snd_soc_dapm_route wm8962_spk_stereo_intercon[] = {
@@ -2914,8 +2919,12 @@ static int wm8962_set_fll(struct snd_soc_component *component, int fll_id, int s
 	switch (fll_id) {
 	case WM8962_FLL_MCLK:
 	case WM8962_FLL_BCLK:
+		fll1 |= (fll_id - 1) << WM8962_FLL_REFCLK_SRC_SHIFT;
+		break;
 	case WM8962_FLL_OSC:
 		fll1 |= (fll_id - 1) << WM8962_FLL_REFCLK_SRC_SHIFT;
+		snd_soc_component_update_bits(component, WM8962_PLL2,
+					      WM8962_OSC_ENA, WM8962_OSC_ENA);
 		break;
 	case WM8962_FLL_INT:
 		snd_soc_component_update_bits(component, WM8962_FLL_CONTROL_1,
@@ -2924,7 +2933,7 @@ static int wm8962_set_fll(struct snd_soc_component *component, int fll_id, int s
 				    WM8962_FLL_FRC_NCO, WM8962_FLL_FRC_NCO);
 		break;
 	default:
-		dev_err(component->dev, "Unknown FLL source %d\n", ret);
+		dev_err(component->dev, "Unknown FLL source %d\n", source);
 		return -EINVAL;
 	}
 
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index c01e31175015..36ea0dcdc7ab 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -739,19 +739,25 @@ static int wm_adsp_request_firmware_file(struct wm_adsp *dsp,
 					 const char *filetype)
 {
 	struct cs_dsp *cs_dsp = &dsp->cs_dsp;
+	const char *fwf;
 	char *s, c;
 	int ret = 0;
 
+	if (dsp->fwf_name)
+		fwf = dsp->fwf_name;
+	else
+		fwf = dsp->cs_dsp.name;
+
 	if (system_name && asoc_component_prefix)
 		*filename = kasprintf(GFP_KERNEL, "%s%s-%s-%s-%s-%s.%s", dir, dsp->part,
-				      dsp->fwf_name, wm_adsp_fw[dsp->fw].file, system_name,
+				      fwf, wm_adsp_fw[dsp->fw].file, system_name,
 				      asoc_component_prefix, filetype);
 	else if (system_name)
 		*filename = kasprintf(GFP_KERNEL, "%s%s-%s-%s-%s.%s", dir, dsp->part,
-				      dsp->fwf_name, wm_adsp_fw[dsp->fw].file, system_name,
+				      fwf, wm_adsp_fw[dsp->fw].file, system_name,
 				      filetype);
 	else
-		*filename = kasprintf(GFP_KERNEL, "%s%s-%s-%s.%s", dir, dsp->part, dsp->fwf_name,
+		*filename = kasprintf(GFP_KERNEL, "%s%s-%s-%s.%s", dir, dsp->part, fwf,
 				      wm_adsp_fw[dsp->fw].file, filetype);
 
 	if (*filename == NULL)
@@ -823,6 +829,23 @@ static int wm_adsp_request_firmware_files(struct wm_adsp *dsp,
 		}
 	}
 
+	/* Check system-specific bin without wmfw before falling back to generic */
+	if (dsp->wmfw_optional && system_name) {
+		if (asoc_component_prefix)
+			wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
+						      cirrus_dir, system_name,
+						      asoc_component_prefix, "bin");
+
+		if (!*coeff_firmware)
+			wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
+						      cirrus_dir, system_name,
+						      NULL, "bin");
+
+		if (*coeff_firmware)
+			return 0;
+	}
+
+	/* Check legacy location */
 	if (!wm_adsp_request_firmware_file(dsp, wmfw_firmware, wmfw_filename,
 					   "", NULL, NULL, "wmfw")) {
 		wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
@@ -830,62 +853,28 @@ static int wm_adsp_request_firmware_files(struct wm_adsp *dsp,
 		return 0;
 	}
 
+	/* Fall back to generic wmfw and optional matching bin */
 	ret = wm_adsp_request_firmware_file(dsp, wmfw_firmware, wmfw_filename,
 					    cirrus_dir, NULL, NULL, "wmfw");
-	if (!ret) {
+	if (!ret || dsp->wmfw_optional) {
 		wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
 					      cirrus_dir, NULL, NULL, "bin");
 		return 0;
 	}
 
-	if (dsp->wmfw_optional) {
-		if (system_name) {
-			if (asoc_component_prefix)
-				wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
-							      cirrus_dir, system_name,
-							      asoc_component_prefix, "bin");
-
-			if (!*coeff_firmware)
-				wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
-							      cirrus_dir, system_name,
-							      NULL, "bin");
-		}
-
-		if (!*coeff_firmware)
-			wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
-						      "", NULL, NULL, "bin");
-
-		if (!*coeff_firmware)
-			wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
-						      cirrus_dir, NULL, NULL, "bin");
-
-		return 0;
-	}
-
 	adsp_err(dsp, "Failed to request firmware <%s>%s-%s-%s<-%s<%s>>.wmfw\n",
-		 cirrus_dir, dsp->part, dsp->fwf_name, wm_adsp_fw[dsp->fw].file,
-		 system_name, asoc_component_prefix);
+		 cirrus_dir, dsp->part,
+		 dsp->fwf_name ? dsp->fwf_name : dsp->cs_dsp.name,
+		 wm_adsp_fw[dsp->fw].file, system_name, asoc_component_prefix);
 
 	return -ENOENT;
 }
 
 static int wm_adsp_common_init(struct wm_adsp *dsp)
 {
-	char *p;
-
 	INIT_LIST_HEAD(&dsp->compr_list);
 	INIT_LIST_HEAD(&dsp->buffer_list);
 
-	if (!dsp->fwf_name) {
-		p = devm_kstrdup(dsp->cs_dsp.dev, dsp->cs_dsp.name, GFP_KERNEL);
-		if (!p)
-			return -ENOMEM;
-
-		dsp->fwf_name = p;
-		for (; *p != 0; ++p)
-			*p = tolower(*p);
-	}
-
 	return 0;
 }
 
diff --git a/sound/soc/codecs/wsa883x.c b/sound/soc/codecs/wsa883x.c
index cb83c569e18d..a2e86ef7d18f 100644
--- a/sound/soc/codecs/wsa883x.c
+++ b/sound/soc/codecs/wsa883x.c
@@ -1098,7 +1098,11 @@ static int wsa_dev_mode_put(struct snd_kcontrol *kcontrol,
 	return 1;
 }
 
-static const DECLARE_TLV_DB_SCALE(pa_gain, -300, 150, -300);
+static const SNDRV_CTL_TLVD_DECLARE_DB_RANGE(pa_gain,
+	0, 14, TLV_DB_SCALE_ITEM(-300, 0, 0),
+	15, 29, TLV_DB_SCALE_ITEM(-300, 150, 0),
+	30, 31, TLV_DB_SCALE_ITEM(1800, 0, 0),
+);
 
 static int wsa883x_get_swr_port(struct snd_kcontrol *kcontrol,
 				struct snd_ctl_elem_value *ucontrol)
diff --git a/sound/soc/fsl/fsl_xcvr.c b/sound/soc/fsl/fsl_xcvr.c
index f0fb33d719c2..c46f64557a7f 100644
--- a/sound/soc/fsl/fsl_xcvr.c
+++ b/sound/soc/fsl/fsl_xcvr.c
@@ -174,7 +174,9 @@ static int fsl_xcvr_activate_ctl(struct snd_soc_dai *dai, const char *name,
 	struct snd_kcontrol *kctl;
 	bool enabled;
 
-	kctl = snd_soc_card_get_kcontrol(card, name);
+	lockdep_assert_held(&card->snd_card->controls_rwsem);
+
+	kctl = snd_soc_card_get_kcontrol_locked(card, name);
 	if (kctl == NULL)
 		return -ENOENT;
 
@@ -576,10 +578,14 @@ static int fsl_xcvr_startup(struct snd_pcm_substream *substream,
 	xcvr->streams |= BIT(substream->stream);
 
 	if (!xcvr->soc_data->spdif_only) {
+		struct snd_soc_card *card = dai->component->card;
+
 		/* Disable XCVR controls if there is stream started */
+		down_read(&card->snd_card->controls_rwsem);
 		fsl_xcvr_activate_ctl(dai, fsl_xcvr_mode_kctl.name, false);
 		fsl_xcvr_activate_ctl(dai, fsl_xcvr_arc_mode_kctl.name, false);
 		fsl_xcvr_activate_ctl(dai, fsl_xcvr_earc_capds_kctl.name, false);
+		up_read(&card->snd_card->controls_rwsem);
 	}
 
 	return 0;
@@ -598,11 +604,15 @@ static void fsl_xcvr_shutdown(struct snd_pcm_substream *substream,
 	/* Enable XCVR controls if there is no stream started */
 	if (!xcvr->streams) {
 		if (!xcvr->soc_data->spdif_only) {
+			struct snd_soc_card *card = dai->component->card;
+
+			down_read(&card->snd_card->controls_rwsem);
 			fsl_xcvr_activate_ctl(dai, fsl_xcvr_mode_kctl.name, true);
 			fsl_xcvr_activate_ctl(dai, fsl_xcvr_arc_mode_kctl.name,
 						(xcvr->mode == FSL_XCVR_MODE_ARC));
 			fsl_xcvr_activate_ctl(dai, fsl_xcvr_earc_capds_kctl.name,
 						(xcvr->mode == FSL_XCVR_MODE_EARC));
+			up_read(&card->snd_card->controls_rwsem);
 		}
 		ret = regmap_update_bits(xcvr->regmap, FSL_XCVR_EXT_IER0,
 					 FSL_XCVR_IRQ_EARC_ALL, 0);
diff --git a/sound/soc/generic/audio-graph-card2.c b/sound/soc/generic/audio-graph-card2.c
index 9c94677f681a..62606e20be9a 100644
--- a/sound/soc/generic/audio-graph-card2.c
+++ b/sound/soc/generic/audio-graph-card2.c
@@ -556,7 +556,7 @@ static int graph_parse_node_multi_nm(struct snd_soc_dai_link *dai_link,
 		struct device_node *mcodec_port;
 		int codec_idx;
 
-		if (*nm_idx >= nm_max)
+		if (*nm_idx > nm_max)
 			break;
 
 		mcpu_ep_n = of_get_next_child(mcpu_port, mcpu_ep_n);
diff --git a/sound/soc/intel/avs/core.c b/sound/soc/intel/avs/core.c
index 59c3793f65df..db78eb2f0108 100644
--- a/sound/soc/intel/avs/core.c
+++ b/sound/soc/intel/avs/core.c
@@ -477,6 +477,9 @@ static int avs_pci_probe(struct pci_dev *pci, const struct pci_device_id *id)
 	return 0;
 
 err_i915_init:
+	pci_free_irq(pci, 0, adev);
+	pci_free_irq(pci, 0, bus);
+	pci_free_irq_vectors(pci);
 	pci_clear_master(pci);
 	pci_set_drvdata(pci, NULL);
 err_acquire_irq:
diff --git a/sound/soc/intel/avs/topology.c b/sound/soc/intel/avs/topology.c
index 778236d3fd28..48b3c67c9103 100644
--- a/sound/soc/intel/avs/topology.c
+++ b/sound/soc/intel/avs/topology.c
@@ -857,7 +857,7 @@ assign_copier_gtw_instance(struct snd_soc_component *comp, struct avs_tplg_modcf
 	}
 
 	/* If topology sets value don't overwrite it */
-	if (cfg->copier.vindex.i2s.instance)
+	if (cfg->copier.vindex.val)
 		return;
 
 	mach = dev_get_platdata(comp->card->dev);
diff --git a/sound/soc/intel/boards/bxt_da7219_max98357a.c b/sound/soc/intel/boards/bxt_da7219_max98357a.c
index 816fad8c1ff0..540f7a29310a 100644
--- a/sound/soc/intel/boards/bxt_da7219_max98357a.c
+++ b/sound/soc/intel/boards/bxt_da7219_max98357a.c
@@ -797,6 +797,9 @@ static int broxton_audio_probe(struct platform_device *pdev)
 		broxton_audio_card.name = "glkda7219max";
 		/* Fixup the SSP entries for geminilake */
 		for (i = 0; i < ARRAY_SIZE(broxton_dais); i++) {
+			if (!broxton_dais[i].codecs->dai_name)
+				continue;
+
 			/* MAXIM_CODEC is connected to SSP1. */
 			if (!strcmp(broxton_dais[i].codecs->dai_name,
 				    BXT_MAXIM_CODEC_DAI)) {
@@ -822,6 +825,9 @@ static int broxton_audio_probe(struct platform_device *pdev)
 			broxton_audio_card.name = "cmlda7219max";
 
 		for (i = 0; i < ARRAY_SIZE(broxton_dais); i++) {
+			if (!broxton_dais[i].codecs->dai_name)
+				continue;
+
 			/* MAXIM_CODEC is connected to SSP1. */
 			if (!strcmp(broxton_dais[i].codecs->dai_name,
 					BXT_MAXIM_CODEC_DAI)) {
diff --git a/sound/soc/intel/boards/bxt_rt298.c b/sound/soc/intel/boards/bxt_rt298.c
index 4631106f2a28..c0eb65c14aa9 100644
--- a/sound/soc/intel/boards/bxt_rt298.c
+++ b/sound/soc/intel/boards/bxt_rt298.c
@@ -604,7 +604,8 @@ static int broxton_audio_probe(struct platform_device *pdev)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(broxton_rt298_dais); i++) {
-		if (!strncmp(card->dai_link[i].codecs->name, "i2c-INT343A:00",
+		if (card->dai_link[i].codecs->name &&
+		    !strncmp(card->dai_link[i].codecs->name, "i2c-INT343A:00",
 			     I2C_NAME_SIZE)) {
 			if (!strncmp(card->name, "broxton-rt298",
 				     PLATFORM_NAME_SIZE)) {
diff --git a/sound/soc/intel/boards/bytcht_cx2072x.c b/sound/soc/intel/boards/bytcht_cx2072x.c
index 10a84a2c1036..c014d85a08b2 100644
--- a/sound/soc/intel/boards/bytcht_cx2072x.c
+++ b/sound/soc/intel/boards/bytcht_cx2072x.c
@@ -241,7 +241,8 @@ static int snd_byt_cht_cx2072x_probe(struct platform_device *pdev)
 
 	/* fix index of codec dai */
 	for (i = 0; i < ARRAY_SIZE(byt_cht_cx2072x_dais); i++) {
-		if (!strcmp(byt_cht_cx2072x_dais[i].codecs->name,
+		if (byt_cht_cx2072x_dais[i].codecs->name &&
+		    !strcmp(byt_cht_cx2072x_dais[i].codecs->name,
 			    "i2c-14F10720:00")) {
 			dai_index = i;
 			break;
diff --git a/sound/soc/intel/boards/bytcht_da7213.c b/sound/soc/intel/boards/bytcht_da7213.c
index 7e5eea690023..f4ac3ddd148b 100644
--- a/sound/soc/intel/boards/bytcht_da7213.c
+++ b/sound/soc/intel/boards/bytcht_da7213.c
@@ -245,7 +245,8 @@ static int bytcht_da7213_probe(struct platform_device *pdev)
 
 	/* fix index of codec dai */
 	for (i = 0; i < ARRAY_SIZE(dailink); i++) {
-		if (!strcmp(dailink[i].codecs->name, "i2c-DLGS7213:00")) {
+		if (dailink[i].codecs->name &&
+		    !strcmp(dailink[i].codecs->name, "i2c-DLGS7213:00")) {
 			dai_index = i;
 			break;
 		}
diff --git a/sound/soc/intel/boards/bytcht_es8316.c b/sound/soc/intel/boards/bytcht_es8316.c
index 1564a88a885e..2fcec2e02bb5 100644
--- a/sound/soc/intel/boards/bytcht_es8316.c
+++ b/sound/soc/intel/boards/bytcht_es8316.c
@@ -546,7 +546,8 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev)
 
 	/* fix index of codec dai */
 	for (i = 0; i < ARRAY_SIZE(byt_cht_es8316_dais); i++) {
-		if (!strcmp(byt_cht_es8316_dais[i].codecs->name,
+		if (byt_cht_es8316_dais[i].codecs->name &&
+		    !strcmp(byt_cht_es8316_dais[i].codecs->name,
 			    "i2c-ESSX8316:00")) {
 			dai_index = i;
 			break;
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 42466b4b1ca4..05f38d1f7d82 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -685,6 +685,18 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 					BYT_RT5640_SSP0_AIF1 |
 					BYT_RT5640_MCLK_EN),
 	},
+	{	/* Chuwi Vi8 dual-boot (CWI506) */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Insyde"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "i86"),
+			/* The above are too generic, also match BIOS info */
+			DMI_MATCH(DMI_BIOS_VERSION, "CHUWI2.D86JHBNR02"),
+		},
+		.driver_data = (void *)(BYTCR_INPUT_DEFAULTS |
+					BYT_RT5640_MONO_SPEAKER |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
 	{
 		/* Chuwi Vi10 (CWI505) */
 		.matches = {
@@ -1652,7 +1664,8 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev)
 
 	/* fix index of codec dai */
 	for (i = 0; i < ARRAY_SIZE(byt_rt5640_dais); i++) {
-		if (!strcmp(byt_rt5640_dais[i].codecs->name,
+		if (byt_rt5640_dais[i].codecs->name &&
+		    !strcmp(byt_rt5640_dais[i].codecs->name,
 			    "i2c-10EC5640:00")) {
 			dai_index = i;
 			break;
diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index f9fe8414f454..80c841b000a3 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -910,7 +910,8 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 
 	/* fix index of codec dai */
 	for (i = 0; i < ARRAY_SIZE(byt_rt5651_dais); i++) {
-		if (!strcmp(byt_rt5651_dais[i].codecs->name,
+		if (byt_rt5651_dais[i].codecs->name &&
+		    !strcmp(byt_rt5651_dais[i].codecs->name,
 			    "i2c-10EC5651:00")) {
 			dai_index = i;
 			break;
diff --git a/sound/soc/intel/boards/bytcr_wm5102.c b/sound/soc/intel/boards/bytcr_wm5102.c
index 6978ebde6693..cccb5e90c0fe 100644
--- a/sound/soc/intel/boards/bytcr_wm5102.c
+++ b/sound/soc/intel/boards/bytcr_wm5102.c
@@ -605,7 +605,8 @@ static int snd_byt_wm5102_mc_probe(struct platform_device *pdev)
 
 	/* find index of codec dai */
 	for (i = 0; i < ARRAY_SIZE(byt_wm5102_dais); i++) {
-		if (!strcmp(byt_wm5102_dais[i].codecs->name,
+		if (byt_wm5102_dais[i].codecs->name &&
+		    !strcmp(byt_wm5102_dais[i].codecs->name,
 			    "wm5102-codec")) {
 			dai_index = i;
 			break;
diff --git a/sound/soc/intel/boards/cht_bsw_rt5645.c b/sound/soc/intel/boards/cht_bsw_rt5645.c
index c952a96cde7e..eb41b7115d01 100644
--- a/sound/soc/intel/boards/cht_bsw_rt5645.c
+++ b/sound/soc/intel/boards/cht_bsw_rt5645.c
@@ -40,7 +40,6 @@ struct cht_acpi_card {
 struct cht_mc_private {
 	struct snd_soc_jack jack;
 	struct cht_acpi_card *acpi_card;
-	char codec_name[SND_ACPI_I2C_ID_LEN];
 	struct clk *mclk;
 };
 
@@ -567,14 +566,14 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 	}
 
 	card->dev = &pdev->dev;
-	sprintf(drv->codec_name, "i2c-%s:00", drv->acpi_card->codec_id);
 
 	/* set correct codec name */
 	for (i = 0; i < ARRAY_SIZE(cht_dailink); i++)
-		if (!strcmp(card->dai_link[i].codecs->name,
+		if (cht_dailink[i].codecs->name &&
+		    !strcmp(cht_dailink[i].codecs->name,
 			    "i2c-10EC5645:00")) {
-			card->dai_link[i].codecs->name = drv->codec_name;
 			dai_index = i;
+			break;
 		}
 
 	/* fixup codec name based on HID */
diff --git a/sound/soc/intel/boards/cht_bsw_rt5672.c b/sound/soc/intel/boards/cht_bsw_rt5672.c
index 8cf0b33cc02e..be2d1a8dbca8 100644
--- a/sound/soc/intel/boards/cht_bsw_rt5672.c
+++ b/sound/soc/intel/boards/cht_bsw_rt5672.c
@@ -466,7 +466,8 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 
 	/* find index of codec dai */
 	for (i = 0; i < ARRAY_SIZE(cht_dailink); i++) {
-		if (!strcmp(cht_dailink[i].codecs->name, RT5672_I2C_DEFAULT)) {
+		if (cht_dailink[i].codecs->name &&
+		    !strcmp(cht_dailink[i].codecs->name, RT5672_I2C_DEFAULT)) {
 			dai_index = i;
 			break;
 		}
diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c
index 9ecee43ad84d..300391fbc2fc 100644
--- a/sound/soc/intel/boards/sof_sdw.c
+++ b/sound/soc/intel/boards/sof_sdw.c
@@ -1256,11 +1256,11 @@ static int fill_sdw_codec_dlc(struct device *dev,
 	else if (is_unique_device(adr_link, sdw_version, mfg_id, part_id,
 				  class_id, adr_index))
 		codec->name = devm_kasprintf(dev, GFP_KERNEL,
-					     "sdw:%01x:%04x:%04x:%02x", link_id,
+					     "sdw:0:%01x:%04x:%04x:%02x", link_id,
 					     mfg_id, part_id, class_id);
 	else
 		codec->name = devm_kasprintf(dev, GFP_KERNEL,
-					     "sdw:%01x:%04x:%04x:%02x:%01x", link_id,
+					     "sdw:0:%01x:%04x:%04x:%02x:%01x", link_id,
 					     mfg_id, part_id, class_id, unique_id);
 
 	if (!codec->name)
diff --git a/sound/soc/mediatek/common/mtk-dsp-sof-common.c b/sound/soc/mediatek/common/mtk-dsp-sof-common.c
index f3894010f656..7ec8965a70c0 100644
--- a/sound/soc/mediatek/common/mtk-dsp-sof-common.c
+++ b/sound/soc/mediatek/common/mtk-dsp-sof-common.c
@@ -24,7 +24,7 @@ int mtk_sof_dai_link_fixup(struct snd_soc_pcm_runtime *rtd,
 		struct snd_soc_dai_link *sof_dai_link = NULL;
 		const struct sof_conn_stream *conn = &sof_priv->conn_streams[i];
 
-		if (strcmp(rtd->dai_link->name, conn->normal_link))
+		if (conn->normal_link && strcmp(rtd->dai_link->name, conn->normal_link))
 			continue;
 
 		for_each_card_rtds(card, runtime) {
diff --git a/sound/soc/mediatek/mt8192/mt8192-mt6359-rt1015-rt5682.c b/sound/soc/mediatek/mt8192/mt8192-mt6359-rt1015-rt5682.c
index 5bd6addd1450..bfcb2c486c39 100644
--- a/sound/soc/mediatek/mt8192/mt8192-mt6359-rt1015-rt5682.c
+++ b/sound/soc/mediatek/mt8192/mt8192-mt6359-rt1015-rt5682.c
@@ -1208,7 +1208,8 @@ static int mt8192_mt6359_dev_probe(struct platform_device *pdev)
 			dai_link->ignore = 0;
 		}
 
-		if (strcmp(dai_link->codecs[0].dai_name, RT1015_CODEC_DAI) == 0)
+		if (dai_link->num_codecs && dai_link->codecs[0].dai_name &&
+		    strcmp(dai_link->codecs[0].dai_name, RT1015_CODEC_DAI) == 0)
 			dai_link->ops = &mt8192_rt1015_i2s_ops;
 
 		if (!dai_link->platforms->name)
diff --git a/sound/soc/mediatek/mt8195/mt8195-afe-pcm.c b/sound/soc/mediatek/mt8195/mt8195-afe-pcm.c
index 1e33863c85ca..620d7ade1992 100644
--- a/sound/soc/mediatek/mt8195/mt8195-afe-pcm.c
+++ b/sound/soc/mediatek/mt8195/mt8195-afe-pcm.c
@@ -1795,10 +1795,6 @@ static const struct snd_kcontrol_new mt8195_memif_controls[] = {
 			    MT8195_AFE_IRQ_28),
 };
 
-static const struct snd_soc_component_driver mt8195_afe_pcm_dai_component = {
-	.name = "mt8195-afe-pcm-dai",
-};
-
 static const struct mtk_base_memif_data memif_data[MT8195_AFE_MEMIF_NUM] = {
 	[MT8195_AFE_MEMIF_DL2] = {
 		.name = "DL2",
@@ -3037,7 +3033,6 @@ static int mt8195_afe_pcm_dev_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct reset_control *rstc;
 	int i, irq_id, ret;
-	struct snd_soc_component *component;
 
 	ret = of_reserved_mem_device_init(dev);
 	if (ret)
@@ -3170,36 +3165,12 @@ static int mt8195_afe_pcm_dev_probe(struct platform_device *pdev)
 
 	/* register component */
 	ret = devm_snd_soc_register_component(dev, &mt8195_afe_component,
-					      NULL, 0);
+					      afe->dai_drivers, afe->num_dai_drivers);
 	if (ret) {
 		dev_warn(dev, "err_platform\n");
 		goto err_pm_put;
 	}
 
-	component = devm_kzalloc(dev, sizeof(*component), GFP_KERNEL);
-	if (!component) {
-		ret = -ENOMEM;
-		goto err_pm_put;
-	}
-
-	ret = snd_soc_component_initialize(component,
-					   &mt8195_afe_pcm_dai_component,
-					   dev);
-	if (ret)
-		goto err_pm_put;
-
-#ifdef CONFIG_DEBUG_FS
-	component->debugfs_prefix = "pcm";
-#endif
-
-	ret = snd_soc_add_component(component,
-				    afe->dai_drivers,
-				    afe->num_dai_drivers);
-	if (ret) {
-		dev_warn(dev, "err_dai_component\n");
-		goto err_pm_put;
-	}
-
 	ret = regmap_multi_reg_write(afe->regmap, mt8195_afe_reg_defaults,
 				     ARRAY_SIZE(mt8195_afe_reg_defaults));
 	if (ret)
@@ -3224,8 +3195,6 @@ err_pm_put:
 
 static void mt8195_afe_pcm_dev_remove(struct platform_device *pdev)
 {
-	snd_soc_unregister_component(&pdev->dev);
-
 	pm_runtime_disable(&pdev->dev);
 	if (!pm_runtime_status_suspended(&pdev->dev))
 		mt8195_afe_runtime_suspend(&pdev->dev);
diff --git a/sound/soc/mediatek/mt8195/mt8195-mt6359.c b/sound/soc/mediatek/mt8195/mt8195-mt6359.c
index 4feb9fb76967..53fd8a897b9d 100644
--- a/sound/soc/mediatek/mt8195/mt8195-mt6359.c
+++ b/sound/soc/mediatek/mt8195/mt8195-mt6359.c
@@ -934,12 +934,11 @@ SND_SOC_DAILINK_DEFS(ETDM1_IN_BE,
 
 SND_SOC_DAILINK_DEFS(ETDM2_IN_BE,
 		     DAILINK_COMP_ARRAY(COMP_CPU("ETDM2_IN")),
-		     DAILINK_COMP_ARRAY(COMP_DUMMY()),
+		     DAILINK_COMP_ARRAY(COMP_EMPTY()),
 		     DAILINK_COMP_ARRAY(COMP_EMPTY()));
 
 SND_SOC_DAILINK_DEFS(ETDM1_OUT_BE,
 		     DAILINK_COMP_ARRAY(COMP_CPU("ETDM1_OUT")),
-		     DAILINK_COMP_ARRAY(COMP_DUMMY()),
 		     DAILINK_COMP_ARRAY(COMP_EMPTY()));
 
 SND_SOC_DAILINK_DEFS(ETDM2_OUT_BE,
@@ -1237,8 +1236,6 @@ static struct snd_soc_dai_link mt8195_mt6359_dai_links[] = {
 			SND_SOC_DAIFMT_NB_NF |
 			SND_SOC_DAIFMT_CBS_CFS,
 		.dpcm_capture = 1,
-		.init = mt8195_rt5682_init,
-		.ops = &mt8195_rt5682_etdm_ops,
 		.be_hw_params_fixup = mt8195_etdm_hw_params_fixup,
 		SND_SOC_DAILINK_REG(ETDM2_IN_BE),
 	},
@@ -1249,7 +1246,6 @@ static struct snd_soc_dai_link mt8195_mt6359_dai_links[] = {
 			SND_SOC_DAIFMT_NB_NF |
 			SND_SOC_DAIFMT_CBS_CFS,
 		.dpcm_playback = 1,
-		.ops = &mt8195_rt5682_etdm_ops,
 		.be_hw_params_fixup = mt8195_etdm_hw_params_fixup,
 		SND_SOC_DAILINK_REG(ETDM1_OUT_BE),
 	},
@@ -1381,7 +1377,7 @@ static int mt8195_mt6359_dev_probe(struct platform_device *pdev)
 	struct snd_soc_dai_link *dai_link;
 	struct mtk_soc_card_data *soc_card_data;
 	struct mt8195_mt6359_priv *mach_priv;
-	struct device_node *platform_node, *adsp_node, *dp_node, *hdmi_node;
+	struct device_node *platform_node, *adsp_node, *codec_node, *dp_node, *hdmi_node;
 	struct mt8195_card_data *card_data;
 	int is5682s = 0;
 	int init6359 = 0;
@@ -1401,8 +1397,12 @@ static int mt8195_mt6359_dev_probe(struct platform_device *pdev)
 	if (!card->name)
 		card->name = card_data->name;
 
-	if (strstr(card->name, "_5682s"))
+	if (strstr(card->name, "_5682s")) {
+		codec_node = of_find_compatible_node(NULL, NULL, "realtek,rt5682s");
 		is5682s = 1;
+	} else
+		codec_node = of_find_compatible_node(NULL, NULL, "realtek,rt5682i");
+
 	soc_card_data = devm_kzalloc(&pdev->dev, sizeof(*card_data), GFP_KERNEL);
 	if (!soc_card_data)
 		return -ENOMEM;
@@ -1488,12 +1488,27 @@ static int mt8195_mt6359_dev_probe(struct platform_device *pdev)
 				dai_link->codecs->dai_name = "i2s-hifi";
 				dai_link->init = mt8195_hdmi_codec_init;
 			}
-		} else if (strcmp(dai_link->name, "ETDM1_OUT_BE") == 0 ||
-			   strcmp(dai_link->name, "ETDM2_IN_BE") == 0) {
-			dai_link->codecs->name =
-				is5682s ? RT5682S_DEV0_NAME : RT5682_DEV0_NAME;
-			dai_link->codecs->dai_name =
-				is5682s ? RT5682S_CODEC_DAI : RT5682_CODEC_DAI;
+		} else if (strcmp(dai_link->name, "ETDM1_OUT_BE") == 0) {
+			if (!codec_node) {
+				dev_err(&pdev->dev, "Codec not found!\n");
+			} else {
+				dai_link->codecs->of_node = codec_node;
+				dai_link->codecs->name = NULL;
+				dai_link->codecs->dai_name =
+					is5682s ? RT5682S_CODEC_DAI : RT5682_CODEC_DAI;
+				dai_link->init = mt8195_rt5682_init;
+				dai_link->ops = &mt8195_rt5682_etdm_ops;
+			}
+		} else if (strcmp(dai_link->name, "ETDM2_IN_BE") == 0) {
+			if (!codec_node) {
+				dev_err(&pdev->dev, "Codec not found!\n");
+			} else {
+				dai_link->codecs->of_node = codec_node;
+				dai_link->codecs->name = NULL;
+				dai_link->codecs->dai_name =
+					is5682s ? RT5682S_CODEC_DAI : RT5682_CODEC_DAI;
+				dai_link->ops = &mt8195_rt5682_etdm_ops;
+			}
 		} else if (strcmp(dai_link->name, "DL_SRC_BE") == 0 ||
 			   strcmp(dai_link->name, "UL_SRC1_BE") == 0 ||
 			   strcmp(dai_link->name, "UL_SRC2_BE") == 0) {
diff --git a/sound/soc/qcom/lpass-cdc-dma.c b/sound/soc/qcom/lpass-cdc-dma.c
index 48b03e60e3a3..8106c586f68a 100644
--- a/sound/soc/qcom/lpass-cdc-dma.c
+++ b/sound/soc/qcom/lpass-cdc-dma.c
@@ -259,7 +259,7 @@ static int lpass_cdc_dma_daiops_trigger(struct snd_pcm_substream *substream,
 				    int cmd, struct snd_soc_dai *dai)
 {
 	struct snd_soc_pcm_runtime *soc_runtime = snd_soc_substream_to_rtd(substream);
-	struct lpaif_dmactl *dmactl;
+	struct lpaif_dmactl *dmactl = NULL;
 	int ret = 0, id;
 
 	switch (cmd) {
diff --git a/sound/soc/qcom/qdsp6/q6apm-dai.c b/sound/soc/qcom/qdsp6/q6apm-dai.c
index 052e40cb38fe..00bbd291be5c 100644
--- a/sound/soc/qcom/qdsp6/q6apm-dai.c
+++ b/sound/soc/qcom/qdsp6/q6apm-dai.c
@@ -123,7 +123,7 @@ static struct snd_pcm_hardware q6apm_dai_hardware_playback = {
 	.fifo_size =            0,
 };
 
-static void event_handler(uint32_t opcode, uint32_t token, uint32_t *payload, void *priv)
+static void event_handler(uint32_t opcode, uint32_t token, void *payload, void *priv)
 {
 	struct q6apm_dai_rtd *prtd = priv;
 	struct snd_pcm_substream *substream = prtd->substream;
@@ -157,7 +157,7 @@ static void event_handler(uint32_t opcode, uint32_t token, uint32_t *payload, vo
 }
 
 static void event_handler_compr(uint32_t opcode, uint32_t token,
-				uint32_t *payload, void *priv)
+				void *payload, void *priv)
 {
 	struct q6apm_dai_rtd *prtd = priv;
 	struct snd_compr_stream *substream = prtd->cstream;
@@ -352,7 +352,7 @@ static int q6apm_dai_open(struct snd_soc_component *component,
 
 	spin_lock_init(&prtd->lock);
 	prtd->substream = substream;
-	prtd->graph = q6apm_graph_open(dev, (q6apm_cb)event_handler, prtd, graph_id);
+	prtd->graph = q6apm_graph_open(dev, event_handler, prtd, graph_id);
 	if (IS_ERR(prtd->graph)) {
 		dev_err(dev, "%s: Could not allocate memory\n", __func__);
 		ret = PTR_ERR(prtd->graph);
@@ -496,7 +496,7 @@ static int q6apm_dai_compr_open(struct snd_soc_component *component,
 		return -ENOMEM;
 
 	prtd->cstream = stream;
-	prtd->graph = q6apm_graph_open(dev, (q6apm_cb)event_handler_compr, prtd, graph_id);
+	prtd->graph = q6apm_graph_open(dev, event_handler_compr, prtd, graph_id);
 	if (IS_ERR(prtd->graph)) {
 		ret = PTR_ERR(prtd->graph);
 		kfree(prtd);
diff --git a/sound/soc/qcom/sc8280xp.c b/sound/soc/qcom/sc8280xp.c
index ed4bb551bfbb..b7fd503a1666 100644
--- a/sound/soc/qcom/sc8280xp.c
+++ b/sound/soc/qcom/sc8280xp.c
@@ -32,12 +32,14 @@ static int sc8280xp_snd_init(struct snd_soc_pcm_runtime *rtd)
 	case WSA_CODEC_DMA_RX_0:
 	case WSA_CODEC_DMA_RX_1:
 		/*
-		 * set limit of 0dB on Digital Volume for Speakers,
-		 * this can prevent damage of speakers to some extent without
-		 * active speaker protection
+		 * Set limit of -3 dB on Digital Volume and 0 dB on PA Volume
+		 * to reduce the risk of speaker damage until we have active
+		 * speaker protection in place.
 		 */
-		snd_soc_limit_volume(card, "WSA_RX0 Digital Volume", 84);
-		snd_soc_limit_volume(card, "WSA_RX1 Digital Volume", 84);
+		snd_soc_limit_volume(card, "WSA_RX0 Digital Volume", 81);
+		snd_soc_limit_volume(card, "WSA_RX1 Digital Volume", 81);
+		snd_soc_limit_volume(card, "SpkrLeft PA Volume", 17);
+		snd_soc_limit_volume(card, "SpkrRight PA Volume", 17);
 		break;
 	default:
 		break;
diff --git a/sound/soc/rockchip/rk3399_gru_sound.c b/sound/soc/rockchip/rk3399_gru_sound.c
index 1a504ebd3a0e..6c89c7331229 100644
--- a/sound/soc/rockchip/rk3399_gru_sound.c
+++ b/sound/soc/rockchip/rk3399_gru_sound.c
@@ -446,7 +446,7 @@ static const struct rockchip_sound_route rockchip_routes[] = {
 
 struct dailink_match_data {
 	const char *compatible;
-	struct bus_type *bus_type;
+	const struct bus_type *bus_type;
 };
 
 static const struct dailink_match_data dailink_match[] = {
diff --git a/sound/soc/sh/rcar/adg.c b/sound/soc/sh/rcar/adg.c
index 230c48648af3..afd69c6eb654 100644
--- a/sound/soc/sh/rcar/adg.c
+++ b/sound/soc/sh/rcar/adg.c
@@ -111,6 +111,13 @@ static u32 rsnd_adg_ssi_ws_timing_gen2(struct rsnd_dai_stream *io)
 			ws = 7;
 			break;
 		}
+	} else {
+		/*
+		 * SSI8 is not connected to ADG.
+		 * Thus SSI9 is using ws = 8
+		 */
+		if (id == 9)
+			ws = 8;
 	}
 
 	return (0x6 + ws) << 8;
diff --git a/sound/soc/soc-card.c b/sound/soc/soc-card.c
index 285ab4c9c716..8a2f163da6bc 100644
--- a/sound/soc/soc-card.c
+++ b/sound/soc/soc-card.c
@@ -5,6 +5,9 @@
 // Copyright (C) 2019 Renesas Electronics Corp.
 // Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
 //
+
+#include <linux/lockdep.h>
+#include <linux/rwsem.h>
 #include <sound/soc.h>
 #include <sound/jack.h>
 
@@ -26,12 +29,15 @@ static inline int _soc_card_ret(struct snd_soc_card *card,
 	return ret;
 }
 
-struct snd_kcontrol *snd_soc_card_get_kcontrol(struct snd_soc_card *soc_card,
-					       const char *name)
+struct snd_kcontrol *snd_soc_card_get_kcontrol_locked(struct snd_soc_card *soc_card,
+						      const char *name)
 {
 	struct snd_card *card = soc_card->snd_card;
 	struct snd_kcontrol *kctl;
 
+	/* must be held read or write */
+	lockdep_assert_held(&card->controls_rwsem);
+
 	if (unlikely(!name))
 		return NULL;
 
@@ -40,6 +46,20 @@ struct snd_kcontrol *snd_soc_card_get_kcontrol(struct snd_soc_card *soc_card,
 			return kctl;
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(snd_soc_card_get_kcontrol_locked);
+
+struct snd_kcontrol *snd_soc_card_get_kcontrol(struct snd_soc_card *soc_card,
+					       const char *name)
+{
+	struct snd_card *card = soc_card->snd_card;
+	struct snd_kcontrol *kctl;
+
+	down_read(&card->controls_rwsem);
+	kctl = snd_soc_card_get_kcontrol_locked(soc_card, name);
+	up_read(&card->controls_rwsem);
+
+	return kctl;
+}
 EXPORT_SYMBOL_GPL(snd_soc_card_get_kcontrol);
 
 static int jack_new(struct snd_soc_card *card, const char *id, int type,
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index f8524b5bfb33..516350533e73 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1037,7 +1037,7 @@ component_dai_empty:
 	return -EINVAL;
 }
 
-#define MAX_DEFAULT_CH_MAP_SIZE 7
+#define MAX_DEFAULT_CH_MAP_SIZE 8
 static struct snd_soc_dai_link_ch_map default_ch_map_sync[MAX_DEFAULT_CH_MAP_SIZE] = {
 	{ .cpu = 0, .codec = 0 },
 	{ .cpu = 1, .codec = 1 },
@@ -1046,6 +1046,7 @@ static struct snd_soc_dai_link_ch_map default_ch_map_sync[MAX_DEFAULT_CH_MAP_SIZ
 	{ .cpu = 4, .codec = 4 },
 	{ .cpu = 5, .codec = 5 },
 	{ .cpu = 6, .codec = 6 },
+	{ .cpu = 7, .codec = 7 },
 };
 static struct snd_soc_dai_link_ch_map default_ch_map_1cpu[MAX_DEFAULT_CH_MAP_SIZE] = {
 	{ .cpu = 0, .codec = 0 },
@@ -1055,6 +1056,7 @@ static struct snd_soc_dai_link_ch_map default_ch_map_1cpu[MAX_DEFAULT_CH_MAP_SIZ
 	{ .cpu = 0, .codec = 4 },
 	{ .cpu = 0, .codec = 5 },
 	{ .cpu = 0, .codec = 6 },
+	{ .cpu = 0, .codec = 7 },
 };
 static struct snd_soc_dai_link_ch_map default_ch_map_1codec[MAX_DEFAULT_CH_MAP_SIZE] = {
 	{ .cpu = 0, .codec = 0 },
@@ -1064,6 +1066,7 @@ static struct snd_soc_dai_link_ch_map default_ch_map_1codec[MAX_DEFAULT_CH_MAP_S
 	{ .cpu = 4, .codec = 0 },
 	{ .cpu = 5, .codec = 0 },
 	{ .cpu = 6, .codec = 0 },
+	{ .cpu = 7, .codec = 0 },
 };
 static int snd_soc_compensate_channel_connection_map(struct snd_soc_card *card,
 						     struct snd_soc_dai_link *dai_link)
diff --git a/sound/soc/sof/amd/acp-ipc.c b/sound/soc/sof/amd/acp-ipc.c
index 2743f07a5e08..b44b1b1adb6e 100644
--- a/sound/soc/sof/amd/acp-ipc.c
+++ b/sound/soc/sof/amd/acp-ipc.c
@@ -188,11 +188,13 @@ irqreturn_t acp_sof_ipc_irq_thread(int irq, void *context)
 
 	dsp_ack = snd_sof_dsp_read(sdev, ACP_DSP_BAR, ACP_SCRATCH_REG_0 + dsp_ack_write);
 	if (dsp_ack) {
+		spin_lock_irq(&sdev->ipc_lock);
 		/* handle immediate reply from DSP core */
 		acp_dsp_ipc_get_reply(sdev);
 		snd_sof_ipc_reply(sdev, 0);
 		/* set the done bit */
 		acp_dsp_ipc_dsp_done(sdev);
+		spin_unlock_irq(&sdev->ipc_lock);
 		ipc_irq = true;
 	}
 
diff --git a/sound/soc/sof/amd/acp.c b/sound/soc/sof/amd/acp.c
index 32a741fcb84f..07632ae6ccf5 100644
--- a/sound/soc/sof/amd/acp.c
+++ b/sound/soc/sof/amd/acp.c
@@ -355,21 +355,20 @@ static irqreturn_t acp_irq_thread(int irq, void *context)
 	unsigned int count = ACP_HW_SEM_RETRY_COUNT;
 
 	spin_lock_irq(&sdev->ipc_lock);
-	while (snd_sof_dsp_read(sdev, ACP_DSP_BAR, desc->hw_semaphore_offset)) {
-		/* Wait until acquired HW Semaphore lock or timeout */
-		count--;
-		if (!count) {
-			dev_err(sdev->dev, "%s: Failed to acquire HW lock\n", __func__);
-			spin_unlock_irq(&sdev->ipc_lock);
-			return IRQ_NONE;
-		}
+	/* Wait until acquired HW Semaphore lock or timeout */
+	while (snd_sof_dsp_read(sdev, ACP_DSP_BAR, desc->hw_semaphore_offset) && --count)
+		;
+	spin_unlock_irq(&sdev->ipc_lock);
+
+	if (!count) {
+		dev_err(sdev->dev, "%s: Failed to acquire HW lock\n", __func__);
+		return IRQ_NONE;
 	}
 
 	sof_ops(sdev)->irq_thread(irq, sdev);
 	/* Unlock or Release HW Semaphore */
 	snd_sof_dsp_write(sdev, ACP_DSP_BAR, desc->hw_semaphore_offset, 0x0);
 
-	spin_unlock_irq(&sdev->ipc_lock);
 	return IRQ_HANDLED;
 };
 
diff --git a/sound/soc/sof/intel/pci-lnl.c b/sound/soc/sof/intel/pci-lnl.c
index 78a57eb9cbc3..b26ffe767fab 100644
--- a/sound/soc/sof/intel/pci-lnl.c
+++ b/sound/soc/sof/intel/pci-lnl.c
@@ -36,7 +36,7 @@ static const struct sof_dev_desc lnl_desc = {
 		[SOF_IPC_TYPE_4] = "intel/sof-ipc4/lnl",
 	},
 	.default_tplg_path = {
-		[SOF_IPC_TYPE_4] = "intel/sof-ace-tplg",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
 	},
 	.default_fw_filename = {
 		[SOF_IPC_TYPE_4] = "sof-lnl.ri",
diff --git a/sound/soc/sof/intel/pci-tgl.c b/sound/soc/sof/intel/pci-tgl.c
index 0660d4b2ac96..a361ee9d1107 100644
--- a/sound/soc/sof/intel/pci-tgl.c
+++ b/sound/soc/sof/intel/pci-tgl.c
@@ -33,18 +33,18 @@ static const struct sof_dev_desc tgl_desc = {
 	.dspless_mode_supported	= true,		/* Only supported for HDaudio */
 	.default_fw_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof",
-		[SOF_IPC_TYPE_4] = "intel/avs/tgl",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4/tgl",
 	},
 	.default_lib_path = {
-		[SOF_IPC_TYPE_4] = "intel/avs-lib/tgl",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/tgl",
 	},
 	.default_tplg_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof-tplg",
-		[SOF_IPC_TYPE_4] = "intel/avs-tplg",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
 	},
 	.default_fw_filename = {
 		[SOF_IPC_TYPE_3] = "sof-tgl.ri",
-		[SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+		[SOF_IPC_TYPE_4] = "sof-tgl.ri",
 	},
 	.nocodec_tplg_filename = "sof-tgl-nocodec.tplg",
 	.ops = &sof_tgl_ops,
@@ -66,18 +66,18 @@ static const struct sof_dev_desc tglh_desc = {
 	.dspless_mode_supported	= true,		/* Only supported for HDaudio */
 	.default_fw_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof",
-		[SOF_IPC_TYPE_4] = "intel/avs/tgl-h",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4/tgl-h",
 	},
 	.default_lib_path = {
-		[SOF_IPC_TYPE_4] = "intel/avs-lib/tgl-h",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/tgl-h",
 	},
 	.default_tplg_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof-tplg",
-		[SOF_IPC_TYPE_4] = "intel/avs-tplg",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
 	},
 	.default_fw_filename = {
 		[SOF_IPC_TYPE_3] = "sof-tgl-h.ri",
-		[SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+		[SOF_IPC_TYPE_4] = "sof-tgl-h.ri",
 	},
 	.nocodec_tplg_filename = "sof-tgl-nocodec.tplg",
 	.ops = &sof_tgl_ops,
@@ -98,18 +98,18 @@ static const struct sof_dev_desc ehl_desc = {
 	.dspless_mode_supported	= true,		/* Only supported for HDaudio */
 	.default_fw_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof",
-		[SOF_IPC_TYPE_4] = "intel/avs/ehl",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4/ehl",
 	},
 	.default_lib_path = {
-		[SOF_IPC_TYPE_4] = "intel/avs-lib/ehl",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/ehl",
 	},
 	.default_tplg_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof-tplg",
-		[SOF_IPC_TYPE_4] = "intel/avs-tplg",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
 	},
 	.default_fw_filename = {
 		[SOF_IPC_TYPE_3] = "sof-ehl.ri",
-		[SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+		[SOF_IPC_TYPE_4] = "sof-ehl.ri",
 	},
 	.nocodec_tplg_filename = "sof-ehl-nocodec.tplg",
 	.ops = &sof_tgl_ops,
@@ -131,18 +131,18 @@ static const struct sof_dev_desc adls_desc = {
 	.dspless_mode_supported	= true,		/* Only supported for HDaudio */
 	.default_fw_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof",
-		[SOF_IPC_TYPE_4] = "intel/avs/adl-s",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4/adl-s",
 	},
 	.default_lib_path = {
-		[SOF_IPC_TYPE_4] = "intel/avs-lib/adl-s",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/adl-s",
 	},
 	.default_tplg_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof-tplg",
-		[SOF_IPC_TYPE_4] = "intel/avs-tplg",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
 	},
 	.default_fw_filename = {
 		[SOF_IPC_TYPE_3] = "sof-adl-s.ri",
-		[SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+		[SOF_IPC_TYPE_4] = "sof-adl-s.ri",
 	},
 	.nocodec_tplg_filename = "sof-adl-nocodec.tplg",
 	.ops = &sof_tgl_ops,
@@ -164,18 +164,18 @@ static const struct sof_dev_desc adl_desc = {
 	.dspless_mode_supported	= true,		/* Only supported for HDaudio */
 	.default_fw_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof",
-		[SOF_IPC_TYPE_4] = "intel/avs/adl",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4/adl",
 	},
 	.default_lib_path = {
-		[SOF_IPC_TYPE_4] = "intel/avs-lib/adl",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/adl",
 	},
 	.default_tplg_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof-tplg",
-		[SOF_IPC_TYPE_4] = "intel/avs-tplg",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
 	},
 	.default_fw_filename = {
 		[SOF_IPC_TYPE_3] = "sof-adl.ri",
-		[SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+		[SOF_IPC_TYPE_4] = "sof-adl.ri",
 	},
 	.nocodec_tplg_filename = "sof-adl-nocodec.tplg",
 	.ops = &sof_tgl_ops,
@@ -197,18 +197,18 @@ static const struct sof_dev_desc adl_n_desc = {
 	.dspless_mode_supported	= true,		/* Only supported for HDaudio */
 	.default_fw_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof",
-		[SOF_IPC_TYPE_4] = "intel/avs/adl-n",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4/adl-n",
 	},
 	.default_lib_path = {
-		[SOF_IPC_TYPE_4] = "intel/avs-lib/adl-n",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/adl-n",
 	},
 	.default_tplg_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof-tplg",
-		[SOF_IPC_TYPE_4] = "intel/avs-tplg",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
 	},
 	.default_fw_filename = {
 		[SOF_IPC_TYPE_3] = "sof-adl-n.ri",
-		[SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+		[SOF_IPC_TYPE_4] = "sof-adl-n.ri",
 	},
 	.nocodec_tplg_filename = "sof-adl-nocodec.tplg",
 	.ops = &sof_tgl_ops,
@@ -230,18 +230,18 @@ static const struct sof_dev_desc rpls_desc = {
 	.dspless_mode_supported	= true,		/* Only supported for HDaudio */
 	.default_fw_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof",
-		[SOF_IPC_TYPE_4] = "intel/avs/rpl-s",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4/rpl-s",
 	},
 	.default_lib_path = {
-		[SOF_IPC_TYPE_4] = "intel/avs-lib/rpl-s",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/rpl-s",
 	},
 	.default_tplg_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof-tplg",
-		[SOF_IPC_TYPE_4] = "intel/avs-tplg",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
 	},
 	.default_fw_filename = {
 		[SOF_IPC_TYPE_3] = "sof-rpl-s.ri",
-		[SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+		[SOF_IPC_TYPE_4] = "sof-rpl-s.ri",
 	},
 	.nocodec_tplg_filename = "sof-rpl-nocodec.tplg",
 	.ops = &sof_tgl_ops,
@@ -263,18 +263,18 @@ static const struct sof_dev_desc rpl_desc = {
 	.dspless_mode_supported	= true,		/* Only supported for HDaudio */
 	.default_fw_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof",
-		[SOF_IPC_TYPE_4] = "intel/avs/rpl",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4/rpl",
 	},
 	.default_lib_path = {
-		[SOF_IPC_TYPE_4] = "intel/avs-lib/rpl",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/rpl",
 	},
 	.default_tplg_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof-tplg",
-		[SOF_IPC_TYPE_4] = "intel/avs-tplg",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
 	},
 	.default_fw_filename = {
 		[SOF_IPC_TYPE_3] = "sof-rpl.ri",
-		[SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+		[SOF_IPC_TYPE_4] = "sof-rpl.ri",
 	},
 	.nocodec_tplg_filename = "sof-rpl-nocodec.tplg",
 	.ops = &sof_tgl_ops,
diff --git a/sound/soc/sof/ipc3-dtrace.c b/sound/soc/sof/ipc3-dtrace.c
index 93b189c2d2ee..0dca139322f3 100644
--- a/sound/soc/sof/ipc3-dtrace.c
+++ b/sound/soc/sof/ipc3-dtrace.c
@@ -137,7 +137,6 @@ static int trace_filter_parse(struct snd_sof_dev *sdev, char *string,
 			dev_err(sdev->dev,
 				"Parsing filter entry '%s' failed with %d\n",
 				entry, entry_len);
-			kfree(*out);
 			return -EINVAL;
 		}
 	}
@@ -209,13 +208,13 @@ static ssize_t dfsentry_trace_filter_write(struct file *file, const char __user
 		ret = ipc3_trace_update_filter(sdev, num_elems, elems);
 		if (ret < 0) {
 			dev_err(sdev->dev, "Filter update failed: %d\n", ret);
-			kfree(elems);
 			goto error;
 		}
 	}
 	ret = count;
 error:
 	kfree(string);
+	kfree(elems);
 	return ret;
 }
 
diff --git a/sound/soc/sof/ipc3-topology.c b/sound/soc/sof/ipc3-topology.c
index a8832a1c1a24..d47698f4be2d 100644
--- a/sound/soc/sof/ipc3-topology.c
+++ b/sound/soc/sof/ipc3-topology.c
@@ -2360,27 +2360,16 @@ static int sof_tear_down_left_over_pipelines(struct snd_sof_dev *sdev)
 	return 0;
 }
 
-/*
- * For older firmware, this function doesn't free widgets for static pipelines during suspend.
- * It only resets use_count for all widgets.
- */
-static int sof_ipc3_tear_down_all_pipelines(struct snd_sof_dev *sdev, bool verify)
+static int sof_ipc3_free_widgets_in_list(struct snd_sof_dev *sdev, bool include_scheduler,
+					 bool *dyn_widgets, bool verify)
 {
 	struct sof_ipc_fw_version *v = &sdev->fw_ready.version;
 	struct snd_sof_widget *swidget;
-	struct snd_sof_route *sroute;
-	bool dyn_widgets = false;
 	int ret;
 
-	/*
-	 * This function is called during suspend and for one-time topology verification during
-	 * first boot. In both cases, there is no need to protect swidget->use_count and
-	 * sroute->setup because during suspend all running streams are suspended and during
-	 * topology loading the sound card unavailable to open PCMs.
-	 */
 	list_for_each_entry(swidget, &sdev->widget_list, list) {
 		if (swidget->dynamic_pipeline_widget) {
-			dyn_widgets = true;
+			*dyn_widgets = true;
 			continue;
 		}
 
@@ -2395,11 +2384,49 @@ static int sof_ipc3_tear_down_all_pipelines(struct snd_sof_dev *sdev, bool verif
 			continue;
 		}
 
+		if (include_scheduler && swidget->id != snd_soc_dapm_scheduler)
+			continue;
+
+		if (!include_scheduler && swidget->id == snd_soc_dapm_scheduler)
+			continue;
+
 		ret = sof_widget_free(sdev, swidget);
 		if (ret < 0)
 			return ret;
 	}
 
+	return 0;
+}
+
+/*
+ * For older firmware, this function doesn't free widgets for static pipelines during suspend.
+ * It only resets use_count for all widgets.
+ */
+static int sof_ipc3_tear_down_all_pipelines(struct snd_sof_dev *sdev, bool verify)
+{
+	struct sof_ipc_fw_version *v = &sdev->fw_ready.version;
+	struct snd_sof_widget *swidget;
+	struct snd_sof_route *sroute;
+	bool dyn_widgets = false;
+	int ret;
+
+	/*
+	 * This function is called during suspend and for one-time topology verification during
+	 * first boot. In both cases, there is no need to protect swidget->use_count and
+	 * sroute->setup because during suspend all running streams are suspended and during
+	 * topology loading the sound card unavailable to open PCMs. Do not free the scheduler
+	 * widgets yet so that the secondary cores do not get powered down before all the widgets
+	 * associated with the scheduler are freed.
+	 */
+	ret = sof_ipc3_free_widgets_in_list(sdev, false, &dyn_widgets, verify);
+	if (ret < 0)
+		return ret;
+
+	/* free all the scheduler widgets now */
+	ret = sof_ipc3_free_widgets_in_list(sdev, true, &dyn_widgets, verify);
+	if (ret < 0)
+		return ret;
+
 	/*
 	 * Tear down all pipelines associated with PCMs that did not get suspended
 	 * and unset the prepare flag so that they can be set up again during resume.
diff --git a/sound/soc/sof/ipc3.c b/sound/soc/sof/ipc3.c
index fb40378ad084..c03dd513fbff 100644
--- a/sound/soc/sof/ipc3.c
+++ b/sound/soc/sof/ipc3.c
@@ -1067,7 +1067,7 @@ static void sof_ipc3_rx_msg(struct snd_sof_dev *sdev)
 		return;
 	}
 
-	if (hdr.size < sizeof(hdr)) {
+	if (hdr.size < sizeof(hdr) || hdr.size > SOF_IPC_MSG_MAX_SIZE) {
 		dev_err(sdev->dev, "The received message size is invalid\n");
 		return;
 	}
diff --git a/sound/soc/sof/ipc4-loader.c b/sound/soc/sof/ipc4-loader.c
index 3539b0a66e1b..c79479afa8d0 100644
--- a/sound/soc/sof/ipc4-loader.c
+++ b/sound/soc/sof/ipc4-loader.c
@@ -482,13 +482,10 @@ void sof_ipc4_update_cpc_from_manifest(struct snd_sof_dev *sdev,
 		msg = "No CPC match in the firmware file's manifest";
 
 no_cpc:
-	dev_warn(sdev->dev, "%s (UUID: %pUL): %s (ibs/obs: %u/%u)\n",
-		 fw_module->man4_module_entry.name,
-		 &fw_module->man4_module_entry.uuid, msg, basecfg->ibs,
-		 basecfg->obs);
-	dev_warn_once(sdev->dev, "Please try to update the firmware.\n");
-	dev_warn_once(sdev->dev, "If the issue persists, file a bug at\n");
-	dev_warn_once(sdev->dev, "https://github.com/thesofproject/sof/issues/\n");
+	dev_dbg(sdev->dev, "%s (UUID: %pUL): %s (ibs/obs: %u/%u)\n",
+		fw_module->man4_module_entry.name,
+		&fw_module->man4_module_entry.uuid, msg, basecfg->ibs,
+		basecfg->obs);
 }
 
 const struct sof_ipc_fw_loader_ops ipc4_loader_ops = {
diff --git a/sound/soc/sof/ipc4-pcm.c b/sound/soc/sof/ipc4-pcm.c
index 39039a647cca..07eb5c6d4adf 100644
--- a/sound/soc/sof/ipc4-pcm.c
+++ b/sound/soc/sof/ipc4-pcm.c
@@ -413,7 +413,18 @@ skip_pause_transition:
 	ret = sof_ipc4_set_multi_pipeline_state(sdev, state, trigger_list);
 	if (ret < 0) {
 		dev_err(sdev->dev, "failed to set final state %d for all pipelines\n", state);
-		goto free;
+		/*
+		 * workaround: if the firmware is crashed while setting the
+		 * pipelines to reset state we must ignore the error code and
+		 * reset it to 0.
+		 * Since the firmware is crashed we will not send IPC messages
+		 * and we are going to see errors printed, but the state of the
+		 * widgets will be correct for the next boot.
+		 */
+		if (sdev->fw_state != SOF_FW_CRASHED || state != SOF_IPC4_PIPE_RESET)
+			goto free;
+
+		ret = 0;
 	}
 
 	/* update RUNNING/RESET state for all pipelines that were just triggered */
@@ -768,10 +779,8 @@ static void sof_ipc4_build_time_info(struct snd_sof_dev *sdev, struct snd_sof_pc
 	info->llp_offset = offsetof(struct sof_ipc4_fw_registers, llp_evad_reading_slot) +
 					sdev->fw_info_box.offset;
 	sof_mailbox_read(sdev, info->llp_offset, &llp_slot, sizeof(llp_slot));
-	if (llp_slot.node_id != dai_copier->data.gtw_cfg.node_id) {
-		dev_info(sdev->dev, "no llp found, fall back to default HDA path");
+	if (llp_slot.node_id != dai_copier->data.gtw_cfg.node_id)
 		info->llp_offset = 0;
-	}
 }
 
 static int sof_ipc4_pcm_hw_params(struct snd_soc_component *component,
diff --git a/sound/soc/sunxi/sun4i-spdif.c b/sound/soc/sunxi/sun4i-spdif.c
index 702386823d17..f41c30955857 100644
--- a/sound/soc/sunxi/sun4i-spdif.c
+++ b/sound/soc/sunxi/sun4i-spdif.c
@@ -577,6 +577,11 @@ static const struct of_device_id sun4i_spdif_of_match[] = {
 		.compatible = "allwinner,sun50i-h6-spdif",
 		.data = &sun50i_h6_spdif_quirks,
 	},
+	{
+		.compatible = "allwinner,sun50i-h616-spdif",
+		/* Essentially the same as the H6, but without RX */
+		.data = &sun50i_h6_spdif_quirks,
+	},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, sun4i_spdif_of_match);
diff --git a/sound/usb/clock.c b/sound/usb/clock.c
index 33db334e6556..60fcb872a80b 100644
--- a/sound/usb/clock.c
+++ b/sound/usb/clock.c
@@ -261,6 +261,8 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip,
 	int ret, i, cur, err, pins, clock_id;
 	const u8 *sources;
 	int proto = fmt->protocol;
+	bool readable, writeable;
+	u32 bmControls;
 
 	entity_id &= 0xff;
 
@@ -292,11 +294,27 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip,
 		sources = GET_VAL(selector, proto, baCSourceID);
 		cur = 0;
 
+		if (proto == UAC_VERSION_3)
+			bmControls = le32_to_cpu(*(__le32 *)(&selector->v3.baCSourceID[0] + pins));
+		else
+			bmControls = *(__u8 *)(&selector->v2.baCSourceID[0] + pins);
+
+		readable = uac_v2v3_control_is_readable(bmControls,
+							UAC2_CX_CLOCK_SELECTOR);
+		writeable = uac_v2v3_control_is_writeable(bmControls,
+							  UAC2_CX_CLOCK_SELECTOR);
+
 		if (pins == 1) {
 			ret = 1;
 			goto find_source;
 		}
 
+		/* for now just warn about buggy device */
+		if (!readable)
+			usb_audio_warn(chip,
+				"%s(): clock selector control is not readable, id %d\n",
+				__func__, clock_id);
+
 		/* the entity ID we are looking at is a selector.
 		 * find out what it currently selects */
 		ret = uac_clock_selector_get_val(chip, clock_id);
@@ -325,17 +343,29 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip,
 					      visited, validate);
 		if (ret > 0) {
 			/* Skip setting clock selector again for some devices */
-			if (chip->quirk_flags & QUIRK_FLAG_SKIP_CLOCK_SELECTOR)
+			if (chip->quirk_flags & QUIRK_FLAG_SKIP_CLOCK_SELECTOR ||
+			    !writeable)
 				return ret;
 			err = uac_clock_selector_set_val(chip, entity_id, cur);
-			if (err < 0)
+			if (err < 0) {
+				if (pins == 1) {
+					usb_audio_dbg(chip,
+						      "%s(): selector returned an error, "
+						      "assuming a firmware bug, id %d, ret %d\n",
+						      __func__, clock_id, err);
+					return ret;
+				}
 				return err;
+			}
 		}
 
 		if (!validate || ret > 0 || !chip->autoclock)
 			return ret;
 
 	find_others:
+		if (!writeable)
+			return -ENXIO;
+
 		/* The current clock source is invalid, try others. */
 		for (i = 1; i <= pins; i++) {
 			if (i == cur)
diff --git a/sound/usb/format.c b/sound/usb/format.c
index ab5fed9f55b6..3b45d0ee7693 100644
--- a/sound/usb/format.c
+++ b/sound/usb/format.c
@@ -470,9 +470,11 @@ static int validate_sample_rate_table_v2v3(struct snd_usb_audio *chip,
 					   int clock)
 {
 	struct usb_device *dev = chip->dev;
+	struct usb_host_interface *alts;
 	unsigned int *table;
 	unsigned int nr_rates;
 	int i, err;
+	u32 bmControls;
 
 	/* performing the rate verification may lead to unexpected USB bus
 	 * behavior afterwards by some unknown reason.  Do this only for the
@@ -481,6 +483,24 @@ static int validate_sample_rate_table_v2v3(struct snd_usb_audio *chip,
 	if (!(chip->quirk_flags & QUIRK_FLAG_VALIDATE_RATES))
 		return 0; /* don't perform the validation as default */
 
+	alts = snd_usb_get_host_interface(chip, fp->iface, fp->altsetting);
+	if (!alts)
+		return 0;
+
+	if (fp->protocol == UAC_VERSION_3) {
+		struct uac3_as_header_descriptor *as = snd_usb_find_csint_desc(
+				alts->extra, alts->extralen, NULL, UAC_AS_GENERAL);
+		bmControls = le32_to_cpu(as->bmControls);
+	} else {
+		struct uac2_as_header_descriptor *as = snd_usb_find_csint_desc(
+				alts->extra, alts->extralen, NULL, UAC_AS_GENERAL);
+		bmControls = as->bmControls;
+	}
+
+	if (!uac_v2v3_control_is_readable(bmControls,
+				UAC2_AS_VAL_ALT_SETTINGS))
+		return 0;
+
 	table = kcalloc(fp->nr_rates, sizeof(*table), GFP_KERNEL);
 	if (!table)
 		return -ENOMEM;
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index 6b0993258e03..c1f2e5a03de9 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -1742,50 +1742,44 @@ static void snd_usbmidi_get_port_info(struct snd_rawmidi *rmidi, int number,
 	}
 }
 
-static struct usb_midi_in_jack_descriptor *find_usb_in_jack_descriptor(
-					struct usb_host_interface *hostif, uint8_t jack_id)
+/* return iJack for the corresponding jackID */
+static int find_usb_ijack(struct usb_host_interface *hostif, uint8_t jack_id)
 {
 	unsigned char *extra = hostif->extra;
 	int extralen = hostif->extralen;
+	struct usb_descriptor_header *h;
+	struct usb_midi_out_jack_descriptor *outjd;
+	struct usb_midi_in_jack_descriptor *injd;
+	size_t sz;
 
 	while (extralen > 4) {
-		struct usb_midi_in_jack_descriptor *injd =
-				(struct usb_midi_in_jack_descriptor *)extra;
+		h = (struct usb_descriptor_header *)extra;
+		if (h->bDescriptorType != USB_DT_CS_INTERFACE)
+			goto next;
 
+		outjd = (struct usb_midi_out_jack_descriptor *)h;
+		if (h->bLength >= sizeof(*outjd) &&
+		    outjd->bDescriptorSubtype == UAC_MIDI_OUT_JACK &&
+		    outjd->bJackID == jack_id) {
+			sz = USB_DT_MIDI_OUT_SIZE(outjd->bNrInputPins);
+			if (outjd->bLength < sz)
+				goto next;
+			return *(extra + sz - 1);
+		}
+
+		injd = (struct usb_midi_in_jack_descriptor *)h;
 		if (injd->bLength >= sizeof(*injd) &&
-		    injd->bDescriptorType == USB_DT_CS_INTERFACE &&
 		    injd->bDescriptorSubtype == UAC_MIDI_IN_JACK &&
-				injd->bJackID == jack_id)
-			return injd;
-		if (!extra[0])
-			break;
-		extralen -= extra[0];
-		extra += extra[0];
-	}
-	return NULL;
-}
-
-static struct usb_midi_out_jack_descriptor *find_usb_out_jack_descriptor(
-					struct usb_host_interface *hostif, uint8_t jack_id)
-{
-	unsigned char *extra = hostif->extra;
-	int extralen = hostif->extralen;
+		    injd->bJackID == jack_id)
+			return injd->iJack;
 
-	while (extralen > 4) {
-		struct usb_midi_out_jack_descriptor *outjd =
-				(struct usb_midi_out_jack_descriptor *)extra;
-
-		if (outjd->bLength >= sizeof(*outjd) &&
-		    outjd->bDescriptorType == USB_DT_CS_INTERFACE &&
-		    outjd->bDescriptorSubtype == UAC_MIDI_OUT_JACK &&
-				outjd->bJackID == jack_id)
-			return outjd;
+next:
 		if (!extra[0])
 			break;
 		extralen -= extra[0];
 		extra += extra[0];
 	}
-	return NULL;
+	return 0;
 }
 
 static void snd_usbmidi_init_substream(struct snd_usb_midi *umidi,
@@ -1796,13 +1790,10 @@ static void snd_usbmidi_init_substream(struct snd_usb_midi *umidi,
 	const char *name_format;
 	struct usb_interface *intf;
 	struct usb_host_interface *hostif;
-	struct usb_midi_in_jack_descriptor *injd;
-	struct usb_midi_out_jack_descriptor *outjd;
 	uint8_t jack_name_buf[32];
 	uint8_t *default_jack_name = "MIDI";
 	uint8_t *jack_name = default_jack_name;
 	uint8_t iJack;
-	size_t sz;
 	int res;
 
 	struct snd_rawmidi_substream *substream =
@@ -1816,21 +1807,7 @@ static void snd_usbmidi_init_substream(struct snd_usb_midi *umidi,
 	intf = umidi->iface;
 	if (intf && jack_id >= 0) {
 		hostif = intf->cur_altsetting;
-		iJack = 0;
-		if (stream != SNDRV_RAWMIDI_STREAM_OUTPUT) {
-			/* in jacks connect to outs */
-			outjd = find_usb_out_jack_descriptor(hostif, jack_id);
-			if (outjd) {
-				sz = USB_DT_MIDI_OUT_SIZE(outjd->bNrInputPins);
-				if (outjd->bLength >= sz)
-					iJack = *(((uint8_t *) outjd) + sz - sizeof(uint8_t));
-			}
-		} else {
-			/* and out jacks connect to ins */
-			injd = find_usb_in_jack_descriptor(hostif, jack_id);
-			if (injd)
-				iJack = injd->iJack;
-		}
+		iJack = find_usb_ijack(hostif, jack_id);
 		if (iJack != 0) {
 			res = usb_string(umidi->dev, iJack, jack_name_buf,
 			  ARRAY_SIZE(jack_name_buf));
diff --git a/sound/usb/midi2.c b/sound/usb/midi2.c
index 1ec177fe284e..820d3e4b672a 100644
--- a/sound/usb/midi2.c
+++ b/sound/usb/midi2.c
@@ -1085,7 +1085,7 @@ int snd_usb_midi_v2_create(struct snd_usb_audio *chip,
 	}
 	if ((quirk && quirk->type != QUIRK_MIDI_STANDARD_INTERFACE) ||
 	    iface->num_altsetting < 2) {
-		usb_audio_info(chip, "Quirk or no altest; falling back to MIDI 1.0\n");
+		usb_audio_info(chip, "Quirk or no altset; falling back to MIDI 1.0\n");
 		goto fallback_to_midi1;
 	}
 	hostif = &iface->altsetting[1];
diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c
index 1de3ddc50eb6..6de605a601e5 100644
--- a/sound/usb/mixer_scarlett2.c
+++ b/sound/usb/mixer_scarlett2.c
@@ -5361,9 +5361,9 @@ static int scarlett2_add_line_out_ctls(struct usb_mixer_interface *mixer)
 			if (private->vol_sw_hw_switch[index])
 				scarlett2_vol_ctl_set_writable(mixer, i, 0);
 
-			snprintf(s, sizeof(s),
-				 "Line Out %02d Volume Control Playback Enum",
-				 i + 1);
+			scnprintf(s, sizeof(s),
+				  "Line Out %02d Volume Control Playback Enum",
+				  i + 1);
 			err = scarlett2_add_new_ctl(mixer,
 						    &scarlett2_sw_hw_enum_ctl,
 						    i, 1, s,
@@ -5406,8 +5406,8 @@ static int scarlett2_add_line_in_ctls(struct usb_mixer_interface *mixer)
 
 	/* Add input level (line/inst) controls */
 	for (i = 0; i < info->level_input_count; i++) {
-		snprintf(s, sizeof(s), fmt, i + 1 + info->level_input_first,
-			 "Level", "Enum");
+		scnprintf(s, sizeof(s), fmt, i + 1 + info->level_input_first,
+			  "Level", "Enum");
 		err = scarlett2_add_new_ctl(mixer, &scarlett2_level_enum_ctl,
 					    i, 1, s, &private->level_ctls[i]);
 		if (err < 0)
@@ -5416,7 +5416,7 @@ static int scarlett2_add_line_in_ctls(struct usb_mixer_interface *mixer)
 
 	/* Add input pad controls */
 	for (i = 0; i < info->pad_input_count; i++) {
-		snprintf(s, sizeof(s), fmt, i + 1, "Pad", "Switch");
+		scnprintf(s, sizeof(s), fmt, i + 1, "Pad", "Switch");
 		err = scarlett2_add_new_ctl(mixer, &scarlett2_pad_ctl,
 					    i, 1, s, &private->pad_ctls[i]);
 		if (err < 0)
@@ -5425,8 +5425,8 @@ static int scarlett2_add_line_in_ctls(struct usb_mixer_interface *mixer)
 
 	/* Add input air controls */
 	for (i = 0; i < info->air_input_count; i++) {
-		snprintf(s, sizeof(s), fmt, i + 1 + info->air_input_first,
-			 "Air", info->air_option ? "Enum" : "Switch");
+		scnprintf(s, sizeof(s), fmt, i + 1 + info->air_input_first,
+			  "Air", info->air_option ? "Enum" : "Switch");
 		err = scarlett2_add_new_ctl(
 			mixer, &scarlett2_air_ctl[info->air_option],
 			i, 1, s, &private->air_ctls[i]);
@@ -5481,9 +5481,9 @@ static int scarlett2_add_line_in_ctls(struct usb_mixer_interface *mixer)
 
 		for (i = 0; i < info->gain_input_count; i++) {
 			if (i % 2) {
-				snprintf(s, sizeof(s),
-					 "Line In %d-%d Link Capture Switch",
-					 i, i + 1);
+				scnprintf(s, sizeof(s),
+					  "Line In %d-%d Link Capture Switch",
+					  i, i + 1);
 				err = scarlett2_add_new_ctl(
 					mixer, &scarlett2_input_link_ctl,
 					i / 2, 1, s,
@@ -5492,30 +5492,30 @@ static int scarlett2_add_line_in_ctls(struct usb_mixer_interface *mixer)
 					return err;
 			}
 
-			snprintf(s, sizeof(s), fmt, i + 1,
-				 "Gain", "Volume");
+			scnprintf(s, sizeof(s), fmt, i + 1,
+				  "Gain", "Volume");
 			err = scarlett2_add_new_ctl(
 				mixer, &scarlett2_input_gain_ctl,
 				i, 1, s, &private->input_gain_ctls[i]);
 			if (err < 0)
 				return err;
 
-			snprintf(s, sizeof(s), fmt, i + 1,
-				 "Autogain", "Switch");
+			scnprintf(s, sizeof(s), fmt, i + 1,
+				  "Autogain", "Switch");
 			err = scarlett2_add_new_ctl(
 				mixer, &scarlett2_autogain_switch_ctl,
 				i, 1, s, &private->autogain_ctls[i]);
 			if (err < 0)
 				return err;
 
-			snprintf(s, sizeof(s), fmt, i + 1,
-				 "Autogain Status", "Enum");
+			scnprintf(s, sizeof(s), fmt, i + 1,
+				  "Autogain Status", "Enum");
 			err = scarlett2_add_new_ctl(
 				mixer, &scarlett2_autogain_status_ctl,
 				i, 1, s, &private->autogain_status_ctls[i]);
 
-			snprintf(s, sizeof(s), fmt, i + 1,
-				 "Safe", "Switch");
+			scnprintf(s, sizeof(s), fmt, i + 1,
+				  "Safe", "Switch");
 			err = scarlett2_add_new_ctl(
 				mixer, &scarlett2_safe_ctl,
 				i, 1, s, &private->safe_ctls[i]);
@@ -5902,8 +5902,8 @@ static int scarlett2_add_direct_monitor_ctls(struct usb_mixer_interface *mixer)
 			for (k = 0; k < private->num_mix_in; k++, index++) {
 				char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
 
-				snprintf(name, sizeof(name), format,
-					 mix_type, 'A' + j, k + 1);
+				scnprintf(name, sizeof(name), format,
+					  mix_type, 'A' + j, k + 1);
 
 				err = scarlett2_add_new_ctl(
 					mixer, &scarlett2_monitor_mix_ctl,
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 07cc6a201579..09712e61c606 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2031,10 +2031,14 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M | QUIRK_FLAG_IGNORE_CTL_ERROR),
 	DEVICE_FLG(0x0499, 0x1509, /* Steinberg UR22 */
 		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
+	DEVICE_FLG(0x0499, 0x3108, /* Yamaha YIT-W12TX */
+		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x04d8, 0xfeea, /* Benchmark DAC1 Pre */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x04e8, 0xa051, /* Samsung USBC Headset (AKG) */
 		   QUIRK_FLAG_SKIP_CLOCK_SELECTOR | QUIRK_FLAG_CTL_MSG_DELAY_5M),
+	DEVICE_FLG(0x0525, 0xa4ad, /* Hamedal C20 usb camero */
+		   QUIRK_FLAG_IFACE_SKIP_CLOSE),
 	DEVICE_FLG(0x054c, 0x0b8c, /* Sony WALKMAN NW-A45 DAC */
 		   QUIRK_FLAG_SET_IFACE_FIRST),
 	DEVICE_FLG(0x0556, 0x0014, /* Phoenix Audio TMX320VC */
@@ -2073,14 +2077,22 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
 	DEVICE_FLG(0x0763, 0x2031, /* M-Audio Fast Track C600 */
 		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
+	DEVICE_FLG(0x07fd, 0x000b, /* MOTU M Series 2nd hardware revision */
+		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
 	DEVICE_FLG(0x08bb, 0x2702, /* LineX FM Transmitter */
 		   QUIRK_FLAG_IGNORE_CTL_ERROR),
 	DEVICE_FLG(0x0951, 0x16ad, /* Kingston HyperX */
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
 	DEVICE_FLG(0x0b0e, 0x0349, /* Jabra 550a */
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
+	DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */
+		   QUIRK_FLAG_FIXED_RATE),
+	DEVICE_FLG(0x0ecb, 0x2069, /* JBL Quantum810 Wireless */
+		   QUIRK_FLAG_FIXED_RATE),
 	DEVICE_FLG(0x0fd9, 0x0008, /* Hauppauge HVR-950Q */
 		   QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER),
+	DEVICE_FLG(0x1224, 0x2a25, /* Jieli Technology USB PHY 2.0 */
+		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x1395, 0x740a, /* Sennheiser DECT */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x1397, 0x0507, /* Behringer UMC202HD */
@@ -2113,6 +2125,10 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY),
 	DEVICE_FLG(0x1901, 0x0191, /* GE B850V3 CP2114 audio interface */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x19f7, 0x0035, /* RODE NT-USB+ */
+		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x1bcf, 0x2283, /* NexiGo N930AF FHD Webcam */
+		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x2040, 0x7200, /* Hauppauge HVR-950Q */
 		   QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER),
 	DEVICE_FLG(0x2040, 0x7201, /* Hauppauge HVR-950Q-MXL */
@@ -2155,6 +2171,12 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_IGNORE_CTL_ERROR),
 	DEVICE_FLG(0x2912, 0x30c8, /* Audioengine D1 */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x2b53, 0x0023, /* Fiero SC-01 (firmware v1.0.0 @ 48 kHz) */
+		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
+	DEVICE_FLG(0x2b53, 0x0024, /* Fiero SC-01 (firmware v1.0.0 @ 96 kHz) */
+		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
+	DEVICE_FLG(0x2b53, 0x0031, /* Fiero SC-01 (firmware v1.1.0) */
+		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
 	DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */
 		   QUIRK_FLAG_IGNORE_CTL_ERROR),
 	DEVICE_FLG(0x413c, 0xa506, /* Dell AE515 sound bar */
@@ -2163,22 +2185,6 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_ALIGN_TRANSFER),
 	DEVICE_FLG(0x534d, 0x2109, /* MacroSilicon MS2109 */
 		   QUIRK_FLAG_ALIGN_TRANSFER),
-	DEVICE_FLG(0x1224, 0x2a25, /* Jieli Technology USB PHY 2.0 */
-		   QUIRK_FLAG_GET_SAMPLE_RATE),
-	DEVICE_FLG(0x2b53, 0x0023, /* Fiero SC-01 (firmware v1.0.0 @ 48 kHz) */
-		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
-	DEVICE_FLG(0x2b53, 0x0024, /* Fiero SC-01 (firmware v1.0.0 @ 96 kHz) */
-		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
-	DEVICE_FLG(0x2b53, 0x0031, /* Fiero SC-01 (firmware v1.1.0) */
-		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
-	DEVICE_FLG(0x0525, 0xa4ad, /* Hamedal C20 usb camero */
-		   QUIRK_FLAG_IFACE_SKIP_CLOSE),
-	DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */
-		   QUIRK_FLAG_FIXED_RATE),
-	DEVICE_FLG(0x0ecb, 0x2069, /* JBL Quantum810 Wireless */
-		   QUIRK_FLAG_FIXED_RATE),
-	DEVICE_FLG(0x1bcf, 0x2283, /* NexiGo N930AF FHD Webcam */
-		   QUIRK_FLAG_GET_SAMPLE_RATE),
 
 	/* Vendor matches */
 	VENDOR_FLG(0x045e, /* MS Lifecam */
diff --git a/sound/virtio/virtio_card.c b/sound/virtio/virtio_card.c
index e2847c040f75..b158c3cb8e5f 100644
--- a/sound/virtio/virtio_card.c
+++ b/sound/virtio/virtio_card.c
@@ -91,8 +91,6 @@ static void virtsnd_event_notify_cb(struct virtqueue *vqueue)
 			virtsnd_event_dispatch(snd, event);
 			virtsnd_event_send(vqueue, event, true, GFP_ATOMIC);
 		}
-		if (unlikely(virtqueue_is_broken(vqueue)))
-			break;
 	} while (!virtqueue_enable_cb(vqueue));
 	spin_unlock_irqrestore(&queue->lock, flags);
 }
diff --git a/sound/virtio/virtio_ctl_msg.c b/sound/virtio/virtio_ctl_msg.c
index 18dc5aca2e0c..9dabea01277f 100644
--- a/sound/virtio/virtio_ctl_msg.c
+++ b/sound/virtio/virtio_ctl_msg.c
@@ -303,8 +303,6 @@ void virtsnd_ctl_notify_cb(struct virtqueue *vqueue)
 		virtqueue_disable_cb(vqueue);
 		while ((msg = virtqueue_get_buf(vqueue, &length)))
 			virtsnd_ctl_msg_complete(msg);
-		if (unlikely(virtqueue_is_broken(vqueue)))
-			break;
 	} while (!virtqueue_enable_cb(vqueue));
 	spin_unlock_irqrestore(&queue->lock, flags);
 }
diff --git a/sound/virtio/virtio_pcm_msg.c b/sound/virtio/virtio_pcm_msg.c
index 542446c4c7ba..8c32efaf4c52 100644
--- a/sound/virtio/virtio_pcm_msg.c
+++ b/sound/virtio/virtio_pcm_msg.c
@@ -358,8 +358,6 @@ static inline void virtsnd_pcm_notify_cb(struct virtio_snd_queue *queue)
 		virtqueue_disable_cb(queue->vqueue);
 		while ((msg = virtqueue_get_buf(queue->vqueue, &written_bytes)))
 			virtsnd_pcm_msg_complete(msg, written_bytes);
-		if (unlikely(virtqueue_is_broken(queue->vqueue)))
-			break;
 	} while (!virtqueue_enable_cb(queue->vqueue));
 	spin_unlock_irqrestore(&queue->lock, flags);
 }
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index f4542d2718f4..29cb275a219d 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -198,6 +198,7 @@
 #define X86_FEATURE_CAT_L3		( 7*32+ 4) /* Cache Allocation Technology L3 */
 #define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
 #define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_TDX_HOST_PLATFORM	( 7*32+ 7) /* Platform supports being a TDX host */
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_XCOMPACTED		( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */
@@ -308,10 +309,14 @@
 #define X86_FEATURE_SMBA		(11*32+21) /* "" Slow Memory Bandwidth Allocation */
 #define X86_FEATURE_BMEC		(11*32+22) /* "" Bandwidth Monitoring Event Configuration */
 #define X86_FEATURE_USER_SHSTK		(11*32+23) /* Shadow stack support for user mode applications */
-
 #define X86_FEATURE_SRSO		(11*32+24) /* "" AMD BTB untrain RETs */
 #define X86_FEATURE_SRSO_ALIAS		(11*32+25) /* "" AMD BTB untrain RETs through aliasing */
 #define X86_FEATURE_IBPB_ON_VMEXIT	(11*32+26) /* "" Issue an IBPB only on VMEXIT */
+#define X86_FEATURE_APIC_MSRS_FENCE	(11*32+27) /* "" IA32_TSC_DEADLINE and X2APIC MSRs need fencing */
+#define X86_FEATURE_ZEN2		(11*32+28) /* "" CPU based on Zen2 microarchitecture */
+#define X86_FEATURE_ZEN3		(11*32+29) /* "" CPU based on Zen3 microarchitecture */
+#define X86_FEATURE_ZEN4		(11*32+30) /* "" CPU based on Zen4 microarchitecture */
+#define X86_FEATURE_ZEN1		(11*32+31) /* "" CPU based on Zen1 microarchitecture */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
@@ -495,6 +500,7 @@
 #define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
 #define X86_BUG_SMT_RSB			X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */
 #define X86_BUG_GDS			X86_BUG(30) /* CPU is affected by Gather Data Sampling */
+#define X86_BUG_TDX_PW_MCE		X86_BUG(31) /* CPU may incur #MC if non-TD software does partial write to TDX private memory */
 
 /* BUG word 2 */
 #define X86_BUG_SRSO			X86_BUG(1*32 + 0) /* AMD SRSO bug */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 1d51e1850ed0..f1bd7b91b3c6 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -237,6 +237,11 @@
 #define LBR_INFO_CYCLES			0xffff
 #define LBR_INFO_BR_TYPE_OFFSET		56
 #define LBR_INFO_BR_TYPE		(0xfull << LBR_INFO_BR_TYPE_OFFSET)
+#define LBR_INFO_BR_CNTR_OFFSET		32
+#define LBR_INFO_BR_CNTR_NUM		4
+#define LBR_INFO_BR_CNTR_BITS		2
+#define LBR_INFO_BR_CNTR_MASK		GENMASK_ULL(LBR_INFO_BR_CNTR_BITS - 1, 0)
+#define LBR_INFO_BR_CNTR_FULL_MASK	GENMASK_ULL(LBR_INFO_BR_CNTR_NUM * LBR_INFO_BR_CNTR_BITS - 1, 0)
 
 #define MSR_ARCH_LBR_CTL		0x000014ce
 #define ARCH_LBR_CTL_LBREN		BIT(0)
@@ -536,6 +541,9 @@
 #define MSR_RELOAD_PMC0			0x000014c1
 #define MSR_RELOAD_FIXED_CTR0		0x00001309
 
+/* KeyID partitioning between MKTME and TDX */
+#define MSR_IA32_MKTME_KEYID_PARTITIONING	0x00000087
+
 /*
  * AMD64 MSRs. Not complete. See the architecture manual for a more
  * complete list.
diff --git a/tools/arch/x86/include/asm/rmwcc.h b/tools/arch/x86/include/asm/rmwcc.h
index 11ff975242ca..e2ff22b379a4 100644
--- a/tools/arch/x86/include/asm/rmwcc.h
+++ b/tools/arch/x86/include/asm/rmwcc.h
@@ -4,7 +4,7 @@
 
 #define __GEN_RMWcc(fullop, var, cc, ...)				\
 do {									\
-	asm_volatile_goto (fullop "; j" cc " %l[cc_label]"		\
+	asm goto (fullop "; j" cc " %l[cc_label]"		\
 			: : "m" (var), ## __VA_ARGS__ 			\
 			: "memory" : cc_label);				\
 	return 0;							\
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 1a6a1f987949..a448d0964fc0 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -562,4 +562,7 @@ struct kvm_pmu_event_filter {
 /* x86-specific KVM_EXIT_HYPERCALL flags. */
 #define KVM_EXIT_HYPERCALL_LONG_MODE	BIT(0)
 
+#define KVM_X86_DEFAULT_VM	0
+#define KVM_X86_SW_PROTECTED_VM	1
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index d055b82d22cc..59cf6f9065aa 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -1,11 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /* Copyright 2002 Andi Kleen */
 
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
-#include <asm/export.h>
 
 .section .noinstr.text, "ax"
 
@@ -39,7 +39,7 @@ SYM_TYPED_FUNC_START(__memcpy)
 SYM_FUNC_END(__memcpy)
 EXPORT_SYMBOL(__memcpy)
 
-SYM_FUNC_ALIAS(memcpy, __memcpy)
+SYM_FUNC_ALIAS_MEMFUNC(memcpy, __memcpy)
 EXPORT_SYMBOL(memcpy)
 
 SYM_FUNC_START_LOCAL(memcpy_orig)
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index 7c59a704c458..0199d56cb479 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -1,10 +1,10 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright 2002 Andi Kleen, SuSE Labs */
 
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
-#include <asm/export.h>
 
 .section .noinstr.text, "ax"
 
@@ -40,7 +40,7 @@ SYM_FUNC_START(__memset)
 SYM_FUNC_END(__memset)
 EXPORT_SYMBOL(__memset)
 
-SYM_FUNC_ALIAS(memset, __memset)
+SYM_FUNC_ALIAS_MEMFUNC(memset, __memset)
 EXPORT_SYMBOL(memset)
 
 SYM_FUNC_START_LOCAL(memset_orig)
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 934e2777a2db..64df118376df 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -32,6 +32,7 @@ FEATURE_TESTS_BASIC :=                  \
         backtrace                       \
         dwarf                           \
         dwarf_getlocations              \
+        dwarf_getcfi                    \
         eventfd                         \
         fortify-source                  \
         get_current_dir_name            \
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index dad79ede4e0a..37722e509eb9 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -7,6 +7,7 @@ FILES=                                          \
          test-bionic.bin                        \
          test-dwarf.bin                         \
          test-dwarf_getlocations.bin            \
+         test-dwarf_getcfi.bin                  \
          test-eventfd.bin                       \
          test-fortify-source.bin                \
          test-get_current_dir_name.bin          \
@@ -154,6 +155,9 @@ $(OUTPUT)test-dwarf.bin:
 $(OUTPUT)test-dwarf_getlocations.bin:
 	$(BUILD) $(DWARFLIBS)
 
+$(OUTPUT)test-dwarf_getcfi.bin:
+	$(BUILD) $(DWARFLIBS)
+
 $(OUTPUT)test-libelf-getphdrnum.bin:
 	$(BUILD) -lelf
 
diff --git a/tools/build/feature/test-dwarf_getcfi.c b/tools/build/feature/test-dwarf_getcfi.c
new file mode 100644
index 000000000000..50e7d7cb7bdf
--- /dev/null
+++ b/tools/build/feature/test-dwarf_getcfi.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <elfutils/libdw.h>
+
+int main(void)
+{
+	Dwarf *dwarf = NULL;
+	return dwarf_getcfi(dwarf) == NULL;
+}
diff --git a/tools/build/feature/test-libopencsd.c b/tools/build/feature/test-libopencsd.c
index eb6303ff446e..4cfcef9da3e4 100644
--- a/tools/build/feature/test-libopencsd.c
+++ b/tools/build/feature/test-libopencsd.c
@@ -4,9 +4,9 @@
 /*
  * Check OpenCSD library version is sufficient to provide required features
  */
-#define OCSD_MIN_VER ((1 << 16) | (1 << 8) | (1))
+#define OCSD_MIN_VER ((1 << 16) | (2 << 8) | (1))
 #if !defined(OCSD_VER_NUM) || (OCSD_VER_NUM < OCSD_MIN_VER)
-#error "OpenCSD >= 1.1.1 is required"
+#error "OpenCSD >= 1.2.1 is required"
 #endif
 
 int main(void)
diff --git a/tools/counter/Build b/tools/counter/Build
index 33f4a51d715e..4bbadb7ec93a 100644
--- a/tools/counter/Build
+++ b/tools/counter/Build
@@ -1 +1,2 @@
 counter_example-y += counter_example.o
+counter_watch_events-y += counter_watch_events.o
diff --git a/tools/counter/Makefile b/tools/counter/Makefile
index b2c2946f44c9..d82d35a520f6 100644
--- a/tools/counter/Makefile
+++ b/tools/counter/Makefile
@@ -12,9 +12,10 @@ endif
 # (this improves performance and avoids hard-to-debug behaviour);
 MAKEFLAGS += -r
 
-override CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include
+override CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include \
+	 -I$(srctree)/tools/include
 
-ALL_TARGETS := counter_example
+ALL_TARGETS := counter_example counter_watch_events
 ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS))
 
 all: $(ALL_PROGRAMS)
@@ -37,12 +38,19 @@ $(COUNTER_EXAMPLE): prepare FORCE
 $(OUTPUT)counter_example: $(COUNTER_EXAMPLE)
 	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
 
+COUNTER_WATCH_EVENTS := $(OUTPUT)counter_watch_events.o
+$(COUNTER_WATCH_EVENTS): prepare FORCE
+	$(Q)$(MAKE) $(build)=counter_watch_events
+$(OUTPUT)counter_watch_events: $(COUNTER_WATCH_EVENTS)
+	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
+
 clean:
 	rm -f $(ALL_PROGRAMS)
 	rm -rf $(OUTPUT)include/linux/counter.h
 	rm -df $(OUTPUT)include/linux
 	rm -df $(OUTPUT)include
 	find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete
+	find $(or $(OUTPUT),.) -name '\.*.o.cmd' -delete
 
 install: $(ALL_PROGRAMS)
 	install -d -m 755 $(DESTDIR)$(bindir);		\
diff --git a/tools/counter/counter_watch_events.c b/tools/counter/counter_watch_events.c
new file mode 100644
index 000000000000..107631e0f2e3
--- /dev/null
+++ b/tools/counter/counter_watch_events.c
@@ -0,0 +1,406 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Counter Watch Events - Test various counter watch events in a userspace application
+ *
+ * Copyright (C) STMicroelectronics 2023 - All Rights Reserved
+ * Author: Fabrice Gasnier <fabrice.gasnier@foss.st.com>.
+ */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <getopt.h>
+#include <linux/counter.h>
+#include <linux/kernel.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <unistd.h>
+
+static struct counter_watch simple_watch[] = {
+	{
+		/* Component data: Count 0 count */
+		.component.type = COUNTER_COMPONENT_COUNT,
+		.component.scope = COUNTER_SCOPE_COUNT,
+		.component.parent = 0,
+		/* Event type: overflow or underflow */
+		.event = COUNTER_EVENT_OVERFLOW_UNDERFLOW,
+		/* Device event channel 0 */
+		.channel = 0,
+	},
+};
+
+static const char * const counter_event_type_name[] = {
+	"COUNTER_EVENT_OVERFLOW",
+	"COUNTER_EVENT_UNDERFLOW",
+	"COUNTER_EVENT_OVERFLOW_UNDERFLOW",
+	"COUNTER_EVENT_THRESHOLD",
+	"COUNTER_EVENT_INDEX",
+	"COUNTER_EVENT_CHANGE_OF_STATE",
+	"COUNTER_EVENT_CAPTURE",
+};
+
+static const char * const counter_component_type_name[] = {
+	"COUNTER_COMPONENT_NONE",
+	"COUNTER_COMPONENT_SIGNAL",
+	"COUNTER_COMPONENT_COUNT",
+	"COUNTER_COMPONENT_FUNCTION",
+	"COUNTER_COMPONENT_SYNAPSE_ACTION",
+	"COUNTER_COMPONENT_EXTENSION",
+};
+
+static const char * const counter_scope_name[] = {
+	"COUNTER_SCOPE_DEVICE",
+	"COUNTER_SCOPE_SIGNAL",
+	"COUNTER_SCOPE_COUNT",
+};
+
+static void print_watch(struct counter_watch *watch, int nwatch)
+{
+	int i;
+
+	/* prints the watch array in C-like structure */
+	printf("watch[%d] = {\n", nwatch);
+	for (i = 0; i < nwatch; i++) {
+		printf(" [%d] =\t{\n"
+		       "\t\t.component.type = %s\n"
+		       "\t\t.component.scope = %s\n"
+		       "\t\t.component.parent = %d\n"
+		       "\t\t.component.id = %d\n"
+		       "\t\t.event = %s\n"
+		       "\t\t.channel = %d\n"
+		       "\t},\n",
+		       i,
+		       counter_component_type_name[watch[i].component.type],
+		       counter_scope_name[watch[i].component.scope],
+		       watch[i].component.parent,
+		       watch[i].component.id,
+		       counter_event_type_name[watch[i].event],
+		       watch[i].channel);
+	}
+	printf("};\n");
+}
+
+static void print_usage(void)
+{
+	fprintf(stderr, "Usage:\n\n"
+		"counter_watch_events [options] [-w <watchoptions>]\n"
+		"counter_watch_events [options] [-w <watch1 options>] [-w <watch2 options>]...\n"
+		"\n"
+		"When no --watch option has been provided, simple watch example is used:\n"
+		"counter_watch_events [options] -w comp_count,scope_count,evt_ovf_udf\n"
+		"\n"
+		"Test various watch events for given counter device.\n"
+		"\n"
+		"Options:\n"
+		"  -d, --debug                Prints debug information\n"
+		"  -h, --help                 Prints usage\n"
+		"  -n, --device-num <n>       Use /dev/counter<n> [default: /dev/counter0]\n"
+		"  -l, --loop <n>             Loop for <n> events [default: 0 (forever)]\n"
+		"  -w, --watch <watchoptions> comma-separated list of watch options\n"
+		"\n"
+		"Watch options:\n"
+		"  scope_device               (COUNTER_SCOPE_DEVICE) [default: scope_device]\n"
+		"  scope_signal               (COUNTER_SCOPE_SIGNAL)\n"
+		"  scope_count                (COUNTER_SCOPE_COUNT)\n"
+		"\n"
+		"  comp_none                  (COUNTER_COMPONENT_NONE) [default: comp_none]\n"
+		"  comp_signal                (COUNTER_COMPONENT_SIGNAL)\n"
+		"  comp_count                 (COUNTER_COMPONENT_COUNT)\n"
+		"  comp_function              (COUNTER_COMPONENT_FUNCTION)\n"
+		"  comp_synapse_action        (COUNTER_COMPONENT_SYNAPSE_ACTION)\n"
+		"  comp_extension             (COUNTER_COMPONENT_EXTENSION)\n"
+		"\n"
+		"  evt_ovf                    (COUNTER_EVENT_OVERFLOW) [default: evt_ovf]\n"
+		"  evt_udf                    (COUNTER_EVENT_UNDERFLOW)\n"
+		"  evt_ovf_udf                (COUNTER_EVENT_OVERFLOW_UNDERFLOW)\n"
+		"  evt_threshold              (COUNTER_EVENT_THRESHOLD)\n"
+		"  evt_index                  (COUNTER_EVENT_INDEX)\n"
+		"  evt_change_of_state        (COUNTER_EVENT_CHANGE_OF_STATE)\n"
+		"  evt_capture                (COUNTER_EVENT_CAPTURE)\n"
+		"\n"
+		"  chan=<n>                   channel <n> for this watch [default: 0]\n"
+		"  id=<n>                     component id <n> for this watch [default: 0]\n"
+		"  parent=<n>                 component parent <n> for this watch [default: 0]\n"
+		"\n"
+		"Example with two watched events:\n\n"
+		"counter_watch_events -d \\\n"
+		"\t-w comp_count,scope_count,evt_ovf_udf \\\n"
+		"\t-w comp_extension,scope_count,evt_capture,id=7,chan=3\n"
+		);
+}
+
+static const struct option longopts[] = {
+	{ "debug",		no_argument,       0, 'd' },
+	{ "help",		no_argument,       0, 'h' },
+	{ "device-num",		required_argument, 0, 'n' },
+	{ "loop",		required_argument, 0, 'l' },
+	{ "watch",		required_argument, 0, 'w' },
+	{ },
+};
+
+/* counter watch subopts */
+enum {
+	WATCH_SCOPE_DEVICE,
+	WATCH_SCOPE_SIGNAL,
+	WATCH_SCOPE_COUNT,
+	WATCH_COMPONENT_NONE,
+	WATCH_COMPONENT_SIGNAL,
+	WATCH_COMPONENT_COUNT,
+	WATCH_COMPONENT_FUNCTION,
+	WATCH_COMPONENT_SYNAPSE_ACTION,
+	WATCH_COMPONENT_EXTENSION,
+	WATCH_EVENT_OVERFLOW,
+	WATCH_EVENT_UNDERFLOW,
+	WATCH_EVENT_OVERFLOW_UNDERFLOW,
+	WATCH_EVENT_THRESHOLD,
+	WATCH_EVENT_INDEX,
+	WATCH_EVENT_CHANGE_OF_STATE,
+	WATCH_EVENT_CAPTURE,
+	WATCH_CHANNEL,
+	WATCH_ID,
+	WATCH_PARENT,
+	WATCH_SUBOPTS_MAX,
+};
+
+static char * const counter_watch_subopts[WATCH_SUBOPTS_MAX + 1] = {
+	/* component.scope */
+	[WATCH_SCOPE_DEVICE] = "scope_device",
+	[WATCH_SCOPE_SIGNAL] = "scope_signal",
+	[WATCH_SCOPE_COUNT] = "scope_count",
+	/* component.type */
+	[WATCH_COMPONENT_NONE] = "comp_none",
+	[WATCH_COMPONENT_SIGNAL] = "comp_signal",
+	[WATCH_COMPONENT_COUNT] = "comp_count",
+	[WATCH_COMPONENT_FUNCTION] = "comp_function",
+	[WATCH_COMPONENT_SYNAPSE_ACTION] = "comp_synapse_action",
+	[WATCH_COMPONENT_EXTENSION] = "comp_extension",
+	/* event */
+	[WATCH_EVENT_OVERFLOW] = "evt_ovf",
+	[WATCH_EVENT_UNDERFLOW] = "evt_udf",
+	[WATCH_EVENT_OVERFLOW_UNDERFLOW] = "evt_ovf_udf",
+	[WATCH_EVENT_THRESHOLD] = "evt_threshold",
+	[WATCH_EVENT_INDEX] = "evt_index",
+	[WATCH_EVENT_CHANGE_OF_STATE] = "evt_change_of_state",
+	[WATCH_EVENT_CAPTURE] = "evt_capture",
+	/* channel, id, parent */
+	[WATCH_CHANNEL] = "chan",
+	[WATCH_ID] = "id",
+	[WATCH_PARENT] = "parent",
+	/* Empty entry ends the opts array */
+	NULL
+};
+
+int main(int argc, char **argv)
+{
+	int c, fd, i, ret, rc = 0, debug = 0, loop = 0, dev_num = 0, nwatch = 0;
+	struct counter_event event_data;
+	char *device_name = NULL, *subopts, *value;
+	struct counter_watch *watches;
+
+	/*
+	 * 1st pass:
+	 * - list watch events number to allocate the watch array.
+	 * - parse normal options (other than watch options)
+	 */
+	while ((c = getopt_long(argc, argv, "dhn:l:w:", longopts, NULL)) != -1) {
+		switch (c) {
+		case 'd':
+			debug = 1;
+			break;
+		case 'h':
+			print_usage();
+			return EXIT_SUCCESS;
+		case 'n':
+			dev_num = strtoul(optarg, NULL, 10);
+			if (errno) {
+				perror("strtol failed: --device-num <n>\n");
+				return EXIT_FAILURE;
+			}
+			break;
+		case 'l':
+			loop = strtol(optarg, NULL, 10);
+			if (errno) {
+				perror("strtol failed: --loop <n>\n");
+				return EXIT_FAILURE;
+			}
+			break;
+		case 'w':
+			nwatch++;
+			break;
+		default:
+			return EXIT_FAILURE;
+		}
+	}
+
+	if (nwatch) {
+		watches = calloc(nwatch, sizeof(*watches));
+		if (!watches) {
+			perror("Error allocating watches\n");
+			return EXIT_FAILURE;
+		}
+	} else {
+		/* default to simple watch example */
+		watches = simple_watch;
+		nwatch = ARRAY_SIZE(simple_watch);
+	}
+
+	/* 2nd pass: parse watch sub-options to fill in watch array */
+	optind = 1;
+	i = 0;
+	while ((c = getopt_long(argc, argv, "dhn:l:w:", longopts, NULL)) != -1) {
+		switch (c) {
+		case 'w':
+			subopts = optarg;
+			while (*subopts != '\0') {
+				ret = getsubopt(&subopts, counter_watch_subopts, &value);
+				switch (ret) {
+				case WATCH_SCOPE_DEVICE:
+				case WATCH_SCOPE_SIGNAL:
+				case WATCH_SCOPE_COUNT:
+					/* match with counter_scope */
+					watches[i].component.scope = ret;
+					break;
+				case WATCH_COMPONENT_NONE:
+				case WATCH_COMPONENT_SIGNAL:
+				case WATCH_COMPONENT_COUNT:
+				case WATCH_COMPONENT_FUNCTION:
+				case WATCH_COMPONENT_SYNAPSE_ACTION:
+				case WATCH_COMPONENT_EXTENSION:
+					/* match counter_component_type: subtract enum value */
+					ret -= WATCH_COMPONENT_NONE;
+					watches[i].component.type = ret;
+					break;
+				case WATCH_EVENT_OVERFLOW:
+				case WATCH_EVENT_UNDERFLOW:
+				case WATCH_EVENT_OVERFLOW_UNDERFLOW:
+				case WATCH_EVENT_THRESHOLD:
+				case WATCH_EVENT_INDEX:
+				case WATCH_EVENT_CHANGE_OF_STATE:
+				case WATCH_EVENT_CAPTURE:
+					/* match counter_event_type: subtract enum value */
+					ret -= WATCH_EVENT_OVERFLOW;
+					watches[i].event = ret;
+					break;
+				case WATCH_CHANNEL:
+					if (!value) {
+						fprintf(stderr, "Invalid chan=<number>\n");
+						rc = EXIT_FAILURE;
+						goto err_free_watches;
+					}
+					watches[i].channel = strtoul(value, NULL, 10);
+					if (errno) {
+						perror("strtoul failed: chan=<number>\n");
+						rc = EXIT_FAILURE;
+						goto err_free_watches;
+					}
+					break;
+				case WATCH_ID:
+					if (!value) {
+						fprintf(stderr, "Invalid id=<number>\n");
+						rc = EXIT_FAILURE;
+						goto err_free_watches;
+					}
+					watches[i].component.id = strtoul(value, NULL, 10);
+					if (errno) {
+						perror("strtoul failed: id=<number>\n");
+						rc = EXIT_FAILURE;
+						goto err_free_watches;
+					}
+					break;
+				case WATCH_PARENT:
+					if (!value) {
+						fprintf(stderr, "Invalid parent=<number>\n");
+						rc = EXIT_FAILURE;
+						goto err_free_watches;
+					}
+					watches[i].component.parent = strtoul(value, NULL, 10);
+					if (errno) {
+						perror("strtoul failed: parent=<number>\n");
+						rc = EXIT_FAILURE;
+						goto err_free_watches;
+					}
+					break;
+				default:
+					fprintf(stderr, "Unknown suboption '%s'\n", value);
+					rc = EXIT_FAILURE;
+					goto err_free_watches;
+				}
+			}
+			i++;
+			break;
+		}
+	}
+
+	if (debug)
+		print_watch(watches, nwatch);
+
+	ret = asprintf(&device_name, "/dev/counter%d", dev_num);
+	if (ret < 0) {
+		fprintf(stderr, "asprintf failed\n");
+		rc = EXIT_FAILURE;
+		goto err_free_watches;
+	}
+
+	if (debug)
+		printf("Opening %s\n", device_name);
+
+	fd = open(device_name, O_RDWR);
+	if (fd == -1) {
+		fprintf(stderr, "Unable to open %s: %s\n", device_name, strerror(errno));
+		free(device_name);
+		rc = EXIT_FAILURE;
+		goto err_free_watches;
+	}
+	free(device_name);
+
+	for (i = 0; i < nwatch; i++) {
+		ret = ioctl(fd, COUNTER_ADD_WATCH_IOCTL, watches + i);
+		if (ret == -1) {
+			fprintf(stderr, "Error adding watches[%d]: %s\n", i,
+				strerror(errno));
+			rc = EXIT_FAILURE;
+			goto err_close;
+		}
+	}
+
+	ret = ioctl(fd, COUNTER_ENABLE_EVENTS_IOCTL);
+	if (ret == -1) {
+		perror("Error enabling events");
+		rc = EXIT_FAILURE;
+		goto err_close;
+	}
+
+	for (i = 0; loop <= 0 || i < loop; i++) {
+		ret = read(fd, &event_data, sizeof(event_data));
+		if (ret == -1) {
+			perror("Failed to read event data");
+			rc = EXIT_FAILURE;
+			goto err_close;
+		}
+
+		if (ret != sizeof(event_data)) {
+			fprintf(stderr, "Failed to read event data (got: %d)\n", ret);
+			rc = EXIT_FAILURE;
+			goto err_close;
+		}
+
+		printf("Timestamp: %llu\tData: %llu\t event: %s\tch: %d\n",
+		       event_data.timestamp, event_data.value,
+		       counter_event_type_name[event_data.watch.event],
+		       event_data.watch.channel);
+
+		if (event_data.status) {
+			fprintf(stderr, "Error %d: %s\n", event_data.status,
+				strerror(event_data.status));
+		}
+	}
+
+err_close:
+	close(fd);
+err_free_watches:
+	if (watches != simple_watch)
+		free(watches);
+
+	return rc;
+}
diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c
index 2eaaa7123b04..8073c9e4fe46 100644
--- a/tools/iio/iio_event_monitor.c
+++ b/tools/iio/iio_event_monitor.c
@@ -105,6 +105,8 @@ static const char * const iio_modifier_names[] = {
 	[IIO_MOD_LIGHT_GREEN] = "green",
 	[IIO_MOD_LIGHT_BLUE] = "blue",
 	[IIO_MOD_LIGHT_UV] = "uv",
+	[IIO_MOD_LIGHT_UVA] = "uva",
+	[IIO_MOD_LIGHT_UVB] = "uvb",
 	[IIO_MOD_LIGHT_DUV] = "duv",
 	[IIO_MOD_QUATERNION] = "quaternion",
 	[IIO_MOD_TEMP_AMBIENT] = "ambient",
diff --git a/tools/include/asm-generic/unaligned.h b/tools/include/asm-generic/unaligned.h
index 2fd551915c20..cdd2fd078027 100644
--- a/tools/include/asm-generic/unaligned.h
+++ b/tools/include/asm-generic/unaligned.h
@@ -105,9 +105,9 @@ static inline u32 get_unaligned_le24(const void *p)
 
 static inline void __put_unaligned_be24(const u32 val, u8 *p)
 {
-	*p++ = val >> 16;
-	*p++ = val >> 8;
-	*p++ = val;
+	*p++ = (val >> 16) & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = val & 0xff;
 }
 
 static inline void put_unaligned_be24(const u32 val, void *p)
@@ -117,9 +117,9 @@ static inline void put_unaligned_be24(const u32 val, void *p)
 
 static inline void __put_unaligned_le24(const u32 val, u8 *p)
 {
-	*p++ = val;
-	*p++ = val >> 8;
-	*p++ = val >> 16;
+	*p++ = val & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = (val >> 16) & 0xff;
 }
 
 static inline void put_unaligned_le24(const u32 val, void *p)
@@ -129,12 +129,12 @@ static inline void put_unaligned_le24(const u32 val, void *p)
 
 static inline void __put_unaligned_be48(const u64 val, u8 *p)
 {
-	*p++ = val >> 40;
-	*p++ = val >> 32;
-	*p++ = val >> 24;
-	*p++ = val >> 16;
-	*p++ = val >> 8;
-	*p++ = val;
+	*p++ = (val >> 40) & 0xff;
+	*p++ = (val >> 32) & 0xff;
+	*p++ = (val >> 24) & 0xff;
+	*p++ = (val >> 16) & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = val & 0xff;
 }
 
 static inline void put_unaligned_be48(const u64 val, void *p)
diff --git a/tools/include/linux/compiler_types.h b/tools/include/linux/compiler_types.h
index 1bdd834bdd57..d09f9dc172a4 100644
--- a/tools/include/linux/compiler_types.h
+++ b/tools/include/linux/compiler_types.h
@@ -36,8 +36,8 @@
 #include <linux/compiler-gcc.h>
 #endif
 
-#ifndef asm_volatile_goto
-#define asm_volatile_goto(x...) asm goto(x)
+#ifndef asm_goto_output
+#define asm_goto_output(x...) asm goto(x)
 #endif
 
 #endif /* __LINUX_COMPILER_TYPES_H */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 756b013fb832..75f00965ab15 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -829,8 +829,21 @@ __SYSCALL(__NR_futex_wait, sys_futex_wait)
 #define __NR_futex_requeue 456
 __SYSCALL(__NR_futex_requeue, sys_futex_requeue)
 
+#define __NR_statmount   457
+__SYSCALL(__NR_statmount, sys_statmount)
+
+#define __NR_listmount   458
+__SYSCALL(__NR_listmount, sys_listmount)
+
+#define __NR_lsm_get_self_attr 459
+__SYSCALL(__NR_lsm_get_self_attr, sys_lsm_get_self_attr)
+#define __NR_lsm_set_self_attr 460
+__SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr)
+#define __NR_lsm_list_modules 461
+__SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules)
+
 #undef __NR_syscalls
-#define __NR_syscalls 457
+#define __NR_syscalls 462
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index de723566c5ae..16122819edfe 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -713,7 +713,8 @@ struct drm_gem_open {
 /**
  * DRM_CAP_ASYNC_PAGE_FLIP
  *
- * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC.
+ * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC for legacy
+ * page-flips.
  */
 #define DRM_CAP_ASYNC_PAGE_FLIP		0x7
 /**
@@ -773,6 +774,13 @@ struct drm_gem_open {
  * :ref:`drm_sync_objects`.
  */
 #define DRM_CAP_SYNCOBJ_TIMELINE	0x14
+/**
+ * DRM_CAP_ATOMIC_ASYNC_PAGE_FLIP
+ *
+ * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC for atomic
+ * commits.
+ */
+#define DRM_CAP_ATOMIC_ASYNC_PAGE_FLIP	0x15
 
 /* DRM_IOCTL_GET_CAP ioctl argument type */
 struct drm_get_cap {
@@ -842,6 +850,31 @@ struct drm_get_cap {
  */
 #define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS	5
 
+/**
+ * DRM_CLIENT_CAP_CURSOR_PLANE_HOTSPOT
+ *
+ * Drivers for para-virtualized hardware (e.g. vmwgfx, qxl, virtio and
+ * virtualbox) have additional restrictions for cursor planes (thus
+ * making cursor planes on those drivers not truly universal,) e.g.
+ * they need cursor planes to act like one would expect from a mouse
+ * cursor and have correctly set hotspot properties.
+ * If this client cap is not set the DRM core will hide cursor plane on
+ * those virtualized drivers because not setting it implies that the
+ * client is not capable of dealing with those extra restictions.
+ * Clients which do set cursor hotspot and treat the cursor plane
+ * like a mouse cursor should set this property.
+ * The client must enable &DRM_CLIENT_CAP_ATOMIC first.
+ *
+ * Setting this property on drivers which do not special case
+ * cursor planes (i.e. non-virtualized drivers) will return
+ * EOPNOTSUPP, which can be used by userspace to gauge
+ * requirements of the hardware/drivers they're running on.
+ *
+ * This capability is always supported for atomic-capable virtualized
+ * drivers starting from kernel version 6.6.
+ */
+#define DRM_CLIENT_CAP_CURSOR_PLANE_HOTSPOT	6
+
 /* DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
 struct drm_set_client_cap {
 	__u64 capability;
@@ -893,6 +926,7 @@ struct drm_syncobj_transfer {
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0)
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1)
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE (1 << 2) /* wait for time point to become available */
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE (1 << 3) /* set fence deadline to deadline_nsec */
 struct drm_syncobj_wait {
 	__u64 handles;
 	/* absolute timeout */
@@ -901,6 +935,14 @@ struct drm_syncobj_wait {
 	__u32 flags;
 	__u32 first_signaled; /* only valid when not waiting all */
 	__u32 pad;
+	/**
+	 * @deadline_nsec - fence deadline hint
+	 *
+	 * Deadline hint, in absolute CLOCK_MONOTONIC, to set on backing
+	 * fence(s) if the DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE flag is
+	 * set.
+	 */
+	__u64 deadline_nsec;
 };
 
 struct drm_syncobj_timeline_wait {
@@ -913,6 +955,14 @@ struct drm_syncobj_timeline_wait {
 	__u32 flags;
 	__u32 first_signaled; /* only valid when not waiting all */
 	__u32 pad;
+	/**
+	 * @deadline_nsec - fence deadline hint
+	 *
+	 * Deadline hint, in absolute CLOCK_MONOTONIC, to set on backing
+	 * fence(s) if the DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE flag is
+	 * set.
+	 */
+	__u64 deadline_nsec;
 };
 
 /**
@@ -1218,6 +1268,26 @@ extern "C" {
 
 #define DRM_IOCTL_SYNCOBJ_EVENTFD	DRM_IOWR(0xCF, struct drm_syncobj_eventfd)
 
+/**
+ * DRM_IOCTL_MODE_CLOSEFB - Close a framebuffer.
+ *
+ * This closes a framebuffer previously added via ADDFB/ADDFB2. The IOCTL
+ * argument is a framebuffer object ID.
+ *
+ * This IOCTL is similar to &DRM_IOCTL_MODE_RMFB, except it doesn't disable
+ * planes and CRTCs. As long as the framebuffer is used by a plane, it's kept
+ * alive. When the plane no longer uses the framebuffer (because the
+ * framebuffer is replaced with another one, or the plane is disabled), the
+ * framebuffer is cleaned up.
+ *
+ * This is useful to implement flicker-free transitions between two processes.
+ *
+ * Depending on the threat model, user-space may want to ensure that the
+ * framebuffer doesn't expose any sensitive user information: closed
+ * framebuffers attached to a plane can be read back by the next DRM master.
+ */
+#define DRM_IOCTL_MODE_CLOSEFB		DRM_IOWR(0xD0, struct drm_mode_closefb)
+
 /*
  * Device specific ioctls should only be in their respective headers
  * The device specific ioctl range is from 0x40 to 0x9f.
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 218edb0a96f8..fd4f9574d177 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -693,7 +693,7 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_HAS_EXEC_FENCE	 44
 
 /* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to capture
- * user specified bufffers for post-mortem debugging of GPU hangs. See
+ * user-specified buffers for post-mortem debugging of GPU hangs. See
  * EXEC_OBJECT_CAPTURE.
  */
 #define I915_PARAM_HAS_EXEC_CAPTURE	 45
@@ -1606,7 +1606,7 @@ struct drm_i915_gem_busy {
 	 * is accurate.
 	 *
 	 * The returned dword is split into two fields to indicate both
-	 * the engine classess on which the object is being read, and the
+	 * the engine classes on which the object is being read, and the
 	 * engine class on which it is currently being written (if any).
 	 *
 	 * The low word (bits 0:15) indicate if the object is being written
@@ -1815,7 +1815,7 @@ struct drm_i915_gem_madvise {
 	__u32 handle;
 
 	/* Advice: either the buffer will be needed again in the near future,
-	 *         or wont be and could be discarded under memory pressure.
+	 *         or won't be and could be discarded under memory pressure.
 	 */
 	__u32 madv;
 
@@ -3246,7 +3246,7 @@ struct drm_i915_query_topology_info {
  * 	// enough to hold our array of engines. The kernel will fill out the
  * 	// item.length for us, which is the number of bytes we need.
  * 	//
- * 	// Alternatively a large buffer can be allocated straight away enabling
+ *	// Alternatively a large buffer can be allocated straightaway enabling
  * 	// querying in one pass, in which case item.length should contain the
  * 	// length of the provided buffer.
  * 	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
@@ -3256,7 +3256,7 @@ struct drm_i915_query_topology_info {
  * 	// Now that we allocated the required number of bytes, we call the ioctl
  * 	// again, this time with the data_ptr pointing to our newly allocated
  * 	// blob, which the kernel can then populate with info on all engines.
- * 	item.data_ptr = (uintptr_t)&info,
+ *	item.data_ptr = (uintptr_t)&info;
  *
  * 	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
  * 	if (err) ...
@@ -3286,7 +3286,7 @@ struct drm_i915_query_topology_info {
 /**
  * struct drm_i915_engine_info
  *
- * Describes one engine and it's capabilities as known to the driver.
+ * Describes one engine and its capabilities as known to the driver.
  */
 struct drm_i915_engine_info {
 	/** @engine: Engine class and instance. */
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
index 6c80f96049bd..282e90aeb163 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/include/uapi/linux/fcntl.h
@@ -116,5 +116,8 @@
 #define AT_HANDLE_FID		AT_REMOVEDIR	/* file handle is needed to
 					compare object identity and may not
 					be usable to open_by_handle_at(2) */
+#if defined(__KERNEL__)
+#define AT_GETATTR_NOSEC	0x80000000
+#endif
 
 #endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 211b86de35ac..c3308536482b 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -16,76 +16,6 @@
 
 #define KVM_API_VERSION 12
 
-/* *** Deprecated interfaces *** */
-
-#define KVM_TRC_SHIFT           16
-
-#define KVM_TRC_ENTRYEXIT       (1 << KVM_TRC_SHIFT)
-#define KVM_TRC_HANDLER         (1 << (KVM_TRC_SHIFT + 1))
-
-#define KVM_TRC_VMENTRY         (KVM_TRC_ENTRYEXIT + 0x01)
-#define KVM_TRC_VMEXIT          (KVM_TRC_ENTRYEXIT + 0x02)
-#define KVM_TRC_PAGE_FAULT      (KVM_TRC_HANDLER + 0x01)
-
-#define KVM_TRC_HEAD_SIZE       12
-#define KVM_TRC_CYCLE_SIZE      8
-#define KVM_TRC_EXTRA_MAX       7
-
-#define KVM_TRC_INJ_VIRQ         (KVM_TRC_HANDLER + 0x02)
-#define KVM_TRC_REDELIVER_EVT    (KVM_TRC_HANDLER + 0x03)
-#define KVM_TRC_PEND_INTR        (KVM_TRC_HANDLER + 0x04)
-#define KVM_TRC_IO_READ          (KVM_TRC_HANDLER + 0x05)
-#define KVM_TRC_IO_WRITE         (KVM_TRC_HANDLER + 0x06)
-#define KVM_TRC_CR_READ          (KVM_TRC_HANDLER + 0x07)
-#define KVM_TRC_CR_WRITE         (KVM_TRC_HANDLER + 0x08)
-#define KVM_TRC_DR_READ          (KVM_TRC_HANDLER + 0x09)
-#define KVM_TRC_DR_WRITE         (KVM_TRC_HANDLER + 0x0A)
-#define KVM_TRC_MSR_READ         (KVM_TRC_HANDLER + 0x0B)
-#define KVM_TRC_MSR_WRITE        (KVM_TRC_HANDLER + 0x0C)
-#define KVM_TRC_CPUID            (KVM_TRC_HANDLER + 0x0D)
-#define KVM_TRC_INTR             (KVM_TRC_HANDLER + 0x0E)
-#define KVM_TRC_NMI              (KVM_TRC_HANDLER + 0x0F)
-#define KVM_TRC_VMMCALL          (KVM_TRC_HANDLER + 0x10)
-#define KVM_TRC_HLT              (KVM_TRC_HANDLER + 0x11)
-#define KVM_TRC_CLTS             (KVM_TRC_HANDLER + 0x12)
-#define KVM_TRC_LMSW             (KVM_TRC_HANDLER + 0x13)
-#define KVM_TRC_APIC_ACCESS      (KVM_TRC_HANDLER + 0x14)
-#define KVM_TRC_TDP_FAULT        (KVM_TRC_HANDLER + 0x15)
-#define KVM_TRC_GTLB_WRITE       (KVM_TRC_HANDLER + 0x16)
-#define KVM_TRC_STLB_WRITE       (KVM_TRC_HANDLER + 0x17)
-#define KVM_TRC_STLB_INVAL       (KVM_TRC_HANDLER + 0x18)
-#define KVM_TRC_PPC_INSTR        (KVM_TRC_HANDLER + 0x19)
-
-struct kvm_user_trace_setup {
-	__u32 buf_size;
-	__u32 buf_nr;
-};
-
-#define __KVM_DEPRECATED_MAIN_W_0x06 \
-	_IOW(KVMIO, 0x06, struct kvm_user_trace_setup)
-#define __KVM_DEPRECATED_MAIN_0x07 _IO(KVMIO, 0x07)
-#define __KVM_DEPRECATED_MAIN_0x08 _IO(KVMIO, 0x08)
-
-#define __KVM_DEPRECATED_VM_R_0x70 _IOR(KVMIO, 0x70, struct kvm_assigned_irq)
-
-struct kvm_breakpoint {
-	__u32 enabled;
-	__u32 padding;
-	__u64 address;
-};
-
-struct kvm_debug_guest {
-	__u32 enabled;
-	__u32 pad;
-	struct kvm_breakpoint breakpoints[4];
-	__u32 singlestep;
-};
-
-#define __KVM_DEPRECATED_VCPU_W_0x87 _IOW(KVMIO, 0x87, struct kvm_debug_guest)
-
-/* *** End of deprecated interfaces *** */
-
-
 /* for KVM_SET_USER_MEMORY_REGION */
 struct kvm_userspace_memory_region {
 	__u32 slot;
@@ -95,6 +25,19 @@ struct kvm_userspace_memory_region {
 	__u64 userspace_addr; /* start of the userspace allocated memory */
 };
 
+/* for KVM_SET_USER_MEMORY_REGION2 */
+struct kvm_userspace_memory_region2 {
+	__u32 slot;
+	__u32 flags;
+	__u64 guest_phys_addr;
+	__u64 memory_size;
+	__u64 userspace_addr;
+	__u64 guest_memfd_offset;
+	__u32 guest_memfd;
+	__u32 pad1;
+	__u64 pad2[14];
+};
+
 /*
  * The bit 0 ~ bit 15 of kvm_userspace_memory_region::flags are visible for
  * userspace, other bits are reserved for kvm internal use which are defined
@@ -102,6 +45,7 @@ struct kvm_userspace_memory_region {
  */
 #define KVM_MEM_LOG_DIRTY_PAGES	(1UL << 0)
 #define KVM_MEM_READONLY	(1UL << 1)
+#define KVM_MEM_GUEST_MEMFD	(1UL << 2)
 
 /* for KVM_IRQ_LINE */
 struct kvm_irq_level {
@@ -265,6 +209,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_RISCV_CSR        36
 #define KVM_EXIT_NOTIFY           37
 #define KVM_EXIT_LOONGARCH_IOCSR  38
+#define KVM_EXIT_MEMORY_FAULT     39
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -518,6 +463,13 @@ struct kvm_run {
 #define KVM_NOTIFY_CONTEXT_INVALID	(1 << 0)
 			__u32 flags;
 		} notify;
+		/* KVM_EXIT_MEMORY_FAULT */
+		struct {
+#define KVM_MEMORY_EXIT_FLAG_PRIVATE	(1ULL << 3)
+			__u64 flags;
+			__u64 gpa;
+			__u64 size;
+		} memory_fault;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -945,9 +897,6 @@ struct kvm_ppc_resize_hpt {
  */
 #define KVM_GET_VCPU_MMAP_SIZE    _IO(KVMIO,   0x04) /* in bytes */
 #define KVM_GET_SUPPORTED_CPUID   _IOWR(KVMIO, 0x05, struct kvm_cpuid2)
-#define KVM_TRACE_ENABLE          __KVM_DEPRECATED_MAIN_W_0x06
-#define KVM_TRACE_PAUSE           __KVM_DEPRECATED_MAIN_0x07
-#define KVM_TRACE_DISABLE         __KVM_DEPRECATED_MAIN_0x08
 #define KVM_GET_EMULATED_CPUID	  _IOWR(KVMIO, 0x09, struct kvm_cpuid2)
 #define KVM_GET_MSR_FEATURE_INDEX_LIST    _IOWR(KVMIO, 0x0a, struct kvm_msr_list)
 
@@ -1201,6 +1150,11 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
 #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
 #define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230
+#define KVM_CAP_USER_MEMORY2 231
+#define KVM_CAP_MEMORY_FAULT_INFO 232
+#define KVM_CAP_MEMORY_ATTRIBUTES 233
+#define KVM_CAP_GUEST_MEMFD 234
+#define KVM_CAP_VM_TYPES 235
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1291,6 +1245,7 @@ struct kvm_x86_mce {
 #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL	(1 << 4)
 #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND		(1 << 5)
 #define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG	(1 << 6)
+#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE	(1 << 7)
 
 struct kvm_xen_hvm_config {
 	__u32 flags;
@@ -1483,6 +1438,8 @@ struct kvm_vfio_spapr_tce {
 					struct kvm_userspace_memory_region)
 #define KVM_SET_TSS_ADDR          _IO(KVMIO,   0x47)
 #define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO,  0x48, __u64)
+#define KVM_SET_USER_MEMORY_REGION2 _IOW(KVMIO, 0x49, \
+					 struct kvm_userspace_memory_region2)
 
 /* enable ucontrol for s390 */
 struct kvm_s390_ucas_mapping {
@@ -1507,20 +1464,8 @@ struct kvm_s390_ucas_mapping {
 			_IOW(KVMIO,  0x67, struct kvm_coalesced_mmio_zone)
 #define KVM_UNREGISTER_COALESCED_MMIO \
 			_IOW(KVMIO,  0x68, struct kvm_coalesced_mmio_zone)
-#define KVM_ASSIGN_PCI_DEVICE     _IOR(KVMIO,  0x69, \
-				       struct kvm_assigned_pci_dev)
 #define KVM_SET_GSI_ROUTING       _IOW(KVMIO,  0x6a, struct kvm_irq_routing)
-/* deprecated, replaced by KVM_ASSIGN_DEV_IRQ */
-#define KVM_ASSIGN_IRQ            __KVM_DEPRECATED_VM_R_0x70
-#define KVM_ASSIGN_DEV_IRQ        _IOW(KVMIO,  0x70, struct kvm_assigned_irq)
 #define KVM_REINJECT_CONTROL      _IO(KVMIO,   0x71)
-#define KVM_DEASSIGN_PCI_DEVICE   _IOW(KVMIO,  0x72, \
-				       struct kvm_assigned_pci_dev)
-#define KVM_ASSIGN_SET_MSIX_NR    _IOW(KVMIO,  0x73, \
-				       struct kvm_assigned_msix_nr)
-#define KVM_ASSIGN_SET_MSIX_ENTRY _IOW(KVMIO,  0x74, \
-				       struct kvm_assigned_msix_entry)
-#define KVM_DEASSIGN_DEV_IRQ      _IOW(KVMIO,  0x75, struct kvm_assigned_irq)
 #define KVM_IRQFD                 _IOW(KVMIO,  0x76, struct kvm_irqfd)
 #define KVM_CREATE_PIT2		  _IOW(KVMIO,  0x77, struct kvm_pit_config)
 #define KVM_SET_BOOT_CPU_ID       _IO(KVMIO,   0x78)
@@ -1537,9 +1482,6 @@ struct kvm_s390_ucas_mapping {
 *  KVM_CAP_VM_TSC_CONTROL to set defaults for a VM */
 #define KVM_SET_TSC_KHZ           _IO(KVMIO,  0xa2)
 #define KVM_GET_TSC_KHZ           _IO(KVMIO,  0xa3)
-/* Available with KVM_CAP_PCI_2_3 */
-#define KVM_ASSIGN_SET_INTX_MASK  _IOW(KVMIO,  0xa4, \
-				       struct kvm_assigned_pci_dev)
 /* Available with KVM_CAP_SIGNAL_MSI */
 #define KVM_SIGNAL_MSI            _IOW(KVMIO,  0xa5, struct kvm_msi)
 /* Available with KVM_CAP_PPC_GET_SMMU_INFO */
@@ -1592,8 +1534,6 @@ struct kvm_s390_ucas_mapping {
 #define KVM_SET_SREGS             _IOW(KVMIO,  0x84, struct kvm_sregs)
 #define KVM_TRANSLATE             _IOWR(KVMIO, 0x85, struct kvm_translation)
 #define KVM_INTERRUPT             _IOW(KVMIO,  0x86, struct kvm_interrupt)
-/* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */
-#define KVM_DEBUG_GUEST           __KVM_DEPRECATED_VCPU_W_0x87
 #define KVM_GET_MSRS              _IOWR(KVMIO, 0x88, struct kvm_msrs)
 #define KVM_SET_MSRS              _IOW(KVMIO,  0x89, struct kvm_msrs)
 #define KVM_SET_CPUID             _IOW(KVMIO,  0x8a, struct kvm_cpuid)
@@ -2267,4 +2207,24 @@ struct kvm_s390_zpci_op {
 /* flags for kvm_s390_zpci_op->u.reg_aen.flags */
 #define KVM_S390_ZPCIOP_REGAEN_HOST    (1 << 0)
 
+/* Available with KVM_CAP_MEMORY_ATTRIBUTES */
+#define KVM_SET_MEMORY_ATTRIBUTES              _IOW(KVMIO,  0xd2, struct kvm_memory_attributes)
+
+struct kvm_memory_attributes {
+	__u64 address;
+	__u64 size;
+	__u64 attributes;
+	__u64 flags;
+};
+
+#define KVM_MEMORY_ATTRIBUTE_PRIVATE           (1ULL << 3)
+
+#define KVM_CREATE_GUEST_MEMFD	_IOWR(KVMIO,  0xd4, struct kvm_create_guest_memfd)
+
+struct kvm_create_guest_memfd {
+	__u64 size;
+	__u64 flags;
+	__u64 reserved[6];
+};
+
 #endif /* __LINUX_KVM_H */
diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h
index bb242fdcfe6b..ad5478dbad00 100644
--- a/tools/include/uapi/linux/mount.h
+++ b/tools/include/uapi/linux/mount.h
@@ -138,4 +138,74 @@ struct mount_attr {
 /* List of all mount_attr versions. */
 #define MOUNT_ATTR_SIZE_VER0	32 /* sizeof first published struct */
 
+
+/*
+ * Structure for getting mount/superblock/filesystem info with statmount(2).
+ *
+ * The interface is similar to statx(2): individual fields or groups can be
+ * selected with the @mask argument of statmount().  Kernel will set the @mask
+ * field according to the supported fields.
+ *
+ * If string fields are selected, then the caller needs to pass a buffer that
+ * has space after the fixed part of the structure.  Nul terminated strings are
+ * copied there and offsets relative to @str are stored in the relevant fields.
+ * If the buffer is too small, then EOVERFLOW is returned.  The actually used
+ * size is returned in @size.
+ */
+struct statmount {
+	__u32 size;		/* Total size, including strings */
+	__u32 __spare1;
+	__u64 mask;		/* What results were written */
+	__u32 sb_dev_major;	/* Device ID */
+	__u32 sb_dev_minor;
+	__u64 sb_magic;		/* ..._SUPER_MAGIC */
+	__u32 sb_flags;		/* SB_{RDONLY,SYNCHRONOUS,DIRSYNC,LAZYTIME} */
+	__u32 fs_type;		/* [str] Filesystem type */
+	__u64 mnt_id;		/* Unique ID of mount */
+	__u64 mnt_parent_id;	/* Unique ID of parent (for root == mnt_id) */
+	__u32 mnt_id_old;	/* Reused IDs used in proc/.../mountinfo */
+	__u32 mnt_parent_id_old;
+	__u64 mnt_attr;		/* MOUNT_ATTR_... */
+	__u64 mnt_propagation;	/* MS_{SHARED,SLAVE,PRIVATE,UNBINDABLE} */
+	__u64 mnt_peer_group;	/* ID of shared peer group */
+	__u64 mnt_master;	/* Mount receives propagation from this ID */
+	__u64 propagate_from;	/* Propagation from in current namespace */
+	__u32 mnt_root;		/* [str] Root of mount relative to root of fs */
+	__u32 mnt_point;	/* [str] Mountpoint relative to current root */
+	__u64 __spare2[50];
+	char str[];		/* Variable size part containing strings */
+};
+
+/*
+ * Structure for passing mount ID and miscellaneous parameters to statmount(2)
+ * and listmount(2).
+ *
+ * For statmount(2) @param represents the request mask.
+ * For listmount(2) @param represents the last listed mount id (or zero).
+ */
+struct mnt_id_req {
+	__u32 size;
+	__u32 spare;
+	__u64 mnt_id;
+	__u64 param;
+};
+
+/* List of all mnt_id_req versions. */
+#define MNT_ID_REQ_SIZE_VER0	24 /* sizeof first published struct */
+
+/*
+ * @mask bits for statmount(2)
+ */
+#define STATMOUNT_SB_BASIC		0x00000001U     /* Want/got sb_... */
+#define STATMOUNT_MNT_BASIC		0x00000002U	/* Want/got mnt_... */
+#define STATMOUNT_PROPAGATE_FROM	0x00000004U	/* Want/got propagate_from */
+#define STATMOUNT_MNT_ROOT		0x00000008U	/* Want/got mnt_root  */
+#define STATMOUNT_MNT_POINT		0x00000010U	/* Want/got mnt_point */
+#define STATMOUNT_FS_TYPE		0x00000020U	/* Want/got fs_type */
+
+/*
+ * Special @mnt_id values that can be passed to listmount
+ */
+#define LSMT_ROOT		0xffffffffffffffff	/* root mount */
+
 #endif /* _UAPI_LINUX_MOUNT_H */
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 39c6a250dd1b..3a64499b0f5d 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -204,6 +204,8 @@ enum perf_branch_sample_type_shift {
 
 	PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT	= 18, /* save privilege mode */
 
+	PERF_SAMPLE_BRANCH_COUNTERS_SHIFT	= 19, /* save occurrences of events on a branch */
+
 	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
 };
 
@@ -235,6 +237,8 @@ enum perf_branch_sample_type {
 
 	PERF_SAMPLE_BRANCH_PRIV_SAVE	= 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT,
 
+	PERF_SAMPLE_BRANCH_COUNTERS	= 1U << PERF_SAMPLE_BRANCH_COUNTERS_SHIFT,
+
 	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
 
@@ -982,6 +986,12 @@ enum perf_event_type {
 	 *	{ u64                   nr;
 	 *	  { u64	hw_idx; } && PERF_SAMPLE_BRANCH_HW_INDEX
 	 *        { u64 from, to, flags } lbr[nr];
+	 *        #
+	 *        # The format of the counters is decided by the
+	 *        # "branch_counter_nr" and "branch_counter_width",
+	 *        # which are defined in the ABI.
+	 *        #
+	 *        { u64 counters; } cntr[nr] && PERF_SAMPLE_BRANCH_COUNTERS
 	 *      } && PERF_SAMPLE_BRANCH_STACK
 	 *
 	 * 	{ u64			abi; # enum perf_sample_regs_abi
@@ -1427,6 +1437,9 @@ struct perf_branch_entry {
 		reserved:31;
 };
 
+/* Size of used info bits in struct perf_branch_entry */
+#define PERF_BRANCH_ENTRY_INFO_BITS_MAX		33
+
 union perf_sample_weight {
 	__u64		full;
 #if defined(__LITTLE_ENDIAN_BITFIELD)
diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
index 7cab2c65d3d7..2f2ee82d5517 100644
--- a/tools/include/uapi/linux/stat.h
+++ b/tools/include/uapi/linux/stat.h
@@ -154,6 +154,7 @@ struct statx {
 #define STATX_BTIME		0x00000800U	/* Want/got stx_btime */
 #define STATX_MNT_ID		0x00001000U	/* Got stx_mnt_id */
 #define STATX_DIOALIGN		0x00002000U	/* Want/got direct I/O alignment info */
+#define STATX_MNT_ID_UNIQUE	0x00004000U	/* Want/got extended stx_mount_id */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 5cb0eeec2c8a..337fde770e45 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -16,6 +16,7 @@
 #include <sys/mount.h>
 
 #include "fs.h"
+#include "../io.h"
 #include "debug-internal.h"
 
 #define _STR(x) #x
@@ -344,53 +345,24 @@ int filename__read_ull(const char *filename, unsigned long long *value)
 	return filename__read_ull_base(filename, value, 0);
 }
 
-#define STRERR_BUFSIZE  128     /* For the buffer size of strerror_r */
-
 int filename__read_str(const char *filename, char **buf, size_t *sizep)
 {
-	size_t size = 0, alloc_size = 0;
-	void *bf = NULL, *nbf;
-	int fd, n, err = 0;
-	char sbuf[STRERR_BUFSIZE];
+	struct io io;
+	char bf[128];
+	int err;
 
-	fd = open(filename, O_RDONLY);
-	if (fd < 0)
+	io.fd = open(filename, O_RDONLY);
+	if (io.fd < 0)
 		return -errno;
-
-	do {
-		if (size == alloc_size) {
-			alloc_size += BUFSIZ;
-			nbf = realloc(bf, alloc_size);
-			if (!nbf) {
-				err = -ENOMEM;
-				break;
-			}
-
-			bf = nbf;
-		}
-
-		n = read(fd, bf + size, alloc_size - size);
-		if (n < 0) {
-			if (size) {
-				pr_warn("read failed %d: %s\n", errno,
-					strerror_r(errno, sbuf, sizeof(sbuf)));
-				err = 0;
-			} else
-				err = -errno;
-
-			break;
-		}
-
-		size += n;
-	} while (n > 0);
-
-	if (!err) {
-		*sizep = size;
-		*buf   = bf;
+	io__init(&io, io.fd, bf, sizeof(bf));
+	*buf = NULL;
+	err = io__getdelim(&io, buf, sizep, /*delim=*/-1);
+	if (err < 0) {
+		free(*buf);
+		*buf = NULL;
 	} else
-		free(bf);
-
-	close(fd);
+		err = 0;
+	close(io.fd);
 	return err;
 }
 
@@ -475,15 +447,22 @@ int sysfs__read_str(const char *entry, char **buf, size_t *sizep)
 
 int sysfs__read_bool(const char *entry, bool *value)
 {
-	char *buf;
-	size_t size;
-	int ret;
+	struct io io;
+	char bf[16];
+	int ret = 0;
+	char path[PATH_MAX];
+	const char *sysfs = sysfs__mountpoint();
+
+	if (!sysfs)
+		return -1;
 
-	ret = sysfs__read_str(entry, &buf, &size);
-	if (ret < 0)
-		return ret;
+	snprintf(path, sizeof(path), "%s/%s", sysfs, entry);
+	io.fd = open(path, O_RDONLY);
+	if (io.fd < 0)
+		return -errno;
 
-	switch (buf[0]) {
+	io__init(&io, io.fd, bf, sizeof(bf));
+	switch (io__get_char(&io)) {
 	case '1':
 	case 'y':
 	case 'Y':
@@ -497,8 +476,7 @@ int sysfs__read_bool(const char *entry, bool *value)
 	default:
 		ret = -1;
 	}
-
-	free(buf);
+	close(io.fd);
 
 	return ret;
 }
diff --git a/tools/lib/api/io.h b/tools/lib/api/io.h
index a77b74c5fb65..84adf8102018 100644
--- a/tools/lib/api/io.h
+++ b/tools/lib/api/io.h
@@ -12,6 +12,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+#include <linux/types.h>
 
 struct io {
 	/* File descriptor being read/ */
@@ -140,8 +141,8 @@ static inline int io__get_dec(struct io *io, __u64 *dec)
 	}
 }
 
-/* Read up to and including the first newline following the pattern of getline. */
-static inline ssize_t io__getline(struct io *io, char **line_out, size_t *line_len_out)
+/* Read up to and including the first delim. */
+static inline ssize_t io__getdelim(struct io *io, char **line_out, size_t *line_len_out, int delim)
 {
 	char buf[128];
 	int buf_pos = 0;
@@ -151,7 +152,7 @@ static inline ssize_t io__getline(struct io *io, char **line_out, size_t *line_l
 
 	/* TODO: reuse previously allocated memory. */
 	free(*line_out);
-	while (ch != '\n') {
+	while (ch != delim) {
 		ch = io__get_char(io);
 
 		if (ch < 0)
@@ -184,4 +185,9 @@ err_out:
 	return -ENOMEM;
 }
 
+static inline ssize_t io__getline(struct io *io, char **line_out, size_t *line_len_out)
+{
+	return io__getdelim(io, line_out, line_len_out, /*delim=*/'\n');
+}
+
 #endif /* __API_IO__ */
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index c5a42ac309fd..afd09571c482 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -6695,6 +6695,67 @@ static struct {
 	/* all other program types don't have "named" context structs */
 };
 
+static bool need_func_arg_type_fixup(const struct btf *btf, const struct bpf_program *prog,
+				     const char *subprog_name, int arg_idx,
+				     int arg_type_id, const char *ctx_name)
+{
+	const struct btf_type *t;
+	const char *tname;
+
+	/* check if existing parameter already matches verifier expectations */
+	t = skip_mods_and_typedefs(btf, arg_type_id, NULL);
+	if (!btf_is_ptr(t))
+		goto out_warn;
+
+	/* typedef bpf_user_pt_regs_t is a special PITA case, valid for kprobe
+	 * and perf_event programs, so check this case early on and forget
+	 * about it for subsequent checks
+	 */
+	while (btf_is_mod(t))
+		t = btf__type_by_id(btf, t->type);
+	if (btf_is_typedef(t) &&
+	    (prog->type == BPF_PROG_TYPE_KPROBE || prog->type == BPF_PROG_TYPE_PERF_EVENT)) {
+		tname = btf__str_by_offset(btf, t->name_off) ?: "<anon>";
+		if (strcmp(tname, "bpf_user_pt_regs_t") == 0)
+			return false; /* canonical type for kprobe/perf_event */
+	}
+
+	/* now we can ignore typedefs moving forward */
+	t = skip_mods_and_typedefs(btf, t->type, NULL);
+
+	/* if it's `void *`, definitely fix up BTF info */
+	if (btf_is_void(t))
+		return true;
+
+	/* if it's already proper canonical type, no need to fix up */
+	tname = btf__str_by_offset(btf, t->name_off) ?: "<anon>";
+	if (btf_is_struct(t) && strcmp(tname, ctx_name) == 0)
+		return false;
+
+	/* special cases */
+	switch (prog->type) {
+	case BPF_PROG_TYPE_KPROBE:
+	case BPF_PROG_TYPE_PERF_EVENT:
+		/* `struct pt_regs *` is expected, but we need to fix up */
+		if (btf_is_struct(t) && strcmp(tname, "pt_regs") == 0)
+			return true;
+		break;
+	case BPF_PROG_TYPE_RAW_TRACEPOINT:
+	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
+		/* allow u64* as ctx */
+		if (btf_is_int(t) && t->size == 8)
+			return true;
+		break;
+	default:
+		break;
+	}
+
+out_warn:
+	pr_warn("prog '%s': subprog '%s' arg#%d is expected to be of `struct %s *` type\n",
+		prog->name, subprog_name, arg_idx, ctx_name);
+	return false;
+}
+
 static int clone_func_btf_info(struct btf *btf, int orig_fn_id, struct bpf_program *prog)
 {
 	int fn_id, fn_proto_id, ret_type_id, orig_proto_id;
@@ -6757,6 +6818,69 @@ static int clone_func_btf_info(struct btf *btf, int orig_fn_id, struct bpf_progr
 	return fn_id;
 }
 
+static int probe_kern_arg_ctx_tag(void)
+{
+	/* To minimize merge conflicts with BPF token series that refactors
+	 * feature detection code a lot, we don't integrate
+	 * probe_kern_arg_ctx_tag() into kernel_supports() feature-detection
+	 * framework yet, doing our own caching internally.
+	 * This will be cleaned up a bit later when bpf/bpf-next trees settle.
+	 */
+	static int cached_result = -1;
+	static const char strs[] = "\0a\0b\0arg:ctx\0";
+	const __u32 types[] = {
+		/* [1] INT */
+		BTF_TYPE_INT_ENC(1 /* "a" */, BTF_INT_SIGNED, 0, 32, 4),
+		/* [2] PTR -> VOID */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 0),
+		/* [3] FUNC_PROTO `int(void *a)` */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 1),
+		BTF_PARAM_ENC(1 /* "a" */, 2),
+		/* [4] FUNC 'a' -> FUNC_PROTO (main prog) */
+		BTF_TYPE_ENC(1 /* "a" */, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 3),
+		/* [5] FUNC_PROTO `int(void *b __arg_ctx)` */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 1),
+		BTF_PARAM_ENC(3 /* "b" */, 2),
+		/* [6] FUNC 'b' -> FUNC_PROTO (subprog) */
+		BTF_TYPE_ENC(3 /* "b" */, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 5),
+		/* [7] DECL_TAG 'arg:ctx' -> func 'b' arg 'b' */
+		BTF_TYPE_DECL_TAG_ENC(5 /* "arg:ctx" */, 6, 0),
+	};
+	const struct bpf_insn insns[] = {
+		/* main prog */
+		BPF_CALL_REL(+1),
+		BPF_EXIT_INSN(),
+		/* global subprog */
+		BPF_EMIT_CALL(BPF_FUNC_get_func_ip), /* needs PTR_TO_CTX */
+		BPF_EXIT_INSN(),
+	};
+	const struct bpf_func_info_min func_infos[] = {
+		{ 0, 4 }, /* main prog -> FUNC 'a' */
+		{ 2, 6 }, /* subprog -> FUNC 'b' */
+	};
+	LIBBPF_OPTS(bpf_prog_load_opts, opts);
+	int prog_fd, btf_fd, insn_cnt = ARRAY_SIZE(insns);
+
+	if (cached_result >= 0)
+		return cached_result;
+
+	btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs));
+	if (btf_fd < 0)
+		return 0;
+
+	opts.prog_btf_fd = btf_fd;
+	opts.func_info = &func_infos;
+	opts.func_info_cnt = ARRAY_SIZE(func_infos);
+	opts.func_info_rec_size = sizeof(func_infos[0]);
+
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, "det_arg_ctx",
+				"GPL", insns, insn_cnt, &opts);
+	close(btf_fd);
+
+	cached_result = probe_fd(prog_fd);
+	return cached_result;
+}
+
 /* Check if main program or global subprog's function prototype has `arg:ctx`
  * argument tags, and, if necessary, substitute correct type to match what BPF
  * verifier would expect, taking into account specific program type. This
@@ -6766,7 +6890,7 @@ static int clone_func_btf_info(struct btf *btf, int orig_fn_id, struct bpf_progr
  */
 static int bpf_program_fixup_func_info(struct bpf_object *obj, struct bpf_program *prog)
 {
-	const char *ctx_name = NULL, *ctx_tag = "arg:ctx";
+	const char *ctx_name = NULL, *ctx_tag = "arg:ctx", *fn_name;
 	struct bpf_func_info_min *func_rec;
 	struct btf_type *fn_t, *fn_proto_t;
 	struct btf *btf = obj->btf;
@@ -6780,6 +6904,10 @@ static int bpf_program_fixup_func_info(struct bpf_object *obj, struct bpf_progra
 	if (!obj->btf_ext || !prog->func_info)
 		return 0;
 
+	/* don't do any fix ups if kernel natively supports __arg_ctx */
+	if (probe_kern_arg_ctx_tag() > 0)
+		return 0;
+
 	/* some BPF program types just don't have named context structs, so
 	 * this fallback mechanism doesn't work for them
 	 */
@@ -6842,15 +6970,11 @@ static int bpf_program_fixup_func_info(struct bpf_object *obj, struct bpf_progra
 		if (arg_idx < 0 || arg_idx >= arg_cnt)
 			continue;
 
-		/* check if existing parameter already matches verifier expectations */
+		/* check if we should fix up argument type */
 		p = &btf_params(fn_proto_t)[arg_idx];
-		t = skip_mods_and_typedefs(btf, p->type, NULL);
-		if (btf_is_ptr(t) &&
-		    (t = skip_mods_and_typedefs(btf, t->type, NULL)) &&
-		    btf_is_struct(t) &&
-		    strcmp(btf__str_by_offset(btf, t->name_off), ctx_name) == 0) {
-			continue; /* no need for fix up */
-		}
+		fn_name = btf__str_by_offset(btf, fn_t->name_off) ?: "<anon>";
+		if (!need_func_arg_type_fixup(btf, prog, fn_name, arg_idx, p->type, ctx_name))
+			continue;
 
 		/* clone fn/fn_proto, unless we already did it for another arg */
 		if (func_rec->type_id == orig_fn_id) {
diff --git a/tools/lib/perf/Documentation/examples/sampling.c b/tools/lib/perf/Documentation/examples/sampling.c
index 8e1a926a9cfe..bc142f0664b5 100644
--- a/tools/lib/perf/Documentation/examples/sampling.c
+++ b/tools/lib/perf/Documentation/examples/sampling.c
@@ -39,7 +39,7 @@ int main(int argc, char **argv)
 
 	libperf_init(libperf_print);
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus) {
 		fprintf(stderr, "failed to create cpus\n");
 		return -1;
diff --git a/tools/lib/perf/Documentation/libperf-sampling.txt b/tools/lib/perf/Documentation/libperf-sampling.txt
index d6ca24f6ef78..2378980fab8a 100644
--- a/tools/lib/perf/Documentation/libperf-sampling.txt
+++ b/tools/lib/perf/Documentation/libperf-sampling.txt
@@ -97,7 +97,7 @@ In this case we will monitor all the available CPUs:
 
 [source,c]
 --
- 42         cpus = perf_cpu_map__new(NULL);
+ 42         cpus = perf_cpu_map__new_online_cpus();
  43         if (!cpus) {
  44                 fprintf(stderr, "failed to create cpus\n");
  45                 return -1;
diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt
index a8f1a237931b..fcfb9499ef9c 100644
--- a/tools/lib/perf/Documentation/libperf.txt
+++ b/tools/lib/perf/Documentation/libperf.txt
@@ -37,7 +37,7 @@ SYNOPSIS
 
   struct perf_cpu_map;
 
-  struct perf_cpu_map *perf_cpu_map__dummy_new(void);
+  struct perf_cpu_map *perf_cpu_map__new_any_cpu(void);
   struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
   struct perf_cpu_map *perf_cpu_map__read(FILE *file);
   struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
@@ -46,7 +46,7 @@ SYNOPSIS
   void perf_cpu_map__put(struct perf_cpu_map *map);
   int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
   int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
-  bool perf_cpu_map__empty(const struct perf_cpu_map *map);
+  bool perf_cpu_map__has_any_cpu_or_is_empty(const struct perf_cpu_map *map);
   int perf_cpu_map__max(struct perf_cpu_map *map);
   bool perf_cpu_map__has(const struct perf_cpu_map *map, int cpu);
 
diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index 2a5a29217374..4adcd7920d03 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -9,6 +9,7 @@
 #include <unistd.h>
 #include <ctype.h>
 #include <limits.h>
+#include "internal.h"
 
 void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus)
 {
@@ -27,7 +28,7 @@ struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus)
 	return result;
 }
 
-struct perf_cpu_map *perf_cpu_map__dummy_new(void)
+struct perf_cpu_map *perf_cpu_map__new_any_cpu(void)
 {
 	struct perf_cpu_map *cpus = perf_cpu_map__alloc(1);
 
@@ -66,15 +67,21 @@ void perf_cpu_map__put(struct perf_cpu_map *map)
 	}
 }
 
-static struct perf_cpu_map *cpu_map__default_new(void)
+static struct perf_cpu_map *cpu_map__new_sysconf(void)
 {
 	struct perf_cpu_map *cpus;
-	int nr_cpus;
+	int nr_cpus, nr_cpus_conf;
 
 	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
 	if (nr_cpus < 0)
 		return NULL;
 
+	nr_cpus_conf = sysconf(_SC_NPROCESSORS_CONF);
+	if (nr_cpus != nr_cpus_conf) {
+		pr_warning("Number of online CPUs (%d) differs from the number configured (%d) the CPU map will only cover the first %d CPUs.",
+			nr_cpus, nr_cpus_conf, nr_cpus);
+	}
+
 	cpus = perf_cpu_map__alloc(nr_cpus);
 	if (cpus != NULL) {
 		int i;
@@ -86,9 +93,27 @@ static struct perf_cpu_map *cpu_map__default_new(void)
 	return cpus;
 }
 
-struct perf_cpu_map *perf_cpu_map__default_new(void)
+static struct perf_cpu_map *cpu_map__new_sysfs_online(void)
 {
-	return cpu_map__default_new();
+	struct perf_cpu_map *cpus = NULL;
+	FILE *onlnf;
+
+	onlnf = fopen("/sys/devices/system/cpu/online", "r");
+	if (onlnf) {
+		cpus = perf_cpu_map__read(onlnf);
+		fclose(onlnf);
+	}
+	return cpus;
+}
+
+struct perf_cpu_map *perf_cpu_map__new_online_cpus(void)
+{
+	struct perf_cpu_map *cpus = cpu_map__new_sysfs_online();
+
+	if (cpus)
+		return cpus;
+
+	return cpu_map__new_sysconf();
 }
 
 
@@ -180,27 +205,11 @@ struct perf_cpu_map *perf_cpu_map__read(FILE *file)
 
 	if (nr_cpus > 0)
 		cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
-	else
-		cpus = cpu_map__default_new();
 out_free_tmp:
 	free(tmp_cpus);
 	return cpus;
 }
 
-static struct perf_cpu_map *cpu_map__read_all_cpu_map(void)
-{
-	struct perf_cpu_map *cpus = NULL;
-	FILE *onlnf;
-
-	onlnf = fopen("/sys/devices/system/cpu/online", "r");
-	if (!onlnf)
-		return cpu_map__default_new();
-
-	cpus = perf_cpu_map__read(onlnf);
-	fclose(onlnf);
-	return cpus;
-}
-
 struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 {
 	struct perf_cpu_map *cpus = NULL;
@@ -211,7 +220,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 	int max_entries = 0;
 
 	if (!cpu_list)
-		return cpu_map__read_all_cpu_map();
+		return perf_cpu_map__new_online_cpus();
 
 	/*
 	 * must handle the case of empty cpumap to cover
@@ -268,10 +277,12 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 
 	if (nr_cpus > 0)
 		cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
-	else if (*cpu_list != '\0')
-		cpus = cpu_map__default_new();
-	else
-		cpus = perf_cpu_map__dummy_new();
+	else if (*cpu_list != '\0') {
+		pr_warning("Unexpected characters at end of cpu list ('%s'), using online CPUs.",
+			   cpu_list);
+		cpus = perf_cpu_map__new_online_cpus();
+	} else
+		cpus = perf_cpu_map__new_any_cpu();
 invalid:
 	free(tmp_cpus);
 out:
@@ -300,7 +311,7 @@ int perf_cpu_map__nr(const struct perf_cpu_map *cpus)
 	return cpus ? __perf_cpu_map__nr(cpus) : 1;
 }
 
-bool perf_cpu_map__empty(const struct perf_cpu_map *map)
+bool perf_cpu_map__has_any_cpu_or_is_empty(const struct perf_cpu_map *map)
 {
 	return map ? __perf_cpu_map__cpu(map, 0).cpu == -1 : true;
 }
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 3acbbccc1901..058e3ff10f9b 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -39,7 +39,7 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 	if (evsel->system_wide) {
 		/* System wide: set the cpu map of the evsel to all online CPUs. */
 		perf_cpu_map__put(evsel->cpus);
-		evsel->cpus = perf_cpu_map__new(NULL);
+		evsel->cpus = perf_cpu_map__new_online_cpus();
 	} else if (evlist->has_user_cpus && evsel->is_pmu_core) {
 		/*
 		 * User requested CPUs on a core PMU, ensure the requested CPUs
@@ -619,7 +619,7 @@ static int perf_evlist__nr_mmaps(struct perf_evlist *evlist)
 
 	/* One for each CPU */
 	nr_mmaps = perf_cpu_map__nr(evlist->all_cpus);
-	if (perf_cpu_map__empty(evlist->all_cpus)) {
+	if (perf_cpu_map__has_any_cpu_or_is_empty(evlist->all_cpus)) {
 		/* Plus one for each thread */
 		nr_mmaps += perf_thread_map__nr(evlist->threads);
 		/* Minus the per-thread CPU (-1) */
@@ -653,7 +653,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 	if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
 		return -ENOMEM;
 
-	if (perf_cpu_map__empty(cpus))
+	if (perf_cpu_map__has_any_cpu_or_is_empty(cpus))
 		return mmap_per_thread(evlist, ops, mp);
 
 	return mmap_per_cpu(evlist, ops, mp);
diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index 8b51b008a81f..c07160953224 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -120,7 +120,7 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 		static struct perf_cpu_map *empty_cpu_map;
 
 		if (empty_cpu_map == NULL) {
-			empty_cpu_map = perf_cpu_map__dummy_new();
+			empty_cpu_map = perf_cpu_map__new_any_cpu();
 			if (empty_cpu_map == NULL)
 				return -ENOMEM;
 		}
diff --git a/tools/lib/perf/include/internal/mmap.h b/tools/lib/perf/include/internal/mmap.h
index 5a062af8e9d8..5f08cab61ece 100644
--- a/tools/lib/perf/include/internal/mmap.h
+++ b/tools/lib/perf/include/internal/mmap.h
@@ -33,7 +33,8 @@ struct perf_mmap {
 	bool			 overwrite;
 	u64			 flush;
 	libperf_unmap_cb_t	 unmap_cb;
-	char			 event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);
+	void			*event_copy;
+	size_t			 event_copy_sz;
 	struct perf_mmap	*next;
 };
 
diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index e38d859a384d..228c6c629b0c 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -19,10 +19,23 @@ struct perf_cache {
 struct perf_cpu_map;
 
 /**
- * perf_cpu_map__dummy_new - a map with a singular "any CPU"/dummy -1 value.
+ * perf_cpu_map__new_any_cpu - a map with a singular "any CPU"/dummy -1 value.
+ */
+LIBPERF_API struct perf_cpu_map *perf_cpu_map__new_any_cpu(void);
+/**
+ * perf_cpu_map__new_online_cpus - a map read from
+ *                                 /sys/devices/system/cpu/online if
+ *                                 available. If reading wasn't possible a map
+ *                                 is created using the online processors
+ *                                 assuming the first 'n' processors are all
+ *                                 online.
+ */
+LIBPERF_API struct perf_cpu_map *perf_cpu_map__new_online_cpus(void);
+/**
+ * perf_cpu_map__new - create a map from the given cpu_list such as "0-7". If no
+ *                     cpu_list argument is provided then
+ *                     perf_cpu_map__new_online_cpus is returned.
  */
-LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void);
-LIBPERF_API struct perf_cpu_map *perf_cpu_map__default_new(void);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__read(FILE *file);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
@@ -31,12 +44,23 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__intersect(struct perf_cpu_map *orig,
 							 struct perf_cpu_map *other);
 LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
+/**
+ * perf_cpu_map__cpu - get the CPU value at the given index. Returns -1 if index
+ *                     is invalid.
+ */
 LIBPERF_API struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
+/**
+ * perf_cpu_map__nr - for an empty map returns 1, as perf_cpu_map__cpu returns a
+ *                    cpu of -1 for an invalid index, this makes an empty map
+ *                    look like it contains the "any CPU"/dummy value. Otherwise
+ *                    the result is the number CPUs in the map plus one if the
+ *                    "any CPU"/dummy value is present.
+ */
 LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
 /**
- * perf_cpu_map__empty - is map either empty or the "any CPU"/dummy value.
+ * perf_cpu_map__has_any_cpu_or_is_empty - is map either empty or has the "any CPU"/dummy value.
  */
-LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map);
+LIBPERF_API bool perf_cpu_map__has_any_cpu_or_is_empty(const struct perf_cpu_map *map);
 LIBPERF_API struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map);
 LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu);
 LIBPERF_API bool perf_cpu_map__equal(const struct perf_cpu_map *lhs,
@@ -51,6 +75,12 @@ LIBPERF_API bool perf_cpu_map__has_any_cpu(const struct perf_cpu_map *map);
 	     (idx) < perf_cpu_map__nr(cpus);			\
 	     (idx)++, (cpu) = perf_cpu_map__cpu(cpus, idx))
 
+#define perf_cpu_map__for_each_cpu_skip_any(_cpu, idx, cpus)	\
+	for ((idx) = 0, (_cpu) = perf_cpu_map__cpu(cpus, idx);	\
+	     (idx) < perf_cpu_map__nr(cpus);			\
+	     (idx)++, (_cpu) = perf_cpu_map__cpu(cpus, idx))	\
+		if ((_cpu).cpu != -1)
+
 #define perf_cpu_map__for_each_idx(idx, cpus)				\
 	for ((idx) = 0; (idx) < perf_cpu_map__nr(cpus); (idx)++)
 
diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map
index 190b56ae923a..10b3f3722642 100644
--- a/tools/lib/perf/libperf.map
+++ b/tools/lib/perf/libperf.map
@@ -1,15 +1,15 @@
 LIBPERF_0.0.1 {
 	global:
 		libperf_init;
-		perf_cpu_map__dummy_new;
-		perf_cpu_map__default_new;
+		perf_cpu_map__new_any_cpu;
+		perf_cpu_map__new_online_cpus;
 		perf_cpu_map__get;
 		perf_cpu_map__put;
 		perf_cpu_map__new;
 		perf_cpu_map__read;
 		perf_cpu_map__nr;
 		perf_cpu_map__cpu;
-		perf_cpu_map__empty;
+		perf_cpu_map__has_any_cpu_or_is_empty;
 		perf_cpu_map__max;
 		perf_cpu_map__has;
 		perf_thread_map__new_array;
diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c
index 2184814b37dd..0c903c2372c9 100644
--- a/tools/lib/perf/mmap.c
+++ b/tools/lib/perf/mmap.c
@@ -19,6 +19,7 @@
 void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev,
 		     bool overwrite, libperf_unmap_cb_t unmap_cb)
 {
+	/* Assume fields were zero initialized. */
 	map->fd = -1;
 	map->overwrite = overwrite;
 	map->unmap_cb  = unmap_cb;
@@ -51,13 +52,18 @@ int perf_mmap__mmap(struct perf_mmap *map, struct perf_mmap_param *mp,
 
 void perf_mmap__munmap(struct perf_mmap *map)
 {
-	if (map && map->base != NULL) {
+	if (!map)
+		return;
+
+	zfree(&map->event_copy);
+	map->event_copy_sz = 0;
+	if (map->base) {
 		munmap(map->base, perf_mmap__mmap_len(map));
 		map->base = NULL;
 		map->fd = -1;
 		refcount_set(&map->refcnt, 0);
 	}
-	if (map && map->unmap_cb)
+	if (map->unmap_cb)
 		map->unmap_cb(map);
 }
 
@@ -223,9 +229,17 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map,
 		 */
 		if ((*startp & map->mask) + size != ((*startp + size) & map->mask)) {
 			unsigned int offset = *startp;
-			unsigned int len = min(sizeof(*event), size), cpy;
+			unsigned int len = size, cpy;
 			void *dst = map->event_copy;
 
+			if (size > map->event_copy_sz) {
+				dst = realloc(map->event_copy, size);
+				if (!dst)
+					return NULL;
+				map->event_copy = dst;
+				map->event_copy_sz = size;
+			}
+
 			do {
 				cpy = min(map->mask + 1 - (offset & map->mask), len);
 				memcpy(dst, &data[offset & map->mask], cpy);
diff --git a/tools/lib/perf/tests/test-cpumap.c b/tools/lib/perf/tests/test-cpumap.c
index 87b0510a556f..c998b1dae863 100644
--- a/tools/lib/perf/tests/test-cpumap.c
+++ b/tools/lib/perf/tests/test-cpumap.c
@@ -21,7 +21,7 @@ int test_cpumap(int argc, char **argv)
 
 	libperf_init(libperf_print);
 
-	cpus = perf_cpu_map__dummy_new();
+	cpus = perf_cpu_map__new_any_cpu();
 	if (!cpus)
 		return -1;
 
@@ -29,7 +29,7 @@ int test_cpumap(int argc, char **argv)
 	perf_cpu_map__put(cpus);
 	perf_cpu_map__put(cpus);
 
-	cpus = perf_cpu_map__default_new();
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus)
 		return -1;
 
diff --git a/tools/lib/perf/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c
index ed616fc19b4f..10f70cb41ff1 100644
--- a/tools/lib/perf/tests/test-evlist.c
+++ b/tools/lib/perf/tests/test-evlist.c
@@ -46,7 +46,7 @@ static int test_stat_cpu(void)
 	};
 	int err, idx;
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	__T("failed to create cpus", cpus);
 
 	evlist = perf_evlist__new();
@@ -261,7 +261,7 @@ static int test_mmap_thread(void)
 	threads = perf_thread_map__new_dummy();
 	__T("failed to create threads", threads);
 
-	cpus = perf_cpu_map__dummy_new();
+	cpus = perf_cpu_map__new_any_cpu();
 	__T("failed to create cpus", cpus);
 
 	perf_thread_map__set_pid(threads, 0, pid);
@@ -350,7 +350,7 @@ static int test_mmap_cpus(void)
 
 	attr.config = id;
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	__T("failed to create cpus", cpus);
 
 	evlist = perf_evlist__new();
diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c
index a11fc51bfb68..545ec3150546 100644
--- a/tools/lib/perf/tests/test-evsel.c
+++ b/tools/lib/perf/tests/test-evsel.c
@@ -27,7 +27,7 @@ static int test_stat_cpu(void)
 	};
 	int err, idx;
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	__T("failed to create cpus", cpus);
 
 	evsel = perf_evsel__new(&attr);
diff --git a/tools/lib/subcmd/help.c b/tools/lib/subcmd/help.c
index adfbae27dc36..8561b0f01a24 100644
--- a/tools/lib/subcmd/help.c
+++ b/tools/lib/subcmd/help.c
@@ -52,11 +52,21 @@ void uniq(struct cmdnames *cmds)
 	if (!cmds->cnt)
 		return;
 
-	for (i = j = 1; i < cmds->cnt; i++)
-		if (strcmp(cmds->names[i]->name, cmds->names[i-1]->name))
-			cmds->names[j++] = cmds->names[i];
-
+	for (i = 1; i < cmds->cnt; i++) {
+		if (!strcmp(cmds->names[i]->name, cmds->names[i-1]->name))
+			zfree(&cmds->names[i - 1]);
+	}
+	for (i = 0, j = 0; i < cmds->cnt; i++) {
+		if (cmds->names[i]) {
+			if (i == j)
+				j++;
+			else
+				cmds->names[j++] = cmds->names[i];
+		}
+	}
 	cmds->cnt = j;
+	while (j < i)
+		cmds->names[j++] = NULL;
 }
 
 void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes)
diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c
index c82a7f41b31c..45e49671ae87 100644
--- a/tools/net/ynl/lib/ynl.c
+++ b/tools/net/ynl/lib/ynl.c
@@ -466,6 +466,8 @@ ynl_gemsg_start_dump(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version)
 
 int ynl_recv_ack(struct ynl_sock *ys, int ret)
 {
+	struct ynl_parse_arg yarg = { .ys = ys, };
+
 	if (!ret) {
 		yerr(ys, YNL_ERROR_EXPECT_ACK,
 		     "Expecting an ACK but nothing received");
@@ -478,7 +480,7 @@ int ynl_recv_ack(struct ynl_sock *ys, int ret)
 		return ret;
 	}
 	return mnl_cb_run(ys->rx_buf, ret, ys->seq, ys->portid,
-			  ynl_cb_null, ys);
+			  ynl_cb_null, &yarg);
 }
 
 int ynl_cb_null(const struct nlmsghdr *nlh, void *data)
@@ -521,6 +523,7 @@ ynl_get_family_info_mcast(struct ynl_sock *ys, const struct nlattr *mcasts)
 				ys->mcast_groups[i].name[GENL_NAMSIZ - 1] = 0;
 			}
 		}
+		i++;
 	}
 
 	return 0;
@@ -586,7 +589,13 @@ static int ynl_sock_read_family(struct ynl_sock *ys, const char *family_name)
 		return err;
 	}
 
-	return ynl_recv_ack(ys, err);
+	err = ynl_recv_ack(ys, err);
+	if (err < 0) {
+		free(ys->mcast_groups);
+		return err;
+	}
+
+	return 0;
 }
 
 struct ynl_sock *
@@ -741,11 +750,14 @@ err_free:
 
 static int ynl_ntf_trampoline(const struct nlmsghdr *nlh, void *data)
 {
-	return ynl_ntf_parse((struct ynl_sock *)data, nlh);
+	struct ynl_parse_arg *yarg = data;
+
+	return ynl_ntf_parse(yarg->ys, nlh);
 }
 
 int ynl_ntf_check(struct ynl_sock *ys)
 {
+	struct ynl_parse_arg yarg = { .ys = ys, };
 	ssize_t len;
 	int err;
 
@@ -767,7 +779,7 @@ int ynl_ntf_check(struct ynl_sock *ys)
 			return len;
 
 		err = mnl_cb_run2(ys->rx_buf, len, ys->seq, ys->portid,
-				  ynl_ntf_trampoline, ys,
+				  ynl_ntf_trampoline, &yarg,
 				  ynl_cb_array, NLMSG_MIN_TYPE);
 		if (err < 0)
 			return err;
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index f533e76fb480..f5b81d439387 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -39,6 +39,9 @@ trace/beauty/generated/
 pmu-events/pmu-events.c
 pmu-events/jevents
 pmu-events/metric_test.log
+tests/shell/*.shellcheck_log
+tests/shell/coresight/*.shellcheck_log
+tests/shell/lib/*.shellcheck_log
 feature/
 libapi/
 libbpf/
@@ -49,3 +52,4 @@ libtraceevent/
 libtraceevent_plugins/
 fixdep
 Documentation/doc.dep
+python_ext_build/
diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt
index a97f95825b14..19cc179be9a7 100644
--- a/tools/perf/Documentation/itrace.txt
+++ b/tools/perf/Documentation/itrace.txt
@@ -25,6 +25,7 @@
 		q	quicker (less detailed) decoding
 		A	approximate IPC
 		Z	prefer to ignore timestamps (so-called "timeless" decoding)
+		T	use the timestamp trace as kernel time
 
 	The default is all events i.e. the same as --itrace=iybxwpe,
 	except for perf script where it is --itrace=ce
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index fe168e8165c8..b95524bea021 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -155,6 +155,17 @@ include::itrace.txt[]
 	stdio or stdio2 (Default: 0).  Note that this is about selection of
 	functions to display, not about lines within the function.
 
+--data-type[=TYPE_NAME]::
+	Display data type annotation instead of code.  It infers data type of
+	samples (if they are memory accessing instructions) using DWARF debug
+	information.  It can take an optional argument of data type name.  In
+	that case it'd show annotation for the type only, otherwise it'd show
+	all data types it finds.
+
+--type-stat::
+	Show stats for the data type annotation.
+
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 0b4e79dbd3f6..379f9d7a8ab1 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -251,7 +251,8 @@ annotate.*::
 		addr2line binary to use for file names and line numbers.
 
 	annotate.objdump::
-		objdump binary to use for disassembly and annotations.
+		objdump binary to use for disassembly and annotations,
+		including in the 'perf test' command.
 
 	annotate.disassembler_style::
 		Use this to change the default disassembler style to some other value
@@ -722,7 +723,6 @@ session-<NAME>.*::
 		Defines new record session for daemon. The value is record's
 		command line without the 'record' keyword.
 
-
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index d5f78e125efe..3b12595193c9 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -47,6 +47,10 @@ Print PMU events and metrics limited to the specific PMU name.
 --json::
 Output in JSON format.
 
+-o::
+--output=::
+	Output file name. By default output is written to stdout.
+
 [[EVENT_MODIFIERS]]
 EVENT MODIFIERS
 ---------------
@@ -81,11 +85,13 @@ For Intel systems precise event sampling is implemented with PEBS
 which supports up to precise-level 2, and precise level 3 for
 some special cases
 
-On AMD systems it is implemented using IBS (up to precise-level 2).
-The precise modifier works with event types 0x76 (cpu-cycles, CPU
-clocks not halted) and 0xC1 (micro-ops retired). Both events map to
-IBS execution sampling (IBS op) with the IBS Op Counter Control bit
-(IbsOpCntCtl) set respectively (see the
+On AMD systems it is implemented using IBS OP (up to precise-level 2).
+Unlike Intel PEBS which provides levels of precision, AMD core pmu is
+inherently non-precise and IBS is inherently precise. (i.e. ibs_op//,
+ibs_op//p, ibs_op//pp and ibs_op//ppp are all same). The precise modifier
+works with event types 0x76 (cpu-cycles, CPU clocks not halted) and 0xC1
+(micro-ops retired). Both events map to IBS execution sampling (IBS op)
+with the IBS Op Counter Control bit (IbsOpCntCtl) set respectively (see the
 Core Complex (CCX) -> Processor x86 Core -> Instruction Based Sampling (IBS)
 section of the [AMD Processor Programming Reference (PPR)] relevant to the
 family, model and stepping of the processor being used).
diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
index 503abcba1438..f5938d616d75 100644
--- a/tools/perf/Documentation/perf-lock.txt
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -119,7 +119,7 @@ INFO OPTIONS
 
 
 CONTENTION OPTIONS
---------------
+------------------
 
 -k::
 --key=<value>::
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 1889f66addf2..6015fdd08fb6 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -445,6 +445,10 @@ following filters are defined:
 		     4th-Gen Xeon+ server), the save branch type is unconditionally enabled
 		     when the taken branch stack sampling is enabled.
 	- priv: save privilege state during sampling in case binary is not available later
+	- counter: save occurrences of the event since the last branch entry. Currently, the
+		   feature is only supported by a newer CPU, e.g., Intel Sierra Forest and
+		   later platforms. An error out is expected if it's used on the unsupported
+		   kernel or CPUs.
 
 +
 The option requires at least one branch type among any, any_call, any_ret, ind_call, cond.
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index af068b4f1e5a..38f59ac064f7 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -118,6 +118,9 @@ OPTIONS
 	- retire_lat: On X86, this reports pipeline stall of this instruction compared
 	  to the previous instruction in cycles. And currently supported only on X86
 	- simd: Flags describing a SIMD operation. "e" for empty Arm SVE predicate. "p" for partial Arm SVE predicate
+	- type: Data type of sample memory access.
+	- typeoff: Offset in the data type of sample memory access.
+	- symoff: Offset in the symbol.
 
 	By default, comm, dso and symbol keys are used.
 	(i.e. --sort comm,dso,symbol)
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 8f789fa1242e..5af2e432b54f 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -422,7 +422,34 @@ See perf list output for the possible metrics and metricgroups.
 
 -A::
 --no-aggr::
-Do not aggregate counts across all monitored CPUs.
+--no-merge::
+Do not aggregate/merge counts across monitored CPUs or PMUs.
+
+When multiple events are created from a single event specification,
+stat will, by default, aggregate the event counts and show the result
+in a single row. This option disables that behavior and shows the
+individual events and counts.
+
+Multiple events are created from a single event specification when:
+
+1. PID monitoring isn't requested and the system has more than one
+   CPU. For example, a system with 8 SMT threads will have one event
+   opened on each thread and aggregation is performed across them.
+
+2. Prefix or glob wildcard matching is used for the PMU name. For
+   example, multiple memory controller PMUs may exist typically with a
+   suffix of _0, _1, etc. By default the event counts will all be
+   combined if the PMU is specified without the suffix such as
+   uncore_imc rather than uncore_imc_0.
+
+3. Aliases, which are listed immediately after the Kernel PMU events
+   by perf list, are used.
+
+--hybrid-merge::
+Merge core event counts from all core PMUs. In hybrid or big.LITTLE
+systems by default each core PMU will report its count
+separately. This option forces core PMU counts to be combined to give
+a behavior closer to having a single CPU type in the system.
 
 --topdown::
 Print top-down metrics supported by the CPU. This allows to determine
@@ -475,29 +502,6 @@ highlight 'tma_frontend_bound'. This metric may be drilled into with
 
 Error out if the input is higher than the supported max level.
 
---no-merge::
-Do not merge results from same PMUs.
-
-When multiple events are created from a single event specification,
-stat will, by default, aggregate the event counts and show the result
-in a single row. This option disables that behavior and shows
-the individual events and counts.
-
-Multiple events are created from a single event specification when:
-1. Prefix or glob matching is used for the PMU name.
-2. Aliases, which are listed immediately after the Kernel PMU events
-   by perf list, are used.
-
---hybrid-merge::
-Merge the hybrid event counts from all PMUs.
-
-For hybrid events, by default, the stat aggregates and reports the event
-counts per PMU. But sometimes, it's also useful to aggregate event counts
-from all PMUs. This option enables that behavior and reports the counts
-without PMUs.
-
-For non-hybrid events, it should be no effect.
-
 --smi-cost::
 Measure SMI cost if msr/aperf/ and msr/smi/ events are supported.
 
diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt
index ba3df49c169d..a7cf7bc2f968 100644
--- a/tools/perf/Documentation/perf.txt
+++ b/tools/perf/Documentation/perf.txt
@@ -64,6 +64,9 @@ OPTIONS
           perf-event-open  - Print perf_event_open() arguments and
                              return value
 
+--debug-file::
+	Write debug output to a specified file.
+
 DESCRIPTION
 -----------
 Performance counters for Linux are a new kernel-based subsystem
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index b3e6ed10f40c..aa55850fbc21 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -476,6 +476,11 @@ else
       else
         CFLAGS += -DHAVE_DWARF_GETLOCATIONS_SUPPORT
       endif # dwarf_getlocations
+      ifneq ($(feature-dwarf_getcfi), 1)
+        msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.142);
+      else
+        CFLAGS += -DHAVE_DWARF_CFI_SUPPORT
+      endif # dwarf_getcfi
     endif # Dwarf support
   endif # libelf support
 endif # NO_LIBELF
@@ -680,15 +685,15 @@ ifndef BUILD_BPF_SKEL
 endif
 
 ifeq ($(BUILD_BPF_SKEL),1)
-  ifeq ($(filter -DHAVE_LIBBPF_SUPPORT, $(CFLAGS)),)
-    dummy := $(warning Warning: Disabled BPF skeletons as libbpf is required)
-    BUILD_BPF_SKEL := 0
-  else ifeq ($(filter -DHAVE_LIBELF_SUPPORT, $(CFLAGS)),)
+  ifeq ($(filter -DHAVE_LIBELF_SUPPORT, $(CFLAGS)),)
     dummy := $(warning Warning: Disabled BPF skeletons as libelf is required by bpftool)
     BUILD_BPF_SKEL := 0
   else ifeq ($(filter -DHAVE_ZLIB_SUPPORT, $(CFLAGS)),)
     dummy := $(warning Warning: Disabled BPF skeletons as zlib is required by bpftool)
     BUILD_BPF_SKEL := 0
+  else ifeq ($(filter -DHAVE_LIBBPF_SUPPORT, $(CFLAGS)),)
+    dummy := $(warning Warning: Disabled BPF skeletons as libbpf is required)
+    BUILD_BPF_SKEL := 0
   else ifeq ($(call get-executable,$(CLANG)),)
     dummy := $(warning Warning: Disabled BPF skeletons as clang ($(CLANG)) is missing)
     BUILD_BPF_SKEL := 0
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 058c9aecf608..f8774a9b1377 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -134,6 +134,8 @@ include ../scripts/utilities.mak
 #	x86 instruction decoder - new instructions test
 #
 # Define GEN_VMLINUX_H to generate vmlinux.h from the BTF.
+#
+# Define NO_SHELLCHECK if you do not want to run shellcheck during build
 
 # As per kernel Makefile, avoid funny character set dependencies
 unexport LC_ALL
@@ -227,8 +229,25 @@ else
   force_fixdep := $(config)
 endif
 
+# Runs shellcheck on perf test shell scripts
+ifeq ($(NO_SHELLCHECK),1)
+  SHELLCHECK :=
+else
+  SHELLCHECK := $(shell which shellcheck 2> /dev/null)
+endif
+
+# shellcheck is using in tools/perf/tests/Build with option -a/--check-sourced (
+# introduced in v0.4.7) and -S/--severity (introduced in v0.6.0). So make the
+# minimal shellcheck version as v0.6.0.
+ifneq ($(SHELLCHECK),)
+  ifeq ($(shell expr $(shell $(SHELLCHECK) --version | grep version: | \
+        sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \< 060), 1)
+    SHELLCHECK :=
+  endif
+endif
+
 export srctree OUTPUT RM CC CXX LD AR CFLAGS CXXFLAGS V BISON FLEX AWK
-export HOSTCC HOSTLD HOSTAR HOSTCFLAGS
+export HOSTCC HOSTLD HOSTAR HOSTCFLAGS SHELLCHECK
 
 include $(srctree)/tools/build/Makefile.include
 
@@ -1152,7 +1171,7 @@ bpf-skel-clean:
 
 clean:: $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBSYMBOL)-clean $(LIBPERF)-clean arm64-sysreg-defs-clean fixdep-clean python-clean bpf-skel-clean tests-coresight-targets-clean
 	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIBPERF_A) $(OUTPUT)perf-archive $(OUTPUT)perf-iostat $(LANG_BINDINGS)
-	$(Q)find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
+	$(Q)find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete -o -name '*.shellcheck_log' -delete
 	$(Q)$(RM) $(OUTPUT).config-detected
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(OUTPUT)$(LIBJVMTI).so
 	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 2cf873d71dff..77e6663c1703 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -199,7 +199,7 @@ static int cs_etm_validate_config(struct auxtrace_record *itr,
 {
 	int i, err = -EINVAL;
 	struct perf_cpu_map *event_cpus = evsel->evlist->core.user_requested_cpus;
-	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
+	struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus();
 
 	/* Set option of each CPU we have */
 	for (i = 0; i < cpu__max_cpu().cpu; i++) {
@@ -211,7 +211,7 @@ static int cs_etm_validate_config(struct auxtrace_record *itr,
 		 * program can run on any CPUs in this case, thus don't skip
 		 * validation.
 		 */
-		if (!perf_cpu_map__empty(event_cpus) &&
+		if (!perf_cpu_map__has_any_cpu_or_is_empty(event_cpus) &&
 		    !perf_cpu_map__has(event_cpus, cpu))
 			continue;
 
@@ -435,7 +435,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 	 * Also the case of per-cpu mmaps, need the contextID in order to be notified
 	 * when a context switch happened.
 	 */
-	if (!perf_cpu_map__empty(cpus)) {
+	if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
 		evsel__set_config_if_unset(cs_etm_pmu, cs_etm_evsel,
 					   "timestamp", 1);
 		evsel__set_config_if_unset(cs_etm_pmu, cs_etm_evsel,
@@ -461,7 +461,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 	evsel->core.attr.sample_period = 1;
 
 	/* In per-cpu case, always need the time of mmap events etc */
-	if (!perf_cpu_map__empty(cpus))
+	if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus))
 		evsel__set_sample_bit(evsel, TIME);
 
 	err = cs_etm_validate_config(itr, cs_etm_evsel);
@@ -536,10 +536,10 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 	int i;
 	int etmv3 = 0, etmv4 = 0, ete = 0;
 	struct perf_cpu_map *event_cpus = evlist->core.user_requested_cpus;
-	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
+	struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus();
 
 	/* cpu map is not empty, we have specific CPUs to work with */
-	if (!perf_cpu_map__empty(event_cpus)) {
+	if (!perf_cpu_map__has_any_cpu_or_is_empty(event_cpus)) {
 		for (i = 0; i < cpu__max_cpu().cpu; i++) {
 			struct perf_cpu cpu = { .cpu = i, };
 
@@ -802,7 +802,7 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 	u64 nr_cpu, type;
 	struct perf_cpu_map *cpu_map;
 	struct perf_cpu_map *event_cpus = session->evlist->core.user_requested_cpus;
-	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
+	struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus();
 	struct cs_etm_recording *ptr =
 			container_of(itr, struct cs_etm_recording, itr);
 	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
@@ -814,7 +814,7 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 		return -EINVAL;
 
 	/* If the cpu_map is empty all online CPUs are involved */
-	if (perf_cpu_map__empty(event_cpus)) {
+	if (perf_cpu_map__has_any_cpu_or_is_empty(event_cpus)) {
 		cpu_map = online_cpus;
 	} else {
 		/* Make sure all specified CPUs are online */
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index e3acc739bd00..51ccbfd3d246 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -232,7 +232,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	 * In the case of per-cpu mmaps, sample CPU for AUX event;
 	 * also enable the timestamp tracing for samples correlation.
 	 */
-	if (!perf_cpu_map__empty(cpus)) {
+	if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
 		evsel__set_sample_bit(arm_spe_evsel, CPU);
 		evsel__set_config_if_unset(arm_spe_pmu, arm_spe_evsel,
 					   "ts_enable", 1);
@@ -265,7 +265,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	tracking_evsel->core.attr.sample_period = 1;
 
 	/* In per-cpu case, always need the time of mmap events etc */
-	if (!perf_cpu_map__empty(cpus)) {
+	if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
 		evsel__set_sample_bit(tracking_evsel, TIME);
 		evsel__set_sample_bit(tracking_evsel, CPU);
 
diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c
index a2eef9ec5491..97037499152e 100644
--- a/tools/perf/arch/arm64/util/header.c
+++ b/tools/perf/arch/arm64/util/header.c
@@ -57,7 +57,7 @@ static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus)
 
 int get_cpuid(char *buf, size_t sz)
 {
-	struct perf_cpu_map *cpus = perf_cpu_map__new(NULL);
+	struct perf_cpu_map *cpus = perf_cpu_map__new_online_cpus();
 	int ret;
 
 	if (!cpus)
diff --git a/tools/perf/arch/loongarch/annotate/instructions.c b/tools/perf/arch/loongarch/annotate/instructions.c
index 98e19c5366ac..21cc7e4149f7 100644
--- a/tools/perf/arch/loongarch/annotate/instructions.c
+++ b/tools/perf/arch/loongarch/annotate/instructions.c
@@ -61,10 +61,10 @@ static int loongarch_jump__parse(struct arch *arch, struct ins_operands *ops, st
 	const char *c = strchr(ops->raw, '#');
 	u64 start, end;
 
-	ops->raw_comment = strchr(ops->raw, arch->objdump.comment_char);
-	ops->raw_func_start = strchr(ops->raw, '<');
+	ops->jump.raw_comment = strchr(ops->raw, arch->objdump.comment_char);
+	ops->jump.raw_func_start = strchr(ops->raw, '<');
 
-	if (ops->raw_func_start && c > ops->raw_func_start)
+	if (ops->jump.raw_func_start && c > ops->jump.raw_func_start)
 		c = NULL;
 
 	if (c++ != NULL)
diff --git a/tools/perf/arch/x86/tests/hybrid.c b/tools/perf/arch/x86/tests/hybrid.c
index eb152770f148..40f5d17fedab 100644
--- a/tools/perf/arch/x86/tests/hybrid.c
+++ b/tools/perf/arch/x86/tests/hybrid.c
@@ -47,7 +47,7 @@ static int test__hybrid_hw_group_event(struct evlist *evlist)
 	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
-	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_INSTRUCTIONS));
 	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
 	return TEST_OK;
 }
@@ -102,7 +102,7 @@ static int test__hybrid_group_modifier1(struct evlist *evlist)
 	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
-	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_INSTRUCTIONS));
 	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
 	TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
@@ -163,6 +163,24 @@ static int test__checkevent_pmu(struct evlist *evlist)
 	return TEST_OK;
 }
 
+static int test__hybrid_hw_group_event_2(struct evlist *evlist)
+{
+	struct evsel *evsel, *leader;
+
+	evsel = leader = evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+
+	evsel = evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong config", evsel->core.attr.config == 0x3c);
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+	return TEST_OK;
+}
+
 struct evlist_test {
 	const char *name;
 	bool (*valid)(void);
@@ -171,27 +189,27 @@ struct evlist_test {
 
 static const struct evlist_test test__hybrid_events[] = {
 	{
-		.name  = "cpu_core/cpu-cycles/",
+		.name  = "cpu_core/cycles/",
 		.check = test__hybrid_hw_event_with_pmu,
 		/* 0 */
 	},
 	{
-		.name  = "{cpu_core/cpu-cycles/,cpu_core/instructions/}",
+		.name  = "{cpu_core/cycles/,cpu_core/branches/}",
 		.check = test__hybrid_hw_group_event,
 		/* 1 */
 	},
 	{
-		.name  = "{cpu-clock,cpu_core/cpu-cycles/}",
+		.name  = "{cpu-clock,cpu_core/cycles/}",
 		.check = test__hybrid_sw_hw_group_event,
 		/* 2 */
 	},
 	{
-		.name  = "{cpu_core/cpu-cycles/,cpu-clock}",
+		.name  = "{cpu_core/cycles/,cpu-clock}",
 		.check = test__hybrid_hw_sw_group_event,
 		/* 3 */
 	},
 	{
-		.name  = "{cpu_core/cpu-cycles/k,cpu_core/instructions/u}",
+		.name  = "{cpu_core/cycles/k,cpu_core/branches/u}",
 		.check = test__hybrid_group_modifier1,
 		/* 4 */
 	},
@@ -215,6 +233,11 @@ static const struct evlist_test test__hybrid_events[] = {
 		.check = test__hybrid_cache_event,
 		/* 8 */
 	},
+	{
+		.name  = "{cpu_core/cycles/,cpu_core/cpu-cycles/}",
+		.check = test__hybrid_hw_group_event_2,
+		/* 9 */
+	},
 };
 
 static int test_event(const struct evlist_test *e)
diff --git a/tools/perf/arch/x86/util/dwarf-regs.c b/tools/perf/arch/x86/util/dwarf-regs.c
index 530934805710..399c4a0a29d8 100644
--- a/tools/perf/arch/x86/util/dwarf-regs.c
+++ b/tools/perf/arch/x86/util/dwarf-regs.c
@@ -113,3 +113,41 @@ int regs_query_register_offset(const char *name)
 			return roff->offset;
 	return -EINVAL;
 }
+
+struct dwarf_regs_idx {
+	const char *name;
+	int idx;
+};
+
+static const struct dwarf_regs_idx x86_regidx_table[] = {
+	{ "rax", 0 }, { "eax", 0 }, { "ax", 0 }, { "al", 0 },
+	{ "rdx", 1 }, { "edx", 1 }, { "dx", 1 }, { "dl", 1 },
+	{ "rcx", 2 }, { "ecx", 2 }, { "cx", 2 }, { "cl", 2 },
+	{ "rbx", 3 }, { "edx", 3 }, { "bx", 3 }, { "bl", 3 },
+	{ "rsi", 4 }, { "esi", 4 }, { "si", 4 }, { "sil", 4 },
+	{ "rdi", 5 }, { "edi", 5 }, { "di", 5 }, { "dil", 5 },
+	{ "rbp", 6 }, { "ebp", 6 }, { "bp", 6 }, { "bpl", 6 },
+	{ "rsp", 7 }, { "esp", 7 }, { "sp", 7 }, { "spl", 7 },
+	{ "r8", 8 }, { "r8d", 8 }, { "r8w", 8 }, { "r8b", 8 },
+	{ "r9", 9 }, { "r9d", 9 }, { "r9w", 9 }, { "r9b", 9 },
+	{ "r10", 10 }, { "r10d", 10 }, { "r10w", 10 }, { "r10b", 10 },
+	{ "r11", 11 }, { "r11d", 11 }, { "r11w", 11 }, { "r11b", 11 },
+	{ "r12", 12 }, { "r12d", 12 }, { "r12w", 12 }, { "r12b", 12 },
+	{ "r13", 13 }, { "r13d", 13 }, { "r13w", 13 }, { "r13b", 13 },
+	{ "r14", 14 }, { "r14d", 14 }, { "r14w", 14 }, { "r14b", 14 },
+	{ "r15", 15 }, { "r15d", 15 }, { "r15w", 15 }, { "r15b", 15 },
+	{ "rip", DWARF_REG_PC },
+};
+
+int get_arch_regnum(const char *name)
+{
+	unsigned int i;
+
+	if (*name != '%')
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(x86_regidx_table); i++)
+		if (!strcmp(x86_regidx_table[i].name, name + 1))
+			return x86_regidx_table[i].idx;
+	return -ENOENT;
+}
diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c
index 5741ffe47312..e65b7dbe27fb 100644
--- a/tools/perf/arch/x86/util/event.c
+++ b/tools/perf/arch/x86/util/event.c
@@ -14,66 +14,79 @@
 
 #if defined(__x86_64__)
 
-int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
-				       perf_event__handler_t process,
-				       struct machine *machine)
+struct perf_event__synthesize_extra_kmaps_cb_args {
+	struct perf_tool *tool;
+	perf_event__handler_t process;
+	struct machine *machine;
+	union perf_event *event;
+};
+
+static int perf_event__synthesize_extra_kmaps_cb(struct map *map, void *data)
 {
-	int rc = 0;
-	struct map_rb_node *pos;
-	struct maps *kmaps = machine__kernel_maps(machine);
-	union perf_event *event = zalloc(sizeof(event->mmap) +
-					 machine->id_hdr_size);
+	struct perf_event__synthesize_extra_kmaps_cb_args *args = data;
+	union perf_event *event = args->event;
+	struct kmap *kmap;
+	size_t size;
 
-	if (!event) {
-		pr_debug("Not enough memory synthesizing mmap event "
-			 "for extra kernel maps\n");
-		return -1;
-	}
+	if (!__map__is_extra_kernel_map(map))
+		return 0;
 
-	maps__for_each_entry(kmaps, pos) {
-		struct kmap *kmap;
-		size_t size;
-		struct map *map = pos->map;
+	kmap = map__kmap(map);
 
-		if (!__map__is_extra_kernel_map(map))
-			continue;
+	size = sizeof(event->mmap) - sizeof(event->mmap.filename) +
+		      PERF_ALIGN(strlen(kmap->name) + 1, sizeof(u64)) +
+		      args->machine->id_hdr_size;
 
-		kmap = map__kmap(map);
+	memset(event, 0, size);
 
-		size = sizeof(event->mmap) - sizeof(event->mmap.filename) +
-		       PERF_ALIGN(strlen(kmap->name) + 1, sizeof(u64)) +
-		       machine->id_hdr_size;
+	event->mmap.header.type = PERF_RECORD_MMAP;
 
-		memset(event, 0, size);
+	/*
+	 * kernel uses 0 for user space maps, see kernel/perf_event.c
+	 * __perf_event_mmap
+	 */
+	if (machine__is_host(args->machine))
+		event->header.misc = PERF_RECORD_MISC_KERNEL;
+	else
+		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
 
-		event->mmap.header.type = PERF_RECORD_MMAP;
+	event->mmap.header.size = size;
 
-		/*
-		 * kernel uses 0 for user space maps, see kernel/perf_event.c
-		 * __perf_event_mmap
-		 */
-		if (machine__is_host(machine))
-			event->header.misc = PERF_RECORD_MISC_KERNEL;
-		else
-			event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
+	event->mmap.start = map__start(map);
+	event->mmap.len   = map__size(map);
+	event->mmap.pgoff = map__pgoff(map);
+	event->mmap.pid   = args->machine->pid;
 
-		event->mmap.header.size = size;
+	strlcpy(event->mmap.filename, kmap->name, PATH_MAX);
 
-		event->mmap.start = map__start(map);
-		event->mmap.len   = map__size(map);
-		event->mmap.pgoff = map__pgoff(map);
-		event->mmap.pid   = machine->pid;
+	if (perf_tool__process_synth_event(args->tool, event, args->machine, args->process) != 0)
+		return -1;
 
-		strlcpy(event->mmap.filename, kmap->name, PATH_MAX);
+	return 0;
+}
 
-		if (perf_tool__process_synth_event(tool, event, machine,
-						   process) != 0) {
-			rc = -1;
-			break;
-		}
+int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
+				       perf_event__handler_t process,
+				       struct machine *machine)
+{
+	int rc;
+	struct maps *kmaps = machine__kernel_maps(machine);
+	struct perf_event__synthesize_extra_kmaps_cb_args args = {
+		.tool = tool,
+		.process = process,
+		.machine = machine,
+		.event = zalloc(sizeof(args.event->mmap) + machine->id_hdr_size),
+	};
+
+	if (!args.event) {
+		pr_debug("Not enough memory synthesizing mmap event "
+			 "for extra kernel maps\n");
+		return -1;
 	}
 
-	free(event);
+	rc = maps__for_each_map(kmaps, perf_event__synthesize_extra_kmaps_cb, &args);
+
+	free(args.event);
 	return rc;
 }
 
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index d2c8cac11470..af8ae4647585 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -143,7 +143,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
 	if (!opts->full_auxtrace)
 		return 0;
 
-	if (opts->full_auxtrace && !perf_cpu_map__empty(cpus)) {
+	if (opts->full_auxtrace && !perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
 		pr_err(INTEL_BTS_PMU_NAME " does not support per-cpu recording\n");
 		return -EINVAL;
 	}
@@ -224,7 +224,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
 		 * In the case of per-cpu mmaps, we need the CPU on the
 		 * AUX event.
 		 */
-		if (!perf_cpu_map__empty(cpus))
+		if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus))
 			evsel__set_sample_bit(intel_bts_evsel, CPU);
 	}
 
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index fa0c718b9e72..d199619df3ab 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -369,7 +369,7 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
 			ui__warning("Intel Processor Trace: TSC not available\n");
 	}
 
-	per_cpu_mmaps = !perf_cpu_map__empty(session->evlist->core.user_requested_cpus);
+	per_cpu_mmaps = !perf_cpu_map__has_any_cpu_or_is_empty(session->evlist->core.user_requested_cpus);
 
 	auxtrace_info->type = PERF_AUXTRACE_INTEL_PT;
 	auxtrace_info->priv[INTEL_PT_PMU_TYPE] = intel_pt_pmu->type;
@@ -774,7 +774,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 	 * Per-cpu recording needs sched_switch events to distinguish different
 	 * threads.
 	 */
-	if (have_timing_info && !perf_cpu_map__empty(cpus) &&
+	if (have_timing_info && !perf_cpu_map__has_any_cpu_or_is_empty(cpus) &&
 	    !record_opts__no_switch_events(opts)) {
 		if (perf_can_record_switch_events()) {
 			bool cpu_wide = !target__none(&opts->target) &&
@@ -832,7 +832,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 		 * In the case of per-cpu mmaps, we need the CPU on the
 		 * AUX event.
 		 */
-		if (!perf_cpu_map__empty(cpus))
+		if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus))
 			evsel__set_sample_bit(intel_pt_evsel, CPU);
 	}
 
@@ -858,7 +858,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 			tracking_evsel->immediate = true;
 
 		/* In per-cpu case, always need the time of mmap events etc */
-		if (!perf_cpu_map__empty(cpus)) {
+		if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
 			evsel__set_sample_bit(tracking_evsel, TIME);
 			/* And the CPU for switch events */
 			evsel__set_sample_bit(tracking_evsel, CPU);
@@ -870,7 +870,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 	 * Warn the user when we do not have enough information to decode i.e.
 	 * per-cpu with no sched_switch (except workload-only).
 	 */
-	if (!ptr->have_sched_switch && !perf_cpu_map__empty(cpus) &&
+	if (!ptr->have_sched_switch && !perf_cpu_map__has_any_cpu_or_is_empty(cpus) &&
 	    !target__none(&opts->target) &&
 	    !intel_pt_evsel->core.attr.exclude_user)
 		ui__warning("Intel Processor Trace decoding will not be possible except for kernel tracing!\n");
diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c
index 6bfffe83dde9..d3db73dac66a 100644
--- a/tools/perf/bench/epoll-ctl.c
+++ b/tools/perf/bench/epoll-ctl.c
@@ -330,7 +330,7 @@ int bench_epoll_ctl(int argc, const char **argv)
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
 
-	cpu = perf_cpu_map__new(NULL);
+	cpu = perf_cpu_map__new_online_cpus();
 	if (!cpu)
 		goto errmem;
 
diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c
index cb5174b53940..06bb3187660a 100644
--- a/tools/perf/bench/epoll-wait.c
+++ b/tools/perf/bench/epoll-wait.c
@@ -444,7 +444,7 @@ int bench_epoll_wait(int argc, const char **argv)
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
 
-	cpu = perf_cpu_map__new(NULL);
+	cpu = perf_cpu_map__new_online_cpus();
 	if (!cpu)
 		goto errmem;
 
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 2005a3fa3026..0c69d20efa32 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -138,7 +138,7 @@ int bench_futex_hash(int argc, const char **argv)
 		exit(EXIT_FAILURE);
 	}
 
-	cpu = perf_cpu_map__new(NULL);
+	cpu = perf_cpu_map__new_online_cpus();
 	if (!cpu)
 		goto errmem;
 
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 092cbd52db82..7a4973346180 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -172,7 +172,7 @@ int bench_futex_lock_pi(int argc, const char **argv)
 	if (argc)
 		goto err;
 
-	cpu = perf_cpu_map__new(NULL);
+	cpu = perf_cpu_map__new_online_cpus();
 	if (!cpu)
 		err(EXIT_FAILURE, "calloc");
 
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index c0035990a33c..d9ad736c1a3e 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -174,7 +174,7 @@ int bench_futex_requeue(int argc, const char **argv)
 	if (argc)
 		goto err;
 
-	cpu = perf_cpu_map__new(NULL);
+	cpu = perf_cpu_map__new_online_cpus();
 	if (!cpu)
 		err(EXIT_FAILURE, "cpu_map__new");
 
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 5ab0234d74e6..b66df553e561 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -264,7 +264,7 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 			err(EXIT_FAILURE, "mlockall");
 	}
 
-	cpu = perf_cpu_map__new(NULL);
+	cpu = perf_cpu_map__new_online_cpus();
 	if (!cpu)
 		err(EXIT_FAILURE, "calloc");
 
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 18a5894af8bb..690fd6d3da13 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -149,7 +149,7 @@ int bench_futex_wake(int argc, const char **argv)
 		exit(EXIT_FAILURE);
 	}
 
-	cpu = perf_cpu_map__new(NULL);
+	cpu = perf_cpu_map__new_online_cpus();
 	if (!cpu)
 		err(EXIT_FAILURE, "calloc");
 
diff --git a/tools/perf/bench/sched-seccomp-notify.c b/tools/perf/bench/sched-seccomp-notify.c
index a01c40131493..269c1f4a6852 100644
--- a/tools/perf/bench/sched-seccomp-notify.c
+++ b/tools/perf/bench/sched-seccomp-notify.c
@@ -32,7 +32,7 @@ static bool sync_mode;
 static const struct option options[] = {
 	OPT_U64('l', "loop",	&loops,		"Specify number of loops"),
 	OPT_BOOLEAN('s', "sync-mode", &sync_mode,
-		    "Enable the synchronious mode for seccomp notifications"),
+		    "Enable the synchronous mode for seccomp notifications"),
 	OPT_END()
 };
 
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index aeeb801f1ed7..6c1cc797692d 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -20,6 +20,7 @@
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/annotate.h"
+#include "util/annotate-data.h"
 #include "util/event.h"
 #include <subcmd/parse-options.h>
 #include "util/parse-events.h"
@@ -45,7 +46,6 @@
 struct perf_annotate {
 	struct perf_tool tool;
 	struct perf_session *session;
-	struct annotation_options opts;
 #ifdef HAVE_SLANG_SUPPORT
 	bool	   use_tui;
 #endif
@@ -56,9 +56,13 @@ struct perf_annotate {
 	bool	   skip_missing;
 	bool	   has_br_stack;
 	bool	   group_set;
+	bool	   data_type;
+	bool	   type_stat;
+	bool	   insn_stat;
 	float	   min_percent;
 	const char *sym_hist_filter;
 	const char *cpu_list;
+	const char *target_data_type;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
@@ -94,6 +98,7 @@ static void process_basic_block(struct addr_map_symbol *start,
 	struct annotation *notes = sym ? symbol__annotation(sym) : NULL;
 	struct block_range_iter iter;
 	struct block_range *entry;
+	struct annotated_branch *branch;
 
 	/*
 	 * Sanity; NULL isn't executable and the CPU cannot execute backwards
@@ -105,6 +110,8 @@ static void process_basic_block(struct addr_map_symbol *start,
 	if (!block_range_iter__valid(&iter))
 		return;
 
+	branch = annotation__get_branch(notes);
+
 	/*
 	 * First block in range is a branch target.
 	 */
@@ -118,8 +125,8 @@ static void process_basic_block(struct addr_map_symbol *start,
 		entry->coverage++;
 		entry->sym = sym;
 
-		if (notes)
-			notes->max_coverage = max(notes->max_coverage, entry->coverage);
+		if (branch)
+			branch->max_coverage = max(branch->max_coverage, entry->coverage);
 
 	} while (block_range_iter__next(&iter));
 
@@ -315,9 +322,153 @@ static int hist_entry__tty_annotate(struct hist_entry *he,
 				    struct perf_annotate *ann)
 {
 	if (!ann->use_stdio2)
-		return symbol__tty_annotate(&he->ms, evsel, &ann->opts);
+		return symbol__tty_annotate(&he->ms, evsel);
+
+	return symbol__tty_annotate2(&he->ms, evsel);
+}
+
+static void print_annotated_data_header(struct hist_entry *he, struct evsel *evsel)
+{
+	struct dso *dso = map__dso(he->ms.map);
+	int nr_members = 1;
+	int nr_samples = he->stat.nr_events;
+
+	if (evsel__is_group_event(evsel)) {
+		struct hist_entry *pair;
+
+		list_for_each_entry(pair, &he->pairs.head, pairs.node)
+			nr_samples += pair->stat.nr_events;
+	}
+
+	printf("Annotate type: '%s' in %s (%d samples):\n",
+	       he->mem_type->self.type_name, dso->name, nr_samples);
+
+	if (evsel__is_group_event(evsel)) {
+		struct evsel *pos;
+		int i = 0;
+
+		for_each_group_evsel(pos, evsel)
+			printf(" event[%d] = %s\n", i++, pos->name);
+
+		nr_members = evsel->core.nr_members;
+	}
+
+	printf("============================================================================\n");
+	printf("%*s %10s %10s  %s\n", 11 * nr_members, "samples", "offset", "size", "field");
+}
+
+static void print_annotated_data_type(struct annotated_data_type *mem_type,
+				      struct annotated_member *member,
+				      struct evsel *evsel, int indent)
+{
+	struct annotated_member *child;
+	struct type_hist *h = mem_type->histograms[evsel->core.idx];
+	int i, nr_events = 1, samples = 0;
+
+	for (i = 0; i < member->size; i++)
+		samples += h->addr[member->offset + i].nr_samples;
+	printf(" %10d", samples);
 
-	return symbol__tty_annotate2(&he->ms, evsel, &ann->opts);
+	if (evsel__is_group_event(evsel)) {
+		struct evsel *pos;
+
+		for_each_group_member(pos, evsel) {
+			h = mem_type->histograms[pos->core.idx];
+
+			samples = 0;
+			for (i = 0; i < member->size; i++)
+				samples += h->addr[member->offset + i].nr_samples;
+			printf(" %10d", samples);
+		}
+		nr_events = evsel->core.nr_members;
+	}
+
+	printf(" %10d %10d  %*s%s\t%s",
+	       member->offset, member->size, indent, "", member->type_name,
+	       member->var_name ?: "");
+
+	if (!list_empty(&member->children))
+		printf(" {\n");
+
+	list_for_each_entry(child, &member->children, node)
+		print_annotated_data_type(mem_type, child, evsel, indent + 4);
+
+	if (!list_empty(&member->children))
+		printf("%*s}", 11 * nr_events + 24 + indent, "");
+	printf(";\n");
+}
+
+static void print_annotate_data_stat(struct annotated_data_stat *s)
+{
+#define PRINT_STAT(fld) if (s->fld) printf("%10d : %s\n", s->fld, #fld)
+
+	int bad = s->no_sym +
+			s->no_insn +
+			s->no_insn_ops +
+			s->no_mem_ops +
+			s->no_reg +
+			s->no_dbginfo +
+			s->no_cuinfo +
+			s->no_var +
+			s->no_typeinfo +
+			s->invalid_size +
+			s->bad_offset;
+	int ok = s->total - bad;
+
+	printf("Annotate data type stats:\n");
+	printf("total %d, ok %d (%.1f%%), bad %d (%.1f%%)\n",
+		s->total, ok, 100.0 * ok / (s->total ?: 1), bad, 100.0 * bad / (s->total ?: 1));
+	printf("-----------------------------------------------------------\n");
+	PRINT_STAT(no_sym);
+	PRINT_STAT(no_insn);
+	PRINT_STAT(no_insn_ops);
+	PRINT_STAT(no_mem_ops);
+	PRINT_STAT(no_reg);
+	PRINT_STAT(no_dbginfo);
+	PRINT_STAT(no_cuinfo);
+	PRINT_STAT(no_var);
+	PRINT_STAT(no_typeinfo);
+	PRINT_STAT(invalid_size);
+	PRINT_STAT(bad_offset);
+	printf("\n");
+
+#undef PRINT_STAT
+}
+
+static void print_annotate_item_stat(struct list_head *head, const char *title)
+{
+	struct annotated_item_stat *istat, *pos, *iter;
+	int total_good, total_bad, total;
+	int sum1, sum2;
+	LIST_HEAD(tmp);
+
+	/* sort the list by count */
+	list_splice_init(head, &tmp);
+	total_good = total_bad = 0;
+
+	list_for_each_entry_safe(istat, pos, &tmp, list) {
+		total_good += istat->good;
+		total_bad += istat->bad;
+		sum1 = istat->good + istat->bad;
+
+		list_for_each_entry(iter, head, list) {
+			sum2 = iter->good + iter->bad;
+			if (sum1 > sum2)
+				break;
+		}
+		list_move_tail(&istat->list, &iter->list);
+	}
+	total = total_good + total_bad;
+
+	printf("Annotate %s stats\n", title);
+	printf("total %d, ok %d (%.1f%%), bad %d (%.1f%%)\n\n", total,
+	       total_good, 100.0 * total_good / (total ?: 1),
+	       total_bad, 100.0 * total_bad / (total ?: 1));
+	printf("  %-10s: %5s %5s\n", "Name", "Good", "Bad");
+	printf("-----------------------------------------------------------\n");
+	list_for_each_entry(istat, head, list)
+		printf("  %-10s: %5d %5d\n", istat->name, istat->good, istat->bad);
+	printf("\n");
 }
 
 static void hists__find_annotations(struct hists *hists,
@@ -327,6 +478,11 @@ static void hists__find_annotations(struct hists *hists,
 	struct rb_node *nd = rb_first_cached(&hists->entries), *next;
 	int key = K_RIGHT;
 
+	if (ann->type_stat)
+		print_annotate_data_stat(&ann_data_stat);
+	if (ann->insn_stat)
+		print_annotate_item_stat(&ann_insn_stat, "Instruction");
+
 	while (nd) {
 		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
 		struct annotation *notes;
@@ -359,11 +515,38 @@ find_next:
 			continue;
 		}
 
+		if (ann->data_type) {
+			/* skip unknown type */
+			if (he->mem_type->histograms == NULL)
+				goto find_next;
+
+			if (ann->target_data_type) {
+				const char *type_name = he->mem_type->self.type_name;
+
+				/* skip 'struct ' prefix in the type name */
+				if (strncmp(ann->target_data_type, "struct ", 7) &&
+				    !strncmp(type_name, "struct ", 7))
+					type_name += 7;
+
+				/* skip 'union ' prefix in the type name */
+				if (strncmp(ann->target_data_type, "union ", 6) &&
+				    !strncmp(type_name, "union ", 6))
+					type_name += 6;
+
+				if (strcmp(ann->target_data_type, type_name))
+					goto find_next;
+			}
+
+			print_annotated_data_header(he, evsel);
+			print_annotated_data_type(he->mem_type, &he->mem_type->self, evsel, 0);
+			printf("\n");
+			goto find_next;
+		}
+
 		if (use_browser == 2) {
 			int ret;
 			int (*annotate)(struct hist_entry *he,
 					struct evsel *evsel,
-					struct annotation_options *options,
 					struct hist_browser_timer *hbt);
 
 			annotate = dlsym(perf_gtk_handle,
@@ -373,14 +556,14 @@ find_next:
 				return;
 			}
 
-			ret = annotate(he, evsel, &ann->opts, NULL);
+			ret = annotate(he, evsel, NULL);
 			if (!ret || !ann->skip_missing)
 				return;
 
 			/* skip missing symbols */
 			nd = rb_next(nd);
 		} else if (use_browser == 1) {
-			key = hist_entry__tui_annotate(he, evsel, NULL, &ann->opts);
+			key = hist_entry__tui_annotate(he, evsel, NULL);
 
 			switch (key) {
 			case -1:
@@ -422,9 +605,9 @@ static int __cmd_annotate(struct perf_annotate *ann)
 			goto out;
 	}
 
-	if (!ann->opts.objdump_path) {
+	if (!annotate_opts.objdump_path) {
 		ret = perf_env__lookup_objdump(&session->header.env,
-					       &ann->opts.objdump_path);
+					       &annotate_opts.objdump_path);
 		if (ret)
 			goto out;
 	}
@@ -457,8 +640,20 @@ static int __cmd_annotate(struct perf_annotate *ann)
 			evsel__reset_sample_bit(pos, CALLCHAIN);
 			evsel__output_resort(pos, NULL);
 
-			if (symbol_conf.event_group && !evsel__is_group_leader(pos))
+			/*
+			 * An event group needs to display other events too.
+			 * Let's delay printing until other events are processed.
+			 */
+			if (symbol_conf.event_group) {
+				if (!evsel__is_group_leader(pos)) {
+					struct hists *leader_hists;
+
+					leader_hists = evsel__hists(evsel__leader(pos));
+					hists__match(leader_hists, hists);
+					hists__link(leader_hists, hists);
+				}
 				continue;
+			}
 
 			hists__find_annotations(hists, pos, ann);
 		}
@@ -469,6 +664,20 @@ static int __cmd_annotate(struct perf_annotate *ann)
 		goto out;
 	}
 
+	/* Display group events together */
+	evlist__for_each_entry(session->evlist, pos) {
+		struct hists *hists = evsel__hists(pos);
+		u32 nr_samples = hists->stats.nr_samples;
+
+		if (nr_samples == 0)
+			continue;
+
+		if (!symbol_conf.event_group || !evsel__is_group_leader(pos))
+			continue;
+
+		hists__find_annotations(hists, pos, ann);
+	}
+
 	if (use_browser == 2) {
 		void (*show_annotations)(void);
 
@@ -495,6 +704,17 @@ static int parse_percent_limit(const struct option *opt, const char *str,
 	return 0;
 }
 
+static int parse_data_type(const struct option *opt, const char *str, int unset)
+{
+	struct perf_annotate *ann = opt->value;
+
+	ann->data_type = !unset;
+	if (str)
+		ann->target_data_type = strdup(str);
+
+	return 0;
+}
+
 static const char * const annotate_usage[] = {
 	"perf annotate [<options>]",
 	NULL
@@ -558,9 +778,9 @@ int cmd_annotate(int argc, const char **argv)
 		   "file", "vmlinux pathname"),
 	OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
 		    "load module symbols - WARNING: use only with -k and LIVE kernel"),
-	OPT_BOOLEAN('l', "print-line", &annotate.opts.print_lines,
+	OPT_BOOLEAN('l', "print-line", &annotate_opts.print_lines,
 		    "print matching source lines (may be slow)"),
-	OPT_BOOLEAN('P', "full-paths", &annotate.opts.full_path,
+	OPT_BOOLEAN('P', "full-paths", &annotate_opts.full_path,
 		    "Don't shorten the displayed pathnames"),
 	OPT_BOOLEAN(0, "skip-missing", &annotate.skip_missing,
 		    "Skip symbols that cannot be annotated"),
@@ -571,15 +791,15 @@ int cmd_annotate(int argc, const char **argv)
 	OPT_CALLBACK(0, "symfs", NULL, "directory",
 		     "Look for files with symbols relative to this directory",
 		     symbol__config_symfs),
-	OPT_BOOLEAN(0, "source", &annotate.opts.annotate_src,
+	OPT_BOOLEAN(0, "source", &annotate_opts.annotate_src,
 		    "Interleave source code with assembly code (default)"),
-	OPT_BOOLEAN(0, "asm-raw", &annotate.opts.show_asm_raw,
+	OPT_BOOLEAN(0, "asm-raw", &annotate_opts.show_asm_raw,
 		    "Display raw encoding of assembly instructions (default)"),
 	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
-	OPT_STRING(0, "prefix", &annotate.opts.prefix, "prefix",
+	OPT_STRING(0, "prefix", &annotate_opts.prefix, "prefix",
 		    "Add prefix to source file path names in programs (with --prefix-strip)"),
-	OPT_STRING(0, "prefix-strip", &annotate.opts.prefix_strip, "N",
+	OPT_STRING(0, "prefix-strip", &annotate_opts.prefix_strip, "N",
 		    "Strip first N entries of source file path name in programs (with --prefix)"),
 	OPT_STRING(0, "objdump", &objdump_path, "path",
 		   "objdump binary to use for disassembly and annotations"),
@@ -598,7 +818,7 @@ int cmd_annotate(int argc, const char **argv)
 	OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode",
 			     "'always' (default), 'never' or 'auto' only applicable to --stdio mode",
 			     stdio__config_color, "always"),
-	OPT_CALLBACK(0, "percent-type", &annotate.opts, "local-period",
+	OPT_CALLBACK(0, "percent-type", &annotate_opts, "local-period",
 		     "Set percent type local/global-period/hits",
 		     annotate_parse_percent_type),
 	OPT_CALLBACK(0, "percent-limit", &annotate, "percent",
@@ -606,7 +826,13 @@ int cmd_annotate(int argc, const char **argv)
 	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
 			    "Instruction Tracing options\n" ITRACE_HELP,
 			    itrace_parse_synth_opts),
-
+	OPT_CALLBACK_OPTARG(0, "data-type", &annotate, NULL, "name",
+			    "Show data type annotate for the memory accesses",
+			    parse_data_type),
+	OPT_BOOLEAN(0, "type-stat", &annotate.type_stat,
+		    "Show stats for the data type annotation"),
+	OPT_BOOLEAN(0, "insn-stat", &annotate.insn_stat,
+		    "Show instruction stats for the data type annotation"),
 	OPT_END()
 	};
 	int ret;
@@ -614,13 +840,13 @@ int cmd_annotate(int argc, const char **argv)
 	set_option_flag(options, 0, "show-total-period", PARSE_OPT_EXCLUSIVE);
 	set_option_flag(options, 0, "show-nr-samples", PARSE_OPT_EXCLUSIVE);
 
-	annotation_options__init(&annotate.opts);
+	annotation_options__init();
 
 	ret = hists__init();
 	if (ret < 0)
 		return ret;
 
-	annotation_config__init(&annotate.opts);
+	annotation_config__init();
 
 	argc = parse_options(argc, argv, options, annotate_usage, 0);
 	if (argc) {
@@ -635,13 +861,13 @@ int cmd_annotate(int argc, const char **argv)
 	}
 
 	if (disassembler_style) {
-		annotate.opts.disassembler_style = strdup(disassembler_style);
-		if (!annotate.opts.disassembler_style)
+		annotate_opts.disassembler_style = strdup(disassembler_style);
+		if (!annotate_opts.disassembler_style)
 			return -ENOMEM;
 	}
 	if (objdump_path) {
-		annotate.opts.objdump_path = strdup(objdump_path);
-		if (!annotate.opts.objdump_path)
+		annotate_opts.objdump_path = strdup(objdump_path);
+		if (!annotate_opts.objdump_path)
 			return -ENOMEM;
 	}
 	if (addr2line_path) {
@@ -650,7 +876,7 @@ int cmd_annotate(int argc, const char **argv)
 			return -ENOMEM;
 	}
 
-	if (annotate_check_args(&annotate.opts) < 0)
+	if (annotate_check_args() < 0)
 		return -EINVAL;
 
 #ifdef HAVE_GTK2_SUPPORT
@@ -660,6 +886,13 @@ int cmd_annotate(int argc, const char **argv)
 	}
 #endif
 
+#ifndef HAVE_DWARF_GETLOCATIONS_SUPPORT
+	if (annotate.data_type) {
+		pr_err("Error: Data type profiling is disabled due to missing DWARF support\n");
+		return -ENOTSUP;
+	}
+#endif
+
 	ret = symbol__validate_sym_arguments();
 	if (ret)
 		return ret;
@@ -702,6 +935,14 @@ int cmd_annotate(int argc, const char **argv)
 		use_browser = 2;
 #endif
 
+	/* FIXME: only support stdio for now */
+	if (annotate.data_type) {
+		use_browser = 0;
+		annotate_opts.annotate_src = false;
+		symbol_conf.annotate_data_member = true;
+		symbol_conf.annotate_data_sample = true;
+	}
+
 	setup_browser(true);
 
 	/*
@@ -709,7 +950,10 @@ int cmd_annotate(int argc, const char **argv)
 	 * symbol, we do not care about the processes in annotate,
 	 * set sort order to avoid repeated output.
 	 */
-	sort_order = "dso,symbol";
+	if (annotate.data_type)
+		sort_order = "dso,type";
+	else
+		sort_order = "dso,symbol";
 
 	/*
 	 * Set SORT_MODE__BRANCH so that annotate display IPC/Cycle
@@ -731,7 +975,7 @@ out_delete:
 #ifndef NDEBUG
 	perf_session__delete(annotate.session);
 #endif
-	annotation_options__exit(&annotate.opts);
+	annotation_options__exit();
 
 	return ret;
 }
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index a4cf9de7a7b5..f78eea9e2153 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2320,7 +2320,7 @@ static int setup_nodes(struct perf_session *session)
 		nodes[node] = set;
 
 		/* empty node, skip */
-		if (perf_cpu_map__empty(map))
+		if (perf_cpu_map__has_any_cpu_or_is_empty(map))
 			continue;
 
 		perf_cpu_map__for_each_cpu(cpu, idx, map) {
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index ac2e6c75f912..eb30c8eca488 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -333,7 +333,7 @@ static int set_tracing_func_irqinfo(struct perf_ftrace *ftrace)
 
 static int reset_tracing_cpu(void)
 {
-	struct perf_cpu_map *cpumap = perf_cpu_map__new(NULL);
+	struct perf_cpu_map *cpumap = perf_cpu_map__new_online_cpus();
 	int ret;
 
 	ret = set_tracing_cpumask(cpumap);
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index c8cf2fdd9cff..eb3ef5c24b66 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -2265,6 +2265,12 @@ int cmd_inject(int argc, const char **argv)
 		"perf inject [<options>]",
 		NULL
 	};
+
+	if (!inject.itrace_synth_opts.set) {
+		/* Disable eager loading of kernel symbols that adds overhead to perf inject. */
+		symbol_conf.lazy_load_kernel_maps = true;
+	}
+
 #ifndef HAVE_JITDUMP
 	set_option_nobuild(options, 'j', "jit", "NO_LIBELF=1", true);
 #endif
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 61c2c96cc070..e27a1b1288c2 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -30,6 +30,8 @@
  * functions.
  */
 struct print_state {
+	/** @fp: File to write output to. */
+	FILE *fp;
 	/**
 	 * @pmu_glob: Optionally restrict PMU and metric matching to PMU or
 	 * debugfs subsystem name.
@@ -66,13 +68,15 @@ static void default_print_start(void *ps)
 {
 	struct print_state *print_state = ps;
 
-	if (!print_state->name_only && pager_in_use())
-		printf("\nList of pre-defined events (to be used in -e or -M):\n\n");
+	if (!print_state->name_only && pager_in_use()) {
+		fprintf(print_state->fp,
+			"\nList of pre-defined events (to be used in -e or -M):\n\n");
+	}
 }
 
 static void default_print_end(void *print_state __maybe_unused) {}
 
-static void wordwrap(const char *s, int start, int max, int corr)
+static void wordwrap(FILE *fp, const char *s, int start, int max, int corr)
 {
 	int column = start;
 	int n;
@@ -82,10 +86,10 @@ static void wordwrap(const char *s, int start, int max, int corr)
 		int wlen = strcspn(s, " \t\n");
 
 		if ((column + wlen >= max && column > start) || saw_newline) {
-			printf("\n%*s", start, "");
+			fprintf(fp, "\n%*s", start, "");
 			column = start + corr;
 		}
-		n = printf("%s%.*s", column > start ? " " : "", wlen, s);
+		n = fprintf(fp, "%s%.*s", column > start ? " " : "", wlen, s);
 		if (n <= 0)
 			break;
 		saw_newline = s[wlen] == '\n';
@@ -104,6 +108,7 @@ static void default_print_event(void *ps, const char *pmu_name, const char *topi
 {
 	struct print_state *print_state = ps;
 	int pos;
+	FILE *fp = print_state->fp;
 
 	if (deprecated && !print_state->deprecated)
 		return;
@@ -119,30 +124,30 @@ static void default_print_event(void *ps, const char *pmu_name, const char *topi
 
 	if (print_state->name_only) {
 		if (event_alias && strlen(event_alias))
-			printf("%s ", event_alias);
+			fprintf(fp, "%s ", event_alias);
 		else
-			printf("%s ", event_name);
+			fprintf(fp, "%s ", event_name);
 		return;
 	}
 
 	if (strcmp(print_state->last_topic, topic ?: "")) {
 		if (topic)
-			printf("\n%s:\n", topic);
+			fprintf(fp, "\n%s:\n", topic);
 		zfree(&print_state->last_topic);
 		print_state->last_topic = strdup(topic ?: "");
 	}
 
 	if (event_alias && strlen(event_alias))
-		pos = printf("  %s OR %s", event_name, event_alias);
+		pos = fprintf(fp, "  %s OR %s", event_name, event_alias);
 	else
-		pos = printf("  %s", event_name);
+		pos = fprintf(fp, "  %s", event_name);
 
 	if (!topic && event_type_desc) {
 		for (; pos < 53; pos++)
-			putchar(' ');
-		printf("[%s]\n", event_type_desc);
+			fputc(' ', fp);
+		fprintf(fp, "[%s]\n", event_type_desc);
 	} else
-		putchar('\n');
+		fputc('\n', fp);
 
 	if (desc && print_state->desc) {
 		char *desc_with_unit = NULL;
@@ -155,22 +160,22 @@ static void default_print_event(void *ps, const char *pmu_name, const char *topi
 					      ? "%s. Unit: %s" : "%s Unit: %s",
 					    desc, pmu_name);
 		}
-		printf("%*s", 8, "[");
-		wordwrap(desc_len > 0 ? desc_with_unit : desc, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, desc_len > 0 ? desc_with_unit : desc, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 		free(desc_with_unit);
 	}
 	long_desc = long_desc ?: desc;
 	if (long_desc && print_state->long_desc) {
-		printf("%*s", 8, "[");
-		wordwrap(long_desc, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, long_desc, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 	}
 
 	if (print_state->detailed && encoding_desc) {
-		printf("%*s", 8, "");
-		wordwrap(encoding_desc, 8, pager_get_columns(), 0);
-		putchar('\n');
+		fprintf(fp, "%*s", 8, "");
+		wordwrap(fp, encoding_desc, 8, pager_get_columns(), 0);
+		fputc('\n', fp);
 	}
 }
 
@@ -184,6 +189,7 @@ static void default_print_metric(void *ps,
 				const char *unit __maybe_unused)
 {
 	struct print_state *print_state = ps;
+	FILE *fp = print_state->fp;
 
 	if (print_state->event_glob &&
 	    (!print_state->metrics || !name || !strglobmatch(name, print_state->event_glob)) &&
@@ -192,27 +198,27 @@ static void default_print_metric(void *ps,
 
 	if (!print_state->name_only && !print_state->last_metricgroups) {
 		if (print_state->metricgroups) {
-			printf("\nMetric Groups:\n");
+			fprintf(fp, "\nMetric Groups:\n");
 			if (!print_state->metrics)
-				putchar('\n');
+				fputc('\n', fp);
 		} else {
-			printf("\nMetrics:\n\n");
+			fprintf(fp, "\nMetrics:\n\n");
 		}
 	}
 	if (!print_state->last_metricgroups ||
 	    strcmp(print_state->last_metricgroups, group ?: "")) {
 		if (group && print_state->metricgroups) {
 			if (print_state->name_only)
-				printf("%s ", group);
+				fprintf(fp, "%s ", group);
 			else if (print_state->metrics) {
 				const char *gdesc = describe_metricgroup(group);
 
 				if (gdesc)
-					printf("\n%s: [%s]\n", group, gdesc);
+					fprintf(fp, "\n%s: [%s]\n", group, gdesc);
 				else
-					printf("\n%s:\n", group);
+					fprintf(fp, "\n%s:\n", group);
 			} else
-				printf("%s\n", group);
+				fprintf(fp, "%s\n", group);
 		}
 		zfree(&print_state->last_metricgroups);
 		print_state->last_metricgroups = strdup(group ?: "");
@@ -223,53 +229,59 @@ static void default_print_metric(void *ps,
 	if (print_state->name_only) {
 		if (print_state->metrics &&
 		    !strlist__has_entry(print_state->visited_metrics, name)) {
-			printf("%s ", name);
+			fprintf(fp, "%s ", name);
 			strlist__add(print_state->visited_metrics, name);
 		}
 		return;
 	}
-	printf("  %s\n", name);
+	fprintf(fp, "  %s\n", name);
 
 	if (desc && print_state->desc) {
-		printf("%*s", 8, "[");
-		wordwrap(desc, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, desc, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 	}
 	if (long_desc && print_state->long_desc) {
-		printf("%*s", 8, "[");
-		wordwrap(long_desc, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, long_desc, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 	}
 	if (expr && print_state->detailed) {
-		printf("%*s", 8, "[");
-		wordwrap(expr, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, expr, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 	}
 	if (threshold && print_state->detailed) {
-		printf("%*s", 8, "[");
-		wordwrap(threshold, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, threshold, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 	}
 }
 
 struct json_print_state {
+	/** @fp: File to write output to. */
+	FILE *fp;
 	/** Should a separator be printed prior to the next item? */
 	bool need_sep;
 };
 
-static void json_print_start(void *print_state __maybe_unused)
+static void json_print_start(void *ps)
 {
-	printf("[\n");
+	struct json_print_state *print_state = ps;
+	FILE *fp = print_state->fp;
+
+	fprintf(fp, "[\n");
 }
 
 static void json_print_end(void *ps)
 {
 	struct json_print_state *print_state = ps;
+	FILE *fp = print_state->fp;
 
-	printf("%s]\n", print_state->need_sep ? "\n" : "");
+	fprintf(fp, "%s]\n", print_state->need_sep ? "\n" : "");
 }
 
-static void fix_escape_printf(struct strbuf *buf, const char *fmt, ...)
+static void fix_escape_fprintf(FILE *fp, struct strbuf *buf, const char *fmt, ...)
 {
 	va_list args;
 
@@ -318,7 +330,7 @@ static void fix_escape_printf(struct strbuf *buf, const char *fmt, ...)
 		}
 	}
 	va_end(args);
-	fputs(buf->buf, stdout);
+	fputs(buf->buf, fp);
 }
 
 static void json_print_event(void *ps, const char *pmu_name, const char *topic,
@@ -330,60 +342,71 @@ static void json_print_event(void *ps, const char *pmu_name, const char *topic,
 {
 	struct json_print_state *print_state = ps;
 	bool need_sep = false;
+	FILE *fp = print_state->fp;
 	struct strbuf buf;
 
 	strbuf_init(&buf, 0);
-	printf("%s{\n", print_state->need_sep ? ",\n" : "");
+	fprintf(fp, "%s{\n", print_state->need_sep ? ",\n" : "");
 	print_state->need_sep = true;
 	if (pmu_name) {
-		fix_escape_printf(&buf, "\t\"Unit\": \"%S\"", pmu_name);
+		fix_escape_fprintf(fp, &buf, "\t\"Unit\": \"%S\"", pmu_name);
 		need_sep = true;
 	}
 	if (topic) {
-		fix_escape_printf(&buf, "%s\t\"Topic\": \"%S\"", need_sep ? ",\n" : "", topic);
+		fix_escape_fprintf(fp, &buf, "%s\t\"Topic\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   topic);
 		need_sep = true;
 	}
 	if (event_name) {
-		fix_escape_printf(&buf, "%s\t\"EventName\": \"%S\"", need_sep ? ",\n" : "",
-				  event_name);
+		fix_escape_fprintf(fp, &buf, "%s\t\"EventName\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   event_name);
 		need_sep = true;
 	}
 	if (event_alias && strlen(event_alias)) {
-		fix_escape_printf(&buf, "%s\t\"EventAlias\": \"%S\"", need_sep ? ",\n" : "",
-				  event_alias);
+		fix_escape_fprintf(fp, &buf, "%s\t\"EventAlias\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   event_alias);
 		need_sep = true;
 	}
 	if (scale_unit && strlen(scale_unit)) {
-		fix_escape_printf(&buf, "%s\t\"ScaleUnit\": \"%S\"", need_sep ? ",\n" : "",
-				  scale_unit);
+		fix_escape_fprintf(fp, &buf, "%s\t\"ScaleUnit\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   scale_unit);
 		need_sep = true;
 	}
 	if (event_type_desc) {
-		fix_escape_printf(&buf, "%s\t\"EventType\": \"%S\"", need_sep ? ",\n" : "",
-				  event_type_desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"EventType\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   event_type_desc);
 		need_sep = true;
 	}
 	if (deprecated) {
-		fix_escape_printf(&buf, "%s\t\"Deprecated\": \"%S\"", need_sep ? ",\n" : "",
-				  deprecated ? "1" : "0");
+		fix_escape_fprintf(fp, &buf, "%s\t\"Deprecated\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   deprecated ? "1" : "0");
 		need_sep = true;
 	}
 	if (desc) {
-		fix_escape_printf(&buf, "%s\t\"BriefDescription\": \"%S\"", need_sep ? ",\n" : "",
-				  desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"BriefDescription\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   desc);
 		need_sep = true;
 	}
 	if (long_desc) {
-		fix_escape_printf(&buf, "%s\t\"PublicDescription\": \"%S\"", need_sep ? ",\n" : "",
-				  long_desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"PublicDescription\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   long_desc);
 		need_sep = true;
 	}
 	if (encoding_desc) {
-		fix_escape_printf(&buf, "%s\t\"Encoding\": \"%S\"", need_sep ? ",\n" : "",
-				  encoding_desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"Encoding\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   encoding_desc);
 		need_sep = true;
 	}
-	printf("%s}", need_sep ? "\n" : "");
+	fprintf(fp, "%s}", need_sep ? "\n" : "");
 	strbuf_release(&buf);
 }
 
@@ -394,43 +417,53 @@ static void json_print_metric(void *ps __maybe_unused, const char *group,
 {
 	struct json_print_state *print_state = ps;
 	bool need_sep = false;
+	FILE *fp = print_state->fp;
 	struct strbuf buf;
 
 	strbuf_init(&buf, 0);
-	printf("%s{\n", print_state->need_sep ? ",\n" : "");
+	fprintf(fp, "%s{\n", print_state->need_sep ? ",\n" : "");
 	print_state->need_sep = true;
 	if (group) {
-		fix_escape_printf(&buf, "\t\"MetricGroup\": \"%S\"", group);
+		fix_escape_fprintf(fp, &buf, "\t\"MetricGroup\": \"%S\"", group);
 		need_sep = true;
 	}
 	if (name) {
-		fix_escape_printf(&buf, "%s\t\"MetricName\": \"%S\"", need_sep ? ",\n" : "", name);
+		fix_escape_fprintf(fp, &buf, "%s\t\"MetricName\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   name);
 		need_sep = true;
 	}
 	if (expr) {
-		fix_escape_printf(&buf, "%s\t\"MetricExpr\": \"%S\"", need_sep ? ",\n" : "", expr);
+		fix_escape_fprintf(fp, &buf, "%s\t\"MetricExpr\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   expr);
 		need_sep = true;
 	}
 	if (threshold) {
-		fix_escape_printf(&buf, "%s\t\"MetricThreshold\": \"%S\"", need_sep ? ",\n" : "",
-				  threshold);
+		fix_escape_fprintf(fp, &buf, "%s\t\"MetricThreshold\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   threshold);
 		need_sep = true;
 	}
 	if (unit) {
-		fix_escape_printf(&buf, "%s\t\"ScaleUnit\": \"%S\"", need_sep ? ",\n" : "", unit);
+		fix_escape_fprintf(fp, &buf, "%s\t\"ScaleUnit\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   unit);
 		need_sep = true;
 	}
 	if (desc) {
-		fix_escape_printf(&buf, "%s\t\"BriefDescription\": \"%S\"", need_sep ? ",\n" : "",
-				  desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"BriefDescription\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   desc);
 		need_sep = true;
 	}
 	if (long_desc) {
-		fix_escape_printf(&buf, "%s\t\"PublicDescription\": \"%S\"", need_sep ? ",\n" : "",
-				  long_desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"PublicDescription\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   long_desc);
 		need_sep = true;
 	}
-	printf("%s}", need_sep ? "\n" : "");
+	fprintf(fp, "%s}", need_sep ? "\n" : "");
 	strbuf_release(&buf);
 }
 
@@ -449,8 +482,12 @@ static bool default_skip_duplicate_pmus(void *ps)
 int cmd_list(int argc, const char **argv)
 {
 	int i, ret = 0;
-	struct print_state default_ps = {};
-	struct print_state json_ps = {};
+	struct print_state default_ps = {
+		.fp = stdout,
+	};
+	struct print_state json_ps = {
+		.fp = stdout,
+	};
 	void *ps = &default_ps;
 	struct print_callbacks print_cb = {
 		.print_start = default_print_start,
@@ -461,6 +498,7 @@ int cmd_list(int argc, const char **argv)
 	};
 	const char *cputype = NULL;
 	const char *unit_name = NULL;
+	const char *output_path = NULL;
 	bool json = false;
 	struct option list_options[] = {
 		OPT_BOOLEAN(0, "raw-dump", &default_ps.name_only, "Dump raw events"),
@@ -471,6 +509,7 @@ int cmd_list(int argc, const char **argv)
 			    "Print longer event descriptions."),
 		OPT_BOOLEAN(0, "details", &default_ps.detailed,
 			    "Print information on the perf event names and expressions used internally by events."),
+		OPT_STRING('o', "output", &output_path, "file", "output file name"),
 		OPT_BOOLEAN(0, "deprecated", &default_ps.deprecated,
 			    "Print deprecated events."),
 		OPT_STRING(0, "cputype", &cputype, "cpu type",
@@ -497,6 +536,11 @@ int cmd_list(int argc, const char **argv)
 	argc = parse_options(argc, argv, list_options, list_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 
+	if (output_path) {
+		default_ps.fp = fopen(output_path, "w");
+		json_ps.fp = default_ps.fp;
+	}
+
 	setup_pager();
 
 	if (!default_ps.name_only)
@@ -618,5 +662,8 @@ out:
 	free(default_ps.last_topic);
 	free(default_ps.last_metricgroups);
 	strlist__delete(default_ps.visited_metrics);
+	if (output_path)
+		fclose(default_ps.fp);
+
 	return ret;
 }
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index a3ff2f4edbaa..230461280e45 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -2285,8 +2285,10 @@ setup_args:
 		else
 			ev_name = strdup(contention_tracepoints[j].name);
 
-		if (!ev_name)
+		if (!ev_name) {
+			free(rec_argv);
 			return -ENOMEM;
+		}
 
 		rec_argv[i++] = "-e";
 		rec_argv[i++] = ev_name;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index dcf288a4fb9a..86c910125172 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -270,7 +270,7 @@ static int record__write(struct record *rec, struct mmap *map __maybe_unused,
 
 static int record__aio_enabled(struct record *rec);
 static int record__comp_enabled(struct record *rec);
-static size_t zstd_compress(struct perf_session *session, struct mmap *map,
+static ssize_t zstd_compress(struct perf_session *session, struct mmap *map,
 			    void *dst, size_t dst_size, void *src, size_t src_size);
 
 #ifdef HAVE_AIO_SUPPORT
@@ -405,9 +405,13 @@ static int record__aio_pushfn(struct mmap *map, void *to, void *buf, size_t size
 	 */
 
 	if (record__comp_enabled(aio->rec)) {
-		size = zstd_compress(aio->rec->session, NULL, aio->data + aio->size,
-				     mmap__mmap_len(map) - aio->size,
-				     buf, size);
+		ssize_t compressed = zstd_compress(aio->rec->session, NULL, aio->data + aio->size,
+						   mmap__mmap_len(map) - aio->size,
+						   buf, size);
+		if (compressed < 0)
+			return (int)compressed;
+
+		size = compressed;
 	} else {
 		memcpy(aio->data + aio->size, buf, size);
 	}
@@ -633,7 +637,13 @@ static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size)
 	struct record *rec = to;
 
 	if (record__comp_enabled(rec)) {
-		size = zstd_compress(rec->session, map, map->data, mmap__mmap_len(map), bf, size);
+		ssize_t compressed = zstd_compress(rec->session, map, map->data,
+						   mmap__mmap_len(map), bf, size);
+
+		if (compressed < 0)
+			return (int)compressed;
+
+		size = compressed;
 		bf   = map->data;
 	}
 
@@ -1350,7 +1360,7 @@ static int record__open(struct record *rec)
 	evlist__for_each_entry(evlist, pos) {
 try_again:
 		if (evsel__open(pos, pos->core.cpus, pos->core.threads) < 0) {
-			if (evsel__fallback(pos, errno, msg, sizeof(msg))) {
+			if (evsel__fallback(pos, &opts->target, errno, msg, sizeof(msg))) {
 				if (verbose > 0)
 					ui__warning("%s\n", msg);
 				goto try_again;
@@ -1527,10 +1537,10 @@ static size_t process_comp_header(void *record, size_t increment)
 	return size;
 }
 
-static size_t zstd_compress(struct perf_session *session, struct mmap *map,
+static ssize_t zstd_compress(struct perf_session *session, struct mmap *map,
 			    void *dst, size_t dst_size, void *src, size_t src_size)
 {
-	size_t compressed;
+	ssize_t compressed;
 	size_t max_record_size = PERF_SAMPLE_MAX_SIZE - sizeof(struct perf_record_compressed) - 1;
 	struct zstd_data *zstd_data = &session->zstd_data;
 
@@ -1539,6 +1549,8 @@ static size_t zstd_compress(struct perf_session *session, struct mmap *map,
 
 	compressed = zstd_compress_stream_to_records(zstd_data, dst, dst_size, src, src_size,
 						     max_record_size, process_comp_header);
+	if (compressed < 0)
+		return compressed;
 
 	if (map && map->file) {
 		thread->bytes_transferred += src_size;
@@ -1912,21 +1924,13 @@ static void __record__save_lost_samples(struct record *rec, struct evsel *evsel,
 static void record__read_lost_samples(struct record *rec)
 {
 	struct perf_session *session = rec->session;
-	struct perf_record_lost_samples *lost;
+	struct perf_record_lost_samples *lost = NULL;
 	struct evsel *evsel;
 
 	/* there was an error during record__open */
 	if (session->evlist == NULL)
 		return;
 
-	lost = zalloc(PERF_SAMPLE_MAX_SIZE);
-	if (lost == NULL) {
-		pr_debug("Memory allocation failed\n");
-		return;
-	}
-
-	lost->header.type = PERF_RECORD_LOST_SAMPLES;
-
 	evlist__for_each_entry(session->evlist, evsel) {
 		struct xyarray *xy = evsel->core.sample_id;
 		u64 lost_count;
@@ -1949,6 +1953,15 @@ static void record__read_lost_samples(struct record *rec)
 				}
 
 				if (count.lost) {
+					if (!lost) {
+						lost = zalloc(sizeof(*lost) +
+							      session->machines.host.id_hdr_size);
+						if (!lost) {
+							pr_debug("Memory allocation failed\n");
+							return;
+						}
+						lost->header.type = PERF_RECORD_LOST_SAMPLES;
+					}
 					__record__save_lost_samples(rec, evsel, lost,
 								    x, y, count.lost, 0);
 				}
@@ -1956,9 +1969,19 @@ static void record__read_lost_samples(struct record *rec)
 		}
 
 		lost_count = perf_bpf_filter__lost_count(evsel);
-		if (lost_count)
+		if (lost_count) {
+			if (!lost) {
+				lost = zalloc(sizeof(*lost) +
+					      session->machines.host.id_hdr_size);
+				if (!lost) {
+					pr_debug("Memory allocation failed\n");
+					return;
+				}
+				lost->header.type = PERF_RECORD_LOST_SAMPLES;
+			}
 			__record__save_lost_samples(rec, evsel, lost, 0, 0, lost_count,
 						    PERF_RECORD_MISC_LOST_SAMPLES_BPF);
+		}
 	}
 out:
 	free(lost);
@@ -2216,32 +2239,6 @@ static void hit_auxtrace_snapshot_trigger(struct record *rec)
 	}
 }
 
-static void record__uniquify_name(struct record *rec)
-{
-	struct evsel *pos;
-	struct evlist *evlist = rec->evlist;
-	char *new_name;
-	int ret;
-
-	if (perf_pmus__num_core_pmus() == 1)
-		return;
-
-	evlist__for_each_entry(evlist, pos) {
-		if (!evsel__is_hybrid(pos))
-			continue;
-
-		if (strchr(pos->name, '/'))
-			continue;
-
-		ret = asprintf(&new_name, "%s/%s/",
-			       pos->pmu_name, pos->name);
-		if (ret) {
-			free(pos->name);
-			pos->name = new_name;
-		}
-	}
-}
-
 static int record__terminate_thread(struct record_thread *thread_data)
 {
 	int err;
@@ -2475,7 +2472,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	if (data->is_pipe && rec->evlist->core.nr_entries == 1)
 		rec->opts.sample_id = true;
 
-	record__uniquify_name(rec);
+	evlist__uniquify_name(rec->evlist);
 
 	/* Debug message used by test scripts */
 	pr_debug3("perf record opening and mmapping events\n");
@@ -3580,9 +3577,7 @@ static int record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_cp
 	if (cpu_map__is_dummy(cpus))
 		return 0;
 
-	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
-		if (cpu.cpu == -1)
-			continue;
+	perf_cpu_map__for_each_cpu_skip_any(cpu, idx, cpus) {
 		/* Return ENODEV is input cpu is greater than max cpu */
 		if ((unsigned long)cpu.cpu > mask->nbits)
 			return -ENODEV;
@@ -3989,6 +3984,8 @@ int cmd_record(int argc, const char **argv)
 # undef set_nobuild
 #endif
 
+	/* Disable eager loading of kernel symbols that adds overhead to perf record. */
+	symbol_conf.lazy_load_kernel_maps = true;
 	rec->opts.affinity = PERF_AFFINITY_SYS;
 
 	rec->evlist = evlist__new();
@@ -4083,8 +4080,8 @@ int cmd_record(int argc, const char **argv)
 	}
 
 	if (rec->switch_output.num_files) {
-		rec->switch_output.filenames = calloc(sizeof(char *),
-						      rec->switch_output.num_files);
+		rec->switch_output.filenames = calloc(rec->switch_output.num_files,
+						      sizeof(char *));
 		if (!rec->switch_output.filenames) {
 			err = -EINVAL;
 			goto out_opts;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 9cb1da2dc0c0..f2ed2b7e80a3 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -96,9 +96,9 @@ struct report {
 	bool			stitch_lbr;
 	bool			disable_order;
 	bool			skip_empty;
+	bool			data_type;
 	int			max_stack;
 	struct perf_read_values	show_threads_values;
-	struct annotation_options annotation_opts;
 	const char		*pretty_printing_style;
 	const char		*cpu_list;
 	const char		*symbol_filter_str;
@@ -171,7 +171,7 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter,
 	struct mem_info *mi;
 	struct branch_info *bi;
 
-	if (!ui__has_annotation() && !rep->symbol_ipc)
+	if (!ui__has_annotation() && !rep->symbol_ipc && !rep->data_type)
 		return 0;
 
 	if (sort__mode == SORT_MODE__BRANCH) {
@@ -541,8 +541,7 @@ static int evlist__tui_block_hists_browse(struct evlist *evlist, struct report *
 	evlist__for_each_entry(evlist, pos) {
 		ret = report__browse_block_hists(&rep->block_reports[i++].hist,
 						 rep->min_percent, pos,
-						 &rep->session->header.env,
-						 &rep->annotation_opts);
+						 &rep->session->header.env);
 		if (ret != 0)
 			return ret;
 	}
@@ -574,8 +573,7 @@ static int evlist__tty_browse_hists(struct evlist *evlist, struct report *rep, c
 
 		if (rep->total_cycles_mode) {
 			report__browse_block_hists(&rep->block_reports[i++].hist,
-						   rep->min_percent, pos,
-						   NULL, NULL);
+						   rep->min_percent, pos, NULL);
 			continue;
 		}
 
@@ -670,7 +668,7 @@ static int report__browse_hists(struct report *rep)
 		}
 
 		ret = evlist__tui_browse_hists(evlist, help, NULL, rep->min_percent,
-					       &session->header.env, true, &rep->annotation_opts);
+					       &session->header.env, true);
 		/*
 		 * Usually "ret" is the last pressed key, and we only
 		 * care if the key notifies us to switch data file.
@@ -745,7 +743,7 @@ static int hists__resort_cb(struct hist_entry *he, void *arg)
 	if (rep->symbol_ipc && sym && !sym->annotate2) {
 		struct evsel *evsel = hists_to_evsel(he->hists);
 
-		symbol__annotate2(&he->ms, evsel, &rep->annotation_opts, NULL);
+		symbol__annotate2(&he->ms, evsel, NULL);
 	}
 
 	return 0;
@@ -859,27 +857,47 @@ static struct task *tasks_list(struct task *task, struct machine *machine)
 	return tasks_list(parent_task, machine);
 }
 
-static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp)
+struct maps__fprintf_task_args {
+	int indent;
+	FILE *fp;
+	size_t printed;
+};
+
+static int maps__fprintf_task_cb(struct map *map, void *data)
 {
-	size_t printed = 0;
-	struct map_rb_node *rb_node;
+	struct maps__fprintf_task_args *args = data;
+	const struct dso *dso = map__dso(map);
+	u32 prot = map__prot(map);
+	int ret;
 
-	maps__for_each_entry(maps, rb_node) {
-		struct map *map = rb_node->map;
-		const struct dso *dso = map__dso(map);
-		u32 prot = map__prot(map);
+	ret = fprintf(args->fp,
+		"%*s  %" PRIx64 "-%" PRIx64 " %c%c%c%c %08" PRIx64 " %" PRIu64 " %s\n",
+		args->indent, "", map__start(map), map__end(map),
+		prot & PROT_READ ? 'r' : '-',
+		prot & PROT_WRITE ? 'w' : '-',
+		prot & PROT_EXEC ? 'x' : '-',
+		map__flags(map) ? 's' : 'p',
+		map__pgoff(map),
+		dso->id.ino, dso->name);
 
-		printed += fprintf(fp, "%*s  %" PRIx64 "-%" PRIx64 " %c%c%c%c %08" PRIx64 " %" PRIu64 " %s\n",
-				   indent, "", map__start(map), map__end(map),
-				   prot & PROT_READ ? 'r' : '-',
-				   prot & PROT_WRITE ? 'w' : '-',
-				   prot & PROT_EXEC ? 'x' : '-',
-				   map__flags(map) ? 's' : 'p',
-				   map__pgoff(map),
-				   dso->id.ino, dso->name);
-	}
+	if (ret < 0)
+		return ret;
+
+	args->printed += ret;
+	return 0;
+}
+
+static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp)
+{
+	struct maps__fprintf_task_args args = {
+		.indent = indent,
+		.fp = fp,
+		.printed = 0,
+	};
 
-	return printed;
+	maps__for_each_map(maps, maps__fprintf_task_cb, &args);
+
+	return args.printed;
 }
 
 static void task__print_level(struct task *task, FILE *fp, int level)
@@ -1341,15 +1359,15 @@ int cmd_report(int argc, const char **argv)
 		   "list of cpus to profile"),
 	OPT_BOOLEAN('I', "show-info", &report.show_full_info,
 		    "Display extended information about perf.data file"),
-	OPT_BOOLEAN(0, "source", &report.annotation_opts.annotate_src,
+	OPT_BOOLEAN(0, "source", &annotate_opts.annotate_src,
 		    "Interleave source code with assembly code (default)"),
-	OPT_BOOLEAN(0, "asm-raw", &report.annotation_opts.show_asm_raw,
+	OPT_BOOLEAN(0, "asm-raw", &annotate_opts.show_asm_raw,
 		    "Display raw encoding of assembly instructions (default)"),
 	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
-	OPT_STRING(0, "prefix", &report.annotation_opts.prefix, "prefix",
+	OPT_STRING(0, "prefix", &annotate_opts.prefix, "prefix",
 		    "Add prefix to source file path names in programs (with --prefix-strip)"),
-	OPT_STRING(0, "prefix-strip", &report.annotation_opts.prefix_strip, "N",
+	OPT_STRING(0, "prefix-strip", &annotate_opts.prefix_strip, "N",
 		    "Strip first N entries of source file path name in programs (with --prefix)"),
 	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
 		    "Show a column with the sum of periods"),
@@ -1401,7 +1419,7 @@ int cmd_report(int argc, const char **argv)
 		   "Time span of interest (start,stop)"),
 	OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name,
 		    "Show inline function"),
-	OPT_CALLBACK(0, "percent-type", &report.annotation_opts, "local-period",
+	OPT_CALLBACK(0, "percent-type", &annotate_opts, "local-period",
 		     "Set percent type local/global-period/hits",
 		     annotate_parse_percent_type),
 	OPT_BOOLEAN(0, "ns", &symbol_conf.nanosecs, "Show times in nanosecs"),
@@ -1426,7 +1444,14 @@ int cmd_report(int argc, const char **argv)
 	if (ret < 0)
 		goto exit;
 
-	annotation_options__init(&report.annotation_opts);
+	/*
+	 * tasks_mode require access to exited threads to list those that are in
+	 * the data file. Off-cpu events are synthesized after other events and
+	 * reference exited threads.
+	 */
+	symbol_conf.keep_exited_threads = true;
+
+	annotation_options__init();
 
 	ret = perf_config(report__config, &report);
 	if (ret)
@@ -1445,13 +1470,13 @@ int cmd_report(int argc, const char **argv)
 	}
 
 	if (disassembler_style) {
-		report.annotation_opts.disassembler_style = strdup(disassembler_style);
-		if (!report.annotation_opts.disassembler_style)
+		annotate_opts.disassembler_style = strdup(disassembler_style);
+		if (!annotate_opts.disassembler_style)
 			return -ENOMEM;
 	}
 	if (objdump_path) {
-		report.annotation_opts.objdump_path = strdup(objdump_path);
-		if (!report.annotation_opts.objdump_path)
+		annotate_opts.objdump_path = strdup(objdump_path);
+		if (!annotate_opts.objdump_path)
 			return -ENOMEM;
 	}
 	if (addr2line_path) {
@@ -1460,7 +1485,7 @@ int cmd_report(int argc, const char **argv)
 			return -ENOMEM;
 	}
 
-	if (annotate_check_args(&report.annotation_opts) < 0) {
+	if (annotate_check_args() < 0) {
 		ret = -EINVAL;
 		goto exit;
 	}
@@ -1615,6 +1640,16 @@ repeat:
 			sort_order = NULL;
 	}
 
+	if (sort_order && strstr(sort_order, "type")) {
+		report.data_type = true;
+		annotate_opts.annotate_src = false;
+
+#ifndef HAVE_DWARF_GETLOCATIONS_SUPPORT
+		pr_err("Error: Data type profiling is disabled due to missing DWARF support\n");
+		goto error;
+#endif
+	}
+
 	if (strcmp(input_name, "-") != 0)
 		setup_browser(true);
 	else
@@ -1673,7 +1708,7 @@ repeat:
 	 * so don't allocate extra space that won't be used in the stdio
 	 * implementation.
 	 */
-	if (ui__has_annotation() || report.symbol_ipc ||
+	if (ui__has_annotation() || report.symbol_ipc || report.data_type ||
 	    report.total_cycles_mode) {
 		ret = symbol__annotation_init();
 		if (ret < 0)
@@ -1692,7 +1727,7 @@ repeat:
 			 */
 			symbol_conf.priv_size += sizeof(u32);
 		}
-		annotation_config__init(&report.annotation_opts);
+		annotation_config__init();
 	}
 
 	if (symbol__init(&session->header.env) < 0)
@@ -1746,7 +1781,7 @@ error:
 	zstd_fini(&(session->zstd_data));
 	perf_session__delete(session);
 exit:
-	annotation_options__exit(&report.annotation_opts);
+	annotation_options__exit();
 	free(sort_order_help);
 	free(field_order_help);
 	return ret;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a3af805a1d57..5fe9abc6a524 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -653,7 +653,7 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)
 		if ((evsel__leader(counter) != counter) ||
 		    !(counter->core.leader->nr_members > 1))
 			return COUNTER_SKIP;
-	} else if (evsel__fallback(counter, errno, msg, sizeof(msg))) {
+	} else if (evsel__fallback(counter, &target, errno, msg, sizeof(msg))) {
 		if (verbose > 0)
 			ui__warning("%s\n", msg);
 		return COUNTER_RETRY;
@@ -1204,8 +1204,9 @@ static struct option stat_options[] = {
 	OPT_STRING('C', "cpu", &target.cpu_list, "cpu",
 		    "list of cpus to monitor in system-wide"),
 	OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode,
-		    "disable CPU count aggregation", AGGR_NONE),
-	OPT_BOOLEAN(0, "no-merge", &stat_config.no_merge, "Do not merge identical named events"),
+		    "disable aggregation across CPUs or PMUs", AGGR_NONE),
+	OPT_SET_UINT(0, "no-merge", &stat_config.aggr_mode,
+		    "disable aggregation the same as -A or -no-aggr", AGGR_NONE),
 	OPT_BOOLEAN(0, "hybrid-merge", &stat_config.hybrid_merge,
 		    "Merge identical named hybrid events"),
 	OPT_STRING('x', "field-separator", &stat_config.csv_sep, "separator",
@@ -1255,7 +1256,7 @@ static struct option stat_options[] = {
 	OPT_BOOLEAN(0, "metric-no-merge", &stat_config.metric_no_merge,
 		       "don't try to share events between metrics in a group"),
 	OPT_BOOLEAN(0, "metric-no-threshold", &stat_config.metric_no_threshold,
-		       "don't try to share events between metrics in a group  "),
+		       "disable adding events for the metric threshold calculation"),
 	OPT_BOOLEAN(0, "topdown", &topdown_run,
 			"measure top-down statistics"),
 	OPT_UINTEGER(0, "td-level", &stat_config.topdown_level,
@@ -1316,7 +1317,7 @@ static int cpu__get_cache_id_from_map(struct perf_cpu cpu, char *map)
 	 * be the first online CPU in the cache domain else use the
 	 * first online CPU of the cache domain as the ID.
 	 */
-	if (perf_cpu_map__empty(cpu_map))
+	if (perf_cpu_map__has_any_cpu_or_is_empty(cpu_map))
 		id = cpu.cpu;
 	else
 		id = perf_cpu_map__cpu(cpu_map, 0).cpu;
@@ -1622,7 +1623,7 @@ static int perf_stat_init_aggr_mode(void)
 	 * taking the highest cpu number to be the size of
 	 * the aggregation translate cpumap.
 	 */
-	if (!perf_cpu_map__empty(evsel_list->core.user_requested_cpus))
+	if (!perf_cpu_map__has_any_cpu_or_is_empty(evsel_list->core.user_requested_cpus))
 		nr = perf_cpu_map__max(evsel_list->core.user_requested_cpus).cpu;
 	else
 		nr = 0;
@@ -2289,7 +2290,7 @@ int process_stat_config_event(struct perf_session *session,
 
 	perf_event__read_stat_config(&stat_config, &event->stat_config);
 
-	if (perf_cpu_map__empty(st->cpus)) {
+	if (perf_cpu_map__has_any_cpu_or_is_empty(st->cpus)) {
 		if (st->aggr_mode != AGGR_UNSET)
 			pr_warning("warning: processing task data, aggregation mode not set\n");
 	} else if (st->aggr_mode != AGGR_UNSET) {
@@ -2695,15 +2696,19 @@ int cmd_stat(int argc, const char **argv)
 	 */
 	if (metrics) {
 		const char *pmu = parse_events_option_args.pmu_filter ?: "all";
+		int ret = metricgroup__parse_groups(evsel_list, pmu, metrics,
+						stat_config.metric_no_group,
+						stat_config.metric_no_merge,
+						stat_config.metric_no_threshold,
+						stat_config.user_requested_cpu_list,
+						stat_config.system_wide,
+						&stat_config.metric_events);
 
-		metricgroup__parse_groups(evsel_list, pmu, metrics,
-					stat_config.metric_no_group,
-					stat_config.metric_no_merge,
-					stat_config.metric_no_threshold,
-					stat_config.user_requested_cpu_list,
-					stat_config.system_wide,
-					&stat_config.metric_events);
 		zfree(&metrics);
+		if (ret) {
+			status = ret;
+			goto out;
+		}
 	}
 
 	if (add_default_attributes())
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ea8c7eca5eee..5301d1badd43 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -147,7 +147,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 		return err;
 	}
 
-	err = symbol__annotate(&he->ms, evsel, &top->annotation_opts, NULL);
+	err = symbol__annotate(&he->ms, evsel, NULL);
 	if (err == 0) {
 		top->sym_filter_entry = he;
 	} else {
@@ -261,9 +261,9 @@ static void perf_top__show_details(struct perf_top *top)
 		goto out_unlock;
 
 	printf("Showing %s for %s\n", evsel__name(top->sym_evsel), symbol->name);
-	printf("  Events  Pcnt (>=%d%%)\n", top->annotation_opts.min_pcnt);
+	printf("  Events  Pcnt (>=%d%%)\n", annotate_opts.min_pcnt);
 
-	more = symbol__annotate_printf(&he->ms, top->sym_evsel, &top->annotation_opts);
+	more = symbol__annotate_printf(&he->ms, top->sym_evsel);
 
 	if (top->evlist->enabled) {
 		if (top->zero)
@@ -357,7 +357,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
 
 static void prompt_integer(int *target, const char *msg)
 {
-	char *buf = malloc(0), *p;
+	char *buf = NULL, *p;
 	size_t dummy = 0;
 	int tmp;
 
@@ -450,7 +450,7 @@ static void perf_top__print_mapped_keys(struct perf_top *top)
 
 	fprintf(stdout, "\t[f]     profile display filter (count).    \t(%d)\n", top->count_filter);
 
-	fprintf(stdout, "\t[F]     annotate display filter (percent). \t(%d%%)\n", top->annotation_opts.min_pcnt);
+	fprintf(stdout, "\t[F]     annotate display filter (percent). \t(%d%%)\n", annotate_opts.min_pcnt);
 	fprintf(stdout, "\t[s]     annotate symbol.                   \t(%s)\n", name?: "NULL");
 	fprintf(stdout, "\t[S]     stop annotation.\n");
 
@@ -553,7 +553,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 			prompt_integer(&top->count_filter, "Enter display event count filter");
 			break;
 		case 'F':
-			prompt_percent(&top->annotation_opts.min_pcnt,
+			prompt_percent(&annotate_opts.min_pcnt,
 				       "Enter details display event filter (percent)");
 			break;
 		case 'K':
@@ -646,8 +646,7 @@ repeat:
 	}
 
 	ret = evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent,
-				       &top->session->header.env, !top->record_opts.overwrite,
-				       &top->annotation_opts);
+				       &top->session->header.env, !top->record_opts.overwrite);
 	if (ret == K_RELOAD) {
 		top->zero = true;
 		goto repeat;
@@ -1027,8 +1026,8 @@ static int perf_top__start_counters(struct perf_top *top)
 
 	evlist__for_each_entry(evlist, counter) {
 try_again:
-		if (evsel__open(counter, top->evlist->core.user_requested_cpus,
-				     top->evlist->core.threads) < 0) {
+		if (evsel__open(counter, counter->core.cpus,
+				counter->core.threads) < 0) {
 
 			/*
 			 * Specially handle overwrite fall back.
@@ -1044,7 +1043,7 @@ try_again:
 			    perf_top_overwrite_fallback(top, counter))
 				goto try_again;
 
-			if (evsel__fallback(counter, errno, msg, sizeof(msg))) {
+			if (evsel__fallback(counter, &opts->target, errno, msg, sizeof(msg))) {
 				if (verbose > 0)
 					ui__warning("%s\n", msg);
 				goto try_again;
@@ -1241,9 +1240,9 @@ static int __cmd_top(struct perf_top *top)
 	pthread_t thread, thread_process;
 	int ret;
 
-	if (!top->annotation_opts.objdump_path) {
+	if (!annotate_opts.objdump_path) {
 		ret = perf_env__lookup_objdump(&top->session->header.env,
-					       &top->annotation_opts.objdump_path);
+					       &annotate_opts.objdump_path);
 		if (ret)
 			return ret;
 	}
@@ -1299,6 +1298,7 @@ static int __cmd_top(struct perf_top *top)
 		}
 	}
 
+	evlist__uniquify_name(top->evlist);
 	ret = perf_top__start_counters(top);
 	if (ret)
 		return ret;
@@ -1536,9 +1536,9 @@ int cmd_top(int argc, const char **argv)
 		   "only consider symbols in these comms"),
 	OPT_STRING(0, "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
 		   "only consider these symbols"),
-	OPT_BOOLEAN(0, "source", &top.annotation_opts.annotate_src,
+	OPT_BOOLEAN(0, "source", &annotate_opts.annotate_src,
 		    "Interleave source code with assembly code (default)"),
-	OPT_BOOLEAN(0, "asm-raw", &top.annotation_opts.show_asm_raw,
+	OPT_BOOLEAN(0, "asm-raw", &annotate_opts.show_asm_raw,
 		    "Display raw encoding of assembly instructions (default)"),
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
 		    "Enable kernel symbol demangling"),
@@ -1549,9 +1549,9 @@ int cmd_top(int argc, const char **argv)
 		   "addr2line binary to use for line numbers"),
 	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
-	OPT_STRING(0, "prefix", &top.annotation_opts.prefix, "prefix",
+	OPT_STRING(0, "prefix", &annotate_opts.prefix, "prefix",
 		    "Add prefix to source file path names in programs (with --prefix-strip)"),
-	OPT_STRING(0, "prefix-strip", &top.annotation_opts.prefix_strip, "N",
+	OPT_STRING(0, "prefix-strip", &annotate_opts.prefix_strip, "N",
 		    "Strip first N entries of source file path name in programs (with --prefix)"),
 	OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"),
 	OPT_CALLBACK(0, "percent-limit", &top, "percent",
@@ -1609,10 +1609,10 @@ int cmd_top(int argc, const char **argv)
 	if (status < 0)
 		return status;
 
-	annotation_options__init(&top.annotation_opts);
+	annotation_options__init();
 
-	top.annotation_opts.min_pcnt = 5;
-	top.annotation_opts.context  = 4;
+	annotate_opts.min_pcnt = 5;
+	annotate_opts.context  = 4;
 
 	top.evlist = evlist__new();
 	if (top.evlist == NULL)
@@ -1642,13 +1642,13 @@ int cmd_top(int argc, const char **argv)
 		usage_with_options(top_usage, options);
 
 	if (disassembler_style) {
-		top.annotation_opts.disassembler_style = strdup(disassembler_style);
-		if (!top.annotation_opts.disassembler_style)
+		annotate_opts.disassembler_style = strdup(disassembler_style);
+		if (!annotate_opts.disassembler_style)
 			return -ENOMEM;
 	}
 	if (objdump_path) {
-		top.annotation_opts.objdump_path = strdup(objdump_path);
-		if (!top.annotation_opts.objdump_path)
+		annotate_opts.objdump_path = strdup(objdump_path);
+		if (!annotate_opts.objdump_path)
 			return -ENOMEM;
 	}
 	if (addr2line_path) {
@@ -1661,7 +1661,7 @@ int cmd_top(int argc, const char **argv)
 	if (status)
 		goto out_delete_evlist;
 
-	if (annotate_check_args(&top.annotation_opts) < 0)
+	if (annotate_check_args() < 0)
 		goto out_delete_evlist;
 
 	if (!top.evlist->core.nr_entries) {
@@ -1787,7 +1787,7 @@ int cmd_top(int argc, const char **argv)
 	if (status < 0)
 		goto out_delete_evlist;
 
-	annotation_config__init(&top.annotation_opts);
+	annotation_config__init();
 
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
 	status = symbol__init(NULL);
@@ -1840,7 +1840,7 @@ int cmd_top(int argc, const char **argv)
 out_delete_evlist:
 	evlist__delete(top.evlist);
 	perf_session__delete(top.session);
-	annotation_options__exit(&top.annotation_opts);
+	annotation_options__exit();
 
 	return status;
 }
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index e541d0e2777a..109b8e64fe69 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2470,9 +2470,8 @@ static int trace__fprintf_callchain(struct trace *trace, struct perf_sample *sam
 static const char *errno_to_name(struct evsel *evsel, int err)
 {
 	struct perf_env *env = evsel__env(evsel);
-	const char *arch_name = perf_env__arch(env);
 
-	return arch_syscalls__strerrno(arch_name, err);
+	return perf_env__arch_strerrno(env, err);
 }
 
 static int trace__sys_exit(struct trace *trace, struct evsel *evsel,
@@ -4264,12 +4263,11 @@ static size_t thread__dump_stats(struct thread_trace *ttrace,
 			printed += fprintf(fp, " %9.3f %9.2f%%\n", max, pct);
 
 			if (trace->errno_summary && stats->nr_failures) {
-				const char *arch_name = perf_env__arch(trace->host->env);
 				int e;
 
 				for (e = 0; e < stats->max_errno; ++e) {
 					if (stats->errnos[e] != 0)
-						fprintf(fp, "\t\t\t\t%s: %d\n", arch_syscalls__strerrno(arch_name, e + 1), stats->errnos[e]);
+						fprintf(fp, "\t\t\t\t%s: %d\n", perf_env__arch_strerrno(trace->host->env, e + 1), stats->errnos[e]);
 				}
 			}
 		}
diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh
index 133f0eddbcc4..f94795794b36 100644..100755
--- a/tools/perf/perf-archive.sh
+++ b/tools/perf/perf-archive.sh
@@ -4,8 +4,73 @@
 # Arnaldo Carvalho de Melo <acme@redhat.com>
 
 PERF_DATA=perf.data
-if [ $# -ne 0 ] ; then
-	PERF_DATA=$1
+PERF_SYMBOLS=perf.symbols
+PERF_ALL=perf.all
+ALL=0
+UNPACK=0
+
+while [ $# -gt 0 ] ; do
+	if [ $1 == "--all" ]; then
+		ALL=1
+		shift
+	elif [ $1 == "--unpack" ]; then
+		UNPACK=1
+		shift
+	else
+		PERF_DATA=$1
+		UNPACK_TAR=$1
+		shift
+	fi
+done
+
+if [ $UNPACK -eq 1 ]; then
+	if [ ! -z "$UNPACK_TAR" ]; then					# tar given as an argument
+		if [ ! -e "$UNPACK_TAR" ]; then
+			echo "Provided file $UNPACK_TAR does not exist"
+			exit 1
+		fi
+		TARGET="$UNPACK_TAR"
+	else																# search for perf tar in the current directory
+		TARGET=`find . -regex "\./perf.*\.tar\.bz2"`
+		TARGET_NUM=`echo -n "$TARGET" | grep -c '^'`
+
+		if [ -z "$TARGET" -o $TARGET_NUM -gt 1 ]; then
+			echo -e "Error: $TARGET_NUM files found for unpacking:\n$TARGET"
+			echo "Provide the requested file as an argument"
+			exit 1
+		else
+			echo "Found target file for unpacking: $TARGET"
+		fi
+	fi
+
+	if [[ "$TARGET" =~ (\./)?$PERF_ALL.*.tar.bz2 ]]; then				# perf tar generated by --all option
+		TAR_CONTENTS=`tar tvf "$TARGET" | tr -s " " | cut -d " " -f 6`
+		VALID_TAR=`echo "$TAR_CONTENTS" | grep "$PERF_SYMBOLS.tar.bz2" | wc -l`		# check if it contains a sub-tar perf.symbols
+		if [ $VALID_TAR -ne 1 ]; then
+			echo "Error: $TARGET file is not valid (contains zero or multiple sub-tar files with debug symbols)"
+			exit 1
+		fi
+
+		INTERSECT=`comm -12 <(ls) <(echo "$TAR_CONTENTS") | tr "\n" " "`	# check for overwriting
+		if [ ! -z "$INTERSECT" ]; then										# prompt if file(s) already exist in the current directory
+			echo "File(s) ${INTERSECT::-1} already exist in the current directory."
+			while true; do
+				read -p 'Do you wish to overwrite them? ' yn
+				case $yn in
+					[Yy]* ) break;;
+					[Nn]* ) exit 1;;
+					* ) echo "Please answer yes or no.";;
+				esac
+			done
+		fi
+
+		# unzip the perf.data file in the current working directory	and debug symbols in ~/.debug directory
+		tar xvf $TARGET && tar xvf $PERF_SYMBOLS.tar.bz2 -C ~/.debug
+
+	else																# perf tar generated by perf archive (contains only debug symbols)
+		tar xvf $TARGET -C ~/.debug
+	fi
+	exit 0
 fi
 
 #
@@ -39,9 +104,18 @@ while read build_id ; do
 	echo ${filename#$PERF_BUILDID_LINKDIR} >> $MANIFEST
 done
 
-tar cjf $PERF_DATA.tar.bz2 -C $PERF_BUILDID_DIR -T $MANIFEST
-rm $MANIFEST $BUILDIDS || true
+if [ $ALL -eq 1 ]; then						# pack perf.data file together with tar containing debug symbols
+	HOSTNAME=$(hostname)
+	DATE=$(date '+%Y%m%d-%H%M%S')
+	tar cjf $PERF_SYMBOLS.tar.bz2 -C $PERF_BUILDID_DIR -T $MANIFEST
+	tar cjf	$PERF_ALL-$HOSTNAME-$DATE.tar.bz2 $PERF_DATA $PERF_SYMBOLS.tar.bz2
+	rm $PERF_SYMBOLS.tar.bz2 $MANIFEST $BUILDIDS || true
+else										# pack only the debug symbols
+	tar cjf $PERF_DATA.tar.bz2 -C $PERF_BUILDID_DIR -T $MANIFEST
+	rm $MANIFEST $BUILDIDS || true
+fi
+
 echo -e "Now please run:\n"
-echo -e "$ tar xvf $PERF_DATA.tar.bz2 -C ~/.debug\n"
-echo "wherever you need to run 'perf report' on."
+echo -e "$ perf archive --unpack\n"
+echo "or unpack the tar manually wherever you need to run 'perf report' on."
 exit 0
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index d3fc8090413c..921bee0a6437 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -39,6 +39,7 @@
 #include <linux/zalloc.h>
 
 static int use_pager = -1;
+static FILE *debug_fp = NULL;
 
 struct cmd_struct {
 	const char *cmd;
@@ -162,6 +163,19 @@ static void commit_pager_choice(void)
 	}
 }
 
+static int set_debug_file(const char *path)
+{
+	debug_fp = fopen(path, "w");
+	if (!debug_fp) {
+		fprintf(stderr, "Open debug file '%s' failed: %s\n",
+			path, strerror(errno));
+		return -1;
+	}
+
+	debug_set_file(debug_fp);
+	return 0;
+}
+
 struct option options[] = {
 	OPT_ARGUMENT("help", "help"),
 	OPT_ARGUMENT("version", "version"),
@@ -174,6 +188,7 @@ struct option options[] = {
 	OPT_ARGUMENT("list-cmds", "list-cmds"),
 	OPT_ARGUMENT("list-opts", "list-opts"),
 	OPT_ARGUMENT("debug", "debug"),
+	OPT_ARGUMENT("debug-file", "debug-file"),
 	OPT_END()
 };
 
@@ -287,6 +302,18 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
 
 			(*argv)++;
 			(*argc)--;
+		} else if (!strcmp(cmd, "--debug-file")) {
+			if (*argc < 2) {
+				fprintf(stderr, "No path given for --debug-file.\n");
+				usage(perf_usage_string);
+			}
+
+			if (set_debug_file((*argv)[1]))
+				usage(perf_usage_string);
+
+			(*argv)++;
+			(*argc)--;
+
 		} else {
 			fprintf(stderr, "Unknown option: %s\n", cmd);
 			usage(perf_usage_string);
@@ -547,5 +574,8 @@ int main(int argc, const char **argv)
 	fprintf(stderr, "Failed to run command '%s': %s\n",
 		cmd, str_error_r(errno, sbuf, sizeof(sbuf)));
 out:
+	if (debug_fp)
+		fclose(debug_fp);
+
 	return 1;
 }
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json
index 88b23b85e33c..879ff21e0b17 100644
--- a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json
@@ -110,7 +110,7 @@
     {
         "PublicDescription": "Flushes due to memory hazards",
         "EventCode": "0x121",
-        "EventName": "BPU_FLUSH_MEM_FAULT",
+        "EventName": "GPC_FLUSH_MEM_FAULT",
         "BriefDescription": "Flushes due to memory hazards"
     },
     {
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/branch.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/branch.json
new file mode 100644
index 000000000000..a632755fc086
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/branch.json
@@ -0,0 +1,125 @@
+[
+    {
+        "ArchStdEvent": "BR_IMMED_SPEC"
+    },
+    {
+        "ArchStdEvent": "BR_RETURN_SPEC"
+    },
+    {
+        "ArchStdEvent": "BR_INDIRECT_SPEC"
+    },
+    {
+        "ArchStdEvent": "BR_MIS_PRED"
+    },
+    {
+        "ArchStdEvent": "BR_PRED"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, branch not taken",
+        "EventCode": "0x8107",
+        "EventName": "BR_SKIP_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, branch not taken"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, immediate branch taken",
+        "EventCode": "0x8108",
+        "EventName": "BR_IMMED_TAKEN_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, immediate branch taken"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, indirect branch excluding return retired",
+        "EventCode": "0x810c",
+        "EventName": "BR_INDNR_TAKEN_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, indirect branch excluding return retired"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, predicted immediate branch",
+        "EventCode": "0x8110",
+        "EventName": "BR_IMMED_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, predicted immediate branch"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, mispredicted immediate branch",
+        "EventCode": "0x8111",
+        "EventName": "BR_IMMED_MIS_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, mispredicted immediate branch"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, predicted indirect branch",
+        "EventCode": "0x8112",
+        "EventName": "BR_IND_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, predicted indirect branch"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, mispredicted indirect branch",
+        "EventCode": "0x8113",
+        "EventName": "BR_IND_MIS_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, mispredicted indirect branch"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, predicted procedure return",
+        "EventCode": "0x8114",
+        "EventName": "BR_RETURN_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, predicted procedure return"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, mispredicted procedure return",
+        "EventCode": "0x8115",
+        "EventName": "BR_RETURN_MIS_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, mispredicted procedure return"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, predicted indirect branch excluding return",
+        "EventCode": "0x8116",
+        "EventName": "BR_INDNR_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, predicted indirect branch excluding return"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, mispredicted indirect branch excluding return",
+        "EventCode": "0x8117",
+        "EventName": "BR_INDNR_MIS_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, mispredicted indirect branch excluding return"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, predicted branch, taken",
+        "EventCode": "0x8118",
+        "EventName": "BR_TAKEN_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, predicted branch, taken"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, mispredicted branch, taken",
+        "EventCode": "0x8119",
+        "EventName": "BR_TAKEN_MIS_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, mispredicted branch, taken"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, predicted branch, not taken",
+        "EventCode": "0x811a",
+        "EventName": "BR_SKIP_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, predicted branch, not taken"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, mispredicted branch, not taken",
+        "EventCode": "0x811b",
+        "EventName": "BR_SKIP_MIS_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, mispredicted branch, not taken"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, predicted branch",
+        "EventCode": "0x811c",
+        "EventName": "BR_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, predicted branch"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, indirect branch",
+        "EventCode": "0x811d",
+        "EventName": "BR_IND_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, indirect branch"
+    },
+    {
+        "PublicDescription": "Branch Record captured.",
+        "EventCode": "0x811f",
+        "EventName": "BRB_FILTRATE",
+        "BriefDescription": "Branch Record captured."
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/bus.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/bus.json
new file mode 100644
index 000000000000..2aeb9907831d
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/bus.json
@@ -0,0 +1,20 @@
+[
+    {
+        "ArchStdEvent": "CPU_CYCLES"
+    },
+    {
+        "ArchStdEvent": "BUS_CYCLES"
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_RD"
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_WR"
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS"
+    },
+    {
+        "ArchStdEvent": "CNT_CYCLES"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/cache.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/cache.json
new file mode 100644
index 000000000000..c50d8e930b05
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/cache.json
@@ -0,0 +1,206 @@
+[
+    {
+        "ArchStdEvent": "L1D_CACHE_RD"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WR"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_RD"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_INVAL"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_RD"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_WR"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_RD"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WR"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL_RD"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL_WR"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB_VICTIM"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB_CLEAN"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_INVAL"
+    },
+    {
+        "ArchStdEvent": "L1I_CACHE_REFILL"
+    },
+    {
+        "ArchStdEvent": "L1I_TLB_REFILL"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL"
+    },
+    {
+        "ArchStdEvent": "L1I_CACHE"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB"
+    },
+    {
+        "ArchStdEvent": "L1I_TLB"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL"
+    },
+    {
+        "ArchStdEvent": "L2I_TLB_REFILL"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB"
+    },
+    {
+        "ArchStdEvent": "L2I_TLB"
+    },
+    {
+        "ArchStdEvent": "DTLB_WALK"
+    },
+    {
+        "ArchStdEvent": "ITLB_WALK"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_WR"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_LMISS_RD"
+    },
+    {
+        "ArchStdEvent": "L1I_CACHE_LMISS"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_LMISS_RD"
+    },
+    {
+        "PublicDescription": "Level 1 data or unified cache demand access",
+        "EventCode": "0x8140",
+        "EventName": "L1D_CACHE_RW",
+        "BriefDescription": "Level 1 data or unified cache demand access"
+    },
+    {
+        "PublicDescription": "Level 1 data or unified cache preload or prefetch",
+        "EventCode": "0x8142",
+        "EventName": "L1D_CACHE_PRFM",
+        "BriefDescription": "Level 1 data or unified cache preload or prefetch"
+    },
+    {
+        "PublicDescription": "Level 1 data or unified cache refill, preload or prefetch",
+        "EventCode": "0x8146",
+        "EventName": "L1D_CACHE_REFILL_PRFM",
+        "BriefDescription": "Level 1 data or unified cache refill, preload or prefetch"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_RD"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_WR"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL_RD"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL_WR"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_RD"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_WR"
+    },
+    {
+        "PublicDescription": "L1D TLB miss",
+        "EventCode": "0xD600",
+        "EventName": "L1D_TLB_MISS",
+        "BriefDescription": "L1D TLB miss"
+    },
+    {
+        "PublicDescription": "Level 1 prefetcher, load prefetch requests generated",
+        "EventCode": "0xd606",
+        "EventName": "L1_PREFETCH_LD_GEN",
+        "BriefDescription": "Level 1 prefetcher, load prefetch requests generated"
+    },
+    {
+        "PublicDescription": "Level 1 prefetcher, load prefetch fills into the level 1 cache",
+        "EventCode": "0xd607",
+        "EventName": "L1_PREFETCH_LD_FILL",
+        "BriefDescription": "Level 1 prefetcher, load prefetch fills into the level 1 cache"
+    },
+    {
+        "PublicDescription": "Level 1 prefetcher, load prefetch to level 2 generated",
+        "EventCode": "0xd608",
+        "EventName": "L1_PREFETCH_L2_REQ",
+        "BriefDescription": "Level 1 prefetcher, load prefetch to level 2 generated"
+    },
+    {
+        "PublicDescription": "L1 prefetcher, distance was reset",
+        "EventCode": "0xd609",
+        "EventName": "L1_PREFETCH_DIST_RST",
+        "BriefDescription": "L1 prefetcher, distance was reset"
+    },
+    {
+        "PublicDescription": "L1 prefetcher, distance was increased",
+        "EventCode": "0xd60a",
+        "EventName": "L1_PREFETCH_DIST_INC",
+        "BriefDescription": "L1 prefetcher, distance was increased"
+    },
+    {
+        "PublicDescription": "Level 1 prefetcher, table entry is trained",
+        "EventCode": "0xd60b",
+        "EventName": "L1_PREFETCH_ENTRY_TRAINED",
+        "BriefDescription": "Level 1 prefetcher, table entry is trained"
+    },
+    {
+        "PublicDescription": "L1 data cache refill - Read or Write",
+        "EventCode": "0xd60e",
+        "EventName": "L1D_CACHE_REFILL_RW",
+        "BriefDescription": "L1 data cache refill - Read or Write"
+    },
+    {
+        "PublicDescription": "Level 2 cache refill from instruction-side miss, including IMMU refills",
+        "EventCode": "0xD701",
+        "EventName": "L2C_INST_REFILL",
+        "BriefDescription": "Level 2 cache refill from instruction-side miss, including IMMU refills"
+    },
+    {
+        "PublicDescription": "Level 2 cache refill from data-side miss, including DMMU refills",
+        "EventCode": "0xD702",
+        "EventName": "L2C_DATA_REFILL",
+        "BriefDescription": "Level 2 cache refill from data-side miss, including DMMU refills"
+    },
+    {
+        "PublicDescription": "Level 2 cache prefetcher, load prefetch requests generated",
+        "EventCode": "0xD703",
+        "EventName": "L2_PREFETCH_REQ",
+        "BriefDescription": "Level 2 cache prefetcher, load prefetch requests generated"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/core-imp-def.json
new file mode 100644
index 000000000000..eb5a2208d260
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/core-imp-def.json
@@ -0,0 +1,464 @@
+[
+    {
+        "PublicDescription": "Level 2 prefetch requests, refilled to L2 cache",
+        "EventCode": "0x10A",
+        "EventName": "L2_PREFETCH_REFILL",
+        "BriefDescription": "Level 2 prefetch requests, refilled to L2 cache"
+    },
+    {
+        "PublicDescription": "Level 2 prefetch requests, late",
+        "EventCode": "0x10B",
+        "EventName": "L2_PREFETCH_UPGRADE",
+        "BriefDescription": "Level 2 prefetch requests, late"
+    },
+    {
+        "PublicDescription": "Predictable branch speculatively executed that hit any level of BTB",
+        "EventCode": "0x110",
+        "EventName": "BPU_HIT_BTB",
+        "BriefDescription": "Predictable branch speculatively executed that hit any level of BTB"
+    },
+    {
+        "PublicDescription": "Predictable conditional branch speculatively executed that hit any level of BTB",
+        "EventCode": "0x111",
+        "EventName": "BPU_CONDITIONAL_BRANCH_HIT_BTB",
+        "BriefDescription": "Predictable conditional branch speculatively executed that hit any level of BTB"
+    },
+    {
+        "PublicDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the indirect predictor",
+        "EventCode": "0x112",
+        "EventName": "BPU_HIT_INDIRECT_PREDICTOR",
+        "BriefDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the indirect predictor"
+    },
+    {
+        "PublicDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the return predictor",
+        "EventCode": "0x113",
+        "EventName": "BPU_HIT_RSB",
+        "BriefDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the return predictor"
+    },
+    {
+        "PublicDescription": "Predictable unconditional branch speculatively executed that did not hit any level of BTB",
+        "EventCode": "0x114",
+        "EventName": "BPU_UNCONDITIONAL_BRANCH_MISS_BTB",
+        "BriefDescription": "Predictable unconditional branch speculatively executed that did not hit any level of BTB"
+    },
+    {
+        "PublicDescription": "Predictable branch speculatively executed, unpredicted",
+        "EventCode": "0x115",
+        "EventName": "BPU_BRANCH_NO_HIT",
+        "BriefDescription": "Predictable branch speculatively executed, unpredicted"
+    },
+    {
+        "PublicDescription": "Predictable branch speculatively executed that hit any level of BTB that mispredict",
+        "EventCode": "0x116",
+        "EventName": "BPU_HIT_BTB_AND_MISPREDICT",
+        "BriefDescription": "Predictable branch speculatively executed that hit any level of BTB that mispredict"
+    },
+    {
+        "PublicDescription": "Predictable conditional branch speculatively executed that hit any level of BTB that (direction) mispredict",
+        "EventCode": "0x117",
+        "EventName": "BPU_CONDITIONAL_BRANCH_HIT_BTB_AND_MISPREDICT",
+        "BriefDescription": "Predictable conditional branch speculatively executed that hit any level of BTB that (direction) mispredict"
+    },
+    {
+        "PublicDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the indirect predictor that mispredict",
+        "EventCode": "0x118",
+        "EventName": "BPU_INDIRECT_BRANCH_HIT_BTB_AND_MISPREDICT",
+        "BriefDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the indirect predictor that mispredict"
+    },
+    {
+        "PublicDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the return predictor that mispredict",
+        "EventCode": "0x119",
+        "EventName": "BPU_HIT_RSB_AND_MISPREDICT",
+        "BriefDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the return predictor that mispredict"
+    },
+    {
+        "PublicDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the overflow/underflow return predictor that mispredict",
+        "EventCode": "0x11a",
+        "EventName": "BPU_MISS_RSB_AND_MISPREDICT",
+        "BriefDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the overflow/underflow return predictor that mispredict"
+    },
+    {
+        "PublicDescription": "Predictable branch speculatively executed, unpredicted, that mispredict",
+        "EventCode": "0x11b",
+        "EventName": "BPU_NO_PREDICTION_MISPREDICT",
+        "BriefDescription": "Predictable branch speculatively executed, unpredicted, that mispredict"
+    },
+    {
+        "PublicDescription": "Preditable branch update the BTB region buffer entry",
+        "EventCode": "0x11c",
+        "EventName": "BPU_BTB_UPDATE",
+        "BriefDescription": "Preditable branch update the BTB region buffer entry"
+    },
+    {
+        "PublicDescription": "Count predict pipe stalls due to speculative return address predictor full",
+        "EventCode": "0x11d",
+        "EventName": "BPU_RSB_FULL_STALL",
+        "BriefDescription": "Count predict pipe stalls due to speculative return address predictor full"
+    },
+    {
+        "PublicDescription": "Macro-ops speculatively decoded",
+        "EventCode": "0x11f",
+        "EventName": "ICF_INST_SPEC_DECODE",
+        "BriefDescription": "Macro-ops speculatively decoded"
+    },
+    {
+        "PublicDescription": "Flushes",
+        "EventCode": "0x120",
+        "EventName": "GPC_FLUSH",
+        "BriefDescription": "Flushes"
+    },
+    {
+        "PublicDescription": "Flushes due to memory hazards",
+        "EventCode": "0x121",
+        "EventName": "GPC_FLUSH_MEM_FAULT",
+        "BriefDescription": "Flushes due to memory hazards"
+    },
+    {
+        "PublicDescription": "ETM extout bit 0",
+        "EventCode": "0x141",
+        "EventName": "MSC_ETM_EXTOUT0",
+        "BriefDescription": "ETM extout bit 0"
+    },
+    {
+        "PublicDescription": "ETM extout bit 1",
+        "EventCode": "0x142",
+        "EventName": "MSC_ETM_EXTOUT1",
+        "BriefDescription": "ETM extout bit 1"
+    },
+    {
+        "PublicDescription": "ETM extout bit 2",
+        "EventCode": "0x143",
+        "EventName": "MSC_ETM_EXTOUT2",
+        "BriefDescription": "ETM extout bit 2"
+    },
+    {
+        "PublicDescription": "ETM extout bit 3",
+        "EventCode": "0x144",
+        "EventName": "MSC_ETM_EXTOUT3",
+        "BriefDescription": "ETM extout bit 3"
+    },
+    {
+        "PublicDescription": "Bus request sn",
+        "EventCode": "0x156",
+        "EventName": "L2C_SNOOP",
+        "BriefDescription": "Bus request sn"
+    },
+    {
+        "PublicDescription": "L2 TXDAT LCRD blocked",
+        "EventCode": "0x169",
+        "EventName": "L2C_DAT_CRD_STALL",
+        "BriefDescription": "L2 TXDAT LCRD blocked"
+    },
+    {
+        "PublicDescription": "L2 TXRSP LCRD blocked",
+        "EventCode": "0x16a",
+        "EventName": "L2C_RSP_CRD_STALL",
+        "BriefDescription": "L2 TXRSP LCRD blocked"
+    },
+    {
+        "PublicDescription": "L2 TXREQ LCRD blocked",
+        "EventCode": "0x16b",
+        "EventName": "L2C_REQ_CRD_STALL",
+        "BriefDescription": "L2 TXREQ LCRD blocked"
+    },
+    {
+        "PublicDescription": "Early mispredict",
+        "EventCode": "0xD100",
+        "EventName": "ICF_EARLY_MIS_PRED",
+        "BriefDescription": "Early mispredict"
+    },
+    {
+        "PublicDescription": "FEQ full cycles",
+        "EventCode": "0xD101",
+        "EventName": "ICF_FEQ_FULL",
+        "BriefDescription": "FEQ full cycles"
+    },
+    {
+        "PublicDescription": "Instruction FIFO Full",
+        "EventCode": "0xD102",
+        "EventName": "ICF_INST_FIFO_FULL",
+        "BriefDescription": "Instruction FIFO Full"
+    },
+    {
+        "PublicDescription": "L1I TLB miss",
+        "EventCode": "0xD103",
+        "EventName": "L1I_TLB_MISS",
+        "BriefDescription": "L1I TLB miss"
+    },
+    {
+        "PublicDescription": "ICF sent 0 instructions to IDR this cycle",
+        "EventCode": "0xD104",
+        "EventName": "ICF_STALL",
+        "BriefDescription": "ICF sent 0 instructions to IDR this cycle"
+    },
+    {
+        "PublicDescription": "PC FIFO Full",
+        "EventCode": "0xD105",
+        "EventName": "ICF_PC_FIFO_FULL",
+        "BriefDescription": "PC FIFO Full"
+    },
+    {
+        "PublicDescription": "Stall due to BOB ID",
+        "EventCode": "0xD200",
+        "EventName": "IDR_STALL_BOB_ID",
+        "BriefDescription": "Stall due to BOB ID"
+    },
+    {
+        "PublicDescription": "Dispatch stall due to LOB entries",
+        "EventCode": "0xD201",
+        "EventName": "IDR_STALL_LOB_ID",
+        "BriefDescription": "Dispatch stall due to LOB entries"
+    },
+    {
+        "PublicDescription": "Dispatch stall due to SOB entries",
+        "EventCode": "0xD202",
+        "EventName": "IDR_STALL_SOB_ID",
+        "BriefDescription": "Dispatch stall due to SOB entries"
+    },
+    {
+        "PublicDescription": "Dispatch stall due to IXU scheduler entries",
+        "EventCode": "0xD203",
+        "EventName": "IDR_STALL_IXU_SCHED",
+        "BriefDescription": "Dispatch stall due to IXU scheduler entries"
+    },
+    {
+        "PublicDescription": "Dispatch stall due to FSU scheduler entries",
+        "EventCode": "0xD204",
+        "EventName": "IDR_STALL_FSU_SCHED",
+        "BriefDescription": "Dispatch stall due to FSU scheduler entries"
+    },
+    {
+        "PublicDescription": "Dispatch stall due to ROB entries",
+        "EventCode": "0xD205",
+        "EventName": "IDR_STALL_ROB_ID",
+        "BriefDescription": "Dispatch stall due to ROB entries"
+    },
+    {
+        "PublicDescription": "Dispatch stall due to flush",
+        "EventCode": "0xD206",
+        "EventName": "IDR_STALL_FLUSH",
+        "BriefDescription": "Dispatch stall due to flush"
+    },
+    {
+        "PublicDescription": "Dispatch stall due to WFI",
+        "EventCode": "0xD207",
+        "EventName": "IDR_STALL_WFI",
+        "BriefDescription": "Dispatch stall due to WFI"
+    },
+    {
+        "PublicDescription": "Number of SWOB drains triggered by timeout",
+        "EventCode": "0xD208",
+        "EventName": "IDR_STALL_SWOB_TIMEOUT",
+        "BriefDescription": "Number of SWOB drains triggered by timeout"
+    },
+    {
+        "PublicDescription": "Number of SWOB drains triggered by system register or special-purpose register read-after-write or specific special-purpose register writes that cause SWOB drain",
+        "EventCode": "0xD209",
+        "EventName": "IDR_STALL_SWOB_RAW",
+        "BriefDescription": "Number of SWOB drains triggered by system register or special-purpose register read-after-write or specific special-purpose register writes that cause SWOB drain"
+    },
+    {
+        "PublicDescription": "Number of SWOB drains triggered by system register write when SWOB full",
+        "EventCode": "0xD20A",
+        "EventName": "IDR_STALL_SWOB_FULL",
+        "BriefDescription": "Number of SWOB drains triggered by system register write when SWOB full"
+    },
+    {
+        "PublicDescription": "Dispatch stall due to L1 instruction cache miss",
+        "EventCode": "0xD20B",
+        "EventName": "STALL_FRONTEND_CACHE",
+        "BriefDescription": "Dispatch stall due to L1 instruction cache miss"
+    },
+    {
+        "PublicDescription": "Dispatch stall due to L1 data cache miss",
+        "EventCode": "0xD20D",
+        "EventName": "STALL_BACKEND_CACHE",
+        "BriefDescription": "Dispatch stall due to L1 data cache miss"
+    },
+    {
+        "PublicDescription": "Dispatch stall due to lack of any core resource",
+        "EventCode": "0xD20F",
+        "EventName": "STALL_BACKEND_RESOURCE",
+        "BriefDescription": "Dispatch stall due to lack of any core resource"
+    },
+    {
+        "PublicDescription": "Instructions issued by the scheduler",
+        "EventCode": "0xD300",
+        "EventName": "IXU_NUM_UOPS_ISSUED",
+        "BriefDescription": "Instructions issued by the scheduler"
+    },
+    {
+        "PublicDescription": "Any uop issued was canceled for any reason",
+        "EventCode": "0xD301",
+        "EventName": "IXU_ISSUE_CANCEL",
+        "BriefDescription": "Any uop issued was canceled for any reason"
+    },
+    {
+        "PublicDescription": "A load wakeup to the scheduler has been canceled",
+        "EventCode": "0xD302",
+        "EventName": "IXU_LOAD_CANCEL",
+        "BriefDescription": "A load wakeup to the scheduler has been canceled"
+    },
+    {
+        "PublicDescription": "The scheduler had to cancel one slow Uop due to resource conflict",
+        "EventCode": "0xD303",
+        "EventName": "IXU_SLOW_CANCEL",
+        "BriefDescription": "The scheduler had to cancel one slow Uop due to resource conflict"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXA",
+        "EventCode": "0xD304",
+        "EventName": "IXU_IXA_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXA"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXA Par 0",
+        "EventCode": "0xD305",
+        "EventName": "IXU_IXA_PAR0_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXA Par 0"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXA Par 1",
+        "EventCode": "0xD306",
+        "EventName": "IXU_IXA_PAR1_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXA Par 1"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXB",
+        "EventCode": "0xD307",
+        "EventName": "IXU_IXB_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXB"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXB Par 0",
+        "EventCode": "0xD308",
+        "EventName": "IXU_IXB_PAR0_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXB Par 0"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXB Par 1",
+        "EventCode": "0xD309",
+        "EventName": "IXU_IXB_PAR1_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXB Par 1"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXC",
+        "EventCode": "0xD30A",
+        "EventName": "IXU_IXC_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXC"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXC Par 0",
+        "EventCode": "0xD30B",
+        "EventName": "IXU_IXC_PAR0_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXC Par 0"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXC Par 1",
+        "EventCode": "0xD30C",
+        "EventName": "IXU_IXC_PAR1_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXC Par 1"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXD",
+        "EventCode": "0xD30D",
+        "EventName": "IXU_IXD_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXD"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXD Par 0",
+        "EventCode": "0xD30E",
+        "EventName": "IXU_IXD_PAR0_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXD Par 0"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXD Par 1",
+        "EventCode": "0xD30F",
+        "EventName": "IXU_IXD_PAR1_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXD Par 1"
+    },
+    {
+        "PublicDescription": "Uops issued by the FSU scheduler",
+        "EventCode": "0xD400",
+        "EventName": "FSU_ISSUED",
+        "BriefDescription": "Uops issued by the FSU scheduler"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on FSX",
+        "EventCode": "0xD401",
+        "EventName": "FSU_FSX_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on FSX"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on FSY",
+        "EventCode": "0xD402",
+        "EventName": "FSU_FSY_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on FSY"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on FSZ",
+        "EventCode": "0xD403",
+        "EventName": "FSU_FSZ_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on FSZ"
+    },
+    {
+        "PublicDescription": "Uops canceled (load cancels)",
+        "EventCode": "0xD404",
+        "EventName": "FSU_CANCEL",
+        "BriefDescription": "Uops canceled (load cancels)"
+    },
+    {
+        "PublicDescription": "Count scheduler stalls due to divide/sqrt",
+        "EventCode": "0xD405",
+        "EventName": "FSU_DIV_SQRT_STALL",
+        "BriefDescription": "Count scheduler stalls due to divide/sqrt"
+    },
+    {
+        "PublicDescription": "Number of SWOB drains",
+        "EventCode": "0xD500",
+        "EventName": "GPC_SWOB_DRAIN",
+        "BriefDescription": "Number of SWOB drains"
+    },
+    {
+        "PublicDescription": "GPC detected a Breakpoint instruction match",
+        "EventCode": "0xD501",
+        "EventName": "BREAKPOINT_MATCH",
+        "BriefDescription": "GPC detected a Breakpoint instruction match"
+    },
+    {
+        "PublicDescription": "Core progress monitor triggered",
+        "EventCode": "0xd502",
+        "EventName": "GPC_CPM_TRIGGER",
+        "BriefDescription": "Core progress monitor triggered"
+    },
+    {
+        "PublicDescription": "Fill buffer full",
+        "EventCode": "0xD601",
+        "EventName": "OFB_FULL",
+        "BriefDescription": "Fill buffer full"
+    },
+    {
+        "PublicDescription": "Load satisified from store forwarded data",
+        "EventCode": "0xD605",
+        "EventName": "LD_FROM_ST_FWD",
+        "BriefDescription": "Load satisified from store forwarded data"
+    },
+    {
+        "PublicDescription": "Store retirement pipe stall",
+        "EventCode": "0xD60C",
+        "EventName": "LSU_ST_RETIRE_STALL",
+        "BriefDescription": "Store retirement pipe stall"
+    },
+    {
+        "PublicDescription": "LSU detected a Watchpoint data match",
+        "EventCode": "0xD60D",
+        "EventName": "WATCHPOINT_MATCH",
+        "BriefDescription": "LSU detected a Watchpoint data match"
+    },
+    {
+        "PublicDescription": "Counts cycles that MSC is telling GPC to stall commit due to ETM ISTALL feature",
+        "EventCode": "0xda00",
+        "EventName": "MSC_ETM_COMMIT_STALL",
+        "BriefDescription": "Counts cycles that MSC is telling GPC to stall commit due to ETM ISTALL feature"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/exception.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/exception.json
new file mode 100644
index 000000000000..bd59ba7b74e4
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/exception.json
@@ -0,0 +1,47 @@
+[
+    {
+        "ArchStdEvent": "EXC_UNDEF"
+    },
+    {
+        "ArchStdEvent": "EXC_SVC"
+    },
+    {
+        "ArchStdEvent": "EXC_PABORT"
+    },
+    {
+        "ArchStdEvent": "EXC_DABORT"
+    },
+    {
+        "ArchStdEvent": "EXC_IRQ"
+    },
+    {
+        "ArchStdEvent": "EXC_FIQ"
+    },
+    {
+        "ArchStdEvent": "EXC_HVC"
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_PABORT"
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_DABORT"
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_OTHER"
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_IRQ"
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_FIQ"
+    },
+    {
+        "ArchStdEvent": "EXC_TAKEN"
+    },
+    {
+        "ArchStdEvent": "EXC_RETURN"
+    },
+    {
+        "ArchStdEvent": "EXC_SMC"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/instruction.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/instruction.json
new file mode 100644
index 000000000000..a6a20f541e33
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/instruction.json
@@ -0,0 +1,128 @@
+[
+    {
+        "ArchStdEvent": "SW_INCR"
+    },
+    {
+        "ArchStdEvent": "ST_RETIRED"
+    },
+    {
+        "ArchStdEvent": "LD_SPEC"
+    },
+    {
+        "ArchStdEvent": "ST_SPEC"
+    },
+    {
+        "ArchStdEvent": "LDST_SPEC"
+    },
+    {
+        "ArchStdEvent": "DP_SPEC"
+    },
+    {
+        "ArchStdEvent": "ASE_SPEC"
+    },
+    {
+        "ArchStdEvent": "VFP_SPEC"
+    },
+    {
+        "ArchStdEvent": "PC_WRITE_SPEC"
+    },
+    {
+        "ArchStdEvent": "BR_IMMED_RETIRED"
+    },
+    {
+        "ArchStdEvent": "BR_RETURN_RETIRED"
+    },
+    {
+        "ArchStdEvent": "CRYPTO_SPEC"
+    },
+    {
+        "ArchStdEvent": "ISB_SPEC"
+    },
+    {
+        "ArchStdEvent": "DSB_SPEC"
+    },
+    {
+        "ArchStdEvent": "DMB_SPEC"
+    },
+    {
+        "ArchStdEvent": "RC_LD_SPEC"
+    },
+    {
+        "ArchStdEvent": "RC_ST_SPEC"
+    },
+    {
+        "ArchStdEvent": "INST_RETIRED"
+    },
+    {
+        "ArchStdEvent": "CID_WRITE_RETIRED"
+    },
+    {
+        "ArchStdEvent": "PC_WRITE_RETIRED"
+    },
+    {
+        "ArchStdEvent": "INST_SPEC"
+    },
+    {
+        "ArchStdEvent": "TTBR_WRITE_RETIRED"
+    },
+    {
+        "ArchStdEvent": "BR_RETIRED"
+    },
+    {
+        "ArchStdEvent": "BR_MIS_PRED_RETIRED"
+    },
+    {
+        "ArchStdEvent": "OP_RETIRED"
+    },
+    {
+        "ArchStdEvent": "OP_SPEC"
+    },
+    {
+        "PublicDescription": "Operation speculatively executed - ASE Scalar",
+        "EventCode": "0xd210",
+        "EventName": "ASE_SCALAR_SPEC",
+        "BriefDescription": "Operation speculatively executed - ASE Scalar"
+    },
+    {
+        "PublicDescription": "Operation speculatively executed - ASE Vector",
+        "EventCode": "0xd211",
+        "EventName": "ASE_VECTOR_SPEC",
+        "BriefDescription": "Operation speculatively executed - ASE Vector"
+    },
+    {
+        "PublicDescription": "Barrier speculatively executed, CSDB",
+        "EventCode": "0x7f",
+        "EventName": "CSDB_SPEC",
+        "BriefDescription": "Barrier speculatively executed, CSDB"
+    },
+    {
+        "PublicDescription": "Prefetch sent to L2.",
+        "EventCode": "0xd106",
+        "EventName": "ICF_PREFETCH_DISPATCH",
+        "BriefDescription": "Prefetch sent to L2."
+    },
+    {
+        "PublicDescription": "Prefetch response received but was dropped since we don't support inflight upgrades.",
+        "EventCode": "0xd107",
+        "EventName": "ICF_PREFETCH_DROPPED_NO_UPGRADE",
+        "BriefDescription": "Prefetch response received but was dropped since we don't support inflight upgrades."
+    },
+    {
+        "PublicDescription": "Prefetch request missed TLB.",
+        "EventCode": "0xd108",
+        "EventName": "ICF_PREFETCH_DROPPED_TLB_MISS",
+        "BriefDescription": "Prefetch request missed TLB."
+    },
+    {
+        "PublicDescription": "Prefetch request dropped since duplicate was found in TLB.",
+        "EventCode": "0xd109",
+        "EventName": "ICF_PREFETCH_DROPPED_DUPLICATE",
+        "BriefDescription": "Prefetch request dropped since duplicate was found in TLB."
+    },
+    {
+        "PublicDescription": "Prefetch request dropped since it was found in cache.",
+        "EventCode": "0xd10a",
+        "EventName": "ICF_PREFETCH_DROPPED_CACHE_HIT",
+        "BriefDescription": "Prefetch request dropped since it was found in cache."
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/intrinsic.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/intrinsic.json
new file mode 100644
index 000000000000..7ecffb989ae0
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/intrinsic.json
@@ -0,0 +1,14 @@
+[
+    {
+        "ArchStdEvent": "LDREX_SPEC"
+    },
+    {
+        "ArchStdEvent": "STREX_PASS_SPEC"
+    },
+    {
+        "ArchStdEvent": "STREX_FAIL_SPEC"
+    },
+    {
+        "ArchStdEvent": "STREX_SPEC"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/memory.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/memory.json
new file mode 100644
index 000000000000..a211d94aacde
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/memory.json
@@ -0,0 +1,41 @@
+[
+    {
+        "ArchStdEvent": "LD_RETIRED"
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_RD"
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_WR"
+    },
+    {
+        "ArchStdEvent": "LD_ALIGN_LAT"
+    },
+    {
+        "ArchStdEvent": "ST_ALIGN_LAT"
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS"
+    },
+    {
+        "ArchStdEvent": "MEMORY_ERROR"
+    },
+    {
+        "ArchStdEvent": "LDST_ALIGN_LAT"
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_CHECKED"
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_CHECKED_RD"
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_CHECKED_WR"
+    },
+    {
+        "PublicDescription": "Flushes due to memory hazards",
+        "EventCode": "0x121",
+        "EventName": "BPU_FLUSH_MEM_FAULT",
+        "BriefDescription": "Flushes due to memory hazards"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json
new file mode 100644
index 000000000000..c5d1d22bd034
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json
@@ -0,0 +1,442 @@
+[
+    {
+        "MetricName": "branch_miss_pred_rate",
+        "MetricExpr": "BR_MIS_PRED / BR_PRED",
+        "BriefDescription": "Branch predictor misprediction rate. May not count branches that are never resolved because they are in the misprediction shadow of an earlier branch",
+        "MetricGroup": "branch",
+        "ScaleUnit": "100%"
+    },
+    {
+        "MetricName": "bus_utilization",
+        "MetricExpr": "BUS_ACCESS / (BUS_CYCLES * 1)",
+        "BriefDescription": "Core-to-uncore bus utilization",
+        "MetricGroup": "Bus",
+        "ScaleUnit": "100percent of bus cycles"
+    },
+    {
+        "MetricName": "l1d_cache_miss_ratio",
+        "MetricExpr": "L1D_CACHE_REFILL / L1D_CACHE",
+        "BriefDescription": "This metric measures the ratio of level 1 data cache accesses missed to the total number of level 1 data cache accesses. This gives an indication of the effectiveness of the level 1 data cache.",
+        "MetricGroup": "Miss_Ratio;L1D_Cache_Effectiveness",
+        "ScaleUnit": "1per cache access"
+    },
+    {
+        "MetricName": "l1i_cache_miss_ratio",
+        "MetricExpr": "L1I_CACHE_REFILL / L1I_CACHE",
+        "BriefDescription": "This metric measures the ratio of level 1 instruction cache accesses missed to the total number of level 1 instruction cache accesses. This gives an indication of the effectiveness of the level 1 instruction cache.",
+        "MetricGroup": "Miss_Ratio;L1I_Cache_Effectiveness",
+        "ScaleUnit": "1per cache access"
+    },
+    {
+        "MetricName": "Miss_Ratio;l1d_cache_read_miss",
+        "MetricExpr": "L1D_CACHE_LMISS_RD / L1D_CACHE_RD",
+        "BriefDescription": "L1D cache read miss rate",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "1per cache read access"
+    },
+    {
+        "MetricName": "l2_cache_miss_ratio",
+        "MetricExpr": "L2D_CACHE_REFILL / L2D_CACHE",
+        "BriefDescription": "This metric measures the ratio of level 2 cache accesses missed to the total number of level 2 cache accesses. This gives an indication of the effectiveness of the level 2 cache, which is a unified cache that stores both data and instruction. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.",
+        "MetricGroup": "Miss_Ratio;L2_Cache_Effectiveness",
+        "ScaleUnit": "1per cache access"
+    },
+    {
+        "MetricName": "l1i_cache_read_miss_rate",
+        "MetricExpr": "L1I_CACHE_LMISS / L1I_CACHE",
+        "BriefDescription": "L1I cache read miss rate",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "1per cache access"
+    },
+    {
+        "MetricName": "l2d_cache_read_miss_rate",
+        "MetricExpr": "L2D_CACHE_LMISS_RD / L2D_CACHE_RD",
+        "BriefDescription": "L2 cache read miss rate",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "1per cache read access"
+    },
+    {
+        "MetricName": "l1d_cache_miss_mpki",
+        "MetricExpr": "(L1D_CACHE_LMISS_RD * 1e3) / INST_RETIRED",
+        "BriefDescription": "Misses per thousand instructions (data)",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "1MPKI"
+    },
+    {
+        "MetricName": "l1i_cache_miss_mpki",
+        "MetricExpr": "(L1I_CACHE_LMISS * 1e3) / INST_RETIRED",
+        "BriefDescription": "Misses per thousand instructions (instruction)",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "1MPKI"
+    },
+    {
+        "MetricName": "simd_percentage",
+        "MetricExpr": "ASE_SPEC / INST_SPEC",
+        "BriefDescription": "This metric measures advanced SIMD operations as a percentage of total operations speculatively executed.",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "100percent of operations"
+    },
+    {
+        "MetricName": "crypto_percentage",
+        "MetricExpr": "CRYPTO_SPEC / INST_SPEC",
+        "BriefDescription": "This metric measures crypto operations as a percentage of operations speculatively executed.",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "100percent of operations"
+    },
+    {
+        "MetricName": "gflops",
+        "MetricExpr": "VFP_SPEC / (duration_time * 1e9)",
+        "BriefDescription": "Giga-floating point operations per second",
+        "MetricGroup": "InstructionMix"
+    },
+    {
+        "MetricName": "integer_dp_percentage",
+        "MetricExpr": "DP_SPEC / INST_SPEC",
+        "BriefDescription": "This metric measures scalar integer operations as a percentage of operations speculatively executed.",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "100percent of operations"
+    },
+    {
+        "MetricName": "ipc",
+        "MetricExpr": "INST_RETIRED / CPU_CYCLES",
+        "BriefDescription": "This metric measures the number of instructions retired per cycle.",
+        "MetricGroup": "General",
+        "ScaleUnit": "1per cycle"
+    },
+    {
+        "MetricName": "load_percentage",
+        "MetricExpr": "LD_SPEC / INST_SPEC",
+        "BriefDescription": "This metric measures load operations as a percentage of operations speculatively executed.",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "100percent of operations"
+    },
+    {
+        "MetricName": "load_store_spec_rate",
+        "MetricExpr": "LDST_SPEC / INST_SPEC",
+        "BriefDescription": "The rate of load or store instructions speculatively executed to overall instructions speclatively executed",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "100percent of operations"
+    },
+    {
+        "MetricName": "retired_mips",
+        "MetricExpr": "INST_RETIRED / (duration_time * 1e6)",
+        "BriefDescription": "Millions of instructions per second",
+        "MetricGroup": "InstructionMix"
+    },
+    {
+        "MetricName": "spec_utilization_mips",
+        "MetricExpr": "INST_SPEC / (duration_time * 1e6)",
+        "BriefDescription": "Millions of instructions per second",
+        "MetricGroup": "PEutilization"
+    },
+    {
+        "MetricName": "pc_write_spec_rate",
+        "MetricExpr": "PC_WRITE_SPEC / INST_SPEC",
+        "BriefDescription": "The rate of software change of the PC speculatively executed to overall instructions speclatively executed",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "100percent of operations"
+    },
+    {
+        "MetricName": "store_percentage",
+        "MetricExpr": "ST_SPEC / INST_SPEC",
+        "BriefDescription": "This metric measures store operations as a percentage of operations speculatively executed.",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "100percent of operations"
+    },
+    {
+        "MetricName": "scalar_fp_percentage",
+        "MetricExpr": "VFP_SPEC / INST_SPEC",
+        "BriefDescription": "This metric measures scalar floating point operations as a percentage of operations speculatively executed.",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "100percent of operations"
+    },
+    {
+        "MetricName": "retired_rate",
+        "MetricExpr": "OP_RETIRED / OP_SPEC",
+        "BriefDescription": "Of all the micro-operations issued, what percentage are retired(committed)",
+        "MetricGroup": "General",
+        "ScaleUnit": "100%"
+    },
+    {
+        "MetricName": "wasted",
+        "MetricExpr": "1 - (OP_RETIRED / (CPU_CYCLES * #slots))",
+        "BriefDescription": "Of all the micro-operations issued, what proportion are lost",
+        "MetricGroup": "General",
+        "ScaleUnit": "100%"
+    },
+    {
+        "MetricName": "wasted_rate",
+        "MetricExpr": "1 - OP_RETIRED / OP_SPEC",
+        "BriefDescription": "Of all the micro-operations issued, what percentage are not retired(committed)",
+        "MetricGroup": "General",
+        "ScaleUnit": "100%"
+    },
+    {
+        "MetricName": "stall_backend_cache_rate",
+        "MetricExpr": "STALL_BACKEND_CACHE / CPU_CYCLES",
+        "BriefDescription": "Proportion of cycles stalled and no operations issued to backend and cache miss",
+        "MetricGroup": "Stall",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "stall_backend_resource_rate",
+        "MetricExpr": "STALL_BACKEND_RESOURCE / CPU_CYCLES",
+        "BriefDescription": "Proportion of cycles stalled and no operations issued to backend and resource full",
+        "MetricGroup": "Stall",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "stall_backend_tlb_rate",
+        "MetricExpr": "STALL_BACKEND_TLB / CPU_CYCLES",
+        "BriefDescription": "Proportion of cycles stalled and no operations issued to backend and TLB miss",
+        "MetricGroup": "Stall",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "stall_frontend_cache_rate",
+        "MetricExpr": "STALL_FRONTEND_CACHE / CPU_CYCLES",
+        "BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and cache miss",
+        "MetricGroup": "Stall",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "stall_frontend_tlb_rate",
+        "MetricExpr": "STALL_FRONTEND_TLB / CPU_CYCLES",
+        "BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and TLB miss",
+        "MetricGroup": "Stall",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "dtlb_walk_ratio",
+        "MetricExpr": "DTLB_WALK / L1D_TLB",
+        "BriefDescription": "This metric measures the ratio of data TLB Walks to the total number of data TLB accesses. This gives an indication of the effectiveness of the data TLB accesses.",
+        "MetricGroup": "Miss_Ratio;DTLB_Effectiveness",
+        "ScaleUnit": "1per TLB access"
+    },
+    {
+        "MetricName": "itlb_walk_ratio",
+        "MetricExpr": "ITLB_WALK / L1I_TLB",
+        "BriefDescription": "This metric measures the ratio of instruction TLB Walks to the total number of instruction TLB accesses. This gives an indication of the effectiveness of the instruction TLB accesses.",
+        "MetricGroup": "Miss_Ratio;ITLB_Effectiveness",
+        "ScaleUnit": "1per TLB access"
+    },
+    {
+        "ArchStdEvent": "backend_bound"
+    },
+    {
+        "ArchStdEvent": "frontend_bound",
+        "MetricExpr": "100 - (retired_fraction + slots_lost_misspeculation_fraction + backend_bound)"
+    },
+    {
+        "MetricName": "slots_lost_misspeculation_fraction",
+        "MetricExpr": "(OP_SPEC - OP_RETIRED) / (CPU_CYCLES * #slots)",
+        "BriefDescription": "Fraction of slots lost due to misspeculation",
+        "DefaultMetricgroupName": "TopdownL1",
+        "MetricGroup": "Default;TopdownL1",
+        "ScaleUnit": "100percent of slots"
+    },
+    {
+        "MetricName": "retired_fraction",
+        "MetricExpr": "OP_RETIRED / (CPU_CYCLES * #slots)",
+        "BriefDescription": "Fraction of slots retiring, useful work",
+        "DefaultMetricgroupName": "TopdownL1",
+        "MetricGroup": "Default;TopdownL1",
+        "ScaleUnit": "100percent of slots"
+    },
+    {
+        "MetricName": "backend_core",
+        "MetricExpr": "(backend_bound / 100) - backend_memory",
+        "BriefDescription": "Fraction of slots the CPU was stalled due to backend non-memory subsystem issues",
+        "MetricGroup": "TopdownL2",
+        "ScaleUnit": "100%"
+    },
+    {
+        "MetricName": "backend_memory",
+        "MetricExpr": "(STALL_BACKEND_TLB + STALL_BACKEND_CACHE) / CPU_CYCLES",
+        "BriefDescription": "Fraction of slots the CPU was stalled due to backend memory subsystem issues (cache/tlb miss)",
+        "MetricGroup": "TopdownL2",
+        "ScaleUnit": "100%"
+    },
+    {
+        "MetricName": "branch_mispredict",
+        "MetricExpr": "(BR_MIS_PRED_RETIRED / GPC_FLUSH) * slots_lost_misspeculation_fraction",
+        "BriefDescription": "Fraction of slots lost due to branch misprediciton",
+        "MetricGroup": "TopdownL2",
+        "ScaleUnit": "1percent of slots"
+    },
+    {
+        "MetricName": "frontend_bandwidth",
+        "MetricExpr": "frontend_bound - frontend_latency",
+        "BriefDescription": "Fraction of slots the CPU did not dispatch at full bandwidth - able to dispatch partial slots only (1, 2, or 3 uops)",
+        "MetricGroup": "TopdownL2",
+        "ScaleUnit": "1percent of slots"
+    },
+    {
+        "MetricName": "frontend_latency",
+        "MetricExpr": "(STALL_FRONTEND - ((STALL_SLOT_FRONTEND - ((frontend_bound / 100) * CPU_CYCLES * #slots)) / #slots)) / CPU_CYCLES",
+        "BriefDescription": "Fraction of slots the CPU was stalled due to frontend latency issues (cache/tlb miss); nothing to dispatch",
+        "MetricGroup": "TopdownL2",
+        "ScaleUnit": "100percent of slots"
+    },
+    {
+        "MetricName": "other_miss_pred",
+        "MetricExpr": "slots_lost_misspeculation_fraction - branch_mispredict",
+        "BriefDescription": "Fraction of slots lost due to other/non-branch misprediction misspeculation",
+        "MetricGroup": "TopdownL2",
+        "ScaleUnit": "1percent of slots"
+    },
+    {
+        "MetricName": "pipe_utilization",
+        "MetricExpr": "100 * ((IXU_NUM_UOPS_ISSUED + FSU_ISSUED) / (CPU_CYCLES * 6))",
+        "BriefDescription": "Fraction of execute slots utilized",
+        "MetricGroup": "TopdownL2",
+        "ScaleUnit": "1percent of slots"
+    },
+    {
+        "MetricName": "d_cache_l2_miss_rate",
+        "MetricExpr": "STALL_BACKEND_MEM / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled due to data L2 cache miss",
+        "MetricGroup": "TopdownL3",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "d_cache_miss_rate",
+        "MetricExpr": "STALL_BACKEND_CACHE / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled due to data cache miss",
+        "MetricGroup": "TopdownL3",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "d_tlb_miss_rate",
+        "MetricExpr": "STALL_BACKEND_TLB / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled due to data TLB miss",
+        "MetricGroup": "TopdownL3",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "fsu_pipe_utilization",
+        "MetricExpr": "FSU_ISSUED / (CPU_CYCLES * 2)",
+        "BriefDescription": "Fraction of FSU execute slots utilized",
+        "MetricGroup": "TopdownL3",
+        "ScaleUnit": "100percent of slots"
+    },
+    {
+        "MetricName": "i_cache_miss_rate",
+        "MetricExpr": "STALL_FRONTEND_CACHE / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled due to instruction cache miss",
+        "MetricGroup": "TopdownL3",
+        "ScaleUnit": "100percent of slots"
+    },
+    {
+        "MetricName": "i_tlb_miss_rate",
+        "MetricExpr": "STALL_FRONTEND_TLB / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled due to instruction TLB miss",
+        "MetricGroup": "TopdownL3",
+        "ScaleUnit": "100percent of slots"
+    },
+    {
+        "MetricName": "ixu_pipe_utilization",
+        "MetricExpr": "IXU_NUM_UOPS_ISSUED / (CPU_CYCLES * #slots)",
+        "BriefDescription": "Fraction of IXU execute slots utilized",
+        "MetricGroup": "TopdownL3",
+        "ScaleUnit": "100percent of slots"
+    },
+    {
+        "MetricName": "stall_recovery_rate",
+        "MetricExpr": "IDR_STALL_FLUSH / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled due to flush recovery",
+        "MetricGroup": "TopdownL3",
+        "ScaleUnit": "100percent of slots"
+    },
+    {
+        "MetricName": "stall_fsu_sched_rate",
+        "MetricExpr": "IDR_STALL_FSU_SCHED / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled and FSU was full",
+        "MetricGroup": "TopdownL4",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "stall_ixu_sched_rate",
+        "MetricExpr": "IDR_STALL_IXU_SCHED / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled and IXU was full",
+        "MetricGroup": "TopdownL4",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "stall_lob_id_rate",
+        "MetricExpr": "IDR_STALL_LOB_ID / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled and LOB was full",
+        "MetricGroup": "TopdownL4",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "stall_rob_id_rate",
+        "MetricExpr": "IDR_STALL_ROB_ID / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled and ROB was full",
+        "MetricGroup": "TopdownL4",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "stall_sob_id_rate",
+        "MetricExpr": "IDR_STALL_SOB_ID / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled and SOB was full",
+        "MetricGroup": "TopdownL4",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "l1d_cache_access_demand",
+        "MetricExpr": "L1D_CACHE_RW / L1D_CACHE",
+        "BriefDescription": "L1D cache access - demand",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "100percent of cache acceses"
+    },
+    {
+        "MetricName": "l1d_cache_access_prefetces",
+        "MetricExpr": "L1D_CACHE_PRFM / L1D_CACHE",
+        "BriefDescription": "L1D cache access - prefetch",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "100percent of cache acceses"
+    },
+    {
+        "MetricName": "l1d_cache_demand_misses",
+        "MetricExpr": "L1D_CACHE_REFILL_RW / L1D_CACHE",
+        "BriefDescription": "L1D cache demand misses",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "100percent of cache acceses"
+    },
+    {
+        "MetricName": "l1d_cache_demand_misses_read",
+        "MetricExpr": "L1D_CACHE_REFILL_RD / L1D_CACHE",
+        "BriefDescription": "L1D cache demand misses - read",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "100percent of cache acceses"
+    },
+    {
+        "MetricName": "l1d_cache_demand_misses_write",
+        "MetricExpr": "L1D_CACHE_REFILL_WR / L1D_CACHE",
+        "BriefDescription": "L1D cache demand misses - write",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "100percent of cache acceses"
+    },
+    {
+        "MetricName": "l1d_cache_prefetch_misses",
+        "MetricExpr": "L1D_CACHE_REFILL_PRFM / L1D_CACHE",
+        "BriefDescription": "L1D cache prefetch misses",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "100percent of cache acceses"
+    },
+    {
+        "MetricName": "ase_scalar_mix",
+        "MetricExpr": "ASE_SCALAR_SPEC / OP_SPEC",
+        "BriefDescription": "Proportion of advanced SIMD data processing operations (excluding DP_SPEC/LD_SPEC) scalar operations",
+        "MetricGroup": "Instructions",
+        "ScaleUnit": "100percent of cache acceses"
+    },
+    {
+        "MetricName": "ase_vector_mix",
+        "MetricExpr": "ASE_VECTOR_SPEC / OP_SPEC",
+        "BriefDescription": "Proportion of advanced SIMD data processing operations (excluding DP_SPEC/LD_SPEC) vector operations",
+        "MetricGroup": "Instructions",
+        "ScaleUnit": "100percent of cache acceses"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/mmu.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/mmu.json
new file mode 100644
index 000000000000..66d83b680651
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/mmu.json
@@ -0,0 +1,170 @@
+[
+    {
+        "PublicDescription": "Level 2 data translation buffer allocation",
+        "EventCode": "0xD800",
+        "EventName": "MMU_D_OTB_ALLOC",
+        "BriefDescription": "Level 2 data translation buffer allocation"
+    },
+    {
+        "PublicDescription": "Data TLB translation cache hit on S1L2 walk cache entry",
+        "EventCode": "0xd801",
+        "EventName": "MMU_D_TRANS_CACHE_HIT_S1L2_WALK",
+        "BriefDescription": "Data TLB translation cache hit on S1L2 walk cache entry"
+    },
+    {
+        "PublicDescription": "Data TLB translation cache hit on S1L1 walk cache entry",
+        "EventCode": "0xd802",
+        "EventName": "MMU_D_TRANS_CACHE_HIT_S1L1_WALK",
+        "BriefDescription": "Data TLB translation cache hit on S1L1 walk cache entry"
+    },
+    {
+        "PublicDescription": "Data TLB translation cache hit on S1L0 walk cache entry",
+        "EventCode": "0xd803",
+        "EventName": "MMU_D_TRANS_CACHE_HIT_S1L0_WALK",
+        "BriefDescription": "Data TLB translation cache hit on S1L0 walk cache entry"
+    },
+    {
+        "PublicDescription": "Data TLB translation cache hit on S2L2 walk cache entry",
+        "EventCode": "0xd804",
+        "EventName": "MMU_D_TRANS_CACHE_HIT_S2L2_WALK",
+        "BriefDescription": "Data TLB translation cache hit on S2L2 walk cache entry"
+    },
+    {
+        "PublicDescrition": "Data TLB translation cache hit on S2L1 walk cache entry",
+        "EventCode": "0xd805",
+        "EventName": "MMU_D_TRANS_CACHE_HIT_S2L1_WALK",
+        "BriefDescription": "Data TLB translation cache hit on S2L1 walk cache entry"
+    },
+    {
+        "PublicDescrition": "Data TLB translation cache hit on S2L0 walk cache entry",
+        "EventCode": "0xd806",
+        "EventName": "MMU_D_TRANS_CACHE_HIT_S2L0_WALK",
+        "BriefDescription": "Data TLB translation cache hit on S2L0 walk cache entry"
+    },
+    {
+        "PublicDescrition": "Data-side S1 page walk cache lookup",
+        "EventCode": "0xd807",
+        "EventName": "MMU_D_S1_WALK_CACHE_LOOKUP",
+        "BriefDescription": "Data-side S1 page walk cache lookup"
+    },
+    {
+        "PublicDescrition": "Data-side S1 page walk cache refill",
+        "EventCode": "0xd808",
+        "EventName": "MMU_D_S1_WALK_CACHE_REFILL",
+        "BriefDescription": "Data-side S1 page walk cache refill"
+    },
+    {
+        "PublicDescrition": "Data-side S2 page walk cache lookup",
+        "EventCode": "0xd809",
+        "EventName": "MMU_D_S2_WALK_CACHE_LOOKUP",
+        "BriefDescription": "Data-side S2 page walk cache lookup"
+    },
+    {
+        "PublicDescrition": "Data-side S2 page walk cache refill",
+        "EventCode": "0xd80a",
+        "EventName": "MMU_D_S2_WALK_CACHE_REFILL",
+        "BriefDescription": "Data-side S2 page walk cache refill"
+    },
+    {
+        "PublicDescription": "Data-side S1 table walk fault",
+        "EventCode": "0xD80B",
+        "EventName": "MMU_D_S1_WALK_FAULT",
+        "BriefDescription": "Data-side S1 table walk fault"
+    },
+    {
+        "PublicDescription": "Data-side S2 table walk fault",
+        "EventCode": "0xD80C",
+        "EventName": "MMU_D_S2_WALK_FAULT",
+        "BriefDescription": "Data-side S2 table walk fault"
+    },
+    {
+        "PublicDescription": "Data-side table walk steps or descriptor fetches",
+        "EventCode": "0xD80D",
+        "EventName": "MMU_D_WALK_STEPS",
+        "BriefDescription": "Data-side table walk steps or descriptor fetches"
+    },
+    {
+        "PublicDescription": "Level 2 instruction translation buffer allocation",
+        "EventCode": "0xD900",
+        "EventName": "MMU_I_OTB_ALLOC",
+        "BriefDescription": "Level 2 instruction translation buffer allocation"
+    },
+    {
+        "PublicDescrition": "Instruction TLB translation cache hit on S1L2 walk cache entry",
+        "EventCode": "0xd901",
+        "EventName": "MMU_I_TRANS_CACHE_HIT_S1L2_WALK",
+        "BriefDescription": "Instruction TLB translation cache hit on S1L2 walk cache entry"
+    },
+    {
+        "PublicDescrition": "Instruction TLB translation cache hit on S1L1 walk cache entry",
+        "EventCode": "0xd902",
+        "EventName": "MMU_I_TRANS_CACHE_HIT_S1L1_WALK",
+        "BriefDescription": "Instruction TLB translation cache hit on S1L1 walk cache entry"
+    },
+    {
+        "PublicDescrition": "Instruction TLB translation cache hit on S1L0 walk cache entry",
+        "EventCode": "0xd903",
+        "EventName": "MMU_I_TRANS_CACHE_HIT_S1L0_WALK",
+        "BriefDescription": "Instruction TLB translation cache hit on S1L0 walk cache entry"
+    },
+    {
+        "PublicDescrition": "Instruction TLB translation cache hit on S2L2 walk cache entry",
+        "EventCode": "0xd904",
+        "EventName": "MMU_I_TRANS_CACHE_HIT_S2L2_WALK",
+        "BriefDescription": "Instruction TLB translation cache hit on S2L2 walk cache entry"
+    },
+    {
+        "PublicDescrition": "Instruction TLB translation cache hit on S2L1 walk cache entry",
+        "EventCode": "0xd905",
+        "EventName": "MMU_I_TRANS_CACHE_HIT_S2L1_WALK",
+        "BriefDescription": "Instruction TLB translation cache hit on S2L1 walk cache entry"
+    },
+    {
+        "PublicDescrition": "Instruction TLB translation cache hit on S2L0 walk cache entry",
+        "EventCode": "0xd906",
+        "EventName": "MMU_I_TRANS_CACHE_HIT_S2L0_WALK",
+        "BriefDescription": "Instruction TLB translation cache hit on S2L0 walk cache entry"
+    },
+    {
+        "PublicDescrition": "Instruction-side S1 page walk cache lookup",
+        "EventCode": "0xd907",
+        "EventName": "MMU_I_S1_WALK_CACHE_LOOKUP",
+        "BriefDescription": "Instruction-side S1 page walk cache lookup"
+    },
+    {
+        "PublicDescrition": "Instruction-side S1 page walk cache refill",
+        "EventCode": "0xd908",
+        "EventName": "MMU_I_S1_WALK_CACHE_REFILL",
+        "BriefDescription": "Instruction-side S1 page walk cache refill"
+    },
+    {
+        "PublicDescrition": "Instruction-side S2 page walk cache lookup",
+        "EventCode": "0xd909",
+        "EventName": "MMU_I_S2_WALK_CACHE_LOOKUP",
+        "BriefDescription": "Instruction-side S2 page walk cache lookup"
+    },
+    {
+        "PublicDescrition": "Instruction-side S2 page walk cache refill",
+        "EventCode": "0xd90a",
+        "EventName": "MMU_I_S2_WALK_CACHE_REFILL",
+        "BriefDescription": "Instruction-side S2 page walk cache refill"
+    },
+    {
+        "PublicDescription": "Instruction-side S1 table walk fault",
+        "EventCode": "0xD90B",
+        "EventName": "MMU_I_S1_WALK_FAULT",
+        "BriefDescription": "Instruction-side S1 table walk fault"
+    },
+    {
+        "PublicDescription": "Instruction-side S2 table walk fault",
+        "EventCode": "0xD90C",
+        "EventName": "MMU_I_S2_WALK_FAULT",
+        "BriefDescription": "Instruction-side S2 table walk fault"
+    },
+    {
+        "PublicDescription": "Instruction-side table walk steps or descriptor fetches",
+        "EventCode": "0xD90D",
+        "EventName": "MMU_I_WALK_STEPS",
+        "BriefDescription": "Instruction-side table walk steps or descriptor fetches"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/pipeline.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/pipeline.json
new file mode 100644
index 000000000000..2fb2d1f183fc
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/pipeline.json
@@ -0,0 +1,41 @@
+[
+    {
+        "ArchStdEvent": "STALL_FRONTEND",
+        "Errata": "Errata AC03_CPU_29",
+        "BriefDescription": "Impacted by errata, use metrics instead -"
+    },
+    {
+        "ArchStdEvent": "STALL_BACKEND"
+    },
+    {
+        "ArchStdEvent": "STALL",
+        "Errata": "Errata AC03_CPU_29",
+        "BriefDescription": "Impacted by errata, use metrics instead -"
+    },
+    {
+        "ArchStdEvent": "STALL_SLOT_BACKEND"
+    },
+    {
+        "ArchStdEvent": "STALL_SLOT_FRONTEND",
+        "Errata": "Errata AC03_CPU_29",
+        "BriefDescription": "Impacted by errata, use metrics instead -"
+    },
+    {
+        "ArchStdEvent": "STALL_SLOT"
+    },
+    {
+        "ArchStdEvent": "STALL_BACKEND_MEM"
+    },
+    {
+        "PublicDescription": "Frontend stall cycles, TLB",
+        "EventCode": "0x815c",
+        "EventName": "STALL_FRONTEND_TLB",
+        "BriefDescription": "Frontend stall cycles, TLB"
+    },
+    {
+        "PublicDescription": "Backend stall cycles, TLB",
+        "EventCode": "0x8167",
+        "EventName": "STALL_BACKEND_TLB",
+        "BriefDescription": "Backend stall cycles, TLB"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/spe.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/spe.json
new file mode 100644
index 000000000000..20f2165c85fe
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/spe.json
@@ -0,0 +1,14 @@
+[
+    {
+        "ArchStdEvent": "SAMPLE_POP"
+    },
+    {
+        "ArchStdEvent": "SAMPLE_FEED"
+    },
+    {
+        "ArchStdEvent": "SAMPLE_FILTRATE"
+    },
+    {
+        "ArchStdEvent": "SAMPLE_COLLISION"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/cmn/sys/cmn.json b/tools/perf/pmu-events/arch/arm64/arm/cmn/sys/cmn.json
index 428605c37d10..5ec157c39f0d 100644
--- a/tools/perf/pmu-events/arch/arm64/arm/cmn/sys/cmn.json
+++ b/tools/perf/pmu-events/arch/arm64/arm/cmn/sys/cmn.json
@@ -107,7 +107,7 @@
 		"EventName": "hnf_qos_hh_retry",
 		"EventidCode": "0xe",
 		"NodeType": "0x5",
-		"BriefDescription": "Counts number of times a HighHigh priority request is protocolretried at the HN‑F.",
+		"BriefDescription": "Counts number of times a HighHigh priority request is protocolretried at the HN-F.",
 		"Unit": "arm_cmn",
 		"Compat": "(434|436|43c|43a).*"
 	},
diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv
index 5b58db5032c1..f4d1ca4d1493 100644
--- a/tools/perf/pmu-events/arch/arm64/mapfile.csv
+++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv
@@ -42,3 +42,4 @@
 0x00000000480fd010,v1,hisilicon/hip08,core
 0x00000000500f0000,v1,ampere/emag,core
 0x00000000c00fac30,v1,ampere/ampereone,core
+0x00000000c00fac40,v1,ampere/ampereonex,core
diff --git a/tools/perf/pmu-events/arch/powerpc/mapfile.csv b/tools/perf/pmu-events/arch/powerpc/mapfile.csv
index f4908af7ad66..599a588dbeb4 100644
--- a/tools/perf/pmu-events/arch/powerpc/mapfile.csv
+++ b/tools/perf/pmu-events/arch/powerpc/mapfile.csv
@@ -11,8 +11,7 @@
 #
 # Multiple PVRs could map to a single JSON file.
 #
-
-# Power8 entries
 0x004[bcd][[:xdigit:]]{4},1,power8,core
+0x0066[[:xdigit:]]{4},1,power8,core
 0x004e[[:xdigit:]]{4},1,power9,core
 0x0080[[:xdigit:]]{4},1,power10,core
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/datasource.json b/tools/perf/pmu-events/arch/powerpc/power10/datasource.json
index 6b0356f2d301..0eeaaf1a95b8 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/datasource.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/datasource.json
@@ -100,6 +100,11 @@
     "BriefDescription": "The processor's instruction cache was reloaded from a source beyond the local core's L2 due to a demand miss."
   },
   {
+    "EventCode": "0x0003C0000000C040",
+    "EventName": "PM_DATA_FROM_L2MISS_DSRC",
+    "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss."
+  },
+  {
     "EventCode": "0x000380000010C040",
     "EventName": "PM_INST_FROM_L2MISS_ALL",
     "BriefDescription": "The processor's instruction cache was reloaded from a source beyond the local core's L2 due to a demand miss or prefetch reload."
@@ -161,10 +166,15 @@
   },
   {
     "EventCode": "0x000780000000C040",
-    "EventName": "PM_INST_FROM_L3MISS",
+    "EventName": "PM_INST_FROM_L3MISS_DSRC",
     "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss."
   },
   {
+    "EventCode": "0x0007C0000000C040",
+    "EventName": "PM_DATA_FROM_L3MISS_DSRC",
+    "BriefDescription": "The processor's L1 data cache was reloaded from beyond the local core's L3 due to a demand miss."
+  },
+  {
     "EventCode": "0x000780000010C040",
     "EventName": "PM_INST_FROM_L3MISS_ALL",
     "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss or prefetch reload."
@@ -981,7 +991,7 @@
   },
   {
     "EventCode": "0x0003C0000000C142",
-    "EventName": "PM_MRK_DATA_FROM_L2MISS",
+    "EventName": "PM_MRK_DATA_FROM_L2MISS_DSRC",
     "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss for a marked instruction."
   },
   {
@@ -1046,12 +1056,12 @@
   },
   {
     "EventCode": "0x000780000000C142",
-    "EventName": "PM_MRK_INST_FROM_L3MISS",
+    "EventName": "PM_MRK_INST_FROM_L3MISS_DSRC",
     "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss for a marked instruction."
   },
   {
     "EventCode": "0x0007C0000000C142",
-    "EventName": "PM_MRK_DATA_FROM_L3MISS",
+    "EventName": "PM_MRK_DATA_FROM_L3MISS_DSRC",
     "BriefDescription": "The processor's L1 data cache was reloaded from beyond the local core's L3 due to a demand miss for a marked instruction."
   },
   {
diff --git a/tools/perf/pmu-events/arch/riscv/mapfile.csv b/tools/perf/pmu-events/arch/riscv/mapfile.csv
index c61b3d6ef616..cfc449b19810 100644
--- a/tools/perf/pmu-events/arch/riscv/mapfile.csv
+++ b/tools/perf/pmu-events/arch/riscv/mapfile.csv
@@ -15,3 +15,5 @@
 #
 #MVENDORID-MARCHID-MIMPID,Version,Filename,EventType
 0x489-0x8000000000000007-0x[[:xdigit:]]+,v1,sifive/u74,core
+0x5b7-0x0-0x0,v1,thead/c900-legacy,core
+0x67e-0x80000000db0000[89]0-0x[[:xdigit:]]+,v1,starfive/dubhe-80,core
diff --git a/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/common.json b/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/common.json
new file mode 100644
index 000000000000..fbffcacb2ace
--- /dev/null
+++ b/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/common.json
@@ -0,0 +1,172 @@
+[
+  {
+    "EventName": "ACCESS_MMU_STLB",
+    "EventCode": "0x1",
+    "BriefDescription": "access MMU STLB"
+  },
+  {
+    "EventName": "MISS_MMU_STLB",
+    "EventCode": "0x2",
+    "BriefDescription": "miss MMU STLB"
+  },
+  {
+    "EventName": "ACCESS_MMU_PTE_C",
+    "EventCode": "0x3",
+    "BriefDescription": "access MMU PTE-Cache"
+  },
+  {
+    "EventName": "MISS_MMU_PTE_C",
+    "EventCode": "0x4",
+    "BriefDescription": "miss MMU PTE-Cache"
+  },
+  {
+    "EventName": "ROB_FLUSH",
+    "EventCode": "0x5",
+    "BriefDescription": "ROB flush (all kinds of exceptions)"
+  },
+  {
+    "EventName": "BTB_PREDICTION_MISS",
+    "EventCode": "0x6",
+    "BriefDescription": "BTB prediction miss"
+  },
+  {
+    "EventName": "ITLB_MISS",
+    "EventCode": "0x7",
+    "BriefDescription": "ITLB miss"
+  },
+  {
+    "EventName": "SYNC_DEL_FETCH_G",
+    "EventCode": "0x8",
+    "BriefDescription": "SYNC delivery a fetch-group"
+  },
+  {
+    "EventName": "ICACHE_MISS",
+    "EventCode": "0x9",
+    "BriefDescription": "ICache miss"
+  },
+  {
+    "EventName": "BPU_BR_RETIRE",
+    "EventCode": "0xA",
+    "BriefDescription": "condition branch instruction retire"
+  },
+  {
+    "EventName": "BPU_BR_MISS",
+    "EventCode": "0xB",
+    "BriefDescription": "condition branch instruction miss"
+  },
+  {
+    "EventName": "RET_INS_RETIRE",
+    "EventCode": "0xC",
+    "BriefDescription": "return instruction retire"
+  },
+  {
+    "EventName": "RET_INS_MISS",
+    "EventCode": "0xD",
+    "BriefDescription": "return instruction miss"
+  },
+  {
+    "EventName": "INDIRECT_JR_MISS",
+    "EventCode": "0xE",
+    "BriefDescription": "indirect JR instruction miss (inlcude without target)"
+  },
+  {
+    "EventName": "IBUF_VAL_ID_NORDY",
+    "EventCode": "0xF",
+    "BriefDescription": "IBUF valid while ID not ready"
+  },
+  {
+    "EventName": "IBUF_NOVAL_ID_RDY",
+    "EventCode": "0x10",
+    "BriefDescription": "IBUF not valid while ID ready"
+  },
+  {
+    "EventName": "REN_INT_PHY_REG_NORDY",
+    "EventCode": "0x11",
+    "BriefDescription": "REN integer physical register file is not ready"
+  },
+  {
+    "EventName": "REN_FP_PHY_REG_NORDY",
+    "EventCode": "0x12",
+    "BriefDescription": "REN floating point physical register file is not ready"
+  },
+  {
+    "EventName": "REN_CP_NORDY",
+    "EventCode": "0x13",
+    "BriefDescription": "REN checkpoint is not ready"
+  },
+  {
+    "EventName": "DEC_VAL_ROB_NORDY",
+    "EventCode": "0x14",
+    "BriefDescription": "DEC is valid and ROB is not ready"
+  },
+  {
+    "EventName": "OOD_FLUSH_LS_DEP",
+    "EventCode": "0x15",
+    "BriefDescription": "out of order flush due to load/store dependency"
+  },
+  {
+    "EventName": "BRU_RET_IJR_INS",
+    "EventCode": "0x16",
+    "BriefDescription": "BRU retire an IJR instruction"
+  },
+  {
+    "EventName": "ACCESS_DTLB",
+    "EventCode": "0x17",
+    "BriefDescription": "access DTLB"
+  },
+  {
+    "EventName": "MISS_DTLB",
+    "EventCode": "0x18",
+    "BriefDescription": "miss DTLB"
+  },
+  {
+    "EventName": "LOAD_INS_DCACHE",
+    "EventCode": "0x19",
+    "BriefDescription": "load instruction access DCache"
+  },
+  {
+    "EventName": "LOAD_INS_MISS_DCACHE",
+    "EventCode": "0x1A",
+    "BriefDescription": "load instruction miss DCache"
+  },
+  {
+    "EventName": "STORE_INS_DCACHE",
+    "EventCode": "0x1B",
+    "BriefDescription": "store/amo instruction access DCache"
+  },
+  {
+    "EventName": "STORE_INS_MISS_DCACHE",
+    "EventCode": "0x1C",
+    "BriefDescription": "store/amo instruction miss DCache"
+  },
+  {
+    "EventName": "LOAD_SCACHE",
+    "EventCode": "0x1D",
+    "BriefDescription": "load access SCache"
+  },
+  {
+    "EventName": "STORE_SCACHE",
+    "EventCode": "0x1E",
+    "BriefDescription": "store access SCache"
+  },
+  {
+    "EventName": "LOAD_MISS_SCACHE",
+    "EventCode": "0x1F",
+    "BriefDescription": "load miss SCache"
+  },
+  {
+    "EventName": "STORE_MISS_SCACHE",
+    "EventCode": "0x20",
+    "BriefDescription": "store miss SCache"
+  },
+  {
+    "EventName": "L2C_PF_REQ",
+    "EventCode": "0x21",
+    "BriefDescription": "L2C data-prefetcher request"
+  },
+  {
+    "EventName": "L2C_PF_HIT",
+    "EventCode": "0x22",
+    "BriefDescription": "L2C data-prefetcher hit"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/firmware.json b/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/firmware.json
new file mode 100644
index 000000000000..9b4a032186a7
--- /dev/null
+++ b/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/firmware.json
@@ -0,0 +1,68 @@
+[
+  {
+    "ArchStdEvent": "FW_MISALIGNED_LOAD"
+  },
+  {
+    "ArchStdEvent": "FW_MISALIGNED_STORE"
+  },
+  {
+    "ArchStdEvent": "FW_ACCESS_LOAD"
+  },
+  {
+    "ArchStdEvent": "FW_ACCESS_STORE"
+  },
+  {
+    "ArchStdEvent": "FW_ILLEGAL_INSN"
+  },
+  {
+    "ArchStdEvent": "FW_SET_TIMER"
+  },
+  {
+    "ArchStdEvent": "FW_IPI_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_IPI_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_FENCE_I_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_FENCE_I_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_SFENCE_VMA_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_SFENCE_VMA_ASID_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_GVMA_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_GVMA_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_GVMA_VMID_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_GVMA_VMID_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_VVMA_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_VVMA_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_VVMA_ASID_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_VVMA_ASID_RECEIVED"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/cache.json b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/cache.json
new file mode 100644
index 000000000000..2b142348d635
--- /dev/null
+++ b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/cache.json
@@ -0,0 +1,67 @@
+[
+  {
+    "EventName": "L1_ICACHE_ACCESS",
+    "EventCode": "0x00000001",
+    "BriefDescription": "L1 instruction cache access"
+  },
+  {
+    "EventName": "L1_ICACHE_MISS",
+    "EventCode": "0x00000002",
+    "BriefDescription": "L1 instruction cache miss"
+  },
+  {
+    "EventName": "ITLB_MISS",
+    "EventCode": "0x00000003",
+    "BriefDescription": "I-UTLB miss"
+  },
+  {
+    "EventName": "DTLB_MISS",
+    "EventCode": "0x00000004",
+    "BriefDescription": "D-UTLB miss"
+  },
+  {
+    "EventName": "JTLB_MISS",
+    "EventCode": "0x00000005",
+    "BriefDescription": "JTLB miss"
+  },
+  {
+    "EventName": "L1_DCACHE_READ_ACCESS",
+    "EventCode": "0x0000000c",
+    "BriefDescription": "L1 data cache read access"
+  },
+  {
+    "EventName": "L1_DCACHE_READ_MISS",
+    "EventCode": "0x0000000d",
+    "BriefDescription": "L1 data cache read miss"
+  },
+  {
+    "EventName": "L1_DCACHE_WRITE_ACCESS",
+    "EventCode": "0x0000000e",
+    "BriefDescription": "L1 data cache write access"
+  },
+  {
+    "EventName": "L1_DCACHE_WRITE_MISS",
+    "EventCode": "0x0000000f",
+    "BriefDescription": "L1 data cache write miss"
+  },
+  {
+    "EventName": "LL_CACHE_READ_ACCESS",
+    "EventCode": "0x00000010",
+    "BriefDescription": "LL Cache read access"
+  },
+  {
+    "EventName": "LL_CACHE_READ_MISS",
+    "EventCode": "0x00000011",
+    "BriefDescription": "LL Cache read miss"
+  },
+  {
+    "EventName": "LL_CACHE_WRITE_ACCESS",
+    "EventCode": "0x00000012",
+    "BriefDescription": "LL Cache write access"
+  },
+  {
+    "EventName": "LL_CACHE_WRITE_MISS",
+    "EventCode": "0x00000013",
+    "BriefDescription": "LL Cache write miss"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/firmware.json b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/firmware.json
new file mode 100644
index 000000000000..9b4a032186a7
--- /dev/null
+++ b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/firmware.json
@@ -0,0 +1,68 @@
+[
+  {
+    "ArchStdEvent": "FW_MISALIGNED_LOAD"
+  },
+  {
+    "ArchStdEvent": "FW_MISALIGNED_STORE"
+  },
+  {
+    "ArchStdEvent": "FW_ACCESS_LOAD"
+  },
+  {
+    "ArchStdEvent": "FW_ACCESS_STORE"
+  },
+  {
+    "ArchStdEvent": "FW_ILLEGAL_INSN"
+  },
+  {
+    "ArchStdEvent": "FW_SET_TIMER"
+  },
+  {
+    "ArchStdEvent": "FW_IPI_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_IPI_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_FENCE_I_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_FENCE_I_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_SFENCE_VMA_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_SFENCE_VMA_ASID_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_GVMA_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_GVMA_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_GVMA_VMID_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_GVMA_VMID_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_VVMA_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_VVMA_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_VVMA_ASID_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_VVMA_ASID_RECEIVED"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/instruction.json b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/instruction.json
new file mode 100644
index 000000000000..c822b5373333
--- /dev/null
+++ b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/instruction.json
@@ -0,0 +1,72 @@
+[
+  {
+    "EventName": "INST_BRANCH_MISPREDICT",
+    "EventCode": "0x00000006",
+    "BriefDescription": "Mispredicted branch instructions"
+  },
+  {
+    "EventName": "INST_BRANCH",
+    "EventCode": "0x00000007",
+    "BriefDescription": "Retired branch instructions"
+  },
+  {
+    "EventName": "INST_JMP_MISPREDICT",
+    "EventCode": "0x00000008",
+    "BriefDescription": "Indirect branch mispredict"
+  },
+  {
+    "EventName": "INST_JMP",
+    "EventCode": "0x00000009",
+    "BriefDescription": "Retired jmp instructions"
+  },
+  {
+    "EventName": "INST_STORE",
+    "EventCode": "0x0000000b",
+    "BriefDescription": "Retired store instructions"
+  },
+  {
+    "EventName": "INST_ALU",
+    "EventCode": "0x0000001d",
+    "BriefDescription": "Retired ALU instructions"
+  },
+  {
+    "EventName": "INST_LDST",
+    "EventCode": "0x0000001e",
+    "BriefDescription": "Retired Load/Store instructions"
+  },
+  {
+    "EventName": "INST_VECTOR",
+    "EventCode": "0x0000001f",
+    "BriefDescription": "Retired Vector instructions"
+  },
+  {
+    "EventName": "INST_CSR",
+    "EventCode": "0x00000020",
+    "BriefDescription": "Retired CSR instructions"
+  },
+  {
+    "EventName": "INST_SYNC",
+    "EventCode": "0x00000021",
+    "BriefDescription": "Retired sync instructions (AMO/LR/SC instructions)"
+  },
+  {
+    "EventName": "INST_UNALIGNED_ACCESS",
+    "EventCode": "0x00000022",
+    "BriefDescription": "Retired Store/Load instructions with unaligned memory access"
+  },
+  {
+    "EventName": "INST_ECALL",
+    "EventCode": "0x00000025",
+    "BriefDescription": "Retired ecall instructions"
+  },
+  {
+    "EventName": "INST_LONG_JP",
+    "EventCode": "0x00000026",
+    "BriefDescription": "Retired long jump instructions"
+  },
+  {
+    "EventName": "INST_FP",
+    "EventCode": "0x0000002a",
+    "BriefDescription": "Retired FPU instructions"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/microarch.json b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/microarch.json
new file mode 100644
index 000000000000..0ab6f288af91
--- /dev/null
+++ b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/microarch.json
@@ -0,0 +1,80 @@
+[
+  {
+    "EventName": "LSU_SPEC_FAIL",
+    "EventCode": "0x0000000a",
+    "BriefDescription": "LSU speculation fail"
+  },
+  {
+    "EventName": "IDU_RF_PIPE_FAIL",
+    "EventCode": "0x00000014",
+    "BriefDescription": "Instruction decode unit launch pipeline failed in RF state"
+  },
+  {
+    "EventName": "IDU_RF_REG_FAIL",
+    "EventCode": "0x00000015",
+    "BriefDescription": "Instruction decode unit launch register file fail in RF state"
+  },
+  {
+    "EventName": "IDU_RF_INSTRUCTION",
+    "EventCode": "0x00000016",
+    "BriefDescription": "retired instruction count of Instruction decode unit in RF (Register File) stage"
+  },
+  {
+    "EventName": "LSU_4K_STALL",
+    "EventCode": "0x00000017",
+    "BriefDescription": "LSU stall times for long distance data access (Over 4K)",
+    "PublicDescription": "This stall occurs when translate virtual address with page offset over 4k"
+  },
+  {
+    "EventName": "LSU_OTHER_STALL",
+    "EventCode": "0x00000018",
+    "BriefDescription": "LSU stall times for other reasons (except the 4k stall)"
+  },
+  {
+    "EventName": "LSU_SQ_OTHER_DIS",
+    "EventCode": "0x00000019",
+    "BriefDescription": "LSU store queue discard others"
+  },
+  {
+    "EventName": "LSU_SQ_DATA_DISCARD",
+    "EventCode": "0x0000001a",
+    "BriefDescription": "LSU store queue discard data (uops)"
+  },
+  {
+    "EventName": "BRANCH_DIRECTION_MISPREDICTION",
+    "EventCode": "0x0000001b",
+    "BriefDescription": "Branch misprediction in BTB"
+  },
+  {
+    "EventName": "BRANCH_DIRECTION_PREDICTION",
+    "EventCode": "0x0000001c",
+    "BriefDescription": "All branch prediction in BTB",
+    "PublicDescription": "This event including both successful prediction and failed prediction in BTB"
+  },
+  {
+    "EventName": "INTERRUPT_ACK_COUNT",
+    "EventCode": "0x00000023",
+    "BriefDescription": "acknowledged interrupt count"
+  },
+  {
+    "EventName": "INTERRUPT_OFF_CYCLE",
+    "EventCode": "0x00000024",
+    "BriefDescription": "PLIC arbitration time when the interrupt is not responded",
+    "PublicDescription": "The arbitration time is recorded while meeting any of the following:\n- CPU is M-mode and MIE == 0\n- CPU is S-mode and delegation and SIE == 0\n"
+  },
+  {
+    "EventName": "IFU_STALLED_CYCLE",
+    "EventCode": "0x00000027",
+    "BriefDescription": "Number of stall cycles of the instruction fetch unit (IFU)."
+  },
+  {
+    "EventName": "IDU_STALLED_CYCLE",
+    "EventCode": "0x00000028",
+    "BriefDescription": "hpcp_backend_stall Number of stall cycles of the instruction decoding unit (IDU) and next-level pipeline unit."
+  },
+  {
+    "EventName": "SYNC_STALL",
+    "EventCode": "0x00000029",
+    "BriefDescription": "Sync instruction stall cycle fence/fence.i/sync/sfence"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
index 3388b58b8f1a..bbfa3883e533 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
@@ -70,12 +70,6 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Uncore frequency per die [GHZ]",
-        "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9",
-        "MetricGroup": "SoC",
-        "MetricName": "UNCORE_FREQ"
-    },
-    {
         "BriefDescription": "Percentage of cycles spent in System Management Interrupts.",
         "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)",
         "MetricGroup": "smi",
@@ -120,7 +114,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to certain allocation restrictions.",
-        "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_alloc_restriction",
         "MetricThreshold": "tma_alloc_restriction > 0.1",
@@ -130,7 +124,7 @@
     {
         "BriefDescription": "Counts the total number of issue slots  that were not consumed by the backend due to backend stalls",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "TOPDOWN_BE_BOUND.ALL / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL@ / tma_info_core_slots",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.1",
@@ -175,7 +169,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend",
-        "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_detect",
         "MetricThreshold": "tma_branch_detect > 0.05",
@@ -185,7 +179,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to branch mispredicts.",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MISPREDICT@ / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.05",
@@ -195,7 +189,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteer",
         "MetricThreshold": "tma_branch_resteer > 0.05",
@@ -204,7 +198,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to the microcode sequencer (MS).",
-        "MetricExpr": "TOPDOWN_FE_BOUND.CISC / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.CISC@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_cisc",
         "MetricThreshold": "tma_cisc > 0.05",
@@ -223,7 +217,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to decode stalls.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_decode",
         "MetricThreshold": "tma_decode > 0.05",
@@ -241,7 +235,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hit in DRAM or MMIO (Non-DRAM).",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
@@ -251,7 +244,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to a machine clear classified as a fast nuke due to memory ordering, memory disambiguation and memory renaming.",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_fast_nuke",
         "MetricThreshold": "tma_fast_nuke > 0.05",
@@ -260,7 +253,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1",
@@ -270,7 +263,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.15",
@@ -289,7 +282,7 @@
     },
     {
         "BriefDescription": "Counts the number of floating point divide operations per uop.",
-        "MetricExpr": "UOPS_RETIRED.FPDIV / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@UOPS_RETIRED.FPDIV@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_base_group",
         "MetricName": "tma_fpdiv_uops",
         "MetricThreshold": "tma_fpdiv_uops > 0.2",
@@ -299,7 +292,7 @@
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to frontend stalls.",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "TOPDOWN_FE_BOUND.ALL / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ALL@ / tma_info_core_slots",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.2",
@@ -309,7 +302,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to instruction cache misses.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ICACHE@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
         "MetricThreshold": "tma_icache_misses > 0.05",
@@ -336,7 +329,7 @@
     },
     {
         "BriefDescription": "Instructions Per Cycle",
-        "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / tma_info_core_clks",
         "MetricName": "tma_info_core_ipc",
         "Unit": "cpu_atom"
     },
@@ -348,7 +341,7 @@
     },
     {
         "BriefDescription": "Uops Per Instruction",
-        "MetricExpr": "UOPS_RETIRED.ALL / INST_RETIRED.ANY",
+        "MetricExpr": "cpu_atom@UOPS_RETIRED.ALL@ / INST_RETIRED.ANY",
         "MetricName": "tma_info_core_upi",
         "Unit": "cpu_atom"
     },
@@ -372,13 +365,13 @@
     },
     {
         "BriefDescription": "Ratio of all branches which mispredict",
-        "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_atom@BR_MISP_RETIRED.ALL_BRANCHES@ / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricName": "tma_info_inst_mix_branch_mispredict_ratio",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Ratio between Mispredicted branches and unknown branches",
-        "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BACLEARS.ANY",
+        "MetricExpr": "cpu_atom@BR_MISP_RETIRED.ALL_BRANCHES@ / BACLEARS.ANY",
         "MetricName": "tma_info_inst_mix_branch_mispredict_to_unknown_branch_ratio",
         "Unit": "cpu_atom"
     },
@@ -396,61 +389,61 @@
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricName": "tma_info_inst_mix_ipbranch",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instruction per (near) call (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.CALL",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_INST_RETIRED.CALL",
         "MetricName": "tma_info_inst_mix_ipcall",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per Far Branch",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_atom@BR_INST_RETIRED.FAR_BRANCH@ / 2)",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / (cpu_atom@BR_INST_RETIRED.FAR_BRANCH@ / 2)",
         "MetricName": "tma_info_inst_mix_ipfarbranch",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per Load",
-        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / MEM_UOPS_RETIRED.ALL_LOADS",
         "MetricName": "tma_info_inst_mix_ipload",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was not taken",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_atom@BR_MISP_RETIRED.COND@ - cpu_atom@BR_MISP_RETIRED.COND_TAKEN@)",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / (cpu_atom@BR_MISP_RETIRED.COND@ - cpu_atom@BR_MISP_RETIRED.COND_TAKEN@)",
         "MetricName": "tma_info_inst_mix_ipmisp_cond_ntaken",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was taken",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_MISP_RETIRED.COND_TAKEN",
         "MetricName": "tma_info_inst_mix_ipmisp_cond_taken",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired indirect call or jump Branch Misprediction",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_MISP_RETIRED.INDIRECT",
         "MetricName": "tma_info_inst_mix_ipmisp_indirect",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired return Branch Misprediction",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RETURN",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_MISP_RETIRED.RETURN",
         "MetricName": "tma_info_inst_mix_ipmisp_ret",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired Branch Misprediction",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_MISP_RETIRED.ALL_BRANCHES",
         "MetricName": "tma_info_inst_mix_ipmispredict",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per Store",
-        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / MEM_UOPS_RETIRED.ALL_STORES",
         "MetricName": "tma_info_inst_mix_ipstore",
         "Unit": "cpu_atom"
     },
@@ -486,19 +479,19 @@
     },
     {
         "BriefDescription": "Cycle cost per DRAM hit",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
+        "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@ / MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
         "MetricName": "tma_info_memory_cycles_per_demand_load_dram_hit",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Cycle cost per L2 hit",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_L2_HIT@ / MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "MetricName": "tma_info_memory_cycles_per_demand_load_l2_hit",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Cycle cost per LLC hit",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_LOAD_UOPS_RETIRED.L3_HIT",
+        "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / MEM_LOAD_UOPS_RETIRED.L3_HIT",
         "MetricName": "tma_info_memory_cycles_per_demand_load_l3_hit",
         "Unit": "cpu_atom"
     },
@@ -510,7 +503,7 @@
     },
     {
         "BriefDescription": "Average CPU Utilization",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC",
+        "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.REF_TSC@ / TSC",
         "MetricName": "tma_info_system_cpu_utilization",
         "Unit": "cpu_atom"
     },
@@ -530,7 +523,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ITLB@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
         "MetricThreshold": "tma_itlb_misses > 0.05",
@@ -539,7 +532,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a load block.",
-        "MetricExpr": "LD_HEAD.L1_BOUND_AT_RET / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@LD_HEAD.L1_BOUND_AT_RET@ / tma_info_core_clks",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
         "MetricThreshold": "tma_l1_bound > 0.1",
@@ -548,7 +541,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 Cache.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_L2_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_L2_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
@@ -558,7 +550,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -577,7 +568,7 @@
     },
     {
         "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS@ / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.05",
@@ -587,7 +578,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops.",
-        "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_mem_scheduler",
         "MetricThreshold": "tma_mem_scheduler > 0.1",
@@ -596,7 +587,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to stores or loads.",
-        "MetricExpr": "min(cpu_atom@TOPDOWN_BE_BOUND.ALL@ / tma_info_core_slots, cpu_atom@LD_HEAD.ANY_AT_RET@ / tma_info_core_clks + tma_store_bound)",
+        "MetricExpr": "min(tma_backend_bound, cpu_atom@LD_HEAD.ANY_AT_RET@ / tma_info_core_clks + tma_store_bound)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2",
@@ -615,7 +606,7 @@
     },
     {
         "BriefDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS)",
-        "MetricExpr": "UOPS_RETIRED.MS / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@UOPS_RETIRED.MS@ / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_ms_uops",
         "MetricThreshold": "tma_ms_uops > 0.05",
@@ -626,7 +617,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops.",
-        "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_non_mem_scheduler",
         "MetricThreshold": "tma_non_mem_scheduler > 0.1",
@@ -635,7 +626,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to a machine clear (slow nuke).",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_nuke",
         "MetricThreshold": "tma_nuke > 0.05",
@@ -644,7 +635,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to other common frontend stalls not categorized.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_other_fb",
         "MetricThreshold": "tma_other_fb > 0.05",
@@ -653,7 +644,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a number of other load blocks.",
-        "MetricExpr": "LD_HEAD.OTHER_AT_RET / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@LD_HEAD.OTHER_AT_RET@ / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_other_l1",
         "MetricThreshold": "tma_other_l1 > 0.05",
@@ -689,7 +680,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to wrong predecodes.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_predecode",
         "MetricThreshold": "tma_predecode > 0.05",
@@ -698,7 +689,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls).",
-        "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_register",
         "MetricThreshold": "tma_register > 0.1",
@@ -707,7 +698,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to the reorder buffer being full (ROB stalls).",
-        "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_reorder_buffer",
         "MetricThreshold": "tma_reorder_buffer > 0.1",
@@ -728,7 +719,7 @@
     {
         "BriefDescription": "Counts the number of issue slots  that result in retirement slots.",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "TOPDOWN_RETIRING.ALL / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL@ / tma_info_core_slots",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.75",
@@ -747,7 +738,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS).",
-        "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_serialization",
         "MetricThreshold": "tma_serialization > 0.1",
@@ -774,7 +765,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a first level TLB miss.",
-        "MetricExpr": "LD_HEAD.DTLB_MISS_AT_RET / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@LD_HEAD.DTLB_MISS_AT_RET@ / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_stlb_hit",
         "MetricThreshold": "tma_stlb_hit > 0.05",
@@ -783,7 +774,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a second level TLB miss requiring a page walk.",
-        "MetricExpr": "LD_HEAD.PGWALK_AT_RET / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@LD_HEAD.PGWALK_AT_RET@ / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_stlb_miss",
         "MetricThreshold": "tma_stlb_miss > 0.05",
@@ -801,8 +792,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@LD_HEAD.ST_ADDR_AT_RET@ / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
         "MetricThreshold": "tma_store_fwd_blk > 0.05",
@@ -810,6 +800,13 @@
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Uncore frequency per die [GHZ]",
+        "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9",
+        "MetricGroup": "SoC",
+        "MetricName": "UNCORE_FREQ",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "(cpu_core@UOPS_DISPATCHED.PORT_0@ + cpu_core@UOPS_DISPATCHED.PORT_1@ + cpu_core@UOPS_DISPATCHED.PORT_5_11@ + cpu_core@UOPS_DISPATCHED.PORT_6@) / (5 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
@@ -874,7 +871,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers",
-        "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
+        "MetricExpr": "cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
         "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
@@ -904,7 +901,6 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(25 * tma_info_system_average_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) + 24 * tma_info_system_average_frequency * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
@@ -926,7 +922,6 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "24 * tma_info_system_average_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
@@ -947,7 +942,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active",
-        "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@ARITH.DIV_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
         "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
@@ -957,7 +952,6 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
@@ -978,7 +972,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines",
-        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
         "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
@@ -1018,7 +1012,7 @@
     },
     {
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
-        "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@L1D_PEND_MISS.FB_FULL@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
@@ -1153,7 +1147,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
-        "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks",
         "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
         "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
@@ -1163,7 +1157,6 @@
     },
     {
         "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;BrMispredicts;tma_issueBM",
         "MetricName": "tma_info_bad_spec_branch_misprediction_cost",
@@ -1172,7 +1165,7 @@
     },
     {
         "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.COND_NTAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200",
@@ -1180,7 +1173,7 @@
     },
     {
         "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.COND_TAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200",
@@ -1196,7 +1189,7 @@
     },
     {
         "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.RET",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_ret",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_ret < 500",
@@ -1204,7 +1197,7 @@
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;BadSpec;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmispredict",
         "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200",
@@ -1212,7 +1205,6 @@
     },
     {
         "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)",
         "MetricGroup": "Cor;SMT",
         "MetricName": "tma_info_botlnk_l0_core_bound_likely",
@@ -1221,7 +1213,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
@@ -1231,7 +1222,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
@@ -1241,7 +1231,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC",
         "MetricName": "tma_info_bottleneck_big_code",
@@ -1260,7 +1249,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code",
         "MetricGroup": "Fed;FetchBW;Frontend",
         "MetricName": "tma_info_bottleneck_instruction_fetch_bw",
@@ -1269,7 +1257,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))",
         "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_info_bottleneck_memory_bandwidth",
@@ -1279,7 +1266,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_info_bottleneck_memory_data_tlbs",
@@ -1289,7 +1275,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))",
         "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_info_bottleneck_memory_latency",
@@ -1299,7 +1284,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM",
         "MetricName": "tma_info_bottleneck_mispredictions",
@@ -1316,14 +1300,14 @@
     },
     {
         "BriefDescription": "Fraction of branches that are non-taken conditionals",
-        "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_core@BR_INST_RETIRED.COND_NTAKEN@ / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;Branches;CodeGen;PGO",
         "MetricName": "tma_info_branches_cond_nt",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of branches that are taken conditionals",
-        "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_core@BR_INST_RETIRED.COND_TAKEN@ / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;Branches;CodeGen;PGO",
         "MetricName": "tma_info_branches_cond_tk",
         "Unit": "cpu_core"
@@ -1351,7 +1335,7 @@
     },
     {
         "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / tma_info_core_core_clks",
         "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group",
         "MetricName": "tma_info_core_coreipc",
         "Unit": "cpu_core"
@@ -1373,14 +1357,14 @@
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@)",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@)",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / cpu_core@UOPS_ISSUED.ANY@",
+        "MetricExpr": "cpu_core@IDQ.DSB_UOPS@ / cpu_core@UOPS_ISSUED.ANY@",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_frontend_dsb_coverage",
         "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 6 > 0.35",
@@ -1389,28 +1373,28 @@
     },
     {
         "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
-        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
+        "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "UOPS_ISSUED.ANY / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@",
+        "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Latency for L1 instruction cache misses",
-        "MetricExpr": "ICACHE_DATA.STALLS / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@",
+        "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed;FetchLat;IcMiss",
         "MetricName": "tma_info_frontend_icache_miss_latency",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / FRONTEND_RETIRED.ANY_DSB_MISS",
         "MetricGroup": "DSBmiss;Fed",
         "MetricName": "tma_info_frontend_ipdsb_miss_ret",
         "MetricThreshold": "tma_info_frontend_ipdsb_miss_ret < 50",
@@ -1439,14 +1423,14 @@
     },
     {
         "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)",
-        "MetricExpr": "LSD.UOPS / cpu_core@UOPS_ISSUED.ANY@",
+        "MetricExpr": "cpu_core@LSD.UOPS@ / cpu_core@UOPS_ISSUED.ANY@",
         "MetricGroup": "Fed;LSD",
         "MetricName": "tma_info_frontend_lsd_coverage",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Branch instructions per taken branch.",
-        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch",
         "Unit": "cpu_core"
@@ -1461,7 +1445,7 @@
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)",
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
@@ -1470,7 +1454,7 @@
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@)",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@)",
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
@@ -1479,7 +1463,7 @@
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)",
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
@@ -1488,7 +1472,7 @@
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
@@ -1497,7 +1481,7 @@
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
@@ -1506,7 +1490,7 @@
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Branches;Fed;InsType",
         "MetricName": "tma_info_inst_mix_ipbranch",
         "MetricThreshold": "tma_info_inst_mix_ipbranch < 8",
@@ -1514,7 +1498,7 @@
     },
     {
         "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.NEAR_CALL",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_ipcall",
         "MetricThreshold": "tma_info_inst_mix_ipcall < 200",
@@ -1522,7 +1506,7 @@
     },
     {
         "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@) + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@) + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)",
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_ipflop",
         "MetricThreshold": "tma_info_inst_mix_ipflop < 10",
@@ -1530,7 +1514,7 @@
     },
     {
         "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / MEM_INST_RETIRED.ALL_LOADS",
         "MetricGroup": "InsType",
         "MetricName": "tma_info_inst_mix_ipload",
         "MetricThreshold": "tma_info_inst_mix_ipload < 3",
@@ -1538,7 +1522,7 @@
     },
     {
         "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / MEM_INST_RETIRED.ALL_STORES",
         "MetricGroup": "InsType",
         "MetricName": "tma_info_inst_mix_ipstore",
         "MetricThreshold": "tma_info_inst_mix_ipstore < 8",
@@ -1546,7 +1530,7 @@
     },
     {
         "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / cpu_core@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@",
         "MetricGroup": "Prefetches",
         "MetricName": "tma_info_inst_mix_ipswpf",
         "MetricThreshold": "tma_info_inst_mix_ipswpf < 100",
@@ -1554,7 +1538,7 @@
     },
     {
         "BriefDescription": "Instruction per taken branch",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
         "MetricThreshold": "tma_info_inst_mix_iptb < 13",
@@ -1654,14 +1638,14 @@
     },
     {
         "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / MEM_LOAD_COMPLETED.L1_MISS_ANY",
+        "MetricExpr": "cpu_core@L1D_PEND_MISS.PENDING@ / MEM_LOAD_COMPLETED.L1_MISS_ANY",
         "MetricGroup": "Mem;MemoryBound;MemoryLat",
         "MetricName": "tma_info_memory_load_miss_real_latency",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "MetricExpr": "cpu_core@L1D_PEND_MISS.PENDING@ / L1D_PEND_MISS.PENDING_CYCLES",
         "MetricGroup": "Mem;MemoryBW;MemoryBound",
         "MetricName": "tma_info_memory_mlp",
         "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
@@ -1669,28 +1653,28 @@
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss data reads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD@ / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_oro_data_l2_mlp",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Latency for L2 cache miss demand Loads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / OFFCORE_REQUESTS.DEMAND_DATA_RD",
         "MetricGroup": "Memory_Lat;Offcore",
         "MetricName": "tma_info_memory_oro_load_l2_miss_latency",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_oro_load_l2_mlp",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Latency for L3 cache miss demand Loads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD@ / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
         "MetricGroup": "Memory_Lat;Offcore",
         "MetricName": "tma_info_memory_oro_load_l3_miss_latency",
         "Unit": "cpu_core"
@@ -1754,14 +1738,14 @@
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instructions per a microcode Assist invocation",
-        "MetricExpr": "INST_RETIRED.ANY / cpu_core@ASSISTS.ANY\\,umask\\=0x1B@",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@ASSISTS.ANY\\,umask\\=0x1B@",
         "MetricGroup": "Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
         "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
@@ -1777,7 +1761,7 @@
     },
     {
         "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
-        "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
+        "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_strings_cycles",
         "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1",
@@ -1792,7 +1776,7 @@
     },
     {
         "BriefDescription": "Average CPU Utilization",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.REF_TSC@ / TSC",
         "MetricGroup": "HPC;Summary",
         "MetricName": "tma_info_system_cpu_utilization",
         "Unit": "cpu_core"
@@ -1815,7 +1799,7 @@
     },
     {
         "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
-        "MetricExpr": "INST_RETIRED.ANY / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
         "MetricThreshold": "tma_info_system_ipfarbranch < 1e6",
@@ -1838,7 +1822,7 @@
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / cpu_core@UNC_ARB_DAT_OCCUPANCY.RD\\,cmask\\=1@",
+        "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / UNC_ARB_DAT_OCCUPANCY.RD@cmask\\=1@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
@@ -1846,6 +1830,7 @@
     },
     {
         "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.RD + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.RD",
         "MetricGroup": "Mem;MemoryLat;SoC",
         "MetricName": "tma_info_system_mem_read_latency",
@@ -1854,6 +1839,7 @@
     },
     {
         "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.ALL + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.ALL",
         "MetricGroup": "Mem;SoC",
         "MetricName": "tma_info_system_mem_request_latency",
@@ -1896,7 +1882,7 @@
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
         "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.",
@@ -1904,7 +1890,7 @@
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
-        "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / tma_info_thread_clks",
         "MetricGroup": "Ret;Summary",
         "MetricName": "tma_info_thread_ipc",
         "Unit": "cpu_core"
@@ -1971,7 +1957,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
-        "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@ICACHE_TAG.STALLS@ / tma_info_thread_clks",
         "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
         "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
@@ -1991,7 +1977,6 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
@@ -2002,7 +1987,6 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -2023,7 +2007,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)",
-        "MetricExpr": "DECODE.LCP / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@DECODE.LCP@ / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
         "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
@@ -2044,7 +2028,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations",
-        "MetricExpr": "UOPS_DISPATCHED.PORT_2_3_10 / (3 * tma_info_core_core_clks)",
+        "MetricExpr": "cpu_core@UOPS_DISPATCHED.PORT_2_3_10@ / (3 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_load_op_utilization",
         "MetricThreshold": "tma_load_op_utilization > 0.6",
@@ -2063,7 +2047,7 @@
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk",
-        "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
         "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
@@ -2072,7 +2056,6 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(16 * max(0, cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ - cpu_core@L2_RQSTS.ALL_RFO@) + cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@ * (10 * cpu_core@L2_RQSTS.RFO_HIT@ + min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@))) / tma_info_thread_clks",
         "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
@@ -2135,6 +2118,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group",
         "MetricName": "tma_memory_fence",
@@ -2144,7 +2128,6 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -2154,7 +2137,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit",
-        "MetricExpr": "UOPS_RETIRED.MS / tma_info_thread_slots",
+        "MetricExpr": "cpu_core@UOPS_RETIRED.MS@ / tma_info_thread_slots",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS",
         "MetricName": "tma_microcode_sequencer",
         "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
@@ -2224,7 +2207,6 @@
     },
     {
         "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_other_light_ops",
@@ -2245,7 +2227,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)",
-        "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@UOPS_DISPATCHED.PORT_0@ / tma_info_core_core_clks",
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
@@ -2255,7 +2237,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)",
-        "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@UOPS_DISPATCHED.PORT_1@ / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
@@ -2265,7 +2247,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)",
-        "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@UOPS_DISPATCHED.PORT_6@ / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
@@ -2295,7 +2277,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
         "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
@@ -2305,7 +2287,8 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
+        "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
         "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
@@ -2315,7 +2298,8 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
         "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
@@ -2337,7 +2321,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations",
-        "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@RESOURCE_STALLS.SCOREBOARD@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group",
         "MetricName": "tma_serializing_operation",
         "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))",
@@ -2347,7 +2331,7 @@
     },
     {
         "BriefDescription": "This metric represents Shuffle (cross \"vector lane\" data transfers) uops fraction the CPU has retired.",
-        "MetricExpr": "INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)",
+        "MetricExpr": "cpu_core@INT_VEC_RETIRED.SHUFFLES@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group",
         "MetricName": "tma_shuffles",
         "MetricThreshold": "tma_shuffles > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
@@ -2356,7 +2340,8 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions",
-        "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
         "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))",
@@ -2376,8 +2361,7 @@
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
         "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
@@ -2397,7 +2381,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write",
-        "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@EXE_ACTIVITY.BOUND_ON_STORES@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
         "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
@@ -2407,7 +2391,6 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
@@ -2447,7 +2430,7 @@
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk",
-        "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@ / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
         "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
@@ -2466,7 +2449,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears",
-        "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
         "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
index c150c14ac6ed..a35edf7d86a9 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
@@ -195,7 +195,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hit in DRAM or MMIO (Non-DRAM).",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_BOUND_STALLS.LOAD",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
@@ -457,7 +456,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 Cache.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_BOUND_STALLS.LOAD",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
@@ -466,7 +464,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -683,7 +680,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
diff --git a/tools/perf/pmu-events/arch/x86/amdzen4/memory-controller.json b/tools/perf/pmu-events/arch/x86/amdzen4/memory-controller.json
new file mode 100644
index 000000000000..55263e5e4f69
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/amdzen4/memory-controller.json
@@ -0,0 +1,101 @@
+[
+  {
+    "EventName": "umc_mem_clk",
+    "PublicDescription": "Number of memory clock cycles.",
+    "EventCode": "0x00",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_act_cmd.all",
+    "PublicDescription": "Number of ACTIVATE commands sent.",
+    "EventCode": "0x05",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_act_cmd.rd",
+    "PublicDescription": "Number of ACTIVATE commands sent for reads.",
+    "EventCode": "0x05",
+    "RdWrMask": "0x1",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_act_cmd.wr",
+    "PublicDescription": "Number of ACTIVATE commands sent for writes.",
+    "EventCode": "0x05",
+    "RdWrMask": "0x2",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_pchg_cmd.all",
+    "PublicDescription": "Number of PRECHARGE commands sent.",
+    "EventCode": "0x06",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_pchg_cmd.rd",
+    "PublicDescription": "Number of PRECHARGE commands sent for reads.",
+    "EventCode": "0x06",
+    "RdWrMask": "0x1",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_pchg_cmd.wr",
+    "PublicDescription": "Number of PRECHARGE commands sent for writes.",
+    "EventCode": "0x06",
+    "RdWrMask": "0x2",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_cas_cmd.all",
+    "PublicDescription": "Number of CAS commands sent.",
+    "EventCode": "0x0a",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_cas_cmd.rd",
+    "PublicDescription": "Number of CAS commands sent for reads.",
+    "EventCode": "0x0a",
+    "RdWrMask": "0x1",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_cas_cmd.wr",
+    "PublicDescription": "Number of CAS commands sent for writes.",
+    "EventCode": "0x0a",
+    "RdWrMask": "0x2",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_data_slot_clks.all",
+    "PublicDescription": "Number of clocks used by the data bus.",
+    "EventCode": "0x14",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_data_slot_clks.rd",
+    "PublicDescription": "Number of clocks used by the data bus for reads.",
+    "EventCode": "0x14",
+    "RdWrMask": "0x1",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_data_slot_clks.wr",
+    "PublicDescription": "Number of clocks used by the data bus for writes.",
+    "EventCode": "0x14",
+    "RdWrMask": "0x2",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/x86/amdzen4/recommended.json b/tools/perf/pmu-events/arch/x86/amdzen4/recommended.json
index 5e6a793acf7b..96e06401c6cb 100644
--- a/tools/perf/pmu-events/arch/x86/amdzen4/recommended.json
+++ b/tools/perf/pmu-events/arch/x86/amdzen4/recommended.json
@@ -330,5 +330,89 @@
     "MetricGroup": "data_fabric",
     "PerPkg": "1",
     "ScaleUnit": "6.103515625e-5MiB"
+  },
+  {
+    "MetricName": "umc_data_bus_utilization",
+    "BriefDescription": "Memory controller data bus utilization.",
+    "MetricExpr": "d_ratio(umc_data_slot_clks.all / 2, umc_mem_clk)",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1",
+    "ScaleUnit": "100%"
+  },
+  {
+    "MetricName": "umc_cas_cmd_rate",
+    "BriefDescription": "Memory controller CAS command rate.",
+    "MetricExpr": "d_ratio(umc_cas_cmd.all * 1000, umc_mem_clk)",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1"
+  },
+  {
+    "MetricName": "umc_cas_cmd_read_ratio",
+    "BriefDescription": "Ratio of memory controller CAS commands for reads.",
+    "MetricExpr": "d_ratio(umc_cas_cmd.rd, umc_cas_cmd.all)",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1",
+    "ScaleUnit": "100%"
+  },
+  {
+    "MetricName": "umc_cas_cmd_write_ratio",
+    "BriefDescription": "Ratio of memory controller CAS commands for writes.",
+    "MetricExpr": "d_ratio(umc_cas_cmd.wr, umc_cas_cmd.all)",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1",
+    "ScaleUnit": "100%"
+  },
+  {
+    "MetricName": "umc_mem_read_bandwidth",
+    "BriefDescription": "Estimated memory read bandwidth.",
+    "MetricExpr": "(umc_cas_cmd.rd * 64) / 1e6 / duration_time",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1",
+    "ScaleUnit": "1MB/s"
+  },
+  {
+    "MetricName": "umc_mem_write_bandwidth",
+    "BriefDescription": "Estimated memory write bandwidth.",
+    "MetricExpr": "(umc_cas_cmd.wr * 64) / 1e6 / duration_time",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1",
+    "ScaleUnit": "1MB/s"
+  },
+  {
+    "MetricName": "umc_mem_bandwidth",
+    "BriefDescription": "Estimated combined memory bandwidth.",
+    "MetricExpr": "(umc_cas_cmd.all * 64) / 1e6 / duration_time",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1",
+    "ScaleUnit": "1MB/s"
+  },
+  {
+    "MetricName": "umc_cas_cmd_read_ratio",
+    "BriefDescription": "Ratio of memory controller CAS commands for reads.",
+    "MetricExpr": "d_ratio(umc_cas_cmd.rd, umc_cas_cmd.all)",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1",
+    "ScaleUnit": "100%"
+  },
+  {
+    "MetricName": "umc_cas_cmd_rate",
+    "BriefDescription": "Memory controller CAS command rate.",
+    "MetricExpr": "d_ratio(umc_cas_cmd.all * 1000, umc_mem_clk)",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1"
+  },
+  {
+    "MetricName": "umc_activate_cmd_rate",
+    "BriefDescription": "Memory controller ACTIVATE command rate.",
+    "MetricExpr": "d_ratio(umc_act_cmd.all * 1000, umc_mem_clk)",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1"
+  },
+  {
+    "MetricName": "umc_precharge_cmd_rate",
+    "BriefDescription": "Memory controller PRECHARGE command rate.",
+    "MetricExpr": "d_ratio(umc_pchg_cmd.all * 1000, umc_mem_clk)",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1"
   }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
index 84c132af3dfa..8bc6c0707856 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
@@ -1863,6 +1863,12 @@
         "ScaleUnit": "1GHz"
     },
     {
+        "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data receive bandwidth (MB/sec)",
+        "MetricExpr": "UNC_UPI_RxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time",
+        "MetricName": "upi_data_receive_bw",
+        "ScaleUnit": "1MB/s"
+    },
+    {
         "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)",
         "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time",
         "MetricName": "upi_data_transmit_bw",
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json
index 4a9d211e9d4f..1bdefaf96287 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json
@@ -23,27 +23,48 @@
         "UMask": "0x10"
     },
     {
-        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_0",
+        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0]",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_1",
+        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1]",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_1",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
     {
-        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_5",
+        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2]",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_5",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
     {
+        "BriefDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0]",
+        "EventCode": "0xb3",
+        "EventName": "FP_ARITH_DISPATCHED.V0",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1]",
+        "EventCode": "0xb3",
+        "EventName": "FP_ARITH_DISPATCHED.V1",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5]",
+        "EventCode": "0xb3",
+        "EventName": "FP_ARITH_DISPATCHED.V2",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x4"
+    },
+    {
         "BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json
index 6dcf3b763af4..1f8200fb8964 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json
@@ -1,21 +1,5 @@
 [
     {
-        "BriefDescription": "AMX retired arithmetic BF16 operations.",
-        "EventCode": "0xce",
-        "EventName": "AMX_OPS_RETIRED.BF16",
-        "PublicDescription": "Number of AMX-based retired arithmetic bfloat16 (BF16) floating-point operations. Counts TDPBF16PS FP instructions. SW to use operation multiplier of 4",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x2"
-    },
-    {
-        "BriefDescription": "AMX retired arithmetic integer 8-bit operations.",
-        "EventCode": "0xce",
-        "EventName": "AMX_OPS_RETIRED.INT8",
-        "PublicDescription": "Number of AMX-based retired arithmetic integer operations of 8-bit width source operands. Counts TDPB[SS,UU,US,SU]D instructions. SW should use operation multiplier of 8.",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "This event is deprecated. Refer to new event ARITH.DIV_ACTIVE",
         "CounterMask": "1",
         "Deprecated": "1",
@@ -505,7 +489,7 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "INT_MISC.UNKNOWN_BRANCH_CYCLES",
+        "BriefDescription": "Bubble cycles of BAClear (Unknown Branch).",
         "EventCode": "0xad",
         "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES",
         "MSRIndex": "0x3F7",
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-interconnect.json
index 09d840c7da4c..65d088556bae 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-interconnect.json
@@ -4825,11 +4825,11 @@
         "Unit": "M3UPI"
     },
     {
-        "BriefDescription": "Number of allocations into the CRS Egress  used to queue up requests destined to the mesh (AD Bouncable)",
+        "BriefDescription": "Number of allocations into the CRS Egress  used to queue up requests destined to the mesh (AD Bounceable)",
         "EventCode": "0x47",
         "EventName": "UNC_MDF_CRS_TxR_INSERTS.AD_BNC",
         "PerPkg": "1",
-        "PublicDescription": "AD Bouncable : Number of allocations into the CRS Egress",
+        "PublicDescription": "AD Bounceable : Number of allocations into the CRS Egress",
         "UMask": "0x1",
         "Unit": "MDF"
     },
@@ -4861,11 +4861,11 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Number of allocations into the CRS Egress  used to queue up requests destined to the mesh (BL Bouncable)",
+        "BriefDescription": "Number of allocations into the CRS Egress  used to queue up requests destined to the mesh (BL Bounceable)",
         "EventCode": "0x47",
         "EventName": "UNC_MDF_CRS_TxR_INSERTS.BL_BNC",
         "PerPkg": "1",
-        "PublicDescription": "BL Bouncable : Number of allocations into the CRS Egress",
+        "PublicDescription": "BL Bounceable : Number of allocations into the CRS Egress",
         "UMask": "0x4",
         "Unit": "MDF"
     },
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-io.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-io.json
index 557080b74ee5..0761980c34a0 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-io.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-io.json
@@ -1186,6 +1186,36 @@
         "Unit": "IIO"
     },
     {
+        "BriefDescription": ": IOTLB Hits to a 1G Page",
+        "EventCode": "0x40",
+        "EventName": "UNC_IIO_IOMMU0.1G_HITS",
+        "PerPkg": "1",
+        "PortMask": "0x0000",
+        "PublicDescription": ": IOTLB Hits to a 1G Page : Counts if a transaction to a 1G page, on its first lookup, hits the IOTLB.",
+        "UMask": "0x10",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": ": IOTLB Hits to a 2M Page",
+        "EventCode": "0x40",
+        "EventName": "UNC_IIO_IOMMU0.2M_HITS",
+        "PerPkg": "1",
+        "PortMask": "0x0000",
+        "PublicDescription": ": IOTLB Hits to a 2M Page : Counts if a transaction to a 2M page, on its first lookup, hits the IOTLB.",
+        "UMask": "0x8",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": ": IOTLB Hits to a 4K Page",
+        "EventCode": "0x40",
+        "EventName": "UNC_IIO_IOMMU0.4K_HITS",
+        "PerPkg": "1",
+        "PortMask": "0x0000",
+        "PublicDescription": ": IOTLB Hits to a 4K Page : Counts if a transaction to a 4K page, on its first lookup, hits the IOTLB.",
+        "UMask": "0x4",
+        "Unit": "IIO"
+    },
+    {
         "BriefDescription": ": Context cache hits",
         "EventCode": "0x40",
         "EventName": "UNC_IIO_IOMMU0.CTXT_CACHE_HITS",
diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
index e98602c66707..71d78a7841ea 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
@@ -1847,6 +1847,12 @@
         "ScaleUnit": "1GHz"
     },
     {
+        "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data receive bandwidth (MB/sec)",
+        "MetricExpr": "UNC_UPI_RxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time",
+        "MetricName": "upi_data_receive_bw",
+        "ScaleUnit": "1MB/s"
+    },
+    {
         "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)",
         "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time",
         "MetricName": "upi_data_transmit_bw",
diff --git a/tools/perf/pmu-events/arch/x86/icelakex/other.json b/tools/perf/pmu-events/arch/x86/icelakex/other.json
index 63d5faf2fc43..11810daaf150 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/other.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/other.json
@@ -19,7 +19,7 @@
         "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule.",
         "EventCode": "0x28",
         "EventName": "CORE_POWER.LVL2_TURBO_LICENSE",
-        "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server microarchtecture).  This includes high current AVX 512-bit instructions.",
+        "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server microarchitecture).  This includes high current AVX 512-bit instructions.",
         "SampleAfterValue": "200003",
         "UMask": "0x20"
     },
diff --git a/tools/perf/pmu-events/arch/x86/icelakex/pipeline.json b/tools/perf/pmu-events/arch/x86/icelakex/pipeline.json
index 176e5ef2a24a..45ee6bceba7f 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/pipeline.json
@@ -519,7 +519,7 @@
         "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread",
         "EventCode": "0x5e",
         "EventName": "RS_EVENTS.EMPTY_CYCLES",
-        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into stravation periods (e.g. branch mispredictions or i-cache misses)",
+        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
diff --git a/tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json
index f87ea3f66d1b..a066a009c511 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json
@@ -38,7 +38,7 @@
         "EventCode": "0x10",
         "EventName": "UNC_I_COHERENT_OPS.CLFLUSH",
         "PerPkg": "1",
-        "PublicDescription": "Coherent Ops : CLFlush : Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Coherent Ops : CLFlush : Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x80",
         "Unit": "IRP"
     },
@@ -65,7 +65,7 @@
         "EventCode": "0x10",
         "EventName": "UNC_I_COHERENT_OPS.WBMTOI",
         "PerPkg": "1",
-        "PublicDescription": "Coherent Ops : WbMtoI : Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Coherent Ops : WbMtoI : Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x40",
         "Unit": "IRP"
     },
@@ -454,7 +454,7 @@
         "EventCode": "0x11",
         "EventName": "UNC_I_TRANSACTIONS.WRITES",
         "PerPkg": "1",
-        "PublicDescription": "Inbound Transaction Count : Writes : Counts the number of Inbound transactions from the IRP to the Uncore.  This can be filtered based on request type in addition to the source queue.  Note the special filtering equation.  We do OR-reduction on the request type.  If the SOURCE bit is set, then we also do AND qualification based on the source portID. : Trackes only write requests.  Each write request should have a prefetch, so there is no need to explicitly track these requests.  For writes that are tickled and have to retry, the counter will be incremented for each retry.",
+        "PublicDescription": "Inbound Transaction Count : Writes : Counts the number of Inbound transactions from the IRP to the Uncore.  This can be filtered based on request type in addition to the source queue.  Note the special filtering equation.  We do OR-reduction on the request type.  If the SOURCE bit is set, then we also do AND qualification based on the source portID. : Tracks only write requests.  Each write request should have a prefetch, so there is no need to explicitly track these requests.  For writes that are tickled and have to retry, the counter will be incremented for each retry.",
         "UMask": "0x2",
         "Unit": "IRP"
     },
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index e571683f59f3..4d1deed4437a 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -7,7 +7,7 @@ GenuineIntel-6-56,v11,broadwellde,core
 GenuineIntel-6-4F,v22,broadwellx,core
 GenuineIntel-6-55-[56789ABCDEF],v1.20,cascadelakex,core
 GenuineIntel-6-9[6C],v1.04,elkhartlake,core
-GenuineIntel-6-CF,v1.01,emeraldrapids,core
+GenuineIntel-6-CF,v1.02,emeraldrapids,core
 GenuineIntel-6-5[CF],v13,goldmont,core
 GenuineIntel-6-7A,v1.01,goldmontplus,core
 GenuineIntel-6-B6,v1.00,grandridge,core
@@ -15,7 +15,7 @@ GenuineIntel-6-A[DE],v1.01,graniterapids,core
 GenuineIntel-6-(3C|45|46),v33,haswell,core
 GenuineIntel-6-3F,v28,haswellx,core
 GenuineIntel-6-7[DE],v1.19,icelake,core
-GenuineIntel-6-6[AC],v1.21,icelakex,core
+GenuineIntel-6-6[AC],v1.23,icelakex,core
 GenuineIntel-6-3A,v24,ivybridge,core
 GenuineIntel-6-3E,v24,ivytown,core
 GenuineIntel-6-2D,v24,jaketown,core
@@ -26,7 +26,7 @@ GenuineIntel-6-1[AEF],v4,nehalemep,core
 GenuineIntel-6-2E,v4,nehalemex,core
 GenuineIntel-6-A7,v1.01,rocketlake,core
 GenuineIntel-6-2A,v19,sandybridge,core
-GenuineIntel-6-8F,v1.16,sapphirerapids,core
+GenuineIntel-6-8F,v1.17,sapphirerapids,core
 GenuineIntel-6-AF,v1.00,sierraforest,core
 GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core
 GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v57,skylake,core
diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json b/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json
index 0c880e415669..27433fc15ede 100644
--- a/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json
@@ -985,7 +985,7 @@
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / cpu@UNC_ARB_DAT_OCCUPANCY.RD\\,cmask\\=1@",
+        "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / UNC_ARB_DAT_OCCUPANCY.RD@cmask\\=1@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches"
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json
index 4a9d211e9d4f..1bdefaf96287 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json
@@ -23,27 +23,48 @@
         "UMask": "0x10"
     },
     {
-        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_0",
+        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0]",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_1",
+        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1]",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_1",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
     {
-        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_5",
+        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2]",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_5",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
     {
+        "BriefDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0]",
+        "EventCode": "0xb3",
+        "EventName": "FP_ARITH_DISPATCHED.V0",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1]",
+        "EventCode": "0xb3",
+        "EventName": "FP_ARITH_DISPATCHED.V1",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5]",
+        "EventCode": "0xb3",
+        "EventName": "FP_ARITH_DISPATCHED.V2",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x4"
+    },
+    {
         "BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json
index 6dcf3b763af4..2cfe814d2015 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json
@@ -505,7 +505,7 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "INT_MISC.UNKNOWN_BRANCH_CYCLES",
+        "BriefDescription": "Bubble cycles of BAClear (Unknown Branch).",
         "EventCode": "0xad",
         "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES",
         "MSRIndex": "0x3F7",
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
index 06c6d67cb76b..56e54babcc26 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
@@ -400,7 +400,6 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(76 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 75.5 * tma_info_system_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
@@ -421,7 +420,6 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "75.5 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
@@ -449,7 +447,6 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks - tma_pmm_bound if #has_pmem > 0 else MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks)",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
@@ -656,7 +653,6 @@
     },
     {
         "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;BrMispredicts;tma_issueBM",
         "MetricName": "tma_info_bad_spec_branch_misprediction_cost",
@@ -699,7 +695,6 @@
     },
     {
         "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)",
         "MetricGroup": "Cor;SMT",
         "MetricName": "tma_info_botlnk_l0_core_bound_likely",
@@ -707,7 +702,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
@@ -716,7 +710,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
@@ -725,7 +718,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC",
         "MetricName": "tma_info_bottleneck_big_code",
@@ -742,7 +734,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code",
         "MetricGroup": "Fed;FetchBW;Frontend",
         "MetricName": "tma_info_bottleneck_instruction_fetch_bw",
@@ -750,7 +741,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))",
         "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_info_bottleneck_memory_bandwidth",
@@ -759,7 +749,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_info_bottleneck_memory_data_tlbs",
@@ -768,7 +757,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound))",
         "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_info_bottleneck_memory_latency",
@@ -777,7 +765,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM",
         "MetricName": "tma_info_bottleneck_mispredictions",
@@ -1301,6 +1288,7 @@
     },
     {
         "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / duration_time)",
         "MetricGroup": "Mem;MemoryLat;SoC",
         "MetricName": "tma_info_system_mem_read_latency",
@@ -1455,7 +1443,6 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
@@ -1465,7 +1452,6 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -1538,7 +1524,6 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks",
         "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
@@ -1596,6 +1581,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group",
         "MetricName": "tma_memory_fence",
@@ -1604,7 +1590,6 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -1676,7 +1661,6 @@
     },
     {
         "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_other_light_ops",
@@ -1758,6 +1742,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
@@ -1767,6 +1752,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
@@ -1822,6 +1808,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
@@ -1840,7 +1827,6 @@
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
@@ -1868,7 +1854,6 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
@@ -1965,6 +1950,12 @@
         "ScaleUnit": "1GHz"
     },
     {
+        "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data receive bandwidth (MB/sec)",
+        "MetricExpr": "UNC_UPI_RxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time",
+        "MetricName": "upi_data_receive_bw",
+        "ScaleUnit": "1MB/s"
+    },
+    {
         "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)",
         "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time",
         "MetricName": "upi_data_transmit_bw",
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json
index 09d840c7da4c..65d088556bae 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json
@@ -4825,11 +4825,11 @@
         "Unit": "M3UPI"
     },
     {
-        "BriefDescription": "Number of allocations into the CRS Egress  used to queue up requests destined to the mesh (AD Bouncable)",
+        "BriefDescription": "Number of allocations into the CRS Egress  used to queue up requests destined to the mesh (AD Bounceable)",
         "EventCode": "0x47",
         "EventName": "UNC_MDF_CRS_TxR_INSERTS.AD_BNC",
         "PerPkg": "1",
-        "PublicDescription": "AD Bouncable : Number of allocations into the CRS Egress",
+        "PublicDescription": "AD Bounceable : Number of allocations into the CRS Egress",
         "UMask": "0x1",
         "Unit": "MDF"
     },
@@ -4861,11 +4861,11 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Number of allocations into the CRS Egress  used to queue up requests destined to the mesh (BL Bouncable)",
+        "BriefDescription": "Number of allocations into the CRS Egress  used to queue up requests destined to the mesh (BL Bounceable)",
         "EventCode": "0x47",
         "EventName": "UNC_MDF_CRS_TxR_INSERTS.BL_BNC",
         "PerPkg": "1",
-        "PublicDescription": "BL Bouncable : Number of allocations into the CRS Egress",
+        "PublicDescription": "BL Bounceable : Number of allocations into the CRS Egress",
         "UMask": "0x4",
         "Unit": "MDF"
     },
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-io.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-io.json
index 8b5f54fed103..03596db87710 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-io.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-io.json
@@ -1250,6 +1250,36 @@
         "Unit": "IIO"
     },
     {
+        "BriefDescription": ": IOTLB Hits to a 1G Page",
+        "EventCode": "0x40",
+        "EventName": "UNC_IIO_IOMMU0.1G_HITS",
+        "PerPkg": "1",
+        "PortMask": "0x0000",
+        "PublicDescription": ": IOTLB Hits to a 1G Page : Counts if a transaction to a 1G page, on its first lookup, hits the IOTLB.",
+        "UMask": "0x10",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": ": IOTLB Hits to a 2M Page",
+        "EventCode": "0x40",
+        "EventName": "UNC_IIO_IOMMU0.2M_HITS",
+        "PerPkg": "1",
+        "PortMask": "0x0000",
+        "PublicDescription": ": IOTLB Hits to a 2M Page : Counts if a transaction to a 2M page, on its first lookup, hits the IOTLB.",
+        "UMask": "0x8",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": ": IOTLB Hits to a 4K Page",
+        "EventCode": "0x40",
+        "EventName": "UNC_IIO_IOMMU0.4K_HITS",
+        "PerPkg": "1",
+        "PortMask": "0x0000",
+        "PublicDescription": ": IOTLB Hits to a 4K Page : Counts if a transaction to a 4K page, on its first lookup, hits the IOTLB.",
+        "UMask": "0x4",
+        "Unit": "IIO"
+    },
+    {
         "BriefDescription": ": Context cache hits",
         "EventCode": "0x40",
         "EventName": "UNC_IIO_IOMMU0.CTXT_CACHE_HITS",
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
index 4a8f8eeb7525..ec3aa5ef00a3 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
@@ -1807,6 +1807,12 @@
         "ScaleUnit": "1GHz"
     },
     {
+        "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data receive bandwidth (MB/sec)",
+        "MetricExpr": "UNC_UPI_RxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time",
+        "MetricName": "upi_data_receive_bw",
+        "ScaleUnit": "1MB/s"
+    },
+    {
         "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)",
         "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time",
         "MetricName": "upi_data_transmit_bw",
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 3c091ab75305..53ab050c8fa4 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -83,7 +83,7 @@ def c_len(s: str) -> int:
   """Return the length of s a C string
 
   This doesn't handle all escape characters properly. It first assumes
-  all \ are for escaping, it then adjusts as it will have over counted
+  all \\ are for escaping, it then adjusts as it will have over counted
   \\. The code uses \000 rather than \0 as a terminator as an adjacent
   number would be folded into a string of \0 (ie. "\0" + "5" doesn't
   equal a terminator followed by the number 5 but the escape of
@@ -286,6 +286,7 @@ class JsonEvent:
           'imx8_ddr': 'imx8_ddr',
           'L3PMC': 'amd_l3',
           'DFPMC': 'amd_df',
+          'UMCPMC': 'amd_umc',
           'cpu_core': 'cpu_core',
           'cpu_atom': 'cpu_atom',
           'ali_drw': 'ali_drw',
@@ -354,6 +355,7 @@ class JsonEvent:
         ('SampleAfterValue', 'period='),
         ('UMask', 'umask='),
         ('NodeType', 'type='),
+        ('RdWrMask', 'rdwrmask='),
     ]
     for key, value in event_fields:
       if key in jd and jd[key] != '0':
diff --git a/tools/perf/scripts/python/arm-cs-trace-disasm.py b/tools/perf/scripts/python/arm-cs-trace-disasm.py
index d59ff53f1d94..d973c2baed1c 100755
--- a/tools/perf/scripts/python/arm-cs-trace-disasm.py
+++ b/tools/perf/scripts/python/arm-cs-trace-disasm.py
@@ -45,8 +45,8 @@ parser = OptionParser(option_list=option_list)
 # Initialize global dicts and regular expression
 disasm_cache = dict()
 cpu_data = dict()
-disasm_re = re.compile("^\s*([0-9a-fA-F]+):")
-disasm_func_re = re.compile("^\s*([0-9a-fA-F]+)\s.*:")
+disasm_re = re.compile(r"^\s*([0-9a-fA-F]+):")
+disasm_func_re = re.compile(r"^\s*([0-9a-fA-F]+)\s.*:")
 cache_size = 64*1024
 
 glb_source_file_name	= None
@@ -188,6 +188,17 @@ def process_event(param_dict):
 	dso_end = get_optional(param_dict, "dso_map_end")
 	symbol = get_optional(param_dict, "symbol")
 
+	cpu = sample["cpu"]
+	ip = sample["ip"]
+	addr = sample["addr"]
+
+	# Initialize CPU data if it's empty, and directly return back
+	# if this is the first tracing event for this CPU.
+	if (cpu_data.get(str(cpu) + 'addr') == None):
+		cpu_data[str(cpu) + 'addr'] = addr
+		return
+
+
 	if (options.verbose == True):
 		print("Event type: %s" % name)
 		print_sample(sample)
@@ -209,16 +220,6 @@ def process_event(param_dict):
 	if (name[0:8] != "branches"):
 		return
 
-	cpu = sample["cpu"]
-	ip = sample["ip"]
-	addr = sample["addr"]
-
-	# Initialize CPU data if it's empty, and directly return back
-	# if this is the first tracing event for this CPU.
-	if (cpu_data.get(str(cpu) + 'addr') == None):
-		cpu_data[str(cpu) + 'addr'] = addr
-		return
-
 	# The format for packet is:
 	#
 	#		  +------------+------------+------------+
@@ -258,8 +259,9 @@ def process_event(param_dict):
 
 	if (options.objdump_name != None):
 		# It doesn't need to decrease virtual memory offset for disassembly
-		# for kernel dso, so in this case we set vm_start to zero.
-		if (dso == "[kernel.kallsyms]"):
+		# for kernel dso and executable file dso, so in this case we set
+		# vm_start to zero.
+		if (dso == "[kernel.kallsyms]" or dso_start == 0x400000):
 			dso_vm_start = 0
 		else:
 			dso_vm_start = int(dso_start)
diff --git a/tools/perf/scripts/python/compaction-times.py b/tools/perf/scripts/python/compaction-times.py
index 2560a042dc6f..9401f7c14747 100644
--- a/tools/perf/scripts/python/compaction-times.py
+++ b/tools/perf/scripts/python/compaction-times.py
@@ -260,7 +260,7 @@ def pr_help():
 
 comm_re = None
 pid_re = None
-pid_regex = "^(\d*)-(\d*)$|^(\d*)$"
+pid_regex = r"^(\d*)-(\d*)$|^(\d*)$"
 
 opt_proc = popt.DISP_DFL
 opt_disp = topt.DISP_ALL
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 13f2d8a81610..121cf61ba1b3 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -677,8 +677,8 @@ class CallGraphModelBase(TreeModel):
 			#   sqlite supports GLOB (text only) which uses * and ? and is case sensitive
 			if not self.glb.dbref.is_sqlite3:
 				# Escape % and _
-				s = value.replace("%", "\%")
-				s = s.replace("_", "\_")
+				s = value.replace("%", "\\%")
+				s = s.replace("_", "\\_")
 				# Translate * and ? into SQL LIKE pattern characters % and _
 				trans = string.maketrans("*?", "%_")
 				match = " LIKE '" + str(s).translate(trans) + "'"
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 2b45ffa462a6..53ba9c3e20e0 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -77,3 +77,17 @@ CFLAGS_python-use.o   += -DPYTHONPATH="BUILD_STR($(OUTPUT)python)" -DPYTHON="BUI
 CFLAGS_dwarf-unwind.o += -fno-optimize-sibling-calls
 
 perf-y += workloads/
+
+ifdef SHELLCHECK
+  SHELL_TESTS := $(shell find tests/shell -executable -type f -name '*.sh')
+  TEST_LOGS := $(SHELL_TESTS:tests/shell/%=shell/%.shellcheck_log)
+else
+  SHELL_TESTS :=
+  TEST_LOGS :=
+endif
+
+$(OUTPUT)%.shellcheck_log: %
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,test)shellcheck -a -S warning "$<" > $@ || (cat $@ && rm $@ && false)
+
+perf-y += $(TEST_LOGS)
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 61186d0d1cfa..97e1bdd6ec0e 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -188,7 +188,7 @@ static int test__attr(struct test_suite *test __maybe_unused, int subtest __mayb
 	if (perf_pmus__num_core_pmus() > 1) {
 		/*
 		 * TODO: Attribute tests hard code the PMU type. If there are >1
-		 * core PMU then each PMU will have a different type whic
+		 * core PMU then each PMU will have a different type which
 		 * requires additional support.
 		 */
 		pr_debug("Skip test on hybrid systems");
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
index 27c21271a16c..b44e4e6e4443 100644
--- a/tools/perf/tests/attr/base-record
+++ b/tools/perf/tests/attr/base-record
@@ -6,7 +6,7 @@ flags=0|8
 cpu=*
 type=0|1
 size=136
-config=0
+config=0|1
 sample_period=*
 sample_type=263
 read_format=0|4|20
diff --git a/tools/perf/tests/attr/test-record-user-regs-no-sve-aarch64 b/tools/perf/tests/attr/test-record-user-regs-no-sve-aarch64
index fbb065842880..bed765450ca9 100644
--- a/tools/perf/tests/attr/test-record-user-regs-no-sve-aarch64
+++ b/tools/perf/tests/attr/test-record-user-regs-no-sve-aarch64
@@ -6,4 +6,4 @@ args    = --no-bpf-event --user-regs=vg kill >/dev/null 2>&1
 ret     = 129
 test_ret = true
 arch    = aarch64
-auxv    = auxv["AT_HWCAP"] & 0x200000 == 0
+auxv    = auxv["AT_HWCAP"] & 0x400000 == 0
diff --git a/tools/perf/tests/attr/test-record-user-regs-sve-aarch64 b/tools/perf/tests/attr/test-record-user-regs-sve-aarch64
index c598c803221d..a65113cd7311 100644
--- a/tools/perf/tests/attr/test-record-user-regs-sve-aarch64
+++ b/tools/perf/tests/attr/test-record-user-regs-sve-aarch64
@@ -6,7 +6,7 @@ args    = --no-bpf-event --user-regs=vg kill >/dev/null 2>&1
 ret     = 1
 test_ret = true
 arch    = aarch64
-auxv    = auxv["AT_HWCAP"] & 0x200000 == 0x200000
+auxv    = auxv["AT_HWCAP"] & 0x400000 == 0x400000
 kernel_since = 6.1
 
 [event:base-record]
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index cb6f1dd00dc4..4a5973f9bb9b 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -14,6 +14,7 @@
 #include <sys/wait.h>
 #include <sys/stat.h>
 #include "builtin.h"
+#include "config.h"
 #include "hist.h"
 #include "intlist.h"
 #include "tests.h"
@@ -32,6 +33,7 @@
 
 static bool dont_fork;
 const char *dso_to_test;
+const char *test_objdump_path = "objdump";
 
 /*
  * List of architecture specific tests. Not a weak symbol as the array length is
@@ -60,8 +62,6 @@ static struct test_suite *generic_tests[] = {
 	&suite__pmu,
 	&suite__pmu_events,
 	&suite__dso_data,
-	&suite__dso_data_cache,
-	&suite__dso_data_reopen,
 	&suite__perf_evsel__roundtrip_name_test,
 #ifdef HAVE_LIBTRACEEVENT
 	&suite__perf_evsel__tp_sched_test,
@@ -513,6 +513,15 @@ static int run_workload(const char *work, int argc, const char **argv)
 	return -1;
 }
 
+static int perf_test__config(const char *var, const char *value,
+			     void *data __maybe_unused)
+{
+	if (!strcmp(var, "annotate.objdump"))
+		test_objdump_path = value;
+
+	return 0;
+}
+
 int cmd_test(int argc, const char **argv)
 {
 	const char *test_usage[] = {
@@ -529,6 +538,8 @@ int cmd_test(int argc, const char **argv)
 		    "Do not fork for testcase"),
 	OPT_STRING('w', "workload", &workload, "work", "workload to run for testing"),
 	OPT_STRING(0, "dso", &dso_to_test, "dso", "dso to test"),
+	OPT_STRING(0, "objdump", &test_objdump_path, "path",
+		   "objdump binary to use for disassembly and annotations"),
 	OPT_END()
 	};
 	const char * const test_subcommands[] = { "list", NULL };
@@ -538,6 +549,8 @@ int cmd_test(int argc, const char **argv)
         if (ret < 0)
                 return ret;
 
+	perf_config(perf_test__config, NULL);
+
 	/* Unbuffered output */
 	setvbuf(stdout, NULL, _IONBF, 0);
 
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 3af81012014e..7a3a7bbbec71 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -185,7 +185,7 @@ static int read_via_objdump(const char *filename, u64 addr, void *buf,
 	int ret;
 
 	fmt = "%s -z -d --start-address=0x%"PRIx64" --stop-address=0x%"PRIx64" %s";
-	ret = snprintf(cmd, sizeof(cmd), fmt, "objdump", addr, addr + len,
+	ret = snprintf(cmd, sizeof(cmd), fmt, test_objdump_path, addr, addr + len,
 		       filename);
 	if (ret <= 0 || (size_t)ret >= sizeof(cmd))
 		return -1;
@@ -511,38 +511,6 @@ static void fs_something(void)
 	}
 }
 
-#ifdef __s390x__
-#include "header.h" // for get_cpuid()
-#endif
-
-static const char *do_determine_event(bool excl_kernel)
-{
-	const char *event = excl_kernel ? "cycles:u" : "cycles";
-
-#ifdef __s390x__
-	char cpuid[128], model[16], model_c[16], cpum_cf_v[16];
-	unsigned int family;
-	int ret, cpum_cf_a;
-
-	if (get_cpuid(cpuid, sizeof(cpuid)))
-		goto out_clocks;
-	ret = sscanf(cpuid, "%*[^,],%u,%[^,],%[^,],%[^,],%x", &family, model_c,
-		     model, cpum_cf_v, &cpum_cf_a);
-	if (ret != 5)		 /* Not available */
-		goto out_clocks;
-	if (excl_kernel && (cpum_cf_a & 4))
-		return event;
-	if (!excl_kernel && (cpum_cf_a & 2))
-		return event;
-
-	/* Fall through: missing authorization */
-out_clocks:
-	event = excl_kernel ? "cpu-clock:u" : "cpu-clock";
-
-#endif
-	return event;
-}
-
 static void do_something(void)
 {
 	fs_something();
@@ -583,8 +551,10 @@ static int do_test_code_reading(bool try_kcore)
 	int err = -1, ret;
 	pid_t pid;
 	struct map *map;
-	bool have_vmlinux, have_kcore, excl_kernel = false;
+	bool have_vmlinux, have_kcore;
 	struct dso *dso;
+	const char *events[] = { "cycles", "cycles:u", "cpu-clock", "cpu-clock:u", NULL };
+	int evidx = 0;
 
 	pid = getpid();
 
@@ -618,7 +588,7 @@ static int do_test_code_reading(bool try_kcore)
 
 	/* No point getting kernel events if there is no kernel object */
 	if (!have_vmlinux && !have_kcore)
-		excl_kernel = true;
+		evidx++;
 
 	threads = thread_map__new_by_tid(pid);
 	if (!threads) {
@@ -640,13 +610,13 @@ static int do_test_code_reading(bool try_kcore)
 		goto out_put;
 	}
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus) {
 		pr_debug("perf_cpu_map__new failed\n");
 		goto out_put;
 	}
 
-	while (1) {
+	while (events[evidx]) {
 		const char *str;
 
 		evlist = evlist__new();
@@ -657,7 +627,7 @@ static int do_test_code_reading(bool try_kcore)
 
 		perf_evlist__set_maps(&evlist->core, cpus, threads);
 
-		str = do_determine_event(excl_kernel);
+		str = events[evidx];
 		pr_debug("Parsing event '%s'\n", str);
 		ret = parse_event(evlist, str);
 		if (ret < 0) {
@@ -675,32 +645,32 @@ static int do_test_code_reading(bool try_kcore)
 
 		ret = evlist__open(evlist);
 		if (ret < 0) {
-			if (!excl_kernel) {
-				excl_kernel = true;
-				/*
-				 * Both cpus and threads are now owned by evlist
-				 * and will be freed by following perf_evlist__set_maps
-				 * call. Getting reference to keep them alive.
-				 */
-				perf_cpu_map__get(cpus);
-				perf_thread_map__get(threads);
-				perf_evlist__set_maps(&evlist->core, NULL, NULL);
-				evlist__delete(evlist);
-				evlist = NULL;
-				continue;
-			}
+			evidx++;
 
-			if (verbose > 0) {
+			if (events[evidx] == NULL && verbose > 0) {
 				char errbuf[512];
 				evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));
 				pr_debug("perf_evlist__open() failed!\n%s\n", errbuf);
 			}
 
-			goto out_put;
+			/*
+			 * Both cpus and threads are now owned by evlist
+			 * and will be freed by following perf_evlist__set_maps
+			 * call. Getting reference to keep them alive.
+			 */
+			perf_cpu_map__get(cpus);
+			perf_thread_map__get(threads);
+			perf_evlist__set_maps(&evlist->core, NULL, NULL);
+			evlist__delete(evlist);
+			evlist = NULL;
+			continue;
 		}
 		break;
 	}
 
+	if (events[evidx] == NULL)
+		goto out_put;
+
 	ret = evlist__mmap(evlist, UINT_MAX);
 	if (ret < 0) {
 		pr_debug("evlist__mmap failed\n");
@@ -721,7 +691,7 @@ static int do_test_code_reading(bool try_kcore)
 		err = TEST_CODE_READING_NO_KERNEL_OBJ;
 	else if (!have_vmlinux && !try_kcore)
 		err = TEST_CODE_READING_NO_VMLINUX;
-	else if (excl_kernel)
+	else if (strstr(events[evidx], ":u"))
 		err = TEST_CODE_READING_NO_ACCESS;
 	else
 		err = TEST_CODE_READING_OK;
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index 7730fc2ab40b..bd8e396f3e57 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -213,7 +213,7 @@ static int test__cpu_map_intersect(struct test_suite *test __maybe_unused,
 
 static int test__cpu_map_equal(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
-	struct perf_cpu_map *any = perf_cpu_map__dummy_new();
+	struct perf_cpu_map *any = perf_cpu_map__new_any_cpu();
 	struct perf_cpu_map *one = perf_cpu_map__new("1");
 	struct perf_cpu_map *two = perf_cpu_map__new("2");
 	struct perf_cpu_map *empty = perf_cpu_map__intersect(one, two);
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 3419a4ab5590..2d67422c1222 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -394,6 +394,15 @@ static int test__dso_data_reopen(struct test_suite *test __maybe_unused, int sub
 	return 0;
 }
 
-DEFINE_SUITE("DSO data read", dso_data);
-DEFINE_SUITE("DSO data cache", dso_data_cache);
-DEFINE_SUITE("DSO data reopen", dso_data_reopen);
+
+static struct test_case tests__dso_data[] = {
+	TEST_CASE("read", dso_data),
+	TEST_CASE("cache", dso_data_cache),
+	TEST_CASE("reopen", dso_data_reopen),
+	{	.name = NULL, }
+};
+
+struct test_suite suite__dso_data = {
+	.desc = "DSO data tests",
+	.test_cases = tests__dso_data,
+};
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 8f4f9b632e1e..5a3b2bed07f3 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -81,7 +81,7 @@ static int test__keep_tracking(struct test_suite *test __maybe_unused, int subte
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	CHECK_NOT_NULL__(threads);
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	CHECK_NOT_NULL__(cpus);
 
 	evlist = evlist__new();
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index d9945ed25bc5..8a4da7eb637a 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -183,7 +183,7 @@ run += make_install_prefix_slash
 # run += make_install_pdf
 run += make_minimal
 
-old_libbpf := $(shell echo '\#include <bpf/libbpf.h>' | $(CC) -E -dM -x c -| egrep -q "define[[:space:]]+LIBBPF_MAJOR_VERSION[[:space:]]+0{1}")
+old_libbpf := $(shell echo '\#include <bpf/libbpf.h>' | $(CC) -E -dM -x c -| grep -q -E "define[[:space:]]+LIBBPF_MAJOR_VERSION[[:space:]]+0{1}")
 
 ifneq ($(old_libbpf),)
 run += make_libbpf_dynamic
diff --git a/tools/perf/tests/maps.c b/tools/perf/tests/maps.c
index 5bb1123a91a7..bb3fbfe5a73e 100644
--- a/tools/perf/tests/maps.c
+++ b/tools/perf/tests/maps.c
@@ -14,44 +14,59 @@ struct map_def {
 	u64 end;
 };
 
+struct check_maps_cb_args {
+	struct map_def *merged;
+	unsigned int i;
+};
+
+static int check_maps_cb(struct map *map, void *data)
+{
+	struct check_maps_cb_args *args = data;
+	struct map_def *merged = &args->merged[args->i];
+
+	if (map__start(map) != merged->start ||
+	    map__end(map) != merged->end ||
+	    strcmp(map__dso(map)->name, merged->name) ||
+	    refcount_read(map__refcnt(map)) != 1) {
+		return 1;
+	}
+	args->i++;
+	return 0;
+}
+
+static int failed_cb(struct map *map, void *data __maybe_unused)
+{
+	pr_debug("\tstart: %" PRIu64 " end: %" PRIu64 " name: '%s' refcnt: %d\n",
+		map__start(map),
+		map__end(map),
+		map__dso(map)->name,
+		refcount_read(map__refcnt(map)));
+
+	return 0;
+}
+
 static int check_maps(struct map_def *merged, unsigned int size, struct maps *maps)
 {
-	struct map_rb_node *rb_node;
-	unsigned int i = 0;
 	bool failed = false;
 
 	if (maps__nr_maps(maps) != size) {
 		pr_debug("Expected %d maps, got %d", size, maps__nr_maps(maps));
 		failed = true;
 	} else {
-		maps__for_each_entry(maps, rb_node) {
-			struct map *map = rb_node->map;
-
-			if (map__start(map) != merged[i].start ||
-			    map__end(map) != merged[i].end ||
-			    strcmp(map__dso(map)->name, merged[i].name) ||
-			    refcount_read(map__refcnt(map)) != 1) {
-				failed = true;
-			}
-			i++;
-		}
+		struct check_maps_cb_args args = {
+			.merged = merged,
+			.i = 0,
+		};
+		failed = maps__for_each_map(maps, check_maps_cb, &args);
 	}
 	if (failed) {
 		pr_debug("Expected:\n");
-		for (i = 0; i < size; i++) {
+		for (unsigned int i = 0; i < size; i++) {
 			pr_debug("\tstart: %" PRIu64 " end: %" PRIu64 " name: '%s' refcnt: 1\n",
 				merged[i].start, merged[i].end, merged[i].name);
 		}
 		pr_debug("Got:\n");
-		maps__for_each_entry(maps, rb_node) {
-			struct map *map = rb_node->map;
-
-			pr_debug("\tstart: %" PRIu64 " end: %" PRIu64 " name: '%s' refcnt: %d\n",
-				map__start(map),
-				map__end(map),
-				map__dso(map)->name,
-				refcount_read(map__refcnt(map)));
-		}
+		maps__for_each_map(maps, failed_cb, NULL);
 	}
 	return failed ? TEST_FAIL : TEST_OK;
 }
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 886a13a77a16..012c8ae439fd 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -52,7 +52,7 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest
 		return -1;
 	}
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	if (cpus == NULL) {
 		pr_debug("perf_cpu_map__new\n");
 		goto out_free_threads;
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index f3275be83a33..fb114118c876 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -37,7 +37,7 @@ static int test__openat_syscall_event_on_all_cpus(struct test_suite *test __mayb
 		return -1;
 	}
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	if (cpus == NULL) {
 		pr_debug("perf_cpu_map__new\n");
 		goto out_thread_map_delete;
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index f78be21a5999..fbdf710d5eea 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -162,6 +162,22 @@ static int test__checkevent_numeric(struct evlist *evlist)
 	return TEST_OK;
 }
 
+
+static int assert_hw(struct perf_evsel *evsel, enum perf_hw_id id, const char *name)
+{
+	struct perf_pmu *pmu;
+
+	if (evsel->attr.type == PERF_TYPE_HARDWARE) {
+		TEST_ASSERT_VAL("wrong config", test_perf_config(evsel, id));
+		return 0;
+	}
+	pmu = perf_pmus__find_by_type(evsel->attr.type);
+
+	TEST_ASSERT_VAL("unexpected PMU type", pmu);
+	TEST_ASSERT_VAL("PMU missing event", perf_pmu__have_event(pmu, name));
+	return 0;
+}
+
 static int test__checkevent_symbolic_name(struct evlist *evlist)
 {
 	struct perf_evsel *evsel;
@@ -169,10 +185,12 @@ static int test__checkevent_symbolic_name(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong number of entries", 0 != evlist->core.nr_entries);
 
 	perf_evlist__for_each_evsel(&evlist->core, evsel) {
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
-		TEST_ASSERT_VAL("wrong config",
-				test_perf_config(evsel, PERF_COUNT_HW_INSTRUCTIONS));
+		int ret = assert_hw(evsel, PERF_COUNT_HW_INSTRUCTIONS, "instructions");
+
+		if (ret)
+			return ret;
 	}
+
 	return TEST_OK;
 }
 
@@ -183,8 +201,10 @@ static int test__checkevent_symbolic_name_config(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong number of entries", 0 != evlist->core.nr_entries);
 
 	perf_evlist__for_each_evsel(&evlist->core, evsel) {
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
-		TEST_ASSERT_VAL("wrong config", test_perf_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		int ret = assert_hw(evsel, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+
+		if (ret)
+			return ret;
 		/*
 		 * The period value gets configured within evlist__config,
 		 * while this test executes only parse events method.
@@ -861,10 +881,14 @@ static int test__group1(struct evlist *evlist)
 			evlist__nr_groups(evlist) == num_core_entries());
 
 	for (int i = 0; i < num_core_entries(); i++) {
+		int ret;
+
 		/* instructions:k */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_INSTRUCTIONS, "instructions");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -878,8 +902,10 @@ static int test__group1(struct evlist *evlist)
 
 		/* cycles:upp */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -907,6 +933,8 @@ static int test__group2(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist__nr_groups(evlist));
 
 	evlist__for_each_entry(evlist, evsel) {
+		int ret;
+
 		if (evsel->core.attr.type == PERF_TYPE_SOFTWARE) {
 			/* faults + :ku modifier */
 			leader = evsel;
@@ -939,8 +967,10 @@ static int test__group2(struct evlist *evlist)
 			continue;
 		}
 		/* cycles:k */
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -957,6 +987,7 @@ static int test__group2(struct evlist *evlist)
 static int test__group3(struct evlist *evlist __maybe_unused)
 {
 	struct evsel *evsel, *group1_leader = NULL, *group2_leader = NULL;
+	int ret;
 
 	TEST_ASSERT_VAL("wrong number of entries",
 			evlist->core.nr_entries == (3 * perf_pmus__num_core_pmus() + 2));
@@ -1045,8 +1076,10 @@ static int test__group3(struct evlist *evlist __maybe_unused)
 			continue;
 		}
 		/* instructions:u */
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_INSTRUCTIONS, "instructions");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -1070,10 +1103,14 @@ static int test__group4(struct evlist *evlist __maybe_unused)
 			num_core_entries() == evlist__nr_groups(evlist));
 
 	for (int i = 0; i < num_core_entries(); i++) {
+		int ret;
+
 		/* cycles:u + p */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -1089,8 +1126,10 @@ static int test__group4(struct evlist *evlist __maybe_unused)
 
 		/* instructions:kp + p */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_INSTRUCTIONS, "instructions");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -1108,6 +1147,7 @@ static int test__group4(struct evlist *evlist __maybe_unused)
 static int test__group5(struct evlist *evlist __maybe_unused)
 {
 	struct evsel *evsel = NULL, *leader;
+	int ret;
 
 	TEST_ASSERT_VAL("wrong number of entries",
 			evlist->core.nr_entries == (5 * num_core_entries()));
@@ -1117,8 +1157,10 @@ static int test__group5(struct evlist *evlist __maybe_unused)
 	for (int i = 0; i < num_core_entries(); i++) {
 		/* cycles + G */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1133,8 +1175,10 @@ static int test__group5(struct evlist *evlist __maybe_unused)
 
 		/* instructions + G */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_INSTRUCTIONS, "instructions");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1148,8 +1192,10 @@ static int test__group5(struct evlist *evlist __maybe_unused)
 	for (int i = 0; i < num_core_entries(); i++) {
 		/* cycles:G */
 		evsel = leader = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1164,8 +1210,10 @@ static int test__group5(struct evlist *evlist __maybe_unused)
 
 		/* instructions:G */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_INSTRUCTIONS, "instructions");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1178,8 +1226,10 @@ static int test__group5(struct evlist *evlist __maybe_unused)
 	for (int i = 0; i < num_core_entries(); i++) {
 		/* cycles */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1201,10 +1251,14 @@ static int test__group_gh1(struct evlist *evlist)
 			evlist__nr_groups(evlist) == num_core_entries());
 
 	for (int i = 0; i < num_core_entries(); i++) {
+		int ret;
+
 		/* cycles + :H group modifier */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1218,8 +1272,10 @@ static int test__group_gh1(struct evlist *evlist)
 
 		/* cache-misses:G + :H group modifier */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1242,10 +1298,14 @@ static int test__group_gh2(struct evlist *evlist)
 			evlist__nr_groups(evlist) == num_core_entries());
 
 	for (int i = 0; i < num_core_entries(); i++) {
+		int ret;
+
 		/* cycles + :G group modifier */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1259,8 +1319,10 @@ static int test__group_gh2(struct evlist *evlist)
 
 		/* cache-misses:H + :G group modifier */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1283,10 +1345,14 @@ static int test__group_gh3(struct evlist *evlist)
 			evlist__nr_groups(evlist) == num_core_entries());
 
 	for (int i = 0; i < num_core_entries(); i++) {
+		int ret;
+
 		/* cycles:G + :u group modifier */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -1300,8 +1366,10 @@ static int test__group_gh3(struct evlist *evlist)
 
 		/* cache-misses:H + :u group modifier */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -1324,10 +1392,14 @@ static int test__group_gh4(struct evlist *evlist)
 			evlist__nr_groups(evlist) == num_core_entries());
 
 	for (int i = 0; i < num_core_entries(); i++) {
+		int ret;
+
 		/* cycles:G + :uG group modifier */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -1341,8 +1413,10 @@ static int test__group_gh4(struct evlist *evlist)
 
 		/* cache-misses:H + :uG group modifier */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -1363,10 +1437,14 @@ static int test__leader_sample1(struct evlist *evlist)
 			evlist->core.nr_entries == (3 * num_core_entries()));
 
 	for (int i = 0; i < num_core_entries(); i++) {
+		int ret;
+
 		/* cycles - sampling group leader */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1379,8 +1457,10 @@ static int test__leader_sample1(struct evlist *evlist)
 
 		/* cache-misses - not sampling */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1392,8 +1472,10 @@ static int test__leader_sample1(struct evlist *evlist)
 
 		/* branch-misses - not sampling */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_BRANCH_MISSES, "branch-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1415,10 +1497,14 @@ static int test__leader_sample2(struct evlist *evlist __maybe_unused)
 			evlist->core.nr_entries == (2 * num_core_entries()));
 
 	for (int i = 0; i < num_core_entries(); i++) {
+		int ret;
+
 		/* instructions - sampling group leader */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_INSTRUCTIONS, "instructions");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -1431,8 +1517,10 @@ static int test__leader_sample2(struct evlist *evlist __maybe_unused)
 
 		/* branch-misses - not sampling */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_BRANCH_MISSES, "branch-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -1472,10 +1560,14 @@ static int test__pinned_group(struct evlist *evlist)
 			evlist->core.nr_entries == (3 * num_core_entries()));
 
 	for (int i = 0; i < num_core_entries(); i++) {
+		int ret;
+
 		/* cycles - group leader */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
 		TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
 		/* TODO: The group modifier is not copied to the split group leader. */
@@ -1484,13 +1576,18 @@ static int test__pinned_group(struct evlist *evlist)
 
 		/* cache-misses - can not be pinned, but will go on with the leader */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong pinned", !evsel->core.attr.pinned);
 
 		/* branch-misses - ditto */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_BRANCH_MISSES, "branch-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong pinned", !evsel->core.attr.pinned);
 	}
 	return TEST_OK;
@@ -1517,10 +1614,14 @@ static int test__exclusive_group(struct evlist *evlist)
 			evlist->core.nr_entries == 3 * num_core_entries());
 
 	for (int i = 0; i < num_core_entries(); i++) {
+		int ret;
+
 		/* cycles - group leader */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
 		TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
 		/* TODO: The group modifier is not copied to the split group leader. */
@@ -1529,13 +1630,18 @@ static int test__exclusive_group(struct evlist *evlist)
 
 		/* cache-misses - can not be pinned, but will go on with the leader */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclusive", !evsel->core.attr.exclusive);
 
 		/* branch-misses - ditto */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_BRANCH_MISSES, "branch-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclusive", !evsel->core.attr.exclusive);
 	}
 	return TEST_OK;
@@ -1677,9 +1783,11 @@ static int test__checkevent_raw_pmu(struct evlist *evlist)
 static int test__sym_event_slash(struct evlist *evlist)
 {
 	struct evsel *evsel = evlist__first(evlist);
+	int ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+
+	if (ret)
+		return ret;
 
-	TEST_ASSERT_VAL("wrong type", evsel->core.attr.type == PERF_TYPE_HARDWARE);
-	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
 	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 	return TEST_OK;
 }
@@ -1687,9 +1795,11 @@ static int test__sym_event_slash(struct evlist *evlist)
 static int test__sym_event_dc(struct evlist *evlist)
 {
 	struct evsel *evsel = evlist__first(evlist);
+	int ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+
+	if (ret)
+		return ret;
 
-	TEST_ASSERT_VAL("wrong type", evsel->core.attr.type == PERF_TYPE_HARDWARE);
-	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
 	TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user);
 	return TEST_OK;
 }
@@ -1697,9 +1807,11 @@ static int test__sym_event_dc(struct evlist *evlist)
 static int test__term_equal_term(struct evlist *evlist)
 {
 	struct evsel *evsel = evlist__first(evlist);
+	int ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+
+	if (ret)
+		return ret;
 
-	TEST_ASSERT_VAL("wrong type", evsel->core.attr.type == PERF_TYPE_HARDWARE);
-	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
 	TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "name") == 0);
 	return TEST_OK;
 }
@@ -1707,9 +1819,11 @@ static int test__term_equal_term(struct evlist *evlist)
 static int test__term_equal_legacy(struct evlist *evlist)
 {
 	struct evsel *evsel = evlist__first(evlist);
+	int ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+
+	if (ret)
+		return ret;
 
-	TEST_ASSERT_VAL("wrong type", evsel->core.attr.type == PERF_TYPE_HARDWARE);
-	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
 	TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "l1d") == 0);
 	return TEST_OK;
 }
@@ -2549,7 +2663,7 @@ static int test__pmu_events(struct test_suite *test __maybe_unused, int subtest
 			if (strchr(ent->d_name, '.'))
 				continue;
 
-			/* exclude parametrized ones (name contains '?') */
+			/* exclude parameterized ones (name contains '?') */
 			n = snprintf(pmu_event, sizeof(pmu_event), "%s%s", path, ent->d_name);
 			if (n >= PATH_MAX) {
 				pr_err("pmu event name crossed PATH_MAX(%d) size\n", PATH_MAX);
@@ -2578,7 +2692,7 @@ static int test__pmu_events(struct test_suite *test __maybe_unused, int subtest
 			fclose(file);
 
 			if (is_event_parameterized == 1) {
-				pr_debug("skipping parametrized PMU event: %s which contains ?\n", pmu_event);
+				pr_debug("skipping parameterized PMU event: %s which contains ?\n", pmu_event);
 				continue;
 			}
 
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index efcd71c2738a..bbe2ddeb9b74 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -93,7 +93,7 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	CHECK_NOT_NULL__(threads);
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	CHECK_NOT_NULL__(cpus);
 
 	evlist = evlist__new();
diff --git a/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c b/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c
index a7e169d1bf64..5f886cd09e6b 100644
--- a/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c
+++ b/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c
@@ -42,7 +42,6 @@ static pthread_t new_thr(void *(*fn) (void *arg), void *arg)
 int main(int argc, char **argv)
 {
 	unsigned long i, len, size, thr;
-	pthread_t threads[256];
 	struct args args[256];
 	long long v;
 
diff --git a/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c b/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c
index c0158fac7d0b..e05a559253ca 100644
--- a/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c
+++ b/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c
@@ -57,7 +57,6 @@ static pthread_t new_thr(void *(*fn) (void *arg), void *arg)
 int main(int argc, char **argv)
 {
 	unsigned int i, len, thr;
-	pthread_t threads[256];
 	struct args args[256];
 
 	if (argc < 3) {
diff --git a/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c b/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c
index 8f6d384208ed..0fc7bf1a25af 100644
--- a/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c
+++ b/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c
@@ -51,7 +51,6 @@ static pthread_t new_thr(void *(*fn) (void *arg), void *arg)
 int main(int argc, char **argv)
 {
 	unsigned int i, thr;
-	pthread_t threads[256];
 	struct args args[256];
 
 	if (argc < 2) {
diff --git a/tools/perf/tests/shell/daemon.sh b/tools/perf/tests/shell/daemon.sh
index 4c598cfc5afa..e5fa8d6f9eb1 100755
--- a/tools/perf/tests/shell/daemon.sh
+++ b/tools/perf/tests/shell/daemon.sh
@@ -414,16 +414,30 @@ EOF
 	# start daemon
 	daemon_start ${config} test
 
-	# send 2 signals
-	perf daemon signal --config ${config} --session test
-	perf daemon signal --config ${config}
-
-	# stop daemon
-	daemon_exit ${config}
-
-	# count is 2 perf.data for signals and 1 for perf record finished
-	count=`ls ${base}/session-test/*perf.data* | wc -l`
-	if [ ${count} -ne 3 ]; then
+        # send 2 signals then exit. Do this in a loop watching the number of
+        # files to avoid races. If the loop retries more than 600 times then
+        # give up.
+	local retries=0
+	local signals=0
+	local success=0
+	while [ ${retries} -lt 600 ] && [ ${success} -eq 0 ]; do
+		local files
+		files=`ls ${base}/session-test/*perf.data* 2> /dev/null | wc -l`
+		if [ ${signals} -eq 0 ]; then
+			perf daemon signal --config ${config} --session test
+			signals=1
+		elif [ ${signals} -eq 1 ] && [ $files -ge 1 ]; then
+			perf daemon signal --config ${config}
+			signals=2
+		elif [ ${signals} -eq 2 ] && [ $files -ge 2 ]; then
+			daemon_exit ${config}
+			signals=3
+		elif [ ${signals} -eq 3 ] && [ $files -ge 3 ]; then
+			success=1
+		fi
+		retries=$((${retries} +1))
+	done
+	if [ ${success} -eq 0 ]; then
 		error=1
 		echo "FAILED: perf data no generated"
 	fi
diff --git a/tools/perf/tests/shell/diff.sh b/tools/perf/tests/shell/diff.sh
new file mode 100755
index 000000000000..14b87af88703
--- /dev/null
+++ b/tools/perf/tests/shell/diff.sh
@@ -0,0 +1,108 @@
+#!/bin/sh
+# perf diff tests
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+err=0
+perfdata1=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+perfdata2=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+perfdata3=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+testprog="perf test -w thloop"
+
+shelldir=$(dirname "$0")
+# shellcheck source=lib/perf_has_symbol.sh
+. "${shelldir}"/lib/perf_has_symbol.sh
+
+testsym="test_loop"
+
+skip_test_missing_symbol ${testsym}
+
+cleanup() {
+  rm -rf "${perfdata1}"
+  rm -rf "${perfdata1}".old
+  rm -rf "${perfdata2}"
+  rm -rf "${perfdata2}".old
+  rm -rf "${perfdata3}"
+  rm -rf "${perfdata3}".old
+
+  trap - EXIT TERM INT
+}
+
+trap_cleanup() {
+  cleanup
+  exit 1
+}
+trap trap_cleanup EXIT TERM INT
+
+make_data() {
+  file="$1"
+  if ! perf record -o "${file}" ${testprog} 2> /dev/null
+  then
+    echo "Workload record [Failed record]"
+    echo 1
+    return
+  fi
+  if ! perf report -i "${file}" -q | grep -q "${testsym}"
+  then
+    echo "Workload record [Failed missing output]"
+    echo 1
+    return
+  fi
+  echo 0
+}
+
+test_two_files() {
+  echo "Basic two file diff test"
+  err=$(make_data "${perfdata1}")
+  if [ $err != 0 ]
+  then
+    return
+  fi
+  err=$(make_data "${perfdata2}")
+  if [ $err != 0 ]
+  then
+    return
+  fi
+
+  if ! perf diff "${perfdata1}" "${perfdata2}" | grep -q "${testsym}"
+  then
+    echo "Basic two file diff test [Failed diff]"
+    err=1
+    return
+  fi
+  echo "Basic two file diff test [Success]"
+}
+
+test_three_files() {
+  echo "Basic three file diff test"
+  err=$(make_data "${perfdata1}")
+  if [ $err != 0 ]
+  then
+    return
+  fi
+  err=$(make_data "${perfdata2}")
+  if [ $err != 0 ]
+  then
+    return
+  fi
+  err=$(make_data "${perfdata3}")
+  if [ $err != 0 ]
+  then
+    return
+  fi
+
+  if ! perf diff "${perfdata1}" "${perfdata2}" "${perfdata3}" | grep -q "${testsym}"
+  then
+    echo "Basic three file diff test [Failed diff]"
+    err=1
+    return
+  fi
+  echo "Basic three file diff test [Success]"
+}
+
+test_two_files
+test_three_files
+
+cleanup
+exit $err
diff --git a/tools/perf/tests/shell/lib/perf_has_symbol.sh b/tools/perf/tests/shell/lib/perf_has_symbol.sh
new file mode 100644
index 000000000000..5d59c32ae3e7
--- /dev/null
+++ b/tools/perf/tests/shell/lib/perf_has_symbol.sh
@@ -0,0 +1,21 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+perf_has_symbol()
+{
+	if perf test -vv "Symbols" 2>&1 | grep "[[:space:]]$1$"; then
+		echo "perf does have symbol '$1'"
+		return 0
+	fi
+	echo "perf does not have symbol '$1'"
+	return 1
+}
+
+skip_test_missing_symbol()
+{
+	if ! perf_has_symbol "$1" ; then
+		echo "perf is missing symbols - skipping test"
+		exit 2
+	fi
+	return 0
+}
diff --git a/tools/perf/tests/shell/lib/setup_python.sh b/tools/perf/tests/shell/lib/setup_python.sh
new file mode 100644
index 000000000000..c2fce1793538
--- /dev/null
+++ b/tools/perf/tests/shell/lib/setup_python.sh
@@ -0,0 +1,16 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+if [ "x$PYTHON" = "x" ]
+then
+  python3 --version >/dev/null 2>&1 && PYTHON=python3
+fi
+if [ "x$PYTHON" = "x" ]
+then
+  python --version >/dev/null 2>&1 && PYTHON=python
+fi
+if [ "x$PYTHON" = "x" ]
+then
+  echo Skipping test, python not detected please set environment variable PYTHON.
+  exit 2
+fi
diff --git a/tools/perf/tests/shell/list.sh b/tools/perf/tests/shell/list.sh
new file mode 100755
index 000000000000..8a868ae64560
--- /dev/null
+++ b/tools/perf/tests/shell/list.sh
@@ -0,0 +1,34 @@
+#!/bin/sh
+# perf list tests
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+shelldir=$(dirname "$0")
+# shellcheck source=lib/setup_python.sh
+. "${shelldir}"/lib/setup_python.sh
+
+list_output=$(mktemp /tmp/__perf_test.list_output.json.XXXXX)
+
+cleanup() {
+  rm -f "${list_output}"
+
+  trap - EXIT TERM INT
+}
+
+trap_cleanup() {
+  cleanup
+  exit 1
+}
+trap trap_cleanup EXIT TERM INT
+
+test_list_json() {
+  echo "Json output test"
+  perf list -j -o "${list_output}"
+  $PYTHON -m json.tool "${list_output}"
+  echo "Json output test [Success]"
+}
+
+test_list_json
+cleanup
+exit 0
diff --git a/tools/perf/tests/shell/pipe_test.sh b/tools/perf/tests/shell/pipe_test.sh
index 8dd115dd35a7..a78d35d2cff0 100755
--- a/tools/perf/tests/shell/pipe_test.sh
+++ b/tools/perf/tests/shell/pipe_test.sh
@@ -2,10 +2,17 @@
 # perf pipe recording and injection test
 # SPDX-License-Identifier: GPL-2.0
 
+shelldir=$(dirname "$0")
+# shellcheck source=lib/perf_has_symbol.sh
+. "${shelldir}"/lib/perf_has_symbol.sh
+
+sym="noploop"
+
+skip_test_missing_symbol ${sym}
+
 data=$(mktemp /tmp/perf.data.XXXXXX)
 prog="perf test -w noploop"
 task="perf"
-sym="noploop"
 
 if ! perf record -e task-clock:u -o - ${prog} | perf report -i - --task | grep ${task}; then
 	echo "cannot find the test file in the perf report"
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index eebeea6bdc76..72c65570db37 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -45,7 +45,10 @@ trace_libc_inet_pton_backtrace() {
 		;;
 	ppc64|ppc64le)
 		eventattr='max-stack=4'
-		echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		# Add gaih_inet to expected backtrace only if it is part of libc.
+		if nm $libc | grep -F -q gaih_inet.; then
+			echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		fi
 		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
 		echo ".*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh
index 29443b8e8876..3d1a7759a7b2 100755
--- a/tools/perf/tests/shell/record.sh
+++ b/tools/perf/tests/shell/record.sh
@@ -8,10 +8,19 @@ shelldir=$(dirname "$0")
 # shellcheck source=lib/waiting.sh
 . "${shelldir}"/lib/waiting.sh
 
+# shellcheck source=lib/perf_has_symbol.sh
+. "${shelldir}"/lib/perf_has_symbol.sh
+
+testsym="test_loop"
+
+skip_test_missing_symbol ${testsym}
+
 err=0
 perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
 testprog="perf test -w thloop"
-testsym="test_loop"
+cpu_pmu_dir="/sys/bus/event_source/devices/cpu*"
+br_cntr_file="/caps/branch_counter_nr"
+br_cntr_output="branch stack counters"
 
 cleanup() {
   rm -rf "${perfdata}"
@@ -155,10 +164,37 @@ test_workload() {
   echo "Basic target workload test [Success]"
 }
 
+test_branch_counter() {
+  echo "Basic branch counter test"
+  # Check if the branch counter feature is supported
+  for dir in $cpu_pmu_dir
+  do
+    if [ ! -e "$dir$br_cntr_file" ]
+    then
+      echo "branch counter feature not supported on all core PMUs ($dir) [Skipped]"
+      return
+    fi
+  done
+  if ! perf record -o "${perfdata}" -j any,counter ${testprog} 2> /dev/null
+  then
+    echo "Basic branch counter test [Failed record]"
+    err=1
+    return
+  fi
+  if ! perf report -i "${perfdata}" -D -q | grep -q "$br_cntr_output"
+  then
+    echo "Basic branch record test [Failed missing output]"
+    err=1
+    return
+  fi
+  echo "Basic branch counter test [Success]"
+}
+
 test_per_thread
 test_register_capture
 test_system_wide
 test_workload
+test_branch_counter
 
 cleanup
 exit $err
diff --git a/tools/perf/tests/shell/record_offcpu.sh b/tools/perf/tests/shell/record_offcpu.sh
index a1ef8f0d2b5c..67c925f3a15a 100755
--- a/tools/perf/tests/shell/record_offcpu.sh
+++ b/tools/perf/tests/shell/record_offcpu.sh
@@ -77,9 +77,9 @@ test_offcpu_child() {
     err=1
     return
   fi
-  # each process waits for read and write, so it should be more than 800 events
+  # each process waits at least for poll, so it should be more than 400 events
   if ! perf report -i ${perfdata} -s comm -q -n -t ';' --percent-limit=90 | \
-    awk -F ";" '{ if (NF > 3 && int($3) < 800) exit 1; }'
+    awk -F ";" '{ if (NF > 3 && int($3) < 400) exit 1; }'
   then
     echo "Child task off-cpu test [Failed invalid output]"
     err=1
diff --git a/tools/perf/tests/shell/script.sh b/tools/perf/tests/shell/script.sh
new file mode 100755
index 000000000000..fa4d71e2e72a
--- /dev/null
+++ b/tools/perf/tests/shell/script.sh
@@ -0,0 +1,72 @@
+#!/bin/sh
+# perf script tests
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+temp_dir=$(mktemp -d /tmp/perf-test-script.XXXXXXXXXX)
+
+perfdatafile="${temp_dir}/perf.data"
+db_test="${temp_dir}/db_test.py"
+
+err=0
+
+cleanup()
+{
+	trap - EXIT TERM INT
+	sane=$(echo "${temp_dir}" | cut -b 1-21)
+	if [ "${sane}" = "/tmp/perf-test-script" ] ; then
+		echo "--- Cleaning up ---"
+		rm -f "${temp_dir}/"*
+		rmdir "${temp_dir}"
+	fi
+}
+
+trap_cleanup()
+{
+	cleanup
+	exit 1
+}
+
+trap trap_cleanup EXIT TERM INT
+
+
+test_db()
+{
+	echo "DB test"
+
+	# Check if python script is supported
+        if perf version --build-options | grep python | grep -q OFF ; then
+		echo "SKIP: python scripting is not supported"
+		err=2
+		return
+	fi
+
+	cat << "_end_of_file_" > "${db_test}"
+perf_db_export_mode = True
+perf_db_export_calls = False
+perf_db_export_callchains = True
+
+def sample_table(*args):
+    print(f'sample_table({args})')
+
+def call_path_table(*args):
+    print(f'call_path_table({args}')
+_end_of_file_
+	case $(uname -m)
+	in s390x)
+		cmd_flags="--call-graph dwarf -e cpu-clock";;
+	*)
+		cmd_flags="-g";;
+	esac
+
+	perf record $cmd_flags -o "${perfdatafile}" true
+	perf script -i "${perfdatafile}" -s "${db_test}"
+	echo "DB test [Success]"
+}
+
+test_db
+
+cleanup
+
+exit $err
diff --git a/tools/perf/tests/shell/stat+json_output.sh b/tools/perf/tests/shell/stat+json_output.sh
index 196e22672c50..3bc900533a5d 100755
--- a/tools/perf/tests/shell/stat+json_output.sh
+++ b/tools/perf/tests/shell/stat+json_output.sh
@@ -8,20 +8,10 @@ set -e
 
 skip_test=0
 
+shelldir=$(dirname "$0")
+# shellcheck source=lib/setup_python.sh
+. "${shelldir}"/lib/setup_python.sh
 pythonchecker=$(dirname $0)/lib/perf_json_output_lint.py
-if [ "x$PYTHON" == "x" ]
-then
-	if which python3 > /dev/null
-	then
-		PYTHON=python3
-	elif which python > /dev/null
-	then
-		PYTHON=python
-	else
-		echo Skipping test, python not detected please set environment variable PYTHON.
-		exit 2
-	fi
-fi
 
 stat_output=$(mktemp /tmp/__perf_test.stat_output.json.XXXXX)
 
diff --git a/tools/perf/tests/shell/stat_all_pmu.sh b/tools/perf/tests/shell/stat_all_pmu.sh
index c77955419173..d2a3506e0d19 100755
--- a/tools/perf/tests/shell/stat_all_pmu.sh
+++ b/tools/perf/tests/shell/stat_all_pmu.sh
@@ -4,7 +4,7 @@
 
 set -e
 
-# Test all PMU events; however exclude parametrized ones (name contains '?')
+# Test all PMU events; however exclude parameterized ones (name contains '?')
 for p in $(perf list --raw-dump pmu | sed 's/[[:graph:]]\+?[[:graph:]]\+[[:space:]]//g'); do
   echo "Testing $p"
   result=$(perf stat -e "$p" true 2>&1)
diff --git a/tools/perf/tests/shell/stat_metrics_values.sh b/tools/perf/tests/shell/stat_metrics_values.sh
index ad94c936de7e..7ca172599aa6 100755
--- a/tools/perf/tests/shell/stat_metrics_values.sh
+++ b/tools/perf/tests/shell/stat_metrics_values.sh
@@ -1,16 +1,10 @@
 #!/bin/bash
 # perf metrics value validation
 # SPDX-License-Identifier: GPL-2.0
-if [ "x$PYTHON" == "x" ]
-then
-	if which python3 > /dev/null
-	then
-		PYTHON=python3
-	else
-		echo Skipping test, python3 not detected please set environment variable PYTHON.
-		exit 2
-	fi
-fi
+
+shelldir=$(dirname "$0")
+# shellcheck source=lib/setup_python.sh
+. "${shelldir}"/lib/setup_python.sh
 
 grep -q GenuineIntel /proc/cpuinfo || { echo Skipping non-Intel; exit 2; }
 
diff --git a/tools/perf/tests/shell/test_arm_callgraph_fp.sh b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
index 66dfdfdad553..e342e6c8aa50 100755
--- a/tools/perf/tests/shell/test_arm_callgraph_fp.sh
+++ b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
@@ -2,8 +2,14 @@
 # Check Arm64 callgraphs are complete in fp mode
 # SPDX-License-Identifier: GPL-2.0
 
+shelldir=$(dirname "$0")
+# shellcheck source=lib/perf_has_symbol.sh
+. "${shelldir}"/lib/perf_has_symbol.sh
+
 lscpu | grep -q "aarch64" || exit 2
 
+skip_test_missing_symbol leafloop
+
 PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
 TEST_PROGRAM="perf test -w leafloop"
 
diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh
index 09908d71c994..5f14d0cb013f 100755
--- a/tools/perf/tests/shell/test_brstack.sh
+++ b/tools/perf/tests/shell/test_brstack.sh
@@ -4,6 +4,10 @@
 # SPDX-License-Identifier: GPL-2.0
 # German Gomez <german.gomez@arm.com>, 2022
 
+shelldir=$(dirname "$0")
+# shellcheck source=lib/perf_has_symbol.sh
+. "${shelldir}"/lib/perf_has_symbol.sh
+
 # skip the test if the hardware doesn't support branch stack sampling
 # and if the architecture doesn't support filter types: any,save_type,u
 if ! perf record -o- --no-buildid --branch-filter any,save_type,u -- true > /dev/null 2>&1 ; then
@@ -11,6 +15,8 @@ if ! perf record -o- --no-buildid --branch-filter any,save_type,u -- true > /dev
 	exit 2
 fi
 
+skip_test_missing_symbol brstack_bench
+
 TMPDIR=$(mktemp -d /tmp/__perf_test.program.XXXXX)
 TESTPROG="perf test -w brstack"
 
diff --git a/tools/perf/tests/shell/test_data_symbol.sh b/tools/perf/tests/shell/test_data_symbol.sh
index 69bb6fe86c50..3dfa91832aa8 100755
--- a/tools/perf/tests/shell/test_data_symbol.sh
+++ b/tools/perf/tests/shell/test_data_symbol.sh
@@ -4,6 +4,13 @@
 # SPDX-License-Identifier: GPL-2.0
 # Leo Yan <leo.yan@linaro.org>, 2022
 
+shelldir=$(dirname "$0")
+# shellcheck source=lib/waiting.sh
+. "${shelldir}"/lib/waiting.sh
+
+# shellcheck source=lib/perf_has_symbol.sh
+. "${shelldir}"/lib/perf_has_symbol.sh
+
 skip_if_no_mem_event() {
 	perf mem record -e list 2>&1 | grep -E -q 'available' && return 0
 	return 2
@@ -11,8 +18,11 @@ skip_if_no_mem_event() {
 
 skip_if_no_mem_event || exit 2
 
+skip_test_missing_symbol buf1
+
 TEST_PROGRAM="perf test -w datasym"
 PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+ERR_FILE=$(mktemp /tmp/__perf_test.stderr.XXXXX)
 
 check_result() {
 	# The memory report format is as below:
@@ -50,13 +60,15 @@ echo "Recording workload..."
 # specific CPU and test in per-CPU mode.
 is_amd=$(grep -E -c 'vendor_id.*AuthenticAMD' /proc/cpuinfo)
 if (($is_amd >= 1)); then
-	perf mem record -o ${PERF_DATA} -C 0 -- taskset -c 0 $TEST_PROGRAM &
+	perf mem record -vvv -o ${PERF_DATA} -C 0 -- taskset -c 0 $TEST_PROGRAM 2>"${ERR_FILE}" &
 else
-	perf mem record --all-user -o ${PERF_DATA} -- $TEST_PROGRAM &
+	perf mem record -vvv --all-user -o ${PERF_DATA} -- $TEST_PROGRAM 2>"${ERR_FILE}" &
 fi
 
 PERFPID=$!
 
+wait_for_perf_to_start ${PERFPID} "${ERR_FILE}"
+
 sleep 1
 
 kill $PERFPID
diff --git a/tools/perf/tests/shell/test_perf_data_converter_json.sh b/tools/perf/tests/shell/test_perf_data_converter_json.sh
index 6ded58f98f55..c4f1b59d116f 100755
--- a/tools/perf/tests/shell/test_perf_data_converter_json.sh
+++ b/tools/perf/tests/shell/test_perf_data_converter_json.sh
@@ -6,16 +6,9 @@ set -e
 
 err=0
 
-if [ "$PYTHON" = "" ] ; then
-	if which python3 > /dev/null ; then
-		PYTHON=python3
-	elif which python > /dev/null ; then
-		PYTHON=python
-	else
-		echo Skipping test, python not detected please set environment variable PYTHON.
-		exit 2
-	fi
-fi
+shelldir=$(dirname "$0")
+# shellcheck source=lib/setup_python.sh
+. "${shelldir}"/lib/setup_python.sh
 
 perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
 result=$(mktemp /tmp/__perf_test.output.json.XXXXX)
diff --git a/tools/perf/tests/sigtrap.c b/tools/perf/tests/sigtrap.c
index 1de7478ec189..e6fd934b027a 100644
--- a/tools/perf/tests/sigtrap.c
+++ b/tools/perf/tests/sigtrap.c
@@ -57,36 +57,79 @@ static struct perf_event_attr make_event_attr(void)
 #ifdef HAVE_BPF_SKEL
 #include <bpf/btf.h>
 
-static bool attr_has_sigtrap(void)
+static struct btf *btf;
+
+static bool btf__available(void)
 {
-	bool ret = false;
-	struct btf *btf;
-	const struct btf_type *t;
+	if (btf == NULL)
+		btf = btf__load_vmlinux_btf();
+
+	return btf != NULL;
+}
+
+static void btf__exit(void)
+{
+	btf__free(btf);
+	btf = NULL;
+}
+
+static const struct btf_member *__btf_type__find_member_by_name(int type_id, const char *member_name)
+{
+	const struct btf_type *t = btf__type_by_id(btf, type_id);
 	const struct btf_member *m;
-	const char *name;
-	int i, id;
+	int i;
+
+	for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) {
+		const char *current_member_name = btf__name_by_offset(btf, m->name_off);
+		if (!strcmp(current_member_name, member_name))
+			return m;
+	}
 
-	btf = btf__load_vmlinux_btf();
-	if (btf == NULL) {
+	return NULL;
+}
+
+static bool attr_has_sigtrap(void)
+{
+	int id;
+
+	if (!btf__available()) {
 		/* should be an old kernel */
 		return false;
 	}
 
 	id = btf__find_by_name_kind(btf, "perf_event_attr", BTF_KIND_STRUCT);
 	if (id < 0)
-		goto out;
+		return false;
 
-	t = btf__type_by_id(btf, id);
-	for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) {
-		name = btf__name_by_offset(btf, m->name_off);
-		if (!strcmp(name, "sigtrap")) {
-			ret = true;
-			break;
-		}
-	}
-out:
-	btf__free(btf);
-	return ret;
+	return __btf_type__find_member_by_name(id, "sigtrap") != NULL;
+}
+
+static bool kernel_with_sleepable_spinlocks(void)
+{
+	const struct btf_member *member;
+	const struct btf_type *type;
+	const char *type_name;
+	int id;
+
+	if (!btf__available())
+		return false;
+
+	id = btf__find_by_name_kind(btf, "spinlock", BTF_KIND_STRUCT);
+	if (id < 0)
+		return false;
+
+	// Only RT has a "lock" member for "struct spinlock"
+	member = __btf_type__find_member_by_name(id, "lock");
+	if (member == NULL)
+		return false;
+
+	// But check its type as well
+	type = btf__type_by_id(btf, member->type);
+	if (!type || !btf_is_struct(type))
+		return false;
+
+	type_name = btf__name_by_offset(btf, type->name_off);
+	return type_name && !strcmp(type_name, "rt_mutex_base");
 }
 #else  /* !HAVE_BPF_SKEL */
 static bool attr_has_sigtrap(void)
@@ -109,6 +152,15 @@ static bool attr_has_sigtrap(void)
 
 	return ret;
 }
+
+static bool kernel_with_sleepable_spinlocks(void)
+{
+	return false;
+}
+
+static void btf__exit(void)
+{
+}
 #endif  /* HAVE_BPF_SKEL */
 
 static void
@@ -147,7 +199,7 @@ static int run_test_threads(pthread_t *threads, pthread_barrier_t *barrier)
 
 static int run_stress_test(int fd, pthread_t *threads, pthread_barrier_t *barrier)
 {
-	int ret;
+	int ret, expected_sigtraps;
 
 	ctx.iterate_on = 3000;
 
@@ -156,7 +208,16 @@ static int run_stress_test(int fd, pthread_t *threads, pthread_barrier_t *barrie
 	ret = run_test_threads(threads, barrier);
 	TEST_ASSERT_EQUAL("disable failed", ioctl(fd, PERF_EVENT_IOC_DISABLE, 0), 0);
 
-	TEST_ASSERT_EQUAL("unexpected sigtraps", ctx.signal_count, NUM_THREADS * ctx.iterate_on);
+	expected_sigtraps = NUM_THREADS * ctx.iterate_on;
+
+	if (ctx.signal_count < expected_sigtraps && kernel_with_sleepable_spinlocks()) {
+		pr_debug("Expected %d sigtraps, got %d, running on a kernel with sleepable spinlocks.\n",
+			 expected_sigtraps, ctx.signal_count);
+		pr_debug("See https://lore.kernel.org/all/e368f2c848d77fbc8d259f44e2055fe469c219cf.camel@gmx.de/\n");
+		return TEST_SKIP;
+	} else
+		TEST_ASSERT_EQUAL("unexpected sigtraps", ctx.signal_count, expected_sigtraps);
+
 	TEST_ASSERT_EQUAL("missing signals or incorrectly delivered", ctx.tids_want_signal, 0);
 	TEST_ASSERT_VAL("unexpected si_addr", ctx.first_siginfo.si_addr == &ctx.iterate_on);
 #if 0 /* FIXME: enable when libc's signal.h has si_perf_{type,data} */
@@ -221,6 +282,7 @@ out_restore_sigaction:
 	sigaction(SIGTRAP, &oldact, NULL);
 out:
 	pthread_barrier_destroy(&barrier);
+	btf__exit();
 	return ret;
 }
 
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 4d7493fa0105..290716783ac6 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -62,7 +62,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	}
 	evlist__add(evlist, evsel);
 
-	cpus = perf_cpu_map__dummy_new();
+	cpus = perf_cpu_map__new_any_cpu();
 	threads = thread_map__new_by_tid(getpid());
 	if (!cpus || !threads) {
 		err = -ENOMEM;
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index e52b031bedc5..5cab17a1942e 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -351,7 +351,7 @@ static int test__switch_tracking(struct test_suite *test __maybe_unused, int sub
 		goto out_err;
 	}
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus) {
 		pr_debug("perf_cpu_map__new failed!\n");
 		goto out_err;
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 968dddde6dda..d33d0952025c 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -70,7 +70,7 @@ static int test__task_exit(struct test_suite *test __maybe_unused, int subtest _
 	 * evlist__prepare_workload we'll fill in the only thread
 	 * we're monitoring, the one forked there.
 	 */
-	cpus = perf_cpu_map__dummy_new();
+	cpus = perf_cpu_map__new_any_cpu();
 	threads = thread_map__new_by_tid(-1);
 	if (!cpus || !threads) {
 		err = -ENOMEM;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index b394f3ac2d66..dad3d7414142 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -207,5 +207,6 @@ DECLARE_WORKLOAD(brstack);
 DECLARE_WORKLOAD(datasym);
 
 extern const char *dso_to_test;
+extern const char *test_objdump_path;
 
 #endif /* TESTS_H */
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 9dee63734e66..2a842f53fbb5 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -215,7 +215,7 @@ static int test__session_topology(struct test_suite *test __maybe_unused, int su
 	if (session_write_header(path))
 		goto free_path;
 
-	map = perf_cpu_map__new(NULL);
+	map = perf_cpu_map__new_online_cpus();
 	if (map == NULL) {
 		pr_debug("failed to get system cpumap\n");
 		goto free_path;
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 1078a93b01aa..822f893e67d5 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -112,18 +112,92 @@ static bool is_ignored_symbol(const char *name, char type)
 	return false;
 }
 
+struct test__vmlinux_matches_kallsyms_cb_args {
+	struct machine kallsyms;
+	struct map *vmlinux_map;
+	bool header_printed;
+};
+
+static int test__vmlinux_matches_kallsyms_cb1(struct map *map, void *data)
+{
+	struct test__vmlinux_matches_kallsyms_cb_args *args = data;
+	struct dso *dso = map__dso(map);
+	/*
+	 * If it is the kernel, kallsyms is always "[kernel.kallsyms]", while
+	 * the kernel will have the path for the vmlinux file being used, so use
+	 * the short name, less descriptive but the same ("[kernel]" in both
+	 * cases.
+	 */
+	struct map *pair = maps__find_by_name(args->kallsyms.kmaps,
+					(dso->kernel ? dso->short_name : dso->name));
+
+	if (pair)
+		map__set_priv(pair, 1);
+	else {
+		if (!args->header_printed) {
+			pr_info("WARN: Maps only in vmlinux:\n");
+			args->header_printed = true;
+		}
+		map__fprintf(map, stderr);
+	}
+	return 0;
+}
+
+static int test__vmlinux_matches_kallsyms_cb2(struct map *map, void *data)
+{
+	struct test__vmlinux_matches_kallsyms_cb_args *args = data;
+	struct map *pair;
+	u64 mem_start = map__unmap_ip(args->vmlinux_map, map__start(map));
+	u64 mem_end = map__unmap_ip(args->vmlinux_map, map__end(map));
+
+	pair = maps__find(args->kallsyms.kmaps, mem_start);
+	if (pair == NULL || map__priv(pair))
+		return 0;
+
+	if (map__start(pair) == mem_start) {
+		struct dso *dso = map__dso(map);
+
+		if (!args->header_printed) {
+			pr_info("WARN: Maps in vmlinux with a different name in kallsyms:\n");
+			args->header_printed = true;
+		}
+
+		pr_info("WARN: %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as",
+			map__start(map), map__end(map), map__pgoff(map), dso->name);
+		if (mem_end != map__end(pair))
+			pr_info(":\nWARN: *%" PRIx64 "-%" PRIx64 " %" PRIx64,
+				map__start(pair), map__end(pair), map__pgoff(pair));
+		pr_info(" %s\n", dso->name);
+		map__set_priv(pair, 1);
+	}
+	return 0;
+}
+
+static int test__vmlinux_matches_kallsyms_cb3(struct map *map, void *data)
+{
+	struct test__vmlinux_matches_kallsyms_cb_args *args = data;
+
+	if (!map__priv(map)) {
+		if (!args->header_printed) {
+			pr_info("WARN: Maps only in kallsyms:\n");
+			args->header_printed = true;
+		}
+		map__fprintf(map, stderr);
+	}
+	return 0;
+}
+
 static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused,
 					int subtest __maybe_unused)
 {
 	int err = TEST_FAIL;
 	struct rb_node *nd;
 	struct symbol *sym;
-	struct map *kallsyms_map, *vmlinux_map;
-	struct map_rb_node *rb_node;
-	struct machine kallsyms, vmlinux;
+	struct map *kallsyms_map;
+	struct machine vmlinux;
 	struct maps *maps;
 	u64 mem_start, mem_end;
-	bool header_printed;
+	struct test__vmlinux_matches_kallsyms_cb_args args;
 
 	/*
 	 * Step 1:
@@ -131,7 +205,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused
 	 * Init the machines that will hold kernel, modules obtained from
 	 * both vmlinux + .ko files and from /proc/kallsyms split by modules.
 	 */
-	machine__init(&kallsyms, "", HOST_KERNEL_ID);
+	machine__init(&args.kallsyms, "", HOST_KERNEL_ID);
 	machine__init(&vmlinux, "", HOST_KERNEL_ID);
 
 	maps = machine__kernel_maps(&vmlinux);
@@ -143,7 +217,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused
 	 * load /proc/kallsyms. Also create the modules maps from /proc/modules
 	 * and find the .ko files that match them in /lib/modules/`uname -r`/.
 	 */
-	if (machine__create_kernel_maps(&kallsyms) < 0) {
+	if (machine__create_kernel_maps(&args.kallsyms) < 0) {
 		pr_debug("machine__create_kernel_maps failed");
 		err = TEST_SKIP;
 		goto out;
@@ -160,7 +234,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused
 	 * be compacted against the list of modules found in the "vmlinux"
 	 * code and with the one got from /proc/modules from the "kallsyms" code.
 	 */
-	if (machine__load_kallsyms(&kallsyms, "/proc/kallsyms") <= 0) {
+	if (machine__load_kallsyms(&args.kallsyms, "/proc/kallsyms") <= 0) {
 		pr_debug("machine__load_kallsyms failed");
 		err = TEST_SKIP;
 		goto out;
@@ -174,7 +248,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused
 	 * to see if the running kernel was relocated by checking if it has the
 	 * same value in the vmlinux file we load.
 	 */
-	kallsyms_map = machine__kernel_map(&kallsyms);
+	kallsyms_map = machine__kernel_map(&args.kallsyms);
 
 	/*
 	 * Step 5:
@@ -186,7 +260,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused
 		goto out;
 	}
 
-	vmlinux_map = machine__kernel_map(&vmlinux);
+	args.vmlinux_map = machine__kernel_map(&vmlinux);
 
 	/*
 	 * Step 6:
@@ -213,7 +287,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused
 	 * in the kallsyms dso. For the ones that are in both, check its names and
 	 * end addresses too.
 	 */
-	map__for_each_symbol(vmlinux_map, sym, nd) {
+	map__for_each_symbol(args.vmlinux_map, sym, nd) {
 		struct symbol *pair, *first_pair;
 
 		sym  = rb_entry(nd, struct symbol, rb_node);
@@ -221,10 +295,10 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused
 		if (sym->start == sym->end)
 			continue;
 
-		mem_start = map__unmap_ip(vmlinux_map, sym->start);
-		mem_end = map__unmap_ip(vmlinux_map, sym->end);
+		mem_start = map__unmap_ip(args.vmlinux_map, sym->start);
+		mem_end = map__unmap_ip(args.vmlinux_map, sym->end);
 
-		first_pair = machine__find_kernel_symbol(&kallsyms, mem_start, NULL);
+		first_pair = machine__find_kernel_symbol(&args.kallsyms, mem_start, NULL);
 		pair = first_pair;
 
 		if (pair && UM(pair->start) == mem_start) {
@@ -253,7 +327,8 @@ next_pair:
 				 */
 				continue;
 			} else {
-				pair = machine__find_kernel_symbol_by_name(&kallsyms, sym->name, NULL);
+				pair = machine__find_kernel_symbol_by_name(&args.kallsyms,
+									   sym->name, NULL);
 				if (pair) {
 					if (UM(pair->start) == mem_start)
 						goto next_pair;
@@ -267,7 +342,7 @@ next_pair:
 
 				continue;
 			}
-		} else if (mem_start == map__end(kallsyms.vmlinux_map)) {
+		} else if (mem_start == map__end(args.kallsyms.vmlinux_map)) {
 			/*
 			 * Ignore aliases to _etext, i.e. to the end of the kernel text area,
 			 * such as __indirect_thunk_end.
@@ -289,78 +364,18 @@ next_pair:
 	if (verbose <= 0)
 		goto out;
 
-	header_printed = false;
-
-	maps__for_each_entry(maps, rb_node) {
-		struct map *map = rb_node->map;
-		struct dso *dso = map__dso(map);
-		/*
-		 * If it is the kernel, kallsyms is always "[kernel.kallsyms]", while
-		 * the kernel will have the path for the vmlinux file being used,
-		 * so use the short name, less descriptive but the same ("[kernel]" in
-		 * both cases.
-		 */
-		struct map *pair = maps__find_by_name(kallsyms.kmaps, (dso->kernel ?
-								dso->short_name :
-								dso->name));
-		if (pair) {
-			map__set_priv(pair, 1);
-		} else {
-			if (!header_printed) {
-				pr_info("WARN: Maps only in vmlinux:\n");
-				header_printed = true;
-			}
-			map__fprintf(map, stderr);
-		}
-	}
-
-	header_printed = false;
-
-	maps__for_each_entry(maps, rb_node) {
-		struct map *pair, *map = rb_node->map;
-
-		mem_start = map__unmap_ip(vmlinux_map, map__start(map));
-		mem_end = map__unmap_ip(vmlinux_map, map__end(map));
+	args.header_printed = false;
+	maps__for_each_map(maps, test__vmlinux_matches_kallsyms_cb1, &args);
 
-		pair = maps__find(kallsyms.kmaps, mem_start);
-		if (pair == NULL || map__priv(pair))
-			continue;
-
-		if (map__start(pair) == mem_start) {
-			struct dso *dso = map__dso(map);
-
-			if (!header_printed) {
-				pr_info("WARN: Maps in vmlinux with a different name in kallsyms:\n");
-				header_printed = true;
-			}
-
-			pr_info("WARN: %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as",
-				map__start(map), map__end(map), map__pgoff(map), dso->name);
-			if (mem_end != map__end(pair))
-				pr_info(":\nWARN: *%" PRIx64 "-%" PRIx64 " %" PRIx64,
-					map__start(pair), map__end(pair), map__pgoff(pair));
-			pr_info(" %s\n", dso->name);
-			map__set_priv(pair, 1);
-		}
-	}
-
-	header_printed = false;
-
-	maps = machine__kernel_maps(&kallsyms);
+	args.header_printed = false;
+	maps__for_each_map(maps, test__vmlinux_matches_kallsyms_cb2, &args);
 
-	maps__for_each_entry(maps, rb_node) {
-		struct map *map = rb_node->map;
+	args.header_printed = false;
+	maps = machine__kernel_maps(&args.kallsyms);
+	maps__for_each_map(maps, test__vmlinux_matches_kallsyms_cb3, &args);
 
-		if (!map__priv(map)) {
-			if (!header_printed) {
-				pr_info("WARN: Maps only in kallsyms:\n");
-				header_printed = true;
-			}
-			map__fprintf(map, stderr);
-		}
-	}
 out:
-	machine__exit(&kallsyms);
+	machine__exit(&args.kallsyms);
 	machine__exit(&vmlinux);
 	return err;
 }
diff --git a/tools/perf/tests/workloads/thloop.c b/tools/perf/tests/workloads/thloop.c
index af05269c2eb8..457b29f91c3e 100644
--- a/tools/perf/tests/workloads/thloop.c
+++ b/tools/perf/tests/workloads/thloop.c
@@ -7,7 +7,6 @@
 #include "../tests.h"
 
 static volatile sig_atomic_t done;
-static volatile unsigned count;
 
 /* We want to check this symbol in perf report */
 noinline void test_loop(void);
@@ -19,8 +18,7 @@ static void sighandler(int sig __maybe_unused)
 
 noinline void test_loop(void)
 {
-	while (!done)
-		__atomic_fetch_add(&count, 1, __ATOMIC_RELAXED);
+	while (!done);
 }
 
 static void *thfunc(void *arg)
diff --git a/tools/perf/trace/beauty/arch_errno_names.sh b/tools/perf/trace/beauty/arch_errno_names.sh
index cc09dcaa891e..7df4bf5b55a3 100755
--- a/tools/perf/trace/beauty/arch_errno_names.sh
+++ b/tools/perf/trace/beauty/arch_errno_names.sh
@@ -57,13 +57,13 @@ create_arch_errno_table_func()
 	archlist="$1"
 	default="$2"
 
-	printf 'const char *arch_syscalls__strerrno(const char *arch, int err)\n'
+	printf 'arch_syscalls__strerrno_t *arch_syscalls__strerrno_function(const char *arch)\n'
 	printf '{\n'
 	for arch in $archlist; do
 		printf '\tif (!strcmp(arch, "%s"))\n' $(arch_string "$arch")
-		printf '\t\treturn errno_to_name__%s(err);\n' $(arch_string "$arch")
+		printf '\t\treturn errno_to_name__%s;\n' $(arch_string "$arch")
 	done
-	printf '\treturn errno_to_name__%s(err);\n' $(arch_string "$default")
+	printf '\treturn errno_to_name__%s;\n' $(arch_string "$default")
 	printf '}\n'
 }
 
@@ -76,7 +76,9 @@ EoHEADER
 
 # Create list of architectures that have a specific errno.h.
 archlist=""
-for arch in $(find $toolsdir/arch -maxdepth 1 -mindepth 1 -type d -printf "%f\n" | sort -r); do
+for f in $toolsdir/arch/*/include/uapi/asm/errno.h; do
+	d=${f%/include/uapi/asm/errno.h}
+	arch="${d##*/}"
 	test -f $toolsdir/arch/$arch/include/uapi/asm/errno.h && archlist="$archlist $arch"
 done
 
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 788e8f6bd90e..9feb794f5c6e 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -251,6 +251,4 @@ size_t open__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool sh
 void syscall_arg__set_ret_scnprintf(struct syscall_arg *arg,
 				    size_t (*ret_scnprintf)(char *bf, size_t size, struct syscall_arg *arg));
 
-const char *arch_syscalls__strerrno(const char *arch, int err);
-
 #endif /* _PERF_TRACE_BEAUTY_H */
diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh
index 8059342ca412..9455d9672f14 100755
--- a/tools/perf/trace/beauty/prctl_option.sh
+++ b/tools/perf/trace/beauty/prctl_option.sh
@@ -4,9 +4,9 @@
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *prctl_options[] = {\n"
-regex='^#define[[:space:]]{1}PR_(\w+)[[:space:]]*([[:xdigit:]]+)([[:space:]]*\/.*)?$'
+regex='^#define[[:space:]]{1}PR_(\w+)[[:space:]]*([[:xdigit:]]+)([[:space:]]*/.*)?$'
 grep -E $regex ${header_dir}/prctl.h | grep -v PR_SET_PTRACER | \
-	sed -r "s/$regex/\2 \1/g"	| \
+	sed -E "s%$regex%\2 \1%g"	| \
 	sort -n | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
 
diff --git a/tools/perf/trace/beauty/socket.sh b/tools/perf/trace/beauty/socket.sh
index 8bc7ba62203e..670c6db298ae 100755
--- a/tools/perf/trace/beauty/socket.sh
+++ b/tools/perf/trace/beauty/socket.sh
@@ -18,10 +18,10 @@ grep -E $ipproto_regex ${uapi_header_dir}/in.h | \
 printf "};\n\n"
 
 printf "static const char *socket_level[] = {\n"
-socket_level_regex='^#define[[:space:]]+SOL_(\w+)[[:space:]]+([[:digit:]]+)([[:space:]]+\/.*)?'
+socket_level_regex='^#define[[:space:]]+SOL_(\w+)[[:space:]]+([[:digit:]]+)([[:space:]]+/.*)?'
 
 grep -E $socket_level_regex ${beauty_header_dir}/socket.h | \
-	sed -r "s/$socket_level_regex/\2 \1/g"	| \
+	sed -E "s%$socket_level_regex%\2 \1%g"	| \
 	sort -n | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n\n"
 
diff --git a/tools/perf/trace/beauty/statx.c b/tools/perf/trace/beauty/statx.c
index 5f5320f7c6e2..dc5943a6352d 100644
--- a/tools/perf/trace/beauty/statx.c
+++ b/tools/perf/trace/beauty/statx.c
@@ -67,6 +67,7 @@ size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_a
 	P_FLAG(BTIME);
 	P_FLAG(MNT_ID);
 	P_FLAG(DIOALIGN);
+	P_FLAG(MNT_ID_UNIQUE);
 
 #undef P_FLAG
 
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index ccdb2cd11fbf..ec5e21932876 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -27,7 +27,6 @@ struct annotate_browser {
 	struct rb_node		   *curr_hot;
 	struct annotation_line	   *selection;
 	struct arch		   *arch;
-	struct annotation_options  *opts;
 	bool			    searching_backwards;
 	char			    search_bf[128];
 };
@@ -38,11 +37,10 @@ static inline struct annotation *browser__annotation(struct ui_browser *browser)
 	return symbol__annotation(ms->sym);
 }
 
-static bool disasm_line__filter(struct ui_browser *browser, void *entry)
+static bool disasm_line__filter(struct ui_browser *browser __maybe_unused, void *entry)
 {
-	struct annotation *notes = browser__annotation(browser);
 	struct annotation_line *al = list_entry(entry, struct annotation_line, node);
-	return annotation_line__filter(al, notes);
+	return annotation_line__filter(al);
 }
 
 static int ui_browser__jumps_percent_color(struct ui_browser *browser, int nr, bool current)
@@ -97,7 +95,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 	struct annotation_write_ops ops = {
 		.first_line		 = row == 0,
 		.current_entry		 = is_current_entry,
-		.change_color		 = (!notes->options->hide_src_code &&
+		.change_color		 = (!annotate_opts.hide_src_code &&
 					    (!is_current_entry ||
 					     (browser->use_navkeypressed &&
 					      !browser->navkeypressed))),
@@ -114,7 +112,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 	if (!browser->navkeypressed)
 		ops.width += 1;
 
-	annotation_line__write(al, notes, &ops, ab->opts);
+	annotation_line__write(al, notes, &ops);
 
 	if (ops.current_entry)
 		ab->selection = al;
@@ -128,7 +126,7 @@ static int is_fused(struct annotate_browser *ab, struct disasm_line *cursor)
 
 	while (pos && pos->al.offset == -1) {
 		pos = list_prev_entry(pos, al.node);
-		if (!ab->opts->hide_src_code)
+		if (!annotate_opts.hide_src_code)
 			diff++;
 	}
 
@@ -188,14 +186,14 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 	 *  name right after the '<' token and probably treating this like a
 	 *  'call' instruction.
 	 */
-	target = notes->offsets[cursor->ops.target.offset];
+	target = notes->src->offsets[cursor->ops.target.offset];
 	if (target == NULL) {
 		ui_helpline__printf("WARN: jump target inconsistency, press 'o', notes->offsets[%#x] = NULL\n",
 				    cursor->ops.target.offset);
 		return;
 	}
 
-	if (notes->options->hide_src_code) {
+	if (annotate_opts.hide_src_code) {
 		from = cursor->al.idx_asm;
 		to = target->idx_asm;
 	} else {
@@ -224,7 +222,7 @@ static unsigned int annotate_browser__refresh(struct ui_browser *browser)
 	int ret = ui_browser__list_head_refresh(browser);
 	int pcnt_width = annotation__pcnt_width(notes);
 
-	if (notes->options->jump_arrows)
+	if (annotate_opts.jump_arrows)
 		annotate_browser__draw_current_jump(browser);
 
 	ui_browser__set_color(browser, HE_COLORSET_NORMAL);
@@ -258,7 +256,7 @@ static void disasm_rb_tree__insert(struct annotate_browser *browser,
 		parent = *p;
 		l = rb_entry(parent, struct annotation_line, rb_node);
 
-		if (disasm__cmp(al, l, browser->opts->percent_type) < 0)
+		if (disasm__cmp(al, l, annotate_opts.percent_type) < 0)
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
@@ -270,7 +268,6 @@ static void disasm_rb_tree__insert(struct annotate_browser *browser,
 static void annotate_browser__set_top(struct annotate_browser *browser,
 				      struct annotation_line *pos, u32 idx)
 {
-	struct annotation *notes = browser__annotation(&browser->b);
 	unsigned back;
 
 	ui_browser__refresh_dimensions(&browser->b);
@@ -280,7 +277,7 @@ static void annotate_browser__set_top(struct annotate_browser *browser,
 	while (browser->b.top_idx != 0 && back != 0) {
 		pos = list_entry(pos->node.prev, struct annotation_line, node);
 
-		if (annotation_line__filter(pos, notes))
+		if (annotation_line__filter(pos))
 			continue;
 
 		--browser->b.top_idx;
@@ -294,11 +291,10 @@ static void annotate_browser__set_top(struct annotate_browser *browser,
 static void annotate_browser__set_rb_top(struct annotate_browser *browser,
 					 struct rb_node *nd)
 {
-	struct annotation *notes = browser__annotation(&browser->b);
 	struct annotation_line * pos = rb_entry(nd, struct annotation_line, rb_node);
 	u32 idx = pos->idx;
 
-	if (notes->options->hide_src_code)
+	if (annotate_opts.hide_src_code)
 		idx = pos->idx_asm;
 	annotate_browser__set_top(browser, pos, idx);
 	browser->curr_hot = nd;
@@ -331,13 +327,13 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser,
 			double percent;
 
 			percent = annotation_data__percent(&pos->al.data[i],
-							   browser->opts->percent_type);
+							   annotate_opts.percent_type);
 
 			if (max_percent < percent)
 				max_percent = percent;
 		}
 
-		if (max_percent < 0.01 && pos->al.ipc == 0) {
+		if (max_percent < 0.01 && (!pos->al.cycles || pos->al.cycles->ipc == 0)) {
 			RB_CLEAR_NODE(&pos->al.rb_node);
 			continue;
 		}
@@ -380,12 +376,12 @@ static bool annotate_browser__toggle_source(struct annotate_browser *browser)
 	browser->b.seek(&browser->b, offset, SEEK_CUR);
 	al = list_entry(browser->b.top, struct annotation_line, node);
 
-	if (notes->options->hide_src_code) {
+	if (annotate_opts.hide_src_code) {
 		if (al->idx_asm < offset)
 			offset = al->idx;
 
-		browser->b.nr_entries = notes->nr_entries;
-		notes->options->hide_src_code = false;
+		browser->b.nr_entries = notes->src->nr_entries;
+		annotate_opts.hide_src_code = false;
 		browser->b.seek(&browser->b, -offset, SEEK_CUR);
 		browser->b.top_idx = al->idx - offset;
 		browser->b.index = al->idx;
@@ -402,8 +398,8 @@ static bool annotate_browser__toggle_source(struct annotate_browser *browser)
 		if (al->idx_asm < offset)
 			offset = al->idx_asm;
 
-		browser->b.nr_entries = notes->nr_asm_entries;
-		notes->options->hide_src_code = true;
+		browser->b.nr_entries = notes->src->nr_asm_entries;
+		annotate_opts.hide_src_code = true;
 		browser->b.seek(&browser->b, -offset, SEEK_CUR);
 		browser->b.top_idx = al->idx_asm - offset;
 		browser->b.index = al->idx_asm;
@@ -435,7 +431,7 @@ static void ui_browser__init_asm_mode(struct ui_browser *browser)
 {
 	struct annotation *notes = browser__annotation(browser);
 	ui_browser__reset_index(browser);
-	browser->nr_entries = notes->nr_asm_entries;
+	browser->nr_entries = notes->src->nr_asm_entries;
 }
 
 static int sym_title(struct symbol *sym, struct map *map, char *title,
@@ -483,8 +479,8 @@ static bool annotate_browser__callq(struct annotate_browser *browser,
 	target_ms.map = ms->map;
 	target_ms.sym = dl->ops.target.sym;
 	annotation__unlock(notes);
-	symbol__tui_annotate(&target_ms, evsel, hbt, browser->opts);
-	sym_title(ms->sym, ms->map, title, sizeof(title), browser->opts->percent_type);
+	symbol__tui_annotate(&target_ms, evsel, hbt);
+	sym_title(ms->sym, ms->map, title, sizeof(title), annotate_opts.percent_type);
 	ui_browser__show_title(&browser->b, title);
 	return true;
 }
@@ -500,7 +496,7 @@ struct disasm_line *annotate_browser__find_offset(struct annotate_browser *brows
 	list_for_each_entry(pos, &notes->src->source, al.node) {
 		if (pos->al.offset == offset)
 			return pos;
-		if (!annotation_line__filter(&pos->al, notes))
+		if (!annotation_line__filter(&pos->al))
 			++*idx;
 	}
 
@@ -544,7 +540,7 @@ struct annotation_line *annotate_browser__find_string(struct annotate_browser *b
 
 	*idx = browser->b.index;
 	list_for_each_entry_continue(al, &notes->src->source, node) {
-		if (annotation_line__filter(al, notes))
+		if (annotation_line__filter(al))
 			continue;
 
 		++*idx;
@@ -581,7 +577,7 @@ struct annotation_line *annotate_browser__find_string_reverse(struct annotate_br
 
 	*idx = browser->b.index;
 	list_for_each_entry_continue_reverse(al, &notes->src->source, node) {
-		if (annotation_line__filter(al, notes))
+		if (annotation_line__filter(al))
 			continue;
 
 		--*idx;
@@ -659,7 +655,6 @@ bool annotate_browser__continue_search_reverse(struct annotate_browser *browser,
 
 static int annotate_browser__show(struct ui_browser *browser, char *title, const char *help)
 {
-	struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
 	struct map_symbol *ms = browser->priv;
 	struct symbol *sym = ms->sym;
 	char symbol_dso[SYM_TITLE_MAX_SIZE];
@@ -667,7 +662,7 @@ static int annotate_browser__show(struct ui_browser *browser, char *title, const
 	if (ui_browser__show(browser, title, help) < 0)
 		return -1;
 
-	sym_title(sym, ms->map, symbol_dso, sizeof(symbol_dso), ab->opts->percent_type);
+	sym_title(sym, ms->map, symbol_dso, sizeof(symbol_dso), annotate_opts.percent_type);
 
 	ui_browser__gotorc_title(browser, 0, 0);
 	ui_browser__set_color(browser, HE_COLORSET_ROOT);
@@ -809,7 +804,7 @@ static int annotate_browser__run(struct annotate_browser *browser,
 			annotate_browser__show(&browser->b, title, help);
 			continue;
 		case 'k':
-			notes->options->show_linenr = !notes->options->show_linenr;
+			annotate_opts.show_linenr = !annotate_opts.show_linenr;
 			continue;
 		case 'l':
 			annotate_browser__show_full_location (&browser->b);
@@ -822,18 +817,18 @@ static int annotate_browser__run(struct annotate_browser *browser,
 				ui_helpline__puts(help);
 			continue;
 		case 'o':
-			notes->options->use_offset = !notes->options->use_offset;
+			annotate_opts.use_offset = !annotate_opts.use_offset;
 			annotation__update_column_widths(notes);
 			continue;
 		case 'O':
-			if (++notes->options->offset_level > ANNOTATION__MAX_OFFSET_LEVEL)
-				notes->options->offset_level = ANNOTATION__MIN_OFFSET_LEVEL;
+			if (++annotate_opts.offset_level > ANNOTATION__MAX_OFFSET_LEVEL)
+				annotate_opts.offset_level = ANNOTATION__MIN_OFFSET_LEVEL;
 			continue;
 		case 'j':
-			notes->options->jump_arrows = !notes->options->jump_arrows;
+			annotate_opts.jump_arrows = !annotate_opts.jump_arrows;
 			continue;
 		case 'J':
-			notes->options->show_nr_jumps = !notes->options->show_nr_jumps;
+			annotate_opts.show_nr_jumps = !annotate_opts.show_nr_jumps;
 			annotation__update_column_widths(notes);
 			continue;
 		case '/':
@@ -860,7 +855,7 @@ show_help:
 					   browser->b.height,
 					   browser->b.index,
 					   browser->b.top_idx,
-					   notes->nr_asm_entries);
+					   notes->src->nr_asm_entries);
 		}
 			continue;
 		case K_ENTER:
@@ -884,7 +879,7 @@ show_sup_ins:
 			continue;
 		}
 		case 'P':
-			map_symbol__annotation_dump(ms, evsel, browser->opts);
+			map_symbol__annotation_dump(ms, evsel);
 			continue;
 		case 't':
 			if (symbol_conf.show_total_period) {
@@ -897,15 +892,15 @@ show_sup_ins:
 			annotation__update_column_widths(notes);
 			continue;
 		case 'c':
-			if (notes->options->show_minmax_cycle)
-				notes->options->show_minmax_cycle = false;
+			if (annotate_opts.show_minmax_cycle)
+				annotate_opts.show_minmax_cycle = false;
 			else
-				notes->options->show_minmax_cycle = true;
+				annotate_opts.show_minmax_cycle = true;
 			annotation__update_column_widths(notes);
 			continue;
 		case 'p':
 		case 'b':
-			switch_percent_type(browser->opts, key == 'b');
+			switch_percent_type(&annotate_opts, key == 'b');
 			hists__scnprintf_title(hists, title, sizeof(title));
 			annotate_browser__show(&browser->b, title, help);
 			continue;
@@ -932,26 +927,24 @@ out:
 }
 
 int map_symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
-			     struct hist_browser_timer *hbt,
-			     struct annotation_options *opts)
+			     struct hist_browser_timer *hbt)
 {
-	return symbol__tui_annotate(ms, evsel, hbt, opts);
+	return symbol__tui_annotate(ms, evsel, hbt);
 }
 
 int hist_entry__tui_annotate(struct hist_entry *he, struct evsel *evsel,
-			     struct hist_browser_timer *hbt,
-			     struct annotation_options *opts)
+			     struct hist_browser_timer *hbt)
 {
 	/* reset abort key so that it can get Ctrl-C as a key */
 	SLang_reset_tty();
 	SLang_init_tty(0, 0, 0);
+	SLtty_set_suspend_state(true);
 
-	return map_symbol__tui_annotate(&he->ms, evsel, hbt, opts);
+	return map_symbol__tui_annotate(&he->ms, evsel, hbt);
 }
 
 int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
-			 struct hist_browser_timer *hbt,
-			 struct annotation_options *opts)
+			 struct hist_browser_timer *hbt)
 {
 	struct symbol *sym = ms->sym;
 	struct annotation *notes = symbol__annotation(sym);
@@ -965,7 +958,6 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
 			.priv	 = ms,
 			.use_navkeypressed = true,
 		},
-		.opts = opts,
 	};
 	struct dso *dso;
 	int ret = -1, err;
@@ -979,7 +971,7 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
 		return -1;
 
 	if (not_annotated) {
-		err = symbol__annotate2(ms, evsel, opts, &browser.arch);
+		err = symbol__annotate2(ms, evsel, &browser.arch);
 		if (err) {
 			char msg[BUFSIZ];
 			dso->annotate_warned = true;
@@ -991,12 +983,12 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
 
 	ui_helpline__push("Press ESC to exit");
 
-	browser.b.width = notes->max_line_len;
-	browser.b.nr_entries = notes->nr_entries;
+	browser.b.width = notes->src->max_line_len;
+	browser.b.nr_entries = notes->src->nr_entries;
 	browser.b.entries = &notes->src->source,
 	browser.b.width += 18; /* Percentage */
 
-	if (notes->options->hide_src_code)
+	if (annotate_opts.hide_src_code)
 		ui_browser__init_asm_mode(&browser.b);
 
 	ret = annotate_browser__run(&browser, evsel, hbt);
@@ -1006,6 +998,6 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
 
 out_free_offsets:
 	if(not_annotated)
-		zfree(&notes->offsets);
+		zfree(&notes->src->offsets);
 	return ret;
 }
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index f4812b226818..0c02b3a8e121 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -2250,8 +2250,7 @@ struct hist_browser *hist_browser__new(struct hists *hists)
 static struct hist_browser *
 perf_evsel_browser__new(struct evsel *evsel,
 			struct hist_browser_timer *hbt,
-			struct perf_env *env,
-			struct annotation_options *annotation_opts)
+			struct perf_env *env)
 {
 	struct hist_browser *browser = hist_browser__new(evsel__hists(evsel));
 
@@ -2259,7 +2258,6 @@ perf_evsel_browser__new(struct evsel *evsel,
 		browser->hbt   = hbt;
 		browser->env   = env;
 		browser->title = hists_browser__scnprintf_title;
-		browser->annotation_opts = annotation_opts;
 	}
 	return browser;
 }
@@ -2432,8 +2430,8 @@ do_annotate(struct hist_browser *browser, struct popup_action *act)
 	struct hist_entry *he;
 	int err;
 
-	if (!browser->annotation_opts->objdump_path &&
-	    perf_env__lookup_objdump(browser->env, &browser->annotation_opts->objdump_path))
+	if (!annotate_opts.objdump_path &&
+	    perf_env__lookup_objdump(browser->env, &annotate_opts.objdump_path))
 		return 0;
 
 	notes = symbol__annotation(act->ms.sym);
@@ -2445,8 +2443,7 @@ do_annotate(struct hist_browser *browser, struct popup_action *act)
 	else
 		evsel = hists_to_evsel(browser->hists);
 
-	err = map_symbol__tui_annotate(&act->ms, evsel, browser->hbt,
-				       browser->annotation_opts);
+	err = map_symbol__tui_annotate(&act->ms, evsel, browser->hbt);
 	he = hist_browser__selected_entry(browser);
 	/*
 	 * offer option to annotate the other branch source or target
@@ -2943,11 +2940,10 @@ next:
 
 static int evsel__hists_browse(struct evsel *evsel, int nr_events, const char *helpline,
 			       bool left_exits, struct hist_browser_timer *hbt, float min_pcnt,
-			       struct perf_env *env, bool warn_lost_event,
-			       struct annotation_options *annotation_opts)
+			       struct perf_env *env, bool warn_lost_event)
 {
 	struct hists *hists = evsel__hists(evsel);
-	struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env, annotation_opts);
+	struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env);
 	struct branch_info *bi = NULL;
 #define MAX_OPTIONS  16
 	char *options[MAX_OPTIONS];
@@ -3004,6 +3000,7 @@ static int evsel__hists_browse(struct evsel *evsel, int nr_events, const char *h
 	/* reset abort key so that it can get Ctrl-C as a key */
 	SLang_reset_tty();
 	SLang_init_tty(0, 0, 0);
+	SLtty_set_suspend_state(true);
 
 	if (min_pcnt)
 		browser->min_pcnt = min_pcnt;
@@ -3398,7 +3395,6 @@ out:
 struct evsel_menu {
 	struct ui_browser b;
 	struct evsel *selection;
-	struct annotation_options *annotation_opts;
 	bool lost_events, lost_events_warned;
 	float min_pcnt;
 	struct perf_env *env;
@@ -3499,8 +3495,7 @@ browse_hists:
 				hbt->timer(hbt->arg);
 			key = evsel__hists_browse(pos, nr_events, help, true, hbt,
 						  menu->min_pcnt, menu->env,
-						  warn_lost_event,
-						  menu->annotation_opts);
+						  warn_lost_event);
 			ui_browser__show_title(&menu->b, title);
 			switch (key) {
 			case K_TAB:
@@ -3557,7 +3552,7 @@ static bool filter_group_entries(struct ui_browser *browser __maybe_unused,
 
 static int __evlist__tui_browse_hists(struct evlist *evlist, int nr_entries, const char *help,
 				      struct hist_browser_timer *hbt, float min_pcnt, struct perf_env *env,
-				      bool warn_lost_event, struct annotation_options *annotation_opts)
+				      bool warn_lost_event)
 {
 	struct evsel *pos;
 	struct evsel_menu menu = {
@@ -3572,7 +3567,6 @@ static int __evlist__tui_browse_hists(struct evlist *evlist, int nr_entries, con
 		},
 		.min_pcnt = min_pcnt,
 		.env = env,
-		.annotation_opts = annotation_opts,
 	};
 
 	ui_helpline__push("Press ESC to exit");
@@ -3607,8 +3601,7 @@ static bool evlist__single_entry(struct evlist *evlist)
 }
 
 int evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt,
-			     float min_pcnt, struct perf_env *env, bool warn_lost_event,
-			     struct annotation_options *annotation_opts)
+			     float min_pcnt, struct perf_env *env, bool warn_lost_event)
 {
 	int nr_entries = evlist->core.nr_entries;
 
@@ -3617,7 +3610,7 @@ single_entry: {
 		struct evsel *first = evlist__first(evlist);
 
 		return evsel__hists_browse(first, nr_entries, help, false, hbt, min_pcnt,
-					   env, warn_lost_event, annotation_opts);
+					   env, warn_lost_event);
 	}
 	}
 
@@ -3635,7 +3628,7 @@ single_entry: {
 	}
 
 	return __evlist__tui_browse_hists(evlist, nr_entries, help, hbt, min_pcnt, env,
-					  warn_lost_event, annotation_opts);
+					  warn_lost_event);
 }
 
 static int block_hists_browser__title(struct hist_browser *browser, char *bf,
@@ -3654,8 +3647,7 @@ static int block_hists_browser__title(struct hist_browser *browser, char *bf,
 }
 
 int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel,
-			   float min_percent, struct perf_env *env,
-			   struct annotation_options *annotation_opts)
+			   float min_percent, struct perf_env *env)
 {
 	struct hists *hists = &bh->block_hists;
 	struct hist_browser *browser;
@@ -3672,11 +3664,11 @@ int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel,
 	browser->title = block_hists_browser__title;
 	browser->min_pcnt = min_percent;
 	browser->env = env;
-	browser->annotation_opts = annotation_opts;
 
 	/* reset abort key so that it can get Ctrl-C as a key */
 	SLang_reset_tty();
 	SLang_init_tty(0, 0, 0);
+	SLtty_set_suspend_state(true);
 
 	memset(&action, 0, sizeof(action));
 
diff --git a/tools/perf/ui/browsers/hists.h b/tools/perf/ui/browsers/hists.h
index 1e938d9ffa5e..de46f6c56b0e 100644
--- a/tools/perf/ui/browsers/hists.h
+++ b/tools/perf/ui/browsers/hists.h
@@ -4,7 +4,6 @@
 
 #include "ui/browser.h"
 
-struct annotation_options;
 struct evsel;
 
 struct hist_browser {
@@ -15,7 +14,6 @@ struct hist_browser {
 	struct hist_browser_timer *hbt;
 	struct pstack	    *pstack;
 	struct perf_env	    *env;
-	struct annotation_options *annotation_opts;
 	struct evsel	    *block_evsel;
 	int		     print_seq;
 	bool		     show_dso;
diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c
index 47d2c7a8cbe1..50d45054ed6c 100644
--- a/tools/perf/ui/browsers/scripts.c
+++ b/tools/perf/ui/browsers/scripts.c
@@ -166,6 +166,7 @@ void run_script(char *cmd)
 	printf("\033[c\033[H\033[J");
 	fflush(stdout);
 	SLang_init_tty(0, 0, 0);
+	SLtty_set_suspend_state(true);
 	SLsmg_refresh();
 }
 
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index 2effac77ca8c..394861245fd3 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -162,7 +162,6 @@ static int perf_gtk__annotate_symbol(GtkWidget *window, struct map_symbol *ms,
 }
 
 static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel,
-				struct annotation_options *options,
 				struct hist_browser_timer *hbt)
 {
 	struct dso *dso = map__dso(ms->map);
@@ -176,7 +175,7 @@ static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel,
 	if (dso->annotate_warned)
 		return -1;
 
-	err = symbol__annotate(ms, evsel, options, NULL);
+	err = symbol__annotate(ms, evsel, NULL);
 	if (err) {
 		char msg[BUFSIZ];
 		dso->annotate_warned = true;
@@ -244,10 +243,9 @@ static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel,
 
 int hist_entry__gtk_annotate(struct hist_entry *he,
 			     struct evsel *evsel,
-			     struct annotation_options *options,
 			     struct hist_browser_timer *hbt)
 {
-	return symbol__gtk_annotate(&he->ms, evsel, options, hbt);
+	return symbol__gtk_annotate(&he->ms, evsel, hbt);
 }
 
 void perf_gtk__show_annotations(void)
diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h
index 1e84dceb5267..a2b497f03fd6 100644
--- a/tools/perf/ui/gtk/gtk.h
+++ b/tools/perf/ui/gtk/gtk.h
@@ -56,13 +56,11 @@ struct evsel;
 struct evlist;
 struct hist_entry;
 struct hist_browser_timer;
-struct annotation_options;
 
 int evlist__gtk_browse_hists(struct evlist *evlist, const char *help,
 			     struct hist_browser_timer *hbt, float min_pcnt);
 int hist_entry__gtk_annotate(struct hist_entry *he,
 			     struct evsel *evsel,
-			     struct annotation_options *options,
 			     struct hist_browser_timer *hbt);
 void perf_gtk__show_annotations(void);
 
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index 605d9e175ea7..16c6eff4d241 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -2,12 +2,14 @@
 #include <signal.h>
 #include <stdbool.h>
 #include <stdlib.h>
+#include <termios.h>
 #include <unistd.h>
 #include <linux/kernel.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
 #include <execinfo.h>
 #endif
 
+#include "../../util/color.h"
 #include "../../util/debug.h"
 #include "../browser.h"
 #include "../helpline.h"
@@ -121,6 +123,23 @@ static void ui__signal(int sig)
 	exit(0);
 }
 
+static void ui__sigcont(int sig)
+{
+	static struct termios tty;
+
+	if (sig == SIGTSTP) {
+		while (tcgetattr(SLang_TT_Read_FD, &tty) == -1 && errno == EINTR)
+			;
+		while (write(SLang_TT_Read_FD, PERF_COLOR_RESET, sizeof(PERF_COLOR_RESET) - 1) == -1 && errno == EINTR)
+			;
+		raise(SIGSTOP);
+	} else {
+		while (tcsetattr(SLang_TT_Read_FD, TCSADRAIN, &tty) == -1 && errno == EINTR)
+			;
+		raise(SIGWINCH);
+	}
+}
+
 int ui__init(void)
 {
 	int err;
@@ -135,6 +154,7 @@ int ui__init(void)
 	err = SLang_init_tty(-1, 0, 0);
 	if (err < 0)
 		goto out;
+	SLtty_set_suspend_state(true);
 
 	err = SLkp_init();
 	if (err < 0) {
@@ -149,6 +169,8 @@ int ui__init(void)
 	signal(SIGINT, ui__signal);
 	signal(SIGQUIT, ui__signal);
 	signal(SIGTERM, ui__signal);
+	signal(SIGTSTP, ui__sigcont);
+	signal(SIGCONT, ui__sigcont);
 
 	perf_error__register(&perf_tui_eops);
 
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 988473bf907a..8027f450fa3e 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -195,6 +195,8 @@ endif
 perf-$(CONFIG_DWARF) += probe-finder.o
 perf-$(CONFIG_DWARF) += dwarf-aux.o
 perf-$(CONFIG_DWARF) += dwarf-regs.o
+perf-$(CONFIG_DWARF) += debuginfo.o
+perf-$(CONFIG_DWARF) += annotate-data.o
 
 perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 perf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind-local.o
diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
new file mode 100644
index 000000000000..f22b4f18271c
--- /dev/null
+++ b/tools/perf/util/annotate-data.c
@@ -0,0 +1,405 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Convert sample address to data type using DWARF debug info.
+ *
+ * Written by Namhyung Kim <namhyung@kernel.org>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <inttypes.h>
+
+#include "annotate-data.h"
+#include "debuginfo.h"
+#include "debug.h"
+#include "dso.h"
+#include "evsel.h"
+#include "evlist.h"
+#include "map.h"
+#include "map_symbol.h"
+#include "strbuf.h"
+#include "symbol.h"
+#include "symbol_conf.h"
+
+/*
+ * Compare type name and size to maintain them in a tree.
+ * I'm not sure if DWARF would have information of a single type in many
+ * different places (compilation units).  If not, it could compare the
+ * offset of the type entry in the .debug_info section.
+ */
+static int data_type_cmp(const void *_key, const struct rb_node *node)
+{
+	const struct annotated_data_type *key = _key;
+	struct annotated_data_type *type;
+
+	type = rb_entry(node, struct annotated_data_type, node);
+
+	if (key->self.size != type->self.size)
+		return key->self.size - type->self.size;
+	return strcmp(key->self.type_name, type->self.type_name);
+}
+
+static bool data_type_less(struct rb_node *node_a, const struct rb_node *node_b)
+{
+	struct annotated_data_type *a, *b;
+
+	a = rb_entry(node_a, struct annotated_data_type, node);
+	b = rb_entry(node_b, struct annotated_data_type, node);
+
+	if (a->self.size != b->self.size)
+		return a->self.size < b->self.size;
+	return strcmp(a->self.type_name, b->self.type_name) < 0;
+}
+
+/* Recursively add new members for struct/union */
+static int __add_member_cb(Dwarf_Die *die, void *arg)
+{
+	struct annotated_member *parent = arg;
+	struct annotated_member *member;
+	Dwarf_Die member_type, die_mem;
+	Dwarf_Word size, loc;
+	Dwarf_Attribute attr;
+	struct strbuf sb;
+	int tag;
+
+	if (dwarf_tag(die) != DW_TAG_member)
+		return DIE_FIND_CB_SIBLING;
+
+	member = zalloc(sizeof(*member));
+	if (member == NULL)
+		return DIE_FIND_CB_END;
+
+	strbuf_init(&sb, 32);
+	die_get_typename(die, &sb);
+
+	die_get_real_type(die, &member_type);
+	if (dwarf_aggregate_size(&member_type, &size) < 0)
+		size = 0;
+
+	if (!dwarf_attr_integrate(die, DW_AT_data_member_location, &attr))
+		loc = 0;
+	else
+		dwarf_formudata(&attr, &loc);
+
+	member->type_name = strbuf_detach(&sb, NULL);
+	/* member->var_name can be NULL */
+	if (dwarf_diename(die))
+		member->var_name = strdup(dwarf_diename(die));
+	member->size = size;
+	member->offset = loc + parent->offset;
+	INIT_LIST_HEAD(&member->children);
+	list_add_tail(&member->node, &parent->children);
+
+	tag = dwarf_tag(&member_type);
+	switch (tag) {
+	case DW_TAG_structure_type:
+	case DW_TAG_union_type:
+		die_find_child(&member_type, __add_member_cb, member, &die_mem);
+		break;
+	default:
+		break;
+	}
+	return DIE_FIND_CB_SIBLING;
+}
+
+static void add_member_types(struct annotated_data_type *parent, Dwarf_Die *type)
+{
+	Dwarf_Die die_mem;
+
+	die_find_child(type, __add_member_cb, &parent->self, &die_mem);
+}
+
+static void delete_members(struct annotated_member *member)
+{
+	struct annotated_member *child, *tmp;
+
+	list_for_each_entry_safe(child, tmp, &member->children, node) {
+		list_del(&child->node);
+		delete_members(child);
+		free(child->type_name);
+		free(child->var_name);
+		free(child);
+	}
+}
+
+static struct annotated_data_type *dso__findnew_data_type(struct dso *dso,
+							  Dwarf_Die *type_die)
+{
+	struct annotated_data_type *result = NULL;
+	struct annotated_data_type key;
+	struct rb_node *node;
+	struct strbuf sb;
+	char *type_name;
+	Dwarf_Word size;
+
+	strbuf_init(&sb, 32);
+	if (die_get_typename_from_type(type_die, &sb) < 0)
+		strbuf_add(&sb, "(unknown type)", 14);
+	type_name = strbuf_detach(&sb, NULL);
+	dwarf_aggregate_size(type_die, &size);
+
+	/* Check existing nodes in dso->data_types tree */
+	key.self.type_name = type_name;
+	key.self.size = size;
+	node = rb_find(&key, &dso->data_types, data_type_cmp);
+	if (node) {
+		result = rb_entry(node, struct annotated_data_type, node);
+		free(type_name);
+		return result;
+	}
+
+	/* If not, add a new one */
+	result = zalloc(sizeof(*result));
+	if (result == NULL) {
+		free(type_name);
+		return NULL;
+	}
+
+	result->self.type_name = type_name;
+	result->self.size = size;
+	INIT_LIST_HEAD(&result->self.children);
+
+	if (symbol_conf.annotate_data_member)
+		add_member_types(result, type_die);
+
+	rb_add(&result->node, &dso->data_types, data_type_less);
+	return result;
+}
+
+static bool find_cu_die(struct debuginfo *di, u64 pc, Dwarf_Die *cu_die)
+{
+	Dwarf_Off off, next_off;
+	size_t header_size;
+
+	if (dwarf_addrdie(di->dbg, pc, cu_die) != NULL)
+		return cu_die;
+
+	/*
+	 * There are some kernels don't have full aranges and contain only a few
+	 * aranges entries.  Fallback to iterate all CU entries in .debug_info
+	 * in case it's missing.
+	 */
+	off = 0;
+	while (dwarf_nextcu(di->dbg, off, &next_off, &header_size,
+			    NULL, NULL, NULL) == 0) {
+		if (dwarf_offdie(di->dbg, off + header_size, cu_die) &&
+		    dwarf_haspc(cu_die, pc))
+			return true;
+
+		off = next_off;
+	}
+	return false;
+}
+
+/* The type info will be saved in @type_die */
+static int check_variable(Dwarf_Die *var_die, Dwarf_Die *type_die, int offset)
+{
+	Dwarf_Word size;
+
+	/* Get the type of the variable */
+	if (die_get_real_type(var_die, type_die) == NULL) {
+		pr_debug("variable has no type\n");
+		ann_data_stat.no_typeinfo++;
+		return -1;
+	}
+
+	/*
+	 * It expects a pointer type for a memory access.
+	 * Convert to a real type it points to.
+	 */
+	if (dwarf_tag(type_die) != DW_TAG_pointer_type ||
+	    die_get_real_type(type_die, type_die) == NULL) {
+		pr_debug("no pointer or no type\n");
+		ann_data_stat.no_typeinfo++;
+		return -1;
+	}
+
+	/* Get the size of the actual type */
+	if (dwarf_aggregate_size(type_die, &size) < 0) {
+		pr_debug("type size is unknown\n");
+		ann_data_stat.invalid_size++;
+		return -1;
+	}
+
+	/* Minimal sanity check */
+	if ((unsigned)offset >= size) {
+		pr_debug("offset: %d is bigger than size: %" PRIu64 "\n", offset, size);
+		ann_data_stat.bad_offset++;
+		return -1;
+	}
+
+	return 0;
+}
+
+/* The result will be saved in @type_die */
+static int find_data_type_die(struct debuginfo *di, u64 pc,
+			      int reg, int offset, Dwarf_Die *type_die)
+{
+	Dwarf_Die cu_die, var_die;
+	Dwarf_Die *scopes = NULL;
+	int ret = -1;
+	int i, nr_scopes;
+
+	/* Get a compile_unit for this address */
+	if (!find_cu_die(di, pc, &cu_die)) {
+		pr_debug("cannot find CU for address %" PRIx64 "\n", pc);
+		ann_data_stat.no_cuinfo++;
+		return -1;
+	}
+
+	/* Get a list of nested scopes - i.e. (inlined) functions and blocks. */
+	nr_scopes = die_get_scopes(&cu_die, pc, &scopes);
+
+	/* Search from the inner-most scope to the outer */
+	for (i = nr_scopes - 1; i >= 0; i--) {
+		/* Look up variables/parameters in this scope */
+		if (!die_find_variable_by_reg(&scopes[i], pc, reg, &var_die))
+			continue;
+
+		/* Found a variable, see if it's correct */
+		ret = check_variable(&var_die, type_die, offset);
+		goto out;
+	}
+	if (ret < 0)
+		ann_data_stat.no_var++;
+
+out:
+	free(scopes);
+	return ret;
+}
+
+/**
+ * find_data_type - Return a data type at the location
+ * @ms: map and symbol at the location
+ * @ip: instruction address of the memory access
+ * @reg: register that holds the base address
+ * @offset: offset from the base address
+ *
+ * This functions searches the debug information of the binary to get the data
+ * type it accesses.  The exact location is expressed by (ip, reg, offset).
+ * It return %NULL if not found.
+ */
+struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
+					   int reg, int offset)
+{
+	struct annotated_data_type *result = NULL;
+	struct dso *dso = map__dso(ms->map);
+	struct debuginfo *di;
+	Dwarf_Die type_die;
+	u64 pc;
+
+	di = debuginfo__new(dso->long_name);
+	if (di == NULL) {
+		pr_debug("cannot get the debug info\n");
+		return NULL;
+	}
+
+	/*
+	 * IP is a relative instruction address from the start of the map, as
+	 * it can be randomized/relocated, it needs to translate to PC which is
+	 * a file address for DWARF processing.
+	 */
+	pc = map__rip_2objdump(ms->map, ip);
+	if (find_data_type_die(di, pc, reg, offset, &type_die) < 0)
+		goto out;
+
+	result = dso__findnew_data_type(dso, &type_die);
+
+out:
+	debuginfo__delete(di);
+	return result;
+}
+
+static int alloc_data_type_histograms(struct annotated_data_type *adt, int nr_entries)
+{
+	int i;
+	size_t sz = sizeof(struct type_hist);
+
+	sz += sizeof(struct type_hist_entry) * adt->self.size;
+
+	/* Allocate a table of pointers for each event */
+	adt->nr_histograms = nr_entries;
+	adt->histograms = calloc(nr_entries, sizeof(*adt->histograms));
+	if (adt->histograms == NULL)
+		return -ENOMEM;
+
+	/*
+	 * Each histogram is allocated for the whole size of the type.
+	 * TODO: Probably we can move the histogram to members.
+	 */
+	for (i = 0; i < nr_entries; i++) {
+		adt->histograms[i] = zalloc(sz);
+		if (adt->histograms[i] == NULL)
+			goto err;
+	}
+	return 0;
+
+err:
+	while (--i >= 0)
+		free(adt->histograms[i]);
+	free(adt->histograms);
+	return -ENOMEM;
+}
+
+static void delete_data_type_histograms(struct annotated_data_type *adt)
+{
+	for (int i = 0; i < adt->nr_histograms; i++)
+		free(adt->histograms[i]);
+	free(adt->histograms);
+}
+
+void annotated_data_type__tree_delete(struct rb_root *root)
+{
+	struct annotated_data_type *pos;
+
+	while (!RB_EMPTY_ROOT(root)) {
+		struct rb_node *node = rb_first(root);
+
+		rb_erase(node, root);
+		pos = rb_entry(node, struct annotated_data_type, node);
+		delete_members(&pos->self);
+		delete_data_type_histograms(pos);
+		free(pos->self.type_name);
+		free(pos);
+	}
+}
+
+/**
+ * annotated_data_type__update_samples - Update histogram
+ * @adt: Data type to update
+ * @evsel: Event to update
+ * @offset: Offset in the type
+ * @nr_samples: Number of samples at this offset
+ * @period: Event count at this offset
+ *
+ * This function updates type histogram at @ofs for @evsel.  Samples are
+ * aggregated before calling this function so it can be called with more
+ * than one samples at a certain offset.
+ */
+int annotated_data_type__update_samples(struct annotated_data_type *adt,
+					struct evsel *evsel, int offset,
+					int nr_samples, u64 period)
+{
+	struct type_hist *h;
+
+	if (adt == NULL)
+		return 0;
+
+	if (adt->histograms == NULL) {
+		int nr = evsel->evlist->core.nr_entries;
+
+		if (alloc_data_type_histograms(adt, nr) < 0)
+			return -1;
+	}
+
+	if (offset < 0 || offset >= adt->self.size)
+		return -1;
+
+	h = adt->histograms[evsel->core.idx];
+
+	h->nr_samples += nr_samples;
+	h->addr[offset].nr_samples += nr_samples;
+	h->period += period;
+	h->addr[offset].period += period;
+	return 0;
+}
diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h
new file mode 100644
index 000000000000..8e73096c01d1
--- /dev/null
+++ b/tools/perf/util/annotate-data.h
@@ -0,0 +1,143 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _PERF_ANNOTATE_DATA_H
+#define _PERF_ANNOTATE_DATA_H
+
+#include <errno.h>
+#include <linux/compiler.h>
+#include <linux/rbtree.h>
+#include <linux/types.h>
+
+struct evsel;
+struct map_symbol;
+
+/**
+ * struct annotated_member - Type of member field
+ * @node: List entry in the parent list
+ * @children: List head for child nodes
+ * @type_name: Name of the member type
+ * @var_name: Name of the member variable
+ * @offset: Offset from the outer data type
+ * @size: Size of the member field
+ *
+ * This represents a member type in a data type.
+ */
+struct annotated_member {
+	struct list_head node;
+	struct list_head children;
+	char *type_name;
+	char *var_name;
+	int offset;
+	int size;
+};
+
+/**
+ * struct type_hist_entry - Histogram entry per offset
+ * @nr_samples: Number of samples
+ * @period: Count of event
+ */
+struct type_hist_entry {
+	int nr_samples;
+	u64 period;
+};
+
+/**
+ * struct type_hist - Type histogram for each event
+ * @nr_samples: Total number of samples in this data type
+ * @period: Total count of the event in this data type
+ * @offset: Array of histogram entry
+ */
+struct type_hist {
+	u64			nr_samples;
+	u64			period;
+	struct type_hist_entry	addr[];
+};
+
+/**
+ * struct annotated_data_type - Data type to profile
+ * @node: RB-tree node for dso->type_tree
+ * @self: Actual type information
+ * @nr_histogram: Number of histogram entries
+ * @histograms: An array of pointers to histograms
+ *
+ * This represents a data type accessed by samples in the profile data.
+ */
+struct annotated_data_type {
+	struct rb_node node;
+	struct annotated_member self;
+	int nr_histograms;
+	struct type_hist **histograms;
+};
+
+extern struct annotated_data_type unknown_type;
+
+/**
+ * struct annotated_data_stat - Debug statistics
+ * @total: Total number of entry
+ * @no_sym: No symbol or map found
+ * @no_insn: Failed to get disasm line
+ * @no_insn_ops: The instruction has no operands
+ * @no_mem_ops: The instruction has no memory operands
+ * @no_reg: Failed to extract a register from the operand
+ * @no_dbginfo: The binary has no debug information
+ * @no_cuinfo: Failed to find a compile_unit
+ * @no_var: Failed to find a matching variable
+ * @no_typeinfo: Failed to get a type info for the variable
+ * @invalid_size: Failed to get a size info of the type
+ * @bad_offset: The access offset is out of the type
+ */
+struct annotated_data_stat {
+	int total;
+	int no_sym;
+	int no_insn;
+	int no_insn_ops;
+	int no_mem_ops;
+	int no_reg;
+	int no_dbginfo;
+	int no_cuinfo;
+	int no_var;
+	int no_typeinfo;
+	int invalid_size;
+	int bad_offset;
+};
+extern struct annotated_data_stat ann_data_stat;
+
+#ifdef HAVE_DWARF_SUPPORT
+
+/* Returns data type at the location (ip, reg, offset) */
+struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
+					   int reg, int offset);
+
+/* Update type access histogram at the given offset */
+int annotated_data_type__update_samples(struct annotated_data_type *adt,
+					struct evsel *evsel, int offset,
+					int nr_samples, u64 period);
+
+/* Release all data type information in the tree */
+void annotated_data_type__tree_delete(struct rb_root *root);
+
+#else /* HAVE_DWARF_SUPPORT */
+
+static inline struct annotated_data_type *
+find_data_type(struct map_symbol *ms __maybe_unused, u64 ip __maybe_unused,
+	       int reg __maybe_unused, int offset __maybe_unused)
+{
+	return NULL;
+}
+
+static inline int
+annotated_data_type__update_samples(struct annotated_data_type *adt __maybe_unused,
+				    struct evsel *evsel __maybe_unused,
+				    int offset __maybe_unused,
+				    int nr_samples __maybe_unused,
+				    u64 period __maybe_unused)
+{
+	return -1;
+}
+
+static inline void annotated_data_type__tree_delete(struct rb_root *root __maybe_unused)
+{
+}
+
+#endif /* HAVE_DWARF_SUPPORT */
+
+#endif /* _PERF_ANNOTATE_DATA_H */
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 82956adf9963..9b70ab110ce7 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -25,12 +25,14 @@
 #include "units.h"
 #include "debug.h"
 #include "annotate.h"
+#include "annotate-data.h"
 #include "evsel.h"
 #include "evlist.h"
 #include "bpf-event.h"
 #include "bpf-utils.h"
 #include "block-range.h"
 #include "string2.h"
+#include "dwarf-regs.h"
 #include "util/event.h"
 #include "util/sharded_mutex.h"
 #include "arch/common.h"
@@ -57,6 +59,9 @@
 
 #include <linux/ctype.h>
 
+/* global annotation options */
+struct annotation_options annotate_opts;
+
 static regex_t	 file_lineno;
 
 static struct ins_ops *ins__find(struct arch *arch, const char *name);
@@ -85,6 +90,8 @@ struct arch {
 	struct		{
 		char comment_char;
 		char skip_functions_char;
+		char register_char;
+		char memory_ref_char;
 	} objdump;
 };
 
@@ -96,6 +103,10 @@ static struct ins_ops nop_ops;
 static struct ins_ops lock_ops;
 static struct ins_ops ret_ops;
 
+/* Data type collection debug statistics */
+struct annotated_data_stat ann_data_stat;
+LIST_HEAD(ann_insn_stat);
+
 static int arch__grow_instructions(struct arch *arch)
 {
 	struct ins *new_instructions;
@@ -188,6 +199,8 @@ static struct arch architectures[] = {
 		.insn_suffix = "bwlq",
 		.objdump =  {
 			.comment_char = '#',
+			.register_char = '%',
+			.memory_ref_char = '(',
 		},
 	},
 	{
@@ -340,10 +353,10 @@ bool ins__is_call(const struct ins *ins)
  */
 static inline const char *validate_comma(const char *c, struct ins_operands *ops)
 {
-	if (ops->raw_comment && c > ops->raw_comment)
+	if (ops->jump.raw_comment && c > ops->jump.raw_comment)
 		return NULL;
 
-	if (ops->raw_func_start && c > ops->raw_func_start)
+	if (ops->jump.raw_func_start && c > ops->jump.raw_func_start)
 		return NULL;
 
 	return c;
@@ -359,8 +372,8 @@ static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_s
 	const char *c = strchr(ops->raw, ',');
 	u64 start, end;
 
-	ops->raw_comment = strchr(ops->raw, arch->objdump.comment_char);
-	ops->raw_func_start = strchr(ops->raw, '<');
+	ops->jump.raw_comment = strchr(ops->raw, arch->objdump.comment_char);
+	ops->jump.raw_func_start = strchr(ops->raw, '<');
 
 	c = validate_comma(c, ops);
 
@@ -462,7 +475,16 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 			 ops->target.offset);
 }
 
+static void jump__delete(struct ins_operands *ops __maybe_unused)
+{
+	/*
+	 * The ops->jump.raw_comment and ops->jump.raw_func_start belong to the
+	 * raw string, don't free them.
+	 */
+}
+
 static struct ins_ops jump_ops = {
+	.free	   = jump__delete,
 	.parse	   = jump__parse,
 	.scnprintf = jump__scnprintf,
 };
@@ -557,6 +579,34 @@ static struct ins_ops lock_ops = {
 	.scnprintf = lock__scnprintf,
 };
 
+/*
+ * Check if the operand has more than one registers like x86 SIB addressing:
+ *   0x1234(%rax, %rbx, 8)
+ *
+ * But it doesn't care segment selectors like %gs:0x5678(%rcx), so just check
+ * the input string after 'memory_ref_char' if exists.
+ */
+static bool check_multi_regs(struct arch *arch, const char *op)
+{
+	int count = 0;
+
+	if (arch->objdump.register_char == 0)
+		return false;
+
+	if (arch->objdump.memory_ref_char) {
+		op = strchr(op, arch->objdump.memory_ref_char);
+		if (op == NULL)
+			return false;
+	}
+
+	while ((op = strchr(op, arch->objdump.register_char)) != NULL) {
+		count++;
+		op++;
+	}
+
+	return count > 1;
+}
+
 static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms __maybe_unused)
 {
 	char *s = strchr(ops->raw, ','), *target, *comment, prev;
@@ -584,6 +634,8 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_sy
 	if (ops->source.raw == NULL)
 		return -1;
 
+	ops->source.multi_regs = check_multi_regs(arch, ops->source.raw);
+
 	target = skip_spaces(++s);
 	comment = strchr(s, arch->objdump.comment_char);
 
@@ -604,6 +656,8 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_sy
 	if (ops->target.raw == NULL)
 		goto out_free_source;
 
+	ops->target.multi_regs = check_multi_regs(arch, ops->target.raw);
+
 	if (comment == NULL)
 		return 0;
 
@@ -795,6 +849,11 @@ static struct arch *arch__find(const char *name)
 	return bsearch(name, architectures, nmemb, sizeof(struct arch), arch__key_cmp);
 }
 
+bool arch__is(struct arch *arch, const char *name)
+{
+	return !strcmp(arch->name, name);
+}
+
 static struct annotated_source *annotated_source__new(void)
 {
 	struct annotated_source *src = zalloc(sizeof(*src));
@@ -810,7 +869,6 @@ static __maybe_unused void annotated_source__delete(struct annotated_source *src
 	if (src == NULL)
 		return;
 	zfree(&src->histograms);
-	zfree(&src->cycles_hist);
 	free(src);
 }
 
@@ -845,18 +903,6 @@ static int annotated_source__alloc_histograms(struct annotated_source *src,
 	return src->histograms ? 0 : -1;
 }
 
-/* The cycles histogram is lazily allocated. */
-static int symbol__alloc_hist_cycles(struct symbol *sym)
-{
-	struct annotation *notes = symbol__annotation(sym);
-	const size_t size = symbol__size(sym);
-
-	notes->src->cycles_hist = calloc(size, sizeof(struct cyc_hist));
-	if (notes->src->cycles_hist == NULL)
-		return -1;
-	return 0;
-}
-
 void symbol__annotate_zero_histograms(struct symbol *sym)
 {
 	struct annotation *notes = symbol__annotation(sym);
@@ -865,9 +911,10 @@ void symbol__annotate_zero_histograms(struct symbol *sym)
 	if (notes->src != NULL) {
 		memset(notes->src->histograms, 0,
 		       notes->src->nr_histograms * notes->src->sizeof_sym_hist);
-		if (notes->src->cycles_hist)
-			memset(notes->src->cycles_hist, 0,
-				symbol__size(sym) * sizeof(struct cyc_hist));
+	}
+	if (notes->branch && notes->branch->cycles_hist) {
+		memset(notes->branch->cycles_hist, 0,
+		       symbol__size(sym) * sizeof(struct cyc_hist));
 	}
 	annotation__unlock(notes);
 }
@@ -958,23 +1005,33 @@ static int __symbol__inc_addr_samples(struct map_symbol *ms,
 	return 0;
 }
 
+struct annotated_branch *annotation__get_branch(struct annotation *notes)
+{
+	if (notes == NULL)
+		return NULL;
+
+	if (notes->branch == NULL)
+		notes->branch = zalloc(sizeof(*notes->branch));
+
+	return notes->branch;
+}
+
 static struct cyc_hist *symbol__cycles_hist(struct symbol *sym)
 {
 	struct annotation *notes = symbol__annotation(sym);
+	struct annotated_branch *branch;
 
-	if (notes->src == NULL) {
-		notes->src = annotated_source__new();
-		if (notes->src == NULL)
-			return NULL;
-		goto alloc_cycles_hist;
-	}
+	branch = annotation__get_branch(notes);
+	if (branch == NULL)
+		return NULL;
+
+	if (branch->cycles_hist == NULL) {
+		const size_t size = symbol__size(sym);
 
-	if (!notes->src->cycles_hist) {
-alloc_cycles_hist:
-		symbol__alloc_hist_cycles(sym);
+		branch->cycles_hist = calloc(size, sizeof(struct cyc_hist));
 	}
 
-	return notes->src->cycles_hist;
+	return branch->cycles_hist;
 }
 
 struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists)
@@ -1077,12 +1134,20 @@ static unsigned annotation__count_insn(struct annotation *notes, u64 start, u64
 	u64 offset;
 
 	for (offset = start; offset <= end; offset++) {
-		if (notes->offsets[offset])
+		if (notes->src->offsets[offset])
 			n_insn++;
 	}
 	return n_insn;
 }
 
+static void annotated_branch__delete(struct annotated_branch *branch)
+{
+	if (branch) {
+		zfree(&branch->cycles_hist);
+		free(branch);
+	}
+}
+
 static void annotation__count_and_fill(struct annotation *notes, u64 start, u64 end, struct cyc_hist *ch)
 {
 	unsigned n_insn;
@@ -1091,6 +1156,7 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64
 
 	n_insn = annotation__count_insn(notes, start, end);
 	if (n_insn && ch->num && ch->cycles) {
+		struct annotated_branch *branch;
 		float ipc = n_insn / ((double)ch->cycles / (double)ch->num);
 
 		/* Hide data when there are too many overlaps. */
@@ -1098,54 +1164,76 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64
 			return;
 
 		for (offset = start; offset <= end; offset++) {
-			struct annotation_line *al = notes->offsets[offset];
+			struct annotation_line *al = notes->src->offsets[offset];
 
-			if (al && al->ipc == 0.0) {
-				al->ipc = ipc;
+			if (al && al->cycles && al->cycles->ipc == 0.0) {
+				al->cycles->ipc = ipc;
 				cover_insn++;
 			}
 		}
 
-		if (cover_insn) {
-			notes->hit_cycles += ch->cycles;
-			notes->hit_insn += n_insn * ch->num;
-			notes->cover_insn += cover_insn;
+		branch = annotation__get_branch(notes);
+		if (cover_insn && branch) {
+			branch->hit_cycles += ch->cycles;
+			branch->hit_insn += n_insn * ch->num;
+			branch->cover_insn += cover_insn;
 		}
 	}
 }
 
-void annotation__compute_ipc(struct annotation *notes, size_t size)
+static int annotation__compute_ipc(struct annotation *notes, size_t size)
 {
+	int err = 0;
 	s64 offset;
 
-	if (!notes->src || !notes->src->cycles_hist)
-		return;
+	if (!notes->branch || !notes->branch->cycles_hist)
+		return 0;
 
-	notes->total_insn = annotation__count_insn(notes, 0, size - 1);
-	notes->hit_cycles = 0;
-	notes->hit_insn = 0;
-	notes->cover_insn = 0;
+	notes->branch->total_insn = annotation__count_insn(notes, 0, size - 1);
+	notes->branch->hit_cycles = 0;
+	notes->branch->hit_insn = 0;
+	notes->branch->cover_insn = 0;
 
 	annotation__lock(notes);
 	for (offset = size - 1; offset >= 0; --offset) {
 		struct cyc_hist *ch;
 
-		ch = &notes->src->cycles_hist[offset];
+		ch = &notes->branch->cycles_hist[offset];
 		if (ch && ch->cycles) {
 			struct annotation_line *al;
 
+			al = notes->src->offsets[offset];
+			if (al && al->cycles == NULL) {
+				al->cycles = zalloc(sizeof(*al->cycles));
+				if (al->cycles == NULL) {
+					err = ENOMEM;
+					break;
+				}
+			}
 			if (ch->have_start)
 				annotation__count_and_fill(notes, ch->start, offset, ch);
-			al = notes->offsets[offset];
 			if (al && ch->num_aggr) {
-				al->cycles = ch->cycles_aggr / ch->num_aggr;
-				al->cycles_max = ch->cycles_max;
-				al->cycles_min = ch->cycles_min;
+				al->cycles->avg = ch->cycles_aggr / ch->num_aggr;
+				al->cycles->max = ch->cycles_max;
+				al->cycles->min = ch->cycles_min;
+			}
+		}
+	}
+
+	if (err) {
+		while (++offset < (s64)size) {
+			struct cyc_hist *ch = &notes->branch->cycles_hist[offset];
+
+			if (ch && ch->cycles) {
+				struct annotation_line *al = notes->src->offsets[offset];
+				if (al)
+					zfree(&al->cycles);
 			}
-			notes->have_cycles = true;
 		}
 	}
+
 	annotation__unlock(notes);
+	return 0;
 }
 
 int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample,
@@ -1225,6 +1313,7 @@ static void annotation_line__exit(struct annotation_line *al)
 {
 	zfree_srcline(&al->path);
 	zfree(&al->line);
+	zfree(&al->cycles);
 }
 
 static size_t disasm_line_size(int nr)
@@ -1299,6 +1388,7 @@ int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool r
 void annotation__exit(struct annotation *notes)
 {
 	annotated_source__delete(notes->src);
+	annotated_branch__delete(notes->branch);
 }
 
 static struct sharded_mutex *sharded_mutex;
@@ -1817,7 +1907,6 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 				   struct annotate_args *args)
 {
 	struct annotation *notes = symbol__annotation(sym);
-	struct annotation_options *opts = args->options;
 	struct bpf_prog_linfo *prog_linfo = NULL;
 	struct bpf_prog_info_node *info_node;
 	int len = sym->end - sym->start;
@@ -1927,7 +2016,7 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 		prev_buf_size = buf_size;
 		fflush(s);
 
-		if (!opts->hide_src_code && srcline) {
+		if (!annotate_opts.hide_src_code && srcline) {
 			args->offset = -1;
 			args->line = strdup(srcline);
 			args->line_nr = 0;
@@ -2050,7 +2139,7 @@ static char *expand_tabs(char *line, char **storage, size_t *storage_len)
 
 static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 {
-	struct annotation_options *opts = args->options;
+	struct annotation_options *opts = &annotate_opts;
 	struct map *map = args->ms.map;
 	struct dso *dso = map__dso(map);
 	char *command;
@@ -2113,12 +2202,13 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 	err = asprintf(&command,
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
-		 " -l -d %s %s %s %c%s%c %s%s -C \"$1\"",
+		 " %s -d %s %s %s %c%s%c %s%s -C \"$1\"",
 		 opts->objdump_path ?: "objdump",
 		 opts->disassembler_style ? "-M " : "",
 		 opts->disassembler_style ?: "",
 		 map__rip_2objdump(map, sym->start),
 		 map__rip_2objdump(map, sym->end),
+		 opts->show_linenr ? "-l" : "",
 		 opts->show_asm_raw ? "" : "--no-show-raw-insn",
 		 opts->annotate_src ? "-S" : "",
 		 opts->prefix ? "--prefix " : "",
@@ -2299,15 +2389,8 @@ void symbol__calc_percent(struct symbol *sym, struct evsel *evsel)
 	annotation__calc_percent(notes, evsel, symbol__size(sym));
 }
 
-int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
-		     struct annotation_options *options, struct arch **parch)
+static int evsel__get_arch(struct evsel *evsel, struct arch **parch)
 {
-	struct symbol *sym = ms->sym;
-	struct annotation *notes = symbol__annotation(sym);
-	struct annotate_args args = {
-		.evsel		= evsel,
-		.options	= options,
-	};
 	struct perf_env *env = evsel__env(evsel);
 	const char *arch_name = perf_env__arch(env);
 	struct arch *arch;
@@ -2316,25 +2399,45 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
 	if (!arch_name)
 		return errno;
 
-	args.arch = arch = arch__find(arch_name);
+	*parch = arch = arch__find(arch_name);
 	if (arch == NULL) {
 		pr_err("%s: unsupported arch %s\n", __func__, arch_name);
 		return ENOTSUP;
 	}
 
-	if (parch)
-		*parch = arch;
-
 	if (arch->init) {
 		err = arch->init(arch, env ? env->cpuid : NULL);
 		if (err) {
-			pr_err("%s: failed to initialize %s arch priv area\n", __func__, arch->name);
+			pr_err("%s: failed to initialize %s arch priv area\n",
+			       __func__, arch->name);
 			return err;
 		}
 	}
+	return 0;
+}
 
+int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
+		     struct arch **parch)
+{
+	struct symbol *sym = ms->sym;
+	struct annotation *notes = symbol__annotation(sym);
+	struct annotate_args args = {
+		.evsel		= evsel,
+		.options	= &annotate_opts,
+	};
+	struct arch *arch = NULL;
+	int err;
+
+	err = evsel__get_arch(evsel, &arch);
+	if (err < 0)
+		return err;
+
+	if (parch)
+		*parch = arch;
+
+	args.arch = arch;
 	args.ms = *ms;
-	if (notes->options && notes->options->full_addr)
+	if (annotate_opts.full_addr)
 		notes->start = map__objdump_2mem(ms->map, ms->sym->start);
 	else
 		notes->start = map__rip_2objdump(ms->map, ms->sym->start);
@@ -2342,12 +2445,12 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
 	return symbol__disassemble(sym, &args);
 }
 
-static void insert_source_line(struct rb_root *root, struct annotation_line *al,
-			       struct annotation_options *opts)
+static void insert_source_line(struct rb_root *root, struct annotation_line *al)
 {
 	struct annotation_line *iter;
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
+	unsigned int percent_type = annotate_opts.percent_type;
 	int i, ret;
 
 	while (*p != NULL) {
@@ -2358,7 +2461,7 @@ static void insert_source_line(struct rb_root *root, struct annotation_line *al,
 		if (ret == 0) {
 			for (i = 0; i < al->data_nr; i++) {
 				iter->data[i].percent_sum += annotation_data__percent(&al->data[i],
-										      opts->percent_type);
+										      percent_type);
 			}
 			return;
 		}
@@ -2371,7 +2474,7 @@ static void insert_source_line(struct rb_root *root, struct annotation_line *al,
 
 	for (i = 0; i < al->data_nr; i++) {
 		al->data[i].percent_sum = annotation_data__percent(&al->data[i],
-								   opts->percent_type);
+								   percent_type);
 	}
 
 	rb_link_node(&al->rb_node, parent, p);
@@ -2493,8 +2596,7 @@ static int annotated_source__addr_fmt_width(struct list_head *lines, u64 start)
 	return 0;
 }
 
-int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel,
-			    struct annotation_options *opts)
+int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel)
 {
 	struct map *map = ms->map;
 	struct symbol *sym = ms->sym;
@@ -2505,6 +2607,7 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel,
 	struct annotation *notes = symbol__annotation(sym);
 	struct sym_hist *h = annotation__histogram(notes, evsel->core.idx);
 	struct annotation_line *pos, *queue = NULL;
+	struct annotation_options *opts = &annotate_opts;
 	u64 start = map__rip_2objdump(map, sym->start);
 	int printed = 2, queue_len = 0, addr_fmt_width;
 	int more = 0;
@@ -2633,8 +2736,7 @@ static void FILE__write_graph(void *fp, int graph)
 	fputs(s, fp);
 }
 
-static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp,
-				     struct annotation_options *opts)
+static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp)
 {
 	struct annotation *notes = symbol__annotation(sym);
 	struct annotation_write_ops wops = {
@@ -2649,9 +2751,9 @@ static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp,
 	struct annotation_line *al;
 
 	list_for_each_entry(al, &notes->src->source, node) {
-		if (annotation_line__filter(al, notes))
+		if (annotation_line__filter(al))
 			continue;
-		annotation_line__write(al, notes, &wops, opts);
+		annotation_line__write(al, notes, &wops);
 		fputc('\n', fp);
 		wops.first_line = false;
 	}
@@ -2659,8 +2761,7 @@ static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp,
 	return 0;
 }
 
-int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel,
-				struct annotation_options *opts)
+int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel)
 {
 	const char *ev_name = evsel__name(evsel);
 	char buf[1024];
@@ -2682,7 +2783,7 @@ int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel,
 
 	fprintf(fp, "%s() %s\nEvent: %s\n\n",
 		ms->sym->name, map__dso(ms->map)->long_name, ev_name);
-	symbol__annotate_fprintf2(ms->sym, fp, opts);
+	symbol__annotate_fprintf2(ms->sym, fp);
 
 	fclose(fp);
 	err = 0;
@@ -2769,7 +2870,7 @@ void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym)
 		return;
 
 	for (offset = 0; offset < size; ++offset) {
-		struct annotation_line *al = notes->offsets[offset];
+		struct annotation_line *al = notes->src->offsets[offset];
 		struct disasm_line *dl;
 
 		dl = disasm_line(al);
@@ -2777,7 +2878,7 @@ void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym)
 		if (!disasm_line__is_valid_local_jump(dl, sym))
 			continue;
 
-		al = notes->offsets[dl->ops.target.offset];
+		al = notes->src->offsets[dl->ops.target.offset];
 
 		/*
 		 * FIXME: Oops, no jump target? Buggy disassembler? Or do we
@@ -2794,19 +2895,20 @@ void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym)
 void annotation__set_offsets(struct annotation *notes, s64 size)
 {
 	struct annotation_line *al;
+	struct annotated_source *src = notes->src;
 
-	notes->max_line_len = 0;
-	notes->nr_entries = 0;
-	notes->nr_asm_entries = 0;
+	src->max_line_len = 0;
+	src->nr_entries = 0;
+	src->nr_asm_entries = 0;
 
-	list_for_each_entry(al, &notes->src->source, node) {
+	list_for_each_entry(al, &src->source, node) {
 		size_t line_len = strlen(al->line);
 
-		if (notes->max_line_len < line_len)
-			notes->max_line_len = line_len;
-		al->idx = notes->nr_entries++;
+		if (src->max_line_len < line_len)
+			src->max_line_len = line_len;
+		al->idx = src->nr_entries++;
 		if (al->offset != -1) {
-			al->idx_asm = notes->nr_asm_entries++;
+			al->idx_asm = src->nr_asm_entries++;
 			/*
 			 * FIXME: short term bandaid to cope with assembly
 			 * routines that comes with labels in the same column
@@ -2815,7 +2917,7 @@ void annotation__set_offsets(struct annotation *notes, s64 size)
 			 * E.g. copy_user_generic_unrolled
  			 */
 			if (al->offset < size)
-				notes->offsets[al->offset] = al;
+				notes->src->offsets[al->offset] = al;
 		} else
 			al->idx_asm = -1;
 	}
@@ -2858,24 +2960,24 @@ void annotation__init_column_widths(struct annotation *notes, struct symbol *sym
 
 void annotation__update_column_widths(struct annotation *notes)
 {
-	if (notes->options->use_offset)
+	if (annotate_opts.use_offset)
 		notes->widths.target = notes->widths.min_addr;
-	else if (notes->options->full_addr)
+	else if (annotate_opts.full_addr)
 		notes->widths.target = BITS_PER_LONG / 4;
 	else
 		notes->widths.target = notes->widths.max_addr;
 
 	notes->widths.addr = notes->widths.target;
 
-	if (notes->options->show_nr_jumps)
+	if (annotate_opts.show_nr_jumps)
 		notes->widths.addr += notes->widths.jumps + 1;
 }
 
 void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *ms)
 {
-	notes->options->full_addr = !notes->options->full_addr;
+	annotate_opts.full_addr = !annotate_opts.full_addr;
 
-	if (notes->options->full_addr)
+	if (annotate_opts.full_addr)
 		notes->start = map__objdump_2mem(ms->map, ms->sym->start);
 	else
 		notes->start = map__rip_2objdump(ms->map, ms->sym->start);
@@ -2884,8 +2986,7 @@ void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *m
 }
 
 static void annotation__calc_lines(struct annotation *notes, struct map *map,
-				   struct rb_root *root,
-				   struct annotation_options *opts)
+				   struct rb_root *root)
 {
 	struct annotation_line *al;
 	struct rb_root tmp_root = RB_ROOT;
@@ -2898,7 +2999,7 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map,
 			double percent;
 
 			percent = annotation_data__percent(&al->data[i],
-							   opts->percent_type);
+							   annotate_opts.percent_type);
 
 			if (percent > percent_max)
 				percent_max = percent;
@@ -2909,22 +3010,20 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map,
 
 		al->path = get_srcline(map__dso(map), notes->start + al->offset, NULL,
 				       false, true, notes->start + al->offset);
-		insert_source_line(&tmp_root, al, opts);
+		insert_source_line(&tmp_root, al);
 	}
 
 	resort_source_line(root, &tmp_root);
 }
 
-static void symbol__calc_lines(struct map_symbol *ms, struct rb_root *root,
-			       struct annotation_options *opts)
+static void symbol__calc_lines(struct map_symbol *ms, struct rb_root *root)
 {
 	struct annotation *notes = symbol__annotation(ms->sym);
 
-	annotation__calc_lines(notes, ms->map, root, opts);
+	annotation__calc_lines(notes, ms->map, root);
 }
 
-int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel,
-			  struct annotation_options *opts)
+int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel)
 {
 	struct dso *dso = map__dso(ms->map);
 	struct symbol *sym = ms->sym;
@@ -2933,7 +3032,7 @@ int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel,
 	char buf[1024];
 	int err;
 
-	err = symbol__annotate2(ms, evsel, opts, NULL);
+	err = symbol__annotate2(ms, evsel, NULL);
 	if (err) {
 		char msg[BUFSIZ];
 
@@ -2943,31 +3042,31 @@ int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel,
 		return -1;
 	}
 
-	if (opts->print_lines) {
-		srcline_full_filename = opts->full_path;
-		symbol__calc_lines(ms, &source_line, opts);
+	if (annotate_opts.print_lines) {
+		srcline_full_filename = annotate_opts.full_path;
+		symbol__calc_lines(ms, &source_line);
 		print_summary(&source_line, dso->long_name);
 	}
 
 	hists__scnprintf_title(hists, buf, sizeof(buf));
 	fprintf(stdout, "%s, [percent: %s]\n%s() %s\n",
-		buf, percent_type_str(opts->percent_type), sym->name, dso->long_name);
-	symbol__annotate_fprintf2(sym, stdout, opts);
+		buf, percent_type_str(annotate_opts.percent_type), sym->name,
+		dso->long_name);
+	symbol__annotate_fprintf2(sym, stdout);
 
 	annotated_source__purge(symbol__annotation(sym)->src);
 
 	return 0;
 }
 
-int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel,
-			 struct annotation_options *opts)
+int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel)
 {
 	struct dso *dso = map__dso(ms->map);
 	struct symbol *sym = ms->sym;
 	struct rb_root source_line = RB_ROOT;
 	int err;
 
-	err = symbol__annotate(ms, evsel, opts, NULL);
+	err = symbol__annotate(ms, evsel, NULL);
 	if (err) {
 		char msg[BUFSIZ];
 
@@ -2979,13 +3078,13 @@ int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel,
 
 	symbol__calc_percent(sym, evsel);
 
-	if (opts->print_lines) {
-		srcline_full_filename = opts->full_path;
-		symbol__calc_lines(ms, &source_line, opts);
+	if (annotate_opts.print_lines) {
+		srcline_full_filename = annotate_opts.full_path;
+		symbol__calc_lines(ms, &source_line);
 		print_summary(&source_line, dso->long_name);
 	}
 
-	symbol__annotate_printf(ms, evsel, opts);
+	symbol__annotate_printf(ms, evsel);
 
 	annotated_source__purge(symbol__annotation(sym)->src);
 
@@ -3046,19 +3145,20 @@ call_like:
 		obj__printf(obj, "  ");
 	}
 
-	disasm_line__scnprintf(dl, bf, size, !notes->options->use_offset, notes->widths.max_ins_name);
+	disasm_line__scnprintf(dl, bf, size, !annotate_opts.use_offset, notes->widths.max_ins_name);
 }
 
 static void ipc_coverage_string(char *bf, int size, struct annotation *notes)
 {
 	double ipc = 0.0, coverage = 0.0;
+	struct annotated_branch *branch = annotation__get_branch(notes);
 
-	if (notes->hit_cycles)
-		ipc = notes->hit_insn / ((double)notes->hit_cycles);
+	if (branch && branch->hit_cycles)
+		ipc = branch->hit_insn / ((double)branch->hit_cycles);
 
-	if (notes->total_insn) {
-		coverage = notes->cover_insn * 100.0 /
-			((double)notes->total_insn);
+	if (branch && branch->total_insn) {
+		coverage = branch->cover_insn * 100.0 /
+			((double)branch->total_insn);
 	}
 
 	scnprintf(bf, size, "(Average IPC: %.2f, IPC Coverage: %.1f%%)",
@@ -3083,8 +3183,8 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 	int printed;
 
 	if (first_line && (al->offset == -1 || percent_max == 0.0)) {
-		if (notes->have_cycles) {
-			if (al->ipc == 0.0 && al->cycles == 0)
+		if (notes->branch && al->cycles) {
+			if (al->cycles->ipc == 0.0 && al->cycles->avg == 0)
 				show_title = true;
 		} else
 			show_title = true;
@@ -3120,18 +3220,18 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 		}
 	}
 
-	if (notes->have_cycles) {
-		if (al->ipc)
-			obj__printf(obj, "%*.2f ", ANNOTATION__IPC_WIDTH - 1, al->ipc);
+	if (notes->branch) {
+		if (al->cycles && al->cycles->ipc)
+			obj__printf(obj, "%*.2f ", ANNOTATION__IPC_WIDTH - 1, al->cycles->ipc);
 		else if (!show_title)
 			obj__printf(obj, "%*s", ANNOTATION__IPC_WIDTH, " ");
 		else
 			obj__printf(obj, "%*s ", ANNOTATION__IPC_WIDTH - 1, "IPC");
 
-		if (!notes->options->show_minmax_cycle) {
-			if (al->cycles)
+		if (!annotate_opts.show_minmax_cycle) {
+			if (al->cycles && al->cycles->avg)
 				obj__printf(obj, "%*" PRIu64 " ",
-					   ANNOTATION__CYCLES_WIDTH - 1, al->cycles);
+					   ANNOTATION__CYCLES_WIDTH - 1, al->cycles->avg);
 			else if (!show_title)
 				obj__printf(obj, "%*s",
 					    ANNOTATION__CYCLES_WIDTH, " ");
@@ -3145,8 +3245,8 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 
 				scnprintf(str, sizeof(str),
 					"%" PRIu64 "(%" PRIu64 "/%" PRIu64 ")",
-					al->cycles, al->cycles_min,
-					al->cycles_max);
+					al->cycles->avg, al->cycles->min,
+					al->cycles->max);
 
 				obj__printf(obj, "%*s ",
 					    ANNOTATION__MINMAX_CYCLES_WIDTH - 1,
@@ -3172,7 +3272,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 	if (!*al->line)
 		obj__printf(obj, "%-*s", width - pcnt_width - cycles_width, " ");
 	else if (al->offset == -1) {
-		if (al->line_nr && notes->options->show_linenr)
+		if (al->line_nr && annotate_opts.show_linenr)
 			printed = scnprintf(bf, sizeof(bf), "%-*d ", notes->widths.addr + 1, al->line_nr);
 		else
 			printed = scnprintf(bf, sizeof(bf), "%-*s  ", notes->widths.addr, " ");
@@ -3182,15 +3282,15 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 		u64 addr = al->offset;
 		int color = -1;
 
-		if (!notes->options->use_offset)
+		if (!annotate_opts.use_offset)
 			addr += notes->start;
 
-		if (!notes->options->use_offset) {
+		if (!annotate_opts.use_offset) {
 			printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr);
 		} else {
 			if (al->jump_sources &&
-			    notes->options->offset_level >= ANNOTATION__OFFSET_JUMP_TARGETS) {
-				if (notes->options->show_nr_jumps) {
+			    annotate_opts.offset_level >= ANNOTATION__OFFSET_JUMP_TARGETS) {
+				if (annotate_opts.show_nr_jumps) {
 					int prev;
 					printed = scnprintf(bf, sizeof(bf), "%*d ",
 							    notes->widths.jumps,
@@ -3204,9 +3304,9 @@ print_addr:
 				printed = scnprintf(bf, sizeof(bf), "%*" PRIx64 ": ",
 						    notes->widths.target, addr);
 			} else if (ins__is_call(&disasm_line(al)->ins) &&
-				   notes->options->offset_level >= ANNOTATION__OFFSET_CALL) {
+				   annotate_opts.offset_level >= ANNOTATION__OFFSET_CALL) {
 				goto print_addr;
-			} else if (notes->options->offset_level == ANNOTATION__MAX_OFFSET_LEVEL) {
+			} else if (annotate_opts.offset_level == ANNOTATION__MAX_OFFSET_LEVEL) {
 				goto print_addr;
 			} else {
 				printed = scnprintf(bf, sizeof(bf), "%-*s  ",
@@ -3228,43 +3328,44 @@ print_addr:
 }
 
 void annotation_line__write(struct annotation_line *al, struct annotation *notes,
-			    struct annotation_write_ops *wops,
-			    struct annotation_options *opts)
+			    struct annotation_write_ops *wops)
 {
 	__annotation_line__write(al, notes, wops->first_line, wops->current_entry,
 				 wops->change_color, wops->width, wops->obj,
-				 opts->percent_type,
+				 annotate_opts.percent_type,
 				 wops->set_color, wops->set_percent_color,
 				 wops->set_jumps_percent_color, wops->printf,
 				 wops->write_graph);
 }
 
 int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
-		      struct annotation_options *options, struct arch **parch)
+		      struct arch **parch)
 {
 	struct symbol *sym = ms->sym;
 	struct annotation *notes = symbol__annotation(sym);
 	size_t size = symbol__size(sym);
 	int nr_pcnt = 1, err;
 
-	notes->offsets = zalloc(size * sizeof(struct annotation_line *));
-	if (notes->offsets == NULL)
+	notes->src->offsets = zalloc(size * sizeof(struct annotation_line *));
+	if (notes->src->offsets == NULL)
 		return ENOMEM;
 
 	if (evsel__is_group_event(evsel))
 		nr_pcnt = evsel->core.nr_members;
 
-	err = symbol__annotate(ms, evsel, options, parch);
+	err = symbol__annotate(ms, evsel, parch);
 	if (err)
 		goto out_free_offsets;
 
-	notes->options = options;
-
 	symbol__calc_percent(sym, evsel);
 
 	annotation__set_offsets(notes, size);
 	annotation__mark_jump_targets(notes, sym);
-	annotation__compute_ipc(notes, size);
+
+	err = annotation__compute_ipc(notes, size);
+	if (err)
+		goto out_free_offsets;
+
 	annotation__init_column_widths(notes, sym);
 	notes->nr_events = nr_pcnt;
 
@@ -3274,7 +3375,7 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
 	return 0;
 
 out_free_offsets:
-	zfree(&notes->offsets);
+	zfree(&notes->src->offsets);
 	return err;
 }
 
@@ -3337,8 +3438,10 @@ static int annotation__config(const char *var, const char *value, void *data)
 	return 0;
 }
 
-void annotation_options__init(struct annotation_options *opt)
+void annotation_options__init(void)
 {
+	struct annotation_options *opt = &annotate_opts;
+
 	memset(opt, 0, sizeof(*opt));
 
 	/* Default values. */
@@ -3349,16 +3452,15 @@ void annotation_options__init(struct annotation_options *opt)
 	opt->percent_type = PERCENT_PERIOD_LOCAL;
 }
 
-
-void annotation_options__exit(struct annotation_options *opt)
+void annotation_options__exit(void)
 {
-	zfree(&opt->disassembler_style);
-	zfree(&opt->objdump_path);
+	zfree(&annotate_opts.disassembler_style);
+	zfree(&annotate_opts.objdump_path);
 }
 
-void annotation_config__init(struct annotation_options *opt)
+void annotation_config__init(void)
 {
-	perf_config(annotation__config, opt);
+	perf_config(annotation__config, &annotate_opts);
 }
 
 static unsigned int parse_percent_type(char *str1, char *str2)
@@ -3382,10 +3484,9 @@ static unsigned int parse_percent_type(char *str1, char *str2)
 	return type;
 }
 
-int annotate_parse_percent_type(const struct option *opt, const char *_str,
+int annotate_parse_percent_type(const struct option *opt __maybe_unused, const char *_str,
 				int unset __maybe_unused)
 {
-	struct annotation_options *opts = opt->value;
 	unsigned int type;
 	char *str1, *str2;
 	int err = -1;
@@ -3404,7 +3505,7 @@ int annotate_parse_percent_type(const struct option *opt, const char *_str,
 	if (type == (unsigned int) -1)
 		type = parse_percent_type(str2, str1);
 	if (type != (unsigned int) -1) {
-		opts->percent_type = type;
+		annotate_opts.percent_type = type;
 		err = 0;
 	}
 
@@ -3413,11 +3514,267 @@ out:
 	return err;
 }
 
-int annotate_check_args(struct annotation_options *args)
+int annotate_check_args(void)
 {
+	struct annotation_options *args = &annotate_opts;
+
 	if (args->prefix_strip && !args->prefix) {
 		pr_err("--prefix-strip requires --prefix\n");
 		return -1;
 	}
 	return 0;
 }
+
+/*
+ * Get register number and access offset from the given instruction.
+ * It assumes AT&T x86 asm format like OFFSET(REG).  Maybe it needs
+ * to revisit the format when it handles different architecture.
+ * Fills @reg and @offset when return 0.
+ */
+static int extract_reg_offset(struct arch *arch, const char *str,
+			      struct annotated_op_loc *op_loc)
+{
+	char *p;
+	char *regname;
+
+	if (arch->objdump.register_char == 0)
+		return -1;
+
+	/*
+	 * It should start from offset, but it's possible to skip 0
+	 * in the asm.  So 0(%rax) should be same as (%rax).
+	 *
+	 * However, it also start with a segment select register like
+	 * %gs:0x18(%rbx).  In that case it should skip the part.
+	 */
+	if (*str == arch->objdump.register_char) {
+		while (*str && !isdigit(*str) &&
+		       *str != arch->objdump.memory_ref_char)
+			str++;
+	}
+
+	op_loc->offset = strtol(str, &p, 0);
+
+	p = strchr(p, arch->objdump.register_char);
+	if (p == NULL)
+		return -1;
+
+	regname = strdup(p);
+	if (regname == NULL)
+		return -1;
+
+	op_loc->reg = get_dwarf_regnum(regname, 0);
+	free(regname);
+	return 0;
+}
+
+/**
+ * annotate_get_insn_location - Get location of instruction
+ * @arch: the architecture info
+ * @dl: the target instruction
+ * @loc: a buffer to save the data
+ *
+ * Get detailed location info (register and offset) in the instruction.
+ * It needs both source and target operand and whether it accesses a
+ * memory location.  The offset field is meaningful only when the
+ * corresponding mem flag is set.
+ *
+ * Some examples on x86:
+ *
+ *   mov  (%rax), %rcx   # src_reg = rax, src_mem = 1, src_offset = 0
+ *                       # dst_reg = rcx, dst_mem = 0
+ *
+ *   mov  0x18, %r8      # src_reg = -1, dst_reg = r8
+ */
+int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
+			       struct annotated_insn_loc *loc)
+{
+	struct ins_operands *ops;
+	struct annotated_op_loc *op_loc;
+	int i;
+
+	if (!strcmp(dl->ins.name, "lock"))
+		ops = dl->ops.locked.ops;
+	else
+		ops = &dl->ops;
+
+	if (ops == NULL)
+		return -1;
+
+	memset(loc, 0, sizeof(*loc));
+
+	for_each_insn_op_loc(loc, i, op_loc) {
+		const char *insn_str = ops->source.raw;
+
+		if (i == INSN_OP_TARGET)
+			insn_str = ops->target.raw;
+
+		/* Invalidate the register by default */
+		op_loc->reg = -1;
+
+		if (insn_str == NULL)
+			continue;
+
+		if (strchr(insn_str, arch->objdump.memory_ref_char)) {
+			op_loc->mem_ref = true;
+			extract_reg_offset(arch, insn_str, op_loc);
+		} else {
+			char *s = strdup(insn_str);
+
+			if (s) {
+				op_loc->reg = get_dwarf_regnum(s, 0);
+				free(s);
+			}
+		}
+	}
+
+	return 0;
+}
+
+static void symbol__ensure_annotate(struct map_symbol *ms, struct evsel *evsel)
+{
+	struct disasm_line *dl, *tmp_dl;
+	struct annotation *notes;
+
+	notes = symbol__annotation(ms->sym);
+	if (!list_empty(&notes->src->source))
+		return;
+
+	if (symbol__annotate(ms, evsel, NULL) < 0)
+		return;
+
+	/* remove non-insn disasm lines for simplicity */
+	list_for_each_entry_safe(dl, tmp_dl, &notes->src->source, al.node) {
+		if (dl->al.offset == -1) {
+			list_del(&dl->al.node);
+			free(dl);
+		}
+	}
+}
+
+static struct disasm_line *find_disasm_line(struct symbol *sym, u64 ip)
+{
+	struct disasm_line *dl;
+	struct annotation *notes;
+
+	notes = symbol__annotation(sym);
+
+	list_for_each_entry(dl, &notes->src->source, al.node) {
+		if (sym->start + dl->al.offset == ip)
+			return dl;
+	}
+	return NULL;
+}
+
+static struct annotated_item_stat *annotate_data_stat(struct list_head *head,
+						      const char *name)
+{
+	struct annotated_item_stat *istat;
+
+	list_for_each_entry(istat, head, list) {
+		if (!strcmp(istat->name, name))
+			return istat;
+	}
+
+	istat = zalloc(sizeof(*istat));
+	if (istat == NULL)
+		return NULL;
+
+	istat->name = strdup(name);
+	if (istat->name == NULL) {
+		free(istat);
+		return NULL;
+	}
+
+	list_add_tail(&istat->list, head);
+	return istat;
+}
+
+/**
+ * hist_entry__get_data_type - find data type for given hist entry
+ * @he: hist entry
+ *
+ * This function first annotates the instruction at @he->ip and extracts
+ * register and offset info from it.  Then it searches the DWARF debug
+ * info to get a variable and type information using the address, register,
+ * and offset.
+ */
+struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
+{
+	struct map_symbol *ms = &he->ms;
+	struct evsel *evsel = hists_to_evsel(he->hists);
+	struct arch *arch;
+	struct disasm_line *dl;
+	struct annotated_insn_loc loc;
+	struct annotated_op_loc *op_loc;
+	struct annotated_data_type *mem_type;
+	struct annotated_item_stat *istat;
+	u64 ip = he->ip;
+	int i;
+
+	ann_data_stat.total++;
+
+	if (ms->map == NULL || ms->sym == NULL) {
+		ann_data_stat.no_sym++;
+		return NULL;
+	}
+
+	if (!symbol_conf.init_annotation) {
+		ann_data_stat.no_sym++;
+		return NULL;
+	}
+
+	if (evsel__get_arch(evsel, &arch) < 0) {
+		ann_data_stat.no_insn++;
+		return NULL;
+	}
+
+	/* Make sure it runs objdump to get disasm of the function */
+	symbol__ensure_annotate(ms, evsel);
+
+	/*
+	 * Get a disasm to extract the location from the insn.
+	 * This is too slow...
+	 */
+	dl = find_disasm_line(ms->sym, ip);
+	if (dl == NULL) {
+		ann_data_stat.no_insn++;
+		return NULL;
+	}
+
+	istat = annotate_data_stat(&ann_insn_stat, dl->ins.name);
+	if (istat == NULL) {
+		ann_data_stat.no_insn++;
+		return NULL;
+	}
+
+	if (annotate_get_insn_location(arch, dl, &loc) < 0) {
+		ann_data_stat.no_insn_ops++;
+		istat->bad++;
+		return NULL;
+	}
+
+	for_each_insn_op_loc(&loc, i, op_loc) {
+		if (!op_loc->mem_ref)
+			continue;
+
+		mem_type = find_data_type(ms, ip, op_loc->reg, op_loc->offset);
+		if (mem_type)
+			istat->good++;
+		else
+			istat->bad++;
+
+		if (symbol_conf.annotate_data_sample) {
+			annotated_data_type__update_samples(mem_type, evsel,
+							    op_loc->offset,
+							    he->stat.nr_events,
+							    he->stat.period);
+		}
+		he->mem_type_off = op_loc->offset;
+		return mem_type;
+	}
+
+	ann_data_stat.no_mem_ops++;
+	istat->bad++;
+	return NULL;
+}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 962780559176..dba50762c6e8 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -23,6 +23,7 @@ struct option;
 struct perf_sample;
 struct evsel;
 struct symbol;
+struct annotated_data_type;
 
 struct ins {
 	const char     *name;
@@ -31,8 +32,6 @@ struct ins {
 
 struct ins_operands {
 	char	*raw;
-	char	*raw_comment;
-	char	*raw_func_start;
 	struct {
 		char	*raw;
 		char	*name;
@@ -41,22 +40,30 @@ struct ins_operands {
 		s64	offset;
 		bool	offset_avail;
 		bool	outside;
+		bool	multi_regs;
 	} target;
 	union {
 		struct {
 			char	*raw;
 			char	*name;
 			u64	addr;
+			bool	multi_regs;
 		} source;
 		struct {
 			struct ins	    ins;
 			struct ins_operands *ops;
 		} locked;
+		struct {
+			char	*raw_comment;
+			char	*raw_func_start;
+		} jump;
 	};
 };
 
 struct arch;
 
+bool arch__is(struct arch *arch, const char *name);
+
 struct ins_ops {
 	void (*free)(struct ins_operands *ops);
 	int (*parse)(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms);
@@ -101,6 +108,8 @@ struct annotation_options {
 	unsigned int percent_type;
 };
 
+extern struct annotation_options annotate_opts;
+
 enum {
 	ANNOTATION__OFFSET_JUMP_TARGETS = 1,
 	ANNOTATION__OFFSET_CALL,
@@ -130,6 +139,13 @@ struct annotation_data {
 	struct sym_hist_entry	 he;
 };
 
+struct cycles_info {
+	float			 ipc;
+	u64			 avg;
+	u64			 max;
+	u64			 min;
+};
+
 struct annotation_line {
 	struct list_head	 node;
 	struct rb_node		 rb_node;
@@ -137,12 +153,9 @@ struct annotation_line {
 	char			*line;
 	int			 line_nr;
 	char			*fileloc;
-	int			 jump_sources;
-	float			 ipc;
-	u64			 cycles;
-	u64			 cycles_max;
-	u64			 cycles_min;
 	char			*path;
+	struct cycles_info	*cycles;
+	int			 jump_sources;
 	u32			 idx;
 	int			 idx_asm;
 	int			 data_nr;
@@ -214,8 +227,7 @@ struct annotation_write_ops {
 };
 
 void annotation_line__write(struct annotation_line *al, struct annotation *notes,
-			    struct annotation_write_ops *ops,
-			    struct annotation_options *opts);
+			    struct annotation_write_ops *ops);
 
 int __annotation__scnprintf_samples_period(struct annotation *notes,
 					   char *bf, size_t size,
@@ -264,27 +276,29 @@ struct cyc_hist {
  * returns.
  */
 struct annotated_source {
-	struct list_head   source;
-	int    		   nr_histograms;
-	size_t		   sizeof_sym_hist;
-	struct cyc_hist	   *cycles_hist;
-	struct sym_hist	   *histograms;
+	struct list_head	source;
+	size_t			sizeof_sym_hist;
+	struct sym_hist		*histograms;
+	struct annotation_line	**offsets;
+	int    			nr_histograms;
+	int			nr_entries;
+	int			nr_asm_entries;
+	u16			max_line_len;
 };
 
-struct LOCKABLE annotation {
-	u64			max_coverage;
-	u64			start;
+struct annotated_branch {
 	u64			hit_cycles;
 	u64			hit_insn;
 	unsigned int		total_insn;
 	unsigned int		cover_insn;
-	struct annotation_options *options;
-	struct annotation_line	**offsets;
+	struct cyc_hist		*cycles_hist;
+	u64			max_coverage;
+};
+
+struct LOCKABLE annotation {
+	u64			start;
 	int			nr_events;
 	int			max_jump_sources;
-	int			nr_entries;
-	int			nr_asm_entries;
-	u16			max_line_len;
 	struct {
 		u8		addr;
 		u8		jumps;
@@ -293,8 +307,8 @@ struct LOCKABLE annotation {
 		u8		max_addr;
 		u8		max_ins_name;
 	} widths;
-	bool			have_cycles;
 	struct annotated_source *src;
+	struct annotated_branch *branch;
 };
 
 static inline void annotation__init(struct annotation *notes __maybe_unused)
@@ -308,10 +322,10 @@ bool annotation__trylock(struct annotation *notes) EXCLUSIVE_TRYLOCK_FUNCTION(tr
 
 static inline int annotation__cycles_width(struct annotation *notes)
 {
-	if (notes->have_cycles && notes->options->show_minmax_cycle)
+	if (notes->branch && annotate_opts.show_minmax_cycle)
 		return ANNOTATION__IPC_WIDTH + ANNOTATION__MINMAX_CYCLES_WIDTH;
 
-	return notes->have_cycles ? ANNOTATION__IPC_WIDTH + ANNOTATION__CYCLES_WIDTH : 0;
+	return notes->branch ? ANNOTATION__IPC_WIDTH + ANNOTATION__CYCLES_WIDTH : 0;
 }
 
 static inline int annotation__pcnt_width(struct annotation *notes)
@@ -319,13 +333,12 @@ static inline int annotation__pcnt_width(struct annotation *notes)
 	return (symbol_conf.show_total_period ? 12 : 7) * notes->nr_events;
 }
 
-static inline bool annotation_line__filter(struct annotation_line *al, struct annotation *notes)
+static inline bool annotation_line__filter(struct annotation_line *al)
 {
-	return notes->options->hide_src_code && al->offset == -1;
+	return annotate_opts.hide_src_code && al->offset == -1;
 }
 
 void annotation__set_offsets(struct annotation *notes, s64 size);
-void annotation__compute_ipc(struct annotation *notes, size_t size);
 void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym);
 void annotation__update_column_widths(struct annotation *notes);
 void annotation__init_column_widths(struct annotation *notes, struct symbol *sym);
@@ -349,6 +362,8 @@ static inline struct annotation *symbol__annotation(struct symbol *sym)
 int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample,
 				 struct evsel *evsel);
 
+struct annotated_branch *annotation__get_branch(struct annotation *notes);
+
 int addr_map_symbol__account_cycles(struct addr_map_symbol *ams,
 				    struct addr_map_symbol *start,
 				    unsigned cycles);
@@ -361,11 +376,9 @@ void symbol__annotate_zero_histograms(struct symbol *sym);
 
 int symbol__annotate(struct map_symbol *ms,
 		     struct evsel *evsel,
-		     struct annotation_options *options,
 		     struct arch **parch);
 int symbol__annotate2(struct map_symbol *ms,
 		      struct evsel *evsel,
-		      struct annotation_options *options,
 		      struct arch **parch);
 
 enum symbol_disassemble_errno {
@@ -392,43 +405,86 @@ enum symbol_disassemble_errno {
 
 int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, size_t buflen);
 
-int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel,
-			    struct annotation_options *options);
+int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel);
 void symbol__annotate_zero_histogram(struct symbol *sym, int evidx);
 void symbol__annotate_decay_histogram(struct symbol *sym, int evidx);
 void annotated_source__purge(struct annotated_source *as);
 
-int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel,
-				struct annotation_options *opts);
+int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel);
 
 bool ui__has_annotation(void);
 
-int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts);
+int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel);
 
-int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts);
+int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel);
 
 #ifdef HAVE_SLANG_SUPPORT
 int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
-			 struct hist_browser_timer *hbt,
-			 struct annotation_options *opts);
+			 struct hist_browser_timer *hbt);
 #else
 static inline int symbol__tui_annotate(struct map_symbol *ms __maybe_unused,
 				struct evsel *evsel  __maybe_unused,
-				struct hist_browser_timer *hbt __maybe_unused,
-				struct annotation_options *opts __maybe_unused)
+				struct hist_browser_timer *hbt __maybe_unused)
 {
 	return 0;
 }
 #endif
 
-void annotation_options__init(struct annotation_options *opt);
-void annotation_options__exit(struct annotation_options *opt);
+void annotation_options__init(void);
+void annotation_options__exit(void);
 
-void annotation_config__init(struct annotation_options *opt);
+void annotation_config__init(void);
 
 int annotate_parse_percent_type(const struct option *opt, const char *_str,
 				int unset);
 
-int annotate_check_args(struct annotation_options *args);
+int annotate_check_args(void);
+
+/**
+ * struct annotated_op_loc - Location info of instruction operand
+ * @reg: Register in the operand
+ * @offset: Memory access offset in the operand
+ * @mem_ref: Whether the operand accesses memory
+ */
+struct annotated_op_loc {
+	int reg;
+	int offset;
+	bool mem_ref;
+};
+
+enum annotated_insn_ops {
+	INSN_OP_SOURCE = 0,
+	INSN_OP_TARGET = 1,
+
+	INSN_OP_MAX,
+};
+
+/**
+ * struct annotated_insn_loc - Location info of instruction
+ * @ops: Array of location info for source and target operands
+ */
+struct annotated_insn_loc {
+	struct annotated_op_loc ops[INSN_OP_MAX];
+};
+
+#define for_each_insn_op_loc(insn_loc, i, op_loc)			\
+	for (i = INSN_OP_SOURCE, op_loc = &(insn_loc)->ops[i];		\
+	     i < INSN_OP_MAX;						\
+	     i++, op_loc++)
+
+/* Get detailed location info in the instruction */
+int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
+			       struct annotated_insn_loc *loc);
+
+/* Returns a data type from the sample instruction (if any) */
+struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he);
+
+struct annotated_item_stat {
+	struct list_head list;
+	char *name;
+	int good;
+	int bad;
+};
+extern struct list_head ann_insn_stat;
 
 #endif	/* __PERF_ANNOTATE_H */
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index a0368202a746..3684e6009b63 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -174,7 +174,7 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
 				   struct evlist *evlist,
 				   struct evsel *evsel, int idx)
 {
-	bool per_cpu = !perf_cpu_map__empty(evlist->core.user_requested_cpus);
+	bool per_cpu = !perf_cpu_map__has_any_cpu_or_is_empty(evlist->core.user_requested_cpus);
 
 	mp->mmap_needed = evsel->needs_auxtrace_mmap;
 
@@ -648,7 +648,7 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
 
 static int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx)
 {
-	bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.user_requested_cpus);
+	bool per_cpu_mmaps = !perf_cpu_map__has_any_cpu_or_is_empty(evlist->core.user_requested_cpus);
 
 	if (per_cpu_mmaps) {
 		struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->core.all_cpus, idx);
@@ -1638,6 +1638,9 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts,
 		case 'Z':
 			synth_opts->timeless_decoding = true;
 			break;
+		case 'T':
+			synth_opts->use_timestamp = true;
+			break;
 		case ' ':
 		case ',':
 			break;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 29eb82dff574..55702215a82d 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -99,6 +99,7 @@ enum itrace_period_type {
  * @remote_access: whether to synthesize remote access events
  * @mem: whether to synthesize memory events
  * @timeless_decoding: prefer "timeless" decoding i.e. ignore timestamps
+ * @use_timestamp: use the timestamp trace as kernel time
  * @vm_time_correlation: perform VM Time Correlation
  * @vm_tm_corr_dry_run: VM Time Correlation dry-run
  * @vm_tm_corr_args:  VM Time Correlation implementation-specific arguments
@@ -146,6 +147,7 @@ struct itrace_synth_opts {
 	bool			remote_access;
 	bool			mem;
 	bool			timeless_decoding;
+	bool			use_timestamp;
 	bool			vm_time_correlation;
 	bool			vm_tm_corr_dry_run;
 	char			*vm_tm_corr_args;
@@ -678,6 +680,7 @@ bool auxtrace__evsel_is_auxtrace(struct perf_session *session,
 "				q:			quicker (less detailed) decoding\n" \
 "				A:			approximate IPC\n" \
 "				Z:			prefer to ignore timestamps (so-called \"timeless\" decoding)\n" \
+"				T:			use the timestamp trace as kernel time\n" \
 "				PERIOD[ns|us|ms|i|t]:   specify period to sample stream\n" \
 "				concatenate multiple options. Default is iybxwpe or cewp\n"
 
diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c
index 591fc1edd385..dec910989701 100644
--- a/tools/perf/util/block-info.c
+++ b/tools/perf/util/block-info.c
@@ -129,9 +129,9 @@ int block_info__process_sym(struct hist_entry *he, struct block_hist *bh,
 	al.sym = he->ms.sym;
 
 	notes = symbol__annotation(he->ms.sym);
-	if (!notes || !notes->src || !notes->src->cycles_hist)
+	if (!notes || !notes->branch || !notes->branch->cycles_hist)
 		return 0;
-	ch = notes->src->cycles_hist;
+	ch = notes->branch->cycles_hist;
 	for (unsigned int i = 0; i < symbol__size(he->ms.sym); i++) {
 		if (ch[i].num_aggr) {
 			struct block_info *bi;
@@ -464,8 +464,7 @@ void block_info__free_report(struct block_report *reps, int nr_reps)
 }
 
 int report__browse_block_hists(struct block_hist *bh, float min_percent,
-			       struct evsel *evsel, struct perf_env *env,
-			       struct annotation_options *annotation_opts)
+			       struct evsel *evsel, struct perf_env *env)
 {
 	int ret;
 
@@ -477,8 +476,7 @@ int report__browse_block_hists(struct block_hist *bh, float min_percent,
 		return 0;
 	case 1:
 		symbol_conf.report_individual_block = true;
-		ret = block_hists_tui_browse(bh, evsel, min_percent,
-					     env, annotation_opts);
+		ret = block_hists_tui_browse(bh, evsel, min_percent, env);
 		return ret;
 	default:
 		return -1;
diff --git a/tools/perf/util/block-info.h b/tools/perf/util/block-info.h
index 42e9dcc4cf0a..96f53e89795e 100644
--- a/tools/perf/util/block-info.h
+++ b/tools/perf/util/block-info.h
@@ -78,8 +78,7 @@ struct block_report *block_info__create_report(struct evlist *evlist,
 void block_info__free_report(struct block_report *reps, int nr_reps);
 
 int report__browse_block_hists(struct block_hist *bh, float min_percent,
-			       struct evsel *evsel, struct perf_env *env,
-			       struct annotation_options *annotation_opts);
+			       struct evsel *evsel, struct perf_env *env);
 
 float block_info__total_cycles_percent(struct hist_entry *he);
 
diff --git a/tools/perf/util/block-range.c b/tools/perf/util/block-range.c
index 680e92774d0c..15c42196c24c 100644
--- a/tools/perf/util/block-range.c
+++ b/tools/perf/util/block-range.c
@@ -311,6 +311,7 @@ done:
 double block_range__coverage(struct block_range *br)
 {
 	struct symbol *sym;
+	struct annotated_branch *branch;
 
 	if (!br) {
 		if (block_ranges.blocks)
@@ -323,5 +324,9 @@ double block_range__coverage(struct block_range *br)
 	if (!sym)
 		return -1;
 
-	return (double)br->coverage / symbol__annotation(sym)->max_coverage;
+	branch = symbol__annotation(sym)->branch;
+	if (!branch)
+		return -1;
+
+	return (double)br->coverage / branch->max_coverage;
 }
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 38fcf3ba5749..3573e0b7ef3e 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -386,6 +386,9 @@ int perf_event__synthesize_bpf_events(struct perf_session *session,
 	int err;
 	int fd;
 
+	if (opts->no_bpf_event)
+		return 0;
+
 	event = malloc(sizeof(event->bpf) + KSYM_NAME_LEN + machine->id_hdr_size);
 	if (!event)
 		return -1;
@@ -542,9 +545,9 @@ int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env)
 	return evlist__add_sb_event(evlist, &attr, bpf_event__sb_cb, env);
 }
 
-void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
-				    struct perf_env *env,
-				    FILE *fp)
+void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
+				      struct perf_env *env,
+				      FILE *fp)
 {
 	__u32 *prog_lens = (__u32 *)(uintptr_t)(info->jited_func_lens);
 	__u64 *prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms);
@@ -560,7 +563,7 @@ void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
 	if (info->btf_id) {
 		struct btf_node *node;
 
-		node = perf_env__find_btf(env, info->btf_id);
+		node = __perf_env__find_btf(env, info->btf_id);
 		if (node)
 			btf = btf__new((__u8 *)(node->data),
 				       node->data_size);
diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h
index 1bcbd4fb6c66..e2f0420905f5 100644
--- a/tools/perf/util/bpf-event.h
+++ b/tools/perf/util/bpf-event.h
@@ -33,9 +33,9 @@ struct btf_node {
 int machine__process_bpf(struct machine *machine, union perf_event *event,
 			 struct perf_sample *sample);
 int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env);
-void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
-				    struct perf_env *env,
-				    FILE *fp);
+void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
+				      struct perf_env *env,
+				      FILE *fp);
 #else
 static inline int machine__process_bpf(struct machine *machine __maybe_unused,
 				       union perf_event *event __maybe_unused,
@@ -50,9 +50,9 @@ static inline int evlist__add_bpf_sb_event(struct evlist *evlist __maybe_unused,
 	return 0;
 }
 
-static inline void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info __maybe_unused,
-						  struct perf_env *env __maybe_unused,
-						  FILE *fp __maybe_unused)
+static inline void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info __maybe_unused,
+						    struct perf_env *env __maybe_unused,
+						    FILE *fp __maybe_unused)
 {
 
 }
diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c
index 7f9b0e46e008..7a8af60e0f51 100644
--- a/tools/perf/util/bpf_counter.c
+++ b/tools/perf/util/bpf_counter.c
@@ -455,7 +455,7 @@ static int bperf__load(struct evsel *evsel, struct target *target)
 		return -1;
 
 	if (!all_cpu_map) {
-		all_cpu_map = perf_cpu_map__new(NULL);
+		all_cpu_map = perf_cpu_map__new_online_cpus();
 		if (!all_cpu_map)
 			return -1;
 	}
diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c
index f1716c089c99..31ff19afc20c 100644
--- a/tools/perf/util/bpf_lock_contention.c
+++ b/tools/perf/util/bpf_lock_contention.c
@@ -318,7 +318,7 @@ int lock_contention_read(struct lock_contention *con)
 	}
 
 	/* make sure it loads the kernel map */
-	map__load(maps__first(machine->kmaps)->map);
+	maps__load_first(machine->kmaps);
 
 	prev_key = NULL;
 	while (!bpf_map_get_next_key(fd, prev_key, &key)) {
diff --git a/tools/perf/util/compress.h b/tools/perf/util/compress.h
index 0cd3369af2a4..b29109cd3609 100644
--- a/tools/perf/util/compress.h
+++ b/tools/perf/util/compress.h
@@ -3,6 +3,8 @@
 #define PERF_COMPRESS_H
 
 #include <stdbool.h>
+#include <stddef.h>
+#include <sys/types.h>
 #ifdef HAVE_ZSTD_SUPPORT
 #include <zstd.h>
 #endif
@@ -21,6 +23,7 @@ struct zstd_data {
 #ifdef HAVE_ZSTD_SUPPORT
 	ZSTD_CStream	*cstream;
 	ZSTD_DStream	*dstream;
+	int comp_level;
 #endif
 };
 
@@ -29,7 +32,7 @@ struct zstd_data {
 int zstd_init(struct zstd_data *data, int level);
 int zstd_fini(struct zstd_data *data);
 
-size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
+ssize_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
 				       void *src, size_t src_size, size_t max_record_size,
 				       size_t process_header(void *record, size_t increment));
 
@@ -48,7 +51,7 @@ static inline int zstd_fini(struct zstd_data *data __maybe_unused)
 }
 
 static inline
-size_t zstd_compress_stream_to_records(struct zstd_data *data __maybe_unused,
+ssize_t zstd_compress_stream_to_records(struct zstd_data *data __maybe_unused,
 				       void *dst __maybe_unused, size_t dst_size __maybe_unused,
 				       void *src __maybe_unused, size_t src_size __maybe_unused,
 				       size_t max_record_size __maybe_unused,
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 0e090e8bc334..0581ee0fa5f2 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -672,7 +672,7 @@ struct perf_cpu_map *cpu_map__online(void) /* thread unsafe */
 	static struct perf_cpu_map *online;
 
 	if (!online)
-		online = perf_cpu_map__new(NULL); /* from /sys/devices/system/cpu/online */
+		online = perf_cpu_map__new_online_cpus(); /* from /sys/devices/system/cpu/online */
 
 	return online;
 }
diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c
index 81cfc85f4668..8bbeb2dc76fd 100644
--- a/tools/perf/util/cputopo.c
+++ b/tools/perf/util/cputopo.c
@@ -267,7 +267,7 @@ struct cpu_topology *cpu_topology__new(void)
 	ncpus = cpu__max_present_cpu().cpu;
 
 	/* build online CPU map */
-	map = perf_cpu_map__new(NULL);
+	map = perf_cpu_map__new_online_cpus();
 	if (map == NULL) {
 		pr_debug("failed to get system cpumap\n");
 		return NULL;
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index a9873d14c632..d65d7485886c 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -3346,12 +3346,27 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
 	etm->metadata = metadata;
 	etm->auxtrace_type = auxtrace_info->type;
 
-	/* Use virtual timestamps if all ETMs report ts_source = 1 */
-	etm->has_virtual_ts = cs_etm__has_virtual_ts(metadata, num_cpu);
+	if (etm->synth_opts.use_timestamp)
+		/*
+		 * Prior to Armv8.4, Arm CPUs don't support FEAT_TRF feature,
+		 * therefore the decoder cannot know if the timestamp trace is
+		 * same with the kernel time.
+		 *
+		 * If a user has knowledge for the working platform and can
+		 * specify itrace option 'T' to tell decoder to forcely use the
+		 * traced timestamp as the kernel time.
+		 */
+		etm->has_virtual_ts = true;
+	else
+		/* Use virtual timestamps if all ETMs report ts_source = 1 */
+		etm->has_virtual_ts = cs_etm__has_virtual_ts(metadata, num_cpu);
 
 	if (!etm->has_virtual_ts)
 		ui__warning("Virtual timestamps are not enabled, or not supported by the traced system.\n"
-			    "The time field of the samples will not be set accurately.\n\n");
+			    "The time field of the samples will not be set accurately.\n"
+			    "For Arm CPUs prior to Armv8.4 or without support FEAT_TRF,\n"
+			    "you can specify the itrace option 'T' for timestamp decoding\n"
+			    "if the Coresight timestamp on the platform is same with the kernel time.\n\n");
 
 	etm->auxtrace.process_event = cs_etm__process_event;
 	etm->auxtrace.process_auxtrace_event = cs_etm__process_auxtrace_event;
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index b9fb71ab7a73..106429155c2e 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -253,8 +253,8 @@ static struct call_path *call_path_from_sample(struct db_export *dbe,
 		 */
 		addr_location__init(&al);
 		al.sym = node->ms.sym;
-		al.map = node->ms.map;
-		al.maps = thread__maps(thread);
+		al.map = map__get(node->ms.map);
+		al.maps = maps__get(thread__maps(thread));
 		al.addr = node->ip;
 
 		if (al.map && !al.sym)
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 88378c4c5dd9..e282b4ceb4d2 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -38,12 +38,21 @@ bool dump_trace = false, quiet = false;
 int debug_ordered_events;
 static int redirect_to_stderr;
 int debug_data_convert;
-static FILE *debug_file;
+static FILE *_debug_file;
 bool debug_display_time;
 
+FILE *debug_file(void)
+{
+	if (!_debug_file) {
+		pr_warning_once("debug_file not set");
+		debug_set_file(stderr);
+	}
+	return _debug_file;
+}
+
 void debug_set_file(FILE *file)
 {
-	debug_file = file;
+	_debug_file = file;
 }
 
 void debug_set_display_time(bool set)
@@ -78,8 +87,8 @@ int veprintf(int level, int var, const char *fmt, va_list args)
 		if (use_browser >= 1 && !redirect_to_stderr) {
 			ui_helpline__vshow(fmt, args);
 		} else {
-			ret = fprintf_time(debug_file);
-			ret += vfprintf(debug_file, fmt, args);
+			ret = fprintf_time(debug_file());
+			ret += vfprintf(debug_file(), fmt, args);
 		}
 	}
 
@@ -107,9 +116,8 @@ static int veprintf_time(u64 t, const char *fmt, va_list args)
 	nsecs -= secs  * NSEC_PER_SEC;
 	usecs  = nsecs / NSEC_PER_USEC;
 
-	ret = fprintf(stderr, "[%13" PRIu64 ".%06" PRIu64 "] ",
-		      secs, usecs);
-	ret += vfprintf(stderr, fmt, args);
+	ret = fprintf(debug_file(), "[%13" PRIu64 ".%06" PRIu64 "] ", secs, usecs);
+	ret += vfprintf(debug_file(), fmt, args);
 	return ret;
 }
 
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index f99468a7f681..de8870980d44 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -77,6 +77,7 @@ int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __printf(4, 5)
 int veprintf(int level, int var, const char *fmt, va_list args);
 
 int perf_debug_option(const char *str);
+FILE *debug_file(void);
 void debug_set_file(FILE *file);
 void debug_set_display_time(bool set);
 void perf_debug_setup(void);
diff --git a/tools/perf/util/debuginfo.c b/tools/perf/util/debuginfo.c
new file mode 100644
index 000000000000..19acf4775d35
--- /dev/null
+++ b/tools/perf/util/debuginfo.c
@@ -0,0 +1,205 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * DWARF debug information handling code.  Copied from probe-finder.c.
+ *
+ * Written by Masami Hiramatsu <mhiramat@redhat.com>
+ */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/zalloc.h>
+
+#include "build-id.h"
+#include "dso.h"
+#include "debug.h"
+#include "debuginfo.h"
+#include "symbol.h"
+
+#ifdef HAVE_DEBUGINFOD_SUPPORT
+#include <elfutils/debuginfod.h>
+#endif
+
+/* Dwarf FL wrappers */
+static char *debuginfo_path;	/* Currently dummy */
+
+static const Dwfl_Callbacks offline_callbacks = {
+	.find_debuginfo = dwfl_standard_find_debuginfo,
+	.debuginfo_path = &debuginfo_path,
+
+	.section_address = dwfl_offline_section_address,
+
+	/* We use this table for core files too.  */
+	.find_elf = dwfl_build_id_find_elf,
+};
+
+/* Get a Dwarf from offline image */
+static int debuginfo__init_offline_dwarf(struct debuginfo *dbg,
+					 const char *path)
+{
+	GElf_Addr dummy;
+	int fd;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return fd;
+
+	dbg->dwfl = dwfl_begin(&offline_callbacks);
+	if (!dbg->dwfl)
+		goto error;
+
+	dwfl_report_begin(dbg->dwfl);
+	dbg->mod = dwfl_report_offline(dbg->dwfl, "", "", fd);
+	if (!dbg->mod)
+		goto error;
+
+	dbg->dbg = dwfl_module_getdwarf(dbg->mod, &dbg->bias);
+	if (!dbg->dbg)
+		goto error;
+
+	dwfl_module_build_id(dbg->mod, &dbg->build_id, &dummy);
+
+	dwfl_report_end(dbg->dwfl, NULL, NULL);
+
+	return 0;
+error:
+	if (dbg->dwfl)
+		dwfl_end(dbg->dwfl);
+	else
+		close(fd);
+	memset(dbg, 0, sizeof(*dbg));
+
+	return -ENOENT;
+}
+
+static struct debuginfo *__debuginfo__new(const char *path)
+{
+	struct debuginfo *dbg = zalloc(sizeof(*dbg));
+	if (!dbg)
+		return NULL;
+
+	if (debuginfo__init_offline_dwarf(dbg, path) < 0)
+		zfree(&dbg);
+	if (dbg)
+		pr_debug("Open Debuginfo file: %s\n", path);
+	return dbg;
+}
+
+enum dso_binary_type distro_dwarf_types[] = {
+	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
+	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
+	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
+	DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__NOT_FOUND,
+};
+
+struct debuginfo *debuginfo__new(const char *path)
+{
+	enum dso_binary_type *type;
+	char buf[PATH_MAX], nil = '\0';
+	struct dso *dso;
+	struct debuginfo *dinfo = NULL;
+	struct build_id bid;
+
+	/* Try to open distro debuginfo files */
+	dso = dso__new(path);
+	if (!dso)
+		goto out;
+
+	/* Set the build id for DSO_BINARY_TYPE__BUILDID_DEBUGINFO */
+	if (is_regular_file(path) && filename__read_build_id(path, &bid) > 0)
+		dso__set_build_id(dso, &bid);
+
+	for (type = distro_dwarf_types;
+	     !dinfo && *type != DSO_BINARY_TYPE__NOT_FOUND;
+	     type++) {
+		if (dso__read_binary_type_filename(dso, *type, &nil,
+						   buf, PATH_MAX) < 0)
+			continue;
+		dinfo = __debuginfo__new(buf);
+	}
+	dso__put(dso);
+
+out:
+	/* if failed to open all distro debuginfo, open given binary */
+	return dinfo ? : __debuginfo__new(path);
+}
+
+void debuginfo__delete(struct debuginfo *dbg)
+{
+	if (dbg) {
+		if (dbg->dwfl)
+			dwfl_end(dbg->dwfl);
+		free(dbg);
+	}
+}
+
+/* For the kernel module, we need a special code to get a DIE */
+int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
+				bool adjust_offset)
+{
+	int n, i;
+	Elf32_Word shndx;
+	Elf_Scn *scn;
+	Elf *elf;
+	GElf_Shdr mem, *shdr;
+	const char *p;
+
+	elf = dwfl_module_getelf(dbg->mod, &dbg->bias);
+	if (!elf)
+		return -EINVAL;
+
+	/* Get the number of relocations */
+	n = dwfl_module_relocations(dbg->mod);
+	if (n < 0)
+		return -ENOENT;
+	/* Search the relocation related .text section */
+	for (i = 0; i < n; i++) {
+		p = dwfl_module_relocation_info(dbg->mod, i, &shndx);
+		if (strcmp(p, ".text") == 0) {
+			/* OK, get the section header */
+			scn = elf_getscn(elf, shndx);
+			if (!scn)
+				return -ENOENT;
+			shdr = gelf_getshdr(scn, &mem);
+			if (!shdr)
+				return -ENOENT;
+			*offs = shdr->sh_addr;
+			if (adjust_offset)
+				*offs -= shdr->sh_offset;
+		}
+	}
+	return 0;
+}
+
+#ifdef HAVE_DEBUGINFOD_SUPPORT
+int get_source_from_debuginfod(const char *raw_path,
+			       const char *sbuild_id, char **new_path)
+{
+	debuginfod_client *c = debuginfod_begin();
+	const char *p = raw_path;
+	int fd;
+
+	if (!c)
+		return -ENOMEM;
+
+	fd = debuginfod_find_source(c, (const unsigned char *)sbuild_id,
+				0, p, new_path);
+	pr_debug("Search %s from debuginfod -> %d\n", p, fd);
+	if (fd >= 0)
+		close(fd);
+	debuginfod_end(c);
+	if (fd < 0) {
+		pr_debug("Failed to find %s in debuginfod (%s)\n",
+			raw_path, sbuild_id);
+		return -ENOENT;
+	}
+	pr_debug("Got a source %s\n", *new_path);
+
+	return 0;
+}
+#endif /* HAVE_DEBUGINFOD_SUPPORT */
diff --git a/tools/perf/util/debuginfo.h b/tools/perf/util/debuginfo.h
new file mode 100644
index 000000000000..4d65b8c605fc
--- /dev/null
+++ b/tools/perf/util/debuginfo.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _PERF_DEBUGINFO_H
+#define _PERF_DEBUGINFO_H
+
+#include <errno.h>
+#include <linux/compiler.h>
+
+#ifdef HAVE_DWARF_SUPPORT
+
+#include "dwarf-aux.h"
+
+/* debug information structure */
+struct debuginfo {
+	Dwarf		*dbg;
+	Dwfl_Module	*mod;
+	Dwfl		*dwfl;
+	Dwarf_Addr	bias;
+	const unsigned char	*build_id;
+};
+
+/* This also tries to open distro debuginfo */
+struct debuginfo *debuginfo__new(const char *path);
+void debuginfo__delete(struct debuginfo *dbg);
+
+int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
+			       bool adjust_offset);
+
+#else /* HAVE_DWARF_SUPPORT */
+
+/* dummy debug information structure */
+struct debuginfo {
+};
+
+static inline struct debuginfo *debuginfo__new(const char *path __maybe_unused)
+{
+	return NULL;
+}
+
+static inline void debuginfo__delete(struct debuginfo *dbg __maybe_unused)
+{
+}
+
+static inline int debuginfo__get_text_offset(struct debuginfo *dbg __maybe_unused,
+					     Dwarf_Addr *offs __maybe_unused,
+					     bool adjust_offset __maybe_unused)
+{
+	return -EINVAL;
+}
+
+#endif /* HAVE_DWARF_SUPPORT */
+
+#ifdef HAVE_DEBUGINFOD_SUPPORT
+int get_source_from_debuginfod(const char *raw_path, const char *sbuild_id,
+			       char **new_path);
+#else /* HAVE_DEBUGINFOD_SUPPORT */
+static inline int get_source_from_debuginfod(const char *raw_path __maybe_unused,
+					     const char *sbuild_id __maybe_unused,
+					     char **new_path __maybe_unused)
+{
+	return -ENOTSUP;
+}
+#endif /* HAVE_DEBUGINFOD_SUPPORT */
+
+#endif /* _PERF_DEBUGINFO_H */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 1f629b6fb7cf..22fd5fa806ed 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -31,6 +31,7 @@
 #include "debug.h"
 #include "string2.h"
 #include "vdso.h"
+#include "annotate-data.h"
 
 static const char * const debuglink_paths[] = {
 	"%.0s%s",
@@ -1327,6 +1328,7 @@ struct dso *dso__new_id(const char *name, struct dso_id *id)
 		dso->data.cache = RB_ROOT;
 		dso->inlined_nodes = RB_ROOT_CACHED;
 		dso->srclines = RB_ROOT_CACHED;
+		dso->data_types = RB_ROOT;
 		dso->data.fd = -1;
 		dso->data.status = DSO_DATA_STATUS_UNKNOWN;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
@@ -1370,6 +1372,8 @@ void dso__delete(struct dso *dso)
 	symbols__delete(&dso->symbols);
 	dso->symbol_names_len = 0;
 	zfree(&dso->symbol_names);
+	annotated_data_type__tree_delete(&dso->data_types);
+
 	if (dso->short_name_allocated) {
 		zfree((char **)&dso->short_name);
 		dso->short_name_allocated = false;
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 3759de8c2267..ce9f3849a773 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -154,6 +154,8 @@ struct dso {
 	size_t		 symbol_names_len;
 	struct rb_root_cached inlined_nodes;
 	struct rb_root_cached srclines;
+	struct rb_root	data_types;
+
 	struct {
 		u64		addr;
 		struct symbol	*symbol;
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 2941d88f2199..7aa5fee0da19 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -1051,32 +1051,28 @@ Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
 }
 
 /**
- * die_get_typename - Get the name of given variable DIE
- * @vr_die: a variable DIE
+ * die_get_typename_from_type - Get the name of given type DIE
+ * @type_die: a type DIE
  * @buf: a strbuf for result type name
  *
- * Get the name of @vr_die and stores it to @buf. Return 0 if succeeded.
+ * Get the name of @type_die and stores it to @buf. Return 0 if succeeded.
  * and Return -ENOENT if failed to find type name.
  * Note that the result will stores typedef name if possible, and stores
  * "*(function_type)" if the type is a function pointer.
  */
-int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
+int die_get_typename_from_type(Dwarf_Die *type_die, struct strbuf *buf)
 {
-	Dwarf_Die type;
 	int tag, ret;
 	const char *tmp = "";
 
-	if (__die_get_real_type(vr_die, &type) == NULL)
-		return -ENOENT;
-
-	tag = dwarf_tag(&type);
+	tag = dwarf_tag(type_die);
 	if (tag == DW_TAG_array_type || tag == DW_TAG_pointer_type)
 		tmp = "*";
 	else if (tag == DW_TAG_subroutine_type) {
 		/* Function pointer */
 		return strbuf_add(buf, "(function_type)", 15);
 	} else {
-		const char *name = dwarf_diename(&type);
+		const char *name = dwarf_diename(type_die);
 
 		if (tag == DW_TAG_union_type)
 			tmp = "union ";
@@ -1089,8 +1085,35 @@ int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
 		/* Write a base name */
 		return strbuf_addf(buf, "%s%s", tmp, name ?: "");
 	}
-	ret = die_get_typename(&type, buf);
-	return ret ? ret : strbuf_addstr(buf, tmp);
+	ret = die_get_typename(type_die, buf);
+	if (ret < 0) {
+		/* void pointer has no type attribute */
+		if (tag == DW_TAG_pointer_type && ret == -ENOENT)
+			return strbuf_addf(buf, "void*");
+
+		return ret;
+	}
+	return strbuf_addstr(buf, tmp);
+}
+
+/**
+ * die_get_typename - Get the name of given variable DIE
+ * @vr_die: a variable DIE
+ * @buf: a strbuf for result type name
+ *
+ * Get the name of @vr_die and stores it to @buf. Return 0 if succeeded.
+ * and Return -ENOENT if failed to find type name.
+ * Note that the result will stores typedef name if possible, and stores
+ * "*(function_type)" if the type is a function pointer.
+ */
+int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
+{
+	Dwarf_Die type;
+
+	if (__die_get_real_type(vr_die, &type) == NULL)
+		return -ENOENT;
+
+	return die_get_typename_from_type(&type, buf);
 }
 
 /**
@@ -1238,12 +1261,151 @@ int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf)
 out:
 	return ret;
 }
-#else
-int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
-		      Dwarf_Die *vr_die __maybe_unused,
-		      struct strbuf *buf __maybe_unused)
+
+/* Interval parameters for __die_find_var_reg_cb() */
+struct find_var_data {
+	/* Target instruction address */
+	Dwarf_Addr pc;
+	/* Target memory address (for global data) */
+	Dwarf_Addr addr;
+	/* Target register */
+	unsigned reg;
+	/* Access offset, set for global data */
+	int offset;
+};
+
+/* Max number of registers DW_OP_regN supports */
+#define DWARF_OP_DIRECT_REGS  32
+
+/* Only checks direct child DIEs in the given scope. */
+static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg)
+{
+	struct find_var_data *data = arg;
+	int tag = dwarf_tag(die_mem);
+	ptrdiff_t off = 0;
+	Dwarf_Attribute attr;
+	Dwarf_Addr base, start, end;
+	Dwarf_Op *ops;
+	size_t nops;
+
+	if (tag != DW_TAG_variable && tag != DW_TAG_formal_parameter)
+		return DIE_FIND_CB_SIBLING;
+
+	if (dwarf_attr(die_mem, DW_AT_location, &attr) == NULL)
+		return DIE_FIND_CB_SIBLING;
+
+	while ((off = dwarf_getlocations(&attr, off, &base, &start, &end, &ops, &nops)) > 0) {
+		/* Assuming the location list is sorted by address */
+		if (end < data->pc)
+			continue;
+		if (start > data->pc)
+			break;
+
+		/* Only match with a simple case */
+		if (data->reg < DWARF_OP_DIRECT_REGS) {
+			if (ops->atom == (DW_OP_reg0 + data->reg) && nops == 1)
+				return DIE_FIND_CB_END;
+		} else {
+			if (ops->atom == DW_OP_regx && ops->number == data->reg &&
+			    nops == 1)
+				return DIE_FIND_CB_END;
+		}
+	}
+	return DIE_FIND_CB_SIBLING;
+}
+
+/**
+ * die_find_variable_by_reg - Find a variable saved in a register
+ * @sc_die: a scope DIE
+ * @pc: the program address to find
+ * @reg: the register number to find
+ * @die_mem: a buffer to save the resulting DIE
+ *
+ * Find the variable DIE accessed by the given register.
+ */
+Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die, Dwarf_Addr pc, int reg,
+				    Dwarf_Die *die_mem)
+{
+	struct find_var_data data = {
+		.pc = pc,
+		.reg = reg,
+	};
+	return die_find_child(sc_die, __die_find_var_reg_cb, &data, die_mem);
+}
+
+/* Only checks direct child DIEs in the given scope */
+static int __die_find_var_addr_cb(Dwarf_Die *die_mem, void *arg)
+{
+	struct find_var_data *data = arg;
+	int tag = dwarf_tag(die_mem);
+	ptrdiff_t off = 0;
+	Dwarf_Attribute attr;
+	Dwarf_Addr base, start, end;
+	Dwarf_Word size;
+	Dwarf_Die type_die;
+	Dwarf_Op *ops;
+	size_t nops;
+
+	if (tag != DW_TAG_variable)
+		return DIE_FIND_CB_SIBLING;
+
+	if (dwarf_attr(die_mem, DW_AT_location, &attr) == NULL)
+		return DIE_FIND_CB_SIBLING;
+
+	while ((off = dwarf_getlocations(&attr, off, &base, &start, &end, &ops, &nops)) > 0) {
+		if (ops->atom != DW_OP_addr)
+			continue;
+
+		if (data->addr < ops->number)
+			continue;
+
+		if (data->addr == ops->number) {
+			/* Update offset relative to the start of the variable */
+			data->offset = 0;
+			return DIE_FIND_CB_END;
+		}
+
+		if (die_get_real_type(die_mem, &type_die) == NULL)
+			continue;
+
+		if (dwarf_aggregate_size(&type_die, &size) < 0)
+			continue;
+
+		if (data->addr >= ops->number + size)
+			continue;
+
+		/* Update offset relative to the start of the variable */
+		data->offset = data->addr - ops->number;
+		return DIE_FIND_CB_END;
+	}
+	return DIE_FIND_CB_SIBLING;
+}
+
+/**
+ * die_find_variable_by_addr - Find variable located at given address
+ * @sc_die: a scope DIE
+ * @pc: the program address to find
+ * @addr: the data address to find
+ * @die_mem: a buffer to save the resulting DIE
+ * @offset: the offset in the resulting type
+ *
+ * Find the variable DIE located at the given address (in PC-relative mode).
+ * This is usually for global variables.
+ */
+Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr pc,
+				     Dwarf_Addr addr, Dwarf_Die *die_mem,
+				     int *offset)
 {
-	return -ENOTSUP;
+	struct find_var_data data = {
+		.pc = pc,
+		.addr = addr,
+	};
+	Dwarf_Die *result;
+
+	result = die_find_child(sc_die, __die_find_var_addr_cb, &data, die_mem);
+	if (result)
+		*offset = data.offset;
+	return result;
 }
 #endif
 
@@ -1425,3 +1587,56 @@ void die_skip_prologue(Dwarf_Die *sp_die, Dwarf_Die *cu_die,
 
 	*entrypc = postprologue_addr;
 }
+
+/* Internal parameters for __die_find_scope_cb() */
+struct find_scope_data {
+	/* Target instruction address */
+	Dwarf_Addr pc;
+	/* Number of scopes found [output] */
+	int nr;
+	/* Array of scopes found, 0 for the outermost one. [output] */
+	Dwarf_Die *scopes;
+};
+
+static int __die_find_scope_cb(Dwarf_Die *die_mem, void *arg)
+{
+	struct find_scope_data *data = arg;
+
+	if (dwarf_haspc(die_mem, data->pc)) {
+		Dwarf_Die *tmp;
+
+		tmp = realloc(data->scopes, (data->nr + 1) * sizeof(*tmp));
+		if (tmp == NULL)
+			return DIE_FIND_CB_END;
+
+		memcpy(tmp + data->nr, die_mem, sizeof(*die_mem));
+		data->scopes = tmp;
+		data->nr++;
+		return DIE_FIND_CB_CHILD;
+	}
+	return DIE_FIND_CB_SIBLING;
+}
+
+/**
+ * die_get_scopes - Return a list of scopes including the address
+ * @cu_die: a compile unit DIE
+ * @pc: the address to find
+ * @scopes: the array of DIEs for scopes (result)
+ *
+ * This function does the same as the dwarf_getscopes() but doesn't follow
+ * the origins of inlined functions.  It returns the number of scopes saved
+ * in the @scopes argument.  The outer scope will be saved first (index 0) and
+ * the last one is the innermost scope at the @pc.
+ */
+int die_get_scopes(Dwarf_Die *cu_die, Dwarf_Addr pc, Dwarf_Die **scopes)
+{
+	struct find_scope_data data = {
+		.pc = pc,
+	};
+	Dwarf_Die die_mem;
+
+	die_find_child(cu_die, __die_find_scope_cb, &data, &die_mem);
+
+	*scopes = data.scopes;
+	return data.nr;
+}
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index 7ec8bc1083bb..4e64caac6df8 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -116,12 +116,14 @@ Dwarf_Die *die_find_variable_at(Dwarf_Die *sp_die, const char *name,
 Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
 			   Dwarf_Die *die_mem);
 
+/* Get the name of given type DIE */
+int die_get_typename_from_type(Dwarf_Die *type_die, struct strbuf *buf);
+
 /* Get the name of given variable DIE */
 int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf);
 
 /* Get the name and type of given variable DIE, stored as "type\tname" */
 int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf);
-int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf);
 
 /* Check if target program is compiled with optimization */
 bool die_is_optimized_target(Dwarf_Die *cu_die);
@@ -130,4 +132,49 @@ bool die_is_optimized_target(Dwarf_Die *cu_die);
 void die_skip_prologue(Dwarf_Die *sp_die, Dwarf_Die *cu_die,
 		       Dwarf_Addr *entrypc);
 
-#endif
+/* Get the list of including scopes */
+int die_get_scopes(Dwarf_Die *cu_die, Dwarf_Addr pc, Dwarf_Die **scopes);
+
+#ifdef HAVE_DWARF_GETLOCATIONS_SUPPORT
+
+/* Get byte offset range of given variable DIE */
+int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf);
+
+/* Find a variable saved in the 'reg' at given address */
+Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die, Dwarf_Addr pc, int reg,
+				    Dwarf_Die *die_mem);
+
+/* Find a (global) variable located in the 'addr' */
+Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr pc,
+				     Dwarf_Addr addr, Dwarf_Die *die_mem,
+				     int *offset);
+
+#else /*  HAVE_DWARF_GETLOCATIONS_SUPPORT */
+
+static inline int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
+				    Dwarf_Die *vr_die __maybe_unused,
+				    struct strbuf *buf __maybe_unused)
+{
+	return -ENOTSUP;
+}
+
+static inline Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die __maybe_unused,
+						  Dwarf_Addr pc __maybe_unused,
+						  int reg __maybe_unused,
+						  Dwarf_Die *die_mem __maybe_unused)
+{
+	return NULL;
+}
+
+static inline Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die __maybe_unused,
+						   Dwarf_Addr pc __maybe_unused,
+						   Dwarf_Addr addr __maybe_unused,
+						   Dwarf_Die *die_mem __maybe_unused,
+						   int *offset __maybe_unused)
+{
+	return NULL;
+}
+
+#endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
+
+#endif /* _DWARF_AUX_H */
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index 69cfaa5953bf..5b7f86c0063f 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -5,9 +5,12 @@
  * Written by: Masami Hiramatsu <mhiramat@kernel.org>
  */
 
+#include <stdlib.h>
+#include <string.h>
 #include <debug.h>
 #include <dwarf-regs.h>
 #include <elf.h>
+#include <errno.h>
 #include <linux/kernel.h>
 
 #ifndef EM_AARCH64
@@ -68,3 +71,34 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine)
 	}
 	return NULL;
 }
+
+__weak int get_arch_regnum(const char *name __maybe_unused)
+{
+	return -ENOTSUP;
+}
+
+/* Return DWARF register number from architecture register name */
+int get_dwarf_regnum(const char *name, unsigned int machine)
+{
+	char *regname = strdup(name);
+	int reg = -1;
+	char *p;
+
+	if (regname == NULL)
+		return -EINVAL;
+
+	/* For convenience, remove trailing characters */
+	p = strpbrk(regname, " ,)");
+	if (p)
+		*p = '\0';
+
+	switch (machine) {
+	case EM_NONE:	/* Generic arch - use host arch */
+		reg = get_arch_regnum(regname);
+		break;
+	default:
+		pr_err("ELF MACHINE %x is not supported.\n", machine);
+	}
+	free(regname);
+	return reg;
+}
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 44140b7f596a..a459374d0a1a 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -3,6 +3,7 @@
 #include "debug.h"
 #include "env.h"
 #include "util/header.h"
+#include "linux/compiler.h"
 #include <linux/ctype.h>
 #include <linux/zalloc.h>
 #include "cgroup.h"
@@ -12,6 +13,7 @@
 #include <string.h>
 #include "pmus.h"
 #include "strbuf.h"
+#include "trace/beauty/beauty.h"
 
 struct perf_env perf_env;
 
@@ -23,12 +25,18 @@ struct perf_env perf_env;
 void perf_env__insert_bpf_prog_info(struct perf_env *env,
 				    struct bpf_prog_info_node *info_node)
 {
+	down_write(&env->bpf_progs.lock);
+	__perf_env__insert_bpf_prog_info(env, info_node);
+	up_write(&env->bpf_progs.lock);
+}
+
+void __perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node)
+{
 	__u32 prog_id = info_node->info_linear->info.id;
 	struct bpf_prog_info_node *node;
 	struct rb_node *parent = NULL;
 	struct rb_node **p;
 
-	down_write(&env->bpf_progs.lock);
 	p = &env->bpf_progs.infos.rb_node;
 
 	while (*p != NULL) {
@@ -40,15 +48,13 @@ void perf_env__insert_bpf_prog_info(struct perf_env *env,
 			p = &(*p)->rb_right;
 		} else {
 			pr_debug("duplicated bpf prog info %u\n", prog_id);
-			goto out;
+			return;
 		}
 	}
 
 	rb_link_node(&info_node->rb_node, parent, p);
 	rb_insert_color(&info_node->rb_node, &env->bpf_progs.infos);
 	env->bpf_progs.infos_cnt++;
-out:
-	up_write(&env->bpf_progs.lock);
 }
 
 struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
@@ -78,13 +84,21 @@ out:
 
 bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
 {
+	bool ret;
+
+	down_write(&env->bpf_progs.lock);
+	ret = __perf_env__insert_btf(env, btf_node);
+	up_write(&env->bpf_progs.lock);
+	return ret;
+}
+
+bool __perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
+{
 	struct rb_node *parent = NULL;
 	__u32 btf_id = btf_node->id;
 	struct btf_node *node;
 	struct rb_node **p;
-	bool ret = true;
 
-	down_write(&env->bpf_progs.lock);
 	p = &env->bpf_progs.btfs.rb_node;
 
 	while (*p != NULL) {
@@ -96,25 +110,31 @@ bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
 			p = &(*p)->rb_right;
 		} else {
 			pr_debug("duplicated btf %u\n", btf_id);
-			ret = false;
-			goto out;
+			return false;
 		}
 	}
 
 	rb_link_node(&btf_node->rb_node, parent, p);
 	rb_insert_color(&btf_node->rb_node, &env->bpf_progs.btfs);
 	env->bpf_progs.btfs_cnt++;
-out:
-	up_write(&env->bpf_progs.lock);
-	return ret;
+	return true;
 }
 
 struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id)
 {
+	struct btf_node *res;
+
+	down_read(&env->bpf_progs.lock);
+	res = __perf_env__find_btf(env, btf_id);
+	up_read(&env->bpf_progs.lock);
+	return res;
+}
+
+struct btf_node *__perf_env__find_btf(struct perf_env *env, __u32 btf_id)
+{
 	struct btf_node *node = NULL;
 	struct rb_node *n;
 
-	down_read(&env->bpf_progs.lock);
 	n = env->bpf_progs.btfs.rb_node;
 
 	while (n) {
@@ -124,13 +144,9 @@ struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id)
 		else if (btf_id > node->id)
 			n = n->rb_right;
 		else
-			goto out;
+			return node;
 	}
-	node = NULL;
-
-out:
-	up_read(&env->bpf_progs.lock);
-	return node;
+	return NULL;
 }
 
 /* purge data in bpf_progs.infos tree */
@@ -453,6 +469,18 @@ const char *perf_env__arch(struct perf_env *env)
 	return normalize_arch(arch_name);
 }
 
+const char *perf_env__arch_strerrno(struct perf_env *env __maybe_unused, int err __maybe_unused)
+{
+#if defined(HAVE_SYSCALL_TABLE_SUPPORT) && defined(HAVE_LIBTRACEEVENT)
+	if (env->arch_strerrno == NULL)
+		env->arch_strerrno = arch_syscalls__strerrno_function(perf_env__arch(env));
+
+	return env->arch_strerrno ? env->arch_strerrno(err) : "no arch specific strerrno function";
+#else
+	return "!(HAVE_SYSCALL_TABLE_SUPPORT && HAVE_LIBTRACEEVENT)";
+#endif
+}
+
 const char *perf_env__cpuid(struct perf_env *env)
 {
 	int status;
@@ -531,6 +559,24 @@ int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu)
 	return cpu.cpu >= 0 && cpu.cpu < env->nr_numa_map ? env->numa_map[cpu.cpu] : -1;
 }
 
+bool perf_env__has_pmu_mapping(struct perf_env *env, const char *pmu_name)
+{
+	char *pmu_mapping = env->pmu_mappings, *colon;
+
+	for (int i = 0; i < env->nr_pmu_mappings; ++i) {
+		if (strtoul(pmu_mapping, &colon, 0) == ULONG_MAX || *colon != ':')
+			goto out_error;
+
+		pmu_mapping = colon + 1;
+		if (strcmp(pmu_mapping, pmu_name) == 0)
+			return true;
+
+		pmu_mapping += strlen(pmu_mapping) + 1;
+	}
+out_error:
+	return false;
+}
+
 char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name,
 			     const char *cap)
 {
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 4566c51f2fd9..7c527e65c186 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -46,10 +46,17 @@ struct hybrid_node {
 struct pmu_caps {
 	int		nr_caps;
 	unsigned int    max_branches;
+	unsigned int	br_cntr_nr;
+	unsigned int	br_cntr_width;
+
 	char            **caps;
 	char            *pmu_name;
 };
 
+typedef const char *(arch_syscalls__strerrno_t)(int err);
+
+arch_syscalls__strerrno_t *arch_syscalls__strerrno_function(const char *arch);
+
 struct perf_env {
 	char			*hostname;
 	char			*os_release;
@@ -62,6 +69,8 @@ struct perf_env {
 	unsigned long long	total_mem;
 	unsigned int		msr_pmu_type;
 	unsigned int		max_branches;
+	unsigned int		br_cntr_nr;
+	unsigned int		br_cntr_width;
 	int			kernel_is_64_bit;
 
 	int			nr_cmdline;
@@ -130,6 +139,7 @@ struct perf_env {
 		 */
 		bool	enabled;
 	} clock;
+	arch_syscalls__strerrno_t *arch_strerrno;
 };
 
 enum perf_compress_type {
@@ -159,19 +169,26 @@ int perf_env__read_cpu_topology_map(struct perf_env *env);
 void cpu_cache_level__free(struct cpu_cache_level *cache);
 
 const char *perf_env__arch(struct perf_env *env);
+const char *perf_env__arch_strerrno(struct perf_env *env, int err);
 const char *perf_env__cpuid(struct perf_env *env);
 const char *perf_env__raw_arch(struct perf_env *env);
 int perf_env__nr_cpus_avail(struct perf_env *env);
 
 void perf_env__init(struct perf_env *env);
+void __perf_env__insert_bpf_prog_info(struct perf_env *env,
+				      struct bpf_prog_info_node *info_node);
 void perf_env__insert_bpf_prog_info(struct perf_env *env,
 				    struct bpf_prog_info_node *info_node);
 struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
 							__u32 prog_id);
 bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
+bool __perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
 struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id);
+struct btf_node *__perf_env__find_btf(struct perf_env *env, __u32 btf_id);
 
 int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu);
 char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name,
 			     const char *cap);
+
+bool perf_env__has_pmu_mapping(struct perf_env *env, const char *pmu_name);
 #endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 923c0fb15122..68f45e9e63b6 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -617,13 +617,13 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
 	if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) {
 		al->level = 'k';
 		maps = machine__kernel_maps(machine);
-		load_map = true;
+		load_map = !symbol_conf.lazy_load_kernel_maps;
 	} else if (cpumode == PERF_RECORD_MISC_USER && perf_host) {
 		al->level = '.';
 	} else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) {
 		al->level = 'g';
 		maps = machine__kernel_maps(machine);
-		load_map = true;
+		load_map = !symbol_conf.lazy_load_kernel_maps;
 	} else if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest) {
 		al->level = 'u';
 	} else {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e36da58522ef..55a300a0977b 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -103,7 +103,14 @@ struct evlist *evlist__new_default(void)
 	err = parse_event(evlist, can_profile_kernel ? "cycles:P" : "cycles:Pu");
 	if (err) {
 		evlist__delete(evlist);
-		evlist = NULL;
+		return NULL;
+	}
+
+	if (evlist->core.nr_entries > 1) {
+		struct evsel *evsel;
+
+		evlist__for_each_entry(evlist, evsel)
+			evsel__set_sample_id(evsel, /*can_sample_identifier=*/false);
 	}
 
 	return evlist;
@@ -1056,7 +1063,7 @@ int evlist__create_maps(struct evlist *evlist, struct target *target)
 		return -1;
 
 	if (target__uses_dummy_map(target))
-		cpus = perf_cpu_map__dummy_new();
+		cpus = perf_cpu_map__new_any_cpu();
 	else
 		cpus = perf_cpu_map__new(target->cpu_list);
 
@@ -1352,7 +1359,7 @@ static int evlist__create_syswide_maps(struct evlist *evlist)
 	 * error, and we may not want to do that fallback to a
 	 * default cpu identity map :-\
 	 */
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus)
 		goto out;
 
@@ -2518,3 +2525,33 @@ void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_lis
 	}
 	perf_cpu_map__put(user_requested_cpus);
 }
+
+void evlist__uniquify_name(struct evlist *evlist)
+{
+	char *new_name, empty_attributes[2] = ":", *attributes;
+	struct evsel *pos;
+
+	if (perf_pmus__num_core_pmus() == 1)
+		return;
+
+	evlist__for_each_entry(evlist, pos) {
+		if (!evsel__is_hybrid(pos))
+			continue;
+
+		if (strchr(pos->name, '/'))
+			continue;
+
+		attributes = strchr(pos->name, ':');
+		if (attributes)
+			*attributes = '\0';
+		else
+			attributes = empty_attributes;
+
+		if (asprintf(&new_name, "%s/%s/%s", pos->pmu_name, pos->name, attributes + 1)) {
+			free(pos->name);
+			pos->name = new_name;
+		} else {
+			*attributes = ':';
+		}
+	}
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 98e7ddb2bd30..cb91dc9117a2 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -442,5 +442,6 @@ struct evsel *evlist__find_evsel(struct evlist *evlist, int idx);
 int evlist__scnprintf_evsels(struct evlist *evlist, size_t size, char *bf);
 void evlist__check_mem_load_aux(struct evlist *evlist);
 void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_list);
+void evlist__uniquify_name(struct evlist *evlist);
 
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 72a5dfc38d38..6d7c9c58a9bc 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1801,7 +1801,7 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
 
 	if (cpus == NULL) {
 		if (empty_cpu_map == NULL) {
-			empty_cpu_map = perf_cpu_map__dummy_new();
+			empty_cpu_map = perf_cpu_map__new_any_cpu();
 			if (empty_cpu_map == NULL)
 				return -ENOMEM;
 		}
@@ -1832,6 +1832,8 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
 
 static void evsel__disable_missing_features(struct evsel *evsel)
 {
+	if (perf_missing_features.branch_counters)
+		evsel->core.attr.branch_sample_type &= ~PERF_SAMPLE_BRANCH_COUNTERS;
 	if (perf_missing_features.read_lost)
 		evsel->core.attr.read_format &= ~PERF_FORMAT_LOST;
 	if (perf_missing_features.weight_struct) {
@@ -1885,7 +1887,12 @@ bool evsel__detect_missing_features(struct evsel *evsel)
 	 * Must probe features in the order they were added to the
 	 * perf_event_attr interface.
 	 */
-	if (!perf_missing_features.read_lost &&
+	if (!perf_missing_features.branch_counters &&
+	    (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS)) {
+		perf_missing_features.branch_counters = true;
+		pr_debug2("switching off branch counters support\n");
+		return true;
+	} else if (!perf_missing_features.read_lost &&
 	    (evsel->core.attr.read_format & PERF_FORMAT_LOST)) {
 		perf_missing_features.read_lost = true;
 		pr_debug2("switching off PERF_FORMAT_LOST support\n");
@@ -2318,6 +2325,22 @@ u64 evsel__bitfield_swap_branch_flags(u64 value)
 	return new_val;
 }
 
+static inline bool evsel__has_branch_counters(const struct evsel *evsel)
+{
+	struct evsel *cur, *leader = evsel__leader(evsel);
+
+	/* The branch counters feature only supports group */
+	if (!leader || !evsel->evlist)
+		return false;
+
+	evlist__for_each_entry(evsel->evlist, cur) {
+		if ((leader == evsel__leader(cur)) &&
+		    (cur->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS))
+			return true;
+	}
+	return false;
+}
+
 int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 			struct perf_sample *data)
 {
@@ -2551,6 +2574,16 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 
 		OVERFLOW_CHECK(array, sz, max_size);
 		array = (void *)array + sz;
+
+		if (evsel__has_branch_counters(evsel)) {
+			OVERFLOW_CHECK_u64(array);
+
+			data->branch_stack_cntr = (u64 *)array;
+			sz = data->branch_stack->nr * sizeof(u64);
+
+			OVERFLOW_CHECK(array, sz, max_size);
+			array = (void *)array + sz;
+		}
 	}
 
 	if (type & PERF_SAMPLE_REGS_USER) {
@@ -2820,7 +2853,8 @@ u64 evsel__intval_common(struct evsel *evsel, struct perf_sample *sample, const
 
 #endif
 
-bool evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize)
+bool evsel__fallback(struct evsel *evsel, struct target *target, int err,
+		     char *msg, size_t msgsize)
 {
 	int paranoid;
 
@@ -2828,18 +2862,19 @@ bool evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize)
 	    evsel->core.attr.type   == PERF_TYPE_HARDWARE &&
 	    evsel->core.attr.config == PERF_COUNT_HW_CPU_CYCLES) {
 		/*
-		 * If it's cycles then fall back to hrtimer based
-		 * cpu-clock-tick sw counter, which is always available even if
-		 * no PMU support.
+		 * If it's cycles then fall back to hrtimer based cpu-clock sw
+		 * counter, which is always available even if no PMU support.
 		 *
 		 * PPC returns ENXIO until 2.6.37 (behavior changed with commit
 		 * b0a873e).
 		 */
-		scnprintf(msg, msgsize, "%s",
-"The cycles event is not supported, trying to fall back to cpu-clock-ticks");
-
 		evsel->core.attr.type   = PERF_TYPE_SOFTWARE;
-		evsel->core.attr.config = PERF_COUNT_SW_CPU_CLOCK;
+		evsel->core.attr.config = target__has_cpu(target)
+			? PERF_COUNT_SW_CPU_CLOCK
+			: PERF_COUNT_SW_TASK_CLOCK;
+		scnprintf(msg, msgsize,
+			"The cycles event is not supported, trying to fall back to %s",
+			target__has_cpu(target) ? "cpu-clock" : "task-clock");
 
 		zfree(&evsel->name);
 		return true;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d791316a1792..efbb6e848287 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -191,6 +191,7 @@ struct perf_missing_features {
 	bool code_page_size;
 	bool weight_struct;
 	bool read_lost;
+	bool branch_counters;
 };
 
 extern struct perf_missing_features perf_missing_features;
@@ -459,7 +460,8 @@ static inline bool evsel__is_clock(const struct evsel *evsel)
 	       evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK);
 }
 
-bool evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize);
+bool evsel__fallback(struct evsel *evsel, struct target *target, int err,
+		     char *msg, size_t msgsize);
 int evsel__open_strerror(struct evsel *evsel, struct target *target,
 			 int err, char *msg, size_t size);
 
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
index fefc72066c4e..ac17a3cb59dc 100644
--- a/tools/perf/util/genelf.c
+++ b/tools/perf/util/genelf.c
@@ -293,9 +293,9 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym,
 	 */
 	phdr = elf_newphdr(e, 1);
 	phdr[0].p_type = PT_LOAD;
-	phdr[0].p_offset = 0;
-	phdr[0].p_vaddr = 0;
-	phdr[0].p_paddr = 0;
+	phdr[0].p_offset = GEN_ELF_TEXT_OFFSET;
+	phdr[0].p_vaddr = GEN_ELF_TEXT_OFFSET;
+	phdr[0].p_paddr = GEN_ELF_TEXT_OFFSET;
 	phdr[0].p_filesz = csize;
 	phdr[0].p_memsz = csize;
 	phdr[0].p_flags = PF_X | PF_R;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index e86b9439ffee..3fe28edc3d01 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1444,7 +1444,9 @@ static int build_mem_topology(struct memory_node **nodesp, u64 *cntp)
 			nodes = new_nodes;
 			size += 4;
 		}
-		ret = memory_node__read(&nodes[cnt++], idx);
+		ret = memory_node__read(&nodes[cnt], idx);
+		if (!ret)
+			cnt += 1;
 	}
 out:
 	closedir(dir);
@@ -1847,8 +1849,8 @@ static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp)
 		node = rb_entry(next, struct bpf_prog_info_node, rb_node);
 		next = rb_next(&node->rb_node);
 
-		bpf_event__print_bpf_prog_info(&node->info_linear->info,
-					       env, fp);
+		__bpf_event__print_bpf_prog_info(&node->info_linear->info,
+						 env, fp);
 	}
 
 	up_read(&env->bpf_progs.lock);
@@ -2145,6 +2147,14 @@ static void print_pmu_caps(struct feat_fd *ff, FILE *fp)
 		__print_pmu_caps(fp, pmu_caps->nr_caps, pmu_caps->caps,
 				 pmu_caps->pmu_name);
 	}
+
+	if (strcmp(perf_env__arch(&ff->ph->env), "x86") == 0 &&
+	    perf_env__has_pmu_mapping(&ff->ph->env, "ibs_op")) {
+		char *max_precise = perf_env__find_pmu_cap(&ff->ph->env, "cpu", "max_precise");
+
+		if (max_precise != NULL && atoi(max_precise) == 0)
+			fprintf(fp, "# AMD systems uses ibs_op// PMU for some precise events, e.g.: cycles:p, see the 'perf list' man page for further details.\n");
+	}
 }
 
 static void print_pmu_mappings(struct feat_fd *ff, FILE *fp)
@@ -3178,7 +3188,7 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused)
 		/* after reading from file, translate offset to address */
 		bpil_offs_to_addr(info_linear);
 		info_node->info_linear = info_linear;
-		perf_env__insert_bpf_prog_info(env, info_node);
+		__perf_env__insert_bpf_prog_info(env, info_node);
 	}
 
 	up_write(&env->bpf_progs.lock);
@@ -3225,7 +3235,7 @@ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused)
 		if (__do_read(ff, node->data, data_size))
 			goto out;
 
-		perf_env__insert_btf(env, node);
+		__perf_env__insert_btf(env, node);
 		node = NULL;
 	}
 
@@ -3259,7 +3269,9 @@ static int process_compressed(struct feat_fd *ff,
 }
 
 static int __process_pmu_caps(struct feat_fd *ff, int *nr_caps,
-			      char ***caps, unsigned int *max_branches)
+			      char ***caps, unsigned int *max_branches,
+			      unsigned int *br_cntr_nr,
+			      unsigned int *br_cntr_width)
 {
 	char *name, *value, *ptr;
 	u32 nr_pmu_caps, i;
@@ -3294,6 +3306,12 @@ static int __process_pmu_caps(struct feat_fd *ff, int *nr_caps,
 		if (!strcmp(name, "branches"))
 			*max_branches = atoi(value);
 
+		if (!strcmp(name, "branch_counter_nr"))
+			*br_cntr_nr = atoi(value);
+
+		if (!strcmp(name, "branch_counter_width"))
+			*br_cntr_width = atoi(value);
+
 		free(value);
 		free(name);
 	}
@@ -3318,7 +3336,9 @@ static int process_cpu_pmu_caps(struct feat_fd *ff,
 {
 	int ret = __process_pmu_caps(ff, &ff->ph->env.nr_cpu_pmu_caps,
 				     &ff->ph->env.cpu_pmu_caps,
-				     &ff->ph->env.max_branches);
+				     &ff->ph->env.max_branches,
+				     &ff->ph->env.br_cntr_nr,
+				     &ff->ph->env.br_cntr_width);
 
 	if (!ret && !ff->ph->env.cpu_pmu_caps)
 		pr_debug("cpu pmu capabilities not available\n");
@@ -3347,7 +3367,9 @@ static int process_pmu_caps(struct feat_fd *ff, void *data __maybe_unused)
 	for (i = 0; i < nr_pmu; i++) {
 		ret = __process_pmu_caps(ff, &pmu_caps[i].nr_caps,
 					 &pmu_caps[i].caps,
-					 &pmu_caps[i].max_branches);
+					 &pmu_caps[i].max_branches,
+					 &pmu_caps[i].br_cntr_nr,
+					 &pmu_caps[i].br_cntr_width);
 		if (ret)
 			goto err;
 
@@ -4369,9 +4391,10 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp)
 		ret += fprintf(fp, "... ");
 
 		map = cpu_map__new_data(&ev->cpus.cpus);
-		if (map)
+		if (map) {
 			ret += cpu_map__fprintf(map, fp);
-		else
+			perf_cpu_map__put(map);
+		} else
 			ret += fprintf(fp, "failed to get cpus\n");
 		break;
 	default:
diff --git a/tools/perf/util/hisi-ptt.c b/tools/perf/util/hisi-ptt.c
index 43bd1ca62d58..52d0ce302ca0 100644
--- a/tools/perf/util/hisi-ptt.c
+++ b/tools/perf/util/hisi-ptt.c
@@ -123,6 +123,7 @@ static int hisi_ptt_process_auxtrace_event(struct perf_session *session,
 	if (dump_trace)
 		hisi_ptt_dump_event(ptt, data, size);
 
+	free(data);
 	return 0;
 }
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 0888b7163b7c..fa359180ebf8 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -491,8 +491,8 @@ static int hist_entry__init(struct hist_entry *he,
 	}
 
 	if (symbol_conf.res_sample) {
-		he->res_samples = calloc(sizeof(struct res_sample),
-					symbol_conf.res_sample);
+		he->res_samples = calloc(symbol_conf.res_sample,
+					sizeof(struct res_sample));
 		if (!he->res_samples)
 			goto err_srcline;
 	}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index afc9f1c7f4dc..4a0aea0c9e00 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -82,6 +82,9 @@ enum hist_column {
 	HISTC_ADDR_TO,
 	HISTC_ADDR,
 	HISTC_SIMD,
+	HISTC_TYPE,
+	HISTC_TYPE_OFFSET,
+	HISTC_SYMBOL_OFFSET,
 	HISTC_NR_COLS, /* Last entry */
 };
 
@@ -457,7 +460,6 @@ struct hist_browser_timer {
 	int refresh;
 };
 
-struct annotation_options;
 struct res_sample;
 
 enum rstype {
@@ -473,16 +475,13 @@ struct block_hist;
 void attr_to_script(char *buf, struct perf_event_attr *attr);
 
 int map_symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
-			     struct hist_browser_timer *hbt,
-			     struct annotation_options *annotation_opts);
+			     struct hist_browser_timer *hbt);
 
 int hist_entry__tui_annotate(struct hist_entry *he, struct evsel *evsel,
-			     struct hist_browser_timer *hbt,
-			     struct annotation_options *annotation_opts);
+			     struct hist_browser_timer *hbt);
 
 int evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt,
-			     float min_pcnt, struct perf_env *env, bool warn_lost_event,
-			     struct annotation_options *annotation_options);
+			     float min_pcnt, struct perf_env *env, bool warn_lost_event);
 
 int script_browse(const char *script_opt, struct evsel *evsel);
 
@@ -492,8 +491,7 @@ int res_sample_browse(struct res_sample *res_samples, int num_res,
 void res_sample_init(void);
 
 int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel,
-			   float min_percent, struct perf_env *env,
-			   struct annotation_options *annotation_opts);
+			   float min_percent, struct perf_env *env);
 #else
 static inline
 int evlist__tui_browse_hists(struct evlist *evlist __maybe_unused,
@@ -501,23 +499,20 @@ int evlist__tui_browse_hists(struct evlist *evlist __maybe_unused,
 			     struct hist_browser_timer *hbt __maybe_unused,
 			     float min_pcnt __maybe_unused,
 			     struct perf_env *env __maybe_unused,
-			     bool warn_lost_event __maybe_unused,
-			     struct annotation_options *annotation_options __maybe_unused)
+			     bool warn_lost_event __maybe_unused)
 {
 	return 0;
 }
 static inline int map_symbol__tui_annotate(struct map_symbol *ms __maybe_unused,
 					   struct evsel *evsel __maybe_unused,
-					   struct hist_browser_timer *hbt __maybe_unused,
-					   struct annotation_options *annotation_options __maybe_unused)
+					   struct hist_browser_timer *hbt __maybe_unused)
 {
 	return 0;
 }
 
 static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused,
 					   struct evsel *evsel __maybe_unused,
-					   struct hist_browser_timer *hbt __maybe_unused,
-					   struct annotation_options *annotation_opts __maybe_unused)
+					   struct hist_browser_timer *hbt __maybe_unused)
 {
 	return 0;
 }
@@ -541,8 +536,7 @@ static inline void res_sample_init(void) {}
 static inline int block_hists_tui_browse(struct block_hist *bh __maybe_unused,
 					 struct evsel *evsel __maybe_unused,
 					 float min_percent __maybe_unused,
-					 struct perf_env *env __maybe_unused,
-					 struct annotation_options *annotation_opts __maybe_unused)
+					 struct perf_env *env __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index 7d99a084e82d..01fb25a1150a 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -2,6 +2,9 @@
 #ifndef _PERF_DWARF_REGS_H_
 #define _PERF_DWARF_REGS_H_
 
+#define DWARF_REG_PC  0xd3af9c /* random number */
+#define DWARF_REG_FB  0xd3affb /* random number */
+
 #ifdef HAVE_DWARF_SUPPORT
 const char *get_arch_regstr(unsigned int n);
 /*
@@ -10,6 +13,22 @@ const char *get_arch_regstr(unsigned int n);
  * machine: ELF machine signature (EM_*)
  */
 const char *get_dwarf_regstr(unsigned int n, unsigned int machine);
+
+int get_arch_regnum(const char *name);
+/*
+ * get_dwarf_regnum - Returns DWARF regnum from register name
+ * name: architecture register name
+ * machine: ELF machine signature (EM_*)
+ */
+int get_dwarf_regnum(const char *name, unsigned int machine);
+
+#else /* HAVE_DWARF_SUPPORT */
+
+static inline int get_dwarf_regnum(const char *name __maybe_unused,
+				   unsigned int machine __maybe_unused)
+{
+	return -1;
+}
 #endif
 
 #ifdef HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h
index 75e2248416f5..178b00205fe6 100644
--- a/tools/perf/util/include/linux/linkage.h
+++ b/tools/perf/util/include/linux/linkage.h
@@ -115,6 +115,10 @@
 	SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_WEAK)
 #endif
 
+#ifndef SYM_FUNC_ALIAS_MEMFUNC
+#define SYM_FUNC_ALIAS_MEMFUNC SYM_FUNC_ALIAS
+#endif
+
 // In the kernel sources (include/linux/cfi_types.h), this has a different
 // definition when CONFIG_CFI_CLANG is used, for tools/ just use the !clang
 // definition:
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 90c750150b19..b397a769006f 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -453,7 +453,7 @@ static struct thread *findnew_guest_code(struct machine *machine,
 	 * Guest code can be found in hypervisor process at the same address
 	 * so copy host maps.
 	 */
-	err = maps__clone(thread, thread__maps(host_thread));
+	err = maps__copy_from(thread__maps(thread), thread__maps(host_thread));
 	thread__put(host_thread);
 	if (err)
 		goto out_err;
@@ -1285,33 +1285,46 @@ static u64 find_entry_trampoline(struct dso *dso)
 #define X86_64_CPU_ENTRY_AREA_SIZE	0x2c000
 #define X86_64_ENTRY_TRAMPOLINE		0x6000
 
+struct machine__map_x86_64_entry_trampolines_args {
+	struct maps *kmaps;
+	bool found;
+};
+
+static int machine__map_x86_64_entry_trampolines_cb(struct map *map, void *data)
+{
+	struct machine__map_x86_64_entry_trampolines_args *args = data;
+	struct map *dest_map;
+	struct kmap *kmap = __map__kmap(map);
+
+	if (!kmap || !is_entry_trampoline(kmap->name))
+		return 0;
+
+	dest_map = maps__find(args->kmaps, map__pgoff(map));
+	if (dest_map != map)
+		map__set_pgoff(map, map__map_ip(dest_map, map__pgoff(map)));
+
+	args->found = true;
+	return 0;
+}
+
 /* Map x86_64 PTI entry trampolines */
 int machine__map_x86_64_entry_trampolines(struct machine *machine,
 					  struct dso *kernel)
 {
-	struct maps *kmaps = machine__kernel_maps(machine);
+	struct machine__map_x86_64_entry_trampolines_args args = {
+		.kmaps = machine__kernel_maps(machine),
+		.found = false,
+	};
 	int nr_cpus_avail, cpu;
-	bool found = false;
-	struct map_rb_node *rb_node;
 	u64 pgoff;
 
 	/*
 	 * In the vmlinux case, pgoff is a virtual address which must now be
 	 * mapped to a vmlinux offset.
 	 */
-	maps__for_each_entry(kmaps, rb_node) {
-		struct map *dest_map, *map = rb_node->map;
-		struct kmap *kmap = __map__kmap(map);
-
-		if (!kmap || !is_entry_trampoline(kmap->name))
-			continue;
+	maps__for_each_map(args.kmaps, machine__map_x86_64_entry_trampolines_cb, &args);
 
-		dest_map = maps__find(kmaps, map__pgoff(map));
-		if (dest_map != map)
-			map__set_pgoff(map, map__map_ip(dest_map, map__pgoff(map)));
-		found = true;
-	}
-	if (found || machine->trampolines_mapped)
+	if (args.found || machine->trampolines_mapped)
 		return 0;
 
 	pgoff = find_entry_trampoline(kernel);
@@ -1359,8 +1372,7 @@ __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 	if (machine->vmlinux_map == NULL)
 		return -ENOMEM;
 
-	map__set_map_ip(machine->vmlinux_map, identity__map_ip);
-	map__set_unmap_ip(machine->vmlinux_map, identity__map_ip);
+	map__set_mapping_type(machine->vmlinux_map, MAPPING_TYPE__IDENTITY);
 	return maps__insert(machine__kernel_maps(machine), machine->vmlinux_map);
 }
 
@@ -1750,12 +1762,11 @@ int machine__create_kernel_maps(struct machine *machine)
 
 	if (end == ~0ULL) {
 		/* update end address of the kernel map using adjacent module address */
-		struct map_rb_node *rb_node = maps__find_node(machine__kernel_maps(machine),
-							machine__kernel_map(machine));
-		struct map_rb_node *next = map_rb_node__next(rb_node);
+		struct map *next = maps__find_next_entry(machine__kernel_maps(machine),
+							 machine__kernel_map(machine));
 
 		if (next)
-			machine__set_kernel_mmap(machine, start, map__start(next->map));
+			machine__set_kernel_mmap(machine, start, map__start(next));
 	}
 
 out_put:
@@ -2157,9 +2168,13 @@ int machine__process_exit_event(struct machine *machine, union perf_event *event
 	if (dump_trace)
 		perf_event__fprintf_task(event, stdout);
 
-	if (thread != NULL)
-		thread__put(thread);
-
+	if (thread != NULL) {
+		if (symbol_conf.keep_exited_threads)
+			thread__set_exited(thread, /*exited=*/true);
+		else
+			machine__remove_thread(machine, thread);
+	}
+	thread__put(thread);
 	return 0;
 }
 
@@ -3395,16 +3410,8 @@ int machine__for_each_dso(struct machine *machine, machine__dso_t fn, void *priv
 int machine__for_each_kernel_map(struct machine *machine, machine__map_t fn, void *priv)
 {
 	struct maps *maps = machine__kernel_maps(machine);
-	struct map_rb_node *pos;
-	int err = 0;
 
-	maps__for_each_entry(maps, pos) {
-		err = fn(pos->map, priv);
-		if (err != 0) {
-			break;
-		}
-	}
-	return err;
+	return maps__for_each_map(maps, fn, priv);
 }
 
 bool machine__is_lock_function(struct machine *machine, u64 addr)
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index f64b83004421..54c67cb7ecef 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -109,8 +109,7 @@ void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso)
 	map__set_pgoff(map, pgoff);
 	map__set_reloc(map, 0);
 	map__set_dso(map, dso__get(dso));
-	map__set_map_ip(map, map__dso_map_ip);
-	map__set_unmap_ip(map, map__dso_unmap_ip);
+	map__set_mapping_type(map, MAPPING_TYPE__DSO);
 	map__set_erange_warned(map, false);
 	refcount_set(map__refcnt(map), 1);
 }
@@ -172,7 +171,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 		map__init(result, start, start + len, pgoff, dso);
 
 		if (anon || no_dso) {
-			map->map_ip = map->unmap_ip = identity__map_ip;
+			map->mapping_type = MAPPING_TYPE__IDENTITY;
 
 			/*
 			 * Set memory without DSO as loaded. All map__find_*
@@ -630,18 +629,3 @@ struct maps *map__kmaps(struct map *map)
 	}
 	return kmap->kmaps;
 }
-
-u64 map__dso_map_ip(const struct map *map, u64 ip)
-{
-	return ip - map__start(map) + map__pgoff(map);
-}
-
-u64 map__dso_unmap_ip(const struct map *map, u64 ip)
-{
-	return ip + map__start(map) - map__pgoff(map);
-}
-
-u64 identity__map_ip(const struct map *map __maybe_unused, u64 ip)
-{
-	return ip;
-}
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 1b53d53adc86..49756716cb13 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -16,23 +16,25 @@ struct dso;
 struct maps;
 struct machine;
 
+enum mapping_type {
+	/* map__map_ip/map__unmap_ip are given as offsets in the DSO. */
+	MAPPING_TYPE__DSO,
+	/* map__map_ip/map__unmap_ip are just the given ip value. */
+	MAPPING_TYPE__IDENTITY,
+};
+
 DECLARE_RC_STRUCT(map) {
 	u64			start;
 	u64			end;
-	bool			erange_warned:1;
-	bool			priv:1;
-	u32			prot;
 	u64			pgoff;
 	u64			reloc;
-
-	/* ip -> dso rip */
-	u64			(*map_ip)(const struct map *, u64);
-	/* dso rip -> ip */
-	u64			(*unmap_ip)(const struct map *, u64);
-
 	struct dso		*dso;
 	refcount_t		refcnt;
+	u32			prot;
 	u32			flags;
+	enum mapping_type	mapping_type:8;
+	bool			erange_warned;
+	bool			priv;
 };
 
 struct kmap;
@@ -41,38 +43,11 @@ struct kmap *__map__kmap(struct map *map);
 struct kmap *map__kmap(struct map *map);
 struct maps *map__kmaps(struct map *map);
 
-/* ip -> dso rip */
-u64 map__dso_map_ip(const struct map *map, u64 ip);
-/* dso rip -> ip */
-u64 map__dso_unmap_ip(const struct map *map, u64 ip);
-/* Returns ip */
-u64 identity__map_ip(const struct map *map __maybe_unused, u64 ip);
-
 static inline struct dso *map__dso(const struct map *map)
 {
 	return RC_CHK_ACCESS(map)->dso;
 }
 
-static inline u64 map__map_ip(const struct map *map, u64 ip)
-{
-	return RC_CHK_ACCESS(map)->map_ip(map, ip);
-}
-
-static inline u64 map__unmap_ip(const struct map *map, u64 ip)
-{
-	return RC_CHK_ACCESS(map)->unmap_ip(map, ip);
-}
-
-static inline void *map__map_ip_ptr(struct map *map)
-{
-	return RC_CHK_ACCESS(map)->map_ip;
-}
-
-static inline void* map__unmap_ip_ptr(struct map *map)
-{
-	return RC_CHK_ACCESS(map)->unmap_ip;
-}
-
 static inline u64 map__start(const struct map *map)
 {
 	return RC_CHK_ACCESS(map)->start;
@@ -123,6 +98,34 @@ static inline size_t map__size(const struct map *map)
 	return map__end(map) - map__start(map);
 }
 
+/* ip -> dso rip */
+static inline u64 map__dso_map_ip(const struct map *map, u64 ip)
+{
+	return ip - map__start(map) + map__pgoff(map);
+}
+
+/* dso rip -> ip */
+static inline u64 map__dso_unmap_ip(const struct map *map, u64 rip)
+{
+	return rip + map__start(map) - map__pgoff(map);
+}
+
+static inline u64 map__map_ip(const struct map *map, u64 ip_or_rip)
+{
+	if ((RC_CHK_ACCESS(map)->mapping_type) == MAPPING_TYPE__DSO)
+		return map__dso_map_ip(map, ip_or_rip);
+	else
+		return ip_or_rip;
+}
+
+static inline u64 map__unmap_ip(const struct map *map, u64 ip_or_rip)
+{
+	if ((RC_CHK_ACCESS(map)->mapping_type) == MAPPING_TYPE__DSO)
+		return map__dso_unmap_ip(map, ip_or_rip);
+	else
+		return ip_or_rip;
+}
+
 /* rip/ip <-> addr suitable for passing to `objdump --start-address=` */
 u64 map__rip_2objdump(struct map *map, u64 rip);
 
@@ -294,13 +297,13 @@ static inline void map__set_dso(struct map *map, struct dso *dso)
 	RC_CHK_ACCESS(map)->dso = dso;
 }
 
-static inline void map__set_map_ip(struct map *map, u64 (*map_ip)(const struct map *map, u64 ip))
+static inline void map__set_mapping_type(struct map *map, enum mapping_type type)
 {
-	RC_CHK_ACCESS(map)->map_ip = map_ip;
+	RC_CHK_ACCESS(map)->mapping_type = type;
 }
 
-static inline void map__set_unmap_ip(struct map *map, u64 (*unmap_ip)(const struct map *map, u64 rip))
+static inline enum mapping_type map__mapping_type(struct map *map)
 {
-	RC_CHK_ACCESS(map)->unmap_ip = unmap_ip;
+	return RC_CHK_ACCESS(map)->mapping_type;
 }
 #endif /* __PERF_MAP_H */
diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
index 233438c95b53..0334fc18d9c6 100644
--- a/tools/perf/util/maps.c
+++ b/tools/perf/util/maps.c
@@ -10,6 +10,68 @@
 #include "ui/ui.h"
 #include "unwind.h"
 
+struct map_rb_node {
+	struct rb_node rb_node;
+	struct map *map;
+};
+
+#define maps__for_each_entry(maps, map) \
+	for (map = maps__first(maps); map; map = map_rb_node__next(map))
+
+#define maps__for_each_entry_safe(maps, map, next) \
+	for (map = maps__first(maps), next = map_rb_node__next(map); map; \
+	     map = next, next = map_rb_node__next(map))
+
+static struct rb_root *maps__entries(struct maps *maps)
+{
+	return &RC_CHK_ACCESS(maps)->entries;
+}
+
+static struct rw_semaphore *maps__lock(struct maps *maps)
+{
+	return &RC_CHK_ACCESS(maps)->lock;
+}
+
+static struct map **maps__maps_by_name(struct maps *maps)
+{
+	return RC_CHK_ACCESS(maps)->maps_by_name;
+}
+
+static struct map_rb_node *maps__first(struct maps *maps)
+{
+	struct rb_node *first = rb_first(maps__entries(maps));
+
+	if (first)
+		return rb_entry(first, struct map_rb_node, rb_node);
+	return NULL;
+}
+
+static struct map_rb_node *map_rb_node__next(struct map_rb_node *node)
+{
+	struct rb_node *next;
+
+	if (!node)
+		return NULL;
+
+	next = rb_next(&node->rb_node);
+
+	if (!next)
+		return NULL;
+
+	return rb_entry(next, struct map_rb_node, rb_node);
+}
+
+static struct map_rb_node *maps__find_node(struct maps *maps, struct map *map)
+{
+	struct map_rb_node *rb_node;
+
+	maps__for_each_entry(maps, rb_node) {
+		if (rb_node->RC_CHK_ACCESS(map) == RC_CHK_ACCESS(map))
+			return rb_node;
+	}
+	return NULL;
+}
+
 static void maps__init(struct maps *maps, struct machine *machine)
 {
 	refcount_set(maps__refcnt(maps), 1);
@@ -196,6 +258,41 @@ void maps__put(struct maps *maps)
 		RC_CHK_PUT(maps);
 }
 
+int maps__for_each_map(struct maps *maps, int (*cb)(struct map *map, void *data), void *data)
+{
+	struct map_rb_node *pos;
+	int ret = 0;
+
+	down_read(maps__lock(maps));
+	maps__for_each_entry(maps, pos)	{
+		ret = cb(pos->map, data);
+		if (ret)
+			break;
+	}
+	up_read(maps__lock(maps));
+	return ret;
+}
+
+void maps__remove_maps(struct maps *maps, bool (*cb)(struct map *map, void *data), void *data)
+{
+	struct map_rb_node *pos, *next;
+	unsigned int start_nr_maps;
+
+	down_write(maps__lock(maps));
+
+	start_nr_maps = maps__nr_maps(maps);
+	maps__for_each_entry_safe(maps, pos, next)	{
+		if (cb(pos->map, data)) {
+			__maps__remove(maps, pos);
+			--RC_CHK_ACCESS(maps)->nr_maps;
+		}
+	}
+	if (maps__maps_by_name(maps) && start_nr_maps != maps__nr_maps(maps))
+		__maps__free_maps_by_name(maps);
+
+	up_write(maps__lock(maps));
+}
+
 struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp)
 {
 	struct map *map = maps__find(maps, addr);
@@ -210,31 +307,40 @@ struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp)
 	return NULL;
 }
 
-struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp)
-{
+struct maps__find_symbol_by_name_args {
+	struct map **mapp;
+	const char *name;
 	struct symbol *sym;
-	struct map_rb_node *pos;
+};
 
-	down_read(maps__lock(maps));
+static int maps__find_symbol_by_name_cb(struct map *map, void *data)
+{
+	struct maps__find_symbol_by_name_args *args = data;
 
-	maps__for_each_entry(maps, pos) {
-		sym = map__find_symbol_by_name(pos->map, name);
+	args->sym = map__find_symbol_by_name(map, args->name);
+	if (!args->sym)
+		return 0;
 
-		if (sym == NULL)
-			continue;
-		if (!map__contains_symbol(pos->map, sym)) {
-			sym = NULL;
-			continue;
-		}
-		if (mapp != NULL)
-			*mapp = pos->map;
-		goto out;
+	if (!map__contains_symbol(map, args->sym)) {
+		args->sym = NULL;
+		return 0;
 	}
 
-	sym = NULL;
-out:
-	up_read(maps__lock(maps));
-	return sym;
+	if (args->mapp != NULL)
+		*args->mapp = map__get(map);
+	return 1;
+}
+
+struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp)
+{
+	struct maps__find_symbol_by_name_args args = {
+		.mapp = mapp,
+		.name = name,
+		.sym = NULL,
+	};
+
+	maps__for_each_map(maps, maps__find_symbol_by_name_cb, &args);
+	return args.sym;
 }
 
 int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams)
@@ -253,41 +359,46 @@ int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams)
 	return ams->ms.sym ? 0 : -1;
 }
 
-size_t maps__fprintf(struct maps *maps, FILE *fp)
-{
-	size_t printed = 0;
-	struct map_rb_node *pos;
+struct maps__fprintf_args {
+	FILE *fp;
+	size_t printed;
+};
 
-	down_read(maps__lock(maps));
+static int maps__fprintf_cb(struct map *map, void *data)
+{
+	struct maps__fprintf_args *args = data;
 
-	maps__for_each_entry(maps, pos) {
-		printed += fprintf(fp, "Map:");
-		printed += map__fprintf(pos->map, fp);
-		if (verbose > 2) {
-			printed += dso__fprintf(map__dso(pos->map), fp);
-			printed += fprintf(fp, "--\n");
-		}
+	args->printed += fprintf(args->fp, "Map:");
+	args->printed += map__fprintf(map, args->fp);
+	if (verbose > 2) {
+		args->printed += dso__fprintf(map__dso(map), args->fp);
+		args->printed += fprintf(args->fp, "--\n");
 	}
+	return 0;
+}
 
-	up_read(maps__lock(maps));
+size_t maps__fprintf(struct maps *maps, FILE *fp)
+{
+	struct maps__fprintf_args args = {
+		.fp = fp,
+		.printed = 0,
+	};
+
+	maps__for_each_map(maps, maps__fprintf_cb, &args);
 
-	return printed;
+	return args.printed;
 }
 
-int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
+/*
+ * Find first map where end > map->start.
+ * Same as find_vma() in kernel.
+ */
+static struct rb_node *first_ending_after(struct maps *maps, const struct map *map)
 {
 	struct rb_root *root;
 	struct rb_node *next, *first;
-	int err = 0;
-
-	down_write(maps__lock(maps));
 
 	root = maps__entries(maps);
-
-	/*
-	 * Find first map where end > map->start.
-	 * Same as find_vma() in kernel.
-	 */
 	next = root->rb_node;
 	first = NULL;
 	while (next) {
@@ -301,8 +412,23 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
 		} else
 			next = next->rb_right;
 	}
+	return first;
+}
 
-	next = first;
+/*
+ * Adds new to maps, if new overlaps existing entries then the existing maps are
+ * adjusted or removed so that new fits without overlapping any entries.
+ */
+int maps__fixup_overlap_and_insert(struct maps *maps, struct map *new)
+{
+
+	struct rb_node *next;
+	int err = 0;
+	FILE *fp = debug_file();
+
+	down_write(maps__lock(maps));
+
+	next = first_ending_after(maps, new);
 	while (next && !err) {
 		struct map_rb_node *pos = rb_entry(next, struct map_rb_node, rb_node);
 		next = rb_next(&pos->rb_node);
@@ -311,27 +437,27 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
 		 * Stop if current map starts after map->end.
 		 * Maps are ordered by start: next will not overlap for sure.
 		 */
-		if (map__start(pos->map) >= map__end(map))
+		if (map__start(pos->map) >= map__end(new))
 			break;
 
 		if (verbose >= 2) {
 
 			if (use_browser) {
 				pr_debug("overlapping maps in %s (disable tui for more info)\n",
-					 map__dso(map)->name);
+					 map__dso(new)->name);
 			} else {
-				fputs("overlapping maps:\n", fp);
-				map__fprintf(map, fp);
+				pr_debug("overlapping maps:\n");
+				map__fprintf(new, fp);
 				map__fprintf(pos->map, fp);
 			}
 		}
 
-		rb_erase_init(&pos->rb_node, root);
+		rb_erase_init(&pos->rb_node, maps__entries(maps));
 		/*
 		 * Now check if we need to create new maps for areas not
 		 * overlapped by the new map:
 		 */
-		if (map__start(map) > map__start(pos->map)) {
+		if (map__start(new) > map__start(pos->map)) {
 			struct map *before = map__clone(pos->map);
 
 			if (before == NULL) {
@@ -339,7 +465,7 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
 				goto put_map;
 			}
 
-			map__set_end(before, map__start(map));
+			map__set_end(before, map__start(new));
 			err = __maps__insert(maps, before);
 			if (err) {
 				map__put(before);
@@ -351,7 +477,7 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
 			map__put(before);
 		}
 
-		if (map__end(map) < map__end(pos->map)) {
+		if (map__end(new) < map__end(pos->map)) {
 			struct map *after = map__clone(pos->map);
 
 			if (after == NULL) {
@@ -359,10 +485,10 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
 				goto put_map;
 			}
 
-			map__set_start(after, map__end(map));
-			map__add_pgoff(after, map__end(map) - map__start(pos->map));
-			assert(map__map_ip(pos->map, map__end(map)) ==
-				map__map_ip(after, map__end(map)));
+			map__set_start(after, map__end(new));
+			map__add_pgoff(after, map__end(new) - map__start(pos->map));
+			assert(map__map_ip(pos->map, map__end(new)) ==
+				map__map_ip(after, map__end(new)));
 			err = __maps__insert(maps, after);
 			if (err) {
 				map__put(after);
@@ -376,16 +502,14 @@ put_map:
 		map__put(pos->map);
 		free(pos);
 	}
+	/* Add the map. */
+	err = __maps__insert(maps, new);
 	up_write(maps__lock(maps));
 	return err;
 }
 
-/*
- * XXX This should not really _copy_ te maps, but refcount them.
- */
-int maps__clone(struct thread *thread, struct maps *parent)
+int maps__copy_from(struct maps *maps, struct maps *parent)
 {
-	struct maps *maps = thread__maps(thread);
 	int err;
 	struct map_rb_node *rb_node;
 
@@ -416,17 +540,6 @@ out_unlock:
 	return err;
 }
 
-struct map_rb_node *maps__find_node(struct maps *maps, struct map *map)
-{
-	struct map_rb_node *rb_node;
-
-	maps__for_each_entry(maps, rb_node) {
-		if (rb_node->RC_CHK_ACCESS(map) == RC_CHK_ACCESS(map))
-			return rb_node;
-	}
-	return NULL;
-}
-
 struct map *maps__find(struct maps *maps, u64 ip)
 {
 	struct rb_node *p;
@@ -452,26 +565,275 @@ out:
 	return m ? m->map : NULL;
 }
 
-struct map_rb_node *maps__first(struct maps *maps)
+static int map__strcmp(const void *a, const void *b)
 {
-	struct rb_node *first = rb_first(maps__entries(maps));
+	const struct map *map_a = *(const struct map **)a;
+	const struct map *map_b = *(const struct map **)b;
+	const struct dso *dso_a = map__dso(map_a);
+	const struct dso *dso_b = map__dso(map_b);
+	int ret = strcmp(dso_a->short_name, dso_b->short_name);
 
-	if (first)
-		return rb_entry(first, struct map_rb_node, rb_node);
-	return NULL;
+	if (ret == 0 && map_a != map_b) {
+		/*
+		 * Ensure distinct but name equal maps have an order in part to
+		 * aid reference counting.
+		 */
+		ret = (int)map__start(map_a) - (int)map__start(map_b);
+		if (ret == 0)
+			ret = (int)((intptr_t)map_a - (intptr_t)map_b);
+	}
+
+	return ret;
 }
 
-struct map_rb_node *map_rb_node__next(struct map_rb_node *node)
+static int map__strcmp_name(const void *name, const void *b)
 {
-	struct rb_node *next;
+	const struct dso *dso = map__dso(*(const struct map **)b);
 
-	if (!node)
-		return NULL;
+	return strcmp(name, dso->short_name);
+}
 
-	next = rb_next(&node->rb_node);
+void __maps__sort_by_name(struct maps *maps)
+{
+	qsort(maps__maps_by_name(maps), maps__nr_maps(maps), sizeof(struct map *), map__strcmp);
+}
 
-	if (!next)
+static int map__groups__sort_by_name_from_rbtree(struct maps *maps)
+{
+	struct map_rb_node *rb_node;
+	struct map **maps_by_name = realloc(maps__maps_by_name(maps),
+					    maps__nr_maps(maps) * sizeof(struct map *));
+	int i = 0;
+
+	if (maps_by_name == NULL)
+		return -1;
+
+	up_read(maps__lock(maps));
+	down_write(maps__lock(maps));
+
+	RC_CHK_ACCESS(maps)->maps_by_name = maps_by_name;
+	RC_CHK_ACCESS(maps)->nr_maps_allocated = maps__nr_maps(maps);
+
+	maps__for_each_entry(maps, rb_node)
+		maps_by_name[i++] = map__get(rb_node->map);
+
+	__maps__sort_by_name(maps);
+
+	up_write(maps__lock(maps));
+	down_read(maps__lock(maps));
+
+	return 0;
+}
+
+static struct map *__maps__find_by_name(struct maps *maps, const char *name)
+{
+	struct map **mapp;
+
+	if (maps__maps_by_name(maps) == NULL &&
+	    map__groups__sort_by_name_from_rbtree(maps))
 		return NULL;
 
-	return rb_entry(next, struct map_rb_node, rb_node);
+	mapp = bsearch(name, maps__maps_by_name(maps), maps__nr_maps(maps),
+		       sizeof(*mapp), map__strcmp_name);
+	if (mapp)
+		return *mapp;
+	return NULL;
+}
+
+struct map *maps__find_by_name(struct maps *maps, const char *name)
+{
+	struct map_rb_node *rb_node;
+	struct map *map;
+
+	down_read(maps__lock(maps));
+
+
+	if (RC_CHK_ACCESS(maps)->last_search_by_name) {
+		const struct dso *dso = map__dso(RC_CHK_ACCESS(maps)->last_search_by_name);
+
+		if (strcmp(dso->short_name, name) == 0) {
+			map = RC_CHK_ACCESS(maps)->last_search_by_name;
+			goto out_unlock;
+		}
+	}
+	/*
+	 * If we have maps->maps_by_name, then the name isn't in the rbtree,
+	 * as maps->maps_by_name mirrors the rbtree when lookups by name are
+	 * made.
+	 */
+	map = __maps__find_by_name(maps, name);
+	if (map || maps__maps_by_name(maps) != NULL)
+		goto out_unlock;
+
+	/* Fallback to traversing the rbtree... */
+	maps__for_each_entry(maps, rb_node) {
+		struct dso *dso;
+
+		map = rb_node->map;
+		dso = map__dso(map);
+		if (strcmp(dso->short_name, name) == 0) {
+			RC_CHK_ACCESS(maps)->last_search_by_name = map;
+			goto out_unlock;
+		}
+	}
+	map = NULL;
+
+out_unlock:
+	up_read(maps__lock(maps));
+	return map;
+}
+
+struct map *maps__find_next_entry(struct maps *maps, struct map *map)
+{
+	struct map_rb_node *rb_node = maps__find_node(maps, map);
+	struct map_rb_node *next = map_rb_node__next(rb_node);
+
+	if (next)
+		return next->map;
+
+	return NULL;
+}
+
+void maps__fixup_end(struct maps *maps)
+{
+	struct map_rb_node *prev = NULL, *curr;
+
+	down_write(maps__lock(maps));
+
+	maps__for_each_entry(maps, curr) {
+		if (prev && (!map__end(prev->map) || map__end(prev->map) > map__start(curr->map)))
+			map__set_end(prev->map, map__start(curr->map));
+
+		prev = curr;
+	}
+
+	/*
+	 * We still haven't the actual symbols, so guess the
+	 * last map final address.
+	 */
+	if (curr && !map__end(curr->map))
+		map__set_end(curr->map, ~0ULL);
+
+	up_write(maps__lock(maps));
+}
+
+/*
+ * Merges map into maps by splitting the new map within the existing map
+ * regions.
+ */
+int maps__merge_in(struct maps *kmaps, struct map *new_map)
+{
+	struct map_rb_node *rb_node;
+	struct rb_node *first;
+	bool overlaps;
+	LIST_HEAD(merged);
+	int err = 0;
+
+	down_read(maps__lock(kmaps));
+	first = first_ending_after(kmaps, new_map);
+	rb_node = first ? rb_entry(first, struct map_rb_node, rb_node) : NULL;
+	overlaps = rb_node && map__start(rb_node->map) < map__end(new_map);
+	up_read(maps__lock(kmaps));
+
+	if (!overlaps)
+		return maps__insert(kmaps, new_map);
+
+	maps__for_each_entry(kmaps, rb_node) {
+		struct map *old_map = rb_node->map;
+
+		/* no overload with this one */
+		if (map__end(new_map) < map__start(old_map) ||
+		    map__start(new_map) >= map__end(old_map))
+			continue;
+
+		if (map__start(new_map) < map__start(old_map)) {
+			/*
+			 * |new......
+			 *       |old....
+			 */
+			if (map__end(new_map) < map__end(old_map)) {
+				/*
+				 * |new......|     -> |new..|
+				 *       |old....| ->       |old....|
+				 */
+				map__set_end(new_map, map__start(old_map));
+			} else {
+				/*
+				 * |new.............| -> |new..|       |new..|
+				 *       |old....|    ->       |old....|
+				 */
+				struct map_list_node *m = map_list_node__new();
+
+				if (!m) {
+					err = -ENOMEM;
+					goto out;
+				}
+
+				m->map = map__clone(new_map);
+				if (!m->map) {
+					free(m);
+					err = -ENOMEM;
+					goto out;
+				}
+
+				map__set_end(m->map, map__start(old_map));
+				list_add_tail(&m->node, &merged);
+				map__add_pgoff(new_map, map__end(old_map) - map__start(new_map));
+				map__set_start(new_map, map__end(old_map));
+			}
+		} else {
+			/*
+			 *      |new......
+			 * |old....
+			 */
+			if (map__end(new_map) < map__end(old_map)) {
+				/*
+				 *      |new..|   -> x
+				 * |old.........| -> |old.........|
+				 */
+				map__put(new_map);
+				new_map = NULL;
+				break;
+			} else {
+				/*
+				 *      |new......| ->         |new...|
+				 * |old....|        -> |old....|
+				 */
+				map__add_pgoff(new_map, map__end(old_map) - map__start(new_map));
+				map__set_start(new_map, map__end(old_map));
+			}
+		}
+	}
+
+out:
+	while (!list_empty(&merged)) {
+		struct map_list_node *old_node;
+
+		old_node = list_entry(merged.next, struct map_list_node, node);
+		list_del_init(&old_node->node);
+		if (!err)
+			err = maps__insert(kmaps, old_node->map);
+		map__put(old_node->map);
+		free(old_node);
+	}
+
+	if (new_map) {
+		if (!err)
+			err = maps__insert(kmaps, new_map);
+		map__put(new_map);
+	}
+	return err;
+}
+
+void maps__load_first(struct maps *maps)
+{
+	struct map_rb_node *first;
+
+	down_read(maps__lock(maps));
+
+	first = maps__first(maps);
+	if (first)
+		map__load(first->map);
+
+	up_read(maps__lock(maps));
 }
diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h
index 83144e0645ed..d836d04c9402 100644
--- a/tools/perf/util/maps.h
+++ b/tools/perf/util/maps.h
@@ -14,24 +14,18 @@ struct ref_reloc_sym;
 struct machine;
 struct map;
 struct maps;
-struct thread;
 
-struct map_rb_node {
-	struct rb_node rb_node;
+struct map_list_node {
+	struct list_head node;
 	struct map *map;
 };
 
-struct map_rb_node *maps__first(struct maps *maps);
-struct map_rb_node *map_rb_node__next(struct map_rb_node *node);
-struct map_rb_node *maps__find_node(struct maps *maps, struct map *map);
-struct map *maps__find(struct maps *maps, u64 addr);
-
-#define maps__for_each_entry(maps, map) \
-	for (map = maps__first(maps); map; map = map_rb_node__next(map))
+static inline struct map_list_node *map_list_node__new(void)
+{
+	return malloc(sizeof(struct map_list_node));
+}
 
-#define maps__for_each_entry_safe(maps, map, next) \
-	for (map = maps__first(maps), next = map_rb_node__next(map); map; \
-	     map = next, next = map_rb_node__next(map))
+struct map *maps__find(struct maps *maps, u64 addr);
 
 DECLARE_RC_STRUCT(maps) {
 	struct rb_root      entries;
@@ -58,7 +52,7 @@ struct kmap {
 
 struct maps *maps__new(struct machine *machine);
 bool maps__empty(struct maps *maps);
-int maps__clone(struct thread *thread, struct maps *parent);
+int maps__copy_from(struct maps *maps, struct maps *parent);
 
 struct maps *maps__get(struct maps *maps);
 void maps__put(struct maps *maps);
@@ -71,26 +65,16 @@ static inline void __maps__zput(struct maps **map)
 
 #define maps__zput(map) __maps__zput(&map)
 
-static inline struct rb_root *maps__entries(struct maps *maps)
-{
-	return &RC_CHK_ACCESS(maps)->entries;
-}
+/* Iterate over map calling cb for each entry. */
+int maps__for_each_map(struct maps *maps, int (*cb)(struct map *map, void *data), void *data);
+/* Iterate over map removing an entry if cb returns true. */
+void maps__remove_maps(struct maps *maps, bool (*cb)(struct map *map, void *data), void *data);
 
 static inline struct machine *maps__machine(struct maps *maps)
 {
 	return RC_CHK_ACCESS(maps)->machine;
 }
 
-static inline struct rw_semaphore *maps__lock(struct maps *maps)
-{
-	return &RC_CHK_ACCESS(maps)->lock;
-}
-
-static inline struct map **maps__maps_by_name(struct maps *maps)
-{
-	return RC_CHK_ACCESS(maps)->maps_by_name;
-}
-
 static inline unsigned int maps__nr_maps(const struct maps *maps)
 {
 	return RC_CHK_ACCESS(maps)->nr_maps;
@@ -125,12 +109,18 @@ struct addr_map_symbol;
 
 int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams);
 
-int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp);
+int maps__fixup_overlap_and_insert(struct maps *maps, struct map *new);
 
 struct map *maps__find_by_name(struct maps *maps, const char *name);
 
+struct map *maps__find_next_entry(struct maps *maps, struct map *map);
+
 int maps__merge_in(struct maps *kmaps, struct map *new_map);
 
 void __maps__sort_by_name(struct maps *maps);
 
+void maps__fixup_end(struct maps *maps);
+
+void maps__load_first(struct maps *maps);
+
 #endif // __PERF_MAPS_H
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 954b235e12e5..3a2e3687878c 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -100,11 +100,14 @@ int perf_mem_events__parse(const char *str)
 	return -1;
 }
 
-static bool perf_mem_event__supported(const char *mnt, char *sysfs_name)
+static bool perf_mem_event__supported(const char *mnt, struct perf_pmu *pmu,
+				      struct perf_mem_event *e)
 {
+	char sysfs_name[100];
 	char path[PATH_MAX];
 	struct stat st;
 
+	scnprintf(sysfs_name, sizeof(sysfs_name), e->sysfs_name, pmu->name);
 	scnprintf(path, PATH_MAX, "%s/devices/%s", mnt, sysfs_name);
 	return !stat(path, &st);
 }
@@ -120,7 +123,6 @@ int perf_mem_events__init(void)
 
 	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
 		struct perf_mem_event *e = perf_mem_events__ptr(j);
-		char sysfs_name[100];
 		struct perf_pmu *pmu = NULL;
 
 		/*
@@ -136,12 +138,12 @@ int perf_mem_events__init(void)
 		 * of core PMU.
 		 */
 		while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-			scnprintf(sysfs_name, sizeof(sysfs_name), e->sysfs_name, pmu->name);
-			e->supported |= perf_mem_event__supported(mnt, sysfs_name);
+			e->supported |= perf_mem_event__supported(mnt, pmu, e);
+			if (e->supported) {
+				found = true;
+				break;
+			}
 		}
-
-		if (e->supported)
-			found = true;
 	}
 
 	return found ? 0 : -ENOENT;
@@ -167,13 +169,10 @@ static void perf_mem_events__print_unsupport_hybrid(struct perf_mem_event *e,
 						    int idx)
 {
 	const char *mnt = sysfs__mount();
-	char sysfs_name[100];
 	struct perf_pmu *pmu = NULL;
 
 	while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-		scnprintf(sysfs_name, sizeof(sysfs_name), e->sysfs_name,
-			  pmu->name);
-		if (!perf_mem_event__supported(mnt, sysfs_name)) {
+		if (!perf_mem_event__supported(mnt, pmu, e)) {
 			pr_err("failed: event '%s' not supported\n",
 			       perf_mem_events__name(idx, pmu->name));
 		}
@@ -183,6 +182,7 @@ static void perf_mem_events__print_unsupport_hybrid(struct perf_mem_event *e,
 int perf_mem_events__record_args(const char **rec_argv, int *argv_nr,
 				 char **rec_tmp, int *tmp_nr)
 {
+	const char *mnt = sysfs__mount();
 	int i = *argv_nr, k = 0;
 	struct perf_mem_event *e;
 
@@ -211,6 +211,9 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr,
 			while ((pmu = perf_pmus__scan(pmu)) != NULL) {
 				const char *s = perf_mem_events__name(j, pmu->name);
 
+				if (!perf_mem_event__supported(mnt, pmu, e))
+					continue;
+
 				rec_argv[i++] = "-e";
 				if (s) {
 					char *copy = strdup(s);
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index ca3e0404f187..966cca5a3e88 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -286,7 +286,7 @@ static int setup_metric_events(const char *pmu, struct hashmap *ids,
 	*out_metric_events = NULL;
 	ids_size = hashmap__size(ids);
 
-	metric_events = calloc(sizeof(void *), ids_size + 1);
+	metric_events = calloc(ids_size + 1, sizeof(void *));
 	if (!metric_events)
 		return -ENOMEM;
 
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 49093b21ee2d..122ee198a86e 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -295,15 +295,14 @@ int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, struct perf_cpu
 
 	map->core.flush = mp->flush;
 
-	map->comp_level = mp->comp_level;
 #ifndef PYTHON_PERF
-	if (zstd_init(&map->zstd_data, map->comp_level)) {
+	if (zstd_init(&map->zstd_data, mp->comp_level)) {
 		pr_debug2("failed to init mmap compressor, error %d\n", errno);
 		return -1;
 	}
 #endif
 
-	if (map->comp_level && !perf_mmap__aio_enabled(map)) {
+	if (mp->comp_level && !perf_mmap__aio_enabled(map)) {
 		map->data = mmap(NULL, mmap__mmap_len(map), PROT_READ|PROT_WRITE,
 				 MAP_PRIVATE|MAP_ANONYMOUS, 0, 0);
 		if (map->data == MAP_FAILED) {
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index f944c3cd5efa..0df6e1621c7e 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -39,7 +39,6 @@ struct mmap {
 #endif
 	struct mmap_cpu_mask	affinity_mask;
 	void		*data;
-	int		comp_level;
 	struct perf_data_file *file;
 	struct zstd_data      zstd_data;
 };
diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c
index fd67d204d720..f7f7aff3d85a 100644
--- a/tools/perf/util/parse-branch-options.c
+++ b/tools/perf/util/parse-branch-options.c
@@ -36,6 +36,7 @@ static const struct branch_mode branch_modes[] = {
 	BRANCH_OPT("stack", PERF_SAMPLE_BRANCH_CALL_STACK),
 	BRANCH_OPT("hw_index", PERF_SAMPLE_BRANCH_HW_INDEX),
 	BRANCH_OPT("priv", PERF_SAMPLE_BRANCH_PRIV_SAVE),
+	BRANCH_OPT("counter", PERF_SAMPLE_BRANCH_COUNTERS),
 	BRANCH_END
 };
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index aa2f5c6fc7fc..66eabcea4242 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -976,7 +976,7 @@ static int config_term_pmu(struct perf_event_attr *attr,
 			   struct parse_events_error *err)
 {
 	if (term->type_term == PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE) {
-		const struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type);
+		struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type);
 
 		if (!pmu) {
 			char *err_str;
@@ -986,15 +986,23 @@ static int config_term_pmu(struct perf_event_attr *attr,
 							   err_str, /*help=*/NULL);
 			return -EINVAL;
 		}
-		if (perf_pmu__supports_legacy_cache(pmu)) {
+		/*
+		 * Rewrite the PMU event to a legacy cache one unless the PMU
+		 * doesn't support legacy cache events or the event is present
+		 * within the PMU.
+		 */
+		if (perf_pmu__supports_legacy_cache(pmu) &&
+		    !perf_pmu__have_event(pmu, term->config)) {
 			attr->type = PERF_TYPE_HW_CACHE;
 			return parse_events__decode_legacy_cache(term->config, pmu->type,
 								 &attr->config);
-		} else
+		} else {
 			term->type_term = PARSE_EVENTS__TERM_TYPE_USER;
+			term->no_value = true;
+		}
 	}
 	if (term->type_term == PARSE_EVENTS__TERM_TYPE_HARDWARE) {
-		const struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type);
+		struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type);
 
 		if (!pmu) {
 			char *err_str;
@@ -1004,10 +1012,19 @@ static int config_term_pmu(struct perf_event_attr *attr,
 							   err_str, /*help=*/NULL);
 			return -EINVAL;
 		}
-		attr->type = PERF_TYPE_HARDWARE;
-		attr->config = term->val.num;
-		if (perf_pmus__supports_extended_type())
-			attr->config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT;
+		/*
+		 * If the PMU has a sysfs or json event prefer it over
+		 * legacy. ARM requires this.
+		 */
+		if (perf_pmu__have_event(pmu, term->config)) {
+			term->type_term = PARSE_EVENTS__TERM_TYPE_USER;
+			term->no_value = true;
+		} else {
+			attr->type = PERF_TYPE_HARDWARE;
+			attr->config = term->val.num;
+			if (perf_pmus__supports_extended_type())
+				attr->config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT;
+		}
 		return 0;
 	}
 	if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER ||
@@ -1381,6 +1398,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 	YYLTYPE *loc = loc_;
 	LIST_HEAD(config_terms);
 	struct parse_events_terms parsed_terms;
+	bool alias_rewrote_terms = false;
 
 	pmu = parse_state->fake_pmu ?: perf_pmus__find(name);
 
@@ -1433,7 +1451,15 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 		return evsel ? 0 : -ENOMEM;
 	}
 
-	if (!parse_state->fake_pmu && perf_pmu__check_alias(pmu, &parsed_terms, &info, err)) {
+	/* Configure attr/terms with a known PMU, this will set hardcoded terms. */
+	if (config_attr(&attr, &parsed_terms, parse_state->error, config_term_pmu)) {
+		parse_events_terms__exit(&parsed_terms);
+		return -EINVAL;
+	}
+
+	/* Look for event names in the terms and rewrite into format based terms. */
+	if (!parse_state->fake_pmu && perf_pmu__check_alias(pmu, &parsed_terms,
+							    &info, &alias_rewrote_terms, err)) {
 		parse_events_terms__exit(&parsed_terms);
 		return -EINVAL;
 	}
@@ -1447,11 +1473,9 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 		strbuf_release(&sb);
 	}
 
-	/*
-	 * Configure hardcoded terms first, no need to check
-	 * return value when called with fail == 0 ;)
-	 */
-	if (config_attr(&attr, &parsed_terms, parse_state->error, config_term_pmu)) {
+	/* Configure attr/terms again if an alias was expanded. */
+	if (alias_rewrote_terms &&
+	    config_attr(&attr, &parsed_terms, parse_state->error, config_term_pmu)) {
 		parse_events_terms__exit(&parsed_terms);
 		return -EINVAL;
 	}
diff --git a/tools/perf/util/perf_api_probe.c b/tools/perf/util/perf_api_probe.c
index e1e2d701599c..1de3b69cdf4a 100644
--- a/tools/perf/util/perf_api_probe.c
+++ b/tools/perf/util/perf_api_probe.c
@@ -64,7 +64,7 @@ static bool perf_probe_api(setup_probe_fn_t fn)
 	struct perf_cpu cpu;
 	int ret, i = 0;
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus)
 		return false;
 	cpu = perf_cpu_map__cpu(cpus, 0);
@@ -140,7 +140,7 @@ bool perf_can_record_cpu_wide(void)
 	struct perf_cpu cpu;
 	int fd;
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus)
 		return false;
 
diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c
index 2247991451f3..8f04d3b7f3ec 100644
--- a/tools/perf/util/perf_event_attr_fprintf.c
+++ b/tools/perf/util/perf_event_attr_fprintf.c
@@ -55,6 +55,7 @@ static void __p_branch_sample_type(char *buf, size_t size, u64 value)
 		bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP),
 		bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES),
 		bit_name(TYPE_SAVE), bit_name(HW_INDEX), bit_name(PRIV_SAVE),
+		bit_name(COUNTERS),
 		{ .name = NULL, }
 	};
 #undef bit_name
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index d3c9aa4326be..3c9609944a2f 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1494,12 +1494,14 @@ static int check_info_data(struct perf_pmu *pmu,
  * defined for the alias
  */
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_terms,
-			  struct perf_pmu_info *info, struct parse_events_error *err)
+			  struct perf_pmu_info *info, bool *rewrote_terms,
+			  struct parse_events_error *err)
 {
 	struct parse_events_term *term, *h;
 	struct perf_pmu_alias *alias;
 	int ret;
 
+	*rewrote_terms = false;
 	info->per_pkg = false;
 
 	/*
@@ -1521,7 +1523,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_
 						NULL);
 			return ret;
 		}
-
+		*rewrote_terms = true;
 		ret = check_info_data(pmu, alias, info, err, term->err_term);
 		if (ret)
 			return ret;
@@ -1615,6 +1617,8 @@ bool perf_pmu__auto_merge_stats(const struct perf_pmu *pmu)
 
 bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name)
 {
+	if (!name)
+		return false;
 	if (perf_pmu__find_alias(pmu, name, /*load=*/ true) != NULL)
 		return true;
 	if (pmu->cpu_aliases_added || !pmu->events_table)
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index d2895d415f08..424c3fee0949 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -201,7 +201,8 @@ int perf_pmu__config_terms(const struct perf_pmu *pmu,
 __u64 perf_pmu__format_bits(struct perf_pmu *pmu, const char *name);
 int perf_pmu__format_type(struct perf_pmu *pmu, const char *name);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_terms,
-			  struct perf_pmu_info *info, struct parse_events_error *err);
+			  struct perf_pmu_info *info, bool *rewrote_terms,
+			  struct parse_events_error *err);
 int perf_pmu__find_event(struct perf_pmu *pmu, const char *event, void *state, pmu_event_callback cb);
 
 int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd, bool eager_load);
diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c
index b0fc48be623f..9e47712507cc 100644
--- a/tools/perf/util/print-events.c
+++ b/tools/perf/util/print-events.c
@@ -66,7 +66,7 @@ void print_tracepoint_events(const struct print_callbacks *print_cb __maybe_unus
 
 	put_tracing_file(events_path);
 	if (events_fd < 0) {
-		printf("Error: failed to open tracing events directory\n");
+		pr_err("Error: failed to open tracing events directory\n");
 		return;
 	}
 
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 1a5b7fa459b2..a1a796043691 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -149,10 +149,32 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr,
 	return 0;
 }
 
+struct kernel_get_module_map_cb_args {
+	const char *module;
+	struct map *result;
+};
+
+static int kernel_get_module_map_cb(struct map *map, void *data)
+{
+	struct kernel_get_module_map_cb_args *args = data;
+	struct dso *dso = map__dso(map);
+	const char *short_name = dso->short_name; /* short_name is "[module]" */
+	u16 short_name_len =  dso->short_name_len;
+
+	if (strncmp(short_name + 1, args->module, short_name_len - 2) == 0 &&
+	    args->module[short_name_len - 2] == '\0') {
+		args->result = map__get(map);
+		return 1;
+	}
+	return 0;
+}
+
 static struct map *kernel_get_module_map(const char *module)
 {
-	struct maps *maps = machine__kernel_maps(host_machine);
-	struct map_rb_node *pos;
+	struct kernel_get_module_map_cb_args args = {
+		.module = module,
+		.result = NULL,
+	};
 
 	/* A file path -- this is an offline module */
 	if (module && strchr(module, '/'))
@@ -164,19 +186,9 @@ static struct map *kernel_get_module_map(const char *module)
 		return map__get(map);
 	}
 
-	maps__for_each_entry(maps, pos) {
-		/* short_name is "[module]" */
-		struct dso *dso = map__dso(pos->map);
-		const char *short_name = dso->short_name;
-		u16 short_name_len =  dso->short_name_len;
+	maps__for_each_map(machine__kernel_maps(host_machine), kernel_get_module_map_cb, &args);
 
-		if (strncmp(short_name + 1, module,
-			    short_name_len - 2) == 0 &&
-		    module[short_name_len - 2] == '\0') {
-			return map__get(pos->map);
-		}
-	}
-	return NULL;
+	return args.result;
 }
 
 struct map *get_target_map(const char *target, struct nsinfo *nsi, bool user)
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index f171360b0ef4..c8923375e30d 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -23,6 +23,7 @@
 #include "event.h"
 #include "dso.h"
 #include "debug.h"
+#include "debuginfo.h"
 #include "intlist.h"
 #include "strbuf.h"
 #include "strlist.h"
@@ -31,128 +32,9 @@
 #include "probe-file.h"
 #include "string2.h"
 
-#ifdef HAVE_DEBUGINFOD_SUPPORT
-#include <elfutils/debuginfod.h>
-#endif
-
 /* Kprobe tracer basic type is up to u64 */
 #define MAX_BASIC_TYPE_BITS	64
 
-/* Dwarf FL wrappers */
-static char *debuginfo_path;	/* Currently dummy */
-
-static const Dwfl_Callbacks offline_callbacks = {
-	.find_debuginfo = dwfl_standard_find_debuginfo,
-	.debuginfo_path = &debuginfo_path,
-
-	.section_address = dwfl_offline_section_address,
-
-	/* We use this table for core files too.  */
-	.find_elf = dwfl_build_id_find_elf,
-};
-
-/* Get a Dwarf from offline image */
-static int debuginfo__init_offline_dwarf(struct debuginfo *dbg,
-					 const char *path)
-{
-	GElf_Addr dummy;
-	int fd;
-
-	fd = open(path, O_RDONLY);
-	if (fd < 0)
-		return fd;
-
-	dbg->dwfl = dwfl_begin(&offline_callbacks);
-	if (!dbg->dwfl)
-		goto error;
-
-	dwfl_report_begin(dbg->dwfl);
-	dbg->mod = dwfl_report_offline(dbg->dwfl, "", "", fd);
-	if (!dbg->mod)
-		goto error;
-
-	dbg->dbg = dwfl_module_getdwarf(dbg->mod, &dbg->bias);
-	if (!dbg->dbg)
-		goto error;
-
-	dwfl_module_build_id(dbg->mod, &dbg->build_id, &dummy);
-
-	dwfl_report_end(dbg->dwfl, NULL, NULL);
-
-	return 0;
-error:
-	if (dbg->dwfl)
-		dwfl_end(dbg->dwfl);
-	else
-		close(fd);
-	memset(dbg, 0, sizeof(*dbg));
-
-	return -ENOENT;
-}
-
-static struct debuginfo *__debuginfo__new(const char *path)
-{
-	struct debuginfo *dbg = zalloc(sizeof(*dbg));
-	if (!dbg)
-		return NULL;
-
-	if (debuginfo__init_offline_dwarf(dbg, path) < 0)
-		zfree(&dbg);
-	if (dbg)
-		pr_debug("Open Debuginfo file: %s\n", path);
-	return dbg;
-}
-
-enum dso_binary_type distro_dwarf_types[] = {
-	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
-	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
-	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
-	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
-	DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO,
-	DSO_BINARY_TYPE__NOT_FOUND,
-};
-
-struct debuginfo *debuginfo__new(const char *path)
-{
-	enum dso_binary_type *type;
-	char buf[PATH_MAX], nil = '\0';
-	struct dso *dso;
-	struct debuginfo *dinfo = NULL;
-	struct build_id bid;
-
-	/* Try to open distro debuginfo files */
-	dso = dso__new(path);
-	if (!dso)
-		goto out;
-
-	/* Set the build id for DSO_BINARY_TYPE__BUILDID_DEBUGINFO */
-	if (is_regular_file(path) && filename__read_build_id(path, &bid) > 0)
-		dso__set_build_id(dso, &bid);
-
-	for (type = distro_dwarf_types;
-	     !dinfo && *type != DSO_BINARY_TYPE__NOT_FOUND;
-	     type++) {
-		if (dso__read_binary_type_filename(dso, *type, &nil,
-						   buf, PATH_MAX) < 0)
-			continue;
-		dinfo = __debuginfo__new(buf);
-	}
-	dso__put(dso);
-
-out:
-	/* if failed to open all distro debuginfo, open given binary */
-	return dinfo ? : __debuginfo__new(path);
-}
-
-void debuginfo__delete(struct debuginfo *dbg)
-{
-	if (dbg) {
-		if (dbg->dwfl)
-			dwfl_end(dbg->dwfl);
-		free(dbg);
-	}
-}
-
 /*
  * Probe finder related functions
  */
@@ -722,7 +604,7 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 	ret = dwarf_getlocation_addr(&fb_attr, pf->addr, &pf->fb_ops, &nops, 1);
 	if (ret <= 0 || nops == 0) {
 		pf->fb_ops = NULL;
-#if _ELFUTILS_PREREQ(0, 142)
+#ifdef HAVE_DWARF_CFI_SUPPORT
 	} else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa &&
 		   (pf->cfi_eh != NULL || pf->cfi_dbg != NULL)) {
 		if ((dwarf_cfi_addrframe(pf->cfi_eh, pf->addr, &frame) != 0 &&
@@ -733,7 +615,7 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 			free(frame);
 			return -ENOENT;
 		}
-#endif
+#endif /* HAVE_DWARF_CFI_SUPPORT */
 	}
 
 	/* Call finder's callback handler */
@@ -1258,7 +1140,7 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 
 	pf->machine = ehdr.e_machine;
 
-#if _ELFUTILS_PREREQ(0, 142)
+#ifdef HAVE_DWARF_CFI_SUPPORT
 	do {
 		GElf_Shdr shdr;
 
@@ -1268,7 +1150,7 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 
 		pf->cfi_dbg = dwarf_getcfi(dbg->dbg);
 	} while (0);
-#endif
+#endif /* HAVE_DWARF_CFI_SUPPORT */
 
 	ret = debuginfo__find_probe_location(dbg, pf);
 	return ret;
@@ -1677,44 +1559,6 @@ int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 	return (ret < 0) ? ret : af.nvls;
 }
 
-/* For the kernel module, we need a special code to get a DIE */
-int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
-				bool adjust_offset)
-{
-	int n, i;
-	Elf32_Word shndx;
-	Elf_Scn *scn;
-	Elf *elf;
-	GElf_Shdr mem, *shdr;
-	const char *p;
-
-	elf = dwfl_module_getelf(dbg->mod, &dbg->bias);
-	if (!elf)
-		return -EINVAL;
-
-	/* Get the number of relocations */
-	n = dwfl_module_relocations(dbg->mod);
-	if (n < 0)
-		return -ENOENT;
-	/* Search the relocation related .text section */
-	for (i = 0; i < n; i++) {
-		p = dwfl_module_relocation_info(dbg->mod, i, &shndx);
-		if (strcmp(p, ".text") == 0) {
-			/* OK, get the section header */
-			scn = elf_getscn(elf, shndx);
-			if (!scn)
-				return -ENOENT;
-			shdr = gelf_getshdr(scn, &mem);
-			if (!shdr)
-				return -ENOENT;
-			*offs = shdr->sh_addr;
-			if (adjust_offset)
-				*offs -= shdr->sh_offset;
-		}
-	}
-	return 0;
-}
-
 /* Reverse search */
 int debuginfo__find_probe_point(struct debuginfo *dbg, u64 addr,
 				struct perf_probe_point *ppt)
@@ -2009,41 +1853,6 @@ found:
 	return (ret < 0) ? ret : lf.found;
 }
 
-#ifdef HAVE_DEBUGINFOD_SUPPORT
-/* debuginfod doesn't require the comp_dir but buildid is required */
-static int get_source_from_debuginfod(const char *raw_path,
-				const char *sbuild_id, char **new_path)
-{
-	debuginfod_client *c = debuginfod_begin();
-	const char *p = raw_path;
-	int fd;
-
-	if (!c)
-		return -ENOMEM;
-
-	fd = debuginfod_find_source(c, (const unsigned char *)sbuild_id,
-				0, p, new_path);
-	pr_debug("Search %s from debuginfod -> %d\n", p, fd);
-	if (fd >= 0)
-		close(fd);
-	debuginfod_end(c);
-	if (fd < 0) {
-		pr_debug("Failed to find %s in debuginfod (%s)\n",
-			raw_path, sbuild_id);
-		return -ENOENT;
-	}
-	pr_debug("Got a source %s\n", *new_path);
-
-	return 0;
-}
-#else
-static inline int get_source_from_debuginfod(const char *raw_path __maybe_unused,
-				const char *sbuild_id __maybe_unused,
-				char **new_path __maybe_unused)
-{
-	return -ENOTSUP;
-}
-#endif
 /*
  * Find a src file from a DWARF tag path. Prepend optional source path prefix
  * and chop off leading directories that do not exist. Result is passed back as
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 8bc1c80d3c1c..3add5ff516e1 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -24,21 +24,7 @@ static inline int is_c_varname(const char *name)
 #ifdef HAVE_DWARF_SUPPORT
 
 #include "dwarf-aux.h"
-
-/* TODO: export debuginfo data structure even if no dwarf support */
-
-/* debug information structure */
-struct debuginfo {
-	Dwarf		*dbg;
-	Dwfl_Module	*mod;
-	Dwfl		*dwfl;
-	Dwarf_Addr	bias;
-	const unsigned char	*build_id;
-};
-
-/* This also tries to open distro debuginfo */
-struct debuginfo *debuginfo__new(const char *path);
-void debuginfo__delete(struct debuginfo *dbg);
+#include "debuginfo.h"
 
 /* Find probe_trace_events specified by perf_probe_event from debuginfo */
 int debuginfo__find_trace_events(struct debuginfo *dbg,
@@ -49,9 +35,6 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 int debuginfo__find_probe_point(struct debuginfo *dbg, u64 addr,
 				struct perf_probe_point *ppt);
 
-int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
-			       bool adjust_offset);
-
 /* Find a line range */
 int debuginfo__find_line_range(struct debuginfo *dbg, struct line_range *lr);
 
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 9eb5c6a08999..87e817b3cf7e 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -237,8 +237,8 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str)
 
 	evsel = evlist__last(temp_evlist);
 
-	if (!evlist || perf_cpu_map__empty(evlist->core.user_requested_cpus)) {
-		struct perf_cpu_map *cpus = perf_cpu_map__new(NULL);
+	if (!evlist || perf_cpu_map__has_any_cpu_or_is_empty(evlist->core.user_requested_cpus)) {
+		struct perf_cpu_map *cpus = perf_cpu_map__new_online_cpus();
 
 		if (cpus)
 			cpu =  perf_cpu_map__cpu(cpus, 0);
diff --git a/tools/perf/util/s390-cpumcf-kernel.h b/tools/perf/util/s390-cpumcf-kernel.h
index f55ca07f3ca1..74b36644e384 100644
--- a/tools/perf/util/s390-cpumcf-kernel.h
+++ b/tools/perf/util/s390-cpumcf-kernel.h
@@ -12,6 +12,8 @@
 #define	S390_CPUMCF_DIAG_DEF	0xfeef	/* Counter diagnostic entry ID */
 #define	PERF_EVENT_CPUM_CF_DIAG	0xBC000	/* Event: Counter sets */
 #define PERF_EVENT_CPUM_SF_DIAG	0xBD000 /* Event: Combined-sampling */
+#define PERF_EVENT_PAI_CRYPTO_ALL	0x1000 /* Event: CRYPTO_ALL */
+#define PERF_EVENT_PAI_NNPA_ALL	0x1800 /* Event: NNPA_ALL */
 
 struct cf_ctrset_entry {	/* CPU-M CF counter set entry (8 byte) */
 	unsigned int def:16;	/* 0-15  Data Entry Format */
diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c
index 115b16edb451..53383e97ec9d 100644
--- a/tools/perf/util/s390-sample-raw.c
+++ b/tools/perf/util/s390-sample-raw.c
@@ -51,8 +51,6 @@ static bool s390_cpumcfdg_testctr(struct perf_sample *sample)
 	struct cf_trailer_entry *te;
 	struct cf_ctrset_entry *cep, ce;
 
-	if (!len)
-		return false;
 	while (offset < len) {
 		cep = (struct cf_ctrset_entry *)(buf + offset);
 		ce.def = be16_to_cpu(cep->def);
@@ -125,6 +123,9 @@ static int get_counterset_start(int setnr)
 		return 128;
 	case CPUMF_CTR_SET_MT_DIAG:		/* Diagnostic counter set */
 		return 448;
+	case PERF_EVENT_PAI_NNPA_ALL:		/* PAI NNPA counter set */
+	case PERF_EVENT_PAI_CRYPTO_ALL:		/* PAI CRYPTO counter set */
+		return setnr;
 	default:
 		return -1;
 	}
@@ -212,27 +213,120 @@ static void s390_cpumcfdg_dump(struct perf_pmu *pmu, struct perf_sample *sample)
 	}
 }
 
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wpacked"
+#pragma GCC diagnostic ignored "-Wattributes"
+/*
+ * Check for consistency of PAI_CRYPTO/PAI_NNPA raw data.
+ */
+struct pai_data {		/* Event number and value */
+	u16 event_nr;
+	u64 event_val;
+} __packed;
+
+#pragma GCC diagnostic pop
+
+/*
+ * Test for valid raw data. At least one PAI event should be in the raw
+ * data section.
+ */
+static bool s390_pai_all_test(struct perf_sample *sample)
+{
+	size_t len = sample->raw_size;
+
+	if (len < 0xa)
+		return false;
+	return true;
+}
+
+static void s390_pai_all_dump(struct evsel *evsel, struct perf_sample *sample)
+{
+	size_t len = sample->raw_size, offset = 0;
+	unsigned char *p = sample->raw_data;
+	const char *color = PERF_COLOR_BLUE;
+	struct pai_data pai_data;
+	char *ev_name;
+
+	while (offset < len) {
+		memcpy(&pai_data.event_nr, p, sizeof(pai_data.event_nr));
+		pai_data.event_nr = be16_to_cpu(pai_data.event_nr);
+		p += sizeof(pai_data.event_nr);
+		offset += sizeof(pai_data.event_nr);
+
+		memcpy(&pai_data.event_val, p, sizeof(pai_data.event_val));
+		pai_data.event_val = be64_to_cpu(pai_data.event_val);
+		p += sizeof(pai_data.event_val);
+		offset += sizeof(pai_data.event_val);
+
+		ev_name = get_counter_name(evsel->core.attr.config,
+					   pai_data.event_nr, evsel->pmu);
+		color_fprintf(stdout, color, "\tCounter:%03d %s Value:%#018lx\n",
+			      pai_data.event_nr, ev_name ?: "<unknown>",
+			      pai_data.event_val);
+		free(ev_name);
+
+		if (offset + 0xa > len)
+			break;
+	}
+	color_fprintf(stdout, color, "\n");
+}
+
 /* S390 specific trace event function. Check for PERF_RECORD_SAMPLE events
- * and if the event was triggered by a counter set diagnostic event display
- * its raw data.
+ * and if the event was triggered by a
+ * - counter set diagnostic event
+ * - processor activity assist (PAI) crypto counter event
+ * - processor activity assist (PAI) neural network processor assist (NNPA)
+ *   counter event
+ * display its raw data.
  * The function is only invoked when the dump flag -D is set.
+ *
+ * Function evlist__s390_sample_raw() is defined as call back after it has
+ * been verified that the perf.data file was created on s390 platform.
  */
-void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, struct perf_sample *sample)
+void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event,
+			     struct perf_sample *sample)
 {
+	const char *pai_name;
 	struct evsel *evsel;
 
 	if (event->header.type != PERF_RECORD_SAMPLE)
 		return;
 
 	evsel = evlist__event2evsel(evlist, event);
-	if (evsel == NULL ||
-	    evsel->core.attr.config != PERF_EVENT_CPUM_CF_DIAG)
+	if (!evsel)
+		return;
+
+	/* Check for raw data in sample */
+	if (!sample->raw_size || !sample->raw_data)
 		return;
 
 	/* Display raw data on screen */
-	if (!s390_cpumcfdg_testctr(sample)) {
-		pr_err("Invalid counter set data encountered\n");
+	if (evsel->core.attr.config == PERF_EVENT_CPUM_CF_DIAG) {
+		if (!evsel->pmu)
+			evsel->pmu = perf_pmus__find("cpum_cf");
+		if (!s390_cpumcfdg_testctr(sample))
+			pr_err("Invalid counter set data encountered\n");
+		else
+			s390_cpumcfdg_dump(evsel->pmu, sample);
+		return;
+	}
+
+	switch (evsel->core.attr.config) {
+	case PERF_EVENT_PAI_NNPA_ALL:
+		pai_name = "NNPA_ALL";
+		break;
+	case PERF_EVENT_PAI_CRYPTO_ALL:
+		pai_name = "CRYPTO_ALL";
+		break;
+	default:
 		return;
 	}
-	s390_cpumcfdg_dump(evsel->pmu, sample);
+
+	if (!s390_pai_all_test(sample)) {
+		pr_err("Invalid %s raw data encountered\n", pai_name);
+	} else {
+		if (!evsel->pmu)
+			evsel->pmu = perf_pmus__find_by_type(evsel->core.attr.type);
+		s390_pai_all_dump(evsel, sample);
+	}
 }
diff --git a/tools/perf/util/sample.h b/tools/perf/util/sample.h
index c92ad0f51ecd..70b2c3135555 100644
--- a/tools/perf/util/sample.h
+++ b/tools/perf/util/sample.h
@@ -113,6 +113,7 @@ struct perf_sample {
 	void *raw_data;
 	struct ip_callchain *callchain;
 	struct branch_stack *branch_stack;
+	u64 *branch_stack_cntr;
 	struct regs_dump  user_regs;
 	struct regs_dump  intr_regs;
 	struct stack_dump user_stack;
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 603091317bed..b072ac5d3bc2 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -490,6 +490,9 @@ static int perl_start_script(const char *script, int argc, const char **argv,
 	scripting_context->session = session;
 
 	command_line = malloc((argc + 2) * sizeof(const char *));
+	if (!command_line)
+		return -ENOMEM;
+
 	command_line[0] = "";
 	command_line[1] = script;
 	for (i = 2; i < argc + 2; i++)
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 94312741443a..860e1837ba96 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -353,6 +353,8 @@ static PyObject *get_field_numeric_entry(struct tep_event *event,
 
 	if (is_array) {
 		list = PyList_New(field->arraylen);
+		if (!list)
+			Py_FatalError("couldn't create Python list");
 		item_size = field->size / field->arraylen;
 		n_items = field->arraylen;
 	} else {
@@ -754,7 +756,7 @@ static void regs_map(struct regs_dump *regs, uint64_t mask, const char *arch, ch
 	}
 }
 
-static void set_regs_in_dict(PyObject *dict,
+static int set_regs_in_dict(PyObject *dict,
 			     struct perf_sample *sample,
 			     struct evsel *evsel)
 {
@@ -770,6 +772,8 @@ static void set_regs_in_dict(PyObject *dict,
 	 */
 	int size = __sw_hweight64(attr->sample_regs_intr) * 28;
 	char *bf = malloc(size);
+	if (!bf)
+		return -1;
 
 	regs_map(&sample->intr_regs, attr->sample_regs_intr, arch, bf, size);
 
@@ -781,6 +785,8 @@ static void set_regs_in_dict(PyObject *dict,
 	pydict_set_item_string_decref(dict, "uregs",
 			_PyUnicode_FromString(bf));
 	free(bf);
+
+	return 0;
 }
 
 static void set_sym_in_dict(PyObject *dict, struct addr_location *al,
@@ -920,7 +926,8 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
 			PyLong_FromUnsignedLongLong(sample->cyc_cnt));
 	}
 
-	set_regs_in_dict(dict, sample, evsel);
+	if (set_regs_in_dict(dict, sample, evsel))
+		Py_FatalError("Failed to setting regs in dict");
 
 	return dict;
 }
@@ -1918,12 +1925,18 @@ static int python_start_script(const char *script, int argc, const char **argv,
 	scripting_context->session = session;
 #if PY_MAJOR_VERSION < 3
 	command_line = malloc((argc + 1) * sizeof(const char *));
+	if (!command_line)
+		return -1;
+
 	command_line[0] = script;
 	for (i = 1; i < argc + 1; i++)
 		command_line[i] = argv[i - 1];
 	PyImport_AppendInittab(name, initperf_trace_context);
 #else
 	command_line = malloc((argc + 1) * sizeof(wchar_t *));
+	if (!command_line)
+		return -1;
+
 	command_line[0] = Py_DecodeLocale(script, NULL);
 	for (i = 1; i < argc + 1; i++)
 		command_line[i] = Py_DecodeLocale(argv[i - 1], NULL);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 1e9aa8ed15b6..199d3e8df315 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -115,6 +115,11 @@ static int perf_session__open(struct perf_session *session, int repipe_fd)
 		return -1;
 	}
 
+	if (perf_header__has_feat(&session->header, HEADER_AUXTRACE)) {
+		/* Auxiliary events may reference exited threads, hold onto dead ones. */
+		symbol_conf.keep_exited_threads = true;
+	}
+
 	if (perf_data__is_pipe(data))
 		return 0;
 
@@ -1150,9 +1155,13 @@ static void callchain__printf(struct evsel *evsel,
 		       i, callchain->ips[i]);
 }
 
-static void branch_stack__printf(struct perf_sample *sample, bool callstack)
+static void branch_stack__printf(struct perf_sample *sample,
+				 struct evsel *evsel)
 {
 	struct branch_entry *entries = perf_sample__branch_entries(sample);
+	bool callstack = evsel__has_branch_callstack(evsel);
+	u64 *branch_stack_cntr = sample->branch_stack_cntr;
+	struct perf_env *env = evsel__env(evsel);
 	uint64_t i;
 
 	if (!callstack) {
@@ -1194,6 +1203,13 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 			}
 		}
 	}
+
+	if (branch_stack_cntr) {
+		printf("... branch stack counters: nr:%" PRIu64 " (counter width: %u max counter nr:%u)\n",
+			sample->branch_stack->nr, env->br_cntr_width, env->br_cntr_nr);
+		for (i = 0; i < sample->branch_stack->nr; i++)
+			printf("..... %2"PRIu64": %016" PRIx64 "\n", i, branch_stack_cntr[i]);
+	}
 }
 
 static void regs_dump__printf(u64 mask, u64 *regs, const char *arch)
@@ -1355,7 +1371,7 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
 		callchain__printf(evsel, sample);
 
 	if (evsel__has_br_stack(evsel))
-		branch_stack__printf(sample, evsel__has_branch_callstack(evsel));
+		branch_stack__printf(sample, evsel);
 
 	if (sample_type & PERF_SAMPLE_REGS_USER)
 		regs_user__printf(sample, arch);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 80e4f6132740..30254eb63709 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -24,6 +24,7 @@
 #include "strbuf.h"
 #include "mem-events.h"
 #include "annotate.h"
+#include "annotate-data.h"
 #include "event.h"
 #include "time-utils.h"
 #include "cgroup.h"
@@ -418,6 +419,52 @@ struct sort_entry sort_sym = {
 	.se_width_idx	= HISTC_SYMBOL,
 };
 
+/* --sort symoff */
+
+static int64_t
+sort__symoff_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	int64_t ret;
+
+	ret = sort__sym_cmp(left, right);
+	if (ret)
+		return ret;
+
+	return left->ip - right->ip;
+}
+
+static int64_t
+sort__symoff_sort(struct hist_entry *left, struct hist_entry *right)
+{
+	int64_t ret;
+
+	ret = sort__sym_sort(left, right);
+	if (ret)
+		return ret;
+
+	return left->ip - right->ip;
+}
+
+static int
+hist_entry__symoff_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width)
+{
+	struct symbol *sym = he->ms.sym;
+
+	if (sym == NULL)
+		return repsep_snprintf(bf, size, "[%c] %-#.*llx", he->level, width - 4, he->ip);
+
+	return repsep_snprintf(bf, size, "[%c] %s+0x%llx", he->level, sym->name, he->ip - sym->start);
+}
+
+struct sort_entry sort_sym_offset = {
+	.se_header	= "Symbol Offset",
+	.se_cmp		= sort__symoff_cmp,
+	.se_sort	= sort__symoff_sort,
+	.se_snprintf	= hist_entry__symoff_snprintf,
+	.se_filter	= hist_entry__sym_filter,
+	.se_width_idx	= HISTC_SYMBOL_OFFSET,
+};
+
 /* --sort srcline */
 
 char *hist_entry__srcline(struct hist_entry *he)
@@ -583,21 +630,21 @@ static int hist_entry__sym_ipc_snprintf(struct hist_entry *he, char *bf,
 {
 
 	struct symbol *sym = he->ms.sym;
-	struct annotation *notes;
+	struct annotated_branch *branch;
 	double ipc = 0.0, coverage = 0.0;
 	char tmp[64];
 
 	if (!sym)
 		return repsep_snprintf(bf, size, "%-*s", width, "-");
 
-	notes = symbol__annotation(sym);
+	branch = symbol__annotation(sym)->branch;
 
-	if (notes->hit_cycles)
-		ipc = notes->hit_insn / ((double)notes->hit_cycles);
+	if (branch && branch->hit_cycles)
+		ipc = branch->hit_insn / ((double)branch->hit_cycles);
 
-	if (notes->total_insn) {
-		coverage = notes->cover_insn * 100.0 /
-			((double)notes->total_insn);
+	if (branch && branch->total_insn) {
+		coverage = branch->cover_insn * 100.0 /
+			((double)branch->total_insn);
 	}
 
 	snprintf(tmp, sizeof(tmp), "%-5.2f [%5.1f%%]", ipc, coverage);
@@ -2094,7 +2141,7 @@ struct sort_entry sort_dso_size = {
 	.se_width_idx	= HISTC_DSO_SIZE,
 };
 
-/* --sort dso_size */
+/* --sort addr */
 
 static int64_t
 sort__addr_cmp(struct hist_entry *left, struct hist_entry *right)
@@ -2131,6 +2178,152 @@ struct sort_entry sort_addr = {
 	.se_width_idx	= HISTC_ADDR,
 };
 
+/* --sort type */
+
+struct annotated_data_type unknown_type = {
+	.self = {
+		.type_name = (char *)"(unknown)",
+		.children = LIST_HEAD_INIT(unknown_type.self.children),
+	},
+};
+
+static int64_t
+sort__type_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return sort__addr_cmp(left, right);
+}
+
+static void sort__type_init(struct hist_entry *he)
+{
+	if (he->mem_type)
+		return;
+
+	he->mem_type = hist_entry__get_data_type(he);
+	if (he->mem_type == NULL) {
+		he->mem_type = &unknown_type;
+		he->mem_type_off = 0;
+	}
+}
+
+static int64_t
+sort__type_collapse(struct hist_entry *left, struct hist_entry *right)
+{
+	struct annotated_data_type *left_type = left->mem_type;
+	struct annotated_data_type *right_type = right->mem_type;
+
+	if (!left_type) {
+		sort__type_init(left);
+		left_type = left->mem_type;
+	}
+
+	if (!right_type) {
+		sort__type_init(right);
+		right_type = right->mem_type;
+	}
+
+	return strcmp(left_type->self.type_name, right_type->self.type_name);
+}
+
+static int64_t
+sort__type_sort(struct hist_entry *left, struct hist_entry *right)
+{
+	return sort__type_collapse(left, right);
+}
+
+static int hist_entry__type_snprintf(struct hist_entry *he, char *bf,
+				     size_t size, unsigned int width)
+{
+	return repsep_snprintf(bf, size, "%-*s", width, he->mem_type->self.type_name);
+}
+
+struct sort_entry sort_type = {
+	.se_header	= "Data Type",
+	.se_cmp		= sort__type_cmp,
+	.se_collapse	= sort__type_collapse,
+	.se_sort	= sort__type_sort,
+	.se_init	= sort__type_init,
+	.se_snprintf	= hist_entry__type_snprintf,
+	.se_width_idx	= HISTC_TYPE,
+};
+
+/* --sort typeoff */
+
+static int64_t
+sort__typeoff_sort(struct hist_entry *left, struct hist_entry *right)
+{
+	struct annotated_data_type *left_type = left->mem_type;
+	struct annotated_data_type *right_type = right->mem_type;
+	int64_t ret;
+
+	if (!left_type) {
+		sort__type_init(left);
+		left_type = left->mem_type;
+	}
+
+	if (!right_type) {
+		sort__type_init(right);
+		right_type = right->mem_type;
+	}
+
+	ret = strcmp(left_type->self.type_name, right_type->self.type_name);
+	if (ret)
+		return ret;
+	return left->mem_type_off - right->mem_type_off;
+}
+
+static void fill_member_name(char *buf, size_t sz, struct annotated_member *m,
+			     int offset, bool first)
+{
+	struct annotated_member *child;
+
+	if (list_empty(&m->children))
+		return;
+
+	list_for_each_entry(child, &m->children, node) {
+		if (child->offset <= offset && offset < child->offset + child->size) {
+			int len = 0;
+
+			/* It can have anonymous struct/union members */
+			if (child->var_name) {
+				len = scnprintf(buf, sz, "%s%s",
+						first ? "" : ".", child->var_name);
+				first = false;
+			}
+
+			fill_member_name(buf + len, sz - len, child, offset, first);
+			return;
+		}
+	}
+}
+
+static int hist_entry__typeoff_snprintf(struct hist_entry *he, char *bf,
+				     size_t size, unsigned int width __maybe_unused)
+{
+	struct annotated_data_type *he_type = he->mem_type;
+	char buf[4096];
+
+	buf[0] = '\0';
+	if (list_empty(&he_type->self.children))
+		snprintf(buf, sizeof(buf), "no field");
+	else
+		fill_member_name(buf, sizeof(buf), &he_type->self,
+				 he->mem_type_off, true);
+	buf[4095] = '\0';
+
+	return repsep_snprintf(bf, size, "%s %+d (%s)", he_type->self.type_name,
+			       he->mem_type_off, buf);
+}
+
+struct sort_entry sort_type_offset = {
+	.se_header	= "Data Type Offset",
+	.se_cmp		= sort__type_cmp,
+	.se_collapse	= sort__typeoff_sort,
+	.se_sort	= sort__typeoff_sort,
+	.se_init	= sort__type_init,
+	.se_snprintf	= hist_entry__typeoff_snprintf,
+	.se_width_idx	= HISTC_TYPE_OFFSET,
+};
+
 
 struct sort_dimension {
 	const char		*name;
@@ -2185,7 +2378,10 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_ADDR, "addr", sort_addr),
 	DIM(SORT_LOCAL_RETIRE_LAT, "local_retire_lat", sort_local_p_stage_cyc),
 	DIM(SORT_GLOBAL_RETIRE_LAT, "retire_lat", sort_global_p_stage_cyc),
-	DIM(SORT_SIMD, "simd", sort_simd)
+	DIM(SORT_SIMD, "simd", sort_simd),
+	DIM(SORT_ANNOTATE_DATA_TYPE, "type", sort_type),
+	DIM(SORT_ANNOTATE_DATA_TYPE_OFFSET, "typeoff", sort_type_offset),
+	DIM(SORT_SYM_OFFSET, "symoff", sort_sym_offset),
 };
 
 #undef DIM
@@ -3205,6 +3401,8 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 			list->thread = 1;
 		} else if (sd->entry == &sort_comm) {
 			list->comm = 1;
+		} else if (sd->entry == &sort_type_offset) {
+			symbol_conf.annotate_data_member = true;
 		}
 
 		return __sort_dimension__add(sd, list, level);
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index ecfb7f1359d5..6f6b4189a389 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -15,6 +15,7 @@
 
 struct option;
 struct thread;
+struct annotated_data_type;
 
 extern regex_t parent_regex;
 extern const char *sort_order;
@@ -34,6 +35,7 @@ extern struct sort_entry sort_dso_to;
 extern struct sort_entry sort_sym_from;
 extern struct sort_entry sort_sym_to;
 extern struct sort_entry sort_srcline;
+extern struct sort_entry sort_type;
 extern const char default_mem_sort_order[];
 extern bool chk_double_cl;
 
@@ -111,6 +113,7 @@ struct hist_entry {
 	u64			p_stage_cyc;
 	u8			cpumode;
 	u8			depth;
+	int			mem_type_off;
 	struct simd_flags	simd_flags;
 
 	/* We are added by hists__add_dummy_entry. */
@@ -154,6 +157,7 @@ struct hist_entry {
 	struct perf_hpp_list	*hpp_list;
 	struct hist_entry	*parent_he;
 	struct hist_entry_ops	*ops;
+	struct annotated_data_type *mem_type;
 	union {
 		/* this is for hierarchical entry structure */
 		struct {
@@ -243,6 +247,9 @@ enum sort_type {
 	SORT_LOCAL_RETIRE_LAT,
 	SORT_GLOBAL_RETIRE_LAT,
 	SORT_SIMD,
+	SORT_ANNOTATE_DATA_TYPE,
+	SORT_ANNOTATE_DATA_TYPE_OFFSET,
+	SORT_SYM_OFFSET,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index afe6db8e7bf4..8c61f8627ebc 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -898,7 +898,7 @@ static bool hybrid_uniquify(struct evsel *evsel, struct perf_stat_config *config
 
 static void uniquify_counter(struct perf_stat_config *config, struct evsel *counter)
 {
-	if (config->no_merge || hybrid_uniquify(counter, config))
+	if (config->aggr_mode == AGGR_NONE || hybrid_uniquify(counter, config))
 		uniquify_event_name(counter);
 }
 
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 1c5c3eeba4cf..e31426167852 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -264,7 +264,7 @@ static void print_ll_miss(struct perf_stat_config *config,
 	static const double color_ratios[3] = {20.0, 10.0, 5.0};
 
 	print_ratio(config, evsel, aggr_idx, misses, out, STAT_LL_CACHE, color_ratios,
-		    "of all L1-icache accesses");
+		    "of all LL-cache accesses");
 }
 
 static void print_dtlb_miss(struct perf_stat_config *config,
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index ec3506042217..b0bcf92f0f9c 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -315,7 +315,7 @@ static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals,
 	if (!counter->per_pkg)
 		return 0;
 
-	if (perf_cpu_map__empty(cpus))
+	if (perf_cpu_map__has_any_cpu_or_is_empty(cpus))
 		return 0;
 
 	if (!mask) {
@@ -592,7 +592,7 @@ void perf_stat_merge_counters(struct perf_stat_config *config, struct evlist *ev
 {
 	struct evsel *evsel;
 
-	if (config->no_merge)
+	if (config->aggr_mode == AGGR_NONE)
 		return;
 
 	evlist__for_each_entry(evlist, evsel)
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 325d0fad1842..4357ba114822 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -76,7 +76,6 @@ struct perf_stat_config {
 	bool			 null_run;
 	bool			 ru_display;
 	bool			 big_num;
-	bool			 no_merge;
 	bool			 hybrid_merge;
 	bool			 walltime_run_table;
 	bool			 all_kernel;
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 9e7eeaf616b8..4b934ed3bfd1 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1392,8 +1392,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 			map__set_start(map, shdr->sh_addr + ref_reloc(kmap));
 			map__set_end(map, map__start(map) + shdr->sh_size);
 			map__set_pgoff(map, shdr->sh_offset);
-			map__set_map_ip(map, map__dso_map_ip);
-			map__set_unmap_ip(map, map__dso_unmap_ip);
+			map__set_mapping_type(map, MAPPING_TYPE__DSO);
 			/* Ensure maps are correctly ordered */
 			if (kmaps) {
 				int err;
@@ -1455,8 +1454,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 			map__set_end(curr_map, map__start(curr_map) + shdr->sh_size);
 			map__set_pgoff(curr_map, shdr->sh_offset);
 		} else {
-			map__set_map_ip(curr_map, identity__map_ip);
-			map__set_unmap_ip(curr_map, identity__map_ip);
+			map__set_mapping_type(curr_map, MAPPING_TYPE__IDENTITY);
 		}
 		curr_dso->symtab_type = dso->symtab_type;
 		if (maps__insert(kmaps, curr_map))
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index a81a14769bd1..1da8b713509c 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -159,9 +159,10 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 				goto out_free;
 
 			ret = read_build_id(buf, buf_size, bid, need_swap);
-			if (ret == 0)
+			if (ret == 0) {
 				ret = bid->size;
-			break;
+				break;
+			}
 		}
 	} else {
 		Elf64_Ehdr ehdr;
@@ -210,9 +211,10 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 				goto out_free;
 
 			ret = read_build_id(buf, buf_size, bid, need_swap);
-			if (ret == 0)
+			if (ret == 0) {
 				ret = bid->size;
-			break;
+				break;
+			}
 		}
 	}
 out_free:
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 82cc74b9358e..be212ba157dc 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -48,11 +48,6 @@ static bool symbol__is_idle(const char *name);
 int vmlinux_path__nr_entries;
 char **vmlinux_path;
 
-struct map_list_node {
-	struct list_head node;
-	struct map *map;
-};
-
 struct symbol_conf symbol_conf = {
 	.nanosecs		= false,
 	.use_modules		= true,
@@ -90,11 +85,6 @@ static enum dso_binary_type binary_type_symtab[] = {
 
 #define DSO_BINARY_TYPE__SYMTAB_CNT ARRAY_SIZE(binary_type_symtab)
 
-static struct map_list_node *map_list_node__new(void)
-{
-	return malloc(sizeof(struct map_list_node));
-}
-
 static bool symbol_type__filter(char symbol_type)
 {
 	symbol_type = toupper(symbol_type);
@@ -270,29 +260,6 @@ void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms)
 		curr->end = roundup(curr->start, 4096) + 4096;
 }
 
-void maps__fixup_end(struct maps *maps)
-{
-	struct map_rb_node *prev = NULL, *curr;
-
-	down_write(maps__lock(maps));
-
-	maps__for_each_entry(maps, curr) {
-		if (prev != NULL && !map__end(prev->map))
-			map__set_end(prev->map, map__start(curr->map));
-
-		prev = curr;
-	}
-
-	/*
-	 * We still haven't the actual symbols, so guess the
-	 * last map final address.
-	 */
-	if (curr && !map__end(curr->map))
-		map__set_end(curr->map, ~0ULL);
-
-	up_write(maps__lock(maps));
-}
-
 struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char *name)
 {
 	size_t namelen = strlen(name) + 1;
@@ -956,8 +923,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta,
 				return -1;
 			}
 
-			map__set_map_ip(curr_map, identity__map_ip);
-			map__set_unmap_ip(curr_map, identity__map_ip);
+			map__set_mapping_type(curr_map, MAPPING_TYPE__IDENTITY);
 			if (maps__insert(kmaps, curr_map)) {
 				dso__put(ndso);
 				return -1;
@@ -1148,33 +1114,35 @@ out_delete_from:
 	return ret;
 }
 
+static int do_validate_kcore_modules_cb(struct map *old_map, void *data)
+{
+	struct rb_root *modules = data;
+	struct module_info *mi;
+	struct dso *dso;
+
+	if (!__map__is_kmodule(old_map))
+		return 0;
+
+	dso = map__dso(old_map);
+	/* Module must be in memory at the same address */
+	mi = find_module(dso->short_name, modules);
+	if (!mi || mi->start != map__start(old_map))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int do_validate_kcore_modules(const char *filename, struct maps *kmaps)
 {
 	struct rb_root modules = RB_ROOT;
-	struct map_rb_node *old_node;
 	int err;
 
 	err = read_proc_modules(filename, &modules);
 	if (err)
 		return err;
 
-	maps__for_each_entry(kmaps, old_node) {
-		struct map *old_map = old_node->map;
-		struct module_info *mi;
-		struct dso *dso;
+	err = maps__for_each_map(kmaps, do_validate_kcore_modules_cb, &modules);
 
-		if (!__map__is_kmodule(old_map)) {
-			continue;
-		}
-		dso = map__dso(old_map);
-		/* Module must be in memory at the same address */
-		mi = find_module(dso->short_name, &modules);
-		if (!mi || mi->start != map__start(old_map)) {
-			err = -EINVAL;
-			goto out;
-		}
-	}
-out:
 	delete_modules(&modules);
 	return err;
 }
@@ -1271,101 +1239,15 @@ static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data)
 	return 0;
 }
 
-/*
- * Merges map into maps by splitting the new map within the existing map
- * regions.
- */
-int maps__merge_in(struct maps *kmaps, struct map *new_map)
+static bool remove_old_maps(struct map *map, void *data)
 {
-	struct map_rb_node *rb_node;
-	LIST_HEAD(merged);
-	int err = 0;
-
-	maps__for_each_entry(kmaps, rb_node) {
-		struct map *old_map = rb_node->map;
-
-		/* no overload with this one */
-		if (map__end(new_map) < map__start(old_map) ||
-		    map__start(new_map) >= map__end(old_map))
-			continue;
-
-		if (map__start(new_map) < map__start(old_map)) {
-			/*
-			 * |new......
-			 *       |old....
-			 */
-			if (map__end(new_map) < map__end(old_map)) {
-				/*
-				 * |new......|     -> |new..|
-				 *       |old....| ->       |old....|
-				 */
-				map__set_end(new_map, map__start(old_map));
-			} else {
-				/*
-				 * |new.............| -> |new..|       |new..|
-				 *       |old....|    ->       |old....|
-				 */
-				struct map_list_node *m = map_list_node__new();
-
-				if (!m) {
-					err = -ENOMEM;
-					goto out;
-				}
-
-				m->map = map__clone(new_map);
-				if (!m->map) {
-					free(m);
-					err = -ENOMEM;
-					goto out;
-				}
-
-				map__set_end(m->map, map__start(old_map));
-				list_add_tail(&m->node, &merged);
-				map__add_pgoff(new_map, map__end(old_map) - map__start(new_map));
-				map__set_start(new_map, map__end(old_map));
-			}
-		} else {
-			/*
-			 *      |new......
-			 * |old....
-			 */
-			if (map__end(new_map) < map__end(old_map)) {
-				/*
-				 *      |new..|   -> x
-				 * |old.........| -> |old.........|
-				 */
-				map__put(new_map);
-				new_map = NULL;
-				break;
-			} else {
-				/*
-				 *      |new......| ->         |new...|
-				 * |old....|        -> |old....|
-				 */
-				map__add_pgoff(new_map, map__end(old_map) - map__start(new_map));
-				map__set_start(new_map, map__end(old_map));
-			}
-		}
-	}
-
-out:
-	while (!list_empty(&merged)) {
-		struct map_list_node *old_node;
-
-		old_node = list_entry(merged.next, struct map_list_node, node);
-		list_del_init(&old_node->node);
-		if (!err)
-			err = maps__insert(kmaps, old_node->map);
-		map__put(old_node->map);
-		free(old_node);
-	}
+	const struct map *map_to_save = data;
 
-	if (new_map) {
-		if (!err)
-			err = maps__insert(kmaps, new_map);
-		map__put(new_map);
-	}
-	return err;
+	/*
+	 * We need to preserve eBPF maps even if they are covered by kcore,
+	 * because we need to access eBPF dso for source data.
+	 */
+	return !RC_CHK_EQUAL(map, map_to_save) && !__map__is_bpf_prog(map);
 }
 
 static int dso__load_kcore(struct dso *dso, struct map *map,
@@ -1374,7 +1256,6 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	struct maps *kmaps = map__kmaps(map);
 	struct kcore_mapfn_data md;
 	struct map *replacement_map = NULL;
-	struct map_rb_node *old_node, *next;
 	struct machine *machine;
 	bool is_64_bit;
 	int err, fd;
@@ -1421,17 +1302,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	}
 
 	/* Remove old maps */
-	maps__for_each_entry_safe(kmaps, old_node, next) {
-		struct map *old_map = old_node->map;
-
-		/*
-		 * We need to preserve eBPF maps even if they are
-		 * covered by kcore, because we need to access
-		 * eBPF dso for source data.
-		 */
-		if (old_map != map && !__map__is_bpf_prog(old_map))
-			maps__remove(kmaps, old_map);
-	}
+	maps__remove_maps(kmaps, remove_old_maps, map);
 	machine->trampolines_mapped = false;
 
 	/* Find the kernel map using the '_stext' symbol */
@@ -1475,8 +1346,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 			map__set_start(map, map__start(new_map));
 			map__set_end(map, map__end(new_map));
 			map__set_pgoff(map, map__pgoff(new_map));
-			map__set_map_ip(map, map__map_ip_ptr(new_map));
-			map__set_unmap_ip(map, map__unmap_ip_ptr(new_map));
+			map__set_mapping_type(map, map__mapping_type(new_map));
 			/* Ensure maps are correctly ordered */
 			map_ref = map__get(map);
 			maps__remove(kmaps, map_ref);
@@ -2067,124 +1937,6 @@ out:
 	return ret;
 }
 
-static int map__strcmp(const void *a, const void *b)
-{
-	const struct map *map_a = *(const struct map **)a;
-	const struct map *map_b = *(const struct map **)b;
-	const struct dso *dso_a = map__dso(map_a);
-	const struct dso *dso_b = map__dso(map_b);
-	int ret = strcmp(dso_a->short_name, dso_b->short_name);
-
-	if (ret == 0 && map_a != map_b) {
-		/*
-		 * Ensure distinct but name equal maps have an order in part to
-		 * aid reference counting.
-		 */
-		ret = (int)map__start(map_a) - (int)map__start(map_b);
-		if (ret == 0)
-			ret = (int)((intptr_t)map_a - (intptr_t)map_b);
-	}
-
-	return ret;
-}
-
-static int map__strcmp_name(const void *name, const void *b)
-{
-	const struct dso *dso = map__dso(*(const struct map **)b);
-
-	return strcmp(name, dso->short_name);
-}
-
-void __maps__sort_by_name(struct maps *maps)
-{
-	qsort(maps__maps_by_name(maps), maps__nr_maps(maps), sizeof(struct map *), map__strcmp);
-}
-
-static int map__groups__sort_by_name_from_rbtree(struct maps *maps)
-{
-	struct map_rb_node *rb_node;
-	struct map **maps_by_name = realloc(maps__maps_by_name(maps),
-					    maps__nr_maps(maps) * sizeof(struct map *));
-	int i = 0;
-
-	if (maps_by_name == NULL)
-		return -1;
-
-	up_read(maps__lock(maps));
-	down_write(maps__lock(maps));
-
-	RC_CHK_ACCESS(maps)->maps_by_name = maps_by_name;
-	RC_CHK_ACCESS(maps)->nr_maps_allocated = maps__nr_maps(maps);
-
-	maps__for_each_entry(maps, rb_node)
-		maps_by_name[i++] = map__get(rb_node->map);
-
-	__maps__sort_by_name(maps);
-
-	up_write(maps__lock(maps));
-	down_read(maps__lock(maps));
-
-	return 0;
-}
-
-static struct map *__maps__find_by_name(struct maps *maps, const char *name)
-{
-	struct map **mapp;
-
-	if (maps__maps_by_name(maps) == NULL &&
-	    map__groups__sort_by_name_from_rbtree(maps))
-		return NULL;
-
-	mapp = bsearch(name, maps__maps_by_name(maps), maps__nr_maps(maps),
-		       sizeof(*mapp), map__strcmp_name);
-	if (mapp)
-		return *mapp;
-	return NULL;
-}
-
-struct map *maps__find_by_name(struct maps *maps, const char *name)
-{
-	struct map_rb_node *rb_node;
-	struct map *map;
-
-	down_read(maps__lock(maps));
-
-
-	if (RC_CHK_ACCESS(maps)->last_search_by_name) {
-		const struct dso *dso = map__dso(RC_CHK_ACCESS(maps)->last_search_by_name);
-
-		if (strcmp(dso->short_name, name) == 0) {
-			map = RC_CHK_ACCESS(maps)->last_search_by_name;
-			goto out_unlock;
-		}
-	}
-	/*
-	 * If we have maps->maps_by_name, then the name isn't in the rbtree,
-	 * as maps->maps_by_name mirrors the rbtree when lookups by name are
-	 * made.
-	 */
-	map = __maps__find_by_name(maps, name);
-	if (map || maps__maps_by_name(maps) != NULL)
-		goto out_unlock;
-
-	/* Fallback to traversing the rbtree... */
-	maps__for_each_entry(maps, rb_node) {
-		struct dso *dso;
-
-		map = rb_node->map;
-		dso = map__dso(map);
-		if (strcmp(dso->short_name, name) == 0) {
-			RC_CHK_ACCESS(maps)->last_search_by_name = map;
-			goto out_unlock;
-		}
-	}
-	map = NULL;
-
-out_unlock:
-	up_read(maps__lock(maps));
-	return map;
-}
-
 int dso__load_vmlinux(struct dso *dso, struct map *map,
 		      const char *vmlinux, bool vmlinux_allocated)
 {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index af87c46b3f89..071837ddce2a 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -189,7 +189,6 @@ void __symbols__insert(struct rb_root_cached *symbols, struct symbol *sym,
 void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym);
 void symbols__fixup_duplicate(struct rb_root_cached *symbols);
 void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms);
-void maps__fixup_end(struct maps *maps);
 
 typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data);
 int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data,
diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h
index 0b589570d1d0..c114bbceef40 100644
--- a/tools/perf/util/symbol_conf.h
+++ b/tools/perf/util/symbol_conf.h
@@ -42,7 +42,11 @@ struct symbol_conf {
 			inline_name,
 			disable_add2line_warn,
 			buildid_mmap2,
-			guest_code;
+			guest_code,
+			lazy_load_kernel_maps,
+			keep_exited_threads,
+			annotate_data_member,
+			annotate_data_sample;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index a0579c7d7b9e..2a0289c14959 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -665,18 +665,74 @@ int perf_event__synthesize_cgroups(struct perf_tool *tool __maybe_unused,
 }
 #endif
 
+struct perf_event__synthesize_modules_maps_cb_args {
+	struct perf_tool *tool;
+	perf_event__handler_t process;
+	struct machine *machine;
+	union perf_event *event;
+};
+
+static int perf_event__synthesize_modules_maps_cb(struct map *map, void *data)
+{
+	struct perf_event__synthesize_modules_maps_cb_args *args = data;
+	union perf_event *event = args->event;
+	struct dso *dso;
+	size_t size;
+
+	if (!__map__is_kmodule(map))
+		return 0;
+
+	dso = map__dso(map);
+	if (symbol_conf.buildid_mmap2) {
+		size = PERF_ALIGN(dso->long_name_len + 1, sizeof(u64));
+		event->mmap2.header.type = PERF_RECORD_MMAP2;
+		event->mmap2.header.size = (sizeof(event->mmap2) -
+					(sizeof(event->mmap2.filename) - size));
+		memset(event->mmap2.filename + size, 0, args->machine->id_hdr_size);
+		event->mmap2.header.size += args->machine->id_hdr_size;
+		event->mmap2.start = map__start(map);
+		event->mmap2.len   = map__size(map);
+		event->mmap2.pid   = args->machine->pid;
+
+		memcpy(event->mmap2.filename, dso->long_name, dso->long_name_len + 1);
+
+		perf_record_mmap2__read_build_id(&event->mmap2, args->machine, false);
+	} else {
+		size = PERF_ALIGN(dso->long_name_len + 1, sizeof(u64));
+		event->mmap.header.type = PERF_RECORD_MMAP;
+		event->mmap.header.size = (sizeof(event->mmap) -
+					(sizeof(event->mmap.filename) - size));
+		memset(event->mmap.filename + size, 0, args->machine->id_hdr_size);
+		event->mmap.header.size += args->machine->id_hdr_size;
+		event->mmap.start = map__start(map);
+		event->mmap.len   = map__size(map);
+		event->mmap.pid   = args->machine->pid;
+
+		memcpy(event->mmap.filename, dso->long_name, dso->long_name_len + 1);
+	}
+
+	if (perf_tool__process_synth_event(args->tool, event, args->machine, args->process) != 0)
+		return -1;
+
+	return 0;
+}
+
 int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process,
 				   struct machine *machine)
 {
-	int rc = 0;
-	struct map_rb_node *pos;
+	int rc;
 	struct maps *maps = machine__kernel_maps(machine);
-	union perf_event *event;
-	size_t size = symbol_conf.buildid_mmap2 ?
-			sizeof(event->mmap2) : sizeof(event->mmap);
+	struct perf_event__synthesize_modules_maps_cb_args args = {
+		.tool = tool,
+		.process = process,
+		.machine = machine,
+	};
+	size_t size = symbol_conf.buildid_mmap2
+		? sizeof(args.event->mmap2)
+		: sizeof(args.event->mmap);
 
-	event = zalloc(size + machine->id_hdr_size);
-	if (event == NULL) {
+	args.event = zalloc(size + machine->id_hdr_size);
+	if (args.event == NULL) {
 		pr_debug("Not enough memory synthesizing mmap event "
 			 "for kernel modules\n");
 		return -1;
@@ -687,53 +743,13 @@ int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t
 	 * __perf_event_mmap
 	 */
 	if (machine__is_host(machine))
-		event->header.misc = PERF_RECORD_MISC_KERNEL;
+		args.event->header.misc = PERF_RECORD_MISC_KERNEL;
 	else
-		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
-
-	maps__for_each_entry(maps, pos) {
-		struct map *map = pos->map;
-		struct dso *dso;
+		args.event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
 
-		if (!__map__is_kmodule(map))
-			continue;
+	rc = maps__for_each_map(maps, perf_event__synthesize_modules_maps_cb, &args);
 
-		dso = map__dso(map);
-		if (symbol_conf.buildid_mmap2) {
-			size = PERF_ALIGN(dso->long_name_len + 1, sizeof(u64));
-			event->mmap2.header.type = PERF_RECORD_MMAP2;
-			event->mmap2.header.size = (sizeof(event->mmap2) -
-						(sizeof(event->mmap2.filename) - size));
-			memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
-			event->mmap2.header.size += machine->id_hdr_size;
-			event->mmap2.start = map__start(map);
-			event->mmap2.len   = map__size(map);
-			event->mmap2.pid   = machine->pid;
-
-			memcpy(event->mmap2.filename, dso->long_name, dso->long_name_len + 1);
-
-			perf_record_mmap2__read_build_id(&event->mmap2, machine, false);
-		} else {
-			size = PERF_ALIGN(dso->long_name_len + 1, sizeof(u64));
-			event->mmap.header.type = PERF_RECORD_MMAP;
-			event->mmap.header.size = (sizeof(event->mmap) -
-						(sizeof(event->mmap.filename) - size));
-			memset(event->mmap.filename + size, 0, machine->id_hdr_size);
-			event->mmap.header.size += machine->id_hdr_size;
-			event->mmap.start = map__start(map);
-			event->mmap.len   = map__size(map);
-			event->mmap.pid   = machine->pid;
-
-			memcpy(event->mmap.filename, dso->long_name, dso->long_name_len + 1);
-		}
-
-		if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
-			rc = -1;
-			break;
-		}
-	}
-
-	free(event);
+	free(args.event);
 	return rc;
 }
 
@@ -1039,11 +1055,11 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	if (thread_nr > n)
 		thread_nr = n;
 
-	synthesize_threads = calloc(sizeof(pthread_t), thread_nr);
+	synthesize_threads = calloc(thread_nr, sizeof(pthread_t));
 	if (synthesize_threads == NULL)
 		goto free_dirent;
 
-	args = calloc(sizeof(*args), thread_nr);
+	args = calloc(thread_nr, sizeof(*args));
 	if (args == NULL)
 		goto free_threads;
 
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index fe5e6991ae4b..89c47a5098e2 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -345,38 +345,36 @@ int thread__insert_map(struct thread *thread, struct map *map)
 	if (ret)
 		return ret;
 
-	maps__fixup_overlappings(thread__maps(thread), map, stderr);
-	return maps__insert(thread__maps(thread), map);
+	return maps__fixup_overlap_and_insert(thread__maps(thread), map);
 }
 
-static int __thread__prepare_access(struct thread *thread)
+struct thread__prepare_access_maps_cb_args {
+	int err;
+	struct maps *maps;
+};
+
+static int thread__prepare_access_maps_cb(struct map *map, void *data)
 {
 	bool initialized = false;
-	int err = 0;
-	struct maps *maps = thread__maps(thread);
-	struct map_rb_node *rb_node;
-
-	down_read(maps__lock(maps));
-
-	maps__for_each_entry(maps, rb_node) {
-		err = unwind__prepare_access(thread__maps(thread), rb_node->map, &initialized);
-		if (err || initialized)
-			break;
-	}
+	struct thread__prepare_access_maps_cb_args *args = data;
 
-	up_read(maps__lock(maps));
+	args->err = unwind__prepare_access(args->maps, map, &initialized);
 
-	return err;
+	return (args->err || initialized) ? 1 : 0;
 }
 
 static int thread__prepare_access(struct thread *thread)
 {
-	int err = 0;
+	struct thread__prepare_access_maps_cb_args args = {
+		.err = 0,
+	};
 
-	if (dwarf_callchain_users)
-		err = __thread__prepare_access(thread);
+	if (dwarf_callchain_users) {
+		args.maps = thread__maps(thread);
+		maps__for_each_map(thread__maps(thread), thread__prepare_access_maps_cb, &args);
+	}
 
-	return err;
+	return args.err;
 }
 
 static int thread__clone_maps(struct thread *thread, struct thread *parent, bool do_maps_clone)
@@ -385,14 +383,14 @@ static int thread__clone_maps(struct thread *thread, struct thread *parent, bool
 	if (thread__pid(thread) == thread__pid(parent))
 		return thread__prepare_access(thread);
 
-	if (thread__maps(thread) == thread__maps(parent)) {
+	if (RC_CHK_EQUAL(thread__maps(thread), thread__maps(parent))) {
 		pr_debug("broken map groups on thread %d/%d parent %d/%d\n",
 			 thread__pid(thread), thread__tid(thread),
 			 thread__pid(parent), thread__tid(parent));
 		return 0;
 	}
 	/* But this one is new process, copy maps. */
-	return do_maps_clone ? maps__clone(thread, thread__maps(parent)) : 0;
+	return do_maps_clone ? maps__copy_from(thread__maps(thread), thread__maps(parent)) : 0;
 }
 
 int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone)
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index e79225a0ea46..0df775b5c110 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -36,13 +36,22 @@ struct thread_rb_node {
 };
 
 DECLARE_RC_STRUCT(thread) {
+	/** @maps: mmaps associated with this thread. */
 	struct maps		*maps;
 	pid_t			pid_; /* Not all tools update this */
+	/** @tid: thread ID number unique to a machine. */
 	pid_t			tid;
+	/** @ppid: parent process of the process this thread belongs to. */
 	pid_t			ppid;
 	int			cpu;
 	int			guest_cpu; /* For QEMU thread */
 	refcount_t		refcnt;
+	/**
+	 * @exited: Has the thread had an exit event. Such threads are usually
+	 * removed from the machine's threads but some events/tools require
+	 * access to dead threads.
+	 */
+	bool			exited;
 	bool			comm_set;
 	int			comm_len;
 	struct list_head	namespaces_list;
@@ -189,6 +198,11 @@ static inline refcount_t *thread__refcnt(struct thread *thread)
 	return &RC_CHK_ACCESS(thread)->refcnt;
 }
 
+static inline void thread__set_exited(struct thread *thread, bool exited)
+{
+	RC_CHK_ACCESS(thread)->exited = exited;
+}
+
 static inline bool thread__comm_set(const struct thread *thread)
 {
 	return RC_CHK_ACCESS(thread)->comm_set;
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index be7157de0451..4db3d1bd686c 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -28,6 +28,7 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
 	struct record_opts *opts = &top->record_opts;
 	struct target *target = &opts->target;
 	size_t ret = 0;
+	int nr_cpus;
 
 	if (top->samples) {
 		samples_per_sec = top->samples / top->delay_secs;
@@ -93,19 +94,17 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
 	else
 		ret += SNPRINTF(bf + ret, size - ret, " (all");
 
+	nr_cpus = perf_cpu_map__nr(top->evlist->core.user_requested_cpus);
 	if (target->cpu_list)
 		ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)",
-				perf_cpu_map__nr(top->evlist->core.user_requested_cpus) > 1
-				? "s" : "",
+				nr_cpus > 1 ? "s" : "",
 				target->cpu_list);
 	else {
 		if (target->tid)
 			ret += SNPRINTF(bf + ret, size - ret, ")");
 		else
 			ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)",
-					perf_cpu_map__nr(top->evlist->core.user_requested_cpus),
-					perf_cpu_map__nr(top->evlist->core.user_requested_cpus) > 1
-					? "s" : "");
+					nr_cpus, nr_cpus > 1 ? "s" : "");
 	}
 
 	perf_top__reset_sample_counters(top);
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index a8b0d79bd96c..4c5588dbb131 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -21,7 +21,6 @@ struct perf_top {
 	struct perf_tool   tool;
 	struct evlist *evlist, *sb_evlist;
 	struct record_opts record_opts;
-	struct annotation_options annotation_opts;
 	struct evswitch	   evswitch;
 	/*
 	 * Symbols will be added here in perf_event__process_sample and will
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 8554db3fc0d7..6013335a8dae 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -46,6 +46,7 @@ static int __report_module(struct addr_location *al, u64 ip,
 {
 	Dwfl_Module *mod;
 	struct dso *dso = NULL;
+	Dwarf_Addr base;
 	/*
 	 * Some callers will use al->sym, so we can't just use the
 	 * cheaper thread__find_map() here.
@@ -58,13 +59,25 @@ static int __report_module(struct addr_location *al, u64 ip,
 	if (!dso)
 		return 0;
 
+	/*
+	 * The generated JIT DSO files only map the code segment without
+	 * ELF headers.  Since JIT codes used to be packed in a memory
+	 * segment, calculating the base address using pgoff falls into
+	 * a different code in another DSO.  So just use the map->start
+	 * directly to pick the correct one.
+	 */
+	if (!strncmp(dso->long_name, "/tmp/jitted-", 12))
+		base = map__start(al->map);
+	else
+		base = map__start(al->map) - map__pgoff(al->map);
+
 	mod = dwfl_addrmodule(ui->dwfl, ip);
 	if (mod) {
 		Dwarf_Addr s;
 
 		dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL);
-		if (s != map__start(al->map) - map__pgoff(al->map))
-			mod = 0;
+		if (s != base)
+			mod = NULL;
 	}
 
 	if (!mod) {
@@ -72,14 +85,14 @@ static int __report_module(struct addr_location *al, u64 ip,
 
 		__symbol__join_symfs(filename, sizeof(filename), dso->long_name);
 		mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1,
-				      map__start(al->map) - map__pgoff(al->map), false);
+				      base, false);
 	}
 	if (!mod) {
 		char filename[PATH_MAX];
 
 		if (dso__build_id_filename(dso, filename, sizeof(filename), false))
 			mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1,
-					      map__start(al->map) - map__pgoff(al->map), false);
+					      base, false);
 	}
 
 	if (mod) {
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index c0641882fd2f..dac536e28360 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -302,12 +302,31 @@ static int unwind_spec_ehframe(struct dso *dso, struct machine *machine,
 	return 0;
 }
 
+struct read_unwind_spec_eh_frame_maps_cb_args {
+	struct dso *dso;
+	u64 base_addr;
+};
+
+static int read_unwind_spec_eh_frame_maps_cb(struct map *map, void *data)
+{
+
+	struct read_unwind_spec_eh_frame_maps_cb_args *args = data;
+
+	if (map__dso(map) == args->dso && map__start(map) - map__pgoff(map) < args->base_addr)
+		args->base_addr = map__start(map) - map__pgoff(map);
+
+	return 0;
+}
+
+
 static int read_unwind_spec_eh_frame(struct dso *dso, struct unwind_info *ui,
 				     u64 *table_data, u64 *segbase,
 				     u64 *fde_count)
 {
-	struct map_rb_node *map_node;
-	u64 base_addr = UINT64_MAX;
+	struct read_unwind_spec_eh_frame_maps_cb_args args = {
+		.dso = dso,
+		.base_addr = UINT64_MAX,
+	};
 	int ret, fd;
 
 	if (dso->data.eh_frame_hdr_offset == 0) {
@@ -325,16 +344,11 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct unwind_info *ui,
 			return -EINVAL;
 	}
 
-	maps__for_each_entry(thread__maps(ui->thread), map_node) {
-		struct map *map = map_node->map;
-		u64 start = map__start(map);
+	maps__for_each_map(thread__maps(ui->thread), read_unwind_spec_eh_frame_maps_cb, &args);
 
-		if (map__dso(map) == dso && start < base_addr)
-			base_addr = start;
-	}
-	base_addr -= dso->data.elf_base_addr;
+	args.base_addr -= dso->data.elf_base_addr;
 	/* Address of .eh_frame_hdr */
-	*segbase = base_addr + dso->data.eh_frame_hdr_addr;
+	*segbase = args.base_addr + dso->data.eh_frame_hdr_addr;
 	ret = unwind_spec_ehframe(dso, ui->machine, dso->data.eh_frame_hdr_offset,
 				   table_data, fde_count);
 	if (ret)
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index ae3eee69b659..df8963796187 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -140,23 +140,34 @@ static struct dso *__machine__addnew_vdso(struct machine *machine, const char *s
 	return dso;
 }
 
+struct machine__thread_dso_type_maps_cb_args {
+	struct machine *machine;
+	enum dso_type dso_type;
+};
+
+static int machine__thread_dso_type_maps_cb(struct map *map, void *data)
+{
+	struct machine__thread_dso_type_maps_cb_args *args = data;
+	struct dso *dso = map__dso(map);
+
+	if (!dso || dso->long_name[0] != '/')
+		return 0;
+
+	args->dso_type = dso__type(dso, args->machine);
+	return (args->dso_type != DSO__TYPE_UNKNOWN) ? 1 : 0;
+}
+
 static enum dso_type machine__thread_dso_type(struct machine *machine,
 					      struct thread *thread)
 {
-	enum dso_type dso_type = DSO__TYPE_UNKNOWN;
-	struct map_rb_node *rb_node;
-
-	maps__for_each_entry(thread__maps(thread), rb_node) {
-		struct dso *dso = map__dso(rb_node->map);
+	struct machine__thread_dso_type_maps_cb_args args = {
+		.machine = machine,
+		.dso_type = DSO__TYPE_UNKNOWN,
+	};
 
-		if (!dso || dso->long_name[0] != '/')
-			continue;
-		dso_type = dso__type(dso, machine);
-		if (dso_type != DSO__TYPE_UNKNOWN)
-			break;
-	}
+	maps__for_each_map(thread__maps(thread), machine__thread_dso_type_maps_cb, &args);
 
-	return dso_type;
+	return args.dso_type;
 }
 
 #if BITS_PER_LONG == 64
diff --git a/tools/perf/util/zstd.c b/tools/perf/util/zstd.c
index 48dd2b018c47..57027e0ac7b6 100644
--- a/tools/perf/util/zstd.c
+++ b/tools/perf/util/zstd.c
@@ -7,35 +7,9 @@
 
 int zstd_init(struct zstd_data *data, int level)
 {
-	size_t ret;
-
-	data->dstream = ZSTD_createDStream();
-	if (data->dstream == NULL) {
-		pr_err("Couldn't create decompression stream.\n");
-		return -1;
-	}
-
-	ret = ZSTD_initDStream(data->dstream);
-	if (ZSTD_isError(ret)) {
-		pr_err("Failed to initialize decompression stream: %s\n", ZSTD_getErrorName(ret));
-		return -1;
-	}
-
-	if (!level)
-		return 0;
-
-	data->cstream = ZSTD_createCStream();
-	if (data->cstream == NULL) {
-		pr_err("Couldn't create compression stream.\n");
-		return -1;
-	}
-
-	ret = ZSTD_initCStream(data->cstream, level);
-	if (ZSTD_isError(ret)) {
-		pr_err("Failed to initialize compression stream: %s\n", ZSTD_getErrorName(ret));
-		return -1;
-	}
-
+	data->comp_level = level;
+	data->dstream = NULL;
+	data->cstream = NULL;
 	return 0;
 }
 
@@ -54,7 +28,7 @@ int zstd_fini(struct zstd_data *data)
 	return 0;
 }
 
-size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
+ssize_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
 				       void *src, size_t src_size, size_t max_record_size,
 				       size_t process_header(void *record, size_t increment))
 {
@@ -63,6 +37,21 @@ size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t
 	ZSTD_outBuffer output;
 	void *record;
 
+	if (!data->cstream) {
+		data->cstream = ZSTD_createCStream();
+		if (data->cstream == NULL) {
+			pr_err("Couldn't create compression stream.\n");
+			return -1;
+		}
+
+		ret = ZSTD_initCStream(data->cstream, data->comp_level);
+		if (ZSTD_isError(ret)) {
+			pr_err("Failed to initialize compression stream: %s\n",
+				ZSTD_getErrorName(ret));
+			return -1;
+		}
+	}
+
 	while (input.pos < input.size) {
 		record = dst;
 		size = process_header(record, 0);
@@ -96,6 +85,20 @@ size_t zstd_decompress_stream(struct zstd_data *data, void *src, size_t src_size
 	ZSTD_inBuffer input = { src, src_size, 0 };
 	ZSTD_outBuffer output = { dst, dst_size, 0 };
 
+	if (!data->dstream) {
+		data->dstream = ZSTD_createDStream();
+		if (data->dstream == NULL) {
+			pr_err("Couldn't create decompression stream.\n");
+			return 0;
+		}
+
+		ret = ZSTD_initDStream(data->dstream);
+		if (ZSTD_isError(ret)) {
+			pr_err("Failed to initialize decompression stream: %s\n",
+				ZSTD_getErrorName(ret));
+			return 0;
+		}
+	}
 	while (input.pos < input.size) {
 		ret = ZSTD_decompressStream(data->dstream, &output, &input);
 		if (ZSTD_isError(ret)) {
diff --git a/tools/power/cpupower/bench/Makefile b/tools/power/cpupower/bench/Makefile
index d9d9923af85c..a4b902f9e1c4 100644
--- a/tools/power/cpupower/bench/Makefile
+++ b/tools/power/cpupower/bench/Makefile
@@ -15,7 +15,7 @@ LIBS = -L../ -L$(OUTPUT) -lm -lcpupower
 OBJS = $(OUTPUT)main.o $(OUTPUT)parse.o $(OUTPUT)system.o $(OUTPUT)benchmark.o
 endif
 
-CFLAGS += -D_GNU_SOURCE -I../lib -DDEFAULT_CONFIG_FILE=\"$(confdir)/cpufreq-bench.conf\"
+override CFLAGS += -D_GNU_SOURCE -I../lib -DDEFAULT_CONFIG_FILE=\"$(confdir)/cpufreq-bench.conf\"
 
 $(OUTPUT)%.o : %.c
 	$(ECHO) "  CC      " $@
diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild
index 95dc58b94178..030b388800f0 100644
--- a/tools/testing/cxl/Kbuild
+++ b/tools/testing/cxl/Kbuild
@@ -13,6 +13,7 @@ ldflags-y += --wrap=cxl_hdm_decode_init
 ldflags-y += --wrap=cxl_dvsec_rr_decode
 ldflags-y += --wrap=devm_cxl_add_rch_dport
 ldflags-y += --wrap=cxl_rcd_component_reg_phys
+ldflags-y += --wrap=cxl_endpoint_parse_cdat
 
 DRIVERS := ../../../drivers
 CXL_SRC := $(DRIVERS)/cxl
@@ -58,10 +59,13 @@ cxl_core-y += $(CXL_CORE_SRC)/mbox.o
 cxl_core-y += $(CXL_CORE_SRC)/pci.o
 cxl_core-y += $(CXL_CORE_SRC)/hdm.o
 cxl_core-y += $(CXL_CORE_SRC)/pmu.o
+cxl_core-y += $(CXL_CORE_SRC)/cdat.o
 cxl_core-$(CONFIG_TRACING) += $(CXL_CORE_SRC)/trace.o
 cxl_core-$(CONFIG_CXL_REGION) += $(CXL_CORE_SRC)/region.o
 cxl_core-y += config_check.o
 cxl_core-y += cxl_core_test.o
 cxl_core-y += cxl_core_exports.o
 
+KBUILD_CFLAGS := $(filter-out -Wmissing-prototypes -Wmissing-declarations, $(KBUILD_CFLAGS))
+
 obj-m += test/
diff --git a/tools/testing/cxl/test/Kbuild b/tools/testing/cxl/test/Kbuild
index 61d5f7bcddf9..6b1927897856 100644
--- a/tools/testing/cxl/test/Kbuild
+++ b/tools/testing/cxl/test/Kbuild
@@ -8,3 +8,5 @@ obj-m += cxl_mock_mem.o
 cxl_test-y := cxl.o
 cxl_mock-y := mock.o
 cxl_mock_mem-y := mem.o
+
+KBUILD_CFLAGS := $(filter-out -Wmissing-prototypes -Wmissing-declarations, $(KBUILD_CFLAGS))
diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c
index f4e517a0c774..908e0d083936 100644
--- a/tools/testing/cxl/test/cxl.c
+++ b/tools/testing/cxl/test/cxl.c
@@ -15,6 +15,8 @@
 
 static int interleave_arithmetic;
 
+#define FAKE_QTG_ID	42
+
 #define NR_CXL_HOST_BRIDGES 2
 #define NR_CXL_SINGLE_HOST 1
 #define NR_CXL_RCH 1
@@ -68,15 +70,19 @@ static struct acpi_device acpi0017_mock;
 static struct acpi_device host_bridge[NR_BRIDGES] = {
 	[0] = {
 		.handle = &host_bridge[0],
+		.pnp.unique_id = "0",
 	},
 	[1] = {
 		.handle = &host_bridge[1],
+		.pnp.unique_id = "1",
 	},
 	[2] = {
 		.handle = &host_bridge[2],
+		.pnp.unique_id = "2",
 	},
 	[3] = {
 		.handle = &host_bridge[3],
+		.pnp.unique_id = "3",
 	},
 };
 
@@ -205,7 +211,7 @@ static struct {
 			.granularity = 4,
 			.restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 |
 					ACPI_CEDT_CFMWS_RESTRICT_VOLATILE,
-			.qtg_id = 0,
+			.qtg_id = FAKE_QTG_ID,
 			.window_size = SZ_256M * 4UL,
 		},
 		.target = { 0 },
@@ -220,7 +226,7 @@ static struct {
 			.granularity = 4,
 			.restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 |
 					ACPI_CEDT_CFMWS_RESTRICT_VOLATILE,
-			.qtg_id = 1,
+			.qtg_id = FAKE_QTG_ID,
 			.window_size = SZ_256M * 8UL,
 		},
 		.target = { 0, 1, },
@@ -235,7 +241,7 @@ static struct {
 			.granularity = 4,
 			.restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 |
 					ACPI_CEDT_CFMWS_RESTRICT_PMEM,
-			.qtg_id = 2,
+			.qtg_id = FAKE_QTG_ID,
 			.window_size = SZ_256M * 4UL,
 		},
 		.target = { 0 },
@@ -250,7 +256,7 @@ static struct {
 			.granularity = 4,
 			.restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 |
 					ACPI_CEDT_CFMWS_RESTRICT_PMEM,
-			.qtg_id = 3,
+			.qtg_id = FAKE_QTG_ID,
 			.window_size = SZ_256M * 8UL,
 		},
 		.target = { 0, 1, },
@@ -265,7 +271,7 @@ static struct {
 			.granularity = 4,
 			.restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 |
 					ACPI_CEDT_CFMWS_RESTRICT_PMEM,
-			.qtg_id = 4,
+			.qtg_id = FAKE_QTG_ID,
 			.window_size = SZ_256M * 4UL,
 		},
 		.target = { 2 },
@@ -280,7 +286,7 @@ static struct {
 			.granularity = 4,
 			.restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 |
 					ACPI_CEDT_CFMWS_RESTRICT_VOLATILE,
-			.qtg_id = 5,
+			.qtg_id = FAKE_QTG_ID,
 			.window_size = SZ_256M,
 		},
 		.target = { 3 },
@@ -297,7 +303,7 @@ static struct {
 			.granularity = 4,
 			.restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 |
 					ACPI_CEDT_CFMWS_RESTRICT_PMEM,
-			.qtg_id = 0,
+			.qtg_id = FAKE_QTG_ID,
 			.window_size = SZ_256M * 8UL,
 		},
 		.target = { 0, },
@@ -313,7 +319,7 @@ static struct {
 			.granularity = 0,
 			.restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 |
 					ACPI_CEDT_CFMWS_RESTRICT_PMEM,
-			.qtg_id = 1,
+			.qtg_id = FAKE_QTG_ID,
 			.window_size = SZ_256M * 8UL,
 		},
 		.target = { 0, 1, },
@@ -329,7 +335,7 @@ static struct {
 			.granularity = 0,
 			.restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 |
 					ACPI_CEDT_CFMWS_RESTRICT_PMEM,
-			.qtg_id = 0,
+			.qtg_id = FAKE_QTG_ID,
 			.window_size = SZ_256M * 16UL,
 		},
 		.target = { 0, 1, 0, 1, },
@@ -972,6 +978,48 @@ static int mock_cxl_port_enumerate_dports(struct cxl_port *port)
 	return 0;
 }
 
+/*
+ * Faking the cxl_dpa_perf for the memdev when appropriate.
+ */
+static void dpa_perf_setup(struct cxl_port *endpoint, struct range *range,
+			   struct cxl_dpa_perf *dpa_perf)
+{
+	dpa_perf->qos_class = FAKE_QTG_ID;
+	dpa_perf->dpa_range = *range;
+	dpa_perf->coord.read_latency = 500;
+	dpa_perf->coord.write_latency = 500;
+	dpa_perf->coord.read_bandwidth = 1000;
+	dpa_perf->coord.write_bandwidth = 1000;
+}
+
+static void mock_cxl_endpoint_parse_cdat(struct cxl_port *port)
+{
+	struct cxl_root *cxl_root __free(put_cxl_root) =
+		find_cxl_root(port);
+	struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+	struct range pmem_range = {
+		.start = cxlds->pmem_res.start,
+		.end = cxlds->pmem_res.end,
+	};
+	struct range ram_range = {
+		.start = cxlds->ram_res.start,
+		.end = cxlds->ram_res.end,
+	};
+
+	if (!cxl_root)
+		return;
+
+	if (range_len(&ram_range))
+		dpa_perf_setup(port, &ram_range, &mds->ram_perf);
+
+	if (range_len(&pmem_range))
+		dpa_perf_setup(port, &pmem_range, &mds->pmem_perf);
+
+	cxl_memdev_update_perf(cxlmd);
+}
+
 static struct cxl_mock_ops cxl_mock_ops = {
 	.is_mock_adev = is_mock_adev,
 	.is_mock_bridge = is_mock_bridge,
@@ -985,6 +1033,7 @@ static struct cxl_mock_ops cxl_mock_ops = {
 	.devm_cxl_setup_hdm = mock_cxl_setup_hdm,
 	.devm_cxl_add_passthrough_decoder = mock_cxl_add_passthrough_decoder,
 	.devm_cxl_enumerate_decoders = mock_cxl_enumerate_decoders,
+	.cxl_endpoint_parse_cdat = mock_cxl_endpoint_parse_cdat,
 	.list = LIST_HEAD_INIT(cxl_mock_ops.list),
 };
 
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index ee61fa3a2411..35ee41e435ab 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -251,7 +251,8 @@ static int mock_get_event(struct device *dev, struct cxl_mbox_cmd *cmd)
 	for (i = 0; i < CXL_TEST_EVENT_CNT && !event_log_empty(log); i++) {
 		memcpy(&pl->records[i], event_get_current(log),
 		       sizeof(pl->records[i]));
-		pl->records[i].hdr.handle = event_get_cur_event_handle(log);
+		pl->records[i].event.generic.hdr.handle =
+				event_get_cur_event_handle(log);
 		log->cur_idx++;
 	}
 
@@ -337,87 +338,109 @@ static void cxl_mock_event_trigger(struct device *dev)
 }
 
 struct cxl_event_record_raw maint_needed = {
-	.hdr = {
-		.id = UUID_INIT(0xBA5EBA11, 0xABCD, 0xEFEB,
-				0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5),
-		.length = sizeof(struct cxl_event_record_raw),
-		.flags[0] = CXL_EVENT_RECORD_FLAG_MAINT_NEEDED,
-		/* .handle = Set dynamically */
-		.related_handle = cpu_to_le16(0xa5b6),
+	.id = UUID_INIT(0xBA5EBA11, 0xABCD, 0xEFEB,
+			0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5),
+	.event.generic = {
+		.hdr = {
+			.length = sizeof(struct cxl_event_record_raw),
+			.flags[0] = CXL_EVENT_RECORD_FLAG_MAINT_NEEDED,
+			/* .handle = Set dynamically */
+			.related_handle = cpu_to_le16(0xa5b6),
+		},
+		.data = { 0xDE, 0xAD, 0xBE, 0xEF },
 	},
-	.data = { 0xDE, 0xAD, 0xBE, 0xEF },
 };
 
 struct cxl_event_record_raw hardware_replace = {
-	.hdr = {
-		.id = UUID_INIT(0xABCDEFEB, 0xBA11, 0xBA5E,
-				0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5),
-		.length = sizeof(struct cxl_event_record_raw),
-		.flags[0] = CXL_EVENT_RECORD_FLAG_HW_REPLACE,
-		/* .handle = Set dynamically */
-		.related_handle = cpu_to_le16(0xb6a5),
+	.id = UUID_INIT(0xABCDEFEB, 0xBA11, 0xBA5E,
+			0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5),
+	.event.generic = {
+		.hdr = {
+			.length = sizeof(struct cxl_event_record_raw),
+			.flags[0] = CXL_EVENT_RECORD_FLAG_HW_REPLACE,
+			/* .handle = Set dynamically */
+			.related_handle = cpu_to_le16(0xb6a5),
+		},
+		.data = { 0xDE, 0xAD, 0xBE, 0xEF },
 	},
-	.data = { 0xDE, 0xAD, 0xBE, 0xEF },
 };
 
-struct cxl_event_gen_media gen_media = {
-	.hdr = {
-		.id = UUID_INIT(0xfbcd0a77, 0xc260, 0x417f,
-				0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6),
-		.length = sizeof(struct cxl_event_gen_media),
-		.flags[0] = CXL_EVENT_RECORD_FLAG_PERMANENT,
-		/* .handle = Set dynamically */
-		.related_handle = cpu_to_le16(0),
+struct cxl_test_gen_media {
+	uuid_t id;
+	struct cxl_event_gen_media rec;
+} __packed;
+
+struct cxl_test_gen_media gen_media = {
+	.id = CXL_EVENT_GEN_MEDIA_UUID,
+	.rec = {
+		.hdr = {
+			.length = sizeof(struct cxl_test_gen_media),
+			.flags[0] = CXL_EVENT_RECORD_FLAG_PERMANENT,
+			/* .handle = Set dynamically */
+			.related_handle = cpu_to_le16(0),
+		},
+		.phys_addr = cpu_to_le64(0x2000),
+		.descriptor = CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT,
+		.type = CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR,
+		.transaction_type = CXL_GMER_TRANS_HOST_WRITE,
+		/* .validity_flags = <set below> */
+		.channel = 1,
+		.rank = 30
 	},
-	.phys_addr = cpu_to_le64(0x2000),
-	.descriptor = CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT,
-	.type = CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR,
-	.transaction_type = CXL_GMER_TRANS_HOST_WRITE,
-	/* .validity_flags = <set below> */
-	.channel = 1,
-	.rank = 30
 };
 
-struct cxl_event_dram dram = {
-	.hdr = {
-		.id = UUID_INIT(0x601dcbb3, 0x9c06, 0x4eab,
-				0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24),
-		.length = sizeof(struct cxl_event_dram),
-		.flags[0] = CXL_EVENT_RECORD_FLAG_PERF_DEGRADED,
-		/* .handle = Set dynamically */
-		.related_handle = cpu_to_le16(0),
+struct cxl_test_dram {
+	uuid_t id;
+	struct cxl_event_dram rec;
+} __packed;
+
+struct cxl_test_dram dram = {
+	.id = CXL_EVENT_DRAM_UUID,
+	.rec = {
+		.hdr = {
+			.length = sizeof(struct cxl_test_dram),
+			.flags[0] = CXL_EVENT_RECORD_FLAG_PERF_DEGRADED,
+			/* .handle = Set dynamically */
+			.related_handle = cpu_to_le16(0),
+		},
+		.phys_addr = cpu_to_le64(0x8000),
+		.descriptor = CXL_GMER_EVT_DESC_THRESHOLD_EVENT,
+		.type = CXL_GMER_MEM_EVT_TYPE_INV_ADDR,
+		.transaction_type = CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB,
+		/* .validity_flags = <set below> */
+		.channel = 1,
+		.bank_group = 5,
+		.bank = 2,
+		.column = {0xDE, 0xAD},
 	},
-	.phys_addr = cpu_to_le64(0x8000),
-	.descriptor = CXL_GMER_EVT_DESC_THRESHOLD_EVENT,
-	.type = CXL_GMER_MEM_EVT_TYPE_INV_ADDR,
-	.transaction_type = CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB,
-	/* .validity_flags = <set below> */
-	.channel = 1,
-	.bank_group = 5,
-	.bank = 2,
-	.column = {0xDE, 0xAD},
 };
 
-struct cxl_event_mem_module mem_module = {
-	.hdr = {
-		.id = UUID_INIT(0xfe927475, 0xdd59, 0x4339,
-				0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74),
-		.length = sizeof(struct cxl_event_mem_module),
-		/* .handle = Set dynamically */
-		.related_handle = cpu_to_le16(0),
+struct cxl_test_mem_module {
+	uuid_t id;
+	struct cxl_event_mem_module rec;
+} __packed;
+
+struct cxl_test_mem_module mem_module = {
+	.id = CXL_EVENT_MEM_MODULE_UUID,
+	.rec = {
+		.hdr = {
+			.length = sizeof(struct cxl_test_mem_module),
+			/* .handle = Set dynamically */
+			.related_handle = cpu_to_le16(0),
+		},
+		.event_type = CXL_MMER_TEMP_CHANGE,
+		.info = {
+			.health_status = CXL_DHI_HS_PERFORMANCE_DEGRADED,
+			.media_status = CXL_DHI_MS_ALL_DATA_LOST,
+			.add_status = (CXL_DHI_AS_CRITICAL << 2) |
+				      (CXL_DHI_AS_WARNING << 4) |
+				      (CXL_DHI_AS_WARNING << 5),
+			.device_temp = { 0xDE, 0xAD},
+			.dirty_shutdown_cnt = { 0xde, 0xad, 0xbe, 0xef },
+			.cor_vol_err_cnt = { 0xde, 0xad, 0xbe, 0xef },
+			.cor_per_err_cnt = { 0xde, 0xad, 0xbe, 0xef },
+		}
 	},
-	.event_type = CXL_MMER_TEMP_CHANGE,
-	.info = {
-		.health_status = CXL_DHI_HS_PERFORMANCE_DEGRADED,
-		.media_status = CXL_DHI_MS_ALL_DATA_LOST,
-		.add_status = (CXL_DHI_AS_CRITICAL << 2) |
-			      (CXL_DHI_AS_WARNING << 4) |
-			      (CXL_DHI_AS_WARNING << 5),
-		.device_temp = { 0xDE, 0xAD},
-		.dirty_shutdown_cnt = { 0xde, 0xad, 0xbe, 0xef },
-		.cor_vol_err_cnt = { 0xde, 0xad, 0xbe, 0xef },
-		.cor_per_err_cnt = { 0xde, 0xad, 0xbe, 0xef },
-	}
 };
 
 static int mock_set_timestamp(struct cxl_dev_state *cxlds,
@@ -439,11 +462,11 @@ static int mock_set_timestamp(struct cxl_dev_state *cxlds,
 static void cxl_mock_add_event_logs(struct mock_event_store *mes)
 {
 	put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK,
-			   &gen_media.validity_flags);
+			   &gen_media.rec.validity_flags);
 
 	put_unaligned_le16(CXL_DER_VALID_CHANNEL | CXL_DER_VALID_BANK_GROUP |
 			   CXL_DER_VALID_BANK | CXL_DER_VALID_COLUMN,
-			   &dram.validity_flags);
+			   &dram.rec.validity_flags);
 
 	mes_add_event(mes, CXL_EVENT_TYPE_INFO, &maint_needed);
 	mes_add_event(mes, CXL_EVENT_TYPE_INFO,
diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c
index 1a61e68e3095..6f737941dc0e 100644
--- a/tools/testing/cxl/test/mock.c
+++ b/tools/testing/cxl/test/mock.c
@@ -285,6 +285,20 @@ resource_size_t __wrap_cxl_rcd_component_reg_phys(struct device *dev,
 }
 EXPORT_SYMBOL_NS_GPL(__wrap_cxl_rcd_component_reg_phys, CXL);
 
+void __wrap_cxl_endpoint_parse_cdat(struct cxl_port *port)
+{
+	int index;
+	struct cxl_mock_ops *ops = get_cxl_mock_ops(&index);
+	struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev);
+
+	if (ops && ops->is_mock_dev(cxlmd->dev.parent))
+		ops->cxl_endpoint_parse_cdat(port);
+	else
+		cxl_endpoint_parse_cdat(port);
+	put_cxl_mock_ops(index);
+}
+EXPORT_SYMBOL_NS_GPL(__wrap_cxl_endpoint_parse_cdat, CXL);
+
 MODULE_LICENSE("GPL v2");
 MODULE_IMPORT_NS(ACPI);
 MODULE_IMPORT_NS(CXL);
diff --git a/tools/testing/cxl/test/mock.h b/tools/testing/cxl/test/mock.h
index a94223750346..d1b0271d2822 100644
--- a/tools/testing/cxl/test/mock.h
+++ b/tools/testing/cxl/test/mock.h
@@ -25,6 +25,7 @@ struct cxl_mock_ops {
 	int (*devm_cxl_add_passthrough_decoder)(struct cxl_port *port);
 	int (*devm_cxl_enumerate_decoders)(
 		struct cxl_hdm *hdm, struct cxl_endpoint_dvsec_info *info);
+	void (*cxl_endpoint_parse_cdat)(struct cxl_port *port);
 };
 
 void register_cxl_mock_ops(struct cxl_mock_ops *ops);
diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py
index 0b6488efed47..7254c110ff23 100644
--- a/tools/testing/kunit/kunit_kernel.py
+++ b/tools/testing/kunit/kunit_kernel.py
@@ -146,6 +146,7 @@ class LinuxSourceTreeOperationsUml(LinuxSourceTreeOperations):
 		"""Runs the Linux UML binary. Must be named 'linux'."""
 		linux_bin = os.path.join(build_dir, 'linux')
 		params.extend(['mem=1G', 'console=tty', 'kunit_shutdown=halt'])
+		print('Running tests with:\n$', linux_bin, ' '.join(shlex.quote(arg) for arg in params))
 		return subprocess.Popen([linux_bin] + params,
 					   stdin=subprocess.PIPE,
 					   stdout=subprocess.PIPE,
diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild
index 8153251ea389..91a3627f301a 100644
--- a/tools/testing/nvdimm/Kbuild
+++ b/tools/testing/nvdimm/Kbuild
@@ -82,4 +82,6 @@ libnvdimm-$(CONFIG_NVDIMM_KEYS) += $(NVDIMM_SRC)/security.o
 libnvdimm-y += libnvdimm_test.o
 libnvdimm-y += config_check.o
 
+KBUILD_CFLAGS := $(filter-out -Wmissing-prototypes -Wmissing-declarations, $(KBUILD_CFLAGS))
+
 obj-m += test/
diff --git a/tools/testing/nvdimm/test/Kbuild b/tools/testing/nvdimm/test/Kbuild
index 197bcb2b7f35..003d48f5f24f 100644
--- a/tools/testing/nvdimm/test/Kbuild
+++ b/tools/testing/nvdimm/test/Kbuild
@@ -7,6 +7,7 @@ obj-m += nfit_test_iomap.o
 
 ifeq  ($(CONFIG_ACPI_NFIT),m)
 	nfit_test-y := nfit.o
+	obj-m += ndtest.o
 else
 	nfit_test-y := ndtest.o
 endif
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 15b6a111c3be..cd9ae576bfde 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -67,6 +67,7 @@ TARGETS += nsfs
 TARGETS += perf_events
 TARGETS += pidfd
 TARGETS += pid_namespace
+TARGETS += power_supply
 TARGETS += powerpc
 TARGETS += prctl
 TARGETS += proc
@@ -78,6 +79,7 @@ TARGETS += riscv
 TARGETS += rlimits
 TARGETS += rseq
 TARGETS += rtc
+TARGETS += rust
 TARGETS += seccomp
 TARGETS += sgx
 TARGETS += sigaltstack
@@ -236,6 +238,7 @@ ifdef INSTALL_PATH
 	install -m 744 kselftest/module.sh $(INSTALL_PATH)/kselftest/
 	install -m 744 kselftest/runner.sh $(INSTALL_PATH)/kselftest/
 	install -m 744 kselftest/prefix.pl $(INSTALL_PATH)/kselftest/
+	install -m 744 kselftest/ktap_helpers.sh $(INSTALL_PATH)/kselftest/
 	install -m 744 run_kselftest.sh $(INSTALL_PATH)/
 	rm -f $(TEST_LIST)
 	@ret=1;	\
diff --git a/tools/testing/selftests/bpf/prog_tests/iters.c b/tools/testing/selftests/bpf/prog_tests/iters.c
index bf84d4a1d9ae..3c440370c1f0 100644
--- a/tools/testing/selftests/bpf/prog_tests/iters.c
+++ b/tools/testing/selftests/bpf/prog_tests/iters.c
@@ -193,6 +193,7 @@ static void subtest_task_iters(void)
 	ASSERT_EQ(skel->bss->procs_cnt, 1, "procs_cnt");
 	ASSERT_EQ(skel->bss->threads_cnt, thread_num + 1, "threads_cnt");
 	ASSERT_EQ(skel->bss->proc_threads_cnt, thread_num + 1, "proc_threads_cnt");
+	ASSERT_EQ(skel->bss->invalid_cnt, 0, "invalid_cnt");
 	pthread_mutex_unlock(&do_nothing_mutex);
 	for (int i = 0; i < thread_num; i++)
 		ASSERT_OK(pthread_join(thread_ids[i], &ret), "pthread_join");
diff --git a/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c b/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c
new file mode 100644
index 000000000000..3405923fe4e6
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2024. Huawei Technologies Co., Ltd */
+#include "test_progs.h"
+#include "read_vsyscall.skel.h"
+
+#if defined(__x86_64__)
+/* For VSYSCALL_ADDR */
+#include <asm/vsyscall.h>
+#else
+/* To prevent build failure on non-x86 arch */
+#define VSYSCALL_ADDR 0UL
+#endif
+
+struct read_ret_desc {
+	const char *name;
+	int ret;
+} all_read[] = {
+	{ .name = "probe_read_kernel", .ret = -ERANGE },
+	{ .name = "probe_read_kernel_str", .ret = -ERANGE },
+	{ .name = "probe_read", .ret = -ERANGE },
+	{ .name = "probe_read_str", .ret = -ERANGE },
+	{ .name = "probe_read_user", .ret = -EFAULT },
+	{ .name = "probe_read_user_str", .ret = -EFAULT },
+	{ .name = "copy_from_user", .ret = -EFAULT },
+	{ .name = "copy_from_user_task", .ret = -EFAULT },
+};
+
+void test_read_vsyscall(void)
+{
+	struct read_vsyscall *skel;
+	unsigned int i;
+	int err;
+
+#if !defined(__x86_64__)
+	test__skip();
+	return;
+#endif
+	skel = read_vsyscall__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "read_vsyscall open_load"))
+		return;
+
+	skel->bss->target_pid = getpid();
+	err = read_vsyscall__attach(skel);
+	if (!ASSERT_EQ(err, 0, "read_vsyscall attach"))
+		goto out;
+
+	/* userspace may don't have vsyscall page due to LEGACY_VSYSCALL_NONE,
+	 * but it doesn't affect the returned error codes.
+	 */
+	skel->bss->user_ptr = (void *)VSYSCALL_ADDR;
+	usleep(1);
+
+	for (i = 0; i < ARRAY_SIZE(all_read); i++)
+		ASSERT_EQ(skel->bss->read_ret[i], all_read[i].ret, all_read[i].name);
+out:
+	read_vsyscall__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
new file mode 100644
index 000000000000..0c365f36c73b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2024 Meta
+
+#include <test_progs.h>
+#include "network_helpers.h"
+#include "sock_iter_batch.skel.h"
+
+#define TEST_NS "sock_iter_batch_netns"
+
+static const int nr_soreuse = 4;
+
+static void do_test(int sock_type, bool onebyone)
+{
+	int err, i, nread, to_read, total_read, iter_fd = -1;
+	int first_idx, second_idx, indices[nr_soreuse];
+	struct bpf_link *link = NULL;
+	struct sock_iter_batch *skel;
+	int *fds[2] = {};
+
+	skel = sock_iter_batch__open();
+	if (!ASSERT_OK_PTR(skel, "sock_iter_batch__open"))
+		return;
+
+	/* Prepare 2 buckets of sockets in the kernel hashtable */
+	for (i = 0; i < ARRAY_SIZE(fds); i++) {
+		int local_port;
+
+		fds[i] = start_reuseport_server(AF_INET6, sock_type, "::1", 0, 0,
+						nr_soreuse);
+		if (!ASSERT_OK_PTR(fds[i], "start_reuseport_server"))
+			goto done;
+		local_port = get_socket_local_port(*fds[i]);
+		if (!ASSERT_GE(local_port, 0, "get_socket_local_port"))
+			goto done;
+		skel->rodata->ports[i] = ntohs(local_port);
+	}
+
+	err = sock_iter_batch__load(skel);
+	if (!ASSERT_OK(err, "sock_iter_batch__load"))
+		goto done;
+
+	link = bpf_program__attach_iter(sock_type == SOCK_STREAM ?
+					skel->progs.iter_tcp_soreuse :
+					skel->progs.iter_udp_soreuse,
+					NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter"))
+		goto done;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (!ASSERT_GE(iter_fd, 0, "bpf_iter_create"))
+		goto done;
+
+	/* Test reading a bucket (either from fds[0] or fds[1]).
+	 * Only read "nr_soreuse - 1" number of sockets
+	 * from a bucket and leave one socket out from
+	 * that bucket on purpose.
+	 */
+	to_read = (nr_soreuse - 1) * sizeof(*indices);
+	total_read = 0;
+	first_idx = -1;
+	do {
+		nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read);
+		if (nread <= 0 || nread % sizeof(*indices))
+			break;
+		total_read += nread;
+
+		if (first_idx == -1)
+			first_idx = indices[0];
+		for (i = 0; i < nread / sizeof(*indices); i++)
+			ASSERT_EQ(indices[i], first_idx, "first_idx");
+	} while (total_read < to_read);
+	ASSERT_EQ(nread, onebyone ? sizeof(*indices) : to_read, "nread");
+	ASSERT_EQ(total_read, to_read, "total_read");
+
+	free_fds(fds[first_idx], nr_soreuse);
+	fds[first_idx] = NULL;
+
+	/* Read the "whole" second bucket */
+	to_read = nr_soreuse * sizeof(*indices);
+	total_read = 0;
+	second_idx = !first_idx;
+	do {
+		nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read);
+		if (nread <= 0 || nread % sizeof(*indices))
+			break;
+		total_read += nread;
+
+		for (i = 0; i < nread / sizeof(*indices); i++)
+			ASSERT_EQ(indices[i], second_idx, "second_idx");
+	} while (total_read <= to_read);
+	ASSERT_EQ(nread, 0, "nread");
+	/* Both so_reuseport ports should be in different buckets, so
+	 * total_read must equal to the expected to_read.
+	 *
+	 * For a very unlikely case, both ports collide at the same bucket,
+	 * the bucket offset (i.e. 3) will be skipped and it cannot
+	 * expect the to_read number of bytes.
+	 */
+	if (skel->bss->bucket[0] != skel->bss->bucket[1])
+		ASSERT_EQ(total_read, to_read, "total_read");
+
+done:
+	for (i = 0; i < ARRAY_SIZE(fds); i++)
+		free_fds(fds[i], nr_soreuse);
+	if (iter_fd < 0)
+		close(iter_fd);
+	bpf_link__destroy(link);
+	sock_iter_batch__destroy(skel);
+}
+
+void test_sock_iter_batch(void)
+{
+	struct nstoken *nstoken = NULL;
+
+	SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null");
+	SYS(done, "ip netns add %s", TEST_NS);
+	SYS(done, "ip -net %s link set dev lo up", TEST_NS);
+
+	nstoken = open_netns(TEST_NS);
+	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+		goto done;
+
+	if (test__start_subtest("tcp")) {
+		do_test(SOCK_STREAM, true);
+		do_test(SOCK_STREAM, false);
+	}
+	if (test__start_subtest("udp")) {
+		do_test(SOCK_DGRAM, true);
+		do_test(SOCK_DGRAM, false);
+	}
+	close_netns(nstoken);
+
+done:
+	SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null");
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
index 67d4ef9e62b3..e905cbaf6b3d 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
@@ -47,6 +47,19 @@ static void subtest_ctx_arg_rewrite(void)
 	struct btf *btf = NULL;
 	__u32 info_len = sizeof(info);
 	int err, fd, i;
+	struct btf *kern_btf = NULL;
+
+	kern_btf = btf__load_vmlinux_btf();
+	if (!ASSERT_OK_PTR(kern_btf, "kern_btf_load"))
+		return;
+
+	/* simple detection of kernel native arg:ctx tag support */
+	if (btf__find_by_name_kind(kern_btf, "bpf_subprog_arg_info", BTF_KIND_STRUCT) > 0) {
+		test__skip();
+		btf__free(kern_btf);
+		return;
+	}
+	btf__free(kern_btf);
 
 	skel = test_global_func_ctx_args__open();
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c
index 760ad96b4be0..d66687f1ee6a 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer.c
@@ -4,10 +4,29 @@
 #include "timer.skel.h"
 #include "timer_failure.skel.h"
 
+#define NUM_THR 8
+
+static void *spin_lock_thread(void *arg)
+{
+	int i, err, prog_fd = *(int *)arg;
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+
+	for (i = 0; i < 10000; i++) {
+		err = bpf_prog_test_run_opts(prog_fd, &topts);
+		if (!ASSERT_OK(err, "test_run_opts err") ||
+		    !ASSERT_OK(topts.retval, "test_run_opts retval"))
+			break;
+	}
+
+	pthread_exit(arg);
+}
+
 static int timer(struct timer *timer_skel)
 {
-	int err, prog_fd;
+	int i, err, prog_fd;
 	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	pthread_t thread_id[NUM_THR];
+	void *ret;
 
 	err = timer__attach(timer_skel);
 	if (!ASSERT_OK(err, "timer_attach"))
@@ -43,6 +62,20 @@ static int timer(struct timer *timer_skel)
 	/* check that code paths completed */
 	ASSERT_EQ(timer_skel->bss->ok, 1 | 2 | 4, "ok");
 
+	prog_fd = bpf_program__fd(timer_skel->progs.race);
+	for (i = 0; i < NUM_THR; i++) {
+		err = pthread_create(&thread_id[i], NULL,
+				     &spin_lock_thread, &prog_fd);
+		if (!ASSERT_OK(err, "pthread_create"))
+			break;
+	}
+
+	while (i) {
+		err = pthread_join(thread_id[--i], &ret);
+		if (ASSERT_OK(err, "pthread_join"))
+			ASSERT_EQ(ret, (void *)&prog_fd, "pthread_join");
+	}
+
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
index c3b45745cbcc..6d8b54124cb3 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
@@ -511,7 +511,7 @@ static void test_xdp_bonding_features(struct skeletons *skeletons)
 	if (!ASSERT_OK(err, "bond bpf_xdp_query"))
 		goto out;
 
-	if (!ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_MASK,
+	if (!ASSERT_EQ(query_opts.feature_flags, 0,
 		       "bond query_opts.feature_flags"))
 		goto out;
 
@@ -601,7 +601,7 @@ static void test_xdp_bonding_features(struct skeletons *skeletons)
 	if (!ASSERT_OK(err, "bond bpf_xdp_query"))
 		goto out;
 
-	ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_MASK,
+	ASSERT_EQ(query_opts.feature_flags, 0,
 		  "bond query_opts.feature_flags");
 out:
 	bpf_link__destroy(link);
diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
index 1bdc680b0e0e..e8bd4b7b5ef7 100644
--- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
+++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
@@ -72,6 +72,8 @@
 #define inet_rcv_saddr		sk.__sk_common.skc_rcv_saddr
 #define inet_dport		sk.__sk_common.skc_dport
 
+#define udp_portaddr_hash	inet.sk.__sk_common.skc_u16hashes[1]
+
 #define ir_loc_addr		req.__req_common.skc_rcv_saddr
 #define ir_num			req.__req_common.skc_num
 #define ir_rmt_addr		req.__req_common.skc_daddr
@@ -85,6 +87,7 @@
 #define sk_rmem_alloc		sk_backlog.rmem_alloc
 #define sk_refcnt		__sk_common.skc_refcnt
 #define sk_state		__sk_common.skc_state
+#define sk_net			__sk_common.skc_net
 #define sk_v6_daddr		__sk_common.skc_v6_daddr
 #define sk_v6_rcv_saddr		__sk_common.skc_v6_rcv_saddr
 #define sk_flags		__sk_common.skc_flags
diff --git a/tools/testing/selftests/bpf/progs/iters_task.c b/tools/testing/selftests/bpf/progs/iters_task.c
index c9b4055cd410..e4d53e40ff20 100644
--- a/tools/testing/selftests/bpf/progs/iters_task.c
+++ b/tools/testing/selftests/bpf/progs/iters_task.c
@@ -10,7 +10,7 @@
 char _license[] SEC("license") = "GPL";
 
 pid_t target_pid;
-int procs_cnt, threads_cnt, proc_threads_cnt;
+int procs_cnt, threads_cnt, proc_threads_cnt, invalid_cnt;
 
 void bpf_rcu_read_lock(void) __ksym;
 void bpf_rcu_read_unlock(void) __ksym;
@@ -26,6 +26,16 @@ int iter_task_for_each_sleep(void *ctx)
 	procs_cnt = threads_cnt = proc_threads_cnt = 0;
 
 	bpf_rcu_read_lock();
+	bpf_for_each(task, pos, NULL, ~0U) {
+		/* Below instructions shouldn't be executed for invalid flags */
+		invalid_cnt++;
+	}
+
+	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_PROC_THREADS) {
+		/* Below instructions shouldn't be executed for invalid task__nullable */
+		invalid_cnt++;
+	}
+
 	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS)
 		if (pos->pid == target_pid)
 			procs_cnt++;
diff --git a/tools/testing/selftests/bpf/progs/read_vsyscall.c b/tools/testing/selftests/bpf/progs/read_vsyscall.c
new file mode 100644
index 000000000000..986f96687ae1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/read_vsyscall.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2024. Huawei Technologies Co., Ltd */
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+
+int target_pid = 0;
+void *user_ptr = 0;
+int read_ret[8];
+
+char _license[] SEC("license") = "GPL";
+
+SEC("fentry/" SYS_PREFIX "sys_nanosleep")
+int do_probe_read(void *ctx)
+{
+	char buf[8];
+
+	if ((bpf_get_current_pid_tgid() >> 32) != target_pid)
+		return 0;
+
+	read_ret[0] = bpf_probe_read_kernel(buf, sizeof(buf), user_ptr);
+	read_ret[1] = bpf_probe_read_kernel_str(buf, sizeof(buf), user_ptr);
+	read_ret[2] = bpf_probe_read(buf, sizeof(buf), user_ptr);
+	read_ret[3] = bpf_probe_read_str(buf, sizeof(buf), user_ptr);
+	read_ret[4] = bpf_probe_read_user(buf, sizeof(buf), user_ptr);
+	read_ret[5] = bpf_probe_read_user_str(buf, sizeof(buf), user_ptr);
+
+	return 0;
+}
+
+SEC("fentry.s/" SYS_PREFIX "sys_nanosleep")
+int do_copy_from_user(void *ctx)
+{
+	char buf[8];
+
+	if ((bpf_get_current_pid_tgid() >> 32) != target_pid)
+		return 0;
+
+	read_ret[6] = bpf_copy_from_user(buf, sizeof(buf), user_ptr);
+	read_ret[7] = bpf_copy_from_user_task(buf, sizeof(buf), user_ptr,
+					      bpf_get_current_task_btf(), 0);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/sock_iter_batch.c b/tools/testing/selftests/bpf/progs/sock_iter_batch.c
new file mode 100644
index 000000000000..ffbbfe1fa1c1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/sock_iter_batch.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2024 Meta
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_endian.h>
+#include "bpf_tracing_net.h"
+#include "bpf_kfuncs.h"
+
+#define ATTR __always_inline
+#include "test_jhash.h"
+
+static bool ipv6_addr_loopback(const struct in6_addr *a)
+{
+	return (a->s6_addr32[0] | a->s6_addr32[1] |
+		a->s6_addr32[2] | (a->s6_addr32[3] ^ bpf_htonl(1))) == 0;
+}
+
+volatile const __u16 ports[2];
+unsigned int bucket[2];
+
+SEC("iter/tcp")
+int iter_tcp_soreuse(struct bpf_iter__tcp *ctx)
+{
+	struct sock *sk = (struct sock *)ctx->sk_common;
+	struct inet_hashinfo *hinfo;
+	unsigned int hash;
+	struct net *net;
+	int idx;
+
+	if (!sk)
+		return 0;
+
+	sk = bpf_rdonly_cast(sk, bpf_core_type_id_kernel(struct sock));
+	if (sk->sk_family != AF_INET6 ||
+	    sk->sk_state != TCP_LISTEN ||
+	    !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr))
+		return 0;
+
+	if (sk->sk_num == ports[0])
+		idx = 0;
+	else if (sk->sk_num == ports[1])
+		idx = 1;
+	else
+		return 0;
+
+	/* bucket selection as in inet_lhash2_bucket_sk() */
+	net = sk->sk_net.net;
+	hash = jhash2(sk->sk_v6_rcv_saddr.s6_addr32, 4, net->hash_mix);
+	hash ^= sk->sk_num;
+	hinfo = net->ipv4.tcp_death_row.hashinfo;
+	bucket[idx] = hash & hinfo->lhash2_mask;
+	bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx));
+
+	return 0;
+}
+
+#define udp_sk(ptr) container_of(ptr, struct udp_sock, inet.sk)
+
+SEC("iter/udp")
+int iter_udp_soreuse(struct bpf_iter__udp *ctx)
+{
+	struct sock *sk = (struct sock *)ctx->udp_sk;
+	struct udp_table *udptable;
+	int idx;
+
+	if (!sk)
+		return 0;
+
+	sk = bpf_rdonly_cast(sk, bpf_core_type_id_kernel(struct sock));
+	if (sk->sk_family != AF_INET6 ||
+	    !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr))
+		return 0;
+
+	if (sk->sk_num == ports[0])
+		idx = 0;
+	else if (sk->sk_num == ports[1])
+		idx = 1;
+	else
+		return 0;
+
+	/* bucket selection as in udp_hashslot2() */
+	udptable = sk->sk_net.net->ipv4.udp_table;
+	bucket[idx] = udp_sk(sk)->udp_portaddr_hash & udptable->mask;
+	bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx));
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_jhash.h b/tools/testing/selftests/bpf/progs/test_jhash.h
index c300734d26f6..ef53559bbbdf 100644
--- a/tools/testing/selftests/bpf/progs/test_jhash.h
+++ b/tools/testing/selftests/bpf/progs/test_jhash.h
@@ -69,3 +69,34 @@ u32 jhash(const void *key, u32 length, u32 initval)
 
 	return c;
 }
+
+static __always_inline u32 jhash2(const u32 *k, u32 length, u32 initval)
+{
+	u32 a, b, c;
+
+	/* Set up the internal state */
+	a = b = c = JHASH_INITVAL + (length<<2) + initval;
+
+	/* Handle most of the key */
+	while (length > 3) {
+		a += k[0];
+		b += k[1];
+		c += k[2];
+		__jhash_mix(a, b, c);
+		length -= 3;
+		k += 3;
+	}
+
+	/* Handle the last 3 u32's */
+	switch (length) {
+	case 3: c += k[2];
+	case 2: b += k[1];
+	case 1: a += k[0];
+		__jhash_final(a, b, c);
+		break;
+	case 0:	/* Nothing left to add */
+		break;
+	}
+
+	return c;
+}
diff --git a/tools/testing/selftests/bpf/progs/timer.c b/tools/testing/selftests/bpf/progs/timer.c
index 8b946c8188c6..f615da97df26 100644
--- a/tools/testing/selftests/bpf/progs/timer.c
+++ b/tools/testing/selftests/bpf/progs/timer.c
@@ -51,7 +51,8 @@ struct {
 	__uint(max_entries, 1);
 	__type(key, int);
 	__type(value, struct elem);
-} abs_timer SEC(".maps"), soft_timer_pinned SEC(".maps"), abs_timer_pinned SEC(".maps");
+} abs_timer SEC(".maps"), soft_timer_pinned SEC(".maps"), abs_timer_pinned SEC(".maps"),
+	race_array SEC(".maps");
 
 __u64 bss_data;
 __u64 abs_data;
@@ -390,3 +391,34 @@ int BPF_PROG2(test5, int, a)
 
 	return 0;
 }
+
+static int race_timer_callback(void *race_array, int *race_key, struct bpf_timer *timer)
+{
+	bpf_timer_start(timer, 1000000, 0);
+	return 0;
+}
+
+SEC("syscall")
+int race(void *ctx)
+{
+	struct bpf_timer *timer;
+	int err, race_key = 0;
+	struct elem init;
+
+	__builtin_memset(&init, 0, sizeof(struct elem));
+	bpf_map_update_elem(&race_array, &race_key, &init, BPF_ANY);
+
+	timer = bpf_map_lookup_elem(&race_array, &race_key);
+	if (!timer)
+		return 1;
+
+	err = bpf_timer_init(timer, &race_array, CLOCK_MONOTONIC);
+	if (err && err != -EBUSY)
+		return 1;
+
+	bpf_timer_set_callback(timer, race_timer_callback);
+	bpf_timer_start(timer, 0, 0);
+	bpf_timer_cancel(timer);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
index 9eeb2d89cda8..67dddd941891 100644
--- a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
+++ b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
@@ -3,6 +3,7 @@
 
 #include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 #include "bpf_misc.h"
 #include "xdp_metadata.h"
 #include "bpf_kfuncs.h"
@@ -138,25 +139,182 @@ __weak int subprog_ctx_tag(void *ctx __arg_ctx)
 	return bpf_get_stack(ctx, stack, sizeof(stack), 0);
 }
 
+__weak int raw_tp_canonical(struct bpf_raw_tracepoint_args *ctx __arg_ctx)
+{
+	return 0;
+}
+
+__weak int raw_tp_u64_array(u64 *ctx __arg_ctx)
+{
+	return 0;
+}
+
 SEC("?raw_tp")
 __success __log_level(2)
 int arg_tag_ctx_raw_tp(void *ctx)
 {
-	return subprog_ctx_tag(ctx);
+	return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx);
+}
+
+SEC("?raw_tp.w")
+__success __log_level(2)
+int arg_tag_ctx_raw_tp_writable(void *ctx)
+{
+	return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx);
+}
+
+SEC("?tp_btf/sys_enter")
+__success __log_level(2)
+int arg_tag_ctx_raw_tp_btf(void *ctx)
+{
+	return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx);
+}
+
+struct whatever { };
+
+__weak int tp_whatever(struct whatever *ctx __arg_ctx)
+{
+	return 0;
 }
 
 SEC("?tp")
 __success __log_level(2)
 int arg_tag_ctx_tp(void *ctx)
 {
-	return subprog_ctx_tag(ctx);
+	return subprog_ctx_tag(ctx) + tp_whatever(ctx);
+}
+
+__weak int kprobe_subprog_pt_regs(struct pt_regs *ctx __arg_ctx)
+{
+	return 0;
+}
+
+__weak int kprobe_subprog_typedef(bpf_user_pt_regs_t *ctx __arg_ctx)
+{
+	return 0;
 }
 
 SEC("?kprobe")
 __success __log_level(2)
 int arg_tag_ctx_kprobe(void *ctx)
 {
-	return subprog_ctx_tag(ctx);
+	return subprog_ctx_tag(ctx) +
+	       kprobe_subprog_pt_regs(ctx) +
+	       kprobe_subprog_typedef(ctx);
+}
+
+__weak int perf_subprog_regs(
+#if defined(bpf_target_riscv)
+	struct user_regs_struct *ctx __arg_ctx
+#elif defined(bpf_target_s390)
+	/* user_pt_regs typedef is anonymous struct, so only `void *` works */
+	void *ctx __arg_ctx
+#elif defined(bpf_target_loongarch) || defined(bpf_target_arm64) || defined(bpf_target_powerpc)
+	struct user_pt_regs *ctx __arg_ctx
+#else
+	struct pt_regs *ctx __arg_ctx
+#endif
+)
+{
+	return 0;
+}
+
+__weak int perf_subprog_typedef(bpf_user_pt_regs_t *ctx __arg_ctx)
+{
+	return 0;
+}
+
+__weak int perf_subprog_canonical(struct bpf_perf_event_data *ctx __arg_ctx)
+{
+	return 0;
+}
+
+SEC("?perf_event")
+__success __log_level(2)
+int arg_tag_ctx_perf(void *ctx)
+{
+	return subprog_ctx_tag(ctx) +
+	       perf_subprog_regs(ctx) +
+	       perf_subprog_typedef(ctx) +
+	       perf_subprog_canonical(ctx);
+}
+
+__weak int iter_subprog_void(void *ctx __arg_ctx)
+{
+	return 0;
+}
+
+__weak int iter_subprog_typed(struct bpf_iter__task *ctx __arg_ctx)
+{
+	return 0;
+}
+
+SEC("?iter/task")
+__success __log_level(2)
+int arg_tag_ctx_iter_task(struct bpf_iter__task *ctx)
+{
+	return (iter_subprog_void(ctx) + iter_subprog_typed(ctx)) & 1;
+}
+
+__weak int tracing_subprog_void(void *ctx __arg_ctx)
+{
+	return 0;
+}
+
+__weak int tracing_subprog_u64(u64 *ctx __arg_ctx)
+{
+	return 0;
+}
+
+int acc;
+
+SEC("?fentry/" SYS_PREFIX "sys_nanosleep")
+__success __log_level(2)
+int BPF_PROG(arg_tag_ctx_fentry)
+{
+	acc += tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+	return 0;
+}
+
+SEC("?fexit/" SYS_PREFIX "sys_nanosleep")
+__success __log_level(2)
+int BPF_PROG(arg_tag_ctx_fexit)
+{
+	acc += tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+	return 0;
+}
+
+SEC("?fmod_ret/" SYS_PREFIX "sys_nanosleep")
+__success __log_level(2)
+int BPF_PROG(arg_tag_ctx_fmod_ret)
+{
+	return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+}
+
+SEC("?lsm/bpf")
+__success __log_level(2)
+int BPF_PROG(arg_tag_ctx_lsm)
+{
+	return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+}
+
+SEC("?struct_ops/test_1")
+__success __log_level(2)
+int BPF_PROG(arg_tag_ctx_struct_ops)
+{
+	return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+}
+
+SEC(".struct_ops")
+struct bpf_dummy_ops dummy_1 = {
+	.test_1 = (void *)arg_tag_ctx_struct_ops,
+};
+
+SEC("?syscall")
+__success __log_level(2)
+int arg_tag_ctx_syscall(void *ctx)
+{
+	return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx) + tp_whatever(ctx);
 }
 
 __weak int subprog_dynptr(struct bpf_dynptr *dptr)
diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
index 5905e036e0ea..a955a6358206 100644
--- a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
+++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
@@ -239,4 +239,74 @@ int bpf_loop_iter_limit_nested(void *unused)
 	return 1000 * a + b + c;
 }
 
+struct iter_limit_bug_ctx {
+	__u64 a;
+	__u64 b;
+	__u64 c;
+};
+
+static __naked void iter_limit_bug_cb(void)
+{
+	/* This is the same as C code below, but written
+	 * in assembly to control which branches are fall-through.
+	 *
+	 *   switch (bpf_get_prandom_u32()) {
+	 *   case 1:  ctx->a = 42; break;
+	 *   case 2:  ctx->b = 42; break;
+	 *   default: ctx->c = 42; break;
+	 *   }
+	 */
+	asm volatile (
+	"r9 = r2;"
+	"call %[bpf_get_prandom_u32];"
+	"r1 = r0;"
+	"r2 = 42;"
+	"r0 = 0;"
+	"if r1 == 0x1 goto 1f;"
+	"if r1 == 0x2 goto 2f;"
+	"*(u64 *)(r9 + 16) = r2;"
+	"exit;"
+	"1: *(u64 *)(r9 + 0) = r2;"
+	"exit;"
+	"2: *(u64 *)(r9 + 8) = r2;"
+	"exit;"
+	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all
+	);
+}
+
+SEC("tc")
+__failure
+__flag(BPF_F_TEST_STATE_FREQ)
+int iter_limit_bug(struct __sk_buff *skb)
+{
+	struct iter_limit_bug_ctx ctx = { 7, 7, 7 };
+
+	bpf_loop(2, iter_limit_bug_cb, &ctx, 0);
+
+	/* This is the same as C code below,
+	 * written in assembly to guarantee checks order.
+	 *
+	 *   if (ctx.a == 42 && ctx.b == 42 && ctx.c == 7)
+	 *     asm volatile("r1 /= 0;":::"r1");
+	 */
+	asm volatile (
+	"r1 = *(u64 *)%[ctx_a];"
+	"if r1 != 42 goto 1f;"
+	"r1 = *(u64 *)%[ctx_b];"
+	"if r1 != 42 goto 1f;"
+	"r1 = *(u64 *)%[ctx_c];"
+	"if r1 != 7 goto 1f;"
+	"r1 /= 0;"
+	"1:"
+	:
+	: [ctx_a]"m"(ctx.a),
+	  [ctx_b]"m"(ctx.b),
+	  [ctx_c]"m"(ctx.c)
+	: "r1"
+	);
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c b/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c
index 71814a753216..a9ab37d3b9e2 100644
--- a/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c
+++ b/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c
@@ -146,4 +146,23 @@ l0_%=:	exit;						\
 	: __clobber_all);
 }
 
+SEC("flow_dissector")
+__description("flow_keys illegal alu op with variable offset")
+__failure __msg("R7 pointer arithmetic on flow_keys prohibited")
+__naked void flow_keys_illegal_variable_offset_alu(void)
+{
+	asm volatile("					\
+	r6 = r1;					\
+	r7 = *(u64*)(r6 + %[flow_keys_off]);		\
+	r8 = 8;						\
+	r8 /= 1;					\
+	r8 &= 8;					\
+	r7 += r8;					\
+	r0 = *(u64*)(r7 + 0);				\
+	exit;						\
+"	:
+	: __imm_const(flow_keys_off, offsetof(struct __sk_buff, flow_keys))
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c
index 534576f06df1..c59e4adb905d 100644
--- a/tools/testing/selftests/core/close_range_test.c
+++ b/tools/testing/selftests/core/close_range_test.c
@@ -12,6 +12,7 @@
 #include <syscall.h>
 #include <unistd.h>
 #include <sys/resource.h>
+#include <linux/close_range.h>
 
 #include "../kselftest_harness.h"
 #include "../clone3/clone3_selftests.h"
diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh
index c54d1697f439..9a3d3c389dad 100755
--- a/tools/testing/selftests/drivers/net/bonding/bond_options.sh
+++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh
@@ -62,6 +62,8 @@ prio_test()
 
 	# create bond
 	bond_reset "${param}"
+	# set active_slave to primary eth1 specifically
+	ip -n ${s_ns} link set bond0 type bond active_slave eth1
 
 	# check bonding member prio value
 	ip -n ${s_ns} link set eth0 type bond_slave prio 0
@@ -162,7 +164,7 @@ prio_arp()
 	local mode=$1
 
 	for primary_reselect in 0 1 2; do
-		prio_test "mode active-backup arp_interval 100 arp_ip_target ${g_ip4} primary eth1 primary_reselect $primary_reselect"
+		prio_test "mode $mode arp_interval 100 arp_ip_target ${g_ip4} primary eth1 primary_reselect $primary_reselect"
 		log_test "prio" "$mode arp_ip_target primary_reselect $primary_reselect"
 	done
 }
@@ -178,7 +180,7 @@ prio_ns()
 	fi
 
 	for primary_reselect in 0 1 2; do
-		prio_test "mode active-backup arp_interval 100 ns_ip6_target ${g_ip6} primary eth1 primary_reselect $primary_reselect"
+		prio_test "mode $mode arp_interval 100 ns_ip6_target ${g_ip6} primary eth1 primary_reselect $primary_reselect"
 		log_test "prio" "$mode ns_ip6_target primary_reselect $primary_reselect"
 	done
 }
@@ -194,9 +196,9 @@ prio()
 
 	for mode in $modes; do
 		prio_miimon $mode
-		prio_arp $mode
-		prio_ns $mode
 	done
+	prio_arp "active-backup"
+	prio_ns "active-backup"
 }
 
 arp_validate_test()
diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config
index 70638fa50b2c..899d7fb6ea8e 100644
--- a/tools/testing/selftests/drivers/net/bonding/config
+++ b/tools/testing/selftests/drivers/net/bonding/config
@@ -1,2 +1,10 @@
 CONFIG_BONDING=y
+CONFIG_BRIDGE=y
+CONFIG_DUMMY=y
+CONFIG_IPV6=y
 CONFIG_MACVLAN=y
+CONFIG_NET_ACT_GACT=y
+CONFIG_NET_CLS_FLOWER=y
+CONFIG_NET_SCH_INGRESS=y
+CONFIG_NLMON=y
+CONFIG_VETH=y
diff --git a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh
index 2a268b17b61f..dbdd736a41d3 100644
--- a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh
+++ b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh
@@ -48,6 +48,17 @@ test_LAG_cleanup()
 	ip link add mv0 link "$name" up address "$ucaddr" type macvlan
 	# Used to test dev->mc handling
 	ip address add "$addr6" dev "$name"
+
+	# Check that addresses were added as expected
+	(grep_bridge_fdb "$ucaddr" bridge fdb show dev dummy1 ||
+		grep_bridge_fdb "$ucaddr" bridge fdb show dev dummy2) >/dev/null
+	check_err $? "macvlan unicast address not found on a slave"
+
+	# mcaddr is added asynchronously by addrconf_dad_work(), use busywait
+	(busywait 10000 grep_bridge_fdb "$mcaddr" bridge fdb show dev dummy1 ||
+		grep_bridge_fdb "$mcaddr" bridge fdb show dev dummy2) >/dev/null
+	check_err $? "IPv6 solicited-node multicast mac address not found on a slave"
+
 	ip link set dev "$name" down
 	ip link del "$name"
 
diff --git a/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh b/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh
index ad4c845a4ac7..b76bf5030952 100755
--- a/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh
+++ b/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 # Regression Test:
diff --git a/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh b/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh
index 2330d37453f9..8c2619002147 100755
--- a/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh
+++ b/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 # Regression Test:
diff --git a/tools/testing/selftests/drivers/net/bonding/settings b/tools/testing/selftests/drivers/net/bonding/settings
index 6091b45d226b..79b65bdf05db 100644
--- a/tools/testing/selftests/drivers/net/bonding/settings
+++ b/tools/testing/selftests/drivers/net/bonding/settings
@@ -1 +1 @@
-timeout=120
+timeout=1200
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
index 42ce602d8d49..0f0f4f05807c 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
@@ -40,7 +40,6 @@
 # |   + $swp1          $swp3 +                    + $swp4                     |
 # |   | iPOOL1        iPOOL0 |                    | iPOOL2                    |
 # |   | ePOOL4        ePOOL5 |                    | ePOOL4                    |
-# |   |                1Gbps |                    | 1Gbps                     |
 # |   |        PFC:enabled=1 |                    | PFC:enabled=1             |
 # | +-|----------------------|-+                +-|------------------------+  |
 # | | + $swp1.111  $swp3.111 + |                | + $swp4.111              |  |
@@ -120,6 +119,9 @@ h2_destroy()
 
 switch_create()
 {
+	local lanes_swp4
+	local pg1_size
+
 	# pools
 	# -----
 
@@ -229,7 +231,20 @@ switch_create()
 	dcb pfc set dev $swp4 prio-pfc all:off 1:on
 	# PG0 will get autoconfigured to Xoff, give PG1 arbitrarily 100K, which
 	# is (-2*MTU) about 80K of delay provision.
-	dcb buffer set dev $swp4 buffer-size all:0 1:$_100KB
+	pg1_size=$_100KB
+
+	setup_wait_dev_with_timeout $swp4
+
+	lanes_swp4=$(ethtool $swp4 | grep 'Lanes:')
+	lanes_swp4=${lanes_swp4#*"Lanes: "}
+
+	# 8-lane ports use two buffers among which the configured buffer
+	# is split, so double the size to get twice (20K + 80K).
+	if [[ $lanes_swp4 -eq 8 ]]; then
+		pg1_size=$((pg1_size * 2))
+	fi
+
+	dcb buffer set dev $swp4 buffer-size all:0 1:$pg1_size
 
 	# bridges
 	# -------
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
index fb850e0ec837..616d3581419c 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
@@ -10,7 +10,8 @@ lib_dir=$(dirname $0)/../../../../net/forwarding
 ALL_TESTS="single_mask_test identical_filters_test two_masks_test \
 	multiple_masks_test ctcam_edge_cases_test delta_simple_test \
 	delta_two_masks_one_key_test delta_simple_rehash_test \
-	bloom_simple_test bloom_complex_test bloom_delta_test"
+	bloom_simple_test bloom_complex_test bloom_delta_test \
+	max_erp_entries_test max_group_size_test"
 NUM_NETIFS=2
 source $lib_dir/lib.sh
 source $lib_dir/tc_common.sh
@@ -983,6 +984,109 @@ bloom_delta_test()
 	log_test "bloom delta test ($tcflags)"
 }
 
+max_erp_entries_test()
+{
+	# The number of eRP entries is limited. Once the maximum number of eRPs
+	# has been reached, filters cannot be added. This test verifies that
+	# when this limit is reached, inserstion fails without crashing.
+
+	RET=0
+
+	local num_masks=32
+	local num_regions=15
+	local chain_failed
+	local mask_failed
+	local ret
+
+	if [[ "$tcflags" != "skip_sw" ]]; then
+		return 0;
+	fi
+
+	for ((i=1; i < $num_regions; i++)); do
+		for ((j=$num_masks; j >= 0; j--)); do
+			tc filter add dev $h2 ingress chain $i protocol ip \
+				pref $i	handle $j flower $tcflags \
+				dst_ip 192.1.0.0/$j &> /dev/null
+			ret=$?
+
+			if [ $ret -ne 0 ]; then
+				chain_failed=$i
+				mask_failed=$j
+				break 2
+			fi
+		done
+	done
+
+	# We expect to exceed the maximum number of eRP entries, so that
+	# insertion eventually fails. Otherwise, the test should be adjusted to
+	# add more filters.
+	check_fail $ret "expected to exceed number of eRP entries"
+
+	for ((; i >= 1; i--)); do
+		for ((j=0; j <= $num_masks; j++)); do
+			tc filter del dev $h2 ingress chain $i protocol ip \
+				pref $i handle $j flower &> /dev/null
+		done
+	done
+
+	log_test "max eRP entries test ($tcflags). " \
+		"max chain $chain_failed, mask $mask_failed"
+}
+
+max_group_size_test()
+{
+	# The number of ACLs in an ACL group is limited. Once the maximum
+	# number of ACLs has been reached, filters cannot be added. This test
+	# verifies that when this limit is reached, insertion fails without
+	# crashing.
+
+	RET=0
+
+	local num_acls=32
+	local max_size
+	local ret
+
+	if [[ "$tcflags" != "skip_sw" ]]; then
+		return 0;
+	fi
+
+	for ((i=1; i < $num_acls; i++)); do
+		if [[ $(( i % 2 )) == 1 ]]; then
+			tc filter add dev $h2 ingress pref $i proto ipv4 \
+				flower $tcflags dst_ip 198.51.100.1/32 \
+				ip_proto tcp tcp_flags 0x01/0x01 \
+				action drop &> /dev/null
+		else
+			tc filter add dev $h2 ingress pref $i proto ipv6 \
+				flower $tcflags dst_ip 2001:db8:1::1/128 \
+				action drop &> /dev/null
+		fi
+
+		ret=$?
+		[[ $ret -ne 0 ]] && max_size=$((i - 1)) && break
+	done
+
+	# We expect to exceed the maximum number of ACLs in a group, so that
+	# insertion eventually fails. Otherwise, the test should be adjusted to
+	# add more filters.
+	check_fail $ret "expected to exceed number of ACLs in a group"
+
+	for ((; i >= 1; i--)); do
+		if [[ $(( i % 2 )) == 1 ]]; then
+			tc filter del dev $h2 ingress pref $i proto ipv4 \
+				flower $tcflags dst_ip 198.51.100.1/32 \
+				ip_proto tcp tcp_flags 0x01/0x01 \
+				action drop &> /dev/null
+		else
+			tc filter del dev $h2 ingress pref $i proto ipv6 \
+				flower $tcflags dst_ip 2001:db8:1::1/128 \
+				action drop &> /dev/null
+		fi
+	done
+
+	log_test "max ACL group size test ($tcflags). max size $max_size"
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
diff --git a/tools/testing/selftests/drivers/net/netdevsim/config b/tools/testing/selftests/drivers/net/netdevsim/config
new file mode 100644
index 000000000000..adf45a3a78b4
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/config
@@ -0,0 +1,10 @@
+CONFIG_DUMMY=y
+CONFIG_GENEVE=m
+CONFIG_IPV6=y
+CONFIG_NETDEVSIM=m
+CONFIG_NET_SCH_MQPRIO=y
+CONFIG_NET_SCH_MULTIQ=y
+CONFIG_NET_SCH_PRIO=y
+CONFIG_PSAMPLE=y
+CONFIG_PTP_1588_CLOCK_MOCK=y
+CONFIG_VXLAN=m
diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh
index 922744059aaa..80160579e0cc 100644
--- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh
@@ -51,6 +51,7 @@ function make_netdev {
     fi
 
     echo $NSIM_ID $@ > /sys/bus/netdevsim/new_device
+    udevadm settle
     # get new device name
     ls /sys/bus/netdevsim/devices/netdevsim${NSIM_ID}/net/
 }
diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh
index 0c56746e9ce0..7d7829f57550 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh
@@ -8,16 +8,20 @@ NSIM_NETDEV=$(make_netdev)
 
 set -o pipefail
 
+# Since commit 2b3ddcb35357 ("ethtool: fec: Change the prompt ...")
+# in ethtool CLI the Configured lines start with Supported/Configured.
+configured=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2 | head -1 | cut -d' ' -f1)
+
 # netdevsim starts out with None/None
 s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-check $? "$s" "Configured FEC encodings: None
+check $? "$s" "$configured FEC encodings: None
 Active FEC encoding: None"
 
 # Test Auto
 $ETHTOOL --set-fec $NSIM_NETDEV encoding auto
 check $?
 s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-check $? "$s" "Configured FEC encodings: Auto
+check $? "$s" "$configured FEC encodings: Auto
 Active FEC encoding: Off"
 
 # Test case in-sensitivity
@@ -25,7 +29,7 @@ for o in off Off OFF; do
     $ETHTOOL --set-fec $NSIM_NETDEV encoding $o
     check $?
     s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-    check $? "$s" "Configured FEC encodings: Off
+    check $? "$s" "$configured FEC encodings: Off
 Active FEC encoding: Off"
 done
 
@@ -33,7 +37,7 @@ for o in BaseR baser BAser; do
     $ETHTOOL --set-fec $NSIM_NETDEV encoding $o
     check $?
     s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-    check $? "$s" "Configured FEC encodings: BaseR
+    check $? "$s" "$configured FEC encodings: BaseR
 Active FEC encoding: BaseR"
 done
 
@@ -41,7 +45,7 @@ for o in llrs rs; do
     $ETHTOOL --set-fec $NSIM_NETDEV encoding $o
     check $?
     s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-    check $? "$s" "Configured FEC encodings: ${o^^}
+    check $? "$s" "$configured FEC encodings: ${o^^}
 Active FEC encoding: ${o^^}"
 done
 
@@ -49,13 +53,13 @@ done
 $ETHTOOL --set-fec $NSIM_NETDEV encoding rs llrs
 check $?
 s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-check $? "$s" "Configured FEC encodings: RS LLRS
+check $? "$s" "$configured FEC encodings: RS LLRS
 Active FEC encoding: LLRS"
 
 $ETHTOOL --set-fec $NSIM_NETDEV encoding rs off auto
 check $?
 s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-check $? "$s" "Configured FEC encodings: Auto Off RS
+check $? "$s" "$configured FEC encodings: Auto Off RS
 Active FEC encoding: RS"
 
 # Make sure other link modes are rejected
diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh
index 1b08e042cf94..f98435c502f6 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh
@@ -233,6 +233,7 @@ function print_tables {
 function get_netdev_name {
     local -n old=$1
 
+    udevadm settle
     new=$(ls /sys/class/net)
 
     for netdev in $new; do
@@ -269,6 +270,7 @@ for port in 0 1; do
 	echo 1 > $NSIM_DEV_SYS/new_port
     fi
     NSIM_NETDEV=`get_netdev_name old_netdevs`
+    ifconfig $NSIM_NETDEV up
 
     msg="new NIC device created"
     exp0=( 0 0 0 0 )
@@ -430,6 +432,7 @@ for port in 0 1; do
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     overflow_table0 "overflow NIC table"
@@ -487,6 +490,7 @@ for port in 0 1; do
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     overflow_table0 "overflow NIC table"
@@ -543,6 +547,7 @@ for port in 0 1; do
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     overflow_table0 "destroy NIC"
@@ -572,6 +577,7 @@ for port in 0 1; do
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     msg="create VxLANs v6"
@@ -632,6 +638,7 @@ for port in 0 1; do
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error
@@ -687,6 +694,7 @@ for port in 0 1; do
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     msg="create VxLANs v6"
@@ -746,6 +754,7 @@ for port in 0 1; do
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     msg="create VxLANs v6"
@@ -876,6 +885,7 @@ msg="re-add a port"
 
 echo 2 > $NSIM_DEV_SYS/del_port
 echo 2 > $NSIM_DEV_SYS/new_port
+NSIM_NETDEV=`get_netdev_name old_netdevs`
 check_tables
 
 msg="replace VxLAN in overflow table"
diff --git a/tools/testing/selftests/drivers/net/team/config b/tools/testing/selftests/drivers/net/team/config
index 265b6882cc21..b5e3a3aad4bf 100644
--- a/tools/testing/selftests/drivers/net/team/config
+++ b/tools/testing/selftests/drivers/net/team/config
@@ -1,3 +1,5 @@
+CONFIG_DUMMY=y
+CONFIG_IPV6=y
+CONFIG_MACVLAN=y
 CONFIG_NET_TEAM=y
 CONFIG_NET_TEAM_MODE_LOADBALANCE=y
-CONFIG_MACVLAN=y
diff --git a/tools/testing/selftests/dt/Makefile b/tools/testing/selftests/dt/Makefile
index 62dc00ee4978..2d33ee9e9b71 100644
--- a/tools/testing/selftests/dt/Makefile
+++ b/tools/testing/selftests/dt/Makefile
@@ -4,7 +4,7 @@ ifneq ($(PY3),)
 
 TEST_PROGS := test_unprobed_devices.sh
 TEST_GEN_FILES := compatible_list
-TEST_FILES := compatible_ignore_list ktap_helpers.sh
+TEST_FILES := compatible_ignore_list
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/dt/test_unprobed_devices.sh b/tools/testing/selftests/dt/test_unprobed_devices.sh
index b07af2a4c4de..2d7e70c5ad2d 100755
--- a/tools/testing/selftests/dt/test_unprobed_devices.sh
+++ b/tools/testing/selftests/dt/test_unprobed_devices.sh
@@ -15,16 +15,12 @@
 
 DIR="$(dirname $(readlink -f "$0"))"
 
-source "${DIR}"/ktap_helpers.sh
+source "${DIR}"/../kselftest/ktap_helpers.sh
 
 PDT=/proc/device-tree/
 COMPAT_LIST="${DIR}"/compatible_list
 IGNORE_LIST="${DIR}"/compatible_ignore_list
 
-KSFT_PASS=0
-KSFT_FAIL=1
-KSFT_SKIP=4
-
 ktap_print_header
 
 if [[ ! -d "${PDT}" ]]; then
@@ -33,8 +29,8 @@ if [[ ! -d "${PDT}" ]]; then
 fi
 
 nodes_compatible=$(
-	for node_compat in $(find ${PDT} -name compatible); do
-		node=$(dirname "${node_compat}")
+	for node in $(find ${PDT} -type d); do
+		[ ! -f "${node}"/compatible ] && continue
 		# Check if node is available
 		if [[ -e "${node}"/status ]]; then
 			status=$(tr -d '\000' < "${node}"/status)
@@ -46,10 +42,11 @@ nodes_compatible=$(
 
 nodes_dev_bound=$(
 	IFS=$'\n'
-	for uevent in $(find /sys/devices -name uevent); do
-		if [[ -d "$(dirname "${uevent}")"/driver ]]; then
-			grep '^OF_FULLNAME=' "${uevent}" | sed -e 's|OF_FULLNAME=||'
-		fi
+	for dev_dir in $(find /sys/devices -type d); do
+		[ ! -f "${dev_dir}"/uevent ] && continue
+		[ ! -d "${dev_dir}"/driver ] && continue
+
+		grep '^OF_FULLNAME=' "${dev_dir}"/uevent | sed -e 's|OF_FULLNAME=||'
 	done
 	)
 
diff --git a/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c b/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c
index e19ab0e85709..759f86e7d263 100644
--- a/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c
+++ b/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c
@@ -10,7 +10,6 @@
 #include <linux/mount.h>
 #include <sys/syscall.h>
 #include <sys/stat.h>
-#include <sys/mount.h>
 #include <sys/mman.h>
 #include <sched.h>
 #include <fcntl.h>
@@ -32,7 +31,11 @@ static int sys_fsmount(int fd, unsigned int flags, unsigned int attr_flags)
 {
 	return syscall(__NR_fsmount, fd, flags, attr_flags);
 }
-
+static int sys_mount(const char *src, const char *tgt, const char *fst,
+		unsigned long flags, const void *data)
+{
+	return syscall(__NR_mount, src, tgt, fst, flags, data);
+}
 static int sys_move_mount(int from_dfd, const char *from_pathname,
 			  int to_dfd, const char *to_pathname,
 			  unsigned int flags)
@@ -166,8 +169,7 @@ int main(int argc, char **argv)
 		ksft_test_result_skip("unable to create a new mount namespace\n");
 		return 1;
 	}
-
-	if (mount(NULL, "/", NULL, MS_SLAVE | MS_REC, NULL) == -1) {
+	if (sys_mount(NULL, "/", NULL, MS_SLAVE | MS_REC, NULL) == -1) {
 		pr_perror("mount");
 		return 1;
 	}
diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index c778d4dcc17e..25d4e0fca385 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -504,7 +504,7 @@ prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w`
 if [ "$KTAP" = "1" ]; then
   echo -n "# Totals:"
   echo -n " pass:"`echo $PASSED_CASES | wc -w`
-  echo -n " faii:"`echo $FAILED_CASES | wc -w`
+  echo -n " fail:"`echo $FAILED_CASES | wc -w`
   echo -n " xfail:"`echo $XFAILED_CASES | wc -w`
   echo -n " xpass:0"
   echo -n " skip:"`echo $UNTESTED_CASES $UNSUPPORTED_CASES | wc -w`
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_subbuf_size.tc b/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_subbuf_size.tc
new file mode 100644
index 000000000000..d44d09a33a74
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_subbuf_size.tc
@@ -0,0 +1,95 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Change the ringbuffer sub-buffer size
+# requires: buffer_subbuf_size_kb
+# flags: instance
+
+get_buffer_data_size() {
+	sed -ne 's/^.*data.*size:\([0-9][0-9]*\).*/\1/p' events/header_page
+}
+
+get_buffer_data_offset() {
+	sed -ne 's/^.*data.*offset:\([0-9][0-9]*\).*/\1/p' events/header_page
+}
+
+get_event_header_size() {
+	type_len=`sed -ne 's/^.*type_len.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event`
+	time_len=`sed -ne 's/^.*time_delta.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event`
+	array_len=`sed -ne 's/^.*array.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event`
+	total_bits=$((type_len+time_len+array_len))
+	total_bits=$((total_bits+7))
+	echo $((total_bits/8))
+}
+
+get_print_event_buf_offset() {
+	sed -ne 's/^.*buf.*offset:\([0-9][0-9]*\).*/\1/p' events/ftrace/print/format
+}
+
+event_header_size=`get_event_header_size`
+print_header_size=`get_print_event_buf_offset`
+
+data_offset=`get_buffer_data_offset`
+
+marker_meta=$((event_header_size+print_header_size))
+
+make_str() {
+        cnt=$1
+	printf -- 'X%.0s' $(seq $cnt)
+}
+
+write_buffer() {
+	size=$1
+
+	str=`make_str $size`
+
+	# clear the buffer
+	echo > trace
+
+	# write the string into the marker
+	echo $str > trace_marker
+
+	echo $str
+}
+
+test_buffer() {
+	size_kb=$1
+	page_size=$((size_kb*1024))
+
+	size=`get_buffer_data_size`
+
+	# the size must be greater than or equal to page_size - data_offset
+	page_size=$((page_size-data_offset))
+	if [ $size -lt $page_size ]; then
+		exit fail
+	fi
+
+	# Now add a little more the meta data overhead will overflow
+
+	str=`write_buffer $size`
+
+	# Make sure the line was broken
+	new_str=`awk ' /tracing_mark_write:/ { sub(/^.*tracing_mark_write: /,"");printf "%s", $0; exit}' trace`
+
+	if [ "$new_str" = "$str" ]; then
+		exit fail;
+	fi
+
+	# Make sure the entire line can be found
+	new_str=`awk ' /tracing_mark_write:/ { sub(/^.*tracing_mark_write: /,"");printf "%s", $0; }' trace`
+
+	if [ "$new_str" != "$str" ]; then
+		exit fail;
+	fi
+}
+
+ORIG=`cat buffer_subbuf_size_kb`
+
+# Could test bigger sizes than 32K, but then creating the string
+# to write into the ring buffer takes too long
+for a in 4 8 16 32 ; do
+	echo $a > buffer_subbuf_size_kb
+	test_buffer $a
+done
+
+echo $ORIG > buffer_subbuf_size_kb
+
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc b/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc
index add7d5bf585d..c45094d1e1d2 100644
--- a/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc
+++ b/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc
@@ -1,6 +1,6 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
-# description: Test file and directory owership changes for eventfs
+# description: Test file and directory ownership changes for eventfs
 
 original_group=`stat -c "%g" .`
 original_owner=`stat -c "%u" .`
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/trace_marker.tc b/tools/testing/selftests/ftrace/test.d/00basic/trace_marker.tc
new file mode 100644
index 000000000000..9aa0db2b84fc
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/00basic/trace_marker.tc
@@ -0,0 +1,82 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Basic tests on writing to trace_marker
+# requires: trace_marker
+# flags: instance
+
+get_buffer_data_size() {
+	sed -ne 's/^.*data.*size:\([0-9][0-9]*\).*/\1/p' events/header_page
+}
+
+get_buffer_data_offset() {
+	sed -ne 's/^.*data.*offset:\([0-9][0-9]*\).*/\1/p' events/header_page
+}
+
+get_event_header_size() {
+	type_len=`sed -ne 's/^.*type_len.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event`
+	time_len=`sed -ne 's/^.*time_delta.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event`
+	array_len=`sed -ne 's/^.*array.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event`
+	total_bits=$((type_len+time_len+array_len))
+	total_bits=$((total_bits+7))
+	echo $((total_bits/8))
+}
+
+get_print_event_buf_offset() {
+	sed -ne 's/^.*buf.*offset:\([0-9][0-9]*\).*/\1/p' events/ftrace/print/format
+}
+
+event_header_size=`get_event_header_size`
+print_header_size=`get_print_event_buf_offset`
+
+data_offset=`get_buffer_data_offset`
+
+marker_meta=$((event_header_size+print_header_size))
+
+make_str() {
+        cnt=$1
+	# subtract two for \n\0 as marker adds these
+	cnt=$((cnt-2))
+	printf -- 'X%.0s' $(seq $cnt)
+}
+
+write_buffer() {
+	size=$1
+
+	str=`make_str $size`
+
+	# clear the buffer
+	echo > trace
+
+	# write the string into the marker
+	echo -n $str > trace_marker
+
+	echo $str
+}
+
+test_buffer() {
+
+	size=`get_buffer_data_size`
+	oneline_size=$((size-marker_meta))
+	echo size = $size
+	echo meta size = $marker_meta
+
+	# Now add a little more the meta data overhead will overflow
+
+	str=`write_buffer $size`
+
+	# Make sure the line was broken
+	new_str=`awk ' /tracing_mark_write:/ { sub(/^.*tracing_mark_write: /,"");printf "%s", $0; exit}' trace`
+
+	if [ "$new_str" = "$str" ]; then
+		exit fail;
+	fi
+
+	# Make sure the entire line can be found
+	new_str=`awk ' /tracing_mark_write:/ { sub(/^.*tracing_mark_write: /,"");printf "%s", $0; }' trace`
+
+	if [ "$new_str" != "$str" ]; then
+		exit fail;
+	fi
+}
+
+test_buffer
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_hotplug.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_hotplug.tc
new file mode 100644
index 000000000000..ccfbfde3d942
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_hotplug.tc
@@ -0,0 +1,42 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-or-later
+# description: ftrace - function trace across cpu hotplug
+# requires: function:tracer
+
+if ! which nproc ; then
+  nproc() {
+    ls -d /sys/devices/system/cpu/cpu[0-9]* | wc -l
+  }
+fi
+
+NP=`nproc`
+
+if [ $NP -eq 1 ] ;then
+  echo "We cannot test cpu hotplug in UP environment"
+  exit_unresolved
+fi
+
+# Find online cpu
+for i in /sys/devices/system/cpu/cpu[1-9]*; do
+	if [ -f $i/online ] && [ "$(cat $i/online)" = "1" ]; then
+		cpu=$i
+		break
+	fi
+done
+
+if [ -z "$cpu" ]; then
+	echo "We cannot test cpu hotplug with a single cpu online"
+	exit_unresolved
+fi
+
+echo 0 > tracing_on
+echo > trace
+
+: "Set $(basename $cpu) offline/online with function tracer enabled"
+echo function > current_tracer
+echo 1 > tracing_on
+(echo 0 > $cpu/online)
+(echo "forked"; sleep 1)
+(echo 1 > $cpu/online)
+echo 0 > tracing_on
+echo nop > current_tracer
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
index 4562e13cb26b..717898894ef7 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
@@ -40,7 +40,7 @@ grep "id: \(unknown_\|sys_\)" events/raw_syscalls/sys_exit/hist > /dev/null || \
 
 reset_trigger
 
-echo "Test histgram with log2 modifier"
+echo "Test histogram with log2 modifier"
 
 echo 'hist:keys=bytes_req.log2' > events/kmem/kmalloc/trigger
 for i in `seq 1 10` ; do ( echo "forked" > /dev/null); done
diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi.c b/tools/testing/selftests/futex/functional/futex_requeue_pi.c
index 1ee5518ee6b7..7f3ca5c78df1 100644
--- a/tools/testing/selftests/futex/functional/futex_requeue_pi.c
+++ b/tools/testing/selftests/futex/functional/futex_requeue_pi.c
@@ -17,6 +17,8 @@
  *
  *****************************************************************************/
 
+#define _GNU_SOURCE
+
 #include <errno.h>
 #include <limits.h>
 #include <pthread.h>
@@ -358,6 +360,7 @@ out:
 
 int main(int argc, char *argv[])
 {
+	const char *test_name;
 	int c, ret;
 
 	while ((c = getopt(argc, argv, "bchlot:v:")) != -1) {
@@ -397,6 +400,14 @@ int main(int argc, char *argv[])
 		"\tArguments: broadcast=%d locked=%d owner=%d timeout=%ldns\n",
 		broadcast, locked, owner, timeout_ns);
 
+	ret = asprintf(&test_name,
+		       "%s broadcast=%d locked=%d owner=%d timeout=%ldns",
+		       TEST_NAME, broadcast, locked, owner, timeout_ns);
+	if (ret < 0) {
+		ksft_print_msg("Failed to generate test name\n");
+		test_name = TEST_NAME;
+	}
+
 	/*
 	 * FIXME: unit_test is obsolete now that we parse options and the
 	 * various style of runs are done by run.sh - simplify the code and move
@@ -404,6 +415,6 @@ int main(int argc, char *argv[])
 	 */
 	ret = unit_test(broadcast, locked, owner, timeout_ns);
 
-	print_result(TEST_NAME, ret);
+	print_result(test_name, ret);
 	return ret;
 }
diff --git a/tools/testing/selftests/hid/tests/test_wacom_generic.py b/tools/testing/selftests/hid/tests/test_wacom_generic.py
index 352fc39f3c6c..b62c7dba6777 100644
--- a/tools/testing/selftests/hid/tests/test_wacom_generic.py
+++ b/tools/testing/selftests/hid/tests/test_wacom_generic.py
@@ -880,8 +880,8 @@ class TestDTH2452Tablet(test_multitouch.BaseTest.TestMultitouch, TouchTabletTest
         does not overlap with other contacts. The value of `t` may be
         incremented over time to move the point along a linear path.
         """
-        x = 50 + 10 * contact_id + t
-        y = 100 + 100 * contact_id + t
+        x = 50 + 10 * contact_id + t * 11
+        y = 100 + 100 * contact_id + t * 11
         return test_multitouch.Touch(contact_id, x, y)
 
     def make_contacts(self, n, t=0):
@@ -902,8 +902,8 @@ class TestDTH2452Tablet(test_multitouch.BaseTest.TestMultitouch, TouchTabletTest
         tracking_id = contact_ids.tracking_id
         slot_num = contact_ids.slot_num
 
-        x = 50 + 10 * contact_id + t
-        y = 100 + 100 * contact_id + t
+        x = 50 + 10 * contact_id + t * 11
+        y = 100 + 100 * contact_id + t * 11
 
         # If the data isn't supposed to be stored in any slots, there is
         # nothing we can check for in the evdev stream.
diff --git a/tools/testing/selftests/iommu/config b/tools/testing/selftests/iommu/config
index 6c4f901d6fed..110d73917615 100644
--- a/tools/testing/selftests/iommu/config
+++ b/tools/testing/selftests/iommu/config
@@ -1,2 +1,3 @@
-CONFIG_IOMMUFD
-CONFIG_IOMMUFD_TEST
+CONFIG_IOMMUFD=y
+CONFIG_FAULT_INJECTION=y
+CONFIG_IOMMUFD_TEST=y
diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c
index 6ed328c863c4..edf1c99c9936 100644
--- a/tools/testing/selftests/iommu/iommufd.c
+++ b/tools/testing/selftests/iommu/iommufd.c
@@ -12,6 +12,7 @@
 static unsigned long HUGEPAGE_SIZE;
 
 #define MOCK_PAGE_SIZE (PAGE_SIZE / 2)
+#define MOCK_HUGE_PAGE_SIZE (512 * MOCK_PAGE_SIZE)
 
 static unsigned long get_huge_page_size(void)
 {
@@ -116,6 +117,7 @@ TEST_F(iommufd, cmd_length)
 	TEST_LENGTH(iommu_destroy, IOMMU_DESTROY, id);
 	TEST_LENGTH(iommu_hw_info, IOMMU_GET_HW_INFO, __reserved);
 	TEST_LENGTH(iommu_hwpt_alloc, IOMMU_HWPT_ALLOC, __reserved);
+	TEST_LENGTH(iommu_hwpt_invalidate, IOMMU_HWPT_INVALIDATE, __reserved);
 	TEST_LENGTH(iommu_ioas_alloc, IOMMU_IOAS_ALLOC, out_ioas_id);
 	TEST_LENGTH(iommu_ioas_iova_ranges, IOMMU_IOAS_IOVA_RANGES,
 		    out_iova_alignment);
@@ -271,7 +273,9 @@ TEST_F(iommufd_ioas, alloc_hwpt_nested)
 	struct iommu_hwpt_selftest data = {
 		.iotlb = IOMMU_TEST_IOTLB_DEFAULT,
 	};
+	struct iommu_hwpt_invalidate_selftest inv_reqs[2] = {};
 	uint32_t nested_hwpt_id[2] = {};
+	uint32_t num_inv;
 	uint32_t parent_hwpt_id = 0;
 	uint32_t parent_hwpt_id_not_work = 0;
 	uint32_t test_hwpt_id = 0;
@@ -330,6 +334,10 @@ TEST_F(iommufd_ioas, alloc_hwpt_nested)
 					   &nested_hwpt_id[1],
 					   IOMMU_HWPT_DATA_SELFTEST, &data,
 					   sizeof(data));
+		test_cmd_hwpt_check_iotlb_all(nested_hwpt_id[0],
+					      IOMMU_TEST_IOTLB_DEFAULT);
+		test_cmd_hwpt_check_iotlb_all(nested_hwpt_id[1],
+					      IOMMU_TEST_IOTLB_DEFAULT);
 
 		/* Negative test: a nested hwpt on top of a nested hwpt */
 		test_err_hwpt_alloc_nested(EINVAL, self->device_id,
@@ -340,6 +348,151 @@ TEST_F(iommufd_ioas, alloc_hwpt_nested)
 		EXPECT_ERRNO(EBUSY,
 			     _test_ioctl_destroy(self->fd, parent_hwpt_id));
 
+		/* hwpt_invalidate only supports a user-managed hwpt (nested) */
+		num_inv = 1;
+		test_err_hwpt_invalidate(ENOENT, parent_hwpt_id, inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(!num_inv);
+
+		/* Check data_type by passing zero-length array */
+		num_inv = 0;
+		test_cmd_hwpt_invalidate(nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(!num_inv);
+
+		/* Negative test: Invalid data_type */
+		num_inv = 1;
+		test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST_INVALID,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(!num_inv);
+
+		/* Negative test: structure size sanity */
+		num_inv = 1;
+		test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs) + 1, &num_inv);
+		assert(!num_inv);
+
+		num_inv = 1;
+		test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 1, &num_inv);
+		assert(!num_inv);
+
+		/* Negative test: invalid flag is passed */
+		num_inv = 1;
+		inv_reqs[0].flags = 0xffffffff;
+		test_err_hwpt_invalidate(EOPNOTSUPP, nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(!num_inv);
+
+		/* Negative test: invalid data_uptr when array is not empty */
+		num_inv = 1;
+		inv_reqs[0].flags = 0;
+		test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], NULL,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(!num_inv);
+
+		/* Negative test: invalid entry_len when array is not empty */
+		num_inv = 1;
+		inv_reqs[0].flags = 0;
+		test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 0, &num_inv);
+		assert(!num_inv);
+
+		/* Negative test: invalid iotlb_id */
+		num_inv = 1;
+		inv_reqs[0].flags = 0;
+		inv_reqs[0].iotlb_id = MOCK_NESTED_DOMAIN_IOTLB_ID_MAX + 1;
+		test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(!num_inv);
+
+		/*
+		 * Invalidate the 1st iotlb entry but fail the 2nd request
+		 * due to invalid flags configuration in the 2nd request.
+		 */
+		num_inv = 2;
+		inv_reqs[0].flags = 0;
+		inv_reqs[0].iotlb_id = 0;
+		inv_reqs[1].flags = 0xffffffff;
+		inv_reqs[1].iotlb_id = 1;
+		test_err_hwpt_invalidate(EOPNOTSUPP, nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(num_inv == 1);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 0, 0);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 1,
+					  IOMMU_TEST_IOTLB_DEFAULT);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 2,
+					  IOMMU_TEST_IOTLB_DEFAULT);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 3,
+					  IOMMU_TEST_IOTLB_DEFAULT);
+
+		/*
+		 * Invalidate the 1st iotlb entry but fail the 2nd request
+		 * due to invalid iotlb_id configuration in the 2nd request.
+		 */
+		num_inv = 2;
+		inv_reqs[0].flags = 0;
+		inv_reqs[0].iotlb_id = 0;
+		inv_reqs[1].flags = 0;
+		inv_reqs[1].iotlb_id = MOCK_NESTED_DOMAIN_IOTLB_ID_MAX + 1;
+		test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(num_inv == 1);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 0, 0);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 1,
+					  IOMMU_TEST_IOTLB_DEFAULT);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 2,
+					  IOMMU_TEST_IOTLB_DEFAULT);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 3,
+					  IOMMU_TEST_IOTLB_DEFAULT);
+
+		/* Invalidate the 2nd iotlb entry and verify */
+		num_inv = 1;
+		inv_reqs[0].flags = 0;
+		inv_reqs[0].iotlb_id = 1;
+		test_cmd_hwpt_invalidate(nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(num_inv == 1);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 0, 0);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 1, 0);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 2,
+					  IOMMU_TEST_IOTLB_DEFAULT);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 3,
+					  IOMMU_TEST_IOTLB_DEFAULT);
+
+		/* Invalidate the 3rd and 4th iotlb entries and verify */
+		num_inv = 2;
+		inv_reqs[0].flags = 0;
+		inv_reqs[0].iotlb_id = 2;
+		inv_reqs[1].flags = 0;
+		inv_reqs[1].iotlb_id = 3;
+		test_cmd_hwpt_invalidate(nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(num_inv == 2);
+		test_cmd_hwpt_check_iotlb_all(nested_hwpt_id[0], 0);
+
+		/* Invalidate all iotlb entries for nested_hwpt_id[1] and verify */
+		num_inv = 1;
+		inv_reqs[0].flags = IOMMU_TEST_INVALIDATE_FLAG_ALL;
+		test_cmd_hwpt_invalidate(nested_hwpt_id[1], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(num_inv == 1);
+		test_cmd_hwpt_check_iotlb_all(nested_hwpt_id[1], 0);
+
 		/* Attach device to nested_hwpt_id[0] that then will be busy */
 		test_cmd_mock_domain_replace(self->stdev_id, nested_hwpt_id[0]);
 		EXPECT_ERRNO(EBUSY,
@@ -1564,10 +1717,12 @@ FIXTURE(iommufd_dirty_tracking)
 FIXTURE_VARIANT(iommufd_dirty_tracking)
 {
 	unsigned long buffer_size;
+	bool hugepages;
 };
 
 FIXTURE_SETUP(iommufd_dirty_tracking)
 {
+	int mmap_flags;
 	void *vrc;
 	int rc;
 
@@ -1580,25 +1735,41 @@ FIXTURE_SETUP(iommufd_dirty_tracking)
 			   variant->buffer_size, rc);
 	}
 
+	mmap_flags = MAP_SHARED | MAP_ANONYMOUS | MAP_FIXED;
+	if (variant->hugepages) {
+		/*
+		 * MAP_POPULATE will cause the kernel to fail mmap if THPs are
+		 * not available.
+		 */
+		mmap_flags |= MAP_HUGETLB | MAP_POPULATE;
+	}
 	assert((uintptr_t)self->buffer % HUGEPAGE_SIZE == 0);
 	vrc = mmap(self->buffer, variant->buffer_size, PROT_READ | PROT_WRITE,
-		   MAP_SHARED | MAP_ANONYMOUS | MAP_FIXED, -1, 0);
+		   mmap_flags, -1, 0);
 	assert(vrc == self->buffer);
 
 	self->page_size = MOCK_PAGE_SIZE;
 	self->bitmap_size =
 		variant->buffer_size / self->page_size / BITS_PER_BYTE;
 
-	/* Provision with an extra (MOCK_PAGE_SIZE) for the unaligned case */
+	/* Provision with an extra (PAGE_SIZE) for the unaligned case */
 	rc = posix_memalign(&self->bitmap, PAGE_SIZE,
-			    self->bitmap_size + MOCK_PAGE_SIZE);
+			    self->bitmap_size + PAGE_SIZE);
 	assert(!rc);
 	assert(self->bitmap);
 	assert((uintptr_t)self->bitmap % PAGE_SIZE == 0);
 
 	test_ioctl_ioas_alloc(&self->ioas_id);
-	test_cmd_mock_domain(self->ioas_id, &self->stdev_id, &self->hwpt_id,
-			     &self->idev_id);
+	/* Enable 1M mock IOMMU hugepages */
+	if (variant->hugepages) {
+		test_cmd_mock_domain_flags(self->ioas_id,
+					   MOCK_FLAGS_DEVICE_HUGE_IOVA,
+					   &self->stdev_id, &self->hwpt_id,
+					   &self->idev_id);
+	} else {
+		test_cmd_mock_domain(self->ioas_id, &self->stdev_id,
+				     &self->hwpt_id, &self->idev_id);
+	}
 }
 
 FIXTURE_TEARDOWN(iommufd_dirty_tracking)
@@ -1632,12 +1803,26 @@ FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty128M)
 	.buffer_size = 128UL * 1024UL * 1024UL,
 };
 
+FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty128M_huge)
+{
+	/* 4K bitmap (128M IOVA range) */
+	.buffer_size = 128UL * 1024UL * 1024UL,
+	.hugepages = true,
+};
+
 FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty256M)
 {
 	/* 8K bitmap (256M IOVA range) */
 	.buffer_size = 256UL * 1024UL * 1024UL,
 };
 
+FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty256M_huge)
+{
+	/* 8K bitmap (256M IOVA range) */
+	.buffer_size = 256UL * 1024UL * 1024UL,
+	.hugepages = true,
+};
+
 TEST_F(iommufd_dirty_tracking, enforce_dirty)
 {
 	uint32_t ioas_id, stddev_id, idev_id;
@@ -1697,65 +1882,80 @@ TEST_F(iommufd_dirty_tracking, device_dirty_capability)
 
 TEST_F(iommufd_dirty_tracking, get_dirty_bitmap)
 {
-	uint32_t stddev_id;
+	uint32_t page_size = MOCK_PAGE_SIZE;
 	uint32_t hwpt_id;
 	uint32_t ioas_id;
 
+	if (variant->hugepages)
+		page_size = MOCK_HUGE_PAGE_SIZE;
+
 	test_ioctl_ioas_alloc(&ioas_id);
 	test_ioctl_ioas_map_fixed_id(ioas_id, self->buffer,
 				     variant->buffer_size, MOCK_APERTURE_START);
 
 	test_cmd_hwpt_alloc(self->idev_id, ioas_id,
 			    IOMMU_HWPT_ALLOC_DIRTY_TRACKING, &hwpt_id);
-	test_cmd_mock_domain(hwpt_id, &stddev_id, NULL, NULL);
 
 	test_cmd_set_dirty_tracking(hwpt_id, true);
 
 	test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size,
-				MOCK_APERTURE_START, self->page_size,
+				MOCK_APERTURE_START, self->page_size, page_size,
 				self->bitmap, self->bitmap_size, 0, _metadata);
 
 	/* PAGE_SIZE unaligned bitmap */
 	test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size,
-				MOCK_APERTURE_START, self->page_size,
+				MOCK_APERTURE_START, self->page_size, page_size,
 				self->bitmap + MOCK_PAGE_SIZE,
 				self->bitmap_size, 0, _metadata);
 
-	test_ioctl_destroy(stddev_id);
+	/* u64 unaligned bitmap */
+	test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size,
+				MOCK_APERTURE_START, self->page_size, page_size,
+				self->bitmap + 0xff1, self->bitmap_size, 0,
+				_metadata);
+
 	test_ioctl_destroy(hwpt_id);
 }
 
 TEST_F(iommufd_dirty_tracking, get_dirty_bitmap_no_clear)
 {
-	uint32_t stddev_id;
+	uint32_t page_size = MOCK_PAGE_SIZE;
 	uint32_t hwpt_id;
 	uint32_t ioas_id;
 
+	if (variant->hugepages)
+		page_size = MOCK_HUGE_PAGE_SIZE;
+
 	test_ioctl_ioas_alloc(&ioas_id);
 	test_ioctl_ioas_map_fixed_id(ioas_id, self->buffer,
 				     variant->buffer_size, MOCK_APERTURE_START);
 
 	test_cmd_hwpt_alloc(self->idev_id, ioas_id,
 			    IOMMU_HWPT_ALLOC_DIRTY_TRACKING, &hwpt_id);
-	test_cmd_mock_domain(hwpt_id, &stddev_id, NULL, NULL);
 
 	test_cmd_set_dirty_tracking(hwpt_id, true);
 
 	test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size,
-				MOCK_APERTURE_START, self->page_size,
+				MOCK_APERTURE_START, self->page_size, page_size,
 				self->bitmap, self->bitmap_size,
 				IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR,
 				_metadata);
 
 	/* Unaligned bitmap */
 	test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size,
-				MOCK_APERTURE_START, self->page_size,
+				MOCK_APERTURE_START, self->page_size, page_size,
 				self->bitmap + MOCK_PAGE_SIZE,
 				self->bitmap_size,
 				IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR,
 				_metadata);
 
-	test_ioctl_destroy(stddev_id);
+	/* u64 unaligned bitmap */
+	test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size,
+				MOCK_APERTURE_START, self->page_size, page_size,
+				self->bitmap + 0xff1, self->bitmap_size,
+				IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR,
+				_metadata);
+
 	test_ioctl_destroy(hwpt_id);
 }
 
diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h
index ad9202335656..8d2b46b2114d 100644
--- a/tools/testing/selftests/iommu/iommufd_utils.h
+++ b/tools/testing/selftests/iommu/iommufd_utils.h
@@ -195,6 +195,61 @@ static int _test_cmd_hwpt_alloc(int fd, __u32 device_id, __u32 pt_id,
 		     _test_cmd_hwpt_alloc(self->fd, device_id, pt_id, flags, \
 					  hwpt_id, data_type, data, data_len))
 
+#define test_cmd_hwpt_check_iotlb(hwpt_id, iotlb_id, expected)                 \
+	({                                                                     \
+		struct iommu_test_cmd test_cmd = {                             \
+			.size = sizeof(test_cmd),                              \
+			.op = IOMMU_TEST_OP_MD_CHECK_IOTLB,                    \
+			.id = hwpt_id,                                         \
+			.check_iotlb = {                                       \
+				.id = iotlb_id,                                \
+				.iotlb = expected,                             \
+			},                                                     \
+		};                                                             \
+		ASSERT_EQ(0,                                                   \
+			  ioctl(self->fd,                                      \
+				_IOMMU_TEST_CMD(IOMMU_TEST_OP_MD_CHECK_IOTLB), \
+				&test_cmd));                                   \
+	})
+
+#define test_cmd_hwpt_check_iotlb_all(hwpt_id, expected)                       \
+	({                                                                     \
+		int i;                                                         \
+		for (i = 0; i < MOCK_NESTED_DOMAIN_IOTLB_NUM; i++)             \
+			test_cmd_hwpt_check_iotlb(hwpt_id, i, expected);       \
+	})
+
+static int _test_cmd_hwpt_invalidate(int fd, __u32 hwpt_id, void *reqs,
+				     uint32_t data_type, uint32_t lreq,
+				     uint32_t *nreqs)
+{
+	struct iommu_hwpt_invalidate cmd = {
+		.size = sizeof(cmd),
+		.hwpt_id = hwpt_id,
+		.data_type = data_type,
+		.data_uptr = (uint64_t)reqs,
+		.entry_len = lreq,
+		.entry_num = *nreqs,
+	};
+	int rc = ioctl(fd, IOMMU_HWPT_INVALIDATE, &cmd);
+	*nreqs = cmd.entry_num;
+	return rc;
+}
+
+#define test_cmd_hwpt_invalidate(hwpt_id, reqs, data_type, lreq, nreqs)       \
+	({                                                                    \
+		ASSERT_EQ(0,                                                  \
+			  _test_cmd_hwpt_invalidate(self->fd, hwpt_id, reqs,  \
+						    data_type, lreq, nreqs)); \
+	})
+#define test_err_hwpt_invalidate(_errno, hwpt_id, reqs, data_type, lreq, \
+				 nreqs)                                  \
+	({                                                               \
+		EXPECT_ERRNO(_errno, _test_cmd_hwpt_invalidate(          \
+					     self->fd, hwpt_id, reqs,    \
+					     data_type, lreq, nreqs));   \
+	})
+
 static int _test_cmd_access_replace_ioas(int fd, __u32 access_id,
 					 unsigned int ioas_id)
 {
@@ -289,16 +344,19 @@ static int _test_cmd_mock_domain_set_dirty(int fd, __u32 hwpt_id, size_t length,
 						  page_size, bitmap, nr))
 
 static int _test_mock_dirty_bitmaps(int fd, __u32 hwpt_id, size_t length,
-				    __u64 iova, size_t page_size, __u64 *bitmap,
+				    __u64 iova, size_t page_size,
+				    size_t pte_page_size, __u64 *bitmap,
 				    __u64 bitmap_size, __u32 flags,
 				    struct __test_metadata *_metadata)
 {
-	unsigned long i, nbits = bitmap_size * BITS_PER_BYTE;
-	unsigned long nr = nbits / 2;
+	unsigned long npte = pte_page_size / page_size, pteset = 2 * npte;
+	unsigned long nbits = bitmap_size * BITS_PER_BYTE;
+	unsigned long j, i, nr = nbits / pteset ?: 1;
 	__u64 out_dirty = 0;
 
 	/* Mark all even bits as dirty in the mock domain */
-	for (i = 0; i < nbits; i += 2)
+	memset(bitmap, 0, bitmap_size);
+	for (i = 0; i < nbits; i += pteset)
 		set_bit(i, (unsigned long *)bitmap);
 
 	test_cmd_mock_domain_set_dirty(fd, hwpt_id, length, iova, page_size,
@@ -310,8 +368,12 @@ static int _test_mock_dirty_bitmaps(int fd, __u32 hwpt_id, size_t length,
 	test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, page_size, bitmap,
 				  flags);
 	/* Beware ASSERT_EQ() is two statements -- braces are not redundant! */
-	for (i = 0; i < nbits; i++) {
-		ASSERT_EQ(!(i % 2), test_bit(i, (unsigned long *)bitmap));
+	for (i = 0; i < nbits; i += pteset) {
+		for (j = 0; j < pteset; j++) {
+			ASSERT_EQ(j < npte,
+				  test_bit(i + j, (unsigned long *)bitmap));
+		}
+		ASSERT_EQ(!(i % pteset), test_bit(i, (unsigned long *)bitmap));
 	}
 
 	memset(bitmap, 0, bitmap_size);
@@ -319,19 +381,23 @@ static int _test_mock_dirty_bitmaps(int fd, __u32 hwpt_id, size_t length,
 				  flags);
 
 	/* It as read already -- expect all zeroes */
-	for (i = 0; i < nbits; i++) {
-		ASSERT_EQ(!(i % 2) && (flags &
-				       IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR),
-			  test_bit(i, (unsigned long *)bitmap));
+	for (i = 0; i < nbits; i += pteset) {
+		for (j = 0; j < pteset; j++) {
+			ASSERT_EQ(
+				(j < npte) &&
+					(flags &
+					 IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR),
+				test_bit(i + j, (unsigned long *)bitmap));
+		}
 	}
 
 	return 0;
 }
-#define test_mock_dirty_bitmaps(hwpt_id, length, iova, page_size, bitmap,      \
-				bitmap_size, flags, _metadata)                 \
+#define test_mock_dirty_bitmaps(hwpt_id, length, iova, page_size, pte_size,\
+				bitmap, bitmap_size, flags, _metadata)     \
 	ASSERT_EQ(0, _test_mock_dirty_bitmaps(self->fd, hwpt_id, length, iova, \
-					      page_size, bitmap, bitmap_size,  \
-					      flags, _metadata))
+					      page_size, pte_size, bitmap,     \
+					      bitmap_size, flags, _metadata))
 
 static int _test_cmd_create_access(int fd, unsigned int ioas_id,
 				   __u32 *access_id, unsigned int flags)
diff --git a/tools/testing/selftests/dt/ktap_helpers.sh b/tools/testing/selftests/kselftest/ktap_helpers.sh
index 8dfae51bb4e2..f2fbb914e058 100644
--- a/tools/testing/selftests/dt/ktap_helpers.sh
+++ b/tools/testing/selftests/kselftest/ktap_helpers.sh
@@ -9,14 +9,27 @@ KTAP_CNT_PASS=0
 KTAP_CNT_FAIL=0
 KTAP_CNT_SKIP=0
 
+KSFT_PASS=0
+KSFT_FAIL=1
+KSFT_XFAIL=2
+KSFT_XPASS=3
+KSFT_SKIP=4
+
+KSFT_NUM_TESTS=0
+
 ktap_print_header() {
 	echo "TAP version 13"
 }
 
+ktap_print_msg()
+{
+	echo "#" $@
+}
+
 ktap_set_plan() {
-	num_tests="$1"
+	KSFT_NUM_TESTS="$1"
 
-	echo "1..$num_tests"
+	echo "1..$KSFT_NUM_TESTS"
 }
 
 ktap_skip_all() {
@@ -65,6 +78,34 @@ ktap_test_fail() {
 	KTAP_CNT_FAIL=$((KTAP_CNT_FAIL+1))
 }
 
+ktap_test_result() {
+	description="$1"
+	shift
+
+	if $@; then
+		ktap_test_pass "$description"
+	else
+		ktap_test_fail "$description"
+	fi
+}
+
+ktap_exit_fail_msg() {
+	echo "Bail out! " $@
+	ktap_print_totals
+
+	exit "$KSFT_FAIL"
+}
+
+ktap_finished() {
+	ktap_print_totals
+
+	if [ $(("$KTAP_CNT_PASS" + "$KTAP_CNT_SKIP")) -eq "$KSFT_NUM_TESTS" ]; then
+		exit "$KSFT_PASS"
+	else
+		exit "$KSFT_FAIL"
+	fi
+}
+
 ktap_print_totals() {
 	echo "# Totals: pass:$KTAP_CNT_PASS fail:$KTAP_CNT_FAIL xfail:0 xpass:0 skip:$KTAP_CNT_SKIP error:0"
 }
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 3e0c36b8ddd5..492e937fab00 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -77,11 +77,12 @@ TEST_GEN_PROGS_x86_64 += x86_64/hyperv_svm_test
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_tlb_flush
 TEST_GEN_PROGS_x86_64 += x86_64/kvm_clock_test
 TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test
-TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test
 TEST_GEN_PROGS_x86_64 += x86_64/monitor_mwait_test
 TEST_GEN_PROGS_x86_64 += x86_64/nested_exceptions_test
 TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
 TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test
+TEST_GEN_PROGS_x86_64 += x86_64/private_mem_conversions_test
+TEST_GEN_PROGS_x86_64 += x86_64/private_mem_kvm_exits_test
 TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id
 TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
 TEST_GEN_PROGS_x86_64 += x86_64/smaller_maxphyaddr_emulation_test
@@ -124,6 +125,7 @@ TEST_GEN_PROGS_x86_64 += access_tracking_perf_test
 TEST_GEN_PROGS_x86_64 += demand_paging_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
 TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
+TEST_GEN_PROGS_x86_64 += guest_memfd_test
 TEST_GEN_PROGS_x86_64 += guest_print_test
 TEST_GEN_PROGS_x86_64 += hardware_disable_test
 TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
@@ -184,12 +186,13 @@ TEST_GEN_PROGS_s390x += kvm_binary_stats_test
 
 TEST_GEN_PROGS_riscv += demand_paging_test
 TEST_GEN_PROGS_riscv += dirty_log_test
-TEST_GEN_PROGS_riscv += guest_print_test
 TEST_GEN_PROGS_riscv += get-reg-list
+TEST_GEN_PROGS_riscv += guest_print_test
+TEST_GEN_PROGS_riscv += kvm_binary_stats_test
 TEST_GEN_PROGS_riscv += kvm_create_max_vcpus
 TEST_GEN_PROGS_riscv += kvm_page_table_test
 TEST_GEN_PROGS_riscv += set_memory_region_test
-TEST_GEN_PROGS_riscv += kvm_binary_stats_test
+TEST_GEN_PROGS_riscv += steal_time
 
 SPLIT_TESTS += get-reg-list
 
diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c
index 274b8465b42a..2cb8dd1f8275 100644
--- a/tools/testing/selftests/kvm/aarch64/arch_timer.c
+++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c
@@ -248,7 +248,7 @@ static void *test_vcpu_run(void *arg)
 		REPORT_GUEST_ASSERT(uc);
 		break;
 	default:
-		TEST_FAIL("Unexpected guest exit\n");
+		TEST_FAIL("Unexpected guest exit");
 	}
 
 	return NULL;
@@ -287,7 +287,7 @@ static int test_migrate_vcpu(unsigned int vcpu_idx)
 
 	/* Allow the error where the vCPU thread is already finished */
 	TEST_ASSERT(ret == 0 || ret == ESRCH,
-		    "Failed to migrate the vCPU:%u to pCPU: %u; ret: %d\n",
+		    "Failed to migrate the vCPU:%u to pCPU: %u; ret: %d",
 		    vcpu_idx, new_pcpu, ret);
 
 	return ret;
@@ -326,12 +326,12 @@ static void test_run(struct kvm_vm *vm)
 
 	pthread_mutex_init(&vcpu_done_map_lock, NULL);
 	vcpu_done_map = bitmap_zalloc(test_args.nr_vcpus);
-	TEST_ASSERT(vcpu_done_map, "Failed to allocate vcpu done bitmap\n");
+	TEST_ASSERT(vcpu_done_map, "Failed to allocate vcpu done bitmap");
 
 	for (i = 0; i < (unsigned long)test_args.nr_vcpus; i++) {
 		ret = pthread_create(&pt_vcpu_run[i], NULL, test_vcpu_run,
 				     (void *)(unsigned long)i);
-		TEST_ASSERT(!ret, "Failed to create vCPU-%d pthread\n", i);
+		TEST_ASSERT(!ret, "Failed to create vCPU-%d pthread", i);
 	}
 
 	/* Spawn a thread to control the vCPU migrations */
@@ -340,7 +340,7 @@ static void test_run(struct kvm_vm *vm)
 
 		ret = pthread_create(&pt_vcpu_migration, NULL,
 					test_vcpu_migration, NULL);
-		TEST_ASSERT(!ret, "Failed to create the migration pthread\n");
+		TEST_ASSERT(!ret, "Failed to create the migration pthread");
 	}
 
 
@@ -384,7 +384,7 @@ static struct kvm_vm *test_vm_create(void)
 		if (kvm_has_cap(KVM_CAP_COUNTER_OFFSET))
 			vm_ioctl(vm, KVM_ARM_SET_COUNTER_OFFSET, &test_args.offset);
 		else
-			TEST_FAIL("no support for global offset\n");
+			TEST_FAIL("no support for global offset");
 	}
 
 	for (i = 0; i < nr_vcpus; i++)
diff --git a/tools/testing/selftests/kvm/aarch64/hypercalls.c b/tools/testing/selftests/kvm/aarch64/hypercalls.c
index 31f66ba97228..27c10e7a7e01 100644
--- a/tools/testing/selftests/kvm/aarch64/hypercalls.c
+++ b/tools/testing/selftests/kvm/aarch64/hypercalls.c
@@ -175,18 +175,18 @@ static void test_fw_regs_before_vm_start(struct kvm_vcpu *vcpu)
 		/* First 'read' should be an upper limit of the features supported */
 		vcpu_get_reg(vcpu, reg_info->reg, &val);
 		TEST_ASSERT(val == FW_REG_ULIMIT_VAL(reg_info->max_feat_bit),
-			"Expected all the features to be set for reg: 0x%lx; expected: 0x%lx; read: 0x%lx\n",
+			"Expected all the features to be set for reg: 0x%lx; expected: 0x%lx; read: 0x%lx",
 			reg_info->reg, FW_REG_ULIMIT_VAL(reg_info->max_feat_bit), val);
 
 		/* Test a 'write' by disabling all the features of the register map */
 		ret = __vcpu_set_reg(vcpu, reg_info->reg, 0);
 		TEST_ASSERT(ret == 0,
-			"Failed to clear all the features of reg: 0x%lx; ret: %d\n",
+			"Failed to clear all the features of reg: 0x%lx; ret: %d",
 			reg_info->reg, errno);
 
 		vcpu_get_reg(vcpu, reg_info->reg, &val);
 		TEST_ASSERT(val == 0,
-			"Expected all the features to be cleared for reg: 0x%lx\n", reg_info->reg);
+			"Expected all the features to be cleared for reg: 0x%lx", reg_info->reg);
 
 		/*
 		 * Test enabling a feature that's not supported.
@@ -195,7 +195,7 @@ static void test_fw_regs_before_vm_start(struct kvm_vcpu *vcpu)
 		if (reg_info->max_feat_bit < 63) {
 			ret = __vcpu_set_reg(vcpu, reg_info->reg, BIT(reg_info->max_feat_bit + 1));
 			TEST_ASSERT(ret != 0 && errno == EINVAL,
-			"Unexpected behavior or return value (%d) while setting an unsupported feature for reg: 0x%lx\n",
+			"Unexpected behavior or return value (%d) while setting an unsupported feature for reg: 0x%lx",
 			errno, reg_info->reg);
 		}
 	}
@@ -216,7 +216,7 @@ static void test_fw_regs_after_vm_start(struct kvm_vcpu *vcpu)
 		 */
 		vcpu_get_reg(vcpu, reg_info->reg, &val);
 		TEST_ASSERT(val == 0,
-			"Expected all the features to be cleared for reg: 0x%lx\n",
+			"Expected all the features to be cleared for reg: 0x%lx",
 			reg_info->reg);
 
 		/*
@@ -226,7 +226,7 @@ static void test_fw_regs_after_vm_start(struct kvm_vcpu *vcpu)
 		 */
 		ret = __vcpu_set_reg(vcpu, reg_info->reg, FW_REG_ULIMIT_VAL(reg_info->max_feat_bit));
 		TEST_ASSERT(ret != 0 && errno == EBUSY,
-		"Unexpected behavior or return value (%d) while setting a feature while VM is running for reg: 0x%lx\n",
+		"Unexpected behavior or return value (%d) while setting a feature while VM is running for reg: 0x%lx",
 		errno, reg_info->reg);
 	}
 }
@@ -265,7 +265,7 @@ static void test_guest_stage(struct kvm_vm **vm, struct kvm_vcpu **vcpu)
 	case TEST_STAGE_HVC_IFACE_FALSE_INFO:
 		break;
 	default:
-		TEST_FAIL("Unknown test stage: %d\n", prev_stage);
+		TEST_FAIL("Unknown test stage: %d", prev_stage);
 	}
 }
 
@@ -294,7 +294,7 @@ static void test_run(void)
 			REPORT_GUEST_ASSERT(uc);
 			break;
 		default:
-			TEST_FAIL("Unexpected guest exit\n");
+			TEST_FAIL("Unexpected guest exit");
 		}
 	}
 
diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
index eb4217b7c768..53fddad57cbb 100644
--- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
@@ -414,10 +414,10 @@ static bool punch_hole_in_backing_store(struct kvm_vm *vm,
 	if (fd != -1) {
 		ret = fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
 				0, paging_size);
-		TEST_ASSERT(ret == 0, "fallocate failed\n");
+		TEST_ASSERT(ret == 0, "fallocate failed");
 	} else {
 		ret = madvise(hva, paging_size, MADV_DONTNEED);
-		TEST_ASSERT(ret == 0, "madvise failed\n");
+		TEST_ASSERT(ret == 0, "madvise failed");
 	}
 
 	return true;
@@ -501,7 +501,7 @@ static bool handle_cmd(struct kvm_vm *vm, int cmd)
 
 void fail_vcpu_run_no_handler(int ret)
 {
-	TEST_FAIL("Unexpected vcpu run failure\n");
+	TEST_FAIL("Unexpected vcpu run failure");
 }
 
 void fail_vcpu_run_mmio_no_syndrome_handler(int ret)
@@ -705,7 +705,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	print_test_banner(mode, p);
 
-	vm = ____vm_create(mode);
+	vm = ____vm_create(VM_SHAPE(mode));
 	setup_memslots(vm, p);
 	kvm_vm_elf_load(vm, program_invocation_name);
 	setup_ucall(vm);
diff --git a/tools/testing/selftests/kvm/aarch64/smccc_filter.c b/tools/testing/selftests/kvm/aarch64/smccc_filter.c
index f4ceae9c8925..2d189f3da228 100644
--- a/tools/testing/selftests/kvm/aarch64/smccc_filter.c
+++ b/tools/testing/selftests/kvm/aarch64/smccc_filter.c
@@ -178,7 +178,7 @@ static void expect_call_denied(struct kvm_vcpu *vcpu)
 	struct ucall uc;
 
 	if (get_ucall(vcpu, &uc) != UCALL_SYNC)
-		TEST_FAIL("Unexpected ucall: %lu\n", uc.cmd);
+		TEST_FAIL("Unexpected ucall: %lu", uc.cmd);
 
 	TEST_ASSERT(uc.args[1] == SMCCC_RET_NOT_SUPPORTED,
 		    "Unexpected SMCCC return code: %lu", uc.args[1]);
diff --git a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
index 9d51b5691349..5f9713364693 100644
--- a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
+++ b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
@@ -517,11 +517,11 @@ static void test_create_vpmu_vm_with_pmcr_n(uint64_t pmcr_n, bool expect_fail)
 
 	if (expect_fail)
 		TEST_ASSERT(pmcr_orig == pmcr,
-			    "PMCR.N modified by KVM to a larger value (PMCR: 0x%lx) for pmcr_n: 0x%lx\n",
+			    "PMCR.N modified by KVM to a larger value (PMCR: 0x%lx) for pmcr_n: 0x%lx",
 			    pmcr, pmcr_n);
 	else
 		TEST_ASSERT(pmcr_n == get_pmcr_n(pmcr),
-			    "Failed to update PMCR.N to %lu (received: %lu)\n",
+			    "Failed to update PMCR.N to %lu (received: %lu)",
 			    pmcr_n, get_pmcr_n(pmcr));
 }
 
@@ -594,12 +594,12 @@ static void run_pmregs_validity_test(uint64_t pmcr_n)
 		 */
 		vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), &reg_val);
 		TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
-			    "Initial read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx\n",
+			    "Initial read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx",
 			    KVM_ARM64_SYS_REG(set_reg_id), reg_val);
 
 		vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id), &reg_val);
 		TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
-			    "Initial read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx\n",
+			    "Initial read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx",
 			    KVM_ARM64_SYS_REG(clr_reg_id), reg_val);
 
 		/*
@@ -611,12 +611,12 @@ static void run_pmregs_validity_test(uint64_t pmcr_n)
 
 		vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), &reg_val);
 		TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
-			    "Read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx\n",
+			    "Read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx",
 			    KVM_ARM64_SYS_REG(set_reg_id), reg_val);
 
 		vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id), &reg_val);
 		TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
-			    "Read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx\n",
+			    "Read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx",
 			    KVM_ARM64_SYS_REG(clr_reg_id), reg_val);
 	}
 
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 09c116a82a84..bf3609f71854 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -45,10 +45,10 @@ static void vcpu_worker(struct memstress_vcpu_args *vcpu_args)
 
 	/* Let the guest access its memory */
 	ret = _vcpu_run(vcpu);
-	TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
+	TEST_ASSERT(ret == 0, "vcpu_run failed: %d", ret);
 	if (get_ucall(vcpu, NULL) != UCALL_SYNC) {
 		TEST_ASSERT(false,
-			    "Invalid guest sync status: exit_reason=%s\n",
+			    "Invalid guest sync status: exit_reason=%s",
 			    exit_reason_str(run->exit_reason));
 	}
 
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index d374dbcf9a53..504f6fe980e8 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -88,9 +88,9 @@ static void vcpu_worker(struct memstress_vcpu_args *vcpu_args)
 		ret = _vcpu_run(vcpu);
 		ts_diff = timespec_elapsed(start);
 
-		TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
+		TEST_ASSERT(ret == 0, "vcpu_run failed: %d", ret);
 		TEST_ASSERT(get_ucall(vcpu, NULL) == UCALL_SYNC,
-			    "Invalid guest sync status: exit_reason=%s\n",
+			    "Invalid guest sync status: exit_reason=%s",
 			    exit_reason_str(run->exit_reason));
 
 		pr_debug("Got sync event from vCPU %d\n", vcpu_idx);
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 936f3a8d1b83..eaad5b20854c 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -262,7 +262,7 @@ static void default_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err)
 		    "vcpu run failed: errno=%d", err);
 
 	TEST_ASSERT(get_ucall(vcpu, NULL) == UCALL_SYNC,
-		    "Invalid guest sync status: exit_reason=%s\n",
+		    "Invalid guest sync status: exit_reason=%s",
 		    exit_reason_str(run->exit_reason));
 
 	vcpu_handle_sync_stop();
@@ -376,7 +376,10 @@ static void dirty_ring_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot,
 
 	cleared = kvm_vm_reset_dirty_ring(vcpu->vm);
 
-	/* Cleared pages should be the same as collected */
+	/*
+	 * Cleared pages should be the same as collected, as KVM is supposed to
+	 * clear only the entries that have been harvested.
+	 */
 	TEST_ASSERT(cleared == count, "Reset dirty pages (%u) mismatch "
 		    "with collected (%u)", cleared, count);
 
@@ -410,17 +413,11 @@ static void dirty_ring_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err)
 		pr_info("vcpu continues now.\n");
 	} else {
 		TEST_ASSERT(false, "Invalid guest sync status: "
-			    "exit_reason=%s\n",
+			    "exit_reason=%s",
 			    exit_reason_str(run->exit_reason));
 	}
 }
 
-static void dirty_ring_before_vcpu_join(void)
-{
-	/* Kick another round of vcpu just to make sure it will quit */
-	sem_post(&sem_vcpu_cont);
-}
-
 struct log_mode {
 	const char *name;
 	/* Return true if this mode is supported, otherwise false */
@@ -433,7 +430,6 @@ struct log_mode {
 				     uint32_t *ring_buf_idx);
 	/* Hook to call when after each vcpu run */
 	void (*after_vcpu_run)(struct kvm_vcpu *vcpu, int ret, int err);
-	void (*before_vcpu_join) (void);
 } log_modes[LOG_MODE_NUM] = {
 	{
 		.name = "dirty-log",
@@ -452,7 +448,6 @@ struct log_mode {
 		.supported = dirty_ring_supported,
 		.create_vm_done = dirty_ring_create_vm_done,
 		.collect_dirty_pages = dirty_ring_collect_dirty_pages,
-		.before_vcpu_join = dirty_ring_before_vcpu_join,
 		.after_vcpu_run = dirty_ring_after_vcpu_run,
 	},
 };
@@ -513,14 +508,6 @@ static void log_mode_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err)
 		mode->after_vcpu_run(vcpu, ret, err);
 }
 
-static void log_mode_before_vcpu_join(void)
-{
-	struct log_mode *mode = &log_modes[host_log_mode];
-
-	if (mode->before_vcpu_join)
-		mode->before_vcpu_join();
-}
-
 static void generate_random_array(uint64_t *guest_array, uint64_t size)
 {
 	uint64_t i;
@@ -699,7 +686,7 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, struct kvm_vcpu **vcpu,
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
-	vm = __vm_create(mode, 1, extra_mem_pages);
+	vm = __vm_create(VM_SHAPE(mode), 1, extra_mem_pages);
 
 	log_mode_create_vm_done(vm);
 	*vcpu = vm_vcpu_add(vm, 0, guest_code);
@@ -719,6 +706,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	struct kvm_vm *vm;
 	unsigned long *bmap;
 	uint32_t ring_buf_idx = 0;
+	int sem_val;
 
 	if (!log_mode_supported()) {
 		print_skip("Log mode '%s' not supported",
@@ -788,12 +776,22 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	/* Start the iterations */
 	iteration = 1;
 	sync_global_to_guest(vm, iteration);
-	host_quit = false;
+	WRITE_ONCE(host_quit, false);
 	host_dirty_count = 0;
 	host_clear_count = 0;
 	host_track_next_count = 0;
 	WRITE_ONCE(dirty_ring_vcpu_ring_full, false);
 
+	/*
+	 * Ensure the previous iteration didn't leave a dangling semaphore, i.e.
+	 * that the main task and vCPU worker were synchronized and completed
+	 * verification of all iterations.
+	 */
+	sem_getvalue(&sem_vcpu_stop, &sem_val);
+	TEST_ASSERT_EQ(sem_val, 0);
+	sem_getvalue(&sem_vcpu_cont, &sem_val);
+	TEST_ASSERT_EQ(sem_val, 0);
+
 	pthread_create(&vcpu_thread, NULL, vcpu_worker, vcpu);
 
 	while (iteration < p->iterations) {
@@ -819,15 +817,21 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		assert(host_log_mode == LOG_MODE_DIRTY_RING ||
 		       atomic_read(&vcpu_sync_stop_requested) == false);
 		vm_dirty_log_verify(mode, bmap);
-		sem_post(&sem_vcpu_cont);
 
-		iteration++;
+		/*
+		 * Set host_quit before sem_vcpu_cont in the final iteration to
+		 * ensure that the vCPU worker doesn't resume the guest.  As
+		 * above, the dirty ring test may stop and wait even when not
+		 * explicitly request to do so, i.e. would hang waiting for a
+		 * "continue" if it's allowed to resume the guest.
+		 */
+		if (++iteration == p->iterations)
+			WRITE_ONCE(host_quit, true);
+
+		sem_post(&sem_vcpu_cont);
 		sync_global_to_guest(vm, iteration);
 	}
 
-	/* Tell the vcpu thread to quit */
-	host_quit = true;
-	log_mode_before_vcpu_join();
 	pthread_join(vcpu_thread, NULL);
 
 	pr_info("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), "
diff --git a/tools/testing/selftests/kvm/get-reg-list.c b/tools/testing/selftests/kvm/get-reg-list.c
index 8274ef04301f..91f05f78e824 100644
--- a/tools/testing/selftests/kvm/get-reg-list.c
+++ b/tools/testing/selftests/kvm/get-reg-list.c
@@ -152,7 +152,7 @@ static void check_supported(struct vcpu_reg_list *c)
 			continue;
 
 		__TEST_REQUIRE(kvm_has_cap(s->capability),
-			       "%s: %s not available, skipping tests\n",
+			       "%s: %s not available, skipping tests",
 			       config_name(c), s->name);
 	}
 }
diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c
new file mode 100644
index 000000000000..c78a98c1a915
--- /dev/null
+++ b/tools/testing/selftests/kvm/guest_memfd_test.c
@@ -0,0 +1,198 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright Intel Corporation, 2023
+ *
+ * Author: Chao Peng <chao.p.peng@linux.intel.com>
+ */
+
+#define _GNU_SOURCE
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <stdio.h>
+#include <fcntl.h>
+
+#include <linux/bitmap.h>
+#include <linux/falloc.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#include "test_util.h"
+#include "kvm_util_base.h"
+
+static void test_file_read_write(int fd)
+{
+	char buf[64];
+
+	TEST_ASSERT(read(fd, buf, sizeof(buf)) < 0,
+		    "read on a guest_mem fd should fail");
+	TEST_ASSERT(write(fd, buf, sizeof(buf)) < 0,
+		    "write on a guest_mem fd should fail");
+	TEST_ASSERT(pread(fd, buf, sizeof(buf), 0) < 0,
+		    "pread on a guest_mem fd should fail");
+	TEST_ASSERT(pwrite(fd, buf, sizeof(buf), 0) < 0,
+		    "pwrite on a guest_mem fd should fail");
+}
+
+static void test_mmap(int fd, size_t page_size)
+{
+	char *mem;
+
+	mem = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+	TEST_ASSERT_EQ(mem, MAP_FAILED);
+}
+
+static void test_file_size(int fd, size_t page_size, size_t total_size)
+{
+	struct stat sb;
+	int ret;
+
+	ret = fstat(fd, &sb);
+	TEST_ASSERT(!ret, "fstat should succeed");
+	TEST_ASSERT_EQ(sb.st_size, total_size);
+	TEST_ASSERT_EQ(sb.st_blksize, page_size);
+}
+
+static void test_fallocate(int fd, size_t page_size, size_t total_size)
+{
+	int ret;
+
+	ret = fallocate(fd, FALLOC_FL_KEEP_SIZE, 0, total_size);
+	TEST_ASSERT(!ret, "fallocate with aligned offset and size should succeed");
+
+	ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE,
+			page_size - 1, page_size);
+	TEST_ASSERT(ret, "fallocate with unaligned offset should fail");
+
+	ret = fallocate(fd, FALLOC_FL_KEEP_SIZE, total_size, page_size);
+	TEST_ASSERT(ret, "fallocate beginning at total_size should fail");
+
+	ret = fallocate(fd, FALLOC_FL_KEEP_SIZE, total_size + page_size, page_size);
+	TEST_ASSERT(ret, "fallocate beginning after total_size should fail");
+
+	ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE,
+			total_size, page_size);
+	TEST_ASSERT(!ret, "fallocate(PUNCH_HOLE) at total_size should succeed");
+
+	ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE,
+			total_size + page_size, page_size);
+	TEST_ASSERT(!ret, "fallocate(PUNCH_HOLE) after total_size should succeed");
+
+	ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE,
+			page_size, page_size - 1);
+	TEST_ASSERT(ret, "fallocate with unaligned size should fail");
+
+	ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE,
+			page_size, page_size);
+	TEST_ASSERT(!ret, "fallocate(PUNCH_HOLE) with aligned offset and size should succeed");
+
+	ret = fallocate(fd, FALLOC_FL_KEEP_SIZE, page_size, page_size);
+	TEST_ASSERT(!ret, "fallocate to restore punched hole should succeed");
+}
+
+static void test_invalid_punch_hole(int fd, size_t page_size, size_t total_size)
+{
+	struct {
+		off_t offset;
+		off_t len;
+	} testcases[] = {
+		{0, 1},
+		{0, page_size - 1},
+		{0, page_size + 1},
+
+		{1, 1},
+		{1, page_size - 1},
+		{1, page_size},
+		{1, page_size + 1},
+
+		{page_size, 1},
+		{page_size, page_size - 1},
+		{page_size, page_size + 1},
+	};
+	int ret, i;
+
+	for (i = 0; i < ARRAY_SIZE(testcases); i++) {
+		ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE,
+				testcases[i].offset, testcases[i].len);
+		TEST_ASSERT(ret == -1 && errno == EINVAL,
+			    "PUNCH_HOLE with !PAGE_SIZE offset (%lx) and/or length (%lx) should fail",
+			    testcases[i].offset, testcases[i].len);
+	}
+}
+
+static void test_create_guest_memfd_invalid(struct kvm_vm *vm)
+{
+	size_t page_size = getpagesize();
+	uint64_t flag;
+	size_t size;
+	int fd;
+
+	for (size = 1; size < page_size; size++) {
+		fd = __vm_create_guest_memfd(vm, size, 0);
+		TEST_ASSERT(fd == -1 && errno == EINVAL,
+			    "guest_memfd() with non-page-aligned page size '0x%lx' should fail with EINVAL",
+			    size);
+	}
+
+	for (flag = 0; flag; flag <<= 1) {
+		fd = __vm_create_guest_memfd(vm, page_size, flag);
+		TEST_ASSERT(fd == -1 && errno == EINVAL,
+			    "guest_memfd() with flag '0x%lx' should fail with EINVAL",
+			    flag);
+	}
+}
+
+static void test_create_guest_memfd_multiple(struct kvm_vm *vm)
+{
+	int fd1, fd2, ret;
+	struct stat st1, st2;
+
+	fd1 = __vm_create_guest_memfd(vm, 4096, 0);
+	TEST_ASSERT(fd1 != -1, "memfd creation should succeed");
+
+	ret = fstat(fd1, &st1);
+	TEST_ASSERT(ret != -1, "memfd fstat should succeed");
+	TEST_ASSERT(st1.st_size == 4096, "memfd st_size should match requested size");
+
+	fd2 = __vm_create_guest_memfd(vm, 8192, 0);
+	TEST_ASSERT(fd2 != -1, "memfd creation should succeed");
+
+	ret = fstat(fd2, &st2);
+	TEST_ASSERT(ret != -1, "memfd fstat should succeed");
+	TEST_ASSERT(st2.st_size == 8192, "second memfd st_size should match requested size");
+
+	ret = fstat(fd1, &st1);
+	TEST_ASSERT(ret != -1, "memfd fstat should succeed");
+	TEST_ASSERT(st1.st_size == 4096, "first memfd st_size should still match requested size");
+	TEST_ASSERT(st1.st_ino != st2.st_ino, "different memfd should have different inode numbers");
+}
+
+int main(int argc, char *argv[])
+{
+	size_t page_size;
+	size_t total_size;
+	int fd;
+	struct kvm_vm *vm;
+
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_GUEST_MEMFD));
+
+	page_size = getpagesize();
+	total_size = page_size * 4;
+
+	vm = vm_create_barebones();
+
+	test_create_guest_memfd_invalid(vm);
+	test_create_guest_memfd_multiple(vm);
+
+	fd = vm_create_guest_memfd(vm, total_size, 0);
+
+	test_file_read_write(fd);
+	test_mmap(fd, page_size);
+	test_file_size(fd, page_size, total_size);
+	test_fallocate(fd, page_size, total_size);
+	test_invalid_punch_hole(fd, page_size, total_size);
+
+	close(fd);
+}
diff --git a/tools/testing/selftests/kvm/guest_print_test.c b/tools/testing/selftests/kvm/guest_print_test.c
index 41230b746190..3502caa3590c 100644
--- a/tools/testing/selftests/kvm/guest_print_test.c
+++ b/tools/testing/selftests/kvm/guest_print_test.c
@@ -98,7 +98,7 @@ static void ucall_abort(const char *assert_msg, const char *expected_assert_msg)
 	int offset = len_str - len_substr;
 
 	TEST_ASSERT(len_substr <= len_str,
-		    "Expected '%s' to be a substring of '%s'\n",
+		    "Expected '%s' to be a substring of '%s'",
 		    assert_msg, expected_assert_msg);
 
 	TEST_ASSERT(strcmp(&assert_msg[offset], expected_assert_msg) == 0,
@@ -116,7 +116,7 @@ static void run_test(struct kvm_vcpu *vcpu, const char *expected_printf,
 		vcpu_run(vcpu);
 
 		TEST_ASSERT(run->exit_reason == UCALL_EXIT_REASON,
-			    "Unexpected exit reason: %u (%s),\n",
+			    "Unexpected exit reason: %u (%s),",
 			    run->exit_reason, exit_reason_str(run->exit_reason));
 
 		switch (get_ucall(vcpu, &uc)) {
@@ -161,11 +161,11 @@ static void test_limits(void)
 	vcpu_run(vcpu);
 
 	TEST_ASSERT(run->exit_reason == UCALL_EXIT_REASON,
-		    "Unexpected exit reason: %u (%s),\n",
+		    "Unexpected exit reason: %u (%s),",
 		    run->exit_reason, exit_reason_str(run->exit_reason));
 
 	TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_ABORT,
-		    "Unexpected ucall command: %lu,  Expected: %u (UCALL_ABORT)\n",
+		    "Unexpected ucall command: %lu,  Expected: %u (UCALL_ABORT)",
 		    uc.cmd, UCALL_ABORT);
 
 	kvm_vm_free(vm);
diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c
index f5d59b9934f1..decc521fc760 100644
--- a/tools/testing/selftests/kvm/hardware_disable_test.c
+++ b/tools/testing/selftests/kvm/hardware_disable_test.c
@@ -41,7 +41,7 @@ static void *run_vcpu(void *arg)
 
 	vcpu_run(vcpu);
 
-	TEST_ASSERT(false, "%s: exited with reason %d: %s\n",
+	TEST_ASSERT(false, "%s: exited with reason %d: %s",
 		    __func__, run->exit_reason,
 		    exit_reason_str(run->exit_reason));
 	pthread_exit(NULL);
@@ -55,7 +55,7 @@ static void *sleeping_thread(void *arg)
 		fd = open("/dev/null", O_RDWR);
 		close(fd);
 	}
-	TEST_ASSERT(false, "%s: exited\n", __func__);
+	TEST_ASSERT(false, "%s: exited", __func__);
 	pthread_exit(NULL);
 }
 
@@ -118,7 +118,7 @@ static void run_test(uint32_t run)
 	for (i = 0; i < VCPU_NUM; ++i)
 		check_join(threads[i], &b);
 	/* Should not be reached */
-	TEST_ASSERT(false, "%s: [%d] child escaped the ninja\n", __func__, run);
+	TEST_ASSERT(false, "%s: [%d] child escaped the ninja", __func__, run);
 }
 
 void wait_for_child_setup(pid_t pid)
diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
index c42d683102c7..cf20e44e86f2 100644
--- a/tools/testing/selftests/kvm/include/aarch64/processor.h
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -119,8 +119,8 @@ enum {
 /* Access flag update enable/disable */
 #define TCR_EL1_HA		(1ULL << 39)
 
-void aarch64_get_supported_page_sizes(uint32_t ipa,
-				      bool *ps4k, bool *ps16k, bool *ps64k);
+void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k,
+					uint32_t *ipa16k, uint32_t *ipa64k);
 
 void vm_init_descriptor_tables(struct kvm_vm *vm);
 void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu);
diff --git a/tools/testing/selftests/kvm/include/guest_modes.h b/tools/testing/selftests/kvm/include/guest_modes.h
index b691df33e64e..63f5167397cc 100644
--- a/tools/testing/selftests/kvm/include/guest_modes.h
+++ b/tools/testing/selftests/kvm/include/guest_modes.h
@@ -11,8 +11,8 @@ struct guest_mode {
 
 extern struct guest_mode guest_modes[NUM_VM_MODES];
 
-#define guest_mode_append(mode, supported, enabled) ({ \
-	guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
+#define guest_mode_append(mode, enabled) ({ \
+	guest_modes[mode] = (struct guest_mode){ (enabled), (enabled) }; \
 })
 
 void guest_modes_append_default(void);
diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index a18db6a7b3cf..9e5afc472c14 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -44,7 +44,7 @@ typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */
 typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
 
 struct userspace_mem_region {
-	struct kvm_userspace_memory_region region;
+	struct kvm_userspace_memory_region2 region;
 	struct sparsebit *unused_phy_pages;
 	int fd;
 	off_t offset;
@@ -129,6 +129,7 @@ struct vcpu_reg_sublist {
 	const char *name;
 	long capability;
 	int feature;
+	int feature_type;
 	bool finalize;
 	__u64 *regs;
 	__u64 regs_n;
@@ -171,6 +172,7 @@ static inline struct userspace_mem_region *vm_get_mem_region(struct kvm_vm *vm,
 
 enum vm_guest_mode {
 	VM_MODE_P52V48_4K,
+	VM_MODE_P52V48_16K,
 	VM_MODE_P52V48_64K,
 	VM_MODE_P48V48_4K,
 	VM_MODE_P48V48_16K,
@@ -188,6 +190,23 @@ enum vm_guest_mode {
 	NUM_VM_MODES,
 };
 
+struct vm_shape {
+	enum vm_guest_mode mode;
+	unsigned int type;
+};
+
+#define VM_TYPE_DEFAULT			0
+
+#define VM_SHAPE(__mode)			\
+({						\
+	struct vm_shape shape = {		\
+		.mode = (__mode),		\
+		.type = VM_TYPE_DEFAULT		\
+	};					\
+						\
+	shape;					\
+})
+
 #if defined(__aarch64__)
 
 extern enum vm_guest_mode vm_mode_default;
@@ -220,6 +239,8 @@ extern enum vm_guest_mode vm_mode_default;
 
 #endif
 
+#define VM_SHAPE_DEFAULT	VM_SHAPE(VM_MODE_DEFAULT)
+
 #define MIN_PAGE_SIZE		(1U << MIN_PAGE_SHIFT)
 #define PTES_PER_MIN_PAGE	ptes_per_page(MIN_PAGE_SIZE)
 
@@ -248,6 +269,13 @@ static inline bool kvm_has_cap(long cap)
 #define __KVM_SYSCALL_ERROR(_name, _ret) \
 	"%s failed, rc: %i errno: %i (%s)", (_name), (_ret), errno, strerror(errno)
 
+/*
+ * Use the "inner", double-underscore macro when reporting errors from within
+ * other macros so that the name of ioctl() and not its literal numeric value
+ * is printed on error.  The "outer" macro is strongly preferred when reporting
+ * errors "directly", i.e. without an additional layer of macros, as it reduces
+ * the probability of passing in the wrong string.
+ */
 #define __KVM_IOCTL_ERROR(_name, _ret)	__KVM_SYSCALL_ERROR(_name, _ret)
 #define KVM_IOCTL_ERROR(_ioctl, _ret) __KVM_IOCTL_ERROR(#_ioctl, _ret)
 
@@ -260,17 +288,13 @@ static inline bool kvm_has_cap(long cap)
 #define __kvm_ioctl(kvm_fd, cmd, arg)				\
 	kvm_do_ioctl(kvm_fd, cmd, arg)
 
-
-#define _kvm_ioctl(kvm_fd, cmd, name, arg)			\
+#define kvm_ioctl(kvm_fd, cmd, arg)				\
 ({								\
 	int ret = __kvm_ioctl(kvm_fd, cmd, arg);		\
 								\
-	TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret));	\
+	TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(#cmd, ret));	\
 })
 
-#define kvm_ioctl(kvm_fd, cmd, arg) \
-	_kvm_ioctl(kvm_fd, cmd, #cmd, arg)
-
 static __always_inline void static_assert_is_vm(struct kvm_vm *vm) { }
 
 #define __vm_ioctl(vm, cmd, arg)				\
@@ -279,17 +303,42 @@ static __always_inline void static_assert_is_vm(struct kvm_vm *vm) { }
 	kvm_do_ioctl((vm)->fd, cmd, arg);			\
 })
 
-#define _vm_ioctl(vm, cmd, name, arg)				\
+/*
+ * Assert that a VM or vCPU ioctl() succeeded, with extra magic to detect if
+ * the ioctl() failed because KVM killed/bugged the VM.  To detect a dead VM,
+ * probe KVM_CAP_USER_MEMORY, which (a) has been supported by KVM since before
+ * selftests existed and (b) should never outright fail, i.e. is supposed to
+ * return 0 or 1.  If KVM kills a VM, KVM returns -EIO for all ioctl()s for the
+ * VM and its vCPUs, including KVM_CHECK_EXTENSION.
+ */
+#define __TEST_ASSERT_VM_VCPU_IOCTL(cond, name, ret, vm)				\
+do {											\
+	int __errno = errno;								\
+											\
+	static_assert_is_vm(vm);							\
+											\
+	if (cond)									\
+		break;									\
+											\
+	if (errno == EIO &&								\
+	    __vm_ioctl(vm, KVM_CHECK_EXTENSION, (void *)KVM_CAP_USER_MEMORY) < 0) {	\
+		TEST_ASSERT(errno == EIO, "KVM killed the VM, should return -EIO");	\
+		TEST_FAIL("KVM killed/bugged the VM, check the kernel log for clues");	\
+	}										\
+	errno = __errno;								\
+	TEST_ASSERT(cond, __KVM_IOCTL_ERROR(name, ret));				\
+} while (0)
+
+#define TEST_ASSERT_VM_VCPU_IOCTL(cond, cmd, ret, vm)		\
+	__TEST_ASSERT_VM_VCPU_IOCTL(cond, #cmd, ret, vm)
+
+#define vm_ioctl(vm, cmd, arg)					\
 ({								\
 	int ret = __vm_ioctl(vm, cmd, arg);			\
 								\
-	TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret));	\
+	__TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, vm);		\
 })
 
-#define vm_ioctl(vm, cmd, arg)					\
-	_vm_ioctl(vm, cmd, #cmd, arg)
-
-
 static __always_inline void static_assert_is_vcpu(struct kvm_vcpu *vcpu) { }
 
 #define __vcpu_ioctl(vcpu, cmd, arg)				\
@@ -298,16 +347,13 @@ static __always_inline void static_assert_is_vcpu(struct kvm_vcpu *vcpu) { }
 	kvm_do_ioctl((vcpu)->fd, cmd, arg);			\
 })
 
-#define _vcpu_ioctl(vcpu, cmd, name, arg)			\
+#define vcpu_ioctl(vcpu, cmd, arg)				\
 ({								\
 	int ret = __vcpu_ioctl(vcpu, cmd, arg);			\
 								\
-	TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret));	\
+	__TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, (vcpu)->vm);	\
 })
 
-#define vcpu_ioctl(vcpu, cmd, arg)				\
-	_vcpu_ioctl(vcpu, cmd, #cmd, arg)
-
 /*
  * Looks up and returns the value corresponding to the capability
  * (KVM_CAP_*) given by cap.
@@ -316,7 +362,7 @@ static inline int vm_check_cap(struct kvm_vm *vm, long cap)
 {
 	int ret =  __vm_ioctl(vm, KVM_CHECK_EXTENSION, (void *)cap);
 
-	TEST_ASSERT(ret >= 0, KVM_IOCTL_ERROR(KVM_CHECK_EXTENSION, ret));
+	TEST_ASSERT_VM_VCPU_IOCTL(ret >= 0, KVM_CHECK_EXTENSION, ret, vm);
 	return ret;
 }
 
@@ -333,6 +379,54 @@ static inline void vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0)
 	vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap);
 }
 
+static inline void vm_set_memory_attributes(struct kvm_vm *vm, uint64_t gpa,
+					    uint64_t size, uint64_t attributes)
+{
+	struct kvm_memory_attributes attr = {
+		.attributes = attributes,
+		.address = gpa,
+		.size = size,
+		.flags = 0,
+	};
+
+	/*
+	 * KVM_SET_MEMORY_ATTRIBUTES overwrites _all_ attributes.  These flows
+	 * need significant enhancements to support multiple attributes.
+	 */
+	TEST_ASSERT(!attributes || attributes == KVM_MEMORY_ATTRIBUTE_PRIVATE,
+		    "Update me to support multiple attributes!");
+
+	vm_ioctl(vm, KVM_SET_MEMORY_ATTRIBUTES, &attr);
+}
+
+
+static inline void vm_mem_set_private(struct kvm_vm *vm, uint64_t gpa,
+				      uint64_t size)
+{
+	vm_set_memory_attributes(vm, gpa, size, KVM_MEMORY_ATTRIBUTE_PRIVATE);
+}
+
+static inline void vm_mem_set_shared(struct kvm_vm *vm, uint64_t gpa,
+				     uint64_t size)
+{
+	vm_set_memory_attributes(vm, gpa, size, 0);
+}
+
+void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t gpa, uint64_t size,
+			    bool punch_hole);
+
+static inline void vm_guest_mem_punch_hole(struct kvm_vm *vm, uint64_t gpa,
+					   uint64_t size)
+{
+	vm_guest_mem_fallocate(vm, gpa, size, true);
+}
+
+static inline void vm_guest_mem_allocate(struct kvm_vm *vm, uint64_t gpa,
+					 uint64_t size)
+{
+	vm_guest_mem_fallocate(vm, gpa, size, false);
+}
+
 void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size);
 const char *vm_guest_mode_string(uint32_t i);
 
@@ -375,7 +469,7 @@ static inline int vm_get_stats_fd(struct kvm_vm *vm)
 {
 	int fd = __vm_ioctl(vm, KVM_GET_STATS_FD, NULL);
 
-	TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_GET_STATS_FD, fd));
+	TEST_ASSERT_VM_VCPU_IOCTL(fd >= 0, KVM_GET_STATS_FD, fd, vm);
 	return fd;
 }
 
@@ -431,14 +525,44 @@ static inline uint64_t vm_get_stat(struct kvm_vm *vm, const char *stat_name)
 
 void vm_create_irqchip(struct kvm_vm *vm);
 
+static inline int __vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size,
+					uint64_t flags)
+{
+	struct kvm_create_guest_memfd guest_memfd = {
+		.size = size,
+		.flags = flags,
+	};
+
+	return __vm_ioctl(vm, KVM_CREATE_GUEST_MEMFD, &guest_memfd);
+}
+
+static inline int vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size,
+					uint64_t flags)
+{
+	int fd = __vm_create_guest_memfd(vm, size, flags);
+
+	TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_GUEST_MEMFD, fd));
+	return fd;
+}
+
 void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
 			       uint64_t gpa, uint64_t size, void *hva);
 int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
 				uint64_t gpa, uint64_t size, void *hva);
+void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
+				uint64_t gpa, uint64_t size, void *hva,
+				uint32_t guest_memfd, uint64_t guest_memfd_offset);
+int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
+				 uint64_t gpa, uint64_t size, void *hva,
+				 uint32_t guest_memfd, uint64_t guest_memfd_offset);
+
 void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	enum vm_mem_backing_src_type src_type,
 	uint64_t guest_paddr, uint32_t slot, uint64_t npages,
 	uint32_t flags);
+void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
+		uint64_t guest_paddr, uint32_t slot, uint64_t npages,
+		uint32_t flags, int guest_memfd_fd, uint64_t guest_memfd_offset);
 
 void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
 void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa);
@@ -587,7 +711,7 @@ static inline int vcpu_get_stats_fd(struct kvm_vcpu *vcpu)
 {
 	int fd = __vcpu_ioctl(vcpu, KVM_GET_STATS_FD, NULL);
 
-	TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_GET_STATS_FD, fd));
+	TEST_ASSERT_VM_VCPU_IOCTL(fd >= 0, KVM_CHECK_EXTENSION, fd, vcpu->vm);
 	return fd;
 }
 
@@ -713,21 +837,33 @@ vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm);
  * __vm_create() does NOT create vCPUs, @nr_runnable_vcpus is used purely to
  * calculate the amount of memory needed for per-vCPU data, e.g. stacks.
  */
-struct kvm_vm *____vm_create(enum vm_guest_mode mode);
-struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus,
+struct kvm_vm *____vm_create(struct vm_shape shape);
+struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus,
 			   uint64_t nr_extra_pages);
 
 static inline struct kvm_vm *vm_create_barebones(void)
 {
-	return ____vm_create(VM_MODE_DEFAULT);
+	return ____vm_create(VM_SHAPE_DEFAULT);
 }
 
+#ifdef __x86_64__
+static inline struct kvm_vm *vm_create_barebones_protected_vm(void)
+{
+	const struct vm_shape shape = {
+		.mode = VM_MODE_DEFAULT,
+		.type = KVM_X86_SW_PROTECTED_VM,
+	};
+
+	return ____vm_create(shape);
+}
+#endif
+
 static inline struct kvm_vm *vm_create(uint32_t nr_runnable_vcpus)
 {
-	return __vm_create(VM_MODE_DEFAULT, nr_runnable_vcpus, 0);
+	return __vm_create(VM_SHAPE_DEFAULT, nr_runnable_vcpus, 0);
 }
 
-struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
+struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, uint32_t nr_vcpus,
 				      uint64_t extra_mem_pages,
 				      void *guest_code, struct kvm_vcpu *vcpus[]);
 
@@ -735,17 +871,27 @@ static inline struct kvm_vm *vm_create_with_vcpus(uint32_t nr_vcpus,
 						  void *guest_code,
 						  struct kvm_vcpu *vcpus[])
 {
-	return __vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, 0,
+	return __vm_create_with_vcpus(VM_SHAPE_DEFAULT, nr_vcpus, 0,
 				      guest_code, vcpus);
 }
 
+
+struct kvm_vm *__vm_create_shape_with_one_vcpu(struct vm_shape shape,
+					       struct kvm_vcpu **vcpu,
+					       uint64_t extra_mem_pages,
+					       void *guest_code);
+
 /*
  * Create a VM with a single vCPU with reasonable defaults and @extra_mem_pages
  * additional pages of guest memory.  Returns the VM and vCPU (via out param).
  */
-struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
-					 uint64_t extra_mem_pages,
-					 void *guest_code);
+static inline struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
+						       uint64_t extra_mem_pages,
+						       void *guest_code)
+{
+	return __vm_create_shape_with_one_vcpu(VM_SHAPE_DEFAULT, vcpu,
+					       extra_mem_pages, guest_code);
+}
 
 static inline struct kvm_vm *vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
 						     void *guest_code)
@@ -753,6 +899,13 @@ static inline struct kvm_vm *vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
 	return __vm_create_with_one_vcpu(vcpu, 0, guest_code);
 }
 
+static inline struct kvm_vm *vm_create_shape_with_one_vcpu(struct vm_shape shape,
+							   struct kvm_vcpu **vcpu,
+							   void *guest_code)
+{
+	return __vm_create_shape_with_one_vcpu(shape, vcpu, 0, guest_code);
+}
+
 struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm);
 
 void kvm_pin_this_task_to_pcpu(uint32_t pcpu);
@@ -776,10 +929,6 @@ vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages)
 	return n;
 }
 
-struct kvm_userspace_memory_region *
-kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
-				 uint64_t end);
-
 #define sync_global_to_guest(vm, g) ({				\
 	typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g));	\
 	memcpy(_p, &(g), sizeof(g));				\
diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h
index 5b62a3d2aa9b..a0f9efe5a2a8 100644
--- a/tools/testing/selftests/kvm/include/riscv/processor.h
+++ b/tools/testing/selftests/kvm/include/riscv/processor.h
@@ -10,10 +10,10 @@
 #include "kvm_util.h"
 #include <linux/stringify.h>
 
-static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t idx,
-				    uint64_t  size)
+static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t subtype,
+				    uint64_t idx, uint64_t size)
 {
-	return KVM_REG_RISCV | type | idx | size;
+	return KVM_REG_RISCV | type | subtype | idx | size;
 }
 
 #if __riscv_xlen == 64
@@ -22,24 +22,30 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t idx,
 #define KVM_REG_SIZE_ULONG	KVM_REG_SIZE_U32
 #endif
 
-#define RISCV_CONFIG_REG(name)	__kvm_reg_id(KVM_REG_RISCV_CONFIG, \
-					     KVM_REG_RISCV_CONFIG_REG(name), \
-					     KVM_REG_SIZE_ULONG)
+#define RISCV_CONFIG_REG(name)		__kvm_reg_id(KVM_REG_RISCV_CONFIG, 0,		\
+						     KVM_REG_RISCV_CONFIG_REG(name),	\
+						     KVM_REG_SIZE_ULONG)
 
-#define RISCV_CORE_REG(name)	__kvm_reg_id(KVM_REG_RISCV_CORE, \
-					     KVM_REG_RISCV_CORE_REG(name), \
-					     KVM_REG_SIZE_ULONG)
+#define RISCV_CORE_REG(name)		__kvm_reg_id(KVM_REG_RISCV_CORE, 0,		\
+						     KVM_REG_RISCV_CORE_REG(name),	\
+						     KVM_REG_SIZE_ULONG)
 
-#define RISCV_CSR_REG(name)	__kvm_reg_id(KVM_REG_RISCV_CSR, \
-					     KVM_REG_RISCV_CSR_REG(name), \
-					     KVM_REG_SIZE_ULONG)
+#define RISCV_GENERAL_CSR_REG(name)	__kvm_reg_id(KVM_REG_RISCV_CSR,			\
+						     KVM_REG_RISCV_CSR_GENERAL,		\
+						     KVM_REG_RISCV_CSR_REG(name),	\
+						     KVM_REG_SIZE_ULONG)
 
-#define RISCV_TIMER_REG(name)	__kvm_reg_id(KVM_REG_RISCV_TIMER, \
-					     KVM_REG_RISCV_TIMER_REG(name), \
-					     KVM_REG_SIZE_U64)
+#define RISCV_TIMER_REG(name)		__kvm_reg_id(KVM_REG_RISCV_TIMER, 0,		\
+						     KVM_REG_RISCV_TIMER_REG(name),	\
+						     KVM_REG_SIZE_U64)
 
-#define RISCV_ISA_EXT_REG(idx)	__kvm_reg_id(KVM_REG_RISCV_ISA_EXT, \
-					     idx, KVM_REG_SIZE_ULONG)
+#define RISCV_ISA_EXT_REG(idx)		__kvm_reg_id(KVM_REG_RISCV_ISA_EXT,		\
+						     KVM_REG_RISCV_ISA_SINGLE,		\
+						     idx, KVM_REG_SIZE_ULONG)
+
+#define RISCV_SBI_EXT_REG(idx)		__kvm_reg_id(KVM_REG_RISCV_SBI_EXT,		\
+						     KVM_REG_RISCV_SBI_SINGLE,		\
+						     idx, KVM_REG_SIZE_ULONG)
 
 /* L3 index Bit[47:39] */
 #define PGTBL_L3_INDEX_MASK			0x0000FF8000000000ULL
@@ -102,6 +108,17 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t idx,
 #define SATP_ASID_SHIFT				44
 #define SATP_ASID_MASK				_AC(0xFFFF, UL)
 
+/* SBI return error codes */
+#define SBI_SUCCESS				0
+#define SBI_ERR_FAILURE				-1
+#define SBI_ERR_NOT_SUPPORTED			-2
+#define SBI_ERR_INVALID_PARAM			-3
+#define SBI_ERR_DENIED				-4
+#define SBI_ERR_INVALID_ADDRESS			-5
+#define SBI_ERR_ALREADY_AVAILABLE		-6
+#define SBI_ERR_ALREADY_STARTED			-7
+#define SBI_ERR_ALREADY_STOPPED			-8
+
 #define SBI_EXT_EXPERIMENTAL_START		0x08000000
 #define SBI_EXT_EXPERIMENTAL_END		0x08FFFFFF
 
@@ -109,6 +126,15 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t idx,
 #define KVM_RISCV_SELFTESTS_SBI_UCALL		0
 #define KVM_RISCV_SELFTESTS_SBI_UNEXP		1
 
+enum sbi_ext_id {
+	SBI_EXT_BASE = 0x10,
+	SBI_EXT_STA = 0x535441,
+};
+
+enum sbi_ext_base_fid {
+	SBI_EXT_BASE_PROBE_EXT = 3,
+};
+
 struct sbiret {
 	long error;
 	long value;
@@ -119,4 +145,6 @@ struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
 			unsigned long arg3, unsigned long arg4,
 			unsigned long arg5);
 
+bool guest_sbi_probe_extension(int extid, long *out_val);
+
 #endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index 8e5f413a593d..50a5e31ba8da 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -142,6 +142,11 @@ static inline bool backing_src_is_shared(enum vm_mem_backing_src_type t)
 	return vm_mem_backing_src_alias(t)->flag & MAP_SHARED;
 }
 
+static inline bool backing_src_can_be_huge(enum vm_mem_backing_src_type t)
+{
+	return t != VM_MEM_SRC_ANONYMOUS && t != VM_MEM_SRC_SHMEM;
+}
+
 /* Aligns x up to the next multiple of size. Size must be a power of 2. */
 static inline uint64_t align_up(uint64_t x, uint64_t size)
 {
@@ -186,8 +191,10 @@ static inline uint32_t atoi_non_negative(const char *name, const char *num_str)
 }
 
 int guest_vsnprintf(char *buf, int n, const char *fmt, va_list args);
-int guest_snprintf(char *buf, int n, const char *fmt, ...);
+__printf(3, 4) int guest_snprintf(char *buf, int n, const char *fmt, ...);
 
 char *strdup_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2), nonnull(1)));
 
+char *sys_get_cur_clocksource(void);
+
 #endif /* SELFTEST_KVM_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h
index ce33d306c2cb..d9d6581b8d4f 100644
--- a/tools/testing/selftests/kvm/include/ucall_common.h
+++ b/tools/testing/selftests/kvm/include/ucall_common.h
@@ -34,9 +34,10 @@ void ucall_arch_do_ucall(vm_vaddr_t uc);
 void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu);
 
 void ucall(uint64_t cmd, int nargs, ...);
-void ucall_fmt(uint64_t cmd, const char *fmt, ...);
-void ucall_assert(uint64_t cmd, const char *exp, const char *file,
-		  unsigned int line, const char *fmt, ...);
+__printf(2, 3) void ucall_fmt(uint64_t cmd, const char *fmt, ...);
+__printf(5, 6) void ucall_assert(uint64_t cmd, const char *exp,
+				 const char *file, unsigned int line,
+				 const char *fmt, ...);
 uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc);
 void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa);
 int ucall_nr_pages_required(uint64_t page_size);
@@ -52,6 +53,17 @@ int ucall_nr_pages_required(uint64_t page_size);
 #define GUEST_SYNC_ARGS(stage, arg1, arg2, arg3, arg4)	\
 				ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4)
 #define GUEST_SYNC(stage)	ucall(UCALL_SYNC, 2, "hello", stage)
+#define GUEST_SYNC1(arg0)	ucall(UCALL_SYNC, 1, arg0)
+#define GUEST_SYNC2(arg0, arg1)	ucall(UCALL_SYNC, 2, arg0, arg1)
+#define GUEST_SYNC3(arg0, arg1, arg2) \
+				ucall(UCALL_SYNC, 3, arg0, arg1, arg2)
+#define GUEST_SYNC4(arg0, arg1, arg2, arg3) \
+				ucall(UCALL_SYNC, 4, arg0, arg1, arg2, arg3)
+#define GUEST_SYNC5(arg0, arg1, arg2, arg3, arg4) \
+				ucall(UCALL_SYNC, 5, arg0, arg1, arg2, arg3, arg4)
+#define GUEST_SYNC6(arg0, arg1, arg2, arg3, arg4, arg5) \
+				ucall(UCALL_SYNC, 6, arg0, arg1, arg2, arg3, arg4, arg5)
+
 #define GUEST_PRINTF(_fmt, _args...) ucall_fmt(UCALL_PRINTF, _fmt, ##_args)
 #define GUEST_DONE()		ucall(UCALL_DONE, 0)
 
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 25bc61dac5fb..5bca8c947c82 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -15,6 +15,7 @@
 #include <asm/msr-index.h>
 #include <asm/prctl.h>
 
+#include <linux/kvm_para.h>
 #include <linux/stringify.h>
 
 #include "../kvm_util.h"
@@ -1194,6 +1195,20 @@ uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
 uint64_t __xen_hypercall(uint64_t nr, uint64_t a0, void *a1);
 void xen_hypercall(uint64_t nr, uint64_t a0, void *a1);
 
+static inline uint64_t __kvm_hypercall_map_gpa_range(uint64_t gpa,
+						     uint64_t size, uint64_t flags)
+{
+	return kvm_hypercall(KVM_HC_MAP_GPA_RANGE, gpa, size >> PAGE_SHIFT, flags, 0);
+}
+
+static inline void kvm_hypercall_map_gpa_range(uint64_t gpa, uint64_t size,
+					       uint64_t flags)
+{
+	uint64_t ret = __kvm_hypercall_map_gpa_range(gpa, size, flags);
+
+	GUEST_ASSERT(!ret);
+}
+
 void __vm_xsave_require_permission(uint64_t xfeature, const char *name);
 
 #define vm_xsave_require_permission(xfeature)	\
@@ -1256,4 +1271,6 @@ void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 #define PFERR_GUEST_PAGE_MASK	BIT_ULL(PFERR_GUEST_PAGE_BIT)
 #define PFERR_IMPLICIT_ACCESS	BIT_ULL(PFERR_IMPLICIT_ACCESS_BIT)
 
+bool sys_clocksource_is_based_on_tsc(void);
+
 #endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
index 31b3cb24b9a7..b9e23265e4b3 100644
--- a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
+++ b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
@@ -65,7 +65,7 @@ int main(int argc, char *argv[])
 
 			int r = setrlimit(RLIMIT_NOFILE, &rl);
 			__TEST_REQUIRE(r >= 0,
-				       "RLIMIT_NOFILE hard limit is too low (%d, wanted %d)\n",
+				       "RLIMIT_NOFILE hard limit is too low (%d, wanted %d)",
 				       old_rlim_max, nr_fds_wanted);
 		} else {
 			TEST_ASSERT(!setrlimit(RLIMIT_NOFILE, &rl), "setrlimit() failed!");
diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c
index 69f26d80c821..e0ba97ac1c56 100644
--- a/tools/testing/selftests/kvm/kvm_page_table_test.c
+++ b/tools/testing/selftests/kvm/kvm_page_table_test.c
@@ -204,9 +204,9 @@ static void *vcpu_worker(void *data)
 		ret = _vcpu_run(vcpu);
 		ts_diff = timespec_elapsed(start);
 
-		TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
+		TEST_ASSERT(ret == 0, "vcpu_run failed: %d", ret);
 		TEST_ASSERT(get_ucall(vcpu, NULL) == UCALL_SYNC,
-			    "Invalid guest sync status: exit_reason=%s\n",
+			    "Invalid guest sync status: exit_reason=%s",
 			    exit_reason_str(vcpu->run->exit_reason));
 
 		pr_debug("Got sync event from vCPU %d\n", vcpu->id);
@@ -254,7 +254,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg)
 
 	/* Create a VM with enough guest pages */
 	guest_num_pages = test_mem_size / guest_page_size;
-	vm = __vm_create_with_vcpus(mode, nr_vcpus, guest_num_pages,
+	vm = __vm_create_with_vcpus(VM_SHAPE(mode), nr_vcpus, guest_num_pages,
 				    guest_code, test_args.vcpus);
 
 	/* Align down GPA of the testing memslot */
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 6fe12e985ba5..43b9a7283360 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -12,6 +12,7 @@
 #include "kvm_util.h"
 #include "processor.h"
 #include <linux/bitfield.h>
+#include <linux/sizes.h>
 
 #define DEFAULT_ARM64_GUEST_STACK_VADDR_MIN	0xac0000
 
@@ -58,13 +59,25 @@ static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva)
 	return (gva >> vm->page_shift) & mask;
 }
 
+static inline bool use_lpa2_pte_format(struct kvm_vm *vm)
+{
+	return (vm->page_size == SZ_4K || vm->page_size == SZ_16K) &&
+	    (vm->pa_bits > 48 || vm->va_bits > 48);
+}
+
 static uint64_t addr_pte(struct kvm_vm *vm, uint64_t pa, uint64_t attrs)
 {
 	uint64_t pte;
 
-	pte = pa & GENMASK(47, vm->page_shift);
-	if (vm->page_shift == 16)
-		pte |= FIELD_GET(GENMASK(51, 48), pa) << 12;
+	if (use_lpa2_pte_format(vm)) {
+		pte = pa & GENMASK(49, vm->page_shift);
+		pte |= FIELD_GET(GENMASK(51, 50), pa) << 8;
+		attrs &= ~GENMASK(9, 8);
+	} else {
+		pte = pa & GENMASK(47, vm->page_shift);
+		if (vm->page_shift == 16)
+			pte |= FIELD_GET(GENMASK(51, 48), pa) << 12;
+	}
 	pte |= attrs;
 
 	return pte;
@@ -74,9 +87,14 @@ static uint64_t pte_addr(struct kvm_vm *vm, uint64_t pte)
 {
 	uint64_t pa;
 
-	pa = pte & GENMASK(47, vm->page_shift);
-	if (vm->page_shift == 16)
-		pa |= FIELD_GET(GENMASK(15, 12), pte) << 48;
+	if (use_lpa2_pte_format(vm)) {
+		pa = pte & GENMASK(49, vm->page_shift);
+		pa |= FIELD_GET(GENMASK(9, 8), pte) << 50;
+	} else {
+		pa = pte & GENMASK(47, vm->page_shift);
+		if (vm->page_shift == 16)
+			pa |= FIELD_GET(GENMASK(15, 12), pte) << 48;
+	}
 
 	return pa;
 }
@@ -266,9 +284,6 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
 
 	/* Configure base granule size */
 	switch (vm->mode) {
-	case VM_MODE_P52V48_4K:
-		TEST_FAIL("AArch64 does not support 4K sized pages "
-			  "with 52-bit physical address ranges");
 	case VM_MODE_PXXV48_4K:
 		TEST_FAIL("AArch64 does not support 4K sized pages "
 			  "with ANY-bit physical address ranges");
@@ -278,12 +293,14 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
 	case VM_MODE_P36V48_64K:
 		tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
 		break;
+	case VM_MODE_P52V48_16K:
 	case VM_MODE_P48V48_16K:
 	case VM_MODE_P40V48_16K:
 	case VM_MODE_P36V48_16K:
 	case VM_MODE_P36V47_16K:
 		tcr_el1 |= 2ul << 14; /* TG0 = 16KB */
 		break;
+	case VM_MODE_P52V48_4K:
 	case VM_MODE_P48V48_4K:
 	case VM_MODE_P40V48_4K:
 	case VM_MODE_P36V48_4K:
@@ -297,6 +314,8 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
 
 	/* Configure output size */
 	switch (vm->mode) {
+	case VM_MODE_P52V48_4K:
+	case VM_MODE_P52V48_16K:
 	case VM_MODE_P52V48_64K:
 		tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
 		ttbr0_el1 |= FIELD_GET(GENMASK(51, 48), vm->pgd) << 2;
@@ -325,6 +344,8 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
 	/* TCR_EL1 |= IRGN0:WBWA | ORGN0:WBWA | SH0:Inner-Shareable */;
 	tcr_el1 |= (1 << 8) | (1 << 10) | (3 << 12);
 	tcr_el1 |= (64 - vm->va_bits) /* T0SZ */;
+	if (use_lpa2_pte_format(vm))
+		tcr_el1 |= (1ul << 59) /* DS */;
 
 	vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), sctlr_el1);
 	vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1), tcr_el1);
@@ -377,7 +398,7 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)
 	int i;
 
 	TEST_ASSERT(num >= 1 && num <= 8, "Unsupported number of args,\n"
-		    "  num: %u\n", num);
+		    "  num: %u", num);
 
 	va_start(ap, num);
 
@@ -492,12 +513,24 @@ uint32_t guest_get_vcpuid(void)
 	return read_sysreg(tpidr_el1);
 }
 
-void aarch64_get_supported_page_sizes(uint32_t ipa,
-				      bool *ps4k, bool *ps16k, bool *ps64k)
+static uint32_t max_ipa_for_page_size(uint32_t vm_ipa, uint32_t gran,
+				uint32_t not_sup_val, uint32_t ipa52_min_val)
+{
+	if (gran == not_sup_val)
+		return 0;
+	else if (gran >= ipa52_min_val && vm_ipa >= 52)
+		return 52;
+	else
+		return min(vm_ipa, 48U);
+}
+
+void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k,
+					uint32_t *ipa16k, uint32_t *ipa64k)
 {
 	struct kvm_vcpu_init preferred_init;
 	int kvm_fd, vm_fd, vcpu_fd, err;
 	uint64_t val;
+	uint32_t gran;
 	struct kvm_one_reg reg = {
 		.id	= KVM_ARM64_SYS_REG(SYS_ID_AA64MMFR0_EL1),
 		.addr	= (uint64_t)&val,
@@ -518,9 +551,17 @@ void aarch64_get_supported_page_sizes(uint32_t ipa,
 	err = ioctl(vcpu_fd, KVM_GET_ONE_REG, &reg);
 	TEST_ASSERT(err == 0, KVM_IOCTL_ERROR(KVM_GET_ONE_REG, vcpu_fd));
 
-	*ps4k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN4), val) != 0xf;
-	*ps64k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN64), val) == 0;
-	*ps16k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN16), val) != 0;
+	gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN4), val);
+	*ipa4k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN4_NI,
+					ID_AA64MMFR0_EL1_TGRAN4_52_BIT);
+
+	gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN64), val);
+	*ipa64k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN64_NI,
+					ID_AA64MMFR0_EL1_TGRAN64_IMP);
+
+	gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN16), val);
+	*ipa16k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN16_NI,
+					ID_AA64MMFR0_EL1_TGRAN16_52_BIT);
 
 	close(vcpu_fd);
 	close(vm_fd);
diff --git a/tools/testing/selftests/kvm/lib/aarch64/vgic.c b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
index b5f28d21a947..184378d593e9 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/vgic.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
@@ -38,7 +38,7 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs,
 	struct list_head *iter;
 	unsigned int nr_gic_pages, nr_vcpus_created = 0;
 
-	TEST_ASSERT(nr_vcpus, "Number of vCPUs cannot be empty\n");
+	TEST_ASSERT(nr_vcpus, "Number of vCPUs cannot be empty");
 
 	/*
 	 * Make sure that the caller is infact calling this
@@ -47,7 +47,7 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs,
 	list_for_each(iter, &vm->vcpus)
 		nr_vcpus_created++;
 	TEST_ASSERT(nr_vcpus == nr_vcpus_created,
-			"Number of vCPUs requested (%u) doesn't match with the ones created for the VM (%u)\n",
+			"Number of vCPUs requested (%u) doesn't match with the ones created for the VM (%u)",
 			nr_vcpus, nr_vcpus_created);
 
 	/* Distributor setup */
diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c
index 266f3876e10a..f34d926d9735 100644
--- a/tools/testing/selftests/kvm/lib/elf.c
+++ b/tools/testing/selftests/kvm/lib/elf.c
@@ -184,7 +184,7 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename)
 				"Seek to program segment offset failed,\n"
 				"  program header idx: %u errno: %i\n"
 				"  offset_rv: 0x%jx\n"
-				"  expected: 0x%jx\n",
+				"  expected: 0x%jx",
 				n1, errno, (intmax_t) offset_rv,
 				(intmax_t) phdr.p_offset);
 			test_read(fd, addr_gva2hva(vm, phdr.p_vaddr),
diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c
index 1df3ce4b16fd..b04901e55138 100644
--- a/tools/testing/selftests/kvm/lib/guest_modes.c
+++ b/tools/testing/selftests/kvm/lib/guest_modes.c
@@ -14,37 +14,33 @@ struct guest_mode guest_modes[NUM_VM_MODES];
 void guest_modes_append_default(void)
 {
 #ifndef __aarch64__
-	guest_mode_append(VM_MODE_DEFAULT, true, true);
+	guest_mode_append(VM_MODE_DEFAULT, true);
 #else
 	{
 		unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
-		bool ps4k, ps16k, ps64k;
+		uint32_t ipa4k, ipa16k, ipa64k;
 		int i;
 
-		aarch64_get_supported_page_sizes(limit, &ps4k, &ps16k, &ps64k);
+		aarch64_get_supported_page_sizes(limit, &ipa4k, &ipa16k, &ipa64k);
 
-		vm_mode_default = NUM_VM_MODES;
+		guest_mode_append(VM_MODE_P52V48_4K, ipa4k >= 52);
+		guest_mode_append(VM_MODE_P52V48_16K, ipa16k >= 52);
+		guest_mode_append(VM_MODE_P52V48_64K, ipa64k >= 52);
 
-		if (limit >= 52)
-			guest_mode_append(VM_MODE_P52V48_64K, ps64k, ps64k);
-		if (limit >= 48) {
-			guest_mode_append(VM_MODE_P48V48_4K, ps4k, ps4k);
-			guest_mode_append(VM_MODE_P48V48_16K, ps16k, ps16k);
-			guest_mode_append(VM_MODE_P48V48_64K, ps64k, ps64k);
-		}
-		if (limit >= 40) {
-			guest_mode_append(VM_MODE_P40V48_4K, ps4k, ps4k);
-			guest_mode_append(VM_MODE_P40V48_16K, ps16k, ps16k);
-			guest_mode_append(VM_MODE_P40V48_64K, ps64k, ps64k);
-			if (ps4k)
-				vm_mode_default = VM_MODE_P40V48_4K;
-		}
-		if (limit >= 36) {
-			guest_mode_append(VM_MODE_P36V48_4K, ps4k, ps4k);
-			guest_mode_append(VM_MODE_P36V48_16K, ps16k, ps16k);
-			guest_mode_append(VM_MODE_P36V48_64K, ps64k, ps64k);
-			guest_mode_append(VM_MODE_P36V47_16K, ps16k, ps16k);
-		}
+		guest_mode_append(VM_MODE_P48V48_4K, ipa4k >= 48);
+		guest_mode_append(VM_MODE_P48V48_16K, ipa16k >= 48);
+		guest_mode_append(VM_MODE_P48V48_64K, ipa64k >= 48);
+
+		guest_mode_append(VM_MODE_P40V48_4K, ipa4k >= 40);
+		guest_mode_append(VM_MODE_P40V48_16K, ipa16k >= 40);
+		guest_mode_append(VM_MODE_P40V48_64K, ipa64k >= 40);
+
+		guest_mode_append(VM_MODE_P36V48_4K, ipa4k >= 36);
+		guest_mode_append(VM_MODE_P36V48_16K, ipa16k >= 36);
+		guest_mode_append(VM_MODE_P36V48_64K, ipa64k >= 36);
+		guest_mode_append(VM_MODE_P36V47_16K, ipa16k >= 36);
+
+		vm_mode_default = ipa4k >= 40 ? VM_MODE_P40V48_4K : NUM_VM_MODES;
 
 		/*
 		 * Pick the first supported IPA size if the default
@@ -72,7 +68,7 @@ void guest_modes_append_default(void)
 		close(kvm_fd);
 		/* Starting with z13 we have 47bits of physical address */
 		if (info.ibc >= 0x30)
-			guest_mode_append(VM_MODE_P47V64_4K, true, true);
+			guest_mode_append(VM_MODE_P47V64_4K, true);
 	}
 #endif
 #ifdef __riscv
@@ -80,9 +76,9 @@ void guest_modes_append_default(void)
 		unsigned int sz = kvm_check_cap(KVM_CAP_VM_GPA_BITS);
 
 		if (sz >= 52)
-			guest_mode_append(VM_MODE_P52V48_4K, true, true);
+			guest_mode_append(VM_MODE_P52V48_4K, true);
 		if (sz >= 48)
-			guest_mode_append(VM_MODE_P48V48_4K, true, true);
+			guest_mode_append(VM_MODE_P48V48_4K, true);
 	}
 #endif
 }
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 7a8af1821f5d..1b197426f29f 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -27,7 +27,8 @@ int open_path_or_exit(const char *path, int flags)
 	int fd;
 
 	fd = open(path, flags);
-	__TEST_REQUIRE(fd >= 0, "%s not available (errno: %d)", path, errno);
+	__TEST_REQUIRE(fd >= 0 || errno != ENOENT, "Cannot open %s: %s", path, strerror(errno));
+	TEST_ASSERT(fd >= 0, "Failed to open '%s'", path);
 
 	return fd;
 }
@@ -148,6 +149,7 @@ const char *vm_guest_mode_string(uint32_t i)
 {
 	static const char * const strings[] = {
 		[VM_MODE_P52V48_4K]	= "PA-bits:52,  VA-bits:48,  4K pages",
+		[VM_MODE_P52V48_16K]	= "PA-bits:52,  VA-bits:48, 16K pages",
 		[VM_MODE_P52V48_64K]	= "PA-bits:52,  VA-bits:48, 64K pages",
 		[VM_MODE_P48V48_4K]	= "PA-bits:48,  VA-bits:48,  4K pages",
 		[VM_MODE_P48V48_16K]	= "PA-bits:48,  VA-bits:48, 16K pages",
@@ -173,6 +175,7 @@ const char *vm_guest_mode_string(uint32_t i)
 
 const struct vm_guest_mode_params vm_guest_mode_params[] = {
 	[VM_MODE_P52V48_4K]	= { 52, 48,  0x1000, 12 },
+	[VM_MODE_P52V48_16K]	= { 52, 48,  0x4000, 14 },
 	[VM_MODE_P52V48_64K]	= { 52, 48, 0x10000, 16 },
 	[VM_MODE_P48V48_4K]	= { 48, 48,  0x1000, 12 },
 	[VM_MODE_P48V48_16K]	= { 48, 48,  0x4000, 14 },
@@ -209,7 +212,7 @@ __weak void vm_vaddr_populate_bitmap(struct kvm_vm *vm)
 		(1ULL << (vm->va_bits - 1)) >> vm->page_shift);
 }
 
-struct kvm_vm *____vm_create(enum vm_guest_mode mode)
+struct kvm_vm *____vm_create(struct vm_shape shape)
 {
 	struct kvm_vm *vm;
 
@@ -221,13 +224,13 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode)
 	vm->regions.hva_tree = RB_ROOT;
 	hash_init(vm->regions.slot_hash);
 
-	vm->mode = mode;
-	vm->type = 0;
+	vm->mode = shape.mode;
+	vm->type = shape.type;
 
-	vm->pa_bits = vm_guest_mode_params[mode].pa_bits;
-	vm->va_bits = vm_guest_mode_params[mode].va_bits;
-	vm->page_size = vm_guest_mode_params[mode].page_size;
-	vm->page_shift = vm_guest_mode_params[mode].page_shift;
+	vm->pa_bits = vm_guest_mode_params[vm->mode].pa_bits;
+	vm->va_bits = vm_guest_mode_params[vm->mode].va_bits;
+	vm->page_size = vm_guest_mode_params[vm->mode].page_size;
+	vm->page_shift = vm_guest_mode_params[vm->mode].page_shift;
 
 	/* Setup mode specific traits. */
 	switch (vm->mode) {
@@ -251,6 +254,7 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode)
 	case VM_MODE_P36V48_64K:
 		vm->pgtable_levels = 3;
 		break;
+	case VM_MODE_P52V48_16K:
 	case VM_MODE_P48V48_16K:
 	case VM_MODE_P40V48_16K:
 	case VM_MODE_P36V48_16K:
@@ -265,7 +269,7 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode)
 		/*
 		 * Ignore KVM support for 5-level paging (vm->va_bits == 57),
 		 * it doesn't take effect unless a CR4.LA57 is set, which it
-		 * isn't for this VM_MODE.
+		 * isn't for this mode (48-bit virtual address space).
 		 */
 		TEST_ASSERT(vm->va_bits == 48 || vm->va_bits == 57,
 			    "Linear address width (%d bits) not supported",
@@ -285,10 +289,11 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode)
 		vm->pgtable_levels = 5;
 		break;
 	default:
-		TEST_FAIL("Unknown guest mode, mode: 0x%x", mode);
+		TEST_FAIL("Unknown guest mode: 0x%x", vm->mode);
 	}
 
 #ifdef __aarch64__
+	TEST_ASSERT(!vm->type, "ARM doesn't support test-provided types");
 	if (vm->pa_bits != 40)
 		vm->type = KVM_VM_TYPE_ARM_IPA_SIZE(vm->pa_bits);
 #endif
@@ -316,7 +321,7 @@ static uint64_t vm_nr_pages_required(enum vm_guest_mode mode,
 	uint64_t nr_pages;
 
 	TEST_ASSERT(nr_runnable_vcpus,
-		    "Use vm_create_barebones() for VMs that _never_ have vCPUs\n");
+		    "Use vm_create_barebones() for VMs that _never_ have vCPUs");
 
 	TEST_ASSERT(nr_runnable_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS),
 		    "nr_vcpus = %d too large for host, max-vcpus = %d",
@@ -347,19 +352,19 @@ static uint64_t vm_nr_pages_required(enum vm_guest_mode mode,
 	return vm_adjust_num_guest_pages(mode, nr_pages);
 }
 
-struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus,
+struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus,
 			   uint64_t nr_extra_pages)
 {
-	uint64_t nr_pages = vm_nr_pages_required(mode, nr_runnable_vcpus,
+	uint64_t nr_pages = vm_nr_pages_required(shape.mode, nr_runnable_vcpus,
 						 nr_extra_pages);
 	struct userspace_mem_region *slot0;
 	struct kvm_vm *vm;
 	int i;
 
-	pr_debug("%s: mode='%s' pages='%ld'\n", __func__,
-		 vm_guest_mode_string(mode), nr_pages);
+	pr_debug("%s: mode='%s' type='%d', pages='%ld'\n", __func__,
+		 vm_guest_mode_string(shape.mode), shape.type, nr_pages);
 
-	vm = ____vm_create(mode);
+	vm = ____vm_create(shape);
 
 	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, 0, 0, nr_pages, 0);
 	for (i = 0; i < NR_MEM_REGIONS; i++)
@@ -400,7 +405,7 @@ struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus,
  * extra_mem_pages is only used to calculate the maximum page table size,
  * no real memory allocation for non-slot0 memory in this function.
  */
-struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
+struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, uint32_t nr_vcpus,
 				      uint64_t extra_mem_pages,
 				      void *guest_code, struct kvm_vcpu *vcpus[])
 {
@@ -409,7 +414,7 @@ struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus
 
 	TEST_ASSERT(!nr_vcpus || vcpus, "Must provide vCPU array");
 
-	vm = __vm_create(mode, nr_vcpus, extra_mem_pages);
+	vm = __vm_create(shape, nr_vcpus, extra_mem_pages);
 
 	for (i = 0; i < nr_vcpus; ++i)
 		vcpus[i] = vm_vcpu_add(vm, i, guest_code);
@@ -417,15 +422,15 @@ struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus
 	return vm;
 }
 
-struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
-					 uint64_t extra_mem_pages,
-					 void *guest_code)
+struct kvm_vm *__vm_create_shape_with_one_vcpu(struct vm_shape shape,
+					       struct kvm_vcpu **vcpu,
+					       uint64_t extra_mem_pages,
+					       void *guest_code)
 {
 	struct kvm_vcpu *vcpus[1];
 	struct kvm_vm *vm;
 
-	vm = __vm_create_with_vcpus(VM_MODE_DEFAULT, 1, extra_mem_pages,
-				    guest_code, vcpus);
+	vm = __vm_create_with_vcpus(shape, 1, extra_mem_pages, guest_code, vcpus);
 
 	*vcpu = vcpus[0];
 	return vm;
@@ -453,8 +458,9 @@ void kvm_vm_restart(struct kvm_vm *vmp)
 		vm_create_irqchip(vmp);
 
 	hash_for_each(vmp->regions.slot_hash, ctr, region, slot_node) {
-		int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION, &region->region);
-		TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
+		int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION2, &region->region);
+
+		TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION2 IOCTL failed,\n"
 			    "  rc: %i errno: %i\n"
 			    "  slot: %u flags: 0x%x\n"
 			    "  guest_phys_addr: 0x%llx size: 0x%llx",
@@ -486,7 +492,7 @@ void kvm_pin_this_task_to_pcpu(uint32_t pcpu)
 	CPU_ZERO(&mask);
 	CPU_SET(pcpu, &mask);
 	r = sched_setaffinity(0, sizeof(mask), &mask);
-	TEST_ASSERT(!r, "sched_setaffinity() failed for pCPU '%u'.\n", pcpu);
+	TEST_ASSERT(!r, "sched_setaffinity() failed for pCPU '%u'.", pcpu);
 }
 
 static uint32_t parse_pcpu(const char *cpu_str, const cpu_set_t *allowed_mask)
@@ -494,7 +500,7 @@ static uint32_t parse_pcpu(const char *cpu_str, const cpu_set_t *allowed_mask)
 	uint32_t pcpu = atoi_non_negative("CPU number", cpu_str);
 
 	TEST_ASSERT(CPU_ISSET(pcpu, allowed_mask),
-		    "Not allowed to run on pCPU '%d', check cgroups?\n", pcpu);
+		    "Not allowed to run on pCPU '%d', check cgroups?", pcpu);
 	return pcpu;
 }
 
@@ -524,7 +530,7 @@ void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[],
 	int i, r;
 
 	cpu_list = strdup(pcpus_string);
-	TEST_ASSERT(cpu_list, "strdup() allocation failed.\n");
+	TEST_ASSERT(cpu_list, "strdup() allocation failed.");
 
 	r = sched_getaffinity(0, sizeof(allowed_mask), &allowed_mask);
 	TEST_ASSERT(!r, "sched_getaffinity() failed");
@@ -533,7 +539,7 @@ void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[],
 
 	/* 1. Get all pcpus for vcpus. */
 	for (i = 0; i < nr_vcpus; i++) {
-		TEST_ASSERT(cpu, "pCPU not provided for vCPU '%d'\n", i);
+		TEST_ASSERT(cpu, "pCPU not provided for vCPU '%d'", i);
 		vcpu_to_pcpu[i] = parse_pcpu(cpu, &allowed_mask);
 		cpu = strtok(NULL, delim);
 	}
@@ -590,35 +596,6 @@ userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end)
 	return NULL;
 }
 
-/*
- * KVM Userspace Memory Region Find
- *
- * Input Args:
- *   vm - Virtual Machine
- *   start - Starting VM physical address
- *   end - Ending VM physical address, inclusive.
- *
- * Output Args: None
- *
- * Return:
- *   Pointer to overlapping region, NULL if no such region.
- *
- * Public interface to userspace_mem_region_find. Allows tests to look up
- * the memslot datastructure for a given range of guest physical memory.
- */
-struct kvm_userspace_memory_region *
-kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
-				 uint64_t end)
-{
-	struct userspace_mem_region *region;
-
-	region = userspace_mem_region_find(vm, start, end);
-	if (!region)
-		return NULL;
-
-	return &region->region;
-}
-
 __weak void vcpu_arch_free(struct kvm_vcpu *vcpu)
 {
 
@@ -686,7 +663,7 @@ static void __vm_mem_region_delete(struct kvm_vm *vm,
 	}
 
 	region->region.memory_size = 0;
-	vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, &region->region);
+	vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->region);
 
 	sparsebit_free(&region->unused_phy_pages);
 	ret = munmap(region->mmap_start, region->mmap_size);
@@ -697,6 +674,8 @@ static void __vm_mem_region_delete(struct kvm_vm *vm,
 		TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret));
 		close(region->fd);
 	}
+	if (region->region.guest_memfd >= 0)
+		close(region->region.guest_memfd);
 
 	free(region);
 }
@@ -898,36 +877,44 @@ void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
 		    errno, strerror(errno));
 }
 
-/*
- * VM Userspace Memory Region Add
- *
- * Input Args:
- *   vm - Virtual Machine
- *   src_type - Storage source for this region.
- *              NULL to use anonymous memory.
- *   guest_paddr - Starting guest physical address
- *   slot - KVM region slot
- *   npages - Number of physical pages
- *   flags - KVM memory region flags (e.g. KVM_MEM_LOG_DIRTY_PAGES)
- *
- * Output Args: None
- *
- * Return: None
- *
- * Allocates a memory area of the number of pages specified by npages
- * and maps it to the VM specified by vm, at a starting physical address
- * given by guest_paddr.  The region is created with a KVM region slot
- * given by slot, which must be unique and < KVM_MEM_SLOTS_NUM.  The
- * region is created with the flags given by flags.
- */
-void vm_userspace_mem_region_add(struct kvm_vm *vm,
-	enum vm_mem_backing_src_type src_type,
-	uint64_t guest_paddr, uint32_t slot, uint64_t npages,
-	uint32_t flags)
+int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
+				 uint64_t gpa, uint64_t size, void *hva,
+				 uint32_t guest_memfd, uint64_t guest_memfd_offset)
+{
+	struct kvm_userspace_memory_region2 region = {
+		.slot = slot,
+		.flags = flags,
+		.guest_phys_addr = gpa,
+		.memory_size = size,
+		.userspace_addr = (uintptr_t)hva,
+		.guest_memfd = guest_memfd,
+		.guest_memfd_offset = guest_memfd_offset,
+	};
+
+	return ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION2, &region);
+}
+
+void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
+				uint64_t gpa, uint64_t size, void *hva,
+				uint32_t guest_memfd, uint64_t guest_memfd_offset)
+{
+	int ret = __vm_set_user_memory_region2(vm, slot, flags, gpa, size, hva,
+					       guest_memfd, guest_memfd_offset);
+
+	TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION2 failed, errno = %d (%s)",
+		    errno, strerror(errno));
+}
+
+
+/* FIXME: This thing needs to be ripped apart and rewritten. */
+void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
+		uint64_t guest_paddr, uint32_t slot, uint64_t npages,
+		uint32_t flags, int guest_memfd, uint64_t guest_memfd_offset)
 {
 	int ret;
 	struct userspace_mem_region *region;
 	size_t backing_src_pagesz = get_backing_src_pagesz(src_type);
+	size_t mem_size = npages * vm->page_size;
 	size_t alignment;
 
 	TEST_ASSERT(vm_adjust_num_guest_pages(vm->mode, npages) == npages,
@@ -980,7 +967,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	/* Allocate and initialize new mem region structure. */
 	region = calloc(1, sizeof(*region));
 	TEST_ASSERT(region != NULL, "Insufficient Memory");
-	region->mmap_size = npages * vm->page_size;
+	region->mmap_size = mem_size;
 
 #ifdef __s390x__
 	/* On s390x, the host address must be aligned to 1M (due to PGSTEs) */
@@ -1027,14 +1014,38 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	/* As needed perform madvise */
 	if ((src_type == VM_MEM_SRC_ANONYMOUS ||
 	     src_type == VM_MEM_SRC_ANONYMOUS_THP) && thp_configured()) {
-		ret = madvise(region->host_mem, npages * vm->page_size,
+		ret = madvise(region->host_mem, mem_size,
 			      src_type == VM_MEM_SRC_ANONYMOUS ? MADV_NOHUGEPAGE : MADV_HUGEPAGE);
 		TEST_ASSERT(ret == 0, "madvise failed, addr: %p length: 0x%lx src_type: %s",
-			    region->host_mem, npages * vm->page_size,
+			    region->host_mem, mem_size,
 			    vm_mem_backing_src_alias(src_type)->name);
 	}
 
 	region->backing_src_type = src_type;
+
+	if (flags & KVM_MEM_GUEST_MEMFD) {
+		if (guest_memfd < 0) {
+			uint32_t guest_memfd_flags = 0;
+			TEST_ASSERT(!guest_memfd_offset,
+				    "Offset must be zero when creating new guest_memfd");
+			guest_memfd = vm_create_guest_memfd(vm, mem_size, guest_memfd_flags);
+		} else {
+			/*
+			 * Install a unique fd for each memslot so that the fd
+			 * can be closed when the region is deleted without
+			 * needing to track if the fd is owned by the framework
+			 * or by the caller.
+			 */
+			guest_memfd = dup(guest_memfd);
+			TEST_ASSERT(guest_memfd >= 0, __KVM_SYSCALL_ERROR("dup()", guest_memfd));
+		}
+
+		region->region.guest_memfd = guest_memfd;
+		region->region.guest_memfd_offset = guest_memfd_offset;
+	} else {
+		region->region.guest_memfd = -1;
+	}
+
 	region->unused_phy_pages = sparsebit_alloc();
 	sparsebit_set_num(region->unused_phy_pages,
 		guest_paddr >> vm->page_shift, npages);
@@ -1043,13 +1054,14 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	region->region.guest_phys_addr = guest_paddr;
 	region->region.memory_size = npages * vm->page_size;
 	region->region.userspace_addr = (uintptr_t) region->host_mem;
-	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, &region->region);
-	TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
+	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->region);
+	TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION2 IOCTL failed,\n"
 		"  rc: %i errno: %i\n"
 		"  slot: %u flags: 0x%x\n"
-		"  guest_phys_addr: 0x%lx size: 0x%lx",
+		"  guest_phys_addr: 0x%lx size: 0x%lx guest_memfd: %d",
 		ret, errno, slot, flags,
-		guest_paddr, (uint64_t) region->region.memory_size);
+		guest_paddr, (uint64_t) region->region.memory_size,
+		region->region.guest_memfd);
 
 	/* Add to quick lookup data structures */
 	vm_userspace_mem_region_gpa_insert(&vm->regions.gpa_tree, region);
@@ -1070,6 +1082,14 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	}
 }
 
+void vm_userspace_mem_region_add(struct kvm_vm *vm,
+				 enum vm_mem_backing_src_type src_type,
+				 uint64_t guest_paddr, uint32_t slot,
+				 uint64_t npages, uint32_t flags)
+{
+	vm_mem_add(vm, src_type, guest_paddr, slot, npages, flags, -1, 0);
+}
+
 /*
  * Memslot to region
  *
@@ -1126,9 +1146,9 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags)
 
 	region->region.flags = flags;
 
-	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, &region->region);
+	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->region);
 
-	TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
+	TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION2 IOCTL failed,\n"
 		"  rc: %i errno: %i slot: %u flags: 0x%x",
 		ret, errno, slot, flags);
 }
@@ -1156,9 +1176,9 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa)
 
 	region->region.guest_phys_addr = new_gpa;
 
-	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, &region->region);
+	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->region);
 
-	TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION failed\n"
+	TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION2 failed\n"
 		    "ret: %i errno: %i slot: %u new_gpa: 0x%lx",
 		    ret, errno, slot, new_gpa);
 }
@@ -1181,6 +1201,34 @@ void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot)
 	__vm_mem_region_delete(vm, memslot2region(vm, slot), true);
 }
 
+void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t base, uint64_t size,
+			    bool punch_hole)
+{
+	const int mode = FALLOC_FL_KEEP_SIZE | (punch_hole ? FALLOC_FL_PUNCH_HOLE : 0);
+	struct userspace_mem_region *region;
+	uint64_t end = base + size;
+	uint64_t gpa, len;
+	off_t fd_offset;
+	int ret;
+
+	for (gpa = base; gpa < end; gpa += len) {
+		uint64_t offset;
+
+		region = userspace_mem_region_find(vm, gpa, gpa);
+		TEST_ASSERT(region && region->region.flags & KVM_MEM_GUEST_MEMFD,
+			    "Private memory region not found for GPA 0x%lx", gpa);
+
+		offset = gpa - region->region.guest_phys_addr;
+		fd_offset = region->region.guest_memfd_offset + offset;
+		len = min_t(uint64_t, end - gpa, region->region.memory_size - offset);
+
+		ret = fallocate(region->region.guest_memfd, mode, fd_offset, len);
+		TEST_ASSERT(!ret, "fallocate() failed to %s at %lx (len = %lu), fd = %d, mode = %x, offset = %lx",
+			    punch_hole ? "punch hole" : "allocate", gpa, len,
+			    region->region.guest_memfd, mode, fd_offset);
+	}
+}
+
 /* Returns the size of a vCPU's kvm_run structure. */
 static int vcpu_mmap_sz(void)
 {
@@ -1218,7 +1266,7 @@ struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 	struct kvm_vcpu *vcpu;
 
 	/* Confirm a vcpu with the specified id doesn't already exist. */
-	TEST_ASSERT(!vcpu_exists(vm, vcpu_id), "vCPU%d already exists\n", vcpu_id);
+	TEST_ASSERT(!vcpu_exists(vm, vcpu_id), "vCPU%d already exists", vcpu_id);
 
 	/* Allocate and initialize new vcpu structure. */
 	vcpu = calloc(1, sizeof(*vcpu));
@@ -1227,7 +1275,7 @@ struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 	vcpu->vm = vm;
 	vcpu->id = vcpu_id;
 	vcpu->fd = __vm_ioctl(vm, KVM_CREATE_VCPU, (void *)(unsigned long)vcpu_id);
-	TEST_ASSERT(vcpu->fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_VCPU, vcpu->fd));
+	TEST_ASSERT_VM_VCPU_IOCTL(vcpu->fd >= 0, KVM_CREATE_VCPU, vcpu->fd, vm);
 
 	TEST_ASSERT(vcpu_mmap_sz() >= sizeof(*vcpu->run), "vcpu mmap size "
 		"smaller than expected, vcpu_mmap_sz: %i expected_min: %zi",
diff --git a/tools/testing/selftests/kvm/lib/memstress.c b/tools/testing/selftests/kvm/lib/memstress.c
index df457452d146..cf2c73971308 100644
--- a/tools/testing/selftests/kvm/lib/memstress.c
+++ b/tools/testing/selftests/kvm/lib/memstress.c
@@ -168,7 +168,8 @@ struct kvm_vm *memstress_create_vm(enum vm_guest_mode mode, int nr_vcpus,
 	 * The memory is also added to memslot 0, but that's a benign side
 	 * effect as KVM allows aliasing HVAs in meslots.
 	 */
-	vm = __vm_create_with_vcpus(mode, nr_vcpus, slot0_pages + guest_num_pages,
+	vm = __vm_create_with_vcpus(VM_SHAPE(mode), nr_vcpus,
+				    slot0_pages + guest_num_pages,
 				    memstress_guest_code, vcpus);
 
 	args->vm = vm;
@@ -191,7 +192,7 @@ struct kvm_vm *memstress_create_vm(enum vm_guest_mode mode, int nr_vcpus,
 	TEST_ASSERT(guest_num_pages < region_end_gfn,
 		    "Requested more guest memory than address space allows.\n"
 		    "    guest pages: %" PRIx64 " max gfn: %" PRIx64
-		    " nr_vcpus: %d wss: %" PRIx64 "]\n",
+		    " nr_vcpus: %d wss: %" PRIx64 "]",
 		    guest_num_pages, region_end_gfn - 1, nr_vcpus, vcpu_memory_bytes);
 
 	args->gpa = (region_end_gfn - guest_num_pages - 1) * args->guest_page_size;
diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c
index d146ca71e0c0..2bb33a8ac03c 100644
--- a/tools/testing/selftests/kvm/lib/riscv/processor.c
+++ b/tools/testing/selftests/kvm/lib/riscv/processor.c
@@ -201,7 +201,7 @@ void riscv_vcpu_mmu_setup(struct kvm_vcpu *vcpu)
 	satp = (vm->pgd >> PGTBL_PAGE_SIZE_SHIFT) & SATP_PPN;
 	satp |= SATP_MODE_48;
 
-	vcpu_set_reg(vcpu, RISCV_CSR_REG(satp), satp);
+	vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(satp), satp);
 }
 
 void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent)
@@ -315,7 +315,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 	vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.pc), (unsigned long)guest_code);
 
 	/* Setup default exception vector of guest */
-	vcpu_set_reg(vcpu, RISCV_CSR_REG(stvec), (unsigned long)guest_unexp_trap);
+	vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(stvec), (unsigned long)guest_unexp_trap);
 
 	return vcpu;
 }
@@ -327,7 +327,7 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)
 	int i;
 
 	TEST_ASSERT(num >= 1 && num <= 8, "Unsupported number of args,\n"
-		    "  num: %u\n", num);
+		    "  num: %u", num);
 
 	va_start(ap, num);
 
@@ -367,3 +367,48 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)
 void assert_on_unhandled_exception(struct kvm_vcpu *vcpu)
 {
 }
+
+struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
+			unsigned long arg1, unsigned long arg2,
+			unsigned long arg3, unsigned long arg4,
+			unsigned long arg5)
+{
+	register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0);
+	register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1);
+	register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2);
+	register uintptr_t a3 asm ("a3") = (uintptr_t)(arg3);
+	register uintptr_t a4 asm ("a4") = (uintptr_t)(arg4);
+	register uintptr_t a5 asm ("a5") = (uintptr_t)(arg5);
+	register uintptr_t a6 asm ("a6") = (uintptr_t)(fid);
+	register uintptr_t a7 asm ("a7") = (uintptr_t)(ext);
+	struct sbiret ret;
+
+	asm volatile (
+		"ecall"
+		: "+r" (a0), "+r" (a1)
+		: "r" (a2), "r" (a3), "r" (a4), "r" (a5), "r" (a6), "r" (a7)
+		: "memory");
+	ret.error = a0;
+	ret.value = a1;
+
+	return ret;
+}
+
+bool guest_sbi_probe_extension(int extid, long *out_val)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_BASE, SBI_EXT_BASE_PROBE_EXT, extid,
+			0, 0, 0, 0, 0);
+
+	__GUEST_ASSERT(!ret.error || ret.error == SBI_ERR_NOT_SUPPORTED,
+		       "ret.error=%ld, ret.value=%ld\n", ret.error, ret.value);
+
+	if (ret.error == SBI_ERR_NOT_SUPPORTED)
+		return false;
+
+	if (out_val)
+		*out_val = ret.value;
+
+	return true;
+}
diff --git a/tools/testing/selftests/kvm/lib/riscv/ucall.c b/tools/testing/selftests/kvm/lib/riscv/ucall.c
index fe6d1004f018..14ee17151a59 100644
--- a/tools/testing/selftests/kvm/lib/riscv/ucall.c
+++ b/tools/testing/selftests/kvm/lib/riscv/ucall.c
@@ -10,32 +10,6 @@
 #include "kvm_util.h"
 #include "processor.h"
 
-struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
-			unsigned long arg1, unsigned long arg2,
-			unsigned long arg3, unsigned long arg4,
-			unsigned long arg5)
-{
-	register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0);
-	register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1);
-	register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2);
-	register uintptr_t a3 asm ("a3") = (uintptr_t)(arg3);
-	register uintptr_t a4 asm ("a4") = (uintptr_t)(arg4);
-	register uintptr_t a5 asm ("a5") = (uintptr_t)(arg5);
-	register uintptr_t a6 asm ("a6") = (uintptr_t)(fid);
-	register uintptr_t a7 asm ("a7") = (uintptr_t)(ext);
-	struct sbiret ret;
-
-	asm volatile (
-		"ecall"
-		: "+r" (a0), "+r" (a1)
-		: "r" (a2), "r" (a3), "r" (a4), "r" (a5), "r" (a6), "r" (a7)
-		: "memory");
-	ret.error = a0;
-	ret.value = a1;
-
-	return ret;
-}
-
 void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c
index 15945121daf1..f6d227892cbc 100644
--- a/tools/testing/selftests/kvm/lib/s390x/processor.c
+++ b/tools/testing/selftests/kvm/lib/s390x/processor.c
@@ -198,7 +198,7 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)
 	int i;
 
 	TEST_ASSERT(num >= 1 && num <= 5, "Unsupported number of args,\n"
-		    "  num: %u\n",
+		    "  num: %u",
 		    num);
 
 	va_start(ap, num);
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index 5d7f28b02d73..5a8f8becb129 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -392,3 +392,28 @@ char *strdup_printf(const char *fmt, ...)
 
 	return str;
 }
+
+#define CLOCKSOURCE_PATH "/sys/devices/system/clocksource/clocksource0/current_clocksource"
+
+char *sys_get_cur_clocksource(void)
+{
+	char *clk_name;
+	struct stat st;
+	FILE *fp;
+
+	fp = fopen(CLOCKSOURCE_PATH, "r");
+	TEST_ASSERT(fp, "failed to open clocksource file, errno: %d", errno);
+
+	TEST_ASSERT(!fstat(fileno(fp), &st), "failed to stat clocksource file, errno: %d",
+		    errno);
+
+	clk_name = malloc(st.st_size);
+	TEST_ASSERT(clk_name, "failed to allocate buffer to read file");
+
+	TEST_ASSERT(fgets(clk_name, st.st_size, fp), "failed to read clocksource file: %d",
+		    ferror(fp));
+
+	fclose(fp);
+
+	return clk_name;
+}
diff --git a/tools/testing/selftests/kvm/lib/userfaultfd_util.c b/tools/testing/selftests/kvm/lib/userfaultfd_util.c
index 271f63891581..f4eef6eb2dc2 100644
--- a/tools/testing/selftests/kvm/lib/userfaultfd_util.c
+++ b/tools/testing/selftests/kvm/lib/userfaultfd_util.c
@@ -69,7 +69,7 @@ static void *uffd_handler_thread_fn(void *arg)
 		if (pollfd[1].revents & POLLIN) {
 			r = read(pollfd[1].fd, &tmp_chr, 1);
 			TEST_ASSERT(r == 1,
-				    "Error reading pipefd in UFFD thread\n");
+				    "Error reading pipefd in UFFD thread");
 			break;
 		}
 
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index d8288374078e..f639b3e062e3 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -170,10 +170,10 @@ static uint64_t *virt_create_upper_pte(struct kvm_vm *vm,
 		 * this level.
 		 */
 		TEST_ASSERT(current_level != target_level,
-			    "Cannot create hugepage at level: %u, vaddr: 0x%lx\n",
+			    "Cannot create hugepage at level: %u, vaddr: 0x%lx",
 			    current_level, vaddr);
 		TEST_ASSERT(!(*pte & PTE_LARGE_MASK),
-			    "Cannot create page table at level: %u, vaddr: 0x%lx\n",
+			    "Cannot create page table at level: %u, vaddr: 0x%lx",
 			    current_level, vaddr);
 	}
 	return pte;
@@ -220,7 +220,7 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level)
 	/* Fill in page table entry. */
 	pte = virt_get_pte(vm, pde, vaddr, PG_LEVEL_4K);
 	TEST_ASSERT(!(*pte & PTE_PRESENT_MASK),
-		    "PTE already present for 4k page at vaddr: 0x%lx\n", vaddr);
+		    "PTE already present for 4k page at vaddr: 0x%lx", vaddr);
 	*pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK);
 }
 
@@ -253,7 +253,7 @@ static bool vm_is_target_pte(uint64_t *pte, int *level, int current_level)
 	if (*pte & PTE_LARGE_MASK) {
 		TEST_ASSERT(*level == PG_LEVEL_NONE ||
 			    *level == current_level,
-			    "Unexpected hugepage at level %d\n", current_level);
+			    "Unexpected hugepage at level %d", current_level);
 		*level = current_level;
 	}
 
@@ -825,7 +825,7 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)
 	struct kvm_regs regs;
 
 	TEST_ASSERT(num >= 1 && num <= 6, "Unsupported number of args,\n"
-		    "  num: %u\n",
+		    "  num: %u",
 		    num);
 
 	va_start(ap, num);
@@ -1299,3 +1299,14 @@ void kvm_selftest_arch_init(void)
 	host_cpu_is_intel = this_cpu_is_intel();
 	host_cpu_is_amd = this_cpu_is_amd();
 }
+
+bool sys_clocksource_is_based_on_tsc(void)
+{
+	char *clk_name = sys_get_cur_clocksource();
+	bool ret = !strcmp(clk_name, "tsc\n") ||
+		   !strcmp(clk_name, "hyperv_clocksource_tsc_page\n");
+
+	free(clk_name);
+
+	return ret;
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index 59d97531c9b1..089b8925b6b2 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -54,7 +54,7 @@ int vcpu_enable_evmcs(struct kvm_vcpu *vcpu)
 	/* KVM should return supported EVMCS version range */
 	TEST_ASSERT(((evmcs_ver >> 8) >= (evmcs_ver & 0xff)) &&
 		    (evmcs_ver & 0xff) > 0,
-		    "Incorrect EVMCS version range: %x:%x\n",
+		    "Incorrect EVMCS version range: %x:%x",
 		    evmcs_ver & 0xff, evmcs_ver >> 8);
 
 	return evmcs_ver;
@@ -387,10 +387,10 @@ static void nested_create_pte(struct kvm_vm *vm,
 		 * this level.
 		 */
 		TEST_ASSERT(current_level != target_level,
-			    "Cannot create hugepage at level: %u, nested_paddr: 0x%lx\n",
+			    "Cannot create hugepage at level: %u, nested_paddr: 0x%lx",
 			    current_level, nested_paddr);
 		TEST_ASSERT(!pte->page_size,
-			    "Cannot create page table at level: %u, nested_paddr: 0x%lx\n",
+			    "Cannot create page table at level: %u, nested_paddr: 0x%lx",
 			    current_level, nested_paddr);
 	}
 }
diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
index 9855c41ca811..156361966612 100644
--- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c
+++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
@@ -45,7 +45,7 @@ static void vcpu_worker(struct memstress_vcpu_args *vcpu_args)
 	/* Let the guest access its memory until a stop signal is received */
 	while (!READ_ONCE(memstress_args.stop_vcpus)) {
 		ret = _vcpu_run(vcpu);
-		TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
+		TEST_ASSERT(ret == 0, "vcpu_run failed: %d", ret);
 
 		if (get_ucall(vcpu, NULL) == UCALL_SYNC)
 			continue;
diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c
index 8698d1ab60d0..579a64f97333 100644
--- a/tools/testing/selftests/kvm/memslot_perf_test.c
+++ b/tools/testing/selftests/kvm/memslot_perf_test.c
@@ -175,11 +175,11 @@ static void wait_for_vcpu(void)
 	struct timespec ts;
 
 	TEST_ASSERT(!clock_gettime(CLOCK_REALTIME, &ts),
-		    "clock_gettime() failed: %d\n", errno);
+		    "clock_gettime() failed: %d", errno);
 
 	ts.tv_sec += 2;
 	TEST_ASSERT(!sem_timedwait(&vcpu_ready, &ts),
-		    "sem_timedwait() failed: %d\n", errno);
+		    "sem_timedwait() failed: %d", errno);
 }
 
 static void *vm_gpa2hva(struct vm_data *data, uint64_t gpa, uint64_t *rempages)
@@ -336,7 +336,7 @@ static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots,
 
 		gpa = vm_phy_pages_alloc(data->vm, npages, guest_addr, slot);
 		TEST_ASSERT(gpa == guest_addr,
-			    "vm_phy_pages_alloc() failed\n");
+			    "vm_phy_pages_alloc() failed");
 
 		data->hva_slots[slot - 1] = addr_gpa2hva(data->vm, guest_addr);
 		memset(data->hva_slots[slot - 1], 0, npages * guest_page_size);
diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 25de4b8bc347..6435e7a65642 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -12,6 +12,11 @@
 
 #define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK)
 
+enum {
+	VCPU_FEATURE_ISA_EXT = 0,
+	VCPU_FEATURE_SBI_EXT,
+};
+
 static bool isa_ext_cant_disable[KVM_RISCV_ISA_EXT_MAX];
 
 bool filter_reg(__u64 reg)
@@ -28,31 +33,74 @@ bool filter_reg(__u64 reg)
 	 *
 	 * Note: The below list is alphabetically sorted.
 	 */
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_A:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_C:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_D:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_F:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_H:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_I:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_M:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_V:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SMSTATEEN:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSAIA:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSTC:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVINVAL:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVNAPOT:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVPBMT:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBA:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBB:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBS:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOM:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOZ:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICNTR:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICOND:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICSR:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIFENCEI:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHPM:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_A:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_C:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_D:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_F:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_H:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_I:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_M:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_V:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SMSTATEEN:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSAIA:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSTC:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVINVAL:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVNAPOT:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVPBMT:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBA:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBB:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBC:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKB:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKC:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKX:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBS:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFA:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFH:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFHMIN:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICNTR:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICOND:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICSR:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIFENCEI:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHINTNTL:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHPM:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKND:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKNE:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKNH:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKR:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKSED:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKSH:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKT:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBB:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBC:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVFH:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVFHMIN:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKB:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKG:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKNED:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKNHA:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKNHB:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKSED:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKSH:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKT:
+	/*
+	 * Like ISA_EXT registers, SBI_EXT registers are only visible when the
+	 * host supports them and disabling them does not affect the visibility
+	 * of the SBI_EXT register itself.
+	 */
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_V01:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_TIME:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_IPI:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_RFENCE:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_SRST:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_HSM:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_PMU:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_DBCN:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_STA:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR:
 		return true;
 	/* AIA registers are always available when Ssaia can't be disabled */
 	case KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(siselect):
@@ -75,12 +123,12 @@ bool check_reject_set(int err)
 	return err == EINVAL;
 }
 
-static inline bool vcpu_has_ext(struct kvm_vcpu *vcpu, int ext)
+static bool vcpu_has_ext(struct kvm_vcpu *vcpu, uint64_t ext_id)
 {
 	int ret;
 	unsigned long value;
 
-	ret = __vcpu_get_reg(vcpu, RISCV_ISA_EXT_REG(ext), &value);
+	ret = __vcpu_get_reg(vcpu, ext_id, &value);
 	return (ret) ? false : !!value;
 }
 
@@ -88,6 +136,7 @@ void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c)
 {
 	unsigned long isa_ext_state[KVM_RISCV_ISA_EXT_MAX] = { 0 };
 	struct vcpu_reg_sublist *s;
+	uint64_t feature;
 	int rc;
 
 	for (int i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++)
@@ -103,16 +152,32 @@ void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c)
 			isa_ext_cant_disable[i] = true;
 	}
 
+	for (int i = 0; i < KVM_RISCV_SBI_EXT_MAX; i++) {
+		rc = __vcpu_set_reg(vcpu, RISCV_SBI_EXT_REG(i), 0);
+		TEST_ASSERT(!rc || (rc == -1 && errno == ENOENT), "Unexpected error");
+	}
+
 	for_each_sublist(c, s) {
 		if (!s->feature)
 			continue;
 
+		switch (s->feature_type) {
+		case VCPU_FEATURE_ISA_EXT:
+			feature = RISCV_ISA_EXT_REG(s->feature);
+			break;
+		case VCPU_FEATURE_SBI_EXT:
+			feature = RISCV_SBI_EXT_REG(s->feature);
+			break;
+		default:
+			TEST_FAIL("Unknown feature type");
+		}
+
 		/* Try to enable the desired extension */
-		__vcpu_set_reg(vcpu, RISCV_ISA_EXT_REG(s->feature), 1);
+		__vcpu_set_reg(vcpu, feature, 1);
 
 		/* Double check whether the desired extension was enabled */
-		__TEST_REQUIRE(vcpu_has_ext(vcpu, s->feature),
-			       "%s not available, skipping tests\n", s->name);
+		__TEST_REQUIRE(vcpu_has_ext(vcpu, feature),
+			       "%s not available, skipping tests", s->name);
 	}
 }
 
@@ -335,15 +400,10 @@ static const char *fp_d_id_to_str(const char *prefix, __u64 id)
 }
 
 #define KVM_ISA_EXT_ARR(ext)		\
-[KVM_RISCV_ISA_EXT_##ext] = "KVM_RISCV_ISA_EXT_" #ext
+[KVM_RISCV_ISA_EXT_##ext] = "KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_" #ext
 
-static const char *isa_ext_id_to_str(const char *prefix, __u64 id)
+static const char *isa_ext_single_id_to_str(__u64 reg_off)
 {
-	/* reg_off is the offset into unsigned long kvm_isa_ext_arr[] */
-	__u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_ISA_EXT);
-
-	assert((id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_ISA_EXT);
-
 	static const char * const kvm_isa_ext_reg_name[] = {
 		KVM_ISA_EXT_ARR(A),
 		KVM_ISA_EXT_ARR(C),
@@ -361,23 +421,87 @@ static const char *isa_ext_id_to_str(const char *prefix, __u64 id)
 		KVM_ISA_EXT_ARR(SVPBMT),
 		KVM_ISA_EXT_ARR(ZBA),
 		KVM_ISA_EXT_ARR(ZBB),
+		KVM_ISA_EXT_ARR(ZBC),
+		KVM_ISA_EXT_ARR(ZBKB),
+		KVM_ISA_EXT_ARR(ZBKC),
+		KVM_ISA_EXT_ARR(ZBKX),
 		KVM_ISA_EXT_ARR(ZBS),
+		KVM_ISA_EXT_ARR(ZFA),
+		KVM_ISA_EXT_ARR(ZFH),
+		KVM_ISA_EXT_ARR(ZFHMIN),
 		KVM_ISA_EXT_ARR(ZICBOM),
 		KVM_ISA_EXT_ARR(ZICBOZ),
 		KVM_ISA_EXT_ARR(ZICNTR),
 		KVM_ISA_EXT_ARR(ZICOND),
 		KVM_ISA_EXT_ARR(ZICSR),
 		KVM_ISA_EXT_ARR(ZIFENCEI),
+		KVM_ISA_EXT_ARR(ZIHINTNTL),
 		KVM_ISA_EXT_ARR(ZIHINTPAUSE),
 		KVM_ISA_EXT_ARR(ZIHPM),
+		KVM_ISA_EXT_ARR(ZKND),
+		KVM_ISA_EXT_ARR(ZKNE),
+		KVM_ISA_EXT_ARR(ZKNH),
+		KVM_ISA_EXT_ARR(ZKR),
+		KVM_ISA_EXT_ARR(ZKSED),
+		KVM_ISA_EXT_ARR(ZKSH),
+		KVM_ISA_EXT_ARR(ZKT),
+		KVM_ISA_EXT_ARR(ZVBB),
+		KVM_ISA_EXT_ARR(ZVBC),
+		KVM_ISA_EXT_ARR(ZVFH),
+		KVM_ISA_EXT_ARR(ZVFHMIN),
+		KVM_ISA_EXT_ARR(ZVKB),
+		KVM_ISA_EXT_ARR(ZVKG),
+		KVM_ISA_EXT_ARR(ZVKNED),
+		KVM_ISA_EXT_ARR(ZVKNHA),
+		KVM_ISA_EXT_ARR(ZVKNHB),
+		KVM_ISA_EXT_ARR(ZVKSED),
+		KVM_ISA_EXT_ARR(ZVKSH),
+		KVM_ISA_EXT_ARR(ZVKT),
 	};
 
 	if (reg_off >= ARRAY_SIZE(kvm_isa_ext_reg_name))
-		return strdup_printf("%lld /* UNKNOWN */", reg_off);
+		return strdup_printf("KVM_REG_RISCV_ISA_SINGLE | %lld /* UNKNOWN */", reg_off);
 
 	return kvm_isa_ext_reg_name[reg_off];
 }
 
+static const char *isa_ext_multi_id_to_str(__u64 reg_subtype, __u64 reg_off)
+{
+	const char *unknown = "";
+
+	if (reg_off > KVM_REG_RISCV_ISA_MULTI_REG_LAST)
+		unknown = " /* UNKNOWN */";
+
+	switch (reg_subtype) {
+	case KVM_REG_RISCV_ISA_MULTI_EN:
+		return strdup_printf("KVM_REG_RISCV_ISA_MULTI_EN | %lld%s", reg_off, unknown);
+	case KVM_REG_RISCV_ISA_MULTI_DIS:
+		return strdup_printf("KVM_REG_RISCV_ISA_MULTI_DIS | %lld%s", reg_off, unknown);
+	}
+
+	return strdup_printf("%lld | %lld /* UNKNOWN */", reg_subtype, reg_off);
+}
+
+static const char *isa_ext_id_to_str(const char *prefix, __u64 id)
+{
+	__u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_ISA_EXT);
+	__u64 reg_subtype = reg_off & KVM_REG_RISCV_SUBTYPE_MASK;
+
+	assert((id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_ISA_EXT);
+
+	reg_off &= ~KVM_REG_RISCV_SUBTYPE_MASK;
+
+	switch (reg_subtype) {
+	case KVM_REG_RISCV_ISA_SINGLE:
+		return isa_ext_single_id_to_str(reg_off);
+	case KVM_REG_RISCV_ISA_MULTI_EN:
+	case KVM_REG_RISCV_ISA_MULTI_DIS:
+		return isa_ext_multi_id_to_str(reg_subtype, reg_off);
+	}
+
+	return strdup_printf("%lld | %lld /* UNKNOWN */", reg_subtype, reg_off);
+}
+
 #define KVM_SBI_EXT_ARR(ext)		\
 [ext] = "KVM_REG_RISCV_SBI_SINGLE | " #ext
 
@@ -392,6 +516,7 @@ static const char *sbi_ext_single_id_to_str(__u64 reg_off)
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_SRST),
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_HSM),
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_PMU),
+		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_STA),
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_EXPERIMENTAL),
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_VENDOR),
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_DBCN),
@@ -440,6 +565,32 @@ static const char *sbi_ext_id_to_str(const char *prefix, __u64 id)
 	return strdup_printf("%lld | %lld /* UNKNOWN */", reg_subtype, reg_off);
 }
 
+static const char *sbi_sta_id_to_str(__u64 reg_off)
+{
+	switch (reg_off) {
+	case 0: return "KVM_REG_RISCV_SBI_STA | KVM_REG_RISCV_SBI_STA_REG(shmem_lo)";
+	case 1: return "KVM_REG_RISCV_SBI_STA | KVM_REG_RISCV_SBI_STA_REG(shmem_hi)";
+	}
+	return strdup_printf("KVM_REG_RISCV_SBI_STA | %lld /* UNKNOWN */", reg_off);
+}
+
+static const char *sbi_id_to_str(const char *prefix, __u64 id)
+{
+	__u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_SBI_STATE);
+	__u64 reg_subtype = reg_off & KVM_REG_RISCV_SUBTYPE_MASK;
+
+	assert((id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_SBI_STATE);
+
+	reg_off &= ~KVM_REG_RISCV_SUBTYPE_MASK;
+
+	switch (reg_subtype) {
+	case KVM_REG_RISCV_SBI_STA:
+		return sbi_sta_id_to_str(reg_off);
+	}
+
+	return strdup_printf("%lld | %lld /* UNKNOWN */", reg_subtype, reg_off);
+}
+
 void print_reg(const char *prefix, __u64 id)
 {
 	const char *reg_size = NULL;
@@ -496,6 +647,10 @@ void print_reg(const char *prefix, __u64 id)
 		printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_SBI_EXT | %s,\n",
 				reg_size, sbi_ext_id_to_str(prefix, id));
 		break;
+	case KVM_REG_RISCV_SBI_STATE:
+		printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_SBI_STATE | %s,\n",
+				reg_size, sbi_id_to_str(prefix, id));
+		break;
 	default:
 		printf("\tKVM_REG_RISCV | %s | 0x%llx /* UNKNOWN */,\n",
 				reg_size, id & ~REG_MASK);
@@ -561,18 +716,6 @@ static __u64 base_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(time),
 	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(compare),
 	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(state),
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_V01,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_TIME,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_IPI,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_RFENCE,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_SRST,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_HSM,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_PMU,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_DBCN,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_MULTI_EN | 0,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_MULTI_DIS | 0,
 };
 
 /*
@@ -583,66 +726,31 @@ static __u64 base_skips_set[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(state),
 };
 
-static __u64 h_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_H,
+static __u64 sbi_base_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_V01,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_TIME,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_IPI,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_RFENCE,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_SRST,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_HSM,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR,
+};
+
+static __u64 sbi_sta_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_STA,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_STA | KVM_REG_RISCV_SBI_STA_REG(shmem_lo),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_STA | KVM_REG_RISCV_SBI_STA_REG(shmem_hi),
 };
 
 static __u64 zicbom_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicbom_block_size),
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOM,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM,
 };
 
 static __u64 zicboz_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicboz_block_size),
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOZ,
-};
-
-static __u64 svpbmt_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVPBMT,
-};
-
-static __u64 sstc_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSTC,
-};
-
-static __u64 svinval_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVINVAL,
-};
-
-static __u64 zihintpause_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHINTPAUSE,
-};
-
-static __u64 zba_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBA,
-};
-
-static __u64 zbb_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBB,
-};
-
-static __u64 zbs_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBS,
-};
-
-static __u64 zicntr_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICNTR,
-};
-
-static __u64 zicond_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICOND,
-};
-
-static __u64 zicsr_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICSR,
-};
-
-static __u64 zifencei_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIFENCEI,
-};
-
-static __u64 zihpm_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHPM,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ,
 };
 
 static __u64 aia_regs[] = {
@@ -653,12 +761,12 @@ static __u64 aia_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(siph),
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio1h),
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio2h),
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSAIA,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSAIA,
 };
 
 static __u64 smstateen_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_SMSTATEEN | KVM_REG_RISCV_CSR_SMSTATEEN_REG(sstateen0),
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SMSTATEEN,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SMSTATEEN,
 };
 
 static __u64 fp_f_regs[] = {
@@ -695,7 +803,7 @@ static __u64 fp_f_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[30]),
 	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[31]),
 	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(fcsr),
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_F,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_F,
 };
 
 static __u64 fp_d_regs[] = {
@@ -732,224 +840,196 @@ static __u64 fp_d_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[30]),
 	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[31]),
 	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(fcsr),
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_D,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_D,
 };
 
-#define BASE_SUBLIST \
+#define SUBLIST_BASE \
 	{"base", .regs = base_regs, .regs_n = ARRAY_SIZE(base_regs), \
 	 .skips_set = base_skips_set, .skips_set_n = ARRAY_SIZE(base_skips_set),}
-#define H_REGS_SUBLIST \
-	{"h", .feature = KVM_RISCV_ISA_EXT_H, .regs = h_regs, .regs_n = ARRAY_SIZE(h_regs),}
-#define ZICBOM_REGS_SUBLIST \
+#define SUBLIST_SBI_BASE \
+	{"sbi-base", .feature_type = VCPU_FEATURE_SBI_EXT, .feature = KVM_RISCV_SBI_EXT_V01, \
+	 .regs = sbi_base_regs, .regs_n = ARRAY_SIZE(sbi_base_regs),}
+#define SUBLIST_SBI_STA \
+	{"sbi-sta", .feature_type = VCPU_FEATURE_SBI_EXT, .feature = KVM_RISCV_SBI_EXT_STA, \
+	 .regs = sbi_sta_regs, .regs_n = ARRAY_SIZE(sbi_sta_regs),}
+#define SUBLIST_ZICBOM \
 	{"zicbom", .feature = KVM_RISCV_ISA_EXT_ZICBOM, .regs = zicbom_regs, .regs_n = ARRAY_SIZE(zicbom_regs),}
-#define ZICBOZ_REGS_SUBLIST \
+#define SUBLIST_ZICBOZ \
 	{"zicboz", .feature = KVM_RISCV_ISA_EXT_ZICBOZ, .regs = zicboz_regs, .regs_n = ARRAY_SIZE(zicboz_regs),}
-#define SVPBMT_REGS_SUBLIST \
-	{"svpbmt", .feature = KVM_RISCV_ISA_EXT_SVPBMT, .regs = svpbmt_regs, .regs_n = ARRAY_SIZE(svpbmt_regs),}
-#define SSTC_REGS_SUBLIST \
-	{"sstc", .feature = KVM_RISCV_ISA_EXT_SSTC, .regs = sstc_regs, .regs_n = ARRAY_SIZE(sstc_regs),}
-#define SVINVAL_REGS_SUBLIST \
-	{"svinval", .feature = KVM_RISCV_ISA_EXT_SVINVAL, .regs = svinval_regs, .regs_n = ARRAY_SIZE(svinval_regs),}
-#define ZIHINTPAUSE_REGS_SUBLIST \
-	{"zihintpause", .feature = KVM_RISCV_ISA_EXT_ZIHINTPAUSE, .regs = zihintpause_regs, .regs_n = ARRAY_SIZE(zihintpause_regs),}
-#define ZBA_REGS_SUBLIST \
-	{"zba", .feature = KVM_RISCV_ISA_EXT_ZBA, .regs = zba_regs, .regs_n = ARRAY_SIZE(zba_regs),}
-#define ZBB_REGS_SUBLIST \
-	{"zbb", .feature = KVM_RISCV_ISA_EXT_ZBB, .regs = zbb_regs, .regs_n = ARRAY_SIZE(zbb_regs),}
-#define ZBS_REGS_SUBLIST \
-	{"zbs", .feature = KVM_RISCV_ISA_EXT_ZBS, .regs = zbs_regs, .regs_n = ARRAY_SIZE(zbs_regs),}
-#define ZICNTR_REGS_SUBLIST \
-	{"zicntr", .feature = KVM_RISCV_ISA_EXT_ZICNTR, .regs = zicntr_regs, .regs_n = ARRAY_SIZE(zicntr_regs),}
-#define ZICOND_REGS_SUBLIST \
-	{"zicond", .feature = KVM_RISCV_ISA_EXT_ZICOND, .regs = zicond_regs, .regs_n = ARRAY_SIZE(zicond_regs),}
-#define ZICSR_REGS_SUBLIST \
-	{"zicsr", .feature = KVM_RISCV_ISA_EXT_ZICSR, .regs = zicsr_regs, .regs_n = ARRAY_SIZE(zicsr_regs),}
-#define ZIFENCEI_REGS_SUBLIST \
-	{"zifencei", .feature = KVM_RISCV_ISA_EXT_ZIFENCEI, .regs = zifencei_regs, .regs_n = ARRAY_SIZE(zifencei_regs),}
-#define ZIHPM_REGS_SUBLIST \
-	{"zihpm", .feature = KVM_RISCV_ISA_EXT_ZIHPM, .regs = zihpm_regs, .regs_n = ARRAY_SIZE(zihpm_regs),}
-#define AIA_REGS_SUBLIST \
+#define SUBLIST_AIA \
 	{"aia", .feature = KVM_RISCV_ISA_EXT_SSAIA, .regs = aia_regs, .regs_n = ARRAY_SIZE(aia_regs),}
-#define SMSTATEEN_REGS_SUBLIST \
+#define SUBLIST_SMSTATEEN \
 	{"smstateen", .feature = KVM_RISCV_ISA_EXT_SMSTATEEN, .regs = smstateen_regs, .regs_n = ARRAY_SIZE(smstateen_regs),}
-#define FP_F_REGS_SUBLIST \
+#define SUBLIST_FP_F \
 	{"fp_f", .feature = KVM_RISCV_ISA_EXT_F, .regs = fp_f_regs, \
 		.regs_n = ARRAY_SIZE(fp_f_regs),}
-#define FP_D_REGS_SUBLIST \
+#define SUBLIST_FP_D \
 	{"fp_d", .feature = KVM_RISCV_ISA_EXT_D, .regs = fp_d_regs, \
 		.regs_n = ARRAY_SIZE(fp_d_regs),}
 
-static struct vcpu_reg_list h_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	H_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zicbom_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZICBOM_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zicboz_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZICBOZ_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list svpbmt_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	SVPBMT_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list sstc_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	SSTC_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list svinval_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	SVINVAL_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zihintpause_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZIHINTPAUSE_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zba_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZBA_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zbb_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZBB_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zbs_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZBS_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zicntr_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZICNTR_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zicond_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZICOND_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zicsr_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZICSR_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zifencei_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZIFENCEI_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zihpm_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZIHPM_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list aia_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	AIA_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list smstateen_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	SMSTATEEN_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list fp_f_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	FP_F_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list fp_d_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	FP_D_REGS_SUBLIST,
-	{0},
-	},
-};
+#define KVM_ISA_EXT_SIMPLE_CONFIG(ext, extu)			\
+static __u64 regs_##ext[] = {					\
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG |			\
+	KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE |	\
+	KVM_RISCV_ISA_EXT_##extu,				\
+};								\
+static struct vcpu_reg_list config_##ext = {			\
+	.sublists = {						\
+		SUBLIST_BASE,					\
+		{						\
+			.name = #ext,				\
+			.feature = KVM_RISCV_ISA_EXT_##extu,	\
+			.regs = regs_##ext,			\
+			.regs_n = ARRAY_SIZE(regs_##ext),	\
+		},						\
+		{0},						\
+	},							\
+}								\
+
+#define KVM_SBI_EXT_SIMPLE_CONFIG(ext, extu)			\
+static __u64 regs_sbi_##ext[] = {				\
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG |			\
+	KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE |	\
+	KVM_RISCV_SBI_EXT_##extu,				\
+};								\
+static struct vcpu_reg_list config_sbi_##ext = {		\
+	.sublists = {						\
+		SUBLIST_BASE,					\
+		{						\
+			.name = "sbi-"#ext,			\
+			.feature_type = VCPU_FEATURE_SBI_EXT,	\
+			.feature = KVM_RISCV_SBI_EXT_##extu,	\
+			.regs = regs_sbi_##ext,			\
+			.regs_n = ARRAY_SIZE(regs_sbi_##ext),	\
+		},						\
+		{0},						\
+	},							\
+}								\
+
+#define KVM_ISA_EXT_SUBLIST_CONFIG(ext, extu)			\
+static struct vcpu_reg_list config_##ext = {			\
+	.sublists = {						\
+		SUBLIST_BASE,					\
+		SUBLIST_##extu,					\
+		{0},						\
+	},							\
+}								\
+
+#define KVM_SBI_EXT_SUBLIST_CONFIG(ext, extu)			\
+static struct vcpu_reg_list config_sbi_##ext = {		\
+	.sublists = {						\
+		SUBLIST_BASE,					\
+		SUBLIST_SBI_##extu,				\
+		{0},						\
+	},							\
+}								\
+
+/* Note: The below list is alphabetically sorted. */
+
+KVM_SBI_EXT_SUBLIST_CONFIG(base, BASE);
+KVM_SBI_EXT_SUBLIST_CONFIG(sta, STA);
+KVM_SBI_EXT_SIMPLE_CONFIG(pmu, PMU);
+KVM_SBI_EXT_SIMPLE_CONFIG(dbcn, DBCN);
+
+KVM_ISA_EXT_SUBLIST_CONFIG(aia, AIA);
+KVM_ISA_EXT_SUBLIST_CONFIG(fp_f, FP_F);
+KVM_ISA_EXT_SUBLIST_CONFIG(fp_d, FP_D);
+KVM_ISA_EXT_SIMPLE_CONFIG(h, H);
+KVM_ISA_EXT_SUBLIST_CONFIG(smstateen, SMSTATEEN);
+KVM_ISA_EXT_SIMPLE_CONFIG(sstc, SSTC);
+KVM_ISA_EXT_SIMPLE_CONFIG(svinval, SVINVAL);
+KVM_ISA_EXT_SIMPLE_CONFIG(svnapot, SVNAPOT);
+KVM_ISA_EXT_SIMPLE_CONFIG(svpbmt, SVPBMT);
+KVM_ISA_EXT_SIMPLE_CONFIG(zba, ZBA);
+KVM_ISA_EXT_SIMPLE_CONFIG(zbb, ZBB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zbc, ZBC);
+KVM_ISA_EXT_SIMPLE_CONFIG(zbkb, ZBKB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zbkc, ZBKC);
+KVM_ISA_EXT_SIMPLE_CONFIG(zbkx, ZBKX);
+KVM_ISA_EXT_SIMPLE_CONFIG(zbs, ZBS);
+KVM_ISA_EXT_SIMPLE_CONFIG(zfa, ZFA);
+KVM_ISA_EXT_SIMPLE_CONFIG(zfh, ZFH);
+KVM_ISA_EXT_SIMPLE_CONFIG(zfhmin, ZFHMIN);
+KVM_ISA_EXT_SUBLIST_CONFIG(zicbom, ZICBOM);
+KVM_ISA_EXT_SUBLIST_CONFIG(zicboz, ZICBOZ);
+KVM_ISA_EXT_SIMPLE_CONFIG(zicntr, ZICNTR);
+KVM_ISA_EXT_SIMPLE_CONFIG(zicond, ZICOND);
+KVM_ISA_EXT_SIMPLE_CONFIG(zicsr, ZICSR);
+KVM_ISA_EXT_SIMPLE_CONFIG(zifencei, ZIFENCEI);
+KVM_ISA_EXT_SIMPLE_CONFIG(zihintntl, ZIHINTNTL);
+KVM_ISA_EXT_SIMPLE_CONFIG(zihintpause, ZIHINTPAUSE);
+KVM_ISA_EXT_SIMPLE_CONFIG(zihpm, ZIHPM);
+KVM_ISA_EXT_SIMPLE_CONFIG(zknd, ZKND);
+KVM_ISA_EXT_SIMPLE_CONFIG(zkne, ZKNE);
+KVM_ISA_EXT_SIMPLE_CONFIG(zknh, ZKNH);
+KVM_ISA_EXT_SIMPLE_CONFIG(zkr, ZKR);
+KVM_ISA_EXT_SIMPLE_CONFIG(zksed, ZKSED);
+KVM_ISA_EXT_SIMPLE_CONFIG(zksh, ZKSH);
+KVM_ISA_EXT_SIMPLE_CONFIG(zkt, ZKT);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvbb, ZVBB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvbc, ZVBC);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvfh, ZVFH);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvfhmin, ZVFHMIN);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvkb, ZVKB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvkg, ZVKG);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvkned, ZVKNED);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvknha, ZVKNHA);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvknhb, ZVKNHB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvksed, ZVKSED);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvksh, ZVKSH);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvkt, ZVKT);
 
 struct vcpu_reg_list *vcpu_configs[] = {
-	&h_config,
-	&zicbom_config,
-	&zicboz_config,
-	&svpbmt_config,
-	&sstc_config,
-	&svinval_config,
-	&zihintpause_config,
-	&zba_config,
-	&zbb_config,
-	&zbs_config,
-	&zicntr_config,
-	&zicond_config,
-	&zicsr_config,
-	&zifencei_config,
-	&zihpm_config,
-	&aia_config,
-	&smstateen_config,
-	&fp_f_config,
-	&fp_d_config,
+	&config_sbi_base,
+	&config_sbi_sta,
+	&config_sbi_pmu,
+	&config_sbi_dbcn,
+	&config_aia,
+	&config_fp_f,
+	&config_fp_d,
+	&config_h,
+	&config_smstateen,
+	&config_sstc,
+	&config_svinval,
+	&config_svnapot,
+	&config_svpbmt,
+	&config_zba,
+	&config_zbb,
+	&config_zbc,
+	&config_zbkb,
+	&config_zbkc,
+	&config_zbkx,
+	&config_zbs,
+	&config_zfa,
+	&config_zfh,
+	&config_zfhmin,
+	&config_zicbom,
+	&config_zicboz,
+	&config_zicntr,
+	&config_zicond,
+	&config_zicsr,
+	&config_zifencei,
+	&config_zihintntl,
+	&config_zihintpause,
+	&config_zihpm,
+	&config_zknd,
+	&config_zkne,
+	&config_zknh,
+	&config_zkr,
+	&config_zksed,
+	&config_zksh,
+	&config_zkt,
+	&config_zvbb,
+	&config_zvbc,
+	&config_zvfh,
+	&config_zvfhmin,
+	&config_zvkb,
+	&config_zvkg,
+	&config_zvkned,
+	&config_zvknha,
+	&config_zvknhb,
+	&config_zvksed,
+	&config_zvksh,
+	&config_zvkt,
 };
 int vcpu_configs_n = ARRAY_SIZE(vcpu_configs);
diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c
index f74e76d03b7e..28f97fb52044 100644
--- a/tools/testing/selftests/kvm/rseq_test.c
+++ b/tools/testing/selftests/kvm/rseq_test.c
@@ -245,7 +245,7 @@ int main(int argc, char *argv[])
 		} while (snapshot != atomic_read(&seq_cnt));
 
 		TEST_ASSERT(rseq_cpu == cpu,
-			    "rseq CPU = %d, sched CPU = %d\n", rseq_cpu, cpu);
+			    "rseq CPU = %d, sched CPU = %d", rseq_cpu, cpu);
 	}
 
 	/*
@@ -256,7 +256,7 @@ int main(int argc, char *argv[])
 	 * migrations given the 1us+ delay in the migration task.
 	 */
 	TEST_ASSERT(i > (NR_TASK_MIGRATIONS / 2),
-		    "Only performed %d KVM_RUNs, task stalled too much?\n", i);
+		    "Only performed %d KVM_RUNs, task stalled too much?", i);
 
 	pthread_join(migration_thread, NULL);
 
diff --git a/tools/testing/selftests/kvm/s390x/cmma_test.c b/tools/testing/selftests/kvm/s390x/cmma_test.c
index c8e0a6495a63..626a2b8a2037 100644
--- a/tools/testing/selftests/kvm/s390x/cmma_test.c
+++ b/tools/testing/selftests/kvm/s390x/cmma_test.c
@@ -94,11 +94,6 @@ static void guest_dirty_test_data(void)
 	);
 }
 
-static struct kvm_vm *create_vm(void)
-{
-	return ____vm_create(VM_MODE_DEFAULT);
-}
-
 static void create_main_memslot(struct kvm_vm *vm)
 {
 	int i;
@@ -157,7 +152,7 @@ static struct kvm_vm *create_vm_two_memslots(void)
 {
 	struct kvm_vm *vm;
 
-	vm = create_vm();
+	vm = vm_create_barebones();
 
 	create_memslots(vm);
 
@@ -276,7 +271,7 @@ static void assert_exit_was_hypercall(struct kvm_vcpu *vcpu)
 
 static void test_migration_mode(void)
 {
-	struct kvm_vm *vm = create_vm();
+	struct kvm_vm *vm = vm_create_barebones();
 	struct kvm_vcpu *vcpu;
 	u64 orig_psw;
 	int rc;
@@ -670,7 +665,7 @@ struct testdef {
  */
 static int machine_has_cmma(void)
 {
-	struct kvm_vm *vm = create_vm();
+	struct kvm_vm *vm = vm_create_barebones();
 	int r;
 
 	r = !__kvm_has_device_attr(vm->fd, KVM_S390_VM_MEM_CTRL, KVM_S390_VM_MEM_ENABLE_CMMA);
diff --git a/tools/testing/selftests/kvm/s390x/resets.c b/tools/testing/selftests/kvm/s390x/resets.c
index e41e2cb8ffa9..357943f2bea8 100644
--- a/tools/testing/selftests/kvm/s390x/resets.c
+++ b/tools/testing/selftests/kvm/s390x/resets.c
@@ -78,7 +78,7 @@ static void assert_noirq(struct kvm_vcpu *vcpu)
 	 * (notably, the emergency call interrupt we have injected) should
 	 * be cleared by the resets, so this should be 0.
 	 */
-	TEST_ASSERT(irqs >= 0, "Could not fetch IRQs: errno %d\n", errno);
+	TEST_ASSERT(irqs >= 0, "Could not fetch IRQs: errno %d", errno);
 	TEST_ASSERT(!irqs, "IRQ pending");
 }
 
@@ -199,7 +199,7 @@ static void inject_irq(struct kvm_vcpu *vcpu)
 	irq->type = KVM_S390_INT_EMERGENCY;
 	irq->u.emerg.code = vcpu->id;
 	irqs = __vcpu_ioctl(vcpu, KVM_S390_SET_IRQ_STATE, &irq_state);
-	TEST_ASSERT(irqs >= 0, "Error injecting EMERGENCY IRQ errno %d\n", errno);
+	TEST_ASSERT(irqs >= 0, "Error injecting EMERGENCY IRQ errno %d", errno);
 }
 
 static struct kvm_vm *create_vm(struct kvm_vcpu **vcpu)
diff --git a/tools/testing/selftests/kvm/s390x/sync_regs_test.c b/tools/testing/selftests/kvm/s390x/sync_regs_test.c
index 636a70ddac1e..43fb25ddc3ec 100644
--- a/tools/testing/selftests/kvm/s390x/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/s390x/sync_regs_test.c
@@ -39,13 +39,13 @@ static void guest_code(void)
 #define REG_COMPARE(reg) \
 	TEST_ASSERT(left->reg == right->reg, \
 		    "Register " #reg \
-		    " values did not match: 0x%llx, 0x%llx\n", \
+		    " values did not match: 0x%llx, 0x%llx", \
 		    left->reg, right->reg)
 
 #define REG_COMPARE32(reg) \
 	TEST_ASSERT(left->reg == right->reg, \
 		    "Register " #reg \
-		    " values did not match: 0x%x, 0x%x\n", \
+		    " values did not match: 0x%x, 0x%x", \
 		    left->reg, right->reg)
 
 
@@ -82,14 +82,14 @@ void test_read_invalid(struct kvm_vcpu *vcpu)
 	run->kvm_valid_regs = INVALID_SYNC_FIELD;
 	rv = _vcpu_run(vcpu);
 	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d",
 		    rv);
 	run->kvm_valid_regs = 0;
 
 	run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
 	rv = _vcpu_run(vcpu);
 	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d",
 		    rv);
 	run->kvm_valid_regs = 0;
 }
@@ -103,14 +103,14 @@ void test_set_invalid(struct kvm_vcpu *vcpu)
 	run->kvm_dirty_regs = INVALID_SYNC_FIELD;
 	rv = _vcpu_run(vcpu);
 	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d",
 		    rv);
 	run->kvm_dirty_regs = 0;
 
 	run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
 	rv = _vcpu_run(vcpu);
 	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d",
 		    rv);
 	run->kvm_dirty_regs = 0;
 }
@@ -125,12 +125,12 @@ void test_req_and_verify_all_valid_regs(struct kvm_vcpu *vcpu)
 	/* Request and verify all valid register sets. */
 	run->kvm_valid_regs = TEST_SYNC_FIELDS;
 	rv = _vcpu_run(vcpu);
-	TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv);
+	TEST_ASSERT(rv == 0, "vcpu_run failed: %d", rv);
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC);
 	TEST_ASSERT(run->s390_sieic.icptcode == 4 &&
 		    (run->s390_sieic.ipa >> 8) == 0x83 &&
 		    (run->s390_sieic.ipb >> 16) == 0x501,
-		    "Unexpected interception code: ic=%u, ipa=0x%x, ipb=0x%x\n",
+		    "Unexpected interception code: ic=%u, ipa=0x%x, ipb=0x%x",
 		    run->s390_sieic.icptcode, run->s390_sieic.ipa,
 		    run->s390_sieic.ipb);
 
@@ -161,7 +161,7 @@ void test_set_and_verify_various_reg_values(struct kvm_vcpu *vcpu)
 	}
 
 	rv = _vcpu_run(vcpu);
-	TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv);
+	TEST_ASSERT(rv == 0, "vcpu_run failed: %d", rv);
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC);
 	TEST_ASSERT(run->s.regs.gprs[11] == 0xBAD1DEA + 1,
 		    "r11 sync regs value incorrect 0x%llx.",
@@ -193,7 +193,7 @@ void test_clear_kvm_dirty_regs_bits(struct kvm_vcpu *vcpu)
 	run->s.regs.gprs[11] = 0xDEADBEEF;
 	run->s.regs.diag318 = 0x4B1D;
 	rv = _vcpu_run(vcpu);
-	TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv);
+	TEST_ASSERT(rv == 0, "vcpu_run failed: %d", rv);
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC);
 	TEST_ASSERT(run->s.regs.gprs[11] != 0xDEADBEEF,
 		    "r11 sync regs value incorrect 0x%llx.",
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index b32960189f5f..06b43ed23580 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -98,11 +98,11 @@ static void wait_for_vcpu(void)
 	struct timespec ts;
 
 	TEST_ASSERT(!clock_gettime(CLOCK_REALTIME, &ts),
-		    "clock_gettime() failed: %d\n", errno);
+		    "clock_gettime() failed: %d", errno);
 
 	ts.tv_sec += 2;
 	TEST_ASSERT(!sem_timedwait(&vcpu_ready, &ts),
-		    "sem_timedwait() failed: %d\n", errno);
+		    "sem_timedwait() failed: %d", errno);
 
 	/* Wait for the vCPU thread to reenter the guest. */
 	usleep(100000);
@@ -157,17 +157,17 @@ static void guest_code_move_memory_region(void)
 	 */
 	val = guest_spin_on_val(0);
 	__GUEST_ASSERT(val == 1 || val == MMIO_VAL,
-		       "Expected '1' or MMIO ('%llx'), got '%llx'", MMIO_VAL, val);
+		       "Expected '1' or MMIO ('%lx'), got '%lx'", MMIO_VAL, val);
 
 	/* Spin until the misaligning memory region move completes. */
 	val = guest_spin_on_val(MMIO_VAL);
 	__GUEST_ASSERT(val == 1 || val == 0,
-		       "Expected '0' or '1' (no MMIO), got '%llx'", val);
+		       "Expected '0' or '1' (no MMIO), got '%lx'", val);
 
 	/* Spin until the memory region starts to get re-aligned. */
 	val = guest_spin_on_val(0);
 	__GUEST_ASSERT(val == 1 || val == MMIO_VAL,
-		       "Expected '1' or MMIO ('%llx'), got '%llx'", MMIO_VAL, val);
+		       "Expected '1' or MMIO ('%lx'), got '%lx'", MMIO_VAL, val);
 
 	/* Spin until the re-aligning memory region move completes. */
 	val = guest_spin_on_val(MMIO_VAL);
@@ -302,7 +302,7 @@ static void test_delete_memory_region(void)
 	if (run->exit_reason == KVM_EXIT_INTERNAL_ERROR)
 		TEST_ASSERT(regs.rip >= final_rip_start &&
 			    regs.rip < final_rip_end,
-			    "Bad rip, expected 0x%lx - 0x%lx, got 0x%llx\n",
+			    "Bad rip, expected 0x%lx - 0x%lx, got 0x%llx",
 			    final_rip_start, final_rip_end, regs.rip);
 
 	kvm_vm_free(vm);
@@ -326,6 +326,65 @@ static void test_zero_memory_regions(void)
 }
 #endif /* __x86_64__ */
 
+static void test_invalid_memory_region_flags(void)
+{
+	uint32_t supported_flags = KVM_MEM_LOG_DIRTY_PAGES;
+	const uint32_t v2_only_flags = KVM_MEM_GUEST_MEMFD;
+	struct kvm_vm *vm;
+	int r, i;
+
+#if defined __aarch64__ || defined __x86_64__
+	supported_flags |= KVM_MEM_READONLY;
+#endif
+
+#ifdef __x86_64__
+	if (kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM))
+		vm = vm_create_barebones_protected_vm();
+	else
+#endif
+		vm = vm_create_barebones();
+
+	if (kvm_check_cap(KVM_CAP_MEMORY_ATTRIBUTES) & KVM_MEMORY_ATTRIBUTE_PRIVATE)
+		supported_flags |= KVM_MEM_GUEST_MEMFD;
+
+	for (i = 0; i < 32; i++) {
+		if ((supported_flags & BIT(i)) && !(v2_only_flags & BIT(i)))
+			continue;
+
+		r = __vm_set_user_memory_region(vm, 0, BIT(i),
+						0, MEM_REGION_SIZE, NULL);
+
+		TEST_ASSERT(r && errno == EINVAL,
+			    "KVM_SET_USER_MEMORY_REGION should have failed on v2 only flag 0x%lx", BIT(i));
+
+		if (supported_flags & BIT(i))
+			continue;
+
+		r = __vm_set_user_memory_region2(vm, 0, BIT(i),
+						 0, MEM_REGION_SIZE, NULL, 0, 0);
+		TEST_ASSERT(r && errno == EINVAL,
+			    "KVM_SET_USER_MEMORY_REGION2 should have failed on unsupported flag 0x%lx", BIT(i));
+	}
+
+	if (supported_flags & KVM_MEM_GUEST_MEMFD) {
+		int guest_memfd = vm_create_guest_memfd(vm, MEM_REGION_SIZE, 0);
+
+		r = __vm_set_user_memory_region2(vm, 0,
+						 KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_GUEST_MEMFD,
+						 0, MEM_REGION_SIZE, NULL, guest_memfd, 0);
+		TEST_ASSERT(r && errno == EINVAL,
+			    "KVM_SET_USER_MEMORY_REGION2 should have failed, dirty logging private memory is unsupported");
+
+		r = __vm_set_user_memory_region2(vm, 0,
+						 KVM_MEM_READONLY | KVM_MEM_GUEST_MEMFD,
+						 0, MEM_REGION_SIZE, NULL, guest_memfd, 0);
+		TEST_ASSERT(r && errno == EINVAL,
+			    "KVM_SET_USER_MEMORY_REGION2 should have failed, read-only GUEST_MEMFD memslots are unsupported");
+
+		close(guest_memfd);
+	}
+}
+
 /*
  * Test it can be added memory slots up to KVM_CAP_NR_MEMSLOTS, then any
  * tentative to add further slots should fail.
@@ -385,13 +444,105 @@ static void test_add_max_memory_regions(void)
 	kvm_vm_free(vm);
 }
 
+
+#ifdef __x86_64__
+static void test_invalid_guest_memfd(struct kvm_vm *vm, int memfd,
+				     size_t offset, const char *msg)
+{
+	int r = __vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
+					     MEM_REGION_GPA, MEM_REGION_SIZE,
+					     0, memfd, offset);
+	TEST_ASSERT(r == -1 && errno == EINVAL, "%s", msg);
+}
+
+static void test_add_private_memory_region(void)
+{
+	struct kvm_vm *vm, *vm2;
+	int memfd, i;
+
+	pr_info("Testing ADD of KVM_MEM_GUEST_MEMFD memory regions\n");
+
+	vm = vm_create_barebones_protected_vm();
+
+	test_invalid_guest_memfd(vm, vm->kvm_fd, 0, "KVM fd should fail");
+	test_invalid_guest_memfd(vm, vm->fd, 0, "VM's fd should fail");
+
+	memfd = kvm_memfd_alloc(MEM_REGION_SIZE, false);
+	test_invalid_guest_memfd(vm, memfd, 0, "Regular memfd() should fail");
+	close(memfd);
+
+	vm2 = vm_create_barebones_protected_vm();
+	memfd = vm_create_guest_memfd(vm2, MEM_REGION_SIZE, 0);
+	test_invalid_guest_memfd(vm, memfd, 0, "Other VM's guest_memfd() should fail");
+
+	vm_set_user_memory_region2(vm2, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
+				   MEM_REGION_GPA, MEM_REGION_SIZE, 0, memfd, 0);
+	close(memfd);
+	kvm_vm_free(vm2);
+
+	memfd = vm_create_guest_memfd(vm, MEM_REGION_SIZE, 0);
+	for (i = 1; i < PAGE_SIZE; i++)
+		test_invalid_guest_memfd(vm, memfd, i, "Unaligned offset should fail");
+
+	vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
+				   MEM_REGION_GPA, MEM_REGION_SIZE, 0, memfd, 0);
+	close(memfd);
+
+	kvm_vm_free(vm);
+}
+
+static void test_add_overlapping_private_memory_regions(void)
+{
+	struct kvm_vm *vm;
+	int memfd;
+	int r;
+
+	pr_info("Testing ADD of overlapping KVM_MEM_GUEST_MEMFD memory regions\n");
+
+	vm = vm_create_barebones_protected_vm();
+
+	memfd = vm_create_guest_memfd(vm, MEM_REGION_SIZE * 4, 0);
+
+	vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
+				   MEM_REGION_GPA, MEM_REGION_SIZE * 2, 0, memfd, 0);
+
+	vm_set_user_memory_region2(vm, MEM_REGION_SLOT + 1, KVM_MEM_GUEST_MEMFD,
+				   MEM_REGION_GPA * 2, MEM_REGION_SIZE * 2,
+				   0, memfd, MEM_REGION_SIZE * 2);
+
+	/*
+	 * Delete the first memslot, and then attempt to recreate it except
+	 * with a "bad" offset that results in overlap in the guest_memfd().
+	 */
+	vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
+				   MEM_REGION_GPA, 0, NULL, -1, 0);
+
+	/* Overlap the front half of the other slot. */
+	r = __vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
+					 MEM_REGION_GPA * 2 - MEM_REGION_SIZE,
+					 MEM_REGION_SIZE * 2,
+					 0, memfd, 0);
+	TEST_ASSERT(r == -1 && errno == EEXIST, "%s",
+		    "Overlapping guest_memfd() bindings should fail with EEXIST");
+
+	/* And now the back half of the other slot. */
+	r = __vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
+					 MEM_REGION_GPA * 2 + MEM_REGION_SIZE,
+					 MEM_REGION_SIZE * 2,
+					 0, memfd, 0);
+	TEST_ASSERT(r == -1 && errno == EEXIST, "%s",
+		    "Overlapping guest_memfd() bindings should fail with EEXIST");
+
+	close(memfd);
+	kvm_vm_free(vm);
+}
+#endif
+
 int main(int argc, char *argv[])
 {
 #ifdef __x86_64__
 	int i, loops;
-#endif
 
-#ifdef __x86_64__
 	/*
 	 * FIXME: the zero-memslot test fails on aarch64 and s390x because
 	 * KVM_RUN fails with ENOEXEC or EFAULT.
@@ -399,9 +550,19 @@ int main(int argc, char *argv[])
 	test_zero_memory_regions();
 #endif
 
+	test_invalid_memory_region_flags();
+
 	test_add_max_memory_regions();
 
 #ifdef __x86_64__
+	if (kvm_has_cap(KVM_CAP_GUEST_MEMFD) &&
+	    (kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM))) {
+		test_add_private_memory_region();
+		test_add_overlapping_private_memory_regions();
+	} else {
+		pr_info("Skipping tests for KVM_MEM_GUEST_MEMFD memory regions\n");
+	}
+
 	if (argc > 1)
 		loops = atoi_positive("Number of iterations", argv[1]);
 	else
diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c
index 171adfb2a6cb..bae0c5026f82 100644
--- a/tools/testing/selftests/kvm/steal_time.c
+++ b/tools/testing/selftests/kvm/steal_time.c
@@ -11,7 +11,9 @@
 #include <pthread.h>
 #include <linux/kernel.h>
 #include <asm/kvm.h>
+#ifndef __riscv
 #include <asm/kvm_para.h>
+#endif
 
 #include "test_util.h"
 #include "kvm_util.h"
@@ -203,6 +205,103 @@ static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx)
 	pr_info("    st_time: %ld\n", st->st_time);
 }
 
+#elif defined(__riscv)
+
+/* SBI STA shmem must have 64-byte alignment */
+#define STEAL_TIME_SIZE		((sizeof(struct sta_struct) + 63) & ~63)
+
+static vm_paddr_t st_gpa[NR_VCPUS];
+
+struct sta_struct {
+	uint32_t sequence;
+	uint32_t flags;
+	uint64_t steal;
+	uint8_t preempted;
+	uint8_t pad[47];
+} __packed;
+
+static void sta_set_shmem(vm_paddr_t gpa, unsigned long flags)
+{
+	unsigned long lo = (unsigned long)gpa;
+#if __riscv_xlen == 32
+	unsigned long hi = (unsigned long)(gpa >> 32);
+#else
+	unsigned long hi = gpa == -1 ? -1 : 0;
+#endif
+	struct sbiret ret = sbi_ecall(SBI_EXT_STA, 0, lo, hi, flags, 0, 0, 0);
+
+	GUEST_ASSERT(ret.value == 0 && ret.error == 0);
+}
+
+static void check_status(struct sta_struct *st)
+{
+	GUEST_ASSERT(!(READ_ONCE(st->sequence) & 1));
+	GUEST_ASSERT(READ_ONCE(st->flags) == 0);
+	GUEST_ASSERT(READ_ONCE(st->preempted) == 0);
+}
+
+static void guest_code(int cpu)
+{
+	struct sta_struct *st = st_gva[cpu];
+	uint32_t sequence;
+	long out_val = 0;
+	bool probe;
+
+	probe = guest_sbi_probe_extension(SBI_EXT_STA, &out_val);
+	GUEST_ASSERT(probe && out_val == 1);
+
+	sta_set_shmem(st_gpa[cpu], 0);
+	GUEST_SYNC(0);
+
+	check_status(st);
+	WRITE_ONCE(guest_stolen_time[cpu], st->steal);
+	sequence = READ_ONCE(st->sequence);
+	check_status(st);
+	GUEST_SYNC(1);
+
+	check_status(st);
+	GUEST_ASSERT(sequence < READ_ONCE(st->sequence));
+	WRITE_ONCE(guest_stolen_time[cpu], st->steal);
+	check_status(st);
+	GUEST_DONE();
+}
+
+static bool is_steal_time_supported(struct kvm_vcpu *vcpu)
+{
+	uint64_t id = RISCV_SBI_EXT_REG(KVM_RISCV_SBI_EXT_STA);
+	unsigned long enabled;
+
+	vcpu_get_reg(vcpu, id, &enabled);
+	TEST_ASSERT(enabled == 0 || enabled == 1, "Expected boolean result");
+
+	return enabled;
+}
+
+static void steal_time_init(struct kvm_vcpu *vcpu, uint32_t i)
+{
+	/* ST_GPA_BASE is identity mapped */
+	st_gva[i] = (void *)(ST_GPA_BASE + i * STEAL_TIME_SIZE);
+	st_gpa[i] = addr_gva2gpa(vcpu->vm, (vm_vaddr_t)st_gva[i]);
+	sync_global_to_guest(vcpu->vm, st_gva[i]);
+	sync_global_to_guest(vcpu->vm, st_gpa[i]);
+}
+
+static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx)
+{
+	struct sta_struct *st = addr_gva2hva(vm, (ulong)st_gva[vcpu_idx]);
+	int i;
+
+	pr_info("VCPU%d:\n", vcpu_idx);
+	pr_info("    sequence:  %d\n", st->sequence);
+	pr_info("    flags:     %d\n", st->flags);
+	pr_info("    steal:     %"PRIu64"\n", st->steal);
+	pr_info("    preempted: %d\n", st->preempted);
+	pr_info("    pad:      ");
+	for (i = 0; i < 47; ++i)
+		pr_info("%d", st->pad[i]);
+	pr_info("\n");
+}
+
 #endif
 
 static void *do_steal_time(void *arg)
diff --git a/tools/testing/selftests/kvm/system_counter_offset_test.c b/tools/testing/selftests/kvm/system_counter_offset_test.c
index 7f5b330b6a1b..513d421a9bff 100644
--- a/tools/testing/selftests/kvm/system_counter_offset_test.c
+++ b/tools/testing/selftests/kvm/system_counter_offset_test.c
@@ -108,7 +108,7 @@ static void enter_guest(struct kvm_vcpu *vcpu)
 			handle_abort(&uc);
 			return;
 		default:
-			TEST_ASSERT(0, "unhandled ucall %ld\n",
+			TEST_ASSERT(0, "unhandled ucall %ld",
 				    get_ucall(vcpu, &uc));
 		}
 	}
diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c
index 11329e5ff945..eae521f050e0 100644
--- a/tools/testing/selftests/kvm/x86_64/amx_test.c
+++ b/tools/testing/selftests/kvm/x86_64/amx_test.c
@@ -221,7 +221,7 @@ int main(int argc, char *argv[])
 	vm_vaddr_t amx_cfg, tiledata, xstate;
 	struct ucall uc;
 	u32 amx_offset;
-	int stage, ret;
+	int ret;
 
 	/*
 	 * Note, all off-by-default features must be enabled before anything
@@ -263,7 +263,7 @@ int main(int argc, char *argv[])
 	memset(addr_gva2hva(vm, xstate), 0, PAGE_SIZE * DIV_ROUND_UP(XSAVE_SIZE, PAGE_SIZE));
 	vcpu_args_set(vcpu, 3, amx_cfg, tiledata, xstate);
 
-	for (stage = 1; ; stage++) {
+	for (;;) {
 		vcpu_run(vcpu);
 		TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 
@@ -296,7 +296,7 @@ int main(int argc, char *argv[])
 				void *tiles_data = (void *)addr_gva2hva(vm, tiledata);
 				/* Only check TMM0 register, 1 tile */
 				ret = memcmp(amx_start, tiles_data, TILE_SIZE);
-				TEST_ASSERT(ret == 0, "memcmp failed, ret=%d\n", ret);
+				TEST_ASSERT(ret == 0, "memcmp failed, ret=%d", ret);
 				kvm_x86_state_cleanup(state);
 				break;
 			case 9:
diff --git a/tools/testing/selftests/kvm/x86_64/cpuid_test.c b/tools/testing/selftests/kvm/x86_64/cpuid_test.c
index 3b34d8156d1c..8c579ce714e9 100644
--- a/tools/testing/selftests/kvm/x86_64/cpuid_test.c
+++ b/tools/testing/selftests/kvm/x86_64/cpuid_test.c
@@ -84,7 +84,7 @@ static void compare_cpuids(const struct kvm_cpuid2 *cpuid1,
 
 		TEST_ASSERT(e1->function == e2->function &&
 			    e1->index == e2->index && e1->flags == e2->flags,
-			    "CPUID entries[%d] mismtach: 0x%x.%d.%x vs. 0x%x.%d.%x\n",
+			    "CPUID entries[%d] mismtach: 0x%x.%d.%x vs. 0x%x.%d.%x",
 			    i, e1->function, e1->index, e1->flags,
 			    e2->function, e2->index, e2->flags);
 
@@ -170,7 +170,7 @@ static void test_get_cpuid2(struct kvm_vcpu *vcpu)
 
 	vcpu_ioctl(vcpu, KVM_GET_CPUID2, cpuid);
 	TEST_ASSERT(cpuid->nent == vcpu->cpuid->nent,
-		    "KVM didn't update nent on success, wanted %u, got %u\n",
+		    "KVM didn't update nent on success, wanted %u, got %u",
 		    vcpu->cpuid->nent, cpuid->nent);
 
 	for (i = 0; i < vcpu->cpuid->nent; i++) {
diff --git a/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c b/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c
index 634c6bfcd572..ee3b384b991c 100644
--- a/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c
+++ b/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c
@@ -92,7 +92,6 @@ static void run_test(enum vm_guest_mode mode, void *unused)
 	uint64_t host_num_pages;
 	uint64_t pages_per_slot;
 	int i;
-	uint64_t total_4k_pages;
 	struct kvm_page_stats stats_populated;
 	struct kvm_page_stats stats_dirty_logging_enabled;
 	struct kvm_page_stats stats_dirty_pass[ITERATIONS];
@@ -107,6 +106,9 @@ static void run_test(enum vm_guest_mode mode, void *unused)
 	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
 	host_num_pages = vm_num_host_pages(mode, guest_num_pages);
 	pages_per_slot = host_num_pages / SLOTS;
+	TEST_ASSERT_EQ(host_num_pages, pages_per_slot * SLOTS);
+	TEST_ASSERT(!(host_num_pages % 512),
+		    "Number of pages, '%lu' not a multiple of 2MiB", host_num_pages);
 
 	bitmaps = memstress_alloc_bitmaps(SLOTS, pages_per_slot);
 
@@ -165,10 +167,8 @@ static void run_test(enum vm_guest_mode mode, void *unused)
 	memstress_free_bitmaps(bitmaps, SLOTS);
 	memstress_destroy_vm(vm);
 
-	/* Make assertions about the page counts. */
-	total_4k_pages = stats_populated.pages_4k;
-	total_4k_pages += stats_populated.pages_2m * 512;
-	total_4k_pages += stats_populated.pages_1g * 512 * 512;
+	TEST_ASSERT_EQ((stats_populated.pages_2m * 512 +
+			stats_populated.pages_1g * 512 * 512), host_num_pages);
 
 	/*
 	 * Check that all huge pages were split. Since large pages can only
@@ -180,19 +180,22 @@ static void run_test(enum vm_guest_mode mode, void *unused)
 	 */
 	if (dirty_log_manual_caps) {
 		TEST_ASSERT_EQ(stats_clear_pass[0].hugepages, 0);
-		TEST_ASSERT_EQ(stats_clear_pass[0].pages_4k, total_4k_pages);
+		TEST_ASSERT(stats_clear_pass[0].pages_4k >= host_num_pages,
+			    "Expected at least '%lu' 4KiB pages, found only '%lu'",
+			    host_num_pages, stats_clear_pass[0].pages_4k);
 		TEST_ASSERT_EQ(stats_dirty_logging_enabled.hugepages, stats_populated.hugepages);
 	} else {
 		TEST_ASSERT_EQ(stats_dirty_logging_enabled.hugepages, 0);
-		TEST_ASSERT_EQ(stats_dirty_logging_enabled.pages_4k, total_4k_pages);
+		TEST_ASSERT(stats_dirty_logging_enabled.pages_4k >= host_num_pages,
+			    "Expected at least '%lu' 4KiB pages, found only '%lu'",
+			    host_num_pages, stats_dirty_logging_enabled.pages_4k);
 	}
 
 	/*
 	 * Once dirty logging is disabled and the vCPUs have touched all their
-	 * memory again, the page counts should be the same as they were
+	 * memory again, the hugepage counts should be the same as they were
 	 * right after initial population of memory.
 	 */
-	TEST_ASSERT_EQ(stats_populated.pages_4k, stats_repopulated.pages_4k);
 	TEST_ASSERT_EQ(stats_populated.pages_2m, stats_repopulated.pages_2m);
 	TEST_ASSERT_EQ(stats_populated.pages_1g, stats_repopulated.pages_1g);
 }
diff --git a/tools/testing/selftests/kvm/x86_64/flds_emulation.h b/tools/testing/selftests/kvm/x86_64/flds_emulation.h
index 0a1573d52882..37b1a9f52864 100644
--- a/tools/testing/selftests/kvm/x86_64/flds_emulation.h
+++ b/tools/testing/selftests/kvm/x86_64/flds_emulation.h
@@ -41,7 +41,7 @@ static inline void handle_flds_emulation_failure_exit(struct kvm_vcpu *vcpu)
 
 	insn_bytes = run->emulation_failure.insn_bytes;
 	TEST_ASSERT(insn_bytes[0] == 0xd9 && insn_bytes[1] == 0,
-		    "Expected 'flds [eax]', opcode '0xd9 0x00', got opcode 0x%02x 0x%02x\n",
+		    "Expected 'flds [eax]', opcode '0xd9 0x00', got opcode 0x%02x 0x%02x",
 		    insn_bytes[0], insn_bytes[1]);
 
 	vcpu_regs_get(vcpu, &regs);
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
index f25749eaa6a8..e058bc676cd6 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
@@ -211,6 +211,9 @@ int main(void)
 	vm_vaddr_t tsc_page_gva;
 	int stage;
 
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_TIME));
+	TEST_REQUIRE(sys_clocksource_is_based_on_tsc());
+
 	vm = vm_create_with_one_vcpu(&vcpu, guest_main);
 
 	vcpu_set_hv_cpuid(vcpu);
@@ -218,7 +221,7 @@ int main(void)
 	tsc_page_gva = vm_vaddr_alloc_page(vm);
 	memset(addr_gva2hva(vm, tsc_page_gva), 0x0, getpagesize());
 	TEST_ASSERT((addr_gva2gpa(vm, tsc_page_gva) & (getpagesize() - 1)) == 0,
-		"TSC page has to be page aligned\n");
+		"TSC page has to be page aligned");
 	vcpu_args_set(vcpu, 2, tsc_page_gva, addr_gva2gpa(vm, tsc_page_gva));
 
 	host_check_tsc_msr_rdtsc(vcpu);
@@ -235,7 +238,7 @@ int main(void)
 			break;
 		case UCALL_DONE:
 			/* Keep in sync with guest_main() */
-			TEST_ASSERT(stage == 11, "Testing ended prematurely, stage %d\n",
+			TEST_ASSERT(stage == 11, "Testing ended prematurely, stage %d",
 				    stage);
 			goto out;
 		default:
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c
index 7bde0c4dfdbd..4c7257ecd2a6 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c
@@ -240,11 +240,12 @@ int main(int argc, char *argv[])
 	struct ucall uc;
 	int stage;
 
-	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
-
 	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
 	TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE));
 	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS));
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_DIRECT_TLBFLUSH));
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
 
 	hcall_page = vm_vaddr_alloc_pages(vm, 1);
 	memset(addr_gva2hva(vm, hcall_page), 0x0,  getpagesize());
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c b/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c
index e036db1f32b9..949e08e98f31 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c
@@ -43,6 +43,8 @@ int main(void)
 	uint64_t *outval;
 	struct ucall uc;
 
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_CPUID));
+
 	/* Verify if extended hypercalls are supported */
 	if (!kvm_cpuid_has(kvm_get_supported_hv_cpuid(),
 			   HV_ENABLE_EXTENDED_HYPERCALLS)) {
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
index 9f28aa276c4e..b923a285e96f 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
@@ -55,18 +55,18 @@ static void guest_msr(struct msr_data *msr)
 	if (msr->fault_expected)
 		__GUEST_ASSERT(vector == GP_VECTOR,
 			       "Expected #GP on %sMSR(0x%x), got vector '0x%x'",
-			       msr->idx, msr->write ? "WR" : "RD", vector);
+			       msr->write ? "WR" : "RD", msr->idx, vector);
 	else
 		__GUEST_ASSERT(!vector,
 			       "Expected success on %sMSR(0x%x), got vector '0x%x'",
-			       msr->idx, msr->write ? "WR" : "RD", vector);
+			       msr->write ? "WR" : "RD", msr->idx, vector);
 
 	if (vector || is_write_only_msr(msr->idx))
 		goto done;
 
 	if (msr->write)
 		__GUEST_ASSERT(!vector,
-			       "WRMSR(0x%x) to '0x%llx', RDMSR read '0x%llx'",
+			       "WRMSR(0x%x) to '0x%lx', RDMSR read '0x%lx'",
 			       msr->idx, msr->write_val, msr_val);
 
 	/* Invariant TSC bit appears when TSC invariant control MSR is written to */
@@ -102,11 +102,11 @@ static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall)
 	vector = __hyperv_hypercall(hcall->control, input, output, &res);
 	if (hcall->ud_expected) {
 		__GUEST_ASSERT(vector == UD_VECTOR,
-			       "Expected #UD for control '%u', got vector '0x%x'",
+			       "Expected #UD for control '%lu', got vector '0x%x'",
 			       hcall->control, vector);
 	} else {
 		__GUEST_ASSERT(!vector,
-			       "Expected no exception for control '%u', got vector '0x%x'",
+			       "Expected no exception for control '%lu', got vector '0x%x'",
 			       hcall->control, vector);
 		GUEST_ASSERT_EQ(res, hcall->expect);
 	}
@@ -454,7 +454,7 @@ static void guest_test_msrs_access(void)
 		case 44:
 			/* MSR is not available when CPUID feature bit is unset */
 			if (!has_invtsc)
-				continue;
+				goto next_stage;
 			msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL;
 			msr->write = false;
 			msr->fault_expected = true;
@@ -462,7 +462,7 @@ static void guest_test_msrs_access(void)
 		case 45:
 			/* MSR is vailable when CPUID feature bit is set */
 			if (!has_invtsc)
-				continue;
+				goto next_stage;
 			vcpu_set_cpuid_feature(vcpu, HV_ACCESS_TSC_INVARIANT);
 			msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL;
 			msr->write = false;
@@ -471,7 +471,7 @@ static void guest_test_msrs_access(void)
 		case 46:
 			/* Writing bits other than 0 is forbidden */
 			if (!has_invtsc)
-				continue;
+				goto next_stage;
 			msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL;
 			msr->write = true;
 			msr->write_val = 0xdeadbeef;
@@ -480,7 +480,7 @@ static void guest_test_msrs_access(void)
 		case 47:
 			/* Setting bit 0 enables the feature */
 			if (!has_invtsc)
-				continue;
+				goto next_stage;
 			msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL;
 			msr->write = true;
 			msr->write_val = 1;
@@ -513,6 +513,7 @@ static void guest_test_msrs_access(void)
 			return;
 		}
 
+next_stage:
 		stage++;
 		kvm_vm_free(vm);
 	}
@@ -690,6 +691,8 @@ static void guest_test_hcalls_access(void)
 
 int main(void)
 {
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_ENFORCE_CPUID));
+
 	pr_info("Testing access to Hyper-V specific MSRs\n");
 	guest_test_msrs_access();
 
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
index 6feb5ddb031d..f1617762c22f 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
@@ -248,6 +248,8 @@ int main(int argc, char *argv[])
 	int stage = 1, r;
 	struct ucall uc;
 
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_SEND_IPI));
+
 	vm = vm_create_with_one_vcpu(&vcpu[0], sender_guest_code);
 
 	/* Hypercall input/output */
@@ -287,7 +289,7 @@ int main(int argc, char *argv[])
 		switch (get_ucall(vcpu[0], &uc)) {
 		case UCALL_SYNC:
 			TEST_ASSERT(uc.args[1] == stage,
-				    "Unexpected stage: %ld (%d expected)\n",
+				    "Unexpected stage: %ld (%d expected)",
 				    uc.args[1], stage);
 			break;
 		case UCALL_DONE:
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
index 6c1278562090..c9b18707edc0 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
@@ -158,6 +158,7 @@ int main(int argc, char *argv[])
 	int stage;
 
 	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM));
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_DIRECT_TLBFLUSH));
 
 	/* Create VM */
 	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c b/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c
index 4758b6ef5618..05b56095cf76 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c
@@ -590,6 +590,8 @@ int main(int argc, char *argv[])
 	struct ucall uc;
 	int stage = 1, r, i;
 
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_TLBFLUSH));
+
 	vm = vm_create_with_one_vcpu(&vcpu[0], sender_guest_code);
 
 	/* Test data page */
@@ -656,7 +658,7 @@ int main(int argc, char *argv[])
 		switch (get_ucall(vcpu[0], &uc)) {
 		case UCALL_SYNC:
 			TEST_ASSERT(uc.args[1] == stage,
-				    "Unexpected stage: %ld (%d expected)\n",
+				    "Unexpected stage: %ld (%d expected)",
 				    uc.args[1], stage);
 			break;
 		case UCALL_ABORT:
diff --git a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c b/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c
index 1778704360a6..5bc12222d87a 100644
--- a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c
+++ b/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c
@@ -92,7 +92,7 @@ static void setup_clock(struct kvm_vm *vm, struct test_case *test_case)
 				break;
 		} while (errno == EINTR);
 
-		TEST_ASSERT(!r, "clock_gettime() failed: %d\n", r);
+		TEST_ASSERT(!r, "clock_gettime() failed: %d", r);
 
 		data.realtime = ts.tv_sec * NSEC_PER_SEC;
 		data.realtime += ts.tv_nsec;
@@ -127,47 +127,11 @@ static void enter_guest(struct kvm_vcpu *vcpu)
 			handle_abort(&uc);
 			return;
 		default:
-			TEST_ASSERT(0, "unhandled ucall: %ld\n", uc.cmd);
+			TEST_ASSERT(0, "unhandled ucall: %ld", uc.cmd);
 		}
 	}
 }
 
-#define CLOCKSOURCE_PATH "/sys/devices/system/clocksource/clocksource0/current_clocksource"
-
-static void check_clocksource(void)
-{
-	char *clk_name;
-	struct stat st;
-	FILE *fp;
-
-	fp = fopen(CLOCKSOURCE_PATH, "r");
-	if (!fp) {
-		pr_info("failed to open clocksource file: %d; assuming TSC.\n",
-			errno);
-		return;
-	}
-
-	if (fstat(fileno(fp), &st)) {
-		pr_info("failed to stat clocksource file: %d; assuming TSC.\n",
-			errno);
-		goto out;
-	}
-
-	clk_name = malloc(st.st_size);
-	TEST_ASSERT(clk_name, "failed to allocate buffer to read file\n");
-
-	if (!fgets(clk_name, st.st_size, fp)) {
-		pr_info("failed to read clocksource file: %d; assuming TSC.\n",
-			ferror(fp));
-		goto out;
-	}
-
-	TEST_ASSERT(!strncmp(clk_name, "tsc\n", st.st_size),
-		    "clocksource not supported: %s", clk_name);
-out:
-	fclose(fp);
-}
-
 int main(void)
 {
 	struct kvm_vcpu *vcpu;
@@ -179,7 +143,7 @@ int main(void)
 	flags = kvm_check_cap(KVM_CAP_ADJUST_CLOCK);
 	TEST_REQUIRE(flags & KVM_CLOCK_REALTIME);
 
-	check_clocksource();
+	TEST_REQUIRE(sys_clocksource_is_based_on_tsc());
 
 	vm = vm_create_with_one_vcpu(&vcpu, guest_main);
 
diff --git a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c
deleted file mode 100644
index ce1ccc4c1503..000000000000
--- a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c
+++ /dev/null
@@ -1,121 +0,0 @@
-/*
- * mmio_warning_test
- *
- * Copyright (C) 2019, Google LLC.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- *
- * Test that we don't get a kernel warning when we call KVM_RUN after a
- * triple fault occurs.  To get the triple fault to occur we call KVM_RUN
- * on a VCPU that hasn't been properly setup.
- *
- */
-
-#define _GNU_SOURCE
-#include <fcntl.h>
-#include <kvm_util.h>
-#include <linux/kvm.h>
-#include <processor.h>
-#include <pthread.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <sys/ioctl.h>
-#include <sys/mman.h>
-#include <sys/stat.h>
-#include <sys/types.h>
-#include <sys/wait.h>
-#include <test_util.h>
-#include <unistd.h>
-
-#define NTHREAD 4
-#define NPROCESS 5
-
-struct thread_context {
-	int kvmcpu;
-	struct kvm_run *run;
-};
-
-void *thr(void *arg)
-{
-	struct thread_context *tc = (struct thread_context *)arg;
-	int res;
-	int kvmcpu = tc->kvmcpu;
-	struct kvm_run *run = tc->run;
-
-	res = ioctl(kvmcpu, KVM_RUN, 0);
-	pr_info("ret1=%d exit_reason=%d suberror=%d\n",
-		res, run->exit_reason, run->internal.suberror);
-
-	return 0;
-}
-
-void test(void)
-{
-	int i, kvm, kvmvm, kvmcpu;
-	pthread_t th[NTHREAD];
-	struct kvm_run *run;
-	struct thread_context tc;
-
-	kvm = open("/dev/kvm", O_RDWR);
-	TEST_ASSERT(kvm != -1, "failed to open /dev/kvm");
-	kvmvm = __kvm_ioctl(kvm, KVM_CREATE_VM, NULL);
-	TEST_ASSERT(kvmvm > 0, KVM_IOCTL_ERROR(KVM_CREATE_VM, kvmvm));
-	kvmcpu = ioctl(kvmvm, KVM_CREATE_VCPU, 0);
-	TEST_ASSERT(kvmcpu != -1, KVM_IOCTL_ERROR(KVM_CREATE_VCPU, kvmcpu));
-	run = (struct kvm_run *)mmap(0, 4096, PROT_READ|PROT_WRITE, MAP_SHARED,
-				    kvmcpu, 0);
-	tc.kvmcpu = kvmcpu;
-	tc.run = run;
-	srand(getpid());
-	for (i = 0; i < NTHREAD; i++) {
-		pthread_create(&th[i], NULL, thr, (void *)(uintptr_t)&tc);
-		usleep(rand() % 10000);
-	}
-	for (i = 0; i < NTHREAD; i++)
-		pthread_join(th[i], NULL);
-}
-
-int get_warnings_count(void)
-{
-	int warnings;
-	FILE *f;
-
-	f = popen("dmesg | grep \"WARNING:\" | wc -l", "r");
-	if (fscanf(f, "%d", &warnings) < 1)
-		warnings = 0;
-	pclose(f);
-
-	return warnings;
-}
-
-int main(void)
-{
-	int warnings_before, warnings_after;
-
-	TEST_REQUIRE(host_cpu_is_intel);
-
-	TEST_REQUIRE(!vm_is_unrestricted_guest(NULL));
-
-	warnings_before = get_warnings_count();
-
-	for (int i = 0; i < NPROCESS; ++i) {
-		int status;
-		int pid = fork();
-
-		if (pid < 0)
-			exit(1);
-		if (pid == 0) {
-			test();
-			exit(0);
-		}
-		while (waitpid(pid, &status, __WALL) != pid)
-			;
-	}
-
-	warnings_after = get_warnings_count();
-	TEST_ASSERT(warnings_before == warnings_after,
-		   "Warnings found in kernel.  Run 'dmesg' to inspect them.");
-
-	return 0;
-}
diff --git a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c
index 80aa3d8b18f8..853802641e1e 100644
--- a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c
+++ b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c
@@ -27,10 +27,12 @@ do {									\
 									\
 	if (fault_wanted)						\
 		__GUEST_ASSERT((vector) == UD_VECTOR,			\
-			       "Expected #UD on " insn " for testcase '0x%x', got '0x%x'", vector); \
+			       "Expected #UD on " insn " for testcase '0x%x', got '0x%x'", \
+			       testcase, vector);			\
 	else								\
 		__GUEST_ASSERT(!(vector),				\
-			       "Expected success on " insn " for testcase '0x%x', got '0x%x'", vector); \
+			       "Expected success on " insn " for testcase '0x%x', got '0x%x'", \
+			       testcase, vector);			\
 } while (0)
 
 static void guest_monitor_wait(int testcase)
diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
index 83e25bccc139..17bbb96fc4df 100644
--- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
+++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
@@ -257,9 +257,9 @@ int main(int argc, char **argv)
 	TEST_REQUIRE(kvm_has_cap(KVM_CAP_VM_DISABLE_NX_HUGE_PAGES));
 
 	__TEST_REQUIRE(token == MAGIC_TOKEN,
-		       "This test must be run with the magic token %d.\n"
-		       "This is done by nx_huge_pages_test.sh, which\n"
-		       "also handles environment setup for the test.", MAGIC_TOKEN);
+		       "This test must be run with the magic token via '-t %d'.\n"
+		       "Running via nx_huge_pages_test.sh, which also handles "
+		       "environment setup, is strongly recommended.", MAGIC_TOKEN);
 
 	run_test(reclaim_period_ms, false, reboot_permissions);
 	run_test(reclaim_period_ms, true, reboot_permissions);
diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
index c9a07963d68a..87011965dc41 100644
--- a/tools/testing/selftests/kvm/x86_64/platform_info_test.c
+++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
@@ -44,7 +44,7 @@ static void test_msr_platform_info_enabled(struct kvm_vcpu *vcpu)
 
 	get_ucall(vcpu, &uc);
 	TEST_ASSERT(uc.cmd == UCALL_SYNC,
-			"Received ucall other than UCALL_SYNC: %lu\n", uc.cmd);
+			"Received ucall other than UCALL_SYNC: %lu", uc.cmd);
 	TEST_ASSERT((uc.args[1] & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) ==
 		MSR_PLATFORM_INFO_MAX_TURBO_RATIO,
 		"Expected MSR_PLATFORM_INFO to have max turbo ratio mask: %i.",
diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
index 283cc55597a4..a3bd54b925ab 100644
--- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
+++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
@@ -866,7 +866,7 @@ static void __test_fixed_counter_bitmap(struct kvm_vcpu *vcpu, uint8_t idx,
 	 * userspace doesn't set any pmu filter.
 	 */
 	count = run_vcpu_to_sync(vcpu);
-	TEST_ASSERT(count, "Unexpected count value: %ld\n", count);
+	TEST_ASSERT(count, "Unexpected count value: %ld", count);
 
 	for (i = 0; i < BIT(nr_fixed_counters); i++) {
 		bitmap = BIT(i);
diff --git a/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c b/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c
new file mode 100644
index 000000000000..65ad38b6be1f
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c
@@ -0,0 +1,482 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022, Google LLC.
+ */
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <limits.h>
+#include <pthread.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/kvm_para.h>
+#include <linux/memfd.h>
+#include <linux/sizes.h>
+
+#include <test_util.h>
+#include <kvm_util.h>
+#include <processor.h>
+
+#define BASE_DATA_SLOT		10
+#define BASE_DATA_GPA		((uint64_t)(1ull << 32))
+#define PER_CPU_DATA_SIZE	((uint64_t)(SZ_2M + PAGE_SIZE))
+
+/* Horrific macro so that the line info is captured accurately :-( */
+#define memcmp_g(gpa, pattern,  size)								\
+do {												\
+	uint8_t *mem = (uint8_t *)gpa;								\
+	size_t i;										\
+												\
+	for (i = 0; i < size; i++)								\
+		__GUEST_ASSERT(mem[i] == pattern,						\
+			       "Guest expected 0x%x at offset %lu (gpa 0x%lx), got 0x%x",	\
+			       pattern, i, gpa + i, mem[i]);					\
+} while (0)
+
+static void memcmp_h(uint8_t *mem, uint64_t gpa, uint8_t pattern, size_t size)
+{
+	size_t i;
+
+	for (i = 0; i < size; i++)
+		TEST_ASSERT(mem[i] == pattern,
+			    "Host expected 0x%x at gpa 0x%lx, got 0x%x",
+			    pattern, gpa + i, mem[i]);
+}
+
+/*
+ * Run memory conversion tests with explicit conversion:
+ * Execute KVM hypercall to map/unmap gpa range which will cause userspace exit
+ * to back/unback private memory. Subsequent accesses by guest to the gpa range
+ * will not cause exit to userspace.
+ *
+ * Test memory conversion scenarios with following steps:
+ * 1) Access private memory using private access and verify that memory contents
+ *   are not visible to userspace.
+ * 2) Convert memory to shared using explicit conversions and ensure that
+ *   userspace is able to access the shared regions.
+ * 3) Convert memory back to private using explicit conversions and ensure that
+ *   userspace is again not able to access converted private regions.
+ */
+
+#define GUEST_STAGE(o, s) { .offset = o, .size = s }
+
+enum ucall_syncs {
+	SYNC_SHARED,
+	SYNC_PRIVATE,
+};
+
+static void guest_sync_shared(uint64_t gpa, uint64_t size,
+			      uint8_t current_pattern, uint8_t new_pattern)
+{
+	GUEST_SYNC5(SYNC_SHARED, gpa, size, current_pattern, new_pattern);
+}
+
+static void guest_sync_private(uint64_t gpa, uint64_t size, uint8_t pattern)
+{
+	GUEST_SYNC4(SYNC_PRIVATE, gpa, size, pattern);
+}
+
+/* Arbitrary values, KVM doesn't care about the attribute flags. */
+#define MAP_GPA_SET_ATTRIBUTES	BIT(0)
+#define MAP_GPA_SHARED		BIT(1)
+#define MAP_GPA_DO_FALLOCATE	BIT(2)
+
+static void guest_map_mem(uint64_t gpa, uint64_t size, bool map_shared,
+			  bool do_fallocate)
+{
+	uint64_t flags = MAP_GPA_SET_ATTRIBUTES;
+
+	if (map_shared)
+		flags |= MAP_GPA_SHARED;
+	if (do_fallocate)
+		flags |= MAP_GPA_DO_FALLOCATE;
+	kvm_hypercall_map_gpa_range(gpa, size, flags);
+}
+
+static void guest_map_shared(uint64_t gpa, uint64_t size, bool do_fallocate)
+{
+	guest_map_mem(gpa, size, true, do_fallocate);
+}
+
+static void guest_map_private(uint64_t gpa, uint64_t size, bool do_fallocate)
+{
+	guest_map_mem(gpa, size, false, do_fallocate);
+}
+
+struct {
+	uint64_t offset;
+	uint64_t size;
+} static const test_ranges[] = {
+	GUEST_STAGE(0, PAGE_SIZE),
+	GUEST_STAGE(0, SZ_2M),
+	GUEST_STAGE(PAGE_SIZE, PAGE_SIZE),
+	GUEST_STAGE(PAGE_SIZE, SZ_2M),
+	GUEST_STAGE(SZ_2M, PAGE_SIZE),
+};
+
+static void guest_test_explicit_conversion(uint64_t base_gpa, bool do_fallocate)
+{
+	const uint8_t def_p = 0xaa;
+	const uint8_t init_p = 0xcc;
+	uint64_t j;
+	int i;
+
+	/* Memory should be shared by default. */
+	memset((void *)base_gpa, def_p, PER_CPU_DATA_SIZE);
+	memcmp_g(base_gpa, def_p, PER_CPU_DATA_SIZE);
+	guest_sync_shared(base_gpa, PER_CPU_DATA_SIZE, def_p, init_p);
+
+	memcmp_g(base_gpa, init_p, PER_CPU_DATA_SIZE);
+
+	for (i = 0; i < ARRAY_SIZE(test_ranges); i++) {
+		uint64_t gpa = base_gpa + test_ranges[i].offset;
+		uint64_t size = test_ranges[i].size;
+		uint8_t p1 = 0x11;
+		uint8_t p2 = 0x22;
+		uint8_t p3 = 0x33;
+		uint8_t p4 = 0x44;
+
+		/*
+		 * Set the test region to pattern one to differentiate it from
+		 * the data range as a whole (contains the initial pattern).
+		 */
+		memset((void *)gpa, p1, size);
+
+		/*
+		 * Convert to private, set and verify the private data, and
+		 * then verify that the rest of the data (map shared) still
+		 * holds the initial pattern, and that the host always sees the
+		 * shared memory (initial pattern).  Unlike shared memory,
+		 * punching a hole in private memory is destructive, i.e.
+		 * previous values aren't guaranteed to be preserved.
+		 */
+		guest_map_private(gpa, size, do_fallocate);
+
+		if (size > PAGE_SIZE) {
+			memset((void *)gpa, p2, PAGE_SIZE);
+			goto skip;
+		}
+
+		memset((void *)gpa, p2, size);
+		guest_sync_private(gpa, size, p1);
+
+		/*
+		 * Verify that the private memory was set to pattern two, and
+		 * that shared memory still holds the initial pattern.
+		 */
+		memcmp_g(gpa, p2, size);
+		if (gpa > base_gpa)
+			memcmp_g(base_gpa, init_p, gpa - base_gpa);
+		if (gpa + size < base_gpa + PER_CPU_DATA_SIZE)
+			memcmp_g(gpa + size, init_p,
+				 (base_gpa + PER_CPU_DATA_SIZE) - (gpa + size));
+
+		/*
+		 * Convert odd-number page frames back to shared to verify KVM
+		 * also correctly handles holes in private ranges.
+		 */
+		for (j = 0; j < size; j += PAGE_SIZE) {
+			if ((j >> PAGE_SHIFT) & 1) {
+				guest_map_shared(gpa + j, PAGE_SIZE, do_fallocate);
+				guest_sync_shared(gpa + j, PAGE_SIZE, p1, p3);
+
+				memcmp_g(gpa + j, p3, PAGE_SIZE);
+			} else {
+				guest_sync_private(gpa + j, PAGE_SIZE, p1);
+			}
+		}
+
+skip:
+		/*
+		 * Convert the entire region back to shared, explicitly write
+		 * pattern three to fill in the even-number frames before
+		 * asking the host to verify (and write pattern four).
+		 */
+		guest_map_shared(gpa, size, do_fallocate);
+		memset((void *)gpa, p3, size);
+		guest_sync_shared(gpa, size, p3, p4);
+		memcmp_g(gpa, p4, size);
+
+		/* Reset the shared memory back to the initial pattern. */
+		memset((void *)gpa, init_p, size);
+
+		/*
+		 * Free (via PUNCH_HOLE) *all* private memory so that the next
+		 * iteration starts from a clean slate, e.g. with respect to
+		 * whether or not there are pages/folios in guest_mem.
+		 */
+		guest_map_shared(base_gpa, PER_CPU_DATA_SIZE, true);
+	}
+}
+
+static void guest_punch_hole(uint64_t gpa, uint64_t size)
+{
+	/* "Mapping" memory shared via fallocate() is done via PUNCH_HOLE. */
+	uint64_t flags = MAP_GPA_SHARED | MAP_GPA_DO_FALLOCATE;
+
+	kvm_hypercall_map_gpa_range(gpa, size, flags);
+}
+
+/*
+ * Test that PUNCH_HOLE actually frees memory by punching holes without doing a
+ * proper conversion.  Freeing (PUNCH_HOLE) should zap SPTEs, and reallocating
+ * (subsequent fault) should zero memory.
+ */
+static void guest_test_punch_hole(uint64_t base_gpa, bool precise)
+{
+	const uint8_t init_p = 0xcc;
+	int i;
+
+	/*
+	 * Convert the entire range to private, this testcase is all about
+	 * punching holes in guest_memfd, i.e. shared mappings aren't needed.
+	 */
+	guest_map_private(base_gpa, PER_CPU_DATA_SIZE, false);
+
+	for (i = 0; i < ARRAY_SIZE(test_ranges); i++) {
+		uint64_t gpa = base_gpa + test_ranges[i].offset;
+		uint64_t size = test_ranges[i].size;
+
+		/*
+		 * Free all memory before each iteration, even for the !precise
+		 * case where the memory will be faulted back in.  Freeing and
+		 * reallocating should obviously work, and freeing all memory
+		 * minimizes the probability of cross-testcase influence.
+		 */
+		guest_punch_hole(base_gpa, PER_CPU_DATA_SIZE);
+
+		/* Fault-in and initialize memory, and verify the pattern. */
+		if (precise) {
+			memset((void *)gpa, init_p, size);
+			memcmp_g(gpa, init_p, size);
+		} else {
+			memset((void *)base_gpa, init_p, PER_CPU_DATA_SIZE);
+			memcmp_g(base_gpa, init_p, PER_CPU_DATA_SIZE);
+		}
+
+		/*
+		 * Punch a hole at the target range and verify that reads from
+		 * the guest succeed and return zeroes.
+		 */
+		guest_punch_hole(gpa, size);
+		memcmp_g(gpa, 0, size);
+	}
+}
+
+static void guest_code(uint64_t base_gpa)
+{
+	/*
+	 * Run the conversion test twice, with and without doing fallocate() on
+	 * the guest_memfd backing when converting between shared and private.
+	 */
+	guest_test_explicit_conversion(base_gpa, false);
+	guest_test_explicit_conversion(base_gpa, true);
+
+	/*
+	 * Run the PUNCH_HOLE test twice too, once with the entire guest_memfd
+	 * faulted in, once with only the target range faulted in.
+	 */
+	guest_test_punch_hole(base_gpa, false);
+	guest_test_punch_hole(base_gpa, true);
+	GUEST_DONE();
+}
+
+static void handle_exit_hypercall(struct kvm_vcpu *vcpu)
+{
+	struct kvm_run *run = vcpu->run;
+	uint64_t gpa = run->hypercall.args[0];
+	uint64_t size = run->hypercall.args[1] * PAGE_SIZE;
+	bool set_attributes = run->hypercall.args[2] & MAP_GPA_SET_ATTRIBUTES;
+	bool map_shared = run->hypercall.args[2] & MAP_GPA_SHARED;
+	bool do_fallocate = run->hypercall.args[2] & MAP_GPA_DO_FALLOCATE;
+	struct kvm_vm *vm = vcpu->vm;
+
+	TEST_ASSERT(run->hypercall.nr == KVM_HC_MAP_GPA_RANGE,
+		    "Wanted MAP_GPA_RANGE (%u), got '%llu'",
+		    KVM_HC_MAP_GPA_RANGE, run->hypercall.nr);
+
+	if (do_fallocate)
+		vm_guest_mem_fallocate(vm, gpa, size, map_shared);
+
+	if (set_attributes)
+		vm_set_memory_attributes(vm, gpa, size,
+					 map_shared ? 0 : KVM_MEMORY_ATTRIBUTE_PRIVATE);
+	run->hypercall.ret = 0;
+}
+
+static bool run_vcpus;
+
+static void *__test_mem_conversions(void *__vcpu)
+{
+	struct kvm_vcpu *vcpu = __vcpu;
+	struct kvm_run *run = vcpu->run;
+	struct kvm_vm *vm = vcpu->vm;
+	struct ucall uc;
+
+	while (!READ_ONCE(run_vcpus))
+		;
+
+	for ( ;; ) {
+		vcpu_run(vcpu);
+
+		if (run->exit_reason == KVM_EXIT_HYPERCALL) {
+			handle_exit_hypercall(vcpu);
+			continue;
+		}
+
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Wanted KVM_EXIT_IO, got exit reason: %u (%s)",
+			    run->exit_reason, exit_reason_str(run->exit_reason));
+
+		switch (get_ucall(vcpu, &uc)) {
+		case UCALL_ABORT:
+			REPORT_GUEST_ASSERT(uc);
+		case UCALL_SYNC: {
+			uint64_t gpa  = uc.args[1];
+			size_t size = uc.args[2];
+			size_t i;
+
+			TEST_ASSERT(uc.args[0] == SYNC_SHARED ||
+				    uc.args[0] == SYNC_PRIVATE,
+				    "Unknown sync command '%ld'", uc.args[0]);
+
+			for (i = 0; i < size; i += vm->page_size) {
+				size_t nr_bytes = min_t(size_t, vm->page_size, size - i);
+				uint8_t *hva = addr_gpa2hva(vm, gpa + i);
+
+				/* In all cases, the host should observe the shared data. */
+				memcmp_h(hva, gpa + i, uc.args[3], nr_bytes);
+
+				/* For shared, write the new pattern to guest memory. */
+				if (uc.args[0] == SYNC_SHARED)
+					memset(hva, uc.args[4], nr_bytes);
+			}
+			break;
+		}
+		case UCALL_DONE:
+			return NULL;
+		default:
+			TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd);
+		}
+	}
+}
+
+static void test_mem_conversions(enum vm_mem_backing_src_type src_type, uint32_t nr_vcpus,
+				 uint32_t nr_memslots)
+{
+	/*
+	 * Allocate enough memory so that each vCPU's chunk of memory can be
+	 * naturally aligned with respect to the size of the backing store.
+	 */
+	const size_t alignment = max_t(size_t, SZ_2M, get_backing_src_pagesz(src_type));
+	const size_t per_cpu_size = align_up(PER_CPU_DATA_SIZE, alignment);
+	const size_t memfd_size = per_cpu_size * nr_vcpus;
+	const size_t slot_size = memfd_size / nr_memslots;
+	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
+	pthread_t threads[KVM_MAX_VCPUS];
+	struct kvm_vm *vm;
+	int memfd, i, r;
+
+	const struct vm_shape shape = {
+		.mode = VM_MODE_DEFAULT,
+		.type = KVM_X86_SW_PROTECTED_VM,
+	};
+
+	TEST_ASSERT(slot_size * nr_memslots == memfd_size,
+		    "The memfd size (0x%lx) needs to be cleanly divisible by the number of memslots (%u)",
+		    memfd_size, nr_memslots);
+	vm = __vm_create_with_vcpus(shape, nr_vcpus, 0, guest_code, vcpus);
+
+	vm_enable_cap(vm, KVM_CAP_EXIT_HYPERCALL, (1 << KVM_HC_MAP_GPA_RANGE));
+
+	memfd = vm_create_guest_memfd(vm, memfd_size, 0);
+
+	for (i = 0; i < nr_memslots; i++)
+		vm_mem_add(vm, src_type, BASE_DATA_GPA + slot_size * i,
+			   BASE_DATA_SLOT + i, slot_size / vm->page_size,
+			   KVM_MEM_GUEST_MEMFD, memfd, slot_size * i);
+
+	for (i = 0; i < nr_vcpus; i++) {
+		uint64_t gpa =  BASE_DATA_GPA + i * per_cpu_size;
+
+		vcpu_args_set(vcpus[i], 1, gpa);
+
+		/*
+		 * Map only what is needed so that an out-of-bounds access
+		 * results #PF => SHUTDOWN instead of data corruption.
+		 */
+		virt_map(vm, gpa, gpa, PER_CPU_DATA_SIZE / vm->page_size);
+
+		pthread_create(&threads[i], NULL, __test_mem_conversions, vcpus[i]);
+	}
+
+	WRITE_ONCE(run_vcpus, true);
+
+	for (i = 0; i < nr_vcpus; i++)
+		pthread_join(threads[i], NULL);
+
+	kvm_vm_free(vm);
+
+	/*
+	 * Allocate and free memory from the guest_memfd after closing the VM
+	 * fd.  The guest_memfd is gifted a reference to its owning VM, i.e.
+	 * should prevent the VM from being fully destroyed until the last
+	 * reference to the guest_memfd is also put.
+	 */
+	r = fallocate(memfd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, memfd_size);
+	TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r));
+
+	r = fallocate(memfd, FALLOC_FL_KEEP_SIZE, 0, memfd_size);
+	TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r));
+}
+
+static void usage(const char *cmd)
+{
+	puts("");
+	printf("usage: %s [-h] [-m nr_memslots] [-s mem_type] [-n nr_vcpus]\n", cmd);
+	puts("");
+	backing_src_help("-s");
+	puts("");
+	puts(" -n: specify the number of vcpus (default: 1)");
+	puts("");
+	puts(" -m: specify the number of memslots (default: 1)");
+	puts("");
+}
+
+int main(int argc, char *argv[])
+{
+	enum vm_mem_backing_src_type src_type = DEFAULT_VM_MEM_SRC;
+	uint32_t nr_memslots = 1;
+	uint32_t nr_vcpus = 1;
+	int opt;
+
+	TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM));
+
+	while ((opt = getopt(argc, argv, "hm:s:n:")) != -1) {
+		switch (opt) {
+		case 's':
+			src_type = parse_backing_src_type(optarg);
+			break;
+		case 'n':
+			nr_vcpus = atoi_positive("nr_vcpus", optarg);
+			break;
+		case 'm':
+			nr_memslots = atoi_positive("nr_memslots", optarg);
+			break;
+		case 'h':
+		default:
+			usage(argv[0]);
+			exit(0);
+		}
+	}
+
+	test_mem_conversions(src_type, nr_vcpus, nr_memslots);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/private_mem_kvm_exits_test.c b/tools/testing/selftests/kvm/x86_64/private_mem_kvm_exits_test.c
new file mode 100644
index 000000000000..13e72fcec8dd
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/private_mem_kvm_exits_test.c
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023, Google LLC.
+ */
+#include <linux/kvm.h>
+#include <pthread.h>
+#include <stdint.h>
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "test_util.h"
+
+/* Arbitrarily selected to avoid overlaps with anything else */
+#define EXITS_TEST_GVA 0xc0000000
+#define EXITS_TEST_GPA EXITS_TEST_GVA
+#define EXITS_TEST_NPAGES 1
+#define EXITS_TEST_SIZE (EXITS_TEST_NPAGES * PAGE_SIZE)
+#define EXITS_TEST_SLOT 10
+
+static uint64_t guest_repeatedly_read(void)
+{
+	volatile uint64_t value;
+
+	while (true)
+		value = *((uint64_t *) EXITS_TEST_GVA);
+
+	return value;
+}
+
+static uint32_t run_vcpu_get_exit_reason(struct kvm_vcpu *vcpu)
+{
+	int r;
+
+	r = _vcpu_run(vcpu);
+	if (r) {
+		TEST_ASSERT(errno == EFAULT, KVM_IOCTL_ERROR(KVM_RUN, r));
+		TEST_ASSERT_EQ(vcpu->run->exit_reason, KVM_EXIT_MEMORY_FAULT);
+	}
+	return vcpu->run->exit_reason;
+}
+
+const struct vm_shape protected_vm_shape = {
+	.mode = VM_MODE_DEFAULT,
+	.type = KVM_X86_SW_PROTECTED_VM,
+};
+
+static void test_private_access_memslot_deleted(void)
+{
+	struct kvm_vm *vm;
+	struct kvm_vcpu *vcpu;
+	pthread_t vm_thread;
+	void *thread_return;
+	uint32_t exit_reason;
+
+	vm = vm_create_shape_with_one_vcpu(protected_vm_shape, &vcpu,
+					   guest_repeatedly_read);
+
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+				    EXITS_TEST_GPA, EXITS_TEST_SLOT,
+				    EXITS_TEST_NPAGES,
+				    KVM_MEM_GUEST_MEMFD);
+
+	virt_map(vm, EXITS_TEST_GVA, EXITS_TEST_GPA, EXITS_TEST_NPAGES);
+
+	/* Request to access page privately */
+	vm_mem_set_private(vm, EXITS_TEST_GPA, EXITS_TEST_SIZE);
+
+	pthread_create(&vm_thread, NULL,
+		       (void *(*)(void *))run_vcpu_get_exit_reason,
+		       (void *)vcpu);
+
+	vm_mem_region_delete(vm, EXITS_TEST_SLOT);
+
+	pthread_join(vm_thread, &thread_return);
+	exit_reason = (uint32_t)(uint64_t)thread_return;
+
+	TEST_ASSERT_EQ(exit_reason, KVM_EXIT_MEMORY_FAULT);
+	TEST_ASSERT_EQ(vcpu->run->memory_fault.flags, KVM_MEMORY_EXIT_FLAG_PRIVATE);
+	TEST_ASSERT_EQ(vcpu->run->memory_fault.gpa, EXITS_TEST_GPA);
+	TEST_ASSERT_EQ(vcpu->run->memory_fault.size, EXITS_TEST_SIZE);
+
+	kvm_vm_free(vm);
+}
+
+static void test_private_access_memslot_not_private(void)
+{
+	struct kvm_vm *vm;
+	struct kvm_vcpu *vcpu;
+	uint32_t exit_reason;
+
+	vm = vm_create_shape_with_one_vcpu(protected_vm_shape, &vcpu,
+					   guest_repeatedly_read);
+
+	/* Add a non-private memslot (flags = 0) */
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+				    EXITS_TEST_GPA, EXITS_TEST_SLOT,
+				    EXITS_TEST_NPAGES, 0);
+
+	virt_map(vm, EXITS_TEST_GVA, EXITS_TEST_GPA, EXITS_TEST_NPAGES);
+
+	/* Request to access page privately */
+	vm_mem_set_private(vm, EXITS_TEST_GPA, EXITS_TEST_SIZE);
+
+	exit_reason = run_vcpu_get_exit_reason(vcpu);
+
+	TEST_ASSERT_EQ(exit_reason, KVM_EXIT_MEMORY_FAULT);
+	TEST_ASSERT_EQ(vcpu->run->memory_fault.flags, KVM_MEMORY_EXIT_FLAG_PRIVATE);
+	TEST_ASSERT_EQ(vcpu->run->memory_fault.gpa, EXITS_TEST_GPA);
+	TEST_ASSERT_EQ(vcpu->run->memory_fault.size, EXITS_TEST_SIZE);
+
+	kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
+	TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM));
+
+	test_private_access_memslot_deleted();
+	test_private_access_memslot_not_private();
+}
diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
index c7ef97561038..a49828adf294 100644
--- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
+++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
@@ -91,7 +91,7 @@ static void sev_migrate_from(struct kvm_vm *dst, struct kvm_vm *src)
 	int ret;
 
 	ret = __sev_migrate_from(dst, src);
-	TEST_ASSERT(!ret, "Migration failed, ret: %d, errno: %d\n", ret, errno);
+	TEST_ASSERT(!ret, "Migration failed, ret: %d, errno: %d", ret, errno);
 }
 
 static void test_sev_migrate_from(bool es)
@@ -113,7 +113,7 @@ static void test_sev_migrate_from(bool es)
 	/* Migrate the guest back to the original VM. */
 	ret = __sev_migrate_from(src_vm, dst_vms[NR_MIGRATE_TEST_VMS - 1]);
 	TEST_ASSERT(ret == -1 && errno == EIO,
-		    "VM that was migrated from should be dead. ret %d, errno: %d\n", ret,
+		    "VM that was migrated from should be dead. ret %d, errno: %d", ret,
 		    errno);
 
 	kvm_vm_free(src_vm);
@@ -172,7 +172,7 @@ static void test_sev_migrate_parameters(void)
 	vm_no_sev = aux_vm_create(true);
 	ret = __sev_migrate_from(vm_no_vcpu, vm_no_sev);
 	TEST_ASSERT(ret == -1 && errno == EINVAL,
-		    "Migrations require SEV enabled. ret %d, errno: %d\n", ret,
+		    "Migrations require SEV enabled. ret %d, errno: %d", ret,
 		    errno);
 
 	if (!have_sev_es)
@@ -187,25 +187,25 @@ static void test_sev_migrate_parameters(void)
 	ret = __sev_migrate_from(sev_vm, sev_es_vm);
 	TEST_ASSERT(
 		ret == -1 && errno == EINVAL,
-		"Should not be able migrate to SEV enabled VM. ret: %d, errno: %d\n",
+		"Should not be able migrate to SEV enabled VM. ret: %d, errno: %d",
 		ret, errno);
 
 	ret = __sev_migrate_from(sev_es_vm, sev_vm);
 	TEST_ASSERT(
 		ret == -1 && errno == EINVAL,
-		"Should not be able migrate to SEV-ES enabled VM. ret: %d, errno: %d\n",
+		"Should not be able migrate to SEV-ES enabled VM. ret: %d, errno: %d",
 		ret, errno);
 
 	ret = __sev_migrate_from(vm_no_vcpu, sev_es_vm);
 	TEST_ASSERT(
 		ret == -1 && errno == EINVAL,
-		"SEV-ES migrations require same number of vCPUS. ret: %d, errno: %d\n",
+		"SEV-ES migrations require same number of vCPUS. ret: %d, errno: %d",
 		ret, errno);
 
 	ret = __sev_migrate_from(vm_no_vcpu, sev_es_vm_no_vmsa);
 	TEST_ASSERT(
 		ret == -1 && errno == EINVAL,
-		"SEV-ES migrations require UPDATE_VMSA. ret %d, errno: %d\n",
+		"SEV-ES migrations require UPDATE_VMSA. ret %d, errno: %d",
 		ret, errno);
 
 	kvm_vm_free(sev_vm);
@@ -227,7 +227,7 @@ static void sev_mirror_create(struct kvm_vm *dst, struct kvm_vm *src)
 	int ret;
 
 	ret = __sev_mirror_create(dst, src);
-	TEST_ASSERT(!ret, "Copying context failed, ret: %d, errno: %d\n", ret, errno);
+	TEST_ASSERT(!ret, "Copying context failed, ret: %d, errno: %d", ret, errno);
 }
 
 static void verify_mirror_allowed_cmds(int vm_fd)
@@ -259,7 +259,7 @@ static void verify_mirror_allowed_cmds(int vm_fd)
 		ret = __sev_ioctl(vm_fd, cmd_id, NULL, &fw_error);
 		TEST_ASSERT(
 			ret == -1 && errno == EINVAL,
-			"Should not be able call command: %d. ret: %d, errno: %d\n",
+			"Should not be able call command: %d. ret: %d, errno: %d",
 			cmd_id, ret, errno);
 	}
 
@@ -301,18 +301,18 @@ static void test_sev_mirror_parameters(void)
 	ret = __sev_mirror_create(sev_vm, sev_vm);
 	TEST_ASSERT(
 		ret == -1 && errno == EINVAL,
-		"Should not be able copy context to self. ret: %d, errno: %d\n",
+		"Should not be able copy context to self. ret: %d, errno: %d",
 		ret, errno);
 
 	ret = __sev_mirror_create(vm_no_vcpu, vm_with_vcpu);
 	TEST_ASSERT(ret == -1 && errno == EINVAL,
-		    "Copy context requires SEV enabled. ret %d, errno: %d\n", ret,
+		    "Copy context requires SEV enabled. ret %d, errno: %d", ret,
 		    errno);
 
 	ret = __sev_mirror_create(vm_with_vcpu, sev_vm);
 	TEST_ASSERT(
 		ret == -1 && errno == EINVAL,
-		"SEV copy context requires no vCPUS on the destination. ret: %d, errno: %d\n",
+		"SEV copy context requires no vCPUS on the destination. ret: %d, errno: %d",
 		ret, errno);
 
 	if (!have_sev_es)
@@ -322,13 +322,13 @@ static void test_sev_mirror_parameters(void)
 	ret = __sev_mirror_create(sev_vm, sev_es_vm);
 	TEST_ASSERT(
 		ret == -1 && errno == EINVAL,
-		"Should not be able copy context to SEV enabled VM. ret: %d, errno: %d\n",
+		"Should not be able copy context to SEV enabled VM. ret: %d, errno: %d",
 		ret, errno);
 
 	ret = __sev_mirror_create(sev_es_vm, sev_vm);
 	TEST_ASSERT(
 		ret == -1 && errno == EINVAL,
-		"Should not be able copy context to SEV-ES enabled VM. ret: %d, errno: %d\n",
+		"Should not be able copy context to SEV-ES enabled VM. ret: %d, errno: %d",
 		ret, errno);
 
 	kvm_vm_free(sev_es_vm);
diff --git a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c b/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c
index 06edf00a97d6..1a46dd7bb391 100644
--- a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c
+++ b/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c
@@ -74,7 +74,7 @@ int main(int argc, char *argv[])
 				    MEM_REGION_SIZE / PAGE_SIZE, 0);
 	gpa = vm_phy_pages_alloc(vm, MEM_REGION_SIZE / PAGE_SIZE,
 				 MEM_REGION_GPA, MEM_REGION_SLOT);
-	TEST_ASSERT(gpa == MEM_REGION_GPA, "Failed vm_phy_pages_alloc\n");
+	TEST_ASSERT(gpa == MEM_REGION_GPA, "Failed vm_phy_pages_alloc");
 	virt_map(vm, MEM_REGION_GVA, MEM_REGION_GPA, 1);
 	hva = addr_gpa2hva(vm, MEM_REGION_GPA);
 	memset(hva, 0, PAGE_SIZE);
@@ -102,7 +102,7 @@ int main(int argc, char *argv[])
 	case UCALL_DONE:
 		break;
 	default:
-		TEST_FAIL("Unrecognized ucall: %lu\n", uc.cmd);
+		TEST_FAIL("Unrecognized ucall: %lu", uc.cmd);
 	}
 
 	kvm_vm_free(vm);
diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
index 7ee44496cf97..0c7ce3d4e83a 100644
--- a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
+++ b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
@@ -103,7 +103,7 @@ static void l1_guest_code(struct svm_test_data *svm, uint64_t is_nmi, uint64_t i
 
 	run_guest(vmcb, svm->vmcb_gpa);
 	__GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL,
-		       "Expected VMMCAL #VMEXIT, got '0x%x', info1 = '0x%llx, info2 = '0x%llx'",
+		       "Expected VMMCAL #VMEXIT, got '0x%x', info1 = '0x%lx, info2 = '0x%lx'",
 		       vmcb->control.exit_code,
 		       vmcb->control.exit_info_1, vmcb->control.exit_info_2);
 
@@ -133,7 +133,7 @@ static void l1_guest_code(struct svm_test_data *svm, uint64_t is_nmi, uint64_t i
 
 	run_guest(vmcb, svm->vmcb_gpa);
 	__GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_HLT,
-		       "Expected HLT #VMEXIT, got '0x%x', info1 = '0x%llx, info2 = '0x%llx'",
+		       "Expected HLT #VMEXIT, got '0x%x', info1 = '0x%lx, info2 = '0x%lx'",
 		       vmcb->control.exit_code,
 		       vmcb->control.exit_info_1, vmcb->control.exit_info_2);
 
diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
index 00965ba33f73..a91b5b145fa3 100644
--- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
@@ -46,7 +46,7 @@ static void compare_regs(struct kvm_regs *left, struct kvm_regs *right)
 #define REG_COMPARE(reg) \
 	TEST_ASSERT(left->reg == right->reg, \
 		    "Register " #reg \
-		    " values did not match: 0x%llx, 0x%llx\n", \
+		    " values did not match: 0x%llx, 0x%llx", \
 		    left->reg, right->reg)
 	REG_COMPARE(rax);
 	REG_COMPARE(rbx);
@@ -230,14 +230,14 @@ int main(int argc, char *argv[])
 	run->kvm_valid_regs = INVALID_SYNC_FIELD;
 	rv = _vcpu_run(vcpu);
 	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d",
 		    rv);
 	run->kvm_valid_regs = 0;
 
 	run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
 	rv = _vcpu_run(vcpu);
 	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d",
 		    rv);
 	run->kvm_valid_regs = 0;
 
@@ -245,14 +245,14 @@ int main(int argc, char *argv[])
 	run->kvm_dirty_regs = INVALID_SYNC_FIELD;
 	rv = _vcpu_run(vcpu);
 	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d",
 		    rv);
 	run->kvm_dirty_regs = 0;
 
 	run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
 	rv = _vcpu_run(vcpu);
 	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d",
 		    rv);
 	run->kvm_dirty_regs = 0;
 
diff --git a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c
index 85f34ca7e49e..dcbb3c29fb8e 100644
--- a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c
+++ b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c
@@ -143,7 +143,7 @@ static void run_vcpu_expect_gp(struct kvm_vcpu *vcpu)
 
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 	TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_SYNC,
-		    "Expect UCALL_SYNC\n");
+		    "Expect UCALL_SYNC");
 	TEST_ASSERT(uc.args[1] == SYNC_GP, "#GP is expected.");
 	printf("vCPU received GP in guest.\n");
 }
@@ -188,7 +188,7 @@ static void *run_ucna_injection(void *arg)
 
 	TEST_ASSERT_KVM_EXIT_REASON(params->vcpu, KVM_EXIT_IO);
 	TEST_ASSERT(get_ucall(params->vcpu, &uc) == UCALL_SYNC,
-		    "Expect UCALL_SYNC\n");
+		    "Expect UCALL_SYNC");
 	TEST_ASSERT(uc.args[1] == SYNC_FIRST_UCNA, "Injecting first UCNA.");
 
 	printf("Injecting first UCNA at %#x.\n", FIRST_UCNA_ADDR);
@@ -198,7 +198,7 @@ static void *run_ucna_injection(void *arg)
 
 	TEST_ASSERT_KVM_EXIT_REASON(params->vcpu, KVM_EXIT_IO);
 	TEST_ASSERT(get_ucall(params->vcpu, &uc) == UCALL_SYNC,
-		    "Expect UCALL_SYNC\n");
+		    "Expect UCALL_SYNC");
 	TEST_ASSERT(uc.args[1] == SYNC_SECOND_UCNA, "Injecting second UCNA.");
 
 	printf("Injecting second UCNA at %#x.\n", SECOND_UCNA_ADDR);
@@ -208,7 +208,7 @@ static void *run_ucna_injection(void *arg)
 
 	TEST_ASSERT_KVM_EXIT_REASON(params->vcpu, KVM_EXIT_IO);
 	if (get_ucall(params->vcpu, &uc) == UCALL_ABORT) {
-		TEST_ASSERT(false, "vCPU assertion failure: %s.\n",
+		TEST_ASSERT(false, "vCPU assertion failure: %s.",
 			    (const char *)uc.args[0]);
 	}
 
@@ -271,7 +271,7 @@ int main(int argc, char *argv[])
 
 	kvm_check_cap(KVM_CAP_MCE);
 
-	vm = __vm_create(VM_MODE_DEFAULT, 3, 0);
+	vm = __vm_create(VM_SHAPE_DEFAULT, 3, 0);
 
 	kvm_ioctl(vm->kvm_fd, KVM_X86_GET_MCE_CAP_SUPPORTED,
 		  &supported_mcg_caps);
diff --git a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
index 255c50b0dc32..9481cbcf284f 100644
--- a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
+++ b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
@@ -71,7 +71,7 @@ int main(int argc, char *argv[])
 			break;
 
 		TEST_ASSERT(run->io.port == 0x80,
-			    "Expected I/O at port 0x80, got port 0x%x\n", run->io.port);
+			    "Expected I/O at port 0x80, got port 0x%x", run->io.port);
 
 		/*
 		 * Modify the rep string count in RCX: 2 => 1 and 3 => 8192.
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c
index 2bed5fb3a0d6..a81a24761aac 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c
@@ -99,7 +99,7 @@ int main(int argc, char *argv[])
 			TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_INTERNAL_ERROR);
 			TEST_ASSERT(run->internal.suberror ==
 				    KVM_INTERNAL_ERROR_EMULATION,
-				    "Got internal suberror other than KVM_INTERNAL_ERROR_EMULATION: %u\n",
+				    "Got internal suberror other than KVM_INTERNAL_ERROR_EMULATION: %u",
 				    run->internal.suberror);
 			break;
 		}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
index e4ad5fef52ff..7f6f5f23fb9b 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
@@ -128,17 +128,17 @@ int main(int argc, char *argv[])
 			 */
 			kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
 			if (uc.args[1]) {
-				TEST_ASSERT(test_bit(0, bmap), "Page 0 incorrectly reported clean\n");
-				TEST_ASSERT(host_test_mem[0] == 1, "Page 0 not written by guest\n");
+				TEST_ASSERT(test_bit(0, bmap), "Page 0 incorrectly reported clean");
+				TEST_ASSERT(host_test_mem[0] == 1, "Page 0 not written by guest");
 			} else {
-				TEST_ASSERT(!test_bit(0, bmap), "Page 0 incorrectly reported dirty\n");
-				TEST_ASSERT(host_test_mem[0] == 0xaaaaaaaaaaaaaaaaULL, "Page 0 written by guest\n");
+				TEST_ASSERT(!test_bit(0, bmap), "Page 0 incorrectly reported dirty");
+				TEST_ASSERT(host_test_mem[0] == 0xaaaaaaaaaaaaaaaaULL, "Page 0 written by guest");
 			}
 
-			TEST_ASSERT(!test_bit(1, bmap), "Page 1 incorrectly reported dirty\n");
-			TEST_ASSERT(host_test_mem[4096 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 1 written by guest\n");
-			TEST_ASSERT(!test_bit(2, bmap), "Page 2 incorrectly reported dirty\n");
-			TEST_ASSERT(host_test_mem[8192 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 2 written by guest\n");
+			TEST_ASSERT(!test_bit(1, bmap), "Page 1 incorrectly reported dirty");
+			TEST_ASSERT(host_test_mem[4096 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 1 written by guest");
+			TEST_ASSERT(!test_bit(2, bmap), "Page 2 incorrectly reported dirty");
+			TEST_ASSERT(host_test_mem[8192 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 2 written by guest");
 			break;
 		case UCALL_DONE:
 			done = true;
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c
index a9b827c69f32..fad3634fd9eb 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c
@@ -28,7 +28,7 @@ static void __run_vcpu_with_invalid_state(struct kvm_vcpu *vcpu)
 
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_INTERNAL_ERROR);
 	TEST_ASSERT(run->emulation_failure.suberror == KVM_INTERNAL_ERROR_EMULATION,
-		    "Expected emulation failure, got %d\n",
+		    "Expected emulation failure, got %d",
 		    run->emulation_failure.suberror);
 }
 
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c
index e710b6e7fb38..1759fa5cb3f2 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c
@@ -116,23 +116,6 @@ static void l1_guest_code(struct vmx_pages *vmx_pages)
 	GUEST_DONE();
 }
 
-static bool system_has_stable_tsc(void)
-{
-	bool tsc_is_stable;
-	FILE *fp;
-	char buf[4];
-
-	fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
-	if (fp == NULL)
-		return false;
-
-	tsc_is_stable = fgets(buf, sizeof(buf), fp) &&
-			!strncmp(buf, "tsc", sizeof(buf));
-
-	fclose(fp);
-	return tsc_is_stable;
-}
-
 int main(int argc, char *argv[])
 {
 	struct kvm_vcpu *vcpu;
@@ -148,7 +131,7 @@ int main(int argc, char *argv[])
 
 	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
 	TEST_REQUIRE(kvm_has_cap(KVM_CAP_TSC_CONTROL));
-	TEST_REQUIRE(system_has_stable_tsc());
+	TEST_REQUIRE(sys_clocksource_is_based_on_tsc());
 
 	/*
 	 * We set L1's scale factor to be a random number from 2 to 10.
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
index ebbcb0a3f743..2a8d4ac2f020 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
@@ -56,7 +56,7 @@ static void guest_test_perf_capabilities_gp(uint64_t val)
 	uint8_t vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, val);
 
 	__GUEST_ASSERT(vector == GP_VECTOR,
-		       "Expected #GP for value '0x%llx', got vector '0x%x'",
+		       "Expected #GP for value '0x%lx', got vector '0x%x'",
 		       val, vector);
 }
 
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
index 41ea7028a1f8..67a62a5a8895 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
@@ -125,21 +125,25 @@ void test_vmx_nested_state(struct kvm_vcpu *vcpu)
 
 	/*
 	 * Setting vmxon_pa == -1ull and vmcs_pa == -1ull exits early without
-	 * setting the nested state but flags other than eVMCS must be clear.
-	 * The eVMCS flag can be set if the enlightened VMCS capability has
-	 * been enabled.
+	 * setting the nested state. When the eVMCS flag is not set, the
+	 * expected return value is '0'.
 	 */
 	set_default_vmx_state(state, state_sz);
+	state->flags = 0;
 	state->hdr.vmx.vmxon_pa = -1ull;
 	state->hdr.vmx.vmcs12_pa = -1ull;
-	test_nested_state_expect_einval(vcpu, state);
+	test_nested_state(vcpu, state);
 
-	state->flags &= KVM_STATE_NESTED_EVMCS;
+	/*
+	 * When eVMCS is supported, the eVMCS flag can only be set if the
+	 * enlightened VMCS capability has been enabled.
+	 */
 	if (have_evmcs) {
+		state->flags = KVM_STATE_NESTED_EVMCS;
 		test_nested_state_expect_einval(vcpu, state);
 		vcpu_enable_evmcs(vcpu);
+		test_nested_state(vcpu, state);
 	}
-	test_nested_state(vcpu, state);
 
 	/* It is invalid to have vmxon_pa == -1ull and SMM flags non-zero. */
 	state->hdr.vmx.smm.flags = 1;
diff --git a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c
index 67ac2a3292ef..725c206ba0b9 100644
--- a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c
@@ -216,7 +216,7 @@ static void *vcpu_thread(void *arg)
 			    "Halting vCPU halted %lu times, woke %lu times, received %lu IPIs.\n"
 			    "Halter TPR=%#x PPR=%#x LVR=%#x\n"
 			    "Migrations attempted: %lu\n"
-			    "Migrations completed: %lu\n",
+			    "Migrations completed: %lu",
 			    vcpu->id, (const char *)uc.args[0],
 			    params->data->ipis_sent, params->data->hlt_count,
 			    params->data->wake_count,
@@ -288,7 +288,7 @@ void do_migrations(struct test_data_page *data, int run_secs, int delay_usecs,
 	}
 
 	TEST_ASSERT(nodes > 1,
-		    "Did not find at least 2 numa nodes. Can't do migration\n");
+		    "Did not find at least 2 numa nodes. Can't do migration");
 
 	fprintf(stderr, "Migrating amongst %d nodes found\n", nodes);
 
@@ -347,7 +347,7 @@ void do_migrations(struct test_data_page *data, int run_secs, int delay_usecs,
 				    wake_count != data->wake_count,
 				    "IPI, HLT and wake count have not increased "
 				    "in the last %lu seconds. "
-				    "HLTer is likely hung.\n", interval_secs);
+				    "HLTer is likely hung.", interval_secs);
 
 			ipis_sent = data->ipis_sent;
 			hlt_count = data->hlt_count;
@@ -381,7 +381,7 @@ void get_cmdline_args(int argc, char *argv[], int *run_secs,
 				    "-m adds calls to migrate_pages while vCPUs are running."
 				    " Default is no migrations.\n"
 				    "-d <delay microseconds> - delay between migrate_pages() calls."
-				    " Default is %d microseconds.\n",
+				    " Default is %d microseconds.",
 				    DEFAULT_RUN_SECS, DEFAULT_DELAY_USECS);
 		}
 	}
diff --git a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c
index 77d04a7bdadd..25a0b0db5c3c 100644
--- a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c
@@ -25,7 +25,7 @@ do {											\
 											\
 	__GUEST_ASSERT((__supported & (xfeatures)) != (xfeatures) ||			\
 		       __supported == ((xfeatures) | (dependencies)),			\
-		       "supported = 0x%llx, xfeatures = 0x%llx, dependencies = 0x%llx",	\
+		       "supported = 0x%lx, xfeatures = 0x%llx, dependencies = 0x%llx",	\
 		       __supported, (xfeatures), (dependencies));			\
 } while (0)
 
@@ -42,7 +42,7 @@ do {									\
 	uint64_t __supported = (supported_xcr0) & (xfeatures);		\
 									\
 	__GUEST_ASSERT(!__supported || __supported == (xfeatures),	\
-		       "supported = 0x%llx, xfeatures = 0x%llx",	\
+		       "supported = 0x%lx, xfeatures = 0x%llx",		\
 		       __supported, (xfeatures));			\
 } while (0)
 
@@ -81,7 +81,7 @@ static void guest_code(void)
 
 	vector = xsetbv_safe(0, supported_xcr0);
 	__GUEST_ASSERT(!vector,
-		       "Expected success on XSETBV(0x%llx), got vector '0x%x'",
+		       "Expected success on XSETBV(0x%lx), got vector '0x%x'",
 		       supported_xcr0, vector);
 
 	for (i = 0; i < 64; i++) {
@@ -90,7 +90,7 @@ static void guest_code(void)
 
 		vector = xsetbv_safe(0, supported_xcr0 | BIT_ULL(i));
 		__GUEST_ASSERT(vector == GP_VECTOR,
-			       "Expected #GP on XSETBV(0x%llx), supported XCR0 = %llx, got vector '0x%x'",
+			       "Expected #GP on XSETBV(0x%llx), supported XCR0 = %lx, got vector '0x%x'",
 			       BIT_ULL(i), supported_xcr0, vector);
 	}
 
@@ -116,7 +116,7 @@ int main(int argc, char *argv[])
 		vcpu_run(vcpu);
 
 		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-			    "Unexpected exit reason: %u (%s),\n",
+			    "Unexpected exit reason: %u (%s),",
 			    run->exit_reason,
 			    exit_reason_str(run->exit_reason));
 
diff --git a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c
index e0ddf47362e7..167c97abff1b 100644
--- a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c
@@ -29,7 +29,7 @@ int main(int argc, char *argv[])
 
 	xss_val = vcpu_get_msr(vcpu, MSR_IA32_XSS);
 	TEST_ASSERT(xss_val == 0,
-		    "MSR_IA32_XSS should be initialized to zero\n");
+		    "MSR_IA32_XSS should be initialized to zero");
 
 	vcpu_set_msr(vcpu, MSR_IA32_XSS, xss_val);
 
diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h
index 5b79758cae62..e64bbdf0e86e 100644
--- a/tools/testing/selftests/landlock/common.h
+++ b/tools/testing/selftests/landlock/common.h
@@ -9,6 +9,7 @@
 
 #include <errno.h>
 #include <linux/landlock.h>
+#include <linux/securebits.h>
 #include <sys/capability.h>
 #include <sys/socket.h>
 #include <sys/syscall.h>
@@ -115,11 +116,16 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all)
 		/* clang-format off */
 		CAP_DAC_OVERRIDE,
 		CAP_MKNOD,
+		CAP_NET_ADMIN,
+		CAP_NET_BIND_SERVICE,
 		CAP_SYS_ADMIN,
 		CAP_SYS_CHROOT,
-		CAP_NET_BIND_SERVICE,
 		/* clang-format on */
 	};
+	const unsigned int noroot = SECBIT_NOROOT | SECBIT_NOROOT_LOCKED;
+
+	if ((cap_get_secbits() & noroot) != noroot)
+		EXPECT_EQ(0, cap_set_secbits(noroot));
 
 	cap_p = cap_get_proc();
 	EXPECT_NE(NULL, cap_p)
@@ -137,6 +143,8 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all)
 			TH_LOG("Failed to cap_set_flag: %s", strerror(errno));
 		}
 	}
+
+	/* Automatically resets ambient capabilities. */
 	EXPECT_NE(-1, cap_set_proc(cap_p))
 	{
 		TH_LOG("Failed to cap_set_proc: %s", strerror(errno));
@@ -145,6 +153,9 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all)
 	{
 		TH_LOG("Failed to cap_free: %s", strerror(errno));
 	}
+
+	/* Quickly checks that ambient capabilities are cleared. */
+	EXPECT_NE(-1, cap_get_ambient(caps[0]));
 }
 
 /* We cannot put such helpers in a library because of kselftest_harness.h . */
@@ -158,8 +169,9 @@ static void __maybe_unused drop_caps(struct __test_metadata *const _metadata)
 	_init_caps(_metadata, true);
 }
 
-static void _effective_cap(struct __test_metadata *const _metadata,
-			   const cap_value_t caps, const cap_flag_value_t value)
+static void _change_cap(struct __test_metadata *const _metadata,
+			const cap_flag_t flag, const cap_value_t cap,
+			const cap_flag_value_t value)
 {
 	cap_t cap_p;
 
@@ -168,7 +180,7 @@ static void _effective_cap(struct __test_metadata *const _metadata,
 	{
 		TH_LOG("Failed to cap_get_proc: %s", strerror(errno));
 	}
-	EXPECT_NE(-1, cap_set_flag(cap_p, CAP_EFFECTIVE, 1, &caps, value))
+	EXPECT_NE(-1, cap_set_flag(cap_p, flag, 1, &cap, value))
 	{
 		TH_LOG("Failed to cap_set_flag: %s", strerror(errno));
 	}
@@ -183,15 +195,35 @@ static void _effective_cap(struct __test_metadata *const _metadata,
 }
 
 static void __maybe_unused set_cap(struct __test_metadata *const _metadata,
-				   const cap_value_t caps)
+				   const cap_value_t cap)
 {
-	_effective_cap(_metadata, caps, CAP_SET);
+	_change_cap(_metadata, CAP_EFFECTIVE, cap, CAP_SET);
 }
 
 static void __maybe_unused clear_cap(struct __test_metadata *const _metadata,
-				     const cap_value_t caps)
+				     const cap_value_t cap)
+{
+	_change_cap(_metadata, CAP_EFFECTIVE, cap, CAP_CLEAR);
+}
+
+static void __maybe_unused
+set_ambient_cap(struct __test_metadata *const _metadata, const cap_value_t cap)
+{
+	_change_cap(_metadata, CAP_INHERITABLE, cap, CAP_SET);
+
+	EXPECT_NE(-1, cap_set_ambient(cap, CAP_SET))
+	{
+		TH_LOG("Failed to set ambient capability %d: %s", cap,
+		       strerror(errno));
+	}
+}
+
+static void __maybe_unused clear_ambient_cap(
+	struct __test_metadata *const _metadata, const cap_value_t cap)
 {
-	_effective_cap(_metadata, caps, CAP_CLEAR);
+	EXPECT_EQ(1, cap_get_ambient(cap));
+	_change_cap(_metadata, CAP_INHERITABLE, cap, CAP_CLEAR);
+	EXPECT_EQ(0, cap_get_ambient(cap));
 }
 
 /* Receives an FD from a UNIX socket. Returns the received FD, or -errno. */
diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c
index 50818904397c..2d6d9b43d958 100644
--- a/tools/testing/selftests/landlock/fs_test.c
+++ b/tools/testing/selftests/landlock/fs_test.c
@@ -241,9 +241,11 @@ struct mnt_opt {
 	const char *const data;
 };
 
-const struct mnt_opt mnt_tmp = {
+#define MNT_TMP_DATA "size=4m,mode=700"
+
+static const struct mnt_opt mnt_tmp = {
 	.type = "tmpfs",
-	.data = "size=4m,mode=700",
+	.data = MNT_TMP_DATA,
 };
 
 static int mount_opt(const struct mnt_opt *const mnt, const char *const target)
@@ -4632,7 +4634,10 @@ FIXTURE_VARIANT(layout3_fs)
 /* clang-format off */
 FIXTURE_VARIANT_ADD(layout3_fs, tmpfs) {
 	/* clang-format on */
-	.mnt = mnt_tmp,
+	.mnt = {
+		.type = "tmpfs",
+		.data = MNT_TMP_DATA,
+	},
 	.file_path = file1_s1d1,
 };
 
diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c
index ea5f727dd257..936cfc879f1d 100644
--- a/tools/testing/selftests/landlock/net_test.c
+++ b/tools/testing/selftests/landlock/net_test.c
@@ -17,6 +17,7 @@
 #include <string.h>
 #include <sys/prctl.h>
 #include <sys/socket.h>
+#include <sys/syscall.h>
 #include <sys/un.h>
 
 #include "common.h"
@@ -54,6 +55,11 @@ struct service_fixture {
 	};
 };
 
+static pid_t sys_gettid(void)
+{
+	return syscall(__NR_gettid);
+}
+
 static int set_service(struct service_fixture *const srv,
 		       const struct protocol_variant prot,
 		       const unsigned short index)
@@ -88,7 +94,7 @@ static int set_service(struct service_fixture *const srv,
 	case AF_UNIX:
 		srv->unix_addr.sun_family = prot.domain;
 		sprintf(srv->unix_addr.sun_path,
-			"_selftests-landlock-net-tid%d-index%d", gettid(),
+			"_selftests-landlock-net-tid%d-index%d", sys_gettid(),
 			index);
 		srv->unix_addr_len = SUN_LEN(&srv->unix_addr);
 		srv->unix_addr.sun_path[0] = '\0';
@@ -101,8 +107,11 @@ static void setup_loopback(struct __test_metadata *const _metadata)
 {
 	set_cap(_metadata, CAP_SYS_ADMIN);
 	ASSERT_EQ(0, unshare(CLONE_NEWNET));
-	ASSERT_EQ(0, system("ip link set dev lo up"));
 	clear_cap(_metadata, CAP_SYS_ADMIN);
+
+	set_ambient_cap(_metadata, CAP_NET_ADMIN);
+	ASSERT_EQ(0, system("ip link set dev lo up"));
+	clear_ambient_cap(_metadata, CAP_NET_ADMIN);
 }
 
 static bool is_restricted(const struct protocol_variant *const prot,
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index aa646e0661f3..286ce0ee102b 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -58,7 +58,8 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS))
 TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED))
 TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES))
 
-all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
+all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) \
+	$(if $(TEST_GEN_MODS_DIR),gen_mods_dir)
 
 define RUN_TESTS
 	BASE_DIR="$(selfdir)";			\
@@ -71,8 +72,8 @@ endef
 
 run_tests: all
 ifdef building_out_of_srctree
-	@if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \
-		rsync -aq --copy-unsafe-links $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT); \
+	@if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)$(TEST_GEN_MODS_DIR)" != "X" ]; then \
+		rsync -aq --copy-unsafe-links $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(TEST_GEN_MODS_DIR) $(OUTPUT); \
 	fi
 	@if [ "X$(TEST_PROGS)" != "X" ]; then \
 		$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) \
@@ -84,11 +85,22 @@ else
 	@$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS))
 endif
 
+gen_mods_dir:
+	$(Q)$(MAKE) -C $(TEST_GEN_MODS_DIR)
+
+clean_mods_dir:
+	$(Q)$(MAKE) -C $(TEST_GEN_MODS_DIR) clean
+
 define INSTALL_SINGLE_RULE
 	$(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH))
 	$(if $(INSTALL_LIST),rsync -a --copy-unsafe-links $(INSTALL_LIST) $(INSTALL_PATH)/)
 endef
 
+define INSTALL_MODS_RULE
+	$(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH)/$(INSTALL_LIST))
+	$(if $(INSTALL_LIST),rsync -a --copy-unsafe-links $(INSTALL_LIST)/*.ko $(INSTALL_PATH)/$(INSTALL_LIST))
+endef
+
 define INSTALL_RULE
 	$(eval INSTALL_LIST = $(TEST_PROGS)) $(INSTALL_SINGLE_RULE)
 	$(eval INSTALL_LIST = $(TEST_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE)
@@ -97,6 +109,7 @@ define INSTALL_RULE
 	$(eval INSTALL_LIST = $(TEST_CUSTOM_PROGS)) $(INSTALL_SINGLE_RULE)
 	$(eval INSTALL_LIST = $(TEST_GEN_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE)
 	$(eval INSTALL_LIST = $(TEST_GEN_FILES)) $(INSTALL_SINGLE_RULE)
+	$(eval INSTALL_LIST = $(notdir $(TEST_GEN_MODS_DIR))) $(INSTALL_MODS_RULE)
 	$(eval INSTALL_LIST = $(wildcard config settings)) $(INSTALL_SINGLE_RULE)
 endef
 
@@ -122,7 +135,7 @@ define CLEAN
 	$(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN)
 endef
 
-clean:
+clean: $(if $(TEST_GEN_MODS_DIR),clean_mods_dir)
 	$(CLEAN)
 
 # Enables to extend CFLAGS and LDFLAGS from command line, e.g.
@@ -153,4 +166,4 @@ $(OUTPUT)/%:%.S
 	$(LINK.S) $^ $(LDLIBS) -o $@
 endif
 
-.PHONY: run_tests all clean install emit_tests
+.PHONY: run_tests all clean install emit_tests gen_mods_dir clean_mods_dir
diff --git a/tools/testing/selftests/livepatch/.gitignore b/tools/testing/selftests/livepatch/.gitignore
new file mode 100644
index 000000000000..f1e9c2a20e99
--- /dev/null
+++ b/tools/testing/selftests/livepatch/.gitignore
@@ -0,0 +1 @@
+test_klp-call_getpid
diff --git a/tools/testing/selftests/livepatch/Makefile b/tools/testing/selftests/livepatch/Makefile
index 02fadc9d55e0..35418a4790be 100644
--- a/tools/testing/selftests/livepatch/Makefile
+++ b/tools/testing/selftests/livepatch/Makefile
@@ -1,5 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
+TEST_GEN_FILES := test_klp-call_getpid
+TEST_GEN_MODS_DIR := test_modules
 TEST_PROGS_EXTENDED := functions.sh
 TEST_PROGS := \
 	test-livepatch.sh \
@@ -7,7 +9,8 @@ TEST_PROGS := \
 	test-shadow-vars.sh \
 	test-state.sh \
 	test-ftrace.sh \
-	test-sysfs.sh
+	test-sysfs.sh \
+	test-syscall.sh
 
 TEST_FILES := settings
 
diff --git a/tools/testing/selftests/livepatch/README b/tools/testing/selftests/livepatch/README
index 0942dd5826f8..d2035dd64a2b 100644
--- a/tools/testing/selftests/livepatch/README
+++ b/tools/testing/selftests/livepatch/README
@@ -13,23 +13,36 @@ the message buffer for only the duration of each individual test.)
 Config
 ------
 
-Set these config options and their prerequisites:
+Set CONFIG_LIVEPATCH=y option and it's prerequisites.
 
-CONFIG_LIVEPATCH=y
-CONFIG_TEST_LIVEPATCH=m
 
+Building the tests
+------------------
+
+To only build the tests without running them, run:
+
+  % make -C tools/testing/selftests/livepatch
+
+The command above will compile all test modules and test programs, making them
+ready to be packaged if so desired.
 
 Running the tests
 -----------------
 
-Test kernel modules are built as part of lib/ (make modules) and need to
-be installed (make modules_install) as the test scripts will modprobe
-them.
+Test kernel modules are built before running the livepatch selftests.  The
+modules are located under test_modules directory, and are built as out-of-tree
+modules.  This is specially useful since the same sources can be built and
+tested on systems with different kABI, ensuring they the tests are backwards
+compatible.  The modules will be loaded by the test scripts using insmod.
 
 To run the livepatch selftests, from the top of the kernel source tree:
 
   % make -C tools/testing/selftests TARGETS=livepatch run_tests
 
+or
+
+  % make kselftest TARGETS=livepatch
+
 
 Adding tests
 ------------
diff --git a/tools/testing/selftests/livepatch/config b/tools/testing/selftests/livepatch/config
index ad23100cb27c..e88bf518a23a 100644
--- a/tools/testing/selftests/livepatch/config
+++ b/tools/testing/selftests/livepatch/config
@@ -1,3 +1,2 @@
 CONFIG_LIVEPATCH=y
 CONFIG_DYNAMIC_DEBUG=y
-CONFIG_TEST_LIVEPATCH=m
diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh
index c8416c54b463..fc4c6a016d38 100644
--- a/tools/testing/selftests/livepatch/functions.sh
+++ b/tools/testing/selftests/livepatch/functions.sh
@@ -34,6 +34,18 @@ function is_root() {
 	fi
 }
 
+# Check if we can compile the modules before loading them
+function has_kdir() {
+	if [ -z "$KDIR" ]; then
+		KDIR="/lib/modules/$(uname -r)/build"
+	fi
+
+	if [ ! -d "$KDIR" ]; then
+		echo "skip all tests: KDIR ($KDIR) not available to compile modules."
+		exit $ksft_skip
+	fi
+}
+
 # die(msg) - game over, man
 #	msg - dying words
 function die() {
@@ -42,17 +54,6 @@ function die() {
 	exit 1
 }
 
-# save existing dmesg so we can detect new content
-function save_dmesg() {
-	SAVED_DMESG=$(mktemp --tmpdir -t klp-dmesg-XXXXXX)
-	dmesg > "$SAVED_DMESG"
-}
-
-# cleanup temporary dmesg file from save_dmesg()
-function cleanup_dmesg_file() {
-	rm -f "$SAVED_DMESG"
-}
-
 function push_config() {
 	DYNAMIC_DEBUG=$(grep '^kernel/livepatch' /sys/kernel/debug/dynamic_debug/control | \
 			awk -F'[: ]' '{print "file " $1 " line " $2 " " $4}')
@@ -99,7 +100,6 @@ function set_ftrace_enabled() {
 
 function cleanup() {
 	pop_config
-	cleanup_dmesg_file
 }
 
 # setup_config - save the current config and set a script exit trap that
@@ -108,6 +108,7 @@ function cleanup() {
 #		 the ftrace_enabled sysctl.
 function setup_config() {
 	is_root
+	has_kdir
 	push_config
 	set_dynamic_debug
 	set_ftrace_enabled 1
@@ -127,16 +128,14 @@ function loop_until() {
 	done
 }
 
-function assert_mod() {
-	local mod="$1"
-
-	modprobe --dry-run "$mod" &>/dev/null
-}
-
 function is_livepatch_mod() {
 	local mod="$1"
 
-	if [[ $(modinfo "$mod" | awk '/^livepatch:/{print $NF}') == "Y" ]]; then
+	if [[ ! -f "test_modules/$mod.ko" ]]; then
+		die "Can't find \"test_modules/$mod.ko\", try \"make\""
+	fi
+
+	if [[ $(modinfo "test_modules/$mod.ko" | awk '/^livepatch:/{print $NF}') == "Y" ]]; then
 		return 0
 	fi
 
@@ -146,9 +145,9 @@ function is_livepatch_mod() {
 function __load_mod() {
 	local mod="$1"; shift
 
-	local msg="% modprobe $mod $*"
+	local msg="% insmod test_modules/$mod.ko $*"
 	log "${msg%% }"
-	ret=$(modprobe "$mod" "$@" 2>&1)
+	ret=$(insmod "test_modules/$mod.ko" "$@" 2>&1)
 	if [[ "$ret" != "" ]]; then
 		die "$ret"
 	fi
@@ -161,13 +160,10 @@ function __load_mod() {
 
 # load_mod(modname, params) - load a kernel module
 #	modname - module name to load
-#	params  - module parameters to pass to modprobe
+#	params  - module parameters to pass to insmod
 function load_mod() {
 	local mod="$1"; shift
 
-	assert_mod "$mod" ||
-		skip "unable to load module ${mod}, verify CONFIG_TEST_LIVEPATCH=m and run self-tests as root"
-
 	is_livepatch_mod "$mod" &&
 		die "use load_lp() to load the livepatch module $mod"
 
@@ -177,13 +173,10 @@ function load_mod() {
 # load_lp_nowait(modname, params) - load a kernel module with a livepatch
 #			but do not wait on until the transition finishes
 #	modname - module name to load
-#	params  - module parameters to pass to modprobe
+#	params  - module parameters to pass to insmod
 function load_lp_nowait() {
 	local mod="$1"; shift
 
-	assert_mod "$mod" ||
-		skip "unable to load module ${mod}, verify CONFIG_TEST_LIVEPATCH=m and run self-tests as root"
-
 	is_livepatch_mod "$mod" ||
 		die "module $mod is not a livepatch"
 
@@ -196,7 +189,7 @@ function load_lp_nowait() {
 
 # load_lp(modname, params) - load a kernel module with a livepatch
 #	modname - module name to load
-#	params  - module parameters to pass to modprobe
+#	params  - module parameters to pass to insmod
 function load_lp() {
 	local mod="$1"; shift
 
@@ -209,13 +202,13 @@ function load_lp() {
 
 # load_failing_mod(modname, params) - load a kernel module, expect to fail
 #	modname - module name to load
-#	params  - module parameters to pass to modprobe
+#	params  - module parameters to pass to insmod
 function load_failing_mod() {
 	local mod="$1"; shift
 
-	local msg="% modprobe $mod $*"
+	local msg="% insmod test_modules/$mod.ko $*"
 	log "${msg%% }"
-	ret=$(modprobe "$mod" "$@" 2>&1)
+	ret=$(insmod "test_modules/$mod.ko" "$@" 2>&1)
 	if [[ "$ret" == "" ]]; then
 		die "$mod unexpectedly loaded"
 	fi
@@ -280,7 +273,15 @@ function set_pre_patch_ret {
 function start_test {
 	local test="$1"
 
-	save_dmesg
+	# Dump something unique into the dmesg log, then stash the entry
+	# in LAST_DMESG.  The check_result() function will use it to
+	# find new kernel messages since the test started.
+	local last_dmesg_msg="livepatch kselftest timestamp: $(date --rfc-3339=ns)"
+	log "$last_dmesg_msg"
+	loop_until 'dmesg | grep -q "$last_dmesg_msg"' ||
+		die "buffer busy? can't find canary dmesg message: $last_dmesg_msg"
+	LAST_DMESG=$(dmesg | grep "$last_dmesg_msg")
+
 	echo -n "TEST: $test ... "
 	log "===== TEST: $test ====="
 }
@@ -291,23 +292,24 @@ function check_result {
 	local expect="$*"
 	local result
 
-	# Note: when comparing dmesg output, the kernel log timestamps
-	# help differentiate repeated testing runs.  Remove them with a
-	# post-comparison sed filter.
-
-	result=$(dmesg | comm --nocheck-order -13 "$SAVED_DMESG" - | \
+	# Test results include any new dmesg entry since LAST_DMESG, then:
+	# - include lines matching keywords
+	# - exclude lines matching keywords
+	# - filter out dmesg timestamp prefixes
+	result=$(dmesg | awk -v last_dmesg="$LAST_DMESG" 'p; $0 == last_dmesg { p=1 }' | \
 		 grep -e 'livepatch:' -e 'test_klp' | \
 		 grep -v '\(tainting\|taints\) kernel' | \
 		 sed 's/^\[[ 0-9.]*\] //')
 
 	if [[ "$expect" == "$result" ]] ; then
 		echo "ok"
+	elif [[ "$result" == "" ]] ; then
+		echo -e "not ok\n\nbuffer overrun? can't find canary dmesg entry: $LAST_DMESG\n"
+		die "livepatch kselftest(s) failed"
 	else
 		echo -e "not ok\n\n$(diff -upr --label expected --label result <(echo "$expect") <(echo "$result"))\n"
 		die "livepatch kselftest(s) failed"
 	fi
-
-	cleanup_dmesg_file
 }
 
 # check_sysfs_rights(modname, rel_path, expected_rights) - check sysfs
diff --git a/tools/testing/selftests/livepatch/test-callbacks.sh b/tools/testing/selftests/livepatch/test-callbacks.sh
index 90b26dbb2626..32b150e25b10 100755
--- a/tools/testing/selftests/livepatch/test-callbacks.sh
+++ b/tools/testing/selftests/livepatch/test-callbacks.sh
@@ -34,9 +34,9 @@ disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 unload_mod $MOD_TARGET
 
-check_result "% modprobe $MOD_TARGET
+check_result "% insmod test_modules/$MOD_TARGET.ko
 $MOD_TARGET: ${MOD_TARGET}_init
-% modprobe $MOD_LIVEPATCH
+% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -81,7 +81,7 @@ disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 unload_mod $MOD_TARGET
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -89,7 +89,7 @@ livepatch: '$MOD_LIVEPATCH': starting patching transition
 livepatch: '$MOD_LIVEPATCH': completing patching transition
 $MOD_LIVEPATCH: post_patch_callback: vmlinux
 livepatch: '$MOD_LIVEPATCH': patching complete
-% modprobe $MOD_TARGET
+% insmod test_modules/$MOD_TARGET.ko
 livepatch: applying patch '$MOD_LIVEPATCH' to loading module '$MOD_TARGET'
 $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init
 $MOD_LIVEPATCH: post_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init
@@ -129,9 +129,9 @@ unload_mod $MOD_TARGET
 disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 
-check_result "% modprobe $MOD_TARGET
+check_result "% insmod test_modules/$MOD_TARGET.ko
 $MOD_TARGET: ${MOD_TARGET}_init
-% modprobe $MOD_LIVEPATCH
+% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -177,7 +177,7 @@ unload_mod $MOD_TARGET
 disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -185,7 +185,7 @@ livepatch: '$MOD_LIVEPATCH': starting patching transition
 livepatch: '$MOD_LIVEPATCH': completing patching transition
 $MOD_LIVEPATCH: post_patch_callback: vmlinux
 livepatch: '$MOD_LIVEPATCH': patching complete
-% modprobe $MOD_TARGET
+% insmod test_modules/$MOD_TARGET.ko
 livepatch: applying patch '$MOD_LIVEPATCH' to loading module '$MOD_TARGET'
 $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init
 $MOD_LIVEPATCH: post_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init
@@ -219,7 +219,7 @@ load_lp $MOD_LIVEPATCH
 disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -254,9 +254,9 @@ load_mod $MOD_TARGET
 load_failing_mod $MOD_LIVEPATCH pre_patch_ret=-19
 unload_mod $MOD_TARGET
 
-check_result "% modprobe $MOD_TARGET
+check_result "% insmod test_modules/$MOD_TARGET.ko
 $MOD_TARGET: ${MOD_TARGET}_init
-% modprobe $MOD_LIVEPATCH pre_patch_ret=-19
+% insmod test_modules/$MOD_LIVEPATCH.ko pre_patch_ret=-19
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 test_klp_callbacks_demo: pre_patch_callback: vmlinux
@@ -265,7 +265,7 @@ livepatch: failed to enable patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': canceling patching transition, going to unpatch
 livepatch: '$MOD_LIVEPATCH': completing unpatching transition
 livepatch: '$MOD_LIVEPATCH': unpatching complete
-modprobe: ERROR: could not insert '$MOD_LIVEPATCH': No such device
+insmod: ERROR: could not insert module test_modules/$MOD_LIVEPATCH.ko: No such device
 % rmmod $MOD_TARGET
 $MOD_TARGET: ${MOD_TARGET}_exit"
 
@@ -295,7 +295,7 @@ load_failing_mod $MOD_TARGET
 disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -304,12 +304,12 @@ livepatch: '$MOD_LIVEPATCH': completing patching transition
 $MOD_LIVEPATCH: post_patch_callback: vmlinux
 livepatch: '$MOD_LIVEPATCH': patching complete
 % echo -19 > /sys/module/$MOD_LIVEPATCH/parameters/pre_patch_ret
-% modprobe $MOD_TARGET
+% insmod test_modules/$MOD_TARGET.ko
 livepatch: applying patch '$MOD_LIVEPATCH' to loading module '$MOD_TARGET'
 $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init
 livepatch: pre-patch callback failed for object '$MOD_TARGET'
 livepatch: patch '$MOD_LIVEPATCH' failed for module '$MOD_TARGET', refusing to load module '$MOD_TARGET'
-modprobe: ERROR: could not insert '$MOD_TARGET': No such device
+insmod: ERROR: could not insert module test_modules/$MOD_TARGET.ko: No such device
 % echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH/enabled
 livepatch: '$MOD_LIVEPATCH': initializing unpatching transition
 $MOD_LIVEPATCH: pre_unpatch_callback: vmlinux
@@ -340,11 +340,11 @@ disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 unload_mod $MOD_TARGET_BUSY
 
-check_result "% modprobe $MOD_TARGET_BUSY block_transition=N
+check_result "% insmod test_modules/$MOD_TARGET_BUSY.ko block_transition=N
 $MOD_TARGET_BUSY: ${MOD_TARGET_BUSY}_init
 $MOD_TARGET_BUSY: busymod_work_func enter
 $MOD_TARGET_BUSY: busymod_work_func exit
-% modprobe $MOD_LIVEPATCH
+% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -354,7 +354,7 @@ livepatch: '$MOD_LIVEPATCH': completing patching transition
 $MOD_LIVEPATCH: post_patch_callback: vmlinux
 $MOD_LIVEPATCH: post_patch_callback: $MOD_TARGET_BUSY -> [MODULE_STATE_LIVE] Normal state
 livepatch: '$MOD_LIVEPATCH': patching complete
-% modprobe $MOD_TARGET
+% insmod test_modules/$MOD_TARGET.ko
 livepatch: applying patch '$MOD_LIVEPATCH' to loading module '$MOD_TARGET'
 $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init
 $MOD_LIVEPATCH: post_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init
@@ -421,16 +421,16 @@ disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 unload_mod $MOD_TARGET_BUSY
 
-check_result "% modprobe $MOD_TARGET_BUSY block_transition=Y
+check_result "% insmod test_modules/$MOD_TARGET_BUSY.ko block_transition=Y
 $MOD_TARGET_BUSY: ${MOD_TARGET_BUSY}_init
 $MOD_TARGET_BUSY: busymod_work_func enter
-% modprobe $MOD_LIVEPATCH
+% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
 $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET_BUSY -> [MODULE_STATE_LIVE] Normal state
 livepatch: '$MOD_LIVEPATCH': starting patching transition
-% modprobe $MOD_TARGET
+% insmod test_modules/$MOD_TARGET.ko
 livepatch: applying patch '$MOD_LIVEPATCH' to loading module '$MOD_TARGET'
 $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init
 $MOD_TARGET: ${MOD_TARGET}_init
@@ -467,7 +467,7 @@ disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH2
 unload_lp $MOD_LIVEPATCH
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -475,7 +475,7 @@ livepatch: '$MOD_LIVEPATCH': starting patching transition
 livepatch: '$MOD_LIVEPATCH': completing patching transition
 $MOD_LIVEPATCH: post_patch_callback: vmlinux
 livepatch: '$MOD_LIVEPATCH': patching complete
-% modprobe $MOD_LIVEPATCH2
+% insmod test_modules/$MOD_LIVEPATCH2.ko
 livepatch: enabling patch '$MOD_LIVEPATCH2'
 livepatch: '$MOD_LIVEPATCH2': initializing patching transition
 $MOD_LIVEPATCH2: pre_patch_callback: vmlinux
@@ -523,7 +523,7 @@ disable_lp $MOD_LIVEPATCH2
 unload_lp $MOD_LIVEPATCH2
 unload_lp $MOD_LIVEPATCH
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -531,7 +531,7 @@ livepatch: '$MOD_LIVEPATCH': starting patching transition
 livepatch: '$MOD_LIVEPATCH': completing patching transition
 $MOD_LIVEPATCH: post_patch_callback: vmlinux
 livepatch: '$MOD_LIVEPATCH': patching complete
-% modprobe $MOD_LIVEPATCH2 replace=1
+% insmod test_modules/$MOD_LIVEPATCH2.ko replace=1
 livepatch: enabling patch '$MOD_LIVEPATCH2'
 livepatch: '$MOD_LIVEPATCH2': initializing patching transition
 $MOD_LIVEPATCH2: pre_patch_callback: vmlinux
diff --git a/tools/testing/selftests/livepatch/test-ftrace.sh b/tools/testing/selftests/livepatch/test-ftrace.sh
index 825540a5194d..730218bce99c 100755
--- a/tools/testing/selftests/livepatch/test-ftrace.sh
+++ b/tools/testing/selftests/livepatch/test-ftrace.sh
@@ -35,7 +35,7 @@ disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 
 check_result "livepatch: kernel.ftrace_enabled = 0
-% modprobe $MOD_LIVEPATCH
+% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 livepatch: failed to register ftrace handler for function 'cmdline_proc_show' (-16)
@@ -44,9 +44,9 @@ livepatch: failed to enable patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': canceling patching transition, going to unpatch
 livepatch: '$MOD_LIVEPATCH': completing unpatching transition
 livepatch: '$MOD_LIVEPATCH': unpatching complete
-modprobe: ERROR: could not insert '$MOD_LIVEPATCH': Device or resource busy
+insmod: ERROR: could not insert module test_modules/$MOD_LIVEPATCH.ko: Device or resource busy
 livepatch: kernel.ftrace_enabled = 1
-% modprobe $MOD_LIVEPATCH
+% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 livepatch: '$MOD_LIVEPATCH': starting patching transition
diff --git a/tools/testing/selftests/livepatch/test-livepatch.sh b/tools/testing/selftests/livepatch/test-livepatch.sh
index 5fe79ac34be1..e3455a6b1158 100755
--- a/tools/testing/selftests/livepatch/test-livepatch.sh
+++ b/tools/testing/selftests/livepatch/test-livepatch.sh
@@ -31,7 +31,7 @@ if [[ "$(cat /proc/cmdline)" == "$MOD_LIVEPATCH: this has been live patched" ]]
 	die "livepatch kselftest(s) failed"
 fi
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 livepatch: '$MOD_LIVEPATCH': starting patching transition
@@ -75,14 +75,14 @@ unload_lp $MOD_LIVEPATCH
 grep 'live patched' /proc/cmdline > /dev/kmsg
 grep 'live patched' /proc/meminfo > /dev/kmsg
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 livepatch: '$MOD_LIVEPATCH': starting patching transition
 livepatch: '$MOD_LIVEPATCH': completing patching transition
 livepatch: '$MOD_LIVEPATCH': patching complete
 $MOD_LIVEPATCH: this has been live patched
-% modprobe $MOD_REPLACE replace=0
+% insmod test_modules/$MOD_REPLACE.ko replace=0
 livepatch: enabling patch '$MOD_REPLACE'
 livepatch: '$MOD_REPLACE': initializing patching transition
 livepatch: '$MOD_REPLACE': starting patching transition
@@ -135,14 +135,14 @@ unload_lp $MOD_REPLACE
 grep 'live patched' /proc/cmdline > /dev/kmsg
 grep 'live patched' /proc/meminfo > /dev/kmsg
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 livepatch: '$MOD_LIVEPATCH': starting patching transition
 livepatch: '$MOD_LIVEPATCH': completing patching transition
 livepatch: '$MOD_LIVEPATCH': patching complete
 $MOD_LIVEPATCH: this has been live patched
-% modprobe $MOD_REPLACE replace=1
+% insmod test_modules/$MOD_REPLACE.ko replace=1
 livepatch: enabling patch '$MOD_REPLACE'
 livepatch: '$MOD_REPLACE': initializing patching transition
 livepatch: '$MOD_REPLACE': starting patching transition
diff --git a/tools/testing/selftests/livepatch/test-shadow-vars.sh b/tools/testing/selftests/livepatch/test-shadow-vars.sh
index e04cb354f56b..1218c155bffe 100755
--- a/tools/testing/selftests/livepatch/test-shadow-vars.sh
+++ b/tools/testing/selftests/livepatch/test-shadow-vars.sh
@@ -16,7 +16,7 @@ start_test "basic shadow variable API"
 load_mod $MOD_TEST
 unload_mod $MOD_TEST
 
-check_result "% modprobe $MOD_TEST
+check_result "% insmod test_modules/$MOD_TEST.ko
 $MOD_TEST: klp_shadow_get(obj=PTR1, id=0x1234) = PTR0
 $MOD_TEST:   got expected NULL result
 $MOD_TEST: shadow_ctor: PTR3 -> PTR2
diff --git a/tools/testing/selftests/livepatch/test-state.sh b/tools/testing/selftests/livepatch/test-state.sh
index 38656721c958..10a52ac06185 100755
--- a/tools/testing/selftests/livepatch/test-state.sh
+++ b/tools/testing/selftests/livepatch/test-state.sh
@@ -19,7 +19,7 @@ load_lp $MOD_LIVEPATCH
 disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -51,7 +51,7 @@ unload_lp $MOD_LIVEPATCH
 disable_lp $MOD_LIVEPATCH2
 unload_lp $MOD_LIVEPATCH2
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -61,7 +61,7 @@ livepatch: '$MOD_LIVEPATCH': completing patching transition
 $MOD_LIVEPATCH: post_patch_callback: vmlinux
 $MOD_LIVEPATCH: fix_console_loglevel: fixing console_loglevel
 livepatch: '$MOD_LIVEPATCH': patching complete
-% modprobe $MOD_LIVEPATCH2
+% insmod test_modules/$MOD_LIVEPATCH2.ko
 livepatch: enabling patch '$MOD_LIVEPATCH2'
 livepatch: '$MOD_LIVEPATCH2': initializing patching transition
 $MOD_LIVEPATCH2: pre_patch_callback: vmlinux
@@ -96,7 +96,7 @@ disable_lp $MOD_LIVEPATCH2
 unload_lp $MOD_LIVEPATCH2
 unload_lp $MOD_LIVEPATCH3
 
-check_result "% modprobe $MOD_LIVEPATCH2
+check_result "% insmod test_modules/$MOD_LIVEPATCH2.ko
 livepatch: enabling patch '$MOD_LIVEPATCH2'
 livepatch: '$MOD_LIVEPATCH2': initializing patching transition
 $MOD_LIVEPATCH2: pre_patch_callback: vmlinux
@@ -106,7 +106,7 @@ livepatch: '$MOD_LIVEPATCH2': completing patching transition
 $MOD_LIVEPATCH2: post_patch_callback: vmlinux
 $MOD_LIVEPATCH2: fix_console_loglevel: fixing console_loglevel
 livepatch: '$MOD_LIVEPATCH2': patching complete
-% modprobe $MOD_LIVEPATCH3
+% insmod test_modules/$MOD_LIVEPATCH3.ko
 livepatch: enabling patch '$MOD_LIVEPATCH3'
 livepatch: '$MOD_LIVEPATCH3': initializing patching transition
 $MOD_LIVEPATCH3: pre_patch_callback: vmlinux
@@ -117,7 +117,7 @@ $MOD_LIVEPATCH3: post_patch_callback: vmlinux
 $MOD_LIVEPATCH3: fix_console_loglevel: taking over the console_loglevel change
 livepatch: '$MOD_LIVEPATCH3': patching complete
 % rmmod $MOD_LIVEPATCH2
-% modprobe $MOD_LIVEPATCH2
+% insmod test_modules/$MOD_LIVEPATCH2.ko
 livepatch: enabling patch '$MOD_LIVEPATCH2'
 livepatch: '$MOD_LIVEPATCH2': initializing patching transition
 $MOD_LIVEPATCH2: pre_patch_callback: vmlinux
@@ -149,7 +149,7 @@ load_failing_mod $MOD_LIVEPATCH
 disable_lp $MOD_LIVEPATCH2
 unload_lp $MOD_LIVEPATCH2
 
-check_result "% modprobe $MOD_LIVEPATCH2
+check_result "% insmod test_modules/$MOD_LIVEPATCH2.ko
 livepatch: enabling patch '$MOD_LIVEPATCH2'
 livepatch: '$MOD_LIVEPATCH2': initializing patching transition
 $MOD_LIVEPATCH2: pre_patch_callback: vmlinux
@@ -159,9 +159,9 @@ livepatch: '$MOD_LIVEPATCH2': completing patching transition
 $MOD_LIVEPATCH2: post_patch_callback: vmlinux
 $MOD_LIVEPATCH2: fix_console_loglevel: fixing console_loglevel
 livepatch: '$MOD_LIVEPATCH2': patching complete
-% modprobe $MOD_LIVEPATCH
+% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: Livepatch patch ($MOD_LIVEPATCH) is not compatible with the already installed livepatches.
-modprobe: ERROR: could not insert '$MOD_LIVEPATCH': Invalid argument
+insmod: ERROR: could not insert module test_modules/$MOD_LIVEPATCH.ko: Invalid parameters
 % echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH2/enabled
 livepatch: '$MOD_LIVEPATCH2': initializing unpatching transition
 $MOD_LIVEPATCH2: pre_unpatch_callback: vmlinux
diff --git a/tools/testing/selftests/livepatch/test-syscall.sh b/tools/testing/selftests/livepatch/test-syscall.sh
new file mode 100755
index 000000000000..b76a881d4013
--- /dev/null
+++ b/tools/testing/selftests/livepatch/test-syscall.sh
@@ -0,0 +1,53 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2023 SUSE
+# Author: Marcos Paulo de Souza <mpdesouza@suse.com>
+
+. $(dirname $0)/functions.sh
+
+MOD_SYSCALL=test_klp_syscall
+
+setup_config
+
+# - Start _NRPROC processes calling getpid and load a livepatch to patch the
+#   getpid syscall. Check if all the processes transitioned to the livepatched
+#   state.
+
+start_test "patch getpid syscall while being heavily hammered"
+
+for i in $(seq 1 $(getconf _NPROCESSORS_ONLN)); do
+	./test_klp-call_getpid &
+	pids[$i]="$!"
+done
+
+pid_list=$(echo ${pids[@]} | tr ' ' ',')
+load_lp $MOD_SYSCALL klp_pids=$pid_list
+
+# wait for all tasks to transition to patched state
+loop_until 'grep -q '^0$' /sys/kernel/test_klp_syscall/npids'
+
+pending_pids=$(cat /sys/kernel/test_klp_syscall/npids)
+log "$MOD_SYSCALL: Remaining not livepatched processes: $pending_pids"
+
+for pid in ${pids[@]}; do
+	kill $pid || true
+done
+
+disable_lp $MOD_SYSCALL
+unload_lp $MOD_SYSCALL
+
+check_result "% insmod test_modules/$MOD_SYSCALL.ko klp_pids=$pid_list
+livepatch: enabling patch '$MOD_SYSCALL'
+livepatch: '$MOD_SYSCALL': initializing patching transition
+livepatch: '$MOD_SYSCALL': starting patching transition
+livepatch: '$MOD_SYSCALL': completing patching transition
+livepatch: '$MOD_SYSCALL': patching complete
+$MOD_SYSCALL: Remaining not livepatched processes: 0
+% echo 0 > /sys/kernel/livepatch/$MOD_SYSCALL/enabled
+livepatch: '$MOD_SYSCALL': initializing unpatching transition
+livepatch: '$MOD_SYSCALL': starting unpatching transition
+livepatch: '$MOD_SYSCALL': completing unpatching transition
+livepatch: '$MOD_SYSCALL': unpatching complete
+% rmmod $MOD_SYSCALL"
+
+exit 0
diff --git a/tools/testing/selftests/livepatch/test-sysfs.sh b/tools/testing/selftests/livepatch/test-sysfs.sh
index 7f76f280189a..6c646afa7395 100755
--- a/tools/testing/selftests/livepatch/test-sysfs.sh
+++ b/tools/testing/selftests/livepatch/test-sysfs.sh
@@ -27,7 +27,7 @@ disable_lp $MOD_LIVEPATCH
 
 unload_lp $MOD_LIVEPATCH
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 livepatch: '$MOD_LIVEPATCH': starting patching transition
@@ -56,7 +56,7 @@ check_sysfs_value  "$MOD_LIVEPATCH" "$MOD_TARGET/patched" "0"
 disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 
-check_result "% modprobe test_klp_callbacks_demo
+check_result "% insmod test_modules/test_klp_callbacks_demo.ko
 livepatch: enabling patch 'test_klp_callbacks_demo'
 livepatch: 'test_klp_callbacks_demo': initializing patching transition
 test_klp_callbacks_demo: pre_patch_callback: vmlinux
@@ -64,7 +64,7 @@ livepatch: 'test_klp_callbacks_demo': starting patching transition
 livepatch: 'test_klp_callbacks_demo': completing patching transition
 test_klp_callbacks_demo: post_patch_callback: vmlinux
 livepatch: 'test_klp_callbacks_demo': patching complete
-% modprobe test_klp_callbacks_mod
+% insmod test_modules/test_klp_callbacks_mod.ko
 livepatch: applying patch 'test_klp_callbacks_demo' to loading module 'test_klp_callbacks_mod'
 test_klp_callbacks_demo: pre_patch_callback: test_klp_callbacks_mod -> [MODULE_STATE_COMING] Full formed, running module_init
 test_klp_callbacks_demo: post_patch_callback: test_klp_callbacks_mod -> [MODULE_STATE_COMING] Full formed, running module_init
diff --git a/tools/testing/selftests/livepatch/test_klp-call_getpid.c b/tools/testing/selftests/livepatch/test_klp-call_getpid.c
new file mode 100644
index 000000000000..ce321a2d7308
--- /dev/null
+++ b/tools/testing/selftests/livepatch/test_klp-call_getpid.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 SUSE
+ * Authors: Libor Pechacek <lpechacek@suse.cz>
+ *          Marcos Paulo de Souza <mpdesouza@suse.com>
+ */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <signal.h>
+
+static int stop;
+static int sig_int;
+
+void hup_handler(int signum)
+{
+	stop = 1;
+}
+
+void int_handler(int signum)
+{
+	stop = 1;
+	sig_int = 1;
+}
+
+int main(int argc, char *argv[])
+{
+	long count = 0;
+
+	signal(SIGHUP, &hup_handler);
+	signal(SIGINT, &int_handler);
+
+	while (!stop) {
+		(void)syscall(SYS_getpid);
+		count++;
+	}
+
+	if (sig_int)
+		printf("%ld iterations done\n", count);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/livepatch/test_modules/Makefile b/tools/testing/selftests/livepatch/test_modules/Makefile
new file mode 100644
index 000000000000..e6e638c4bcba
--- /dev/null
+++ b/tools/testing/selftests/livepatch/test_modules/Makefile
@@ -0,0 +1,26 @@
+TESTMODS_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST)))))
+KDIR ?= /lib/modules/$(shell uname -r)/build
+
+obj-m += test_klp_atomic_replace.o \
+	test_klp_callbacks_busy.o \
+	test_klp_callbacks_demo.o \
+	test_klp_callbacks_demo2.o \
+	test_klp_callbacks_mod.o \
+	test_klp_livepatch.o \
+	test_klp_state.o \
+	test_klp_state2.o \
+	test_klp_state3.o \
+	test_klp_shadow_vars.o \
+	test_klp_syscall.o
+
+# Ensure that KDIR exists, otherwise skip the compilation
+modules:
+ifneq ("$(wildcard $(KDIR))", "")
+	$(Q)$(MAKE) -C $(KDIR) modules KBUILD_EXTMOD=$(TESTMODS_DIR)
+endif
+
+# Ensure that KDIR exists, otherwise skip the clean target
+clean:
+ifneq ("$(wildcard $(KDIR))", "")
+	$(Q)$(MAKE) -C $(KDIR) clean KBUILD_EXTMOD=$(TESTMODS_DIR)
+endif
diff --git a/lib/livepatch/test_klp_atomic_replace.c b/tools/testing/selftests/livepatch/test_modules/test_klp_atomic_replace.c
index 5af7093ca00c..5af7093ca00c 100644
--- a/lib/livepatch/test_klp_atomic_replace.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_atomic_replace.c
diff --git a/lib/livepatch/test_klp_callbacks_busy.c b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_busy.c
index 133929e0ce8f..133929e0ce8f 100644
--- a/lib/livepatch/test_klp_callbacks_busy.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_busy.c
diff --git a/lib/livepatch/test_klp_callbacks_demo.c b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_demo.c
index 3fd8fe1cd1cc..3fd8fe1cd1cc 100644
--- a/lib/livepatch/test_klp_callbacks_demo.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_demo.c
diff --git a/lib/livepatch/test_klp_callbacks_demo2.c b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_demo2.c
index 5417573e80af..5417573e80af 100644
--- a/lib/livepatch/test_klp_callbacks_demo2.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_demo2.c
diff --git a/lib/livepatch/test_klp_callbacks_mod.c b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_mod.c
index 8fbe645b1c2c..8fbe645b1c2c 100644
--- a/lib/livepatch/test_klp_callbacks_mod.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_mod.c
diff --git a/lib/livepatch/test_klp_livepatch.c b/tools/testing/selftests/livepatch/test_modules/test_klp_livepatch.c
index aff08199de71..aff08199de71 100644
--- a/lib/livepatch/test_klp_livepatch.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_livepatch.c
diff --git a/lib/livepatch/test_klp_shadow_vars.c b/tools/testing/selftests/livepatch/test_modules/test_klp_shadow_vars.c
index b99116490858..b99116490858 100644
--- a/lib/livepatch/test_klp_shadow_vars.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_shadow_vars.c
diff --git a/lib/livepatch/test_klp_state.c b/tools/testing/selftests/livepatch/test_modules/test_klp_state.c
index 57a4253acb01..57a4253acb01 100644
--- a/lib/livepatch/test_klp_state.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_state.c
diff --git a/lib/livepatch/test_klp_state2.c b/tools/testing/selftests/livepatch/test_modules/test_klp_state2.c
index c978ea4d5e67..c978ea4d5e67 100644
--- a/lib/livepatch/test_klp_state2.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_state2.c
diff --git a/lib/livepatch/test_klp_state3.c b/tools/testing/selftests/livepatch/test_modules/test_klp_state3.c
index 9226579d10c5..9226579d10c5 100644
--- a/lib/livepatch/test_klp_state3.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_state3.c
diff --git a/tools/testing/selftests/livepatch/test_modules/test_klp_syscall.c b/tools/testing/selftests/livepatch/test_modules/test_klp_syscall.c
new file mode 100644
index 000000000000..dd802783ea84
--- /dev/null
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_syscall.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2017-2023 SUSE
+ * Authors: Libor Pechacek <lpechacek@suse.cz>
+ *          Nicolai Stange <nstange@suse.de>
+ *          Marcos Paulo de Souza <mpdesouza@suse.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/livepatch.h>
+
+#if defined(__x86_64__)
+#define FN_PREFIX __x64_
+#elif defined(__s390x__)
+#define FN_PREFIX __s390x_
+#elif defined(__aarch64__)
+#define FN_PREFIX __arm64_
+#else
+/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER */
+#define FN_PREFIX
+#endif
+
+/* Protects klp_pids */
+static DEFINE_MUTEX(kpid_mutex);
+
+static unsigned int npids, npids_pending;
+static int klp_pids[NR_CPUS];
+module_param_array(klp_pids, int, &npids_pending, 0);
+MODULE_PARM_DESC(klp_pids, "Array of pids to be transitioned to livepatched state.");
+
+static ssize_t npids_show(struct kobject *kobj, struct kobj_attribute *attr,
+			  char *buf)
+{
+	return sprintf(buf, "%u\n", npids_pending);
+}
+
+static struct kobj_attribute klp_attr = __ATTR_RO(npids);
+static struct kobject *klp_kobj;
+
+static asmlinkage long lp_sys_getpid(void)
+{
+	int i;
+
+	mutex_lock(&kpid_mutex);
+	if (npids_pending > 0) {
+		for (i = 0; i < npids; i++) {
+			if (current->pid == klp_pids[i]) {
+				klp_pids[i] = 0;
+				npids_pending--;
+				break;
+			}
+		}
+	}
+	mutex_unlock(&kpid_mutex);
+
+	return task_tgid_vnr(current);
+}
+
+static struct klp_func vmlinux_funcs[] = {
+	{
+		.old_name = __stringify(FN_PREFIX) "sys_getpid",
+		.new_func = lp_sys_getpid,
+	}, {}
+};
+
+static struct klp_object objs[] = {
+	{
+		/* name being NULL means vmlinux */
+		.funcs = vmlinux_funcs,
+	}, {}
+};
+
+static struct klp_patch patch = {
+	.mod = THIS_MODULE,
+	.objs = objs,
+};
+
+static int livepatch_init(void)
+{
+	int ret;
+
+	klp_kobj = kobject_create_and_add("test_klp_syscall", kernel_kobj);
+	if (!klp_kobj)
+		return -ENOMEM;
+
+	ret = sysfs_create_file(klp_kobj, &klp_attr.attr);
+	if (ret) {
+		kobject_put(klp_kobj);
+		return ret;
+	}
+
+	/*
+	 * Save the number pids to transition to livepatched state before the
+	 * number of pending pids is decremented.
+	 */
+	npids = npids_pending;
+
+	return klp_enable_patch(&patch);
+}
+
+static void livepatch_exit(void)
+{
+	kobject_put(klp_kobj);
+}
+
+module_init(livepatch_init);
+module_exit(livepatch_exit);
+MODULE_LICENSE("GPL");
+MODULE_INFO(livepatch, "Y");
+MODULE_AUTHOR("Libor Pechacek <lpechacek@suse.cz>");
+MODULE_AUTHOR("Nicolai Stange <nstange@suse.de>");
+MODULE_AUTHOR("Marcos Paulo de Souza <mpdesouza@suse.com>");
+MODULE_DESCRIPTION("Livepatch test: syscall transition");
diff --git a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
index 0899019a7fcb..e14bdd4455f2 100755
--- a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
+++ b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 # Kselftest framework requirement - SKIP code is 4.
diff --git a/tools/testing/selftests/mm/hugepage-vmemmap.c b/tools/testing/selftests/mm/hugepage-vmemmap.c
index 5b354c209e93..894d28c3dd47 100644
--- a/tools/testing/selftests/mm/hugepage-vmemmap.c
+++ b/tools/testing/selftests/mm/hugepage-vmemmap.c
@@ -10,10 +10,7 @@
 #include <unistd.h>
 #include <sys/mman.h>
 #include <fcntl.h>
-
-#define MAP_LENGTH		(2UL * 1024 * 1024)
-
-#define PAGE_SIZE		4096
+#include "vm_util.h"
 
 #define PAGE_COMPOUND_HEAD	(1UL << 15)
 #define PAGE_COMPOUND_TAIL	(1UL << 16)
@@ -39,6 +36,9 @@
 #define MAP_FLAGS		(MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB)
 #endif
 
+static size_t pagesize;
+static size_t maplength;
+
 static void write_bytes(char *addr, size_t length)
 {
 	unsigned long i;
@@ -56,7 +56,7 @@ static unsigned long virt_to_pfn(void *addr)
 	if (fd < 0)
 		return -1UL;
 
-	lseek(fd, (unsigned long)addr / PAGE_SIZE * sizeof(pagemap), SEEK_SET);
+	lseek(fd, (unsigned long)addr / pagesize * sizeof(pagemap), SEEK_SET);
 	read(fd, &pagemap, sizeof(pagemap));
 	close(fd);
 
@@ -86,7 +86,7 @@ static int check_page_flags(unsigned long pfn)
 	 * this also verifies kernel has correctly set the fake page_head to tail
 	 * while hugetlb_free_vmemmap is enabled.
 	 */
-	for (i = 1; i < MAP_LENGTH / PAGE_SIZE; i++) {
+	for (i = 1; i < maplength / pagesize; i++) {
 		read(fd, &pageflags, sizeof(pageflags));
 		if ((pageflags & TAIL_PAGE_FLAGS) != TAIL_PAGE_FLAGS ||
 		    (pageflags & HEAD_PAGE_FLAGS) == HEAD_PAGE_FLAGS) {
@@ -106,18 +106,25 @@ int main(int argc, char **argv)
 	void *addr;
 	unsigned long pfn;
 
-	addr = mmap(MAP_ADDR, MAP_LENGTH, PROT_READ | PROT_WRITE, MAP_FLAGS, -1, 0);
+	pagesize  = psize();
+	maplength = default_huge_page_size();
+	if (!maplength) {
+		printf("Unable to determine huge page size\n");
+		exit(1);
+	}
+
+	addr = mmap(MAP_ADDR, maplength, PROT_READ | PROT_WRITE, MAP_FLAGS, -1, 0);
 	if (addr == MAP_FAILED) {
 		perror("mmap");
 		exit(1);
 	}
 
 	/* Trigger allocation of HugeTLB page. */
-	write_bytes(addr, MAP_LENGTH);
+	write_bytes(addr, maplength);
 
 	pfn = virt_to_pfn(addr);
 	if (pfn == -1UL) {
-		munmap(addr, MAP_LENGTH);
+		munmap(addr, maplength);
 		perror("virt_to_pfn");
 		exit(1);
 	}
@@ -125,13 +132,13 @@ int main(int argc, char **argv)
 	printf("Returned address is %p whose pfn is %lx\n", addr, pfn);
 
 	if (check_page_flags(pfn) < 0) {
-		munmap(addr, MAP_LENGTH);
+		munmap(addr, maplength);
 		perror("check_page_flags");
 		exit(1);
 	}
 
 	/* munmap() length of MAP_HUGETLB memory must be hugepage aligned */
-	if (munmap(addr, MAP_LENGTH)) {
+	if (munmap(addr, maplength)) {
 		perror("munmap");
 		exit(1);
 	}
diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c
index 380b691d3eb9..b748c48908d9 100644
--- a/tools/testing/selftests/mm/ksm_tests.c
+++ b/tools/testing/selftests/mm/ksm_tests.c
@@ -566,7 +566,7 @@ static int ksm_merge_hugepages_time(int merge_type, int mapping, int prot,
 	if (map_ptr_orig == MAP_FAILED)
 		err(2, "initial mmap");
 
-	if (madvise(map_ptr, len + HPAGE_SIZE, MADV_HUGEPAGE))
+	if (madvise(map_ptr, len, MADV_HUGEPAGE))
 		err(2, "MADV_HUGEPAGE");
 
 	pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
diff --git a/tools/testing/selftests/mm/map_hugetlb.c b/tools/testing/selftests/mm/map_hugetlb.c
index 193281560b61..86e8f2048a40 100644
--- a/tools/testing/selftests/mm/map_hugetlb.c
+++ b/tools/testing/selftests/mm/map_hugetlb.c
@@ -15,6 +15,7 @@
 #include <unistd.h>
 #include <sys/mman.h>
 #include <fcntl.h>
+#include "vm_util.h"
 
 #define LENGTH (256UL*1024*1024)
 #define PROTECTION (PROT_READ | PROT_WRITE)
@@ -58,10 +59,16 @@ int main(int argc, char **argv)
 {
 	void *addr;
 	int ret;
+	size_t hugepage_size;
 	size_t length = LENGTH;
 	int flags = FLAGS;
 	int shift = 0;
 
+	hugepage_size = default_huge_page_size();
+	/* munmap with fail if the length is not page aligned */
+	if (hugepage_size > length)
+		length = hugepage_size;
+
 	if (argc > 1)
 		length = atol(argv[1]) << 20;
 	if (argc > 2) {
diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c
index 1d4c1589c305..2f8b991f78cb 100644
--- a/tools/testing/selftests/mm/mremap_test.c
+++ b/tools/testing/selftests/mm/mremap_test.c
@@ -360,7 +360,8 @@ static long long remap_region(struct config c, unsigned int threshold_mb,
 			      char pattern_seed)
 {
 	void *addr, *src_addr, *dest_addr, *dest_preamble_addr;
-	unsigned long long i;
+	int d;
+	unsigned long long t;
 	struct timespec t_start = {0, 0}, t_end = {0, 0};
 	long long  start_ns, end_ns, align_mask, ret, offset;
 	unsigned long long threshold;
@@ -378,8 +379,8 @@ static long long remap_region(struct config c, unsigned int threshold_mb,
 
 	/* Set byte pattern for source block. */
 	srand(pattern_seed);
-	for (i = 0; i < threshold; i++)
-		memset((char *) src_addr + i, (char) rand(), 1);
+	for (t = 0; t < threshold; t++)
+		memset((char *) src_addr + t, (char) rand(), 1);
 
 	/* Mask to zero out lower bits of address for alignment */
 	align_mask = ~(c.dest_alignment - 1);
@@ -420,8 +421,8 @@ static long long remap_region(struct config c, unsigned int threshold_mb,
 
 		/* Set byte pattern for the dest preamble block. */
 		srand(pattern_seed);
-		for (i = 0; i < c.dest_preamble_size; i++)
-			memset((char *) dest_preamble_addr + i, (char) rand(), 1);
+		for (d = 0; d < c.dest_preamble_size; d++)
+			memset((char *) dest_preamble_addr + d, (char) rand(), 1);
 	}
 
 	clock_gettime(CLOCK_MONOTONIC, &t_start);
@@ -437,14 +438,14 @@ static long long remap_region(struct config c, unsigned int threshold_mb,
 
 	/* Verify byte pattern after remapping */
 	srand(pattern_seed);
-	for (i = 0; i < threshold; i++) {
+	for (t = 0; t < threshold; t++) {
 		char c = (char) rand();
 
-		if (((char *) dest_addr)[i] != c) {
+		if (((char *) dest_addr)[t] != c) {
 			ksft_print_msg("Data after remap doesn't match at offset %llu\n",
-				       i);
+				       t);
 			ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff,
-					((char *) dest_addr)[i] & 0xff);
+					((char *) dest_addr)[t] & 0xff);
 			ret = -1;
 			goto clean_up_dest;
 		}
@@ -453,14 +454,14 @@ static long long remap_region(struct config c, unsigned int threshold_mb,
 	/* Verify the dest preamble byte pattern after remapping */
 	if (c.dest_preamble_size) {
 		srand(pattern_seed);
-		for (i = 0; i < c.dest_preamble_size; i++) {
+		for (d = 0; d < c.dest_preamble_size; d++) {
 			char c = (char) rand();
 
-			if (((char *) dest_preamble_addr)[i] != c) {
+			if (((char *) dest_preamble_addr)[d] != c) {
 				ksft_print_msg("Preamble data after remap doesn't match at offset %d\n",
-					       i);
+					       d);
 				ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff,
-					       ((char *) dest_preamble_addr)[i] & 0xff);
+					       ((char *) dest_preamble_addr)[d] & 0xff);
 				ret = -1;
 				goto clean_up_dest;
 			}
diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c
index cce90a10515a..2b9f8cc52639 100644
--- a/tools/testing/selftests/mm/uffd-unit-tests.c
+++ b/tools/testing/selftests/mm/uffd-unit-tests.c
@@ -1517,6 +1517,12 @@ int main(int argc, char *argv[])
 				continue;
 
 			uffd_test_start("%s on %s", test->name, mem_type->name);
+			if ((mem_type->mem_flag == MEM_HUGETLB ||
+			    mem_type->mem_flag == MEM_HUGETLB_PRIVATE) &&
+			    (default_huge_page_size() == 0)) {
+				uffd_test_skip("huge page size is 0, feature missing?");
+				continue;
+			}
 			if (!uffd_feature_supported(test)) {
 				uffd_test_skip("feature missing");
 				continue;
diff --git a/tools/testing/selftests/mm/va_high_addr_switch.sh b/tools/testing/selftests/mm/va_high_addr_switch.sh
index 45cae7cab27e..a0a75f302904 100755
--- a/tools/testing/selftests/mm/va_high_addr_switch.sh
+++ b/tools/testing/selftests/mm/va_high_addr_switch.sh
@@ -29,9 +29,15 @@ check_supported_x86_64()
 	# See man 1 gzip under '-f'.
 	local pg_table_levels=$(gzip -dcfq "${config}" | grep PGTABLE_LEVELS | cut -d'=' -f 2)
 
+	local cpu_supports_pl5=$(awk '/^flags/ {if (/la57/) {print 0;}
+		else {print 1}; exit}' /proc/cpuinfo 2>/dev/null)
+
 	if [[ "${pg_table_levels}" -lt 5 ]]; then
 		echo "$0: PGTABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test"
 		exit $ksft_skip
+	elif [[ "${cpu_supports_pl5}" -ne 0 ]]; then
+		echo "$0: CPU does not have the necessary la57 flag to support page table level 5"
+		exit $ksft_skip
 	fi
 }
 
diff --git a/tools/testing/selftests/mm/write_hugetlb_memory.sh b/tools/testing/selftests/mm/write_hugetlb_memory.sh
index 70a02301f4c2..3d2d2eb9d6ff 100755
--- a/tools/testing/selftests/mm/write_hugetlb_memory.sh
+++ b/tools/testing/selftests/mm/write_hugetlb_memory.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 set -e
diff --git a/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c b/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c
index 50ed5d475dd1..bcf51d785a37 100644
--- a/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c
+++ b/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c
@@ -218,7 +218,7 @@ static bool move_mount_set_group_supported(void)
 	if (mount(NULL, SET_GROUP_FROM, NULL, MS_SHARED, 0))
 		return -1;
 
-	ret = syscall(SYS_move_mount, AT_FDCWD, SET_GROUP_FROM,
+	ret = syscall(__NR_move_mount, AT_FDCWD, SET_GROUP_FROM,
 		      AT_FDCWD, SET_GROUP_TO, MOVE_MOUNT_SET_GROUP);
 	umount2("/tmp", MNT_DETACH);
 
@@ -363,7 +363,7 @@ TEST_F(move_mount_set_group, complex_sharing_copying)
 		       CLONE_VM | CLONE_FILES); ASSERT_GT(pid, 0);
 	ASSERT_EQ(wait_for_pid(pid), 0);
 
-	ASSERT_EQ(syscall(SYS_move_mount, ca_from.mntfd, "",
+	ASSERT_EQ(syscall(__NR_move_mount, ca_from.mntfd, "",
 			  ca_to.mntfd, "", MOVE_MOUNT_SET_GROUP
 			  | MOVE_MOUNT_F_EMPTY_PATH | MOVE_MOUNT_T_EMPTY_PATH),
 		  0);
diff --git a/tools/testing/selftests/mqueue/setting b/tools/testing/selftests/mqueue/setting
new file mode 100644
index 000000000000..a953c96aa16e
--- /dev/null
+++ b/tools/testing/selftests/mqueue/setting
@@ -0,0 +1 @@
+timeout=180
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 50818075e566..211753756bde 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -53,8 +53,7 @@ TEST_PROGS += bind_bhash.sh
 TEST_PROGS += ip_local_port_range.sh
 TEST_PROGS += rps_default_mask.sh
 TEST_PROGS += big_tcp.sh
-TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh
-TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh lib.sh
+TEST_PROGS_EXTENDED := toeplitz_client.sh toeplitz.sh
 TEST_GEN_FILES =  socket nettest
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
 TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite
@@ -84,6 +83,7 @@ TEST_PROGS += sctp_vrf.sh
 TEST_GEN_FILES += sctp_hello
 TEST_GEN_FILES += csum
 TEST_GEN_FILES += nat6to4.o
+TEST_GEN_FILES += xdp_dummy.o
 TEST_GEN_FILES += ip_local_port_range
 TEST_GEN_FILES += bind_wildcard
 TEST_PROGS += test_vxlan_mdb.sh
@@ -95,6 +95,7 @@ TEST_PROGS += fq_band_pktlimit.sh
 TEST_PROGS += vlan_hw_filter.sh
 
 TEST_FILES := settings
+TEST_FILES += in_netns.sh lib.sh net_helper.sh setup_loopback.sh setup_veth.sh
 
 include ../lib.mk
 
@@ -104,7 +105,7 @@ $(OUTPUT)/tcp_inq: LDLIBS += -lpthread
 $(OUTPUT)/bind_bhash: LDLIBS += -lpthread
 $(OUTPUT)/io_uring_zerocopy_tx: CFLAGS += -I../../../include/
 
-# Rules to generate bpf obj nat6to4.o
+# Rules to generate bpf objs
 CLANG ?= clang
 SCRATCH_DIR := $(OUTPUT)/tools
 BUILD_DIR := $(SCRATCH_DIR)/build
@@ -139,7 +140,7 @@ endif
 
 CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH))
 
-$(OUTPUT)/nat6to4.o: nat6to4.c $(BPFOBJ) | $(MAKE_DIRS)
+$(OUTPUT)/nat6to4.o $(OUTPUT)/xdp_dummy.o: $(OUTPUT)/%.o : %.c $(BPFOBJ) | $(MAKE_DIRS)
 	$(CLANG) -O2 --target=bpf -c $< $(CCINCLUDE) $(CLANG_SYS_INCLUDES) -o $@
 
 $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)		       \
diff --git a/tools/testing/selftests/net/big_tcp.sh b/tools/testing/selftests/net/big_tcp.sh
index cde9a91c4797..2db9d15cd45f 100755
--- a/tools/testing/selftests/net/big_tcp.sh
+++ b/tools/testing/selftests/net/big_tcp.sh
@@ -122,7 +122,9 @@ do_netperf() {
 	local netns=$1
 
 	[ "$NF" = "6" ] && serip=$SERVER_IP6
-	ip net exec $netns netperf -$NF -t TCP_STREAM -H $serip 2>&1 >/dev/null
+
+	# use large write to be sure to generate big tcp packets
+	ip net exec $netns netperf -$NF -t TCP_STREAM -l 1 -H $serip -- -m 262144 2>&1 >/dev/null
 }
 
 do_test() {
diff --git a/tools/testing/selftests/net/cmsg_ipv6.sh b/tools/testing/selftests/net/cmsg_ipv6.sh
index f30bd57d5e38..8bc23fb4c82b 100755
--- a/tools/testing/selftests/net/cmsg_ipv6.sh
+++ b/tools/testing/selftests/net/cmsg_ipv6.sh
@@ -89,7 +89,7 @@ for ovr in setsock cmsg both diff; do
 	check_result $? 0 "TCLASS $prot $ovr - pass"
 
 	while [ -d /proc/$BG ]; do
-	    $NSEXE ./cmsg_sender -6 -p u $TGT6 1234
+	    $NSEXE ./cmsg_sender -6 -p $p $m $((TOS2)) $TGT6 1234
 	done
 
 	tcpdump -r $TMPF -v 2>&1 | grep "class $TOS2" >> /dev/null
@@ -126,7 +126,7 @@ for ovr in setsock cmsg both diff; do
 	check_result $? 0 "HOPLIMIT $prot $ovr - pass"
 
 	while [ -d /proc/$BG ]; do
-	    $NSEXE ./cmsg_sender -6 -p u $TGT6 1234
+	    $NSEXE ./cmsg_sender -6 -p $p $m $LIM $TGT6 1234
 	done
 
 	tcpdump -r $TMPF -v 2>&1 | grep "hlim $LIM[^0-9]" >> /dev/null
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 8da562a9ae87..5e4390cac17e 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -1,5 +1,6 @@
 CONFIG_USER_NS=y
 CONFIG_NET_NS=y
+CONFIG_BONDING=m
 CONFIG_BPF_SYSCALL=y
 CONFIG_TEST_BPF=m
 CONFIG_NUMA=y
@@ -14,30 +15,74 @@ CONFIG_VETH=y
 CONFIG_NET_IPVTI=y
 CONFIG_IPV6_VTI=y
 CONFIG_DUMMY=y
+CONFIG_BRIDGE_VLAN_FILTERING=y
 CONFIG_BRIDGE=y
+CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_VLAN_8021Q=y
+CONFIG_GENEVE=m
 CONFIG_IFB=y
+CONFIG_INET_DIAG=y
+CONFIG_INET_ESP=y
+CONFIG_INET_ESP_OFFLOAD=y
+CONFIG_NET_FOU=y
+CONFIG_NET_FOU_IP_TUNNELS=y
+CONFIG_IP_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NETFILTER_ADVANCED=y
 CONFIG_NF_CONNTRACK=m
+CONFIG_IPV6_SIT=y
+CONFIG_IP_DCCP=m
 CONFIG_NF_NAT=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP6_NF_NAT=m
+CONFIG_IP6_NF_RAW=m
 CONFIG_IP_NF_NAT=m
+CONFIG_IP_NF_RAW=m
+CONFIG_IP_NF_TARGET_TTL=m
+CONFIG_IPV6_GRE=m
+CONFIG_IPV6_SEG6_LWTUNNEL=y
+CONFIG_L2TP_ETH=m
+CONFIG_L2TP_IP=m
+CONFIG_L2TP=m
+CONFIG_L2TP_V3=y
+CONFIG_MACSEC=m
+CONFIG_MACVLAN=y
+CONFIG_MACVTAP=y
+CONFIG_MPLS=y
+CONFIG_MPTCP=y
 CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_IPV6=y
 CONFIG_NF_TABLES_IPV4=y
 CONFIG_NFT_NAT=m
+CONFIG_NETFILTER_XT_MATCH_LENGTH=m
+CONFIG_NET_ACT_CSUM=m
+CONFIG_NET_ACT_CT=m
+CONFIG_NET_ACT_GACT=m
+CONFIG_NET_ACT_PEDIT=m
+CONFIG_NET_CLS_BASIC=m
+CONFIG_NET_CLS_BPF=m
+CONFIG_NET_CLS_MATCHALL=m
+CONFIG_NET_CLS_U32=m
+CONFIG_NET_IPGRE_DEMUX=m
+CONFIG_NET_IPGRE=m
+CONFIG_NET_IPIP=y
+CONFIG_NET_SCH_FQ_CODEL=m
+CONFIG_NET_SCH_HTB=m
 CONFIG_NET_SCH_FQ=m
 CONFIG_NET_SCH_ETF=m
 CONFIG_NET_SCH_NETEM=y
+CONFIG_NET_SCH_PRIO=m
+CONFIG_NFT_COMPAT=m
+CONFIG_NF_FLOW_TABLE=m
+CONFIG_PSAMPLE=m
+CONFIG_TCP_MD5SIG=y
 CONFIG_TEST_BLACKHOLE_DEV=m
 CONFIG_KALLSYMS=y
+CONFIG_TLS=m
 CONFIG_TRACEPOINTS=y
 CONFIG_NET_DROP_MONITOR=m
 CONFIG_NETDEVSIM=m
-CONFIG_NET_FOU=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_SCH_INGRESS=m
@@ -48,7 +93,10 @@ CONFIG_BAREUDP=m
 CONFIG_IPV6_IOAM6_LWTUNNEL=y
 CONFIG_CRYPTO_SM4_GENERIC=y
 CONFIG_AMT=m
+CONFIG_TUN=y
 CONFIG_VXLAN=m
 CONFIG_IP_SCTP=m
 CONFIG_NETFILTER_XT_MATCH_POLICY=m
 CONFIG_CRYPTO_ARIA=y
+CONFIG_XFRM_INTERFACE=m
+CONFIG_XFRM_USER=m
diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index 452693514be4..4de92632f483 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -112,7 +112,7 @@ TEST_PROGS = bridge_fdb_learning_limit.sh \
 	vxlan_symmetric_ipv6.sh \
 	vxlan_symmetric.sh
 
-TEST_PROGS_EXTENDED := devlink_lib.sh \
+TEST_FILES := devlink_lib.sh \
 	ethtool_lib.sh \
 	fib_offload_lib.sh \
 	forwarding.config.sample \
diff --git a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh
index 9af9f6964808..c62331b2e006 100755
--- a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh
@@ -327,10 +327,10 @@ locked_port_mab_redirect()
 	RET=0
 	check_port_mab_support || return 0
 
-	bridge link set dev $swp1 learning on locked on mab on
 	tc qdisc add dev $swp1 clsact
 	tc filter add dev $swp1 ingress protocol all pref 1 handle 101 flower \
 		action mirred egress redirect dev $swp2
+	bridge link set dev $swp1 learning on locked on mab on
 
 	ping_do $h1 192.0.2.2
 	check_err $? "Ping did not work with redirection"
@@ -349,8 +349,8 @@ locked_port_mab_redirect()
 	check_err $? "Locked entry not created after deleting filter"
 
 	bridge fdb del `mac_get $h1` vlan 1 dev $swp1 master
-	tc qdisc del dev $swp1 clsact
 	bridge link set dev $swp1 learning off locked off mab off
+	tc qdisc del dev $swp1 clsact
 
 	log_test "Locked port MAB redirect"
 }
diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh
index 61348f71728c..d9d587454d20 100755
--- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh
@@ -329,7 +329,7 @@ __cfg_test_port_ip_star_g()
 
 	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00"
 	check_err $? "(*, G) \"permanent\" entry has a pending group timer"
-	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "\/0.00"
+	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "/0.00"
 	check_err $? "\"permanent\" source entry has a pending source timer"
 
 	bridge mdb del dev br0 port $swp1 grp $grp vid 10
@@ -346,7 +346,7 @@ __cfg_test_port_ip_star_g()
 
 	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00"
 	check_fail $? "(*, G) EXCLUDE entry does not have a pending group timer"
-	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "\/0.00"
+	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "/0.00"
 	check_err $? "\"blocked\" source entry has a pending source timer"
 
 	bridge mdb del dev br0 port $swp1 grp $grp vid 10
@@ -363,7 +363,7 @@ __cfg_test_port_ip_star_g()
 
 	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00"
 	check_err $? "(*, G) INCLUDE entry has a pending group timer"
-	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "\/0.00"
+	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "/0.00"
 	check_fail $? "Source entry does not have a pending source timer"
 
 	bridge mdb del dev br0 port $swp1 grp $grp vid 10
@@ -1252,14 +1252,17 @@ fwd_test()
 	echo
 	log_info "# Forwarding tests"
 
+	# Set the Max Response Delay to 100 centiseconds (1 second) so that the
+	# bridge will start forwarding according to its MDB soon after a
+	# multicast querier is enabled.
+	ip link set dev br0 type bridge mcast_query_response_interval 100
+
 	# Forwarding according to MDB entries only takes place when the bridge
 	# detects that there is a valid querier in the network. Set the bridge
 	# as the querier and assign it a valid IPv6 link-local address to be
 	# used as the source address for MLD queries.
 	ip -6 address add fe80::1/64 nodad dev br0
 	ip link set dev br0 type bridge mcast_querier 1
-	# Wait the default Query Response Interval (10 seconds) for the bridge
-	# to determine that there are no other queriers in the network.
 	sleep 10
 
 	fwd_test_host
@@ -1267,6 +1270,7 @@ fwd_test()
 
 	ip link set dev br0 type bridge mcast_querier 0
 	ip -6 address del fe80::1/64 dev br0
+	ip link set dev br0 type bridge mcast_query_response_interval 1000
 }
 
 ctrl_igmpv3_is_in_test()
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 8a61464ab6eb..8a61464ab6eb 100755..100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh
index b0f5e55d2d0b..589629636502 100755
--- a/tools/testing/selftests/net/forwarding/tc_actions.sh
+++ b/tools/testing/selftests/net/forwarding/tc_actions.sh
@@ -235,9 +235,6 @@ mirred_egress_to_ingress_tcp_test()
 	check_err $? "didn't mirred redirect ICMP"
 	tc_check_packets "dev $h1 ingress" 102 10
 	check_err $? "didn't drop mirred ICMP"
-	local overlimits=$(tc_rule_stats_get ${h1} 101 egress .overlimits)
-	test ${overlimits} = 10
-	check_err $? "wrong overlimits, expected 10 got ${overlimits}"
 
 	tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower
 	tc filter del dev $h1 egress protocol ip pref 101 handle 101 flower
diff --git a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh
index 20a7cb7222b8..c2420bb72c12 100755
--- a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh
+++ b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh
@@ -209,14 +209,17 @@ test_l2_miss_multicast()
 	# both registered and unregistered multicast traffic.
 	bridge link set dev $swp2 mcast_router 2
 
+	# Set the Max Response Delay to 100 centiseconds (1 second) so that the
+	# bridge will start forwarding according to its MDB soon after a
+	# multicast querier is enabled.
+	ip link set dev br1 type bridge mcast_query_response_interval 100
+
 	# Forwarding according to MDB entries only takes place when the bridge
 	# detects that there is a valid querier in the network. Set the bridge
 	# as the querier and assign it a valid IPv6 link-local address to be
 	# used as the source address for MLD queries.
 	ip link set dev br1 type bridge mcast_querier 1
 	ip -6 address add fe80::1/64 nodad dev br1
-	# Wait the default Query Response Interval (10 seconds) for the bridge
-	# to determine that there are no other queriers in the network.
 	sleep 10
 
 	test_l2_miss_multicast_ipv4
@@ -224,6 +227,7 @@ test_l2_miss_multicast()
 
 	ip -6 address del fe80::1/64 dev br1
 	ip link set dev br1 type bridge mcast_querier 0
+	ip link set dev br1 type bridge mcast_query_response_interval 1000
 	bridge link set dev $swp2 mcast_router 1
 }
 
diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh
index 19352f106c1d..02c21ff4ca81 100755
--- a/tools/testing/selftests/net/gro.sh
+++ b/tools/testing/selftests/net/gro.sh
@@ -31,6 +31,11 @@ run_test() {
       1>>log.txt
     wait "${server_pid}"
     exit_code=$?
+    if [[ ${test} == "large" && -n "${KSFT_MACHINE_SLOW}" && \
+          ${exit_code} -ne 0 ]]; then
+        echo "Ignoring errors due to slow environment" 1>&2
+        exit_code=0
+    fi
     if [[ "${exit_code}" -eq 0 ]]; then
         break;
     fi
diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh
index fe59ca3e5596..12491850ae98 100755
--- a/tools/testing/selftests/net/ioam6.sh
+++ b/tools/testing/selftests/net/ioam6.sh
@@ -367,14 +367,12 @@ run_test()
   local desc=$2
   local node_src=$3
   local node_dst=$4
-  local ip6_src=$5
-  local ip6_dst=$6
-  local if_dst=$7
-  local trace_type=$8
-  local ioam_ns=$9
-
-  ip netns exec $node_dst ./ioam6_parser $if_dst $name $ip6_src $ip6_dst \
-         $trace_type $ioam_ns &
+  local ip6_dst=$5
+  local trace_type=$6
+  local ioam_ns=$7
+  local type=$8
+
+  ip netns exec $node_dst ./ioam6_parser $name $trace_type $ioam_ns $type &
   local spid=$!
   sleep 0.1
 
@@ -489,7 +487,7 @@ out_undef_ns()
          trace prealloc type 0x800000 ns 0 size 4 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0x800000 0
+         db01::1 0x800000 0 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
@@ -509,7 +507,7 @@ out_no_room()
          trace prealloc type 0xc00000 ns 123 size 4 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0xc00000 123
+         db01::1 0xc00000 123 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
@@ -543,14 +541,14 @@ out_bits()
       if [ $cmd_res != 0 ]
       then
         npassed=$((npassed+1))
-        log_test_passed "$descr"
+        log_test_passed "$descr ($1 mode)"
       else
         nfailed=$((nfailed+1))
-        log_test_failed "$descr"
+        log_test_failed "$descr ($1 mode)"
       fi
     else
 	run_test "out_bit$i" "$descr ($1 mode)" $ioam_node_alpha \
-           $ioam_node_beta db01::2 db01::1 veth0 ${bit2type[$i]} 123
+           $ioam_node_beta db01::1 ${bit2type[$i]} 123 $1
     fi
   done
 
@@ -574,7 +572,7 @@ out_full_supp_trace()
          trace prealloc type 0xfff002 ns 123 size 100 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0xfff002 123
+         db01::1 0xfff002 123 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
@@ -604,7 +602,7 @@ in_undef_ns()
          trace prealloc type 0x800000 ns 0 size 4 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0x800000 0
+         db01::1 0x800000 0 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
@@ -624,7 +622,7 @@ in_no_room()
          trace prealloc type 0xc00000 ns 123 size 4 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0xc00000 123
+         db01::1 0xc00000 123 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
@@ -651,7 +649,7 @@ in_bits()
            dev veth0
 
     run_test "in_bit$i" "${desc/<n>/$i} ($1 mode)" $ioam_node_alpha \
-           $ioam_node_beta db01::2 db01::1 veth0 ${bit2type[$i]} 123
+           $ioam_node_beta db01::1 ${bit2type[$i]} 123 $1
   done
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
@@ -679,7 +677,7 @@ in_oflag()
          trace prealloc type 0xc00000 ns 123 size 4 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0xc00000 123
+         db01::1 0xc00000 123 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 
@@ -703,7 +701,7 @@ in_full_supp_trace()
          trace prealloc type 0xfff002 ns 123 size 80 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0xfff002 123
+         db01::1 0xfff002 123 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
@@ -731,7 +729,7 @@ fwd_full_supp_trace()
          trace prealloc type 0xfff002 ns 123 size 244 via db01::1 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_gamma \
-         db01::2 db02::2 veth0 0xfff002 123
+         db02::2 0xfff002 123 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_gamma link set ip6tnl0 down
 }
diff --git a/tools/testing/selftests/net/ioam6_parser.c b/tools/testing/selftests/net/ioam6_parser.c
index d9d1d4190126..895e5bb5044b 100644
--- a/tools/testing/selftests/net/ioam6_parser.c
+++ b/tools/testing/selftests/net/ioam6_parser.c
@@ -8,7 +8,6 @@
 #include <errno.h>
 #include <limits.h>
 #include <linux/const.h>
-#include <linux/if_ether.h>
 #include <linux/ioam6.h>
 #include <linux/ipv6.h>
 #include <stdlib.h>
@@ -512,14 +511,6 @@ static int str2id(const char *tname)
 	return -1;
 }
 
-static int ipv6_addr_equal(const struct in6_addr *a1, const struct in6_addr *a2)
-{
-	return ((a1->s6_addr32[0] ^ a2->s6_addr32[0]) |
-		(a1->s6_addr32[1] ^ a2->s6_addr32[1]) |
-		(a1->s6_addr32[2] ^ a2->s6_addr32[2]) |
-		(a1->s6_addr32[3] ^ a2->s6_addr32[3])) == 0;
-}
-
 static int get_u32(__u32 *val, const char *arg, int base)
 {
 	unsigned long res;
@@ -603,70 +594,80 @@ static int (*func[__TEST_MAX])(int, struct ioam6_trace_hdr *, __u32, __u16) = {
 
 int main(int argc, char **argv)
 {
-	int fd, size, hoplen, tid, ret = 1;
-	struct in6_addr src, dst;
+	int fd, size, hoplen, tid, ret = 1, on = 1;
 	struct ioam6_hdr *opt;
-	struct ipv6hdr *ip6h;
-	__u8 buffer[400], *p;
-	__u16 ioam_ns;
+	struct cmsghdr *cmsg;
+	struct msghdr msg;
+	struct iovec iov;
+	__u8 buffer[512];
 	__u32 tr_type;
+	__u16 ioam_ns;
+	__u8 *ptr;
 
-	if (argc != 7)
+	if (argc != 5)
 		goto out;
 
-	tid = str2id(argv[2]);
+	tid = str2id(argv[1]);
 	if (tid < 0 || !func[tid])
 		goto out;
 
-	if (inet_pton(AF_INET6, argv[3], &src) != 1 ||
-	    inet_pton(AF_INET6, argv[4], &dst) != 1)
+	if (get_u32(&tr_type, argv[2], 16) ||
+	    get_u16(&ioam_ns, argv[3], 0))
 		goto out;
 
-	if (get_u32(&tr_type, argv[5], 16) ||
-	    get_u16(&ioam_ns, argv[6], 0))
+	fd = socket(PF_INET6, SOCK_RAW,
+		    !strcmp(argv[4], "encap") ? IPPROTO_IPV6 : IPPROTO_ICMPV6);
+	if (fd < 0)
 		goto out;
 
-	fd = socket(AF_PACKET, SOCK_DGRAM, __cpu_to_be16(ETH_P_IPV6));
-	if (!fd)
-		goto out;
+	setsockopt(fd, IPPROTO_IPV6, IPV6_RECVHOPOPTS,  &on, sizeof(on));
 
-	if (setsockopt(fd, SOL_SOCKET, SO_BINDTODEVICE,
-		       argv[1], strlen(argv[1])))
+	iov.iov_len = 1;
+	iov.iov_base = malloc(CMSG_SPACE(sizeof(buffer)));
+	if (!iov.iov_base)
 		goto close;
-
 recv:
-	size = recv(fd, buffer, sizeof(buffer), 0);
+	memset(&msg, 0, sizeof(msg));
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+	msg.msg_control = buffer;
+	msg.msg_controllen = CMSG_SPACE(sizeof(buffer));
+
+	size = recvmsg(fd, &msg, 0);
 	if (size <= 0)
 		goto close;
 
-	ip6h = (struct ipv6hdr *)buffer;
+	for (cmsg = CMSG_FIRSTHDR(&msg); cmsg; cmsg = CMSG_NXTHDR(&msg, cmsg)) {
+		if (cmsg->cmsg_level != IPPROTO_IPV6 ||
+		    cmsg->cmsg_type != IPV6_HOPOPTS ||
+		    cmsg->cmsg_len < sizeof(struct ipv6_hopopt_hdr))
+			continue;
 
-	if (!ipv6_addr_equal(&ip6h->saddr, &src) ||
-	    !ipv6_addr_equal(&ip6h->daddr, &dst))
-		goto recv;
+		ptr = (__u8 *)CMSG_DATA(cmsg);
 
-	if (ip6h->nexthdr != IPPROTO_HOPOPTS)
-		goto close;
+		hoplen = (ptr[1] + 1) << 3;
+		ptr += sizeof(struct ipv6_hopopt_hdr);
 
-	p = buffer + sizeof(*ip6h);
-	hoplen = (p[1] + 1) << 3;
-	p += sizeof(struct ipv6_hopopt_hdr);
+		while (hoplen > 0) {
+			opt = (struct ioam6_hdr *)ptr;
 
-	while (hoplen > 0) {
-		opt = (struct ioam6_hdr *)p;
+			if (opt->opt_type == IPV6_TLV_IOAM &&
+			    opt->type == IOAM6_TYPE_PREALLOC) {
+				ptr += sizeof(*opt);
+				ret = func[tid](tid,
+						(struct ioam6_trace_hdr *)ptr,
+						tr_type, ioam_ns);
+				goto close;
+			}
 
-		if (opt->opt_type == IPV6_TLV_IOAM &&
-		    opt->type == IOAM6_TYPE_PREALLOC) {
-			p += sizeof(*opt);
-			ret = func[tid](tid, (struct ioam6_trace_hdr *)p,
-					   tr_type, ioam_ns);
-			break;
+			ptr += opt->opt_len + 2;
+			hoplen -= opt->opt_len + 2;
 		}
-
-		p += opt->opt_len + 2;
-		hoplen -= opt->opt_len + 2;
 	}
+
+	goto recv;
 close:
+	free(iov.iov_base);
 	close(fd);
 out:
 	return ret;
diff --git a/tools/testing/selftests/net/ip_local_port_range.c b/tools/testing/selftests/net/ip_local_port_range.c
index 0f217a1cc837..6ebd58869a63 100644
--- a/tools/testing/selftests/net/ip_local_port_range.c
+++ b/tools/testing/selftests/net/ip_local_port_range.c
@@ -16,6 +16,10 @@
 #define IP_LOCAL_PORT_RANGE 51
 #endif
 
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+
 static __u32 pack_port_range(__u16 lo, __u16 hi)
 {
 	return (hi << 16) | (lo << 0);
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index dca549443801..f9fe182dfbd4 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -4,6 +4,9 @@
 ##############################################################################
 # Defines
 
+WAIT_TIMEOUT=${WAIT_TIMEOUT:=20}
+BUSYWAIT_TIMEOUT=$((WAIT_TIMEOUT * 1000)) # ms
+
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
 # namespace list created by setup_ns
@@ -48,7 +51,7 @@ cleanup_ns()
 
 	for ns in "$@"; do
 		ip netns delete "${ns}" &> /dev/null
-		if ! busywait 2 ip netns list \| grep -vq "^$ns$" &> /dev/null; then
+		if ! busywait $BUSYWAIT_TIMEOUT ip netns list \| grep -vq "^$ns$" &> /dev/null; then
 			echo "Warn: Failed to remove namespace $ns"
 			ret=1
 		fi
diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config
index e317c2e44dae..4f80014cae49 100644
--- a/tools/testing/selftests/net/mptcp/config
+++ b/tools/testing/selftests/net/mptcp/config
@@ -22,8 +22,11 @@ CONFIG_NFT_TPROXY=m
 CONFIG_NFT_SOCKET=m
 CONFIG_IP_ADVANCED_ROUTER=y
 CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_NF_FILTER=m
+CONFIG_IP_NF_MANGLE=m
 CONFIG_IP_NF_TARGET_REJECT=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_IP6_NF_FILTER=m
 CONFIG_NET_ACT_CSUM=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_CLS_ACT=y
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 04fcb8a077c9..75fc95675e2d 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -20,7 +20,7 @@ flush_pids()
 
 	ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGUSR1 &>/dev/null
 
-	for _ in $(seq 10); do
+	for _ in $(seq $((timeout_poll * 10))); do
 		[ -z "$(ip netns pids "${ns}")" ] && break
 		sleep 0.1
 	done
@@ -62,14 +62,14 @@ __chk_nr()
 	nr=$(eval $command)
 
 	printf "%-50s" "$msg"
-	if [ $nr != $expected ]; then
-		if [ $nr = "$skip" ] && ! mptcp_lib_expect_all_features; then
+	if [ "$nr" != "$expected" ]; then
+		if [ "$nr" = "$skip" ] && ! mptcp_lib_expect_all_features; then
 			echo "[ skip ] Feature probably not supported"
 			mptcp_lib_result_skip "${msg}"
 		else
 			echo "[ fail ] expected $expected found $nr"
 			mptcp_lib_result_fail "${msg}"
-			ret=$test_cnt
+			ret=${KSFT_FAIL}
 		fi
 	else
 		echo "[  ok  ]"
@@ -91,6 +91,15 @@ chk_msk_nr()
 	__chk_msk_nr "grep -c token:" "$@"
 }
 
+chk_listener_nr()
+{
+	local expected=$1
+	local msg="$2"
+
+	__chk_nr "ss -nlHMON $ns | wc -l" "$expected" "$msg - mptcp" 0
+	__chk_nr "ss -nlHtON $ns | wc -l" "$expected" "$msg - subflows"
+}
+
 wait_msk_nr()
 {
 	local condition="grep -c token:"
@@ -115,11 +124,11 @@ wait_msk_nr()
 	if [ $i -ge $timeout ]; then
 		echo "[ fail ] timeout while expecting $expected max $max last $nr"
 		mptcp_lib_result_fail "${msg} # timeout"
-		ret=$test_cnt
+		ret=${KSFT_FAIL}
 	elif [ $nr != $expected ]; then
 		echo "[ fail ] expected $expected found $nr"
 		mptcp_lib_result_fail "${msg} # unexpected result"
-		ret=$test_cnt
+		ret=${KSFT_FAIL}
 	else
 		echo "[  ok  ]"
 		mptcp_lib_result_pass "${msg}"
@@ -166,9 +175,13 @@ chk_msk_listen()
 chk_msk_inuse()
 {
 	local expected=$1
-	local msg="$2"
+	local msg="....chk ${2:-${expected}} msk in use"
 	local listen_nr
 
+	if [ "${expected}" -eq 0 ]; then
+		msg+=" after flush"
+	fi
+
 	listen_nr=$(ss -N "${ns}" -Ml | grep -c LISTEN)
 	expected=$((expected + listen_nr))
 
@@ -179,16 +192,21 @@ chk_msk_inuse()
 		sleep 0.1
 	done
 
-	__chk_nr get_msk_inuse $expected "$msg" 0
+	__chk_nr get_msk_inuse $expected "${msg}" 0
 }
 
 # $1: cestab nr
 chk_msk_cestab()
 {
-	local cestab=$1
+	local expected=$1
+	local msg="....chk ${2:-${expected}} cestab"
+
+	if [ "${expected}" -eq 0 ]; then
+		msg+=" after flush"
+	fi
 
 	__chk_nr "mptcp_lib_get_counter ${ns} MPTcpExtMPCurrEstab" \
-		 "${cestab}" "....chk ${cestab} cestab" ""
+		 "${expected}" "${msg}" ""
 }
 
 wait_connected()
@@ -227,12 +245,12 @@ wait_connected $ns 10000
 chk_msk_nr 2 "after MPC handshake "
 chk_msk_remote_key_nr 2 "....chk remote_key"
 chk_msk_fallback_nr 0 "....chk no fallback"
-chk_msk_inuse 2 "....chk 2 msk in use"
+chk_msk_inuse 2
 chk_msk_cestab 2
 flush_pids
 
-chk_msk_inuse 0 "....chk 0 msk in use after flush"
-chk_msk_cestab 0
+chk_msk_inuse 0 "2->0"
+chk_msk_cestab 0 "2->0"
 
 echo "a" | \
 	timeout ${timeout_test} \
@@ -247,12 +265,12 @@ echo "b" | \
 				127.0.0.1 >/dev/null &
 wait_connected $ns 10001
 chk_msk_fallback_nr 1 "check fallback"
-chk_msk_inuse 1 "....chk 1 msk in use"
+chk_msk_inuse 1
 chk_msk_cestab 1
 flush_pids
 
-chk_msk_inuse 0 "....chk 0 msk in use after flush"
-chk_msk_cestab 0
+chk_msk_inuse 0 "1->0"
+chk_msk_cestab 0 "1->0"
 
 NR_CLIENTS=100
 for I in `seq 1 $NR_CLIENTS`; do
@@ -273,12 +291,28 @@ for I in `seq 1 $NR_CLIENTS`; do
 done
 
 wait_msk_nr $((NR_CLIENTS*2)) "many msk socket present"
-chk_msk_inuse $((NR_CLIENTS*2)) "....chk many msk in use"
-chk_msk_cestab $((NR_CLIENTS*2))
+chk_msk_inuse $((NR_CLIENTS*2)) "many"
+chk_msk_cestab $((NR_CLIENTS*2)) "many"
 flush_pids
 
-chk_msk_inuse 0 "....chk 0 msk in use after flush"
-chk_msk_cestab 0
+chk_msk_inuse 0 "many->0"
+chk_msk_cestab 0 "many->0"
+
+chk_listener_nr 0 "no listener sockets"
+NR_SERVERS=100
+for I in $(seq 1 $NR_SERVERS); do
+	ip netns exec $ns ./mptcp_connect -p $((I + 20001)) \
+		-t ${timeout_poll} -l 0.0.0.0 >/dev/null 2>&1 &
+done
+mptcp_lib_wait_local_port_listen $ns $((NR_SERVERS + 20001))
+
+chk_listener_nr $NR_SERVERS "many listener sockets"
+
+# graceful termination
+for I in $(seq 1 $NR_SERVERS); do
+	echo a | ip netns exec $ns ./mptcp_connect -p $((I + 20001)) 127.0.0.1 >/dev/null 2>&1 &
+done
+flush_pids
 
 mptcp_lib_result_print_all_tap
 exit $ret
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 3a5b63026191..e4581b0dfb96 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -161,6 +161,11 @@ check_tools()
 		exit $ksft_skip
 	fi
 
+	if ! ss -h | grep -q MPTCP; then
+		echo "SKIP: ss tool does not support MPTCP"
+		exit $ksft_skip
+	fi
+
 	# Use the legacy version if available to support old kernel versions
 	if iptables-legacy -V &> /dev/null; then
 		iptables="iptables-legacy"
@@ -643,13 +648,6 @@ kill_events_pids()
 	mptcp_lib_kill_wait $evts_ns2_pid
 }
 
-kill_tests_wait()
-{
-	#shellcheck disable=SC2046
-	kill -SIGUSR1 $(ip netns pids $ns2) $(ip netns pids $ns1)
-	wait
-}
-
 pm_nl_set_limits()
 {
 	local ns=$1
@@ -3340,16 +3338,17 @@ userspace_pm_rm_sf()
 {
 	local evts=$evts_ns1
 	local t=${3:-1}
-	local ip=4
+	local ip
 	local tk da dp sp
 	local cnt
 
 	[ "$1" == "$ns2" ] && evts=$evts_ns2
-	if mptcp_lib_is_v6 $2; then ip=6; fi
+	[ -n "$(mptcp_lib_evts_get_info "saddr4" "$evts" $t)" ] && ip=4
+	[ -n "$(mptcp_lib_evts_get_info "saddr6" "$evts" $t)" ] && ip=6
 	tk=$(mptcp_lib_evts_get_info token "$evts")
-	da=$(mptcp_lib_evts_get_info "daddr$ip" "$evts" $t)
-	dp=$(mptcp_lib_evts_get_info dport "$evts" $t)
-	sp=$(mptcp_lib_evts_get_info sport "$evts" $t)
+	da=$(mptcp_lib_evts_get_info "daddr$ip" "$evts" $t $2)
+	dp=$(mptcp_lib_evts_get_info dport "$evts" $t $2)
+	sp=$(mptcp_lib_evts_get_info sport "$evts" $t $2)
 
 	cnt=$(rm_sf_count ${1})
 	ip netns exec $1 ./pm_nl_ctl dsf lip $2 lport $sp \
@@ -3436,24 +3435,27 @@ userspace_tests()
 	if reset_with_events "userspace pm add & remove address" &&
 	   continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
 		set_userspace_pm $ns1
-		pm_nl_set_limits $ns2 1 1
+		pm_nl_set_limits $ns2 2 2
 		speed=5 \
 			run_tests $ns1 $ns2 10.0.1.1 &
 		local tests_pid=$!
 		wait_mpj $ns1
 		userspace_pm_add_addr $ns1 10.0.2.1 10
-		chk_join_nr 1 1 1
-		chk_add_nr 1 1
-		chk_mptcp_info subflows 1 subflows 1
-		chk_subflows_total 2 2
-		chk_mptcp_info add_addr_signal 1 add_addr_accepted 1
+		userspace_pm_add_addr $ns1 10.0.3.1 20
+		chk_join_nr 2 2 2
+		chk_add_nr 2 2
+		chk_mptcp_info subflows 2 subflows 2
+		chk_subflows_total 3 3
+		chk_mptcp_info add_addr_signal 2 add_addr_accepted 2
 		userspace_pm_rm_addr $ns1 10
 		userspace_pm_rm_sf $ns1 "::ffff:10.0.2.1" $SUB_ESTABLISHED
-		chk_rm_nr 1 1 invert
+		userspace_pm_rm_addr $ns1 20
+		userspace_pm_rm_sf $ns1 10.0.3.1 $SUB_ESTABLISHED
+		chk_rm_nr 2 2 invert
 		chk_mptcp_info subflows 0 subflows 0
 		chk_subflows_total 1 1
 		kill_events_pids
-		wait $tests_pid
+		mptcp_lib_kill_wait $tests_pid
 	fi
 
 	# userspace pm create destroy subflow
@@ -3475,7 +3477,7 @@ userspace_tests()
 		chk_mptcp_info subflows 0 subflows 0
 		chk_subflows_total 1 1
 		kill_events_pids
-		wait $tests_pid
+		mptcp_lib_kill_wait $tests_pid
 	fi
 
 	# userspace pm create id 0 subflow
@@ -3494,7 +3496,7 @@ userspace_tests()
 		chk_mptcp_info subflows 1 subflows 1
 		chk_subflows_total 2 2
 		kill_events_pids
-		wait $tests_pid
+		mptcp_lib_kill_wait $tests_pid
 	fi
 
 	# userspace pm remove initial subflow
@@ -3518,7 +3520,7 @@ userspace_tests()
 		chk_mptcp_info subflows 1 subflows 1
 		chk_subflows_total 1 1
 		kill_events_pids
-		wait $tests_pid
+		mptcp_lib_kill_wait $tests_pid
 	fi
 
 	# userspace pm send RM_ADDR for ID 0
@@ -3544,7 +3546,7 @@ userspace_tests()
 		chk_mptcp_info subflows 1 subflows 1
 		chk_subflows_total 1 1
 		kill_events_pids
-		wait $tests_pid
+		mptcp_lib_kill_wait $tests_pid
 	fi
 }
 
@@ -3558,7 +3560,8 @@ endpoint_tests()
 		pm_nl_set_limits $ns2 2 2
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
 		speed=slow \
-			run_tests $ns1 $ns2 10.0.1.1 2>/dev/null &
+			run_tests $ns1 $ns2 10.0.1.1 &
+		local tests_pid=$!
 
 		wait_mpj $ns1
 		pm_nl_check_endpoint "creation" \
@@ -3573,7 +3576,7 @@ endpoint_tests()
 		pm_nl_add_endpoint $ns2 10.0.2.2 flags signal
 		pm_nl_check_endpoint "modif is allowed" \
 			$ns2 10.0.2.2 id 1 flags signal
-		kill_tests_wait
+		mptcp_lib_kill_wait $tests_pid
 	fi
 
 	if reset "delete and re-add" &&
@@ -3582,7 +3585,8 @@ endpoint_tests()
 		pm_nl_set_limits $ns2 1 1
 		pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow
 		test_linkfail=4 speed=20 \
-			run_tests $ns1 $ns2 10.0.1.1 2>/dev/null &
+			run_tests $ns1 $ns2 10.0.1.1 &
+		local tests_pid=$!
 
 		wait_mpj $ns2
 		chk_subflow_nr "before delete" 2
@@ -3597,7 +3601,7 @@ endpoint_tests()
 		wait_mpj $ns2
 		chk_subflow_nr "after re-add" 2
 		chk_mptcp_info subflows 1 subflows 1
-		kill_tests_wait
+		mptcp_lib_kill_wait $tests_pid
 	fi
 }
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index 022262a2cfe0..3777d66fc56d 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -6,7 +6,7 @@ readonly KSFT_FAIL=1
 readonly KSFT_SKIP=4
 
 # shellcheck disable=SC2155 # declare and assign separately
-readonly KSFT_TEST=$(basename "${0}" | sed 's/\.sh$//g')
+readonly KSFT_TEST="${MPTCP_LIB_KSFT_TEST:-$(basename "${0}" .sh)}"
 
 MPTCP_LIB_SUBTESTS=()
 
@@ -213,9 +213,9 @@ mptcp_lib_get_info_value() {
 	grep "${2}" | sed -n 's/.*\('"${1}"':\)\([0-9a-f:.]*\).*$/\2/p;q'
 }
 
-# $1: info name ; $2: evts_ns ; $3: event type
+# $1: info name ; $2: evts_ns ; [$3: event type; [$4: addr]]
 mptcp_lib_evts_get_info() {
-	mptcp_lib_get_info_value "${1}" "^type:${3:-1}," < "${2}"
+	grep "${4:-}" "${2}" | mptcp_lib_get_info_value "${1}" "^type:${3:-1},"
 }
 
 # $1: PID
diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index 8f4ff123a7eb..71899a3ffa7a 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -183,7 +183,7 @@ check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \
 subflow 10.0.1.1" "          (nobackup)"
 
 # fullmesh support has been added later
-ip netns exec $ns1 ./pm_nl_ctl set id 1 flags fullmesh
+ip netns exec $ns1 ./pm_nl_ctl set id 1 flags fullmesh 2>/dev/null
 if ip netns exec $ns1 ./pm_nl_ctl dump | grep -q "fullmesh" ||
    mptcp_lib_expect_all_features; then
 	check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \
@@ -194,6 +194,12 @@ subflow 10.0.1.1" "          (nofullmesh)"
 	ip netns exec $ns1 ./pm_nl_ctl set id 1 flags backup,fullmesh
 	check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \
 subflow,backup,fullmesh 10.0.1.1" "          (backup,fullmesh)"
+else
+	for st in fullmesh nofullmesh backup,fullmesh; do
+		st="          (${st})"
+		printf "%-50s%s\n" "${st}" "[SKIP]"
+		mptcp_lib_result_skip "${st}"
+	done
 fi
 
 mptcp_lib_result_print_all_tap
diff --git a/tools/testing/selftests/net/mptcp/settings b/tools/testing/selftests/net/mptcp/settings
index 79b65bdf05db..abc5648b59ab 100644
--- a/tools/testing/selftests/net/mptcp/settings
+++ b/tools/testing/selftests/net/mptcp/settings
@@ -1 +1 @@
-timeout=1200
+timeout=1800
diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index ae8ad5d6fb9d..8f9ddb3ad4fe 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -250,7 +250,8 @@ run_test()
 		[ $bail -eq 0 ] || exit $ret
 	fi
 
-	printf "%-60s" "$msg - reverse direction"
+	msg+=" - reverse direction"
+	printf "%-60s" "${msg}"
 	do_transfer $large $small $time
 	lret=$?
 	mptcp_lib_result_code "${lret}" "${msg}"
@@ -284,12 +285,12 @@ done
 
 setup
 run_test 10 10 0 0 "balanced bwidth"
-run_test 10 10 1 50 "balanced bwidth with unbalanced delay"
+run_test 10 10 1 25 "balanced bwidth with unbalanced delay"
 
 # we still need some additional infrastructure to pass the following test-cases
-run_test 30 10 0 0 "unbalanced bwidth"
-run_test 30 10 1 50 "unbalanced bwidth with unbalanced delay"
-run_test 30 10 50 1 "unbalanced bwidth with opposed, unbalanced delay"
+run_test 10 3 0 0 "unbalanced bwidth"
+run_test 10 3 1 25 "unbalanced bwidth with unbalanced delay"
+run_test 10 3 25 1 "unbalanced bwidth with opposed, unbalanced delay"
 
 mptcp_lib_result_print_all_tap
 exit $ret
diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index 6167837f48e1..1b94a75604fe 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -75,7 +75,7 @@ print_test()
 {
 	test_name="${1}"
 
-	_printf "%-63s" "${test_name}"
+	_printf "%-68s" "${test_name}"
 }
 
 print_results()
@@ -542,7 +542,7 @@ verify_subflow_events()
 	local remid
 	local info
 
-	info="${e_saddr} (${e_from}) => ${e_daddr} (${e_to})"
+	info="${e_saddr} (${e_from}) => ${e_daddr}:${e_dport} (${e_to})"
 
 	if [ "$e_type" = "$SUB_ESTABLISHED" ]
 	then
diff --git a/tools/testing/selftests/net/net_helper.sh b/tools/testing/selftests/net/net_helper.sh
index 4fe0befa13fb..6596fe03c77f 100755..100644
--- a/tools/testing/selftests/net/net_helper.sh
+++ b/tools/testing/selftests/net/net_helper.sh
@@ -8,13 +8,16 @@ wait_local_port_listen()
 	local listener_ns="${1}"
 	local port="${2}"
 	local protocol="${3}"
-	local port_hex
+	local pattern
 	local i
 
-	port_hex="$(printf "%04X" "${port}")"
+	pattern=":$(printf "%04X" "${port}") "
+
+	# for tcp protocol additionally check the socket state
+	[ ${protocol} = "tcp" ] && pattern="${pattern}0A"
 	for i in $(seq 10); do
-		if ip netns exec "${listener_ns}" cat /proc/net/"${protocol}"* | \
-		   grep -q "${port_hex}"; then
+		if ip netns exec "${listener_ns}" awk '{print $2" "$4}' \
+		   /proc/net/"${protocol}"* | grep -q "${pattern}"; then
 			break
 		fi
 		sleep 0.1
diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
index f8499d4c87f3..36e40256ab92 100755
--- a/tools/testing/selftests/net/openvswitch/openvswitch.sh
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -502,9 +502,22 @@ test_netlink_checks () {
 	    wc -l) == 2 ] || \
 	      return 1
 
+	info "Checking clone depth"
 	ERR_MSG="Flow actions may not be safe on all matching packets"
 	PRE_TEST=$(dmesg | grep -c "${ERR_MSG}")
 	ovs_add_flow "test_netlink_checks" nv0 \
+		'in_port(1),eth(),eth_type(0x800),ipv4()' \
+		'clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(drop)))))))))))))))))' \
+		>/dev/null 2>&1 && return 1
+	POST_TEST=$(dmesg | grep -c "${ERR_MSG}")
+
+	if [ "$PRE_TEST" == "$POST_TEST" ]; then
+		info "failed - clone depth too large"
+		return 1
+	fi
+
+	PRE_TEST=$(dmesg | grep -c "${ERR_MSG}")
+	ovs_add_flow "test_netlink_checks" nv0 \
 		'in_port(1),eth(),eth_type(0x0806),arp()' 'drop(0),2' \
 		&> /dev/null && return 1
 	POST_TEST=$(dmesg | grep -c "${ERR_MSG}")
diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
index b97e621face9..5e0e539a323d 100644
--- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
+++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
@@ -299,7 +299,7 @@ class ovsactions(nla):
         ("OVS_ACTION_ATTR_PUSH_NSH", "none"),
         ("OVS_ACTION_ATTR_POP_NSH", "flag"),
         ("OVS_ACTION_ATTR_METER", "none"),
-        ("OVS_ACTION_ATTR_CLONE", "none"),
+        ("OVS_ACTION_ATTR_CLONE", "recursive"),
         ("OVS_ACTION_ATTR_CHECK_PKT_LEN", "none"),
         ("OVS_ACTION_ATTR_ADD_MPLS", "none"),
         ("OVS_ACTION_ATTR_DEC_TTL", "none"),
@@ -465,29 +465,42 @@ class ovsactions(nla):
                     print_str += "pop_mpls"
             else:
                 datum = self.get_attr(field[0])
-                print_str += datum.dpstr(more)
+                if field[0] == "OVS_ACTION_ATTR_CLONE":
+                    print_str += "clone("
+                    print_str += datum.dpstr(more)
+                    print_str += ")"
+                else:
+                    print_str += datum.dpstr(more)
 
         return print_str
 
     def parse(self, actstr):
+        totallen = len(actstr)
         while len(actstr) != 0:
             parsed = False
+            parencount = 0
             if actstr.startswith("drop"):
                 # If no reason is provided, the implicit drop is used (i.e no
                 # action). If some reason is given, an explicit action is used.
-                actstr, reason = parse_extract_field(
-                    actstr,
-                    "drop(",
-                    "([0-9]+)",
-                    lambda x: int(x, 0),
-                    False,
-                    None,
-                )
+                reason = None
+                if actstr.startswith("drop("):
+                    parencount += 1
+
+                    actstr, reason = parse_extract_field(
+                        actstr,
+                        "drop(",
+                        "([0-9]+)",
+                        lambda x: int(x, 0),
+                        False,
+                        None,
+                    )
+
                 if reason is not None:
                     self["attrs"].append(["OVS_ACTION_ATTR_DROP", reason])
                     parsed = True
                 else:
-                    return
+                    actstr = actstr[len("drop"): ]
+                    return (totallen - len(actstr))
 
             elif parse_starts_block(actstr, "^(\d+)", False, True):
                 actstr, output = parse_extract_field(
@@ -504,6 +517,7 @@ class ovsactions(nla):
                     False,
                     0,
                 )
+                parencount += 1
                 self["attrs"].append(["OVS_ACTION_ATTR_RECIRC", recircid])
                 parsed = True
 
@@ -516,12 +530,22 @@ class ovsactions(nla):
 
             for flat_act in parse_flat_map:
                 if parse_starts_block(actstr, flat_act[0], False):
-                    actstr += len(flat_act[0])
+                    actstr = actstr[len(flat_act[0]):]
                     self["attrs"].append([flat_act[1]])
                     actstr = actstr[strspn(actstr, ", ") :]
                     parsed = True
 
-            if parse_starts_block(actstr, "ct(", False):
+            if parse_starts_block(actstr, "clone(", False):
+                parencount += 1
+                subacts = ovsactions()
+                actstr = actstr[len("clone("):]
+                parsedLen = subacts.parse(actstr)
+                lst = []
+                self["attrs"].append(("OVS_ACTION_ATTR_CLONE", subacts))
+                actstr = actstr[parsedLen:]
+                parsed = True
+            elif parse_starts_block(actstr, "ct(", False):
+                parencount += 1
                 actstr = actstr[len("ct(") :]
                 ctact = ovsactions.ctact()
 
@@ -553,6 +577,7 @@ class ovsactions(nla):
                         natact = ovsactions.ctact.natattr()
 
                         if actstr.startswith("("):
+                            parencount += 1
                             t = None
                             actstr = actstr[1:]
                             if actstr.startswith("src"):
@@ -607,15 +632,29 @@ class ovsactions(nla):
                                     actstr = actstr[strspn(actstr, ", ") :]
 
                         ctact["attrs"].append(["OVS_CT_ATTR_NAT", natact])
-                        actstr = actstr[strspn(actstr, ",) ") :]
+                        actstr = actstr[strspn(actstr, ", ") :]
 
                 self["attrs"].append(["OVS_ACTION_ATTR_CT", ctact])
                 parsed = True
 
-            actstr = actstr[strspn(actstr, "), ") :]
+            actstr = actstr[strspn(actstr, ", ") :]
+            while parencount > 0:
+                parencount -= 1
+                actstr = actstr[strspn(actstr, " "):]
+                if len(actstr) and actstr[0] != ")":
+                    raise ValueError("Action str: '%s' unbalanced" % actstr)
+                actstr = actstr[1:]
+
+            if len(actstr) and actstr[0] == ")":
+                return (totallen - len(actstr))
+
+            actstr = actstr[strspn(actstr, ", ") :]
+
             if not parsed:
                 raise ValueError("Action str: '%s' not supported" % actstr)
 
+        return (totallen - len(actstr))
+
 
 class ovskey(nla):
     nla_flags = NLA_F_NESTED
@@ -2111,6 +2150,8 @@ def main(argv):
     ovsflow = OvsFlow()
     ndb = NDB()
 
+    sys.setrecursionlimit(100000)
+
     if hasattr(args, "showdp"):
         found = False
         for iface in ndb.interfaces:
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index f10879788f61..cfc84958025a 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -199,6 +199,7 @@
 #	Same as above but with IPv6
 
 source lib.sh
+source net_helper.sh
 
 PAUSE_ON_FAIL=no
 VERBOSE=0
@@ -707,23 +708,23 @@ setup_xfrm6() {
 }
 
 setup_xfrm4udp() {
-	setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0"
-	setup_nettest_xfrm 4 4500
+	setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0" && \
+		setup_nettest_xfrm 4 4500
 }
 
 setup_xfrm6udp() {
-	setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0"
-	setup_nettest_xfrm 6 4500
+	setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0" && \
+		setup_nettest_xfrm 6 4500
 }
 
 setup_xfrm4udprouted() {
-	setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0"
-	setup_nettest_xfrm 4 4500
+	setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0" && \
+		setup_nettest_xfrm 4 4500
 }
 
 setup_xfrm6udprouted() {
-	setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0"
-	setup_nettest_xfrm 6 4500
+	setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0" && \
+		setup_nettest_xfrm 6 4500
 }
 
 setup_routing_old() {
@@ -1335,12 +1336,14 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() {
 		else
 			TCPDST="TCP:[${dst}]:50000"
 		fi
-		${ns_b} socat -T 3 -u -6 TCP-LISTEN:50000 STDOUT > $tmpoutfile &
+		${ns_b} socat -T 3 -u -6 TCP-LISTEN:50000,reuseaddr STDOUT > $tmpoutfile &
+		local socat_pid=$!
 
-		sleep 1
+		wait_local_port_listen ${NS_B} 50000 tcp
 
-		dd if=/dev/zero of=/dev/stdout status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3
+		dd if=/dev/zero status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3
 
+		wait ${socat_pid}
 		size=$(du -sb $tmpoutfile)
 		size=${size%%/tmp/*}
 
@@ -1954,6 +1957,13 @@ check_command() {
 	return 0
 }
 
+check_running() {
+	pid=${1}
+	cmd=${2}
+
+	[ "$(cat /proc/${pid}/cmdline 2>/dev/null | tr -d '\0')" = "{cmd}" ]
+}
+
 test_cleanup_vxlanX_exception() {
 	outer="${1}"
 	encap="vxlan"
@@ -1984,11 +1994,12 @@ test_cleanup_vxlanX_exception() {
 
 	${ns_a} ip link del dev veth_A-R1 &
 	iplink_pid=$!
-	sleep 1
-	if [ "$(cat /proc/${iplink_pid}/cmdline 2>/dev/null | tr -d '\0')" = "iplinkdeldevveth_A-R1" ]; then
-		err "  can't delete veth device in a timely manner, PMTU dst likely leaked"
-		return 1
-	fi
+	for i in $(seq 1 20); do
+		check_running ${iplink_pid} "iplinkdeldevveth_A-R1" || return 0
+		sleep 0.1
+	done
+	err "  can't delete veth device in a timely manner, PMTU dst likely leaked"
+	return 1
 }
 
 test_cleanup_ipv6_exception() {
diff --git a/tools/testing/selftests/net/rps_default_mask.sh b/tools/testing/selftests/net/rps_default_mask.sh
index a26c5624429f..4287a8529890 100755
--- a/tools/testing/selftests/net/rps_default_mask.sh
+++ b/tools/testing/selftests/net/rps_default_mask.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 readonly ksft_skip=4
@@ -33,6 +33,10 @@ chk_rps() {
 
 	rps_mask=$($cmd /sys/class/net/$dev_name/queues/rx-0/rps_cpus)
 	printf "%-60s" "$msg"
+
+	# In case there is more than 32 CPUs we need to remove commas from masks
+	rps_mask=${rps_mask//,}
+	expected_rps_mask=${expected_rps_mask//,}
 	if [ $rps_mask -eq $expected_rps_mask ]; then
 		echo "[ ok ]"
 	else
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index a10a32952f21..874a2952aa8e 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -28,6 +28,7 @@ ALL_TESTS="
 	kci_test_neigh_get
 	kci_test_bridge_parent_id
 	kci_test_address_proto
+	kci_test_enslave_bonding
 "
 
 devdummy="test-dummy0"
@@ -439,7 +440,6 @@ kci_test_encap_vxlan()
 	local ret=0
 	vxlan="test-vxlan0"
 	vlan="test-vlan0"
-	testns="$1"
 	run_cmd ip -netns "$testns" link add "$vxlan" type vxlan id 42 group 239.1.1.1 \
 		dev "$devdummy" dstport 4789
 	if [ $? -ne 0 ]; then
@@ -484,7 +484,6 @@ kci_test_encap_fou()
 {
 	local ret=0
 	name="test-fou"
-	testns="$1"
 	run_cmd_grep 'Usage: ip fou' ip fou help
 	if [ $? -ne 0 ];then
 		end_test "SKIP: fou: iproute2 too old"
@@ -525,8 +524,8 @@ kci_test_encap()
 	run_cmd ip -netns "$testns" link set lo up
 	run_cmd ip -netns "$testns" link add name "$devdummy" type dummy
 	run_cmd ip -netns "$testns" link set "$devdummy" up
-	run_cmd kci_test_encap_vxlan "$testns"
-	run_cmd kci_test_encap_fou "$testns"
+	run_cmd kci_test_encap_vxlan
+	run_cmd kci_test_encap_fou
 
 	ip netns del "$testns"
 	return $ret
@@ -1241,6 +1240,31 @@ kci_test_address_proto()
 	return $ret
 }
 
+kci_test_enslave_bonding()
+{
+	local bond="bond123"
+	local ret=0
+
+	setup_ns testns
+	if [ $? -ne 0 ]; then
+		end_test "SKIP bonding tests: cannot add net namespace $testns"
+		return $ksft_skip
+	fi
+
+	run_cmd ip -netns $testns link add dev $bond type bond mode balance-rr
+	run_cmd ip -netns $testns link add dev $devdummy type dummy
+	run_cmd ip -netns $testns link set dev $devdummy up
+	run_cmd ip -netns $testns link set dev $devdummy master $bond down
+	if [ $ret -ne 0 ]; then
+		end_test "FAIL: initially up interface added to a bond and set down"
+		ip netns del "$testns"
+		return 1
+	fi
+
+	end_test "PASS: enslave interface in a bond"
+	ip netns del "$testns"
+}
+
 kci_test_rtnl()
 {
 	local current_test
diff --git a/tools/testing/selftests/net/setup_loopback.sh b/tools/testing/selftests/net/setup_loopback.sh
index 2070b57849de..2070b57849de 100755..100644
--- a/tools/testing/selftests/net/setup_loopback.sh
+++ b/tools/testing/selftests/net/setup_loopback.sh
diff --git a/tools/testing/selftests/net/setup_veth.sh b/tools/testing/selftests/net/setup_veth.sh
index a9a1759e035c..1f78a87f6f37 100644
--- a/tools/testing/selftests/net/setup_veth.sh
+++ b/tools/testing/selftests/net/setup_veth.sh
@@ -11,7 +11,7 @@ setup_veth_ns() {
 	local -r ns_mac="$4"
 
 	[[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}"
-	echo 100000 > "/sys/class/net/${ns_dev}/gro_flush_timeout"
+	echo 1000000 > "/sys/class/net/${ns_dev}/gro_flush_timeout"
 	ip link set dev "${ns_dev}" netns "${ns_name}" mtu 65535
 	ip -netns "${ns_name}" link set dev "${ns_dev}" up
 
diff --git a/tools/testing/selftests/net/so_incoming_cpu.c b/tools/testing/selftests/net/so_incoming_cpu.c
index a14818164102..e9fa14e10732 100644
--- a/tools/testing/selftests/net/so_incoming_cpu.c
+++ b/tools/testing/selftests/net/so_incoming_cpu.c
@@ -3,19 +3,16 @@
 #define _GNU_SOURCE
 #include <sched.h>
 
+#include <fcntl.h>
+
 #include <netinet/in.h>
 #include <sys/socket.h>
 #include <sys/sysinfo.h>
 
 #include "../kselftest_harness.h"
 
-#define CLIENT_PER_SERVER	32 /* More sockets, more reliable */
-#define NR_SERVER		self->nproc
-#define NR_CLIENT		(CLIENT_PER_SERVER * NR_SERVER)
-
 FIXTURE(so_incoming_cpu)
 {
-	int nproc;
 	int *servers;
 	union {
 		struct sockaddr addr;
@@ -56,12 +53,47 @@ FIXTURE_VARIANT_ADD(so_incoming_cpu, after_all_listen)
 	.when_to_set = AFTER_ALL_LISTEN,
 };
 
+static void write_sysctl(struct __test_metadata *_metadata,
+			 char *filename, char *string)
+{
+	int fd, len, ret;
+
+	fd = open(filename, O_WRONLY);
+	ASSERT_NE(fd, -1);
+
+	len = strlen(string);
+	ret = write(fd, string, len);
+	ASSERT_EQ(ret, len);
+}
+
+static void setup_netns(struct __test_metadata *_metadata)
+{
+	ASSERT_EQ(unshare(CLONE_NEWNET), 0);
+	ASSERT_EQ(system("ip link set lo up"), 0);
+
+	write_sysctl(_metadata, "/proc/sys/net/ipv4/ip_local_port_range", "10000 60001");
+	write_sysctl(_metadata, "/proc/sys/net/ipv4/tcp_tw_reuse", "0");
+}
+
+#define NR_PORT				(60001 - 10000 - 1)
+#define NR_CLIENT_PER_SERVER_DEFAULT	32
+static int nr_client_per_server, nr_server, nr_client;
+
 FIXTURE_SETUP(so_incoming_cpu)
 {
-	self->nproc = get_nprocs();
-	ASSERT_LE(2, self->nproc);
+	setup_netns(_metadata);
+
+	nr_server = get_nprocs();
+	ASSERT_LE(2, nr_server);
+
+	if (NR_CLIENT_PER_SERVER_DEFAULT * nr_server < NR_PORT)
+		nr_client_per_server = NR_CLIENT_PER_SERVER_DEFAULT;
+	else
+		nr_client_per_server = NR_PORT / nr_server;
+
+	nr_client = nr_client_per_server * nr_server;
 
-	self->servers = malloc(sizeof(int) * NR_SERVER);
+	self->servers = malloc(sizeof(int) * nr_server);
 	ASSERT_NE(self->servers, NULL);
 
 	self->in_addr.sin_family = AF_INET;
@@ -74,7 +106,7 @@ FIXTURE_TEARDOWN(so_incoming_cpu)
 {
 	int i;
 
-	for (i = 0; i < NR_SERVER; i++)
+	for (i = 0; i < nr_server; i++)
 		close(self->servers[i]);
 
 	free(self->servers);
@@ -110,10 +142,10 @@ int create_server(struct __test_metadata *_metadata,
 	if (variant->when_to_set == BEFORE_LISTEN)
 		set_so_incoming_cpu(_metadata, fd, cpu);
 
-	/* We don't use CLIENT_PER_SERVER here not to block
+	/* We don't use nr_client_per_server here not to block
 	 * this test at connect() if SO_INCOMING_CPU is broken.
 	 */
-	ret = listen(fd, NR_CLIENT);
+	ret = listen(fd, nr_client);
 	ASSERT_EQ(ret, 0);
 
 	if (variant->when_to_set == AFTER_LISTEN)
@@ -128,7 +160,7 @@ void create_servers(struct __test_metadata *_metadata,
 {
 	int i, ret;
 
-	for (i = 0; i < NR_SERVER; i++) {
+	for (i = 0; i < nr_server; i++) {
 		self->servers[i] = create_server(_metadata, self, variant, i);
 
 		if (i == 0) {
@@ -138,7 +170,7 @@ void create_servers(struct __test_metadata *_metadata,
 	}
 
 	if (variant->when_to_set == AFTER_ALL_LISTEN) {
-		for (i = 0; i < NR_SERVER; i++)
+		for (i = 0; i < nr_server; i++)
 			set_so_incoming_cpu(_metadata, self->servers[i], i);
 	}
 }
@@ -149,7 +181,7 @@ void create_clients(struct __test_metadata *_metadata,
 	cpu_set_t cpu_set;
 	int i, j, fd, ret;
 
-	for (i = 0; i < NR_SERVER; i++) {
+	for (i = 0; i < nr_server; i++) {
 		CPU_ZERO(&cpu_set);
 
 		CPU_SET(i, &cpu_set);
@@ -162,7 +194,7 @@ void create_clients(struct __test_metadata *_metadata,
 		ret = sched_setaffinity(0, sizeof(cpu_set), &cpu_set);
 		ASSERT_EQ(ret, 0);
 
-		for (j = 0; j < CLIENT_PER_SERVER; j++) {
+		for (j = 0; j < nr_client_per_server; j++) {
 			fd  = socket(AF_INET, SOCK_STREAM, 0);
 			ASSERT_NE(fd, -1);
 
@@ -180,8 +212,8 @@ void verify_incoming_cpu(struct __test_metadata *_metadata,
 	int i, j, fd, cpu, ret, total = 0;
 	socklen_t len = sizeof(int);
 
-	for (i = 0; i < NR_SERVER; i++) {
-		for (j = 0; j < CLIENT_PER_SERVER; j++) {
+	for (i = 0; i < nr_server; i++) {
+		for (j = 0; j < nr_client_per_server; j++) {
 			/* If we see -EAGAIN here, SO_INCOMING_CPU is broken */
 			fd = accept(self->servers[i], &self->addr, &self->addrlen);
 			ASSERT_NE(fd, -1);
@@ -195,7 +227,7 @@ void verify_incoming_cpu(struct __test_metadata *_metadata,
 		}
 	}
 
-	ASSERT_EQ(total, NR_CLIENT);
+	ASSERT_EQ(total, nr_client);
 	TH_LOG("SO_INCOMING_CPU is very likely to be "
 	       "working correctly with %d sockets.", total);
 }
diff --git a/tools/testing/selftests/net/so_txtime.sh b/tools/testing/selftests/net/so_txtime.sh
index 3f06f4d286a9..5e861ad32a42 100755
--- a/tools/testing/selftests/net/so_txtime.sh
+++ b/tools/testing/selftests/net/so_txtime.sh
@@ -5,6 +5,7 @@
 
 set -e
 
+readonly ksft_skip=4
 readonly DEV="veth0"
 readonly BIN="./so_txtime"
 
@@ -46,7 +47,7 @@ ip -netns "${NS2}" addr add 192.168.1.2/24 dev "${DEV}"
 ip -netns "${NS1}" addr add       fd::1/64 dev "${DEV}" nodad
 ip -netns "${NS2}" addr add       fd::2/64 dev "${DEV}" nodad
 
-do_test() {
+run_test() {
 	local readonly IP="$1"
 	local readonly CLOCK="$2"
 	local readonly TXARGS="$3"
@@ -64,12 +65,25 @@ do_test() {
 	fi
 
 	local readonly START="$(date +%s%N --date="+ 0.1 seconds")"
+
 	ip netns exec "${NS2}" "${BIN}" -"${IP}" -c "${CLOCK}" -t "${START}" -S "${SADDR}" -D "${DADDR}" "${RXARGS}" -r &
 	ip netns exec "${NS1}" "${BIN}" -"${IP}" -c "${CLOCK}" -t "${START}" -S "${SADDR}" -D "${DADDR}" "${TXARGS}"
 	wait "$!"
 }
 
+do_test() {
+	run_test $@
+	[ $? -ne 0 ] && ret=1
+}
+
+do_fail_test() {
+	run_test $@
+	[ $? -eq 0 ] && ret=1
+}
+
 ip netns exec "${NS1}" tc qdisc add dev "${DEV}" root fq
+set +e
+ret=0
 do_test 4 mono a,-1 a,-1
 do_test 6 mono a,0 a,0
 do_test 6 mono a,10 a,10
@@ -77,13 +91,20 @@ do_test 4 mono a,10,b,20 a,10,b,20
 do_test 6 mono a,20,b,10 b,20,a,20
 
 if ip netns exec "${NS1}" tc qdisc replace dev "${DEV}" root etf clockid CLOCK_TAI delta 400000; then
-	! do_test 4 tai a,-1 a,-1
-	! do_test 6 tai a,0 a,0
+	do_fail_test 4 tai a,-1 a,-1
+	do_fail_test 6 tai a,0 a,0
 	do_test 6 tai a,10 a,10
 	do_test 4 tai a,10,b,20 a,10,b,20
 	do_test 6 tai a,20,b,10 b,10,a,20
 else
 	echo "tc ($(tc -V)) does not support qdisc etf. skipping"
+	[ $ret -eq 0 ] && ret=$ksft_skip
 fi
 
-echo OK. All tests passed
+if [ $ret -eq 0 ]; then
+	echo OK. All tests passed
+elif [[ $ret -ne $ksft_skip && -n "$KSFT_MACHINE_SLOW" ]]; then
+	echo "Ignoring errors due to slow environment" 1>&2
+	ret=0
+fi
+exit $ret
diff --git a/tools/testing/selftests/net/tcp_ao/Makefile b/tools/testing/selftests/net/tcp_ao/Makefile
index 8e60bae67aa9..522d991e310e 100644
--- a/tools/testing/selftests/net/tcp_ao/Makefile
+++ b/tools/testing/selftests/net/tcp_ao/Makefile
@@ -52,5 +52,5 @@ $(OUTPUT)/%_ipv6: %.c
 
 $(OUTPUT)/icmps-accept_ipv4: CFLAGS+= -DTEST_ICMPS_ACCEPT
 $(OUTPUT)/icmps-accept_ipv6: CFLAGS+= -DTEST_ICMPS_ACCEPT
-$(OUTPUT)/bench-lookups_ipv4: LDFLAGS+= -lm
-$(OUTPUT)/bench-lookups_ipv6: LDFLAGS+= -lm
+$(OUTPUT)/bench-lookups_ipv4: LDLIBS+= -lm
+$(OUTPUT)/bench-lookups_ipv6: LDLIBS+= -lm
diff --git a/tools/testing/selftests/net/tcp_ao/config b/tools/testing/selftests/net/tcp_ao/config
new file mode 100644
index 000000000000..d3277a9de987
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/config
@@ -0,0 +1,10 @@
+CONFIG_CRYPTO_HMAC=y
+CONFIG_CRYPTO_RMD160=y
+CONFIG_CRYPTO_SHA1=y
+CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_IPV6=y
+CONFIG_NET_L3_MASTER_DEV=y
+CONFIG_NET_VRF=y
+CONFIG_TCP_AO=y
+CONFIG_TCP_MD5SIG=y
+CONFIG_VETH=m
diff --git a/tools/testing/selftests/net/tcp_ao/key-management.c b/tools/testing/selftests/net/tcp_ao/key-management.c
index c48b4970ca17..24e62120b792 100644
--- a/tools/testing/selftests/net/tcp_ao/key-management.c
+++ b/tools/testing/selftests/net/tcp_ao/key-management.c
@@ -417,9 +417,9 @@ struct test_key {
 		matches_vrf		: 1,
 		is_current		: 1,
 		is_rnext		: 1,
-		used_on_handshake	: 1,
-		used_after_accept	: 1,
-		used_on_client		: 1;
+		used_on_server_tx	: 1,
+		used_on_client_tx	: 1,
+		skip_counters_checks	: 1;
 };
 
 struct key_collection {
@@ -609,16 +609,14 @@ static int key_collection_socket(bool server, unsigned int port)
 				addr = &this_ip_dest;
 			sndid = key->client_keyid;
 			rcvid = key->server_keyid;
-			set_current = key->is_current;
-			set_rnext = key->is_rnext;
+			key->used_on_client_tx = set_current = key->is_current;
+			key->used_on_server_tx = set_rnext = key->is_rnext;
 		}
 
 		if (test_add_key_cr(sk, key->password, key->len,
 				    *addr, vrf, sndid, rcvid, key->maclen,
 				    key->alg, set_current, set_rnext))
 			test_key_error("setsockopt(TCP_AO_ADD_KEY)", key);
-		if (set_current || set_rnext)
-			key->used_on_handshake = 1;
 #ifdef DEBUG
 		test_print("%s [%u/%u] key: { %s, %u:%u, %u, %u:%u:%u:%u (%u)}",
 			   server ? "server" : "client", i, collection.nr_keys,
@@ -640,22 +638,22 @@ static void verify_counters(const char *tst_name, bool is_listen_sk, bool server
 	for (i = 0; i < collection.nr_keys; i++) {
 		struct test_key *key = &collection.keys[i];
 		uint8_t sndid, rcvid;
-		bool was_used;
+		bool rx_cnt_expected;
 
+		if (key->skip_counters_checks)
+			continue;
 		if (server) {
 			sndid = key->server_keyid;
 			rcvid = key->client_keyid;
-			if (is_listen_sk)
-				was_used = key->used_on_handshake;
-			else
-				was_used = key->used_after_accept;
+			rx_cnt_expected = key->used_on_client_tx;
 		} else {
 			sndid = key->client_keyid;
 			rcvid = key->server_keyid;
-			was_used = key->used_on_client;
+			rx_cnt_expected = key->used_on_server_tx;
 		}
 
-		test_tcp_ao_key_counters_cmp(tst_name, a, b, was_used,
+		test_tcp_ao_key_counters_cmp(tst_name, a, b,
+					     rx_cnt_expected ? TEST_CNT_KEY_GOOD : 0,
 					     sndid, rcvid);
 	}
 	test_tcp_ao_counters_free(a);
@@ -843,7 +841,7 @@ static void end_server(const char *tst_name, int sk,
 	synchronize_threads(); /* 4: verified => closed */
 	close(sk);
 
-	verify_counters(tst_name, true, false, begin, &end);
+	verify_counters(tst_name, false, true, begin, &end);
 	synchronize_threads(); /* 5: counters */
 }
 
@@ -916,9 +914,8 @@ static int run_client(const char *tst_name, unsigned int port,
 		current_index = nr_keys - 1;
 	if (rnext_index < 0)
 		rnext_index = nr_keys - 1;
-	collection.keys[current_index].used_on_handshake = 1;
-	collection.keys[rnext_index].used_after_accept = 1;
-	collection.keys[rnext_index].used_on_client = 1;
+	collection.keys[current_index].used_on_client_tx = 1;
+	collection.keys[rnext_index].used_on_server_tx = 1;
 
 	synchronize_threads(); /* 3: accepted => send data */
 	if (test_client_verify(sk, msg_sz, msg_nr, TEST_TIMEOUT_SEC)) {
@@ -1059,7 +1056,16 @@ static void check_current_back(const char *tst_name, unsigned int port,
 		test_error("Can't change the current key");
 	if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC))
 		test_fail("verify failed");
-	collection.keys[rotate_to_index].used_after_accept = 1;
+	/* There is a race here: between setting the current_key with
+	 * setsockopt(TCP_AO_INFO) and starting to send some data - there
+	 * might have been a segment received with the desired
+	 * RNext_key set. In turn that would mean that the first outgoing
+	 * segment will have the desired current_key (flipped back).
+	 * Which is what the user/test wants. As it's racy, skip checking
+	 * the counters, yet check what are the resulting current/rnext
+	 * keys on both sides.
+	 */
+	collection.keys[rotate_to_index].skip_counters_checks = 1;
 
 	end_client(tst_name, sk, nr_keys, current_index, rnext_index, &tmp);
 }
@@ -1089,7 +1095,7 @@ static void roll_over_keys(const char *tst_name, unsigned int port,
 		}
 		verify_current_rnext(tst_name, sk, -1,
 				     collection.keys[i].server_keyid);
-		collection.keys[i].used_on_client = 1;
+		collection.keys[i].used_on_server_tx = 1;
 		synchronize_threads(); /* verify current/rnext */
 	}
 	end_client(tst_name, sk, nr_keys, current_index, rnext_index, &tmp);
diff --git a/tools/testing/selftests/net/tcp_ao/lib/sock.c b/tools/testing/selftests/net/tcp_ao/lib/sock.c
index c75d82885a2e..15aeb0963058 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/sock.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/sock.c
@@ -62,7 +62,9 @@ int test_wait_fd(int sk, time_t sec, bool write)
 		return -ETIMEDOUT;
 	}
 
-	if (getsockopt(sk, SOL_SOCKET, SO_ERROR, &ret, &slen) || ret)
+	if (getsockopt(sk, SOL_SOCKET, SO_ERROR, &ret, &slen))
+		return -errno;
+	if (ret)
 		return -ret;
 	return 0;
 }
@@ -584,9 +586,11 @@ int test_client_verify(int sk, const size_t msg_len, const size_t nr,
 {
 	size_t buf_sz = msg_len * nr;
 	char *buf = alloca(buf_sz);
+	ssize_t ret;
 
 	randomize_buffer(buf, buf_sz);
-	if (test_client_loop(sk, buf, buf_sz, msg_len, timeout_sec) != buf_sz)
-		return -1;
-	return 0;
+	ret = test_client_loop(sk, buf, buf_sz, msg_len, timeout_sec);
+	if (ret < 0)
+		return (int)ret;
+	return ret != buf_sz ? -1 : 0;
 }
diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c
index ac06009a7f5f..7df8b8700e39 100644
--- a/tools/testing/selftests/net/tcp_ao/rst.c
+++ b/tools/testing/selftests/net/tcp_ao/rst.c
@@ -1,10 +1,33 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Author: Dmitry Safonov <dima@arista.com> */
+/*
+ * The test checks that both active and passive reset have correct TCP-AO
+ * signature. An "active" reset (abort) here is procured from closing
+ * listen() socket with non-accepted connections in the queue:
+ * inet_csk_listen_stop() => inet_child_forget() =>
+ *                        => tcp_disconnect() => tcp_send_active_reset()
+ *
+ * The passive reset is quite hard to get on established TCP connections.
+ * It could be procured from non-established states, but the synchronization
+ * part from userspace in order to reliably get RST seems uneasy.
+ * So, instead it's procured by corrupting SEQ number on TIMED-WAIT state.
+ *
+ * It's important to test both passive and active RST as they go through
+ * different code-paths:
+ * - tcp_send_active_reset() makes no-data skb, sends it with tcp_transmit_skb()
+ * - tcp_v*_send_reset() create their reply skbs and send them with
+ *   ip_send_unicast_reply()
+ *
+ * In both cases TCP-AO signatures have to be correct, which is verified by
+ * (1) checking that the TCP-AO connection was reset and (2) TCP-AO counters.
+ *
+ * Author: Dmitry Safonov <dima@arista.com>
+ */
 #include <inttypes.h>
 #include "../../../../include/linux/kernel.h"
 #include "aolib.h"
 
 const size_t quota = 1000;
+const size_t packet_sz = 100;
 /*
  * Backlog == 0 means 1 connection in queue, see:
  * commit 64a146513f8f ("[NET]: Revert incorrect accept queue...")
@@ -59,26 +82,6 @@ static void close_forced(int sk)
 	close(sk);
 }
 
-static int test_wait_for_exception(int sk, time_t sec)
-{
-	struct timeval tv = { .tv_sec = sec };
-	struct timeval *ptv = NULL;
-	fd_set efds;
-	int ret;
-
-	FD_ZERO(&efds);
-	FD_SET(sk, &efds);
-
-	if (sec)
-		ptv = &tv;
-
-	errno = 0;
-	ret = select(sk + 1, NULL, NULL, &efds, ptv);
-	if (ret < 0)
-		return -errno;
-	return ret ? sk : 0;
-}
-
 static void test_server_active_rst(unsigned int port)
 {
 	struct tcp_ao_counters cnt1, cnt2;
@@ -155,17 +158,16 @@ static void test_server_passive_rst(unsigned int port)
 			test_fail("server returned %zd", bytes);
 	}
 
-	synchronize_threads(); /* 3: chekpoint/restore the connection */
+	synchronize_threads(); /* 3: checkpoint the client */
+	synchronize_threads(); /* 4: close the server, creating twsk */
 	if (test_get_tcp_ao_counters(sk, &ao2))
 		test_error("test_get_tcp_ao_counters()");
-
-	synchronize_threads(); /* 4: terminate server + send more on client */
-	bytes = test_server_run(sk, quota, TEST_RETRANSMIT_SEC);
 	close(sk);
+
+	synchronize_threads(); /* 5: restore the socket, send more data */
 	test_tcp_ao_counters_cmp("passive RST server", &ao1, &ao2, TEST_CNT_GOOD);
 
-	synchronize_threads(); /* 5: verified => closed */
-	close(sk);
+	synchronize_threads(); /* 6: server exits */
 }
 
 static void *server_fn(void *arg)
@@ -284,7 +286,7 @@ static void test_client_active_rst(unsigned int port)
 		test_error("test_wait_fds(): %d", err);
 
 	synchronize_threads(); /* 3: close listen socket */
-	if (test_client_verify(sk[0], 100, quota / 100, TEST_TIMEOUT_SEC))
+	if (test_client_verify(sk[0], packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC))
 		test_fail("Failed to send data on connected socket");
 	else
 		test_ok("Verified established tcp connection");
@@ -323,7 +325,6 @@ static void test_client_passive_rst(unsigned int port)
 	struct tcp_sock_state img;
 	sockaddr_af saddr;
 	int sk, err;
-	socklen_t slen = sizeof(err);
 
 	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
 	if (sk < 0)
@@ -337,18 +338,51 @@ static void test_client_passive_rst(unsigned int port)
 		test_error("failed to connect()");
 
 	synchronize_threads(); /* 2: accepted => send data */
-	if (test_client_verify(sk, 100, quota / 100, TEST_TIMEOUT_SEC))
+	if (test_client_verify(sk, packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC))
 		test_fail("Failed to send data on connected socket");
 	else
 		test_ok("Verified established tcp connection");
 
-	synchronize_threads(); /* 3: chekpoint/restore the connection */
+	synchronize_threads(); /* 3: checkpoint the client */
 	test_enable_repair(sk);
 	test_sock_checkpoint(sk, &img, &saddr);
 	test_ao_checkpoint(sk, &ao_img);
-	test_kill_sk(sk);
+	test_disable_repair(sk);
 
-	img.out.seq += quota;
+	synchronize_threads(); /* 4: close the server, creating twsk */
+
+	/*
+	 * The "corruption" in SEQ has to be small enough to fit into TCP
+	 * window, see tcp_timewait_state_process() for out-of-window
+	 * segments.
+	 */
+	img.out.seq += 5; /* 5 is more noticeable in tcpdump than 1 */
+
+	/*
+	 * FIXME: This is kind-of ugly and dirty, but it works.
+	 *
+	 * At this moment, the server has close'ed(sk).
+	 * The passive RST that is being targeted here is new data after
+	 * half-duplex close, see tcp_timewait_state_process() => TCP_TW_RST
+	 *
+	 * What is needed here is:
+	 * (1) wait for FIN from the server
+	 * (2) make sure that the ACK from the client went out
+	 * (3) make sure that the ACK was received and processed by the server
+	 *
+	 * Otherwise, the data that will be sent from "repaired" socket
+	 * post SEQ corruption may get to the server before it's in
+	 * TCP_FIN_WAIT2.
+	 *
+	 * (1) is easy with select()/poll()
+	 * (2) is possible by polling tcpi_state from TCP_INFO
+	 * (3) is quite complex: as server's socket was already closed,
+	 *     probably the way to do it would be tcp-diag.
+	 */
+	sleep(TEST_RETRANSMIT_SEC);
+
+	synchronize_threads(); /* 5: restore the socket, send more data */
+	test_kill_sk(sk);
 
 	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
 	if (sk < 0)
@@ -366,25 +400,33 @@ static void test_client_passive_rst(unsigned int port)
 	test_disable_repair(sk);
 	test_sock_state_free(&img);
 
-	synchronize_threads(); /* 4: terminate server + send more on client */
-	if (test_client_verify(sk, 100, quota / 100, 2 * TEST_TIMEOUT_SEC))
-		test_ok("client connection broken post-seq-adjust");
-	else
-		test_fail("client connection still works post-seq-adjust");
-
-	test_wait_for_exception(sk, TEST_TIMEOUT_SEC);
-
-	if (getsockopt(sk, SOL_SOCKET, SO_ERROR, &err, &slen))
-		test_error("getsockopt()");
-	if (err != ECONNRESET && err != EPIPE)
-		test_fail("client connection was not reset: %d", err);
+	/*
+	 * This is how "passive reset" is acquired in this test from TCP_TW_RST:
+	 *
+	 * IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [P.], seq 901:1001, ack 1001, win 249,
+	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0x10217d6c36a22379086ef3b1], length 100
+	 * IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [F.], seq 1001, ack 1001, win 249,
+	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0x104ffc99b98c10a5298cc268], length 0
+	 * IP 10.0.1.1.59772 > 10.0.254.1.7011: Flags [.], ack 1002, win 251,
+	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0xe496dd4f7f5a8a66873c6f93,nop,nop,sack 1 {1001:1002}], length 0
+	 * IP 10.0.1.1.59772 > 10.0.254.1.7011: Flags [P.], seq 1006:1106, ack 1001, win 251,
+	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0x1b5f3330fb23fbcd0c77d0ca], length 100
+	 * IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [R], seq 3215596252, win 0,
+	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0x0bcfbbf497bce844312304b2], length 0
+	 */
+	err = test_client_verify(sk, packet_sz, quota / packet_sz, 2 * TEST_TIMEOUT_SEC);
+	/* Make sure that the connection was reset, not timeouted */
+	if (err && err == -ECONNRESET)
+		test_ok("client sock was passively reset post-seq-adjust");
+	else if (err)
+		test_fail("client sock was not reset post-seq-adjust: %d", err);
 	else
-		test_ok("client connection was reset");
+		test_fail("client sock is yet connected post-seq-adjust");
 
 	if (test_get_tcp_ao_counters(sk, &ao2))
 		test_error("test_get_tcp_ao_counters()");
 
-	synchronize_threads(); /* 5: verified => closed */
+	synchronize_threads(); /* 6: server exits */
 	close(sk);
 	test_tcp_ao_counters_cmp("client passive RST", &ao1, &ao2, TEST_CNT_GOOD);
 }
@@ -410,6 +452,6 @@ static void *client_fn(void *arg)
 
 int main(int argc, char *argv[])
 {
-	test_init(15, server_fn, client_fn);
+	test_init(14, server_fn, client_fn);
 	return 0;
 }
diff --git a/tools/testing/selftests/net/tcp_ao/settings b/tools/testing/selftests/net/tcp_ao/settings
new file mode 100644
index 000000000000..6091b45d226b
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/settings
@@ -0,0 +1 @@
+timeout=120
diff --git a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
index c5b568cd7d90..6b59a652159f 100644
--- a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
+++ b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
@@ -110,9 +110,9 @@ static void try_accept(const char *tst_name, unsigned int port,
 		test_tcp_ao_counters_cmp(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected);
 
 out:
-	synchronize_threads(); /* close() */
+	synchronize_threads(); /* test_kill_sk() */
 	if (sk > 0)
-		close(sk);
+		test_kill_sk(sk);
 }
 
 static void server_add_routes(void)
@@ -302,10 +302,10 @@ static void try_connect(const char *tst_name, unsigned int port,
 		test_ok("%s: connected", tst_name);
 
 out:
-	synchronize_threads(); /* close() */
+	synchronize_threads(); /* test_kill_sk() */
 	/* _test_connect_socket() cleans up on failure */
 	if (ret > 0)
-		close(sk);
+		test_kill_sk(sk);
 }
 
 #define PREINSTALL_MD5_FIRST	BIT(0)
@@ -486,10 +486,10 @@ static void try_to_add(const char *tst_name, unsigned int port,
 	}
 
 out:
-	synchronize_threads(); /* close() */
+	synchronize_threads(); /* test_kill_sk() */
 	/* _test_connect_socket() cleans up on failure */
 	if (ret > 0)
-		close(sk);
+		test_kill_sk(sk);
 }
 
 static void client_add_ip(union tcp_addr *client, const char *ip)
diff --git a/tools/testing/selftests/net/test_bridge_backup_port.sh b/tools/testing/selftests/net/test_bridge_backup_port.sh
index 70a7d87ba2d2..1b3f89e2b86e 100755
--- a/tools/testing/selftests/net/test_bridge_backup_port.sh
+++ b/tools/testing/selftests/net/test_bridge_backup_port.sh
@@ -124,6 +124,16 @@ tc_check_packets()
 	[[ $pkts == $count ]]
 }
 
+bridge_link_check()
+{
+	local ns=$1; shift
+	local dev=$1; shift
+	local state=$1; shift
+
+	bridge -n $ns -d -j link show dev $dev | \
+		jq -e ".[][\"state\"] == \"$state\"" &> /dev/null
+}
+
 ################################################################################
 # Setup
 
@@ -259,6 +269,7 @@ backup_port()
 	log_test $? 0 "No forwarding out of vx0"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
 	log_test $? 0 "swp1 carrier off"
 
 	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -268,6 +279,7 @@ backup_port()
 	log_test $? 0 "No forwarding out of vx0"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier on"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding
 	log_test $? 0 "swp1 carrier on"
 
 	# Configure vx0 as the backup port of swp1 and check that packets are
@@ -284,6 +296,7 @@ backup_port()
 	log_test $? 0 "No forwarding out of vx0"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
 	log_test $? 0 "swp1 carrier off"
 
 	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -293,6 +306,7 @@ backup_port()
 	log_test $? 0 "Forwarding out of vx0"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier on"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding
 	log_test $? 0 "swp1 carrier on"
 
 	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -314,6 +328,7 @@ backup_port()
 	log_test $? 0 "No forwarding out of vx0"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
 	log_test $? 0 "swp1 carrier off"
 
 	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -369,6 +384,7 @@ backup_nhid()
 	log_test $? 0 "No forwarding out of vx0"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
 	log_test $? 0 "swp1 carrier off"
 
 	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -382,6 +398,7 @@ backup_nhid()
 	log_test $? 0 "Forwarding using VXLAN FDB entry"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier on"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding
 	log_test $? 0 "swp1 carrier on"
 
 	# Configure nexthop ID 10 as the backup nexthop ID of swp1 and check
@@ -398,6 +415,7 @@ backup_nhid()
 	log_test $? 0 "No forwarding out of vx0"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
 	log_test $? 0 "swp1 carrier off"
 
 	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -411,6 +429,7 @@ backup_nhid()
 	log_test $? 0 "No forwarding using VXLAN FDB entry"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier on"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding
 	log_test $? 0 "swp1 carrier on"
 
 	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -441,6 +460,7 @@ backup_nhid()
 	log_test $? 0 "No forwarding using VXLAN FDB entry"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
 	log_test $? 0 "swp1 carrier off"
 
 	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -497,6 +517,7 @@ backup_nhid_invalid()
 	log_test $? 0 "Valid nexthop as backup nexthop"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
 	log_test $? 0 "swp1 carrier off"
 
 	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -604,7 +625,9 @@ backup_nhid_ping()
 	run_cmd "bridge -n $sw2 link set dev swp1 backup_nhid 10"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
 	run_cmd "ip -n $sw2 link set dev swp1 carrier off"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw2 swp1 disabled
 
 	run_cmd "ip netns exec $sw1 ping -i 0.1 -c 10 -w $PING_TIMEOUT 192.0.2.66"
 	log_test $? 0 "Ping with backup nexthop ID"
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 464853a7f982..b95c249f81c2 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -707,6 +707,20 @@ TEST_F(tls, splice_from_pipe)
 	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
 }
 
+TEST_F(tls, splice_more)
+{
+	unsigned int f = SPLICE_F_NONBLOCK | SPLICE_F_MORE | SPLICE_F_GIFT;
+	int send_len = TLS_PAYLOAD_MAX_LEN;
+	char mem_send[TLS_PAYLOAD_MAX_LEN];
+	int i, send_pipe = 1;
+	int p[2];
+
+	ASSERT_GE(pipe(p), 0);
+	EXPECT_GE(write(p[1], mem_send, send_len), 0);
+	for (i = 0; i < 32; i++)
+		EXPECT_EQ(splice(p[0], NULL, self->fd, NULL, send_pipe, f), 1);
+}
+
 TEST_F(tls, splice_from_pipe2)
 {
 	int send_len = 16000;
@@ -988,12 +1002,12 @@ TEST_F(tls, recv_partial)
 
 	memset(recv_mem, 0, sizeof(recv_mem));
 	EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
-	EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_first),
-		       MSG_WAITALL), -1);
+	EXPECT_EQ(recv(self->cfd, recv_mem, strlen(test_str_first),
+		       MSG_WAITALL), strlen(test_str_first));
 	EXPECT_EQ(memcmp(test_str_first, recv_mem, strlen(test_str_first)), 0);
 	memset(recv_mem, 0, sizeof(recv_mem));
-	EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_second),
-		       MSG_WAITALL), -1);
+	EXPECT_EQ(recv(self->cfd, recv_mem, strlen(test_str_second),
+		       MSG_WAITALL), strlen(test_str_second));
 	EXPECT_EQ(memcmp(test_str_second, recv_mem, strlen(test_str_second)),
 		  0);
 }
@@ -1471,6 +1485,51 @@ TEST_F(tls, control_msg)
 	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
 }
 
+TEST_F(tls, control_msg_nomerge)
+{
+	char *rec1 = "1111";
+	char *rec2 = "2222";
+	int send_len = 5;
+	char buf[15];
+
+	if (self->notls)
+		SKIP(return, "no TLS support");
+
+	EXPECT_EQ(tls_send_cmsg(self->fd, 100, rec1, send_len, 0), send_len);
+	EXPECT_EQ(tls_send_cmsg(self->fd, 100, rec2, send_len, 0), send_len);
+
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, 100, buf, sizeof(buf), MSG_PEEK), send_len);
+	EXPECT_EQ(memcmp(buf, rec1, send_len), 0);
+
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, 100, buf, sizeof(buf), MSG_PEEK), send_len);
+	EXPECT_EQ(memcmp(buf, rec1, send_len), 0);
+
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, 100, buf, sizeof(buf), 0), send_len);
+	EXPECT_EQ(memcmp(buf, rec1, send_len), 0);
+
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, 100, buf, sizeof(buf), 0), send_len);
+	EXPECT_EQ(memcmp(buf, rec2, send_len), 0);
+}
+
+TEST_F(tls, data_control_data)
+{
+	char *rec1 = "1111";
+	char *rec2 = "2222";
+	char *rec3 = "3333";
+	int send_len = 5;
+	char buf[15];
+
+	if (self->notls)
+		SKIP(return, "no TLS support");
+
+	EXPECT_EQ(send(self->fd, rec1, send_len, 0), send_len);
+	EXPECT_EQ(tls_send_cmsg(self->fd, 100, rec2, send_len, 0), send_len);
+	EXPECT_EQ(send(self->fd, rec3, send_len, 0), send_len);
+
+	EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_PEEK), send_len);
+	EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_PEEK), send_len);
+}
+
 TEST_F(tls, shutdown)
 {
 	char const *test_str = "test_read";
@@ -1860,13 +1919,13 @@ TEST_F(tls_err, poll_partial_rec_async)
 		/* Child should sleep in poll(), never get a wake */
 		pfd.fd = self->cfd2;
 		pfd.events = POLLIN;
-		EXPECT_EQ(poll(&pfd, 1, 5), 0);
+		EXPECT_EQ(poll(&pfd, 1, 20), 0);
 
 		EXPECT_EQ(write(p[1], &token, 1), 1); /* Barrier #1 */
 
 		pfd.fd = self->cfd2;
 		pfd.events = POLLIN;
-		EXPECT_EQ(poll(&pfd, 1, 5), 1);
+		EXPECT_EQ(poll(&pfd, 1, 20), 1);
 
 		exit(!_metadata->passed);
 	}
diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
index af5dc57c8ce9..8802604148dd 100755
--- a/tools/testing/selftests/net/udpgro.sh
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -7,7 +7,7 @@ source net_helper.sh
 
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
-BPF_FILE="../bpf/xdp_dummy.bpf.o"
+BPF_FILE="xdp_dummy.o"
 
 # set global exit status, but never reset nonzero one.
 check_err()
@@ -197,7 +197,7 @@ run_all() {
 }
 
 if [ ! -f ${BPF_FILE} ]; then
-	echo "Missing ${BPF_FILE}. Build bpf selftest first"
+	echo "Missing ${BPF_FILE}. Run 'make' first"
 	exit -1
 fi
 
diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh
index cb664679b434..7080eae5312b 100755
--- a/tools/testing/selftests/net/udpgro_bench.sh
+++ b/tools/testing/selftests/net/udpgro_bench.sh
@@ -7,7 +7,7 @@ source net_helper.sh
 
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
-BPF_FILE="../bpf/xdp_dummy.bpf.o"
+BPF_FILE="xdp_dummy.o"
 
 cleanup() {
 	local -r jobs="$(jobs -p)"
@@ -84,7 +84,7 @@ run_all() {
 }
 
 if [ ! -f ${BPF_FILE} ]; then
-	echo "Missing ${BPF_FILE}. Build bpf selftest first"
+	echo "Missing ${BPF_FILE}. Run 'make' first"
 	exit -1
 fi
 
diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh
index dd47fa96f6b3..e1ff645bd3d1 100755
--- a/tools/testing/selftests/net/udpgro_frglist.sh
+++ b/tools/testing/selftests/net/udpgro_frglist.sh
@@ -7,7 +7,7 @@ source net_helper.sh
 
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
-BPF_FILE="../bpf/xdp_dummy.bpf.o"
+BPF_FILE="xdp_dummy.o"
 
 cleanup() {
 	local -r jobs="$(jobs -p)"
@@ -85,12 +85,12 @@ run_all() {
 }
 
 if [ ! -f ${BPF_FILE} ]; then
-	echo "Missing ${BPF_FILE}. Build bpf selftest first"
+	echo "Missing ${BPF_FILE}. Run 'make' first"
 	exit -1
 fi
 
 if [ ! -f nat6to4.o ]; then
-	echo "Missing nat6to4 helper. Build bpf nat6to4.o selftest first"
+	echo "Missing nat6to4 helper. Run 'make' first"
 	exit -1
 fi
 
diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
index c079565add39..9cd5e885e91f 100755
--- a/tools/testing/selftests/net/udpgro_fwd.sh
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -1,7 +1,9 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-BPF_FILE="../bpf/xdp_dummy.bpf.o"
+source net_helper.sh
+
+BPF_FILE="xdp_dummy.o"
 readonly BASE="ns-$(mktemp -u XXXXXX)"
 readonly SRC=2
 readonly DST=1
@@ -37,6 +39,10 @@ create_ns() {
 	for ns in $NS_SRC $NS_DST; do
 		ip netns add $ns
 		ip -n $ns link set dev lo up
+
+		# disable route solicitations to decrease 'noise' traffic
+		ip netns exec $ns sysctl -qw net.ipv6.conf.default.router_solicitations=0
+		ip netns exec $ns sysctl -qw net.ipv6.conf.all.router_solicitations=0
 	done
 
 	ip link add name veth$SRC type veth peer name veth$DST
@@ -78,6 +84,12 @@ create_vxlan_pair() {
 		create_vxlan_endpoint $BASE$ns veth$ns $BM_NET_V6$((3 - $ns)) vxlan6$ns 6
 		ip -n $BASE$ns addr add dev vxlan6$ns $OL_NET_V6$ns/24 nodad
 	done
+
+	# preload neighbur cache, do avoid some noisy traffic
+	local addr_dst=$(ip -j -n $BASE$DST link show dev vxlan6$DST  |jq -r '.[]["address"]')
+	local addr_src=$(ip -j -n $BASE$SRC link show dev vxlan6$SRC  |jq -r '.[]["address"]')
+	ip -n $BASE$DST neigh add dev vxlan6$DST lladdr $addr_src $OL_NET_V6$SRC
+	ip -n $BASE$SRC neigh add dev vxlan6$SRC lladdr $addr_dst $OL_NET_V6$DST
 }
 
 is_ipv6() {
@@ -117,9 +129,9 @@ run_test() {
 	# not enable GRO
 	ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 4789
 	ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 8000
-	ip netns exec $NS_DST ./udpgso_bench_rx -C 1000 -R 10 -n 10 -l 1300 $rx_args &
+	ip netns exec $NS_DST ./udpgso_bench_rx -C 2000 -R 100 -n 10 -l 1300 $rx_args &
 	local spid=$!
-	sleep 0.1
+	wait_local_port_listen "$NS_DST" 8000 udp
 	ip netns exec $NS_SRC ./udpgso_bench_tx $family -M 1 -s 13000 -S 1300 -D $dst
 	local retc=$?
 	wait $spid
@@ -166,9 +178,9 @@ run_bench() {
 	# bind the sender and the receiver to different CPUs to try
 	# get reproducible results
 	ip netns exec $NS_DST bash -c "echo 2 > /sys/class/net/veth$DST/queues/rx-0/rps_cpus"
-	ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 1000 -R 10  &
+	ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 2000 -R 100  &
 	local spid=$!
-	sleep 0.1
+	wait_local_port_listen "$NS_DST" 8000 udp
 	ip netns exec $NS_SRC taskset 0x1 ./udpgso_bench_tx $family -l 3 -S 1300 -D $dst
 	local retc=$?
 	wait $spid
diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c
index f35a924d4a30..1cbadd267c96 100644
--- a/tools/testing/selftests/net/udpgso_bench_rx.c
+++ b/tools/testing/selftests/net/udpgso_bench_rx.c
@@ -375,7 +375,7 @@ static void do_recv(void)
 			do_flush_udp(fd);
 
 		tnow = gettimeofday_ms();
-		if (tnow > treport) {
+		if (!cfg_expected_pkt_nr && tnow > treport) {
 			if (packets)
 				fprintf(stderr,
 					"%s rx: %6lu MB/s %8lu calls/s\n",
diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh
index 2d073595c620..5ae85def0739 100755
--- a/tools/testing/selftests/net/veth.sh
+++ b/tools/testing/selftests/net/veth.sh
@@ -1,7 +1,7 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 
-BPF_FILE="../bpf/xdp_dummy.bpf.o"
+BPF_FILE="xdp_dummy.o"
 readonly STATS="$(mktemp -p /tmp ns-XXXXXX)"
 readonly BASE=`basename $STATS`
 readonly SRC=2
@@ -218,7 +218,7 @@ while getopts "hs:" option; do
 done
 
 if [ ! -f ${BPF_FILE} ]; then
-	echo "Missing ${BPF_FILE}. Build bpf selftest first"
+	echo "Missing ${BPF_FILE}. Run 'make' first"
 	exit 1
 fi
 
@@ -247,6 +247,20 @@ chk_gro "        - aggregation with TSO off" 1
 cleanup
 
 create_ns
+ip -n $NS_DST link set dev veth$DST up
+ip -n $NS_DST link set dev veth$DST xdp object ${BPF_FILE} section xdp
+chk_gro_flag "gro vs xdp while down - gro flag on" $DST on
+ip -n $NS_DST link set dev veth$DST down
+chk_gro_flag "                      - after down" $DST on
+ip -n $NS_DST link set dev veth$DST xdp off
+chk_gro_flag "                      - after xdp off" $DST off
+ip -n $NS_DST link set dev veth$DST up
+chk_gro_flag "                      - after up" $DST off
+ip -n $NS_SRC link set dev veth$SRC xdp object ${BPF_FILE} section xdp
+chk_gro_flag "                      - after peer xdp" $DST off
+cleanup
+
+create_ns
 chk_channels "default channels" $DST 1 1
 
 ip -n $NS_DST link set dev veth$DST down
diff --git a/tools/testing/selftests/net/xdp_dummy.c b/tools/testing/selftests/net/xdp_dummy.c
new file mode 100644
index 000000000000..d988b2e0cee8
--- /dev/null
+++ b/tools/testing/selftests/net/xdp_dummy.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define KBUILD_MODNAME "xdp_dummy"
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("xdp")
+int xdp_dummy_prog(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index db27153eb4a0..936c3085bb83 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -7,7 +7,8 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \
 	nft_queue.sh nft_meta.sh nf_nat_edemux.sh \
 	ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \
 	conntrack_vrf.sh nft_synproxy.sh rpath.sh nft_audit.sh \
-	conntrack_sctp_collision.sh xt_string.sh
+	conntrack_sctp_collision.sh xt_string.sh \
+	bridge_netfilter.sh
 
 HOSTPKG_CONFIG := pkg-config
 
diff --git a/tools/testing/selftests/netfilter/bridge_netfilter.sh b/tools/testing/selftests/netfilter/bridge_netfilter.sh
new file mode 100644
index 000000000000..659b3ab02c8b
--- /dev/null
+++ b/tools/testing/selftests/netfilter/bridge_netfilter.sh
@@ -0,0 +1,188 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test bridge netfilter + conntrack, a combination that doesn't really work,
+# with multicast/broadcast packets racing for hash table insertion.
+
+#           eth0    br0     eth0
+# setup is: ns1 <->,ns0 <-> ns3
+#           ns2 <-'    `'-> ns4
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+sfx=$(mktemp -u "XXXXXXXX")
+ns0="ns0-$sfx"
+ns1="ns1-$sfx"
+ns2="ns2-$sfx"
+ns3="ns3-$sfx"
+ns4="ns4-$sfx"
+
+ebtables -V > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ebtables"
+	exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+for i in $(seq 0 4); do
+  eval ip netns add \$ns$i
+done
+
+cleanup() {
+  for i in $(seq 0 4); do eval ip netns del \$ns$i;done
+}
+
+trap cleanup EXIT
+
+do_ping()
+{
+	fromns="$1"
+	dstip="$2"
+
+	ip netns exec $fromns ping -c 1 -q $dstip > /dev/null
+	if [ $? -ne 0 ]; then
+		echo "ERROR: ping from $fromns to $dstip"
+		ip netns exec ${ns0} nft list ruleset
+		ret=1
+	fi
+}
+
+bcast_ping()
+{
+	fromns="$1"
+	dstip="$2"
+
+	for i in $(seq 1 1000); do
+		ip netns exec $fromns ping -q -f -b -c 1 -q $dstip > /dev/null 2>&1
+		if [ $? -ne 0 ]; then
+			echo "ERROR: ping -b from $fromns to $dstip"
+			ip netns exec ${ns0} nft list ruleset
+			fi
+	done
+}
+
+ip link add veth1 netns ${ns0} type veth peer name eth0 netns ${ns1}
+if [ $? -ne 0 ]; then
+	echo "SKIP: Can't create veth device"
+	exit $ksft_skip
+fi
+
+ip link add veth2 netns ${ns0} type veth peer name eth0 netns $ns2
+ip link add veth3 netns ${ns0} type veth peer name eth0 netns $ns3
+ip link add veth4 netns ${ns0} type veth peer name eth0 netns $ns4
+
+ip -net ${ns0} link set lo up
+
+for i in $(seq 1 4); do
+  ip -net ${ns0} link set veth$i up
+done
+
+ip -net ${ns0} link add br0 type bridge stp_state 0 forward_delay 0 nf_call_iptables 1 nf_call_ip6tables 1 nf_call_arptables 1
+if [ $? -ne 0 ]; then
+	echo "SKIP: Can't create bridge br0"
+	exit $ksft_skip
+fi
+
+# make veth0,1,2 part of bridge.
+for i in $(seq 1 3); do
+  ip -net ${ns0} link set veth$i master br0
+done
+
+# add a macvlan on top of the bridge.
+MACVLAN_ADDR=ba:f3:13:37:42:23
+ip -net ${ns0} link add link br0 name macvlan0 type macvlan mode private
+ip -net ${ns0} link set macvlan0 address ${MACVLAN_ADDR}
+ip -net ${ns0} link set macvlan0 up
+ip -net ${ns0} addr add 10.23.0.1/24 dev macvlan0
+
+# add a macvlan on top of veth4.
+MACVLAN_ADDR=ba:f3:13:37:42:24
+ip -net ${ns0} link add link veth4 name macvlan4 type macvlan mode vepa
+ip -net ${ns0} link set macvlan4 address ${MACVLAN_ADDR}
+ip -net ${ns0} link set macvlan4 up
+
+# make the macvlan part of the bridge.
+# veth4 is not a bridge port, only the macvlan on top of it.
+ip -net ${ns0} link set macvlan4 master br0
+
+ip -net ${ns0} link set br0 up
+ip -net ${ns0} addr add 10.0.0.1/24 dev br0
+ip netns exec ${ns0} sysctl -q net.bridge.bridge-nf-call-iptables=1
+ret=$?
+if [ $ret -ne 0 ] ; then
+	echo "SKIP: bridge netfilter not available"
+	ret=$ksft_skip
+fi
+
+# for testing, so namespaces will reply to ping -b probes.
+ip netns exec ${ns0} sysctl -q net.ipv4.icmp_echo_ignore_broadcasts=0
+
+# enable conntrack in ns0 and drop broadcast packets in forward to
+# avoid them from getting confirmed in the postrouting hook before
+# the cloned skb is passed up the stack.
+ip netns exec ${ns0} nft -f - <<EOF
+table ip filter {
+	chain input {
+		type filter hook input priority 1; policy accept
+		iifname br0 counter
+		ct state new accept
+	}
+}
+
+table bridge filter {
+	chain forward {
+		type filter hook forward priority 0; policy accept
+		meta pkttype broadcast ip protocol icmp counter drop
+	}
+}
+EOF
+
+# place 1, 2 & 3 in same subnet, connected via ns0:br0.
+# ns4 is placed in same subnet as well, but its not
+# part of the bridge: the corresponding veth4 is not
+# part of the bridge, only its macvlan interface.
+for i in $(seq 1 4); do
+  eval ip -net \$ns$i link set lo up
+  eval ip -net \$ns$i link set eth0 up
+done
+for i in $(seq 1 2); do
+  eval ip -net \$ns$i addr add 10.0.0.1$i/24 dev eth0
+done
+
+ip -net ${ns3} addr add 10.23.0.13/24 dev eth0
+ip -net ${ns4} addr add 10.23.0.14/24 dev eth0
+
+# test basic connectivity
+do_ping ${ns1} 10.0.0.12
+do_ping ${ns3} 10.23.0.1
+do_ping ${ns4} 10.23.0.1
+
+if [ $ret -eq 0 ];then
+	echo "PASS: netns connectivity: ns1 can reach ns2, ns3 and ns4 can reach ns0"
+fi
+
+bcast_ping ${ns1} 10.0.0.255
+
+# This should deliver broadcast to macvlan0, which is on top of ns0:br0.
+bcast_ping ${ns3} 10.23.0.255
+
+# same, this time via veth4:macvlan4.
+bcast_ping ${ns4} 10.23.0.255
+
+read t < /proc/sys/kernel/tainted
+
+if [ $t -eq 0 ];then
+	echo PASS: kernel not tainted
+else
+	echo ERROR: kernel is tainted
+	ret=1
+fi
+
+exit $ret
diff --git a/tools/testing/selftests/netfilter/conntrack_dump_flush.c b/tools/testing/selftests/netfilter/conntrack_dump_flush.c
index f18c6db13bbf..b11ea8ee6719 100644
--- a/tools/testing/selftests/netfilter/conntrack_dump_flush.c
+++ b/tools/testing/selftests/netfilter/conntrack_dump_flush.c
@@ -13,7 +13,7 @@
 #include "../kselftest_harness.h"
 
 #define TEST_ZONE_ID 123
-#define CTA_FILTER_F_CTA_TUPLE_ZONE (1 << 2)
+#define NF_CT_DEFAULT_ZONE_ID 0
 
 static int reply_counter;
 
@@ -336,6 +336,9 @@ FIXTURE_SETUP(conntrack_dump_flush)
 	ret = conntrack_data_generate_v4(self->sock, 0xf4f4f4f4, 0xf5f5f5f5,
 					 TEST_ZONE_ID + 2);
 	EXPECT_EQ(ret, 0);
+	ret = conntrack_data_generate_v4(self->sock, 0xf6f6f6f6, 0xf7f7f7f7,
+					 NF_CT_DEFAULT_ZONE_ID);
+	EXPECT_EQ(ret, 0);
 
 	src = (struct in6_addr) {{
 		.__u6_addr32 = {
@@ -395,6 +398,26 @@ FIXTURE_SETUP(conntrack_dump_flush)
 					 TEST_ZONE_ID + 2);
 	EXPECT_EQ(ret, 0);
 
+	src = (struct in6_addr) {{
+		.__u6_addr32 = {
+			0xb80d0120,
+			0x00000000,
+			0x00000000,
+			0x07000000
+		}
+	}};
+	dst = (struct in6_addr) {{
+		.__u6_addr32 = {
+			0xb80d0120,
+			0x00000000,
+			0x00000000,
+			0x08000000
+		}
+	}};
+	ret = conntrack_data_generate_v6(self->sock, src, dst,
+					 NF_CT_DEFAULT_ZONE_ID);
+	EXPECT_EQ(ret, 0);
+
 	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID);
 	EXPECT_GE(ret, 2);
 	if (ret > 2)
@@ -425,6 +448,24 @@ TEST_F(conntrack_dump_flush, test_flush_by_zone)
 	EXPECT_EQ(ret, 2);
 	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID + 2);
 	EXPECT_EQ(ret, 2);
+	ret = conntracK_count_zone(self->sock, NF_CT_DEFAULT_ZONE_ID);
+	EXPECT_EQ(ret, 2);
+}
+
+TEST_F(conntrack_dump_flush, test_flush_by_zone_default)
+{
+	int ret;
+
+	ret = conntrack_flush_zone(self->sock, NF_CT_DEFAULT_ZONE_ID);
+	EXPECT_EQ(ret, 0);
+	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID);
+	EXPECT_EQ(ret, 2);
+	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID + 1);
+	EXPECT_EQ(ret, 2);
+	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID + 2);
+	EXPECT_EQ(ret, 2);
+	ret = conntracK_count_zone(self->sock, NF_CT_DEFAULT_ZONE_ID);
+	EXPECT_EQ(ret, 0);
 }
 
 TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/pidfd/pidfd_getfd_test.c b/tools/testing/selftests/pidfd/pidfd_getfd_test.c
index 0930e2411dfb..cd51d547b751 100644
--- a/tools/testing/selftests/pidfd/pidfd_getfd_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_getfd_test.c
@@ -5,6 +5,7 @@
 #include <fcntl.h>
 #include <limits.h>
 #include <linux/types.h>
+#include <poll.h>
 #include <sched.h>
 #include <signal.h>
 #include <stdio.h>
@@ -129,6 +130,7 @@ FIXTURE(child)
 	 * When it is closed, the child will exit.
 	 */
 	int sk;
+	bool ignore_child_result;
 };
 
 FIXTURE_SETUP(child)
@@ -165,10 +167,14 @@ FIXTURE_SETUP(child)
 
 FIXTURE_TEARDOWN(child)
 {
+	int ret;
+
 	EXPECT_EQ(0, close(self->pidfd));
 	EXPECT_EQ(0, close(self->sk));
 
-	EXPECT_EQ(0, wait_for_pid(self->pid));
+	ret = wait_for_pid(self->pid);
+	if (!self->ignore_child_result)
+		EXPECT_EQ(0, ret);
 }
 
 TEST_F(child, disable_ptrace)
@@ -235,6 +241,29 @@ TEST(flags_set)
 	EXPECT_EQ(errno, EINVAL);
 }
 
+TEST_F(child, no_strange_EBADF)
+{
+	struct pollfd fds;
+
+	self->ignore_child_result = true;
+
+	fds.fd = self->pidfd;
+	fds.events = POLLIN;
+
+	ASSERT_EQ(kill(self->pid, SIGKILL), 0);
+	ASSERT_EQ(poll(&fds, 1, 5000), 1);
+
+	/*
+	 * It used to be that pidfd_getfd() could race with the exiting thread
+	 * between exit_files() and release_task(), and get a non-null task
+	 * with a NULL files struct, and you'd get EBADF, which was slightly
+	 * confusing.
+	 */
+	errno = 0;
+	EXPECT_EQ(sys_pidfd_getfd(self->pidfd, self->remote_fd, 0), -1);
+	EXPECT_EQ(errno, ESRCH);
+}
+
 #if __NR_pidfd_getfd == -1
 int main(void)
 {
diff --git a/tools/testing/selftests/power_supply/Makefile b/tools/testing/selftests/power_supply/Makefile
new file mode 100644
index 000000000000..44f0658d3d2e
--- /dev/null
+++ b/tools/testing/selftests/power_supply/Makefile
@@ -0,0 +1,4 @@
+TEST_PROGS := test_power_supply_properties.sh
+TEST_FILES := helpers.sh
+
+include ../lib.mk
diff --git a/tools/testing/selftests/power_supply/helpers.sh b/tools/testing/selftests/power_supply/helpers.sh
new file mode 100644
index 000000000000..1ec90d7c9108
--- /dev/null
+++ b/tools/testing/selftests/power_supply/helpers.sh
@@ -0,0 +1,178 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2022, 2024 Collabora Ltd
+SYSFS_SUPPLIES=/sys/class/power_supply
+
+calc() {
+	awk "BEGIN { print $* }";
+}
+
+test_sysfs_prop() {
+	PROP="$1"
+	VALUE="$2" # optional
+
+	PROP_PATH="$SYSFS_SUPPLIES"/"$DEVNAME"/"$PROP"
+	TEST_NAME="$DEVNAME".sysfs."$PROP"
+
+	if [ -z "$VALUE" ]; then
+		ktap_test_result "$TEST_NAME" [ -f "$PROP_PATH" ]
+	else
+		ktap_test_result "$TEST_NAME" grep -q "$VALUE" "$PROP_PATH"
+	fi
+}
+
+to_human_readable_unit() {
+	VALUE="$1"
+	UNIT="$2"
+
+	case "$VALUE" in
+		*[!0-9]* ) return ;; # Not a number
+	esac
+
+	if [ "$UNIT" = "uA" ]; then
+		new_unit="mA"
+		div=1000
+	elif [ "$UNIT" = "uV" ]; then
+		new_unit="V"
+		div=1000000
+	elif [ "$UNIT" = "uAh" ]; then
+		new_unit="Ah"
+		div=1000000
+	elif [ "$UNIT" = "uW" ]; then
+		new_unit="mW"
+		div=1000
+	elif [ "$UNIT" = "uWh" ]; then
+		new_unit="Wh"
+		div=1000000
+	else
+		return
+	fi
+
+	value_converted=$(calc "$VALUE"/"$div")
+	echo "$value_converted" "$new_unit"
+}
+
+_check_sysfs_prop_available() {
+	PROP=$1
+
+	PROP_PATH="$SYSFS_SUPPLIES"/"$DEVNAME"/"$PROP"
+	TEST_NAME="$DEVNAME".sysfs."$PROP"
+
+	if [ ! -e "$PROP_PATH" ] ; then
+		ktap_test_skip "$TEST_NAME"
+		return 1
+	fi
+
+	if ! cat "$PROP_PATH" >/dev/null; then
+		ktap_print_msg "Failed to read"
+		ktap_test_fail "$TEST_NAME"
+		return 1
+	fi
+
+	return 0
+}
+
+test_sysfs_prop_optional() {
+	PROP=$1
+	UNIT=$2 # optional
+
+	TEST_NAME="$DEVNAME".sysfs."$PROP"
+
+	_check_sysfs_prop_available "$PROP" || return
+	DATA=$(cat "$SYSFS_SUPPLIES"/"$DEVNAME"/"$PROP")
+
+	ktap_print_msg "Reported: '$DATA' $UNIT ($(to_human_readable_unit "$DATA" "$UNIT"))"
+	ktap_test_pass "$TEST_NAME"
+}
+
+test_sysfs_prop_optional_range() {
+	PROP=$1
+	MIN=$2
+	MAX=$3
+	UNIT=$4 # optional
+
+	TEST_NAME="$DEVNAME".sysfs."$PROP"
+
+	_check_sysfs_prop_available "$PROP" || return
+	DATA=$(cat "$SYSFS_SUPPLIES"/"$DEVNAME"/"$PROP")
+
+	if [ "$DATA" -lt "$MIN" ] || [ "$DATA" -gt "$MAX" ]; then
+		ktap_print_msg "'$DATA' is out of range (min=$MIN, max=$MAX)"
+		ktap_test_fail "$TEST_NAME"
+	else
+		ktap_print_msg "Reported: '$DATA' $UNIT ($(to_human_readable_unit "$DATA" "$UNIT"))"
+		ktap_test_pass "$TEST_NAME"
+	fi
+}
+
+test_sysfs_prop_optional_list() {
+	PROP=$1
+	LIST=$2
+
+	TEST_NAME="$DEVNAME".sysfs."$PROP"
+
+	_check_sysfs_prop_available "$PROP" || return
+	DATA=$(cat "$SYSFS_SUPPLIES"/"$DEVNAME"/"$PROP")
+
+	valid=0
+
+	OLDIFS=$IFS
+	IFS=","
+	for item in $LIST; do
+		if [ "$DATA" = "$item" ]; then
+			valid=1
+			break
+		fi
+	done
+	if [ "$valid" -eq 1 ]; then
+		ktap_print_msg "Reported: '$DATA'"
+		ktap_test_pass "$TEST_NAME"
+	else
+		ktap_print_msg "'$DATA' is not a valid value for this property"
+		ktap_test_fail "$TEST_NAME"
+	fi
+	IFS=$OLDIFS
+}
+
+dump_file() {
+	FILE="$1"
+	while read -r line; do
+		ktap_print_msg "$line"
+	done < "$FILE"
+}
+
+__test_uevent_prop() {
+	PROP="$1"
+	OPTIONAL="$2"
+	VALUE="$3" # optional
+
+	UEVENT_PATH="$SYSFS_SUPPLIES"/"$DEVNAME"/uevent
+	TEST_NAME="$DEVNAME".uevent."$PROP"
+
+	if ! grep -q "POWER_SUPPLY_$PROP=" "$UEVENT_PATH"; then
+		if [ "$OPTIONAL" -eq 1 ]; then
+			ktap_test_skip "$TEST_NAME"
+		else
+			ktap_print_msg "Missing property"
+			ktap_test_fail "$TEST_NAME"
+		fi
+		return
+	fi
+
+	if ! grep -q "POWER_SUPPLY_$PROP=$VALUE" "$UEVENT_PATH"; then
+		ktap_print_msg "Invalid value for uevent property, dumping..."
+		dump_file "$UEVENT_PATH"
+		ktap_test_fail "$TEST_NAME"
+	else
+		ktap_test_pass "$TEST_NAME"
+	fi
+}
+
+test_uevent_prop() {
+	__test_uevent_prop "$1" 0 "$2"
+}
+
+test_uevent_prop_optional() {
+	__test_uevent_prop "$1" 1 "$2"
+}
diff --git a/tools/testing/selftests/power_supply/test_power_supply_properties.sh b/tools/testing/selftests/power_supply/test_power_supply_properties.sh
new file mode 100755
index 000000000000..df272dfe1d2a
--- /dev/null
+++ b/tools/testing/selftests/power_supply/test_power_supply_properties.sh
@@ -0,0 +1,114 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2022, 2024 Collabora Ltd
+#
+# This test validates the power supply uAPI: namely, the files in sysfs and
+# lines in uevent that expose the power supply properties.
+#
+# By default all power supplies available are tested. Optionally the name of a
+# power supply can be passed as a parameter to test only that one instead.
+DIR="$(dirname "$(readlink -f "$0")")"
+
+. "${DIR}"/../kselftest/ktap_helpers.sh
+
+. "${DIR}"/helpers.sh
+
+count_tests() {
+	SUPPLIES=$1
+
+	# This needs to be updated every time a new test is added.
+	NUM_TESTS=33
+
+	total_tests=0
+
+	for i in $SUPPLIES; do
+		total_tests=$(("$total_tests" + "$NUM_TESTS"))
+	done
+
+	echo "$total_tests"
+}
+
+ktap_print_header
+
+SYSFS_SUPPLIES=/sys/class/power_supply/
+
+if [ $# -eq 0 ]; then
+	supplies=$(ls "$SYSFS_SUPPLIES")
+else
+	supplies=$1
+fi
+
+ktap_set_plan "$(count_tests "$supplies")"
+
+for DEVNAME in $supplies; do
+	ktap_print_msg Testing device "$DEVNAME"
+
+	if [ ! -d "$SYSFS_SUPPLIES"/"$DEVNAME" ]; then
+		ktap_test_fail "$DEVNAME".exists
+		ktap_exit_fail_msg Device does not exist
+	fi
+
+	ktap_test_pass "$DEVNAME".exists
+
+	test_uevent_prop NAME "$DEVNAME"
+
+	test_sysfs_prop type
+	SUPPLY_TYPE=$(cat "$SYSFS_SUPPLIES"/"$DEVNAME"/type)
+	# This fails on kernels < 5.8 (needs 2ad3d74e3c69f)
+	test_uevent_prop TYPE "$SUPPLY_TYPE"
+
+	test_sysfs_prop_optional usb_type
+
+	test_sysfs_prop_optional_range online 0 2
+	test_sysfs_prop_optional_range present 0 1
+
+	test_sysfs_prop_optional_list status "Unknown","Charging","Discharging","Not charging","Full"
+
+	# Capacity is reported as percentage, thus any value less than 0 and
+	# greater than 100 are not allowed.
+	test_sysfs_prop_optional_range capacity 0 100 "%"
+
+	test_sysfs_prop_optional_list capacity_level "Unknown","Critical","Low","Normal","High","Full"
+
+	test_sysfs_prop_optional model_name
+	test_sysfs_prop_optional manufacturer
+	test_sysfs_prop_optional serial_number
+	test_sysfs_prop_optional_list technology "Unknown","NiMH","Li-ion","Li-poly","LiFe","NiCd","LiMn"
+
+	test_sysfs_prop_optional cycle_count
+
+	test_sysfs_prop_optional_list scope "Unknown","System","Device"
+
+	test_sysfs_prop_optional input_current_limit "uA"
+	test_sysfs_prop_optional input_voltage_limit "uV"
+
+	# Technically the power-supply class does not limit reported values.
+	# E.g. one could expose an RTC backup-battery, which goes below 1.5V or
+	# an electric vehicle battery with over 300V. But most devices do not
+	# have a step-up capable regulator behind the battery and operate with
+	# voltages considered safe to touch, so we limit the allowed range to
+	# 1.8V-60V to catch drivers reporting incorrectly scaled values. E.g. a
+	# common mistake is reporting data in mV instead of µV.
+	test_sysfs_prop_optional_range voltage_now 1800000 60000000 "uV"
+	test_sysfs_prop_optional_range voltage_min 1800000 60000000 "uV"
+	test_sysfs_prop_optional_range voltage_max 1800000 60000000 "uV"
+	test_sysfs_prop_optional_range voltage_min_design 1800000 60000000 "uV"
+	test_sysfs_prop_optional_range voltage_max_design 1800000 60000000 "uV"
+
+	# current based systems
+	test_sysfs_prop_optional current_now "uA"
+	test_sysfs_prop_optional current_max "uA"
+	test_sysfs_prop_optional charge_now "uAh"
+	test_sysfs_prop_optional charge_full "uAh"
+	test_sysfs_prop_optional charge_full_design "uAh"
+
+	# power based systems
+	test_sysfs_prop_optional power_now "uW"
+	test_sysfs_prop_optional energy_now "uWh"
+	test_sysfs_prop_optional energy_full "uWh"
+	test_sysfs_prop_optional energy_full_design "uWh"
+	test_sysfs_prop_optional energy_full_design "uWh"
+done
+
+ktap_finished
diff --git a/tools/testing/selftests/powerpc/math/fpu_signal.c b/tools/testing/selftests/powerpc/math/fpu_signal.c
index 7b1addd50420..8a64f63e37ce 100644
--- a/tools/testing/selftests/powerpc/math/fpu_signal.c
+++ b/tools/testing/selftests/powerpc/math/fpu_signal.c
@@ -18,6 +18,7 @@
 #include <pthread.h>
 
 #include "utils.h"
+#include "fpu.h"
 
 /* Number of times each thread should receive the signal */
 #define ITERATIONS 10
@@ -27,9 +28,7 @@
  */
 #define THREAD_FACTOR 8
 
-__thread double darray[] = {0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0,
-		     1.1, 1.2, 1.3, 1.4, 1.5, 1.6, 1.7, 1.8, 1.9, 2.0,
-		     2.1};
+__thread double darray[32];
 
 bool bad_context;
 int threads_starting;
@@ -43,9 +42,9 @@ void signal_fpu_sig(int sig, siginfo_t *info, void *context)
 	ucontext_t *uc = context;
 	mcontext_t *mc = &uc->uc_mcontext;
 
-	/* Only the non volatiles were loaded up */
-	for (i = 14; i < 32; i++) {
-		if (mc->fp_regs[i] != darray[i - 14]) {
+	// Don't check f30/f31, they're used as scratches in check_all_fprs()
+	for (i = 0; i < 30; i++) {
+		if (mc->fp_regs[i] != darray[i]) {
 			bad_context = true;
 			break;
 		}
@@ -54,7 +53,6 @@ void signal_fpu_sig(int sig, siginfo_t *info, void *context)
 
 void *signal_fpu_c(void *p)
 {
-	int i;
 	long rc;
 	struct sigaction act;
 	act.sa_sigaction = signal_fpu_sig;
@@ -64,9 +62,7 @@ void *signal_fpu_c(void *p)
 		return p;
 
 	srand(pthread_self());
-	for (i = 0; i < 21; i++)
-		darray[i] = rand();
-
+	randomise_darray(darray, ARRAY_SIZE(darray));
 	rc = preempt_fpu(darray, &threads_starting, &running);
 
 	return (void *) rc;
diff --git a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c
index 98cbb9109ee6..505294da1b9f 100644
--- a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c
+++ b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c
@@ -263,10 +263,10 @@ static int papr_vpd_system_loc_code(void)
 	off_t size;
 	int fd;
 
-	SKIP_IF_MSG(get_system_loc_code(&lc),
-		    "Cannot determine system location code");
 	SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
 		    DEVPATH " not present");
+	SKIP_IF_MSG(get_system_loc_code(&lc),
+		    "Cannot determine system location code");
 
 	FAIL_IF(devfd < 0);
 
diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c
index bcbca356d56a..1b339d6bbff1 100644
--- a/tools/testing/selftests/resctrl/cache.c
+++ b/tools/testing/selftests/resctrl/cache.c
@@ -3,106 +3,59 @@
 #include <stdint.h>
 #include "resctrl.h"
 
-struct read_format {
-	__u64 nr;			/* The number of events */
-	struct {
-		__u64 value;		/* The value of the event */
-	} values[2];
-};
-
-static struct perf_event_attr pea_llc_miss;
-static struct read_format rf_cqm;
-static int fd_lm;
 char llc_occup_path[1024];
 
-static void initialize_perf_event_attr(void)
+void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config)
 {
-	pea_llc_miss.type = PERF_TYPE_HARDWARE;
-	pea_llc_miss.size = sizeof(struct perf_event_attr);
-	pea_llc_miss.read_format = PERF_FORMAT_GROUP;
-	pea_llc_miss.exclude_kernel = 1;
-	pea_llc_miss.exclude_hv = 1;
-	pea_llc_miss.exclude_idle = 1;
-	pea_llc_miss.exclude_callchain_kernel = 1;
-	pea_llc_miss.inherit = 1;
-	pea_llc_miss.exclude_guest = 1;
-	pea_llc_miss.disabled = 1;
-}
-
-static void ioctl_perf_event_ioc_reset_enable(void)
-{
-	ioctl(fd_lm, PERF_EVENT_IOC_RESET, 0);
-	ioctl(fd_lm, PERF_EVENT_IOC_ENABLE, 0);
-}
-
-static int perf_event_open_llc_miss(pid_t pid, int cpu_no)
-{
-	fd_lm = perf_event_open(&pea_llc_miss, pid, cpu_no, -1,
-				PERF_FLAG_FD_CLOEXEC);
-	if (fd_lm == -1) {
-		perror("Error opening leader");
-		ctrlc_handler(0, NULL, NULL);
-		return -1;
-	}
-
-	return 0;
-}
-
-static void initialize_llc_perf(void)
-{
-	memset(&pea_llc_miss, 0, sizeof(struct perf_event_attr));
-	memset(&rf_cqm, 0, sizeof(struct read_format));
-
-	/* Initialize perf_event_attr structures for HW_CACHE_MISSES */
-	initialize_perf_event_attr();
-
-	pea_llc_miss.config = PERF_COUNT_HW_CACHE_MISSES;
-
-	rf_cqm.nr = 1;
+	memset(pea, 0, sizeof(*pea));
+	pea->type = PERF_TYPE_HARDWARE;
+	pea->size = sizeof(*pea);
+	pea->read_format = PERF_FORMAT_GROUP;
+	pea->exclude_kernel = 1;
+	pea->exclude_hv = 1;
+	pea->exclude_idle = 1;
+	pea->exclude_callchain_kernel = 1;
+	pea->inherit = 1;
+	pea->exclude_guest = 1;
+	pea->disabled = 1;
+	pea->config = config;
 }
 
-static int reset_enable_llc_perf(pid_t pid, int cpu_no)
+/* Start counters to log values */
+int perf_event_reset_enable(int pe_fd)
 {
-	int ret = 0;
+	int ret;
 
-	ret = perf_event_open_llc_miss(pid, cpu_no);
+	ret = ioctl(pe_fd, PERF_EVENT_IOC_RESET, 0);
 	if (ret < 0)
 		return ret;
 
-	/* Start counters to log values */
-	ioctl_perf_event_ioc_reset_enable();
+	ret = ioctl(pe_fd, PERF_EVENT_IOC_ENABLE, 0);
+	if (ret < 0)
+		return ret;
 
 	return 0;
 }
 
-/*
- * get_llc_perf:	llc cache miss through perf events
- * @llc_perf_miss:	LLC miss counter that is filled on success
- *
- * Perf events like HW_CACHE_MISSES could be used to validate number of
- * cache lines allocated.
- *
- * Return: =0 on success.  <0 on failure.
- */
-static int get_llc_perf(unsigned long *llc_perf_miss)
+void perf_event_initialize_read_format(struct perf_event_read *pe_read)
 {
-	__u64 total_misses;
-	int ret;
-
-	/* Stop counters after one span to get miss rate */
+	memset(pe_read, 0, sizeof(*pe_read));
+	pe_read->nr = 1;
+}
 
-	ioctl(fd_lm, PERF_EVENT_IOC_DISABLE, 0);
+int perf_open(struct perf_event_attr *pea, pid_t pid, int cpu_no)
+{
+	int pe_fd;
 
-	ret = read(fd_lm, &rf_cqm, sizeof(struct read_format));
-	if (ret == -1) {
-		perror("Could not get llc misses through perf");
+	pe_fd = perf_event_open(pea, pid, cpu_no, -1, PERF_FLAG_FD_CLOEXEC);
+	if (pe_fd == -1) {
+		ksft_perror("Error opening leader");
 		return -1;
 	}
 
-	total_misses = rf_cqm.values[0].value;
-	*llc_perf_miss = total_misses;
+	perf_event_reset_enable(pe_fd);
 
-	return 0;
+	return pe_fd;
 }
 
 /*
@@ -124,12 +77,12 @@ static int get_llc_occu_resctrl(unsigned long *llc_occupancy)
 
 	fp = fopen(llc_occup_path, "r");
 	if (!fp) {
-		perror("Failed to open results file");
+		ksft_perror("Failed to open results file");
 
-		return errno;
+		return -1;
 	}
 	if (fscanf(fp, "%lu", llc_occupancy) <= 0) {
-		perror("Could not get llc occupancy");
+		ksft_perror("Could not get llc occupancy");
 		fclose(fp);
 
 		return -1;
@@ -146,163 +99,91 @@ static int get_llc_occu_resctrl(unsigned long *llc_occupancy)
  * @llc_value:		perf miss value /
  *			llc occupancy value reported by resctrl FS
  *
- * Return:		0 on success. non-zero on failure.
+ * Return:		0 on success, < 0 on error.
  */
-static int print_results_cache(char *filename, int bm_pid,
-			       unsigned long llc_value)
+static int print_results_cache(const char *filename, int bm_pid, __u64 llc_value)
 {
 	FILE *fp;
 
 	if (strcmp(filename, "stdio") == 0 || strcmp(filename, "stderr") == 0) {
-		printf("Pid: %d \t LLC_value: %lu\n", bm_pid,
-		       llc_value);
+		printf("Pid: %d \t LLC_value: %llu\n", bm_pid, llc_value);
 	} else {
 		fp = fopen(filename, "a");
 		if (!fp) {
-			perror("Cannot open results file");
+			ksft_perror("Cannot open results file");
 
-			return errno;
+			return -1;
 		}
-		fprintf(fp, "Pid: %d \t llc_value: %lu\n", bm_pid, llc_value);
+		fprintf(fp, "Pid: %d \t llc_value: %llu\n", bm_pid, llc_value);
 		fclose(fp);
 	}
 
 	return 0;
 }
 
-int measure_cache_vals(struct resctrl_val_param *param, int bm_pid)
+/*
+ * perf_event_measure - Measure perf events
+ * @filename:	Filename for writing the results
+ * @bm_pid:	PID that runs the benchmark
+ *
+ * Measures perf events (e.g., cache misses) and writes the results into
+ * @filename. @bm_pid is written to the results file along with the measured
+ * value.
+ *
+ * Return: =0 on success. <0 on failure.
+ */
+int perf_event_measure(int pe_fd, struct perf_event_read *pe_read,
+		       const char *filename, int bm_pid)
 {
-	unsigned long llc_perf_miss = 0, llc_occu_resc = 0, llc_value = 0;
 	int ret;
 
-	/*
-	 * Measure cache miss from perf.
-	 */
-	if (!strncmp(param->resctrl_val, CAT_STR, sizeof(CAT_STR))) {
-		ret = get_llc_perf(&llc_perf_miss);
-		if (ret < 0)
-			return ret;
-		llc_value = llc_perf_miss;
-	}
+	/* Stop counters after one span to get miss rate */
+	ret = ioctl(pe_fd, PERF_EVENT_IOC_DISABLE, 0);
+	if (ret < 0)
+		return ret;
 
-	/*
-	 * Measure llc occupancy from resctrl.
-	 */
-	if (!strncmp(param->resctrl_val, CMT_STR, sizeof(CMT_STR))) {
-		ret = get_llc_occu_resctrl(&llc_occu_resc);
-		if (ret < 0)
-			return ret;
-		llc_value = llc_occu_resc;
+	ret = read(pe_fd, pe_read, sizeof(*pe_read));
+	if (ret == -1) {
+		ksft_perror("Could not get perf value");
+		return -1;
 	}
-	ret = print_results_cache(param->filename, bm_pid, llc_value);
-	if (ret)
-		return ret;
 
-	return 0;
+	return print_results_cache(filename, bm_pid, pe_read->values[0].value);
 }
 
 /*
- * cache_val:		execute benchmark and measure LLC occupancy resctrl
- * and perf cache miss for the benchmark
- * @param:		parameters passed to cache_val()
- * @span:		buffer size for the benchmark
+ * measure_llc_resctrl - Measure resctrl LLC value from resctrl
+ * @filename:	Filename for writing the results
+ * @bm_pid:	PID that runs the benchmark
  *
- * Return:		0 on success. non-zero on failure.
+ * Measures LLC occupancy from resctrl and writes the results into @filename.
+ * @bm_pid is written to the results file along with the measured value.
+ *
+ * Return: =0 on success. <0 on failure.
  */
-int cat_val(struct resctrl_val_param *param, size_t span)
+int measure_llc_resctrl(const char *filename, int bm_pid)
 {
-	int memflush = 1, operation = 0, ret = 0;
-	char *resctrl_val = param->resctrl_val;
-	pid_t bm_pid;
-
-	if (strcmp(param->filename, "") == 0)
-		sprintf(param->filename, "stdio");
-
-	bm_pid = getpid();
-
-	/* Taskset benchmark to specified cpu */
-	ret = taskset_benchmark(bm_pid, param->cpu_no);
-	if (ret)
-		return ret;
+	unsigned long llc_occu_resc = 0;
+	int ret;
 
-	/* Write benchmark to specified con_mon grp, mon_grp in resctrl FS*/
-	ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp,
-				      resctrl_val);
-	if (ret)
+	ret = get_llc_occu_resctrl(&llc_occu_resc);
+	if (ret < 0)
 		return ret;
 
-	initialize_llc_perf();
-
-	/* Test runs until the callback setup() tells the test to stop. */
-	while (1) {
-		ret = param->setup(param);
-		if (ret == END_OF_TESTS) {
-			ret = 0;
-			break;
-		}
-		if (ret < 0)
-			break;
-		ret = reset_enable_llc_perf(bm_pid, param->cpu_no);
-		if (ret)
-			break;
-
-		if (run_fill_buf(span, memflush, operation, true)) {
-			fprintf(stderr, "Error-running fill buffer\n");
-			ret = -1;
-			goto pe_close;
-		}
-
-		sleep(1);
-		ret = measure_cache_vals(param, bm_pid);
-		if (ret)
-			goto pe_close;
-	}
-
-	return ret;
-
-pe_close:
-	close(fd_lm);
-	return ret;
+	return print_results_cache(filename, bm_pid, llc_occu_resc);
 }
 
 /*
- * show_cache_info:	show cache test result information
- * @sum_llc_val:	sum of LLC cache result data
- * @no_of_bits:		number of bits
- * @cache_span:		cache span in bytes for CMT or in lines for CAT
- * @max_diff:		max difference
- * @max_diff_percent:	max difference percentage
- * @num_of_runs:	number of runs
- * @platform:		show test information on this platform
- * @cmt:		CMT test or CAT test
- *
- * Return:		0 on success. non-zero on failure.
+ * show_cache_info - Show generic cache test information
+ * @no_of_bits:		Number of bits
+ * @avg_llc_val:	Average of LLC cache result data
+ * @cache_span:		Cache span
+ * @lines:		@cache_span in lines or bytes
  */
-int show_cache_info(unsigned long sum_llc_val, int no_of_bits,
-		    size_t cache_span, unsigned long max_diff,
-		    unsigned long max_diff_percent, unsigned long num_of_runs,
-		    bool platform, bool cmt)
+void show_cache_info(int no_of_bits, __u64 avg_llc_val, size_t cache_span, bool lines)
 {
-	unsigned long avg_llc_val = 0;
-	float diff_percent;
-	long avg_diff = 0;
-	int ret;
-
-	avg_llc_val = sum_llc_val / num_of_runs;
-	avg_diff = (long)abs(cache_span - avg_llc_val);
-	diff_percent = ((float)cache_span - avg_llc_val) / cache_span * 100;
-
-	ret = platform && abs((int)diff_percent) > max_diff_percent &&
-	      (cmt ? (abs(avg_diff) > max_diff) : true);
-
-	ksft_print_msg("%s Check cache miss rate within %lu%%\n",
-		       ret ? "Fail:" : "Pass:", max_diff_percent);
-
-	ksft_print_msg("Percent diff=%d\n", abs((int)diff_percent));
 	ksft_print_msg("Number of bits: %d\n", no_of_bits);
-	ksft_print_msg("Average LLC val: %lu\n", avg_llc_val);
-	ksft_print_msg("Cache span (%s): %zu\n", cmt ? "bytes" : "lines",
+	ksft_print_msg("Average LLC val: %llu\n", avg_llc_val);
+	ksft_print_msg("Cache span (%s): %zu\n", lines ? "lines" : "bytes",
 		       cache_span);
-
-	return ret;
 }
diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index 224ba8544d8a..4cb991be8e31 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -11,108 +11,254 @@
 #include "resctrl.h"
 #include <unistd.h>
 
-#define RESULT_FILE_NAME1	"result_cat1"
-#define RESULT_FILE_NAME2	"result_cat2"
+#define RESULT_FILE_NAME	"result_cat"
 #define NUM_OF_RUNS		5
-#define MAX_DIFF_PERCENT	4
-#define MAX_DIFF		1000000
 
 /*
- * Change schemata. Write schemata to specified
- * con_mon grp, mon_grp in resctrl FS.
- * Run 5 times in order to get average values.
+ * Minimum difference in LLC misses between a test with n+1 bits CBM to the
+ * test with n bits is MIN_DIFF_PERCENT_PER_BIT * (n - 1). With e.g. 5 vs 4
+ * bits in the CBM mask, the minimum difference must be at least
+ * MIN_DIFF_PERCENT_PER_BIT * (4 - 1) = 3 percent.
+ *
+ * The relationship between number of used CBM bits and difference in LLC
+ * misses is not expected to be linear. With a small number of bits, the
+ * margin is smaller than with larger number of bits. For selftest purposes,
+ * however, linear approach is enough because ultimately only pass/fail
+ * decision has to be made and distinction between strong and stronger
+ * signal is irrelevant.
  */
-static int cat_setup(struct resctrl_val_param *p)
+#define MIN_DIFF_PERCENT_PER_BIT	1UL
+
+static int show_results_info(__u64 sum_llc_val, int no_of_bits,
+			     unsigned long cache_span,
+			     unsigned long min_diff_percent,
+			     unsigned long num_of_runs, bool platform,
+			     __s64 *prev_avg_llc_val)
 {
-	char schemata[64];
+	__u64 avg_llc_val = 0;
+	float avg_diff;
 	int ret = 0;
 
-	/* Run NUM_OF_RUNS times */
-	if (p->num_of_runs >= NUM_OF_RUNS)
-		return END_OF_TESTS;
+	avg_llc_val = sum_llc_val / num_of_runs;
+	if (*prev_avg_llc_val) {
+		float delta = (__s64)(avg_llc_val - *prev_avg_llc_val);
+
+		avg_diff = delta / *prev_avg_llc_val;
+		ret = platform && (avg_diff * 100) < (float)min_diff_percent;
+
+		ksft_print_msg("%s Check cache miss rate changed more than %.1f%%\n",
+			       ret ? "Fail:" : "Pass:", (float)min_diff_percent);
 
-	if (p->num_of_runs == 0) {
-		sprintf(schemata, "%lx", p->mask);
-		ret = write_schemata(p->ctrlgrp, schemata, p->cpu_no,
-				     p->resctrl_val);
+		ksft_print_msg("Percent diff=%.1f\n", avg_diff * 100);
 	}
-	p->num_of_runs++;
+	*prev_avg_llc_val = avg_llc_val;
+
+	show_cache_info(no_of_bits, avg_llc_val, cache_span, true);
 
 	return ret;
 }
 
-static int check_results(struct resctrl_val_param *param, size_t span)
+/* Remove the highest bit from CBM */
+static unsigned long next_mask(unsigned long current_mask)
+{
+	return current_mask & (current_mask >> 1);
+}
+
+static int check_results(struct resctrl_val_param *param, const char *cache_type,
+			 unsigned long cache_total_size, unsigned long full_cache_mask,
+			 unsigned long current_mask)
 {
 	char *token_array[8], temp[512];
-	unsigned long sum_llc_perf_miss = 0;
-	int runs = 0, no_of_bits = 0;
+	__u64 sum_llc_perf_miss = 0;
+	__s64 prev_avg_llc_val = 0;
+	unsigned long alloc_size;
+	int runs = 0;
+	int fail = 0;
+	int ret;
 	FILE *fp;
 
 	ksft_print_msg("Checking for pass/fail\n");
 	fp = fopen(param->filename, "r");
 	if (!fp) {
-		perror("# Cannot open file");
+		ksft_perror("Cannot open file");
 
-		return errno;
+		return -1;
 	}
 
 	while (fgets(temp, sizeof(temp), fp)) {
 		char *token = strtok(temp, ":\t");
 		int fields = 0;
+		int bits;
 
 		while (token) {
 			token_array[fields++] = token;
 			token = strtok(NULL, ":\t");
 		}
-		/*
-		 * Discard the first value which is inaccurate due to monitoring
-		 * setup transition phase.
-		 */
-		if (runs > 0)
-			sum_llc_perf_miss += strtoul(token_array[3], NULL, 0);
+
+		sum_llc_perf_miss += strtoull(token_array[3], NULL, 0);
 		runs++;
+
+		if (runs < NUM_OF_RUNS)
+			continue;
+
+		if (!current_mask) {
+			ksft_print_msg("Unexpected empty cache mask\n");
+			break;
+		}
+
+		alloc_size = cache_portion_size(cache_total_size, current_mask, full_cache_mask);
+
+		bits = count_bits(current_mask);
+
+		ret = show_results_info(sum_llc_perf_miss, bits,
+					alloc_size / 64,
+					MIN_DIFF_PERCENT_PER_BIT * (bits - 1),
+					runs, get_vendor() == ARCH_INTEL,
+					&prev_avg_llc_val);
+		if (ret)
+			fail = 1;
+
+		runs = 0;
+		sum_llc_perf_miss = 0;
+		current_mask = next_mask(current_mask);
 	}
 
 	fclose(fp);
-	no_of_bits = count_bits(param->mask);
 
-	return show_cache_info(sum_llc_perf_miss, no_of_bits, span / 64,
-			       MAX_DIFF, MAX_DIFF_PERCENT, runs - 1,
-			       get_vendor() == ARCH_INTEL, false);
+	return fail;
 }
 
 void cat_test_cleanup(void)
 {
-	remove(RESULT_FILE_NAME1);
-	remove(RESULT_FILE_NAME2);
+	remove(RESULT_FILE_NAME);
 }
 
-int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
+/*
+ * cat_test - Execute CAT benchmark and measure cache misses
+ * @test:		Test information structure
+ * @uparams:		User supplied parameters
+ * @param:		Parameters passed to cat_test()
+ * @span:		Buffer size for the benchmark
+ * @current_mask	Start mask for the first iteration
+ *
+ * Run CAT selftest by varying the allocated cache portion and comparing the
+ * impact on cache misses (the result analysis is done in check_results()
+ * and show_results_info(), not in this function).
+ *
+ * One bit is removed from the CAT allocation bit mask (in current_mask) for
+ * each subsequent test which keeps reducing the size of the allocated cache
+ * portion. A single test flushes the buffer, reads it to warm up the cache,
+ * and reads the buffer again. The cache misses are measured during the last
+ * read pass.
+ *
+ * Return:		0 when the test was run, < 0 on error.
+ */
+static int cat_test(const struct resctrl_test *test,
+		    const struct user_params *uparams,
+		    struct resctrl_val_param *param,
+		    size_t span, unsigned long current_mask)
 {
-	unsigned long l_mask, l_mask_1;
-	int ret, pipefd[2], sibling_cpu_no;
-	unsigned long cache_size = 0;
-	unsigned long long_mask;
-	char cbm_mask[256];
+	char *resctrl_val = param->resctrl_val;
+	struct perf_event_read pe_read;
+	struct perf_event_attr pea;
+	cpu_set_t old_affinity;
+	unsigned char *buf;
+	char schemata[64];
+	int ret, i, pe_fd;
+	pid_t bm_pid;
+
+	if (strcmp(param->filename, "") == 0)
+		sprintf(param->filename, "stdio");
+
+	bm_pid = getpid();
+
+	/* Taskset benchmark to specified cpu */
+	ret = taskset_benchmark(bm_pid, uparams->cpu, &old_affinity);
+	if (ret)
+		return ret;
+
+	/* Write benchmark to specified con_mon grp, mon_grp in resctrl FS*/
+	ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp,
+				      resctrl_val);
+	if (ret)
+		goto reset_affinity;
+
+	perf_event_attr_initialize(&pea, PERF_COUNT_HW_CACHE_MISSES);
+	perf_event_initialize_read_format(&pe_read);
+	pe_fd = perf_open(&pea, bm_pid, uparams->cpu);
+	if (pe_fd < 0) {
+		ret = -1;
+		goto reset_affinity;
+	}
+
+	buf = alloc_buffer(span, 1);
+	if (!buf) {
+		ret = -1;
+		goto pe_close;
+	}
+
+	while (current_mask) {
+		snprintf(schemata, sizeof(schemata), "%lx", param->mask & ~current_mask);
+		ret = write_schemata("", schemata, uparams->cpu, test->resource);
+		if (ret)
+			goto free_buf;
+		snprintf(schemata, sizeof(schemata), "%lx", current_mask);
+		ret = write_schemata(param->ctrlgrp, schemata, uparams->cpu, test->resource);
+		if (ret)
+			goto free_buf;
+
+		for (i = 0; i < NUM_OF_RUNS; i++) {
+			mem_flush(buf, span);
+			fill_cache_read(buf, span, true);
+
+			ret = perf_event_reset_enable(pe_fd);
+			if (ret)
+				goto free_buf;
+
+			fill_cache_read(buf, span, true);
+
+			ret = perf_event_measure(pe_fd, &pe_read, param->filename, bm_pid);
+			if (ret)
+				goto free_buf;
+		}
+		current_mask = next_mask(current_mask);
+	}
+
+free_buf:
+	free(buf);
+pe_close:
+	close(pe_fd);
+reset_affinity:
+	taskset_restore(bm_pid, &old_affinity);
+
+	return ret;
+}
+
+static int cat_run_test(const struct resctrl_test *test, const struct user_params *uparams)
+{
+	unsigned long long_mask, start_mask, full_cache_mask;
+	unsigned long cache_total_size = 0;
+	int n = uparams->bits;
+	unsigned int start;
 	int count_of_bits;
-	char pipe_message;
 	size_t span;
+	int ret;
 
-	/* Get default cbm mask for L3/L2 cache */
-	ret = get_cbm_mask(cache_type, cbm_mask);
+	ret = get_full_cbm(test->resource, &full_cache_mask);
+	if (ret)
+		return ret;
+	/* Get the largest contiguous exclusive portion of the cache */
+	ret = get_mask_no_shareable(test->resource, &long_mask);
 	if (ret)
 		return ret;
-
-	long_mask = strtoul(cbm_mask, NULL, 16);
 
 	/* Get L3/L2 cache size */
-	ret = get_cache_size(cpu_no, cache_type, &cache_size);
+	ret = get_cache_size(uparams->cpu, test->resource, &cache_total_size);
 	if (ret)
 		return ret;
-	ksft_print_msg("Cache size :%lu\n", cache_size);
+	ksft_print_msg("Cache size :%lu\n", cache_total_size);
 
-	/* Get max number of bits from default-cabm mask */
-	count_of_bits = count_bits(long_mask);
+	count_of_bits = count_contiguous_bits(long_mask, &start);
 
 	if (!n)
 		n = count_of_bits / 2;
@@ -123,89 +269,124 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 			       count_of_bits - 1);
 		return -1;
 	}
-
-	/* Get core id from same socket for running another thread */
-	sibling_cpu_no = get_core_sibling(cpu_no);
-	if (sibling_cpu_no < 0)
-		return -1;
+	start_mask = create_bit_mask(start, n);
 
 	struct resctrl_val_param param = {
 		.resctrl_val	= CAT_STR,
-		.cpu_no		= cpu_no,
-		.setup		= cat_setup,
+		.ctrlgrp	= "c1",
+		.filename	= RESULT_FILE_NAME,
+		.num_of_runs	= 0,
 	};
+	param.mask = long_mask;
+	span = cache_portion_size(cache_total_size, start_mask, full_cache_mask);
 
-	l_mask = long_mask >> n;
-	l_mask_1 = ~l_mask & long_mask;
+	remove(param.filename);
 
-	/* Set param values for parent thread which will be allocated bitmask
-	 * with (max_bits - n) bits
-	 */
-	span = cache_size * (count_of_bits - n) / count_of_bits;
-	strcpy(param.ctrlgrp, "c2");
-	strcpy(param.mongrp, "m2");
-	strcpy(param.filename, RESULT_FILE_NAME2);
-	param.mask = l_mask;
-	param.num_of_runs = 0;
-
-	if (pipe(pipefd)) {
-		perror("# Unable to create pipe");
-		return errno;
-	}
+	ret = cat_test(test, uparams, &param, span, start_mask);
+	if (ret)
+		goto out;
 
-	fflush(stdout);
-	bm_pid = fork();
+	ret = check_results(&param, test->resource,
+			    cache_total_size, full_cache_mask, start_mask);
+out:
+	cat_test_cleanup();
 
-	/* Set param values for child thread which will be allocated bitmask
-	 * with n bits
-	 */
-	if (bm_pid == 0) {
-		param.mask = l_mask_1;
-		strcpy(param.ctrlgrp, "c1");
-		strcpy(param.mongrp, "m1");
-		span = cache_size * n / count_of_bits;
-		strcpy(param.filename, RESULT_FILE_NAME1);
-		param.num_of_runs = 0;
-		param.cpu_no = sibling_cpu_no;
+	return ret;
+}
+
+static int noncont_cat_run_test(const struct resctrl_test *test,
+				const struct user_params *uparams)
+{
+	unsigned long full_cache_mask, cont_mask, noncont_mask;
+	unsigned int eax, ebx, ecx, edx, sparse_masks;
+	int bit_center, ret;
+	char schemata[64];
+
+	/* Check to compare sparse_masks content to CPUID output. */
+	ret = resource_info_unsigned_get(test->resource, "sparse_masks", &sparse_masks);
+	if (ret)
+		return ret;
+
+	if (!strcmp(test->resource, "L3"))
+		__cpuid_count(0x10, 1, eax, ebx, ecx, edx);
+	else if (!strcmp(test->resource, "L2"))
+		__cpuid_count(0x10, 2, eax, ebx, ecx, edx);
+	else
+		return -EINVAL;
+
+	if (sparse_masks != ((ecx >> 3) & 1)) {
+		ksft_print_msg("CPUID output doesn't match 'sparse_masks' file content!\n");
+		return 1;
 	}
 
-	remove(param.filename);
+	/* Write checks initialization. */
+	ret = get_full_cbm(test->resource, &full_cache_mask);
+	if (ret < 0)
+		return ret;
+	bit_center = count_bits(full_cache_mask) / 2;
 
-	ret = cat_val(&param, span);
-	if (ret == 0)
-		ret = check_results(&param, span);
-
-	if (bm_pid == 0) {
-		/* Tell parent that child is ready */
-		close(pipefd[0]);
-		pipe_message = 1;
-		if (write(pipefd[1], &pipe_message, sizeof(pipe_message)) <
-		    sizeof(pipe_message))
-			/*
-			 * Just print the error message.
-			 * Let while(1) run and wait for itself to be killed.
-			 */
-			perror("# failed signaling parent process");
-
-		close(pipefd[1]);
-		while (1)
-			;
-	} else {
-		/* Parent waits for child to be ready. */
-		close(pipefd[1]);
-		pipe_message = 0;
-		while (pipe_message != 1) {
-			if (read(pipefd[0], &pipe_message,
-				 sizeof(pipe_message)) < sizeof(pipe_message)) {
-				perror("# failed reading from child process");
-				break;
-			}
-		}
-		close(pipefd[0]);
-		kill(bm_pid, SIGKILL);
+	/*
+	 * The bit_center needs to be at least 3 to properly calculate the CBM
+	 * hole in the noncont_mask. If it's smaller return an error since the
+	 * cache mask is too short and that shouldn't happen.
+	 */
+	if (bit_center < 3)
+		return -EINVAL;
+	cont_mask = full_cache_mask >> bit_center;
+
+	/* Contiguous mask write check. */
+	snprintf(schemata, sizeof(schemata), "%lx", cont_mask);
+	ret = write_schemata("", schemata, uparams->cpu, test->resource);
+	if (ret) {
+		ksft_print_msg("Write of contiguous CBM failed\n");
+		return 1;
 	}
 
-	cat_test_cleanup();
+	/*
+	 * Non-contiguous mask write check. CBM has a 0xf hole approximately in the middle.
+	 * Output is compared with support information to catch any edge case errors.
+	 */
+	noncont_mask = ~(0xfUL << (bit_center - 2)) & full_cache_mask;
+	snprintf(schemata, sizeof(schemata), "%lx", noncont_mask);
+	ret = write_schemata("", schemata, uparams->cpu, test->resource);
+	if (ret && sparse_masks)
+		ksft_print_msg("Non-contiguous CBMs supported but write of non-contiguous CBM failed\n");
+	else if (ret && !sparse_masks)
+		ksft_print_msg("Non-contiguous CBMs not supported and write of non-contiguous CBM failed as expected\n");
+	else if (!ret && !sparse_masks)
+		ksft_print_msg("Non-contiguous CBMs not supported but write of non-contiguous CBM succeeded\n");
+
+	return !ret == !sparse_masks;
+}
 
-	return ret;
+static bool noncont_cat_feature_check(const struct resctrl_test *test)
+{
+	if (!resctrl_resource_exists(test->resource))
+		return false;
+
+	return resource_info_file_exists(test->resource, "sparse_masks");
 }
+
+struct resctrl_test l3_cat_test = {
+	.name = "L3_CAT",
+	.group = "CAT",
+	.resource = "L3",
+	.feature_check = test_resource_feature_check,
+	.run_test = cat_run_test,
+};
+
+struct resctrl_test l3_noncont_cat_test = {
+	.name = "L3_NONCONT_CAT",
+	.group = "CAT",
+	.resource = "L3",
+	.feature_check = noncont_cat_feature_check,
+	.run_test = noncont_cat_run_test,
+};
+
+struct resctrl_test l2_noncont_cat_test = {
+	.name = "L2_NONCONT_CAT",
+	.group = "CAT",
+	.resource = "L2",
+	.feature_check = noncont_cat_feature_check,
+	.run_test = noncont_cat_run_test,
+};
diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index 50bdbce9fba9..a81f91222a89 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -16,7 +16,9 @@
 #define MAX_DIFF		2000000
 #define MAX_DIFF_PERCENT	15
 
-static int cmt_setup(struct resctrl_val_param *p)
+static int cmt_setup(const struct resctrl_test *test,
+		     const struct user_params *uparams,
+		     struct resctrl_val_param *p)
 {
 	/* Run NUM_OF_RUNS times */
 	if (p->num_of_runs >= NUM_OF_RUNS)
@@ -27,6 +29,33 @@ static int cmt_setup(struct resctrl_val_param *p)
 	return 0;
 }
 
+static int show_results_info(unsigned long sum_llc_val, int no_of_bits,
+			     unsigned long cache_span, unsigned long max_diff,
+			     unsigned long max_diff_percent, unsigned long num_of_runs,
+			     bool platform)
+{
+	unsigned long avg_llc_val = 0;
+	float diff_percent;
+	long avg_diff = 0;
+	int ret;
+
+	avg_llc_val = sum_llc_val / num_of_runs;
+	avg_diff = (long)abs(cache_span - avg_llc_val);
+	diff_percent = ((float)cache_span - avg_llc_val) / cache_span * 100;
+
+	ret = platform && abs((int)diff_percent) > max_diff_percent &&
+	      abs(avg_diff) > max_diff;
+
+	ksft_print_msg("%s Check cache miss rate within %lu%%\n",
+		       ret ? "Fail:" : "Pass:", max_diff_percent);
+
+	ksft_print_msg("Percent diff=%d\n", abs((int)diff_percent));
+
+	show_cache_info(no_of_bits, avg_llc_val, cache_span, false);
+
+	return ret;
+}
+
 static int check_results(struct resctrl_val_param *param, size_t span, int no_of_bits)
 {
 	char *token_array[8], temp[512];
@@ -37,9 +66,9 @@ static int check_results(struct resctrl_val_param *param, size_t span, int no_of
 	ksft_print_msg("Checking for pass/fail\n");
 	fp = fopen(param->filename, "r");
 	if (!fp) {
-		perror("# Error in opening file\n");
+		ksft_perror("Error in opening file");
 
-		return errno;
+		return -1;
 	}
 
 	while (fgets(temp, sizeof(temp), fp)) {
@@ -58,9 +87,8 @@ static int check_results(struct resctrl_val_param *param, size_t span, int no_of
 	}
 	fclose(fp);
 
-	return show_cache_info(sum_llc_occu_resc, no_of_bits, span,
-			       MAX_DIFF, MAX_DIFF_PERCENT, runs - 1,
-			       true, true);
+	return show_results_info(sum_llc_occu_resc, no_of_bits, span,
+				 MAX_DIFF, MAX_DIFF_PERCENT, runs - 1, true);
 }
 
 void cmt_test_cleanup(void)
@@ -68,28 +96,26 @@ void cmt_test_cleanup(void)
 	remove(RESULT_FILE_NAME);
 }
 
-int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd)
+static int cmt_run_test(const struct resctrl_test *test, const struct user_params *uparams)
 {
-	const char * const *cmd = benchmark_cmd;
+	const char * const *cmd = uparams->benchmark_cmd;
 	const char *new_cmd[BENCHMARK_ARGS];
-	unsigned long cache_size = 0;
+	unsigned long cache_total_size = 0;
+	int n = uparams->bits ? : 5;
 	unsigned long long_mask;
 	char *span_str = NULL;
-	char cbm_mask[256];
 	int count_of_bits;
 	size_t span;
 	int ret, i;
 
-	ret = get_cbm_mask("L3", cbm_mask);
+	ret = get_full_cbm("L3", &long_mask);
 	if (ret)
 		return ret;
 
-	long_mask = strtoul(cbm_mask, NULL, 16);
-
-	ret = get_cache_size(cpu_no, "L3", &cache_size);
+	ret = get_cache_size(uparams->cpu, "L3", &cache_total_size);
 	if (ret)
 		return ret;
-	ksft_print_msg("Cache size :%lu\n", cache_size);
+	ksft_print_msg("Cache size :%lu\n", cache_total_size);
 
 	count_of_bits = count_bits(long_mask);
 
@@ -103,19 +129,18 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd)
 		.resctrl_val	= CMT_STR,
 		.ctrlgrp	= "c1",
 		.mongrp		= "m1",
-		.cpu_no		= cpu_no,
 		.filename	= RESULT_FILE_NAME,
 		.mask		= ~(long_mask << n) & long_mask,
 		.num_of_runs	= 0,
 		.setup		= cmt_setup,
 	};
 
-	span = cache_size * n / count_of_bits;
+	span = cache_portion_size(cache_total_size, param.mask, long_mask);
 
 	if (strcmp(cmd[0], "fill_buf") == 0) {
 		/* Duplicate the command to be able to replace span in it */
-		for (i = 0; benchmark_cmd[i]; i++)
-			new_cmd[i] = benchmark_cmd[i];
+		for (i = 0; uparams->benchmark_cmd[i]; i++)
+			new_cmd[i] = uparams->benchmark_cmd[i];
 		new_cmd[i] = NULL;
 
 		ret = asprintf(&span_str, "%zu", span);
@@ -127,11 +152,13 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd)
 
 	remove(RESULT_FILE_NAME);
 
-	ret = resctrl_val(cmd, &param);
+	ret = resctrl_val(test, uparams, cmd, &param);
 	if (ret)
 		goto out;
 
 	ret = check_results(&param, span, n);
+	if (ret && (get_vendor() == ARCH_INTEL))
+		ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
 
 out:
 	cmt_test_cleanup();
@@ -139,3 +166,16 @@ out:
 
 	return ret;
 }
+
+static bool cmt_feature_check(const struct resctrl_test *test)
+{
+	return test_resource_feature_check(test) &&
+	       resctrl_mon_feature_exists("L3_MON", "llc_occupancy");
+}
+
+struct resctrl_test cmt_test = {
+	.name = "CMT",
+	.resource = "L3",
+	.feature_check = cmt_feature_check,
+	.run_test = cmt_run_test,
+};
diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c
index 0d425f26583a..ae120f1735c0 100644
--- a/tools/testing/selftests/resctrl/fill_buf.c
+++ b/tools/testing/selftests/resctrl/fill_buf.c
@@ -38,7 +38,7 @@ static void cl_flush(void *p)
 #endif
 }
 
-static void mem_flush(unsigned char *buf, size_t buf_size)
+void mem_flush(unsigned char *buf, size_t buf_size)
 {
 	unsigned char *cp = buf;
 	size_t i = 0;
@@ -51,39 +51,38 @@ static void mem_flush(unsigned char *buf, size_t buf_size)
 	sb();
 }
 
-static void *malloc_and_init_memory(size_t buf_size)
-{
-	void *p = NULL;
-	uint64_t *p64;
-	size_t s64;
-	int ret;
-
-	ret = posix_memalign(&p, PAGE_SIZE, buf_size);
-	if (ret < 0)
-		return NULL;
-
-	p64 = (uint64_t *)p;
-	s64 = buf_size / sizeof(uint64_t);
-
-	while (s64 > 0) {
-		*p64 = (uint64_t)rand();
-		p64 += (CL_SIZE / sizeof(uint64_t));
-		s64 -= (CL_SIZE / sizeof(uint64_t));
-	}
-
-	return p;
-}
+/*
+ * Buffer index step advance to workaround HW prefetching interfering with
+ * the measurements.
+ *
+ * Must be a prime to step through all indexes of the buffer.
+ *
+ * Some primes work better than others on some architectures (from MBA/MBM
+ * result stability point of view).
+ */
+#define FILL_IDX_MULT	23
 
 static int fill_one_span_read(unsigned char *buf, size_t buf_size)
 {
-	unsigned char *end_ptr = buf + buf_size;
-	unsigned char sum, *p;
-
-	sum = 0;
-	p = buf;
-	while (p < end_ptr) {
-		sum += *p;
-		p += (CL_SIZE / 2);
+	unsigned int size = buf_size / (CL_SIZE / 2);
+	unsigned int i, idx = 0;
+	unsigned char sum = 0;
+
+	/*
+	 * Read the buffer in an order that is unexpected by HW prefetching
+	 * optimizations to prevent them interfering with the caching pattern.
+	 *
+	 * The read order is (in terms of halves of cachelines):
+	 *	i * FILL_IDX_MULT % size
+	 * The formula is open-coded below to avoiding modulo inside the loop
+	 * as it improves MBA/MBM result stability on some architectures.
+	 */
+	for (i = 0; i < size; i++) {
+		sum += buf[idx * (CL_SIZE / 2)];
+
+		idx += FILL_IDX_MULT;
+		while (idx >= size)
+			idx -= size;
 	}
 
 	return sum;
@@ -101,10 +100,9 @@ static void fill_one_span_write(unsigned char *buf, size_t buf_size)
 	}
 }
 
-static int fill_cache_read(unsigned char *buf, size_t buf_size, bool once)
+void fill_cache_read(unsigned char *buf, size_t buf_size, bool once)
 {
 	int ret = 0;
-	FILE *fp;
 
 	while (1) {
 		ret = fill_one_span_read(buf, buf_size);
@@ -113,67 +111,59 @@ static int fill_cache_read(unsigned char *buf, size_t buf_size, bool once)
 	}
 
 	/* Consume read result so that reading memory is not optimized out. */
-	fp = fopen("/dev/null", "w");
-	if (!fp) {
-		perror("Unable to write to /dev/null");
-		return -1;
-	}
-	fprintf(fp, "Sum: %d ", ret);
-	fclose(fp);
-
-	return 0;
+	*value_sink = ret;
 }
 
-static int fill_cache_write(unsigned char *buf, size_t buf_size, bool once)
+static void fill_cache_write(unsigned char *buf, size_t buf_size, bool once)
 {
 	while (1) {
 		fill_one_span_write(buf, buf_size);
 		if (once)
 			break;
 	}
-
-	return 0;
 }
 
-static int fill_cache(size_t buf_size, int memflush, int op, bool once)
+unsigned char *alloc_buffer(size_t buf_size, int memflush)
 {
-	unsigned char *buf;
+	void *buf = NULL;
+	uint64_t *p64;
+	size_t s64;
 	int ret;
 
-	buf = malloc_and_init_memory(buf_size);
-	if (!buf)
-		return -1;
-
-	/* Flush the memory before using to avoid "cache hot pages" effect */
-	if (memflush)
-		mem_flush(buf, buf_size);
-
-	if (op == 0)
-		ret = fill_cache_read(buf, buf_size, once);
-	else
-		ret = fill_cache_write(buf, buf_size, once);
+	ret = posix_memalign(&buf, PAGE_SIZE, buf_size);
+	if (ret < 0)
+		return NULL;
 
-	free(buf);
+	/* Initialize the buffer */
+	p64 = buf;
+	s64 = buf_size / sizeof(uint64_t);
 
-	if (ret) {
-		printf("\n Error in fill cache read/write...\n");
-		return -1;
+	while (s64 > 0) {
+		*p64 = (uint64_t)rand();
+		p64 += (CL_SIZE / sizeof(uint64_t));
+		s64 -= (CL_SIZE / sizeof(uint64_t));
 	}
 
+	/* Flush the memory before using to avoid "cache hot pages" effect */
+	if (memflush)
+		mem_flush(buf, buf_size);
 
-	return 0;
+	return buf;
 }
 
-int run_fill_buf(size_t span, int memflush, int op, bool once)
+int run_fill_buf(size_t buf_size, int memflush, int op, bool once)
 {
-	size_t cache_size = span;
-	int ret;
+	unsigned char *buf;
 
-	ret = fill_cache(cache_size, memflush, op, once);
-	if (ret) {
-		printf("\n Error in fill cache\n");
+	buf = alloc_buffer(buf_size, memflush);
+	if (!buf)
 		return -1;
-	}
+
+	if (op == 0)
+		fill_cache_read(buf, buf_size, once);
+	else
+		fill_cache_write(buf, buf_size, once);
+	free(buf);
 
 	return 0;
 }
diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index d3bf4368341e..7946e32e85c8 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -22,7 +22,9 @@
  * con_mon grp, mon_grp in resctrl FS.
  * For each allocation, run 5 times in order to get average values.
  */
-static int mba_setup(struct resctrl_val_param *p)
+static int mba_setup(const struct resctrl_test *test,
+		     const struct user_params *uparams,
+		     struct resctrl_val_param *p)
 {
 	static int runs_per_allocation, allocation = 100;
 	char allocation_str[64];
@@ -40,8 +42,7 @@ static int mba_setup(struct resctrl_val_param *p)
 
 	sprintf(allocation_str, "%d", allocation);
 
-	ret = write_schemata(p->ctrlgrp, allocation_str, p->cpu_no,
-			     p->resctrl_val);
+	ret = write_schemata(p->ctrlgrp, allocation_str, uparams->cpu, test->resource);
 	if (ret < 0)
 		return ret;
 
@@ -109,9 +110,9 @@ static int check_results(void)
 
 	fp = fopen(output, "r");
 	if (!fp) {
-		perror(output);
+		ksft_perror(output);
 
-		return errno;
+		return -1;
 	}
 
 	runs = 0;
@@ -141,13 +142,12 @@ void mba_test_cleanup(void)
 	remove(RESULT_FILE_NAME);
 }
 
-int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd)
+static int mba_run_test(const struct resctrl_test *test, const struct user_params *uparams)
 {
 	struct resctrl_val_param param = {
 		.resctrl_val	= MBA_STR,
 		.ctrlgrp	= "c1",
 		.mongrp		= "m1",
-		.cpu_no		= cpu_no,
 		.filename	= RESULT_FILE_NAME,
 		.bw_report	= "reads",
 		.setup		= mba_setup
@@ -156,7 +156,7 @@ int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd)
 
 	remove(RESULT_FILE_NAME);
 
-	ret = resctrl_val(benchmark_cmd, &param);
+	ret = resctrl_val(test, uparams, uparams->benchmark_cmd, &param);
 	if (ret)
 		goto out;
 
@@ -167,3 +167,17 @@ out:
 
 	return ret;
 }
+
+static bool mba_feature_check(const struct resctrl_test *test)
+{
+	return test_resource_feature_check(test) &&
+	       resctrl_mon_feature_exists("L3_MON", "mbm_local_bytes");
+}
+
+struct resctrl_test mba_test = {
+	.name = "MBA",
+	.resource = "MB",
+	.vendor_specific = ARCH_INTEL,
+	.feature_check = mba_feature_check,
+	.run_test = mba_run_test,
+};
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index 741533f2b075..d67ffa3ec63a 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -59,9 +59,9 @@ static int check_results(size_t span)
 
 	fp = fopen(output, "r");
 	if (!fp) {
-		perror(output);
+		ksft_perror(output);
 
-		return errno;
+		return -1;
 	}
 
 	runs = 0;
@@ -86,7 +86,9 @@ static int check_results(size_t span)
 	return ret;
 }
 
-static int mbm_setup(struct resctrl_val_param *p)
+static int mbm_setup(const struct resctrl_test *test,
+		     const struct user_params *uparams,
+		     struct resctrl_val_param *p)
 {
 	int ret = 0;
 
@@ -95,9 +97,8 @@ static int mbm_setup(struct resctrl_val_param *p)
 		return END_OF_TESTS;
 
 	/* Set up shemata with 100% allocation on the first run. */
-	if (p->num_of_runs == 0 && validate_resctrl_feature_request("MB", NULL))
-		ret = write_schemata(p->ctrlgrp, "100", p->cpu_no,
-				     p->resctrl_val);
+	if (p->num_of_runs == 0 && resctrl_resource_exists("MB"))
+		ret = write_schemata(p->ctrlgrp, "100", uparams->cpu, test->resource);
 
 	p->num_of_runs++;
 
@@ -109,13 +110,12 @@ void mbm_test_cleanup(void)
 	remove(RESULT_FILE_NAME);
 }
 
-int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd)
+static int mbm_run_test(const struct resctrl_test *test, const struct user_params *uparams)
 {
 	struct resctrl_val_param param = {
 		.resctrl_val	= MBM_STR,
 		.ctrlgrp	= "c1",
 		.mongrp		= "m1",
-		.cpu_no		= cpu_no,
 		.filename	= RESULT_FILE_NAME,
 		.bw_report	= "reads",
 		.setup		= mbm_setup
@@ -124,14 +124,30 @@ int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd)
 
 	remove(RESULT_FILE_NAME);
 
-	ret = resctrl_val(benchmark_cmd, &param);
+	ret = resctrl_val(test, uparams, uparams->benchmark_cmd, &param);
 	if (ret)
 		goto out;
 
 	ret = check_results(DEFAULT_SPAN);
+	if (ret && (get_vendor() == ARCH_INTEL))
+		ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
 
 out:
 	mbm_test_cleanup();
 
 	return ret;
 }
+
+static bool mbm_feature_check(const struct resctrl_test *test)
+{
+	return resctrl_mon_feature_exists("L3_MON", "mbm_total_bytes") &&
+	       resctrl_mon_feature_exists("L3_MON", "mbm_local_bytes");
+}
+
+struct resctrl_test mbm_test = {
+	.name = "MBM",
+	.resource = "MB",
+	.vendor_specific = ARCH_INTEL,
+	.feature_check = mbm_feature_check,
+	.run_test = mbm_run_test,
+};
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index a33f414f6019..2051bd135e0d 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -28,6 +28,12 @@
 #define PHYS_ID_PATH		"/sys/devices/system/cpu/cpu"
 #define INFO_PATH		"/sys/fs/resctrl/info"
 
+/*
+ * CPU vendor IDs
+ *
+ * Define as bits because they're used for vendor_specific bitmask in
+ * the struct resctrl_test.
+ */
 #define ARCH_INTEL     1
 #define ARCH_AMD       2
 
@@ -37,20 +43,52 @@
 
 #define DEFAULT_SPAN		(250 * MB)
 
-#define PARENT_EXIT(err_msg)			\
+#define PARENT_EXIT()				\
 	do {					\
-		perror(err_msg);		\
 		kill(ppid, SIGKILL);		\
 		umount_resctrlfs();		\
 		exit(EXIT_FAILURE);		\
 	} while (0)
 
 /*
+ * user_params:		User supplied parameters
+ * @cpu:		CPU number to which the benchmark will be bound to
+ * @bits:		Number of bits used for cache allocation size
+ * @benchmark_cmd:	Benchmark command to run during (some of the) tests
+ */
+struct user_params {
+	int cpu;
+	int bits;
+	const char *benchmark_cmd[BENCHMARK_ARGS];
+};
+
+/*
+ * resctrl_test:	resctrl test definition
+ * @name:		Test name
+ * @group:		Test group - a common name for tests that share some characteristic
+ *			(e.g., L3 CAT test belongs to the CAT group). Can be NULL
+ * @resource:		Resource to test (e.g., MB, L3, L2, etc.)
+ * @vendor_specific:	Bitmask for vendor-specific tests (can be 0 for universal tests)
+ * @disabled:		Test is disabled
+ * @feature_check:	Callback to check required resctrl features
+ * @run_test:		Callback to run the test
+ */
+struct resctrl_test {
+	const char	*name;
+	const char	*group;
+	const char	*resource;
+	unsigned int	vendor_specific;
+	bool		disabled;
+	bool		(*feature_check)(const struct resctrl_test *test);
+	int		(*run_test)(const struct resctrl_test *test,
+				    const struct user_params *uparams);
+};
+
+/*
  * resctrl_val_param:	resctrl test parameters
  * @resctrl_val:	Resctrl feature (Eg: mbm, mba.. etc)
  * @ctrlgrp:		Name of the control monitor group (con_mon grp)
  * @mongrp:		Name of the monitor group (mon grp)
- * @cpu_no:		CPU number to which the benchmark would be binded
  * @filename:		Name of file to which the o/p should be written
  * @bw_report:		Bandwidth report type (reads vs writes)
  * @setup:		Call back function to setup test environment
@@ -59,12 +97,20 @@ struct resctrl_val_param {
 	char		*resctrl_val;
 	char		ctrlgrp[64];
 	char		mongrp[64];
-	int		cpu_no;
 	char		filename[64];
 	char		*bw_report;
 	unsigned long	mask;
 	int		num_of_runs;
-	int		(*setup)(struct resctrl_val_param *param);
+	int		(*setup)(const struct resctrl_test *test,
+				 const struct user_params *uparams,
+				 struct resctrl_val_param *param);
+};
+
+struct perf_event_read {
+	__u64 nr;			/* The number of events */
+	struct {
+		__u64 value;		/* The value of the event */
+	} values[2];
 };
 
 #define MBM_STR			"mbm"
@@ -72,6 +118,13 @@ struct resctrl_val_param {
 #define CMT_STR			"cmt"
 #define CAT_STR			"cat"
 
+/*
+ * Memory location that consumes values compiler must not optimize away.
+ * Volatile ensures writes to this location cannot be optimized away by
+ * compiler.
+ */
+extern volatile int *value_sink;
+
 extern pid_t bm_pid, ppid;
 
 extern char llc_occup_path[1024];
@@ -79,42 +132,84 @@ extern char llc_occup_path[1024];
 int get_vendor(void);
 bool check_resctrlfs_support(void);
 int filter_dmesg(void);
-int get_resource_id(int cpu_no, int *resource_id);
+int get_domain_id(const char *resource, int cpu_no, int *domain_id);
 int mount_resctrlfs(void);
 int umount_resctrlfs(void);
 int validate_bw_report_request(char *bw_report);
-bool validate_resctrl_feature_request(const char *resource, const char *feature);
+bool resctrl_resource_exists(const char *resource);
+bool resctrl_mon_feature_exists(const char *resource, const char *feature);
+bool resource_info_file_exists(const char *resource, const char *file);
+bool test_resource_feature_check(const struct resctrl_test *test);
 char *fgrep(FILE *inf, const char *str);
-int taskset_benchmark(pid_t bm_pid, int cpu_no);
-int write_schemata(char *ctrlgrp, char *schemata, int cpu_no,
-		   char *resctrl_val);
+int taskset_benchmark(pid_t bm_pid, int cpu_no, cpu_set_t *old_affinity);
+int taskset_restore(pid_t bm_pid, cpu_set_t *old_affinity);
+int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, const char *resource);
 int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
 			    char *resctrl_val);
 int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu,
 		    int group_fd, unsigned long flags);
-int run_fill_buf(size_t span, int memflush, int op, bool once);
-int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *param);
-int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd);
+unsigned char *alloc_buffer(size_t buf_size, int memflush);
+void mem_flush(unsigned char *buf, size_t buf_size);
+void fill_cache_read(unsigned char *buf, size_t buf_size, bool once);
+int run_fill_buf(size_t buf_size, int memflush, int op, bool once);
+int resctrl_val(const struct resctrl_test *test,
+		const struct user_params *uparams,
+		const char * const *benchmark_cmd,
+		struct resctrl_val_param *param);
 void tests_cleanup(void);
 void mbm_test_cleanup(void);
-int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd);
 void mba_test_cleanup(void);
-int get_cbm_mask(char *cache_type, char *cbm_mask);
-int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size);
+unsigned long create_bit_mask(unsigned int start, unsigned int len);
+unsigned int count_contiguous_bits(unsigned long val, unsigned int *start);
+int get_full_cbm(const char *cache_type, unsigned long *mask);
+int get_mask_no_shareable(const char *cache_type, unsigned long *mask);
+int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size);
+int resource_info_unsigned_get(const char *resource, const char *filename, unsigned int *val);
 void ctrlc_handler(int signum, siginfo_t *info, void *ptr);
 int signal_handler_register(void);
 void signal_handler_unregister(void);
-int cat_val(struct resctrl_val_param *param, size_t span);
 void cat_test_cleanup(void);
-int cat_perf_miss_val(int cpu_no, int no_of_bits, char *cache_type);
-int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd);
 unsigned int count_bits(unsigned long n);
 void cmt_test_cleanup(void);
-int get_core_sibling(int cpu_no);
-int measure_cache_vals(struct resctrl_val_param *param, int bm_pid);
-int show_cache_info(unsigned long sum_llc_val, int no_of_bits,
-		    size_t cache_span, unsigned long max_diff,
-		    unsigned long max_diff_percent, unsigned long num_of_runs,
-		    bool platform, bool cmt);
+
+void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config);
+void perf_event_initialize_read_format(struct perf_event_read *pe_read);
+int perf_open(struct perf_event_attr *pea, pid_t pid, int cpu_no);
+int perf_event_reset_enable(int pe_fd);
+int perf_event_measure(int pe_fd, struct perf_event_read *pe_read,
+		       const char *filename, int bm_pid);
+int measure_llc_resctrl(const char *filename, int bm_pid);
+void show_cache_info(int no_of_bits, __u64 avg_llc_val, size_t cache_span, bool lines);
+
+/*
+ * cache_portion_size - Calculate the size of a cache portion
+ * @cache_size:		Total cache size in bytes
+ * @portion_mask:	Cache portion mask
+ * @full_cache_mask:	Full Cache Bit Mask (CBM) for the cache
+ *
+ * Return: The size of the cache portion in bytes.
+ */
+static inline unsigned long cache_portion_size(unsigned long cache_size,
+					       unsigned long portion_mask,
+					       unsigned long full_cache_mask)
+{
+	unsigned int bits = count_bits(full_cache_mask);
+
+	/*
+	 * With no bits the full CBM, assume cache cannot be split into
+	 * smaller portions. To avoid divide by zero, return cache_size.
+	 */
+	if (!bits)
+		return cache_size;
+
+	return cache_size * count_bits(portion_mask) / bits;
+}
+
+extern struct resctrl_test mbm_test;
+extern struct resctrl_test mba_test;
+extern struct resctrl_test cmt_test;
+extern struct resctrl_test l3_cat_test;
+extern struct resctrl_test l3_noncont_cat_test;
+extern struct resctrl_test l2_noncont_cat_test;
 
 #endif /* RESCTRL_H */
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index 2bbe3045a018..f3dc1b9696e7 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -10,6 +10,19 @@
  */
 #include "resctrl.h"
 
+/* Volatile memory sink to prevent compiler optimizations */
+static volatile int sink_target;
+volatile int *value_sink = &sink_target;
+
+static struct resctrl_test *resctrl_tests[] = {
+	&mbm_test,
+	&mba_test,
+	&cmt_test,
+	&l3_cat_test,
+	&l3_noncont_cat_test,
+	&l2_noncont_cat_test,
+};
+
 static int detect_vendor(void)
 {
 	FILE *inf = fopen("/proc/cpuinfo", "r");
@@ -49,11 +62,20 @@ int get_vendor(void)
 
 static void cmd_help(void)
 {
+	int i;
+
 	printf("usage: resctrl_tests [-h] [-t test list] [-n no_of_bits] [-b benchmark_cmd [option]...]\n");
 	printf("\t-b benchmark_cmd [option]...: run specified benchmark for MBM, MBA and CMT\n");
 	printf("\t   default benchmark is builtin fill_buf\n");
-	printf("\t-t test list: run tests specified in the test list, ");
+	printf("\t-t test list: run tests/groups specified by the list, ");
 	printf("e.g. -t mbm,mba,cmt,cat\n");
+	printf("\t\tSupported tests (group):\n");
+	for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++) {
+		if (resctrl_tests[i]->group)
+			printf("\t\t\t%s (%s)\n", resctrl_tests[i]->name, resctrl_tests[i]->group);
+		else
+			printf("\t\t\t%s\n", resctrl_tests[i]->name);
+	}
 	printf("\t-n no_of_bits: run cache tests using specified no of bits in cache bit mask\n");
 	printf("\t-p cpu_no: specify CPU number to run the test. 1 is default\n");
 	printf("\t-h: help\n");
@@ -92,116 +114,63 @@ static void test_cleanup(void)
 	signal_handler_unregister();
 }
 
-static void run_mbm_test(const char * const *benchmark_cmd, int cpu_no)
+static bool test_vendor_specific_check(const struct resctrl_test *test)
 {
-	int res;
-
-	ksft_print_msg("Starting MBM BW change ...\n");
-
-	if (test_prepare()) {
-		ksft_exit_fail_msg("Abnormal failure when preparing for the test\n");
-		return;
-	}
-
-	if (!validate_resctrl_feature_request("L3_MON", "mbm_total_bytes") ||
-	    !validate_resctrl_feature_request("L3_MON", "mbm_local_bytes") ||
-	    (get_vendor() != ARCH_INTEL)) {
-		ksft_test_result_skip("Hardware does not support MBM or MBM is disabled\n");
-		goto cleanup;
-	}
-
-	res = mbm_bw_change(cpu_no, benchmark_cmd);
-	ksft_test_result(!res, "MBM: bw change\n");
-	if ((get_vendor() == ARCH_INTEL) && res)
-		ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
+	if (!test->vendor_specific)
+		return true;
 
-cleanup:
-	test_cleanup();
+	return get_vendor() & test->vendor_specific;
 }
 
-static void run_mba_test(const char * const *benchmark_cmd, int cpu_no)
+static void run_single_test(const struct resctrl_test *test, const struct user_params *uparams)
 {
-	int res;
-
-	ksft_print_msg("Starting MBA Schemata change ...\n");
+	int ret;
 
-	if (test_prepare()) {
-		ksft_exit_fail_msg("Abnormal failure when preparing for the test\n");
+	if (test->disabled)
 		return;
-	}
 
-	if (!validate_resctrl_feature_request("MB", NULL) ||
-	    !validate_resctrl_feature_request("L3_MON", "mbm_local_bytes") ||
-	    (get_vendor() != ARCH_INTEL)) {
-		ksft_test_result_skip("Hardware does not support MBA or MBA is disabled\n");
-		goto cleanup;
+	if (!test_vendor_specific_check(test)) {
+		ksft_test_result_skip("Hardware does not support %s\n", test->name);
+		return;
 	}
 
-	res = mba_schemata_change(cpu_no, benchmark_cmd);
-	ksft_test_result(!res, "MBA: schemata change\n");
-
-cleanup:
-	test_cleanup();
-}
-
-static void run_cmt_test(const char * const *benchmark_cmd, int cpu_no)
-{
-	int res;
-
-	ksft_print_msg("Starting CMT test ...\n");
+	ksft_print_msg("Starting %s test ...\n", test->name);
 
 	if (test_prepare()) {
 		ksft_exit_fail_msg("Abnormal failure when preparing for the test\n");
 		return;
 	}
 
-	if (!validate_resctrl_feature_request("L3_MON", "llc_occupancy") ||
-	    !validate_resctrl_feature_request("L3", NULL)) {
-		ksft_test_result_skip("Hardware does not support CMT or CMT is disabled\n");
+	if (!test->feature_check(test)) {
+		ksft_test_result_skip("Hardware does not support %s or %s is disabled\n",
+				      test->name, test->name);
 		goto cleanup;
 	}
 
-	res = cmt_resctrl_val(cpu_no, 5, benchmark_cmd);
-	ksft_test_result(!res, "CMT: test\n");
-	if ((get_vendor() == ARCH_INTEL) && res)
-		ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
+	ret = test->run_test(test, uparams);
+	ksft_test_result(!ret, "%s: test\n", test->name);
 
 cleanup:
 	test_cleanup();
 }
 
-static void run_cat_test(int cpu_no, int no_of_bits)
+static void init_user_params(struct user_params *uparams)
 {
-	int res;
-
-	ksft_print_msg("Starting CAT test ...\n");
-
-	if (test_prepare()) {
-		ksft_exit_fail_msg("Abnormal failure when preparing for the test\n");
-		return;
-	}
-
-	if (!validate_resctrl_feature_request("L3", NULL)) {
-		ksft_test_result_skip("Hardware does not support CAT or CAT is disabled\n");
-		goto cleanup;
-	}
+	memset(uparams, 0, sizeof(*uparams));
 
-	res = cat_perf_miss_val(cpu_no, no_of_bits, "L3");
-	ksft_test_result(!res, "CAT: test\n");
-
-cleanup:
-	test_cleanup();
+	uparams->cpu = 1;
+	uparams->bits = 0;
 }
 
 int main(int argc, char **argv)
 {
-	bool mbm_test = true, mba_test = true, cmt_test = true;
-	const char *benchmark_cmd[BENCHMARK_ARGS] = {};
-	int c, cpu_no = 1, i, no_of_bits = 0;
+	int tests = ARRAY_SIZE(resctrl_tests);
+	bool test_param_seen = false;
+	struct user_params uparams;
 	char *span_str = NULL;
-	bool cat_test = true;
-	int tests = 0;
-	int ret;
+	int ret, c, i;
+
+	init_user_params(&uparams);
 
 	while ((c = getopt(argc, argv, "ht:b:n:p:")) != -1) {
 		char *token;
@@ -219,32 +188,35 @@ int main(int argc, char **argv)
 
 			/* Extract benchmark command from command line. */
 			for (i = 0; i < argc - optind; i++)
-				benchmark_cmd[i] = argv[i + optind];
-			benchmark_cmd[i] = NULL;
+				uparams.benchmark_cmd[i] = argv[i + optind];
+			uparams.benchmark_cmd[i] = NULL;
 
 			goto last_arg;
 		case 't':
 			token = strtok(optarg, ",");
 
-			mbm_test = false;
-			mba_test = false;
-			cmt_test = false;
-			cat_test = false;
+			if (!test_param_seen) {
+				for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++)
+					resctrl_tests[i]->disabled = true;
+				tests = 0;
+				test_param_seen = true;
+			}
 			while (token) {
-				if (!strncmp(token, MBM_STR, sizeof(MBM_STR))) {
-					mbm_test = true;
-					tests++;
-				} else if (!strncmp(token, MBA_STR, sizeof(MBA_STR))) {
-					mba_test = true;
-					tests++;
-				} else if (!strncmp(token, CMT_STR, sizeof(CMT_STR))) {
-					cmt_test = true;
-					tests++;
-				} else if (!strncmp(token, CAT_STR, sizeof(CAT_STR))) {
-					cat_test = true;
-					tests++;
-				} else {
-					printf("invalid argument\n");
+				bool found = false;
+
+				for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++) {
+					if (!strcasecmp(token, resctrl_tests[i]->name) ||
+					    (resctrl_tests[i]->group &&
+					     !strcasecmp(token, resctrl_tests[i]->group))) {
+						if (resctrl_tests[i]->disabled)
+							tests++;
+						resctrl_tests[i]->disabled = false;
+						found = true;
+					}
+				}
+
+				if (!found) {
+					printf("invalid test: %s\n", token);
 
 					return -1;
 				}
@@ -252,11 +224,11 @@ int main(int argc, char **argv)
 			}
 			break;
 		case 'p':
-			cpu_no = atoi(optarg);
+			uparams.cpu = atoi(optarg);
 			break;
 		case 'n':
-			no_of_bits = atoi(optarg);
-			if (no_of_bits <= 0) {
+			uparams.bits = atoi(optarg);
+			if (uparams.bits <= 0) {
 				printf("Bail out! invalid argument for no_of_bits\n");
 				return -1;
 			}
@@ -291,32 +263,23 @@ last_arg:
 
 	filter_dmesg();
 
-	if (!benchmark_cmd[0]) {
+	if (!uparams.benchmark_cmd[0]) {
 		/* If no benchmark is given by "-b" argument, use fill_buf. */
-		benchmark_cmd[0] = "fill_buf";
+		uparams.benchmark_cmd[0] = "fill_buf";
 		ret = asprintf(&span_str, "%u", DEFAULT_SPAN);
 		if (ret < 0)
 			ksft_exit_fail_msg("Out of memory!\n");
-		benchmark_cmd[1] = span_str;
-		benchmark_cmd[2] = "1";
-		benchmark_cmd[3] = "0";
-		benchmark_cmd[4] = "false";
-		benchmark_cmd[5] = NULL;
+		uparams.benchmark_cmd[1] = span_str;
+		uparams.benchmark_cmd[2] = "1";
+		uparams.benchmark_cmd[3] = "0";
+		uparams.benchmark_cmd[4] = "false";
+		uparams.benchmark_cmd[5] = NULL;
 	}
 
-	ksft_set_plan(tests ? : 4);
-
-	if (mbm_test)
-		run_mbm_test(benchmark_cmd, cpu_no);
-
-	if (mba_test)
-		run_mba_test(benchmark_cmd, cpu_no);
-
-	if (cmt_test)
-		run_cmt_test(benchmark_cmd, cpu_no);
+	ksft_set_plan(tests);
 
-	if (cat_test)
-		run_cat_test(cpu_no, no_of_bits);
+	for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++)
+		run_single_test(resctrl_tests[i], &uparams);
 
 	free(span_str);
 	ksft_finished();
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 88789678917b..5a49f07a6c85 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -156,12 +156,12 @@ static int read_from_imc_dir(char *imc_dir, int count)
 	sprintf(imc_counter_type, "%s%s", imc_dir, "type");
 	fp = fopen(imc_counter_type, "r");
 	if (!fp) {
-		perror("Failed to open imc counter type file");
+		ksft_perror("Failed to open iMC counter type file");
 
 		return -1;
 	}
 	if (fscanf(fp, "%u", &imc_counters_config[count][READ].type) <= 0) {
-		perror("Could not get imc type");
+		ksft_perror("Could not get iMC type");
 		fclose(fp);
 
 		return -1;
@@ -175,12 +175,12 @@ static int read_from_imc_dir(char *imc_dir, int count)
 	sprintf(imc_counter_cfg, "%s%s", imc_dir, READ_FILE_NAME);
 	fp = fopen(imc_counter_cfg, "r");
 	if (!fp) {
-		perror("Failed to open imc config file");
+		ksft_perror("Failed to open iMC config file");
 
 		return -1;
 	}
 	if (fscanf(fp, "%s", cas_count_cfg) <= 0) {
-		perror("Could not get imc cas count read");
+		ksft_perror("Could not get iMC cas count read");
 		fclose(fp);
 
 		return -1;
@@ -193,12 +193,12 @@ static int read_from_imc_dir(char *imc_dir, int count)
 	sprintf(imc_counter_cfg, "%s%s", imc_dir, WRITE_FILE_NAME);
 	fp = fopen(imc_counter_cfg, "r");
 	if (!fp) {
-		perror("Failed to open imc config file");
+		ksft_perror("Failed to open iMC config file");
 
 		return -1;
 	}
 	if  (fscanf(fp, "%s", cas_count_cfg) <= 0) {
-		perror("Could not get imc cas count write");
+		ksft_perror("Could not get iMC cas count write");
 		fclose(fp);
 
 		return -1;
@@ -262,12 +262,12 @@ static int num_of_imcs(void)
 		}
 		closedir(dp);
 		if (count == 0) {
-			perror("Unable find iMC counters!\n");
+			ksft_print_msg("Unable to find iMC counters\n");
 
 			return -1;
 		}
 	} else {
-		perror("Unable to open PMU directory!\n");
+		ksft_perror("Unable to open PMU directory");
 
 		return -1;
 	}
@@ -339,14 +339,14 @@ static int get_mem_bw_imc(int cpu_no, char *bw_report, float *bw_imc)
 
 		if (read(r->fd, &r->return_value,
 			 sizeof(struct membw_read_format)) == -1) {
-			perror("Couldn't get read b/w through iMC");
+			ksft_perror("Couldn't get read b/w through iMC");
 
 			return -1;
 		}
 
 		if (read(w->fd, &w->return_value,
 			 sizeof(struct membw_read_format)) == -1) {
-			perror("Couldn't get write bw through iMC");
+			ksft_perror("Couldn't get write bw through iMC");
 
 			return -1;
 		}
@@ -387,20 +387,20 @@ static int get_mem_bw_imc(int cpu_no, char *bw_report, float *bw_imc)
 	return 0;
 }
 
-void set_mbm_path(const char *ctrlgrp, const char *mongrp, int resource_id)
+void set_mbm_path(const char *ctrlgrp, const char *mongrp, int domain_id)
 {
 	if (ctrlgrp && mongrp)
 		sprintf(mbm_total_path, CON_MON_MBM_LOCAL_BYTES_PATH,
-			RESCTRL_PATH, ctrlgrp, mongrp, resource_id);
+			RESCTRL_PATH, ctrlgrp, mongrp, domain_id);
 	else if (!ctrlgrp && mongrp)
 		sprintf(mbm_total_path, MON_MBM_LOCAL_BYTES_PATH, RESCTRL_PATH,
-			mongrp, resource_id);
+			mongrp, domain_id);
 	else if (ctrlgrp && !mongrp)
 		sprintf(mbm_total_path, CON_MBM_LOCAL_BYTES_PATH, RESCTRL_PATH,
-			ctrlgrp, resource_id);
+			ctrlgrp, domain_id);
 	else if (!ctrlgrp && !mongrp)
 		sprintf(mbm_total_path, MBM_LOCAL_BYTES_PATH, RESCTRL_PATH,
-			resource_id);
+			domain_id);
 }
 
 /*
@@ -413,23 +413,23 @@ void set_mbm_path(const char *ctrlgrp, const char *mongrp, int resource_id)
 static void initialize_mem_bw_resctrl(const char *ctrlgrp, const char *mongrp,
 				      int cpu_no, char *resctrl_val)
 {
-	int resource_id;
+	int domain_id;
 
-	if (get_resource_id(cpu_no, &resource_id) < 0) {
-		perror("Could not get resource_id");
+	if (get_domain_id("MB", cpu_no, &domain_id) < 0) {
+		ksft_print_msg("Could not get domain ID\n");
 		return;
 	}
 
 	if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)))
-		set_mbm_path(ctrlgrp, mongrp, resource_id);
+		set_mbm_path(ctrlgrp, mongrp, domain_id);
 
 	if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) {
 		if (ctrlgrp)
 			sprintf(mbm_total_path, CON_MBM_LOCAL_BYTES_PATH,
-				RESCTRL_PATH, ctrlgrp, resource_id);
+				RESCTRL_PATH, ctrlgrp, domain_id);
 		else
 			sprintf(mbm_total_path, MBM_LOCAL_BYTES_PATH,
-				RESCTRL_PATH, resource_id);
+				RESCTRL_PATH, domain_id);
 	}
 }
 
@@ -449,12 +449,12 @@ static int get_mem_bw_resctrl(unsigned long *mbm_total)
 
 	fp = fopen(mbm_total_path, "r");
 	if (!fp) {
-		perror("Failed to open total bw file");
+		ksft_perror("Failed to open total bw file");
 
 		return -1;
 	}
 	if (fscanf(fp, "%lu", mbm_total) <= 0) {
-		perror("Could not get mbm local bytes");
+		ksft_perror("Could not get mbm local bytes");
 		fclose(fp);
 
 		return -1;
@@ -495,7 +495,7 @@ int signal_handler_register(void)
 	if (sigaction(SIGINT, &sigact, NULL) ||
 	    sigaction(SIGTERM, &sigact, NULL) ||
 	    sigaction(SIGHUP, &sigact, NULL)) {
-		perror("# sigaction");
+		ksft_perror("sigaction");
 		ret = -1;
 	}
 	return ret;
@@ -515,7 +515,7 @@ void signal_handler_unregister(void)
 	if (sigaction(SIGINT, &sigact, NULL) ||
 	    sigaction(SIGTERM, &sigact, NULL) ||
 	    sigaction(SIGHUP, &sigact, NULL)) {
-		perror("# sigaction");
+		ksft_perror("sigaction");
 	}
 }
 
@@ -526,7 +526,7 @@ void signal_handler_unregister(void)
  * @bw_imc:		perf imc counter value
  * @bw_resc:		memory bandwidth value
  *
- * Return:		0 on success. non-zero on failure.
+ * Return:		0 on success, < 0 on error.
  */
 static int print_results_bw(char *filename,  int bm_pid, float bw_imc,
 			    unsigned long bw_resc)
@@ -540,16 +540,16 @@ static int print_results_bw(char *filename,  int bm_pid, float bw_imc,
 	} else {
 		fp = fopen(filename, "a");
 		if (!fp) {
-			perror("Cannot open results file");
+			ksft_perror("Cannot open results file");
 
-			return errno;
+			return -1;
 		}
 		if (fprintf(fp, "Pid: %d \t Mem_BW_iMC: %f \t Mem_BW_resc: %lu \t Difference: %lu\n",
 			    bm_pid, bw_imc, bw_resc, diff) <= 0) {
+			ksft_print_msg("Could not log results\n");
 			fclose(fp);
-			perror("Could not log results.");
 
-			return errno;
+			return -1;
 		}
 		fclose(fp);
 	}
@@ -582,19 +582,20 @@ static void set_cmt_path(const char *ctrlgrp, const char *mongrp, char sock_num)
 static void initialize_llc_occu_resctrl(const char *ctrlgrp, const char *mongrp,
 					int cpu_no, char *resctrl_val)
 {
-	int resource_id;
+	int domain_id;
 
-	if (get_resource_id(cpu_no, &resource_id) < 0) {
-		perror("# Unable to resource_id");
+	if (get_domain_id("L3", cpu_no, &domain_id) < 0) {
+		ksft_print_msg("Could not get domain ID\n");
 		return;
 	}
 
 	if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
-		set_cmt_path(ctrlgrp, mongrp, resource_id);
+		set_cmt_path(ctrlgrp, mongrp, domain_id);
 }
 
-static int
-measure_vals(struct resctrl_val_param *param, unsigned long *bw_resc_start)
+static int measure_vals(const struct user_params *uparams,
+			struct resctrl_val_param *param,
+			unsigned long *bw_resc_start)
 {
 	unsigned long bw_resc, bw_resc_end;
 	float bw_imc;
@@ -607,7 +608,7 @@ measure_vals(struct resctrl_val_param *param, unsigned long *bw_resc_start)
 	 * Compare the two values to validate resctrl value.
 	 * It takes 1sec to measure the data.
 	 */
-	ret = get_mem_bw_imc(param->cpu_no, param->bw_report, &bw_imc);
+	ret = get_mem_bw_imc(uparams->cpu, param->bw_report, &bw_imc);
 	if (ret < 0)
 		return ret;
 
@@ -647,20 +648,24 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext)
 	 * stdio (console)
 	 */
 	fp = freopen("/dev/null", "w", stdout);
-	if (!fp)
-		PARENT_EXIT("Unable to direct benchmark status to /dev/null");
+	if (!fp) {
+		ksft_perror("Unable to direct benchmark status to /dev/null");
+		PARENT_EXIT();
+	}
 
 	if (strcmp(benchmark_cmd[0], "fill_buf") == 0) {
 		/* Execute default fill_buf benchmark */
 		span = strtoul(benchmark_cmd[1], NULL, 10);
 		memflush =  atoi(benchmark_cmd[2]);
 		operation = atoi(benchmark_cmd[3]);
-		if (!strcmp(benchmark_cmd[4], "true"))
+		if (!strcmp(benchmark_cmd[4], "true")) {
 			once = true;
-		else if (!strcmp(benchmark_cmd[4], "false"))
+		} else if (!strcmp(benchmark_cmd[4], "false")) {
 			once = false;
-		else
-			PARENT_EXIT("Invalid once parameter");
+		} else {
+			ksft_print_msg("Invalid once parameter\n");
+			PARENT_EXIT();
+		}
 
 		if (run_fill_buf(span, memflush, operation, once))
 			fprintf(stderr, "Error in running fill buffer\n");
@@ -668,22 +673,28 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext)
 		/* Execute specified benchmark */
 		ret = execvp(benchmark_cmd[0], benchmark_cmd);
 		if (ret)
-			perror("wrong\n");
+			ksft_perror("execvp");
 	}
 
 	fclose(stdout);
-	PARENT_EXIT("Unable to run specified benchmark");
+	ksft_print_msg("Unable to run specified benchmark\n");
+	PARENT_EXIT();
 }
 
 /*
  * resctrl_val:	execute benchmark and measure memory bandwidth on
  *			the benchmark
+ * @test:		test information structure
+ * @uparams:		user supplied parameters
  * @benchmark_cmd:	benchmark command and its arguments
  * @param:		parameters passed to resctrl_val()
  *
- * Return:		0 on success. non-zero on failure.
+ * Return:		0 when the test was run, < 0 on error.
  */
-int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *param)
+int resctrl_val(const struct resctrl_test *test,
+		const struct user_params *uparams,
+		const char * const *benchmark_cmd,
+		struct resctrl_val_param *param)
 {
 	char *resctrl_val = param->resctrl_val;
 	unsigned long bw_resc_start = 0;
@@ -709,7 +720,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 	ppid = getpid();
 
 	if (pipe(pipefd)) {
-		perror("# Unable to create pipe");
+		ksft_perror("Unable to create pipe");
 
 		return -1;
 	}
@@ -721,7 +732,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 	fflush(stdout);
 	bm_pid = fork();
 	if (bm_pid == -1) {
-		perror("# Unable to fork");
+		ksft_perror("Unable to fork");
 
 		return -1;
 	}
@@ -738,15 +749,17 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 		sigact.sa_flags = SA_SIGINFO;
 
 		/* Register for "SIGUSR1" signal from parent */
-		if (sigaction(SIGUSR1, &sigact, NULL))
-			PARENT_EXIT("Can't register child for signal");
+		if (sigaction(SIGUSR1, &sigact, NULL)) {
+			ksft_perror("Can't register child for signal");
+			PARENT_EXIT();
+		}
 
 		/* Tell parent that child is ready */
 		close(pipefd[0]);
 		pipe_message = 1;
 		if (write(pipefd[1], &pipe_message, sizeof(pipe_message)) <
 		    sizeof(pipe_message)) {
-			perror("# failed signaling parent process");
+			ksft_perror("Failed signaling parent process");
 			close(pipefd[1]);
 			return -1;
 		}
@@ -755,7 +768,8 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 		/* Suspend child until delivery of "SIGUSR1" from parent */
 		sigsuspend(&sigact.sa_mask);
 
-		PARENT_EXIT("Child is done");
+		ksft_perror("Child is done");
+		PARENT_EXIT();
 	}
 
 	ksft_print_msg("Benchmark PID: %d\n", bm_pid);
@@ -769,7 +783,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 	value.sival_ptr = (void *)benchmark_cmd;
 
 	/* Taskset benchmark to specified cpu */
-	ret = taskset_benchmark(bm_pid, param->cpu_no);
+	ret = taskset_benchmark(bm_pid, uparams->cpu, NULL);
 	if (ret)
 		goto out;
 
@@ -786,17 +800,17 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 			goto out;
 
 		initialize_mem_bw_resctrl(param->ctrlgrp, param->mongrp,
-					  param->cpu_no, resctrl_val);
+					  uparams->cpu, resctrl_val);
 	} else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
 		initialize_llc_occu_resctrl(param->ctrlgrp, param->mongrp,
-					    param->cpu_no, resctrl_val);
+					    uparams->cpu, resctrl_val);
 
 	/* Parent waits for child to be ready. */
 	close(pipefd[1]);
 	while (pipe_message != 1) {
 		if (read(pipefd[0], &pipe_message, sizeof(pipe_message)) <
 		    sizeof(pipe_message)) {
-			perror("# failed reading message from child process");
+			ksft_perror("Failed reading message from child process");
 			close(pipefd[0]);
 			goto out;
 		}
@@ -805,8 +819,8 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 
 	/* Signal child to start benchmark */
 	if (sigqueue(bm_pid, SIGUSR1, value) == -1) {
-		perror("# sigqueue SIGUSR1 to child");
-		ret = errno;
+		ksft_perror("sigqueue SIGUSR1 to child");
+		ret = -1;
 		goto out;
 	}
 
@@ -815,7 +829,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 
 	/* Test runs until the callback setup() tells the test to stop. */
 	while (1) {
-		ret = param->setup(param);
+		ret = param->setup(test, uparams, param);
 		if (ret == END_OF_TESTS) {
 			ret = 0;
 			break;
@@ -825,12 +839,12 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 
 		if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) ||
 		    !strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) {
-			ret = measure_vals(param, &bw_resc_start);
+			ret = measure_vals(uparams, param, &bw_resc_start);
 			if (ret)
 				break;
 		} else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) {
 			sleep(1);
-			ret = measure_cache_vals(param, bm_pid);
+			ret = measure_llc_resctrl(param->filename, bm_pid);
 			if (ret)
 				break;
 		}
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index 5ebd43683876..1cade75176eb 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -20,7 +20,7 @@ static int find_resctrl_mount(char *buffer)
 
 	mounts = fopen("/proc/mounts", "r");
 	if (!mounts) {
-		perror("/proc/mounts");
+		ksft_perror("/proc/mounts");
 		return -ENXIO;
 	}
 	while (!feof(mounts)) {
@@ -56,7 +56,7 @@ static int find_resctrl_mount(char *buffer)
  * Mounts resctrl FS. Fails if resctrl FS is already mounted to avoid
  * pre-existing settings interfering with the test results.
  *
- * Return: 0 on success, non-zero on failure
+ * Return: 0 on success, < 0 on error.
  */
 int mount_resctrlfs(void)
 {
@@ -69,7 +69,7 @@ int mount_resctrlfs(void)
 	ksft_print_msg("Mounting resctrl to \"%s\"\n", RESCTRL_PATH);
 	ret = mount("resctrl", RESCTRL_PATH, "resctrl", 0, NULL);
 	if (ret)
-		perror("# mount");
+		ksft_perror("mount");
 
 	return ret;
 }
@@ -86,41 +86,67 @@ int umount_resctrlfs(void)
 		return ret;
 
 	if (umount(mountpoint)) {
-		perror("# Unable to umount resctrl");
+		ksft_perror("Unable to umount resctrl");
 
-		return errno;
+		return -1;
 	}
 
 	return 0;
 }
 
 /*
- * get_resource_id - Get socket number/l3 id for a specified CPU
+ * get_cache_level - Convert cache level from string to integer
+ * @cache_type:		Cache level as string
+ *
+ * Return: cache level as integer or -1 if @cache_type is invalid.
+ */
+static int get_cache_level(const char *cache_type)
+{
+	if (!strcmp(cache_type, "L3"))
+		return 3;
+	if (!strcmp(cache_type, "L2"))
+		return 2;
+
+	ksft_print_msg("Invalid cache level\n");
+	return -1;
+}
+
+static int get_resource_cache_level(const char *resource)
+{
+	/* "MB" use L3 (LLC) as resource */
+	if (!strcmp(resource, "MB"))
+		return 3;
+	return get_cache_level(resource);
+}
+
+/*
+ * get_domain_id - Get resctrl domain ID for a specified CPU
+ * @resource:	resource name
  * @cpu_no:	CPU number
- * @resource_id: Socket number or l3_id
+ * @domain_id:	domain ID (cache ID; for MB, L3 cache ID)
  *
  * Return: >= 0 on success, < 0 on failure.
  */
-int get_resource_id(int cpu_no, int *resource_id)
+int get_domain_id(const char *resource, int cpu_no, int *domain_id)
 {
 	char phys_pkg_path[1024];
+	int cache_num;
 	FILE *fp;
 
-	if (get_vendor() == ARCH_AMD)
-		sprintf(phys_pkg_path, "%s%d/cache/index3/id",
-			PHYS_ID_PATH, cpu_no);
-	else
-		sprintf(phys_pkg_path, "%s%d/topology/physical_package_id",
-			PHYS_ID_PATH, cpu_no);
+	cache_num = get_resource_cache_level(resource);
+	if (cache_num < 0)
+		return cache_num;
+
+	sprintf(phys_pkg_path, "%s%d/cache/index%d/id", PHYS_ID_PATH, cpu_no, cache_num);
 
 	fp = fopen(phys_pkg_path, "r");
 	if (!fp) {
-		perror("Failed to open physical_package_id");
+		ksft_perror("Failed to open cache id file");
 
 		return -1;
 	}
-	if (fscanf(fp, "%d", resource_id) <= 0) {
-		perror("Could not get socket number or l3 id");
+	if (fscanf(fp, "%d", domain_id) <= 0) {
+		ksft_perror("Could not get domain ID");
 		fclose(fp);
 
 		return -1;
@@ -138,31 +164,26 @@ int get_resource_id(int cpu_no, int *resource_id)
  *
  * Return: = 0 on success, < 0 on failure.
  */
-int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size)
+int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size)
 {
 	char cache_path[1024], cache_str[64];
 	int length, i, cache_num;
 	FILE *fp;
 
-	if (!strcmp(cache_type, "L3")) {
-		cache_num = 3;
-	} else if (!strcmp(cache_type, "L2")) {
-		cache_num = 2;
-	} else {
-		perror("Invalid cache level");
-		return -1;
-	}
+	cache_num = get_cache_level(cache_type);
+	if (cache_num < 0)
+		return cache_num;
 
 	sprintf(cache_path, "/sys/bus/cpu/devices/cpu%d/cache/index%d/size",
 		cpu_no, cache_num);
 	fp = fopen(cache_path, "r");
 	if (!fp) {
-		perror("Failed to open cache size");
+		ksft_perror("Failed to open cache size");
 
 		return -1;
 	}
 	if (fscanf(fp, "%s", cache_str) <= 0) {
-		perror("Could not get cache_size");
+		ksft_perror("Could not get cache_size");
 		fclose(fp);
 
 		return -1;
@@ -196,30 +217,29 @@ int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size)
 #define CORE_SIBLINGS_PATH	"/sys/bus/cpu/devices/cpu"
 
 /*
- * get_cbm_mask - Get cbm mask for given cache
- * @cache_type:	Cache level L2/L3
- * @cbm_mask:	cbm_mask returned as a string
+ * get_bit_mask - Get bit mask from given file
+ * @filename:	File containing the mask
+ * @mask:	The bit mask returned as unsigned long
  *
  * Return: = 0 on success, < 0 on failure.
  */
-int get_cbm_mask(char *cache_type, char *cbm_mask)
+static int get_bit_mask(const char *filename, unsigned long *mask)
 {
-	char cbm_mask_path[1024];
 	FILE *fp;
 
-	if (!cbm_mask)
+	if (!filename || !mask)
 		return -1;
 
-	sprintf(cbm_mask_path, "%s/%s/cbm_mask", INFO_PATH, cache_type);
-
-	fp = fopen(cbm_mask_path, "r");
+	fp = fopen(filename, "r");
 	if (!fp) {
-		perror("Failed to open cache level");
-
+		ksft_print_msg("Failed to open bit mask file '%s': %s\n",
+			       filename, strerror(errno));
 		return -1;
 	}
-	if (fscanf(fp, "%s", cbm_mask) <= 0) {
-		perror("Could not get max cbm_mask");
+
+	if (fscanf(fp, "%lx", mask) <= 0) {
+		ksft_print_msg("Could not read bit mask file '%s': %s\n",
+			       filename, strerror(errno));
 		fclose(fp);
 
 		return -1;
@@ -230,64 +250,200 @@ int get_cbm_mask(char *cache_type, char *cbm_mask)
 }
 
 /*
- * get_core_sibling - Get sibling core id from the same socket for given CPU
- * @cpu_no:	CPU number
+ * resource_info_unsigned_get - Read an unsigned value from
+ * /sys/fs/resctrl/info/@resource/@filename
+ * @resource:	Resource name that matches directory name in
+ *		/sys/fs/resctrl/info
+ * @filename:	File in /sys/fs/resctrl/info/@resource
+ * @val:	Contains read value on success.
  *
- * Return:	> 0 on success, < 0 on failure.
+ * Return: = 0 on success, < 0 on failure. On success the read
+ * value is saved into @val.
  */
-int get_core_sibling(int cpu_no)
+int resource_info_unsigned_get(const char *resource, const char *filename,
+			       unsigned int *val)
 {
-	char core_siblings_path[1024], cpu_list_str[64];
-	int sibling_cpu_no = -1;
+	char file_path[PATH_MAX];
 	FILE *fp;
 
-	sprintf(core_siblings_path, "%s%d/topology/core_siblings_list",
-		CORE_SIBLINGS_PATH, cpu_no);
+	snprintf(file_path, sizeof(file_path), "%s/%s/%s", INFO_PATH, resource,
+		 filename);
 
-	fp = fopen(core_siblings_path, "r");
+	fp = fopen(file_path, "r");
 	if (!fp) {
-		perror("Failed to open core siblings path");
-
+		ksft_print_msg("Error opening %s: %m\n", file_path);
 		return -1;
 	}
-	if (fscanf(fp, "%s", cpu_list_str) <= 0) {
-		perror("Could not get core_siblings list");
-		fclose(fp);
 
+	if (fscanf(fp, "%u", val) <= 0) {
+		ksft_print_msg("Could not get contents of %s: %m\n", file_path);
+		fclose(fp);
 		return -1;
 	}
+
 	fclose(fp);
+	return 0;
+}
 
-	char *token = strtok(cpu_list_str, "-,");
+/*
+ * create_bit_mask- Create bit mask from start, len pair
+ * @start:	LSB of the mask
+ * @len		Number of bits in the mask
+ */
+unsigned long create_bit_mask(unsigned int start, unsigned int len)
+{
+	return ((1UL << len) - 1UL) << start;
+}
 
-	while (token) {
-		sibling_cpu_no = atoi(token);
-		/* Skipping core 0 as we don't want to run test on core 0 */
-		if (sibling_cpu_no != 0 && sibling_cpu_no != cpu_no)
-			break;
-		token = strtok(NULL, "-,");
+/*
+ * count_contiguous_bits - Returns the longest train of bits in a bit mask
+ * @val		A bit mask
+ * @start	The location of the least-significant bit of the longest train
+ *
+ * Return:	The length of the contiguous bits in the longest train of bits
+ */
+unsigned int count_contiguous_bits(unsigned long val, unsigned int *start)
+{
+	unsigned long last_val;
+	unsigned int count = 0;
+
+	while (val) {
+		last_val = val;
+		val &= (val >> 1);
+		count++;
+	}
+
+	if (start) {
+		if (count)
+			*start = ffsl(last_val) - 1;
+		else
+			*start = 0;
 	}
 
-	return sibling_cpu_no;
+	return count;
+}
+
+/*
+ * get_full_cbm - Get full Cache Bit Mask (CBM)
+ * @cache_type:	Cache type as "L2" or "L3"
+ * @mask:	Full cache bit mask representing the maximal portion of cache
+ *		available for allocation, returned as unsigned long.
+ *
+ * Return: = 0 on success, < 0 on failure.
+ */
+int get_full_cbm(const char *cache_type, unsigned long *mask)
+{
+	char cbm_path[PATH_MAX];
+	int ret;
+
+	if (!cache_type)
+		return -1;
+
+	snprintf(cbm_path, sizeof(cbm_path), "%s/%s/cbm_mask",
+		 INFO_PATH, cache_type);
+
+	ret = get_bit_mask(cbm_path, mask);
+	if (ret || !*mask)
+		return -1;
+
+	return 0;
+}
+
+/*
+ * get_shareable_mask - Get shareable mask from shareable_bits
+ * @cache_type:		Cache type as "L2" or "L3"
+ * @shareable_mask:	Shareable mask returned as unsigned long
+ *
+ * Return: = 0 on success, < 0 on failure.
+ */
+static int get_shareable_mask(const char *cache_type, unsigned long *shareable_mask)
+{
+	char mask_path[PATH_MAX];
+
+	if (!cache_type)
+		return -1;
+
+	snprintf(mask_path, sizeof(mask_path), "%s/%s/shareable_bits",
+		 INFO_PATH, cache_type);
+
+	return get_bit_mask(mask_path, shareable_mask);
+}
+
+/*
+ * get_mask_no_shareable - Get Cache Bit Mask (CBM) without shareable bits
+ * @cache_type:		Cache type as "L2" or "L3"
+ * @mask:		The largest exclusive portion of the cache out of the
+ *			full CBM, returned as unsigned long
+ *
+ * Parts of a cache may be shared with other devices such as GPU. This function
+ * calculates the largest exclusive portion of the cache where no other devices
+ * besides CPU have access to the cache portion.
+ *
+ * Return: = 0 on success, < 0 on failure.
+ */
+int get_mask_no_shareable(const char *cache_type, unsigned long *mask)
+{
+	unsigned long full_mask, shareable_mask;
+	unsigned int start, len;
+
+	if (get_full_cbm(cache_type, &full_mask) < 0)
+		return -1;
+	if (get_shareable_mask(cache_type, &shareable_mask) < 0)
+		return -1;
+
+	len = count_contiguous_bits(full_mask & ~shareable_mask, &start);
+	if (!len)
+		return -1;
+
+	*mask = create_bit_mask(start, len);
+
+	return 0;
 }
 
 /*
  * taskset_benchmark - Taskset PID (i.e. benchmark) to a specified cpu
- * @bm_pid:	PID that should be binded
- * @cpu_no:	CPU number at which the PID would be binded
+ * @bm_pid:		PID that should be binded
+ * @cpu_no:		CPU number at which the PID would be binded
+ * @old_affinity:	When not NULL, set to old CPU affinity
  *
- * Return: 0 on success, non-zero on failure
+ * Return: 0 on success, < 0 on error.
  */
-int taskset_benchmark(pid_t bm_pid, int cpu_no)
+int taskset_benchmark(pid_t bm_pid, int cpu_no, cpu_set_t *old_affinity)
 {
 	cpu_set_t my_set;
 
+	if (old_affinity) {
+		CPU_ZERO(old_affinity);
+		if (sched_getaffinity(bm_pid, sizeof(*old_affinity),
+				      old_affinity)) {
+			ksft_perror("Unable to read CPU affinity");
+			return -1;
+		}
+	}
+
 	CPU_ZERO(&my_set);
 	CPU_SET(cpu_no, &my_set);
 
 	if (sched_setaffinity(bm_pid, sizeof(cpu_set_t), &my_set)) {
-		perror("Unable to taskset benchmark");
+		ksft_perror("Unable to taskset benchmark");
+
+		return -1;
+	}
+
+	return 0;
+}
 
+/*
+ * taskset_restore - Taskset PID to the earlier CPU affinity
+ * @bm_pid:		PID that should be reset
+ * @old_affinity:	The old CPU affinity to restore
+ *
+ * Return: 0 on success, < 0 on error.
+ */
+int taskset_restore(pid_t bm_pid, cpu_set_t *old_affinity)
+{
+	if (sched_setaffinity(bm_pid, sizeof(*old_affinity), old_affinity)) {
+		ksft_perror("Unable to restore CPU affinity");
 		return -1;
 	}
 
@@ -300,7 +456,7 @@ int taskset_benchmark(pid_t bm_pid, int cpu_no)
  * @grp:	Full path and name of the group
  * @parent_grp:	Full path and name of the parent group
  *
- * Return: 0 on success, non-zero on failure
+ * Return: 0 on success, < 0 on error.
  */
 static int create_grp(const char *grp_name, char *grp, const char *parent_grp)
 {
@@ -325,7 +481,7 @@ static int create_grp(const char *grp_name, char *grp, const char *parent_grp)
 		}
 		closedir(dp);
 	} else {
-		perror("Unable to open resctrl for group");
+		ksft_perror("Unable to open resctrl for group");
 
 		return -1;
 	}
@@ -333,7 +489,7 @@ static int create_grp(const char *grp_name, char *grp, const char *parent_grp)
 	/* Requested grp doesn't exist, hence create it */
 	if (found_grp == 0) {
 		if (mkdir(grp, 0) == -1) {
-			perror("Unable to create group");
+			ksft_perror("Unable to create group");
 
 			return -1;
 		}
@@ -348,12 +504,12 @@ static int write_pid_to_tasks(char *tasks, pid_t pid)
 
 	fp = fopen(tasks, "w");
 	if (!fp) {
-		perror("Failed to open tasks file");
+		ksft_perror("Failed to open tasks file");
 
 		return -1;
 	}
 	if (fprintf(fp, "%d\n", pid) < 0) {
-		perror("Failed to wr pid to tasks file");
+		ksft_print_msg("Failed to write pid to tasks file\n");
 		fclose(fp);
 
 		return -1;
@@ -376,7 +532,7 @@ static int write_pid_to_tasks(char *tasks, pid_t pid)
  * pid is not written, this means that pid is in con_mon grp and hence
  * should consult con_mon grp's mon_data directory for results.
  *
- * Return: 0 on success, non-zero on failure
+ * Return: 0 on success, < 0 on error.
  */
 int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
 			    char *resctrl_val)
@@ -420,7 +576,7 @@ int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
 out:
 	ksft_print_msg("Writing benchmark parameters to resctrl FS\n");
 	if (ret)
-		perror("# writing to resctrlfs");
+		ksft_print_msg("Failed writing to resctrlfs\n");
 
 	return ret;
 }
@@ -430,23 +586,17 @@ out:
  * @ctrlgrp:		Name of the con_mon grp
  * @schemata:		Schemata that should be updated to
  * @cpu_no:		CPU number that the benchmark PID is binded to
- * @resctrl_val:	Resctrl feature (Eg: mbm, mba.. etc)
+ * @resource:		Resctrl resource (Eg: MB, L3, L2, etc.)
  *
- * Update schemata of a con_mon grp *only* if requested resctrl feature is
+ * Update schemata of a con_mon grp *only* if requested resctrl resource is
  * allocation type
  *
- * Return: 0 on success, non-zero on failure
+ * Return: 0 on success, < 0 on error.
  */
-int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val)
+int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, const char *resource)
 {
 	char controlgroup[1024], reason[128], schema[1024] = {};
-	int resource_id, fd, schema_len = -1, ret = 0;
-
-	if (strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) &&
-	    strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) &&
-	    strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR)) &&
-	    strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
-		return -ENOENT;
+	int domain_id, fd, schema_len, ret = 0;
 
 	if (!schemata) {
 		ksft_print_msg("Skipping empty schemata update\n");
@@ -454,8 +604,8 @@ int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val)
 		return -1;
 	}
 
-	if (get_resource_id(cpu_no, &resource_id) < 0) {
-		sprintf(reason, "Failed to get resource id");
+	if (get_domain_id(resource, cpu_no, &domain_id) < 0) {
+		sprintf(reason, "Failed to get domain ID");
 		ret = -1;
 
 		goto out;
@@ -466,14 +616,8 @@ int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val)
 	else
 		sprintf(controlgroup, "%s/schemata", RESCTRL_PATH);
 
-	if (!strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR)) ||
-	    !strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
-		schema_len = snprintf(schema, sizeof(schema), "%s%d%c%s\n",
-				      "L3:", resource_id, '=', schemata);
-	if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) ||
-	    !strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)))
-		schema_len = snprintf(schema, sizeof(schema), "%s%d%c%s\n",
-				      "MB:", resource_id, '=', schemata);
+	schema_len = snprintf(schema, sizeof(schema), "%s:%d=%s\n",
+			      resource, domain_id, schemata);
 	if (schema_len < 0 || schema_len >= sizeof(schema)) {
 		snprintf(reason, sizeof(reason),
 			 "snprintf() failed with return value : %d", schema_len);
@@ -564,20 +708,16 @@ char *fgrep(FILE *inf, const char *str)
 }
 
 /*
- * validate_resctrl_feature_request - Check if requested feature is valid.
- * @resource:	Required resource (e.g., MB, L3, L2, L3_MON, etc.)
- * @feature:	Required monitor feature (in mon_features file). Can only be
- *		set for L3_MON. Must be NULL for all other resources.
+ * resctrl_resource_exists - Check if a resource is supported.
+ * @resource:	Resctrl resource (e.g., MB, L3, L2, L3_MON, etc.)
  *
- * Return: True if the resource/feature is supported, else false. False is
+ * Return: True if the resource is supported, else false. False is
  *         also returned if resctrl FS is not mounted.
  */
-bool validate_resctrl_feature_request(const char *resource, const char *feature)
+bool resctrl_resource_exists(const char *resource)
 {
 	char res_path[PATH_MAX];
 	struct stat statbuf;
-	char *res;
-	FILE *inf;
 	int ret;
 
 	if (!resource)
@@ -592,8 +732,25 @@ bool validate_resctrl_feature_request(const char *resource, const char *feature)
 	if (stat(res_path, &statbuf))
 		return false;
 
-	if (!feature)
-		return true;
+	return true;
+}
+
+/*
+ * resctrl_mon_feature_exists - Check if requested monitoring feature is valid.
+ * @resource:	Resource that uses the mon_features file. Currently only L3_MON
+ *		is valid.
+ * @feature:	Required monitor feature (in mon_features file).
+ *
+ * Return: True if the feature is supported, else false.
+ */
+bool resctrl_mon_feature_exists(const char *resource, const char *feature)
+{
+	char res_path[PATH_MAX];
+	char *res;
+	FILE *inf;
+
+	if (!feature || !resource)
+		return false;
 
 	snprintf(res_path, sizeof(res_path), "%s/%s/mon_features", INFO_PATH, resource);
 	inf = fopen(res_path, "r");
@@ -607,6 +764,36 @@ bool validate_resctrl_feature_request(const char *resource, const char *feature)
 	return !!res;
 }
 
+/*
+ * resource_info_file_exists - Check if a file is present inside
+ * /sys/fs/resctrl/info/@resource.
+ * @resource:	Required resource (Eg: MB, L3, L2, etc.)
+ * @file:	Required file.
+ *
+ * Return: True if the /sys/fs/resctrl/info/@resource/@file exists, else false.
+ */
+bool resource_info_file_exists(const char *resource, const char *file)
+{
+	char res_path[PATH_MAX];
+	struct stat statbuf;
+
+	if (!file || !resource)
+		return false;
+
+	snprintf(res_path, sizeof(res_path), "%s/%s/%s", INFO_PATH, resource,
+		 file);
+
+	if (stat(res_path, &statbuf))
+		return false;
+
+	return true;
+}
+
+bool test_resource_feature_check(const struct resctrl_test *test)
+{
+	return resctrl_resource_exists(test->resource);
+}
+
 int filter_dmesg(void)
 {
 	char line[1024];
@@ -617,7 +804,7 @@ int filter_dmesg(void)
 
 	ret = pipe(pipefds);
 	if (ret) {
-		perror("pipe");
+		ksft_perror("pipe");
 		return ret;
 	}
 	fflush(stdout);
@@ -626,13 +813,13 @@ int filter_dmesg(void)
 		close(pipefds[0]);
 		dup2(pipefds[1], STDOUT_FILENO);
 		execlp("dmesg", "dmesg", NULL);
-		perror("executing dmesg");
+		ksft_perror("Executing dmesg");
 		exit(1);
 	}
 	close(pipefds[1]);
 	fp = fdopen(pipefds[0], "r");
 	if (!fp) {
-		perror("fdopen(pipe)");
+		ksft_perror("fdopen(pipe)");
 		kill(pid, SIGTERM);
 
 		return -1;
diff --git a/tools/testing/selftests/riscv/hwprobe/Makefile b/tools/testing/selftests/riscv/hwprobe/Makefile
index f224b84591fb..cec81610a5f2 100644
--- a/tools/testing/selftests/riscv/hwprobe/Makefile
+++ b/tools/testing/selftests/riscv/hwprobe/Makefile
@@ -4,7 +4,7 @@
 
 CFLAGS += -I$(top_srcdir)/tools/include
 
-TEST_GEN_PROGS := hwprobe cbo
+TEST_GEN_PROGS := hwprobe cbo which-cpus
 
 include ../../lib.mk
 
@@ -13,3 +13,6 @@ $(OUTPUT)/hwprobe: hwprobe.c sys_hwprobe.S
 
 $(OUTPUT)/cbo: cbo.c sys_hwprobe.S
 	$(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^
+
+$(OUTPUT)/which-cpus: which-cpus.c sys_hwprobe.S
+	$(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^
diff --git a/tools/testing/selftests/riscv/hwprobe/cbo.c b/tools/testing/selftests/riscv/hwprobe/cbo.c
index 50a2cc8aef38..c537d52fafc5 100644
--- a/tools/testing/selftests/riscv/hwprobe/cbo.c
+++ b/tools/testing/selftests/riscv/hwprobe/cbo.c
@@ -36,16 +36,14 @@ static void sigill_handler(int sig, siginfo_t *info, void *context)
 	regs[0] += 4;
 }
 
-static void cbo_insn(char *base, int fn)
-{
-	uint32_t insn = MK_CBO(fn);
-
-	asm volatile(
-	"mv	a0, %0\n"
-	"li	a1, %1\n"
-	".4byte	%2\n"
-	: : "r" (base), "i" (fn), "i" (insn) : "a0", "a1", "memory");
-}
+#define cbo_insn(base, fn)							\
+({										\
+	asm volatile(								\
+	"mv	a0, %0\n"							\
+	"li	a1, %1\n"							\
+	".4byte	%2\n"								\
+	: : "r" (base), "i" (fn), "i" (MK_CBO(fn)) : "a0", "a1", "memory");	\
+})
 
 static void cbo_inval(char *base) { cbo_insn(base, 0); }
 static void cbo_clean(char *base) { cbo_insn(base, 1); }
@@ -97,7 +95,7 @@ static void test_zicboz(void *arg)
 	block_size = pair.value;
 	ksft_test_result(rc == 0 && pair.key == RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE &&
 			 is_power_of_2(block_size), "Zicboz block size\n");
-	ksft_print_msg("Zicboz block size: %ld\n", block_size);
+	ksft_print_msg("Zicboz block size: %llu\n", block_size);
 
 	illegal_insn = false;
 	cbo_zero(&mem[block_size]);
@@ -121,7 +119,7 @@ static void test_zicboz(void *arg)
 		for (j = 0; j < block_size; ++j) {
 			if (mem[i * block_size + j] != expected) {
 				ksft_test_result_fail("cbo.zero check\n");
-				ksft_print_msg("cbo.zero check: mem[%d] != 0x%x\n",
+				ksft_print_msg("cbo.zero check: mem[%llu] != 0x%x\n",
 					       i * block_size + j, expected);
 				return;
 			}
@@ -201,7 +199,7 @@ int main(int argc, char **argv)
 	pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0;
 	rc = riscv_hwprobe(&pair, 1, sizeof(cpu_set_t), (unsigned long *)&cpus, 0);
 	if (rc < 0)
-		ksft_exit_fail_msg("hwprobe() failed with %d\n", rc);
+		ksft_exit_fail_msg("hwprobe() failed with %ld\n", rc);
 	assert(rc == 0 && pair.key == RISCV_HWPROBE_KEY_IMA_EXT_0);
 
 	if (pair.value & RISCV_HWPROBE_EXT_ZICBOZ) {
diff --git a/tools/testing/selftests/riscv/hwprobe/hwprobe.c b/tools/testing/selftests/riscv/hwprobe/hwprobe.c
index c474891df307..fd73c87804f3 100644
--- a/tools/testing/selftests/riscv/hwprobe/hwprobe.c
+++ b/tools/testing/selftests/riscv/hwprobe/hwprobe.c
@@ -29,7 +29,7 @@ int main(int argc, char **argv)
 		/* Fail if the kernel claims not to recognize a base key. */
 		if ((i < 4) && (pairs[i].key != i))
 			ksft_exit_fail_msg("Failed to recognize base key: key != i, "
-					   "key=%ld, i=%ld\n", pairs[i].key, i);
+					   "key=%lld, i=%ld\n", pairs[i].key, i);
 
 		if (pairs[i].key != RISCV_HWPROBE_KEY_BASE_BEHAVIOR)
 			continue;
@@ -37,7 +37,7 @@ int main(int argc, char **argv)
 		if (pairs[i].value & RISCV_HWPROBE_BASE_BEHAVIOR_IMA)
 			continue;
 
-		ksft_exit_fail_msg("Unexpected pair: (%ld, %ld)\n", pairs[i].key, pairs[i].value);
+		ksft_exit_fail_msg("Unexpected pair: (%lld, %llu)\n", pairs[i].key, pairs[i].value);
 	}
 
 	out = riscv_hwprobe(pairs, 8, 0, 0, 0);
@@ -47,7 +47,7 @@ int main(int argc, char **argv)
 	ksft_test_result(out != 0, "Bad CPU set\n");
 
 	out = riscv_hwprobe(pairs, 8, 1, 0, 0);
-	ksft_test_result(out != 0, "NULL CPU set with non-zero count\n");
+	ksft_test_result(out != 0, "NULL CPU set with non-zero size\n");
 
 	pairs[0].key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR;
 	out = riscv_hwprobe(pairs, 1, 1, &cpus, 0);
diff --git a/tools/testing/selftests/riscv/hwprobe/hwprobe.h b/tools/testing/selftests/riscv/hwprobe/hwprobe.h
index 721b0ce73a56..e3fccb390c4d 100644
--- a/tools/testing/selftests/riscv/hwprobe/hwprobe.h
+++ b/tools/testing/selftests/riscv/hwprobe/hwprobe.h
@@ -10,6 +10,6 @@
  * contain the call.
  */
 long riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-		   size_t cpu_count, unsigned long *cpus, unsigned int flags);
+		   size_t cpusetsize, unsigned long *cpus, unsigned int flags);
 
 #endif
diff --git a/tools/testing/selftests/riscv/hwprobe/which-cpus.c b/tools/testing/selftests/riscv/hwprobe/which-cpus.c
new file mode 100644
index 000000000000..82c121412dfc
--- /dev/null
+++ b/tools/testing/selftests/riscv/hwprobe/which-cpus.c
@@ -0,0 +1,154 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023 Ventana Micro Systems Inc.
+ *
+ * Test the RISCV_HWPROBE_WHICH_CPUS flag of hwprobe. Also provides a command
+ * line interface to get the cpu list for arbitrary hwprobe pairs.
+ */
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sched.h>
+#include <unistd.h>
+#include <assert.h>
+
+#include "hwprobe.h"
+#include "../../kselftest.h"
+
+static void help(void)
+{
+	printf("\n"
+	       "which-cpus: [-h] [<key=value> [<key=value> ...]]\n\n"
+	       "   Without parameters, tests the RISCV_HWPROBE_WHICH_CPUS flag of hwprobe.\n"
+	       "   With parameters, where each parameter is a hwprobe pair written as\n"
+	       "   <key=value>, outputs the cpulist for cpus which all match the given set\n"
+	       "   of pairs.  'key' and 'value' should be in numeric form, e.g. 4=0x3b\n");
+}
+
+static void print_cpulist(cpu_set_t *cpus)
+{
+	int start = 0, end = 0;
+
+	if (!CPU_COUNT(cpus)) {
+		printf("cpus: None\n");
+		return;
+	}
+
+	printf("cpus:");
+	for (int i = 0, c = 0; i < CPU_COUNT(cpus); i++, c++) {
+		if (start != end && !CPU_ISSET(c, cpus))
+			printf("-%d", end);
+
+		while (!CPU_ISSET(c, cpus))
+			++c;
+
+		if (i != 0 && c == end + 1) {
+			end = c;
+			continue;
+		}
+
+		printf("%c%d", i == 0 ? ' ' : ',', c);
+		start = end = c;
+	}
+	if (start != end)
+		printf("-%d", end);
+	printf("\n");
+}
+
+static void do_which_cpus(int argc, char **argv, cpu_set_t *cpus)
+{
+	struct riscv_hwprobe *pairs;
+	int nr_pairs = argc - 1;
+	char *start, *end;
+	int rc;
+
+	pairs = malloc(nr_pairs * sizeof(struct riscv_hwprobe));
+	assert(pairs);
+
+	for (int i = 0; i < nr_pairs; i++) {
+		start = argv[i + 1];
+		pairs[i].key = strtol(start, &end, 0);
+		assert(end != start && *end == '=');
+		start = end + 1;
+		pairs[i].value = strtoul(start, &end, 0);
+		assert(end != start && *end == '\0');
+	}
+
+	rc = riscv_hwprobe(pairs, nr_pairs, sizeof(cpu_set_t), (unsigned long *)cpus, RISCV_HWPROBE_WHICH_CPUS);
+	assert(rc == 0);
+	print_cpulist(cpus);
+	free(pairs);
+}
+
+int main(int argc, char **argv)
+{
+	struct riscv_hwprobe pairs[2];
+	cpu_set_t cpus_aff, cpus;
+	__u64 ext0_all;
+	long rc;
+
+	rc = sched_getaffinity(0, sizeof(cpu_set_t), &cpus_aff);
+	assert(rc == 0);
+
+	if (argc > 1) {
+		if (!strcmp(argv[1], "-h"))
+			help();
+		else
+			do_which_cpus(argc, argv, &cpus_aff);
+		return 0;
+	}
+
+	ksft_print_header();
+	ksft_set_plan(7);
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, };
+	rc = riscv_hwprobe(pairs, 1, 0, NULL, 0);
+	assert(rc == 0 && pairs[0].key == RISCV_HWPROBE_KEY_BASE_BEHAVIOR &&
+	       pairs[0].value == RISCV_HWPROBE_BASE_BEHAVIOR_IMA);
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_IMA_EXT_0, };
+	rc = riscv_hwprobe(pairs, 1, 0, NULL, 0);
+	assert(rc == 0 && pairs[0].key == RISCV_HWPROBE_KEY_IMA_EXT_0);
+	ext0_all = pairs[0].value;
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	CPU_ZERO(&cpus);
+	rc = riscv_hwprobe(pairs, 1, 0, (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == -EINVAL, "no cpusetsize\n");
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	rc = riscv_hwprobe(pairs, 1, sizeof(cpu_set_t), NULL, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == -EINVAL, "NULL cpus\n");
+
+	pairs[0] = (struct riscv_hwprobe){ .key = 0xbadc0de, };
+	CPU_ZERO(&cpus);
+	rc = riscv_hwprobe(pairs, 1, sizeof(cpu_set_t), (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == 0 && CPU_COUNT(&cpus) == 0, "unknown key\n");
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	pairs[1] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	CPU_ZERO(&cpus);
+	rc = riscv_hwprobe(pairs, 2, sizeof(cpu_set_t), (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == 0, "duplicate keys\n");
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	pairs[1] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_IMA_EXT_0, .value = ext0_all, };
+	CPU_ZERO(&cpus);
+	rc = riscv_hwprobe(pairs, 2, sizeof(cpu_set_t), (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == 0 && CPU_COUNT(&cpus) == sysconf(_SC_NPROCESSORS_ONLN), "set all cpus\n");
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	pairs[1] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_IMA_EXT_0, .value = ext0_all, };
+	memcpy(&cpus, &cpus_aff, sizeof(cpu_set_t));
+	rc = riscv_hwprobe(pairs, 2, sizeof(cpu_set_t), (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == 0 && CPU_EQUAL(&cpus, &cpus_aff), "set all affinity cpus\n");
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	pairs[1] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_IMA_EXT_0, .value = ~ext0_all, };
+	memcpy(&cpus, &cpus_aff, sizeof(cpu_set_t));
+	rc = riscv_hwprobe(pairs, 2, sizeof(cpu_set_t), (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == 0 && CPU_COUNT(&cpus) == 0, "clear all cpus\n");
+
+	ksft_finished();
+}
diff --git a/tools/testing/selftests/riscv/mm/mmap_test.h b/tools/testing/selftests/riscv/mm/mmap_test.h
index 9b8434f62f57..2e0db9c5be6c 100644
--- a/tools/testing/selftests/riscv/mm/mmap_test.h
+++ b/tools/testing/selftests/riscv/mm/mmap_test.h
@@ -18,6 +18,8 @@ struct addresses {
 	int *on_56_addr;
 };
 
+// Only works on 64 bit
+#if __riscv_xlen == 64
 static inline void do_mmaps(struct addresses *mmap_addresses)
 {
 	/*
@@ -50,6 +52,7 @@ static inline void do_mmaps(struct addresses *mmap_addresses)
 	mmap_addresses->on_56_addr =
 		mmap(on_56_bits, 5 * sizeof(int), prot, flags, 0, 0);
 }
+#endif /* __riscv_xlen == 64 */
 
 static inline int memory_layout(void)
 {
diff --git a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c
index 66764edb0d52..1dd94197da30 100644
--- a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c
+++ b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c
@@ -27,7 +27,7 @@ int main(void)
 
 	datap = malloc(MAX_VSIZE);
 	if (!datap) {
-		ksft_test_result_fail("fail to allocate memory for size = %lu\n", MAX_VSIZE);
+		ksft_test_result_fail("fail to allocate memory for size = %d\n", MAX_VSIZE);
 		exit(-1);
 	}
 
diff --git a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c
index 2c0d2b1126c1..1f9969bed235 100644
--- a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c
+++ b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c
@@ -1,4 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/wait.h>
+
 #define THIS_PROGRAM "./vstate_exec_nolibc"
 
 int main(int argc, char **argv)
diff --git a/tools/testing/selftests/riscv/vector/vstate_prctl.c b/tools/testing/selftests/riscv/vector/vstate_prctl.c
index b348b475be57..27668fb3b6d0 100644
--- a/tools/testing/selftests/riscv/vector/vstate_prctl.c
+++ b/tools/testing/selftests/riscv/vector/vstate_prctl.c
@@ -1,20 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #include <sys/prctl.h>
 #include <unistd.h>
-#include <asm/hwprobe.h>
 #include <errno.h>
 #include <sys/wait.h>
 
+#include "../hwprobe/hwprobe.h"
 #include "../../kselftest.h"
 
-/*
- * Rather than relying on having a new enough libc to define this, just do it
- * ourselves.  This way we don't need to be coupled to a new-enough libc to
- * contain the call.
- */
-long riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-		   size_t cpu_count, unsigned long *cpus, unsigned int flags);
-
 #define NEXT_PROGRAM "./vstate_exec_nolibc"
 static int launch_test(int test_inherit)
 {
@@ -68,7 +60,7 @@ int test_and_compare_child(long provided, long expected, int inherit)
 	}
 	rc = launch_test(inherit);
 	if (rc != expected) {
-		ksft_test_result_fail("Test failed, check %d != %d\n", rc,
+		ksft_test_result_fail("Test failed, check %d != %ld\n", rc,
 				      expected);
 		return -2;
 	}
@@ -87,7 +79,7 @@ int main(void)
 	pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0;
 	rc = riscv_hwprobe(&pair, 1, 0, NULL, 0);
 	if (rc < 0) {
-		ksft_test_result_fail("hwprobe() failed with %d\n", rc);
+		ksft_test_result_fail("hwprobe() failed with %ld\n", rc);
 		return -1;
 	}
 
diff --git a/tools/testing/selftests/rseq/basic_percpu_ops_test.c b/tools/testing/selftests/rseq/basic_percpu_ops_test.c
index 887542961968..2348d2c20d0a 100644
--- a/tools/testing/selftests/rseq/basic_percpu_ops_test.c
+++ b/tools/testing/selftests/rseq/basic_percpu_ops_test.c
@@ -24,6 +24,11 @@ bool rseq_validate_cpu_id(void)
 {
 	return rseq_mm_cid_available();
 }
+static
+bool rseq_use_cpu_index(void)
+{
+	return false;	/* Use mm_cid */
+}
 #else
 # define RSEQ_PERCPU	RSEQ_PERCPU_CPU_ID
 static
@@ -36,6 +41,11 @@ bool rseq_validate_cpu_id(void)
 {
 	return rseq_current_cpu_raw() >= 0;
 }
+static
+bool rseq_use_cpu_index(void)
+{
+	return true;	/* Use cpu_id as index. */
+}
 #endif
 
 struct percpu_lock_entry {
@@ -274,7 +284,7 @@ void test_percpu_list(void)
 	/* Generate list entries for every usable cpu. */
 	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
 	for (i = 0; i < CPU_SETSIZE; i++) {
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 		for (j = 1; j <= 100; j++) {
 			struct percpu_list_node *node;
@@ -299,7 +309,7 @@ void test_percpu_list(void)
 	for (i = 0; i < CPU_SETSIZE; i++) {
 		struct percpu_list_node *node;
 
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 
 		while ((node = __percpu_list_pop(&list, i))) {
diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index 20403d58345c..2f37961240ca 100644
--- a/tools/testing/selftests/rseq/param_test.c
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -288,6 +288,11 @@ bool rseq_validate_cpu_id(void)
 {
 	return rseq_mm_cid_available();
 }
+static
+bool rseq_use_cpu_index(void)
+{
+	return false;	/* Use mm_cid */
+}
 # ifdef TEST_MEMBARRIER
 /*
  * Membarrier does not currently support targeting a mm_cid, so
@@ -312,6 +317,11 @@ bool rseq_validate_cpu_id(void)
 {
 	return rseq_current_cpu_raw() >= 0;
 }
+static
+bool rseq_use_cpu_index(void)
+{
+	return true;	/* Use cpu_id as index. */
+}
 # ifdef TEST_MEMBARRIER
 static
 int rseq_membarrier_expedited(int cpu)
@@ -715,7 +725,7 @@ void test_percpu_list(void)
 	/* Generate list entries for every usable cpu. */
 	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
 	for (i = 0; i < CPU_SETSIZE; i++) {
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 		for (j = 1; j <= 100; j++) {
 			struct percpu_list_node *node;
@@ -752,7 +762,7 @@ void test_percpu_list(void)
 	for (i = 0; i < CPU_SETSIZE; i++) {
 		struct percpu_list_node *node;
 
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 
 		while ((node = __percpu_list_pop(&list, i))) {
@@ -902,7 +912,7 @@ void test_percpu_buffer(void)
 	/* Generate list entries for every usable cpu. */
 	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
 	for (i = 0; i < CPU_SETSIZE; i++) {
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 		/* Worse-case is every item in same CPU. */
 		buffer.c[i].array =
@@ -952,7 +962,7 @@ void test_percpu_buffer(void)
 	for (i = 0; i < CPU_SETSIZE; i++) {
 		struct percpu_buffer_node *node;
 
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 
 		while ((node = __percpu_buffer_pop(&buffer, i))) {
@@ -1113,7 +1123,7 @@ void test_percpu_memcpy_buffer(void)
 	/* Generate list entries for every usable cpu. */
 	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
 	for (i = 0; i < CPU_SETSIZE; i++) {
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 		/* Worse-case is every item in same CPU. */
 		buffer.c[i].array =
@@ -1160,7 +1170,7 @@ void test_percpu_memcpy_buffer(void)
 	for (i = 0; i < CPU_SETSIZE; i++) {
 		struct percpu_memcpy_buffer_node item;
 
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 
 		while (__percpu_memcpy_buffer_pop(&buffer, &item, i)) {
diff --git a/tools/testing/selftests/rust/Makefile b/tools/testing/selftests/rust/Makefile
new file mode 100644
index 000000000000..fce1584d3bc0
--- /dev/null
+++ b/tools/testing/selftests/rust/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+TEST_PROGS += test_probe_samples.sh
+
+include ../lib.mk
diff --git a/tools/testing/selftests/rust/config b/tools/testing/selftests/rust/config
new file mode 100644
index 000000000000..b4002acd40bc
--- /dev/null
+++ b/tools/testing/selftests/rust/config
@@ -0,0 +1,5 @@
+CONFIG_RUST=y
+CONFIG_SAMPLES=y
+CONFIG_SAMPLES_RUST=y
+CONFIG_SAMPLE_RUST_MINIMAL=m
+CONFIG_SAMPLE_RUST_PRINT=m
\ No newline at end of file
diff --git a/tools/testing/selftests/rust/test_probe_samples.sh b/tools/testing/selftests/rust/test_probe_samples.sh
new file mode 100755
index 000000000000..ad0397e4986f
--- /dev/null
+++ b/tools/testing/selftests/rust/test_probe_samples.sh
@@ -0,0 +1,41 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2023 Collabora Ltd
+#
+# This script tests whether the rust sample modules can
+# be added and removed correctly.
+#
+DIR="$(dirname "$(readlink -f "$0")")"
+
+KTAP_HELPERS="${DIR}/../kselftest/ktap_helpers.sh"
+if [ -e "$KTAP_HELPERS" ]; then
+    source "$KTAP_HELPERS"
+else
+    echo "$KTAP_HELPERS file not found [SKIP]"
+    exit 4
+fi
+
+rust_sample_modules=("rust_minimal" "rust_print")
+
+ktap_print_header
+
+for sample in "${rust_sample_modules[@]}"; do
+    if ! /sbin/modprobe -n -q "$sample"; then
+        ktap_skip_all "module $sample is not found in /lib/modules/$(uname -r)"
+        exit "$KSFT_SKIP"
+    fi
+done
+
+ktap_set_plan "${#rust_sample_modules[@]}"
+
+for sample in "${rust_sample_modules[@]}"; do
+    if /sbin/modprobe -q "$sample"; then
+        /sbin/modprobe -q -r "$sample"
+        ktap_test_pass "$sample"
+    else
+        ktap_test_fail "$sample"
+    fi
+done
+
+ktap_finished
diff --git a/tools/testing/selftests/sched/cs_prctl_test.c b/tools/testing/selftests/sched/cs_prctl_test.c
index 7ba057154343..62fba7356af2 100644
--- a/tools/testing/selftests/sched/cs_prctl_test.c
+++ b/tools/testing/selftests/sched/cs_prctl_test.c
@@ -276,7 +276,7 @@ int main(int argc, char *argv[])
 	if (setpgid(0, 0) != 0)
 		handle_error("process group");
 
-	printf("\n## Create a thread/process/process group hiearchy\n");
+	printf("\n## Create a thread/process/process group hierarchy\n");
 	create_processes(num_processes, num_threads, procs);
 	need_cleanup = 1;
 	disp_processes(num_processes, procs);
diff --git a/tools/testing/selftests/seccomp/seccomp_benchmark.c b/tools/testing/selftests/seccomp/seccomp_benchmark.c
index 5b5c9d558dee..97b86980b768 100644
--- a/tools/testing/selftests/seccomp/seccomp_benchmark.c
+++ b/tools/testing/selftests/seccomp/seccomp_benchmark.c
@@ -38,10 +38,10 @@ unsigned long long timing(clockid_t clk_id, unsigned long long samples)
 	i *= 1000000000ULL;
 	i += finish.tv_nsec - start.tv_nsec;
 
-	printf("%lu.%09lu - %lu.%09lu = %llu (%.1fs)\n",
-		finish.tv_sec, finish.tv_nsec,
-		start.tv_sec, start.tv_nsec,
-		i, (double)i / 1000000000.0);
+	ksft_print_msg("%lu.%09lu - %lu.%09lu = %llu (%.1fs)\n",
+		       finish.tv_sec, finish.tv_nsec,
+		       start.tv_sec, start.tv_nsec,
+		       i, (double)i / 1000000000.0);
 
 	return i;
 }
@@ -53,7 +53,7 @@ unsigned long long calibrate(void)
 	pid_t pid, ret;
 	int seconds = 15;
 
-	printf("Calibrating sample size for %d seconds worth of syscalls ...\n", seconds);
+	ksft_print_msg("Calibrating sample size for %d seconds worth of syscalls ...\n", seconds);
 
 	samples = 0;
 	pid = getpid();
@@ -98,24 +98,36 @@ bool le(int i_one, int i_two)
 }
 
 long compare(const char *name_one, const char *name_eval, const char *name_two,
-	     unsigned long long one, bool (*eval)(int, int), unsigned long long two)
+	     unsigned long long one, bool (*eval)(int, int), unsigned long long two,
+	     bool skip)
 {
 	bool good;
 
-	printf("\t%s %s %s (%lld %s %lld): ", name_one, name_eval, name_two,
-	       (long long)one, name_eval, (long long)two);
+	if (skip) {
+		ksft_test_result_skip("%s %s %s\n", name_one, name_eval,
+				      name_two);
+		return 0;
+	}
+
+	ksft_print_msg("\t%s %s %s (%lld %s %lld): ", name_one, name_eval, name_two,
+		       (long long)one, name_eval, (long long)two);
 	if (one > INT_MAX) {
-		printf("Miscalculation! Measurement went negative: %lld\n", (long long)one);
-		return 1;
+		ksft_print_msg("Miscalculation! Measurement went negative: %lld\n", (long long)one);
+		good = false;
+		goto out;
 	}
 	if (two > INT_MAX) {
-		printf("Miscalculation! Measurement went negative: %lld\n", (long long)two);
-		return 1;
+		ksft_print_msg("Miscalculation! Measurement went negative: %lld\n", (long long)two);
+		good = false;
+		goto out;
 	}
 
 	good = eval(one, two);
 	printf("%s\n", good ? "✔️" : "❌");
 
+out:
+	ksft_test_result(good, "%s %s %s\n", name_one, name_eval, name_two);
+
 	return good ? 0 : 1;
 }
 
@@ -142,15 +154,22 @@ int main(int argc, char *argv[])
 	unsigned long long samples, calc;
 	unsigned long long native, filter1, filter2, bitmap1, bitmap2;
 	unsigned long long entry, per_filter1, per_filter2;
+	bool skip = false;
 
 	setbuf(stdout, NULL);
 
-	printf("Running on:\n");
+	ksft_print_header();
+	ksft_set_plan(7);
+
+	ksft_print_msg("Running on:\n");
+	ksft_print_msg("");
 	system("uname -a");
 
-	printf("Current BPF sysctl settings:\n");
+	ksft_print_msg("Current BPF sysctl settings:\n");
 	/* Avoid using "sysctl" which may not be installed. */
+	ksft_print_msg("");
 	system("grep -H . /proc/sys/net/core/bpf_jit_enable");
+	ksft_print_msg("");
 	system("grep -H . /proc/sys/net/core/bpf_jit_harden");
 
 	if (argc > 1)
@@ -158,11 +177,11 @@ int main(int argc, char *argv[])
 	else
 		samples = calibrate();
 
-	printf("Benchmarking %llu syscalls...\n", samples);
+	ksft_print_msg("Benchmarking %llu syscalls...\n", samples);
 
 	/* Native call */
 	native = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
-	printf("getpid native: %llu ns\n", native);
+	ksft_print_msg("getpid native: %llu ns\n", native);
 
 	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
 	assert(ret == 0);
@@ -172,35 +191,37 @@ int main(int argc, char *argv[])
 	assert(ret == 0);
 
 	bitmap1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
-	printf("getpid RET_ALLOW 1 filter (bitmap): %llu ns\n", bitmap1);
+	ksft_print_msg("getpid RET_ALLOW 1 filter (bitmap): %llu ns\n", bitmap1);
 
 	/* Second filter resulting in a bitmap */
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &bitmap_prog);
 	assert(ret == 0);
 
 	bitmap2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
-	printf("getpid RET_ALLOW 2 filters (bitmap): %llu ns\n", bitmap2);
+	ksft_print_msg("getpid RET_ALLOW 2 filters (bitmap): %llu ns\n", bitmap2);
 
 	/* Third filter, can no longer be converted to bitmap */
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
 	assert(ret == 0);
 
 	filter1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
-	printf("getpid RET_ALLOW 3 filters (full): %llu ns\n", filter1);
+	ksft_print_msg("getpid RET_ALLOW 3 filters (full): %llu ns\n", filter1);
 
 	/* Fourth filter, can not be converted to bitmap because of filter 3 */
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &bitmap_prog);
 	assert(ret == 0);
 
 	filter2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
-	printf("getpid RET_ALLOW 4 filters (full): %llu ns\n", filter2);
+	ksft_print_msg("getpid RET_ALLOW 4 filters (full): %llu ns\n", filter2);
 
 	/* Estimations */
 #define ESTIMATE(fmt, var, what)	do {			\
 		var = (what);					\
-		printf("Estimated " fmt ": %llu ns\n", var);	\
-		if (var > INT_MAX)				\
-			goto more_samples;			\
+		ksft_print_msg("Estimated " fmt ": %llu ns\n", var);	\
+		if (var > INT_MAX) {				\
+			skip = true;				\
+			ret |= 1;				\
+		}						\
 	} while (0)
 
 	ESTIMATE("total seccomp overhead for 1 bitmapped filter", calc,
@@ -218,31 +239,34 @@ int main(int argc, char *argv[])
 	ESTIMATE("seccomp per-filter overhead (filters / 4)", per_filter2,
 		 (filter2 - native - entry) / 4);
 
-	printf("Expectations:\n");
-	ret |= compare("native", "≤", "1 bitmap", native, le, bitmap1);
-	bits = compare("native", "≤", "1 filter", native, le, filter1);
+	ksft_print_msg("Expectations:\n");
+	ret |= compare("native", "≤", "1 bitmap", native, le, bitmap1,
+		       skip);
+	bits = compare("native", "≤", "1 filter", native, le, filter1,
+		       skip);
 	if (bits)
-		goto more_samples;
+		skip = true;
 
 	ret |= compare("per-filter (last 2 diff)", "≈", "per-filter (filters / 4)",
-			per_filter1, approx, per_filter2);
+		       per_filter1, approx, per_filter2, skip);
 
 	bits = compare("1 bitmapped", "≈", "2 bitmapped",
-			bitmap1 - native, approx, bitmap2 - native);
+		       bitmap1 - native, approx, bitmap2 - native, skip);
 	if (bits) {
-		printf("Skipping constant action bitmap expectations: they appear unsupported.\n");
-		goto out;
+		ksft_print_msg("Skipping constant action bitmap expectations: they appear unsupported.\n");
+		skip = true;
 	}
 
-	ret |= compare("entry", "≈", "1 bitmapped", entry, approx, bitmap1 - native);
-	ret |= compare("entry", "≈", "2 bitmapped", entry, approx, bitmap2 - native);
+	ret |= compare("entry", "≈", "1 bitmapped", entry, approx,
+		       bitmap1 - native, skip);
+	ret |= compare("entry", "≈", "2 bitmapped", entry, approx,
+		       bitmap2 - native, skip);
 	ret |= compare("native + entry + (per filter * 4)", "≈", "4 filters total",
-			entry + (per_filter1 * 4) + native, approx, filter2);
-	if (ret == 0)
-		goto out;
+		       entry + (per_filter1 * 4) + native, approx, filter2,
+		       skip);
 
-more_samples:
-	printf("Saw unexpected benchmark result. Try running again with more samples?\n");
-out:
-	return 0;
+	if (ret)
+		ksft_print_msg("Saw unexpected benchmark result. Try running again with more samples?\n");
+
+	ksft_finished();
 }
diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile
index 50aab6b57da3..867f88ce2570 100644
--- a/tools/testing/selftests/sgx/Makefile
+++ b/tools/testing/selftests/sgx/Makefile
@@ -12,14 +12,16 @@ OBJCOPY := $(CROSS_COMPILE)objcopy
 endif
 
 INCLUDES := -I$(top_srcdir)/tools/include
-HOST_CFLAGS := -Wall -Werror -g $(INCLUDES) -fPIC -z noexecstack
-ENCL_CFLAGS := -Wall -Werror -static -nostdlib -nostartfiles -fPIC \
+HOST_CFLAGS := -Wall -Werror -g $(INCLUDES) -fPIC
+HOST_LDFLAGS := -z noexecstack -lcrypto
+ENCL_CFLAGS += -Wall -Werror -static-pie -nostdlib -ffreestanding -fPIE \
 	       -fno-stack-protector -mrdrnd $(INCLUDES)
+ENCL_LDFLAGS := -Wl,-T,test_encl.lds,--build-id=none
 
+ifeq ($(CAN_BUILD_X86_64), 1)
 TEST_CUSTOM_PROGS := $(OUTPUT)/test_sgx
 TEST_FILES := $(OUTPUT)/test_encl.elf
 
-ifeq ($(CAN_BUILD_X86_64), 1)
 all: $(TEST_CUSTOM_PROGS) $(OUTPUT)/test_encl.elf
 endif
 
@@ -28,7 +30,7 @@ $(OUTPUT)/test_sgx: $(OUTPUT)/main.o \
 		    $(OUTPUT)/sigstruct.o \
 		    $(OUTPUT)/call.o \
 		    $(OUTPUT)/sign_key.o
-	$(CC) $(HOST_CFLAGS) -o $@ $^ -lcrypto
+	$(CC) $(HOST_CFLAGS) -o $@ $^ $(HOST_LDFLAGS)
 
 $(OUTPUT)/main.o: main.c
 	$(CC) $(HOST_CFLAGS) -c $< -o $@
@@ -45,8 +47,8 @@ $(OUTPUT)/call.o: call.S
 $(OUTPUT)/sign_key.o: sign_key.S
 	$(CC) $(HOST_CFLAGS) -c $< -o $@
 
-$(OUTPUT)/test_encl.elf: test_encl.lds test_encl.c test_encl_bootstrap.S
-	$(CC) $(ENCL_CFLAGS) -T $^ -o $@ -Wl,--build-id=none
+$(OUTPUT)/test_encl.elf: test_encl.c test_encl_bootstrap.S
+	$(CC) $(ENCL_CFLAGS) $^ -o $@ $(ENCL_LDFLAGS)
 
 EXTRA_CLEAN := \
 	$(OUTPUT)/test_encl.elf \
diff --git a/tools/testing/selftests/sgx/defines.h b/tools/testing/selftests/sgx/defines.h
index d8587c971941..402f8787a71c 100644
--- a/tools/testing/selftests/sgx/defines.h
+++ b/tools/testing/selftests/sgx/defines.h
@@ -13,6 +13,8 @@
 
 #define __aligned(x) __attribute__((__aligned__(x)))
 #define __packed __attribute__((packed))
+#define __used __attribute__((used))
+#define __section(x)__attribute__((__section__(x)))
 
 #include "../../../../arch/x86/include/asm/sgx.h"
 #include "../../../../arch/x86/include/asm/enclu.h"
diff --git a/tools/testing/selftests/sgx/load.c b/tools/testing/selftests/sgx/load.c
index 94bdeac1cf04..c9f658e44de6 100644
--- a/tools/testing/selftests/sgx/load.c
+++ b/tools/testing/selftests/sgx/load.c
@@ -136,11 +136,11 @@ static bool encl_ioc_add_pages(struct encl *encl, struct encl_segment *seg)
  */
 uint64_t encl_get_entry(struct encl *encl, const char *symbol)
 {
+	Elf64_Sym *symtab = NULL;
+	char *sym_names = NULL;
 	Elf64_Shdr *sections;
-	Elf64_Sym *symtab;
 	Elf64_Ehdr *ehdr;
-	char *sym_names;
-	int num_sym;
+	int num_sym = 0;
 	int i;
 
 	ehdr = encl->bin;
@@ -161,6 +161,9 @@ uint64_t encl_get_entry(struct encl *encl, const char *symbol)
 		}
 	}
 
+	if (!symtab || !sym_names)
+		return 0;
+
 	for (i = 0; i < num_sym; i++) {
 		Elf64_Sym *sym = &symtab[i];
 
diff --git a/tools/testing/selftests/sgx/sigstruct.c b/tools/testing/selftests/sgx/sigstruct.c
index a07896a46364..d73b29becf5b 100644
--- a/tools/testing/selftests/sgx/sigstruct.c
+++ b/tools/testing/selftests/sgx/sigstruct.c
@@ -318,9 +318,9 @@ bool encl_measure(struct encl *encl)
 	struct sgx_sigstruct *sigstruct = &encl->sigstruct;
 	struct sgx_sigstruct_payload payload;
 	uint8_t digest[SHA256_DIGEST_LENGTH];
+	EVP_MD_CTX *ctx = NULL;
 	unsigned int siglen;
 	RSA *key = NULL;
-	EVP_MD_CTX *ctx;
 	int i;
 
 	memset(sigstruct, 0, sizeof(*sigstruct));
@@ -384,7 +384,8 @@ bool encl_measure(struct encl *encl)
 	return true;
 
 err:
-	EVP_MD_CTX_destroy(ctx);
+	if (ctx)
+		EVP_MD_CTX_destroy(ctx);
 	RSA_free(key);
 	return false;
 }
diff --git a/tools/testing/selftests/sgx/test_encl.c b/tools/testing/selftests/sgx/test_encl.c
index c0d6397295e3..2c4d709cce2d 100644
--- a/tools/testing/selftests/sgx/test_encl.c
+++ b/tools/testing/selftests/sgx/test_encl.c
@@ -5,11 +5,12 @@
 #include "defines.h"
 
 /*
- * Data buffer spanning two pages that will be placed first in .data
- * segment. Even if not used internally the second page is needed by
- * external test manipulating page permissions.
+ * Data buffer spanning two pages that will be placed first in the .data
+ * segment via the linker script. Even if not used internally the second page
+ * is needed by external test manipulating page permissions, so mark
+ * encl_buffer as "used" to make sure it is entirely preserved by the compiler.
  */
-static uint8_t encl_buffer[8192] = { 1 };
+static uint8_t __used __section(".data.encl_buffer") encl_buffer[8192] = { 1 };
 
 enum sgx_enclu_function {
 	EACCEPT = 0x5,
@@ -24,10 +25,11 @@ static void do_encl_emodpe(void *_op)
 	secinfo.flags = op->flags;
 
 	asm volatile(".byte 0x0f, 0x01, 0xd7"
-				:
+				: /* no outputs */
 				: "a" (EMODPE),
 				  "b" (&secinfo),
-				  "c" (op->epc_addr));
+				  "c" (op->epc_addr)
+				: "memory" /* read from secinfo pointer */);
 }
 
 static void do_encl_eaccept(void *_op)
@@ -42,7 +44,8 @@ static void do_encl_eaccept(void *_op)
 				: "=a" (rax)
 				: "a" (EACCEPT),
 				  "b" (&secinfo),
-				  "c" (op->epc_addr));
+				  "c" (op->epc_addr)
+				: "memory" /* read from secinfo pointer */);
 
 	op->ret = rax;
 }
@@ -119,21 +122,41 @@ static void do_encl_op_nop(void *_op)
 
 }
 
+/*
+ * Symbol placed at the start of the enclave image by the linker script.
+ * Declare this extern symbol with visibility "hidden" to ensure the compiler
+ * does not access it through the GOT and generates position-independent
+ * addressing as __encl_base(%rip), so we can get the actual enclave base
+ * during runtime.
+ */
+extern const uint8_t __attribute__((visibility("hidden"))) __encl_base;
+
+typedef void (*encl_op_t)(void *);
+static const encl_op_t encl_op_array[ENCL_OP_MAX] = {
+	do_encl_op_put_to_buf,
+	do_encl_op_get_from_buf,
+	do_encl_op_put_to_addr,
+	do_encl_op_get_from_addr,
+	do_encl_op_nop,
+	do_encl_eaccept,
+	do_encl_emodpe,
+	do_encl_init_tcs_page,
+};
+
 void encl_body(void *rdi,  void *rsi)
 {
-	const void (*encl_op_array[ENCL_OP_MAX])(void *) = {
-		do_encl_op_put_to_buf,
-		do_encl_op_get_from_buf,
-		do_encl_op_put_to_addr,
-		do_encl_op_get_from_addr,
-		do_encl_op_nop,
-		do_encl_eaccept,
-		do_encl_emodpe,
-		do_encl_init_tcs_page,
-	};
-
-	struct encl_op_header *op = (struct encl_op_header *)rdi;
-
-	if (op->type < ENCL_OP_MAX)
-		(*encl_op_array[op->type])(op);
+	struct encl_op_header *header = (struct encl_op_header *)rdi;
+	encl_op_t op;
+
+	if (header->type >= ENCL_OP_MAX)
+		return;
+
+	/*
+	 * The enclave base address needs to be added, as this call site
+	 * *cannot be* made rip-relative by the compiler, or fixed up by
+	 * any other possible means.
+	 */
+	op = ((uint64_t)&__encl_base) + encl_op_array[header->type];
+
+	(*op)(header);
 }
diff --git a/tools/testing/selftests/sgx/test_encl.lds b/tools/testing/selftests/sgx/test_encl.lds
index a1ec64f7d91f..ffe851a1cac4 100644
--- a/tools/testing/selftests/sgx/test_encl.lds
+++ b/tools/testing/selftests/sgx/test_encl.lds
@@ -10,6 +10,7 @@ PHDRS
 SECTIONS
 {
 	. = 0;
+        __encl_base = .;
 	.tcs : {
 		*(.tcs*)
 	} : tcs
@@ -23,6 +24,7 @@ SECTIONS
 	} : text
 
 	.data : {
+		*(.data.encl_buffer)
 		*(.data*)
 	} : data
 
@@ -31,11 +33,9 @@ SECTIONS
 		*(.note*)
 		*(.debug*)
 		*(.eh_frame*)
+		*(.dyn*)
+		*(.gnu.hash)
 	}
 }
 
-ASSERT(!DEFINED(.altinstructions), "ALTERNATIVES are not supported in enclaves")
-ASSERT(!DEFINED(.altinstr_replacement), "ALTERNATIVES are not supported in enclaves")
-ASSERT(!DEFINED(.discard.retpoline_safe), "RETPOLINE ALTERNATIVES are not supported in enclaves")
-ASSERT(!DEFINED(.discard.nospec), "RETPOLINE ALTERNATIVES are not supported in enclaves")
-ASSERT(!DEFINED(.got.plt), "Libcalls are not supported in enclaves")
+ASSERT(!DEFINED(_GLOBAL_OFFSET_TABLE_), "Libcalls through GOT are not supported in enclaves")
diff --git a/tools/testing/selftests/sgx/test_encl_bootstrap.S b/tools/testing/selftests/sgx/test_encl_bootstrap.S
index 03ae0f57e29d..d8c4ac94e032 100644
--- a/tools/testing/selftests/sgx/test_encl_bootstrap.S
+++ b/tools/testing/selftests/sgx/test_encl_bootstrap.S
@@ -42,9 +42,12 @@
 encl_entry:
 	# RBX contains the base address for TCS, which is the first address
 	# inside the enclave for TCS #1 and one page into the enclave for
-	# TCS #2. By adding the value of encl_stack to it, we get
-	# the absolute address for the stack.
-	lea	(encl_stack)(%rbx), %rax
+	# TCS #2. First make it relative by substracting __encl_base and
+	# then add the address of encl_stack to get the address for the stack.
+	lea __encl_base(%rip), %rax
+	sub %rax, %rbx
+	lea encl_stack(%rip), %rax
+	add %rbx, %rax
 	jmp encl_entry_core
 encl_dyn_entry:
 	# Entry point for dynamically created TCS page expected to follow
@@ -55,25 +58,12 @@ encl_entry_core:
 	push	%rax
 
 	push	%rcx # push the address after EENTER
-	push	%rbx # push the enclave base address
 
+	# NOTE: as the selftest enclave is *not* intended for production,
+	# simplify the code by not initializing ABI registers on entry or
+	# cleansing caller-save registers on exit.
 	call	encl_body
 
-	pop	%rbx # pop the enclave base address
-
-	/* Clear volatile GPRs, except RAX (EEXIT function). */
-	xor     %rcx, %rcx
-	xor     %rdx, %rdx
-	xor     %rdi, %rdi
-	xor     %rsi, %rsi
-	xor     %r8, %r8
-	xor     %r9, %r9
-	xor     %r10, %r10
-	xor     %r11, %r11
-
-	# Reset status flags.
-	add     %rdx, %rdx # OF = SF = AF = CF = 0; ZF = PF = 1
-
 	# Prepare EEXIT target by popping the address of the instruction after
 	# EENTER to RBX.
 	pop	%rbx
diff --git a/tools/testing/selftests/thermal/intel/power_floor/.gitignore b/tools/testing/selftests/thermal/intel/power_floor/.gitignore
new file mode 100644
index 000000000000..1b9a76406f18
--- /dev/null
+++ b/tools/testing/selftests/thermal/intel/power_floor/.gitignore
@@ -0,0 +1 @@
+power_floor_test
diff --git a/tools/testing/selftests/thermal/intel/workload_hint/.gitignore b/tools/testing/selftests/thermal/intel/workload_hint/.gitignore
new file mode 100644
index 000000000000..d697b034a3a8
--- /dev/null
+++ b/tools/testing/selftests/thermal/intel/workload_hint/.gitignore
@@ -0,0 +1 @@
+workload_hint_test
diff --git a/tools/testing/selftests/uevent/.gitignore b/tools/testing/selftests/uevent/.gitignore
new file mode 100644
index 000000000000..382afb74cd40
--- /dev/null
+++ b/tools/testing/selftests/uevent/.gitignore
@@ -0,0 +1 @@
+uevent_filtering
diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile
index 2456a399eb9a..afd18c678ff5 100644
--- a/tools/tracing/rtla/Makefile
+++ b/tools/tracing/rtla/Makefile
@@ -28,10 +28,15 @@ FOPTS	:=	-flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong \
 		-fasynchronous-unwind-tables -fstack-clash-protection
 WOPTS	:= 	-Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized
 
+ifeq ($(CC),clang)
+  FOPTS := $(filter-out -ffat-lto-objects, $(FOPTS))
+  WOPTS := $(filter-out -Wno-maybe-uninitialized, $(WOPTS))
+endif
+
 TRACEFS_HEADERS	:= $$($(PKG_CONFIG) --cflags libtracefs)
 
 CFLAGS	:=	-O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS) $(EXTRA_CFLAGS)
-LDFLAGS	:=	-ggdb $(EXTRA_LDFLAGS)
+LDFLAGS	:=	-flto=auto -ggdb $(EXTRA_LDFLAGS)
 LIBS	:=	$$($(PKG_CONFIG) --libs libtracefs)
 
 SRC	:=	$(wildcard src/*.c)
diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c
index 8f81fa007364..01870d50942a 100644
--- a/tools/tracing/rtla/src/osnoise_hist.c
+++ b/tools/tracing/rtla/src/osnoise_hist.c
@@ -135,8 +135,7 @@ static void osnoise_hist_update_multiple(struct osnoise_tool *tool, int cpu,
 	if (params->output_divisor)
 		duration = duration / params->output_divisor;
 
-	if (data->bucket_size)
-		bucket = duration / data->bucket_size;
+	bucket = duration / data->bucket_size;
 
 	total_duration = duration * count;
 
@@ -480,7 +479,11 @@ static void osnoise_hist_usage(char *usage)
 
 	for (i = 0; msg[i]; i++)
 		fprintf(stderr, "%s\n", msg[i]);
-	exit(1);
+
+	if (usage)
+		exit(EXIT_FAILURE);
+
+	exit(EXIT_SUCCESS);
 }
 
 /*
diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c
index f7c959be8677..457360db0767 100644
--- a/tools/tracing/rtla/src/osnoise_top.c
+++ b/tools/tracing/rtla/src/osnoise_top.c
@@ -331,7 +331,11 @@ static void osnoise_top_usage(struct osnoise_top_params *params, char *usage)
 
 	for (i = 0; msg[i]; i++)
 		fprintf(stderr, "%s\n", msg[i]);
-	exit(1);
+
+	if (usage)
+		exit(EXIT_FAILURE);
+
+	exit(EXIT_SUCCESS);
 }
 
 /*
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
index 47d3d8b53cb2..dbf154082f95 100644
--- a/tools/tracing/rtla/src/timerlat_hist.c
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -178,8 +178,7 @@ timerlat_hist_update(struct osnoise_tool *tool, int cpu,
 	if (params->output_divisor)
 		latency = latency / params->output_divisor;
 
-	if (data->bucket_size)
-		bucket = latency / data->bucket_size;
+	bucket = latency / data->bucket_size;
 
 	if (!context) {
 		hist = data->hist[cpu].irq;
@@ -546,7 +545,11 @@ static void timerlat_hist_usage(char *usage)
 
 	for (i = 0; msg[i]; i++)
 		fprintf(stderr, "%s\n", msg[i]);
-	exit(1);
+
+	if (usage)
+		exit(EXIT_FAILURE);
+
+	exit(EXIT_SUCCESS);
 }
 
 /*
diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c
index 1640f121baca..3e9af2c38688 100644
--- a/tools/tracing/rtla/src/timerlat_top.c
+++ b/tools/tracing/rtla/src/timerlat_top.c
@@ -375,7 +375,11 @@ static void timerlat_top_usage(char *usage)
 
 	for (i = 0; msg[i]; i++)
 		fprintf(stderr, "%s\n", msg[i]);
-	exit(1);
+
+	if (usage)
+		exit(EXIT_FAILURE);
+
+	exit(EXIT_SUCCESS);
 }
 
 /*
diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c
index c769d7b3842c..9ac71a66840c 100644
--- a/tools/tracing/rtla/src/utils.c
+++ b/tools/tracing/rtla/src/utils.c
@@ -238,12 +238,6 @@ static inline int sched_setattr(pid_t pid, const struct sched_attr *attr,
 	return syscall(__NR_sched_setattr, pid, attr, flags);
 }
 
-static inline int sched_getattr(pid_t pid, struct sched_attr *attr,
-				unsigned int size, unsigned int flags)
-{
-	return syscall(__NR_sched_getattr, pid, attr, size, flags);
-}
-
 int __set_sched_attr(int pid, struct sched_attr *attr)
 {
 	int flags = 0;
@@ -479,13 +473,13 @@ int parse_prio(char *arg, struct sched_attr *sched_param)
 		if (prio == INVALID_VAL)
 			return -1;
 
-		if (prio < sched_get_priority_min(SCHED_OTHER))
+		if (prio < MIN_NICE)
 			return -1;
-		if (prio > sched_get_priority_max(SCHED_OTHER))
+		if (prio > MAX_NICE)
 			return -1;
 
 		sched_param->sched_policy   = SCHED_OTHER;
-		sched_param->sched_priority = prio;
+		sched_param->sched_nice = prio;
 		break;
 	default:
 		return -1;
@@ -536,7 +530,7 @@ int set_cpu_dma_latency(int32_t latency)
  */
 static const int find_mount(const char *fs, char *mp, int sizeof_mp)
 {
-	char mount_point[MAX_PATH];
+	char mount_point[MAX_PATH+1];
 	char type[100];
 	int found = 0;
 	FILE *fp;
diff --git a/tools/tracing/rtla/src/utils.h b/tools/tracing/rtla/src/utils.h
index 04ed1e650495..d44513e6c66a 100644
--- a/tools/tracing/rtla/src/utils.h
+++ b/tools/tracing/rtla/src/utils.h
@@ -9,6 +9,8 @@
  */
 #define BUFF_U64_STR_SIZE	24
 #define MAX_PATH		1024
+#define MAX_NICE		20
+#define MIN_NICE		-19
 
 #define container_of(ptr, type, member)({			\
 	const typeof(((type *)0)->member) *__mptr = (ptr);	\
diff --git a/tools/verification/rv/Makefile b/tools/verification/rv/Makefile
index 3d0f3888a58c..485f8aeddbe0 100644
--- a/tools/verification/rv/Makefile
+++ b/tools/verification/rv/Makefile
@@ -28,10 +28,15 @@ FOPTS	:=	-flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong \
 		-fasynchronous-unwind-tables -fstack-clash-protection
 WOPTS	:= 	-Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized
 
+ifeq ($(CC),clang)
+  FOPTS := $(filter-out -ffat-lto-objects, $(FOPTS))
+  WOPTS := $(filter-out -Wno-maybe-uninitialized, $(WOPTS))
+endif
+
 TRACEFS_HEADERS	:= $$($(PKG_CONFIG) --cflags libtracefs)
 
 CFLAGS	:=	-O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS) $(EXTRA_CFLAGS) -I include
-LDFLAGS	:=	-ggdb $(EXTRA_LDFLAGS)
+LDFLAGS	:=	-flto=auto -ggdb $(EXTRA_LDFLAGS)
 LIBS	:=	$$($(PKG_CONFIG) --libs libtracefs)
 
 SRC	:=	$(wildcard src/*.c)
diff --git a/tools/verification/rv/src/in_kernel.c b/tools/verification/rv/src/in_kernel.c
index ad28582bcf2b..f04479ecc96c 100644
--- a/tools/verification/rv/src/in_kernel.c
+++ b/tools/verification/rv/src/in_kernel.c
@@ -210,9 +210,9 @@ static char *ikm_read_reactor(char *monitor_name)
 static char *ikm_get_current_reactor(char *monitor_name)
 {
 	char *reactors = ikm_read_reactor(monitor_name);
+	char *curr_reactor = NULL;
 	char *start;
 	char *end;
-	char *curr_reactor;
 
 	if (!reactors)
 		return NULL;
diff --git a/usr/gen_init_cpio.c b/usr/gen_init_cpio.c
index 61230532fef1..edcdb8abfa31 100644
--- a/usr/gen_init_cpio.c
+++ b/usr/gen_init_cpio.c
@@ -27,6 +27,7 @@
 static unsigned int offset;
 static unsigned int ino = 721;
 static time_t default_mtime;
+static bool do_file_mtime;
 static bool do_csum = false;
 
 struct file_handler {
@@ -329,6 +330,7 @@ static int cpio_mkfile(const char *name, const char *location,
 	int file;
 	int retval;
 	int rc = -1;
+	time_t mtime;
 	int namesize;
 	unsigned int i;
 	uint32_t csum = 0;
@@ -347,16 +349,21 @@ static int cpio_mkfile(const char *name, const char *location,
 		goto error;
 	}
 
-	if (buf.st_mtime > 0xffffffff) {
-		fprintf(stderr, "%s: Timestamp exceeds maximum cpio timestamp, clipping.\n",
-			location);
-		buf.st_mtime = 0xffffffff;
-	}
+	if (do_file_mtime) {
+		mtime = default_mtime;
+	} else {
+		mtime = buf.st_mtime;
+		if (mtime > 0xffffffff) {
+			fprintf(stderr, "%s: Timestamp exceeds maximum cpio timestamp, clipping.\n",
+					location);
+			mtime = 0xffffffff;
+		}
 
-	if (buf.st_mtime < 0) {
-		fprintf(stderr, "%s: Timestamp negative, clipping.\n",
-			location);
-		buf.st_mtime = 0;
+		if (mtime < 0) {
+			fprintf(stderr, "%s: Timestamp negative, clipping.\n",
+					location);
+			mtime = 0;
+		}
 	}
 
 	if (buf.st_size > 0xffffffff) {
@@ -387,7 +394,7 @@ static int cpio_mkfile(const char *name, const char *location,
 			(long) uid,		/* uid */
 			(long) gid,		/* gid */
 			nlinks,			/* nlink */
-			(long) buf.st_mtime,	/* mtime */
+			(long) mtime,		/* mtime */
 			size,			/* filesize */
 			3,			/* major */
 			1,			/* minor */
@@ -536,8 +543,9 @@ static void usage(const char *prog)
 		"file /sbin/kinit /usr/src/klibc/kinit/kinit 0755 0 0\n"
 		"\n"
 		"<timestamp> is time in seconds since Epoch that will be used\n"
-		"as mtime for symlinks, special files and directories. The default\n"
-		"is to use the current time for these entries.\n"
+		"as mtime for symlinks, directories, regular and special files.\n"
+		"The default is to use the current time for all files, but\n"
+		"preserve modification time for regular files.\n"
 		"-c: calculate and store 32-bit checksums for file data.\n",
 		prog);
 }
@@ -594,6 +602,7 @@ int main (int argc, char *argv[])
 				usage(argv[0]);
 				exit(1);
 			}
+			do_file_mtime = true;
 			break;
 		case 'c':
 			do_csum = true;
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 484d0873061c..184dab4ee871 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -4,13 +4,16 @@
 config HAVE_KVM
        bool
 
-config HAVE_KVM_PFNCACHE
+config KVM_COMMON
        bool
+       select EVENTFD
+       select INTERVAL_TREE
+       select PREEMPT_NOTIFIERS
 
-config HAVE_KVM_IRQCHIP
+config HAVE_KVM_PFNCACHE
        bool
 
-config HAVE_KVM_IRQFD
+config HAVE_KVM_IRQCHIP
        bool
 
 config HAVE_KVM_IRQ_ROUTING
@@ -39,10 +42,6 @@ config NEED_KVM_DIRTY_RING_WITH_BITMAP
 	bool
 	depends on HAVE_KVM_DIRTY_RING
 
-config HAVE_KVM_EVENTFD
-       bool
-       select EVENTFD
-
 config KVM_MMIO
        bool
 
@@ -92,3 +91,20 @@ config HAVE_KVM_PM_NOTIFIER
 
 config KVM_GENERIC_HARDWARE_ENABLING
        bool
+
+config KVM_GENERIC_MMU_NOTIFIER
+       select MMU_NOTIFIER
+       bool
+
+config KVM_GENERIC_MEMORY_ATTRIBUTES
+       depends on KVM_GENERIC_MMU_NOTIFIER
+       bool
+
+config KVM_PRIVATE_MEM
+       select XARRAY_MULTI
+       bool
+
+config KVM_GENERIC_PRIVATE_MEM
+       select KVM_GENERIC_MEMORY_ATTRIBUTES
+       select KVM_PRIVATE_MEM
+       bool
diff --git a/virt/kvm/Makefile.kvm b/virt/kvm/Makefile.kvm
index 2c27d5d0c367..724c89af78af 100644
--- a/virt/kvm/Makefile.kvm
+++ b/virt/kvm/Makefile.kvm
@@ -12,3 +12,4 @@ kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o
 kvm-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(KVM)/irqchip.o
 kvm-$(CONFIG_HAVE_KVM_DIRTY_RING) += $(KVM)/dirty_ring.o
 kvm-$(CONFIG_HAVE_KVM_PFNCACHE) += $(KVM)/pfncache.o
+kvm-$(CONFIG_KVM_PRIVATE_MEM) += $(KVM)/guest_memfd.o
diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c
index c1cd7dfe4a90..86d267db87bb 100644
--- a/virt/kvm/dirty_ring.c
+++ b/virt/kvm/dirty_ring.c
@@ -58,7 +58,7 @@ static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask)
 	as_id = slot >> 16;
 	id = (u16)slot;
 
-	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
 		return;
 
 	memslot = id_to_memslot(__kvm_memslots(kvm, as_id), id);
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index c0e230f4c3e9..229570059a1b 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -28,7 +28,7 @@
 
 #include <kvm/iodev.h>
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 
 static struct workqueue_struct *irqfd_cleanup_wq;
 
@@ -526,21 +526,7 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
 	synchronize_srcu(&kvm->irq_srcu);
 	kvm_arch_post_irq_ack_notifier_list_update(kvm);
 }
-#endif
-
-void
-kvm_eventfd_init(struct kvm *kvm)
-{
-#ifdef CONFIG_HAVE_KVM_IRQFD
-	spin_lock_init(&kvm->irqfds.lock);
-	INIT_LIST_HEAD(&kvm->irqfds.items);
-	INIT_LIST_HEAD(&kvm->irqfds.resampler_list);
-	mutex_init(&kvm->irqfds.resampler_lock);
-#endif
-	INIT_LIST_HEAD(&kvm->ioeventfds);
-}
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
 /*
  * shutdown any irqfd's that match fd+gsi
  */
@@ -1012,3 +998,15 @@ kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 
 	return kvm_assign_ioeventfd(kvm, args);
 }
+
+void
+kvm_eventfd_init(struct kvm *kvm)
+{
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
+	spin_lock_init(&kvm->irqfds.lock);
+	INIT_LIST_HEAD(&kvm->irqfds.items);
+	INIT_LIST_HEAD(&kvm->irqfds.resampler_list);
+	mutex_init(&kvm->irqfds.resampler_lock);
+#endif
+	INIT_LIST_HEAD(&kvm->ioeventfds);
+}
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
new file mode 100644
index 000000000000..0f4e0cf4f158
--- /dev/null
+++ b/virt/kvm/guest_memfd.c
@@ -0,0 +1,532 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/backing-dev.h>
+#include <linux/falloc.h>
+#include <linux/kvm_host.h>
+#include <linux/pagemap.h>
+#include <linux/anon_inodes.h>
+
+#include "kvm_mm.h"
+
+struct kvm_gmem {
+	struct kvm *kvm;
+	struct xarray bindings;
+	struct list_head entry;
+};
+
+static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
+{
+	struct folio *folio;
+
+	/* TODO: Support huge pages. */
+	folio = filemap_grab_folio(inode->i_mapping, index);
+	if (IS_ERR_OR_NULL(folio))
+		return NULL;
+
+	/*
+	 * Use the up-to-date flag to track whether or not the memory has been
+	 * zeroed before being handed off to the guest.  There is no backing
+	 * storage for the memory, so the folio will remain up-to-date until
+	 * it's removed.
+	 *
+	 * TODO: Skip clearing pages when trusted firmware will do it when
+	 * assigning memory to the guest.
+	 */
+	if (!folio_test_uptodate(folio)) {
+		unsigned long nr_pages = folio_nr_pages(folio);
+		unsigned long i;
+
+		for (i = 0; i < nr_pages; i++)
+			clear_highpage(folio_page(folio, i));
+
+		folio_mark_uptodate(folio);
+	}
+
+	/*
+	 * Ignore accessed, referenced, and dirty flags.  The memory is
+	 * unevictable and there is no storage to write back to.
+	 */
+	return folio;
+}
+
+static void kvm_gmem_invalidate_begin(struct kvm_gmem *gmem, pgoff_t start,
+				      pgoff_t end)
+{
+	bool flush = false, found_memslot = false;
+	struct kvm_memory_slot *slot;
+	struct kvm *kvm = gmem->kvm;
+	unsigned long index;
+
+	xa_for_each_range(&gmem->bindings, index, slot, start, end - 1) {
+		pgoff_t pgoff = slot->gmem.pgoff;
+
+		struct kvm_gfn_range gfn_range = {
+			.start = slot->base_gfn + max(pgoff, start) - pgoff,
+			.end = slot->base_gfn + min(pgoff + slot->npages, end) - pgoff,
+			.slot = slot,
+			.may_block = true,
+		};
+
+		if (!found_memslot) {
+			found_memslot = true;
+
+			KVM_MMU_LOCK(kvm);
+			kvm_mmu_invalidate_begin(kvm);
+		}
+
+		flush |= kvm_mmu_unmap_gfn_range(kvm, &gfn_range);
+	}
+
+	if (flush)
+		kvm_flush_remote_tlbs(kvm);
+
+	if (found_memslot)
+		KVM_MMU_UNLOCK(kvm);
+}
+
+static void kvm_gmem_invalidate_end(struct kvm_gmem *gmem, pgoff_t start,
+				    pgoff_t end)
+{
+	struct kvm *kvm = gmem->kvm;
+
+	if (xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) {
+		KVM_MMU_LOCK(kvm);
+		kvm_mmu_invalidate_end(kvm);
+		KVM_MMU_UNLOCK(kvm);
+	}
+}
+
+static long kvm_gmem_punch_hole(struct inode *inode, loff_t offset, loff_t len)
+{
+	struct list_head *gmem_list = &inode->i_mapping->i_private_list;
+	pgoff_t start = offset >> PAGE_SHIFT;
+	pgoff_t end = (offset + len) >> PAGE_SHIFT;
+	struct kvm_gmem *gmem;
+
+	/*
+	 * Bindings must be stable across invalidation to ensure the start+end
+	 * are balanced.
+	 */
+	filemap_invalidate_lock(inode->i_mapping);
+
+	list_for_each_entry(gmem, gmem_list, entry)
+		kvm_gmem_invalidate_begin(gmem, start, end);
+
+	truncate_inode_pages_range(inode->i_mapping, offset, offset + len - 1);
+
+	list_for_each_entry(gmem, gmem_list, entry)
+		kvm_gmem_invalidate_end(gmem, start, end);
+
+	filemap_invalidate_unlock(inode->i_mapping);
+
+	return 0;
+}
+
+static long kvm_gmem_allocate(struct inode *inode, loff_t offset, loff_t len)
+{
+	struct address_space *mapping = inode->i_mapping;
+	pgoff_t start, index, end;
+	int r;
+
+	/* Dedicated guest is immutable by default. */
+	if (offset + len > i_size_read(inode))
+		return -EINVAL;
+
+	filemap_invalidate_lock_shared(mapping);
+
+	start = offset >> PAGE_SHIFT;
+	end = (offset + len) >> PAGE_SHIFT;
+
+	r = 0;
+	for (index = start; index < end; ) {
+		struct folio *folio;
+
+		if (signal_pending(current)) {
+			r = -EINTR;
+			break;
+		}
+
+		folio = kvm_gmem_get_folio(inode, index);
+		if (!folio) {
+			r = -ENOMEM;
+			break;
+		}
+
+		index = folio_next_index(folio);
+
+		folio_unlock(folio);
+		folio_put(folio);
+
+		/* 64-bit only, wrapping the index should be impossible. */
+		if (WARN_ON_ONCE(!index))
+			break;
+
+		cond_resched();
+	}
+
+	filemap_invalidate_unlock_shared(mapping);
+
+	return r;
+}
+
+static long kvm_gmem_fallocate(struct file *file, int mode, loff_t offset,
+			       loff_t len)
+{
+	int ret;
+
+	if (!(mode & FALLOC_FL_KEEP_SIZE))
+		return -EOPNOTSUPP;
+
+	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+		return -EOPNOTSUPP;
+
+	if (!PAGE_ALIGNED(offset) || !PAGE_ALIGNED(len))
+		return -EINVAL;
+
+	if (mode & FALLOC_FL_PUNCH_HOLE)
+		ret = kvm_gmem_punch_hole(file_inode(file), offset, len);
+	else
+		ret = kvm_gmem_allocate(file_inode(file), offset, len);
+
+	if (!ret)
+		file_modified(file);
+	return ret;
+}
+
+static int kvm_gmem_release(struct inode *inode, struct file *file)
+{
+	struct kvm_gmem *gmem = file->private_data;
+	struct kvm_memory_slot *slot;
+	struct kvm *kvm = gmem->kvm;
+	unsigned long index;
+
+	/*
+	 * Prevent concurrent attempts to *unbind* a memslot.  This is the last
+	 * reference to the file and thus no new bindings can be created, but
+	 * dereferencing the slot for existing bindings needs to be protected
+	 * against memslot updates, specifically so that unbind doesn't race
+	 * and free the memslot (kvm_gmem_get_file() will return NULL).
+	 */
+	mutex_lock(&kvm->slots_lock);
+
+	filemap_invalidate_lock(inode->i_mapping);
+
+	xa_for_each(&gmem->bindings, index, slot)
+		rcu_assign_pointer(slot->gmem.file, NULL);
+
+	synchronize_rcu();
+
+	/*
+	 * All in-flight operations are gone and new bindings can be created.
+	 * Zap all SPTEs pointed at by this file.  Do not free the backing
+	 * memory, as its lifetime is associated with the inode, not the file.
+	 */
+	kvm_gmem_invalidate_begin(gmem, 0, -1ul);
+	kvm_gmem_invalidate_end(gmem, 0, -1ul);
+
+	list_del(&gmem->entry);
+
+	filemap_invalidate_unlock(inode->i_mapping);
+
+	mutex_unlock(&kvm->slots_lock);
+
+	xa_destroy(&gmem->bindings);
+	kfree(gmem);
+
+	kvm_put_kvm(kvm);
+
+	return 0;
+}
+
+static inline struct file *kvm_gmem_get_file(struct kvm_memory_slot *slot)
+{
+	/*
+	 * Do not return slot->gmem.file if it has already been closed;
+	 * there might be some time between the last fput() and when
+	 * kvm_gmem_release() clears slot->gmem.file, and you do not
+	 * want to spin in the meanwhile.
+	 */
+	return get_file_active(&slot->gmem.file);
+}
+
+static struct file_operations kvm_gmem_fops = {
+	.open		= generic_file_open,
+	.release	= kvm_gmem_release,
+	.fallocate	= kvm_gmem_fallocate,
+};
+
+void kvm_gmem_init(struct module *module)
+{
+	kvm_gmem_fops.owner = module;
+}
+
+static int kvm_gmem_migrate_folio(struct address_space *mapping,
+				  struct folio *dst, struct folio *src,
+				  enum migrate_mode mode)
+{
+	WARN_ON_ONCE(1);
+	return -EINVAL;
+}
+
+static int kvm_gmem_error_folio(struct address_space *mapping, struct folio *folio)
+{
+	struct list_head *gmem_list = &mapping->i_private_list;
+	struct kvm_gmem *gmem;
+	pgoff_t start, end;
+
+	filemap_invalidate_lock_shared(mapping);
+
+	start = folio->index;
+	end = start + folio_nr_pages(folio);
+
+	list_for_each_entry(gmem, gmem_list, entry)
+		kvm_gmem_invalidate_begin(gmem, start, end);
+
+	/*
+	 * Do not truncate the range, what action is taken in response to the
+	 * error is userspace's decision (assuming the architecture supports
+	 * gracefully handling memory errors).  If/when the guest attempts to
+	 * access a poisoned page, kvm_gmem_get_pfn() will return -EHWPOISON,
+	 * at which point KVM can either terminate the VM or propagate the
+	 * error to userspace.
+	 */
+
+	list_for_each_entry(gmem, gmem_list, entry)
+		kvm_gmem_invalidate_end(gmem, start, end);
+
+	filemap_invalidate_unlock_shared(mapping);
+
+	return MF_DELAYED;
+}
+
+static const struct address_space_operations kvm_gmem_aops = {
+	.dirty_folio = noop_dirty_folio,
+	.migrate_folio	= kvm_gmem_migrate_folio,
+	.error_remove_folio = kvm_gmem_error_folio,
+};
+
+static int kvm_gmem_getattr(struct mnt_idmap *idmap, const struct path *path,
+			    struct kstat *stat, u32 request_mask,
+			    unsigned int query_flags)
+{
+	struct inode *inode = path->dentry->d_inode;
+
+	generic_fillattr(idmap, request_mask, inode, stat);
+	return 0;
+}
+
+static int kvm_gmem_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+			    struct iattr *attr)
+{
+	return -EINVAL;
+}
+static const struct inode_operations kvm_gmem_iops = {
+	.getattr	= kvm_gmem_getattr,
+	.setattr	= kvm_gmem_setattr,
+};
+
+static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags)
+{
+	const char *anon_name = "[kvm-gmem]";
+	struct kvm_gmem *gmem;
+	struct inode *inode;
+	struct file *file;
+	int fd, err;
+
+	fd = get_unused_fd_flags(0);
+	if (fd < 0)
+		return fd;
+
+	gmem = kzalloc(sizeof(*gmem), GFP_KERNEL);
+	if (!gmem) {
+		err = -ENOMEM;
+		goto err_fd;
+	}
+
+	file = anon_inode_create_getfile(anon_name, &kvm_gmem_fops, gmem,
+					 O_RDWR, NULL);
+	if (IS_ERR(file)) {
+		err = PTR_ERR(file);
+		goto err_gmem;
+	}
+
+	file->f_flags |= O_LARGEFILE;
+
+	inode = file->f_inode;
+	WARN_ON(file->f_mapping != inode->i_mapping);
+
+	inode->i_private = (void *)(unsigned long)flags;
+	inode->i_op = &kvm_gmem_iops;
+	inode->i_mapping->a_ops = &kvm_gmem_aops;
+	inode->i_mode |= S_IFREG;
+	inode->i_size = size;
+	mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
+	mapping_set_unmovable(inode->i_mapping);
+	/* Unmovable mappings are supposed to be marked unevictable as well. */
+	WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping));
+
+	kvm_get_kvm(kvm);
+	gmem->kvm = kvm;
+	xa_init(&gmem->bindings);
+	list_add(&gmem->entry, &inode->i_mapping->i_private_list);
+
+	fd_install(fd, file);
+	return fd;
+
+err_gmem:
+	kfree(gmem);
+err_fd:
+	put_unused_fd(fd);
+	return err;
+}
+
+int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args)
+{
+	loff_t size = args->size;
+	u64 flags = args->flags;
+	u64 valid_flags = 0;
+
+	if (flags & ~valid_flags)
+		return -EINVAL;
+
+	if (size <= 0 || !PAGE_ALIGNED(size))
+		return -EINVAL;
+
+	return __kvm_gmem_create(kvm, size, flags);
+}
+
+int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
+		  unsigned int fd, loff_t offset)
+{
+	loff_t size = slot->npages << PAGE_SHIFT;
+	unsigned long start, end;
+	struct kvm_gmem *gmem;
+	struct inode *inode;
+	struct file *file;
+	int r = -EINVAL;
+
+	BUILD_BUG_ON(sizeof(gfn_t) != sizeof(slot->gmem.pgoff));
+
+	file = fget(fd);
+	if (!file)
+		return -EBADF;
+
+	if (file->f_op != &kvm_gmem_fops)
+		goto err;
+
+	gmem = file->private_data;
+	if (gmem->kvm != kvm)
+		goto err;
+
+	inode = file_inode(file);
+
+	if (offset < 0 || !PAGE_ALIGNED(offset) ||
+	    offset + size > i_size_read(inode))
+		goto err;
+
+	filemap_invalidate_lock(inode->i_mapping);
+
+	start = offset >> PAGE_SHIFT;
+	end = start + slot->npages;
+
+	if (!xa_empty(&gmem->bindings) &&
+	    xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) {
+		filemap_invalidate_unlock(inode->i_mapping);
+		goto err;
+	}
+
+	/*
+	 * No synchronize_rcu() needed, any in-flight readers are guaranteed to
+	 * be see either a NULL file or this new file, no need for them to go
+	 * away.
+	 */
+	rcu_assign_pointer(slot->gmem.file, file);
+	slot->gmem.pgoff = start;
+
+	xa_store_range(&gmem->bindings, start, end - 1, slot, GFP_KERNEL);
+	filemap_invalidate_unlock(inode->i_mapping);
+
+	/*
+	 * Drop the reference to the file, even on success.  The file pins KVM,
+	 * not the other way 'round.  Active bindings are invalidated if the
+	 * file is closed before memslots are destroyed.
+	 */
+	r = 0;
+err:
+	fput(file);
+	return r;
+}
+
+void kvm_gmem_unbind(struct kvm_memory_slot *slot)
+{
+	unsigned long start = slot->gmem.pgoff;
+	unsigned long end = start + slot->npages;
+	struct kvm_gmem *gmem;
+	struct file *file;
+
+	/*
+	 * Nothing to do if the underlying file was already closed (or is being
+	 * closed right now), kvm_gmem_release() invalidates all bindings.
+	 */
+	file = kvm_gmem_get_file(slot);
+	if (!file)
+		return;
+
+	gmem = file->private_data;
+
+	filemap_invalidate_lock(file->f_mapping);
+	xa_store_range(&gmem->bindings, start, end - 1, NULL, GFP_KERNEL);
+	rcu_assign_pointer(slot->gmem.file, NULL);
+	synchronize_rcu();
+	filemap_invalidate_unlock(file->f_mapping);
+
+	fput(file);
+}
+
+int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+		     gfn_t gfn, kvm_pfn_t *pfn, int *max_order)
+{
+	pgoff_t index = gfn - slot->base_gfn + slot->gmem.pgoff;
+	struct kvm_gmem *gmem;
+	struct folio *folio;
+	struct page *page;
+	struct file *file;
+	int r;
+
+	file = kvm_gmem_get_file(slot);
+	if (!file)
+		return -EFAULT;
+
+	gmem = file->private_data;
+
+	if (WARN_ON_ONCE(xa_load(&gmem->bindings, index) != slot)) {
+		r = -EIO;
+		goto out_fput;
+	}
+
+	folio = kvm_gmem_get_folio(file_inode(file), index);
+	if (!folio) {
+		r = -ENOMEM;
+		goto out_fput;
+	}
+
+	if (folio_test_hwpoison(folio)) {
+		r = -EHWPOISON;
+		goto out_unlock;
+	}
+
+	page = folio_file_page(folio, index);
+
+	*pfn = page_to_pfn(page);
+	if (max_order)
+		*max_order = 0;
+
+	r = 0;
+
+out_unlock:
+	folio_unlock(folio);
+out_fput:
+	fput(file);
+
+	return r;
+}
+EXPORT_SYMBOL_GPL(kvm_gmem_get_pfn);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 7db96875ac46..0f50960b0e3a 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -533,31 +533,44 @@ void kvm_destroy_vcpus(struct kvm *kvm)
 }
 EXPORT_SYMBOL_GPL(kvm_destroy_vcpus);
 
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
 {
 	return container_of(mn, struct kvm, mmu_notifier);
 }
 
-typedef bool (*hva_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
+typedef bool (*gfn_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
 
-typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start,
-			     unsigned long end);
+typedef void (*on_lock_fn_t)(struct kvm *kvm);
 
-typedef void (*on_unlock_fn_t)(struct kvm *kvm);
-
-struct kvm_hva_range {
-	unsigned long start;
-	unsigned long end;
+struct kvm_mmu_notifier_range {
+	/*
+	 * 64-bit addresses, as KVM notifiers can operate on host virtual
+	 * addresses (unsigned long) and guest physical addresses (64-bit).
+	 */
+	u64 start;
+	u64 end;
 	union kvm_mmu_notifier_arg arg;
-	hva_handler_t handler;
+	gfn_handler_t handler;
 	on_lock_fn_t on_lock;
-	on_unlock_fn_t on_unlock;
 	bool flush_on_ret;
 	bool may_block;
 };
 
 /*
+ * The inner-most helper returns a tuple containing the return value from the
+ * arch- and action-specific handler, plus a flag indicating whether or not at
+ * least one memslot was found, i.e. if the handler found guest memory.
+ *
+ * Note, most notifiers are averse to booleans, so even though KVM tracks the
+ * return from arch code as a bool, outer helpers will cast it to an int. :-(
+ */
+typedef struct kvm_mmu_notifier_return {
+	bool ret;
+	bool found_memslot;
+} kvm_mn_ret_t;
+
+/*
  * Use a dedicated stub instead of NULL to indicate that there is no callback
  * function/handler.  The compiler technically can't guarantee that a real
  * function will have a non-zero address, and so it will generate code to
@@ -578,26 +591,29 @@ static const union kvm_mmu_notifier_arg KVM_MMU_NOTIFIER_NO_ARG;
 	     node;							     \
 	     node = interval_tree_iter_next(node, start, last))	     \
 
-static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
-						  const struct kvm_hva_range *range)
+static __always_inline kvm_mn_ret_t __kvm_handle_hva_range(struct kvm *kvm,
+							   const struct kvm_mmu_notifier_range *range)
 {
-	bool ret = false, locked = false;
+	struct kvm_mmu_notifier_return r = {
+		.ret = false,
+		.found_memslot = false,
+	};
 	struct kvm_gfn_range gfn_range;
 	struct kvm_memory_slot *slot;
 	struct kvm_memslots *slots;
 	int i, idx;
 
 	if (WARN_ON_ONCE(range->end <= range->start))
-		return 0;
+		return r;
 
 	/* A null handler is allowed if and only if on_lock() is provided. */
 	if (WARN_ON_ONCE(IS_KVM_NULL_FN(range->on_lock) &&
 			 IS_KVM_NULL_FN(range->handler)))
-		return 0;
+		return r;
 
 	idx = srcu_read_lock(&kvm->srcu);
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		struct interval_tree_node *node;
 
 		slots = __kvm_memslots(kvm, i);
@@ -606,9 +622,9 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 			unsigned long hva_start, hva_end;
 
 			slot = container_of(node, struct kvm_memory_slot, hva_node[slots->node_idx]);
-			hva_start = max(range->start, slot->userspace_addr);
-			hva_end = min(range->end, slot->userspace_addr +
-						  (slot->npages << PAGE_SHIFT));
+			hva_start = max_t(unsigned long, range->start, slot->userspace_addr);
+			hva_end = min_t(unsigned long, range->end,
+					slot->userspace_addr + (slot->npages << PAGE_SHIFT));
 
 			/*
 			 * To optimize for the likely case where the address
@@ -627,71 +643,66 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 			gfn_range.end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, slot);
 			gfn_range.slot = slot;
 
-			if (!locked) {
-				locked = true;
+			if (!r.found_memslot) {
+				r.found_memslot = true;
 				KVM_MMU_LOCK(kvm);
 				if (!IS_KVM_NULL_FN(range->on_lock))
-					range->on_lock(kvm, range->start, range->end);
+					range->on_lock(kvm);
+
 				if (IS_KVM_NULL_FN(range->handler))
 					break;
 			}
-			ret |= range->handler(kvm, &gfn_range);
+			r.ret |= range->handler(kvm, &gfn_range);
 		}
 	}
 
-	if (range->flush_on_ret && ret)
+	if (range->flush_on_ret && r.ret)
 		kvm_flush_remote_tlbs(kvm);
 
-	if (locked) {
+	if (r.found_memslot)
 		KVM_MMU_UNLOCK(kvm);
-		if (!IS_KVM_NULL_FN(range->on_unlock))
-			range->on_unlock(kvm);
-	}
 
 	srcu_read_unlock(&kvm->srcu, idx);
 
-	/* The notifiers are averse to booleans. :-( */
-	return (int)ret;
+	return r;
 }
 
 static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
 						unsigned long start,
 						unsigned long end,
 						union kvm_mmu_notifier_arg arg,
-						hva_handler_t handler)
+						gfn_handler_t handler)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	const struct kvm_hva_range range = {
+	const struct kvm_mmu_notifier_range range = {
 		.start		= start,
 		.end		= end,
 		.arg		= arg,
 		.handler	= handler,
 		.on_lock	= (void *)kvm_null_fn,
-		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= true,
 		.may_block	= false,
 	};
 
-	return __kvm_handle_hva_range(kvm, &range);
+	return __kvm_handle_hva_range(kvm, &range).ret;
 }
 
 static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn,
 							 unsigned long start,
 							 unsigned long end,
-							 hva_handler_t handler)
+							 gfn_handler_t handler)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	const struct kvm_hva_range range = {
+	const struct kvm_mmu_notifier_range range = {
 		.start		= start,
 		.end		= end,
 		.handler	= handler,
 		.on_lock	= (void *)kvm_null_fn,
-		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= false,
 	};
 
-	return __kvm_handle_hva_range(kvm, &range);
+	return __kvm_handle_hva_range(kvm, &range).ret;
 }
 
 static bool kvm_change_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
@@ -736,16 +747,29 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 	kvm_handle_hva_range(mn, address, address + 1, arg, kvm_change_spte_gfn);
 }
 
-void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
-			      unsigned long end)
+void kvm_mmu_invalidate_begin(struct kvm *kvm)
 {
+	lockdep_assert_held_write(&kvm->mmu_lock);
 	/*
 	 * The count increase must become visible at unlock time as no
 	 * spte can be established without taking the mmu_lock and
 	 * count is also read inside the mmu_lock critical section.
 	 */
 	kvm->mmu_invalidate_in_progress++;
+
 	if (likely(kvm->mmu_invalidate_in_progress == 1)) {
+		kvm->mmu_invalidate_range_start = INVALID_GPA;
+		kvm->mmu_invalidate_range_end = INVALID_GPA;
+	}
+}
+
+void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end)
+{
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	WARN_ON_ONCE(!kvm->mmu_invalidate_in_progress);
+
+	if (likely(kvm->mmu_invalidate_range_start == INVALID_GPA)) {
 		kvm->mmu_invalidate_range_start = start;
 		kvm->mmu_invalidate_range_end = end;
 	} else {
@@ -765,16 +789,21 @@ void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
 	}
 }
 
+bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+	kvm_mmu_invalidate_range_add(kvm, range->start, range->end);
+	return kvm_unmap_gfn_range(kvm, range);
+}
+
 static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 					const struct mmu_notifier_range *range)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	const struct kvm_hva_range hva_range = {
+	const struct kvm_mmu_notifier_range hva_range = {
 		.start		= range->start,
 		.end		= range->end,
-		.handler	= kvm_unmap_gfn_range,
+		.handler	= kvm_mmu_unmap_gfn_range,
 		.on_lock	= kvm_mmu_invalidate_begin,
-		.on_unlock	= kvm_arch_guest_memory_reclaimed,
 		.flush_on_ret	= true,
 		.may_block	= mmu_notifier_range_blockable(range),
 	};
@@ -806,14 +835,21 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end,
 					  hva_range.may_block);
 
-	__kvm_handle_hva_range(kvm, &hva_range);
+	/*
+	 * If one or more memslots were found and thus zapped, notify arch code
+	 * that guest memory has been reclaimed.  This needs to be done *after*
+	 * dropping mmu_lock, as x86's reclaim path is slooooow.
+	 */
+	if (__kvm_handle_hva_range(kvm, &hva_range).found_memslot)
+		kvm_arch_guest_memory_reclaimed(kvm);
 
 	return 0;
 }
 
-void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
-			    unsigned long end)
+void kvm_mmu_invalidate_end(struct kvm *kvm)
 {
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
 	/*
 	 * This sequence increase will notify the kvm page fault that
 	 * the page that is going to be mapped in the spte could have
@@ -827,18 +863,24 @@ void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
 	 * in conjunction with the smp_rmb in mmu_invalidate_retry().
 	 */
 	kvm->mmu_invalidate_in_progress--;
+	KVM_BUG_ON(kvm->mmu_invalidate_in_progress < 0, kvm);
+
+	/*
+	 * Assert that at least one range was added between start() and end().
+	 * Not adding a range isn't fatal, but it is a KVM bug.
+	 */
+	WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA);
 }
 
 static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 					const struct mmu_notifier_range *range)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	const struct kvm_hva_range hva_range = {
+	const struct kvm_mmu_notifier_range hva_range = {
 		.start		= range->start,
 		.end		= range->end,
 		.handler	= (void *)kvm_null_fn,
 		.on_lock	= kvm_mmu_invalidate_end,
-		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= mmu_notifier_range_blockable(range),
 	};
@@ -857,8 +899,6 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 	 */
 	if (wake)
 		rcuwait_wake_up(&kvm->mn_memslots_update_rcuwait);
-
-	BUG_ON(kvm->mmu_invalidate_in_progress < 0);
 }
 
 static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
@@ -932,14 +972,14 @@ static int kvm_init_mmu_notifier(struct kvm *kvm)
 	return mmu_notifier_register(&kvm->mmu_notifier, current->mm);
 }
 
-#else  /* !(CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER) */
+#else  /* !CONFIG_KVM_GENERIC_MMU_NOTIFIER */
 
 static int kvm_init_mmu_notifier(struct kvm *kvm)
 {
 	return 0;
 }
 
-#endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */
+#endif /* CONFIG_KVM_GENERIC_MMU_NOTIFIER */
 
 #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
 static int kvm_pm_notifier_call(struct notifier_block *bl,
@@ -985,6 +1025,9 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
 /* This does not remove the slot from struct kvm_memslots data structures */
 static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
 {
+	if (slot->flags & KVM_MEM_GUEST_MEMFD)
+		kvm_gmem_unbind(slot);
+
 	kvm_destroy_dirty_bitmap(slot);
 
 	kvm_arch_free_memslot(kvm, slot);
@@ -1166,6 +1209,9 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	spin_lock_init(&kvm->mn_invalidate_lock);
 	rcuwait_init(&kvm->mn_memslots_update_rcuwait);
 	xa_init(&kvm->vcpu_array);
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	xa_init(&kvm->mem_attr_array);
+#endif
 
 	INIT_LIST_HEAD(&kvm->gpc_list);
 	spin_lock_init(&kvm->gpc_lock);
@@ -1190,7 +1236,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 		goto out_err_no_irq_srcu;
 
 	refcount_set(&kvm->users_count, 1);
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		for (j = 0; j < 2; j++) {
 			slots = &kvm->__memslots[i][j];
 
@@ -1222,7 +1268,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	if (r)
 		goto out_err_no_disable;
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 	INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
 #endif
 
@@ -1256,7 +1302,7 @@ out_err:
 out_err_no_debugfs:
 	kvm_coalesced_mmio_free(kvm);
 out_no_coalesced_mmio:
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 	if (kvm->mmu_notifier.ops)
 		mmu_notifier_unregister(&kvm->mmu_notifier, current->mm);
 #endif
@@ -1315,7 +1361,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 		kvm->buses[i] = NULL;
 	}
 	kvm_coalesced_mmio_free(kvm);
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 	mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);
 	/*
 	 * At this point, pending calls to invalidate_range_start()
@@ -1324,20 +1370,30 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	 * No threads can be waiting in kvm_swap_active_memslots() as the
 	 * last reference on KVM has been dropped, but freeing
 	 * memslots would deadlock without this manual intervention.
+	 *
+	 * If the count isn't unbalanced, i.e. KVM did NOT unregister its MMU
+	 * notifier between a start() and end(), then there shouldn't be any
+	 * in-progress invalidations.
 	 */
 	WARN_ON(rcuwait_active(&kvm->mn_memslots_update_rcuwait));
-	kvm->mn_active_invalidate_count = 0;
+	if (kvm->mn_active_invalidate_count)
+		kvm->mn_active_invalidate_count = 0;
+	else
+		WARN_ON(kvm->mmu_invalidate_in_progress);
 #else
 	kvm_flush_shadow_all(kvm);
 #endif
 	kvm_arch_destroy_vm(kvm);
 	kvm_destroy_devices(kvm);
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		kvm_free_memslots(kvm, &kvm->__memslots[i][0]);
 		kvm_free_memslots(kvm, &kvm->__memslots[i][1]);
 	}
 	cleanup_srcu_struct(&kvm->irq_srcu);
 	cleanup_srcu_struct(&kvm->srcu);
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	xa_destroy(&kvm->mem_attr_array);
+#endif
 	kvm_arch_free_vm(kvm);
 	preempt_notifier_dec();
 	hardware_disable_all();
@@ -1538,12 +1594,34 @@ static void kvm_replace_memslot(struct kvm *kvm,
 	}
 }
 
-static int check_memory_region_flags(const struct kvm_userspace_memory_region *mem)
+/*
+ * Flags that do not access any of the extra space of struct
+ * kvm_userspace_memory_region2.  KVM_SET_USER_MEMORY_REGION_V1_FLAGS
+ * only allows these.
+ */
+#define KVM_SET_USER_MEMORY_REGION_V1_FLAGS \
+	(KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_READONLY)
+
+static int check_memory_region_flags(struct kvm *kvm,
+				     const struct kvm_userspace_memory_region2 *mem)
 {
 	u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
 
+	if (kvm_arch_has_private_mem(kvm))
+		valid_flags |= KVM_MEM_GUEST_MEMFD;
+
+	/* Dirty logging private memory is not currently supported. */
+	if (mem->flags & KVM_MEM_GUEST_MEMFD)
+		valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
+
 #ifdef __KVM_HAVE_READONLY_MEM
-	valid_flags |= KVM_MEM_READONLY;
+	/*
+	 * GUEST_MEMFD is incompatible with read-only memslots, as writes to
+	 * read-only memslots have emulated MMIO, not page fault, semantics,
+	 * and KVM doesn't allow emulated MMIO for private memory.
+	 */
+	if (!(mem->flags & KVM_MEM_GUEST_MEMFD))
+		valid_flags |= KVM_MEM_READONLY;
 #endif
 
 	if (mem->flags & ~valid_flags)
@@ -1603,7 +1681,7 @@ static void kvm_swap_active_memslots(struct kvm *kvm, int as_id)
 	 * space 0 will use generations 0, 2, 4, ... while address space 1 will
 	 * use generations 1, 3, 5, ...
 	 */
-	gen += KVM_ADDRESS_SPACE_NUM;
+	gen += kvm_arch_nr_memslot_as_ids(kvm);
 
 	kvm_arch_memslots_updated(kvm, gen);
 
@@ -1940,7 +2018,7 @@ static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id,
  * Must be called holding kvm->slots_lock for write.
  */
 int __kvm_set_memory_region(struct kvm *kvm,
-			    const struct kvm_userspace_memory_region *mem)
+			    const struct kvm_userspace_memory_region2 *mem)
 {
 	struct kvm_memory_slot *old, *new;
 	struct kvm_memslots *slots;
@@ -1950,7 +2028,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	int as_id, id;
 	int r;
 
-	r = check_memory_region_flags(mem);
+	r = check_memory_region_flags(kvm, mem);
 	if (r)
 		return r;
 
@@ -1969,7 +2047,11 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	     !access_ok((void __user *)(unsigned long)mem->userspace_addr,
 			mem->memory_size))
 		return -EINVAL;
-	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM)
+	if (mem->flags & KVM_MEM_GUEST_MEMFD &&
+	    (mem->guest_memfd_offset & (PAGE_SIZE - 1) ||
+	     mem->guest_memfd_offset + mem->memory_size < mem->guest_memfd_offset))
+		return -EINVAL;
+	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_MEM_SLOTS_NUM)
 		return -EINVAL;
 	if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
 		return -EINVAL;
@@ -2007,6 +2089,9 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages)
 			return -EINVAL;
 	} else { /* Modify an existing slot. */
+		/* Private memslots are immutable, they can only be deleted. */
+		if (mem->flags & KVM_MEM_GUEST_MEMFD)
+			return -EINVAL;
 		if ((mem->userspace_addr != old->userspace_addr) ||
 		    (npages != old->npages) ||
 		    ((mem->flags ^ old->flags) & KVM_MEM_READONLY))
@@ -2035,16 +2120,29 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	new->npages = npages;
 	new->flags = mem->flags;
 	new->userspace_addr = mem->userspace_addr;
+	if (mem->flags & KVM_MEM_GUEST_MEMFD) {
+		r = kvm_gmem_bind(kvm, new, mem->guest_memfd, mem->guest_memfd_offset);
+		if (r)
+			goto out;
+	}
 
 	r = kvm_set_memslot(kvm, old, new, change);
 	if (r)
-		kfree(new);
+		goto out_unbind;
+
+	return 0;
+
+out_unbind:
+	if (mem->flags & KVM_MEM_GUEST_MEMFD)
+		kvm_gmem_unbind(new);
+out:
+	kfree(new);
 	return r;
 }
 EXPORT_SYMBOL_GPL(__kvm_set_memory_region);
 
 int kvm_set_memory_region(struct kvm *kvm,
-			  const struct kvm_userspace_memory_region *mem)
+			  const struct kvm_userspace_memory_region2 *mem)
 {
 	int r;
 
@@ -2056,7 +2154,7 @@ int kvm_set_memory_region(struct kvm *kvm,
 EXPORT_SYMBOL_GPL(kvm_set_memory_region);
 
 static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
-					  struct kvm_userspace_memory_region *mem)
+					  struct kvm_userspace_memory_region2 *mem)
 {
 	if ((u16)mem->slot >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
@@ -2089,7 +2187,7 @@ int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log,
 
 	as_id = log->slot >> 16;
 	id = (u16)log->slot;
-	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
 
 	slots = __kvm_memslots(kvm, as_id);
@@ -2151,7 +2249,7 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
 
 	as_id = log->slot >> 16;
 	id = (u16)log->slot;
-	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
 
 	slots = __kvm_memslots(kvm, as_id);
@@ -2263,7 +2361,7 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm,
 
 	as_id = log->slot >> 16;
 	id = (u16)log->slot;
-	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
 
 	if (log->first_page & 63)
@@ -2335,6 +2433,200 @@ static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm,
 }
 #endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */
 
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+/*
+ * Returns true if _all_ gfns in the range [@start, @end) have attributes
+ * matching @attrs.
+ */
+bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
+				     unsigned long attrs)
+{
+	XA_STATE(xas, &kvm->mem_attr_array, start);
+	unsigned long index;
+	bool has_attrs;
+	void *entry;
+
+	rcu_read_lock();
+
+	if (!attrs) {
+		has_attrs = !xas_find(&xas, end - 1);
+		goto out;
+	}
+
+	has_attrs = true;
+	for (index = start; index < end; index++) {
+		do {
+			entry = xas_next(&xas);
+		} while (xas_retry(&xas, entry));
+
+		if (xas.xa_index != index || xa_to_value(entry) != attrs) {
+			has_attrs = false;
+			break;
+		}
+	}
+
+out:
+	rcu_read_unlock();
+	return has_attrs;
+}
+
+static u64 kvm_supported_mem_attributes(struct kvm *kvm)
+{
+	if (!kvm || kvm_arch_has_private_mem(kvm))
+		return KVM_MEMORY_ATTRIBUTE_PRIVATE;
+
+	return 0;
+}
+
+static __always_inline void kvm_handle_gfn_range(struct kvm *kvm,
+						 struct kvm_mmu_notifier_range *range)
+{
+	struct kvm_gfn_range gfn_range;
+	struct kvm_memory_slot *slot;
+	struct kvm_memslots *slots;
+	struct kvm_memslot_iter iter;
+	bool found_memslot = false;
+	bool ret = false;
+	int i;
+
+	gfn_range.arg = range->arg;
+	gfn_range.may_block = range->may_block;
+
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
+		slots = __kvm_memslots(kvm, i);
+
+		kvm_for_each_memslot_in_gfn_range(&iter, slots, range->start, range->end) {
+			slot = iter.slot;
+			gfn_range.slot = slot;
+
+			gfn_range.start = max(range->start, slot->base_gfn);
+			gfn_range.end = min(range->end, slot->base_gfn + slot->npages);
+			if (gfn_range.start >= gfn_range.end)
+				continue;
+
+			if (!found_memslot) {
+				found_memslot = true;
+				KVM_MMU_LOCK(kvm);
+				if (!IS_KVM_NULL_FN(range->on_lock))
+					range->on_lock(kvm);
+			}
+
+			ret |= range->handler(kvm, &gfn_range);
+		}
+	}
+
+	if (range->flush_on_ret && ret)
+		kvm_flush_remote_tlbs(kvm);
+
+	if (found_memslot)
+		KVM_MMU_UNLOCK(kvm);
+}
+
+static bool kvm_pre_set_memory_attributes(struct kvm *kvm,
+					  struct kvm_gfn_range *range)
+{
+	/*
+	 * Unconditionally add the range to the invalidation set, regardless of
+	 * whether or not the arch callback actually needs to zap SPTEs.  E.g.
+	 * if KVM supports RWX attributes in the future and the attributes are
+	 * going from R=>RW, zapping isn't strictly necessary.  Unconditionally
+	 * adding the range allows KVM to require that MMU invalidations add at
+	 * least one range between begin() and end(), e.g. allows KVM to detect
+	 * bugs where the add() is missed.  Relaxing the rule *might* be safe,
+	 * but it's not obvious that allowing new mappings while the attributes
+	 * are in flux is desirable or worth the complexity.
+	 */
+	kvm_mmu_invalidate_range_add(kvm, range->start, range->end);
+
+	return kvm_arch_pre_set_memory_attributes(kvm, range);
+}
+
+/* Set @attributes for the gfn range [@start, @end). */
+static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
+				     unsigned long attributes)
+{
+	struct kvm_mmu_notifier_range pre_set_range = {
+		.start = start,
+		.end = end,
+		.handler = kvm_pre_set_memory_attributes,
+		.on_lock = kvm_mmu_invalidate_begin,
+		.flush_on_ret = true,
+		.may_block = true,
+	};
+	struct kvm_mmu_notifier_range post_set_range = {
+		.start = start,
+		.end = end,
+		.arg.attributes = attributes,
+		.handler = kvm_arch_post_set_memory_attributes,
+		.on_lock = kvm_mmu_invalidate_end,
+		.may_block = true,
+	};
+	unsigned long i;
+	void *entry;
+	int r = 0;
+
+	entry = attributes ? xa_mk_value(attributes) : NULL;
+
+	mutex_lock(&kvm->slots_lock);
+
+	/* Nothing to do if the entire range as the desired attributes. */
+	if (kvm_range_has_memory_attributes(kvm, start, end, attributes))
+		goto out_unlock;
+
+	/*
+	 * Reserve memory ahead of time to avoid having to deal with failures
+	 * partway through setting the new attributes.
+	 */
+	for (i = start; i < end; i++) {
+		r = xa_reserve(&kvm->mem_attr_array, i, GFP_KERNEL_ACCOUNT);
+		if (r)
+			goto out_unlock;
+	}
+
+	kvm_handle_gfn_range(kvm, &pre_set_range);
+
+	for (i = start; i < end; i++) {
+		r = xa_err(xa_store(&kvm->mem_attr_array, i, entry,
+				    GFP_KERNEL_ACCOUNT));
+		KVM_BUG_ON(r, kvm);
+	}
+
+	kvm_handle_gfn_range(kvm, &post_set_range);
+
+out_unlock:
+	mutex_unlock(&kvm->slots_lock);
+
+	return r;
+}
+static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm,
+					   struct kvm_memory_attributes *attrs)
+{
+	gfn_t start, end;
+
+	/* flags is currently not used. */
+	if (attrs->flags)
+		return -EINVAL;
+	if (attrs->attributes & ~kvm_supported_mem_attributes(kvm))
+		return -EINVAL;
+	if (attrs->size == 0 || attrs->address + attrs->size < attrs->address)
+		return -EINVAL;
+	if (!PAGE_ALIGNED(attrs->address) || !PAGE_ALIGNED(attrs->size))
+		return -EINVAL;
+
+	start = attrs->address >> PAGE_SHIFT;
+	end = (attrs->address + attrs->size) >> PAGE_SHIFT;
+
+	/*
+	 * xarray tracks data using "unsigned long", and as a result so does
+	 * KVM.  For simplicity, supports generic attributes only on 64-bit
+	 * architectures.
+	 */
+	BUILD_BUG_ON(sizeof(attrs->attributes) != sizeof(unsigned long));
+
+	return kvm_vm_set_mem_attributes(kvm, start, end, attrs->attributes);
+}
+#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
+
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
 {
 	return __gfn_to_memslot(kvm_memslots(kvm), gfn);
@@ -4527,13 +4819,14 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 {
 	switch (arg) {
 	case KVM_CAP_USER_MEMORY:
+	case KVM_CAP_USER_MEMORY2:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
 	case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS:
 	case KVM_CAP_INTERNAL_ERROR_DATA:
 #ifdef CONFIG_HAVE_KVM_MSI
 	case KVM_CAP_SIGNAL_MSI:
 #endif
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 	case KVM_CAP_IRQFD:
 #endif
 	case KVM_CAP_IOEVENTFD_ANY_LENGTH:
@@ -4555,9 +4848,11 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 	case KVM_CAP_IRQ_ROUTING:
 		return KVM_MAX_IRQ_ROUTES;
 #endif
-#if KVM_ADDRESS_SPACE_NUM > 1
+#if KVM_MAX_NR_ADDRESS_SPACES > 1
 	case KVM_CAP_MULTI_ADDRESS_SPACE:
-		return KVM_ADDRESS_SPACE_NUM;
+		if (kvm)
+			return kvm_arch_nr_memslot_as_ids(kvm);
+		return KVM_MAX_NR_ADDRESS_SPACES;
 #endif
 	case KVM_CAP_NR_MEMSLOTS:
 		return KVM_USER_MEM_SLOTS;
@@ -4578,7 +4873,16 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 #endif
 	case KVM_CAP_BINARY_STATS_FD:
 	case KVM_CAP_SYSTEM_EVENT_DATA:
+	case KVM_CAP_DEVICE_CTRL:
 		return 1;
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	case KVM_CAP_MEMORY_ATTRIBUTES:
+		return kvm_supported_mem_attributes(kvm);
+#endif
+#ifdef CONFIG_KVM_PRIVATE_MEM
+	case KVM_CAP_GUEST_MEMFD:
+		return !kvm || kvm_arch_has_private_mem(kvm);
+#endif
 	default:
 		break;
 	}
@@ -4657,7 +4961,7 @@ bool kvm_are_all_memslots_empty(struct kvm *kvm)
 
 	lockdep_assert_held(&kvm->slots_lock);
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		if (!kvm_memslots_empty(__kvm_memslots(kvm, i)))
 			return false;
 	}
@@ -4783,6 +5087,14 @@ static int kvm_vm_ioctl_get_stats_fd(struct kvm *kvm)
 	return fd;
 }
 
+#define SANITY_CHECK_MEM_REGION_FIELD(field)					\
+do {										\
+	BUILD_BUG_ON(offsetof(struct kvm_userspace_memory_region, field) !=		\
+		     offsetof(struct kvm_userspace_memory_region2, field));	\
+	BUILD_BUG_ON(sizeof_field(struct kvm_userspace_memory_region, field) !=		\
+		     sizeof_field(struct kvm_userspace_memory_region2, field));	\
+} while (0)
+
 static long kvm_vm_ioctl(struct file *filp,
 			   unsigned int ioctl, unsigned long arg)
 {
@@ -4805,15 +5117,39 @@ static long kvm_vm_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_enable_cap_generic(kvm, &cap);
 		break;
 	}
+	case KVM_SET_USER_MEMORY_REGION2:
 	case KVM_SET_USER_MEMORY_REGION: {
-		struct kvm_userspace_memory_region kvm_userspace_mem;
+		struct kvm_userspace_memory_region2 mem;
+		unsigned long size;
+
+		if (ioctl == KVM_SET_USER_MEMORY_REGION) {
+			/*
+			 * Fields beyond struct kvm_userspace_memory_region shouldn't be
+			 * accessed, but avoid leaking kernel memory in case of a bug.
+			 */
+			memset(&mem, 0, sizeof(mem));
+			size = sizeof(struct kvm_userspace_memory_region);
+		} else {
+			size = sizeof(struct kvm_userspace_memory_region2);
+		}
+
+		/* Ensure the common parts of the two structs are identical. */
+		SANITY_CHECK_MEM_REGION_FIELD(slot);
+		SANITY_CHECK_MEM_REGION_FIELD(flags);
+		SANITY_CHECK_MEM_REGION_FIELD(guest_phys_addr);
+		SANITY_CHECK_MEM_REGION_FIELD(memory_size);
+		SANITY_CHECK_MEM_REGION_FIELD(userspace_addr);
 
 		r = -EFAULT;
-		if (copy_from_user(&kvm_userspace_mem, argp,
-						sizeof(kvm_userspace_mem)))
+		if (copy_from_user(&mem, argp, size))
 			goto out;
 
-		r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem);
+		r = -EINVAL;
+		if (ioctl == KVM_SET_USER_MEMORY_REGION &&
+		    (mem.flags & ~KVM_SET_USER_MEMORY_REGION_V1_FLAGS))
+			goto out;
+
+		r = kvm_vm_ioctl_set_memory_region(kvm, &mem);
 		break;
 	}
 	case KVM_GET_DIRTY_LOG: {
@@ -4927,9 +5263,8 @@ static long kvm_vm_ioctl(struct file *filp,
 			goto out;
 		if (routing.nr) {
 			urouting = argp;
-			entries = vmemdup_user(urouting->entries,
-					       array_size(sizeof(*entries),
-							  routing.nr));
+			entries = vmemdup_array_user(urouting->entries,
+						     routing.nr, sizeof(*entries));
 			if (IS_ERR(entries)) {
 				r = PTR_ERR(entries);
 				goto out;
@@ -4941,6 +5276,18 @@ static long kvm_vm_ioctl(struct file *filp,
 		break;
 	}
 #endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	case KVM_SET_MEMORY_ATTRIBUTES: {
+		struct kvm_memory_attributes attrs;
+
+		r = -EFAULT;
+		if (copy_from_user(&attrs, argp, sizeof(attrs)))
+			goto out;
+
+		r = kvm_vm_ioctl_set_mem_attributes(kvm, &attrs);
+		break;
+	}
+#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
 	case KVM_CREATE_DEVICE: {
 		struct kvm_create_device cd;
 
@@ -4968,6 +5315,18 @@ static long kvm_vm_ioctl(struct file *filp,
 	case KVM_GET_STATS_FD:
 		r = kvm_vm_ioctl_get_stats_fd(kvm);
 		break;
+#ifdef CONFIG_KVM_PRIVATE_MEM
+	case KVM_CREATE_GUEST_MEMFD: {
+		struct kvm_create_guest_memfd guest_memfd;
+
+		r = -EFAULT;
+		if (copy_from_user(&guest_memfd, argp, sizeof(guest_memfd)))
+			goto out;
+
+		r = kvm_gmem_create(kvm, &guest_memfd);
+		break;
+	}
+#endif
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 	}
@@ -5139,11 +5498,6 @@ static long kvm_dev_ioctl(struct file *filp,
 		r += PAGE_SIZE;    /* coalesced mmio ring page */
 #endif
 		break;
-	case KVM_TRACE_ENABLE:
-	case KVM_TRACE_PAUSE:
-	case KVM_TRACE_DISABLE:
-		r = -EOPNOTSUPP;
-		break;
 	default:
 		return kvm_arch_dev_ioctl(filp, ioctl, arg);
 	}
@@ -6104,6 +6458,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module)
 	if (WARN_ON_ONCE(r))
 		goto err_vfio;
 
+	kvm_gmem_init(module);
+
 	/*
 	 * Registration _must_ be the very last thing done, as this exposes
 	 * /dev/kvm to userspace, i.e. all infrastructure must be setup!
diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h
index 180f1a09e6ba..ecefc7ec51af 100644
--- a/virt/kvm/kvm_mm.h
+++ b/virt/kvm/kvm_mm.h
@@ -37,4 +37,30 @@ static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm,
 }
 #endif /* HAVE_KVM_PFNCACHE */
 
+#ifdef CONFIG_KVM_PRIVATE_MEM
+void kvm_gmem_init(struct module *module);
+int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args);
+int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
+		  unsigned int fd, loff_t offset);
+void kvm_gmem_unbind(struct kvm_memory_slot *slot);
+#else
+static inline void kvm_gmem_init(struct module *module)
+{
+
+}
+
+static inline int kvm_gmem_bind(struct kvm *kvm,
+					 struct kvm_memory_slot *slot,
+					 unsigned int fd, loff_t offset)
+{
+	WARN_ON_ONCE(1);
+	return -EIO;
+}
+
+static inline void kvm_gmem_unbind(struct kvm_memory_slot *slot)
+{
+	WARN_ON_ONCE(1);
+}
+#endif /* CONFIG_KVM_PRIVATE_MEM */
+
 #endif /* __KVM_MM_H__ */